{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 65106,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 0.6326836347579956,
      "eval_runtime": 164.9174,
      "eval_samples_per_second": 145.521,
      "eval_steps_per_second": 18.191,
      "step": 0
    },
    {
      "epoch": 3.0719134949159833e-05,
      "grad_norm": 2.2060632705688477,
      "learning_rate": 0.0,
      "loss": 0.8824,
      "step": 1
    },
    {
      "epoch": 6.143826989831967e-05,
      "grad_norm": 1.6191656589508057,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.7731,
      "step": 2
    },
    {
      "epoch": 9.21574048474795e-05,
      "grad_norm": 1.736921787261963,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 0.8734,
      "step": 3
    },
    {
      "epoch": 0.00012287653979663933,
      "grad_norm": 1.4968067407608032,
      "learning_rate": 6.000000000000001e-07,
      "loss": 0.7427,
      "step": 4
    },
    {
      "epoch": 0.00015359567474579916,
      "grad_norm": 1.4621388912200928,
      "learning_rate": 8.000000000000001e-07,
      "loss": 0.77,
      "step": 5
    },
    {
      "epoch": 0.000184314809694959,
      "grad_norm": 1.5482256412506104,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.8165,
      "step": 6
    },
    {
      "epoch": 0.0002150339446441188,
      "grad_norm": 1.5582091808319092,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 0.819,
      "step": 7
    },
    {
      "epoch": 0.00024575307959327867,
      "grad_norm": 1.513546347618103,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.8363,
      "step": 8
    },
    {
      "epoch": 0.0002764722145424385,
      "grad_norm": 1.4339336156845093,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.8125,
      "step": 9
    },
    {
      "epoch": 0.0003071913494915983,
      "grad_norm": 1.2125071287155151,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.7789,
      "step": 10
    },
    {
      "epoch": 0.00033791048444075815,
      "grad_norm": 1.23660147190094,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7282,
      "step": 11
    },
    {
      "epoch": 0.000368629619389918,
      "grad_norm": 1.056510329246521,
      "learning_rate": 2.2e-06,
      "loss": 0.7939,
      "step": 12
    },
    {
      "epoch": 0.0003993487543390778,
      "grad_norm": 0.9758861064910889,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.8209,
      "step": 13
    },
    {
      "epoch": 0.0004300678892882376,
      "grad_norm": 0.7711737751960754,
      "learning_rate": 2.6e-06,
      "loss": 0.7855,
      "step": 14
    },
    {
      "epoch": 0.00046078702423739745,
      "grad_norm": 0.7413145303726196,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.8504,
      "step": 15
    },
    {
      "epoch": 0.0004915061591865573,
      "grad_norm": 0.5642073750495911,
      "learning_rate": 3e-06,
      "loss": 0.7012,
      "step": 16
    },
    {
      "epoch": 0.0005222252941357172,
      "grad_norm": 0.53790283203125,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.7729,
      "step": 17
    },
    {
      "epoch": 0.000552944429084877,
      "grad_norm": 0.5495612621307373,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.7109,
      "step": 18
    },
    {
      "epoch": 0.0005836635640340368,
      "grad_norm": 0.6268466711044312,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.7447,
      "step": 19
    },
    {
      "epoch": 0.0006143826989831966,
      "grad_norm": 0.6037240624427795,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.7352,
      "step": 20
    },
    {
      "epoch": 0.0006451018339323565,
      "grad_norm": 0.6931290626525879,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8001,
      "step": 21
    },
    {
      "epoch": 0.0006758209688815163,
      "grad_norm": 0.7875220775604248,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.7863,
      "step": 22
    },
    {
      "epoch": 0.0007065401038306761,
      "grad_norm": 0.6257062554359436,
      "learning_rate": 4.4e-06,
      "loss": 0.653,
      "step": 23
    },
    {
      "epoch": 0.000737259238779836,
      "grad_norm": 0.6351224780082703,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.7564,
      "step": 24
    },
    {
      "epoch": 0.0007679783737289958,
      "grad_norm": 0.6733613014221191,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.7801,
      "step": 25
    },
    {
      "epoch": 0.0007986975086781556,
      "grad_norm": 0.5667824745178223,
      "learning_rate": 5e-06,
      "loss": 0.7634,
      "step": 26
    },
    {
      "epoch": 0.0008294166436273154,
      "grad_norm": 0.6039953231811523,
      "learning_rate": 5.2e-06,
      "loss": 0.7154,
      "step": 27
    },
    {
      "epoch": 0.0008601357785764753,
      "grad_norm": 0.49980399012565613,
      "learning_rate": 5.400000000000001e-06,
      "loss": 0.7394,
      "step": 28
    },
    {
      "epoch": 0.0008908549135256351,
      "grad_norm": 0.5537846088409424,
      "learning_rate": 5.600000000000001e-06,
      "loss": 0.7897,
      "step": 29
    },
    {
      "epoch": 0.0009215740484747949,
      "grad_norm": 0.4041750133037567,
      "learning_rate": 5.8e-06,
      "loss": 0.6538,
      "step": 30
    },
    {
      "epoch": 0.0009522931834239547,
      "grad_norm": 0.4942256808280945,
      "learning_rate": 6e-06,
      "loss": 0.7338,
      "step": 31
    },
    {
      "epoch": 0.0009830123183731147,
      "grad_norm": 0.45916399359703064,
      "learning_rate": 6.200000000000001e-06,
      "loss": 0.733,
      "step": 32
    },
    {
      "epoch": 0.0010137314533222744,
      "grad_norm": 0.47235965728759766,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 0.6785,
      "step": 33
    },
    {
      "epoch": 0.0010444505882714343,
      "grad_norm": 0.426445335149765,
      "learning_rate": 6.600000000000001e-06,
      "loss": 0.6756,
      "step": 34
    },
    {
      "epoch": 0.001075169723220594,
      "grad_norm": 0.41867509484291077,
      "learning_rate": 6.800000000000001e-06,
      "loss": 0.6992,
      "step": 35
    },
    {
      "epoch": 0.001105888858169754,
      "grad_norm": 0.5253549814224243,
      "learning_rate": 7e-06,
      "loss": 0.7337,
      "step": 36
    },
    {
      "epoch": 0.0011366079931189137,
      "grad_norm": 0.5028246641159058,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 0.8443,
      "step": 37
    },
    {
      "epoch": 0.0011673271280680736,
      "grad_norm": 0.5090922117233276,
      "learning_rate": 7.4e-06,
      "loss": 0.7386,
      "step": 38
    },
    {
      "epoch": 0.0011980462630172333,
      "grad_norm": 0.5473935008049011,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.7312,
      "step": 39
    },
    {
      "epoch": 0.0012287653979663933,
      "grad_norm": 0.4583193361759186,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.6579,
      "step": 40
    },
    {
      "epoch": 0.001259484532915553,
      "grad_norm": 0.4007287323474884,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7216,
      "step": 41
    },
    {
      "epoch": 0.001290203667864713,
      "grad_norm": 0.4102514386177063,
      "learning_rate": 8.2e-06,
      "loss": 0.7233,
      "step": 42
    },
    {
      "epoch": 0.0013209228028138727,
      "grad_norm": 0.43275970220565796,
      "learning_rate": 8.400000000000001e-06,
      "loss": 0.6587,
      "step": 43
    },
    {
      "epoch": 0.0013516419377630326,
      "grad_norm": 0.4226611852645874,
      "learning_rate": 8.6e-06,
      "loss": 0.7169,
      "step": 44
    },
    {
      "epoch": 0.0013823610727121925,
      "grad_norm": 0.3732317090034485,
      "learning_rate": 8.8e-06,
      "loss": 0.6469,
      "step": 45
    },
    {
      "epoch": 0.0014130802076613522,
      "grad_norm": 0.38714149594306946,
      "learning_rate": 9e-06,
      "loss": 0.7462,
      "step": 46
    },
    {
      "epoch": 0.0014437993426105122,
      "grad_norm": 0.4405876398086548,
      "learning_rate": 9.200000000000002e-06,
      "loss": 0.6285,
      "step": 47
    },
    {
      "epoch": 0.001474518477559672,
      "grad_norm": 0.4298103153705597,
      "learning_rate": 9.4e-06,
      "loss": 0.6269,
      "step": 48
    },
    {
      "epoch": 0.0015052376125088318,
      "grad_norm": 0.42390310764312744,
      "learning_rate": 9.600000000000001e-06,
      "loss": 0.6781,
      "step": 49
    },
    {
      "epoch": 0.0015359567474579915,
      "grad_norm": 0.7648850679397583,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.6272,
      "step": 50
    },
    {
      "epoch": 0.0015666758824071515,
      "grad_norm": 0.7110830545425415,
      "learning_rate": 1e-05,
      "loss": 0.6519,
      "step": 51
    },
    {
      "epoch": 0.0015973950173563112,
      "grad_norm": 0.4206750988960266,
      "learning_rate": 1.02e-05,
      "loss": 0.7422,
      "step": 52
    },
    {
      "epoch": 0.0016281141523054711,
      "grad_norm": 0.40987375378608704,
      "learning_rate": 1.04e-05,
      "loss": 0.7703,
      "step": 53
    },
    {
      "epoch": 0.0016588332872546309,
      "grad_norm": 0.3642449975013733,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 0.7055,
      "step": 54
    },
    {
      "epoch": 0.0016895524222037908,
      "grad_norm": 0.4124760329723358,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 0.701,
      "step": 55
    },
    {
      "epoch": 0.0017202715571529505,
      "grad_norm": 0.43547341227531433,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7221,
      "step": 56
    },
    {
      "epoch": 0.0017509906921021104,
      "grad_norm": 0.40725192427635193,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.6446,
      "step": 57
    },
    {
      "epoch": 0.0017817098270512702,
      "grad_norm": 0.47742313146591187,
      "learning_rate": 1.14e-05,
      "loss": 0.7022,
      "step": 58
    },
    {
      "epoch": 0.00181242896200043,
      "grad_norm": 0.4527803659439087,
      "learning_rate": 1.16e-05,
      "loss": 0.7304,
      "step": 59
    },
    {
      "epoch": 0.0018431480969495898,
      "grad_norm": 0.3985797166824341,
      "learning_rate": 1.18e-05,
      "loss": 0.7555,
      "step": 60
    },
    {
      "epoch": 0.0018738672318987497,
      "grad_norm": 0.40599048137664795,
      "learning_rate": 1.2e-05,
      "loss": 0.6678,
      "step": 61
    },
    {
      "epoch": 0.0019045863668479095,
      "grad_norm": 0.46422773599624634,
      "learning_rate": 1.22e-05,
      "loss": 0.7375,
      "step": 62
    },
    {
      "epoch": 0.0019353055017970694,
      "grad_norm": 0.41334936022758484,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 0.6874,
      "step": 63
    },
    {
      "epoch": 0.0019660246367462293,
      "grad_norm": 0.40186694264411926,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 0.659,
      "step": 64
    },
    {
      "epoch": 0.001996743771695389,
      "grad_norm": 0.41983962059020996,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.6874,
      "step": 65
    },
    {
      "epoch": 0.0020274629066445488,
      "grad_norm": 0.41536056995391846,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.6925,
      "step": 66
    },
    {
      "epoch": 0.002058182041593709,
      "grad_norm": 0.431587278842926,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 0.7492,
      "step": 67
    },
    {
      "epoch": 0.0020889011765428686,
      "grad_norm": 0.41855955123901367,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 0.6918,
      "step": 68
    },
    {
      "epoch": 0.0021196203114920284,
      "grad_norm": 0.4394783079624176,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 0.7476,
      "step": 69
    },
    {
      "epoch": 0.002150339446441188,
      "grad_norm": 0.4353363811969757,
      "learning_rate": 1.38e-05,
      "loss": 0.7128,
      "step": 70
    },
    {
      "epoch": 0.0021810585813903482,
      "grad_norm": 0.40552258491516113,
      "learning_rate": 1.4e-05,
      "loss": 0.6977,
      "step": 71
    },
    {
      "epoch": 0.002211777716339508,
      "grad_norm": 0.388932466506958,
      "learning_rate": 1.4200000000000001e-05,
      "loss": 0.6838,
      "step": 72
    },
    {
      "epoch": 0.0022424968512886677,
      "grad_norm": 0.44696030020713806,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.7916,
      "step": 73
    },
    {
      "epoch": 0.0022732159862378274,
      "grad_norm": 0.3827476501464844,
      "learning_rate": 1.46e-05,
      "loss": 0.7288,
      "step": 74
    },
    {
      "epoch": 0.0023039351211869875,
      "grad_norm": 0.4317185580730438,
      "learning_rate": 1.48e-05,
      "loss": 0.6822,
      "step": 75
    },
    {
      "epoch": 0.0023346542561361473,
      "grad_norm": 0.4701237380504608,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7314,
      "step": 76
    },
    {
      "epoch": 0.002365373391085307,
      "grad_norm": 0.4364073574542999,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.6788,
      "step": 77
    },
    {
      "epoch": 0.0023960925260344667,
      "grad_norm": 0.40740522742271423,
      "learning_rate": 1.54e-05,
      "loss": 0.7423,
      "step": 78
    },
    {
      "epoch": 0.002426811660983627,
      "grad_norm": 0.561620831489563,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.6379,
      "step": 79
    },
    {
      "epoch": 0.0024575307959327866,
      "grad_norm": 0.41717392206192017,
      "learning_rate": 1.58e-05,
      "loss": 0.6998,
      "step": 80
    },
    {
      "epoch": 0.0024882499308819463,
      "grad_norm": 0.39351895451545715,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7005,
      "step": 81
    },
    {
      "epoch": 0.002518969065831106,
      "grad_norm": 0.45525091886520386,
      "learning_rate": 1.62e-05,
      "loss": 0.669,
      "step": 82
    },
    {
      "epoch": 0.002549688200780266,
      "grad_norm": 0.49478185176849365,
      "learning_rate": 1.64e-05,
      "loss": 0.7142,
      "step": 83
    },
    {
      "epoch": 0.002580407335729426,
      "grad_norm": 0.3819921314716339,
      "learning_rate": 1.66e-05,
      "loss": 0.6877,
      "step": 84
    },
    {
      "epoch": 0.0026111264706785856,
      "grad_norm": 0.6958513855934143,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.695,
      "step": 85
    },
    {
      "epoch": 0.0026418456056277453,
      "grad_norm": 0.4809763431549072,
      "learning_rate": 1.7e-05,
      "loss": 0.6389,
      "step": 86
    },
    {
      "epoch": 0.0026725647405769055,
      "grad_norm": 0.5927045941352844,
      "learning_rate": 1.72e-05,
      "loss": 0.6551,
      "step": 87
    },
    {
      "epoch": 0.002703283875526065,
      "grad_norm": 0.6305676698684692,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 0.6817,
      "step": 88
    },
    {
      "epoch": 0.002734003010475225,
      "grad_norm": 2.6431007385253906,
      "learning_rate": 1.76e-05,
      "loss": 0.5582,
      "step": 89
    },
    {
      "epoch": 0.002764722145424385,
      "grad_norm": 0.4043395221233368,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 0.6677,
      "step": 90
    },
    {
      "epoch": 0.0027954412803735448,
      "grad_norm": 0.49771586060523987,
      "learning_rate": 1.8e-05,
      "loss": 0.7156,
      "step": 91
    },
    {
      "epoch": 0.0028261604153227045,
      "grad_norm": 0.43804931640625,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 0.6696,
      "step": 92
    },
    {
      "epoch": 0.002856879550271864,
      "grad_norm": 0.39800825715065,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.7048,
      "step": 93
    },
    {
      "epoch": 0.0028875986852210244,
      "grad_norm": 0.40523940324783325,
      "learning_rate": 1.86e-05,
      "loss": 0.6458,
      "step": 94
    },
    {
      "epoch": 0.002918317820170184,
      "grad_norm": 0.3812132477760315,
      "learning_rate": 1.88e-05,
      "loss": 0.6346,
      "step": 95
    },
    {
      "epoch": 0.002949036955119344,
      "grad_norm": 0.4807397425174713,
      "learning_rate": 1.9e-05,
      "loss": 0.7656,
      "step": 96
    },
    {
      "epoch": 0.0029797560900685035,
      "grad_norm": 0.4357774257659912,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.6349,
      "step": 97
    },
    {
      "epoch": 0.0030104752250176637,
      "grad_norm": 0.45396918058395386,
      "learning_rate": 1.94e-05,
      "loss": 0.7982,
      "step": 98
    },
    {
      "epoch": 0.0030411943599668234,
      "grad_norm": 0.461595356464386,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.709,
      "step": 99
    },
    {
      "epoch": 0.003071913494915983,
      "grad_norm": 0.4501061737537384,
      "learning_rate": 1.98e-05,
      "loss": 0.7047,
      "step": 100
    },
    {
      "epoch": 0.003102632629865143,
      "grad_norm": 0.3854588568210602,
      "learning_rate": 2e-05,
      "loss": 0.6107,
      "step": 101
    },
    {
      "epoch": 0.003133351764814303,
      "grad_norm": 0.5553824305534363,
      "learning_rate": 1.999999998832215e-05,
      "loss": 0.7218,
      "step": 102
    },
    {
      "epoch": 0.0031640708997634627,
      "grad_norm": 0.4018421769142151,
      "learning_rate": 1.9999999953288605e-05,
      "loss": 0.5644,
      "step": 103
    },
    {
      "epoch": 0.0031947900347126224,
      "grad_norm": 0.39340701699256897,
      "learning_rate": 1.9999999894899357e-05,
      "loss": 0.6485,
      "step": 104
    },
    {
      "epoch": 0.003225509169661782,
      "grad_norm": 0.6755144596099854,
      "learning_rate": 1.9999999813154413e-05,
      "loss": 0.7112,
      "step": 105
    },
    {
      "epoch": 0.0032562283046109423,
      "grad_norm": 0.591421902179718,
      "learning_rate": 1.9999999708053776e-05,
      "loss": 0.7892,
      "step": 106
    },
    {
      "epoch": 0.003286947439560102,
      "grad_norm": 0.45002928376197815,
      "learning_rate": 1.9999999579597435e-05,
      "loss": 0.6684,
      "step": 107
    },
    {
      "epoch": 0.0033176665745092617,
      "grad_norm": 0.6268222332000732,
      "learning_rate": 1.9999999427785397e-05,
      "loss": 0.657,
      "step": 108
    },
    {
      "epoch": 0.003348385709458422,
      "grad_norm": 0.7430928945541382,
      "learning_rate": 1.9999999252617665e-05,
      "loss": 0.7015,
      "step": 109
    },
    {
      "epoch": 0.0033791048444075816,
      "grad_norm": 1.0364269018173218,
      "learning_rate": 1.999999905409423e-05,
      "loss": 0.7512,
      "step": 110
    },
    {
      "epoch": 0.0034098239793567413,
      "grad_norm": 0.43804025650024414,
      "learning_rate": 1.9999998832215105e-05,
      "loss": 0.6397,
      "step": 111
    },
    {
      "epoch": 0.003440543114305901,
      "grad_norm": 0.4407244920730591,
      "learning_rate": 1.9999998586980283e-05,
      "loss": 0.6981,
      "step": 112
    },
    {
      "epoch": 0.003471262249255061,
      "grad_norm": 0.43327078223228455,
      "learning_rate": 1.9999998318389764e-05,
      "loss": 0.6826,
      "step": 113
    },
    {
      "epoch": 0.003501981384204221,
      "grad_norm": 0.42031970620155334,
      "learning_rate": 1.999999802644355e-05,
      "loss": 0.7271,
      "step": 114
    },
    {
      "epoch": 0.0035327005191533806,
      "grad_norm": 0.4113335609436035,
      "learning_rate": 1.9999997711141646e-05,
      "loss": 0.6303,
      "step": 115
    },
    {
      "epoch": 0.0035634196541025403,
      "grad_norm": 0.4468602240085602,
      "learning_rate": 1.9999997372484046e-05,
      "loss": 0.6167,
      "step": 116
    },
    {
      "epoch": 0.0035941387890517005,
      "grad_norm": 0.45326897501945496,
      "learning_rate": 1.9999997010470754e-05,
      "loss": 0.6268,
      "step": 117
    },
    {
      "epoch": 0.00362485792400086,
      "grad_norm": 0.40296611189842224,
      "learning_rate": 1.9999996625101774e-05,
      "loss": 0.6144,
      "step": 118
    },
    {
      "epoch": 0.00365557705895002,
      "grad_norm": 0.43666744232177734,
      "learning_rate": 1.99999962163771e-05,
      "loss": 0.659,
      "step": 119
    },
    {
      "epoch": 0.0036862961938991796,
      "grad_norm": 0.4473617374897003,
      "learning_rate": 1.999999578429674e-05,
      "loss": 0.7029,
      "step": 120
    },
    {
      "epoch": 0.0037170153288483398,
      "grad_norm": 0.41308149695396423,
      "learning_rate": 1.9999995328860685e-05,
      "loss": 0.6833,
      "step": 121
    },
    {
      "epoch": 0.0037477344637974995,
      "grad_norm": 0.4639977514743805,
      "learning_rate": 1.9999994850068946e-05,
      "loss": 0.7144,
      "step": 122
    },
    {
      "epoch": 0.0037784535987466592,
      "grad_norm": 0.43590787053108215,
      "learning_rate": 1.999999434792152e-05,
      "loss": 0.7556,
      "step": 123
    },
    {
      "epoch": 0.003809172733695819,
      "grad_norm": 0.4142620265483856,
      "learning_rate": 1.9999993822418413e-05,
      "loss": 0.6164,
      "step": 124
    },
    {
      "epoch": 0.003839891868644979,
      "grad_norm": 0.43738052248954773,
      "learning_rate": 1.999999327355962e-05,
      "loss": 0.7166,
      "step": 125
    },
    {
      "epoch": 0.003870611003594139,
      "grad_norm": 0.6542159914970398,
      "learning_rate": 1.999999270134514e-05,
      "loss": 0.7099,
      "step": 126
    },
    {
      "epoch": 0.0039013301385432985,
      "grad_norm": 0.4329463839530945,
      "learning_rate": 1.999999210577498e-05,
      "loss": 0.648,
      "step": 127
    },
    {
      "epoch": 0.003932049273492459,
      "grad_norm": 0.45176026225090027,
      "learning_rate": 1.9999991486849144e-05,
      "loss": 0.7054,
      "step": 128
    },
    {
      "epoch": 0.003962768408441618,
      "grad_norm": 0.4022347629070282,
      "learning_rate": 1.9999990844567628e-05,
      "loss": 0.6461,
      "step": 129
    },
    {
      "epoch": 0.003993487543390778,
      "grad_norm": 0.537884533405304,
      "learning_rate": 1.9999990178930432e-05,
      "loss": 0.6664,
      "step": 130
    },
    {
      "epoch": 0.004024206678339938,
      "grad_norm": 0.39311736822128296,
      "learning_rate": 1.9999989489937563e-05,
      "loss": 0.6682,
      "step": 131
    },
    {
      "epoch": 0.0040549258132890975,
      "grad_norm": 0.42505621910095215,
      "learning_rate": 1.999998877758902e-05,
      "loss": 0.7108,
      "step": 132
    },
    {
      "epoch": 0.004085644948238257,
      "grad_norm": 0.5580906867980957,
      "learning_rate": 1.9999988041884806e-05,
      "loss": 0.7079,
      "step": 133
    },
    {
      "epoch": 0.004116364083187418,
      "grad_norm": 0.4688013195991516,
      "learning_rate": 1.999998728282492e-05,
      "loss": 0.6672,
      "step": 134
    },
    {
      "epoch": 0.004147083218136578,
      "grad_norm": 0.42082464694976807,
      "learning_rate": 1.9999986500409366e-05,
      "loss": 0.6729,
      "step": 135
    },
    {
      "epoch": 0.004177802353085737,
      "grad_norm": 0.38066428899765015,
      "learning_rate": 1.9999985694638144e-05,
      "loss": 0.667,
      "step": 136
    },
    {
      "epoch": 0.004208521488034897,
      "grad_norm": 0.4260127544403076,
      "learning_rate": 1.999998486551126e-05,
      "loss": 0.7275,
      "step": 137
    },
    {
      "epoch": 0.004239240622984057,
      "grad_norm": 0.4907187521457672,
      "learning_rate": 1.999998401302871e-05,
      "loss": 0.7384,
      "step": 138
    },
    {
      "epoch": 0.0042699597579332164,
      "grad_norm": 1.410542607307434,
      "learning_rate": 1.9999983137190496e-05,
      "loss": 0.7092,
      "step": 139
    },
    {
      "epoch": 0.004300678892882376,
      "grad_norm": 0.43692833185195923,
      "learning_rate": 1.999998223799663e-05,
      "loss": 0.6813,
      "step": 140
    },
    {
      "epoch": 0.004331398027831536,
      "grad_norm": 0.36459484696388245,
      "learning_rate": 1.9999981315447104e-05,
      "loss": 0.6672,
      "step": 141
    },
    {
      "epoch": 0.0043621171627806965,
      "grad_norm": 0.4163941442966461,
      "learning_rate": 1.9999980369541922e-05,
      "loss": 0.6917,
      "step": 142
    },
    {
      "epoch": 0.004392836297729856,
      "grad_norm": 0.4046642482280731,
      "learning_rate": 1.999997940028109e-05,
      "loss": 0.6789,
      "step": 143
    },
    {
      "epoch": 0.004423555432679016,
      "grad_norm": 0.5259842872619629,
      "learning_rate": 1.9999978407664606e-05,
      "loss": 0.6927,
      "step": 144
    },
    {
      "epoch": 0.004454274567628176,
      "grad_norm": 0.4637850821018219,
      "learning_rate": 1.9999977391692472e-05,
      "loss": 0.7026,
      "step": 145
    },
    {
      "epoch": 0.004484993702577335,
      "grad_norm": 0.3918446898460388,
      "learning_rate": 1.9999976352364692e-05,
      "loss": 0.6085,
      "step": 146
    },
    {
      "epoch": 0.004515712837526495,
      "grad_norm": 0.36016353964805603,
      "learning_rate": 1.9999975289681273e-05,
      "loss": 0.6761,
      "step": 147
    },
    {
      "epoch": 0.004546431972475655,
      "grad_norm": 0.4215168356895447,
      "learning_rate": 1.9999974203642215e-05,
      "loss": 0.6938,
      "step": 148
    },
    {
      "epoch": 0.0045771511074248145,
      "grad_norm": 0.43267011642456055,
      "learning_rate": 1.9999973094247514e-05,
      "loss": 0.7183,
      "step": 149
    },
    {
      "epoch": 0.004607870242373975,
      "grad_norm": 0.36801448464393616,
      "learning_rate": 1.999997196149718e-05,
      "loss": 0.7292,
      "step": 150
    },
    {
      "epoch": 0.004638589377323135,
      "grad_norm": 0.4573562741279602,
      "learning_rate": 1.999997080539121e-05,
      "loss": 0.6087,
      "step": 151
    },
    {
      "epoch": 0.0046693085122722945,
      "grad_norm": 0.44994789361953735,
      "learning_rate": 1.9999969625929613e-05,
      "loss": 0.7521,
      "step": 152
    },
    {
      "epoch": 0.004700027647221454,
      "grad_norm": 0.4156774878501892,
      "learning_rate": 1.999996842311239e-05,
      "loss": 0.7256,
      "step": 153
    },
    {
      "epoch": 0.004730746782170614,
      "grad_norm": 0.3742092549800873,
      "learning_rate": 1.999996719693954e-05,
      "loss": 0.5957,
      "step": 154
    },
    {
      "epoch": 0.004761465917119774,
      "grad_norm": 0.39144250750541687,
      "learning_rate": 1.9999965947411067e-05,
      "loss": 0.5903,
      "step": 155
    },
    {
      "epoch": 0.004792185052068933,
      "grad_norm": 0.4047008156776428,
      "learning_rate": 1.9999964674526976e-05,
      "loss": 0.706,
      "step": 156
    },
    {
      "epoch": 0.004822904187018094,
      "grad_norm": 0.41821542382240295,
      "learning_rate": 1.999996337828727e-05,
      "loss": 0.6303,
      "step": 157
    },
    {
      "epoch": 0.004853623321967254,
      "grad_norm": 0.39450523257255554,
      "learning_rate": 1.9999962058691947e-05,
      "loss": 0.6936,
      "step": 158
    },
    {
      "epoch": 0.004884342456916413,
      "grad_norm": 0.4165686070919037,
      "learning_rate": 1.9999960715741016e-05,
      "loss": 0.677,
      "step": 159
    },
    {
      "epoch": 0.004915061591865573,
      "grad_norm": 0.4115440547466278,
      "learning_rate": 1.9999959349434484e-05,
      "loss": 0.6726,
      "step": 160
    },
    {
      "epoch": 0.004945780726814733,
      "grad_norm": 0.4328663945198059,
      "learning_rate": 1.9999957959772345e-05,
      "loss": 0.608,
      "step": 161
    },
    {
      "epoch": 0.0049764998617638926,
      "grad_norm": 0.42647549510002136,
      "learning_rate": 1.9999956546754605e-05,
      "loss": 0.7748,
      "step": 162
    },
    {
      "epoch": 0.005007218996713052,
      "grad_norm": 0.37625035643577576,
      "learning_rate": 1.999995511038127e-05,
      "loss": 0.7053,
      "step": 163
    },
    {
      "epoch": 0.005037938131662212,
      "grad_norm": 0.4004875123500824,
      "learning_rate": 1.999995365065234e-05,
      "loss": 0.7369,
      "step": 164
    },
    {
      "epoch": 0.005068657266611373,
      "grad_norm": 0.3631172776222229,
      "learning_rate": 1.9999952167567817e-05,
      "loss": 0.6568,
      "step": 165
    },
    {
      "epoch": 0.005099376401560532,
      "grad_norm": 0.4089898467063904,
      "learning_rate": 1.9999950661127713e-05,
      "loss": 0.665,
      "step": 166
    },
    {
      "epoch": 0.005130095536509692,
      "grad_norm": 0.40408825874328613,
      "learning_rate": 1.999994913133202e-05,
      "loss": 0.7395,
      "step": 167
    },
    {
      "epoch": 0.005160814671458852,
      "grad_norm": 0.4584376811981201,
      "learning_rate": 1.9999947578180753e-05,
      "loss": 0.5894,
      "step": 168
    },
    {
      "epoch": 0.0051915338064080115,
      "grad_norm": 0.39729058742523193,
      "learning_rate": 1.9999946001673907e-05,
      "loss": 0.6294,
      "step": 169
    },
    {
      "epoch": 0.005222252941357171,
      "grad_norm": 0.39025962352752686,
      "learning_rate": 1.999994440181149e-05,
      "loss": 0.7337,
      "step": 170
    },
    {
      "epoch": 0.005252972076306331,
      "grad_norm": 0.37553146481513977,
      "learning_rate": 1.99999427785935e-05,
      "loss": 0.6327,
      "step": 171
    },
    {
      "epoch": 0.005283691211255491,
      "grad_norm": 0.4529859125614166,
      "learning_rate": 1.999994113201995e-05,
      "loss": 0.6937,
      "step": 172
    },
    {
      "epoch": 0.005314410346204651,
      "grad_norm": 0.4317130148410797,
      "learning_rate": 1.9999939462090837e-05,
      "loss": 0.7041,
      "step": 173
    },
    {
      "epoch": 0.005345129481153811,
      "grad_norm": 0.40663379430770874,
      "learning_rate": 1.9999937768806167e-05,
      "loss": 0.6595,
      "step": 174
    },
    {
      "epoch": 0.005375848616102971,
      "grad_norm": 0.4241580069065094,
      "learning_rate": 1.9999936052165947e-05,
      "loss": 0.7627,
      "step": 175
    },
    {
      "epoch": 0.00540656775105213,
      "grad_norm": 0.39949244260787964,
      "learning_rate": 1.999993431217018e-05,
      "loss": 0.6418,
      "step": 176
    },
    {
      "epoch": 0.00543728688600129,
      "grad_norm": 0.5206996202468872,
      "learning_rate": 1.999993254881886e-05,
      "loss": 0.7191,
      "step": 177
    },
    {
      "epoch": 0.00546800602095045,
      "grad_norm": 0.439113587141037,
      "learning_rate": 1.9999930762112002e-05,
      "loss": 0.65,
      "step": 178
    },
    {
      "epoch": 0.0054987251558996095,
      "grad_norm": 1.0398123264312744,
      "learning_rate": 1.999992895204961e-05,
      "loss": 0.5634,
      "step": 179
    },
    {
      "epoch": 0.00552944429084877,
      "grad_norm": 0.3822295665740967,
      "learning_rate": 1.9999927118631682e-05,
      "loss": 0.6217,
      "step": 180
    },
    {
      "epoch": 0.00556016342579793,
      "grad_norm": 0.4115304946899414,
      "learning_rate": 1.999992526185823e-05,
      "loss": 0.6477,
      "step": 181
    },
    {
      "epoch": 0.0055908825607470895,
      "grad_norm": 0.4077301621437073,
      "learning_rate": 1.9999923381729253e-05,
      "loss": 0.7123,
      "step": 182
    },
    {
      "epoch": 0.005621601695696249,
      "grad_norm": 0.37694165110588074,
      "learning_rate": 1.9999921478244752e-05,
      "loss": 0.6258,
      "step": 183
    },
    {
      "epoch": 0.005652320830645409,
      "grad_norm": 0.4390418231487274,
      "learning_rate": 1.999991955140474e-05,
      "loss": 0.6808,
      "step": 184
    },
    {
      "epoch": 0.005683039965594569,
      "grad_norm": 0.5014764666557312,
      "learning_rate": 1.999991760120922e-05,
      "loss": 0.5788,
      "step": 185
    },
    {
      "epoch": 0.005713759100543728,
      "grad_norm": 0.3456033170223236,
      "learning_rate": 1.999991562765819e-05,
      "loss": 0.6716,
      "step": 186
    },
    {
      "epoch": 0.005744478235492888,
      "grad_norm": 0.39686164259910583,
      "learning_rate": 1.999991363075166e-05,
      "loss": 0.6912,
      "step": 187
    },
    {
      "epoch": 0.005775197370442049,
      "grad_norm": 0.4266481101512909,
      "learning_rate": 1.9999911610489633e-05,
      "loss": 0.679,
      "step": 188
    },
    {
      "epoch": 0.005805916505391208,
      "grad_norm": 0.3565369248390198,
      "learning_rate": 1.9999909566872113e-05,
      "loss": 0.63,
      "step": 189
    },
    {
      "epoch": 0.005836635640340368,
      "grad_norm": 0.4318750202655792,
      "learning_rate": 1.9999907499899107e-05,
      "loss": 0.6051,
      "step": 190
    },
    {
      "epoch": 0.005867354775289528,
      "grad_norm": 0.39390119910240173,
      "learning_rate": 1.999990540957062e-05,
      "loss": 0.7896,
      "step": 191
    },
    {
      "epoch": 0.005898073910238688,
      "grad_norm": 0.3787881135940552,
      "learning_rate": 1.9999903295886653e-05,
      "loss": 0.6158,
      "step": 192
    },
    {
      "epoch": 0.005928793045187847,
      "grad_norm": 0.4039481282234192,
      "learning_rate": 1.9999901158847213e-05,
      "loss": 0.7293,
      "step": 193
    },
    {
      "epoch": 0.005959512180137007,
      "grad_norm": 0.42687293887138367,
      "learning_rate": 1.9999898998452307e-05,
      "loss": 0.657,
      "step": 194
    },
    {
      "epoch": 0.005990231315086168,
      "grad_norm": 0.35309216380119324,
      "learning_rate": 1.999989681470194e-05,
      "loss": 0.6857,
      "step": 195
    },
    {
      "epoch": 0.006020950450035327,
      "grad_norm": 0.41449591517448425,
      "learning_rate": 1.999989460759611e-05,
      "loss": 0.7634,
      "step": 196
    },
    {
      "epoch": 0.006051669584984487,
      "grad_norm": 0.34888550639152527,
      "learning_rate": 1.9999892377134836e-05,
      "loss": 0.7087,
      "step": 197
    },
    {
      "epoch": 0.006082388719933647,
      "grad_norm": 0.38623496890068054,
      "learning_rate": 1.999989012331811e-05,
      "loss": 0.742,
      "step": 198
    },
    {
      "epoch": 0.0061131078548828065,
      "grad_norm": 0.3828396201133728,
      "learning_rate": 1.9999887846145944e-05,
      "loss": 0.6124,
      "step": 199
    },
    {
      "epoch": 0.006143826989831966,
      "grad_norm": 0.405282586812973,
      "learning_rate": 1.999988554561834e-05,
      "loss": 0.675,
      "step": 200
    },
    {
      "epoch": 0.006174546124781126,
      "grad_norm": 0.39675867557525635,
      "learning_rate": 1.9999883221735304e-05,
      "loss": 0.5764,
      "step": 201
    },
    {
      "epoch": 0.006205265259730286,
      "grad_norm": 0.4089547395706177,
      "learning_rate": 1.9999880874496845e-05,
      "loss": 0.7398,
      "step": 202
    },
    {
      "epoch": 0.006235984394679446,
      "grad_norm": 0.4142422676086426,
      "learning_rate": 1.9999878503902964e-05,
      "loss": 0.6223,
      "step": 203
    },
    {
      "epoch": 0.006266703529628606,
      "grad_norm": 0.3979097008705139,
      "learning_rate": 1.999987610995367e-05,
      "loss": 0.5788,
      "step": 204
    },
    {
      "epoch": 0.006297422664577766,
      "grad_norm": 0.38964784145355225,
      "learning_rate": 1.9999873692648966e-05,
      "loss": 0.6611,
      "step": 205
    },
    {
      "epoch": 0.006328141799526925,
      "grad_norm": 0.47635364532470703,
      "learning_rate": 1.999987125198886e-05,
      "loss": 0.611,
      "step": 206
    },
    {
      "epoch": 0.006358860934476085,
      "grad_norm": 0.3504014015197754,
      "learning_rate": 1.9999868787973352e-05,
      "loss": 0.5862,
      "step": 207
    },
    {
      "epoch": 0.006389580069425245,
      "grad_norm": 0.41913169622421265,
      "learning_rate": 1.9999866300602457e-05,
      "loss": 0.645,
      "step": 208
    },
    {
      "epoch": 0.0064202992043744045,
      "grad_norm": 0.4096449017524719,
      "learning_rate": 1.9999863789876174e-05,
      "loss": 0.6304,
      "step": 209
    },
    {
      "epoch": 0.006451018339323564,
      "grad_norm": 0.3602648675441742,
      "learning_rate": 1.999986125579451e-05,
      "loss": 0.6444,
      "step": 210
    },
    {
      "epoch": 0.006481737474272725,
      "grad_norm": 0.402296245098114,
      "learning_rate": 1.9999858698357472e-05,
      "loss": 0.7308,
      "step": 211
    },
    {
      "epoch": 0.0065124566092218845,
      "grad_norm": 0.3972809910774231,
      "learning_rate": 1.9999856117565067e-05,
      "loss": 0.6929,
      "step": 212
    },
    {
      "epoch": 0.006543175744171044,
      "grad_norm": 0.40088996291160583,
      "learning_rate": 1.9999853513417298e-05,
      "loss": 0.6613,
      "step": 213
    },
    {
      "epoch": 0.006573894879120204,
      "grad_norm": 1.0582997798919678,
      "learning_rate": 1.9999850885914173e-05,
      "loss": 0.7935,
      "step": 214
    },
    {
      "epoch": 0.006604614014069364,
      "grad_norm": 0.38180917501449585,
      "learning_rate": 1.9999848235055698e-05,
      "loss": 0.6419,
      "step": 215
    },
    {
      "epoch": 0.006635333149018523,
      "grad_norm": 0.4208572506904602,
      "learning_rate": 1.999984556084188e-05,
      "loss": 0.6565,
      "step": 216
    },
    {
      "epoch": 0.006666052283967683,
      "grad_norm": 0.369809091091156,
      "learning_rate": 1.9999842863272723e-05,
      "loss": 0.599,
      "step": 217
    },
    {
      "epoch": 0.006696771418916844,
      "grad_norm": 0.3528952896595001,
      "learning_rate": 1.9999840142348238e-05,
      "loss": 0.6812,
      "step": 218
    },
    {
      "epoch": 0.0067274905538660034,
      "grad_norm": 0.41435348987579346,
      "learning_rate": 1.9999837398068425e-05,
      "loss": 0.6297,
      "step": 219
    },
    {
      "epoch": 0.006758209688815163,
      "grad_norm": 0.39285483956336975,
      "learning_rate": 1.999983463043329e-05,
      "loss": 0.7044,
      "step": 220
    },
    {
      "epoch": 0.006788928823764323,
      "grad_norm": 0.38261091709136963,
      "learning_rate": 1.9999831839442847e-05,
      "loss": 0.7441,
      "step": 221
    },
    {
      "epoch": 0.006819647958713483,
      "grad_norm": 0.36022257804870605,
      "learning_rate": 1.99998290250971e-05,
      "loss": 0.6705,
      "step": 222
    },
    {
      "epoch": 0.006850367093662642,
      "grad_norm": 0.3939741849899292,
      "learning_rate": 1.999982618739605e-05,
      "loss": 0.7046,
      "step": 223
    },
    {
      "epoch": 0.006881086228611802,
      "grad_norm": 0.3867575228214264,
      "learning_rate": 1.9999823326339708e-05,
      "loss": 0.6751,
      "step": 224
    },
    {
      "epoch": 0.006911805363560962,
      "grad_norm": 0.4314223527908325,
      "learning_rate": 1.9999820441928082e-05,
      "loss": 0.6127,
      "step": 225
    },
    {
      "epoch": 0.006942524498510122,
      "grad_norm": 0.37257808446884155,
      "learning_rate": 1.9999817534161177e-05,
      "loss": 0.7028,
      "step": 226
    },
    {
      "epoch": 0.006973243633459282,
      "grad_norm": 0.3947150707244873,
      "learning_rate": 1.9999814603039e-05,
      "loss": 0.7125,
      "step": 227
    },
    {
      "epoch": 0.007003962768408442,
      "grad_norm": 0.3422849476337433,
      "learning_rate": 1.9999811648561555e-05,
      "loss": 0.5899,
      "step": 228
    },
    {
      "epoch": 0.0070346819033576015,
      "grad_norm": 0.34524112939834595,
      "learning_rate": 1.9999808670728856e-05,
      "loss": 0.621,
      "step": 229
    },
    {
      "epoch": 0.007065401038306761,
      "grad_norm": 0.3779149055480957,
      "learning_rate": 1.99998056695409e-05,
      "loss": 0.6688,
      "step": 230
    },
    {
      "epoch": 0.007096120173255921,
      "grad_norm": 0.40354642271995544,
      "learning_rate": 1.9999802644997707e-05,
      "loss": 0.7037,
      "step": 231
    },
    {
      "epoch": 0.007126839308205081,
      "grad_norm": 0.36464571952819824,
      "learning_rate": 1.999979959709927e-05,
      "loss": 0.6438,
      "step": 232
    },
    {
      "epoch": 0.00715755844315424,
      "grad_norm": 0.38330891728401184,
      "learning_rate": 1.9999796525845606e-05,
      "loss": 0.6663,
      "step": 233
    },
    {
      "epoch": 0.007188277578103401,
      "grad_norm": 0.4111490845680237,
      "learning_rate": 1.9999793431236717e-05,
      "loss": 0.6654,
      "step": 234
    },
    {
      "epoch": 0.007218996713052561,
      "grad_norm": 0.40398624539375305,
      "learning_rate": 1.9999790313272612e-05,
      "loss": 0.6901,
      "step": 235
    },
    {
      "epoch": 0.00724971584800172,
      "grad_norm": 0.4054335653781891,
      "learning_rate": 1.9999787171953298e-05,
      "loss": 0.6193,
      "step": 236
    },
    {
      "epoch": 0.00728043498295088,
      "grad_norm": 0.45651334524154663,
      "learning_rate": 1.9999784007278782e-05,
      "loss": 0.6828,
      "step": 237
    },
    {
      "epoch": 0.00731115411790004,
      "grad_norm": 0.4088228940963745,
      "learning_rate": 1.9999780819249074e-05,
      "loss": 0.6513,
      "step": 238
    },
    {
      "epoch": 0.0073418732528491995,
      "grad_norm": 0.3671337366104126,
      "learning_rate": 1.999977760786418e-05,
      "loss": 0.6647,
      "step": 239
    },
    {
      "epoch": 0.007372592387798359,
      "grad_norm": 0.3689892292022705,
      "learning_rate": 1.9999774373124105e-05,
      "loss": 0.6374,
      "step": 240
    },
    {
      "epoch": 0.00740331152274752,
      "grad_norm": 0.4682154059410095,
      "learning_rate": 1.999977111502886e-05,
      "loss": 0.6567,
      "step": 241
    },
    {
      "epoch": 0.0074340306576966796,
      "grad_norm": 0.35766980051994324,
      "learning_rate": 1.9999767833578453e-05,
      "loss": 0.7022,
      "step": 242
    },
    {
      "epoch": 0.007464749792645839,
      "grad_norm": 0.38158681988716125,
      "learning_rate": 1.9999764528772883e-05,
      "loss": 0.7223,
      "step": 243
    },
    {
      "epoch": 0.007495468927594999,
      "grad_norm": 0.40947428345680237,
      "learning_rate": 1.9999761200612172e-05,
      "loss": 0.6185,
      "step": 244
    },
    {
      "epoch": 0.007526188062544159,
      "grad_norm": 0.48650962114334106,
      "learning_rate": 1.9999757849096316e-05,
      "loss": 0.7419,
      "step": 245
    },
    {
      "epoch": 0.0075569071974933184,
      "grad_norm": 0.3855099678039551,
      "learning_rate": 1.999975447422533e-05,
      "loss": 0.7115,
      "step": 246
    },
    {
      "epoch": 0.007587626332442478,
      "grad_norm": 0.383861780166626,
      "learning_rate": 1.9999751075999215e-05,
      "loss": 0.6983,
      "step": 247
    },
    {
      "epoch": 0.007618345467391638,
      "grad_norm": 0.3975721597671509,
      "learning_rate": 1.999974765441799e-05,
      "loss": 0.6461,
      "step": 248
    },
    {
      "epoch": 0.0076490646023407985,
      "grad_norm": 0.4092705249786377,
      "learning_rate": 1.9999744209481647e-05,
      "loss": 0.6444,
      "step": 249
    },
    {
      "epoch": 0.007679783737289958,
      "grad_norm": 0.3585764765739441,
      "learning_rate": 1.999974074119021e-05,
      "loss": 0.6558,
      "step": 250
    },
    {
      "epoch": 0.007710502872239118,
      "grad_norm": 0.34911248087882996,
      "learning_rate": 1.999973724954368e-05,
      "loss": 0.6142,
      "step": 251
    },
    {
      "epoch": 0.007741222007188278,
      "grad_norm": 0.3658337891101837,
      "learning_rate": 1.999973373454206e-05,
      "loss": 0.7271,
      "step": 252
    },
    {
      "epoch": 0.007771941142137437,
      "grad_norm": 0.39929425716400146,
      "learning_rate": 1.999973019618537e-05,
      "loss": 0.6636,
      "step": 253
    },
    {
      "epoch": 0.007802660277086597,
      "grad_norm": 0.4133506417274475,
      "learning_rate": 1.999972663447361e-05,
      "loss": 0.6044,
      "step": 254
    },
    {
      "epoch": 0.007833379412035758,
      "grad_norm": 0.46768030524253845,
      "learning_rate": 1.9999723049406785e-05,
      "loss": 0.6723,
      "step": 255
    },
    {
      "epoch": 0.007864098546984917,
      "grad_norm": 0.3781800866127014,
      "learning_rate": 1.999971944098491e-05,
      "loss": 0.6659,
      "step": 256
    },
    {
      "epoch": 0.007894817681934077,
      "grad_norm": 0.3629230558872223,
      "learning_rate": 1.9999715809207995e-05,
      "loss": 0.56,
      "step": 257
    },
    {
      "epoch": 0.007925536816883237,
      "grad_norm": 0.34650668501853943,
      "learning_rate": 1.9999712154076046e-05,
      "loss": 0.6414,
      "step": 258
    },
    {
      "epoch": 0.007956255951832397,
      "grad_norm": 0.4147944450378418,
      "learning_rate": 1.9999708475589067e-05,
      "loss": 0.7194,
      "step": 259
    },
    {
      "epoch": 0.007986975086781556,
      "grad_norm": 0.38641059398651123,
      "learning_rate": 1.9999704773747072e-05,
      "loss": 0.6329,
      "step": 260
    },
    {
      "epoch": 0.008017694221730716,
      "grad_norm": 0.3812808394432068,
      "learning_rate": 1.9999701048550072e-05,
      "loss": 0.7474,
      "step": 261
    },
    {
      "epoch": 0.008048413356679876,
      "grad_norm": 0.3580913543701172,
      "learning_rate": 1.9999697299998066e-05,
      "loss": 0.6158,
      "step": 262
    },
    {
      "epoch": 0.008079132491629035,
      "grad_norm": 0.40415745973587036,
      "learning_rate": 1.999969352809107e-05,
      "loss": 0.7341,
      "step": 263
    },
    {
      "epoch": 0.008109851626578195,
      "grad_norm": 0.37502536177635193,
      "learning_rate": 1.9999689732829095e-05,
      "loss": 0.6728,
      "step": 264
    },
    {
      "epoch": 0.008140570761527355,
      "grad_norm": 0.3997909724712372,
      "learning_rate": 1.9999685914212143e-05,
      "loss": 0.6767,
      "step": 265
    },
    {
      "epoch": 0.008171289896476515,
      "grad_norm": 0.3480750322341919,
      "learning_rate": 1.9999682072240226e-05,
      "loss": 0.6943,
      "step": 266
    },
    {
      "epoch": 0.008202009031425674,
      "grad_norm": 0.4592234492301941,
      "learning_rate": 1.9999678206913355e-05,
      "loss": 0.7125,
      "step": 267
    },
    {
      "epoch": 0.008232728166374836,
      "grad_norm": 0.5680233836174011,
      "learning_rate": 1.9999674318231535e-05,
      "loss": 0.6677,
      "step": 268
    },
    {
      "epoch": 0.008263447301323995,
      "grad_norm": 0.46107569336891174,
      "learning_rate": 1.999967040619478e-05,
      "loss": 0.7797,
      "step": 269
    },
    {
      "epoch": 0.008294166436273155,
      "grad_norm": 0.48123297095298767,
      "learning_rate": 1.9999666470803095e-05,
      "loss": 0.7401,
      "step": 270
    },
    {
      "epoch": 0.008324885571222315,
      "grad_norm": 0.43247920274734497,
      "learning_rate": 1.999966251205649e-05,
      "loss": 0.5787,
      "step": 271
    },
    {
      "epoch": 0.008355604706171475,
      "grad_norm": 0.4157200753688812,
      "learning_rate": 1.9999658529954975e-05,
      "loss": 0.702,
      "step": 272
    },
    {
      "epoch": 0.008386323841120634,
      "grad_norm": 0.40017959475517273,
      "learning_rate": 1.999965452449856e-05,
      "loss": 0.6436,
      "step": 273
    },
    {
      "epoch": 0.008417042976069794,
      "grad_norm": 0.46761250495910645,
      "learning_rate": 1.9999650495687253e-05,
      "loss": 0.7264,
      "step": 274
    },
    {
      "epoch": 0.008447762111018954,
      "grad_norm": 0.38971495628356934,
      "learning_rate": 1.9999646443521064e-05,
      "loss": 0.6621,
      "step": 275
    },
    {
      "epoch": 0.008478481245968113,
      "grad_norm": 0.335269957780838,
      "learning_rate": 1.9999642368000002e-05,
      "loss": 0.6791,
      "step": 276
    },
    {
      "epoch": 0.008509200380917273,
      "grad_norm": 0.37881919741630554,
      "learning_rate": 1.9999638269124076e-05,
      "loss": 0.6573,
      "step": 277
    },
    {
      "epoch": 0.008539919515866433,
      "grad_norm": 0.41773054003715515,
      "learning_rate": 1.9999634146893298e-05,
      "loss": 0.5777,
      "step": 278
    },
    {
      "epoch": 0.008570638650815593,
      "grad_norm": 1.0363740921020508,
      "learning_rate": 1.9999630001307676e-05,
      "loss": 0.6935,
      "step": 279
    },
    {
      "epoch": 0.008601357785764752,
      "grad_norm": 0.3823683261871338,
      "learning_rate": 1.999962583236722e-05,
      "loss": 0.6592,
      "step": 280
    },
    {
      "epoch": 0.008632076920713912,
      "grad_norm": 0.4405483901500702,
      "learning_rate": 1.9999621640071937e-05,
      "loss": 0.6655,
      "step": 281
    },
    {
      "epoch": 0.008662796055663072,
      "grad_norm": 0.38129326701164246,
      "learning_rate": 1.999961742442184e-05,
      "loss": 0.6721,
      "step": 282
    },
    {
      "epoch": 0.008693515190612233,
      "grad_norm": 0.35498368740081787,
      "learning_rate": 1.9999613185416945e-05,
      "loss": 0.6929,
      "step": 283
    },
    {
      "epoch": 0.008724234325561393,
      "grad_norm": 0.43427222967147827,
      "learning_rate": 1.9999608923057247e-05,
      "loss": 0.6333,
      "step": 284
    },
    {
      "epoch": 0.008754953460510553,
      "grad_norm": 0.3337889313697815,
      "learning_rate": 1.9999604637342767e-05,
      "loss": 0.586,
      "step": 285
    },
    {
      "epoch": 0.008785672595459712,
      "grad_norm": 0.4489438235759735,
      "learning_rate": 1.9999600328273508e-05,
      "loss": 0.6355,
      "step": 286
    },
    {
      "epoch": 0.008816391730408872,
      "grad_norm": 0.42258504033088684,
      "learning_rate": 1.999959599584949e-05,
      "loss": 0.6204,
      "step": 287
    },
    {
      "epoch": 0.008847110865358032,
      "grad_norm": 0.33534491062164307,
      "learning_rate": 1.9999591640070715e-05,
      "loss": 0.5926,
      "step": 288
    },
    {
      "epoch": 0.008877830000307192,
      "grad_norm": 0.41799235343933105,
      "learning_rate": 1.9999587260937195e-05,
      "loss": 0.7327,
      "step": 289
    },
    {
      "epoch": 0.008908549135256351,
      "grad_norm": 0.40292006731033325,
      "learning_rate": 1.999958285844894e-05,
      "loss": 0.6498,
      "step": 290
    },
    {
      "epoch": 0.008939268270205511,
      "grad_norm": 0.7016105055809021,
      "learning_rate": 1.999957843260596e-05,
      "loss": 0.6208,
      "step": 291
    },
    {
      "epoch": 0.00896998740515467,
      "grad_norm": 0.3725782036781311,
      "learning_rate": 1.999957398340827e-05,
      "loss": 0.6172,
      "step": 292
    },
    {
      "epoch": 0.00900070654010383,
      "grad_norm": 0.39071616530418396,
      "learning_rate": 1.9999569510855873e-05,
      "loss": 0.715,
      "step": 293
    },
    {
      "epoch": 0.00903142567505299,
      "grad_norm": 0.3588090240955353,
      "learning_rate": 1.9999565014948785e-05,
      "loss": 0.6251,
      "step": 294
    },
    {
      "epoch": 0.00906214481000215,
      "grad_norm": 0.40229129791259766,
      "learning_rate": 1.9999560495687013e-05,
      "loss": 0.6563,
      "step": 295
    },
    {
      "epoch": 0.00909286394495131,
      "grad_norm": 0.3493892550468445,
      "learning_rate": 1.999955595307057e-05,
      "loss": 0.6356,
      "step": 296
    },
    {
      "epoch": 0.00912358307990047,
      "grad_norm": 0.35623547434806824,
      "learning_rate": 1.9999551387099468e-05,
      "loss": 0.6282,
      "step": 297
    },
    {
      "epoch": 0.009154302214849629,
      "grad_norm": 0.38631561398506165,
      "learning_rate": 1.9999546797773712e-05,
      "loss": 0.6539,
      "step": 298
    },
    {
      "epoch": 0.00918502134979879,
      "grad_norm": 0.3356530964374542,
      "learning_rate": 1.9999542185093316e-05,
      "loss": 0.69,
      "step": 299
    },
    {
      "epoch": 0.00921574048474795,
      "grad_norm": 0.3222956955432892,
      "learning_rate": 1.999953754905829e-05,
      "loss": 0.5983,
      "step": 300
    },
    {
      "epoch": 0.00924645961969711,
      "grad_norm": 0.336961030960083,
      "learning_rate": 1.999953288966865e-05,
      "loss": 0.6822,
      "step": 301
    },
    {
      "epoch": 0.00927717875464627,
      "grad_norm": 0.3628532886505127,
      "learning_rate": 1.99995282069244e-05,
      "loss": 0.6674,
      "step": 302
    },
    {
      "epoch": 0.00930789788959543,
      "grad_norm": 0.3731553256511688,
      "learning_rate": 1.9999523500825554e-05,
      "loss": 0.606,
      "step": 303
    },
    {
      "epoch": 0.009338617024544589,
      "grad_norm": 0.35044553875923157,
      "learning_rate": 1.9999518771372122e-05,
      "loss": 0.6227,
      "step": 304
    },
    {
      "epoch": 0.009369336159493749,
      "grad_norm": 0.35342147946357727,
      "learning_rate": 1.999951401856412e-05,
      "loss": 0.6714,
      "step": 305
    },
    {
      "epoch": 0.009400055294442908,
      "grad_norm": 0.3623189926147461,
      "learning_rate": 1.9999509242401546e-05,
      "loss": 0.6875,
      "step": 306
    },
    {
      "epoch": 0.009430774429392068,
      "grad_norm": 0.37557607889175415,
      "learning_rate": 1.9999504442884426e-05,
      "loss": 0.6599,
      "step": 307
    },
    {
      "epoch": 0.009461493564341228,
      "grad_norm": 0.3845899999141693,
      "learning_rate": 1.9999499620012764e-05,
      "loss": 0.6536,
      "step": 308
    },
    {
      "epoch": 0.009492212699290388,
      "grad_norm": 0.3518262803554535,
      "learning_rate": 1.9999494773786574e-05,
      "loss": 0.6633,
      "step": 309
    },
    {
      "epoch": 0.009522931834239547,
      "grad_norm": 0.35807764530181885,
      "learning_rate": 1.999948990420586e-05,
      "loss": 0.659,
      "step": 310
    },
    {
      "epoch": 0.009553650969188707,
      "grad_norm": 0.5970296859741211,
      "learning_rate": 1.9999485011270644e-05,
      "loss": 0.5517,
      "step": 311
    },
    {
      "epoch": 0.009584370104137867,
      "grad_norm": 0.3578811287879944,
      "learning_rate": 1.999948009498093e-05,
      "loss": 0.6496,
      "step": 312
    },
    {
      "epoch": 0.009615089239087026,
      "grad_norm": 0.3578011691570282,
      "learning_rate": 1.999947515533673e-05,
      "loss": 0.6423,
      "step": 313
    },
    {
      "epoch": 0.009645808374036188,
      "grad_norm": 0.41529035568237305,
      "learning_rate": 1.999947019233806e-05,
      "loss": 0.669,
      "step": 314
    },
    {
      "epoch": 0.009676527508985348,
      "grad_norm": 0.36085063219070435,
      "learning_rate": 1.999946520598493e-05,
      "loss": 0.6035,
      "step": 315
    },
    {
      "epoch": 0.009707246643934507,
      "grad_norm": 0.41266924142837524,
      "learning_rate": 1.999946019627735e-05,
      "loss": 0.6619,
      "step": 316
    },
    {
      "epoch": 0.009737965778883667,
      "grad_norm": 0.37145596742630005,
      "learning_rate": 1.999945516321533e-05,
      "loss": 0.7088,
      "step": 317
    },
    {
      "epoch": 0.009768684913832827,
      "grad_norm": 0.38889577984809875,
      "learning_rate": 1.9999450106798888e-05,
      "loss": 0.6121,
      "step": 318
    },
    {
      "epoch": 0.009799404048781987,
      "grad_norm": 0.4038635492324829,
      "learning_rate": 1.999944502702803e-05,
      "loss": 0.6331,
      "step": 319
    },
    {
      "epoch": 0.009830123183731146,
      "grad_norm": 0.42760738730430603,
      "learning_rate": 1.9999439923902766e-05,
      "loss": 0.6331,
      "step": 320
    },
    {
      "epoch": 0.009860842318680306,
      "grad_norm": 0.3894347846508026,
      "learning_rate": 1.999943479742312e-05,
      "loss": 0.7133,
      "step": 321
    },
    {
      "epoch": 0.009891561453629466,
      "grad_norm": 0.35994023084640503,
      "learning_rate": 1.999942964758909e-05,
      "loss": 0.6835,
      "step": 322
    },
    {
      "epoch": 0.009922280588578625,
      "grad_norm": 0.37454649806022644,
      "learning_rate": 1.9999424474400697e-05,
      "loss": 0.6567,
      "step": 323
    },
    {
      "epoch": 0.009952999723527785,
      "grad_norm": 0.3578818142414093,
      "learning_rate": 1.9999419277857946e-05,
      "loss": 0.6133,
      "step": 324
    },
    {
      "epoch": 0.009983718858476945,
      "grad_norm": 0.35288044810295105,
      "learning_rate": 1.9999414057960854e-05,
      "loss": 0.6021,
      "step": 325
    },
    {
      "epoch": 0.010014437993426105,
      "grad_norm": 0.42110273241996765,
      "learning_rate": 1.999940881470943e-05,
      "loss": 0.6784,
      "step": 326
    },
    {
      "epoch": 0.010045157128375264,
      "grad_norm": 0.3750227987766266,
      "learning_rate": 1.9999403548103692e-05,
      "loss": 0.6934,
      "step": 327
    },
    {
      "epoch": 0.010075876263324424,
      "grad_norm": 0.49750158190727234,
      "learning_rate": 1.999939825814365e-05,
      "loss": 0.6628,
      "step": 328
    },
    {
      "epoch": 0.010106595398273585,
      "grad_norm": 0.4880644381046295,
      "learning_rate": 1.999939294482931e-05,
      "loss": 0.6438,
      "step": 329
    },
    {
      "epoch": 0.010137314533222745,
      "grad_norm": 0.39149752259254456,
      "learning_rate": 1.9999387608160693e-05,
      "loss": 0.6487,
      "step": 330
    },
    {
      "epoch": 0.010168033668171905,
      "grad_norm": 0.3597683608531952,
      "learning_rate": 1.999938224813781e-05,
      "loss": 0.6257,
      "step": 331
    },
    {
      "epoch": 0.010198752803121065,
      "grad_norm": 0.35471296310424805,
      "learning_rate": 1.9999376864760664e-05,
      "loss": 0.5989,
      "step": 332
    },
    {
      "epoch": 0.010229471938070224,
      "grad_norm": 0.38467466831207275,
      "learning_rate": 1.9999371458029283e-05,
      "loss": 0.6762,
      "step": 333
    },
    {
      "epoch": 0.010260191073019384,
      "grad_norm": 1.087361216545105,
      "learning_rate": 1.9999366027943665e-05,
      "loss": 0.616,
      "step": 334
    },
    {
      "epoch": 0.010290910207968544,
      "grad_norm": 0.36453086137771606,
      "learning_rate": 1.999936057450383e-05,
      "loss": 0.6441,
      "step": 335
    },
    {
      "epoch": 0.010321629342917703,
      "grad_norm": 0.3416441082954407,
      "learning_rate": 1.9999355097709795e-05,
      "loss": 0.6209,
      "step": 336
    },
    {
      "epoch": 0.010352348477866863,
      "grad_norm": 0.3924543559551239,
      "learning_rate": 1.9999349597561565e-05,
      "loss": 0.7156,
      "step": 337
    },
    {
      "epoch": 0.010383067612816023,
      "grad_norm": 0.3669499456882477,
      "learning_rate": 1.9999344074059157e-05,
      "loss": 0.69,
      "step": 338
    },
    {
      "epoch": 0.010413786747765183,
      "grad_norm": 0.36612990498542786,
      "learning_rate": 1.999933852720258e-05,
      "loss": 0.7049,
      "step": 339
    },
    {
      "epoch": 0.010444505882714342,
      "grad_norm": 0.36199188232421875,
      "learning_rate": 1.999933295699185e-05,
      "loss": 0.5896,
      "step": 340
    },
    {
      "epoch": 0.010475225017663502,
      "grad_norm": 0.40106144547462463,
      "learning_rate": 1.9999327363426985e-05,
      "loss": 0.6656,
      "step": 341
    },
    {
      "epoch": 0.010505944152612662,
      "grad_norm": 0.3442155718803406,
      "learning_rate": 1.9999321746507986e-05,
      "loss": 0.6688,
      "step": 342
    },
    {
      "epoch": 0.010536663287561822,
      "grad_norm": 1.9197670221328735,
      "learning_rate": 1.9999316106234876e-05,
      "loss": 0.6966,
      "step": 343
    },
    {
      "epoch": 0.010567382422510981,
      "grad_norm": 0.4096560478210449,
      "learning_rate": 1.9999310442607662e-05,
      "loss": 0.6671,
      "step": 344
    },
    {
      "epoch": 0.010598101557460143,
      "grad_norm": 0.31059959530830383,
      "learning_rate": 1.999930475562636e-05,
      "loss": 0.623,
      "step": 345
    },
    {
      "epoch": 0.010628820692409302,
      "grad_norm": 0.49931785464286804,
      "learning_rate": 1.9999299045290988e-05,
      "loss": 0.724,
      "step": 346
    },
    {
      "epoch": 0.010659539827358462,
      "grad_norm": 0.4200448989868164,
      "learning_rate": 1.9999293311601552e-05,
      "loss": 0.7036,
      "step": 347
    },
    {
      "epoch": 0.010690258962307622,
      "grad_norm": 0.4106113314628601,
      "learning_rate": 1.9999287554558066e-05,
      "loss": 0.7176,
      "step": 348
    },
    {
      "epoch": 0.010720978097256782,
      "grad_norm": 0.34463292360305786,
      "learning_rate": 1.999928177416055e-05,
      "loss": 0.746,
      "step": 349
    },
    {
      "epoch": 0.010751697232205941,
      "grad_norm": 0.35606110095977783,
      "learning_rate": 1.999927597040901e-05,
      "loss": 0.6822,
      "step": 350
    },
    {
      "epoch": 0.010782416367155101,
      "grad_norm": 0.34727346897125244,
      "learning_rate": 1.9999270143303465e-05,
      "loss": 0.5823,
      "step": 351
    },
    {
      "epoch": 0.01081313550210426,
      "grad_norm": 0.3678117096424103,
      "learning_rate": 1.9999264292843923e-05,
      "loss": 0.6291,
      "step": 352
    },
    {
      "epoch": 0.01084385463705342,
      "grad_norm": 0.39331579208374023,
      "learning_rate": 1.99992584190304e-05,
      "loss": 0.6074,
      "step": 353
    },
    {
      "epoch": 0.01087457377200258,
      "grad_norm": 0.3936454653739929,
      "learning_rate": 1.9999252521862917e-05,
      "loss": 0.6587,
      "step": 354
    },
    {
      "epoch": 0.01090529290695174,
      "grad_norm": 0.43232443928718567,
      "learning_rate": 1.9999246601341475e-05,
      "loss": 0.7187,
      "step": 355
    },
    {
      "epoch": 0.0109360120419009,
      "grad_norm": 0.4093814492225647,
      "learning_rate": 1.9999240657466095e-05,
      "loss": 0.7158,
      "step": 356
    },
    {
      "epoch": 0.01096673117685006,
      "grad_norm": 0.3415032625198364,
      "learning_rate": 1.9999234690236794e-05,
      "loss": 0.6987,
      "step": 357
    },
    {
      "epoch": 0.010997450311799219,
      "grad_norm": 1.124853491783142,
      "learning_rate": 1.9999228699653578e-05,
      "loss": 0.6117,
      "step": 358
    },
    {
      "epoch": 0.011028169446748379,
      "grad_norm": 0.4822380542755127,
      "learning_rate": 1.9999222685716468e-05,
      "loss": 0.6702,
      "step": 359
    },
    {
      "epoch": 0.01105888858169754,
      "grad_norm": 0.33252909779548645,
      "learning_rate": 1.9999216648425473e-05,
      "loss": 0.6723,
      "step": 360
    },
    {
      "epoch": 0.0110896077166467,
      "grad_norm": 0.3503856062889099,
      "learning_rate": 1.999921058778061e-05,
      "loss": 0.5881,
      "step": 361
    },
    {
      "epoch": 0.01112032685159586,
      "grad_norm": 0.3378940522670746,
      "learning_rate": 1.9999204503781896e-05,
      "loss": 0.6501,
      "step": 362
    },
    {
      "epoch": 0.01115104598654502,
      "grad_norm": 0.3460848331451416,
      "learning_rate": 1.9999198396429337e-05,
      "loss": 0.6441,
      "step": 363
    },
    {
      "epoch": 0.011181765121494179,
      "grad_norm": 0.3655117452144623,
      "learning_rate": 1.999919226572295e-05,
      "loss": 0.7047,
      "step": 364
    },
    {
      "epoch": 0.011212484256443339,
      "grad_norm": 0.4178818166255951,
      "learning_rate": 1.9999186111662756e-05,
      "loss": 0.7082,
      "step": 365
    },
    {
      "epoch": 0.011243203391392498,
      "grad_norm": 0.4033735394477844,
      "learning_rate": 1.999917993424876e-05,
      "loss": 0.7278,
      "step": 366
    },
    {
      "epoch": 0.011273922526341658,
      "grad_norm": 0.32997870445251465,
      "learning_rate": 1.9999173733480987e-05,
      "loss": 0.6431,
      "step": 367
    },
    {
      "epoch": 0.011304641661290818,
      "grad_norm": 0.3790479898452759,
      "learning_rate": 1.999916750935944e-05,
      "loss": 0.5667,
      "step": 368
    },
    {
      "epoch": 0.011335360796239978,
      "grad_norm": 0.3373287320137024,
      "learning_rate": 1.9999161261884142e-05,
      "loss": 0.6058,
      "step": 369
    },
    {
      "epoch": 0.011366079931189137,
      "grad_norm": 0.3604663014411926,
      "learning_rate": 1.9999154991055102e-05,
      "loss": 0.6194,
      "step": 370
    },
    {
      "epoch": 0.011396799066138297,
      "grad_norm": 0.3682262599468231,
      "learning_rate": 1.999914869687234e-05,
      "loss": 0.6911,
      "step": 371
    },
    {
      "epoch": 0.011427518201087457,
      "grad_norm": 0.35400623083114624,
      "learning_rate": 1.9999142379335867e-05,
      "loss": 0.6196,
      "step": 372
    },
    {
      "epoch": 0.011458237336036617,
      "grad_norm": 0.3947265148162842,
      "learning_rate": 1.9999136038445695e-05,
      "loss": 0.6581,
      "step": 373
    },
    {
      "epoch": 0.011488956470985776,
      "grad_norm": 0.4798475503921509,
      "learning_rate": 1.9999129674201847e-05,
      "loss": 0.6726,
      "step": 374
    },
    {
      "epoch": 0.011519675605934938,
      "grad_norm": 0.35179272294044495,
      "learning_rate": 1.999912328660433e-05,
      "loss": 0.6398,
      "step": 375
    },
    {
      "epoch": 0.011550394740884097,
      "grad_norm": 0.5301125645637512,
      "learning_rate": 1.9999116875653167e-05,
      "loss": 0.6353,
      "step": 376
    },
    {
      "epoch": 0.011581113875833257,
      "grad_norm": 0.38167908787727356,
      "learning_rate": 1.9999110441348364e-05,
      "loss": 0.6339,
      "step": 377
    },
    {
      "epoch": 0.011611833010782417,
      "grad_norm": 0.3411039412021637,
      "learning_rate": 1.9999103983689944e-05,
      "loss": 0.6464,
      "step": 378
    },
    {
      "epoch": 0.011642552145731577,
      "grad_norm": 0.36295250058174133,
      "learning_rate": 1.9999097502677914e-05,
      "loss": 0.5786,
      "step": 379
    },
    {
      "epoch": 0.011673271280680736,
      "grad_norm": 0.5244048833847046,
      "learning_rate": 1.9999090998312295e-05,
      "loss": 0.6284,
      "step": 380
    },
    {
      "epoch": 0.011703990415629896,
      "grad_norm": 0.3522769808769226,
      "learning_rate": 1.99990844705931e-05,
      "loss": 0.7016,
      "step": 381
    },
    {
      "epoch": 0.011734709550579056,
      "grad_norm": 0.3721171021461487,
      "learning_rate": 1.9999077919520346e-05,
      "loss": 0.6314,
      "step": 382
    },
    {
      "epoch": 0.011765428685528215,
      "grad_norm": 0.3392050564289093,
      "learning_rate": 1.9999071345094047e-05,
      "loss": 0.6272,
      "step": 383
    },
    {
      "epoch": 0.011796147820477375,
      "grad_norm": 0.4184630215167999,
      "learning_rate": 1.999906474731422e-05,
      "loss": 0.6294,
      "step": 384
    },
    {
      "epoch": 0.011826866955426535,
      "grad_norm": 0.4917213022708893,
      "learning_rate": 1.9999058126180877e-05,
      "loss": 0.6854,
      "step": 385
    },
    {
      "epoch": 0.011857586090375695,
      "grad_norm": 0.362532377243042,
      "learning_rate": 1.9999051481694036e-05,
      "loss": 0.6606,
      "step": 386
    },
    {
      "epoch": 0.011888305225324854,
      "grad_norm": 0.3755333423614502,
      "learning_rate": 1.999904481385371e-05,
      "loss": 0.6519,
      "step": 387
    },
    {
      "epoch": 0.011919024360274014,
      "grad_norm": 0.40992051362991333,
      "learning_rate": 1.999903812265992e-05,
      "loss": 0.6902,
      "step": 388
    },
    {
      "epoch": 0.011949743495223174,
      "grad_norm": 0.4052127003669739,
      "learning_rate": 1.9999031408112676e-05,
      "loss": 0.7251,
      "step": 389
    },
    {
      "epoch": 0.011980462630172335,
      "grad_norm": 0.3541010022163391,
      "learning_rate": 1.9999024670211996e-05,
      "loss": 0.6237,
      "step": 390
    },
    {
      "epoch": 0.012011181765121495,
      "grad_norm": 0.354582279920578,
      "learning_rate": 1.9999017908957896e-05,
      "loss": 0.6678,
      "step": 391
    },
    {
      "epoch": 0.012041900900070655,
      "grad_norm": 0.5061604380607605,
      "learning_rate": 1.9999011124350393e-05,
      "loss": 0.6559,
      "step": 392
    },
    {
      "epoch": 0.012072620035019814,
      "grad_norm": 0.3392725884914398,
      "learning_rate": 1.99990043163895e-05,
      "loss": 0.6907,
      "step": 393
    },
    {
      "epoch": 0.012103339169968974,
      "grad_norm": 0.388367623090744,
      "learning_rate": 1.9998997485075228e-05,
      "loss": 0.6801,
      "step": 394
    },
    {
      "epoch": 0.012134058304918134,
      "grad_norm": 0.3592967391014099,
      "learning_rate": 1.9998990630407607e-05,
      "loss": 0.6578,
      "step": 395
    },
    {
      "epoch": 0.012164777439867294,
      "grad_norm": 0.3641335070133209,
      "learning_rate": 1.9998983752386644e-05,
      "loss": 0.6405,
      "step": 396
    },
    {
      "epoch": 0.012195496574816453,
      "grad_norm": 0.3645850419998169,
      "learning_rate": 1.9998976851012353e-05,
      "loss": 0.6921,
      "step": 397
    },
    {
      "epoch": 0.012226215709765613,
      "grad_norm": 0.3746393918991089,
      "learning_rate": 1.9998969926284756e-05,
      "loss": 0.6901,
      "step": 398
    },
    {
      "epoch": 0.012256934844714773,
      "grad_norm": 0.3751750886440277,
      "learning_rate": 1.9998962978203865e-05,
      "loss": 0.6872,
      "step": 399
    },
    {
      "epoch": 0.012287653979663932,
      "grad_norm": 0.36580783128738403,
      "learning_rate": 1.9998956006769696e-05,
      "loss": 0.6844,
      "step": 400
    },
    {
      "epoch": 0.012318373114613092,
      "grad_norm": 0.33628973364830017,
      "learning_rate": 1.999894901198227e-05,
      "loss": 0.5891,
      "step": 401
    },
    {
      "epoch": 0.012349092249562252,
      "grad_norm": 0.37504246830940247,
      "learning_rate": 1.9998941993841597e-05,
      "loss": 0.6494,
      "step": 402
    },
    {
      "epoch": 0.012379811384511412,
      "grad_norm": 0.4191441237926483,
      "learning_rate": 1.99989349523477e-05,
      "loss": 0.6378,
      "step": 403
    },
    {
      "epoch": 0.012410530519460571,
      "grad_norm": 0.31190699338912964,
      "learning_rate": 1.9998927887500593e-05,
      "loss": 0.6079,
      "step": 404
    },
    {
      "epoch": 0.012441249654409731,
      "grad_norm": 0.36322441697120667,
      "learning_rate": 1.999892079930029e-05,
      "loss": 0.7134,
      "step": 405
    },
    {
      "epoch": 0.012471968789358892,
      "grad_norm": 0.38948509097099304,
      "learning_rate": 1.9998913687746807e-05,
      "loss": 0.6873,
      "step": 406
    },
    {
      "epoch": 0.012502687924308052,
      "grad_norm": 0.346432626247406,
      "learning_rate": 1.999890655284017e-05,
      "loss": 0.6548,
      "step": 407
    },
    {
      "epoch": 0.012533407059257212,
      "grad_norm": 0.4184305965900421,
      "learning_rate": 1.9998899394580378e-05,
      "loss": 0.6886,
      "step": 408
    },
    {
      "epoch": 0.012564126194206372,
      "grad_norm": 0.3532783091068268,
      "learning_rate": 1.9998892212967465e-05,
      "loss": 0.7087,
      "step": 409
    },
    {
      "epoch": 0.012594845329155531,
      "grad_norm": 0.35029298067092896,
      "learning_rate": 1.9998885008001437e-05,
      "loss": 0.6724,
      "step": 410
    },
    {
      "epoch": 0.012625564464104691,
      "grad_norm": 0.4311799705028534,
      "learning_rate": 1.9998877779682318e-05,
      "loss": 0.6089,
      "step": 411
    },
    {
      "epoch": 0.01265628359905385,
      "grad_norm": 0.3698045611381531,
      "learning_rate": 1.9998870528010118e-05,
      "loss": 0.6595,
      "step": 412
    },
    {
      "epoch": 0.01268700273400301,
      "grad_norm": 0.385349303483963,
      "learning_rate": 1.999886325298486e-05,
      "loss": 0.6558,
      "step": 413
    },
    {
      "epoch": 0.01271772186895217,
      "grad_norm": 0.3399409055709839,
      "learning_rate": 1.999885595460656e-05,
      "loss": 0.606,
      "step": 414
    },
    {
      "epoch": 0.01274844100390133,
      "grad_norm": 0.3290490508079529,
      "learning_rate": 1.9998848632875232e-05,
      "loss": 0.6109,
      "step": 415
    },
    {
      "epoch": 0.01277916013885049,
      "grad_norm": 0.43345990777015686,
      "learning_rate": 1.9998841287790897e-05,
      "loss": 0.6037,
      "step": 416
    },
    {
      "epoch": 0.01280987927379965,
      "grad_norm": 0.3873814046382904,
      "learning_rate": 1.9998833919353565e-05,
      "loss": 0.7078,
      "step": 417
    },
    {
      "epoch": 0.012840598408748809,
      "grad_norm": 0.39010190963745117,
      "learning_rate": 1.999882652756326e-05,
      "loss": 0.7128,
      "step": 418
    },
    {
      "epoch": 0.012871317543697969,
      "grad_norm": 0.36289942264556885,
      "learning_rate": 1.999881911242e-05,
      "loss": 0.6815,
      "step": 419
    },
    {
      "epoch": 0.012902036678647128,
      "grad_norm": 0.36228346824645996,
      "learning_rate": 1.9998811673923796e-05,
      "loss": 0.5598,
      "step": 420
    },
    {
      "epoch": 0.01293275581359629,
      "grad_norm": 0.3516004681587219,
      "learning_rate": 1.999880421207467e-05,
      "loss": 0.6214,
      "step": 421
    },
    {
      "epoch": 0.01296347494854545,
      "grad_norm": 0.3334968090057373,
      "learning_rate": 1.999879672687264e-05,
      "loss": 0.6706,
      "step": 422
    },
    {
      "epoch": 0.01299419408349461,
      "grad_norm": 0.43286290764808655,
      "learning_rate": 1.9998789218317723e-05,
      "loss": 0.6315,
      "step": 423
    },
    {
      "epoch": 0.013024913218443769,
      "grad_norm": 0.40665122866630554,
      "learning_rate": 1.999878168640993e-05,
      "loss": 0.6175,
      "step": 424
    },
    {
      "epoch": 0.013055632353392929,
      "grad_norm": 0.3742751181125641,
      "learning_rate": 1.999877413114929e-05,
      "loss": 0.563,
      "step": 425
    },
    {
      "epoch": 0.013086351488342089,
      "grad_norm": 0.4124602973461151,
      "learning_rate": 1.9998766552535813e-05,
      "loss": 0.7052,
      "step": 426
    },
    {
      "epoch": 0.013117070623291248,
      "grad_norm": 0.3557966947555542,
      "learning_rate": 1.9998758950569516e-05,
      "loss": 0.7493,
      "step": 427
    },
    {
      "epoch": 0.013147789758240408,
      "grad_norm": 0.3962048590183258,
      "learning_rate": 1.999875132525042e-05,
      "loss": 0.6723,
      "step": 428
    },
    {
      "epoch": 0.013178508893189568,
      "grad_norm": 0.3799072206020355,
      "learning_rate": 1.9998743676578547e-05,
      "loss": 0.7543,
      "step": 429
    },
    {
      "epoch": 0.013209228028138727,
      "grad_norm": 0.3397122621536255,
      "learning_rate": 1.9998736004553904e-05,
      "loss": 0.655,
      "step": 430
    },
    {
      "epoch": 0.013239947163087887,
      "grad_norm": 0.33056625723838806,
      "learning_rate": 1.9998728309176515e-05,
      "loss": 0.6709,
      "step": 431
    },
    {
      "epoch": 0.013270666298037047,
      "grad_norm": 0.37026017904281616,
      "learning_rate": 1.99987205904464e-05,
      "loss": 0.6711,
      "step": 432
    },
    {
      "epoch": 0.013301385432986207,
      "grad_norm": 0.4748310446739197,
      "learning_rate": 1.9998712848363577e-05,
      "loss": 0.6709,
      "step": 433
    },
    {
      "epoch": 0.013332104567935366,
      "grad_norm": 0.31772613525390625,
      "learning_rate": 1.999870508292806e-05,
      "loss": 0.6029,
      "step": 434
    },
    {
      "epoch": 0.013362823702884526,
      "grad_norm": 0.3760957717895508,
      "learning_rate": 1.9998697294139866e-05,
      "loss": 0.6413,
      "step": 435
    },
    {
      "epoch": 0.013393542837833687,
      "grad_norm": 0.3804575502872467,
      "learning_rate": 1.9998689481999015e-05,
      "loss": 0.6301,
      "step": 436
    },
    {
      "epoch": 0.013424261972782847,
      "grad_norm": 0.3949744403362274,
      "learning_rate": 1.999868164650553e-05,
      "loss": 0.7035,
      "step": 437
    },
    {
      "epoch": 0.013454981107732007,
      "grad_norm": 0.36304038763046265,
      "learning_rate": 1.999867378765943e-05,
      "loss": 0.6092,
      "step": 438
    },
    {
      "epoch": 0.013485700242681167,
      "grad_norm": 0.33922120928764343,
      "learning_rate": 1.999866590546072e-05,
      "loss": 0.6859,
      "step": 439
    },
    {
      "epoch": 0.013516419377630326,
      "grad_norm": 0.3809610903263092,
      "learning_rate": 1.9998657999909432e-05,
      "loss": 0.6901,
      "step": 440
    },
    {
      "epoch": 0.013547138512579486,
      "grad_norm": 0.340664267539978,
      "learning_rate": 1.999865007100558e-05,
      "loss": 0.5094,
      "step": 441
    },
    {
      "epoch": 0.013577857647528646,
      "grad_norm": 0.34022846817970276,
      "learning_rate": 1.9998642118749184e-05,
      "loss": 0.6508,
      "step": 442
    },
    {
      "epoch": 0.013608576782477805,
      "grad_norm": 0.3372526168823242,
      "learning_rate": 1.999863414314026e-05,
      "loss": 0.5852,
      "step": 443
    },
    {
      "epoch": 0.013639295917426965,
      "grad_norm": 0.3284006416797638,
      "learning_rate": 1.9998626144178824e-05,
      "loss": 0.5451,
      "step": 444
    },
    {
      "epoch": 0.013670015052376125,
      "grad_norm": 0.3568611443042755,
      "learning_rate": 1.99986181218649e-05,
      "loss": 0.5759,
      "step": 445
    },
    {
      "epoch": 0.013700734187325285,
      "grad_norm": 0.39511221647262573,
      "learning_rate": 1.9998610076198507e-05,
      "loss": 0.6191,
      "step": 446
    },
    {
      "epoch": 0.013731453322274444,
      "grad_norm": 0.37458544969558716,
      "learning_rate": 1.9998602007179662e-05,
      "loss": 0.731,
      "step": 447
    },
    {
      "epoch": 0.013762172457223604,
      "grad_norm": 0.35774555802345276,
      "learning_rate": 1.9998593914808383e-05,
      "loss": 0.6403,
      "step": 448
    },
    {
      "epoch": 0.013792891592172764,
      "grad_norm": 0.3269951045513153,
      "learning_rate": 1.999858579908469e-05,
      "loss": 0.534,
      "step": 449
    },
    {
      "epoch": 0.013823610727121923,
      "grad_norm": 0.36316394805908203,
      "learning_rate": 1.99985776600086e-05,
      "loss": 0.6796,
      "step": 450
    },
    {
      "epoch": 0.013854329862071083,
      "grad_norm": 0.45881199836730957,
      "learning_rate": 1.9998569497580137e-05,
      "loss": 0.6818,
      "step": 451
    },
    {
      "epoch": 0.013885048997020245,
      "grad_norm": 0.3773094117641449,
      "learning_rate": 1.999856131179931e-05,
      "loss": 0.5793,
      "step": 452
    },
    {
      "epoch": 0.013915768131969404,
      "grad_norm": 0.4114103615283966,
      "learning_rate": 1.999855310266615e-05,
      "loss": 0.6635,
      "step": 453
    },
    {
      "epoch": 0.013946487266918564,
      "grad_norm": 0.39250558614730835,
      "learning_rate": 1.999854487018067e-05,
      "loss": 0.6543,
      "step": 454
    },
    {
      "epoch": 0.013977206401867724,
      "grad_norm": 0.39579471945762634,
      "learning_rate": 1.999853661434289e-05,
      "loss": 0.6709,
      "step": 455
    },
    {
      "epoch": 0.014007925536816884,
      "grad_norm": 0.33862248063087463,
      "learning_rate": 1.999852833515283e-05,
      "loss": 0.6579,
      "step": 456
    },
    {
      "epoch": 0.014038644671766043,
      "grad_norm": 0.36259809136390686,
      "learning_rate": 1.9998520032610507e-05,
      "loss": 0.6782,
      "step": 457
    },
    {
      "epoch": 0.014069363806715203,
      "grad_norm": 0.4477958083152771,
      "learning_rate": 1.9998511706715944e-05,
      "loss": 0.6075,
      "step": 458
    },
    {
      "epoch": 0.014100082941664363,
      "grad_norm": 0.4580737054347992,
      "learning_rate": 1.999850335746916e-05,
      "loss": 0.6711,
      "step": 459
    },
    {
      "epoch": 0.014130802076613522,
      "grad_norm": 0.3472817540168762,
      "learning_rate": 1.999849498487017e-05,
      "loss": 0.6435,
      "step": 460
    },
    {
      "epoch": 0.014161521211562682,
      "grad_norm": 0.3777022063732147,
      "learning_rate": 1.9998486588919e-05,
      "loss": 0.6518,
      "step": 461
    },
    {
      "epoch": 0.014192240346511842,
      "grad_norm": 0.35256606340408325,
      "learning_rate": 1.9998478169615662e-05,
      "loss": 0.6282,
      "step": 462
    },
    {
      "epoch": 0.014222959481461002,
      "grad_norm": 0.3950614035129547,
      "learning_rate": 1.9998469726960183e-05,
      "loss": 0.6714,
      "step": 463
    },
    {
      "epoch": 0.014253678616410161,
      "grad_norm": 0.3608599603176117,
      "learning_rate": 1.9998461260952577e-05,
      "loss": 0.6027,
      "step": 464
    },
    {
      "epoch": 0.014284397751359321,
      "grad_norm": 1.1909950971603394,
      "learning_rate": 1.999845277159287e-05,
      "loss": 0.6617,
      "step": 465
    },
    {
      "epoch": 0.01431511688630848,
      "grad_norm": 0.3181091845035553,
      "learning_rate": 1.9998444258881077e-05,
      "loss": 0.6252,
      "step": 466
    },
    {
      "epoch": 0.014345836021257642,
      "grad_norm": 0.3597394526004791,
      "learning_rate": 1.999843572281722e-05,
      "loss": 0.6043,
      "step": 467
    },
    {
      "epoch": 0.014376555156206802,
      "grad_norm": 0.3624703884124756,
      "learning_rate": 1.9998427163401314e-05,
      "loss": 0.5565,
      "step": 468
    },
    {
      "epoch": 0.014407274291155962,
      "grad_norm": 0.354559987783432,
      "learning_rate": 1.9998418580633388e-05,
      "loss": 0.6388,
      "step": 469
    },
    {
      "epoch": 0.014437993426105121,
      "grad_norm": 0.39622339606285095,
      "learning_rate": 1.9998409974513455e-05,
      "loss": 0.6887,
      "step": 470
    },
    {
      "epoch": 0.014468712561054281,
      "grad_norm": 0.683638870716095,
      "learning_rate": 1.9998401345041535e-05,
      "loss": 0.646,
      "step": 471
    },
    {
      "epoch": 0.01449943169600344,
      "grad_norm": 0.3551875352859497,
      "learning_rate": 1.9998392692217655e-05,
      "loss": 0.6936,
      "step": 472
    },
    {
      "epoch": 0.0145301508309526,
      "grad_norm": 0.35588881373405457,
      "learning_rate": 1.9998384016041826e-05,
      "loss": 0.6654,
      "step": 473
    },
    {
      "epoch": 0.01456086996590176,
      "grad_norm": 0.33561286330223083,
      "learning_rate": 1.9998375316514077e-05,
      "loss": 0.6105,
      "step": 474
    },
    {
      "epoch": 0.01459158910085092,
      "grad_norm": 0.6108133792877197,
      "learning_rate": 1.999836659363442e-05,
      "loss": 0.734,
      "step": 475
    },
    {
      "epoch": 0.01462230823580008,
      "grad_norm": 0.3363146185874939,
      "learning_rate": 1.9998357847402884e-05,
      "loss": 0.6213,
      "step": 476
    },
    {
      "epoch": 0.01465302737074924,
      "grad_norm": 0.4399028420448303,
      "learning_rate": 1.9998349077819484e-05,
      "loss": 0.6105,
      "step": 477
    },
    {
      "epoch": 0.014683746505698399,
      "grad_norm": 0.34152963757514954,
      "learning_rate": 1.9998340284884235e-05,
      "loss": 0.6596,
      "step": 478
    },
    {
      "epoch": 0.014714465640647559,
      "grad_norm": 0.3742964267730713,
      "learning_rate": 1.9998331468597172e-05,
      "loss": 0.7002,
      "step": 479
    },
    {
      "epoch": 0.014745184775596719,
      "grad_norm": 0.3924769163131714,
      "learning_rate": 1.9998322628958306e-05,
      "loss": 0.5889,
      "step": 480
    },
    {
      "epoch": 0.014775903910545878,
      "grad_norm": 0.4139409065246582,
      "learning_rate": 1.9998313765967656e-05,
      "loss": 0.5764,
      "step": 481
    },
    {
      "epoch": 0.01480662304549504,
      "grad_norm": 0.3535204231739044,
      "learning_rate": 1.999830487962525e-05,
      "loss": 0.5987,
      "step": 482
    },
    {
      "epoch": 0.0148373421804442,
      "grad_norm": 0.37848347425460815,
      "learning_rate": 1.99982959699311e-05,
      "loss": 0.68,
      "step": 483
    },
    {
      "epoch": 0.014868061315393359,
      "grad_norm": 0.4101581871509552,
      "learning_rate": 1.9998287036885235e-05,
      "loss": 0.6625,
      "step": 484
    },
    {
      "epoch": 0.014898780450342519,
      "grad_norm": 0.360139399766922,
      "learning_rate": 1.999827808048767e-05,
      "loss": 0.7029,
      "step": 485
    },
    {
      "epoch": 0.014929499585291679,
      "grad_norm": 0.5190515518188477,
      "learning_rate": 1.999826910073843e-05,
      "loss": 0.6072,
      "step": 486
    },
    {
      "epoch": 0.014960218720240838,
      "grad_norm": 0.40456128120422363,
      "learning_rate": 1.9998260097637537e-05,
      "loss": 0.6654,
      "step": 487
    },
    {
      "epoch": 0.014990937855189998,
      "grad_norm": 0.4523564577102661,
      "learning_rate": 1.9998251071185005e-05,
      "loss": 0.6575,
      "step": 488
    },
    {
      "epoch": 0.015021656990139158,
      "grad_norm": 0.38104692101478577,
      "learning_rate": 1.999824202138086e-05,
      "loss": 0.6989,
      "step": 489
    },
    {
      "epoch": 0.015052376125088317,
      "grad_norm": 0.35218968987464905,
      "learning_rate": 1.9998232948225123e-05,
      "loss": 0.7114,
      "step": 490
    },
    {
      "epoch": 0.015083095260037477,
      "grad_norm": 0.3803866505622864,
      "learning_rate": 1.9998223851717816e-05,
      "loss": 0.6345,
      "step": 491
    },
    {
      "epoch": 0.015113814394986637,
      "grad_norm": 0.57049560546875,
      "learning_rate": 1.9998214731858956e-05,
      "loss": 0.5909,
      "step": 492
    },
    {
      "epoch": 0.015144533529935797,
      "grad_norm": 0.3569631576538086,
      "learning_rate": 1.999820558864857e-05,
      "loss": 0.6669,
      "step": 493
    },
    {
      "epoch": 0.015175252664884956,
      "grad_norm": 0.3685276508331299,
      "learning_rate": 1.9998196422086672e-05,
      "loss": 0.6752,
      "step": 494
    },
    {
      "epoch": 0.015205971799834116,
      "grad_norm": 0.37512511014938354,
      "learning_rate": 1.9998187232173295e-05,
      "loss": 0.6267,
      "step": 495
    },
    {
      "epoch": 0.015236690934783276,
      "grad_norm": 0.3476499617099762,
      "learning_rate": 1.9998178018908446e-05,
      "loss": 0.5931,
      "step": 496
    },
    {
      "epoch": 0.015267410069732437,
      "grad_norm": 0.5179610848426819,
      "learning_rate": 1.9998168782292163e-05,
      "loss": 0.698,
      "step": 497
    },
    {
      "epoch": 0.015298129204681597,
      "grad_norm": 0.3833017647266388,
      "learning_rate": 1.9998159522324448e-05,
      "loss": 0.703,
      "step": 498
    },
    {
      "epoch": 0.015328848339630757,
      "grad_norm": 0.38522037863731384,
      "learning_rate": 1.999815023900534e-05,
      "loss": 0.6898,
      "step": 499
    },
    {
      "epoch": 0.015359567474579916,
      "grad_norm": 0.4121200144290924,
      "learning_rate": 1.9998140932334854e-05,
      "loss": 0.6283,
      "step": 500
    },
    {
      "epoch": 0.015390286609529076,
      "grad_norm": 0.32847708463668823,
      "learning_rate": 1.999813160231301e-05,
      "loss": 0.6833,
      "step": 501
    },
    {
      "epoch": 0.015421005744478236,
      "grad_norm": 0.33107444643974304,
      "learning_rate": 1.999812224893983e-05,
      "loss": 0.6341,
      "step": 502
    },
    {
      "epoch": 0.015451724879427396,
      "grad_norm": 0.3629991114139557,
      "learning_rate": 1.9998112872215342e-05,
      "loss": 0.7044,
      "step": 503
    },
    {
      "epoch": 0.015482444014376555,
      "grad_norm": 0.37641698122024536,
      "learning_rate": 1.999810347213956e-05,
      "loss": 0.6606,
      "step": 504
    },
    {
      "epoch": 0.015513163149325715,
      "grad_norm": 0.37335672974586487,
      "learning_rate": 1.9998094048712507e-05,
      "loss": 0.6255,
      "step": 505
    },
    {
      "epoch": 0.015543882284274875,
      "grad_norm": 0.36234939098358154,
      "learning_rate": 1.999808460193421e-05,
      "loss": 0.694,
      "step": 506
    },
    {
      "epoch": 0.015574601419224034,
      "grad_norm": 0.42407071590423584,
      "learning_rate": 1.9998075131804685e-05,
      "loss": 0.7052,
      "step": 507
    },
    {
      "epoch": 0.015605320554173194,
      "grad_norm": 0.42430660128593445,
      "learning_rate": 1.999806563832396e-05,
      "loss": 0.6378,
      "step": 508
    },
    {
      "epoch": 0.015636039689122354,
      "grad_norm": 0.3993668556213379,
      "learning_rate": 1.9998056121492057e-05,
      "loss": 0.6179,
      "step": 509
    },
    {
      "epoch": 0.015666758824071515,
      "grad_norm": 0.3538491129875183,
      "learning_rate": 1.999804658130899e-05,
      "loss": 0.614,
      "step": 510
    },
    {
      "epoch": 0.015697477959020673,
      "grad_norm": 0.39544254541397095,
      "learning_rate": 1.999803701777479e-05,
      "loss": 0.6662,
      "step": 511
    },
    {
      "epoch": 0.015728197093969835,
      "grad_norm": 0.35190457105636597,
      "learning_rate": 1.9998027430889476e-05,
      "loss": 0.6239,
      "step": 512
    },
    {
      "epoch": 0.015758916228918993,
      "grad_norm": 0.3516015112400055,
      "learning_rate": 1.9998017820653072e-05,
      "loss": 0.6962,
      "step": 513
    },
    {
      "epoch": 0.015789635363868154,
      "grad_norm": 0.3892490565776825,
      "learning_rate": 1.9998008187065592e-05,
      "loss": 0.6338,
      "step": 514
    },
    {
      "epoch": 0.015820354498817312,
      "grad_norm": 0.32652202248573303,
      "learning_rate": 1.9997998530127075e-05,
      "loss": 0.5617,
      "step": 515
    },
    {
      "epoch": 0.015851073633766474,
      "grad_norm": 0.3441597819328308,
      "learning_rate": 1.999798884983753e-05,
      "loss": 0.626,
      "step": 516
    },
    {
      "epoch": 0.01588179276871563,
      "grad_norm": 0.3360462188720703,
      "learning_rate": 1.9997979146196985e-05,
      "loss": 0.6315,
      "step": 517
    },
    {
      "epoch": 0.015912511903664793,
      "grad_norm": 2.5117130279541016,
      "learning_rate": 1.9997969419205458e-05,
      "loss": 0.6744,
      "step": 518
    },
    {
      "epoch": 0.01594323103861395,
      "grad_norm": 0.3741868734359741,
      "learning_rate": 1.9997959668862977e-05,
      "loss": 0.6908,
      "step": 519
    },
    {
      "epoch": 0.015973950173563112,
      "grad_norm": 0.3500064015388489,
      "learning_rate": 1.9997949895169567e-05,
      "loss": 0.4988,
      "step": 520
    },
    {
      "epoch": 0.016004669308512274,
      "grad_norm": 0.396871417760849,
      "learning_rate": 1.999794009812524e-05,
      "loss": 0.6251,
      "step": 521
    },
    {
      "epoch": 0.016035388443461432,
      "grad_norm": 0.380485862493515,
      "learning_rate": 1.999793027773003e-05,
      "loss": 0.5989,
      "step": 522
    },
    {
      "epoch": 0.016066107578410593,
      "grad_norm": 0.5101944804191589,
      "learning_rate": 1.9997920433983956e-05,
      "loss": 0.7179,
      "step": 523
    },
    {
      "epoch": 0.01609682671335975,
      "grad_norm": 0.42518511414527893,
      "learning_rate": 1.9997910566887037e-05,
      "loss": 0.5832,
      "step": 524
    },
    {
      "epoch": 0.016127545848308913,
      "grad_norm": 0.371922105550766,
      "learning_rate": 1.9997900676439303e-05,
      "loss": 0.6074,
      "step": 525
    },
    {
      "epoch": 0.01615826498325807,
      "grad_norm": 0.37057992815971375,
      "learning_rate": 1.9997890762640774e-05,
      "loss": 0.6276,
      "step": 526
    },
    {
      "epoch": 0.016188984118207232,
      "grad_norm": 0.3425723910331726,
      "learning_rate": 1.999788082549147e-05,
      "loss": 0.6603,
      "step": 527
    },
    {
      "epoch": 0.01621970325315639,
      "grad_norm": 0.3937438428401947,
      "learning_rate": 1.9997870864991416e-05,
      "loss": 0.648,
      "step": 528
    },
    {
      "epoch": 0.01625042238810555,
      "grad_norm": 0.42374852299690247,
      "learning_rate": 1.9997860881140644e-05,
      "loss": 0.5851,
      "step": 529
    },
    {
      "epoch": 0.01628114152305471,
      "grad_norm": 0.3818710446357727,
      "learning_rate": 1.9997850873939163e-05,
      "loss": 0.6358,
      "step": 530
    },
    {
      "epoch": 0.01631186065800387,
      "grad_norm": 0.34825989603996277,
      "learning_rate": 1.9997840843387005e-05,
      "loss": 0.696,
      "step": 531
    },
    {
      "epoch": 0.01634257979295303,
      "grad_norm": 0.5634368658065796,
      "learning_rate": 1.999783078948419e-05,
      "loss": 0.598,
      "step": 532
    },
    {
      "epoch": 0.01637329892790219,
      "grad_norm": 0.3791891038417816,
      "learning_rate": 1.9997820712230745e-05,
      "loss": 0.6235,
      "step": 533
    },
    {
      "epoch": 0.01640401806285135,
      "grad_norm": 0.3309478163719177,
      "learning_rate": 1.999781061162669e-05,
      "loss": 0.5736,
      "step": 534
    },
    {
      "epoch": 0.01643473719780051,
      "grad_norm": 0.41343048214912415,
      "learning_rate": 1.999780048767205e-05,
      "loss": 0.7395,
      "step": 535
    },
    {
      "epoch": 0.01646545633274967,
      "grad_norm": 0.4153267741203308,
      "learning_rate": 1.999779034036685e-05,
      "loss": 0.6646,
      "step": 536
    },
    {
      "epoch": 0.01649617546769883,
      "grad_norm": 0.39774152636528015,
      "learning_rate": 1.999778016971111e-05,
      "loss": 0.683,
      "step": 537
    },
    {
      "epoch": 0.01652689460264799,
      "grad_norm": 0.35458850860595703,
      "learning_rate": 1.999776997570486e-05,
      "loss": 0.6235,
      "step": 538
    },
    {
      "epoch": 0.01655761373759715,
      "grad_norm": 0.3556102514266968,
      "learning_rate": 1.9997759758348118e-05,
      "loss": 0.7218,
      "step": 539
    },
    {
      "epoch": 0.01658833287254631,
      "grad_norm": 0.4062642455101013,
      "learning_rate": 1.999774951764091e-05,
      "loss": 0.5745,
      "step": 540
    },
    {
      "epoch": 0.016619052007495468,
      "grad_norm": 0.3656878173351288,
      "learning_rate": 1.999773925358326e-05,
      "loss": 0.6394,
      "step": 541
    },
    {
      "epoch": 0.01664977114244463,
      "grad_norm": 0.3587823212146759,
      "learning_rate": 1.9997728966175192e-05,
      "loss": 0.6091,
      "step": 542
    },
    {
      "epoch": 0.016680490277393788,
      "grad_norm": 0.4865284562110901,
      "learning_rate": 1.9997718655416726e-05,
      "loss": 0.646,
      "step": 543
    },
    {
      "epoch": 0.01671120941234295,
      "grad_norm": 0.353466272354126,
      "learning_rate": 1.9997708321307896e-05,
      "loss": 0.6551,
      "step": 544
    },
    {
      "epoch": 0.016741928547292107,
      "grad_norm": 0.3422155976295471,
      "learning_rate": 1.9997697963848716e-05,
      "loss": 0.6432,
      "step": 545
    },
    {
      "epoch": 0.01677264768224127,
      "grad_norm": 0.35569289326667786,
      "learning_rate": 1.9997687583039216e-05,
      "loss": 0.6861,
      "step": 546
    },
    {
      "epoch": 0.016803366817190427,
      "grad_norm": 0.4082132875919342,
      "learning_rate": 1.9997677178879417e-05,
      "loss": 0.6735,
      "step": 547
    },
    {
      "epoch": 0.016834085952139588,
      "grad_norm": 0.37187737226486206,
      "learning_rate": 1.9997666751369345e-05,
      "loss": 0.7366,
      "step": 548
    },
    {
      "epoch": 0.016864805087088746,
      "grad_norm": 0.36215445399284363,
      "learning_rate": 1.9997656300509024e-05,
      "loss": 0.5643,
      "step": 549
    },
    {
      "epoch": 0.016895524222037907,
      "grad_norm": 0.3834013342857361,
      "learning_rate": 1.9997645826298478e-05,
      "loss": 0.7153,
      "step": 550
    },
    {
      "epoch": 0.01692624335698707,
      "grad_norm": 0.34866228699684143,
      "learning_rate": 1.9997635328737734e-05,
      "loss": 0.6419,
      "step": 551
    },
    {
      "epoch": 0.016956962491936227,
      "grad_norm": 0.37599804997444153,
      "learning_rate": 1.9997624807826813e-05,
      "loss": 0.6726,
      "step": 552
    },
    {
      "epoch": 0.01698768162688539,
      "grad_norm": 0.6900972127914429,
      "learning_rate": 1.999761426356574e-05,
      "loss": 0.6094,
      "step": 553
    },
    {
      "epoch": 0.017018400761834546,
      "grad_norm": 0.33605897426605225,
      "learning_rate": 1.9997603695954543e-05,
      "loss": 0.6587,
      "step": 554
    },
    {
      "epoch": 0.017049119896783708,
      "grad_norm": 0.34976935386657715,
      "learning_rate": 1.999759310499324e-05,
      "loss": 0.6358,
      "step": 555
    },
    {
      "epoch": 0.017079839031732866,
      "grad_norm": 0.3821108937263489,
      "learning_rate": 1.9997582490681867e-05,
      "loss": 0.6899,
      "step": 556
    },
    {
      "epoch": 0.017110558166682027,
      "grad_norm": 0.3232705891132355,
      "learning_rate": 1.9997571853020437e-05,
      "loss": 0.6831,
      "step": 557
    },
    {
      "epoch": 0.017141277301631185,
      "grad_norm": 0.3710523545742035,
      "learning_rate": 1.9997561192008982e-05,
      "loss": 0.6348,
      "step": 558
    },
    {
      "epoch": 0.017171996436580347,
      "grad_norm": 0.3424838185310364,
      "learning_rate": 1.999755050764752e-05,
      "loss": 0.6134,
      "step": 559
    },
    {
      "epoch": 0.017202715571529505,
      "grad_norm": 0.3667562007904053,
      "learning_rate": 1.999753979993609e-05,
      "loss": 0.6363,
      "step": 560
    },
    {
      "epoch": 0.017233434706478666,
      "grad_norm": 0.3751333951950073,
      "learning_rate": 1.9997529068874697e-05,
      "loss": 0.6536,
      "step": 561
    },
    {
      "epoch": 0.017264153841427824,
      "grad_norm": 0.3676891326904297,
      "learning_rate": 1.9997518314463383e-05,
      "loss": 0.7063,
      "step": 562
    },
    {
      "epoch": 0.017294872976376986,
      "grad_norm": 0.3435770571231842,
      "learning_rate": 1.9997507536702165e-05,
      "loss": 0.6254,
      "step": 563
    },
    {
      "epoch": 0.017325592111326144,
      "grad_norm": 0.37565135955810547,
      "learning_rate": 1.9997496735591067e-05,
      "loss": 0.6652,
      "step": 564
    },
    {
      "epoch": 0.017356311246275305,
      "grad_norm": 0.3480658531188965,
      "learning_rate": 1.9997485911130124e-05,
      "loss": 0.6396,
      "step": 565
    },
    {
      "epoch": 0.017387030381224466,
      "grad_norm": 0.34443679451942444,
      "learning_rate": 1.999747506331935e-05,
      "loss": 0.7708,
      "step": 566
    },
    {
      "epoch": 0.017417749516173624,
      "grad_norm": 0.34110283851623535,
      "learning_rate": 1.9997464192158773e-05,
      "loss": 0.6559,
      "step": 567
    },
    {
      "epoch": 0.017448468651122786,
      "grad_norm": 0.370608389377594,
      "learning_rate": 1.9997453297648422e-05,
      "loss": 0.6121,
      "step": 568
    },
    {
      "epoch": 0.017479187786071944,
      "grad_norm": 0.3690973222255707,
      "learning_rate": 1.9997442379788324e-05,
      "loss": 0.6774,
      "step": 569
    },
    {
      "epoch": 0.017509906921021105,
      "grad_norm": 0.3351481854915619,
      "learning_rate": 1.99974314385785e-05,
      "loss": 0.6453,
      "step": 570
    },
    {
      "epoch": 0.017540626055970263,
      "grad_norm": 0.33749860525131226,
      "learning_rate": 1.999742047401897e-05,
      "loss": 0.61,
      "step": 571
    },
    {
      "epoch": 0.017571345190919425,
      "grad_norm": 0.35784682631492615,
      "learning_rate": 1.9997409486109773e-05,
      "loss": 0.5679,
      "step": 572
    },
    {
      "epoch": 0.017602064325868583,
      "grad_norm": 0.4049821197986603,
      "learning_rate": 1.9997398474850926e-05,
      "loss": 0.5999,
      "step": 573
    },
    {
      "epoch": 0.017632783460817744,
      "grad_norm": 0.3599804639816284,
      "learning_rate": 1.9997387440242458e-05,
      "loss": 0.709,
      "step": 574
    },
    {
      "epoch": 0.017663502595766902,
      "grad_norm": 0.39153963327407837,
      "learning_rate": 1.9997376382284394e-05,
      "loss": 0.6476,
      "step": 575
    },
    {
      "epoch": 0.017694221730716064,
      "grad_norm": 0.36624693870544434,
      "learning_rate": 1.9997365300976753e-05,
      "loss": 0.6799,
      "step": 576
    },
    {
      "epoch": 0.01772494086566522,
      "grad_norm": 0.3636245131492615,
      "learning_rate": 1.999735419631957e-05,
      "loss": 0.6686,
      "step": 577
    },
    {
      "epoch": 0.017755660000614383,
      "grad_norm": 0.3377722501754761,
      "learning_rate": 1.9997343068312872e-05,
      "loss": 0.6324,
      "step": 578
    },
    {
      "epoch": 0.01778637913556354,
      "grad_norm": 0.37362775206565857,
      "learning_rate": 1.999733191695668e-05,
      "loss": 0.6422,
      "step": 579
    },
    {
      "epoch": 0.017817098270512702,
      "grad_norm": 0.39325955510139465,
      "learning_rate": 1.999732074225102e-05,
      "loss": 0.664,
      "step": 580
    },
    {
      "epoch": 0.01784781740546186,
      "grad_norm": 0.4099566638469696,
      "learning_rate": 1.999730954419592e-05,
      "loss": 0.7237,
      "step": 581
    },
    {
      "epoch": 0.017878536540411022,
      "grad_norm": 0.35113975405693054,
      "learning_rate": 1.9997298322791402e-05,
      "loss": 0.6564,
      "step": 582
    },
    {
      "epoch": 0.017909255675360183,
      "grad_norm": 0.379182904958725,
      "learning_rate": 1.9997287078037498e-05,
      "loss": 0.6373,
      "step": 583
    },
    {
      "epoch": 0.01793997481030934,
      "grad_norm": 0.3741150498390198,
      "learning_rate": 1.9997275809934233e-05,
      "loss": 0.6666,
      "step": 584
    },
    {
      "epoch": 0.017970693945258503,
      "grad_norm": 0.4382103383541107,
      "learning_rate": 1.999726451848163e-05,
      "loss": 0.6797,
      "step": 585
    },
    {
      "epoch": 0.01800141308020766,
      "grad_norm": 0.39685511589050293,
      "learning_rate": 1.9997253203679718e-05,
      "loss": 0.6729,
      "step": 586
    },
    {
      "epoch": 0.018032132215156822,
      "grad_norm": 0.3549593985080719,
      "learning_rate": 1.9997241865528526e-05,
      "loss": 0.5899,
      "step": 587
    },
    {
      "epoch": 0.01806285135010598,
      "grad_norm": 0.35407641530036926,
      "learning_rate": 1.9997230504028074e-05,
      "loss": 0.6364,
      "step": 588
    },
    {
      "epoch": 0.01809357048505514,
      "grad_norm": 0.349229097366333,
      "learning_rate": 1.9997219119178394e-05,
      "loss": 0.6009,
      "step": 589
    },
    {
      "epoch": 0.0181242896200043,
      "grad_norm": 0.31240102648735046,
      "learning_rate": 1.9997207710979505e-05,
      "loss": 0.6565,
      "step": 590
    },
    {
      "epoch": 0.01815500875495346,
      "grad_norm": 0.36765244603157043,
      "learning_rate": 1.9997196279431444e-05,
      "loss": 0.6724,
      "step": 591
    },
    {
      "epoch": 0.01818572788990262,
      "grad_norm": 0.38883981108665466,
      "learning_rate": 1.9997184824534233e-05,
      "loss": 0.703,
      "step": 592
    },
    {
      "epoch": 0.01821644702485178,
      "grad_norm": 0.3177252411842346,
      "learning_rate": 1.9997173346287897e-05,
      "loss": 0.5853,
      "step": 593
    },
    {
      "epoch": 0.01824716615980094,
      "grad_norm": 0.35797935724258423,
      "learning_rate": 1.9997161844692465e-05,
      "loss": 0.6474,
      "step": 594
    },
    {
      "epoch": 0.0182778852947501,
      "grad_norm": 0.40504375100135803,
      "learning_rate": 1.9997150319747964e-05,
      "loss": 0.6879,
      "step": 595
    },
    {
      "epoch": 0.018308604429699258,
      "grad_norm": 0.41175809502601624,
      "learning_rate": 1.999713877145442e-05,
      "loss": 0.6556,
      "step": 596
    },
    {
      "epoch": 0.01833932356464842,
      "grad_norm": 0.36256200075149536,
      "learning_rate": 1.999712719981186e-05,
      "loss": 0.6123,
      "step": 597
    },
    {
      "epoch": 0.01837004269959758,
      "grad_norm": 1.7380759716033936,
      "learning_rate": 1.999711560482031e-05,
      "loss": 0.5889,
      "step": 598
    },
    {
      "epoch": 0.01840076183454674,
      "grad_norm": 0.35388273000717163,
      "learning_rate": 1.9997103986479805e-05,
      "loss": 0.6453,
      "step": 599
    },
    {
      "epoch": 0.0184314809694959,
      "grad_norm": 0.3751313388347626,
      "learning_rate": 1.9997092344790355e-05,
      "loss": 0.6683,
      "step": 600
    },
    {
      "epoch": 0.01846220010444506,
      "grad_norm": 0.4096778333187103,
      "learning_rate": 1.9997080679752005e-05,
      "loss": 0.6361,
      "step": 601
    },
    {
      "epoch": 0.01849291923939422,
      "grad_norm": 0.3577617406845093,
      "learning_rate": 1.999706899136477e-05,
      "loss": 0.7152,
      "step": 602
    },
    {
      "epoch": 0.018523638374343378,
      "grad_norm": 0.3427104949951172,
      "learning_rate": 1.9997057279628687e-05,
      "loss": 0.6885,
      "step": 603
    },
    {
      "epoch": 0.01855435750929254,
      "grad_norm": 0.35069340467453003,
      "learning_rate": 1.999704554454378e-05,
      "loss": 0.6332,
      "step": 604
    },
    {
      "epoch": 0.018585076644241697,
      "grad_norm": 0.3404875099658966,
      "learning_rate": 1.999703378611007e-05,
      "loss": 0.6969,
      "step": 605
    },
    {
      "epoch": 0.01861579577919086,
      "grad_norm": 0.41629061102867126,
      "learning_rate": 1.999702200432759e-05,
      "loss": 0.6799,
      "step": 606
    },
    {
      "epoch": 0.018646514914140017,
      "grad_norm": 0.3499424159526825,
      "learning_rate": 1.9997010199196368e-05,
      "loss": 0.7034,
      "step": 607
    },
    {
      "epoch": 0.018677234049089178,
      "grad_norm": 0.4346235692501068,
      "learning_rate": 1.999699837071643e-05,
      "loss": 0.6681,
      "step": 608
    },
    {
      "epoch": 0.018707953184038336,
      "grad_norm": 0.319369375705719,
      "learning_rate": 1.9996986518887803e-05,
      "loss": 0.5927,
      "step": 609
    },
    {
      "epoch": 0.018738672318987497,
      "grad_norm": 0.34068673849105835,
      "learning_rate": 1.999697464371052e-05,
      "loss": 0.5987,
      "step": 610
    },
    {
      "epoch": 0.018769391453936655,
      "grad_norm": 0.3689308166503906,
      "learning_rate": 1.99969627451846e-05,
      "loss": 0.6897,
      "step": 611
    },
    {
      "epoch": 0.018800110588885817,
      "grad_norm": 0.3898228704929352,
      "learning_rate": 1.9996950823310077e-05,
      "loss": 0.7454,
      "step": 612
    },
    {
      "epoch": 0.01883082972383498,
      "grad_norm": 0.38592562079429626,
      "learning_rate": 1.9996938878086976e-05,
      "loss": 0.6769,
      "step": 613
    },
    {
      "epoch": 0.018861548858784136,
      "grad_norm": 0.307441383600235,
      "learning_rate": 1.9996926909515328e-05,
      "loss": 0.6565,
      "step": 614
    },
    {
      "epoch": 0.018892267993733298,
      "grad_norm": 0.36085936427116394,
      "learning_rate": 1.999691491759516e-05,
      "loss": 0.6423,
      "step": 615
    },
    {
      "epoch": 0.018922987128682456,
      "grad_norm": 0.3521069586277008,
      "learning_rate": 1.9996902902326496e-05,
      "loss": 0.5909,
      "step": 616
    },
    {
      "epoch": 0.018953706263631617,
      "grad_norm": 0.4399057924747467,
      "learning_rate": 1.9996890863709367e-05,
      "loss": 0.5927,
      "step": 617
    },
    {
      "epoch": 0.018984425398580775,
      "grad_norm": 0.3735198974609375,
      "learning_rate": 1.9996878801743805e-05,
      "loss": 0.7315,
      "step": 618
    },
    {
      "epoch": 0.019015144533529937,
      "grad_norm": 0.3371661901473999,
      "learning_rate": 1.9996866716429834e-05,
      "loss": 0.6963,
      "step": 619
    },
    {
      "epoch": 0.019045863668479095,
      "grad_norm": 0.3382458984851837,
      "learning_rate": 1.999685460776748e-05,
      "loss": 0.6525,
      "step": 620
    },
    {
      "epoch": 0.019076582803428256,
      "grad_norm": 0.3707584738731384,
      "learning_rate": 1.9996842475756773e-05,
      "loss": 0.7032,
      "step": 621
    },
    {
      "epoch": 0.019107301938377414,
      "grad_norm": 0.3761541545391083,
      "learning_rate": 1.999683032039774e-05,
      "loss": 0.6864,
      "step": 622
    },
    {
      "epoch": 0.019138021073326576,
      "grad_norm": 0.39501962065696716,
      "learning_rate": 1.999681814169042e-05,
      "loss": 0.7545,
      "step": 623
    },
    {
      "epoch": 0.019168740208275734,
      "grad_norm": 0.37704703211784363,
      "learning_rate": 1.9996805939634826e-05,
      "loss": 0.6846,
      "step": 624
    },
    {
      "epoch": 0.019199459343224895,
      "grad_norm": 0.3340139389038086,
      "learning_rate": 1.9996793714230997e-05,
      "loss": 0.6824,
      "step": 625
    },
    {
      "epoch": 0.019230178478174053,
      "grad_norm": 0.39260411262512207,
      "learning_rate": 1.9996781465478956e-05,
      "loss": 0.674,
      "step": 626
    },
    {
      "epoch": 0.019260897613123214,
      "grad_norm": 0.3635219931602478,
      "learning_rate": 1.9996769193378736e-05,
      "loss": 0.692,
      "step": 627
    },
    {
      "epoch": 0.019291616748072376,
      "grad_norm": 0.4429719150066376,
      "learning_rate": 1.9996756897930362e-05,
      "loss": 0.6444,
      "step": 628
    },
    {
      "epoch": 0.019322335883021534,
      "grad_norm": 0.5513244867324829,
      "learning_rate": 1.9996744579133863e-05,
      "loss": 0.6108,
      "step": 629
    },
    {
      "epoch": 0.019353055017970695,
      "grad_norm": 0.3571275472640991,
      "learning_rate": 1.999673223698927e-05,
      "loss": 0.6533,
      "step": 630
    },
    {
      "epoch": 0.019383774152919853,
      "grad_norm": 0.5451866984367371,
      "learning_rate": 1.9996719871496614e-05,
      "loss": 0.6953,
      "step": 631
    },
    {
      "epoch": 0.019414493287869015,
      "grad_norm": 0.3355654776096344,
      "learning_rate": 1.9996707482655915e-05,
      "loss": 0.6528,
      "step": 632
    },
    {
      "epoch": 0.019445212422818173,
      "grad_norm": 0.3886340260505676,
      "learning_rate": 1.9996695070467213e-05,
      "loss": 0.6084,
      "step": 633
    },
    {
      "epoch": 0.019475931557767334,
      "grad_norm": 0.3285294473171234,
      "learning_rate": 1.9996682634930526e-05,
      "loss": 0.6433,
      "step": 634
    },
    {
      "epoch": 0.019506650692716492,
      "grad_norm": 0.344137966632843,
      "learning_rate": 1.999667017604589e-05,
      "loss": 0.6041,
      "step": 635
    },
    {
      "epoch": 0.019537369827665654,
      "grad_norm": 0.38496875762939453,
      "learning_rate": 1.9996657693813334e-05,
      "loss": 0.6424,
      "step": 636
    },
    {
      "epoch": 0.01956808896261481,
      "grad_norm": 0.37379342317581177,
      "learning_rate": 1.9996645188232887e-05,
      "loss": 0.6142,
      "step": 637
    },
    {
      "epoch": 0.019598808097563973,
      "grad_norm": 0.35943636298179626,
      "learning_rate": 1.9996632659304573e-05,
      "loss": 0.642,
      "step": 638
    },
    {
      "epoch": 0.01962952723251313,
      "grad_norm": 0.383228063583374,
      "learning_rate": 1.999662010702843e-05,
      "loss": 0.6321,
      "step": 639
    },
    {
      "epoch": 0.019660246367462293,
      "grad_norm": 0.34772342443466187,
      "learning_rate": 1.999660753140448e-05,
      "loss": 0.6929,
      "step": 640
    },
    {
      "epoch": 0.01969096550241145,
      "grad_norm": 0.37511345744132996,
      "learning_rate": 1.9996594932432755e-05,
      "loss": 0.684,
      "step": 641
    },
    {
      "epoch": 0.019721684637360612,
      "grad_norm": 0.4366251826286316,
      "learning_rate": 1.9996582310113285e-05,
      "loss": 0.678,
      "step": 642
    },
    {
      "epoch": 0.019752403772309773,
      "grad_norm": 0.4729257822036743,
      "learning_rate": 1.9996569664446098e-05,
      "loss": 0.6917,
      "step": 643
    },
    {
      "epoch": 0.01978312290725893,
      "grad_norm": 0.338461309671402,
      "learning_rate": 1.9996556995431223e-05,
      "loss": 0.6788,
      "step": 644
    },
    {
      "epoch": 0.019813842042208093,
      "grad_norm": 0.4378059208393097,
      "learning_rate": 1.9996544303068695e-05,
      "loss": 0.732,
      "step": 645
    },
    {
      "epoch": 0.01984456117715725,
      "grad_norm": 0.38162198662757874,
      "learning_rate": 1.999653158735854e-05,
      "loss": 0.6496,
      "step": 646
    },
    {
      "epoch": 0.019875280312106412,
      "grad_norm": 0.34327518939971924,
      "learning_rate": 1.9996518848300783e-05,
      "loss": 0.5781,
      "step": 647
    },
    {
      "epoch": 0.01990599944705557,
      "grad_norm": 0.655466616153717,
      "learning_rate": 1.999650608589546e-05,
      "loss": 0.603,
      "step": 648
    },
    {
      "epoch": 0.01993671858200473,
      "grad_norm": 0.4052770733833313,
      "learning_rate": 1.99964933001426e-05,
      "loss": 0.633,
      "step": 649
    },
    {
      "epoch": 0.01996743771695389,
      "grad_norm": 0.35274645686149597,
      "learning_rate": 1.9996480491042228e-05,
      "loss": 0.642,
      "step": 650
    },
    {
      "epoch": 0.01999815685190305,
      "grad_norm": 0.3503863513469696,
      "learning_rate": 1.9996467658594382e-05,
      "loss": 0.6778,
      "step": 651
    },
    {
      "epoch": 0.02002887598685221,
      "grad_norm": 0.4011728763580322,
      "learning_rate": 1.9996454802799086e-05,
      "loss": 0.6183,
      "step": 652
    },
    {
      "epoch": 0.02005959512180137,
      "grad_norm": 0.35220634937286377,
      "learning_rate": 1.999644192365637e-05,
      "loss": 0.6796,
      "step": 653
    },
    {
      "epoch": 0.02009031425675053,
      "grad_norm": 0.35523271560668945,
      "learning_rate": 1.9996429021166266e-05,
      "loss": 0.6267,
      "step": 654
    },
    {
      "epoch": 0.02012103339169969,
      "grad_norm": 0.35560765862464905,
      "learning_rate": 1.999641609532881e-05,
      "loss": 0.6581,
      "step": 655
    },
    {
      "epoch": 0.020151752526648848,
      "grad_norm": 0.3332947790622711,
      "learning_rate": 1.9996403146144017e-05,
      "loss": 0.6577,
      "step": 656
    },
    {
      "epoch": 0.02018247166159801,
      "grad_norm": 0.4000426232814789,
      "learning_rate": 1.999639017361193e-05,
      "loss": 0.5903,
      "step": 657
    },
    {
      "epoch": 0.02021319079654717,
      "grad_norm": 0.3624047338962555,
      "learning_rate": 1.999637717773258e-05,
      "loss": 0.6296,
      "step": 658
    },
    {
      "epoch": 0.02024390993149633,
      "grad_norm": 0.3693142831325531,
      "learning_rate": 1.999636415850599e-05,
      "loss": 0.6395,
      "step": 659
    },
    {
      "epoch": 0.02027462906644549,
      "grad_norm": 0.3308466076850891,
      "learning_rate": 1.999635111593219e-05,
      "loss": 0.6513,
      "step": 660
    },
    {
      "epoch": 0.02030534820139465,
      "grad_norm": 0.4649997055530548,
      "learning_rate": 1.9996338050011218e-05,
      "loss": 0.6194,
      "step": 661
    },
    {
      "epoch": 0.02033606733634381,
      "grad_norm": 0.37187445163726807,
      "learning_rate": 1.9996324960743098e-05,
      "loss": 0.6349,
      "step": 662
    },
    {
      "epoch": 0.020366786471292968,
      "grad_norm": 0.3458600640296936,
      "learning_rate": 1.999631184812786e-05,
      "loss": 0.732,
      "step": 663
    },
    {
      "epoch": 0.02039750560624213,
      "grad_norm": 0.3875254690647125,
      "learning_rate": 1.9996298712165544e-05,
      "loss": 0.6638,
      "step": 664
    },
    {
      "epoch": 0.020428224741191287,
      "grad_norm": 0.33852434158325195,
      "learning_rate": 1.999628555285617e-05,
      "loss": 0.6338,
      "step": 665
    },
    {
      "epoch": 0.02045894387614045,
      "grad_norm": 0.3661525249481201,
      "learning_rate": 1.9996272370199775e-05,
      "loss": 0.6487,
      "step": 666
    },
    {
      "epoch": 0.020489663011089607,
      "grad_norm": 0.43532538414001465,
      "learning_rate": 1.9996259164196386e-05,
      "loss": 0.6447,
      "step": 667
    },
    {
      "epoch": 0.020520382146038768,
      "grad_norm": 0.34020864963531494,
      "learning_rate": 1.999624593484604e-05,
      "loss": 0.6866,
      "step": 668
    },
    {
      "epoch": 0.020551101280987926,
      "grad_norm": 0.34931477904319763,
      "learning_rate": 1.9996232682148756e-05,
      "loss": 0.631,
      "step": 669
    },
    {
      "epoch": 0.020581820415937088,
      "grad_norm": 0.35504257678985596,
      "learning_rate": 1.999621940610458e-05,
      "loss": 0.6354,
      "step": 670
    },
    {
      "epoch": 0.020612539550886246,
      "grad_norm": 0.3335193693637848,
      "learning_rate": 1.999620610671353e-05,
      "loss": 0.6088,
      "step": 671
    },
    {
      "epoch": 0.020643258685835407,
      "grad_norm": 0.3360497057437897,
      "learning_rate": 1.9996192783975642e-05,
      "loss": 0.5768,
      "step": 672
    },
    {
      "epoch": 0.02067397782078457,
      "grad_norm": 0.35713326930999756,
      "learning_rate": 1.9996179437890954e-05,
      "loss": 0.6847,
      "step": 673
    },
    {
      "epoch": 0.020704696955733726,
      "grad_norm": 0.5350825786590576,
      "learning_rate": 1.9996166068459483e-05,
      "loss": 0.6799,
      "step": 674
    },
    {
      "epoch": 0.020735416090682888,
      "grad_norm": 0.3860687017440796,
      "learning_rate": 1.9996152675681274e-05,
      "loss": 0.68,
      "step": 675
    },
    {
      "epoch": 0.020766135225632046,
      "grad_norm": 0.365662544965744,
      "learning_rate": 1.999613925955635e-05,
      "loss": 0.6335,
      "step": 676
    },
    {
      "epoch": 0.020796854360581207,
      "grad_norm": 0.36162814497947693,
      "learning_rate": 1.9996125820084745e-05,
      "loss": 0.6509,
      "step": 677
    },
    {
      "epoch": 0.020827573495530365,
      "grad_norm": 0.4481048882007599,
      "learning_rate": 1.999611235726649e-05,
      "loss": 0.6778,
      "step": 678
    },
    {
      "epoch": 0.020858292630479527,
      "grad_norm": 0.37087756395339966,
      "learning_rate": 1.9996098871101617e-05,
      "loss": 0.6782,
      "step": 679
    },
    {
      "epoch": 0.020889011765428685,
      "grad_norm": 0.43033871054649353,
      "learning_rate": 1.9996085361590155e-05,
      "loss": 0.6212,
      "step": 680
    },
    {
      "epoch": 0.020919730900377846,
      "grad_norm": 0.3877839744091034,
      "learning_rate": 1.999607182873214e-05,
      "loss": 0.6683,
      "step": 681
    },
    {
      "epoch": 0.020950450035327004,
      "grad_norm": 0.3336257338523865,
      "learning_rate": 1.99960582725276e-05,
      "loss": 0.6524,
      "step": 682
    },
    {
      "epoch": 0.020981169170276166,
      "grad_norm": 0.3160320222377777,
      "learning_rate": 1.9996044692976567e-05,
      "loss": 0.5913,
      "step": 683
    },
    {
      "epoch": 0.021011888305225324,
      "grad_norm": 0.33931928873062134,
      "learning_rate": 1.9996031090079075e-05,
      "loss": 0.5923,
      "step": 684
    },
    {
      "epoch": 0.021042607440174485,
      "grad_norm": 0.33188575506210327,
      "learning_rate": 1.9996017463835153e-05,
      "loss": 0.6683,
      "step": 685
    },
    {
      "epoch": 0.021073326575123643,
      "grad_norm": 0.35781964659690857,
      "learning_rate": 1.9996003814244835e-05,
      "loss": 0.6404,
      "step": 686
    },
    {
      "epoch": 0.021104045710072804,
      "grad_norm": 0.3614464998245239,
      "learning_rate": 1.9995990141308154e-05,
      "loss": 0.6202,
      "step": 687
    },
    {
      "epoch": 0.021134764845021962,
      "grad_norm": 0.358516663312912,
      "learning_rate": 1.9995976445025134e-05,
      "loss": 0.6329,
      "step": 688
    },
    {
      "epoch": 0.021165483979971124,
      "grad_norm": 0.361712783575058,
      "learning_rate": 1.9995962725395817e-05,
      "loss": 0.6538,
      "step": 689
    },
    {
      "epoch": 0.021196203114920285,
      "grad_norm": 0.37210845947265625,
      "learning_rate": 1.999594898242023e-05,
      "loss": 0.703,
      "step": 690
    },
    {
      "epoch": 0.021226922249869443,
      "grad_norm": 0.37681689858436584,
      "learning_rate": 1.999593521609841e-05,
      "loss": 0.6056,
      "step": 691
    },
    {
      "epoch": 0.021257641384818605,
      "grad_norm": 0.46939870715141296,
      "learning_rate": 1.999592142643038e-05,
      "loss": 0.7577,
      "step": 692
    },
    {
      "epoch": 0.021288360519767763,
      "grad_norm": 0.36975857615470886,
      "learning_rate": 1.999590761341618e-05,
      "loss": 0.7174,
      "step": 693
    },
    {
      "epoch": 0.021319079654716924,
      "grad_norm": 0.34185007214546204,
      "learning_rate": 1.9995893777055836e-05,
      "loss": 0.6457,
      "step": 694
    },
    {
      "epoch": 0.021349798789666082,
      "grad_norm": 0.3308317959308624,
      "learning_rate": 1.999587991734939e-05,
      "loss": 0.6848,
      "step": 695
    },
    {
      "epoch": 0.021380517924615244,
      "grad_norm": 0.3272716999053955,
      "learning_rate": 1.9995866034296862e-05,
      "loss": 0.6562,
      "step": 696
    },
    {
      "epoch": 0.0214112370595644,
      "grad_norm": 0.31899935007095337,
      "learning_rate": 1.9995852127898297e-05,
      "loss": 0.6303,
      "step": 697
    },
    {
      "epoch": 0.021441956194513563,
      "grad_norm": 0.343513160943985,
      "learning_rate": 1.9995838198153715e-05,
      "loss": 0.6489,
      "step": 698
    },
    {
      "epoch": 0.02147267532946272,
      "grad_norm": 0.3756782114505768,
      "learning_rate": 1.9995824245063157e-05,
      "loss": 0.6966,
      "step": 699
    },
    {
      "epoch": 0.021503394464411883,
      "grad_norm": 0.34475603699684143,
      "learning_rate": 1.9995810268626657e-05,
      "loss": 0.6059,
      "step": 700
    },
    {
      "epoch": 0.02153411359936104,
      "grad_norm": 0.3745661973953247,
      "learning_rate": 1.999579626884424e-05,
      "loss": 0.6981,
      "step": 701
    },
    {
      "epoch": 0.021564832734310202,
      "grad_norm": 0.39941927790641785,
      "learning_rate": 1.9995782245715943e-05,
      "loss": 0.6425,
      "step": 702
    },
    {
      "epoch": 0.02159555186925936,
      "grad_norm": 0.3506154417991638,
      "learning_rate": 1.9995768199241802e-05,
      "loss": 0.6518,
      "step": 703
    },
    {
      "epoch": 0.02162627100420852,
      "grad_norm": 0.36155733466148376,
      "learning_rate": 1.9995754129421844e-05,
      "loss": 0.7037,
      "step": 704
    },
    {
      "epoch": 0.021656990139157683,
      "grad_norm": 0.31318923830986023,
      "learning_rate": 1.9995740036256102e-05,
      "loss": 0.6144,
      "step": 705
    },
    {
      "epoch": 0.02168770927410684,
      "grad_norm": 0.36624830961227417,
      "learning_rate": 1.9995725919744614e-05,
      "loss": 0.6446,
      "step": 706
    },
    {
      "epoch": 0.021718428409056002,
      "grad_norm": 0.3366883397102356,
      "learning_rate": 1.9995711779887408e-05,
      "loss": 0.5609,
      "step": 707
    },
    {
      "epoch": 0.02174914754400516,
      "grad_norm": 0.34616565704345703,
      "learning_rate": 1.999569761668452e-05,
      "loss": 0.6338,
      "step": 708
    },
    {
      "epoch": 0.021779866678954322,
      "grad_norm": 0.3957144618034363,
      "learning_rate": 1.999568343013598e-05,
      "loss": 0.6372,
      "step": 709
    },
    {
      "epoch": 0.02181058581390348,
      "grad_norm": 0.33683693408966064,
      "learning_rate": 1.999566922024183e-05,
      "loss": 0.7073,
      "step": 710
    },
    {
      "epoch": 0.02184130494885264,
      "grad_norm": 0.3823423683643341,
      "learning_rate": 1.999565498700209e-05,
      "loss": 0.6907,
      "step": 711
    },
    {
      "epoch": 0.0218720240838018,
      "grad_norm": 0.4063527584075928,
      "learning_rate": 1.99956407304168e-05,
      "loss": 0.5691,
      "step": 712
    },
    {
      "epoch": 0.02190274321875096,
      "grad_norm": 0.3939085602760315,
      "learning_rate": 1.9995626450485996e-05,
      "loss": 0.6788,
      "step": 713
    },
    {
      "epoch": 0.02193346235370012,
      "grad_norm": 0.389740526676178,
      "learning_rate": 1.9995612147209706e-05,
      "loss": 0.6848,
      "step": 714
    },
    {
      "epoch": 0.02196418148864928,
      "grad_norm": 0.33408400416374207,
      "learning_rate": 1.9995597820587966e-05,
      "loss": 0.6911,
      "step": 715
    },
    {
      "epoch": 0.021994900623598438,
      "grad_norm": 0.5136900544166565,
      "learning_rate": 1.9995583470620808e-05,
      "loss": 0.68,
      "step": 716
    },
    {
      "epoch": 0.0220256197585476,
      "grad_norm": 0.34777143597602844,
      "learning_rate": 1.999556909730827e-05,
      "loss": 0.5712,
      "step": 717
    },
    {
      "epoch": 0.022056338893496757,
      "grad_norm": 0.44120004773139954,
      "learning_rate": 1.999555470065038e-05,
      "loss": 0.6556,
      "step": 718
    },
    {
      "epoch": 0.02208705802844592,
      "grad_norm": 0.34619706869125366,
      "learning_rate": 1.9995540280647177e-05,
      "loss": 0.5688,
      "step": 719
    },
    {
      "epoch": 0.02211777716339508,
      "grad_norm": 0.35979968309402466,
      "learning_rate": 1.999552583729869e-05,
      "loss": 0.6327,
      "step": 720
    },
    {
      "epoch": 0.02214849629834424,
      "grad_norm": 0.36372044682502747,
      "learning_rate": 1.9995511370604953e-05,
      "loss": 0.6747,
      "step": 721
    },
    {
      "epoch": 0.0221792154332934,
      "grad_norm": 0.3400021195411682,
      "learning_rate": 1.9995496880566e-05,
      "loss": 0.6644,
      "step": 722
    },
    {
      "epoch": 0.022209934568242558,
      "grad_norm": 0.3551691472530365,
      "learning_rate": 1.999548236718187e-05,
      "loss": 0.6554,
      "step": 723
    },
    {
      "epoch": 0.02224065370319172,
      "grad_norm": 0.5034741759300232,
      "learning_rate": 1.999546783045259e-05,
      "loss": 0.595,
      "step": 724
    },
    {
      "epoch": 0.022271372838140877,
      "grad_norm": 0.3290124237537384,
      "learning_rate": 1.9995453270378195e-05,
      "loss": 0.6337,
      "step": 725
    },
    {
      "epoch": 0.02230209197309004,
      "grad_norm": 0.32322415709495544,
      "learning_rate": 1.9995438686958725e-05,
      "loss": 0.6227,
      "step": 726
    },
    {
      "epoch": 0.022332811108039197,
      "grad_norm": 0.35580378770828247,
      "learning_rate": 1.9995424080194207e-05,
      "loss": 0.6709,
      "step": 727
    },
    {
      "epoch": 0.022363530242988358,
      "grad_norm": 0.35495415329933167,
      "learning_rate": 1.9995409450084678e-05,
      "loss": 0.6129,
      "step": 728
    },
    {
      "epoch": 0.022394249377937516,
      "grad_norm": 0.36138176918029785,
      "learning_rate": 1.9995394796630176e-05,
      "loss": 0.6723,
      "step": 729
    },
    {
      "epoch": 0.022424968512886678,
      "grad_norm": 0.41997915506362915,
      "learning_rate": 1.9995380119830727e-05,
      "loss": 0.6933,
      "step": 730
    },
    {
      "epoch": 0.022455687647835836,
      "grad_norm": 0.39947545528411865,
      "learning_rate": 1.9995365419686373e-05,
      "loss": 0.7338,
      "step": 731
    },
    {
      "epoch": 0.022486406782784997,
      "grad_norm": 0.34646695852279663,
      "learning_rate": 1.9995350696197143e-05,
      "loss": 0.6538,
      "step": 732
    },
    {
      "epoch": 0.022517125917734155,
      "grad_norm": 0.36460742354393005,
      "learning_rate": 1.9995335949363073e-05,
      "loss": 0.7014,
      "step": 733
    },
    {
      "epoch": 0.022547845052683316,
      "grad_norm": 0.3511771857738495,
      "learning_rate": 1.9995321179184198e-05,
      "loss": 0.5649,
      "step": 734
    },
    {
      "epoch": 0.022578564187632478,
      "grad_norm": 0.384949266910553,
      "learning_rate": 1.9995306385660553e-05,
      "loss": 0.5573,
      "step": 735
    },
    {
      "epoch": 0.022609283322581636,
      "grad_norm": 0.3244633972644806,
      "learning_rate": 1.9995291568792172e-05,
      "loss": 0.6293,
      "step": 736
    },
    {
      "epoch": 0.022640002457530797,
      "grad_norm": 0.3582436740398407,
      "learning_rate": 1.999527672857909e-05,
      "loss": 0.6812,
      "step": 737
    },
    {
      "epoch": 0.022670721592479955,
      "grad_norm": 0.3974528908729553,
      "learning_rate": 1.9995261865021337e-05,
      "loss": 0.6567,
      "step": 738
    },
    {
      "epoch": 0.022701440727429117,
      "grad_norm": 0.34583213925361633,
      "learning_rate": 1.9995246978118957e-05,
      "loss": 0.6519,
      "step": 739
    },
    {
      "epoch": 0.022732159862378275,
      "grad_norm": 0.35737287998199463,
      "learning_rate": 1.9995232067871976e-05,
      "loss": 0.6415,
      "step": 740
    },
    {
      "epoch": 0.022762878997327436,
      "grad_norm": 0.38277292251586914,
      "learning_rate": 1.9995217134280436e-05,
      "loss": 0.6042,
      "step": 741
    },
    {
      "epoch": 0.022793598132276594,
      "grad_norm": 0.37878045439720154,
      "learning_rate": 1.9995202177344366e-05,
      "loss": 0.6012,
      "step": 742
    },
    {
      "epoch": 0.022824317267225756,
      "grad_norm": 0.35402625799179077,
      "learning_rate": 1.9995187197063803e-05,
      "loss": 0.7019,
      "step": 743
    },
    {
      "epoch": 0.022855036402174914,
      "grad_norm": 0.34049639105796814,
      "learning_rate": 1.9995172193438782e-05,
      "loss": 0.5754,
      "step": 744
    },
    {
      "epoch": 0.022885755537124075,
      "grad_norm": 0.5275947451591492,
      "learning_rate": 1.999515716646934e-05,
      "loss": 0.6833,
      "step": 745
    },
    {
      "epoch": 0.022916474672073233,
      "grad_norm": 0.3617114722728729,
      "learning_rate": 1.999514211615551e-05,
      "loss": 0.6544,
      "step": 746
    },
    {
      "epoch": 0.022947193807022395,
      "grad_norm": 0.31442174315452576,
      "learning_rate": 1.9995127042497325e-05,
      "loss": 0.6007,
      "step": 747
    },
    {
      "epoch": 0.022977912941971552,
      "grad_norm": 0.3456467092037201,
      "learning_rate": 1.9995111945494826e-05,
      "loss": 0.6111,
      "step": 748
    },
    {
      "epoch": 0.023008632076920714,
      "grad_norm": 0.39414599537849426,
      "learning_rate": 1.9995096825148045e-05,
      "loss": 0.5804,
      "step": 749
    },
    {
      "epoch": 0.023039351211869875,
      "grad_norm": 0.4285268187522888,
      "learning_rate": 1.9995081681457016e-05,
      "loss": 0.6215,
      "step": 750
    },
    {
      "epoch": 0.023070070346819033,
      "grad_norm": 0.34765833616256714,
      "learning_rate": 1.9995066514421775e-05,
      "loss": 0.6209,
      "step": 751
    },
    {
      "epoch": 0.023100789481768195,
      "grad_norm": 0.3567025363445282,
      "learning_rate": 1.999505132404236e-05,
      "loss": 0.6387,
      "step": 752
    },
    {
      "epoch": 0.023131508616717353,
      "grad_norm": 0.3617381155490875,
      "learning_rate": 1.9995036110318804e-05,
      "loss": 0.6759,
      "step": 753
    },
    {
      "epoch": 0.023162227751666514,
      "grad_norm": 0.3386414051055908,
      "learning_rate": 1.9995020873251143e-05,
      "loss": 0.6702,
      "step": 754
    },
    {
      "epoch": 0.023192946886615672,
      "grad_norm": 0.5528104305267334,
      "learning_rate": 1.999500561283941e-05,
      "loss": 0.6896,
      "step": 755
    },
    {
      "epoch": 0.023223666021564834,
      "grad_norm": 0.375530868768692,
      "learning_rate": 1.9994990329083647e-05,
      "loss": 0.7641,
      "step": 756
    },
    {
      "epoch": 0.02325438515651399,
      "grad_norm": 0.38734525442123413,
      "learning_rate": 1.9994975021983885e-05,
      "loss": 0.5741,
      "step": 757
    },
    {
      "epoch": 0.023285104291463153,
      "grad_norm": 0.353128045797348,
      "learning_rate": 1.9994959691540163e-05,
      "loss": 0.6586,
      "step": 758
    },
    {
      "epoch": 0.02331582342641231,
      "grad_norm": 0.4162643551826477,
      "learning_rate": 1.999494433775251e-05,
      "loss": 0.6727,
      "step": 759
    },
    {
      "epoch": 0.023346542561361473,
      "grad_norm": 0.38830530643463135,
      "learning_rate": 1.999492896062097e-05,
      "loss": 0.6702,
      "step": 760
    },
    {
      "epoch": 0.02337726169631063,
      "grad_norm": 0.3813096284866333,
      "learning_rate": 1.9994913560145574e-05,
      "loss": 0.6763,
      "step": 761
    },
    {
      "epoch": 0.023407980831259792,
      "grad_norm": 0.35217440128326416,
      "learning_rate": 1.999489813632636e-05,
      "loss": 0.652,
      "step": 762
    },
    {
      "epoch": 0.02343869996620895,
      "grad_norm": 0.3833211064338684,
      "learning_rate": 1.999488268916336e-05,
      "loss": 0.6241,
      "step": 763
    },
    {
      "epoch": 0.02346941910115811,
      "grad_norm": 0.3450303375720978,
      "learning_rate": 1.9994867218656616e-05,
      "loss": 0.5678,
      "step": 764
    },
    {
      "epoch": 0.023500138236107273,
      "grad_norm": 0.401212215423584,
      "learning_rate": 1.9994851724806164e-05,
      "loss": 0.7116,
      "step": 765
    },
    {
      "epoch": 0.02353085737105643,
      "grad_norm": 0.36074939370155334,
      "learning_rate": 1.9994836207612036e-05,
      "loss": 0.717,
      "step": 766
    },
    {
      "epoch": 0.023561576506005592,
      "grad_norm": 0.35319191217422485,
      "learning_rate": 1.9994820667074267e-05,
      "loss": 0.7284,
      "step": 767
    },
    {
      "epoch": 0.02359229564095475,
      "grad_norm": 0.36707571148872375,
      "learning_rate": 1.9994805103192903e-05,
      "loss": 0.6625,
      "step": 768
    },
    {
      "epoch": 0.023623014775903912,
      "grad_norm": 0.3228600025177002,
      "learning_rate": 1.999478951596797e-05,
      "loss": 0.5961,
      "step": 769
    },
    {
      "epoch": 0.02365373391085307,
      "grad_norm": 0.3475819230079651,
      "learning_rate": 1.9994773905399504e-05,
      "loss": 0.5508,
      "step": 770
    },
    {
      "epoch": 0.02368445304580223,
      "grad_norm": 0.40725216269493103,
      "learning_rate": 1.999475827148755e-05,
      "loss": 0.6972,
      "step": 771
    },
    {
      "epoch": 0.02371517218075139,
      "grad_norm": 0.35891595482826233,
      "learning_rate": 1.999474261423214e-05,
      "loss": 0.5908,
      "step": 772
    },
    {
      "epoch": 0.02374589131570055,
      "grad_norm": 0.3445408046245575,
      "learning_rate": 1.999472693363331e-05,
      "loss": 0.5806,
      "step": 773
    },
    {
      "epoch": 0.02377661045064971,
      "grad_norm": 0.3231574296951294,
      "learning_rate": 1.9994711229691093e-05,
      "loss": 0.6987,
      "step": 774
    },
    {
      "epoch": 0.02380732958559887,
      "grad_norm": 0.34939518570899963,
      "learning_rate": 1.9994695502405538e-05,
      "loss": 0.5971,
      "step": 775
    },
    {
      "epoch": 0.023838048720548028,
      "grad_norm": 0.3990110754966736,
      "learning_rate": 1.999467975177667e-05,
      "loss": 0.6759,
      "step": 776
    },
    {
      "epoch": 0.02386876785549719,
      "grad_norm": 0.3214031457901001,
      "learning_rate": 1.9994663977804527e-05,
      "loss": 0.6156,
      "step": 777
    },
    {
      "epoch": 0.023899486990446348,
      "grad_norm": 0.34276875853538513,
      "learning_rate": 1.9994648180489153e-05,
      "loss": 0.615,
      "step": 778
    },
    {
      "epoch": 0.02393020612539551,
      "grad_norm": 0.3451148569583893,
      "learning_rate": 1.9994632359830574e-05,
      "loss": 0.6537,
      "step": 779
    },
    {
      "epoch": 0.02396092526034467,
      "grad_norm": 0.624241292476654,
      "learning_rate": 1.999461651582884e-05,
      "loss": 0.6242,
      "step": 780
    },
    {
      "epoch": 0.02399164439529383,
      "grad_norm": 0.3776779770851135,
      "learning_rate": 1.9994600648483976e-05,
      "loss": 0.6412,
      "step": 781
    },
    {
      "epoch": 0.02402236353024299,
      "grad_norm": 0.3751891851425171,
      "learning_rate": 1.9994584757796023e-05,
      "loss": 0.645,
      "step": 782
    },
    {
      "epoch": 0.024053082665192148,
      "grad_norm": 0.34398311376571655,
      "learning_rate": 1.9994568843765022e-05,
      "loss": 0.6562,
      "step": 783
    },
    {
      "epoch": 0.02408380180014131,
      "grad_norm": 0.4200153648853302,
      "learning_rate": 1.999455290639101e-05,
      "loss": 0.7578,
      "step": 784
    },
    {
      "epoch": 0.024114520935090467,
      "grad_norm": 0.37069088220596313,
      "learning_rate": 1.9994536945674018e-05,
      "loss": 0.6435,
      "step": 785
    },
    {
      "epoch": 0.02414524007003963,
      "grad_norm": 0.34032025933265686,
      "learning_rate": 1.9994520961614087e-05,
      "loss": 0.603,
      "step": 786
    },
    {
      "epoch": 0.024175959204988787,
      "grad_norm": 0.3333638906478882,
      "learning_rate": 1.9994504954211256e-05,
      "loss": 0.6867,
      "step": 787
    },
    {
      "epoch": 0.024206678339937948,
      "grad_norm": 0.341990202665329,
      "learning_rate": 1.9994488923465562e-05,
      "loss": 0.6199,
      "step": 788
    },
    {
      "epoch": 0.024237397474887106,
      "grad_norm": 0.42287757992744446,
      "learning_rate": 1.9994472869377036e-05,
      "loss": 0.668,
      "step": 789
    },
    {
      "epoch": 0.024268116609836268,
      "grad_norm": 0.31478404998779297,
      "learning_rate": 1.9994456791945725e-05,
      "loss": 0.6067,
      "step": 790
    },
    {
      "epoch": 0.024298835744785426,
      "grad_norm": 0.3145131468772888,
      "learning_rate": 1.999444069117166e-05,
      "loss": 0.5834,
      "step": 791
    },
    {
      "epoch": 0.024329554879734587,
      "grad_norm": 0.3533474802970886,
      "learning_rate": 1.9994424567054885e-05,
      "loss": 0.6195,
      "step": 792
    },
    {
      "epoch": 0.024360274014683745,
      "grad_norm": 0.3833659291267395,
      "learning_rate": 1.9994408419595427e-05,
      "loss": 0.645,
      "step": 793
    },
    {
      "epoch": 0.024390993149632906,
      "grad_norm": 0.3944745659828186,
      "learning_rate": 1.9994392248793334e-05,
      "loss": 0.7117,
      "step": 794
    },
    {
      "epoch": 0.024421712284582064,
      "grad_norm": 0.368807852268219,
      "learning_rate": 1.9994376054648642e-05,
      "loss": 0.6191,
      "step": 795
    },
    {
      "epoch": 0.024452431419531226,
      "grad_norm": 0.4665679335594177,
      "learning_rate": 1.9994359837161382e-05,
      "loss": 0.6531,
      "step": 796
    },
    {
      "epoch": 0.024483150554480387,
      "grad_norm": 0.34524843096733093,
      "learning_rate": 1.99943435963316e-05,
      "loss": 0.6637,
      "step": 797
    },
    {
      "epoch": 0.024513869689429545,
      "grad_norm": 0.3749580681324005,
      "learning_rate": 1.999432733215933e-05,
      "loss": 0.6151,
      "step": 798
    },
    {
      "epoch": 0.024544588824378707,
      "grad_norm": 0.32194986939430237,
      "learning_rate": 1.999431104464461e-05,
      "loss": 0.5592,
      "step": 799
    },
    {
      "epoch": 0.024575307959327865,
      "grad_norm": 0.3510719835758209,
      "learning_rate": 1.9994294733787474e-05,
      "loss": 0.6076,
      "step": 800
    },
    {
      "epoch": 0.024606027094277026,
      "grad_norm": 0.36355942487716675,
      "learning_rate": 1.9994278399587968e-05,
      "loss": 0.6031,
      "step": 801
    },
    {
      "epoch": 0.024636746229226184,
      "grad_norm": 0.39445173740386963,
      "learning_rate": 1.9994262042046128e-05,
      "loss": 0.6225,
      "step": 802
    },
    {
      "epoch": 0.024667465364175346,
      "grad_norm": 0.3646094501018524,
      "learning_rate": 1.999424566116199e-05,
      "loss": 0.5859,
      "step": 803
    },
    {
      "epoch": 0.024698184499124504,
      "grad_norm": 0.3574069142341614,
      "learning_rate": 1.9994229256935595e-05,
      "loss": 0.6482,
      "step": 804
    },
    {
      "epoch": 0.024728903634073665,
      "grad_norm": 0.3421379327774048,
      "learning_rate": 1.9994212829366976e-05,
      "loss": 0.645,
      "step": 805
    },
    {
      "epoch": 0.024759622769022823,
      "grad_norm": 0.34817564487457275,
      "learning_rate": 1.999419637845618e-05,
      "loss": 0.7169,
      "step": 806
    },
    {
      "epoch": 0.024790341903971985,
      "grad_norm": 0.4101845920085907,
      "learning_rate": 1.9994179904203238e-05,
      "loss": 0.6419,
      "step": 807
    },
    {
      "epoch": 0.024821061038921143,
      "grad_norm": 0.32005947828292847,
      "learning_rate": 1.999416340660819e-05,
      "loss": 0.599,
      "step": 808
    },
    {
      "epoch": 0.024851780173870304,
      "grad_norm": 0.36604833602905273,
      "learning_rate": 1.9994146885671078e-05,
      "loss": 0.6331,
      "step": 809
    },
    {
      "epoch": 0.024882499308819462,
      "grad_norm": 0.3340514600276947,
      "learning_rate": 1.9994130341391934e-05,
      "loss": 0.6004,
      "step": 810
    },
    {
      "epoch": 0.024913218443768623,
      "grad_norm": 0.36938372254371643,
      "learning_rate": 1.9994113773770802e-05,
      "loss": 0.6308,
      "step": 811
    },
    {
      "epoch": 0.024943937578717785,
      "grad_norm": 0.33159640431404114,
      "learning_rate": 1.999409718280772e-05,
      "loss": 0.6067,
      "step": 812
    },
    {
      "epoch": 0.024974656713666943,
      "grad_norm": 0.5651868581771851,
      "learning_rate": 1.9994080568502725e-05,
      "loss": 0.6208,
      "step": 813
    },
    {
      "epoch": 0.025005375848616104,
      "grad_norm": 0.3704703450202942,
      "learning_rate": 1.9994063930855857e-05,
      "loss": 0.7532,
      "step": 814
    },
    {
      "epoch": 0.025036094983565262,
      "grad_norm": 0.35838672518730164,
      "learning_rate": 1.9994047269867157e-05,
      "loss": 0.5827,
      "step": 815
    },
    {
      "epoch": 0.025066814118514424,
      "grad_norm": 0.4924098253250122,
      "learning_rate": 1.9994030585536662e-05,
      "loss": 0.6933,
      "step": 816
    },
    {
      "epoch": 0.02509753325346358,
      "grad_norm": 0.47129446268081665,
      "learning_rate": 1.9994013877864405e-05,
      "loss": 0.5615,
      "step": 817
    },
    {
      "epoch": 0.025128252388412743,
      "grad_norm": 0.3338177502155304,
      "learning_rate": 1.9993997146850438e-05,
      "loss": 0.5392,
      "step": 818
    },
    {
      "epoch": 0.0251589715233619,
      "grad_norm": 0.3910692632198334,
      "learning_rate": 1.9993980392494787e-05,
      "loss": 0.6248,
      "step": 819
    },
    {
      "epoch": 0.025189690658311063,
      "grad_norm": 0.3745579719543457,
      "learning_rate": 1.9993963614797497e-05,
      "loss": 0.6016,
      "step": 820
    },
    {
      "epoch": 0.02522040979326022,
      "grad_norm": 0.40972140431404114,
      "learning_rate": 1.9993946813758607e-05,
      "loss": 0.6921,
      "step": 821
    },
    {
      "epoch": 0.025251128928209382,
      "grad_norm": 0.32721611857414246,
      "learning_rate": 1.999392998937816e-05,
      "loss": 0.5915,
      "step": 822
    },
    {
      "epoch": 0.02528184806315854,
      "grad_norm": 0.3533724546432495,
      "learning_rate": 1.999391314165619e-05,
      "loss": 0.6254,
      "step": 823
    },
    {
      "epoch": 0.0253125671981077,
      "grad_norm": 0.360741525888443,
      "learning_rate": 1.999389627059274e-05,
      "loss": 0.6552,
      "step": 824
    },
    {
      "epoch": 0.02534328633305686,
      "grad_norm": 0.35991933941841125,
      "learning_rate": 1.9993879376187845e-05,
      "loss": 0.636,
      "step": 825
    },
    {
      "epoch": 0.02537400546800602,
      "grad_norm": 0.3693443238735199,
      "learning_rate": 1.9993862458441544e-05,
      "loss": 0.6132,
      "step": 826
    },
    {
      "epoch": 0.025404724602955182,
      "grad_norm": 0.42027372121810913,
      "learning_rate": 1.999384551735388e-05,
      "loss": 0.5749,
      "step": 827
    },
    {
      "epoch": 0.02543544373790434,
      "grad_norm": 0.3683750629425049,
      "learning_rate": 1.9993828552924895e-05,
      "loss": 0.5891,
      "step": 828
    },
    {
      "epoch": 0.025466162872853502,
      "grad_norm": 0.3447107672691345,
      "learning_rate": 1.9993811565154624e-05,
      "loss": 0.6319,
      "step": 829
    },
    {
      "epoch": 0.02549688200780266,
      "grad_norm": 0.3316881060600281,
      "learning_rate": 1.9993794554043107e-05,
      "loss": 0.6595,
      "step": 830
    },
    {
      "epoch": 0.02552760114275182,
      "grad_norm": 0.3164406716823578,
      "learning_rate": 1.9993777519590388e-05,
      "loss": 0.5373,
      "step": 831
    },
    {
      "epoch": 0.02555832027770098,
      "grad_norm": 0.35530632734298706,
      "learning_rate": 1.9993760461796504e-05,
      "loss": 0.6145,
      "step": 832
    },
    {
      "epoch": 0.02558903941265014,
      "grad_norm": 0.34377995133399963,
      "learning_rate": 1.999374338066149e-05,
      "loss": 0.7133,
      "step": 833
    },
    {
      "epoch": 0.0256197585475993,
      "grad_norm": 0.34587007761001587,
      "learning_rate": 1.999372627618539e-05,
      "loss": 0.6881,
      "step": 834
    },
    {
      "epoch": 0.02565047768254846,
      "grad_norm": 0.3629341423511505,
      "learning_rate": 1.999370914836825e-05,
      "loss": 0.6366,
      "step": 835
    },
    {
      "epoch": 0.025681196817497618,
      "grad_norm": 0.34330689907073975,
      "learning_rate": 1.99936919972101e-05,
      "loss": 0.6038,
      "step": 836
    },
    {
      "epoch": 0.02571191595244678,
      "grad_norm": 0.3261229991912842,
      "learning_rate": 1.9993674822710986e-05,
      "loss": 0.5594,
      "step": 837
    },
    {
      "epoch": 0.025742635087395938,
      "grad_norm": 0.36150410771369934,
      "learning_rate": 1.9993657624870947e-05,
      "loss": 0.6053,
      "step": 838
    },
    {
      "epoch": 0.0257733542223451,
      "grad_norm": 0.3431285321712494,
      "learning_rate": 1.999364040369002e-05,
      "loss": 0.6636,
      "step": 839
    },
    {
      "epoch": 0.025804073357294257,
      "grad_norm": 0.354445219039917,
      "learning_rate": 1.999362315916825e-05,
      "loss": 0.6036,
      "step": 840
    },
    {
      "epoch": 0.02583479249224342,
      "grad_norm": 0.3431447148323059,
      "learning_rate": 1.9993605891305677e-05,
      "loss": 0.6243,
      "step": 841
    },
    {
      "epoch": 0.02586551162719258,
      "grad_norm": 0.30395689606666565,
      "learning_rate": 1.9993588600102336e-05,
      "loss": 0.5895,
      "step": 842
    },
    {
      "epoch": 0.025896230762141738,
      "grad_norm": 0.31611546874046326,
      "learning_rate": 1.9993571285558275e-05,
      "loss": 0.5428,
      "step": 843
    },
    {
      "epoch": 0.0259269498970909,
      "grad_norm": 0.33272844552993774,
      "learning_rate": 1.9993553947673525e-05,
      "loss": 0.6215,
      "step": 844
    },
    {
      "epoch": 0.025957669032040057,
      "grad_norm": 0.3784993886947632,
      "learning_rate": 1.9993536586448136e-05,
      "loss": 0.6762,
      "step": 845
    },
    {
      "epoch": 0.02598838816698922,
      "grad_norm": 0.35857489705085754,
      "learning_rate": 1.999351920188214e-05,
      "loss": 0.6659,
      "step": 846
    },
    {
      "epoch": 0.026019107301938377,
      "grad_norm": 0.3249307870864868,
      "learning_rate": 1.9993501793975586e-05,
      "loss": 0.6286,
      "step": 847
    },
    {
      "epoch": 0.026049826436887538,
      "grad_norm": 0.349250465631485,
      "learning_rate": 1.9993484362728508e-05,
      "loss": 0.7103,
      "step": 848
    },
    {
      "epoch": 0.026080545571836696,
      "grad_norm": 0.33687305450439453,
      "learning_rate": 1.999346690814095e-05,
      "loss": 0.5929,
      "step": 849
    },
    {
      "epoch": 0.026111264706785858,
      "grad_norm": 0.3357529938220978,
      "learning_rate": 1.9993449430212955e-05,
      "loss": 0.645,
      "step": 850
    },
    {
      "epoch": 0.026141983841735016,
      "grad_norm": 0.3701726794242859,
      "learning_rate": 1.999343192894456e-05,
      "loss": 0.6337,
      "step": 851
    },
    {
      "epoch": 0.026172702976684177,
      "grad_norm": 0.3886323571205139,
      "learning_rate": 1.99934144043358e-05,
      "loss": 0.6362,
      "step": 852
    },
    {
      "epoch": 0.026203422111633335,
      "grad_norm": 0.33953696489334106,
      "learning_rate": 1.9993396856386732e-05,
      "loss": 0.6392,
      "step": 853
    },
    {
      "epoch": 0.026234141246582496,
      "grad_norm": 0.327877938747406,
      "learning_rate": 1.999337928509738e-05,
      "loss": 0.6176,
      "step": 854
    },
    {
      "epoch": 0.026264860381531654,
      "grad_norm": 0.3984313905239105,
      "learning_rate": 1.9993361690467798e-05,
      "loss": 0.6304,
      "step": 855
    },
    {
      "epoch": 0.026295579516480816,
      "grad_norm": 0.3199312686920166,
      "learning_rate": 1.9993344072498022e-05,
      "loss": 0.6465,
      "step": 856
    },
    {
      "epoch": 0.026326298651429977,
      "grad_norm": 0.36998212337493896,
      "learning_rate": 1.999332643118809e-05,
      "loss": 0.7073,
      "step": 857
    },
    {
      "epoch": 0.026357017786379135,
      "grad_norm": 0.370624840259552,
      "learning_rate": 1.999330876653805e-05,
      "loss": 0.6967,
      "step": 858
    },
    {
      "epoch": 0.026387736921328297,
      "grad_norm": 0.319754034280777,
      "learning_rate": 1.9993291078547936e-05,
      "loss": 0.611,
      "step": 859
    },
    {
      "epoch": 0.026418456056277455,
      "grad_norm": 0.3540596067905426,
      "learning_rate": 1.9993273367217795e-05,
      "loss": 0.6786,
      "step": 860
    },
    {
      "epoch": 0.026449175191226616,
      "grad_norm": 0.3391339182853699,
      "learning_rate": 1.9993255632547665e-05,
      "loss": 0.5998,
      "step": 861
    },
    {
      "epoch": 0.026479894326175774,
      "grad_norm": 0.33535754680633545,
      "learning_rate": 1.999323787453759e-05,
      "loss": 0.6467,
      "step": 862
    },
    {
      "epoch": 0.026510613461124936,
      "grad_norm": 0.403915673494339,
      "learning_rate": 1.9993220093187605e-05,
      "loss": 0.6947,
      "step": 863
    },
    {
      "epoch": 0.026541332596074094,
      "grad_norm": 0.3407231867313385,
      "learning_rate": 1.999320228849776e-05,
      "loss": 0.6535,
      "step": 864
    },
    {
      "epoch": 0.026572051731023255,
      "grad_norm": 0.34311601519584656,
      "learning_rate": 1.9993184460468096e-05,
      "loss": 0.6544,
      "step": 865
    },
    {
      "epoch": 0.026602770865972413,
      "grad_norm": 0.3273365795612335,
      "learning_rate": 1.9993166609098645e-05,
      "loss": 0.5689,
      "step": 866
    },
    {
      "epoch": 0.026633490000921575,
      "grad_norm": 0.30608561635017395,
      "learning_rate": 1.9993148734389462e-05,
      "loss": 0.6108,
      "step": 867
    },
    {
      "epoch": 0.026664209135870733,
      "grad_norm": 0.320281058549881,
      "learning_rate": 1.9993130836340578e-05,
      "loss": 0.6337,
      "step": 868
    },
    {
      "epoch": 0.026694928270819894,
      "grad_norm": 0.43544432520866394,
      "learning_rate": 1.9993112914952043e-05,
      "loss": 0.6234,
      "step": 869
    },
    {
      "epoch": 0.026725647405769052,
      "grad_norm": 0.379352867603302,
      "learning_rate": 1.9993094970223895e-05,
      "loss": 0.5824,
      "step": 870
    },
    {
      "epoch": 0.026756366540718213,
      "grad_norm": 0.34356755018234253,
      "learning_rate": 1.999307700215617e-05,
      "loss": 0.5832,
      "step": 871
    },
    {
      "epoch": 0.026787085675667375,
      "grad_norm": 0.36516669392585754,
      "learning_rate": 1.9993059010748917e-05,
      "loss": 0.6431,
      "step": 872
    },
    {
      "epoch": 0.026817804810616533,
      "grad_norm": 0.3460361361503601,
      "learning_rate": 1.9993040996002183e-05,
      "loss": 0.6466,
      "step": 873
    },
    {
      "epoch": 0.026848523945565694,
      "grad_norm": 0.32557782530784607,
      "learning_rate": 1.9993022957916e-05,
      "loss": 0.6117,
      "step": 874
    },
    {
      "epoch": 0.026879243080514852,
      "grad_norm": 0.3667413294315338,
      "learning_rate": 1.9993004896490412e-05,
      "loss": 0.6783,
      "step": 875
    },
    {
      "epoch": 0.026909962215464014,
      "grad_norm": 0.3549968898296356,
      "learning_rate": 1.9992986811725465e-05,
      "loss": 0.6018,
      "step": 876
    },
    {
      "epoch": 0.026940681350413172,
      "grad_norm": 0.3632084131240845,
      "learning_rate": 1.99929687036212e-05,
      "loss": 0.6765,
      "step": 877
    },
    {
      "epoch": 0.026971400485362333,
      "grad_norm": 0.45459064841270447,
      "learning_rate": 1.9992950572177657e-05,
      "loss": 0.6686,
      "step": 878
    },
    {
      "epoch": 0.02700211962031149,
      "grad_norm": 0.3806736171245575,
      "learning_rate": 1.9992932417394882e-05,
      "loss": 0.6493,
      "step": 879
    },
    {
      "epoch": 0.027032838755260653,
      "grad_norm": 0.3853391706943512,
      "learning_rate": 1.9992914239272918e-05,
      "loss": 0.6816,
      "step": 880
    },
    {
      "epoch": 0.02706355789020981,
      "grad_norm": 0.3224543631076813,
      "learning_rate": 1.9992896037811797e-05,
      "loss": 0.6645,
      "step": 881
    },
    {
      "epoch": 0.027094277025158972,
      "grad_norm": 0.3574940860271454,
      "learning_rate": 1.9992877813011574e-05,
      "loss": 0.6623,
      "step": 882
    },
    {
      "epoch": 0.02712499616010813,
      "grad_norm": 0.3445385694503784,
      "learning_rate": 1.9992859564872287e-05,
      "loss": 0.6362,
      "step": 883
    },
    {
      "epoch": 0.02715571529505729,
      "grad_norm": 0.3310242295265198,
      "learning_rate": 1.999284129339398e-05,
      "loss": 0.6039,
      "step": 884
    },
    {
      "epoch": 0.02718643443000645,
      "grad_norm": 0.34740573167800903,
      "learning_rate": 1.9992822998576692e-05,
      "loss": 0.6253,
      "step": 885
    },
    {
      "epoch": 0.02721715356495561,
      "grad_norm": 0.3663191497325897,
      "learning_rate": 1.999280468042047e-05,
      "loss": 0.6713,
      "step": 886
    },
    {
      "epoch": 0.027247872699904772,
      "grad_norm": 0.5052487850189209,
      "learning_rate": 1.999278633892535e-05,
      "loss": 0.6952,
      "step": 887
    },
    {
      "epoch": 0.02727859183485393,
      "grad_norm": 0.3309720456600189,
      "learning_rate": 1.9992767974091385e-05,
      "loss": 0.6636,
      "step": 888
    },
    {
      "epoch": 0.027309310969803092,
      "grad_norm": 0.34106194972991943,
      "learning_rate": 1.999274958591861e-05,
      "loss": 0.6298,
      "step": 889
    },
    {
      "epoch": 0.02734003010475225,
      "grad_norm": 0.37429702281951904,
      "learning_rate": 1.9992731174407073e-05,
      "loss": 0.6412,
      "step": 890
    },
    {
      "epoch": 0.02737074923970141,
      "grad_norm": 0.589742124080658,
      "learning_rate": 1.999271273955681e-05,
      "loss": 0.6488,
      "step": 891
    },
    {
      "epoch": 0.02740146837465057,
      "grad_norm": 0.34701046347618103,
      "learning_rate": 1.999269428136787e-05,
      "loss": 0.7622,
      "step": 892
    },
    {
      "epoch": 0.02743218750959973,
      "grad_norm": 0.3558473587036133,
      "learning_rate": 1.9992675799840294e-05,
      "loss": 0.72,
      "step": 893
    },
    {
      "epoch": 0.02746290664454889,
      "grad_norm": 0.4320787191390991,
      "learning_rate": 1.9992657294974133e-05,
      "loss": 0.6344,
      "step": 894
    },
    {
      "epoch": 0.02749362577949805,
      "grad_norm": 0.3307746946811676,
      "learning_rate": 1.9992638766769416e-05,
      "loss": 0.6672,
      "step": 895
    },
    {
      "epoch": 0.027524344914447208,
      "grad_norm": 0.33231550455093384,
      "learning_rate": 1.9992620215226193e-05,
      "loss": 0.6256,
      "step": 896
    },
    {
      "epoch": 0.02755506404939637,
      "grad_norm": 0.6375876069068909,
      "learning_rate": 1.9992601640344513e-05,
      "loss": 0.6433,
      "step": 897
    },
    {
      "epoch": 0.027585783184345528,
      "grad_norm": 0.356007844209671,
      "learning_rate": 1.9992583042124408e-05,
      "loss": 0.6657,
      "step": 898
    },
    {
      "epoch": 0.02761650231929469,
      "grad_norm": 0.3650149703025818,
      "learning_rate": 1.9992564420565926e-05,
      "loss": 0.693,
      "step": 899
    },
    {
      "epoch": 0.027647221454243847,
      "grad_norm": 0.4083043932914734,
      "learning_rate": 1.999254577566912e-05,
      "loss": 0.6994,
      "step": 900
    },
    {
      "epoch": 0.02767794058919301,
      "grad_norm": 0.3430173993110657,
      "learning_rate": 1.999252710743402e-05,
      "loss": 0.6392,
      "step": 901
    },
    {
      "epoch": 0.027708659724142166,
      "grad_norm": 0.3918071985244751,
      "learning_rate": 1.9992508415860675e-05,
      "loss": 0.6068,
      "step": 902
    },
    {
      "epoch": 0.027739378859091328,
      "grad_norm": 0.30533114075660706,
      "learning_rate": 1.999248970094913e-05,
      "loss": 0.6058,
      "step": 903
    },
    {
      "epoch": 0.02777009799404049,
      "grad_norm": 0.32990822196006775,
      "learning_rate": 1.999247096269943e-05,
      "loss": 0.6189,
      "step": 904
    },
    {
      "epoch": 0.027800817128989647,
      "grad_norm": 0.37144070863723755,
      "learning_rate": 1.9992452201111613e-05,
      "loss": 0.7093,
      "step": 905
    },
    {
      "epoch": 0.02783153626393881,
      "grad_norm": 0.33553409576416016,
      "learning_rate": 1.9992433416185728e-05,
      "loss": 0.6329,
      "step": 906
    },
    {
      "epoch": 0.027862255398887967,
      "grad_norm": 0.34402376413345337,
      "learning_rate": 1.999241460792181e-05,
      "loss": 0.5957,
      "step": 907
    },
    {
      "epoch": 0.027892974533837128,
      "grad_norm": 0.3575018644332886,
      "learning_rate": 1.9992395776319918e-05,
      "loss": 0.7001,
      "step": 908
    },
    {
      "epoch": 0.027923693668786286,
      "grad_norm": 0.5423919558525085,
      "learning_rate": 1.9992376921380085e-05,
      "loss": 0.6312,
      "step": 909
    },
    {
      "epoch": 0.027954412803735448,
      "grad_norm": 0.36307886242866516,
      "learning_rate": 1.999235804310236e-05,
      "loss": 0.6899,
      "step": 910
    },
    {
      "epoch": 0.027985131938684606,
      "grad_norm": 0.3432862460613251,
      "learning_rate": 1.999233914148678e-05,
      "loss": 0.6332,
      "step": 911
    },
    {
      "epoch": 0.028015851073633767,
      "grad_norm": 0.3484271466732025,
      "learning_rate": 1.99923202165334e-05,
      "loss": 0.6826,
      "step": 912
    },
    {
      "epoch": 0.028046570208582925,
      "grad_norm": 0.3533470928668976,
      "learning_rate": 1.9992301268242254e-05,
      "loss": 0.6419,
      "step": 913
    },
    {
      "epoch": 0.028077289343532087,
      "grad_norm": 0.34541529417037964,
      "learning_rate": 1.999228229661339e-05,
      "loss": 0.6058,
      "step": 914
    },
    {
      "epoch": 0.028108008478481245,
      "grad_norm": 0.36948898434638977,
      "learning_rate": 1.9992263301646854e-05,
      "loss": 0.6531,
      "step": 915
    },
    {
      "epoch": 0.028138727613430406,
      "grad_norm": 0.3919905126094818,
      "learning_rate": 1.999224428334269e-05,
      "loss": 0.6754,
      "step": 916
    },
    {
      "epoch": 0.028169446748379564,
      "grad_norm": 0.37425386905670166,
      "learning_rate": 1.9992225241700943e-05,
      "loss": 0.6725,
      "step": 917
    },
    {
      "epoch": 0.028200165883328725,
      "grad_norm": 0.33044975996017456,
      "learning_rate": 1.9992206176721652e-05,
      "loss": 0.6737,
      "step": 918
    },
    {
      "epoch": 0.028230885018277887,
      "grad_norm": 0.3141992390155792,
      "learning_rate": 1.999218708840487e-05,
      "loss": 0.6525,
      "step": 919
    },
    {
      "epoch": 0.028261604153227045,
      "grad_norm": 0.360970675945282,
      "learning_rate": 1.9992167976750637e-05,
      "loss": 0.721,
      "step": 920
    },
    {
      "epoch": 0.028292323288176206,
      "grad_norm": 0.3297577202320099,
      "learning_rate": 1.9992148841758994e-05,
      "loss": 0.6428,
      "step": 921
    },
    {
      "epoch": 0.028323042423125364,
      "grad_norm": 0.3619009256362915,
      "learning_rate": 1.9992129683429994e-05,
      "loss": 0.6031,
      "step": 922
    },
    {
      "epoch": 0.028353761558074526,
      "grad_norm": 0.3066405653953552,
      "learning_rate": 1.999211050176367e-05,
      "loss": 0.5744,
      "step": 923
    },
    {
      "epoch": 0.028384480693023684,
      "grad_norm": 0.35686203837394714,
      "learning_rate": 1.9992091296760083e-05,
      "loss": 0.6865,
      "step": 924
    },
    {
      "epoch": 0.028415199827972845,
      "grad_norm": 0.4501313269138336,
      "learning_rate": 1.9992072068419264e-05,
      "loss": 0.5582,
      "step": 925
    },
    {
      "epoch": 0.028445918962922003,
      "grad_norm": 0.3558783531188965,
      "learning_rate": 1.9992052816741263e-05,
      "loss": 0.614,
      "step": 926
    },
    {
      "epoch": 0.028476638097871165,
      "grad_norm": 0.3103170096874237,
      "learning_rate": 1.9992033541726126e-05,
      "loss": 0.591,
      "step": 927
    },
    {
      "epoch": 0.028507357232820323,
      "grad_norm": 0.3640974462032318,
      "learning_rate": 1.9992014243373897e-05,
      "loss": 0.5335,
      "step": 928
    },
    {
      "epoch": 0.028538076367769484,
      "grad_norm": 0.34118396043777466,
      "learning_rate": 1.9991994921684622e-05,
      "loss": 0.5728,
      "step": 929
    },
    {
      "epoch": 0.028568795502718642,
      "grad_norm": 0.37271228432655334,
      "learning_rate": 1.9991975576658342e-05,
      "loss": 0.6489,
      "step": 930
    },
    {
      "epoch": 0.028599514637667803,
      "grad_norm": 0.32607826590538025,
      "learning_rate": 1.9991956208295106e-05,
      "loss": 0.6328,
      "step": 931
    },
    {
      "epoch": 0.02863023377261696,
      "grad_norm": 0.4843723475933075,
      "learning_rate": 1.999193681659496e-05,
      "loss": 0.6742,
      "step": 932
    },
    {
      "epoch": 0.028660952907566123,
      "grad_norm": 0.34481140971183777,
      "learning_rate": 1.9991917401557948e-05,
      "loss": 0.658,
      "step": 933
    },
    {
      "epoch": 0.028691672042515284,
      "grad_norm": 0.35286298394203186,
      "learning_rate": 1.999189796318411e-05,
      "loss": 0.6628,
      "step": 934
    },
    {
      "epoch": 0.028722391177464442,
      "grad_norm": 0.3482709228992462,
      "learning_rate": 1.9991878501473504e-05,
      "loss": 0.7318,
      "step": 935
    },
    {
      "epoch": 0.028753110312413604,
      "grad_norm": 0.35179585218429565,
      "learning_rate": 1.9991859016426163e-05,
      "loss": 0.638,
      "step": 936
    },
    {
      "epoch": 0.028783829447362762,
      "grad_norm": 0.371429443359375,
      "learning_rate": 1.9991839508042136e-05,
      "loss": 0.7079,
      "step": 937
    },
    {
      "epoch": 0.028814548582311923,
      "grad_norm": 0.3398880958557129,
      "learning_rate": 1.9991819976321474e-05,
      "loss": 0.5865,
      "step": 938
    },
    {
      "epoch": 0.02884526771726108,
      "grad_norm": 0.37276071310043335,
      "learning_rate": 1.9991800421264217e-05,
      "loss": 0.704,
      "step": 939
    },
    {
      "epoch": 0.028875986852210243,
      "grad_norm": 0.35747987031936646,
      "learning_rate": 1.9991780842870413e-05,
      "loss": 0.622,
      "step": 940
    },
    {
      "epoch": 0.0289067059871594,
      "grad_norm": 0.48391324281692505,
      "learning_rate": 1.999176124114011e-05,
      "loss": 0.6132,
      "step": 941
    },
    {
      "epoch": 0.028937425122108562,
      "grad_norm": 0.349644273519516,
      "learning_rate": 1.9991741616073347e-05,
      "loss": 0.6095,
      "step": 942
    },
    {
      "epoch": 0.02896814425705772,
      "grad_norm": 0.33420729637145996,
      "learning_rate": 1.9991721967670173e-05,
      "loss": 0.6068,
      "step": 943
    },
    {
      "epoch": 0.02899886339200688,
      "grad_norm": 0.3364189565181732,
      "learning_rate": 1.9991702295930634e-05,
      "loss": 0.6172,
      "step": 944
    },
    {
      "epoch": 0.02902958252695604,
      "grad_norm": 0.3340352773666382,
      "learning_rate": 1.999168260085478e-05,
      "loss": 0.6584,
      "step": 945
    },
    {
      "epoch": 0.0290603016619052,
      "grad_norm": 0.3347535729408264,
      "learning_rate": 1.999166288244265e-05,
      "loss": 0.5865,
      "step": 946
    },
    {
      "epoch": 0.02909102079685436,
      "grad_norm": 0.35337284207344055,
      "learning_rate": 1.9991643140694298e-05,
      "loss": 0.6618,
      "step": 947
    },
    {
      "epoch": 0.02912173993180352,
      "grad_norm": 0.3245721161365509,
      "learning_rate": 1.999162337560976e-05,
      "loss": 0.5904,
      "step": 948
    },
    {
      "epoch": 0.029152459066752682,
      "grad_norm": 0.36671164631843567,
      "learning_rate": 1.9991603587189092e-05,
      "loss": 0.5839,
      "step": 949
    },
    {
      "epoch": 0.02918317820170184,
      "grad_norm": 0.34232187271118164,
      "learning_rate": 1.9991583775432334e-05,
      "loss": 0.5626,
      "step": 950
    },
    {
      "epoch": 0.029213897336651,
      "grad_norm": 0.3917906880378723,
      "learning_rate": 1.9991563940339534e-05,
      "loss": 0.6784,
      "step": 951
    },
    {
      "epoch": 0.02924461647160016,
      "grad_norm": 0.4486294984817505,
      "learning_rate": 1.9991544081910743e-05,
      "loss": 0.6921,
      "step": 952
    },
    {
      "epoch": 0.02927533560654932,
      "grad_norm": 0.4337921142578125,
      "learning_rate": 1.9991524200145997e-05,
      "loss": 0.6889,
      "step": 953
    },
    {
      "epoch": 0.02930605474149848,
      "grad_norm": 0.41638249158859253,
      "learning_rate": 1.999150429504535e-05,
      "loss": 0.6286,
      "step": 954
    },
    {
      "epoch": 0.02933677387644764,
      "grad_norm": 0.32168474793434143,
      "learning_rate": 1.999148436660885e-05,
      "loss": 0.627,
      "step": 955
    },
    {
      "epoch": 0.029367493011396798,
      "grad_norm": 0.34400907158851624,
      "learning_rate": 1.999146441483654e-05,
      "loss": 0.5621,
      "step": 956
    },
    {
      "epoch": 0.02939821214634596,
      "grad_norm": 0.3773561716079712,
      "learning_rate": 1.999144443972846e-05,
      "loss": 0.6157,
      "step": 957
    },
    {
      "epoch": 0.029428931281295118,
      "grad_norm": 0.3841872215270996,
      "learning_rate": 1.999142444128467e-05,
      "loss": 0.6361,
      "step": 958
    },
    {
      "epoch": 0.02945965041624428,
      "grad_norm": 0.3586106598377228,
      "learning_rate": 1.999140441950521e-05,
      "loss": 0.6932,
      "step": 959
    },
    {
      "epoch": 0.029490369551193437,
      "grad_norm": 0.3461854159832001,
      "learning_rate": 1.9991384374390127e-05,
      "loss": 0.6584,
      "step": 960
    },
    {
      "epoch": 0.0295210886861426,
      "grad_norm": 0.48548853397369385,
      "learning_rate": 1.999136430593947e-05,
      "loss": 0.644,
      "step": 961
    },
    {
      "epoch": 0.029551807821091756,
      "grad_norm": 0.3546416461467743,
      "learning_rate": 1.999134421415328e-05,
      "loss": 0.6752,
      "step": 962
    },
    {
      "epoch": 0.029582526956040918,
      "grad_norm": 0.3347010910511017,
      "learning_rate": 1.999132409903161e-05,
      "loss": 0.5618,
      "step": 963
    },
    {
      "epoch": 0.02961324609099008,
      "grad_norm": 0.35680463910102844,
      "learning_rate": 1.9991303960574503e-05,
      "loss": 0.663,
      "step": 964
    },
    {
      "epoch": 0.029643965225939237,
      "grad_norm": 0.36602479219436646,
      "learning_rate": 1.999128379878201e-05,
      "loss": 0.6647,
      "step": 965
    },
    {
      "epoch": 0.0296746843608884,
      "grad_norm": 0.3482474088668823,
      "learning_rate": 1.9991263613654176e-05,
      "loss": 0.632,
      "step": 966
    },
    {
      "epoch": 0.029705403495837557,
      "grad_norm": 0.36395663022994995,
      "learning_rate": 1.9991243405191045e-05,
      "loss": 0.6093,
      "step": 967
    },
    {
      "epoch": 0.029736122630786718,
      "grad_norm": 0.4002844989299774,
      "learning_rate": 1.9991223173392668e-05,
      "loss": 0.676,
      "step": 968
    },
    {
      "epoch": 0.029766841765735876,
      "grad_norm": 0.3626173436641693,
      "learning_rate": 1.9991202918259095e-05,
      "loss": 0.677,
      "step": 969
    },
    {
      "epoch": 0.029797560900685038,
      "grad_norm": 0.3409412205219269,
      "learning_rate": 1.999118263979037e-05,
      "loss": 0.6178,
      "step": 970
    },
    {
      "epoch": 0.029828280035634196,
      "grad_norm": 0.3712298572063446,
      "learning_rate": 1.9991162337986534e-05,
      "loss": 0.6617,
      "step": 971
    },
    {
      "epoch": 0.029858999170583357,
      "grad_norm": 0.35912397503852844,
      "learning_rate": 1.9991142012847647e-05,
      "loss": 0.6982,
      "step": 972
    },
    {
      "epoch": 0.029889718305532515,
      "grad_norm": 0.3603551387786865,
      "learning_rate": 1.9991121664373745e-05,
      "loss": 0.6532,
      "step": 973
    },
    {
      "epoch": 0.029920437440481677,
      "grad_norm": 0.3421851098537445,
      "learning_rate": 1.9991101292564884e-05,
      "loss": 0.6465,
      "step": 974
    },
    {
      "epoch": 0.029951156575430835,
      "grad_norm": 0.4020642042160034,
      "learning_rate": 1.9991080897421105e-05,
      "loss": 0.6809,
      "step": 975
    },
    {
      "epoch": 0.029981875710379996,
      "grad_norm": 0.4122118651866913,
      "learning_rate": 1.9991060478942464e-05,
      "loss": 0.6071,
      "step": 976
    },
    {
      "epoch": 0.030012594845329154,
      "grad_norm": 0.3102165460586548,
      "learning_rate": 1.9991040037129e-05,
      "loss": 0.6066,
      "step": 977
    },
    {
      "epoch": 0.030043313980278315,
      "grad_norm": 0.3728201687335968,
      "learning_rate": 1.9991019571980764e-05,
      "loss": 0.5976,
      "step": 978
    },
    {
      "epoch": 0.030074033115227477,
      "grad_norm": 0.36967578530311584,
      "learning_rate": 1.9990999083497804e-05,
      "loss": 0.6243,
      "step": 979
    },
    {
      "epoch": 0.030104752250176635,
      "grad_norm": 0.35314464569091797,
      "learning_rate": 1.999097857168017e-05,
      "loss": 0.6259,
      "step": 980
    },
    {
      "epoch": 0.030135471385125796,
      "grad_norm": 0.34373918175697327,
      "learning_rate": 1.9990958036527903e-05,
      "loss": 0.6841,
      "step": 981
    },
    {
      "epoch": 0.030166190520074954,
      "grad_norm": 0.32499226927757263,
      "learning_rate": 1.9990937478041062e-05,
      "loss": 0.6508,
      "step": 982
    },
    {
      "epoch": 0.030196909655024116,
      "grad_norm": 0.3431761562824249,
      "learning_rate": 1.9990916896219685e-05,
      "loss": 0.6711,
      "step": 983
    },
    {
      "epoch": 0.030227628789973274,
      "grad_norm": 0.33923274278640747,
      "learning_rate": 1.9990896291063825e-05,
      "loss": 0.5533,
      "step": 984
    },
    {
      "epoch": 0.030258347924922435,
      "grad_norm": 0.3480401635169983,
      "learning_rate": 1.999087566257353e-05,
      "loss": 0.6545,
      "step": 985
    },
    {
      "epoch": 0.030289067059871593,
      "grad_norm": 0.35932230949401855,
      "learning_rate": 1.9990855010748844e-05,
      "loss": 0.5466,
      "step": 986
    },
    {
      "epoch": 0.030319786194820755,
      "grad_norm": 0.39288341999053955,
      "learning_rate": 1.999083433558982e-05,
      "loss": 0.6442,
      "step": 987
    },
    {
      "epoch": 0.030350505329769913,
      "grad_norm": 0.3493782579898834,
      "learning_rate": 1.9990813637096503e-05,
      "loss": 0.6954,
      "step": 988
    },
    {
      "epoch": 0.030381224464719074,
      "grad_norm": 0.3798350989818573,
      "learning_rate": 1.9990792915268946e-05,
      "loss": 0.5755,
      "step": 989
    },
    {
      "epoch": 0.030411943599668232,
      "grad_norm": 0.36563122272491455,
      "learning_rate": 1.9990772170107193e-05,
      "loss": 0.5911,
      "step": 990
    },
    {
      "epoch": 0.030442662734617393,
      "grad_norm": 0.36792153120040894,
      "learning_rate": 1.9990751401611295e-05,
      "loss": 0.6221,
      "step": 991
    },
    {
      "epoch": 0.03047338186956655,
      "grad_norm": 0.3902142345905304,
      "learning_rate": 1.9990730609781296e-05,
      "loss": 0.6217,
      "step": 992
    },
    {
      "epoch": 0.030504101004515713,
      "grad_norm": 0.3285065293312073,
      "learning_rate": 1.999070979461725e-05,
      "loss": 0.6514,
      "step": 993
    },
    {
      "epoch": 0.030534820139464874,
      "grad_norm": 0.35930368304252625,
      "learning_rate": 1.9990688956119206e-05,
      "loss": 0.647,
      "step": 994
    },
    {
      "epoch": 0.030565539274414032,
      "grad_norm": 0.34278202056884766,
      "learning_rate": 1.9990668094287206e-05,
      "loss": 0.704,
      "step": 995
    },
    {
      "epoch": 0.030596258409363194,
      "grad_norm": 0.3557632267475128,
      "learning_rate": 1.9990647209121305e-05,
      "loss": 0.6233,
      "step": 996
    },
    {
      "epoch": 0.030626977544312352,
      "grad_norm": 0.4094691276550293,
      "learning_rate": 1.999062630062155e-05,
      "loss": 0.6053,
      "step": 997
    },
    {
      "epoch": 0.030657696679261513,
      "grad_norm": 0.5025925040245056,
      "learning_rate": 1.999060536878799e-05,
      "loss": 0.7051,
      "step": 998
    },
    {
      "epoch": 0.03068841581421067,
      "grad_norm": 0.3355008661746979,
      "learning_rate": 1.9990584413620673e-05,
      "loss": 0.5396,
      "step": 999
    },
    {
      "epoch": 0.030719134949159833,
      "grad_norm": 0.36267465353012085,
      "learning_rate": 1.9990563435119646e-05,
      "loss": 0.6351,
      "step": 1000
    },
    {
      "epoch": 0.03074985408410899,
      "grad_norm": 0.34036964178085327,
      "learning_rate": 1.9990542433284962e-05,
      "loss": 0.6418,
      "step": 1001
    },
    {
      "epoch": 0.030780573219058152,
      "grad_norm": 0.3541405200958252,
      "learning_rate": 1.999052140811667e-05,
      "loss": 0.629,
      "step": 1002
    },
    {
      "epoch": 0.03081129235400731,
      "grad_norm": 0.36128905415534973,
      "learning_rate": 1.9990500359614815e-05,
      "loss": 0.6617,
      "step": 1003
    },
    {
      "epoch": 0.03084201148895647,
      "grad_norm": 0.3653033673763275,
      "learning_rate": 1.999047928777945e-05,
      "loss": 0.6218,
      "step": 1004
    },
    {
      "epoch": 0.03087273062390563,
      "grad_norm": 0.37695032358169556,
      "learning_rate": 1.9990458192610623e-05,
      "loss": 0.6505,
      "step": 1005
    },
    {
      "epoch": 0.03090344975885479,
      "grad_norm": 0.3268383741378784,
      "learning_rate": 1.9990437074108385e-05,
      "loss": 0.6213,
      "step": 1006
    },
    {
      "epoch": 0.03093416889380395,
      "grad_norm": 0.345052570104599,
      "learning_rate": 1.999041593227278e-05,
      "loss": 0.6649,
      "step": 1007
    },
    {
      "epoch": 0.03096488802875311,
      "grad_norm": 0.35672691464424133,
      "learning_rate": 1.9990394767103863e-05,
      "loss": 0.6848,
      "step": 1008
    },
    {
      "epoch": 0.03099560716370227,
      "grad_norm": 0.3338707983493805,
      "learning_rate": 1.9990373578601678e-05,
      "loss": 0.619,
      "step": 1009
    },
    {
      "epoch": 0.03102632629865143,
      "grad_norm": 0.3253258466720581,
      "learning_rate": 1.9990352366766282e-05,
      "loss": 0.5523,
      "step": 1010
    },
    {
      "epoch": 0.03105704543360059,
      "grad_norm": 0.3613380491733551,
      "learning_rate": 1.9990331131597717e-05,
      "loss": 0.5879,
      "step": 1011
    },
    {
      "epoch": 0.03108776456854975,
      "grad_norm": 0.33052125573158264,
      "learning_rate": 1.9990309873096038e-05,
      "loss": 0.5923,
      "step": 1012
    },
    {
      "epoch": 0.03111848370349891,
      "grad_norm": 0.3249853551387787,
      "learning_rate": 1.9990288591261294e-05,
      "loss": 0.6219,
      "step": 1013
    },
    {
      "epoch": 0.03114920283844807,
      "grad_norm": 0.4121742248535156,
      "learning_rate": 1.9990267286093534e-05,
      "loss": 0.6363,
      "step": 1014
    },
    {
      "epoch": 0.03117992197339723,
      "grad_norm": 0.3123716711997986,
      "learning_rate": 1.99902459575928e-05,
      "loss": 0.5666,
      "step": 1015
    },
    {
      "epoch": 0.031210641108346388,
      "grad_norm": 0.35195404291152954,
      "learning_rate": 1.9990224605759156e-05,
      "loss": 0.5756,
      "step": 1016
    },
    {
      "epoch": 0.03124136024329555,
      "grad_norm": 0.812134325504303,
      "learning_rate": 1.9990203230592643e-05,
      "loss": 0.5645,
      "step": 1017
    },
    {
      "epoch": 0.03127207937824471,
      "grad_norm": 0.3393416404724121,
      "learning_rate": 1.999018183209331e-05,
      "loss": 0.5099,
      "step": 1018
    },
    {
      "epoch": 0.03130279851319387,
      "grad_norm": 0.3292752802371979,
      "learning_rate": 1.999016041026121e-05,
      "loss": 0.6746,
      "step": 1019
    },
    {
      "epoch": 0.03133351764814303,
      "grad_norm": 0.3554602265357971,
      "learning_rate": 1.99901389650964e-05,
      "loss": 0.6105,
      "step": 1020
    },
    {
      "epoch": 0.031364236783092185,
      "grad_norm": 0.3844868838787079,
      "learning_rate": 1.9990117496598913e-05,
      "loss": 0.6186,
      "step": 1021
    },
    {
      "epoch": 0.031394955918041346,
      "grad_norm": 0.38540178537368774,
      "learning_rate": 1.9990096004768812e-05,
      "loss": 0.7329,
      "step": 1022
    },
    {
      "epoch": 0.03142567505299051,
      "grad_norm": 0.37618565559387207,
      "learning_rate": 1.9990074489606144e-05,
      "loss": 0.6144,
      "step": 1023
    },
    {
      "epoch": 0.03145639418793967,
      "grad_norm": 0.3909849524497986,
      "learning_rate": 1.999005295111096e-05,
      "loss": 0.6905,
      "step": 1024
    },
    {
      "epoch": 0.03148711332288883,
      "grad_norm": 0.43792369961738586,
      "learning_rate": 1.999003138928331e-05,
      "loss": 0.6473,
      "step": 1025
    },
    {
      "epoch": 0.031517832457837985,
      "grad_norm": 0.3736238479614258,
      "learning_rate": 1.9990009804123245e-05,
      "loss": 0.679,
      "step": 1026
    },
    {
      "epoch": 0.03154855159278715,
      "grad_norm": 0.3628404140472412,
      "learning_rate": 1.9989988195630815e-05,
      "loss": 0.6373,
      "step": 1027
    },
    {
      "epoch": 0.03157927072773631,
      "grad_norm": 0.3571937084197998,
      "learning_rate": 1.9989966563806065e-05,
      "loss": 0.6805,
      "step": 1028
    },
    {
      "epoch": 0.03160998986268547,
      "grad_norm": 0.35794422030448914,
      "learning_rate": 1.9989944908649055e-05,
      "loss": 0.6166,
      "step": 1029
    },
    {
      "epoch": 0.031640708997634624,
      "grad_norm": 0.36259719729423523,
      "learning_rate": 1.998992323015983e-05,
      "loss": 0.6653,
      "step": 1030
    },
    {
      "epoch": 0.031671428132583786,
      "grad_norm": 0.3342472314834595,
      "learning_rate": 1.998990152833844e-05,
      "loss": 0.6321,
      "step": 1031
    },
    {
      "epoch": 0.03170214726753295,
      "grad_norm": 0.3626025915145874,
      "learning_rate": 1.9989879803184937e-05,
      "loss": 0.6433,
      "step": 1032
    },
    {
      "epoch": 0.03173286640248211,
      "grad_norm": 0.33758050203323364,
      "learning_rate": 1.9989858054699373e-05,
      "loss": 0.6284,
      "step": 1033
    },
    {
      "epoch": 0.03176358553743126,
      "grad_norm": 0.40521734952926636,
      "learning_rate": 1.99898362828818e-05,
      "loss": 0.7224,
      "step": 1034
    },
    {
      "epoch": 0.031794304672380425,
      "grad_norm": 0.35888582468032837,
      "learning_rate": 1.9989814487732265e-05,
      "loss": 0.6287,
      "step": 1035
    },
    {
      "epoch": 0.031825023807329586,
      "grad_norm": 0.33606529235839844,
      "learning_rate": 1.998979266925082e-05,
      "loss": 0.6271,
      "step": 1036
    },
    {
      "epoch": 0.03185574294227875,
      "grad_norm": 0.45442995429039,
      "learning_rate": 1.9989770827437515e-05,
      "loss": 0.5186,
      "step": 1037
    },
    {
      "epoch": 0.0318864620772279,
      "grad_norm": 0.3163524270057678,
      "learning_rate": 1.9989748962292407e-05,
      "loss": 0.5533,
      "step": 1038
    },
    {
      "epoch": 0.03191718121217706,
      "grad_norm": 0.33671003580093384,
      "learning_rate": 1.998972707381554e-05,
      "loss": 0.6325,
      "step": 1039
    },
    {
      "epoch": 0.031947900347126225,
      "grad_norm": 0.36726388335227966,
      "learning_rate": 1.9989705162006967e-05,
      "loss": 0.5739,
      "step": 1040
    },
    {
      "epoch": 0.031978619482075386,
      "grad_norm": 0.372280478477478,
      "learning_rate": 1.998968322686674e-05,
      "loss": 0.59,
      "step": 1041
    },
    {
      "epoch": 0.03200933861702455,
      "grad_norm": 0.33566126227378845,
      "learning_rate": 1.9989661268394915e-05,
      "loss": 0.5694,
      "step": 1042
    },
    {
      "epoch": 0.0320400577519737,
      "grad_norm": 0.36734333634376526,
      "learning_rate": 1.998963928659153e-05,
      "loss": 0.6471,
      "step": 1043
    },
    {
      "epoch": 0.032070776886922864,
      "grad_norm": 0.3498312830924988,
      "learning_rate": 1.998961728145665e-05,
      "loss": 0.6134,
      "step": 1044
    },
    {
      "epoch": 0.032101496021872025,
      "grad_norm": 0.3177320957183838,
      "learning_rate": 1.9989595252990322e-05,
      "loss": 0.5913,
      "step": 1045
    },
    {
      "epoch": 0.03213221515682119,
      "grad_norm": 0.33551815152168274,
      "learning_rate": 1.9989573201192594e-05,
      "loss": 0.6877,
      "step": 1046
    },
    {
      "epoch": 0.03216293429177034,
      "grad_norm": 0.368248850107193,
      "learning_rate": 1.998955112606352e-05,
      "loss": 0.6127,
      "step": 1047
    },
    {
      "epoch": 0.0321936534267195,
      "grad_norm": 0.32530200481414795,
      "learning_rate": 1.9989529027603155e-05,
      "loss": 0.5903,
      "step": 1048
    },
    {
      "epoch": 0.032224372561668664,
      "grad_norm": 0.3521789312362671,
      "learning_rate": 1.9989506905811544e-05,
      "loss": 0.6469,
      "step": 1049
    },
    {
      "epoch": 0.032255091696617826,
      "grad_norm": 0.3289661407470703,
      "learning_rate": 1.998948476068874e-05,
      "loss": 0.6371,
      "step": 1050
    },
    {
      "epoch": 0.03228581083156698,
      "grad_norm": 0.34857144951820374,
      "learning_rate": 1.9989462592234803e-05,
      "loss": 0.6517,
      "step": 1051
    },
    {
      "epoch": 0.03231652996651614,
      "grad_norm": 0.3379706144332886,
      "learning_rate": 1.9989440400449776e-05,
      "loss": 0.6029,
      "step": 1052
    },
    {
      "epoch": 0.0323472491014653,
      "grad_norm": 0.3823551535606384,
      "learning_rate": 1.998941818533371e-05,
      "loss": 0.6207,
      "step": 1053
    },
    {
      "epoch": 0.032377968236414464,
      "grad_norm": 0.3838878870010376,
      "learning_rate": 1.9989395946886665e-05,
      "loss": 0.5994,
      "step": 1054
    },
    {
      "epoch": 0.03240868737136362,
      "grad_norm": 0.335249662399292,
      "learning_rate": 1.9989373685108683e-05,
      "loss": 0.6793,
      "step": 1055
    },
    {
      "epoch": 0.03243940650631278,
      "grad_norm": 0.33423668146133423,
      "learning_rate": 1.9989351399999825e-05,
      "loss": 0.5696,
      "step": 1056
    },
    {
      "epoch": 0.03247012564126194,
      "grad_norm": 0.4110044836997986,
      "learning_rate": 1.9989329091560136e-05,
      "loss": 0.5768,
      "step": 1057
    },
    {
      "epoch": 0.0325008447762111,
      "grad_norm": 0.38590484857559204,
      "learning_rate": 1.9989306759789673e-05,
      "loss": 0.6829,
      "step": 1058
    },
    {
      "epoch": 0.032531563911160265,
      "grad_norm": 0.3750787377357483,
      "learning_rate": 1.9989284404688488e-05,
      "loss": 0.6269,
      "step": 1059
    },
    {
      "epoch": 0.03256228304610942,
      "grad_norm": 0.4510061740875244,
      "learning_rate": 1.998926202625663e-05,
      "loss": 0.594,
      "step": 1060
    },
    {
      "epoch": 0.03259300218105858,
      "grad_norm": 0.476958692073822,
      "learning_rate": 1.9989239624494155e-05,
      "loss": 0.682,
      "step": 1061
    },
    {
      "epoch": 0.03262372131600774,
      "grad_norm": 0.33054396510124207,
      "learning_rate": 1.998921719940111e-05,
      "loss": 0.6032,
      "step": 1062
    },
    {
      "epoch": 0.032654440450956904,
      "grad_norm": 0.3750171363353729,
      "learning_rate": 1.9989194750977553e-05,
      "loss": 0.6736,
      "step": 1063
    },
    {
      "epoch": 0.03268515958590606,
      "grad_norm": 0.38967016339302063,
      "learning_rate": 1.9989172279223532e-05,
      "loss": 0.6868,
      "step": 1064
    },
    {
      "epoch": 0.03271587872085522,
      "grad_norm": 0.3347996473312378,
      "learning_rate": 1.9989149784139103e-05,
      "loss": 0.5866,
      "step": 1065
    },
    {
      "epoch": 0.03274659785580438,
      "grad_norm": 0.3479015827178955,
      "learning_rate": 1.9989127265724317e-05,
      "loss": 0.6203,
      "step": 1066
    },
    {
      "epoch": 0.03277731699075354,
      "grad_norm": 0.3617999255657196,
      "learning_rate": 1.9989104723979225e-05,
      "loss": 0.6017,
      "step": 1067
    },
    {
      "epoch": 0.0328080361257027,
      "grad_norm": 0.42498594522476196,
      "learning_rate": 1.9989082158903885e-05,
      "loss": 0.5863,
      "step": 1068
    },
    {
      "epoch": 0.03283875526065186,
      "grad_norm": 0.32549619674682617,
      "learning_rate": 1.9989059570498343e-05,
      "loss": 0.6573,
      "step": 1069
    },
    {
      "epoch": 0.03286947439560102,
      "grad_norm": 0.3284909129142761,
      "learning_rate": 1.9989036958762654e-05,
      "loss": 0.6017,
      "step": 1070
    },
    {
      "epoch": 0.03290019353055018,
      "grad_norm": 0.8762412071228027,
      "learning_rate": 1.9989014323696873e-05,
      "loss": 0.6019,
      "step": 1071
    },
    {
      "epoch": 0.03293091266549934,
      "grad_norm": 0.3486361801624298,
      "learning_rate": 1.9988991665301053e-05,
      "loss": 0.7148,
      "step": 1072
    },
    {
      "epoch": 0.0329616318004485,
      "grad_norm": 0.3163992166519165,
      "learning_rate": 1.9988968983575245e-05,
      "loss": 0.6407,
      "step": 1073
    },
    {
      "epoch": 0.03299235093539766,
      "grad_norm": 0.46429967880249023,
      "learning_rate": 1.99889462785195e-05,
      "loss": 0.7093,
      "step": 1074
    },
    {
      "epoch": 0.03302307007034682,
      "grad_norm": 0.34972095489501953,
      "learning_rate": 1.9988923550133873e-05,
      "loss": 0.648,
      "step": 1075
    },
    {
      "epoch": 0.03305378920529598,
      "grad_norm": 0.33597803115844727,
      "learning_rate": 1.9988900798418417e-05,
      "loss": 0.6691,
      "step": 1076
    },
    {
      "epoch": 0.033084508340245136,
      "grad_norm": 0.4052893817424774,
      "learning_rate": 1.9988878023373187e-05,
      "loss": 0.6522,
      "step": 1077
    },
    {
      "epoch": 0.0331152274751943,
      "grad_norm": 0.33047980070114136,
      "learning_rate": 1.9988855224998237e-05,
      "loss": 0.6507,
      "step": 1078
    },
    {
      "epoch": 0.03314594661014346,
      "grad_norm": 0.3311249017715454,
      "learning_rate": 1.9988832403293618e-05,
      "loss": 0.6329,
      "step": 1079
    },
    {
      "epoch": 0.03317666574509262,
      "grad_norm": 0.3254491090774536,
      "learning_rate": 1.998880955825938e-05,
      "loss": 0.6163,
      "step": 1080
    },
    {
      "epoch": 0.033207384880041775,
      "grad_norm": 0.39359042048454285,
      "learning_rate": 1.9988786689895582e-05,
      "loss": 0.6223,
      "step": 1081
    },
    {
      "epoch": 0.033238104014990937,
      "grad_norm": 0.32798635959625244,
      "learning_rate": 1.998876379820227e-05,
      "loss": 0.6064,
      "step": 1082
    },
    {
      "epoch": 0.0332688231499401,
      "grad_norm": 0.3486401438713074,
      "learning_rate": 1.998874088317951e-05,
      "loss": 0.6426,
      "step": 1083
    },
    {
      "epoch": 0.03329954228488926,
      "grad_norm": 0.35808810591697693,
      "learning_rate": 1.9988717944827343e-05,
      "loss": 0.6659,
      "step": 1084
    },
    {
      "epoch": 0.033330261419838414,
      "grad_norm": 0.38490602374076843,
      "learning_rate": 1.998869498314583e-05,
      "loss": 0.6362,
      "step": 1085
    },
    {
      "epoch": 0.033360980554787575,
      "grad_norm": 0.32536956667900085,
      "learning_rate": 1.998867199813502e-05,
      "loss": 0.6341,
      "step": 1086
    },
    {
      "epoch": 0.03339169968973674,
      "grad_norm": 0.3295762240886688,
      "learning_rate": 1.9988648989794972e-05,
      "loss": 0.6103,
      "step": 1087
    },
    {
      "epoch": 0.0334224188246859,
      "grad_norm": 0.328519731760025,
      "learning_rate": 1.9988625958125735e-05,
      "loss": 0.6089,
      "step": 1088
    },
    {
      "epoch": 0.03345313795963506,
      "grad_norm": 0.3444724678993225,
      "learning_rate": 1.9988602903127365e-05,
      "loss": 0.6724,
      "step": 1089
    },
    {
      "epoch": 0.033483857094584214,
      "grad_norm": 0.3777585029602051,
      "learning_rate": 1.9988579824799914e-05,
      "loss": 0.6476,
      "step": 1090
    },
    {
      "epoch": 0.033514576229533376,
      "grad_norm": 0.32039839029312134,
      "learning_rate": 1.998855672314344e-05,
      "loss": 0.5772,
      "step": 1091
    },
    {
      "epoch": 0.03354529536448254,
      "grad_norm": 0.346576988697052,
      "learning_rate": 1.998853359815799e-05,
      "loss": 0.6687,
      "step": 1092
    },
    {
      "epoch": 0.0335760144994317,
      "grad_norm": 0.3695865571498871,
      "learning_rate": 1.9988510449843624e-05,
      "loss": 0.6032,
      "step": 1093
    },
    {
      "epoch": 0.03360673363438085,
      "grad_norm": 0.3498518466949463,
      "learning_rate": 1.9988487278200397e-05,
      "loss": 0.6022,
      "step": 1094
    },
    {
      "epoch": 0.033637452769330015,
      "grad_norm": 0.4260594844818115,
      "learning_rate": 1.9988464083228358e-05,
      "loss": 0.6013,
      "step": 1095
    },
    {
      "epoch": 0.033668171904279176,
      "grad_norm": 0.33936771750450134,
      "learning_rate": 1.9988440864927565e-05,
      "loss": 0.6827,
      "step": 1096
    },
    {
      "epoch": 0.03369889103922834,
      "grad_norm": 0.3518911898136139,
      "learning_rate": 1.9988417623298068e-05,
      "loss": 0.6752,
      "step": 1097
    },
    {
      "epoch": 0.03372961017417749,
      "grad_norm": 0.33924180269241333,
      "learning_rate": 1.9988394358339928e-05,
      "loss": 0.711,
      "step": 1098
    },
    {
      "epoch": 0.033760329309126653,
      "grad_norm": 0.3468928933143616,
      "learning_rate": 1.998837107005319e-05,
      "loss": 0.6432,
      "step": 1099
    },
    {
      "epoch": 0.033791048444075815,
      "grad_norm": 0.3473166227340698,
      "learning_rate": 1.9988347758437917e-05,
      "loss": 0.6069,
      "step": 1100
    },
    {
      "epoch": 0.033821767579024976,
      "grad_norm": 0.33215394616127014,
      "learning_rate": 1.998832442349416e-05,
      "loss": 0.5644,
      "step": 1101
    },
    {
      "epoch": 0.03385248671397414,
      "grad_norm": 0.33224251866340637,
      "learning_rate": 1.9988301065221973e-05,
      "loss": 0.6538,
      "step": 1102
    },
    {
      "epoch": 0.03388320584892329,
      "grad_norm": 0.42301124334335327,
      "learning_rate": 1.9988277683621413e-05,
      "loss": 0.6977,
      "step": 1103
    },
    {
      "epoch": 0.033913924983872454,
      "grad_norm": 0.3450161814689636,
      "learning_rate": 1.9988254278692533e-05,
      "loss": 0.6426,
      "step": 1104
    },
    {
      "epoch": 0.033944644118821615,
      "grad_norm": 0.33796852827072144,
      "learning_rate": 1.9988230850435385e-05,
      "loss": 0.6752,
      "step": 1105
    },
    {
      "epoch": 0.03397536325377078,
      "grad_norm": 0.36280930042266846,
      "learning_rate": 1.998820739885003e-05,
      "loss": 0.7304,
      "step": 1106
    },
    {
      "epoch": 0.03400608238871993,
      "grad_norm": 0.3155999481678009,
      "learning_rate": 1.9988183923936515e-05,
      "loss": 0.645,
      "step": 1107
    },
    {
      "epoch": 0.03403680152366909,
      "grad_norm": 0.39948561787605286,
      "learning_rate": 1.99881604256949e-05,
      "loss": 0.6919,
      "step": 1108
    },
    {
      "epoch": 0.034067520658618254,
      "grad_norm": 0.3763177692890167,
      "learning_rate": 1.998813690412524e-05,
      "loss": 0.5657,
      "step": 1109
    },
    {
      "epoch": 0.034098239793567416,
      "grad_norm": 0.3410244286060333,
      "learning_rate": 1.998811335922759e-05,
      "loss": 0.6499,
      "step": 1110
    },
    {
      "epoch": 0.03412895892851657,
      "grad_norm": 0.4885820746421814,
      "learning_rate": 1.9988089791002e-05,
      "loss": 0.619,
      "step": 1111
    },
    {
      "epoch": 0.03415967806346573,
      "grad_norm": 0.36203864216804504,
      "learning_rate": 1.998806619944853e-05,
      "loss": 0.6533,
      "step": 1112
    },
    {
      "epoch": 0.03419039719841489,
      "grad_norm": 0.337883323431015,
      "learning_rate": 1.9988042584567236e-05,
      "loss": 0.5459,
      "step": 1113
    },
    {
      "epoch": 0.034221116333364054,
      "grad_norm": 0.3576014041900635,
      "learning_rate": 1.998801894635817e-05,
      "loss": 0.6642,
      "step": 1114
    },
    {
      "epoch": 0.03425183546831321,
      "grad_norm": 0.35070136189460754,
      "learning_rate": 1.9987995284821387e-05,
      "loss": 0.6656,
      "step": 1115
    },
    {
      "epoch": 0.03428255460326237,
      "grad_norm": 0.36463361978530884,
      "learning_rate": 1.9987971599956943e-05,
      "loss": 0.6276,
      "step": 1116
    },
    {
      "epoch": 0.03431327373821153,
      "grad_norm": 0.33819615840911865,
      "learning_rate": 1.9987947891764897e-05,
      "loss": 0.6317,
      "step": 1117
    },
    {
      "epoch": 0.03434399287316069,
      "grad_norm": 0.3403265178203583,
      "learning_rate": 1.99879241602453e-05,
      "loss": 0.6562,
      "step": 1118
    },
    {
      "epoch": 0.034374712008109855,
      "grad_norm": 0.35242852568626404,
      "learning_rate": 1.9987900405398207e-05,
      "loss": 0.679,
      "step": 1119
    },
    {
      "epoch": 0.03440543114305901,
      "grad_norm": 0.5605168342590332,
      "learning_rate": 1.9987876627223676e-05,
      "loss": 0.587,
      "step": 1120
    },
    {
      "epoch": 0.03443615027800817,
      "grad_norm": 0.6877058744430542,
      "learning_rate": 1.998785282572176e-05,
      "loss": 0.6493,
      "step": 1121
    },
    {
      "epoch": 0.03446686941295733,
      "grad_norm": 0.33031851053237915,
      "learning_rate": 1.9987829000892517e-05,
      "loss": 0.5746,
      "step": 1122
    },
    {
      "epoch": 0.034497588547906494,
      "grad_norm": 0.351340651512146,
      "learning_rate": 1.9987805152736e-05,
      "loss": 0.6415,
      "step": 1123
    },
    {
      "epoch": 0.03452830768285565,
      "grad_norm": 0.3523685038089752,
      "learning_rate": 1.9987781281252272e-05,
      "loss": 0.6289,
      "step": 1124
    },
    {
      "epoch": 0.03455902681780481,
      "grad_norm": 0.35850510001182556,
      "learning_rate": 1.998775738644138e-05,
      "loss": 0.6245,
      "step": 1125
    },
    {
      "epoch": 0.03458974595275397,
      "grad_norm": 0.3614632785320282,
      "learning_rate": 1.9987733468303383e-05,
      "loss": 0.6177,
      "step": 1126
    },
    {
      "epoch": 0.03462046508770313,
      "grad_norm": 0.5139718055725098,
      "learning_rate": 1.9987709526838338e-05,
      "loss": 0.6196,
      "step": 1127
    },
    {
      "epoch": 0.03465118422265229,
      "grad_norm": 0.3231205940246582,
      "learning_rate": 1.9987685562046297e-05,
      "loss": 0.5182,
      "step": 1128
    },
    {
      "epoch": 0.03468190335760145,
      "grad_norm": 0.3981630802154541,
      "learning_rate": 1.998766157392732e-05,
      "loss": 0.6017,
      "step": 1129
    },
    {
      "epoch": 0.03471262249255061,
      "grad_norm": 0.3593992590904236,
      "learning_rate": 1.9987637562481464e-05,
      "loss": 0.6839,
      "step": 1130
    },
    {
      "epoch": 0.03474334162749977,
      "grad_norm": 0.34997332096099854,
      "learning_rate": 1.998761352770878e-05,
      "loss": 0.6096,
      "step": 1131
    },
    {
      "epoch": 0.03477406076244893,
      "grad_norm": 0.3157402276992798,
      "learning_rate": 1.998758946960933e-05,
      "loss": 0.6551,
      "step": 1132
    },
    {
      "epoch": 0.03480477989739809,
      "grad_norm": 0.33537814021110535,
      "learning_rate": 1.9987565388183164e-05,
      "loss": 0.5809,
      "step": 1133
    },
    {
      "epoch": 0.03483549903234725,
      "grad_norm": 0.38313373923301697,
      "learning_rate": 1.9987541283430347e-05,
      "loss": 0.6214,
      "step": 1134
    },
    {
      "epoch": 0.03486621816729641,
      "grad_norm": 0.36110833287239075,
      "learning_rate": 1.9987517155350923e-05,
      "loss": 0.7066,
      "step": 1135
    },
    {
      "epoch": 0.03489693730224557,
      "grad_norm": 0.3341173827648163,
      "learning_rate": 1.9987493003944957e-05,
      "loss": 0.6129,
      "step": 1136
    },
    {
      "epoch": 0.034927656437194726,
      "grad_norm": 0.5185731649398804,
      "learning_rate": 1.9987468829212506e-05,
      "loss": 0.5703,
      "step": 1137
    },
    {
      "epoch": 0.03495837557214389,
      "grad_norm": 0.48208731412887573,
      "learning_rate": 1.9987444631153626e-05,
      "loss": 0.6604,
      "step": 1138
    },
    {
      "epoch": 0.03498909470709305,
      "grad_norm": 0.3346957564353943,
      "learning_rate": 1.998742040976837e-05,
      "loss": 0.6467,
      "step": 1139
    },
    {
      "epoch": 0.03501981384204221,
      "grad_norm": 0.40110841393470764,
      "learning_rate": 1.998739616505679e-05,
      "loss": 0.6154,
      "step": 1140
    },
    {
      "epoch": 0.035050532976991365,
      "grad_norm": 0.3996373116970062,
      "learning_rate": 1.9987371897018955e-05,
      "loss": 0.6254,
      "step": 1141
    },
    {
      "epoch": 0.03508125211194053,
      "grad_norm": 0.3233530819416046,
      "learning_rate": 1.9987347605654913e-05,
      "loss": 0.663,
      "step": 1142
    },
    {
      "epoch": 0.03511197124688969,
      "grad_norm": 0.3848903179168701,
      "learning_rate": 1.9987323290964725e-05,
      "loss": 0.5948,
      "step": 1143
    },
    {
      "epoch": 0.03514269038183885,
      "grad_norm": 0.3306058645248413,
      "learning_rate": 1.9987298952948446e-05,
      "loss": 0.6513,
      "step": 1144
    },
    {
      "epoch": 0.035173409516788004,
      "grad_norm": 0.37019258737564087,
      "learning_rate": 1.998727459160613e-05,
      "loss": 0.5442,
      "step": 1145
    },
    {
      "epoch": 0.035204128651737165,
      "grad_norm": 0.3646225333213806,
      "learning_rate": 1.9987250206937837e-05,
      "loss": 0.6951,
      "step": 1146
    },
    {
      "epoch": 0.03523484778668633,
      "grad_norm": 0.34737294912338257,
      "learning_rate": 1.9987225798943626e-05,
      "loss": 0.6929,
      "step": 1147
    },
    {
      "epoch": 0.03526556692163549,
      "grad_norm": 0.3375813364982605,
      "learning_rate": 1.998720136762355e-05,
      "loss": 0.6828,
      "step": 1148
    },
    {
      "epoch": 0.03529628605658465,
      "grad_norm": 0.32294291257858276,
      "learning_rate": 1.998717691297767e-05,
      "loss": 0.6447,
      "step": 1149
    },
    {
      "epoch": 0.035327005191533804,
      "grad_norm": 0.3601262867450714,
      "learning_rate": 1.998715243500604e-05,
      "loss": 0.6343,
      "step": 1150
    },
    {
      "epoch": 0.035357724326482966,
      "grad_norm": 0.3922213315963745,
      "learning_rate": 1.9987127933708715e-05,
      "loss": 0.6946,
      "step": 1151
    },
    {
      "epoch": 0.03538844346143213,
      "grad_norm": 0.34392884373664856,
      "learning_rate": 1.9987103409085758e-05,
      "loss": 0.6455,
      "step": 1152
    },
    {
      "epoch": 0.03541916259638129,
      "grad_norm": 0.32858920097351074,
      "learning_rate": 1.9987078861137225e-05,
      "loss": 0.6681,
      "step": 1153
    },
    {
      "epoch": 0.03544988173133044,
      "grad_norm": 0.33385196328163147,
      "learning_rate": 1.998705428986317e-05,
      "loss": 0.559,
      "step": 1154
    },
    {
      "epoch": 0.035480600866279605,
      "grad_norm": 0.3941601514816284,
      "learning_rate": 1.998702969526365e-05,
      "loss": 0.6134,
      "step": 1155
    },
    {
      "epoch": 0.035511320001228766,
      "grad_norm": 1.1655091047286987,
      "learning_rate": 1.9987005077338727e-05,
      "loss": 0.6687,
      "step": 1156
    },
    {
      "epoch": 0.03554203913617793,
      "grad_norm": 0.329611599445343,
      "learning_rate": 1.9986980436088457e-05,
      "loss": 0.629,
      "step": 1157
    },
    {
      "epoch": 0.03557275827112708,
      "grad_norm": 0.3688400685787201,
      "learning_rate": 1.9986955771512896e-05,
      "loss": 0.6032,
      "step": 1158
    },
    {
      "epoch": 0.035603477406076244,
      "grad_norm": 0.3553326427936554,
      "learning_rate": 1.99869310836121e-05,
      "loss": 0.7169,
      "step": 1159
    },
    {
      "epoch": 0.035634196541025405,
      "grad_norm": 0.3208097815513611,
      "learning_rate": 1.998690637238613e-05,
      "loss": 0.6528,
      "step": 1160
    },
    {
      "epoch": 0.035664915675974566,
      "grad_norm": 0.3430224359035492,
      "learning_rate": 1.9986881637835045e-05,
      "loss": 0.5713,
      "step": 1161
    },
    {
      "epoch": 0.03569563481092372,
      "grad_norm": 0.3426739573478699,
      "learning_rate": 1.9986856879958896e-05,
      "loss": 0.6446,
      "step": 1162
    },
    {
      "epoch": 0.03572635394587288,
      "grad_norm": 0.33965155482292175,
      "learning_rate": 1.998683209875775e-05,
      "loss": 0.6827,
      "step": 1163
    },
    {
      "epoch": 0.035757073080822044,
      "grad_norm": 1.1401686668395996,
      "learning_rate": 1.998680729423166e-05,
      "loss": 0.6602,
      "step": 1164
    },
    {
      "epoch": 0.035787792215771205,
      "grad_norm": 0.45226195454597473,
      "learning_rate": 1.998678246638068e-05,
      "loss": 0.5895,
      "step": 1165
    },
    {
      "epoch": 0.03581851135072037,
      "grad_norm": 0.33200159668922424,
      "learning_rate": 1.9986757615204877e-05,
      "loss": 0.6269,
      "step": 1166
    },
    {
      "epoch": 0.03584923048566952,
      "grad_norm": 0.39806219935417175,
      "learning_rate": 1.9986732740704302e-05,
      "loss": 0.5095,
      "step": 1167
    },
    {
      "epoch": 0.03587994962061868,
      "grad_norm": 0.32058918476104736,
      "learning_rate": 1.9986707842879015e-05,
      "loss": 0.6019,
      "step": 1168
    },
    {
      "epoch": 0.035910668755567844,
      "grad_norm": 0.35292816162109375,
      "learning_rate": 1.9986682921729073e-05,
      "loss": 0.6797,
      "step": 1169
    },
    {
      "epoch": 0.035941387890517006,
      "grad_norm": 0.33664676547050476,
      "learning_rate": 1.9986657977254538e-05,
      "loss": 0.6342,
      "step": 1170
    },
    {
      "epoch": 0.03597210702546616,
      "grad_norm": 0.3467969298362732,
      "learning_rate": 1.9986633009455466e-05,
      "loss": 0.5918,
      "step": 1171
    },
    {
      "epoch": 0.03600282616041532,
      "grad_norm": 0.3353050947189331,
      "learning_rate": 1.9986608018331912e-05,
      "loss": 0.647,
      "step": 1172
    },
    {
      "epoch": 0.03603354529536448,
      "grad_norm": 0.365765780210495,
      "learning_rate": 1.998658300388394e-05,
      "loss": 0.7645,
      "step": 1173
    },
    {
      "epoch": 0.036064264430313644,
      "grad_norm": 0.3525621294975281,
      "learning_rate": 1.9986557966111605e-05,
      "loss": 0.6484,
      "step": 1174
    },
    {
      "epoch": 0.0360949835652628,
      "grad_norm": 0.35533735156059265,
      "learning_rate": 1.9986532905014965e-05,
      "loss": 0.6002,
      "step": 1175
    },
    {
      "epoch": 0.03612570270021196,
      "grad_norm": 0.34509676694869995,
      "learning_rate": 1.9986507820594083e-05,
      "loss": 0.5839,
      "step": 1176
    },
    {
      "epoch": 0.03615642183516112,
      "grad_norm": 0.3451254367828369,
      "learning_rate": 1.9986482712849013e-05,
      "loss": 0.6817,
      "step": 1177
    },
    {
      "epoch": 0.03618714097011028,
      "grad_norm": 0.3528457283973694,
      "learning_rate": 1.9986457581779818e-05,
      "loss": 0.6283,
      "step": 1178
    },
    {
      "epoch": 0.036217860105059445,
      "grad_norm": 0.34501558542251587,
      "learning_rate": 1.998643242738655e-05,
      "loss": 0.6239,
      "step": 1179
    },
    {
      "epoch": 0.0362485792400086,
      "grad_norm": 0.3607727289199829,
      "learning_rate": 1.998640724966927e-05,
      "loss": 0.681,
      "step": 1180
    },
    {
      "epoch": 0.03627929837495776,
      "grad_norm": 0.36807841062545776,
      "learning_rate": 1.9986382048628043e-05,
      "loss": 0.6561,
      "step": 1181
    },
    {
      "epoch": 0.03631001750990692,
      "grad_norm": 0.30417513847351074,
      "learning_rate": 1.998635682426292e-05,
      "loss": 0.5269,
      "step": 1182
    },
    {
      "epoch": 0.036340736644856084,
      "grad_norm": 0.3167667090892792,
      "learning_rate": 1.9986331576573965e-05,
      "loss": 0.6324,
      "step": 1183
    },
    {
      "epoch": 0.03637145577980524,
      "grad_norm": 0.3423810601234436,
      "learning_rate": 1.9986306305561235e-05,
      "loss": 0.5935,
      "step": 1184
    },
    {
      "epoch": 0.0364021749147544,
      "grad_norm": 0.36603233218193054,
      "learning_rate": 1.998628101122479e-05,
      "loss": 0.6519,
      "step": 1185
    },
    {
      "epoch": 0.03643289404970356,
      "grad_norm": 0.3313036262989044,
      "learning_rate": 1.9986255693564688e-05,
      "loss": 0.6593,
      "step": 1186
    },
    {
      "epoch": 0.03646361318465272,
      "grad_norm": 0.39743563532829285,
      "learning_rate": 1.9986230352580985e-05,
      "loss": 0.6745,
      "step": 1187
    },
    {
      "epoch": 0.03649433231960188,
      "grad_norm": 0.34477776288986206,
      "learning_rate": 1.998620498827375e-05,
      "loss": 0.653,
      "step": 1188
    },
    {
      "epoch": 0.03652505145455104,
      "grad_norm": 0.40885576605796814,
      "learning_rate": 1.998617960064303e-05,
      "loss": 0.7001,
      "step": 1189
    },
    {
      "epoch": 0.0365557705895002,
      "grad_norm": 0.36339232325553894,
      "learning_rate": 1.9986154189688894e-05,
      "loss": 0.5629,
      "step": 1190
    },
    {
      "epoch": 0.03658648972444936,
      "grad_norm": 0.3135628402233124,
      "learning_rate": 1.9986128755411397e-05,
      "loss": 0.6855,
      "step": 1191
    },
    {
      "epoch": 0.036617208859398516,
      "grad_norm": 0.3271785080432892,
      "learning_rate": 1.9986103297810597e-05,
      "loss": 0.5927,
      "step": 1192
    },
    {
      "epoch": 0.03664792799434768,
      "grad_norm": 0.3556221127510071,
      "learning_rate": 1.9986077816886555e-05,
      "loss": 0.6973,
      "step": 1193
    },
    {
      "epoch": 0.03667864712929684,
      "grad_norm": 0.3333517611026764,
      "learning_rate": 1.998605231263933e-05,
      "loss": 0.633,
      "step": 1194
    },
    {
      "epoch": 0.036709366264246,
      "grad_norm": 0.38100293278694153,
      "learning_rate": 1.9986026785068986e-05,
      "loss": 0.6813,
      "step": 1195
    },
    {
      "epoch": 0.03674008539919516,
      "grad_norm": 0.3444337248802185,
      "learning_rate": 1.9986001234175578e-05,
      "loss": 0.6261,
      "step": 1196
    },
    {
      "epoch": 0.036770804534144316,
      "grad_norm": 0.362163245677948,
      "learning_rate": 1.9985975659959165e-05,
      "loss": 0.5683,
      "step": 1197
    },
    {
      "epoch": 0.03680152366909348,
      "grad_norm": 0.337381511926651,
      "learning_rate": 1.998595006241981e-05,
      "loss": 0.6431,
      "step": 1198
    },
    {
      "epoch": 0.03683224280404264,
      "grad_norm": 0.36392587423324585,
      "learning_rate": 1.998592444155757e-05,
      "loss": 0.6649,
      "step": 1199
    },
    {
      "epoch": 0.0368629619389918,
      "grad_norm": 0.393775999546051,
      "learning_rate": 1.9985898797372506e-05,
      "loss": 0.668,
      "step": 1200
    },
    {
      "epoch": 0.036893681073940955,
      "grad_norm": 0.35453563928604126,
      "learning_rate": 1.998587312986468e-05,
      "loss": 0.6413,
      "step": 1201
    },
    {
      "epoch": 0.03692440020889012,
      "grad_norm": 0.41804438829421997,
      "learning_rate": 1.9985847439034147e-05,
      "loss": 0.665,
      "step": 1202
    },
    {
      "epoch": 0.03695511934383928,
      "grad_norm": 0.34605711698532104,
      "learning_rate": 1.9985821724880972e-05,
      "loss": 0.5767,
      "step": 1203
    },
    {
      "epoch": 0.03698583847878844,
      "grad_norm": 0.4035540819168091,
      "learning_rate": 1.9985795987405213e-05,
      "loss": 0.6547,
      "step": 1204
    },
    {
      "epoch": 0.037016557613737594,
      "grad_norm": 0.36091601848602295,
      "learning_rate": 1.998577022660693e-05,
      "loss": 0.599,
      "step": 1205
    },
    {
      "epoch": 0.037047276748686755,
      "grad_norm": 0.33805254101753235,
      "learning_rate": 1.998574444248618e-05,
      "loss": 0.619,
      "step": 1206
    },
    {
      "epoch": 0.03707799588363592,
      "grad_norm": 0.3593480587005615,
      "learning_rate": 1.998571863504303e-05,
      "loss": 0.6414,
      "step": 1207
    },
    {
      "epoch": 0.03710871501858508,
      "grad_norm": 0.35659322142601013,
      "learning_rate": 1.9985692804277535e-05,
      "loss": 0.6121,
      "step": 1208
    },
    {
      "epoch": 0.03713943415353424,
      "grad_norm": 0.34227725863456726,
      "learning_rate": 1.998566695018976e-05,
      "loss": 0.7017,
      "step": 1209
    },
    {
      "epoch": 0.037170153288483394,
      "grad_norm": 0.34966111183166504,
      "learning_rate": 1.998564107277976e-05,
      "loss": 0.576,
      "step": 1210
    },
    {
      "epoch": 0.037200872423432556,
      "grad_norm": 0.3284471333026886,
      "learning_rate": 1.99856151720476e-05,
      "loss": 0.6127,
      "step": 1211
    },
    {
      "epoch": 0.03723159155838172,
      "grad_norm": 0.38893088698387146,
      "learning_rate": 1.9985589247993334e-05,
      "loss": 0.647,
      "step": 1212
    },
    {
      "epoch": 0.03726231069333088,
      "grad_norm": 0.3554762601852417,
      "learning_rate": 1.9985563300617034e-05,
      "loss": 0.619,
      "step": 1213
    },
    {
      "epoch": 0.03729302982828003,
      "grad_norm": 0.3509194850921631,
      "learning_rate": 1.998553732991875e-05,
      "loss": 0.6253,
      "step": 1214
    },
    {
      "epoch": 0.037323748963229195,
      "grad_norm": 0.3803483843803406,
      "learning_rate": 1.998551133589854e-05,
      "loss": 0.5794,
      "step": 1215
    },
    {
      "epoch": 0.037354468098178356,
      "grad_norm": 0.3450569212436676,
      "learning_rate": 1.9985485318556477e-05,
      "loss": 0.6154,
      "step": 1216
    },
    {
      "epoch": 0.03738518723312752,
      "grad_norm": 0.34689244627952576,
      "learning_rate": 1.9985459277892616e-05,
      "loss": 0.654,
      "step": 1217
    },
    {
      "epoch": 0.03741590636807667,
      "grad_norm": 1.2905505895614624,
      "learning_rate": 1.9985433213907014e-05,
      "loss": 0.6252,
      "step": 1218
    },
    {
      "epoch": 0.037446625503025834,
      "grad_norm": 0.3544299602508545,
      "learning_rate": 1.998540712659974e-05,
      "loss": 0.5893,
      "step": 1219
    },
    {
      "epoch": 0.037477344637974995,
      "grad_norm": 0.3478759527206421,
      "learning_rate": 1.9985381015970845e-05,
      "loss": 0.6743,
      "step": 1220
    },
    {
      "epoch": 0.037508063772924156,
      "grad_norm": 0.3556002676486969,
      "learning_rate": 1.99853548820204e-05,
      "loss": 0.6095,
      "step": 1221
    },
    {
      "epoch": 0.03753878290787331,
      "grad_norm": 0.380756139755249,
      "learning_rate": 1.9985328724748457e-05,
      "loss": 0.6336,
      "step": 1222
    },
    {
      "epoch": 0.03756950204282247,
      "grad_norm": 1.2980037927627563,
      "learning_rate": 1.998530254415509e-05,
      "loss": 0.6716,
      "step": 1223
    },
    {
      "epoch": 0.037600221177771634,
      "grad_norm": 0.35682734847068787,
      "learning_rate": 1.9985276340240342e-05,
      "loss": 0.6459,
      "step": 1224
    },
    {
      "epoch": 0.037630940312720795,
      "grad_norm": 0.35538023710250854,
      "learning_rate": 1.9985250113004285e-05,
      "loss": 0.5214,
      "step": 1225
    },
    {
      "epoch": 0.03766165944766996,
      "grad_norm": 0.3652734160423279,
      "learning_rate": 1.9985223862446984e-05,
      "loss": 0.6394,
      "step": 1226
    },
    {
      "epoch": 0.03769237858261911,
      "grad_norm": 0.33052316308021545,
      "learning_rate": 1.9985197588568492e-05,
      "loss": 0.5973,
      "step": 1227
    },
    {
      "epoch": 0.03772309771756827,
      "grad_norm": 0.3559899628162384,
      "learning_rate": 1.9985171291368875e-05,
      "loss": 0.6623,
      "step": 1228
    },
    {
      "epoch": 0.037753816852517434,
      "grad_norm": 0.31526419520378113,
      "learning_rate": 1.998514497084819e-05,
      "loss": 0.5926,
      "step": 1229
    },
    {
      "epoch": 0.037784535987466596,
      "grad_norm": 0.2998439371585846,
      "learning_rate": 1.9985118627006505e-05,
      "loss": 0.593,
      "step": 1230
    },
    {
      "epoch": 0.03781525512241575,
      "grad_norm": 0.3625462055206299,
      "learning_rate": 1.9985092259843878e-05,
      "loss": 0.669,
      "step": 1231
    },
    {
      "epoch": 0.03784597425736491,
      "grad_norm": 0.34353965520858765,
      "learning_rate": 1.998506586936037e-05,
      "loss": 0.6884,
      "step": 1232
    },
    {
      "epoch": 0.03787669339231407,
      "grad_norm": 0.34745660424232483,
      "learning_rate": 1.998503945555604e-05,
      "loss": 0.577,
      "step": 1233
    },
    {
      "epoch": 0.037907412527263235,
      "grad_norm": 0.3209642767906189,
      "learning_rate": 1.9985013018430957e-05,
      "loss": 0.6665,
      "step": 1234
    },
    {
      "epoch": 0.03793813166221239,
      "grad_norm": 0.42744413018226624,
      "learning_rate": 1.998498655798518e-05,
      "loss": 0.6684,
      "step": 1235
    },
    {
      "epoch": 0.03796885079716155,
      "grad_norm": 0.3818417191505432,
      "learning_rate": 1.9984960074218768e-05,
      "loss": 0.6862,
      "step": 1236
    },
    {
      "epoch": 0.03799956993211071,
      "grad_norm": 0.3814997375011444,
      "learning_rate": 1.998493356713178e-05,
      "loss": 0.666,
      "step": 1237
    },
    {
      "epoch": 0.03803028906705987,
      "grad_norm": 0.3493185341358185,
      "learning_rate": 1.9984907036724287e-05,
      "loss": 0.5934,
      "step": 1238
    },
    {
      "epoch": 0.038061008202009035,
      "grad_norm": 0.37946295738220215,
      "learning_rate": 1.9984880482996348e-05,
      "loss": 0.6088,
      "step": 1239
    },
    {
      "epoch": 0.03809172733695819,
      "grad_norm": 0.3961479663848877,
      "learning_rate": 1.998485390594802e-05,
      "loss": 0.5218,
      "step": 1240
    },
    {
      "epoch": 0.03812244647190735,
      "grad_norm": 0.39373499155044556,
      "learning_rate": 1.9984827305579366e-05,
      "loss": 0.7145,
      "step": 1241
    },
    {
      "epoch": 0.03815316560685651,
      "grad_norm": 0.9995068311691284,
      "learning_rate": 1.9984800681890456e-05,
      "loss": 0.5873,
      "step": 1242
    },
    {
      "epoch": 0.038183884741805674,
      "grad_norm": 2.5733673572540283,
      "learning_rate": 1.9984774034881343e-05,
      "loss": 0.5964,
      "step": 1243
    },
    {
      "epoch": 0.03821460387675483,
      "grad_norm": 0.39437639713287354,
      "learning_rate": 1.998474736455209e-05,
      "loss": 0.5413,
      "step": 1244
    },
    {
      "epoch": 0.03824532301170399,
      "grad_norm": 0.3916095793247223,
      "learning_rate": 1.998472067090277e-05,
      "loss": 0.6366,
      "step": 1245
    },
    {
      "epoch": 0.03827604214665315,
      "grad_norm": 0.3696109652519226,
      "learning_rate": 1.9984693953933434e-05,
      "loss": 0.6416,
      "step": 1246
    },
    {
      "epoch": 0.03830676128160231,
      "grad_norm": 0.46778205037117004,
      "learning_rate": 1.9984667213644147e-05,
      "loss": 0.6534,
      "step": 1247
    },
    {
      "epoch": 0.03833748041655147,
      "grad_norm": 0.3470768630504608,
      "learning_rate": 1.9984640450034972e-05,
      "loss": 0.6319,
      "step": 1248
    },
    {
      "epoch": 0.03836819955150063,
      "grad_norm": 0.33619794249534607,
      "learning_rate": 1.9984613663105974e-05,
      "loss": 0.6064,
      "step": 1249
    },
    {
      "epoch": 0.03839891868644979,
      "grad_norm": 0.3386102318763733,
      "learning_rate": 1.9984586852857214e-05,
      "loss": 0.6615,
      "step": 1250
    },
    {
      "epoch": 0.03842963782139895,
      "grad_norm": 0.3598247170448303,
      "learning_rate": 1.998456001928875e-05,
      "loss": 0.6221,
      "step": 1251
    },
    {
      "epoch": 0.038460356956348106,
      "grad_norm": 0.32594582438468933,
      "learning_rate": 1.9984533162400653e-05,
      "loss": 0.665,
      "step": 1252
    },
    {
      "epoch": 0.03849107609129727,
      "grad_norm": 0.5428548455238342,
      "learning_rate": 1.998450628219298e-05,
      "loss": 0.5848,
      "step": 1253
    },
    {
      "epoch": 0.03852179522624643,
      "grad_norm": 0.40160736441612244,
      "learning_rate": 1.9984479378665795e-05,
      "loss": 0.5992,
      "step": 1254
    },
    {
      "epoch": 0.03855251436119559,
      "grad_norm": 0.5563382506370544,
      "learning_rate": 1.998445245181916e-05,
      "loss": 0.7348,
      "step": 1255
    },
    {
      "epoch": 0.03858323349614475,
      "grad_norm": 0.3989725112915039,
      "learning_rate": 1.9984425501653142e-05,
      "loss": 0.6279,
      "step": 1256
    },
    {
      "epoch": 0.038613952631093906,
      "grad_norm": 0.3328264653682709,
      "learning_rate": 1.99843985281678e-05,
      "loss": 0.6831,
      "step": 1257
    },
    {
      "epoch": 0.03864467176604307,
      "grad_norm": 0.4014774262905121,
      "learning_rate": 1.9984371531363197e-05,
      "loss": 0.7586,
      "step": 1258
    },
    {
      "epoch": 0.03867539090099223,
      "grad_norm": 0.3358435034751892,
      "learning_rate": 1.9984344511239395e-05,
      "loss": 0.689,
      "step": 1259
    },
    {
      "epoch": 0.03870611003594139,
      "grad_norm": 0.43563520908355713,
      "learning_rate": 1.998431746779646e-05,
      "loss": 0.6152,
      "step": 1260
    },
    {
      "epoch": 0.038736829170890545,
      "grad_norm": 0.3358006775379181,
      "learning_rate": 1.9984290401034458e-05,
      "loss": 0.621,
      "step": 1261
    },
    {
      "epoch": 0.03876754830583971,
      "grad_norm": 0.3727252781391144,
      "learning_rate": 1.9984263310953445e-05,
      "loss": 0.7041,
      "step": 1262
    },
    {
      "epoch": 0.03879826744078887,
      "grad_norm": 0.4676095247268677,
      "learning_rate": 1.9984236197553487e-05,
      "loss": 0.6208,
      "step": 1263
    },
    {
      "epoch": 0.03882898657573803,
      "grad_norm": 0.43992066383361816,
      "learning_rate": 1.998420906083465e-05,
      "loss": 0.695,
      "step": 1264
    },
    {
      "epoch": 0.038859705710687184,
      "grad_norm": 0.3355921804904938,
      "learning_rate": 1.9984181900796997e-05,
      "loss": 0.6561,
      "step": 1265
    },
    {
      "epoch": 0.038890424845636345,
      "grad_norm": 0.42735740542411804,
      "learning_rate": 1.9984154717440588e-05,
      "loss": 0.6101,
      "step": 1266
    },
    {
      "epoch": 0.03892114398058551,
      "grad_norm": 0.34911462664604187,
      "learning_rate": 1.9984127510765486e-05,
      "loss": 0.5908,
      "step": 1267
    },
    {
      "epoch": 0.03895186311553467,
      "grad_norm": 0.3263993263244629,
      "learning_rate": 1.998410028077176e-05,
      "loss": 0.5888,
      "step": 1268
    },
    {
      "epoch": 0.03898258225048382,
      "grad_norm": 0.35734114050865173,
      "learning_rate": 1.998407302745947e-05,
      "loss": 0.6248,
      "step": 1269
    },
    {
      "epoch": 0.039013301385432984,
      "grad_norm": 0.3556295931339264,
      "learning_rate": 1.998404575082868e-05,
      "loss": 0.657,
      "step": 1270
    },
    {
      "epoch": 0.039044020520382146,
      "grad_norm": 0.3525039255619049,
      "learning_rate": 1.9984018450879456e-05,
      "loss": 0.5289,
      "step": 1271
    },
    {
      "epoch": 0.03907473965533131,
      "grad_norm": 0.3490462303161621,
      "learning_rate": 1.9983991127611855e-05,
      "loss": 0.62,
      "step": 1272
    },
    {
      "epoch": 0.03910545879028047,
      "grad_norm": 0.32000699639320374,
      "learning_rate": 1.998396378102595e-05,
      "loss": 0.5396,
      "step": 1273
    },
    {
      "epoch": 0.03913617792522962,
      "grad_norm": 0.36176151037216187,
      "learning_rate": 1.9983936411121795e-05,
      "loss": 0.6796,
      "step": 1274
    },
    {
      "epoch": 0.039166897060178785,
      "grad_norm": 0.5960634350776672,
      "learning_rate": 1.9983909017899464e-05,
      "loss": 0.5856,
      "step": 1275
    },
    {
      "epoch": 0.039197616195127946,
      "grad_norm": 0.34495842456817627,
      "learning_rate": 1.9983881601359015e-05,
      "loss": 0.6505,
      "step": 1276
    },
    {
      "epoch": 0.03922833533007711,
      "grad_norm": 0.33138707280158997,
      "learning_rate": 1.9983854161500514e-05,
      "loss": 0.5956,
      "step": 1277
    },
    {
      "epoch": 0.03925905446502626,
      "grad_norm": 0.35902804136276245,
      "learning_rate": 1.9983826698324022e-05,
      "loss": 0.6064,
      "step": 1278
    },
    {
      "epoch": 0.039289773599975424,
      "grad_norm": 0.3806832432746887,
      "learning_rate": 1.9983799211829605e-05,
      "loss": 0.642,
      "step": 1279
    },
    {
      "epoch": 0.039320492734924585,
      "grad_norm": 0.36414170265197754,
      "learning_rate": 1.9983771702017333e-05,
      "loss": 0.6582,
      "step": 1280
    },
    {
      "epoch": 0.039351211869873746,
      "grad_norm": 0.3456595540046692,
      "learning_rate": 1.998374416888726e-05,
      "loss": 0.6926,
      "step": 1281
    },
    {
      "epoch": 0.0393819310048229,
      "grad_norm": 0.331032931804657,
      "learning_rate": 1.9983716612439458e-05,
      "loss": 0.5856,
      "step": 1282
    },
    {
      "epoch": 0.03941265013977206,
      "grad_norm": 0.3527127504348755,
      "learning_rate": 1.9983689032673984e-05,
      "loss": 0.7143,
      "step": 1283
    },
    {
      "epoch": 0.039443369274721224,
      "grad_norm": 0.3437643051147461,
      "learning_rate": 1.9983661429590913e-05,
      "loss": 0.7129,
      "step": 1284
    },
    {
      "epoch": 0.039474088409670385,
      "grad_norm": 0.38078218698501587,
      "learning_rate": 1.99836338031903e-05,
      "loss": 0.6534,
      "step": 1285
    },
    {
      "epoch": 0.03950480754461955,
      "grad_norm": 0.44422438740730286,
      "learning_rate": 1.9983606153472212e-05,
      "loss": 0.8031,
      "step": 1286
    },
    {
      "epoch": 0.0395355266795687,
      "grad_norm": 0.37358132004737854,
      "learning_rate": 1.9983578480436718e-05,
      "loss": 0.6237,
      "step": 1287
    },
    {
      "epoch": 0.03956624581451786,
      "grad_norm": 0.34754785895347595,
      "learning_rate": 1.9983550784083877e-05,
      "loss": 0.6246,
      "step": 1288
    },
    {
      "epoch": 0.039596964949467024,
      "grad_norm": 0.37022921442985535,
      "learning_rate": 1.9983523064413758e-05,
      "loss": 0.6402,
      "step": 1289
    },
    {
      "epoch": 0.039627684084416186,
      "grad_norm": 0.8107430934906006,
      "learning_rate": 1.9983495321426424e-05,
      "loss": 0.6298,
      "step": 1290
    },
    {
      "epoch": 0.03965840321936534,
      "grad_norm": 0.41078561544418335,
      "learning_rate": 1.9983467555121937e-05,
      "loss": 0.6476,
      "step": 1291
    },
    {
      "epoch": 0.0396891223543145,
      "grad_norm": 0.4743632972240448,
      "learning_rate": 1.9983439765500364e-05,
      "loss": 0.6304,
      "step": 1292
    },
    {
      "epoch": 0.03971984148926366,
      "grad_norm": 0.346250057220459,
      "learning_rate": 1.998341195256177e-05,
      "loss": 0.6441,
      "step": 1293
    },
    {
      "epoch": 0.039750560624212825,
      "grad_norm": 0.37644070386886597,
      "learning_rate": 1.998338411630622e-05,
      "loss": 0.6204,
      "step": 1294
    },
    {
      "epoch": 0.03978127975916198,
      "grad_norm": 0.43439558148384094,
      "learning_rate": 1.998335625673378e-05,
      "loss": 0.657,
      "step": 1295
    },
    {
      "epoch": 0.03981199889411114,
      "grad_norm": 0.3847845196723938,
      "learning_rate": 1.9983328373844516e-05,
      "loss": 0.5702,
      "step": 1296
    },
    {
      "epoch": 0.0398427180290603,
      "grad_norm": 0.3555111885070801,
      "learning_rate": 1.998330046763849e-05,
      "loss": 0.575,
      "step": 1297
    },
    {
      "epoch": 0.03987343716400946,
      "grad_norm": 0.35155341029167175,
      "learning_rate": 1.9983272538115768e-05,
      "loss": 0.6301,
      "step": 1298
    },
    {
      "epoch": 0.03990415629895862,
      "grad_norm": 0.4040221869945526,
      "learning_rate": 1.9983244585276415e-05,
      "loss": 0.6567,
      "step": 1299
    },
    {
      "epoch": 0.03993487543390778,
      "grad_norm": 0.33256182074546814,
      "learning_rate": 1.99832166091205e-05,
      "loss": 0.5542,
      "step": 1300
    },
    {
      "epoch": 0.03996559456885694,
      "grad_norm": 0.4011290967464447,
      "learning_rate": 1.9983188609648084e-05,
      "loss": 0.657,
      "step": 1301
    },
    {
      "epoch": 0.0399963137038061,
      "grad_norm": 0.3467792272567749,
      "learning_rate": 1.998316058685923e-05,
      "loss": 0.6367,
      "step": 1302
    },
    {
      "epoch": 0.040027032838755264,
      "grad_norm": 0.3791506886482239,
      "learning_rate": 1.9983132540754012e-05,
      "loss": 0.6649,
      "step": 1303
    },
    {
      "epoch": 0.04005775197370442,
      "grad_norm": 0.3354448974132538,
      "learning_rate": 1.998310447133249e-05,
      "loss": 0.6354,
      "step": 1304
    },
    {
      "epoch": 0.04008847110865358,
      "grad_norm": 0.3629630208015442,
      "learning_rate": 1.998307637859473e-05,
      "loss": 0.685,
      "step": 1305
    },
    {
      "epoch": 0.04011919024360274,
      "grad_norm": 0.3527342975139618,
      "learning_rate": 1.9983048262540796e-05,
      "loss": 0.6809,
      "step": 1306
    },
    {
      "epoch": 0.0401499093785519,
      "grad_norm": 0.3353877365589142,
      "learning_rate": 1.9983020123170757e-05,
      "loss": 0.6398,
      "step": 1307
    },
    {
      "epoch": 0.04018062851350106,
      "grad_norm": 0.43226921558380127,
      "learning_rate": 1.998299196048468e-05,
      "loss": 0.5849,
      "step": 1308
    },
    {
      "epoch": 0.04021134764845022,
      "grad_norm": 0.39846912026405334,
      "learning_rate": 1.9982963774482624e-05,
      "loss": 0.5311,
      "step": 1309
    },
    {
      "epoch": 0.04024206678339938,
      "grad_norm": 0.4026656746864319,
      "learning_rate": 1.9982935565164662e-05,
      "loss": 0.6953,
      "step": 1310
    },
    {
      "epoch": 0.04027278591834854,
      "grad_norm": 0.46269744634628296,
      "learning_rate": 1.9982907332530855e-05,
      "loss": 0.7117,
      "step": 1311
    },
    {
      "epoch": 0.040303505053297696,
      "grad_norm": 0.333202987909317,
      "learning_rate": 1.998287907658127e-05,
      "loss": 0.6078,
      "step": 1312
    },
    {
      "epoch": 0.04033422418824686,
      "grad_norm": 0.8267314434051514,
      "learning_rate": 1.9982850797315977e-05,
      "loss": 0.5873,
      "step": 1313
    },
    {
      "epoch": 0.04036494332319602,
      "grad_norm": 0.32276901602745056,
      "learning_rate": 1.9982822494735036e-05,
      "loss": 0.6274,
      "step": 1314
    },
    {
      "epoch": 0.04039566245814518,
      "grad_norm": 0.4270782768726349,
      "learning_rate": 1.9982794168838513e-05,
      "loss": 0.6155,
      "step": 1315
    },
    {
      "epoch": 0.04042638159309434,
      "grad_norm": 0.36716511845588684,
      "learning_rate": 1.998276581962648e-05,
      "loss": 0.6267,
      "step": 1316
    },
    {
      "epoch": 0.040457100728043496,
      "grad_norm": 0.3697338402271271,
      "learning_rate": 1.9982737447099005e-05,
      "loss": 0.6471,
      "step": 1317
    },
    {
      "epoch": 0.04048781986299266,
      "grad_norm": 0.3661898076534271,
      "learning_rate": 1.998270905125614e-05,
      "loss": 0.6449,
      "step": 1318
    },
    {
      "epoch": 0.04051853899794182,
      "grad_norm": 0.32294878363609314,
      "learning_rate": 1.9982680632097967e-05,
      "loss": 0.6529,
      "step": 1319
    },
    {
      "epoch": 0.04054925813289098,
      "grad_norm": 0.34810781478881836,
      "learning_rate": 1.9982652189624544e-05,
      "loss": 0.6789,
      "step": 1320
    },
    {
      "epoch": 0.040579977267840135,
      "grad_norm": 0.32672739028930664,
      "learning_rate": 1.9982623723835942e-05,
      "loss": 0.6444,
      "step": 1321
    },
    {
      "epoch": 0.0406106964027893,
      "grad_norm": 0.36555731296539307,
      "learning_rate": 1.9982595234732224e-05,
      "loss": 0.659,
      "step": 1322
    },
    {
      "epoch": 0.04064141553773846,
      "grad_norm": 0.3887861371040344,
      "learning_rate": 1.998256672231346e-05,
      "loss": 0.5944,
      "step": 1323
    },
    {
      "epoch": 0.04067213467268762,
      "grad_norm": 0.3768608570098877,
      "learning_rate": 1.998253818657971e-05,
      "loss": 0.6287,
      "step": 1324
    },
    {
      "epoch": 0.040702853807636774,
      "grad_norm": 0.3339996039867401,
      "learning_rate": 1.9982509627531046e-05,
      "loss": 0.582,
      "step": 1325
    },
    {
      "epoch": 0.040733572942585936,
      "grad_norm": 0.33874088525772095,
      "learning_rate": 1.9982481045167536e-05,
      "loss": 0.6492,
      "step": 1326
    },
    {
      "epoch": 0.0407642920775351,
      "grad_norm": 0.43983194231987,
      "learning_rate": 1.998245243948924e-05,
      "loss": 0.5989,
      "step": 1327
    },
    {
      "epoch": 0.04079501121248426,
      "grad_norm": 0.3397119343280792,
      "learning_rate": 1.9982423810496235e-05,
      "loss": 0.591,
      "step": 1328
    },
    {
      "epoch": 0.04082573034743341,
      "grad_norm": 0.3484622538089752,
      "learning_rate": 1.9982395158188577e-05,
      "loss": 0.6904,
      "step": 1329
    },
    {
      "epoch": 0.040856449482382574,
      "grad_norm": 0.3267402648925781,
      "learning_rate": 1.998236648256634e-05,
      "loss": 0.6489,
      "step": 1330
    },
    {
      "epoch": 0.040887168617331736,
      "grad_norm": 0.36569881439208984,
      "learning_rate": 1.9982337783629588e-05,
      "loss": 0.6858,
      "step": 1331
    },
    {
      "epoch": 0.0409178877522809,
      "grad_norm": 0.33135324716567993,
      "learning_rate": 1.998230906137839e-05,
      "loss": 0.6024,
      "step": 1332
    },
    {
      "epoch": 0.04094860688723006,
      "grad_norm": 0.3579927384853363,
      "learning_rate": 1.998228031581281e-05,
      "loss": 0.6235,
      "step": 1333
    },
    {
      "epoch": 0.04097932602217921,
      "grad_norm": 0.554391622543335,
      "learning_rate": 1.998225154693292e-05,
      "loss": 0.7404,
      "step": 1334
    },
    {
      "epoch": 0.041010045157128375,
      "grad_norm": 0.34545570611953735,
      "learning_rate": 1.9982222754738784e-05,
      "loss": 0.7289,
      "step": 1335
    },
    {
      "epoch": 0.041040764292077536,
      "grad_norm": 0.35289642214775085,
      "learning_rate": 1.998219393923047e-05,
      "loss": 0.6505,
      "step": 1336
    },
    {
      "epoch": 0.0410714834270267,
      "grad_norm": 0.35704490542411804,
      "learning_rate": 1.9982165100408042e-05,
      "loss": 0.6668,
      "step": 1337
    },
    {
      "epoch": 0.04110220256197585,
      "grad_norm": 0.3648998439311981,
      "learning_rate": 1.998213623827157e-05,
      "loss": 0.5093,
      "step": 1338
    },
    {
      "epoch": 0.041132921696925014,
      "grad_norm": 0.5972452163696289,
      "learning_rate": 1.9982107352821124e-05,
      "loss": 0.6392,
      "step": 1339
    },
    {
      "epoch": 0.041163640831874175,
      "grad_norm": 0.34235504269599915,
      "learning_rate": 1.9982078444056768e-05,
      "loss": 0.6845,
      "step": 1340
    },
    {
      "epoch": 0.041194359966823337,
      "grad_norm": 0.40513327717781067,
      "learning_rate": 1.9982049511978575e-05,
      "loss": 0.6188,
      "step": 1341
    },
    {
      "epoch": 0.04122507910177249,
      "grad_norm": 0.3554416298866272,
      "learning_rate": 1.9982020556586604e-05,
      "loss": 0.5828,
      "step": 1342
    },
    {
      "epoch": 0.04125579823672165,
      "grad_norm": 0.35149258375167847,
      "learning_rate": 1.9981991577880925e-05,
      "loss": 0.631,
      "step": 1343
    },
    {
      "epoch": 0.041286517371670814,
      "grad_norm": 0.31266769766807556,
      "learning_rate": 1.998196257586161e-05,
      "loss": 0.7006,
      "step": 1344
    },
    {
      "epoch": 0.041317236506619975,
      "grad_norm": 0.33909475803375244,
      "learning_rate": 1.9981933550528728e-05,
      "loss": 0.6174,
      "step": 1345
    },
    {
      "epoch": 0.04134795564156914,
      "grad_norm": 0.36623668670654297,
      "learning_rate": 1.9981904501882336e-05,
      "loss": 0.6313,
      "step": 1346
    },
    {
      "epoch": 0.04137867477651829,
      "grad_norm": 0.3229750394821167,
      "learning_rate": 1.9981875429922514e-05,
      "loss": 0.582,
      "step": 1347
    },
    {
      "epoch": 0.04140939391146745,
      "grad_norm": 0.3288065791130066,
      "learning_rate": 1.9981846334649322e-05,
      "loss": 0.6085,
      "step": 1348
    },
    {
      "epoch": 0.041440113046416614,
      "grad_norm": 0.3143009841442108,
      "learning_rate": 1.998181721606283e-05,
      "loss": 0.5698,
      "step": 1349
    },
    {
      "epoch": 0.041470832181365776,
      "grad_norm": 0.3113131523132324,
      "learning_rate": 1.998178807416311e-05,
      "loss": 0.6169,
      "step": 1350
    },
    {
      "epoch": 0.04150155131631493,
      "grad_norm": 0.3403845429420471,
      "learning_rate": 1.9981758908950226e-05,
      "loss": 0.6312,
      "step": 1351
    },
    {
      "epoch": 0.04153227045126409,
      "grad_norm": 0.37382861971855164,
      "learning_rate": 1.9981729720424247e-05,
      "loss": 0.7344,
      "step": 1352
    },
    {
      "epoch": 0.04156298958621325,
      "grad_norm": 0.4893076419830322,
      "learning_rate": 1.998170050858524e-05,
      "loss": 0.6182,
      "step": 1353
    },
    {
      "epoch": 0.041593708721162415,
      "grad_norm": 0.3977046310901642,
      "learning_rate": 1.9981671273433273e-05,
      "loss": 0.6471,
      "step": 1354
    },
    {
      "epoch": 0.04162442785611157,
      "grad_norm": 0.3733634948730469,
      "learning_rate": 1.9981642014968417e-05,
      "loss": 0.6244,
      "step": 1355
    },
    {
      "epoch": 0.04165514699106073,
      "grad_norm": 0.40803149342536926,
      "learning_rate": 1.998161273319074e-05,
      "loss": 0.5487,
      "step": 1356
    },
    {
      "epoch": 0.04168586612600989,
      "grad_norm": 0.340304434299469,
      "learning_rate": 1.998158342810031e-05,
      "loss": 0.643,
      "step": 1357
    },
    {
      "epoch": 0.04171658526095905,
      "grad_norm": 0.3310611844062805,
      "learning_rate": 1.9981554099697194e-05,
      "loss": 0.6541,
      "step": 1358
    },
    {
      "epoch": 0.04174730439590821,
      "grad_norm": 0.34450089931488037,
      "learning_rate": 1.998152474798146e-05,
      "loss": 0.6408,
      "step": 1359
    },
    {
      "epoch": 0.04177802353085737,
      "grad_norm": 0.33022892475128174,
      "learning_rate": 1.998149537295318e-05,
      "loss": 0.6216,
      "step": 1360
    },
    {
      "epoch": 0.04180874266580653,
      "grad_norm": 0.3132493793964386,
      "learning_rate": 1.998146597461242e-05,
      "loss": 0.509,
      "step": 1361
    },
    {
      "epoch": 0.04183946180075569,
      "grad_norm": 0.38062700629234314,
      "learning_rate": 1.9981436552959246e-05,
      "loss": 0.6868,
      "step": 1362
    },
    {
      "epoch": 0.041870180935704854,
      "grad_norm": 0.469441294670105,
      "learning_rate": 1.9981407107993733e-05,
      "loss": 0.6549,
      "step": 1363
    },
    {
      "epoch": 0.04190090007065401,
      "grad_norm": 0.3415747880935669,
      "learning_rate": 1.9981377639715943e-05,
      "loss": 0.65,
      "step": 1364
    },
    {
      "epoch": 0.04193161920560317,
      "grad_norm": 0.31847482919692993,
      "learning_rate": 1.9981348148125953e-05,
      "loss": 0.7101,
      "step": 1365
    },
    {
      "epoch": 0.04196233834055233,
      "grad_norm": 0.32223549485206604,
      "learning_rate": 1.9981318633223824e-05,
      "loss": 0.6363,
      "step": 1366
    },
    {
      "epoch": 0.04199305747550149,
      "grad_norm": 0.3406137526035309,
      "learning_rate": 1.998128909500963e-05,
      "loss": 0.6027,
      "step": 1367
    },
    {
      "epoch": 0.04202377661045065,
      "grad_norm": 0.38347071409225464,
      "learning_rate": 1.998125953348344e-05,
      "loss": 0.5966,
      "step": 1368
    },
    {
      "epoch": 0.04205449574539981,
      "grad_norm": 0.35691577196121216,
      "learning_rate": 1.9981229948645317e-05,
      "loss": 0.5651,
      "step": 1369
    },
    {
      "epoch": 0.04208521488034897,
      "grad_norm": 0.3855243921279907,
      "learning_rate": 1.998120034049534e-05,
      "loss": 0.6293,
      "step": 1370
    },
    {
      "epoch": 0.04211593401529813,
      "grad_norm": 0.34988829493522644,
      "learning_rate": 1.998117070903357e-05,
      "loss": 0.5896,
      "step": 1371
    },
    {
      "epoch": 0.042146653150247286,
      "grad_norm": 0.3378292918205261,
      "learning_rate": 1.9981141054260076e-05,
      "loss": 0.6267,
      "step": 1372
    },
    {
      "epoch": 0.04217737228519645,
      "grad_norm": 0.3438066840171814,
      "learning_rate": 1.9981111376174932e-05,
      "loss": 0.5228,
      "step": 1373
    },
    {
      "epoch": 0.04220809142014561,
      "grad_norm": 0.34191304445266724,
      "learning_rate": 1.9981081674778205e-05,
      "loss": 0.6482,
      "step": 1374
    },
    {
      "epoch": 0.04223881055509477,
      "grad_norm": 0.34952497482299805,
      "learning_rate": 1.9981051950069962e-05,
      "loss": 0.6408,
      "step": 1375
    },
    {
      "epoch": 0.042269529690043925,
      "grad_norm": 0.3141106367111206,
      "learning_rate": 1.998102220205028e-05,
      "loss": 0.6703,
      "step": 1376
    },
    {
      "epoch": 0.042300248824993086,
      "grad_norm": 0.39198148250579834,
      "learning_rate": 1.998099243071922e-05,
      "loss": 0.6121,
      "step": 1377
    },
    {
      "epoch": 0.04233096795994225,
      "grad_norm": 0.5472900867462158,
      "learning_rate": 1.998096263607686e-05,
      "loss": 0.6347,
      "step": 1378
    },
    {
      "epoch": 0.04236168709489141,
      "grad_norm": 0.3278624415397644,
      "learning_rate": 1.998093281812326e-05,
      "loss": 0.6486,
      "step": 1379
    },
    {
      "epoch": 0.04239240622984057,
      "grad_norm": 0.33763113617897034,
      "learning_rate": 1.9980902976858496e-05,
      "loss": 0.5879,
      "step": 1380
    },
    {
      "epoch": 0.042423125364789725,
      "grad_norm": 0.40945038199424744,
      "learning_rate": 1.9980873112282637e-05,
      "loss": 0.6476,
      "step": 1381
    },
    {
      "epoch": 0.04245384449973889,
      "grad_norm": 0.3597598373889923,
      "learning_rate": 1.9980843224395746e-05,
      "loss": 0.6091,
      "step": 1382
    },
    {
      "epoch": 0.04248456363468805,
      "grad_norm": 0.35325631499290466,
      "learning_rate": 1.9980813313197906e-05,
      "loss": 0.6006,
      "step": 1383
    },
    {
      "epoch": 0.04251528276963721,
      "grad_norm": 0.3527797758579254,
      "learning_rate": 1.9980783378689176e-05,
      "loss": 0.6606,
      "step": 1384
    },
    {
      "epoch": 0.042546001904586364,
      "grad_norm": 0.3115088641643524,
      "learning_rate": 1.998075342086963e-05,
      "loss": 0.5569,
      "step": 1385
    },
    {
      "epoch": 0.042576721039535526,
      "grad_norm": 0.3726767599582672,
      "learning_rate": 1.998072343973934e-05,
      "loss": 0.6297,
      "step": 1386
    },
    {
      "epoch": 0.04260744017448469,
      "grad_norm": 0.3506571054458618,
      "learning_rate": 1.9980693435298367e-05,
      "loss": 0.5663,
      "step": 1387
    },
    {
      "epoch": 0.04263815930943385,
      "grad_norm": 0.3337964415550232,
      "learning_rate": 1.998066340754679e-05,
      "loss": 0.6094,
      "step": 1388
    },
    {
      "epoch": 0.042668878444383,
      "grad_norm": 0.31702691316604614,
      "learning_rate": 1.998063335648468e-05,
      "loss": 0.5518,
      "step": 1389
    },
    {
      "epoch": 0.042699597579332164,
      "grad_norm": 0.41954272985458374,
      "learning_rate": 1.99806032821121e-05,
      "loss": 0.6333,
      "step": 1390
    },
    {
      "epoch": 0.042730316714281326,
      "grad_norm": 0.33430716395378113,
      "learning_rate": 1.9980573184429125e-05,
      "loss": 0.5633,
      "step": 1391
    },
    {
      "epoch": 0.04276103584923049,
      "grad_norm": 0.33189457654953003,
      "learning_rate": 1.9980543063435826e-05,
      "loss": 0.6754,
      "step": 1392
    },
    {
      "epoch": 0.04279175498417965,
      "grad_norm": 0.34805548191070557,
      "learning_rate": 1.9980512919132272e-05,
      "loss": 0.5565,
      "step": 1393
    },
    {
      "epoch": 0.0428224741191288,
      "grad_norm": 0.3961887061595917,
      "learning_rate": 1.9980482751518527e-05,
      "loss": 0.6858,
      "step": 1394
    },
    {
      "epoch": 0.042853193254077965,
      "grad_norm": 0.36680492758750916,
      "learning_rate": 1.9980452560594673e-05,
      "loss": 0.5789,
      "step": 1395
    },
    {
      "epoch": 0.042883912389027126,
      "grad_norm": 0.43212810158729553,
      "learning_rate": 1.9980422346360777e-05,
      "loss": 0.6794,
      "step": 1396
    },
    {
      "epoch": 0.04291463152397629,
      "grad_norm": 0.3258790671825409,
      "learning_rate": 1.9980392108816904e-05,
      "loss": 0.6235,
      "step": 1397
    },
    {
      "epoch": 0.04294535065892544,
      "grad_norm": 0.33876070380210876,
      "learning_rate": 1.9980361847963128e-05,
      "loss": 0.574,
      "step": 1398
    },
    {
      "epoch": 0.042976069793874604,
      "grad_norm": 0.3398304879665375,
      "learning_rate": 1.9980331563799523e-05,
      "loss": 0.6843,
      "step": 1399
    },
    {
      "epoch": 0.043006788928823765,
      "grad_norm": 0.37226569652557373,
      "learning_rate": 1.998030125632615e-05,
      "loss": 0.5872,
      "step": 1400
    },
    {
      "epoch": 0.04303750806377293,
      "grad_norm": 0.3657737374305725,
      "learning_rate": 1.9980270925543093e-05,
      "loss": 0.6204,
      "step": 1401
    },
    {
      "epoch": 0.04306822719872208,
      "grad_norm": 0.7144231200218201,
      "learning_rate": 1.9980240571450414e-05,
      "loss": 0.641,
      "step": 1402
    },
    {
      "epoch": 0.04309894633367124,
      "grad_norm": 0.3397647738456726,
      "learning_rate": 1.9980210194048184e-05,
      "loss": 0.6162,
      "step": 1403
    },
    {
      "epoch": 0.043129665468620404,
      "grad_norm": 0.3834957480430603,
      "learning_rate": 1.998017979333648e-05,
      "loss": 0.5438,
      "step": 1404
    },
    {
      "epoch": 0.043160384603569565,
      "grad_norm": 0.3419320583343506,
      "learning_rate": 1.9980149369315363e-05,
      "loss": 0.5891,
      "step": 1405
    },
    {
      "epoch": 0.04319110373851872,
      "grad_norm": 0.36903810501098633,
      "learning_rate": 1.9980118921984915e-05,
      "loss": 0.6397,
      "step": 1406
    },
    {
      "epoch": 0.04322182287346788,
      "grad_norm": 0.32629451155662537,
      "learning_rate": 1.99800884513452e-05,
      "loss": 0.639,
      "step": 1407
    },
    {
      "epoch": 0.04325254200841704,
      "grad_norm": 0.37720727920532227,
      "learning_rate": 1.9980057957396296e-05,
      "loss": 0.6481,
      "step": 1408
    },
    {
      "epoch": 0.043283261143366204,
      "grad_norm": 0.3799186050891876,
      "learning_rate": 1.9980027440138268e-05,
      "loss": 0.6832,
      "step": 1409
    },
    {
      "epoch": 0.043313980278315366,
      "grad_norm": 0.3101624548435211,
      "learning_rate": 1.9979996899571187e-05,
      "loss": 0.6249,
      "step": 1410
    },
    {
      "epoch": 0.04334469941326452,
      "grad_norm": 0.3461057245731354,
      "learning_rate": 1.9979966335695127e-05,
      "loss": 0.6777,
      "step": 1411
    },
    {
      "epoch": 0.04337541854821368,
      "grad_norm": 0.328911691904068,
      "learning_rate": 1.9979935748510158e-05,
      "loss": 0.7588,
      "step": 1412
    },
    {
      "epoch": 0.04340613768316284,
      "grad_norm": 0.34436020255088806,
      "learning_rate": 1.9979905138016353e-05,
      "loss": 0.6467,
      "step": 1413
    },
    {
      "epoch": 0.043436856818112005,
      "grad_norm": 0.36390817165374756,
      "learning_rate": 1.997987450421378e-05,
      "loss": 0.6275,
      "step": 1414
    },
    {
      "epoch": 0.04346757595306116,
      "grad_norm": 0.38903191685676575,
      "learning_rate": 1.9979843847102515e-05,
      "loss": 0.6571,
      "step": 1415
    },
    {
      "epoch": 0.04349829508801032,
      "grad_norm": 0.33003270626068115,
      "learning_rate": 1.997981316668263e-05,
      "loss": 0.6261,
      "step": 1416
    },
    {
      "epoch": 0.04352901422295948,
      "grad_norm": 0.31904131174087524,
      "learning_rate": 1.997978246295419e-05,
      "loss": 0.551,
      "step": 1417
    },
    {
      "epoch": 0.043559733357908643,
      "grad_norm": 0.4109552800655365,
      "learning_rate": 1.9979751735917275e-05,
      "loss": 0.6741,
      "step": 1418
    },
    {
      "epoch": 0.0435904524928578,
      "grad_norm": 0.6238108277320862,
      "learning_rate": 1.997972098557195e-05,
      "loss": 0.6126,
      "step": 1419
    },
    {
      "epoch": 0.04362117162780696,
      "grad_norm": 0.3267028331756592,
      "learning_rate": 1.9979690211918293e-05,
      "loss": 0.5529,
      "step": 1420
    },
    {
      "epoch": 0.04365189076275612,
      "grad_norm": 0.33773040771484375,
      "learning_rate": 1.9979659414956368e-05,
      "loss": 0.5857,
      "step": 1421
    },
    {
      "epoch": 0.04368260989770528,
      "grad_norm": 0.3527114987373352,
      "learning_rate": 1.9979628594686255e-05,
      "loss": 0.5598,
      "step": 1422
    },
    {
      "epoch": 0.043713329032654444,
      "grad_norm": 0.3142206072807312,
      "learning_rate": 1.997959775110802e-05,
      "loss": 0.6842,
      "step": 1423
    },
    {
      "epoch": 0.0437440481676036,
      "grad_norm": 0.3595605790615082,
      "learning_rate": 1.997956688422174e-05,
      "loss": 0.6865,
      "step": 1424
    },
    {
      "epoch": 0.04377476730255276,
      "grad_norm": 0.36609315872192383,
      "learning_rate": 1.9979535994027485e-05,
      "loss": 0.5621,
      "step": 1425
    },
    {
      "epoch": 0.04380548643750192,
      "grad_norm": 0.3660450577735901,
      "learning_rate": 1.9979505080525323e-05,
      "loss": 0.6267,
      "step": 1426
    },
    {
      "epoch": 0.04383620557245108,
      "grad_norm": 0.33784806728363037,
      "learning_rate": 1.997947414371533e-05,
      "loss": 0.6512,
      "step": 1427
    },
    {
      "epoch": 0.04386692470740024,
      "grad_norm": 0.32937437295913696,
      "learning_rate": 1.997944318359758e-05,
      "loss": 0.672,
      "step": 1428
    },
    {
      "epoch": 0.0438976438423494,
      "grad_norm": 0.3826597332954407,
      "learning_rate": 1.9979412200172147e-05,
      "loss": 0.5954,
      "step": 1429
    },
    {
      "epoch": 0.04392836297729856,
      "grad_norm": 0.3578501045703888,
      "learning_rate": 1.9979381193439095e-05,
      "loss": 0.7192,
      "step": 1430
    },
    {
      "epoch": 0.04395908211224772,
      "grad_norm": 2.2008795738220215,
      "learning_rate": 1.9979350163398504e-05,
      "loss": 0.6604,
      "step": 1431
    },
    {
      "epoch": 0.043989801247196876,
      "grad_norm": 0.32416272163391113,
      "learning_rate": 1.9979319110050443e-05,
      "loss": 0.6595,
      "step": 1432
    },
    {
      "epoch": 0.04402052038214604,
      "grad_norm": 0.39766889810562134,
      "learning_rate": 1.9979288033394983e-05,
      "loss": 0.6021,
      "step": 1433
    },
    {
      "epoch": 0.0440512395170952,
      "grad_norm": 0.4091089367866516,
      "learning_rate": 1.9979256933432202e-05,
      "loss": 0.6592,
      "step": 1434
    },
    {
      "epoch": 0.04408195865204436,
      "grad_norm": 0.42348575592041016,
      "learning_rate": 1.9979225810162167e-05,
      "loss": 0.5446,
      "step": 1435
    },
    {
      "epoch": 0.044112677786993515,
      "grad_norm": 0.3059660792350769,
      "learning_rate": 1.9979194663584954e-05,
      "loss": 0.6734,
      "step": 1436
    },
    {
      "epoch": 0.044143396921942676,
      "grad_norm": 0.30541545152664185,
      "learning_rate": 1.9979163493700637e-05,
      "loss": 0.5623,
      "step": 1437
    },
    {
      "epoch": 0.04417411605689184,
      "grad_norm": 0.3510250747203827,
      "learning_rate": 1.9979132300509283e-05,
      "loss": 0.6416,
      "step": 1438
    },
    {
      "epoch": 0.044204835191841,
      "grad_norm": 0.31188827753067017,
      "learning_rate": 1.997910108401097e-05,
      "loss": 0.5719,
      "step": 1439
    },
    {
      "epoch": 0.04423555432679016,
      "grad_norm": 0.3400861620903015,
      "learning_rate": 1.9979069844205773e-05,
      "loss": 0.6733,
      "step": 1440
    },
    {
      "epoch": 0.044266273461739315,
      "grad_norm": 0.3580463230609894,
      "learning_rate": 1.9979038581093757e-05,
      "loss": 0.6159,
      "step": 1441
    },
    {
      "epoch": 0.04429699259668848,
      "grad_norm": 0.3390311300754547,
      "learning_rate": 1.9979007294675e-05,
      "loss": 0.6727,
      "step": 1442
    },
    {
      "epoch": 0.04432771173163764,
      "grad_norm": 0.3564579486846924,
      "learning_rate": 1.9978975984949574e-05,
      "loss": 0.6026,
      "step": 1443
    },
    {
      "epoch": 0.0443584308665868,
      "grad_norm": 0.35155758261680603,
      "learning_rate": 1.9978944651917556e-05,
      "loss": 0.6054,
      "step": 1444
    },
    {
      "epoch": 0.044389150001535954,
      "grad_norm": 0.34290528297424316,
      "learning_rate": 1.9978913295579013e-05,
      "loss": 0.6391,
      "step": 1445
    },
    {
      "epoch": 0.044419869136485116,
      "grad_norm": 0.3204345107078552,
      "learning_rate": 1.9978881915934023e-05,
      "loss": 0.5447,
      "step": 1446
    },
    {
      "epoch": 0.04445058827143428,
      "grad_norm": 0.34730637073516846,
      "learning_rate": 1.9978850512982654e-05,
      "loss": 0.5865,
      "step": 1447
    },
    {
      "epoch": 0.04448130740638344,
      "grad_norm": 0.36416298151016235,
      "learning_rate": 1.9978819086724987e-05,
      "loss": 0.6315,
      "step": 1448
    },
    {
      "epoch": 0.04451202654133259,
      "grad_norm": 0.32476168870925903,
      "learning_rate": 1.9978787637161087e-05,
      "loss": 0.6705,
      "step": 1449
    },
    {
      "epoch": 0.044542745676281754,
      "grad_norm": 0.3341827094554901,
      "learning_rate": 1.9978756164291034e-05,
      "loss": 0.586,
      "step": 1450
    },
    {
      "epoch": 0.044573464811230916,
      "grad_norm": 0.35912227630615234,
      "learning_rate": 1.99787246681149e-05,
      "loss": 0.5861,
      "step": 1451
    },
    {
      "epoch": 0.04460418394618008,
      "grad_norm": 0.34328487515449524,
      "learning_rate": 1.9978693148632757e-05,
      "loss": 0.6699,
      "step": 1452
    },
    {
      "epoch": 0.04463490308112924,
      "grad_norm": 0.3288676142692566,
      "learning_rate": 1.997866160584468e-05,
      "loss": 0.6401,
      "step": 1453
    },
    {
      "epoch": 0.04466562221607839,
      "grad_norm": 0.32186517119407654,
      "learning_rate": 1.997863003975074e-05,
      "loss": 0.6666,
      "step": 1454
    },
    {
      "epoch": 0.044696341351027555,
      "grad_norm": 0.3401786983013153,
      "learning_rate": 1.9978598450351013e-05,
      "loss": 0.6003,
      "step": 1455
    },
    {
      "epoch": 0.044727060485976716,
      "grad_norm": 0.3354983627796173,
      "learning_rate": 1.997856683764557e-05,
      "loss": 0.6607,
      "step": 1456
    },
    {
      "epoch": 0.04475777962092588,
      "grad_norm": 0.36971738934516907,
      "learning_rate": 1.997853520163449e-05,
      "loss": 0.6413,
      "step": 1457
    },
    {
      "epoch": 0.04478849875587503,
      "grad_norm": 0.4143010675907135,
      "learning_rate": 1.9978503542317845e-05,
      "loss": 0.6348,
      "step": 1458
    },
    {
      "epoch": 0.044819217890824194,
      "grad_norm": 0.46499133110046387,
      "learning_rate": 1.9978471859695706e-05,
      "loss": 0.6554,
      "step": 1459
    },
    {
      "epoch": 0.044849937025773355,
      "grad_norm": 0.5254920125007629,
      "learning_rate": 1.9978440153768153e-05,
      "loss": 0.6116,
      "step": 1460
    },
    {
      "epoch": 0.04488065616072252,
      "grad_norm": 0.38139066100120544,
      "learning_rate": 1.9978408424535255e-05,
      "loss": 0.5671,
      "step": 1461
    },
    {
      "epoch": 0.04491137529567167,
      "grad_norm": 0.31457269191741943,
      "learning_rate": 1.997837667199708e-05,
      "loss": 0.6146,
      "step": 1462
    },
    {
      "epoch": 0.04494209443062083,
      "grad_norm": 0.3491078019142151,
      "learning_rate": 1.9978344896153718e-05,
      "loss": 0.5766,
      "step": 1463
    },
    {
      "epoch": 0.044972813565569994,
      "grad_norm": 0.36150890588760376,
      "learning_rate": 1.9978313097005232e-05,
      "loss": 0.6061,
      "step": 1464
    },
    {
      "epoch": 0.045003532700519155,
      "grad_norm": 0.37765732407569885,
      "learning_rate": 1.99782812745517e-05,
      "loss": 0.6203,
      "step": 1465
    },
    {
      "epoch": 0.04503425183546831,
      "grad_norm": 0.3623577952384949,
      "learning_rate": 1.9978249428793193e-05,
      "loss": 0.5941,
      "step": 1466
    },
    {
      "epoch": 0.04506497097041747,
      "grad_norm": 0.36662980914115906,
      "learning_rate": 1.9978217559729788e-05,
      "loss": 0.6235,
      "step": 1467
    },
    {
      "epoch": 0.04509569010536663,
      "grad_norm": 0.33251652121543884,
      "learning_rate": 1.997818566736156e-05,
      "loss": 0.5661,
      "step": 1468
    },
    {
      "epoch": 0.045126409240315794,
      "grad_norm": 0.3359599709510803,
      "learning_rate": 1.997815375168858e-05,
      "loss": 0.5544,
      "step": 1469
    },
    {
      "epoch": 0.045157128375264956,
      "grad_norm": 0.32382041215896606,
      "learning_rate": 1.9978121812710927e-05,
      "loss": 0.5927,
      "step": 1470
    },
    {
      "epoch": 0.04518784751021411,
      "grad_norm": 0.3252922296524048,
      "learning_rate": 1.9978089850428676e-05,
      "loss": 0.4875,
      "step": 1471
    },
    {
      "epoch": 0.04521856664516327,
      "grad_norm": 0.33955198526382446,
      "learning_rate": 1.9978057864841896e-05,
      "loss": 0.5927,
      "step": 1472
    },
    {
      "epoch": 0.04524928578011243,
      "grad_norm": 0.3254089653491974,
      "learning_rate": 1.9978025855950665e-05,
      "loss": 0.5663,
      "step": 1473
    },
    {
      "epoch": 0.045280004915061595,
      "grad_norm": 0.3900725841522217,
      "learning_rate": 1.9977993823755057e-05,
      "loss": 0.6608,
      "step": 1474
    },
    {
      "epoch": 0.04531072405001075,
      "grad_norm": 0.31601065397262573,
      "learning_rate": 1.997796176825515e-05,
      "loss": 0.5711,
      "step": 1475
    },
    {
      "epoch": 0.04534144318495991,
      "grad_norm": 0.34350335597991943,
      "learning_rate": 1.9977929689451016e-05,
      "loss": 0.585,
      "step": 1476
    },
    {
      "epoch": 0.04537216231990907,
      "grad_norm": 0.33578652143478394,
      "learning_rate": 1.9977897587342728e-05,
      "loss": 0.6119,
      "step": 1477
    },
    {
      "epoch": 0.045402881454858234,
      "grad_norm": 0.340859979391098,
      "learning_rate": 1.9977865461930368e-05,
      "loss": 0.5741,
      "step": 1478
    },
    {
      "epoch": 0.04543360058980739,
      "grad_norm": 0.435679167509079,
      "learning_rate": 1.9977833313214004e-05,
      "loss": 0.5694,
      "step": 1479
    },
    {
      "epoch": 0.04546431972475655,
      "grad_norm": 0.3523082137107849,
      "learning_rate": 1.997780114119371e-05,
      "loss": 0.6662,
      "step": 1480
    },
    {
      "epoch": 0.04549503885970571,
      "grad_norm": 0.38861361145973206,
      "learning_rate": 1.9977768945869572e-05,
      "loss": 0.6694,
      "step": 1481
    },
    {
      "epoch": 0.04552575799465487,
      "grad_norm": 0.35401690006256104,
      "learning_rate": 1.997773672724165e-05,
      "loss": 0.6435,
      "step": 1482
    },
    {
      "epoch": 0.04555647712960403,
      "grad_norm": 0.5448992252349854,
      "learning_rate": 1.9977704485310032e-05,
      "loss": 0.6583,
      "step": 1483
    },
    {
      "epoch": 0.04558719626455319,
      "grad_norm": 0.367035448551178,
      "learning_rate": 1.9977672220074786e-05,
      "loss": 0.6472,
      "step": 1484
    },
    {
      "epoch": 0.04561791539950235,
      "grad_norm": 0.30278944969177246,
      "learning_rate": 1.997763993153599e-05,
      "loss": 0.6311,
      "step": 1485
    },
    {
      "epoch": 0.04564863453445151,
      "grad_norm": 0.3472312390804291,
      "learning_rate": 1.997760761969372e-05,
      "loss": 0.6651,
      "step": 1486
    },
    {
      "epoch": 0.04567935366940067,
      "grad_norm": 0.40772393345832825,
      "learning_rate": 1.997757528454805e-05,
      "loss": 0.5877,
      "step": 1487
    },
    {
      "epoch": 0.04571007280434983,
      "grad_norm": 0.3308549225330353,
      "learning_rate": 1.997754292609906e-05,
      "loss": 0.7004,
      "step": 1488
    },
    {
      "epoch": 0.04574079193929899,
      "grad_norm": 0.3354812264442444,
      "learning_rate": 1.9977510544346815e-05,
      "loss": 0.6888,
      "step": 1489
    },
    {
      "epoch": 0.04577151107424815,
      "grad_norm": 0.37962910532951355,
      "learning_rate": 1.9977478139291403e-05,
      "loss": 0.6213,
      "step": 1490
    },
    {
      "epoch": 0.04580223020919731,
      "grad_norm": 0.31664037704467773,
      "learning_rate": 1.997744571093289e-05,
      "loss": 0.63,
      "step": 1491
    },
    {
      "epoch": 0.045832949344146466,
      "grad_norm": 0.31045863032341003,
      "learning_rate": 1.9977413259271356e-05,
      "loss": 0.5555,
      "step": 1492
    },
    {
      "epoch": 0.04586366847909563,
      "grad_norm": 0.3578523099422455,
      "learning_rate": 1.997738078430688e-05,
      "loss": 0.6412,
      "step": 1493
    },
    {
      "epoch": 0.04589438761404479,
      "grad_norm": 0.31463494896888733,
      "learning_rate": 1.997734828603953e-05,
      "loss": 0.5666,
      "step": 1494
    },
    {
      "epoch": 0.04592510674899395,
      "grad_norm": 0.34017422795295715,
      "learning_rate": 1.9977315764469387e-05,
      "loss": 0.6019,
      "step": 1495
    },
    {
      "epoch": 0.045955825883943105,
      "grad_norm": 0.3557920455932617,
      "learning_rate": 1.9977283219596527e-05,
      "loss": 0.6685,
      "step": 1496
    },
    {
      "epoch": 0.045986545018892266,
      "grad_norm": 0.3509226441383362,
      "learning_rate": 1.9977250651421028e-05,
      "loss": 0.6637,
      "step": 1497
    },
    {
      "epoch": 0.04601726415384143,
      "grad_norm": 0.3282249867916107,
      "learning_rate": 1.997721805994296e-05,
      "loss": 0.5905,
      "step": 1498
    },
    {
      "epoch": 0.04604798328879059,
      "grad_norm": 0.3344109058380127,
      "learning_rate": 1.9977185445162402e-05,
      "loss": 0.5815,
      "step": 1499
    },
    {
      "epoch": 0.04607870242373975,
      "grad_norm": 0.3479396402835846,
      "learning_rate": 1.997715280707943e-05,
      "loss": 0.6773,
      "step": 1500
    },
    {
      "epoch": 0.046109421558688905,
      "grad_norm": 0.4208886921405792,
      "learning_rate": 1.9977120145694126e-05,
      "loss": 0.5612,
      "step": 1501
    },
    {
      "epoch": 0.04614014069363807,
      "grad_norm": 0.40888920426368713,
      "learning_rate": 1.997708746100656e-05,
      "loss": 0.6609,
      "step": 1502
    },
    {
      "epoch": 0.04617085982858723,
      "grad_norm": 0.3395008146762848,
      "learning_rate": 1.9977054753016806e-05,
      "loss": 0.5936,
      "step": 1503
    },
    {
      "epoch": 0.04620157896353639,
      "grad_norm": 0.3486707806587219,
      "learning_rate": 1.9977022021724944e-05,
      "loss": 0.6374,
      "step": 1504
    },
    {
      "epoch": 0.046232298098485544,
      "grad_norm": 0.32248854637145996,
      "learning_rate": 1.9976989267131053e-05,
      "loss": 0.5666,
      "step": 1505
    },
    {
      "epoch": 0.046263017233434706,
      "grad_norm": 0.3303990662097931,
      "learning_rate": 1.9976956489235204e-05,
      "loss": 0.5912,
      "step": 1506
    },
    {
      "epoch": 0.04629373636838387,
      "grad_norm": 0.36752432584762573,
      "learning_rate": 1.997692368803748e-05,
      "loss": 0.5867,
      "step": 1507
    },
    {
      "epoch": 0.04632445550333303,
      "grad_norm": 0.3922474980354309,
      "learning_rate": 1.9976890863537948e-05,
      "loss": 0.6185,
      "step": 1508
    },
    {
      "epoch": 0.04635517463828218,
      "grad_norm": 0.3277745842933655,
      "learning_rate": 1.9976858015736697e-05,
      "loss": 0.6353,
      "step": 1509
    },
    {
      "epoch": 0.046385893773231344,
      "grad_norm": 0.33256980776786804,
      "learning_rate": 1.9976825144633793e-05,
      "loss": 0.6097,
      "step": 1510
    },
    {
      "epoch": 0.046416612908180506,
      "grad_norm": 0.359630823135376,
      "learning_rate": 1.9976792250229318e-05,
      "loss": 0.6131,
      "step": 1511
    },
    {
      "epoch": 0.04644733204312967,
      "grad_norm": 0.5256035923957825,
      "learning_rate": 1.997675933252335e-05,
      "loss": 0.5965,
      "step": 1512
    },
    {
      "epoch": 0.04647805117807882,
      "grad_norm": 0.41148775815963745,
      "learning_rate": 1.9976726391515958e-05,
      "loss": 0.7274,
      "step": 1513
    },
    {
      "epoch": 0.04650877031302798,
      "grad_norm": 0.3620133697986603,
      "learning_rate": 1.9976693427207232e-05,
      "loss": 0.5982,
      "step": 1514
    },
    {
      "epoch": 0.046539489447977145,
      "grad_norm": 0.33658626675605774,
      "learning_rate": 1.9976660439597237e-05,
      "loss": 0.6405,
      "step": 1515
    },
    {
      "epoch": 0.046570208582926306,
      "grad_norm": 0.3355967700481415,
      "learning_rate": 1.997662742868606e-05,
      "loss": 0.7334,
      "step": 1516
    },
    {
      "epoch": 0.04660092771787547,
      "grad_norm": 0.3297376036643982,
      "learning_rate": 1.997659439447377e-05,
      "loss": 0.6044,
      "step": 1517
    },
    {
      "epoch": 0.04663164685282462,
      "grad_norm": 0.3391709625720978,
      "learning_rate": 1.997656133696044e-05,
      "loss": 0.6688,
      "step": 1518
    },
    {
      "epoch": 0.046662365987773784,
      "grad_norm": 0.3304705023765564,
      "learning_rate": 1.9976528256146162e-05,
      "loss": 0.6482,
      "step": 1519
    },
    {
      "epoch": 0.046693085122722945,
      "grad_norm": 0.3371427059173584,
      "learning_rate": 1.9976495152031007e-05,
      "loss": 0.5933,
      "step": 1520
    },
    {
      "epoch": 0.04672380425767211,
      "grad_norm": 0.3329218327999115,
      "learning_rate": 1.9976462024615045e-05,
      "loss": 0.6615,
      "step": 1521
    },
    {
      "epoch": 0.04675452339262126,
      "grad_norm": 0.3517970144748688,
      "learning_rate": 1.9976428873898366e-05,
      "loss": 0.7042,
      "step": 1522
    },
    {
      "epoch": 0.04678524252757042,
      "grad_norm": 0.32224196195602417,
      "learning_rate": 1.9976395699881034e-05,
      "loss": 0.5852,
      "step": 1523
    },
    {
      "epoch": 0.046815961662519584,
      "grad_norm": 0.33342045545578003,
      "learning_rate": 1.9976362502563137e-05,
      "loss": 0.6849,
      "step": 1524
    },
    {
      "epoch": 0.046846680797468745,
      "grad_norm": 0.32047998905181885,
      "learning_rate": 1.997632928194475e-05,
      "loss": 0.6463,
      "step": 1525
    },
    {
      "epoch": 0.0468773999324179,
      "grad_norm": 0.3257700800895691,
      "learning_rate": 1.9976296038025948e-05,
      "loss": 0.6344,
      "step": 1526
    },
    {
      "epoch": 0.04690811906736706,
      "grad_norm": 0.35298335552215576,
      "learning_rate": 1.9976262770806806e-05,
      "loss": 0.5705,
      "step": 1527
    },
    {
      "epoch": 0.04693883820231622,
      "grad_norm": 0.3183249831199646,
      "learning_rate": 1.9976229480287406e-05,
      "loss": 0.6058,
      "step": 1528
    },
    {
      "epoch": 0.046969557337265384,
      "grad_norm": 0.31748098134994507,
      "learning_rate": 1.9976196166467828e-05,
      "loss": 0.5766,
      "step": 1529
    },
    {
      "epoch": 0.047000276472214546,
      "grad_norm": 0.3378646969795227,
      "learning_rate": 1.997616282934815e-05,
      "loss": 0.6195,
      "step": 1530
    },
    {
      "epoch": 0.0470309956071637,
      "grad_norm": 0.33636677265167236,
      "learning_rate": 1.9976129468928444e-05,
      "loss": 0.5486,
      "step": 1531
    },
    {
      "epoch": 0.04706171474211286,
      "grad_norm": 0.346770703792572,
      "learning_rate": 1.997609608520879e-05,
      "loss": 0.6155,
      "step": 1532
    },
    {
      "epoch": 0.04709243387706202,
      "grad_norm": 0.3523155450820923,
      "learning_rate": 1.9976062678189265e-05,
      "loss": 0.701,
      "step": 1533
    },
    {
      "epoch": 0.047123153012011185,
      "grad_norm": 0.33391839265823364,
      "learning_rate": 1.997602924786995e-05,
      "loss": 0.5706,
      "step": 1534
    },
    {
      "epoch": 0.04715387214696034,
      "grad_norm": 0.3638920187950134,
      "learning_rate": 1.9975995794250925e-05,
      "loss": 0.5597,
      "step": 1535
    },
    {
      "epoch": 0.0471845912819095,
      "grad_norm": 0.3479497730731964,
      "learning_rate": 1.9975962317332263e-05,
      "loss": 0.5867,
      "step": 1536
    },
    {
      "epoch": 0.04721531041685866,
      "grad_norm": 0.3112768530845642,
      "learning_rate": 1.9975928817114046e-05,
      "loss": 0.6336,
      "step": 1537
    },
    {
      "epoch": 0.047246029551807824,
      "grad_norm": 0.3886876702308655,
      "learning_rate": 1.997589529359635e-05,
      "loss": 0.6129,
      "step": 1538
    },
    {
      "epoch": 0.04727674868675698,
      "grad_norm": 0.4790090024471283,
      "learning_rate": 1.9975861746779252e-05,
      "loss": 0.6039,
      "step": 1539
    },
    {
      "epoch": 0.04730746782170614,
      "grad_norm": 0.3459738492965698,
      "learning_rate": 1.9975828176662832e-05,
      "loss": 0.6329,
      "step": 1540
    },
    {
      "epoch": 0.0473381869566553,
      "grad_norm": 0.3439803719520569,
      "learning_rate": 1.997579458324717e-05,
      "loss": 0.6069,
      "step": 1541
    },
    {
      "epoch": 0.04736890609160446,
      "grad_norm": 0.3112871050834656,
      "learning_rate": 1.9975760966532345e-05,
      "loss": 0.5899,
      "step": 1542
    },
    {
      "epoch": 0.04739962522655362,
      "grad_norm": 0.33760762214660645,
      "learning_rate": 1.997572732651843e-05,
      "loss": 0.6275,
      "step": 1543
    },
    {
      "epoch": 0.04743034436150278,
      "grad_norm": 0.32981356978416443,
      "learning_rate": 1.997569366320551e-05,
      "loss": 0.6024,
      "step": 1544
    },
    {
      "epoch": 0.04746106349645194,
      "grad_norm": 0.4020029902458191,
      "learning_rate": 1.9975659976593657e-05,
      "loss": 0.6039,
      "step": 1545
    },
    {
      "epoch": 0.0474917826314011,
      "grad_norm": 0.3561566174030304,
      "learning_rate": 1.9975626266682957e-05,
      "loss": 0.7257,
      "step": 1546
    },
    {
      "epoch": 0.04752250176635026,
      "grad_norm": 0.33351147174835205,
      "learning_rate": 1.9975592533473484e-05,
      "loss": 0.6535,
      "step": 1547
    },
    {
      "epoch": 0.04755322090129942,
      "grad_norm": 0.32751715183258057,
      "learning_rate": 1.997555877696532e-05,
      "loss": 0.5961,
      "step": 1548
    },
    {
      "epoch": 0.04758394003624858,
      "grad_norm": 0.6751850247383118,
      "learning_rate": 1.997552499715854e-05,
      "loss": 0.6425,
      "step": 1549
    },
    {
      "epoch": 0.04761465917119774,
      "grad_norm": 0.33825552463531494,
      "learning_rate": 1.9975491194053223e-05,
      "loss": 0.6531,
      "step": 1550
    },
    {
      "epoch": 0.0476453783061469,
      "grad_norm": 0.33470311760902405,
      "learning_rate": 1.9975457367649448e-05,
      "loss": 0.5947,
      "step": 1551
    },
    {
      "epoch": 0.047676097441096056,
      "grad_norm": 0.37409093976020813,
      "learning_rate": 1.99754235179473e-05,
      "loss": 0.5729,
      "step": 1552
    },
    {
      "epoch": 0.04770681657604522,
      "grad_norm": 0.34536245465278625,
      "learning_rate": 1.9975389644946853e-05,
      "loss": 0.6385,
      "step": 1553
    },
    {
      "epoch": 0.04773753571099438,
      "grad_norm": 0.3762564957141876,
      "learning_rate": 1.9975355748648185e-05,
      "loss": 0.6596,
      "step": 1554
    },
    {
      "epoch": 0.04776825484594354,
      "grad_norm": 0.3271220624446869,
      "learning_rate": 1.997532182905138e-05,
      "loss": 0.6539,
      "step": 1555
    },
    {
      "epoch": 0.047798973980892695,
      "grad_norm": 0.3872227370738983,
      "learning_rate": 1.997528788615651e-05,
      "loss": 0.7396,
      "step": 1556
    },
    {
      "epoch": 0.047829693115841856,
      "grad_norm": 0.31722933053970337,
      "learning_rate": 1.9975253919963663e-05,
      "loss": 0.6518,
      "step": 1557
    },
    {
      "epoch": 0.04786041225079102,
      "grad_norm": 0.3098757266998291,
      "learning_rate": 1.9975219930472913e-05,
      "loss": 0.6431,
      "step": 1558
    },
    {
      "epoch": 0.04789113138574018,
      "grad_norm": 0.3384096622467041,
      "learning_rate": 1.997518591768434e-05,
      "loss": 0.6132,
      "step": 1559
    },
    {
      "epoch": 0.04792185052068934,
      "grad_norm": 0.4054543673992157,
      "learning_rate": 1.997515188159802e-05,
      "loss": 0.5855,
      "step": 1560
    },
    {
      "epoch": 0.047952569655638495,
      "grad_norm": 0.35157856345176697,
      "learning_rate": 1.997511782221404e-05,
      "loss": 0.6538,
      "step": 1561
    },
    {
      "epoch": 0.04798328879058766,
      "grad_norm": 0.37904587388038635,
      "learning_rate": 1.9975083739532474e-05,
      "loss": 0.5607,
      "step": 1562
    },
    {
      "epoch": 0.04801400792553682,
      "grad_norm": 0.3330012261867523,
      "learning_rate": 1.9975049633553402e-05,
      "loss": 0.6413,
      "step": 1563
    },
    {
      "epoch": 0.04804472706048598,
      "grad_norm": 0.3533659875392914,
      "learning_rate": 1.9975015504276907e-05,
      "loss": 0.6096,
      "step": 1564
    },
    {
      "epoch": 0.048075446195435134,
      "grad_norm": 0.316693514585495,
      "learning_rate": 1.9974981351703064e-05,
      "loss": 0.6011,
      "step": 1565
    },
    {
      "epoch": 0.048106165330384296,
      "grad_norm": 0.36805659532546997,
      "learning_rate": 1.9974947175831957e-05,
      "loss": 0.7139,
      "step": 1566
    },
    {
      "epoch": 0.04813688446533346,
      "grad_norm": 0.35783979296684265,
      "learning_rate": 1.9974912976663666e-05,
      "loss": 0.5848,
      "step": 1567
    },
    {
      "epoch": 0.04816760360028262,
      "grad_norm": 0.3219115138053894,
      "learning_rate": 1.997487875419827e-05,
      "loss": 0.5772,
      "step": 1568
    },
    {
      "epoch": 0.04819832273523177,
      "grad_norm": 0.3617928624153137,
      "learning_rate": 1.9974844508435844e-05,
      "loss": 0.6541,
      "step": 1569
    },
    {
      "epoch": 0.048229041870180935,
      "grad_norm": 0.3374931514263153,
      "learning_rate": 1.9974810239376476e-05,
      "loss": 0.6277,
      "step": 1570
    },
    {
      "epoch": 0.048259761005130096,
      "grad_norm": 0.32027724385261536,
      "learning_rate": 1.997477594702024e-05,
      "loss": 0.6263,
      "step": 1571
    },
    {
      "epoch": 0.04829048014007926,
      "grad_norm": 0.3411986529827118,
      "learning_rate": 1.9974741631367214e-05,
      "loss": 0.6527,
      "step": 1572
    },
    {
      "epoch": 0.04832119927502841,
      "grad_norm": 0.3594294488430023,
      "learning_rate": 1.9974707292417487e-05,
      "loss": 0.6526,
      "step": 1573
    },
    {
      "epoch": 0.04835191840997757,
      "grad_norm": 0.37739384174346924,
      "learning_rate": 1.9974672930171136e-05,
      "loss": 0.6564,
      "step": 1574
    },
    {
      "epoch": 0.048382637544926735,
      "grad_norm": 0.4125100076198578,
      "learning_rate": 1.9974638544628237e-05,
      "loss": 0.6811,
      "step": 1575
    },
    {
      "epoch": 0.048413356679875896,
      "grad_norm": 0.4873066842556,
      "learning_rate": 1.9974604135788873e-05,
      "loss": 0.6472,
      "step": 1576
    },
    {
      "epoch": 0.04844407581482506,
      "grad_norm": 0.3150804340839386,
      "learning_rate": 1.9974569703653128e-05,
      "loss": 0.5568,
      "step": 1577
    },
    {
      "epoch": 0.04847479494977421,
      "grad_norm": 0.3466322422027588,
      "learning_rate": 1.9974535248221073e-05,
      "loss": 0.6358,
      "step": 1578
    },
    {
      "epoch": 0.048505514084723374,
      "grad_norm": 0.3265446722507477,
      "learning_rate": 1.9974500769492797e-05,
      "loss": 0.6912,
      "step": 1579
    },
    {
      "epoch": 0.048536233219672535,
      "grad_norm": 0.37474381923675537,
      "learning_rate": 1.9974466267468377e-05,
      "loss": 0.5628,
      "step": 1580
    },
    {
      "epoch": 0.0485669523546217,
      "grad_norm": 0.6572012901306152,
      "learning_rate": 1.9974431742147898e-05,
      "loss": 0.6057,
      "step": 1581
    },
    {
      "epoch": 0.04859767148957085,
      "grad_norm": 0.3566594123840332,
      "learning_rate": 1.9974397193531434e-05,
      "loss": 0.6826,
      "step": 1582
    },
    {
      "epoch": 0.04862839062452001,
      "grad_norm": 0.5015448927879333,
      "learning_rate": 1.997436262161907e-05,
      "loss": 0.5952,
      "step": 1583
    },
    {
      "epoch": 0.048659109759469174,
      "grad_norm": 0.33665817975997925,
      "learning_rate": 1.9974328026410883e-05,
      "loss": 0.586,
      "step": 1584
    },
    {
      "epoch": 0.048689828894418336,
      "grad_norm": 0.3693210482597351,
      "learning_rate": 1.9974293407906958e-05,
      "loss": 0.6243,
      "step": 1585
    },
    {
      "epoch": 0.04872054802936749,
      "grad_norm": 0.36246031522750854,
      "learning_rate": 1.9974258766107373e-05,
      "loss": 0.6524,
      "step": 1586
    },
    {
      "epoch": 0.04875126716431665,
      "grad_norm": 0.4176059365272522,
      "learning_rate": 1.9974224101012214e-05,
      "loss": 0.6688,
      "step": 1587
    },
    {
      "epoch": 0.04878198629926581,
      "grad_norm": 0.3751685917377472,
      "learning_rate": 1.9974189412621556e-05,
      "loss": 0.6376,
      "step": 1588
    },
    {
      "epoch": 0.048812705434214974,
      "grad_norm": 0.37172165513038635,
      "learning_rate": 1.9974154700935478e-05,
      "loss": 0.6676,
      "step": 1589
    },
    {
      "epoch": 0.04884342456916413,
      "grad_norm": 0.37124791741371155,
      "learning_rate": 1.997411996595407e-05,
      "loss": 0.5672,
      "step": 1590
    },
    {
      "epoch": 0.04887414370411329,
      "grad_norm": 0.3678755760192871,
      "learning_rate": 1.9974085207677406e-05,
      "loss": 0.624,
      "step": 1591
    },
    {
      "epoch": 0.04890486283906245,
      "grad_norm": 0.3361211121082306,
      "learning_rate": 1.997405042610557e-05,
      "loss": 0.5884,
      "step": 1592
    },
    {
      "epoch": 0.04893558197401161,
      "grad_norm": 0.35418471693992615,
      "learning_rate": 1.9974015621238646e-05,
      "loss": 0.633,
      "step": 1593
    },
    {
      "epoch": 0.048966301108960775,
      "grad_norm": 0.3511559069156647,
      "learning_rate": 1.997398079307671e-05,
      "loss": 0.6021,
      "step": 1594
    },
    {
      "epoch": 0.04899702024390993,
      "grad_norm": 0.3330918252468109,
      "learning_rate": 1.997394594161984e-05,
      "loss": 0.6972,
      "step": 1595
    },
    {
      "epoch": 0.04902773937885909,
      "grad_norm": 0.3222728967666626,
      "learning_rate": 1.9973911066868127e-05,
      "loss": 0.5819,
      "step": 1596
    },
    {
      "epoch": 0.04905845851380825,
      "grad_norm": 0.31858038902282715,
      "learning_rate": 1.997387616882165e-05,
      "loss": 0.5669,
      "step": 1597
    },
    {
      "epoch": 0.049089177648757414,
      "grad_norm": 0.33087068796157837,
      "learning_rate": 1.9973841247480487e-05,
      "loss": 0.5517,
      "step": 1598
    },
    {
      "epoch": 0.04911989678370657,
      "grad_norm": 0.33781805634498596,
      "learning_rate": 1.997380630284472e-05,
      "loss": 0.636,
      "step": 1599
    },
    {
      "epoch": 0.04915061591865573,
      "grad_norm": 0.4171277582645416,
      "learning_rate": 1.997377133491443e-05,
      "loss": 0.5651,
      "step": 1600
    },
    {
      "epoch": 0.04918133505360489,
      "grad_norm": 0.3270309269428253,
      "learning_rate": 1.9973736343689703e-05,
      "loss": 0.61,
      "step": 1601
    },
    {
      "epoch": 0.04921205418855405,
      "grad_norm": 0.32625848054885864,
      "learning_rate": 1.997370132917062e-05,
      "loss": 0.6293,
      "step": 1602
    },
    {
      "epoch": 0.04924277332350321,
      "grad_norm": 0.4175812900066376,
      "learning_rate": 1.997366629135726e-05,
      "loss": 0.6014,
      "step": 1603
    },
    {
      "epoch": 0.04927349245845237,
      "grad_norm": 0.6452588438987732,
      "learning_rate": 1.9973631230249704e-05,
      "loss": 0.5702,
      "step": 1604
    },
    {
      "epoch": 0.04930421159340153,
      "grad_norm": 0.30845406651496887,
      "learning_rate": 1.9973596145848035e-05,
      "loss": 0.6482,
      "step": 1605
    },
    {
      "epoch": 0.04933493072835069,
      "grad_norm": 0.3601158857345581,
      "learning_rate": 1.9973561038152337e-05,
      "loss": 0.5936,
      "step": 1606
    },
    {
      "epoch": 0.04936564986329985,
      "grad_norm": 0.38791725039482117,
      "learning_rate": 1.997352590716269e-05,
      "loss": 0.7201,
      "step": 1607
    },
    {
      "epoch": 0.04939636899824901,
      "grad_norm": 0.31345584988594055,
      "learning_rate": 1.997349075287918e-05,
      "loss": 0.6502,
      "step": 1608
    },
    {
      "epoch": 0.04942708813319817,
      "grad_norm": 0.3697737157344818,
      "learning_rate": 1.9973455575301886e-05,
      "loss": 0.6035,
      "step": 1609
    },
    {
      "epoch": 0.04945780726814733,
      "grad_norm": 0.32363954186439514,
      "learning_rate": 1.9973420374430886e-05,
      "loss": 0.7158,
      "step": 1610
    },
    {
      "epoch": 0.04948852640309649,
      "grad_norm": 0.3198433220386505,
      "learning_rate": 1.9973385150266267e-05,
      "loss": 0.6393,
      "step": 1611
    },
    {
      "epoch": 0.049519245538045646,
      "grad_norm": 0.3102641701698303,
      "learning_rate": 1.9973349902808113e-05,
      "loss": 0.6113,
      "step": 1612
    },
    {
      "epoch": 0.04954996467299481,
      "grad_norm": 0.34853553771972656,
      "learning_rate": 1.99733146320565e-05,
      "loss": 0.6422,
      "step": 1613
    },
    {
      "epoch": 0.04958068380794397,
      "grad_norm": 0.31733274459838867,
      "learning_rate": 1.9973279338011516e-05,
      "loss": 0.638,
      "step": 1614
    },
    {
      "epoch": 0.04961140294289313,
      "grad_norm": 0.314637154340744,
      "learning_rate": 1.9973244020673243e-05,
      "loss": 0.6516,
      "step": 1615
    },
    {
      "epoch": 0.049642122077842285,
      "grad_norm": 0.4583761394023895,
      "learning_rate": 1.997320868004176e-05,
      "loss": 0.6295,
      "step": 1616
    },
    {
      "epoch": 0.049672841212791446,
      "grad_norm": 0.31452253460884094,
      "learning_rate": 1.997317331611715e-05,
      "loss": 0.6754,
      "step": 1617
    },
    {
      "epoch": 0.04970356034774061,
      "grad_norm": 0.34458106756210327,
      "learning_rate": 1.99731379288995e-05,
      "loss": 0.5799,
      "step": 1618
    },
    {
      "epoch": 0.04973427948268977,
      "grad_norm": 0.3168652057647705,
      "learning_rate": 1.9973102518388893e-05,
      "loss": 0.6147,
      "step": 1619
    },
    {
      "epoch": 0.049764998617638924,
      "grad_norm": 0.31987428665161133,
      "learning_rate": 1.99730670845854e-05,
      "loss": 0.7054,
      "step": 1620
    },
    {
      "epoch": 0.049795717752588085,
      "grad_norm": 0.3057861626148224,
      "learning_rate": 1.997303162748912e-05,
      "loss": 0.5597,
      "step": 1621
    },
    {
      "epoch": 0.04982643688753725,
      "grad_norm": 0.4233693480491638,
      "learning_rate": 1.9972996147100125e-05,
      "loss": 0.6706,
      "step": 1622
    },
    {
      "epoch": 0.04985715602248641,
      "grad_norm": 0.3018213212490082,
      "learning_rate": 1.9972960643418503e-05,
      "loss": 0.6036,
      "step": 1623
    },
    {
      "epoch": 0.04988787515743557,
      "grad_norm": 0.33124321699142456,
      "learning_rate": 1.997292511644433e-05,
      "loss": 0.5172,
      "step": 1624
    },
    {
      "epoch": 0.049918594292384724,
      "grad_norm": 0.30949515104293823,
      "learning_rate": 1.99728895661777e-05,
      "loss": 0.6224,
      "step": 1625
    },
    {
      "epoch": 0.049949313427333886,
      "grad_norm": 0.380548894405365,
      "learning_rate": 1.9972853992618685e-05,
      "loss": 0.6887,
      "step": 1626
    },
    {
      "epoch": 0.04998003256228305,
      "grad_norm": 0.38368430733680725,
      "learning_rate": 1.997281839576738e-05,
      "loss": 0.6189,
      "step": 1627
    },
    {
      "epoch": 0.05001075169723221,
      "grad_norm": 0.43819427490234375,
      "learning_rate": 1.9972782775623852e-05,
      "loss": 0.5916,
      "step": 1628
    },
    {
      "epoch": 0.05004147083218136,
      "grad_norm": 0.41229456663131714,
      "learning_rate": 1.9972747132188197e-05,
      "loss": 0.5813,
      "step": 1629
    },
    {
      "epoch": 0.050072189967130525,
      "grad_norm": 0.3749625086784363,
      "learning_rate": 1.9972711465460494e-05,
      "loss": 0.6286,
      "step": 1630
    },
    {
      "epoch": 0.050102909102079686,
      "grad_norm": 0.32124078273773193,
      "learning_rate": 1.997267577544083e-05,
      "loss": 0.598,
      "step": 1631
    },
    {
      "epoch": 0.05013362823702885,
      "grad_norm": 0.3479023873806,
      "learning_rate": 1.9972640062129282e-05,
      "loss": 0.6067,
      "step": 1632
    },
    {
      "epoch": 0.050164347371978,
      "grad_norm": 0.48171094059944153,
      "learning_rate": 1.9972604325525936e-05,
      "loss": 0.6425,
      "step": 1633
    },
    {
      "epoch": 0.05019506650692716,
      "grad_norm": 0.330768883228302,
      "learning_rate": 1.9972568565630877e-05,
      "loss": 0.6233,
      "step": 1634
    },
    {
      "epoch": 0.050225785641876325,
      "grad_norm": 0.32223352789878845,
      "learning_rate": 1.997253278244419e-05,
      "loss": 0.5836,
      "step": 1635
    },
    {
      "epoch": 0.050256504776825486,
      "grad_norm": 0.341009259223938,
      "learning_rate": 1.997249697596596e-05,
      "loss": 0.6334,
      "step": 1636
    },
    {
      "epoch": 0.05028722391177465,
      "grad_norm": 0.34071841835975647,
      "learning_rate": 1.997246114619626e-05,
      "loss": 0.6203,
      "step": 1637
    },
    {
      "epoch": 0.0503179430467238,
      "grad_norm": 0.3425106406211853,
      "learning_rate": 1.997242529313518e-05,
      "loss": 0.6273,
      "step": 1638
    },
    {
      "epoch": 0.050348662181672964,
      "grad_norm": 0.3437378406524658,
      "learning_rate": 1.9972389416782808e-05,
      "loss": 0.5916,
      "step": 1639
    },
    {
      "epoch": 0.050379381316622125,
      "grad_norm": 0.32230859994888306,
      "learning_rate": 1.997235351713922e-05,
      "loss": 0.602,
      "step": 1640
    },
    {
      "epoch": 0.05041010045157129,
      "grad_norm": 0.3632746934890747,
      "learning_rate": 1.997231759420451e-05,
      "loss": 0.6859,
      "step": 1641
    },
    {
      "epoch": 0.05044081958652044,
      "grad_norm": 0.3984330892562866,
      "learning_rate": 1.997228164797875e-05,
      "loss": 0.6805,
      "step": 1642
    },
    {
      "epoch": 0.0504715387214696,
      "grad_norm": 0.31781619787216187,
      "learning_rate": 1.9972245678462032e-05,
      "loss": 0.5995,
      "step": 1643
    },
    {
      "epoch": 0.050502257856418764,
      "grad_norm": 0.3396299183368683,
      "learning_rate": 1.9972209685654437e-05,
      "loss": 0.5892,
      "step": 1644
    },
    {
      "epoch": 0.050532976991367926,
      "grad_norm": 0.3552519679069519,
      "learning_rate": 1.9972173669556053e-05,
      "loss": 0.6061,
      "step": 1645
    },
    {
      "epoch": 0.05056369612631708,
      "grad_norm": 0.33940160274505615,
      "learning_rate": 1.9972137630166955e-05,
      "loss": 0.593,
      "step": 1646
    },
    {
      "epoch": 0.05059441526126624,
      "grad_norm": 0.411429226398468,
      "learning_rate": 1.9972101567487237e-05,
      "loss": 0.6938,
      "step": 1647
    },
    {
      "epoch": 0.0506251343962154,
      "grad_norm": 0.34179040789604187,
      "learning_rate": 1.9972065481516983e-05,
      "loss": 0.647,
      "step": 1648
    },
    {
      "epoch": 0.050655853531164564,
      "grad_norm": 0.363298237323761,
      "learning_rate": 1.9972029372256266e-05,
      "loss": 0.6203,
      "step": 1649
    },
    {
      "epoch": 0.05068657266611372,
      "grad_norm": 0.35668376088142395,
      "learning_rate": 1.9971993239705183e-05,
      "loss": 0.6778,
      "step": 1650
    },
    {
      "epoch": 0.05071729180106288,
      "grad_norm": 0.3233514726161957,
      "learning_rate": 1.9971957083863814e-05,
      "loss": 0.6426,
      "step": 1651
    },
    {
      "epoch": 0.05074801093601204,
      "grad_norm": 0.38480865955352783,
      "learning_rate": 1.9971920904732238e-05,
      "loss": 0.5662,
      "step": 1652
    },
    {
      "epoch": 0.0507787300709612,
      "grad_norm": 0.33321690559387207,
      "learning_rate": 1.9971884702310545e-05,
      "loss": 0.6974,
      "step": 1653
    },
    {
      "epoch": 0.050809449205910365,
      "grad_norm": 0.33720824122428894,
      "learning_rate": 1.9971848476598824e-05,
      "loss": 0.5444,
      "step": 1654
    },
    {
      "epoch": 0.05084016834085952,
      "grad_norm": 0.3110780119895935,
      "learning_rate": 1.997181222759715e-05,
      "loss": 0.666,
      "step": 1655
    },
    {
      "epoch": 0.05087088747580868,
      "grad_norm": 0.36159563064575195,
      "learning_rate": 1.9971775955305614e-05,
      "loss": 0.5475,
      "step": 1656
    },
    {
      "epoch": 0.05090160661075784,
      "grad_norm": 0.3299364149570465,
      "learning_rate": 1.99717396597243e-05,
      "loss": 0.617,
      "step": 1657
    },
    {
      "epoch": 0.050932325745707004,
      "grad_norm": 0.3755226135253906,
      "learning_rate": 1.997170334085329e-05,
      "loss": 0.611,
      "step": 1658
    },
    {
      "epoch": 0.05096304488065616,
      "grad_norm": 0.31369540095329285,
      "learning_rate": 1.997166699869267e-05,
      "loss": 0.668,
      "step": 1659
    },
    {
      "epoch": 0.05099376401560532,
      "grad_norm": 0.33271852135658264,
      "learning_rate": 1.9971630633242525e-05,
      "loss": 0.7082,
      "step": 1660
    },
    {
      "epoch": 0.05102448315055448,
      "grad_norm": 0.3282442092895508,
      "learning_rate": 1.9971594244502942e-05,
      "loss": 0.5718,
      "step": 1661
    },
    {
      "epoch": 0.05105520228550364,
      "grad_norm": 0.38441911339759827,
      "learning_rate": 1.9971557832474002e-05,
      "loss": 0.6738,
      "step": 1662
    },
    {
      "epoch": 0.0510859214204528,
      "grad_norm": 0.351683646440506,
      "learning_rate": 1.9971521397155793e-05,
      "loss": 0.5522,
      "step": 1663
    },
    {
      "epoch": 0.05111664055540196,
      "grad_norm": 0.40883177518844604,
      "learning_rate": 1.99714849385484e-05,
      "loss": 0.6556,
      "step": 1664
    },
    {
      "epoch": 0.05114735969035112,
      "grad_norm": 0.3257603347301483,
      "learning_rate": 1.9971448456651906e-05,
      "loss": 0.6419,
      "step": 1665
    },
    {
      "epoch": 0.05117807882530028,
      "grad_norm": 0.4220370352268219,
      "learning_rate": 1.99714119514664e-05,
      "loss": 0.6404,
      "step": 1666
    },
    {
      "epoch": 0.05120879796024944,
      "grad_norm": 0.3198326826095581,
      "learning_rate": 1.9971375422991962e-05,
      "loss": 0.6203,
      "step": 1667
    },
    {
      "epoch": 0.0512395170951986,
      "grad_norm": 0.3326724171638489,
      "learning_rate": 1.9971338871228684e-05,
      "loss": 0.6021,
      "step": 1668
    },
    {
      "epoch": 0.05127023623014776,
      "grad_norm": 0.35600051283836365,
      "learning_rate": 1.9971302296176646e-05,
      "loss": 0.5888,
      "step": 1669
    },
    {
      "epoch": 0.05130095536509692,
      "grad_norm": 0.3490760922431946,
      "learning_rate": 1.9971265697835934e-05,
      "loss": 0.5674,
      "step": 1670
    },
    {
      "epoch": 0.05133167450004608,
      "grad_norm": 0.3330647051334381,
      "learning_rate": 1.9971229076206638e-05,
      "loss": 0.5826,
      "step": 1671
    },
    {
      "epoch": 0.051362393634995236,
      "grad_norm": 0.3673471212387085,
      "learning_rate": 1.997119243128884e-05,
      "loss": 0.6201,
      "step": 1672
    },
    {
      "epoch": 0.0513931127699444,
      "grad_norm": 0.34637609124183655,
      "learning_rate": 1.997115576308262e-05,
      "loss": 0.5956,
      "step": 1673
    },
    {
      "epoch": 0.05142383190489356,
      "grad_norm": 0.32922089099884033,
      "learning_rate": 1.997111907158807e-05,
      "loss": 0.6585,
      "step": 1674
    },
    {
      "epoch": 0.05145455103984272,
      "grad_norm": 0.36187902092933655,
      "learning_rate": 1.997108235680528e-05,
      "loss": 0.6389,
      "step": 1675
    },
    {
      "epoch": 0.051485270174791875,
      "grad_norm": 0.3523949086666107,
      "learning_rate": 1.997104561873433e-05,
      "loss": 0.5296,
      "step": 1676
    },
    {
      "epoch": 0.051515989309741037,
      "grad_norm": 0.5153689980506897,
      "learning_rate": 1.9971008857375305e-05,
      "loss": 0.634,
      "step": 1677
    },
    {
      "epoch": 0.0515467084446902,
      "grad_norm": 0.41411033272743225,
      "learning_rate": 1.9970972072728294e-05,
      "loss": 0.6311,
      "step": 1678
    },
    {
      "epoch": 0.05157742757963936,
      "grad_norm": 0.3246355354785919,
      "learning_rate": 1.997093526479338e-05,
      "loss": 0.5896,
      "step": 1679
    },
    {
      "epoch": 0.051608146714588514,
      "grad_norm": 0.46703168749809265,
      "learning_rate": 1.997089843357065e-05,
      "loss": 0.5243,
      "step": 1680
    },
    {
      "epoch": 0.051638865849537675,
      "grad_norm": 0.4030819535255432,
      "learning_rate": 1.997086157906019e-05,
      "loss": 0.6053,
      "step": 1681
    },
    {
      "epoch": 0.05166958498448684,
      "grad_norm": 0.3761485517024994,
      "learning_rate": 1.9970824701262085e-05,
      "loss": 0.6481,
      "step": 1682
    },
    {
      "epoch": 0.051700304119436,
      "grad_norm": 0.7228783369064331,
      "learning_rate": 1.9970787800176426e-05,
      "loss": 0.5928,
      "step": 1683
    },
    {
      "epoch": 0.05173102325438516,
      "grad_norm": 0.3218024969100952,
      "learning_rate": 1.9970750875803294e-05,
      "loss": 0.6075,
      "step": 1684
    },
    {
      "epoch": 0.051761742389334314,
      "grad_norm": 0.410461962223053,
      "learning_rate": 1.9970713928142776e-05,
      "loss": 0.6254,
      "step": 1685
    },
    {
      "epoch": 0.051792461524283476,
      "grad_norm": 0.31899458169937134,
      "learning_rate": 1.9970676957194962e-05,
      "loss": 0.6254,
      "step": 1686
    },
    {
      "epoch": 0.05182318065923264,
      "grad_norm": 0.3944074809551239,
      "learning_rate": 1.9970639962959938e-05,
      "loss": 0.6313,
      "step": 1687
    },
    {
      "epoch": 0.0518538997941818,
      "grad_norm": 0.957227885723114,
      "learning_rate": 1.9970602945437783e-05,
      "loss": 0.628,
      "step": 1688
    },
    {
      "epoch": 0.05188461892913095,
      "grad_norm": 0.32219892740249634,
      "learning_rate": 1.9970565904628588e-05,
      "loss": 0.6311,
      "step": 1689
    },
    {
      "epoch": 0.051915338064080115,
      "grad_norm": 0.3373182415962219,
      "learning_rate": 1.997052884053244e-05,
      "loss": 0.6165,
      "step": 1690
    },
    {
      "epoch": 0.051946057199029276,
      "grad_norm": 0.35779833793640137,
      "learning_rate": 1.997049175314943e-05,
      "loss": 0.6559,
      "step": 1691
    },
    {
      "epoch": 0.05197677633397844,
      "grad_norm": 0.3302483558654785,
      "learning_rate": 1.9970454642479636e-05,
      "loss": 0.5413,
      "step": 1692
    },
    {
      "epoch": 0.05200749546892759,
      "grad_norm": 0.3374185562133789,
      "learning_rate": 1.9970417508523153e-05,
      "loss": 0.6166,
      "step": 1693
    },
    {
      "epoch": 0.05203821460387675,
      "grad_norm": 0.3562318980693817,
      "learning_rate": 1.997038035128006e-05,
      "loss": 0.6394,
      "step": 1694
    },
    {
      "epoch": 0.052068933738825915,
      "grad_norm": 0.30988162755966187,
      "learning_rate": 1.9970343170750446e-05,
      "loss": 0.6422,
      "step": 1695
    },
    {
      "epoch": 0.052099652873775076,
      "grad_norm": 0.3686848282814026,
      "learning_rate": 1.9970305966934403e-05,
      "loss": 0.7171,
      "step": 1696
    },
    {
      "epoch": 0.05213037200872423,
      "grad_norm": 0.3901228606700897,
      "learning_rate": 1.9970268739832014e-05,
      "loss": 0.7016,
      "step": 1697
    },
    {
      "epoch": 0.05216109114367339,
      "grad_norm": 0.3580358028411865,
      "learning_rate": 1.9970231489443364e-05,
      "loss": 0.5929,
      "step": 1698
    },
    {
      "epoch": 0.052191810278622554,
      "grad_norm": 0.32933008670806885,
      "learning_rate": 1.9970194215768542e-05,
      "loss": 0.5992,
      "step": 1699
    },
    {
      "epoch": 0.052222529413571715,
      "grad_norm": 0.2849575877189636,
      "learning_rate": 1.9970156918807636e-05,
      "loss": 0.5287,
      "step": 1700
    },
    {
      "epoch": 0.05225324854852088,
      "grad_norm": 0.3584528863430023,
      "learning_rate": 1.9970119598560734e-05,
      "loss": 0.6353,
      "step": 1701
    },
    {
      "epoch": 0.05228396768347003,
      "grad_norm": 0.3351663649082184,
      "learning_rate": 1.9970082255027917e-05,
      "loss": 0.619,
      "step": 1702
    },
    {
      "epoch": 0.05231468681841919,
      "grad_norm": 0.4637466371059418,
      "learning_rate": 1.997004488820928e-05,
      "loss": 0.6933,
      "step": 1703
    },
    {
      "epoch": 0.052345405953368354,
      "grad_norm": 0.3082723617553711,
      "learning_rate": 1.9970007498104907e-05,
      "loss": 0.6118,
      "step": 1704
    },
    {
      "epoch": 0.052376125088317516,
      "grad_norm": 0.3228706121444702,
      "learning_rate": 1.9969970084714884e-05,
      "loss": 0.5609,
      "step": 1705
    },
    {
      "epoch": 0.05240684422326667,
      "grad_norm": 0.459017813205719,
      "learning_rate": 1.9969932648039298e-05,
      "loss": 0.5658,
      "step": 1706
    },
    {
      "epoch": 0.05243756335821583,
      "grad_norm": 0.4038344919681549,
      "learning_rate": 1.996989518807824e-05,
      "loss": 0.6269,
      "step": 1707
    },
    {
      "epoch": 0.05246828249316499,
      "grad_norm": 0.3404841721057892,
      "learning_rate": 1.9969857704831798e-05,
      "loss": 0.6568,
      "step": 1708
    },
    {
      "epoch": 0.052499001628114154,
      "grad_norm": 0.35428181290626526,
      "learning_rate": 1.9969820198300053e-05,
      "loss": 0.5812,
      "step": 1709
    },
    {
      "epoch": 0.05252972076306331,
      "grad_norm": 0.32055121660232544,
      "learning_rate": 1.99697826684831e-05,
      "loss": 0.6316,
      "step": 1710
    },
    {
      "epoch": 0.05256043989801247,
      "grad_norm": 0.31095001101493835,
      "learning_rate": 1.9969745115381015e-05,
      "loss": 0.5626,
      "step": 1711
    },
    {
      "epoch": 0.05259115903296163,
      "grad_norm": 0.41241323947906494,
      "learning_rate": 1.9969707538993904e-05,
      "loss": 0.6062,
      "step": 1712
    },
    {
      "epoch": 0.05262187816791079,
      "grad_norm": 0.3453739881515503,
      "learning_rate": 1.9969669939321837e-05,
      "loss": 0.7103,
      "step": 1713
    },
    {
      "epoch": 0.052652597302859955,
      "grad_norm": 0.35108473896980286,
      "learning_rate": 1.9969632316364915e-05,
      "loss": 0.5966,
      "step": 1714
    },
    {
      "epoch": 0.05268331643780911,
      "grad_norm": 0.3071790635585785,
      "learning_rate": 1.996959467012322e-05,
      "loss": 0.5721,
      "step": 1715
    },
    {
      "epoch": 0.05271403557275827,
      "grad_norm": 0.342948317527771,
      "learning_rate": 1.9969557000596838e-05,
      "loss": 0.6325,
      "step": 1716
    },
    {
      "epoch": 0.05274475470770743,
      "grad_norm": 0.36018943786621094,
      "learning_rate": 1.9969519307785862e-05,
      "loss": 0.7135,
      "step": 1717
    },
    {
      "epoch": 0.052775473842656594,
      "grad_norm": 0.4865421950817108,
      "learning_rate": 1.9969481591690377e-05,
      "loss": 0.6305,
      "step": 1718
    },
    {
      "epoch": 0.05280619297760575,
      "grad_norm": 0.3245712220668793,
      "learning_rate": 1.9969443852310467e-05,
      "loss": 0.5766,
      "step": 1719
    },
    {
      "epoch": 0.05283691211255491,
      "grad_norm": 0.3359595835208893,
      "learning_rate": 1.9969406089646232e-05,
      "loss": 0.6175,
      "step": 1720
    },
    {
      "epoch": 0.05286763124750407,
      "grad_norm": 0.33772316575050354,
      "learning_rate": 1.9969368303697746e-05,
      "loss": 0.6443,
      "step": 1721
    },
    {
      "epoch": 0.05289835038245323,
      "grad_norm": 0.37347254157066345,
      "learning_rate": 1.996933049446511e-05,
      "loss": 0.6089,
      "step": 1722
    },
    {
      "epoch": 0.05292906951740239,
      "grad_norm": 0.3811996579170227,
      "learning_rate": 1.99692926619484e-05,
      "loss": 0.5863,
      "step": 1723
    },
    {
      "epoch": 0.05295978865235155,
      "grad_norm": 0.364454984664917,
      "learning_rate": 1.9969254806147717e-05,
      "loss": 0.5847,
      "step": 1724
    },
    {
      "epoch": 0.05299050778730071,
      "grad_norm": 0.3238917291164398,
      "learning_rate": 1.996921692706314e-05,
      "loss": 0.5748,
      "step": 1725
    },
    {
      "epoch": 0.05302122692224987,
      "grad_norm": 0.3327987492084503,
      "learning_rate": 1.996917902469476e-05,
      "loss": 0.6356,
      "step": 1726
    },
    {
      "epoch": 0.053051946057199026,
      "grad_norm": 0.3554466962814331,
      "learning_rate": 1.996914109904267e-05,
      "loss": 0.6154,
      "step": 1727
    },
    {
      "epoch": 0.05308266519214819,
      "grad_norm": 0.33200323581695557,
      "learning_rate": 1.996910315010695e-05,
      "loss": 0.6428,
      "step": 1728
    },
    {
      "epoch": 0.05311338432709735,
      "grad_norm": 0.3314322233200073,
      "learning_rate": 1.9969065177887696e-05,
      "loss": 0.5371,
      "step": 1729
    },
    {
      "epoch": 0.05314410346204651,
      "grad_norm": 0.33848699927330017,
      "learning_rate": 1.9969027182384993e-05,
      "loss": 0.65,
      "step": 1730
    },
    {
      "epoch": 0.05317482259699567,
      "grad_norm": 0.3499906063079834,
      "learning_rate": 1.996898916359893e-05,
      "loss": 0.603,
      "step": 1731
    },
    {
      "epoch": 0.053205541731944826,
      "grad_norm": 0.3205356299877167,
      "learning_rate": 1.9968951121529598e-05,
      "loss": 0.6111,
      "step": 1732
    },
    {
      "epoch": 0.05323626086689399,
      "grad_norm": 0.34398016333580017,
      "learning_rate": 1.9968913056177085e-05,
      "loss": 0.6106,
      "step": 1733
    },
    {
      "epoch": 0.05326698000184315,
      "grad_norm": 0.332608699798584,
      "learning_rate": 1.9968874967541477e-05,
      "loss": 0.5559,
      "step": 1734
    },
    {
      "epoch": 0.05329769913679231,
      "grad_norm": 0.3016985356807709,
      "learning_rate": 1.9968836855622867e-05,
      "loss": 0.531,
      "step": 1735
    },
    {
      "epoch": 0.053328418271741465,
      "grad_norm": 0.3576187193393707,
      "learning_rate": 1.996879872042134e-05,
      "loss": 0.6087,
      "step": 1736
    },
    {
      "epoch": 0.05335913740669063,
      "grad_norm": 0.32663413882255554,
      "learning_rate": 1.996876056193699e-05,
      "loss": 0.6651,
      "step": 1737
    },
    {
      "epoch": 0.05338985654163979,
      "grad_norm": 0.416313111782074,
      "learning_rate": 1.9968722380169906e-05,
      "loss": 0.5658,
      "step": 1738
    },
    {
      "epoch": 0.05342057567658895,
      "grad_norm": 0.3951456546783447,
      "learning_rate": 1.996868417512017e-05,
      "loss": 0.6773,
      "step": 1739
    },
    {
      "epoch": 0.053451294811538104,
      "grad_norm": 0.48338189721107483,
      "learning_rate": 1.9968645946787875e-05,
      "loss": 0.7154,
      "step": 1740
    },
    {
      "epoch": 0.053482013946487265,
      "grad_norm": 0.34798914194107056,
      "learning_rate": 1.9968607695173116e-05,
      "loss": 0.6022,
      "step": 1741
    },
    {
      "epoch": 0.05351273308143643,
      "grad_norm": 0.40057680010795593,
      "learning_rate": 1.9968569420275975e-05,
      "loss": 0.6754,
      "step": 1742
    },
    {
      "epoch": 0.05354345221638559,
      "grad_norm": 0.3306162357330322,
      "learning_rate": 1.9968531122096545e-05,
      "loss": 0.568,
      "step": 1743
    },
    {
      "epoch": 0.05357417135133475,
      "grad_norm": 0.3748723566532135,
      "learning_rate": 1.9968492800634913e-05,
      "loss": 0.618,
      "step": 1744
    },
    {
      "epoch": 0.053604890486283904,
      "grad_norm": 0.30966079235076904,
      "learning_rate": 1.996845445589117e-05,
      "loss": 0.6878,
      "step": 1745
    },
    {
      "epoch": 0.053635609621233066,
      "grad_norm": 0.3186560273170471,
      "learning_rate": 1.9968416087865405e-05,
      "loss": 0.6537,
      "step": 1746
    },
    {
      "epoch": 0.05366632875618223,
      "grad_norm": 0.3570191562175751,
      "learning_rate": 1.996837769655771e-05,
      "loss": 0.7086,
      "step": 1747
    },
    {
      "epoch": 0.05369704789113139,
      "grad_norm": 0.3589688837528229,
      "learning_rate": 1.996833928196817e-05,
      "loss": 0.6437,
      "step": 1748
    },
    {
      "epoch": 0.05372776702608054,
      "grad_norm": 0.3615206778049469,
      "learning_rate": 1.996830084409688e-05,
      "loss": 0.5804,
      "step": 1749
    },
    {
      "epoch": 0.053758486161029705,
      "grad_norm": 0.3345549404621124,
      "learning_rate": 1.9968262382943927e-05,
      "loss": 0.7215,
      "step": 1750
    },
    {
      "epoch": 0.053789205295978866,
      "grad_norm": 0.3486518859863281,
      "learning_rate": 1.99682238985094e-05,
      "loss": 0.7676,
      "step": 1751
    },
    {
      "epoch": 0.05381992443092803,
      "grad_norm": 0.30950355529785156,
      "learning_rate": 1.9968185390793387e-05,
      "loss": 0.6181,
      "step": 1752
    },
    {
      "epoch": 0.05385064356587718,
      "grad_norm": 0.3626912832260132,
      "learning_rate": 1.9968146859795987e-05,
      "loss": 0.7019,
      "step": 1753
    },
    {
      "epoch": 0.053881362700826343,
      "grad_norm": 0.3275771141052246,
      "learning_rate": 1.996810830551728e-05,
      "loss": 0.6282,
      "step": 1754
    },
    {
      "epoch": 0.053912081835775505,
      "grad_norm": 0.4009876549243927,
      "learning_rate": 1.996806972795736e-05,
      "loss": 0.65,
      "step": 1755
    },
    {
      "epoch": 0.053942800970724666,
      "grad_norm": 0.3567888140678406,
      "learning_rate": 1.9968031127116315e-05,
      "loss": 0.583,
      "step": 1756
    },
    {
      "epoch": 0.05397352010567382,
      "grad_norm": 0.3097861409187317,
      "learning_rate": 1.9967992502994243e-05,
      "loss": 0.6725,
      "step": 1757
    },
    {
      "epoch": 0.05400423924062298,
      "grad_norm": 0.33761295676231384,
      "learning_rate": 1.9967953855591223e-05,
      "loss": 0.599,
      "step": 1758
    },
    {
      "epoch": 0.054034958375572144,
      "grad_norm": 0.344808965921402,
      "learning_rate": 1.9967915184907353e-05,
      "loss": 0.5943,
      "step": 1759
    },
    {
      "epoch": 0.054065677510521305,
      "grad_norm": 0.32958218455314636,
      "learning_rate": 1.9967876490942722e-05,
      "loss": 0.6732,
      "step": 1760
    },
    {
      "epoch": 0.05409639664547047,
      "grad_norm": 0.32065731287002563,
      "learning_rate": 1.9967837773697417e-05,
      "loss": 0.5628,
      "step": 1761
    },
    {
      "epoch": 0.05412711578041962,
      "grad_norm": 0.3384649157524109,
      "learning_rate": 1.9967799033171534e-05,
      "loss": 0.5858,
      "step": 1762
    },
    {
      "epoch": 0.05415783491536878,
      "grad_norm": 0.38876229524612427,
      "learning_rate": 1.9967760269365157e-05,
      "loss": 0.5885,
      "step": 1763
    },
    {
      "epoch": 0.054188554050317944,
      "grad_norm": 0.4863390624523163,
      "learning_rate": 1.996772148227838e-05,
      "loss": 0.5833,
      "step": 1764
    },
    {
      "epoch": 0.054219273185267106,
      "grad_norm": 0.352750301361084,
      "learning_rate": 1.9967682671911294e-05,
      "loss": 0.594,
      "step": 1765
    },
    {
      "epoch": 0.05424999232021626,
      "grad_norm": 0.3516665995121002,
      "learning_rate": 1.996764383826399e-05,
      "loss": 0.6692,
      "step": 1766
    },
    {
      "epoch": 0.05428071145516542,
      "grad_norm": 0.3806980848312378,
      "learning_rate": 1.9967604981336556e-05,
      "loss": 0.6181,
      "step": 1767
    },
    {
      "epoch": 0.05431143059011458,
      "grad_norm": 0.3783700466156006,
      "learning_rate": 1.9967566101129085e-05,
      "loss": 0.5741,
      "step": 1768
    },
    {
      "epoch": 0.054342149725063744,
      "grad_norm": 0.4128999412059784,
      "learning_rate": 1.9967527197641666e-05,
      "loss": 0.5392,
      "step": 1769
    },
    {
      "epoch": 0.0543728688600129,
      "grad_norm": 0.9719181060791016,
      "learning_rate": 1.9967488270874393e-05,
      "loss": 0.685,
      "step": 1770
    },
    {
      "epoch": 0.05440358799496206,
      "grad_norm": 0.33161112666130066,
      "learning_rate": 1.9967449320827358e-05,
      "loss": 0.5686,
      "step": 1771
    },
    {
      "epoch": 0.05443430712991122,
      "grad_norm": 0.3345581293106079,
      "learning_rate": 1.9967410347500646e-05,
      "loss": 0.6247,
      "step": 1772
    },
    {
      "epoch": 0.05446502626486038,
      "grad_norm": 0.34420591592788696,
      "learning_rate": 1.9967371350894347e-05,
      "loss": 0.6516,
      "step": 1773
    },
    {
      "epoch": 0.054495745399809545,
      "grad_norm": 0.3308345675468445,
      "learning_rate": 1.996733233100856e-05,
      "loss": 0.5793,
      "step": 1774
    },
    {
      "epoch": 0.0545264645347587,
      "grad_norm": 0.396537721157074,
      "learning_rate": 1.9967293287843373e-05,
      "loss": 0.622,
      "step": 1775
    },
    {
      "epoch": 0.05455718366970786,
      "grad_norm": 0.32373932003974915,
      "learning_rate": 1.9967254221398873e-05,
      "loss": 0.5834,
      "step": 1776
    },
    {
      "epoch": 0.05458790280465702,
      "grad_norm": 0.5956937074661255,
      "learning_rate": 1.9967215131675156e-05,
      "loss": 0.6589,
      "step": 1777
    },
    {
      "epoch": 0.054618621939606184,
      "grad_norm": 0.33745530247688293,
      "learning_rate": 1.9967176018672315e-05,
      "loss": 0.6526,
      "step": 1778
    },
    {
      "epoch": 0.05464934107455534,
      "grad_norm": 0.3374810218811035,
      "learning_rate": 1.9967136882390436e-05,
      "loss": 0.5269,
      "step": 1779
    },
    {
      "epoch": 0.0546800602095045,
      "grad_norm": 0.3114989697933197,
      "learning_rate": 1.9967097722829615e-05,
      "loss": 0.6264,
      "step": 1780
    },
    {
      "epoch": 0.05471077934445366,
      "grad_norm": 0.3103391230106354,
      "learning_rate": 1.9967058539989937e-05,
      "loss": 0.6085,
      "step": 1781
    },
    {
      "epoch": 0.05474149847940282,
      "grad_norm": 0.3351426422595978,
      "learning_rate": 1.99670193338715e-05,
      "loss": 0.6653,
      "step": 1782
    },
    {
      "epoch": 0.05477221761435198,
      "grad_norm": 0.333210289478302,
      "learning_rate": 1.9966980104474395e-05,
      "loss": 0.5896,
      "step": 1783
    },
    {
      "epoch": 0.05480293674930114,
      "grad_norm": 0.3972318470478058,
      "learning_rate": 1.996694085179871e-05,
      "loss": 0.582,
      "step": 1784
    },
    {
      "epoch": 0.0548336558842503,
      "grad_norm": 0.3368469476699829,
      "learning_rate": 1.9966901575844537e-05,
      "loss": 0.6089,
      "step": 1785
    },
    {
      "epoch": 0.05486437501919946,
      "grad_norm": 0.3137270212173462,
      "learning_rate": 1.996686227661197e-05,
      "loss": 0.6137,
      "step": 1786
    },
    {
      "epoch": 0.054895094154148616,
      "grad_norm": 0.3790385127067566,
      "learning_rate": 1.99668229541011e-05,
      "loss": 0.6153,
      "step": 1787
    },
    {
      "epoch": 0.05492581328909778,
      "grad_norm": 0.3525201976299286,
      "learning_rate": 1.9966783608312022e-05,
      "loss": 0.6533,
      "step": 1788
    },
    {
      "epoch": 0.05495653242404694,
      "grad_norm": 0.4979594349861145,
      "learning_rate": 1.996674423924482e-05,
      "loss": 0.6987,
      "step": 1789
    },
    {
      "epoch": 0.0549872515589961,
      "grad_norm": 0.3671897053718567,
      "learning_rate": 1.9966704846899595e-05,
      "loss": 0.5983,
      "step": 1790
    },
    {
      "epoch": 0.05501797069394526,
      "grad_norm": 0.3712370693683624,
      "learning_rate": 1.9966665431276435e-05,
      "loss": 0.6116,
      "step": 1791
    },
    {
      "epoch": 0.055048689828894416,
      "grad_norm": 0.38204923272132874,
      "learning_rate": 1.9966625992375427e-05,
      "loss": 0.6007,
      "step": 1792
    },
    {
      "epoch": 0.05507940896384358,
      "grad_norm": 0.3614477515220642,
      "learning_rate": 1.996658653019667e-05,
      "loss": 0.5865,
      "step": 1793
    },
    {
      "epoch": 0.05511012809879274,
      "grad_norm": 0.33504560589790344,
      "learning_rate": 1.9966547044740258e-05,
      "loss": 0.6174,
      "step": 1794
    },
    {
      "epoch": 0.0551408472337419,
      "grad_norm": 0.3353455364704132,
      "learning_rate": 1.9966507536006273e-05,
      "loss": 0.6599,
      "step": 1795
    },
    {
      "epoch": 0.055171566368691055,
      "grad_norm": 0.37101733684539795,
      "learning_rate": 1.996646800399482e-05,
      "loss": 0.5846,
      "step": 1796
    },
    {
      "epoch": 0.05520228550364022,
      "grad_norm": 0.415584921836853,
      "learning_rate": 1.9966428448705982e-05,
      "loss": 0.6294,
      "step": 1797
    },
    {
      "epoch": 0.05523300463858938,
      "grad_norm": 0.3864404857158661,
      "learning_rate": 1.9966388870139853e-05,
      "loss": 0.6278,
      "step": 1798
    },
    {
      "epoch": 0.05526372377353854,
      "grad_norm": 0.6925176382064819,
      "learning_rate": 1.9966349268296527e-05,
      "loss": 0.545,
      "step": 1799
    },
    {
      "epoch": 0.055294442908487694,
      "grad_norm": 0.32420557737350464,
      "learning_rate": 1.9966309643176095e-05,
      "loss": 0.6888,
      "step": 1800
    },
    {
      "epoch": 0.055325162043436855,
      "grad_norm": 0.32321715354919434,
      "learning_rate": 1.9966269994778655e-05,
      "loss": 0.5997,
      "step": 1801
    },
    {
      "epoch": 0.05535588117838602,
      "grad_norm": 0.3477127254009247,
      "learning_rate": 1.9966230323104293e-05,
      "loss": 0.6304,
      "step": 1802
    },
    {
      "epoch": 0.05538660031333518,
      "grad_norm": 0.37694552540779114,
      "learning_rate": 1.9966190628153103e-05,
      "loss": 0.5925,
      "step": 1803
    },
    {
      "epoch": 0.05541731944828433,
      "grad_norm": 0.5167793035507202,
      "learning_rate": 1.9966150909925183e-05,
      "loss": 0.5952,
      "step": 1804
    },
    {
      "epoch": 0.055448038583233494,
      "grad_norm": 0.3316456079483032,
      "learning_rate": 1.9966111168420618e-05,
      "loss": 0.6407,
      "step": 1805
    },
    {
      "epoch": 0.055478757718182656,
      "grad_norm": 0.390786737203598,
      "learning_rate": 1.9966071403639503e-05,
      "loss": 0.6364,
      "step": 1806
    },
    {
      "epoch": 0.05550947685313182,
      "grad_norm": 0.3137774169445038,
      "learning_rate": 1.9966031615581936e-05,
      "loss": 0.6109,
      "step": 1807
    },
    {
      "epoch": 0.05554019598808098,
      "grad_norm": 0.3803066313266754,
      "learning_rate": 1.9965991804248002e-05,
      "loss": 0.5329,
      "step": 1808
    },
    {
      "epoch": 0.05557091512303013,
      "grad_norm": 0.36643847823143005,
      "learning_rate": 1.9965951969637803e-05,
      "loss": 0.6092,
      "step": 1809
    },
    {
      "epoch": 0.055601634257979295,
      "grad_norm": 0.34362462162971497,
      "learning_rate": 1.9965912111751426e-05,
      "loss": 0.686,
      "step": 1810
    },
    {
      "epoch": 0.055632353392928456,
      "grad_norm": 0.32659971714019775,
      "learning_rate": 1.996587223058896e-05,
      "loss": 0.6673,
      "step": 1811
    },
    {
      "epoch": 0.05566307252787762,
      "grad_norm": 0.326425701379776,
      "learning_rate": 1.9965832326150506e-05,
      "loss": 0.6497,
      "step": 1812
    },
    {
      "epoch": 0.05569379166282677,
      "grad_norm": 0.3291676938533783,
      "learning_rate": 1.996579239843616e-05,
      "loss": 0.6723,
      "step": 1813
    },
    {
      "epoch": 0.055724510797775934,
      "grad_norm": 0.34406304359436035,
      "learning_rate": 1.9965752447446e-05,
      "loss": 0.6455,
      "step": 1814
    },
    {
      "epoch": 0.055755229932725095,
      "grad_norm": 0.31995972990989685,
      "learning_rate": 1.996571247318014e-05,
      "loss": 0.5241,
      "step": 1815
    },
    {
      "epoch": 0.055785949067674256,
      "grad_norm": 0.35008370876312256,
      "learning_rate": 1.9965672475638654e-05,
      "loss": 0.7469,
      "step": 1816
    },
    {
      "epoch": 0.05581666820262341,
      "grad_norm": 0.3419457674026489,
      "learning_rate": 1.996563245482165e-05,
      "loss": 0.602,
      "step": 1817
    },
    {
      "epoch": 0.05584738733757257,
      "grad_norm": 0.3613872230052948,
      "learning_rate": 1.9965592410729212e-05,
      "loss": 0.6162,
      "step": 1818
    },
    {
      "epoch": 0.055878106472521734,
      "grad_norm": 0.3541260063648224,
      "learning_rate": 1.9965552343361437e-05,
      "loss": 0.6228,
      "step": 1819
    },
    {
      "epoch": 0.055908825607470895,
      "grad_norm": 0.35104671120643616,
      "learning_rate": 1.996551225271842e-05,
      "loss": 0.7081,
      "step": 1820
    },
    {
      "epoch": 0.05593954474242006,
      "grad_norm": 0.397500216960907,
      "learning_rate": 1.996547213880025e-05,
      "loss": 0.6632,
      "step": 1821
    },
    {
      "epoch": 0.05597026387736921,
      "grad_norm": 0.3174766004085541,
      "learning_rate": 1.996543200160703e-05,
      "loss": 0.6176,
      "step": 1822
    },
    {
      "epoch": 0.05600098301231837,
      "grad_norm": 0.36102616786956787,
      "learning_rate": 1.996539184113884e-05,
      "loss": 0.5808,
      "step": 1823
    },
    {
      "epoch": 0.056031702147267534,
      "grad_norm": 0.3269558548927307,
      "learning_rate": 1.996535165739579e-05,
      "loss": 0.606,
      "step": 1824
    },
    {
      "epoch": 0.056062421282216696,
      "grad_norm": 0.3468816578388214,
      "learning_rate": 1.996531145037796e-05,
      "loss": 0.6293,
      "step": 1825
    },
    {
      "epoch": 0.05609314041716585,
      "grad_norm": 0.3510095179080963,
      "learning_rate": 1.9965271220085446e-05,
      "loss": 0.5887,
      "step": 1826
    },
    {
      "epoch": 0.05612385955211501,
      "grad_norm": 0.3229139745235443,
      "learning_rate": 1.996523096651835e-05,
      "loss": 0.6503,
      "step": 1827
    },
    {
      "epoch": 0.05615457868706417,
      "grad_norm": 0.3386416435241699,
      "learning_rate": 1.996519068967676e-05,
      "loss": 0.6425,
      "step": 1828
    },
    {
      "epoch": 0.056185297822013335,
      "grad_norm": 0.3360848128795624,
      "learning_rate": 1.996515038956077e-05,
      "loss": 0.6006,
      "step": 1829
    },
    {
      "epoch": 0.05621601695696249,
      "grad_norm": 0.4475609064102173,
      "learning_rate": 1.9965110066170475e-05,
      "loss": 0.6766,
      "step": 1830
    },
    {
      "epoch": 0.05624673609191165,
      "grad_norm": 0.36392685770988464,
      "learning_rate": 1.9965069719505972e-05,
      "loss": 0.6182,
      "step": 1831
    },
    {
      "epoch": 0.05627745522686081,
      "grad_norm": 0.7619168758392334,
      "learning_rate": 1.9965029349567352e-05,
      "loss": 0.6581,
      "step": 1832
    },
    {
      "epoch": 0.05630817436180997,
      "grad_norm": 0.3269537687301636,
      "learning_rate": 1.9964988956354706e-05,
      "loss": 0.6013,
      "step": 1833
    },
    {
      "epoch": 0.05633889349675913,
      "grad_norm": 0.3960472047328949,
      "learning_rate": 1.9964948539868135e-05,
      "loss": 0.5932,
      "step": 1834
    },
    {
      "epoch": 0.05636961263170829,
      "grad_norm": 0.38066351413726807,
      "learning_rate": 1.9964908100107735e-05,
      "loss": 0.6471,
      "step": 1835
    },
    {
      "epoch": 0.05640033176665745,
      "grad_norm": 0.3433813154697418,
      "learning_rate": 1.9964867637073594e-05,
      "loss": 0.6981,
      "step": 1836
    },
    {
      "epoch": 0.05643105090160661,
      "grad_norm": 0.3386608362197876,
      "learning_rate": 1.9964827150765806e-05,
      "loss": 0.6089,
      "step": 1837
    },
    {
      "epoch": 0.056461770036555774,
      "grad_norm": 0.31819021701812744,
      "learning_rate": 1.9964786641184467e-05,
      "loss": 0.5727,
      "step": 1838
    },
    {
      "epoch": 0.05649248917150493,
      "grad_norm": 0.3429846465587616,
      "learning_rate": 1.9964746108329678e-05,
      "loss": 0.6361,
      "step": 1839
    },
    {
      "epoch": 0.05652320830645409,
      "grad_norm": 0.35714486241340637,
      "learning_rate": 1.9964705552201526e-05,
      "loss": 0.661,
      "step": 1840
    },
    {
      "epoch": 0.05655392744140325,
      "grad_norm": 0.32667797803878784,
      "learning_rate": 1.9964664972800108e-05,
      "loss": 0.5749,
      "step": 1841
    },
    {
      "epoch": 0.05658464657635241,
      "grad_norm": 0.4207698106765747,
      "learning_rate": 1.9964624370125518e-05,
      "loss": 0.5503,
      "step": 1842
    },
    {
      "epoch": 0.05661536571130157,
      "grad_norm": 0.4215468764305115,
      "learning_rate": 1.9964583744177854e-05,
      "loss": 0.7191,
      "step": 1843
    },
    {
      "epoch": 0.05664608484625073,
      "grad_norm": 0.5196759104728699,
      "learning_rate": 1.9964543094957207e-05,
      "loss": 0.6739,
      "step": 1844
    },
    {
      "epoch": 0.05667680398119989,
      "grad_norm": 0.3433223068714142,
      "learning_rate": 1.9964502422463673e-05,
      "loss": 0.6302,
      "step": 1845
    },
    {
      "epoch": 0.05670752311614905,
      "grad_norm": 0.3245305120944977,
      "learning_rate": 1.9964461726697353e-05,
      "loss": 0.6519,
      "step": 1846
    },
    {
      "epoch": 0.056738242251098206,
      "grad_norm": 0.33324727416038513,
      "learning_rate": 1.9964421007658332e-05,
      "loss": 0.6084,
      "step": 1847
    },
    {
      "epoch": 0.05676896138604737,
      "grad_norm": 0.32655832171440125,
      "learning_rate": 1.996438026534671e-05,
      "loss": 0.6613,
      "step": 1848
    },
    {
      "epoch": 0.05679968052099653,
      "grad_norm": 0.4154995083808899,
      "learning_rate": 1.9964339499762583e-05,
      "loss": 0.6961,
      "step": 1849
    },
    {
      "epoch": 0.05683039965594569,
      "grad_norm": 0.3287869989871979,
      "learning_rate": 1.9964298710906048e-05,
      "loss": 0.6156,
      "step": 1850
    },
    {
      "epoch": 0.05686111879089485,
      "grad_norm": 0.3565879166126251,
      "learning_rate": 1.9964257898777194e-05,
      "loss": 0.6149,
      "step": 1851
    },
    {
      "epoch": 0.056891837925844006,
      "grad_norm": 0.3523060977458954,
      "learning_rate": 1.9964217063376117e-05,
      "loss": 0.5629,
      "step": 1852
    },
    {
      "epoch": 0.05692255706079317,
      "grad_norm": 0.3587956428527832,
      "learning_rate": 1.996417620470292e-05,
      "loss": 0.6421,
      "step": 1853
    },
    {
      "epoch": 0.05695327619574233,
      "grad_norm": 0.3773297965526581,
      "learning_rate": 1.9964135322757693e-05,
      "loss": 0.6417,
      "step": 1854
    },
    {
      "epoch": 0.05698399533069149,
      "grad_norm": 0.3549673855304718,
      "learning_rate": 1.996409441754053e-05,
      "loss": 0.6191,
      "step": 1855
    },
    {
      "epoch": 0.057014714465640645,
      "grad_norm": 0.31769442558288574,
      "learning_rate": 1.996405348905153e-05,
      "loss": 0.6062,
      "step": 1856
    },
    {
      "epoch": 0.05704543360058981,
      "grad_norm": 0.37908053398132324,
      "learning_rate": 1.9964012537290783e-05,
      "loss": 0.7115,
      "step": 1857
    },
    {
      "epoch": 0.05707615273553897,
      "grad_norm": 0.33274707198143005,
      "learning_rate": 1.9963971562258395e-05,
      "loss": 0.6494,
      "step": 1858
    },
    {
      "epoch": 0.05710687187048813,
      "grad_norm": 0.3254900574684143,
      "learning_rate": 1.9963930563954454e-05,
      "loss": 0.6296,
      "step": 1859
    },
    {
      "epoch": 0.057137591005437284,
      "grad_norm": 0.3304414749145508,
      "learning_rate": 1.996388954237906e-05,
      "loss": 0.5853,
      "step": 1860
    },
    {
      "epoch": 0.057168310140386445,
      "grad_norm": 0.45191147923469543,
      "learning_rate": 1.9963848497532298e-05,
      "loss": 0.6332,
      "step": 1861
    },
    {
      "epoch": 0.05719902927533561,
      "grad_norm": 0.34929314255714417,
      "learning_rate": 1.996380742941428e-05,
      "loss": 0.6308,
      "step": 1862
    },
    {
      "epoch": 0.05722974841028477,
      "grad_norm": 0.44320791959762573,
      "learning_rate": 1.9963766338025086e-05,
      "loss": 0.5749,
      "step": 1863
    },
    {
      "epoch": 0.05726046754523392,
      "grad_norm": 0.38186830282211304,
      "learning_rate": 1.9963725223364826e-05,
      "loss": 0.7038,
      "step": 1864
    },
    {
      "epoch": 0.057291186680183084,
      "grad_norm": 0.35562124848365784,
      "learning_rate": 1.996368408543359e-05,
      "loss": 0.6504,
      "step": 1865
    },
    {
      "epoch": 0.057321905815132246,
      "grad_norm": 0.4203442335128784,
      "learning_rate": 1.996364292423147e-05,
      "loss": 0.5932,
      "step": 1866
    },
    {
      "epoch": 0.05735262495008141,
      "grad_norm": 0.32171741127967834,
      "learning_rate": 1.9963601739758568e-05,
      "loss": 0.6459,
      "step": 1867
    },
    {
      "epoch": 0.05738334408503057,
      "grad_norm": 0.3384965658187866,
      "learning_rate": 1.996356053201498e-05,
      "loss": 0.6221,
      "step": 1868
    },
    {
      "epoch": 0.05741406321997972,
      "grad_norm": 0.35755300521850586,
      "learning_rate": 1.99635193010008e-05,
      "loss": 0.6074,
      "step": 1869
    },
    {
      "epoch": 0.057444782354928885,
      "grad_norm": 0.35449323058128357,
      "learning_rate": 1.9963478046716123e-05,
      "loss": 0.6477,
      "step": 1870
    },
    {
      "epoch": 0.057475501489878046,
      "grad_norm": 0.36527958512306213,
      "learning_rate": 1.9963436769161046e-05,
      "loss": 0.6173,
      "step": 1871
    },
    {
      "epoch": 0.05750622062482721,
      "grad_norm": 0.3522111177444458,
      "learning_rate": 1.996339546833567e-05,
      "loss": 0.6596,
      "step": 1872
    },
    {
      "epoch": 0.05753693975977636,
      "grad_norm": 0.364387571811676,
      "learning_rate": 1.996335414424009e-05,
      "loss": 0.6656,
      "step": 1873
    },
    {
      "epoch": 0.057567658894725524,
      "grad_norm": 0.3396987020969391,
      "learning_rate": 1.9963312796874396e-05,
      "loss": 0.6133,
      "step": 1874
    },
    {
      "epoch": 0.057598378029674685,
      "grad_norm": 0.4459451138973236,
      "learning_rate": 1.9963271426238688e-05,
      "loss": 0.544,
      "step": 1875
    },
    {
      "epoch": 0.057629097164623846,
      "grad_norm": 0.3512122333049774,
      "learning_rate": 1.9963230032333068e-05,
      "loss": 0.7005,
      "step": 1876
    },
    {
      "epoch": 0.057659816299573,
      "grad_norm": 0.3311053216457367,
      "learning_rate": 1.9963188615157627e-05,
      "loss": 0.6254,
      "step": 1877
    },
    {
      "epoch": 0.05769053543452216,
      "grad_norm": 0.36754411458969116,
      "learning_rate": 1.9963147174712462e-05,
      "loss": 0.614,
      "step": 1878
    },
    {
      "epoch": 0.057721254569471324,
      "grad_norm": 0.3394148051738739,
      "learning_rate": 1.996310571099767e-05,
      "loss": 0.5888,
      "step": 1879
    },
    {
      "epoch": 0.057751973704420485,
      "grad_norm": 0.6702133417129517,
      "learning_rate": 1.996306422401335e-05,
      "loss": 0.6552,
      "step": 1880
    },
    {
      "epoch": 0.05778269283936965,
      "grad_norm": 0.336073637008667,
      "learning_rate": 1.99630227137596e-05,
      "loss": 0.6284,
      "step": 1881
    },
    {
      "epoch": 0.0578134119743188,
      "grad_norm": 0.333565890789032,
      "learning_rate": 1.9962981180236512e-05,
      "loss": 0.6309,
      "step": 1882
    },
    {
      "epoch": 0.05784413110926796,
      "grad_norm": 0.328255832195282,
      "learning_rate": 1.9962939623444186e-05,
      "loss": 0.5806,
      "step": 1883
    },
    {
      "epoch": 0.057874850244217124,
      "grad_norm": 0.33637914061546326,
      "learning_rate": 1.996289804338272e-05,
      "loss": 0.6502,
      "step": 1884
    },
    {
      "epoch": 0.057905569379166286,
      "grad_norm": 0.38039854168891907,
      "learning_rate": 1.9962856440052208e-05,
      "loss": 0.5823,
      "step": 1885
    },
    {
      "epoch": 0.05793628851411544,
      "grad_norm": 0.35690635442733765,
      "learning_rate": 1.9962814813452753e-05,
      "loss": 0.5955,
      "step": 1886
    },
    {
      "epoch": 0.0579670076490646,
      "grad_norm": 0.3070641756057739,
      "learning_rate": 1.9962773163584445e-05,
      "loss": 0.6028,
      "step": 1887
    },
    {
      "epoch": 0.05799772678401376,
      "grad_norm": 0.35995957255363464,
      "learning_rate": 1.9962731490447383e-05,
      "loss": 0.7271,
      "step": 1888
    },
    {
      "epoch": 0.058028445918962925,
      "grad_norm": 0.3890112638473511,
      "learning_rate": 1.996268979404167e-05,
      "loss": 0.6347,
      "step": 1889
    },
    {
      "epoch": 0.05805916505391208,
      "grad_norm": 0.3295291066169739,
      "learning_rate": 1.9962648074367394e-05,
      "loss": 0.6074,
      "step": 1890
    },
    {
      "epoch": 0.05808988418886124,
      "grad_norm": 0.361087828874588,
      "learning_rate": 1.996260633142466e-05,
      "loss": 0.6289,
      "step": 1891
    },
    {
      "epoch": 0.0581206033238104,
      "grad_norm": 0.34797289967536926,
      "learning_rate": 1.9962564565213565e-05,
      "loss": 0.5912,
      "step": 1892
    },
    {
      "epoch": 0.05815132245875956,
      "grad_norm": 0.3457486033439636,
      "learning_rate": 1.9962522775734204e-05,
      "loss": 0.6287,
      "step": 1893
    },
    {
      "epoch": 0.05818204159370872,
      "grad_norm": 0.3835926651954651,
      "learning_rate": 1.9962480962986675e-05,
      "loss": 0.6334,
      "step": 1894
    },
    {
      "epoch": 0.05821276072865788,
      "grad_norm": 0.46173426508903503,
      "learning_rate": 1.9962439126971073e-05,
      "loss": 0.5848,
      "step": 1895
    },
    {
      "epoch": 0.05824347986360704,
      "grad_norm": 0.5842630863189697,
      "learning_rate": 1.9962397267687503e-05,
      "loss": 0.6981,
      "step": 1896
    },
    {
      "epoch": 0.0582741989985562,
      "grad_norm": 0.31368395686149597,
      "learning_rate": 1.9962355385136053e-05,
      "loss": 0.6539,
      "step": 1897
    },
    {
      "epoch": 0.058304918133505364,
      "grad_norm": 0.36070555448532104,
      "learning_rate": 1.996231347931683e-05,
      "loss": 0.5601,
      "step": 1898
    },
    {
      "epoch": 0.05833563726845452,
      "grad_norm": 0.3700317144393921,
      "learning_rate": 1.996227155022993e-05,
      "loss": 0.6711,
      "step": 1899
    },
    {
      "epoch": 0.05836635640340368,
      "grad_norm": 0.37846943736076355,
      "learning_rate": 1.9962229597875447e-05,
      "loss": 0.7282,
      "step": 1900
    },
    {
      "epoch": 0.05839707553835284,
      "grad_norm": 0.3402721583843231,
      "learning_rate": 1.996218762225348e-05,
      "loss": 0.581,
      "step": 1901
    },
    {
      "epoch": 0.058427794673302,
      "grad_norm": 0.34083840250968933,
      "learning_rate": 1.996214562336413e-05,
      "loss": 0.6463,
      "step": 1902
    },
    {
      "epoch": 0.05845851380825116,
      "grad_norm": 0.3564232885837555,
      "learning_rate": 1.996210360120749e-05,
      "loss": 0.6563,
      "step": 1903
    },
    {
      "epoch": 0.05848923294320032,
      "grad_norm": 0.4010450541973114,
      "learning_rate": 1.9962061555783667e-05,
      "loss": 0.6782,
      "step": 1904
    },
    {
      "epoch": 0.05851995207814948,
      "grad_norm": 0.3669174015522003,
      "learning_rate": 1.996201948709275e-05,
      "loss": 0.718,
      "step": 1905
    },
    {
      "epoch": 0.05855067121309864,
      "grad_norm": 0.32990458607673645,
      "learning_rate": 1.996197739513484e-05,
      "loss": 0.5863,
      "step": 1906
    },
    {
      "epoch": 0.058581390348047796,
      "grad_norm": 0.34461724758148193,
      "learning_rate": 1.9961935279910035e-05,
      "loss": 0.6445,
      "step": 1907
    },
    {
      "epoch": 0.05861210948299696,
      "grad_norm": 0.33632513880729675,
      "learning_rate": 1.9961893141418436e-05,
      "loss": 0.6195,
      "step": 1908
    },
    {
      "epoch": 0.05864282861794612,
      "grad_norm": 0.33710768818855286,
      "learning_rate": 1.9961850979660142e-05,
      "loss": 0.6783,
      "step": 1909
    },
    {
      "epoch": 0.05867354775289528,
      "grad_norm": 0.3746880888938904,
      "learning_rate": 1.9961808794635246e-05,
      "loss": 0.5438,
      "step": 1910
    },
    {
      "epoch": 0.058704266887844435,
      "grad_norm": 0.43682464957237244,
      "learning_rate": 1.9961766586343853e-05,
      "loss": 0.5646,
      "step": 1911
    },
    {
      "epoch": 0.058734986022793596,
      "grad_norm": 0.34957990050315857,
      "learning_rate": 1.9961724354786053e-05,
      "loss": 0.6046,
      "step": 1912
    },
    {
      "epoch": 0.05876570515774276,
      "grad_norm": 0.4093162715435028,
      "learning_rate": 1.9961682099961956e-05,
      "loss": 0.6684,
      "step": 1913
    },
    {
      "epoch": 0.05879642429269192,
      "grad_norm": 0.3118473291397095,
      "learning_rate": 1.9961639821871653e-05,
      "loss": 0.6549,
      "step": 1914
    },
    {
      "epoch": 0.05882714342764108,
      "grad_norm": 0.325076699256897,
      "learning_rate": 1.9961597520515245e-05,
      "loss": 0.6655,
      "step": 1915
    },
    {
      "epoch": 0.058857862562590235,
      "grad_norm": 0.31546851992607117,
      "learning_rate": 1.9961555195892828e-05,
      "loss": 0.635,
      "step": 1916
    },
    {
      "epoch": 0.0588885816975394,
      "grad_norm": 0.3521716594696045,
      "learning_rate": 1.9961512848004502e-05,
      "loss": 0.6021,
      "step": 1917
    },
    {
      "epoch": 0.05891930083248856,
      "grad_norm": 0.294404000043869,
      "learning_rate": 1.996147047685037e-05,
      "loss": 0.5636,
      "step": 1918
    },
    {
      "epoch": 0.05895001996743772,
      "grad_norm": 0.33375808596611023,
      "learning_rate": 1.9961428082430527e-05,
      "loss": 0.5356,
      "step": 1919
    },
    {
      "epoch": 0.058980739102386874,
      "grad_norm": 0.3853186368942261,
      "learning_rate": 1.996138566474507e-05,
      "loss": 0.7362,
      "step": 1920
    },
    {
      "epoch": 0.059011458237336036,
      "grad_norm": 0.3215197026729584,
      "learning_rate": 1.9961343223794107e-05,
      "loss": 0.5889,
      "step": 1921
    },
    {
      "epoch": 0.0590421773722852,
      "grad_norm": 0.3713286817073822,
      "learning_rate": 1.996130075957773e-05,
      "loss": 0.6738,
      "step": 1922
    },
    {
      "epoch": 0.05907289650723436,
      "grad_norm": 0.516392171382904,
      "learning_rate": 1.996125827209604e-05,
      "loss": 0.6039,
      "step": 1923
    },
    {
      "epoch": 0.05910361564218351,
      "grad_norm": 0.3217048645019531,
      "learning_rate": 1.996121576134913e-05,
      "loss": 0.6858,
      "step": 1924
    },
    {
      "epoch": 0.059134334777132674,
      "grad_norm": 0.33400759100914,
      "learning_rate": 1.9961173227337108e-05,
      "loss": 0.5944,
      "step": 1925
    },
    {
      "epoch": 0.059165053912081836,
      "grad_norm": 0.32303401827812195,
      "learning_rate": 1.9961130670060073e-05,
      "loss": 0.6157,
      "step": 1926
    },
    {
      "epoch": 0.059195773047031,
      "grad_norm": 0.3906562328338623,
      "learning_rate": 1.996108808951812e-05,
      "loss": 0.6809,
      "step": 1927
    },
    {
      "epoch": 0.05922649218198016,
      "grad_norm": 0.3516508936882019,
      "learning_rate": 1.996104548571135e-05,
      "loss": 0.6279,
      "step": 1928
    },
    {
      "epoch": 0.05925721131692931,
      "grad_norm": 0.3840316832065582,
      "learning_rate": 1.996100285863986e-05,
      "loss": 0.7507,
      "step": 1929
    },
    {
      "epoch": 0.059287930451878475,
      "grad_norm": 0.33520829677581787,
      "learning_rate": 1.9960960208303753e-05,
      "loss": 0.4881,
      "step": 1930
    },
    {
      "epoch": 0.059318649586827636,
      "grad_norm": 0.36315110325813293,
      "learning_rate": 1.9960917534703128e-05,
      "loss": 0.677,
      "step": 1931
    },
    {
      "epoch": 0.0593493687217768,
      "grad_norm": 0.3510785400867462,
      "learning_rate": 1.9960874837838086e-05,
      "loss": 0.6949,
      "step": 1932
    },
    {
      "epoch": 0.05938008785672595,
      "grad_norm": 0.3370154798030853,
      "learning_rate": 1.9960832117708728e-05,
      "loss": 0.6104,
      "step": 1933
    },
    {
      "epoch": 0.059410806991675114,
      "grad_norm": 0.33316150307655334,
      "learning_rate": 1.9960789374315146e-05,
      "loss": 0.6694,
      "step": 1934
    },
    {
      "epoch": 0.059441526126624275,
      "grad_norm": 0.3218884766101837,
      "learning_rate": 1.9960746607657448e-05,
      "loss": 0.6159,
      "step": 1935
    },
    {
      "epoch": 0.059472245261573436,
      "grad_norm": 0.37028834223747253,
      "learning_rate": 1.9960703817735726e-05,
      "loss": 0.6328,
      "step": 1936
    },
    {
      "epoch": 0.05950296439652259,
      "grad_norm": 0.3951369524002075,
      "learning_rate": 1.996066100455009e-05,
      "loss": 0.5957,
      "step": 1937
    },
    {
      "epoch": 0.05953368353147175,
      "grad_norm": 0.2833153307437897,
      "learning_rate": 1.996061816810063e-05,
      "loss": 0.6079,
      "step": 1938
    },
    {
      "epoch": 0.059564402666420914,
      "grad_norm": 0.30723920464515686,
      "learning_rate": 1.9960575308387452e-05,
      "loss": 0.5969,
      "step": 1939
    },
    {
      "epoch": 0.059595121801370075,
      "grad_norm": 0.3215668201446533,
      "learning_rate": 1.9960532425410653e-05,
      "loss": 0.5895,
      "step": 1940
    },
    {
      "epoch": 0.05962584093631923,
      "grad_norm": 0.3341771364212036,
      "learning_rate": 1.996048951917034e-05,
      "loss": 0.5528,
      "step": 1941
    },
    {
      "epoch": 0.05965656007126839,
      "grad_norm": 0.32899585366249084,
      "learning_rate": 1.9960446589666603e-05,
      "loss": 0.5894,
      "step": 1942
    },
    {
      "epoch": 0.05968727920621755,
      "grad_norm": 0.33236971497535706,
      "learning_rate": 1.996040363689955e-05,
      "loss": 0.5846,
      "step": 1943
    },
    {
      "epoch": 0.059717998341166714,
      "grad_norm": 0.37765568494796753,
      "learning_rate": 1.996036066086928e-05,
      "loss": 0.5184,
      "step": 1944
    },
    {
      "epoch": 0.059748717476115876,
      "grad_norm": 0.5443404912948608,
      "learning_rate": 1.996031766157589e-05,
      "loss": 0.61,
      "step": 1945
    },
    {
      "epoch": 0.05977943661106503,
      "grad_norm": 1.7714771032333374,
      "learning_rate": 1.9960274639019482e-05,
      "loss": 0.5958,
      "step": 1946
    },
    {
      "epoch": 0.05981015574601419,
      "grad_norm": 0.32788190245628357,
      "learning_rate": 1.9960231593200162e-05,
      "loss": 0.5766,
      "step": 1947
    },
    {
      "epoch": 0.05984087488096335,
      "grad_norm": 0.3337060809135437,
      "learning_rate": 1.996018852411802e-05,
      "loss": 0.6893,
      "step": 1948
    },
    {
      "epoch": 0.059871594015912515,
      "grad_norm": 0.34407633543014526,
      "learning_rate": 1.9960145431773163e-05,
      "loss": 0.657,
      "step": 1949
    },
    {
      "epoch": 0.05990231315086167,
      "grad_norm": 0.357710063457489,
      "learning_rate": 1.9960102316165694e-05,
      "loss": 0.6068,
      "step": 1950
    },
    {
      "epoch": 0.05993303228581083,
      "grad_norm": 0.36166834831237793,
      "learning_rate": 1.9960059177295705e-05,
      "loss": 0.6723,
      "step": 1951
    },
    {
      "epoch": 0.05996375142075999,
      "grad_norm": 0.3370208740234375,
      "learning_rate": 1.9960016015163305e-05,
      "loss": 0.593,
      "step": 1952
    },
    {
      "epoch": 0.05999447055570915,
      "grad_norm": 0.3309382200241089,
      "learning_rate": 1.995997282976859e-05,
      "loss": 0.5448,
      "step": 1953
    },
    {
      "epoch": 0.06002518969065831,
      "grad_norm": 0.3434211015701294,
      "learning_rate": 1.9959929621111667e-05,
      "loss": 0.6144,
      "step": 1954
    },
    {
      "epoch": 0.06005590882560747,
      "grad_norm": 0.33767828345298767,
      "learning_rate": 1.9959886389192632e-05,
      "loss": 0.6763,
      "step": 1955
    },
    {
      "epoch": 0.06008662796055663,
      "grad_norm": 0.3372674882411957,
      "learning_rate": 1.9959843134011582e-05,
      "loss": 0.6525,
      "step": 1956
    },
    {
      "epoch": 0.06011734709550579,
      "grad_norm": 0.42414262890815735,
      "learning_rate": 1.9959799855568626e-05,
      "loss": 0.5901,
      "step": 1957
    },
    {
      "epoch": 0.060148066230454954,
      "grad_norm": 0.32659855484962463,
      "learning_rate": 1.995975655386386e-05,
      "loss": 0.7091,
      "step": 1958
    },
    {
      "epoch": 0.06017878536540411,
      "grad_norm": 0.3550529181957245,
      "learning_rate": 1.995971322889739e-05,
      "loss": 0.5484,
      "step": 1959
    },
    {
      "epoch": 0.06020950450035327,
      "grad_norm": 0.3221299648284912,
      "learning_rate": 1.9959669880669313e-05,
      "loss": 0.6626,
      "step": 1960
    },
    {
      "epoch": 0.06024022363530243,
      "grad_norm": 0.38942691683769226,
      "learning_rate": 1.9959626509179733e-05,
      "loss": 0.5829,
      "step": 1961
    },
    {
      "epoch": 0.06027094277025159,
      "grad_norm": 0.40637823939323425,
      "learning_rate": 1.995958311442875e-05,
      "loss": 0.7706,
      "step": 1962
    },
    {
      "epoch": 0.06030166190520075,
      "grad_norm": 0.35358142852783203,
      "learning_rate": 1.995953969641646e-05,
      "loss": 0.6262,
      "step": 1963
    },
    {
      "epoch": 0.06033238104014991,
      "grad_norm": 0.3889586329460144,
      "learning_rate": 1.9959496255142973e-05,
      "loss": 0.6075,
      "step": 1964
    },
    {
      "epoch": 0.06036310017509907,
      "grad_norm": 0.3544589877128601,
      "learning_rate": 1.995945279060839e-05,
      "loss": 0.5939,
      "step": 1965
    },
    {
      "epoch": 0.06039381931004823,
      "grad_norm": 0.47478851675987244,
      "learning_rate": 1.9959409302812803e-05,
      "loss": 0.684,
      "step": 1966
    },
    {
      "epoch": 0.060424538444997386,
      "grad_norm": 0.3987491726875305,
      "learning_rate": 1.9959365791756324e-05,
      "loss": 0.6862,
      "step": 1967
    },
    {
      "epoch": 0.06045525757994655,
      "grad_norm": 0.33788686990737915,
      "learning_rate": 1.995932225743905e-05,
      "loss": 0.6017,
      "step": 1968
    },
    {
      "epoch": 0.06048597671489571,
      "grad_norm": 0.35874420404434204,
      "learning_rate": 1.995927869986108e-05,
      "loss": 0.6155,
      "step": 1969
    },
    {
      "epoch": 0.06051669584984487,
      "grad_norm": 0.30768996477127075,
      "learning_rate": 1.9959235119022528e-05,
      "loss": 0.6335,
      "step": 1970
    },
    {
      "epoch": 0.060547414984794025,
      "grad_norm": 0.3538748621940613,
      "learning_rate": 1.995919151492348e-05,
      "loss": 0.7285,
      "step": 1971
    },
    {
      "epoch": 0.060578134119743186,
      "grad_norm": 0.32906243205070496,
      "learning_rate": 1.995914788756404e-05,
      "loss": 0.6362,
      "step": 1972
    },
    {
      "epoch": 0.06060885325469235,
      "grad_norm": 0.7795906662940979,
      "learning_rate": 1.9959104236944325e-05,
      "loss": 0.627,
      "step": 1973
    },
    {
      "epoch": 0.06063957238964151,
      "grad_norm": 0.3739781081676483,
      "learning_rate": 1.995906056306442e-05,
      "loss": 0.6602,
      "step": 1974
    },
    {
      "epoch": 0.06067029152459067,
      "grad_norm": 0.33342576026916504,
      "learning_rate": 1.9959016865924435e-05,
      "loss": 0.6336,
      "step": 1975
    },
    {
      "epoch": 0.060701010659539825,
      "grad_norm": 0.3325606882572174,
      "learning_rate": 1.995897314552447e-05,
      "loss": 0.6575,
      "step": 1976
    },
    {
      "epoch": 0.06073172979448899,
      "grad_norm": 0.363676518201828,
      "learning_rate": 1.995892940186463e-05,
      "loss": 0.6119,
      "step": 1977
    },
    {
      "epoch": 0.06076244892943815,
      "grad_norm": 0.3407360315322876,
      "learning_rate": 1.9958885634945013e-05,
      "loss": 0.5727,
      "step": 1978
    },
    {
      "epoch": 0.06079316806438731,
      "grad_norm": 0.34714728593826294,
      "learning_rate": 1.9958841844765723e-05,
      "loss": 0.5528,
      "step": 1979
    },
    {
      "epoch": 0.060823887199336464,
      "grad_norm": 0.3789319694042206,
      "learning_rate": 1.9958798031326864e-05,
      "loss": 0.6909,
      "step": 1980
    },
    {
      "epoch": 0.060854606334285626,
      "grad_norm": 0.3390599489212036,
      "learning_rate": 1.9958754194628537e-05,
      "loss": 0.6981,
      "step": 1981
    },
    {
      "epoch": 0.06088532546923479,
      "grad_norm": 0.3374008536338806,
      "learning_rate": 1.9958710334670842e-05,
      "loss": 0.6679,
      "step": 1982
    },
    {
      "epoch": 0.06091604460418395,
      "grad_norm": 0.3059338629245758,
      "learning_rate": 1.9958666451453883e-05,
      "loss": 0.5899,
      "step": 1983
    },
    {
      "epoch": 0.0609467637391331,
      "grad_norm": 0.32157742977142334,
      "learning_rate": 1.9958622544977765e-05,
      "loss": 0.6735,
      "step": 1984
    },
    {
      "epoch": 0.060977482874082264,
      "grad_norm": 0.35762548446655273,
      "learning_rate": 1.9958578615242587e-05,
      "loss": 0.6715,
      "step": 1985
    },
    {
      "epoch": 0.061008202009031426,
      "grad_norm": 0.4238846004009247,
      "learning_rate": 1.9958534662248453e-05,
      "loss": 0.5757,
      "step": 1986
    },
    {
      "epoch": 0.06103892114398059,
      "grad_norm": 0.5919464230537415,
      "learning_rate": 1.9958490685995465e-05,
      "loss": 0.6297,
      "step": 1987
    },
    {
      "epoch": 0.06106964027892975,
      "grad_norm": 0.36047831177711487,
      "learning_rate": 1.995844668648373e-05,
      "loss": 0.6197,
      "step": 1988
    },
    {
      "epoch": 0.0611003594138789,
      "grad_norm": 0.4208289086818695,
      "learning_rate": 1.9958402663713344e-05,
      "loss": 0.5795,
      "step": 1989
    },
    {
      "epoch": 0.061131078548828065,
      "grad_norm": 0.3347480297088623,
      "learning_rate": 1.9958358617684418e-05,
      "loss": 0.6772,
      "step": 1990
    },
    {
      "epoch": 0.061161797683777226,
      "grad_norm": 0.36140525341033936,
      "learning_rate": 1.9958314548397045e-05,
      "loss": 0.5645,
      "step": 1991
    },
    {
      "epoch": 0.06119251681872639,
      "grad_norm": 0.3452851176261902,
      "learning_rate": 1.9958270455851333e-05,
      "loss": 0.7188,
      "step": 1992
    },
    {
      "epoch": 0.06122323595367554,
      "grad_norm": 0.3738088011741638,
      "learning_rate": 1.9958226340047386e-05,
      "loss": 0.6284,
      "step": 1993
    },
    {
      "epoch": 0.061253955088624704,
      "grad_norm": 0.36979958415031433,
      "learning_rate": 1.9958182200985305e-05,
      "loss": 0.6323,
      "step": 1994
    },
    {
      "epoch": 0.061284674223573865,
      "grad_norm": 0.3399437963962555,
      "learning_rate": 1.99581380386652e-05,
      "loss": 0.5732,
      "step": 1995
    },
    {
      "epoch": 0.061315393358523027,
      "grad_norm": 0.3622000515460968,
      "learning_rate": 1.9958093853087158e-05,
      "loss": 0.6186,
      "step": 1996
    },
    {
      "epoch": 0.06134611249347218,
      "grad_norm": 0.3338692784309387,
      "learning_rate": 1.99580496442513e-05,
      "loss": 0.6405,
      "step": 1997
    },
    {
      "epoch": 0.06137683162842134,
      "grad_norm": 0.3561590313911438,
      "learning_rate": 1.995800541215772e-05,
      "loss": 0.583,
      "step": 1998
    },
    {
      "epoch": 0.061407550763370504,
      "grad_norm": 0.39040496945381165,
      "learning_rate": 1.995796115680652e-05,
      "loss": 0.6663,
      "step": 1999
    },
    {
      "epoch": 0.061438269898319665,
      "grad_norm": 0.34152212738990784,
      "learning_rate": 1.9957916878197808e-05,
      "loss": 0.5743,
      "step": 2000
    },
    {
      "epoch": 0.06146898903326882,
      "grad_norm": 0.32716041803359985,
      "learning_rate": 1.9957872576331688e-05,
      "loss": 0.5898,
      "step": 2001
    },
    {
      "epoch": 0.06149970816821798,
      "grad_norm": 0.3220956027507782,
      "learning_rate": 1.9957828251208258e-05,
      "loss": 0.6262,
      "step": 2002
    },
    {
      "epoch": 0.06153042730316714,
      "grad_norm": 0.35508161783218384,
      "learning_rate": 1.9957783902827625e-05,
      "loss": 0.6901,
      "step": 2003
    },
    {
      "epoch": 0.061561146438116304,
      "grad_norm": 0.3355950117111206,
      "learning_rate": 1.9957739531189896e-05,
      "loss": 0.5956,
      "step": 2004
    },
    {
      "epoch": 0.061591865573065466,
      "grad_norm": 0.32397258281707764,
      "learning_rate": 1.9957695136295167e-05,
      "loss": 0.6232,
      "step": 2005
    },
    {
      "epoch": 0.06162258470801462,
      "grad_norm": 0.3622901141643524,
      "learning_rate": 1.9957650718143546e-05,
      "loss": 0.581,
      "step": 2006
    },
    {
      "epoch": 0.06165330384296378,
      "grad_norm": 0.3379761874675751,
      "learning_rate": 1.9957606276735137e-05,
      "loss": 0.7019,
      "step": 2007
    },
    {
      "epoch": 0.06168402297791294,
      "grad_norm": 0.37739211320877075,
      "learning_rate": 1.9957561812070043e-05,
      "loss": 0.5951,
      "step": 2008
    },
    {
      "epoch": 0.061714742112862105,
      "grad_norm": 0.31355494260787964,
      "learning_rate": 1.995751732414837e-05,
      "loss": 0.6131,
      "step": 2009
    },
    {
      "epoch": 0.06174546124781126,
      "grad_norm": 0.47889384627342224,
      "learning_rate": 1.9957472812970215e-05,
      "loss": 0.6291,
      "step": 2010
    },
    {
      "epoch": 0.06177618038276042,
      "grad_norm": 0.3297981023788452,
      "learning_rate": 1.9957428278535688e-05,
      "loss": 0.5747,
      "step": 2011
    },
    {
      "epoch": 0.06180689951770958,
      "grad_norm": 0.4766994118690491,
      "learning_rate": 1.9957383720844892e-05,
      "loss": 0.5804,
      "step": 2012
    },
    {
      "epoch": 0.06183761865265874,
      "grad_norm": 0.33408433198928833,
      "learning_rate": 1.9957339139897933e-05,
      "loss": 0.6645,
      "step": 2013
    },
    {
      "epoch": 0.0618683377876079,
      "grad_norm": 0.34987059235572815,
      "learning_rate": 1.9957294535694915e-05,
      "loss": 0.6459,
      "step": 2014
    },
    {
      "epoch": 0.06189905692255706,
      "grad_norm": 0.35812458395957947,
      "learning_rate": 1.9957249908235936e-05,
      "loss": 0.6221,
      "step": 2015
    },
    {
      "epoch": 0.06192977605750622,
      "grad_norm": 0.3241878151893616,
      "learning_rate": 1.9957205257521106e-05,
      "loss": 0.6355,
      "step": 2016
    },
    {
      "epoch": 0.06196049519245538,
      "grad_norm": 0.3208383023738861,
      "learning_rate": 1.9957160583550528e-05,
      "loss": 0.6038,
      "step": 2017
    },
    {
      "epoch": 0.06199121432740454,
      "grad_norm": 0.3224657475948334,
      "learning_rate": 1.9957115886324305e-05,
      "loss": 0.652,
      "step": 2018
    },
    {
      "epoch": 0.0620219334623537,
      "grad_norm": 0.3631000220775604,
      "learning_rate": 1.9957071165842542e-05,
      "loss": 0.644,
      "step": 2019
    },
    {
      "epoch": 0.06205265259730286,
      "grad_norm": 0.45039403438568115,
      "learning_rate": 1.9957026422105347e-05,
      "loss": 0.6209,
      "step": 2020
    },
    {
      "epoch": 0.06208337173225202,
      "grad_norm": 0.33488887548446655,
      "learning_rate": 1.9956981655112822e-05,
      "loss": 0.6399,
      "step": 2021
    },
    {
      "epoch": 0.06211409086720118,
      "grad_norm": 0.37546268105506897,
      "learning_rate": 1.9956936864865065e-05,
      "loss": 0.6463,
      "step": 2022
    },
    {
      "epoch": 0.06214481000215034,
      "grad_norm": 0.314593642950058,
      "learning_rate": 1.995689205136219e-05,
      "loss": 0.6604,
      "step": 2023
    },
    {
      "epoch": 0.0621755291370995,
      "grad_norm": 0.3480203151702881,
      "learning_rate": 1.9956847214604302e-05,
      "loss": 0.5937,
      "step": 2024
    },
    {
      "epoch": 0.06220624827204866,
      "grad_norm": 0.343314528465271,
      "learning_rate": 1.9956802354591496e-05,
      "loss": 0.6662,
      "step": 2025
    },
    {
      "epoch": 0.06223696740699782,
      "grad_norm": 0.3652275502681732,
      "learning_rate": 1.9956757471323885e-05,
      "loss": 0.6379,
      "step": 2026
    },
    {
      "epoch": 0.062267686541946976,
      "grad_norm": 0.3650220036506653,
      "learning_rate": 1.995671256480157e-05,
      "loss": 0.5957,
      "step": 2027
    },
    {
      "epoch": 0.06229840567689614,
      "grad_norm": 0.35878440737724304,
      "learning_rate": 1.995666763502466e-05,
      "loss": 0.6018,
      "step": 2028
    },
    {
      "epoch": 0.0623291248118453,
      "grad_norm": 0.3804531693458557,
      "learning_rate": 1.9956622681993255e-05,
      "loss": 0.6474,
      "step": 2029
    },
    {
      "epoch": 0.06235984394679446,
      "grad_norm": 0.33783742785453796,
      "learning_rate": 1.9956577705707463e-05,
      "loss": 0.604,
      "step": 2030
    },
    {
      "epoch": 0.062390563081743615,
      "grad_norm": 0.3206551671028137,
      "learning_rate": 1.9956532706167392e-05,
      "loss": 0.6501,
      "step": 2031
    },
    {
      "epoch": 0.062421282216692776,
      "grad_norm": 0.31462362408638,
      "learning_rate": 1.995648768337314e-05,
      "loss": 0.6115,
      "step": 2032
    },
    {
      "epoch": 0.06245200135164194,
      "grad_norm": 0.3736492395401001,
      "learning_rate": 1.9956442637324814e-05,
      "loss": 0.5779,
      "step": 2033
    },
    {
      "epoch": 0.0624827204865911,
      "grad_norm": 0.34888580441474915,
      "learning_rate": 1.9956397568022527e-05,
      "loss": 0.6153,
      "step": 2034
    },
    {
      "epoch": 0.06251343962154025,
      "grad_norm": 0.3450947403907776,
      "learning_rate": 1.9956352475466373e-05,
      "loss": 0.5892,
      "step": 2035
    },
    {
      "epoch": 0.06254415875648942,
      "grad_norm": 0.3257576823234558,
      "learning_rate": 1.995630735965646e-05,
      "loss": 0.5703,
      "step": 2036
    },
    {
      "epoch": 0.06257487789143858,
      "grad_norm": 0.4108649492263794,
      "learning_rate": 1.9956262220592902e-05,
      "loss": 0.6349,
      "step": 2037
    },
    {
      "epoch": 0.06260559702638774,
      "grad_norm": 0.3595578074455261,
      "learning_rate": 1.9956217058275796e-05,
      "loss": 0.689,
      "step": 2038
    },
    {
      "epoch": 0.0626363161613369,
      "grad_norm": 0.37989306449890137,
      "learning_rate": 1.995617187270525e-05,
      "loss": 0.5531,
      "step": 2039
    },
    {
      "epoch": 0.06266703529628606,
      "grad_norm": 0.3185305893421173,
      "learning_rate": 1.995612666388137e-05,
      "loss": 0.6399,
      "step": 2040
    },
    {
      "epoch": 0.06269775443123522,
      "grad_norm": 0.3371380567550659,
      "learning_rate": 1.995608143180426e-05,
      "loss": 0.6269,
      "step": 2041
    },
    {
      "epoch": 0.06272847356618437,
      "grad_norm": 0.32660025358200073,
      "learning_rate": 1.9956036176474024e-05,
      "loss": 0.6373,
      "step": 2042
    },
    {
      "epoch": 0.06275919270113353,
      "grad_norm": 0.4529273211956024,
      "learning_rate": 1.995599089789077e-05,
      "loss": 0.7178,
      "step": 2043
    },
    {
      "epoch": 0.06278991183608269,
      "grad_norm": 0.3270372152328491,
      "learning_rate": 1.9955945596054608e-05,
      "loss": 0.6177,
      "step": 2044
    },
    {
      "epoch": 0.06282063097103185,
      "grad_norm": 0.35735514760017395,
      "learning_rate": 1.9955900270965636e-05,
      "loss": 0.6139,
      "step": 2045
    },
    {
      "epoch": 0.06285135010598102,
      "grad_norm": 0.42778611183166504,
      "learning_rate": 1.995585492262397e-05,
      "loss": 0.5606,
      "step": 2046
    },
    {
      "epoch": 0.06288206924093018,
      "grad_norm": 0.33018603920936584,
      "learning_rate": 1.9955809551029702e-05,
      "loss": 0.7136,
      "step": 2047
    },
    {
      "epoch": 0.06291278837587934,
      "grad_norm": 0.4222186505794525,
      "learning_rate": 1.995576415618295e-05,
      "loss": 0.5416,
      "step": 2048
    },
    {
      "epoch": 0.0629435075108285,
      "grad_norm": 0.3369393050670624,
      "learning_rate": 1.9955718738083814e-05,
      "loss": 0.6799,
      "step": 2049
    },
    {
      "epoch": 0.06297422664577766,
      "grad_norm": 0.33394452929496765,
      "learning_rate": 1.99556732967324e-05,
      "loss": 0.7366,
      "step": 2050
    },
    {
      "epoch": 0.06300494578072681,
      "grad_norm": 0.32370445132255554,
      "learning_rate": 1.995562783212882e-05,
      "loss": 0.6478,
      "step": 2051
    },
    {
      "epoch": 0.06303566491567597,
      "grad_norm": 0.3291032314300537,
      "learning_rate": 1.9955582344273174e-05,
      "loss": 0.5856,
      "step": 2052
    },
    {
      "epoch": 0.06306638405062513,
      "grad_norm": 0.35613158345222473,
      "learning_rate": 1.995553683316557e-05,
      "loss": 0.6358,
      "step": 2053
    },
    {
      "epoch": 0.0630971031855743,
      "grad_norm": 0.41023147106170654,
      "learning_rate": 1.995549129880611e-05,
      "loss": 0.5944,
      "step": 2054
    },
    {
      "epoch": 0.06312782232052346,
      "grad_norm": 0.35625216364860535,
      "learning_rate": 1.995544574119491e-05,
      "loss": 0.6607,
      "step": 2055
    },
    {
      "epoch": 0.06315854145547262,
      "grad_norm": 0.6555358171463013,
      "learning_rate": 1.995540016033207e-05,
      "loss": 0.699,
      "step": 2056
    },
    {
      "epoch": 0.06318926059042178,
      "grad_norm": 0.31461217999458313,
      "learning_rate": 1.9955354556217696e-05,
      "loss": 0.5648,
      "step": 2057
    },
    {
      "epoch": 0.06321997972537094,
      "grad_norm": 0.35454753041267395,
      "learning_rate": 1.99553089288519e-05,
      "loss": 0.623,
      "step": 2058
    },
    {
      "epoch": 0.06325069886032009,
      "grad_norm": 0.3599033057689667,
      "learning_rate": 1.9955263278234782e-05,
      "loss": 0.6192,
      "step": 2059
    },
    {
      "epoch": 0.06328141799526925,
      "grad_norm": 0.3375680148601532,
      "learning_rate": 1.995521760436645e-05,
      "loss": 0.6223,
      "step": 2060
    },
    {
      "epoch": 0.06331213713021841,
      "grad_norm": 0.3603276312351227,
      "learning_rate": 1.9955171907247014e-05,
      "loss": 0.6708,
      "step": 2061
    },
    {
      "epoch": 0.06334285626516757,
      "grad_norm": 0.36193907260894775,
      "learning_rate": 1.995512618687658e-05,
      "loss": 0.6489,
      "step": 2062
    },
    {
      "epoch": 0.06337357540011673,
      "grad_norm": 0.42661309242248535,
      "learning_rate": 1.9955080443255252e-05,
      "loss": 0.5622,
      "step": 2063
    },
    {
      "epoch": 0.0634042945350659,
      "grad_norm": 0.3199162483215332,
      "learning_rate": 1.9955034676383138e-05,
      "loss": 0.5712,
      "step": 2064
    },
    {
      "epoch": 0.06343501367001506,
      "grad_norm": 0.32310736179351807,
      "learning_rate": 1.9954988886260346e-05,
      "loss": 0.5701,
      "step": 2065
    },
    {
      "epoch": 0.06346573280496422,
      "grad_norm": 0.3517463803291321,
      "learning_rate": 1.995494307288698e-05,
      "loss": 0.6471,
      "step": 2066
    },
    {
      "epoch": 0.06349645193991338,
      "grad_norm": 0.3411223888397217,
      "learning_rate": 1.9954897236263154e-05,
      "loss": 0.6022,
      "step": 2067
    },
    {
      "epoch": 0.06352717107486253,
      "grad_norm": 0.33211588859558105,
      "learning_rate": 1.9954851376388967e-05,
      "loss": 0.5958,
      "step": 2068
    },
    {
      "epoch": 0.06355789020981169,
      "grad_norm": 0.3234077990055084,
      "learning_rate": 1.995480549326453e-05,
      "loss": 0.5383,
      "step": 2069
    },
    {
      "epoch": 0.06358860934476085,
      "grad_norm": 0.31032007932662964,
      "learning_rate": 1.9954759586889948e-05,
      "loss": 0.6081,
      "step": 2070
    },
    {
      "epoch": 0.06361932847971001,
      "grad_norm": 0.3390188217163086,
      "learning_rate": 1.995471365726533e-05,
      "loss": 0.5522,
      "step": 2071
    },
    {
      "epoch": 0.06365004761465917,
      "grad_norm": 0.3211539387702942,
      "learning_rate": 1.9954667704390783e-05,
      "loss": 0.6225,
      "step": 2072
    },
    {
      "epoch": 0.06368076674960833,
      "grad_norm": 0.3500007092952728,
      "learning_rate": 1.995462172826642e-05,
      "loss": 0.5669,
      "step": 2073
    },
    {
      "epoch": 0.0637114858845575,
      "grad_norm": 0.3570995330810547,
      "learning_rate": 1.9954575728892334e-05,
      "loss": 0.6177,
      "step": 2074
    },
    {
      "epoch": 0.06374220501950666,
      "grad_norm": 0.31760019063949585,
      "learning_rate": 1.9954529706268648e-05,
      "loss": 0.5468,
      "step": 2075
    },
    {
      "epoch": 0.0637729241544558,
      "grad_norm": 0.3548451066017151,
      "learning_rate": 1.9954483660395458e-05,
      "loss": 0.6281,
      "step": 2076
    },
    {
      "epoch": 0.06380364328940497,
      "grad_norm": 0.3533082902431488,
      "learning_rate": 1.9954437591272878e-05,
      "loss": 0.6018,
      "step": 2077
    },
    {
      "epoch": 0.06383436242435413,
      "grad_norm": 0.316623330116272,
      "learning_rate": 1.9954391498901015e-05,
      "loss": 0.6324,
      "step": 2078
    },
    {
      "epoch": 0.06386508155930329,
      "grad_norm": 0.8445413708686829,
      "learning_rate": 1.9954345383279975e-05,
      "loss": 0.5649,
      "step": 2079
    },
    {
      "epoch": 0.06389580069425245,
      "grad_norm": 0.3582322895526886,
      "learning_rate": 1.9954299244409866e-05,
      "loss": 0.6857,
      "step": 2080
    },
    {
      "epoch": 0.06392651982920161,
      "grad_norm": 0.38850030303001404,
      "learning_rate": 1.9954253082290794e-05,
      "loss": 0.5548,
      "step": 2081
    },
    {
      "epoch": 0.06395723896415077,
      "grad_norm": 0.34235695004463196,
      "learning_rate": 1.9954206896922872e-05,
      "loss": 0.5873,
      "step": 2082
    },
    {
      "epoch": 0.06398795809909993,
      "grad_norm": 0.3226953148841858,
      "learning_rate": 1.99541606883062e-05,
      "loss": 0.6257,
      "step": 2083
    },
    {
      "epoch": 0.0640186772340491,
      "grad_norm": 0.3573955297470093,
      "learning_rate": 1.9954114456440893e-05,
      "loss": 0.6359,
      "step": 2084
    },
    {
      "epoch": 0.06404939636899824,
      "grad_norm": 0.3314650058746338,
      "learning_rate": 1.995406820132706e-05,
      "loss": 0.646,
      "step": 2085
    },
    {
      "epoch": 0.0640801155039474,
      "grad_norm": 0.3612213134765625,
      "learning_rate": 1.9954021922964802e-05,
      "loss": 0.5611,
      "step": 2086
    },
    {
      "epoch": 0.06411083463889657,
      "grad_norm": 0.37518632411956787,
      "learning_rate": 1.995397562135423e-05,
      "loss": 0.6228,
      "step": 2087
    },
    {
      "epoch": 0.06414155377384573,
      "grad_norm": 0.3344673812389374,
      "learning_rate": 1.9953929296495455e-05,
      "loss": 0.6411,
      "step": 2088
    },
    {
      "epoch": 0.06417227290879489,
      "grad_norm": 0.32260623574256897,
      "learning_rate": 1.995388294838858e-05,
      "loss": 0.5879,
      "step": 2089
    },
    {
      "epoch": 0.06420299204374405,
      "grad_norm": 0.38375124335289,
      "learning_rate": 1.9953836577033718e-05,
      "loss": 0.5695,
      "step": 2090
    },
    {
      "epoch": 0.06423371117869321,
      "grad_norm": 0.34943363070487976,
      "learning_rate": 1.9953790182430976e-05,
      "loss": 0.5646,
      "step": 2091
    },
    {
      "epoch": 0.06426443031364237,
      "grad_norm": 0.3503745496273041,
      "learning_rate": 1.995374376458046e-05,
      "loss": 0.5949,
      "step": 2092
    },
    {
      "epoch": 0.06429514944859152,
      "grad_norm": 0.3671824336051941,
      "learning_rate": 1.9953697323482283e-05,
      "loss": 0.5476,
      "step": 2093
    },
    {
      "epoch": 0.06432586858354068,
      "grad_norm": 0.3636349141597748,
      "learning_rate": 1.9953650859136548e-05,
      "loss": 0.6286,
      "step": 2094
    },
    {
      "epoch": 0.06435658771848984,
      "grad_norm": 0.372244268655777,
      "learning_rate": 1.9953604371543368e-05,
      "loss": 0.6271,
      "step": 2095
    },
    {
      "epoch": 0.064387306853439,
      "grad_norm": 0.34529027342796326,
      "learning_rate": 1.995355786070285e-05,
      "loss": 0.6282,
      "step": 2096
    },
    {
      "epoch": 0.06441802598838817,
      "grad_norm": 0.32633864879608154,
      "learning_rate": 1.99535113266151e-05,
      "loss": 0.6553,
      "step": 2097
    },
    {
      "epoch": 0.06444874512333733,
      "grad_norm": 0.33246153593063354,
      "learning_rate": 1.995346476928023e-05,
      "loss": 0.606,
      "step": 2098
    },
    {
      "epoch": 0.06447946425828649,
      "grad_norm": 0.330211877822876,
      "learning_rate": 1.995341818869835e-05,
      "loss": 0.6395,
      "step": 2099
    },
    {
      "epoch": 0.06451018339323565,
      "grad_norm": 0.33483198285102844,
      "learning_rate": 1.9953371584869567e-05,
      "loss": 0.547,
      "step": 2100
    },
    {
      "epoch": 0.06454090252818481,
      "grad_norm": 0.33768245577812195,
      "learning_rate": 1.9953324957793987e-05,
      "loss": 0.648,
      "step": 2101
    },
    {
      "epoch": 0.06457162166313396,
      "grad_norm": 0.3206245005130768,
      "learning_rate": 1.995327830747172e-05,
      "loss": 0.6001,
      "step": 2102
    },
    {
      "epoch": 0.06460234079808312,
      "grad_norm": 0.40937384963035583,
      "learning_rate": 1.9953231633902882e-05,
      "loss": 0.5764,
      "step": 2103
    },
    {
      "epoch": 0.06463305993303228,
      "grad_norm": 0.3958721458911896,
      "learning_rate": 1.9953184937087573e-05,
      "loss": 0.6037,
      "step": 2104
    },
    {
      "epoch": 0.06466377906798144,
      "grad_norm": 0.3331458270549774,
      "learning_rate": 1.9953138217025905e-05,
      "loss": 0.6549,
      "step": 2105
    },
    {
      "epoch": 0.0646944982029306,
      "grad_norm": 0.3487420678138733,
      "learning_rate": 1.9953091473717988e-05,
      "loss": 0.6022,
      "step": 2106
    },
    {
      "epoch": 0.06472521733787977,
      "grad_norm": 0.3472624719142914,
      "learning_rate": 1.9953044707163932e-05,
      "loss": 0.647,
      "step": 2107
    },
    {
      "epoch": 0.06475593647282893,
      "grad_norm": 0.3412119746208191,
      "learning_rate": 1.9952997917363843e-05,
      "loss": 0.5626,
      "step": 2108
    },
    {
      "epoch": 0.06478665560777809,
      "grad_norm": 0.3638586103916168,
      "learning_rate": 1.9952951104317836e-05,
      "loss": 0.645,
      "step": 2109
    },
    {
      "epoch": 0.06481737474272724,
      "grad_norm": 0.3402235507965088,
      "learning_rate": 1.9952904268026013e-05,
      "loss": 0.7019,
      "step": 2110
    },
    {
      "epoch": 0.0648480938776764,
      "grad_norm": 0.3330906927585602,
      "learning_rate": 1.9952857408488485e-05,
      "loss": 0.6554,
      "step": 2111
    },
    {
      "epoch": 0.06487881301262556,
      "grad_norm": 0.37610435485839844,
      "learning_rate": 1.9952810525705368e-05,
      "loss": 0.5456,
      "step": 2112
    },
    {
      "epoch": 0.06490953214757472,
      "grad_norm": 0.32916611433029175,
      "learning_rate": 1.9952763619676763e-05,
      "loss": 0.7011,
      "step": 2113
    },
    {
      "epoch": 0.06494025128252388,
      "grad_norm": 0.35643884539604187,
      "learning_rate": 1.9952716690402786e-05,
      "loss": 0.637,
      "step": 2114
    },
    {
      "epoch": 0.06497097041747305,
      "grad_norm": 0.3439774215221405,
      "learning_rate": 1.9952669737883545e-05,
      "loss": 0.6282,
      "step": 2115
    },
    {
      "epoch": 0.0650016895524222,
      "grad_norm": 0.3599433898925781,
      "learning_rate": 1.9952622762119147e-05,
      "loss": 0.6712,
      "step": 2116
    },
    {
      "epoch": 0.06503240868737137,
      "grad_norm": 0.3816385567188263,
      "learning_rate": 1.9952575763109706e-05,
      "loss": 0.5633,
      "step": 2117
    },
    {
      "epoch": 0.06506312782232053,
      "grad_norm": 0.46776336431503296,
      "learning_rate": 1.9952528740855327e-05,
      "loss": 0.5629,
      "step": 2118
    },
    {
      "epoch": 0.06509384695726968,
      "grad_norm": 0.3818588852882385,
      "learning_rate": 1.995248169535612e-05,
      "loss": 0.6649,
      "step": 2119
    },
    {
      "epoch": 0.06512456609221884,
      "grad_norm": 0.32152682542800903,
      "learning_rate": 1.99524346266122e-05,
      "loss": 0.5904,
      "step": 2120
    },
    {
      "epoch": 0.065155285227168,
      "grad_norm": 0.3332715332508087,
      "learning_rate": 1.9952387534623673e-05,
      "loss": 0.695,
      "step": 2121
    },
    {
      "epoch": 0.06518600436211716,
      "grad_norm": 0.32111167907714844,
      "learning_rate": 1.995234041939065e-05,
      "loss": 0.6337,
      "step": 2122
    },
    {
      "epoch": 0.06521672349706632,
      "grad_norm": 0.3152373433113098,
      "learning_rate": 1.9952293280913242e-05,
      "loss": 0.6186,
      "step": 2123
    },
    {
      "epoch": 0.06524744263201548,
      "grad_norm": 0.3914032578468323,
      "learning_rate": 1.9952246119191557e-05,
      "loss": 0.6375,
      "step": 2124
    },
    {
      "epoch": 0.06527816176696465,
      "grad_norm": 0.3522087335586548,
      "learning_rate": 1.9952198934225705e-05,
      "loss": 0.6225,
      "step": 2125
    },
    {
      "epoch": 0.06530888090191381,
      "grad_norm": 0.33481672406196594,
      "learning_rate": 1.99521517260158e-05,
      "loss": 0.6261,
      "step": 2126
    },
    {
      "epoch": 0.06533960003686297,
      "grad_norm": 0.3173021376132965,
      "learning_rate": 1.9952104494561947e-05,
      "loss": 0.6228,
      "step": 2127
    },
    {
      "epoch": 0.06537031917181212,
      "grad_norm": 0.3427012860774994,
      "learning_rate": 1.995205723986426e-05,
      "loss": 0.6566,
      "step": 2128
    },
    {
      "epoch": 0.06540103830676128,
      "grad_norm": 0.3746190369129181,
      "learning_rate": 1.9952009961922846e-05,
      "loss": 0.6358,
      "step": 2129
    },
    {
      "epoch": 0.06543175744171044,
      "grad_norm": 0.3233788311481476,
      "learning_rate": 1.995196266073782e-05,
      "loss": 0.6889,
      "step": 2130
    },
    {
      "epoch": 0.0654624765766596,
      "grad_norm": 0.6477028131484985,
      "learning_rate": 1.995191533630929e-05,
      "loss": 0.6384,
      "step": 2131
    },
    {
      "epoch": 0.06549319571160876,
      "grad_norm": 0.45228806138038635,
      "learning_rate": 1.9951867988637365e-05,
      "loss": 0.6398,
      "step": 2132
    },
    {
      "epoch": 0.06552391484655792,
      "grad_norm": 0.3472476005554199,
      "learning_rate": 1.995182061772216e-05,
      "loss": 0.6323,
      "step": 2133
    },
    {
      "epoch": 0.06555463398150708,
      "grad_norm": 0.3458273410797119,
      "learning_rate": 1.9951773223563783e-05,
      "loss": 0.5658,
      "step": 2134
    },
    {
      "epoch": 0.06558535311645625,
      "grad_norm": 0.33673110604286194,
      "learning_rate": 1.995172580616234e-05,
      "loss": 0.5645,
      "step": 2135
    },
    {
      "epoch": 0.0656160722514054,
      "grad_norm": 0.36029210686683655,
      "learning_rate": 1.9951678365517953e-05,
      "loss": 0.5992,
      "step": 2136
    },
    {
      "epoch": 0.06564679138635456,
      "grad_norm": 0.3110905885696411,
      "learning_rate": 1.9951630901630722e-05,
      "loss": 0.5349,
      "step": 2137
    },
    {
      "epoch": 0.06567751052130372,
      "grad_norm": 0.3103884160518646,
      "learning_rate": 1.9951583414500764e-05,
      "loss": 0.5824,
      "step": 2138
    },
    {
      "epoch": 0.06570822965625288,
      "grad_norm": 0.3443349599838257,
      "learning_rate": 1.9951535904128185e-05,
      "loss": 0.6294,
      "step": 2139
    },
    {
      "epoch": 0.06573894879120204,
      "grad_norm": 0.3701552450656891,
      "learning_rate": 1.99514883705131e-05,
      "loss": 0.4986,
      "step": 2140
    },
    {
      "epoch": 0.0657696679261512,
      "grad_norm": 0.2963980436325073,
      "learning_rate": 1.995144081365562e-05,
      "loss": 0.5955,
      "step": 2141
    },
    {
      "epoch": 0.06580038706110036,
      "grad_norm": 0.3400505781173706,
      "learning_rate": 1.9951393233555855e-05,
      "loss": 0.527,
      "step": 2142
    },
    {
      "epoch": 0.06583110619604952,
      "grad_norm": 0.3331143260002136,
      "learning_rate": 1.9951345630213915e-05,
      "loss": 0.6365,
      "step": 2143
    },
    {
      "epoch": 0.06586182533099869,
      "grad_norm": 0.3495553135871887,
      "learning_rate": 1.9951298003629917e-05,
      "loss": 0.5282,
      "step": 2144
    },
    {
      "epoch": 0.06589254446594783,
      "grad_norm": 0.32302752137184143,
      "learning_rate": 1.9951250353803958e-05,
      "loss": 0.6029,
      "step": 2145
    },
    {
      "epoch": 0.065923263600897,
      "grad_norm": 0.32959187030792236,
      "learning_rate": 1.9951202680736167e-05,
      "loss": 0.5879,
      "step": 2146
    },
    {
      "epoch": 0.06595398273584616,
      "grad_norm": 0.3058619499206543,
      "learning_rate": 1.9951154984426645e-05,
      "loss": 0.5665,
      "step": 2147
    },
    {
      "epoch": 0.06598470187079532,
      "grad_norm": 0.3739256262779236,
      "learning_rate": 1.9951107264875505e-05,
      "loss": 0.6685,
      "step": 2148
    },
    {
      "epoch": 0.06601542100574448,
      "grad_norm": 0.33411556482315063,
      "learning_rate": 1.995105952208286e-05,
      "loss": 0.6673,
      "step": 2149
    },
    {
      "epoch": 0.06604614014069364,
      "grad_norm": 0.32287248969078064,
      "learning_rate": 1.9951011756048818e-05,
      "loss": 0.6358,
      "step": 2150
    },
    {
      "epoch": 0.0660768592756428,
      "grad_norm": 0.3576965928077698,
      "learning_rate": 1.9950963966773497e-05,
      "loss": 0.5938,
      "step": 2151
    },
    {
      "epoch": 0.06610757841059196,
      "grad_norm": 0.3274233043193817,
      "learning_rate": 1.9950916154256998e-05,
      "loss": 0.5995,
      "step": 2152
    },
    {
      "epoch": 0.06613829754554111,
      "grad_norm": 0.3117865324020386,
      "learning_rate": 1.9950868318499447e-05,
      "loss": 0.5917,
      "step": 2153
    },
    {
      "epoch": 0.06616901668049027,
      "grad_norm": 0.3457801938056946,
      "learning_rate": 1.995082045950094e-05,
      "loss": 0.6459,
      "step": 2154
    },
    {
      "epoch": 0.06619973581543943,
      "grad_norm": 0.3461821973323822,
      "learning_rate": 1.9950772577261602e-05,
      "loss": 0.5878,
      "step": 2155
    },
    {
      "epoch": 0.0662304549503886,
      "grad_norm": 0.3079778850078583,
      "learning_rate": 1.995072467178154e-05,
      "loss": 0.6572,
      "step": 2156
    },
    {
      "epoch": 0.06626117408533776,
      "grad_norm": 0.3415226638317108,
      "learning_rate": 1.9950676743060866e-05,
      "loss": 0.6231,
      "step": 2157
    },
    {
      "epoch": 0.06629189322028692,
      "grad_norm": 0.33916139602661133,
      "learning_rate": 1.995062879109969e-05,
      "loss": 0.5889,
      "step": 2158
    },
    {
      "epoch": 0.06632261235523608,
      "grad_norm": 0.3025778830051422,
      "learning_rate": 1.9950580815898127e-05,
      "loss": 0.5918,
      "step": 2159
    },
    {
      "epoch": 0.06635333149018524,
      "grad_norm": 0.3727894127368927,
      "learning_rate": 1.9950532817456287e-05,
      "loss": 0.6332,
      "step": 2160
    },
    {
      "epoch": 0.0663840506251344,
      "grad_norm": 0.3237680494785309,
      "learning_rate": 1.9950484795774282e-05,
      "loss": 0.5384,
      "step": 2161
    },
    {
      "epoch": 0.06641476976008355,
      "grad_norm": 0.33803215622901917,
      "learning_rate": 1.9950436750852224e-05,
      "loss": 0.6623,
      "step": 2162
    },
    {
      "epoch": 0.06644548889503271,
      "grad_norm": 0.36024630069732666,
      "learning_rate": 1.9950388682690228e-05,
      "loss": 0.6538,
      "step": 2163
    },
    {
      "epoch": 0.06647620802998187,
      "grad_norm": 0.38099226355552673,
      "learning_rate": 1.9950340591288402e-05,
      "loss": 0.6681,
      "step": 2164
    },
    {
      "epoch": 0.06650692716493103,
      "grad_norm": 0.3577551245689392,
      "learning_rate": 1.9950292476646865e-05,
      "loss": 0.6139,
      "step": 2165
    },
    {
      "epoch": 0.0665376462998802,
      "grad_norm": 0.3705735504627228,
      "learning_rate": 1.995024433876572e-05,
      "loss": 0.6357,
      "step": 2166
    },
    {
      "epoch": 0.06656836543482936,
      "grad_norm": 0.38249045610427856,
      "learning_rate": 1.9950196177645086e-05,
      "loss": 0.6819,
      "step": 2167
    },
    {
      "epoch": 0.06659908456977852,
      "grad_norm": 0.33235689997673035,
      "learning_rate": 1.9950147993285074e-05,
      "loss": 0.5917,
      "step": 2168
    },
    {
      "epoch": 0.06662980370472768,
      "grad_norm": 0.34283697605133057,
      "learning_rate": 1.9950099785685798e-05,
      "loss": 0.5834,
      "step": 2169
    },
    {
      "epoch": 0.06666052283967683,
      "grad_norm": 0.35009679198265076,
      "learning_rate": 1.9950051554847367e-05,
      "loss": 0.5781,
      "step": 2170
    },
    {
      "epoch": 0.06669124197462599,
      "grad_norm": 0.3518453538417816,
      "learning_rate": 1.9950003300769895e-05,
      "loss": 0.5908,
      "step": 2171
    },
    {
      "epoch": 0.06672196110957515,
      "grad_norm": 0.3643420934677124,
      "learning_rate": 1.99499550234535e-05,
      "loss": 0.6281,
      "step": 2172
    },
    {
      "epoch": 0.06675268024452431,
      "grad_norm": 0.3717498481273651,
      "learning_rate": 1.9949906722898283e-05,
      "loss": 0.5998,
      "step": 2173
    },
    {
      "epoch": 0.06678339937947347,
      "grad_norm": 0.33876290917396545,
      "learning_rate": 1.994985839910437e-05,
      "loss": 0.6156,
      "step": 2174
    },
    {
      "epoch": 0.06681411851442264,
      "grad_norm": 0.30981507897377014,
      "learning_rate": 1.9949810052071866e-05,
      "loss": 0.6361,
      "step": 2175
    },
    {
      "epoch": 0.0668448376493718,
      "grad_norm": 0.3320583403110504,
      "learning_rate": 1.9949761681800885e-05,
      "loss": 0.6606,
      "step": 2176
    },
    {
      "epoch": 0.06687555678432096,
      "grad_norm": 0.35287216305732727,
      "learning_rate": 1.994971328829154e-05,
      "loss": 0.6165,
      "step": 2177
    },
    {
      "epoch": 0.06690627591927012,
      "grad_norm": 0.3695656359195709,
      "learning_rate": 1.9949664871543944e-05,
      "loss": 0.6199,
      "step": 2178
    },
    {
      "epoch": 0.06693699505421927,
      "grad_norm": 0.35671326518058777,
      "learning_rate": 1.9949616431558218e-05,
      "loss": 0.7255,
      "step": 2179
    },
    {
      "epoch": 0.06696771418916843,
      "grad_norm": 0.32923802733421326,
      "learning_rate": 1.994956796833446e-05,
      "loss": 0.6272,
      "step": 2180
    },
    {
      "epoch": 0.06699843332411759,
      "grad_norm": 0.3100261390209198,
      "learning_rate": 1.9949519481872793e-05,
      "loss": 0.5415,
      "step": 2181
    },
    {
      "epoch": 0.06702915245906675,
      "grad_norm": 0.35098424553871155,
      "learning_rate": 1.994947097217333e-05,
      "loss": 0.5633,
      "step": 2182
    },
    {
      "epoch": 0.06705987159401591,
      "grad_norm": 0.3194218575954437,
      "learning_rate": 1.9949422439236185e-05,
      "loss": 0.5973,
      "step": 2183
    },
    {
      "epoch": 0.06709059072896507,
      "grad_norm": 0.4437752068042755,
      "learning_rate": 1.9949373883061462e-05,
      "loss": 0.7611,
      "step": 2184
    },
    {
      "epoch": 0.06712130986391424,
      "grad_norm": 0.30451834201812744,
      "learning_rate": 1.9949325303649284e-05,
      "loss": 0.5577,
      "step": 2185
    },
    {
      "epoch": 0.0671520289988634,
      "grad_norm": 0.3236548900604248,
      "learning_rate": 1.9949276700999768e-05,
      "loss": 0.6526,
      "step": 2186
    },
    {
      "epoch": 0.06718274813381256,
      "grad_norm": 0.34792137145996094,
      "learning_rate": 1.9949228075113013e-05,
      "loss": 0.6377,
      "step": 2187
    },
    {
      "epoch": 0.0672134672687617,
      "grad_norm": 0.37232786417007446,
      "learning_rate": 1.9949179425989147e-05,
      "loss": 0.6068,
      "step": 2188
    },
    {
      "epoch": 0.06724418640371087,
      "grad_norm": 0.36086997389793396,
      "learning_rate": 1.9949130753628273e-05,
      "loss": 0.5905,
      "step": 2189
    },
    {
      "epoch": 0.06727490553866003,
      "grad_norm": 0.3678576350212097,
      "learning_rate": 1.9949082058030514e-05,
      "loss": 0.6277,
      "step": 2190
    },
    {
      "epoch": 0.06730562467360919,
      "grad_norm": 0.3111893832683563,
      "learning_rate": 1.9949033339195975e-05,
      "loss": 0.6299,
      "step": 2191
    },
    {
      "epoch": 0.06733634380855835,
      "grad_norm": 0.3356234133243561,
      "learning_rate": 1.9948984597124778e-05,
      "loss": 0.6017,
      "step": 2192
    },
    {
      "epoch": 0.06736706294350751,
      "grad_norm": 0.3536360561847687,
      "learning_rate": 1.9948935831817027e-05,
      "loss": 0.6462,
      "step": 2193
    },
    {
      "epoch": 0.06739778207845668,
      "grad_norm": 0.3472273051738739,
      "learning_rate": 1.9948887043272846e-05,
      "loss": 0.687,
      "step": 2194
    },
    {
      "epoch": 0.06742850121340584,
      "grad_norm": 0.3442753851413727,
      "learning_rate": 1.994883823149234e-05,
      "loss": 0.6947,
      "step": 2195
    },
    {
      "epoch": 0.06745922034835498,
      "grad_norm": 0.34007900953292847,
      "learning_rate": 1.9948789396475636e-05,
      "loss": 0.579,
      "step": 2196
    },
    {
      "epoch": 0.06748993948330415,
      "grad_norm": 0.3170677423477173,
      "learning_rate": 1.994874053822283e-05,
      "loss": 0.5501,
      "step": 2197
    },
    {
      "epoch": 0.06752065861825331,
      "grad_norm": 0.32207638025283813,
      "learning_rate": 1.9948691656734053e-05,
      "loss": 0.6087,
      "step": 2198
    },
    {
      "epoch": 0.06755137775320247,
      "grad_norm": 0.32594001293182373,
      "learning_rate": 1.9948642752009405e-05,
      "loss": 0.5433,
      "step": 2199
    },
    {
      "epoch": 0.06758209688815163,
      "grad_norm": 0.3319441080093384,
      "learning_rate": 1.994859382404901e-05,
      "loss": 0.6014,
      "step": 2200
    },
    {
      "epoch": 0.06761281602310079,
      "grad_norm": 0.325753390789032,
      "learning_rate": 1.9948544872852982e-05,
      "loss": 0.5819,
      "step": 2201
    },
    {
      "epoch": 0.06764353515804995,
      "grad_norm": 0.2985192835330963,
      "learning_rate": 1.994849589842143e-05,
      "loss": 0.6178,
      "step": 2202
    },
    {
      "epoch": 0.06767425429299911,
      "grad_norm": 0.32980191707611084,
      "learning_rate": 1.9948446900754473e-05,
      "loss": 0.6096,
      "step": 2203
    },
    {
      "epoch": 0.06770497342794828,
      "grad_norm": 0.32874277234077454,
      "learning_rate": 1.994839787985222e-05,
      "loss": 0.6337,
      "step": 2204
    },
    {
      "epoch": 0.06773569256289742,
      "grad_norm": 0.3212631046772003,
      "learning_rate": 1.9948348835714793e-05,
      "loss": 0.6087,
      "step": 2205
    },
    {
      "epoch": 0.06776641169784658,
      "grad_norm": 0.350879967212677,
      "learning_rate": 1.99482997683423e-05,
      "loss": 0.5664,
      "step": 2206
    },
    {
      "epoch": 0.06779713083279575,
      "grad_norm": 0.3025473952293396,
      "learning_rate": 1.994825067773486e-05,
      "loss": 0.5442,
      "step": 2207
    },
    {
      "epoch": 0.06782784996774491,
      "grad_norm": 0.3510275185108185,
      "learning_rate": 1.9948201563892584e-05,
      "loss": 0.5291,
      "step": 2208
    },
    {
      "epoch": 0.06785856910269407,
      "grad_norm": 0.3357773423194885,
      "learning_rate": 1.9948152426815588e-05,
      "loss": 0.6192,
      "step": 2209
    },
    {
      "epoch": 0.06788928823764323,
      "grad_norm": 0.39369672536849976,
      "learning_rate": 1.994810326650399e-05,
      "loss": 0.7361,
      "step": 2210
    },
    {
      "epoch": 0.06792000737259239,
      "grad_norm": 0.36984783411026,
      "learning_rate": 1.9948054082957896e-05,
      "loss": 0.5873,
      "step": 2211
    },
    {
      "epoch": 0.06795072650754155,
      "grad_norm": 0.43243589997291565,
      "learning_rate": 1.9948004876177434e-05,
      "loss": 0.6249,
      "step": 2212
    },
    {
      "epoch": 0.0679814456424907,
      "grad_norm": 0.3033086955547333,
      "learning_rate": 1.994795564616271e-05,
      "loss": 0.6024,
      "step": 2213
    },
    {
      "epoch": 0.06801216477743986,
      "grad_norm": 0.3519750237464905,
      "learning_rate": 1.994790639291384e-05,
      "loss": 0.5912,
      "step": 2214
    },
    {
      "epoch": 0.06804288391238902,
      "grad_norm": 0.3444477319717407,
      "learning_rate": 1.9947857116430938e-05,
      "loss": 0.6537,
      "step": 2215
    },
    {
      "epoch": 0.06807360304733819,
      "grad_norm": 0.32625457644462585,
      "learning_rate": 1.9947807816714123e-05,
      "loss": 0.6347,
      "step": 2216
    },
    {
      "epoch": 0.06810432218228735,
      "grad_norm": 0.3351273834705353,
      "learning_rate": 1.994775849376351e-05,
      "loss": 0.5991,
      "step": 2217
    },
    {
      "epoch": 0.06813504131723651,
      "grad_norm": 0.4342171847820282,
      "learning_rate": 1.9947709147579208e-05,
      "loss": 0.767,
      "step": 2218
    },
    {
      "epoch": 0.06816576045218567,
      "grad_norm": 0.349337100982666,
      "learning_rate": 1.994765977816134e-05,
      "loss": 0.6768,
      "step": 2219
    },
    {
      "epoch": 0.06819647958713483,
      "grad_norm": 0.3772926926612854,
      "learning_rate": 1.9947610385510013e-05,
      "loss": 0.7065,
      "step": 2220
    },
    {
      "epoch": 0.06822719872208399,
      "grad_norm": 0.3229788541793823,
      "learning_rate": 1.9947560969625353e-05,
      "loss": 0.5053,
      "step": 2221
    },
    {
      "epoch": 0.06825791785703314,
      "grad_norm": 0.33497437834739685,
      "learning_rate": 1.9947511530507467e-05,
      "loss": 0.6534,
      "step": 2222
    },
    {
      "epoch": 0.0682886369919823,
      "grad_norm": 0.3466551899909973,
      "learning_rate": 1.9947462068156473e-05,
      "loss": 0.6401,
      "step": 2223
    },
    {
      "epoch": 0.06831935612693146,
      "grad_norm": 0.35122209787368774,
      "learning_rate": 1.9947412582572487e-05,
      "loss": 0.616,
      "step": 2224
    },
    {
      "epoch": 0.06835007526188062,
      "grad_norm": 0.31898894906044006,
      "learning_rate": 1.9947363073755625e-05,
      "loss": 0.6504,
      "step": 2225
    },
    {
      "epoch": 0.06838079439682979,
      "grad_norm": 0.7081322073936462,
      "learning_rate": 1.9947313541706e-05,
      "loss": 0.6698,
      "step": 2226
    },
    {
      "epoch": 0.06841151353177895,
      "grad_norm": 0.33141574263572693,
      "learning_rate": 1.994726398642373e-05,
      "loss": 0.5923,
      "step": 2227
    },
    {
      "epoch": 0.06844223266672811,
      "grad_norm": 0.36821237206459045,
      "learning_rate": 1.994721440790893e-05,
      "loss": 0.6302,
      "step": 2228
    },
    {
      "epoch": 0.06847295180167727,
      "grad_norm": 0.3279934823513031,
      "learning_rate": 1.994716480616172e-05,
      "loss": 0.6228,
      "step": 2229
    },
    {
      "epoch": 0.06850367093662642,
      "grad_norm": 0.34491825103759766,
      "learning_rate": 1.9947115181182206e-05,
      "loss": 0.6311,
      "step": 2230
    },
    {
      "epoch": 0.06853439007157558,
      "grad_norm": 0.3310839533805847,
      "learning_rate": 1.9947065532970513e-05,
      "loss": 0.5552,
      "step": 2231
    },
    {
      "epoch": 0.06856510920652474,
      "grad_norm": 0.35003000497817993,
      "learning_rate": 1.9947015861526757e-05,
      "loss": 0.6093,
      "step": 2232
    },
    {
      "epoch": 0.0685958283414739,
      "grad_norm": 0.32708999514579773,
      "learning_rate": 1.994696616685104e-05,
      "loss": 0.6409,
      "step": 2233
    },
    {
      "epoch": 0.06862654747642306,
      "grad_norm": 0.3440236449241638,
      "learning_rate": 1.9946916448943502e-05,
      "loss": 0.6195,
      "step": 2234
    },
    {
      "epoch": 0.06865726661137223,
      "grad_norm": 0.3515322804450989,
      "learning_rate": 1.994686670780424e-05,
      "loss": 0.7262,
      "step": 2235
    },
    {
      "epoch": 0.06868798574632139,
      "grad_norm": 0.35663193464279175,
      "learning_rate": 1.9946816943433375e-05,
      "loss": 0.5967,
      "step": 2236
    },
    {
      "epoch": 0.06871870488127055,
      "grad_norm": 0.2946612238883972,
      "learning_rate": 1.9946767155831023e-05,
      "loss": 0.6521,
      "step": 2237
    },
    {
      "epoch": 0.06874942401621971,
      "grad_norm": 0.4454301595687866,
      "learning_rate": 1.9946717344997305e-05,
      "loss": 0.6523,
      "step": 2238
    },
    {
      "epoch": 0.06878014315116886,
      "grad_norm": 0.3690214157104492,
      "learning_rate": 1.994666751093233e-05,
      "loss": 0.6302,
      "step": 2239
    },
    {
      "epoch": 0.06881086228611802,
      "grad_norm": 0.29992982745170593,
      "learning_rate": 1.9946617653636223e-05,
      "loss": 0.5953,
      "step": 2240
    },
    {
      "epoch": 0.06884158142106718,
      "grad_norm": 0.33487552404403687,
      "learning_rate": 1.9946567773109095e-05,
      "loss": 0.6012,
      "step": 2241
    },
    {
      "epoch": 0.06887230055601634,
      "grad_norm": 0.3518930971622467,
      "learning_rate": 1.9946517869351062e-05,
      "loss": 0.5544,
      "step": 2242
    },
    {
      "epoch": 0.0689030196909655,
      "grad_norm": 0.32719117403030396,
      "learning_rate": 1.9946467942362242e-05,
      "loss": 0.541,
      "step": 2243
    },
    {
      "epoch": 0.06893373882591466,
      "grad_norm": 0.3556510806083679,
      "learning_rate": 1.994641799214275e-05,
      "loss": 0.661,
      "step": 2244
    },
    {
      "epoch": 0.06896445796086383,
      "grad_norm": 0.3943074643611908,
      "learning_rate": 1.9946368018692708e-05,
      "loss": 0.6122,
      "step": 2245
    },
    {
      "epoch": 0.06899517709581299,
      "grad_norm": 0.35023805499076843,
      "learning_rate": 1.9946318022012226e-05,
      "loss": 0.6368,
      "step": 2246
    },
    {
      "epoch": 0.06902589623076213,
      "grad_norm": 0.35899481177330017,
      "learning_rate": 1.9946268002101426e-05,
      "loss": 0.5897,
      "step": 2247
    },
    {
      "epoch": 0.0690566153657113,
      "grad_norm": 0.3251500427722931,
      "learning_rate": 1.9946217958960422e-05,
      "loss": 0.6765,
      "step": 2248
    },
    {
      "epoch": 0.06908733450066046,
      "grad_norm": 0.36872854828834534,
      "learning_rate": 1.994616789258933e-05,
      "loss": 0.6119,
      "step": 2249
    },
    {
      "epoch": 0.06911805363560962,
      "grad_norm": 0.33494773507118225,
      "learning_rate": 1.9946117802988266e-05,
      "loss": 0.6515,
      "step": 2250
    },
    {
      "epoch": 0.06914877277055878,
      "grad_norm": 0.30779212713241577,
      "learning_rate": 1.994606769015735e-05,
      "loss": 0.6315,
      "step": 2251
    },
    {
      "epoch": 0.06917949190550794,
      "grad_norm": 0.32273975014686584,
      "learning_rate": 1.99460175540967e-05,
      "loss": 0.6472,
      "step": 2252
    },
    {
      "epoch": 0.0692102110404571,
      "grad_norm": 0.41840842366218567,
      "learning_rate": 1.9945967394806432e-05,
      "loss": 0.6202,
      "step": 2253
    },
    {
      "epoch": 0.06924093017540627,
      "grad_norm": 0.355185329914093,
      "learning_rate": 1.994591721228666e-05,
      "loss": 0.6333,
      "step": 2254
    },
    {
      "epoch": 0.06927164931035543,
      "grad_norm": 0.3869832158088684,
      "learning_rate": 1.9945867006537507e-05,
      "loss": 0.6168,
      "step": 2255
    },
    {
      "epoch": 0.06930236844530457,
      "grad_norm": 0.34259966015815735,
      "learning_rate": 1.9945816777559087e-05,
      "loss": 0.6816,
      "step": 2256
    },
    {
      "epoch": 0.06933308758025374,
      "grad_norm": 0.430733323097229,
      "learning_rate": 1.9945766525351516e-05,
      "loss": 0.667,
      "step": 2257
    },
    {
      "epoch": 0.0693638067152029,
      "grad_norm": 0.33048900961875916,
      "learning_rate": 1.994571624991491e-05,
      "loss": 0.5609,
      "step": 2258
    },
    {
      "epoch": 0.06939452585015206,
      "grad_norm": 0.3378935158252716,
      "learning_rate": 1.9945665951249393e-05,
      "loss": 0.629,
      "step": 2259
    },
    {
      "epoch": 0.06942524498510122,
      "grad_norm": 0.36652514338493347,
      "learning_rate": 1.9945615629355077e-05,
      "loss": 0.5554,
      "step": 2260
    },
    {
      "epoch": 0.06945596412005038,
      "grad_norm": 0.32435449957847595,
      "learning_rate": 1.9945565284232082e-05,
      "loss": 0.7183,
      "step": 2261
    },
    {
      "epoch": 0.06948668325499954,
      "grad_norm": 0.3089374303817749,
      "learning_rate": 1.9945514915880523e-05,
      "loss": 0.5832,
      "step": 2262
    },
    {
      "epoch": 0.0695174023899487,
      "grad_norm": 0.3346021771430969,
      "learning_rate": 1.994546452430052e-05,
      "loss": 0.63,
      "step": 2263
    },
    {
      "epoch": 0.06954812152489787,
      "grad_norm": 0.41662389039993286,
      "learning_rate": 1.994541410949219e-05,
      "loss": 0.7098,
      "step": 2264
    },
    {
      "epoch": 0.06957884065984701,
      "grad_norm": 0.35666322708129883,
      "learning_rate": 1.9945363671455654e-05,
      "loss": 0.6115,
      "step": 2265
    },
    {
      "epoch": 0.06960955979479617,
      "grad_norm": 0.32230043411254883,
      "learning_rate": 1.994531321019102e-05,
      "loss": 0.5534,
      "step": 2266
    },
    {
      "epoch": 0.06964027892974534,
      "grad_norm": 0.4277683198451996,
      "learning_rate": 1.9945262725698415e-05,
      "loss": 0.559,
      "step": 2267
    },
    {
      "epoch": 0.0696709980646945,
      "grad_norm": 0.35958540439605713,
      "learning_rate": 1.9945212217977955e-05,
      "loss": 0.6841,
      "step": 2268
    },
    {
      "epoch": 0.06970171719964366,
      "grad_norm": 0.37720420956611633,
      "learning_rate": 1.9945161687029762e-05,
      "loss": 0.5834,
      "step": 2269
    },
    {
      "epoch": 0.06973243633459282,
      "grad_norm": 0.37763404846191406,
      "learning_rate": 1.9945111132853943e-05,
      "loss": 0.6331,
      "step": 2270
    },
    {
      "epoch": 0.06976315546954198,
      "grad_norm": 0.3571881651878357,
      "learning_rate": 1.9945060555450624e-05,
      "loss": 0.6178,
      "step": 2271
    },
    {
      "epoch": 0.06979387460449114,
      "grad_norm": 0.3198193609714508,
      "learning_rate": 1.9945009954819924e-05,
      "loss": 0.5818,
      "step": 2272
    },
    {
      "epoch": 0.06982459373944029,
      "grad_norm": 0.5529232621192932,
      "learning_rate": 1.9944959330961953e-05,
      "loss": 0.6286,
      "step": 2273
    },
    {
      "epoch": 0.06985531287438945,
      "grad_norm": 0.36903703212738037,
      "learning_rate": 1.994490868387684e-05,
      "loss": 0.6199,
      "step": 2274
    },
    {
      "epoch": 0.06988603200933861,
      "grad_norm": 0.35598793625831604,
      "learning_rate": 1.99448580135647e-05,
      "loss": 0.6665,
      "step": 2275
    },
    {
      "epoch": 0.06991675114428778,
      "grad_norm": 0.3389105796813965,
      "learning_rate": 1.9944807320025644e-05,
      "loss": 0.5844,
      "step": 2276
    },
    {
      "epoch": 0.06994747027923694,
      "grad_norm": 0.5125939249992371,
      "learning_rate": 1.9944756603259798e-05,
      "loss": 0.6452,
      "step": 2277
    },
    {
      "epoch": 0.0699781894141861,
      "grad_norm": 0.3350171446800232,
      "learning_rate": 1.9944705863267278e-05,
      "loss": 0.5952,
      "step": 2278
    },
    {
      "epoch": 0.07000890854913526,
      "grad_norm": 0.3530266284942627,
      "learning_rate": 1.9944655100048204e-05,
      "loss": 0.6312,
      "step": 2279
    },
    {
      "epoch": 0.07003962768408442,
      "grad_norm": 0.34833967685699463,
      "learning_rate": 1.9944604313602693e-05,
      "loss": 0.6096,
      "step": 2280
    },
    {
      "epoch": 0.07007034681903358,
      "grad_norm": 0.34933724999427795,
      "learning_rate": 1.9944553503930865e-05,
      "loss": 0.5973,
      "step": 2281
    },
    {
      "epoch": 0.07010106595398273,
      "grad_norm": 0.3486560881137848,
      "learning_rate": 1.9944502671032837e-05,
      "loss": 0.6277,
      "step": 2282
    },
    {
      "epoch": 0.07013178508893189,
      "grad_norm": 0.34632110595703125,
      "learning_rate": 1.9944451814908726e-05,
      "loss": 0.6534,
      "step": 2283
    },
    {
      "epoch": 0.07016250422388105,
      "grad_norm": 0.3313484489917755,
      "learning_rate": 1.994440093555866e-05,
      "loss": 0.682,
      "step": 2284
    },
    {
      "epoch": 0.07019322335883021,
      "grad_norm": 0.32189467549324036,
      "learning_rate": 1.9944350032982743e-05,
      "loss": 0.6427,
      "step": 2285
    },
    {
      "epoch": 0.07022394249377938,
      "grad_norm": 0.41524431109428406,
      "learning_rate": 1.9944299107181105e-05,
      "loss": 0.5632,
      "step": 2286
    },
    {
      "epoch": 0.07025466162872854,
      "grad_norm": 0.35633614659309387,
      "learning_rate": 1.9944248158153864e-05,
      "loss": 0.6101,
      "step": 2287
    },
    {
      "epoch": 0.0702853807636777,
      "grad_norm": 0.3450487554073334,
      "learning_rate": 1.9944197185901136e-05,
      "loss": 0.6219,
      "step": 2288
    },
    {
      "epoch": 0.07031609989862686,
      "grad_norm": 0.3279600143432617,
      "learning_rate": 1.9944146190423042e-05,
      "loss": 0.5961,
      "step": 2289
    },
    {
      "epoch": 0.07034681903357601,
      "grad_norm": 0.33049142360687256,
      "learning_rate": 1.9944095171719698e-05,
      "loss": 0.6571,
      "step": 2290
    },
    {
      "epoch": 0.07037753816852517,
      "grad_norm": 0.3888467848300934,
      "learning_rate": 1.9944044129791226e-05,
      "loss": 0.5651,
      "step": 2291
    },
    {
      "epoch": 0.07040825730347433,
      "grad_norm": 0.316631555557251,
      "learning_rate": 1.9943993064637747e-05,
      "loss": 0.6095,
      "step": 2292
    },
    {
      "epoch": 0.07043897643842349,
      "grad_norm": 0.3150646388530731,
      "learning_rate": 1.9943941976259373e-05,
      "loss": 0.5393,
      "step": 2293
    },
    {
      "epoch": 0.07046969557337265,
      "grad_norm": 0.3414592146873474,
      "learning_rate": 1.994389086465623e-05,
      "loss": 0.5886,
      "step": 2294
    },
    {
      "epoch": 0.07050041470832182,
      "grad_norm": 0.45348697900772095,
      "learning_rate": 1.9943839729828433e-05,
      "loss": 0.6592,
      "step": 2295
    },
    {
      "epoch": 0.07053113384327098,
      "grad_norm": 0.3132486045360565,
      "learning_rate": 1.994378857177611e-05,
      "loss": 0.662,
      "step": 2296
    },
    {
      "epoch": 0.07056185297822014,
      "grad_norm": 0.3697911202907562,
      "learning_rate": 1.9943737390499368e-05,
      "loss": 0.6458,
      "step": 2297
    },
    {
      "epoch": 0.0705925721131693,
      "grad_norm": 0.317377507686615,
      "learning_rate": 1.9943686185998337e-05,
      "loss": 0.6278,
      "step": 2298
    },
    {
      "epoch": 0.07062329124811845,
      "grad_norm": 0.37609127163887024,
      "learning_rate": 1.994363495827313e-05,
      "loss": 0.5128,
      "step": 2299
    },
    {
      "epoch": 0.07065401038306761,
      "grad_norm": 0.34507983922958374,
      "learning_rate": 1.9943583707323872e-05,
      "loss": 0.6882,
      "step": 2300
    },
    {
      "epoch": 0.07068472951801677,
      "grad_norm": 0.32441240549087524,
      "learning_rate": 1.9943532433150678e-05,
      "loss": 0.6271,
      "step": 2301
    },
    {
      "epoch": 0.07071544865296593,
      "grad_norm": 0.375387966632843,
      "learning_rate": 1.994348113575367e-05,
      "loss": 0.5773,
      "step": 2302
    },
    {
      "epoch": 0.07074616778791509,
      "grad_norm": 0.33356645703315735,
      "learning_rate": 1.9943429815132967e-05,
      "loss": 0.6013,
      "step": 2303
    },
    {
      "epoch": 0.07077688692286425,
      "grad_norm": 0.3719983696937561,
      "learning_rate": 1.9943378471288687e-05,
      "loss": 0.6801,
      "step": 2304
    },
    {
      "epoch": 0.07080760605781342,
      "grad_norm": 0.3404647707939148,
      "learning_rate": 1.9943327104220956e-05,
      "loss": 0.6471,
      "step": 2305
    },
    {
      "epoch": 0.07083832519276258,
      "grad_norm": 0.3903762400150299,
      "learning_rate": 1.994327571392989e-05,
      "loss": 0.6995,
      "step": 2306
    },
    {
      "epoch": 0.07086904432771172,
      "grad_norm": 0.3524881601333618,
      "learning_rate": 1.9943224300415608e-05,
      "loss": 0.5735,
      "step": 2307
    },
    {
      "epoch": 0.07089976346266089,
      "grad_norm": 0.3640892505645752,
      "learning_rate": 1.9943172863678228e-05,
      "loss": 0.6708,
      "step": 2308
    },
    {
      "epoch": 0.07093048259761005,
      "grad_norm": 0.34076252579689026,
      "learning_rate": 1.9943121403717874e-05,
      "loss": 0.6152,
      "step": 2309
    },
    {
      "epoch": 0.07096120173255921,
      "grad_norm": 0.34372198581695557,
      "learning_rate": 1.994306992053467e-05,
      "loss": 0.6042,
      "step": 2310
    },
    {
      "epoch": 0.07099192086750837,
      "grad_norm": 0.4769997000694275,
      "learning_rate": 1.994301841412873e-05,
      "loss": 0.622,
      "step": 2311
    },
    {
      "epoch": 0.07102264000245753,
      "grad_norm": 0.3170176148414612,
      "learning_rate": 1.9942966884500175e-05,
      "loss": 0.5337,
      "step": 2312
    },
    {
      "epoch": 0.0710533591374067,
      "grad_norm": 0.35010942816734314,
      "learning_rate": 1.9942915331649126e-05,
      "loss": 0.6023,
      "step": 2313
    },
    {
      "epoch": 0.07108407827235586,
      "grad_norm": 0.3587970733642578,
      "learning_rate": 1.9942863755575704e-05,
      "loss": 0.5152,
      "step": 2314
    },
    {
      "epoch": 0.07111479740730502,
      "grad_norm": 0.34760305285453796,
      "learning_rate": 1.9942812156280033e-05,
      "loss": 0.5594,
      "step": 2315
    },
    {
      "epoch": 0.07114551654225416,
      "grad_norm": 0.3742259442806244,
      "learning_rate": 1.9942760533762225e-05,
      "loss": 0.5659,
      "step": 2316
    },
    {
      "epoch": 0.07117623567720333,
      "grad_norm": 0.36210277676582336,
      "learning_rate": 1.9942708888022406e-05,
      "loss": 0.6614,
      "step": 2317
    },
    {
      "epoch": 0.07120695481215249,
      "grad_norm": 0.3308568596839905,
      "learning_rate": 1.9942657219060698e-05,
      "loss": 0.6233,
      "step": 2318
    },
    {
      "epoch": 0.07123767394710165,
      "grad_norm": 0.3983585834503174,
      "learning_rate": 1.9942605526877222e-05,
      "loss": 0.5789,
      "step": 2319
    },
    {
      "epoch": 0.07126839308205081,
      "grad_norm": 0.3281286358833313,
      "learning_rate": 1.994255381147209e-05,
      "loss": 0.5178,
      "step": 2320
    },
    {
      "epoch": 0.07129911221699997,
      "grad_norm": 0.3261682987213135,
      "learning_rate": 1.9942502072845433e-05,
      "loss": 0.5969,
      "step": 2321
    },
    {
      "epoch": 0.07132983135194913,
      "grad_norm": 0.3409619927406311,
      "learning_rate": 1.994245031099737e-05,
      "loss": 0.5368,
      "step": 2322
    },
    {
      "epoch": 0.0713605504868983,
      "grad_norm": 0.4014226198196411,
      "learning_rate": 1.9942398525928017e-05,
      "loss": 0.6459,
      "step": 2323
    },
    {
      "epoch": 0.07139126962184744,
      "grad_norm": 0.33894264698028564,
      "learning_rate": 1.9942346717637497e-05,
      "loss": 0.6673,
      "step": 2324
    },
    {
      "epoch": 0.0714219887567966,
      "grad_norm": 0.343667596578598,
      "learning_rate": 1.9942294886125934e-05,
      "loss": 0.5949,
      "step": 2325
    },
    {
      "epoch": 0.07145270789174576,
      "grad_norm": 0.3785068690776825,
      "learning_rate": 1.9942243031393444e-05,
      "loss": 0.6453,
      "step": 2326
    },
    {
      "epoch": 0.07148342702669493,
      "grad_norm": 0.35941192507743835,
      "learning_rate": 1.9942191153440156e-05,
      "loss": 0.6209,
      "step": 2327
    },
    {
      "epoch": 0.07151414616164409,
      "grad_norm": 0.35576051473617554,
      "learning_rate": 1.9942139252266185e-05,
      "loss": 0.5594,
      "step": 2328
    },
    {
      "epoch": 0.07154486529659325,
      "grad_norm": 0.35480037331581116,
      "learning_rate": 1.994208732787165e-05,
      "loss": 0.6243,
      "step": 2329
    },
    {
      "epoch": 0.07157558443154241,
      "grad_norm": 0.3774089813232422,
      "learning_rate": 1.9942035380256677e-05,
      "loss": 0.5906,
      "step": 2330
    },
    {
      "epoch": 0.07160630356649157,
      "grad_norm": 0.33675557374954224,
      "learning_rate": 1.9941983409421385e-05,
      "loss": 0.6886,
      "step": 2331
    },
    {
      "epoch": 0.07163702270144073,
      "grad_norm": 0.3092780113220215,
      "learning_rate": 1.9941931415365897e-05,
      "loss": 0.5213,
      "step": 2332
    },
    {
      "epoch": 0.07166774183638988,
      "grad_norm": 0.3463011384010315,
      "learning_rate": 1.9941879398090336e-05,
      "loss": 0.6377,
      "step": 2333
    },
    {
      "epoch": 0.07169846097133904,
      "grad_norm": 0.3536158800125122,
      "learning_rate": 1.9941827357594823e-05,
      "loss": 0.6058,
      "step": 2334
    },
    {
      "epoch": 0.0717291801062882,
      "grad_norm": 0.3352678418159485,
      "learning_rate": 1.994177529387947e-05,
      "loss": 0.6406,
      "step": 2335
    },
    {
      "epoch": 0.07175989924123737,
      "grad_norm": 0.3921270966529846,
      "learning_rate": 1.9941723206944415e-05,
      "loss": 0.5709,
      "step": 2336
    },
    {
      "epoch": 0.07179061837618653,
      "grad_norm": 0.36226755380630493,
      "learning_rate": 1.9941671096789767e-05,
      "loss": 0.6557,
      "step": 2337
    },
    {
      "epoch": 0.07182133751113569,
      "grad_norm": 0.3200473189353943,
      "learning_rate": 1.9941618963415652e-05,
      "loss": 0.6685,
      "step": 2338
    },
    {
      "epoch": 0.07185205664608485,
      "grad_norm": 0.32420361042022705,
      "learning_rate": 1.9941566806822195e-05,
      "loss": 0.5278,
      "step": 2339
    },
    {
      "epoch": 0.07188277578103401,
      "grad_norm": 0.4029267728328705,
      "learning_rate": 1.994151462700951e-05,
      "loss": 0.651,
      "step": 2340
    },
    {
      "epoch": 0.07191349491598317,
      "grad_norm": 0.3506752550601959,
      "learning_rate": 1.9941462423977725e-05,
      "loss": 0.5895,
      "step": 2341
    },
    {
      "epoch": 0.07194421405093232,
      "grad_norm": 0.3415878713130951,
      "learning_rate": 1.994141019772696e-05,
      "loss": 0.627,
      "step": 2342
    },
    {
      "epoch": 0.07197493318588148,
      "grad_norm": 0.31377658247947693,
      "learning_rate": 1.9941357948257336e-05,
      "loss": 0.5209,
      "step": 2343
    },
    {
      "epoch": 0.07200565232083064,
      "grad_norm": 0.4006168842315674,
      "learning_rate": 1.9941305675568978e-05,
      "loss": 0.627,
      "step": 2344
    },
    {
      "epoch": 0.0720363714557798,
      "grad_norm": 0.36485832929611206,
      "learning_rate": 1.9941253379662003e-05,
      "loss": 0.5889,
      "step": 2345
    },
    {
      "epoch": 0.07206709059072897,
      "grad_norm": 0.35250672698020935,
      "learning_rate": 1.994120106053654e-05,
      "loss": 0.5875,
      "step": 2346
    },
    {
      "epoch": 0.07209780972567813,
      "grad_norm": 0.33126139640808105,
      "learning_rate": 1.994114871819271e-05,
      "loss": 0.6719,
      "step": 2347
    },
    {
      "epoch": 0.07212852886062729,
      "grad_norm": 0.3363138437271118,
      "learning_rate": 1.9941096352630628e-05,
      "loss": 0.5875,
      "step": 2348
    },
    {
      "epoch": 0.07215924799557645,
      "grad_norm": 0.4345424473285675,
      "learning_rate": 1.9941043963850424e-05,
      "loss": 0.6054,
      "step": 2349
    },
    {
      "epoch": 0.0721899671305256,
      "grad_norm": 0.3654957711696625,
      "learning_rate": 1.9940991551852217e-05,
      "loss": 0.6151,
      "step": 2350
    },
    {
      "epoch": 0.07222068626547476,
      "grad_norm": 0.355685830116272,
      "learning_rate": 1.9940939116636126e-05,
      "loss": 0.6425,
      "step": 2351
    },
    {
      "epoch": 0.07225140540042392,
      "grad_norm": 0.35184353590011597,
      "learning_rate": 1.9940886658202282e-05,
      "loss": 0.596,
      "step": 2352
    },
    {
      "epoch": 0.07228212453537308,
      "grad_norm": 0.6204710006713867,
      "learning_rate": 1.9940834176550804e-05,
      "loss": 0.5397,
      "step": 2353
    },
    {
      "epoch": 0.07231284367032224,
      "grad_norm": 0.36159420013427734,
      "learning_rate": 1.9940781671681808e-05,
      "loss": 0.6805,
      "step": 2354
    },
    {
      "epoch": 0.0723435628052714,
      "grad_norm": 0.34708112478256226,
      "learning_rate": 1.9940729143595425e-05,
      "loss": 0.6081,
      "step": 2355
    },
    {
      "epoch": 0.07237428194022057,
      "grad_norm": 0.3197517693042755,
      "learning_rate": 1.9940676592291778e-05,
      "loss": 0.5547,
      "step": 2356
    },
    {
      "epoch": 0.07240500107516973,
      "grad_norm": 0.3518645763397217,
      "learning_rate": 1.9940624017770984e-05,
      "loss": 0.6578,
      "step": 2357
    },
    {
      "epoch": 0.07243572021011889,
      "grad_norm": 0.35610949993133545,
      "learning_rate": 1.9940571420033167e-05,
      "loss": 0.651,
      "step": 2358
    },
    {
      "epoch": 0.07246643934506804,
      "grad_norm": 0.4015142619609833,
      "learning_rate": 1.994051879907845e-05,
      "loss": 0.6297,
      "step": 2359
    },
    {
      "epoch": 0.0724971584800172,
      "grad_norm": 0.3155009150505066,
      "learning_rate": 1.9940466154906965e-05,
      "loss": 0.5167,
      "step": 2360
    },
    {
      "epoch": 0.07252787761496636,
      "grad_norm": 0.3717946410179138,
      "learning_rate": 1.994041348751882e-05,
      "loss": 0.6334,
      "step": 2361
    },
    {
      "epoch": 0.07255859674991552,
      "grad_norm": 0.3706805408000946,
      "learning_rate": 1.9940360796914144e-05,
      "loss": 0.6089,
      "step": 2362
    },
    {
      "epoch": 0.07258931588486468,
      "grad_norm": 0.3583068251609802,
      "learning_rate": 1.9940308083093066e-05,
      "loss": 0.6208,
      "step": 2363
    },
    {
      "epoch": 0.07262003501981384,
      "grad_norm": 0.3196122348308563,
      "learning_rate": 1.99402553460557e-05,
      "loss": 0.5309,
      "step": 2364
    },
    {
      "epoch": 0.072650754154763,
      "grad_norm": 0.3746194541454315,
      "learning_rate": 1.9940202585802177e-05,
      "loss": 0.6055,
      "step": 2365
    },
    {
      "epoch": 0.07268147328971217,
      "grad_norm": 0.37152329087257385,
      "learning_rate": 1.9940149802332613e-05,
      "loss": 0.6555,
      "step": 2366
    },
    {
      "epoch": 0.07271219242466131,
      "grad_norm": 0.3165590465068817,
      "learning_rate": 1.994009699564714e-05,
      "loss": 0.6072,
      "step": 2367
    },
    {
      "epoch": 0.07274291155961048,
      "grad_norm": 0.3682546615600586,
      "learning_rate": 1.994004416574587e-05,
      "loss": 0.621,
      "step": 2368
    },
    {
      "epoch": 0.07277363069455964,
      "grad_norm": 0.334236741065979,
      "learning_rate": 1.993999131262894e-05,
      "loss": 0.6649,
      "step": 2369
    },
    {
      "epoch": 0.0728043498295088,
      "grad_norm": 0.31573131680488586,
      "learning_rate": 1.993993843629646e-05,
      "loss": 0.5988,
      "step": 2370
    },
    {
      "epoch": 0.07283506896445796,
      "grad_norm": 0.43167757987976074,
      "learning_rate": 1.993988553674856e-05,
      "loss": 0.6602,
      "step": 2371
    },
    {
      "epoch": 0.07286578809940712,
      "grad_norm": 0.3301078975200653,
      "learning_rate": 1.9939832613985363e-05,
      "loss": 0.7288,
      "step": 2372
    },
    {
      "epoch": 0.07289650723435628,
      "grad_norm": 0.3498932719230652,
      "learning_rate": 1.9939779668007e-05,
      "loss": 0.6893,
      "step": 2373
    },
    {
      "epoch": 0.07292722636930545,
      "grad_norm": 0.3463471531867981,
      "learning_rate": 1.993972669881358e-05,
      "loss": 0.622,
      "step": 2374
    },
    {
      "epoch": 0.0729579455042546,
      "grad_norm": 0.514157772064209,
      "learning_rate": 1.9939673706405235e-05,
      "loss": 0.5697,
      "step": 2375
    },
    {
      "epoch": 0.07298866463920375,
      "grad_norm": 0.32319241762161255,
      "learning_rate": 1.993962069078209e-05,
      "loss": 0.5567,
      "step": 2376
    },
    {
      "epoch": 0.07301938377415292,
      "grad_norm": 0.3460410535335541,
      "learning_rate": 1.9939567651944266e-05,
      "loss": 0.5902,
      "step": 2377
    },
    {
      "epoch": 0.07305010290910208,
      "grad_norm": 0.36054372787475586,
      "learning_rate": 1.9939514589891887e-05,
      "loss": 0.6386,
      "step": 2378
    },
    {
      "epoch": 0.07308082204405124,
      "grad_norm": 0.3617940843105316,
      "learning_rate": 1.9939461504625073e-05,
      "loss": 0.6332,
      "step": 2379
    },
    {
      "epoch": 0.0731115411790004,
      "grad_norm": 0.3256889581680298,
      "learning_rate": 1.993940839614396e-05,
      "loss": 0.5449,
      "step": 2380
    },
    {
      "epoch": 0.07314226031394956,
      "grad_norm": 0.36186841130256653,
      "learning_rate": 1.993935526444866e-05,
      "loss": 0.6813,
      "step": 2381
    },
    {
      "epoch": 0.07317297944889872,
      "grad_norm": 0.4319345951080322,
      "learning_rate": 1.9939302109539303e-05,
      "loss": 0.6801,
      "step": 2382
    },
    {
      "epoch": 0.07320369858384788,
      "grad_norm": 0.32260259985923767,
      "learning_rate": 1.9939248931416014e-05,
      "loss": 0.5786,
      "step": 2383
    },
    {
      "epoch": 0.07323441771879703,
      "grad_norm": 0.33656251430511475,
      "learning_rate": 1.993919573007891e-05,
      "loss": 0.7092,
      "step": 2384
    },
    {
      "epoch": 0.0732651368537462,
      "grad_norm": 0.3366798460483551,
      "learning_rate": 1.9939142505528126e-05,
      "loss": 0.5323,
      "step": 2385
    },
    {
      "epoch": 0.07329585598869535,
      "grad_norm": 0.3359346389770508,
      "learning_rate": 1.9939089257763778e-05,
      "loss": 0.664,
      "step": 2386
    },
    {
      "epoch": 0.07332657512364452,
      "grad_norm": 0.8740454316139221,
      "learning_rate": 1.9939035986785993e-05,
      "loss": 0.6494,
      "step": 2387
    },
    {
      "epoch": 0.07335729425859368,
      "grad_norm": 0.3123961389064789,
      "learning_rate": 1.993898269259489e-05,
      "loss": 0.6727,
      "step": 2388
    },
    {
      "epoch": 0.07338801339354284,
      "grad_norm": 0.3513924181461334,
      "learning_rate": 1.9938929375190607e-05,
      "loss": 0.6359,
      "step": 2389
    },
    {
      "epoch": 0.073418732528492,
      "grad_norm": 0.34043487906455994,
      "learning_rate": 1.9938876034573257e-05,
      "loss": 0.6134,
      "step": 2390
    },
    {
      "epoch": 0.07344945166344116,
      "grad_norm": 0.3346777856349945,
      "learning_rate": 1.9938822670742968e-05,
      "loss": 0.6867,
      "step": 2391
    },
    {
      "epoch": 0.07348017079839032,
      "grad_norm": 0.3113040328025818,
      "learning_rate": 1.9938769283699867e-05,
      "loss": 0.652,
      "step": 2392
    },
    {
      "epoch": 0.07351088993333947,
      "grad_norm": 0.3436412811279297,
      "learning_rate": 1.9938715873444072e-05,
      "loss": 0.6135,
      "step": 2393
    },
    {
      "epoch": 0.07354160906828863,
      "grad_norm": 0.3263019621372223,
      "learning_rate": 1.9938662439975715e-05,
      "loss": 0.6095,
      "step": 2394
    },
    {
      "epoch": 0.0735723282032378,
      "grad_norm": 0.3352179229259491,
      "learning_rate": 1.9938608983294915e-05,
      "loss": 0.575,
      "step": 2395
    },
    {
      "epoch": 0.07360304733818696,
      "grad_norm": 0.3300243020057678,
      "learning_rate": 1.99385555034018e-05,
      "loss": 0.6393,
      "step": 2396
    },
    {
      "epoch": 0.07363376647313612,
      "grad_norm": 0.3261314332485199,
      "learning_rate": 1.9938502000296497e-05,
      "loss": 0.5757,
      "step": 2397
    },
    {
      "epoch": 0.07366448560808528,
      "grad_norm": 0.3490402400493622,
      "learning_rate": 1.9938448473979126e-05,
      "loss": 0.5504,
      "step": 2398
    },
    {
      "epoch": 0.07369520474303444,
      "grad_norm": 0.3098176419734955,
      "learning_rate": 1.9938394924449816e-05,
      "loss": 0.5768,
      "step": 2399
    },
    {
      "epoch": 0.0737259238779836,
      "grad_norm": 0.34357723593711853,
      "learning_rate": 1.993834135170869e-05,
      "loss": 0.6161,
      "step": 2400
    },
    {
      "epoch": 0.07375664301293276,
      "grad_norm": 0.31747958064079285,
      "learning_rate": 1.9938287755755873e-05,
      "loss": 0.6478,
      "step": 2401
    },
    {
      "epoch": 0.07378736214788191,
      "grad_norm": 0.3904709815979004,
      "learning_rate": 1.993823413659149e-05,
      "loss": 0.6443,
      "step": 2402
    },
    {
      "epoch": 0.07381808128283107,
      "grad_norm": 0.3252991735935211,
      "learning_rate": 1.993818049421567e-05,
      "loss": 0.6151,
      "step": 2403
    },
    {
      "epoch": 0.07384880041778023,
      "grad_norm": 0.33654919266700745,
      "learning_rate": 1.9938126828628537e-05,
      "loss": 0.6489,
      "step": 2404
    },
    {
      "epoch": 0.0738795195527294,
      "grad_norm": 0.38823971152305603,
      "learning_rate": 1.993807313983021e-05,
      "loss": 0.5497,
      "step": 2405
    },
    {
      "epoch": 0.07391023868767856,
      "grad_norm": 0.32952508330345154,
      "learning_rate": 1.9938019427820824e-05,
      "loss": 0.6854,
      "step": 2406
    },
    {
      "epoch": 0.07394095782262772,
      "grad_norm": 0.5573270320892334,
      "learning_rate": 1.9937965692600496e-05,
      "loss": 0.5863,
      "step": 2407
    },
    {
      "epoch": 0.07397167695757688,
      "grad_norm": 0.3821525573730469,
      "learning_rate": 1.9937911934169355e-05,
      "loss": 0.6139,
      "step": 2408
    },
    {
      "epoch": 0.07400239609252604,
      "grad_norm": 0.3163740932941437,
      "learning_rate": 1.9937858152527526e-05,
      "loss": 0.6567,
      "step": 2409
    },
    {
      "epoch": 0.07403311522747519,
      "grad_norm": 0.3503473997116089,
      "learning_rate": 1.9937804347675137e-05,
      "loss": 0.6365,
      "step": 2410
    },
    {
      "epoch": 0.07406383436242435,
      "grad_norm": 0.31511732935905457,
      "learning_rate": 1.993775051961231e-05,
      "loss": 0.6185,
      "step": 2411
    },
    {
      "epoch": 0.07409455349737351,
      "grad_norm": 0.3281126618385315,
      "learning_rate": 1.9937696668339176e-05,
      "loss": 0.6693,
      "step": 2412
    },
    {
      "epoch": 0.07412527263232267,
      "grad_norm": 0.8676486611366272,
      "learning_rate": 1.9937642793855855e-05,
      "loss": 0.6166,
      "step": 2413
    },
    {
      "epoch": 0.07415599176727183,
      "grad_norm": 0.3348962068557739,
      "learning_rate": 1.9937588896162475e-05,
      "loss": 0.633,
      "step": 2414
    },
    {
      "epoch": 0.074186710902221,
      "grad_norm": 0.3614314794540405,
      "learning_rate": 1.9937534975259163e-05,
      "loss": 0.6006,
      "step": 2415
    },
    {
      "epoch": 0.07421743003717016,
      "grad_norm": 0.32203245162963867,
      "learning_rate": 1.9937481031146043e-05,
      "loss": 0.5114,
      "step": 2416
    },
    {
      "epoch": 0.07424814917211932,
      "grad_norm": 0.3887616991996765,
      "learning_rate": 1.9937427063823245e-05,
      "loss": 0.6093,
      "step": 2417
    },
    {
      "epoch": 0.07427886830706848,
      "grad_norm": 0.32728227972984314,
      "learning_rate": 1.9937373073290887e-05,
      "loss": 0.5381,
      "step": 2418
    },
    {
      "epoch": 0.07430958744201763,
      "grad_norm": 0.3311820328235626,
      "learning_rate": 1.99373190595491e-05,
      "loss": 0.6365,
      "step": 2419
    },
    {
      "epoch": 0.07434030657696679,
      "grad_norm": 0.3788667619228363,
      "learning_rate": 1.9937265022598016e-05,
      "loss": 0.6056,
      "step": 2420
    },
    {
      "epoch": 0.07437102571191595,
      "grad_norm": 0.3504379391670227,
      "learning_rate": 1.9937210962437754e-05,
      "loss": 0.6617,
      "step": 2421
    },
    {
      "epoch": 0.07440174484686511,
      "grad_norm": 0.34318187832832336,
      "learning_rate": 1.993715687906844e-05,
      "loss": 0.6231,
      "step": 2422
    },
    {
      "epoch": 0.07443246398181427,
      "grad_norm": 0.38719552755355835,
      "learning_rate": 1.9937102772490204e-05,
      "loss": 0.6133,
      "step": 2423
    },
    {
      "epoch": 0.07446318311676343,
      "grad_norm": 0.37958914041519165,
      "learning_rate": 1.993704864270317e-05,
      "loss": 0.6737,
      "step": 2424
    },
    {
      "epoch": 0.0744939022517126,
      "grad_norm": 0.33352354168891907,
      "learning_rate": 1.9936994489707463e-05,
      "loss": 0.5844,
      "step": 2425
    },
    {
      "epoch": 0.07452462138666176,
      "grad_norm": 0.36835914850234985,
      "learning_rate": 1.9936940313503213e-05,
      "loss": 0.6407,
      "step": 2426
    },
    {
      "epoch": 0.0745553405216109,
      "grad_norm": 0.3791012465953827,
      "learning_rate": 1.9936886114090544e-05,
      "loss": 0.4855,
      "step": 2427
    },
    {
      "epoch": 0.07458605965656007,
      "grad_norm": 0.3943319618701935,
      "learning_rate": 1.9936831891469583e-05,
      "loss": 0.6123,
      "step": 2428
    },
    {
      "epoch": 0.07461677879150923,
      "grad_norm": 0.3538697063922882,
      "learning_rate": 1.9936777645640458e-05,
      "loss": 0.6664,
      "step": 2429
    },
    {
      "epoch": 0.07464749792645839,
      "grad_norm": 0.32536080479621887,
      "learning_rate": 1.9936723376603298e-05,
      "loss": 0.649,
      "step": 2430
    },
    {
      "epoch": 0.07467821706140755,
      "grad_norm": 0.4689594805240631,
      "learning_rate": 1.993666908435822e-05,
      "loss": 0.6474,
      "step": 2431
    },
    {
      "epoch": 0.07470893619635671,
      "grad_norm": 0.3708209693431854,
      "learning_rate": 1.9936614768905362e-05,
      "loss": 0.6121,
      "step": 2432
    },
    {
      "epoch": 0.07473965533130587,
      "grad_norm": 0.33430150151252747,
      "learning_rate": 1.9936560430244848e-05,
      "loss": 0.5542,
      "step": 2433
    },
    {
      "epoch": 0.07477037446625504,
      "grad_norm": 0.32218194007873535,
      "learning_rate": 1.9936506068376797e-05,
      "loss": 0.6173,
      "step": 2434
    },
    {
      "epoch": 0.0748010936012042,
      "grad_norm": 0.3490361273288727,
      "learning_rate": 1.9936451683301347e-05,
      "loss": 0.6056,
      "step": 2435
    },
    {
      "epoch": 0.07483181273615334,
      "grad_norm": 0.31083083152770996,
      "learning_rate": 1.9936397275018618e-05,
      "loss": 0.6352,
      "step": 2436
    },
    {
      "epoch": 0.0748625318711025,
      "grad_norm": 0.3655105531215668,
      "learning_rate": 1.993634284352874e-05,
      "loss": 0.5831,
      "step": 2437
    },
    {
      "epoch": 0.07489325100605167,
      "grad_norm": 0.37039968371391296,
      "learning_rate": 1.9936288388831838e-05,
      "loss": 0.6676,
      "step": 2438
    },
    {
      "epoch": 0.07492397014100083,
      "grad_norm": 0.3468782901763916,
      "learning_rate": 1.993623391092804e-05,
      "loss": 0.5885,
      "step": 2439
    },
    {
      "epoch": 0.07495468927594999,
      "grad_norm": 0.37939924001693726,
      "learning_rate": 1.9936179409817477e-05,
      "loss": 0.6516,
      "step": 2440
    },
    {
      "epoch": 0.07498540841089915,
      "grad_norm": 0.36011841893196106,
      "learning_rate": 1.9936124885500274e-05,
      "loss": 0.5899,
      "step": 2441
    },
    {
      "epoch": 0.07501612754584831,
      "grad_norm": 0.37312963604927063,
      "learning_rate": 1.9936070337976553e-05,
      "loss": 0.594,
      "step": 2442
    },
    {
      "epoch": 0.07504684668079747,
      "grad_norm": 0.31900861859321594,
      "learning_rate": 1.9936015767246446e-05,
      "loss": 0.5896,
      "step": 2443
    },
    {
      "epoch": 0.07507756581574662,
      "grad_norm": 0.32950448989868164,
      "learning_rate": 1.9935961173310083e-05,
      "loss": 0.5911,
      "step": 2444
    },
    {
      "epoch": 0.07510828495069578,
      "grad_norm": 0.30742791295051575,
      "learning_rate": 1.9935906556167586e-05,
      "loss": 0.5484,
      "step": 2445
    },
    {
      "epoch": 0.07513900408564494,
      "grad_norm": 0.36050426959991455,
      "learning_rate": 1.993585191581909e-05,
      "loss": 0.6279,
      "step": 2446
    },
    {
      "epoch": 0.0751697232205941,
      "grad_norm": 0.3534471094608307,
      "learning_rate": 1.9935797252264716e-05,
      "loss": 0.5827,
      "step": 2447
    },
    {
      "epoch": 0.07520044235554327,
      "grad_norm": 0.33655068278312683,
      "learning_rate": 1.993574256550459e-05,
      "loss": 0.5961,
      "step": 2448
    },
    {
      "epoch": 0.07523116149049243,
      "grad_norm": 0.35631951689720154,
      "learning_rate": 1.9935687855538846e-05,
      "loss": 0.5183,
      "step": 2449
    },
    {
      "epoch": 0.07526188062544159,
      "grad_norm": 0.3675488531589508,
      "learning_rate": 1.9935633122367607e-05,
      "loss": 0.6121,
      "step": 2450
    },
    {
      "epoch": 0.07529259976039075,
      "grad_norm": 0.35517418384552,
      "learning_rate": 1.9935578365991006e-05,
      "loss": 0.6596,
      "step": 2451
    },
    {
      "epoch": 0.07532331889533991,
      "grad_norm": 0.3383217453956604,
      "learning_rate": 1.993552358640917e-05,
      "loss": 0.5894,
      "step": 2452
    },
    {
      "epoch": 0.07535403803028906,
      "grad_norm": 0.341969758272171,
      "learning_rate": 1.993546878362222e-05,
      "loss": 0.5671,
      "step": 2453
    },
    {
      "epoch": 0.07538475716523822,
      "grad_norm": 0.4088347256183624,
      "learning_rate": 1.9935413957630288e-05,
      "loss": 0.6735,
      "step": 2454
    },
    {
      "epoch": 0.07541547630018738,
      "grad_norm": 0.36870071291923523,
      "learning_rate": 1.993535910843351e-05,
      "loss": 0.6339,
      "step": 2455
    },
    {
      "epoch": 0.07544619543513655,
      "grad_norm": 0.32350388169288635,
      "learning_rate": 1.9935304236032e-05,
      "loss": 0.5366,
      "step": 2456
    },
    {
      "epoch": 0.0754769145700857,
      "grad_norm": 0.3748690187931061,
      "learning_rate": 1.993524934042589e-05,
      "loss": 0.6513,
      "step": 2457
    },
    {
      "epoch": 0.07550763370503487,
      "grad_norm": 0.32318809628486633,
      "learning_rate": 1.993519442161532e-05,
      "loss": 0.6239,
      "step": 2458
    },
    {
      "epoch": 0.07553835283998403,
      "grad_norm": 0.29844483733177185,
      "learning_rate": 1.9935139479600404e-05,
      "loss": 0.628,
      "step": 2459
    },
    {
      "epoch": 0.07556907197493319,
      "grad_norm": 0.3190557658672333,
      "learning_rate": 1.9935084514381277e-05,
      "loss": 0.6204,
      "step": 2460
    },
    {
      "epoch": 0.07559979110988234,
      "grad_norm": 0.3238297402858734,
      "learning_rate": 1.993502952595807e-05,
      "loss": 0.5993,
      "step": 2461
    },
    {
      "epoch": 0.0756305102448315,
      "grad_norm": 0.3271649479866028,
      "learning_rate": 1.99349745143309e-05,
      "loss": 0.6096,
      "step": 2462
    },
    {
      "epoch": 0.07566122937978066,
      "grad_norm": 0.34880128502845764,
      "learning_rate": 1.9934919479499913e-05,
      "loss": 0.5984,
      "step": 2463
    },
    {
      "epoch": 0.07569194851472982,
      "grad_norm": 0.37039124965667725,
      "learning_rate": 1.993486442146522e-05,
      "loss": 0.5636,
      "step": 2464
    },
    {
      "epoch": 0.07572266764967898,
      "grad_norm": 0.33419129252433777,
      "learning_rate": 1.993480934022696e-05,
      "loss": 0.6413,
      "step": 2465
    },
    {
      "epoch": 0.07575338678462815,
      "grad_norm": 0.3515890836715698,
      "learning_rate": 1.993475423578526e-05,
      "loss": 0.6676,
      "step": 2466
    },
    {
      "epoch": 0.07578410591957731,
      "grad_norm": 0.32323887944221497,
      "learning_rate": 1.9934699108140244e-05,
      "loss": 0.6137,
      "step": 2467
    },
    {
      "epoch": 0.07581482505452647,
      "grad_norm": 0.3376542329788208,
      "learning_rate": 1.993464395729205e-05,
      "loss": 0.5625,
      "step": 2468
    },
    {
      "epoch": 0.07584554418947563,
      "grad_norm": 0.3449452221393585,
      "learning_rate": 1.9934588783240796e-05,
      "loss": 0.5811,
      "step": 2469
    },
    {
      "epoch": 0.07587626332442478,
      "grad_norm": 0.3311859369277954,
      "learning_rate": 1.9934533585986623e-05,
      "loss": 0.6436,
      "step": 2470
    },
    {
      "epoch": 0.07590698245937394,
      "grad_norm": 0.4326750636100769,
      "learning_rate": 1.9934478365529645e-05,
      "loss": 0.6297,
      "step": 2471
    },
    {
      "epoch": 0.0759377015943231,
      "grad_norm": 0.3386635184288025,
      "learning_rate": 1.9934423121870002e-05,
      "loss": 0.5267,
      "step": 2472
    },
    {
      "epoch": 0.07596842072927226,
      "grad_norm": 0.435200035572052,
      "learning_rate": 1.993436785500782e-05,
      "loss": 0.65,
      "step": 2473
    },
    {
      "epoch": 0.07599913986422142,
      "grad_norm": 0.37801307439804077,
      "learning_rate": 1.993431256494323e-05,
      "loss": 0.5121,
      "step": 2474
    },
    {
      "epoch": 0.07602985899917059,
      "grad_norm": 0.32581260800361633,
      "learning_rate": 1.9934257251676357e-05,
      "loss": 0.599,
      "step": 2475
    },
    {
      "epoch": 0.07606057813411975,
      "grad_norm": 0.34863656759262085,
      "learning_rate": 1.993420191520733e-05,
      "loss": 0.6612,
      "step": 2476
    },
    {
      "epoch": 0.07609129726906891,
      "grad_norm": 0.37314242124557495,
      "learning_rate": 1.9934146555536284e-05,
      "loss": 0.6298,
      "step": 2477
    },
    {
      "epoch": 0.07612201640401807,
      "grad_norm": 0.3531608581542969,
      "learning_rate": 1.9934091172663345e-05,
      "loss": 0.6869,
      "step": 2478
    },
    {
      "epoch": 0.07615273553896722,
      "grad_norm": 0.32910585403442383,
      "learning_rate": 1.993403576658864e-05,
      "loss": 0.5595,
      "step": 2479
    },
    {
      "epoch": 0.07618345467391638,
      "grad_norm": 0.45403623580932617,
      "learning_rate": 1.9933980337312305e-05,
      "loss": 0.6081,
      "step": 2480
    },
    {
      "epoch": 0.07621417380886554,
      "grad_norm": 0.37874236702919006,
      "learning_rate": 1.9933924884834464e-05,
      "loss": 0.5567,
      "step": 2481
    },
    {
      "epoch": 0.0762448929438147,
      "grad_norm": 0.37998706102371216,
      "learning_rate": 1.9933869409155244e-05,
      "loss": 0.6869,
      "step": 2482
    },
    {
      "epoch": 0.07627561207876386,
      "grad_norm": 0.3363747298717499,
      "learning_rate": 1.993381391027478e-05,
      "loss": 0.6606,
      "step": 2483
    },
    {
      "epoch": 0.07630633121371302,
      "grad_norm": 0.35554298758506775,
      "learning_rate": 1.99337583881932e-05,
      "loss": 0.6818,
      "step": 2484
    },
    {
      "epoch": 0.07633705034866219,
      "grad_norm": 0.4194576144218445,
      "learning_rate": 1.9933702842910635e-05,
      "loss": 0.6591,
      "step": 2485
    },
    {
      "epoch": 0.07636776948361135,
      "grad_norm": 0.4392673969268799,
      "learning_rate": 1.993364727442721e-05,
      "loss": 0.6481,
      "step": 2486
    },
    {
      "epoch": 0.0763984886185605,
      "grad_norm": 0.34611082077026367,
      "learning_rate": 1.993359168274306e-05,
      "loss": 0.5975,
      "step": 2487
    },
    {
      "epoch": 0.07642920775350966,
      "grad_norm": 0.3356529772281647,
      "learning_rate": 1.9933536067858313e-05,
      "loss": 0.6244,
      "step": 2488
    },
    {
      "epoch": 0.07645992688845882,
      "grad_norm": 0.3184433579444885,
      "learning_rate": 1.99334804297731e-05,
      "loss": 0.6252,
      "step": 2489
    },
    {
      "epoch": 0.07649064602340798,
      "grad_norm": 0.3446669578552246,
      "learning_rate": 1.993342476848755e-05,
      "loss": 0.6664,
      "step": 2490
    },
    {
      "epoch": 0.07652136515835714,
      "grad_norm": 0.42689579725265503,
      "learning_rate": 1.993336908400179e-05,
      "loss": 0.7492,
      "step": 2491
    },
    {
      "epoch": 0.0765520842933063,
      "grad_norm": 0.35681504011154175,
      "learning_rate": 1.9933313376315952e-05,
      "loss": 0.5803,
      "step": 2492
    },
    {
      "epoch": 0.07658280342825546,
      "grad_norm": 0.37526610493659973,
      "learning_rate": 1.993325764543017e-05,
      "loss": 0.6491,
      "step": 2493
    },
    {
      "epoch": 0.07661352256320463,
      "grad_norm": 0.3606531023979187,
      "learning_rate": 1.9933201891344568e-05,
      "loss": 0.5643,
      "step": 2494
    },
    {
      "epoch": 0.07664424169815379,
      "grad_norm": 0.2922174334526062,
      "learning_rate": 1.9933146114059285e-05,
      "loss": 0.6075,
      "step": 2495
    },
    {
      "epoch": 0.07667496083310293,
      "grad_norm": 0.32933056354522705,
      "learning_rate": 1.993309031357444e-05,
      "loss": 0.6708,
      "step": 2496
    },
    {
      "epoch": 0.0767056799680521,
      "grad_norm": 0.3272293508052826,
      "learning_rate": 1.993303448989017e-05,
      "loss": 0.563,
      "step": 2497
    },
    {
      "epoch": 0.07673639910300126,
      "grad_norm": 0.357683002948761,
      "learning_rate": 1.9932978643006604e-05,
      "loss": 0.5923,
      "step": 2498
    },
    {
      "epoch": 0.07676711823795042,
      "grad_norm": 0.33317482471466064,
      "learning_rate": 1.9932922772923873e-05,
      "loss": 0.6636,
      "step": 2499
    },
    {
      "epoch": 0.07679783737289958,
      "grad_norm": 0.34001195430755615,
      "learning_rate": 1.9932866879642107e-05,
      "loss": 0.6026,
      "step": 2500
    },
    {
      "epoch": 0.07682855650784874,
      "grad_norm": 0.3284319043159485,
      "learning_rate": 1.9932810963161436e-05,
      "loss": 0.5248,
      "step": 2501
    },
    {
      "epoch": 0.0768592756427979,
      "grad_norm": 0.349875271320343,
      "learning_rate": 1.9932755023481993e-05,
      "loss": 0.5863,
      "step": 2502
    },
    {
      "epoch": 0.07688999477774706,
      "grad_norm": 0.3613593280315399,
      "learning_rate": 1.9932699060603907e-05,
      "loss": 0.6434,
      "step": 2503
    },
    {
      "epoch": 0.07692071391269621,
      "grad_norm": 0.3686390221118927,
      "learning_rate": 1.993264307452731e-05,
      "loss": 0.5803,
      "step": 2504
    },
    {
      "epoch": 0.07695143304764537,
      "grad_norm": 0.3269595503807068,
      "learning_rate": 1.9932587065252326e-05,
      "loss": 0.5658,
      "step": 2505
    },
    {
      "epoch": 0.07698215218259453,
      "grad_norm": 0.3564971387386322,
      "learning_rate": 1.9932531032779095e-05,
      "loss": 0.6164,
      "step": 2506
    },
    {
      "epoch": 0.0770128713175437,
      "grad_norm": 0.3069271147251129,
      "learning_rate": 1.9932474977107746e-05,
      "loss": 0.5788,
      "step": 2507
    },
    {
      "epoch": 0.07704359045249286,
      "grad_norm": 0.30893707275390625,
      "learning_rate": 1.9932418898238405e-05,
      "loss": 0.5849,
      "step": 2508
    },
    {
      "epoch": 0.07707430958744202,
      "grad_norm": 0.29526185989379883,
      "learning_rate": 1.9932362796171206e-05,
      "loss": 0.474,
      "step": 2509
    },
    {
      "epoch": 0.07710502872239118,
      "grad_norm": 0.3152792751789093,
      "learning_rate": 1.993230667090628e-05,
      "loss": 0.5433,
      "step": 2510
    },
    {
      "epoch": 0.07713574785734034,
      "grad_norm": 0.37666696310043335,
      "learning_rate": 1.993225052244376e-05,
      "loss": 0.6594,
      "step": 2511
    },
    {
      "epoch": 0.0771664669922895,
      "grad_norm": 0.336330384016037,
      "learning_rate": 1.9932194350783776e-05,
      "loss": 0.6188,
      "step": 2512
    },
    {
      "epoch": 0.07719718612723865,
      "grad_norm": 0.6543074250221252,
      "learning_rate": 1.9932138155926456e-05,
      "loss": 0.7542,
      "step": 2513
    },
    {
      "epoch": 0.07722790526218781,
      "grad_norm": 0.31721827387809753,
      "learning_rate": 1.9932081937871935e-05,
      "loss": 0.6287,
      "step": 2514
    },
    {
      "epoch": 0.07725862439713697,
      "grad_norm": 0.5091707110404968,
      "learning_rate": 1.993202569662034e-05,
      "loss": 0.6508,
      "step": 2515
    },
    {
      "epoch": 0.07728934353208614,
      "grad_norm": 0.3712039291858673,
      "learning_rate": 1.993196943217181e-05,
      "loss": 0.6244,
      "step": 2516
    },
    {
      "epoch": 0.0773200626670353,
      "grad_norm": 0.3303382992744446,
      "learning_rate": 1.9931913144526467e-05,
      "loss": 0.7121,
      "step": 2517
    },
    {
      "epoch": 0.07735078180198446,
      "grad_norm": 0.332744836807251,
      "learning_rate": 1.993185683368445e-05,
      "loss": 0.6541,
      "step": 2518
    },
    {
      "epoch": 0.07738150093693362,
      "grad_norm": 0.34520775079727173,
      "learning_rate": 1.993180049964589e-05,
      "loss": 0.6439,
      "step": 2519
    },
    {
      "epoch": 0.07741222007188278,
      "grad_norm": 0.34182849526405334,
      "learning_rate": 1.9931744142410912e-05,
      "loss": 0.6045,
      "step": 2520
    },
    {
      "epoch": 0.07744293920683193,
      "grad_norm": 0.3610750734806061,
      "learning_rate": 1.9931687761979654e-05,
      "loss": 0.6502,
      "step": 2521
    },
    {
      "epoch": 0.07747365834178109,
      "grad_norm": 0.3256135880947113,
      "learning_rate": 1.9931631358352242e-05,
      "loss": 0.6301,
      "step": 2522
    },
    {
      "epoch": 0.07750437747673025,
      "grad_norm": 0.36114227771759033,
      "learning_rate": 1.9931574931528817e-05,
      "loss": 0.6363,
      "step": 2523
    },
    {
      "epoch": 0.07753509661167941,
      "grad_norm": 0.3857135474681854,
      "learning_rate": 1.9931518481509502e-05,
      "loss": 0.5551,
      "step": 2524
    },
    {
      "epoch": 0.07756581574662857,
      "grad_norm": 0.36042138934135437,
      "learning_rate": 1.9931462008294434e-05,
      "loss": 0.565,
      "step": 2525
    },
    {
      "epoch": 0.07759653488157774,
      "grad_norm": 0.3447607159614563,
      "learning_rate": 1.9931405511883742e-05,
      "loss": 0.615,
      "step": 2526
    },
    {
      "epoch": 0.0776272540165269,
      "grad_norm": 0.37190955877304077,
      "learning_rate": 1.9931348992277554e-05,
      "loss": 0.6596,
      "step": 2527
    },
    {
      "epoch": 0.07765797315147606,
      "grad_norm": 0.3389231264591217,
      "learning_rate": 1.9931292449476016e-05,
      "loss": 0.6934,
      "step": 2528
    },
    {
      "epoch": 0.07768869228642522,
      "grad_norm": 0.3379162549972534,
      "learning_rate": 1.9931235883479246e-05,
      "loss": 0.6482,
      "step": 2529
    },
    {
      "epoch": 0.07771941142137437,
      "grad_norm": 0.3351997137069702,
      "learning_rate": 1.993117929428738e-05,
      "loss": 0.6633,
      "step": 2530
    },
    {
      "epoch": 0.07775013055632353,
      "grad_norm": 0.34079205989837646,
      "learning_rate": 1.9931122681900554e-05,
      "loss": 0.6576,
      "step": 2531
    },
    {
      "epoch": 0.07778084969127269,
      "grad_norm": 0.30306681990623474,
      "learning_rate": 1.9931066046318892e-05,
      "loss": 0.6199,
      "step": 2532
    },
    {
      "epoch": 0.07781156882622185,
      "grad_norm": 0.3111242949962616,
      "learning_rate": 1.9931009387542538e-05,
      "loss": 0.5913,
      "step": 2533
    },
    {
      "epoch": 0.07784228796117101,
      "grad_norm": 0.32320067286491394,
      "learning_rate": 1.9930952705571613e-05,
      "loss": 0.6257,
      "step": 2534
    },
    {
      "epoch": 0.07787300709612018,
      "grad_norm": 0.33074334263801575,
      "learning_rate": 1.9930896000406256e-05,
      "loss": 0.5517,
      "step": 2535
    },
    {
      "epoch": 0.07790372623106934,
      "grad_norm": 0.33213502168655396,
      "learning_rate": 1.99308392720466e-05,
      "loss": 0.5186,
      "step": 2536
    },
    {
      "epoch": 0.0779344453660185,
      "grad_norm": 0.33391860127449036,
      "learning_rate": 1.9930782520492774e-05,
      "loss": 0.6253,
      "step": 2537
    },
    {
      "epoch": 0.07796516450096765,
      "grad_norm": 0.3306761085987091,
      "learning_rate": 1.993072574574491e-05,
      "loss": 0.7053,
      "step": 2538
    },
    {
      "epoch": 0.07799588363591681,
      "grad_norm": 0.35078611969947815,
      "learning_rate": 1.9930668947803144e-05,
      "loss": 0.6863,
      "step": 2539
    },
    {
      "epoch": 0.07802660277086597,
      "grad_norm": 0.3536697328090668,
      "learning_rate": 1.993061212666761e-05,
      "loss": 0.581,
      "step": 2540
    },
    {
      "epoch": 0.07805732190581513,
      "grad_norm": 0.47167104482650757,
      "learning_rate": 1.993055528233843e-05,
      "loss": 0.6092,
      "step": 2541
    },
    {
      "epoch": 0.07808804104076429,
      "grad_norm": 0.3312068581581116,
      "learning_rate": 1.9930498414815754e-05,
      "loss": 0.6395,
      "step": 2542
    },
    {
      "epoch": 0.07811876017571345,
      "grad_norm": 0.39657771587371826,
      "learning_rate": 1.99304415240997e-05,
      "loss": 0.621,
      "step": 2543
    },
    {
      "epoch": 0.07814947931066261,
      "grad_norm": 0.3782680928707123,
      "learning_rate": 1.9930384610190407e-05,
      "loss": 0.6322,
      "step": 2544
    },
    {
      "epoch": 0.07818019844561178,
      "grad_norm": 0.3931754529476166,
      "learning_rate": 1.9930327673088005e-05,
      "loss": 0.6306,
      "step": 2545
    },
    {
      "epoch": 0.07821091758056094,
      "grad_norm": 0.32752808928489685,
      "learning_rate": 1.9930270712792634e-05,
      "loss": 0.5884,
      "step": 2546
    },
    {
      "epoch": 0.07824163671551009,
      "grad_norm": 0.3295663297176361,
      "learning_rate": 1.993021372930442e-05,
      "loss": 0.6907,
      "step": 2547
    },
    {
      "epoch": 0.07827235585045925,
      "grad_norm": 0.45207929611206055,
      "learning_rate": 1.9930156722623496e-05,
      "loss": 0.6314,
      "step": 2548
    },
    {
      "epoch": 0.07830307498540841,
      "grad_norm": 0.36948058009147644,
      "learning_rate": 1.9930099692750004e-05,
      "loss": 0.6933,
      "step": 2549
    },
    {
      "epoch": 0.07833379412035757,
      "grad_norm": 0.33911609649658203,
      "learning_rate": 1.9930042639684065e-05,
      "loss": 0.5008,
      "step": 2550
    },
    {
      "epoch": 0.07836451325530673,
      "grad_norm": 0.3380142152309418,
      "learning_rate": 1.992998556342582e-05,
      "loss": 0.5651,
      "step": 2551
    },
    {
      "epoch": 0.07839523239025589,
      "grad_norm": 0.5416232943534851,
      "learning_rate": 1.99299284639754e-05,
      "loss": 0.6272,
      "step": 2552
    },
    {
      "epoch": 0.07842595152520505,
      "grad_norm": 0.31836748123168945,
      "learning_rate": 1.9929871341332937e-05,
      "loss": 0.6123,
      "step": 2553
    },
    {
      "epoch": 0.07845667066015422,
      "grad_norm": 0.30304020643234253,
      "learning_rate": 1.9929814195498567e-05,
      "loss": 0.527,
      "step": 2554
    },
    {
      "epoch": 0.07848738979510338,
      "grad_norm": 0.36214837431907654,
      "learning_rate": 1.992975702647242e-05,
      "loss": 0.5639,
      "step": 2555
    },
    {
      "epoch": 0.07851810893005252,
      "grad_norm": 0.3240317702293396,
      "learning_rate": 1.9929699834254636e-05,
      "loss": 0.6172,
      "step": 2556
    },
    {
      "epoch": 0.07854882806500169,
      "grad_norm": 0.367611289024353,
      "learning_rate": 1.9929642618845346e-05,
      "loss": 0.6417,
      "step": 2557
    },
    {
      "epoch": 0.07857954719995085,
      "grad_norm": 0.3312862813472748,
      "learning_rate": 1.9929585380244676e-05,
      "loss": 0.5482,
      "step": 2558
    },
    {
      "epoch": 0.07861026633490001,
      "grad_norm": 0.32803112268447876,
      "learning_rate": 1.992952811845277e-05,
      "loss": 0.646,
      "step": 2559
    },
    {
      "epoch": 0.07864098546984917,
      "grad_norm": 0.36769798398017883,
      "learning_rate": 1.992947083346976e-05,
      "loss": 0.6571,
      "step": 2560
    },
    {
      "epoch": 0.07867170460479833,
      "grad_norm": 0.3001982569694519,
      "learning_rate": 1.992941352529577e-05,
      "loss": 0.6088,
      "step": 2561
    },
    {
      "epoch": 0.07870242373974749,
      "grad_norm": 0.3441161513328552,
      "learning_rate": 1.9929356193930947e-05,
      "loss": 0.6632,
      "step": 2562
    },
    {
      "epoch": 0.07873314287469665,
      "grad_norm": 0.373363196849823,
      "learning_rate": 1.9929298839375417e-05,
      "loss": 0.574,
      "step": 2563
    },
    {
      "epoch": 0.0787638620096458,
      "grad_norm": 0.3323586583137512,
      "learning_rate": 1.9929241461629315e-05,
      "loss": 0.5971,
      "step": 2564
    },
    {
      "epoch": 0.07879458114459496,
      "grad_norm": 0.3849039375782013,
      "learning_rate": 1.992918406069278e-05,
      "loss": 0.6474,
      "step": 2565
    },
    {
      "epoch": 0.07882530027954412,
      "grad_norm": 0.3034350275993347,
      "learning_rate": 1.9929126636565937e-05,
      "loss": 0.5991,
      "step": 2566
    },
    {
      "epoch": 0.07885601941449329,
      "grad_norm": 0.3615133464336395,
      "learning_rate": 1.992906918924893e-05,
      "loss": 0.6636,
      "step": 2567
    },
    {
      "epoch": 0.07888673854944245,
      "grad_norm": 0.3255395293235779,
      "learning_rate": 1.9929011718741888e-05,
      "loss": 0.5857,
      "step": 2568
    },
    {
      "epoch": 0.07891745768439161,
      "grad_norm": 0.33248642086982727,
      "learning_rate": 1.9928954225044944e-05,
      "loss": 0.6184,
      "step": 2569
    },
    {
      "epoch": 0.07894817681934077,
      "grad_norm": 0.564972996711731,
      "learning_rate": 1.9928896708158234e-05,
      "loss": 0.6282,
      "step": 2570
    },
    {
      "epoch": 0.07897889595428993,
      "grad_norm": 0.2928917109966278,
      "learning_rate": 1.9928839168081892e-05,
      "loss": 0.5441,
      "step": 2571
    },
    {
      "epoch": 0.0790096150892391,
      "grad_norm": 0.36047419905662537,
      "learning_rate": 1.9928781604816056e-05,
      "loss": 0.6951,
      "step": 2572
    },
    {
      "epoch": 0.07904033422418824,
      "grad_norm": 0.3274795413017273,
      "learning_rate": 1.9928724018360852e-05,
      "loss": 0.5983,
      "step": 2573
    },
    {
      "epoch": 0.0790710533591374,
      "grad_norm": 0.3415004014968872,
      "learning_rate": 1.9928666408716424e-05,
      "loss": 0.5939,
      "step": 2574
    },
    {
      "epoch": 0.07910177249408656,
      "grad_norm": 0.37627875804901123,
      "learning_rate": 1.99286087758829e-05,
      "loss": 0.6591,
      "step": 2575
    },
    {
      "epoch": 0.07913249162903573,
      "grad_norm": 0.33888760209083557,
      "learning_rate": 1.9928551119860414e-05,
      "loss": 0.5956,
      "step": 2576
    },
    {
      "epoch": 0.07916321076398489,
      "grad_norm": 0.35889023542404175,
      "learning_rate": 1.992849344064911e-05,
      "loss": 0.7161,
      "step": 2577
    },
    {
      "epoch": 0.07919392989893405,
      "grad_norm": 0.322185218334198,
      "learning_rate": 1.9928435738249112e-05,
      "loss": 0.5791,
      "step": 2578
    },
    {
      "epoch": 0.07922464903388321,
      "grad_norm": 0.3304510712623596,
      "learning_rate": 1.992837801266056e-05,
      "loss": 0.6535,
      "step": 2579
    },
    {
      "epoch": 0.07925536816883237,
      "grad_norm": 0.3246460258960724,
      "learning_rate": 1.9928320263883586e-05,
      "loss": 0.6991,
      "step": 2580
    },
    {
      "epoch": 0.07928608730378152,
      "grad_norm": 0.3504895269870758,
      "learning_rate": 1.992826249191833e-05,
      "loss": 0.6158,
      "step": 2581
    },
    {
      "epoch": 0.07931680643873068,
      "grad_norm": 0.35232171416282654,
      "learning_rate": 1.9928204696764923e-05,
      "loss": 0.6834,
      "step": 2582
    },
    {
      "epoch": 0.07934752557367984,
      "grad_norm": 0.344690203666687,
      "learning_rate": 1.99281468784235e-05,
      "loss": 0.6944,
      "step": 2583
    },
    {
      "epoch": 0.079378244708629,
      "grad_norm": 0.3745235502719879,
      "learning_rate": 1.9928089036894193e-05,
      "loss": 0.6045,
      "step": 2584
    },
    {
      "epoch": 0.07940896384357816,
      "grad_norm": 0.3229826092720032,
      "learning_rate": 1.9928031172177144e-05,
      "loss": 0.6211,
      "step": 2585
    },
    {
      "epoch": 0.07943968297852733,
      "grad_norm": 0.31463873386383057,
      "learning_rate": 1.9927973284272486e-05,
      "loss": 0.576,
      "step": 2586
    },
    {
      "epoch": 0.07947040211347649,
      "grad_norm": 0.37938106060028076,
      "learning_rate": 1.9927915373180352e-05,
      "loss": 0.6868,
      "step": 2587
    },
    {
      "epoch": 0.07950112124842565,
      "grad_norm": 0.3318946957588196,
      "learning_rate": 1.9927857438900874e-05,
      "loss": 0.6523,
      "step": 2588
    },
    {
      "epoch": 0.07953184038337481,
      "grad_norm": 0.37501659989356995,
      "learning_rate": 1.9927799481434194e-05,
      "loss": 0.5997,
      "step": 2589
    },
    {
      "epoch": 0.07956255951832396,
      "grad_norm": 0.33932632207870483,
      "learning_rate": 1.9927741500780452e-05,
      "loss": 0.5828,
      "step": 2590
    },
    {
      "epoch": 0.07959327865327312,
      "grad_norm": 0.4965178966522217,
      "learning_rate": 1.992768349693977e-05,
      "loss": 0.6024,
      "step": 2591
    },
    {
      "epoch": 0.07962399778822228,
      "grad_norm": 0.354361891746521,
      "learning_rate": 1.9927625469912287e-05,
      "loss": 0.6041,
      "step": 2592
    },
    {
      "epoch": 0.07965471692317144,
      "grad_norm": 0.414718359708786,
      "learning_rate": 1.9927567419698146e-05,
      "loss": 0.646,
      "step": 2593
    },
    {
      "epoch": 0.0796854360581206,
      "grad_norm": 0.326719731092453,
      "learning_rate": 1.9927509346297477e-05,
      "loss": 0.5491,
      "step": 2594
    },
    {
      "epoch": 0.07971615519306977,
      "grad_norm": 0.3372949957847595,
      "learning_rate": 1.9927451249710417e-05,
      "loss": 0.6862,
      "step": 2595
    },
    {
      "epoch": 0.07974687432801893,
      "grad_norm": 0.33408963680267334,
      "learning_rate": 1.99273931299371e-05,
      "loss": 0.5724,
      "step": 2596
    },
    {
      "epoch": 0.07977759346296809,
      "grad_norm": 0.38652995228767395,
      "learning_rate": 1.9927334986977665e-05,
      "loss": 0.6248,
      "step": 2597
    },
    {
      "epoch": 0.07980831259791724,
      "grad_norm": 0.3323294222354889,
      "learning_rate": 1.9927276820832242e-05,
      "loss": 0.519,
      "step": 2598
    },
    {
      "epoch": 0.0798390317328664,
      "grad_norm": 0.3355146646499634,
      "learning_rate": 1.9927218631500976e-05,
      "loss": 0.6455,
      "step": 2599
    },
    {
      "epoch": 0.07986975086781556,
      "grad_norm": 0.35886266827583313,
      "learning_rate": 1.9927160418983992e-05,
      "loss": 0.6277,
      "step": 2600
    },
    {
      "epoch": 0.07990047000276472,
      "grad_norm": 0.35720446705818176,
      "learning_rate": 1.9927102183281436e-05,
      "loss": 0.7014,
      "step": 2601
    },
    {
      "epoch": 0.07993118913771388,
      "grad_norm": 0.3642016351222992,
      "learning_rate": 1.9927043924393437e-05,
      "loss": 0.6634,
      "step": 2602
    },
    {
      "epoch": 0.07996190827266304,
      "grad_norm": 0.40999141335487366,
      "learning_rate": 1.9926985642320137e-05,
      "loss": 0.6259,
      "step": 2603
    },
    {
      "epoch": 0.0799926274076122,
      "grad_norm": 0.33645880222320557,
      "learning_rate": 1.9926927337061665e-05,
      "loss": 0.5454,
      "step": 2604
    },
    {
      "epoch": 0.08002334654256137,
      "grad_norm": 0.3706991374492645,
      "learning_rate": 1.9926869008618163e-05,
      "loss": 0.6293,
      "step": 2605
    },
    {
      "epoch": 0.08005406567751053,
      "grad_norm": 0.3196882903575897,
      "learning_rate": 1.9926810656989763e-05,
      "loss": 0.6429,
      "step": 2606
    },
    {
      "epoch": 0.08008478481245968,
      "grad_norm": 0.33217158913612366,
      "learning_rate": 1.9926752282176605e-05,
      "loss": 0.6181,
      "step": 2607
    },
    {
      "epoch": 0.08011550394740884,
      "grad_norm": 0.35770994424819946,
      "learning_rate": 1.9926693884178823e-05,
      "loss": 0.6686,
      "step": 2608
    },
    {
      "epoch": 0.080146223082358,
      "grad_norm": 0.31575438380241394,
      "learning_rate": 1.9926635462996556e-05,
      "loss": 0.6115,
      "step": 2609
    },
    {
      "epoch": 0.08017694221730716,
      "grad_norm": 0.37533774971961975,
      "learning_rate": 1.9926577018629934e-05,
      "loss": 0.7062,
      "step": 2610
    },
    {
      "epoch": 0.08020766135225632,
      "grad_norm": 0.37693262100219727,
      "learning_rate": 1.9926518551079102e-05,
      "loss": 0.6056,
      "step": 2611
    },
    {
      "epoch": 0.08023838048720548,
      "grad_norm": 0.3437855839729309,
      "learning_rate": 1.9926460060344196e-05,
      "loss": 0.6329,
      "step": 2612
    },
    {
      "epoch": 0.08026909962215464,
      "grad_norm": 0.3656896650791168,
      "learning_rate": 1.992640154642534e-05,
      "loss": 0.6516,
      "step": 2613
    },
    {
      "epoch": 0.0802998187571038,
      "grad_norm": 0.32682138681411743,
      "learning_rate": 1.992634300932269e-05,
      "loss": 0.5925,
      "step": 2614
    },
    {
      "epoch": 0.08033053789205297,
      "grad_norm": 0.3157438039779663,
      "learning_rate": 1.9926284449036366e-05,
      "loss": 0.6509,
      "step": 2615
    },
    {
      "epoch": 0.08036125702700211,
      "grad_norm": 0.3685324490070343,
      "learning_rate": 1.9926225865566513e-05,
      "loss": 0.7052,
      "step": 2616
    },
    {
      "epoch": 0.08039197616195128,
      "grad_norm": 0.34214314818382263,
      "learning_rate": 1.9926167258913268e-05,
      "loss": 0.5773,
      "step": 2617
    },
    {
      "epoch": 0.08042269529690044,
      "grad_norm": 0.32922083139419556,
      "learning_rate": 1.9926108629076764e-05,
      "loss": 0.5358,
      "step": 2618
    },
    {
      "epoch": 0.0804534144318496,
      "grad_norm": 0.3413679301738739,
      "learning_rate": 1.992604997605714e-05,
      "loss": 0.6098,
      "step": 2619
    },
    {
      "epoch": 0.08048413356679876,
      "grad_norm": 0.3216688930988312,
      "learning_rate": 1.9925991299854536e-05,
      "loss": 0.569,
      "step": 2620
    },
    {
      "epoch": 0.08051485270174792,
      "grad_norm": 0.3432796895503998,
      "learning_rate": 1.9925932600469082e-05,
      "loss": 0.6023,
      "step": 2621
    },
    {
      "epoch": 0.08054557183669708,
      "grad_norm": 0.3745849132537842,
      "learning_rate": 1.992587387790092e-05,
      "loss": 0.568,
      "step": 2622
    },
    {
      "epoch": 0.08057629097164624,
      "grad_norm": 0.3953138589859009,
      "learning_rate": 1.992581513215019e-05,
      "loss": 0.5162,
      "step": 2623
    },
    {
      "epoch": 0.08060701010659539,
      "grad_norm": 0.3325346112251282,
      "learning_rate": 1.9925756363217023e-05,
      "loss": 0.6357,
      "step": 2624
    },
    {
      "epoch": 0.08063772924154455,
      "grad_norm": 0.3602798879146576,
      "learning_rate": 1.9925697571101556e-05,
      "loss": 0.6243,
      "step": 2625
    },
    {
      "epoch": 0.08066844837649371,
      "grad_norm": 0.3427089750766754,
      "learning_rate": 1.9925638755803933e-05,
      "loss": 0.6865,
      "step": 2626
    },
    {
      "epoch": 0.08069916751144288,
      "grad_norm": 0.8025543093681335,
      "learning_rate": 1.992557991732429e-05,
      "loss": 0.6642,
      "step": 2627
    },
    {
      "epoch": 0.08072988664639204,
      "grad_norm": 0.3177221119403839,
      "learning_rate": 1.9925521055662755e-05,
      "loss": 0.6084,
      "step": 2628
    },
    {
      "epoch": 0.0807606057813412,
      "grad_norm": 0.3240867853164673,
      "learning_rate": 1.9925462170819475e-05,
      "loss": 0.5661,
      "step": 2629
    },
    {
      "epoch": 0.08079132491629036,
      "grad_norm": 0.3161257803440094,
      "learning_rate": 1.9925403262794586e-05,
      "loss": 0.6437,
      "step": 2630
    },
    {
      "epoch": 0.08082204405123952,
      "grad_norm": 0.31474098563194275,
      "learning_rate": 1.9925344331588226e-05,
      "loss": 0.6781,
      "step": 2631
    },
    {
      "epoch": 0.08085276318618868,
      "grad_norm": 0.3435790538787842,
      "learning_rate": 1.992528537720053e-05,
      "loss": 0.6259,
      "step": 2632
    },
    {
      "epoch": 0.08088348232113783,
      "grad_norm": 0.3514094948768616,
      "learning_rate": 1.9925226399631633e-05,
      "loss": 0.6093,
      "step": 2633
    },
    {
      "epoch": 0.08091420145608699,
      "grad_norm": 0.33251839876174927,
      "learning_rate": 1.992516739888168e-05,
      "loss": 0.6361,
      "step": 2634
    },
    {
      "epoch": 0.08094492059103615,
      "grad_norm": 0.3178584575653076,
      "learning_rate": 1.9925108374950808e-05,
      "loss": 0.5529,
      "step": 2635
    },
    {
      "epoch": 0.08097563972598532,
      "grad_norm": 0.30904000997543335,
      "learning_rate": 1.992504932783915e-05,
      "loss": 0.6106,
      "step": 2636
    },
    {
      "epoch": 0.08100635886093448,
      "grad_norm": 0.38167572021484375,
      "learning_rate": 1.9924990257546845e-05,
      "loss": 0.5826,
      "step": 2637
    },
    {
      "epoch": 0.08103707799588364,
      "grad_norm": 0.3108833432197571,
      "learning_rate": 1.992493116407403e-05,
      "loss": 0.4768,
      "step": 2638
    },
    {
      "epoch": 0.0810677971308328,
      "grad_norm": 0.3342158794403076,
      "learning_rate": 1.9924872047420848e-05,
      "loss": 0.6665,
      "step": 2639
    },
    {
      "epoch": 0.08109851626578196,
      "grad_norm": 0.36095502972602844,
      "learning_rate": 1.9924812907587433e-05,
      "loss": 0.6232,
      "step": 2640
    },
    {
      "epoch": 0.08112923540073111,
      "grad_norm": 0.32967355847358704,
      "learning_rate": 1.9924753744573925e-05,
      "loss": 0.5866,
      "step": 2641
    },
    {
      "epoch": 0.08115995453568027,
      "grad_norm": 0.41543862223625183,
      "learning_rate": 1.9924694558380463e-05,
      "loss": 0.5832,
      "step": 2642
    },
    {
      "epoch": 0.08119067367062943,
      "grad_norm": 0.31920337677001953,
      "learning_rate": 1.992463534900718e-05,
      "loss": 0.5077,
      "step": 2643
    },
    {
      "epoch": 0.0812213928055786,
      "grad_norm": 0.3503342866897583,
      "learning_rate": 1.9924576116454223e-05,
      "loss": 0.5825,
      "step": 2644
    },
    {
      "epoch": 0.08125211194052775,
      "grad_norm": 0.32780715823173523,
      "learning_rate": 1.992451686072172e-05,
      "loss": 0.5743,
      "step": 2645
    },
    {
      "epoch": 0.08128283107547692,
      "grad_norm": 0.34778738021850586,
      "learning_rate": 1.992445758180982e-05,
      "loss": 0.5775,
      "step": 2646
    },
    {
      "epoch": 0.08131355021042608,
      "grad_norm": 0.34641531109809875,
      "learning_rate": 1.9924398279718654e-05,
      "loss": 0.6549,
      "step": 2647
    },
    {
      "epoch": 0.08134426934537524,
      "grad_norm": 0.3568730056285858,
      "learning_rate": 1.9924338954448362e-05,
      "loss": 0.5707,
      "step": 2648
    },
    {
      "epoch": 0.0813749884803244,
      "grad_norm": 0.3204611837863922,
      "learning_rate": 1.9924279605999084e-05,
      "loss": 0.6259,
      "step": 2649
    },
    {
      "epoch": 0.08140570761527355,
      "grad_norm": 0.3123834431171417,
      "learning_rate": 1.9924220234370956e-05,
      "loss": 0.5535,
      "step": 2650
    },
    {
      "epoch": 0.08143642675022271,
      "grad_norm": 0.3149631917476654,
      "learning_rate": 1.992416083956412e-05,
      "loss": 0.6457,
      "step": 2651
    },
    {
      "epoch": 0.08146714588517187,
      "grad_norm": 0.30782538652420044,
      "learning_rate": 1.9924101421578714e-05,
      "loss": 0.5652,
      "step": 2652
    },
    {
      "epoch": 0.08149786502012103,
      "grad_norm": 0.32899174094200134,
      "learning_rate": 1.9924041980414873e-05,
      "loss": 0.629,
      "step": 2653
    },
    {
      "epoch": 0.0815285841550702,
      "grad_norm": 0.37759241461753845,
      "learning_rate": 1.9923982516072745e-05,
      "loss": 0.6031,
      "step": 2654
    },
    {
      "epoch": 0.08155930329001936,
      "grad_norm": 0.7862966656684875,
      "learning_rate": 1.9923923028552458e-05,
      "loss": 0.5819,
      "step": 2655
    },
    {
      "epoch": 0.08159002242496852,
      "grad_norm": 0.3619701862335205,
      "learning_rate": 1.9923863517854158e-05,
      "loss": 0.6662,
      "step": 2656
    },
    {
      "epoch": 0.08162074155991768,
      "grad_norm": 0.33081796765327454,
      "learning_rate": 1.9923803983977977e-05,
      "loss": 0.5243,
      "step": 2657
    },
    {
      "epoch": 0.08165146069486683,
      "grad_norm": 0.383810430765152,
      "learning_rate": 1.9923744426924064e-05,
      "loss": 0.6531,
      "step": 2658
    },
    {
      "epoch": 0.08168217982981599,
      "grad_norm": 0.32071760296821594,
      "learning_rate": 1.9923684846692552e-05,
      "loss": 0.5111,
      "step": 2659
    },
    {
      "epoch": 0.08171289896476515,
      "grad_norm": 0.4031817317008972,
      "learning_rate": 1.992362524328358e-05,
      "loss": 0.6755,
      "step": 2660
    },
    {
      "epoch": 0.08174361809971431,
      "grad_norm": 0.3139403164386749,
      "learning_rate": 1.9923565616697287e-05,
      "loss": 0.5017,
      "step": 2661
    },
    {
      "epoch": 0.08177433723466347,
      "grad_norm": 0.3343051075935364,
      "learning_rate": 1.9923505966933815e-05,
      "loss": 0.5577,
      "step": 2662
    },
    {
      "epoch": 0.08180505636961263,
      "grad_norm": 0.3245469927787781,
      "learning_rate": 1.99234462939933e-05,
      "loss": 0.6244,
      "step": 2663
    },
    {
      "epoch": 0.0818357755045618,
      "grad_norm": 0.338379830121994,
      "learning_rate": 1.9923386597875883e-05,
      "loss": 0.7066,
      "step": 2664
    },
    {
      "epoch": 0.08186649463951096,
      "grad_norm": 0.32091495394706726,
      "learning_rate": 1.9923326878581706e-05,
      "loss": 0.6323,
      "step": 2665
    },
    {
      "epoch": 0.08189721377446012,
      "grad_norm": 0.3154975473880768,
      "learning_rate": 1.9923267136110906e-05,
      "loss": 0.581,
      "step": 2666
    },
    {
      "epoch": 0.08192793290940927,
      "grad_norm": 0.3442096412181854,
      "learning_rate": 1.992320737046362e-05,
      "loss": 0.5482,
      "step": 2667
    },
    {
      "epoch": 0.08195865204435843,
      "grad_norm": 0.31430405378341675,
      "learning_rate": 1.9923147581639992e-05,
      "loss": 0.5676,
      "step": 2668
    },
    {
      "epoch": 0.08198937117930759,
      "grad_norm": 0.3364175856113434,
      "learning_rate": 1.992308776964016e-05,
      "loss": 0.5633,
      "step": 2669
    },
    {
      "epoch": 0.08202009031425675,
      "grad_norm": 0.32822877168655396,
      "learning_rate": 1.9923027934464267e-05,
      "loss": 0.5112,
      "step": 2670
    },
    {
      "epoch": 0.08205080944920591,
      "grad_norm": 0.3952302038669586,
      "learning_rate": 1.9922968076112444e-05,
      "loss": 0.63,
      "step": 2671
    },
    {
      "epoch": 0.08208152858415507,
      "grad_norm": 0.31103256344795227,
      "learning_rate": 1.9922908194584834e-05,
      "loss": 0.6087,
      "step": 2672
    },
    {
      "epoch": 0.08211224771910423,
      "grad_norm": 0.3132093846797943,
      "learning_rate": 1.9922848289881583e-05,
      "loss": 0.5979,
      "step": 2673
    },
    {
      "epoch": 0.0821429668540534,
      "grad_norm": 0.37856748700141907,
      "learning_rate": 1.9922788362002826e-05,
      "loss": 0.611,
      "step": 2674
    },
    {
      "epoch": 0.08217368598900254,
      "grad_norm": 0.3739640414714813,
      "learning_rate": 1.9922728410948705e-05,
      "loss": 0.6316,
      "step": 2675
    },
    {
      "epoch": 0.0822044051239517,
      "grad_norm": 0.340451180934906,
      "learning_rate": 1.9922668436719356e-05,
      "loss": 0.5511,
      "step": 2676
    },
    {
      "epoch": 0.08223512425890087,
      "grad_norm": 0.33999231457710266,
      "learning_rate": 1.9922608439314922e-05,
      "loss": 0.6395,
      "step": 2677
    },
    {
      "epoch": 0.08226584339385003,
      "grad_norm": 0.3960931897163391,
      "learning_rate": 1.9922548418735544e-05,
      "loss": 0.5778,
      "step": 2678
    },
    {
      "epoch": 0.08229656252879919,
      "grad_norm": 0.34952008724212646,
      "learning_rate": 1.9922488374981362e-05,
      "loss": 0.6456,
      "step": 2679
    },
    {
      "epoch": 0.08232728166374835,
      "grad_norm": 0.3363831341266632,
      "learning_rate": 1.992242830805252e-05,
      "loss": 0.571,
      "step": 2680
    },
    {
      "epoch": 0.08235800079869751,
      "grad_norm": 0.6826049089431763,
      "learning_rate": 1.9922368217949146e-05,
      "loss": 0.5913,
      "step": 2681
    },
    {
      "epoch": 0.08238871993364667,
      "grad_norm": 0.426200270652771,
      "learning_rate": 1.992230810467139e-05,
      "loss": 0.6152,
      "step": 2682
    },
    {
      "epoch": 0.08241943906859583,
      "grad_norm": 0.34454798698425293,
      "learning_rate": 1.9922247968219393e-05,
      "loss": 0.7544,
      "step": 2683
    },
    {
      "epoch": 0.08245015820354498,
      "grad_norm": 0.3461996614933014,
      "learning_rate": 1.9922187808593293e-05,
      "loss": 0.594,
      "step": 2684
    },
    {
      "epoch": 0.08248087733849414,
      "grad_norm": 0.3694542348384857,
      "learning_rate": 1.9922127625793228e-05,
      "loss": 0.5862,
      "step": 2685
    },
    {
      "epoch": 0.0825115964734433,
      "grad_norm": 0.34679052233695984,
      "learning_rate": 1.992206741981934e-05,
      "loss": 0.5713,
      "step": 2686
    },
    {
      "epoch": 0.08254231560839247,
      "grad_norm": 0.4831583499908447,
      "learning_rate": 1.9922007190671774e-05,
      "loss": 0.6112,
      "step": 2687
    },
    {
      "epoch": 0.08257303474334163,
      "grad_norm": 0.3507954776287079,
      "learning_rate": 1.9921946938350664e-05,
      "loss": 0.6539,
      "step": 2688
    },
    {
      "epoch": 0.08260375387829079,
      "grad_norm": 0.32169172167778015,
      "learning_rate": 1.9921886662856155e-05,
      "loss": 0.6661,
      "step": 2689
    },
    {
      "epoch": 0.08263447301323995,
      "grad_norm": 0.38097020983695984,
      "learning_rate": 1.992182636418839e-05,
      "loss": 0.6307,
      "step": 2690
    },
    {
      "epoch": 0.08266519214818911,
      "grad_norm": 0.3176480531692505,
      "learning_rate": 1.99217660423475e-05,
      "loss": 0.5834,
      "step": 2691
    },
    {
      "epoch": 0.08269591128313827,
      "grad_norm": 0.3161037564277649,
      "learning_rate": 1.9921705697333636e-05,
      "loss": 0.6188,
      "step": 2692
    },
    {
      "epoch": 0.08272663041808742,
      "grad_norm": 0.5181129574775696,
      "learning_rate": 1.9921645329146936e-05,
      "loss": 0.5889,
      "step": 2693
    },
    {
      "epoch": 0.08275734955303658,
      "grad_norm": 0.3611733317375183,
      "learning_rate": 1.9921584937787542e-05,
      "loss": 0.658,
      "step": 2694
    },
    {
      "epoch": 0.08278806868798574,
      "grad_norm": 0.3489021062850952,
      "learning_rate": 1.992152452325559e-05,
      "loss": 0.5959,
      "step": 2695
    },
    {
      "epoch": 0.0828187878229349,
      "grad_norm": 0.3422315716743469,
      "learning_rate": 1.9921464085551226e-05,
      "loss": 0.6513,
      "step": 2696
    },
    {
      "epoch": 0.08284950695788407,
      "grad_norm": 0.37429267168045044,
      "learning_rate": 1.992140362467459e-05,
      "loss": 0.6203,
      "step": 2697
    },
    {
      "epoch": 0.08288022609283323,
      "grad_norm": 0.36002856492996216,
      "learning_rate": 1.9921343140625826e-05,
      "loss": 0.6883,
      "step": 2698
    },
    {
      "epoch": 0.08291094522778239,
      "grad_norm": 0.35953766107559204,
      "learning_rate": 1.9921282633405067e-05,
      "loss": 0.6783,
      "step": 2699
    },
    {
      "epoch": 0.08294166436273155,
      "grad_norm": 0.29967978596687317,
      "learning_rate": 1.992122210301246e-05,
      "loss": 0.5739,
      "step": 2700
    },
    {
      "epoch": 0.0829723834976807,
      "grad_norm": 0.3844905495643616,
      "learning_rate": 1.992116154944815e-05,
      "loss": 0.6931,
      "step": 2701
    },
    {
      "epoch": 0.08300310263262986,
      "grad_norm": 0.336186945438385,
      "learning_rate": 1.9921100972712272e-05,
      "loss": 0.6006,
      "step": 2702
    },
    {
      "epoch": 0.08303382176757902,
      "grad_norm": 0.34563153982162476,
      "learning_rate": 1.992104037280497e-05,
      "loss": 0.5421,
      "step": 2703
    },
    {
      "epoch": 0.08306454090252818,
      "grad_norm": 0.3917716443538666,
      "learning_rate": 1.9920979749726382e-05,
      "loss": 0.6443,
      "step": 2704
    },
    {
      "epoch": 0.08309526003747734,
      "grad_norm": 0.3517506718635559,
      "learning_rate": 1.9920919103476658e-05,
      "loss": 0.5966,
      "step": 2705
    },
    {
      "epoch": 0.0831259791724265,
      "grad_norm": 0.32867568731307983,
      "learning_rate": 1.992085843405593e-05,
      "loss": 0.6665,
      "step": 2706
    },
    {
      "epoch": 0.08315669830737567,
      "grad_norm": 0.38762763142585754,
      "learning_rate": 1.9920797741464347e-05,
      "loss": 0.6138,
      "step": 2707
    },
    {
      "epoch": 0.08318741744232483,
      "grad_norm": 0.3345802426338196,
      "learning_rate": 1.9920737025702048e-05,
      "loss": 0.6551,
      "step": 2708
    },
    {
      "epoch": 0.08321813657727399,
      "grad_norm": 0.6928338408470154,
      "learning_rate": 1.9920676286769172e-05,
      "loss": 0.5185,
      "step": 2709
    },
    {
      "epoch": 0.08324885571222314,
      "grad_norm": 0.348686546087265,
      "learning_rate": 1.992061552466587e-05,
      "loss": 0.6363,
      "step": 2710
    },
    {
      "epoch": 0.0832795748471723,
      "grad_norm": 0.4703623652458191,
      "learning_rate": 1.9920554739392273e-05,
      "loss": 0.5719,
      "step": 2711
    },
    {
      "epoch": 0.08331029398212146,
      "grad_norm": 0.3457019627094269,
      "learning_rate": 1.992049393094853e-05,
      "loss": 0.6378,
      "step": 2712
    },
    {
      "epoch": 0.08334101311707062,
      "grad_norm": 0.3253428637981415,
      "learning_rate": 1.9920433099334776e-05,
      "loss": 0.63,
      "step": 2713
    },
    {
      "epoch": 0.08337173225201978,
      "grad_norm": 0.35192522406578064,
      "learning_rate": 1.992037224455116e-05,
      "loss": 0.5784,
      "step": 2714
    },
    {
      "epoch": 0.08340245138696895,
      "grad_norm": 0.3452894687652588,
      "learning_rate": 1.9920311366597824e-05,
      "loss": 0.5397,
      "step": 2715
    },
    {
      "epoch": 0.0834331705219181,
      "grad_norm": 0.35289767384529114,
      "learning_rate": 1.9920250465474908e-05,
      "loss": 0.7256,
      "step": 2716
    },
    {
      "epoch": 0.08346388965686727,
      "grad_norm": 0.37886708974838257,
      "learning_rate": 1.992018954118255e-05,
      "loss": 0.6043,
      "step": 2717
    },
    {
      "epoch": 0.08349460879181642,
      "grad_norm": 0.3592909872531891,
      "learning_rate": 1.99201285937209e-05,
      "loss": 0.6519,
      "step": 2718
    },
    {
      "epoch": 0.08352532792676558,
      "grad_norm": 0.3316820561885834,
      "learning_rate": 1.9920067623090096e-05,
      "loss": 0.6436,
      "step": 2719
    },
    {
      "epoch": 0.08355604706171474,
      "grad_norm": 0.33537569642066956,
      "learning_rate": 1.992000662929028e-05,
      "loss": 0.6579,
      "step": 2720
    },
    {
      "epoch": 0.0835867661966639,
      "grad_norm": 0.3264249265193939,
      "learning_rate": 1.9919945612321597e-05,
      "loss": 0.5952,
      "step": 2721
    },
    {
      "epoch": 0.08361748533161306,
      "grad_norm": 0.3459533452987671,
      "learning_rate": 1.9919884572184188e-05,
      "loss": 0.6165,
      "step": 2722
    },
    {
      "epoch": 0.08364820446656222,
      "grad_norm": 0.33968856930732727,
      "learning_rate": 1.9919823508878196e-05,
      "loss": 0.5776,
      "step": 2723
    },
    {
      "epoch": 0.08367892360151138,
      "grad_norm": 0.3457880914211273,
      "learning_rate": 1.991976242240376e-05,
      "loss": 0.606,
      "step": 2724
    },
    {
      "epoch": 0.08370964273646055,
      "grad_norm": 0.37574470043182373,
      "learning_rate": 1.9919701312761032e-05,
      "loss": 0.6106,
      "step": 2725
    },
    {
      "epoch": 0.08374036187140971,
      "grad_norm": 0.3702535033226013,
      "learning_rate": 1.9919640179950148e-05,
      "loss": 0.5971,
      "step": 2726
    },
    {
      "epoch": 0.08377108100635886,
      "grad_norm": 0.32573631405830383,
      "learning_rate": 1.991957902397125e-05,
      "loss": 0.6145,
      "step": 2727
    },
    {
      "epoch": 0.08380180014130802,
      "grad_norm": 0.3460420072078705,
      "learning_rate": 1.991951784482448e-05,
      "loss": 0.5441,
      "step": 2728
    },
    {
      "epoch": 0.08383251927625718,
      "grad_norm": 0.32881563901901245,
      "learning_rate": 1.9919456642509985e-05,
      "loss": 0.6357,
      "step": 2729
    },
    {
      "epoch": 0.08386323841120634,
      "grad_norm": 0.3538065254688263,
      "learning_rate": 1.9919395417027907e-05,
      "loss": 0.6155,
      "step": 2730
    },
    {
      "epoch": 0.0838939575461555,
      "grad_norm": 0.316703200340271,
      "learning_rate": 1.991933416837839e-05,
      "loss": 0.6628,
      "step": 2731
    },
    {
      "epoch": 0.08392467668110466,
      "grad_norm": 0.357222318649292,
      "learning_rate": 1.9919272896561573e-05,
      "loss": 0.6162,
      "step": 2732
    },
    {
      "epoch": 0.08395539581605382,
      "grad_norm": 0.3429494798183441,
      "learning_rate": 1.9919211601577603e-05,
      "loss": 0.627,
      "step": 2733
    },
    {
      "epoch": 0.08398611495100299,
      "grad_norm": 0.33518558740615845,
      "learning_rate": 1.9919150283426617e-05,
      "loss": 0.6616,
      "step": 2734
    },
    {
      "epoch": 0.08401683408595213,
      "grad_norm": 0.3606233298778534,
      "learning_rate": 1.9919088942108768e-05,
      "loss": 0.6587,
      "step": 2735
    },
    {
      "epoch": 0.0840475532209013,
      "grad_norm": 0.3249228298664093,
      "learning_rate": 1.9919027577624192e-05,
      "loss": 0.6269,
      "step": 2736
    },
    {
      "epoch": 0.08407827235585046,
      "grad_norm": 0.5909728407859802,
      "learning_rate": 1.9918966189973034e-05,
      "loss": 0.5614,
      "step": 2737
    },
    {
      "epoch": 0.08410899149079962,
      "grad_norm": 0.3120335340499878,
      "learning_rate": 1.9918904779155438e-05,
      "loss": 0.6058,
      "step": 2738
    },
    {
      "epoch": 0.08413971062574878,
      "grad_norm": 0.33864280581474304,
      "learning_rate": 1.9918843345171548e-05,
      "loss": 0.6584,
      "step": 2739
    },
    {
      "epoch": 0.08417042976069794,
      "grad_norm": 0.42759689688682556,
      "learning_rate": 1.9918781888021503e-05,
      "loss": 0.6482,
      "step": 2740
    },
    {
      "epoch": 0.0842011488956471,
      "grad_norm": 0.3346795439720154,
      "learning_rate": 1.9918720407705453e-05,
      "loss": 0.6814,
      "step": 2741
    },
    {
      "epoch": 0.08423186803059626,
      "grad_norm": 0.34863877296447754,
      "learning_rate": 1.991865890422354e-05,
      "loss": 0.5982,
      "step": 2742
    },
    {
      "epoch": 0.08426258716554542,
      "grad_norm": 0.3381490409374237,
      "learning_rate": 1.9918597377575905e-05,
      "loss": 0.5952,
      "step": 2743
    },
    {
      "epoch": 0.08429330630049457,
      "grad_norm": 0.6565993428230286,
      "learning_rate": 1.9918535827762695e-05,
      "loss": 0.6715,
      "step": 2744
    },
    {
      "epoch": 0.08432402543544373,
      "grad_norm": 0.35197967290878296,
      "learning_rate": 1.991847425478405e-05,
      "loss": 0.6102,
      "step": 2745
    },
    {
      "epoch": 0.0843547445703929,
      "grad_norm": 0.3346687853336334,
      "learning_rate": 1.9918412658640113e-05,
      "loss": 0.6287,
      "step": 2746
    },
    {
      "epoch": 0.08438546370534206,
      "grad_norm": 0.3382863998413086,
      "learning_rate": 1.9918351039331038e-05,
      "loss": 0.6486,
      "step": 2747
    },
    {
      "epoch": 0.08441618284029122,
      "grad_norm": 0.7111436724662781,
      "learning_rate": 1.9918289396856957e-05,
      "loss": 0.5822,
      "step": 2748
    },
    {
      "epoch": 0.08444690197524038,
      "grad_norm": 0.3520011305809021,
      "learning_rate": 1.9918227731218013e-05,
      "loss": 0.6151,
      "step": 2749
    },
    {
      "epoch": 0.08447762111018954,
      "grad_norm": 0.385083943605423,
      "learning_rate": 1.991816604241436e-05,
      "loss": 0.6438,
      "step": 2750
    },
    {
      "epoch": 0.0845083402451387,
      "grad_norm": 0.41696402430534363,
      "learning_rate": 1.9918104330446143e-05,
      "loss": 0.6688,
      "step": 2751
    },
    {
      "epoch": 0.08453905938008785,
      "grad_norm": 0.35154059529304504,
      "learning_rate": 1.9918042595313495e-05,
      "loss": 0.6262,
      "step": 2752
    },
    {
      "epoch": 0.08456977851503701,
      "grad_norm": 0.3268583118915558,
      "learning_rate": 1.9917980837016566e-05,
      "loss": 0.5999,
      "step": 2753
    },
    {
      "epoch": 0.08460049764998617,
      "grad_norm": 0.3404058516025543,
      "learning_rate": 1.99179190555555e-05,
      "loss": 0.6448,
      "step": 2754
    },
    {
      "epoch": 0.08463121678493533,
      "grad_norm": 0.519973635673523,
      "learning_rate": 1.9917857250930445e-05,
      "loss": 0.6016,
      "step": 2755
    },
    {
      "epoch": 0.0846619359198845,
      "grad_norm": 0.33483049273490906,
      "learning_rate": 1.9917795423141537e-05,
      "loss": 0.6214,
      "step": 2756
    },
    {
      "epoch": 0.08469265505483366,
      "grad_norm": 0.38468945026397705,
      "learning_rate": 1.9917733572188927e-05,
      "loss": 0.633,
      "step": 2757
    },
    {
      "epoch": 0.08472337418978282,
      "grad_norm": 0.34885361790657043,
      "learning_rate": 1.991767169807276e-05,
      "loss": 0.6027,
      "step": 2758
    },
    {
      "epoch": 0.08475409332473198,
      "grad_norm": 0.3374369144439697,
      "learning_rate": 1.9917609800793173e-05,
      "loss": 0.5528,
      "step": 2759
    },
    {
      "epoch": 0.08478481245968114,
      "grad_norm": 0.3894156813621521,
      "learning_rate": 1.991754788035032e-05,
      "loss": 0.6417,
      "step": 2760
    },
    {
      "epoch": 0.08481553159463029,
      "grad_norm": 0.33984124660491943,
      "learning_rate": 1.991748593674434e-05,
      "loss": 0.5777,
      "step": 2761
    },
    {
      "epoch": 0.08484625072957945,
      "grad_norm": 0.36440587043762207,
      "learning_rate": 1.9917423969975378e-05,
      "loss": 0.604,
      "step": 2762
    },
    {
      "epoch": 0.08487696986452861,
      "grad_norm": 0.29852429032325745,
      "learning_rate": 1.991736198004358e-05,
      "loss": 0.5286,
      "step": 2763
    },
    {
      "epoch": 0.08490768899947777,
      "grad_norm": 0.3091351389884949,
      "learning_rate": 1.9917299966949093e-05,
      "loss": 0.5483,
      "step": 2764
    },
    {
      "epoch": 0.08493840813442693,
      "grad_norm": 0.3964248299598694,
      "learning_rate": 1.9917237930692055e-05,
      "loss": 0.6482,
      "step": 2765
    },
    {
      "epoch": 0.0849691272693761,
      "grad_norm": 0.3225655257701874,
      "learning_rate": 1.991717587127262e-05,
      "loss": 0.5907,
      "step": 2766
    },
    {
      "epoch": 0.08499984640432526,
      "grad_norm": 0.3694826662540436,
      "learning_rate": 1.9917113788690922e-05,
      "loss": 0.6675,
      "step": 2767
    },
    {
      "epoch": 0.08503056553927442,
      "grad_norm": 0.3510664701461792,
      "learning_rate": 1.9917051682947116e-05,
      "loss": 0.6474,
      "step": 2768
    },
    {
      "epoch": 0.08506128467422358,
      "grad_norm": 0.3030170500278473,
      "learning_rate": 1.9916989554041346e-05,
      "loss": 0.6736,
      "step": 2769
    },
    {
      "epoch": 0.08509200380917273,
      "grad_norm": 0.41015684604644775,
      "learning_rate": 1.9916927401973752e-05,
      "loss": 0.637,
      "step": 2770
    },
    {
      "epoch": 0.08512272294412189,
      "grad_norm": 0.3464452624320984,
      "learning_rate": 1.991686522674448e-05,
      "loss": 0.6283,
      "step": 2771
    },
    {
      "epoch": 0.08515344207907105,
      "grad_norm": 0.29857194423675537,
      "learning_rate": 1.9916803028353676e-05,
      "loss": 0.5981,
      "step": 2772
    },
    {
      "epoch": 0.08518416121402021,
      "grad_norm": 0.332711398601532,
      "learning_rate": 1.9916740806801486e-05,
      "loss": 0.6546,
      "step": 2773
    },
    {
      "epoch": 0.08521488034896937,
      "grad_norm": 0.32089757919311523,
      "learning_rate": 1.991667856208806e-05,
      "loss": 0.5655,
      "step": 2774
    },
    {
      "epoch": 0.08524559948391854,
      "grad_norm": 0.48914217948913574,
      "learning_rate": 1.9916616294213532e-05,
      "loss": 0.5204,
      "step": 2775
    },
    {
      "epoch": 0.0852763186188677,
      "grad_norm": 0.491437703371048,
      "learning_rate": 1.991655400317806e-05,
      "loss": 0.6461,
      "step": 2776
    },
    {
      "epoch": 0.08530703775381686,
      "grad_norm": 0.35501065850257874,
      "learning_rate": 1.991649168898178e-05,
      "loss": 0.6365,
      "step": 2777
    },
    {
      "epoch": 0.085337756888766,
      "grad_norm": 0.33620485663414,
      "learning_rate": 1.991642935162484e-05,
      "loss": 0.6305,
      "step": 2778
    },
    {
      "epoch": 0.08536847602371517,
      "grad_norm": 0.31454193592071533,
      "learning_rate": 1.991636699110739e-05,
      "loss": 0.6338,
      "step": 2779
    },
    {
      "epoch": 0.08539919515866433,
      "grad_norm": 0.3342844843864441,
      "learning_rate": 1.991630460742957e-05,
      "loss": 0.6707,
      "step": 2780
    },
    {
      "epoch": 0.08542991429361349,
      "grad_norm": 0.32271862030029297,
      "learning_rate": 1.9916242200591533e-05,
      "loss": 0.6007,
      "step": 2781
    },
    {
      "epoch": 0.08546063342856265,
      "grad_norm": 0.4063105285167694,
      "learning_rate": 1.9916179770593414e-05,
      "loss": 0.5967,
      "step": 2782
    },
    {
      "epoch": 0.08549135256351181,
      "grad_norm": 0.32019540667533875,
      "learning_rate": 1.9916117317435365e-05,
      "loss": 0.6065,
      "step": 2783
    },
    {
      "epoch": 0.08552207169846097,
      "grad_norm": 0.29301518201828003,
      "learning_rate": 1.9916054841117535e-05,
      "loss": 0.5687,
      "step": 2784
    },
    {
      "epoch": 0.08555279083341014,
      "grad_norm": 0.35023796558380127,
      "learning_rate": 1.9915992341640065e-05,
      "loss": 0.5872,
      "step": 2785
    },
    {
      "epoch": 0.0855835099683593,
      "grad_norm": 0.33498892188072205,
      "learning_rate": 1.99159298190031e-05,
      "loss": 0.6183,
      "step": 2786
    },
    {
      "epoch": 0.08561422910330845,
      "grad_norm": 0.3699277937412262,
      "learning_rate": 1.991586727320679e-05,
      "loss": 0.6039,
      "step": 2787
    },
    {
      "epoch": 0.0856449482382576,
      "grad_norm": 0.3337472379207611,
      "learning_rate": 1.9915804704251277e-05,
      "loss": 0.6237,
      "step": 2788
    },
    {
      "epoch": 0.08567566737320677,
      "grad_norm": 0.30646103620529175,
      "learning_rate": 1.9915742112136715e-05,
      "loss": 0.6427,
      "step": 2789
    },
    {
      "epoch": 0.08570638650815593,
      "grad_norm": 0.3532959222793579,
      "learning_rate": 1.9915679496863244e-05,
      "loss": 0.5626,
      "step": 2790
    },
    {
      "epoch": 0.08573710564310509,
      "grad_norm": 0.41130560636520386,
      "learning_rate": 1.9915616858431005e-05,
      "loss": 0.6085,
      "step": 2791
    },
    {
      "epoch": 0.08576782477805425,
      "grad_norm": 0.3900735080242157,
      "learning_rate": 1.9915554196840157e-05,
      "loss": 0.6539,
      "step": 2792
    },
    {
      "epoch": 0.08579854391300341,
      "grad_norm": 0.3587592840194702,
      "learning_rate": 1.9915491512090836e-05,
      "loss": 0.6383,
      "step": 2793
    },
    {
      "epoch": 0.08582926304795258,
      "grad_norm": 0.33698222041130066,
      "learning_rate": 1.9915428804183193e-05,
      "loss": 0.59,
      "step": 2794
    },
    {
      "epoch": 0.08585998218290172,
      "grad_norm": 0.3374677002429962,
      "learning_rate": 1.9915366073117374e-05,
      "loss": 0.6414,
      "step": 2795
    },
    {
      "epoch": 0.08589070131785088,
      "grad_norm": 0.3035382032394409,
      "learning_rate": 1.9915303318893522e-05,
      "loss": 0.552,
      "step": 2796
    },
    {
      "epoch": 0.08592142045280005,
      "grad_norm": 0.33329853415489197,
      "learning_rate": 1.991524054151179e-05,
      "loss": 0.5586,
      "step": 2797
    },
    {
      "epoch": 0.08595213958774921,
      "grad_norm": 0.35550135374069214,
      "learning_rate": 1.9915177740972322e-05,
      "loss": 0.6133,
      "step": 2798
    },
    {
      "epoch": 0.08598285872269837,
      "grad_norm": 0.3372306525707245,
      "learning_rate": 1.9915114917275262e-05,
      "loss": 0.5544,
      "step": 2799
    },
    {
      "epoch": 0.08601357785764753,
      "grad_norm": 0.3994026780128479,
      "learning_rate": 1.991505207042076e-05,
      "loss": 0.6421,
      "step": 2800
    },
    {
      "epoch": 0.08604429699259669,
      "grad_norm": 0.39369380474090576,
      "learning_rate": 1.991498920040896e-05,
      "loss": 0.6721,
      "step": 2801
    },
    {
      "epoch": 0.08607501612754585,
      "grad_norm": 0.347217857837677,
      "learning_rate": 1.991492630724001e-05,
      "loss": 0.6608,
      "step": 2802
    },
    {
      "epoch": 0.08610573526249501,
      "grad_norm": 0.3108981251716614,
      "learning_rate": 1.9914863390914057e-05,
      "loss": 0.5695,
      "step": 2803
    },
    {
      "epoch": 0.08613645439744416,
      "grad_norm": 0.3242701590061188,
      "learning_rate": 1.9914800451431252e-05,
      "loss": 0.625,
      "step": 2804
    },
    {
      "epoch": 0.08616717353239332,
      "grad_norm": 0.3623962700366974,
      "learning_rate": 1.9914737488791735e-05,
      "loss": 0.5836,
      "step": 2805
    },
    {
      "epoch": 0.08619789266734249,
      "grad_norm": 0.3292767107486725,
      "learning_rate": 1.9914674502995655e-05,
      "loss": 0.6065,
      "step": 2806
    },
    {
      "epoch": 0.08622861180229165,
      "grad_norm": 0.32808005809783936,
      "learning_rate": 1.9914611494043165e-05,
      "loss": 0.633,
      "step": 2807
    },
    {
      "epoch": 0.08625933093724081,
      "grad_norm": 0.32331836223602295,
      "learning_rate": 1.99145484619344e-05,
      "loss": 0.6504,
      "step": 2808
    },
    {
      "epoch": 0.08629005007218997,
      "grad_norm": 0.3609849810600281,
      "learning_rate": 1.991448540666952e-05,
      "loss": 0.5794,
      "step": 2809
    },
    {
      "epoch": 0.08632076920713913,
      "grad_norm": 0.3300676643848419,
      "learning_rate": 1.9914422328248663e-05,
      "loss": 0.6674,
      "step": 2810
    },
    {
      "epoch": 0.08635148834208829,
      "grad_norm": 0.46421581506729126,
      "learning_rate": 1.9914359226671985e-05,
      "loss": 0.6618,
      "step": 2811
    },
    {
      "epoch": 0.08638220747703744,
      "grad_norm": 0.3513796329498291,
      "learning_rate": 1.9914296101939628e-05,
      "loss": 0.6679,
      "step": 2812
    },
    {
      "epoch": 0.0864129266119866,
      "grad_norm": 0.37734779715538025,
      "learning_rate": 1.9914232954051736e-05,
      "loss": 0.6308,
      "step": 2813
    },
    {
      "epoch": 0.08644364574693576,
      "grad_norm": 0.33486729860305786,
      "learning_rate": 1.9914169783008463e-05,
      "loss": 0.5969,
      "step": 2814
    },
    {
      "epoch": 0.08647436488188492,
      "grad_norm": 0.3413872718811035,
      "learning_rate": 1.9914106588809955e-05,
      "loss": 0.6205,
      "step": 2815
    },
    {
      "epoch": 0.08650508401683409,
      "grad_norm": 0.3983655273914337,
      "learning_rate": 1.991404337145636e-05,
      "loss": 0.6502,
      "step": 2816
    },
    {
      "epoch": 0.08653580315178325,
      "grad_norm": 0.4158492982387543,
      "learning_rate": 1.9913980130947822e-05,
      "loss": 0.6394,
      "step": 2817
    },
    {
      "epoch": 0.08656652228673241,
      "grad_norm": 0.34144526720046997,
      "learning_rate": 1.9913916867284488e-05,
      "loss": 0.5334,
      "step": 2818
    },
    {
      "epoch": 0.08659724142168157,
      "grad_norm": 0.3516261577606201,
      "learning_rate": 1.9913853580466512e-05,
      "loss": 0.6151,
      "step": 2819
    },
    {
      "epoch": 0.08662796055663073,
      "grad_norm": 0.317141592502594,
      "learning_rate": 1.991379027049404e-05,
      "loss": 0.6478,
      "step": 2820
    },
    {
      "epoch": 0.08665867969157988,
      "grad_norm": 0.32025477290153503,
      "learning_rate": 1.991372693736722e-05,
      "loss": 0.6165,
      "step": 2821
    },
    {
      "epoch": 0.08668939882652904,
      "grad_norm": 0.34148645401000977,
      "learning_rate": 1.9913663581086192e-05,
      "loss": 0.661,
      "step": 2822
    },
    {
      "epoch": 0.0867201179614782,
      "grad_norm": 0.3270363211631775,
      "learning_rate": 1.9913600201651113e-05,
      "loss": 0.6277,
      "step": 2823
    },
    {
      "epoch": 0.08675083709642736,
      "grad_norm": 0.3432461619377136,
      "learning_rate": 1.991353679906213e-05,
      "loss": 0.5838,
      "step": 2824
    },
    {
      "epoch": 0.08678155623137652,
      "grad_norm": 0.3382496237754822,
      "learning_rate": 1.9913473373319388e-05,
      "loss": 0.69,
      "step": 2825
    },
    {
      "epoch": 0.08681227536632569,
      "grad_norm": 0.34858521819114685,
      "learning_rate": 1.9913409924423037e-05,
      "loss": 0.624,
      "step": 2826
    },
    {
      "epoch": 0.08684299450127485,
      "grad_norm": 0.33826982975006104,
      "learning_rate": 1.9913346452373226e-05,
      "loss": 0.6343,
      "step": 2827
    },
    {
      "epoch": 0.08687371363622401,
      "grad_norm": 0.36341753602027893,
      "learning_rate": 1.99132829571701e-05,
      "loss": 0.623,
      "step": 2828
    },
    {
      "epoch": 0.08690443277117317,
      "grad_norm": 0.3546089828014374,
      "learning_rate": 1.991321943881381e-05,
      "loss": 0.6001,
      "step": 2829
    },
    {
      "epoch": 0.08693515190612232,
      "grad_norm": 0.3757322132587433,
      "learning_rate": 1.9913155897304503e-05,
      "loss": 0.6556,
      "step": 2830
    },
    {
      "epoch": 0.08696587104107148,
      "grad_norm": 0.2994716465473175,
      "learning_rate": 1.9913092332642326e-05,
      "loss": 0.655,
      "step": 2831
    },
    {
      "epoch": 0.08699659017602064,
      "grad_norm": 0.4100935757160187,
      "learning_rate": 1.9913028744827435e-05,
      "loss": 0.5849,
      "step": 2832
    },
    {
      "epoch": 0.0870273093109698,
      "grad_norm": 0.35454490780830383,
      "learning_rate": 1.9912965133859972e-05,
      "loss": 0.5888,
      "step": 2833
    },
    {
      "epoch": 0.08705802844591896,
      "grad_norm": 0.32594066858291626,
      "learning_rate": 1.9912901499740084e-05,
      "loss": 0.5506,
      "step": 2834
    },
    {
      "epoch": 0.08708874758086813,
      "grad_norm": 0.5282639265060425,
      "learning_rate": 1.9912837842467922e-05,
      "loss": 0.5824,
      "step": 2835
    },
    {
      "epoch": 0.08711946671581729,
      "grad_norm": 0.3428315222263336,
      "learning_rate": 1.9912774162043636e-05,
      "loss": 0.6716,
      "step": 2836
    },
    {
      "epoch": 0.08715018585076645,
      "grad_norm": 0.35618677735328674,
      "learning_rate": 1.9912710458467375e-05,
      "loss": 0.7194,
      "step": 2837
    },
    {
      "epoch": 0.0871809049857156,
      "grad_norm": 0.31580251455307007,
      "learning_rate": 1.9912646731739284e-05,
      "loss": 0.6413,
      "step": 2838
    },
    {
      "epoch": 0.08721162412066476,
      "grad_norm": 0.418367862701416,
      "learning_rate": 1.991258298185952e-05,
      "loss": 0.6989,
      "step": 2839
    },
    {
      "epoch": 0.08724234325561392,
      "grad_norm": 0.3112344443798065,
      "learning_rate": 1.991251920882822e-05,
      "loss": 0.5506,
      "step": 2840
    },
    {
      "epoch": 0.08727306239056308,
      "grad_norm": 0.3268982470035553,
      "learning_rate": 1.991245541264554e-05,
      "loss": 0.5543,
      "step": 2841
    },
    {
      "epoch": 0.08730378152551224,
      "grad_norm": 0.32092201709747314,
      "learning_rate": 1.991239159331163e-05,
      "loss": 0.5815,
      "step": 2842
    },
    {
      "epoch": 0.0873345006604614,
      "grad_norm": 0.3718336522579193,
      "learning_rate": 1.9912327750826633e-05,
      "loss": 0.6201,
      "step": 2843
    },
    {
      "epoch": 0.08736521979541056,
      "grad_norm": 0.31510481238365173,
      "learning_rate": 1.9912263885190705e-05,
      "loss": 0.5851,
      "step": 2844
    },
    {
      "epoch": 0.08739593893035973,
      "grad_norm": 0.309508353471756,
      "learning_rate": 1.9912199996403995e-05,
      "loss": 0.6237,
      "step": 2845
    },
    {
      "epoch": 0.08742665806530889,
      "grad_norm": 0.34252476692199707,
      "learning_rate": 1.9912136084466648e-05,
      "loss": 0.5881,
      "step": 2846
    },
    {
      "epoch": 0.08745737720025804,
      "grad_norm": 0.35060063004493713,
      "learning_rate": 1.9912072149378813e-05,
      "loss": 0.5722,
      "step": 2847
    },
    {
      "epoch": 0.0874880963352072,
      "grad_norm": 0.3413955867290497,
      "learning_rate": 1.9912008191140645e-05,
      "loss": 0.6421,
      "step": 2848
    },
    {
      "epoch": 0.08751881547015636,
      "grad_norm": 0.5456919074058533,
      "learning_rate": 1.9911944209752285e-05,
      "loss": 0.671,
      "step": 2849
    },
    {
      "epoch": 0.08754953460510552,
      "grad_norm": 0.29840075969696045,
      "learning_rate": 1.9911880205213888e-05,
      "loss": 0.5522,
      "step": 2850
    },
    {
      "epoch": 0.08758025374005468,
      "grad_norm": 0.33422204852104187,
      "learning_rate": 1.9911816177525605e-05,
      "loss": 0.6457,
      "step": 2851
    },
    {
      "epoch": 0.08761097287500384,
      "grad_norm": 0.4383237063884735,
      "learning_rate": 1.9911752126687584e-05,
      "loss": 0.6568,
      "step": 2852
    },
    {
      "epoch": 0.087641692009953,
      "grad_norm": 0.35408708453178406,
      "learning_rate": 1.9911688052699973e-05,
      "loss": 0.6203,
      "step": 2853
    },
    {
      "epoch": 0.08767241114490217,
      "grad_norm": 0.3402441143989563,
      "learning_rate": 1.9911623955562917e-05,
      "loss": 0.6541,
      "step": 2854
    },
    {
      "epoch": 0.08770313027985131,
      "grad_norm": 1.3859615325927734,
      "learning_rate": 1.9911559835276576e-05,
      "loss": 0.6043,
      "step": 2855
    },
    {
      "epoch": 0.08773384941480047,
      "grad_norm": 0.43770483136177063,
      "learning_rate": 1.9911495691841096e-05,
      "loss": 0.5152,
      "step": 2856
    },
    {
      "epoch": 0.08776456854974964,
      "grad_norm": 0.33351629972457886,
      "learning_rate": 1.9911431525256622e-05,
      "loss": 0.6532,
      "step": 2857
    },
    {
      "epoch": 0.0877952876846988,
      "grad_norm": 0.3767330050468445,
      "learning_rate": 1.991136733552331e-05,
      "loss": 0.6132,
      "step": 2858
    },
    {
      "epoch": 0.08782600681964796,
      "grad_norm": 0.37083521485328674,
      "learning_rate": 1.9911303122641303e-05,
      "loss": 0.6347,
      "step": 2859
    },
    {
      "epoch": 0.08785672595459712,
      "grad_norm": 0.35362112522125244,
      "learning_rate": 1.991123888661076e-05,
      "loss": 0.5693,
      "step": 2860
    },
    {
      "epoch": 0.08788744508954628,
      "grad_norm": 0.3187294900417328,
      "learning_rate": 1.9911174627431825e-05,
      "loss": 0.5534,
      "step": 2861
    },
    {
      "epoch": 0.08791816422449544,
      "grad_norm": 0.3199913203716278,
      "learning_rate": 1.991111034510465e-05,
      "loss": 0.6294,
      "step": 2862
    },
    {
      "epoch": 0.0879488833594446,
      "grad_norm": 0.35881945490837097,
      "learning_rate": 1.9911046039629384e-05,
      "loss": 0.6256,
      "step": 2863
    },
    {
      "epoch": 0.08797960249439375,
      "grad_norm": 0.33297836780548096,
      "learning_rate": 1.9910981711006176e-05,
      "loss": 0.556,
      "step": 2864
    },
    {
      "epoch": 0.08801032162934291,
      "grad_norm": 0.3296140432357788,
      "learning_rate": 1.9910917359235183e-05,
      "loss": 0.5923,
      "step": 2865
    },
    {
      "epoch": 0.08804104076429208,
      "grad_norm": 0.5501864552497864,
      "learning_rate": 1.9910852984316545e-05,
      "loss": 0.5133,
      "step": 2866
    },
    {
      "epoch": 0.08807175989924124,
      "grad_norm": 0.35824161767959595,
      "learning_rate": 1.9910788586250422e-05,
      "loss": 0.5847,
      "step": 2867
    },
    {
      "epoch": 0.0881024790341904,
      "grad_norm": 0.3572606146335602,
      "learning_rate": 1.9910724165036958e-05,
      "loss": 0.6512,
      "step": 2868
    },
    {
      "epoch": 0.08813319816913956,
      "grad_norm": 0.34366223216056824,
      "learning_rate": 1.9910659720676303e-05,
      "loss": 0.5165,
      "step": 2869
    },
    {
      "epoch": 0.08816391730408872,
      "grad_norm": 0.41351693868637085,
      "learning_rate": 1.9910595253168612e-05,
      "loss": 0.6976,
      "step": 2870
    },
    {
      "epoch": 0.08819463643903788,
      "grad_norm": 0.31898489594459534,
      "learning_rate": 1.9910530762514035e-05,
      "loss": 0.6606,
      "step": 2871
    },
    {
      "epoch": 0.08822535557398703,
      "grad_norm": 0.30670279264450073,
      "learning_rate": 1.991046624871272e-05,
      "loss": 0.6231,
      "step": 2872
    },
    {
      "epoch": 0.08825607470893619,
      "grad_norm": 0.39864426851272583,
      "learning_rate": 1.991040171176482e-05,
      "loss": 0.6758,
      "step": 2873
    },
    {
      "epoch": 0.08828679384388535,
      "grad_norm": 0.3141469657421112,
      "learning_rate": 1.9910337151670485e-05,
      "loss": 0.6179,
      "step": 2874
    },
    {
      "epoch": 0.08831751297883451,
      "grad_norm": 0.35336899757385254,
      "learning_rate": 1.9910272568429863e-05,
      "loss": 0.5648,
      "step": 2875
    },
    {
      "epoch": 0.08834823211378368,
      "grad_norm": 0.3492419719696045,
      "learning_rate": 1.991020796204311e-05,
      "loss": 0.659,
      "step": 2876
    },
    {
      "epoch": 0.08837895124873284,
      "grad_norm": 0.32687893509864807,
      "learning_rate": 1.9910143332510375e-05,
      "loss": 0.6416,
      "step": 2877
    },
    {
      "epoch": 0.088409670383682,
      "grad_norm": 0.3387722671031952,
      "learning_rate": 1.9910078679831802e-05,
      "loss": 0.6063,
      "step": 2878
    },
    {
      "epoch": 0.08844038951863116,
      "grad_norm": 0.34158802032470703,
      "learning_rate": 1.9910014004007553e-05,
      "loss": 0.6731,
      "step": 2879
    },
    {
      "epoch": 0.08847110865358032,
      "grad_norm": 0.3612844944000244,
      "learning_rate": 1.9909949305037775e-05,
      "loss": 0.6836,
      "step": 2880
    },
    {
      "epoch": 0.08850182778852947,
      "grad_norm": 0.35798513889312744,
      "learning_rate": 1.9909884582922616e-05,
      "loss": 0.6321,
      "step": 2881
    },
    {
      "epoch": 0.08853254692347863,
      "grad_norm": 0.36449822783470154,
      "learning_rate": 1.990981983766223e-05,
      "loss": 0.7124,
      "step": 2882
    },
    {
      "epoch": 0.08856326605842779,
      "grad_norm": 0.3064562678337097,
      "learning_rate": 1.990975506925677e-05,
      "loss": 0.5711,
      "step": 2883
    },
    {
      "epoch": 0.08859398519337695,
      "grad_norm": 0.3235557973384857,
      "learning_rate": 1.9909690277706382e-05,
      "loss": 0.583,
      "step": 2884
    },
    {
      "epoch": 0.08862470432832611,
      "grad_norm": 0.3273548185825348,
      "learning_rate": 1.990962546301122e-05,
      "loss": 0.6964,
      "step": 2885
    },
    {
      "epoch": 0.08865542346327528,
      "grad_norm": 0.3228119909763336,
      "learning_rate": 1.9909560625171437e-05,
      "loss": 0.6063,
      "step": 2886
    },
    {
      "epoch": 0.08868614259822444,
      "grad_norm": 0.3395960330963135,
      "learning_rate": 1.9909495764187185e-05,
      "loss": 0.6326,
      "step": 2887
    },
    {
      "epoch": 0.0887168617331736,
      "grad_norm": 0.4731431007385254,
      "learning_rate": 1.990943088005861e-05,
      "loss": 0.6298,
      "step": 2888
    },
    {
      "epoch": 0.08874758086812275,
      "grad_norm": 0.34216126799583435,
      "learning_rate": 1.9909365972785868e-05,
      "loss": 0.6779,
      "step": 2889
    },
    {
      "epoch": 0.08877830000307191,
      "grad_norm": 0.3331107497215271,
      "learning_rate": 1.990930104236911e-05,
      "loss": 0.6074,
      "step": 2890
    },
    {
      "epoch": 0.08880901913802107,
      "grad_norm": 0.34649214148521423,
      "learning_rate": 1.9909236088808488e-05,
      "loss": 0.6713,
      "step": 2891
    },
    {
      "epoch": 0.08883973827297023,
      "grad_norm": 0.3513472378253937,
      "learning_rate": 1.9909171112104153e-05,
      "loss": 0.5745,
      "step": 2892
    },
    {
      "epoch": 0.08887045740791939,
      "grad_norm": 0.3868349492549896,
      "learning_rate": 1.990910611225626e-05,
      "loss": 0.5796,
      "step": 2893
    },
    {
      "epoch": 0.08890117654286855,
      "grad_norm": 0.3720909059047699,
      "learning_rate": 1.990904108926495e-05,
      "loss": 0.5836,
      "step": 2894
    },
    {
      "epoch": 0.08893189567781772,
      "grad_norm": 0.3021162450313568,
      "learning_rate": 1.990897604313039e-05,
      "loss": 0.6363,
      "step": 2895
    },
    {
      "epoch": 0.08896261481276688,
      "grad_norm": 0.339372843503952,
      "learning_rate": 1.9908910973852718e-05,
      "loss": 0.5994,
      "step": 2896
    },
    {
      "epoch": 0.08899333394771604,
      "grad_norm": 0.3337930142879486,
      "learning_rate": 1.9908845881432095e-05,
      "loss": 0.6792,
      "step": 2897
    },
    {
      "epoch": 0.08902405308266519,
      "grad_norm": 0.3452436029911041,
      "learning_rate": 1.990878076586867e-05,
      "loss": 0.6242,
      "step": 2898
    },
    {
      "epoch": 0.08905477221761435,
      "grad_norm": 0.31822165846824646,
      "learning_rate": 1.9908715627162597e-05,
      "loss": 0.6051,
      "step": 2899
    },
    {
      "epoch": 0.08908549135256351,
      "grad_norm": 0.3396959602832794,
      "learning_rate": 1.9908650465314027e-05,
      "loss": 0.6757,
      "step": 2900
    },
    {
      "epoch": 0.08911621048751267,
      "grad_norm": 0.332762211561203,
      "learning_rate": 1.990858528032311e-05,
      "loss": 0.628,
      "step": 2901
    },
    {
      "epoch": 0.08914692962246183,
      "grad_norm": 0.3452206552028656,
      "learning_rate": 1.990852007219e-05,
      "loss": 0.5918,
      "step": 2902
    },
    {
      "epoch": 0.089177648757411,
      "grad_norm": 0.34633803367614746,
      "learning_rate": 1.990845484091485e-05,
      "loss": 0.6361,
      "step": 2903
    },
    {
      "epoch": 0.08920836789236015,
      "grad_norm": 0.3373040556907654,
      "learning_rate": 1.9908389586497814e-05,
      "loss": 0.5998,
      "step": 2904
    },
    {
      "epoch": 0.08923908702730932,
      "grad_norm": 0.32763364911079407,
      "learning_rate": 1.990832430893904e-05,
      "loss": 0.6768,
      "step": 2905
    },
    {
      "epoch": 0.08926980616225848,
      "grad_norm": 0.33780422806739807,
      "learning_rate": 1.990825900823868e-05,
      "loss": 0.5992,
      "step": 2906
    },
    {
      "epoch": 0.08930052529720763,
      "grad_norm": 0.33109140396118164,
      "learning_rate": 1.9908193684396893e-05,
      "loss": 0.5952,
      "step": 2907
    },
    {
      "epoch": 0.08933124443215679,
      "grad_norm": 0.33682510256767273,
      "learning_rate": 1.9908128337413826e-05,
      "loss": 0.6728,
      "step": 2908
    },
    {
      "epoch": 0.08936196356710595,
      "grad_norm": 0.33662328124046326,
      "learning_rate": 1.9908062967289633e-05,
      "loss": 0.5544,
      "step": 2909
    },
    {
      "epoch": 0.08939268270205511,
      "grad_norm": 0.30653098225593567,
      "learning_rate": 1.9907997574024472e-05,
      "loss": 0.6151,
      "step": 2910
    },
    {
      "epoch": 0.08942340183700427,
      "grad_norm": 0.4054519832134247,
      "learning_rate": 1.9907932157618487e-05,
      "loss": 0.6017,
      "step": 2911
    },
    {
      "epoch": 0.08945412097195343,
      "grad_norm": 0.3121623694896698,
      "learning_rate": 1.9907866718071832e-05,
      "loss": 0.6051,
      "step": 2912
    },
    {
      "epoch": 0.0894848401069026,
      "grad_norm": 0.5889284014701843,
      "learning_rate": 1.9907801255384664e-05,
      "loss": 0.5359,
      "step": 2913
    },
    {
      "epoch": 0.08951555924185176,
      "grad_norm": 0.3040056824684143,
      "learning_rate": 1.9907735769557136e-05,
      "loss": 0.6183,
      "step": 2914
    },
    {
      "epoch": 0.0895462783768009,
      "grad_norm": 0.3106307089328766,
      "learning_rate": 1.9907670260589395e-05,
      "loss": 0.5851,
      "step": 2915
    },
    {
      "epoch": 0.08957699751175006,
      "grad_norm": 0.4000803232192993,
      "learning_rate": 1.9907604728481603e-05,
      "loss": 0.5602,
      "step": 2916
    },
    {
      "epoch": 0.08960771664669923,
      "grad_norm": 0.45386168360710144,
      "learning_rate": 1.9907539173233907e-05,
      "loss": 0.5751,
      "step": 2917
    },
    {
      "epoch": 0.08963843578164839,
      "grad_norm": 0.31115126609802246,
      "learning_rate": 1.990747359484646e-05,
      "loss": 0.6519,
      "step": 2918
    },
    {
      "epoch": 0.08966915491659755,
      "grad_norm": 0.3603752851486206,
      "learning_rate": 1.9907407993319414e-05,
      "loss": 0.6236,
      "step": 2919
    },
    {
      "epoch": 0.08969987405154671,
      "grad_norm": 0.3088606894016266,
      "learning_rate": 1.9907342368652926e-05,
      "loss": 0.5799,
      "step": 2920
    },
    {
      "epoch": 0.08973059318649587,
      "grad_norm": 0.3614917993545532,
      "learning_rate": 1.9907276720847152e-05,
      "loss": 0.5758,
      "step": 2921
    },
    {
      "epoch": 0.08976131232144503,
      "grad_norm": 0.3321084678173065,
      "learning_rate": 1.990721104990224e-05,
      "loss": 0.6324,
      "step": 2922
    },
    {
      "epoch": 0.0897920314563942,
      "grad_norm": 0.348568856716156,
      "learning_rate": 1.9907145355818342e-05,
      "loss": 0.668,
      "step": 2923
    },
    {
      "epoch": 0.08982275059134334,
      "grad_norm": 0.3571713864803314,
      "learning_rate": 1.9907079638595615e-05,
      "loss": 0.6349,
      "step": 2924
    },
    {
      "epoch": 0.0898534697262925,
      "grad_norm": 0.35281437635421753,
      "learning_rate": 1.9907013898234212e-05,
      "loss": 0.6343,
      "step": 2925
    },
    {
      "epoch": 0.08988418886124167,
      "grad_norm": 0.35248422622680664,
      "learning_rate": 1.9906948134734287e-05,
      "loss": 0.5553,
      "step": 2926
    },
    {
      "epoch": 0.08991490799619083,
      "grad_norm": 0.3309333920478821,
      "learning_rate": 1.990688234809599e-05,
      "loss": 0.5623,
      "step": 2927
    },
    {
      "epoch": 0.08994562713113999,
      "grad_norm": 0.3356938362121582,
      "learning_rate": 1.990681653831948e-05,
      "loss": 0.6489,
      "step": 2928
    },
    {
      "epoch": 0.08997634626608915,
      "grad_norm": 0.31630897521972656,
      "learning_rate": 1.990675070540491e-05,
      "loss": 0.613,
      "step": 2929
    },
    {
      "epoch": 0.09000706540103831,
      "grad_norm": 0.3446984589099884,
      "learning_rate": 1.9906684849352428e-05,
      "loss": 0.6738,
      "step": 2930
    },
    {
      "epoch": 0.09003778453598747,
      "grad_norm": 0.33326825499534607,
      "learning_rate": 1.9906618970162196e-05,
      "loss": 0.5874,
      "step": 2931
    },
    {
      "epoch": 0.09006850367093662,
      "grad_norm": 0.3563658595085144,
      "learning_rate": 1.9906553067834357e-05,
      "loss": 0.587,
      "step": 2932
    },
    {
      "epoch": 0.09009922280588578,
      "grad_norm": 0.3508792519569397,
      "learning_rate": 1.9906487142369075e-05,
      "loss": 0.5906,
      "step": 2933
    },
    {
      "epoch": 0.09012994194083494,
      "grad_norm": 0.36717477440834045,
      "learning_rate": 1.9906421193766502e-05,
      "loss": 0.5918,
      "step": 2934
    },
    {
      "epoch": 0.0901606610757841,
      "grad_norm": 0.32346364855766296,
      "learning_rate": 1.9906355222026787e-05,
      "loss": 0.5731,
      "step": 2935
    },
    {
      "epoch": 0.09019138021073327,
      "grad_norm": 0.3407783508300781,
      "learning_rate": 1.9906289227150092e-05,
      "loss": 0.5307,
      "step": 2936
    },
    {
      "epoch": 0.09022209934568243,
      "grad_norm": 0.31510129570961,
      "learning_rate": 1.9906223209136564e-05,
      "loss": 0.531,
      "step": 2937
    },
    {
      "epoch": 0.09025281848063159,
      "grad_norm": 0.3410637378692627,
      "learning_rate": 1.9906157167986357e-05,
      "loss": 0.6489,
      "step": 2938
    },
    {
      "epoch": 0.09028353761558075,
      "grad_norm": 0.352766752243042,
      "learning_rate": 1.9906091103699633e-05,
      "loss": 0.6011,
      "step": 2939
    },
    {
      "epoch": 0.09031425675052991,
      "grad_norm": 0.32410386204719543,
      "learning_rate": 1.9906025016276538e-05,
      "loss": 0.5191,
      "step": 2940
    },
    {
      "epoch": 0.09034497588547906,
      "grad_norm": 0.5000545978546143,
      "learning_rate": 1.990595890571723e-05,
      "loss": 0.5787,
      "step": 2941
    },
    {
      "epoch": 0.09037569502042822,
      "grad_norm": 0.5013996958732605,
      "learning_rate": 1.9905892772021868e-05,
      "loss": 0.6701,
      "step": 2942
    },
    {
      "epoch": 0.09040641415537738,
      "grad_norm": 0.3647080659866333,
      "learning_rate": 1.9905826615190597e-05,
      "loss": 0.6515,
      "step": 2943
    },
    {
      "epoch": 0.09043713329032654,
      "grad_norm": 0.4589601755142212,
      "learning_rate": 1.990576043522358e-05,
      "loss": 0.6307,
      "step": 2944
    },
    {
      "epoch": 0.0904678524252757,
      "grad_norm": 0.3605164587497711,
      "learning_rate": 1.990569423212096e-05,
      "loss": 0.661,
      "step": 2945
    },
    {
      "epoch": 0.09049857156022487,
      "grad_norm": 0.31450337171554565,
      "learning_rate": 1.9905628005882906e-05,
      "loss": 0.5853,
      "step": 2946
    },
    {
      "epoch": 0.09052929069517403,
      "grad_norm": 0.32791391015052795,
      "learning_rate": 1.9905561756509565e-05,
      "loss": 0.549,
      "step": 2947
    },
    {
      "epoch": 0.09056000983012319,
      "grad_norm": 0.34124642610549927,
      "learning_rate": 1.9905495484001088e-05,
      "loss": 0.5848,
      "step": 2948
    },
    {
      "epoch": 0.09059072896507234,
      "grad_norm": 0.3467124104499817,
      "learning_rate": 1.990542918835764e-05,
      "loss": 0.5292,
      "step": 2949
    },
    {
      "epoch": 0.0906214481000215,
      "grad_norm": 0.35150575637817383,
      "learning_rate": 1.990536286957937e-05,
      "loss": 0.6124,
      "step": 2950
    },
    {
      "epoch": 0.09065216723497066,
      "grad_norm": 0.3905400037765503,
      "learning_rate": 1.990529652766643e-05,
      "loss": 0.6358,
      "step": 2951
    },
    {
      "epoch": 0.09068288636991982,
      "grad_norm": 0.32531070709228516,
      "learning_rate": 1.990523016261898e-05,
      "loss": 0.6339,
      "step": 2952
    },
    {
      "epoch": 0.09071360550486898,
      "grad_norm": 0.34192341566085815,
      "learning_rate": 1.990516377443717e-05,
      "loss": 0.5326,
      "step": 2953
    },
    {
      "epoch": 0.09074432463981814,
      "grad_norm": 0.35302433371543884,
      "learning_rate": 1.9905097363121166e-05,
      "loss": 0.6556,
      "step": 2954
    },
    {
      "epoch": 0.0907750437747673,
      "grad_norm": 0.3235360383987427,
      "learning_rate": 1.990503092867111e-05,
      "loss": 0.639,
      "step": 2955
    },
    {
      "epoch": 0.09080576290971647,
      "grad_norm": 0.4077363610267639,
      "learning_rate": 1.9904964471087163e-05,
      "loss": 0.639,
      "step": 2956
    },
    {
      "epoch": 0.09083648204466563,
      "grad_norm": 0.4379468858242035,
      "learning_rate": 1.990489799036948e-05,
      "loss": 0.6666,
      "step": 2957
    },
    {
      "epoch": 0.09086720117961478,
      "grad_norm": 0.33784446120262146,
      "learning_rate": 1.9904831486518216e-05,
      "loss": 0.6273,
      "step": 2958
    },
    {
      "epoch": 0.09089792031456394,
      "grad_norm": 0.370843768119812,
      "learning_rate": 1.9904764959533527e-05,
      "loss": 0.6934,
      "step": 2959
    },
    {
      "epoch": 0.0909286394495131,
      "grad_norm": 0.34431809186935425,
      "learning_rate": 1.9904698409415564e-05,
      "loss": 0.5961,
      "step": 2960
    },
    {
      "epoch": 0.09095935858446226,
      "grad_norm": 0.32182204723358154,
      "learning_rate": 1.9904631836164492e-05,
      "loss": 0.5857,
      "step": 2961
    },
    {
      "epoch": 0.09099007771941142,
      "grad_norm": 0.3572239875793457,
      "learning_rate": 1.990456523978046e-05,
      "loss": 0.622,
      "step": 2962
    },
    {
      "epoch": 0.09102079685436058,
      "grad_norm": 0.6481896042823792,
      "learning_rate": 1.990449862026362e-05,
      "loss": 0.5241,
      "step": 2963
    },
    {
      "epoch": 0.09105151598930974,
      "grad_norm": 0.35661813616752625,
      "learning_rate": 1.9904431977614135e-05,
      "loss": 0.5909,
      "step": 2964
    },
    {
      "epoch": 0.0910822351242589,
      "grad_norm": 0.3629101514816284,
      "learning_rate": 1.9904365311832154e-05,
      "loss": 0.6445,
      "step": 2965
    },
    {
      "epoch": 0.09111295425920805,
      "grad_norm": 0.3305891752243042,
      "learning_rate": 1.9904298622917838e-05,
      "loss": 0.6258,
      "step": 2966
    },
    {
      "epoch": 0.09114367339415722,
      "grad_norm": 0.48888248205184937,
      "learning_rate": 1.990423191087134e-05,
      "loss": 0.5333,
      "step": 2967
    },
    {
      "epoch": 0.09117439252910638,
      "grad_norm": 0.3347196578979492,
      "learning_rate": 1.990416517569282e-05,
      "loss": 0.6316,
      "step": 2968
    },
    {
      "epoch": 0.09120511166405554,
      "grad_norm": 0.3497677743434906,
      "learning_rate": 1.990409841738243e-05,
      "loss": 0.6389,
      "step": 2969
    },
    {
      "epoch": 0.0912358307990047,
      "grad_norm": 0.4351593852043152,
      "learning_rate": 1.9904031635940322e-05,
      "loss": 0.5856,
      "step": 2970
    },
    {
      "epoch": 0.09126654993395386,
      "grad_norm": 0.5817432403564453,
      "learning_rate": 1.990396483136666e-05,
      "loss": 0.6497,
      "step": 2971
    },
    {
      "epoch": 0.09129726906890302,
      "grad_norm": 0.3639446794986725,
      "learning_rate": 1.9903898003661593e-05,
      "loss": 0.641,
      "step": 2972
    },
    {
      "epoch": 0.09132798820385218,
      "grad_norm": 0.32966291904449463,
      "learning_rate": 1.9903831152825285e-05,
      "loss": 0.6218,
      "step": 2973
    },
    {
      "epoch": 0.09135870733880135,
      "grad_norm": 0.42890846729278564,
      "learning_rate": 1.9903764278857885e-05,
      "loss": 0.5123,
      "step": 2974
    },
    {
      "epoch": 0.09138942647375049,
      "grad_norm": 0.33704906702041626,
      "learning_rate": 1.9903697381759554e-05,
      "loss": 0.5445,
      "step": 2975
    },
    {
      "epoch": 0.09142014560869965,
      "grad_norm": 0.41058990359306335,
      "learning_rate": 1.9903630461530444e-05,
      "loss": 0.7687,
      "step": 2976
    },
    {
      "epoch": 0.09145086474364882,
      "grad_norm": 0.35460764169692993,
      "learning_rate": 1.9903563518170714e-05,
      "loss": 0.5701,
      "step": 2977
    },
    {
      "epoch": 0.09148158387859798,
      "grad_norm": 0.3408917188644409,
      "learning_rate": 1.990349655168052e-05,
      "loss": 0.5679,
      "step": 2978
    },
    {
      "epoch": 0.09151230301354714,
      "grad_norm": 0.3375881016254425,
      "learning_rate": 1.9903429562060018e-05,
      "loss": 0.6125,
      "step": 2979
    },
    {
      "epoch": 0.0915430221484963,
      "grad_norm": 0.3554691970348358,
      "learning_rate": 1.9903362549309366e-05,
      "loss": 0.6484,
      "step": 2980
    },
    {
      "epoch": 0.09157374128344546,
      "grad_norm": 0.30589696764945984,
      "learning_rate": 1.9903295513428715e-05,
      "loss": 0.6045,
      "step": 2981
    },
    {
      "epoch": 0.09160446041839462,
      "grad_norm": 0.31686222553253174,
      "learning_rate": 1.9903228454418227e-05,
      "loss": 0.5719,
      "step": 2982
    },
    {
      "epoch": 0.09163517955334378,
      "grad_norm": 0.3413853347301483,
      "learning_rate": 1.990316137227806e-05,
      "loss": 0.6269,
      "step": 2983
    },
    {
      "epoch": 0.09166589868829293,
      "grad_norm": 0.3475573658943176,
      "learning_rate": 1.990309426700837e-05,
      "loss": 0.5253,
      "step": 2984
    },
    {
      "epoch": 0.0916966178232421,
      "grad_norm": 0.4952273666858673,
      "learning_rate": 1.9903027138609308e-05,
      "loss": 0.5404,
      "step": 2985
    },
    {
      "epoch": 0.09172733695819126,
      "grad_norm": 0.3303493559360504,
      "learning_rate": 1.9902959987081033e-05,
      "loss": 0.5733,
      "step": 2986
    },
    {
      "epoch": 0.09175805609314042,
      "grad_norm": 0.3828124701976776,
      "learning_rate": 1.9902892812423706e-05,
      "loss": 0.6357,
      "step": 2987
    },
    {
      "epoch": 0.09178877522808958,
      "grad_norm": 0.3044688403606415,
      "learning_rate": 1.990282561463748e-05,
      "loss": 0.5374,
      "step": 2988
    },
    {
      "epoch": 0.09181949436303874,
      "grad_norm": 0.32026684284210205,
      "learning_rate": 1.9902758393722514e-05,
      "loss": 0.6285,
      "step": 2989
    },
    {
      "epoch": 0.0918502134979879,
      "grad_norm": 0.31739017367362976,
      "learning_rate": 1.9902691149678962e-05,
      "loss": 0.5538,
      "step": 2990
    },
    {
      "epoch": 0.09188093263293706,
      "grad_norm": 0.47062382102012634,
      "learning_rate": 1.990262388250699e-05,
      "loss": 0.5952,
      "step": 2991
    },
    {
      "epoch": 0.09191165176788621,
      "grad_norm": 0.34932741522789,
      "learning_rate": 1.9902556592206742e-05,
      "loss": 0.6454,
      "step": 2992
    },
    {
      "epoch": 0.09194237090283537,
      "grad_norm": 0.32357731461524963,
      "learning_rate": 1.990248927877838e-05,
      "loss": 0.7157,
      "step": 2993
    },
    {
      "epoch": 0.09197309003778453,
      "grad_norm": 0.5949954986572266,
      "learning_rate": 1.9902421942222068e-05,
      "loss": 0.7233,
      "step": 2994
    },
    {
      "epoch": 0.0920038091727337,
      "grad_norm": 0.31200310587882996,
      "learning_rate": 1.9902354582537957e-05,
      "loss": 0.5432,
      "step": 2995
    },
    {
      "epoch": 0.09203452830768286,
      "grad_norm": 0.3419654965400696,
      "learning_rate": 1.99022871997262e-05,
      "loss": 0.5639,
      "step": 2996
    },
    {
      "epoch": 0.09206524744263202,
      "grad_norm": 0.36676156520843506,
      "learning_rate": 1.9902219793786965e-05,
      "loss": 0.5943,
      "step": 2997
    },
    {
      "epoch": 0.09209596657758118,
      "grad_norm": 0.3639043867588043,
      "learning_rate": 1.9902152364720403e-05,
      "loss": 0.6216,
      "step": 2998
    },
    {
      "epoch": 0.09212668571253034,
      "grad_norm": 0.434451699256897,
      "learning_rate": 1.990208491252667e-05,
      "loss": 0.6669,
      "step": 2999
    },
    {
      "epoch": 0.0921574048474795,
      "grad_norm": 0.35373491048812866,
      "learning_rate": 1.9902017437205932e-05,
      "loss": 0.673,
      "step": 3000
    },
    {
      "epoch": 0.09218812398242865,
      "grad_norm": 0.28852495551109314,
      "learning_rate": 1.9901949938758336e-05,
      "loss": 0.5131,
      "step": 3001
    },
    {
      "epoch": 0.09221884311737781,
      "grad_norm": 0.43100324273109436,
      "learning_rate": 1.9901882417184043e-05,
      "loss": 0.5765,
      "step": 3002
    },
    {
      "epoch": 0.09224956225232697,
      "grad_norm": 0.3322145640850067,
      "learning_rate": 1.9901814872483216e-05,
      "loss": 0.5696,
      "step": 3003
    },
    {
      "epoch": 0.09228028138727613,
      "grad_norm": 0.3334522545337677,
      "learning_rate": 1.9901747304656008e-05,
      "loss": 0.6507,
      "step": 3004
    },
    {
      "epoch": 0.0923110005222253,
      "grad_norm": 0.3649522066116333,
      "learning_rate": 1.9901679713702577e-05,
      "loss": 0.5689,
      "step": 3005
    },
    {
      "epoch": 0.09234171965717446,
      "grad_norm": 0.32084330916404724,
      "learning_rate": 1.990161209962308e-05,
      "loss": 0.7135,
      "step": 3006
    },
    {
      "epoch": 0.09237243879212362,
      "grad_norm": 0.3886111080646515,
      "learning_rate": 1.9901544462417678e-05,
      "loss": 0.633,
      "step": 3007
    },
    {
      "epoch": 0.09240315792707278,
      "grad_norm": 0.3965243995189667,
      "learning_rate": 1.990147680208653e-05,
      "loss": 0.5873,
      "step": 3008
    },
    {
      "epoch": 0.09243387706202193,
      "grad_norm": 0.34569305181503296,
      "learning_rate": 1.990140911862979e-05,
      "loss": 0.621,
      "step": 3009
    },
    {
      "epoch": 0.09246459619697109,
      "grad_norm": 0.32436683773994446,
      "learning_rate": 1.990134141204761e-05,
      "loss": 0.6281,
      "step": 3010
    },
    {
      "epoch": 0.09249531533192025,
      "grad_norm": 0.3427463471889496,
      "learning_rate": 1.9901273682340165e-05,
      "loss": 0.6045,
      "step": 3011
    },
    {
      "epoch": 0.09252603446686941,
      "grad_norm": 0.39211928844451904,
      "learning_rate": 1.9901205929507602e-05,
      "loss": 0.585,
      "step": 3012
    },
    {
      "epoch": 0.09255675360181857,
      "grad_norm": 0.45308804512023926,
      "learning_rate": 1.990113815355008e-05,
      "loss": 0.5895,
      "step": 3013
    },
    {
      "epoch": 0.09258747273676773,
      "grad_norm": 0.3194686770439148,
      "learning_rate": 1.9901070354467757e-05,
      "loss": 0.5983,
      "step": 3014
    },
    {
      "epoch": 0.0926181918717169,
      "grad_norm": 0.3314695358276367,
      "learning_rate": 1.9901002532260793e-05,
      "loss": 0.5466,
      "step": 3015
    },
    {
      "epoch": 0.09264891100666606,
      "grad_norm": 0.322365403175354,
      "learning_rate": 1.990093468692935e-05,
      "loss": 0.6173,
      "step": 3016
    },
    {
      "epoch": 0.09267963014161522,
      "grad_norm": 0.354158490896225,
      "learning_rate": 1.9900866818473576e-05,
      "loss": 0.5488,
      "step": 3017
    },
    {
      "epoch": 0.09271034927656437,
      "grad_norm": 0.3489501476287842,
      "learning_rate": 1.990079892689364e-05,
      "loss": 0.6065,
      "step": 3018
    },
    {
      "epoch": 0.09274106841151353,
      "grad_norm": 0.3137321174144745,
      "learning_rate": 1.9900731012189697e-05,
      "loss": 0.5581,
      "step": 3019
    },
    {
      "epoch": 0.09277178754646269,
      "grad_norm": 0.37211352586746216,
      "learning_rate": 1.9900663074361906e-05,
      "loss": 0.5455,
      "step": 3020
    },
    {
      "epoch": 0.09280250668141185,
      "grad_norm": 0.36809325218200684,
      "learning_rate": 1.990059511341042e-05,
      "loss": 0.5984,
      "step": 3021
    },
    {
      "epoch": 0.09283322581636101,
      "grad_norm": 0.3194848299026489,
      "learning_rate": 1.9900527129335406e-05,
      "loss": 0.5877,
      "step": 3022
    },
    {
      "epoch": 0.09286394495131017,
      "grad_norm": 0.31725338101387024,
      "learning_rate": 1.9900459122137023e-05,
      "loss": 0.5611,
      "step": 3023
    },
    {
      "epoch": 0.09289466408625933,
      "grad_norm": 0.33301427960395813,
      "learning_rate": 1.990039109181542e-05,
      "loss": 0.6142,
      "step": 3024
    },
    {
      "epoch": 0.0929253832212085,
      "grad_norm": 0.3177962005138397,
      "learning_rate": 1.9900323038370768e-05,
      "loss": 0.6265,
      "step": 3025
    },
    {
      "epoch": 0.09295610235615764,
      "grad_norm": 0.3507539629936218,
      "learning_rate": 1.9900254961803215e-05,
      "loss": 0.6028,
      "step": 3026
    },
    {
      "epoch": 0.0929868214911068,
      "grad_norm": 0.32503560185432434,
      "learning_rate": 1.990018686211293e-05,
      "loss": 0.6341,
      "step": 3027
    },
    {
      "epoch": 0.09301754062605597,
      "grad_norm": 0.34986966848373413,
      "learning_rate": 1.9900118739300062e-05,
      "loss": 0.5831,
      "step": 3028
    },
    {
      "epoch": 0.09304825976100513,
      "grad_norm": 0.31542861461639404,
      "learning_rate": 1.9900050593364777e-05,
      "loss": 0.5814,
      "step": 3029
    },
    {
      "epoch": 0.09307897889595429,
      "grad_norm": 0.36861687898635864,
      "learning_rate": 1.9899982424307233e-05,
      "loss": 0.6381,
      "step": 3030
    },
    {
      "epoch": 0.09310969803090345,
      "grad_norm": 0.36474472284317017,
      "learning_rate": 1.989991423212759e-05,
      "loss": 0.6607,
      "step": 3031
    },
    {
      "epoch": 0.09314041716585261,
      "grad_norm": 0.364353746175766,
      "learning_rate": 1.9899846016826006e-05,
      "loss": 0.5877,
      "step": 3032
    },
    {
      "epoch": 0.09317113630080177,
      "grad_norm": 0.33549854159355164,
      "learning_rate": 1.9899777778402637e-05,
      "loss": 0.6245,
      "step": 3033
    },
    {
      "epoch": 0.09320185543575094,
      "grad_norm": 0.33939433097839355,
      "learning_rate": 1.9899709516857648e-05,
      "loss": 0.6662,
      "step": 3034
    },
    {
      "epoch": 0.09323257457070008,
      "grad_norm": 0.34682485461235046,
      "learning_rate": 1.9899641232191196e-05,
      "loss": 0.5758,
      "step": 3035
    },
    {
      "epoch": 0.09326329370564924,
      "grad_norm": 0.37717172503471375,
      "learning_rate": 1.9899572924403442e-05,
      "loss": 0.543,
      "step": 3036
    },
    {
      "epoch": 0.0932940128405984,
      "grad_norm": 0.3646458685398102,
      "learning_rate": 1.9899504593494542e-05,
      "loss": 0.5769,
      "step": 3037
    },
    {
      "epoch": 0.09332473197554757,
      "grad_norm": 0.3156493008136749,
      "learning_rate": 1.9899436239464657e-05,
      "loss": 0.6887,
      "step": 3038
    },
    {
      "epoch": 0.09335545111049673,
      "grad_norm": 0.3352205753326416,
      "learning_rate": 1.9899367862313944e-05,
      "loss": 0.6679,
      "step": 3039
    },
    {
      "epoch": 0.09338617024544589,
      "grad_norm": 0.3556821346282959,
      "learning_rate": 1.9899299462042573e-05,
      "loss": 0.6345,
      "step": 3040
    },
    {
      "epoch": 0.09341688938039505,
      "grad_norm": 0.32613930106163025,
      "learning_rate": 1.9899231038650692e-05,
      "loss": 0.6857,
      "step": 3041
    },
    {
      "epoch": 0.09344760851534421,
      "grad_norm": 0.39716362953186035,
      "learning_rate": 1.9899162592138467e-05,
      "loss": 0.6593,
      "step": 3042
    },
    {
      "epoch": 0.09347832765029337,
      "grad_norm": 0.386440247297287,
      "learning_rate": 1.9899094122506058e-05,
      "loss": 0.6452,
      "step": 3043
    },
    {
      "epoch": 0.09350904678524252,
      "grad_norm": 0.37525397539138794,
      "learning_rate": 1.9899025629753623e-05,
      "loss": 0.558,
      "step": 3044
    },
    {
      "epoch": 0.09353976592019168,
      "grad_norm": 0.3854731619358063,
      "learning_rate": 1.989895711388132e-05,
      "loss": 0.6333,
      "step": 3045
    },
    {
      "epoch": 0.09357048505514085,
      "grad_norm": 0.5604630708694458,
      "learning_rate": 1.9898888574889312e-05,
      "loss": 0.655,
      "step": 3046
    },
    {
      "epoch": 0.09360120419009,
      "grad_norm": 0.362789511680603,
      "learning_rate": 1.989882001277776e-05,
      "loss": 0.6075,
      "step": 3047
    },
    {
      "epoch": 0.09363192332503917,
      "grad_norm": 0.337336927652359,
      "learning_rate": 1.989875142754682e-05,
      "loss": 0.6302,
      "step": 3048
    },
    {
      "epoch": 0.09366264245998833,
      "grad_norm": 0.328815758228302,
      "learning_rate": 1.9898682819196657e-05,
      "loss": 0.5639,
      "step": 3049
    },
    {
      "epoch": 0.09369336159493749,
      "grad_norm": 0.3341332674026489,
      "learning_rate": 1.989861418772743e-05,
      "loss": 0.6073,
      "step": 3050
    },
    {
      "epoch": 0.09372408072988665,
      "grad_norm": 0.4035934805870056,
      "learning_rate": 1.9898545533139297e-05,
      "loss": 0.6292,
      "step": 3051
    },
    {
      "epoch": 0.0937547998648358,
      "grad_norm": 0.36576902866363525,
      "learning_rate": 1.9898476855432418e-05,
      "loss": 0.6708,
      "step": 3052
    },
    {
      "epoch": 0.09378551899978496,
      "grad_norm": 0.2967241704463959,
      "learning_rate": 1.9898408154606956e-05,
      "loss": 0.5991,
      "step": 3053
    },
    {
      "epoch": 0.09381623813473412,
      "grad_norm": 0.3600403666496277,
      "learning_rate": 1.989833943066307e-05,
      "loss": 0.61,
      "step": 3054
    },
    {
      "epoch": 0.09384695726968328,
      "grad_norm": 0.31540101766586304,
      "learning_rate": 1.9898270683600922e-05,
      "loss": 0.5982,
      "step": 3055
    },
    {
      "epoch": 0.09387767640463245,
      "grad_norm": 0.358182430267334,
      "learning_rate": 1.989820191342067e-05,
      "loss": 0.5896,
      "step": 3056
    },
    {
      "epoch": 0.09390839553958161,
      "grad_norm": 0.39075520634651184,
      "learning_rate": 1.9898133120122478e-05,
      "loss": 0.6628,
      "step": 3057
    },
    {
      "epoch": 0.09393911467453077,
      "grad_norm": 0.36949241161346436,
      "learning_rate": 1.9898064303706506e-05,
      "loss": 0.647,
      "step": 3058
    },
    {
      "epoch": 0.09396983380947993,
      "grad_norm": 0.4862317442893982,
      "learning_rate": 1.989799546417291e-05,
      "loss": 0.6744,
      "step": 3059
    },
    {
      "epoch": 0.09400055294442909,
      "grad_norm": 0.3393234312534332,
      "learning_rate": 1.9897926601521856e-05,
      "loss": 0.595,
      "step": 3060
    },
    {
      "epoch": 0.09403127207937824,
      "grad_norm": 0.3569565415382385,
      "learning_rate": 1.9897857715753503e-05,
      "loss": 0.7393,
      "step": 3061
    },
    {
      "epoch": 0.0940619912143274,
      "grad_norm": 0.33074215054512024,
      "learning_rate": 1.9897788806868012e-05,
      "loss": 0.4774,
      "step": 3062
    },
    {
      "epoch": 0.09409271034927656,
      "grad_norm": 0.45157933235168457,
      "learning_rate": 1.9897719874865545e-05,
      "loss": 0.6368,
      "step": 3063
    },
    {
      "epoch": 0.09412342948422572,
      "grad_norm": 0.33859291672706604,
      "learning_rate": 1.989765091974626e-05,
      "loss": 0.5694,
      "step": 3064
    },
    {
      "epoch": 0.09415414861917488,
      "grad_norm": 0.31172916293144226,
      "learning_rate": 1.9897581941510323e-05,
      "loss": 0.6045,
      "step": 3065
    },
    {
      "epoch": 0.09418486775412405,
      "grad_norm": 0.3353649973869324,
      "learning_rate": 1.9897512940157887e-05,
      "loss": 0.6344,
      "step": 3066
    },
    {
      "epoch": 0.09421558688907321,
      "grad_norm": 0.4823385179042816,
      "learning_rate": 1.9897443915689126e-05,
      "loss": 0.6728,
      "step": 3067
    },
    {
      "epoch": 0.09424630602402237,
      "grad_norm": 0.33116960525512695,
      "learning_rate": 1.9897374868104185e-05,
      "loss": 0.6332,
      "step": 3068
    },
    {
      "epoch": 0.09427702515897152,
      "grad_norm": 0.3635295033454895,
      "learning_rate": 1.989730579740324e-05,
      "loss": 0.5749,
      "step": 3069
    },
    {
      "epoch": 0.09430774429392068,
      "grad_norm": 0.36007440090179443,
      "learning_rate": 1.9897236703586445e-05,
      "loss": 0.6432,
      "step": 3070
    },
    {
      "epoch": 0.09433846342886984,
      "grad_norm": 0.43777427077293396,
      "learning_rate": 1.9897167586653962e-05,
      "loss": 0.5993,
      "step": 3071
    },
    {
      "epoch": 0.094369182563819,
      "grad_norm": 0.35600051283836365,
      "learning_rate": 1.989709844660595e-05,
      "loss": 0.6014,
      "step": 3072
    },
    {
      "epoch": 0.09439990169876816,
      "grad_norm": 0.386452853679657,
      "learning_rate": 1.9897029283442576e-05,
      "loss": 0.6903,
      "step": 3073
    },
    {
      "epoch": 0.09443062083371732,
      "grad_norm": 0.30540695786476135,
      "learning_rate": 1.9896960097163996e-05,
      "loss": 0.6,
      "step": 3074
    },
    {
      "epoch": 0.09446133996866649,
      "grad_norm": 0.34095388650894165,
      "learning_rate": 1.9896890887770382e-05,
      "loss": 0.6659,
      "step": 3075
    },
    {
      "epoch": 0.09449205910361565,
      "grad_norm": 0.33221685886383057,
      "learning_rate": 1.9896821655261882e-05,
      "loss": 0.6207,
      "step": 3076
    },
    {
      "epoch": 0.09452277823856481,
      "grad_norm": 0.33590376377105713,
      "learning_rate": 1.9896752399638663e-05,
      "loss": 0.5465,
      "step": 3077
    },
    {
      "epoch": 0.09455349737351396,
      "grad_norm": 0.4194725751876831,
      "learning_rate": 1.989668312090089e-05,
      "loss": 0.5983,
      "step": 3078
    },
    {
      "epoch": 0.09458421650846312,
      "grad_norm": 0.4226672649383545,
      "learning_rate": 1.989661381904872e-05,
      "loss": 0.6009,
      "step": 3079
    },
    {
      "epoch": 0.09461493564341228,
      "grad_norm": 0.3343108296394348,
      "learning_rate": 1.9896544494082323e-05,
      "loss": 0.5806,
      "step": 3080
    },
    {
      "epoch": 0.09464565477836144,
      "grad_norm": 0.3709106147289276,
      "learning_rate": 1.989647514600185e-05,
      "loss": 0.6288,
      "step": 3081
    },
    {
      "epoch": 0.0946763739133106,
      "grad_norm": 0.3619639575481415,
      "learning_rate": 1.989640577480747e-05,
      "loss": 0.5544,
      "step": 3082
    },
    {
      "epoch": 0.09470709304825976,
      "grad_norm": 0.3328418433666229,
      "learning_rate": 1.9896336380499343e-05,
      "loss": 0.6505,
      "step": 3083
    },
    {
      "epoch": 0.09473781218320892,
      "grad_norm": 0.34509384632110596,
      "learning_rate": 1.989626696307763e-05,
      "loss": 0.5889,
      "step": 3084
    },
    {
      "epoch": 0.09476853131815809,
      "grad_norm": 0.5031507611274719,
      "learning_rate": 1.9896197522542495e-05,
      "loss": 0.5791,
      "step": 3085
    },
    {
      "epoch": 0.09479925045310723,
      "grad_norm": 0.3560812473297119,
      "learning_rate": 1.9896128058894103e-05,
      "loss": 0.606,
      "step": 3086
    },
    {
      "epoch": 0.0948299695880564,
      "grad_norm": 0.3324228525161743,
      "learning_rate": 1.9896058572132608e-05,
      "loss": 0.6184,
      "step": 3087
    },
    {
      "epoch": 0.09486068872300556,
      "grad_norm": 0.35801437497138977,
      "learning_rate": 1.989598906225818e-05,
      "loss": 0.6576,
      "step": 3088
    },
    {
      "epoch": 0.09489140785795472,
      "grad_norm": 0.37792912125587463,
      "learning_rate": 1.989591952927098e-05,
      "loss": 0.6766,
      "step": 3089
    },
    {
      "epoch": 0.09492212699290388,
      "grad_norm": 0.31696853041648865,
      "learning_rate": 1.9895849973171163e-05,
      "loss": 0.5247,
      "step": 3090
    },
    {
      "epoch": 0.09495284612785304,
      "grad_norm": 0.34134209156036377,
      "learning_rate": 1.98957803939589e-05,
      "loss": 0.6969,
      "step": 3091
    },
    {
      "epoch": 0.0949835652628022,
      "grad_norm": 0.3069455623626709,
      "learning_rate": 1.989571079163435e-05,
      "loss": 0.5695,
      "step": 3092
    },
    {
      "epoch": 0.09501428439775136,
      "grad_norm": 0.3588535785675049,
      "learning_rate": 1.9895641166197678e-05,
      "loss": 0.5858,
      "step": 3093
    },
    {
      "epoch": 0.09504500353270053,
      "grad_norm": 0.3107183575630188,
      "learning_rate": 1.9895571517649045e-05,
      "loss": 0.5978,
      "step": 3094
    },
    {
      "epoch": 0.09507572266764967,
      "grad_norm": 0.33750200271606445,
      "learning_rate": 1.9895501845988612e-05,
      "loss": 0.6533,
      "step": 3095
    },
    {
      "epoch": 0.09510644180259883,
      "grad_norm": 0.3359595835208893,
      "learning_rate": 1.9895432151216544e-05,
      "loss": 0.5512,
      "step": 3096
    },
    {
      "epoch": 0.095137160937548,
      "grad_norm": 0.3142557442188263,
      "learning_rate": 1.9895362433333005e-05,
      "loss": 0.613,
      "step": 3097
    },
    {
      "epoch": 0.09516788007249716,
      "grad_norm": 0.31841665506362915,
      "learning_rate": 1.9895292692338152e-05,
      "loss": 0.6419,
      "step": 3098
    },
    {
      "epoch": 0.09519859920744632,
      "grad_norm": 0.46296221017837524,
      "learning_rate": 1.9895222928232157e-05,
      "loss": 0.5942,
      "step": 3099
    },
    {
      "epoch": 0.09522931834239548,
      "grad_norm": 0.3235425651073456,
      "learning_rate": 1.9895153141015174e-05,
      "loss": 0.6305,
      "step": 3100
    },
    {
      "epoch": 0.09526003747734464,
      "grad_norm": 0.31966596841812134,
      "learning_rate": 1.989508333068737e-05,
      "loss": 0.5959,
      "step": 3101
    },
    {
      "epoch": 0.0952907566122938,
      "grad_norm": 0.3342626094818115,
      "learning_rate": 1.9895013497248907e-05,
      "loss": 0.6852,
      "step": 3102
    },
    {
      "epoch": 0.09532147574724295,
      "grad_norm": 0.5294504761695862,
      "learning_rate": 1.9894943640699952e-05,
      "loss": 0.6147,
      "step": 3103
    },
    {
      "epoch": 0.09535219488219211,
      "grad_norm": 0.3317243158817291,
      "learning_rate": 1.9894873761040663e-05,
      "loss": 0.5752,
      "step": 3104
    },
    {
      "epoch": 0.09538291401714127,
      "grad_norm": 0.4122965335845947,
      "learning_rate": 1.9894803858271207e-05,
      "loss": 0.544,
      "step": 3105
    },
    {
      "epoch": 0.09541363315209044,
      "grad_norm": 0.3633585572242737,
      "learning_rate": 1.9894733932391742e-05,
      "loss": 0.6825,
      "step": 3106
    },
    {
      "epoch": 0.0954443522870396,
      "grad_norm": 0.3257274627685547,
      "learning_rate": 1.989466398340244e-05,
      "loss": 0.6506,
      "step": 3107
    },
    {
      "epoch": 0.09547507142198876,
      "grad_norm": 0.43088841438293457,
      "learning_rate": 1.9894594011303456e-05,
      "loss": 0.5546,
      "step": 3108
    },
    {
      "epoch": 0.09550579055693792,
      "grad_norm": 0.3653255105018616,
      "learning_rate": 1.9894524016094957e-05,
      "loss": 0.5903,
      "step": 3109
    },
    {
      "epoch": 0.09553650969188708,
      "grad_norm": 0.33667659759521484,
      "learning_rate": 1.9894453997777106e-05,
      "loss": 0.6037,
      "step": 3110
    },
    {
      "epoch": 0.09556722882683624,
      "grad_norm": 0.33307379484176636,
      "learning_rate": 1.9894383956350065e-05,
      "loss": 0.6758,
      "step": 3111
    },
    {
      "epoch": 0.09559794796178539,
      "grad_norm": 0.34529703855514526,
      "learning_rate": 1.9894313891814003e-05,
      "loss": 0.6138,
      "step": 3112
    },
    {
      "epoch": 0.09562866709673455,
      "grad_norm": 0.6320335268974304,
      "learning_rate": 1.9894243804169076e-05,
      "loss": 0.5579,
      "step": 3113
    },
    {
      "epoch": 0.09565938623168371,
      "grad_norm": 0.3275863826274872,
      "learning_rate": 1.9894173693415455e-05,
      "loss": 0.5342,
      "step": 3114
    },
    {
      "epoch": 0.09569010536663287,
      "grad_norm": 0.3275385797023773,
      "learning_rate": 1.98941035595533e-05,
      "loss": 0.6256,
      "step": 3115
    },
    {
      "epoch": 0.09572082450158204,
      "grad_norm": 0.32727739214897156,
      "learning_rate": 1.9894033402582772e-05,
      "loss": 0.6416,
      "step": 3116
    },
    {
      "epoch": 0.0957515436365312,
      "grad_norm": 0.3242000937461853,
      "learning_rate": 1.989396322250404e-05,
      "loss": 0.505,
      "step": 3117
    },
    {
      "epoch": 0.09578226277148036,
      "grad_norm": 0.49472177028656006,
      "learning_rate": 1.9893893019317268e-05,
      "loss": 0.6617,
      "step": 3118
    },
    {
      "epoch": 0.09581298190642952,
      "grad_norm": 0.36516624689102173,
      "learning_rate": 1.9893822793022616e-05,
      "loss": 0.6831,
      "step": 3119
    },
    {
      "epoch": 0.09584370104137868,
      "grad_norm": 0.31274929642677307,
      "learning_rate": 1.9893752543620248e-05,
      "loss": 0.6104,
      "step": 3120
    },
    {
      "epoch": 0.09587442017632783,
      "grad_norm": 0.3973565697669983,
      "learning_rate": 1.9893682271110333e-05,
      "loss": 0.6541,
      "step": 3121
    },
    {
      "epoch": 0.09590513931127699,
      "grad_norm": 0.31526824831962585,
      "learning_rate": 1.989361197549303e-05,
      "loss": 0.6684,
      "step": 3122
    },
    {
      "epoch": 0.09593585844622615,
      "grad_norm": 0.5545879006385803,
      "learning_rate": 1.9893541656768508e-05,
      "loss": 0.5869,
      "step": 3123
    },
    {
      "epoch": 0.09596657758117531,
      "grad_norm": 0.3378651440143585,
      "learning_rate": 1.9893471314936925e-05,
      "loss": 0.5708,
      "step": 3124
    },
    {
      "epoch": 0.09599729671612448,
      "grad_norm": 0.4120694100856781,
      "learning_rate": 1.989340094999845e-05,
      "loss": 0.707,
      "step": 3125
    },
    {
      "epoch": 0.09602801585107364,
      "grad_norm": 0.33883607387542725,
      "learning_rate": 1.989333056195325e-05,
      "loss": 0.633,
      "step": 3126
    },
    {
      "epoch": 0.0960587349860228,
      "grad_norm": 0.29885026812553406,
      "learning_rate": 1.9893260150801482e-05,
      "loss": 0.5015,
      "step": 3127
    },
    {
      "epoch": 0.09608945412097196,
      "grad_norm": 0.34195348620414734,
      "learning_rate": 1.989318971654331e-05,
      "loss": 0.6404,
      "step": 3128
    },
    {
      "epoch": 0.09612017325592111,
      "grad_norm": 0.3431924283504486,
      "learning_rate": 1.989311925917891e-05,
      "loss": 0.6043,
      "step": 3129
    },
    {
      "epoch": 0.09615089239087027,
      "grad_norm": 0.31518083810806274,
      "learning_rate": 1.9893048778708436e-05,
      "loss": 0.5943,
      "step": 3130
    },
    {
      "epoch": 0.09618161152581943,
      "grad_norm": 0.3537110388278961,
      "learning_rate": 1.9892978275132053e-05,
      "loss": 0.6236,
      "step": 3131
    },
    {
      "epoch": 0.09621233066076859,
      "grad_norm": 0.35050931572914124,
      "learning_rate": 1.9892907748449933e-05,
      "loss": 0.5989,
      "step": 3132
    },
    {
      "epoch": 0.09624304979571775,
      "grad_norm": 0.31870096921920776,
      "learning_rate": 1.989283719866223e-05,
      "loss": 0.5664,
      "step": 3133
    },
    {
      "epoch": 0.09627376893066691,
      "grad_norm": 0.33222806453704834,
      "learning_rate": 1.989276662576912e-05,
      "loss": 0.6104,
      "step": 3134
    },
    {
      "epoch": 0.09630448806561608,
      "grad_norm": 0.39251580834388733,
      "learning_rate": 1.989269602977076e-05,
      "loss": 0.7119,
      "step": 3135
    },
    {
      "epoch": 0.09633520720056524,
      "grad_norm": 0.3274654448032379,
      "learning_rate": 1.989262541066732e-05,
      "loss": 0.5689,
      "step": 3136
    },
    {
      "epoch": 0.0963659263355144,
      "grad_norm": 0.3265276253223419,
      "learning_rate": 1.989255476845896e-05,
      "loss": 0.61,
      "step": 3137
    },
    {
      "epoch": 0.09639664547046355,
      "grad_norm": 0.34639081358909607,
      "learning_rate": 1.989248410314585e-05,
      "loss": 0.6734,
      "step": 3138
    },
    {
      "epoch": 0.09642736460541271,
      "grad_norm": 0.3711862862110138,
      "learning_rate": 1.989241341472815e-05,
      "loss": 0.6433,
      "step": 3139
    },
    {
      "epoch": 0.09645808374036187,
      "grad_norm": 0.3116357922554016,
      "learning_rate": 1.989234270320603e-05,
      "loss": 0.5965,
      "step": 3140
    },
    {
      "epoch": 0.09648880287531103,
      "grad_norm": 0.3611212372779846,
      "learning_rate": 1.989227196857965e-05,
      "loss": 0.6003,
      "step": 3141
    },
    {
      "epoch": 0.09651952201026019,
      "grad_norm": 0.34351107478141785,
      "learning_rate": 1.989220121084918e-05,
      "loss": 0.5991,
      "step": 3142
    },
    {
      "epoch": 0.09655024114520935,
      "grad_norm": 0.31570589542388916,
      "learning_rate": 1.9892130430014783e-05,
      "loss": 0.6425,
      "step": 3143
    },
    {
      "epoch": 0.09658096028015851,
      "grad_norm": 0.3305307924747467,
      "learning_rate": 1.9892059626076624e-05,
      "loss": 0.5559,
      "step": 3144
    },
    {
      "epoch": 0.09661167941510768,
      "grad_norm": 0.3336349427700043,
      "learning_rate": 1.9891988799034866e-05,
      "loss": 0.6433,
      "step": 3145
    },
    {
      "epoch": 0.09664239855005682,
      "grad_norm": 0.3306734263896942,
      "learning_rate": 1.989191794888968e-05,
      "loss": 0.5666,
      "step": 3146
    },
    {
      "epoch": 0.09667311768500599,
      "grad_norm": 0.3830919563770294,
      "learning_rate": 1.989184707564123e-05,
      "loss": 0.6408,
      "step": 3147
    },
    {
      "epoch": 0.09670383681995515,
      "grad_norm": 0.34692418575286865,
      "learning_rate": 1.9891776179289678e-05,
      "loss": 0.6745,
      "step": 3148
    },
    {
      "epoch": 0.09673455595490431,
      "grad_norm": 0.34817132353782654,
      "learning_rate": 1.98917052598352e-05,
      "loss": 0.6525,
      "step": 3149
    },
    {
      "epoch": 0.09676527508985347,
      "grad_norm": 0.34807950258255005,
      "learning_rate": 1.9891634317277943e-05,
      "loss": 0.5664,
      "step": 3150
    },
    {
      "epoch": 0.09679599422480263,
      "grad_norm": 0.3407091200351715,
      "learning_rate": 1.9891563351618088e-05,
      "loss": 0.6136,
      "step": 3151
    },
    {
      "epoch": 0.09682671335975179,
      "grad_norm": 0.3422669768333435,
      "learning_rate": 1.9891492362855795e-05,
      "loss": 0.5827,
      "step": 3152
    },
    {
      "epoch": 0.09685743249470095,
      "grad_norm": 0.30555665493011475,
      "learning_rate": 1.989142135099123e-05,
      "loss": 0.5669,
      "step": 3153
    },
    {
      "epoch": 0.09688815162965012,
      "grad_norm": 0.34539994597435,
      "learning_rate": 1.989135031602456e-05,
      "loss": 0.5998,
      "step": 3154
    },
    {
      "epoch": 0.09691887076459926,
      "grad_norm": 0.38171660900115967,
      "learning_rate": 1.989127925795595e-05,
      "loss": 0.7091,
      "step": 3155
    },
    {
      "epoch": 0.09694958989954842,
      "grad_norm": 0.34479010105133057,
      "learning_rate": 1.9891208176785567e-05,
      "loss": 0.6304,
      "step": 3156
    },
    {
      "epoch": 0.09698030903449759,
      "grad_norm": 0.3492222726345062,
      "learning_rate": 1.9891137072513577e-05,
      "loss": 0.7334,
      "step": 3157
    },
    {
      "epoch": 0.09701102816944675,
      "grad_norm": 0.3133176565170288,
      "learning_rate": 1.9891065945140146e-05,
      "loss": 0.6112,
      "step": 3158
    },
    {
      "epoch": 0.09704174730439591,
      "grad_norm": 0.3359071910381317,
      "learning_rate": 1.989099479466544e-05,
      "loss": 0.5579,
      "step": 3159
    },
    {
      "epoch": 0.09707246643934507,
      "grad_norm": 0.3366149663925171,
      "learning_rate": 1.9890923621089625e-05,
      "loss": 0.5694,
      "step": 3160
    },
    {
      "epoch": 0.09710318557429423,
      "grad_norm": 0.35750600695610046,
      "learning_rate": 1.9890852424412867e-05,
      "loss": 0.6398,
      "step": 3161
    },
    {
      "epoch": 0.0971339047092434,
      "grad_norm": 0.363984614610672,
      "learning_rate": 1.9890781204635327e-05,
      "loss": 0.6014,
      "step": 3162
    },
    {
      "epoch": 0.09716462384419254,
      "grad_norm": 0.292131245136261,
      "learning_rate": 1.9890709961757184e-05,
      "loss": 0.6785,
      "step": 3163
    },
    {
      "epoch": 0.0971953429791417,
      "grad_norm": 0.35772615671157837,
      "learning_rate": 1.9890638695778595e-05,
      "loss": 0.6284,
      "step": 3164
    },
    {
      "epoch": 0.09722606211409086,
      "grad_norm": 0.3279832601547241,
      "learning_rate": 1.9890567406699727e-05,
      "loss": 0.5879,
      "step": 3165
    },
    {
      "epoch": 0.09725678124904003,
      "grad_norm": 0.36719343066215515,
      "learning_rate": 1.9890496094520747e-05,
      "loss": 0.6648,
      "step": 3166
    },
    {
      "epoch": 0.09728750038398919,
      "grad_norm": 0.4615706503391266,
      "learning_rate": 1.9890424759241825e-05,
      "loss": 0.5563,
      "step": 3167
    },
    {
      "epoch": 0.09731821951893835,
      "grad_norm": 0.35545116662979126,
      "learning_rate": 1.9890353400863126e-05,
      "loss": 0.6227,
      "step": 3168
    },
    {
      "epoch": 0.09734893865388751,
      "grad_norm": 0.40542760491371155,
      "learning_rate": 1.9890282019384816e-05,
      "loss": 0.5837,
      "step": 3169
    },
    {
      "epoch": 0.09737965778883667,
      "grad_norm": 0.32620513439178467,
      "learning_rate": 1.989021061480706e-05,
      "loss": 0.6079,
      "step": 3170
    },
    {
      "epoch": 0.09741037692378583,
      "grad_norm": 0.3204731047153473,
      "learning_rate": 1.9890139187130027e-05,
      "loss": 0.6088,
      "step": 3171
    },
    {
      "epoch": 0.09744109605873498,
      "grad_norm": 0.3572083115577698,
      "learning_rate": 1.989006773635388e-05,
      "loss": 0.6513,
      "step": 3172
    },
    {
      "epoch": 0.09747181519368414,
      "grad_norm": 0.347637414932251,
      "learning_rate": 1.9889996262478793e-05,
      "loss": 0.6231,
      "step": 3173
    },
    {
      "epoch": 0.0975025343286333,
      "grad_norm": 0.32068097591400146,
      "learning_rate": 1.988992476550493e-05,
      "loss": 0.5563,
      "step": 3174
    },
    {
      "epoch": 0.09753325346358246,
      "grad_norm": 0.3442131578922272,
      "learning_rate": 1.9889853245432454e-05,
      "loss": 0.6599,
      "step": 3175
    },
    {
      "epoch": 0.09756397259853163,
      "grad_norm": 0.31120118498802185,
      "learning_rate": 1.9889781702261537e-05,
      "loss": 0.5984,
      "step": 3176
    },
    {
      "epoch": 0.09759469173348079,
      "grad_norm": 0.3388780951499939,
      "learning_rate": 1.988971013599234e-05,
      "loss": 0.5861,
      "step": 3177
    },
    {
      "epoch": 0.09762541086842995,
      "grad_norm": 0.36215415596961975,
      "learning_rate": 1.988963854662504e-05,
      "loss": 0.652,
      "step": 3178
    },
    {
      "epoch": 0.09765613000337911,
      "grad_norm": 0.3817155957221985,
      "learning_rate": 1.9889566934159797e-05,
      "loss": 0.6593,
      "step": 3179
    },
    {
      "epoch": 0.09768684913832826,
      "grad_norm": 0.30760952830314636,
      "learning_rate": 1.988949529859678e-05,
      "loss": 0.5537,
      "step": 3180
    },
    {
      "epoch": 0.09771756827327742,
      "grad_norm": 0.35300004482269287,
      "learning_rate": 1.9889423639936156e-05,
      "loss": 0.5739,
      "step": 3181
    },
    {
      "epoch": 0.09774828740822658,
      "grad_norm": 0.3388673961162567,
      "learning_rate": 1.988935195817809e-05,
      "loss": 0.5217,
      "step": 3182
    },
    {
      "epoch": 0.09777900654317574,
      "grad_norm": 0.2992795407772064,
      "learning_rate": 1.988928025332275e-05,
      "loss": 0.5705,
      "step": 3183
    },
    {
      "epoch": 0.0978097256781249,
      "grad_norm": 0.3405119478702545,
      "learning_rate": 1.9889208525370313e-05,
      "loss": 0.5893,
      "step": 3184
    },
    {
      "epoch": 0.09784044481307407,
      "grad_norm": 0.3696826696395874,
      "learning_rate": 1.9889136774320933e-05,
      "loss": 0.6017,
      "step": 3185
    },
    {
      "epoch": 0.09787116394802323,
      "grad_norm": 0.3242189884185791,
      "learning_rate": 1.9889065000174784e-05,
      "loss": 0.627,
      "step": 3186
    },
    {
      "epoch": 0.09790188308297239,
      "grad_norm": 0.3538976311683655,
      "learning_rate": 1.988899320293203e-05,
      "loss": 0.5933,
      "step": 3187
    },
    {
      "epoch": 0.09793260221792155,
      "grad_norm": 0.32799381017684937,
      "learning_rate": 1.988892138259285e-05,
      "loss": 0.5951,
      "step": 3188
    },
    {
      "epoch": 0.0979633213528707,
      "grad_norm": 0.3303426206111908,
      "learning_rate": 1.98888495391574e-05,
      "loss": 0.6432,
      "step": 3189
    },
    {
      "epoch": 0.09799404048781986,
      "grad_norm": 0.33012378215789795,
      "learning_rate": 1.9888777672625847e-05,
      "loss": 0.6053,
      "step": 3190
    },
    {
      "epoch": 0.09802475962276902,
      "grad_norm": 0.32762783765792847,
      "learning_rate": 1.9888705782998366e-05,
      "loss": 0.603,
      "step": 3191
    },
    {
      "epoch": 0.09805547875771818,
      "grad_norm": 0.37913039326667786,
      "learning_rate": 1.9888633870275123e-05,
      "loss": 0.5543,
      "step": 3192
    },
    {
      "epoch": 0.09808619789266734,
      "grad_norm": 0.37761685252189636,
      "learning_rate": 1.9888561934456286e-05,
      "loss": 0.59,
      "step": 3193
    },
    {
      "epoch": 0.0981169170276165,
      "grad_norm": 0.39236336946487427,
      "learning_rate": 1.988848997554202e-05,
      "loss": 0.6448,
      "step": 3194
    },
    {
      "epoch": 0.09814763616256567,
      "grad_norm": 0.340372234582901,
      "learning_rate": 1.9888417993532494e-05,
      "loss": 0.6262,
      "step": 3195
    },
    {
      "epoch": 0.09817835529751483,
      "grad_norm": 0.3991527855396271,
      "learning_rate": 1.988834598842788e-05,
      "loss": 0.6509,
      "step": 3196
    },
    {
      "epoch": 0.09820907443246399,
      "grad_norm": 0.3481108248233795,
      "learning_rate": 1.988827396022834e-05,
      "loss": 0.5462,
      "step": 3197
    },
    {
      "epoch": 0.09823979356741314,
      "grad_norm": 0.3726717531681061,
      "learning_rate": 1.9888201908934047e-05,
      "loss": 0.6151,
      "step": 3198
    },
    {
      "epoch": 0.0982705127023623,
      "grad_norm": 0.3433361351490021,
      "learning_rate": 1.988812983454517e-05,
      "loss": 0.6198,
      "step": 3199
    },
    {
      "epoch": 0.09830123183731146,
      "grad_norm": 0.3662789463996887,
      "learning_rate": 1.9888057737061873e-05,
      "loss": 0.579,
      "step": 3200
    },
    {
      "epoch": 0.09833195097226062,
      "grad_norm": 0.46841180324554443,
      "learning_rate": 1.988798561648433e-05,
      "loss": 0.6624,
      "step": 3201
    },
    {
      "epoch": 0.09836267010720978,
      "grad_norm": 1.2390342950820923,
      "learning_rate": 1.9887913472812702e-05,
      "loss": 0.5985,
      "step": 3202
    },
    {
      "epoch": 0.09839338924215894,
      "grad_norm": 0.3182505667209625,
      "learning_rate": 1.988784130604716e-05,
      "loss": 0.6478,
      "step": 3203
    },
    {
      "epoch": 0.0984241083771081,
      "grad_norm": 0.3574591279029846,
      "learning_rate": 1.9887769116187877e-05,
      "loss": 0.696,
      "step": 3204
    },
    {
      "epoch": 0.09845482751205727,
      "grad_norm": 0.3146666884422302,
      "learning_rate": 1.988769690323502e-05,
      "loss": 0.57,
      "step": 3205
    },
    {
      "epoch": 0.09848554664700641,
      "grad_norm": 0.33564484119415283,
      "learning_rate": 1.9887624667188755e-05,
      "loss": 0.5238,
      "step": 3206
    },
    {
      "epoch": 0.09851626578195558,
      "grad_norm": 0.3015575408935547,
      "learning_rate": 1.9887552408049253e-05,
      "loss": 0.5853,
      "step": 3207
    },
    {
      "epoch": 0.09854698491690474,
      "grad_norm": 0.3676294982433319,
      "learning_rate": 1.988748012581668e-05,
      "loss": 0.5594,
      "step": 3208
    },
    {
      "epoch": 0.0985777040518539,
      "grad_norm": 0.33213144540786743,
      "learning_rate": 1.988740782049121e-05,
      "loss": 0.6204,
      "step": 3209
    },
    {
      "epoch": 0.09860842318680306,
      "grad_norm": 0.46569740772247314,
      "learning_rate": 1.9887335492073e-05,
      "loss": 0.6253,
      "step": 3210
    },
    {
      "epoch": 0.09863914232175222,
      "grad_norm": 0.48497289419174194,
      "learning_rate": 1.9887263140562235e-05,
      "loss": 0.6403,
      "step": 3211
    },
    {
      "epoch": 0.09866986145670138,
      "grad_norm": 1.1228139400482178,
      "learning_rate": 1.9887190765959078e-05,
      "loss": 0.5504,
      "step": 3212
    },
    {
      "epoch": 0.09870058059165054,
      "grad_norm": 0.540431797504425,
      "learning_rate": 1.9887118368263692e-05,
      "loss": 0.7101,
      "step": 3213
    },
    {
      "epoch": 0.0987312997265997,
      "grad_norm": 0.32820016145706177,
      "learning_rate": 1.988704594747625e-05,
      "loss": 0.5193,
      "step": 3214
    },
    {
      "epoch": 0.09876201886154885,
      "grad_norm": 0.36457279324531555,
      "learning_rate": 1.9886973503596924e-05,
      "loss": 0.6225,
      "step": 3215
    },
    {
      "epoch": 0.09879273799649801,
      "grad_norm": 0.3551771938800812,
      "learning_rate": 1.988690103662588e-05,
      "loss": 0.6826,
      "step": 3216
    },
    {
      "epoch": 0.09882345713144718,
      "grad_norm": 0.3317866623401642,
      "learning_rate": 1.9886828546563287e-05,
      "loss": 0.5606,
      "step": 3217
    },
    {
      "epoch": 0.09885417626639634,
      "grad_norm": 0.3296241760253906,
      "learning_rate": 1.9886756033409318e-05,
      "loss": 0.6746,
      "step": 3218
    },
    {
      "epoch": 0.0988848954013455,
      "grad_norm": 0.36483967304229736,
      "learning_rate": 1.988668349716414e-05,
      "loss": 0.5625,
      "step": 3219
    },
    {
      "epoch": 0.09891561453629466,
      "grad_norm": 0.31270354986190796,
      "learning_rate": 1.9886610937827918e-05,
      "loss": 0.6376,
      "step": 3220
    },
    {
      "epoch": 0.09894633367124382,
      "grad_norm": 0.3909209668636322,
      "learning_rate": 1.988653835540083e-05,
      "loss": 0.6278,
      "step": 3221
    },
    {
      "epoch": 0.09897705280619298,
      "grad_norm": 0.40044069290161133,
      "learning_rate": 1.988646574988304e-05,
      "loss": 0.6131,
      "step": 3222
    },
    {
      "epoch": 0.09900777194114213,
      "grad_norm": 0.30838102102279663,
      "learning_rate": 1.9886393121274715e-05,
      "loss": 0.569,
      "step": 3223
    },
    {
      "epoch": 0.09903849107609129,
      "grad_norm": 0.30814129114151,
      "learning_rate": 1.9886320469576036e-05,
      "loss": 0.5982,
      "step": 3224
    },
    {
      "epoch": 0.09906921021104045,
      "grad_norm": 0.32787784934043884,
      "learning_rate": 1.988624779478716e-05,
      "loss": 0.5327,
      "step": 3225
    },
    {
      "epoch": 0.09909992934598962,
      "grad_norm": 0.3302150368690491,
      "learning_rate": 1.988617509690826e-05,
      "loss": 0.5122,
      "step": 3226
    },
    {
      "epoch": 0.09913064848093878,
      "grad_norm": 0.37652719020843506,
      "learning_rate": 1.9886102375939512e-05,
      "loss": 0.6208,
      "step": 3227
    },
    {
      "epoch": 0.09916136761588794,
      "grad_norm": 0.37248003482818604,
      "learning_rate": 1.988602963188108e-05,
      "loss": 0.6214,
      "step": 3228
    },
    {
      "epoch": 0.0991920867508371,
      "grad_norm": 0.34426459670066833,
      "learning_rate": 1.9885956864733136e-05,
      "loss": 0.6419,
      "step": 3229
    },
    {
      "epoch": 0.09922280588578626,
      "grad_norm": 0.3469007909297943,
      "learning_rate": 1.9885884074495848e-05,
      "loss": 0.5561,
      "step": 3230
    },
    {
      "epoch": 0.09925352502073542,
      "grad_norm": 0.3551928997039795,
      "learning_rate": 1.9885811261169387e-05,
      "loss": 0.5981,
      "step": 3231
    },
    {
      "epoch": 0.09928424415568457,
      "grad_norm": 0.3593151271343231,
      "learning_rate": 1.9885738424753923e-05,
      "loss": 0.6381,
      "step": 3232
    },
    {
      "epoch": 0.09931496329063373,
      "grad_norm": 0.35658353567123413,
      "learning_rate": 1.988566556524963e-05,
      "loss": 0.6341,
      "step": 3233
    },
    {
      "epoch": 0.09934568242558289,
      "grad_norm": 0.36657246947288513,
      "learning_rate": 1.9885592682656673e-05,
      "loss": 0.6083,
      "step": 3234
    },
    {
      "epoch": 0.09937640156053205,
      "grad_norm": 0.33080846071243286,
      "learning_rate": 1.9885519776975225e-05,
      "loss": 0.5498,
      "step": 3235
    },
    {
      "epoch": 0.09940712069548122,
      "grad_norm": 0.34186798334121704,
      "learning_rate": 1.988544684820545e-05,
      "loss": 0.6732,
      "step": 3236
    },
    {
      "epoch": 0.09943783983043038,
      "grad_norm": 0.40575557947158813,
      "learning_rate": 1.9885373896347528e-05,
      "loss": 0.6761,
      "step": 3237
    },
    {
      "epoch": 0.09946855896537954,
      "grad_norm": 0.37897878885269165,
      "learning_rate": 1.988530092140162e-05,
      "loss": 0.6037,
      "step": 3238
    },
    {
      "epoch": 0.0994992781003287,
      "grad_norm": 0.37084636092185974,
      "learning_rate": 1.988522792336791e-05,
      "loss": 0.6208,
      "step": 3239
    },
    {
      "epoch": 0.09952999723527785,
      "grad_norm": 0.39701297879219055,
      "learning_rate": 1.9885154902246554e-05,
      "loss": 0.6201,
      "step": 3240
    },
    {
      "epoch": 0.09956071637022701,
      "grad_norm": 0.34214484691619873,
      "learning_rate": 1.988508185803773e-05,
      "loss": 0.6261,
      "step": 3241
    },
    {
      "epoch": 0.09959143550517617,
      "grad_norm": 0.4026789665222168,
      "learning_rate": 1.9885008790741603e-05,
      "loss": 0.6536,
      "step": 3242
    },
    {
      "epoch": 0.09962215464012533,
      "grad_norm": 0.35370704531669617,
      "learning_rate": 1.9884935700358353e-05,
      "loss": 0.5205,
      "step": 3243
    },
    {
      "epoch": 0.0996528737750745,
      "grad_norm": 0.31261146068573,
      "learning_rate": 1.9884862586888146e-05,
      "loss": 0.5779,
      "step": 3244
    },
    {
      "epoch": 0.09968359291002366,
      "grad_norm": 0.31941211223602295,
      "learning_rate": 1.9884789450331148e-05,
      "loss": 0.6413,
      "step": 3245
    },
    {
      "epoch": 0.09971431204497282,
      "grad_norm": 0.34385713934898376,
      "learning_rate": 1.9884716290687535e-05,
      "loss": 0.5711,
      "step": 3246
    },
    {
      "epoch": 0.09974503117992198,
      "grad_norm": 0.3420011103153229,
      "learning_rate": 1.9884643107957477e-05,
      "loss": 0.6275,
      "step": 3247
    },
    {
      "epoch": 0.09977575031487114,
      "grad_norm": 0.37562310695648193,
      "learning_rate": 1.9884569902141142e-05,
      "loss": 0.6829,
      "step": 3248
    },
    {
      "epoch": 0.09980646944982029,
      "grad_norm": 0.3496978282928467,
      "learning_rate": 1.988449667323871e-05,
      "loss": 0.5974,
      "step": 3249
    },
    {
      "epoch": 0.09983718858476945,
      "grad_norm": 0.36009493470191956,
      "learning_rate": 1.9884423421250337e-05,
      "loss": 0.5582,
      "step": 3250
    },
    {
      "epoch": 0.09986790771971861,
      "grad_norm": 0.31608545780181885,
      "learning_rate": 1.988435014617621e-05,
      "loss": 0.6193,
      "step": 3251
    },
    {
      "epoch": 0.09989862685466777,
      "grad_norm": 0.35845357179641724,
      "learning_rate": 1.988427684801649e-05,
      "loss": 0.594,
      "step": 3252
    },
    {
      "epoch": 0.09992934598961693,
      "grad_norm": 0.33128246665000916,
      "learning_rate": 1.9884203526771352e-05,
      "loss": 0.5934,
      "step": 3253
    },
    {
      "epoch": 0.0999600651245661,
      "grad_norm": 0.3620995879173279,
      "learning_rate": 1.9884130182440967e-05,
      "loss": 0.6672,
      "step": 3254
    },
    {
      "epoch": 0.09999078425951526,
      "grad_norm": 0.35481715202331543,
      "learning_rate": 1.9884056815025505e-05,
      "loss": 0.7009,
      "step": 3255
    },
    {
      "epoch": 0.10002150339446442,
      "grad_norm": 0.3524946868419647,
      "learning_rate": 1.988398342452514e-05,
      "loss": 0.5872,
      "step": 3256
    },
    {
      "epoch": 0.10005222252941358,
      "grad_norm": 0.359903484582901,
      "learning_rate": 1.988391001094004e-05,
      "loss": 0.6225,
      "step": 3257
    },
    {
      "epoch": 0.10008294166436273,
      "grad_norm": 0.30613529682159424,
      "learning_rate": 1.9883836574270374e-05,
      "loss": 0.6274,
      "step": 3258
    },
    {
      "epoch": 0.10011366079931189,
      "grad_norm": 0.36041247844696045,
      "learning_rate": 1.988376311451632e-05,
      "loss": 0.5894,
      "step": 3259
    },
    {
      "epoch": 0.10014437993426105,
      "grad_norm": 2.1787195205688477,
      "learning_rate": 1.9883689631678047e-05,
      "loss": 0.5658,
      "step": 3260
    },
    {
      "epoch": 0.10017509906921021,
      "grad_norm": 0.3624386191368103,
      "learning_rate": 1.988361612575573e-05,
      "loss": 0.6283,
      "step": 3261
    },
    {
      "epoch": 0.10020581820415937,
      "grad_norm": 0.3233952224254608,
      "learning_rate": 1.9883542596749533e-05,
      "loss": 0.5664,
      "step": 3262
    },
    {
      "epoch": 0.10023653733910853,
      "grad_norm": 0.39429712295532227,
      "learning_rate": 1.988346904465963e-05,
      "loss": 0.6253,
      "step": 3263
    },
    {
      "epoch": 0.1002672564740577,
      "grad_norm": 0.3670956790447235,
      "learning_rate": 1.98833954694862e-05,
      "loss": 0.6989,
      "step": 3264
    },
    {
      "epoch": 0.10029797560900686,
      "grad_norm": 0.3167235553264618,
      "learning_rate": 1.988332187122941e-05,
      "loss": 0.5127,
      "step": 3265
    },
    {
      "epoch": 0.100328694743956,
      "grad_norm": 0.32421088218688965,
      "learning_rate": 1.9883248249889425e-05,
      "loss": 0.6342,
      "step": 3266
    },
    {
      "epoch": 0.10035941387890517,
      "grad_norm": 0.3206900954246521,
      "learning_rate": 1.988317460546643e-05,
      "loss": 0.6364,
      "step": 3267
    },
    {
      "epoch": 0.10039013301385433,
      "grad_norm": 0.3310061991214752,
      "learning_rate": 1.988310093796059e-05,
      "loss": 0.6175,
      "step": 3268
    },
    {
      "epoch": 0.10042085214880349,
      "grad_norm": 0.4110753536224365,
      "learning_rate": 1.9883027247372076e-05,
      "loss": 0.5197,
      "step": 3269
    },
    {
      "epoch": 0.10045157128375265,
      "grad_norm": 0.34525465965270996,
      "learning_rate": 1.988295353370106e-05,
      "loss": 0.5682,
      "step": 3270
    },
    {
      "epoch": 0.10048229041870181,
      "grad_norm": 0.3513871431350708,
      "learning_rate": 1.9882879796947718e-05,
      "loss": 0.7262,
      "step": 3271
    },
    {
      "epoch": 0.10051300955365097,
      "grad_norm": 0.3012881577014923,
      "learning_rate": 1.988280603711222e-05,
      "loss": 0.6312,
      "step": 3272
    },
    {
      "epoch": 0.10054372868860013,
      "grad_norm": 0.35105040669441223,
      "learning_rate": 1.9882732254194736e-05,
      "loss": 0.5294,
      "step": 3273
    },
    {
      "epoch": 0.1005744478235493,
      "grad_norm": 0.7928096055984497,
      "learning_rate": 1.9882658448195443e-05,
      "loss": 0.6321,
      "step": 3274
    },
    {
      "epoch": 0.10060516695849844,
      "grad_norm": 0.33293625712394714,
      "learning_rate": 1.9882584619114512e-05,
      "loss": 0.5833,
      "step": 3275
    },
    {
      "epoch": 0.1006358860934476,
      "grad_norm": 0.3995696008205414,
      "learning_rate": 1.988251076695211e-05,
      "loss": 0.6682,
      "step": 3276
    },
    {
      "epoch": 0.10066660522839677,
      "grad_norm": 0.3311254382133484,
      "learning_rate": 1.9882436891708416e-05,
      "loss": 0.6126,
      "step": 3277
    },
    {
      "epoch": 0.10069732436334593,
      "grad_norm": 0.4280281960964203,
      "learning_rate": 1.9882362993383602e-05,
      "loss": 0.6563,
      "step": 3278
    },
    {
      "epoch": 0.10072804349829509,
      "grad_norm": 0.34369105100631714,
      "learning_rate": 1.988228907197784e-05,
      "loss": 0.6365,
      "step": 3279
    },
    {
      "epoch": 0.10075876263324425,
      "grad_norm": 0.3648221492767334,
      "learning_rate": 1.9882215127491298e-05,
      "loss": 0.5216,
      "step": 3280
    },
    {
      "epoch": 0.10078948176819341,
      "grad_norm": 0.3379635810852051,
      "learning_rate": 1.9882141159924153e-05,
      "loss": 0.5971,
      "step": 3281
    },
    {
      "epoch": 0.10082020090314257,
      "grad_norm": 0.350720077753067,
      "learning_rate": 1.9882067169276577e-05,
      "loss": 0.6579,
      "step": 3282
    },
    {
      "epoch": 0.10085092003809172,
      "grad_norm": 0.3155682682991028,
      "learning_rate": 1.9881993155548745e-05,
      "loss": 0.5674,
      "step": 3283
    },
    {
      "epoch": 0.10088163917304088,
      "grad_norm": 0.36580705642700195,
      "learning_rate": 1.9881919118740828e-05,
      "loss": 0.6115,
      "step": 3284
    },
    {
      "epoch": 0.10091235830799004,
      "grad_norm": 0.36517637968063354,
      "learning_rate": 1.9881845058852997e-05,
      "loss": 0.6742,
      "step": 3285
    },
    {
      "epoch": 0.1009430774429392,
      "grad_norm": 0.3886603116989136,
      "learning_rate": 1.9881770975885427e-05,
      "loss": 0.6219,
      "step": 3286
    },
    {
      "epoch": 0.10097379657788837,
      "grad_norm": 0.34510332345962524,
      "learning_rate": 1.9881696869838292e-05,
      "loss": 0.5408,
      "step": 3287
    },
    {
      "epoch": 0.10100451571283753,
      "grad_norm": 0.3264683485031128,
      "learning_rate": 1.9881622740711765e-05,
      "loss": 0.6292,
      "step": 3288
    },
    {
      "epoch": 0.10103523484778669,
      "grad_norm": 0.3278883397579193,
      "learning_rate": 1.9881548588506017e-05,
      "loss": 0.6179,
      "step": 3289
    },
    {
      "epoch": 0.10106595398273585,
      "grad_norm": 0.34580516815185547,
      "learning_rate": 1.988147441322122e-05,
      "loss": 0.5821,
      "step": 3290
    },
    {
      "epoch": 0.10109667311768501,
      "grad_norm": 0.3468242883682251,
      "learning_rate": 1.988140021485755e-05,
      "loss": 0.6418,
      "step": 3291
    },
    {
      "epoch": 0.10112739225263416,
      "grad_norm": 0.3375232219696045,
      "learning_rate": 1.9881325993415183e-05,
      "loss": 0.6242,
      "step": 3292
    },
    {
      "epoch": 0.10115811138758332,
      "grad_norm": 0.4066527187824249,
      "learning_rate": 1.9881251748894285e-05,
      "loss": 0.5861,
      "step": 3293
    },
    {
      "epoch": 0.10118883052253248,
      "grad_norm": 0.34245970845222473,
      "learning_rate": 1.9881177481295033e-05,
      "loss": 0.5271,
      "step": 3294
    },
    {
      "epoch": 0.10121954965748164,
      "grad_norm": 0.33548909425735474,
      "learning_rate": 1.9881103190617602e-05,
      "loss": 0.568,
      "step": 3295
    },
    {
      "epoch": 0.1012502687924308,
      "grad_norm": 0.3868129849433899,
      "learning_rate": 1.9881028876862166e-05,
      "loss": 0.6104,
      "step": 3296
    },
    {
      "epoch": 0.10128098792737997,
      "grad_norm": 0.48436084389686584,
      "learning_rate": 1.9880954540028897e-05,
      "loss": 0.7015,
      "step": 3297
    },
    {
      "epoch": 0.10131170706232913,
      "grad_norm": 0.322892963886261,
      "learning_rate": 1.9880880180117968e-05,
      "loss": 0.5548,
      "step": 3298
    },
    {
      "epoch": 0.10134242619727829,
      "grad_norm": 0.3423095643520355,
      "learning_rate": 1.9880805797129552e-05,
      "loss": 0.6441,
      "step": 3299
    },
    {
      "epoch": 0.10137314533222744,
      "grad_norm": 0.3243393301963806,
      "learning_rate": 1.9880731391063825e-05,
      "loss": 0.5787,
      "step": 3300
    },
    {
      "epoch": 0.1014038644671766,
      "grad_norm": 0.4149682819843292,
      "learning_rate": 1.988065696192096e-05,
      "loss": 0.6298,
      "step": 3301
    },
    {
      "epoch": 0.10143458360212576,
      "grad_norm": 0.31153905391693115,
      "learning_rate": 1.988058250970113e-05,
      "loss": 0.5146,
      "step": 3302
    },
    {
      "epoch": 0.10146530273707492,
      "grad_norm": 0.33997583389282227,
      "learning_rate": 1.9880508034404512e-05,
      "loss": 0.6519,
      "step": 3303
    },
    {
      "epoch": 0.10149602187202408,
      "grad_norm": 0.40162330865859985,
      "learning_rate": 1.9880433536031272e-05,
      "loss": 0.5912,
      "step": 3304
    },
    {
      "epoch": 0.10152674100697325,
      "grad_norm": 0.37630707025527954,
      "learning_rate": 1.9880359014581592e-05,
      "loss": 0.6958,
      "step": 3305
    },
    {
      "epoch": 0.1015574601419224,
      "grad_norm": 0.38757815957069397,
      "learning_rate": 1.9880284470055645e-05,
      "loss": 0.6432,
      "step": 3306
    },
    {
      "epoch": 0.10158817927687157,
      "grad_norm": 0.3097861707210541,
      "learning_rate": 1.9880209902453606e-05,
      "loss": 0.5675,
      "step": 3307
    },
    {
      "epoch": 0.10161889841182073,
      "grad_norm": 0.32999154925346375,
      "learning_rate": 1.9880135311775642e-05,
      "loss": 0.661,
      "step": 3308
    },
    {
      "epoch": 0.10164961754676988,
      "grad_norm": 0.3612196147441864,
      "learning_rate": 1.9880060698021936e-05,
      "loss": 0.6672,
      "step": 3309
    },
    {
      "epoch": 0.10168033668171904,
      "grad_norm": 0.3236655592918396,
      "learning_rate": 1.9879986061192653e-05,
      "loss": 0.5548,
      "step": 3310
    },
    {
      "epoch": 0.1017110558166682,
      "grad_norm": 0.37208595871925354,
      "learning_rate": 1.9879911401287977e-05,
      "loss": 0.5669,
      "step": 3311
    },
    {
      "epoch": 0.10174177495161736,
      "grad_norm": 0.3480599522590637,
      "learning_rate": 1.9879836718308074e-05,
      "loss": 0.6682,
      "step": 3312
    },
    {
      "epoch": 0.10177249408656652,
      "grad_norm": 0.3658190369606018,
      "learning_rate": 1.9879762012253126e-05,
      "loss": 0.6547,
      "step": 3313
    },
    {
      "epoch": 0.10180321322151568,
      "grad_norm": 0.32774636149406433,
      "learning_rate": 1.98796872831233e-05,
      "loss": 0.5839,
      "step": 3314
    },
    {
      "epoch": 0.10183393235646485,
      "grad_norm": 0.34338146448135376,
      "learning_rate": 1.9879612530918776e-05,
      "loss": 0.6209,
      "step": 3315
    },
    {
      "epoch": 0.10186465149141401,
      "grad_norm": 0.3632097542285919,
      "learning_rate": 1.9879537755639728e-05,
      "loss": 0.6339,
      "step": 3316
    },
    {
      "epoch": 0.10189537062636315,
      "grad_norm": 0.46870946884155273,
      "learning_rate": 1.9879462957286335e-05,
      "loss": 0.6167,
      "step": 3317
    },
    {
      "epoch": 0.10192608976131232,
      "grad_norm": 0.3515945374965668,
      "learning_rate": 1.9879388135858757e-05,
      "loss": 0.6847,
      "step": 3318
    },
    {
      "epoch": 0.10195680889626148,
      "grad_norm": 0.326180636882782,
      "learning_rate": 1.9879313291357182e-05,
      "loss": 0.6072,
      "step": 3319
    },
    {
      "epoch": 0.10198752803121064,
      "grad_norm": 0.33071663975715637,
      "learning_rate": 1.987923842378178e-05,
      "loss": 0.5917,
      "step": 3320
    },
    {
      "epoch": 0.1020182471661598,
      "grad_norm": 0.32090839743614197,
      "learning_rate": 1.9879163533132728e-05,
      "loss": 0.5661,
      "step": 3321
    },
    {
      "epoch": 0.10204896630110896,
      "grad_norm": 0.32336312532424927,
      "learning_rate": 1.9879088619410195e-05,
      "loss": 0.5408,
      "step": 3322
    },
    {
      "epoch": 0.10207968543605812,
      "grad_norm": 0.3294239342212677,
      "learning_rate": 1.9879013682614368e-05,
      "loss": 0.635,
      "step": 3323
    },
    {
      "epoch": 0.10211040457100728,
      "grad_norm": 0.30902040004730225,
      "learning_rate": 1.987893872274541e-05,
      "loss": 0.6282,
      "step": 3324
    },
    {
      "epoch": 0.10214112370595645,
      "grad_norm": 0.3844924569129944,
      "learning_rate": 1.98788637398035e-05,
      "loss": 0.584,
      "step": 3325
    },
    {
      "epoch": 0.1021718428409056,
      "grad_norm": 0.3408164978027344,
      "learning_rate": 1.9878788733788817e-05,
      "loss": 0.6256,
      "step": 3326
    },
    {
      "epoch": 0.10220256197585476,
      "grad_norm": 0.3339153230190277,
      "learning_rate": 1.987871370470153e-05,
      "loss": 0.5468,
      "step": 3327
    },
    {
      "epoch": 0.10223328111080392,
      "grad_norm": 0.3190523386001587,
      "learning_rate": 1.9878638652541823e-05,
      "loss": 0.5836,
      "step": 3328
    },
    {
      "epoch": 0.10226400024575308,
      "grad_norm": 0.33561238646507263,
      "learning_rate": 1.9878563577309856e-05,
      "loss": 0.6093,
      "step": 3329
    },
    {
      "epoch": 0.10229471938070224,
      "grad_norm": 0.3750517964363098,
      "learning_rate": 1.987848847900582e-05,
      "loss": 0.5633,
      "step": 3330
    },
    {
      "epoch": 0.1023254385156514,
      "grad_norm": 0.4086240530014038,
      "learning_rate": 1.9878413357629885e-05,
      "loss": 0.5474,
      "step": 3331
    },
    {
      "epoch": 0.10235615765060056,
      "grad_norm": 0.41579195857048035,
      "learning_rate": 1.987833821318222e-05,
      "loss": 0.5946,
      "step": 3332
    },
    {
      "epoch": 0.10238687678554972,
      "grad_norm": 0.3820441663265228,
      "learning_rate": 1.9878263045663012e-05,
      "loss": 0.5846,
      "step": 3333
    },
    {
      "epoch": 0.10241759592049889,
      "grad_norm": 0.3447595238685608,
      "learning_rate": 1.987818785507243e-05,
      "loss": 0.6691,
      "step": 3334
    },
    {
      "epoch": 0.10244831505544803,
      "grad_norm": 0.36575114727020264,
      "learning_rate": 1.987811264141065e-05,
      "loss": 0.6293,
      "step": 3335
    },
    {
      "epoch": 0.1024790341903972,
      "grad_norm": 0.3342439532279968,
      "learning_rate": 1.9878037404677847e-05,
      "loss": 0.5907,
      "step": 3336
    },
    {
      "epoch": 0.10250975332534636,
      "grad_norm": 0.41989102959632874,
      "learning_rate": 1.98779621448742e-05,
      "loss": 0.6735,
      "step": 3337
    },
    {
      "epoch": 0.10254047246029552,
      "grad_norm": 0.366451621055603,
      "learning_rate": 1.9877886861999877e-05,
      "loss": 0.5885,
      "step": 3338
    },
    {
      "epoch": 0.10257119159524468,
      "grad_norm": 0.35216495394706726,
      "learning_rate": 1.9877811556055064e-05,
      "loss": 0.6258,
      "step": 3339
    },
    {
      "epoch": 0.10260191073019384,
      "grad_norm": 0.3150026500225067,
      "learning_rate": 1.987773622703993e-05,
      "loss": 0.5848,
      "step": 3340
    },
    {
      "epoch": 0.102632629865143,
      "grad_norm": 0.32018280029296875,
      "learning_rate": 1.9877660874954655e-05,
      "loss": 0.5679,
      "step": 3341
    },
    {
      "epoch": 0.10266334900009216,
      "grad_norm": 0.3118934631347656,
      "learning_rate": 1.9877585499799414e-05,
      "loss": 0.5957,
      "step": 3342
    },
    {
      "epoch": 0.10269406813504131,
      "grad_norm": 0.6014252305030823,
      "learning_rate": 1.987751010157438e-05,
      "loss": 0.6404,
      "step": 3343
    },
    {
      "epoch": 0.10272478726999047,
      "grad_norm": 0.3465321958065033,
      "learning_rate": 1.9877434680279736e-05,
      "loss": 0.6414,
      "step": 3344
    },
    {
      "epoch": 0.10275550640493963,
      "grad_norm": 0.33455878496170044,
      "learning_rate": 1.987735923591565e-05,
      "loss": 0.5236,
      "step": 3345
    },
    {
      "epoch": 0.1027862255398888,
      "grad_norm": 0.4493517279624939,
      "learning_rate": 1.9877283768482297e-05,
      "loss": 0.6782,
      "step": 3346
    },
    {
      "epoch": 0.10281694467483796,
      "grad_norm": 0.33761411905288696,
      "learning_rate": 1.9877208277979864e-05,
      "loss": 0.6519,
      "step": 3347
    },
    {
      "epoch": 0.10284766380978712,
      "grad_norm": 0.3426732122898102,
      "learning_rate": 1.987713276440852e-05,
      "loss": 0.5677,
      "step": 3348
    },
    {
      "epoch": 0.10287838294473628,
      "grad_norm": 0.3466872274875641,
      "learning_rate": 1.9877057227768442e-05,
      "loss": 0.6554,
      "step": 3349
    },
    {
      "epoch": 0.10290910207968544,
      "grad_norm": 0.36354297399520874,
      "learning_rate": 1.9876981668059806e-05,
      "loss": 0.6212,
      "step": 3350
    },
    {
      "epoch": 0.1029398212146346,
      "grad_norm": 0.33885109424591064,
      "learning_rate": 1.9876906085282793e-05,
      "loss": 0.5397,
      "step": 3351
    },
    {
      "epoch": 0.10297054034958375,
      "grad_norm": 0.32476162910461426,
      "learning_rate": 1.9876830479437573e-05,
      "loss": 0.723,
      "step": 3352
    },
    {
      "epoch": 0.10300125948453291,
      "grad_norm": 0.33648350834846497,
      "learning_rate": 1.9876754850524326e-05,
      "loss": 0.6803,
      "step": 3353
    },
    {
      "epoch": 0.10303197861948207,
      "grad_norm": 0.3188552260398865,
      "learning_rate": 1.9876679198543227e-05,
      "loss": 0.5922,
      "step": 3354
    },
    {
      "epoch": 0.10306269775443123,
      "grad_norm": 0.581777036190033,
      "learning_rate": 1.9876603523494456e-05,
      "loss": 0.6327,
      "step": 3355
    },
    {
      "epoch": 0.1030934168893804,
      "grad_norm": 0.3482327461242676,
      "learning_rate": 1.987652782537819e-05,
      "loss": 0.5821,
      "step": 3356
    },
    {
      "epoch": 0.10312413602432956,
      "grad_norm": 0.4128420054912567,
      "learning_rate": 1.9876452104194597e-05,
      "loss": 0.7026,
      "step": 3357
    },
    {
      "epoch": 0.10315485515927872,
      "grad_norm": 0.35158807039260864,
      "learning_rate": 1.9876376359943865e-05,
      "loss": 0.6654,
      "step": 3358
    },
    {
      "epoch": 0.10318557429422788,
      "grad_norm": 0.34143081307411194,
      "learning_rate": 1.9876300592626166e-05,
      "loss": 0.5736,
      "step": 3359
    },
    {
      "epoch": 0.10321629342917703,
      "grad_norm": 0.33089399337768555,
      "learning_rate": 1.9876224802241676e-05,
      "loss": 0.5224,
      "step": 3360
    },
    {
      "epoch": 0.10324701256412619,
      "grad_norm": 0.32293233275413513,
      "learning_rate": 1.9876148988790574e-05,
      "loss": 0.6484,
      "step": 3361
    },
    {
      "epoch": 0.10327773169907535,
      "grad_norm": 0.34166866540908813,
      "learning_rate": 1.9876073152273038e-05,
      "loss": 0.6567,
      "step": 3362
    },
    {
      "epoch": 0.10330845083402451,
      "grad_norm": 0.353118896484375,
      "learning_rate": 1.987599729268924e-05,
      "loss": 0.6478,
      "step": 3363
    },
    {
      "epoch": 0.10333916996897367,
      "grad_norm": 0.3449006676673889,
      "learning_rate": 1.9875921410039364e-05,
      "loss": 0.5923,
      "step": 3364
    },
    {
      "epoch": 0.10336988910392284,
      "grad_norm": 0.3197091817855835,
      "learning_rate": 1.987584550432358e-05,
      "loss": 0.6435,
      "step": 3365
    },
    {
      "epoch": 0.103400608238872,
      "grad_norm": 0.3524058163166046,
      "learning_rate": 1.987576957554207e-05,
      "loss": 0.581,
      "step": 3366
    },
    {
      "epoch": 0.10343132737382116,
      "grad_norm": 0.35161375999450684,
      "learning_rate": 1.9875693623695012e-05,
      "loss": 0.5951,
      "step": 3367
    },
    {
      "epoch": 0.10346204650877032,
      "grad_norm": 0.3134300112724304,
      "learning_rate": 1.9875617648782582e-05,
      "loss": 0.6118,
      "step": 3368
    },
    {
      "epoch": 0.10349276564371947,
      "grad_norm": 0.3463611900806427,
      "learning_rate": 1.9875541650804956e-05,
      "loss": 0.681,
      "step": 3369
    },
    {
      "epoch": 0.10352348477866863,
      "grad_norm": 0.3985813558101654,
      "learning_rate": 1.9875465629762316e-05,
      "loss": 0.7398,
      "step": 3370
    },
    {
      "epoch": 0.10355420391361779,
      "grad_norm": 0.32477596402168274,
      "learning_rate": 1.9875389585654832e-05,
      "loss": 0.7319,
      "step": 3371
    },
    {
      "epoch": 0.10358492304856695,
      "grad_norm": 0.3299289643764496,
      "learning_rate": 1.9875313518482685e-05,
      "loss": 0.6276,
      "step": 3372
    },
    {
      "epoch": 0.10361564218351611,
      "grad_norm": 0.3683394491672516,
      "learning_rate": 1.987523742824606e-05,
      "loss": 0.6059,
      "step": 3373
    },
    {
      "epoch": 0.10364636131846527,
      "grad_norm": 0.32284900546073914,
      "learning_rate": 1.987516131494512e-05,
      "loss": 0.5808,
      "step": 3374
    },
    {
      "epoch": 0.10367708045341444,
      "grad_norm": 0.32530537247657776,
      "learning_rate": 1.987508517858006e-05,
      "loss": 0.5979,
      "step": 3375
    },
    {
      "epoch": 0.1037077995883636,
      "grad_norm": 0.32396018505096436,
      "learning_rate": 1.9875009019151042e-05,
      "loss": 0.6183,
      "step": 3376
    },
    {
      "epoch": 0.10373851872331274,
      "grad_norm": 0.3267766535282135,
      "learning_rate": 1.9874932836658253e-05,
      "loss": 0.6234,
      "step": 3377
    },
    {
      "epoch": 0.1037692378582619,
      "grad_norm": 0.3189561069011688,
      "learning_rate": 1.987485663110187e-05,
      "loss": 0.6315,
      "step": 3378
    },
    {
      "epoch": 0.10379995699321107,
      "grad_norm": 0.3408612906932831,
      "learning_rate": 1.987478040248207e-05,
      "loss": 0.6152,
      "step": 3379
    },
    {
      "epoch": 0.10383067612816023,
      "grad_norm": 0.41029730439186096,
      "learning_rate": 1.9874704150799026e-05,
      "loss": 0.6367,
      "step": 3380
    },
    {
      "epoch": 0.10386139526310939,
      "grad_norm": 0.3840169906616211,
      "learning_rate": 1.9874627876052924e-05,
      "loss": 0.6051,
      "step": 3381
    },
    {
      "epoch": 0.10389211439805855,
      "grad_norm": 0.361579030752182,
      "learning_rate": 1.9874551578243942e-05,
      "loss": 0.6481,
      "step": 3382
    },
    {
      "epoch": 0.10392283353300771,
      "grad_norm": 0.383648544549942,
      "learning_rate": 1.987447525737225e-05,
      "loss": 0.6965,
      "step": 3383
    },
    {
      "epoch": 0.10395355266795687,
      "grad_norm": 0.37728843092918396,
      "learning_rate": 1.9874398913438035e-05,
      "loss": 0.6193,
      "step": 3384
    },
    {
      "epoch": 0.10398427180290604,
      "grad_norm": 0.3863455057144165,
      "learning_rate": 1.987432254644147e-05,
      "loss": 0.6267,
      "step": 3385
    },
    {
      "epoch": 0.10401499093785518,
      "grad_norm": 0.3271351456642151,
      "learning_rate": 1.9874246156382736e-05,
      "loss": 0.6049,
      "step": 3386
    },
    {
      "epoch": 0.10404571007280435,
      "grad_norm": 0.34353017807006836,
      "learning_rate": 1.987416974326201e-05,
      "loss": 0.6014,
      "step": 3387
    },
    {
      "epoch": 0.1040764292077535,
      "grad_norm": 0.35475918650627136,
      "learning_rate": 1.9874093307079473e-05,
      "loss": 0.529,
      "step": 3388
    },
    {
      "epoch": 0.10410714834270267,
      "grad_norm": 0.38387593626976013,
      "learning_rate": 1.9874016847835298e-05,
      "loss": 0.696,
      "step": 3389
    },
    {
      "epoch": 0.10413786747765183,
      "grad_norm": 0.3422696888446808,
      "learning_rate": 1.9873940365529668e-05,
      "loss": 0.5813,
      "step": 3390
    },
    {
      "epoch": 0.10416858661260099,
      "grad_norm": 0.35487478971481323,
      "learning_rate": 1.9873863860162763e-05,
      "loss": 0.6172,
      "step": 3391
    },
    {
      "epoch": 0.10419930574755015,
      "grad_norm": 0.3138427734375,
      "learning_rate": 1.9873787331734755e-05,
      "loss": 0.655,
      "step": 3392
    },
    {
      "epoch": 0.10423002488249931,
      "grad_norm": 0.4507734775543213,
      "learning_rate": 1.987371078024583e-05,
      "loss": 0.6574,
      "step": 3393
    },
    {
      "epoch": 0.10426074401744846,
      "grad_norm": 0.4047156274318695,
      "learning_rate": 1.9873634205696163e-05,
      "loss": 0.5948,
      "step": 3394
    },
    {
      "epoch": 0.10429146315239762,
      "grad_norm": 0.3993381857872009,
      "learning_rate": 1.9873557608085937e-05,
      "loss": 0.6764,
      "step": 3395
    },
    {
      "epoch": 0.10432218228734678,
      "grad_norm": 0.385838121175766,
      "learning_rate": 1.9873480987415323e-05,
      "loss": 0.7104,
      "step": 3396
    },
    {
      "epoch": 0.10435290142229595,
      "grad_norm": 0.3451135456562042,
      "learning_rate": 1.987340434368451e-05,
      "loss": 0.6599,
      "step": 3397
    },
    {
      "epoch": 0.10438362055724511,
      "grad_norm": 0.3311775326728821,
      "learning_rate": 1.9873327676893666e-05,
      "loss": 0.6212,
      "step": 3398
    },
    {
      "epoch": 0.10441433969219427,
      "grad_norm": 0.36715981364250183,
      "learning_rate": 1.987325098704298e-05,
      "loss": 0.7158,
      "step": 3399
    },
    {
      "epoch": 0.10444505882714343,
      "grad_norm": 0.3411772549152374,
      "learning_rate": 1.9873174274132622e-05,
      "loss": 0.6217,
      "step": 3400
    },
    {
      "epoch": 0.10447577796209259,
      "grad_norm": 0.32418715953826904,
      "learning_rate": 1.987309753816278e-05,
      "loss": 0.6127,
      "step": 3401
    },
    {
      "epoch": 0.10450649709704175,
      "grad_norm": 0.32916319370269775,
      "learning_rate": 1.9873020779133626e-05,
      "loss": 0.7133,
      "step": 3402
    },
    {
      "epoch": 0.1045372162319909,
      "grad_norm": 0.3439186215400696,
      "learning_rate": 1.9872943997045344e-05,
      "loss": 0.5625,
      "step": 3403
    },
    {
      "epoch": 0.10456793536694006,
      "grad_norm": 0.3174929916858673,
      "learning_rate": 1.9872867191898113e-05,
      "loss": 0.5709,
      "step": 3404
    },
    {
      "epoch": 0.10459865450188922,
      "grad_norm": 0.3424277901649475,
      "learning_rate": 1.987279036369211e-05,
      "loss": 0.6184,
      "step": 3405
    },
    {
      "epoch": 0.10462937363683839,
      "grad_norm": 0.5531808137893677,
      "learning_rate": 1.9872713512427516e-05,
      "loss": 0.5988,
      "step": 3406
    },
    {
      "epoch": 0.10466009277178755,
      "grad_norm": 0.3487642705440521,
      "learning_rate": 1.9872636638104507e-05,
      "loss": 0.6398,
      "step": 3407
    },
    {
      "epoch": 0.10469081190673671,
      "grad_norm": 0.3647867739200592,
      "learning_rate": 1.9872559740723273e-05,
      "loss": 0.6844,
      "step": 3408
    },
    {
      "epoch": 0.10472153104168587,
      "grad_norm": 0.32465678453445435,
      "learning_rate": 1.987248282028398e-05,
      "loss": 0.6036,
      "step": 3409
    },
    {
      "epoch": 0.10475225017663503,
      "grad_norm": 0.33469387888908386,
      "learning_rate": 1.9872405876786813e-05,
      "loss": 0.6385,
      "step": 3410
    },
    {
      "epoch": 0.10478296931158419,
      "grad_norm": 0.2913793921470642,
      "learning_rate": 1.987232891023196e-05,
      "loss": 0.6037,
      "step": 3411
    },
    {
      "epoch": 0.10481368844653334,
      "grad_norm": 0.33242788910865784,
      "learning_rate": 1.9872251920619584e-05,
      "loss": 0.5973,
      "step": 3412
    },
    {
      "epoch": 0.1048444075814825,
      "grad_norm": 0.3290729820728302,
      "learning_rate": 1.987217490794988e-05,
      "loss": 0.5715,
      "step": 3413
    },
    {
      "epoch": 0.10487512671643166,
      "grad_norm": 0.3005902171134949,
      "learning_rate": 1.987209787222302e-05,
      "loss": 0.5634,
      "step": 3414
    },
    {
      "epoch": 0.10490584585138082,
      "grad_norm": 0.3476839065551758,
      "learning_rate": 1.9872020813439187e-05,
      "loss": 0.5947,
      "step": 3415
    },
    {
      "epoch": 0.10493656498632999,
      "grad_norm": 0.3725834786891937,
      "learning_rate": 1.987194373159856e-05,
      "loss": 0.5858,
      "step": 3416
    },
    {
      "epoch": 0.10496728412127915,
      "grad_norm": 0.36059942841529846,
      "learning_rate": 1.987186662670132e-05,
      "loss": 0.5783,
      "step": 3417
    },
    {
      "epoch": 0.10499800325622831,
      "grad_norm": 0.40658167004585266,
      "learning_rate": 1.9871789498747645e-05,
      "loss": 0.6011,
      "step": 3418
    },
    {
      "epoch": 0.10502872239117747,
      "grad_norm": 0.3487873673439026,
      "learning_rate": 1.9871712347737716e-05,
      "loss": 0.6177,
      "step": 3419
    },
    {
      "epoch": 0.10505944152612662,
      "grad_norm": 0.4027774930000305,
      "learning_rate": 1.9871635173671712e-05,
      "loss": 0.7066,
      "step": 3420
    },
    {
      "epoch": 0.10509016066107578,
      "grad_norm": 0.3590320646762848,
      "learning_rate": 1.9871557976549815e-05,
      "loss": 0.6498,
      "step": 3421
    },
    {
      "epoch": 0.10512087979602494,
      "grad_norm": 0.3469177484512329,
      "learning_rate": 1.9871480756372205e-05,
      "loss": 0.5918,
      "step": 3422
    },
    {
      "epoch": 0.1051515989309741,
      "grad_norm": 0.3012349605560303,
      "learning_rate": 1.9871403513139064e-05,
      "loss": 0.6022,
      "step": 3423
    },
    {
      "epoch": 0.10518231806592326,
      "grad_norm": 0.3203411400318146,
      "learning_rate": 1.987132624685057e-05,
      "loss": 0.6126,
      "step": 3424
    },
    {
      "epoch": 0.10521303720087243,
      "grad_norm": 0.45684704184532166,
      "learning_rate": 1.9871248957506903e-05,
      "loss": 0.5836,
      "step": 3425
    },
    {
      "epoch": 0.10524375633582159,
      "grad_norm": 0.41580966114997864,
      "learning_rate": 1.9871171645108246e-05,
      "loss": 0.719,
      "step": 3426
    },
    {
      "epoch": 0.10527447547077075,
      "grad_norm": 0.3926449716091156,
      "learning_rate": 1.9871094309654778e-05,
      "loss": 0.6042,
      "step": 3427
    },
    {
      "epoch": 0.10530519460571991,
      "grad_norm": 0.3490860164165497,
      "learning_rate": 1.987101695114668e-05,
      "loss": 0.6156,
      "step": 3428
    },
    {
      "epoch": 0.10533591374066906,
      "grad_norm": 0.330984503030777,
      "learning_rate": 1.9870939569584134e-05,
      "loss": 0.6573,
      "step": 3429
    },
    {
      "epoch": 0.10536663287561822,
      "grad_norm": 0.32824939489364624,
      "learning_rate": 1.9870862164967316e-05,
      "loss": 0.6282,
      "step": 3430
    },
    {
      "epoch": 0.10539735201056738,
      "grad_norm": 0.33163386583328247,
      "learning_rate": 1.987078473729641e-05,
      "loss": 0.6184,
      "step": 3431
    },
    {
      "epoch": 0.10542807114551654,
      "grad_norm": 0.34851354360580444,
      "learning_rate": 1.9870707286571597e-05,
      "loss": 0.6521,
      "step": 3432
    },
    {
      "epoch": 0.1054587902804657,
      "grad_norm": 0.3479584753513336,
      "learning_rate": 1.9870629812793062e-05,
      "loss": 0.6575,
      "step": 3433
    },
    {
      "epoch": 0.10548950941541486,
      "grad_norm": 0.315220445394516,
      "learning_rate": 1.9870552315960977e-05,
      "loss": 0.5467,
      "step": 3434
    },
    {
      "epoch": 0.10552022855036403,
      "grad_norm": 0.3071170151233673,
      "learning_rate": 1.987047479607553e-05,
      "loss": 0.5982,
      "step": 3435
    },
    {
      "epoch": 0.10555094768531319,
      "grad_norm": 0.32807835936546326,
      "learning_rate": 1.9870397253136898e-05,
      "loss": 0.6025,
      "step": 3436
    },
    {
      "epoch": 0.10558166682026233,
      "grad_norm": 0.5509961843490601,
      "learning_rate": 1.9870319687145264e-05,
      "loss": 0.5788,
      "step": 3437
    },
    {
      "epoch": 0.1056123859552115,
      "grad_norm": 0.31846436858177185,
      "learning_rate": 1.9870242098100815e-05,
      "loss": 0.5586,
      "step": 3438
    },
    {
      "epoch": 0.10564310509016066,
      "grad_norm": 0.3222493827342987,
      "learning_rate": 1.9870164486003717e-05,
      "loss": 0.5762,
      "step": 3439
    },
    {
      "epoch": 0.10567382422510982,
      "grad_norm": 0.41203203797340393,
      "learning_rate": 1.9870086850854167e-05,
      "loss": 0.5826,
      "step": 3440
    },
    {
      "epoch": 0.10570454336005898,
      "grad_norm": 0.3611575663089752,
      "learning_rate": 1.9870009192652337e-05,
      "loss": 0.6272,
      "step": 3441
    },
    {
      "epoch": 0.10573526249500814,
      "grad_norm": 0.33497780561447144,
      "learning_rate": 1.986993151139841e-05,
      "loss": 0.6324,
      "step": 3442
    },
    {
      "epoch": 0.1057659816299573,
      "grad_norm": 0.32794028520584106,
      "learning_rate": 1.9869853807092575e-05,
      "loss": 0.6106,
      "step": 3443
    },
    {
      "epoch": 0.10579670076490647,
      "grad_norm": 0.3575765788555145,
      "learning_rate": 1.9869776079735e-05,
      "loss": 0.6867,
      "step": 3444
    },
    {
      "epoch": 0.10582741989985563,
      "grad_norm": 0.3414032459259033,
      "learning_rate": 1.9869698329325876e-05,
      "loss": 0.5478,
      "step": 3445
    },
    {
      "epoch": 0.10585813903480477,
      "grad_norm": 0.36993423104286194,
      "learning_rate": 1.9869620555865384e-05,
      "loss": 0.6368,
      "step": 3446
    },
    {
      "epoch": 0.10588885816975394,
      "grad_norm": 0.3795616924762726,
      "learning_rate": 1.9869542759353702e-05,
      "loss": 0.6654,
      "step": 3447
    },
    {
      "epoch": 0.1059195773047031,
      "grad_norm": 0.40292730927467346,
      "learning_rate": 1.9869464939791015e-05,
      "loss": 0.6155,
      "step": 3448
    },
    {
      "epoch": 0.10595029643965226,
      "grad_norm": 0.3794935345649719,
      "learning_rate": 1.9869387097177503e-05,
      "loss": 0.604,
      "step": 3449
    },
    {
      "epoch": 0.10598101557460142,
      "grad_norm": 0.3322625160217285,
      "learning_rate": 1.9869309231513347e-05,
      "loss": 0.6315,
      "step": 3450
    },
    {
      "epoch": 0.10601173470955058,
      "grad_norm": 0.3488585948944092,
      "learning_rate": 1.986923134279873e-05,
      "loss": 0.569,
      "step": 3451
    },
    {
      "epoch": 0.10604245384449974,
      "grad_norm": 0.31652525067329407,
      "learning_rate": 1.9869153431033838e-05,
      "loss": 0.5263,
      "step": 3452
    },
    {
      "epoch": 0.1060731729794489,
      "grad_norm": 0.40059995651245117,
      "learning_rate": 1.9869075496218844e-05,
      "loss": 0.693,
      "step": 3453
    },
    {
      "epoch": 0.10610389211439805,
      "grad_norm": 0.360721230506897,
      "learning_rate": 1.9868997538353935e-05,
      "loss": 0.6356,
      "step": 3454
    },
    {
      "epoch": 0.10613461124934721,
      "grad_norm": 0.362016886472702,
      "learning_rate": 1.9868919557439295e-05,
      "loss": 0.5974,
      "step": 3455
    },
    {
      "epoch": 0.10616533038429637,
      "grad_norm": 0.3159463107585907,
      "learning_rate": 1.9868841553475103e-05,
      "loss": 0.5762,
      "step": 3456
    },
    {
      "epoch": 0.10619604951924554,
      "grad_norm": 0.3351120352745056,
      "learning_rate": 1.9868763526461542e-05,
      "loss": 0.6173,
      "step": 3457
    },
    {
      "epoch": 0.1062267686541947,
      "grad_norm": 0.37833738327026367,
      "learning_rate": 1.9868685476398798e-05,
      "loss": 0.6136,
      "step": 3458
    },
    {
      "epoch": 0.10625748778914386,
      "grad_norm": 0.35164880752563477,
      "learning_rate": 1.9868607403287047e-05,
      "loss": 0.5283,
      "step": 3459
    },
    {
      "epoch": 0.10628820692409302,
      "grad_norm": 0.34129154682159424,
      "learning_rate": 1.9868529307126473e-05,
      "loss": 0.6767,
      "step": 3460
    },
    {
      "epoch": 0.10631892605904218,
      "grad_norm": 0.38312384486198425,
      "learning_rate": 1.9868451187917265e-05,
      "loss": 0.6678,
      "step": 3461
    },
    {
      "epoch": 0.10634964519399134,
      "grad_norm": 0.339773029088974,
      "learning_rate": 1.9868373045659596e-05,
      "loss": 0.5806,
      "step": 3462
    },
    {
      "epoch": 0.10638036432894049,
      "grad_norm": 0.36767128109931946,
      "learning_rate": 1.9868294880353652e-05,
      "loss": 0.5957,
      "step": 3463
    },
    {
      "epoch": 0.10641108346388965,
      "grad_norm": 0.3161228597164154,
      "learning_rate": 1.9868216691999617e-05,
      "loss": 0.6111,
      "step": 3464
    },
    {
      "epoch": 0.10644180259883881,
      "grad_norm": 0.3610501289367676,
      "learning_rate": 1.9868138480597673e-05,
      "loss": 0.5523,
      "step": 3465
    },
    {
      "epoch": 0.10647252173378798,
      "grad_norm": 0.36486586928367615,
      "learning_rate": 1.9868060246148002e-05,
      "loss": 0.6227,
      "step": 3466
    },
    {
      "epoch": 0.10650324086873714,
      "grad_norm": 0.34363508224487305,
      "learning_rate": 1.9867981988650786e-05,
      "loss": 0.5495,
      "step": 3467
    },
    {
      "epoch": 0.1065339600036863,
      "grad_norm": 0.3732171952724457,
      "learning_rate": 1.986790370810621e-05,
      "loss": 0.567,
      "step": 3468
    },
    {
      "epoch": 0.10656467913863546,
      "grad_norm": 0.3281377851963043,
      "learning_rate": 1.9867825404514456e-05,
      "loss": 0.6404,
      "step": 3469
    },
    {
      "epoch": 0.10659539827358462,
      "grad_norm": 0.3282632529735565,
      "learning_rate": 1.9867747077875706e-05,
      "loss": 0.5971,
      "step": 3470
    },
    {
      "epoch": 0.10662611740853378,
      "grad_norm": 0.3331635892391205,
      "learning_rate": 1.9867668728190144e-05,
      "loss": 0.5716,
      "step": 3471
    },
    {
      "epoch": 0.10665683654348293,
      "grad_norm": 0.36009323596954346,
      "learning_rate": 1.9867590355457954e-05,
      "loss": 0.6278,
      "step": 3472
    },
    {
      "epoch": 0.10668755567843209,
      "grad_norm": 0.3530612885951996,
      "learning_rate": 1.9867511959679313e-05,
      "loss": 0.6058,
      "step": 3473
    },
    {
      "epoch": 0.10671827481338125,
      "grad_norm": 0.3470054268836975,
      "learning_rate": 1.9867433540854412e-05,
      "loss": 0.6318,
      "step": 3474
    },
    {
      "epoch": 0.10674899394833041,
      "grad_norm": 0.34973645210266113,
      "learning_rate": 1.9867355098983432e-05,
      "loss": 0.5766,
      "step": 3475
    },
    {
      "epoch": 0.10677971308327958,
      "grad_norm": 0.3279939293861389,
      "learning_rate": 1.9867276634066553e-05,
      "loss": 0.7215,
      "step": 3476
    },
    {
      "epoch": 0.10681043221822874,
      "grad_norm": 0.36407825350761414,
      "learning_rate": 1.986719814610396e-05,
      "loss": 0.558,
      "step": 3477
    },
    {
      "epoch": 0.1068411513531779,
      "grad_norm": 0.3348643183708191,
      "learning_rate": 1.986711963509584e-05,
      "loss": 0.5209,
      "step": 3478
    },
    {
      "epoch": 0.10687187048812706,
      "grad_norm": 0.818617582321167,
      "learning_rate": 1.986704110104237e-05,
      "loss": 0.5632,
      "step": 3479
    },
    {
      "epoch": 0.10690258962307621,
      "grad_norm": 0.514984130859375,
      "learning_rate": 1.9866962543943736e-05,
      "loss": 0.578,
      "step": 3480
    },
    {
      "epoch": 0.10693330875802537,
      "grad_norm": 0.31598973274230957,
      "learning_rate": 1.9866883963800123e-05,
      "loss": 0.6558,
      "step": 3481
    },
    {
      "epoch": 0.10696402789297453,
      "grad_norm": 0.33607158064842224,
      "learning_rate": 1.9866805360611715e-05,
      "loss": 0.5762,
      "step": 3482
    },
    {
      "epoch": 0.10699474702792369,
      "grad_norm": 0.31652718782424927,
      "learning_rate": 1.9866726734378692e-05,
      "loss": 0.5867,
      "step": 3483
    },
    {
      "epoch": 0.10702546616287285,
      "grad_norm": 0.3445282578468323,
      "learning_rate": 1.9866648085101236e-05,
      "loss": 0.6758,
      "step": 3484
    },
    {
      "epoch": 0.10705618529782202,
      "grad_norm": 0.3151656687259674,
      "learning_rate": 1.986656941277954e-05,
      "loss": 0.6869,
      "step": 3485
    },
    {
      "epoch": 0.10708690443277118,
      "grad_norm": 0.33601903915405273,
      "learning_rate": 1.986649071741378e-05,
      "loss": 0.5309,
      "step": 3486
    },
    {
      "epoch": 0.10711762356772034,
      "grad_norm": 0.4403543472290039,
      "learning_rate": 1.9866411999004143e-05,
      "loss": 0.634,
      "step": 3487
    },
    {
      "epoch": 0.1071483427026695,
      "grad_norm": 0.31385430693626404,
      "learning_rate": 1.9866333257550813e-05,
      "loss": 0.5622,
      "step": 3488
    },
    {
      "epoch": 0.10717906183761865,
      "grad_norm": 0.33242735266685486,
      "learning_rate": 1.9866254493053966e-05,
      "loss": 0.6139,
      "step": 3489
    },
    {
      "epoch": 0.10720978097256781,
      "grad_norm": 0.3707055449485779,
      "learning_rate": 1.98661757055138e-05,
      "loss": 0.5957,
      "step": 3490
    },
    {
      "epoch": 0.10724050010751697,
      "grad_norm": 0.3350510895252228,
      "learning_rate": 1.9866096894930487e-05,
      "loss": 0.552,
      "step": 3491
    },
    {
      "epoch": 0.10727121924246613,
      "grad_norm": 0.542445957660675,
      "learning_rate": 1.9866018061304218e-05,
      "loss": 0.6299,
      "step": 3492
    },
    {
      "epoch": 0.10730193837741529,
      "grad_norm": 0.37483662366867065,
      "learning_rate": 1.9865939204635173e-05,
      "loss": 0.6641,
      "step": 3493
    },
    {
      "epoch": 0.10733265751236445,
      "grad_norm": 0.32842907309532166,
      "learning_rate": 1.986586032492354e-05,
      "loss": 0.6102,
      "step": 3494
    },
    {
      "epoch": 0.10736337664731362,
      "grad_norm": 0.35350799560546875,
      "learning_rate": 1.9865781422169498e-05,
      "loss": 0.6602,
      "step": 3495
    },
    {
      "epoch": 0.10739409578226278,
      "grad_norm": 0.3558604121208191,
      "learning_rate": 1.9865702496373237e-05,
      "loss": 0.6078,
      "step": 3496
    },
    {
      "epoch": 0.10742481491721192,
      "grad_norm": 0.32265138626098633,
      "learning_rate": 1.986562354753494e-05,
      "loss": 0.6542,
      "step": 3497
    },
    {
      "epoch": 0.10745553405216109,
      "grad_norm": 0.3723835051059723,
      "learning_rate": 1.9865544575654787e-05,
      "loss": 0.6901,
      "step": 3498
    },
    {
      "epoch": 0.10748625318711025,
      "grad_norm": 0.364217072725296,
      "learning_rate": 1.9865465580732967e-05,
      "loss": 0.6273,
      "step": 3499
    },
    {
      "epoch": 0.10751697232205941,
      "grad_norm": 0.38424980640411377,
      "learning_rate": 1.9865386562769666e-05,
      "loss": 0.6146,
      "step": 3500
    },
    {
      "epoch": 0.10754769145700857,
      "grad_norm": 0.3182368874549866,
      "learning_rate": 1.9865307521765062e-05,
      "loss": 0.6384,
      "step": 3501
    },
    {
      "epoch": 0.10757841059195773,
      "grad_norm": 0.3424476981163025,
      "learning_rate": 1.9865228457719343e-05,
      "loss": 0.6097,
      "step": 3502
    },
    {
      "epoch": 0.1076091297269069,
      "grad_norm": 0.3679790198802948,
      "learning_rate": 1.9865149370632695e-05,
      "loss": 0.5779,
      "step": 3503
    },
    {
      "epoch": 0.10763984886185606,
      "grad_norm": 0.3697637617588043,
      "learning_rate": 1.9865070260505303e-05,
      "loss": 0.6273,
      "step": 3504
    },
    {
      "epoch": 0.10767056799680522,
      "grad_norm": 0.3749689757823944,
      "learning_rate": 1.986499112733735e-05,
      "loss": 0.5149,
      "step": 3505
    },
    {
      "epoch": 0.10770128713175436,
      "grad_norm": 0.35091137886047363,
      "learning_rate": 1.986491197112902e-05,
      "loss": 0.6481,
      "step": 3506
    },
    {
      "epoch": 0.10773200626670353,
      "grad_norm": 0.32427695393562317,
      "learning_rate": 1.98648327918805e-05,
      "loss": 0.6334,
      "step": 3507
    },
    {
      "epoch": 0.10776272540165269,
      "grad_norm": 0.3559042513370514,
      "learning_rate": 1.9864753589591975e-05,
      "loss": 0.5967,
      "step": 3508
    },
    {
      "epoch": 0.10779344453660185,
      "grad_norm": 0.3369046449661255,
      "learning_rate": 1.9864674364263624e-05,
      "loss": 0.5827,
      "step": 3509
    },
    {
      "epoch": 0.10782416367155101,
      "grad_norm": 0.3360154926776886,
      "learning_rate": 1.9864595115895645e-05,
      "loss": 0.6644,
      "step": 3510
    },
    {
      "epoch": 0.10785488280650017,
      "grad_norm": 0.3208048641681671,
      "learning_rate": 1.986451584448821e-05,
      "loss": 0.652,
      "step": 3511
    },
    {
      "epoch": 0.10788560194144933,
      "grad_norm": 0.3626754879951477,
      "learning_rate": 1.986443655004151e-05,
      "loss": 0.6007,
      "step": 3512
    },
    {
      "epoch": 0.1079163210763985,
      "grad_norm": 0.3851911723613739,
      "learning_rate": 1.986435723255573e-05,
      "loss": 0.5919,
      "step": 3513
    },
    {
      "epoch": 0.10794704021134764,
      "grad_norm": 0.391366571187973,
      "learning_rate": 1.9864277892031057e-05,
      "loss": 0.6019,
      "step": 3514
    },
    {
      "epoch": 0.1079777593462968,
      "grad_norm": 0.38969114422798157,
      "learning_rate": 1.9864198528467667e-05,
      "loss": 0.5993,
      "step": 3515
    },
    {
      "epoch": 0.10800847848124596,
      "grad_norm": 0.3346009850502014,
      "learning_rate": 1.986411914186576e-05,
      "loss": 0.6163,
      "step": 3516
    },
    {
      "epoch": 0.10803919761619513,
      "grad_norm": 0.36977264285087585,
      "learning_rate": 1.9864039732225514e-05,
      "loss": 0.5769,
      "step": 3517
    },
    {
      "epoch": 0.10806991675114429,
      "grad_norm": 0.3331477642059326,
      "learning_rate": 1.986396029954711e-05,
      "loss": 0.6374,
      "step": 3518
    },
    {
      "epoch": 0.10810063588609345,
      "grad_norm": 0.3944768011569977,
      "learning_rate": 1.986388084383074e-05,
      "loss": 0.6852,
      "step": 3519
    },
    {
      "epoch": 0.10813135502104261,
      "grad_norm": 0.31893298029899597,
      "learning_rate": 1.9863801365076585e-05,
      "loss": 0.623,
      "step": 3520
    },
    {
      "epoch": 0.10816207415599177,
      "grad_norm": 0.32927021384239197,
      "learning_rate": 1.9863721863284835e-05,
      "loss": 0.5849,
      "step": 3521
    },
    {
      "epoch": 0.10819279329094093,
      "grad_norm": 0.36919930577278137,
      "learning_rate": 1.9863642338455672e-05,
      "loss": 0.6387,
      "step": 3522
    },
    {
      "epoch": 0.10822351242589008,
      "grad_norm": 0.3350495398044586,
      "learning_rate": 1.9863562790589287e-05,
      "loss": 0.5441,
      "step": 3523
    },
    {
      "epoch": 0.10825423156083924,
      "grad_norm": 0.318958044052124,
      "learning_rate": 1.9863483219685856e-05,
      "loss": 0.5289,
      "step": 3524
    },
    {
      "epoch": 0.1082849506957884,
      "grad_norm": 0.3514644503593445,
      "learning_rate": 1.9863403625745578e-05,
      "loss": 0.623,
      "step": 3525
    },
    {
      "epoch": 0.10831566983073757,
      "grad_norm": 0.4432719945907593,
      "learning_rate": 1.986332400876863e-05,
      "loss": 0.7456,
      "step": 3526
    },
    {
      "epoch": 0.10834638896568673,
      "grad_norm": 0.35523155331611633,
      "learning_rate": 1.9863244368755197e-05,
      "loss": 0.6499,
      "step": 3527
    },
    {
      "epoch": 0.10837710810063589,
      "grad_norm": 0.38579124212265015,
      "learning_rate": 1.986316470570547e-05,
      "loss": 0.5339,
      "step": 3528
    },
    {
      "epoch": 0.10840782723558505,
      "grad_norm": 0.3619006872177124,
      "learning_rate": 1.9863085019619633e-05,
      "loss": 0.6466,
      "step": 3529
    },
    {
      "epoch": 0.10843854637053421,
      "grad_norm": 0.3567807972431183,
      "learning_rate": 1.9863005310497873e-05,
      "loss": 0.5561,
      "step": 3530
    },
    {
      "epoch": 0.10846926550548336,
      "grad_norm": 0.3405373990535736,
      "learning_rate": 1.9862925578340375e-05,
      "loss": 0.6747,
      "step": 3531
    },
    {
      "epoch": 0.10849998464043252,
      "grad_norm": 0.33904680609703064,
      "learning_rate": 1.9862845823147325e-05,
      "loss": 0.5627,
      "step": 3532
    },
    {
      "epoch": 0.10853070377538168,
      "grad_norm": 0.36760711669921875,
      "learning_rate": 1.9862766044918912e-05,
      "loss": 0.5824,
      "step": 3533
    },
    {
      "epoch": 0.10856142291033084,
      "grad_norm": 0.29830652475357056,
      "learning_rate": 1.9862686243655313e-05,
      "loss": 0.6683,
      "step": 3534
    },
    {
      "epoch": 0.10859214204528,
      "grad_norm": 0.4152737557888031,
      "learning_rate": 1.986260641935673e-05,
      "loss": 0.5788,
      "step": 3535
    },
    {
      "epoch": 0.10862286118022917,
      "grad_norm": 0.3278442919254303,
      "learning_rate": 1.9862526572023334e-05,
      "loss": 0.6371,
      "step": 3536
    },
    {
      "epoch": 0.10865358031517833,
      "grad_norm": 0.30844974517822266,
      "learning_rate": 1.986244670165532e-05,
      "loss": 0.5578,
      "step": 3537
    },
    {
      "epoch": 0.10868429945012749,
      "grad_norm": 0.32755953073501587,
      "learning_rate": 1.9862366808252877e-05,
      "loss": 0.5979,
      "step": 3538
    },
    {
      "epoch": 0.10871501858507665,
      "grad_norm": 0.36990633606910706,
      "learning_rate": 1.986228689181619e-05,
      "loss": 0.5197,
      "step": 3539
    },
    {
      "epoch": 0.1087457377200258,
      "grad_norm": 0.38616272807121277,
      "learning_rate": 1.9862206952345432e-05,
      "loss": 0.5922,
      "step": 3540
    },
    {
      "epoch": 0.10877645685497496,
      "grad_norm": 0.4480770230293274,
      "learning_rate": 1.986212698984081e-05,
      "loss": 0.5577,
      "step": 3541
    },
    {
      "epoch": 0.10880717598992412,
      "grad_norm": 0.3624168038368225,
      "learning_rate": 1.98620470043025e-05,
      "loss": 0.6729,
      "step": 3542
    },
    {
      "epoch": 0.10883789512487328,
      "grad_norm": 0.3767770826816559,
      "learning_rate": 1.9861966995730687e-05,
      "loss": 0.616,
      "step": 3543
    },
    {
      "epoch": 0.10886861425982244,
      "grad_norm": 0.38926181197166443,
      "learning_rate": 1.9861886964125564e-05,
      "loss": 0.6632,
      "step": 3544
    },
    {
      "epoch": 0.1088993333947716,
      "grad_norm": 0.3576256334781647,
      "learning_rate": 1.9861806909487312e-05,
      "loss": 0.6028,
      "step": 3545
    },
    {
      "epoch": 0.10893005252972077,
      "grad_norm": 0.3318727910518646,
      "learning_rate": 1.9861726831816127e-05,
      "loss": 0.6288,
      "step": 3546
    },
    {
      "epoch": 0.10896077166466993,
      "grad_norm": 0.36502209305763245,
      "learning_rate": 1.9861646731112184e-05,
      "loss": 0.68,
      "step": 3547
    },
    {
      "epoch": 0.10899149079961909,
      "grad_norm": 0.3323136866092682,
      "learning_rate": 1.986156660737568e-05,
      "loss": 0.6085,
      "step": 3548
    },
    {
      "epoch": 0.10902220993456824,
      "grad_norm": 0.3636404573917389,
      "learning_rate": 1.98614864606068e-05,
      "loss": 0.6791,
      "step": 3549
    },
    {
      "epoch": 0.1090529290695174,
      "grad_norm": 0.3158240020275116,
      "learning_rate": 1.986140629080573e-05,
      "loss": 0.5692,
      "step": 3550
    },
    {
      "epoch": 0.10908364820446656,
      "grad_norm": 0.32174256443977356,
      "learning_rate": 1.9861326097972652e-05,
      "loss": 0.5762,
      "step": 3551
    },
    {
      "epoch": 0.10911436733941572,
      "grad_norm": 0.3713470995426178,
      "learning_rate": 1.986124588210776e-05,
      "loss": 0.5883,
      "step": 3552
    },
    {
      "epoch": 0.10914508647436488,
      "grad_norm": 0.35260289907455444,
      "learning_rate": 1.9861165643211243e-05,
      "loss": 0.6054,
      "step": 3553
    },
    {
      "epoch": 0.10917580560931404,
      "grad_norm": 0.32799071073532104,
      "learning_rate": 1.986108538128328e-05,
      "loss": 0.6258,
      "step": 3554
    },
    {
      "epoch": 0.1092065247442632,
      "grad_norm": 0.3113437592983246,
      "learning_rate": 1.9861005096324067e-05,
      "loss": 0.541,
      "step": 3555
    },
    {
      "epoch": 0.10923724387921237,
      "grad_norm": 0.34527596831321716,
      "learning_rate": 1.9860924788333785e-05,
      "loss": 0.6811,
      "step": 3556
    },
    {
      "epoch": 0.10926796301416151,
      "grad_norm": 0.33286911249160767,
      "learning_rate": 1.9860844457312626e-05,
      "loss": 0.6088,
      "step": 3557
    },
    {
      "epoch": 0.10929868214911068,
      "grad_norm": 0.3324921131134033,
      "learning_rate": 1.986076410326078e-05,
      "loss": 0.6608,
      "step": 3558
    },
    {
      "epoch": 0.10932940128405984,
      "grad_norm": 0.3607599139213562,
      "learning_rate": 1.9860683726178423e-05,
      "loss": 0.5402,
      "step": 3559
    },
    {
      "epoch": 0.109360120419009,
      "grad_norm": 0.31252723932266235,
      "learning_rate": 1.9860603326065756e-05,
      "loss": 0.6396,
      "step": 3560
    },
    {
      "epoch": 0.10939083955395816,
      "grad_norm": 0.34485357999801636,
      "learning_rate": 1.986052290292296e-05,
      "loss": 0.5765,
      "step": 3561
    },
    {
      "epoch": 0.10942155868890732,
      "grad_norm": 0.45759209990501404,
      "learning_rate": 1.9860442456750223e-05,
      "loss": 0.5491,
      "step": 3562
    },
    {
      "epoch": 0.10945227782385648,
      "grad_norm": 0.3685763478279114,
      "learning_rate": 1.9860361987547735e-05,
      "loss": 0.5905,
      "step": 3563
    },
    {
      "epoch": 0.10948299695880565,
      "grad_norm": 0.37201449275016785,
      "learning_rate": 1.9860281495315684e-05,
      "loss": 0.5921,
      "step": 3564
    },
    {
      "epoch": 0.1095137160937548,
      "grad_norm": 0.34410780668258667,
      "learning_rate": 1.9860200980054257e-05,
      "loss": 0.5732,
      "step": 3565
    },
    {
      "epoch": 0.10954443522870395,
      "grad_norm": 0.34331223368644714,
      "learning_rate": 1.9860120441763638e-05,
      "loss": 0.6213,
      "step": 3566
    },
    {
      "epoch": 0.10957515436365312,
      "grad_norm": 0.5508716702461243,
      "learning_rate": 1.9860039880444023e-05,
      "loss": 0.571,
      "step": 3567
    },
    {
      "epoch": 0.10960587349860228,
      "grad_norm": 0.3191051781177521,
      "learning_rate": 1.9859959296095594e-05,
      "loss": 0.5455,
      "step": 3568
    },
    {
      "epoch": 0.10963659263355144,
      "grad_norm": 0.3307940363883972,
      "learning_rate": 1.9859878688718545e-05,
      "loss": 0.6314,
      "step": 3569
    },
    {
      "epoch": 0.1096673117685006,
      "grad_norm": 0.3467053174972534,
      "learning_rate": 1.9859798058313055e-05,
      "loss": 0.5978,
      "step": 3570
    },
    {
      "epoch": 0.10969803090344976,
      "grad_norm": 0.36862242221832275,
      "learning_rate": 1.985971740487932e-05,
      "loss": 0.5999,
      "step": 3571
    },
    {
      "epoch": 0.10972875003839892,
      "grad_norm": 0.600034773349762,
      "learning_rate": 1.985963672841753e-05,
      "loss": 0.6125,
      "step": 3572
    },
    {
      "epoch": 0.10975946917334808,
      "grad_norm": 0.3595225214958191,
      "learning_rate": 1.9859556028927868e-05,
      "loss": 0.6143,
      "step": 3573
    },
    {
      "epoch": 0.10979018830829723,
      "grad_norm": 0.3493101894855499,
      "learning_rate": 1.9859475306410523e-05,
      "loss": 0.5708,
      "step": 3574
    },
    {
      "epoch": 0.1098209074432464,
      "grad_norm": 0.3422781825065613,
      "learning_rate": 1.9859394560865687e-05,
      "loss": 0.6512,
      "step": 3575
    },
    {
      "epoch": 0.10985162657819555,
      "grad_norm": 0.3491266965866089,
      "learning_rate": 1.9859313792293545e-05,
      "loss": 0.677,
      "step": 3576
    },
    {
      "epoch": 0.10988234571314472,
      "grad_norm": 0.3646570146083832,
      "learning_rate": 1.9859233000694287e-05,
      "loss": 0.6677,
      "step": 3577
    },
    {
      "epoch": 0.10991306484809388,
      "grad_norm": 0.3285301625728607,
      "learning_rate": 1.98591521860681e-05,
      "loss": 0.5922,
      "step": 3578
    },
    {
      "epoch": 0.10994378398304304,
      "grad_norm": 0.32042428851127625,
      "learning_rate": 1.9859071348415177e-05,
      "loss": 0.6228,
      "step": 3579
    },
    {
      "epoch": 0.1099745031179922,
      "grad_norm": 0.4295864999294281,
      "learning_rate": 1.9858990487735703e-05,
      "loss": 0.6637,
      "step": 3580
    },
    {
      "epoch": 0.11000522225294136,
      "grad_norm": 0.31378769874572754,
      "learning_rate": 1.985890960402987e-05,
      "loss": 0.6695,
      "step": 3581
    },
    {
      "epoch": 0.11003594138789052,
      "grad_norm": 0.3562178313732147,
      "learning_rate": 1.985882869729786e-05,
      "loss": 0.6239,
      "step": 3582
    },
    {
      "epoch": 0.11006666052283967,
      "grad_norm": 0.3252597153186798,
      "learning_rate": 1.9858747767539873e-05,
      "loss": 0.6176,
      "step": 3583
    },
    {
      "epoch": 0.11009737965778883,
      "grad_norm": 0.40002956986427307,
      "learning_rate": 1.985866681475609e-05,
      "loss": 0.5504,
      "step": 3584
    },
    {
      "epoch": 0.110128098792738,
      "grad_norm": 0.45329511165618896,
      "learning_rate": 1.9858585838946705e-05,
      "loss": 0.5736,
      "step": 3585
    },
    {
      "epoch": 0.11015881792768716,
      "grad_norm": 0.8407210111618042,
      "learning_rate": 1.98585048401119e-05,
      "loss": 0.5832,
      "step": 3586
    },
    {
      "epoch": 0.11018953706263632,
      "grad_norm": 0.3354388475418091,
      "learning_rate": 1.985842381825187e-05,
      "loss": 0.6149,
      "step": 3587
    },
    {
      "epoch": 0.11022025619758548,
      "grad_norm": 0.32311496138572693,
      "learning_rate": 1.98583427733668e-05,
      "loss": 0.571,
      "step": 3588
    },
    {
      "epoch": 0.11025097533253464,
      "grad_norm": 0.35623839497566223,
      "learning_rate": 1.9858261705456888e-05,
      "loss": 0.5491,
      "step": 3589
    },
    {
      "epoch": 0.1102816944674838,
      "grad_norm": 0.3393486440181732,
      "learning_rate": 1.9858180614522313e-05,
      "loss": 0.6303,
      "step": 3590
    },
    {
      "epoch": 0.11031241360243295,
      "grad_norm": 0.3281818628311157,
      "learning_rate": 1.9858099500563268e-05,
      "loss": 0.5975,
      "step": 3591
    },
    {
      "epoch": 0.11034313273738211,
      "grad_norm": 0.3343569338321686,
      "learning_rate": 1.9858018363579946e-05,
      "loss": 0.5665,
      "step": 3592
    },
    {
      "epoch": 0.11037385187233127,
      "grad_norm": 0.37314268946647644,
      "learning_rate": 1.9857937203572534e-05,
      "loss": 0.5653,
      "step": 3593
    },
    {
      "epoch": 0.11040457100728043,
      "grad_norm": 0.33678436279296875,
      "learning_rate": 1.9857856020541218e-05,
      "loss": 0.575,
      "step": 3594
    },
    {
      "epoch": 0.1104352901422296,
      "grad_norm": 0.3310183584690094,
      "learning_rate": 1.985777481448619e-05,
      "loss": 0.6562,
      "step": 3595
    },
    {
      "epoch": 0.11046600927717876,
      "grad_norm": 0.35815104842185974,
      "learning_rate": 1.9857693585407643e-05,
      "loss": 0.6543,
      "step": 3596
    },
    {
      "epoch": 0.11049672841212792,
      "grad_norm": 0.3451935946941376,
      "learning_rate": 1.9857612333305764e-05,
      "loss": 0.6392,
      "step": 3597
    },
    {
      "epoch": 0.11052744754707708,
      "grad_norm": 0.3795121908187866,
      "learning_rate": 1.9857531058180744e-05,
      "loss": 0.6157,
      "step": 3598
    },
    {
      "epoch": 0.11055816668202624,
      "grad_norm": 0.44748643040657043,
      "learning_rate": 1.9857449760032768e-05,
      "loss": 0.6165,
      "step": 3599
    },
    {
      "epoch": 0.11058888581697539,
      "grad_norm": 0.3774811029434204,
      "learning_rate": 1.9857368438862034e-05,
      "loss": 0.592,
      "step": 3600
    },
    {
      "epoch": 0.11061960495192455,
      "grad_norm": 0.7576661109924316,
      "learning_rate": 1.9857287094668727e-05,
      "loss": 0.6334,
      "step": 3601
    },
    {
      "epoch": 0.11065032408687371,
      "grad_norm": 0.4565783739089966,
      "learning_rate": 1.9857205727453034e-05,
      "loss": 0.6089,
      "step": 3602
    },
    {
      "epoch": 0.11068104322182287,
      "grad_norm": 0.33544954657554626,
      "learning_rate": 1.9857124337215152e-05,
      "loss": 0.5833,
      "step": 3603
    },
    {
      "epoch": 0.11071176235677203,
      "grad_norm": 0.34579914808273315,
      "learning_rate": 1.9857042923955267e-05,
      "loss": 0.5423,
      "step": 3604
    },
    {
      "epoch": 0.1107424814917212,
      "grad_norm": 0.33484408259391785,
      "learning_rate": 1.985696148767357e-05,
      "loss": 0.6156,
      "step": 3605
    },
    {
      "epoch": 0.11077320062667036,
      "grad_norm": 0.35987773537635803,
      "learning_rate": 1.9856880028370252e-05,
      "loss": 0.5401,
      "step": 3606
    },
    {
      "epoch": 0.11080391976161952,
      "grad_norm": 0.45957496762275696,
      "learning_rate": 1.9856798546045502e-05,
      "loss": 0.633,
      "step": 3607
    },
    {
      "epoch": 0.11083463889656867,
      "grad_norm": 0.32677319645881653,
      "learning_rate": 1.985671704069951e-05,
      "loss": 0.5728,
      "step": 3608
    },
    {
      "epoch": 0.11086535803151783,
      "grad_norm": 0.3927885890007019,
      "learning_rate": 1.9856635512332464e-05,
      "loss": 0.5766,
      "step": 3609
    },
    {
      "epoch": 0.11089607716646699,
      "grad_norm": 0.3126145005226135,
      "learning_rate": 1.985655396094456e-05,
      "loss": 0.6341,
      "step": 3610
    },
    {
      "epoch": 0.11092679630141615,
      "grad_norm": 0.4004031717777252,
      "learning_rate": 1.9856472386535986e-05,
      "loss": 0.5509,
      "step": 3611
    },
    {
      "epoch": 0.11095751543636531,
      "grad_norm": 0.3809654414653778,
      "learning_rate": 1.9856390789106933e-05,
      "loss": 0.6373,
      "step": 3612
    },
    {
      "epoch": 0.11098823457131447,
      "grad_norm": 0.3488551080226898,
      "learning_rate": 1.985630916865759e-05,
      "loss": 0.5984,
      "step": 3613
    },
    {
      "epoch": 0.11101895370626363,
      "grad_norm": 0.32215163111686707,
      "learning_rate": 1.9856227525188148e-05,
      "loss": 0.6228,
      "step": 3614
    },
    {
      "epoch": 0.1110496728412128,
      "grad_norm": 0.3190827965736389,
      "learning_rate": 1.9856145858698798e-05,
      "loss": 0.5187,
      "step": 3615
    },
    {
      "epoch": 0.11108039197616196,
      "grad_norm": 0.34365713596343994,
      "learning_rate": 1.985606416918973e-05,
      "loss": 0.4838,
      "step": 3616
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.3539183735847473,
      "learning_rate": 1.985598245666114e-05,
      "loss": 0.6466,
      "step": 3617
    },
    {
      "epoch": 0.11114183024606027,
      "grad_norm": 0.35482561588287354,
      "learning_rate": 1.9855900721113213e-05,
      "loss": 0.5995,
      "step": 3618
    },
    {
      "epoch": 0.11117254938100943,
      "grad_norm": 0.3133988678455353,
      "learning_rate": 1.985581896254614e-05,
      "loss": 0.5521,
      "step": 3619
    },
    {
      "epoch": 0.11120326851595859,
      "grad_norm": 0.40497711300849915,
      "learning_rate": 1.9855737180960114e-05,
      "loss": 0.5745,
      "step": 3620
    },
    {
      "epoch": 0.11123398765090775,
      "grad_norm": 0.4514729082584381,
      "learning_rate": 1.9855655376355326e-05,
      "loss": 0.5743,
      "step": 3621
    },
    {
      "epoch": 0.11126470678585691,
      "grad_norm": 0.3270755410194397,
      "learning_rate": 1.9855573548731968e-05,
      "loss": 0.6327,
      "step": 3622
    },
    {
      "epoch": 0.11129542592080607,
      "grad_norm": 0.29781270027160645,
      "learning_rate": 1.985549169809023e-05,
      "loss": 0.6158,
      "step": 3623
    },
    {
      "epoch": 0.11132614505575524,
      "grad_norm": 0.387952983379364,
      "learning_rate": 1.9855409824430298e-05,
      "loss": 0.5433,
      "step": 3624
    },
    {
      "epoch": 0.1113568641907044,
      "grad_norm": 0.37318992614746094,
      "learning_rate": 1.985532792775237e-05,
      "loss": 0.6663,
      "step": 3625
    },
    {
      "epoch": 0.11138758332565354,
      "grad_norm": 0.29879212379455566,
      "learning_rate": 1.9855246008056637e-05,
      "loss": 0.4902,
      "step": 3626
    },
    {
      "epoch": 0.1114183024606027,
      "grad_norm": 0.5849641561508179,
      "learning_rate": 1.9855164065343287e-05,
      "loss": 0.5597,
      "step": 3627
    },
    {
      "epoch": 0.11144902159555187,
      "grad_norm": 0.3768247961997986,
      "learning_rate": 1.9855082099612514e-05,
      "loss": 0.6423,
      "step": 3628
    },
    {
      "epoch": 0.11147974073050103,
      "grad_norm": 0.3498307168483734,
      "learning_rate": 1.985500011086451e-05,
      "loss": 0.6133,
      "step": 3629
    },
    {
      "epoch": 0.11151045986545019,
      "grad_norm": 0.29821786284446716,
      "learning_rate": 1.985491809909946e-05,
      "loss": 0.5848,
      "step": 3630
    },
    {
      "epoch": 0.11154117900039935,
      "grad_norm": 0.34664052724838257,
      "learning_rate": 1.9854836064317567e-05,
      "loss": 0.6322,
      "step": 3631
    },
    {
      "epoch": 0.11157189813534851,
      "grad_norm": 0.4375780522823334,
      "learning_rate": 1.9854754006519012e-05,
      "loss": 0.6018,
      "step": 3632
    },
    {
      "epoch": 0.11160261727029767,
      "grad_norm": 0.31445521116256714,
      "learning_rate": 1.985467192570399e-05,
      "loss": 0.6104,
      "step": 3633
    },
    {
      "epoch": 0.11163333640524682,
      "grad_norm": 0.3879116177558899,
      "learning_rate": 1.98545898218727e-05,
      "loss": 0.5503,
      "step": 3634
    },
    {
      "epoch": 0.11166405554019598,
      "grad_norm": 0.36149361729621887,
      "learning_rate": 1.985450769502532e-05,
      "loss": 0.7001,
      "step": 3635
    },
    {
      "epoch": 0.11169477467514514,
      "grad_norm": 0.3327271640300751,
      "learning_rate": 1.985442554516205e-05,
      "loss": 0.6133,
      "step": 3636
    },
    {
      "epoch": 0.1117254938100943,
      "grad_norm": 0.304849773645401,
      "learning_rate": 1.9854343372283084e-05,
      "loss": 0.5727,
      "step": 3637
    },
    {
      "epoch": 0.11175621294504347,
      "grad_norm": 0.3618071675300598,
      "learning_rate": 1.9854261176388608e-05,
      "loss": 0.6015,
      "step": 3638
    },
    {
      "epoch": 0.11178693207999263,
      "grad_norm": 0.3424777090549469,
      "learning_rate": 1.985417895747882e-05,
      "loss": 0.601,
      "step": 3639
    },
    {
      "epoch": 0.11181765121494179,
      "grad_norm": 0.3185243308544159,
      "learning_rate": 1.9854096715553907e-05,
      "loss": 0.5732,
      "step": 3640
    },
    {
      "epoch": 0.11184837034989095,
      "grad_norm": 0.3296416103839874,
      "learning_rate": 1.9854014450614062e-05,
      "loss": 0.6338,
      "step": 3641
    },
    {
      "epoch": 0.11187908948484011,
      "grad_norm": 0.3447137176990509,
      "learning_rate": 1.985393216265948e-05,
      "loss": 0.6074,
      "step": 3642
    },
    {
      "epoch": 0.11190980861978926,
      "grad_norm": 0.876660943031311,
      "learning_rate": 1.985384985169035e-05,
      "loss": 0.7593,
      "step": 3643
    },
    {
      "epoch": 0.11194052775473842,
      "grad_norm": 0.3131575286388397,
      "learning_rate": 1.9853767517706865e-05,
      "loss": 0.5763,
      "step": 3644
    },
    {
      "epoch": 0.11197124688968758,
      "grad_norm": 0.4026492238044739,
      "learning_rate": 1.985368516070922e-05,
      "loss": 0.6161,
      "step": 3645
    },
    {
      "epoch": 0.11200196602463675,
      "grad_norm": 0.4172850549221039,
      "learning_rate": 1.9853602780697604e-05,
      "loss": 0.5094,
      "step": 3646
    },
    {
      "epoch": 0.1120326851595859,
      "grad_norm": 0.48110243678092957,
      "learning_rate": 1.9853520377672208e-05,
      "loss": 0.6445,
      "step": 3647
    },
    {
      "epoch": 0.11206340429453507,
      "grad_norm": 0.3275093734264374,
      "learning_rate": 1.9853437951633232e-05,
      "loss": 0.5757,
      "step": 3648
    },
    {
      "epoch": 0.11209412342948423,
      "grad_norm": 0.3749914765357971,
      "learning_rate": 1.985335550258086e-05,
      "loss": 0.5821,
      "step": 3649
    },
    {
      "epoch": 0.11212484256443339,
      "grad_norm": 0.30625709891319275,
      "learning_rate": 1.9853273030515288e-05,
      "loss": 0.5455,
      "step": 3650
    },
    {
      "epoch": 0.11215556169938254,
      "grad_norm": 0.3580871820449829,
      "learning_rate": 1.985319053543671e-05,
      "loss": 0.6422,
      "step": 3651
    },
    {
      "epoch": 0.1121862808343317,
      "grad_norm": 0.31980985403060913,
      "learning_rate": 1.9853108017345314e-05,
      "loss": 0.5981,
      "step": 3652
    },
    {
      "epoch": 0.11221699996928086,
      "grad_norm": 0.3333090543746948,
      "learning_rate": 1.9853025476241303e-05,
      "loss": 0.6169,
      "step": 3653
    },
    {
      "epoch": 0.11224771910423002,
      "grad_norm": 0.43548858165740967,
      "learning_rate": 1.9852942912124857e-05,
      "loss": 0.5449,
      "step": 3654
    },
    {
      "epoch": 0.11227843823917918,
      "grad_norm": 0.32213085889816284,
      "learning_rate": 1.9852860324996176e-05,
      "loss": 0.5257,
      "step": 3655
    },
    {
      "epoch": 0.11230915737412835,
      "grad_norm": 0.35707730054855347,
      "learning_rate": 1.9852777714855453e-05,
      "loss": 0.5594,
      "step": 3656
    },
    {
      "epoch": 0.11233987650907751,
      "grad_norm": 0.36646443605422974,
      "learning_rate": 1.985269508170288e-05,
      "loss": 0.6604,
      "step": 3657
    },
    {
      "epoch": 0.11237059564402667,
      "grad_norm": 0.3372706472873688,
      "learning_rate": 1.9852612425538646e-05,
      "loss": 0.6402,
      "step": 3658
    },
    {
      "epoch": 0.11240131477897583,
      "grad_norm": 0.3468382656574249,
      "learning_rate": 1.985252974636295e-05,
      "loss": 0.6137,
      "step": 3659
    },
    {
      "epoch": 0.11243203391392498,
      "grad_norm": 0.34987303614616394,
      "learning_rate": 1.9852447044175982e-05,
      "loss": 0.6234,
      "step": 3660
    },
    {
      "epoch": 0.11246275304887414,
      "grad_norm": 0.3773833215236664,
      "learning_rate": 1.9852364318977935e-05,
      "loss": 0.6917,
      "step": 3661
    },
    {
      "epoch": 0.1124934721838233,
      "grad_norm": 0.3723367750644684,
      "learning_rate": 1.985228157076901e-05,
      "loss": 0.6675,
      "step": 3662
    },
    {
      "epoch": 0.11252419131877246,
      "grad_norm": 0.3827250599861145,
      "learning_rate": 1.9852198799549382e-05,
      "loss": 0.5986,
      "step": 3663
    },
    {
      "epoch": 0.11255491045372162,
      "grad_norm": 0.3177677392959595,
      "learning_rate": 1.985211600531926e-05,
      "loss": 0.4962,
      "step": 3664
    },
    {
      "epoch": 0.11258562958867079,
      "grad_norm": 0.34122058749198914,
      "learning_rate": 1.9852033188078837e-05,
      "loss": 0.7325,
      "step": 3665
    },
    {
      "epoch": 0.11261634872361995,
      "grad_norm": 0.45283445715904236,
      "learning_rate": 1.98519503478283e-05,
      "loss": 0.6029,
      "step": 3666
    },
    {
      "epoch": 0.11264706785856911,
      "grad_norm": 0.32625705003738403,
      "learning_rate": 1.9851867484567842e-05,
      "loss": 0.5449,
      "step": 3667
    },
    {
      "epoch": 0.11267778699351826,
      "grad_norm": 0.4151667654514313,
      "learning_rate": 1.9851784598297665e-05,
      "loss": 0.61,
      "step": 3668
    },
    {
      "epoch": 0.11270850612846742,
      "grad_norm": 0.351315975189209,
      "learning_rate": 1.9851701689017956e-05,
      "loss": 0.5806,
      "step": 3669
    },
    {
      "epoch": 0.11273922526341658,
      "grad_norm": 0.3853437304496765,
      "learning_rate": 1.9851618756728905e-05,
      "loss": 0.5871,
      "step": 3670
    },
    {
      "epoch": 0.11276994439836574,
      "grad_norm": 0.3557128608226776,
      "learning_rate": 1.9851535801430713e-05,
      "loss": 0.6086,
      "step": 3671
    },
    {
      "epoch": 0.1128006635333149,
      "grad_norm": 0.3255499005317688,
      "learning_rate": 1.9851452823123572e-05,
      "loss": 0.5972,
      "step": 3672
    },
    {
      "epoch": 0.11283138266826406,
      "grad_norm": 0.3665372133255005,
      "learning_rate": 1.9851369821807672e-05,
      "loss": 0.6552,
      "step": 3673
    },
    {
      "epoch": 0.11286210180321322,
      "grad_norm": 0.3607790768146515,
      "learning_rate": 1.9851286797483213e-05,
      "loss": 0.7137,
      "step": 3674
    },
    {
      "epoch": 0.11289282093816239,
      "grad_norm": 0.3338436484336853,
      "learning_rate": 1.9851203750150385e-05,
      "loss": 0.5541,
      "step": 3675
    },
    {
      "epoch": 0.11292354007311155,
      "grad_norm": 0.3600040376186371,
      "learning_rate": 1.9851120679809384e-05,
      "loss": 0.5497,
      "step": 3676
    },
    {
      "epoch": 0.1129542592080607,
      "grad_norm": 0.3450561761856079,
      "learning_rate": 1.98510375864604e-05,
      "loss": 0.5412,
      "step": 3677
    },
    {
      "epoch": 0.11298497834300986,
      "grad_norm": 0.34481704235076904,
      "learning_rate": 1.985095447010363e-05,
      "loss": 0.572,
      "step": 3678
    },
    {
      "epoch": 0.11301569747795902,
      "grad_norm": 0.332034170627594,
      "learning_rate": 1.9850871330739268e-05,
      "loss": 0.5842,
      "step": 3679
    },
    {
      "epoch": 0.11304641661290818,
      "grad_norm": 0.3462934195995331,
      "learning_rate": 1.985078816836751e-05,
      "loss": 0.624,
      "step": 3680
    },
    {
      "epoch": 0.11307713574785734,
      "grad_norm": 0.31092169880867004,
      "learning_rate": 1.9850704982988546e-05,
      "loss": 0.6484,
      "step": 3681
    },
    {
      "epoch": 0.1131078548828065,
      "grad_norm": 0.2953418791294098,
      "learning_rate": 1.9850621774602574e-05,
      "loss": 0.517,
      "step": 3682
    },
    {
      "epoch": 0.11313857401775566,
      "grad_norm": 0.3259090185165405,
      "learning_rate": 1.9850538543209784e-05,
      "loss": 0.6249,
      "step": 3683
    },
    {
      "epoch": 0.11316929315270483,
      "grad_norm": 0.3289620876312256,
      "learning_rate": 1.9850455288810377e-05,
      "loss": 0.5804,
      "step": 3684
    },
    {
      "epoch": 0.11320001228765399,
      "grad_norm": 0.3384961187839508,
      "learning_rate": 1.9850372011404542e-05,
      "loss": 0.6028,
      "step": 3685
    },
    {
      "epoch": 0.11323073142260313,
      "grad_norm": 0.3455812335014343,
      "learning_rate": 1.9850288710992476e-05,
      "loss": 0.642,
      "step": 3686
    },
    {
      "epoch": 0.1132614505575523,
      "grad_norm": 0.3522243797779083,
      "learning_rate": 1.985020538757437e-05,
      "loss": 0.6369,
      "step": 3687
    },
    {
      "epoch": 0.11329216969250146,
      "grad_norm": 0.36047083139419556,
      "learning_rate": 1.9850122041150424e-05,
      "loss": 0.6434,
      "step": 3688
    },
    {
      "epoch": 0.11332288882745062,
      "grad_norm": 0.32674795389175415,
      "learning_rate": 1.985003867172083e-05,
      "loss": 0.5916,
      "step": 3689
    },
    {
      "epoch": 0.11335360796239978,
      "grad_norm": 0.3712977170944214,
      "learning_rate": 1.9849955279285785e-05,
      "loss": 0.6613,
      "step": 3690
    },
    {
      "epoch": 0.11338432709734894,
      "grad_norm": 0.3866407573223114,
      "learning_rate": 1.984987186384548e-05,
      "loss": 0.6041,
      "step": 3691
    },
    {
      "epoch": 0.1134150462322981,
      "grad_norm": 0.3390164077281952,
      "learning_rate": 1.9849788425400107e-05,
      "loss": 0.6058,
      "step": 3692
    },
    {
      "epoch": 0.11344576536724726,
      "grad_norm": 0.35366421937942505,
      "learning_rate": 1.984970496394987e-05,
      "loss": 0.6616,
      "step": 3693
    },
    {
      "epoch": 0.11347648450219641,
      "grad_norm": 0.3490495979785919,
      "learning_rate": 1.9849621479494955e-05,
      "loss": 0.6785,
      "step": 3694
    },
    {
      "epoch": 0.11350720363714557,
      "grad_norm": 0.5634581446647644,
      "learning_rate": 1.9849537972035567e-05,
      "loss": 0.5639,
      "step": 3695
    },
    {
      "epoch": 0.11353792277209473,
      "grad_norm": 0.41927042603492737,
      "learning_rate": 1.984945444157189e-05,
      "loss": 0.6334,
      "step": 3696
    },
    {
      "epoch": 0.1135686419070439,
      "grad_norm": 0.41765859723091125,
      "learning_rate": 1.9849370888104126e-05,
      "loss": 0.5963,
      "step": 3697
    },
    {
      "epoch": 0.11359936104199306,
      "grad_norm": 0.4777277112007141,
      "learning_rate": 1.984928731163247e-05,
      "loss": 0.5959,
      "step": 3698
    },
    {
      "epoch": 0.11363008017694222,
      "grad_norm": 0.3572618365287781,
      "learning_rate": 1.9849203712157114e-05,
      "loss": 0.5823,
      "step": 3699
    },
    {
      "epoch": 0.11366079931189138,
      "grad_norm": 0.32865867018699646,
      "learning_rate": 1.9849120089678252e-05,
      "loss": 0.5877,
      "step": 3700
    },
    {
      "epoch": 0.11369151844684054,
      "grad_norm": 0.31242507696151733,
      "learning_rate": 1.984903644419609e-05,
      "loss": 0.5413,
      "step": 3701
    },
    {
      "epoch": 0.1137222375817897,
      "grad_norm": 0.32249462604522705,
      "learning_rate": 1.984895277571081e-05,
      "loss": 0.6699,
      "step": 3702
    },
    {
      "epoch": 0.11375295671673885,
      "grad_norm": 0.3626345694065094,
      "learning_rate": 1.984886908422261e-05,
      "loss": 0.6249,
      "step": 3703
    },
    {
      "epoch": 0.11378367585168801,
      "grad_norm": 0.38088729977607727,
      "learning_rate": 1.9848785369731695e-05,
      "loss": 0.6256,
      "step": 3704
    },
    {
      "epoch": 0.11381439498663717,
      "grad_norm": 0.3482777774333954,
      "learning_rate": 1.984870163223825e-05,
      "loss": 0.5718,
      "step": 3705
    },
    {
      "epoch": 0.11384511412158634,
      "grad_norm": 0.3128650188446045,
      "learning_rate": 1.984861787174248e-05,
      "loss": 0.5532,
      "step": 3706
    },
    {
      "epoch": 0.1138758332565355,
      "grad_norm": 0.32504501938819885,
      "learning_rate": 1.9848534088244568e-05,
      "loss": 0.6289,
      "step": 3707
    },
    {
      "epoch": 0.11390655239148466,
      "grad_norm": 0.3439810276031494,
      "learning_rate": 1.984845028174472e-05,
      "loss": 0.6143,
      "step": 3708
    },
    {
      "epoch": 0.11393727152643382,
      "grad_norm": 0.31374475359916687,
      "learning_rate": 1.984836645224313e-05,
      "loss": 0.5006,
      "step": 3709
    },
    {
      "epoch": 0.11396799066138298,
      "grad_norm": 0.3303595781326294,
      "learning_rate": 1.9848282599739986e-05,
      "loss": 0.6244,
      "step": 3710
    },
    {
      "epoch": 0.11399870979633213,
      "grad_norm": 0.3594200313091278,
      "learning_rate": 1.9848198724235496e-05,
      "loss": 0.6323,
      "step": 3711
    },
    {
      "epoch": 0.11402942893128129,
      "grad_norm": 0.3224477767944336,
      "learning_rate": 1.984811482572985e-05,
      "loss": 0.6207,
      "step": 3712
    },
    {
      "epoch": 0.11406014806623045,
      "grad_norm": 0.3226579427719116,
      "learning_rate": 1.9848030904223242e-05,
      "loss": 0.5579,
      "step": 3713
    },
    {
      "epoch": 0.11409086720117961,
      "grad_norm": 0.3188364803791046,
      "learning_rate": 1.984794695971587e-05,
      "loss": 0.5743,
      "step": 3714
    },
    {
      "epoch": 0.11412158633612877,
      "grad_norm": 0.3319861888885498,
      "learning_rate": 1.9847862992207933e-05,
      "loss": 0.5972,
      "step": 3715
    },
    {
      "epoch": 0.11415230547107794,
      "grad_norm": 0.32829591631889343,
      "learning_rate": 1.984777900169962e-05,
      "loss": 0.6356,
      "step": 3716
    },
    {
      "epoch": 0.1141830246060271,
      "grad_norm": 0.34315094351768494,
      "learning_rate": 1.9847694988191137e-05,
      "loss": 0.584,
      "step": 3717
    },
    {
      "epoch": 0.11421374374097626,
      "grad_norm": 0.33385223150253296,
      "learning_rate": 1.984761095168267e-05,
      "loss": 0.6258,
      "step": 3718
    },
    {
      "epoch": 0.11424446287592542,
      "grad_norm": 0.34356430172920227,
      "learning_rate": 1.9847526892174423e-05,
      "loss": 0.7014,
      "step": 3719
    },
    {
      "epoch": 0.11427518201087457,
      "grad_norm": 0.32874423265457153,
      "learning_rate": 1.9847442809666587e-05,
      "loss": 0.5858,
      "step": 3720
    },
    {
      "epoch": 0.11430590114582373,
      "grad_norm": 0.33098146319389343,
      "learning_rate": 1.984735870415936e-05,
      "loss": 0.5838,
      "step": 3721
    },
    {
      "epoch": 0.11433662028077289,
      "grad_norm": 0.43197765946388245,
      "learning_rate": 1.984727457565294e-05,
      "loss": 0.6773,
      "step": 3722
    },
    {
      "epoch": 0.11436733941572205,
      "grad_norm": 0.3538738787174225,
      "learning_rate": 1.984719042414752e-05,
      "loss": 0.5701,
      "step": 3723
    },
    {
      "epoch": 0.11439805855067121,
      "grad_norm": 0.3129217028617859,
      "learning_rate": 1.9847106249643305e-05,
      "loss": 0.5988,
      "step": 3724
    },
    {
      "epoch": 0.11442877768562038,
      "grad_norm": 0.37899449467658997,
      "learning_rate": 1.984702205214048e-05,
      "loss": 0.6804,
      "step": 3725
    },
    {
      "epoch": 0.11445949682056954,
      "grad_norm": 0.3788180947303772,
      "learning_rate": 1.984693783163925e-05,
      "loss": 0.5832,
      "step": 3726
    },
    {
      "epoch": 0.1144902159555187,
      "grad_norm": 0.3483436107635498,
      "learning_rate": 1.9846853588139806e-05,
      "loss": 0.6779,
      "step": 3727
    },
    {
      "epoch": 0.11452093509046785,
      "grad_norm": 0.5696409344673157,
      "learning_rate": 1.984676932164235e-05,
      "loss": 0.5686,
      "step": 3728
    },
    {
      "epoch": 0.11455165422541701,
      "grad_norm": 0.3305493891239166,
      "learning_rate": 1.984668503214708e-05,
      "loss": 0.5898,
      "step": 3729
    },
    {
      "epoch": 0.11458237336036617,
      "grad_norm": 0.3107776343822479,
      "learning_rate": 1.9846600719654185e-05,
      "loss": 0.6256,
      "step": 3730
    },
    {
      "epoch": 0.11461309249531533,
      "grad_norm": 0.3834291696548462,
      "learning_rate": 1.9846516384163866e-05,
      "loss": 0.7225,
      "step": 3731
    },
    {
      "epoch": 0.11464381163026449,
      "grad_norm": 0.3137303292751312,
      "learning_rate": 1.9846432025676324e-05,
      "loss": 0.5782,
      "step": 3732
    },
    {
      "epoch": 0.11467453076521365,
      "grad_norm": 0.29800671339035034,
      "learning_rate": 1.984634764419175e-05,
      "loss": 0.5595,
      "step": 3733
    },
    {
      "epoch": 0.11470524990016281,
      "grad_norm": 0.36078667640686035,
      "learning_rate": 1.9846263239710343e-05,
      "loss": 0.59,
      "step": 3734
    },
    {
      "epoch": 0.11473596903511198,
      "grad_norm": 0.34919342398643494,
      "learning_rate": 1.9846178812232303e-05,
      "loss": 0.6349,
      "step": 3735
    },
    {
      "epoch": 0.11476668817006114,
      "grad_norm": 0.4742375910282135,
      "learning_rate": 1.984609436175782e-05,
      "loss": 0.5852,
      "step": 3736
    },
    {
      "epoch": 0.11479740730501029,
      "grad_norm": 0.4074249267578125,
      "learning_rate": 1.98460098882871e-05,
      "loss": 0.6288,
      "step": 3737
    },
    {
      "epoch": 0.11482812643995945,
      "grad_norm": 0.36118096113204956,
      "learning_rate": 1.9845925391820336e-05,
      "loss": 0.576,
      "step": 3738
    },
    {
      "epoch": 0.11485884557490861,
      "grad_norm": 0.37920767068862915,
      "learning_rate": 1.9845840872357723e-05,
      "loss": 0.5994,
      "step": 3739
    },
    {
      "epoch": 0.11488956470985777,
      "grad_norm": 0.3272668421268463,
      "learning_rate": 1.9845756329899464e-05,
      "loss": 0.6378,
      "step": 3740
    },
    {
      "epoch": 0.11492028384480693,
      "grad_norm": 0.30889472365379333,
      "learning_rate": 1.984567176444575e-05,
      "loss": 0.5942,
      "step": 3741
    },
    {
      "epoch": 0.11495100297975609,
      "grad_norm": 0.3245025873184204,
      "learning_rate": 1.9845587175996787e-05,
      "loss": 0.6037,
      "step": 3742
    },
    {
      "epoch": 0.11498172211470525,
      "grad_norm": 0.3550287187099457,
      "learning_rate": 1.9845502564552762e-05,
      "loss": 0.5402,
      "step": 3743
    },
    {
      "epoch": 0.11501244124965442,
      "grad_norm": 0.32287874817848206,
      "learning_rate": 1.984541793011388e-05,
      "loss": 0.5974,
      "step": 3744
    },
    {
      "epoch": 0.11504316038460356,
      "grad_norm": 0.3560314476490021,
      "learning_rate": 1.984533327268034e-05,
      "loss": 0.6511,
      "step": 3745
    },
    {
      "epoch": 0.11507387951955272,
      "grad_norm": 2.647883892059326,
      "learning_rate": 1.9845248592252334e-05,
      "loss": 0.6932,
      "step": 3746
    },
    {
      "epoch": 0.11510459865450189,
      "grad_norm": 0.4019797444343567,
      "learning_rate": 1.9845163888830062e-05,
      "loss": 0.4805,
      "step": 3747
    },
    {
      "epoch": 0.11513531778945105,
      "grad_norm": 0.3559793531894684,
      "learning_rate": 1.9845079162413723e-05,
      "loss": 0.6695,
      "step": 3748
    },
    {
      "epoch": 0.11516603692440021,
      "grad_norm": 0.3049938678741455,
      "learning_rate": 1.9844994413003515e-05,
      "loss": 0.6378,
      "step": 3749
    },
    {
      "epoch": 0.11519675605934937,
      "grad_norm": 0.3690749406814575,
      "learning_rate": 1.9844909640599632e-05,
      "loss": 0.6406,
      "step": 3750
    },
    {
      "epoch": 0.11522747519429853,
      "grad_norm": 0.3373993933200836,
      "learning_rate": 1.9844824845202278e-05,
      "loss": 0.6461,
      "step": 3751
    },
    {
      "epoch": 0.11525819432924769,
      "grad_norm": 0.3101414442062378,
      "learning_rate": 1.9844740026811645e-05,
      "loss": 0.6391,
      "step": 3752
    },
    {
      "epoch": 0.11528891346419685,
      "grad_norm": 0.31894198060035706,
      "learning_rate": 1.9844655185427937e-05,
      "loss": 0.5255,
      "step": 3753
    },
    {
      "epoch": 0.115319632599146,
      "grad_norm": 0.3327147364616394,
      "learning_rate": 1.9844570321051346e-05,
      "loss": 0.5781,
      "step": 3754
    },
    {
      "epoch": 0.11535035173409516,
      "grad_norm": 0.3393171429634094,
      "learning_rate": 1.9844485433682077e-05,
      "loss": 0.6234,
      "step": 3755
    },
    {
      "epoch": 0.11538107086904432,
      "grad_norm": 0.4035336971282959,
      "learning_rate": 1.9844400523320325e-05,
      "loss": 0.7211,
      "step": 3756
    },
    {
      "epoch": 0.11541179000399349,
      "grad_norm": 0.3127652108669281,
      "learning_rate": 1.9844315589966285e-05,
      "loss": 0.6024,
      "step": 3757
    },
    {
      "epoch": 0.11544250913894265,
      "grad_norm": 0.3839256167411804,
      "learning_rate": 1.9844230633620158e-05,
      "loss": 0.6948,
      "step": 3758
    },
    {
      "epoch": 0.11547322827389181,
      "grad_norm": 0.3628309667110443,
      "learning_rate": 1.984414565428215e-05,
      "loss": 0.7031,
      "step": 3759
    },
    {
      "epoch": 0.11550394740884097,
      "grad_norm": 0.3668003976345062,
      "learning_rate": 1.9844060651952443e-05,
      "loss": 0.5777,
      "step": 3760
    },
    {
      "epoch": 0.11553466654379013,
      "grad_norm": 0.4155294895172119,
      "learning_rate": 1.9843975626631247e-05,
      "loss": 0.5939,
      "step": 3761
    },
    {
      "epoch": 0.1155653856787393,
      "grad_norm": 0.33983907103538513,
      "learning_rate": 1.9843890578318762e-05,
      "loss": 0.6047,
      "step": 3762
    },
    {
      "epoch": 0.11559610481368844,
      "grad_norm": 0.37674611806869507,
      "learning_rate": 1.984380550701518e-05,
      "loss": 0.5999,
      "step": 3763
    },
    {
      "epoch": 0.1156268239486376,
      "grad_norm": 0.30768948793411255,
      "learning_rate": 1.9843720412720706e-05,
      "loss": 0.5912,
      "step": 3764
    },
    {
      "epoch": 0.11565754308358676,
      "grad_norm": 0.3394695818424225,
      "learning_rate": 1.9843635295435534e-05,
      "loss": 0.5756,
      "step": 3765
    },
    {
      "epoch": 0.11568826221853593,
      "grad_norm": 0.35003724694252014,
      "learning_rate": 1.9843550155159862e-05,
      "loss": 0.6306,
      "step": 3766
    },
    {
      "epoch": 0.11571898135348509,
      "grad_norm": 0.32819175720214844,
      "learning_rate": 1.9843464991893896e-05,
      "loss": 0.5785,
      "step": 3767
    },
    {
      "epoch": 0.11574970048843425,
      "grad_norm": 0.3929077982902527,
      "learning_rate": 1.9843379805637827e-05,
      "loss": 0.5988,
      "step": 3768
    },
    {
      "epoch": 0.11578041962338341,
      "grad_norm": 0.3248562216758728,
      "learning_rate": 1.9843294596391857e-05,
      "loss": 0.4749,
      "step": 3769
    },
    {
      "epoch": 0.11581113875833257,
      "grad_norm": 0.4304574131965637,
      "learning_rate": 1.9843209364156182e-05,
      "loss": 0.5714,
      "step": 3770
    },
    {
      "epoch": 0.11584185789328172,
      "grad_norm": 0.34659627079963684,
      "learning_rate": 1.9843124108931007e-05,
      "loss": 0.4858,
      "step": 3771
    },
    {
      "epoch": 0.11587257702823088,
      "grad_norm": 0.333219975233078,
      "learning_rate": 1.984303883071653e-05,
      "loss": 0.5371,
      "step": 3772
    },
    {
      "epoch": 0.11590329616318004,
      "grad_norm": 0.34022560715675354,
      "learning_rate": 1.9842953529512948e-05,
      "loss": 0.6022,
      "step": 3773
    },
    {
      "epoch": 0.1159340152981292,
      "grad_norm": 0.3372803032398224,
      "learning_rate": 1.984286820532046e-05,
      "loss": 0.5485,
      "step": 3774
    },
    {
      "epoch": 0.11596473443307836,
      "grad_norm": 0.42921972274780273,
      "learning_rate": 1.9842782858139264e-05,
      "loss": 0.6161,
      "step": 3775
    },
    {
      "epoch": 0.11599545356802753,
      "grad_norm": 0.353121280670166,
      "learning_rate": 1.9842697487969563e-05,
      "loss": 0.6383,
      "step": 3776
    },
    {
      "epoch": 0.11602617270297669,
      "grad_norm": 0.3229205906391144,
      "learning_rate": 1.9842612094811554e-05,
      "loss": 0.6034,
      "step": 3777
    },
    {
      "epoch": 0.11605689183792585,
      "grad_norm": 0.3326924443244934,
      "learning_rate": 1.9842526678665436e-05,
      "loss": 0.6238,
      "step": 3778
    },
    {
      "epoch": 0.11608761097287501,
      "grad_norm": 0.3515435755252838,
      "learning_rate": 1.984244123953141e-05,
      "loss": 0.6342,
      "step": 3779
    },
    {
      "epoch": 0.11611833010782416,
      "grad_norm": 0.322115421295166,
      "learning_rate": 1.9842355777409677e-05,
      "loss": 0.5998,
      "step": 3780
    },
    {
      "epoch": 0.11614904924277332,
      "grad_norm": 0.31537431478500366,
      "learning_rate": 1.984227029230043e-05,
      "loss": 0.5922,
      "step": 3781
    },
    {
      "epoch": 0.11617976837772248,
      "grad_norm": 0.4828987121582031,
      "learning_rate": 1.984218478420388e-05,
      "loss": 0.6102,
      "step": 3782
    },
    {
      "epoch": 0.11621048751267164,
      "grad_norm": 0.35756558179855347,
      "learning_rate": 1.9842099253120216e-05,
      "loss": 0.6345,
      "step": 3783
    },
    {
      "epoch": 0.1162412066476208,
      "grad_norm": 0.33306509256362915,
      "learning_rate": 1.9842013699049644e-05,
      "loss": 0.5995,
      "step": 3784
    },
    {
      "epoch": 0.11627192578256997,
      "grad_norm": 0.37958404421806335,
      "learning_rate": 1.984192812199236e-05,
      "loss": 0.5855,
      "step": 3785
    },
    {
      "epoch": 0.11630264491751913,
      "grad_norm": 0.34764793515205383,
      "learning_rate": 1.9841842521948565e-05,
      "loss": 0.634,
      "step": 3786
    },
    {
      "epoch": 0.11633336405246829,
      "grad_norm": 0.34162887930870056,
      "learning_rate": 1.9841756898918462e-05,
      "loss": 0.5449,
      "step": 3787
    },
    {
      "epoch": 0.11636408318741744,
      "grad_norm": 0.6509524583816528,
      "learning_rate": 1.9841671252902246e-05,
      "loss": 0.5426,
      "step": 3788
    },
    {
      "epoch": 0.1163948023223666,
      "grad_norm": 0.4084666073322296,
      "learning_rate": 1.984158558390012e-05,
      "loss": 0.6141,
      "step": 3789
    },
    {
      "epoch": 0.11642552145731576,
      "grad_norm": 0.33353424072265625,
      "learning_rate": 1.9841499891912284e-05,
      "loss": 0.5514,
      "step": 3790
    },
    {
      "epoch": 0.11645624059226492,
      "grad_norm": 0.37195223569869995,
      "learning_rate": 1.9841414176938936e-05,
      "loss": 0.6418,
      "step": 3791
    },
    {
      "epoch": 0.11648695972721408,
      "grad_norm": 0.34068968892097473,
      "learning_rate": 1.9841328438980282e-05,
      "loss": 0.5621,
      "step": 3792
    },
    {
      "epoch": 0.11651767886216324,
      "grad_norm": 0.3459191620349884,
      "learning_rate": 1.9841242678036515e-05,
      "loss": 0.6149,
      "step": 3793
    },
    {
      "epoch": 0.1165483979971124,
      "grad_norm": 0.3548637628555298,
      "learning_rate": 1.984115689410784e-05,
      "loss": 0.6391,
      "step": 3794
    },
    {
      "epoch": 0.11657911713206157,
      "grad_norm": 0.33104750514030457,
      "learning_rate": 1.9841071087194452e-05,
      "loss": 0.6297,
      "step": 3795
    },
    {
      "epoch": 0.11660983626701073,
      "grad_norm": 0.3076324462890625,
      "learning_rate": 1.984098525729656e-05,
      "loss": 0.5669,
      "step": 3796
    },
    {
      "epoch": 0.11664055540195988,
      "grad_norm": 0.4566512107849121,
      "learning_rate": 1.9840899404414355e-05,
      "loss": 0.6418,
      "step": 3797
    },
    {
      "epoch": 0.11667127453690904,
      "grad_norm": 0.33666276931762695,
      "learning_rate": 1.9840813528548045e-05,
      "loss": 0.7073,
      "step": 3798
    },
    {
      "epoch": 0.1167019936718582,
      "grad_norm": 0.3549008369445801,
      "learning_rate": 1.984072762969783e-05,
      "loss": 0.5787,
      "step": 3799
    },
    {
      "epoch": 0.11673271280680736,
      "grad_norm": 0.3410724699497223,
      "learning_rate": 1.9840641707863902e-05,
      "loss": 0.5126,
      "step": 3800
    },
    {
      "epoch": 0.11676343194175652,
      "grad_norm": 0.33260494470596313,
      "learning_rate": 1.9840555763046474e-05,
      "loss": 0.6209,
      "step": 3801
    },
    {
      "epoch": 0.11679415107670568,
      "grad_norm": 0.40066155791282654,
      "learning_rate": 1.984046979524574e-05,
      "loss": 0.6069,
      "step": 3802
    },
    {
      "epoch": 0.11682487021165484,
      "grad_norm": 0.3189440071582794,
      "learning_rate": 1.98403838044619e-05,
      "loss": 0.5718,
      "step": 3803
    },
    {
      "epoch": 0.116855589346604,
      "grad_norm": 0.3291054368019104,
      "learning_rate": 1.9840297790695152e-05,
      "loss": 0.5983,
      "step": 3804
    },
    {
      "epoch": 0.11688630848155315,
      "grad_norm": 0.3631213307380676,
      "learning_rate": 1.9840211753945707e-05,
      "loss": 0.555,
      "step": 3805
    },
    {
      "epoch": 0.11691702761650231,
      "grad_norm": 0.31198278069496155,
      "learning_rate": 1.984012569421376e-05,
      "loss": 0.5892,
      "step": 3806
    },
    {
      "epoch": 0.11694774675145148,
      "grad_norm": 0.3877051770687103,
      "learning_rate": 1.9840039611499512e-05,
      "loss": 0.7014,
      "step": 3807
    },
    {
      "epoch": 0.11697846588640064,
      "grad_norm": 0.3448989987373352,
      "learning_rate": 1.983995350580316e-05,
      "loss": 0.6528,
      "step": 3808
    },
    {
      "epoch": 0.1170091850213498,
      "grad_norm": 0.40667808055877686,
      "learning_rate": 1.9839867377124915e-05,
      "loss": 0.5476,
      "step": 3809
    },
    {
      "epoch": 0.11703990415629896,
      "grad_norm": 0.35547158122062683,
      "learning_rate": 1.9839781225464972e-05,
      "loss": 0.6293,
      "step": 3810
    },
    {
      "epoch": 0.11707062329124812,
      "grad_norm": 0.3515092134475708,
      "learning_rate": 1.983969505082353e-05,
      "loss": 0.6259,
      "step": 3811
    },
    {
      "epoch": 0.11710134242619728,
      "grad_norm": 0.3396672010421753,
      "learning_rate": 1.9839608853200795e-05,
      "loss": 0.6297,
      "step": 3812
    },
    {
      "epoch": 0.11713206156114644,
      "grad_norm": 0.3585609793663025,
      "learning_rate": 1.9839522632596964e-05,
      "loss": 0.6007,
      "step": 3813
    },
    {
      "epoch": 0.11716278069609559,
      "grad_norm": 0.33318907022476196,
      "learning_rate": 1.983943638901224e-05,
      "loss": 0.6413,
      "step": 3814
    },
    {
      "epoch": 0.11719349983104475,
      "grad_norm": 0.3204422891139984,
      "learning_rate": 1.983935012244683e-05,
      "loss": 0.6021,
      "step": 3815
    },
    {
      "epoch": 0.11722421896599391,
      "grad_norm": 0.33354270458221436,
      "learning_rate": 1.9839263832900925e-05,
      "loss": 0.6168,
      "step": 3816
    },
    {
      "epoch": 0.11725493810094308,
      "grad_norm": 0.3516763746738434,
      "learning_rate": 1.9839177520374737e-05,
      "loss": 0.5841,
      "step": 3817
    },
    {
      "epoch": 0.11728565723589224,
      "grad_norm": 0.39533543586730957,
      "learning_rate": 1.983909118486846e-05,
      "loss": 0.5651,
      "step": 3818
    },
    {
      "epoch": 0.1173163763708414,
      "grad_norm": 0.34915685653686523,
      "learning_rate": 1.98390048263823e-05,
      "loss": 0.5749,
      "step": 3819
    },
    {
      "epoch": 0.11734709550579056,
      "grad_norm": 0.3903295695781708,
      "learning_rate": 1.9838918444916456e-05,
      "loss": 0.6288,
      "step": 3820
    },
    {
      "epoch": 0.11737781464073972,
      "grad_norm": 0.36053407192230225,
      "learning_rate": 1.983883204047113e-05,
      "loss": 0.5076,
      "step": 3821
    },
    {
      "epoch": 0.11740853377568887,
      "grad_norm": 0.35079336166381836,
      "learning_rate": 1.9838745613046526e-05,
      "loss": 0.6153,
      "step": 3822
    },
    {
      "epoch": 0.11743925291063803,
      "grad_norm": 0.3538878858089447,
      "learning_rate": 1.9838659162642843e-05,
      "loss": 0.6409,
      "step": 3823
    },
    {
      "epoch": 0.11746997204558719,
      "grad_norm": 0.33198291063308716,
      "learning_rate": 1.9838572689260288e-05,
      "loss": 0.6063,
      "step": 3824
    },
    {
      "epoch": 0.11750069118053635,
      "grad_norm": 0.4453510046005249,
      "learning_rate": 1.9838486192899057e-05,
      "loss": 0.6036,
      "step": 3825
    },
    {
      "epoch": 0.11753141031548552,
      "grad_norm": 0.3433864116668701,
      "learning_rate": 1.9838399673559353e-05,
      "loss": 0.6457,
      "step": 3826
    },
    {
      "epoch": 0.11756212945043468,
      "grad_norm": 0.3363216817378998,
      "learning_rate": 1.9838313131241384e-05,
      "loss": 0.6801,
      "step": 3827
    },
    {
      "epoch": 0.11759284858538384,
      "grad_norm": 0.32750171422958374,
      "learning_rate": 1.983822656594534e-05,
      "loss": 0.5869,
      "step": 3828
    },
    {
      "epoch": 0.117623567720333,
      "grad_norm": 0.31059730052948,
      "learning_rate": 1.9838139977671437e-05,
      "loss": 0.5051,
      "step": 3829
    },
    {
      "epoch": 0.11765428685528216,
      "grad_norm": 0.33741238713264465,
      "learning_rate": 1.9838053366419867e-05,
      "loss": 0.5908,
      "step": 3830
    },
    {
      "epoch": 0.11768500599023131,
      "grad_norm": 0.3483133614063263,
      "learning_rate": 1.983796673219084e-05,
      "loss": 0.5663,
      "step": 3831
    },
    {
      "epoch": 0.11771572512518047,
      "grad_norm": 0.346077024936676,
      "learning_rate": 1.9837880074984554e-05,
      "loss": 0.6599,
      "step": 3832
    },
    {
      "epoch": 0.11774644426012963,
      "grad_norm": 0.3484307527542114,
      "learning_rate": 1.983779339480121e-05,
      "loss": 0.6264,
      "step": 3833
    },
    {
      "epoch": 0.1177771633950788,
      "grad_norm": 0.3494051694869995,
      "learning_rate": 1.9837706691641014e-05,
      "loss": 0.6573,
      "step": 3834
    },
    {
      "epoch": 0.11780788253002795,
      "grad_norm": 0.3423261344432831,
      "learning_rate": 1.9837619965504166e-05,
      "loss": 0.5985,
      "step": 3835
    },
    {
      "epoch": 0.11783860166497712,
      "grad_norm": 0.4452187418937683,
      "learning_rate": 1.9837533216390868e-05,
      "loss": 0.6038,
      "step": 3836
    },
    {
      "epoch": 0.11786932079992628,
      "grad_norm": 0.35844603180885315,
      "learning_rate": 1.9837446444301327e-05,
      "loss": 0.5782,
      "step": 3837
    },
    {
      "epoch": 0.11790003993487544,
      "grad_norm": 0.3511697053909302,
      "learning_rate": 1.9837359649235743e-05,
      "loss": 0.5472,
      "step": 3838
    },
    {
      "epoch": 0.1179307590698246,
      "grad_norm": 0.3367350995540619,
      "learning_rate": 1.9837272831194316e-05,
      "loss": 0.6328,
      "step": 3839
    },
    {
      "epoch": 0.11796147820477375,
      "grad_norm": 0.32530418038368225,
      "learning_rate": 1.9837185990177256e-05,
      "loss": 0.5681,
      "step": 3840
    },
    {
      "epoch": 0.11799219733972291,
      "grad_norm": 0.35378775000572205,
      "learning_rate": 1.9837099126184755e-05,
      "loss": 0.5468,
      "step": 3841
    },
    {
      "epoch": 0.11802291647467207,
      "grad_norm": 0.3151406943798065,
      "learning_rate": 1.9837012239217025e-05,
      "loss": 0.6262,
      "step": 3842
    },
    {
      "epoch": 0.11805363560962123,
      "grad_norm": 0.3474234640598297,
      "learning_rate": 1.9836925329274265e-05,
      "loss": 0.6024,
      "step": 3843
    },
    {
      "epoch": 0.1180843547445704,
      "grad_norm": 0.35663512349128723,
      "learning_rate": 1.9836838396356677e-05,
      "loss": 0.6183,
      "step": 3844
    },
    {
      "epoch": 0.11811507387951956,
      "grad_norm": 0.3165830373764038,
      "learning_rate": 1.9836751440464473e-05,
      "loss": 0.5777,
      "step": 3845
    },
    {
      "epoch": 0.11814579301446872,
      "grad_norm": 0.34394243359565735,
      "learning_rate": 1.9836664461597843e-05,
      "loss": 0.6572,
      "step": 3846
    },
    {
      "epoch": 0.11817651214941788,
      "grad_norm": 0.3493430018424988,
      "learning_rate": 1.9836577459756998e-05,
      "loss": 0.547,
      "step": 3847
    },
    {
      "epoch": 0.11820723128436703,
      "grad_norm": 0.35046690702438354,
      "learning_rate": 1.983649043494214e-05,
      "loss": 0.5032,
      "step": 3848
    },
    {
      "epoch": 0.11823795041931619,
      "grad_norm": 0.3600539267063141,
      "learning_rate": 1.9836403387153468e-05,
      "loss": 0.6485,
      "step": 3849
    },
    {
      "epoch": 0.11826866955426535,
      "grad_norm": 0.35563549399375916,
      "learning_rate": 1.9836316316391192e-05,
      "loss": 0.597,
      "step": 3850
    },
    {
      "epoch": 0.11829938868921451,
      "grad_norm": 0.34732431173324585,
      "learning_rate": 1.9836229222655513e-05,
      "loss": 0.5515,
      "step": 3851
    },
    {
      "epoch": 0.11833010782416367,
      "grad_norm": 0.39190781116485596,
      "learning_rate": 1.9836142105946633e-05,
      "loss": 0.6264,
      "step": 3852
    },
    {
      "epoch": 0.11836082695911283,
      "grad_norm": 0.33471590280532837,
      "learning_rate": 1.9836054966264756e-05,
      "loss": 0.7082,
      "step": 3853
    },
    {
      "epoch": 0.118391546094062,
      "grad_norm": 0.2903788685798645,
      "learning_rate": 1.9835967803610082e-05,
      "loss": 0.5498,
      "step": 3854
    },
    {
      "epoch": 0.11842226522901116,
      "grad_norm": 0.33770647644996643,
      "learning_rate": 1.9835880617982824e-05,
      "loss": 0.5813,
      "step": 3855
    },
    {
      "epoch": 0.11845298436396032,
      "grad_norm": 0.3273617923259735,
      "learning_rate": 1.9835793409383178e-05,
      "loss": 0.6033,
      "step": 3856
    },
    {
      "epoch": 0.11848370349890947,
      "grad_norm": 0.4108556807041168,
      "learning_rate": 1.983570617781135e-05,
      "loss": 0.6154,
      "step": 3857
    },
    {
      "epoch": 0.11851442263385863,
      "grad_norm": 0.32634884119033813,
      "learning_rate": 1.9835618923267542e-05,
      "loss": 0.6398,
      "step": 3858
    },
    {
      "epoch": 0.11854514176880779,
      "grad_norm": 0.35963988304138184,
      "learning_rate": 1.983553164575196e-05,
      "loss": 0.5995,
      "step": 3859
    },
    {
      "epoch": 0.11857586090375695,
      "grad_norm": 0.3171011805534363,
      "learning_rate": 1.9835444345264805e-05,
      "loss": 0.6097,
      "step": 3860
    },
    {
      "epoch": 0.11860658003870611,
      "grad_norm": 0.34885114431381226,
      "learning_rate": 1.9835357021806283e-05,
      "loss": 0.6725,
      "step": 3861
    },
    {
      "epoch": 0.11863729917365527,
      "grad_norm": 0.33659636974334717,
      "learning_rate": 1.98352696753766e-05,
      "loss": 0.6263,
      "step": 3862
    },
    {
      "epoch": 0.11866801830860443,
      "grad_norm": 0.345864862203598,
      "learning_rate": 1.9835182305975958e-05,
      "loss": 0.6878,
      "step": 3863
    },
    {
      "epoch": 0.1186987374435536,
      "grad_norm": 0.3344501256942749,
      "learning_rate": 1.983509491360456e-05,
      "loss": 0.6976,
      "step": 3864
    },
    {
      "epoch": 0.11872945657850274,
      "grad_norm": 0.3600524663925171,
      "learning_rate": 1.983500749826261e-05,
      "loss": 0.5744,
      "step": 3865
    },
    {
      "epoch": 0.1187601757134519,
      "grad_norm": 0.34627002477645874,
      "learning_rate": 1.9834920059950312e-05,
      "loss": 0.6329,
      "step": 3866
    },
    {
      "epoch": 0.11879089484840107,
      "grad_norm": 0.3632673919200897,
      "learning_rate": 1.9834832598667874e-05,
      "loss": 0.6597,
      "step": 3867
    },
    {
      "epoch": 0.11882161398335023,
      "grad_norm": 0.3345303535461426,
      "learning_rate": 1.9834745114415498e-05,
      "loss": 0.6314,
      "step": 3868
    },
    {
      "epoch": 0.11885233311829939,
      "grad_norm": 0.34338265657424927,
      "learning_rate": 1.9834657607193387e-05,
      "loss": 0.6468,
      "step": 3869
    },
    {
      "epoch": 0.11888305225324855,
      "grad_norm": 0.3748895227909088,
      "learning_rate": 1.9834570077001745e-05,
      "loss": 0.5923,
      "step": 3870
    },
    {
      "epoch": 0.11891377138819771,
      "grad_norm": 0.32660892605781555,
      "learning_rate": 1.983448252384078e-05,
      "loss": 0.5221,
      "step": 3871
    },
    {
      "epoch": 0.11894449052314687,
      "grad_norm": 0.3502084016799927,
      "learning_rate": 1.9834394947710692e-05,
      "loss": 0.6627,
      "step": 3872
    },
    {
      "epoch": 0.11897520965809603,
      "grad_norm": 0.30891314148902893,
      "learning_rate": 1.9834307348611686e-05,
      "loss": 0.5511,
      "step": 3873
    },
    {
      "epoch": 0.11900592879304518,
      "grad_norm": 0.3325452506542206,
      "learning_rate": 1.9834219726543973e-05,
      "loss": 0.5449,
      "step": 3874
    },
    {
      "epoch": 0.11903664792799434,
      "grad_norm": 0.5842499136924744,
      "learning_rate": 1.9834132081507752e-05,
      "loss": 0.6583,
      "step": 3875
    },
    {
      "epoch": 0.1190673670629435,
      "grad_norm": 0.3352312445640564,
      "learning_rate": 1.9834044413503227e-05,
      "loss": 0.631,
      "step": 3876
    },
    {
      "epoch": 0.11909808619789267,
      "grad_norm": 0.3834969699382782,
      "learning_rate": 1.9833956722530607e-05,
      "loss": 0.6591,
      "step": 3877
    },
    {
      "epoch": 0.11912880533284183,
      "grad_norm": 0.3675040900707245,
      "learning_rate": 1.983386900859009e-05,
      "loss": 0.5557,
      "step": 3878
    },
    {
      "epoch": 0.11915952446779099,
      "grad_norm": 0.3189936578273773,
      "learning_rate": 1.9833781271681885e-05,
      "loss": 0.618,
      "step": 3879
    },
    {
      "epoch": 0.11919024360274015,
      "grad_norm": 0.34971049427986145,
      "learning_rate": 1.9833693511806204e-05,
      "loss": 0.5779,
      "step": 3880
    },
    {
      "epoch": 0.11922096273768931,
      "grad_norm": 0.33449026942253113,
      "learning_rate": 1.9833605728963242e-05,
      "loss": 0.5387,
      "step": 3881
    },
    {
      "epoch": 0.11925168187263846,
      "grad_norm": 0.3554786741733551,
      "learning_rate": 1.9833517923153205e-05,
      "loss": 0.6796,
      "step": 3882
    },
    {
      "epoch": 0.11928240100758762,
      "grad_norm": 0.33844923973083496,
      "learning_rate": 1.98334300943763e-05,
      "loss": 0.5773,
      "step": 3883
    },
    {
      "epoch": 0.11931312014253678,
      "grad_norm": 0.3381737470626831,
      "learning_rate": 1.983334224263273e-05,
      "loss": 0.6867,
      "step": 3884
    },
    {
      "epoch": 0.11934383927748594,
      "grad_norm": 0.34445738792419434,
      "learning_rate": 1.983325436792271e-05,
      "loss": 0.6461,
      "step": 3885
    },
    {
      "epoch": 0.1193745584124351,
      "grad_norm": 0.31351014971733093,
      "learning_rate": 1.9833166470246433e-05,
      "loss": 0.5947,
      "step": 3886
    },
    {
      "epoch": 0.11940527754738427,
      "grad_norm": 0.37371188402175903,
      "learning_rate": 1.983307854960411e-05,
      "loss": 0.5805,
      "step": 3887
    },
    {
      "epoch": 0.11943599668233343,
      "grad_norm": 0.33106374740600586,
      "learning_rate": 1.983299060599594e-05,
      "loss": 0.6741,
      "step": 3888
    },
    {
      "epoch": 0.11946671581728259,
      "grad_norm": 0.32118386030197144,
      "learning_rate": 1.983290263942214e-05,
      "loss": 0.6814,
      "step": 3889
    },
    {
      "epoch": 0.11949743495223175,
      "grad_norm": 0.317035973072052,
      "learning_rate": 1.9832814649882908e-05,
      "loss": 0.5218,
      "step": 3890
    },
    {
      "epoch": 0.1195281540871809,
      "grad_norm": 0.35566845536231995,
      "learning_rate": 1.983272663737845e-05,
      "loss": 0.6273,
      "step": 3891
    },
    {
      "epoch": 0.11955887322213006,
      "grad_norm": 0.3858028054237366,
      "learning_rate": 1.9832638601908972e-05,
      "loss": 0.5585,
      "step": 3892
    },
    {
      "epoch": 0.11958959235707922,
      "grad_norm": 0.3593459725379944,
      "learning_rate": 1.9832550543474683e-05,
      "loss": 0.6332,
      "step": 3893
    },
    {
      "epoch": 0.11962031149202838,
      "grad_norm": 0.33717164397239685,
      "learning_rate": 1.983246246207578e-05,
      "loss": 0.6388,
      "step": 3894
    },
    {
      "epoch": 0.11965103062697754,
      "grad_norm": 0.35333141684532166,
      "learning_rate": 1.9832374357712475e-05,
      "loss": 0.6424,
      "step": 3895
    },
    {
      "epoch": 0.1196817497619267,
      "grad_norm": 0.4183734357357025,
      "learning_rate": 1.9832286230384977e-05,
      "loss": 0.5967,
      "step": 3896
    },
    {
      "epoch": 0.11971246889687587,
      "grad_norm": 0.32164302468299866,
      "learning_rate": 1.9832198080093485e-05,
      "loss": 0.5661,
      "step": 3897
    },
    {
      "epoch": 0.11974318803182503,
      "grad_norm": 0.3270011842250824,
      "learning_rate": 1.983210990683821e-05,
      "loss": 0.5604,
      "step": 3898
    },
    {
      "epoch": 0.11977390716677418,
      "grad_norm": 0.3338240385055542,
      "learning_rate": 1.9832021710619355e-05,
      "loss": 0.6621,
      "step": 3899
    },
    {
      "epoch": 0.11980462630172334,
      "grad_norm": 0.31285688281059265,
      "learning_rate": 1.9831933491437124e-05,
      "loss": 0.638,
      "step": 3900
    },
    {
      "epoch": 0.1198353454366725,
      "grad_norm": 0.3494952917098999,
      "learning_rate": 1.983184524929173e-05,
      "loss": 0.5914,
      "step": 3901
    },
    {
      "epoch": 0.11986606457162166,
      "grad_norm": 0.46165359020233154,
      "learning_rate": 1.983175698418337e-05,
      "loss": 0.5944,
      "step": 3902
    },
    {
      "epoch": 0.11989678370657082,
      "grad_norm": 0.3261806070804596,
      "learning_rate": 1.9831668696112257e-05,
      "loss": 0.6334,
      "step": 3903
    },
    {
      "epoch": 0.11992750284151998,
      "grad_norm": 0.35612115263938904,
      "learning_rate": 1.9831580385078596e-05,
      "loss": 0.6868,
      "step": 3904
    },
    {
      "epoch": 0.11995822197646915,
      "grad_norm": 0.4452011287212372,
      "learning_rate": 1.983149205108259e-05,
      "loss": 0.5628,
      "step": 3905
    },
    {
      "epoch": 0.1199889411114183,
      "grad_norm": 0.33042868971824646,
      "learning_rate": 1.9831403694124448e-05,
      "loss": 0.6068,
      "step": 3906
    },
    {
      "epoch": 0.12001966024636747,
      "grad_norm": 0.3113292157649994,
      "learning_rate": 1.983131531420438e-05,
      "loss": 0.5913,
      "step": 3907
    },
    {
      "epoch": 0.12005037938131662,
      "grad_norm": 0.3179704546928406,
      "learning_rate": 1.9831226911322584e-05,
      "loss": 0.5751,
      "step": 3908
    },
    {
      "epoch": 0.12008109851626578,
      "grad_norm": 0.8271068930625916,
      "learning_rate": 1.9831138485479276e-05,
      "loss": 0.7179,
      "step": 3909
    },
    {
      "epoch": 0.12011181765121494,
      "grad_norm": 0.33125758171081543,
      "learning_rate": 1.9831050036674653e-05,
      "loss": 0.691,
      "step": 3910
    },
    {
      "epoch": 0.1201425367861641,
      "grad_norm": 0.3675740957260132,
      "learning_rate": 1.9830961564908926e-05,
      "loss": 0.6536,
      "step": 3911
    },
    {
      "epoch": 0.12017325592111326,
      "grad_norm": 0.42607542872428894,
      "learning_rate": 1.9830873070182304e-05,
      "loss": 0.5145,
      "step": 3912
    },
    {
      "epoch": 0.12020397505606242,
      "grad_norm": 0.35502108931541443,
      "learning_rate": 1.983078455249499e-05,
      "loss": 0.5938,
      "step": 3913
    },
    {
      "epoch": 0.12023469419101158,
      "grad_norm": 0.34407833218574524,
      "learning_rate": 1.983069601184719e-05,
      "loss": 0.6589,
      "step": 3914
    },
    {
      "epoch": 0.12026541332596075,
      "grad_norm": 0.5482780933380127,
      "learning_rate": 1.9830607448239118e-05,
      "loss": 0.6676,
      "step": 3915
    },
    {
      "epoch": 0.12029613246090991,
      "grad_norm": 0.37145930528640747,
      "learning_rate": 1.9830518861670973e-05,
      "loss": 0.5876,
      "step": 3916
    },
    {
      "epoch": 0.12032685159585906,
      "grad_norm": 0.33146893978118896,
      "learning_rate": 1.9830430252142966e-05,
      "loss": 0.6269,
      "step": 3917
    },
    {
      "epoch": 0.12035757073080822,
      "grad_norm": 0.3547433316707611,
      "learning_rate": 1.98303416196553e-05,
      "loss": 0.5836,
      "step": 3918
    },
    {
      "epoch": 0.12038828986575738,
      "grad_norm": 0.35710620880126953,
      "learning_rate": 1.9830252964208186e-05,
      "loss": 0.6977,
      "step": 3919
    },
    {
      "epoch": 0.12041900900070654,
      "grad_norm": 0.3274984061717987,
      "learning_rate": 1.983016428580183e-05,
      "loss": 0.6498,
      "step": 3920
    },
    {
      "epoch": 0.1204497281356557,
      "grad_norm": 0.3938191533088684,
      "learning_rate": 1.9830075584436437e-05,
      "loss": 0.5975,
      "step": 3921
    },
    {
      "epoch": 0.12048044727060486,
      "grad_norm": 0.3467743694782257,
      "learning_rate": 1.9829986860112217e-05,
      "loss": 0.6599,
      "step": 3922
    },
    {
      "epoch": 0.12051116640555402,
      "grad_norm": 0.346174955368042,
      "learning_rate": 1.982989811282938e-05,
      "loss": 0.6363,
      "step": 3923
    },
    {
      "epoch": 0.12054188554050319,
      "grad_norm": 0.33710408210754395,
      "learning_rate": 1.9829809342588126e-05,
      "loss": 0.5381,
      "step": 3924
    },
    {
      "epoch": 0.12057260467545233,
      "grad_norm": 0.3725569546222687,
      "learning_rate": 1.9829720549388662e-05,
      "loss": 0.6222,
      "step": 3925
    },
    {
      "epoch": 0.1206033238104015,
      "grad_norm": 0.3377701938152313,
      "learning_rate": 1.9829631733231207e-05,
      "loss": 0.6047,
      "step": 3926
    },
    {
      "epoch": 0.12063404294535066,
      "grad_norm": 0.3403909504413605,
      "learning_rate": 1.9829542894115953e-05,
      "loss": 0.673,
      "step": 3927
    },
    {
      "epoch": 0.12066476208029982,
      "grad_norm": 0.38384753465652466,
      "learning_rate": 1.982945403204312e-05,
      "loss": 0.5977,
      "step": 3928
    },
    {
      "epoch": 0.12069548121524898,
      "grad_norm": 0.3164873719215393,
      "learning_rate": 1.982936514701291e-05,
      "loss": 0.5639,
      "step": 3929
    },
    {
      "epoch": 0.12072620035019814,
      "grad_norm": 0.41482552886009216,
      "learning_rate": 1.982927623902553e-05,
      "loss": 0.5967,
      "step": 3930
    },
    {
      "epoch": 0.1207569194851473,
      "grad_norm": 0.35810133814811707,
      "learning_rate": 1.9829187308081188e-05,
      "loss": 0.5431,
      "step": 3931
    },
    {
      "epoch": 0.12078763862009646,
      "grad_norm": 0.3880980610847473,
      "learning_rate": 1.9829098354180095e-05,
      "loss": 0.6813,
      "step": 3932
    },
    {
      "epoch": 0.12081835775504562,
      "grad_norm": 0.38677525520324707,
      "learning_rate": 1.9829009377322455e-05,
      "loss": 0.5897,
      "step": 3933
    },
    {
      "epoch": 0.12084907688999477,
      "grad_norm": 0.37059515714645386,
      "learning_rate": 1.9828920377508477e-05,
      "loss": 0.5981,
      "step": 3934
    },
    {
      "epoch": 0.12087979602494393,
      "grad_norm": 0.37518709897994995,
      "learning_rate": 1.9828831354738368e-05,
      "loss": 0.7018,
      "step": 3935
    },
    {
      "epoch": 0.1209105151598931,
      "grad_norm": 0.35395392775535583,
      "learning_rate": 1.982874230901234e-05,
      "loss": 0.5805,
      "step": 3936
    },
    {
      "epoch": 0.12094123429484226,
      "grad_norm": 0.3598932921886444,
      "learning_rate": 1.9828653240330596e-05,
      "loss": 0.6751,
      "step": 3937
    },
    {
      "epoch": 0.12097195342979142,
      "grad_norm": 0.33778977394104004,
      "learning_rate": 1.9828564148693344e-05,
      "loss": 0.5732,
      "step": 3938
    },
    {
      "epoch": 0.12100267256474058,
      "grad_norm": 0.40862467885017395,
      "learning_rate": 1.9828475034100798e-05,
      "loss": 0.5727,
      "step": 3939
    },
    {
      "epoch": 0.12103339169968974,
      "grad_norm": 0.4066392183303833,
      "learning_rate": 1.982838589655316e-05,
      "loss": 0.5524,
      "step": 3940
    },
    {
      "epoch": 0.1210641108346389,
      "grad_norm": 0.3237483501434326,
      "learning_rate": 1.9828296736050642e-05,
      "loss": 0.5487,
      "step": 3941
    },
    {
      "epoch": 0.12109482996958805,
      "grad_norm": 0.39570796489715576,
      "learning_rate": 1.982820755259345e-05,
      "loss": 0.5519,
      "step": 3942
    },
    {
      "epoch": 0.12112554910453721,
      "grad_norm": 0.3457581400871277,
      "learning_rate": 1.982811834618179e-05,
      "loss": 0.5305,
      "step": 3943
    },
    {
      "epoch": 0.12115626823948637,
      "grad_norm": 0.41069817543029785,
      "learning_rate": 1.9828029116815876e-05,
      "loss": 0.6147,
      "step": 3944
    },
    {
      "epoch": 0.12118698737443553,
      "grad_norm": 0.36869239807128906,
      "learning_rate": 1.982793986449591e-05,
      "loss": 0.6376,
      "step": 3945
    },
    {
      "epoch": 0.1212177065093847,
      "grad_norm": 0.3301643133163452,
      "learning_rate": 1.9827850589222112e-05,
      "loss": 0.6026,
      "step": 3946
    },
    {
      "epoch": 0.12124842564433386,
      "grad_norm": 0.3382440209388733,
      "learning_rate": 1.9827761290994676e-05,
      "loss": 0.604,
      "step": 3947
    },
    {
      "epoch": 0.12127914477928302,
      "grad_norm": 0.34945160150527954,
      "learning_rate": 1.9827671969813816e-05,
      "loss": 0.6132,
      "step": 3948
    },
    {
      "epoch": 0.12130986391423218,
      "grad_norm": 0.348328560590744,
      "learning_rate": 1.9827582625679745e-05,
      "loss": 0.6777,
      "step": 3949
    },
    {
      "epoch": 0.12134058304918134,
      "grad_norm": 0.34425222873687744,
      "learning_rate": 1.982749325859267e-05,
      "loss": 0.4752,
      "step": 3950
    },
    {
      "epoch": 0.12137130218413049,
      "grad_norm": 0.3280732035636902,
      "learning_rate": 1.9827403868552796e-05,
      "loss": 0.6825,
      "step": 3951
    },
    {
      "epoch": 0.12140202131907965,
      "grad_norm": 0.3628527522087097,
      "learning_rate": 1.9827314455560334e-05,
      "loss": 0.6261,
      "step": 3952
    },
    {
      "epoch": 0.12143274045402881,
      "grad_norm": 0.5230919122695923,
      "learning_rate": 1.982722501961549e-05,
      "loss": 0.5608,
      "step": 3953
    },
    {
      "epoch": 0.12146345958897797,
      "grad_norm": 0.3235064446926117,
      "learning_rate": 1.982713556071848e-05,
      "loss": 0.5473,
      "step": 3954
    },
    {
      "epoch": 0.12149417872392713,
      "grad_norm": 0.4075738489627838,
      "learning_rate": 1.982704607886951e-05,
      "loss": 0.6289,
      "step": 3955
    },
    {
      "epoch": 0.1215248978588763,
      "grad_norm": 0.39766696095466614,
      "learning_rate": 1.9826956574068782e-05,
      "loss": 0.6519,
      "step": 3956
    },
    {
      "epoch": 0.12155561699382546,
      "grad_norm": 0.32231828570365906,
      "learning_rate": 1.982686704631651e-05,
      "loss": 0.6576,
      "step": 3957
    },
    {
      "epoch": 0.12158633612877462,
      "grad_norm": 0.33975353837013245,
      "learning_rate": 1.9826777495612908e-05,
      "loss": 0.5573,
      "step": 3958
    },
    {
      "epoch": 0.12161705526372377,
      "grad_norm": 0.36280354857444763,
      "learning_rate": 1.982668792195818e-05,
      "loss": 0.6411,
      "step": 3959
    },
    {
      "epoch": 0.12164777439867293,
      "grad_norm": 0.36505335569381714,
      "learning_rate": 1.9826598325352537e-05,
      "loss": 0.6328,
      "step": 3960
    },
    {
      "epoch": 0.12167849353362209,
      "grad_norm": 0.32857245206832886,
      "learning_rate": 1.9826508705796186e-05,
      "loss": 0.6363,
      "step": 3961
    },
    {
      "epoch": 0.12170921266857125,
      "grad_norm": 0.3662493824958801,
      "learning_rate": 1.982641906328934e-05,
      "loss": 0.6378,
      "step": 3962
    },
    {
      "epoch": 0.12173993180352041,
      "grad_norm": 0.35013043880462646,
      "learning_rate": 1.98263293978322e-05,
      "loss": 0.6158,
      "step": 3963
    },
    {
      "epoch": 0.12177065093846957,
      "grad_norm": 0.4397788345813751,
      "learning_rate": 1.9826239709424984e-05,
      "loss": 0.6515,
      "step": 3964
    },
    {
      "epoch": 0.12180137007341874,
      "grad_norm": 0.3326026201248169,
      "learning_rate": 1.9826149998067904e-05,
      "loss": 0.6147,
      "step": 3965
    },
    {
      "epoch": 0.1218320892083679,
      "grad_norm": 0.37156540155410767,
      "learning_rate": 1.9826060263761158e-05,
      "loss": 0.5788,
      "step": 3966
    },
    {
      "epoch": 0.12186280834331706,
      "grad_norm": 0.40321114659309387,
      "learning_rate": 1.9825970506504965e-05,
      "loss": 0.7567,
      "step": 3967
    },
    {
      "epoch": 0.1218935274782662,
      "grad_norm": 0.34397241473197937,
      "learning_rate": 1.9825880726299532e-05,
      "loss": 0.547,
      "step": 3968
    },
    {
      "epoch": 0.12192424661321537,
      "grad_norm": 0.30680570006370544,
      "learning_rate": 1.9825790923145066e-05,
      "loss": 0.6319,
      "step": 3969
    },
    {
      "epoch": 0.12195496574816453,
      "grad_norm": 0.32828232645988464,
      "learning_rate": 1.982570109704178e-05,
      "loss": 0.6188,
      "step": 3970
    },
    {
      "epoch": 0.12198568488311369,
      "grad_norm": 0.40697893500328064,
      "learning_rate": 1.9825611247989887e-05,
      "loss": 0.5798,
      "step": 3971
    },
    {
      "epoch": 0.12201640401806285,
      "grad_norm": 0.32895222306251526,
      "learning_rate": 1.9825521375989586e-05,
      "loss": 0.6937,
      "step": 3972
    },
    {
      "epoch": 0.12204712315301201,
      "grad_norm": 0.3389405608177185,
      "learning_rate": 1.9825431481041096e-05,
      "loss": 0.7321,
      "step": 3973
    },
    {
      "epoch": 0.12207784228796117,
      "grad_norm": 0.34431394934654236,
      "learning_rate": 1.9825341563144627e-05,
      "loss": 0.596,
      "step": 3974
    },
    {
      "epoch": 0.12210856142291034,
      "grad_norm": 0.3791449964046478,
      "learning_rate": 1.9825251622300386e-05,
      "loss": 0.5922,
      "step": 3975
    },
    {
      "epoch": 0.1221392805578595,
      "grad_norm": 0.37983354926109314,
      "learning_rate": 1.982516165850858e-05,
      "loss": 0.6301,
      "step": 3976
    },
    {
      "epoch": 0.12216999969280865,
      "grad_norm": 0.4144596755504608,
      "learning_rate": 1.9825071671769428e-05,
      "loss": 0.5662,
      "step": 3977
    },
    {
      "epoch": 0.1222007188277578,
      "grad_norm": 0.34635189175605774,
      "learning_rate": 1.9824981662083133e-05,
      "loss": 0.6157,
      "step": 3978
    },
    {
      "epoch": 0.12223143796270697,
      "grad_norm": 0.4916316568851471,
      "learning_rate": 1.9824891629449905e-05,
      "loss": 0.6309,
      "step": 3979
    },
    {
      "epoch": 0.12226215709765613,
      "grad_norm": 0.3522813618183136,
      "learning_rate": 1.9824801573869958e-05,
      "loss": 0.5777,
      "step": 3980
    },
    {
      "epoch": 0.12229287623260529,
      "grad_norm": 0.33436158299446106,
      "learning_rate": 1.98247114953435e-05,
      "loss": 0.6122,
      "step": 3981
    },
    {
      "epoch": 0.12232359536755445,
      "grad_norm": 0.3479422926902771,
      "learning_rate": 1.9824621393870745e-05,
      "loss": 0.5839,
      "step": 3982
    },
    {
      "epoch": 0.12235431450250361,
      "grad_norm": 0.3738364279270172,
      "learning_rate": 1.9824531269451895e-05,
      "loss": 0.6317,
      "step": 3983
    },
    {
      "epoch": 0.12238503363745278,
      "grad_norm": 0.3325660526752472,
      "learning_rate": 1.982444112208717e-05,
      "loss": 0.5761,
      "step": 3984
    },
    {
      "epoch": 0.12241575277240192,
      "grad_norm": 0.4070984423160553,
      "learning_rate": 1.9824350951776777e-05,
      "loss": 0.6037,
      "step": 3985
    },
    {
      "epoch": 0.12244647190735108,
      "grad_norm": 0.3364180028438568,
      "learning_rate": 1.9824260758520925e-05,
      "loss": 0.6233,
      "step": 3986
    },
    {
      "epoch": 0.12247719104230025,
      "grad_norm": 0.34717434644699097,
      "learning_rate": 1.9824170542319824e-05,
      "loss": 0.6043,
      "step": 3987
    },
    {
      "epoch": 0.12250791017724941,
      "grad_norm": 0.3137715458869934,
      "learning_rate": 1.9824080303173692e-05,
      "loss": 0.5445,
      "step": 3988
    },
    {
      "epoch": 0.12253862931219857,
      "grad_norm": 0.34967148303985596,
      "learning_rate": 1.982399004108273e-05,
      "loss": 0.6045,
      "step": 3989
    },
    {
      "epoch": 0.12256934844714773,
      "grad_norm": 0.34322500228881836,
      "learning_rate": 1.9823899756047154e-05,
      "loss": 0.6196,
      "step": 3990
    },
    {
      "epoch": 0.12260006758209689,
      "grad_norm": 0.3416459858417511,
      "learning_rate": 1.9823809448067174e-05,
      "loss": 0.6035,
      "step": 3991
    },
    {
      "epoch": 0.12263078671704605,
      "grad_norm": 0.33335167169570923,
      "learning_rate": 1.9823719117143003e-05,
      "loss": 0.5563,
      "step": 3992
    },
    {
      "epoch": 0.12266150585199521,
      "grad_norm": 0.34754320979118347,
      "learning_rate": 1.9823628763274847e-05,
      "loss": 0.6162,
      "step": 3993
    },
    {
      "epoch": 0.12269222498694436,
      "grad_norm": 0.29994997382164,
      "learning_rate": 1.982353838646292e-05,
      "loss": 0.5561,
      "step": 3994
    },
    {
      "epoch": 0.12272294412189352,
      "grad_norm": 0.3437344431877136,
      "learning_rate": 1.9823447986707436e-05,
      "loss": 0.6195,
      "step": 3995
    },
    {
      "epoch": 0.12275366325684268,
      "grad_norm": 0.33683550357818604,
      "learning_rate": 1.98233575640086e-05,
      "loss": 0.5331,
      "step": 3996
    },
    {
      "epoch": 0.12278438239179185,
      "grad_norm": 0.3869773745536804,
      "learning_rate": 1.9823267118366627e-05,
      "loss": 0.6351,
      "step": 3997
    },
    {
      "epoch": 0.12281510152674101,
      "grad_norm": 0.33615756034851074,
      "learning_rate": 1.982317664978173e-05,
      "loss": 0.5921,
      "step": 3998
    },
    {
      "epoch": 0.12284582066169017,
      "grad_norm": 0.434918075799942,
      "learning_rate": 1.9823086158254115e-05,
      "loss": 0.6165,
      "step": 3999
    },
    {
      "epoch": 0.12287653979663933,
      "grad_norm": 0.3312654495239258,
      "learning_rate": 1.9822995643784e-05,
      "loss": 0.6075,
      "step": 4000
    },
    {
      "epoch": 0.12290725893158849,
      "grad_norm": 0.341169148683548,
      "learning_rate": 1.9822905106371587e-05,
      "loss": 0.5655,
      "step": 4001
    },
    {
      "epoch": 0.12293797806653764,
      "grad_norm": 0.335526704788208,
      "learning_rate": 1.9822814546017097e-05,
      "loss": 0.54,
      "step": 4002
    },
    {
      "epoch": 0.1229686972014868,
      "grad_norm": 0.34037959575653076,
      "learning_rate": 1.9822723962720736e-05,
      "loss": 0.512,
      "step": 4003
    },
    {
      "epoch": 0.12299941633643596,
      "grad_norm": 0.35534003376960754,
      "learning_rate": 1.982263335648272e-05,
      "loss": 0.6263,
      "step": 4004
    },
    {
      "epoch": 0.12303013547138512,
      "grad_norm": 0.37607112526893616,
      "learning_rate": 1.9822542727303255e-05,
      "loss": 0.673,
      "step": 4005
    },
    {
      "epoch": 0.12306085460633429,
      "grad_norm": 0.3173495829105377,
      "learning_rate": 1.9822452075182557e-05,
      "loss": 0.5673,
      "step": 4006
    },
    {
      "epoch": 0.12309157374128345,
      "grad_norm": 0.35260820388793945,
      "learning_rate": 1.9822361400120833e-05,
      "loss": 0.5247,
      "step": 4007
    },
    {
      "epoch": 0.12312229287623261,
      "grad_norm": 1.023559331893921,
      "learning_rate": 1.98222707021183e-05,
      "loss": 0.5274,
      "step": 4008
    },
    {
      "epoch": 0.12315301201118177,
      "grad_norm": 0.34445062279701233,
      "learning_rate": 1.982217998117517e-05,
      "loss": 0.6498,
      "step": 4009
    },
    {
      "epoch": 0.12318373114613093,
      "grad_norm": 0.3192446231842041,
      "learning_rate": 1.982208923729165e-05,
      "loss": 0.598,
      "step": 4010
    },
    {
      "epoch": 0.12321445028108008,
      "grad_norm": 0.3213036358356476,
      "learning_rate": 1.9821998470467956e-05,
      "loss": 0.6102,
      "step": 4011
    },
    {
      "epoch": 0.12324516941602924,
      "grad_norm": 0.3353501260280609,
      "learning_rate": 1.98219076807043e-05,
      "loss": 0.5829,
      "step": 4012
    },
    {
      "epoch": 0.1232758885509784,
      "grad_norm": 0.3570382297039032,
      "learning_rate": 1.982181686800089e-05,
      "loss": 0.5752,
      "step": 4013
    },
    {
      "epoch": 0.12330660768592756,
      "grad_norm": 0.4134616553783417,
      "learning_rate": 1.982172603235794e-05,
      "loss": 0.573,
      "step": 4014
    },
    {
      "epoch": 0.12333732682087672,
      "grad_norm": 0.4141969084739685,
      "learning_rate": 1.9821635173775666e-05,
      "loss": 0.5871,
      "step": 4015
    },
    {
      "epoch": 0.12336804595582589,
      "grad_norm": 0.34857290983200073,
      "learning_rate": 1.9821544292254272e-05,
      "loss": 0.5816,
      "step": 4016
    },
    {
      "epoch": 0.12339876509077505,
      "grad_norm": 0.32643958926200867,
      "learning_rate": 1.9821453387793982e-05,
      "loss": 0.5542,
      "step": 4017
    },
    {
      "epoch": 0.12342948422572421,
      "grad_norm": 0.36153870820999146,
      "learning_rate": 1.9821362460394996e-05,
      "loss": 0.5405,
      "step": 4018
    },
    {
      "epoch": 0.12346020336067336,
      "grad_norm": 0.35618409514427185,
      "learning_rate": 1.9821271510057535e-05,
      "loss": 0.6565,
      "step": 4019
    },
    {
      "epoch": 0.12349092249562252,
      "grad_norm": 0.3445967137813568,
      "learning_rate": 1.982118053678181e-05,
      "loss": 0.6054,
      "step": 4020
    },
    {
      "epoch": 0.12352164163057168,
      "grad_norm": 0.32705429196357727,
      "learning_rate": 1.9821089540568027e-05,
      "loss": 0.5797,
      "step": 4021
    },
    {
      "epoch": 0.12355236076552084,
      "grad_norm": 0.36389535665512085,
      "learning_rate": 1.982099852141641e-05,
      "loss": 0.6561,
      "step": 4022
    },
    {
      "epoch": 0.12358307990047,
      "grad_norm": 0.41328972578048706,
      "learning_rate": 1.982090747932716e-05,
      "loss": 0.5125,
      "step": 4023
    },
    {
      "epoch": 0.12361379903541916,
      "grad_norm": 0.3937087059020996,
      "learning_rate": 1.9820816414300496e-05,
      "loss": 0.6931,
      "step": 4024
    },
    {
      "epoch": 0.12364451817036833,
      "grad_norm": 0.329829603433609,
      "learning_rate": 1.982072532633663e-05,
      "loss": 0.6015,
      "step": 4025
    },
    {
      "epoch": 0.12367523730531749,
      "grad_norm": 0.3478061258792877,
      "learning_rate": 1.9820634215435774e-05,
      "loss": 0.6173,
      "step": 4026
    },
    {
      "epoch": 0.12370595644026665,
      "grad_norm": 0.3430708646774292,
      "learning_rate": 1.9820543081598142e-05,
      "loss": 0.5596,
      "step": 4027
    },
    {
      "epoch": 0.1237366755752158,
      "grad_norm": 0.3253670334815979,
      "learning_rate": 1.9820451924823945e-05,
      "loss": 0.5575,
      "step": 4028
    },
    {
      "epoch": 0.12376739471016496,
      "grad_norm": 0.2984340786933899,
      "learning_rate": 1.9820360745113394e-05,
      "loss": 0.5504,
      "step": 4029
    },
    {
      "epoch": 0.12379811384511412,
      "grad_norm": 0.32694923877716064,
      "learning_rate": 1.982026954246671e-05,
      "loss": 0.6261,
      "step": 4030
    },
    {
      "epoch": 0.12382883298006328,
      "grad_norm": 0.3490961790084839,
      "learning_rate": 1.9820178316884096e-05,
      "loss": 0.6279,
      "step": 4031
    },
    {
      "epoch": 0.12385955211501244,
      "grad_norm": 0.3355979323387146,
      "learning_rate": 1.982008706836577e-05,
      "loss": 0.6135,
      "step": 4032
    },
    {
      "epoch": 0.1238902712499616,
      "grad_norm": 0.3568604290485382,
      "learning_rate": 1.9819995796911947e-05,
      "loss": 0.6029,
      "step": 4033
    },
    {
      "epoch": 0.12392099038491076,
      "grad_norm": 0.3725469410419464,
      "learning_rate": 1.981990450252284e-05,
      "loss": 0.6214,
      "step": 4034
    },
    {
      "epoch": 0.12395170951985993,
      "grad_norm": 0.33064812421798706,
      "learning_rate": 1.9819813185198653e-05,
      "loss": 0.6069,
      "step": 4035
    },
    {
      "epoch": 0.12398242865480907,
      "grad_norm": 0.3642444610595703,
      "learning_rate": 1.981972184493961e-05,
      "loss": 0.5816,
      "step": 4036
    },
    {
      "epoch": 0.12401314778975824,
      "grad_norm": 0.33744901418685913,
      "learning_rate": 1.9819630481745924e-05,
      "loss": 0.6184,
      "step": 4037
    },
    {
      "epoch": 0.1240438669247074,
      "grad_norm": 0.341227650642395,
      "learning_rate": 1.98195390956178e-05,
      "loss": 0.7287,
      "step": 4038
    },
    {
      "epoch": 0.12407458605965656,
      "grad_norm": 0.3672991096973419,
      "learning_rate": 1.981944768655546e-05,
      "loss": 0.6314,
      "step": 4039
    },
    {
      "epoch": 0.12410530519460572,
      "grad_norm": 0.32346588373184204,
      "learning_rate": 1.9819356254559115e-05,
      "loss": 0.5335,
      "step": 4040
    },
    {
      "epoch": 0.12413602432955488,
      "grad_norm": 0.3156619071960449,
      "learning_rate": 1.9819264799628975e-05,
      "loss": 0.534,
      "step": 4041
    },
    {
      "epoch": 0.12416674346450404,
      "grad_norm": 0.3547787666320801,
      "learning_rate": 1.9819173321765256e-05,
      "loss": 0.6041,
      "step": 4042
    },
    {
      "epoch": 0.1241974625994532,
      "grad_norm": 0.36787083745002747,
      "learning_rate": 1.9819081820968174e-05,
      "loss": 0.6687,
      "step": 4043
    },
    {
      "epoch": 0.12422818173440237,
      "grad_norm": 0.3263132572174072,
      "learning_rate": 1.9818990297237943e-05,
      "loss": 0.6019,
      "step": 4044
    },
    {
      "epoch": 0.12425890086935151,
      "grad_norm": 0.4869674742221832,
      "learning_rate": 1.9818898750574772e-05,
      "loss": 0.6187,
      "step": 4045
    },
    {
      "epoch": 0.12428962000430067,
      "grad_norm": 0.5172162055969238,
      "learning_rate": 1.9818807180978875e-05,
      "loss": 0.6106,
      "step": 4046
    },
    {
      "epoch": 0.12432033913924984,
      "grad_norm": 0.3472331166267395,
      "learning_rate": 1.981871558845047e-05,
      "loss": 0.5912,
      "step": 4047
    },
    {
      "epoch": 0.124351058274199,
      "grad_norm": 0.3214357793331146,
      "learning_rate": 1.981862397298977e-05,
      "loss": 0.6031,
      "step": 4048
    },
    {
      "epoch": 0.12438177740914816,
      "grad_norm": 0.3514290153980255,
      "learning_rate": 1.9818532334596985e-05,
      "loss": 0.6251,
      "step": 4049
    },
    {
      "epoch": 0.12441249654409732,
      "grad_norm": 0.36372897028923035,
      "learning_rate": 1.9818440673272333e-05,
      "loss": 0.555,
      "step": 4050
    },
    {
      "epoch": 0.12444321567904648,
      "grad_norm": 0.32103201746940613,
      "learning_rate": 1.981834898901603e-05,
      "loss": 0.5883,
      "step": 4051
    },
    {
      "epoch": 0.12447393481399564,
      "grad_norm": 0.33416178822517395,
      "learning_rate": 1.9818257281828287e-05,
      "loss": 0.6361,
      "step": 4052
    },
    {
      "epoch": 0.1245046539489448,
      "grad_norm": 0.3045358657836914,
      "learning_rate": 1.9818165551709313e-05,
      "loss": 0.6378,
      "step": 4053
    },
    {
      "epoch": 0.12453537308389395,
      "grad_norm": 0.32837557792663574,
      "learning_rate": 1.981807379865933e-05,
      "loss": 0.5781,
      "step": 4054
    },
    {
      "epoch": 0.12456609221884311,
      "grad_norm": 0.3130966126918793,
      "learning_rate": 1.9817982022678555e-05,
      "loss": 0.6105,
      "step": 4055
    },
    {
      "epoch": 0.12459681135379228,
      "grad_norm": 0.338255375623703,
      "learning_rate": 1.9817890223767194e-05,
      "loss": 0.6446,
      "step": 4056
    },
    {
      "epoch": 0.12462753048874144,
      "grad_norm": 0.3252028226852417,
      "learning_rate": 1.9817798401925465e-05,
      "loss": 0.5365,
      "step": 4057
    },
    {
      "epoch": 0.1246582496236906,
      "grad_norm": 0.3865405023097992,
      "learning_rate": 1.9817706557153578e-05,
      "loss": 0.6176,
      "step": 4058
    },
    {
      "epoch": 0.12468896875863976,
      "grad_norm": 0.3588906526565552,
      "learning_rate": 1.9817614689451757e-05,
      "loss": 0.6364,
      "step": 4059
    },
    {
      "epoch": 0.12471968789358892,
      "grad_norm": 0.3471241891384125,
      "learning_rate": 1.981752279882021e-05,
      "loss": 0.6205,
      "step": 4060
    },
    {
      "epoch": 0.12475040702853808,
      "grad_norm": 0.394599974155426,
      "learning_rate": 1.981743088525915e-05,
      "loss": 0.5721,
      "step": 4061
    },
    {
      "epoch": 0.12478112616348723,
      "grad_norm": 0.3496752679347992,
      "learning_rate": 1.9817338948768795e-05,
      "loss": 0.6135,
      "step": 4062
    },
    {
      "epoch": 0.12481184529843639,
      "grad_norm": 0.34640687704086304,
      "learning_rate": 1.9817246989349363e-05,
      "loss": 0.6161,
      "step": 4063
    },
    {
      "epoch": 0.12484256443338555,
      "grad_norm": 0.33708661794662476,
      "learning_rate": 1.9817155007001064e-05,
      "loss": 0.5113,
      "step": 4064
    },
    {
      "epoch": 0.12487328356833471,
      "grad_norm": 0.3403373956680298,
      "learning_rate": 1.981706300172411e-05,
      "loss": 0.5763,
      "step": 4065
    },
    {
      "epoch": 0.12490400270328388,
      "grad_norm": 0.3514322340488434,
      "learning_rate": 1.9816970973518725e-05,
      "loss": 0.6399,
      "step": 4066
    },
    {
      "epoch": 0.12493472183823304,
      "grad_norm": 0.3370497524738312,
      "learning_rate": 1.9816878922385117e-05,
      "loss": 0.5519,
      "step": 4067
    },
    {
      "epoch": 0.1249654409731822,
      "grad_norm": 0.32534220814704895,
      "learning_rate": 1.98167868483235e-05,
      "loss": 0.5223,
      "step": 4068
    },
    {
      "epoch": 0.12499616010813136,
      "grad_norm": 0.35554641485214233,
      "learning_rate": 1.9816694751334094e-05,
      "loss": 0.7176,
      "step": 4069
    },
    {
      "epoch": 0.1250268792430805,
      "grad_norm": 0.41027936339378357,
      "learning_rate": 1.981660263141711e-05,
      "loss": 0.6406,
      "step": 4070
    },
    {
      "epoch": 0.12505759837802968,
      "grad_norm": 0.35321253538131714,
      "learning_rate": 1.9816510488572768e-05,
      "loss": 0.6702,
      "step": 4071
    },
    {
      "epoch": 0.12508831751297883,
      "grad_norm": 0.4247465431690216,
      "learning_rate": 1.981641832280128e-05,
      "loss": 0.5829,
      "step": 4072
    },
    {
      "epoch": 0.125119036647928,
      "grad_norm": 0.3844532072544098,
      "learning_rate": 1.981632613410286e-05,
      "loss": 0.6498,
      "step": 4073
    },
    {
      "epoch": 0.12514975578287715,
      "grad_norm": 0.3773910701274872,
      "learning_rate": 1.9816233922477723e-05,
      "loss": 0.5949,
      "step": 4074
    },
    {
      "epoch": 0.1251804749178263,
      "grad_norm": 0.30154159665107727,
      "learning_rate": 1.981614168792609e-05,
      "loss": 0.529,
      "step": 4075
    },
    {
      "epoch": 0.12521119405277548,
      "grad_norm": 0.3629368245601654,
      "learning_rate": 1.981604943044817e-05,
      "loss": 0.6,
      "step": 4076
    },
    {
      "epoch": 0.12524191318772462,
      "grad_norm": 0.3227355480194092,
      "learning_rate": 1.981595715004418e-05,
      "loss": 0.6354,
      "step": 4077
    },
    {
      "epoch": 0.1252726323226738,
      "grad_norm": 0.3186333477497101,
      "learning_rate": 1.981586484671434e-05,
      "loss": 0.6366,
      "step": 4078
    },
    {
      "epoch": 0.12530335145762295,
      "grad_norm": 0.3339761197566986,
      "learning_rate": 1.9815772520458857e-05,
      "loss": 0.6654,
      "step": 4079
    },
    {
      "epoch": 0.12533407059257212,
      "grad_norm": 0.40091216564178467,
      "learning_rate": 1.9815680171277956e-05,
      "loss": 0.6013,
      "step": 4080
    },
    {
      "epoch": 0.12536478972752127,
      "grad_norm": 0.3458215296268463,
      "learning_rate": 1.981558779917185e-05,
      "loss": 0.579,
      "step": 4081
    },
    {
      "epoch": 0.12539550886247045,
      "grad_norm": 0.41100654006004333,
      "learning_rate": 1.9815495404140747e-05,
      "loss": 0.5997,
      "step": 4082
    },
    {
      "epoch": 0.1254262279974196,
      "grad_norm": 0.3338417410850525,
      "learning_rate": 1.9815402986184874e-05,
      "loss": 0.5685,
      "step": 4083
    },
    {
      "epoch": 0.12545694713236874,
      "grad_norm": 0.3260349631309509,
      "learning_rate": 1.981531054530444e-05,
      "loss": 0.6094,
      "step": 4084
    },
    {
      "epoch": 0.12548766626731792,
      "grad_norm": 0.34699514508247375,
      "learning_rate": 1.9815218081499662e-05,
      "loss": 0.632,
      "step": 4085
    },
    {
      "epoch": 0.12551838540226706,
      "grad_norm": 0.425396591424942,
      "learning_rate": 1.9815125594770758e-05,
      "loss": 0.6026,
      "step": 4086
    },
    {
      "epoch": 0.12554910453721624,
      "grad_norm": 0.3404061198234558,
      "learning_rate": 1.9815033085117944e-05,
      "loss": 0.5417,
      "step": 4087
    },
    {
      "epoch": 0.12557982367216539,
      "grad_norm": 0.3974739611148834,
      "learning_rate": 1.9814940552541433e-05,
      "loss": 0.6238,
      "step": 4088
    },
    {
      "epoch": 0.12561054280711456,
      "grad_norm": 0.3673137426376343,
      "learning_rate": 1.9814847997041443e-05,
      "loss": 0.6242,
      "step": 4089
    },
    {
      "epoch": 0.1256412619420637,
      "grad_norm": 0.3146202862262726,
      "learning_rate": 1.981475541861819e-05,
      "loss": 0.5558,
      "step": 4090
    },
    {
      "epoch": 0.12567198107701288,
      "grad_norm": 0.3716023862361908,
      "learning_rate": 1.981466281727189e-05,
      "loss": 0.5798,
      "step": 4091
    },
    {
      "epoch": 0.12570270021196203,
      "grad_norm": 0.3551847040653229,
      "learning_rate": 1.981457019300276e-05,
      "loss": 0.611,
      "step": 4092
    },
    {
      "epoch": 0.12573341934691118,
      "grad_norm": 0.3965971767902374,
      "learning_rate": 1.9814477545811015e-05,
      "loss": 0.6503,
      "step": 4093
    },
    {
      "epoch": 0.12576413848186035,
      "grad_norm": 0.3657153844833374,
      "learning_rate": 1.981438487569687e-05,
      "loss": 0.6818,
      "step": 4094
    },
    {
      "epoch": 0.1257948576168095,
      "grad_norm": 0.368564248085022,
      "learning_rate": 1.981429218266055e-05,
      "loss": 0.5671,
      "step": 4095
    },
    {
      "epoch": 0.12582557675175868,
      "grad_norm": 0.37346938252449036,
      "learning_rate": 1.9814199466702264e-05,
      "loss": 0.6251,
      "step": 4096
    },
    {
      "epoch": 0.12585629588670783,
      "grad_norm": 0.46099886298179626,
      "learning_rate": 1.9814106727822225e-05,
      "loss": 0.5951,
      "step": 4097
    },
    {
      "epoch": 0.125887015021657,
      "grad_norm": 0.9393325448036194,
      "learning_rate": 1.981401396602066e-05,
      "loss": 0.5993,
      "step": 4098
    },
    {
      "epoch": 0.12591773415660615,
      "grad_norm": 0.32662755250930786,
      "learning_rate": 1.9813921181297774e-05,
      "loss": 0.5492,
      "step": 4099
    },
    {
      "epoch": 0.12594845329155532,
      "grad_norm": 0.29848650097846985,
      "learning_rate": 1.9813828373653795e-05,
      "loss": 0.5467,
      "step": 4100
    },
    {
      "epoch": 0.12597917242650447,
      "grad_norm": 0.3566511571407318,
      "learning_rate": 1.981373554308893e-05,
      "loss": 0.4794,
      "step": 4101
    },
    {
      "epoch": 0.12600989156145362,
      "grad_norm": 0.33830347657203674,
      "learning_rate": 1.98136426896034e-05,
      "loss": 0.6224,
      "step": 4102
    },
    {
      "epoch": 0.1260406106964028,
      "grad_norm": 0.3949575424194336,
      "learning_rate": 1.9813549813197427e-05,
      "loss": 0.6093,
      "step": 4103
    },
    {
      "epoch": 0.12607132983135194,
      "grad_norm": 0.3097324073314667,
      "learning_rate": 1.981345691387122e-05,
      "loss": 0.5877,
      "step": 4104
    },
    {
      "epoch": 0.12610204896630112,
      "grad_norm": 0.30452415347099304,
      "learning_rate": 1.9813363991625e-05,
      "loss": 0.6941,
      "step": 4105
    },
    {
      "epoch": 0.12613276810125026,
      "grad_norm": 0.3659488260746002,
      "learning_rate": 1.981327104645898e-05,
      "loss": 0.6005,
      "step": 4106
    },
    {
      "epoch": 0.12616348723619944,
      "grad_norm": 0.3741089701652527,
      "learning_rate": 1.9813178078373385e-05,
      "loss": 0.649,
      "step": 4107
    },
    {
      "epoch": 0.1261942063711486,
      "grad_norm": 0.39291682839393616,
      "learning_rate": 1.9813085087368424e-05,
      "loss": 0.5739,
      "step": 4108
    },
    {
      "epoch": 0.12622492550609773,
      "grad_norm": 0.33800652623176575,
      "learning_rate": 1.981299207344432e-05,
      "loss": 0.5692,
      "step": 4109
    },
    {
      "epoch": 0.1262556446410469,
      "grad_norm": 0.298652708530426,
      "learning_rate": 1.9812899036601285e-05,
      "loss": 0.5772,
      "step": 4110
    },
    {
      "epoch": 0.12628636377599606,
      "grad_norm": 0.36987534165382385,
      "learning_rate": 1.981280597683954e-05,
      "loss": 0.6267,
      "step": 4111
    },
    {
      "epoch": 0.12631708291094523,
      "grad_norm": 0.33516284823417664,
      "learning_rate": 1.98127128941593e-05,
      "loss": 0.5912,
      "step": 4112
    },
    {
      "epoch": 0.12634780204589438,
      "grad_norm": 0.66704922914505,
      "learning_rate": 1.9812619788560785e-05,
      "loss": 0.6405,
      "step": 4113
    },
    {
      "epoch": 0.12637852118084356,
      "grad_norm": 0.34584134817123413,
      "learning_rate": 1.9812526660044212e-05,
      "loss": 0.6525,
      "step": 4114
    },
    {
      "epoch": 0.1264092403157927,
      "grad_norm": 0.33145758509635925,
      "learning_rate": 1.9812433508609797e-05,
      "loss": 0.5952,
      "step": 4115
    },
    {
      "epoch": 0.12643995945074188,
      "grad_norm": 0.2905735969543457,
      "learning_rate": 1.9812340334257757e-05,
      "loss": 0.5177,
      "step": 4116
    },
    {
      "epoch": 0.12647067858569103,
      "grad_norm": 0.3490558862686157,
      "learning_rate": 1.9812247136988313e-05,
      "loss": 0.614,
      "step": 4117
    },
    {
      "epoch": 0.12650139772064017,
      "grad_norm": 0.32255879044532776,
      "learning_rate": 1.981215391680168e-05,
      "loss": 0.5445,
      "step": 4118
    },
    {
      "epoch": 0.12653211685558935,
      "grad_norm": 0.40051403641700745,
      "learning_rate": 1.9812060673698073e-05,
      "loss": 0.6469,
      "step": 4119
    },
    {
      "epoch": 0.1265628359905385,
      "grad_norm": 0.35837772488594055,
      "learning_rate": 1.981196740767772e-05,
      "loss": 0.6473,
      "step": 4120
    },
    {
      "epoch": 0.12659355512548767,
      "grad_norm": 0.35840678215026855,
      "learning_rate": 1.9811874118740827e-05,
      "loss": 0.6246,
      "step": 4121
    },
    {
      "epoch": 0.12662427426043682,
      "grad_norm": 0.36751827597618103,
      "learning_rate": 1.981178080688762e-05,
      "loss": 0.6084,
      "step": 4122
    },
    {
      "epoch": 0.126654993395386,
      "grad_norm": 0.34752824902534485,
      "learning_rate": 1.981168747211831e-05,
      "loss": 0.6762,
      "step": 4123
    },
    {
      "epoch": 0.12668571253033514,
      "grad_norm": 0.3345435857772827,
      "learning_rate": 1.981159411443312e-05,
      "loss": 0.5452,
      "step": 4124
    },
    {
      "epoch": 0.12671643166528432,
      "grad_norm": 0.3513478934764862,
      "learning_rate": 1.9811500733832264e-05,
      "loss": 0.6362,
      "step": 4125
    },
    {
      "epoch": 0.12674715080023347,
      "grad_norm": 0.3629491329193115,
      "learning_rate": 1.9811407330315965e-05,
      "loss": 0.5663,
      "step": 4126
    },
    {
      "epoch": 0.1267778699351826,
      "grad_norm": 0.44739046692848206,
      "learning_rate": 1.981131390388444e-05,
      "loss": 0.4968,
      "step": 4127
    },
    {
      "epoch": 0.1268085890701318,
      "grad_norm": 0.3355485498905182,
      "learning_rate": 1.9811220454537906e-05,
      "loss": 0.531,
      "step": 4128
    },
    {
      "epoch": 0.12683930820508094,
      "grad_norm": 0.3767832815647125,
      "learning_rate": 1.9811126982276582e-05,
      "loss": 0.6285,
      "step": 4129
    },
    {
      "epoch": 0.1268700273400301,
      "grad_norm": 0.3364431858062744,
      "learning_rate": 1.9811033487100683e-05,
      "loss": 0.5892,
      "step": 4130
    },
    {
      "epoch": 0.12690074647497926,
      "grad_norm": 0.32281869649887085,
      "learning_rate": 1.9810939969010432e-05,
      "loss": 0.6149,
      "step": 4131
    },
    {
      "epoch": 0.12693146560992843,
      "grad_norm": 0.35355496406555176,
      "learning_rate": 1.9810846428006046e-05,
      "loss": 0.6069,
      "step": 4132
    },
    {
      "epoch": 0.12696218474487758,
      "grad_norm": 0.37478742003440857,
      "learning_rate": 1.981075286408774e-05,
      "loss": 0.6631,
      "step": 4133
    },
    {
      "epoch": 0.12699290387982676,
      "grad_norm": 0.37912115454673767,
      "learning_rate": 1.9810659277255738e-05,
      "loss": 0.5834,
      "step": 4134
    },
    {
      "epoch": 0.1270236230147759,
      "grad_norm": 0.37822598218917847,
      "learning_rate": 1.9810565667510254e-05,
      "loss": 0.5613,
      "step": 4135
    },
    {
      "epoch": 0.12705434214972505,
      "grad_norm": 0.3545427620410919,
      "learning_rate": 1.9810472034851512e-05,
      "loss": 0.6691,
      "step": 4136
    },
    {
      "epoch": 0.12708506128467423,
      "grad_norm": 0.3341190218925476,
      "learning_rate": 1.9810378379279726e-05,
      "loss": 0.6055,
      "step": 4137
    },
    {
      "epoch": 0.12711578041962338,
      "grad_norm": 0.3469977378845215,
      "learning_rate": 1.9810284700795116e-05,
      "loss": 0.6054,
      "step": 4138
    },
    {
      "epoch": 0.12714649955457255,
      "grad_norm": 0.3458942770957947,
      "learning_rate": 1.9810190999397903e-05,
      "loss": 0.607,
      "step": 4139
    },
    {
      "epoch": 0.1271772186895217,
      "grad_norm": 0.31423330307006836,
      "learning_rate": 1.98100972750883e-05,
      "loss": 0.6812,
      "step": 4140
    },
    {
      "epoch": 0.12720793782447087,
      "grad_norm": 0.3494483530521393,
      "learning_rate": 1.981000352786653e-05,
      "loss": 0.5985,
      "step": 4141
    },
    {
      "epoch": 0.12723865695942002,
      "grad_norm": 0.32029852271080017,
      "learning_rate": 1.9809909757732814e-05,
      "loss": 0.5398,
      "step": 4142
    },
    {
      "epoch": 0.12726937609436917,
      "grad_norm": 0.3512006402015686,
      "learning_rate": 1.9809815964687368e-05,
      "loss": 0.6145,
      "step": 4143
    },
    {
      "epoch": 0.12730009522931834,
      "grad_norm": 0.44339439272880554,
      "learning_rate": 1.980972214873041e-05,
      "loss": 0.4751,
      "step": 4144
    },
    {
      "epoch": 0.1273308143642675,
      "grad_norm": 0.3727782666683197,
      "learning_rate": 1.9809628309862163e-05,
      "loss": 0.5949,
      "step": 4145
    },
    {
      "epoch": 0.12736153349921667,
      "grad_norm": 0.3588993549346924,
      "learning_rate": 1.9809534448082845e-05,
      "loss": 0.5955,
      "step": 4146
    },
    {
      "epoch": 0.12739225263416581,
      "grad_norm": 0.3903571367263794,
      "learning_rate": 1.9809440563392672e-05,
      "loss": 0.5023,
      "step": 4147
    },
    {
      "epoch": 0.127422971769115,
      "grad_norm": 0.33360254764556885,
      "learning_rate": 1.9809346655791867e-05,
      "loss": 0.6339,
      "step": 4148
    },
    {
      "epoch": 0.12745369090406414,
      "grad_norm": 0.35657694935798645,
      "learning_rate": 1.9809252725280647e-05,
      "loss": 0.7013,
      "step": 4149
    },
    {
      "epoch": 0.1274844100390133,
      "grad_norm": 0.3323673605918884,
      "learning_rate": 1.9809158771859232e-05,
      "loss": 0.571,
      "step": 4150
    },
    {
      "epoch": 0.12751512917396246,
      "grad_norm": 0.42442458868026733,
      "learning_rate": 1.980906479552784e-05,
      "loss": 0.6201,
      "step": 4151
    },
    {
      "epoch": 0.1275458483089116,
      "grad_norm": 0.8313340544700623,
      "learning_rate": 1.9808970796286693e-05,
      "loss": 0.6505,
      "step": 4152
    },
    {
      "epoch": 0.12757656744386078,
      "grad_norm": 0.31842145323753357,
      "learning_rate": 1.980887677413601e-05,
      "loss": 0.5961,
      "step": 4153
    },
    {
      "epoch": 0.12760728657880993,
      "grad_norm": 0.3233353793621063,
      "learning_rate": 1.9808782729076013e-05,
      "loss": 0.6518,
      "step": 4154
    },
    {
      "epoch": 0.1276380057137591,
      "grad_norm": 0.366288959980011,
      "learning_rate": 1.9808688661106914e-05,
      "loss": 0.6116,
      "step": 4155
    },
    {
      "epoch": 0.12766872484870825,
      "grad_norm": 0.33674097061157227,
      "learning_rate": 1.9808594570228942e-05,
      "loss": 0.5,
      "step": 4156
    },
    {
      "epoch": 0.12769944398365743,
      "grad_norm": 0.30180782079696655,
      "learning_rate": 1.980850045644231e-05,
      "loss": 0.6146,
      "step": 4157
    },
    {
      "epoch": 0.12773016311860658,
      "grad_norm": 0.35168373584747314,
      "learning_rate": 1.980840631974724e-05,
      "loss": 0.5956,
      "step": 4158
    },
    {
      "epoch": 0.12776088225355575,
      "grad_norm": 0.3350053131580353,
      "learning_rate": 1.9808312160143953e-05,
      "loss": 0.6214,
      "step": 4159
    },
    {
      "epoch": 0.1277916013885049,
      "grad_norm": 0.32799032330513,
      "learning_rate": 1.980821797763267e-05,
      "loss": 0.623,
      "step": 4160
    },
    {
      "epoch": 0.12782232052345405,
      "grad_norm": 0.33669546246528625,
      "learning_rate": 1.9808123772213603e-05,
      "loss": 0.5743,
      "step": 4161
    },
    {
      "epoch": 0.12785303965840322,
      "grad_norm": 0.35535046458244324,
      "learning_rate": 1.980802954388698e-05,
      "loss": 0.6624,
      "step": 4162
    },
    {
      "epoch": 0.12788375879335237,
      "grad_norm": 0.35869717597961426,
      "learning_rate": 1.9807935292653024e-05,
      "loss": 0.6037,
      "step": 4163
    },
    {
      "epoch": 0.12791447792830155,
      "grad_norm": 0.35203149914741516,
      "learning_rate": 1.9807841018511945e-05,
      "loss": 0.5727,
      "step": 4164
    },
    {
      "epoch": 0.1279451970632507,
      "grad_norm": 0.31383320689201355,
      "learning_rate": 1.980774672146397e-05,
      "loss": 0.5718,
      "step": 4165
    },
    {
      "epoch": 0.12797591619819987,
      "grad_norm": 0.36762869358062744,
      "learning_rate": 1.980765240150932e-05,
      "loss": 0.5872,
      "step": 4166
    },
    {
      "epoch": 0.12800663533314902,
      "grad_norm": 0.5352159142494202,
      "learning_rate": 1.9807558058648207e-05,
      "loss": 0.5424,
      "step": 4167
    },
    {
      "epoch": 0.1280373544680982,
      "grad_norm": 0.3300909101963043,
      "learning_rate": 1.9807463692880864e-05,
      "loss": 0.6546,
      "step": 4168
    },
    {
      "epoch": 0.12806807360304734,
      "grad_norm": 0.3230202794075012,
      "learning_rate": 1.98073693042075e-05,
      "loss": 0.6002,
      "step": 4169
    },
    {
      "epoch": 0.1280987927379965,
      "grad_norm": 0.3218047618865967,
      "learning_rate": 1.980727489262834e-05,
      "loss": 0.5515,
      "step": 4170
    },
    {
      "epoch": 0.12812951187294566,
      "grad_norm": 0.3347569406032562,
      "learning_rate": 1.9807180458143605e-05,
      "loss": 0.5845,
      "step": 4171
    },
    {
      "epoch": 0.1281602310078948,
      "grad_norm": 0.3820458948612213,
      "learning_rate": 1.9807086000753518e-05,
      "loss": 0.6707,
      "step": 4172
    },
    {
      "epoch": 0.12819095014284398,
      "grad_norm": 0.3322044014930725,
      "learning_rate": 1.9806991520458294e-05,
      "loss": 0.5272,
      "step": 4173
    },
    {
      "epoch": 0.12822166927779313,
      "grad_norm": 0.3289972245693207,
      "learning_rate": 1.9806897017258158e-05,
      "loss": 0.5804,
      "step": 4174
    },
    {
      "epoch": 0.1282523884127423,
      "grad_norm": 0.323691725730896,
      "learning_rate": 1.980680249115333e-05,
      "loss": 0.5593,
      "step": 4175
    },
    {
      "epoch": 0.12828310754769146,
      "grad_norm": 0.31711336970329285,
      "learning_rate": 1.9806707942144024e-05,
      "loss": 0.6161,
      "step": 4176
    },
    {
      "epoch": 0.12831382668264063,
      "grad_norm": 0.35475096106529236,
      "learning_rate": 1.980661337023047e-05,
      "loss": 0.6122,
      "step": 4177
    },
    {
      "epoch": 0.12834454581758978,
      "grad_norm": 0.32817718386650085,
      "learning_rate": 1.9806518775412886e-05,
      "loss": 0.6436,
      "step": 4178
    },
    {
      "epoch": 0.12837526495253893,
      "grad_norm": 0.464938223361969,
      "learning_rate": 1.9806424157691497e-05,
      "loss": 0.6106,
      "step": 4179
    },
    {
      "epoch": 0.1284059840874881,
      "grad_norm": 0.3981035053730011,
      "learning_rate": 1.9806329517066512e-05,
      "loss": 0.6089,
      "step": 4180
    },
    {
      "epoch": 0.12843670322243725,
      "grad_norm": 0.3213074803352356,
      "learning_rate": 1.9806234853538164e-05,
      "loss": 0.556,
      "step": 4181
    },
    {
      "epoch": 0.12846742235738642,
      "grad_norm": 0.2999817430973053,
      "learning_rate": 1.9806140167106667e-05,
      "loss": 0.5873,
      "step": 4182
    },
    {
      "epoch": 0.12849814149233557,
      "grad_norm": 0.3213011920452118,
      "learning_rate": 1.9806045457772247e-05,
      "loss": 0.5746,
      "step": 4183
    },
    {
      "epoch": 0.12852886062728475,
      "grad_norm": 0.3249133229255676,
      "learning_rate": 1.9805950725535124e-05,
      "loss": 0.6231,
      "step": 4184
    },
    {
      "epoch": 0.1285595797622339,
      "grad_norm": 0.4175771474838257,
      "learning_rate": 1.9805855970395517e-05,
      "loss": 0.6454,
      "step": 4185
    },
    {
      "epoch": 0.12859029889718304,
      "grad_norm": 0.43649062514305115,
      "learning_rate": 1.9805761192353646e-05,
      "loss": 0.6067,
      "step": 4186
    },
    {
      "epoch": 0.12862101803213222,
      "grad_norm": 0.4572054147720337,
      "learning_rate": 1.9805666391409737e-05,
      "loss": 0.6238,
      "step": 4187
    },
    {
      "epoch": 0.12865173716708136,
      "grad_norm": 0.32612159848213196,
      "learning_rate": 1.980557156756401e-05,
      "loss": 0.65,
      "step": 4188
    },
    {
      "epoch": 0.12868245630203054,
      "grad_norm": 0.3082496225833893,
      "learning_rate": 1.9805476720816683e-05,
      "loss": 0.5985,
      "step": 4189
    },
    {
      "epoch": 0.1287131754369797,
      "grad_norm": 0.3602977991104126,
      "learning_rate": 1.9805381851167986e-05,
      "loss": 0.5571,
      "step": 4190
    },
    {
      "epoch": 0.12874389457192886,
      "grad_norm": 0.3504650890827179,
      "learning_rate": 1.9805286958618127e-05,
      "loss": 0.6559,
      "step": 4191
    },
    {
      "epoch": 0.128774613706878,
      "grad_norm": 0.3600429892539978,
      "learning_rate": 1.980519204316734e-05,
      "loss": 0.6604,
      "step": 4192
    },
    {
      "epoch": 0.12880533284182719,
      "grad_norm": 0.3629418611526489,
      "learning_rate": 1.9805097104815844e-05,
      "loss": 0.5883,
      "step": 4193
    },
    {
      "epoch": 0.12883605197677633,
      "grad_norm": 0.35946372151374817,
      "learning_rate": 1.9805002143563858e-05,
      "loss": 0.5541,
      "step": 4194
    },
    {
      "epoch": 0.12886677111172548,
      "grad_norm": 0.5136677622795105,
      "learning_rate": 1.9804907159411604e-05,
      "loss": 0.6262,
      "step": 4195
    },
    {
      "epoch": 0.12889749024667466,
      "grad_norm": 0.32676243782043457,
      "learning_rate": 1.9804812152359303e-05,
      "loss": 0.6257,
      "step": 4196
    },
    {
      "epoch": 0.1289282093816238,
      "grad_norm": 0.37862542271614075,
      "learning_rate": 1.980471712240718e-05,
      "loss": 0.592,
      "step": 4197
    },
    {
      "epoch": 0.12895892851657298,
      "grad_norm": 0.3604101836681366,
      "learning_rate": 1.9804622069555456e-05,
      "loss": 0.566,
      "step": 4198
    },
    {
      "epoch": 0.12898964765152213,
      "grad_norm": 0.34152135252952576,
      "learning_rate": 1.980452699380435e-05,
      "loss": 0.5531,
      "step": 4199
    },
    {
      "epoch": 0.1290203667864713,
      "grad_norm": 0.42523515224456787,
      "learning_rate": 1.980443189515409e-05,
      "loss": 0.6015,
      "step": 4200
    },
    {
      "epoch": 0.12905108592142045,
      "grad_norm": 0.30686524510383606,
      "learning_rate": 1.9804336773604892e-05,
      "loss": 0.5382,
      "step": 4201
    },
    {
      "epoch": 0.12908180505636963,
      "grad_norm": 0.3675273060798645,
      "learning_rate": 1.980424162915698e-05,
      "loss": 0.6195,
      "step": 4202
    },
    {
      "epoch": 0.12911252419131877,
      "grad_norm": 0.735525906085968,
      "learning_rate": 1.9804146461810577e-05,
      "loss": 0.658,
      "step": 4203
    },
    {
      "epoch": 0.12914324332626792,
      "grad_norm": 0.38372528553009033,
      "learning_rate": 1.9804051271565907e-05,
      "loss": 0.5329,
      "step": 4204
    },
    {
      "epoch": 0.1291739624612171,
      "grad_norm": 0.33951514959335327,
      "learning_rate": 1.980395605842319e-05,
      "loss": 0.6332,
      "step": 4205
    },
    {
      "epoch": 0.12920468159616624,
      "grad_norm": 0.3604397177696228,
      "learning_rate": 1.980386082238265e-05,
      "loss": 0.6786,
      "step": 4206
    },
    {
      "epoch": 0.12923540073111542,
      "grad_norm": 1.0651787519454956,
      "learning_rate": 1.9803765563444507e-05,
      "loss": 0.5598,
      "step": 4207
    },
    {
      "epoch": 0.12926611986606457,
      "grad_norm": 0.336865097284317,
      "learning_rate": 1.9803670281608984e-05,
      "loss": 0.6172,
      "step": 4208
    },
    {
      "epoch": 0.12929683900101374,
      "grad_norm": 0.36271917819976807,
      "learning_rate": 1.9803574976876305e-05,
      "loss": 0.6619,
      "step": 4209
    },
    {
      "epoch": 0.1293275581359629,
      "grad_norm": 0.3532068729400635,
      "learning_rate": 1.9803479649246692e-05,
      "loss": 0.6085,
      "step": 4210
    },
    {
      "epoch": 0.12935827727091206,
      "grad_norm": 0.349139928817749,
      "learning_rate": 1.980338429872037e-05,
      "loss": 0.5731,
      "step": 4211
    },
    {
      "epoch": 0.1293889964058612,
      "grad_norm": 0.3591964840888977,
      "learning_rate": 1.9803288925297556e-05,
      "loss": 0.6943,
      "step": 4212
    },
    {
      "epoch": 0.12941971554081036,
      "grad_norm": 0.4120277166366577,
      "learning_rate": 1.9803193528978477e-05,
      "loss": 0.6488,
      "step": 4213
    },
    {
      "epoch": 0.12945043467575953,
      "grad_norm": 0.3952070474624634,
      "learning_rate": 1.9803098109763355e-05,
      "loss": 0.5829,
      "step": 4214
    },
    {
      "epoch": 0.12948115381070868,
      "grad_norm": 0.499146968126297,
      "learning_rate": 1.9803002667652415e-05,
      "loss": 0.6279,
      "step": 4215
    },
    {
      "epoch": 0.12951187294565786,
      "grad_norm": 0.3574534058570862,
      "learning_rate": 1.9802907202645876e-05,
      "loss": 0.6222,
      "step": 4216
    },
    {
      "epoch": 0.129542592080607,
      "grad_norm": 0.4165816307067871,
      "learning_rate": 1.980281171474396e-05,
      "loss": 0.5968,
      "step": 4217
    },
    {
      "epoch": 0.12957331121555618,
      "grad_norm": 0.34909817576408386,
      "learning_rate": 1.9802716203946895e-05,
      "loss": 0.6153,
      "step": 4218
    },
    {
      "epoch": 0.12960403035050533,
      "grad_norm": 0.33065325021743774,
      "learning_rate": 1.9802620670254905e-05,
      "loss": 0.5666,
      "step": 4219
    },
    {
      "epoch": 0.12963474948545448,
      "grad_norm": 0.34706881642341614,
      "learning_rate": 1.9802525113668204e-05,
      "loss": 0.6344,
      "step": 4220
    },
    {
      "epoch": 0.12966546862040365,
      "grad_norm": 0.3462289273738861,
      "learning_rate": 1.9802429534187025e-05,
      "loss": 0.5895,
      "step": 4221
    },
    {
      "epoch": 0.1296961877553528,
      "grad_norm": 0.311054527759552,
      "learning_rate": 1.9802333931811586e-05,
      "loss": 0.5266,
      "step": 4222
    },
    {
      "epoch": 0.12972690689030197,
      "grad_norm": 0.34167975187301636,
      "learning_rate": 1.980223830654211e-05,
      "loss": 0.6194,
      "step": 4223
    },
    {
      "epoch": 0.12975762602525112,
      "grad_norm": 0.3233288526535034,
      "learning_rate": 1.980214265837882e-05,
      "loss": 0.5591,
      "step": 4224
    },
    {
      "epoch": 0.1297883451602003,
      "grad_norm": 0.3204280734062195,
      "learning_rate": 1.9802046987321946e-05,
      "loss": 0.6095,
      "step": 4225
    },
    {
      "epoch": 0.12981906429514944,
      "grad_norm": 0.3584391474723816,
      "learning_rate": 1.9801951293371705e-05,
      "loss": 0.6604,
      "step": 4226
    },
    {
      "epoch": 0.12984978343009862,
      "grad_norm": 0.3422292470932007,
      "learning_rate": 1.980185557652832e-05,
      "loss": 0.5558,
      "step": 4227
    },
    {
      "epoch": 0.12988050256504777,
      "grad_norm": 0.3297055959701538,
      "learning_rate": 1.9801759836792023e-05,
      "loss": 0.6061,
      "step": 4228
    },
    {
      "epoch": 0.12991122169999691,
      "grad_norm": 0.34796321392059326,
      "learning_rate": 1.980166407416303e-05,
      "loss": 0.6992,
      "step": 4229
    },
    {
      "epoch": 0.1299419408349461,
      "grad_norm": 0.70027756690979,
      "learning_rate": 1.980156828864156e-05,
      "loss": 0.5911,
      "step": 4230
    },
    {
      "epoch": 0.12997265996989524,
      "grad_norm": 0.3644903302192688,
      "learning_rate": 1.9801472480227844e-05,
      "loss": 0.655,
      "step": 4231
    },
    {
      "epoch": 0.1300033791048444,
      "grad_norm": 0.3245377838611603,
      "learning_rate": 1.980137664892211e-05,
      "loss": 0.5683,
      "step": 4232
    },
    {
      "epoch": 0.13003409823979356,
      "grad_norm": 0.3277278542518616,
      "learning_rate": 1.9801280794724568e-05,
      "loss": 0.553,
      "step": 4233
    },
    {
      "epoch": 0.13006481737474274,
      "grad_norm": 0.3350740969181061,
      "learning_rate": 1.9801184917635456e-05,
      "loss": 0.5624,
      "step": 4234
    },
    {
      "epoch": 0.13009553650969188,
      "grad_norm": 0.3985815644264221,
      "learning_rate": 1.980108901765499e-05,
      "loss": 0.5929,
      "step": 4235
    },
    {
      "epoch": 0.13012625564464106,
      "grad_norm": 0.33505308628082275,
      "learning_rate": 1.98009930947834e-05,
      "loss": 0.609,
      "step": 4236
    },
    {
      "epoch": 0.1301569747795902,
      "grad_norm": 0.324090838432312,
      "learning_rate": 1.9800897149020902e-05,
      "loss": 0.573,
      "step": 4237
    },
    {
      "epoch": 0.13018769391453935,
      "grad_norm": 0.3388899266719818,
      "learning_rate": 1.9800801180367726e-05,
      "loss": 0.6409,
      "step": 4238
    },
    {
      "epoch": 0.13021841304948853,
      "grad_norm": 0.33197978138923645,
      "learning_rate": 1.9800705188824093e-05,
      "loss": 0.6093,
      "step": 4239
    },
    {
      "epoch": 0.13024913218443768,
      "grad_norm": 0.3329910635948181,
      "learning_rate": 1.980060917439023e-05,
      "loss": 0.5556,
      "step": 4240
    },
    {
      "epoch": 0.13027985131938685,
      "grad_norm": 0.32539790868759155,
      "learning_rate": 1.980051313706636e-05,
      "loss": 0.6191,
      "step": 4241
    },
    {
      "epoch": 0.130310570454336,
      "grad_norm": 0.33585062623023987,
      "learning_rate": 1.9800417076852706e-05,
      "loss": 0.6274,
      "step": 4242
    },
    {
      "epoch": 0.13034128958928518,
      "grad_norm": 0.3267397880554199,
      "learning_rate": 1.9800320993749495e-05,
      "loss": 0.6119,
      "step": 4243
    },
    {
      "epoch": 0.13037200872423432,
      "grad_norm": 0.3327142596244812,
      "learning_rate": 1.9800224887756946e-05,
      "loss": 0.6097,
      "step": 4244
    },
    {
      "epoch": 0.1304027278591835,
      "grad_norm": 0.29694288969039917,
      "learning_rate": 1.9800128758875293e-05,
      "loss": 0.5281,
      "step": 4245
    },
    {
      "epoch": 0.13043344699413265,
      "grad_norm": 0.31498339772224426,
      "learning_rate": 1.980003260710475e-05,
      "loss": 0.5453,
      "step": 4246
    },
    {
      "epoch": 0.1304641661290818,
      "grad_norm": 0.3311323821544647,
      "learning_rate": 1.979993643244555e-05,
      "loss": 0.6721,
      "step": 4247
    },
    {
      "epoch": 0.13049488526403097,
      "grad_norm": 0.3245963454246521,
      "learning_rate": 1.9799840234897912e-05,
      "loss": 0.6109,
      "step": 4248
    },
    {
      "epoch": 0.13052560439898012,
      "grad_norm": 0.3155243992805481,
      "learning_rate": 1.979974401446206e-05,
      "loss": 0.641,
      "step": 4249
    },
    {
      "epoch": 0.1305563235339293,
      "grad_norm": 0.31478723883628845,
      "learning_rate": 1.9799647771138227e-05,
      "loss": 0.5683,
      "step": 4250
    },
    {
      "epoch": 0.13058704266887844,
      "grad_norm": 1.5693448781967163,
      "learning_rate": 1.9799551504926628e-05,
      "loss": 0.5521,
      "step": 4251
    },
    {
      "epoch": 0.13061776180382761,
      "grad_norm": 0.3539428114891052,
      "learning_rate": 1.9799455215827494e-05,
      "loss": 0.6763,
      "step": 4252
    },
    {
      "epoch": 0.13064848093877676,
      "grad_norm": 0.40604153275489807,
      "learning_rate": 1.979935890384105e-05,
      "loss": 0.655,
      "step": 4253
    },
    {
      "epoch": 0.13067920007372594,
      "grad_norm": 0.37342336773872375,
      "learning_rate": 1.9799262568967516e-05,
      "loss": 0.574,
      "step": 4254
    },
    {
      "epoch": 0.13070991920867508,
      "grad_norm": 0.3450070023536682,
      "learning_rate": 1.9799166211207122e-05,
      "loss": 0.7382,
      "step": 4255
    },
    {
      "epoch": 0.13074063834362423,
      "grad_norm": 0.3235737681388855,
      "learning_rate": 1.9799069830560088e-05,
      "loss": 0.5912,
      "step": 4256
    },
    {
      "epoch": 0.1307713574785734,
      "grad_norm": 0.3245849609375,
      "learning_rate": 1.9798973427026643e-05,
      "loss": 0.5616,
      "step": 4257
    },
    {
      "epoch": 0.13080207661352256,
      "grad_norm": 0.3204537630081177,
      "learning_rate": 1.9798877000607012e-05,
      "loss": 0.5962,
      "step": 4258
    },
    {
      "epoch": 0.13083279574847173,
      "grad_norm": 0.3556336462497711,
      "learning_rate": 1.979878055130142e-05,
      "loss": 0.5549,
      "step": 4259
    },
    {
      "epoch": 0.13086351488342088,
      "grad_norm": 0.3368959128856659,
      "learning_rate": 1.9798684079110092e-05,
      "loss": 0.5767,
      "step": 4260
    },
    {
      "epoch": 0.13089423401837005,
      "grad_norm": 0.3417651057243347,
      "learning_rate": 1.979858758403325e-05,
      "loss": 0.5933,
      "step": 4261
    },
    {
      "epoch": 0.1309249531533192,
      "grad_norm": 0.36948224902153015,
      "learning_rate": 1.9798491066071123e-05,
      "loss": 0.6437,
      "step": 4262
    },
    {
      "epoch": 0.13095567228826835,
      "grad_norm": 0.33175426721572876,
      "learning_rate": 1.9798394525223938e-05,
      "loss": 0.5737,
      "step": 4263
    },
    {
      "epoch": 0.13098639142321752,
      "grad_norm": 0.36188217997550964,
      "learning_rate": 1.9798297961491918e-05,
      "loss": 0.6362,
      "step": 4264
    },
    {
      "epoch": 0.13101711055816667,
      "grad_norm": 0.3442288935184479,
      "learning_rate": 1.9798201374875287e-05,
      "loss": 0.605,
      "step": 4265
    },
    {
      "epoch": 0.13104782969311585,
      "grad_norm": 0.3236364722251892,
      "learning_rate": 1.9798104765374276e-05,
      "loss": 0.6085,
      "step": 4266
    },
    {
      "epoch": 0.131078548828065,
      "grad_norm": 0.37995025515556335,
      "learning_rate": 1.97980081329891e-05,
      "loss": 0.5845,
      "step": 4267
    },
    {
      "epoch": 0.13110926796301417,
      "grad_norm": 0.31641361117362976,
      "learning_rate": 1.979791147772e-05,
      "loss": 0.513,
      "step": 4268
    },
    {
      "epoch": 0.13113998709796332,
      "grad_norm": 0.3252931535243988,
      "learning_rate": 1.979781479956719e-05,
      "loss": 0.6443,
      "step": 4269
    },
    {
      "epoch": 0.1311707062329125,
      "grad_norm": 0.3615519106388092,
      "learning_rate": 1.97977180985309e-05,
      "loss": 0.5138,
      "step": 4270
    },
    {
      "epoch": 0.13120142536786164,
      "grad_norm": 0.3259580135345459,
      "learning_rate": 1.9797621374611352e-05,
      "loss": 0.6058,
      "step": 4271
    },
    {
      "epoch": 0.1312321445028108,
      "grad_norm": 0.33849358558654785,
      "learning_rate": 1.9797524627808776e-05,
      "loss": 0.6891,
      "step": 4272
    },
    {
      "epoch": 0.13126286363775996,
      "grad_norm": 0.34179776906967163,
      "learning_rate": 1.97974278581234e-05,
      "loss": 0.668,
      "step": 4273
    },
    {
      "epoch": 0.1312935827727091,
      "grad_norm": 0.3398226201534271,
      "learning_rate": 1.9797331065555447e-05,
      "loss": 0.5683,
      "step": 4274
    },
    {
      "epoch": 0.1313243019076583,
      "grad_norm": 0.36450478434562683,
      "learning_rate": 1.979723425010514e-05,
      "loss": 0.6672,
      "step": 4275
    },
    {
      "epoch": 0.13135502104260743,
      "grad_norm": 0.3161754310131073,
      "learning_rate": 1.9797137411772706e-05,
      "loss": 0.5813,
      "step": 4276
    },
    {
      "epoch": 0.1313857401775566,
      "grad_norm": 0.3997567594051361,
      "learning_rate": 1.9797040550558378e-05,
      "loss": 0.5843,
      "step": 4277
    },
    {
      "epoch": 0.13141645931250576,
      "grad_norm": 0.3380495309829712,
      "learning_rate": 1.9796943666462377e-05,
      "loss": 0.6336,
      "step": 4278
    },
    {
      "epoch": 0.13144717844745493,
      "grad_norm": 0.37068691849708557,
      "learning_rate": 1.979684675948493e-05,
      "loss": 0.585,
      "step": 4279
    },
    {
      "epoch": 0.13147789758240408,
      "grad_norm": 0.3373292088508606,
      "learning_rate": 1.979674982962626e-05,
      "loss": 0.6921,
      "step": 4280
    },
    {
      "epoch": 0.13150861671735323,
      "grad_norm": 0.35809484124183655,
      "learning_rate": 1.9796652876886598e-05,
      "loss": 0.6877,
      "step": 4281
    },
    {
      "epoch": 0.1315393358523024,
      "grad_norm": 0.3724095821380615,
      "learning_rate": 1.9796555901266173e-05,
      "loss": 0.6082,
      "step": 4282
    },
    {
      "epoch": 0.13157005498725155,
      "grad_norm": 0.44795355200767517,
      "learning_rate": 1.9796458902765202e-05,
      "loss": 0.6928,
      "step": 4283
    },
    {
      "epoch": 0.13160077412220073,
      "grad_norm": 0.3761241137981415,
      "learning_rate": 1.979636188138392e-05,
      "loss": 0.6092,
      "step": 4284
    },
    {
      "epoch": 0.13163149325714987,
      "grad_norm": 0.34612640738487244,
      "learning_rate": 1.979626483712255e-05,
      "loss": 0.6317,
      "step": 4285
    },
    {
      "epoch": 0.13166221239209905,
      "grad_norm": 0.3491370677947998,
      "learning_rate": 1.9796167769981323e-05,
      "loss": 0.5922,
      "step": 4286
    },
    {
      "epoch": 0.1316929315270482,
      "grad_norm": 0.35416269302368164,
      "learning_rate": 1.9796070679960455e-05,
      "loss": 0.616,
      "step": 4287
    },
    {
      "epoch": 0.13172365066199737,
      "grad_norm": 0.3798975348472595,
      "learning_rate": 1.9795973567060184e-05,
      "loss": 0.6498,
      "step": 4288
    },
    {
      "epoch": 0.13175436979694652,
      "grad_norm": 0.32274964451789856,
      "learning_rate": 1.9795876431280732e-05,
      "loss": 0.5367,
      "step": 4289
    },
    {
      "epoch": 0.13178508893189567,
      "grad_norm": 0.36896470189094543,
      "learning_rate": 1.9795779272622325e-05,
      "loss": 0.621,
      "step": 4290
    },
    {
      "epoch": 0.13181580806684484,
      "grad_norm": 0.33969131112098694,
      "learning_rate": 1.9795682091085195e-05,
      "loss": 0.6385,
      "step": 4291
    },
    {
      "epoch": 0.131846527201794,
      "grad_norm": 0.33554041385650635,
      "learning_rate": 1.9795584886669563e-05,
      "loss": 0.7011,
      "step": 4292
    },
    {
      "epoch": 0.13187724633674316,
      "grad_norm": 0.34219199419021606,
      "learning_rate": 1.979548765937566e-05,
      "loss": 0.5393,
      "step": 4293
    },
    {
      "epoch": 0.1319079654716923,
      "grad_norm": 0.34001001715660095,
      "learning_rate": 1.9795390409203707e-05,
      "loss": 0.598,
      "step": 4294
    },
    {
      "epoch": 0.1319386846066415,
      "grad_norm": 0.36672675609588623,
      "learning_rate": 1.979529313615394e-05,
      "loss": 0.6373,
      "step": 4295
    },
    {
      "epoch": 0.13196940374159064,
      "grad_norm": 0.3439866006374359,
      "learning_rate": 1.979519584022658e-05,
      "loss": 0.6316,
      "step": 4296
    },
    {
      "epoch": 0.1320001228765398,
      "grad_norm": 0.3510702848434448,
      "learning_rate": 1.9795098521421855e-05,
      "loss": 0.5251,
      "step": 4297
    },
    {
      "epoch": 0.13203084201148896,
      "grad_norm": 0.3555569052696228,
      "learning_rate": 1.9795001179739994e-05,
      "loss": 0.5707,
      "step": 4298
    },
    {
      "epoch": 0.1320615611464381,
      "grad_norm": 0.3365461826324463,
      "learning_rate": 1.9794903815181226e-05,
      "loss": 0.6253,
      "step": 4299
    },
    {
      "epoch": 0.13209228028138728,
      "grad_norm": 0.32344210147857666,
      "learning_rate": 1.9794806427745776e-05,
      "loss": 0.5724,
      "step": 4300
    },
    {
      "epoch": 0.13212299941633643,
      "grad_norm": 0.6185758113861084,
      "learning_rate": 1.979470901743387e-05,
      "loss": 0.5468,
      "step": 4301
    },
    {
      "epoch": 0.1321537185512856,
      "grad_norm": 0.32118409872055054,
      "learning_rate": 1.9794611584245734e-05,
      "loss": 0.5242,
      "step": 4302
    },
    {
      "epoch": 0.13218443768623475,
      "grad_norm": 0.3544711768627167,
      "learning_rate": 1.9794514128181604e-05,
      "loss": 0.6119,
      "step": 4303
    },
    {
      "epoch": 0.13221515682118393,
      "grad_norm": 0.34140098094940186,
      "learning_rate": 1.9794416649241696e-05,
      "loss": 0.6576,
      "step": 4304
    },
    {
      "epoch": 0.13224587595613307,
      "grad_norm": 0.48005542159080505,
      "learning_rate": 1.9794319147426247e-05,
      "loss": 0.635,
      "step": 4305
    },
    {
      "epoch": 0.13227659509108222,
      "grad_norm": 0.33215007185935974,
      "learning_rate": 1.9794221622735487e-05,
      "loss": 0.5298,
      "step": 4306
    },
    {
      "epoch": 0.1323073142260314,
      "grad_norm": 0.3357847034931183,
      "learning_rate": 1.979412407516963e-05,
      "loss": 0.5329,
      "step": 4307
    },
    {
      "epoch": 0.13233803336098054,
      "grad_norm": 0.31066787242889404,
      "learning_rate": 1.9794026504728917e-05,
      "loss": 0.5649,
      "step": 4308
    },
    {
      "epoch": 0.13236875249592972,
      "grad_norm": 0.3548673093318939,
      "learning_rate": 1.979392891141357e-05,
      "loss": 0.6288,
      "step": 4309
    },
    {
      "epoch": 0.13239947163087887,
      "grad_norm": 0.4137327969074249,
      "learning_rate": 1.9793831295223818e-05,
      "loss": 0.5691,
      "step": 4310
    },
    {
      "epoch": 0.13243019076582804,
      "grad_norm": 0.338111937046051,
      "learning_rate": 1.979373365615989e-05,
      "loss": 0.5899,
      "step": 4311
    },
    {
      "epoch": 0.1324609099007772,
      "grad_norm": 0.36080965399742126,
      "learning_rate": 1.979363599422201e-05,
      "loss": 0.6012,
      "step": 4312
    },
    {
      "epoch": 0.13249162903572637,
      "grad_norm": 0.3582145869731903,
      "learning_rate": 1.9793538309410412e-05,
      "loss": 0.585,
      "step": 4313
    },
    {
      "epoch": 0.1325223481706755,
      "grad_norm": 0.37289300560951233,
      "learning_rate": 1.979344060172532e-05,
      "loss": 0.5524,
      "step": 4314
    },
    {
      "epoch": 0.13255306730562466,
      "grad_norm": 0.3706514537334442,
      "learning_rate": 1.9793342871166966e-05,
      "loss": 0.6612,
      "step": 4315
    },
    {
      "epoch": 0.13258378644057384,
      "grad_norm": 0.30807971954345703,
      "learning_rate": 1.9793245117735572e-05,
      "loss": 0.545,
      "step": 4316
    },
    {
      "epoch": 0.13261450557552298,
      "grad_norm": 0.7305949926376343,
      "learning_rate": 1.9793147341431372e-05,
      "loss": 0.627,
      "step": 4317
    },
    {
      "epoch": 0.13264522471047216,
      "grad_norm": 0.3361455202102661,
      "learning_rate": 1.979304954225459e-05,
      "loss": 0.5985,
      "step": 4318
    },
    {
      "epoch": 0.1326759438454213,
      "grad_norm": 0.35588130354881287,
      "learning_rate": 1.979295172020546e-05,
      "loss": 0.6707,
      "step": 4319
    },
    {
      "epoch": 0.13270666298037048,
      "grad_norm": 0.4502997398376465,
      "learning_rate": 1.9792853875284206e-05,
      "loss": 0.5664,
      "step": 4320
    },
    {
      "epoch": 0.13273738211531963,
      "grad_norm": 0.33355608582496643,
      "learning_rate": 1.9792756007491062e-05,
      "loss": 0.5473,
      "step": 4321
    },
    {
      "epoch": 0.1327681012502688,
      "grad_norm": 0.3379453420639038,
      "learning_rate": 1.9792658116826246e-05,
      "loss": 0.6497,
      "step": 4322
    },
    {
      "epoch": 0.13279882038521795,
      "grad_norm": 0.34069690108299255,
      "learning_rate": 1.9792560203289996e-05,
      "loss": 0.6374,
      "step": 4323
    },
    {
      "epoch": 0.1328295395201671,
      "grad_norm": 0.34663498401641846,
      "learning_rate": 1.9792462266882538e-05,
      "loss": 0.6109,
      "step": 4324
    },
    {
      "epoch": 0.13286025865511628,
      "grad_norm": 0.3214302361011505,
      "learning_rate": 1.97923643076041e-05,
      "loss": 0.6454,
      "step": 4325
    },
    {
      "epoch": 0.13289097779006542,
      "grad_norm": 0.3539555072784424,
      "learning_rate": 1.979226632545491e-05,
      "loss": 0.6387,
      "step": 4326
    },
    {
      "epoch": 0.1329216969250146,
      "grad_norm": 0.33972111344337463,
      "learning_rate": 1.9792168320435202e-05,
      "loss": 0.5789,
      "step": 4327
    },
    {
      "epoch": 0.13295241605996375,
      "grad_norm": 0.33387529850006104,
      "learning_rate": 1.9792070292545194e-05,
      "loss": 0.607,
      "step": 4328
    },
    {
      "epoch": 0.13298313519491292,
      "grad_norm": 0.3223400115966797,
      "learning_rate": 1.9791972241785128e-05,
      "loss": 0.5137,
      "step": 4329
    },
    {
      "epoch": 0.13301385432986207,
      "grad_norm": 0.3193095028400421,
      "learning_rate": 1.979187416815523e-05,
      "loss": 0.5703,
      "step": 4330
    },
    {
      "epoch": 0.13304457346481124,
      "grad_norm": 0.3480003774166107,
      "learning_rate": 1.9791776071655718e-05,
      "loss": 0.5364,
      "step": 4331
    },
    {
      "epoch": 0.1330752925997604,
      "grad_norm": 0.3290407061576843,
      "learning_rate": 1.9791677952286833e-05,
      "loss": 0.5318,
      "step": 4332
    },
    {
      "epoch": 0.13310601173470954,
      "grad_norm": 0.35076090693473816,
      "learning_rate": 1.97915798100488e-05,
      "loss": 0.6265,
      "step": 4333
    },
    {
      "epoch": 0.13313673086965871,
      "grad_norm": 0.3215453028678894,
      "learning_rate": 1.9791481644941846e-05,
      "loss": 0.6457,
      "step": 4334
    },
    {
      "epoch": 0.13316745000460786,
      "grad_norm": 0.32855623960494995,
      "learning_rate": 1.9791383456966206e-05,
      "loss": 0.6014,
      "step": 4335
    },
    {
      "epoch": 0.13319816913955704,
      "grad_norm": 0.2952263057231903,
      "learning_rate": 1.9791285246122106e-05,
      "loss": 0.6235,
      "step": 4336
    },
    {
      "epoch": 0.13322888827450619,
      "grad_norm": 0.319308876991272,
      "learning_rate": 1.9791187012409774e-05,
      "loss": 0.5512,
      "step": 4337
    },
    {
      "epoch": 0.13325960740945536,
      "grad_norm": 0.3745132088661194,
      "learning_rate": 1.9791088755829442e-05,
      "loss": 0.6279,
      "step": 4338
    },
    {
      "epoch": 0.1332903265444045,
      "grad_norm": 0.36250582337379456,
      "learning_rate": 1.9790990476381338e-05,
      "loss": 0.6062,
      "step": 4339
    },
    {
      "epoch": 0.13332104567935366,
      "grad_norm": 0.3208746016025543,
      "learning_rate": 1.979089217406569e-05,
      "loss": 0.5858,
      "step": 4340
    },
    {
      "epoch": 0.13335176481430283,
      "grad_norm": 0.43410617113113403,
      "learning_rate": 1.9790793848882733e-05,
      "loss": 0.5598,
      "step": 4341
    },
    {
      "epoch": 0.13338248394925198,
      "grad_norm": 0.3328767716884613,
      "learning_rate": 1.9790695500832692e-05,
      "loss": 0.5297,
      "step": 4342
    },
    {
      "epoch": 0.13341320308420115,
      "grad_norm": 0.3389059901237488,
      "learning_rate": 1.9790597129915798e-05,
      "loss": 0.6435,
      "step": 4343
    },
    {
      "epoch": 0.1334439222191503,
      "grad_norm": 0.3368482291698456,
      "learning_rate": 1.979049873613228e-05,
      "loss": 0.6036,
      "step": 4344
    },
    {
      "epoch": 0.13347464135409948,
      "grad_norm": 0.32054680585861206,
      "learning_rate": 1.9790400319482365e-05,
      "loss": 0.6164,
      "step": 4345
    },
    {
      "epoch": 0.13350536048904862,
      "grad_norm": 0.35870561003685,
      "learning_rate": 1.9790301879966295e-05,
      "loss": 0.5644,
      "step": 4346
    },
    {
      "epoch": 0.1335360796239978,
      "grad_norm": 0.32240307331085205,
      "learning_rate": 1.9790203417584282e-05,
      "loss": 0.5292,
      "step": 4347
    },
    {
      "epoch": 0.13356679875894695,
      "grad_norm": 0.31549590826034546,
      "learning_rate": 1.9790104932336568e-05,
      "loss": 0.6133,
      "step": 4348
    },
    {
      "epoch": 0.1335975178938961,
      "grad_norm": 0.3353824019432068,
      "learning_rate": 1.9790006424223385e-05,
      "loss": 0.6261,
      "step": 4349
    },
    {
      "epoch": 0.13362823702884527,
      "grad_norm": 0.37589672207832336,
      "learning_rate": 1.978990789324495e-05,
      "loss": 0.6025,
      "step": 4350
    },
    {
      "epoch": 0.13365895616379442,
      "grad_norm": 0.3105200529098511,
      "learning_rate": 1.978980933940151e-05,
      "loss": 0.5072,
      "step": 4351
    },
    {
      "epoch": 0.1336896752987436,
      "grad_norm": 0.3886089622974396,
      "learning_rate": 1.9789710762693282e-05,
      "loss": 0.5371,
      "step": 4352
    },
    {
      "epoch": 0.13372039443369274,
      "grad_norm": 0.33407777547836304,
      "learning_rate": 1.97896121631205e-05,
      "loss": 0.6313,
      "step": 4353
    },
    {
      "epoch": 0.13375111356864192,
      "grad_norm": 0.30718809366226196,
      "learning_rate": 1.97895135406834e-05,
      "loss": 0.5947,
      "step": 4354
    },
    {
      "epoch": 0.13378183270359106,
      "grad_norm": 0.3320011496543884,
      "learning_rate": 1.9789414895382203e-05,
      "loss": 0.6711,
      "step": 4355
    },
    {
      "epoch": 0.13381255183854024,
      "grad_norm": 0.337852418422699,
      "learning_rate": 1.9789316227217145e-05,
      "loss": 0.6173,
      "step": 4356
    },
    {
      "epoch": 0.1338432709734894,
      "grad_norm": 0.3337247371673584,
      "learning_rate": 1.9789217536188454e-05,
      "loss": 0.6986,
      "step": 4357
    },
    {
      "epoch": 0.13387399010843853,
      "grad_norm": 0.37444108724594116,
      "learning_rate": 1.9789118822296362e-05,
      "loss": 0.618,
      "step": 4358
    },
    {
      "epoch": 0.1339047092433877,
      "grad_norm": 0.3417365252971649,
      "learning_rate": 1.9789020085541103e-05,
      "loss": 0.6108,
      "step": 4359
    },
    {
      "epoch": 0.13393542837833686,
      "grad_norm": 0.3381365239620209,
      "learning_rate": 1.97889213259229e-05,
      "loss": 0.5741,
      "step": 4360
    },
    {
      "epoch": 0.13396614751328603,
      "grad_norm": 0.4111553728580475,
      "learning_rate": 1.9788822543441986e-05,
      "loss": 0.654,
      "step": 4361
    },
    {
      "epoch": 0.13399686664823518,
      "grad_norm": 0.3512863218784332,
      "learning_rate": 1.97887237380986e-05,
      "loss": 0.5569,
      "step": 4362
    },
    {
      "epoch": 0.13402758578318436,
      "grad_norm": 0.3039816617965698,
      "learning_rate": 1.978862490989296e-05,
      "loss": 0.6099,
      "step": 4363
    },
    {
      "epoch": 0.1340583049181335,
      "grad_norm": 0.40568414330482483,
      "learning_rate": 1.978852605882531e-05,
      "loss": 0.6174,
      "step": 4364
    },
    {
      "epoch": 0.13408902405308268,
      "grad_norm": 0.33759164810180664,
      "learning_rate": 1.9788427184895863e-05,
      "loss": 0.6121,
      "step": 4365
    },
    {
      "epoch": 0.13411974318803183,
      "grad_norm": 0.35140833258628845,
      "learning_rate": 1.978832828810487e-05,
      "loss": 0.6022,
      "step": 4366
    },
    {
      "epoch": 0.13415046232298097,
      "grad_norm": 0.32849910855293274,
      "learning_rate": 1.978822936845255e-05,
      "loss": 0.6171,
      "step": 4367
    },
    {
      "epoch": 0.13418118145793015,
      "grad_norm": 0.3553868532180786,
      "learning_rate": 1.9788130425939133e-05,
      "loss": 0.614,
      "step": 4368
    },
    {
      "epoch": 0.1342119005928793,
      "grad_norm": 0.37060636281967163,
      "learning_rate": 1.9788031460564857e-05,
      "loss": 0.6201,
      "step": 4369
    },
    {
      "epoch": 0.13424261972782847,
      "grad_norm": 0.3612472116947174,
      "learning_rate": 1.978793247232995e-05,
      "loss": 0.6294,
      "step": 4370
    },
    {
      "epoch": 0.13427333886277762,
      "grad_norm": 0.3392025828361511,
      "learning_rate": 1.978783346123464e-05,
      "loss": 0.5875,
      "step": 4371
    },
    {
      "epoch": 0.1343040579977268,
      "grad_norm": 0.32892054319381714,
      "learning_rate": 1.9787734427279167e-05,
      "loss": 0.6101,
      "step": 4372
    },
    {
      "epoch": 0.13433477713267594,
      "grad_norm": 0.3510526418685913,
      "learning_rate": 1.9787635370463753e-05,
      "loss": 0.5671,
      "step": 4373
    },
    {
      "epoch": 0.13436549626762512,
      "grad_norm": 0.3518812358379364,
      "learning_rate": 1.9787536290788635e-05,
      "loss": 0.6524,
      "step": 4374
    },
    {
      "epoch": 0.13439621540257427,
      "grad_norm": 0.31839925050735474,
      "learning_rate": 1.9787437188254042e-05,
      "loss": 0.5399,
      "step": 4375
    },
    {
      "epoch": 0.1344269345375234,
      "grad_norm": 0.3263569176197052,
      "learning_rate": 1.9787338062860206e-05,
      "loss": 0.6333,
      "step": 4376
    },
    {
      "epoch": 0.1344576536724726,
      "grad_norm": 0.42989686131477356,
      "learning_rate": 1.9787238914607355e-05,
      "loss": 0.6924,
      "step": 4377
    },
    {
      "epoch": 0.13448837280742174,
      "grad_norm": 0.384536474943161,
      "learning_rate": 1.9787139743495728e-05,
      "loss": 0.6706,
      "step": 4378
    },
    {
      "epoch": 0.1345190919423709,
      "grad_norm": 0.3507455587387085,
      "learning_rate": 1.9787040549525552e-05,
      "loss": 0.6537,
      "step": 4379
    },
    {
      "epoch": 0.13454981107732006,
      "grad_norm": 0.3457149267196655,
      "learning_rate": 1.9786941332697056e-05,
      "loss": 0.6269,
      "step": 4380
    },
    {
      "epoch": 0.13458053021226923,
      "grad_norm": 0.36148393154144287,
      "learning_rate": 1.978684209301048e-05,
      "loss": 0.5836,
      "step": 4381
    },
    {
      "epoch": 0.13461124934721838,
      "grad_norm": 0.3404276669025421,
      "learning_rate": 1.9786742830466046e-05,
      "loss": 0.6,
      "step": 4382
    },
    {
      "epoch": 0.13464196848216753,
      "grad_norm": 1.3200973272323608,
      "learning_rate": 1.9786643545063993e-05,
      "loss": 0.5598,
      "step": 4383
    },
    {
      "epoch": 0.1346726876171167,
      "grad_norm": 0.3306865692138672,
      "learning_rate": 1.978654423680455e-05,
      "loss": 0.6678,
      "step": 4384
    },
    {
      "epoch": 0.13470340675206585,
      "grad_norm": 0.3671681880950928,
      "learning_rate": 1.978644490568795e-05,
      "loss": 0.646,
      "step": 4385
    },
    {
      "epoch": 0.13473412588701503,
      "grad_norm": 0.39160609245300293,
      "learning_rate": 1.9786345551714426e-05,
      "loss": 0.6118,
      "step": 4386
    },
    {
      "epoch": 0.13476484502196417,
      "grad_norm": 0.33711469173431396,
      "learning_rate": 1.978624617488421e-05,
      "loss": 0.6542,
      "step": 4387
    },
    {
      "epoch": 0.13479556415691335,
      "grad_norm": 0.37090814113616943,
      "learning_rate": 1.9786146775197526e-05,
      "loss": 0.6544,
      "step": 4388
    },
    {
      "epoch": 0.1348262832918625,
      "grad_norm": 0.32710468769073486,
      "learning_rate": 1.9786047352654617e-05,
      "loss": 0.6253,
      "step": 4389
    },
    {
      "epoch": 0.13485700242681167,
      "grad_norm": 0.3323386609554291,
      "learning_rate": 1.978594790725571e-05,
      "loss": 0.6112,
      "step": 4390
    },
    {
      "epoch": 0.13488772156176082,
      "grad_norm": 0.39377593994140625,
      "learning_rate": 1.978584843900104e-05,
      "loss": 0.5541,
      "step": 4391
    },
    {
      "epoch": 0.13491844069670997,
      "grad_norm": 0.34699395298957825,
      "learning_rate": 1.9785748947890835e-05,
      "loss": 0.6419,
      "step": 4392
    },
    {
      "epoch": 0.13494915983165914,
      "grad_norm": 0.37308019399642944,
      "learning_rate": 1.978564943392533e-05,
      "loss": 0.5382,
      "step": 4393
    },
    {
      "epoch": 0.1349798789666083,
      "grad_norm": 0.3299615979194641,
      "learning_rate": 1.9785549897104757e-05,
      "loss": 0.5395,
      "step": 4394
    },
    {
      "epoch": 0.13501059810155747,
      "grad_norm": 0.2974483072757721,
      "learning_rate": 1.978545033742935e-05,
      "loss": 0.5797,
      "step": 4395
    },
    {
      "epoch": 0.13504131723650661,
      "grad_norm": 0.4714646339416504,
      "learning_rate": 1.978535075489934e-05,
      "loss": 0.6083,
      "step": 4396
    },
    {
      "epoch": 0.1350720363714558,
      "grad_norm": 0.3137882649898529,
      "learning_rate": 1.978525114951496e-05,
      "loss": 0.5225,
      "step": 4397
    },
    {
      "epoch": 0.13510275550640494,
      "grad_norm": 0.3381197452545166,
      "learning_rate": 1.9785151521276443e-05,
      "loss": 0.6981,
      "step": 4398
    },
    {
      "epoch": 0.1351334746413541,
      "grad_norm": 0.3154951333999634,
      "learning_rate": 1.978505187018402e-05,
      "loss": 0.5508,
      "step": 4399
    },
    {
      "epoch": 0.13516419377630326,
      "grad_norm": 0.4397277235984802,
      "learning_rate": 1.9784952196237927e-05,
      "loss": 0.6968,
      "step": 4400
    },
    {
      "epoch": 0.1351949129112524,
      "grad_norm": 0.3178330361843109,
      "learning_rate": 1.9784852499438394e-05,
      "loss": 0.5215,
      "step": 4401
    },
    {
      "epoch": 0.13522563204620158,
      "grad_norm": 0.3823036849498749,
      "learning_rate": 1.9784752779785656e-05,
      "loss": 0.5532,
      "step": 4402
    },
    {
      "epoch": 0.13525635118115073,
      "grad_norm": 0.30318835377693176,
      "learning_rate": 1.9784653037279938e-05,
      "loss": 0.5542,
      "step": 4403
    },
    {
      "epoch": 0.1352870703160999,
      "grad_norm": 0.33618056774139404,
      "learning_rate": 1.9784553271921488e-05,
      "loss": 0.6276,
      "step": 4404
    },
    {
      "epoch": 0.13531778945104905,
      "grad_norm": 0.3566704988479614,
      "learning_rate": 1.9784453483710523e-05,
      "loss": 0.5843,
      "step": 4405
    },
    {
      "epoch": 0.13534850858599823,
      "grad_norm": 0.3529864251613617,
      "learning_rate": 1.978435367264729e-05,
      "loss": 0.6952,
      "step": 4406
    },
    {
      "epoch": 0.13537922772094738,
      "grad_norm": 0.31415602564811707,
      "learning_rate": 1.9784253838732012e-05,
      "loss": 0.5595,
      "step": 4407
    },
    {
      "epoch": 0.13540994685589655,
      "grad_norm": 0.350422203540802,
      "learning_rate": 1.9784153981964927e-05,
      "loss": 0.5693,
      "step": 4408
    },
    {
      "epoch": 0.1354406659908457,
      "grad_norm": 13.392049789428711,
      "learning_rate": 1.978405410234627e-05,
      "loss": 0.5735,
      "step": 4409
    },
    {
      "epoch": 0.13547138512579485,
      "grad_norm": 0.34208405017852783,
      "learning_rate": 1.9783954199876265e-05,
      "loss": 0.6302,
      "step": 4410
    },
    {
      "epoch": 0.13550210426074402,
      "grad_norm": 0.355143278837204,
      "learning_rate": 1.9783854274555155e-05,
      "loss": 0.6641,
      "step": 4411
    },
    {
      "epoch": 0.13553282339569317,
      "grad_norm": 0.31702661514282227,
      "learning_rate": 1.978375432638317e-05,
      "loss": 0.5458,
      "step": 4412
    },
    {
      "epoch": 0.13556354253064234,
      "grad_norm": 0.35622265934944153,
      "learning_rate": 1.9783654355360543e-05,
      "loss": 0.5393,
      "step": 4413
    },
    {
      "epoch": 0.1355942616655915,
      "grad_norm": 0.34844425320625305,
      "learning_rate": 1.9783554361487508e-05,
      "loss": 0.6131,
      "step": 4414
    },
    {
      "epoch": 0.13562498080054067,
      "grad_norm": 0.328110009431839,
      "learning_rate": 1.9783454344764302e-05,
      "loss": 0.5693,
      "step": 4415
    },
    {
      "epoch": 0.13565569993548982,
      "grad_norm": 0.31540820002555847,
      "learning_rate": 1.978335430519115e-05,
      "loss": 0.6007,
      "step": 4416
    },
    {
      "epoch": 0.13568641907043896,
      "grad_norm": 0.3329354226589203,
      "learning_rate": 1.9783254242768294e-05,
      "loss": 0.6848,
      "step": 4417
    },
    {
      "epoch": 0.13571713820538814,
      "grad_norm": 0.3557731807231903,
      "learning_rate": 1.978315415749596e-05,
      "loss": 0.5817,
      "step": 4418
    },
    {
      "epoch": 0.13574785734033729,
      "grad_norm": 0.35920459032058716,
      "learning_rate": 1.9783054049374392e-05,
      "loss": 0.5782,
      "step": 4419
    },
    {
      "epoch": 0.13577857647528646,
      "grad_norm": 0.6937598586082458,
      "learning_rate": 1.9782953918403813e-05,
      "loss": 0.6473,
      "step": 4420
    },
    {
      "epoch": 0.1358092956102356,
      "grad_norm": 0.36984673142433167,
      "learning_rate": 1.9782853764584466e-05,
      "loss": 0.5697,
      "step": 4421
    },
    {
      "epoch": 0.13584001474518478,
      "grad_norm": 0.32663390040397644,
      "learning_rate": 1.9782753587916578e-05,
      "loss": 0.6273,
      "step": 4422
    },
    {
      "epoch": 0.13587073388013393,
      "grad_norm": 0.3354629576206207,
      "learning_rate": 1.978265338840039e-05,
      "loss": 0.5586,
      "step": 4423
    },
    {
      "epoch": 0.1359014530150831,
      "grad_norm": 0.338153600692749,
      "learning_rate": 1.9782553166036128e-05,
      "loss": 0.6676,
      "step": 4424
    },
    {
      "epoch": 0.13593217215003225,
      "grad_norm": 0.39694347977638245,
      "learning_rate": 1.9782452920824033e-05,
      "loss": 0.5915,
      "step": 4425
    },
    {
      "epoch": 0.1359628912849814,
      "grad_norm": 0.3430796265602112,
      "learning_rate": 1.9782352652764332e-05,
      "loss": 0.6111,
      "step": 4426
    },
    {
      "epoch": 0.13599361041993058,
      "grad_norm": 0.3363812267780304,
      "learning_rate": 1.9782252361857263e-05,
      "loss": 0.6259,
      "step": 4427
    },
    {
      "epoch": 0.13602432955487972,
      "grad_norm": 0.32690146565437317,
      "learning_rate": 1.9782152048103063e-05,
      "loss": 0.6073,
      "step": 4428
    },
    {
      "epoch": 0.1360550486898289,
      "grad_norm": 0.33469367027282715,
      "learning_rate": 1.978205171150196e-05,
      "loss": 0.5679,
      "step": 4429
    },
    {
      "epoch": 0.13608576782477805,
      "grad_norm": 0.33856797218322754,
      "learning_rate": 1.97819513520542e-05,
      "loss": 0.6809,
      "step": 4430
    },
    {
      "epoch": 0.13611648695972722,
      "grad_norm": 0.35788214206695557,
      "learning_rate": 1.9781850969760003e-05,
      "loss": 0.5386,
      "step": 4431
    },
    {
      "epoch": 0.13614720609467637,
      "grad_norm": 0.3780348002910614,
      "learning_rate": 1.9781750564619607e-05,
      "loss": 0.6244,
      "step": 4432
    },
    {
      "epoch": 0.13617792522962555,
      "grad_norm": 0.44539856910705566,
      "learning_rate": 1.9781650136633256e-05,
      "loss": 0.4841,
      "step": 4433
    },
    {
      "epoch": 0.1362086443645747,
      "grad_norm": 0.3708028793334961,
      "learning_rate": 1.9781549685801175e-05,
      "loss": 0.5427,
      "step": 4434
    },
    {
      "epoch": 0.13623936349952384,
      "grad_norm": 0.3530467450618744,
      "learning_rate": 1.9781449212123604e-05,
      "loss": 0.5521,
      "step": 4435
    },
    {
      "epoch": 0.13627008263447302,
      "grad_norm": 0.3464943766593933,
      "learning_rate": 1.9781348715600774e-05,
      "loss": 0.6049,
      "step": 4436
    },
    {
      "epoch": 0.13630080176942216,
      "grad_norm": 0.3399164378643036,
      "learning_rate": 1.978124819623292e-05,
      "loss": 0.5881,
      "step": 4437
    },
    {
      "epoch": 0.13633152090437134,
      "grad_norm": 0.37794429063796997,
      "learning_rate": 1.978114765402028e-05,
      "loss": 0.6751,
      "step": 4438
    },
    {
      "epoch": 0.1363622400393205,
      "grad_norm": 0.34909164905548096,
      "learning_rate": 1.9781047088963082e-05,
      "loss": 0.5876,
      "step": 4439
    },
    {
      "epoch": 0.13639295917426966,
      "grad_norm": 0.31627652049064636,
      "learning_rate": 1.978094650106157e-05,
      "loss": 0.5638,
      "step": 4440
    },
    {
      "epoch": 0.1364236783092188,
      "grad_norm": 0.3764617443084717,
      "learning_rate": 1.978084589031597e-05,
      "loss": 0.5043,
      "step": 4441
    },
    {
      "epoch": 0.13645439744416799,
      "grad_norm": 0.3675718903541565,
      "learning_rate": 1.9780745256726526e-05,
      "loss": 0.6804,
      "step": 4442
    },
    {
      "epoch": 0.13648511657911713,
      "grad_norm": 0.32106924057006836,
      "learning_rate": 1.9780644600293465e-05,
      "loss": 0.6138,
      "step": 4443
    },
    {
      "epoch": 0.13651583571406628,
      "grad_norm": 0.34370118379592896,
      "learning_rate": 1.9780543921017026e-05,
      "loss": 0.5981,
      "step": 4444
    },
    {
      "epoch": 0.13654655484901546,
      "grad_norm": 0.5437188744544983,
      "learning_rate": 1.9780443218897446e-05,
      "loss": 0.671,
      "step": 4445
    },
    {
      "epoch": 0.1365772739839646,
      "grad_norm": 0.36525827646255493,
      "learning_rate": 1.9780342493934953e-05,
      "loss": 0.591,
      "step": 4446
    },
    {
      "epoch": 0.13660799311891378,
      "grad_norm": 0.30241113901138306,
      "learning_rate": 1.9780241746129795e-05,
      "loss": 0.594,
      "step": 4447
    },
    {
      "epoch": 0.13663871225386293,
      "grad_norm": 0.30361974239349365,
      "learning_rate": 1.9780140975482194e-05,
      "loss": 0.6036,
      "step": 4448
    },
    {
      "epoch": 0.1366694313888121,
      "grad_norm": 0.34674033522605896,
      "learning_rate": 1.978004018199239e-05,
      "loss": 0.641,
      "step": 4449
    },
    {
      "epoch": 0.13670015052376125,
      "grad_norm": 0.5231220126152039,
      "learning_rate": 1.977993936566062e-05,
      "loss": 0.5573,
      "step": 4450
    },
    {
      "epoch": 0.13673086965871042,
      "grad_norm": 0.3711162507534027,
      "learning_rate": 1.977983852648712e-05,
      "loss": 0.5209,
      "step": 4451
    },
    {
      "epoch": 0.13676158879365957,
      "grad_norm": 0.3749333620071411,
      "learning_rate": 1.977973766447212e-05,
      "loss": 0.5656,
      "step": 4452
    },
    {
      "epoch": 0.13679230792860872,
      "grad_norm": 0.31625911593437195,
      "learning_rate": 1.9779636779615865e-05,
      "loss": 0.5494,
      "step": 4453
    },
    {
      "epoch": 0.1368230270635579,
      "grad_norm": 0.34151190519332886,
      "learning_rate": 1.9779535871918584e-05,
      "loss": 0.6531,
      "step": 4454
    },
    {
      "epoch": 0.13685374619850704,
      "grad_norm": 0.34074828028678894,
      "learning_rate": 1.9779434941380514e-05,
      "loss": 0.6009,
      "step": 4455
    },
    {
      "epoch": 0.13688446533345622,
      "grad_norm": 0.3442020118236542,
      "learning_rate": 1.977933398800189e-05,
      "loss": 0.5974,
      "step": 4456
    },
    {
      "epoch": 0.13691518446840537,
      "grad_norm": 0.4164305031299591,
      "learning_rate": 1.9779233011782945e-05,
      "loss": 0.6199,
      "step": 4457
    },
    {
      "epoch": 0.13694590360335454,
      "grad_norm": 0.32570451498031616,
      "learning_rate": 1.977913201272392e-05,
      "loss": 0.5474,
      "step": 4458
    },
    {
      "epoch": 0.1369766227383037,
      "grad_norm": 0.36461371183395386,
      "learning_rate": 1.977903099082505e-05,
      "loss": 0.5586,
      "step": 4459
    },
    {
      "epoch": 0.13700734187325284,
      "grad_norm": 0.32858142256736755,
      "learning_rate": 1.9778929946086573e-05,
      "loss": 0.5747,
      "step": 4460
    },
    {
      "epoch": 0.137038061008202,
      "grad_norm": 0.7754678726196289,
      "learning_rate": 1.977882887850872e-05,
      "loss": 0.6536,
      "step": 4461
    },
    {
      "epoch": 0.13706878014315116,
      "grad_norm": 0.387199729681015,
      "learning_rate": 1.977872778809173e-05,
      "loss": 0.6112,
      "step": 4462
    },
    {
      "epoch": 0.13709949927810033,
      "grad_norm": 0.45527201890945435,
      "learning_rate": 1.9778626674835837e-05,
      "loss": 0.5727,
      "step": 4463
    },
    {
      "epoch": 0.13713021841304948,
      "grad_norm": 0.346097469329834,
      "learning_rate": 1.977852553874128e-05,
      "loss": 0.5973,
      "step": 4464
    },
    {
      "epoch": 0.13716093754799866,
      "grad_norm": 0.32482415437698364,
      "learning_rate": 1.9778424379808292e-05,
      "loss": 0.5918,
      "step": 4465
    },
    {
      "epoch": 0.1371916566829478,
      "grad_norm": 0.32827022671699524,
      "learning_rate": 1.977832319803711e-05,
      "loss": 0.6945,
      "step": 4466
    },
    {
      "epoch": 0.13722237581789698,
      "grad_norm": 0.31616514921188354,
      "learning_rate": 1.9778221993427976e-05,
      "loss": 0.4367,
      "step": 4467
    },
    {
      "epoch": 0.13725309495284613,
      "grad_norm": 0.345186710357666,
      "learning_rate": 1.9778120765981118e-05,
      "loss": 0.542,
      "step": 4468
    },
    {
      "epoch": 0.13728381408779528,
      "grad_norm": 0.3524705767631531,
      "learning_rate": 1.9778019515696777e-05,
      "loss": 0.6466,
      "step": 4469
    },
    {
      "epoch": 0.13731453322274445,
      "grad_norm": 0.37942609190940857,
      "learning_rate": 1.9777918242575188e-05,
      "loss": 0.6425,
      "step": 4470
    },
    {
      "epoch": 0.1373452523576936,
      "grad_norm": 0.33622172474861145,
      "learning_rate": 1.9777816946616588e-05,
      "loss": 0.5825,
      "step": 4471
    },
    {
      "epoch": 0.13737597149264277,
      "grad_norm": 0.3774675130844116,
      "learning_rate": 1.9777715627821213e-05,
      "loss": 0.6542,
      "step": 4472
    },
    {
      "epoch": 0.13740669062759192,
      "grad_norm": 0.32253867387771606,
      "learning_rate": 1.9777614286189302e-05,
      "loss": 0.6017,
      "step": 4473
    },
    {
      "epoch": 0.1374374097625411,
      "grad_norm": 0.3692786693572998,
      "learning_rate": 1.9777512921721088e-05,
      "loss": 0.6364,
      "step": 4474
    },
    {
      "epoch": 0.13746812889749024,
      "grad_norm": 0.3408094048500061,
      "learning_rate": 1.977741153441681e-05,
      "loss": 0.6171,
      "step": 4475
    },
    {
      "epoch": 0.13749884803243942,
      "grad_norm": 0.34938549995422363,
      "learning_rate": 1.9777310124276706e-05,
      "loss": 0.5816,
      "step": 4476
    },
    {
      "epoch": 0.13752956716738857,
      "grad_norm": 0.35605061054229736,
      "learning_rate": 1.977720869130101e-05,
      "loss": 0.6307,
      "step": 4477
    },
    {
      "epoch": 0.13756028630233771,
      "grad_norm": 0.31992679834365845,
      "learning_rate": 1.9777107235489962e-05,
      "loss": 0.6542,
      "step": 4478
    },
    {
      "epoch": 0.1375910054372869,
      "grad_norm": 0.40645700693130493,
      "learning_rate": 1.9777005756843797e-05,
      "loss": 0.6119,
      "step": 4479
    },
    {
      "epoch": 0.13762172457223604,
      "grad_norm": 0.35264357924461365,
      "learning_rate": 1.9776904255362752e-05,
      "loss": 0.5535,
      "step": 4480
    },
    {
      "epoch": 0.1376524437071852,
      "grad_norm": 0.33254024386405945,
      "learning_rate": 1.9776802731047065e-05,
      "loss": 0.6284,
      "step": 4481
    },
    {
      "epoch": 0.13768316284213436,
      "grad_norm": 0.36652883887290955,
      "learning_rate": 1.9776701183896968e-05,
      "loss": 0.6613,
      "step": 4482
    },
    {
      "epoch": 0.13771388197708354,
      "grad_norm": 0.3307726979255676,
      "learning_rate": 1.977659961391271e-05,
      "loss": 0.582,
      "step": 4483
    },
    {
      "epoch": 0.13774460111203268,
      "grad_norm": 0.2965764105319977,
      "learning_rate": 1.9776498021094516e-05,
      "loss": 0.5862,
      "step": 4484
    },
    {
      "epoch": 0.13777532024698186,
      "grad_norm": 0.35749056935310364,
      "learning_rate": 1.9776396405442625e-05,
      "loss": 0.5841,
      "step": 4485
    },
    {
      "epoch": 0.137806039381931,
      "grad_norm": 0.35105475783348083,
      "learning_rate": 1.977629476695728e-05,
      "loss": 0.5771,
      "step": 4486
    },
    {
      "epoch": 0.13783675851688015,
      "grad_norm": 0.37409940361976624,
      "learning_rate": 1.977619310563872e-05,
      "loss": 0.6656,
      "step": 4487
    },
    {
      "epoch": 0.13786747765182933,
      "grad_norm": 0.37122705578804016,
      "learning_rate": 1.9776091421487173e-05,
      "loss": 0.6135,
      "step": 4488
    },
    {
      "epoch": 0.13789819678677848,
      "grad_norm": 0.4183451235294342,
      "learning_rate": 1.9775989714502884e-05,
      "loss": 0.5791,
      "step": 4489
    },
    {
      "epoch": 0.13792891592172765,
      "grad_norm": 0.31003618240356445,
      "learning_rate": 1.9775887984686087e-05,
      "loss": 0.582,
      "step": 4490
    },
    {
      "epoch": 0.1379596350566768,
      "grad_norm": 0.313114732503891,
      "learning_rate": 1.9775786232037025e-05,
      "loss": 0.5952,
      "step": 4491
    },
    {
      "epoch": 0.13799035419162597,
      "grad_norm": 0.34014058113098145,
      "learning_rate": 1.977568445655593e-05,
      "loss": 0.6888,
      "step": 4492
    },
    {
      "epoch": 0.13802107332657512,
      "grad_norm": 0.4131802022457123,
      "learning_rate": 1.9775582658243037e-05,
      "loss": 0.5485,
      "step": 4493
    },
    {
      "epoch": 0.13805179246152427,
      "grad_norm": 0.33067095279693604,
      "learning_rate": 1.9775480837098592e-05,
      "loss": 0.5968,
      "step": 4494
    },
    {
      "epoch": 0.13808251159647345,
      "grad_norm": 0.3271838128566742,
      "learning_rate": 1.9775378993122827e-05,
      "loss": 0.5798,
      "step": 4495
    },
    {
      "epoch": 0.1381132307314226,
      "grad_norm": 0.3524806797504425,
      "learning_rate": 1.977527712631598e-05,
      "loss": 0.6271,
      "step": 4496
    },
    {
      "epoch": 0.13814394986637177,
      "grad_norm": 0.33001023530960083,
      "learning_rate": 1.9775175236678293e-05,
      "loss": 0.6359,
      "step": 4497
    },
    {
      "epoch": 0.13817466900132092,
      "grad_norm": 0.3772483170032501,
      "learning_rate": 1.9775073324210005e-05,
      "loss": 0.5992,
      "step": 4498
    },
    {
      "epoch": 0.1382053881362701,
      "grad_norm": 0.348190039396286,
      "learning_rate": 1.9774971388911343e-05,
      "loss": 0.7023,
      "step": 4499
    },
    {
      "epoch": 0.13823610727121924,
      "grad_norm": 0.33349624276161194,
      "learning_rate": 1.977486943078256e-05,
      "loss": 0.6305,
      "step": 4500
    },
    {
      "epoch": 0.1382668264061684,
      "grad_norm": 0.3829382359981537,
      "learning_rate": 1.9774767449823883e-05,
      "loss": 0.6555,
      "step": 4501
    },
    {
      "epoch": 0.13829754554111756,
      "grad_norm": 0.4552218019962311,
      "learning_rate": 1.9774665446035552e-05,
      "loss": 0.6286,
      "step": 4502
    },
    {
      "epoch": 0.1383282646760667,
      "grad_norm": 0.3777869939804077,
      "learning_rate": 1.977456341941781e-05,
      "loss": 0.6435,
      "step": 4503
    },
    {
      "epoch": 0.13835898381101588,
      "grad_norm": 0.34562554955482483,
      "learning_rate": 1.977446136997089e-05,
      "loss": 0.583,
      "step": 4504
    },
    {
      "epoch": 0.13838970294596503,
      "grad_norm": 0.3227694630622864,
      "learning_rate": 1.9774359297695035e-05,
      "loss": 0.6725,
      "step": 4505
    },
    {
      "epoch": 0.1384204220809142,
      "grad_norm": 0.347793310880661,
      "learning_rate": 1.9774257202590485e-05,
      "loss": 0.6139,
      "step": 4506
    },
    {
      "epoch": 0.13845114121586335,
      "grad_norm": 0.39027073979377747,
      "learning_rate": 1.9774155084657468e-05,
      "loss": 0.6077,
      "step": 4507
    },
    {
      "epoch": 0.13848186035081253,
      "grad_norm": 0.3194609582424164,
      "learning_rate": 1.9774052943896233e-05,
      "loss": 0.6012,
      "step": 4508
    },
    {
      "epoch": 0.13851257948576168,
      "grad_norm": 0.3366239368915558,
      "learning_rate": 1.9773950780307013e-05,
      "loss": 0.635,
      "step": 4509
    },
    {
      "epoch": 0.13854329862071085,
      "grad_norm": 0.34745165705680847,
      "learning_rate": 1.9773848593890048e-05,
      "loss": 0.57,
      "step": 4510
    },
    {
      "epoch": 0.13857401775566,
      "grad_norm": 0.33734166622161865,
      "learning_rate": 1.977374638464558e-05,
      "loss": 0.5467,
      "step": 4511
    },
    {
      "epoch": 0.13860473689060915,
      "grad_norm": 0.3994484841823578,
      "learning_rate": 1.977364415257384e-05,
      "loss": 0.5919,
      "step": 4512
    },
    {
      "epoch": 0.13863545602555832,
      "grad_norm": 0.3188476860523224,
      "learning_rate": 1.9773541897675077e-05,
      "loss": 0.5981,
      "step": 4513
    },
    {
      "epoch": 0.13866617516050747,
      "grad_norm": 0.3315235376358032,
      "learning_rate": 1.9773439619949522e-05,
      "loss": 0.6307,
      "step": 4514
    },
    {
      "epoch": 0.13869689429545665,
      "grad_norm": 0.4052271842956543,
      "learning_rate": 1.9773337319397412e-05,
      "loss": 0.6871,
      "step": 4515
    },
    {
      "epoch": 0.1387276134304058,
      "grad_norm": 0.3325587511062622,
      "learning_rate": 1.9773234996018994e-05,
      "loss": 0.5672,
      "step": 4516
    },
    {
      "epoch": 0.13875833256535497,
      "grad_norm": 0.48509910702705383,
      "learning_rate": 1.9773132649814505e-05,
      "loss": 0.669,
      "step": 4517
    },
    {
      "epoch": 0.13878905170030412,
      "grad_norm": 0.33822670578956604,
      "learning_rate": 1.977303028078418e-05,
      "loss": 0.6276,
      "step": 4518
    },
    {
      "epoch": 0.1388197708352533,
      "grad_norm": 0.358920156955719,
      "learning_rate": 1.977292788892826e-05,
      "loss": 0.5958,
      "step": 4519
    },
    {
      "epoch": 0.13885048997020244,
      "grad_norm": 0.5548242330551147,
      "learning_rate": 1.9772825474246984e-05,
      "loss": 0.5679,
      "step": 4520
    },
    {
      "epoch": 0.1388812091051516,
      "grad_norm": 0.3179902732372284,
      "learning_rate": 1.9772723036740594e-05,
      "loss": 0.5314,
      "step": 4521
    },
    {
      "epoch": 0.13891192824010076,
      "grad_norm": 0.35208913683891296,
      "learning_rate": 1.977262057640932e-05,
      "loss": 0.644,
      "step": 4522
    },
    {
      "epoch": 0.1389426473750499,
      "grad_norm": 0.34875544905662537,
      "learning_rate": 1.9772518093253418e-05,
      "loss": 0.6574,
      "step": 4523
    },
    {
      "epoch": 0.13897336650999909,
      "grad_norm": 0.4637799859046936,
      "learning_rate": 1.977241558727311e-05,
      "loss": 0.6507,
      "step": 4524
    },
    {
      "epoch": 0.13900408564494823,
      "grad_norm": 0.3328540027141571,
      "learning_rate": 1.9772313058468647e-05,
      "loss": 0.5286,
      "step": 4525
    },
    {
      "epoch": 0.1390348047798974,
      "grad_norm": 0.46615636348724365,
      "learning_rate": 1.9772210506840264e-05,
      "loss": 0.6131,
      "step": 4526
    },
    {
      "epoch": 0.13906552391484656,
      "grad_norm": 0.44181686639785767,
      "learning_rate": 1.97721079323882e-05,
      "loss": 0.5832,
      "step": 4527
    },
    {
      "epoch": 0.13909624304979573,
      "grad_norm": 0.35354846715927124,
      "learning_rate": 1.9772005335112695e-05,
      "loss": 0.6113,
      "step": 4528
    },
    {
      "epoch": 0.13912696218474488,
      "grad_norm": 0.34187406301498413,
      "learning_rate": 1.9771902715013987e-05,
      "loss": 0.5809,
      "step": 4529
    },
    {
      "epoch": 0.13915768131969403,
      "grad_norm": 0.366234689950943,
      "learning_rate": 1.9771800072092322e-05,
      "loss": 0.5248,
      "step": 4530
    },
    {
      "epoch": 0.1391884004546432,
      "grad_norm": 0.3485596179962158,
      "learning_rate": 1.9771697406347933e-05,
      "loss": 0.5189,
      "step": 4531
    },
    {
      "epoch": 0.13921911958959235,
      "grad_norm": 0.5691792964935303,
      "learning_rate": 1.9771594717781065e-05,
      "loss": 0.5844,
      "step": 4532
    },
    {
      "epoch": 0.13924983872454152,
      "grad_norm": 0.3414352238178253,
      "learning_rate": 1.977149200639195e-05,
      "loss": 0.6125,
      "step": 4533
    },
    {
      "epoch": 0.13928055785949067,
      "grad_norm": 0.36736172437667847,
      "learning_rate": 1.977138927218084e-05,
      "loss": 0.649,
      "step": 4534
    },
    {
      "epoch": 0.13931127699443985,
      "grad_norm": 0.338529109954834,
      "learning_rate": 1.977128651514796e-05,
      "loss": 0.585,
      "step": 4535
    },
    {
      "epoch": 0.139341996129389,
      "grad_norm": 0.33002421259880066,
      "learning_rate": 1.9771183735293565e-05,
      "loss": 0.6044,
      "step": 4536
    },
    {
      "epoch": 0.13937271526433814,
      "grad_norm": 0.34177497029304504,
      "learning_rate": 1.9771080932617884e-05,
      "loss": 0.606,
      "step": 4537
    },
    {
      "epoch": 0.13940343439928732,
      "grad_norm": 0.3579985499382019,
      "learning_rate": 1.977097810712116e-05,
      "loss": 0.5689,
      "step": 4538
    },
    {
      "epoch": 0.13943415353423647,
      "grad_norm": 0.4389031231403351,
      "learning_rate": 1.977087525880364e-05,
      "loss": 0.5173,
      "step": 4539
    },
    {
      "epoch": 0.13946487266918564,
      "grad_norm": 0.30808335542678833,
      "learning_rate": 1.977077238766555e-05,
      "loss": 0.6109,
      "step": 4540
    },
    {
      "epoch": 0.1394955918041348,
      "grad_norm": 0.3606942594051361,
      "learning_rate": 1.9770669493707145e-05,
      "loss": 0.5744,
      "step": 4541
    },
    {
      "epoch": 0.13952631093908396,
      "grad_norm": 0.34838902950286865,
      "learning_rate": 1.977056657692866e-05,
      "loss": 0.6014,
      "step": 4542
    },
    {
      "epoch": 0.1395570300740331,
      "grad_norm": 0.33253204822540283,
      "learning_rate": 1.977046363733033e-05,
      "loss": 0.6009,
      "step": 4543
    },
    {
      "epoch": 0.1395877492089823,
      "grad_norm": 0.34475043416023254,
      "learning_rate": 1.97703606749124e-05,
      "loss": 0.5847,
      "step": 4544
    },
    {
      "epoch": 0.13961846834393143,
      "grad_norm": 0.32102882862091064,
      "learning_rate": 1.9770257689675112e-05,
      "loss": 0.6143,
      "step": 4545
    },
    {
      "epoch": 0.13964918747888058,
      "grad_norm": 0.5088224411010742,
      "learning_rate": 1.9770154681618705e-05,
      "loss": 0.6689,
      "step": 4546
    },
    {
      "epoch": 0.13967990661382976,
      "grad_norm": 0.32154762744903564,
      "learning_rate": 1.9770051650743418e-05,
      "loss": 0.6034,
      "step": 4547
    },
    {
      "epoch": 0.1397106257487789,
      "grad_norm": 0.32160094380378723,
      "learning_rate": 1.9769948597049496e-05,
      "loss": 0.6133,
      "step": 4548
    },
    {
      "epoch": 0.13974134488372808,
      "grad_norm": 0.34840020537376404,
      "learning_rate": 1.9769845520537174e-05,
      "loss": 0.657,
      "step": 4549
    },
    {
      "epoch": 0.13977206401867723,
      "grad_norm": 0.36230310797691345,
      "learning_rate": 1.9769742421206696e-05,
      "loss": 0.5963,
      "step": 4550
    },
    {
      "epoch": 0.1398027831536264,
      "grad_norm": 0.33288830518722534,
      "learning_rate": 1.9769639299058302e-05,
      "loss": 0.5489,
      "step": 4551
    },
    {
      "epoch": 0.13983350228857555,
      "grad_norm": 0.3317974805831909,
      "learning_rate": 1.9769536154092233e-05,
      "loss": 0.6185,
      "step": 4552
    },
    {
      "epoch": 0.13986422142352473,
      "grad_norm": 0.3555822968482971,
      "learning_rate": 1.976943298630873e-05,
      "loss": 0.6684,
      "step": 4553
    },
    {
      "epoch": 0.13989494055847387,
      "grad_norm": 0.33563390374183655,
      "learning_rate": 1.9769329795708033e-05,
      "loss": 0.6243,
      "step": 4554
    },
    {
      "epoch": 0.13992565969342302,
      "grad_norm": 0.32244664430618286,
      "learning_rate": 1.9769226582290385e-05,
      "loss": 0.5904,
      "step": 4555
    },
    {
      "epoch": 0.1399563788283722,
      "grad_norm": 0.2958434224128723,
      "learning_rate": 1.976912334605603e-05,
      "loss": 0.4783,
      "step": 4556
    },
    {
      "epoch": 0.13998709796332134,
      "grad_norm": 0.3816477060317993,
      "learning_rate": 1.97690200870052e-05,
      "loss": 0.5685,
      "step": 4557
    },
    {
      "epoch": 0.14001781709827052,
      "grad_norm": 0.34382790327072144,
      "learning_rate": 1.9768916805138146e-05,
      "loss": 0.6079,
      "step": 4558
    },
    {
      "epoch": 0.14004853623321967,
      "grad_norm": 0.33329030871391296,
      "learning_rate": 1.97688135004551e-05,
      "loss": 0.5812,
      "step": 4559
    },
    {
      "epoch": 0.14007925536816884,
      "grad_norm": 0.3279561996459961,
      "learning_rate": 1.9768710172956308e-05,
      "loss": 0.6198,
      "step": 4560
    },
    {
      "epoch": 0.140109974503118,
      "grad_norm": 0.31055861711502075,
      "learning_rate": 1.9768606822642012e-05,
      "loss": 0.6109,
      "step": 4561
    },
    {
      "epoch": 0.14014069363806717,
      "grad_norm": 0.36717167496681213,
      "learning_rate": 1.9768503449512454e-05,
      "loss": 0.6079,
      "step": 4562
    },
    {
      "epoch": 0.1401714127730163,
      "grad_norm": 0.3305298984050751,
      "learning_rate": 1.9768400053567873e-05,
      "loss": 0.5804,
      "step": 4563
    },
    {
      "epoch": 0.14020213190796546,
      "grad_norm": 0.36205098032951355,
      "learning_rate": 1.976829663480851e-05,
      "loss": 0.639,
      "step": 4564
    },
    {
      "epoch": 0.14023285104291464,
      "grad_norm": 0.2915742099285126,
      "learning_rate": 1.976819319323461e-05,
      "loss": 0.5797,
      "step": 4565
    },
    {
      "epoch": 0.14026357017786378,
      "grad_norm": 0.36095234751701355,
      "learning_rate": 1.9768089728846414e-05,
      "loss": 0.6209,
      "step": 4566
    },
    {
      "epoch": 0.14029428931281296,
      "grad_norm": 0.35170885920524597,
      "learning_rate": 1.976798624164416e-05,
      "loss": 0.5636,
      "step": 4567
    },
    {
      "epoch": 0.1403250084477621,
      "grad_norm": 0.31879758834838867,
      "learning_rate": 1.9767882731628095e-05,
      "loss": 0.5702,
      "step": 4568
    },
    {
      "epoch": 0.14035572758271128,
      "grad_norm": 0.357481986284256,
      "learning_rate": 1.9767779198798453e-05,
      "loss": 0.6592,
      "step": 4569
    },
    {
      "epoch": 0.14038644671766043,
      "grad_norm": 0.3008691966533661,
      "learning_rate": 1.9767675643155483e-05,
      "loss": 0.5779,
      "step": 4570
    },
    {
      "epoch": 0.14041716585260958,
      "grad_norm": 0.37102577090263367,
      "learning_rate": 1.9767572064699423e-05,
      "loss": 0.5809,
      "step": 4571
    },
    {
      "epoch": 0.14044788498755875,
      "grad_norm": 0.3227834701538086,
      "learning_rate": 1.976746846343052e-05,
      "loss": 0.5806,
      "step": 4572
    },
    {
      "epoch": 0.1404786041225079,
      "grad_norm": 0.415253609418869,
      "learning_rate": 1.9767364839349005e-05,
      "loss": 0.5917,
      "step": 4573
    },
    {
      "epoch": 0.14050932325745707,
      "grad_norm": 0.4297698438167572,
      "learning_rate": 1.9767261192455135e-05,
      "loss": 0.6662,
      "step": 4574
    },
    {
      "epoch": 0.14054004239240622,
      "grad_norm": 0.3296424448490143,
      "learning_rate": 1.976715752274914e-05,
      "loss": 0.6346,
      "step": 4575
    },
    {
      "epoch": 0.1405707615273554,
      "grad_norm": 0.6424480080604553,
      "learning_rate": 1.9767053830231267e-05,
      "loss": 0.6679,
      "step": 4576
    },
    {
      "epoch": 0.14060148066230455,
      "grad_norm": 0.29943251609802246,
      "learning_rate": 1.976695011490176e-05,
      "loss": 0.5085,
      "step": 4577
    },
    {
      "epoch": 0.14063219979725372,
      "grad_norm": 0.366623193025589,
      "learning_rate": 1.9766846376760856e-05,
      "loss": 0.4722,
      "step": 4578
    },
    {
      "epoch": 0.14066291893220287,
      "grad_norm": 0.43983981013298035,
      "learning_rate": 1.97667426158088e-05,
      "loss": 0.6263,
      "step": 4579
    },
    {
      "epoch": 0.14069363806715202,
      "grad_norm": 0.3393038511276245,
      "learning_rate": 1.9766638832045836e-05,
      "loss": 0.6323,
      "step": 4580
    },
    {
      "epoch": 0.1407243572021012,
      "grad_norm": 0.33187586069107056,
      "learning_rate": 1.9766535025472205e-05,
      "loss": 0.6052,
      "step": 4581
    },
    {
      "epoch": 0.14075507633705034,
      "grad_norm": 0.36592382192611694,
      "learning_rate": 1.976643119608815e-05,
      "loss": 0.6225,
      "step": 4582
    },
    {
      "epoch": 0.14078579547199951,
      "grad_norm": 0.33447325229644775,
      "learning_rate": 1.976632734389391e-05,
      "loss": 0.6835,
      "step": 4583
    },
    {
      "epoch": 0.14081651460694866,
      "grad_norm": 0.3892289102077484,
      "learning_rate": 1.9766223468889735e-05,
      "loss": 0.5897,
      "step": 4584
    },
    {
      "epoch": 0.14084723374189784,
      "grad_norm": 0.347449392080307,
      "learning_rate": 1.976611957107586e-05,
      "loss": 0.5681,
      "step": 4585
    },
    {
      "epoch": 0.14087795287684698,
      "grad_norm": 0.365726113319397,
      "learning_rate": 1.976601565045253e-05,
      "loss": 0.7155,
      "step": 4586
    },
    {
      "epoch": 0.14090867201179616,
      "grad_norm": 0.33018046617507935,
      "learning_rate": 1.976591170701999e-05,
      "loss": 0.583,
      "step": 4587
    },
    {
      "epoch": 0.1409393911467453,
      "grad_norm": 0.35541409254074097,
      "learning_rate": 1.976580774077848e-05,
      "loss": 0.6382,
      "step": 4588
    },
    {
      "epoch": 0.14097011028169446,
      "grad_norm": 0.35583561658859253,
      "learning_rate": 1.9765703751728243e-05,
      "loss": 0.6549,
      "step": 4589
    },
    {
      "epoch": 0.14100082941664363,
      "grad_norm": 0.3433876037597656,
      "learning_rate": 1.9765599739869527e-05,
      "loss": 0.5577,
      "step": 4590
    },
    {
      "epoch": 0.14103154855159278,
      "grad_norm": 0.3556480407714844,
      "learning_rate": 1.9765495705202568e-05,
      "loss": 0.5743,
      "step": 4591
    },
    {
      "epoch": 0.14106226768654195,
      "grad_norm": 0.3611827492713928,
      "learning_rate": 1.9765391647727614e-05,
      "loss": 0.5469,
      "step": 4592
    },
    {
      "epoch": 0.1410929868214911,
      "grad_norm": 0.3313784897327423,
      "learning_rate": 1.97652875674449e-05,
      "loss": 0.6347,
      "step": 4593
    },
    {
      "epoch": 0.14112370595644028,
      "grad_norm": 0.31829962134361267,
      "learning_rate": 1.9765183464354682e-05,
      "loss": 0.5622,
      "step": 4594
    },
    {
      "epoch": 0.14115442509138942,
      "grad_norm": 0.4398695230484009,
      "learning_rate": 1.976507933845719e-05,
      "loss": 0.714,
      "step": 4595
    },
    {
      "epoch": 0.1411851442263386,
      "grad_norm": 0.36936497688293457,
      "learning_rate": 1.9764975189752676e-05,
      "loss": 0.6616,
      "step": 4596
    },
    {
      "epoch": 0.14121586336128775,
      "grad_norm": 0.33705705404281616,
      "learning_rate": 1.976487101824138e-05,
      "loss": 0.6558,
      "step": 4597
    },
    {
      "epoch": 0.1412465824962369,
      "grad_norm": 0.33451902866363525,
      "learning_rate": 1.976476682392355e-05,
      "loss": 0.5721,
      "step": 4598
    },
    {
      "epoch": 0.14127730163118607,
      "grad_norm": 0.34084415435791016,
      "learning_rate": 1.9764662606799418e-05,
      "loss": 0.6292,
      "step": 4599
    },
    {
      "epoch": 0.14130802076613522,
      "grad_norm": 0.3403288424015045,
      "learning_rate": 1.976455836686924e-05,
      "loss": 0.4941,
      "step": 4600
    },
    {
      "epoch": 0.1413387399010844,
      "grad_norm": 0.3132542669773102,
      "learning_rate": 1.976445410413325e-05,
      "loss": 0.6366,
      "step": 4601
    },
    {
      "epoch": 0.14136945903603354,
      "grad_norm": 0.30922624468803406,
      "learning_rate": 1.9764349818591696e-05,
      "loss": 0.6164,
      "step": 4602
    },
    {
      "epoch": 0.14140017817098272,
      "grad_norm": 0.3108746409416199,
      "learning_rate": 1.9764245510244824e-05,
      "loss": 0.561,
      "step": 4603
    },
    {
      "epoch": 0.14143089730593186,
      "grad_norm": 0.36575958132743835,
      "learning_rate": 1.9764141179092874e-05,
      "loss": 0.6454,
      "step": 4604
    },
    {
      "epoch": 0.14146161644088104,
      "grad_norm": 0.3063628673553467,
      "learning_rate": 1.976403682513609e-05,
      "loss": 0.5578,
      "step": 4605
    },
    {
      "epoch": 0.14149233557583019,
      "grad_norm": 0.35037150979042053,
      "learning_rate": 1.9763932448374715e-05,
      "loss": 0.6107,
      "step": 4606
    },
    {
      "epoch": 0.14152305471077933,
      "grad_norm": 0.3389579951763153,
      "learning_rate": 1.976382804880899e-05,
      "loss": 0.5963,
      "step": 4607
    },
    {
      "epoch": 0.1415537738457285,
      "grad_norm": 0.31780222058296204,
      "learning_rate": 1.976372362643917e-05,
      "loss": 0.6054,
      "step": 4608
    },
    {
      "epoch": 0.14158449298067766,
      "grad_norm": 0.39146894216537476,
      "learning_rate": 1.976361918126549e-05,
      "loss": 0.5478,
      "step": 4609
    },
    {
      "epoch": 0.14161521211562683,
      "grad_norm": 0.3472498059272766,
      "learning_rate": 1.9763514713288193e-05,
      "loss": 0.5813,
      "step": 4610
    },
    {
      "epoch": 0.14164593125057598,
      "grad_norm": 0.34898099303245544,
      "learning_rate": 1.9763410222507527e-05,
      "loss": 0.6486,
      "step": 4611
    },
    {
      "epoch": 0.14167665038552515,
      "grad_norm": 0.3310079276561737,
      "learning_rate": 1.9763305708923735e-05,
      "loss": 0.5921,
      "step": 4612
    },
    {
      "epoch": 0.1417073695204743,
      "grad_norm": 0.32489585876464844,
      "learning_rate": 1.9763201172537057e-05,
      "loss": 0.5924,
      "step": 4613
    },
    {
      "epoch": 0.14173808865542345,
      "grad_norm": 0.6517223715782166,
      "learning_rate": 1.9763096613347744e-05,
      "loss": 0.6533,
      "step": 4614
    },
    {
      "epoch": 0.14176880779037263,
      "grad_norm": 0.34020447731018066,
      "learning_rate": 1.9762992031356037e-05,
      "loss": 0.6598,
      "step": 4615
    },
    {
      "epoch": 0.14179952692532177,
      "grad_norm": 0.4258897006511688,
      "learning_rate": 1.9762887426562182e-05,
      "loss": 0.4998,
      "step": 4616
    },
    {
      "epoch": 0.14183024606027095,
      "grad_norm": 0.32480961084365845,
      "learning_rate": 1.9762782798966417e-05,
      "loss": 0.6019,
      "step": 4617
    },
    {
      "epoch": 0.1418609651952201,
      "grad_norm": 0.3252837359905243,
      "learning_rate": 1.9762678148568996e-05,
      "loss": 0.6327,
      "step": 4618
    },
    {
      "epoch": 0.14189168433016927,
      "grad_norm": 0.3650161325931549,
      "learning_rate": 1.9762573475370156e-05,
      "loss": 0.6141,
      "step": 4619
    },
    {
      "epoch": 0.14192240346511842,
      "grad_norm": 0.29841071367263794,
      "learning_rate": 1.976246877937014e-05,
      "loss": 0.527,
      "step": 4620
    },
    {
      "epoch": 0.1419531226000676,
      "grad_norm": 0.31855303049087524,
      "learning_rate": 1.9762364060569202e-05,
      "loss": 0.5493,
      "step": 4621
    },
    {
      "epoch": 0.14198384173501674,
      "grad_norm": 0.3496769964694977,
      "learning_rate": 1.976225931896758e-05,
      "loss": 0.6515,
      "step": 4622
    },
    {
      "epoch": 0.1420145608699659,
      "grad_norm": 0.35953453183174133,
      "learning_rate": 1.9762154554565518e-05,
      "loss": 0.6489,
      "step": 4623
    },
    {
      "epoch": 0.14204528000491506,
      "grad_norm": 0.3501867353916168,
      "learning_rate": 1.9762049767363263e-05,
      "loss": 0.6187,
      "step": 4624
    },
    {
      "epoch": 0.1420759991398642,
      "grad_norm": 0.4211646020412445,
      "learning_rate": 1.976194495736106e-05,
      "loss": 0.6369,
      "step": 4625
    },
    {
      "epoch": 0.1421067182748134,
      "grad_norm": 0.3481685519218445,
      "learning_rate": 1.976184012455915e-05,
      "loss": 0.5147,
      "step": 4626
    },
    {
      "epoch": 0.14213743740976253,
      "grad_norm": 0.3003503382205963,
      "learning_rate": 1.9761735268957782e-05,
      "loss": 0.5133,
      "step": 4627
    },
    {
      "epoch": 0.1421681565447117,
      "grad_norm": 0.3711954951286316,
      "learning_rate": 1.97616303905572e-05,
      "loss": 0.7272,
      "step": 4628
    },
    {
      "epoch": 0.14219887567966086,
      "grad_norm": 0.35885030031204224,
      "learning_rate": 1.9761525489357648e-05,
      "loss": 0.6079,
      "step": 4629
    },
    {
      "epoch": 0.14222959481461003,
      "grad_norm": 0.3178861737251282,
      "learning_rate": 1.9761420565359373e-05,
      "loss": 0.7056,
      "step": 4630
    },
    {
      "epoch": 0.14226031394955918,
      "grad_norm": 0.3245752453804016,
      "learning_rate": 1.9761315618562616e-05,
      "loss": 0.5439,
      "step": 4631
    },
    {
      "epoch": 0.14229103308450833,
      "grad_norm": 0.3200641870498657,
      "learning_rate": 1.9761210648967625e-05,
      "loss": 0.6018,
      "step": 4632
    },
    {
      "epoch": 0.1423217522194575,
      "grad_norm": 0.322952538728714,
      "learning_rate": 1.9761105656574648e-05,
      "loss": 0.6473,
      "step": 4633
    },
    {
      "epoch": 0.14235247135440665,
      "grad_norm": 0.39527618885040283,
      "learning_rate": 1.976100064138392e-05,
      "loss": 0.5723,
      "step": 4634
    },
    {
      "epoch": 0.14238319048935583,
      "grad_norm": 0.337991863489151,
      "learning_rate": 1.97608956033957e-05,
      "loss": 0.5522,
      "step": 4635
    },
    {
      "epoch": 0.14241390962430497,
      "grad_norm": 0.331394761800766,
      "learning_rate": 1.9760790542610226e-05,
      "loss": 0.6291,
      "step": 4636
    },
    {
      "epoch": 0.14244462875925415,
      "grad_norm": 0.31188562512397766,
      "learning_rate": 1.9760685459027745e-05,
      "loss": 0.6263,
      "step": 4637
    },
    {
      "epoch": 0.1424753478942033,
      "grad_norm": 0.4178604483604431,
      "learning_rate": 1.9760580352648497e-05,
      "loss": 0.6213,
      "step": 4638
    },
    {
      "epoch": 0.14250606702915247,
      "grad_norm": 0.3328765630722046,
      "learning_rate": 1.9760475223472736e-05,
      "loss": 0.6535,
      "step": 4639
    },
    {
      "epoch": 0.14253678616410162,
      "grad_norm": 0.6867932081222534,
      "learning_rate": 1.97603700715007e-05,
      "loss": 0.6237,
      "step": 4640
    },
    {
      "epoch": 0.14256750529905077,
      "grad_norm": 0.33283907175064087,
      "learning_rate": 1.976026489673264e-05,
      "loss": 0.5981,
      "step": 4641
    },
    {
      "epoch": 0.14259822443399994,
      "grad_norm": 0.3323231041431427,
      "learning_rate": 1.9760159699168796e-05,
      "loss": 0.6419,
      "step": 4642
    },
    {
      "epoch": 0.1426289435689491,
      "grad_norm": 0.30864855647087097,
      "learning_rate": 1.9760054478809424e-05,
      "loss": 0.5704,
      "step": 4643
    },
    {
      "epoch": 0.14265966270389827,
      "grad_norm": 0.3363948464393616,
      "learning_rate": 1.975994923565476e-05,
      "loss": 0.6301,
      "step": 4644
    },
    {
      "epoch": 0.1426903818388474,
      "grad_norm": 0.5032851099967957,
      "learning_rate": 1.975984396970505e-05,
      "loss": 0.5094,
      "step": 4645
    },
    {
      "epoch": 0.1427211009737966,
      "grad_norm": 0.43959033489227295,
      "learning_rate": 1.9759738680960544e-05,
      "loss": 0.6279,
      "step": 4646
    },
    {
      "epoch": 0.14275182010874574,
      "grad_norm": 0.35765501856803894,
      "learning_rate": 1.975963336942149e-05,
      "loss": 0.5976,
      "step": 4647
    },
    {
      "epoch": 0.14278253924369488,
      "grad_norm": 0.3533529043197632,
      "learning_rate": 1.975952803508813e-05,
      "loss": 0.6244,
      "step": 4648
    },
    {
      "epoch": 0.14281325837864406,
      "grad_norm": 0.35788679122924805,
      "learning_rate": 1.9759422677960708e-05,
      "loss": 0.561,
      "step": 4649
    },
    {
      "epoch": 0.1428439775135932,
      "grad_norm": 0.3286505341529846,
      "learning_rate": 1.9759317298039475e-05,
      "loss": 0.585,
      "step": 4650
    },
    {
      "epoch": 0.14287469664854238,
      "grad_norm": 0.32490217685699463,
      "learning_rate": 1.9759211895324676e-05,
      "loss": 0.504,
      "step": 4651
    },
    {
      "epoch": 0.14290541578349153,
      "grad_norm": 0.3487645387649536,
      "learning_rate": 1.9759106469816553e-05,
      "loss": 0.5937,
      "step": 4652
    },
    {
      "epoch": 0.1429361349184407,
      "grad_norm": 0.37234926223754883,
      "learning_rate": 1.9759001021515356e-05,
      "loss": 0.6518,
      "step": 4653
    },
    {
      "epoch": 0.14296685405338985,
      "grad_norm": 0.3207632303237915,
      "learning_rate": 1.975889555042133e-05,
      "loss": 0.5604,
      "step": 4654
    },
    {
      "epoch": 0.14299757318833903,
      "grad_norm": 0.41666457056999207,
      "learning_rate": 1.9758790056534723e-05,
      "loss": 0.5472,
      "step": 4655
    },
    {
      "epoch": 0.14302829232328818,
      "grad_norm": 0.34735989570617676,
      "learning_rate": 1.9758684539855782e-05,
      "loss": 0.6056,
      "step": 4656
    },
    {
      "epoch": 0.14305901145823732,
      "grad_norm": 0.31800127029418945,
      "learning_rate": 1.975857900038475e-05,
      "loss": 0.536,
      "step": 4657
    },
    {
      "epoch": 0.1430897305931865,
      "grad_norm": 0.33600714802742004,
      "learning_rate": 1.9758473438121873e-05,
      "loss": 0.642,
      "step": 4658
    },
    {
      "epoch": 0.14312044972813565,
      "grad_norm": 0.3376256227493286,
      "learning_rate": 1.9758367853067403e-05,
      "loss": 0.5418,
      "step": 4659
    },
    {
      "epoch": 0.14315116886308482,
      "grad_norm": 0.3366561532020569,
      "learning_rate": 1.975826224522158e-05,
      "loss": 0.6113,
      "step": 4660
    },
    {
      "epoch": 0.14318188799803397,
      "grad_norm": 0.4281092584133148,
      "learning_rate": 1.975815661458466e-05,
      "loss": 0.769,
      "step": 4661
    },
    {
      "epoch": 0.14321260713298314,
      "grad_norm": 0.34296301007270813,
      "learning_rate": 1.9758050961156877e-05,
      "loss": 0.5739,
      "step": 4662
    },
    {
      "epoch": 0.1432433262679323,
      "grad_norm": 0.3517555594444275,
      "learning_rate": 1.9757945284938488e-05,
      "loss": 0.6235,
      "step": 4663
    },
    {
      "epoch": 0.14327404540288147,
      "grad_norm": 0.49167194962501526,
      "learning_rate": 1.9757839585929735e-05,
      "loss": 0.5019,
      "step": 4664
    },
    {
      "epoch": 0.14330476453783061,
      "grad_norm": 0.3296694755554199,
      "learning_rate": 1.975773386413087e-05,
      "loss": 0.5945,
      "step": 4665
    },
    {
      "epoch": 0.14333548367277976,
      "grad_norm": 0.34413063526153564,
      "learning_rate": 1.9757628119542128e-05,
      "loss": 0.6177,
      "step": 4666
    },
    {
      "epoch": 0.14336620280772894,
      "grad_norm": 0.365961492061615,
      "learning_rate": 1.9757522352163772e-05,
      "loss": 0.5811,
      "step": 4667
    },
    {
      "epoch": 0.14339692194267809,
      "grad_norm": 0.3144555687904358,
      "learning_rate": 1.975741656199604e-05,
      "loss": 0.5593,
      "step": 4668
    },
    {
      "epoch": 0.14342764107762726,
      "grad_norm": 0.3517237901687622,
      "learning_rate": 1.9757310749039176e-05,
      "loss": 0.6119,
      "step": 4669
    },
    {
      "epoch": 0.1434583602125764,
      "grad_norm": 0.3399091958999634,
      "learning_rate": 1.9757204913293437e-05,
      "loss": 0.6032,
      "step": 4670
    },
    {
      "epoch": 0.14348907934752558,
      "grad_norm": 0.3615288734436035,
      "learning_rate": 1.9757099054759055e-05,
      "loss": 0.6092,
      "step": 4671
    },
    {
      "epoch": 0.14351979848247473,
      "grad_norm": 0.35799551010131836,
      "learning_rate": 1.9756993173436293e-05,
      "loss": 0.5749,
      "step": 4672
    },
    {
      "epoch": 0.1435505176174239,
      "grad_norm": 0.3326537013053894,
      "learning_rate": 1.9756887269325396e-05,
      "loss": 0.6497,
      "step": 4673
    },
    {
      "epoch": 0.14358123675237305,
      "grad_norm": 0.3433857262134552,
      "learning_rate": 1.97567813424266e-05,
      "loss": 0.6893,
      "step": 4674
    },
    {
      "epoch": 0.1436119558873222,
      "grad_norm": 0.3642665147781372,
      "learning_rate": 1.9756675392740163e-05,
      "loss": 0.5315,
      "step": 4675
    },
    {
      "epoch": 0.14364267502227138,
      "grad_norm": 0.3321240246295929,
      "learning_rate": 1.9756569420266332e-05,
      "loss": 0.5385,
      "step": 4676
    },
    {
      "epoch": 0.14367339415722052,
      "grad_norm": 0.3875254690647125,
      "learning_rate": 1.975646342500535e-05,
      "loss": 0.5856,
      "step": 4677
    },
    {
      "epoch": 0.1437041132921697,
      "grad_norm": 0.4049750566482544,
      "learning_rate": 1.9756357406957462e-05,
      "loss": 0.5636,
      "step": 4678
    },
    {
      "epoch": 0.14373483242711885,
      "grad_norm": 0.3466750383377075,
      "learning_rate": 1.9756251366122922e-05,
      "loss": 0.6623,
      "step": 4679
    },
    {
      "epoch": 0.14376555156206802,
      "grad_norm": 0.3469845652580261,
      "learning_rate": 1.975614530250198e-05,
      "loss": 0.6359,
      "step": 4680
    },
    {
      "epoch": 0.14379627069701717,
      "grad_norm": 0.36168989539146423,
      "learning_rate": 1.9756039216094875e-05,
      "loss": 0.559,
      "step": 4681
    },
    {
      "epoch": 0.14382698983196635,
      "grad_norm": 0.3183254897594452,
      "learning_rate": 1.9755933106901862e-05,
      "loss": 0.5714,
      "step": 4682
    },
    {
      "epoch": 0.1438577089669155,
      "grad_norm": 0.3528538644313812,
      "learning_rate": 1.975582697492318e-05,
      "loss": 0.6396,
      "step": 4683
    },
    {
      "epoch": 0.14388842810186464,
      "grad_norm": 0.40475693345069885,
      "learning_rate": 1.9755720820159088e-05,
      "loss": 0.5738,
      "step": 4684
    },
    {
      "epoch": 0.14391914723681382,
      "grad_norm": 0.3381171226501465,
      "learning_rate": 1.9755614642609825e-05,
      "loss": 0.4941,
      "step": 4685
    },
    {
      "epoch": 0.14394986637176296,
      "grad_norm": 0.33059805631637573,
      "learning_rate": 1.9755508442275647e-05,
      "loss": 0.604,
      "step": 4686
    },
    {
      "epoch": 0.14398058550671214,
      "grad_norm": 0.35356342792510986,
      "learning_rate": 1.9755402219156795e-05,
      "loss": 0.6365,
      "step": 4687
    },
    {
      "epoch": 0.1440113046416613,
      "grad_norm": 0.3379509150981903,
      "learning_rate": 1.9755295973253525e-05,
      "loss": 0.6089,
      "step": 4688
    },
    {
      "epoch": 0.14404202377661046,
      "grad_norm": 0.3202090561389923,
      "learning_rate": 1.9755189704566075e-05,
      "loss": 0.6272,
      "step": 4689
    },
    {
      "epoch": 0.1440727429115596,
      "grad_norm": 0.34496811032295227,
      "learning_rate": 1.9755083413094696e-05,
      "loss": 0.6063,
      "step": 4690
    },
    {
      "epoch": 0.14410346204650876,
      "grad_norm": 0.31163814663887024,
      "learning_rate": 1.975497709883964e-05,
      "loss": 0.5785,
      "step": 4691
    },
    {
      "epoch": 0.14413418118145793,
      "grad_norm": 0.4002324938774109,
      "learning_rate": 1.9754870761801156e-05,
      "loss": 0.6551,
      "step": 4692
    },
    {
      "epoch": 0.14416490031640708,
      "grad_norm": 0.29813864827156067,
      "learning_rate": 1.975476440197949e-05,
      "loss": 0.4966,
      "step": 4693
    },
    {
      "epoch": 0.14419561945135626,
      "grad_norm": 0.5003029704093933,
      "learning_rate": 1.9754658019374887e-05,
      "loss": 0.5978,
      "step": 4694
    },
    {
      "epoch": 0.1442263385863054,
      "grad_norm": 0.3628714382648468,
      "learning_rate": 1.9754551613987602e-05,
      "loss": 0.6787,
      "step": 4695
    },
    {
      "epoch": 0.14425705772125458,
      "grad_norm": 0.352323055267334,
      "learning_rate": 1.9754445185817878e-05,
      "loss": 0.6049,
      "step": 4696
    },
    {
      "epoch": 0.14428777685620373,
      "grad_norm": 0.366977334022522,
      "learning_rate": 1.975433873486597e-05,
      "loss": 0.628,
      "step": 4697
    },
    {
      "epoch": 0.1443184959911529,
      "grad_norm": 0.4657941162586212,
      "learning_rate": 1.975423226113212e-05,
      "loss": 0.5991,
      "step": 4698
    },
    {
      "epoch": 0.14434921512610205,
      "grad_norm": 0.35605621337890625,
      "learning_rate": 1.975412576461658e-05,
      "loss": 0.6437,
      "step": 4699
    },
    {
      "epoch": 0.1443799342610512,
      "grad_norm": 0.3364267647266388,
      "learning_rate": 1.97540192453196e-05,
      "loss": 0.5956,
      "step": 4700
    },
    {
      "epoch": 0.14441065339600037,
      "grad_norm": 0.3643955886363983,
      "learning_rate": 1.9753912703241424e-05,
      "loss": 0.6613,
      "step": 4701
    },
    {
      "epoch": 0.14444137253094952,
      "grad_norm": 0.36045223474502563,
      "learning_rate": 1.97538061383823e-05,
      "loss": 0.5413,
      "step": 4702
    },
    {
      "epoch": 0.1444720916658987,
      "grad_norm": 0.376110702753067,
      "learning_rate": 1.9753699550742487e-05,
      "loss": 0.6092,
      "step": 4703
    },
    {
      "epoch": 0.14450281080084784,
      "grad_norm": 0.3623325228691101,
      "learning_rate": 1.9753592940322227e-05,
      "loss": 0.5848,
      "step": 4704
    },
    {
      "epoch": 0.14453352993579702,
      "grad_norm": 0.35809409618377686,
      "learning_rate": 1.9753486307121768e-05,
      "loss": 0.6458,
      "step": 4705
    },
    {
      "epoch": 0.14456424907074616,
      "grad_norm": 0.34744828939437866,
      "learning_rate": 1.975337965114136e-05,
      "loss": 0.6586,
      "step": 4706
    },
    {
      "epoch": 0.14459496820569534,
      "grad_norm": 0.38858652114868164,
      "learning_rate": 1.9753272972381253e-05,
      "loss": 0.586,
      "step": 4707
    },
    {
      "epoch": 0.1446256873406445,
      "grad_norm": 0.3550422489643097,
      "learning_rate": 1.9753166270841695e-05,
      "loss": 0.5197,
      "step": 4708
    },
    {
      "epoch": 0.14465640647559364,
      "grad_norm": 0.42899903655052185,
      "learning_rate": 1.9753059546522937e-05,
      "loss": 0.5903,
      "step": 4709
    },
    {
      "epoch": 0.1446871256105428,
      "grad_norm": 0.30753591656684875,
      "learning_rate": 1.9752952799425227e-05,
      "loss": 0.5174,
      "step": 4710
    },
    {
      "epoch": 0.14471784474549196,
      "grad_norm": 0.3572216331958771,
      "learning_rate": 1.9752846029548816e-05,
      "loss": 0.6057,
      "step": 4711
    },
    {
      "epoch": 0.14474856388044113,
      "grad_norm": 0.32215389609336853,
      "learning_rate": 1.975273923689395e-05,
      "loss": 0.5788,
      "step": 4712
    },
    {
      "epoch": 0.14477928301539028,
      "grad_norm": 0.31658607721328735,
      "learning_rate": 1.975263242146088e-05,
      "loss": 0.6641,
      "step": 4713
    },
    {
      "epoch": 0.14481000215033946,
      "grad_norm": 0.33361199498176575,
      "learning_rate": 1.9752525583249858e-05,
      "loss": 0.6225,
      "step": 4714
    },
    {
      "epoch": 0.1448407212852886,
      "grad_norm": 0.329679012298584,
      "learning_rate": 1.975241872226113e-05,
      "loss": 0.6208,
      "step": 4715
    },
    {
      "epoch": 0.14487144042023778,
      "grad_norm": 0.3380034267902374,
      "learning_rate": 1.9752311838494947e-05,
      "loss": 0.6643,
      "step": 4716
    },
    {
      "epoch": 0.14490215955518693,
      "grad_norm": 0.3397764265537262,
      "learning_rate": 1.975220493195156e-05,
      "loss": 0.6701,
      "step": 4717
    },
    {
      "epoch": 0.14493287869013607,
      "grad_norm": 0.36223381757736206,
      "learning_rate": 1.9752098002631214e-05,
      "loss": 0.6128,
      "step": 4718
    },
    {
      "epoch": 0.14496359782508525,
      "grad_norm": 0.37036824226379395,
      "learning_rate": 1.9751991050534164e-05,
      "loss": 0.5787,
      "step": 4719
    },
    {
      "epoch": 0.1449943169600344,
      "grad_norm": 0.3545697331428528,
      "learning_rate": 1.975188407566066e-05,
      "loss": 0.5512,
      "step": 4720
    },
    {
      "epoch": 0.14502503609498357,
      "grad_norm": 0.3577895760536194,
      "learning_rate": 1.975177707801095e-05,
      "loss": 0.5072,
      "step": 4721
    },
    {
      "epoch": 0.14505575522993272,
      "grad_norm": 0.3444124758243561,
      "learning_rate": 1.9751670057585278e-05,
      "loss": 0.5157,
      "step": 4722
    },
    {
      "epoch": 0.1450864743648819,
      "grad_norm": 0.3379819989204407,
      "learning_rate": 1.9751563014383905e-05,
      "loss": 0.6145,
      "step": 4723
    },
    {
      "epoch": 0.14511719349983104,
      "grad_norm": 0.32723814249038696,
      "learning_rate": 1.9751455948407073e-05,
      "loss": 0.5407,
      "step": 4724
    },
    {
      "epoch": 0.14514791263478022,
      "grad_norm": 0.3471226096153259,
      "learning_rate": 1.9751348859655036e-05,
      "loss": 0.5213,
      "step": 4725
    },
    {
      "epoch": 0.14517863176972937,
      "grad_norm": 0.3105807304382324,
      "learning_rate": 1.975124174812804e-05,
      "loss": 0.5027,
      "step": 4726
    },
    {
      "epoch": 0.1452093509046785,
      "grad_norm": 0.34118297696113586,
      "learning_rate": 1.975113461382634e-05,
      "loss": 0.6623,
      "step": 4727
    },
    {
      "epoch": 0.1452400700396277,
      "grad_norm": 0.32293620705604553,
      "learning_rate": 1.9751027456750186e-05,
      "loss": 0.5236,
      "step": 4728
    },
    {
      "epoch": 0.14527078917457684,
      "grad_norm": 0.33103328943252563,
      "learning_rate": 1.975092027689982e-05,
      "loss": 0.6646,
      "step": 4729
    },
    {
      "epoch": 0.145301508309526,
      "grad_norm": 0.3426695466041565,
      "learning_rate": 1.9750813074275506e-05,
      "loss": 0.5524,
      "step": 4730
    },
    {
      "epoch": 0.14533222744447516,
      "grad_norm": 0.3151072561740875,
      "learning_rate": 1.9750705848877484e-05,
      "loss": 0.5938,
      "step": 4731
    },
    {
      "epoch": 0.14536294657942433,
      "grad_norm": 0.4840388000011444,
      "learning_rate": 1.9750598600706006e-05,
      "loss": 0.5666,
      "step": 4732
    },
    {
      "epoch": 0.14539366571437348,
      "grad_norm": 0.36896973848342896,
      "learning_rate": 1.9750491329761323e-05,
      "loss": 0.4947,
      "step": 4733
    },
    {
      "epoch": 0.14542438484932263,
      "grad_norm": 0.3303647041320801,
      "learning_rate": 1.975038403604369e-05,
      "loss": 0.6568,
      "step": 4734
    },
    {
      "epoch": 0.1454551039842718,
      "grad_norm": 0.31108859181404114,
      "learning_rate": 1.9750276719553354e-05,
      "loss": 0.5143,
      "step": 4735
    },
    {
      "epoch": 0.14548582311922095,
      "grad_norm": 0.30921560525894165,
      "learning_rate": 1.9750169380290564e-05,
      "loss": 0.5197,
      "step": 4736
    },
    {
      "epoch": 0.14551654225417013,
      "grad_norm": 0.30200105905532837,
      "learning_rate": 1.9750062018255574e-05,
      "loss": 0.5763,
      "step": 4737
    },
    {
      "epoch": 0.14554726138911928,
      "grad_norm": 0.3989561200141907,
      "learning_rate": 1.9749954633448633e-05,
      "loss": 0.6312,
      "step": 4738
    },
    {
      "epoch": 0.14557798052406845,
      "grad_norm": 0.3365642726421356,
      "learning_rate": 1.974984722586999e-05,
      "loss": 0.6452,
      "step": 4739
    },
    {
      "epoch": 0.1456086996590176,
      "grad_norm": 0.4408011734485626,
      "learning_rate": 1.9749739795519898e-05,
      "loss": 0.6171,
      "step": 4740
    },
    {
      "epoch": 0.14563941879396677,
      "grad_norm": 0.38660791516304016,
      "learning_rate": 1.9749632342398614e-05,
      "loss": 0.698,
      "step": 4741
    },
    {
      "epoch": 0.14567013792891592,
      "grad_norm": 0.33004090189933777,
      "learning_rate": 1.9749524866506374e-05,
      "loss": 0.5913,
      "step": 4742
    },
    {
      "epoch": 0.14570085706386507,
      "grad_norm": 0.4109882414340973,
      "learning_rate": 1.9749417367843442e-05,
      "loss": 0.6664,
      "step": 4743
    },
    {
      "epoch": 0.14573157619881424,
      "grad_norm": 0.3226583003997803,
      "learning_rate": 1.9749309846410065e-05,
      "loss": 0.5147,
      "step": 4744
    },
    {
      "epoch": 0.1457622953337634,
      "grad_norm": 0.301925390958786,
      "learning_rate": 1.9749202302206495e-05,
      "loss": 0.6203,
      "step": 4745
    },
    {
      "epoch": 0.14579301446871257,
      "grad_norm": 0.35408687591552734,
      "learning_rate": 1.9749094735232978e-05,
      "loss": 0.628,
      "step": 4746
    },
    {
      "epoch": 0.14582373360366171,
      "grad_norm": 0.3453104794025421,
      "learning_rate": 1.9748987145489775e-05,
      "loss": 0.6129,
      "step": 4747
    },
    {
      "epoch": 0.1458544527386109,
      "grad_norm": 0.3457273542881012,
      "learning_rate": 1.9748879532977128e-05,
      "loss": 0.5701,
      "step": 4748
    },
    {
      "epoch": 0.14588517187356004,
      "grad_norm": 0.3396053612232208,
      "learning_rate": 1.9748771897695293e-05,
      "loss": 0.6165,
      "step": 4749
    },
    {
      "epoch": 0.1459158910085092,
      "grad_norm": 0.34996071457862854,
      "learning_rate": 1.974866423964452e-05,
      "loss": 0.5614,
      "step": 4750
    },
    {
      "epoch": 0.14594661014345836,
      "grad_norm": 0.37351852655410767,
      "learning_rate": 1.974855655882506e-05,
      "loss": 0.5961,
      "step": 4751
    },
    {
      "epoch": 0.1459773292784075,
      "grad_norm": 0.380794495344162,
      "learning_rate": 1.9748448855237166e-05,
      "loss": 0.6045,
      "step": 4752
    },
    {
      "epoch": 0.14600804841335668,
      "grad_norm": 0.33946162462234497,
      "learning_rate": 1.974834112888109e-05,
      "loss": 0.5526,
      "step": 4753
    },
    {
      "epoch": 0.14603876754830583,
      "grad_norm": 0.33703482151031494,
      "learning_rate": 1.9748233379757083e-05,
      "loss": 0.6197,
      "step": 4754
    },
    {
      "epoch": 0.146069486683255,
      "grad_norm": 0.38042330741882324,
      "learning_rate": 1.974812560786539e-05,
      "loss": 0.6081,
      "step": 4755
    },
    {
      "epoch": 0.14610020581820415,
      "grad_norm": 0.34174180030822754,
      "learning_rate": 1.9748017813206278e-05,
      "loss": 0.6014,
      "step": 4756
    },
    {
      "epoch": 0.14613092495315333,
      "grad_norm": 0.34008848667144775,
      "learning_rate": 1.9747909995779982e-05,
      "loss": 0.5767,
      "step": 4757
    },
    {
      "epoch": 0.14616164408810248,
      "grad_norm": 0.3304292857646942,
      "learning_rate": 1.9747802155586765e-05,
      "loss": 0.607,
      "step": 4758
    },
    {
      "epoch": 0.14619236322305165,
      "grad_norm": 0.34929358959198,
      "learning_rate": 1.9747694292626875e-05,
      "loss": 0.5612,
      "step": 4759
    },
    {
      "epoch": 0.1462230823580008,
      "grad_norm": 0.3347609043121338,
      "learning_rate": 1.9747586406900566e-05,
      "loss": 0.5953,
      "step": 4760
    },
    {
      "epoch": 0.14625380149294995,
      "grad_norm": 0.34422579407691956,
      "learning_rate": 1.9747478498408084e-05,
      "loss": 0.7034,
      "step": 4761
    },
    {
      "epoch": 0.14628452062789912,
      "grad_norm": 0.3285083770751953,
      "learning_rate": 1.974737056714969e-05,
      "loss": 0.5626,
      "step": 4762
    },
    {
      "epoch": 0.14631523976284827,
      "grad_norm": 0.3443434238433838,
      "learning_rate": 1.9747262613125628e-05,
      "loss": 0.5659,
      "step": 4763
    },
    {
      "epoch": 0.14634595889779745,
      "grad_norm": 0.32857251167297363,
      "learning_rate": 1.9747154636336155e-05,
      "loss": 0.6223,
      "step": 4764
    },
    {
      "epoch": 0.1463766780327466,
      "grad_norm": 0.36288875341415405,
      "learning_rate": 1.9747046636781523e-05,
      "loss": 0.5472,
      "step": 4765
    },
    {
      "epoch": 0.14640739716769577,
      "grad_norm": 0.38822874426841736,
      "learning_rate": 1.974693861446198e-05,
      "loss": 0.6164,
      "step": 4766
    },
    {
      "epoch": 0.14643811630264492,
      "grad_norm": 0.34167730808258057,
      "learning_rate": 1.974683056937778e-05,
      "loss": 0.6123,
      "step": 4767
    },
    {
      "epoch": 0.14646883543759406,
      "grad_norm": 0.33870047330856323,
      "learning_rate": 1.974672250152918e-05,
      "loss": 0.5584,
      "step": 4768
    },
    {
      "epoch": 0.14649955457254324,
      "grad_norm": 0.34765103459358215,
      "learning_rate": 1.9746614410916425e-05,
      "loss": 0.5691,
      "step": 4769
    },
    {
      "epoch": 0.1465302737074924,
      "grad_norm": 0.28892984986305237,
      "learning_rate": 1.9746506297539775e-05,
      "loss": 0.5833,
      "step": 4770
    },
    {
      "epoch": 0.14656099284244156,
      "grad_norm": 0.32617899775505066,
      "learning_rate": 1.9746398161399478e-05,
      "loss": 0.6057,
      "step": 4771
    },
    {
      "epoch": 0.1465917119773907,
      "grad_norm": 0.4247855544090271,
      "learning_rate": 1.9746290002495786e-05,
      "loss": 0.6221,
      "step": 4772
    },
    {
      "epoch": 0.14662243111233988,
      "grad_norm": 0.35198086500167847,
      "learning_rate": 1.9746181820828955e-05,
      "loss": 0.5673,
      "step": 4773
    },
    {
      "epoch": 0.14665315024728903,
      "grad_norm": 0.3400936424732208,
      "learning_rate": 1.9746073616399232e-05,
      "loss": 0.5847,
      "step": 4774
    },
    {
      "epoch": 0.1466838693822382,
      "grad_norm": 0.30825960636138916,
      "learning_rate": 1.9745965389206877e-05,
      "loss": 0.6256,
      "step": 4775
    },
    {
      "epoch": 0.14671458851718736,
      "grad_norm": 0.331634521484375,
      "learning_rate": 1.9745857139252138e-05,
      "loss": 0.6003,
      "step": 4776
    },
    {
      "epoch": 0.1467453076521365,
      "grad_norm": 0.30760860443115234,
      "learning_rate": 1.974574886653527e-05,
      "loss": 0.6155,
      "step": 4777
    },
    {
      "epoch": 0.14677602678708568,
      "grad_norm": 0.35115793347358704,
      "learning_rate": 1.9745640571056524e-05,
      "loss": 0.5617,
      "step": 4778
    },
    {
      "epoch": 0.14680674592203483,
      "grad_norm": 0.3482967019081116,
      "learning_rate": 1.9745532252816153e-05,
      "loss": 0.6114,
      "step": 4779
    },
    {
      "epoch": 0.146837465056984,
      "grad_norm": 0.34234291315078735,
      "learning_rate": 1.9745423911814412e-05,
      "loss": 0.5958,
      "step": 4780
    },
    {
      "epoch": 0.14686818419193315,
      "grad_norm": 0.32291436195373535,
      "learning_rate": 1.974531554805155e-05,
      "loss": 0.6199,
      "step": 4781
    },
    {
      "epoch": 0.14689890332688232,
      "grad_norm": 0.34957388043403625,
      "learning_rate": 1.9745207161527826e-05,
      "loss": 0.645,
      "step": 4782
    },
    {
      "epoch": 0.14692962246183147,
      "grad_norm": 0.34600961208343506,
      "learning_rate": 1.974509875224349e-05,
      "loss": 0.6215,
      "step": 4783
    },
    {
      "epoch": 0.14696034159678065,
      "grad_norm": 0.4302138388156891,
      "learning_rate": 1.9744990320198797e-05,
      "loss": 0.7371,
      "step": 4784
    },
    {
      "epoch": 0.1469910607317298,
      "grad_norm": 0.3358970880508423,
      "learning_rate": 1.9744881865393995e-05,
      "loss": 0.623,
      "step": 4785
    },
    {
      "epoch": 0.14702177986667894,
      "grad_norm": 0.31257015466690063,
      "learning_rate": 1.974477338782934e-05,
      "loss": 0.584,
      "step": 4786
    },
    {
      "epoch": 0.14705249900162812,
      "grad_norm": 0.3119466006755829,
      "learning_rate": 1.9744664887505092e-05,
      "loss": 0.6548,
      "step": 4787
    },
    {
      "epoch": 0.14708321813657727,
      "grad_norm": 0.3779031038284302,
      "learning_rate": 1.9744556364421492e-05,
      "loss": 0.6092,
      "step": 4788
    },
    {
      "epoch": 0.14711393727152644,
      "grad_norm": 0.37200111150741577,
      "learning_rate": 1.9744447818578805e-05,
      "loss": 0.5909,
      "step": 4789
    },
    {
      "epoch": 0.1471446564064756,
      "grad_norm": 0.3327055871486664,
      "learning_rate": 1.9744339249977278e-05,
      "loss": 0.5838,
      "step": 4790
    },
    {
      "epoch": 0.14717537554142476,
      "grad_norm": 0.3468448221683502,
      "learning_rate": 1.9744230658617165e-05,
      "loss": 0.6124,
      "step": 4791
    },
    {
      "epoch": 0.1472060946763739,
      "grad_norm": 0.3502403497695923,
      "learning_rate": 1.974412204449872e-05,
      "loss": 0.6174,
      "step": 4792
    },
    {
      "epoch": 0.1472368138113231,
      "grad_norm": 0.3176158368587494,
      "learning_rate": 1.97440134076222e-05,
      "loss": 0.6229,
      "step": 4793
    },
    {
      "epoch": 0.14726753294627223,
      "grad_norm": 0.3774160146713257,
      "learning_rate": 1.9743904747987853e-05,
      "loss": 0.7141,
      "step": 4794
    },
    {
      "epoch": 0.14729825208122138,
      "grad_norm": 0.34015393257141113,
      "learning_rate": 1.974379606559594e-05,
      "loss": 0.6389,
      "step": 4795
    },
    {
      "epoch": 0.14732897121617056,
      "grad_norm": 0.4488866627216339,
      "learning_rate": 1.974368736044671e-05,
      "loss": 0.5891,
      "step": 4796
    },
    {
      "epoch": 0.1473596903511197,
      "grad_norm": 0.336093932390213,
      "learning_rate": 1.9743578632540415e-05,
      "loss": 0.6328,
      "step": 4797
    },
    {
      "epoch": 0.14739040948606888,
      "grad_norm": 0.4007457494735718,
      "learning_rate": 1.9743469881877315e-05,
      "loss": 0.661,
      "step": 4798
    },
    {
      "epoch": 0.14742112862101803,
      "grad_norm": 0.35673320293426514,
      "learning_rate": 1.9743361108457658e-05,
      "loss": 0.5848,
      "step": 4799
    },
    {
      "epoch": 0.1474518477559672,
      "grad_norm": 0.5031554102897644,
      "learning_rate": 1.97432523122817e-05,
      "loss": 0.585,
      "step": 4800
    },
    {
      "epoch": 0.14748256689091635,
      "grad_norm": 0.36293116211891174,
      "learning_rate": 1.9743143493349697e-05,
      "loss": 0.5921,
      "step": 4801
    },
    {
      "epoch": 0.14751328602586553,
      "grad_norm": 0.30360284447669983,
      "learning_rate": 1.9743034651661905e-05,
      "loss": 0.558,
      "step": 4802
    },
    {
      "epoch": 0.14754400516081467,
      "grad_norm": 0.38399043679237366,
      "learning_rate": 1.974292578721857e-05,
      "loss": 0.5604,
      "step": 4803
    },
    {
      "epoch": 0.14757472429576382,
      "grad_norm": 0.3365553319454193,
      "learning_rate": 1.9742816900019954e-05,
      "loss": 0.5896,
      "step": 4804
    },
    {
      "epoch": 0.147605443430713,
      "grad_norm": 0.35880932211875916,
      "learning_rate": 1.974270799006631e-05,
      "loss": 0.5915,
      "step": 4805
    },
    {
      "epoch": 0.14763616256566214,
      "grad_norm": 0.3471909761428833,
      "learning_rate": 1.9742599057357887e-05,
      "loss": 0.5888,
      "step": 4806
    },
    {
      "epoch": 0.14766688170061132,
      "grad_norm": 0.3521879315376282,
      "learning_rate": 1.9742490101894945e-05,
      "loss": 0.6289,
      "step": 4807
    },
    {
      "epoch": 0.14769760083556047,
      "grad_norm": 2.2807838916778564,
      "learning_rate": 1.974238112367774e-05,
      "loss": 0.6294,
      "step": 4808
    },
    {
      "epoch": 0.14772831997050964,
      "grad_norm": 0.33911046385765076,
      "learning_rate": 1.974227212270652e-05,
      "loss": 0.5627,
      "step": 4809
    },
    {
      "epoch": 0.1477590391054588,
      "grad_norm": 0.3293204605579376,
      "learning_rate": 1.9742163098981547e-05,
      "loss": 0.6173,
      "step": 4810
    },
    {
      "epoch": 0.14778975824040794,
      "grad_norm": 0.3551715910434723,
      "learning_rate": 1.974205405250307e-05,
      "loss": 0.6545,
      "step": 4811
    },
    {
      "epoch": 0.1478204773753571,
      "grad_norm": 0.34474244713783264,
      "learning_rate": 1.974194498327134e-05,
      "loss": 0.6563,
      "step": 4812
    },
    {
      "epoch": 0.14785119651030626,
      "grad_norm": 0.3799642324447632,
      "learning_rate": 1.974183589128662e-05,
      "loss": 0.5095,
      "step": 4813
    },
    {
      "epoch": 0.14788191564525544,
      "grad_norm": 0.3548165261745453,
      "learning_rate": 1.9741726776549166e-05,
      "loss": 0.6373,
      "step": 4814
    },
    {
      "epoch": 0.14791263478020458,
      "grad_norm": 0.30076438188552856,
      "learning_rate": 1.9741617639059227e-05,
      "loss": 0.546,
      "step": 4815
    },
    {
      "epoch": 0.14794335391515376,
      "grad_norm": 0.3394749164581299,
      "learning_rate": 1.974150847881706e-05,
      "loss": 0.5952,
      "step": 4816
    },
    {
      "epoch": 0.1479740730501029,
      "grad_norm": 0.4098278880119324,
      "learning_rate": 1.9741399295822917e-05,
      "loss": 0.6344,
      "step": 4817
    },
    {
      "epoch": 0.14800479218505208,
      "grad_norm": 0.34193432331085205,
      "learning_rate": 1.9741290090077058e-05,
      "loss": 0.5785,
      "step": 4818
    },
    {
      "epoch": 0.14803551132000123,
      "grad_norm": 0.36692535877227783,
      "learning_rate": 1.9741180861579734e-05,
      "loss": 0.5973,
      "step": 4819
    },
    {
      "epoch": 0.14806623045495038,
      "grad_norm": 0.3485074043273926,
      "learning_rate": 1.9741071610331203e-05,
      "loss": 0.5421,
      "step": 4820
    },
    {
      "epoch": 0.14809694958989955,
      "grad_norm": 0.37052252888679504,
      "learning_rate": 1.974096233633172e-05,
      "loss": 0.651,
      "step": 4821
    },
    {
      "epoch": 0.1481276687248487,
      "grad_norm": 0.3533651828765869,
      "learning_rate": 1.9740853039581535e-05,
      "loss": 0.6351,
      "step": 4822
    },
    {
      "epoch": 0.14815838785979787,
      "grad_norm": 0.3772926330566406,
      "learning_rate": 1.974074372008091e-05,
      "loss": 0.6659,
      "step": 4823
    },
    {
      "epoch": 0.14818910699474702,
      "grad_norm": 0.6057236194610596,
      "learning_rate": 1.97406343778301e-05,
      "loss": 0.5891,
      "step": 4824
    },
    {
      "epoch": 0.1482198261296962,
      "grad_norm": 0.3263765573501587,
      "learning_rate": 1.9740525012829354e-05,
      "loss": 0.6219,
      "step": 4825
    },
    {
      "epoch": 0.14825054526464534,
      "grad_norm": 0.3561840057373047,
      "learning_rate": 1.9740415625078933e-05,
      "loss": 0.5654,
      "step": 4826
    },
    {
      "epoch": 0.14828126439959452,
      "grad_norm": 0.3668535351753235,
      "learning_rate": 1.974030621457909e-05,
      "loss": 0.616,
      "step": 4827
    },
    {
      "epoch": 0.14831198353454367,
      "grad_norm": 0.3572273254394531,
      "learning_rate": 1.974019678133009e-05,
      "loss": 0.6474,
      "step": 4828
    },
    {
      "epoch": 0.14834270266949282,
      "grad_norm": 0.5557000041007996,
      "learning_rate": 1.974008732533217e-05,
      "loss": 0.5906,
      "step": 4829
    },
    {
      "epoch": 0.148373421804442,
      "grad_norm": 0.3393394649028778,
      "learning_rate": 1.97399778465856e-05,
      "loss": 0.5538,
      "step": 4830
    },
    {
      "epoch": 0.14840414093939114,
      "grad_norm": 0.30344414710998535,
      "learning_rate": 1.9739868345090628e-05,
      "loss": 0.5774,
      "step": 4831
    },
    {
      "epoch": 0.1484348600743403,
      "grad_norm": 0.3095031678676605,
      "learning_rate": 1.973975882084752e-05,
      "loss": 0.5802,
      "step": 4832
    },
    {
      "epoch": 0.14846557920928946,
      "grad_norm": 0.3181275427341461,
      "learning_rate": 1.9739649273856517e-05,
      "loss": 0.5321,
      "step": 4833
    },
    {
      "epoch": 0.14849629834423864,
      "grad_norm": 0.37298038601875305,
      "learning_rate": 1.9739539704117885e-05,
      "loss": 0.5557,
      "step": 4834
    },
    {
      "epoch": 0.14852701747918778,
      "grad_norm": 0.3339169919490814,
      "learning_rate": 1.9739430111631883e-05,
      "loss": 0.6488,
      "step": 4835
    },
    {
      "epoch": 0.14855773661413696,
      "grad_norm": 0.32940781116485596,
      "learning_rate": 1.973932049639876e-05,
      "loss": 0.6137,
      "step": 4836
    },
    {
      "epoch": 0.1485884557490861,
      "grad_norm": 0.3499702513217926,
      "learning_rate": 1.973921085841877e-05,
      "loss": 0.6311,
      "step": 4837
    },
    {
      "epoch": 0.14861917488403525,
      "grad_norm": 0.44025367498397827,
      "learning_rate": 1.9739101197692175e-05,
      "loss": 0.6075,
      "step": 4838
    },
    {
      "epoch": 0.14864989401898443,
      "grad_norm": 0.36970919370651245,
      "learning_rate": 1.973899151421923e-05,
      "loss": 0.6755,
      "step": 4839
    },
    {
      "epoch": 0.14868061315393358,
      "grad_norm": 0.3728230893611908,
      "learning_rate": 1.9738881808000188e-05,
      "loss": 0.568,
      "step": 4840
    },
    {
      "epoch": 0.14871133228888275,
      "grad_norm": 0.3705703616142273,
      "learning_rate": 1.9738772079035308e-05,
      "loss": 0.5974,
      "step": 4841
    },
    {
      "epoch": 0.1487420514238319,
      "grad_norm": 0.3555648624897003,
      "learning_rate": 1.9738662327324848e-05,
      "loss": 0.6622,
      "step": 4842
    },
    {
      "epoch": 0.14877277055878108,
      "grad_norm": 0.34021955728530884,
      "learning_rate": 1.973855255286906e-05,
      "loss": 0.6098,
      "step": 4843
    },
    {
      "epoch": 0.14880348969373022,
      "grad_norm": 0.4137188792228699,
      "learning_rate": 1.9738442755668205e-05,
      "loss": 0.5729,
      "step": 4844
    },
    {
      "epoch": 0.14883420882867937,
      "grad_norm": 0.3055739998817444,
      "learning_rate": 1.9738332935722533e-05,
      "loss": 0.5811,
      "step": 4845
    },
    {
      "epoch": 0.14886492796362855,
      "grad_norm": 0.46475502848625183,
      "learning_rate": 1.9738223093032305e-05,
      "loss": 0.4683,
      "step": 4846
    },
    {
      "epoch": 0.1488956470985777,
      "grad_norm": 0.33170413970947266,
      "learning_rate": 1.9738113227597775e-05,
      "loss": 0.6634,
      "step": 4847
    },
    {
      "epoch": 0.14892636623352687,
      "grad_norm": 0.8211101293563843,
      "learning_rate": 1.973800333941921e-05,
      "loss": 0.6607,
      "step": 4848
    },
    {
      "epoch": 0.14895708536847602,
      "grad_norm": 0.36944326758384705,
      "learning_rate": 1.9737893428496848e-05,
      "loss": 0.7089,
      "step": 4849
    },
    {
      "epoch": 0.1489878045034252,
      "grad_norm": 0.3557504415512085,
      "learning_rate": 1.9737783494830962e-05,
      "loss": 0.6058,
      "step": 4850
    },
    {
      "epoch": 0.14901852363837434,
      "grad_norm": 0.36084431409835815,
      "learning_rate": 1.97376735384218e-05,
      "loss": 0.6009,
      "step": 4851
    },
    {
      "epoch": 0.14904924277332351,
      "grad_norm": 0.32979193329811096,
      "learning_rate": 1.9737563559269622e-05,
      "loss": 0.5818,
      "step": 4852
    },
    {
      "epoch": 0.14907996190827266,
      "grad_norm": 0.32719457149505615,
      "learning_rate": 1.9737453557374686e-05,
      "loss": 0.5469,
      "step": 4853
    },
    {
      "epoch": 0.1491106810432218,
      "grad_norm": 0.35036420822143555,
      "learning_rate": 1.9737343532737245e-05,
      "loss": 0.5393,
      "step": 4854
    },
    {
      "epoch": 0.14914140017817099,
      "grad_norm": 0.3432389795780182,
      "learning_rate": 1.9737233485357558e-05,
      "loss": 0.5812,
      "step": 4855
    },
    {
      "epoch": 0.14917211931312013,
      "grad_norm": 0.3721047043800354,
      "learning_rate": 1.973712341523588e-05,
      "loss": 0.6876,
      "step": 4856
    },
    {
      "epoch": 0.1492028384480693,
      "grad_norm": 0.35495609045028687,
      "learning_rate": 1.9737013322372476e-05,
      "loss": 0.5553,
      "step": 4857
    },
    {
      "epoch": 0.14923355758301846,
      "grad_norm": 0.3209853172302246,
      "learning_rate": 1.9736903206767596e-05,
      "loss": 0.544,
      "step": 4858
    },
    {
      "epoch": 0.14926427671796763,
      "grad_norm": 0.404523640871048,
      "learning_rate": 1.9736793068421493e-05,
      "loss": 0.6521,
      "step": 4859
    },
    {
      "epoch": 0.14929499585291678,
      "grad_norm": 0.36585500836372375,
      "learning_rate": 1.9736682907334437e-05,
      "loss": 0.6226,
      "step": 4860
    },
    {
      "epoch": 0.14932571498786595,
      "grad_norm": 0.3311029076576233,
      "learning_rate": 1.9736572723506673e-05,
      "loss": 0.5848,
      "step": 4861
    },
    {
      "epoch": 0.1493564341228151,
      "grad_norm": 0.9910761713981628,
      "learning_rate": 1.9736462516938464e-05,
      "loss": 0.5675,
      "step": 4862
    },
    {
      "epoch": 0.14938715325776425,
      "grad_norm": 0.3465051054954529,
      "learning_rate": 1.9736352287630066e-05,
      "loss": 0.639,
      "step": 4863
    },
    {
      "epoch": 0.14941787239271342,
      "grad_norm": 0.3524898886680603,
      "learning_rate": 1.973624203558174e-05,
      "loss": 0.5916,
      "step": 4864
    },
    {
      "epoch": 0.14944859152766257,
      "grad_norm": 0.2954869866371155,
      "learning_rate": 1.973613176079374e-05,
      "loss": 0.6079,
      "step": 4865
    },
    {
      "epoch": 0.14947931066261175,
      "grad_norm": 0.310528963804245,
      "learning_rate": 1.9736021463266327e-05,
      "loss": 0.5408,
      "step": 4866
    },
    {
      "epoch": 0.1495100297975609,
      "grad_norm": 0.39237895607948303,
      "learning_rate": 1.9735911142999753e-05,
      "loss": 0.6318,
      "step": 4867
    },
    {
      "epoch": 0.14954074893251007,
      "grad_norm": 0.35592129826545715,
      "learning_rate": 1.973580079999428e-05,
      "loss": 0.5945,
      "step": 4868
    },
    {
      "epoch": 0.14957146806745922,
      "grad_norm": 0.3211767375469208,
      "learning_rate": 1.973569043425016e-05,
      "loss": 0.6383,
      "step": 4869
    },
    {
      "epoch": 0.1496021872024084,
      "grad_norm": 0.34301164746284485,
      "learning_rate": 1.973558004576766e-05,
      "loss": 0.5979,
      "step": 4870
    },
    {
      "epoch": 0.14963290633735754,
      "grad_norm": 0.4573571979999542,
      "learning_rate": 1.973546963454703e-05,
      "loss": 0.6157,
      "step": 4871
    },
    {
      "epoch": 0.1496636254723067,
      "grad_norm": 0.3335179388523102,
      "learning_rate": 1.9735359200588534e-05,
      "loss": 0.6014,
      "step": 4872
    },
    {
      "epoch": 0.14969434460725586,
      "grad_norm": 0.32947319746017456,
      "learning_rate": 1.9735248743892424e-05,
      "loss": 0.617,
      "step": 4873
    },
    {
      "epoch": 0.149725063742205,
      "grad_norm": 0.3283652663230896,
      "learning_rate": 1.973513826445896e-05,
      "loss": 0.6119,
      "step": 4874
    },
    {
      "epoch": 0.1497557828771542,
      "grad_norm": 0.3368741571903229,
      "learning_rate": 1.9735027762288402e-05,
      "loss": 0.5733,
      "step": 4875
    },
    {
      "epoch": 0.14978650201210333,
      "grad_norm": 0.34320947527885437,
      "learning_rate": 1.9734917237381003e-05,
      "loss": 0.5962,
      "step": 4876
    },
    {
      "epoch": 0.1498172211470525,
      "grad_norm": 0.3396119773387909,
      "learning_rate": 1.973480668973703e-05,
      "loss": 0.6678,
      "step": 4877
    },
    {
      "epoch": 0.14984794028200166,
      "grad_norm": 0.40041738748550415,
      "learning_rate": 1.9734696119356736e-05,
      "loss": 0.5517,
      "step": 4878
    },
    {
      "epoch": 0.14987865941695083,
      "grad_norm": 0.3256848156452179,
      "learning_rate": 1.973458552624038e-05,
      "loss": 0.6205,
      "step": 4879
    },
    {
      "epoch": 0.14990937855189998,
      "grad_norm": 0.34792962670326233,
      "learning_rate": 1.9734474910388214e-05,
      "loss": 0.6562,
      "step": 4880
    },
    {
      "epoch": 0.14994009768684913,
      "grad_norm": 0.4179995656013489,
      "learning_rate": 1.9734364271800506e-05,
      "loss": 0.6121,
      "step": 4881
    },
    {
      "epoch": 0.1499708168217983,
      "grad_norm": 0.3125300407409668,
      "learning_rate": 1.973425361047751e-05,
      "loss": 0.6282,
      "step": 4882
    },
    {
      "epoch": 0.15000153595674745,
      "grad_norm": 0.36008089780807495,
      "learning_rate": 1.9734142926419487e-05,
      "loss": 0.5374,
      "step": 4883
    },
    {
      "epoch": 0.15003225509169663,
      "grad_norm": 0.3300665318965912,
      "learning_rate": 1.9734032219626687e-05,
      "loss": 0.632,
      "step": 4884
    },
    {
      "epoch": 0.15006297422664577,
      "grad_norm": 0.32623791694641113,
      "learning_rate": 1.973392149009938e-05,
      "loss": 0.6238,
      "step": 4885
    },
    {
      "epoch": 0.15009369336159495,
      "grad_norm": 0.33197078108787537,
      "learning_rate": 1.9733810737837818e-05,
      "loss": 0.4938,
      "step": 4886
    },
    {
      "epoch": 0.1501244124965441,
      "grad_norm": 0.32357266545295715,
      "learning_rate": 1.9733699962842264e-05,
      "loss": 0.6822,
      "step": 4887
    },
    {
      "epoch": 0.15015513163149324,
      "grad_norm": 0.35154107213020325,
      "learning_rate": 1.973358916511297e-05,
      "loss": 0.5751,
      "step": 4888
    },
    {
      "epoch": 0.15018585076644242,
      "grad_norm": 0.35157617926597595,
      "learning_rate": 1.9733478344650205e-05,
      "loss": 0.5589,
      "step": 4889
    },
    {
      "epoch": 0.15021656990139157,
      "grad_norm": 0.3679426312446594,
      "learning_rate": 1.9733367501454214e-05,
      "loss": 0.6564,
      "step": 4890
    },
    {
      "epoch": 0.15024728903634074,
      "grad_norm": 0.3270335793495178,
      "learning_rate": 1.9733256635525265e-05,
      "loss": 0.6073,
      "step": 4891
    },
    {
      "epoch": 0.1502780081712899,
      "grad_norm": 0.3486824631690979,
      "learning_rate": 1.973314574686362e-05,
      "loss": 0.6348,
      "step": 4892
    },
    {
      "epoch": 0.15030872730623906,
      "grad_norm": 0.4083581566810608,
      "learning_rate": 1.973303483546953e-05,
      "loss": 0.6308,
      "step": 4893
    },
    {
      "epoch": 0.1503394464411882,
      "grad_norm": 0.3388324975967407,
      "learning_rate": 1.9732923901343258e-05,
      "loss": 0.6337,
      "step": 4894
    },
    {
      "epoch": 0.1503701655761374,
      "grad_norm": 0.35632890462875366,
      "learning_rate": 1.973281294448506e-05,
      "loss": 0.6184,
      "step": 4895
    },
    {
      "epoch": 0.15040088471108654,
      "grad_norm": 0.3201945424079895,
      "learning_rate": 1.97327019648952e-05,
      "loss": 0.5966,
      "step": 4896
    },
    {
      "epoch": 0.15043160384603568,
      "grad_norm": 0.32549065351486206,
      "learning_rate": 1.9732590962573934e-05,
      "loss": 0.5933,
      "step": 4897
    },
    {
      "epoch": 0.15046232298098486,
      "grad_norm": 0.3797222971916199,
      "learning_rate": 1.973247993752152e-05,
      "loss": 0.6695,
      "step": 4898
    },
    {
      "epoch": 0.150493042115934,
      "grad_norm": 0.33088791370391846,
      "learning_rate": 1.9732368889738224e-05,
      "loss": 0.5841,
      "step": 4899
    },
    {
      "epoch": 0.15052376125088318,
      "grad_norm": 0.3576861023902893,
      "learning_rate": 1.97322578192243e-05,
      "loss": 0.6714,
      "step": 4900
    },
    {
      "epoch": 0.15055448038583233,
      "grad_norm": 0.39559316635131836,
      "learning_rate": 1.9732146725980006e-05,
      "loss": 0.6624,
      "step": 4901
    },
    {
      "epoch": 0.1505851995207815,
      "grad_norm": 0.3517100512981415,
      "learning_rate": 1.9732035610005606e-05,
      "loss": 0.5378,
      "step": 4902
    },
    {
      "epoch": 0.15061591865573065,
      "grad_norm": 0.33203622698783875,
      "learning_rate": 1.9731924471301355e-05,
      "loss": 0.6021,
      "step": 4903
    },
    {
      "epoch": 0.15064663779067983,
      "grad_norm": 0.33199042081832886,
      "learning_rate": 1.9731813309867517e-05,
      "loss": 0.6023,
      "step": 4904
    },
    {
      "epoch": 0.15067735692562897,
      "grad_norm": 0.3226483464241028,
      "learning_rate": 1.9731702125704346e-05,
      "loss": 0.518,
      "step": 4905
    },
    {
      "epoch": 0.15070807606057812,
      "grad_norm": 0.3974003195762634,
      "learning_rate": 1.9731590918812107e-05,
      "loss": 0.6347,
      "step": 4906
    },
    {
      "epoch": 0.1507387951955273,
      "grad_norm": 0.3119557499885559,
      "learning_rate": 1.9731479689191056e-05,
      "loss": 0.5276,
      "step": 4907
    },
    {
      "epoch": 0.15076951433047645,
      "grad_norm": 0.5529022216796875,
      "learning_rate": 1.973136843684146e-05,
      "loss": 0.5759,
      "step": 4908
    },
    {
      "epoch": 0.15080023346542562,
      "grad_norm": 0.32860803604125977,
      "learning_rate": 1.9731257161763565e-05,
      "loss": 0.5692,
      "step": 4909
    },
    {
      "epoch": 0.15083095260037477,
      "grad_norm": 0.3538283109664917,
      "learning_rate": 1.973114586395765e-05,
      "loss": 0.6305,
      "step": 4910
    },
    {
      "epoch": 0.15086167173532394,
      "grad_norm": 0.2902280390262604,
      "learning_rate": 1.9731034543423956e-05,
      "loss": 0.6115,
      "step": 4911
    },
    {
      "epoch": 0.1508923908702731,
      "grad_norm": 0.36382487416267395,
      "learning_rate": 1.9730923200162753e-05,
      "loss": 0.5919,
      "step": 4912
    },
    {
      "epoch": 0.15092311000522227,
      "grad_norm": 0.3328670859336853,
      "learning_rate": 1.97308118341743e-05,
      "loss": 0.6552,
      "step": 4913
    },
    {
      "epoch": 0.1509538291401714,
      "grad_norm": 0.3893597722053528,
      "learning_rate": 1.9730700445458856e-05,
      "loss": 0.5811,
      "step": 4914
    },
    {
      "epoch": 0.15098454827512056,
      "grad_norm": 0.3250792324542999,
      "learning_rate": 1.9730589034016678e-05,
      "loss": 0.6666,
      "step": 4915
    },
    {
      "epoch": 0.15101526741006974,
      "grad_norm": 0.3149586617946625,
      "learning_rate": 1.9730477599848036e-05,
      "loss": 0.5287,
      "step": 4916
    },
    {
      "epoch": 0.15104598654501888,
      "grad_norm": 0.34516385197639465,
      "learning_rate": 1.9730366142953178e-05,
      "loss": 0.6476,
      "step": 4917
    },
    {
      "epoch": 0.15107670567996806,
      "grad_norm": 0.3535425662994385,
      "learning_rate": 1.9730254663332376e-05,
      "loss": 0.6283,
      "step": 4918
    },
    {
      "epoch": 0.1511074248149172,
      "grad_norm": 0.3435814678668976,
      "learning_rate": 1.9730143160985883e-05,
      "loss": 0.6527,
      "step": 4919
    },
    {
      "epoch": 0.15113814394986638,
      "grad_norm": 0.4311700165271759,
      "learning_rate": 1.973003163591396e-05,
      "loss": 0.6276,
      "step": 4920
    },
    {
      "epoch": 0.15116886308481553,
      "grad_norm": 0.4034916162490845,
      "learning_rate": 1.972992008811687e-05,
      "loss": 0.5686,
      "step": 4921
    },
    {
      "epoch": 0.15119958221976468,
      "grad_norm": 0.3205583393573761,
      "learning_rate": 1.972980851759487e-05,
      "loss": 0.5913,
      "step": 4922
    },
    {
      "epoch": 0.15123030135471385,
      "grad_norm": 0.35011646151542664,
      "learning_rate": 1.972969692434822e-05,
      "loss": 0.6284,
      "step": 4923
    },
    {
      "epoch": 0.151261020489663,
      "grad_norm": 0.3304441273212433,
      "learning_rate": 1.9729585308377192e-05,
      "loss": 0.5177,
      "step": 4924
    },
    {
      "epoch": 0.15129173962461218,
      "grad_norm": 0.33244651556015015,
      "learning_rate": 1.972947366968203e-05,
      "loss": 0.5814,
      "step": 4925
    },
    {
      "epoch": 0.15132245875956132,
      "grad_norm": 0.35305142402648926,
      "learning_rate": 1.9729362008263003e-05,
      "loss": 0.5601,
      "step": 4926
    },
    {
      "epoch": 0.1513531778945105,
      "grad_norm": 0.33509311079978943,
      "learning_rate": 1.9729250324120377e-05,
      "loss": 0.602,
      "step": 4927
    },
    {
      "epoch": 0.15138389702945965,
      "grad_norm": 0.433647096157074,
      "learning_rate": 1.9729138617254408e-05,
      "loss": 0.6239,
      "step": 4928
    },
    {
      "epoch": 0.15141461616440882,
      "grad_norm": 0.3567454218864441,
      "learning_rate": 1.972902688766535e-05,
      "loss": 0.5556,
      "step": 4929
    },
    {
      "epoch": 0.15144533529935797,
      "grad_norm": 0.33331063389778137,
      "learning_rate": 1.9728915135353474e-05,
      "loss": 0.6492,
      "step": 4930
    },
    {
      "epoch": 0.15147605443430712,
      "grad_norm": 0.35652223229408264,
      "learning_rate": 1.9728803360319035e-05,
      "loss": 0.6878,
      "step": 4931
    },
    {
      "epoch": 0.1515067735692563,
      "grad_norm": 0.3296626806259155,
      "learning_rate": 1.9728691562562297e-05,
      "loss": 0.5978,
      "step": 4932
    },
    {
      "epoch": 0.15153749270420544,
      "grad_norm": 0.32020148634910583,
      "learning_rate": 1.972857974208352e-05,
      "loss": 0.6552,
      "step": 4933
    },
    {
      "epoch": 0.15156821183915462,
      "grad_norm": 0.3121306300163269,
      "learning_rate": 1.9728467898882967e-05,
      "loss": 0.5679,
      "step": 4934
    },
    {
      "epoch": 0.15159893097410376,
      "grad_norm": 0.32141393423080444,
      "learning_rate": 1.97283560329609e-05,
      "loss": 0.6285,
      "step": 4935
    },
    {
      "epoch": 0.15162965010905294,
      "grad_norm": 0.35459214448928833,
      "learning_rate": 1.9728244144317578e-05,
      "loss": 0.6157,
      "step": 4936
    },
    {
      "epoch": 0.15166036924400209,
      "grad_norm": 0.35573428869247437,
      "learning_rate": 1.9728132232953257e-05,
      "loss": 0.7715,
      "step": 4937
    },
    {
      "epoch": 0.15169108837895126,
      "grad_norm": 0.3394521176815033,
      "learning_rate": 1.9728020298868206e-05,
      "loss": 0.6352,
      "step": 4938
    },
    {
      "epoch": 0.1517218075139004,
      "grad_norm": 0.3097068965435028,
      "learning_rate": 1.9727908342062685e-05,
      "loss": 0.588,
      "step": 4939
    },
    {
      "epoch": 0.15175252664884956,
      "grad_norm": 0.3012785017490387,
      "learning_rate": 1.9727796362536956e-05,
      "loss": 0.6145,
      "step": 4940
    },
    {
      "epoch": 0.15178324578379873,
      "grad_norm": 0.32570454478263855,
      "learning_rate": 1.972768436029128e-05,
      "loss": 0.6511,
      "step": 4941
    },
    {
      "epoch": 0.15181396491874788,
      "grad_norm": 0.39569348096847534,
      "learning_rate": 1.9727572335325914e-05,
      "loss": 0.6145,
      "step": 4942
    },
    {
      "epoch": 0.15184468405369705,
      "grad_norm": 0.800865113735199,
      "learning_rate": 1.9727460287641124e-05,
      "loss": 0.5693,
      "step": 4943
    },
    {
      "epoch": 0.1518754031886462,
      "grad_norm": 0.32617682218551636,
      "learning_rate": 1.9727348217237172e-05,
      "loss": 0.5608,
      "step": 4944
    },
    {
      "epoch": 0.15190612232359538,
      "grad_norm": 0.34555384516716003,
      "learning_rate": 1.9727236124114316e-05,
      "loss": 0.6074,
      "step": 4945
    },
    {
      "epoch": 0.15193684145854452,
      "grad_norm": 0.4082109332084656,
      "learning_rate": 1.9727124008272827e-05,
      "loss": 0.5635,
      "step": 4946
    },
    {
      "epoch": 0.1519675605934937,
      "grad_norm": 0.34150490164756775,
      "learning_rate": 1.972701186971296e-05,
      "loss": 0.5238,
      "step": 4947
    },
    {
      "epoch": 0.15199827972844285,
      "grad_norm": 0.4103369116783142,
      "learning_rate": 1.9726899708434972e-05,
      "loss": 0.6349,
      "step": 4948
    },
    {
      "epoch": 0.152028998863392,
      "grad_norm": 0.6631600856781006,
      "learning_rate": 1.972678752443913e-05,
      "loss": 0.7341,
      "step": 4949
    },
    {
      "epoch": 0.15205971799834117,
      "grad_norm": 0.3640218675136566,
      "learning_rate": 1.97266753177257e-05,
      "loss": 0.5982,
      "step": 4950
    },
    {
      "epoch": 0.15209043713329032,
      "grad_norm": 0.3596055507659912,
      "learning_rate": 1.9726563088294942e-05,
      "loss": 0.6268,
      "step": 4951
    },
    {
      "epoch": 0.1521211562682395,
      "grad_norm": 0.3377299904823303,
      "learning_rate": 1.9726450836147115e-05,
      "loss": 0.669,
      "step": 4952
    },
    {
      "epoch": 0.15215187540318864,
      "grad_norm": 0.3247532546520233,
      "learning_rate": 1.972633856128248e-05,
      "loss": 0.5829,
      "step": 4953
    },
    {
      "epoch": 0.15218259453813782,
      "grad_norm": 0.343746155500412,
      "learning_rate": 1.9726226263701308e-05,
      "loss": 0.6164,
      "step": 4954
    },
    {
      "epoch": 0.15221331367308696,
      "grad_norm": 0.3226998448371887,
      "learning_rate": 1.972611394340385e-05,
      "loss": 0.6133,
      "step": 4955
    },
    {
      "epoch": 0.15224403280803614,
      "grad_norm": 0.36335867643356323,
      "learning_rate": 1.9726001600390377e-05,
      "loss": 0.6216,
      "step": 4956
    },
    {
      "epoch": 0.1522747519429853,
      "grad_norm": 0.346691370010376,
      "learning_rate": 1.9725889234661144e-05,
      "loss": 0.6003,
      "step": 4957
    },
    {
      "epoch": 0.15230547107793443,
      "grad_norm": 0.32536736130714417,
      "learning_rate": 1.972577684621642e-05,
      "loss": 0.5976,
      "step": 4958
    },
    {
      "epoch": 0.1523361902128836,
      "grad_norm": 0.3481276333332062,
      "learning_rate": 1.9725664435056465e-05,
      "loss": 0.5523,
      "step": 4959
    },
    {
      "epoch": 0.15236690934783276,
      "grad_norm": 0.4066382646560669,
      "learning_rate": 1.972555200118154e-05,
      "loss": 0.5911,
      "step": 4960
    },
    {
      "epoch": 0.15239762848278193,
      "grad_norm": 0.34515976905822754,
      "learning_rate": 1.9725439544591915e-05,
      "loss": 0.5923,
      "step": 4961
    },
    {
      "epoch": 0.15242834761773108,
      "grad_norm": 0.3588673770427704,
      "learning_rate": 1.972532706528784e-05,
      "loss": 0.6143,
      "step": 4962
    },
    {
      "epoch": 0.15245906675268026,
      "grad_norm": 0.34160295128822327,
      "learning_rate": 1.9725214563269585e-05,
      "loss": 0.7171,
      "step": 4963
    },
    {
      "epoch": 0.1524897858876294,
      "grad_norm": 0.35982197523117065,
      "learning_rate": 1.9725102038537415e-05,
      "loss": 0.6319,
      "step": 4964
    },
    {
      "epoch": 0.15252050502257855,
      "grad_norm": 0.3422704041004181,
      "learning_rate": 1.9724989491091588e-05,
      "loss": 0.5777,
      "step": 4965
    },
    {
      "epoch": 0.15255122415752773,
      "grad_norm": 0.35097262263298035,
      "learning_rate": 1.972487692093237e-05,
      "loss": 0.662,
      "step": 4966
    },
    {
      "epoch": 0.15258194329247687,
      "grad_norm": 0.3383050262928009,
      "learning_rate": 1.972476432806002e-05,
      "loss": 0.6296,
      "step": 4967
    },
    {
      "epoch": 0.15261266242742605,
      "grad_norm": 0.3413738012313843,
      "learning_rate": 1.9724651712474808e-05,
      "loss": 0.6212,
      "step": 4968
    },
    {
      "epoch": 0.1526433815623752,
      "grad_norm": 0.3678542971611023,
      "learning_rate": 1.972453907417699e-05,
      "loss": 0.6,
      "step": 4969
    },
    {
      "epoch": 0.15267410069732437,
      "grad_norm": 0.35124602913856506,
      "learning_rate": 1.9724426413166834e-05,
      "loss": 0.5901,
      "step": 4970
    },
    {
      "epoch": 0.15270481983227352,
      "grad_norm": 0.33392852544784546,
      "learning_rate": 1.97243137294446e-05,
      "loss": 0.5496,
      "step": 4971
    },
    {
      "epoch": 0.1527355389672227,
      "grad_norm": 0.3229723274707794,
      "learning_rate": 1.972420102301055e-05,
      "loss": 0.5744,
      "step": 4972
    },
    {
      "epoch": 0.15276625810217184,
      "grad_norm": 0.5563663244247437,
      "learning_rate": 1.9724088293864952e-05,
      "loss": 0.5271,
      "step": 4973
    },
    {
      "epoch": 0.152796977237121,
      "grad_norm": 0.341386616230011,
      "learning_rate": 1.9723975542008066e-05,
      "loss": 0.5892,
      "step": 4974
    },
    {
      "epoch": 0.15282769637207017,
      "grad_norm": 0.6006923913955688,
      "learning_rate": 1.9723862767440157e-05,
      "loss": 0.7016,
      "step": 4975
    },
    {
      "epoch": 0.1528584155070193,
      "grad_norm": 0.34445998072624207,
      "learning_rate": 1.9723749970161485e-05,
      "loss": 0.5739,
      "step": 4976
    },
    {
      "epoch": 0.1528891346419685,
      "grad_norm": 0.31865936517715454,
      "learning_rate": 1.9723637150172318e-05,
      "loss": 0.5886,
      "step": 4977
    },
    {
      "epoch": 0.15291985377691764,
      "grad_norm": 0.35978955030441284,
      "learning_rate": 1.9723524307472917e-05,
      "loss": 0.5543,
      "step": 4978
    },
    {
      "epoch": 0.1529505729118668,
      "grad_norm": 0.4027895927429199,
      "learning_rate": 1.9723411442063542e-05,
      "loss": 0.6055,
      "step": 4979
    },
    {
      "epoch": 0.15298129204681596,
      "grad_norm": 0.35369014739990234,
      "learning_rate": 1.9723298553944466e-05,
      "loss": 0.5632,
      "step": 4980
    },
    {
      "epoch": 0.15301201118176513,
      "grad_norm": 0.3629381060600281,
      "learning_rate": 1.9723185643115945e-05,
      "loss": 0.612,
      "step": 4981
    },
    {
      "epoch": 0.15304273031671428,
      "grad_norm": 0.35895636677742004,
      "learning_rate": 1.9723072709578244e-05,
      "loss": 0.6089,
      "step": 4982
    },
    {
      "epoch": 0.15307344945166343,
      "grad_norm": 0.3464110195636749,
      "learning_rate": 1.9722959753331627e-05,
      "loss": 0.6546,
      "step": 4983
    },
    {
      "epoch": 0.1531041685866126,
      "grad_norm": 0.3057441711425781,
      "learning_rate": 1.972284677437636e-05,
      "loss": 0.5315,
      "step": 4984
    },
    {
      "epoch": 0.15313488772156175,
      "grad_norm": 0.3098561465740204,
      "learning_rate": 1.9722733772712708e-05,
      "loss": 0.6316,
      "step": 4985
    },
    {
      "epoch": 0.15316560685651093,
      "grad_norm": 0.3206138610839844,
      "learning_rate": 1.972262074834093e-05,
      "loss": 0.6093,
      "step": 4986
    },
    {
      "epoch": 0.15319632599146008,
      "grad_norm": 0.34347784519195557,
      "learning_rate": 1.972250770126129e-05,
      "loss": 0.5443,
      "step": 4987
    },
    {
      "epoch": 0.15322704512640925,
      "grad_norm": 0.35404878854751587,
      "learning_rate": 1.9722394631474056e-05,
      "loss": 0.5499,
      "step": 4988
    },
    {
      "epoch": 0.1532577642613584,
      "grad_norm": 0.3880816698074341,
      "learning_rate": 1.972228153897949e-05,
      "loss": 0.6642,
      "step": 4989
    },
    {
      "epoch": 0.15328848339630757,
      "grad_norm": 0.3267437219619751,
      "learning_rate": 1.9722168423777856e-05,
      "loss": 0.5389,
      "step": 4990
    },
    {
      "epoch": 0.15331920253125672,
      "grad_norm": 0.27207812666893005,
      "learning_rate": 1.972205528586942e-05,
      "loss": 0.5188,
      "step": 4991
    },
    {
      "epoch": 0.15334992166620587,
      "grad_norm": 0.3556445837020874,
      "learning_rate": 1.9721942125254445e-05,
      "loss": 0.604,
      "step": 4992
    },
    {
      "epoch": 0.15338064080115504,
      "grad_norm": 0.36455896496772766,
      "learning_rate": 1.9721828941933195e-05,
      "loss": 0.6505,
      "step": 4993
    },
    {
      "epoch": 0.1534113599361042,
      "grad_norm": 0.3516797721385956,
      "learning_rate": 1.9721715735905934e-05,
      "loss": 0.6061,
      "step": 4994
    },
    {
      "epoch": 0.15344207907105337,
      "grad_norm": 0.3720945715904236,
      "learning_rate": 1.9721602507172927e-05,
      "loss": 0.6657,
      "step": 4995
    },
    {
      "epoch": 0.15347279820600251,
      "grad_norm": 0.32599520683288574,
      "learning_rate": 1.9721489255734437e-05,
      "loss": 0.5692,
      "step": 4996
    },
    {
      "epoch": 0.1535035173409517,
      "grad_norm": 0.3009876012802124,
      "learning_rate": 1.972137598159073e-05,
      "loss": 0.541,
      "step": 4997
    },
    {
      "epoch": 0.15353423647590084,
      "grad_norm": 0.32991501688957214,
      "learning_rate": 1.972126268474207e-05,
      "loss": 0.6418,
      "step": 4998
    },
    {
      "epoch": 0.15356495561084998,
      "grad_norm": 0.3624096214771271,
      "learning_rate": 1.972114936518873e-05,
      "loss": 0.6493,
      "step": 4999
    },
    {
      "epoch": 0.15359567474579916,
      "grad_norm": 0.345829576253891,
      "learning_rate": 1.972103602293096e-05,
      "loss": 0.6285,
      "step": 5000
    },
    {
      "epoch": 0.1536263938807483,
      "grad_norm": 0.31113511323928833,
      "learning_rate": 1.972092265796903e-05,
      "loss": 0.665,
      "step": 5001
    },
    {
      "epoch": 0.15365711301569748,
      "grad_norm": 0.31589585542678833,
      "learning_rate": 1.9720809270303207e-05,
      "loss": 0.5583,
      "step": 5002
    },
    {
      "epoch": 0.15368783215064663,
      "grad_norm": 0.31817612051963806,
      "learning_rate": 1.972069585993376e-05,
      "loss": 0.6137,
      "step": 5003
    },
    {
      "epoch": 0.1537185512855958,
      "grad_norm": 0.35874807834625244,
      "learning_rate": 1.9720582426860942e-05,
      "loss": 0.6342,
      "step": 5004
    },
    {
      "epoch": 0.15374927042054495,
      "grad_norm": 0.3284189999103546,
      "learning_rate": 1.972046897108503e-05,
      "loss": 0.6091,
      "step": 5005
    },
    {
      "epoch": 0.15377998955549413,
      "grad_norm": 0.3909201920032501,
      "learning_rate": 1.9720355492606283e-05,
      "loss": 0.6204,
      "step": 5006
    },
    {
      "epoch": 0.15381070869044328,
      "grad_norm": 0.3562530279159546,
      "learning_rate": 1.9720241991424963e-05,
      "loss": 0.6546,
      "step": 5007
    },
    {
      "epoch": 0.15384142782539242,
      "grad_norm": 0.3294016420841217,
      "learning_rate": 1.9720128467541344e-05,
      "loss": 0.6939,
      "step": 5008
    },
    {
      "epoch": 0.1538721469603416,
      "grad_norm": 0.38732486963272095,
      "learning_rate": 1.972001492095568e-05,
      "loss": 0.529,
      "step": 5009
    },
    {
      "epoch": 0.15390286609529075,
      "grad_norm": 0.3355622887611389,
      "learning_rate": 1.971990135166825e-05,
      "loss": 0.5951,
      "step": 5010
    },
    {
      "epoch": 0.15393358523023992,
      "grad_norm": 0.3148454427719116,
      "learning_rate": 1.9719787759679305e-05,
      "loss": 0.5542,
      "step": 5011
    },
    {
      "epoch": 0.15396430436518907,
      "grad_norm": 0.317731648683548,
      "learning_rate": 1.971967414498912e-05,
      "loss": 0.643,
      "step": 5012
    },
    {
      "epoch": 0.15399502350013825,
      "grad_norm": 0.3330687880516052,
      "learning_rate": 1.9719560507597955e-05,
      "loss": 0.6598,
      "step": 5013
    },
    {
      "epoch": 0.1540257426350874,
      "grad_norm": 0.35995063185691833,
      "learning_rate": 1.971944684750608e-05,
      "loss": 0.6476,
      "step": 5014
    },
    {
      "epoch": 0.15405646177003657,
      "grad_norm": 0.31915372610092163,
      "learning_rate": 1.9719333164713762e-05,
      "loss": 0.6064,
      "step": 5015
    },
    {
      "epoch": 0.15408718090498572,
      "grad_norm": 0.32760220766067505,
      "learning_rate": 1.9719219459221258e-05,
      "loss": 0.5773,
      "step": 5016
    },
    {
      "epoch": 0.15411790003993486,
      "grad_norm": 0.3440483808517456,
      "learning_rate": 1.9719105731028837e-05,
      "loss": 0.6683,
      "step": 5017
    },
    {
      "epoch": 0.15414861917488404,
      "grad_norm": 0.3330777585506439,
      "learning_rate": 1.971899198013677e-05,
      "loss": 0.5291,
      "step": 5018
    },
    {
      "epoch": 0.15417933830983319,
      "grad_norm": 0.35699528455734253,
      "learning_rate": 1.9718878206545313e-05,
      "loss": 0.5431,
      "step": 5019
    },
    {
      "epoch": 0.15421005744478236,
      "grad_norm": 0.29825013875961304,
      "learning_rate": 1.971876441025474e-05,
      "loss": 0.5114,
      "step": 5020
    },
    {
      "epoch": 0.1542407765797315,
      "grad_norm": 0.3256905674934387,
      "learning_rate": 1.9718650591265313e-05,
      "loss": 0.5708,
      "step": 5021
    },
    {
      "epoch": 0.15427149571468068,
      "grad_norm": 0.3094388246536255,
      "learning_rate": 1.9718536749577303e-05,
      "loss": 0.5954,
      "step": 5022
    },
    {
      "epoch": 0.15430221484962983,
      "grad_norm": 0.3380347788333893,
      "learning_rate": 1.9718422885190963e-05,
      "loss": 0.66,
      "step": 5023
    },
    {
      "epoch": 0.154332933984579,
      "grad_norm": 0.3990163207054138,
      "learning_rate": 1.9718308998106575e-05,
      "loss": 0.5513,
      "step": 5024
    },
    {
      "epoch": 0.15436365311952815,
      "grad_norm": 0.35449719429016113,
      "learning_rate": 1.9718195088324394e-05,
      "loss": 0.6397,
      "step": 5025
    },
    {
      "epoch": 0.1543943722544773,
      "grad_norm": 0.3179326057434082,
      "learning_rate": 1.9718081155844696e-05,
      "loss": 0.6421,
      "step": 5026
    },
    {
      "epoch": 0.15442509138942648,
      "grad_norm": 0.3849300146102905,
      "learning_rate": 1.9717967200667733e-05,
      "loss": 0.614,
      "step": 5027
    },
    {
      "epoch": 0.15445581052437563,
      "grad_norm": 0.3502308428287506,
      "learning_rate": 1.9717853222793783e-05,
      "loss": 0.6502,
      "step": 5028
    },
    {
      "epoch": 0.1544865296593248,
      "grad_norm": 0.4148201048374176,
      "learning_rate": 1.9717739222223105e-05,
      "loss": 0.6605,
      "step": 5029
    },
    {
      "epoch": 0.15451724879427395,
      "grad_norm": 0.3516957461833954,
      "learning_rate": 1.971762519895597e-05,
      "loss": 0.644,
      "step": 5030
    },
    {
      "epoch": 0.15454796792922312,
      "grad_norm": 0.3283853828907013,
      "learning_rate": 1.971751115299264e-05,
      "loss": 0.5842,
      "step": 5031
    },
    {
      "epoch": 0.15457868706417227,
      "grad_norm": 0.36647510528564453,
      "learning_rate": 1.9717397084333392e-05,
      "loss": 0.612,
      "step": 5032
    },
    {
      "epoch": 0.15460940619912145,
      "grad_norm": 0.3753528594970703,
      "learning_rate": 1.9717282992978478e-05,
      "loss": 0.6232,
      "step": 5033
    },
    {
      "epoch": 0.1546401253340706,
      "grad_norm": 0.4416557252407074,
      "learning_rate": 1.9717168878928173e-05,
      "loss": 0.4763,
      "step": 5034
    },
    {
      "epoch": 0.15467084446901974,
      "grad_norm": 0.3052119314670563,
      "learning_rate": 1.9717054742182742e-05,
      "loss": 0.5685,
      "step": 5035
    },
    {
      "epoch": 0.15470156360396892,
      "grad_norm": 0.3113239109516144,
      "learning_rate": 1.971694058274245e-05,
      "loss": 0.6127,
      "step": 5036
    },
    {
      "epoch": 0.15473228273891806,
      "grad_norm": 0.3531402051448822,
      "learning_rate": 1.9716826400607565e-05,
      "loss": 0.5812,
      "step": 5037
    },
    {
      "epoch": 0.15476300187386724,
      "grad_norm": 0.33439117670059204,
      "learning_rate": 1.971671219577835e-05,
      "loss": 0.5915,
      "step": 5038
    },
    {
      "epoch": 0.1547937210088164,
      "grad_norm": 0.3257230520248413,
      "learning_rate": 1.9716597968255077e-05,
      "loss": 0.5965,
      "step": 5039
    },
    {
      "epoch": 0.15482444014376556,
      "grad_norm": 0.3451187014579773,
      "learning_rate": 1.9716483718038012e-05,
      "loss": 0.7093,
      "step": 5040
    },
    {
      "epoch": 0.1548551592787147,
      "grad_norm": 0.32665252685546875,
      "learning_rate": 1.971636944512742e-05,
      "loss": 0.5646,
      "step": 5041
    },
    {
      "epoch": 0.15488587841366386,
      "grad_norm": 0.32626980543136597,
      "learning_rate": 1.971625514952357e-05,
      "loss": 0.6131,
      "step": 5042
    },
    {
      "epoch": 0.15491659754861303,
      "grad_norm": 0.3340093493461609,
      "learning_rate": 1.9716140831226728e-05,
      "loss": 0.6249,
      "step": 5043
    },
    {
      "epoch": 0.15494731668356218,
      "grad_norm": 0.35985082387924194,
      "learning_rate": 1.9716026490237157e-05,
      "loss": 0.7364,
      "step": 5044
    },
    {
      "epoch": 0.15497803581851136,
      "grad_norm": 0.45398813486099243,
      "learning_rate": 1.9715912126555133e-05,
      "loss": 0.5563,
      "step": 5045
    },
    {
      "epoch": 0.1550087549534605,
      "grad_norm": 0.3353818953037262,
      "learning_rate": 1.9715797740180914e-05,
      "loss": 0.6421,
      "step": 5046
    },
    {
      "epoch": 0.15503947408840968,
      "grad_norm": 0.3066404163837433,
      "learning_rate": 1.9715683331114773e-05,
      "loss": 0.5191,
      "step": 5047
    },
    {
      "epoch": 0.15507019322335883,
      "grad_norm": 0.3753024637699127,
      "learning_rate": 1.9715568899356968e-05,
      "loss": 0.6097,
      "step": 5048
    },
    {
      "epoch": 0.155100912358308,
      "grad_norm": 0.32660579681396484,
      "learning_rate": 1.971545444490778e-05,
      "loss": 0.5891,
      "step": 5049
    },
    {
      "epoch": 0.15513163149325715,
      "grad_norm": 0.37823933362960815,
      "learning_rate": 1.971533996776747e-05,
      "loss": 0.6066,
      "step": 5050
    },
    {
      "epoch": 0.1551623506282063,
      "grad_norm": 0.29149770736694336,
      "learning_rate": 1.9715225467936303e-05,
      "loss": 0.5542,
      "step": 5051
    },
    {
      "epoch": 0.15519306976315547,
      "grad_norm": 0.3353050649166107,
      "learning_rate": 1.9715110945414548e-05,
      "loss": 0.5777,
      "step": 5052
    },
    {
      "epoch": 0.15522378889810462,
      "grad_norm": 0.3575619161128998,
      "learning_rate": 1.9714996400202474e-05,
      "loss": 0.5967,
      "step": 5053
    },
    {
      "epoch": 0.1552545080330538,
      "grad_norm": 0.39224323630332947,
      "learning_rate": 1.971488183230035e-05,
      "loss": 0.5886,
      "step": 5054
    },
    {
      "epoch": 0.15528522716800294,
      "grad_norm": 0.3113049864768982,
      "learning_rate": 1.9714767241708434e-05,
      "loss": 0.5912,
      "step": 5055
    },
    {
      "epoch": 0.15531594630295212,
      "grad_norm": 0.39248034358024597,
      "learning_rate": 1.9714652628427006e-05,
      "loss": 0.6635,
      "step": 5056
    },
    {
      "epoch": 0.15534666543790127,
      "grad_norm": 0.3156565725803375,
      "learning_rate": 1.9714537992456324e-05,
      "loss": 0.5928,
      "step": 5057
    },
    {
      "epoch": 0.15537738457285044,
      "grad_norm": 0.33467355370521545,
      "learning_rate": 1.9714423333796665e-05,
      "loss": 0.6518,
      "step": 5058
    },
    {
      "epoch": 0.1554081037077996,
      "grad_norm": 0.33010849356651306,
      "learning_rate": 1.971430865244829e-05,
      "loss": 0.6289,
      "step": 5059
    },
    {
      "epoch": 0.15543882284274874,
      "grad_norm": 0.3161852955818176,
      "learning_rate": 1.9714193948411467e-05,
      "loss": 0.5874,
      "step": 5060
    },
    {
      "epoch": 0.1554695419776979,
      "grad_norm": 0.34696653485298157,
      "learning_rate": 1.9714079221686467e-05,
      "loss": 0.6134,
      "step": 5061
    },
    {
      "epoch": 0.15550026111264706,
      "grad_norm": 0.34161293506622314,
      "learning_rate": 1.9713964472273556e-05,
      "loss": 0.5698,
      "step": 5062
    },
    {
      "epoch": 0.15553098024759623,
      "grad_norm": 0.3741774559020996,
      "learning_rate": 1.9713849700173004e-05,
      "loss": 0.6451,
      "step": 5063
    },
    {
      "epoch": 0.15556169938254538,
      "grad_norm": 0.363383412361145,
      "learning_rate": 1.9713734905385074e-05,
      "loss": 0.5928,
      "step": 5064
    },
    {
      "epoch": 0.15559241851749456,
      "grad_norm": 0.4020008146762848,
      "learning_rate": 1.9713620087910045e-05,
      "loss": 0.5885,
      "step": 5065
    },
    {
      "epoch": 0.1556231376524437,
      "grad_norm": 0.37068241834640503,
      "learning_rate": 1.9713505247748173e-05,
      "loss": 0.6265,
      "step": 5066
    },
    {
      "epoch": 0.15565385678739288,
      "grad_norm": 0.32770898938179016,
      "learning_rate": 1.9713390384899733e-05,
      "loss": 0.5934,
      "step": 5067
    },
    {
      "epoch": 0.15568457592234203,
      "grad_norm": 0.3148091733455658,
      "learning_rate": 1.971327549936499e-05,
      "loss": 0.5917,
      "step": 5068
    },
    {
      "epoch": 0.15571529505729118,
      "grad_norm": 0.330154687166214,
      "learning_rate": 1.9713160591144213e-05,
      "loss": 0.668,
      "step": 5069
    },
    {
      "epoch": 0.15574601419224035,
      "grad_norm": 0.3466147184371948,
      "learning_rate": 1.971304566023767e-05,
      "loss": 0.614,
      "step": 5070
    },
    {
      "epoch": 0.1557767333271895,
      "grad_norm": 0.4033340811729431,
      "learning_rate": 1.9712930706645633e-05,
      "loss": 0.5869,
      "step": 5071
    },
    {
      "epoch": 0.15580745246213867,
      "grad_norm": 0.42030107975006104,
      "learning_rate": 1.9712815730368365e-05,
      "loss": 0.6261,
      "step": 5072
    },
    {
      "epoch": 0.15583817159708782,
      "grad_norm": 0.33607107400894165,
      "learning_rate": 1.971270073140614e-05,
      "loss": 0.6059,
      "step": 5073
    },
    {
      "epoch": 0.155868890732037,
      "grad_norm": 0.3669484257698059,
      "learning_rate": 1.9712585709759224e-05,
      "loss": 0.5982,
      "step": 5074
    },
    {
      "epoch": 0.15589960986698614,
      "grad_norm": 0.3347281813621521,
      "learning_rate": 1.9712470665427887e-05,
      "loss": 0.6588,
      "step": 5075
    },
    {
      "epoch": 0.1559303290019353,
      "grad_norm": 0.37605470418930054,
      "learning_rate": 1.9712355598412394e-05,
      "loss": 0.5734,
      "step": 5076
    },
    {
      "epoch": 0.15596104813688447,
      "grad_norm": 0.3508245348930359,
      "learning_rate": 1.971224050871302e-05,
      "loss": 0.6483,
      "step": 5077
    },
    {
      "epoch": 0.15599176727183361,
      "grad_norm": 0.3361445665359497,
      "learning_rate": 1.9712125396330025e-05,
      "loss": 0.6425,
      "step": 5078
    },
    {
      "epoch": 0.1560224864067828,
      "grad_norm": 0.31319549679756165,
      "learning_rate": 1.9712010261263685e-05,
      "loss": 0.5854,
      "step": 5079
    },
    {
      "epoch": 0.15605320554173194,
      "grad_norm": 0.3893001079559326,
      "learning_rate": 1.9711895103514267e-05,
      "loss": 0.6927,
      "step": 5080
    },
    {
      "epoch": 0.1560839246766811,
      "grad_norm": 0.30647194385528564,
      "learning_rate": 1.971177992308204e-05,
      "loss": 0.6038,
      "step": 5081
    },
    {
      "epoch": 0.15611464381163026,
      "grad_norm": 0.3465379476547241,
      "learning_rate": 1.9711664719967273e-05,
      "loss": 0.632,
      "step": 5082
    },
    {
      "epoch": 0.15614536294657944,
      "grad_norm": 0.3015036880970001,
      "learning_rate": 1.9711549494170233e-05,
      "loss": 0.6324,
      "step": 5083
    },
    {
      "epoch": 0.15617608208152858,
      "grad_norm": 0.3154418468475342,
      "learning_rate": 1.9711434245691192e-05,
      "loss": 0.619,
      "step": 5084
    },
    {
      "epoch": 0.15620680121647773,
      "grad_norm": 0.38356342911720276,
      "learning_rate": 1.9711318974530418e-05,
      "loss": 0.5953,
      "step": 5085
    },
    {
      "epoch": 0.1562375203514269,
      "grad_norm": 0.3928440511226654,
      "learning_rate": 1.971120368068818e-05,
      "loss": 0.6491,
      "step": 5086
    },
    {
      "epoch": 0.15626823948637605,
      "grad_norm": 0.36644038558006287,
      "learning_rate": 1.971108836416475e-05,
      "loss": 0.6708,
      "step": 5087
    },
    {
      "epoch": 0.15629895862132523,
      "grad_norm": 0.3821943700313568,
      "learning_rate": 1.9710973024960388e-05,
      "loss": 0.5586,
      "step": 5088
    },
    {
      "epoch": 0.15632967775627438,
      "grad_norm": 0.361045241355896,
      "learning_rate": 1.971085766307538e-05,
      "loss": 0.6688,
      "step": 5089
    },
    {
      "epoch": 0.15636039689122355,
      "grad_norm": 0.3347843885421753,
      "learning_rate": 1.971074227850998e-05,
      "loss": 0.5927,
      "step": 5090
    },
    {
      "epoch": 0.1563911160261727,
      "grad_norm": 0.31018415093421936,
      "learning_rate": 1.971062687126446e-05,
      "loss": 0.5543,
      "step": 5091
    },
    {
      "epoch": 0.15642183516112187,
      "grad_norm": 0.334972083568573,
      "learning_rate": 1.97105114413391e-05,
      "loss": 0.539,
      "step": 5092
    },
    {
      "epoch": 0.15645255429607102,
      "grad_norm": 0.36420905590057373,
      "learning_rate": 1.971039598873416e-05,
      "loss": 0.6469,
      "step": 5093
    },
    {
      "epoch": 0.15648327343102017,
      "grad_norm": 0.38430678844451904,
      "learning_rate": 1.971028051344991e-05,
      "loss": 0.5372,
      "step": 5094
    },
    {
      "epoch": 0.15651399256596935,
      "grad_norm": 0.39892882108688354,
      "learning_rate": 1.9710165015486623e-05,
      "loss": 0.6915,
      "step": 5095
    },
    {
      "epoch": 0.1565447117009185,
      "grad_norm": 0.3162928819656372,
      "learning_rate": 1.9710049494844566e-05,
      "loss": 0.5924,
      "step": 5096
    },
    {
      "epoch": 0.15657543083586767,
      "grad_norm": 0.3141995370388031,
      "learning_rate": 1.9709933951524012e-05,
      "loss": 0.6327,
      "step": 5097
    },
    {
      "epoch": 0.15660614997081682,
      "grad_norm": 0.3645155727863312,
      "learning_rate": 1.9709818385525228e-05,
      "loss": 0.4943,
      "step": 5098
    },
    {
      "epoch": 0.156636869105766,
      "grad_norm": 0.32271870970726013,
      "learning_rate": 1.9709702796848486e-05,
      "loss": 0.5524,
      "step": 5099
    },
    {
      "epoch": 0.15666758824071514,
      "grad_norm": 0.3616364300251007,
      "learning_rate": 1.9709587185494055e-05,
      "loss": 0.6197,
      "step": 5100
    },
    {
      "epoch": 0.15669830737566431,
      "grad_norm": 0.3578072786331177,
      "learning_rate": 1.970947155146221e-05,
      "loss": 0.5822,
      "step": 5101
    },
    {
      "epoch": 0.15672902651061346,
      "grad_norm": 0.2915003299713135,
      "learning_rate": 1.9709355894753206e-05,
      "loss": 0.587,
      "step": 5102
    },
    {
      "epoch": 0.1567597456455626,
      "grad_norm": 0.3141416609287262,
      "learning_rate": 1.970924021536733e-05,
      "loss": 0.5388,
      "step": 5103
    },
    {
      "epoch": 0.15679046478051178,
      "grad_norm": 0.35077422857284546,
      "learning_rate": 1.9709124513304842e-05,
      "loss": 0.6054,
      "step": 5104
    },
    {
      "epoch": 0.15682118391546093,
      "grad_norm": 0.3118748664855957,
      "learning_rate": 1.9709008788566016e-05,
      "loss": 0.5744,
      "step": 5105
    },
    {
      "epoch": 0.1568519030504101,
      "grad_norm": 0.3269415497779846,
      "learning_rate": 1.9708893041151125e-05,
      "loss": 0.5567,
      "step": 5106
    },
    {
      "epoch": 0.15688262218535926,
      "grad_norm": 0.3921496868133545,
      "learning_rate": 1.9708777271060434e-05,
      "loss": 0.5777,
      "step": 5107
    },
    {
      "epoch": 0.15691334132030843,
      "grad_norm": 0.3422585129737854,
      "learning_rate": 1.9708661478294216e-05,
      "loss": 0.5412,
      "step": 5108
    },
    {
      "epoch": 0.15694406045525758,
      "grad_norm": 0.3489620089530945,
      "learning_rate": 1.970854566285274e-05,
      "loss": 0.5813,
      "step": 5109
    },
    {
      "epoch": 0.15697477959020675,
      "grad_norm": 0.3350701332092285,
      "learning_rate": 1.970842982473628e-05,
      "loss": 0.6031,
      "step": 5110
    },
    {
      "epoch": 0.1570054987251559,
      "grad_norm": 0.36141687631607056,
      "learning_rate": 1.97083139639451e-05,
      "loss": 0.6232,
      "step": 5111
    },
    {
      "epoch": 0.15703621786010505,
      "grad_norm": 0.35578489303588867,
      "learning_rate": 1.970819808047948e-05,
      "loss": 0.6217,
      "step": 5112
    },
    {
      "epoch": 0.15706693699505422,
      "grad_norm": 0.3484112620353699,
      "learning_rate": 1.970808217433968e-05,
      "loss": 0.6598,
      "step": 5113
    },
    {
      "epoch": 0.15709765613000337,
      "grad_norm": 0.3109627664089203,
      "learning_rate": 1.970796624552598e-05,
      "loss": 0.5889,
      "step": 5114
    },
    {
      "epoch": 0.15712837526495255,
      "grad_norm": 0.3086998462677002,
      "learning_rate": 1.9707850294038646e-05,
      "loss": 0.6138,
      "step": 5115
    },
    {
      "epoch": 0.1571590943999017,
      "grad_norm": 0.36381208896636963,
      "learning_rate": 1.9707734319877948e-05,
      "loss": 0.6587,
      "step": 5116
    },
    {
      "epoch": 0.15718981353485087,
      "grad_norm": 0.36470386385917664,
      "learning_rate": 1.9707618323044163e-05,
      "loss": 0.6568,
      "step": 5117
    },
    {
      "epoch": 0.15722053266980002,
      "grad_norm": 0.3373723030090332,
      "learning_rate": 1.9707502303537553e-05,
      "loss": 0.4709,
      "step": 5118
    },
    {
      "epoch": 0.15725125180474916,
      "grad_norm": 0.33749860525131226,
      "learning_rate": 1.9707386261358394e-05,
      "loss": 0.5927,
      "step": 5119
    },
    {
      "epoch": 0.15728197093969834,
      "grad_norm": 1.1777713298797607,
      "learning_rate": 1.9707270196506956e-05,
      "loss": 0.6035,
      "step": 5120
    },
    {
      "epoch": 0.1573126900746475,
      "grad_norm": 0.29923778772354126,
      "learning_rate": 1.9707154108983512e-05,
      "loss": 0.5358,
      "step": 5121
    },
    {
      "epoch": 0.15734340920959666,
      "grad_norm": 0.30905428528785706,
      "learning_rate": 1.9707037998788333e-05,
      "loss": 0.5973,
      "step": 5122
    },
    {
      "epoch": 0.1573741283445458,
      "grad_norm": 0.5176726579666138,
      "learning_rate": 1.9706921865921687e-05,
      "loss": 0.5694,
      "step": 5123
    },
    {
      "epoch": 0.15740484747949499,
      "grad_norm": 0.3763086795806885,
      "learning_rate": 1.9706805710383845e-05,
      "loss": 0.659,
      "step": 5124
    },
    {
      "epoch": 0.15743556661444413,
      "grad_norm": 0.32315120100975037,
      "learning_rate": 1.9706689532175085e-05,
      "loss": 0.5902,
      "step": 5125
    },
    {
      "epoch": 0.1574662857493933,
      "grad_norm": 0.3604733943939209,
      "learning_rate": 1.9706573331295668e-05,
      "loss": 0.6004,
      "step": 5126
    },
    {
      "epoch": 0.15749700488434246,
      "grad_norm": 0.33654603362083435,
      "learning_rate": 1.9706457107745875e-05,
      "loss": 0.5894,
      "step": 5127
    },
    {
      "epoch": 0.1575277240192916,
      "grad_norm": 0.31940239667892456,
      "learning_rate": 1.9706340861525973e-05,
      "loss": 0.6127,
      "step": 5128
    },
    {
      "epoch": 0.15755844315424078,
      "grad_norm": 0.3555581867694855,
      "learning_rate": 1.9706224592636234e-05,
      "loss": 0.5403,
      "step": 5129
    },
    {
      "epoch": 0.15758916228918993,
      "grad_norm": 0.3392537236213684,
      "learning_rate": 1.9706108301076932e-05,
      "loss": 0.6875,
      "step": 5130
    },
    {
      "epoch": 0.1576198814241391,
      "grad_norm": 0.3268117308616638,
      "learning_rate": 1.970599198684833e-05,
      "loss": 0.6422,
      "step": 5131
    },
    {
      "epoch": 0.15765060055908825,
      "grad_norm": 0.3811015486717224,
      "learning_rate": 1.970587564995071e-05,
      "loss": 0.5602,
      "step": 5132
    },
    {
      "epoch": 0.15768131969403743,
      "grad_norm": 0.37915781140327454,
      "learning_rate": 1.970575929038434e-05,
      "loss": 0.5601,
      "step": 5133
    },
    {
      "epoch": 0.15771203882898657,
      "grad_norm": 0.3932828903198242,
      "learning_rate": 1.9705642908149493e-05,
      "loss": 0.6335,
      "step": 5134
    },
    {
      "epoch": 0.15774275796393575,
      "grad_norm": 0.3161843717098236,
      "learning_rate": 1.9705526503246432e-05,
      "loss": 0.627,
      "step": 5135
    },
    {
      "epoch": 0.1577734770988849,
      "grad_norm": 0.3467511236667633,
      "learning_rate": 1.970541007567544e-05,
      "loss": 0.6328,
      "step": 5136
    },
    {
      "epoch": 0.15780419623383404,
      "grad_norm": 0.34904566407203674,
      "learning_rate": 1.970529362543679e-05,
      "loss": 0.6308,
      "step": 5137
    },
    {
      "epoch": 0.15783491536878322,
      "grad_norm": 0.31158873438835144,
      "learning_rate": 1.9705177152530745e-05,
      "loss": 0.5902,
      "step": 5138
    },
    {
      "epoch": 0.15786563450373237,
      "grad_norm": 0.3390234410762787,
      "learning_rate": 1.9705060656957578e-05,
      "loss": 0.6838,
      "step": 5139
    },
    {
      "epoch": 0.15789635363868154,
      "grad_norm": 0.34048932790756226,
      "learning_rate": 1.9704944138717565e-05,
      "loss": 0.6215,
      "step": 5140
    },
    {
      "epoch": 0.1579270727736307,
      "grad_norm": 0.30955857038497925,
      "learning_rate": 1.9704827597810977e-05,
      "loss": 0.635,
      "step": 5141
    },
    {
      "epoch": 0.15795779190857986,
      "grad_norm": 0.36451244354248047,
      "learning_rate": 1.970471103423809e-05,
      "loss": 0.6074,
      "step": 5142
    },
    {
      "epoch": 0.157988511043529,
      "grad_norm": 0.5044623017311096,
      "learning_rate": 1.970459444799917e-05,
      "loss": 0.6485,
      "step": 5143
    },
    {
      "epoch": 0.1580192301784782,
      "grad_norm": 0.3349839150905609,
      "learning_rate": 1.9704477839094495e-05,
      "loss": 0.5895,
      "step": 5144
    },
    {
      "epoch": 0.15804994931342733,
      "grad_norm": 0.3308391273021698,
      "learning_rate": 1.970436120752433e-05,
      "loss": 0.6138,
      "step": 5145
    },
    {
      "epoch": 0.15808066844837648,
      "grad_norm": 0.3300028443336487,
      "learning_rate": 1.9704244553288952e-05,
      "loss": 0.6453,
      "step": 5146
    },
    {
      "epoch": 0.15811138758332566,
      "grad_norm": 0.3379002809524536,
      "learning_rate": 1.9704127876388636e-05,
      "loss": 0.5822,
      "step": 5147
    },
    {
      "epoch": 0.1581421067182748,
      "grad_norm": 0.39057376980781555,
      "learning_rate": 1.970401117682365e-05,
      "loss": 0.651,
      "step": 5148
    },
    {
      "epoch": 0.15817282585322398,
      "grad_norm": 0.3065847158432007,
      "learning_rate": 1.9703894454594268e-05,
      "loss": 0.5743,
      "step": 5149
    },
    {
      "epoch": 0.15820354498817313,
      "grad_norm": 0.3382980227470398,
      "learning_rate": 1.9703777709700764e-05,
      "loss": 0.5844,
      "step": 5150
    },
    {
      "epoch": 0.1582342641231223,
      "grad_norm": 0.36961451172828674,
      "learning_rate": 1.9703660942143407e-05,
      "loss": 0.6351,
      "step": 5151
    },
    {
      "epoch": 0.15826498325807145,
      "grad_norm": 0.3272973597049713,
      "learning_rate": 1.9703544151922473e-05,
      "loss": 0.5643,
      "step": 5152
    },
    {
      "epoch": 0.15829570239302063,
      "grad_norm": 0.3178774118423462,
      "learning_rate": 1.9703427339038238e-05,
      "loss": 0.5442,
      "step": 5153
    },
    {
      "epoch": 0.15832642152796977,
      "grad_norm": 0.33646345138549805,
      "learning_rate": 1.9703310503490965e-05,
      "loss": 0.5512,
      "step": 5154
    },
    {
      "epoch": 0.15835714066291892,
      "grad_norm": 0.3227737247943878,
      "learning_rate": 1.9703193645280936e-05,
      "loss": 0.5735,
      "step": 5155
    },
    {
      "epoch": 0.1583878597978681,
      "grad_norm": 0.357884019613266,
      "learning_rate": 1.970307676440842e-05,
      "loss": 0.5542,
      "step": 5156
    },
    {
      "epoch": 0.15841857893281724,
      "grad_norm": 0.35693418979644775,
      "learning_rate": 1.9702959860873688e-05,
      "loss": 0.6174,
      "step": 5157
    },
    {
      "epoch": 0.15844929806776642,
      "grad_norm": 0.30237433314323425,
      "learning_rate": 1.9702842934677017e-05,
      "loss": 0.6371,
      "step": 5158
    },
    {
      "epoch": 0.15848001720271557,
      "grad_norm": 0.34544384479522705,
      "learning_rate": 1.970272598581868e-05,
      "loss": 0.566,
      "step": 5159
    },
    {
      "epoch": 0.15851073633766474,
      "grad_norm": 0.5389071702957153,
      "learning_rate": 1.970260901429895e-05,
      "loss": 0.6852,
      "step": 5160
    },
    {
      "epoch": 0.1585414554726139,
      "grad_norm": 0.35351991653442383,
      "learning_rate": 1.9702492020118098e-05,
      "loss": 0.597,
      "step": 5161
    },
    {
      "epoch": 0.15857217460756304,
      "grad_norm": 0.2935900390148163,
      "learning_rate": 1.9702375003276396e-05,
      "loss": 0.5487,
      "step": 5162
    },
    {
      "epoch": 0.1586028937425122,
      "grad_norm": 0.3843997120857239,
      "learning_rate": 1.9702257963774123e-05,
      "loss": 0.5173,
      "step": 5163
    },
    {
      "epoch": 0.15863361287746136,
      "grad_norm": 0.3258801996707916,
      "learning_rate": 1.9702140901611547e-05,
      "loss": 0.5648,
      "step": 5164
    },
    {
      "epoch": 0.15866433201241054,
      "grad_norm": 0.3837225139141083,
      "learning_rate": 1.9702023816788943e-05,
      "loss": 0.5596,
      "step": 5165
    },
    {
      "epoch": 0.15869505114735968,
      "grad_norm": 0.33142024278640747,
      "learning_rate": 1.9701906709306584e-05,
      "loss": 0.6292,
      "step": 5166
    },
    {
      "epoch": 0.15872577028230886,
      "grad_norm": 0.34624502062797546,
      "learning_rate": 1.9701789579164746e-05,
      "loss": 0.6918,
      "step": 5167
    },
    {
      "epoch": 0.158756489417258,
      "grad_norm": 0.3280618190765381,
      "learning_rate": 1.9701672426363702e-05,
      "loss": 0.5754,
      "step": 5168
    },
    {
      "epoch": 0.15878720855220718,
      "grad_norm": 0.34918448328971863,
      "learning_rate": 1.9701555250903724e-05,
      "loss": 0.6759,
      "step": 5169
    },
    {
      "epoch": 0.15881792768715633,
      "grad_norm": 0.3929654061794281,
      "learning_rate": 1.9701438052785082e-05,
      "loss": 0.5321,
      "step": 5170
    },
    {
      "epoch": 0.15884864682210548,
      "grad_norm": 0.3324804902076721,
      "learning_rate": 1.970132083200806e-05,
      "loss": 0.6444,
      "step": 5171
    },
    {
      "epoch": 0.15887936595705465,
      "grad_norm": 0.32850444316864014,
      "learning_rate": 1.970120358857292e-05,
      "loss": 0.594,
      "step": 5172
    },
    {
      "epoch": 0.1589100850920038,
      "grad_norm": 0.347822904586792,
      "learning_rate": 1.9701086322479943e-05,
      "loss": 0.7273,
      "step": 5173
    },
    {
      "epoch": 0.15894080422695298,
      "grad_norm": 0.3416129946708679,
      "learning_rate": 1.9700969033729406e-05,
      "loss": 0.5489,
      "step": 5174
    },
    {
      "epoch": 0.15897152336190212,
      "grad_norm": 0.3403720557689667,
      "learning_rate": 1.970085172232157e-05,
      "loss": 0.5663,
      "step": 5175
    },
    {
      "epoch": 0.1590022424968513,
      "grad_norm": 0.3209337592124939,
      "learning_rate": 1.9700734388256727e-05,
      "loss": 0.5954,
      "step": 5176
    },
    {
      "epoch": 0.15903296163180045,
      "grad_norm": 0.3270992934703827,
      "learning_rate": 1.9700617031535134e-05,
      "loss": 0.5603,
      "step": 5177
    },
    {
      "epoch": 0.15906368076674962,
      "grad_norm": 0.31808924674987793,
      "learning_rate": 1.9700499652157076e-05,
      "loss": 0.6405,
      "step": 5178
    },
    {
      "epoch": 0.15909439990169877,
      "grad_norm": 0.33045193552970886,
      "learning_rate": 1.970038225012282e-05,
      "loss": 0.5658,
      "step": 5179
    },
    {
      "epoch": 0.15912511903664792,
      "grad_norm": 0.3482549488544464,
      "learning_rate": 1.9700264825432648e-05,
      "loss": 0.6767,
      "step": 5180
    },
    {
      "epoch": 0.1591558381715971,
      "grad_norm": 0.4217830002307892,
      "learning_rate": 1.970014737808683e-05,
      "loss": 0.6136,
      "step": 5181
    },
    {
      "epoch": 0.15918655730654624,
      "grad_norm": 0.3292510211467743,
      "learning_rate": 1.970002990808564e-05,
      "loss": 0.501,
      "step": 5182
    },
    {
      "epoch": 0.15921727644149541,
      "grad_norm": 0.36666372418403625,
      "learning_rate": 1.969991241542935e-05,
      "loss": 0.538,
      "step": 5183
    },
    {
      "epoch": 0.15924799557644456,
      "grad_norm": 0.3636276423931122,
      "learning_rate": 1.9699794900118238e-05,
      "loss": 0.6474,
      "step": 5184
    },
    {
      "epoch": 0.15927871471139374,
      "grad_norm": 0.344793438911438,
      "learning_rate": 1.969967736215258e-05,
      "loss": 0.6585,
      "step": 5185
    },
    {
      "epoch": 0.15930943384634288,
      "grad_norm": 0.33774876594543457,
      "learning_rate": 1.9699559801532643e-05,
      "loss": 0.7183,
      "step": 5186
    },
    {
      "epoch": 0.15934015298129206,
      "grad_norm": 0.37210583686828613,
      "learning_rate": 1.969944221825871e-05,
      "loss": 0.5378,
      "step": 5187
    },
    {
      "epoch": 0.1593708721162412,
      "grad_norm": 0.3302317261695862,
      "learning_rate": 1.9699324612331053e-05,
      "loss": 0.5836,
      "step": 5188
    },
    {
      "epoch": 0.15940159125119036,
      "grad_norm": 0.32586872577667236,
      "learning_rate": 1.9699206983749946e-05,
      "loss": 0.5532,
      "step": 5189
    },
    {
      "epoch": 0.15943231038613953,
      "grad_norm": 0.32500937581062317,
      "learning_rate": 1.969908933251566e-05,
      "loss": 0.6612,
      "step": 5190
    },
    {
      "epoch": 0.15946302952108868,
      "grad_norm": 0.3125622570514679,
      "learning_rate": 1.9698971658628476e-05,
      "loss": 0.543,
      "step": 5191
    },
    {
      "epoch": 0.15949374865603785,
      "grad_norm": 0.30098849534988403,
      "learning_rate": 1.969885396208867e-05,
      "loss": 0.5245,
      "step": 5192
    },
    {
      "epoch": 0.159524467790987,
      "grad_norm": 0.35671812295913696,
      "learning_rate": 1.9698736242896506e-05,
      "loss": 0.6387,
      "step": 5193
    },
    {
      "epoch": 0.15955518692593618,
      "grad_norm": 0.3325496017932892,
      "learning_rate": 1.969861850105227e-05,
      "loss": 0.647,
      "step": 5194
    },
    {
      "epoch": 0.15958590606088532,
      "grad_norm": 0.37960296869277954,
      "learning_rate": 1.9698500736556237e-05,
      "loss": 0.638,
      "step": 5195
    },
    {
      "epoch": 0.15961662519583447,
      "grad_norm": 0.37326857447624207,
      "learning_rate": 1.969838294940867e-05,
      "loss": 0.6183,
      "step": 5196
    },
    {
      "epoch": 0.15964734433078365,
      "grad_norm": 0.3570660650730133,
      "learning_rate": 1.969826513960986e-05,
      "loss": 0.5941,
      "step": 5197
    },
    {
      "epoch": 0.1596780634657328,
      "grad_norm": 0.35007134079933167,
      "learning_rate": 1.9698147307160068e-05,
      "loss": 0.682,
      "step": 5198
    },
    {
      "epoch": 0.15970878260068197,
      "grad_norm": 0.3070717751979828,
      "learning_rate": 1.9698029452059583e-05,
      "loss": 0.6004,
      "step": 5199
    },
    {
      "epoch": 0.15973950173563112,
      "grad_norm": 0.3476990759372711,
      "learning_rate": 1.9697911574308667e-05,
      "loss": 0.67,
      "step": 5200
    },
    {
      "epoch": 0.1597702208705803,
      "grad_norm": 0.31259071826934814,
      "learning_rate": 1.9697793673907603e-05,
      "loss": 0.6478,
      "step": 5201
    },
    {
      "epoch": 0.15980094000552944,
      "grad_norm": 0.3569611608982086,
      "learning_rate": 1.9697675750856664e-05,
      "loss": 0.6071,
      "step": 5202
    },
    {
      "epoch": 0.15983165914047862,
      "grad_norm": 0.3261544704437256,
      "learning_rate": 1.9697557805156128e-05,
      "loss": 0.5586,
      "step": 5203
    },
    {
      "epoch": 0.15986237827542776,
      "grad_norm": 0.3263084590435028,
      "learning_rate": 1.9697439836806267e-05,
      "loss": 0.5498,
      "step": 5204
    },
    {
      "epoch": 0.1598930974103769,
      "grad_norm": 0.37663936614990234,
      "learning_rate": 1.9697321845807358e-05,
      "loss": 0.6367,
      "step": 5205
    },
    {
      "epoch": 0.1599238165453261,
      "grad_norm": 0.3402377963066101,
      "learning_rate": 1.9697203832159675e-05,
      "loss": 0.5698,
      "step": 5206
    },
    {
      "epoch": 0.15995453568027523,
      "grad_norm": 0.3652283251285553,
      "learning_rate": 1.9697085795863494e-05,
      "loss": 0.6567,
      "step": 5207
    },
    {
      "epoch": 0.1599852548152244,
      "grad_norm": 0.3536292314529419,
      "learning_rate": 1.9696967736919095e-05,
      "loss": 0.6023,
      "step": 5208
    },
    {
      "epoch": 0.16001597395017356,
      "grad_norm": 0.3380635976791382,
      "learning_rate": 1.9696849655326753e-05,
      "loss": 0.5804,
      "step": 5209
    },
    {
      "epoch": 0.16004669308512273,
      "grad_norm": 0.32408276200294495,
      "learning_rate": 1.969673155108674e-05,
      "loss": 0.5797,
      "step": 5210
    },
    {
      "epoch": 0.16007741222007188,
      "grad_norm": 0.40607455372810364,
      "learning_rate": 1.969661342419933e-05,
      "loss": 0.6235,
      "step": 5211
    },
    {
      "epoch": 0.16010813135502105,
      "grad_norm": 0.31204289197921753,
      "learning_rate": 1.9696495274664805e-05,
      "loss": 0.5893,
      "step": 5212
    },
    {
      "epoch": 0.1601388504899702,
      "grad_norm": 0.31977295875549316,
      "learning_rate": 1.9696377102483435e-05,
      "loss": 0.6201,
      "step": 5213
    },
    {
      "epoch": 0.16016956962491935,
      "grad_norm": 0.40177756547927856,
      "learning_rate": 1.96962589076555e-05,
      "loss": 0.6806,
      "step": 5214
    },
    {
      "epoch": 0.16020028875986853,
      "grad_norm": 0.3245067000389099,
      "learning_rate": 1.969614069018128e-05,
      "loss": 0.5598,
      "step": 5215
    },
    {
      "epoch": 0.16023100789481767,
      "grad_norm": 0.3404003083705902,
      "learning_rate": 1.9696022450061042e-05,
      "loss": 0.5933,
      "step": 5216
    },
    {
      "epoch": 0.16026172702976685,
      "grad_norm": 0.36772772669792175,
      "learning_rate": 1.9695904187295065e-05,
      "loss": 0.6136,
      "step": 5217
    },
    {
      "epoch": 0.160292446164716,
      "grad_norm": 0.3485218286514282,
      "learning_rate": 1.969578590188363e-05,
      "loss": 0.6708,
      "step": 5218
    },
    {
      "epoch": 0.16032316529966517,
      "grad_norm": 0.34387528896331787,
      "learning_rate": 1.9695667593827008e-05,
      "loss": 0.5947,
      "step": 5219
    },
    {
      "epoch": 0.16035388443461432,
      "grad_norm": 0.31417205929756165,
      "learning_rate": 1.9695549263125478e-05,
      "loss": 0.5538,
      "step": 5220
    },
    {
      "epoch": 0.1603846035695635,
      "grad_norm": 0.3125837445259094,
      "learning_rate": 1.9695430909779315e-05,
      "loss": 0.5514,
      "step": 5221
    },
    {
      "epoch": 0.16041532270451264,
      "grad_norm": 0.31472256779670715,
      "learning_rate": 1.9695312533788797e-05,
      "loss": 0.6102,
      "step": 5222
    },
    {
      "epoch": 0.1604460418394618,
      "grad_norm": 0.3471154272556305,
      "learning_rate": 1.9695194135154198e-05,
      "loss": 0.5869,
      "step": 5223
    },
    {
      "epoch": 0.16047676097441096,
      "grad_norm": 0.3256840705871582,
      "learning_rate": 1.96950757138758e-05,
      "loss": 0.5688,
      "step": 5224
    },
    {
      "epoch": 0.1605074801093601,
      "grad_norm": 0.40161705017089844,
      "learning_rate": 1.969495726995387e-05,
      "loss": 0.5926,
      "step": 5225
    },
    {
      "epoch": 0.1605381992443093,
      "grad_norm": 0.31321895122528076,
      "learning_rate": 1.969483880338869e-05,
      "loss": 0.5618,
      "step": 5226
    },
    {
      "epoch": 0.16056891837925844,
      "grad_norm": 0.3343587815761566,
      "learning_rate": 1.9694720314180544e-05,
      "loss": 0.587,
      "step": 5227
    },
    {
      "epoch": 0.1605996375142076,
      "grad_norm": 0.3324110507965088,
      "learning_rate": 1.9694601802329695e-05,
      "loss": 0.5383,
      "step": 5228
    },
    {
      "epoch": 0.16063035664915676,
      "grad_norm": 0.3130726218223572,
      "learning_rate": 1.969448326783643e-05,
      "loss": 0.5457,
      "step": 5229
    },
    {
      "epoch": 0.16066107578410593,
      "grad_norm": 0.3425898253917694,
      "learning_rate": 1.9694364710701016e-05,
      "loss": 0.6507,
      "step": 5230
    },
    {
      "epoch": 0.16069179491905508,
      "grad_norm": 0.3453551232814789,
      "learning_rate": 1.9694246130923746e-05,
      "loss": 0.6408,
      "step": 5231
    },
    {
      "epoch": 0.16072251405400423,
      "grad_norm": 0.32624587416648865,
      "learning_rate": 1.969412752850488e-05,
      "loss": 0.6749,
      "step": 5232
    },
    {
      "epoch": 0.1607532331889534,
      "grad_norm": 0.328003466129303,
      "learning_rate": 1.9694008903444705e-05,
      "loss": 0.6267,
      "step": 5233
    },
    {
      "epoch": 0.16078395232390255,
      "grad_norm": 0.3431280553340912,
      "learning_rate": 1.9693890255743493e-05,
      "loss": 0.5572,
      "step": 5234
    },
    {
      "epoch": 0.16081467145885173,
      "grad_norm": 0.3098984956741333,
      "learning_rate": 1.9693771585401524e-05,
      "loss": 0.6087,
      "step": 5235
    },
    {
      "epoch": 0.16084539059380087,
      "grad_norm": 0.333173930644989,
      "learning_rate": 1.9693652892419076e-05,
      "loss": 0.6089,
      "step": 5236
    },
    {
      "epoch": 0.16087610972875005,
      "grad_norm": 0.32636842131614685,
      "learning_rate": 1.9693534176796423e-05,
      "loss": 0.5653,
      "step": 5237
    },
    {
      "epoch": 0.1609068288636992,
      "grad_norm": 0.4108021557331085,
      "learning_rate": 1.9693415438533844e-05,
      "loss": 0.5422,
      "step": 5238
    },
    {
      "epoch": 0.16093754799864834,
      "grad_norm": 0.3470809757709503,
      "learning_rate": 1.969329667763162e-05,
      "loss": 0.6326,
      "step": 5239
    },
    {
      "epoch": 0.16096826713359752,
      "grad_norm": 0.3575906753540039,
      "learning_rate": 1.9693177894090022e-05,
      "loss": 0.559,
      "step": 5240
    },
    {
      "epoch": 0.16099898626854667,
      "grad_norm": 0.3617265820503235,
      "learning_rate": 1.969305908790933e-05,
      "loss": 0.5868,
      "step": 5241
    },
    {
      "epoch": 0.16102970540349584,
      "grad_norm": 0.3126714825630188,
      "learning_rate": 1.969294025908982e-05,
      "loss": 0.5321,
      "step": 5242
    },
    {
      "epoch": 0.161060424538445,
      "grad_norm": 0.34919944405555725,
      "learning_rate": 1.969282140763177e-05,
      "loss": 0.5749,
      "step": 5243
    },
    {
      "epoch": 0.16109114367339417,
      "grad_norm": 0.30407243967056274,
      "learning_rate": 1.9692702533535463e-05,
      "loss": 0.5066,
      "step": 5244
    },
    {
      "epoch": 0.1611218628083433,
      "grad_norm": 0.33554431796073914,
      "learning_rate": 1.9692583636801167e-05,
      "loss": 0.6208,
      "step": 5245
    },
    {
      "epoch": 0.1611525819432925,
      "grad_norm": 0.3609890043735504,
      "learning_rate": 1.969246471742917e-05,
      "loss": 0.5412,
      "step": 5246
    },
    {
      "epoch": 0.16118330107824164,
      "grad_norm": 0.37021157145500183,
      "learning_rate": 1.9692345775419745e-05,
      "loss": 0.6252,
      "step": 5247
    },
    {
      "epoch": 0.16121402021319078,
      "grad_norm": 0.32604336738586426,
      "learning_rate": 1.9692226810773166e-05,
      "loss": 0.6503,
      "step": 5248
    },
    {
      "epoch": 0.16124473934813996,
      "grad_norm": 0.31392809748649597,
      "learning_rate": 1.9692107823489714e-05,
      "loss": 0.5369,
      "step": 5249
    },
    {
      "epoch": 0.1612754584830891,
      "grad_norm": 0.3235829472541809,
      "learning_rate": 1.969198881356967e-05,
      "loss": 0.5472,
      "step": 5250
    },
    {
      "epoch": 0.16130617761803828,
      "grad_norm": 0.34102678298950195,
      "learning_rate": 1.9691869781013308e-05,
      "loss": 0.6374,
      "step": 5251
    },
    {
      "epoch": 0.16133689675298743,
      "grad_norm": 0.3147267997264862,
      "learning_rate": 1.969175072582091e-05,
      "loss": 0.6006,
      "step": 5252
    },
    {
      "epoch": 0.1613676158879366,
      "grad_norm": 0.3273099362850189,
      "learning_rate": 1.969163164799275e-05,
      "loss": 0.6422,
      "step": 5253
    },
    {
      "epoch": 0.16139833502288575,
      "grad_norm": 0.37581002712249756,
      "learning_rate": 1.9691512547529106e-05,
      "loss": 0.6048,
      "step": 5254
    },
    {
      "epoch": 0.16142905415783493,
      "grad_norm": 0.3420572578907013,
      "learning_rate": 1.9691393424430256e-05,
      "loss": 0.5918,
      "step": 5255
    },
    {
      "epoch": 0.16145977329278408,
      "grad_norm": 0.3604351580142975,
      "learning_rate": 1.969127427869648e-05,
      "loss": 0.5722,
      "step": 5256
    },
    {
      "epoch": 0.16149049242773322,
      "grad_norm": 0.39591073989868164,
      "learning_rate": 1.969115511032806e-05,
      "loss": 0.6721,
      "step": 5257
    },
    {
      "epoch": 0.1615212115626824,
      "grad_norm": 0.3498663604259491,
      "learning_rate": 1.969103591932527e-05,
      "loss": 0.5485,
      "step": 5258
    },
    {
      "epoch": 0.16155193069763155,
      "grad_norm": 0.35169386863708496,
      "learning_rate": 1.9690916705688385e-05,
      "loss": 0.5314,
      "step": 5259
    },
    {
      "epoch": 0.16158264983258072,
      "grad_norm": 0.3233790695667267,
      "learning_rate": 1.969079746941769e-05,
      "loss": 0.5882,
      "step": 5260
    },
    {
      "epoch": 0.16161336896752987,
      "grad_norm": 0.3261513411998749,
      "learning_rate": 1.9690678210513462e-05,
      "loss": 0.5039,
      "step": 5261
    },
    {
      "epoch": 0.16164408810247904,
      "grad_norm": 0.32704079151153564,
      "learning_rate": 1.9690558928975974e-05,
      "loss": 0.5915,
      "step": 5262
    },
    {
      "epoch": 0.1616748072374282,
      "grad_norm": 0.321974515914917,
      "learning_rate": 1.9690439624805512e-05,
      "loss": 0.6081,
      "step": 5263
    },
    {
      "epoch": 0.16170552637237737,
      "grad_norm": 0.35222843289375305,
      "learning_rate": 1.969032029800235e-05,
      "loss": 0.5861,
      "step": 5264
    },
    {
      "epoch": 0.16173624550732651,
      "grad_norm": 0.3516051173210144,
      "learning_rate": 1.969020094856677e-05,
      "loss": 0.6016,
      "step": 5265
    },
    {
      "epoch": 0.16176696464227566,
      "grad_norm": 0.39189010858535767,
      "learning_rate": 1.9690081576499048e-05,
      "loss": 0.5806,
      "step": 5266
    },
    {
      "epoch": 0.16179768377722484,
      "grad_norm": 0.33755064010620117,
      "learning_rate": 1.9689962181799463e-05,
      "loss": 0.577,
      "step": 5267
    },
    {
      "epoch": 0.16182840291217399,
      "grad_norm": 0.3604521155357361,
      "learning_rate": 1.9689842764468293e-05,
      "loss": 0.651,
      "step": 5268
    },
    {
      "epoch": 0.16185912204712316,
      "grad_norm": 0.3424067497253418,
      "learning_rate": 1.9689723324505822e-05,
      "loss": 0.5492,
      "step": 5269
    },
    {
      "epoch": 0.1618898411820723,
      "grad_norm": 0.357449471950531,
      "learning_rate": 1.9689603861912325e-05,
      "loss": 0.5656,
      "step": 5270
    },
    {
      "epoch": 0.16192056031702148,
      "grad_norm": 0.3356103003025055,
      "learning_rate": 1.968948437668808e-05,
      "loss": 0.6312,
      "step": 5271
    },
    {
      "epoch": 0.16195127945197063,
      "grad_norm": 0.3489040434360504,
      "learning_rate": 1.9689364868833366e-05,
      "loss": 0.6335,
      "step": 5272
    },
    {
      "epoch": 0.16198199858691978,
      "grad_norm": 0.3454354405403137,
      "learning_rate": 1.9689245338348467e-05,
      "loss": 0.5801,
      "step": 5273
    },
    {
      "epoch": 0.16201271772186895,
      "grad_norm": 0.6527231931686401,
      "learning_rate": 1.9689125785233657e-05,
      "loss": 0.6563,
      "step": 5274
    },
    {
      "epoch": 0.1620434368568181,
      "grad_norm": 0.35746994614601135,
      "learning_rate": 1.968900620948922e-05,
      "loss": 0.6738,
      "step": 5275
    },
    {
      "epoch": 0.16207415599176728,
      "grad_norm": 0.3397464156150818,
      "learning_rate": 1.968888661111543e-05,
      "loss": 0.6318,
      "step": 5276
    },
    {
      "epoch": 0.16210487512671642,
      "grad_norm": 0.3128187656402588,
      "learning_rate": 1.9688766990112567e-05,
      "loss": 0.5682,
      "step": 5277
    },
    {
      "epoch": 0.1621355942616656,
      "grad_norm": 0.3579995036125183,
      "learning_rate": 1.9688647346480913e-05,
      "loss": 0.6502,
      "step": 5278
    },
    {
      "epoch": 0.16216631339661475,
      "grad_norm": 0.31388410925865173,
      "learning_rate": 1.968852768022075e-05,
      "loss": 0.5634,
      "step": 5279
    },
    {
      "epoch": 0.16219703253156392,
      "grad_norm": 0.4248453378677368,
      "learning_rate": 1.968840799133235e-05,
      "loss": 0.5504,
      "step": 5280
    },
    {
      "epoch": 0.16222775166651307,
      "grad_norm": 0.393790602684021,
      "learning_rate": 1.9688288279815996e-05,
      "loss": 0.6433,
      "step": 5281
    },
    {
      "epoch": 0.16225847080146222,
      "grad_norm": 0.3591558039188385,
      "learning_rate": 1.9688168545671972e-05,
      "loss": 0.6283,
      "step": 5282
    },
    {
      "epoch": 0.1622891899364114,
      "grad_norm": 0.4068864583969116,
      "learning_rate": 1.9688048788900547e-05,
      "loss": 0.5808,
      "step": 5283
    },
    {
      "epoch": 0.16231990907136054,
      "grad_norm": 0.35760825872421265,
      "learning_rate": 1.9687929009502013e-05,
      "loss": 0.5443,
      "step": 5284
    },
    {
      "epoch": 0.16235062820630972,
      "grad_norm": 0.34620776772499084,
      "learning_rate": 1.9687809207476644e-05,
      "loss": 0.6164,
      "step": 5285
    },
    {
      "epoch": 0.16238134734125886,
      "grad_norm": 0.3223918378353119,
      "learning_rate": 1.968768938282472e-05,
      "loss": 0.6362,
      "step": 5286
    },
    {
      "epoch": 0.16241206647620804,
      "grad_norm": 0.3275776505470276,
      "learning_rate": 1.9687569535546518e-05,
      "loss": 0.6025,
      "step": 5287
    },
    {
      "epoch": 0.1624427856111572,
      "grad_norm": 0.36523669958114624,
      "learning_rate": 1.9687449665642324e-05,
      "loss": 0.6503,
      "step": 5288
    },
    {
      "epoch": 0.16247350474610636,
      "grad_norm": 0.3069891929626465,
      "learning_rate": 1.9687329773112412e-05,
      "loss": 0.5954,
      "step": 5289
    },
    {
      "epoch": 0.1625042238810555,
      "grad_norm": 0.3452269732952118,
      "learning_rate": 1.9687209857957068e-05,
      "loss": 0.6042,
      "step": 5290
    },
    {
      "epoch": 0.16253494301600466,
      "grad_norm": 0.33941105008125305,
      "learning_rate": 1.9687089920176566e-05,
      "loss": 0.5673,
      "step": 5291
    },
    {
      "epoch": 0.16256566215095383,
      "grad_norm": 0.3286815285682678,
      "learning_rate": 1.968696995977119e-05,
      "loss": 0.6643,
      "step": 5292
    },
    {
      "epoch": 0.16259638128590298,
      "grad_norm": 0.3441813886165619,
      "learning_rate": 1.9686849976741217e-05,
      "loss": 0.5481,
      "step": 5293
    },
    {
      "epoch": 0.16262710042085216,
      "grad_norm": 0.3541944622993469,
      "learning_rate": 1.9686729971086935e-05,
      "loss": 0.529,
      "step": 5294
    },
    {
      "epoch": 0.1626578195558013,
      "grad_norm": 0.52463299036026,
      "learning_rate": 1.9686609942808613e-05,
      "loss": 0.6299,
      "step": 5295
    },
    {
      "epoch": 0.16268853869075048,
      "grad_norm": 0.3742150068283081,
      "learning_rate": 1.968648989190654e-05,
      "loss": 0.6135,
      "step": 5296
    },
    {
      "epoch": 0.16271925782569963,
      "grad_norm": 0.3055885136127472,
      "learning_rate": 1.9686369818380994e-05,
      "loss": 0.5655,
      "step": 5297
    },
    {
      "epoch": 0.1627499769606488,
      "grad_norm": 0.4754386246204376,
      "learning_rate": 1.9686249722232253e-05,
      "loss": 0.6414,
      "step": 5298
    },
    {
      "epoch": 0.16278069609559795,
      "grad_norm": 0.3428970277309418,
      "learning_rate": 1.96861296034606e-05,
      "loss": 0.6113,
      "step": 5299
    },
    {
      "epoch": 0.1628114152305471,
      "grad_norm": 0.3269561529159546,
      "learning_rate": 1.9686009462066314e-05,
      "loss": 0.6106,
      "step": 5300
    },
    {
      "epoch": 0.16284213436549627,
      "grad_norm": 0.32629409432411194,
      "learning_rate": 1.9685889298049675e-05,
      "loss": 0.5803,
      "step": 5301
    },
    {
      "epoch": 0.16287285350044542,
      "grad_norm": 0.39829862117767334,
      "learning_rate": 1.9685769111410968e-05,
      "loss": 0.5574,
      "step": 5302
    },
    {
      "epoch": 0.1629035726353946,
      "grad_norm": 0.3965721130371094,
      "learning_rate": 1.968564890215047e-05,
      "loss": 0.5197,
      "step": 5303
    },
    {
      "epoch": 0.16293429177034374,
      "grad_norm": 0.3512623906135559,
      "learning_rate": 1.968552867026846e-05,
      "loss": 0.6745,
      "step": 5304
    },
    {
      "epoch": 0.16296501090529292,
      "grad_norm": 0.36277469992637634,
      "learning_rate": 1.9685408415765222e-05,
      "loss": 0.6313,
      "step": 5305
    },
    {
      "epoch": 0.16299573004024207,
      "grad_norm": 0.32855215668678284,
      "learning_rate": 1.968528813864104e-05,
      "loss": 0.5459,
      "step": 5306
    },
    {
      "epoch": 0.16302644917519124,
      "grad_norm": 0.4192831814289093,
      "learning_rate": 1.968516783889619e-05,
      "loss": 0.5718,
      "step": 5307
    },
    {
      "epoch": 0.1630571683101404,
      "grad_norm": 0.35166653990745544,
      "learning_rate": 1.9685047516530955e-05,
      "loss": 0.564,
      "step": 5308
    },
    {
      "epoch": 0.16308788744508954,
      "grad_norm": 0.3353976607322693,
      "learning_rate": 1.968492717154561e-05,
      "loss": 0.4826,
      "step": 5309
    },
    {
      "epoch": 0.1631186065800387,
      "grad_norm": 0.3151121735572815,
      "learning_rate": 1.9684806803940442e-05,
      "loss": 0.6614,
      "step": 5310
    },
    {
      "epoch": 0.16314932571498786,
      "grad_norm": 0.37897735834121704,
      "learning_rate": 1.9684686413715736e-05,
      "loss": 0.6307,
      "step": 5311
    },
    {
      "epoch": 0.16318004484993703,
      "grad_norm": 0.35527166724205017,
      "learning_rate": 1.9684566000871768e-05,
      "loss": 0.6225,
      "step": 5312
    },
    {
      "epoch": 0.16321076398488618,
      "grad_norm": 0.32356253266334534,
      "learning_rate": 1.9684445565408818e-05,
      "loss": 0.5813,
      "step": 5313
    },
    {
      "epoch": 0.16324148311983536,
      "grad_norm": 0.32807084918022156,
      "learning_rate": 1.9684325107327168e-05,
      "loss": 0.5394,
      "step": 5314
    },
    {
      "epoch": 0.1632722022547845,
      "grad_norm": 0.33022332191467285,
      "learning_rate": 1.96842046266271e-05,
      "loss": 0.5257,
      "step": 5315
    },
    {
      "epoch": 0.16330292138973365,
      "grad_norm": 0.34857019782066345,
      "learning_rate": 1.9684084123308898e-05,
      "loss": 0.6127,
      "step": 5316
    },
    {
      "epoch": 0.16333364052468283,
      "grad_norm": 0.36707398295402527,
      "learning_rate": 1.968396359737284e-05,
      "loss": 0.5762,
      "step": 5317
    },
    {
      "epoch": 0.16336435965963197,
      "grad_norm": 0.3125094175338745,
      "learning_rate": 1.9683843048819212e-05,
      "loss": 0.5887,
      "step": 5318
    },
    {
      "epoch": 0.16339507879458115,
      "grad_norm": 0.330702006816864,
      "learning_rate": 1.968372247764829e-05,
      "loss": 0.6494,
      "step": 5319
    },
    {
      "epoch": 0.1634257979295303,
      "grad_norm": 0.3455737829208374,
      "learning_rate": 1.9683601883860356e-05,
      "loss": 0.5347,
      "step": 5320
    },
    {
      "epoch": 0.16345651706447947,
      "grad_norm": 0.5314297676086426,
      "learning_rate": 1.968348126745569e-05,
      "loss": 0.562,
      "step": 5321
    },
    {
      "epoch": 0.16348723619942862,
      "grad_norm": 0.34794801473617554,
      "learning_rate": 1.9683360628434583e-05,
      "loss": 0.606,
      "step": 5322
    },
    {
      "epoch": 0.1635179553343778,
      "grad_norm": 0.3585067689418793,
      "learning_rate": 1.9683239966797312e-05,
      "loss": 0.6376,
      "step": 5323
    },
    {
      "epoch": 0.16354867446932694,
      "grad_norm": 0.36627197265625,
      "learning_rate": 1.9683119282544157e-05,
      "loss": 0.5998,
      "step": 5324
    },
    {
      "epoch": 0.1635793936042761,
      "grad_norm": 0.32843565940856934,
      "learning_rate": 1.9682998575675398e-05,
      "loss": 0.6057,
      "step": 5325
    },
    {
      "epoch": 0.16361011273922527,
      "grad_norm": 0.3344746530056,
      "learning_rate": 1.9682877846191323e-05,
      "loss": 0.6403,
      "step": 5326
    },
    {
      "epoch": 0.16364083187417441,
      "grad_norm": 0.3308068811893463,
      "learning_rate": 1.9682757094092207e-05,
      "loss": 0.6088,
      "step": 5327
    },
    {
      "epoch": 0.1636715510091236,
      "grad_norm": 0.3679450452327728,
      "learning_rate": 1.9682636319378335e-05,
      "loss": 0.6283,
      "step": 5328
    },
    {
      "epoch": 0.16370227014407274,
      "grad_norm": 0.3255029618740082,
      "learning_rate": 1.968251552204999e-05,
      "loss": 0.5368,
      "step": 5329
    },
    {
      "epoch": 0.1637329892790219,
      "grad_norm": 0.3226368725299835,
      "learning_rate": 1.9682394702107457e-05,
      "loss": 0.5748,
      "step": 5330
    },
    {
      "epoch": 0.16376370841397106,
      "grad_norm": 0.3381098806858063,
      "learning_rate": 1.9682273859551016e-05,
      "loss": 0.6592,
      "step": 5331
    },
    {
      "epoch": 0.16379442754892024,
      "grad_norm": 0.3346593677997589,
      "learning_rate": 1.9682152994380943e-05,
      "loss": 0.5996,
      "step": 5332
    },
    {
      "epoch": 0.16382514668386938,
      "grad_norm": 0.32243385910987854,
      "learning_rate": 1.9682032106597528e-05,
      "loss": 0.5643,
      "step": 5333
    },
    {
      "epoch": 0.16385586581881853,
      "grad_norm": 0.3202296197414398,
      "learning_rate": 1.9681911196201053e-05,
      "loss": 0.5786,
      "step": 5334
    },
    {
      "epoch": 0.1638865849537677,
      "grad_norm": 0.2858325242996216,
      "learning_rate": 1.9681790263191796e-05,
      "loss": 0.4511,
      "step": 5335
    },
    {
      "epoch": 0.16391730408871685,
      "grad_norm": 0.35394930839538574,
      "learning_rate": 1.968166930757004e-05,
      "loss": 0.5689,
      "step": 5336
    },
    {
      "epoch": 0.16394802322366603,
      "grad_norm": 0.3471541404724121,
      "learning_rate": 1.9681548329336072e-05,
      "loss": 0.6396,
      "step": 5337
    },
    {
      "epoch": 0.16397874235861518,
      "grad_norm": 0.331368625164032,
      "learning_rate": 1.968142732849017e-05,
      "loss": 0.5676,
      "step": 5338
    },
    {
      "epoch": 0.16400946149356435,
      "grad_norm": 0.3250707983970642,
      "learning_rate": 1.9681306305032618e-05,
      "loss": 0.583,
      "step": 5339
    },
    {
      "epoch": 0.1640401806285135,
      "grad_norm": 0.34573280811309814,
      "learning_rate": 1.96811852589637e-05,
      "loss": 0.6224,
      "step": 5340
    },
    {
      "epoch": 0.16407089976346267,
      "grad_norm": 0.345918744802475,
      "learning_rate": 1.9681064190283697e-05,
      "loss": 0.6119,
      "step": 5341
    },
    {
      "epoch": 0.16410161889841182,
      "grad_norm": 0.3374018669128418,
      "learning_rate": 1.9680943098992894e-05,
      "loss": 0.6389,
      "step": 5342
    },
    {
      "epoch": 0.16413233803336097,
      "grad_norm": 0.35697877407073975,
      "learning_rate": 1.9680821985091573e-05,
      "loss": 0.5927,
      "step": 5343
    },
    {
      "epoch": 0.16416305716831014,
      "grad_norm": 0.47392159700393677,
      "learning_rate": 1.9680700848580015e-05,
      "loss": 0.6313,
      "step": 5344
    },
    {
      "epoch": 0.1641937763032593,
      "grad_norm": 0.314201295375824,
      "learning_rate": 1.9680579689458502e-05,
      "loss": 0.5934,
      "step": 5345
    },
    {
      "epoch": 0.16422449543820847,
      "grad_norm": 0.3263356387615204,
      "learning_rate": 1.968045850772732e-05,
      "loss": 0.5391,
      "step": 5346
    },
    {
      "epoch": 0.16425521457315762,
      "grad_norm": 0.3759841024875641,
      "learning_rate": 1.968033730338675e-05,
      "loss": 0.6163,
      "step": 5347
    },
    {
      "epoch": 0.1642859337081068,
      "grad_norm": 0.3118003010749817,
      "learning_rate": 1.9680216076437082e-05,
      "loss": 0.514,
      "step": 5348
    },
    {
      "epoch": 0.16431665284305594,
      "grad_norm": 0.34171655774116516,
      "learning_rate": 1.968009482687859e-05,
      "loss": 0.6204,
      "step": 5349
    },
    {
      "epoch": 0.16434737197800509,
      "grad_norm": 0.43404650688171387,
      "learning_rate": 1.9679973554711558e-05,
      "loss": 0.7406,
      "step": 5350
    },
    {
      "epoch": 0.16437809111295426,
      "grad_norm": 0.33806777000427246,
      "learning_rate": 1.967985225993627e-05,
      "loss": 0.6496,
      "step": 5351
    },
    {
      "epoch": 0.1644088102479034,
      "grad_norm": 0.31538257002830505,
      "learning_rate": 1.9679730942553018e-05,
      "loss": 0.5972,
      "step": 5352
    },
    {
      "epoch": 0.16443952938285258,
      "grad_norm": 0.32359957695007324,
      "learning_rate": 1.9679609602562076e-05,
      "loss": 0.5445,
      "step": 5353
    },
    {
      "epoch": 0.16447024851780173,
      "grad_norm": 0.35439279675483704,
      "learning_rate": 1.967948823996373e-05,
      "loss": 0.6748,
      "step": 5354
    },
    {
      "epoch": 0.1645009676527509,
      "grad_norm": 0.35975921154022217,
      "learning_rate": 1.967936685475826e-05,
      "loss": 0.6578,
      "step": 5355
    },
    {
      "epoch": 0.16453168678770005,
      "grad_norm": 0.34926027059555054,
      "learning_rate": 1.9679245446945953e-05,
      "loss": 0.5568,
      "step": 5356
    },
    {
      "epoch": 0.16456240592264923,
      "grad_norm": 0.3480025827884674,
      "learning_rate": 1.9679124016527095e-05,
      "loss": 0.539,
      "step": 5357
    },
    {
      "epoch": 0.16459312505759838,
      "grad_norm": 0.33309102058410645,
      "learning_rate": 1.9679002563501964e-05,
      "loss": 0.5534,
      "step": 5358
    },
    {
      "epoch": 0.16462384419254752,
      "grad_norm": 0.36215001344680786,
      "learning_rate": 1.967888108787085e-05,
      "loss": 0.5564,
      "step": 5359
    },
    {
      "epoch": 0.1646545633274967,
      "grad_norm": 0.3058740198612213,
      "learning_rate": 1.9678759589634027e-05,
      "loss": 0.6158,
      "step": 5360
    },
    {
      "epoch": 0.16468528246244585,
      "grad_norm": 0.38918182253837585,
      "learning_rate": 1.9678638068791793e-05,
      "loss": 0.6584,
      "step": 5361
    },
    {
      "epoch": 0.16471600159739502,
      "grad_norm": 0.32340502738952637,
      "learning_rate": 1.9678516525344418e-05,
      "loss": 0.6106,
      "step": 5362
    },
    {
      "epoch": 0.16474672073234417,
      "grad_norm": 0.3745855689048767,
      "learning_rate": 1.9678394959292197e-05,
      "loss": 0.6757,
      "step": 5363
    },
    {
      "epoch": 0.16477743986729335,
      "grad_norm": 0.3551986515522003,
      "learning_rate": 1.9678273370635404e-05,
      "loss": 0.5826,
      "step": 5364
    },
    {
      "epoch": 0.1648081590022425,
      "grad_norm": 0.4287644624710083,
      "learning_rate": 1.967815175937433e-05,
      "loss": 0.6953,
      "step": 5365
    },
    {
      "epoch": 0.16483887813719167,
      "grad_norm": 0.3573298156261444,
      "learning_rate": 1.967803012550926e-05,
      "loss": 0.5906,
      "step": 5366
    },
    {
      "epoch": 0.16486959727214082,
      "grad_norm": 0.36167728900909424,
      "learning_rate": 1.9677908469040465e-05,
      "loss": 0.5747,
      "step": 5367
    },
    {
      "epoch": 0.16490031640708996,
      "grad_norm": 0.3276723325252533,
      "learning_rate": 1.9677786789968248e-05,
      "loss": 0.5837,
      "step": 5368
    },
    {
      "epoch": 0.16493103554203914,
      "grad_norm": 0.35728615522384644,
      "learning_rate": 1.967766508829288e-05,
      "loss": 0.6359,
      "step": 5369
    },
    {
      "epoch": 0.1649617546769883,
      "grad_norm": 0.3153449594974518,
      "learning_rate": 1.967754336401465e-05,
      "loss": 0.5975,
      "step": 5370
    },
    {
      "epoch": 0.16499247381193746,
      "grad_norm": 0.4196654260158539,
      "learning_rate": 1.967742161713384e-05,
      "loss": 0.6195,
      "step": 5371
    },
    {
      "epoch": 0.1650231929468866,
      "grad_norm": 0.36502978205680847,
      "learning_rate": 1.967729984765074e-05,
      "loss": 0.6329,
      "step": 5372
    },
    {
      "epoch": 0.16505391208183579,
      "grad_norm": 0.31954309344291687,
      "learning_rate": 1.9677178055565624e-05,
      "loss": 0.5561,
      "step": 5373
    },
    {
      "epoch": 0.16508463121678493,
      "grad_norm": 0.34217333793640137,
      "learning_rate": 1.967705624087879e-05,
      "loss": 0.6465,
      "step": 5374
    },
    {
      "epoch": 0.1651153503517341,
      "grad_norm": 0.4199885427951813,
      "learning_rate": 1.9676934403590512e-05,
      "loss": 0.4585,
      "step": 5375
    },
    {
      "epoch": 0.16514606948668326,
      "grad_norm": 0.33183538913726807,
      "learning_rate": 1.9676812543701074e-05,
      "loss": 0.6063,
      "step": 5376
    },
    {
      "epoch": 0.1651767886216324,
      "grad_norm": 0.3799321949481964,
      "learning_rate": 1.967669066121077e-05,
      "loss": 0.658,
      "step": 5377
    },
    {
      "epoch": 0.16520750775658158,
      "grad_norm": 0.3886784315109253,
      "learning_rate": 1.9676568756119878e-05,
      "loss": 0.6458,
      "step": 5378
    },
    {
      "epoch": 0.16523822689153073,
      "grad_norm": 0.33512598276138306,
      "learning_rate": 1.967644682842868e-05,
      "loss": 0.5215,
      "step": 5379
    },
    {
      "epoch": 0.1652689460264799,
      "grad_norm": 0.3505151867866516,
      "learning_rate": 1.967632487813747e-05,
      "loss": 0.6205,
      "step": 5380
    },
    {
      "epoch": 0.16529966516142905,
      "grad_norm": 0.3699437379837036,
      "learning_rate": 1.9676202905246525e-05,
      "loss": 0.6516,
      "step": 5381
    },
    {
      "epoch": 0.16533038429637822,
      "grad_norm": 0.3599522113800049,
      "learning_rate": 1.9676080909756135e-05,
      "loss": 0.6274,
      "step": 5382
    },
    {
      "epoch": 0.16536110343132737,
      "grad_norm": 0.33870628476142883,
      "learning_rate": 1.967595889166658e-05,
      "loss": 0.6828,
      "step": 5383
    },
    {
      "epoch": 0.16539182256627655,
      "grad_norm": 0.32093527913093567,
      "learning_rate": 1.9675836850978146e-05,
      "loss": 0.6441,
      "step": 5384
    },
    {
      "epoch": 0.1654225417012257,
      "grad_norm": 0.31124845147132874,
      "learning_rate": 1.967571478769112e-05,
      "loss": 0.5633,
      "step": 5385
    },
    {
      "epoch": 0.16545326083617484,
      "grad_norm": 0.3664240539073944,
      "learning_rate": 1.9675592701805787e-05,
      "loss": 0.6131,
      "step": 5386
    },
    {
      "epoch": 0.16548397997112402,
      "grad_norm": 0.2987099587917328,
      "learning_rate": 1.9675470593322432e-05,
      "loss": 0.4995,
      "step": 5387
    },
    {
      "epoch": 0.16551469910607317,
      "grad_norm": 0.3330497443675995,
      "learning_rate": 1.967534846224134e-05,
      "loss": 0.5884,
      "step": 5388
    },
    {
      "epoch": 0.16554541824102234,
      "grad_norm": 0.3859827518463135,
      "learning_rate": 1.9675226308562795e-05,
      "loss": 0.658,
      "step": 5389
    },
    {
      "epoch": 0.1655761373759715,
      "grad_norm": 0.3449532091617584,
      "learning_rate": 1.9675104132287083e-05,
      "loss": 0.6513,
      "step": 5390
    },
    {
      "epoch": 0.16560685651092066,
      "grad_norm": 0.3169204294681549,
      "learning_rate": 1.967498193341449e-05,
      "loss": 0.6196,
      "step": 5391
    },
    {
      "epoch": 0.1656375756458698,
      "grad_norm": 0.39059674739837646,
      "learning_rate": 1.96748597119453e-05,
      "loss": 0.6361,
      "step": 5392
    },
    {
      "epoch": 0.16566829478081896,
      "grad_norm": 0.3559875786304474,
      "learning_rate": 1.96747374678798e-05,
      "loss": 0.5599,
      "step": 5393
    },
    {
      "epoch": 0.16569901391576813,
      "grad_norm": 0.3604243993759155,
      "learning_rate": 1.9674615201218278e-05,
      "loss": 0.6343,
      "step": 5394
    },
    {
      "epoch": 0.16572973305071728,
      "grad_norm": 0.3353118300437927,
      "learning_rate": 1.9674492911961012e-05,
      "loss": 0.5582,
      "step": 5395
    },
    {
      "epoch": 0.16576045218566646,
      "grad_norm": 0.3450133800506592,
      "learning_rate": 1.967437060010829e-05,
      "loss": 0.6132,
      "step": 5396
    },
    {
      "epoch": 0.1657911713206156,
      "grad_norm": 0.48463043570518494,
      "learning_rate": 1.967424826566041e-05,
      "loss": 0.5874,
      "step": 5397
    },
    {
      "epoch": 0.16582189045556478,
      "grad_norm": 0.3199705183506012,
      "learning_rate": 1.9674125908617637e-05,
      "loss": 0.5652,
      "step": 5398
    },
    {
      "epoch": 0.16585260959051393,
      "grad_norm": 0.3407282531261444,
      "learning_rate": 1.9674003528980275e-05,
      "loss": 0.588,
      "step": 5399
    },
    {
      "epoch": 0.1658833287254631,
      "grad_norm": 0.3423719108104706,
      "learning_rate": 1.9673881126748597e-05,
      "loss": 0.5919,
      "step": 5400
    },
    {
      "epoch": 0.16591404786041225,
      "grad_norm": 0.32458770275115967,
      "learning_rate": 1.9673758701922894e-05,
      "loss": 0.5446,
      "step": 5401
    },
    {
      "epoch": 0.1659447669953614,
      "grad_norm": 0.3258867859840393,
      "learning_rate": 1.9673636254503456e-05,
      "loss": 0.5691,
      "step": 5402
    },
    {
      "epoch": 0.16597548613031057,
      "grad_norm": 0.31917309761047363,
      "learning_rate": 1.967351378449056e-05,
      "loss": 0.6108,
      "step": 5403
    },
    {
      "epoch": 0.16600620526525972,
      "grad_norm": 0.35296937823295593,
      "learning_rate": 1.9673391291884503e-05,
      "loss": 0.7027,
      "step": 5404
    },
    {
      "epoch": 0.1660369244002089,
      "grad_norm": 0.3144349455833435,
      "learning_rate": 1.9673268776685563e-05,
      "loss": 0.573,
      "step": 5405
    },
    {
      "epoch": 0.16606764353515804,
      "grad_norm": 0.3367253243923187,
      "learning_rate": 1.9673146238894024e-05,
      "loss": 0.5272,
      "step": 5406
    },
    {
      "epoch": 0.16609836267010722,
      "grad_norm": 0.3842020034790039,
      "learning_rate": 1.9673023678510178e-05,
      "loss": 0.6339,
      "step": 5407
    },
    {
      "epoch": 0.16612908180505637,
      "grad_norm": 0.3236764967441559,
      "learning_rate": 1.967290109553431e-05,
      "loss": 0.5413,
      "step": 5408
    },
    {
      "epoch": 0.16615980094000554,
      "grad_norm": 0.34252655506134033,
      "learning_rate": 1.9672778489966712e-05,
      "loss": 0.6174,
      "step": 5409
    },
    {
      "epoch": 0.1661905200749547,
      "grad_norm": 0.342131108045578,
      "learning_rate": 1.9672655861807657e-05,
      "loss": 0.5708,
      "step": 5410
    },
    {
      "epoch": 0.16622123920990384,
      "grad_norm": 0.3338090777397156,
      "learning_rate": 1.967253321105744e-05,
      "loss": 0.6129,
      "step": 5411
    },
    {
      "epoch": 0.166251958344853,
      "grad_norm": 0.41813674569129944,
      "learning_rate": 1.9672410537716348e-05,
      "loss": 0.6114,
      "step": 5412
    },
    {
      "epoch": 0.16628267747980216,
      "grad_norm": 0.3538258969783783,
      "learning_rate": 1.9672287841784662e-05,
      "loss": 0.6083,
      "step": 5413
    },
    {
      "epoch": 0.16631339661475134,
      "grad_norm": 0.3479083776473999,
      "learning_rate": 1.967216512326268e-05,
      "loss": 0.5931,
      "step": 5414
    },
    {
      "epoch": 0.16634411574970048,
      "grad_norm": 0.3640499711036682,
      "learning_rate": 1.9672042382150673e-05,
      "loss": 0.5552,
      "step": 5415
    },
    {
      "epoch": 0.16637483488464966,
      "grad_norm": 0.3335842490196228,
      "learning_rate": 1.967191961844894e-05,
      "loss": 0.5285,
      "step": 5416
    },
    {
      "epoch": 0.1664055540195988,
      "grad_norm": 0.3161357641220093,
      "learning_rate": 1.967179683215776e-05,
      "loss": 0.5748,
      "step": 5417
    },
    {
      "epoch": 0.16643627315454798,
      "grad_norm": 0.30205774307250977,
      "learning_rate": 1.9671674023277427e-05,
      "loss": 0.5408,
      "step": 5418
    },
    {
      "epoch": 0.16646699228949713,
      "grad_norm": 0.4041442275047302,
      "learning_rate": 1.9671551191808218e-05,
      "loss": 0.5877,
      "step": 5419
    },
    {
      "epoch": 0.16649771142444628,
      "grad_norm": 0.5493183732032776,
      "learning_rate": 1.967142833775043e-05,
      "loss": 0.6753,
      "step": 5420
    },
    {
      "epoch": 0.16652843055939545,
      "grad_norm": 0.32911431789398193,
      "learning_rate": 1.9671305461104343e-05,
      "loss": 0.6112,
      "step": 5421
    },
    {
      "epoch": 0.1665591496943446,
      "grad_norm": 0.32975608110427856,
      "learning_rate": 1.9671182561870252e-05,
      "loss": 0.5404,
      "step": 5422
    },
    {
      "epoch": 0.16658986882929377,
      "grad_norm": 0.3181585967540741,
      "learning_rate": 1.9671059640048432e-05,
      "loss": 0.6146,
      "step": 5423
    },
    {
      "epoch": 0.16662058796424292,
      "grad_norm": 0.35299283266067505,
      "learning_rate": 1.967093669563918e-05,
      "loss": 0.6335,
      "step": 5424
    },
    {
      "epoch": 0.1666513070991921,
      "grad_norm": 0.3515104055404663,
      "learning_rate": 1.967081372864278e-05,
      "loss": 0.5294,
      "step": 5425
    },
    {
      "epoch": 0.16668202623414125,
      "grad_norm": 0.3566954433917999,
      "learning_rate": 1.967069073905952e-05,
      "loss": 0.6426,
      "step": 5426
    },
    {
      "epoch": 0.1667127453690904,
      "grad_norm": 0.35962820053100586,
      "learning_rate": 1.9670567726889686e-05,
      "loss": 0.5502,
      "step": 5427
    },
    {
      "epoch": 0.16674346450403957,
      "grad_norm": 0.3539987802505493,
      "learning_rate": 1.9670444692133567e-05,
      "loss": 0.6813,
      "step": 5428
    },
    {
      "epoch": 0.16677418363898872,
      "grad_norm": 0.38511890172958374,
      "learning_rate": 1.967032163479145e-05,
      "loss": 0.6322,
      "step": 5429
    },
    {
      "epoch": 0.1668049027739379,
      "grad_norm": 0.40917596220970154,
      "learning_rate": 1.9670198554863614e-05,
      "loss": 0.5033,
      "step": 5430
    },
    {
      "epoch": 0.16683562190888704,
      "grad_norm": 0.32460641860961914,
      "learning_rate": 1.9670075452350358e-05,
      "loss": 0.6393,
      "step": 5431
    },
    {
      "epoch": 0.1668663410438362,
      "grad_norm": 0.3231023848056793,
      "learning_rate": 1.966995232725197e-05,
      "loss": 0.6322,
      "step": 5432
    },
    {
      "epoch": 0.16689706017878536,
      "grad_norm": 0.3566509187221527,
      "learning_rate": 1.9669829179568727e-05,
      "loss": 0.6558,
      "step": 5433
    },
    {
      "epoch": 0.16692777931373454,
      "grad_norm": 0.352836012840271,
      "learning_rate": 1.9669706009300925e-05,
      "loss": 0.4982,
      "step": 5434
    },
    {
      "epoch": 0.16695849844868368,
      "grad_norm": 0.3491121828556061,
      "learning_rate": 1.966958281644885e-05,
      "loss": 0.6232,
      "step": 5435
    },
    {
      "epoch": 0.16698921758363283,
      "grad_norm": 0.3234473168849945,
      "learning_rate": 1.9669459601012787e-05,
      "loss": 0.5554,
      "step": 5436
    },
    {
      "epoch": 0.167019936718582,
      "grad_norm": 0.338652640581131,
      "learning_rate": 1.9669336362993025e-05,
      "loss": 0.5528,
      "step": 5437
    },
    {
      "epoch": 0.16705065585353115,
      "grad_norm": 0.3754640221595764,
      "learning_rate": 1.9669213102389854e-05,
      "loss": 0.5635,
      "step": 5438
    },
    {
      "epoch": 0.16708137498848033,
      "grad_norm": 0.3180187940597534,
      "learning_rate": 1.9669089819203562e-05,
      "loss": 0.6251,
      "step": 5439
    },
    {
      "epoch": 0.16711209412342948,
      "grad_norm": 0.3795541822910309,
      "learning_rate": 1.9668966513434436e-05,
      "loss": 0.6047,
      "step": 5440
    },
    {
      "epoch": 0.16714281325837865,
      "grad_norm": 0.37644296884536743,
      "learning_rate": 1.966884318508276e-05,
      "loss": 0.5493,
      "step": 5441
    },
    {
      "epoch": 0.1671735323933278,
      "grad_norm": 0.3289998769760132,
      "learning_rate": 1.966871983414883e-05,
      "loss": 0.5862,
      "step": 5442
    },
    {
      "epoch": 0.16720425152827698,
      "grad_norm": 0.3375934958457947,
      "learning_rate": 1.966859646063292e-05,
      "loss": 0.5548,
      "step": 5443
    },
    {
      "epoch": 0.16723497066322612,
      "grad_norm": 0.3771961033344269,
      "learning_rate": 1.9668473064535338e-05,
      "loss": 0.5479,
      "step": 5444
    },
    {
      "epoch": 0.16726568979817527,
      "grad_norm": 0.3798579275608063,
      "learning_rate": 1.966834964585636e-05,
      "loss": 0.5935,
      "step": 5445
    },
    {
      "epoch": 0.16729640893312445,
      "grad_norm": 0.3980357050895691,
      "learning_rate": 1.9668226204596275e-05,
      "loss": 0.6286,
      "step": 5446
    },
    {
      "epoch": 0.1673271280680736,
      "grad_norm": 0.3453928232192993,
      "learning_rate": 1.966810274075537e-05,
      "loss": 0.6282,
      "step": 5447
    },
    {
      "epoch": 0.16735784720302277,
      "grad_norm": 0.33319106698036194,
      "learning_rate": 1.966797925433394e-05,
      "loss": 0.5813,
      "step": 5448
    },
    {
      "epoch": 0.16738856633797192,
      "grad_norm": 0.6843703985214233,
      "learning_rate": 1.9667855745332268e-05,
      "loss": 0.5798,
      "step": 5449
    },
    {
      "epoch": 0.1674192854729211,
      "grad_norm": 0.35616663098335266,
      "learning_rate": 1.966773221375064e-05,
      "loss": 0.6086,
      "step": 5450
    },
    {
      "epoch": 0.16745000460787024,
      "grad_norm": 0.396986722946167,
      "learning_rate": 1.9667608659589353e-05,
      "loss": 0.6329,
      "step": 5451
    },
    {
      "epoch": 0.16748072374281942,
      "grad_norm": 0.4249308407306671,
      "learning_rate": 1.966748508284869e-05,
      "loss": 0.6636,
      "step": 5452
    },
    {
      "epoch": 0.16751144287776856,
      "grad_norm": 0.33221033215522766,
      "learning_rate": 1.9667361483528938e-05,
      "loss": 0.5285,
      "step": 5453
    },
    {
      "epoch": 0.1675421620127177,
      "grad_norm": 0.3347570598125458,
      "learning_rate": 1.966723786163039e-05,
      "loss": 0.6131,
      "step": 5454
    },
    {
      "epoch": 0.16757288114766689,
      "grad_norm": 1.1101282835006714,
      "learning_rate": 1.966711421715333e-05,
      "loss": 0.6017,
      "step": 5455
    },
    {
      "epoch": 0.16760360028261603,
      "grad_norm": 0.30101072788238525,
      "learning_rate": 1.9666990550098052e-05,
      "loss": 0.4967,
      "step": 5456
    },
    {
      "epoch": 0.1676343194175652,
      "grad_norm": 0.3163009285926819,
      "learning_rate": 1.9666866860464843e-05,
      "loss": 0.5292,
      "step": 5457
    },
    {
      "epoch": 0.16766503855251436,
      "grad_norm": 0.3248298168182373,
      "learning_rate": 1.966674314825399e-05,
      "loss": 0.5991,
      "step": 5458
    },
    {
      "epoch": 0.16769575768746353,
      "grad_norm": 0.3347892463207245,
      "learning_rate": 1.9666619413465785e-05,
      "loss": 0.5758,
      "step": 5459
    },
    {
      "epoch": 0.16772647682241268,
      "grad_norm": 0.3290795385837555,
      "learning_rate": 1.966649565610051e-05,
      "loss": 0.6311,
      "step": 5460
    },
    {
      "epoch": 0.16775719595736185,
      "grad_norm": 0.34801584482192993,
      "learning_rate": 1.966637187615847e-05,
      "loss": 0.5713,
      "step": 5461
    },
    {
      "epoch": 0.167787915092311,
      "grad_norm": 0.34441784024238586,
      "learning_rate": 1.9666248073639936e-05,
      "loss": 0.6524,
      "step": 5462
    },
    {
      "epoch": 0.16781863422726015,
      "grad_norm": 0.3603041470050812,
      "learning_rate": 1.9666124248545203e-05,
      "loss": 0.6266,
      "step": 5463
    },
    {
      "epoch": 0.16784935336220932,
      "grad_norm": 0.36286452412605286,
      "learning_rate": 1.9666000400874562e-05,
      "loss": 0.5828,
      "step": 5464
    },
    {
      "epoch": 0.16788007249715847,
      "grad_norm": 0.4100978672504425,
      "learning_rate": 1.9665876530628308e-05,
      "loss": 0.5383,
      "step": 5465
    },
    {
      "epoch": 0.16791079163210765,
      "grad_norm": 0.4050084948539734,
      "learning_rate": 1.9665752637806718e-05,
      "loss": 0.5945,
      "step": 5466
    },
    {
      "epoch": 0.1679415107670568,
      "grad_norm": 0.4664899408817291,
      "learning_rate": 1.966562872241009e-05,
      "loss": 0.5991,
      "step": 5467
    },
    {
      "epoch": 0.16797222990200597,
      "grad_norm": 0.30774539709091187,
      "learning_rate": 1.966550478443871e-05,
      "loss": 0.6616,
      "step": 5468
    },
    {
      "epoch": 0.16800294903695512,
      "grad_norm": 0.36028748750686646,
      "learning_rate": 1.9665380823892873e-05,
      "loss": 0.5744,
      "step": 5469
    },
    {
      "epoch": 0.16803366817190427,
      "grad_norm": 0.34222137928009033,
      "learning_rate": 1.9665256840772858e-05,
      "loss": 0.5334,
      "step": 5470
    },
    {
      "epoch": 0.16806438730685344,
      "grad_norm": 0.3483627736568451,
      "learning_rate": 1.9665132835078964e-05,
      "loss": 0.5762,
      "step": 5471
    },
    {
      "epoch": 0.1680951064418026,
      "grad_norm": 0.3024025559425354,
      "learning_rate": 1.9665008806811477e-05,
      "loss": 0.569,
      "step": 5472
    },
    {
      "epoch": 0.16812582557675176,
      "grad_norm": 0.33766546845436096,
      "learning_rate": 1.9664884755970686e-05,
      "loss": 0.6068,
      "step": 5473
    },
    {
      "epoch": 0.1681565447117009,
      "grad_norm": 0.3804508447647095,
      "learning_rate": 1.9664760682556885e-05,
      "loss": 0.6683,
      "step": 5474
    },
    {
      "epoch": 0.1681872638466501,
      "grad_norm": 0.31862974166870117,
      "learning_rate": 1.9664636586570357e-05,
      "loss": 0.6039,
      "step": 5475
    },
    {
      "epoch": 0.16821798298159923,
      "grad_norm": 0.5267075896263123,
      "learning_rate": 1.9664512468011393e-05,
      "loss": 0.6237,
      "step": 5476
    },
    {
      "epoch": 0.1682487021165484,
      "grad_norm": 0.3678168058395386,
      "learning_rate": 1.9664388326880292e-05,
      "loss": 0.6489,
      "step": 5477
    },
    {
      "epoch": 0.16827942125149756,
      "grad_norm": 0.3613138198852539,
      "learning_rate": 1.9664264163177332e-05,
      "loss": 0.6148,
      "step": 5478
    },
    {
      "epoch": 0.1683101403864467,
      "grad_norm": 0.3144119679927826,
      "learning_rate": 1.966413997690281e-05,
      "loss": 0.6042,
      "step": 5479
    },
    {
      "epoch": 0.16834085952139588,
      "grad_norm": 0.3248876631259918,
      "learning_rate": 1.9664015768057013e-05,
      "loss": 0.6415,
      "step": 5480
    },
    {
      "epoch": 0.16837157865634503,
      "grad_norm": 0.3442743718624115,
      "learning_rate": 1.9663891536640233e-05,
      "loss": 0.6253,
      "step": 5481
    },
    {
      "epoch": 0.1684022977912942,
      "grad_norm": 0.3040180802345276,
      "learning_rate": 1.9663767282652756e-05,
      "loss": 0.5976,
      "step": 5482
    },
    {
      "epoch": 0.16843301692624335,
      "grad_norm": 0.34871551394462585,
      "learning_rate": 1.966364300609488e-05,
      "loss": 0.6093,
      "step": 5483
    },
    {
      "epoch": 0.16846373606119253,
      "grad_norm": 0.3716799020767212,
      "learning_rate": 1.966351870696689e-05,
      "loss": 0.6747,
      "step": 5484
    },
    {
      "epoch": 0.16849445519614167,
      "grad_norm": 0.3259848654270172,
      "learning_rate": 1.966339438526908e-05,
      "loss": 0.6017,
      "step": 5485
    },
    {
      "epoch": 0.16852517433109085,
      "grad_norm": 0.30608105659484863,
      "learning_rate": 1.966327004100173e-05,
      "loss": 0.5608,
      "step": 5486
    },
    {
      "epoch": 0.16855589346604,
      "grad_norm": 0.3442974090576172,
      "learning_rate": 1.9663145674165145e-05,
      "loss": 0.6228,
      "step": 5487
    },
    {
      "epoch": 0.16858661260098914,
      "grad_norm": 0.29958638548851013,
      "learning_rate": 1.9663021284759604e-05,
      "loss": 0.5074,
      "step": 5488
    },
    {
      "epoch": 0.16861733173593832,
      "grad_norm": 0.35637542605400085,
      "learning_rate": 1.9662896872785405e-05,
      "loss": 0.5675,
      "step": 5489
    },
    {
      "epoch": 0.16864805087088747,
      "grad_norm": 0.3653794825077057,
      "learning_rate": 1.9662772438242834e-05,
      "loss": 0.6587,
      "step": 5490
    },
    {
      "epoch": 0.16867877000583664,
      "grad_norm": 0.3165616989135742,
      "learning_rate": 1.966264798113218e-05,
      "loss": 0.6352,
      "step": 5491
    },
    {
      "epoch": 0.1687094891407858,
      "grad_norm": 0.3383413255214691,
      "learning_rate": 1.9662523501453743e-05,
      "loss": 0.6319,
      "step": 5492
    },
    {
      "epoch": 0.16874020827573497,
      "grad_norm": 0.3425038754940033,
      "learning_rate": 1.9662398999207805e-05,
      "loss": 0.623,
      "step": 5493
    },
    {
      "epoch": 0.1687709274106841,
      "grad_norm": 0.3209141790866852,
      "learning_rate": 1.9662274474394658e-05,
      "loss": 0.5514,
      "step": 5494
    },
    {
      "epoch": 0.1688016465456333,
      "grad_norm": 0.3829180598258972,
      "learning_rate": 1.9662149927014596e-05,
      "loss": 0.5182,
      "step": 5495
    },
    {
      "epoch": 0.16883236568058244,
      "grad_norm": 0.36745816469192505,
      "learning_rate": 1.9662025357067905e-05,
      "loss": 0.6362,
      "step": 5496
    },
    {
      "epoch": 0.16886308481553158,
      "grad_norm": 0.32287704944610596,
      "learning_rate": 1.966190076455488e-05,
      "loss": 0.5635,
      "step": 5497
    },
    {
      "epoch": 0.16889380395048076,
      "grad_norm": 0.38495224714279175,
      "learning_rate": 1.9661776149475816e-05,
      "loss": 0.6491,
      "step": 5498
    },
    {
      "epoch": 0.1689245230854299,
      "grad_norm": 0.38525599241256714,
      "learning_rate": 1.9661651511830993e-05,
      "loss": 0.6353,
      "step": 5499
    },
    {
      "epoch": 0.16895524222037908,
      "grad_norm": 0.3129827082157135,
      "learning_rate": 1.966152685162071e-05,
      "loss": 0.5633,
      "step": 5500
    },
    {
      "epoch": 0.16898596135532823,
      "grad_norm": 0.32940658926963806,
      "learning_rate": 1.9661402168845257e-05,
      "loss": 0.6109,
      "step": 5501
    },
    {
      "epoch": 0.1690166804902774,
      "grad_norm": 0.3468550741672516,
      "learning_rate": 1.9661277463504924e-05,
      "loss": 0.5997,
      "step": 5502
    },
    {
      "epoch": 0.16904739962522655,
      "grad_norm": 0.3326278626918793,
      "learning_rate": 1.9661152735600003e-05,
      "loss": 0.5902,
      "step": 5503
    },
    {
      "epoch": 0.1690781187601757,
      "grad_norm": 0.38214775919914246,
      "learning_rate": 1.9661027985130784e-05,
      "loss": 0.5965,
      "step": 5504
    },
    {
      "epoch": 0.16910883789512487,
      "grad_norm": 0.3150218427181244,
      "learning_rate": 1.9660903212097563e-05,
      "loss": 0.6574,
      "step": 5505
    },
    {
      "epoch": 0.16913955703007402,
      "grad_norm": 0.3302452266216278,
      "learning_rate": 1.9660778416500625e-05,
      "loss": 0.5942,
      "step": 5506
    },
    {
      "epoch": 0.1691702761650232,
      "grad_norm": 0.34165868163108826,
      "learning_rate": 1.9660653598340263e-05,
      "loss": 0.579,
      "step": 5507
    },
    {
      "epoch": 0.16920099529997235,
      "grad_norm": 0.36234378814697266,
      "learning_rate": 1.966052875761677e-05,
      "loss": 0.5981,
      "step": 5508
    },
    {
      "epoch": 0.16923171443492152,
      "grad_norm": 0.32809343934059143,
      "learning_rate": 1.966040389433044e-05,
      "loss": 0.5654,
      "step": 5509
    },
    {
      "epoch": 0.16926243356987067,
      "grad_norm": 0.36838576197624207,
      "learning_rate": 1.966027900848156e-05,
      "loss": 0.7033,
      "step": 5510
    },
    {
      "epoch": 0.16929315270481984,
      "grad_norm": 0.39379027485847473,
      "learning_rate": 1.9660154100070423e-05,
      "loss": 0.4851,
      "step": 5511
    },
    {
      "epoch": 0.169323871839769,
      "grad_norm": 0.35460153222084045,
      "learning_rate": 1.966002916909732e-05,
      "loss": 0.668,
      "step": 5512
    },
    {
      "epoch": 0.16935459097471814,
      "grad_norm": 0.39369797706604004,
      "learning_rate": 1.9659904215562552e-05,
      "loss": 0.5624,
      "step": 5513
    },
    {
      "epoch": 0.16938531010966731,
      "grad_norm": 0.30127206444740295,
      "learning_rate": 1.96597792394664e-05,
      "loss": 0.5292,
      "step": 5514
    },
    {
      "epoch": 0.16941602924461646,
      "grad_norm": 0.35094118118286133,
      "learning_rate": 1.9659654240809155e-05,
      "loss": 0.5666,
      "step": 5515
    },
    {
      "epoch": 0.16944674837956564,
      "grad_norm": 0.4313194453716278,
      "learning_rate": 1.9659529219591116e-05,
      "loss": 0.5425,
      "step": 5516
    },
    {
      "epoch": 0.16947746751451478,
      "grad_norm": 0.3164213299751282,
      "learning_rate": 1.9659404175812572e-05,
      "loss": 0.5671,
      "step": 5517
    },
    {
      "epoch": 0.16950818664946396,
      "grad_norm": 0.4806155264377594,
      "learning_rate": 1.965927910947381e-05,
      "loss": 0.5423,
      "step": 5518
    },
    {
      "epoch": 0.1695389057844131,
      "grad_norm": 0.34958770871162415,
      "learning_rate": 1.9659154020575132e-05,
      "loss": 0.592,
      "step": 5519
    },
    {
      "epoch": 0.16956962491936228,
      "grad_norm": 0.3365020155906677,
      "learning_rate": 1.9659028909116823e-05,
      "loss": 0.5583,
      "step": 5520
    },
    {
      "epoch": 0.16960034405431143,
      "grad_norm": 0.4219428300857544,
      "learning_rate": 1.965890377509918e-05,
      "loss": 0.5329,
      "step": 5521
    },
    {
      "epoch": 0.16963106318926058,
      "grad_norm": 0.3420490324497223,
      "learning_rate": 1.965877861852249e-05,
      "loss": 0.5823,
      "step": 5522
    },
    {
      "epoch": 0.16966178232420975,
      "grad_norm": 0.35515448451042175,
      "learning_rate": 1.965865343938705e-05,
      "loss": 0.5393,
      "step": 5523
    },
    {
      "epoch": 0.1696925014591589,
      "grad_norm": 0.3513754606246948,
      "learning_rate": 1.9658528237693147e-05,
      "loss": 0.4994,
      "step": 5524
    },
    {
      "epoch": 0.16972322059410808,
      "grad_norm": 0.4636346399784088,
      "learning_rate": 1.965840301344108e-05,
      "loss": 0.6757,
      "step": 5525
    },
    {
      "epoch": 0.16975393972905722,
      "grad_norm": 0.3626987040042877,
      "learning_rate": 1.9658277766631138e-05,
      "loss": 0.5566,
      "step": 5526
    },
    {
      "epoch": 0.1697846588640064,
      "grad_norm": 0.27770087122917175,
      "learning_rate": 1.9658152497263614e-05,
      "loss": 0.552,
      "step": 5527
    },
    {
      "epoch": 0.16981537799895555,
      "grad_norm": 0.35424143075942993,
      "learning_rate": 1.96580272053388e-05,
      "loss": 0.6079,
      "step": 5528
    },
    {
      "epoch": 0.16984609713390472,
      "grad_norm": 0.34435805678367615,
      "learning_rate": 1.9657901890856988e-05,
      "loss": 0.6248,
      "step": 5529
    },
    {
      "epoch": 0.16987681626885387,
      "grad_norm": 0.32738181948661804,
      "learning_rate": 1.9657776553818474e-05,
      "loss": 0.6076,
      "step": 5530
    },
    {
      "epoch": 0.16990753540380302,
      "grad_norm": 0.3548453450202942,
      "learning_rate": 1.9657651194223543e-05,
      "loss": 0.625,
      "step": 5531
    },
    {
      "epoch": 0.1699382545387522,
      "grad_norm": 0.32058414816856384,
      "learning_rate": 1.9657525812072497e-05,
      "loss": 0.6169,
      "step": 5532
    },
    {
      "epoch": 0.16996897367370134,
      "grad_norm": 0.3727938234806061,
      "learning_rate": 1.9657400407365625e-05,
      "loss": 0.6555,
      "step": 5533
    },
    {
      "epoch": 0.16999969280865052,
      "grad_norm": 0.32011500000953674,
      "learning_rate": 1.9657274980103217e-05,
      "loss": 0.5646,
      "step": 5534
    },
    {
      "epoch": 0.17003041194359966,
      "grad_norm": 0.3470783233642578,
      "learning_rate": 1.9657149530285572e-05,
      "loss": 0.6156,
      "step": 5535
    },
    {
      "epoch": 0.17006113107854884,
      "grad_norm": 0.3156416714191437,
      "learning_rate": 1.965702405791298e-05,
      "loss": 0.5514,
      "step": 5536
    },
    {
      "epoch": 0.17009185021349799,
      "grad_norm": 0.3582402169704437,
      "learning_rate": 1.9656898562985733e-05,
      "loss": 0.5452,
      "step": 5537
    },
    {
      "epoch": 0.17012256934844716,
      "grad_norm": 0.30616992712020874,
      "learning_rate": 1.9656773045504125e-05,
      "loss": 0.5283,
      "step": 5538
    },
    {
      "epoch": 0.1701532884833963,
      "grad_norm": 0.3308858871459961,
      "learning_rate": 1.9656647505468452e-05,
      "loss": 0.5851,
      "step": 5539
    },
    {
      "epoch": 0.17018400761834546,
      "grad_norm": 0.3321027457714081,
      "learning_rate": 1.9656521942879002e-05,
      "loss": 0.5211,
      "step": 5540
    },
    {
      "epoch": 0.17021472675329463,
      "grad_norm": 0.34497690200805664,
      "learning_rate": 1.9656396357736067e-05,
      "loss": 0.6227,
      "step": 5541
    },
    {
      "epoch": 0.17024544588824378,
      "grad_norm": 0.36517247557640076,
      "learning_rate": 1.9656270750039948e-05,
      "loss": 0.6266,
      "step": 5542
    },
    {
      "epoch": 0.17027616502319295,
      "grad_norm": 0.3612678050994873,
      "learning_rate": 1.9656145119790933e-05,
      "loss": 0.6609,
      "step": 5543
    },
    {
      "epoch": 0.1703068841581421,
      "grad_norm": 0.3385012447834015,
      "learning_rate": 1.9656019466989316e-05,
      "loss": 0.5795,
      "step": 5544
    },
    {
      "epoch": 0.17033760329309128,
      "grad_norm": 0.34869012236595154,
      "learning_rate": 1.9655893791635393e-05,
      "loss": 0.6222,
      "step": 5545
    },
    {
      "epoch": 0.17036832242804043,
      "grad_norm": 0.3779274523258209,
      "learning_rate": 1.9655768093729456e-05,
      "loss": 0.6475,
      "step": 5546
    },
    {
      "epoch": 0.17039904156298957,
      "grad_norm": 0.4023529589176178,
      "learning_rate": 1.9655642373271794e-05,
      "loss": 0.5915,
      "step": 5547
    },
    {
      "epoch": 0.17042976069793875,
      "grad_norm": 0.31498199701309204,
      "learning_rate": 1.965551663026271e-05,
      "loss": 0.5787,
      "step": 5548
    },
    {
      "epoch": 0.1704604798328879,
      "grad_norm": 0.8628299832344055,
      "learning_rate": 1.965539086470249e-05,
      "loss": 0.6005,
      "step": 5549
    },
    {
      "epoch": 0.17049119896783707,
      "grad_norm": 0.3211572468280792,
      "learning_rate": 1.965526507659143e-05,
      "loss": 0.5627,
      "step": 5550
    },
    {
      "epoch": 0.17052191810278622,
      "grad_norm": 0.33536428213119507,
      "learning_rate": 1.9655139265929827e-05,
      "loss": 0.6693,
      "step": 5551
    },
    {
      "epoch": 0.1705526372377354,
      "grad_norm": 0.33465224504470825,
      "learning_rate": 1.9655013432717968e-05,
      "loss": 0.5415,
      "step": 5552
    },
    {
      "epoch": 0.17058335637268454,
      "grad_norm": 0.38165777921676636,
      "learning_rate": 1.9654887576956155e-05,
      "loss": 0.712,
      "step": 5553
    },
    {
      "epoch": 0.17061407550763372,
      "grad_norm": 0.35175400972366333,
      "learning_rate": 1.9654761698644674e-05,
      "loss": 0.5735,
      "step": 5554
    },
    {
      "epoch": 0.17064479464258286,
      "grad_norm": 0.3485037684440613,
      "learning_rate": 1.9654635797783825e-05,
      "loss": 0.5848,
      "step": 5555
    },
    {
      "epoch": 0.170675513777532,
      "grad_norm": 0.32226577401161194,
      "learning_rate": 1.9654509874373898e-05,
      "loss": 0.5662,
      "step": 5556
    },
    {
      "epoch": 0.1707062329124812,
      "grad_norm": 0.34683430194854736,
      "learning_rate": 1.9654383928415188e-05,
      "loss": 0.579,
      "step": 5557
    },
    {
      "epoch": 0.17073695204743033,
      "grad_norm": 0.3476565480232239,
      "learning_rate": 1.9654257959907994e-05,
      "loss": 0.6512,
      "step": 5558
    },
    {
      "epoch": 0.1707676711823795,
      "grad_norm": 0.3678407073020935,
      "learning_rate": 1.9654131968852606e-05,
      "loss": 0.6936,
      "step": 5559
    },
    {
      "epoch": 0.17079839031732866,
      "grad_norm": 0.34487271308898926,
      "learning_rate": 1.9654005955249316e-05,
      "loss": 0.6476,
      "step": 5560
    },
    {
      "epoch": 0.17082910945227783,
      "grad_norm": 0.3642725944519043,
      "learning_rate": 1.9653879919098423e-05,
      "loss": 0.5894,
      "step": 5561
    },
    {
      "epoch": 0.17085982858722698,
      "grad_norm": 0.3281816244125366,
      "learning_rate": 1.9653753860400214e-05,
      "loss": 0.6368,
      "step": 5562
    },
    {
      "epoch": 0.17089054772217616,
      "grad_norm": 0.36691707372665405,
      "learning_rate": 1.9653627779154995e-05,
      "loss": 0.6099,
      "step": 5563
    },
    {
      "epoch": 0.1709212668571253,
      "grad_norm": 0.39117464423179626,
      "learning_rate": 1.9653501675363052e-05,
      "loss": 0.6431,
      "step": 5564
    },
    {
      "epoch": 0.17095198599207445,
      "grad_norm": 0.3332730829715729,
      "learning_rate": 1.965337554902468e-05,
      "loss": 0.5611,
      "step": 5565
    },
    {
      "epoch": 0.17098270512702363,
      "grad_norm": 0.35758838057518005,
      "learning_rate": 1.9653249400140178e-05,
      "loss": 0.5759,
      "step": 5566
    },
    {
      "epoch": 0.17101342426197277,
      "grad_norm": 0.3162406384944916,
      "learning_rate": 1.9653123228709836e-05,
      "loss": 0.5963,
      "step": 5567
    },
    {
      "epoch": 0.17104414339692195,
      "grad_norm": 0.32974550127983093,
      "learning_rate": 1.9652997034733953e-05,
      "loss": 0.5524,
      "step": 5568
    },
    {
      "epoch": 0.1710748625318711,
      "grad_norm": 0.3820188343524933,
      "learning_rate": 1.9652870818212818e-05,
      "loss": 0.5305,
      "step": 5569
    },
    {
      "epoch": 0.17110558166682027,
      "grad_norm": 0.351349413394928,
      "learning_rate": 1.965274457914673e-05,
      "loss": 0.5954,
      "step": 5570
    },
    {
      "epoch": 0.17113630080176942,
      "grad_norm": 0.3260761499404907,
      "learning_rate": 1.965261831753598e-05,
      "loss": 0.6611,
      "step": 5571
    },
    {
      "epoch": 0.1711670199367186,
      "grad_norm": 0.3345634937286377,
      "learning_rate": 1.965249203338087e-05,
      "loss": 0.5799,
      "step": 5572
    },
    {
      "epoch": 0.17119773907166774,
      "grad_norm": 0.34981727600097656,
      "learning_rate": 1.965236572668169e-05,
      "loss": 0.5858,
      "step": 5573
    },
    {
      "epoch": 0.1712284582066169,
      "grad_norm": 0.37465599179267883,
      "learning_rate": 1.9652239397438736e-05,
      "loss": 0.616,
      "step": 5574
    },
    {
      "epoch": 0.17125917734156607,
      "grad_norm": 0.3405710756778717,
      "learning_rate": 1.96521130456523e-05,
      "loss": 0.5776,
      "step": 5575
    },
    {
      "epoch": 0.1712898964765152,
      "grad_norm": 0.35614854097366333,
      "learning_rate": 1.9651986671322684e-05,
      "loss": 0.6096,
      "step": 5576
    },
    {
      "epoch": 0.1713206156114644,
      "grad_norm": 0.3522805869579315,
      "learning_rate": 1.965186027445018e-05,
      "loss": 0.5824,
      "step": 5577
    },
    {
      "epoch": 0.17135133474641354,
      "grad_norm": 0.32862916588783264,
      "learning_rate": 1.9651733855035078e-05,
      "loss": 0.5915,
      "step": 5578
    },
    {
      "epoch": 0.1713820538813627,
      "grad_norm": 0.3735373318195343,
      "learning_rate": 1.965160741307768e-05,
      "loss": 0.7005,
      "step": 5579
    },
    {
      "epoch": 0.17141277301631186,
      "grad_norm": 0.3380180299282074,
      "learning_rate": 1.9651480948578278e-05,
      "loss": 0.5852,
      "step": 5580
    },
    {
      "epoch": 0.17144349215126103,
      "grad_norm": 0.3365321755409241,
      "learning_rate": 1.9651354461537167e-05,
      "loss": 0.5574,
      "step": 5581
    },
    {
      "epoch": 0.17147421128621018,
      "grad_norm": 0.35373666882514954,
      "learning_rate": 1.9651227951954644e-05,
      "loss": 0.5954,
      "step": 5582
    },
    {
      "epoch": 0.17150493042115933,
      "grad_norm": 0.31934884190559387,
      "learning_rate": 1.9651101419831004e-05,
      "loss": 0.583,
      "step": 5583
    },
    {
      "epoch": 0.1715356495561085,
      "grad_norm": 0.3511893153190613,
      "learning_rate": 1.9650974865166545e-05,
      "loss": 0.5808,
      "step": 5584
    },
    {
      "epoch": 0.17156636869105765,
      "grad_norm": 0.34635064005851746,
      "learning_rate": 1.9650848287961556e-05,
      "loss": 0.6995,
      "step": 5585
    },
    {
      "epoch": 0.17159708782600683,
      "grad_norm": 0.37466922402381897,
      "learning_rate": 1.9650721688216342e-05,
      "loss": 0.5633,
      "step": 5586
    },
    {
      "epoch": 0.17162780696095598,
      "grad_norm": 0.31966257095336914,
      "learning_rate": 1.965059506593119e-05,
      "loss": 0.5755,
      "step": 5587
    },
    {
      "epoch": 0.17165852609590515,
      "grad_norm": 0.3190842866897583,
      "learning_rate": 1.9650468421106397e-05,
      "loss": 0.5986,
      "step": 5588
    },
    {
      "epoch": 0.1716892452308543,
      "grad_norm": 0.30955755710601807,
      "learning_rate": 1.9650341753742266e-05,
      "loss": 0.5614,
      "step": 5589
    },
    {
      "epoch": 0.17171996436580345,
      "grad_norm": 0.37814977765083313,
      "learning_rate": 1.9650215063839086e-05,
      "loss": 0.5732,
      "step": 5590
    },
    {
      "epoch": 0.17175068350075262,
      "grad_norm": 0.3915259838104248,
      "learning_rate": 1.9650088351397155e-05,
      "loss": 0.5641,
      "step": 5591
    },
    {
      "epoch": 0.17178140263570177,
      "grad_norm": 0.37087368965148926,
      "learning_rate": 1.964996161641677e-05,
      "loss": 0.6211,
      "step": 5592
    },
    {
      "epoch": 0.17181212177065094,
      "grad_norm": 0.3033600151538849,
      "learning_rate": 1.964983485889822e-05,
      "loss": 0.5395,
      "step": 5593
    },
    {
      "epoch": 0.1718428409056001,
      "grad_norm": 0.3242299258708954,
      "learning_rate": 1.964970807884181e-05,
      "loss": 0.5849,
      "step": 5594
    },
    {
      "epoch": 0.17187356004054927,
      "grad_norm": 0.34584879875183105,
      "learning_rate": 1.9649581276247836e-05,
      "loss": 0.5214,
      "step": 5595
    },
    {
      "epoch": 0.17190427917549841,
      "grad_norm": 0.33015429973602295,
      "learning_rate": 1.964945445111659e-05,
      "loss": 0.5971,
      "step": 5596
    },
    {
      "epoch": 0.1719349983104476,
      "grad_norm": 0.3855443596839905,
      "learning_rate": 1.9649327603448368e-05,
      "loss": 0.6004,
      "step": 5597
    },
    {
      "epoch": 0.17196571744539674,
      "grad_norm": 0.31823456287384033,
      "learning_rate": 1.9649200733243464e-05,
      "loss": 0.6093,
      "step": 5598
    },
    {
      "epoch": 0.17199643658034589,
      "grad_norm": 0.337131530046463,
      "learning_rate": 1.9649073840502185e-05,
      "loss": 0.5629,
      "step": 5599
    },
    {
      "epoch": 0.17202715571529506,
      "grad_norm": 0.34101352095603943,
      "learning_rate": 1.9648946925224815e-05,
      "loss": 0.5843,
      "step": 5600
    },
    {
      "epoch": 0.1720578748502442,
      "grad_norm": 0.3649226725101471,
      "learning_rate": 1.9648819987411656e-05,
      "loss": 0.5723,
      "step": 5601
    },
    {
      "epoch": 0.17208859398519338,
      "grad_norm": 0.3183785378932953,
      "learning_rate": 1.9648693027063006e-05,
      "loss": 0.6286,
      "step": 5602
    },
    {
      "epoch": 0.17211931312014253,
      "grad_norm": 0.38478654623031616,
      "learning_rate": 1.964856604417916e-05,
      "loss": 0.6409,
      "step": 5603
    },
    {
      "epoch": 0.1721500322550917,
      "grad_norm": 0.40133506059646606,
      "learning_rate": 1.964843903876041e-05,
      "loss": 0.6786,
      "step": 5604
    },
    {
      "epoch": 0.17218075139004085,
      "grad_norm": 0.32408133149147034,
      "learning_rate": 1.964831201080706e-05,
      "loss": 0.5962,
      "step": 5605
    },
    {
      "epoch": 0.17221147052499003,
      "grad_norm": 0.37347209453582764,
      "learning_rate": 1.96481849603194e-05,
      "loss": 0.6239,
      "step": 5606
    },
    {
      "epoch": 0.17224218965993918,
      "grad_norm": 0.35333937406539917,
      "learning_rate": 1.9648057887297737e-05,
      "loss": 0.6208,
      "step": 5607
    },
    {
      "epoch": 0.17227290879488832,
      "grad_norm": 0.33590003848075867,
      "learning_rate": 1.9647930791742354e-05,
      "loss": 0.6243,
      "step": 5608
    },
    {
      "epoch": 0.1723036279298375,
      "grad_norm": 0.33774659037590027,
      "learning_rate": 1.964780367365356e-05,
      "loss": 0.6297,
      "step": 5609
    },
    {
      "epoch": 0.17233434706478665,
      "grad_norm": 0.3409034311771393,
      "learning_rate": 1.9647676533031646e-05,
      "loss": 0.6314,
      "step": 5610
    },
    {
      "epoch": 0.17236506619973582,
      "grad_norm": 0.30403509736061096,
      "learning_rate": 1.9647549369876908e-05,
      "loss": 0.5888,
      "step": 5611
    },
    {
      "epoch": 0.17239578533468497,
      "grad_norm": 0.45810380578041077,
      "learning_rate": 1.9647422184189647e-05,
      "loss": 0.6147,
      "step": 5612
    },
    {
      "epoch": 0.17242650446963415,
      "grad_norm": 0.3310184180736542,
      "learning_rate": 1.9647294975970153e-05,
      "loss": 0.5985,
      "step": 5613
    },
    {
      "epoch": 0.1724572236045833,
      "grad_norm": 0.34987056255340576,
      "learning_rate": 1.964716774521873e-05,
      "loss": 0.5666,
      "step": 5614
    },
    {
      "epoch": 0.17248794273953247,
      "grad_norm": 0.4518604278564453,
      "learning_rate": 1.9647040491935675e-05,
      "loss": 0.55,
      "step": 5615
    },
    {
      "epoch": 0.17251866187448162,
      "grad_norm": 0.3221533000469208,
      "learning_rate": 1.9646913216121282e-05,
      "loss": 0.588,
      "step": 5616
    },
    {
      "epoch": 0.17254938100943076,
      "grad_norm": 0.35560575127601624,
      "learning_rate": 1.964678591777585e-05,
      "loss": 0.5107,
      "step": 5617
    },
    {
      "epoch": 0.17258010014437994,
      "grad_norm": 0.3450881242752075,
      "learning_rate": 1.9646658596899674e-05,
      "loss": 0.5672,
      "step": 5618
    },
    {
      "epoch": 0.1726108192793291,
      "grad_norm": 0.37284907698631287,
      "learning_rate": 1.9646531253493055e-05,
      "loss": 0.6562,
      "step": 5619
    },
    {
      "epoch": 0.17264153841427826,
      "grad_norm": 0.36055877804756165,
      "learning_rate": 1.9646403887556288e-05,
      "loss": 0.5545,
      "step": 5620
    },
    {
      "epoch": 0.1726722575492274,
      "grad_norm": 0.37546882033348083,
      "learning_rate": 1.964627649908967e-05,
      "loss": 0.6487,
      "step": 5621
    },
    {
      "epoch": 0.17270297668417658,
      "grad_norm": 0.32225096225738525,
      "learning_rate": 1.96461490880935e-05,
      "loss": 0.6672,
      "step": 5622
    },
    {
      "epoch": 0.17273369581912573,
      "grad_norm": 0.3978888690471649,
      "learning_rate": 1.9646021654568073e-05,
      "loss": 0.6324,
      "step": 5623
    },
    {
      "epoch": 0.17276441495407488,
      "grad_norm": 0.3681177496910095,
      "learning_rate": 1.9645894198513692e-05,
      "loss": 0.5847,
      "step": 5624
    },
    {
      "epoch": 0.17279513408902406,
      "grad_norm": 0.3708992600440979,
      "learning_rate": 1.964576671993065e-05,
      "loss": 0.5986,
      "step": 5625
    },
    {
      "epoch": 0.1728258532239732,
      "grad_norm": 0.34115391969680786,
      "learning_rate": 1.964563921881925e-05,
      "loss": 0.5365,
      "step": 5626
    },
    {
      "epoch": 0.17285657235892238,
      "grad_norm": 0.42487725615501404,
      "learning_rate": 1.964551169517978e-05,
      "loss": 0.6385,
      "step": 5627
    },
    {
      "epoch": 0.17288729149387153,
      "grad_norm": 0.32360678911209106,
      "learning_rate": 1.9645384149012546e-05,
      "loss": 0.5662,
      "step": 5628
    },
    {
      "epoch": 0.1729180106288207,
      "grad_norm": 0.35036876797676086,
      "learning_rate": 1.9645256580317843e-05,
      "loss": 0.5994,
      "step": 5629
    },
    {
      "epoch": 0.17294872976376985,
      "grad_norm": 0.3198074698448181,
      "learning_rate": 1.964512898909597e-05,
      "loss": 0.5302,
      "step": 5630
    },
    {
      "epoch": 0.17297944889871902,
      "grad_norm": 0.3233049213886261,
      "learning_rate": 1.964500137534723e-05,
      "loss": 0.5657,
      "step": 5631
    },
    {
      "epoch": 0.17301016803366817,
      "grad_norm": 0.3180990219116211,
      "learning_rate": 1.9644873739071912e-05,
      "loss": 0.6293,
      "step": 5632
    },
    {
      "epoch": 0.17304088716861732,
      "grad_norm": 0.3301975429058075,
      "learning_rate": 1.9644746080270315e-05,
      "loss": 0.6084,
      "step": 5633
    },
    {
      "epoch": 0.1730716063035665,
      "grad_norm": 0.3184007704257965,
      "learning_rate": 1.9644618398942744e-05,
      "loss": 0.5745,
      "step": 5634
    },
    {
      "epoch": 0.17310232543851564,
      "grad_norm": 0.3604748845100403,
      "learning_rate": 1.9644490695089488e-05,
      "loss": 0.6986,
      "step": 5635
    },
    {
      "epoch": 0.17313304457346482,
      "grad_norm": 0.3489220142364502,
      "learning_rate": 1.9644362968710854e-05,
      "loss": 0.5871,
      "step": 5636
    },
    {
      "epoch": 0.17316376370841396,
      "grad_norm": 0.35768797993659973,
      "learning_rate": 1.9644235219807137e-05,
      "loss": 0.6393,
      "step": 5637
    },
    {
      "epoch": 0.17319448284336314,
      "grad_norm": 0.31330159306526184,
      "learning_rate": 1.9644107448378632e-05,
      "loss": 0.6005,
      "step": 5638
    },
    {
      "epoch": 0.1732252019783123,
      "grad_norm": 0.3264901340007782,
      "learning_rate": 1.9643979654425644e-05,
      "loss": 0.5653,
      "step": 5639
    },
    {
      "epoch": 0.17325592111326146,
      "grad_norm": 0.36978164315223694,
      "learning_rate": 1.9643851837948467e-05,
      "loss": 0.6447,
      "step": 5640
    },
    {
      "epoch": 0.1732866402482106,
      "grad_norm": 0.30458885431289673,
      "learning_rate": 1.96437239989474e-05,
      "loss": 0.5918,
      "step": 5641
    },
    {
      "epoch": 0.17331735938315976,
      "grad_norm": 0.3346673548221588,
      "learning_rate": 1.9643596137422742e-05,
      "loss": 0.6009,
      "step": 5642
    },
    {
      "epoch": 0.17334807851810893,
      "grad_norm": 0.3385678827762604,
      "learning_rate": 1.9643468253374793e-05,
      "loss": 0.6466,
      "step": 5643
    },
    {
      "epoch": 0.17337879765305808,
      "grad_norm": 0.35234975814819336,
      "learning_rate": 1.964334034680385e-05,
      "loss": 0.57,
      "step": 5644
    },
    {
      "epoch": 0.17340951678800726,
      "grad_norm": 0.3654470145702362,
      "learning_rate": 1.964321241771021e-05,
      "loss": 0.5914,
      "step": 5645
    },
    {
      "epoch": 0.1734402359229564,
      "grad_norm": 0.38410162925720215,
      "learning_rate": 1.9643084466094175e-05,
      "loss": 0.5635,
      "step": 5646
    },
    {
      "epoch": 0.17347095505790558,
      "grad_norm": 0.34213224053382874,
      "learning_rate": 1.9642956491956046e-05,
      "loss": 0.6927,
      "step": 5647
    },
    {
      "epoch": 0.17350167419285473,
      "grad_norm": 0.30476120114326477,
      "learning_rate": 1.9642828495296117e-05,
      "loss": 0.5445,
      "step": 5648
    },
    {
      "epoch": 0.1735323933278039,
      "grad_norm": 0.3183961510658264,
      "learning_rate": 1.9642700476114686e-05,
      "loss": 0.4894,
      "step": 5649
    },
    {
      "epoch": 0.17356311246275305,
      "grad_norm": 0.3175993859767914,
      "learning_rate": 1.9642572434412056e-05,
      "loss": 0.542,
      "step": 5650
    },
    {
      "epoch": 0.1735938315977022,
      "grad_norm": 0.3211466372013092,
      "learning_rate": 1.9642444370188523e-05,
      "loss": 0.5393,
      "step": 5651
    },
    {
      "epoch": 0.17362455073265137,
      "grad_norm": 0.7235485315322876,
      "learning_rate": 1.964231628344439e-05,
      "loss": 0.6612,
      "step": 5652
    },
    {
      "epoch": 0.17365526986760052,
      "grad_norm": 0.3482934534549713,
      "learning_rate": 1.9642188174179956e-05,
      "loss": 0.6013,
      "step": 5653
    },
    {
      "epoch": 0.1736859890025497,
      "grad_norm": 0.35524192452430725,
      "learning_rate": 1.9642060042395514e-05,
      "loss": 0.5851,
      "step": 5654
    },
    {
      "epoch": 0.17371670813749884,
      "grad_norm": 0.3642285466194153,
      "learning_rate": 1.964193188809137e-05,
      "loss": 0.5974,
      "step": 5655
    },
    {
      "epoch": 0.17374742727244802,
      "grad_norm": 0.308187872171402,
      "learning_rate": 1.9641803711267817e-05,
      "loss": 0.5251,
      "step": 5656
    },
    {
      "epoch": 0.17377814640739717,
      "grad_norm": 0.3165641725063324,
      "learning_rate": 1.9641675511925162e-05,
      "loss": 0.554,
      "step": 5657
    },
    {
      "epoch": 0.17380886554234634,
      "grad_norm": 0.3169659972190857,
      "learning_rate": 1.96415472900637e-05,
      "loss": 0.5436,
      "step": 5658
    },
    {
      "epoch": 0.1738395846772955,
      "grad_norm": 0.3664347231388092,
      "learning_rate": 1.964141904568373e-05,
      "loss": 0.58,
      "step": 5659
    },
    {
      "epoch": 0.17387030381224464,
      "grad_norm": 0.35595306754112244,
      "learning_rate": 1.9641290778785555e-05,
      "loss": 0.6153,
      "step": 5660
    },
    {
      "epoch": 0.1739010229471938,
      "grad_norm": 0.34305647015571594,
      "learning_rate": 1.9641162489369467e-05,
      "loss": 0.5924,
      "step": 5661
    },
    {
      "epoch": 0.17393174208214296,
      "grad_norm": 0.4135643243789673,
      "learning_rate": 1.9641034177435774e-05,
      "loss": 0.5844,
      "step": 5662
    },
    {
      "epoch": 0.17396246121709213,
      "grad_norm": 0.572309672832489,
      "learning_rate": 1.964090584298477e-05,
      "loss": 0.6661,
      "step": 5663
    },
    {
      "epoch": 0.17399318035204128,
      "grad_norm": 0.3188706040382385,
      "learning_rate": 1.964077748601676e-05,
      "loss": 0.6969,
      "step": 5664
    },
    {
      "epoch": 0.17402389948699046,
      "grad_norm": 0.34014591574668884,
      "learning_rate": 1.9640649106532042e-05,
      "loss": 0.5931,
      "step": 5665
    },
    {
      "epoch": 0.1740546186219396,
      "grad_norm": 0.3337884545326233,
      "learning_rate": 1.964052070453091e-05,
      "loss": 0.5671,
      "step": 5666
    },
    {
      "epoch": 0.17408533775688875,
      "grad_norm": 0.30931007862091064,
      "learning_rate": 1.964039228001367e-05,
      "loss": 0.5535,
      "step": 5667
    },
    {
      "epoch": 0.17411605689183793,
      "grad_norm": 0.33421021699905396,
      "learning_rate": 1.9640263832980624e-05,
      "loss": 0.5733,
      "step": 5668
    },
    {
      "epoch": 0.17414677602678708,
      "grad_norm": 0.33214837312698364,
      "learning_rate": 1.9640135363432064e-05,
      "loss": 0.6399,
      "step": 5669
    },
    {
      "epoch": 0.17417749516173625,
      "grad_norm": 0.3570050299167633,
      "learning_rate": 1.9640006871368297e-05,
      "loss": 0.6372,
      "step": 5670
    },
    {
      "epoch": 0.1742082142966854,
      "grad_norm": 0.3707194924354553,
      "learning_rate": 1.963987835678962e-05,
      "loss": 0.519,
      "step": 5671
    },
    {
      "epoch": 0.17423893343163457,
      "grad_norm": 0.31791940331459045,
      "learning_rate": 1.9639749819696336e-05,
      "loss": 0.5546,
      "step": 5672
    },
    {
      "epoch": 0.17426965256658372,
      "grad_norm": 0.35124343633651733,
      "learning_rate": 1.9639621260088742e-05,
      "loss": 0.5627,
      "step": 5673
    },
    {
      "epoch": 0.1743003717015329,
      "grad_norm": 0.31733763217926025,
      "learning_rate": 1.9639492677967138e-05,
      "loss": 0.5697,
      "step": 5674
    },
    {
      "epoch": 0.17433109083648204,
      "grad_norm": 0.3432777225971222,
      "learning_rate": 1.9639364073331825e-05,
      "loss": 0.585,
      "step": 5675
    },
    {
      "epoch": 0.1743618099714312,
      "grad_norm": 0.3301388621330261,
      "learning_rate": 1.9639235446183105e-05,
      "loss": 0.618,
      "step": 5676
    },
    {
      "epoch": 0.17439252910638037,
      "grad_norm": 0.4949572682380676,
      "learning_rate": 1.963910679652128e-05,
      "loss": 0.6066,
      "step": 5677
    },
    {
      "epoch": 0.17442324824132951,
      "grad_norm": 0.34608033299446106,
      "learning_rate": 1.9638978124346645e-05,
      "loss": 0.638,
      "step": 5678
    },
    {
      "epoch": 0.1744539673762787,
      "grad_norm": 0.32037535309791565,
      "learning_rate": 1.9638849429659502e-05,
      "loss": 0.5943,
      "step": 5679
    },
    {
      "epoch": 0.17448468651122784,
      "grad_norm": 0.4516572952270508,
      "learning_rate": 1.9638720712460158e-05,
      "loss": 0.4953,
      "step": 5680
    },
    {
      "epoch": 0.174515405646177,
      "grad_norm": 0.31835776567459106,
      "learning_rate": 1.9638591972748904e-05,
      "loss": 0.5968,
      "step": 5681
    },
    {
      "epoch": 0.17454612478112616,
      "grad_norm": 0.33262524008750916,
      "learning_rate": 1.9638463210526045e-05,
      "loss": 0.5356,
      "step": 5682
    },
    {
      "epoch": 0.17457684391607534,
      "grad_norm": 0.3662828505039215,
      "learning_rate": 1.9638334425791886e-05,
      "loss": 0.5648,
      "step": 5683
    },
    {
      "epoch": 0.17460756305102448,
      "grad_norm": 0.33483803272247314,
      "learning_rate": 1.9638205618546723e-05,
      "loss": 0.5617,
      "step": 5684
    },
    {
      "epoch": 0.17463828218597363,
      "grad_norm": 0.3551047146320343,
      "learning_rate": 1.9638076788790855e-05,
      "loss": 0.62,
      "step": 5685
    },
    {
      "epoch": 0.1746690013209228,
      "grad_norm": 0.3223101496696472,
      "learning_rate": 1.9637947936524586e-05,
      "loss": 0.6434,
      "step": 5686
    },
    {
      "epoch": 0.17469972045587195,
      "grad_norm": 0.33438369631767273,
      "learning_rate": 1.963781906174822e-05,
      "loss": 0.5946,
      "step": 5687
    },
    {
      "epoch": 0.17473043959082113,
      "grad_norm": 0.34336990118026733,
      "learning_rate": 1.963769016446205e-05,
      "loss": 0.5769,
      "step": 5688
    },
    {
      "epoch": 0.17476115872577028,
      "grad_norm": 0.36977240443229675,
      "learning_rate": 1.9637561244666385e-05,
      "loss": 0.616,
      "step": 5689
    },
    {
      "epoch": 0.17479187786071945,
      "grad_norm": 0.32806625962257385,
      "learning_rate": 1.963743230236152e-05,
      "loss": 0.6503,
      "step": 5690
    },
    {
      "epoch": 0.1748225969956686,
      "grad_norm": 0.3659497797489166,
      "learning_rate": 1.963730333754776e-05,
      "loss": 0.5782,
      "step": 5691
    },
    {
      "epoch": 0.17485331613061778,
      "grad_norm": 0.3406502902507782,
      "learning_rate": 1.9637174350225404e-05,
      "loss": 0.5474,
      "step": 5692
    },
    {
      "epoch": 0.17488403526556692,
      "grad_norm": 0.35167160630226135,
      "learning_rate": 1.9637045340394757e-05,
      "loss": 0.6464,
      "step": 5693
    },
    {
      "epoch": 0.17491475440051607,
      "grad_norm": 0.292737752199173,
      "learning_rate": 1.9636916308056114e-05,
      "loss": 0.6144,
      "step": 5694
    },
    {
      "epoch": 0.17494547353546525,
      "grad_norm": 0.31501293182373047,
      "learning_rate": 1.9636787253209782e-05,
      "loss": 0.6104,
      "step": 5695
    },
    {
      "epoch": 0.1749761926704144,
      "grad_norm": 0.3093787133693695,
      "learning_rate": 1.963665817585606e-05,
      "loss": 0.5192,
      "step": 5696
    },
    {
      "epoch": 0.17500691180536357,
      "grad_norm": 0.3553764224052429,
      "learning_rate": 1.963652907599525e-05,
      "loss": 0.603,
      "step": 5697
    },
    {
      "epoch": 0.17503763094031272,
      "grad_norm": 0.3240797221660614,
      "learning_rate": 1.9636399953627654e-05,
      "loss": 0.5767,
      "step": 5698
    },
    {
      "epoch": 0.1750683500752619,
      "grad_norm": 0.3481632173061371,
      "learning_rate": 1.963627080875357e-05,
      "loss": 0.5308,
      "step": 5699
    },
    {
      "epoch": 0.17509906921021104,
      "grad_norm": 0.31709152460098267,
      "learning_rate": 1.9636141641373306e-05,
      "loss": 0.527,
      "step": 5700
    },
    {
      "epoch": 0.1751297883451602,
      "grad_norm": 0.3323947787284851,
      "learning_rate": 1.9636012451487158e-05,
      "loss": 0.598,
      "step": 5701
    },
    {
      "epoch": 0.17516050748010936,
      "grad_norm": 0.5247969627380371,
      "learning_rate": 1.963588323909543e-05,
      "loss": 0.6457,
      "step": 5702
    },
    {
      "epoch": 0.1751912266150585,
      "grad_norm": 0.3346257209777832,
      "learning_rate": 1.9635754004198424e-05,
      "loss": 0.6205,
      "step": 5703
    },
    {
      "epoch": 0.17522194575000768,
      "grad_norm": 0.44319528341293335,
      "learning_rate": 1.963562474679644e-05,
      "loss": 0.5461,
      "step": 5704
    },
    {
      "epoch": 0.17525266488495683,
      "grad_norm": 0.3716953694820404,
      "learning_rate": 1.9635495466889787e-05,
      "loss": 0.5719,
      "step": 5705
    },
    {
      "epoch": 0.175283384019906,
      "grad_norm": 0.4499550759792328,
      "learning_rate": 1.9635366164478757e-05,
      "loss": 0.5485,
      "step": 5706
    },
    {
      "epoch": 0.17531410315485516,
      "grad_norm": 0.3294755518436432,
      "learning_rate": 1.9635236839563658e-05,
      "loss": 0.6875,
      "step": 5707
    },
    {
      "epoch": 0.17534482228980433,
      "grad_norm": 0.35993674397468567,
      "learning_rate": 1.963510749214479e-05,
      "loss": 0.6014,
      "step": 5708
    },
    {
      "epoch": 0.17537554142475348,
      "grad_norm": 0.5128867626190186,
      "learning_rate": 1.9634978122222454e-05,
      "loss": 0.6441,
      "step": 5709
    },
    {
      "epoch": 0.17540626055970263,
      "grad_norm": 0.32538819313049316,
      "learning_rate": 1.9634848729796955e-05,
      "loss": 0.6026,
      "step": 5710
    },
    {
      "epoch": 0.1754369796946518,
      "grad_norm": 0.3805907964706421,
      "learning_rate": 1.9634719314868596e-05,
      "loss": 0.6854,
      "step": 5711
    },
    {
      "epoch": 0.17546769882960095,
      "grad_norm": 0.3352387845516205,
      "learning_rate": 1.9634589877437676e-05,
      "loss": 0.5689,
      "step": 5712
    },
    {
      "epoch": 0.17549841796455012,
      "grad_norm": 0.3458799719810486,
      "learning_rate": 1.9634460417504495e-05,
      "loss": 0.5613,
      "step": 5713
    },
    {
      "epoch": 0.17552913709949927,
      "grad_norm": 0.35942038893699646,
      "learning_rate": 1.9634330935069362e-05,
      "loss": 0.5759,
      "step": 5714
    },
    {
      "epoch": 0.17555985623444845,
      "grad_norm": 0.32010528445243835,
      "learning_rate": 1.9634201430132575e-05,
      "loss": 0.5603,
      "step": 5715
    },
    {
      "epoch": 0.1755905753693976,
      "grad_norm": 0.33179616928100586,
      "learning_rate": 1.963407190269444e-05,
      "loss": 0.5816,
      "step": 5716
    },
    {
      "epoch": 0.17562129450434677,
      "grad_norm": 0.3136884570121765,
      "learning_rate": 1.9633942352755257e-05,
      "loss": 0.5191,
      "step": 5717
    },
    {
      "epoch": 0.17565201363929592,
      "grad_norm": 0.3244498670101166,
      "learning_rate": 1.9633812780315324e-05,
      "loss": 0.62,
      "step": 5718
    },
    {
      "epoch": 0.17568273277424507,
      "grad_norm": 0.7702068090438843,
      "learning_rate": 1.963368318537495e-05,
      "loss": 0.5505,
      "step": 5719
    },
    {
      "epoch": 0.17571345190919424,
      "grad_norm": 0.30794650316238403,
      "learning_rate": 1.9633553567934442e-05,
      "loss": 0.5486,
      "step": 5720
    },
    {
      "epoch": 0.1757441710441434,
      "grad_norm": 0.3979911804199219,
      "learning_rate": 1.963342392799409e-05,
      "loss": 0.5905,
      "step": 5721
    },
    {
      "epoch": 0.17577489017909256,
      "grad_norm": 0.3544567823410034,
      "learning_rate": 1.9633294265554208e-05,
      "loss": 0.5599,
      "step": 5722
    },
    {
      "epoch": 0.1758056093140417,
      "grad_norm": 0.3533678352832794,
      "learning_rate": 1.963316458061509e-05,
      "loss": 0.6137,
      "step": 5723
    },
    {
      "epoch": 0.1758363284489909,
      "grad_norm": 0.34221887588500977,
      "learning_rate": 1.963303487317705e-05,
      "loss": 0.6296,
      "step": 5724
    },
    {
      "epoch": 0.17586704758394003,
      "grad_norm": 1.1069225072860718,
      "learning_rate": 1.963290514324038e-05,
      "loss": 0.6194,
      "step": 5725
    },
    {
      "epoch": 0.1758977667188892,
      "grad_norm": 1.52217435836792,
      "learning_rate": 1.9632775390805387e-05,
      "loss": 0.5882,
      "step": 5726
    },
    {
      "epoch": 0.17592848585383836,
      "grad_norm": 0.3795982897281647,
      "learning_rate": 1.9632645615872376e-05,
      "loss": 0.656,
      "step": 5727
    },
    {
      "epoch": 0.1759592049887875,
      "grad_norm": 0.386619508266449,
      "learning_rate": 1.9632515818441648e-05,
      "loss": 0.5244,
      "step": 5728
    },
    {
      "epoch": 0.17598992412373668,
      "grad_norm": 0.30955347418785095,
      "learning_rate": 1.9632385998513505e-05,
      "loss": 0.5999,
      "step": 5729
    },
    {
      "epoch": 0.17602064325868583,
      "grad_norm": 0.338687926530838,
      "learning_rate": 1.963225615608825e-05,
      "loss": 0.5358,
      "step": 5730
    },
    {
      "epoch": 0.176051362393635,
      "grad_norm": 0.3480183482170105,
      "learning_rate": 1.9632126291166192e-05,
      "loss": 0.6566,
      "step": 5731
    },
    {
      "epoch": 0.17608208152858415,
      "grad_norm": 0.30929237604141235,
      "learning_rate": 1.963199640374763e-05,
      "loss": 0.5711,
      "step": 5732
    },
    {
      "epoch": 0.17611280066353333,
      "grad_norm": 0.32771462202072144,
      "learning_rate": 1.9631866493832868e-05,
      "loss": 0.6524,
      "step": 5733
    },
    {
      "epoch": 0.17614351979848247,
      "grad_norm": 0.32370367646217346,
      "learning_rate": 1.9631736561422205e-05,
      "loss": 0.5426,
      "step": 5734
    },
    {
      "epoch": 0.17617423893343165,
      "grad_norm": 0.32531702518463135,
      "learning_rate": 1.9631606606515953e-05,
      "loss": 0.5537,
      "step": 5735
    },
    {
      "epoch": 0.1762049580683808,
      "grad_norm": 0.3675678074359894,
      "learning_rate": 1.963147662911441e-05,
      "loss": 0.6304,
      "step": 5736
    },
    {
      "epoch": 0.17623567720332994,
      "grad_norm": 0.30853405594825745,
      "learning_rate": 1.963134662921788e-05,
      "loss": 0.5944,
      "step": 5737
    },
    {
      "epoch": 0.17626639633827912,
      "grad_norm": 0.3208543360233307,
      "learning_rate": 1.9631216606826668e-05,
      "loss": 0.6433,
      "step": 5738
    },
    {
      "epoch": 0.17629711547322827,
      "grad_norm": 0.34031128883361816,
      "learning_rate": 1.963108656194108e-05,
      "loss": 0.5917,
      "step": 5739
    },
    {
      "epoch": 0.17632783460817744,
      "grad_norm": 0.32263973355293274,
      "learning_rate": 1.963095649456141e-05,
      "loss": 0.5781,
      "step": 5740
    },
    {
      "epoch": 0.1763585537431266,
      "grad_norm": 0.3225199282169342,
      "learning_rate": 1.963082640468797e-05,
      "loss": 0.6047,
      "step": 5741
    },
    {
      "epoch": 0.17638927287807576,
      "grad_norm": 0.3392980992794037,
      "learning_rate": 1.9630696292321066e-05,
      "loss": 0.6107,
      "step": 5742
    },
    {
      "epoch": 0.1764199920130249,
      "grad_norm": 0.33307161927223206,
      "learning_rate": 1.9630566157460997e-05,
      "loss": 0.5975,
      "step": 5743
    },
    {
      "epoch": 0.17645071114797406,
      "grad_norm": 0.34703290462493896,
      "learning_rate": 1.9630436000108067e-05,
      "loss": 0.5709,
      "step": 5744
    },
    {
      "epoch": 0.17648143028292324,
      "grad_norm": 0.3018288016319275,
      "learning_rate": 1.9630305820262584e-05,
      "loss": 0.5509,
      "step": 5745
    },
    {
      "epoch": 0.17651214941787238,
      "grad_norm": 0.562344491481781,
      "learning_rate": 1.9630175617924845e-05,
      "loss": 0.6119,
      "step": 5746
    },
    {
      "epoch": 0.17654286855282156,
      "grad_norm": 0.33096569776535034,
      "learning_rate": 1.963004539309516e-05,
      "loss": 0.607,
      "step": 5747
    },
    {
      "epoch": 0.1765735876877707,
      "grad_norm": 0.3747745156288147,
      "learning_rate": 1.9629915145773832e-05,
      "loss": 0.6524,
      "step": 5748
    },
    {
      "epoch": 0.17660430682271988,
      "grad_norm": 0.31846925616264343,
      "learning_rate": 1.9629784875961165e-05,
      "loss": 0.6015,
      "step": 5749
    },
    {
      "epoch": 0.17663502595766903,
      "grad_norm": 0.33582842350006104,
      "learning_rate": 1.962965458365746e-05,
      "loss": 0.5182,
      "step": 5750
    },
    {
      "epoch": 0.1766657450926182,
      "grad_norm": 0.33399876952171326,
      "learning_rate": 1.962952426886303e-05,
      "loss": 0.581,
      "step": 5751
    },
    {
      "epoch": 0.17669646422756735,
      "grad_norm": 0.3014501631259918,
      "learning_rate": 1.962939393157817e-05,
      "loss": 0.6583,
      "step": 5752
    },
    {
      "epoch": 0.1767271833625165,
      "grad_norm": 0.3024846911430359,
      "learning_rate": 1.9629263571803185e-05,
      "loss": 0.5818,
      "step": 5753
    },
    {
      "epoch": 0.17675790249746567,
      "grad_norm": 0.3692941963672638,
      "learning_rate": 1.9629133189538386e-05,
      "loss": 0.6187,
      "step": 5754
    },
    {
      "epoch": 0.17678862163241482,
      "grad_norm": 0.32692742347717285,
      "learning_rate": 1.9629002784784076e-05,
      "loss": 0.5921,
      "step": 5755
    },
    {
      "epoch": 0.176819340767364,
      "grad_norm": 0.36419326066970825,
      "learning_rate": 1.962887235754055e-05,
      "loss": 0.6278,
      "step": 5756
    },
    {
      "epoch": 0.17685005990231314,
      "grad_norm": 0.3319969177246094,
      "learning_rate": 1.9628741907808126e-05,
      "loss": 0.5802,
      "step": 5757
    },
    {
      "epoch": 0.17688077903726232,
      "grad_norm": 0.3312731981277466,
      "learning_rate": 1.96286114355871e-05,
      "loss": 0.5754,
      "step": 5758
    },
    {
      "epoch": 0.17691149817221147,
      "grad_norm": 0.40532538294792175,
      "learning_rate": 1.9628480940877783e-05,
      "loss": 0.5676,
      "step": 5759
    },
    {
      "epoch": 0.17694221730716064,
      "grad_norm": 0.33322012424468994,
      "learning_rate": 1.9628350423680476e-05,
      "loss": 0.6138,
      "step": 5760
    },
    {
      "epoch": 0.1769729364421098,
      "grad_norm": 0.35307636857032776,
      "learning_rate": 1.962821988399548e-05,
      "loss": 0.6125,
      "step": 5761
    },
    {
      "epoch": 0.17700365557705894,
      "grad_norm": 0.35598546266555786,
      "learning_rate": 1.962808932182311e-05,
      "loss": 0.6228,
      "step": 5762
    },
    {
      "epoch": 0.1770343747120081,
      "grad_norm": 0.32881391048431396,
      "learning_rate": 1.962795873716366e-05,
      "loss": 0.6115,
      "step": 5763
    },
    {
      "epoch": 0.17706509384695726,
      "grad_norm": 0.3414410352706909,
      "learning_rate": 1.9627828130017442e-05,
      "loss": 0.6018,
      "step": 5764
    },
    {
      "epoch": 0.17709581298190644,
      "grad_norm": 0.31860968470573425,
      "learning_rate": 1.9627697500384758e-05,
      "loss": 0.6478,
      "step": 5765
    },
    {
      "epoch": 0.17712653211685558,
      "grad_norm": 0.38471007347106934,
      "learning_rate": 1.9627566848265914e-05,
      "loss": 0.5775,
      "step": 5766
    },
    {
      "epoch": 0.17715725125180476,
      "grad_norm": 0.35019633173942566,
      "learning_rate": 1.9627436173661215e-05,
      "loss": 0.5961,
      "step": 5767
    },
    {
      "epoch": 0.1771879703867539,
      "grad_norm": 0.35821962356567383,
      "learning_rate": 1.962730547657097e-05,
      "loss": 0.6364,
      "step": 5768
    },
    {
      "epoch": 0.17721868952170308,
      "grad_norm": 0.34582415223121643,
      "learning_rate": 1.962717475699548e-05,
      "loss": 0.6402,
      "step": 5769
    },
    {
      "epoch": 0.17724940865665223,
      "grad_norm": 0.3670668601989746,
      "learning_rate": 1.9627044014935048e-05,
      "loss": 0.6279,
      "step": 5770
    },
    {
      "epoch": 0.17728012779160138,
      "grad_norm": 0.3274271786212921,
      "learning_rate": 1.9626913250389982e-05,
      "loss": 0.5495,
      "step": 5771
    },
    {
      "epoch": 0.17731084692655055,
      "grad_norm": 0.3731943368911743,
      "learning_rate": 1.962678246336059e-05,
      "loss": 0.5867,
      "step": 5772
    },
    {
      "epoch": 0.1773415660614997,
      "grad_norm": 0.3146427571773529,
      "learning_rate": 1.9626651653847174e-05,
      "loss": 0.6156,
      "step": 5773
    },
    {
      "epoch": 0.17737228519644888,
      "grad_norm": 0.34232228994369507,
      "learning_rate": 1.962652082185004e-05,
      "loss": 0.5687,
      "step": 5774
    },
    {
      "epoch": 0.17740300433139802,
      "grad_norm": 0.3602336049079895,
      "learning_rate": 1.9626389967369497e-05,
      "loss": 0.6391,
      "step": 5775
    },
    {
      "epoch": 0.1774337234663472,
      "grad_norm": 0.32230815291404724,
      "learning_rate": 1.962625909040585e-05,
      "loss": 0.6528,
      "step": 5776
    },
    {
      "epoch": 0.17746444260129635,
      "grad_norm": 0.3278484046459198,
      "learning_rate": 1.96261281909594e-05,
      "loss": 0.4783,
      "step": 5777
    },
    {
      "epoch": 0.1774951617362455,
      "grad_norm": 0.3238432705402374,
      "learning_rate": 1.962599726903045e-05,
      "loss": 0.5446,
      "step": 5778
    },
    {
      "epoch": 0.17752588087119467,
      "grad_norm": 0.38078105449676514,
      "learning_rate": 1.9625866324619317e-05,
      "loss": 0.5439,
      "step": 5779
    },
    {
      "epoch": 0.17755660000614382,
      "grad_norm": 0.33114346861839294,
      "learning_rate": 1.96257353577263e-05,
      "loss": 0.6469,
      "step": 5780
    },
    {
      "epoch": 0.177587319141093,
      "grad_norm": 0.33132344484329224,
      "learning_rate": 1.9625604368351703e-05,
      "loss": 0.5814,
      "step": 5781
    },
    {
      "epoch": 0.17761803827604214,
      "grad_norm": 0.3414350748062134,
      "learning_rate": 1.9625473356495835e-05,
      "loss": 0.6917,
      "step": 5782
    },
    {
      "epoch": 0.17764875741099131,
      "grad_norm": 0.33242037892341614,
      "learning_rate": 1.962534232215901e-05,
      "loss": 0.6502,
      "step": 5783
    },
    {
      "epoch": 0.17767947654594046,
      "grad_norm": 0.33265525102615356,
      "learning_rate": 1.9625211265341514e-05,
      "loss": 0.5909,
      "step": 5784
    },
    {
      "epoch": 0.17771019568088964,
      "grad_norm": 0.35636553168296814,
      "learning_rate": 1.9625080186043673e-05,
      "loss": 0.6224,
      "step": 5785
    },
    {
      "epoch": 0.17774091481583879,
      "grad_norm": 0.3760618269443512,
      "learning_rate": 1.962494908426578e-05,
      "loss": 0.5654,
      "step": 5786
    },
    {
      "epoch": 0.17777163395078793,
      "grad_norm": 0.3437193036079407,
      "learning_rate": 1.962481796000815e-05,
      "loss": 0.5761,
      "step": 5787
    },
    {
      "epoch": 0.1778023530857371,
      "grad_norm": 0.3655988276004791,
      "learning_rate": 1.9624686813271085e-05,
      "loss": 0.6108,
      "step": 5788
    },
    {
      "epoch": 0.17783307222068626,
      "grad_norm": 0.36786213517189026,
      "learning_rate": 1.962455564405489e-05,
      "loss": 0.613,
      "step": 5789
    },
    {
      "epoch": 0.17786379135563543,
      "grad_norm": 0.33519890904426575,
      "learning_rate": 1.9624424452359877e-05,
      "loss": 0.5835,
      "step": 5790
    },
    {
      "epoch": 0.17789451049058458,
      "grad_norm": 0.2975212335586548,
      "learning_rate": 1.962429323818634e-05,
      "loss": 0.4777,
      "step": 5791
    },
    {
      "epoch": 0.17792522962553375,
      "grad_norm": 0.34186840057373047,
      "learning_rate": 1.9624162001534604e-05,
      "loss": 0.5957,
      "step": 5792
    },
    {
      "epoch": 0.1779559487604829,
      "grad_norm": 0.3320673108100891,
      "learning_rate": 1.9624030742404957e-05,
      "loss": 0.5466,
      "step": 5793
    },
    {
      "epoch": 0.17798666789543208,
      "grad_norm": 0.2832508683204651,
      "learning_rate": 1.9623899460797718e-05,
      "loss": 0.5283,
      "step": 5794
    },
    {
      "epoch": 0.17801738703038122,
      "grad_norm": 0.3308786153793335,
      "learning_rate": 1.9623768156713193e-05,
      "loss": 0.5386,
      "step": 5795
    },
    {
      "epoch": 0.17804810616533037,
      "grad_norm": 0.35667458176612854,
      "learning_rate": 1.9623636830151684e-05,
      "loss": 0.6213,
      "step": 5796
    },
    {
      "epoch": 0.17807882530027955,
      "grad_norm": 0.3427836298942566,
      "learning_rate": 1.9623505481113497e-05,
      "loss": 0.5794,
      "step": 5797
    },
    {
      "epoch": 0.1781095444352287,
      "grad_norm": 0.35619425773620605,
      "learning_rate": 1.962337410959894e-05,
      "loss": 0.6414,
      "step": 5798
    },
    {
      "epoch": 0.17814026357017787,
      "grad_norm": 0.3518011271953583,
      "learning_rate": 1.962324271560832e-05,
      "loss": 0.5827,
      "step": 5799
    },
    {
      "epoch": 0.17817098270512702,
      "grad_norm": 0.3717316687107086,
      "learning_rate": 1.962311129914195e-05,
      "loss": 0.6244,
      "step": 5800
    },
    {
      "epoch": 0.1782017018400762,
      "grad_norm": 0.31487390398979187,
      "learning_rate": 1.9622979860200123e-05,
      "loss": 0.6052,
      "step": 5801
    },
    {
      "epoch": 0.17823242097502534,
      "grad_norm": 0.39106839895248413,
      "learning_rate": 1.962284839878316e-05,
      "loss": 0.5659,
      "step": 5802
    },
    {
      "epoch": 0.17826314010997452,
      "grad_norm": 0.37291470170021057,
      "learning_rate": 1.9622716914891364e-05,
      "loss": 0.5705,
      "step": 5803
    },
    {
      "epoch": 0.17829385924492366,
      "grad_norm": 0.34869319200515747,
      "learning_rate": 1.9622585408525037e-05,
      "loss": 0.6373,
      "step": 5804
    },
    {
      "epoch": 0.1783245783798728,
      "grad_norm": 0.3345906138420105,
      "learning_rate": 1.962245387968449e-05,
      "loss": 0.5867,
      "step": 5805
    },
    {
      "epoch": 0.178355297514822,
      "grad_norm": 0.30773136019706726,
      "learning_rate": 1.9622322328370032e-05,
      "loss": 0.6047,
      "step": 5806
    },
    {
      "epoch": 0.17838601664977113,
      "grad_norm": 0.2998821437358856,
      "learning_rate": 1.962219075458197e-05,
      "loss": 0.5655,
      "step": 5807
    },
    {
      "epoch": 0.1784167357847203,
      "grad_norm": 0.3182363510131836,
      "learning_rate": 1.9622059158320606e-05,
      "loss": 0.6185,
      "step": 5808
    },
    {
      "epoch": 0.17844745491966946,
      "grad_norm": 0.3550657629966736,
      "learning_rate": 1.962192753958625e-05,
      "loss": 0.5999,
      "step": 5809
    },
    {
      "epoch": 0.17847817405461863,
      "grad_norm": 0.3329761326313019,
      "learning_rate": 1.9621795898379212e-05,
      "loss": 0.6839,
      "step": 5810
    },
    {
      "epoch": 0.17850889318956778,
      "grad_norm": 0.3710383474826813,
      "learning_rate": 1.96216642346998e-05,
      "loss": 0.6066,
      "step": 5811
    },
    {
      "epoch": 0.17853961232451696,
      "grad_norm": 0.3317925035953522,
      "learning_rate": 1.9621532548548314e-05,
      "loss": 0.5652,
      "step": 5812
    },
    {
      "epoch": 0.1785703314594661,
      "grad_norm": 0.31721335649490356,
      "learning_rate": 1.9621400839925072e-05,
      "loss": 0.5387,
      "step": 5813
    },
    {
      "epoch": 0.17860105059441525,
      "grad_norm": 0.3430209457874298,
      "learning_rate": 1.962126910883037e-05,
      "loss": 0.6194,
      "step": 5814
    },
    {
      "epoch": 0.17863176972936443,
      "grad_norm": 0.38024261593818665,
      "learning_rate": 1.962113735526453e-05,
      "loss": 0.6136,
      "step": 5815
    },
    {
      "epoch": 0.17866248886431357,
      "grad_norm": 0.33810368180274963,
      "learning_rate": 1.9621005579227846e-05,
      "loss": 0.5892,
      "step": 5816
    },
    {
      "epoch": 0.17869320799926275,
      "grad_norm": 0.3623286783695221,
      "learning_rate": 1.9620873780720632e-05,
      "loss": 0.5121,
      "step": 5817
    },
    {
      "epoch": 0.1787239271342119,
      "grad_norm": 0.33343350887298584,
      "learning_rate": 1.9620741959743195e-05,
      "loss": 0.5485,
      "step": 5818
    },
    {
      "epoch": 0.17875464626916107,
      "grad_norm": 0.3569234609603882,
      "learning_rate": 1.962061011629585e-05,
      "loss": 0.5808,
      "step": 5819
    },
    {
      "epoch": 0.17878536540411022,
      "grad_norm": 0.3416958451271057,
      "learning_rate": 1.962047825037889e-05,
      "loss": 0.591,
      "step": 5820
    },
    {
      "epoch": 0.17881608453905937,
      "grad_norm": 0.3570687174797058,
      "learning_rate": 1.9620346361992634e-05,
      "loss": 0.5956,
      "step": 5821
    },
    {
      "epoch": 0.17884680367400854,
      "grad_norm": 0.36399132013320923,
      "learning_rate": 1.962021445113739e-05,
      "loss": 0.6093,
      "step": 5822
    },
    {
      "epoch": 0.1788775228089577,
      "grad_norm": 0.37462317943573,
      "learning_rate": 1.9620082517813456e-05,
      "loss": 0.6687,
      "step": 5823
    },
    {
      "epoch": 0.17890824194390686,
      "grad_norm": 0.34316208958625793,
      "learning_rate": 1.9619950562021155e-05,
      "loss": 0.6088,
      "step": 5824
    },
    {
      "epoch": 0.178938961078856,
      "grad_norm": 0.36561399698257446,
      "learning_rate": 1.9619818583760786e-05,
      "loss": 0.7036,
      "step": 5825
    },
    {
      "epoch": 0.1789696802138052,
      "grad_norm": 0.3519943058490753,
      "learning_rate": 1.9619686583032655e-05,
      "loss": 0.624,
      "step": 5826
    },
    {
      "epoch": 0.17900039934875434,
      "grad_norm": 0.38444215059280396,
      "learning_rate": 1.9619554559837077e-05,
      "loss": 0.6326,
      "step": 5827
    },
    {
      "epoch": 0.1790311184837035,
      "grad_norm": 0.32651039958000183,
      "learning_rate": 1.9619422514174357e-05,
      "loss": 0.6166,
      "step": 5828
    },
    {
      "epoch": 0.17906183761865266,
      "grad_norm": 0.3256683945655823,
      "learning_rate": 1.9619290446044805e-05,
      "loss": 0.614,
      "step": 5829
    },
    {
      "epoch": 0.1790925567536018,
      "grad_norm": 0.37137094140052795,
      "learning_rate": 1.961915835544873e-05,
      "loss": 0.6044,
      "step": 5830
    },
    {
      "epoch": 0.17912327588855098,
      "grad_norm": 0.32280024886131287,
      "learning_rate": 1.9619026242386434e-05,
      "loss": 0.6139,
      "step": 5831
    },
    {
      "epoch": 0.17915399502350013,
      "grad_norm": 0.32023465633392334,
      "learning_rate": 1.9618894106858234e-05,
      "loss": 0.6148,
      "step": 5832
    },
    {
      "epoch": 0.1791847141584493,
      "grad_norm": 0.32320868968963623,
      "learning_rate": 1.9618761948864433e-05,
      "loss": 0.5297,
      "step": 5833
    },
    {
      "epoch": 0.17921543329339845,
      "grad_norm": 0.3266300559043884,
      "learning_rate": 1.961862976840534e-05,
      "loss": 0.5805,
      "step": 5834
    },
    {
      "epoch": 0.17924615242834763,
      "grad_norm": 0.342905730009079,
      "learning_rate": 1.961849756548127e-05,
      "loss": 0.6467,
      "step": 5835
    },
    {
      "epoch": 0.17927687156329677,
      "grad_norm": 0.33277425169944763,
      "learning_rate": 1.9618365340092523e-05,
      "loss": 0.5448,
      "step": 5836
    },
    {
      "epoch": 0.17930759069824595,
      "grad_norm": 0.35650634765625,
      "learning_rate": 1.9618233092239416e-05,
      "loss": 0.5961,
      "step": 5837
    },
    {
      "epoch": 0.1793383098331951,
      "grad_norm": 0.3802134096622467,
      "learning_rate": 1.9618100821922253e-05,
      "loss": 0.6688,
      "step": 5838
    },
    {
      "epoch": 0.17936902896814425,
      "grad_norm": 0.3339088261127472,
      "learning_rate": 1.9617968529141343e-05,
      "loss": 0.5828,
      "step": 5839
    },
    {
      "epoch": 0.17939974810309342,
      "grad_norm": 0.32241731882095337,
      "learning_rate": 1.9617836213896994e-05,
      "loss": 0.6489,
      "step": 5840
    },
    {
      "epoch": 0.17943046723804257,
      "grad_norm": 0.3094799816608429,
      "learning_rate": 1.9617703876189517e-05,
      "loss": 0.5752,
      "step": 5841
    },
    {
      "epoch": 0.17946118637299174,
      "grad_norm": 0.38574811816215515,
      "learning_rate": 1.9617571516019225e-05,
      "loss": 0.6168,
      "step": 5842
    },
    {
      "epoch": 0.1794919055079409,
      "grad_norm": 0.3265090584754944,
      "learning_rate": 1.961743913338642e-05,
      "loss": 0.5556,
      "step": 5843
    },
    {
      "epoch": 0.17952262464289007,
      "grad_norm": 0.34094005823135376,
      "learning_rate": 1.9617306728291416e-05,
      "loss": 0.6067,
      "step": 5844
    },
    {
      "epoch": 0.1795533437778392,
      "grad_norm": 0.35036829113960266,
      "learning_rate": 1.961717430073452e-05,
      "loss": 0.6297,
      "step": 5845
    },
    {
      "epoch": 0.1795840629127884,
      "grad_norm": 0.32529789209365845,
      "learning_rate": 1.9617041850716037e-05,
      "loss": 0.5409,
      "step": 5846
    },
    {
      "epoch": 0.17961478204773754,
      "grad_norm": 0.3696594536304474,
      "learning_rate": 1.9616909378236288e-05,
      "loss": 0.5857,
      "step": 5847
    },
    {
      "epoch": 0.17964550118268668,
      "grad_norm": 0.35495445132255554,
      "learning_rate": 1.9616776883295572e-05,
      "loss": 0.6142,
      "step": 5848
    },
    {
      "epoch": 0.17967622031763586,
      "grad_norm": 0.3458004295825958,
      "learning_rate": 1.9616644365894203e-05,
      "loss": 0.5518,
      "step": 5849
    },
    {
      "epoch": 0.179706939452585,
      "grad_norm": 0.3345881700515747,
      "learning_rate": 1.9616511826032488e-05,
      "loss": 0.6094,
      "step": 5850
    },
    {
      "epoch": 0.17973765858753418,
      "grad_norm": 0.3390195071697235,
      "learning_rate": 1.961637926371074e-05,
      "loss": 0.5731,
      "step": 5851
    },
    {
      "epoch": 0.17976837772248333,
      "grad_norm": 0.4023333191871643,
      "learning_rate": 1.9616246678929263e-05,
      "loss": 0.6031,
      "step": 5852
    },
    {
      "epoch": 0.1797990968574325,
      "grad_norm": 0.3400143086910248,
      "learning_rate": 1.9616114071688374e-05,
      "loss": 0.6328,
      "step": 5853
    },
    {
      "epoch": 0.17982981599238165,
      "grad_norm": 0.3326917886734009,
      "learning_rate": 1.961598144198838e-05,
      "loss": 0.55,
      "step": 5854
    },
    {
      "epoch": 0.1798605351273308,
      "grad_norm": 0.33303266763687134,
      "learning_rate": 1.9615848789829584e-05,
      "loss": 0.576,
      "step": 5855
    },
    {
      "epoch": 0.17989125426227998,
      "grad_norm": 0.3302069306373596,
      "learning_rate": 1.9615716115212306e-05,
      "loss": 0.5525,
      "step": 5856
    },
    {
      "epoch": 0.17992197339722912,
      "grad_norm": 0.4240674078464508,
      "learning_rate": 1.961558341813685e-05,
      "loss": 0.5361,
      "step": 5857
    },
    {
      "epoch": 0.1799526925321783,
      "grad_norm": 0.32118913531303406,
      "learning_rate": 1.9615450698603527e-05,
      "loss": 0.625,
      "step": 5858
    },
    {
      "epoch": 0.17998341166712745,
      "grad_norm": 0.3132808208465576,
      "learning_rate": 1.961531795661265e-05,
      "loss": 0.4957,
      "step": 5859
    },
    {
      "epoch": 0.18001413080207662,
      "grad_norm": 0.40022581815719604,
      "learning_rate": 1.9615185192164525e-05,
      "loss": 0.6497,
      "step": 5860
    },
    {
      "epoch": 0.18004484993702577,
      "grad_norm": 0.38109326362609863,
      "learning_rate": 1.961505240525946e-05,
      "loss": 0.6693,
      "step": 5861
    },
    {
      "epoch": 0.18007556907197494,
      "grad_norm": 0.3428618013858795,
      "learning_rate": 1.9614919595897778e-05,
      "loss": 0.5728,
      "step": 5862
    },
    {
      "epoch": 0.1801062882069241,
      "grad_norm": 0.3328629434108734,
      "learning_rate": 1.961478676407977e-05,
      "loss": 0.6043,
      "step": 5863
    },
    {
      "epoch": 0.18013700734187324,
      "grad_norm": 0.41157472133636475,
      "learning_rate": 1.961465390980576e-05,
      "loss": 0.5155,
      "step": 5864
    },
    {
      "epoch": 0.18016772647682242,
      "grad_norm": 0.37496158480644226,
      "learning_rate": 1.9614521033076055e-05,
      "loss": 0.6073,
      "step": 5865
    },
    {
      "epoch": 0.18019844561177156,
      "grad_norm": 0.34933289885520935,
      "learning_rate": 1.9614388133890966e-05,
      "loss": 0.713,
      "step": 5866
    },
    {
      "epoch": 0.18022916474672074,
      "grad_norm": 0.3635798692703247,
      "learning_rate": 1.96142552122508e-05,
      "loss": 0.6292,
      "step": 5867
    },
    {
      "epoch": 0.18025988388166989,
      "grad_norm": 0.3239299952983856,
      "learning_rate": 1.9614122268155865e-05,
      "loss": 0.5984,
      "step": 5868
    },
    {
      "epoch": 0.18029060301661906,
      "grad_norm": 0.582528829574585,
      "learning_rate": 1.9613989301606483e-05,
      "loss": 0.6081,
      "step": 5869
    },
    {
      "epoch": 0.1803213221515682,
      "grad_norm": 0.324512779712677,
      "learning_rate": 1.9613856312602952e-05,
      "loss": 0.5772,
      "step": 5870
    },
    {
      "epoch": 0.18035204128651738,
      "grad_norm": 0.3973548114299774,
      "learning_rate": 1.9613723301145594e-05,
      "loss": 0.6242,
      "step": 5871
    },
    {
      "epoch": 0.18038276042146653,
      "grad_norm": 0.34347814321517944,
      "learning_rate": 1.961359026723471e-05,
      "loss": 0.5784,
      "step": 5872
    },
    {
      "epoch": 0.18041347955641568,
      "grad_norm": 0.3494655191898346,
      "learning_rate": 1.9613457210870614e-05,
      "loss": 0.6223,
      "step": 5873
    },
    {
      "epoch": 0.18044419869136485,
      "grad_norm": 0.3337405025959015,
      "learning_rate": 1.961332413205362e-05,
      "loss": 0.5837,
      "step": 5874
    },
    {
      "epoch": 0.180474917826314,
      "grad_norm": 0.3243715167045593,
      "learning_rate": 1.9613191030784033e-05,
      "loss": 0.5431,
      "step": 5875
    },
    {
      "epoch": 0.18050563696126318,
      "grad_norm": 0.36223435401916504,
      "learning_rate": 1.9613057907062168e-05,
      "loss": 0.6252,
      "step": 5876
    },
    {
      "epoch": 0.18053635609621232,
      "grad_norm": 0.32095077633857727,
      "learning_rate": 1.9612924760888337e-05,
      "loss": 0.623,
      "step": 5877
    },
    {
      "epoch": 0.1805670752311615,
      "grad_norm": 0.3077680170536041,
      "learning_rate": 1.9612791592262847e-05,
      "loss": 0.5054,
      "step": 5878
    },
    {
      "epoch": 0.18059779436611065,
      "grad_norm": 0.3415769636631012,
      "learning_rate": 1.961265840118601e-05,
      "loss": 0.557,
      "step": 5879
    },
    {
      "epoch": 0.18062851350105982,
      "grad_norm": 0.32173171639442444,
      "learning_rate": 1.961252518765814e-05,
      "loss": 0.5987,
      "step": 5880
    },
    {
      "epoch": 0.18065923263600897,
      "grad_norm": 0.35862433910369873,
      "learning_rate": 1.9612391951679545e-05,
      "loss": 0.6746,
      "step": 5881
    },
    {
      "epoch": 0.18068995177095812,
      "grad_norm": 0.38454461097717285,
      "learning_rate": 1.9612258693250538e-05,
      "loss": 0.5577,
      "step": 5882
    },
    {
      "epoch": 0.1807206709059073,
      "grad_norm": 0.3392890989780426,
      "learning_rate": 1.961212541237143e-05,
      "loss": 0.5605,
      "step": 5883
    },
    {
      "epoch": 0.18075139004085644,
      "grad_norm": 0.37195006012916565,
      "learning_rate": 1.9611992109042532e-05,
      "loss": 0.7073,
      "step": 5884
    },
    {
      "epoch": 0.18078210917580562,
      "grad_norm": 0.38451117277145386,
      "learning_rate": 1.9611858783264153e-05,
      "loss": 0.5983,
      "step": 5885
    },
    {
      "epoch": 0.18081282831075476,
      "grad_norm": 0.432390034198761,
      "learning_rate": 1.961172543503661e-05,
      "loss": 0.6308,
      "step": 5886
    },
    {
      "epoch": 0.18084354744570394,
      "grad_norm": 0.7474333047866821,
      "learning_rate": 1.9611592064360208e-05,
      "loss": 0.6818,
      "step": 5887
    },
    {
      "epoch": 0.1808742665806531,
      "grad_norm": 0.36927178502082825,
      "learning_rate": 1.9611458671235262e-05,
      "loss": 0.6154,
      "step": 5888
    },
    {
      "epoch": 0.18090498571560226,
      "grad_norm": 0.3362596333026886,
      "learning_rate": 1.961132525566208e-05,
      "loss": 0.5609,
      "step": 5889
    },
    {
      "epoch": 0.1809357048505514,
      "grad_norm": 0.3263687193393707,
      "learning_rate": 1.9611191817640984e-05,
      "loss": 0.6408,
      "step": 5890
    },
    {
      "epoch": 0.18096642398550056,
      "grad_norm": 0.36071231961250305,
      "learning_rate": 1.961105835717227e-05,
      "loss": 0.6418,
      "step": 5891
    },
    {
      "epoch": 0.18099714312044973,
      "grad_norm": 0.32565635442733765,
      "learning_rate": 1.9610924874256262e-05,
      "loss": 0.5349,
      "step": 5892
    },
    {
      "epoch": 0.18102786225539888,
      "grad_norm": 0.32535284757614136,
      "learning_rate": 1.9610791368893268e-05,
      "loss": 0.5298,
      "step": 5893
    },
    {
      "epoch": 0.18105858139034806,
      "grad_norm": 0.3679327964782715,
      "learning_rate": 1.96106578410836e-05,
      "loss": 0.6625,
      "step": 5894
    },
    {
      "epoch": 0.1810893005252972,
      "grad_norm": 0.3955814242362976,
      "learning_rate": 1.9610524290827567e-05,
      "loss": 0.5782,
      "step": 5895
    },
    {
      "epoch": 0.18112001966024638,
      "grad_norm": 0.32898372411727905,
      "learning_rate": 1.9610390718125484e-05,
      "loss": 0.5602,
      "step": 5896
    },
    {
      "epoch": 0.18115073879519553,
      "grad_norm": 0.39398542046546936,
      "learning_rate": 1.9610257122977664e-05,
      "loss": 0.673,
      "step": 5897
    },
    {
      "epoch": 0.18118145793014467,
      "grad_norm": 0.30498769879341125,
      "learning_rate": 1.9610123505384417e-05,
      "loss": 0.5152,
      "step": 5898
    },
    {
      "epoch": 0.18121217706509385,
      "grad_norm": 0.36935940384864807,
      "learning_rate": 1.9609989865346054e-05,
      "loss": 0.6393,
      "step": 5899
    },
    {
      "epoch": 0.181242896200043,
      "grad_norm": 0.3456687033176422,
      "learning_rate": 1.9609856202862893e-05,
      "loss": 0.5531,
      "step": 5900
    },
    {
      "epoch": 0.18127361533499217,
      "grad_norm": 0.3408152163028717,
      "learning_rate": 1.9609722517935236e-05,
      "loss": 0.6154,
      "step": 5901
    },
    {
      "epoch": 0.18130433446994132,
      "grad_norm": 0.3023316562175751,
      "learning_rate": 1.96095888105634e-05,
      "loss": 0.6215,
      "step": 5902
    },
    {
      "epoch": 0.1813350536048905,
      "grad_norm": 0.33503296971321106,
      "learning_rate": 1.9609455080747705e-05,
      "loss": 0.6091,
      "step": 5903
    },
    {
      "epoch": 0.18136577273983964,
      "grad_norm": 0.3858528435230255,
      "learning_rate": 1.960932132848845e-05,
      "loss": 0.6319,
      "step": 5904
    },
    {
      "epoch": 0.18139649187478882,
      "grad_norm": 0.36531034111976624,
      "learning_rate": 1.9609187553785956e-05,
      "loss": 0.5362,
      "step": 5905
    },
    {
      "epoch": 0.18142721100973797,
      "grad_norm": 0.3235782980918884,
      "learning_rate": 1.960905375664054e-05,
      "loss": 0.5558,
      "step": 5906
    },
    {
      "epoch": 0.1814579301446871,
      "grad_norm": 0.36617445945739746,
      "learning_rate": 1.96089199370525e-05,
      "loss": 0.5911,
      "step": 5907
    },
    {
      "epoch": 0.1814886492796363,
      "grad_norm": 0.35041365027427673,
      "learning_rate": 1.9608786095022158e-05,
      "loss": 0.477,
      "step": 5908
    },
    {
      "epoch": 0.18151936841458544,
      "grad_norm": 0.598553478717804,
      "learning_rate": 1.960865223054982e-05,
      "loss": 0.5853,
      "step": 5909
    },
    {
      "epoch": 0.1815500875495346,
      "grad_norm": 0.3344889283180237,
      "learning_rate": 1.9608518343635815e-05,
      "loss": 0.6025,
      "step": 5910
    },
    {
      "epoch": 0.18158080668448376,
      "grad_norm": 0.40220779180526733,
      "learning_rate": 1.9608384434280436e-05,
      "loss": 0.6635,
      "step": 5911
    },
    {
      "epoch": 0.18161152581943293,
      "grad_norm": 0.3518521189689636,
      "learning_rate": 1.9608250502484007e-05,
      "loss": 0.6024,
      "step": 5912
    },
    {
      "epoch": 0.18164224495438208,
      "grad_norm": 0.3279089331626892,
      "learning_rate": 1.960811654824684e-05,
      "loss": 0.5663,
      "step": 5913
    },
    {
      "epoch": 0.18167296408933126,
      "grad_norm": 0.3207658529281616,
      "learning_rate": 1.960798257156924e-05,
      "loss": 0.6182,
      "step": 5914
    },
    {
      "epoch": 0.1817036832242804,
      "grad_norm": 0.3372577428817749,
      "learning_rate": 1.960784857245153e-05,
      "loss": 0.5652,
      "step": 5915
    },
    {
      "epoch": 0.18173440235922955,
      "grad_norm": 0.31637251377105713,
      "learning_rate": 1.9607714550894017e-05,
      "loss": 0.6118,
      "step": 5916
    },
    {
      "epoch": 0.18176512149417873,
      "grad_norm": 0.31511443853378296,
      "learning_rate": 1.960758050689702e-05,
      "loss": 0.578,
      "step": 5917
    },
    {
      "epoch": 0.18179584062912788,
      "grad_norm": 0.31717532873153687,
      "learning_rate": 1.960744644046084e-05,
      "loss": 0.5353,
      "step": 5918
    },
    {
      "epoch": 0.18182655976407705,
      "grad_norm": 0.5572600960731506,
      "learning_rate": 1.9607312351585803e-05,
      "loss": 0.6296,
      "step": 5919
    },
    {
      "epoch": 0.1818572788990262,
      "grad_norm": 0.3623197674751282,
      "learning_rate": 1.9607178240272216e-05,
      "loss": 0.607,
      "step": 5920
    },
    {
      "epoch": 0.18188799803397537,
      "grad_norm": 0.31170743703842163,
      "learning_rate": 1.960704410652039e-05,
      "loss": 0.5196,
      "step": 5921
    },
    {
      "epoch": 0.18191871716892452,
      "grad_norm": 0.372835248708725,
      "learning_rate": 1.9606909950330646e-05,
      "loss": 0.6503,
      "step": 5922
    },
    {
      "epoch": 0.1819494363038737,
      "grad_norm": 0.3382375240325928,
      "learning_rate": 1.9606775771703294e-05,
      "loss": 0.6235,
      "step": 5923
    },
    {
      "epoch": 0.18198015543882284,
      "grad_norm": 0.30778074264526367,
      "learning_rate": 1.960664157063864e-05,
      "loss": 0.6161,
      "step": 5924
    },
    {
      "epoch": 0.182010874573772,
      "grad_norm": 0.3268645107746124,
      "learning_rate": 1.960650734713701e-05,
      "loss": 0.5314,
      "step": 5925
    },
    {
      "epoch": 0.18204159370872117,
      "grad_norm": 0.34165048599243164,
      "learning_rate": 1.9606373101198708e-05,
      "loss": 0.6355,
      "step": 5926
    },
    {
      "epoch": 0.18207231284367031,
      "grad_norm": 0.39230114221572876,
      "learning_rate": 1.960623883282405e-05,
      "loss": 0.6112,
      "step": 5927
    },
    {
      "epoch": 0.1821030319786195,
      "grad_norm": 0.34133443236351013,
      "learning_rate": 1.9606104542013353e-05,
      "loss": 0.5847,
      "step": 5928
    },
    {
      "epoch": 0.18213375111356864,
      "grad_norm": 0.3248072564601898,
      "learning_rate": 1.9605970228766926e-05,
      "loss": 0.5309,
      "step": 5929
    },
    {
      "epoch": 0.1821644702485178,
      "grad_norm": 0.3303869366645813,
      "learning_rate": 1.9605835893085085e-05,
      "loss": 0.5912,
      "step": 5930
    },
    {
      "epoch": 0.18219518938346696,
      "grad_norm": 0.32488423585891724,
      "learning_rate": 1.9605701534968144e-05,
      "loss": 0.531,
      "step": 5931
    },
    {
      "epoch": 0.1822259085184161,
      "grad_norm": 0.33871930837631226,
      "learning_rate": 1.9605567154416418e-05,
      "loss": 0.4753,
      "step": 5932
    },
    {
      "epoch": 0.18225662765336528,
      "grad_norm": 0.3275834023952484,
      "learning_rate": 1.9605432751430217e-05,
      "loss": 0.6243,
      "step": 5933
    },
    {
      "epoch": 0.18228734678831443,
      "grad_norm": 0.35276320576667786,
      "learning_rate": 1.9605298326009857e-05,
      "loss": 0.6332,
      "step": 5934
    },
    {
      "epoch": 0.1823180659232636,
      "grad_norm": 0.3676069676876068,
      "learning_rate": 1.960516387815565e-05,
      "loss": 0.5366,
      "step": 5935
    },
    {
      "epoch": 0.18234878505821275,
      "grad_norm": 0.36111029982566833,
      "learning_rate": 1.9605029407867915e-05,
      "loss": 0.614,
      "step": 5936
    },
    {
      "epoch": 0.18237950419316193,
      "grad_norm": 0.37595903873443604,
      "learning_rate": 1.9604894915146962e-05,
      "loss": 0.5569,
      "step": 5937
    },
    {
      "epoch": 0.18241022332811108,
      "grad_norm": 0.33277520537376404,
      "learning_rate": 1.9604760399993105e-05,
      "loss": 0.5579,
      "step": 5938
    },
    {
      "epoch": 0.18244094246306025,
      "grad_norm": 0.31410112977027893,
      "learning_rate": 1.960462586240666e-05,
      "loss": 0.6531,
      "step": 5939
    },
    {
      "epoch": 0.1824716615980094,
      "grad_norm": 0.32106536626815796,
      "learning_rate": 1.9604491302387944e-05,
      "loss": 0.5256,
      "step": 5940
    },
    {
      "epoch": 0.18250238073295855,
      "grad_norm": 0.34931644797325134,
      "learning_rate": 1.960435671993726e-05,
      "loss": 0.5767,
      "step": 5941
    },
    {
      "epoch": 0.18253309986790772,
      "grad_norm": 0.3302990198135376,
      "learning_rate": 1.9604222115054936e-05,
      "loss": 0.5814,
      "step": 5942
    },
    {
      "epoch": 0.18256381900285687,
      "grad_norm": 0.3591599762439728,
      "learning_rate": 1.960408748774128e-05,
      "loss": 0.5521,
      "step": 5943
    },
    {
      "epoch": 0.18259453813780605,
      "grad_norm": 0.3435882329940796,
      "learning_rate": 1.9603952837996606e-05,
      "loss": 0.5469,
      "step": 5944
    },
    {
      "epoch": 0.1826252572727552,
      "grad_norm": 0.35276541113853455,
      "learning_rate": 1.960381816582123e-05,
      "loss": 0.5818,
      "step": 5945
    },
    {
      "epoch": 0.18265597640770437,
      "grad_norm": 0.3985418379306793,
      "learning_rate": 1.9603683471215467e-05,
      "loss": 0.5575,
      "step": 5946
    },
    {
      "epoch": 0.18268669554265352,
      "grad_norm": 0.33579277992248535,
      "learning_rate": 1.9603548754179628e-05,
      "loss": 0.5025,
      "step": 5947
    },
    {
      "epoch": 0.1827174146776027,
      "grad_norm": 0.34423503279685974,
      "learning_rate": 1.960341401471403e-05,
      "loss": 0.6923,
      "step": 5948
    },
    {
      "epoch": 0.18274813381255184,
      "grad_norm": 0.33499976992607117,
      "learning_rate": 1.960327925281899e-05,
      "loss": 0.5764,
      "step": 5949
    },
    {
      "epoch": 0.18277885294750099,
      "grad_norm": 0.33701130747795105,
      "learning_rate": 1.960314446849482e-05,
      "loss": 0.5487,
      "step": 5950
    },
    {
      "epoch": 0.18280957208245016,
      "grad_norm": 0.33594974875450134,
      "learning_rate": 1.9603009661741834e-05,
      "loss": 0.6243,
      "step": 5951
    },
    {
      "epoch": 0.1828402912173993,
      "grad_norm": 0.3753688931465149,
      "learning_rate": 1.960287483256035e-05,
      "loss": 0.653,
      "step": 5952
    },
    {
      "epoch": 0.18287101035234848,
      "grad_norm": 0.32881298661231995,
      "learning_rate": 1.960273998095068e-05,
      "loss": 0.5434,
      "step": 5953
    },
    {
      "epoch": 0.18290172948729763,
      "grad_norm": 0.36371633410453796,
      "learning_rate": 1.960260510691314e-05,
      "loss": 0.6551,
      "step": 5954
    },
    {
      "epoch": 0.1829324486222468,
      "grad_norm": 0.3733353912830353,
      "learning_rate": 1.9602470210448045e-05,
      "loss": 0.5304,
      "step": 5955
    },
    {
      "epoch": 0.18296316775719595,
      "grad_norm": 0.37299397587776184,
      "learning_rate": 1.9602335291555713e-05,
      "loss": 0.6461,
      "step": 5956
    },
    {
      "epoch": 0.18299388689214513,
      "grad_norm": 1.3790874481201172,
      "learning_rate": 1.9602200350236455e-05,
      "loss": 0.5752,
      "step": 5957
    },
    {
      "epoch": 0.18302460602709428,
      "grad_norm": 0.3504164218902588,
      "learning_rate": 1.9602065386490587e-05,
      "loss": 0.5882,
      "step": 5958
    },
    {
      "epoch": 0.18305532516204343,
      "grad_norm": 0.36477646231651306,
      "learning_rate": 1.960193040031842e-05,
      "loss": 0.6851,
      "step": 5959
    },
    {
      "epoch": 0.1830860442969926,
      "grad_norm": 0.33003389835357666,
      "learning_rate": 1.9601795391720282e-05,
      "loss": 0.6002,
      "step": 5960
    },
    {
      "epoch": 0.18311676343194175,
      "grad_norm": 0.36007821559906006,
      "learning_rate": 1.9601660360696478e-05,
      "loss": 0.5664,
      "step": 5961
    },
    {
      "epoch": 0.18314748256689092,
      "grad_norm": 0.5056244134902954,
      "learning_rate": 1.960152530724732e-05,
      "loss": 0.6184,
      "step": 5962
    },
    {
      "epoch": 0.18317820170184007,
      "grad_norm": 0.3341716229915619,
      "learning_rate": 1.9601390231373136e-05,
      "loss": 0.6319,
      "step": 5963
    },
    {
      "epoch": 0.18320892083678925,
      "grad_norm": 0.33340179920196533,
      "learning_rate": 1.9601255133074234e-05,
      "loss": 0.6361,
      "step": 5964
    },
    {
      "epoch": 0.1832396399717384,
      "grad_norm": 0.5584313869476318,
      "learning_rate": 1.960112001235093e-05,
      "loss": 0.6569,
      "step": 5965
    },
    {
      "epoch": 0.18327035910668757,
      "grad_norm": 0.3839835226535797,
      "learning_rate": 1.9600984869203534e-05,
      "loss": 0.6231,
      "step": 5966
    },
    {
      "epoch": 0.18330107824163672,
      "grad_norm": 0.3001989424228668,
      "learning_rate": 1.960084970363237e-05,
      "loss": 0.5293,
      "step": 5967
    },
    {
      "epoch": 0.18333179737658586,
      "grad_norm": 0.3685603141784668,
      "learning_rate": 1.9600714515637756e-05,
      "loss": 0.6185,
      "step": 5968
    },
    {
      "epoch": 0.18336251651153504,
      "grad_norm": 0.3608408570289612,
      "learning_rate": 1.9600579305219997e-05,
      "loss": 0.595,
      "step": 5969
    },
    {
      "epoch": 0.1833932356464842,
      "grad_norm": 0.4347168505191803,
      "learning_rate": 1.9600444072379416e-05,
      "loss": 0.5467,
      "step": 5970
    },
    {
      "epoch": 0.18342395478143336,
      "grad_norm": 0.32234281301498413,
      "learning_rate": 1.9600308817116328e-05,
      "loss": 0.5524,
      "step": 5971
    },
    {
      "epoch": 0.1834546739163825,
      "grad_norm": 0.32878902554512024,
      "learning_rate": 1.9600173539431047e-05,
      "loss": 0.5782,
      "step": 5972
    },
    {
      "epoch": 0.18348539305133169,
      "grad_norm": 0.3932367265224457,
      "learning_rate": 1.960003823932389e-05,
      "loss": 0.6992,
      "step": 5973
    },
    {
      "epoch": 0.18351611218628083,
      "grad_norm": 0.346364289522171,
      "learning_rate": 1.9599902916795178e-05,
      "loss": 0.6001,
      "step": 5974
    },
    {
      "epoch": 0.18354683132122998,
      "grad_norm": 0.3349640369415283,
      "learning_rate": 1.9599767571845215e-05,
      "loss": 0.6401,
      "step": 5975
    },
    {
      "epoch": 0.18357755045617916,
      "grad_norm": 0.3838599920272827,
      "learning_rate": 1.959963220447433e-05,
      "loss": 0.5242,
      "step": 5976
    },
    {
      "epoch": 0.1836082695911283,
      "grad_norm": 0.4727429747581482,
      "learning_rate": 1.959949681468283e-05,
      "loss": 0.6651,
      "step": 5977
    },
    {
      "epoch": 0.18363898872607748,
      "grad_norm": 0.3628028631210327,
      "learning_rate": 1.9599361402471036e-05,
      "loss": 0.6427,
      "step": 5978
    },
    {
      "epoch": 0.18366970786102663,
      "grad_norm": 0.32610416412353516,
      "learning_rate": 1.9599225967839265e-05,
      "loss": 0.5755,
      "step": 5979
    },
    {
      "epoch": 0.1837004269959758,
      "grad_norm": 0.32578665018081665,
      "learning_rate": 1.9599090510787833e-05,
      "loss": 0.6041,
      "step": 5980
    },
    {
      "epoch": 0.18373114613092495,
      "grad_norm": 0.3499810993671417,
      "learning_rate": 1.959895503131705e-05,
      "loss": 0.5967,
      "step": 5981
    },
    {
      "epoch": 0.18376186526587412,
      "grad_norm": 0.39366087317466736,
      "learning_rate": 1.959881952942724e-05,
      "loss": 0.5533,
      "step": 5982
    },
    {
      "epoch": 0.18379258440082327,
      "grad_norm": 0.49017149209976196,
      "learning_rate": 1.9598684005118717e-05,
      "loss": 0.5961,
      "step": 5983
    },
    {
      "epoch": 0.18382330353577242,
      "grad_norm": 0.3632493019104004,
      "learning_rate": 1.959854845839179e-05,
      "loss": 0.5753,
      "step": 5984
    },
    {
      "epoch": 0.1838540226707216,
      "grad_norm": 0.34930703043937683,
      "learning_rate": 1.959841288924679e-05,
      "loss": 0.668,
      "step": 5985
    },
    {
      "epoch": 0.18388474180567074,
      "grad_norm": 0.32629671692848206,
      "learning_rate": 1.9598277297684026e-05,
      "loss": 0.6289,
      "step": 5986
    },
    {
      "epoch": 0.18391546094061992,
      "grad_norm": 0.33979693055152893,
      "learning_rate": 1.9598141683703813e-05,
      "loss": 0.6037,
      "step": 5987
    },
    {
      "epoch": 0.18394618007556907,
      "grad_norm": 0.3243813216686249,
      "learning_rate": 1.959800604730647e-05,
      "loss": 0.519,
      "step": 5988
    },
    {
      "epoch": 0.18397689921051824,
      "grad_norm": 0.3732922077178955,
      "learning_rate": 1.9597870388492314e-05,
      "loss": 0.5793,
      "step": 5989
    },
    {
      "epoch": 0.1840076183454674,
      "grad_norm": 0.3717234432697296,
      "learning_rate": 1.9597734707261662e-05,
      "loss": 0.5592,
      "step": 5990
    },
    {
      "epoch": 0.18403833748041656,
      "grad_norm": 0.3210951089859009,
      "learning_rate": 1.959759900361483e-05,
      "loss": 0.5277,
      "step": 5991
    },
    {
      "epoch": 0.1840690566153657,
      "grad_norm": 0.38201984763145447,
      "learning_rate": 1.9597463277552133e-05,
      "loss": 0.6161,
      "step": 5992
    },
    {
      "epoch": 0.18409977575031486,
      "grad_norm": 0.33403468132019043,
      "learning_rate": 1.9597327529073892e-05,
      "loss": 0.5948,
      "step": 5993
    },
    {
      "epoch": 0.18413049488526403,
      "grad_norm": 0.32484742999076843,
      "learning_rate": 1.9597191758180422e-05,
      "loss": 0.5988,
      "step": 5994
    },
    {
      "epoch": 0.18416121402021318,
      "grad_norm": 0.34606826305389404,
      "learning_rate": 1.959705596487204e-05,
      "loss": 0.6283,
      "step": 5995
    },
    {
      "epoch": 0.18419193315516236,
      "grad_norm": 0.43828001618385315,
      "learning_rate": 1.9596920149149068e-05,
      "loss": 0.5985,
      "step": 5996
    },
    {
      "epoch": 0.1842226522901115,
      "grad_norm": 0.32886090874671936,
      "learning_rate": 1.9596784311011814e-05,
      "loss": 0.6088,
      "step": 5997
    },
    {
      "epoch": 0.18425337142506068,
      "grad_norm": 0.3961910307407379,
      "learning_rate": 1.95966484504606e-05,
      "loss": 0.5457,
      "step": 5998
    },
    {
      "epoch": 0.18428409056000983,
      "grad_norm": 0.36022260785102844,
      "learning_rate": 1.9596512567495748e-05,
      "loss": 0.6573,
      "step": 5999
    },
    {
      "epoch": 0.184314809694959,
      "grad_norm": 0.32407817244529724,
      "learning_rate": 1.9596376662117566e-05,
      "loss": 0.592,
      "step": 6000
    },
    {
      "epoch": 0.18434552882990815,
      "grad_norm": 0.3651948869228363,
      "learning_rate": 1.9596240734326377e-05,
      "loss": 0.6727,
      "step": 6001
    },
    {
      "epoch": 0.1843762479648573,
      "grad_norm": 0.35053667426109314,
      "learning_rate": 1.9596104784122497e-05,
      "loss": 0.6056,
      "step": 6002
    },
    {
      "epoch": 0.18440696709980647,
      "grad_norm": 0.41368481516838074,
      "learning_rate": 1.9595968811506247e-05,
      "loss": 0.6218,
      "step": 6003
    },
    {
      "epoch": 0.18443768623475562,
      "grad_norm": 0.3544885814189911,
      "learning_rate": 1.959583281647794e-05,
      "loss": 0.5593,
      "step": 6004
    },
    {
      "epoch": 0.1844684053697048,
      "grad_norm": 0.38088977336883545,
      "learning_rate": 1.959569679903789e-05,
      "loss": 0.5893,
      "step": 6005
    },
    {
      "epoch": 0.18449912450465394,
      "grad_norm": 0.36738619208335876,
      "learning_rate": 1.9595560759186428e-05,
      "loss": 0.5658,
      "step": 6006
    },
    {
      "epoch": 0.18452984363960312,
      "grad_norm": 0.38347238302230835,
      "learning_rate": 1.959542469692386e-05,
      "loss": 0.5553,
      "step": 6007
    },
    {
      "epoch": 0.18456056277455227,
      "grad_norm": 0.46234166622161865,
      "learning_rate": 1.9595288612250507e-05,
      "loss": 0.6165,
      "step": 6008
    },
    {
      "epoch": 0.18459128190950141,
      "grad_norm": 0.32287266850471497,
      "learning_rate": 1.959515250516669e-05,
      "loss": 0.5364,
      "step": 6009
    },
    {
      "epoch": 0.1846220010444506,
      "grad_norm": 0.3290674686431885,
      "learning_rate": 1.959501637567272e-05,
      "loss": 0.6304,
      "step": 6010
    },
    {
      "epoch": 0.18465272017939974,
      "grad_norm": 0.3726661205291748,
      "learning_rate": 1.9594880223768923e-05,
      "loss": 0.6575,
      "step": 6011
    },
    {
      "epoch": 0.1846834393143489,
      "grad_norm": 0.3764941394329071,
      "learning_rate": 1.9594744049455612e-05,
      "loss": 0.5763,
      "step": 6012
    },
    {
      "epoch": 0.18471415844929806,
      "grad_norm": 0.3217504918575287,
      "learning_rate": 1.9594607852733106e-05,
      "loss": 0.6161,
      "step": 6013
    },
    {
      "epoch": 0.18474487758424724,
      "grad_norm": 0.3317289352416992,
      "learning_rate": 1.9594471633601723e-05,
      "loss": 0.6825,
      "step": 6014
    },
    {
      "epoch": 0.18477559671919638,
      "grad_norm": 0.32416126132011414,
      "learning_rate": 1.9594335392061782e-05,
      "loss": 0.5056,
      "step": 6015
    },
    {
      "epoch": 0.18480631585414556,
      "grad_norm": 0.3297175467014313,
      "learning_rate": 1.95941991281136e-05,
      "loss": 0.5265,
      "step": 6016
    },
    {
      "epoch": 0.1848370349890947,
      "grad_norm": 0.3464498519897461,
      "learning_rate": 1.9594062841757496e-05,
      "loss": 0.6491,
      "step": 6017
    },
    {
      "epoch": 0.18486775412404385,
      "grad_norm": 0.3648136854171753,
      "learning_rate": 1.959392653299379e-05,
      "loss": 0.6917,
      "step": 6018
    },
    {
      "epoch": 0.18489847325899303,
      "grad_norm": 0.34108299016952515,
      "learning_rate": 1.9593790201822796e-05,
      "loss": 0.6821,
      "step": 6019
    },
    {
      "epoch": 0.18492919239394218,
      "grad_norm": 0.3357943296432495,
      "learning_rate": 1.9593653848244834e-05,
      "loss": 0.596,
      "step": 6020
    },
    {
      "epoch": 0.18495991152889135,
      "grad_norm": 0.3445607125759125,
      "learning_rate": 1.959351747226023e-05,
      "loss": 0.7116,
      "step": 6021
    },
    {
      "epoch": 0.1849906306638405,
      "grad_norm": 0.3208570182323456,
      "learning_rate": 1.959338107386929e-05,
      "loss": 0.5918,
      "step": 6022
    },
    {
      "epoch": 0.18502134979878967,
      "grad_norm": 0.35185733437538147,
      "learning_rate": 1.9593244653072337e-05,
      "loss": 0.5936,
      "step": 6023
    },
    {
      "epoch": 0.18505206893373882,
      "grad_norm": 0.3490707278251648,
      "learning_rate": 1.9593108209869695e-05,
      "loss": 0.6256,
      "step": 6024
    },
    {
      "epoch": 0.185082788068688,
      "grad_norm": 0.35565385222435,
      "learning_rate": 1.959297174426168e-05,
      "loss": 0.6095,
      "step": 6025
    },
    {
      "epoch": 0.18511350720363715,
      "grad_norm": 0.3533627986907959,
      "learning_rate": 1.9592835256248604e-05,
      "loss": 0.5492,
      "step": 6026
    },
    {
      "epoch": 0.1851442263385863,
      "grad_norm": 0.33954399824142456,
      "learning_rate": 1.9592698745830797e-05,
      "loss": 0.5717,
      "step": 6027
    },
    {
      "epoch": 0.18517494547353547,
      "grad_norm": 0.4030175805091858,
      "learning_rate": 1.9592562213008568e-05,
      "loss": 0.6415,
      "step": 6028
    },
    {
      "epoch": 0.18520566460848462,
      "grad_norm": 0.35756099224090576,
      "learning_rate": 1.959242565778224e-05,
      "loss": 0.5971,
      "step": 6029
    },
    {
      "epoch": 0.1852363837434338,
      "grad_norm": 0.3449825942516327,
      "learning_rate": 1.9592289080152135e-05,
      "loss": 0.5691,
      "step": 6030
    },
    {
      "epoch": 0.18526710287838294,
      "grad_norm": 0.35720646381378174,
      "learning_rate": 1.959215248011857e-05,
      "loss": 0.5682,
      "step": 6031
    },
    {
      "epoch": 0.18529782201333211,
      "grad_norm": 0.33691126108169556,
      "learning_rate": 1.9592015857681858e-05,
      "loss": 0.5717,
      "step": 6032
    },
    {
      "epoch": 0.18532854114828126,
      "grad_norm": 0.37356656789779663,
      "learning_rate": 1.9591879212842328e-05,
      "loss": 0.6284,
      "step": 6033
    },
    {
      "epoch": 0.18535926028323044,
      "grad_norm": 0.3681046962738037,
      "learning_rate": 1.9591742545600294e-05,
      "loss": 0.5986,
      "step": 6034
    },
    {
      "epoch": 0.18538997941817958,
      "grad_norm": 0.34624966979026794,
      "learning_rate": 1.959160585595607e-05,
      "loss": 0.6333,
      "step": 6035
    },
    {
      "epoch": 0.18542069855312873,
      "grad_norm": 0.3814019560813904,
      "learning_rate": 1.9591469143909982e-05,
      "loss": 0.55,
      "step": 6036
    },
    {
      "epoch": 0.1854514176880779,
      "grad_norm": 0.3457910418510437,
      "learning_rate": 1.959133240946235e-05,
      "loss": 0.5442,
      "step": 6037
    },
    {
      "epoch": 0.18548213682302706,
      "grad_norm": 0.3134711682796478,
      "learning_rate": 1.959119565261349e-05,
      "loss": 0.6376,
      "step": 6038
    },
    {
      "epoch": 0.18551285595797623,
      "grad_norm": 0.3596256971359253,
      "learning_rate": 1.9591058873363727e-05,
      "loss": 0.6035,
      "step": 6039
    },
    {
      "epoch": 0.18554357509292538,
      "grad_norm": 0.325874000787735,
      "learning_rate": 1.9590922071713373e-05,
      "loss": 0.5621,
      "step": 6040
    },
    {
      "epoch": 0.18557429422787455,
      "grad_norm": 0.3768215477466583,
      "learning_rate": 1.9590785247662748e-05,
      "loss": 0.6441,
      "step": 6041
    },
    {
      "epoch": 0.1856050133628237,
      "grad_norm": 0.3726167380809784,
      "learning_rate": 1.9590648401212178e-05,
      "loss": 0.5633,
      "step": 6042
    },
    {
      "epoch": 0.18563573249777288,
      "grad_norm": 0.3255572021007538,
      "learning_rate": 1.9590511532361978e-05,
      "loss": 0.6068,
      "step": 6043
    },
    {
      "epoch": 0.18566645163272202,
      "grad_norm": 0.48673972487449646,
      "learning_rate": 1.959037464111247e-05,
      "loss": 0.5899,
      "step": 6044
    },
    {
      "epoch": 0.18569717076767117,
      "grad_norm": 0.33345523476600647,
      "learning_rate": 1.959023772746397e-05,
      "loss": 0.639,
      "step": 6045
    },
    {
      "epoch": 0.18572788990262035,
      "grad_norm": 0.35434991121292114,
      "learning_rate": 1.9590100791416802e-05,
      "loss": 0.651,
      "step": 6046
    },
    {
      "epoch": 0.1857586090375695,
      "grad_norm": 0.35615307092666626,
      "learning_rate": 1.9589963832971278e-05,
      "loss": 0.6094,
      "step": 6047
    },
    {
      "epoch": 0.18578932817251867,
      "grad_norm": 0.3168114423751831,
      "learning_rate": 1.958982685212773e-05,
      "loss": 0.5372,
      "step": 6048
    },
    {
      "epoch": 0.18582004730746782,
      "grad_norm": 0.4172329902648926,
      "learning_rate": 1.9589689848886472e-05,
      "loss": 0.6486,
      "step": 6049
    },
    {
      "epoch": 0.185850766442417,
      "grad_norm": 0.33396264910697937,
      "learning_rate": 1.958955282324782e-05,
      "loss": 0.5853,
      "step": 6050
    },
    {
      "epoch": 0.18588148557736614,
      "grad_norm": 0.36648014187812805,
      "learning_rate": 1.95894157752121e-05,
      "loss": 0.6776,
      "step": 6051
    },
    {
      "epoch": 0.1859122047123153,
      "grad_norm": 0.3806343078613281,
      "learning_rate": 1.9589278704779627e-05,
      "loss": 0.6324,
      "step": 6052
    },
    {
      "epoch": 0.18594292384726446,
      "grad_norm": 0.3150605857372284,
      "learning_rate": 1.9589141611950727e-05,
      "loss": 0.5749,
      "step": 6053
    },
    {
      "epoch": 0.1859736429822136,
      "grad_norm": 0.330610454082489,
      "learning_rate": 1.9589004496725717e-05,
      "loss": 0.5241,
      "step": 6054
    },
    {
      "epoch": 0.18600436211716279,
      "grad_norm": 0.33437326550483704,
      "learning_rate": 1.9588867359104915e-05,
      "loss": 0.6162,
      "step": 6055
    },
    {
      "epoch": 0.18603508125211193,
      "grad_norm": 0.38292360305786133,
      "learning_rate": 1.9588730199088643e-05,
      "loss": 0.6434,
      "step": 6056
    },
    {
      "epoch": 0.1860658003870611,
      "grad_norm": 0.38716617226600647,
      "learning_rate": 1.9588593016677223e-05,
      "loss": 0.5892,
      "step": 6057
    },
    {
      "epoch": 0.18609651952201026,
      "grad_norm": 0.32561278343200684,
      "learning_rate": 1.9588455811870977e-05,
      "loss": 0.5285,
      "step": 6058
    },
    {
      "epoch": 0.18612723865695943,
      "grad_norm": 0.3736150562763214,
      "learning_rate": 1.958831858467022e-05,
      "loss": 0.6387,
      "step": 6059
    },
    {
      "epoch": 0.18615795779190858,
      "grad_norm": 0.35929790139198303,
      "learning_rate": 1.9588181335075275e-05,
      "loss": 0.6215,
      "step": 6060
    },
    {
      "epoch": 0.18618867692685773,
      "grad_norm": 0.3317405581474304,
      "learning_rate": 1.9588044063086465e-05,
      "loss": 0.5695,
      "step": 6061
    },
    {
      "epoch": 0.1862193960618069,
      "grad_norm": 0.3674466907978058,
      "learning_rate": 1.9587906768704106e-05,
      "loss": 0.6723,
      "step": 6062
    },
    {
      "epoch": 0.18625011519675605,
      "grad_norm": 0.3293972313404083,
      "learning_rate": 1.9587769451928524e-05,
      "loss": 0.6196,
      "step": 6063
    },
    {
      "epoch": 0.18628083433170523,
      "grad_norm": 0.3501985967159271,
      "learning_rate": 1.9587632112760034e-05,
      "loss": 0.61,
      "step": 6064
    },
    {
      "epoch": 0.18631155346665437,
      "grad_norm": 0.34458476305007935,
      "learning_rate": 1.958749475119896e-05,
      "loss": 0.5451,
      "step": 6065
    },
    {
      "epoch": 0.18634227260160355,
      "grad_norm": 0.3603653013706207,
      "learning_rate": 1.9587357367245626e-05,
      "loss": 0.5064,
      "step": 6066
    },
    {
      "epoch": 0.1863729917365527,
      "grad_norm": 0.46409639716148376,
      "learning_rate": 1.958721996090035e-05,
      "loss": 0.5923,
      "step": 6067
    },
    {
      "epoch": 0.18640371087150187,
      "grad_norm": 0.3251858651638031,
      "learning_rate": 1.9587082532163447e-05,
      "loss": 0.6004,
      "step": 6068
    },
    {
      "epoch": 0.18643443000645102,
      "grad_norm": 0.35332563519477844,
      "learning_rate": 1.9586945081035242e-05,
      "loss": 0.5918,
      "step": 6069
    },
    {
      "epoch": 0.18646514914140017,
      "grad_norm": 0.3431587815284729,
      "learning_rate": 1.958680760751606e-05,
      "loss": 0.6096,
      "step": 6070
    },
    {
      "epoch": 0.18649586827634934,
      "grad_norm": 0.403231143951416,
      "learning_rate": 1.958667011160622e-05,
      "loss": 0.507,
      "step": 6071
    },
    {
      "epoch": 0.1865265874112985,
      "grad_norm": 0.3182508051395416,
      "learning_rate": 1.958653259330604e-05,
      "loss": 0.5548,
      "step": 6072
    },
    {
      "epoch": 0.18655730654624766,
      "grad_norm": 0.39731693267822266,
      "learning_rate": 1.958639505261585e-05,
      "loss": 0.6122,
      "step": 6073
    },
    {
      "epoch": 0.1865880256811968,
      "grad_norm": 0.36136332154273987,
      "learning_rate": 1.9586257489535958e-05,
      "loss": 0.6078,
      "step": 6074
    },
    {
      "epoch": 0.186618744816146,
      "grad_norm": 0.3177822530269623,
      "learning_rate": 1.9586119904066695e-05,
      "loss": 0.529,
      "step": 6075
    },
    {
      "epoch": 0.18664946395109513,
      "grad_norm": 0.33696550130844116,
      "learning_rate": 1.958598229620838e-05,
      "loss": 0.5727,
      "step": 6076
    },
    {
      "epoch": 0.1866801830860443,
      "grad_norm": 0.3250274658203125,
      "learning_rate": 1.9585844665961334e-05,
      "loss": 0.641,
      "step": 6077
    },
    {
      "epoch": 0.18671090222099346,
      "grad_norm": 0.3523365557193756,
      "learning_rate": 1.9585707013325875e-05,
      "loss": 0.6453,
      "step": 6078
    },
    {
      "epoch": 0.1867416213559426,
      "grad_norm": 0.35939228534698486,
      "learning_rate": 1.958556933830233e-05,
      "loss": 0.5481,
      "step": 6079
    },
    {
      "epoch": 0.18677234049089178,
      "grad_norm": 0.34270229935646057,
      "learning_rate": 1.9585431640891022e-05,
      "loss": 0.6337,
      "step": 6080
    },
    {
      "epoch": 0.18680305962584093,
      "grad_norm": 0.4800567030906677,
      "learning_rate": 1.9585293921092265e-05,
      "loss": 0.6359,
      "step": 6081
    },
    {
      "epoch": 0.1868337787607901,
      "grad_norm": 0.3224259316921234,
      "learning_rate": 1.9585156178906382e-05,
      "loss": 0.5776,
      "step": 6082
    },
    {
      "epoch": 0.18686449789573925,
      "grad_norm": 0.33675694465637207,
      "learning_rate": 1.9585018414333704e-05,
      "loss": 0.6243,
      "step": 6083
    },
    {
      "epoch": 0.18689521703068843,
      "grad_norm": 0.3566984236240387,
      "learning_rate": 1.958488062737454e-05,
      "loss": 0.6291,
      "step": 6084
    },
    {
      "epoch": 0.18692593616563757,
      "grad_norm": 0.4642364978790283,
      "learning_rate": 1.9584742818029222e-05,
      "loss": 0.5623,
      "step": 6085
    },
    {
      "epoch": 0.18695665530058675,
      "grad_norm": 0.3475342392921448,
      "learning_rate": 1.9584604986298066e-05,
      "loss": 0.5485,
      "step": 6086
    },
    {
      "epoch": 0.1869873744355359,
      "grad_norm": 0.34220871329307556,
      "learning_rate": 1.9584467132181394e-05,
      "loss": 0.594,
      "step": 6087
    },
    {
      "epoch": 0.18701809357048504,
      "grad_norm": 0.3802169859409332,
      "learning_rate": 1.9584329255679532e-05,
      "loss": 0.52,
      "step": 6088
    },
    {
      "epoch": 0.18704881270543422,
      "grad_norm": 0.3333503305912018,
      "learning_rate": 1.95841913567928e-05,
      "loss": 0.5966,
      "step": 6089
    },
    {
      "epoch": 0.18707953184038337,
      "grad_norm": 0.3343625068664551,
      "learning_rate": 1.9584053435521518e-05,
      "loss": 0.6348,
      "step": 6090
    },
    {
      "epoch": 0.18711025097533254,
      "grad_norm": 0.3174566924571991,
      "learning_rate": 1.958391549186601e-05,
      "loss": 0.5434,
      "step": 6091
    },
    {
      "epoch": 0.1871409701102817,
      "grad_norm": 0.31437018513679504,
      "learning_rate": 1.95837775258266e-05,
      "loss": 0.5693,
      "step": 6092
    },
    {
      "epoch": 0.18717168924523087,
      "grad_norm": 0.38108348846435547,
      "learning_rate": 1.9583639537403608e-05,
      "loss": 0.6713,
      "step": 6093
    },
    {
      "epoch": 0.18720240838018,
      "grad_norm": 0.3565461337566376,
      "learning_rate": 1.9583501526597353e-05,
      "loss": 0.6449,
      "step": 6094
    },
    {
      "epoch": 0.18723312751512916,
      "grad_norm": 0.3443508744239807,
      "learning_rate": 1.9583363493408166e-05,
      "loss": 0.5979,
      "step": 6095
    },
    {
      "epoch": 0.18726384665007834,
      "grad_norm": 0.4205133616924286,
      "learning_rate": 1.958322543783636e-05,
      "loss": 0.5543,
      "step": 6096
    },
    {
      "epoch": 0.18729456578502748,
      "grad_norm": 0.3275512754917145,
      "learning_rate": 1.9583087359882263e-05,
      "loss": 0.5706,
      "step": 6097
    },
    {
      "epoch": 0.18732528491997666,
      "grad_norm": 0.3141806721687317,
      "learning_rate": 1.95829492595462e-05,
      "loss": 0.606,
      "step": 6098
    },
    {
      "epoch": 0.1873560040549258,
      "grad_norm": 0.34745439887046814,
      "learning_rate": 1.9582811136828484e-05,
      "loss": 0.585,
      "step": 6099
    },
    {
      "epoch": 0.18738672318987498,
      "grad_norm": 0.3476618826389313,
      "learning_rate": 1.9582672991729446e-05,
      "loss": 0.6234,
      "step": 6100
    },
    {
      "epoch": 0.18741744232482413,
      "grad_norm": 0.6344875693321228,
      "learning_rate": 1.9582534824249405e-05,
      "loss": 0.5197,
      "step": 6101
    },
    {
      "epoch": 0.1874481614597733,
      "grad_norm": 0.34326761960983276,
      "learning_rate": 1.9582396634388687e-05,
      "loss": 0.5949,
      "step": 6102
    },
    {
      "epoch": 0.18747888059472245,
      "grad_norm": 0.3500531017780304,
      "learning_rate": 1.958225842214761e-05,
      "loss": 0.6098,
      "step": 6103
    },
    {
      "epoch": 0.1875095997296716,
      "grad_norm": 0.4469769299030304,
      "learning_rate": 1.95821201875265e-05,
      "loss": 0.5991,
      "step": 6104
    },
    {
      "epoch": 0.18754031886462078,
      "grad_norm": 0.374724417924881,
      "learning_rate": 1.9581981930525677e-05,
      "loss": 0.557,
      "step": 6105
    },
    {
      "epoch": 0.18757103799956992,
      "grad_norm": 0.3137761652469635,
      "learning_rate": 1.958184365114547e-05,
      "loss": 0.5678,
      "step": 6106
    },
    {
      "epoch": 0.1876017571345191,
      "grad_norm": 0.3454790711402893,
      "learning_rate": 1.9581705349386196e-05,
      "loss": 0.6253,
      "step": 6107
    },
    {
      "epoch": 0.18763247626946825,
      "grad_norm": 0.40637028217315674,
      "learning_rate": 1.9581567025248177e-05,
      "loss": 0.5625,
      "step": 6108
    },
    {
      "epoch": 0.18766319540441742,
      "grad_norm": 0.32152625918388367,
      "learning_rate": 1.9581428678731744e-05,
      "loss": 0.5665,
      "step": 6109
    },
    {
      "epoch": 0.18769391453936657,
      "grad_norm": 0.3547438979148865,
      "learning_rate": 1.9581290309837213e-05,
      "loss": 0.6029,
      "step": 6110
    },
    {
      "epoch": 0.18772463367431574,
      "grad_norm": 0.38398775458335876,
      "learning_rate": 1.958115191856491e-05,
      "loss": 0.6115,
      "step": 6111
    },
    {
      "epoch": 0.1877553528092649,
      "grad_norm": 0.330425888299942,
      "learning_rate": 1.9581013504915157e-05,
      "loss": 0.6206,
      "step": 6112
    },
    {
      "epoch": 0.18778607194421404,
      "grad_norm": 0.3661397099494934,
      "learning_rate": 1.9580875068888277e-05,
      "loss": 0.6086,
      "step": 6113
    },
    {
      "epoch": 0.18781679107916321,
      "grad_norm": 0.3559572100639343,
      "learning_rate": 1.9580736610484596e-05,
      "loss": 0.6568,
      "step": 6114
    },
    {
      "epoch": 0.18784751021411236,
      "grad_norm": 0.32535356283187866,
      "learning_rate": 1.9580598129704435e-05,
      "loss": 0.6172,
      "step": 6115
    },
    {
      "epoch": 0.18787822934906154,
      "grad_norm": 0.3145642578601837,
      "learning_rate": 1.9580459626548117e-05,
      "loss": 0.5614,
      "step": 6116
    },
    {
      "epoch": 0.18790894848401068,
      "grad_norm": 0.35676515102386475,
      "learning_rate": 1.9580321101015967e-05,
      "loss": 0.6049,
      "step": 6117
    },
    {
      "epoch": 0.18793966761895986,
      "grad_norm": 0.3532150983810425,
      "learning_rate": 1.958018255310831e-05,
      "loss": 0.6234,
      "step": 6118
    },
    {
      "epoch": 0.187970386753909,
      "grad_norm": 0.3239244818687439,
      "learning_rate": 1.9580043982825464e-05,
      "loss": 0.5334,
      "step": 6119
    },
    {
      "epoch": 0.18800110588885818,
      "grad_norm": 0.3213599920272827,
      "learning_rate": 1.957990539016776e-05,
      "loss": 0.6456,
      "step": 6120
    },
    {
      "epoch": 0.18803182502380733,
      "grad_norm": 0.3204590082168579,
      "learning_rate": 1.9579766775135512e-05,
      "loss": 0.6241,
      "step": 6121
    },
    {
      "epoch": 0.18806254415875648,
      "grad_norm": 0.3527487516403198,
      "learning_rate": 1.9579628137729053e-05,
      "loss": 0.5988,
      "step": 6122
    },
    {
      "epoch": 0.18809326329370565,
      "grad_norm": 0.3620675802230835,
      "learning_rate": 1.957948947794871e-05,
      "loss": 0.6018,
      "step": 6123
    },
    {
      "epoch": 0.1881239824286548,
      "grad_norm": 0.3765774369239807,
      "learning_rate": 1.957935079579479e-05,
      "loss": 0.6001,
      "step": 6124
    },
    {
      "epoch": 0.18815470156360398,
      "grad_norm": 0.3395152986049652,
      "learning_rate": 1.957921209126763e-05,
      "loss": 0.6415,
      "step": 6125
    },
    {
      "epoch": 0.18818542069855312,
      "grad_norm": 0.3655926287174225,
      "learning_rate": 1.9579073364367556e-05,
      "loss": 0.6441,
      "step": 6126
    },
    {
      "epoch": 0.1882161398335023,
      "grad_norm": 0.3575213551521301,
      "learning_rate": 1.9578934615094882e-05,
      "loss": 0.4742,
      "step": 6127
    },
    {
      "epoch": 0.18824685896845145,
      "grad_norm": 0.7882621884346008,
      "learning_rate": 1.957879584344994e-05,
      "loss": 0.5544,
      "step": 6128
    },
    {
      "epoch": 0.1882775781034006,
      "grad_norm": 0.36553460359573364,
      "learning_rate": 1.9578657049433048e-05,
      "loss": 0.6132,
      "step": 6129
    },
    {
      "epoch": 0.18830829723834977,
      "grad_norm": 0.34742921590805054,
      "learning_rate": 1.9578518233044536e-05,
      "loss": 0.594,
      "step": 6130
    },
    {
      "epoch": 0.18833901637329892,
      "grad_norm": 0.3391280472278595,
      "learning_rate": 1.9578379394284724e-05,
      "loss": 0.6626,
      "step": 6131
    },
    {
      "epoch": 0.1883697355082481,
      "grad_norm": 0.4611179232597351,
      "learning_rate": 1.957824053315394e-05,
      "loss": 0.6273,
      "step": 6132
    },
    {
      "epoch": 0.18840045464319724,
      "grad_norm": 0.34477928280830383,
      "learning_rate": 1.957810164965251e-05,
      "loss": 0.6868,
      "step": 6133
    },
    {
      "epoch": 0.18843117377814642,
      "grad_norm": 0.35330110788345337,
      "learning_rate": 1.9577962743780746e-05,
      "loss": 0.6466,
      "step": 6134
    },
    {
      "epoch": 0.18846189291309556,
      "grad_norm": 0.3290139138698578,
      "learning_rate": 1.957782381553899e-05,
      "loss": 0.7312,
      "step": 6135
    },
    {
      "epoch": 0.18849261204804474,
      "grad_norm": 0.3132963180541992,
      "learning_rate": 1.957768486492755e-05,
      "loss": 0.5251,
      "step": 6136
    },
    {
      "epoch": 0.1885233311829939,
      "grad_norm": 0.3891313672065735,
      "learning_rate": 1.957754589194676e-05,
      "loss": 0.6431,
      "step": 6137
    },
    {
      "epoch": 0.18855405031794303,
      "grad_norm": 0.4019964933395386,
      "learning_rate": 1.9577406896596948e-05,
      "loss": 0.6326,
      "step": 6138
    },
    {
      "epoch": 0.1885847694528922,
      "grad_norm": 0.3696160316467285,
      "learning_rate": 1.9577267878878428e-05,
      "loss": 0.6113,
      "step": 6139
    },
    {
      "epoch": 0.18861548858784136,
      "grad_norm": 0.4576997458934784,
      "learning_rate": 1.957712883879153e-05,
      "loss": 0.5711,
      "step": 6140
    },
    {
      "epoch": 0.18864620772279053,
      "grad_norm": 0.3472917973995209,
      "learning_rate": 1.9576989776336578e-05,
      "loss": 0.5558,
      "step": 6141
    },
    {
      "epoch": 0.18867692685773968,
      "grad_norm": 0.37351468205451965,
      "learning_rate": 1.9576850691513902e-05,
      "loss": 0.7325,
      "step": 6142
    },
    {
      "epoch": 0.18870764599268885,
      "grad_norm": 0.3232671320438385,
      "learning_rate": 1.957671158432382e-05,
      "loss": 0.5995,
      "step": 6143
    },
    {
      "epoch": 0.188738365127638,
      "grad_norm": 0.31099098920822144,
      "learning_rate": 1.9576572454766655e-05,
      "loss": 0.6131,
      "step": 6144
    },
    {
      "epoch": 0.18876908426258718,
      "grad_norm": 0.3682072162628174,
      "learning_rate": 1.9576433302842744e-05,
      "loss": 0.5894,
      "step": 6145
    },
    {
      "epoch": 0.18879980339753633,
      "grad_norm": 0.40763911604881287,
      "learning_rate": 1.95762941285524e-05,
      "loss": 0.5584,
      "step": 6146
    },
    {
      "epoch": 0.18883052253248547,
      "grad_norm": 0.3583739101886749,
      "learning_rate": 1.9576154931895953e-05,
      "loss": 0.5638,
      "step": 6147
    },
    {
      "epoch": 0.18886124166743465,
      "grad_norm": 0.3466792404651642,
      "learning_rate": 1.9576015712873728e-05,
      "loss": 0.67,
      "step": 6148
    },
    {
      "epoch": 0.1888919608023838,
      "grad_norm": 0.3706235885620117,
      "learning_rate": 1.9575876471486048e-05,
      "loss": 0.5006,
      "step": 6149
    },
    {
      "epoch": 0.18892267993733297,
      "grad_norm": 0.32185789942741394,
      "learning_rate": 1.957573720773324e-05,
      "loss": 0.5934,
      "step": 6150
    },
    {
      "epoch": 0.18895339907228212,
      "grad_norm": 0.2972692847251892,
      "learning_rate": 1.957559792161563e-05,
      "loss": 0.5718,
      "step": 6151
    },
    {
      "epoch": 0.1889841182072313,
      "grad_norm": 0.3270997107028961,
      "learning_rate": 1.957545861313354e-05,
      "loss": 0.5904,
      "step": 6152
    },
    {
      "epoch": 0.18901483734218044,
      "grad_norm": 0.3368877172470093,
      "learning_rate": 1.95753192822873e-05,
      "loss": 0.5508,
      "step": 6153
    },
    {
      "epoch": 0.18904555647712962,
      "grad_norm": 0.33197614550590515,
      "learning_rate": 1.957517992907723e-05,
      "loss": 0.5707,
      "step": 6154
    },
    {
      "epoch": 0.18907627561207876,
      "grad_norm": 0.3469868004322052,
      "learning_rate": 1.9575040553503665e-05,
      "loss": 0.5548,
      "step": 6155
    },
    {
      "epoch": 0.1891069947470279,
      "grad_norm": 0.3339208662509918,
      "learning_rate": 1.957490115556692e-05,
      "loss": 0.6025,
      "step": 6156
    },
    {
      "epoch": 0.1891377138819771,
      "grad_norm": 0.3403169810771942,
      "learning_rate": 1.9574761735267324e-05,
      "loss": 0.5898,
      "step": 6157
    },
    {
      "epoch": 0.18916843301692624,
      "grad_norm": 0.32612285017967224,
      "learning_rate": 1.95746222926052e-05,
      "loss": 0.6212,
      "step": 6158
    },
    {
      "epoch": 0.1891991521518754,
      "grad_norm": 0.3538394868373871,
      "learning_rate": 1.9574482827580884e-05,
      "loss": 0.587,
      "step": 6159
    },
    {
      "epoch": 0.18922987128682456,
      "grad_norm": 0.36765214800834656,
      "learning_rate": 1.957434334019469e-05,
      "loss": 0.6342,
      "step": 6160
    },
    {
      "epoch": 0.18926059042177373,
      "grad_norm": 0.3214438855648041,
      "learning_rate": 1.9574203830446952e-05,
      "loss": 0.4788,
      "step": 6161
    },
    {
      "epoch": 0.18929130955672288,
      "grad_norm": 0.3274264931678772,
      "learning_rate": 1.957406429833799e-05,
      "loss": 0.6452,
      "step": 6162
    },
    {
      "epoch": 0.18932202869167206,
      "grad_norm": 0.36095449328422546,
      "learning_rate": 1.957392474386813e-05,
      "loss": 0.6745,
      "step": 6163
    },
    {
      "epoch": 0.1893527478266212,
      "grad_norm": 0.3711467683315277,
      "learning_rate": 1.9573785167037704e-05,
      "loss": 0.6417,
      "step": 6164
    },
    {
      "epoch": 0.18938346696157035,
      "grad_norm": 0.343354731798172,
      "learning_rate": 1.9573645567847034e-05,
      "loss": 0.5863,
      "step": 6165
    },
    {
      "epoch": 0.18941418609651953,
      "grad_norm": 0.33489856123924255,
      "learning_rate": 1.9573505946296442e-05,
      "loss": 0.5786,
      "step": 6166
    },
    {
      "epoch": 0.18944490523146867,
      "grad_norm": 0.33364781737327576,
      "learning_rate": 1.9573366302386264e-05,
      "loss": 0.6131,
      "step": 6167
    },
    {
      "epoch": 0.18947562436641785,
      "grad_norm": 0.36831608414649963,
      "learning_rate": 1.957322663611682e-05,
      "loss": 0.6778,
      "step": 6168
    },
    {
      "epoch": 0.189506343501367,
      "grad_norm": 0.3462827503681183,
      "learning_rate": 1.957308694748843e-05,
      "loss": 0.6051,
      "step": 6169
    },
    {
      "epoch": 0.18953706263631617,
      "grad_norm": 0.3540433645248413,
      "learning_rate": 1.957294723650143e-05,
      "loss": 0.6335,
      "step": 6170
    },
    {
      "epoch": 0.18956778177126532,
      "grad_norm": 0.31336236000061035,
      "learning_rate": 1.9572807503156147e-05,
      "loss": 0.5793,
      "step": 6171
    },
    {
      "epoch": 0.18959850090621447,
      "grad_norm": 0.32031166553497314,
      "learning_rate": 1.95726677474529e-05,
      "loss": 0.5009,
      "step": 6172
    },
    {
      "epoch": 0.18962922004116364,
      "grad_norm": 0.3557322323322296,
      "learning_rate": 1.957252796939202e-05,
      "loss": 0.5869,
      "step": 6173
    },
    {
      "epoch": 0.1896599391761128,
      "grad_norm": 0.4297019839286804,
      "learning_rate": 1.957238816897383e-05,
      "loss": 0.5939,
      "step": 6174
    },
    {
      "epoch": 0.18969065831106197,
      "grad_norm": 0.33955585956573486,
      "learning_rate": 1.9572248346198663e-05,
      "loss": 0.6065,
      "step": 6175
    },
    {
      "epoch": 0.1897213774460111,
      "grad_norm": 0.3240797221660614,
      "learning_rate": 1.9572108501066836e-05,
      "loss": 0.565,
      "step": 6176
    },
    {
      "epoch": 0.1897520965809603,
      "grad_norm": 0.354186087846756,
      "learning_rate": 1.9571968633578687e-05,
      "loss": 0.6309,
      "step": 6177
    },
    {
      "epoch": 0.18978281571590944,
      "grad_norm": 0.3319218158721924,
      "learning_rate": 1.9571828743734533e-05,
      "loss": 0.5899,
      "step": 6178
    },
    {
      "epoch": 0.1898135348508586,
      "grad_norm": 0.3251549303531647,
      "learning_rate": 1.957168883153471e-05,
      "loss": 0.5708,
      "step": 6179
    },
    {
      "epoch": 0.18984425398580776,
      "grad_norm": 0.3802778720855713,
      "learning_rate": 1.9571548896979534e-05,
      "loss": 0.5327,
      "step": 6180
    },
    {
      "epoch": 0.1898749731207569,
      "grad_norm": 0.3435022830963135,
      "learning_rate": 1.9571408940069337e-05,
      "loss": 0.5913,
      "step": 6181
    },
    {
      "epoch": 0.18990569225570608,
      "grad_norm": 0.31950774788856506,
      "learning_rate": 1.9571268960804447e-05,
      "loss": 0.5515,
      "step": 6182
    },
    {
      "epoch": 0.18993641139065523,
      "grad_norm": 1.2712351083755493,
      "learning_rate": 1.957112895918519e-05,
      "loss": 0.5646,
      "step": 6183
    },
    {
      "epoch": 0.1899671305256044,
      "grad_norm": 0.31936290860176086,
      "learning_rate": 1.9570988935211893e-05,
      "loss": 0.6678,
      "step": 6184
    },
    {
      "epoch": 0.18999784966055355,
      "grad_norm": 0.33725520968437195,
      "learning_rate": 1.9570848888884883e-05,
      "loss": 0.6853,
      "step": 6185
    },
    {
      "epoch": 0.19002856879550273,
      "grad_norm": 0.3345917761325836,
      "learning_rate": 1.9570708820204487e-05,
      "loss": 0.6064,
      "step": 6186
    },
    {
      "epoch": 0.19005928793045188,
      "grad_norm": 0.3717612326145172,
      "learning_rate": 1.9570568729171028e-05,
      "loss": 0.5422,
      "step": 6187
    },
    {
      "epoch": 0.19009000706540105,
      "grad_norm": 0.3518766164779663,
      "learning_rate": 1.9570428615784843e-05,
      "loss": 0.6344,
      "step": 6188
    },
    {
      "epoch": 0.1901207262003502,
      "grad_norm": 0.37836116552352905,
      "learning_rate": 1.957028848004625e-05,
      "loss": 0.5748,
      "step": 6189
    },
    {
      "epoch": 0.19015144533529935,
      "grad_norm": 0.5411062240600586,
      "learning_rate": 1.9570148321955586e-05,
      "loss": 0.5706,
      "step": 6190
    },
    {
      "epoch": 0.19018216447024852,
      "grad_norm": 0.4320856034755707,
      "learning_rate": 1.9570008141513167e-05,
      "loss": 0.5279,
      "step": 6191
    },
    {
      "epoch": 0.19021288360519767,
      "grad_norm": 0.3990332782268524,
      "learning_rate": 1.9569867938719324e-05,
      "loss": 0.6178,
      "step": 6192
    },
    {
      "epoch": 0.19024360274014684,
      "grad_norm": 0.3663780391216278,
      "learning_rate": 1.956972771357439e-05,
      "loss": 0.5577,
      "step": 6193
    },
    {
      "epoch": 0.190274321875096,
      "grad_norm": 0.3522452712059021,
      "learning_rate": 1.9569587466078688e-05,
      "loss": 0.5629,
      "step": 6194
    },
    {
      "epoch": 0.19030504101004517,
      "grad_norm": 0.3253523111343384,
      "learning_rate": 1.9569447196232544e-05,
      "loss": 0.6081,
      "step": 6195
    },
    {
      "epoch": 0.19033576014499431,
      "grad_norm": 0.3596937656402588,
      "learning_rate": 1.9569306904036288e-05,
      "loss": 0.5449,
      "step": 6196
    },
    {
      "epoch": 0.1903664792799435,
      "grad_norm": 0.33318009972572327,
      "learning_rate": 1.9569166589490248e-05,
      "loss": 0.6308,
      "step": 6197
    },
    {
      "epoch": 0.19039719841489264,
      "grad_norm": 0.337901771068573,
      "learning_rate": 1.9569026252594755e-05,
      "loss": 0.5527,
      "step": 6198
    },
    {
      "epoch": 0.19042791754984179,
      "grad_norm": 0.4085325002670288,
      "learning_rate": 1.9568885893350126e-05,
      "loss": 0.5376,
      "step": 6199
    },
    {
      "epoch": 0.19045863668479096,
      "grad_norm": 0.3023369312286377,
      "learning_rate": 1.95687455117567e-05,
      "loss": 0.5271,
      "step": 6200
    },
    {
      "epoch": 0.1904893558197401,
      "grad_norm": 0.31457123160362244,
      "learning_rate": 1.9568605107814803e-05,
      "loss": 0.5544,
      "step": 6201
    },
    {
      "epoch": 0.19052007495468928,
      "grad_norm": 0.44319379329681396,
      "learning_rate": 1.9568464681524755e-05,
      "loss": 0.5876,
      "step": 6202
    },
    {
      "epoch": 0.19055079408963843,
      "grad_norm": 0.384607195854187,
      "learning_rate": 1.956832423288689e-05,
      "loss": 0.5848,
      "step": 6203
    },
    {
      "epoch": 0.1905815132245876,
      "grad_norm": 0.4057403802871704,
      "learning_rate": 1.956818376190154e-05,
      "loss": 0.6232,
      "step": 6204
    },
    {
      "epoch": 0.19061223235953675,
      "grad_norm": 0.32678085565567017,
      "learning_rate": 1.9568043268569025e-05,
      "loss": 0.6102,
      "step": 6205
    },
    {
      "epoch": 0.1906429514944859,
      "grad_norm": 0.3516559898853302,
      "learning_rate": 1.956790275288968e-05,
      "loss": 0.6027,
      "step": 6206
    },
    {
      "epoch": 0.19067367062943508,
      "grad_norm": 0.3640667200088501,
      "learning_rate": 1.9567762214863824e-05,
      "loss": 0.6147,
      "step": 6207
    },
    {
      "epoch": 0.19070438976438422,
      "grad_norm": 0.32667532563209534,
      "learning_rate": 1.9567621654491794e-05,
      "loss": 0.5758,
      "step": 6208
    },
    {
      "epoch": 0.1907351088993334,
      "grad_norm": 0.36968910694122314,
      "learning_rate": 1.9567481071773916e-05,
      "loss": 0.5562,
      "step": 6209
    },
    {
      "epoch": 0.19076582803428255,
      "grad_norm": 0.35286203026771545,
      "learning_rate": 1.956734046671052e-05,
      "loss": 0.6255,
      "step": 6210
    },
    {
      "epoch": 0.19079654716923172,
      "grad_norm": 0.31759607791900635,
      "learning_rate": 1.956719983930193e-05,
      "loss": 0.5675,
      "step": 6211
    },
    {
      "epoch": 0.19082726630418087,
      "grad_norm": 0.3365676701068878,
      "learning_rate": 1.9567059189548476e-05,
      "loss": 0.6168,
      "step": 6212
    },
    {
      "epoch": 0.19085798543913005,
      "grad_norm": 0.3232490122318268,
      "learning_rate": 1.956691851745049e-05,
      "loss": 0.5718,
      "step": 6213
    },
    {
      "epoch": 0.1908887045740792,
      "grad_norm": 0.36063340306282043,
      "learning_rate": 1.9566777823008292e-05,
      "loss": 0.5519,
      "step": 6214
    },
    {
      "epoch": 0.19091942370902834,
      "grad_norm": 0.32125377655029297,
      "learning_rate": 1.956663710622222e-05,
      "loss": 0.6289,
      "step": 6215
    },
    {
      "epoch": 0.19095014284397752,
      "grad_norm": 0.3388078212738037,
      "learning_rate": 1.95664963670926e-05,
      "loss": 0.7172,
      "step": 6216
    },
    {
      "epoch": 0.19098086197892666,
      "grad_norm": 0.3145463764667511,
      "learning_rate": 1.9566355605619758e-05,
      "loss": 0.6003,
      "step": 6217
    },
    {
      "epoch": 0.19101158111387584,
      "grad_norm": 0.35213831067085266,
      "learning_rate": 1.9566214821804024e-05,
      "loss": 0.6097,
      "step": 6218
    },
    {
      "epoch": 0.191042300248825,
      "grad_norm": 0.35210782289505005,
      "learning_rate": 1.956607401564573e-05,
      "loss": 0.6225,
      "step": 6219
    },
    {
      "epoch": 0.19107301938377416,
      "grad_norm": 0.3248279392719269,
      "learning_rate": 1.9565933187145196e-05,
      "loss": 0.6619,
      "step": 6220
    },
    {
      "epoch": 0.1911037385187233,
      "grad_norm": 0.32524311542510986,
      "learning_rate": 1.9565792336302763e-05,
      "loss": 0.5821,
      "step": 6221
    },
    {
      "epoch": 0.19113445765367248,
      "grad_norm": 0.35859349370002747,
      "learning_rate": 1.956565146311875e-05,
      "loss": 0.5356,
      "step": 6222
    },
    {
      "epoch": 0.19116517678862163,
      "grad_norm": 0.3532502055168152,
      "learning_rate": 1.9565510567593493e-05,
      "loss": 0.6362,
      "step": 6223
    },
    {
      "epoch": 0.19119589592357078,
      "grad_norm": 0.3316311538219452,
      "learning_rate": 1.9565369649727314e-05,
      "loss": 0.6522,
      "step": 6224
    },
    {
      "epoch": 0.19122661505851996,
      "grad_norm": 0.3410476744174957,
      "learning_rate": 1.956522870952055e-05,
      "loss": 0.6055,
      "step": 6225
    },
    {
      "epoch": 0.1912573341934691,
      "grad_norm": 0.3383321464061737,
      "learning_rate": 1.9565087746973526e-05,
      "loss": 0.5783,
      "step": 6226
    },
    {
      "epoch": 0.19128805332841828,
      "grad_norm": 0.35049957036972046,
      "learning_rate": 1.956494676208657e-05,
      "loss": 0.5664,
      "step": 6227
    },
    {
      "epoch": 0.19131877246336743,
      "grad_norm": 0.3359719514846802,
      "learning_rate": 1.9564805754860014e-05,
      "loss": 0.5797,
      "step": 6228
    },
    {
      "epoch": 0.1913494915983166,
      "grad_norm": 0.35982653498649597,
      "learning_rate": 1.9564664725294188e-05,
      "loss": 0.5774,
      "step": 6229
    },
    {
      "epoch": 0.19138021073326575,
      "grad_norm": 0.337742418050766,
      "learning_rate": 1.9564523673389416e-05,
      "loss": 0.6192,
      "step": 6230
    },
    {
      "epoch": 0.19141092986821492,
      "grad_norm": 0.3423040509223938,
      "learning_rate": 1.9564382599146034e-05,
      "loss": 0.5362,
      "step": 6231
    },
    {
      "epoch": 0.19144164900316407,
      "grad_norm": 0.35927677154541016,
      "learning_rate": 1.9564241502564363e-05,
      "loss": 0.6206,
      "step": 6232
    },
    {
      "epoch": 0.19147236813811322,
      "grad_norm": 0.34046781063079834,
      "learning_rate": 1.9564100383644744e-05,
      "loss": 0.5926,
      "step": 6233
    },
    {
      "epoch": 0.1915030872730624,
      "grad_norm": 0.3323444128036499,
      "learning_rate": 1.95639592423875e-05,
      "loss": 0.6482,
      "step": 6234
    },
    {
      "epoch": 0.19153380640801154,
      "grad_norm": 1.0870851278305054,
      "learning_rate": 1.9563818078792956e-05,
      "loss": 0.5905,
      "step": 6235
    },
    {
      "epoch": 0.19156452554296072,
      "grad_norm": 0.33346718549728394,
      "learning_rate": 1.956367689286145e-05,
      "loss": 0.6516,
      "step": 6236
    },
    {
      "epoch": 0.19159524467790987,
      "grad_norm": 0.36201006174087524,
      "learning_rate": 1.9563535684593308e-05,
      "loss": 0.5973,
      "step": 6237
    },
    {
      "epoch": 0.19162596381285904,
      "grad_norm": 0.4010887145996094,
      "learning_rate": 1.9563394453988863e-05,
      "loss": 0.6137,
      "step": 6238
    },
    {
      "epoch": 0.1916566829478082,
      "grad_norm": 0.3818175494670868,
      "learning_rate": 1.956325320104844e-05,
      "loss": 0.5855,
      "step": 6239
    },
    {
      "epoch": 0.19168740208275736,
      "grad_norm": 0.31991758942604065,
      "learning_rate": 1.9563111925772374e-05,
      "loss": 0.5542,
      "step": 6240
    },
    {
      "epoch": 0.1917181212177065,
      "grad_norm": 0.31085509061813354,
      "learning_rate": 1.956297062816099e-05,
      "loss": 0.5462,
      "step": 6241
    },
    {
      "epoch": 0.19174884035265566,
      "grad_norm": 0.5243284106254578,
      "learning_rate": 1.9562829308214623e-05,
      "loss": 0.5698,
      "step": 6242
    },
    {
      "epoch": 0.19177955948760483,
      "grad_norm": 0.33481141924858093,
      "learning_rate": 1.9562687965933594e-05,
      "loss": 0.5645,
      "step": 6243
    },
    {
      "epoch": 0.19181027862255398,
      "grad_norm": 0.3309917151927948,
      "learning_rate": 1.9562546601318244e-05,
      "loss": 0.5747,
      "step": 6244
    },
    {
      "epoch": 0.19184099775750316,
      "grad_norm": 0.3845181465148926,
      "learning_rate": 1.95624052143689e-05,
      "loss": 0.6407,
      "step": 6245
    },
    {
      "epoch": 0.1918717168924523,
      "grad_norm": 0.3252814710140228,
      "learning_rate": 1.956226380508589e-05,
      "loss": 0.6121,
      "step": 6246
    },
    {
      "epoch": 0.19190243602740148,
      "grad_norm": 0.37284672260284424,
      "learning_rate": 1.9562122373469543e-05,
      "loss": 0.5947,
      "step": 6247
    },
    {
      "epoch": 0.19193315516235063,
      "grad_norm": 0.3408557176589966,
      "learning_rate": 1.9561980919520193e-05,
      "loss": 0.6201,
      "step": 6248
    },
    {
      "epoch": 0.19196387429729977,
      "grad_norm": 0.3703811764717102,
      "learning_rate": 1.9561839443238165e-05,
      "loss": 0.6068,
      "step": 6249
    },
    {
      "epoch": 0.19199459343224895,
      "grad_norm": 0.36165958642959595,
      "learning_rate": 1.9561697944623795e-05,
      "loss": 0.6618,
      "step": 6250
    },
    {
      "epoch": 0.1920253125671981,
      "grad_norm": 0.37223976850509644,
      "learning_rate": 1.9561556423677415e-05,
      "loss": 0.6576,
      "step": 6251
    },
    {
      "epoch": 0.19205603170214727,
      "grad_norm": 0.46847522258758545,
      "learning_rate": 1.956141488039935e-05,
      "loss": 0.6044,
      "step": 6252
    },
    {
      "epoch": 0.19208675083709642,
      "grad_norm": 0.5338642001152039,
      "learning_rate": 1.9561273314789933e-05,
      "loss": 0.6373,
      "step": 6253
    },
    {
      "epoch": 0.1921174699720456,
      "grad_norm": 0.3535264730453491,
      "learning_rate": 1.9561131726849495e-05,
      "loss": 0.5457,
      "step": 6254
    },
    {
      "epoch": 0.19214818910699474,
      "grad_norm": 0.3301853835582733,
      "learning_rate": 1.9560990116578365e-05,
      "loss": 0.538,
      "step": 6255
    },
    {
      "epoch": 0.19217890824194392,
      "grad_norm": 0.3705619275569916,
      "learning_rate": 1.9560848483976874e-05,
      "loss": 0.7194,
      "step": 6256
    },
    {
      "epoch": 0.19220962737689307,
      "grad_norm": 0.3376169204711914,
      "learning_rate": 1.9560706829045356e-05,
      "loss": 0.6667,
      "step": 6257
    },
    {
      "epoch": 0.19224034651184221,
      "grad_norm": 0.39924898743629456,
      "learning_rate": 1.9560565151784138e-05,
      "loss": 0.6504,
      "step": 6258
    },
    {
      "epoch": 0.1922710656467914,
      "grad_norm": 0.30536970496177673,
      "learning_rate": 1.9560423452193553e-05,
      "loss": 0.6106,
      "step": 6259
    },
    {
      "epoch": 0.19230178478174054,
      "grad_norm": 0.3104843497276306,
      "learning_rate": 1.9560281730273932e-05,
      "loss": 0.557,
      "step": 6260
    },
    {
      "epoch": 0.1923325039166897,
      "grad_norm": 0.3345290720462799,
      "learning_rate": 1.9560139986025605e-05,
      "loss": 0.5948,
      "step": 6261
    },
    {
      "epoch": 0.19236322305163886,
      "grad_norm": 1.3528789281845093,
      "learning_rate": 1.95599982194489e-05,
      "loss": 0.6056,
      "step": 6262
    },
    {
      "epoch": 0.19239394218658804,
      "grad_norm": 0.3465305268764496,
      "learning_rate": 1.9559856430544155e-05,
      "loss": 0.5924,
      "step": 6263
    },
    {
      "epoch": 0.19242466132153718,
      "grad_norm": 0.3358083665370941,
      "learning_rate": 1.9559714619311697e-05,
      "loss": 0.6008,
      "step": 6264
    },
    {
      "epoch": 0.19245538045648636,
      "grad_norm": 0.409743994474411,
      "learning_rate": 1.955957278575186e-05,
      "loss": 0.6569,
      "step": 6265
    },
    {
      "epoch": 0.1924860995914355,
      "grad_norm": 0.3236980140209198,
      "learning_rate": 1.955943092986497e-05,
      "loss": 0.6599,
      "step": 6266
    },
    {
      "epoch": 0.19251681872638465,
      "grad_norm": 0.3399198353290558,
      "learning_rate": 1.955928905165136e-05,
      "loss": 0.6111,
      "step": 6267
    },
    {
      "epoch": 0.19254753786133383,
      "grad_norm": 0.3521079123020172,
      "learning_rate": 1.9559147151111365e-05,
      "loss": 0.6501,
      "step": 6268
    },
    {
      "epoch": 0.19257825699628298,
      "grad_norm": 0.3668191432952881,
      "learning_rate": 1.9559005228245317e-05,
      "loss": 0.573,
      "step": 6269
    },
    {
      "epoch": 0.19260897613123215,
      "grad_norm": 0.438985139131546,
      "learning_rate": 1.955886328305354e-05,
      "loss": 0.6145,
      "step": 6270
    },
    {
      "epoch": 0.1926396952661813,
      "grad_norm": 0.3567039370536804,
      "learning_rate": 1.9558721315536372e-05,
      "loss": 0.545,
      "step": 6271
    },
    {
      "epoch": 0.19267041440113047,
      "grad_norm": 0.30235716700553894,
      "learning_rate": 1.9558579325694145e-05,
      "loss": 0.5157,
      "step": 6272
    },
    {
      "epoch": 0.19270113353607962,
      "grad_norm": 0.3147967457771301,
      "learning_rate": 1.9558437313527186e-05,
      "loss": 0.6051,
      "step": 6273
    },
    {
      "epoch": 0.1927318526710288,
      "grad_norm": 0.3339538872241974,
      "learning_rate": 1.955829527903583e-05,
      "loss": 0.5998,
      "step": 6274
    },
    {
      "epoch": 0.19276257180597794,
      "grad_norm": 0.33632832765579224,
      "learning_rate": 1.9558153222220405e-05,
      "loss": 0.6124,
      "step": 6275
    },
    {
      "epoch": 0.1927932909409271,
      "grad_norm": 0.44229355454444885,
      "learning_rate": 1.955801114308125e-05,
      "loss": 0.6218,
      "step": 6276
    },
    {
      "epoch": 0.19282401007587627,
      "grad_norm": 0.37654978036880493,
      "learning_rate": 1.955786904161869e-05,
      "loss": 0.5917,
      "step": 6277
    },
    {
      "epoch": 0.19285472921082542,
      "grad_norm": 0.4572194516658783,
      "learning_rate": 1.955772691783306e-05,
      "loss": 0.6571,
      "step": 6278
    },
    {
      "epoch": 0.1928854483457746,
      "grad_norm": 0.33117055892944336,
      "learning_rate": 1.955758477172469e-05,
      "loss": 0.5707,
      "step": 6279
    },
    {
      "epoch": 0.19291616748072374,
      "grad_norm": 0.3766689598560333,
      "learning_rate": 1.9557442603293916e-05,
      "loss": 0.6496,
      "step": 6280
    },
    {
      "epoch": 0.1929468866156729,
      "grad_norm": 0.3931124210357666,
      "learning_rate": 1.9557300412541064e-05,
      "loss": 0.622,
      "step": 6281
    },
    {
      "epoch": 0.19297760575062206,
      "grad_norm": 0.3235599994659424,
      "learning_rate": 1.9557158199466472e-05,
      "loss": 0.5176,
      "step": 6282
    },
    {
      "epoch": 0.1930083248855712,
      "grad_norm": 0.32710957527160645,
      "learning_rate": 1.9557015964070468e-05,
      "loss": 0.5808,
      "step": 6283
    },
    {
      "epoch": 0.19303904402052038,
      "grad_norm": 0.32394564151763916,
      "learning_rate": 1.9556873706353387e-05,
      "loss": 0.5374,
      "step": 6284
    },
    {
      "epoch": 0.19306976315546953,
      "grad_norm": 0.31914472579956055,
      "learning_rate": 1.9556731426315562e-05,
      "loss": 0.5724,
      "step": 6285
    },
    {
      "epoch": 0.1931004822904187,
      "grad_norm": 0.3280538320541382,
      "learning_rate": 1.955658912395732e-05,
      "loss": 0.682,
      "step": 6286
    },
    {
      "epoch": 0.19313120142536785,
      "grad_norm": 0.39125245809555054,
      "learning_rate": 1.9556446799279e-05,
      "loss": 0.5253,
      "step": 6287
    },
    {
      "epoch": 0.19316192056031703,
      "grad_norm": 0.33672550320625305,
      "learning_rate": 1.9556304452280925e-05,
      "loss": 0.7119,
      "step": 6288
    },
    {
      "epoch": 0.19319263969526618,
      "grad_norm": 0.33820539712905884,
      "learning_rate": 1.955616208296344e-05,
      "loss": 0.5715,
      "step": 6289
    },
    {
      "epoch": 0.19322335883021535,
      "grad_norm": 0.3492792248725891,
      "learning_rate": 1.9556019691326864e-05,
      "loss": 0.6281,
      "step": 6290
    },
    {
      "epoch": 0.1932540779651645,
      "grad_norm": 0.38903066515922546,
      "learning_rate": 1.955587727737154e-05,
      "loss": 0.5875,
      "step": 6291
    },
    {
      "epoch": 0.19328479710011365,
      "grad_norm": 0.33967384696006775,
      "learning_rate": 1.95557348410978e-05,
      "loss": 0.5391,
      "step": 6292
    },
    {
      "epoch": 0.19331551623506282,
      "grad_norm": 0.40521663427352905,
      "learning_rate": 1.9555592382505972e-05,
      "loss": 0.5577,
      "step": 6293
    },
    {
      "epoch": 0.19334623537001197,
      "grad_norm": 0.3108349144458771,
      "learning_rate": 1.955544990159639e-05,
      "loss": 0.5428,
      "step": 6294
    },
    {
      "epoch": 0.19337695450496115,
      "grad_norm": 0.39852166175842285,
      "learning_rate": 1.9555307398369388e-05,
      "loss": 0.5051,
      "step": 6295
    },
    {
      "epoch": 0.1934076736399103,
      "grad_norm": 0.3580273687839508,
      "learning_rate": 1.9555164872825297e-05,
      "loss": 0.5783,
      "step": 6296
    },
    {
      "epoch": 0.19343839277485947,
      "grad_norm": 0.32443422079086304,
      "learning_rate": 1.9555022324964453e-05,
      "loss": 0.5493,
      "step": 6297
    },
    {
      "epoch": 0.19346911190980862,
      "grad_norm": 0.3639150857925415,
      "learning_rate": 1.9554879754787187e-05,
      "loss": 0.6136,
      "step": 6298
    },
    {
      "epoch": 0.1934998310447578,
      "grad_norm": 0.3212595283985138,
      "learning_rate": 1.9554737162293832e-05,
      "loss": 0.5479,
      "step": 6299
    },
    {
      "epoch": 0.19353055017970694,
      "grad_norm": 0.32214656472206116,
      "learning_rate": 1.9554594547484724e-05,
      "loss": 0.5083,
      "step": 6300
    },
    {
      "epoch": 0.1935612693146561,
      "grad_norm": 0.373786598443985,
      "learning_rate": 1.955445191036019e-05,
      "loss": 0.6738,
      "step": 6301
    },
    {
      "epoch": 0.19359198844960526,
      "grad_norm": 0.3506597578525543,
      "learning_rate": 1.9554309250920563e-05,
      "loss": 0.6125,
      "step": 6302
    },
    {
      "epoch": 0.1936227075845544,
      "grad_norm": 0.3565698266029358,
      "learning_rate": 1.955416656916618e-05,
      "loss": 0.5538,
      "step": 6303
    },
    {
      "epoch": 0.19365342671950359,
      "grad_norm": 0.41609033942222595,
      "learning_rate": 1.9554023865097377e-05,
      "loss": 0.4999,
      "step": 6304
    },
    {
      "epoch": 0.19368414585445273,
      "grad_norm": 0.36770111322402954,
      "learning_rate": 1.9553881138714487e-05,
      "loss": 0.5977,
      "step": 6305
    },
    {
      "epoch": 0.1937148649894019,
      "grad_norm": 0.3982047736644745,
      "learning_rate": 1.9553738390017834e-05,
      "loss": 0.5977,
      "step": 6306
    },
    {
      "epoch": 0.19374558412435106,
      "grad_norm": 0.3077632486820221,
      "learning_rate": 1.955359561900776e-05,
      "loss": 0.5296,
      "step": 6307
    },
    {
      "epoch": 0.19377630325930023,
      "grad_norm": 0.4014892578125,
      "learning_rate": 1.9553452825684597e-05,
      "loss": 0.5763,
      "step": 6308
    },
    {
      "epoch": 0.19380702239424938,
      "grad_norm": 0.35175758600234985,
      "learning_rate": 1.9553310010048676e-05,
      "loss": 0.6052,
      "step": 6309
    },
    {
      "epoch": 0.19383774152919853,
      "grad_norm": 0.3417648673057556,
      "learning_rate": 1.9553167172100335e-05,
      "loss": 0.6335,
      "step": 6310
    },
    {
      "epoch": 0.1938684606641477,
      "grad_norm": 0.36610114574432373,
      "learning_rate": 1.9553024311839902e-05,
      "loss": 0.5628,
      "step": 6311
    },
    {
      "epoch": 0.19389917979909685,
      "grad_norm": 0.37169015407562256,
      "learning_rate": 1.9552881429267714e-05,
      "loss": 0.6149,
      "step": 6312
    },
    {
      "epoch": 0.19392989893404602,
      "grad_norm": 0.3705911338329315,
      "learning_rate": 1.955273852438411e-05,
      "loss": 0.605,
      "step": 6313
    },
    {
      "epoch": 0.19396061806899517,
      "grad_norm": 0.41803619265556335,
      "learning_rate": 1.9552595597189408e-05,
      "loss": 0.5507,
      "step": 6314
    },
    {
      "epoch": 0.19399133720394435,
      "grad_norm": 0.3338092565536499,
      "learning_rate": 1.9552452647683958e-05,
      "loss": 0.6374,
      "step": 6315
    },
    {
      "epoch": 0.1940220563388935,
      "grad_norm": 0.3624483346939087,
      "learning_rate": 1.9552309675868087e-05,
      "loss": 0.604,
      "step": 6316
    },
    {
      "epoch": 0.19405277547384267,
      "grad_norm": 0.32347074151039124,
      "learning_rate": 1.955216668174213e-05,
      "loss": 0.5208,
      "step": 6317
    },
    {
      "epoch": 0.19408349460879182,
      "grad_norm": 0.3934149146080017,
      "learning_rate": 1.9552023665306417e-05,
      "loss": 0.5954,
      "step": 6318
    },
    {
      "epoch": 0.19411421374374097,
      "grad_norm": 0.3136445879936218,
      "learning_rate": 1.955188062656129e-05,
      "loss": 0.5701,
      "step": 6319
    },
    {
      "epoch": 0.19414493287869014,
      "grad_norm": 0.38582557439804077,
      "learning_rate": 1.955173756550708e-05,
      "loss": 0.6738,
      "step": 6320
    },
    {
      "epoch": 0.1941756520136393,
      "grad_norm": 0.4027613401412964,
      "learning_rate": 1.9551594482144118e-05,
      "loss": 0.574,
      "step": 6321
    },
    {
      "epoch": 0.19420637114858846,
      "grad_norm": 0.3727557361125946,
      "learning_rate": 1.9551451376472738e-05,
      "loss": 0.5771,
      "step": 6322
    },
    {
      "epoch": 0.1942370902835376,
      "grad_norm": 0.3793748915195465,
      "learning_rate": 1.955130824849328e-05,
      "loss": 0.5729,
      "step": 6323
    },
    {
      "epoch": 0.1942678094184868,
      "grad_norm": 0.4408375322818756,
      "learning_rate": 1.9551165098206068e-05,
      "loss": 0.5529,
      "step": 6324
    },
    {
      "epoch": 0.19429852855343593,
      "grad_norm": 0.32268160581588745,
      "learning_rate": 1.9551021925611445e-05,
      "loss": 0.5119,
      "step": 6325
    },
    {
      "epoch": 0.19432924768838508,
      "grad_norm": 0.36897581815719604,
      "learning_rate": 1.9550878730709746e-05,
      "loss": 0.5919,
      "step": 6326
    },
    {
      "epoch": 0.19435996682333426,
      "grad_norm": 0.3252463936805725,
      "learning_rate": 1.95507355135013e-05,
      "loss": 0.5706,
      "step": 6327
    },
    {
      "epoch": 0.1943906859582834,
      "grad_norm": 0.3508155643939972,
      "learning_rate": 1.9550592273986448e-05,
      "loss": 0.5904,
      "step": 6328
    },
    {
      "epoch": 0.19442140509323258,
      "grad_norm": 0.3795883059501648,
      "learning_rate": 1.9550449012165517e-05,
      "loss": 0.5997,
      "step": 6329
    },
    {
      "epoch": 0.19445212422818173,
      "grad_norm": 0.3807603120803833,
      "learning_rate": 1.955030572803885e-05,
      "loss": 0.5137,
      "step": 6330
    },
    {
      "epoch": 0.1944828433631309,
      "grad_norm": 0.33746466040611267,
      "learning_rate": 1.9550162421606774e-05,
      "loss": 0.6012,
      "step": 6331
    },
    {
      "epoch": 0.19451356249808005,
      "grad_norm": 0.3324538469314575,
      "learning_rate": 1.9550019092869627e-05,
      "loss": 0.5481,
      "step": 6332
    },
    {
      "epoch": 0.19454428163302923,
      "grad_norm": 0.4570996165275574,
      "learning_rate": 1.954987574182774e-05,
      "loss": 0.5346,
      "step": 6333
    },
    {
      "epoch": 0.19457500076797837,
      "grad_norm": 0.37248119711875916,
      "learning_rate": 1.9549732368481454e-05,
      "loss": 0.6624,
      "step": 6334
    },
    {
      "epoch": 0.19460571990292752,
      "grad_norm": 0.5224558711051941,
      "learning_rate": 1.9549588972831103e-05,
      "loss": 0.572,
      "step": 6335
    },
    {
      "epoch": 0.1946364390378767,
      "grad_norm": 0.44954895973205566,
      "learning_rate": 1.954944555487702e-05,
      "loss": 0.7234,
      "step": 6336
    },
    {
      "epoch": 0.19466715817282584,
      "grad_norm": 0.3798839747905731,
      "learning_rate": 1.954930211461954e-05,
      "loss": 0.6387,
      "step": 6337
    },
    {
      "epoch": 0.19469787730777502,
      "grad_norm": 0.3576046824455261,
      "learning_rate": 1.954915865205899e-05,
      "loss": 0.6306,
      "step": 6338
    },
    {
      "epoch": 0.19472859644272417,
      "grad_norm": 0.3532197177410126,
      "learning_rate": 1.9549015167195725e-05,
      "loss": 0.5668,
      "step": 6339
    },
    {
      "epoch": 0.19475931557767334,
      "grad_norm": 0.39078983664512634,
      "learning_rate": 1.954887166003006e-05,
      "loss": 0.5656,
      "step": 6340
    },
    {
      "epoch": 0.1947900347126225,
      "grad_norm": 0.33794912695884705,
      "learning_rate": 1.954872813056234e-05,
      "loss": 0.5433,
      "step": 6341
    },
    {
      "epoch": 0.19482075384757166,
      "grad_norm": 0.3429848253726959,
      "learning_rate": 1.95485845787929e-05,
      "loss": 0.5833,
      "step": 6342
    },
    {
      "epoch": 0.1948514729825208,
      "grad_norm": 0.33688682317733765,
      "learning_rate": 1.9548441004722076e-05,
      "loss": 0.5662,
      "step": 6343
    },
    {
      "epoch": 0.19488219211746996,
      "grad_norm": 0.4458933174610138,
      "learning_rate": 1.95482974083502e-05,
      "loss": 0.638,
      "step": 6344
    },
    {
      "epoch": 0.19491291125241914,
      "grad_norm": 0.35366082191467285,
      "learning_rate": 1.9548153789677604e-05,
      "loss": 0.6756,
      "step": 6345
    },
    {
      "epoch": 0.19494363038736828,
      "grad_norm": 0.32455724477767944,
      "learning_rate": 1.9548010148704634e-05,
      "loss": 0.5505,
      "step": 6346
    },
    {
      "epoch": 0.19497434952231746,
      "grad_norm": 0.3431819677352905,
      "learning_rate": 1.9547866485431614e-05,
      "loss": 0.5775,
      "step": 6347
    },
    {
      "epoch": 0.1950050686572666,
      "grad_norm": 0.35958194732666016,
      "learning_rate": 1.954772279985889e-05,
      "loss": 0.628,
      "step": 6348
    },
    {
      "epoch": 0.19503578779221578,
      "grad_norm": 0.3164888918399811,
      "learning_rate": 1.954757909198679e-05,
      "loss": 0.5972,
      "step": 6349
    },
    {
      "epoch": 0.19506650692716493,
      "grad_norm": 0.3278234899044037,
      "learning_rate": 1.954743536181565e-05,
      "loss": 0.537,
      "step": 6350
    },
    {
      "epoch": 0.1950972260621141,
      "grad_norm": 0.3471832275390625,
      "learning_rate": 1.9547291609345813e-05,
      "loss": 0.5177,
      "step": 6351
    },
    {
      "epoch": 0.19512794519706325,
      "grad_norm": 0.3593100607395172,
      "learning_rate": 1.9547147834577605e-05,
      "loss": 0.5691,
      "step": 6352
    },
    {
      "epoch": 0.1951586643320124,
      "grad_norm": 0.3849337697029114,
      "learning_rate": 1.954700403751137e-05,
      "loss": 0.4631,
      "step": 6353
    },
    {
      "epoch": 0.19518938346696157,
      "grad_norm": 0.3261682689189911,
      "learning_rate": 1.9546860218147438e-05,
      "loss": 0.5741,
      "step": 6354
    },
    {
      "epoch": 0.19522010260191072,
      "grad_norm": 0.3060195744037628,
      "learning_rate": 1.954671637648615e-05,
      "loss": 0.5603,
      "step": 6355
    },
    {
      "epoch": 0.1952508217368599,
      "grad_norm": 0.355910986661911,
      "learning_rate": 1.9546572512527836e-05,
      "loss": 0.6092,
      "step": 6356
    },
    {
      "epoch": 0.19528154087180905,
      "grad_norm": 0.5905948877334595,
      "learning_rate": 1.9546428626272837e-05,
      "loss": 0.5583,
      "step": 6357
    },
    {
      "epoch": 0.19531226000675822,
      "grad_norm": 1.1826802492141724,
      "learning_rate": 1.9546284717721488e-05,
      "loss": 0.5888,
      "step": 6358
    },
    {
      "epoch": 0.19534297914170737,
      "grad_norm": 0.7341731190681458,
      "learning_rate": 1.954614078687412e-05,
      "loss": 0.5553,
      "step": 6359
    },
    {
      "epoch": 0.19537369827665652,
      "grad_norm": 0.3650178909301758,
      "learning_rate": 1.954599683373108e-05,
      "loss": 0.568,
      "step": 6360
    },
    {
      "epoch": 0.1954044174116057,
      "grad_norm": 0.3204135298728943,
      "learning_rate": 1.9545852858292692e-05,
      "loss": 0.5553,
      "step": 6361
    },
    {
      "epoch": 0.19543513654655484,
      "grad_norm": 0.32405468821525574,
      "learning_rate": 1.95457088605593e-05,
      "loss": 0.616,
      "step": 6362
    },
    {
      "epoch": 0.195465855681504,
      "grad_norm": 0.49710774421691895,
      "learning_rate": 1.954556484053124e-05,
      "loss": 0.6547,
      "step": 6363
    },
    {
      "epoch": 0.19549657481645316,
      "grad_norm": 0.3416456878185272,
      "learning_rate": 1.9545420798208842e-05,
      "loss": 0.5682,
      "step": 6364
    },
    {
      "epoch": 0.19552729395140234,
      "grad_norm": 0.3704783320426941,
      "learning_rate": 1.9545276733592452e-05,
      "loss": 0.6406,
      "step": 6365
    },
    {
      "epoch": 0.19555801308635148,
      "grad_norm": 0.3300439417362213,
      "learning_rate": 1.95451326466824e-05,
      "loss": 0.5627,
      "step": 6366
    },
    {
      "epoch": 0.19558873222130066,
      "grad_norm": 0.4302448332309723,
      "learning_rate": 1.9544988537479025e-05,
      "loss": 0.6634,
      "step": 6367
    },
    {
      "epoch": 0.1956194513562498,
      "grad_norm": 0.352956622838974,
      "learning_rate": 1.9544844405982658e-05,
      "loss": 0.7083,
      "step": 6368
    },
    {
      "epoch": 0.19565017049119895,
      "grad_norm": 0.3296522796154022,
      "learning_rate": 1.9544700252193648e-05,
      "loss": 0.5451,
      "step": 6369
    },
    {
      "epoch": 0.19568088962614813,
      "grad_norm": 0.3564494848251343,
      "learning_rate": 1.9544556076112316e-05,
      "loss": 0.5638,
      "step": 6370
    },
    {
      "epoch": 0.19571160876109728,
      "grad_norm": 0.30844566226005554,
      "learning_rate": 1.9544411877739012e-05,
      "loss": 0.6065,
      "step": 6371
    },
    {
      "epoch": 0.19574232789604645,
      "grad_norm": 0.3313705623149872,
      "learning_rate": 1.9544267657074067e-05,
      "loss": 0.6008,
      "step": 6372
    },
    {
      "epoch": 0.1957730470309956,
      "grad_norm": 0.35705164074897766,
      "learning_rate": 1.9544123414117817e-05,
      "loss": 0.5919,
      "step": 6373
    },
    {
      "epoch": 0.19580376616594478,
      "grad_norm": 0.3362959325313568,
      "learning_rate": 1.95439791488706e-05,
      "loss": 0.5642,
      "step": 6374
    },
    {
      "epoch": 0.19583448530089392,
      "grad_norm": 0.31940168142318726,
      "learning_rate": 1.9543834861332754e-05,
      "loss": 0.6267,
      "step": 6375
    },
    {
      "epoch": 0.1958652044358431,
      "grad_norm": 0.3309680223464966,
      "learning_rate": 1.9543690551504616e-05,
      "loss": 0.6019,
      "step": 6376
    },
    {
      "epoch": 0.19589592357079225,
      "grad_norm": 0.35244888067245483,
      "learning_rate": 1.954354621938652e-05,
      "loss": 0.6355,
      "step": 6377
    },
    {
      "epoch": 0.1959266427057414,
      "grad_norm": 0.38712674379348755,
      "learning_rate": 1.9543401864978807e-05,
      "loss": 0.5817,
      "step": 6378
    },
    {
      "epoch": 0.19595736184069057,
      "grad_norm": 0.3223326504230499,
      "learning_rate": 1.954325748828181e-05,
      "loss": 0.6073,
      "step": 6379
    },
    {
      "epoch": 0.19598808097563972,
      "grad_norm": 0.3413582742214203,
      "learning_rate": 1.954311308929587e-05,
      "loss": 0.5926,
      "step": 6380
    },
    {
      "epoch": 0.1960188001105889,
      "grad_norm": 0.3492734432220459,
      "learning_rate": 1.9542968668021324e-05,
      "loss": 0.6875,
      "step": 6381
    },
    {
      "epoch": 0.19604951924553804,
      "grad_norm": 0.37131163477897644,
      "learning_rate": 1.9542824224458508e-05,
      "loss": 0.5967,
      "step": 6382
    },
    {
      "epoch": 0.19608023838048722,
      "grad_norm": 0.327243447303772,
      "learning_rate": 1.954267975860776e-05,
      "loss": 0.6687,
      "step": 6383
    },
    {
      "epoch": 0.19611095751543636,
      "grad_norm": 0.37095773220062256,
      "learning_rate": 1.9542535270469415e-05,
      "loss": 0.6012,
      "step": 6384
    },
    {
      "epoch": 0.19614167665038554,
      "grad_norm": 0.3541910946369171,
      "learning_rate": 1.9542390760043816e-05,
      "loss": 0.6475,
      "step": 6385
    },
    {
      "epoch": 0.19617239578533469,
      "grad_norm": 0.31742486357688904,
      "learning_rate": 1.9542246227331293e-05,
      "loss": 0.6208,
      "step": 6386
    },
    {
      "epoch": 0.19620311492028383,
      "grad_norm": 0.3359781801700592,
      "learning_rate": 1.9542101672332188e-05,
      "loss": 0.5008,
      "step": 6387
    },
    {
      "epoch": 0.196233834055233,
      "grad_norm": 0.34380149841308594,
      "learning_rate": 1.954195709504684e-05,
      "loss": 0.5761,
      "step": 6388
    },
    {
      "epoch": 0.19626455319018216,
      "grad_norm": 0.31248006224632263,
      "learning_rate": 1.9541812495475584e-05,
      "loss": 0.5409,
      "step": 6389
    },
    {
      "epoch": 0.19629527232513133,
      "grad_norm": 0.3833654522895813,
      "learning_rate": 1.9541667873618756e-05,
      "loss": 0.5462,
      "step": 6390
    },
    {
      "epoch": 0.19632599146008048,
      "grad_norm": 0.35575249791145325,
      "learning_rate": 1.95415232294767e-05,
      "loss": 0.6042,
      "step": 6391
    },
    {
      "epoch": 0.19635671059502965,
      "grad_norm": 0.3209853172302246,
      "learning_rate": 1.9541378563049748e-05,
      "loss": 0.586,
      "step": 6392
    },
    {
      "epoch": 0.1963874297299788,
      "grad_norm": 0.33042851090431213,
      "learning_rate": 1.9541233874338242e-05,
      "loss": 0.647,
      "step": 6393
    },
    {
      "epoch": 0.19641814886492798,
      "grad_norm": 0.33431529998779297,
      "learning_rate": 1.9541089163342516e-05,
      "loss": 0.6227,
      "step": 6394
    },
    {
      "epoch": 0.19644886799987712,
      "grad_norm": 0.3249675929546356,
      "learning_rate": 1.9540944430062908e-05,
      "loss": 0.612,
      "step": 6395
    },
    {
      "epoch": 0.19647958713482627,
      "grad_norm": 0.3468773365020752,
      "learning_rate": 1.9540799674499764e-05,
      "loss": 0.5587,
      "step": 6396
    },
    {
      "epoch": 0.19651030626977545,
      "grad_norm": 0.3681642711162567,
      "learning_rate": 1.9540654896653413e-05,
      "loss": 0.6126,
      "step": 6397
    },
    {
      "epoch": 0.1965410254047246,
      "grad_norm": 0.4214549958705902,
      "learning_rate": 1.9540510096524193e-05,
      "loss": 0.5925,
      "step": 6398
    },
    {
      "epoch": 0.19657174453967377,
      "grad_norm": 0.34049078822135925,
      "learning_rate": 1.954036527411245e-05,
      "loss": 0.6023,
      "step": 6399
    },
    {
      "epoch": 0.19660246367462292,
      "grad_norm": 0.35471540689468384,
      "learning_rate": 1.9540220429418516e-05,
      "loss": 0.6169,
      "step": 6400
    },
    {
      "epoch": 0.1966331828095721,
      "grad_norm": 0.37032195925712585,
      "learning_rate": 1.954007556244273e-05,
      "loss": 0.6038,
      "step": 6401
    },
    {
      "epoch": 0.19666390194452124,
      "grad_norm": 0.5136650800704956,
      "learning_rate": 1.9539930673185433e-05,
      "loss": 0.6014,
      "step": 6402
    },
    {
      "epoch": 0.1966946210794704,
      "grad_norm": 0.3367775082588196,
      "learning_rate": 1.953978576164696e-05,
      "loss": 0.6358,
      "step": 6403
    },
    {
      "epoch": 0.19672534021441956,
      "grad_norm": 0.37105515599250793,
      "learning_rate": 1.9539640827827652e-05,
      "loss": 0.4775,
      "step": 6404
    },
    {
      "epoch": 0.1967560593493687,
      "grad_norm": 0.38934525847435,
      "learning_rate": 1.9539495871727845e-05,
      "loss": 0.6729,
      "step": 6405
    },
    {
      "epoch": 0.1967867784843179,
      "grad_norm": 0.3666454553604126,
      "learning_rate": 1.953935089334788e-05,
      "loss": 0.5843,
      "step": 6406
    },
    {
      "epoch": 0.19681749761926703,
      "grad_norm": 0.33023911714553833,
      "learning_rate": 1.9539205892688096e-05,
      "loss": 0.5685,
      "step": 6407
    },
    {
      "epoch": 0.1968482167542162,
      "grad_norm": 0.3335317373275757,
      "learning_rate": 1.953906086974883e-05,
      "loss": 0.5852,
      "step": 6408
    },
    {
      "epoch": 0.19687893588916536,
      "grad_norm": 0.3735830783843994,
      "learning_rate": 1.953891582453042e-05,
      "loss": 0.577,
      "step": 6409
    },
    {
      "epoch": 0.19690965502411453,
      "grad_norm": 0.38877856731414795,
      "learning_rate": 1.9538770757033208e-05,
      "loss": 0.6166,
      "step": 6410
    },
    {
      "epoch": 0.19694037415906368,
      "grad_norm": 0.3454803228378296,
      "learning_rate": 1.953862566725753e-05,
      "loss": 0.6363,
      "step": 6411
    },
    {
      "epoch": 0.19697109329401283,
      "grad_norm": 0.33244481682777405,
      "learning_rate": 1.953848055520372e-05,
      "loss": 0.5693,
      "step": 6412
    },
    {
      "epoch": 0.197001812428962,
      "grad_norm": 0.32584109902381897,
      "learning_rate": 1.953833542087213e-05,
      "loss": 0.6304,
      "step": 6413
    },
    {
      "epoch": 0.19703253156391115,
      "grad_norm": 0.3966572880744934,
      "learning_rate": 1.953819026426309e-05,
      "loss": 0.6978,
      "step": 6414
    },
    {
      "epoch": 0.19706325069886033,
      "grad_norm": 0.4159698486328125,
      "learning_rate": 1.953804508537694e-05,
      "loss": 0.5565,
      "step": 6415
    },
    {
      "epoch": 0.19709396983380947,
      "grad_norm": 0.3767610788345337,
      "learning_rate": 1.9537899884214016e-05,
      "loss": 0.6341,
      "step": 6416
    },
    {
      "epoch": 0.19712468896875865,
      "grad_norm": 0.3294268846511841,
      "learning_rate": 1.9537754660774666e-05,
      "loss": 0.583,
      "step": 6417
    },
    {
      "epoch": 0.1971554081037078,
      "grad_norm": 0.3436012268066406,
      "learning_rate": 1.953760941505922e-05,
      "loss": 0.6083,
      "step": 6418
    },
    {
      "epoch": 0.19718612723865697,
      "grad_norm": 0.33407509326934814,
      "learning_rate": 1.9537464147068025e-05,
      "loss": 0.5573,
      "step": 6419
    },
    {
      "epoch": 0.19721684637360612,
      "grad_norm": 0.38554853200912476,
      "learning_rate": 1.953731885680141e-05,
      "loss": 0.5887,
      "step": 6420
    },
    {
      "epoch": 0.19724756550855527,
      "grad_norm": 0.3414930999279022,
      "learning_rate": 1.953717354425973e-05,
      "loss": 0.7791,
      "step": 6421
    },
    {
      "epoch": 0.19727828464350444,
      "grad_norm": 0.3390360176563263,
      "learning_rate": 1.953702820944331e-05,
      "loss": 0.5811,
      "step": 6422
    },
    {
      "epoch": 0.1973090037784536,
      "grad_norm": 0.34445905685424805,
      "learning_rate": 1.9536882852352494e-05,
      "loss": 0.6269,
      "step": 6423
    },
    {
      "epoch": 0.19733972291340277,
      "grad_norm": 0.3204452395439148,
      "learning_rate": 1.9536737472987623e-05,
      "loss": 0.575,
      "step": 6424
    },
    {
      "epoch": 0.1973704420483519,
      "grad_norm": 0.3205937445163727,
      "learning_rate": 1.9536592071349034e-05,
      "loss": 0.5432,
      "step": 6425
    },
    {
      "epoch": 0.1974011611833011,
      "grad_norm": 0.3321768641471863,
      "learning_rate": 1.953644664743707e-05,
      "loss": 0.6257,
      "step": 6426
    },
    {
      "epoch": 0.19743188031825024,
      "grad_norm": 0.3452436029911041,
      "learning_rate": 1.9536301201252068e-05,
      "loss": 0.6241,
      "step": 6427
    },
    {
      "epoch": 0.1974625994531994,
      "grad_norm": 0.37319841980934143,
      "learning_rate": 1.9536155732794367e-05,
      "loss": 0.6531,
      "step": 6428
    },
    {
      "epoch": 0.19749331858814856,
      "grad_norm": 0.30958208441734314,
      "learning_rate": 1.953601024206431e-05,
      "loss": 0.5188,
      "step": 6429
    },
    {
      "epoch": 0.1975240377230977,
      "grad_norm": 0.33685338497161865,
      "learning_rate": 1.9535864729062236e-05,
      "loss": 0.5196,
      "step": 6430
    },
    {
      "epoch": 0.19755475685804688,
      "grad_norm": 0.46763330698013306,
      "learning_rate": 1.9535719193788486e-05,
      "loss": 0.5875,
      "step": 6431
    },
    {
      "epoch": 0.19758547599299603,
      "grad_norm": 0.39087626338005066,
      "learning_rate": 1.9535573636243394e-05,
      "loss": 0.6501,
      "step": 6432
    },
    {
      "epoch": 0.1976161951279452,
      "grad_norm": 0.32197001576423645,
      "learning_rate": 1.9535428056427305e-05,
      "loss": 0.5968,
      "step": 6433
    },
    {
      "epoch": 0.19764691426289435,
      "grad_norm": 0.30515867471694946,
      "learning_rate": 1.9535282454340555e-05,
      "loss": 0.6203,
      "step": 6434
    },
    {
      "epoch": 0.19767763339784353,
      "grad_norm": 0.3168692886829376,
      "learning_rate": 1.953513682998349e-05,
      "loss": 0.6163,
      "step": 6435
    },
    {
      "epoch": 0.19770835253279267,
      "grad_norm": 0.3341432511806488,
      "learning_rate": 1.9534991183356447e-05,
      "loss": 0.6112,
      "step": 6436
    },
    {
      "epoch": 0.19773907166774182,
      "grad_norm": 0.34830594062805176,
      "learning_rate": 1.9534845514459766e-05,
      "loss": 0.5733,
      "step": 6437
    },
    {
      "epoch": 0.197769790802691,
      "grad_norm": 0.3227662444114685,
      "learning_rate": 1.9534699823293787e-05,
      "loss": 0.5671,
      "step": 6438
    },
    {
      "epoch": 0.19780050993764015,
      "grad_norm": 0.3683364689350128,
      "learning_rate": 1.953455410985885e-05,
      "loss": 0.6314,
      "step": 6439
    },
    {
      "epoch": 0.19783122907258932,
      "grad_norm": 0.35587361454963684,
      "learning_rate": 1.9534408374155296e-05,
      "loss": 0.649,
      "step": 6440
    },
    {
      "epoch": 0.19786194820753847,
      "grad_norm": 0.34121397137641907,
      "learning_rate": 1.9534262616183465e-05,
      "loss": 0.5189,
      "step": 6441
    },
    {
      "epoch": 0.19789266734248764,
      "grad_norm": 0.3259091079235077,
      "learning_rate": 1.95341168359437e-05,
      "loss": 0.6323,
      "step": 6442
    },
    {
      "epoch": 0.1979233864774368,
      "grad_norm": 0.39886727929115295,
      "learning_rate": 1.9533971033436338e-05,
      "loss": 0.5936,
      "step": 6443
    },
    {
      "epoch": 0.19795410561238597,
      "grad_norm": 0.3315318822860718,
      "learning_rate": 1.9533825208661722e-05,
      "loss": 0.5729,
      "step": 6444
    },
    {
      "epoch": 0.19798482474733511,
      "grad_norm": 0.34765633940696716,
      "learning_rate": 1.953367936162019e-05,
      "loss": 0.5443,
      "step": 6445
    },
    {
      "epoch": 0.19801554388228426,
      "grad_norm": 0.3341686427593231,
      "learning_rate": 1.9533533492312085e-05,
      "loss": 0.5111,
      "step": 6446
    },
    {
      "epoch": 0.19804626301723344,
      "grad_norm": 0.8042997121810913,
      "learning_rate": 1.9533387600737744e-05,
      "loss": 0.6,
      "step": 6447
    },
    {
      "epoch": 0.19807698215218258,
      "grad_norm": 0.339678019285202,
      "learning_rate": 1.9533241686897516e-05,
      "loss": 0.5725,
      "step": 6448
    },
    {
      "epoch": 0.19810770128713176,
      "grad_norm": 0.375617116689682,
      "learning_rate": 1.953309575079173e-05,
      "loss": 0.6224,
      "step": 6449
    },
    {
      "epoch": 0.1981384204220809,
      "grad_norm": 0.5088332891464233,
      "learning_rate": 1.9532949792420737e-05,
      "loss": 0.6416,
      "step": 6450
    },
    {
      "epoch": 0.19816913955703008,
      "grad_norm": 0.38662755489349365,
      "learning_rate": 1.9532803811784873e-05,
      "loss": 0.5835,
      "step": 6451
    },
    {
      "epoch": 0.19819985869197923,
      "grad_norm": 0.3311774432659149,
      "learning_rate": 1.953265780888448e-05,
      "loss": 0.6123,
      "step": 6452
    },
    {
      "epoch": 0.1982305778269284,
      "grad_norm": 0.3402464985847473,
      "learning_rate": 1.9532511783719897e-05,
      "loss": 0.5265,
      "step": 6453
    },
    {
      "epoch": 0.19826129696187755,
      "grad_norm": 0.3653241693973541,
      "learning_rate": 1.953236573629147e-05,
      "loss": 0.6542,
      "step": 6454
    },
    {
      "epoch": 0.1982920160968267,
      "grad_norm": 0.3488057255744934,
      "learning_rate": 1.953221966659954e-05,
      "loss": 0.6252,
      "step": 6455
    },
    {
      "epoch": 0.19832273523177588,
      "grad_norm": 0.31706684827804565,
      "learning_rate": 1.9532073574644436e-05,
      "loss": 0.5761,
      "step": 6456
    },
    {
      "epoch": 0.19835345436672502,
      "grad_norm": 0.3225887715816498,
      "learning_rate": 1.9531927460426513e-05,
      "loss": 0.5736,
      "step": 6457
    },
    {
      "epoch": 0.1983841735016742,
      "grad_norm": 0.33263248205184937,
      "learning_rate": 1.9531781323946107e-05,
      "loss": 0.6117,
      "step": 6458
    },
    {
      "epoch": 0.19841489263662335,
      "grad_norm": 0.3264133930206299,
      "learning_rate": 1.9531635165203565e-05,
      "loss": 0.6037,
      "step": 6459
    },
    {
      "epoch": 0.19844561177157252,
      "grad_norm": 0.32914844155311584,
      "learning_rate": 1.9531488984199218e-05,
      "loss": 0.62,
      "step": 6460
    },
    {
      "epoch": 0.19847633090652167,
      "grad_norm": 0.325336754322052,
      "learning_rate": 1.9531342780933412e-05,
      "loss": 0.6141,
      "step": 6461
    },
    {
      "epoch": 0.19850705004147084,
      "grad_norm": 0.899788498878479,
      "learning_rate": 1.9531196555406496e-05,
      "loss": 0.5482,
      "step": 6462
    },
    {
      "epoch": 0.19853776917642,
      "grad_norm": 0.3570587635040283,
      "learning_rate": 1.95310503076188e-05,
      "loss": 0.6205,
      "step": 6463
    },
    {
      "epoch": 0.19856848831136914,
      "grad_norm": 0.32597875595092773,
      "learning_rate": 1.9530904037570672e-05,
      "loss": 0.5587,
      "step": 6464
    },
    {
      "epoch": 0.19859920744631832,
      "grad_norm": 0.35033726692199707,
      "learning_rate": 1.953075774526245e-05,
      "loss": 0.6204,
      "step": 6465
    },
    {
      "epoch": 0.19862992658126746,
      "grad_norm": 0.3471260964870453,
      "learning_rate": 1.9530611430694477e-05,
      "loss": 0.6511,
      "step": 6466
    },
    {
      "epoch": 0.19866064571621664,
      "grad_norm": 0.3436495065689087,
      "learning_rate": 1.9530465093867097e-05,
      "loss": 0.5785,
      "step": 6467
    },
    {
      "epoch": 0.19869136485116579,
      "grad_norm": 0.4071119725704193,
      "learning_rate": 1.953031873478065e-05,
      "loss": 0.5434,
      "step": 6468
    },
    {
      "epoch": 0.19872208398611496,
      "grad_norm": 0.3284960091114044,
      "learning_rate": 1.953017235343548e-05,
      "loss": 0.6406,
      "step": 6469
    },
    {
      "epoch": 0.1987528031210641,
      "grad_norm": 0.31884050369262695,
      "learning_rate": 1.9530025949831925e-05,
      "loss": 0.5618,
      "step": 6470
    },
    {
      "epoch": 0.19878352225601328,
      "grad_norm": 0.2948976457118988,
      "learning_rate": 1.952987952397033e-05,
      "loss": 0.5145,
      "step": 6471
    },
    {
      "epoch": 0.19881424139096243,
      "grad_norm": 0.31598225235939026,
      "learning_rate": 1.9529733075851032e-05,
      "loss": 0.556,
      "step": 6472
    },
    {
      "epoch": 0.19884496052591158,
      "grad_norm": 0.37477636337280273,
      "learning_rate": 1.952958660547438e-05,
      "loss": 0.5891,
      "step": 6473
    },
    {
      "epoch": 0.19887567966086075,
      "grad_norm": 0.34696149826049805,
      "learning_rate": 1.9529440112840712e-05,
      "loss": 0.5315,
      "step": 6474
    },
    {
      "epoch": 0.1989063987958099,
      "grad_norm": 0.32079872488975525,
      "learning_rate": 1.9529293597950373e-05,
      "loss": 0.4944,
      "step": 6475
    },
    {
      "epoch": 0.19893711793075908,
      "grad_norm": 0.3651439845561981,
      "learning_rate": 1.95291470608037e-05,
      "loss": 0.587,
      "step": 6476
    },
    {
      "epoch": 0.19896783706570823,
      "grad_norm": 0.35026660561561584,
      "learning_rate": 1.952900050140104e-05,
      "loss": 0.6038,
      "step": 6477
    },
    {
      "epoch": 0.1989985562006574,
      "grad_norm": 0.40626609325408936,
      "learning_rate": 1.9528853919742733e-05,
      "loss": 0.5608,
      "step": 6478
    },
    {
      "epoch": 0.19902927533560655,
      "grad_norm": 0.34212860465049744,
      "learning_rate": 1.9528707315829124e-05,
      "loss": 0.5661,
      "step": 6479
    },
    {
      "epoch": 0.1990599944705557,
      "grad_norm": 0.33822762966156006,
      "learning_rate": 1.9528560689660553e-05,
      "loss": 0.6121,
      "step": 6480
    },
    {
      "epoch": 0.19909071360550487,
      "grad_norm": 0.32257241010665894,
      "learning_rate": 1.952841404123736e-05,
      "loss": 0.5324,
      "step": 6481
    },
    {
      "epoch": 0.19912143274045402,
      "grad_norm": 0.37860241532325745,
      "learning_rate": 1.9528267370559896e-05,
      "loss": 0.5966,
      "step": 6482
    },
    {
      "epoch": 0.1991521518754032,
      "grad_norm": 0.3262556493282318,
      "learning_rate": 1.9528120677628494e-05,
      "loss": 0.5697,
      "step": 6483
    },
    {
      "epoch": 0.19918287101035234,
      "grad_norm": 0.3663138151168823,
      "learning_rate": 1.9527973962443503e-05,
      "loss": 0.5925,
      "step": 6484
    },
    {
      "epoch": 0.19921359014530152,
      "grad_norm": 0.314195454120636,
      "learning_rate": 1.9527827225005263e-05,
      "loss": 0.617,
      "step": 6485
    },
    {
      "epoch": 0.19924430928025066,
      "grad_norm": 0.31242072582244873,
      "learning_rate": 1.952768046531412e-05,
      "loss": 0.5457,
      "step": 6486
    },
    {
      "epoch": 0.19927502841519984,
      "grad_norm": 0.3955460786819458,
      "learning_rate": 1.952753368337041e-05,
      "loss": 0.5233,
      "step": 6487
    },
    {
      "epoch": 0.199305747550149,
      "grad_norm": 0.3515368700027466,
      "learning_rate": 1.952738687917448e-05,
      "loss": 0.7396,
      "step": 6488
    },
    {
      "epoch": 0.19933646668509813,
      "grad_norm": 0.346470445394516,
      "learning_rate": 1.9527240052726674e-05,
      "loss": 0.5776,
      "step": 6489
    },
    {
      "epoch": 0.1993671858200473,
      "grad_norm": 0.3209567070007324,
      "learning_rate": 1.952709320402733e-05,
      "loss": 0.6791,
      "step": 6490
    },
    {
      "epoch": 0.19939790495499646,
      "grad_norm": 0.3613731861114502,
      "learning_rate": 1.9526946333076798e-05,
      "loss": 0.5042,
      "step": 6491
    },
    {
      "epoch": 0.19942862408994563,
      "grad_norm": 0.3113194406032562,
      "learning_rate": 1.9526799439875415e-05,
      "loss": 0.5702,
      "step": 6492
    },
    {
      "epoch": 0.19945934322489478,
      "grad_norm": 0.3620237112045288,
      "learning_rate": 1.9526652524423528e-05,
      "loss": 0.6182,
      "step": 6493
    },
    {
      "epoch": 0.19949006235984396,
      "grad_norm": 0.35268092155456543,
      "learning_rate": 1.952650558672148e-05,
      "loss": 0.5627,
      "step": 6494
    },
    {
      "epoch": 0.1995207814947931,
      "grad_norm": 0.4094632565975189,
      "learning_rate": 1.952635862676961e-05,
      "loss": 0.6612,
      "step": 6495
    },
    {
      "epoch": 0.19955150062974228,
      "grad_norm": 0.3358514904975891,
      "learning_rate": 1.9526211644568267e-05,
      "loss": 0.6107,
      "step": 6496
    },
    {
      "epoch": 0.19958221976469143,
      "grad_norm": 0.3390800654888153,
      "learning_rate": 1.952606464011779e-05,
      "loss": 0.6081,
      "step": 6497
    },
    {
      "epoch": 0.19961293889964057,
      "grad_norm": 1.4707797765731812,
      "learning_rate": 1.9525917613418525e-05,
      "loss": 0.5629,
      "step": 6498
    },
    {
      "epoch": 0.19964365803458975,
      "grad_norm": 0.36978116631507874,
      "learning_rate": 1.9525770564470813e-05,
      "loss": 0.6267,
      "step": 6499
    },
    {
      "epoch": 0.1996743771695389,
      "grad_norm": 0.30593085289001465,
      "learning_rate": 1.9525623493274998e-05,
      "loss": 0.5504,
      "step": 6500
    },
    {
      "epoch": 0.19970509630448807,
      "grad_norm": 0.33329063653945923,
      "learning_rate": 1.9525476399831422e-05,
      "loss": 0.6537,
      "step": 6501
    },
    {
      "epoch": 0.19973581543943722,
      "grad_norm": 0.37859615683555603,
      "learning_rate": 1.952532928414043e-05,
      "loss": 0.664,
      "step": 6502
    },
    {
      "epoch": 0.1997665345743864,
      "grad_norm": 0.3044280409812927,
      "learning_rate": 1.9525182146202374e-05,
      "loss": 0.5611,
      "step": 6503
    },
    {
      "epoch": 0.19979725370933554,
      "grad_norm": 0.3246181607246399,
      "learning_rate": 1.9525034986017583e-05,
      "loss": 0.637,
      "step": 6504
    },
    {
      "epoch": 0.19982797284428472,
      "grad_norm": 0.3161492645740509,
      "learning_rate": 1.9524887803586413e-05,
      "loss": 0.529,
      "step": 6505
    },
    {
      "epoch": 0.19985869197923387,
      "grad_norm": 0.3204783499240875,
      "learning_rate": 1.9524740598909196e-05,
      "loss": 0.5051,
      "step": 6506
    },
    {
      "epoch": 0.199889411114183,
      "grad_norm": 0.33148109912872314,
      "learning_rate": 1.9524593371986286e-05,
      "loss": 0.5714,
      "step": 6507
    },
    {
      "epoch": 0.1999201302491322,
      "grad_norm": 0.3077986538410187,
      "learning_rate": 1.9524446122818024e-05,
      "loss": 0.5282,
      "step": 6508
    },
    {
      "epoch": 0.19995084938408134,
      "grad_norm": 0.3595099449157715,
      "learning_rate": 1.9524298851404752e-05,
      "loss": 0.7234,
      "step": 6509
    },
    {
      "epoch": 0.1999815685190305,
      "grad_norm": 0.3267649710178375,
      "learning_rate": 1.9524151557746813e-05,
      "loss": 0.5599,
      "step": 6510
    },
    {
      "epoch": 0.20001228765397966,
      "grad_norm": 0.34195294976234436,
      "learning_rate": 1.952400424184455e-05,
      "loss": 0.6082,
      "step": 6511
    },
    {
      "epoch": 0.20004300678892883,
      "grad_norm": 0.3701915442943573,
      "learning_rate": 1.9523856903698317e-05,
      "loss": 0.6498,
      "step": 6512
    },
    {
      "epoch": 0.20007372592387798,
      "grad_norm": 0.32870742678642273,
      "learning_rate": 1.952370954330845e-05,
      "loss": 0.6347,
      "step": 6513
    },
    {
      "epoch": 0.20010444505882716,
      "grad_norm": 0.3228437006473541,
      "learning_rate": 1.952356216067529e-05,
      "loss": 0.5496,
      "step": 6514
    },
    {
      "epoch": 0.2001351641937763,
      "grad_norm": 0.46836817264556885,
      "learning_rate": 1.952341475579919e-05,
      "loss": 0.6847,
      "step": 6515
    },
    {
      "epoch": 0.20016588332872545,
      "grad_norm": 0.34423258900642395,
      "learning_rate": 1.9523267328680483e-05,
      "loss": 0.6491,
      "step": 6516
    },
    {
      "epoch": 0.20019660246367463,
      "grad_norm": 0.30061933398246765,
      "learning_rate": 1.9523119879319527e-05,
      "loss": 0.5364,
      "step": 6517
    },
    {
      "epoch": 0.20022732159862378,
      "grad_norm": 0.3542007505893707,
      "learning_rate": 1.9522972407716656e-05,
      "loss": 0.6873,
      "step": 6518
    },
    {
      "epoch": 0.20025804073357295,
      "grad_norm": 0.32702869176864624,
      "learning_rate": 1.952282491387222e-05,
      "loss": 0.5673,
      "step": 6519
    },
    {
      "epoch": 0.2002887598685221,
      "grad_norm": 0.35464000701904297,
      "learning_rate": 1.952267739778656e-05,
      "loss": 0.6202,
      "step": 6520
    },
    {
      "epoch": 0.20031947900347127,
      "grad_norm": 0.3338501751422882,
      "learning_rate": 1.952252985946002e-05,
      "loss": 0.6467,
      "step": 6521
    },
    {
      "epoch": 0.20035019813842042,
      "grad_norm": 0.35147497057914734,
      "learning_rate": 1.952238229889295e-05,
      "loss": 0.5925,
      "step": 6522
    },
    {
      "epoch": 0.20038091727336957,
      "grad_norm": 0.33275121450424194,
      "learning_rate": 1.952223471608569e-05,
      "loss": 0.6181,
      "step": 6523
    },
    {
      "epoch": 0.20041163640831874,
      "grad_norm": 0.33873251080513,
      "learning_rate": 1.9522087111038584e-05,
      "loss": 0.6058,
      "step": 6524
    },
    {
      "epoch": 0.2004423555432679,
      "grad_norm": 0.4144977331161499,
      "learning_rate": 1.952193948375198e-05,
      "loss": 0.6776,
      "step": 6525
    },
    {
      "epoch": 0.20047307467821707,
      "grad_norm": 0.33509498834609985,
      "learning_rate": 1.952179183422622e-05,
      "loss": 0.666,
      "step": 6526
    },
    {
      "epoch": 0.20050379381316621,
      "grad_norm": 0.3504704236984253,
      "learning_rate": 1.952164416246165e-05,
      "loss": 0.5727,
      "step": 6527
    },
    {
      "epoch": 0.2005345129481154,
      "grad_norm": 1.9860402345657349,
      "learning_rate": 1.9521496468458617e-05,
      "loss": 0.5252,
      "step": 6528
    },
    {
      "epoch": 0.20056523208306454,
      "grad_norm": 0.3603843152523041,
      "learning_rate": 1.9521348752217465e-05,
      "loss": 0.6278,
      "step": 6529
    },
    {
      "epoch": 0.2005959512180137,
      "grad_norm": 0.364622563123703,
      "learning_rate": 1.9521201013738537e-05,
      "loss": 0.6363,
      "step": 6530
    },
    {
      "epoch": 0.20062667035296286,
      "grad_norm": 0.34830495715141296,
      "learning_rate": 1.952105325302218e-05,
      "loss": 0.6091,
      "step": 6531
    },
    {
      "epoch": 0.200657389487912,
      "grad_norm": 0.3232707977294922,
      "learning_rate": 1.9520905470068735e-05,
      "loss": 0.6263,
      "step": 6532
    },
    {
      "epoch": 0.20068810862286118,
      "grad_norm": 0.34429657459259033,
      "learning_rate": 1.9520757664878553e-05,
      "loss": 0.6265,
      "step": 6533
    },
    {
      "epoch": 0.20071882775781033,
      "grad_norm": 0.3794332444667816,
      "learning_rate": 1.9520609837451973e-05,
      "loss": 0.6412,
      "step": 6534
    },
    {
      "epoch": 0.2007495468927595,
      "grad_norm": 0.3291994631290436,
      "learning_rate": 1.952046198778935e-05,
      "loss": 0.551,
      "step": 6535
    },
    {
      "epoch": 0.20078026602770865,
      "grad_norm": 34.656639099121094,
      "learning_rate": 1.9520314115891016e-05,
      "loss": 0.547,
      "step": 6536
    },
    {
      "epoch": 0.20081098516265783,
      "grad_norm": 0.3402886390686035,
      "learning_rate": 1.952016622175733e-05,
      "loss": 0.5751,
      "step": 6537
    },
    {
      "epoch": 0.20084170429760698,
      "grad_norm": 0.33503004908561707,
      "learning_rate": 1.9520018305388627e-05,
      "loss": 0.6392,
      "step": 6538
    },
    {
      "epoch": 0.20087242343255615,
      "grad_norm": 0.3164066672325134,
      "learning_rate": 1.9519870366785257e-05,
      "loss": 0.5239,
      "step": 6539
    },
    {
      "epoch": 0.2009031425675053,
      "grad_norm": 0.3417780101299286,
      "learning_rate": 1.9519722405947563e-05,
      "loss": 0.5826,
      "step": 6540
    },
    {
      "epoch": 0.20093386170245445,
      "grad_norm": 0.37783390283584595,
      "learning_rate": 1.9519574422875894e-05,
      "loss": 0.6373,
      "step": 6541
    },
    {
      "epoch": 0.20096458083740362,
      "grad_norm": 0.32468944787979126,
      "learning_rate": 1.9519426417570596e-05,
      "loss": 0.5515,
      "step": 6542
    },
    {
      "epoch": 0.20099529997235277,
      "grad_norm": 0.3381183445453644,
      "learning_rate": 1.9519278390032012e-05,
      "loss": 0.6284,
      "step": 6543
    },
    {
      "epoch": 0.20102601910730195,
      "grad_norm": 0.3537866473197937,
      "learning_rate": 1.951913034026049e-05,
      "loss": 0.546,
      "step": 6544
    },
    {
      "epoch": 0.2010567382422511,
      "grad_norm": 0.34445920586586,
      "learning_rate": 1.951898226825637e-05,
      "loss": 0.6233,
      "step": 6545
    },
    {
      "epoch": 0.20108745737720027,
      "grad_norm": 0.32523414492607117,
      "learning_rate": 1.951883417402001e-05,
      "loss": 0.634,
      "step": 6546
    },
    {
      "epoch": 0.20111817651214942,
      "grad_norm": 0.36353418231010437,
      "learning_rate": 1.951868605755174e-05,
      "loss": 0.6551,
      "step": 6547
    },
    {
      "epoch": 0.2011488956470986,
      "grad_norm": 0.36003002524375916,
      "learning_rate": 1.9518537918851913e-05,
      "loss": 0.5799,
      "step": 6548
    },
    {
      "epoch": 0.20117961478204774,
      "grad_norm": 0.37651318311691284,
      "learning_rate": 1.9518389757920883e-05,
      "loss": 0.6421,
      "step": 6549
    },
    {
      "epoch": 0.2012103339169969,
      "grad_norm": 0.3531327247619629,
      "learning_rate": 1.951824157475898e-05,
      "loss": 0.6096,
      "step": 6550
    },
    {
      "epoch": 0.20124105305194606,
      "grad_norm": 0.3249610960483551,
      "learning_rate": 1.9518093369366568e-05,
      "loss": 0.5997,
      "step": 6551
    },
    {
      "epoch": 0.2012717721868952,
      "grad_norm": 0.33028489351272583,
      "learning_rate": 1.951794514174398e-05,
      "loss": 0.5798,
      "step": 6552
    },
    {
      "epoch": 0.20130249132184438,
      "grad_norm": 0.3379921019077301,
      "learning_rate": 1.951779689189157e-05,
      "loss": 0.6205,
      "step": 6553
    },
    {
      "epoch": 0.20133321045679353,
      "grad_norm": 0.5564730763435364,
      "learning_rate": 1.9517648619809673e-05,
      "loss": 0.5276,
      "step": 6554
    },
    {
      "epoch": 0.2013639295917427,
      "grad_norm": 0.3519015908241272,
      "learning_rate": 1.951750032549865e-05,
      "loss": 0.5724,
      "step": 6555
    },
    {
      "epoch": 0.20139464872669186,
      "grad_norm": 0.38281768560409546,
      "learning_rate": 1.9517352008958836e-05,
      "loss": 0.5122,
      "step": 6556
    },
    {
      "epoch": 0.201425367861641,
      "grad_norm": 0.33385083079338074,
      "learning_rate": 1.9517203670190582e-05,
      "loss": 0.5824,
      "step": 6557
    },
    {
      "epoch": 0.20145608699659018,
      "grad_norm": 0.4947761595249176,
      "learning_rate": 1.9517055309194236e-05,
      "loss": 0.6711,
      "step": 6558
    },
    {
      "epoch": 0.20148680613153933,
      "grad_norm": 0.341400146484375,
      "learning_rate": 1.9516906925970142e-05,
      "loss": 0.6294,
      "step": 6559
    },
    {
      "epoch": 0.2015175252664885,
      "grad_norm": 0.42718857526779175,
      "learning_rate": 1.951675852051865e-05,
      "loss": 0.6557,
      "step": 6560
    },
    {
      "epoch": 0.20154824440143765,
      "grad_norm": 0.307817667722702,
      "learning_rate": 1.9516610092840103e-05,
      "loss": 0.5752,
      "step": 6561
    },
    {
      "epoch": 0.20157896353638682,
      "grad_norm": 0.328447163105011,
      "learning_rate": 1.9516461642934845e-05,
      "loss": 0.5781,
      "step": 6562
    },
    {
      "epoch": 0.20160968267133597,
      "grad_norm": 0.29990145564079285,
      "learning_rate": 1.951631317080323e-05,
      "loss": 0.5708,
      "step": 6563
    },
    {
      "epoch": 0.20164040180628515,
      "grad_norm": 0.34242022037506104,
      "learning_rate": 1.9516164676445597e-05,
      "loss": 0.5446,
      "step": 6564
    },
    {
      "epoch": 0.2016711209412343,
      "grad_norm": 0.3540363013744354,
      "learning_rate": 1.9516016159862298e-05,
      "loss": 0.6032,
      "step": 6565
    },
    {
      "epoch": 0.20170184007618344,
      "grad_norm": 0.33882150053977966,
      "learning_rate": 1.951586762105368e-05,
      "loss": 0.6284,
      "step": 6566
    },
    {
      "epoch": 0.20173255921113262,
      "grad_norm": 0.49800148606300354,
      "learning_rate": 1.951571906002009e-05,
      "loss": 0.5379,
      "step": 6567
    },
    {
      "epoch": 0.20176327834608176,
      "grad_norm": 0.3575042188167572,
      "learning_rate": 1.951557047676187e-05,
      "loss": 0.606,
      "step": 6568
    },
    {
      "epoch": 0.20179399748103094,
      "grad_norm": 0.32699647545814514,
      "learning_rate": 1.951542187127937e-05,
      "loss": 0.5326,
      "step": 6569
    },
    {
      "epoch": 0.2018247166159801,
      "grad_norm": 0.32276055216789246,
      "learning_rate": 1.9515273243572942e-05,
      "loss": 0.5517,
      "step": 6570
    },
    {
      "epoch": 0.20185543575092926,
      "grad_norm": 0.3375779092311859,
      "learning_rate": 1.9515124593642927e-05,
      "loss": 0.6021,
      "step": 6571
    },
    {
      "epoch": 0.2018861548858784,
      "grad_norm": 0.35713785886764526,
      "learning_rate": 1.9514975921489675e-05,
      "loss": 0.526,
      "step": 6572
    },
    {
      "epoch": 0.20191687402082759,
      "grad_norm": 0.32916179299354553,
      "learning_rate": 1.951482722711353e-05,
      "loss": 0.5266,
      "step": 6573
    },
    {
      "epoch": 0.20194759315577673,
      "grad_norm": 0.3126731514930725,
      "learning_rate": 1.9514678510514843e-05,
      "loss": 0.484,
      "step": 6574
    },
    {
      "epoch": 0.20197831229072588,
      "grad_norm": 0.4116491675376892,
      "learning_rate": 1.951452977169396e-05,
      "loss": 0.6451,
      "step": 6575
    },
    {
      "epoch": 0.20200903142567506,
      "grad_norm": 0.3394833207130432,
      "learning_rate": 1.9514381010651228e-05,
      "loss": 0.5863,
      "step": 6576
    },
    {
      "epoch": 0.2020397505606242,
      "grad_norm": 0.37388962507247925,
      "learning_rate": 1.9514232227386992e-05,
      "loss": 0.498,
      "step": 6577
    },
    {
      "epoch": 0.20207046969557338,
      "grad_norm": 0.33847320079803467,
      "learning_rate": 1.9514083421901606e-05,
      "loss": 0.5785,
      "step": 6578
    },
    {
      "epoch": 0.20210118883052253,
      "grad_norm": 0.3102242350578308,
      "learning_rate": 1.951393459419541e-05,
      "loss": 0.5755,
      "step": 6579
    },
    {
      "epoch": 0.2021319079654717,
      "grad_norm": 0.3905925750732422,
      "learning_rate": 1.9513785744268757e-05,
      "loss": 0.4821,
      "step": 6580
    },
    {
      "epoch": 0.20216262710042085,
      "grad_norm": 0.3499460518360138,
      "learning_rate": 1.9513636872121996e-05,
      "loss": 0.5091,
      "step": 6581
    },
    {
      "epoch": 0.20219334623537003,
      "grad_norm": 0.3212675452232361,
      "learning_rate": 1.9513487977755467e-05,
      "loss": 0.5528,
      "step": 6582
    },
    {
      "epoch": 0.20222406537031917,
      "grad_norm": 0.33409202098846436,
      "learning_rate": 1.9513339061169526e-05,
      "loss": 0.6892,
      "step": 6583
    },
    {
      "epoch": 0.20225478450526832,
      "grad_norm": 0.33074238896369934,
      "learning_rate": 1.9513190122364515e-05,
      "loss": 0.4905,
      "step": 6584
    },
    {
      "epoch": 0.2022855036402175,
      "grad_norm": 0.3438633680343628,
      "learning_rate": 1.9513041161340786e-05,
      "loss": 0.5986,
      "step": 6585
    },
    {
      "epoch": 0.20231622277516664,
      "grad_norm": 0.29840245842933655,
      "learning_rate": 1.951289217809868e-05,
      "loss": 0.5467,
      "step": 6586
    },
    {
      "epoch": 0.20234694191011582,
      "grad_norm": 0.3647548258304596,
      "learning_rate": 1.9512743172638557e-05,
      "loss": 0.5311,
      "step": 6587
    },
    {
      "epoch": 0.20237766104506497,
      "grad_norm": 0.3430781364440918,
      "learning_rate": 1.951259414496075e-05,
      "loss": 0.638,
      "step": 6588
    },
    {
      "epoch": 0.20240838018001414,
      "grad_norm": 0.3473239839076996,
      "learning_rate": 1.951244509506562e-05,
      "loss": 0.5819,
      "step": 6589
    },
    {
      "epoch": 0.2024390993149633,
      "grad_norm": 0.3721223473548889,
      "learning_rate": 1.951229602295351e-05,
      "loss": 0.6251,
      "step": 6590
    },
    {
      "epoch": 0.20246981844991246,
      "grad_norm": 0.3801223039627075,
      "learning_rate": 1.951214692862477e-05,
      "loss": 0.6804,
      "step": 6591
    },
    {
      "epoch": 0.2025005375848616,
      "grad_norm": 0.3340519964694977,
      "learning_rate": 1.9511997812079744e-05,
      "loss": 0.5758,
      "step": 6592
    },
    {
      "epoch": 0.20253125671981076,
      "grad_norm": 0.3462814688682556,
      "learning_rate": 1.9511848673318785e-05,
      "loss": 0.5186,
      "step": 6593
    },
    {
      "epoch": 0.20256197585475993,
      "grad_norm": 0.32819464802742004,
      "learning_rate": 1.9511699512342236e-05,
      "loss": 0.6257,
      "step": 6594
    },
    {
      "epoch": 0.20259269498970908,
      "grad_norm": 0.36146801710128784,
      "learning_rate": 1.9511550329150452e-05,
      "loss": 0.6132,
      "step": 6595
    },
    {
      "epoch": 0.20262341412465826,
      "grad_norm": 0.34507298469543457,
      "learning_rate": 1.9511401123743775e-05,
      "loss": 0.5839,
      "step": 6596
    },
    {
      "epoch": 0.2026541332596074,
      "grad_norm": 0.3447723388671875,
      "learning_rate": 1.9511251896122555e-05,
      "loss": 0.6621,
      "step": 6597
    },
    {
      "epoch": 0.20268485239455658,
      "grad_norm": 0.3409908711910248,
      "learning_rate": 1.9511102646287144e-05,
      "loss": 0.6518,
      "step": 6598
    },
    {
      "epoch": 0.20271557152950573,
      "grad_norm": 0.34025144577026367,
      "learning_rate": 1.951095337423789e-05,
      "loss": 0.5333,
      "step": 6599
    },
    {
      "epoch": 0.20274629066445488,
      "grad_norm": 0.6077988147735596,
      "learning_rate": 1.9510804079975137e-05,
      "loss": 0.5311,
      "step": 6600
    },
    {
      "epoch": 0.20277700979940405,
      "grad_norm": 0.4779179096221924,
      "learning_rate": 1.9510654763499243e-05,
      "loss": 0.5392,
      "step": 6601
    },
    {
      "epoch": 0.2028077289343532,
      "grad_norm": 0.3389855921268463,
      "learning_rate": 1.9510505424810543e-05,
      "loss": 0.5694,
      "step": 6602
    },
    {
      "epoch": 0.20283844806930237,
      "grad_norm": 0.34442436695098877,
      "learning_rate": 1.95103560639094e-05,
      "loss": 0.6686,
      "step": 6603
    },
    {
      "epoch": 0.20286916720425152,
      "grad_norm": 0.36375540494918823,
      "learning_rate": 1.951020668079615e-05,
      "loss": 0.5489,
      "step": 6604
    },
    {
      "epoch": 0.2028998863392007,
      "grad_norm": 0.3026214838027954,
      "learning_rate": 1.951005727547115e-05,
      "loss": 0.5585,
      "step": 6605
    },
    {
      "epoch": 0.20293060547414984,
      "grad_norm": 0.360333651304245,
      "learning_rate": 1.9509907847934753e-05,
      "loss": 0.6205,
      "step": 6606
    },
    {
      "epoch": 0.20296132460909902,
      "grad_norm": 0.35661768913269043,
      "learning_rate": 1.9509758398187294e-05,
      "loss": 0.6256,
      "step": 6607
    },
    {
      "epoch": 0.20299204374404817,
      "grad_norm": 0.36203309893608093,
      "learning_rate": 1.9509608926229134e-05,
      "loss": 0.5413,
      "step": 6608
    },
    {
      "epoch": 0.20302276287899731,
      "grad_norm": 0.3284439742565155,
      "learning_rate": 1.9509459432060618e-05,
      "loss": 0.5359,
      "step": 6609
    },
    {
      "epoch": 0.2030534820139465,
      "grad_norm": 0.3345634937286377,
      "learning_rate": 1.9509309915682096e-05,
      "loss": 0.5685,
      "step": 6610
    },
    {
      "epoch": 0.20308420114889564,
      "grad_norm": 0.35636061429977417,
      "learning_rate": 1.9509160377093915e-05,
      "loss": 0.6086,
      "step": 6611
    },
    {
      "epoch": 0.2031149202838448,
      "grad_norm": 0.35787469148635864,
      "learning_rate": 1.950901081629643e-05,
      "loss": 0.5346,
      "step": 6612
    },
    {
      "epoch": 0.20314563941879396,
      "grad_norm": 0.3651569187641144,
      "learning_rate": 1.950886123328998e-05,
      "loss": 0.6436,
      "step": 6613
    },
    {
      "epoch": 0.20317635855374314,
      "grad_norm": 0.3492932915687561,
      "learning_rate": 1.9508711628074922e-05,
      "loss": 0.5594,
      "step": 6614
    },
    {
      "epoch": 0.20320707768869228,
      "grad_norm": 0.6106798648834229,
      "learning_rate": 1.9508562000651606e-05,
      "loss": 0.6266,
      "step": 6615
    },
    {
      "epoch": 0.20323779682364146,
      "grad_norm": 0.3525736331939697,
      "learning_rate": 1.9508412351020374e-05,
      "loss": 0.5914,
      "step": 6616
    },
    {
      "epoch": 0.2032685159585906,
      "grad_norm": 0.3383195102214813,
      "learning_rate": 1.9508262679181585e-05,
      "loss": 0.5512,
      "step": 6617
    },
    {
      "epoch": 0.20329923509353975,
      "grad_norm": 0.5529532432556152,
      "learning_rate": 1.9508112985135588e-05,
      "loss": 0.6105,
      "step": 6618
    },
    {
      "epoch": 0.20332995422848893,
      "grad_norm": 0.33137595653533936,
      "learning_rate": 1.9507963268882727e-05,
      "loss": 0.6788,
      "step": 6619
    },
    {
      "epoch": 0.20336067336343808,
      "grad_norm": 0.43586328625679016,
      "learning_rate": 1.950781353042335e-05,
      "loss": 0.5824,
      "step": 6620
    },
    {
      "epoch": 0.20339139249838725,
      "grad_norm": 0.4539675712585449,
      "learning_rate": 1.950766376975781e-05,
      "loss": 0.6391,
      "step": 6621
    },
    {
      "epoch": 0.2034221116333364,
      "grad_norm": 0.33548209071159363,
      "learning_rate": 1.950751398688646e-05,
      "loss": 0.5677,
      "step": 6622
    },
    {
      "epoch": 0.20345283076828558,
      "grad_norm": 0.32829052209854126,
      "learning_rate": 1.9507364181809653e-05,
      "loss": 0.6013,
      "step": 6623
    },
    {
      "epoch": 0.20348354990323472,
      "grad_norm": 0.32593879103660583,
      "learning_rate": 1.9507214354527724e-05,
      "loss": 0.584,
      "step": 6624
    },
    {
      "epoch": 0.2035142690381839,
      "grad_norm": 0.31636694073677063,
      "learning_rate": 1.9507064505041036e-05,
      "loss": 0.5987,
      "step": 6625
    },
    {
      "epoch": 0.20354498817313305,
      "grad_norm": 0.3085525929927826,
      "learning_rate": 1.9506914633349933e-05,
      "loss": 0.5357,
      "step": 6626
    },
    {
      "epoch": 0.2035757073080822,
      "grad_norm": 0.3349277079105377,
      "learning_rate": 1.9506764739454768e-05,
      "loss": 0.5676,
      "step": 6627
    },
    {
      "epoch": 0.20360642644303137,
      "grad_norm": 0.3635837435722351,
      "learning_rate": 1.9506614823355892e-05,
      "loss": 0.6065,
      "step": 6628
    },
    {
      "epoch": 0.20363714557798052,
      "grad_norm": 0.3902001678943634,
      "learning_rate": 1.950646488505365e-05,
      "loss": 0.6437,
      "step": 6629
    },
    {
      "epoch": 0.2036678647129297,
      "grad_norm": 0.32659780979156494,
      "learning_rate": 1.9506314924548396e-05,
      "loss": 0.5532,
      "step": 6630
    },
    {
      "epoch": 0.20369858384787884,
      "grad_norm": 0.3552607297897339,
      "learning_rate": 1.950616494184048e-05,
      "loss": 0.5745,
      "step": 6631
    },
    {
      "epoch": 0.20372930298282801,
      "grad_norm": 0.3416440784931183,
      "learning_rate": 1.9506014936930252e-05,
      "loss": 0.525,
      "step": 6632
    },
    {
      "epoch": 0.20376002211777716,
      "grad_norm": 0.36332592368125916,
      "learning_rate": 1.9505864909818062e-05,
      "loss": 0.6524,
      "step": 6633
    },
    {
      "epoch": 0.2037907412527263,
      "grad_norm": 0.4168027937412262,
      "learning_rate": 1.9505714860504258e-05,
      "loss": 0.5858,
      "step": 6634
    },
    {
      "epoch": 0.20382146038767548,
      "grad_norm": 0.3072514832019806,
      "learning_rate": 1.9505564788989198e-05,
      "loss": 0.5645,
      "step": 6635
    },
    {
      "epoch": 0.20385217952262463,
      "grad_norm": 0.3746810257434845,
      "learning_rate": 1.9505414695273225e-05,
      "loss": 0.5339,
      "step": 6636
    },
    {
      "epoch": 0.2038828986575738,
      "grad_norm": 0.78830885887146,
      "learning_rate": 1.9505264579356695e-05,
      "loss": 0.6362,
      "step": 6637
    },
    {
      "epoch": 0.20391361779252296,
      "grad_norm": 0.3537925183773041,
      "learning_rate": 1.9505114441239953e-05,
      "loss": 0.5514,
      "step": 6638
    },
    {
      "epoch": 0.20394433692747213,
      "grad_norm": 0.32247769832611084,
      "learning_rate": 1.950496428092335e-05,
      "loss": 0.5818,
      "step": 6639
    },
    {
      "epoch": 0.20397505606242128,
      "grad_norm": 0.3861912190914154,
      "learning_rate": 1.9504814098407243e-05,
      "loss": 0.585,
      "step": 6640
    },
    {
      "epoch": 0.20400577519737045,
      "grad_norm": 0.37115198373794556,
      "learning_rate": 1.9504663893691976e-05,
      "loss": 0.5404,
      "step": 6641
    },
    {
      "epoch": 0.2040364943323196,
      "grad_norm": 0.3092114329338074,
      "learning_rate": 1.9504513666777904e-05,
      "loss": 0.6405,
      "step": 6642
    },
    {
      "epoch": 0.20406721346726875,
      "grad_norm": 0.3151083290576935,
      "learning_rate": 1.9504363417665378e-05,
      "loss": 0.614,
      "step": 6643
    },
    {
      "epoch": 0.20409793260221792,
      "grad_norm": 0.3517356812953949,
      "learning_rate": 1.9504213146354748e-05,
      "loss": 0.657,
      "step": 6644
    },
    {
      "epoch": 0.20412865173716707,
      "grad_norm": 0.34967732429504395,
      "learning_rate": 1.9504062852846363e-05,
      "loss": 0.5926,
      "step": 6645
    },
    {
      "epoch": 0.20415937087211625,
      "grad_norm": 0.3604682683944702,
      "learning_rate": 1.950391253714057e-05,
      "loss": 0.5631,
      "step": 6646
    },
    {
      "epoch": 0.2041900900070654,
      "grad_norm": 1.7231206893920898,
      "learning_rate": 1.9503762199237735e-05,
      "loss": 0.5797,
      "step": 6647
    },
    {
      "epoch": 0.20422080914201457,
      "grad_norm": 0.3516538143157959,
      "learning_rate": 1.9503611839138194e-05,
      "loss": 0.6041,
      "step": 6648
    },
    {
      "epoch": 0.20425152827696372,
      "grad_norm": 0.37410831451416016,
      "learning_rate": 1.9503461456842304e-05,
      "loss": 0.5154,
      "step": 6649
    },
    {
      "epoch": 0.2042822474119129,
      "grad_norm": 0.3604680001735687,
      "learning_rate": 1.9503311052350417e-05,
      "loss": 0.6308,
      "step": 6650
    },
    {
      "epoch": 0.20431296654686204,
      "grad_norm": 0.3361424207687378,
      "learning_rate": 1.9503160625662886e-05,
      "loss": 0.6071,
      "step": 6651
    },
    {
      "epoch": 0.2043436856818112,
      "grad_norm": 0.41705843806266785,
      "learning_rate": 1.9503010176780055e-05,
      "loss": 0.672,
      "step": 6652
    },
    {
      "epoch": 0.20437440481676036,
      "grad_norm": 0.3414507806301117,
      "learning_rate": 1.9502859705702285e-05,
      "loss": 0.623,
      "step": 6653
    },
    {
      "epoch": 0.2044051239517095,
      "grad_norm": 0.34335505962371826,
      "learning_rate": 1.9502709212429917e-05,
      "loss": 0.608,
      "step": 6654
    },
    {
      "epoch": 0.2044358430866587,
      "grad_norm": 0.2996540367603302,
      "learning_rate": 1.950255869696331e-05,
      "loss": 0.5344,
      "step": 6655
    },
    {
      "epoch": 0.20446656222160783,
      "grad_norm": 0.3551822006702423,
      "learning_rate": 1.9502408159302818e-05,
      "loss": 0.5313,
      "step": 6656
    },
    {
      "epoch": 0.204497281356557,
      "grad_norm": 0.37401479482650757,
      "learning_rate": 1.950225759944878e-05,
      "loss": 0.6485,
      "step": 6657
    },
    {
      "epoch": 0.20452800049150616,
      "grad_norm": 0.354064404964447,
      "learning_rate": 1.950210701740156e-05,
      "loss": 0.6792,
      "step": 6658
    },
    {
      "epoch": 0.20455871962645533,
      "grad_norm": 0.4036164879798889,
      "learning_rate": 1.9501956413161506e-05,
      "loss": 0.634,
      "step": 6659
    },
    {
      "epoch": 0.20458943876140448,
      "grad_norm": 0.3556685745716095,
      "learning_rate": 1.950180578672897e-05,
      "loss": 0.5781,
      "step": 6660
    },
    {
      "epoch": 0.20462015789635363,
      "grad_norm": 0.3513967990875244,
      "learning_rate": 1.95016551381043e-05,
      "loss": 0.5582,
      "step": 6661
    },
    {
      "epoch": 0.2046508770313028,
      "grad_norm": 0.3364560306072235,
      "learning_rate": 1.9501504467287854e-05,
      "loss": 0.629,
      "step": 6662
    },
    {
      "epoch": 0.20468159616625195,
      "grad_norm": 0.3356948494911194,
      "learning_rate": 1.9501353774279977e-05,
      "loss": 0.5625,
      "step": 6663
    },
    {
      "epoch": 0.20471231530120113,
      "grad_norm": 0.3466673195362091,
      "learning_rate": 1.950120305908103e-05,
      "loss": 0.6096,
      "step": 6664
    },
    {
      "epoch": 0.20474303443615027,
      "grad_norm": 0.3192053437232971,
      "learning_rate": 1.9501052321691357e-05,
      "loss": 0.6211,
      "step": 6665
    },
    {
      "epoch": 0.20477375357109945,
      "grad_norm": 0.3372943699359894,
      "learning_rate": 1.9500901562111312e-05,
      "loss": 0.5525,
      "step": 6666
    },
    {
      "epoch": 0.2048044727060486,
      "grad_norm": 0.3789060115814209,
      "learning_rate": 1.9500750780341247e-05,
      "loss": 0.5996,
      "step": 6667
    },
    {
      "epoch": 0.20483519184099777,
      "grad_norm": 0.32060423493385315,
      "learning_rate": 1.9500599976381517e-05,
      "loss": 0.5865,
      "step": 6668
    },
    {
      "epoch": 0.20486591097594692,
      "grad_norm": 0.37170183658599854,
      "learning_rate": 1.9500449150232472e-05,
      "loss": 0.6511,
      "step": 6669
    },
    {
      "epoch": 0.20489663011089607,
      "grad_norm": 0.3629882335662842,
      "learning_rate": 1.9500298301894463e-05,
      "loss": 0.5579,
      "step": 6670
    },
    {
      "epoch": 0.20492734924584524,
      "grad_norm": 0.35207095742225647,
      "learning_rate": 1.9500147431367847e-05,
      "loss": 0.5543,
      "step": 6671
    },
    {
      "epoch": 0.2049580683807944,
      "grad_norm": 0.31447380781173706,
      "learning_rate": 1.9499996538652966e-05,
      "loss": 0.5636,
      "step": 6672
    },
    {
      "epoch": 0.20498878751574356,
      "grad_norm": 0.3467654585838318,
      "learning_rate": 1.949984562375019e-05,
      "loss": 0.5454,
      "step": 6673
    },
    {
      "epoch": 0.2050195066506927,
      "grad_norm": 0.3276960849761963,
      "learning_rate": 1.9499694686659855e-05,
      "loss": 0.6612,
      "step": 6674
    },
    {
      "epoch": 0.2050502257856419,
      "grad_norm": 0.421615868806839,
      "learning_rate": 1.949954372738232e-05,
      "loss": 0.5989,
      "step": 6675
    },
    {
      "epoch": 0.20508094492059104,
      "grad_norm": 0.33358386158943176,
      "learning_rate": 1.9499392745917935e-05,
      "loss": 0.4902,
      "step": 6676
    },
    {
      "epoch": 0.20511166405554018,
      "grad_norm": 0.3267568051815033,
      "learning_rate": 1.9499241742267057e-05,
      "loss": 0.5212,
      "step": 6677
    },
    {
      "epoch": 0.20514238319048936,
      "grad_norm": 0.3408997654914856,
      "learning_rate": 1.949909071643004e-05,
      "loss": 0.6018,
      "step": 6678
    },
    {
      "epoch": 0.2051731023254385,
      "grad_norm": 0.3418179452419281,
      "learning_rate": 1.9498939668407228e-05,
      "loss": 0.6623,
      "step": 6679
    },
    {
      "epoch": 0.20520382146038768,
      "grad_norm": 0.34425777196884155,
      "learning_rate": 1.949878859819898e-05,
      "loss": 0.5995,
      "step": 6680
    },
    {
      "epoch": 0.20523454059533683,
      "grad_norm": 0.35966745018959045,
      "learning_rate": 1.949863750580565e-05,
      "loss": 0.5284,
      "step": 6681
    },
    {
      "epoch": 0.205265259730286,
      "grad_norm": 0.37085482478141785,
      "learning_rate": 1.9498486391227586e-05,
      "loss": 0.6566,
      "step": 6682
    },
    {
      "epoch": 0.20529597886523515,
      "grad_norm": 0.3512696623802185,
      "learning_rate": 1.949833525446515e-05,
      "loss": 0.6425,
      "step": 6683
    },
    {
      "epoch": 0.20532669800018433,
      "grad_norm": 0.3685568571090698,
      "learning_rate": 1.949818409551868e-05,
      "loss": 0.5535,
      "step": 6684
    },
    {
      "epoch": 0.20535741713513347,
      "grad_norm": 0.4878056049346924,
      "learning_rate": 1.9498032914388543e-05,
      "loss": 0.6469,
      "step": 6685
    },
    {
      "epoch": 0.20538813627008262,
      "grad_norm": 0.333373486995697,
      "learning_rate": 1.9497881711075086e-05,
      "loss": 0.5711,
      "step": 6686
    },
    {
      "epoch": 0.2054188554050318,
      "grad_norm": 0.3257802128791809,
      "learning_rate": 1.9497730485578662e-05,
      "loss": 0.6063,
      "step": 6687
    },
    {
      "epoch": 0.20544957453998094,
      "grad_norm": 0.33832573890686035,
      "learning_rate": 1.9497579237899625e-05,
      "loss": 0.6447,
      "step": 6688
    },
    {
      "epoch": 0.20548029367493012,
      "grad_norm": 0.3269714117050171,
      "learning_rate": 1.949742796803833e-05,
      "loss": 0.5458,
      "step": 6689
    },
    {
      "epoch": 0.20551101280987927,
      "grad_norm": 0.4572744071483612,
      "learning_rate": 1.9497276675995126e-05,
      "loss": 0.6623,
      "step": 6690
    },
    {
      "epoch": 0.20554173194482844,
      "grad_norm": 0.3461678922176361,
      "learning_rate": 1.949712536177037e-05,
      "loss": 0.6177,
      "step": 6691
    },
    {
      "epoch": 0.2055724510797776,
      "grad_norm": 0.365709125995636,
      "learning_rate": 1.9496974025364417e-05,
      "loss": 0.5919,
      "step": 6692
    },
    {
      "epoch": 0.20560317021472677,
      "grad_norm": 0.3600093424320221,
      "learning_rate": 1.9496822666777614e-05,
      "loss": 0.598,
      "step": 6693
    },
    {
      "epoch": 0.2056338893496759,
      "grad_norm": 0.3331211805343628,
      "learning_rate": 1.949667128601032e-05,
      "loss": 0.5732,
      "step": 6694
    },
    {
      "epoch": 0.20566460848462506,
      "grad_norm": 0.3261450529098511,
      "learning_rate": 1.9496519883062887e-05,
      "loss": 0.5509,
      "step": 6695
    },
    {
      "epoch": 0.20569532761957424,
      "grad_norm": 0.3141263425350189,
      "learning_rate": 1.9496368457935672e-05,
      "loss": 0.5989,
      "step": 6696
    },
    {
      "epoch": 0.20572604675452338,
      "grad_norm": 0.3514042794704437,
      "learning_rate": 1.949621701062902e-05,
      "loss": 0.5906,
      "step": 6697
    },
    {
      "epoch": 0.20575676588947256,
      "grad_norm": 0.34993547201156616,
      "learning_rate": 1.9496065541143294e-05,
      "loss": 0.57,
      "step": 6698
    },
    {
      "epoch": 0.2057874850244217,
      "grad_norm": 0.32500821352005005,
      "learning_rate": 1.9495914049478843e-05,
      "loss": 0.5551,
      "step": 6699
    },
    {
      "epoch": 0.20581820415937088,
      "grad_norm": 0.44382303953170776,
      "learning_rate": 1.949576253563602e-05,
      "loss": 0.5861,
      "step": 6700
    },
    {
      "epoch": 0.20584892329432003,
      "grad_norm": 0.33887532353401184,
      "learning_rate": 1.949561099961518e-05,
      "loss": 0.5753,
      "step": 6701
    },
    {
      "epoch": 0.2058796424292692,
      "grad_norm": 0.3592597246170044,
      "learning_rate": 1.9495459441416676e-05,
      "loss": 0.5994,
      "step": 6702
    },
    {
      "epoch": 0.20591036156421835,
      "grad_norm": 0.32306522130966187,
      "learning_rate": 1.9495307861040865e-05,
      "loss": 0.5242,
      "step": 6703
    },
    {
      "epoch": 0.2059410806991675,
      "grad_norm": 0.3629536032676697,
      "learning_rate": 1.94951562584881e-05,
      "loss": 0.6439,
      "step": 6704
    },
    {
      "epoch": 0.20597179983411668,
      "grad_norm": 0.9498761892318726,
      "learning_rate": 1.9495004633758738e-05,
      "loss": 0.5557,
      "step": 6705
    },
    {
      "epoch": 0.20600251896906582,
      "grad_norm": 0.3656226694583893,
      "learning_rate": 1.9494852986853124e-05,
      "loss": 0.6494,
      "step": 6706
    },
    {
      "epoch": 0.206033238104015,
      "grad_norm": 0.33172282576560974,
      "learning_rate": 1.949470131777162e-05,
      "loss": 0.4837,
      "step": 6707
    },
    {
      "epoch": 0.20606395723896415,
      "grad_norm": 0.5927642583847046,
      "learning_rate": 1.9494549626514576e-05,
      "loss": 0.598,
      "step": 6708
    },
    {
      "epoch": 0.20609467637391332,
      "grad_norm": 0.32943350076675415,
      "learning_rate": 1.949439791308235e-05,
      "loss": 0.5841,
      "step": 6709
    },
    {
      "epoch": 0.20612539550886247,
      "grad_norm": 0.3079349994659424,
      "learning_rate": 1.9494246177475296e-05,
      "loss": 0.4915,
      "step": 6710
    },
    {
      "epoch": 0.20615611464381162,
      "grad_norm": 0.33529531955718994,
      "learning_rate": 1.9494094419693767e-05,
      "loss": 0.5619,
      "step": 6711
    },
    {
      "epoch": 0.2061868337787608,
      "grad_norm": 0.34418290853500366,
      "learning_rate": 1.949394263973811e-05,
      "loss": 0.5565,
      "step": 6712
    },
    {
      "epoch": 0.20621755291370994,
      "grad_norm": 0.33632805943489075,
      "learning_rate": 1.94937908376087e-05,
      "loss": 0.5229,
      "step": 6713
    },
    {
      "epoch": 0.20624827204865911,
      "grad_norm": 0.3438440263271332,
      "learning_rate": 1.9493639013305867e-05,
      "loss": 0.6661,
      "step": 6714
    },
    {
      "epoch": 0.20627899118360826,
      "grad_norm": 0.314663827419281,
      "learning_rate": 1.949348716682998e-05,
      "loss": 0.5961,
      "step": 6715
    },
    {
      "epoch": 0.20630971031855744,
      "grad_norm": 0.3189111649990082,
      "learning_rate": 1.9493335298181396e-05,
      "loss": 0.529,
      "step": 6716
    },
    {
      "epoch": 0.20634042945350659,
      "grad_norm": 0.3500652313232422,
      "learning_rate": 1.9493183407360457e-05,
      "loss": 0.5742,
      "step": 6717
    },
    {
      "epoch": 0.20637114858845576,
      "grad_norm": 0.3489617109298706,
      "learning_rate": 1.949303149436753e-05,
      "loss": 0.6067,
      "step": 6718
    },
    {
      "epoch": 0.2064018677234049,
      "grad_norm": 0.3479386866092682,
      "learning_rate": 1.9492879559202963e-05,
      "loss": 0.6256,
      "step": 6719
    },
    {
      "epoch": 0.20643258685835406,
      "grad_norm": 0.33005088567733765,
      "learning_rate": 1.9492727601867115e-05,
      "loss": 0.5821,
      "step": 6720
    },
    {
      "epoch": 0.20646330599330323,
      "grad_norm": 0.2937559485435486,
      "learning_rate": 1.9492575622360337e-05,
      "loss": 0.5816,
      "step": 6721
    },
    {
      "epoch": 0.20649402512825238,
      "grad_norm": 0.3080694377422333,
      "learning_rate": 1.9492423620682985e-05,
      "loss": 0.5551,
      "step": 6722
    },
    {
      "epoch": 0.20652474426320155,
      "grad_norm": 0.455829918384552,
      "learning_rate": 1.9492271596835414e-05,
      "loss": 0.6135,
      "step": 6723
    },
    {
      "epoch": 0.2065554633981507,
      "grad_norm": 0.34799233078956604,
      "learning_rate": 1.949211955081798e-05,
      "loss": 0.5795,
      "step": 6724
    },
    {
      "epoch": 0.20658618253309988,
      "grad_norm": 0.35359013080596924,
      "learning_rate": 1.949196748263104e-05,
      "loss": 0.6636,
      "step": 6725
    },
    {
      "epoch": 0.20661690166804902,
      "grad_norm": 0.2990283668041229,
      "learning_rate": 1.9491815392274947e-05,
      "loss": 0.5921,
      "step": 6726
    },
    {
      "epoch": 0.2066476208029982,
      "grad_norm": 0.328865110874176,
      "learning_rate": 1.9491663279750057e-05,
      "loss": 0.6448,
      "step": 6727
    },
    {
      "epoch": 0.20667833993794735,
      "grad_norm": 0.3477078080177307,
      "learning_rate": 1.949151114505672e-05,
      "loss": 0.5982,
      "step": 6728
    },
    {
      "epoch": 0.2067090590728965,
      "grad_norm": 0.4893229007720947,
      "learning_rate": 1.94913589881953e-05,
      "loss": 0.5703,
      "step": 6729
    },
    {
      "epoch": 0.20673977820784567,
      "grad_norm": 0.33547571301460266,
      "learning_rate": 1.9491206809166147e-05,
      "loss": 0.5753,
      "step": 6730
    },
    {
      "epoch": 0.20677049734279482,
      "grad_norm": 0.40696045756340027,
      "learning_rate": 1.949105460796962e-05,
      "loss": 0.5449,
      "step": 6731
    },
    {
      "epoch": 0.206801216477744,
      "grad_norm": 0.3171321153640747,
      "learning_rate": 1.9490902384606066e-05,
      "loss": 0.5575,
      "step": 6732
    },
    {
      "epoch": 0.20683193561269314,
      "grad_norm": 0.3086630403995514,
      "learning_rate": 1.949075013907585e-05,
      "loss": 0.5874,
      "step": 6733
    },
    {
      "epoch": 0.20686265474764232,
      "grad_norm": 0.4153421223163605,
      "learning_rate": 1.9490597871379325e-05,
      "loss": 0.5058,
      "step": 6734
    },
    {
      "epoch": 0.20689337388259146,
      "grad_norm": 0.34306612610816956,
      "learning_rate": 1.9490445581516845e-05,
      "loss": 0.5239,
      "step": 6735
    },
    {
      "epoch": 0.20692409301754064,
      "grad_norm": 0.3167012631893158,
      "learning_rate": 1.949029326948877e-05,
      "loss": 0.628,
      "step": 6736
    },
    {
      "epoch": 0.2069548121524898,
      "grad_norm": 0.3090924918651581,
      "learning_rate": 1.949014093529545e-05,
      "loss": 0.6109,
      "step": 6737
    },
    {
      "epoch": 0.20698553128743893,
      "grad_norm": 0.3655340373516083,
      "learning_rate": 1.9489988578937236e-05,
      "loss": 0.5591,
      "step": 6738
    },
    {
      "epoch": 0.2070162504223881,
      "grad_norm": 0.3268328309059143,
      "learning_rate": 1.94898362004145e-05,
      "loss": 0.5176,
      "step": 6739
    },
    {
      "epoch": 0.20704696955733726,
      "grad_norm": 0.33985400199890137,
      "learning_rate": 1.9489683799727584e-05,
      "loss": 0.5664,
      "step": 6740
    },
    {
      "epoch": 0.20707768869228643,
      "grad_norm": 0.35410717129707336,
      "learning_rate": 1.9489531376876853e-05,
      "loss": 0.6021,
      "step": 6741
    },
    {
      "epoch": 0.20710840782723558,
      "grad_norm": 0.33364248275756836,
      "learning_rate": 1.9489378931862653e-05,
      "loss": 0.6565,
      "step": 6742
    },
    {
      "epoch": 0.20713912696218476,
      "grad_norm": 0.35372763872146606,
      "learning_rate": 1.9489226464685352e-05,
      "loss": 0.6165,
      "step": 6743
    },
    {
      "epoch": 0.2071698460971339,
      "grad_norm": 0.3580309748649597,
      "learning_rate": 1.9489073975345295e-05,
      "loss": 0.4611,
      "step": 6744
    },
    {
      "epoch": 0.20720056523208308,
      "grad_norm": 0.33830949664115906,
      "learning_rate": 1.9488921463842848e-05,
      "loss": 0.5947,
      "step": 6745
    },
    {
      "epoch": 0.20723128436703223,
      "grad_norm": 0.3285672068595886,
      "learning_rate": 1.9488768930178357e-05,
      "loss": 0.6037,
      "step": 6746
    },
    {
      "epoch": 0.20726200350198137,
      "grad_norm": 0.36356693506240845,
      "learning_rate": 1.9488616374352187e-05,
      "loss": 0.6071,
      "step": 6747
    },
    {
      "epoch": 0.20729272263693055,
      "grad_norm": 0.3461548089981079,
      "learning_rate": 1.948846379636469e-05,
      "loss": 0.6122,
      "step": 6748
    },
    {
      "epoch": 0.2073234417718797,
      "grad_norm": 0.35301148891448975,
      "learning_rate": 1.9488311196216224e-05,
      "loss": 0.657,
      "step": 6749
    },
    {
      "epoch": 0.20735416090682887,
      "grad_norm": 0.3461911678314209,
      "learning_rate": 1.9488158573907142e-05,
      "loss": 0.6252,
      "step": 6750
    },
    {
      "epoch": 0.20738488004177802,
      "grad_norm": 0.3336573839187622,
      "learning_rate": 1.9488005929437802e-05,
      "loss": 0.5627,
      "step": 6751
    },
    {
      "epoch": 0.2074155991767272,
      "grad_norm": 0.32154688239097595,
      "learning_rate": 1.9487853262808565e-05,
      "loss": 0.6428,
      "step": 6752
    },
    {
      "epoch": 0.20744631831167634,
      "grad_norm": 0.3433793783187866,
      "learning_rate": 1.9487700574019785e-05,
      "loss": 0.5338,
      "step": 6753
    },
    {
      "epoch": 0.2074770374466255,
      "grad_norm": 0.3497168719768524,
      "learning_rate": 1.9487547863071816e-05,
      "loss": 0.6273,
      "step": 6754
    },
    {
      "epoch": 0.20750775658157466,
      "grad_norm": 0.39206165075302124,
      "learning_rate": 1.948739512996501e-05,
      "loss": 0.6121,
      "step": 6755
    },
    {
      "epoch": 0.2075384757165238,
      "grad_norm": 0.34223899245262146,
      "learning_rate": 1.948724237469974e-05,
      "loss": 0.6694,
      "step": 6756
    },
    {
      "epoch": 0.207569194851473,
      "grad_norm": 0.3360214829444885,
      "learning_rate": 1.9487089597276347e-05,
      "loss": 0.5222,
      "step": 6757
    },
    {
      "epoch": 0.20759991398642214,
      "grad_norm": 0.32551413774490356,
      "learning_rate": 1.9486936797695196e-05,
      "loss": 0.5571,
      "step": 6758
    },
    {
      "epoch": 0.2076306331213713,
      "grad_norm": 0.31696659326553345,
      "learning_rate": 1.9486783975956642e-05,
      "loss": 0.5926,
      "step": 6759
    },
    {
      "epoch": 0.20766135225632046,
      "grad_norm": 0.3646683990955353,
      "learning_rate": 1.948663113206104e-05,
      "loss": 0.6432,
      "step": 6760
    },
    {
      "epoch": 0.20769207139126963,
      "grad_norm": 0.36895596981048584,
      "learning_rate": 1.948647826600875e-05,
      "loss": 0.5775,
      "step": 6761
    },
    {
      "epoch": 0.20772279052621878,
      "grad_norm": 0.32395535707473755,
      "learning_rate": 1.9486325377800125e-05,
      "loss": 0.6439,
      "step": 6762
    },
    {
      "epoch": 0.20775350966116793,
      "grad_norm": 0.32173487544059753,
      "learning_rate": 1.9486172467435525e-05,
      "loss": 0.5906,
      "step": 6763
    },
    {
      "epoch": 0.2077842287961171,
      "grad_norm": 0.3746422529220581,
      "learning_rate": 1.9486019534915307e-05,
      "loss": 0.651,
      "step": 6764
    },
    {
      "epoch": 0.20781494793106625,
      "grad_norm": 0.32395410537719727,
      "learning_rate": 1.9485866580239832e-05,
      "loss": 0.5481,
      "step": 6765
    },
    {
      "epoch": 0.20784566706601543,
      "grad_norm": 0.36253607273101807,
      "learning_rate": 1.9485713603409447e-05,
      "loss": 0.5655,
      "step": 6766
    },
    {
      "epoch": 0.20787638620096457,
      "grad_norm": 0.3335859775543213,
      "learning_rate": 1.948556060442452e-05,
      "loss": 0.4681,
      "step": 6767
    },
    {
      "epoch": 0.20790710533591375,
      "grad_norm": 0.3325766623020172,
      "learning_rate": 1.94854075832854e-05,
      "loss": 0.6084,
      "step": 6768
    },
    {
      "epoch": 0.2079378244708629,
      "grad_norm": 0.3553239703178406,
      "learning_rate": 1.948525453999245e-05,
      "loss": 0.4982,
      "step": 6769
    },
    {
      "epoch": 0.20796854360581207,
      "grad_norm": 0.36132708191871643,
      "learning_rate": 1.9485101474546028e-05,
      "loss": 0.5845,
      "step": 6770
    },
    {
      "epoch": 0.20799926274076122,
      "grad_norm": 0.3245886564254761,
      "learning_rate": 1.9484948386946485e-05,
      "loss": 0.5711,
      "step": 6771
    },
    {
      "epoch": 0.20802998187571037,
      "grad_norm": 0.3502661883831024,
      "learning_rate": 1.9484795277194185e-05,
      "loss": 0.6252,
      "step": 6772
    },
    {
      "epoch": 0.20806070101065954,
      "grad_norm": 0.3425042927265167,
      "learning_rate": 1.948464214528948e-05,
      "loss": 0.6092,
      "step": 6773
    },
    {
      "epoch": 0.2080914201456087,
      "grad_norm": 0.3363659381866455,
      "learning_rate": 1.9484488991232734e-05,
      "loss": 0.6569,
      "step": 6774
    },
    {
      "epoch": 0.20812213928055787,
      "grad_norm": 0.4108564555644989,
      "learning_rate": 1.9484335815024302e-05,
      "loss": 0.6118,
      "step": 6775
    },
    {
      "epoch": 0.208152858415507,
      "grad_norm": 0.3707883358001709,
      "learning_rate": 1.948418261666454e-05,
      "loss": 0.6176,
      "step": 6776
    },
    {
      "epoch": 0.2081835775504562,
      "grad_norm": 0.35873401165008545,
      "learning_rate": 1.9484029396153807e-05,
      "loss": 0.6354,
      "step": 6777
    },
    {
      "epoch": 0.20821429668540534,
      "grad_norm": 0.35628142952919006,
      "learning_rate": 1.9483876153492463e-05,
      "loss": 0.6387,
      "step": 6778
    },
    {
      "epoch": 0.2082450158203545,
      "grad_norm": 0.3002642095088959,
      "learning_rate": 1.948372288868086e-05,
      "loss": 0.5412,
      "step": 6779
    },
    {
      "epoch": 0.20827573495530366,
      "grad_norm": 0.35992079973220825,
      "learning_rate": 1.9483569601719364e-05,
      "loss": 0.6691,
      "step": 6780
    },
    {
      "epoch": 0.2083064540902528,
      "grad_norm": 0.33275890350341797,
      "learning_rate": 1.9483416292608325e-05,
      "loss": 0.621,
      "step": 6781
    },
    {
      "epoch": 0.20833717322520198,
      "grad_norm": 0.36708688735961914,
      "learning_rate": 1.9483262961348107e-05,
      "loss": 0.5959,
      "step": 6782
    },
    {
      "epoch": 0.20836789236015113,
      "grad_norm": 0.34460917115211487,
      "learning_rate": 1.9483109607939064e-05,
      "loss": 0.5578,
      "step": 6783
    },
    {
      "epoch": 0.2083986114951003,
      "grad_norm": 0.35045233368873596,
      "learning_rate": 1.9482956232381564e-05,
      "loss": 0.5472,
      "step": 6784
    },
    {
      "epoch": 0.20842933063004945,
      "grad_norm": 0.3484019935131073,
      "learning_rate": 1.9482802834675947e-05,
      "loss": 0.517,
      "step": 6785
    },
    {
      "epoch": 0.20846004976499863,
      "grad_norm": 0.32270124554634094,
      "learning_rate": 1.9482649414822588e-05,
      "loss": 0.6547,
      "step": 6786
    },
    {
      "epoch": 0.20849076889994778,
      "grad_norm": 0.3300982713699341,
      "learning_rate": 1.9482495972821838e-05,
      "loss": 0.6363,
      "step": 6787
    },
    {
      "epoch": 0.20852148803489692,
      "grad_norm": 0.36167359352111816,
      "learning_rate": 1.9482342508674056e-05,
      "loss": 0.6265,
      "step": 6788
    },
    {
      "epoch": 0.2085522071698461,
      "grad_norm": 0.6796222925186157,
      "learning_rate": 1.9482189022379598e-05,
      "loss": 0.6427,
      "step": 6789
    },
    {
      "epoch": 0.20858292630479525,
      "grad_norm": 0.35929855704307556,
      "learning_rate": 1.948203551393883e-05,
      "loss": 0.5661,
      "step": 6790
    },
    {
      "epoch": 0.20861364543974442,
      "grad_norm": 0.342508465051651,
      "learning_rate": 1.94818819833521e-05,
      "loss": 0.6576,
      "step": 6791
    },
    {
      "epoch": 0.20864436457469357,
      "grad_norm": 0.3828396499156952,
      "learning_rate": 1.948172843061978e-05,
      "loss": 0.6442,
      "step": 6792
    },
    {
      "epoch": 0.20867508370964274,
      "grad_norm": 0.30561819672584534,
      "learning_rate": 1.9481574855742217e-05,
      "loss": 0.4889,
      "step": 6793
    },
    {
      "epoch": 0.2087058028445919,
      "grad_norm": 0.31821557879447937,
      "learning_rate": 1.9481421258719773e-05,
      "loss": 0.5168,
      "step": 6794
    },
    {
      "epoch": 0.20873652197954107,
      "grad_norm": 0.35780394077301025,
      "learning_rate": 1.948126763955281e-05,
      "loss": 0.5778,
      "step": 6795
    },
    {
      "epoch": 0.20876724111449022,
      "grad_norm": 0.343059778213501,
      "learning_rate": 1.9481113998241682e-05,
      "loss": 0.5675,
      "step": 6796
    },
    {
      "epoch": 0.20879796024943936,
      "grad_norm": 0.36691999435424805,
      "learning_rate": 1.9480960334786753e-05,
      "loss": 0.6534,
      "step": 6797
    },
    {
      "epoch": 0.20882867938438854,
      "grad_norm": 0.33397820591926575,
      "learning_rate": 1.9480806649188377e-05,
      "loss": 0.6542,
      "step": 6798
    },
    {
      "epoch": 0.20885939851933769,
      "grad_norm": 0.3316566050052643,
      "learning_rate": 1.9480652941446912e-05,
      "loss": 0.5522,
      "step": 6799
    },
    {
      "epoch": 0.20889011765428686,
      "grad_norm": 0.3801775574684143,
      "learning_rate": 1.9480499211562723e-05,
      "loss": 0.6214,
      "step": 6800
    },
    {
      "epoch": 0.208920836789236,
      "grad_norm": 0.33417773246765137,
      "learning_rate": 1.9480345459536164e-05,
      "loss": 0.61,
      "step": 6801
    },
    {
      "epoch": 0.20895155592418518,
      "grad_norm": 0.3459598124027252,
      "learning_rate": 1.9480191685367598e-05,
      "loss": 0.5863,
      "step": 6802
    },
    {
      "epoch": 0.20898227505913433,
      "grad_norm": 0.33064717054367065,
      "learning_rate": 1.948003788905738e-05,
      "loss": 0.6296,
      "step": 6803
    },
    {
      "epoch": 0.2090129941940835,
      "grad_norm": 0.40053218603134155,
      "learning_rate": 1.9479884070605877e-05,
      "loss": 0.5637,
      "step": 6804
    },
    {
      "epoch": 0.20904371332903265,
      "grad_norm": 0.3567271828651428,
      "learning_rate": 1.9479730230013438e-05,
      "loss": 0.5237,
      "step": 6805
    },
    {
      "epoch": 0.2090744324639818,
      "grad_norm": 0.36614957451820374,
      "learning_rate": 1.9479576367280428e-05,
      "loss": 0.6784,
      "step": 6806
    },
    {
      "epoch": 0.20910515159893098,
      "grad_norm": 0.37432631850242615,
      "learning_rate": 1.9479422482407204e-05,
      "loss": 0.5682,
      "step": 6807
    },
    {
      "epoch": 0.20913587073388012,
      "grad_norm": 0.3388708233833313,
      "learning_rate": 1.947926857539413e-05,
      "loss": 0.5456,
      "step": 6808
    },
    {
      "epoch": 0.2091665898688293,
      "grad_norm": 0.3480341136455536,
      "learning_rate": 1.947911464624156e-05,
      "loss": 0.642,
      "step": 6809
    },
    {
      "epoch": 0.20919730900377845,
      "grad_norm": 0.3100312352180481,
      "learning_rate": 1.9478960694949857e-05,
      "loss": 0.5554,
      "step": 6810
    },
    {
      "epoch": 0.20922802813872762,
      "grad_norm": 0.3863712549209595,
      "learning_rate": 1.947880672151938e-05,
      "loss": 0.574,
      "step": 6811
    },
    {
      "epoch": 0.20925874727367677,
      "grad_norm": 0.3236182630062103,
      "learning_rate": 1.9478652725950484e-05,
      "loss": 0.6017,
      "step": 6812
    },
    {
      "epoch": 0.20928946640862595,
      "grad_norm": 0.3828861117362976,
      "learning_rate": 1.9478498708243534e-05,
      "loss": 0.5983,
      "step": 6813
    },
    {
      "epoch": 0.2093201855435751,
      "grad_norm": 0.304354190826416,
      "learning_rate": 1.947834466839889e-05,
      "loss": 0.5966,
      "step": 6814
    },
    {
      "epoch": 0.20935090467852424,
      "grad_norm": 0.37578994035720825,
      "learning_rate": 1.947819060641691e-05,
      "loss": 0.531,
      "step": 6815
    },
    {
      "epoch": 0.20938162381347342,
      "grad_norm": 0.33401918411254883,
      "learning_rate": 1.947803652229795e-05,
      "loss": 0.535,
      "step": 6816
    },
    {
      "epoch": 0.20941234294842256,
      "grad_norm": 0.34877946972846985,
      "learning_rate": 1.947788241604238e-05,
      "loss": 0.5208,
      "step": 6817
    },
    {
      "epoch": 0.20944306208337174,
      "grad_norm": 0.47943314909935,
      "learning_rate": 1.947772828765055e-05,
      "loss": 0.5951,
      "step": 6818
    },
    {
      "epoch": 0.2094737812183209,
      "grad_norm": 0.3514961898326874,
      "learning_rate": 1.9477574137122827e-05,
      "loss": 0.5694,
      "step": 6819
    },
    {
      "epoch": 0.20950450035327006,
      "grad_norm": 0.341605007648468,
      "learning_rate": 1.9477419964459564e-05,
      "loss": 0.5858,
      "step": 6820
    },
    {
      "epoch": 0.2095352194882192,
      "grad_norm": 0.32916802167892456,
      "learning_rate": 1.947726576966112e-05,
      "loss": 0.6015,
      "step": 6821
    },
    {
      "epoch": 0.20956593862316839,
      "grad_norm": 0.4181038439273834,
      "learning_rate": 1.947711155272787e-05,
      "loss": 0.5427,
      "step": 6822
    },
    {
      "epoch": 0.20959665775811753,
      "grad_norm": 0.3307131826877594,
      "learning_rate": 1.947695731366016e-05,
      "loss": 0.5673,
      "step": 6823
    },
    {
      "epoch": 0.20962737689306668,
      "grad_norm": 0.3298184275627136,
      "learning_rate": 1.9476803052458354e-05,
      "loss": 0.6506,
      "step": 6824
    },
    {
      "epoch": 0.20965809602801586,
      "grad_norm": 0.5908688306808472,
      "learning_rate": 1.9476648769122813e-05,
      "loss": 0.6687,
      "step": 6825
    },
    {
      "epoch": 0.209688815162965,
      "grad_norm": 0.40000155568122864,
      "learning_rate": 1.9476494463653895e-05,
      "loss": 0.6552,
      "step": 6826
    },
    {
      "epoch": 0.20971953429791418,
      "grad_norm": 0.3269423246383667,
      "learning_rate": 1.9476340136051965e-05,
      "loss": 0.6811,
      "step": 6827
    },
    {
      "epoch": 0.20975025343286333,
      "grad_norm": 0.3682125210762024,
      "learning_rate": 1.9476185786317382e-05,
      "loss": 0.5685,
      "step": 6828
    },
    {
      "epoch": 0.2097809725678125,
      "grad_norm": 0.3009730279445648,
      "learning_rate": 1.94760314144505e-05,
      "loss": 0.5235,
      "step": 6829
    },
    {
      "epoch": 0.20981169170276165,
      "grad_norm": 0.3236093521118164,
      "learning_rate": 1.9475877020451686e-05,
      "loss": 0.549,
      "step": 6830
    },
    {
      "epoch": 0.2098424108377108,
      "grad_norm": 0.3141080141067505,
      "learning_rate": 1.94757226043213e-05,
      "loss": 0.6041,
      "step": 6831
    },
    {
      "epoch": 0.20987312997265997,
      "grad_norm": 0.32735732197761536,
      "learning_rate": 1.9475568166059708e-05,
      "loss": 0.5844,
      "step": 6832
    },
    {
      "epoch": 0.20990384910760912,
      "grad_norm": 0.301844984292984,
      "learning_rate": 1.947541370566726e-05,
      "loss": 0.5797,
      "step": 6833
    },
    {
      "epoch": 0.2099345682425583,
      "grad_norm": 0.34587377309799194,
      "learning_rate": 1.9475259223144322e-05,
      "loss": 0.5753,
      "step": 6834
    },
    {
      "epoch": 0.20996528737750744,
      "grad_norm": 0.30843761563301086,
      "learning_rate": 1.9475104718491252e-05,
      "loss": 0.6491,
      "step": 6835
    },
    {
      "epoch": 0.20999600651245662,
      "grad_norm": 0.3184061348438263,
      "learning_rate": 1.9474950191708414e-05,
      "loss": 0.557,
      "step": 6836
    },
    {
      "epoch": 0.21002672564740577,
      "grad_norm": 0.3152425289154053,
      "learning_rate": 1.947479564279617e-05,
      "loss": 0.5766,
      "step": 6837
    },
    {
      "epoch": 0.21005744478235494,
      "grad_norm": 0.35139939188957214,
      "learning_rate": 1.9474641071754882e-05,
      "loss": 0.5715,
      "step": 6838
    },
    {
      "epoch": 0.2100881639173041,
      "grad_norm": 0.3102594017982483,
      "learning_rate": 1.94744864785849e-05,
      "loss": 0.4805,
      "step": 6839
    },
    {
      "epoch": 0.21011888305225324,
      "grad_norm": 0.36538225412368774,
      "learning_rate": 1.94743318632866e-05,
      "loss": 0.6501,
      "step": 6840
    },
    {
      "epoch": 0.2101496021872024,
      "grad_norm": 0.31919384002685547,
      "learning_rate": 1.9474177225860337e-05,
      "loss": 0.5879,
      "step": 6841
    },
    {
      "epoch": 0.21018032132215156,
      "grad_norm": 0.3606884181499481,
      "learning_rate": 1.9474022566306466e-05,
      "loss": 0.5623,
      "step": 6842
    },
    {
      "epoch": 0.21021104045710073,
      "grad_norm": 0.30678993463516235,
      "learning_rate": 1.9473867884625357e-05,
      "loss": 0.5764,
      "step": 6843
    },
    {
      "epoch": 0.21024175959204988,
      "grad_norm": 0.37434282898902893,
      "learning_rate": 1.9473713180817365e-05,
      "loss": 0.4925,
      "step": 6844
    },
    {
      "epoch": 0.21027247872699906,
      "grad_norm": 0.3545511066913605,
      "learning_rate": 1.9473558454882857e-05,
      "loss": 0.6795,
      "step": 6845
    },
    {
      "epoch": 0.2103031978619482,
      "grad_norm": 0.5128963589668274,
      "learning_rate": 1.9473403706822188e-05,
      "loss": 0.6035,
      "step": 6846
    },
    {
      "epoch": 0.21033391699689738,
      "grad_norm": 0.3279101252555847,
      "learning_rate": 1.9473248936635728e-05,
      "loss": 0.6013,
      "step": 6847
    },
    {
      "epoch": 0.21036463613184653,
      "grad_norm": 0.3404775857925415,
      "learning_rate": 1.9473094144323828e-05,
      "loss": 0.5915,
      "step": 6848
    },
    {
      "epoch": 0.21039535526679568,
      "grad_norm": 0.3517005443572998,
      "learning_rate": 1.9472939329886862e-05,
      "loss": 0.5668,
      "step": 6849
    },
    {
      "epoch": 0.21042607440174485,
      "grad_norm": 0.34140822291374207,
      "learning_rate": 1.9472784493325182e-05,
      "loss": 0.5614,
      "step": 6850
    },
    {
      "epoch": 0.210456793536694,
      "grad_norm": 0.37153002619743347,
      "learning_rate": 1.9472629634639148e-05,
      "loss": 0.6374,
      "step": 6851
    },
    {
      "epoch": 0.21048751267164317,
      "grad_norm": 0.38014742732048035,
      "learning_rate": 1.947247475382913e-05,
      "loss": 0.7005,
      "step": 6852
    },
    {
      "epoch": 0.21051823180659232,
      "grad_norm": 0.3855288326740265,
      "learning_rate": 1.9472319850895487e-05,
      "loss": 0.549,
      "step": 6853
    },
    {
      "epoch": 0.2105489509415415,
      "grad_norm": 0.3535619080066681,
      "learning_rate": 1.9472164925838576e-05,
      "loss": 0.5507,
      "step": 6854
    },
    {
      "epoch": 0.21057967007649064,
      "grad_norm": 0.3759792149066925,
      "learning_rate": 1.9472009978658764e-05,
      "loss": 0.6547,
      "step": 6855
    },
    {
      "epoch": 0.21061038921143982,
      "grad_norm": 0.3139233887195587,
      "learning_rate": 1.947185500935641e-05,
      "loss": 0.5621,
      "step": 6856
    },
    {
      "epoch": 0.21064110834638897,
      "grad_norm": 0.3505811393260956,
      "learning_rate": 1.947170001793188e-05,
      "loss": 0.6614,
      "step": 6857
    },
    {
      "epoch": 0.21067182748133811,
      "grad_norm": 0.321439266204834,
      "learning_rate": 1.9471545004385528e-05,
      "loss": 0.55,
      "step": 6858
    },
    {
      "epoch": 0.2107025466162873,
      "grad_norm": 0.3130649924278259,
      "learning_rate": 1.9471389968717725e-05,
      "loss": 0.5832,
      "step": 6859
    },
    {
      "epoch": 0.21073326575123644,
      "grad_norm": 0.3085334897041321,
      "learning_rate": 1.9471234910928827e-05,
      "loss": 0.556,
      "step": 6860
    },
    {
      "epoch": 0.2107639848861856,
      "grad_norm": 0.3236427903175354,
      "learning_rate": 1.94710798310192e-05,
      "loss": 0.6514,
      "step": 6861
    },
    {
      "epoch": 0.21079470402113476,
      "grad_norm": 0.3909730017185211,
      "learning_rate": 1.9470924728989205e-05,
      "loss": 0.5556,
      "step": 6862
    },
    {
      "epoch": 0.21082542315608394,
      "grad_norm": 0.3637202978134155,
      "learning_rate": 1.9470769604839202e-05,
      "loss": 0.5992,
      "step": 6863
    },
    {
      "epoch": 0.21085614229103308,
      "grad_norm": 0.3321051299571991,
      "learning_rate": 1.9470614458569558e-05,
      "loss": 0.5126,
      "step": 6864
    },
    {
      "epoch": 0.21088686142598223,
      "grad_norm": 0.3373319208621979,
      "learning_rate": 1.947045929018063e-05,
      "loss": 0.6416,
      "step": 6865
    },
    {
      "epoch": 0.2109175805609314,
      "grad_norm": 0.3937773108482361,
      "learning_rate": 1.9470304099672782e-05,
      "loss": 0.6015,
      "step": 6866
    },
    {
      "epoch": 0.21094829969588055,
      "grad_norm": 0.32138824462890625,
      "learning_rate": 1.947014888704638e-05,
      "loss": 0.536,
      "step": 6867
    },
    {
      "epoch": 0.21097901883082973,
      "grad_norm": 0.356560617685318,
      "learning_rate": 1.9469993652301783e-05,
      "loss": 0.5876,
      "step": 6868
    },
    {
      "epoch": 0.21100973796577888,
      "grad_norm": 0.3164021670818329,
      "learning_rate": 1.9469838395439353e-05,
      "loss": 0.5547,
      "step": 6869
    },
    {
      "epoch": 0.21104045710072805,
      "grad_norm": 0.3307015299797058,
      "learning_rate": 1.9469683116459456e-05,
      "loss": 0.6408,
      "step": 6870
    },
    {
      "epoch": 0.2110711762356772,
      "grad_norm": 0.35809844732284546,
      "learning_rate": 1.946952781536245e-05,
      "loss": 0.6241,
      "step": 6871
    },
    {
      "epoch": 0.21110189537062637,
      "grad_norm": 0.337424099445343,
      "learning_rate": 1.9469372492148704e-05,
      "loss": 0.5922,
      "step": 6872
    },
    {
      "epoch": 0.21113261450557552,
      "grad_norm": 0.3855310380458832,
      "learning_rate": 1.946921714681858e-05,
      "loss": 0.5714,
      "step": 6873
    },
    {
      "epoch": 0.21116333364052467,
      "grad_norm": 0.4581669569015503,
      "learning_rate": 1.9469061779372433e-05,
      "loss": 0.6413,
      "step": 6874
    },
    {
      "epoch": 0.21119405277547385,
      "grad_norm": 0.314171701669693,
      "learning_rate": 1.9468906389810633e-05,
      "loss": 0.5897,
      "step": 6875
    },
    {
      "epoch": 0.211224771910423,
      "grad_norm": 0.3317662477493286,
      "learning_rate": 1.9468750978133538e-05,
      "loss": 0.5819,
      "step": 6876
    },
    {
      "epoch": 0.21125549104537217,
      "grad_norm": 0.37145477533340454,
      "learning_rate": 1.9468595544341514e-05,
      "loss": 0.5652,
      "step": 6877
    },
    {
      "epoch": 0.21128621018032132,
      "grad_norm": 0.4229167103767395,
      "learning_rate": 1.9468440088434926e-05,
      "loss": 0.4991,
      "step": 6878
    },
    {
      "epoch": 0.2113169293152705,
      "grad_norm": 0.31672149896621704,
      "learning_rate": 1.9468284610414135e-05,
      "loss": 0.6318,
      "step": 6879
    },
    {
      "epoch": 0.21134764845021964,
      "grad_norm": 0.34982433915138245,
      "learning_rate": 1.9468129110279502e-05,
      "loss": 0.6155,
      "step": 6880
    },
    {
      "epoch": 0.2113783675851688,
      "grad_norm": 0.3493845462799072,
      "learning_rate": 1.9467973588031394e-05,
      "loss": 0.6421,
      "step": 6881
    },
    {
      "epoch": 0.21140908672011796,
      "grad_norm": 0.352337509393692,
      "learning_rate": 1.9467818043670172e-05,
      "loss": 0.6424,
      "step": 6882
    },
    {
      "epoch": 0.2114398058550671,
      "grad_norm": 0.32012486457824707,
      "learning_rate": 1.94676624771962e-05,
      "loss": 0.5868,
      "step": 6883
    },
    {
      "epoch": 0.21147052499001628,
      "grad_norm": 0.3392123579978943,
      "learning_rate": 1.946750688860984e-05,
      "loss": 0.6171,
      "step": 6884
    },
    {
      "epoch": 0.21150124412496543,
      "grad_norm": 0.3267022669315338,
      "learning_rate": 1.9467351277911458e-05,
      "loss": 0.6148,
      "step": 6885
    },
    {
      "epoch": 0.2115319632599146,
      "grad_norm": 0.4847431480884552,
      "learning_rate": 1.9467195645101413e-05,
      "loss": 0.6552,
      "step": 6886
    },
    {
      "epoch": 0.21156268239486375,
      "grad_norm": 0.42408645153045654,
      "learning_rate": 1.9467039990180074e-05,
      "loss": 0.6472,
      "step": 6887
    },
    {
      "epoch": 0.21159340152981293,
      "grad_norm": 0.3220108151435852,
      "learning_rate": 1.9466884313147804e-05,
      "loss": 0.6095,
      "step": 6888
    },
    {
      "epoch": 0.21162412066476208,
      "grad_norm": 0.4029952883720398,
      "learning_rate": 1.946672861400496e-05,
      "loss": 0.6031,
      "step": 6889
    },
    {
      "epoch": 0.21165483979971125,
      "grad_norm": 0.33666089177131653,
      "learning_rate": 1.946657289275191e-05,
      "loss": 0.546,
      "step": 6890
    },
    {
      "epoch": 0.2116855589346604,
      "grad_norm": 0.3103611171245575,
      "learning_rate": 1.946641714938902e-05,
      "loss": 0.5579,
      "step": 6891
    },
    {
      "epoch": 0.21171627806960955,
      "grad_norm": 0.34201323986053467,
      "learning_rate": 1.9466261383916654e-05,
      "loss": 0.6085,
      "step": 6892
    },
    {
      "epoch": 0.21174699720455872,
      "grad_norm": 0.3597601056098938,
      "learning_rate": 1.946610559633517e-05,
      "loss": 0.6078,
      "step": 6893
    },
    {
      "epoch": 0.21177771633950787,
      "grad_norm": 0.3278222382068634,
      "learning_rate": 1.9465949786644936e-05,
      "loss": 0.5362,
      "step": 6894
    },
    {
      "epoch": 0.21180843547445705,
      "grad_norm": 0.3123507797718048,
      "learning_rate": 1.9465793954846316e-05,
      "loss": 0.558,
      "step": 6895
    },
    {
      "epoch": 0.2118391546094062,
      "grad_norm": 0.34599238634109497,
      "learning_rate": 1.9465638100939672e-05,
      "loss": 0.7186,
      "step": 6896
    },
    {
      "epoch": 0.21186987374435537,
      "grad_norm": 0.3410007655620575,
      "learning_rate": 1.946548222492537e-05,
      "loss": 0.5725,
      "step": 6897
    },
    {
      "epoch": 0.21190059287930452,
      "grad_norm": 0.32351160049438477,
      "learning_rate": 1.9465326326803772e-05,
      "loss": 0.5914,
      "step": 6898
    },
    {
      "epoch": 0.2119313120142537,
      "grad_norm": 0.342926949262619,
      "learning_rate": 1.9465170406575248e-05,
      "loss": 0.547,
      "step": 6899
    },
    {
      "epoch": 0.21196203114920284,
      "grad_norm": 0.31965070962905884,
      "learning_rate": 1.946501446424015e-05,
      "loss": 0.6086,
      "step": 6900
    },
    {
      "epoch": 0.211992750284152,
      "grad_norm": 0.3552413880825043,
      "learning_rate": 1.9464858499798854e-05,
      "loss": 0.6007,
      "step": 6901
    },
    {
      "epoch": 0.21202346941910116,
      "grad_norm": 0.3169109523296356,
      "learning_rate": 1.9464702513251722e-05,
      "loss": 0.6141,
      "step": 6902
    },
    {
      "epoch": 0.2120541885540503,
      "grad_norm": 0.35254988074302673,
      "learning_rate": 1.946454650459911e-05,
      "loss": 0.4751,
      "step": 6903
    },
    {
      "epoch": 0.21208490768899949,
      "grad_norm": 0.37750425934791565,
      "learning_rate": 1.9464390473841393e-05,
      "loss": 0.6292,
      "step": 6904
    },
    {
      "epoch": 0.21211562682394863,
      "grad_norm": 0.33432063460350037,
      "learning_rate": 1.9464234420978928e-05,
      "loss": 0.5501,
      "step": 6905
    },
    {
      "epoch": 0.2121463459588978,
      "grad_norm": 0.3272215723991394,
      "learning_rate": 1.9464078346012087e-05,
      "loss": 0.5518,
      "step": 6906
    },
    {
      "epoch": 0.21217706509384696,
      "grad_norm": 0.3590032458305359,
      "learning_rate": 1.946392224894123e-05,
      "loss": 0.6285,
      "step": 6907
    },
    {
      "epoch": 0.2122077842287961,
      "grad_norm": 0.46296143531799316,
      "learning_rate": 1.9463766129766717e-05,
      "loss": 0.5426,
      "step": 6908
    },
    {
      "epoch": 0.21223850336374528,
      "grad_norm": 0.3289373815059662,
      "learning_rate": 1.9463609988488922e-05,
      "loss": 0.5747,
      "step": 6909
    },
    {
      "epoch": 0.21226922249869443,
      "grad_norm": 0.34269535541534424,
      "learning_rate": 1.94634538251082e-05,
      "loss": 0.6338,
      "step": 6910
    },
    {
      "epoch": 0.2122999416336436,
      "grad_norm": 0.3120807409286499,
      "learning_rate": 1.9463297639624925e-05,
      "loss": 0.5857,
      "step": 6911
    },
    {
      "epoch": 0.21233066076859275,
      "grad_norm": 0.38941940665245056,
      "learning_rate": 1.9463141432039457e-05,
      "loss": 0.5153,
      "step": 6912
    },
    {
      "epoch": 0.21236137990354192,
      "grad_norm": 0.3725374639034271,
      "learning_rate": 1.9462985202352162e-05,
      "loss": 0.612,
      "step": 6913
    },
    {
      "epoch": 0.21239209903849107,
      "grad_norm": 0.3353291153907776,
      "learning_rate": 1.94628289505634e-05,
      "loss": 0.6364,
      "step": 6914
    },
    {
      "epoch": 0.21242281817344025,
      "grad_norm": 0.3772139847278595,
      "learning_rate": 1.9462672676673543e-05,
      "loss": 0.6409,
      "step": 6915
    },
    {
      "epoch": 0.2124535373083894,
      "grad_norm": 0.3532460331916809,
      "learning_rate": 1.946251638068295e-05,
      "loss": 0.609,
      "step": 6916
    },
    {
      "epoch": 0.21248425644333854,
      "grad_norm": 0.5365630984306335,
      "learning_rate": 1.9462360062591993e-05,
      "loss": 0.5436,
      "step": 6917
    },
    {
      "epoch": 0.21251497557828772,
      "grad_norm": 0.32816532254219055,
      "learning_rate": 1.946220372240103e-05,
      "loss": 0.5793,
      "step": 6918
    },
    {
      "epoch": 0.21254569471323687,
      "grad_norm": 0.3348343074321747,
      "learning_rate": 1.9462047360110433e-05,
      "loss": 0.6198,
      "step": 6919
    },
    {
      "epoch": 0.21257641384818604,
      "grad_norm": 0.312858909368515,
      "learning_rate": 1.9461890975720562e-05,
      "loss": 0.5931,
      "step": 6920
    },
    {
      "epoch": 0.2126071329831352,
      "grad_norm": 0.36463090777397156,
      "learning_rate": 1.9461734569231785e-05,
      "loss": 0.5936,
      "step": 6921
    },
    {
      "epoch": 0.21263785211808436,
      "grad_norm": 0.34361931681632996,
      "learning_rate": 1.9461578140644464e-05,
      "loss": 0.6401,
      "step": 6922
    },
    {
      "epoch": 0.2126685712530335,
      "grad_norm": 0.3445605933666229,
      "learning_rate": 1.9461421689958965e-05,
      "loss": 0.6152,
      "step": 6923
    },
    {
      "epoch": 0.2126992903879827,
      "grad_norm": 0.3404785096645355,
      "learning_rate": 1.9461265217175657e-05,
      "loss": 0.5736,
      "step": 6924
    },
    {
      "epoch": 0.21273000952293183,
      "grad_norm": 0.3043605387210846,
      "learning_rate": 1.9461108722294906e-05,
      "loss": 0.5943,
      "step": 6925
    },
    {
      "epoch": 0.21276072865788098,
      "grad_norm": 0.3497447669506073,
      "learning_rate": 1.946095220531707e-05,
      "loss": 0.6234,
      "step": 6926
    },
    {
      "epoch": 0.21279144779283016,
      "grad_norm": 0.316416472196579,
      "learning_rate": 1.946079566624252e-05,
      "loss": 0.5272,
      "step": 6927
    },
    {
      "epoch": 0.2128221669277793,
      "grad_norm": 0.31701144576072693,
      "learning_rate": 1.9460639105071626e-05,
      "loss": 0.582,
      "step": 6928
    },
    {
      "epoch": 0.21285288606272848,
      "grad_norm": 0.3378000855445862,
      "learning_rate": 1.9460482521804746e-05,
      "loss": 0.6349,
      "step": 6929
    },
    {
      "epoch": 0.21288360519767763,
      "grad_norm": 0.371761292219162,
      "learning_rate": 1.9460325916442248e-05,
      "loss": 0.6684,
      "step": 6930
    },
    {
      "epoch": 0.2129143243326268,
      "grad_norm": 0.3238587975502014,
      "learning_rate": 1.9460169288984496e-05,
      "loss": 0.5465,
      "step": 6931
    },
    {
      "epoch": 0.21294504346757595,
      "grad_norm": 0.3284999430179596,
      "learning_rate": 1.946001263943186e-05,
      "loss": 0.5261,
      "step": 6932
    },
    {
      "epoch": 0.21297576260252513,
      "grad_norm": 0.356264591217041,
      "learning_rate": 1.94598559677847e-05,
      "loss": 0.5382,
      "step": 6933
    },
    {
      "epoch": 0.21300648173747427,
      "grad_norm": 0.31854012608528137,
      "learning_rate": 1.9459699274043392e-05,
      "loss": 0.5505,
      "step": 6934
    },
    {
      "epoch": 0.21303720087242342,
      "grad_norm": 0.3469434976577759,
      "learning_rate": 1.9459542558208292e-05,
      "loss": 0.5821,
      "step": 6935
    },
    {
      "epoch": 0.2130679200073726,
      "grad_norm": 0.3392375409603119,
      "learning_rate": 1.9459385820279772e-05,
      "loss": 0.5563,
      "step": 6936
    },
    {
      "epoch": 0.21309863914232174,
      "grad_norm": 0.3762151896953583,
      "learning_rate": 1.9459229060258193e-05,
      "loss": 0.6733,
      "step": 6937
    },
    {
      "epoch": 0.21312935827727092,
      "grad_norm": 0.34337496757507324,
      "learning_rate": 1.9459072278143927e-05,
      "loss": 0.6065,
      "step": 6938
    },
    {
      "epoch": 0.21316007741222007,
      "grad_norm": 0.8158531188964844,
      "learning_rate": 1.9458915473937335e-05,
      "loss": 0.5543,
      "step": 6939
    },
    {
      "epoch": 0.21319079654716924,
      "grad_norm": 0.3446367383003235,
      "learning_rate": 1.9458758647638785e-05,
      "loss": 0.5289,
      "step": 6940
    },
    {
      "epoch": 0.2132215156821184,
      "grad_norm": 0.34889522194862366,
      "learning_rate": 1.9458601799248644e-05,
      "loss": 0.5796,
      "step": 6941
    },
    {
      "epoch": 0.21325223481706757,
      "grad_norm": 0.367064893245697,
      "learning_rate": 1.945844492876728e-05,
      "loss": 0.554,
      "step": 6942
    },
    {
      "epoch": 0.2132829539520167,
      "grad_norm": 0.34040358662605286,
      "learning_rate": 1.9458288036195053e-05,
      "loss": 0.6423,
      "step": 6943
    },
    {
      "epoch": 0.21331367308696586,
      "grad_norm": 0.39948439598083496,
      "learning_rate": 1.945813112153234e-05,
      "loss": 0.6084,
      "step": 6944
    },
    {
      "epoch": 0.21334439222191504,
      "grad_norm": 0.3264942467212677,
      "learning_rate": 1.9457974184779497e-05,
      "loss": 0.4465,
      "step": 6945
    },
    {
      "epoch": 0.21337511135686418,
      "grad_norm": 0.3026781976222992,
      "learning_rate": 1.9457817225936893e-05,
      "loss": 0.5793,
      "step": 6946
    },
    {
      "epoch": 0.21340583049181336,
      "grad_norm": 0.35538795590400696,
      "learning_rate": 1.94576602450049e-05,
      "loss": 0.6143,
      "step": 6947
    },
    {
      "epoch": 0.2134365496267625,
      "grad_norm": 0.3453122675418854,
      "learning_rate": 1.945750324198388e-05,
      "loss": 0.6984,
      "step": 6948
    },
    {
      "epoch": 0.21346726876171168,
      "grad_norm": 0.3291662335395813,
      "learning_rate": 1.9457346216874197e-05,
      "loss": 0.6051,
      "step": 6949
    },
    {
      "epoch": 0.21349798789666083,
      "grad_norm": 0.4322100877761841,
      "learning_rate": 1.9457189169676228e-05,
      "loss": 0.5839,
      "step": 6950
    },
    {
      "epoch": 0.21352870703160998,
      "grad_norm": 0.33026760816574097,
      "learning_rate": 1.9457032100390326e-05,
      "loss": 0.5729,
      "step": 6951
    },
    {
      "epoch": 0.21355942616655915,
      "grad_norm": 0.32274481654167175,
      "learning_rate": 1.945687500901687e-05,
      "loss": 0.5627,
      "step": 6952
    },
    {
      "epoch": 0.2135901453015083,
      "grad_norm": 0.3137408494949341,
      "learning_rate": 1.9456717895556222e-05,
      "loss": 0.6242,
      "step": 6953
    },
    {
      "epoch": 0.21362086443645747,
      "grad_norm": 0.3570811152458191,
      "learning_rate": 1.945656076000875e-05,
      "loss": 0.6185,
      "step": 6954
    },
    {
      "epoch": 0.21365158357140662,
      "grad_norm": 0.3760155439376831,
      "learning_rate": 1.9456403602374813e-05,
      "loss": 0.6595,
      "step": 6955
    },
    {
      "epoch": 0.2136823027063558,
      "grad_norm": 0.33095690608024597,
      "learning_rate": 1.945624642265479e-05,
      "loss": 0.576,
      "step": 6956
    },
    {
      "epoch": 0.21371302184130495,
      "grad_norm": 0.2784162759780884,
      "learning_rate": 1.9456089220849043e-05,
      "loss": 0.5204,
      "step": 6957
    },
    {
      "epoch": 0.21374374097625412,
      "grad_norm": 0.3640543520450592,
      "learning_rate": 1.945593199695794e-05,
      "loss": 0.6112,
      "step": 6958
    },
    {
      "epoch": 0.21377446011120327,
      "grad_norm": 0.3521929979324341,
      "learning_rate": 1.9455774750981847e-05,
      "loss": 0.576,
      "step": 6959
    },
    {
      "epoch": 0.21380517924615242,
      "grad_norm": 0.35714420676231384,
      "learning_rate": 1.945561748292113e-05,
      "loss": 0.5723,
      "step": 6960
    },
    {
      "epoch": 0.2138358983811016,
      "grad_norm": 0.3550485372543335,
      "learning_rate": 1.9455460192776158e-05,
      "loss": 0.6195,
      "step": 6961
    },
    {
      "epoch": 0.21386661751605074,
      "grad_norm": 0.37049639225006104,
      "learning_rate": 1.94553028805473e-05,
      "loss": 0.6379,
      "step": 6962
    },
    {
      "epoch": 0.21389733665099991,
      "grad_norm": 0.3556708097457886,
      "learning_rate": 1.945514554623492e-05,
      "loss": 0.5748,
      "step": 6963
    },
    {
      "epoch": 0.21392805578594906,
      "grad_norm": 0.31783589720726013,
      "learning_rate": 1.945498818983939e-05,
      "loss": 0.5699,
      "step": 6964
    },
    {
      "epoch": 0.21395877492089824,
      "grad_norm": 0.45802897214889526,
      "learning_rate": 1.945483081136107e-05,
      "loss": 0.5513,
      "step": 6965
    },
    {
      "epoch": 0.21398949405584738,
      "grad_norm": 0.3443422317504883,
      "learning_rate": 1.945467341080034e-05,
      "loss": 0.5514,
      "step": 6966
    },
    {
      "epoch": 0.21402021319079656,
      "grad_norm": 0.3587382733821869,
      "learning_rate": 1.9454515988157553e-05,
      "loss": 0.5756,
      "step": 6967
    },
    {
      "epoch": 0.2140509323257457,
      "grad_norm": 0.321412593126297,
      "learning_rate": 1.9454358543433086e-05,
      "loss": 0.5468,
      "step": 6968
    },
    {
      "epoch": 0.21408165146069486,
      "grad_norm": 0.35887831449508667,
      "learning_rate": 1.9454201076627303e-05,
      "loss": 0.5715,
      "step": 6969
    },
    {
      "epoch": 0.21411237059564403,
      "grad_norm": 0.45508962869644165,
      "learning_rate": 1.9454043587740578e-05,
      "loss": 0.5171,
      "step": 6970
    },
    {
      "epoch": 0.21414308973059318,
      "grad_norm": 0.5978578925132751,
      "learning_rate": 1.9453886076773266e-05,
      "loss": 0.6083,
      "step": 6971
    },
    {
      "epoch": 0.21417380886554235,
      "grad_norm": 0.359482079744339,
      "learning_rate": 1.945372854372575e-05,
      "loss": 0.6475,
      "step": 6972
    },
    {
      "epoch": 0.2142045280004915,
      "grad_norm": 0.3641624450683594,
      "learning_rate": 1.9453570988598388e-05,
      "loss": 0.5393,
      "step": 6973
    },
    {
      "epoch": 0.21423524713544068,
      "grad_norm": 0.40729475021362305,
      "learning_rate": 1.945341341139155e-05,
      "loss": 0.6804,
      "step": 6974
    },
    {
      "epoch": 0.21426596627038982,
      "grad_norm": 0.4528740346431732,
      "learning_rate": 1.9453255812105607e-05,
      "loss": 0.6394,
      "step": 6975
    },
    {
      "epoch": 0.214296685405339,
      "grad_norm": 0.32852935791015625,
      "learning_rate": 1.9453098190740923e-05,
      "loss": 0.5805,
      "step": 6976
    },
    {
      "epoch": 0.21432740454028815,
      "grad_norm": 0.3235732913017273,
      "learning_rate": 1.9452940547297868e-05,
      "loss": 0.5847,
      "step": 6977
    },
    {
      "epoch": 0.2143581236752373,
      "grad_norm": 0.34987977147102356,
      "learning_rate": 1.945278288177681e-05,
      "loss": 0.5464,
      "step": 6978
    },
    {
      "epoch": 0.21438884281018647,
      "grad_norm": 0.36413583159446716,
      "learning_rate": 1.9452625194178118e-05,
      "loss": 0.5234,
      "step": 6979
    },
    {
      "epoch": 0.21441956194513562,
      "grad_norm": 0.4398280680179596,
      "learning_rate": 1.9452467484502158e-05,
      "loss": 0.5832,
      "step": 6980
    },
    {
      "epoch": 0.2144502810800848,
      "grad_norm": 0.32694211602211,
      "learning_rate": 1.9452309752749305e-05,
      "loss": 0.5408,
      "step": 6981
    },
    {
      "epoch": 0.21448100021503394,
      "grad_norm": 0.5400601625442505,
      "learning_rate": 1.9452151998919916e-05,
      "loss": 0.5704,
      "step": 6982
    },
    {
      "epoch": 0.21451171934998312,
      "grad_norm": 0.35813888907432556,
      "learning_rate": 1.945199422301437e-05,
      "loss": 0.5818,
      "step": 6983
    },
    {
      "epoch": 0.21454243848493226,
      "grad_norm": 0.324771523475647,
      "learning_rate": 1.945183642503303e-05,
      "loss": 0.5583,
      "step": 6984
    },
    {
      "epoch": 0.2145731576198814,
      "grad_norm": 0.3319883644580841,
      "learning_rate": 1.9451678604976266e-05,
      "loss": 0.5364,
      "step": 6985
    },
    {
      "epoch": 0.21460387675483059,
      "grad_norm": 0.3361334204673767,
      "learning_rate": 1.9451520762844445e-05,
      "loss": 0.6008,
      "step": 6986
    },
    {
      "epoch": 0.21463459588977973,
      "grad_norm": 0.32287830114364624,
      "learning_rate": 1.945136289863794e-05,
      "loss": 0.4855,
      "step": 6987
    },
    {
      "epoch": 0.2146653150247289,
      "grad_norm": 0.3402499556541443,
      "learning_rate": 1.9451205012357114e-05,
      "loss": 0.5975,
      "step": 6988
    },
    {
      "epoch": 0.21469603415967806,
      "grad_norm": 0.3466370701789856,
      "learning_rate": 1.945104710400234e-05,
      "loss": 0.6287,
      "step": 6989
    },
    {
      "epoch": 0.21472675329462723,
      "grad_norm": 0.35339292883872986,
      "learning_rate": 1.945088917357399e-05,
      "loss": 0.6624,
      "step": 6990
    },
    {
      "epoch": 0.21475747242957638,
      "grad_norm": 0.33826643228530884,
      "learning_rate": 1.945073122107242e-05,
      "loss": 0.5188,
      "step": 6991
    },
    {
      "epoch": 0.21478819156452555,
      "grad_norm": 0.37751156091690063,
      "learning_rate": 1.945057324649801e-05,
      "loss": 0.582,
      "step": 6992
    },
    {
      "epoch": 0.2148189106994747,
      "grad_norm": 0.3432838022708893,
      "learning_rate": 1.945041524985113e-05,
      "loss": 0.5948,
      "step": 6993
    },
    {
      "epoch": 0.21484962983442385,
      "grad_norm": 0.3533337116241455,
      "learning_rate": 1.9450257231132142e-05,
      "loss": 0.5801,
      "step": 6994
    },
    {
      "epoch": 0.21488034896937303,
      "grad_norm": 0.33773550391197205,
      "learning_rate": 1.945009919034142e-05,
      "loss": 0.5526,
      "step": 6995
    },
    {
      "epoch": 0.21491106810432217,
      "grad_norm": 0.3985190987586975,
      "learning_rate": 1.944994112747933e-05,
      "loss": 0.6666,
      "step": 6996
    },
    {
      "epoch": 0.21494178723927135,
      "grad_norm": 0.31864067912101746,
      "learning_rate": 1.9449783042546243e-05,
      "loss": 0.6031,
      "step": 6997
    },
    {
      "epoch": 0.2149725063742205,
      "grad_norm": 0.3137242794036865,
      "learning_rate": 1.9449624935542527e-05,
      "loss": 0.5976,
      "step": 6998
    },
    {
      "epoch": 0.21500322550916967,
      "grad_norm": 0.35759952664375305,
      "learning_rate": 1.9449466806468554e-05,
      "loss": 0.5727,
      "step": 6999
    },
    {
      "epoch": 0.21503394464411882,
      "grad_norm": 0.3251418471336365,
      "learning_rate": 1.9449308655324687e-05,
      "loss": 0.5846,
      "step": 7000
    },
    {
      "epoch": 0.215064663779068,
      "grad_norm": 0.3203136622905731,
      "learning_rate": 1.9449150482111302e-05,
      "loss": 0.5149,
      "step": 7001
    },
    {
      "epoch": 0.21509538291401714,
      "grad_norm": 0.35594484210014343,
      "learning_rate": 1.9448992286828766e-05,
      "loss": 0.5776,
      "step": 7002
    },
    {
      "epoch": 0.2151261020489663,
      "grad_norm": 0.36626413464546204,
      "learning_rate": 1.9448834069477453e-05,
      "loss": 0.5797,
      "step": 7003
    },
    {
      "epoch": 0.21515682118391546,
      "grad_norm": 0.3597395718097687,
      "learning_rate": 1.9448675830057723e-05,
      "loss": 0.5783,
      "step": 7004
    },
    {
      "epoch": 0.2151875403188646,
      "grad_norm": 0.4954650104045868,
      "learning_rate": 1.9448517568569953e-05,
      "loss": 0.6508,
      "step": 7005
    },
    {
      "epoch": 0.2152182594538138,
      "grad_norm": 0.3108378052711487,
      "learning_rate": 1.9448359285014508e-05,
      "loss": 0.5636,
      "step": 7006
    },
    {
      "epoch": 0.21524897858876293,
      "grad_norm": 0.3483054041862488,
      "learning_rate": 1.944820097939176e-05,
      "loss": 0.6315,
      "step": 7007
    },
    {
      "epoch": 0.2152796977237121,
      "grad_norm": 0.3371865451335907,
      "learning_rate": 1.944804265170208e-05,
      "loss": 0.5594,
      "step": 7008
    },
    {
      "epoch": 0.21531041685866126,
      "grad_norm": 0.3657490313053131,
      "learning_rate": 1.944788430194584e-05,
      "loss": 0.6252,
      "step": 7009
    },
    {
      "epoch": 0.21534113599361043,
      "grad_norm": 0.4209143817424774,
      "learning_rate": 1.94477259301234e-05,
      "loss": 0.5653,
      "step": 7010
    },
    {
      "epoch": 0.21537185512855958,
      "grad_norm": 0.35575082898139954,
      "learning_rate": 1.9447567536235142e-05,
      "loss": 0.5545,
      "step": 7011
    },
    {
      "epoch": 0.21540257426350873,
      "grad_norm": 0.38152584433555603,
      "learning_rate": 1.9447409120281427e-05,
      "loss": 0.5803,
      "step": 7012
    },
    {
      "epoch": 0.2154332933984579,
      "grad_norm": 0.3336385190486908,
      "learning_rate": 1.944725068226263e-05,
      "loss": 0.4925,
      "step": 7013
    },
    {
      "epoch": 0.21546401253340705,
      "grad_norm": 0.8241966366767883,
      "learning_rate": 1.9447092222179117e-05,
      "loss": 0.5981,
      "step": 7014
    },
    {
      "epoch": 0.21549473166835623,
      "grad_norm": 0.37771591544151306,
      "learning_rate": 1.9446933740031258e-05,
      "loss": 0.6146,
      "step": 7015
    },
    {
      "epoch": 0.21552545080330537,
      "grad_norm": 0.34676146507263184,
      "learning_rate": 1.9446775235819434e-05,
      "loss": 0.5896,
      "step": 7016
    },
    {
      "epoch": 0.21555616993825455,
      "grad_norm": 0.3655661642551422,
      "learning_rate": 1.9446616709544e-05,
      "loss": 0.6388,
      "step": 7017
    },
    {
      "epoch": 0.2155868890732037,
      "grad_norm": 0.3434339463710785,
      "learning_rate": 1.9446458161205335e-05,
      "loss": 0.6132,
      "step": 7018
    },
    {
      "epoch": 0.21561760820815287,
      "grad_norm": 0.34434202313423157,
      "learning_rate": 1.9446299590803805e-05,
      "loss": 0.608,
      "step": 7019
    },
    {
      "epoch": 0.21564832734310202,
      "grad_norm": 0.3559676706790924,
      "learning_rate": 1.9446140998339784e-05,
      "loss": 0.6188,
      "step": 7020
    },
    {
      "epoch": 0.21567904647805117,
      "grad_norm": 0.3530060350894928,
      "learning_rate": 1.944598238381364e-05,
      "loss": 0.5562,
      "step": 7021
    },
    {
      "epoch": 0.21570976561300034,
      "grad_norm": 0.3233635127544403,
      "learning_rate": 1.9445823747225746e-05,
      "loss": 0.6522,
      "step": 7022
    },
    {
      "epoch": 0.2157404847479495,
      "grad_norm": 0.34793621301651,
      "learning_rate": 1.944566508857647e-05,
      "loss": 0.6175,
      "step": 7023
    },
    {
      "epoch": 0.21577120388289867,
      "grad_norm": 0.34585627913475037,
      "learning_rate": 1.9445506407866187e-05,
      "loss": 0.5658,
      "step": 7024
    },
    {
      "epoch": 0.2158019230178478,
      "grad_norm": 0.3485947251319885,
      "learning_rate": 1.944534770509526e-05,
      "loss": 0.5964,
      "step": 7025
    },
    {
      "epoch": 0.215832642152797,
      "grad_norm": 0.3569158911705017,
      "learning_rate": 1.9445188980264066e-05,
      "loss": 0.5779,
      "step": 7026
    },
    {
      "epoch": 0.21586336128774614,
      "grad_norm": 0.36609789729118347,
      "learning_rate": 1.9445030233372972e-05,
      "loss": 0.5673,
      "step": 7027
    },
    {
      "epoch": 0.21589408042269528,
      "grad_norm": 0.36632686853408813,
      "learning_rate": 1.944487146442235e-05,
      "loss": 0.6028,
      "step": 7028
    },
    {
      "epoch": 0.21592479955764446,
      "grad_norm": 0.3538036346435547,
      "learning_rate": 1.9444712673412572e-05,
      "loss": 0.5898,
      "step": 7029
    },
    {
      "epoch": 0.2159555186925936,
      "grad_norm": 0.4421806335449219,
      "learning_rate": 1.9444553860344007e-05,
      "loss": 0.6369,
      "step": 7030
    },
    {
      "epoch": 0.21598623782754278,
      "grad_norm": 0.3854859173297882,
      "learning_rate": 1.9444395025217027e-05,
      "loss": 0.6452,
      "step": 7031
    },
    {
      "epoch": 0.21601695696249193,
      "grad_norm": 0.39243602752685547,
      "learning_rate": 1.944423616803201e-05,
      "loss": 0.5832,
      "step": 7032
    },
    {
      "epoch": 0.2160476760974411,
      "grad_norm": 0.3506511449813843,
      "learning_rate": 1.944407728878931e-05,
      "loss": 0.4819,
      "step": 7033
    },
    {
      "epoch": 0.21607839523239025,
      "grad_norm": 0.343405157327652,
      "learning_rate": 1.9443918387489307e-05,
      "loss": 0.6088,
      "step": 7034
    },
    {
      "epoch": 0.21610911436733943,
      "grad_norm": 0.4161800444126129,
      "learning_rate": 1.944375946413238e-05,
      "loss": 0.5872,
      "step": 7035
    },
    {
      "epoch": 0.21613983350228858,
      "grad_norm": 0.3719150722026825,
      "learning_rate": 1.9443600518718892e-05,
      "loss": 0.6866,
      "step": 7036
    },
    {
      "epoch": 0.21617055263723772,
      "grad_norm": 0.39957189559936523,
      "learning_rate": 1.9443441551249215e-05,
      "loss": 0.6121,
      "step": 7037
    },
    {
      "epoch": 0.2162012717721869,
      "grad_norm": 0.33701056241989136,
      "learning_rate": 1.9443282561723717e-05,
      "loss": 0.5845,
      "step": 7038
    },
    {
      "epoch": 0.21623199090713605,
      "grad_norm": 0.32902827858924866,
      "learning_rate": 1.9443123550142776e-05,
      "loss": 0.6187,
      "step": 7039
    },
    {
      "epoch": 0.21626271004208522,
      "grad_norm": 0.3454064428806305,
      "learning_rate": 1.944296451650676e-05,
      "loss": 0.5735,
      "step": 7040
    },
    {
      "epoch": 0.21629342917703437,
      "grad_norm": 0.3320229947566986,
      "learning_rate": 1.944280546081604e-05,
      "loss": 0.5281,
      "step": 7041
    },
    {
      "epoch": 0.21632414831198354,
      "grad_norm": 0.39070332050323486,
      "learning_rate": 1.944264638307099e-05,
      "loss": 0.6278,
      "step": 7042
    },
    {
      "epoch": 0.2163548674469327,
      "grad_norm": 0.556035578250885,
      "learning_rate": 1.9442487283271982e-05,
      "loss": 0.6213,
      "step": 7043
    },
    {
      "epoch": 0.21638558658188187,
      "grad_norm": 0.3283368945121765,
      "learning_rate": 1.9442328161419382e-05,
      "loss": 0.5789,
      "step": 7044
    },
    {
      "epoch": 0.21641630571683101,
      "grad_norm": 0.4934787452220917,
      "learning_rate": 1.9442169017513565e-05,
      "loss": 0.5832,
      "step": 7045
    },
    {
      "epoch": 0.21644702485178016,
      "grad_norm": 0.3123880922794342,
      "learning_rate": 1.9442009851554906e-05,
      "loss": 0.6019,
      "step": 7046
    },
    {
      "epoch": 0.21647774398672934,
      "grad_norm": 0.3268885910511017,
      "learning_rate": 1.9441850663543772e-05,
      "loss": 0.614,
      "step": 7047
    },
    {
      "epoch": 0.21650846312167848,
      "grad_norm": 0.34913399815559387,
      "learning_rate": 1.9441691453480534e-05,
      "loss": 0.5723,
      "step": 7048
    },
    {
      "epoch": 0.21653918225662766,
      "grad_norm": 0.4546506702899933,
      "learning_rate": 1.944153222136557e-05,
      "loss": 0.6813,
      "step": 7049
    },
    {
      "epoch": 0.2165699013915768,
      "grad_norm": 0.36651623249053955,
      "learning_rate": 1.9441372967199245e-05,
      "loss": 0.5354,
      "step": 7050
    },
    {
      "epoch": 0.21660062052652598,
      "grad_norm": 0.3774753510951996,
      "learning_rate": 1.9441213690981935e-05,
      "loss": 0.5903,
      "step": 7051
    },
    {
      "epoch": 0.21663133966147513,
      "grad_norm": 0.33642512559890747,
      "learning_rate": 1.9441054392714012e-05,
      "loss": 0.5794,
      "step": 7052
    },
    {
      "epoch": 0.2166620587964243,
      "grad_norm": 0.334236741065979,
      "learning_rate": 1.9440895072395843e-05,
      "loss": 0.5976,
      "step": 7053
    },
    {
      "epoch": 0.21669277793137345,
      "grad_norm": 0.31165754795074463,
      "learning_rate": 1.9440735730027808e-05,
      "loss": 0.5555,
      "step": 7054
    },
    {
      "epoch": 0.2167234970663226,
      "grad_norm": 0.3693506419658661,
      "learning_rate": 1.9440576365610275e-05,
      "loss": 0.6303,
      "step": 7055
    },
    {
      "epoch": 0.21675421620127178,
      "grad_norm": 0.3625418543815613,
      "learning_rate": 1.944041697914362e-05,
      "loss": 0.631,
      "step": 7056
    },
    {
      "epoch": 0.21678493533622092,
      "grad_norm": 0.4176451563835144,
      "learning_rate": 1.9440257570628204e-05,
      "loss": 0.5343,
      "step": 7057
    },
    {
      "epoch": 0.2168156544711701,
      "grad_norm": 0.33605360984802246,
      "learning_rate": 1.9440098140064414e-05,
      "loss": 0.6322,
      "step": 7058
    },
    {
      "epoch": 0.21684637360611925,
      "grad_norm": 0.3271574378013611,
      "learning_rate": 1.943993868745261e-05,
      "loss": 0.5604,
      "step": 7059
    },
    {
      "epoch": 0.21687709274106842,
      "grad_norm": 0.36626800894737244,
      "learning_rate": 1.9439779212793178e-05,
      "loss": 0.5443,
      "step": 7060
    },
    {
      "epoch": 0.21690781187601757,
      "grad_norm": 0.3378170132637024,
      "learning_rate": 1.9439619716086476e-05,
      "loss": 0.5492,
      "step": 7061
    },
    {
      "epoch": 0.21693853101096672,
      "grad_norm": 0.34727978706359863,
      "learning_rate": 1.9439460197332886e-05,
      "loss": 0.5632,
      "step": 7062
    },
    {
      "epoch": 0.2169692501459159,
      "grad_norm": 0.3413423001766205,
      "learning_rate": 1.9439300656532773e-05,
      "loss": 0.5619,
      "step": 7063
    },
    {
      "epoch": 0.21699996928086504,
      "grad_norm": 0.32166028022766113,
      "learning_rate": 1.9439141093686517e-05,
      "loss": 0.5915,
      "step": 7064
    },
    {
      "epoch": 0.21703068841581422,
      "grad_norm": 0.3361012935638428,
      "learning_rate": 1.9438981508794486e-05,
      "loss": 0.59,
      "step": 7065
    },
    {
      "epoch": 0.21706140755076336,
      "grad_norm": 0.34965944290161133,
      "learning_rate": 1.9438821901857058e-05,
      "loss": 0.6345,
      "step": 7066
    },
    {
      "epoch": 0.21709212668571254,
      "grad_norm": 0.3997224271297455,
      "learning_rate": 1.94386622728746e-05,
      "loss": 0.4985,
      "step": 7067
    },
    {
      "epoch": 0.2171228458206617,
      "grad_norm": 0.3304525315761566,
      "learning_rate": 1.9438502621847486e-05,
      "loss": 0.6308,
      "step": 7068
    },
    {
      "epoch": 0.21715356495561086,
      "grad_norm": 0.3641963601112366,
      "learning_rate": 1.9438342948776093e-05,
      "loss": 0.7052,
      "step": 7069
    },
    {
      "epoch": 0.21718428409056,
      "grad_norm": 0.3546707034111023,
      "learning_rate": 1.943818325366079e-05,
      "loss": 0.6893,
      "step": 7070
    },
    {
      "epoch": 0.21721500322550916,
      "grad_norm": 0.38702529668807983,
      "learning_rate": 1.943802353650195e-05,
      "loss": 0.6122,
      "step": 7071
    },
    {
      "epoch": 0.21724572236045833,
      "grad_norm": 0.3563117980957031,
      "learning_rate": 1.9437863797299944e-05,
      "loss": 0.5916,
      "step": 7072
    },
    {
      "epoch": 0.21727644149540748,
      "grad_norm": 0.3742269277572632,
      "learning_rate": 1.9437704036055153e-05,
      "loss": 0.6351,
      "step": 7073
    },
    {
      "epoch": 0.21730716063035665,
      "grad_norm": 0.3273765444755554,
      "learning_rate": 1.9437544252767942e-05,
      "loss": 0.5471,
      "step": 7074
    },
    {
      "epoch": 0.2173378797653058,
      "grad_norm": 0.36251184344291687,
      "learning_rate": 1.9437384447438687e-05,
      "loss": 0.6181,
      "step": 7075
    },
    {
      "epoch": 0.21736859890025498,
      "grad_norm": 0.36197036504745483,
      "learning_rate": 1.9437224620067762e-05,
      "loss": 0.6834,
      "step": 7076
    },
    {
      "epoch": 0.21739931803520413,
      "grad_norm": 0.31233644485473633,
      "learning_rate": 1.943706477065554e-05,
      "loss": 0.5389,
      "step": 7077
    },
    {
      "epoch": 0.2174300371701533,
      "grad_norm": 0.594025731086731,
      "learning_rate": 1.94369048992024e-05,
      "loss": 0.5865,
      "step": 7078
    },
    {
      "epoch": 0.21746075630510245,
      "grad_norm": 0.3725707232952118,
      "learning_rate": 1.94367450057087e-05,
      "loss": 0.5478,
      "step": 7079
    },
    {
      "epoch": 0.2174914754400516,
      "grad_norm": 0.3344149887561798,
      "learning_rate": 1.9436585090174828e-05,
      "loss": 0.5725,
      "step": 7080
    },
    {
      "epoch": 0.21752219457500077,
      "grad_norm": 0.3397082984447479,
      "learning_rate": 1.9436425152601152e-05,
      "loss": 0.5939,
      "step": 7081
    },
    {
      "epoch": 0.21755291370994992,
      "grad_norm": 0.33837518095970154,
      "learning_rate": 1.9436265192988048e-05,
      "loss": 0.6118,
      "step": 7082
    },
    {
      "epoch": 0.2175836328448991,
      "grad_norm": 0.333927720785141,
      "learning_rate": 1.943610521133588e-05,
      "loss": 0.6075,
      "step": 7083
    },
    {
      "epoch": 0.21761435197984824,
      "grad_norm": 0.35752636194229126,
      "learning_rate": 1.9435945207645036e-05,
      "loss": 0.5654,
      "step": 7084
    },
    {
      "epoch": 0.21764507111479742,
      "grad_norm": 0.3594207465648651,
      "learning_rate": 1.9435785181915884e-05,
      "loss": 0.6413,
      "step": 7085
    },
    {
      "epoch": 0.21767579024974656,
      "grad_norm": 0.4951466917991638,
      "learning_rate": 1.943562513414879e-05,
      "loss": 0.635,
      "step": 7086
    },
    {
      "epoch": 0.21770650938469574,
      "grad_norm": 0.39108651876449585,
      "learning_rate": 1.943546506434414e-05,
      "loss": 0.68,
      "step": 7087
    },
    {
      "epoch": 0.2177372285196449,
      "grad_norm": 0.38816037774086,
      "learning_rate": 1.9435304972502306e-05,
      "loss": 0.6243,
      "step": 7088
    },
    {
      "epoch": 0.21776794765459404,
      "grad_norm": 0.29980480670928955,
      "learning_rate": 1.943514485862365e-05,
      "loss": 0.6272,
      "step": 7089
    },
    {
      "epoch": 0.2177986667895432,
      "grad_norm": 0.35475099086761475,
      "learning_rate": 1.9434984722708557e-05,
      "loss": 0.6514,
      "step": 7090
    },
    {
      "epoch": 0.21782938592449236,
      "grad_norm": 0.3401775062084198,
      "learning_rate": 1.94348245647574e-05,
      "loss": 0.6082,
      "step": 7091
    },
    {
      "epoch": 0.21786010505944153,
      "grad_norm": 0.3646056652069092,
      "learning_rate": 1.943466438477055e-05,
      "loss": 0.6254,
      "step": 7092
    },
    {
      "epoch": 0.21789082419439068,
      "grad_norm": 0.3053387701511383,
      "learning_rate": 1.9434504182748384e-05,
      "loss": 0.548,
      "step": 7093
    },
    {
      "epoch": 0.21792154332933986,
      "grad_norm": 0.332308292388916,
      "learning_rate": 1.9434343958691272e-05,
      "loss": 0.5998,
      "step": 7094
    },
    {
      "epoch": 0.217952262464289,
      "grad_norm": 0.36136260628700256,
      "learning_rate": 1.9434183712599594e-05,
      "loss": 0.6501,
      "step": 7095
    },
    {
      "epoch": 0.21798298159923818,
      "grad_norm": 0.35034438967704773,
      "learning_rate": 1.943402344447372e-05,
      "loss": 0.5634,
      "step": 7096
    },
    {
      "epoch": 0.21801370073418733,
      "grad_norm": 0.34205761551856995,
      "learning_rate": 1.9433863154314023e-05,
      "loss": 0.6982,
      "step": 7097
    },
    {
      "epoch": 0.21804441986913647,
      "grad_norm": 0.3207978904247284,
      "learning_rate": 1.943370284212088e-05,
      "loss": 0.5575,
      "step": 7098
    },
    {
      "epoch": 0.21807513900408565,
      "grad_norm": 0.3075382709503174,
      "learning_rate": 1.9433542507894668e-05,
      "loss": 0.5849,
      "step": 7099
    },
    {
      "epoch": 0.2181058581390348,
      "grad_norm": 0.30569988489151,
      "learning_rate": 1.9433382151635757e-05,
      "loss": 0.5826,
      "step": 7100
    },
    {
      "epoch": 0.21813657727398397,
      "grad_norm": 0.36008334159851074,
      "learning_rate": 1.9433221773344523e-05,
      "loss": 0.6038,
      "step": 7101
    },
    {
      "epoch": 0.21816729640893312,
      "grad_norm": 0.3342386782169342,
      "learning_rate": 1.9433061373021342e-05,
      "loss": 0.5419,
      "step": 7102
    },
    {
      "epoch": 0.2181980155438823,
      "grad_norm": 0.32767513394355774,
      "learning_rate": 1.9432900950666583e-05,
      "loss": 0.5714,
      "step": 7103
    },
    {
      "epoch": 0.21822873467883144,
      "grad_norm": 0.34108367562294006,
      "learning_rate": 1.943274050628063e-05,
      "loss": 0.6162,
      "step": 7104
    },
    {
      "epoch": 0.2182594538137806,
      "grad_norm": 0.37323689460754395,
      "learning_rate": 1.9432580039863854e-05,
      "loss": 0.5639,
      "step": 7105
    },
    {
      "epoch": 0.21829017294872977,
      "grad_norm": 0.3200756907463074,
      "learning_rate": 1.9432419551416625e-05,
      "loss": 0.609,
      "step": 7106
    },
    {
      "epoch": 0.2183208920836789,
      "grad_norm": 0.3640434145927429,
      "learning_rate": 1.943225904093932e-05,
      "loss": 0.5655,
      "step": 7107
    },
    {
      "epoch": 0.2183516112186281,
      "grad_norm": 0.3428247570991516,
      "learning_rate": 1.9432098508432317e-05,
      "loss": 0.6397,
      "step": 7108
    },
    {
      "epoch": 0.21838233035357724,
      "grad_norm": 0.3588607907295227,
      "learning_rate": 1.9431937953895993e-05,
      "loss": 0.6421,
      "step": 7109
    },
    {
      "epoch": 0.2184130494885264,
      "grad_norm": 0.3374510109424591,
      "learning_rate": 1.943177737733071e-05,
      "loss": 0.6247,
      "step": 7110
    },
    {
      "epoch": 0.21844376862347556,
      "grad_norm": 0.39502817392349243,
      "learning_rate": 1.9431616778736863e-05,
      "loss": 0.6301,
      "step": 7111
    },
    {
      "epoch": 0.21847448775842473,
      "grad_norm": 0.3737110197544098,
      "learning_rate": 1.943145615811481e-05,
      "loss": 0.5209,
      "step": 7112
    },
    {
      "epoch": 0.21850520689337388,
      "grad_norm": 0.36680659651756287,
      "learning_rate": 1.9431295515464934e-05,
      "loss": 0.6578,
      "step": 7113
    },
    {
      "epoch": 0.21853592602832303,
      "grad_norm": 0.3465538024902344,
      "learning_rate": 1.9431134850787608e-05,
      "loss": 0.5992,
      "step": 7114
    },
    {
      "epoch": 0.2185666451632722,
      "grad_norm": 0.32986098527908325,
      "learning_rate": 1.9430974164083207e-05,
      "loss": 0.6117,
      "step": 7115
    },
    {
      "epoch": 0.21859736429822135,
      "grad_norm": 0.3635178804397583,
      "learning_rate": 1.943081345535211e-05,
      "loss": 0.5698,
      "step": 7116
    },
    {
      "epoch": 0.21862808343317053,
      "grad_norm": 0.3401992619037628,
      "learning_rate": 1.9430652724594686e-05,
      "loss": 0.5809,
      "step": 7117
    },
    {
      "epoch": 0.21865880256811968,
      "grad_norm": 0.3635712265968323,
      "learning_rate": 1.9430491971811317e-05,
      "loss": 0.6257,
      "step": 7118
    },
    {
      "epoch": 0.21868952170306885,
      "grad_norm": 0.3290877640247345,
      "learning_rate": 1.9430331197002375e-05,
      "loss": 0.6396,
      "step": 7119
    },
    {
      "epoch": 0.218720240838018,
      "grad_norm": 0.36079996824264526,
      "learning_rate": 1.9430170400168234e-05,
      "loss": 0.5824,
      "step": 7120
    },
    {
      "epoch": 0.21875095997296717,
      "grad_norm": 0.3184202313423157,
      "learning_rate": 1.9430009581309272e-05,
      "loss": 0.5777,
      "step": 7121
    },
    {
      "epoch": 0.21878167910791632,
      "grad_norm": 0.3563358187675476,
      "learning_rate": 1.9429848740425865e-05,
      "loss": 0.6189,
      "step": 7122
    },
    {
      "epoch": 0.21881239824286547,
      "grad_norm": 0.3160257637500763,
      "learning_rate": 1.9429687877518387e-05,
      "loss": 0.5865,
      "step": 7123
    },
    {
      "epoch": 0.21884311737781464,
      "grad_norm": 0.33754220604896545,
      "learning_rate": 1.9429526992587216e-05,
      "loss": 0.6129,
      "step": 7124
    },
    {
      "epoch": 0.2188738365127638,
      "grad_norm": 0.3504053056240082,
      "learning_rate": 1.9429366085632725e-05,
      "loss": 0.5329,
      "step": 7125
    },
    {
      "epoch": 0.21890455564771297,
      "grad_norm": 0.2995401918888092,
      "learning_rate": 1.9429205156655292e-05,
      "loss": 0.629,
      "step": 7126
    },
    {
      "epoch": 0.21893527478266211,
      "grad_norm": 0.3723814785480499,
      "learning_rate": 1.9429044205655293e-05,
      "loss": 0.6091,
      "step": 7127
    },
    {
      "epoch": 0.2189659939176113,
      "grad_norm": 0.3615216016769409,
      "learning_rate": 1.94288832326331e-05,
      "loss": 0.6404,
      "step": 7128
    },
    {
      "epoch": 0.21899671305256044,
      "grad_norm": 0.32463061809539795,
      "learning_rate": 1.9428722237589092e-05,
      "loss": 0.5277,
      "step": 7129
    },
    {
      "epoch": 0.2190274321875096,
      "grad_norm": 0.32243165373802185,
      "learning_rate": 1.9428561220523644e-05,
      "loss": 0.5582,
      "step": 7130
    },
    {
      "epoch": 0.21905815132245876,
      "grad_norm": 0.35075879096984863,
      "learning_rate": 1.9428400181437132e-05,
      "loss": 0.6402,
      "step": 7131
    },
    {
      "epoch": 0.2190888704574079,
      "grad_norm": 0.3256359100341797,
      "learning_rate": 1.9428239120329936e-05,
      "loss": 0.6862,
      "step": 7132
    },
    {
      "epoch": 0.21911958959235708,
      "grad_norm": 0.3349444568157196,
      "learning_rate": 1.9428078037202427e-05,
      "loss": 0.6368,
      "step": 7133
    },
    {
      "epoch": 0.21915030872730623,
      "grad_norm": 0.33468306064605713,
      "learning_rate": 1.9427916932054985e-05,
      "loss": 0.5385,
      "step": 7134
    },
    {
      "epoch": 0.2191810278622554,
      "grad_norm": 0.32043999433517456,
      "learning_rate": 1.9427755804887984e-05,
      "loss": 0.6236,
      "step": 7135
    },
    {
      "epoch": 0.21921174699720455,
      "grad_norm": 0.3287082314491272,
      "learning_rate": 1.94275946557018e-05,
      "loss": 0.5075,
      "step": 7136
    },
    {
      "epoch": 0.21924246613215373,
      "grad_norm": 0.34141165018081665,
      "learning_rate": 1.9427433484496808e-05,
      "loss": 0.5898,
      "step": 7137
    },
    {
      "epoch": 0.21927318526710288,
      "grad_norm": 0.3634958267211914,
      "learning_rate": 1.942727229127339e-05,
      "loss": 0.6476,
      "step": 7138
    },
    {
      "epoch": 0.21930390440205202,
      "grad_norm": 0.33529090881347656,
      "learning_rate": 1.942711107603192e-05,
      "loss": 0.6174,
      "step": 7139
    },
    {
      "epoch": 0.2193346235370012,
      "grad_norm": 0.33158114552497864,
      "learning_rate": 1.942694983877277e-05,
      "loss": 0.6182,
      "step": 7140
    },
    {
      "epoch": 0.21936534267195035,
      "grad_norm": 0.4355070888996124,
      "learning_rate": 1.9426788579496323e-05,
      "loss": 0.5697,
      "step": 7141
    },
    {
      "epoch": 0.21939606180689952,
      "grad_norm": 0.3543454706668854,
      "learning_rate": 1.9426627298202955e-05,
      "loss": 0.5054,
      "step": 7142
    },
    {
      "epoch": 0.21942678094184867,
      "grad_norm": 0.33288151025772095,
      "learning_rate": 1.9426465994893037e-05,
      "loss": 0.5994,
      "step": 7143
    },
    {
      "epoch": 0.21945750007679785,
      "grad_norm": 0.3313842713832855,
      "learning_rate": 1.942630466956695e-05,
      "loss": 0.4747,
      "step": 7144
    },
    {
      "epoch": 0.219488219211747,
      "grad_norm": 0.3558490574359894,
      "learning_rate": 1.942614332222507e-05,
      "loss": 0.5928,
      "step": 7145
    },
    {
      "epoch": 0.21951893834669617,
      "grad_norm": 0.3685089349746704,
      "learning_rate": 1.9425981952867774e-05,
      "loss": 0.5504,
      "step": 7146
    },
    {
      "epoch": 0.21954965748164532,
      "grad_norm": 0.3376852869987488,
      "learning_rate": 1.942582056149544e-05,
      "loss": 0.5733,
      "step": 7147
    },
    {
      "epoch": 0.21958037661659446,
      "grad_norm": 0.37337741255760193,
      "learning_rate": 1.942565914810844e-05,
      "loss": 0.6297,
      "step": 7148
    },
    {
      "epoch": 0.21961109575154364,
      "grad_norm": 0.3233986794948578,
      "learning_rate": 1.9425497712707163e-05,
      "loss": 0.4732,
      "step": 7149
    },
    {
      "epoch": 0.2196418148864928,
      "grad_norm": 0.32665523886680603,
      "learning_rate": 1.942533625529197e-05,
      "loss": 0.6151,
      "step": 7150
    },
    {
      "epoch": 0.21967253402144196,
      "grad_norm": 0.35440289974212646,
      "learning_rate": 1.942517477586325e-05,
      "loss": 0.6057,
      "step": 7151
    },
    {
      "epoch": 0.2197032531563911,
      "grad_norm": 0.3534461557865143,
      "learning_rate": 1.9425013274421375e-05,
      "loss": 0.5994,
      "step": 7152
    },
    {
      "epoch": 0.21973397229134028,
      "grad_norm": 0.3420439064502716,
      "learning_rate": 1.9424851750966723e-05,
      "loss": 0.5884,
      "step": 7153
    },
    {
      "epoch": 0.21976469142628943,
      "grad_norm": 0.3618740141391754,
      "learning_rate": 1.9424690205499673e-05,
      "loss": 0.6518,
      "step": 7154
    },
    {
      "epoch": 0.2197954105612386,
      "grad_norm": 0.35907652974128723,
      "learning_rate": 1.9424528638020598e-05,
      "loss": 0.5965,
      "step": 7155
    },
    {
      "epoch": 0.21982612969618776,
      "grad_norm": 0.3389209508895874,
      "learning_rate": 1.9424367048529878e-05,
      "loss": 0.6639,
      "step": 7156
    },
    {
      "epoch": 0.2198568488311369,
      "grad_norm": 0.34781283140182495,
      "learning_rate": 1.9424205437027896e-05,
      "loss": 0.5782,
      "step": 7157
    },
    {
      "epoch": 0.21988756796608608,
      "grad_norm": 0.3645617961883545,
      "learning_rate": 1.9424043803515017e-05,
      "loss": 0.5413,
      "step": 7158
    },
    {
      "epoch": 0.21991828710103523,
      "grad_norm": 0.3772139847278595,
      "learning_rate": 1.9423882147991628e-05,
      "loss": 0.6291,
      "step": 7159
    },
    {
      "epoch": 0.2199490062359844,
      "grad_norm": 0.35135146975517273,
      "learning_rate": 1.9423720470458104e-05,
      "loss": 0.6472,
      "step": 7160
    },
    {
      "epoch": 0.21997972537093355,
      "grad_norm": 0.39760822057724,
      "learning_rate": 1.9423558770914823e-05,
      "loss": 0.5996,
      "step": 7161
    },
    {
      "epoch": 0.22001044450588272,
      "grad_norm": 0.3335035443305969,
      "learning_rate": 1.9423397049362163e-05,
      "loss": 0.5843,
      "step": 7162
    },
    {
      "epoch": 0.22004116364083187,
      "grad_norm": 0.3445531129837036,
      "learning_rate": 1.9423235305800503e-05,
      "loss": 0.5666,
      "step": 7163
    },
    {
      "epoch": 0.22007188277578105,
      "grad_norm": 0.5594555735588074,
      "learning_rate": 1.9423073540230214e-05,
      "loss": 0.6114,
      "step": 7164
    },
    {
      "epoch": 0.2201026019107302,
      "grad_norm": 0.3134543001651764,
      "learning_rate": 1.9422911752651685e-05,
      "loss": 0.6084,
      "step": 7165
    },
    {
      "epoch": 0.22013332104567934,
      "grad_norm": 0.3298882246017456,
      "learning_rate": 1.942274994306528e-05,
      "loss": 0.6003,
      "step": 7166
    },
    {
      "epoch": 0.22016404018062852,
      "grad_norm": 0.3763889670372009,
      "learning_rate": 1.942258811147139e-05,
      "loss": 0.5665,
      "step": 7167
    },
    {
      "epoch": 0.22019475931557767,
      "grad_norm": 0.3242780864238739,
      "learning_rate": 1.9422426257870385e-05,
      "loss": 0.5714,
      "step": 7168
    },
    {
      "epoch": 0.22022547845052684,
      "grad_norm": 0.3673727512359619,
      "learning_rate": 1.9422264382262646e-05,
      "loss": 0.5177,
      "step": 7169
    },
    {
      "epoch": 0.220256197585476,
      "grad_norm": 0.3830263912677765,
      "learning_rate": 1.942210248464855e-05,
      "loss": 0.6409,
      "step": 7170
    },
    {
      "epoch": 0.22028691672042516,
      "grad_norm": 0.3231630325317383,
      "learning_rate": 1.9421940565028476e-05,
      "loss": 0.5445,
      "step": 7171
    },
    {
      "epoch": 0.2203176358553743,
      "grad_norm": 0.3969411253929138,
      "learning_rate": 1.9421778623402802e-05,
      "loss": 0.5669,
      "step": 7172
    },
    {
      "epoch": 0.2203483549903235,
      "grad_norm": 0.3272370994091034,
      "learning_rate": 1.9421616659771907e-05,
      "loss": 0.6428,
      "step": 7173
    },
    {
      "epoch": 0.22037907412527263,
      "grad_norm": 0.368362158536911,
      "learning_rate": 1.9421454674136166e-05,
      "loss": 0.5889,
      "step": 7174
    },
    {
      "epoch": 0.22040979326022178,
      "grad_norm": 0.3434748947620392,
      "learning_rate": 1.9421292666495963e-05,
      "loss": 0.6027,
      "step": 7175
    },
    {
      "epoch": 0.22044051239517096,
      "grad_norm": 0.3716348707675934,
      "learning_rate": 1.942113063685167e-05,
      "loss": 0.5897,
      "step": 7176
    },
    {
      "epoch": 0.2204712315301201,
      "grad_norm": 0.31760644912719727,
      "learning_rate": 1.9420968585203667e-05,
      "loss": 0.5359,
      "step": 7177
    },
    {
      "epoch": 0.22050195066506928,
      "grad_norm": 0.4329708218574524,
      "learning_rate": 1.9420806511552337e-05,
      "loss": 0.6072,
      "step": 7178
    },
    {
      "epoch": 0.22053266980001843,
      "grad_norm": 0.3030519187450409,
      "learning_rate": 1.9420644415898055e-05,
      "loss": 0.4949,
      "step": 7179
    },
    {
      "epoch": 0.2205633889349676,
      "grad_norm": 0.35866090655326843,
      "learning_rate": 1.94204822982412e-05,
      "loss": 0.5449,
      "step": 7180
    },
    {
      "epoch": 0.22059410806991675,
      "grad_norm": 0.31370922923088074,
      "learning_rate": 1.942032015858215e-05,
      "loss": 0.4882,
      "step": 7181
    },
    {
      "epoch": 0.2206248272048659,
      "grad_norm": 0.3625671863555908,
      "learning_rate": 1.9420157996921285e-05,
      "loss": 0.5585,
      "step": 7182
    },
    {
      "epoch": 0.22065554633981507,
      "grad_norm": 0.3427303433418274,
      "learning_rate": 1.9419995813258982e-05,
      "loss": 0.5864,
      "step": 7183
    },
    {
      "epoch": 0.22068626547476422,
      "grad_norm": 0.32191741466522217,
      "learning_rate": 1.9419833607595626e-05,
      "loss": 0.5781,
      "step": 7184
    },
    {
      "epoch": 0.2207169846097134,
      "grad_norm": 0.35500389337539673,
      "learning_rate": 1.9419671379931584e-05,
      "loss": 0.6185,
      "step": 7185
    },
    {
      "epoch": 0.22074770374466254,
      "grad_norm": 0.3530677258968353,
      "learning_rate": 1.9419509130267244e-05,
      "loss": 0.6257,
      "step": 7186
    },
    {
      "epoch": 0.22077842287961172,
      "grad_norm": 0.3489549458026886,
      "learning_rate": 1.941934685860298e-05,
      "loss": 0.6493,
      "step": 7187
    },
    {
      "epoch": 0.22080914201456087,
      "grad_norm": 0.34287285804748535,
      "learning_rate": 1.9419184564939176e-05,
      "loss": 0.6074,
      "step": 7188
    },
    {
      "epoch": 0.22083986114951004,
      "grad_norm": 0.35013750195503235,
      "learning_rate": 1.941902224927621e-05,
      "loss": 0.5663,
      "step": 7189
    },
    {
      "epoch": 0.2208705802844592,
      "grad_norm": 0.3187258541584015,
      "learning_rate": 1.9418859911614462e-05,
      "loss": 0.5749,
      "step": 7190
    },
    {
      "epoch": 0.22090129941940834,
      "grad_norm": 0.31968042254447937,
      "learning_rate": 1.9418697551954305e-05,
      "loss": 0.6362,
      "step": 7191
    },
    {
      "epoch": 0.2209320185543575,
      "grad_norm": 0.3210238218307495,
      "learning_rate": 1.9418535170296123e-05,
      "loss": 0.5818,
      "step": 7192
    },
    {
      "epoch": 0.22096273768930666,
      "grad_norm": 0.32481810450553894,
      "learning_rate": 1.941837276664029e-05,
      "loss": 0.5417,
      "step": 7193
    },
    {
      "epoch": 0.22099345682425584,
      "grad_norm": 0.3374452292919159,
      "learning_rate": 1.9418210340987195e-05,
      "loss": 0.5836,
      "step": 7194
    },
    {
      "epoch": 0.22102417595920498,
      "grad_norm": 0.3190440237522125,
      "learning_rate": 1.941804789333721e-05,
      "loss": 0.5843,
      "step": 7195
    },
    {
      "epoch": 0.22105489509415416,
      "grad_norm": 0.36927202343940735,
      "learning_rate": 1.941788542369072e-05,
      "loss": 0.5106,
      "step": 7196
    },
    {
      "epoch": 0.2210856142291033,
      "grad_norm": 0.2898714244365692,
      "learning_rate": 1.9417722932048095e-05,
      "loss": 0.4868,
      "step": 7197
    },
    {
      "epoch": 0.22111633336405248,
      "grad_norm": 0.3173111379146576,
      "learning_rate": 1.9417560418409725e-05,
      "loss": 0.5629,
      "step": 7198
    },
    {
      "epoch": 0.22114705249900163,
      "grad_norm": 0.35951098799705505,
      "learning_rate": 1.9417397882775982e-05,
      "loss": 0.6421,
      "step": 7199
    },
    {
      "epoch": 0.22117777163395078,
      "grad_norm": 0.34194108843803406,
      "learning_rate": 1.941723532514725e-05,
      "loss": 0.5919,
      "step": 7200
    },
    {
      "epoch": 0.22120849076889995,
      "grad_norm": 0.31767261028289795,
      "learning_rate": 1.9417072745523903e-05,
      "loss": 0.5718,
      "step": 7201
    },
    {
      "epoch": 0.2212392099038491,
      "grad_norm": 0.32560548186302185,
      "learning_rate": 1.941691014390633e-05,
      "loss": 0.5907,
      "step": 7202
    },
    {
      "epoch": 0.22126992903879827,
      "grad_norm": 0.3510071337223053,
      "learning_rate": 1.9416747520294906e-05,
      "loss": 0.6011,
      "step": 7203
    },
    {
      "epoch": 0.22130064817374742,
      "grad_norm": 0.36088430881500244,
      "learning_rate": 1.941658487469001e-05,
      "loss": 0.6563,
      "step": 7204
    },
    {
      "epoch": 0.2213313673086966,
      "grad_norm": 0.32846441864967346,
      "learning_rate": 1.941642220709202e-05,
      "loss": 0.6323,
      "step": 7205
    },
    {
      "epoch": 0.22136208644364574,
      "grad_norm": 0.3245893716812134,
      "learning_rate": 1.941625951750132e-05,
      "loss": 0.5742,
      "step": 7206
    },
    {
      "epoch": 0.22139280557859492,
      "grad_norm": 0.33086419105529785,
      "learning_rate": 1.9416096805918284e-05,
      "loss": 0.6249,
      "step": 7207
    },
    {
      "epoch": 0.22142352471354407,
      "grad_norm": 0.3194262385368347,
      "learning_rate": 1.94159340723433e-05,
      "loss": 0.5829,
      "step": 7208
    },
    {
      "epoch": 0.22145424384849322,
      "grad_norm": 0.3440783619880676,
      "learning_rate": 1.9415771316776748e-05,
      "loss": 0.5817,
      "step": 7209
    },
    {
      "epoch": 0.2214849629834424,
      "grad_norm": 0.3303492069244385,
      "learning_rate": 1.9415608539219e-05,
      "loss": 0.5575,
      "step": 7210
    },
    {
      "epoch": 0.22151568211839154,
      "grad_norm": 0.333050936460495,
      "learning_rate": 1.941544573967044e-05,
      "loss": 0.6176,
      "step": 7211
    },
    {
      "epoch": 0.2215464012533407,
      "grad_norm": 0.335805743932724,
      "learning_rate": 1.9415282918131454e-05,
      "loss": 0.5326,
      "step": 7212
    },
    {
      "epoch": 0.22157712038828986,
      "grad_norm": 0.41430655121803284,
      "learning_rate": 1.9415120074602415e-05,
      "loss": 0.631,
      "step": 7213
    },
    {
      "epoch": 0.22160783952323904,
      "grad_norm": 0.33804017305374146,
      "learning_rate": 1.9414957209083702e-05,
      "loss": 0.5758,
      "step": 7214
    },
    {
      "epoch": 0.22163855865818818,
      "grad_norm": 0.3440191447734833,
      "learning_rate": 1.9414794321575702e-05,
      "loss": 0.5132,
      "step": 7215
    },
    {
      "epoch": 0.22166927779313733,
      "grad_norm": 0.3468224108219147,
      "learning_rate": 1.941463141207879e-05,
      "loss": 0.5191,
      "step": 7216
    },
    {
      "epoch": 0.2216999969280865,
      "grad_norm": 0.3893570601940155,
      "learning_rate": 1.941446848059335e-05,
      "loss": 0.6779,
      "step": 7217
    },
    {
      "epoch": 0.22173071606303565,
      "grad_norm": 0.3548140823841095,
      "learning_rate": 1.9414305527119762e-05,
      "loss": 0.5778,
      "step": 7218
    },
    {
      "epoch": 0.22176143519798483,
      "grad_norm": 0.3504079580307007,
      "learning_rate": 1.9414142551658406e-05,
      "loss": 0.5968,
      "step": 7219
    },
    {
      "epoch": 0.22179215433293398,
      "grad_norm": 0.39162158966064453,
      "learning_rate": 1.9413979554209663e-05,
      "loss": 0.594,
      "step": 7220
    },
    {
      "epoch": 0.22182287346788315,
      "grad_norm": 0.4032825231552124,
      "learning_rate": 1.9413816534773913e-05,
      "loss": 0.6314,
      "step": 7221
    },
    {
      "epoch": 0.2218535926028323,
      "grad_norm": 0.31971004605293274,
      "learning_rate": 1.9413653493351536e-05,
      "loss": 0.5183,
      "step": 7222
    },
    {
      "epoch": 0.22188431173778148,
      "grad_norm": 0.316476047039032,
      "learning_rate": 1.9413490429942915e-05,
      "loss": 0.5556,
      "step": 7223
    },
    {
      "epoch": 0.22191503087273062,
      "grad_norm": 0.30760884284973145,
      "learning_rate": 1.941332734454843e-05,
      "loss": 0.5051,
      "step": 7224
    },
    {
      "epoch": 0.22194575000767977,
      "grad_norm": 0.3040778934955597,
      "learning_rate": 1.9413164237168457e-05,
      "loss": 0.4794,
      "step": 7225
    },
    {
      "epoch": 0.22197646914262895,
      "grad_norm": 0.3265877962112427,
      "learning_rate": 1.9413001107803386e-05,
      "loss": 0.4958,
      "step": 7226
    },
    {
      "epoch": 0.2220071882775781,
      "grad_norm": 0.44548872113227844,
      "learning_rate": 1.9412837956453595e-05,
      "loss": 0.6624,
      "step": 7227
    },
    {
      "epoch": 0.22203790741252727,
      "grad_norm": 0.3187565207481384,
      "learning_rate": 1.941267478311946e-05,
      "loss": 0.59,
      "step": 7228
    },
    {
      "epoch": 0.22206862654747642,
      "grad_norm": 0.35425472259521484,
      "learning_rate": 1.9412511587801368e-05,
      "loss": 0.6078,
      "step": 7229
    },
    {
      "epoch": 0.2220993456824256,
      "grad_norm": 0.37612730264663696,
      "learning_rate": 1.9412348370499697e-05,
      "loss": 0.6622,
      "step": 7230
    },
    {
      "epoch": 0.22213006481737474,
      "grad_norm": 0.3793788254261017,
      "learning_rate": 1.941218513121483e-05,
      "loss": 0.5876,
      "step": 7231
    },
    {
      "epoch": 0.22216078395232391,
      "grad_norm": 0.3921734392642975,
      "learning_rate": 1.941202186994714e-05,
      "loss": 0.5966,
      "step": 7232
    },
    {
      "epoch": 0.22219150308727306,
      "grad_norm": 0.3476913273334503,
      "learning_rate": 1.9411858586697027e-05,
      "loss": 0.5956,
      "step": 7233
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.3753911256790161,
      "learning_rate": 1.9411695281464853e-05,
      "loss": 0.5897,
      "step": 7234
    },
    {
      "epoch": 0.22225294135717139,
      "grad_norm": 0.3128328323364258,
      "learning_rate": 1.941153195425101e-05,
      "loss": 0.4938,
      "step": 7235
    },
    {
      "epoch": 0.22228366049212053,
      "grad_norm": 0.32388758659362793,
      "learning_rate": 1.9411368605055876e-05,
      "loss": 0.5559,
      "step": 7236
    },
    {
      "epoch": 0.2223143796270697,
      "grad_norm": 0.36194419860839844,
      "learning_rate": 1.9411205233879836e-05,
      "loss": 0.5585,
      "step": 7237
    },
    {
      "epoch": 0.22234509876201886,
      "grad_norm": 0.30722498893737793,
      "learning_rate": 1.9411041840723267e-05,
      "loss": 0.5528,
      "step": 7238
    },
    {
      "epoch": 0.22237581789696803,
      "grad_norm": 0.33886101841926575,
      "learning_rate": 1.941087842558655e-05,
      "loss": 0.6759,
      "step": 7239
    },
    {
      "epoch": 0.22240653703191718,
      "grad_norm": 0.3695860207080841,
      "learning_rate": 1.9410714988470074e-05,
      "loss": 0.6475,
      "step": 7240
    },
    {
      "epoch": 0.22243725616686635,
      "grad_norm": 0.33189883828163147,
      "learning_rate": 1.9410551529374212e-05,
      "loss": 0.5527,
      "step": 7241
    },
    {
      "epoch": 0.2224679753018155,
      "grad_norm": 0.3799692690372467,
      "learning_rate": 1.941038804829935e-05,
      "loss": 0.6182,
      "step": 7242
    },
    {
      "epoch": 0.22249869443676465,
      "grad_norm": 0.37830138206481934,
      "learning_rate": 1.9410224545245874e-05,
      "loss": 0.5604,
      "step": 7243
    },
    {
      "epoch": 0.22252941357171382,
      "grad_norm": 0.3199932873249054,
      "learning_rate": 1.9410061020214156e-05,
      "loss": 0.5799,
      "step": 7244
    },
    {
      "epoch": 0.22256013270666297,
      "grad_norm": 0.34440889954566956,
      "learning_rate": 1.9409897473204585e-05,
      "loss": 0.5232,
      "step": 7245
    },
    {
      "epoch": 0.22259085184161215,
      "grad_norm": 0.35764384269714355,
      "learning_rate": 1.9409733904217543e-05,
      "loss": 0.5849,
      "step": 7246
    },
    {
      "epoch": 0.2226215709765613,
      "grad_norm": 0.35114040970802307,
      "learning_rate": 1.940957031325341e-05,
      "loss": 0.6643,
      "step": 7247
    },
    {
      "epoch": 0.22265229011151047,
      "grad_norm": 0.3245311975479126,
      "learning_rate": 1.9409406700312567e-05,
      "loss": 0.5557,
      "step": 7248
    },
    {
      "epoch": 0.22268300924645962,
      "grad_norm": 0.33857250213623047,
      "learning_rate": 1.9409243065395397e-05,
      "loss": 0.5887,
      "step": 7249
    },
    {
      "epoch": 0.2227137283814088,
      "grad_norm": 0.31268182396888733,
      "learning_rate": 1.9409079408502286e-05,
      "loss": 0.4847,
      "step": 7250
    },
    {
      "epoch": 0.22274444751635794,
      "grad_norm": 0.35600247979164124,
      "learning_rate": 1.940891572963361e-05,
      "loss": 0.5507,
      "step": 7251
    },
    {
      "epoch": 0.2227751666513071,
      "grad_norm": 0.40057405829429626,
      "learning_rate": 1.9408752028789754e-05,
      "loss": 0.6404,
      "step": 7252
    },
    {
      "epoch": 0.22280588578625626,
      "grad_norm": 0.32984012365341187,
      "learning_rate": 1.9408588305971102e-05,
      "loss": 0.6211,
      "step": 7253
    },
    {
      "epoch": 0.2228366049212054,
      "grad_norm": 0.35753247141838074,
      "learning_rate": 1.9408424561178034e-05,
      "loss": 0.5843,
      "step": 7254
    },
    {
      "epoch": 0.2228673240561546,
      "grad_norm": 0.3563820421695709,
      "learning_rate": 1.9408260794410933e-05,
      "loss": 0.6002,
      "step": 7255
    },
    {
      "epoch": 0.22289804319110373,
      "grad_norm": 0.3608687222003937,
      "learning_rate": 1.940809700567018e-05,
      "loss": 0.5862,
      "step": 7256
    },
    {
      "epoch": 0.2229287623260529,
      "grad_norm": 0.446508526802063,
      "learning_rate": 1.9407933194956164e-05,
      "loss": 0.6057,
      "step": 7257
    },
    {
      "epoch": 0.22295948146100206,
      "grad_norm": 0.33558741211891174,
      "learning_rate": 1.940776936226926e-05,
      "loss": 0.6679,
      "step": 7258
    },
    {
      "epoch": 0.2229902005959512,
      "grad_norm": 0.4057655334472656,
      "learning_rate": 1.9407605507609854e-05,
      "loss": 0.5358,
      "step": 7259
    },
    {
      "epoch": 0.22302091973090038,
      "grad_norm": 0.37614864110946655,
      "learning_rate": 1.940744163097833e-05,
      "loss": 0.6136,
      "step": 7260
    },
    {
      "epoch": 0.22305163886584953,
      "grad_norm": 0.34239548444747925,
      "learning_rate": 1.940727773237507e-05,
      "loss": 0.6088,
      "step": 7261
    },
    {
      "epoch": 0.2230823580007987,
      "grad_norm": 0.32064956426620483,
      "learning_rate": 1.9407113811800454e-05,
      "loss": 0.5675,
      "step": 7262
    },
    {
      "epoch": 0.22311307713574785,
      "grad_norm": 0.33508574962615967,
      "learning_rate": 1.9406949869254866e-05,
      "loss": 0.5856,
      "step": 7263
    },
    {
      "epoch": 0.22314379627069703,
      "grad_norm": 0.34020787477493286,
      "learning_rate": 1.9406785904738687e-05,
      "loss": 0.5811,
      "step": 7264
    },
    {
      "epoch": 0.22317451540564617,
      "grad_norm": 0.3702728748321533,
      "learning_rate": 1.9406621918252306e-05,
      "loss": 0.6372,
      "step": 7265
    },
    {
      "epoch": 0.22320523454059535,
      "grad_norm": 0.3208499550819397,
      "learning_rate": 1.9406457909796104e-05,
      "loss": 0.659,
      "step": 7266
    },
    {
      "epoch": 0.2232359536755445,
      "grad_norm": 0.33966052532196045,
      "learning_rate": 1.9406293879370458e-05,
      "loss": 0.6218,
      "step": 7267
    },
    {
      "epoch": 0.22326667281049364,
      "grad_norm": 0.43061530590057373,
      "learning_rate": 1.9406129826975762e-05,
      "loss": 0.6374,
      "step": 7268
    },
    {
      "epoch": 0.22329739194544282,
      "grad_norm": 0.3767540156841278,
      "learning_rate": 1.9405965752612387e-05,
      "loss": 0.5988,
      "step": 7269
    },
    {
      "epoch": 0.22332811108039197,
      "grad_norm": 0.3326537013053894,
      "learning_rate": 1.9405801656280724e-05,
      "loss": 0.5384,
      "step": 7270
    },
    {
      "epoch": 0.22335883021534114,
      "grad_norm": 0.35221877694129944,
      "learning_rate": 1.9405637537981156e-05,
      "loss": 0.624,
      "step": 7271
    },
    {
      "epoch": 0.2233895493502903,
      "grad_norm": 0.31498655676841736,
      "learning_rate": 1.9405473397714063e-05,
      "loss": 0.5959,
      "step": 7272
    },
    {
      "epoch": 0.22342026848523946,
      "grad_norm": 0.9106410145759583,
      "learning_rate": 1.940530923547983e-05,
      "loss": 0.6769,
      "step": 7273
    },
    {
      "epoch": 0.2234509876201886,
      "grad_norm": 0.3679969906806946,
      "learning_rate": 1.940514505127884e-05,
      "loss": 0.6356,
      "step": 7274
    },
    {
      "epoch": 0.2234817067551378,
      "grad_norm": 0.353985995054245,
      "learning_rate": 1.940498084511148e-05,
      "loss": 0.5396,
      "step": 7275
    },
    {
      "epoch": 0.22351242589008694,
      "grad_norm": 0.37256819009780884,
      "learning_rate": 1.940481661697813e-05,
      "loss": 0.6255,
      "step": 7276
    },
    {
      "epoch": 0.22354314502503608,
      "grad_norm": 0.31664255261421204,
      "learning_rate": 1.9404652366879168e-05,
      "loss": 0.5754,
      "step": 7277
    },
    {
      "epoch": 0.22357386415998526,
      "grad_norm": 0.377149760723114,
      "learning_rate": 1.940448809481499e-05,
      "loss": 0.5047,
      "step": 7278
    },
    {
      "epoch": 0.2236045832949344,
      "grad_norm": 0.38497188687324524,
      "learning_rate": 1.9404323800785968e-05,
      "loss": 0.5563,
      "step": 7279
    },
    {
      "epoch": 0.22363530242988358,
      "grad_norm": 0.41140514612197876,
      "learning_rate": 1.9404159484792495e-05,
      "loss": 0.5729,
      "step": 7280
    },
    {
      "epoch": 0.22366602156483273,
      "grad_norm": 0.32804861664772034,
      "learning_rate": 1.940399514683495e-05,
      "loss": 0.5744,
      "step": 7281
    },
    {
      "epoch": 0.2236967406997819,
      "grad_norm": 0.33464422821998596,
      "learning_rate": 1.9403830786913714e-05,
      "loss": 0.5989,
      "step": 7282
    },
    {
      "epoch": 0.22372745983473105,
      "grad_norm": 0.3336753845214844,
      "learning_rate": 1.940366640502918e-05,
      "loss": 0.6108,
      "step": 7283
    },
    {
      "epoch": 0.22375817896968023,
      "grad_norm": 0.3749425709247589,
      "learning_rate": 1.9403502001181723e-05,
      "loss": 0.573,
      "step": 7284
    },
    {
      "epoch": 0.22378889810462937,
      "grad_norm": 0.3356497287750244,
      "learning_rate": 1.9403337575371733e-05,
      "loss": 0.5221,
      "step": 7285
    },
    {
      "epoch": 0.22381961723957852,
      "grad_norm": 0.36244598031044006,
      "learning_rate": 1.9403173127599588e-05,
      "loss": 0.5863,
      "step": 7286
    },
    {
      "epoch": 0.2238503363745277,
      "grad_norm": 0.34321773052215576,
      "learning_rate": 1.9403008657865678e-05,
      "loss": 0.5795,
      "step": 7287
    },
    {
      "epoch": 0.22388105550947685,
      "grad_norm": 0.36272549629211426,
      "learning_rate": 1.9402844166170385e-05,
      "loss": 0.6019,
      "step": 7288
    },
    {
      "epoch": 0.22391177464442602,
      "grad_norm": 0.3347555696964264,
      "learning_rate": 1.9402679652514093e-05,
      "loss": 0.6483,
      "step": 7289
    },
    {
      "epoch": 0.22394249377937517,
      "grad_norm": 0.33956190943717957,
      "learning_rate": 1.940251511689718e-05,
      "loss": 0.5373,
      "step": 7290
    },
    {
      "epoch": 0.22397321291432434,
      "grad_norm": 0.3172222971916199,
      "learning_rate": 1.9402350559320045e-05,
      "loss": 0.5624,
      "step": 7291
    },
    {
      "epoch": 0.2240039320492735,
      "grad_norm": 0.35386818647384644,
      "learning_rate": 1.9402185979783055e-05,
      "loss": 0.6154,
      "step": 7292
    },
    {
      "epoch": 0.22403465118422264,
      "grad_norm": 0.32279449701309204,
      "learning_rate": 1.9402021378286607e-05,
      "loss": 0.5727,
      "step": 7293
    },
    {
      "epoch": 0.2240653703191718,
      "grad_norm": 0.34865015745162964,
      "learning_rate": 1.9401856754831084e-05,
      "loss": 0.6071,
      "step": 7294
    },
    {
      "epoch": 0.22409608945412096,
      "grad_norm": 0.32429832220077515,
      "learning_rate": 1.9401692109416866e-05,
      "loss": 0.6232,
      "step": 7295
    },
    {
      "epoch": 0.22412680858907014,
      "grad_norm": 0.3141568601131439,
      "learning_rate": 1.9401527442044338e-05,
      "loss": 0.6303,
      "step": 7296
    },
    {
      "epoch": 0.22415752772401928,
      "grad_norm": 0.3448539078235626,
      "learning_rate": 1.9401362752713887e-05,
      "loss": 0.6042,
      "step": 7297
    },
    {
      "epoch": 0.22418824685896846,
      "grad_norm": 0.3808838427066803,
      "learning_rate": 1.94011980414259e-05,
      "loss": 0.5855,
      "step": 7298
    },
    {
      "epoch": 0.2242189659939176,
      "grad_norm": 0.40192991495132446,
      "learning_rate": 1.9401033308180754e-05,
      "loss": 0.5392,
      "step": 7299
    },
    {
      "epoch": 0.22424968512886678,
      "grad_norm": 0.3906198740005493,
      "learning_rate": 1.940086855297884e-05,
      "loss": 0.6582,
      "step": 7300
    },
    {
      "epoch": 0.22428040426381593,
      "grad_norm": 0.3786102533340454,
      "learning_rate": 1.9400703775820543e-05,
      "loss": 0.6042,
      "step": 7301
    },
    {
      "epoch": 0.22431112339876508,
      "grad_norm": 0.29326459765434265,
      "learning_rate": 1.940053897670624e-05,
      "loss": 0.4568,
      "step": 7302
    },
    {
      "epoch": 0.22434184253371425,
      "grad_norm": 0.3058309257030487,
      "learning_rate": 1.9400374155636324e-05,
      "loss": 0.5289,
      "step": 7303
    },
    {
      "epoch": 0.2243725616686634,
      "grad_norm": 0.31788378953933716,
      "learning_rate": 1.940020931261118e-05,
      "loss": 0.4702,
      "step": 7304
    },
    {
      "epoch": 0.22440328080361258,
      "grad_norm": 0.33539125323295593,
      "learning_rate": 1.940004444763119e-05,
      "loss": 0.4825,
      "step": 7305
    },
    {
      "epoch": 0.22443399993856172,
      "grad_norm": 0.3521583378314972,
      "learning_rate": 1.939987956069674e-05,
      "loss": 0.6201,
      "step": 7306
    },
    {
      "epoch": 0.2244647190735109,
      "grad_norm": 0.34196794033050537,
      "learning_rate": 1.9399714651808212e-05,
      "loss": 0.5503,
      "step": 7307
    },
    {
      "epoch": 0.22449543820846005,
      "grad_norm": 0.38174793124198914,
      "learning_rate": 1.9399549720965995e-05,
      "loss": 0.6083,
      "step": 7308
    },
    {
      "epoch": 0.22452615734340922,
      "grad_norm": 0.38010504841804504,
      "learning_rate": 1.9399384768170475e-05,
      "loss": 0.6116,
      "step": 7309
    },
    {
      "epoch": 0.22455687647835837,
      "grad_norm": 0.32622870802879333,
      "learning_rate": 1.9399219793422034e-05,
      "loss": 0.5329,
      "step": 7310
    },
    {
      "epoch": 0.22458759561330752,
      "grad_norm": 0.31432026624679565,
      "learning_rate": 1.939905479672106e-05,
      "loss": 0.5413,
      "step": 7311
    },
    {
      "epoch": 0.2246183147482567,
      "grad_norm": 0.3305554986000061,
      "learning_rate": 1.9398889778067936e-05,
      "loss": 0.5851,
      "step": 7312
    },
    {
      "epoch": 0.22464903388320584,
      "grad_norm": 0.41531622409820557,
      "learning_rate": 1.939872473746305e-05,
      "loss": 0.6308,
      "step": 7313
    },
    {
      "epoch": 0.22467975301815502,
      "grad_norm": 0.4783003330230713,
      "learning_rate": 1.9398559674906784e-05,
      "loss": 0.6013,
      "step": 7314
    },
    {
      "epoch": 0.22471047215310416,
      "grad_norm": 0.36595404148101807,
      "learning_rate": 1.9398394590399526e-05,
      "loss": 0.6299,
      "step": 7315
    },
    {
      "epoch": 0.22474119128805334,
      "grad_norm": 0.32650187611579895,
      "learning_rate": 1.939822948394166e-05,
      "loss": 0.6356,
      "step": 7316
    },
    {
      "epoch": 0.22477191042300249,
      "grad_norm": 0.3189988136291504,
      "learning_rate": 1.9398064355533573e-05,
      "loss": 0.5857,
      "step": 7317
    },
    {
      "epoch": 0.22480262955795166,
      "grad_norm": 0.4128827750682831,
      "learning_rate": 1.9397899205175652e-05,
      "loss": 0.5682,
      "step": 7318
    },
    {
      "epoch": 0.2248333486929008,
      "grad_norm": 0.3469971716403961,
      "learning_rate": 1.9397734032868282e-05,
      "loss": 0.584,
      "step": 7319
    },
    {
      "epoch": 0.22486406782784996,
      "grad_norm": 0.3722459673881531,
      "learning_rate": 1.9397568838611845e-05,
      "loss": 0.5925,
      "step": 7320
    },
    {
      "epoch": 0.22489478696279913,
      "grad_norm": 0.31458425521850586,
      "learning_rate": 1.939740362240673e-05,
      "loss": 0.5144,
      "step": 7321
    },
    {
      "epoch": 0.22492550609774828,
      "grad_norm": 0.37274929881095886,
      "learning_rate": 1.9397238384253324e-05,
      "loss": 0.6625,
      "step": 7322
    },
    {
      "epoch": 0.22495622523269745,
      "grad_norm": 0.33405041694641113,
      "learning_rate": 1.939707312415201e-05,
      "loss": 0.599,
      "step": 7323
    },
    {
      "epoch": 0.2249869443676466,
      "grad_norm": 0.35059091448783875,
      "learning_rate": 1.9396907842103178e-05,
      "loss": 0.6118,
      "step": 7324
    },
    {
      "epoch": 0.22501766350259578,
      "grad_norm": 0.3474101126194,
      "learning_rate": 1.9396742538107206e-05,
      "loss": 0.6079,
      "step": 7325
    },
    {
      "epoch": 0.22504838263754492,
      "grad_norm": 0.30668747425079346,
      "learning_rate": 1.939657721216449e-05,
      "loss": 0.5806,
      "step": 7326
    },
    {
      "epoch": 0.2250791017724941,
      "grad_norm": 0.30133169889450073,
      "learning_rate": 1.9396411864275414e-05,
      "loss": 0.5794,
      "step": 7327
    },
    {
      "epoch": 0.22510982090744325,
      "grad_norm": 0.3993760347366333,
      "learning_rate": 1.939624649444036e-05,
      "loss": 0.5233,
      "step": 7328
    },
    {
      "epoch": 0.2251405400423924,
      "grad_norm": 0.33116549253463745,
      "learning_rate": 1.9396081102659712e-05,
      "loss": 0.5674,
      "step": 7329
    },
    {
      "epoch": 0.22517125917734157,
      "grad_norm": 0.3810521960258484,
      "learning_rate": 1.9395915688933864e-05,
      "loss": 0.6219,
      "step": 7330
    },
    {
      "epoch": 0.22520197831229072,
      "grad_norm": 0.3808867335319519,
      "learning_rate": 1.9395750253263198e-05,
      "loss": 0.5369,
      "step": 7331
    },
    {
      "epoch": 0.2252326974472399,
      "grad_norm": 0.3798576593399048,
      "learning_rate": 1.93955847956481e-05,
      "loss": 0.5186,
      "step": 7332
    },
    {
      "epoch": 0.22526341658218904,
      "grad_norm": 0.3758757710456848,
      "learning_rate": 1.9395419316088958e-05,
      "loss": 0.5404,
      "step": 7333
    },
    {
      "epoch": 0.22529413571713822,
      "grad_norm": 0.36691203713417053,
      "learning_rate": 1.939525381458616e-05,
      "loss": 0.665,
      "step": 7334
    },
    {
      "epoch": 0.22532485485208736,
      "grad_norm": 0.32093968987464905,
      "learning_rate": 1.9395088291140088e-05,
      "loss": 0.5643,
      "step": 7335
    },
    {
      "epoch": 0.2253555739870365,
      "grad_norm": 0.378238320350647,
      "learning_rate": 1.9394922745751134e-05,
      "loss": 0.5369,
      "step": 7336
    },
    {
      "epoch": 0.2253862931219857,
      "grad_norm": 0.3562236726284027,
      "learning_rate": 1.939475717841968e-05,
      "loss": 0.6071,
      "step": 7337
    },
    {
      "epoch": 0.22541701225693483,
      "grad_norm": 0.3510250151157379,
      "learning_rate": 1.9394591589146114e-05,
      "loss": 0.6363,
      "step": 7338
    },
    {
      "epoch": 0.225447731391884,
      "grad_norm": 0.3472912609577179,
      "learning_rate": 1.9394425977930824e-05,
      "loss": 0.5423,
      "step": 7339
    },
    {
      "epoch": 0.22547845052683316,
      "grad_norm": 0.34918931126594543,
      "learning_rate": 1.9394260344774192e-05,
      "loss": 0.5361,
      "step": 7340
    },
    {
      "epoch": 0.22550916966178233,
      "grad_norm": 0.39391931891441345,
      "learning_rate": 1.9394094689676616e-05,
      "loss": 0.5172,
      "step": 7341
    },
    {
      "epoch": 0.22553988879673148,
      "grad_norm": 0.3395105004310608,
      "learning_rate": 1.939392901263847e-05,
      "loss": 0.5618,
      "step": 7342
    },
    {
      "epoch": 0.22557060793168066,
      "grad_norm": 0.39103609323501587,
      "learning_rate": 1.939376331366015e-05,
      "loss": 0.606,
      "step": 7343
    },
    {
      "epoch": 0.2256013270666298,
      "grad_norm": 0.33228006958961487,
      "learning_rate": 1.939359759274204e-05,
      "loss": 0.6044,
      "step": 7344
    },
    {
      "epoch": 0.22563204620157895,
      "grad_norm": 0.32702723145484924,
      "learning_rate": 1.9393431849884526e-05,
      "loss": 0.661,
      "step": 7345
    },
    {
      "epoch": 0.22566276533652813,
      "grad_norm": 0.36131811141967773,
      "learning_rate": 1.9393266085087993e-05,
      "loss": 0.6247,
      "step": 7346
    },
    {
      "epoch": 0.22569348447147727,
      "grad_norm": 0.36233004927635193,
      "learning_rate": 1.9393100298352837e-05,
      "loss": 0.5972,
      "step": 7347
    },
    {
      "epoch": 0.22572420360642645,
      "grad_norm": 0.33884862065315247,
      "learning_rate": 1.9392934489679435e-05,
      "loss": 0.639,
      "step": 7348
    },
    {
      "epoch": 0.2257549227413756,
      "grad_norm": 0.34336191415786743,
      "learning_rate": 1.939276865906818e-05,
      "loss": 0.6654,
      "step": 7349
    },
    {
      "epoch": 0.22578564187632477,
      "grad_norm": 0.33246946334838867,
      "learning_rate": 1.9392602806519456e-05,
      "loss": 0.5886,
      "step": 7350
    },
    {
      "epoch": 0.22581636101127392,
      "grad_norm": 0.2943590581417084,
      "learning_rate": 1.9392436932033655e-05,
      "loss": 0.5847,
      "step": 7351
    },
    {
      "epoch": 0.2258470801462231,
      "grad_norm": 0.32404372096061707,
      "learning_rate": 1.939227103561116e-05,
      "loss": 0.623,
      "step": 7352
    },
    {
      "epoch": 0.22587779928117224,
      "grad_norm": 0.3628520667552948,
      "learning_rate": 1.939210511725236e-05,
      "loss": 0.6296,
      "step": 7353
    },
    {
      "epoch": 0.2259085184161214,
      "grad_norm": 0.30108460783958435,
      "learning_rate": 1.939193917695764e-05,
      "loss": 0.569,
      "step": 7354
    },
    {
      "epoch": 0.22593923755107057,
      "grad_norm": 0.3308115005493164,
      "learning_rate": 1.9391773214727395e-05,
      "loss": 0.5547,
      "step": 7355
    },
    {
      "epoch": 0.2259699566860197,
      "grad_norm": 0.32858237624168396,
      "learning_rate": 1.9391607230562004e-05,
      "loss": 0.536,
      "step": 7356
    },
    {
      "epoch": 0.2260006758209689,
      "grad_norm": 0.3378011882305145,
      "learning_rate": 1.9391441224461858e-05,
      "loss": 0.6078,
      "step": 7357
    },
    {
      "epoch": 0.22603139495591804,
      "grad_norm": 0.3461975157260895,
      "learning_rate": 1.9391275196427347e-05,
      "loss": 0.5692,
      "step": 7358
    },
    {
      "epoch": 0.2260621140908672,
      "grad_norm": 0.33913785219192505,
      "learning_rate": 1.9391109146458857e-05,
      "loss": 0.6414,
      "step": 7359
    },
    {
      "epoch": 0.22609283322581636,
      "grad_norm": 0.41452690958976746,
      "learning_rate": 1.9390943074556777e-05,
      "loss": 0.627,
      "step": 7360
    },
    {
      "epoch": 0.22612355236076553,
      "grad_norm": 0.3057536482810974,
      "learning_rate": 1.9390776980721494e-05,
      "loss": 0.5056,
      "step": 7361
    },
    {
      "epoch": 0.22615427149571468,
      "grad_norm": 0.4267441928386688,
      "learning_rate": 1.939061086495339e-05,
      "loss": 0.5186,
      "step": 7362
    },
    {
      "epoch": 0.22618499063066383,
      "grad_norm": 0.3263033628463745,
      "learning_rate": 1.9390444727252863e-05,
      "loss": 0.528,
      "step": 7363
    },
    {
      "epoch": 0.226215709765613,
      "grad_norm": 0.3514125645160675,
      "learning_rate": 1.9390278567620298e-05,
      "loss": 0.7454,
      "step": 7364
    },
    {
      "epoch": 0.22624642890056215,
      "grad_norm": 0.35905420780181885,
      "learning_rate": 1.9390112386056078e-05,
      "loss": 0.5454,
      "step": 7365
    },
    {
      "epoch": 0.22627714803551133,
      "grad_norm": 0.38070571422576904,
      "learning_rate": 1.9389946182560596e-05,
      "loss": 0.6367,
      "step": 7366
    },
    {
      "epoch": 0.22630786717046047,
      "grad_norm": 0.3762733042240143,
      "learning_rate": 1.9389779957134238e-05,
      "loss": 0.5827,
      "step": 7367
    },
    {
      "epoch": 0.22633858630540965,
      "grad_norm": 0.35853418707847595,
      "learning_rate": 1.9389613709777394e-05,
      "loss": 0.5968,
      "step": 7368
    },
    {
      "epoch": 0.2263693054403588,
      "grad_norm": 0.3401113450527191,
      "learning_rate": 1.9389447440490454e-05,
      "loss": 0.5138,
      "step": 7369
    },
    {
      "epoch": 0.22640002457530797,
      "grad_norm": 0.35725516080856323,
      "learning_rate": 1.93892811492738e-05,
      "loss": 0.6156,
      "step": 7370
    },
    {
      "epoch": 0.22643074371025712,
      "grad_norm": 0.36085283756256104,
      "learning_rate": 1.9389114836127824e-05,
      "loss": 0.616,
      "step": 7371
    },
    {
      "epoch": 0.22646146284520627,
      "grad_norm": 0.32564806938171387,
      "learning_rate": 1.938894850105292e-05,
      "loss": 0.6164,
      "step": 7372
    },
    {
      "epoch": 0.22649218198015544,
      "grad_norm": 0.3233872652053833,
      "learning_rate": 1.9388782144049463e-05,
      "loss": 0.5803,
      "step": 7373
    },
    {
      "epoch": 0.2265229011151046,
      "grad_norm": 0.3873271346092224,
      "learning_rate": 1.9388615765117855e-05,
      "loss": 0.6188,
      "step": 7374
    },
    {
      "epoch": 0.22655362025005377,
      "grad_norm": 0.3377671241760254,
      "learning_rate": 1.938844936425848e-05,
      "loss": 0.5959,
      "step": 7375
    },
    {
      "epoch": 0.22658433938500291,
      "grad_norm": 0.40109509229660034,
      "learning_rate": 1.938828294147172e-05,
      "loss": 0.6394,
      "step": 7376
    },
    {
      "epoch": 0.2266150585199521,
      "grad_norm": 0.35152846574783325,
      "learning_rate": 1.9388116496757975e-05,
      "loss": 0.5199,
      "step": 7377
    },
    {
      "epoch": 0.22664577765490124,
      "grad_norm": 0.3442809283733368,
      "learning_rate": 1.9387950030117627e-05,
      "loss": 0.5702,
      "step": 7378
    },
    {
      "epoch": 0.22667649678985038,
      "grad_norm": 0.3279044032096863,
      "learning_rate": 1.9387783541551065e-05,
      "loss": 0.6007,
      "step": 7379
    },
    {
      "epoch": 0.22670721592479956,
      "grad_norm": 0.3125022053718567,
      "learning_rate": 1.938761703105868e-05,
      "loss": 0.4561,
      "step": 7380
    },
    {
      "epoch": 0.2267379350597487,
      "grad_norm": 0.3144909739494324,
      "learning_rate": 1.938745049864086e-05,
      "loss": 0.6357,
      "step": 7381
    },
    {
      "epoch": 0.22676865419469788,
      "grad_norm": 0.329017698764801,
      "learning_rate": 1.938728394429799e-05,
      "loss": 0.6125,
      "step": 7382
    },
    {
      "epoch": 0.22679937332964703,
      "grad_norm": 0.341309130191803,
      "learning_rate": 1.9387117368030465e-05,
      "loss": 0.5653,
      "step": 7383
    },
    {
      "epoch": 0.2268300924645962,
      "grad_norm": 0.3181845545768738,
      "learning_rate": 1.9386950769838677e-05,
      "loss": 0.5217,
      "step": 7384
    },
    {
      "epoch": 0.22686081159954535,
      "grad_norm": 0.34928297996520996,
      "learning_rate": 1.9386784149723002e-05,
      "loss": 0.6392,
      "step": 7385
    },
    {
      "epoch": 0.22689153073449453,
      "grad_norm": 0.3331514596939087,
      "learning_rate": 1.9386617507683842e-05,
      "loss": 0.5957,
      "step": 7386
    },
    {
      "epoch": 0.22692224986944368,
      "grad_norm": 0.328285813331604,
      "learning_rate": 1.938645084372158e-05,
      "loss": 0.5334,
      "step": 7387
    },
    {
      "epoch": 0.22695296900439282,
      "grad_norm": 0.37842315435409546,
      "learning_rate": 1.9386284157836605e-05,
      "loss": 0.6478,
      "step": 7388
    },
    {
      "epoch": 0.226983688139342,
      "grad_norm": 0.4938315451145172,
      "learning_rate": 1.938611745002931e-05,
      "loss": 0.6377,
      "step": 7389
    },
    {
      "epoch": 0.22701440727429115,
      "grad_norm": 0.35763365030288696,
      "learning_rate": 1.938595072030008e-05,
      "loss": 0.6625,
      "step": 7390
    },
    {
      "epoch": 0.22704512640924032,
      "grad_norm": 0.33605343103408813,
      "learning_rate": 1.9385783968649304e-05,
      "loss": 0.5848,
      "step": 7391
    },
    {
      "epoch": 0.22707584554418947,
      "grad_norm": 0.34544625878334045,
      "learning_rate": 1.938561719507738e-05,
      "loss": 0.5921,
      "step": 7392
    },
    {
      "epoch": 0.22710656467913864,
      "grad_norm": 0.3244796097278595,
      "learning_rate": 1.9385450399584692e-05,
      "loss": 0.5541,
      "step": 7393
    },
    {
      "epoch": 0.2271372838140878,
      "grad_norm": 0.39071816205978394,
      "learning_rate": 1.9385283582171625e-05,
      "loss": 0.521,
      "step": 7394
    },
    {
      "epoch": 0.22716800294903697,
      "grad_norm": 0.3313172161579132,
      "learning_rate": 1.9385116742838573e-05,
      "loss": 0.582,
      "step": 7395
    },
    {
      "epoch": 0.22719872208398612,
      "grad_norm": 0.38669919967651367,
      "learning_rate": 1.9384949881585927e-05,
      "loss": 0.5524,
      "step": 7396
    },
    {
      "epoch": 0.22722944121893526,
      "grad_norm": 0.3380057215690613,
      "learning_rate": 1.9384782998414074e-05,
      "loss": 0.649,
      "step": 7397
    },
    {
      "epoch": 0.22726016035388444,
      "grad_norm": 0.34008917212486267,
      "learning_rate": 1.9384616093323408e-05,
      "loss": 0.5982,
      "step": 7398
    },
    {
      "epoch": 0.22729087948883359,
      "grad_norm": 0.3785461485385895,
      "learning_rate": 1.938444916631431e-05,
      "loss": 0.5531,
      "step": 7399
    },
    {
      "epoch": 0.22732159862378276,
      "grad_norm": 0.343075156211853,
      "learning_rate": 1.938428221738718e-05,
      "loss": 0.5482,
      "step": 7400
    },
    {
      "epoch": 0.2273523177587319,
      "grad_norm": 0.4082321226596832,
      "learning_rate": 1.9384115246542404e-05,
      "loss": 0.6307,
      "step": 7401
    },
    {
      "epoch": 0.22738303689368108,
      "grad_norm": 0.5316211581230164,
      "learning_rate": 1.938394825378037e-05,
      "loss": 0.6285,
      "step": 7402
    },
    {
      "epoch": 0.22741375602863023,
      "grad_norm": 0.3573005497455597,
      "learning_rate": 1.938378123910147e-05,
      "loss": 0.6185,
      "step": 7403
    },
    {
      "epoch": 0.2274444751635794,
      "grad_norm": 0.3370492160320282,
      "learning_rate": 1.9383614202506093e-05,
      "loss": 0.5748,
      "step": 7404
    },
    {
      "epoch": 0.22747519429852855,
      "grad_norm": 0.31930306553840637,
      "learning_rate": 1.938344714399463e-05,
      "loss": 0.5606,
      "step": 7405
    },
    {
      "epoch": 0.2275059134334777,
      "grad_norm": 0.43836915493011475,
      "learning_rate": 1.9383280063567468e-05,
      "loss": 0.5703,
      "step": 7406
    },
    {
      "epoch": 0.22753663256842688,
      "grad_norm": 0.34689727425575256,
      "learning_rate": 1.9383112961225e-05,
      "loss": 0.5091,
      "step": 7407
    },
    {
      "epoch": 0.22756735170337603,
      "grad_norm": 0.3750269114971161,
      "learning_rate": 1.938294583696762e-05,
      "loss": 0.5709,
      "step": 7408
    },
    {
      "epoch": 0.2275980708383252,
      "grad_norm": 0.3299335241317749,
      "learning_rate": 1.9382778690795714e-05,
      "loss": 0.5943,
      "step": 7409
    },
    {
      "epoch": 0.22762878997327435,
      "grad_norm": 0.3183330297470093,
      "learning_rate": 1.9382611522709673e-05,
      "loss": 0.5798,
      "step": 7410
    },
    {
      "epoch": 0.22765950910822352,
      "grad_norm": 0.3359580338001251,
      "learning_rate": 1.9382444332709886e-05,
      "loss": 0.5986,
      "step": 7411
    },
    {
      "epoch": 0.22769022824317267,
      "grad_norm": 0.3416002094745636,
      "learning_rate": 1.9382277120796747e-05,
      "loss": 0.6705,
      "step": 7412
    },
    {
      "epoch": 0.22772094737812182,
      "grad_norm": 0.3403262197971344,
      "learning_rate": 1.9382109886970646e-05,
      "loss": 0.5748,
      "step": 7413
    },
    {
      "epoch": 0.227751666513071,
      "grad_norm": 0.38222330808639526,
      "learning_rate": 1.9381942631231968e-05,
      "loss": 0.5473,
      "step": 7414
    },
    {
      "epoch": 0.22778238564802014,
      "grad_norm": 0.33137020468711853,
      "learning_rate": 1.938177535358111e-05,
      "loss": 0.5488,
      "step": 7415
    },
    {
      "epoch": 0.22781310478296932,
      "grad_norm": 0.3531838655471802,
      "learning_rate": 1.9381608054018462e-05,
      "loss": 0.6129,
      "step": 7416
    },
    {
      "epoch": 0.22784382391791846,
      "grad_norm": 0.29354819655418396,
      "learning_rate": 1.938144073254441e-05,
      "loss": 0.5539,
      "step": 7417
    },
    {
      "epoch": 0.22787454305286764,
      "grad_norm": 0.36375948786735535,
      "learning_rate": 1.9381273389159347e-05,
      "loss": 0.5865,
      "step": 7418
    },
    {
      "epoch": 0.2279052621878168,
      "grad_norm": 0.33908823132514954,
      "learning_rate": 1.938110602386367e-05,
      "loss": 0.6223,
      "step": 7419
    },
    {
      "epoch": 0.22793598132276596,
      "grad_norm": 0.3436124920845032,
      "learning_rate": 1.938093863665776e-05,
      "loss": 0.5772,
      "step": 7420
    },
    {
      "epoch": 0.2279667004577151,
      "grad_norm": 0.4509897828102112,
      "learning_rate": 1.9380771227542015e-05,
      "loss": 0.5496,
      "step": 7421
    },
    {
      "epoch": 0.22799741959266426,
      "grad_norm": 0.35654711723327637,
      "learning_rate": 1.9380603796516824e-05,
      "loss": 0.6003,
      "step": 7422
    },
    {
      "epoch": 0.22802813872761343,
      "grad_norm": 0.348190039396286,
      "learning_rate": 1.9380436343582578e-05,
      "loss": 0.6368,
      "step": 7423
    },
    {
      "epoch": 0.22805885786256258,
      "grad_norm": 0.3682152330875397,
      "learning_rate": 1.9380268868739665e-05,
      "loss": 0.5505,
      "step": 7424
    },
    {
      "epoch": 0.22808957699751176,
      "grad_norm": 0.3381710648536682,
      "learning_rate": 1.938010137198848e-05,
      "loss": 0.6492,
      "step": 7425
    },
    {
      "epoch": 0.2281202961324609,
      "grad_norm": 0.42278847098350525,
      "learning_rate": 1.9379933853329415e-05,
      "loss": 0.5568,
      "step": 7426
    },
    {
      "epoch": 0.22815101526741008,
      "grad_norm": 0.6092449426651001,
      "learning_rate": 1.9379766312762854e-05,
      "loss": 0.5361,
      "step": 7427
    },
    {
      "epoch": 0.22818173440235923,
      "grad_norm": 0.3231405019760132,
      "learning_rate": 1.93795987502892e-05,
      "loss": 0.5929,
      "step": 7428
    },
    {
      "epoch": 0.2282124535373084,
      "grad_norm": 0.3255586624145508,
      "learning_rate": 1.9379431165908836e-05,
      "loss": 0.6008,
      "step": 7429
    },
    {
      "epoch": 0.22824317267225755,
      "grad_norm": 0.3356032967567444,
      "learning_rate": 1.9379263559622154e-05,
      "loss": 0.5606,
      "step": 7430
    },
    {
      "epoch": 0.2282738918072067,
      "grad_norm": 0.3156086504459381,
      "learning_rate": 1.9379095931429547e-05,
      "loss": 0.5398,
      "step": 7431
    },
    {
      "epoch": 0.22830461094215587,
      "grad_norm": 0.3535171449184418,
      "learning_rate": 1.937892828133141e-05,
      "loss": 0.6143,
      "step": 7432
    },
    {
      "epoch": 0.22833533007710502,
      "grad_norm": 0.3699648976325989,
      "learning_rate": 1.9378760609328128e-05,
      "loss": 0.5466,
      "step": 7433
    },
    {
      "epoch": 0.2283660492120542,
      "grad_norm": 0.3485315442085266,
      "learning_rate": 1.9378592915420096e-05,
      "loss": 0.604,
      "step": 7434
    },
    {
      "epoch": 0.22839676834700334,
      "grad_norm": 0.42829641699790955,
      "learning_rate": 1.9378425199607704e-05,
      "loss": 0.5821,
      "step": 7435
    },
    {
      "epoch": 0.22842748748195252,
      "grad_norm": 0.33152347803115845,
      "learning_rate": 1.9378257461891348e-05,
      "loss": 0.5514,
      "step": 7436
    },
    {
      "epoch": 0.22845820661690167,
      "grad_norm": 0.35419774055480957,
      "learning_rate": 1.9378089702271415e-05,
      "loss": 0.596,
      "step": 7437
    },
    {
      "epoch": 0.22848892575185084,
      "grad_norm": 0.3318338394165039,
      "learning_rate": 1.93779219207483e-05,
      "loss": 0.553,
      "step": 7438
    },
    {
      "epoch": 0.2285196448868,
      "grad_norm": 0.36317870020866394,
      "learning_rate": 1.9377754117322388e-05,
      "loss": 0.6069,
      "step": 7439
    },
    {
      "epoch": 0.22855036402174914,
      "grad_norm": 0.34206825494766235,
      "learning_rate": 1.9377586291994084e-05,
      "loss": 0.6825,
      "step": 7440
    },
    {
      "epoch": 0.2285810831566983,
      "grad_norm": 0.3275406062602997,
      "learning_rate": 1.9377418444763768e-05,
      "loss": 0.6105,
      "step": 7441
    },
    {
      "epoch": 0.22861180229164746,
      "grad_norm": 0.32147493958473206,
      "learning_rate": 1.9377250575631836e-05,
      "loss": 0.6127,
      "step": 7442
    },
    {
      "epoch": 0.22864252142659663,
      "grad_norm": 0.3426972031593323,
      "learning_rate": 1.937708268459868e-05,
      "loss": 0.5879,
      "step": 7443
    },
    {
      "epoch": 0.22867324056154578,
      "grad_norm": 0.31555846333503723,
      "learning_rate": 1.9376914771664697e-05,
      "loss": 0.5505,
      "step": 7444
    },
    {
      "epoch": 0.22870395969649496,
      "grad_norm": 0.3266202211380005,
      "learning_rate": 1.9376746836830272e-05,
      "loss": 0.5774,
      "step": 7445
    },
    {
      "epoch": 0.2287346788314441,
      "grad_norm": 0.3319772481918335,
      "learning_rate": 1.9376578880095797e-05,
      "loss": 0.6482,
      "step": 7446
    },
    {
      "epoch": 0.22876539796639328,
      "grad_norm": 0.3574504554271698,
      "learning_rate": 1.9376410901461672e-05,
      "loss": 0.6529,
      "step": 7447
    },
    {
      "epoch": 0.22879611710134243,
      "grad_norm": 0.35581085085868835,
      "learning_rate": 1.9376242900928282e-05,
      "loss": 0.6766,
      "step": 7448
    },
    {
      "epoch": 0.22882683623629158,
      "grad_norm": 0.41221562027931213,
      "learning_rate": 1.937607487849602e-05,
      "loss": 0.5491,
      "step": 7449
    },
    {
      "epoch": 0.22885755537124075,
      "grad_norm": 0.4038274884223938,
      "learning_rate": 1.9375906834165282e-05,
      "loss": 0.5617,
      "step": 7450
    },
    {
      "epoch": 0.2288882745061899,
      "grad_norm": 0.3290782570838928,
      "learning_rate": 1.9375738767936457e-05,
      "loss": 0.4453,
      "step": 7451
    },
    {
      "epoch": 0.22891899364113907,
      "grad_norm": 0.34250175952911377,
      "learning_rate": 1.9375570679809944e-05,
      "loss": 0.6221,
      "step": 7452
    },
    {
      "epoch": 0.22894971277608822,
      "grad_norm": 0.30701887607574463,
      "learning_rate": 1.9375402569786127e-05,
      "loss": 0.6456,
      "step": 7453
    },
    {
      "epoch": 0.2289804319110374,
      "grad_norm": 0.40501177310943604,
      "learning_rate": 1.937523443786541e-05,
      "loss": 0.5994,
      "step": 7454
    },
    {
      "epoch": 0.22901115104598654,
      "grad_norm": 0.35494571924209595,
      "learning_rate": 1.9375066284048166e-05,
      "loss": 0.4769,
      "step": 7455
    },
    {
      "epoch": 0.2290418701809357,
      "grad_norm": 0.3860504925251007,
      "learning_rate": 1.9374898108334807e-05,
      "loss": 0.6088,
      "step": 7456
    },
    {
      "epoch": 0.22907258931588487,
      "grad_norm": 0.357479453086853,
      "learning_rate": 1.9374729910725717e-05,
      "loss": 0.5899,
      "step": 7457
    },
    {
      "epoch": 0.22910330845083401,
      "grad_norm": 0.3647928535938263,
      "learning_rate": 1.9374561691221293e-05,
      "loss": 0.5858,
      "step": 7458
    },
    {
      "epoch": 0.2291340275857832,
      "grad_norm": 0.372729629278183,
      "learning_rate": 1.937439344982192e-05,
      "loss": 0.6123,
      "step": 7459
    },
    {
      "epoch": 0.22916474672073234,
      "grad_norm": 0.3453364670276642,
      "learning_rate": 1.9374225186528002e-05,
      "loss": 0.5541,
      "step": 7460
    },
    {
      "epoch": 0.2291954658556815,
      "grad_norm": 0.34414008259773254,
      "learning_rate": 1.9374056901339927e-05,
      "loss": 0.5296,
      "step": 7461
    },
    {
      "epoch": 0.22922618499063066,
      "grad_norm": 0.3587051331996918,
      "learning_rate": 1.9373888594258083e-05,
      "loss": 0.6517,
      "step": 7462
    },
    {
      "epoch": 0.22925690412557984,
      "grad_norm": 0.32185864448547363,
      "learning_rate": 1.937372026528287e-05,
      "loss": 0.6161,
      "step": 7463
    },
    {
      "epoch": 0.22928762326052898,
      "grad_norm": 0.44936516880989075,
      "learning_rate": 1.937355191441468e-05,
      "loss": 0.5494,
      "step": 7464
    },
    {
      "epoch": 0.22931834239547813,
      "grad_norm": 0.3466988205909729,
      "learning_rate": 1.93733835416539e-05,
      "loss": 0.6399,
      "step": 7465
    },
    {
      "epoch": 0.2293490615304273,
      "grad_norm": 0.3312217891216278,
      "learning_rate": 1.9373215147000932e-05,
      "loss": 0.5736,
      "step": 7466
    },
    {
      "epoch": 0.22937978066537645,
      "grad_norm": 0.431925505399704,
      "learning_rate": 1.9373046730456163e-05,
      "loss": 0.5775,
      "step": 7467
    },
    {
      "epoch": 0.22941049980032563,
      "grad_norm": 0.3234696388244629,
      "learning_rate": 1.937287829201999e-05,
      "loss": 0.6117,
      "step": 7468
    },
    {
      "epoch": 0.22944121893527478,
      "grad_norm": 0.3022303879261017,
      "learning_rate": 1.9372709831692808e-05,
      "loss": 0.608,
      "step": 7469
    },
    {
      "epoch": 0.22947193807022395,
      "grad_norm": 0.3508851230144501,
      "learning_rate": 1.9372541349475006e-05,
      "loss": 0.4912,
      "step": 7470
    },
    {
      "epoch": 0.2295026572051731,
      "grad_norm": 0.36326491832733154,
      "learning_rate": 1.9372372845366977e-05,
      "loss": 0.5748,
      "step": 7471
    },
    {
      "epoch": 0.22953337634012227,
      "grad_norm": 0.32916176319122314,
      "learning_rate": 1.9372204319369116e-05,
      "loss": 0.542,
      "step": 7472
    },
    {
      "epoch": 0.22956409547507142,
      "grad_norm": 0.3626655042171478,
      "learning_rate": 1.9372035771481822e-05,
      "loss": 0.572,
      "step": 7473
    },
    {
      "epoch": 0.22959481461002057,
      "grad_norm": 0.34336742758750916,
      "learning_rate": 1.937186720170548e-05,
      "loss": 0.6382,
      "step": 7474
    },
    {
      "epoch": 0.22962553374496975,
      "grad_norm": 0.34429338574409485,
      "learning_rate": 1.937169861004049e-05,
      "loss": 0.5911,
      "step": 7475
    },
    {
      "epoch": 0.2296562528799189,
      "grad_norm": 0.3594897389411926,
      "learning_rate": 1.937152999648724e-05,
      "loss": 0.5609,
      "step": 7476
    },
    {
      "epoch": 0.22968697201486807,
      "grad_norm": 0.3616867959499359,
      "learning_rate": 1.937136136104613e-05,
      "loss": 0.5621,
      "step": 7477
    },
    {
      "epoch": 0.22971769114981722,
      "grad_norm": 0.3607358932495117,
      "learning_rate": 1.937119270371755e-05,
      "loss": 0.5531,
      "step": 7478
    },
    {
      "epoch": 0.2297484102847664,
      "grad_norm": 0.3903348445892334,
      "learning_rate": 1.9371024024501895e-05,
      "loss": 0.5917,
      "step": 7479
    },
    {
      "epoch": 0.22977912941971554,
      "grad_norm": 0.3360470235347748,
      "learning_rate": 1.937085532339956e-05,
      "loss": 0.5709,
      "step": 7480
    },
    {
      "epoch": 0.22980984855466471,
      "grad_norm": 0.4198625087738037,
      "learning_rate": 1.9370686600410935e-05,
      "loss": 0.605,
      "step": 7481
    },
    {
      "epoch": 0.22984056768961386,
      "grad_norm": 0.35233667492866516,
      "learning_rate": 1.937051785553642e-05,
      "loss": 0.5872,
      "step": 7482
    },
    {
      "epoch": 0.229871286824563,
      "grad_norm": 0.350803017616272,
      "learning_rate": 1.9370349088776406e-05,
      "loss": 0.5588,
      "step": 7483
    },
    {
      "epoch": 0.22990200595951218,
      "grad_norm": 0.3376011550426483,
      "learning_rate": 1.9370180300131286e-05,
      "loss": 0.5901,
      "step": 7484
    },
    {
      "epoch": 0.22993272509446133,
      "grad_norm": 0.5358785390853882,
      "learning_rate": 1.9370011489601455e-05,
      "loss": 0.7617,
      "step": 7485
    },
    {
      "epoch": 0.2299634442294105,
      "grad_norm": 0.35246506333351135,
      "learning_rate": 1.936984265718731e-05,
      "loss": 0.5704,
      "step": 7486
    },
    {
      "epoch": 0.22999416336435966,
      "grad_norm": 0.3326294720172882,
      "learning_rate": 1.936967380288924e-05,
      "loss": 0.6105,
      "step": 7487
    },
    {
      "epoch": 0.23002488249930883,
      "grad_norm": 0.37752148509025574,
      "learning_rate": 1.9369504926707644e-05,
      "loss": 0.6859,
      "step": 7488
    },
    {
      "epoch": 0.23005560163425798,
      "grad_norm": 0.5301054120063782,
      "learning_rate": 1.9369336028642917e-05,
      "loss": 0.5168,
      "step": 7489
    },
    {
      "epoch": 0.23008632076920713,
      "grad_norm": 0.3549875020980835,
      "learning_rate": 1.936916710869545e-05,
      "loss": 0.6376,
      "step": 7490
    },
    {
      "epoch": 0.2301170399041563,
      "grad_norm": 0.33290788531303406,
      "learning_rate": 1.9368998166865638e-05,
      "loss": 0.5356,
      "step": 7491
    },
    {
      "epoch": 0.23014775903910545,
      "grad_norm": 0.3238588869571686,
      "learning_rate": 1.9368829203153876e-05,
      "loss": 0.4919,
      "step": 7492
    },
    {
      "epoch": 0.23017847817405462,
      "grad_norm": 0.36381638050079346,
      "learning_rate": 1.936866021756056e-05,
      "loss": 0.7044,
      "step": 7493
    },
    {
      "epoch": 0.23020919730900377,
      "grad_norm": 0.42452216148376465,
      "learning_rate": 1.9368491210086083e-05,
      "loss": 0.6389,
      "step": 7494
    },
    {
      "epoch": 0.23023991644395295,
      "grad_norm": 0.3306809961795807,
      "learning_rate": 1.936832218073084e-05,
      "loss": 0.5951,
      "step": 7495
    },
    {
      "epoch": 0.2302706355789021,
      "grad_norm": 0.34385159611701965,
      "learning_rate": 1.936815312949523e-05,
      "loss": 0.6244,
      "step": 7496
    },
    {
      "epoch": 0.23030135471385127,
      "grad_norm": 0.35200953483581543,
      "learning_rate": 1.936798405637964e-05,
      "loss": 0.5921,
      "step": 7497
    },
    {
      "epoch": 0.23033207384880042,
      "grad_norm": 0.33038002252578735,
      "learning_rate": 1.936781496138447e-05,
      "loss": 0.5732,
      "step": 7498
    },
    {
      "epoch": 0.23036279298374956,
      "grad_norm": 0.39050304889678955,
      "learning_rate": 1.9367645844510114e-05,
      "loss": 0.6665,
      "step": 7499
    },
    {
      "epoch": 0.23039351211869874,
      "grad_norm": 0.3414463400840759,
      "learning_rate": 1.936747670575697e-05,
      "loss": 0.5897,
      "step": 7500
    },
    {
      "epoch": 0.2304242312536479,
      "grad_norm": 0.33180636167526245,
      "learning_rate": 1.9367307545125427e-05,
      "loss": 0.5954,
      "step": 7501
    },
    {
      "epoch": 0.23045495038859706,
      "grad_norm": 0.3682723045349121,
      "learning_rate": 1.9367138362615882e-05,
      "loss": 0.6972,
      "step": 7502
    },
    {
      "epoch": 0.2304856695235462,
      "grad_norm": 0.3598076105117798,
      "learning_rate": 1.936696915822873e-05,
      "loss": 0.6324,
      "step": 7503
    },
    {
      "epoch": 0.23051638865849539,
      "grad_norm": 0.3836211860179901,
      "learning_rate": 1.936679993196437e-05,
      "loss": 0.5973,
      "step": 7504
    },
    {
      "epoch": 0.23054710779344453,
      "grad_norm": 0.33843305706977844,
      "learning_rate": 1.9366630683823197e-05,
      "loss": 0.5815,
      "step": 7505
    },
    {
      "epoch": 0.2305778269283937,
      "grad_norm": 0.33769190311431885,
      "learning_rate": 1.9366461413805602e-05,
      "loss": 0.6531,
      "step": 7506
    },
    {
      "epoch": 0.23060854606334286,
      "grad_norm": 0.31675535440444946,
      "learning_rate": 1.936629212191198e-05,
      "loss": 0.5979,
      "step": 7507
    },
    {
      "epoch": 0.230639265198292,
      "grad_norm": 0.3020946681499481,
      "learning_rate": 1.936612280814273e-05,
      "loss": 0.5299,
      "step": 7508
    },
    {
      "epoch": 0.23066998433324118,
      "grad_norm": 0.3477190434932709,
      "learning_rate": 1.9365953472498246e-05,
      "loss": 0.6018,
      "step": 7509
    },
    {
      "epoch": 0.23070070346819033,
      "grad_norm": 0.35950568318367004,
      "learning_rate": 1.936578411497893e-05,
      "loss": 0.6338,
      "step": 7510
    },
    {
      "epoch": 0.2307314226031395,
      "grad_norm": 0.3880220353603363,
      "learning_rate": 1.936561473558516e-05,
      "loss": 0.6188,
      "step": 7511
    },
    {
      "epoch": 0.23076214173808865,
      "grad_norm": 0.3593064248561859,
      "learning_rate": 1.936544533431735e-05,
      "loss": 0.5886,
      "step": 7512
    },
    {
      "epoch": 0.23079286087303783,
      "grad_norm": 0.32392406463623047,
      "learning_rate": 1.9365275911175883e-05,
      "loss": 0.5884,
      "step": 7513
    },
    {
      "epoch": 0.23082358000798697,
      "grad_norm": 0.37048155069351196,
      "learning_rate": 1.9365106466161166e-05,
      "loss": 0.6529,
      "step": 7514
    },
    {
      "epoch": 0.23085429914293615,
      "grad_norm": 0.3442489504814148,
      "learning_rate": 1.9364936999273584e-05,
      "loss": 0.6416,
      "step": 7515
    },
    {
      "epoch": 0.2308850182778853,
      "grad_norm": 0.3358599543571472,
      "learning_rate": 1.936476751051354e-05,
      "loss": 0.6786,
      "step": 7516
    },
    {
      "epoch": 0.23091573741283444,
      "grad_norm": 0.3464985191822052,
      "learning_rate": 1.9364597999881428e-05,
      "loss": 0.681,
      "step": 7517
    },
    {
      "epoch": 0.23094645654778362,
      "grad_norm": 0.3333529829978943,
      "learning_rate": 1.936442846737764e-05,
      "loss": 0.543,
      "step": 7518
    },
    {
      "epoch": 0.23097717568273277,
      "grad_norm": 0.3113676905632019,
      "learning_rate": 1.936425891300258e-05,
      "loss": 0.5853,
      "step": 7519
    },
    {
      "epoch": 0.23100789481768194,
      "grad_norm": 0.31625208258628845,
      "learning_rate": 1.9364089336756633e-05,
      "loss": 0.5414,
      "step": 7520
    },
    {
      "epoch": 0.2310386139526311,
      "grad_norm": 0.3336169421672821,
      "learning_rate": 1.9363919738640206e-05,
      "loss": 0.5925,
      "step": 7521
    },
    {
      "epoch": 0.23106933308758026,
      "grad_norm": 0.4663701057434082,
      "learning_rate": 1.936375011865369e-05,
      "loss": 0.5891,
      "step": 7522
    },
    {
      "epoch": 0.2311000522225294,
      "grad_norm": 0.42512816190719604,
      "learning_rate": 1.9363580476797483e-05,
      "loss": 0.7235,
      "step": 7523
    },
    {
      "epoch": 0.2311307713574786,
      "grad_norm": 0.5116162896156311,
      "learning_rate": 1.9363410813071977e-05,
      "loss": 0.5357,
      "step": 7524
    },
    {
      "epoch": 0.23116149049242773,
      "grad_norm": 0.36814916133880615,
      "learning_rate": 1.936324112747757e-05,
      "loss": 0.5336,
      "step": 7525
    },
    {
      "epoch": 0.23119220962737688,
      "grad_norm": 0.34030500054359436,
      "learning_rate": 1.9363071420014665e-05,
      "loss": 0.5912,
      "step": 7526
    },
    {
      "epoch": 0.23122292876232606,
      "grad_norm": 0.3159242868423462,
      "learning_rate": 1.936290169068365e-05,
      "loss": 0.5515,
      "step": 7527
    },
    {
      "epoch": 0.2312536478972752,
      "grad_norm": 0.3174722194671631,
      "learning_rate": 1.936273193948492e-05,
      "loss": 0.5301,
      "step": 7528
    },
    {
      "epoch": 0.23128436703222438,
      "grad_norm": 0.503537654876709,
      "learning_rate": 1.936256216641888e-05,
      "loss": 0.7637,
      "step": 7529
    },
    {
      "epoch": 0.23131508616717353,
      "grad_norm": 0.4433203935623169,
      "learning_rate": 1.9362392371485924e-05,
      "loss": 0.5432,
      "step": 7530
    },
    {
      "epoch": 0.2313458053021227,
      "grad_norm": 0.3555707633495331,
      "learning_rate": 1.9362222554686443e-05,
      "loss": 0.5761,
      "step": 7531
    },
    {
      "epoch": 0.23137652443707185,
      "grad_norm": 0.4291413724422455,
      "learning_rate": 1.9362052716020838e-05,
      "loss": 0.5903,
      "step": 7532
    },
    {
      "epoch": 0.231407243572021,
      "grad_norm": 0.5711989998817444,
      "learning_rate": 1.9361882855489507e-05,
      "loss": 0.5689,
      "step": 7533
    },
    {
      "epoch": 0.23143796270697017,
      "grad_norm": 0.34418943524360657,
      "learning_rate": 1.9361712973092843e-05,
      "loss": 0.6637,
      "step": 7534
    },
    {
      "epoch": 0.23146868184191932,
      "grad_norm": 0.3729333281517029,
      "learning_rate": 1.9361543068831244e-05,
      "loss": 0.5889,
      "step": 7535
    },
    {
      "epoch": 0.2314994009768685,
      "grad_norm": 0.31492385268211365,
      "learning_rate": 1.936137314270511e-05,
      "loss": 0.5236,
      "step": 7536
    },
    {
      "epoch": 0.23153012011181764,
      "grad_norm": 0.3353425860404968,
      "learning_rate": 1.936120319471483e-05,
      "loss": 0.6266,
      "step": 7537
    },
    {
      "epoch": 0.23156083924676682,
      "grad_norm": 0.3360268473625183,
      "learning_rate": 1.9361033224860813e-05,
      "loss": 0.5477,
      "step": 7538
    },
    {
      "epoch": 0.23159155838171597,
      "grad_norm": 0.3353384733200073,
      "learning_rate": 1.9360863233143445e-05,
      "loss": 0.5325,
      "step": 7539
    },
    {
      "epoch": 0.23162227751666514,
      "grad_norm": 0.34184566140174866,
      "learning_rate": 1.9360693219563127e-05,
      "loss": 0.6372,
      "step": 7540
    },
    {
      "epoch": 0.2316529966516143,
      "grad_norm": 0.3610056936740875,
      "learning_rate": 1.9360523184120258e-05,
      "loss": 0.6696,
      "step": 7541
    },
    {
      "epoch": 0.23168371578656344,
      "grad_norm": 0.32596707344055176,
      "learning_rate": 1.9360353126815235e-05,
      "loss": 0.5568,
      "step": 7542
    },
    {
      "epoch": 0.2317144349215126,
      "grad_norm": 0.3487396240234375,
      "learning_rate": 1.9360183047648448e-05,
      "loss": 0.6229,
      "step": 7543
    },
    {
      "epoch": 0.23174515405646176,
      "grad_norm": 0.33364149928092957,
      "learning_rate": 1.9360012946620305e-05,
      "loss": 0.6548,
      "step": 7544
    },
    {
      "epoch": 0.23177587319141094,
      "grad_norm": 0.38248854875564575,
      "learning_rate": 1.9359842823731195e-05,
      "loss": 0.5941,
      "step": 7545
    },
    {
      "epoch": 0.23180659232636008,
      "grad_norm": 0.3733510971069336,
      "learning_rate": 1.935967267898152e-05,
      "loss": 0.6322,
      "step": 7546
    },
    {
      "epoch": 0.23183731146130926,
      "grad_norm": 0.3500770032405853,
      "learning_rate": 1.9359502512371675e-05,
      "loss": 0.5152,
      "step": 7547
    },
    {
      "epoch": 0.2318680305962584,
      "grad_norm": 0.35562944412231445,
      "learning_rate": 1.935933232390206e-05,
      "loss": 0.5523,
      "step": 7548
    },
    {
      "epoch": 0.23189874973120758,
      "grad_norm": 0.37518608570098877,
      "learning_rate": 1.9359162113573066e-05,
      "loss": 0.656,
      "step": 7549
    },
    {
      "epoch": 0.23192946886615673,
      "grad_norm": 0.3618136942386627,
      "learning_rate": 1.93589918813851e-05,
      "loss": 0.5972,
      "step": 7550
    },
    {
      "epoch": 0.23196018800110588,
      "grad_norm": 0.35142409801483154,
      "learning_rate": 1.9358821627338553e-05,
      "loss": 0.6294,
      "step": 7551
    },
    {
      "epoch": 0.23199090713605505,
      "grad_norm": 0.34081152081489563,
      "learning_rate": 1.9358651351433825e-05,
      "loss": 0.5806,
      "step": 7552
    },
    {
      "epoch": 0.2320216262710042,
      "grad_norm": 0.364881694316864,
      "learning_rate": 1.9358481053671313e-05,
      "loss": 0.6021,
      "step": 7553
    },
    {
      "epoch": 0.23205234540595338,
      "grad_norm": 0.3448374569416046,
      "learning_rate": 1.9358310734051415e-05,
      "loss": 0.5321,
      "step": 7554
    },
    {
      "epoch": 0.23208306454090252,
      "grad_norm": 0.2964259684085846,
      "learning_rate": 1.935814039257453e-05,
      "loss": 0.5913,
      "step": 7555
    },
    {
      "epoch": 0.2321137836758517,
      "grad_norm": 0.35290467739105225,
      "learning_rate": 1.9357970029241052e-05,
      "loss": 0.6317,
      "step": 7556
    },
    {
      "epoch": 0.23214450281080085,
      "grad_norm": 0.32346874475479126,
      "learning_rate": 1.935779964405138e-05,
      "loss": 0.6305,
      "step": 7557
    },
    {
      "epoch": 0.23217522194575002,
      "grad_norm": 0.3327173590660095,
      "learning_rate": 1.9357629237005916e-05,
      "loss": 0.5734,
      "step": 7558
    },
    {
      "epoch": 0.23220594108069917,
      "grad_norm": 0.4587315618991852,
      "learning_rate": 1.935745880810506e-05,
      "loss": 0.54,
      "step": 7559
    },
    {
      "epoch": 0.23223666021564832,
      "grad_norm": 0.3273179233074188,
      "learning_rate": 1.9357288357349196e-05,
      "loss": 0.5696,
      "step": 7560
    },
    {
      "epoch": 0.2322673793505975,
      "grad_norm": 1.009809970855713,
      "learning_rate": 1.935711788473874e-05,
      "loss": 0.5902,
      "step": 7561
    },
    {
      "epoch": 0.23229809848554664,
      "grad_norm": 0.31050586700439453,
      "learning_rate": 1.9356947390274076e-05,
      "loss": 0.5864,
      "step": 7562
    },
    {
      "epoch": 0.23232881762049581,
      "grad_norm": 0.37686458230018616,
      "learning_rate": 1.935677687395561e-05,
      "loss": 0.5637,
      "step": 7563
    },
    {
      "epoch": 0.23235953675544496,
      "grad_norm": 0.33764204382896423,
      "learning_rate": 1.935660633578374e-05,
      "loss": 0.5646,
      "step": 7564
    },
    {
      "epoch": 0.23239025589039414,
      "grad_norm": 0.3393482267856598,
      "learning_rate": 1.935643577575886e-05,
      "loss": 0.5195,
      "step": 7565
    },
    {
      "epoch": 0.23242097502534328,
      "grad_norm": 0.3533332347869873,
      "learning_rate": 1.9356265193881373e-05,
      "loss": 0.5764,
      "step": 7566
    },
    {
      "epoch": 0.23245169416029243,
      "grad_norm": 0.3632010519504547,
      "learning_rate": 1.935609459015167e-05,
      "loss": 0.5968,
      "step": 7567
    },
    {
      "epoch": 0.2324824132952416,
      "grad_norm": 0.36706238985061646,
      "learning_rate": 1.935592396457016e-05,
      "loss": 0.606,
      "step": 7568
    },
    {
      "epoch": 0.23251313243019076,
      "grad_norm": 0.34559687972068787,
      "learning_rate": 1.9355753317137233e-05,
      "loss": 0.5591,
      "step": 7569
    },
    {
      "epoch": 0.23254385156513993,
      "grad_norm": 0.6416429877281189,
      "learning_rate": 1.9355582647853294e-05,
      "loss": 0.6624,
      "step": 7570
    },
    {
      "epoch": 0.23257457070008908,
      "grad_norm": 0.35556235909461975,
      "learning_rate": 1.9355411956718735e-05,
      "loss": 0.5388,
      "step": 7571
    },
    {
      "epoch": 0.23260528983503825,
      "grad_norm": 0.3527929186820984,
      "learning_rate": 1.9355241243733957e-05,
      "loss": 0.5279,
      "step": 7572
    },
    {
      "epoch": 0.2326360089699874,
      "grad_norm": 0.5075631737709045,
      "learning_rate": 1.935507050889936e-05,
      "loss": 0.5424,
      "step": 7573
    },
    {
      "epoch": 0.23266672810493658,
      "grad_norm": 0.34188297390937805,
      "learning_rate": 1.9354899752215348e-05,
      "loss": 0.5585,
      "step": 7574
    },
    {
      "epoch": 0.23269744723988572,
      "grad_norm": 0.37462538480758667,
      "learning_rate": 1.9354728973682312e-05,
      "loss": 0.62,
      "step": 7575
    },
    {
      "epoch": 0.23272816637483487,
      "grad_norm": 0.3452500104904175,
      "learning_rate": 1.9354558173300652e-05,
      "loss": 0.565,
      "step": 7576
    },
    {
      "epoch": 0.23275888550978405,
      "grad_norm": 0.391716331243515,
      "learning_rate": 1.9354387351070765e-05,
      "loss": 0.5831,
      "step": 7577
    },
    {
      "epoch": 0.2327896046447332,
      "grad_norm": 0.3293367028236389,
      "learning_rate": 1.935421650699306e-05,
      "loss": 0.4861,
      "step": 7578
    },
    {
      "epoch": 0.23282032377968237,
      "grad_norm": 0.34202179312705994,
      "learning_rate": 1.9354045641067922e-05,
      "loss": 0.6636,
      "step": 7579
    },
    {
      "epoch": 0.23285104291463152,
      "grad_norm": 0.3431051969528198,
      "learning_rate": 1.935387475329576e-05,
      "loss": 0.6538,
      "step": 7580
    },
    {
      "epoch": 0.2328817620495807,
      "grad_norm": 0.3449808955192566,
      "learning_rate": 1.935370384367697e-05,
      "loss": 0.5674,
      "step": 7581
    },
    {
      "epoch": 0.23291248118452984,
      "grad_norm": 0.41646552085876465,
      "learning_rate": 1.9353532912211954e-05,
      "loss": 0.6111,
      "step": 7582
    },
    {
      "epoch": 0.23294320031947902,
      "grad_norm": 0.46686476469039917,
      "learning_rate": 1.9353361958901107e-05,
      "loss": 0.5666,
      "step": 7583
    },
    {
      "epoch": 0.23297391945442816,
      "grad_norm": 0.3711892366409302,
      "learning_rate": 1.935319098374483e-05,
      "loss": 0.6081,
      "step": 7584
    },
    {
      "epoch": 0.2330046385893773,
      "grad_norm": 0.40066757798194885,
      "learning_rate": 1.935301998674352e-05,
      "loss": 0.6595,
      "step": 7585
    },
    {
      "epoch": 0.2330353577243265,
      "grad_norm": 0.3249231278896332,
      "learning_rate": 1.9352848967897583e-05,
      "loss": 0.5701,
      "step": 7586
    },
    {
      "epoch": 0.23306607685927563,
      "grad_norm": 0.363248348236084,
      "learning_rate": 1.935267792720741e-05,
      "loss": 0.6281,
      "step": 7587
    },
    {
      "epoch": 0.2330967959942248,
      "grad_norm": 0.3286391794681549,
      "learning_rate": 1.9352506864673406e-05,
      "loss": 0.5526,
      "step": 7588
    },
    {
      "epoch": 0.23312751512917396,
      "grad_norm": 0.3623926043510437,
      "learning_rate": 1.935233578029597e-05,
      "loss": 0.6452,
      "step": 7589
    },
    {
      "epoch": 0.23315823426412313,
      "grad_norm": 0.34294041991233826,
      "learning_rate": 1.9352164674075496e-05,
      "loss": 0.6021,
      "step": 7590
    },
    {
      "epoch": 0.23318895339907228,
      "grad_norm": 0.32404443621635437,
      "learning_rate": 1.9351993546012394e-05,
      "loss": 0.5451,
      "step": 7591
    },
    {
      "epoch": 0.23321967253402145,
      "grad_norm": 0.40511974692344666,
      "learning_rate": 1.9351822396107057e-05,
      "loss": 0.5898,
      "step": 7592
    },
    {
      "epoch": 0.2332503916689706,
      "grad_norm": 0.3760119080543518,
      "learning_rate": 1.935165122435988e-05,
      "loss": 0.6774,
      "step": 7593
    },
    {
      "epoch": 0.23328111080391975,
      "grad_norm": 0.34347936511039734,
      "learning_rate": 1.9351480030771275e-05,
      "loss": 0.6008,
      "step": 7594
    },
    {
      "epoch": 0.23331182993886893,
      "grad_norm": 0.3501785397529602,
      "learning_rate": 1.9351308815341634e-05,
      "loss": 0.6046,
      "step": 7595
    },
    {
      "epoch": 0.23334254907381807,
      "grad_norm": 0.3187989592552185,
      "learning_rate": 1.9351137578071356e-05,
      "loss": 0.5268,
      "step": 7596
    },
    {
      "epoch": 0.23337326820876725,
      "grad_norm": 0.3335762619972229,
      "learning_rate": 1.9350966318960846e-05,
      "loss": 0.5611,
      "step": 7597
    },
    {
      "epoch": 0.2334039873437164,
      "grad_norm": 0.35123714804649353,
      "learning_rate": 1.93507950380105e-05,
      "loss": 0.5676,
      "step": 7598
    },
    {
      "epoch": 0.23343470647866557,
      "grad_norm": 0.3891028165817261,
      "learning_rate": 1.935062373522072e-05,
      "loss": 0.5636,
      "step": 7599
    },
    {
      "epoch": 0.23346542561361472,
      "grad_norm": 0.33317187428474426,
      "learning_rate": 1.9350452410591902e-05,
      "loss": 0.5371,
      "step": 7600
    },
    {
      "epoch": 0.2334961447485639,
      "grad_norm": 0.3676287531852722,
      "learning_rate": 1.935028106412445e-05,
      "loss": 0.5781,
      "step": 7601
    },
    {
      "epoch": 0.23352686388351304,
      "grad_norm": 0.35073280334472656,
      "learning_rate": 1.9350109695818766e-05,
      "loss": 0.6133,
      "step": 7602
    },
    {
      "epoch": 0.2335575830184622,
      "grad_norm": 0.33085063099861145,
      "learning_rate": 1.9349938305675247e-05,
      "loss": 0.6263,
      "step": 7603
    },
    {
      "epoch": 0.23358830215341136,
      "grad_norm": 0.3627588450908661,
      "learning_rate": 1.9349766893694294e-05,
      "loss": 0.6011,
      "step": 7604
    },
    {
      "epoch": 0.2336190212883605,
      "grad_norm": 0.3363712430000305,
      "learning_rate": 1.9349595459876306e-05,
      "loss": 0.4844,
      "step": 7605
    },
    {
      "epoch": 0.2336497404233097,
      "grad_norm": 0.35848844051361084,
      "learning_rate": 1.9349424004221687e-05,
      "loss": 0.6954,
      "step": 7606
    },
    {
      "epoch": 0.23368045955825884,
      "grad_norm": 0.32867228984832764,
      "learning_rate": 1.9349252526730833e-05,
      "loss": 0.5518,
      "step": 7607
    },
    {
      "epoch": 0.233711178693208,
      "grad_norm": 0.31755903363227844,
      "learning_rate": 1.934908102740415e-05,
      "loss": 0.5543,
      "step": 7608
    },
    {
      "epoch": 0.23374189782815716,
      "grad_norm": 0.3831489384174347,
      "learning_rate": 1.9348909506242033e-05,
      "loss": 0.5645,
      "step": 7609
    },
    {
      "epoch": 0.2337726169631063,
      "grad_norm": 0.4669325649738312,
      "learning_rate": 1.9348737963244886e-05,
      "loss": 0.5257,
      "step": 7610
    },
    {
      "epoch": 0.23380333609805548,
      "grad_norm": 0.3295033872127533,
      "learning_rate": 1.9348566398413107e-05,
      "loss": 0.6141,
      "step": 7611
    },
    {
      "epoch": 0.23383405523300463,
      "grad_norm": 0.37491798400878906,
      "learning_rate": 1.93483948117471e-05,
      "loss": 0.5444,
      "step": 7612
    },
    {
      "epoch": 0.2338647743679538,
      "grad_norm": 0.3535802662372589,
      "learning_rate": 1.9348223203247262e-05,
      "loss": 0.5679,
      "step": 7613
    },
    {
      "epoch": 0.23389549350290295,
      "grad_norm": 0.3212297856807709,
      "learning_rate": 1.9348051572913998e-05,
      "loss": 0.4943,
      "step": 7614
    },
    {
      "epoch": 0.23392621263785213,
      "grad_norm": 0.32565924525260925,
      "learning_rate": 1.9347879920747705e-05,
      "loss": 0.523,
      "step": 7615
    },
    {
      "epoch": 0.23395693177280127,
      "grad_norm": 0.4027366638183594,
      "learning_rate": 1.9347708246748788e-05,
      "loss": 0.5688,
      "step": 7616
    },
    {
      "epoch": 0.23398765090775045,
      "grad_norm": 0.3453314006328583,
      "learning_rate": 1.934753655091764e-05,
      "loss": 0.6907,
      "step": 7617
    },
    {
      "epoch": 0.2340183700426996,
      "grad_norm": 0.31549596786499023,
      "learning_rate": 1.9347364833254674e-05,
      "loss": 0.5399,
      "step": 7618
    },
    {
      "epoch": 0.23404908917764874,
      "grad_norm": 0.3753878176212311,
      "learning_rate": 1.9347193093760283e-05,
      "loss": 0.6061,
      "step": 7619
    },
    {
      "epoch": 0.23407980831259792,
      "grad_norm": 0.42831939458847046,
      "learning_rate": 1.934702133243487e-05,
      "loss": 0.5215,
      "step": 7620
    },
    {
      "epoch": 0.23411052744754707,
      "grad_norm": 0.3093508780002594,
      "learning_rate": 1.9346849549278833e-05,
      "loss": 0.5845,
      "step": 7621
    },
    {
      "epoch": 0.23414124658249624,
      "grad_norm": 0.37070682644844055,
      "learning_rate": 1.934667774429258e-05,
      "loss": 0.6169,
      "step": 7622
    },
    {
      "epoch": 0.2341719657174454,
      "grad_norm": 0.35813337564468384,
      "learning_rate": 1.9346505917476502e-05,
      "loss": 0.6357,
      "step": 7623
    },
    {
      "epoch": 0.23420268485239457,
      "grad_norm": 0.3317505121231079,
      "learning_rate": 1.9346334068831013e-05,
      "loss": 0.5885,
      "step": 7624
    },
    {
      "epoch": 0.2342334039873437,
      "grad_norm": 0.37164127826690674,
      "learning_rate": 1.9346162198356502e-05,
      "loss": 0.6082,
      "step": 7625
    },
    {
      "epoch": 0.2342641231222929,
      "grad_norm": 0.4579634964466095,
      "learning_rate": 1.9345990306053384e-05,
      "loss": 0.6358,
      "step": 7626
    },
    {
      "epoch": 0.23429484225724204,
      "grad_norm": 0.323894202709198,
      "learning_rate": 1.934581839192205e-05,
      "loss": 0.5901,
      "step": 7627
    },
    {
      "epoch": 0.23432556139219118,
      "grad_norm": 0.38115257024765015,
      "learning_rate": 1.9345646455962903e-05,
      "loss": 0.6052,
      "step": 7628
    },
    {
      "epoch": 0.23435628052714036,
      "grad_norm": 0.3939846158027649,
      "learning_rate": 1.9345474498176348e-05,
      "loss": 0.6334,
      "step": 7629
    },
    {
      "epoch": 0.2343869996620895,
      "grad_norm": 0.3436211943626404,
      "learning_rate": 1.9345302518562784e-05,
      "loss": 0.6211,
      "step": 7630
    },
    {
      "epoch": 0.23441771879703868,
      "grad_norm": 0.8204747438430786,
      "learning_rate": 1.934513051712261e-05,
      "loss": 0.5984,
      "step": 7631
    },
    {
      "epoch": 0.23444843793198783,
      "grad_norm": 0.3392956554889679,
      "learning_rate": 1.9344958493856235e-05,
      "loss": 0.6543,
      "step": 7632
    },
    {
      "epoch": 0.234479157066937,
      "grad_norm": 0.3686206638813019,
      "learning_rate": 1.9344786448764056e-05,
      "loss": 0.6674,
      "step": 7633
    },
    {
      "epoch": 0.23450987620188615,
      "grad_norm": 0.3295072019100189,
      "learning_rate": 1.9344614381846474e-05,
      "loss": 0.6194,
      "step": 7634
    },
    {
      "epoch": 0.23454059533683533,
      "grad_norm": 0.3368518352508545,
      "learning_rate": 1.9344442293103892e-05,
      "loss": 0.6064,
      "step": 7635
    },
    {
      "epoch": 0.23457131447178448,
      "grad_norm": 0.3816315531730652,
      "learning_rate": 1.9344270182536717e-05,
      "loss": 0.5524,
      "step": 7636
    },
    {
      "epoch": 0.23460203360673362,
      "grad_norm": 0.3528873920440674,
      "learning_rate": 1.934409805014534e-05,
      "loss": 0.5909,
      "step": 7637
    },
    {
      "epoch": 0.2346327527416828,
      "grad_norm": 0.3190333843231201,
      "learning_rate": 1.9343925895930175e-05,
      "loss": 0.6406,
      "step": 7638
    },
    {
      "epoch": 0.23466347187663195,
      "grad_norm": 0.4158407151699066,
      "learning_rate": 1.9343753719891615e-05,
      "loss": 0.5115,
      "step": 7639
    },
    {
      "epoch": 0.23469419101158112,
      "grad_norm": 0.8014741539955139,
      "learning_rate": 1.9343581522030068e-05,
      "loss": 0.5739,
      "step": 7640
    },
    {
      "epoch": 0.23472491014653027,
      "grad_norm": 0.39527711272239685,
      "learning_rate": 1.9343409302345934e-05,
      "loss": 0.5955,
      "step": 7641
    },
    {
      "epoch": 0.23475562928147944,
      "grad_norm": 0.37352848052978516,
      "learning_rate": 1.934323706083961e-05,
      "loss": 0.6362,
      "step": 7642
    },
    {
      "epoch": 0.2347863484164286,
      "grad_norm": 0.38728877902030945,
      "learning_rate": 1.9343064797511508e-05,
      "loss": 0.6266,
      "step": 7643
    },
    {
      "epoch": 0.23481706755137774,
      "grad_norm": 0.34163758158683777,
      "learning_rate": 1.9342892512362026e-05,
      "loss": 0.4814,
      "step": 7644
    },
    {
      "epoch": 0.23484778668632691,
      "grad_norm": 0.3481205701828003,
      "learning_rate": 1.9342720205391566e-05,
      "loss": 0.6581,
      "step": 7645
    },
    {
      "epoch": 0.23487850582127606,
      "grad_norm": 0.4333837926387787,
      "learning_rate": 1.9342547876600528e-05,
      "loss": 0.5261,
      "step": 7646
    },
    {
      "epoch": 0.23490922495622524,
      "grad_norm": 0.356250524520874,
      "learning_rate": 1.9342375525989318e-05,
      "loss": 0.5447,
      "step": 7647
    },
    {
      "epoch": 0.23493994409117439,
      "grad_norm": 0.3050040602684021,
      "learning_rate": 1.934220315355834e-05,
      "loss": 0.5087,
      "step": 7648
    },
    {
      "epoch": 0.23497066322612356,
      "grad_norm": 0.35950228571891785,
      "learning_rate": 1.934203075930799e-05,
      "loss": 0.5332,
      "step": 7649
    },
    {
      "epoch": 0.2350013823610727,
      "grad_norm": 0.3559632897377014,
      "learning_rate": 1.934185834323868e-05,
      "loss": 0.6611,
      "step": 7650
    },
    {
      "epoch": 0.23503210149602188,
      "grad_norm": 0.3994937539100647,
      "learning_rate": 1.93416859053508e-05,
      "loss": 0.6053,
      "step": 7651
    },
    {
      "epoch": 0.23506282063097103,
      "grad_norm": 0.3113624155521393,
      "learning_rate": 1.9341513445644765e-05,
      "loss": 0.5671,
      "step": 7652
    },
    {
      "epoch": 0.23509353976592018,
      "grad_norm": 0.31709522008895874,
      "learning_rate": 1.934134096412097e-05,
      "loss": 0.5896,
      "step": 7653
    },
    {
      "epoch": 0.23512425890086935,
      "grad_norm": 0.3245203495025635,
      "learning_rate": 1.9341168460779824e-05,
      "loss": 0.4939,
      "step": 7654
    },
    {
      "epoch": 0.2351549780358185,
      "grad_norm": 0.3531922399997711,
      "learning_rate": 1.9340995935621727e-05,
      "loss": 0.6417,
      "step": 7655
    },
    {
      "epoch": 0.23518569717076768,
      "grad_norm": 0.3636716604232788,
      "learning_rate": 1.9340823388647077e-05,
      "loss": 0.5688,
      "step": 7656
    },
    {
      "epoch": 0.23521641630571682,
      "grad_norm": 0.36881935596466064,
      "learning_rate": 1.9340650819856287e-05,
      "loss": 0.4997,
      "step": 7657
    },
    {
      "epoch": 0.235247135440666,
      "grad_norm": 0.36146917939186096,
      "learning_rate": 1.934047822924975e-05,
      "loss": 0.5638,
      "step": 7658
    },
    {
      "epoch": 0.23527785457561515,
      "grad_norm": 0.3437976539134979,
      "learning_rate": 1.934030561682788e-05,
      "loss": 0.5981,
      "step": 7659
    },
    {
      "epoch": 0.23530857371056432,
      "grad_norm": 0.32935625314712524,
      "learning_rate": 1.9340132982591066e-05,
      "loss": 0.6301,
      "step": 7660
    },
    {
      "epoch": 0.23533929284551347,
      "grad_norm": 0.32763633131980896,
      "learning_rate": 1.9339960326539727e-05,
      "loss": 0.5616,
      "step": 7661
    },
    {
      "epoch": 0.23537001198046262,
      "grad_norm": 0.351895272731781,
      "learning_rate": 1.9339787648674252e-05,
      "loss": 0.5391,
      "step": 7662
    },
    {
      "epoch": 0.2354007311154118,
      "grad_norm": 0.36082878708839417,
      "learning_rate": 1.9339614948995055e-05,
      "loss": 0.587,
      "step": 7663
    },
    {
      "epoch": 0.23543145025036094,
      "grad_norm": 0.3583157956600189,
      "learning_rate": 1.933944222750253e-05,
      "loss": 0.5545,
      "step": 7664
    },
    {
      "epoch": 0.23546216938531012,
      "grad_norm": 0.38586872816085815,
      "learning_rate": 1.9339269484197092e-05,
      "loss": 0.6078,
      "step": 7665
    },
    {
      "epoch": 0.23549288852025926,
      "grad_norm": 0.3221229910850525,
      "learning_rate": 1.9339096719079132e-05,
      "loss": 0.515,
      "step": 7666
    },
    {
      "epoch": 0.23552360765520844,
      "grad_norm": 0.4187864363193512,
      "learning_rate": 1.9338923932149064e-05,
      "loss": 0.6033,
      "step": 7667
    },
    {
      "epoch": 0.2355543267901576,
      "grad_norm": 0.5127690434455872,
      "learning_rate": 1.9338751123407284e-05,
      "loss": 0.6238,
      "step": 7668
    },
    {
      "epoch": 0.23558504592510676,
      "grad_norm": 0.49704238772392273,
      "learning_rate": 1.93385782928542e-05,
      "loss": 0.4507,
      "step": 7669
    },
    {
      "epoch": 0.2356157650600559,
      "grad_norm": 0.4091121554374695,
      "learning_rate": 1.9338405440490212e-05,
      "loss": 0.6229,
      "step": 7670
    },
    {
      "epoch": 0.23564648419500506,
      "grad_norm": 0.36017656326293945,
      "learning_rate": 1.933823256631573e-05,
      "loss": 0.5882,
      "step": 7671
    },
    {
      "epoch": 0.23567720332995423,
      "grad_norm": 0.3415447175502777,
      "learning_rate": 1.933805967033115e-05,
      "loss": 0.5652,
      "step": 7672
    },
    {
      "epoch": 0.23570792246490338,
      "grad_norm": 0.34846335649490356,
      "learning_rate": 1.933788675253688e-05,
      "loss": 0.5619,
      "step": 7673
    },
    {
      "epoch": 0.23573864159985256,
      "grad_norm": 0.31977617740631104,
      "learning_rate": 1.9337713812933324e-05,
      "loss": 0.5518,
      "step": 7674
    },
    {
      "epoch": 0.2357693607348017,
      "grad_norm": 0.3410705029964447,
      "learning_rate": 1.9337540851520885e-05,
      "loss": 0.5571,
      "step": 7675
    },
    {
      "epoch": 0.23580007986975088,
      "grad_norm": 0.3209608197212219,
      "learning_rate": 1.9337367868299968e-05,
      "loss": 0.5788,
      "step": 7676
    },
    {
      "epoch": 0.23583079900470003,
      "grad_norm": 0.33878567814826965,
      "learning_rate": 1.9337194863270974e-05,
      "loss": 0.6127,
      "step": 7677
    },
    {
      "epoch": 0.2358615181396492,
      "grad_norm": 0.30212122201919556,
      "learning_rate": 1.933702183643431e-05,
      "loss": 0.5545,
      "step": 7678
    },
    {
      "epoch": 0.23589223727459835,
      "grad_norm": 0.3538045585155487,
      "learning_rate": 1.9336848787790384e-05,
      "loss": 0.5305,
      "step": 7679
    },
    {
      "epoch": 0.2359229564095475,
      "grad_norm": 0.39698582887649536,
      "learning_rate": 1.933667571733959e-05,
      "loss": 0.5815,
      "step": 7680
    },
    {
      "epoch": 0.23595367554449667,
      "grad_norm": 0.31713250279426575,
      "learning_rate": 1.9336502625082342e-05,
      "loss": 0.5977,
      "step": 7681
    },
    {
      "epoch": 0.23598439467944582,
      "grad_norm": 0.36416423320770264,
      "learning_rate": 1.9336329511019035e-05,
      "loss": 0.5352,
      "step": 7682
    },
    {
      "epoch": 0.236015113814395,
      "grad_norm": 0.3482380509376526,
      "learning_rate": 1.9336156375150082e-05,
      "loss": 0.6069,
      "step": 7683
    },
    {
      "epoch": 0.23604583294934414,
      "grad_norm": 0.3824409246444702,
      "learning_rate": 1.933598321747588e-05,
      "loss": 0.5911,
      "step": 7684
    },
    {
      "epoch": 0.23607655208429332,
      "grad_norm": 0.3841603994369507,
      "learning_rate": 1.9335810037996844e-05,
      "loss": 0.6086,
      "step": 7685
    },
    {
      "epoch": 0.23610727121924246,
      "grad_norm": 0.32101744413375854,
      "learning_rate": 1.933563683671337e-05,
      "loss": 0.5019,
      "step": 7686
    },
    {
      "epoch": 0.2361379903541916,
      "grad_norm": 0.3927426040172577,
      "learning_rate": 1.933546361362586e-05,
      "loss": 0.6444,
      "step": 7687
    },
    {
      "epoch": 0.2361687094891408,
      "grad_norm": 0.38245734572410583,
      "learning_rate": 1.9335290368734727e-05,
      "loss": 0.5753,
      "step": 7688
    },
    {
      "epoch": 0.23619942862408994,
      "grad_norm": 0.32920408248901367,
      "learning_rate": 1.9335117102040366e-05,
      "loss": 0.6061,
      "step": 7689
    },
    {
      "epoch": 0.2362301477590391,
      "grad_norm": 0.44558021426200867,
      "learning_rate": 1.933494381354319e-05,
      "loss": 0.5861,
      "step": 7690
    },
    {
      "epoch": 0.23626086689398826,
      "grad_norm": 0.4034399688243866,
      "learning_rate": 1.93347705032436e-05,
      "loss": 0.6005,
      "step": 7691
    },
    {
      "epoch": 0.23629158602893743,
      "grad_norm": 0.33713221549987793,
      "learning_rate": 1.9334597171142002e-05,
      "loss": 0.5933,
      "step": 7692
    },
    {
      "epoch": 0.23632230516388658,
      "grad_norm": 0.4244551360607147,
      "learning_rate": 1.9334423817238803e-05,
      "loss": 0.6989,
      "step": 7693
    },
    {
      "epoch": 0.23635302429883576,
      "grad_norm": 0.3447105586528778,
      "learning_rate": 1.9334250441534405e-05,
      "loss": 0.6015,
      "step": 7694
    },
    {
      "epoch": 0.2363837434337849,
      "grad_norm": 0.34805458784103394,
      "learning_rate": 1.933407704402921e-05,
      "loss": 0.5785,
      "step": 7695
    },
    {
      "epoch": 0.23641446256873405,
      "grad_norm": 0.32866689562797546,
      "learning_rate": 1.9333903624723627e-05,
      "loss": 0.5229,
      "step": 7696
    },
    {
      "epoch": 0.23644518170368323,
      "grad_norm": 0.32703688740730286,
      "learning_rate": 1.933373018361806e-05,
      "loss": 0.6624,
      "step": 7697
    },
    {
      "epoch": 0.23647590083863237,
      "grad_norm": 0.4280700087547302,
      "learning_rate": 1.9333556720712915e-05,
      "loss": 0.5515,
      "step": 7698
    },
    {
      "epoch": 0.23650661997358155,
      "grad_norm": 0.3575366139411926,
      "learning_rate": 1.9333383236008597e-05,
      "loss": 0.6291,
      "step": 7699
    },
    {
      "epoch": 0.2365373391085307,
      "grad_norm": 0.33593156933784485,
      "learning_rate": 1.933320972950551e-05,
      "loss": 0.5783,
      "step": 7700
    },
    {
      "epoch": 0.23656805824347987,
      "grad_norm": 0.31856995820999146,
      "learning_rate": 1.933303620120406e-05,
      "loss": 0.5816,
      "step": 7701
    },
    {
      "epoch": 0.23659877737842902,
      "grad_norm": 0.4161600172519684,
      "learning_rate": 1.933286265110465e-05,
      "loss": 0.7215,
      "step": 7702
    },
    {
      "epoch": 0.2366294965133782,
      "grad_norm": 0.3353427052497864,
      "learning_rate": 1.933268907920769e-05,
      "loss": 0.6098,
      "step": 7703
    },
    {
      "epoch": 0.23666021564832734,
      "grad_norm": 0.39298662543296814,
      "learning_rate": 1.9332515485513582e-05,
      "loss": 0.5791,
      "step": 7704
    },
    {
      "epoch": 0.2366909347832765,
      "grad_norm": 0.3554583787918091,
      "learning_rate": 1.9332341870022736e-05,
      "loss": 0.5708,
      "step": 7705
    },
    {
      "epoch": 0.23672165391822567,
      "grad_norm": 0.33231639862060547,
      "learning_rate": 1.933216823273555e-05,
      "loss": 0.6123,
      "step": 7706
    },
    {
      "epoch": 0.2367523730531748,
      "grad_norm": 0.32306018471717834,
      "learning_rate": 1.9331994573652434e-05,
      "loss": 0.5949,
      "step": 7707
    },
    {
      "epoch": 0.236783092188124,
      "grad_norm": 0.3217405378818512,
      "learning_rate": 1.933182089277379e-05,
      "loss": 0.5405,
      "step": 7708
    },
    {
      "epoch": 0.23681381132307314,
      "grad_norm": 0.36560437083244324,
      "learning_rate": 1.933164719010003e-05,
      "loss": 0.6765,
      "step": 7709
    },
    {
      "epoch": 0.2368445304580223,
      "grad_norm": 0.3603482246398926,
      "learning_rate": 1.9331473465631557e-05,
      "loss": 0.5717,
      "step": 7710
    },
    {
      "epoch": 0.23687524959297146,
      "grad_norm": 0.6808732151985168,
      "learning_rate": 1.9331299719368775e-05,
      "loss": 0.6658,
      "step": 7711
    },
    {
      "epoch": 0.23690596872792063,
      "grad_norm": 0.3710639774799347,
      "learning_rate": 1.933112595131209e-05,
      "loss": 0.6289,
      "step": 7712
    },
    {
      "epoch": 0.23693668786286978,
      "grad_norm": 0.30413395166397095,
      "learning_rate": 1.9330952161461905e-05,
      "loss": 0.5363,
      "step": 7713
    },
    {
      "epoch": 0.23696740699781893,
      "grad_norm": 0.3688679337501526,
      "learning_rate": 1.933077834981864e-05,
      "loss": 0.6192,
      "step": 7714
    },
    {
      "epoch": 0.2369981261327681,
      "grad_norm": 0.35575923323631287,
      "learning_rate": 1.933060451638268e-05,
      "loss": 0.5849,
      "step": 7715
    },
    {
      "epoch": 0.23702884526771725,
      "grad_norm": 0.33094725012779236,
      "learning_rate": 1.9330430661154446e-05,
      "loss": 0.556,
      "step": 7716
    },
    {
      "epoch": 0.23705956440266643,
      "grad_norm": 0.31887176632881165,
      "learning_rate": 1.933025678413434e-05,
      "loss": 0.5694,
      "step": 7717
    },
    {
      "epoch": 0.23709028353761558,
      "grad_norm": 0.3657797873020172,
      "learning_rate": 1.9330082885322764e-05,
      "loss": 0.6719,
      "step": 7718
    },
    {
      "epoch": 0.23712100267256475,
      "grad_norm": 0.3324965536594391,
      "learning_rate": 1.9329908964720133e-05,
      "loss": 0.6388,
      "step": 7719
    },
    {
      "epoch": 0.2371517218075139,
      "grad_norm": 0.33415529131889343,
      "learning_rate": 1.9329735022326845e-05,
      "loss": 0.581,
      "step": 7720
    },
    {
      "epoch": 0.23718244094246305,
      "grad_norm": 0.3483179807662964,
      "learning_rate": 1.932956105814331e-05,
      "loss": 0.5491,
      "step": 7721
    },
    {
      "epoch": 0.23721316007741222,
      "grad_norm": 0.3640226423740387,
      "learning_rate": 1.9329387072169937e-05,
      "loss": 0.5456,
      "step": 7722
    },
    {
      "epoch": 0.23724387921236137,
      "grad_norm": 0.36551204323768616,
      "learning_rate": 1.9329213064407125e-05,
      "loss": 0.624,
      "step": 7723
    },
    {
      "epoch": 0.23727459834731054,
      "grad_norm": 0.3591916263103485,
      "learning_rate": 1.9329039034855285e-05,
      "loss": 0.5748,
      "step": 7724
    },
    {
      "epoch": 0.2373053174822597,
      "grad_norm": 0.33495157957077026,
      "learning_rate": 1.9328864983514823e-05,
      "loss": 0.5929,
      "step": 7725
    },
    {
      "epoch": 0.23733603661720887,
      "grad_norm": 0.3485173285007477,
      "learning_rate": 1.9328690910386142e-05,
      "loss": 0.6303,
      "step": 7726
    },
    {
      "epoch": 0.23736675575215802,
      "grad_norm": 0.3341186046600342,
      "learning_rate": 1.9328516815469657e-05,
      "loss": 0.5982,
      "step": 7727
    },
    {
      "epoch": 0.2373974748871072,
      "grad_norm": 0.33924180269241333,
      "learning_rate": 1.9328342698765767e-05,
      "loss": 0.5341,
      "step": 7728
    },
    {
      "epoch": 0.23742819402205634,
      "grad_norm": 0.3323246240615845,
      "learning_rate": 1.932816856027488e-05,
      "loss": 0.5837,
      "step": 7729
    },
    {
      "epoch": 0.23745891315700549,
      "grad_norm": 0.36458349227905273,
      "learning_rate": 1.9327994399997407e-05,
      "loss": 0.6148,
      "step": 7730
    },
    {
      "epoch": 0.23748963229195466,
      "grad_norm": 0.34718066453933716,
      "learning_rate": 1.9327820217933747e-05,
      "loss": 0.6721,
      "step": 7731
    },
    {
      "epoch": 0.2375203514269038,
      "grad_norm": 0.3540247976779938,
      "learning_rate": 1.9327646014084315e-05,
      "loss": 0.6331,
      "step": 7732
    },
    {
      "epoch": 0.23755107056185298,
      "grad_norm": 0.3684503734111786,
      "learning_rate": 1.9327471788449514e-05,
      "loss": 0.5919,
      "step": 7733
    },
    {
      "epoch": 0.23758178969680213,
      "grad_norm": 0.46011537313461304,
      "learning_rate": 1.932729754102975e-05,
      "loss": 0.6184,
      "step": 7734
    },
    {
      "epoch": 0.2376125088317513,
      "grad_norm": 0.33986809849739075,
      "learning_rate": 1.9327123271825436e-05,
      "loss": 0.5796,
      "step": 7735
    },
    {
      "epoch": 0.23764322796670045,
      "grad_norm": 0.3374120891094208,
      "learning_rate": 1.9326948980836967e-05,
      "loss": 0.5851,
      "step": 7736
    },
    {
      "epoch": 0.23767394710164963,
      "grad_norm": 3.4150466918945312,
      "learning_rate": 1.9326774668064763e-05,
      "loss": 0.6212,
      "step": 7737
    },
    {
      "epoch": 0.23770466623659878,
      "grad_norm": 0.33239367604255676,
      "learning_rate": 1.932660033350922e-05,
      "loss": 0.5369,
      "step": 7738
    },
    {
      "epoch": 0.23773538537154792,
      "grad_norm": 0.3425189256668091,
      "learning_rate": 1.9326425977170754e-05,
      "loss": 0.5843,
      "step": 7739
    },
    {
      "epoch": 0.2377661045064971,
      "grad_norm": 0.3650931119918823,
      "learning_rate": 1.932625159904977e-05,
      "loss": 0.643,
      "step": 7740
    },
    {
      "epoch": 0.23779682364144625,
      "grad_norm": 0.33989810943603516,
      "learning_rate": 1.932607719914667e-05,
      "loss": 0.6032,
      "step": 7741
    },
    {
      "epoch": 0.23782754277639542,
      "grad_norm": 0.33067411184310913,
      "learning_rate": 1.932590277746187e-05,
      "loss": 0.5687,
      "step": 7742
    },
    {
      "epoch": 0.23785826191134457,
      "grad_norm": 0.40546363592147827,
      "learning_rate": 1.932572833399577e-05,
      "loss": 0.589,
      "step": 7743
    },
    {
      "epoch": 0.23788898104629375,
      "grad_norm": 0.36863774061203003,
      "learning_rate": 1.932555386874878e-05,
      "loss": 0.6062,
      "step": 7744
    },
    {
      "epoch": 0.2379197001812429,
      "grad_norm": 0.31500327587127686,
      "learning_rate": 1.932537938172131e-05,
      "loss": 0.5866,
      "step": 7745
    },
    {
      "epoch": 0.23795041931619207,
      "grad_norm": 0.38562583923339844,
      "learning_rate": 1.932520487291376e-05,
      "loss": 0.6745,
      "step": 7746
    },
    {
      "epoch": 0.23798113845114122,
      "grad_norm": 0.681908905506134,
      "learning_rate": 1.9325030342326547e-05,
      "loss": 0.5756,
      "step": 7747
    },
    {
      "epoch": 0.23801185758609036,
      "grad_norm": 0.35309386253356934,
      "learning_rate": 1.9324855789960076e-05,
      "loss": 0.5749,
      "step": 7748
    },
    {
      "epoch": 0.23804257672103954,
      "grad_norm": 0.3863277733325958,
      "learning_rate": 1.9324681215814748e-05,
      "loss": 0.6399,
      "step": 7749
    },
    {
      "epoch": 0.2380732958559887,
      "grad_norm": 0.30405014753341675,
      "learning_rate": 1.932450661989098e-05,
      "loss": 0.5104,
      "step": 7750
    },
    {
      "epoch": 0.23810401499093786,
      "grad_norm": 0.387319415807724,
      "learning_rate": 1.9324332002189175e-05,
      "loss": 0.6099,
      "step": 7751
    },
    {
      "epoch": 0.238134734125887,
      "grad_norm": 0.3496610224246979,
      "learning_rate": 1.932415736270974e-05,
      "loss": 0.5512,
      "step": 7752
    },
    {
      "epoch": 0.23816545326083619,
      "grad_norm": 0.3087685704231262,
      "learning_rate": 1.9323982701453087e-05,
      "loss": 0.665,
      "step": 7753
    },
    {
      "epoch": 0.23819617239578533,
      "grad_norm": 0.34265461564064026,
      "learning_rate": 1.9323808018419617e-05,
      "loss": 0.5932,
      "step": 7754
    },
    {
      "epoch": 0.2382268915307345,
      "grad_norm": 0.3184657096862793,
      "learning_rate": 1.9323633313609743e-05,
      "loss": 0.533,
      "step": 7755
    },
    {
      "epoch": 0.23825761066568366,
      "grad_norm": 0.4897792637348175,
      "learning_rate": 1.9323458587023872e-05,
      "loss": 0.5107,
      "step": 7756
    },
    {
      "epoch": 0.2382883298006328,
      "grad_norm": 0.35523632168769836,
      "learning_rate": 1.9323283838662417e-05,
      "loss": 0.579,
      "step": 7757
    },
    {
      "epoch": 0.23831904893558198,
      "grad_norm": 0.330981582403183,
      "learning_rate": 1.9323109068525778e-05,
      "loss": 0.5497,
      "step": 7758
    },
    {
      "epoch": 0.23834976807053113,
      "grad_norm": 0.33457767963409424,
      "learning_rate": 1.9322934276614368e-05,
      "loss": 0.5733,
      "step": 7759
    },
    {
      "epoch": 0.2383804872054803,
      "grad_norm": 0.3411354422569275,
      "learning_rate": 1.932275946292859e-05,
      "loss": 0.5051,
      "step": 7760
    },
    {
      "epoch": 0.23841120634042945,
      "grad_norm": 0.3682728111743927,
      "learning_rate": 1.9322584627468858e-05,
      "loss": 0.6866,
      "step": 7761
    },
    {
      "epoch": 0.23844192547537862,
      "grad_norm": 0.3637903928756714,
      "learning_rate": 1.9322409770235578e-05,
      "loss": 0.5805,
      "step": 7762
    },
    {
      "epoch": 0.23847264461032777,
      "grad_norm": 0.39284321665763855,
      "learning_rate": 1.9322234891229164e-05,
      "loss": 0.6027,
      "step": 7763
    },
    {
      "epoch": 0.23850336374527692,
      "grad_norm": 0.35097989439964294,
      "learning_rate": 1.9322059990450015e-05,
      "loss": 0.5623,
      "step": 7764
    },
    {
      "epoch": 0.2385340828802261,
      "grad_norm": 0.32582956552505493,
      "learning_rate": 1.932188506789854e-05,
      "loss": 0.543,
      "step": 7765
    },
    {
      "epoch": 0.23856480201517524,
      "grad_norm": 0.34813395142555237,
      "learning_rate": 1.932171012357516e-05,
      "loss": 0.6122,
      "step": 7766
    },
    {
      "epoch": 0.23859552115012442,
      "grad_norm": 0.3784501254558563,
      "learning_rate": 1.932153515748027e-05,
      "loss": 0.5643,
      "step": 7767
    },
    {
      "epoch": 0.23862624028507357,
      "grad_norm": 0.38413646817207336,
      "learning_rate": 1.9321360169614287e-05,
      "loss": 0.5535,
      "step": 7768
    },
    {
      "epoch": 0.23865695942002274,
      "grad_norm": 0.406183123588562,
      "learning_rate": 1.932118515997761e-05,
      "loss": 0.638,
      "step": 7769
    },
    {
      "epoch": 0.2386876785549719,
      "grad_norm": 0.3350162208080292,
      "learning_rate": 1.932101012857066e-05,
      "loss": 0.5746,
      "step": 7770
    },
    {
      "epoch": 0.23871839768992106,
      "grad_norm": 0.33829784393310547,
      "learning_rate": 1.932083507539384e-05,
      "loss": 0.5523,
      "step": 7771
    },
    {
      "epoch": 0.2387491168248702,
      "grad_norm": 0.31705373525619507,
      "learning_rate": 1.9320660000447555e-05,
      "loss": 0.6205,
      "step": 7772
    },
    {
      "epoch": 0.23877983595981936,
      "grad_norm": 0.3191987872123718,
      "learning_rate": 1.9320484903732217e-05,
      "loss": 0.5449,
      "step": 7773
    },
    {
      "epoch": 0.23881055509476853,
      "grad_norm": 0.36392101645469666,
      "learning_rate": 1.932030978524824e-05,
      "loss": 0.7129,
      "step": 7774
    },
    {
      "epoch": 0.23884127422971768,
      "grad_norm": 0.3997855484485626,
      "learning_rate": 1.9320134644996024e-05,
      "loss": 0.5482,
      "step": 7775
    },
    {
      "epoch": 0.23887199336466686,
      "grad_norm": 0.3979213535785675,
      "learning_rate": 1.9319959482975987e-05,
      "loss": 0.59,
      "step": 7776
    },
    {
      "epoch": 0.238902712499616,
      "grad_norm": 0.3063737452030182,
      "learning_rate": 1.931978429918853e-05,
      "loss": 0.6125,
      "step": 7777
    },
    {
      "epoch": 0.23893343163456518,
      "grad_norm": 0.33630600571632385,
      "learning_rate": 1.931960909363407e-05,
      "loss": 0.5853,
      "step": 7778
    },
    {
      "epoch": 0.23896415076951433,
      "grad_norm": 0.3408201038837433,
      "learning_rate": 1.931943386631301e-05,
      "loss": 0.5599,
      "step": 7779
    },
    {
      "epoch": 0.2389948699044635,
      "grad_norm": 0.3145720660686493,
      "learning_rate": 1.931925861722576e-05,
      "loss": 0.562,
      "step": 7780
    },
    {
      "epoch": 0.23902558903941265,
      "grad_norm": 0.32870301604270935,
      "learning_rate": 1.931908334637273e-05,
      "loss": 0.5254,
      "step": 7781
    },
    {
      "epoch": 0.2390563081743618,
      "grad_norm": 0.3488176763057709,
      "learning_rate": 1.931890805375433e-05,
      "loss": 0.5877,
      "step": 7782
    },
    {
      "epoch": 0.23908702730931097,
      "grad_norm": 0.3338836133480072,
      "learning_rate": 1.9318732739370976e-05,
      "loss": 0.522,
      "step": 7783
    },
    {
      "epoch": 0.23911774644426012,
      "grad_norm": 0.3120950162410736,
      "learning_rate": 1.9318557403223062e-05,
      "loss": 0.5908,
      "step": 7784
    },
    {
      "epoch": 0.2391484655792093,
      "grad_norm": 0.3061603307723999,
      "learning_rate": 1.9318382045311013e-05,
      "loss": 0.4664,
      "step": 7785
    },
    {
      "epoch": 0.23917918471415844,
      "grad_norm": 0.3127819299697876,
      "learning_rate": 1.9318206665635228e-05,
      "loss": 0.6252,
      "step": 7786
    },
    {
      "epoch": 0.23920990384910762,
      "grad_norm": 0.33447209000587463,
      "learning_rate": 1.931803126419612e-05,
      "loss": 0.5402,
      "step": 7787
    },
    {
      "epoch": 0.23924062298405677,
      "grad_norm": 0.3591729700565338,
      "learning_rate": 1.9317855840994104e-05,
      "loss": 0.6614,
      "step": 7788
    },
    {
      "epoch": 0.23927134211900594,
      "grad_norm": 0.3287372589111328,
      "learning_rate": 1.9317680396029582e-05,
      "loss": 0.5756,
      "step": 7789
    },
    {
      "epoch": 0.2393020612539551,
      "grad_norm": 0.32909464836120605,
      "learning_rate": 1.9317504929302967e-05,
      "loss": 0.6342,
      "step": 7790
    },
    {
      "epoch": 0.23933278038890424,
      "grad_norm": 0.6835966110229492,
      "learning_rate": 1.9317329440814667e-05,
      "loss": 0.5193,
      "step": 7791
    },
    {
      "epoch": 0.2393634995238534,
      "grad_norm": 0.36104729771614075,
      "learning_rate": 1.9317153930565094e-05,
      "loss": 0.5853,
      "step": 7792
    },
    {
      "epoch": 0.23939421865880256,
      "grad_norm": 0.3740997314453125,
      "learning_rate": 1.931697839855466e-05,
      "loss": 0.6074,
      "step": 7793
    },
    {
      "epoch": 0.23942493779375174,
      "grad_norm": 0.3470056653022766,
      "learning_rate": 1.931680284478377e-05,
      "loss": 0.5723,
      "step": 7794
    },
    {
      "epoch": 0.23945565692870088,
      "grad_norm": 0.35116130113601685,
      "learning_rate": 1.9316627269252836e-05,
      "loss": 0.6979,
      "step": 7795
    },
    {
      "epoch": 0.23948637606365006,
      "grad_norm": 0.37324821949005127,
      "learning_rate": 1.931645167196227e-05,
      "loss": 0.5444,
      "step": 7796
    },
    {
      "epoch": 0.2395170951985992,
      "grad_norm": 0.34813225269317627,
      "learning_rate": 1.9316276052912476e-05,
      "loss": 0.6328,
      "step": 7797
    },
    {
      "epoch": 0.23954781433354835,
      "grad_norm": 0.37935948371887207,
      "learning_rate": 1.9316100412103873e-05,
      "loss": 0.5927,
      "step": 7798
    },
    {
      "epoch": 0.23957853346849753,
      "grad_norm": 0.3527315855026245,
      "learning_rate": 1.9315924749536865e-05,
      "loss": 0.5933,
      "step": 7799
    },
    {
      "epoch": 0.23960925260344668,
      "grad_norm": 0.3751799762248993,
      "learning_rate": 1.9315749065211867e-05,
      "loss": 0.6186,
      "step": 7800
    },
    {
      "epoch": 0.23963997173839585,
      "grad_norm": 0.32956886291503906,
      "learning_rate": 1.9315573359129282e-05,
      "loss": 0.5644,
      "step": 7801
    },
    {
      "epoch": 0.239670690873345,
      "grad_norm": 0.35524246096611023,
      "learning_rate": 1.931539763128953e-05,
      "loss": 0.6097,
      "step": 7802
    },
    {
      "epoch": 0.23970141000829417,
      "grad_norm": 0.35321658849716187,
      "learning_rate": 1.9315221881693012e-05,
      "loss": 0.5968,
      "step": 7803
    },
    {
      "epoch": 0.23973212914324332,
      "grad_norm": 0.40220344066619873,
      "learning_rate": 1.9315046110340143e-05,
      "loss": 0.6235,
      "step": 7804
    },
    {
      "epoch": 0.2397628482781925,
      "grad_norm": 0.32326823472976685,
      "learning_rate": 1.9314870317231333e-05,
      "loss": 0.6687,
      "step": 7805
    },
    {
      "epoch": 0.23979356741314165,
      "grad_norm": 0.3570176362991333,
      "learning_rate": 1.9314694502366994e-05,
      "loss": 0.5888,
      "step": 7806
    },
    {
      "epoch": 0.2398242865480908,
      "grad_norm": 0.33186575770378113,
      "learning_rate": 1.9314518665747536e-05,
      "loss": 0.595,
      "step": 7807
    },
    {
      "epoch": 0.23985500568303997,
      "grad_norm": 0.3309374451637268,
      "learning_rate": 1.931434280737337e-05,
      "loss": 0.6048,
      "step": 7808
    },
    {
      "epoch": 0.23988572481798912,
      "grad_norm": 0.384705513715744,
      "learning_rate": 1.9314166927244903e-05,
      "loss": 0.6753,
      "step": 7809
    },
    {
      "epoch": 0.2399164439529383,
      "grad_norm": 0.33834895491600037,
      "learning_rate": 1.9313991025362552e-05,
      "loss": 0.617,
      "step": 7810
    },
    {
      "epoch": 0.23994716308788744,
      "grad_norm": 0.36451688408851624,
      "learning_rate": 1.931381510172672e-05,
      "loss": 0.563,
      "step": 7811
    },
    {
      "epoch": 0.2399778822228366,
      "grad_norm": 0.34867507219314575,
      "learning_rate": 1.9313639156337827e-05,
      "loss": 0.6688,
      "step": 7812
    },
    {
      "epoch": 0.24000860135778576,
      "grad_norm": 0.34765496850013733,
      "learning_rate": 1.9313463189196277e-05,
      "loss": 0.5385,
      "step": 7813
    },
    {
      "epoch": 0.24003932049273494,
      "grad_norm": 0.3552313446998596,
      "learning_rate": 1.9313287200302487e-05,
      "loss": 0.6122,
      "step": 7814
    },
    {
      "epoch": 0.24007003962768408,
      "grad_norm": 0.33733466267585754,
      "learning_rate": 1.931311118965686e-05,
      "loss": 0.5885,
      "step": 7815
    },
    {
      "epoch": 0.24010075876263323,
      "grad_norm": 0.33912891149520874,
      "learning_rate": 1.931293515725981e-05,
      "loss": 0.5918,
      "step": 7816
    },
    {
      "epoch": 0.2401314778975824,
      "grad_norm": 0.36407941579818726,
      "learning_rate": 1.9312759103111754e-05,
      "loss": 0.6185,
      "step": 7817
    },
    {
      "epoch": 0.24016219703253155,
      "grad_norm": 0.34853997826576233,
      "learning_rate": 1.9312583027213097e-05,
      "loss": 0.6475,
      "step": 7818
    },
    {
      "epoch": 0.24019291616748073,
      "grad_norm": 0.34397777915000916,
      "learning_rate": 1.931240692956425e-05,
      "loss": 0.6099,
      "step": 7819
    },
    {
      "epoch": 0.24022363530242988,
      "grad_norm": 0.36566784977912903,
      "learning_rate": 1.9312230810165628e-05,
      "loss": 0.5643,
      "step": 7820
    },
    {
      "epoch": 0.24025435443737905,
      "grad_norm": 0.6620187759399414,
      "learning_rate": 1.931205466901764e-05,
      "loss": 0.6397,
      "step": 7821
    },
    {
      "epoch": 0.2402850735723282,
      "grad_norm": 0.36219537258148193,
      "learning_rate": 1.93118785061207e-05,
      "loss": 0.5877,
      "step": 7822
    },
    {
      "epoch": 0.24031579270727738,
      "grad_norm": 0.31784185767173767,
      "learning_rate": 1.9311702321475216e-05,
      "loss": 0.595,
      "step": 7823
    },
    {
      "epoch": 0.24034651184222652,
      "grad_norm": 0.3466523587703705,
      "learning_rate": 1.9311526115081597e-05,
      "loss": 0.6164,
      "step": 7824
    },
    {
      "epoch": 0.24037723097717567,
      "grad_norm": 0.3371412456035614,
      "learning_rate": 1.9311349886940264e-05,
      "loss": 0.635,
      "step": 7825
    },
    {
      "epoch": 0.24040795011212485,
      "grad_norm": 0.3117747902870178,
      "learning_rate": 1.931117363705162e-05,
      "loss": 0.4992,
      "step": 7826
    },
    {
      "epoch": 0.240438669247074,
      "grad_norm": 0.37134701013565063,
      "learning_rate": 1.9310997365416085e-05,
      "loss": 0.6486,
      "step": 7827
    },
    {
      "epoch": 0.24046938838202317,
      "grad_norm": 0.3649406135082245,
      "learning_rate": 1.931082107203406e-05,
      "loss": 0.5385,
      "step": 7828
    },
    {
      "epoch": 0.24050010751697232,
      "grad_norm": 0.3606352210044861,
      "learning_rate": 1.9310644756905963e-05,
      "loss": 0.5644,
      "step": 7829
    },
    {
      "epoch": 0.2405308266519215,
      "grad_norm": 0.32484495639801025,
      "learning_rate": 1.9310468420032204e-05,
      "loss": 0.489,
      "step": 7830
    },
    {
      "epoch": 0.24056154578687064,
      "grad_norm": 0.3407883048057556,
      "learning_rate": 1.9310292061413197e-05,
      "loss": 0.5612,
      "step": 7831
    },
    {
      "epoch": 0.24059226492181982,
      "grad_norm": 0.35288557410240173,
      "learning_rate": 1.9310115681049355e-05,
      "loss": 0.6328,
      "step": 7832
    },
    {
      "epoch": 0.24062298405676896,
      "grad_norm": 0.3287113606929779,
      "learning_rate": 1.9309939278941085e-05,
      "loss": 0.5264,
      "step": 7833
    },
    {
      "epoch": 0.2406537031917181,
      "grad_norm": 0.402421236038208,
      "learning_rate": 1.9309762855088802e-05,
      "loss": 0.6029,
      "step": 7834
    },
    {
      "epoch": 0.24068442232666729,
      "grad_norm": 0.3442458212375641,
      "learning_rate": 1.9309586409492915e-05,
      "loss": 0.5546,
      "step": 7835
    },
    {
      "epoch": 0.24071514146161643,
      "grad_norm": 0.34782230854034424,
      "learning_rate": 1.9309409942153842e-05,
      "loss": 0.6357,
      "step": 7836
    },
    {
      "epoch": 0.2407458605965656,
      "grad_norm": 0.32574185729026794,
      "learning_rate": 1.9309233453071993e-05,
      "loss": 0.5366,
      "step": 7837
    },
    {
      "epoch": 0.24077657973151476,
      "grad_norm": 0.37897226214408875,
      "learning_rate": 1.9309056942247776e-05,
      "loss": 0.6164,
      "step": 7838
    },
    {
      "epoch": 0.24080729886646393,
      "grad_norm": 0.32586869597435,
      "learning_rate": 1.930888040968161e-05,
      "loss": 0.59,
      "step": 7839
    },
    {
      "epoch": 0.24083801800141308,
      "grad_norm": 0.32852333784103394,
      "learning_rate": 1.93087038553739e-05,
      "loss": 0.5764,
      "step": 7840
    },
    {
      "epoch": 0.24086873713636223,
      "grad_norm": 0.4305536150932312,
      "learning_rate": 1.9308527279325066e-05,
      "loss": 0.6033,
      "step": 7841
    },
    {
      "epoch": 0.2408994562713114,
      "grad_norm": 0.3355798125267029,
      "learning_rate": 1.930835068153551e-05,
      "loss": 0.6168,
      "step": 7842
    },
    {
      "epoch": 0.24093017540626055,
      "grad_norm": 0.37456241250038147,
      "learning_rate": 1.9308174062005656e-05,
      "loss": 0.5951,
      "step": 7843
    },
    {
      "epoch": 0.24096089454120972,
      "grad_norm": 0.35027360916137695,
      "learning_rate": 1.9307997420735912e-05,
      "loss": 0.6252,
      "step": 7844
    },
    {
      "epoch": 0.24099161367615887,
      "grad_norm": 0.3349452316761017,
      "learning_rate": 1.930782075772669e-05,
      "loss": 0.566,
      "step": 7845
    },
    {
      "epoch": 0.24102233281110805,
      "grad_norm": 1.350369930267334,
      "learning_rate": 1.93076440729784e-05,
      "loss": 0.5513,
      "step": 7846
    },
    {
      "epoch": 0.2410530519460572,
      "grad_norm": 0.3140746057033539,
      "learning_rate": 1.9307467366491455e-05,
      "loss": 0.5303,
      "step": 7847
    },
    {
      "epoch": 0.24108377108100637,
      "grad_norm": 0.3903653025627136,
      "learning_rate": 1.9307290638266275e-05,
      "loss": 0.5685,
      "step": 7848
    },
    {
      "epoch": 0.24111449021595552,
      "grad_norm": 0.3362683057785034,
      "learning_rate": 1.9307113888303265e-05,
      "loss": 0.6236,
      "step": 7849
    },
    {
      "epoch": 0.24114520935090467,
      "grad_norm": 0.35555949807167053,
      "learning_rate": 1.930693711660284e-05,
      "loss": 0.5864,
      "step": 7850
    },
    {
      "epoch": 0.24117592848585384,
      "grad_norm": 0.35139814019203186,
      "learning_rate": 1.9306760323165418e-05,
      "loss": 0.5894,
      "step": 7851
    },
    {
      "epoch": 0.241206647620803,
      "grad_norm": 0.3535762429237366,
      "learning_rate": 1.93065835079914e-05,
      "loss": 0.5963,
      "step": 7852
    },
    {
      "epoch": 0.24123736675575216,
      "grad_norm": 0.4044000208377838,
      "learning_rate": 1.9306406671081214e-05,
      "loss": 0.6477,
      "step": 7853
    },
    {
      "epoch": 0.2412680858907013,
      "grad_norm": 0.37683460116386414,
      "learning_rate": 1.9306229812435257e-05,
      "loss": 0.6218,
      "step": 7854
    },
    {
      "epoch": 0.2412988050256505,
      "grad_norm": 0.36774733662605286,
      "learning_rate": 1.9306052932053957e-05,
      "loss": 0.6126,
      "step": 7855
    },
    {
      "epoch": 0.24132952416059963,
      "grad_norm": 0.4392901062965393,
      "learning_rate": 1.9305876029937717e-05,
      "loss": 0.5969,
      "step": 7856
    },
    {
      "epoch": 0.2413602432955488,
      "grad_norm": 0.37224143743515015,
      "learning_rate": 1.9305699106086954e-05,
      "loss": 0.6484,
      "step": 7857
    },
    {
      "epoch": 0.24139096243049796,
      "grad_norm": 0.374381422996521,
      "learning_rate": 1.9305522160502085e-05,
      "loss": 0.6453,
      "step": 7858
    },
    {
      "epoch": 0.2414216815654471,
      "grad_norm": 0.31542420387268066,
      "learning_rate": 1.9305345193183512e-05,
      "loss": 0.6175,
      "step": 7859
    },
    {
      "epoch": 0.24145240070039628,
      "grad_norm": 0.357710063457489,
      "learning_rate": 1.9305168204131662e-05,
      "loss": 0.5365,
      "step": 7860
    },
    {
      "epoch": 0.24148311983534543,
      "grad_norm": 0.33481547236442566,
      "learning_rate": 1.9304991193346937e-05,
      "loss": 0.5413,
      "step": 7861
    },
    {
      "epoch": 0.2415138389702946,
      "grad_norm": 0.34574899077415466,
      "learning_rate": 1.9304814160829758e-05,
      "loss": 0.5855,
      "step": 7862
    },
    {
      "epoch": 0.24154455810524375,
      "grad_norm": 0.41088902950286865,
      "learning_rate": 1.9304637106580536e-05,
      "loss": 0.5543,
      "step": 7863
    },
    {
      "epoch": 0.24157527724019293,
      "grad_norm": 0.44712191820144653,
      "learning_rate": 1.9304460030599684e-05,
      "loss": 0.5845,
      "step": 7864
    },
    {
      "epoch": 0.24160599637514207,
      "grad_norm": 0.33812204003334045,
      "learning_rate": 1.9304282932887612e-05,
      "loss": 0.622,
      "step": 7865
    },
    {
      "epoch": 0.24163671551009125,
      "grad_norm": 0.3449346125125885,
      "learning_rate": 1.930410581344474e-05,
      "loss": 0.552,
      "step": 7866
    },
    {
      "epoch": 0.2416674346450404,
      "grad_norm": 0.40710118412971497,
      "learning_rate": 1.930392867227148e-05,
      "loss": 0.4625,
      "step": 7867
    },
    {
      "epoch": 0.24169815377998954,
      "grad_norm": 0.32261523604393005,
      "learning_rate": 1.9303751509368246e-05,
      "loss": 0.6027,
      "step": 7868
    },
    {
      "epoch": 0.24172887291493872,
      "grad_norm": 0.3518761098384857,
      "learning_rate": 1.9303574324735445e-05,
      "loss": 0.5961,
      "step": 7869
    },
    {
      "epoch": 0.24175959204988787,
      "grad_norm": 0.34725886583328247,
      "learning_rate": 1.9303397118373502e-05,
      "loss": 0.5574,
      "step": 7870
    },
    {
      "epoch": 0.24179031118483704,
      "grad_norm": 0.43086719512939453,
      "learning_rate": 1.9303219890282823e-05,
      "loss": 0.5696,
      "step": 7871
    },
    {
      "epoch": 0.2418210303197862,
      "grad_norm": 0.336518794298172,
      "learning_rate": 1.9303042640463827e-05,
      "loss": 0.6191,
      "step": 7872
    },
    {
      "epoch": 0.24185174945473537,
      "grad_norm": 0.33859723806381226,
      "learning_rate": 1.930286536891692e-05,
      "loss": 0.5905,
      "step": 7873
    },
    {
      "epoch": 0.2418824685896845,
      "grad_norm": 0.35092803835868835,
      "learning_rate": 1.9302688075642524e-05,
      "loss": 0.6355,
      "step": 7874
    },
    {
      "epoch": 0.2419131877246337,
      "grad_norm": 0.37284156680107117,
      "learning_rate": 1.9302510760641053e-05,
      "loss": 0.5607,
      "step": 7875
    },
    {
      "epoch": 0.24194390685958284,
      "grad_norm": 0.3246413469314575,
      "learning_rate": 1.9302333423912912e-05,
      "loss": 0.61,
      "step": 7876
    },
    {
      "epoch": 0.24197462599453198,
      "grad_norm": 0.3398270010948181,
      "learning_rate": 1.930215606545853e-05,
      "loss": 0.6212,
      "step": 7877
    },
    {
      "epoch": 0.24200534512948116,
      "grad_norm": 0.3218773305416107,
      "learning_rate": 1.9301978685278307e-05,
      "loss": 0.5827,
      "step": 7878
    },
    {
      "epoch": 0.2420360642644303,
      "grad_norm": 0.3600700795650482,
      "learning_rate": 1.930180128337266e-05,
      "loss": 0.6457,
      "step": 7879
    },
    {
      "epoch": 0.24206678339937948,
      "grad_norm": 0.32336053252220154,
      "learning_rate": 1.9301623859742014e-05,
      "loss": 0.5659,
      "step": 7880
    },
    {
      "epoch": 0.24209750253432863,
      "grad_norm": 0.3215004801750183,
      "learning_rate": 1.9301446414386773e-05,
      "loss": 0.5518,
      "step": 7881
    },
    {
      "epoch": 0.2421282216692778,
      "grad_norm": 0.3726419508457184,
      "learning_rate": 1.9301268947307354e-05,
      "loss": 0.5332,
      "step": 7882
    },
    {
      "epoch": 0.24215894080422695,
      "grad_norm": 0.3332030773162842,
      "learning_rate": 1.930109145850417e-05,
      "loss": 0.6095,
      "step": 7883
    },
    {
      "epoch": 0.2421896599391761,
      "grad_norm": 0.3352378010749817,
      "learning_rate": 1.930091394797764e-05,
      "loss": 0.5775,
      "step": 7884
    },
    {
      "epoch": 0.24222037907412527,
      "grad_norm": 0.34070029854774475,
      "learning_rate": 1.9300736415728177e-05,
      "loss": 0.6141,
      "step": 7885
    },
    {
      "epoch": 0.24225109820907442,
      "grad_norm": 0.3302450478076935,
      "learning_rate": 1.930055886175619e-05,
      "loss": 0.5351,
      "step": 7886
    },
    {
      "epoch": 0.2422818173440236,
      "grad_norm": 0.33124175667762756,
      "learning_rate": 1.9300381286062105e-05,
      "loss": 0.5292,
      "step": 7887
    },
    {
      "epoch": 0.24231253647897275,
      "grad_norm": 0.33741042017936707,
      "learning_rate": 1.930020368864632e-05,
      "loss": 0.6031,
      "step": 7888
    },
    {
      "epoch": 0.24234325561392192,
      "grad_norm": 0.3304395079612732,
      "learning_rate": 1.930002606950927e-05,
      "loss": 0.6152,
      "step": 7889
    },
    {
      "epoch": 0.24237397474887107,
      "grad_norm": 0.37930959463119507,
      "learning_rate": 1.9299848428651352e-05,
      "loss": 0.6714,
      "step": 7890
    },
    {
      "epoch": 0.24240469388382024,
      "grad_norm": 0.5670892596244812,
      "learning_rate": 1.9299670766072995e-05,
      "loss": 0.6485,
      "step": 7891
    },
    {
      "epoch": 0.2424354130187694,
      "grad_norm": 0.3453288972377777,
      "learning_rate": 1.9299493081774602e-05,
      "loss": 0.5958,
      "step": 7892
    },
    {
      "epoch": 0.24246613215371854,
      "grad_norm": 0.3202432096004486,
      "learning_rate": 1.9299315375756597e-05,
      "loss": 0.5116,
      "step": 7893
    },
    {
      "epoch": 0.24249685128866771,
      "grad_norm": 0.3570336103439331,
      "learning_rate": 1.929913764801939e-05,
      "loss": 0.6175,
      "step": 7894
    },
    {
      "epoch": 0.24252757042361686,
      "grad_norm": 0.44624701142311096,
      "learning_rate": 1.92989598985634e-05,
      "loss": 0.6628,
      "step": 7895
    },
    {
      "epoch": 0.24255828955856604,
      "grad_norm": 0.34719568490982056,
      "learning_rate": 1.9298782127389035e-05,
      "loss": 0.5573,
      "step": 7896
    },
    {
      "epoch": 0.24258900869351518,
      "grad_norm": 0.33762839436531067,
      "learning_rate": 1.9298604334496715e-05,
      "loss": 0.5828,
      "step": 7897
    },
    {
      "epoch": 0.24261972782846436,
      "grad_norm": 0.3434600532054901,
      "learning_rate": 1.929842651988686e-05,
      "loss": 0.6557,
      "step": 7898
    },
    {
      "epoch": 0.2426504469634135,
      "grad_norm": 0.3997599184513092,
      "learning_rate": 1.9298248683559877e-05,
      "loss": 0.5558,
      "step": 7899
    },
    {
      "epoch": 0.24268116609836268,
      "grad_norm": 0.5556279420852661,
      "learning_rate": 1.9298070825516185e-05,
      "loss": 0.6035,
      "step": 7900
    },
    {
      "epoch": 0.24271188523331183,
      "grad_norm": 0.35131895542144775,
      "learning_rate": 1.92978929457562e-05,
      "loss": 0.6256,
      "step": 7901
    },
    {
      "epoch": 0.24274260436826098,
      "grad_norm": 0.36762747168540955,
      "learning_rate": 1.929771504428034e-05,
      "loss": 0.6083,
      "step": 7902
    },
    {
      "epoch": 0.24277332350321015,
      "grad_norm": 0.3219127058982849,
      "learning_rate": 1.9297537121089012e-05,
      "loss": 0.5874,
      "step": 7903
    },
    {
      "epoch": 0.2428040426381593,
      "grad_norm": 0.3187677562236786,
      "learning_rate": 1.9297359176182637e-05,
      "loss": 0.5491,
      "step": 7904
    },
    {
      "epoch": 0.24283476177310848,
      "grad_norm": 0.32508912682533264,
      "learning_rate": 1.9297181209561633e-05,
      "loss": 0.5487,
      "step": 7905
    },
    {
      "epoch": 0.24286548090805762,
      "grad_norm": 0.3439057767391205,
      "learning_rate": 1.929700322122641e-05,
      "loss": 0.5803,
      "step": 7906
    },
    {
      "epoch": 0.2428962000430068,
      "grad_norm": 0.3246544599533081,
      "learning_rate": 1.929682521117739e-05,
      "loss": 0.5605,
      "step": 7907
    },
    {
      "epoch": 0.24292691917795595,
      "grad_norm": 0.3815654516220093,
      "learning_rate": 1.929664717941498e-05,
      "loss": 0.6008,
      "step": 7908
    },
    {
      "epoch": 0.24295763831290512,
      "grad_norm": 0.4243093729019165,
      "learning_rate": 1.929646912593961e-05,
      "loss": 0.6676,
      "step": 7909
    },
    {
      "epoch": 0.24298835744785427,
      "grad_norm": 0.3636230528354645,
      "learning_rate": 1.9296291050751682e-05,
      "loss": 0.6081,
      "step": 7910
    },
    {
      "epoch": 0.24301907658280342,
      "grad_norm": 0.3483080565929413,
      "learning_rate": 1.9296112953851618e-05,
      "loss": 0.6118,
      "step": 7911
    },
    {
      "epoch": 0.2430497957177526,
      "grad_norm": 0.42559152841567993,
      "learning_rate": 1.929593483523983e-05,
      "loss": 0.6014,
      "step": 7912
    },
    {
      "epoch": 0.24308051485270174,
      "grad_norm": 0.37733063101768494,
      "learning_rate": 1.9295756694916742e-05,
      "loss": 0.6318,
      "step": 7913
    },
    {
      "epoch": 0.24311123398765092,
      "grad_norm": 0.3372984230518341,
      "learning_rate": 1.929557853288276e-05,
      "loss": 0.6271,
      "step": 7914
    },
    {
      "epoch": 0.24314195312260006,
      "grad_norm": 0.35291334986686707,
      "learning_rate": 1.9295400349138305e-05,
      "loss": 0.6337,
      "step": 7915
    },
    {
      "epoch": 0.24317267225754924,
      "grad_norm": 0.3430301547050476,
      "learning_rate": 1.92952221436838e-05,
      "loss": 0.6119,
      "step": 7916
    },
    {
      "epoch": 0.24320339139249839,
      "grad_norm": 0.34510475397109985,
      "learning_rate": 1.929504391651965e-05,
      "loss": 0.5352,
      "step": 7917
    },
    {
      "epoch": 0.24323411052744753,
      "grad_norm": 0.3225047290325165,
      "learning_rate": 1.9294865667646275e-05,
      "loss": 0.544,
      "step": 7918
    },
    {
      "epoch": 0.2432648296623967,
      "grad_norm": 0.3178761601448059,
      "learning_rate": 1.929468739706409e-05,
      "loss": 0.5255,
      "step": 7919
    },
    {
      "epoch": 0.24329554879734586,
      "grad_norm": 0.3678840696811676,
      "learning_rate": 1.929450910477352e-05,
      "loss": 0.7903,
      "step": 7920
    },
    {
      "epoch": 0.24332626793229503,
      "grad_norm": 0.3986068367958069,
      "learning_rate": 1.9294330790774972e-05,
      "loss": 0.6313,
      "step": 7921
    },
    {
      "epoch": 0.24335698706724418,
      "grad_norm": 0.38289502263069153,
      "learning_rate": 1.9294152455068862e-05,
      "loss": 0.6053,
      "step": 7922
    },
    {
      "epoch": 0.24338770620219335,
      "grad_norm": 0.361075222492218,
      "learning_rate": 1.9293974097655615e-05,
      "loss": 0.606,
      "step": 7923
    },
    {
      "epoch": 0.2434184253371425,
      "grad_norm": 0.31814900040626526,
      "learning_rate": 1.9293795718535638e-05,
      "loss": 0.5505,
      "step": 7924
    },
    {
      "epoch": 0.24344914447209168,
      "grad_norm": 0.33222752809524536,
      "learning_rate": 1.9293617317709354e-05,
      "loss": 0.61,
      "step": 7925
    },
    {
      "epoch": 0.24347986360704083,
      "grad_norm": 0.344445139169693,
      "learning_rate": 1.9293438895177176e-05,
      "loss": 0.6176,
      "step": 7926
    },
    {
      "epoch": 0.24351058274198997,
      "grad_norm": 0.35552841424942017,
      "learning_rate": 1.9293260450939525e-05,
      "loss": 0.6091,
      "step": 7927
    },
    {
      "epoch": 0.24354130187693915,
      "grad_norm": 0.33430352807044983,
      "learning_rate": 1.9293081984996814e-05,
      "loss": 0.5695,
      "step": 7928
    },
    {
      "epoch": 0.2435720210118883,
      "grad_norm": 0.3331231474876404,
      "learning_rate": 1.9292903497349464e-05,
      "loss": 0.6192,
      "step": 7929
    },
    {
      "epoch": 0.24360274014683747,
      "grad_norm": 0.34933149814605713,
      "learning_rate": 1.9292724987997883e-05,
      "loss": 0.6531,
      "step": 7930
    },
    {
      "epoch": 0.24363345928178662,
      "grad_norm": 0.340734601020813,
      "learning_rate": 1.92925464569425e-05,
      "loss": 0.6657,
      "step": 7931
    },
    {
      "epoch": 0.2436641784167358,
      "grad_norm": 0.32582753896713257,
      "learning_rate": 1.9292367904183722e-05,
      "loss": 0.5462,
      "step": 7932
    },
    {
      "epoch": 0.24369489755168494,
      "grad_norm": 0.33016127347946167,
      "learning_rate": 1.9292189329721972e-05,
      "loss": 0.6427,
      "step": 7933
    },
    {
      "epoch": 0.24372561668663412,
      "grad_norm": 0.3651644289493561,
      "learning_rate": 1.929201073355766e-05,
      "loss": 0.6554,
      "step": 7934
    },
    {
      "epoch": 0.24375633582158326,
      "grad_norm": 0.34452199935913086,
      "learning_rate": 1.929183211569121e-05,
      "loss": 0.5431,
      "step": 7935
    },
    {
      "epoch": 0.2437870549565324,
      "grad_norm": 0.3737070858478546,
      "learning_rate": 1.9291653476123042e-05,
      "loss": 0.5984,
      "step": 7936
    },
    {
      "epoch": 0.2438177740914816,
      "grad_norm": 0.3509664833545685,
      "learning_rate": 1.9291474814853565e-05,
      "loss": 0.6695,
      "step": 7937
    },
    {
      "epoch": 0.24384849322643073,
      "grad_norm": 0.3614847660064697,
      "learning_rate": 1.9291296131883198e-05,
      "loss": 0.5999,
      "step": 7938
    },
    {
      "epoch": 0.2438792123613799,
      "grad_norm": 0.3268956243991852,
      "learning_rate": 1.9291117427212362e-05,
      "loss": 0.5559,
      "step": 7939
    },
    {
      "epoch": 0.24390993149632906,
      "grad_norm": 0.3502824604511261,
      "learning_rate": 1.929093870084147e-05,
      "loss": 0.6513,
      "step": 7940
    },
    {
      "epoch": 0.24394065063127823,
      "grad_norm": 0.34977295994758606,
      "learning_rate": 1.9290759952770946e-05,
      "loss": 0.6179,
      "step": 7941
    },
    {
      "epoch": 0.24397136976622738,
      "grad_norm": 0.3297165036201477,
      "learning_rate": 1.92905811830012e-05,
      "loss": 0.606,
      "step": 7942
    },
    {
      "epoch": 0.24400208890117656,
      "grad_norm": 0.32554730772972107,
      "learning_rate": 1.9290402391532655e-05,
      "loss": 0.5818,
      "step": 7943
    },
    {
      "epoch": 0.2440328080361257,
      "grad_norm": 0.3472613990306854,
      "learning_rate": 1.9290223578365724e-05,
      "loss": 0.6106,
      "step": 7944
    },
    {
      "epoch": 0.24406352717107485,
      "grad_norm": 0.3511382043361664,
      "learning_rate": 1.929004474350083e-05,
      "loss": 0.6763,
      "step": 7945
    },
    {
      "epoch": 0.24409424630602403,
      "grad_norm": 0.38003870844841003,
      "learning_rate": 1.9289865886938384e-05,
      "loss": 0.5579,
      "step": 7946
    },
    {
      "epoch": 0.24412496544097317,
      "grad_norm": 0.4087676405906677,
      "learning_rate": 1.9289687008678812e-05,
      "loss": 0.6161,
      "step": 7947
    },
    {
      "epoch": 0.24415568457592235,
      "grad_norm": 0.3422110974788666,
      "learning_rate": 1.928950810872252e-05,
      "loss": 0.5713,
      "step": 7948
    },
    {
      "epoch": 0.2441864037108715,
      "grad_norm": 0.33817535638809204,
      "learning_rate": 1.9289329187069938e-05,
      "loss": 0.5698,
      "step": 7949
    },
    {
      "epoch": 0.24421712284582067,
      "grad_norm": 0.36954671144485474,
      "learning_rate": 1.928915024372148e-05,
      "loss": 0.6395,
      "step": 7950
    },
    {
      "epoch": 0.24424784198076982,
      "grad_norm": 0.3292945623397827,
      "learning_rate": 1.928897127867756e-05,
      "loss": 0.5282,
      "step": 7951
    },
    {
      "epoch": 0.244278561115719,
      "grad_norm": 0.42206960916519165,
      "learning_rate": 1.92887922919386e-05,
      "loss": 0.6059,
      "step": 7952
    },
    {
      "epoch": 0.24430928025066814,
      "grad_norm": 0.34441885352134705,
      "learning_rate": 1.9288613283505017e-05,
      "loss": 0.5799,
      "step": 7953
    },
    {
      "epoch": 0.2443399993856173,
      "grad_norm": 0.32794514298439026,
      "learning_rate": 1.928843425337723e-05,
      "loss": 0.6667,
      "step": 7954
    },
    {
      "epoch": 0.24437071852056647,
      "grad_norm": 0.3815188705921173,
      "learning_rate": 1.9288255201555657e-05,
      "loss": 0.5647,
      "step": 7955
    },
    {
      "epoch": 0.2444014376555156,
      "grad_norm": 0.36957207322120667,
      "learning_rate": 1.9288076128040712e-05,
      "loss": 0.5309,
      "step": 7956
    },
    {
      "epoch": 0.2444321567904648,
      "grad_norm": 0.3602535128593445,
      "learning_rate": 1.9287897032832817e-05,
      "loss": 0.5893,
      "step": 7957
    },
    {
      "epoch": 0.24446287592541394,
      "grad_norm": 0.33680954575538635,
      "learning_rate": 1.928771791593239e-05,
      "loss": 0.5443,
      "step": 7958
    },
    {
      "epoch": 0.2444935950603631,
      "grad_norm": 0.34416428208351135,
      "learning_rate": 1.928753877733985e-05,
      "loss": 0.5461,
      "step": 7959
    },
    {
      "epoch": 0.24452431419531226,
      "grad_norm": 0.34001973271369934,
      "learning_rate": 1.9287359617055617e-05,
      "loss": 0.6127,
      "step": 7960
    },
    {
      "epoch": 0.2445550333302614,
      "grad_norm": 0.3661879301071167,
      "learning_rate": 1.9287180435080102e-05,
      "loss": 0.5246,
      "step": 7961
    },
    {
      "epoch": 0.24458575246521058,
      "grad_norm": 0.3917309641838074,
      "learning_rate": 1.9287001231413734e-05,
      "loss": 0.552,
      "step": 7962
    },
    {
      "epoch": 0.24461647160015973,
      "grad_norm": 0.3918893039226532,
      "learning_rate": 1.928682200605692e-05,
      "loss": 0.5524,
      "step": 7963
    },
    {
      "epoch": 0.2446471907351089,
      "grad_norm": 0.3432528078556061,
      "learning_rate": 1.9286642759010087e-05,
      "loss": 0.6223,
      "step": 7964
    },
    {
      "epoch": 0.24467790987005805,
      "grad_norm": 0.3371836543083191,
      "learning_rate": 1.9286463490273655e-05,
      "loss": 0.5581,
      "step": 7965
    },
    {
      "epoch": 0.24470862900500723,
      "grad_norm": 0.3771596848964691,
      "learning_rate": 1.9286284199848034e-05,
      "loss": 0.6633,
      "step": 7966
    },
    {
      "epoch": 0.24473934813995638,
      "grad_norm": 0.31140148639678955,
      "learning_rate": 1.928610488773365e-05,
      "loss": 0.4395,
      "step": 7967
    },
    {
      "epoch": 0.24477006727490555,
      "grad_norm": 0.36741334199905396,
      "learning_rate": 1.9285925553930917e-05,
      "loss": 0.6061,
      "step": 7968
    },
    {
      "epoch": 0.2448007864098547,
      "grad_norm": 0.4739916920661926,
      "learning_rate": 1.928574619844026e-05,
      "loss": 0.5334,
      "step": 7969
    },
    {
      "epoch": 0.24483150554480385,
      "grad_norm": 0.4568001925945282,
      "learning_rate": 1.9285566821262093e-05,
      "loss": 0.4924,
      "step": 7970
    },
    {
      "epoch": 0.24486222467975302,
      "grad_norm": 0.33018478751182556,
      "learning_rate": 1.9285387422396836e-05,
      "loss": 0.5593,
      "step": 7971
    },
    {
      "epoch": 0.24489294381470217,
      "grad_norm": 0.4059334099292755,
      "learning_rate": 1.9285208001844907e-05,
      "loss": 0.5732,
      "step": 7972
    },
    {
      "epoch": 0.24492366294965134,
      "grad_norm": 0.3718136250972748,
      "learning_rate": 1.9285028559606725e-05,
      "loss": 0.5941,
      "step": 7973
    },
    {
      "epoch": 0.2449543820846005,
      "grad_norm": 0.44362252950668335,
      "learning_rate": 1.9284849095682715e-05,
      "loss": 0.6314,
      "step": 7974
    },
    {
      "epoch": 0.24498510121954967,
      "grad_norm": 0.3230489194393158,
      "learning_rate": 1.928466961007329e-05,
      "loss": 0.5835,
      "step": 7975
    },
    {
      "epoch": 0.24501582035449881,
      "grad_norm": 0.45805832743644714,
      "learning_rate": 1.9284490102778867e-05,
      "loss": 0.5668,
      "step": 7976
    },
    {
      "epoch": 0.245046539489448,
      "grad_norm": 0.7389804124832153,
      "learning_rate": 1.9284310573799873e-05,
      "loss": 0.591,
      "step": 7977
    },
    {
      "epoch": 0.24507725862439714,
      "grad_norm": 0.36947330832481384,
      "learning_rate": 1.9284131023136724e-05,
      "loss": 0.6585,
      "step": 7978
    },
    {
      "epoch": 0.24510797775934628,
      "grad_norm": 0.3818102478981018,
      "learning_rate": 1.9283951450789836e-05,
      "loss": 0.594,
      "step": 7979
    },
    {
      "epoch": 0.24513869689429546,
      "grad_norm": 0.3317219316959381,
      "learning_rate": 1.928377185675963e-05,
      "loss": 0.5618,
      "step": 7980
    },
    {
      "epoch": 0.2451694160292446,
      "grad_norm": 0.3449431359767914,
      "learning_rate": 1.9283592241046526e-05,
      "loss": 0.5362,
      "step": 7981
    },
    {
      "epoch": 0.24520013516419378,
      "grad_norm": 0.3423006534576416,
      "learning_rate": 1.9283412603650947e-05,
      "loss": 0.6337,
      "step": 7982
    },
    {
      "epoch": 0.24523085429914293,
      "grad_norm": 0.3555092513561249,
      "learning_rate": 1.928323294457331e-05,
      "loss": 0.5494,
      "step": 7983
    },
    {
      "epoch": 0.2452615734340921,
      "grad_norm": 0.33041542768478394,
      "learning_rate": 1.9283053263814032e-05,
      "loss": 0.5987,
      "step": 7984
    },
    {
      "epoch": 0.24529229256904125,
      "grad_norm": 0.3063499629497528,
      "learning_rate": 1.9282873561373536e-05,
      "loss": 0.6007,
      "step": 7985
    },
    {
      "epoch": 0.24532301170399043,
      "grad_norm": 0.35881417989730835,
      "learning_rate": 1.928269383725224e-05,
      "loss": 0.5529,
      "step": 7986
    },
    {
      "epoch": 0.24535373083893958,
      "grad_norm": 0.39319562911987305,
      "learning_rate": 1.9282514091450565e-05,
      "loss": 0.6086,
      "step": 7987
    },
    {
      "epoch": 0.24538444997388872,
      "grad_norm": 0.34462374448776245,
      "learning_rate": 1.9282334323968926e-05,
      "loss": 0.5773,
      "step": 7988
    },
    {
      "epoch": 0.2454151691088379,
      "grad_norm": 1.8583154678344727,
      "learning_rate": 1.928215453480775e-05,
      "loss": 0.5709,
      "step": 7989
    },
    {
      "epoch": 0.24544588824378705,
      "grad_norm": 0.3400976359844208,
      "learning_rate": 1.9281974723967457e-05,
      "loss": 0.6145,
      "step": 7990
    },
    {
      "epoch": 0.24547660737873622,
      "grad_norm": 0.35774537920951843,
      "learning_rate": 1.928179489144846e-05,
      "loss": 0.5936,
      "step": 7991
    },
    {
      "epoch": 0.24550732651368537,
      "grad_norm": 0.33753687143325806,
      "learning_rate": 1.9281615037251184e-05,
      "loss": 0.5449,
      "step": 7992
    },
    {
      "epoch": 0.24553804564863455,
      "grad_norm": 0.3430008292198181,
      "learning_rate": 1.9281435161376047e-05,
      "loss": 0.6033,
      "step": 7993
    },
    {
      "epoch": 0.2455687647835837,
      "grad_norm": 0.3242656886577606,
      "learning_rate": 1.928125526382347e-05,
      "loss": 0.5093,
      "step": 7994
    },
    {
      "epoch": 0.24559948391853284,
      "grad_norm": 0.3271774649620056,
      "learning_rate": 1.9281075344593873e-05,
      "loss": 0.5723,
      "step": 7995
    },
    {
      "epoch": 0.24563020305348202,
      "grad_norm": 0.3533971309661865,
      "learning_rate": 1.9280895403687676e-05,
      "loss": 0.5809,
      "step": 7996
    },
    {
      "epoch": 0.24566092218843116,
      "grad_norm": 0.3151695132255554,
      "learning_rate": 1.9280715441105303e-05,
      "loss": 0.5115,
      "step": 7997
    },
    {
      "epoch": 0.24569164132338034,
      "grad_norm": 0.3271646499633789,
      "learning_rate": 1.9280535456847168e-05,
      "loss": 0.6286,
      "step": 7998
    },
    {
      "epoch": 0.2457223604583295,
      "grad_norm": 0.4105626344680786,
      "learning_rate": 1.9280355450913696e-05,
      "loss": 0.5976,
      "step": 7999
    },
    {
      "epoch": 0.24575307959327866,
      "grad_norm": 0.36736223101615906,
      "learning_rate": 1.9280175423305302e-05,
      "loss": 0.5329,
      "step": 8000
    },
    {
      "epoch": 0.2457837987282278,
      "grad_norm": 0.35020485520362854,
      "learning_rate": 1.9279995374022412e-05,
      "loss": 0.593,
      "step": 8001
    },
    {
      "epoch": 0.24581451786317698,
      "grad_norm": 0.5364945530891418,
      "learning_rate": 1.9279815303065447e-05,
      "loss": 0.5986,
      "step": 8002
    },
    {
      "epoch": 0.24584523699812613,
      "grad_norm": 0.40308621525764465,
      "learning_rate": 1.9279635210434822e-05,
      "loss": 0.612,
      "step": 8003
    },
    {
      "epoch": 0.24587595613307528,
      "grad_norm": 0.32339322566986084,
      "learning_rate": 1.9279455096130963e-05,
      "loss": 0.5461,
      "step": 8004
    },
    {
      "epoch": 0.24590667526802445,
      "grad_norm": 0.3269807696342468,
      "learning_rate": 1.9279274960154288e-05,
      "loss": 0.6302,
      "step": 8005
    },
    {
      "epoch": 0.2459373944029736,
      "grad_norm": 0.38802364468574524,
      "learning_rate": 1.9279094802505218e-05,
      "loss": 0.6274,
      "step": 8006
    },
    {
      "epoch": 0.24596811353792278,
      "grad_norm": 0.334692120552063,
      "learning_rate": 1.9278914623184173e-05,
      "loss": 0.5446,
      "step": 8007
    },
    {
      "epoch": 0.24599883267287193,
      "grad_norm": 0.40027111768722534,
      "learning_rate": 1.9278734422191577e-05,
      "loss": 0.6228,
      "step": 8008
    },
    {
      "epoch": 0.2460295518078211,
      "grad_norm": 0.37230971455574036,
      "learning_rate": 1.927855419952785e-05,
      "loss": 0.5942,
      "step": 8009
    },
    {
      "epoch": 0.24606027094277025,
      "grad_norm": 0.3404752314090729,
      "learning_rate": 1.9278373955193408e-05,
      "loss": 0.5685,
      "step": 8010
    },
    {
      "epoch": 0.24609099007771942,
      "grad_norm": 0.3528372347354889,
      "learning_rate": 1.9278193689188675e-05,
      "loss": 0.5985,
      "step": 8011
    },
    {
      "epoch": 0.24612170921266857,
      "grad_norm": 0.3204597234725952,
      "learning_rate": 1.9278013401514078e-05,
      "loss": 0.5896,
      "step": 8012
    },
    {
      "epoch": 0.24615242834761772,
      "grad_norm": 0.3132797181606293,
      "learning_rate": 1.9277833092170026e-05,
      "loss": 0.5549,
      "step": 8013
    },
    {
      "epoch": 0.2461831474825669,
      "grad_norm": 0.3895164132118225,
      "learning_rate": 1.9277652761156955e-05,
      "loss": 0.5902,
      "step": 8014
    },
    {
      "epoch": 0.24621386661751604,
      "grad_norm": 2.027799367904663,
      "learning_rate": 1.9277472408475272e-05,
      "loss": 0.6096,
      "step": 8015
    },
    {
      "epoch": 0.24624458575246522,
      "grad_norm": 0.36613667011260986,
      "learning_rate": 1.9277292034125406e-05,
      "loss": 0.6269,
      "step": 8016
    },
    {
      "epoch": 0.24627530488741436,
      "grad_norm": 0.3338070511817932,
      "learning_rate": 1.9277111638107774e-05,
      "loss": 0.5991,
      "step": 8017
    },
    {
      "epoch": 0.24630602402236354,
      "grad_norm": 0.3337520360946655,
      "learning_rate": 1.92769312204228e-05,
      "loss": 0.5579,
      "step": 8018
    },
    {
      "epoch": 0.2463367431573127,
      "grad_norm": 0.35714322328567505,
      "learning_rate": 1.927675078107091e-05,
      "loss": 0.581,
      "step": 8019
    },
    {
      "epoch": 0.24636746229226186,
      "grad_norm": 0.4503204822540283,
      "learning_rate": 1.927657032005252e-05,
      "loss": 0.6275,
      "step": 8020
    },
    {
      "epoch": 0.246398181427211,
      "grad_norm": 0.3484928607940674,
      "learning_rate": 1.9276389837368048e-05,
      "loss": 0.5655,
      "step": 8021
    },
    {
      "epoch": 0.24642890056216016,
      "grad_norm": 0.33261099457740784,
      "learning_rate": 1.927620933301792e-05,
      "loss": 0.6292,
      "step": 8022
    },
    {
      "epoch": 0.24645961969710933,
      "grad_norm": 0.33663511276245117,
      "learning_rate": 1.9276028807002563e-05,
      "loss": 0.669,
      "step": 8023
    },
    {
      "epoch": 0.24649033883205848,
      "grad_norm": 0.3373728096485138,
      "learning_rate": 1.9275848259322387e-05,
      "loss": 0.5407,
      "step": 8024
    },
    {
      "epoch": 0.24652105796700766,
      "grad_norm": 0.3655604422092438,
      "learning_rate": 1.927566768997782e-05,
      "loss": 0.5922,
      "step": 8025
    },
    {
      "epoch": 0.2465517771019568,
      "grad_norm": 0.34678196907043457,
      "learning_rate": 1.9275487098969288e-05,
      "loss": 0.6197,
      "step": 8026
    },
    {
      "epoch": 0.24658249623690598,
      "grad_norm": 0.43887415528297424,
      "learning_rate": 1.9275306486297202e-05,
      "loss": 0.7002,
      "step": 8027
    },
    {
      "epoch": 0.24661321537185513,
      "grad_norm": 0.348991334438324,
      "learning_rate": 1.9275125851961994e-05,
      "loss": 0.5828,
      "step": 8028
    },
    {
      "epoch": 0.2466439345068043,
      "grad_norm": 0.32087478041648865,
      "learning_rate": 1.927494519596408e-05,
      "loss": 0.565,
      "step": 8029
    },
    {
      "epoch": 0.24667465364175345,
      "grad_norm": 0.3426953852176666,
      "learning_rate": 1.9274764518303884e-05,
      "loss": 0.582,
      "step": 8030
    },
    {
      "epoch": 0.2467053727767026,
      "grad_norm": 0.4904937446117401,
      "learning_rate": 1.927458381898183e-05,
      "loss": 0.5104,
      "step": 8031
    },
    {
      "epoch": 0.24673609191165177,
      "grad_norm": 0.3689292073249817,
      "learning_rate": 1.9274403097998335e-05,
      "loss": 0.5955,
      "step": 8032
    },
    {
      "epoch": 0.24676681104660092,
      "grad_norm": 0.38509637117385864,
      "learning_rate": 1.9274222355353824e-05,
      "loss": 0.5392,
      "step": 8033
    },
    {
      "epoch": 0.2467975301815501,
      "grad_norm": 0.41921335458755493,
      "learning_rate": 1.9274041591048722e-05,
      "loss": 0.6243,
      "step": 8034
    },
    {
      "epoch": 0.24682824931649924,
      "grad_norm": 0.3535846173763275,
      "learning_rate": 1.9273860805083443e-05,
      "loss": 0.6042,
      "step": 8035
    },
    {
      "epoch": 0.24685896845144842,
      "grad_norm": 0.3520556390285492,
      "learning_rate": 1.927367999745842e-05,
      "loss": 0.5623,
      "step": 8036
    },
    {
      "epoch": 0.24688968758639757,
      "grad_norm": 0.31558355689048767,
      "learning_rate": 1.9273499168174067e-05,
      "loss": 0.653,
      "step": 8037
    },
    {
      "epoch": 0.2469204067213467,
      "grad_norm": 0.44058355689048767,
      "learning_rate": 1.927331831723081e-05,
      "loss": 0.5983,
      "step": 8038
    },
    {
      "epoch": 0.2469511258562959,
      "grad_norm": 0.5181899666786194,
      "learning_rate": 1.927313744462907e-05,
      "loss": 0.6306,
      "step": 8039
    },
    {
      "epoch": 0.24698184499124504,
      "grad_norm": 0.3423907160758972,
      "learning_rate": 1.9272956550369266e-05,
      "loss": 0.5485,
      "step": 8040
    },
    {
      "epoch": 0.2470125641261942,
      "grad_norm": 0.36887413263320923,
      "learning_rate": 1.927277563445183e-05,
      "loss": 0.5834,
      "step": 8041
    },
    {
      "epoch": 0.24704328326114336,
      "grad_norm": 0.35967332124710083,
      "learning_rate": 1.9272594696877176e-05,
      "loss": 0.5823,
      "step": 8042
    },
    {
      "epoch": 0.24707400239609253,
      "grad_norm": 0.4522888958454132,
      "learning_rate": 1.9272413737645728e-05,
      "loss": 0.6946,
      "step": 8043
    },
    {
      "epoch": 0.24710472153104168,
      "grad_norm": 0.3292714059352875,
      "learning_rate": 1.9272232756757913e-05,
      "loss": 0.5188,
      "step": 8044
    },
    {
      "epoch": 0.24713544066599086,
      "grad_norm": 0.34779655933380127,
      "learning_rate": 1.9272051754214153e-05,
      "loss": 0.5836,
      "step": 8045
    },
    {
      "epoch": 0.24716615980094,
      "grad_norm": 0.3765181601047516,
      "learning_rate": 1.9271870730014863e-05,
      "loss": 0.5761,
      "step": 8046
    },
    {
      "epoch": 0.24719687893588915,
      "grad_norm": 0.34081602096557617,
      "learning_rate": 1.9271689684160475e-05,
      "loss": 0.5028,
      "step": 8047
    },
    {
      "epoch": 0.24722759807083833,
      "grad_norm": 0.34838491678237915,
      "learning_rate": 1.9271508616651406e-05,
      "loss": 0.5435,
      "step": 8048
    },
    {
      "epoch": 0.24725831720578748,
      "grad_norm": 0.5036017894744873,
      "learning_rate": 1.927132752748808e-05,
      "loss": 0.5967,
      "step": 8049
    },
    {
      "epoch": 0.24728903634073665,
      "grad_norm": 0.3305007219314575,
      "learning_rate": 1.9271146416670924e-05,
      "loss": 0.5538,
      "step": 8050
    },
    {
      "epoch": 0.2473197554756858,
      "grad_norm": 0.34508565068244934,
      "learning_rate": 1.927096528420036e-05,
      "loss": 0.5912,
      "step": 8051
    },
    {
      "epoch": 0.24735047461063497,
      "grad_norm": 0.3657954931259155,
      "learning_rate": 1.9270784130076805e-05,
      "loss": 0.5858,
      "step": 8052
    },
    {
      "epoch": 0.24738119374558412,
      "grad_norm": 0.34513232111930847,
      "learning_rate": 1.9270602954300692e-05,
      "loss": 0.6318,
      "step": 8053
    },
    {
      "epoch": 0.2474119128805333,
      "grad_norm": 0.3303806185722351,
      "learning_rate": 1.927042175687243e-05,
      "loss": 0.5491,
      "step": 8054
    },
    {
      "epoch": 0.24744263201548244,
      "grad_norm": 0.3178413510322571,
      "learning_rate": 1.9270240537792457e-05,
      "loss": 0.5779,
      "step": 8055
    },
    {
      "epoch": 0.2474733511504316,
      "grad_norm": 0.3403319716453552,
      "learning_rate": 1.927005929706119e-05,
      "loss": 0.5677,
      "step": 8056
    },
    {
      "epoch": 0.24750407028538077,
      "grad_norm": 0.3283713757991791,
      "learning_rate": 1.9269878034679046e-05,
      "loss": 0.6268,
      "step": 8057
    },
    {
      "epoch": 0.24753478942032991,
      "grad_norm": 0.37047335505485535,
      "learning_rate": 1.9269696750646458e-05,
      "loss": 0.5428,
      "step": 8058
    },
    {
      "epoch": 0.2475655085552791,
      "grad_norm": 0.4081445634365082,
      "learning_rate": 1.9269515444963846e-05,
      "loss": 0.5897,
      "step": 8059
    },
    {
      "epoch": 0.24759622769022824,
      "grad_norm": 0.2964821457862854,
      "learning_rate": 1.9269334117631634e-05,
      "loss": 0.5265,
      "step": 8060
    },
    {
      "epoch": 0.2476269468251774,
      "grad_norm": 0.39377403259277344,
      "learning_rate": 1.926915276865024e-05,
      "loss": 0.6053,
      "step": 8061
    },
    {
      "epoch": 0.24765766596012656,
      "grad_norm": 0.34116706252098083,
      "learning_rate": 1.92689713980201e-05,
      "loss": 0.5968,
      "step": 8062
    },
    {
      "epoch": 0.24768838509507574,
      "grad_norm": 0.3253757655620575,
      "learning_rate": 1.9268790005741627e-05,
      "loss": 0.6742,
      "step": 8063
    },
    {
      "epoch": 0.24771910423002488,
      "grad_norm": 0.3373892605304718,
      "learning_rate": 1.9268608591815245e-05,
      "loss": 0.6066,
      "step": 8064
    },
    {
      "epoch": 0.24774982336497403,
      "grad_norm": 0.35877639055252075,
      "learning_rate": 1.9268427156241384e-05,
      "loss": 0.5821,
      "step": 8065
    },
    {
      "epoch": 0.2477805424999232,
      "grad_norm": 0.3671904504299164,
      "learning_rate": 1.926824569902046e-05,
      "loss": 0.7189,
      "step": 8066
    },
    {
      "epoch": 0.24781126163487235,
      "grad_norm": 0.6446322202682495,
      "learning_rate": 1.9268064220152903e-05,
      "loss": 0.5582,
      "step": 8067
    },
    {
      "epoch": 0.24784198076982153,
      "grad_norm": 0.35551613569259644,
      "learning_rate": 1.9267882719639134e-05,
      "loss": 0.5682,
      "step": 8068
    },
    {
      "epoch": 0.24787269990477068,
      "grad_norm": 0.3259781002998352,
      "learning_rate": 1.926770119747958e-05,
      "loss": 0.589,
      "step": 8069
    },
    {
      "epoch": 0.24790341903971985,
      "grad_norm": 0.3458731770515442,
      "learning_rate": 1.926751965367466e-05,
      "loss": 0.6205,
      "step": 8070
    },
    {
      "epoch": 0.247934138174669,
      "grad_norm": 0.331540584564209,
      "learning_rate": 1.9267338088224802e-05,
      "loss": 0.6153,
      "step": 8071
    },
    {
      "epoch": 0.24796485730961815,
      "grad_norm": 0.3853614628314972,
      "learning_rate": 1.9267156501130428e-05,
      "loss": 0.5625,
      "step": 8072
    },
    {
      "epoch": 0.24799557644456732,
      "grad_norm": 0.3228750228881836,
      "learning_rate": 1.9266974892391964e-05,
      "loss": 0.6221,
      "step": 8073
    },
    {
      "epoch": 0.24802629557951647,
      "grad_norm": 0.32806092500686646,
      "learning_rate": 1.9266793262009833e-05,
      "loss": 0.5397,
      "step": 8074
    },
    {
      "epoch": 0.24805701471446565,
      "grad_norm": 0.4109097421169281,
      "learning_rate": 1.9266611609984458e-05,
      "loss": 0.5849,
      "step": 8075
    },
    {
      "epoch": 0.2480877338494148,
      "grad_norm": 0.3318442106246948,
      "learning_rate": 1.9266429936316266e-05,
      "loss": 0.6451,
      "step": 8076
    },
    {
      "epoch": 0.24811845298436397,
      "grad_norm": 0.3394380807876587,
      "learning_rate": 1.9266248241005678e-05,
      "loss": 0.5933,
      "step": 8077
    },
    {
      "epoch": 0.24814917211931312,
      "grad_norm": 0.3607509732246399,
      "learning_rate": 1.9266066524053124e-05,
      "loss": 0.5998,
      "step": 8078
    },
    {
      "epoch": 0.2481798912542623,
      "grad_norm": 0.3203928768634796,
      "learning_rate": 1.9265884785459016e-05,
      "loss": 0.5327,
      "step": 8079
    },
    {
      "epoch": 0.24821061038921144,
      "grad_norm": 0.3639335036277771,
      "learning_rate": 1.9265703025223793e-05,
      "loss": 0.5511,
      "step": 8080
    },
    {
      "epoch": 0.2482413295241606,
      "grad_norm": 0.3222848176956177,
      "learning_rate": 1.926552124334787e-05,
      "loss": 0.6357,
      "step": 8081
    },
    {
      "epoch": 0.24827204865910976,
      "grad_norm": 0.41348326206207275,
      "learning_rate": 1.926533943983168e-05,
      "loss": 0.5995,
      "step": 8082
    },
    {
      "epoch": 0.2483027677940589,
      "grad_norm": 0.36074647307395935,
      "learning_rate": 1.926515761467564e-05,
      "loss": 0.5604,
      "step": 8083
    },
    {
      "epoch": 0.24833348692900808,
      "grad_norm": 0.36920756101608276,
      "learning_rate": 1.926497576788018e-05,
      "loss": 0.6111,
      "step": 8084
    },
    {
      "epoch": 0.24836420606395723,
      "grad_norm": 0.3723614811897278,
      "learning_rate": 1.9264793899445716e-05,
      "loss": 0.5061,
      "step": 8085
    },
    {
      "epoch": 0.2483949251989064,
      "grad_norm": 0.3587384819984436,
      "learning_rate": 1.9264612009372685e-05,
      "loss": 0.5869,
      "step": 8086
    },
    {
      "epoch": 0.24842564433385556,
      "grad_norm": 0.3501192331314087,
      "learning_rate": 1.9264430097661503e-05,
      "loss": 0.6778,
      "step": 8087
    },
    {
      "epoch": 0.24845636346880473,
      "grad_norm": 0.3487778604030609,
      "learning_rate": 1.9264248164312597e-05,
      "loss": 0.5646,
      "step": 8088
    },
    {
      "epoch": 0.24848708260375388,
      "grad_norm": 0.33425372838974,
      "learning_rate": 1.9264066209326393e-05,
      "loss": 0.5742,
      "step": 8089
    },
    {
      "epoch": 0.24851780173870303,
      "grad_norm": 0.34251436591148376,
      "learning_rate": 1.9263884232703315e-05,
      "loss": 0.5847,
      "step": 8090
    },
    {
      "epoch": 0.2485485208736522,
      "grad_norm": 0.38921821117401123,
      "learning_rate": 1.9263702234443787e-05,
      "loss": 0.5603,
      "step": 8091
    },
    {
      "epoch": 0.24857924000860135,
      "grad_norm": 0.3532021641731262,
      "learning_rate": 1.926352021454824e-05,
      "loss": 0.559,
      "step": 8092
    },
    {
      "epoch": 0.24860995914355052,
      "grad_norm": 0.337065726518631,
      "learning_rate": 1.926333817301709e-05,
      "loss": 0.6507,
      "step": 8093
    },
    {
      "epoch": 0.24864067827849967,
      "grad_norm": 0.35540589690208435,
      "learning_rate": 1.9263156109850766e-05,
      "loss": 0.6026,
      "step": 8094
    },
    {
      "epoch": 0.24867139741344885,
      "grad_norm": 0.3336319029331207,
      "learning_rate": 1.92629740250497e-05,
      "loss": 0.5069,
      "step": 8095
    },
    {
      "epoch": 0.248702116548398,
      "grad_norm": 0.3272562623023987,
      "learning_rate": 1.9262791918614306e-05,
      "loss": 0.6157,
      "step": 8096
    },
    {
      "epoch": 0.24873283568334717,
      "grad_norm": 0.36984437704086304,
      "learning_rate": 1.9262609790545017e-05,
      "loss": 0.5245,
      "step": 8097
    },
    {
      "epoch": 0.24876355481829632,
      "grad_norm": 0.3190847933292389,
      "learning_rate": 1.9262427640842256e-05,
      "loss": 0.6199,
      "step": 8098
    },
    {
      "epoch": 0.24879427395324547,
      "grad_norm": 0.3381030261516571,
      "learning_rate": 1.9262245469506446e-05,
      "loss": 0.5898,
      "step": 8099
    },
    {
      "epoch": 0.24882499308819464,
      "grad_norm": 0.33470797538757324,
      "learning_rate": 1.9262063276538018e-05,
      "loss": 0.5338,
      "step": 8100
    },
    {
      "epoch": 0.2488557122231438,
      "grad_norm": 0.40966424345970154,
      "learning_rate": 1.926188106193739e-05,
      "loss": 0.6545,
      "step": 8101
    },
    {
      "epoch": 0.24888643135809296,
      "grad_norm": 0.3876827657222748,
      "learning_rate": 1.9261698825704997e-05,
      "loss": 0.58,
      "step": 8102
    },
    {
      "epoch": 0.2489171504930421,
      "grad_norm": 0.3821130692958832,
      "learning_rate": 1.9261516567841254e-05,
      "loss": 0.6242,
      "step": 8103
    },
    {
      "epoch": 0.2489478696279913,
      "grad_norm": 0.3381488025188446,
      "learning_rate": 1.9261334288346594e-05,
      "loss": 0.6122,
      "step": 8104
    },
    {
      "epoch": 0.24897858876294043,
      "grad_norm": 0.35091865062713623,
      "learning_rate": 1.9261151987221444e-05,
      "loss": 0.6119,
      "step": 8105
    },
    {
      "epoch": 0.2490093078978896,
      "grad_norm": 0.3124684691429138,
      "learning_rate": 1.9260969664466226e-05,
      "loss": 0.571,
      "step": 8106
    },
    {
      "epoch": 0.24904002703283876,
      "grad_norm": 0.3466022312641144,
      "learning_rate": 1.9260787320081365e-05,
      "loss": 0.5008,
      "step": 8107
    },
    {
      "epoch": 0.2490707461677879,
      "grad_norm": 0.41703495383262634,
      "learning_rate": 1.926060495406729e-05,
      "loss": 0.6287,
      "step": 8108
    },
    {
      "epoch": 0.24910146530273708,
      "grad_norm": 0.31358665227890015,
      "learning_rate": 1.9260422566424423e-05,
      "loss": 0.6127,
      "step": 8109
    },
    {
      "epoch": 0.24913218443768623,
      "grad_norm": 0.3193607032299042,
      "learning_rate": 1.9260240157153196e-05,
      "loss": 0.5134,
      "step": 8110
    },
    {
      "epoch": 0.2491629035726354,
      "grad_norm": 0.2903992533683777,
      "learning_rate": 1.926005772625403e-05,
      "loss": 0.5167,
      "step": 8111
    },
    {
      "epoch": 0.24919362270758455,
      "grad_norm": 0.435953289270401,
      "learning_rate": 1.925987527372735e-05,
      "loss": 0.5766,
      "step": 8112
    },
    {
      "epoch": 0.24922434184253373,
      "grad_norm": 0.32323580980300903,
      "learning_rate": 1.9259692799573586e-05,
      "loss": 0.5281,
      "step": 8113
    },
    {
      "epoch": 0.24925506097748287,
      "grad_norm": 0.36793777346611023,
      "learning_rate": 1.9259510303793166e-05,
      "loss": 0.5419,
      "step": 8114
    },
    {
      "epoch": 0.24928578011243202,
      "grad_norm": 0.36749446392059326,
      "learning_rate": 1.9259327786386507e-05,
      "loss": 0.5959,
      "step": 8115
    },
    {
      "epoch": 0.2493164992473812,
      "grad_norm": 0.3570019006729126,
      "learning_rate": 1.9259145247354047e-05,
      "loss": 0.5079,
      "step": 8116
    },
    {
      "epoch": 0.24934721838233034,
      "grad_norm": 0.37172096967697144,
      "learning_rate": 1.9258962686696203e-05,
      "loss": 0.5902,
      "step": 8117
    },
    {
      "epoch": 0.24937793751727952,
      "grad_norm": 0.3364390432834625,
      "learning_rate": 1.9258780104413407e-05,
      "loss": 0.6258,
      "step": 8118
    },
    {
      "epoch": 0.24940865665222867,
      "grad_norm": 0.4926721155643463,
      "learning_rate": 1.925859750050608e-05,
      "loss": 0.5912,
      "step": 8119
    },
    {
      "epoch": 0.24943937578717784,
      "grad_norm": 0.5522615313529968,
      "learning_rate": 1.9258414874974657e-05,
      "loss": 0.5302,
      "step": 8120
    },
    {
      "epoch": 0.249470094922127,
      "grad_norm": 0.36573806405067444,
      "learning_rate": 1.9258232227819556e-05,
      "loss": 0.5822,
      "step": 8121
    },
    {
      "epoch": 0.24950081405707616,
      "grad_norm": 0.29107245802879333,
      "learning_rate": 1.9258049559041208e-05,
      "loss": 0.5452,
      "step": 8122
    },
    {
      "epoch": 0.2495315331920253,
      "grad_norm": 0.32735809683799744,
      "learning_rate": 1.9257866868640037e-05,
      "loss": 0.6313,
      "step": 8123
    },
    {
      "epoch": 0.24956225232697446,
      "grad_norm": 0.36087432503700256,
      "learning_rate": 1.9257684156616473e-05,
      "loss": 0.6364,
      "step": 8124
    },
    {
      "epoch": 0.24959297146192364,
      "grad_norm": 0.4113445281982422,
      "learning_rate": 1.925750142297094e-05,
      "loss": 0.6035,
      "step": 8125
    },
    {
      "epoch": 0.24962369059687278,
      "grad_norm": 0.3515910506248474,
      "learning_rate": 1.925731866770387e-05,
      "loss": 0.5464,
      "step": 8126
    },
    {
      "epoch": 0.24965440973182196,
      "grad_norm": 0.34351256489753723,
      "learning_rate": 1.9257135890815682e-05,
      "loss": 0.5334,
      "step": 8127
    },
    {
      "epoch": 0.2496851288667711,
      "grad_norm": 0.3360336422920227,
      "learning_rate": 1.9256953092306808e-05,
      "loss": 0.5442,
      "step": 8128
    },
    {
      "epoch": 0.24971584800172028,
      "grad_norm": 0.34417352080345154,
      "learning_rate": 1.9256770272177673e-05,
      "loss": 0.6422,
      "step": 8129
    },
    {
      "epoch": 0.24974656713666943,
      "grad_norm": 0.35187265276908875,
      "learning_rate": 1.9256587430428705e-05,
      "loss": 0.5975,
      "step": 8130
    },
    {
      "epoch": 0.2497772862716186,
      "grad_norm": 0.3715724050998688,
      "learning_rate": 1.9256404567060327e-05,
      "loss": 0.5331,
      "step": 8131
    },
    {
      "epoch": 0.24980800540656775,
      "grad_norm": 0.3819791376590729,
      "learning_rate": 1.9256221682072974e-05,
      "loss": 0.5738,
      "step": 8132
    },
    {
      "epoch": 0.2498387245415169,
      "grad_norm": 0.34458380937576294,
      "learning_rate": 1.9256038775467066e-05,
      "loss": 0.5858,
      "step": 8133
    },
    {
      "epoch": 0.24986944367646607,
      "grad_norm": 0.35639020800590515,
      "learning_rate": 1.9255855847243035e-05,
      "loss": 0.5681,
      "step": 8134
    },
    {
      "epoch": 0.24990016281141522,
      "grad_norm": 0.32901155948638916,
      "learning_rate": 1.9255672897401307e-05,
      "loss": 0.5625,
      "step": 8135
    },
    {
      "epoch": 0.2499308819463644,
      "grad_norm": 0.3390445113182068,
      "learning_rate": 1.925548992594231e-05,
      "loss": 0.6273,
      "step": 8136
    },
    {
      "epoch": 0.24996160108131354,
      "grad_norm": 0.3519945442676544,
      "learning_rate": 1.9255306932866463e-05,
      "loss": 0.6017,
      "step": 8137
    },
    {
      "epoch": 0.24999232021626272,
      "grad_norm": 0.36910974979400635,
      "learning_rate": 1.9255123918174205e-05,
      "loss": 0.6381,
      "step": 8138
    },
    {
      "epoch": 0.2500230393512119,
      "grad_norm": 0.3440738022327423,
      "learning_rate": 1.925494088186596e-05,
      "loss": 0.6243,
      "step": 8139
    },
    {
      "epoch": 0.250053758486161,
      "grad_norm": 0.4196765720844269,
      "learning_rate": 1.925475782394215e-05,
      "loss": 0.6034,
      "step": 8140
    },
    {
      "epoch": 0.2500844776211102,
      "grad_norm": 0.32861560583114624,
      "learning_rate": 1.9254574744403212e-05,
      "loss": 0.5149,
      "step": 8141
    },
    {
      "epoch": 0.25011519675605937,
      "grad_norm": 0.5508907437324524,
      "learning_rate": 1.9254391643249565e-05,
      "loss": 0.5646,
      "step": 8142
    },
    {
      "epoch": 0.2501459158910085,
      "grad_norm": 0.36771056056022644,
      "learning_rate": 1.925420852048164e-05,
      "loss": 0.4936,
      "step": 8143
    },
    {
      "epoch": 0.25017663502595766,
      "grad_norm": 0.3262122869491577,
      "learning_rate": 1.9254025376099865e-05,
      "loss": 0.5458,
      "step": 8144
    },
    {
      "epoch": 0.25020735416090684,
      "grad_norm": 0.32306981086730957,
      "learning_rate": 1.9253842210104666e-05,
      "loss": 0.562,
      "step": 8145
    },
    {
      "epoch": 0.250238073295856,
      "grad_norm": 0.39342984557151794,
      "learning_rate": 1.9253659022496473e-05,
      "loss": 0.5247,
      "step": 8146
    },
    {
      "epoch": 0.25026879243080513,
      "grad_norm": 0.49063554406166077,
      "learning_rate": 1.9253475813275716e-05,
      "loss": 0.6629,
      "step": 8147
    },
    {
      "epoch": 0.2502995115657543,
      "grad_norm": 0.34504005312919617,
      "learning_rate": 1.9253292582442818e-05,
      "loss": 0.6076,
      "step": 8148
    },
    {
      "epoch": 0.2503302307007035,
      "grad_norm": 0.3373686373233795,
      "learning_rate": 1.9253109329998207e-05,
      "loss": 0.5541,
      "step": 8149
    },
    {
      "epoch": 0.2503609498356526,
      "grad_norm": 0.34113234281539917,
      "learning_rate": 1.9252926055942316e-05,
      "loss": 0.5859,
      "step": 8150
    },
    {
      "epoch": 0.2503916689706018,
      "grad_norm": 0.413992315530777,
      "learning_rate": 1.9252742760275568e-05,
      "loss": 0.6391,
      "step": 8151
    },
    {
      "epoch": 0.25042238810555095,
      "grad_norm": 0.37430351972579956,
      "learning_rate": 1.9252559442998395e-05,
      "loss": 0.6406,
      "step": 8152
    },
    {
      "epoch": 0.25045310724050013,
      "grad_norm": 0.398443341255188,
      "learning_rate": 1.9252376104111225e-05,
      "loss": 0.6579,
      "step": 8153
    },
    {
      "epoch": 0.25048382637544925,
      "grad_norm": 0.3596709966659546,
      "learning_rate": 1.9252192743614476e-05,
      "loss": 0.521,
      "step": 8154
    },
    {
      "epoch": 0.2505145455103984,
      "grad_norm": 0.3297251760959625,
      "learning_rate": 1.9252009361508593e-05,
      "loss": 0.5414,
      "step": 8155
    },
    {
      "epoch": 0.2505452646453476,
      "grad_norm": 0.32663118839263916,
      "learning_rate": 1.9251825957793994e-05,
      "loss": 0.6162,
      "step": 8156
    },
    {
      "epoch": 0.2505759837802968,
      "grad_norm": 0.34362348914146423,
      "learning_rate": 1.9251642532471106e-05,
      "loss": 0.5415,
      "step": 8157
    },
    {
      "epoch": 0.2506067029152459,
      "grad_norm": 0.3262234032154083,
      "learning_rate": 1.9251459085540365e-05,
      "loss": 0.5697,
      "step": 8158
    },
    {
      "epoch": 0.25063742205019507,
      "grad_norm": 0.3727857768535614,
      "learning_rate": 1.9251275617002192e-05,
      "loss": 0.538,
      "step": 8159
    },
    {
      "epoch": 0.25066814118514424,
      "grad_norm": 0.34423235058784485,
      "learning_rate": 1.9251092126857022e-05,
      "loss": 0.5658,
      "step": 8160
    },
    {
      "epoch": 0.25069886032009336,
      "grad_norm": 0.36102432012557983,
      "learning_rate": 1.9250908615105278e-05,
      "loss": 0.5984,
      "step": 8161
    },
    {
      "epoch": 0.25072957945504254,
      "grad_norm": 0.3938758671283722,
      "learning_rate": 1.925072508174739e-05,
      "loss": 0.6721,
      "step": 8162
    },
    {
      "epoch": 0.2507602985899917,
      "grad_norm": 0.37073448300361633,
      "learning_rate": 1.9250541526783787e-05,
      "loss": 0.6046,
      "step": 8163
    },
    {
      "epoch": 0.2507910177249409,
      "grad_norm": 0.3660185635089874,
      "learning_rate": 1.9250357950214903e-05,
      "loss": 0.6225,
      "step": 8164
    },
    {
      "epoch": 0.25082173685989,
      "grad_norm": 0.4896341860294342,
      "learning_rate": 1.9250174352041157e-05,
      "loss": 0.5518,
      "step": 8165
    },
    {
      "epoch": 0.2508524559948392,
      "grad_norm": 0.34070372581481934,
      "learning_rate": 1.9249990732262988e-05,
      "loss": 0.609,
      "step": 8166
    },
    {
      "epoch": 0.25088317512978836,
      "grad_norm": 0.8762781620025635,
      "learning_rate": 1.9249807090880813e-05,
      "loss": 0.6292,
      "step": 8167
    },
    {
      "epoch": 0.2509138942647375,
      "grad_norm": 0.34724852442741394,
      "learning_rate": 1.924962342789507e-05,
      "loss": 0.5424,
      "step": 8168
    },
    {
      "epoch": 0.25094461339968666,
      "grad_norm": 0.4010174572467804,
      "learning_rate": 1.924943974330619e-05,
      "loss": 0.6579,
      "step": 8169
    },
    {
      "epoch": 0.25097533253463583,
      "grad_norm": 0.338174045085907,
      "learning_rate": 1.9249256037114594e-05,
      "loss": 0.5181,
      "step": 8170
    },
    {
      "epoch": 0.251006051669585,
      "grad_norm": 0.4042709171772003,
      "learning_rate": 1.924907230932071e-05,
      "loss": 0.5493,
      "step": 8171
    },
    {
      "epoch": 0.2510367708045341,
      "grad_norm": 0.3951626121997833,
      "learning_rate": 1.924888855992498e-05,
      "loss": 0.596,
      "step": 8172
    },
    {
      "epoch": 0.2510674899394833,
      "grad_norm": 0.32995960116386414,
      "learning_rate": 1.924870478892782e-05,
      "loss": 0.5485,
      "step": 8173
    },
    {
      "epoch": 0.2510982090744325,
      "grad_norm": 0.3660335838794708,
      "learning_rate": 1.9248520996329665e-05,
      "loss": 0.5911,
      "step": 8174
    },
    {
      "epoch": 0.2511289282093816,
      "grad_norm": 0.3794623613357544,
      "learning_rate": 1.9248337182130943e-05,
      "loss": 0.5955,
      "step": 8175
    },
    {
      "epoch": 0.25115964734433077,
      "grad_norm": 0.36354729533195496,
      "learning_rate": 1.9248153346332085e-05,
      "loss": 0.6718,
      "step": 8176
    },
    {
      "epoch": 0.25119036647927995,
      "grad_norm": 0.3120976984500885,
      "learning_rate": 1.9247969488933517e-05,
      "loss": 0.5982,
      "step": 8177
    },
    {
      "epoch": 0.2512210856142291,
      "grad_norm": 0.38308849930763245,
      "learning_rate": 1.924778560993567e-05,
      "loss": 0.5373,
      "step": 8178
    },
    {
      "epoch": 0.25125180474917824,
      "grad_norm": 0.3188348710536957,
      "learning_rate": 1.9247601709338974e-05,
      "loss": 0.6313,
      "step": 8179
    },
    {
      "epoch": 0.2512825238841274,
      "grad_norm": 0.4560845196247101,
      "learning_rate": 1.924741778714386e-05,
      "loss": 0.6519,
      "step": 8180
    },
    {
      "epoch": 0.2513132430190766,
      "grad_norm": 0.34158268570899963,
      "learning_rate": 1.9247233843350757e-05,
      "loss": 0.5554,
      "step": 8181
    },
    {
      "epoch": 0.25134396215402577,
      "grad_norm": 0.351362407207489,
      "learning_rate": 1.924704987796009e-05,
      "loss": 0.6034,
      "step": 8182
    },
    {
      "epoch": 0.2513746812889749,
      "grad_norm": 0.35004445910453796,
      "learning_rate": 1.9246865890972298e-05,
      "loss": 0.5859,
      "step": 8183
    },
    {
      "epoch": 0.25140540042392406,
      "grad_norm": 0.33663198351860046,
      "learning_rate": 1.92466818823878e-05,
      "loss": 0.6107,
      "step": 8184
    },
    {
      "epoch": 0.25143611955887324,
      "grad_norm": 0.3563354015350342,
      "learning_rate": 1.924649785220703e-05,
      "loss": 0.5915,
      "step": 8185
    },
    {
      "epoch": 0.25146683869382236,
      "grad_norm": 0.3741229772567749,
      "learning_rate": 1.9246313800430422e-05,
      "loss": 0.5685,
      "step": 8186
    },
    {
      "epoch": 0.25149755782877153,
      "grad_norm": 0.34285444021224976,
      "learning_rate": 1.92461297270584e-05,
      "loss": 0.5993,
      "step": 8187
    },
    {
      "epoch": 0.2515282769637207,
      "grad_norm": 0.33537644147872925,
      "learning_rate": 1.9245945632091396e-05,
      "loss": 0.58,
      "step": 8188
    },
    {
      "epoch": 0.2515589960986699,
      "grad_norm": 0.3187806308269501,
      "learning_rate": 1.924576151552984e-05,
      "loss": 0.6219,
      "step": 8189
    },
    {
      "epoch": 0.251589715233619,
      "grad_norm": 0.3143298625946045,
      "learning_rate": 1.9245577377374165e-05,
      "loss": 0.5398,
      "step": 8190
    },
    {
      "epoch": 0.2516204343685682,
      "grad_norm": 0.33968761563301086,
      "learning_rate": 1.92453932176248e-05,
      "loss": 0.673,
      "step": 8191
    },
    {
      "epoch": 0.25165115350351736,
      "grad_norm": 0.3368196487426758,
      "learning_rate": 1.9245209036282166e-05,
      "loss": 0.5897,
      "step": 8192
    },
    {
      "epoch": 0.2516818726384665,
      "grad_norm": 0.33812272548675537,
      "learning_rate": 1.9245024833346706e-05,
      "loss": 0.6024,
      "step": 8193
    },
    {
      "epoch": 0.25171259177341565,
      "grad_norm": 0.3766481280326843,
      "learning_rate": 1.924484060881884e-05,
      "loss": 0.6476,
      "step": 8194
    },
    {
      "epoch": 0.2517433109083648,
      "grad_norm": 0.36876025795936584,
      "learning_rate": 1.924465636269901e-05,
      "loss": 0.6164,
      "step": 8195
    },
    {
      "epoch": 0.251774030043314,
      "grad_norm": 0.3389958441257477,
      "learning_rate": 1.9244472094987635e-05,
      "loss": 0.5464,
      "step": 8196
    },
    {
      "epoch": 0.2518047491782631,
      "grad_norm": 0.41937723755836487,
      "learning_rate": 1.924428780568515e-05,
      "loss": 0.6162,
      "step": 8197
    },
    {
      "epoch": 0.2518354683132123,
      "grad_norm": 0.33633318543434143,
      "learning_rate": 1.9244103494791988e-05,
      "loss": 0.5877,
      "step": 8198
    },
    {
      "epoch": 0.25186618744816147,
      "grad_norm": 0.3836783468723297,
      "learning_rate": 1.9243919162308574e-05,
      "loss": 0.58,
      "step": 8199
    },
    {
      "epoch": 0.25189690658311065,
      "grad_norm": 0.33981412649154663,
      "learning_rate": 1.924373480823534e-05,
      "loss": 0.6595,
      "step": 8200
    },
    {
      "epoch": 0.25192762571805977,
      "grad_norm": 0.363895982503891,
      "learning_rate": 1.9243550432572723e-05,
      "loss": 0.6425,
      "step": 8201
    },
    {
      "epoch": 0.25195834485300894,
      "grad_norm": 0.36750778555870056,
      "learning_rate": 1.9243366035321145e-05,
      "loss": 0.5451,
      "step": 8202
    },
    {
      "epoch": 0.2519890639879581,
      "grad_norm": 0.3500846028327942,
      "learning_rate": 1.924318161648104e-05,
      "loss": 0.6127,
      "step": 8203
    },
    {
      "epoch": 0.25201978312290724,
      "grad_norm": 1.7660325765609741,
      "learning_rate": 1.924299717605284e-05,
      "loss": 0.5728,
      "step": 8204
    },
    {
      "epoch": 0.2520505022578564,
      "grad_norm": 0.42121273279190063,
      "learning_rate": 1.9242812714036975e-05,
      "loss": 0.6251,
      "step": 8205
    },
    {
      "epoch": 0.2520812213928056,
      "grad_norm": 0.3199688792228699,
      "learning_rate": 1.9242628230433874e-05,
      "loss": 0.5838,
      "step": 8206
    },
    {
      "epoch": 0.25211194052775476,
      "grad_norm": 0.3284425437450409,
      "learning_rate": 1.9242443725243967e-05,
      "loss": 0.5443,
      "step": 8207
    },
    {
      "epoch": 0.2521426596627039,
      "grad_norm": 0.4871874153614044,
      "learning_rate": 1.924225919846769e-05,
      "loss": 0.7046,
      "step": 8208
    },
    {
      "epoch": 0.25217337879765306,
      "grad_norm": 0.40103310346603394,
      "learning_rate": 1.924207465010547e-05,
      "loss": 0.6261,
      "step": 8209
    },
    {
      "epoch": 0.25220409793260223,
      "grad_norm": 0.3049905300140381,
      "learning_rate": 1.9241890080157742e-05,
      "loss": 0.6631,
      "step": 8210
    },
    {
      "epoch": 0.25223481706755135,
      "grad_norm": 0.33946526050567627,
      "learning_rate": 1.924170548862493e-05,
      "loss": 0.5361,
      "step": 8211
    },
    {
      "epoch": 0.25226553620250053,
      "grad_norm": 0.354472815990448,
      "learning_rate": 1.924152087550747e-05,
      "loss": 0.5802,
      "step": 8212
    },
    {
      "epoch": 0.2522962553374497,
      "grad_norm": 0.34480923414230347,
      "learning_rate": 1.9241336240805795e-05,
      "loss": 0.5878,
      "step": 8213
    },
    {
      "epoch": 0.2523269744723989,
      "grad_norm": 0.4066990315914154,
      "learning_rate": 1.9241151584520334e-05,
      "loss": 0.5705,
      "step": 8214
    },
    {
      "epoch": 0.252357693607348,
      "grad_norm": 0.332962304353714,
      "learning_rate": 1.924096690665152e-05,
      "loss": 0.5644,
      "step": 8215
    },
    {
      "epoch": 0.2523884127422972,
      "grad_norm": 0.29440435767173767,
      "learning_rate": 1.9240782207199778e-05,
      "loss": 0.5991,
      "step": 8216
    },
    {
      "epoch": 0.25241913187724635,
      "grad_norm": 0.3963111340999603,
      "learning_rate": 1.9240597486165543e-05,
      "loss": 0.6093,
      "step": 8217
    },
    {
      "epoch": 0.25244985101219547,
      "grad_norm": 0.4008532166481018,
      "learning_rate": 1.924041274354925e-05,
      "loss": 0.5303,
      "step": 8218
    },
    {
      "epoch": 0.25248057014714465,
      "grad_norm": 0.35854944586753845,
      "learning_rate": 1.9240227979351328e-05,
      "loss": 0.5988,
      "step": 8219
    },
    {
      "epoch": 0.2525112892820938,
      "grad_norm": 0.378581702709198,
      "learning_rate": 1.924004319357221e-05,
      "loss": 0.5909,
      "step": 8220
    },
    {
      "epoch": 0.252542008417043,
      "grad_norm": 0.3735653758049011,
      "learning_rate": 1.923985838621232e-05,
      "loss": 0.4872,
      "step": 8221
    },
    {
      "epoch": 0.2525727275519921,
      "grad_norm": 0.4352099895477295,
      "learning_rate": 1.9239673557272098e-05,
      "loss": 0.5242,
      "step": 8222
    },
    {
      "epoch": 0.2526034466869413,
      "grad_norm": 0.3476884961128235,
      "learning_rate": 1.9239488706751977e-05,
      "loss": 0.6236,
      "step": 8223
    },
    {
      "epoch": 0.25263416582189047,
      "grad_norm": 0.3135400712490082,
      "learning_rate": 1.9239303834652377e-05,
      "loss": 0.531,
      "step": 8224
    },
    {
      "epoch": 0.25266488495683964,
      "grad_norm": 0.3418579697608948,
      "learning_rate": 1.9239118940973746e-05,
      "loss": 0.567,
      "step": 8225
    },
    {
      "epoch": 0.25269560409178876,
      "grad_norm": 0.305403470993042,
      "learning_rate": 1.9238934025716502e-05,
      "loss": 0.6091,
      "step": 8226
    },
    {
      "epoch": 0.25272632322673794,
      "grad_norm": 0.3342288136482239,
      "learning_rate": 1.9238749088881085e-05,
      "loss": 0.6021,
      "step": 8227
    },
    {
      "epoch": 0.2527570423616871,
      "grad_norm": 0.32613804936408997,
      "learning_rate": 1.9238564130467923e-05,
      "loss": 0.5693,
      "step": 8228
    },
    {
      "epoch": 0.25278776149663623,
      "grad_norm": 0.3626268208026886,
      "learning_rate": 1.9238379150477447e-05,
      "loss": 0.5343,
      "step": 8229
    },
    {
      "epoch": 0.2528184806315854,
      "grad_norm": 0.33876654505729675,
      "learning_rate": 1.9238194148910098e-05,
      "loss": 0.5205,
      "step": 8230
    },
    {
      "epoch": 0.2528491997665346,
      "grad_norm": 0.3993907570838928,
      "learning_rate": 1.9238009125766296e-05,
      "loss": 0.5771,
      "step": 8231
    },
    {
      "epoch": 0.25287991890148376,
      "grad_norm": 0.3726364076137543,
      "learning_rate": 1.923782408104648e-05,
      "loss": 0.6069,
      "step": 8232
    },
    {
      "epoch": 0.2529106380364329,
      "grad_norm": 0.3255564570426941,
      "learning_rate": 1.923763901475108e-05,
      "loss": 0.5806,
      "step": 8233
    },
    {
      "epoch": 0.25294135717138205,
      "grad_norm": 0.3490222096443176,
      "learning_rate": 1.9237453926880525e-05,
      "loss": 0.5741,
      "step": 8234
    },
    {
      "epoch": 0.25297207630633123,
      "grad_norm": 0.3594990670681,
      "learning_rate": 1.923726881743526e-05,
      "loss": 0.5474,
      "step": 8235
    },
    {
      "epoch": 0.25300279544128035,
      "grad_norm": 0.3388264775276184,
      "learning_rate": 1.9237083686415703e-05,
      "loss": 0.5375,
      "step": 8236
    },
    {
      "epoch": 0.2530335145762295,
      "grad_norm": 0.35153865814208984,
      "learning_rate": 1.9236898533822295e-05,
      "loss": 0.5719,
      "step": 8237
    },
    {
      "epoch": 0.2530642337111787,
      "grad_norm": 0.34760981798171997,
      "learning_rate": 1.9236713359655462e-05,
      "loss": 0.5934,
      "step": 8238
    },
    {
      "epoch": 0.2530949528461279,
      "grad_norm": 0.3594171106815338,
      "learning_rate": 1.923652816391564e-05,
      "loss": 0.5926,
      "step": 8239
    },
    {
      "epoch": 0.253125671981077,
      "grad_norm": 0.3508000075817108,
      "learning_rate": 1.9236342946603265e-05,
      "loss": 0.6361,
      "step": 8240
    },
    {
      "epoch": 0.25315639111602617,
      "grad_norm": 0.3415468633174896,
      "learning_rate": 1.923615770771876e-05,
      "loss": 0.5698,
      "step": 8241
    },
    {
      "epoch": 0.25318711025097534,
      "grad_norm": 0.3664723038673401,
      "learning_rate": 1.9235972447262568e-05,
      "loss": 0.6303,
      "step": 8242
    },
    {
      "epoch": 0.2532178293859245,
      "grad_norm": 0.4330686926841736,
      "learning_rate": 1.923578716523512e-05,
      "loss": 0.6413,
      "step": 8243
    },
    {
      "epoch": 0.25324854852087364,
      "grad_norm": 0.3995680510997772,
      "learning_rate": 1.923560186163684e-05,
      "loss": 0.6848,
      "step": 8244
    },
    {
      "epoch": 0.2532792676558228,
      "grad_norm": 0.3636017441749573,
      "learning_rate": 1.923541653646817e-05,
      "loss": 0.5363,
      "step": 8245
    },
    {
      "epoch": 0.253309986790772,
      "grad_norm": 0.35383370518684387,
      "learning_rate": 1.923523118972954e-05,
      "loss": 0.5979,
      "step": 8246
    },
    {
      "epoch": 0.2533407059257211,
      "grad_norm": 0.33574268221855164,
      "learning_rate": 1.9235045821421383e-05,
      "loss": 0.5797,
      "step": 8247
    },
    {
      "epoch": 0.2533714250606703,
      "grad_norm": 0.35580554604530334,
      "learning_rate": 1.923486043154413e-05,
      "loss": 0.5617,
      "step": 8248
    },
    {
      "epoch": 0.25340214419561946,
      "grad_norm": 0.3412446081638336,
      "learning_rate": 1.9234675020098214e-05,
      "loss": 0.625,
      "step": 8249
    },
    {
      "epoch": 0.25343286333056864,
      "grad_norm": 0.3826681673526764,
      "learning_rate": 1.9234489587084072e-05,
      "loss": 0.5847,
      "step": 8250
    },
    {
      "epoch": 0.25346358246551776,
      "grad_norm": 0.32245388627052307,
      "learning_rate": 1.9234304132502134e-05,
      "loss": 0.5939,
      "step": 8251
    },
    {
      "epoch": 0.25349430160046693,
      "grad_norm": 0.3382636308670044,
      "learning_rate": 1.9234118656352833e-05,
      "loss": 0.5572,
      "step": 8252
    },
    {
      "epoch": 0.2535250207354161,
      "grad_norm": 0.3398440182209015,
      "learning_rate": 1.9233933158636605e-05,
      "loss": 0.5894,
      "step": 8253
    },
    {
      "epoch": 0.2535557398703652,
      "grad_norm": 0.3638000190258026,
      "learning_rate": 1.923374763935388e-05,
      "loss": 0.6477,
      "step": 8254
    },
    {
      "epoch": 0.2535864590053144,
      "grad_norm": 0.36895161867141724,
      "learning_rate": 1.923356209850509e-05,
      "loss": 0.5859,
      "step": 8255
    },
    {
      "epoch": 0.2536171781402636,
      "grad_norm": 0.30955296754837036,
      "learning_rate": 1.9233376536090675e-05,
      "loss": 0.5542,
      "step": 8256
    },
    {
      "epoch": 0.25364789727521275,
      "grad_norm": 0.36906352639198303,
      "learning_rate": 1.9233190952111064e-05,
      "loss": 0.6081,
      "step": 8257
    },
    {
      "epoch": 0.2536786164101619,
      "grad_norm": 0.3356150686740875,
      "learning_rate": 1.923300534656669e-05,
      "loss": 0.6935,
      "step": 8258
    },
    {
      "epoch": 0.25370933554511105,
      "grad_norm": 0.3574443459510803,
      "learning_rate": 1.9232819719457983e-05,
      "loss": 0.6335,
      "step": 8259
    },
    {
      "epoch": 0.2537400546800602,
      "grad_norm": 0.32649660110473633,
      "learning_rate": 1.9232634070785384e-05,
      "loss": 0.5708,
      "step": 8260
    },
    {
      "epoch": 0.25377077381500934,
      "grad_norm": 0.3734080493450165,
      "learning_rate": 1.9232448400549325e-05,
      "loss": 0.5671,
      "step": 8261
    },
    {
      "epoch": 0.2538014929499585,
      "grad_norm": 0.325977623462677,
      "learning_rate": 1.9232262708750236e-05,
      "loss": 0.6072,
      "step": 8262
    },
    {
      "epoch": 0.2538322120849077,
      "grad_norm": 0.3491586744785309,
      "learning_rate": 1.9232076995388555e-05,
      "loss": 0.6572,
      "step": 8263
    },
    {
      "epoch": 0.25386293121985687,
      "grad_norm": 0.3682660758495331,
      "learning_rate": 1.923189126046471e-05,
      "loss": 0.5596,
      "step": 8264
    },
    {
      "epoch": 0.253893650354806,
      "grad_norm": 0.3288169205188751,
      "learning_rate": 1.923170550397914e-05,
      "loss": 0.5981,
      "step": 8265
    },
    {
      "epoch": 0.25392436948975516,
      "grad_norm": 0.3317849636077881,
      "learning_rate": 1.9231519725932277e-05,
      "loss": 0.5698,
      "step": 8266
    },
    {
      "epoch": 0.25395508862470434,
      "grad_norm": 0.3438563942909241,
      "learning_rate": 1.9231333926324556e-05,
      "loss": 0.5793,
      "step": 8267
    },
    {
      "epoch": 0.2539858077596535,
      "grad_norm": 0.37212660908699036,
      "learning_rate": 1.923114810515641e-05,
      "loss": 0.5829,
      "step": 8268
    },
    {
      "epoch": 0.25401652689460263,
      "grad_norm": 0.3788805305957794,
      "learning_rate": 1.923096226242827e-05,
      "loss": 0.5616,
      "step": 8269
    },
    {
      "epoch": 0.2540472460295518,
      "grad_norm": 0.3562413156032562,
      "learning_rate": 1.9230776398140576e-05,
      "loss": 0.6902,
      "step": 8270
    },
    {
      "epoch": 0.254077965164501,
      "grad_norm": 0.3653242588043213,
      "learning_rate": 1.9230590512293757e-05,
      "loss": 0.616,
      "step": 8271
    },
    {
      "epoch": 0.2541086842994501,
      "grad_norm": 0.3443053364753723,
      "learning_rate": 1.923040460488825e-05,
      "loss": 0.6005,
      "step": 8272
    },
    {
      "epoch": 0.2541394034343993,
      "grad_norm": 0.3591475188732147,
      "learning_rate": 1.9230218675924486e-05,
      "loss": 0.5895,
      "step": 8273
    },
    {
      "epoch": 0.25417012256934846,
      "grad_norm": 0.549377977848053,
      "learning_rate": 1.9230032725402904e-05,
      "loss": 0.5725,
      "step": 8274
    },
    {
      "epoch": 0.25420084170429763,
      "grad_norm": 0.3990809917449951,
      "learning_rate": 1.9229846753323936e-05,
      "loss": 0.4525,
      "step": 8275
    },
    {
      "epoch": 0.25423156083924675,
      "grad_norm": 0.3375081419944763,
      "learning_rate": 1.9229660759688018e-05,
      "loss": 0.575,
      "step": 8276
    },
    {
      "epoch": 0.2542622799741959,
      "grad_norm": 0.32362768054008484,
      "learning_rate": 1.922947474449558e-05,
      "loss": 0.5281,
      "step": 8277
    },
    {
      "epoch": 0.2542929991091451,
      "grad_norm": 0.3783341348171234,
      "learning_rate": 1.922928870774706e-05,
      "loss": 0.5236,
      "step": 8278
    },
    {
      "epoch": 0.2543237182440942,
      "grad_norm": 0.33719080686569214,
      "learning_rate": 1.9229102649442892e-05,
      "loss": 0.6079,
      "step": 8279
    },
    {
      "epoch": 0.2543544373790434,
      "grad_norm": 0.35688069462776184,
      "learning_rate": 1.922891656958351e-05,
      "loss": 0.6576,
      "step": 8280
    },
    {
      "epoch": 0.25438515651399257,
      "grad_norm": 0.3592953383922577,
      "learning_rate": 1.922873046816935e-05,
      "loss": 0.5821,
      "step": 8281
    },
    {
      "epoch": 0.25441587564894175,
      "grad_norm": 0.39769431948661804,
      "learning_rate": 1.9228544345200842e-05,
      "loss": 0.5557,
      "step": 8282
    },
    {
      "epoch": 0.25444659478389087,
      "grad_norm": 0.36735329031944275,
      "learning_rate": 1.9228358200678428e-05,
      "loss": 0.6222,
      "step": 8283
    },
    {
      "epoch": 0.25447731391884004,
      "grad_norm": 0.3429044485092163,
      "learning_rate": 1.9228172034602536e-05,
      "loss": 0.5856,
      "step": 8284
    },
    {
      "epoch": 0.2545080330537892,
      "grad_norm": 0.36852896213531494,
      "learning_rate": 1.9227985846973606e-05,
      "loss": 0.5987,
      "step": 8285
    },
    {
      "epoch": 0.25453875218873834,
      "grad_norm": 0.34844517707824707,
      "learning_rate": 1.922779963779207e-05,
      "loss": 0.5977,
      "step": 8286
    },
    {
      "epoch": 0.2545694713236875,
      "grad_norm": 0.33246520161628723,
      "learning_rate": 1.922761340705836e-05,
      "loss": 0.5393,
      "step": 8287
    },
    {
      "epoch": 0.2546001904586367,
      "grad_norm": 0.38701027631759644,
      "learning_rate": 1.922742715477292e-05,
      "loss": 0.5962,
      "step": 8288
    },
    {
      "epoch": 0.25463090959358586,
      "grad_norm": 0.5734824538230896,
      "learning_rate": 1.9227240880936177e-05,
      "loss": 0.6256,
      "step": 8289
    },
    {
      "epoch": 0.254661628728535,
      "grad_norm": 0.3410373628139496,
      "learning_rate": 1.9227054585548566e-05,
      "loss": 0.5992,
      "step": 8290
    },
    {
      "epoch": 0.25469234786348416,
      "grad_norm": 0.4268675744533539,
      "learning_rate": 1.922686826861053e-05,
      "loss": 0.621,
      "step": 8291
    },
    {
      "epoch": 0.25472306699843333,
      "grad_norm": 0.4205310344696045,
      "learning_rate": 1.9226681930122493e-05,
      "loss": 0.55,
      "step": 8292
    },
    {
      "epoch": 0.2547537861333825,
      "grad_norm": 0.33097419142723083,
      "learning_rate": 1.92264955700849e-05,
      "loss": 0.633,
      "step": 8293
    },
    {
      "epoch": 0.25478450526833163,
      "grad_norm": 0.33111780881881714,
      "learning_rate": 1.922630918849818e-05,
      "loss": 0.5962,
      "step": 8294
    },
    {
      "epoch": 0.2548152244032808,
      "grad_norm": 0.3373839855194092,
      "learning_rate": 1.9226122785362774e-05,
      "loss": 0.6012,
      "step": 8295
    },
    {
      "epoch": 0.25484594353823,
      "grad_norm": 0.7855027318000793,
      "learning_rate": 1.922593636067911e-05,
      "loss": 0.6494,
      "step": 8296
    },
    {
      "epoch": 0.2548766626731791,
      "grad_norm": 0.32734623551368713,
      "learning_rate": 1.9225749914447627e-05,
      "loss": 0.6067,
      "step": 8297
    },
    {
      "epoch": 0.2549073818081283,
      "grad_norm": 0.33113759756088257,
      "learning_rate": 1.9225563446668764e-05,
      "loss": 0.5908,
      "step": 8298
    },
    {
      "epoch": 0.25493810094307745,
      "grad_norm": 0.35075080394744873,
      "learning_rate": 1.922537695734295e-05,
      "loss": 0.5158,
      "step": 8299
    },
    {
      "epoch": 0.2549688200780266,
      "grad_norm": 0.3536144495010376,
      "learning_rate": 1.9225190446470626e-05,
      "loss": 0.5716,
      "step": 8300
    },
    {
      "epoch": 0.25499953921297575,
      "grad_norm": 0.31192684173583984,
      "learning_rate": 1.9225003914052225e-05,
      "loss": 0.5235,
      "step": 8301
    },
    {
      "epoch": 0.2550302583479249,
      "grad_norm": 0.33229339122772217,
      "learning_rate": 1.9224817360088182e-05,
      "loss": 0.6497,
      "step": 8302
    },
    {
      "epoch": 0.2550609774828741,
      "grad_norm": 0.32523420453071594,
      "learning_rate": 1.9224630784578936e-05,
      "loss": 0.5882,
      "step": 8303
    },
    {
      "epoch": 0.2550916966178232,
      "grad_norm": 0.3026721477508545,
      "learning_rate": 1.922444418752492e-05,
      "loss": 0.5084,
      "step": 8304
    },
    {
      "epoch": 0.2551224157527724,
      "grad_norm": 0.6374772191047668,
      "learning_rate": 1.922425756892657e-05,
      "loss": 0.6336,
      "step": 8305
    },
    {
      "epoch": 0.25515313488772157,
      "grad_norm": 0.37942519783973694,
      "learning_rate": 1.922407092878432e-05,
      "loss": 0.555,
      "step": 8306
    },
    {
      "epoch": 0.25518385402267074,
      "grad_norm": 0.4033357501029968,
      "learning_rate": 1.9223884267098613e-05,
      "loss": 0.6241,
      "step": 8307
    },
    {
      "epoch": 0.25521457315761986,
      "grad_norm": 0.34557223320007324,
      "learning_rate": 1.922369758386988e-05,
      "loss": 0.5888,
      "step": 8308
    },
    {
      "epoch": 0.25524529229256904,
      "grad_norm": 0.3422186076641083,
      "learning_rate": 1.922351087909855e-05,
      "loss": 0.5857,
      "step": 8309
    },
    {
      "epoch": 0.2552760114275182,
      "grad_norm": 0.33873534202575684,
      "learning_rate": 1.922332415278507e-05,
      "loss": 0.5518,
      "step": 8310
    },
    {
      "epoch": 0.2553067305624674,
      "grad_norm": 0.3332017660140991,
      "learning_rate": 1.9223137404929874e-05,
      "loss": 0.5898,
      "step": 8311
    },
    {
      "epoch": 0.2553374496974165,
      "grad_norm": 0.4061068296432495,
      "learning_rate": 1.9222950635533396e-05,
      "loss": 0.6671,
      "step": 8312
    },
    {
      "epoch": 0.2553681688323657,
      "grad_norm": 0.3732234537601471,
      "learning_rate": 1.922276384459607e-05,
      "loss": 0.5539,
      "step": 8313
    },
    {
      "epoch": 0.25539888796731486,
      "grad_norm": 0.4348270893096924,
      "learning_rate": 1.922257703211834e-05,
      "loss": 0.6074,
      "step": 8314
    },
    {
      "epoch": 0.255429607102264,
      "grad_norm": 0.3958265781402588,
      "learning_rate": 1.9222390198100634e-05,
      "loss": 0.5926,
      "step": 8315
    },
    {
      "epoch": 0.25546032623721315,
      "grad_norm": 0.3367861807346344,
      "learning_rate": 1.9222203342543392e-05,
      "loss": 0.5369,
      "step": 8316
    },
    {
      "epoch": 0.25549104537216233,
      "grad_norm": 0.35535067319869995,
      "learning_rate": 1.9222016465447048e-05,
      "loss": 0.6254,
      "step": 8317
    },
    {
      "epoch": 0.2555217645071115,
      "grad_norm": 0.31930115818977356,
      "learning_rate": 1.922182956681204e-05,
      "loss": 0.597,
      "step": 8318
    },
    {
      "epoch": 0.2555524836420606,
      "grad_norm": 0.3558056354522705,
      "learning_rate": 1.922164264663881e-05,
      "loss": 0.5817,
      "step": 8319
    },
    {
      "epoch": 0.2555832027770098,
      "grad_norm": 0.5783113241195679,
      "learning_rate": 1.9221455704927784e-05,
      "loss": 0.5993,
      "step": 8320
    },
    {
      "epoch": 0.255613921911959,
      "grad_norm": 0.3064529597759247,
      "learning_rate": 1.9221268741679407e-05,
      "loss": 0.5168,
      "step": 8321
    },
    {
      "epoch": 0.2556446410469081,
      "grad_norm": 0.39963752031326294,
      "learning_rate": 1.9221081756894116e-05,
      "loss": 0.5941,
      "step": 8322
    },
    {
      "epoch": 0.25567536018185727,
      "grad_norm": 0.3655494451522827,
      "learning_rate": 1.9220894750572342e-05,
      "loss": 0.5688,
      "step": 8323
    },
    {
      "epoch": 0.25570607931680644,
      "grad_norm": 0.3439558744430542,
      "learning_rate": 1.9220707722714524e-05,
      "loss": 0.5671,
      "step": 8324
    },
    {
      "epoch": 0.2557367984517556,
      "grad_norm": 0.32365167140960693,
      "learning_rate": 1.9220520673321097e-05,
      "loss": 0.5572,
      "step": 8325
    },
    {
      "epoch": 0.25576751758670474,
      "grad_norm": 0.3465307354927063,
      "learning_rate": 1.92203336023925e-05,
      "loss": 0.6031,
      "step": 8326
    },
    {
      "epoch": 0.2557982367216539,
      "grad_norm": 0.3484705090522766,
      "learning_rate": 1.9220146509929174e-05,
      "loss": 0.5351,
      "step": 8327
    },
    {
      "epoch": 0.2558289558566031,
      "grad_norm": 0.3507540225982666,
      "learning_rate": 1.9219959395931548e-05,
      "loss": 0.5553,
      "step": 8328
    },
    {
      "epoch": 0.2558596749915522,
      "grad_norm": 0.3864234983921051,
      "learning_rate": 1.9219772260400068e-05,
      "loss": 0.6467,
      "step": 8329
    },
    {
      "epoch": 0.2558903941265014,
      "grad_norm": 0.35561054944992065,
      "learning_rate": 1.921958510333516e-05,
      "loss": 0.5891,
      "step": 8330
    },
    {
      "epoch": 0.25592111326145056,
      "grad_norm": 0.3526415228843689,
      "learning_rate": 1.921939792473727e-05,
      "loss": 0.4987,
      "step": 8331
    },
    {
      "epoch": 0.25595183239639974,
      "grad_norm": 0.38084927201271057,
      "learning_rate": 1.9219210724606835e-05,
      "loss": 0.5843,
      "step": 8332
    },
    {
      "epoch": 0.25598255153134886,
      "grad_norm": 0.3239787220954895,
      "learning_rate": 1.9219023502944284e-05,
      "loss": 0.5454,
      "step": 8333
    },
    {
      "epoch": 0.25601327066629803,
      "grad_norm": 0.35937100648880005,
      "learning_rate": 1.9218836259750065e-05,
      "loss": 0.5933,
      "step": 8334
    },
    {
      "epoch": 0.2560439898012472,
      "grad_norm": 0.7028899788856506,
      "learning_rate": 1.9218648995024606e-05,
      "loss": 0.6053,
      "step": 8335
    },
    {
      "epoch": 0.2560747089361964,
      "grad_norm": 0.541114330291748,
      "learning_rate": 1.921846170876835e-05,
      "loss": 0.5372,
      "step": 8336
    },
    {
      "epoch": 0.2561054280711455,
      "grad_norm": 0.332061231136322,
      "learning_rate": 1.9218274400981732e-05,
      "loss": 0.5424,
      "step": 8337
    },
    {
      "epoch": 0.2561361472060947,
      "grad_norm": 0.3522573411464691,
      "learning_rate": 1.9218087071665194e-05,
      "loss": 0.6242,
      "step": 8338
    },
    {
      "epoch": 0.25616686634104385,
      "grad_norm": 0.3371701240539551,
      "learning_rate": 1.9217899720819165e-05,
      "loss": 0.5265,
      "step": 8339
    },
    {
      "epoch": 0.256197585475993,
      "grad_norm": 0.3522646129131317,
      "learning_rate": 1.921771234844409e-05,
      "loss": 0.5393,
      "step": 8340
    },
    {
      "epoch": 0.25622830461094215,
      "grad_norm": 0.37950047850608826,
      "learning_rate": 1.9217524954540404e-05,
      "loss": 0.6014,
      "step": 8341
    },
    {
      "epoch": 0.2562590237458913,
      "grad_norm": 0.37030550837516785,
      "learning_rate": 1.921733753910854e-05,
      "loss": 0.593,
      "step": 8342
    },
    {
      "epoch": 0.2562897428808405,
      "grad_norm": 0.44248276948928833,
      "learning_rate": 1.9217150102148947e-05,
      "loss": 0.5534,
      "step": 8343
    },
    {
      "epoch": 0.2563204620157896,
      "grad_norm": 0.3368872404098511,
      "learning_rate": 1.9216962643662053e-05,
      "loss": 0.6871,
      "step": 8344
    },
    {
      "epoch": 0.2563511811507388,
      "grad_norm": 0.38319915533065796,
      "learning_rate": 1.92167751636483e-05,
      "loss": 0.5227,
      "step": 8345
    },
    {
      "epoch": 0.25638190028568797,
      "grad_norm": 0.3318663239479065,
      "learning_rate": 1.9216587662108127e-05,
      "loss": 0.5699,
      "step": 8346
    },
    {
      "epoch": 0.2564126194206371,
      "grad_norm": 0.3618440330028534,
      "learning_rate": 1.9216400139041967e-05,
      "loss": 0.5567,
      "step": 8347
    },
    {
      "epoch": 0.25644333855558626,
      "grad_norm": 0.37384894490242004,
      "learning_rate": 1.921621259445026e-05,
      "loss": 0.6126,
      "step": 8348
    },
    {
      "epoch": 0.25647405769053544,
      "grad_norm": 1.0549741983413696,
      "learning_rate": 1.9216025028333444e-05,
      "loss": 0.6185,
      "step": 8349
    },
    {
      "epoch": 0.2565047768254846,
      "grad_norm": 0.3201773166656494,
      "learning_rate": 1.9215837440691962e-05,
      "loss": 0.5132,
      "step": 8350
    },
    {
      "epoch": 0.25653549596043373,
      "grad_norm": 0.3349142372608185,
      "learning_rate": 1.9215649831526247e-05,
      "loss": 0.5751,
      "step": 8351
    },
    {
      "epoch": 0.2565662150953829,
      "grad_norm": 0.39289531111717224,
      "learning_rate": 1.9215462200836735e-05,
      "loss": 0.6047,
      "step": 8352
    },
    {
      "epoch": 0.2565969342303321,
      "grad_norm": 0.4867169260978699,
      "learning_rate": 1.921527454862387e-05,
      "loss": 0.5975,
      "step": 8353
    },
    {
      "epoch": 0.25662765336528126,
      "grad_norm": 0.3449751138687134,
      "learning_rate": 1.921508687488809e-05,
      "loss": 0.5648,
      "step": 8354
    },
    {
      "epoch": 0.2566583725002304,
      "grad_norm": 0.35124698281288147,
      "learning_rate": 1.921489917962983e-05,
      "loss": 0.5339,
      "step": 8355
    },
    {
      "epoch": 0.25668909163517956,
      "grad_norm": 0.4545419216156006,
      "learning_rate": 1.9214711462849524e-05,
      "loss": 0.5635,
      "step": 8356
    },
    {
      "epoch": 0.25671981077012873,
      "grad_norm": 0.35993334650993347,
      "learning_rate": 1.921452372454762e-05,
      "loss": 0.5789,
      "step": 8357
    },
    {
      "epoch": 0.25675052990507785,
      "grad_norm": 0.3508540987968445,
      "learning_rate": 1.9214335964724552e-05,
      "loss": 0.523,
      "step": 8358
    },
    {
      "epoch": 0.256781249040027,
      "grad_norm": 0.35137107968330383,
      "learning_rate": 1.921414818338076e-05,
      "loss": 0.5821,
      "step": 8359
    },
    {
      "epoch": 0.2568119681749762,
      "grad_norm": 0.4426778554916382,
      "learning_rate": 1.921396038051668e-05,
      "loss": 0.5709,
      "step": 8360
    },
    {
      "epoch": 0.2568426873099254,
      "grad_norm": 0.3565235137939453,
      "learning_rate": 1.9213772556132752e-05,
      "loss": 0.5895,
      "step": 8361
    },
    {
      "epoch": 0.2568734064448745,
      "grad_norm": 0.31514570116996765,
      "learning_rate": 1.9213584710229413e-05,
      "loss": 0.6123,
      "step": 8362
    },
    {
      "epoch": 0.2569041255798237,
      "grad_norm": 0.3502335250377655,
      "learning_rate": 1.9213396842807107e-05,
      "loss": 0.5678,
      "step": 8363
    },
    {
      "epoch": 0.25693484471477285,
      "grad_norm": 0.36160996556282043,
      "learning_rate": 1.9213208953866268e-05,
      "loss": 0.6148,
      "step": 8364
    },
    {
      "epoch": 0.25696556384972197,
      "grad_norm": 0.33181634545326233,
      "learning_rate": 1.9213021043407336e-05,
      "loss": 0.5723,
      "step": 8365
    },
    {
      "epoch": 0.25699628298467114,
      "grad_norm": 0.6849623322486877,
      "learning_rate": 1.921283311143075e-05,
      "loss": 0.5778,
      "step": 8366
    },
    {
      "epoch": 0.2570270021196203,
      "grad_norm": 0.3445869982242584,
      "learning_rate": 1.921264515793695e-05,
      "loss": 0.6034,
      "step": 8367
    },
    {
      "epoch": 0.2570577212545695,
      "grad_norm": 0.35210371017456055,
      "learning_rate": 1.921245718292637e-05,
      "loss": 0.5991,
      "step": 8368
    },
    {
      "epoch": 0.2570884403895186,
      "grad_norm": 0.33658111095428467,
      "learning_rate": 1.9212269186399454e-05,
      "loss": 0.6108,
      "step": 8369
    },
    {
      "epoch": 0.2571191595244678,
      "grad_norm": 0.4272942543029785,
      "learning_rate": 1.921208116835664e-05,
      "loss": 0.631,
      "step": 8370
    },
    {
      "epoch": 0.25714987865941696,
      "grad_norm": 0.35596874356269836,
      "learning_rate": 1.9211893128798372e-05,
      "loss": 0.6175,
      "step": 8371
    },
    {
      "epoch": 0.2571805977943661,
      "grad_norm": 0.37229210138320923,
      "learning_rate": 1.921170506772508e-05,
      "loss": 0.635,
      "step": 8372
    },
    {
      "epoch": 0.25721131692931526,
      "grad_norm": 0.36065563559532166,
      "learning_rate": 1.9211516985137208e-05,
      "loss": 0.6317,
      "step": 8373
    },
    {
      "epoch": 0.25724203606426443,
      "grad_norm": 0.3491560220718384,
      "learning_rate": 1.9211328881035194e-05,
      "loss": 0.6058,
      "step": 8374
    },
    {
      "epoch": 0.2572727551992136,
      "grad_norm": 0.316683828830719,
      "learning_rate": 1.921114075541948e-05,
      "loss": 0.593,
      "step": 8375
    },
    {
      "epoch": 0.25730347433416273,
      "grad_norm": 0.3620360195636749,
      "learning_rate": 1.9210952608290502e-05,
      "loss": 0.5651,
      "step": 8376
    },
    {
      "epoch": 0.2573341934691119,
      "grad_norm": 0.36430102586746216,
      "learning_rate": 1.92107644396487e-05,
      "loss": 0.6605,
      "step": 8377
    },
    {
      "epoch": 0.2573649126040611,
      "grad_norm": 0.3287462294101715,
      "learning_rate": 1.9210576249494517e-05,
      "loss": 0.5726,
      "step": 8378
    },
    {
      "epoch": 0.25739563173901026,
      "grad_norm": 0.35305526852607727,
      "learning_rate": 1.921038803782839e-05,
      "loss": 0.5336,
      "step": 8379
    },
    {
      "epoch": 0.2574263508739594,
      "grad_norm": 0.34467318654060364,
      "learning_rate": 1.9210199804650754e-05,
      "loss": 0.5833,
      "step": 8380
    },
    {
      "epoch": 0.25745707000890855,
      "grad_norm": 0.3426707983016968,
      "learning_rate": 1.9210011549962054e-05,
      "loss": 0.7091,
      "step": 8381
    },
    {
      "epoch": 0.2574877891438577,
      "grad_norm": 0.3380512595176697,
      "learning_rate": 1.9209823273762732e-05,
      "loss": 0.5127,
      "step": 8382
    },
    {
      "epoch": 0.25751850827880685,
      "grad_norm": 0.3261917531490326,
      "learning_rate": 1.9209634976053226e-05,
      "loss": 0.5126,
      "step": 8383
    },
    {
      "epoch": 0.257549227413756,
      "grad_norm": 0.3352435529232025,
      "learning_rate": 1.920944665683397e-05,
      "loss": 0.4357,
      "step": 8384
    },
    {
      "epoch": 0.2575799465487052,
      "grad_norm": 0.3758123517036438,
      "learning_rate": 1.920925831610541e-05,
      "loss": 0.5615,
      "step": 8385
    },
    {
      "epoch": 0.25761066568365437,
      "grad_norm": 0.3901548981666565,
      "learning_rate": 1.9209069953867984e-05,
      "loss": 0.5832,
      "step": 8386
    },
    {
      "epoch": 0.2576413848186035,
      "grad_norm": 0.39872175455093384,
      "learning_rate": 1.9208881570122132e-05,
      "loss": 0.6112,
      "step": 8387
    },
    {
      "epoch": 0.25767210395355267,
      "grad_norm": 0.36001625657081604,
      "learning_rate": 1.9208693164868294e-05,
      "loss": 0.6213,
      "step": 8388
    },
    {
      "epoch": 0.25770282308850184,
      "grad_norm": 0.32904139161109924,
      "learning_rate": 1.920850473810691e-05,
      "loss": 0.4984,
      "step": 8389
    },
    {
      "epoch": 0.25773354222345096,
      "grad_norm": 0.40487271547317505,
      "learning_rate": 1.920831628983842e-05,
      "loss": 0.6284,
      "step": 8390
    },
    {
      "epoch": 0.25776426135840014,
      "grad_norm": 0.3538924753665924,
      "learning_rate": 1.9208127820063263e-05,
      "loss": 0.602,
      "step": 8391
    },
    {
      "epoch": 0.2577949804933493,
      "grad_norm": 0.3537263870239258,
      "learning_rate": 1.920793932878188e-05,
      "loss": 0.5879,
      "step": 8392
    },
    {
      "epoch": 0.2578256996282985,
      "grad_norm": 0.3580808639526367,
      "learning_rate": 1.9207750815994715e-05,
      "loss": 0.6041,
      "step": 8393
    },
    {
      "epoch": 0.2578564187632476,
      "grad_norm": 0.33015739917755127,
      "learning_rate": 1.92075622817022e-05,
      "loss": 0.5588,
      "step": 8394
    },
    {
      "epoch": 0.2578871378981968,
      "grad_norm": 0.3673814833164215,
      "learning_rate": 1.9207373725904784e-05,
      "loss": 0.6002,
      "step": 8395
    },
    {
      "epoch": 0.25791785703314596,
      "grad_norm": 0.38785138726234436,
      "learning_rate": 1.9207185148602905e-05,
      "loss": 0.5237,
      "step": 8396
    },
    {
      "epoch": 0.25794857616809513,
      "grad_norm": 0.3921777307987213,
      "learning_rate": 1.9206996549797e-05,
      "loss": 0.5704,
      "step": 8397
    },
    {
      "epoch": 0.25797929530304425,
      "grad_norm": 0.6662288308143616,
      "learning_rate": 1.920680792948751e-05,
      "loss": 0.5971,
      "step": 8398
    },
    {
      "epoch": 0.25801001443799343,
      "grad_norm": 0.32414183020591736,
      "learning_rate": 1.9206619287674878e-05,
      "loss": 0.4789,
      "step": 8399
    },
    {
      "epoch": 0.2580407335729426,
      "grad_norm": 0.3465017080307007,
      "learning_rate": 1.9206430624359544e-05,
      "loss": 0.5691,
      "step": 8400
    },
    {
      "epoch": 0.2580714527078917,
      "grad_norm": 0.32809552550315857,
      "learning_rate": 1.920624193954195e-05,
      "loss": 0.6133,
      "step": 8401
    },
    {
      "epoch": 0.2581021718428409,
      "grad_norm": 0.3987266719341278,
      "learning_rate": 1.9206053233222533e-05,
      "loss": 0.6697,
      "step": 8402
    },
    {
      "epoch": 0.2581328909777901,
      "grad_norm": 0.3876710832118988,
      "learning_rate": 1.9205864505401737e-05,
      "loss": 0.6622,
      "step": 8403
    },
    {
      "epoch": 0.25816361011273925,
      "grad_norm": 0.38597238063812256,
      "learning_rate": 1.920567575608e-05,
      "loss": 0.6238,
      "step": 8404
    },
    {
      "epoch": 0.25819432924768837,
      "grad_norm": 0.32934948801994324,
      "learning_rate": 1.9205486985257766e-05,
      "loss": 0.5347,
      "step": 8405
    },
    {
      "epoch": 0.25822504838263755,
      "grad_norm": 0.3313177824020386,
      "learning_rate": 1.9205298192935472e-05,
      "loss": 0.6195,
      "step": 8406
    },
    {
      "epoch": 0.2582557675175867,
      "grad_norm": 0.33913710713386536,
      "learning_rate": 1.9205109379113565e-05,
      "loss": 0.5697,
      "step": 8407
    },
    {
      "epoch": 0.25828648665253584,
      "grad_norm": 0.40206462144851685,
      "learning_rate": 1.9204920543792477e-05,
      "loss": 0.5712,
      "step": 8408
    },
    {
      "epoch": 0.258317205787485,
      "grad_norm": 0.3342077136039734,
      "learning_rate": 1.920473168697266e-05,
      "loss": 0.5336,
      "step": 8409
    },
    {
      "epoch": 0.2583479249224342,
      "grad_norm": 0.33197325468063354,
      "learning_rate": 1.9204542808654546e-05,
      "loss": 0.5565,
      "step": 8410
    },
    {
      "epoch": 0.25837864405738337,
      "grad_norm": 0.43398189544677734,
      "learning_rate": 1.9204353908838577e-05,
      "loss": 0.5336,
      "step": 8411
    },
    {
      "epoch": 0.2584093631923325,
      "grad_norm": 0.36541929841041565,
      "learning_rate": 1.92041649875252e-05,
      "loss": 0.6895,
      "step": 8412
    },
    {
      "epoch": 0.25844008232728166,
      "grad_norm": 0.36581993103027344,
      "learning_rate": 1.9203976044714855e-05,
      "loss": 0.6654,
      "step": 8413
    },
    {
      "epoch": 0.25847080146223084,
      "grad_norm": 0.3536546528339386,
      "learning_rate": 1.9203787080407976e-05,
      "loss": 0.5899,
      "step": 8414
    },
    {
      "epoch": 0.25850152059717996,
      "grad_norm": 0.5512863993644714,
      "learning_rate": 1.9203598094605013e-05,
      "loss": 0.6269,
      "step": 8415
    },
    {
      "epoch": 0.25853223973212913,
      "grad_norm": 0.3745993673801422,
      "learning_rate": 1.92034090873064e-05,
      "loss": 0.537,
      "step": 8416
    },
    {
      "epoch": 0.2585629588670783,
      "grad_norm": 0.3713419735431671,
      "learning_rate": 1.9203220058512586e-05,
      "loss": 0.5239,
      "step": 8417
    },
    {
      "epoch": 0.2585936780020275,
      "grad_norm": 0.371114045381546,
      "learning_rate": 1.920303100822401e-05,
      "loss": 0.5597,
      "step": 8418
    },
    {
      "epoch": 0.2586243971369766,
      "grad_norm": 0.5399904847145081,
      "learning_rate": 1.9202841936441107e-05,
      "loss": 0.7273,
      "step": 8419
    },
    {
      "epoch": 0.2586551162719258,
      "grad_norm": 0.30921491980552673,
      "learning_rate": 1.9202652843164328e-05,
      "loss": 0.525,
      "step": 8420
    },
    {
      "epoch": 0.25868583540687495,
      "grad_norm": 0.37394216656684875,
      "learning_rate": 1.920246372839411e-05,
      "loss": 0.5345,
      "step": 8421
    },
    {
      "epoch": 0.25871655454182413,
      "grad_norm": 0.3397185802459717,
      "learning_rate": 1.9202274592130894e-05,
      "loss": 0.535,
      "step": 8422
    },
    {
      "epoch": 0.25874727367677325,
      "grad_norm": 0.3415963351726532,
      "learning_rate": 1.9202085434375124e-05,
      "loss": 0.5212,
      "step": 8423
    },
    {
      "epoch": 0.2587779928117224,
      "grad_norm": 0.3364271819591522,
      "learning_rate": 1.920189625512724e-05,
      "loss": 0.5842,
      "step": 8424
    },
    {
      "epoch": 0.2588087119466716,
      "grad_norm": 0.34548842906951904,
      "learning_rate": 1.9201707054387686e-05,
      "loss": 0.6016,
      "step": 8425
    },
    {
      "epoch": 0.2588394310816207,
      "grad_norm": 0.43948519229888916,
      "learning_rate": 1.9201517832156903e-05,
      "loss": 0.6443,
      "step": 8426
    },
    {
      "epoch": 0.2588701502165699,
      "grad_norm": 0.3031803071498871,
      "learning_rate": 1.9201328588435332e-05,
      "loss": 0.4955,
      "step": 8427
    },
    {
      "epoch": 0.25890086935151907,
      "grad_norm": 0.4351523518562317,
      "learning_rate": 1.9201139323223414e-05,
      "loss": 0.5875,
      "step": 8428
    },
    {
      "epoch": 0.25893158848646824,
      "grad_norm": 0.32699647545814514,
      "learning_rate": 1.9200950036521592e-05,
      "loss": 0.5691,
      "step": 8429
    },
    {
      "epoch": 0.25896230762141736,
      "grad_norm": 0.31974121928215027,
      "learning_rate": 1.920076072833031e-05,
      "loss": 0.6011,
      "step": 8430
    },
    {
      "epoch": 0.25899302675636654,
      "grad_norm": 0.436801016330719,
      "learning_rate": 1.920057139865001e-05,
      "loss": 0.6076,
      "step": 8431
    },
    {
      "epoch": 0.2590237458913157,
      "grad_norm": 0.39863649010658264,
      "learning_rate": 1.920038204748113e-05,
      "loss": 0.4878,
      "step": 8432
    },
    {
      "epoch": 0.25905446502626484,
      "grad_norm": 0.3513449430465698,
      "learning_rate": 1.920019267482412e-05,
      "loss": 0.651,
      "step": 8433
    },
    {
      "epoch": 0.259085184161214,
      "grad_norm": 0.354182630777359,
      "learning_rate": 1.9200003280679414e-05,
      "loss": 0.6561,
      "step": 8434
    },
    {
      "epoch": 0.2591159032961632,
      "grad_norm": 0.3393734097480774,
      "learning_rate": 1.9199813865047455e-05,
      "loss": 0.5759,
      "step": 8435
    },
    {
      "epoch": 0.25914662243111236,
      "grad_norm": 0.5928172469139099,
      "learning_rate": 1.9199624427928693e-05,
      "loss": 0.5985,
      "step": 8436
    },
    {
      "epoch": 0.2591773415660615,
      "grad_norm": 0.32440996170043945,
      "learning_rate": 1.9199434969323564e-05,
      "loss": 0.6021,
      "step": 8437
    },
    {
      "epoch": 0.25920806070101066,
      "grad_norm": 0.341040700674057,
      "learning_rate": 1.919924548923251e-05,
      "loss": 0.5577,
      "step": 8438
    },
    {
      "epoch": 0.25923877983595983,
      "grad_norm": 0.3697914481163025,
      "learning_rate": 1.919905598765598e-05,
      "loss": 0.6025,
      "step": 8439
    },
    {
      "epoch": 0.25926949897090895,
      "grad_norm": 0.3551967442035675,
      "learning_rate": 1.9198866464594407e-05,
      "loss": 0.6382,
      "step": 8440
    },
    {
      "epoch": 0.2593002181058581,
      "grad_norm": 0.36061891913414,
      "learning_rate": 1.9198676920048242e-05,
      "loss": 0.5761,
      "step": 8441
    },
    {
      "epoch": 0.2593309372408073,
      "grad_norm": 0.4187569320201874,
      "learning_rate": 1.919848735401793e-05,
      "loss": 0.7101,
      "step": 8442
    },
    {
      "epoch": 0.2593616563757565,
      "grad_norm": 0.32394054532051086,
      "learning_rate": 1.91982977665039e-05,
      "loss": 0.6386,
      "step": 8443
    },
    {
      "epoch": 0.2593923755107056,
      "grad_norm": 0.3568401634693146,
      "learning_rate": 1.9198108157506607e-05,
      "loss": 0.6404,
      "step": 8444
    },
    {
      "epoch": 0.2594230946456548,
      "grad_norm": 0.36053451895713806,
      "learning_rate": 1.919791852702649e-05,
      "loss": 0.5762,
      "step": 8445
    },
    {
      "epoch": 0.25945381378060395,
      "grad_norm": 0.38450247049331665,
      "learning_rate": 1.919772887506399e-05,
      "loss": 0.5193,
      "step": 8446
    },
    {
      "epoch": 0.2594845329155531,
      "grad_norm": 0.35586583614349365,
      "learning_rate": 1.9197539201619554e-05,
      "loss": 0.5696,
      "step": 8447
    },
    {
      "epoch": 0.25951525205050224,
      "grad_norm": 0.3618321120738983,
      "learning_rate": 1.9197349506693622e-05,
      "loss": 0.5242,
      "step": 8448
    },
    {
      "epoch": 0.2595459711854514,
      "grad_norm": 0.5853043794631958,
      "learning_rate": 1.9197159790286637e-05,
      "loss": 0.5782,
      "step": 8449
    },
    {
      "epoch": 0.2595766903204006,
      "grad_norm": 0.3509127199649811,
      "learning_rate": 1.919697005239904e-05,
      "loss": 0.6589,
      "step": 8450
    },
    {
      "epoch": 0.2596074094553497,
      "grad_norm": 0.39387160539627075,
      "learning_rate": 1.9196780293031283e-05,
      "loss": 0.6226,
      "step": 8451
    },
    {
      "epoch": 0.2596381285902989,
      "grad_norm": 0.37881380319595337,
      "learning_rate": 1.9196590512183802e-05,
      "loss": 0.5628,
      "step": 8452
    },
    {
      "epoch": 0.25966884772524806,
      "grad_norm": 0.3365399241447449,
      "learning_rate": 1.919640070985704e-05,
      "loss": 0.6114,
      "step": 8453
    },
    {
      "epoch": 0.25969956686019724,
      "grad_norm": 0.36410364508628845,
      "learning_rate": 1.9196210886051444e-05,
      "loss": 0.5829,
      "step": 8454
    },
    {
      "epoch": 0.25973028599514636,
      "grad_norm": 0.3657205402851105,
      "learning_rate": 1.9196021040767453e-05,
      "loss": 0.5824,
      "step": 8455
    },
    {
      "epoch": 0.25976100513009553,
      "grad_norm": 0.4126923084259033,
      "learning_rate": 1.9195831174005512e-05,
      "loss": 0.567,
      "step": 8456
    },
    {
      "epoch": 0.2597917242650447,
      "grad_norm": 0.35808369517326355,
      "learning_rate": 1.9195641285766065e-05,
      "loss": 0.5876,
      "step": 8457
    },
    {
      "epoch": 0.25982244339999383,
      "grad_norm": 0.333223819732666,
      "learning_rate": 1.919545137604956e-05,
      "loss": 0.6199,
      "step": 8458
    },
    {
      "epoch": 0.259853162534943,
      "grad_norm": 0.7553547024726868,
      "learning_rate": 1.919526144485643e-05,
      "loss": 0.5869,
      "step": 8459
    },
    {
      "epoch": 0.2598838816698922,
      "grad_norm": 0.3350219428539276,
      "learning_rate": 1.9195071492187128e-05,
      "loss": 0.6632,
      "step": 8460
    },
    {
      "epoch": 0.25991460080484136,
      "grad_norm": 0.34280940890312195,
      "learning_rate": 1.9194881518042097e-05,
      "loss": 0.5472,
      "step": 8461
    },
    {
      "epoch": 0.2599453199397905,
      "grad_norm": 0.46908918023109436,
      "learning_rate": 1.9194691522421776e-05,
      "loss": 0.7192,
      "step": 8462
    },
    {
      "epoch": 0.25997603907473965,
      "grad_norm": 0.3715907633304596,
      "learning_rate": 1.919450150532661e-05,
      "loss": 0.5881,
      "step": 8463
    },
    {
      "epoch": 0.2600067582096888,
      "grad_norm": 0.3595026135444641,
      "learning_rate": 1.919431146675704e-05,
      "loss": 0.5394,
      "step": 8464
    },
    {
      "epoch": 0.260037477344638,
      "grad_norm": 0.3287903666496277,
      "learning_rate": 1.919412140671352e-05,
      "loss": 0.6512,
      "step": 8465
    },
    {
      "epoch": 0.2600681964795871,
      "grad_norm": 0.39930716156959534,
      "learning_rate": 1.9193931325196485e-05,
      "loss": 0.5712,
      "step": 8466
    },
    {
      "epoch": 0.2600989156145363,
      "grad_norm": 0.34330013394355774,
      "learning_rate": 1.9193741222206383e-05,
      "loss": 0.6557,
      "step": 8467
    },
    {
      "epoch": 0.26012963474948547,
      "grad_norm": 0.6558748483657837,
      "learning_rate": 1.9193551097743653e-05,
      "loss": 0.5702,
      "step": 8468
    },
    {
      "epoch": 0.2601603538844346,
      "grad_norm": 0.31744787096977234,
      "learning_rate": 1.9193360951808743e-05,
      "loss": 0.5222,
      "step": 8469
    },
    {
      "epoch": 0.26019107301938377,
      "grad_norm": 0.3556458055973053,
      "learning_rate": 1.9193170784402097e-05,
      "loss": 0.6129,
      "step": 8470
    },
    {
      "epoch": 0.26022179215433294,
      "grad_norm": 0.33022600412368774,
      "learning_rate": 1.9192980595524155e-05,
      "loss": 0.5911,
      "step": 8471
    },
    {
      "epoch": 0.2602525112892821,
      "grad_norm": 0.45150846242904663,
      "learning_rate": 1.9192790385175368e-05,
      "loss": 0.6732,
      "step": 8472
    },
    {
      "epoch": 0.26028323042423124,
      "grad_norm": 0.33907797932624817,
      "learning_rate": 1.919260015335618e-05,
      "loss": 0.6321,
      "step": 8473
    },
    {
      "epoch": 0.2603139495591804,
      "grad_norm": 0.339253693819046,
      "learning_rate": 1.919240990006703e-05,
      "loss": 0.5115,
      "step": 8474
    },
    {
      "epoch": 0.2603446686941296,
      "grad_norm": 0.3328070342540741,
      "learning_rate": 1.9192219625308363e-05,
      "loss": 0.6354,
      "step": 8475
    },
    {
      "epoch": 0.2603753878290787,
      "grad_norm": 0.3555017113685608,
      "learning_rate": 1.9192029329080626e-05,
      "loss": 0.6521,
      "step": 8476
    },
    {
      "epoch": 0.2604061069640279,
      "grad_norm": 0.41972824931144714,
      "learning_rate": 1.9191839011384263e-05,
      "loss": 0.5299,
      "step": 8477
    },
    {
      "epoch": 0.26043682609897706,
      "grad_norm": 0.33733484148979187,
      "learning_rate": 1.919164867221972e-05,
      "loss": 0.5753,
      "step": 8478
    },
    {
      "epoch": 0.26046754523392623,
      "grad_norm": 0.3684072196483612,
      "learning_rate": 1.9191458311587435e-05,
      "loss": 0.5379,
      "step": 8479
    },
    {
      "epoch": 0.26049826436887535,
      "grad_norm": 0.3225468397140503,
      "learning_rate": 1.919126792948786e-05,
      "loss": 0.5347,
      "step": 8480
    },
    {
      "epoch": 0.26052898350382453,
      "grad_norm": 0.4204122722148895,
      "learning_rate": 1.919107752592144e-05,
      "loss": 0.6103,
      "step": 8481
    },
    {
      "epoch": 0.2605597026387737,
      "grad_norm": 0.3356093764305115,
      "learning_rate": 1.919088710088861e-05,
      "loss": 0.6144,
      "step": 8482
    },
    {
      "epoch": 0.2605904217737228,
      "grad_norm": 0.34645208716392517,
      "learning_rate": 1.9190696654389823e-05,
      "loss": 0.5108,
      "step": 8483
    },
    {
      "epoch": 0.260621140908672,
      "grad_norm": 0.37335851788520813,
      "learning_rate": 1.9190506186425523e-05,
      "loss": 0.6211,
      "step": 8484
    },
    {
      "epoch": 0.2606518600436212,
      "grad_norm": 0.3374592959880829,
      "learning_rate": 1.9190315696996154e-05,
      "loss": 0.6119,
      "step": 8485
    },
    {
      "epoch": 0.26068257917857035,
      "grad_norm": 0.4412243366241455,
      "learning_rate": 1.919012518610216e-05,
      "loss": 0.6166,
      "step": 8486
    },
    {
      "epoch": 0.26071329831351947,
      "grad_norm": 0.31606999039649963,
      "learning_rate": 1.918993465374399e-05,
      "loss": 0.5528,
      "step": 8487
    },
    {
      "epoch": 0.26074401744846865,
      "grad_norm": 0.33653852343559265,
      "learning_rate": 1.9189744099922085e-05,
      "loss": 0.6352,
      "step": 8488
    },
    {
      "epoch": 0.2607747365834178,
      "grad_norm": 0.344862163066864,
      "learning_rate": 1.918955352463689e-05,
      "loss": 0.5644,
      "step": 8489
    },
    {
      "epoch": 0.260805455718367,
      "grad_norm": 0.34384918212890625,
      "learning_rate": 1.918936292788885e-05,
      "loss": 0.5499,
      "step": 8490
    },
    {
      "epoch": 0.2608361748533161,
      "grad_norm": 0.33562541007995605,
      "learning_rate": 1.9189172309678413e-05,
      "loss": 0.5977,
      "step": 8491
    },
    {
      "epoch": 0.2608668939882653,
      "grad_norm": 0.33057430386543274,
      "learning_rate": 1.918898167000602e-05,
      "loss": 0.6165,
      "step": 8492
    },
    {
      "epoch": 0.26089761312321447,
      "grad_norm": 0.39845001697540283,
      "learning_rate": 1.918879100887212e-05,
      "loss": 0.6413,
      "step": 8493
    },
    {
      "epoch": 0.2609283322581636,
      "grad_norm": 0.3605203330516815,
      "learning_rate": 1.9188600326277157e-05,
      "loss": 0.5744,
      "step": 8494
    },
    {
      "epoch": 0.26095905139311276,
      "grad_norm": 0.3813885748386383,
      "learning_rate": 1.9188409622221576e-05,
      "loss": 0.6388,
      "step": 8495
    },
    {
      "epoch": 0.26098977052806194,
      "grad_norm": 0.29842594265937805,
      "learning_rate": 1.9188218896705822e-05,
      "loss": 0.5652,
      "step": 8496
    },
    {
      "epoch": 0.2610204896630111,
      "grad_norm": 0.33796894550323486,
      "learning_rate": 1.918802814973034e-05,
      "loss": 0.5524,
      "step": 8497
    },
    {
      "epoch": 0.26105120879796023,
      "grad_norm": 0.36626482009887695,
      "learning_rate": 1.918783738129558e-05,
      "loss": 0.5549,
      "step": 8498
    },
    {
      "epoch": 0.2610819279329094,
      "grad_norm": 0.4122002124786377,
      "learning_rate": 1.918764659140198e-05,
      "loss": 0.7224,
      "step": 8499
    },
    {
      "epoch": 0.2611126470678586,
      "grad_norm": 0.29269230365753174,
      "learning_rate": 1.9187455780049994e-05,
      "loss": 0.5024,
      "step": 8500
    },
    {
      "epoch": 0.2611433662028077,
      "grad_norm": 0.3680095076560974,
      "learning_rate": 1.918726494724006e-05,
      "loss": 0.6163,
      "step": 8501
    },
    {
      "epoch": 0.2611740853377569,
      "grad_norm": 0.37187477946281433,
      "learning_rate": 1.9187074092972627e-05,
      "loss": 0.5487,
      "step": 8502
    },
    {
      "epoch": 0.26120480447270605,
      "grad_norm": 0.3449639081954956,
      "learning_rate": 1.9186883217248143e-05,
      "loss": 0.5546,
      "step": 8503
    },
    {
      "epoch": 0.26123552360765523,
      "grad_norm": 0.3270503878593445,
      "learning_rate": 1.918669232006705e-05,
      "loss": 0.6006,
      "step": 8504
    },
    {
      "epoch": 0.26126624274260435,
      "grad_norm": 0.3097042441368103,
      "learning_rate": 1.9186501401429794e-05,
      "loss": 0.541,
      "step": 8505
    },
    {
      "epoch": 0.2612969618775535,
      "grad_norm": 0.3719574213027954,
      "learning_rate": 1.9186310461336827e-05,
      "loss": 0.5077,
      "step": 8506
    },
    {
      "epoch": 0.2613276810125027,
      "grad_norm": 0.3337031602859497,
      "learning_rate": 1.918611949978859e-05,
      "loss": 0.6245,
      "step": 8507
    },
    {
      "epoch": 0.2613584001474519,
      "grad_norm": 0.32008373737335205,
      "learning_rate": 1.9185928516785527e-05,
      "loss": 0.5037,
      "step": 8508
    },
    {
      "epoch": 0.261389119282401,
      "grad_norm": 0.35328608751296997,
      "learning_rate": 1.9185737512328088e-05,
      "loss": 0.5417,
      "step": 8509
    },
    {
      "epoch": 0.26141983841735017,
      "grad_norm": 0.4180358350276947,
      "learning_rate": 1.9185546486416714e-05,
      "loss": 0.5479,
      "step": 8510
    },
    {
      "epoch": 0.26145055755229935,
      "grad_norm": 0.3193531632423401,
      "learning_rate": 1.918535543905186e-05,
      "loss": 0.5988,
      "step": 8511
    },
    {
      "epoch": 0.26148127668724847,
      "grad_norm": 0.41306576132774353,
      "learning_rate": 1.9185164370233963e-05,
      "loss": 0.6255,
      "step": 8512
    },
    {
      "epoch": 0.26151199582219764,
      "grad_norm": 0.46524518728256226,
      "learning_rate": 1.918497327996347e-05,
      "loss": 0.6345,
      "step": 8513
    },
    {
      "epoch": 0.2615427149571468,
      "grad_norm": 0.3421257436275482,
      "learning_rate": 1.9184782168240835e-05,
      "loss": 0.5594,
      "step": 8514
    },
    {
      "epoch": 0.261573434092096,
      "grad_norm": 0.3875979483127594,
      "learning_rate": 1.91845910350665e-05,
      "loss": 0.642,
      "step": 8515
    },
    {
      "epoch": 0.2616041532270451,
      "grad_norm": 0.3152855634689331,
      "learning_rate": 1.918439988044091e-05,
      "loss": 0.6351,
      "step": 8516
    },
    {
      "epoch": 0.2616348723619943,
      "grad_norm": 0.3307898938655853,
      "learning_rate": 1.918420870436451e-05,
      "loss": 0.5395,
      "step": 8517
    },
    {
      "epoch": 0.26166559149694346,
      "grad_norm": 0.3206230401992798,
      "learning_rate": 1.9184017506837754e-05,
      "loss": 0.633,
      "step": 8518
    },
    {
      "epoch": 0.2616963106318926,
      "grad_norm": 0.346110999584198,
      "learning_rate": 1.9183826287861086e-05,
      "loss": 0.5919,
      "step": 8519
    },
    {
      "epoch": 0.26172702976684176,
      "grad_norm": 0.35199153423309326,
      "learning_rate": 1.9183635047434946e-05,
      "loss": 0.5941,
      "step": 8520
    },
    {
      "epoch": 0.26175774890179093,
      "grad_norm": 0.3227297365665436,
      "learning_rate": 1.9183443785559783e-05,
      "loss": 0.5597,
      "step": 8521
    },
    {
      "epoch": 0.2617884680367401,
      "grad_norm": 0.32325902581214905,
      "learning_rate": 1.9183252502236048e-05,
      "loss": 0.5739,
      "step": 8522
    },
    {
      "epoch": 0.2618191871716892,
      "grad_norm": 0.3115094006061554,
      "learning_rate": 1.9183061197464186e-05,
      "loss": 0.5163,
      "step": 8523
    },
    {
      "epoch": 0.2618499063066384,
      "grad_norm": 0.32263317704200745,
      "learning_rate": 1.9182869871244643e-05,
      "loss": 0.5201,
      "step": 8524
    },
    {
      "epoch": 0.2618806254415876,
      "grad_norm": 0.33352795243263245,
      "learning_rate": 1.9182678523577863e-05,
      "loss": 0.6587,
      "step": 8525
    },
    {
      "epoch": 0.2619113445765367,
      "grad_norm": 0.34361153841018677,
      "learning_rate": 1.91824871544643e-05,
      "loss": 0.6149,
      "step": 8526
    },
    {
      "epoch": 0.2619420637114859,
      "grad_norm": 0.31019067764282227,
      "learning_rate": 1.9182295763904396e-05,
      "loss": 0.5957,
      "step": 8527
    },
    {
      "epoch": 0.26197278284643505,
      "grad_norm": 0.32717934250831604,
      "learning_rate": 1.9182104351898596e-05,
      "loss": 0.5765,
      "step": 8528
    },
    {
      "epoch": 0.2620035019813842,
      "grad_norm": 0.37994396686553955,
      "learning_rate": 1.9181912918447355e-05,
      "loss": 0.6061,
      "step": 8529
    },
    {
      "epoch": 0.26203422111633334,
      "grad_norm": 0.3438194692134857,
      "learning_rate": 1.918172146355111e-05,
      "loss": 0.5919,
      "step": 8530
    },
    {
      "epoch": 0.2620649402512825,
      "grad_norm": 0.3439701199531555,
      "learning_rate": 1.918152998721032e-05,
      "loss": 0.5989,
      "step": 8531
    },
    {
      "epoch": 0.2620956593862317,
      "grad_norm": 0.3134026825428009,
      "learning_rate": 1.9181338489425418e-05,
      "loss": 0.5513,
      "step": 8532
    },
    {
      "epoch": 0.26212637852118087,
      "grad_norm": 0.3630007803440094,
      "learning_rate": 1.918114697019686e-05,
      "loss": 0.5367,
      "step": 8533
    },
    {
      "epoch": 0.26215709765613,
      "grad_norm": 2.1824119091033936,
      "learning_rate": 1.91809554295251e-05,
      "loss": 0.7148,
      "step": 8534
    },
    {
      "epoch": 0.26218781679107916,
      "grad_norm": 0.345398485660553,
      "learning_rate": 1.918076386741057e-05,
      "loss": 0.5927,
      "step": 8535
    },
    {
      "epoch": 0.26221853592602834,
      "grad_norm": 0.3576037585735321,
      "learning_rate": 1.9180572283853728e-05,
      "loss": 0.5814,
      "step": 8536
    },
    {
      "epoch": 0.26224925506097746,
      "grad_norm": 0.3604942262172699,
      "learning_rate": 1.9180380678855015e-05,
      "loss": 0.6848,
      "step": 8537
    },
    {
      "epoch": 0.26227997419592664,
      "grad_norm": 0.34088876843452454,
      "learning_rate": 1.9180189052414883e-05,
      "loss": 0.5965,
      "step": 8538
    },
    {
      "epoch": 0.2623106933308758,
      "grad_norm": 0.3199382424354553,
      "learning_rate": 1.917999740453378e-05,
      "loss": 0.6103,
      "step": 8539
    },
    {
      "epoch": 0.262341412465825,
      "grad_norm": 0.3564507067203522,
      "learning_rate": 1.917980573521215e-05,
      "loss": 0.6536,
      "step": 8540
    },
    {
      "epoch": 0.2623721316007741,
      "grad_norm": 0.32049381732940674,
      "learning_rate": 1.9179614044450443e-05,
      "loss": 0.5994,
      "step": 8541
    },
    {
      "epoch": 0.2624028507357233,
      "grad_norm": 0.3843544125556946,
      "learning_rate": 1.9179422332249105e-05,
      "loss": 0.6521,
      "step": 8542
    },
    {
      "epoch": 0.26243356987067246,
      "grad_norm": 0.2994089424610138,
      "learning_rate": 1.917923059860859e-05,
      "loss": 0.5538,
      "step": 8543
    },
    {
      "epoch": 0.2624642890056216,
      "grad_norm": 0.41258490085601807,
      "learning_rate": 1.9179038843529336e-05,
      "loss": 0.5667,
      "step": 8544
    },
    {
      "epoch": 0.26249500814057075,
      "grad_norm": 0.36281338334083557,
      "learning_rate": 1.9178847067011797e-05,
      "loss": 0.6144,
      "step": 8545
    },
    {
      "epoch": 0.2625257272755199,
      "grad_norm": 0.35347986221313477,
      "learning_rate": 1.9178655269056418e-05,
      "loss": 0.6147,
      "step": 8546
    },
    {
      "epoch": 0.2625564464104691,
      "grad_norm": 0.4175623655319214,
      "learning_rate": 1.9178463449663654e-05,
      "loss": 0.6343,
      "step": 8547
    },
    {
      "epoch": 0.2625871655454182,
      "grad_norm": 0.4029988944530487,
      "learning_rate": 1.9178271608833943e-05,
      "loss": 0.6117,
      "step": 8548
    },
    {
      "epoch": 0.2626178846803674,
      "grad_norm": 0.33154869079589844,
      "learning_rate": 1.917807974656774e-05,
      "loss": 0.5365,
      "step": 8549
    },
    {
      "epoch": 0.2626486038153166,
      "grad_norm": 0.34640833735466003,
      "learning_rate": 1.9177887862865486e-05,
      "loss": 0.6115,
      "step": 8550
    },
    {
      "epoch": 0.26267932295026575,
      "grad_norm": 0.31729528307914734,
      "learning_rate": 1.917769595772764e-05,
      "loss": 0.5378,
      "step": 8551
    },
    {
      "epoch": 0.26271004208521487,
      "grad_norm": 0.46107879281044006,
      "learning_rate": 1.9177504031154642e-05,
      "loss": 1.1178,
      "step": 8552
    },
    {
      "epoch": 0.26274076122016404,
      "grad_norm": 0.3560522198677063,
      "learning_rate": 1.917731208314694e-05,
      "loss": 0.5717,
      "step": 8553
    },
    {
      "epoch": 0.2627714803551132,
      "grad_norm": 0.3685148358345032,
      "learning_rate": 1.917712011370499e-05,
      "loss": 0.5499,
      "step": 8554
    },
    {
      "epoch": 0.26280219949006234,
      "grad_norm": 0.3241267502307892,
      "learning_rate": 1.917692812282923e-05,
      "loss": 0.5362,
      "step": 8555
    },
    {
      "epoch": 0.2628329186250115,
      "grad_norm": 0.3417528569698334,
      "learning_rate": 1.9176736110520114e-05,
      "loss": 0.6444,
      "step": 8556
    },
    {
      "epoch": 0.2628636377599607,
      "grad_norm": 0.3417874872684479,
      "learning_rate": 1.917654407677809e-05,
      "loss": 0.5511,
      "step": 8557
    },
    {
      "epoch": 0.26289435689490986,
      "grad_norm": 0.3350205421447754,
      "learning_rate": 1.917635202160361e-05,
      "loss": 0.6038,
      "step": 8558
    },
    {
      "epoch": 0.262925076029859,
      "grad_norm": 0.3464849591255188,
      "learning_rate": 1.9176159944997114e-05,
      "loss": 0.5525,
      "step": 8559
    },
    {
      "epoch": 0.26295579516480816,
      "grad_norm": 0.4327222406864166,
      "learning_rate": 1.917596784695906e-05,
      "loss": 0.6415,
      "step": 8560
    },
    {
      "epoch": 0.26298651429975733,
      "grad_norm": 0.32474657893180847,
      "learning_rate": 1.9175775727489888e-05,
      "loss": 0.5749,
      "step": 8561
    },
    {
      "epoch": 0.26301723343470645,
      "grad_norm": 0.33323007822036743,
      "learning_rate": 1.9175583586590055e-05,
      "loss": 0.5284,
      "step": 8562
    },
    {
      "epoch": 0.26304795256965563,
      "grad_norm": 0.36922502517700195,
      "learning_rate": 1.9175391424260004e-05,
      "loss": 0.6248,
      "step": 8563
    },
    {
      "epoch": 0.2630786717046048,
      "grad_norm": 0.39141130447387695,
      "learning_rate": 1.9175199240500185e-05,
      "loss": 0.6111,
      "step": 8564
    },
    {
      "epoch": 0.263109390839554,
      "grad_norm": 0.541361391544342,
      "learning_rate": 1.9175007035311046e-05,
      "loss": 0.5266,
      "step": 8565
    },
    {
      "epoch": 0.2631401099745031,
      "grad_norm": 0.7977179288864136,
      "learning_rate": 1.917481480869304e-05,
      "loss": 0.549,
      "step": 8566
    },
    {
      "epoch": 0.2631708291094523,
      "grad_norm": 0.33126649260520935,
      "learning_rate": 1.9174622560646613e-05,
      "loss": 0.6278,
      "step": 8567
    },
    {
      "epoch": 0.26320154824440145,
      "grad_norm": 0.3607638478279114,
      "learning_rate": 1.9174430291172213e-05,
      "loss": 0.5985,
      "step": 8568
    },
    {
      "epoch": 0.26323226737935057,
      "grad_norm": 0.3725287616252899,
      "learning_rate": 1.9174238000270292e-05,
      "loss": 0.6004,
      "step": 8569
    },
    {
      "epoch": 0.26326298651429975,
      "grad_norm": 0.3333872854709625,
      "learning_rate": 1.9174045687941298e-05,
      "loss": 0.5596,
      "step": 8570
    },
    {
      "epoch": 0.2632937056492489,
      "grad_norm": 0.34317559003829956,
      "learning_rate": 1.9173853354185676e-05,
      "loss": 0.6085,
      "step": 8571
    },
    {
      "epoch": 0.2633244247841981,
      "grad_norm": 0.35292309522628784,
      "learning_rate": 1.917366099900388e-05,
      "loss": 0.6209,
      "step": 8572
    },
    {
      "epoch": 0.2633551439191472,
      "grad_norm": 0.4825374484062195,
      "learning_rate": 1.917346862239636e-05,
      "loss": 0.6039,
      "step": 8573
    },
    {
      "epoch": 0.2633858630540964,
      "grad_norm": 0.3660709261894226,
      "learning_rate": 1.917327622436356e-05,
      "loss": 0.5935,
      "step": 8574
    },
    {
      "epoch": 0.26341658218904557,
      "grad_norm": 0.41419005393981934,
      "learning_rate": 1.9173083804905938e-05,
      "loss": 0.6097,
      "step": 8575
    },
    {
      "epoch": 0.26344730132399474,
      "grad_norm": 0.33252617716789246,
      "learning_rate": 1.9172891364023935e-05,
      "loss": 0.4906,
      "step": 8576
    },
    {
      "epoch": 0.26347802045894386,
      "grad_norm": 0.4028460383415222,
      "learning_rate": 1.9172698901718002e-05,
      "loss": 0.523,
      "step": 8577
    },
    {
      "epoch": 0.26350873959389304,
      "grad_norm": 0.34851452708244324,
      "learning_rate": 1.9172506417988594e-05,
      "loss": 0.6729,
      "step": 8578
    },
    {
      "epoch": 0.2635394587288422,
      "grad_norm": 0.3942740559577942,
      "learning_rate": 1.9172313912836154e-05,
      "loss": 0.594,
      "step": 8579
    },
    {
      "epoch": 0.26357017786379133,
      "grad_norm": 0.3468930125236511,
      "learning_rate": 1.9172121386261135e-05,
      "loss": 0.596,
      "step": 8580
    },
    {
      "epoch": 0.2636008969987405,
      "grad_norm": 0.3775671720504761,
      "learning_rate": 1.9171928838263983e-05,
      "loss": 0.6325,
      "step": 8581
    },
    {
      "epoch": 0.2636316161336897,
      "grad_norm": 0.4092210829257965,
      "learning_rate": 1.9171736268845157e-05,
      "loss": 0.5782,
      "step": 8582
    },
    {
      "epoch": 0.26366233526863886,
      "grad_norm": 0.3275635540485382,
      "learning_rate": 1.9171543678005092e-05,
      "loss": 0.5954,
      "step": 8583
    },
    {
      "epoch": 0.263693054403588,
      "grad_norm": 0.4057236611843109,
      "learning_rate": 1.9171351065744255e-05,
      "loss": 0.5596,
      "step": 8584
    },
    {
      "epoch": 0.26372377353853715,
      "grad_norm": 0.3731808066368103,
      "learning_rate": 1.9171158432063082e-05,
      "loss": 0.5731,
      "step": 8585
    },
    {
      "epoch": 0.26375449267348633,
      "grad_norm": 0.31362029910087585,
      "learning_rate": 1.917096577696203e-05,
      "loss": 0.584,
      "step": 8586
    },
    {
      "epoch": 0.26378521180843545,
      "grad_norm": 0.3233252465724945,
      "learning_rate": 1.9170773100441545e-05,
      "loss": 0.519,
      "step": 8587
    },
    {
      "epoch": 0.2638159309433846,
      "grad_norm": 0.3287304639816284,
      "learning_rate": 1.917058040250208e-05,
      "loss": 0.5354,
      "step": 8588
    },
    {
      "epoch": 0.2638466500783338,
      "grad_norm": 0.31928664445877075,
      "learning_rate": 1.9170387683144086e-05,
      "loss": 0.6139,
      "step": 8589
    },
    {
      "epoch": 0.263877369213283,
      "grad_norm": 0.32602551579475403,
      "learning_rate": 1.9170194942368008e-05,
      "loss": 0.6434,
      "step": 8590
    },
    {
      "epoch": 0.2639080883482321,
      "grad_norm": 0.33402854204177856,
      "learning_rate": 1.91700021801743e-05,
      "loss": 0.6487,
      "step": 8591
    },
    {
      "epoch": 0.26393880748318127,
      "grad_norm": 0.3243404030799866,
      "learning_rate": 1.916980939656341e-05,
      "loss": 0.5668,
      "step": 8592
    },
    {
      "epoch": 0.26396952661813045,
      "grad_norm": 0.3539455831050873,
      "learning_rate": 1.916961659153579e-05,
      "loss": 0.6563,
      "step": 8593
    },
    {
      "epoch": 0.2640002457530796,
      "grad_norm": 0.3879533112049103,
      "learning_rate": 1.9169423765091894e-05,
      "loss": 0.6501,
      "step": 8594
    },
    {
      "epoch": 0.26403096488802874,
      "grad_norm": 0.33644822239875793,
      "learning_rate": 1.9169230917232163e-05,
      "loss": 0.6304,
      "step": 8595
    },
    {
      "epoch": 0.2640616840229779,
      "grad_norm": 0.33295971155166626,
      "learning_rate": 1.9169038047957057e-05,
      "loss": 0.5925,
      "step": 8596
    },
    {
      "epoch": 0.2640924031579271,
      "grad_norm": 0.34748509526252747,
      "learning_rate": 1.9168845157267023e-05,
      "loss": 0.6151,
      "step": 8597
    },
    {
      "epoch": 0.2641231222928762,
      "grad_norm": 0.3289951682090759,
      "learning_rate": 1.9168652245162506e-05,
      "loss": 0.5674,
      "step": 8598
    },
    {
      "epoch": 0.2641538414278254,
      "grad_norm": 0.3522871732711792,
      "learning_rate": 1.9168459311643966e-05,
      "loss": 0.5664,
      "step": 8599
    },
    {
      "epoch": 0.26418456056277456,
      "grad_norm": 0.36649706959724426,
      "learning_rate": 1.9168266356711847e-05,
      "loss": 0.6039,
      "step": 8600
    },
    {
      "epoch": 0.26421527969772374,
      "grad_norm": 0.3710519075393677,
      "learning_rate": 1.91680733803666e-05,
      "loss": 0.5879,
      "step": 8601
    },
    {
      "epoch": 0.26424599883267286,
      "grad_norm": 0.4659448266029358,
      "learning_rate": 1.916788038260868e-05,
      "loss": 0.6114,
      "step": 8602
    },
    {
      "epoch": 0.26427671796762203,
      "grad_norm": 0.3291952311992645,
      "learning_rate": 1.9167687363438535e-05,
      "loss": 0.6451,
      "step": 8603
    },
    {
      "epoch": 0.2643074371025712,
      "grad_norm": 0.3181070387363434,
      "learning_rate": 1.9167494322856616e-05,
      "loss": 0.6196,
      "step": 8604
    },
    {
      "epoch": 0.2643381562375203,
      "grad_norm": 0.3475816547870636,
      "learning_rate": 1.916730126086337e-05,
      "loss": 0.5272,
      "step": 8605
    },
    {
      "epoch": 0.2643688753724695,
      "grad_norm": 0.3757767677307129,
      "learning_rate": 1.9167108177459254e-05,
      "loss": 0.618,
      "step": 8606
    },
    {
      "epoch": 0.2643995945074187,
      "grad_norm": 0.31085532903671265,
      "learning_rate": 1.916691507264472e-05,
      "loss": 0.5276,
      "step": 8607
    },
    {
      "epoch": 0.26443031364236785,
      "grad_norm": 0.36124253273010254,
      "learning_rate": 1.916672194642021e-05,
      "loss": 0.6385,
      "step": 8608
    },
    {
      "epoch": 0.264461032777317,
      "grad_norm": 13.547745704650879,
      "learning_rate": 1.9166528798786184e-05,
      "loss": 1.0145,
      "step": 8609
    },
    {
      "epoch": 0.26449175191226615,
      "grad_norm": 0.3517603874206543,
      "learning_rate": 1.9166335629743093e-05,
      "loss": 0.6897,
      "step": 8610
    },
    {
      "epoch": 0.2645224710472153,
      "grad_norm": 0.3518737256526947,
      "learning_rate": 1.916614243929138e-05,
      "loss": 0.5395,
      "step": 8611
    },
    {
      "epoch": 0.26455319018216444,
      "grad_norm": 0.36003583669662476,
      "learning_rate": 1.91659492274315e-05,
      "loss": 0.5464,
      "step": 8612
    },
    {
      "epoch": 0.2645839093171136,
      "grad_norm": 0.34680846333503723,
      "learning_rate": 1.9165755994163907e-05,
      "loss": 0.5929,
      "step": 8613
    },
    {
      "epoch": 0.2646146284520628,
      "grad_norm": 0.3636135458946228,
      "learning_rate": 1.9165562739489054e-05,
      "loss": 0.5978,
      "step": 8614
    },
    {
      "epoch": 0.26464534758701197,
      "grad_norm": 0.35425472259521484,
      "learning_rate": 1.9165369463407385e-05,
      "loss": 0.5357,
      "step": 8615
    },
    {
      "epoch": 0.2646760667219611,
      "grad_norm": 0.3702721893787384,
      "learning_rate": 1.9165176165919357e-05,
      "loss": 0.5563,
      "step": 8616
    },
    {
      "epoch": 0.26470678585691026,
      "grad_norm": 0.3871748745441437,
      "learning_rate": 1.9164982847025423e-05,
      "loss": 0.6642,
      "step": 8617
    },
    {
      "epoch": 0.26473750499185944,
      "grad_norm": 0.8477364778518677,
      "learning_rate": 1.9164789506726026e-05,
      "loss": 0.6267,
      "step": 8618
    },
    {
      "epoch": 0.2647682241268086,
      "grad_norm": 0.5241139531135559,
      "learning_rate": 1.9164596145021627e-05,
      "loss": 0.6858,
      "step": 8619
    },
    {
      "epoch": 0.26479894326175774,
      "grad_norm": 0.34346094727516174,
      "learning_rate": 1.9164402761912673e-05,
      "loss": 0.5613,
      "step": 8620
    },
    {
      "epoch": 0.2648296623967069,
      "grad_norm": 0.3765224516391754,
      "learning_rate": 1.9164209357399616e-05,
      "loss": 0.6356,
      "step": 8621
    },
    {
      "epoch": 0.2648603815316561,
      "grad_norm": 0.3233392536640167,
      "learning_rate": 1.9164015931482907e-05,
      "loss": 0.5384,
      "step": 8622
    },
    {
      "epoch": 0.2648911006666052,
      "grad_norm": 0.3689977824687958,
      "learning_rate": 1.9163822484163e-05,
      "loss": 0.5265,
      "step": 8623
    },
    {
      "epoch": 0.2649218198015544,
      "grad_norm": 0.33127060532569885,
      "learning_rate": 1.9163629015440347e-05,
      "loss": 0.5729,
      "step": 8624
    },
    {
      "epoch": 0.26495253893650356,
      "grad_norm": 0.34674641489982605,
      "learning_rate": 1.9163435525315393e-05,
      "loss": 0.586,
      "step": 8625
    },
    {
      "epoch": 0.26498325807145273,
      "grad_norm": 0.3240914046764374,
      "learning_rate": 1.91632420137886e-05,
      "loss": 0.6215,
      "step": 8626
    },
    {
      "epoch": 0.26501397720640185,
      "grad_norm": 0.33640554547309875,
      "learning_rate": 1.916304848086041e-05,
      "loss": 0.638,
      "step": 8627
    },
    {
      "epoch": 0.265044696341351,
      "grad_norm": 0.33202335238456726,
      "learning_rate": 1.916285492653129e-05,
      "loss": 0.5963,
      "step": 8628
    },
    {
      "epoch": 0.2650754154763002,
      "grad_norm": 0.4308584928512573,
      "learning_rate": 1.9162661350801675e-05,
      "loss": 0.5473,
      "step": 8629
    },
    {
      "epoch": 0.2651061346112493,
      "grad_norm": 0.3613283634185791,
      "learning_rate": 1.916246775367203e-05,
      "loss": 0.6451,
      "step": 8630
    },
    {
      "epoch": 0.2651368537461985,
      "grad_norm": 0.4001268148422241,
      "learning_rate": 1.9162274135142796e-05,
      "loss": 0.5917,
      "step": 8631
    },
    {
      "epoch": 0.2651675728811477,
      "grad_norm": 0.34868407249450684,
      "learning_rate": 1.9162080495214434e-05,
      "loss": 0.6391,
      "step": 8632
    },
    {
      "epoch": 0.26519829201609685,
      "grad_norm": 0.36719056963920593,
      "learning_rate": 1.916188683388739e-05,
      "loss": 0.6264,
      "step": 8633
    },
    {
      "epoch": 0.26522901115104597,
      "grad_norm": 0.43466565012931824,
      "learning_rate": 1.916169315116212e-05,
      "loss": 0.6162,
      "step": 8634
    },
    {
      "epoch": 0.26525973028599514,
      "grad_norm": 0.34804072976112366,
      "learning_rate": 1.916149944703908e-05,
      "loss": 0.6357,
      "step": 8635
    },
    {
      "epoch": 0.2652904494209443,
      "grad_norm": 0.36143893003463745,
      "learning_rate": 1.9161305721518713e-05,
      "loss": 0.6028,
      "step": 8636
    },
    {
      "epoch": 0.26532116855589344,
      "grad_norm": 0.31955575942993164,
      "learning_rate": 1.916111197460148e-05,
      "loss": 0.5466,
      "step": 8637
    },
    {
      "epoch": 0.2653518876908426,
      "grad_norm": 0.40474921464920044,
      "learning_rate": 1.916091820628783e-05,
      "loss": 0.5703,
      "step": 8638
    },
    {
      "epoch": 0.2653826068257918,
      "grad_norm": 0.31477952003479004,
      "learning_rate": 1.9160724416578213e-05,
      "loss": 0.6447,
      "step": 8639
    },
    {
      "epoch": 0.26541332596074096,
      "grad_norm": 0.4715936779975891,
      "learning_rate": 1.916053060547309e-05,
      "loss": 0.5215,
      "step": 8640
    },
    {
      "epoch": 0.2654440450956901,
      "grad_norm": 0.33720293641090393,
      "learning_rate": 1.91603367729729e-05,
      "loss": 0.6249,
      "step": 8641
    },
    {
      "epoch": 0.26547476423063926,
      "grad_norm": 0.34082359075546265,
      "learning_rate": 1.9160142919078112e-05,
      "loss": 0.5642,
      "step": 8642
    },
    {
      "epoch": 0.26550548336558843,
      "grad_norm": 0.36827898025512695,
      "learning_rate": 1.9159949043789167e-05,
      "loss": 0.6115,
      "step": 8643
    },
    {
      "epoch": 0.2655362025005376,
      "grad_norm": 0.3330440819263458,
      "learning_rate": 1.915975514710652e-05,
      "loss": 0.5753,
      "step": 8644
    },
    {
      "epoch": 0.26556692163548673,
      "grad_norm": 0.320085734128952,
      "learning_rate": 1.9159561229030626e-05,
      "loss": 0.6472,
      "step": 8645
    },
    {
      "epoch": 0.2655976407704359,
      "grad_norm": 0.3217692971229553,
      "learning_rate": 1.9159367289561938e-05,
      "loss": 0.4955,
      "step": 8646
    },
    {
      "epoch": 0.2656283599053851,
      "grad_norm": 0.3983650207519531,
      "learning_rate": 1.9159173328700907e-05,
      "loss": 0.5973,
      "step": 8647
    },
    {
      "epoch": 0.2656590790403342,
      "grad_norm": 0.3807363510131836,
      "learning_rate": 1.9158979346447988e-05,
      "loss": 0.6441,
      "step": 8648
    },
    {
      "epoch": 0.2656897981752834,
      "grad_norm": 0.3113970458507538,
      "learning_rate": 1.9158785342803628e-05,
      "loss": 0.5598,
      "step": 8649
    },
    {
      "epoch": 0.26572051731023255,
      "grad_norm": 0.35806983709335327,
      "learning_rate": 1.9158591317768295e-05,
      "loss": 0.6413,
      "step": 8650
    },
    {
      "epoch": 0.2657512364451817,
      "grad_norm": 0.36145317554473877,
      "learning_rate": 1.9158397271342425e-05,
      "loss": 0.6124,
      "step": 8651
    },
    {
      "epoch": 0.26578195558013085,
      "grad_norm": 0.35813474655151367,
      "learning_rate": 1.915820320352648e-05,
      "loss": 0.5748,
      "step": 8652
    },
    {
      "epoch": 0.26581267471508,
      "grad_norm": 0.33496809005737305,
      "learning_rate": 1.9158009114320913e-05,
      "loss": 0.5329,
      "step": 8653
    },
    {
      "epoch": 0.2658433938500292,
      "grad_norm": 0.31693416833877563,
      "learning_rate": 1.9157815003726175e-05,
      "loss": 0.5249,
      "step": 8654
    },
    {
      "epoch": 0.2658741129849783,
      "grad_norm": 0.32396790385246277,
      "learning_rate": 1.915762087174272e-05,
      "loss": 0.5328,
      "step": 8655
    },
    {
      "epoch": 0.2659048321199275,
      "grad_norm": 0.34105533361434937,
      "learning_rate": 1.9157426718371002e-05,
      "loss": 0.5669,
      "step": 8656
    },
    {
      "epoch": 0.26593555125487667,
      "grad_norm": 0.33394908905029297,
      "learning_rate": 1.9157232543611476e-05,
      "loss": 0.6016,
      "step": 8657
    },
    {
      "epoch": 0.26596627038982584,
      "grad_norm": 0.45857465267181396,
      "learning_rate": 1.9157038347464594e-05,
      "loss": 0.6617,
      "step": 8658
    },
    {
      "epoch": 0.26599698952477496,
      "grad_norm": 0.3963107168674469,
      "learning_rate": 1.915684412993081e-05,
      "loss": 0.6011,
      "step": 8659
    },
    {
      "epoch": 0.26602770865972414,
      "grad_norm": 0.352446973323822,
      "learning_rate": 1.9156649891010572e-05,
      "loss": 0.5923,
      "step": 8660
    },
    {
      "epoch": 0.2660584277946733,
      "grad_norm": 0.3275332450866699,
      "learning_rate": 1.9156455630704343e-05,
      "loss": 0.539,
      "step": 8661
    },
    {
      "epoch": 0.2660891469296225,
      "grad_norm": 0.3456118702888489,
      "learning_rate": 1.9156261349012572e-05,
      "loss": 0.5791,
      "step": 8662
    },
    {
      "epoch": 0.2661198660645716,
      "grad_norm": 0.3373566269874573,
      "learning_rate": 1.9156067045935712e-05,
      "loss": 0.5302,
      "step": 8663
    },
    {
      "epoch": 0.2661505851995208,
      "grad_norm": 0.36883556842803955,
      "learning_rate": 1.915587272147422e-05,
      "loss": 0.6227,
      "step": 8664
    },
    {
      "epoch": 0.26618130433446996,
      "grad_norm": 0.3588220477104187,
      "learning_rate": 1.9155678375628544e-05,
      "loss": 0.6248,
      "step": 8665
    },
    {
      "epoch": 0.2662120234694191,
      "grad_norm": 0.3369339406490326,
      "learning_rate": 1.9155484008399144e-05,
      "loss": 0.6689,
      "step": 8666
    },
    {
      "epoch": 0.26624274260436825,
      "grad_norm": 0.3390048146247864,
      "learning_rate": 1.9155289619786472e-05,
      "loss": 0.5686,
      "step": 8667
    },
    {
      "epoch": 0.26627346173931743,
      "grad_norm": 0.34848764538764954,
      "learning_rate": 1.915509520979098e-05,
      "loss": 0.6851,
      "step": 8668
    },
    {
      "epoch": 0.2663041808742666,
      "grad_norm": 0.3103259205818176,
      "learning_rate": 1.915490077841313e-05,
      "loss": 0.6477,
      "step": 8669
    },
    {
      "epoch": 0.2663349000092157,
      "grad_norm": 0.3364870548248291,
      "learning_rate": 1.915470632565336e-05,
      "loss": 0.5323,
      "step": 8670
    },
    {
      "epoch": 0.2663656191441649,
      "grad_norm": 0.34060412645339966,
      "learning_rate": 1.915451185151214e-05,
      "loss": 0.6242,
      "step": 8671
    },
    {
      "epoch": 0.2663963382791141,
      "grad_norm": 0.374696284532547,
      "learning_rate": 1.915431735598992e-05,
      "loss": 0.6195,
      "step": 8672
    },
    {
      "epoch": 0.2664270574140632,
      "grad_norm": 0.389600932598114,
      "learning_rate": 1.915412283908715e-05,
      "loss": 0.6145,
      "step": 8673
    },
    {
      "epoch": 0.26645777654901237,
      "grad_norm": 0.32126542925834656,
      "learning_rate": 1.9153928300804286e-05,
      "loss": 0.6145,
      "step": 8674
    },
    {
      "epoch": 0.26648849568396155,
      "grad_norm": 0.33721697330474854,
      "learning_rate": 1.9153733741141784e-05,
      "loss": 0.6453,
      "step": 8675
    },
    {
      "epoch": 0.2665192148189107,
      "grad_norm": 0.3183304965496063,
      "learning_rate": 1.9153539160100095e-05,
      "loss": 0.5655,
      "step": 8676
    },
    {
      "epoch": 0.26654993395385984,
      "grad_norm": 0.3261716961860657,
      "learning_rate": 1.915334455767968e-05,
      "loss": 0.5648,
      "step": 8677
    },
    {
      "epoch": 0.266580653088809,
      "grad_norm": 0.3437630236148834,
      "learning_rate": 1.915314993388099e-05,
      "loss": 0.6488,
      "step": 8678
    },
    {
      "epoch": 0.2666113722237582,
      "grad_norm": 0.3338691294193268,
      "learning_rate": 1.9152955288704476e-05,
      "loss": 0.5529,
      "step": 8679
    },
    {
      "epoch": 0.2666420913587073,
      "grad_norm": 0.3944566249847412,
      "learning_rate": 1.9152760622150593e-05,
      "loss": 0.6572,
      "step": 8680
    },
    {
      "epoch": 0.2666728104936565,
      "grad_norm": 0.31331443786621094,
      "learning_rate": 1.9152565934219805e-05,
      "loss": 0.5249,
      "step": 8681
    },
    {
      "epoch": 0.26670352962860566,
      "grad_norm": 0.34602057933807373,
      "learning_rate": 1.9152371224912557e-05,
      "loss": 0.5719,
      "step": 8682
    },
    {
      "epoch": 0.26673424876355484,
      "grad_norm": 0.3866533637046814,
      "learning_rate": 1.9152176494229305e-05,
      "loss": 0.6278,
      "step": 8683
    },
    {
      "epoch": 0.26676496789850396,
      "grad_norm": 0.35636788606643677,
      "learning_rate": 1.915198174217051e-05,
      "loss": 0.5574,
      "step": 8684
    },
    {
      "epoch": 0.26679568703345313,
      "grad_norm": 0.3229437470436096,
      "learning_rate": 1.915178696873662e-05,
      "loss": 0.5262,
      "step": 8685
    },
    {
      "epoch": 0.2668264061684023,
      "grad_norm": 0.43372148275375366,
      "learning_rate": 1.915159217392809e-05,
      "loss": 0.6515,
      "step": 8686
    },
    {
      "epoch": 0.2668571253033515,
      "grad_norm": 0.3932594954967499,
      "learning_rate": 1.915139735774538e-05,
      "loss": 0.6472,
      "step": 8687
    },
    {
      "epoch": 0.2668878444383006,
      "grad_norm": 0.3896244466304779,
      "learning_rate": 1.9151202520188943e-05,
      "loss": 0.5888,
      "step": 8688
    },
    {
      "epoch": 0.2669185635732498,
      "grad_norm": 0.31793564558029175,
      "learning_rate": 1.915100766125923e-05,
      "loss": 0.5495,
      "step": 8689
    },
    {
      "epoch": 0.26694928270819895,
      "grad_norm": 0.3580148220062256,
      "learning_rate": 1.9150812780956706e-05,
      "loss": 0.5469,
      "step": 8690
    },
    {
      "epoch": 0.2669800018431481,
      "grad_norm": 0.7980449199676514,
      "learning_rate": 1.915061787928181e-05,
      "loss": 0.7187,
      "step": 8691
    },
    {
      "epoch": 0.26701072097809725,
      "grad_norm": 0.393425315618515,
      "learning_rate": 1.9150422956235016e-05,
      "loss": 0.5972,
      "step": 8692
    },
    {
      "epoch": 0.2670414401130464,
      "grad_norm": 0.2895285189151764,
      "learning_rate": 1.915022801181677e-05,
      "loss": 0.5436,
      "step": 8693
    },
    {
      "epoch": 0.2670721592479956,
      "grad_norm": 0.35438692569732666,
      "learning_rate": 1.915003304602752e-05,
      "loss": 0.5916,
      "step": 8694
    },
    {
      "epoch": 0.2671028783829447,
      "grad_norm": 0.32918208837509155,
      "learning_rate": 1.9149838058867734e-05,
      "loss": 0.6358,
      "step": 8695
    },
    {
      "epoch": 0.2671335975178939,
      "grad_norm": 0.3524302840232849,
      "learning_rate": 1.9149643050337858e-05,
      "loss": 0.6119,
      "step": 8696
    },
    {
      "epoch": 0.26716431665284307,
      "grad_norm": 0.3242788314819336,
      "learning_rate": 1.9149448020438357e-05,
      "loss": 0.5947,
      "step": 8697
    },
    {
      "epoch": 0.2671950357877922,
      "grad_norm": 0.3229874074459076,
      "learning_rate": 1.914925296916968e-05,
      "loss": 0.6013,
      "step": 8698
    },
    {
      "epoch": 0.26722575492274137,
      "grad_norm": 0.354824423789978,
      "learning_rate": 1.914905789653228e-05,
      "loss": 0.6298,
      "step": 8699
    },
    {
      "epoch": 0.26725647405769054,
      "grad_norm": 0.36988961696624756,
      "learning_rate": 1.914886280252662e-05,
      "loss": 0.5598,
      "step": 8700
    },
    {
      "epoch": 0.2672871931926397,
      "grad_norm": 0.34439322352409363,
      "learning_rate": 1.9148667687153152e-05,
      "loss": 0.5418,
      "step": 8701
    },
    {
      "epoch": 0.26731791232758884,
      "grad_norm": 0.3510277569293976,
      "learning_rate": 1.914847255041233e-05,
      "loss": 0.6518,
      "step": 8702
    },
    {
      "epoch": 0.267348631462538,
      "grad_norm": 0.34336963295936584,
      "learning_rate": 1.9148277392304612e-05,
      "loss": 0.5847,
      "step": 8703
    },
    {
      "epoch": 0.2673793505974872,
      "grad_norm": 0.32249927520751953,
      "learning_rate": 1.9148082212830453e-05,
      "loss": 0.5416,
      "step": 8704
    },
    {
      "epoch": 0.26741006973243636,
      "grad_norm": 0.41251808404922485,
      "learning_rate": 1.9147887011990308e-05,
      "loss": 0.5336,
      "step": 8705
    },
    {
      "epoch": 0.2674407888673855,
      "grad_norm": 0.33706411719322205,
      "learning_rate": 1.9147691789784635e-05,
      "loss": 0.5467,
      "step": 8706
    },
    {
      "epoch": 0.26747150800233466,
      "grad_norm": 0.3492804169654846,
      "learning_rate": 1.914749654621389e-05,
      "loss": 0.6012,
      "step": 8707
    },
    {
      "epoch": 0.26750222713728383,
      "grad_norm": 0.3020542860031128,
      "learning_rate": 1.914730128127853e-05,
      "loss": 0.4564,
      "step": 8708
    },
    {
      "epoch": 0.26753294627223295,
      "grad_norm": 0.3618064522743225,
      "learning_rate": 1.9147105994979004e-05,
      "loss": 0.5884,
      "step": 8709
    },
    {
      "epoch": 0.2675636654071821,
      "grad_norm": 0.38659313321113586,
      "learning_rate": 1.9146910687315773e-05,
      "loss": 0.5719,
      "step": 8710
    },
    {
      "epoch": 0.2675943845421313,
      "grad_norm": 0.33900532126426697,
      "learning_rate": 1.9146715358289297e-05,
      "loss": 0.5532,
      "step": 8711
    },
    {
      "epoch": 0.2676251036770805,
      "grad_norm": 0.3218209743499756,
      "learning_rate": 1.9146520007900027e-05,
      "loss": 0.6291,
      "step": 8712
    },
    {
      "epoch": 0.2676558228120296,
      "grad_norm": 0.36449605226516724,
      "learning_rate": 1.914632463614842e-05,
      "loss": 0.5569,
      "step": 8713
    },
    {
      "epoch": 0.2676865419469788,
      "grad_norm": 0.376830518245697,
      "learning_rate": 1.9146129243034934e-05,
      "loss": 0.6303,
      "step": 8714
    },
    {
      "epoch": 0.26771726108192795,
      "grad_norm": 0.33445143699645996,
      "learning_rate": 1.9145933828560025e-05,
      "loss": 0.5689,
      "step": 8715
    },
    {
      "epoch": 0.26774798021687707,
      "grad_norm": 0.30119338631629944,
      "learning_rate": 1.914573839272415e-05,
      "loss": 0.5377,
      "step": 8716
    },
    {
      "epoch": 0.26777869935182624,
      "grad_norm": 0.3272824287414551,
      "learning_rate": 1.914554293552776e-05,
      "loss": 0.5278,
      "step": 8717
    },
    {
      "epoch": 0.2678094184867754,
      "grad_norm": 0.36979183554649353,
      "learning_rate": 1.914534745697132e-05,
      "loss": 0.6396,
      "step": 8718
    },
    {
      "epoch": 0.2678401376217246,
      "grad_norm": 0.44983625411987305,
      "learning_rate": 1.914515195705528e-05,
      "loss": 0.4552,
      "step": 8719
    },
    {
      "epoch": 0.2678708567566737,
      "grad_norm": 0.35280346870422363,
      "learning_rate": 1.9144956435780098e-05,
      "loss": 0.5026,
      "step": 8720
    },
    {
      "epoch": 0.2679015758916229,
      "grad_norm": 0.3629494309425354,
      "learning_rate": 1.9144760893146235e-05,
      "loss": 0.6105,
      "step": 8721
    },
    {
      "epoch": 0.26793229502657206,
      "grad_norm": 0.3300478756427765,
      "learning_rate": 1.914456532915414e-05,
      "loss": 0.5622,
      "step": 8722
    },
    {
      "epoch": 0.2679630141615212,
      "grad_norm": 0.36566174030303955,
      "learning_rate": 1.9144369743804277e-05,
      "loss": 0.5614,
      "step": 8723
    },
    {
      "epoch": 0.26799373329647036,
      "grad_norm": 0.4073520600795746,
      "learning_rate": 1.91441741370971e-05,
      "loss": 0.5545,
      "step": 8724
    },
    {
      "epoch": 0.26802445243141954,
      "grad_norm": 0.33625128865242004,
      "learning_rate": 1.9143978509033064e-05,
      "loss": 0.5344,
      "step": 8725
    },
    {
      "epoch": 0.2680551715663687,
      "grad_norm": 0.37191861867904663,
      "learning_rate": 1.914378285961263e-05,
      "loss": 0.6352,
      "step": 8726
    },
    {
      "epoch": 0.26808589070131783,
      "grad_norm": 0.38028866052627563,
      "learning_rate": 1.9143587188836246e-05,
      "loss": 0.6224,
      "step": 8727
    },
    {
      "epoch": 0.268116609836267,
      "grad_norm": 0.3240302801132202,
      "learning_rate": 1.9143391496704385e-05,
      "loss": 0.5062,
      "step": 8728
    },
    {
      "epoch": 0.2681473289712162,
      "grad_norm": 0.41265347599983215,
      "learning_rate": 1.9143195783217488e-05,
      "loss": 0.6219,
      "step": 8729
    },
    {
      "epoch": 0.26817804810616536,
      "grad_norm": 0.40836480259895325,
      "learning_rate": 1.914300004837602e-05,
      "loss": 0.5122,
      "step": 8730
    },
    {
      "epoch": 0.2682087672411145,
      "grad_norm": 0.3246540129184723,
      "learning_rate": 1.9142804292180437e-05,
      "loss": 0.5901,
      "step": 8731
    },
    {
      "epoch": 0.26823948637606365,
      "grad_norm": 0.3361242711544037,
      "learning_rate": 1.91426085146312e-05,
      "loss": 0.5755,
      "step": 8732
    },
    {
      "epoch": 0.2682702055110128,
      "grad_norm": 0.354328453540802,
      "learning_rate": 1.9142412715728757e-05,
      "loss": 0.5808,
      "step": 8733
    },
    {
      "epoch": 0.26830092464596195,
      "grad_norm": 0.42316415905952454,
      "learning_rate": 1.914221689547357e-05,
      "loss": 0.6059,
      "step": 8734
    },
    {
      "epoch": 0.2683316437809111,
      "grad_norm": 0.5421087145805359,
      "learning_rate": 1.9142021053866103e-05,
      "loss": 0.6387,
      "step": 8735
    },
    {
      "epoch": 0.2683623629158603,
      "grad_norm": 0.34757357835769653,
      "learning_rate": 1.91418251909068e-05,
      "loss": 0.5693,
      "step": 8736
    },
    {
      "epoch": 0.2683930820508095,
      "grad_norm": 0.34967756271362305,
      "learning_rate": 1.914162930659613e-05,
      "loss": 0.6068,
      "step": 8737
    },
    {
      "epoch": 0.2684238011857586,
      "grad_norm": 0.3463193476200104,
      "learning_rate": 1.9141433400934544e-05,
      "loss": 0.6253,
      "step": 8738
    },
    {
      "epoch": 0.26845452032070777,
      "grad_norm": 0.32746225595474243,
      "learning_rate": 1.9141237473922507e-05,
      "loss": 0.5195,
      "step": 8739
    },
    {
      "epoch": 0.26848523945565694,
      "grad_norm": 0.33240628242492676,
      "learning_rate": 1.9141041525560468e-05,
      "loss": 0.6585,
      "step": 8740
    },
    {
      "epoch": 0.26851595859060606,
      "grad_norm": 0.3499237298965454,
      "learning_rate": 1.914084555584889e-05,
      "loss": 0.6428,
      "step": 8741
    },
    {
      "epoch": 0.26854667772555524,
      "grad_norm": 0.39372339844703674,
      "learning_rate": 1.9140649564788225e-05,
      "loss": 0.5839,
      "step": 8742
    },
    {
      "epoch": 0.2685773968605044,
      "grad_norm": 0.5834788680076599,
      "learning_rate": 1.9140453552378935e-05,
      "loss": 0.6261,
      "step": 8743
    },
    {
      "epoch": 0.2686081159954536,
      "grad_norm": 0.3498360216617584,
      "learning_rate": 1.914025751862148e-05,
      "loss": 0.5573,
      "step": 8744
    },
    {
      "epoch": 0.2686388351304027,
      "grad_norm": 0.3862430453300476,
      "learning_rate": 1.9140061463516314e-05,
      "loss": 0.5714,
      "step": 8745
    },
    {
      "epoch": 0.2686695542653519,
      "grad_norm": 0.34388431906700134,
      "learning_rate": 1.91398653870639e-05,
      "loss": 0.6122,
      "step": 8746
    },
    {
      "epoch": 0.26870027340030106,
      "grad_norm": 0.3377215564250946,
      "learning_rate": 1.9139669289264687e-05,
      "loss": 0.5307,
      "step": 8747
    },
    {
      "epoch": 0.26873099253525023,
      "grad_norm": 0.33628585934638977,
      "learning_rate": 1.913947317011914e-05,
      "loss": 0.5866,
      "step": 8748
    },
    {
      "epoch": 0.26876171167019935,
      "grad_norm": 0.5191262364387512,
      "learning_rate": 1.9139277029627714e-05,
      "loss": 0.5521,
      "step": 8749
    },
    {
      "epoch": 0.26879243080514853,
      "grad_norm": 0.3837521970272064,
      "learning_rate": 1.913908086779087e-05,
      "loss": 0.5304,
      "step": 8750
    },
    {
      "epoch": 0.2688231499400977,
      "grad_norm": 0.3514169156551361,
      "learning_rate": 1.9138884684609064e-05,
      "loss": 0.6399,
      "step": 8751
    },
    {
      "epoch": 0.2688538690750468,
      "grad_norm": 0.3408939838409424,
      "learning_rate": 1.913868848008275e-05,
      "loss": 0.6509,
      "step": 8752
    },
    {
      "epoch": 0.268884588209996,
      "grad_norm": 0.3469868004322052,
      "learning_rate": 1.9138492254212397e-05,
      "loss": 0.6015,
      "step": 8753
    },
    {
      "epoch": 0.2689153073449452,
      "grad_norm": 0.3380759358406067,
      "learning_rate": 1.9138296006998452e-05,
      "loss": 0.55,
      "step": 8754
    },
    {
      "epoch": 0.26894602647989435,
      "grad_norm": 0.5519193410873413,
      "learning_rate": 1.913809973844138e-05,
      "loss": 0.6821,
      "step": 8755
    },
    {
      "epoch": 0.26897674561484347,
      "grad_norm": 0.34753289818763733,
      "learning_rate": 1.9137903448541642e-05,
      "loss": 0.5425,
      "step": 8756
    },
    {
      "epoch": 0.26900746474979265,
      "grad_norm": 0.35978060960769653,
      "learning_rate": 1.913770713729969e-05,
      "loss": 0.5108,
      "step": 8757
    },
    {
      "epoch": 0.2690381838847418,
      "grad_norm": 0.33711108565330505,
      "learning_rate": 1.9137510804715983e-05,
      "loss": 0.5946,
      "step": 8758
    },
    {
      "epoch": 0.26906890301969094,
      "grad_norm": 0.31975722312927246,
      "learning_rate": 1.9137314450790984e-05,
      "loss": 0.5946,
      "step": 8759
    },
    {
      "epoch": 0.2690996221546401,
      "grad_norm": 0.32161158323287964,
      "learning_rate": 1.9137118075525147e-05,
      "loss": 0.5021,
      "step": 8760
    },
    {
      "epoch": 0.2691303412895893,
      "grad_norm": 0.3427479863166809,
      "learning_rate": 1.913692167891893e-05,
      "loss": 0.5933,
      "step": 8761
    },
    {
      "epoch": 0.26916106042453847,
      "grad_norm": 0.34702685475349426,
      "learning_rate": 1.91367252609728e-05,
      "loss": 0.5635,
      "step": 8762
    },
    {
      "epoch": 0.2691917795594876,
      "grad_norm": 0.37181591987609863,
      "learning_rate": 1.913652882168721e-05,
      "loss": 0.5859,
      "step": 8763
    },
    {
      "epoch": 0.26922249869443676,
      "grad_norm": 0.4100138545036316,
      "learning_rate": 1.9136332361062613e-05,
      "loss": 0.5317,
      "step": 8764
    },
    {
      "epoch": 0.26925321782938594,
      "grad_norm": 0.32772231101989746,
      "learning_rate": 1.9136135879099477e-05,
      "loss": 0.5491,
      "step": 8765
    },
    {
      "epoch": 0.26928393696433506,
      "grad_norm": 0.304598331451416,
      "learning_rate": 1.9135939375798257e-05,
      "loss": 0.5681,
      "step": 8766
    },
    {
      "epoch": 0.26931465609928423,
      "grad_norm": 0.34933724999427795,
      "learning_rate": 1.9135742851159413e-05,
      "loss": 0.5842,
      "step": 8767
    },
    {
      "epoch": 0.2693453752342334,
      "grad_norm": 0.34307432174682617,
      "learning_rate": 1.9135546305183402e-05,
      "loss": 0.5691,
      "step": 8768
    },
    {
      "epoch": 0.2693760943691826,
      "grad_norm": 0.3506833612918854,
      "learning_rate": 1.913534973787069e-05,
      "loss": 0.6673,
      "step": 8769
    },
    {
      "epoch": 0.2694068135041317,
      "grad_norm": 0.3275294005870819,
      "learning_rate": 1.9135153149221727e-05,
      "loss": 0.618,
      "step": 8770
    },
    {
      "epoch": 0.2694375326390809,
      "grad_norm": 0.36960718035697937,
      "learning_rate": 1.913495653923697e-05,
      "loss": 0.5089,
      "step": 8771
    },
    {
      "epoch": 0.26946825177403005,
      "grad_norm": 0.35343295335769653,
      "learning_rate": 1.9134759907916893e-05,
      "loss": 0.6565,
      "step": 8772
    },
    {
      "epoch": 0.26949897090897923,
      "grad_norm": 0.3468801975250244,
      "learning_rate": 1.9134563255261944e-05,
      "loss": 0.5472,
      "step": 8773
    },
    {
      "epoch": 0.26952969004392835,
      "grad_norm": 0.332366943359375,
      "learning_rate": 1.9134366581272587e-05,
      "loss": 0.5642,
      "step": 8774
    },
    {
      "epoch": 0.2695604091788775,
      "grad_norm": 0.3387770652770996,
      "learning_rate": 1.9134169885949272e-05,
      "loss": 0.4935,
      "step": 8775
    },
    {
      "epoch": 0.2695911283138267,
      "grad_norm": 0.32291948795318604,
      "learning_rate": 1.9133973169292467e-05,
      "loss": 0.5737,
      "step": 8776
    },
    {
      "epoch": 0.2696218474487758,
      "grad_norm": 0.3799710273742676,
      "learning_rate": 1.9133776431302635e-05,
      "loss": 0.6235,
      "step": 8777
    },
    {
      "epoch": 0.269652566583725,
      "grad_norm": 0.3026837706565857,
      "learning_rate": 1.9133579671980228e-05,
      "loss": 0.5733,
      "step": 8778
    },
    {
      "epoch": 0.26968328571867417,
      "grad_norm": 0.36235255002975464,
      "learning_rate": 1.9133382891325706e-05,
      "loss": 0.6167,
      "step": 8779
    },
    {
      "epoch": 0.26971400485362335,
      "grad_norm": 0.33729901909828186,
      "learning_rate": 1.913318608933953e-05,
      "loss": 0.6028,
      "step": 8780
    },
    {
      "epoch": 0.26974472398857247,
      "grad_norm": 0.3713393807411194,
      "learning_rate": 1.913298926602216e-05,
      "loss": 0.6001,
      "step": 8781
    },
    {
      "epoch": 0.26977544312352164,
      "grad_norm": 0.3227938413619995,
      "learning_rate": 1.913279242137406e-05,
      "loss": 0.6855,
      "step": 8782
    },
    {
      "epoch": 0.2698061622584708,
      "grad_norm": 0.3470472991466522,
      "learning_rate": 1.913259555539568e-05,
      "loss": 0.622,
      "step": 8783
    },
    {
      "epoch": 0.26983688139341994,
      "grad_norm": 0.35053467750549316,
      "learning_rate": 1.9132398668087487e-05,
      "loss": 0.5284,
      "step": 8784
    },
    {
      "epoch": 0.2698676005283691,
      "grad_norm": 0.3765382468700409,
      "learning_rate": 1.913220175944994e-05,
      "loss": 0.6632,
      "step": 8785
    },
    {
      "epoch": 0.2698983196633183,
      "grad_norm": 0.3320727050304413,
      "learning_rate": 1.91320048294835e-05,
      "loss": 0.6291,
      "step": 8786
    },
    {
      "epoch": 0.26992903879826746,
      "grad_norm": 0.34642383456230164,
      "learning_rate": 1.913180787818862e-05,
      "loss": 0.6721,
      "step": 8787
    },
    {
      "epoch": 0.2699597579332166,
      "grad_norm": 0.31732189655303955,
      "learning_rate": 1.913161090556577e-05,
      "loss": 0.5667,
      "step": 8788
    },
    {
      "epoch": 0.26999047706816576,
      "grad_norm": 0.3027111291885376,
      "learning_rate": 1.91314139116154e-05,
      "loss": 0.6047,
      "step": 8789
    },
    {
      "epoch": 0.27002119620311493,
      "grad_norm": 0.38515254855155945,
      "learning_rate": 1.9131216896337977e-05,
      "loss": 0.4883,
      "step": 8790
    },
    {
      "epoch": 0.27005191533806405,
      "grad_norm": 0.3503424823284149,
      "learning_rate": 1.913101985973396e-05,
      "loss": 0.5738,
      "step": 8791
    },
    {
      "epoch": 0.27008263447301323,
      "grad_norm": 0.4063030481338501,
      "learning_rate": 1.913082280180381e-05,
      "loss": 0.5803,
      "step": 8792
    },
    {
      "epoch": 0.2701133536079624,
      "grad_norm": 0.3719574511051178,
      "learning_rate": 1.9130625722547982e-05,
      "loss": 0.5778,
      "step": 8793
    },
    {
      "epoch": 0.2701440727429116,
      "grad_norm": 0.31902459263801575,
      "learning_rate": 1.913042862196694e-05,
      "loss": 0.573,
      "step": 8794
    },
    {
      "epoch": 0.2701747918778607,
      "grad_norm": 0.36431774497032166,
      "learning_rate": 1.9130231500061147e-05,
      "loss": 0.5616,
      "step": 8795
    },
    {
      "epoch": 0.2702055110128099,
      "grad_norm": 0.35929057002067566,
      "learning_rate": 1.9130034356831058e-05,
      "loss": 0.5473,
      "step": 8796
    },
    {
      "epoch": 0.27023623014775905,
      "grad_norm": 0.3804222345352173,
      "learning_rate": 1.9129837192277142e-05,
      "loss": 0.5391,
      "step": 8797
    },
    {
      "epoch": 0.2702669492827082,
      "grad_norm": 0.3318871259689331,
      "learning_rate": 1.912964000639985e-05,
      "loss": 0.5405,
      "step": 8798
    },
    {
      "epoch": 0.27029766841765734,
      "grad_norm": 0.36665672063827515,
      "learning_rate": 1.9129442799199643e-05,
      "loss": 0.6162,
      "step": 8799
    },
    {
      "epoch": 0.2703283875526065,
      "grad_norm": 1.0458301305770874,
      "learning_rate": 1.912924557067699e-05,
      "loss": 0.5588,
      "step": 8800
    },
    {
      "epoch": 0.2703591066875557,
      "grad_norm": 0.36511552333831787,
      "learning_rate": 1.912904832083234e-05,
      "loss": 0.6937,
      "step": 8801
    },
    {
      "epoch": 0.2703898258225048,
      "grad_norm": 0.36752644181251526,
      "learning_rate": 1.9128851049666165e-05,
      "loss": 0.5755,
      "step": 8802
    },
    {
      "epoch": 0.270420544957454,
      "grad_norm": 0.3430335819721222,
      "learning_rate": 1.912865375717892e-05,
      "loss": 0.5566,
      "step": 8803
    },
    {
      "epoch": 0.27045126409240317,
      "grad_norm": 0.36485645174980164,
      "learning_rate": 1.912845644337107e-05,
      "loss": 0.5913,
      "step": 8804
    },
    {
      "epoch": 0.27048198322735234,
      "grad_norm": 0.3651985824108124,
      "learning_rate": 1.9128259108243064e-05,
      "loss": 0.6088,
      "step": 8805
    },
    {
      "epoch": 0.27051270236230146,
      "grad_norm": 0.3461216390132904,
      "learning_rate": 1.912806175179538e-05,
      "loss": 0.5424,
      "step": 8806
    },
    {
      "epoch": 0.27054342149725064,
      "grad_norm": 0.3235522210597992,
      "learning_rate": 1.9127864374028467e-05,
      "loss": 0.5912,
      "step": 8807
    },
    {
      "epoch": 0.2705741406321998,
      "grad_norm": 0.6234167814254761,
      "learning_rate": 1.9127666974942786e-05,
      "loss": 0.5318,
      "step": 8808
    },
    {
      "epoch": 0.27060485976714893,
      "grad_norm": 0.3207589089870453,
      "learning_rate": 1.9127469554538804e-05,
      "loss": 0.4937,
      "step": 8809
    },
    {
      "epoch": 0.2706355789020981,
      "grad_norm": 0.35057052969932556,
      "learning_rate": 1.9127272112816978e-05,
      "loss": 0.613,
      "step": 8810
    },
    {
      "epoch": 0.2706662980370473,
      "grad_norm": 0.3662264943122864,
      "learning_rate": 1.9127074649777775e-05,
      "loss": 0.6168,
      "step": 8811
    },
    {
      "epoch": 0.27069701717199646,
      "grad_norm": 0.3365170657634735,
      "learning_rate": 1.912687716542165e-05,
      "loss": 0.6207,
      "step": 8812
    },
    {
      "epoch": 0.2707277363069456,
      "grad_norm": 0.35136595368385315,
      "learning_rate": 1.9126679659749064e-05,
      "loss": 0.5171,
      "step": 8813
    },
    {
      "epoch": 0.27075845544189475,
      "grad_norm": 0.5461302995681763,
      "learning_rate": 1.912648213276048e-05,
      "loss": 0.6367,
      "step": 8814
    },
    {
      "epoch": 0.2707891745768439,
      "grad_norm": 0.33905112743377686,
      "learning_rate": 1.9126284584456362e-05,
      "loss": 0.5995,
      "step": 8815
    },
    {
      "epoch": 0.2708198937117931,
      "grad_norm": 0.3529479503631592,
      "learning_rate": 1.9126087014837165e-05,
      "loss": 0.5837,
      "step": 8816
    },
    {
      "epoch": 0.2708506128467422,
      "grad_norm": 0.3347271978855133,
      "learning_rate": 1.9125889423903357e-05,
      "loss": 0.5695,
      "step": 8817
    },
    {
      "epoch": 0.2708813319816914,
      "grad_norm": 0.4054874777793884,
      "learning_rate": 1.9125691811655397e-05,
      "loss": 0.6749,
      "step": 8818
    },
    {
      "epoch": 0.2709120511166406,
      "grad_norm": 0.3560183048248291,
      "learning_rate": 1.9125494178093748e-05,
      "loss": 0.5195,
      "step": 8819
    },
    {
      "epoch": 0.2709427702515897,
      "grad_norm": 0.33188876509666443,
      "learning_rate": 1.9125296523218866e-05,
      "loss": 0.6446,
      "step": 8820
    },
    {
      "epoch": 0.27097348938653887,
      "grad_norm": 0.34257251024246216,
      "learning_rate": 1.912509884703122e-05,
      "loss": 0.6093,
      "step": 8821
    },
    {
      "epoch": 0.27100420852148804,
      "grad_norm": 0.3774929344654083,
      "learning_rate": 1.9124901149531266e-05,
      "loss": 0.6387,
      "step": 8822
    },
    {
      "epoch": 0.2710349276564372,
      "grad_norm": 0.3429766595363617,
      "learning_rate": 1.912470343071947e-05,
      "loss": 0.616,
      "step": 8823
    },
    {
      "epoch": 0.27106564679138634,
      "grad_norm": 0.4031590223312378,
      "learning_rate": 1.9124505690596292e-05,
      "loss": 0.65,
      "step": 8824
    },
    {
      "epoch": 0.2710963659263355,
      "grad_norm": 0.3609292805194855,
      "learning_rate": 1.9124307929162192e-05,
      "loss": 0.5913,
      "step": 8825
    },
    {
      "epoch": 0.2711270850612847,
      "grad_norm": 0.3417905867099762,
      "learning_rate": 1.9124110146417637e-05,
      "loss": 0.6182,
      "step": 8826
    },
    {
      "epoch": 0.2711578041962338,
      "grad_norm": 0.3306379020214081,
      "learning_rate": 1.912391234236308e-05,
      "loss": 0.5472,
      "step": 8827
    },
    {
      "epoch": 0.271188523331183,
      "grad_norm": 0.35126590728759766,
      "learning_rate": 1.9123714516998993e-05,
      "loss": 0.5891,
      "step": 8828
    },
    {
      "epoch": 0.27121924246613216,
      "grad_norm": 0.35027673840522766,
      "learning_rate": 1.9123516670325833e-05,
      "loss": 0.5746,
      "step": 8829
    },
    {
      "epoch": 0.27124996160108134,
      "grad_norm": 0.3246749937534332,
      "learning_rate": 1.912331880234406e-05,
      "loss": 0.6189,
      "step": 8830
    },
    {
      "epoch": 0.27128068073603046,
      "grad_norm": 0.354961633682251,
      "learning_rate": 1.9123120913054142e-05,
      "loss": 0.6643,
      "step": 8831
    },
    {
      "epoch": 0.27131139987097963,
      "grad_norm": 0.3105543851852417,
      "learning_rate": 1.9122923002456537e-05,
      "loss": 0.496,
      "step": 8832
    },
    {
      "epoch": 0.2713421190059288,
      "grad_norm": 0.3143341839313507,
      "learning_rate": 1.9122725070551706e-05,
      "loss": 0.5558,
      "step": 8833
    },
    {
      "epoch": 0.2713728381408779,
      "grad_norm": 0.47411176562309265,
      "learning_rate": 1.9122527117340114e-05,
      "loss": 0.5882,
      "step": 8834
    },
    {
      "epoch": 0.2714035572758271,
      "grad_norm": 0.35616979002952576,
      "learning_rate": 1.9122329142822224e-05,
      "loss": 0.5367,
      "step": 8835
    },
    {
      "epoch": 0.2714342764107763,
      "grad_norm": 0.5545275807380676,
      "learning_rate": 1.9122131146998498e-05,
      "loss": 0.5933,
      "step": 8836
    },
    {
      "epoch": 0.27146499554572545,
      "grad_norm": 0.5083135962486267,
      "learning_rate": 1.91219331298694e-05,
      "loss": 0.6129,
      "step": 8837
    },
    {
      "epoch": 0.27149571468067457,
      "grad_norm": 0.33757463097572327,
      "learning_rate": 1.9121735091435387e-05,
      "loss": 0.5408,
      "step": 8838
    },
    {
      "epoch": 0.27152643381562375,
      "grad_norm": 0.41185396909713745,
      "learning_rate": 1.9121537031696923e-05,
      "loss": 0.6395,
      "step": 8839
    },
    {
      "epoch": 0.2715571529505729,
      "grad_norm": 0.32927656173706055,
      "learning_rate": 1.9121338950654472e-05,
      "loss": 0.5897,
      "step": 8840
    },
    {
      "epoch": 0.2715878720855221,
      "grad_norm": 0.3563174605369568,
      "learning_rate": 1.91211408483085e-05,
      "loss": 0.599,
      "step": 8841
    },
    {
      "epoch": 0.2716185912204712,
      "grad_norm": 0.3249050974845886,
      "learning_rate": 1.9120942724659465e-05,
      "loss": 0.5756,
      "step": 8842
    },
    {
      "epoch": 0.2716493103554204,
      "grad_norm": 0.34877511858940125,
      "learning_rate": 1.9120744579707833e-05,
      "loss": 0.7053,
      "step": 8843
    },
    {
      "epoch": 0.27168002949036957,
      "grad_norm": 0.40192946791648865,
      "learning_rate": 1.912054641345406e-05,
      "loss": 0.6363,
      "step": 8844
    },
    {
      "epoch": 0.2717107486253187,
      "grad_norm": 0.33977794647216797,
      "learning_rate": 1.912034822589862e-05,
      "loss": 0.6081,
      "step": 8845
    },
    {
      "epoch": 0.27174146776026786,
      "grad_norm": 0.34973058104515076,
      "learning_rate": 1.9120150017041968e-05,
      "loss": 0.4995,
      "step": 8846
    },
    {
      "epoch": 0.27177218689521704,
      "grad_norm": 0.3722167909145355,
      "learning_rate": 1.9119951786884568e-05,
      "loss": 0.6355,
      "step": 8847
    },
    {
      "epoch": 0.2718029060301662,
      "grad_norm": 0.3560855984687805,
      "learning_rate": 1.911975353542688e-05,
      "loss": 0.6365,
      "step": 8848
    },
    {
      "epoch": 0.27183362516511533,
      "grad_norm": 0.31516897678375244,
      "learning_rate": 1.9119555262669375e-05,
      "loss": 0.5073,
      "step": 8849
    },
    {
      "epoch": 0.2718643443000645,
      "grad_norm": 0.3414231538772583,
      "learning_rate": 1.9119356968612514e-05,
      "loss": 0.5917,
      "step": 8850
    },
    {
      "epoch": 0.2718950634350137,
      "grad_norm": 0.3458062708377838,
      "learning_rate": 1.9119158653256752e-05,
      "loss": 0.5908,
      "step": 8851
    },
    {
      "epoch": 0.2719257825699628,
      "grad_norm": 0.348469614982605,
      "learning_rate": 1.9118960316602564e-05,
      "loss": 0.6038,
      "step": 8852
    },
    {
      "epoch": 0.271956501704912,
      "grad_norm": 0.3256475627422333,
      "learning_rate": 1.9118761958650403e-05,
      "loss": 0.5809,
      "step": 8853
    },
    {
      "epoch": 0.27198722083986115,
      "grad_norm": 0.31291434168815613,
      "learning_rate": 1.9118563579400737e-05,
      "loss": 0.5687,
      "step": 8854
    },
    {
      "epoch": 0.27201793997481033,
      "grad_norm": 0.34046798944473267,
      "learning_rate": 1.911836517885403e-05,
      "loss": 0.6351,
      "step": 8855
    },
    {
      "epoch": 0.27204865910975945,
      "grad_norm": 0.4025737941265106,
      "learning_rate": 1.9118166757010743e-05,
      "loss": 0.5983,
      "step": 8856
    },
    {
      "epoch": 0.2720793782447086,
      "grad_norm": 0.3714946508407593,
      "learning_rate": 1.9117968313871343e-05,
      "loss": 0.5832,
      "step": 8857
    },
    {
      "epoch": 0.2721100973796578,
      "grad_norm": 0.39165204763412476,
      "learning_rate": 1.9117769849436292e-05,
      "loss": 0.6649,
      "step": 8858
    },
    {
      "epoch": 0.272140816514607,
      "grad_norm": 0.3350888788700104,
      "learning_rate": 1.911757136370605e-05,
      "loss": 0.6307,
      "step": 8859
    },
    {
      "epoch": 0.2721715356495561,
      "grad_norm": 0.3730376362800598,
      "learning_rate": 1.9117372856681084e-05,
      "loss": 0.6646,
      "step": 8860
    },
    {
      "epoch": 0.27220225478450527,
      "grad_norm": 0.3719291090965271,
      "learning_rate": 1.9117174328361856e-05,
      "loss": 0.5729,
      "step": 8861
    },
    {
      "epoch": 0.27223297391945445,
      "grad_norm": 0.3241090178489685,
      "learning_rate": 1.9116975778748832e-05,
      "loss": 0.5873,
      "step": 8862
    },
    {
      "epoch": 0.27226369305440357,
      "grad_norm": 0.3794568181037903,
      "learning_rate": 1.9116777207842475e-05,
      "loss": 0.6015,
      "step": 8863
    },
    {
      "epoch": 0.27229441218935274,
      "grad_norm": 0.3454555571079254,
      "learning_rate": 1.9116578615643247e-05,
      "loss": 0.5825,
      "step": 8864
    },
    {
      "epoch": 0.2723251313243019,
      "grad_norm": 0.32911139726638794,
      "learning_rate": 1.9116380002151614e-05,
      "loss": 0.5721,
      "step": 8865
    },
    {
      "epoch": 0.2723558504592511,
      "grad_norm": 0.31994473934173584,
      "learning_rate": 1.9116181367368035e-05,
      "loss": 0.5695,
      "step": 8866
    },
    {
      "epoch": 0.2723865695942002,
      "grad_norm": 0.3712998330593109,
      "learning_rate": 1.9115982711292982e-05,
      "loss": 0.5074,
      "step": 8867
    },
    {
      "epoch": 0.2724172887291494,
      "grad_norm": 0.379839152097702,
      "learning_rate": 1.9115784033926912e-05,
      "loss": 0.5021,
      "step": 8868
    },
    {
      "epoch": 0.27244800786409856,
      "grad_norm": 0.3399556875228882,
      "learning_rate": 1.9115585335270294e-05,
      "loss": 0.5864,
      "step": 8869
    },
    {
      "epoch": 0.2724787269990477,
      "grad_norm": 0.3710068464279175,
      "learning_rate": 1.911538661532359e-05,
      "loss": 0.5488,
      "step": 8870
    },
    {
      "epoch": 0.27250944613399686,
      "grad_norm": 0.3313765525817871,
      "learning_rate": 1.9115187874087265e-05,
      "loss": 0.6427,
      "step": 8871
    },
    {
      "epoch": 0.27254016526894603,
      "grad_norm": 0.34828439354896545,
      "learning_rate": 1.9114989111561777e-05,
      "loss": 0.6077,
      "step": 8872
    },
    {
      "epoch": 0.2725708844038952,
      "grad_norm": 0.41461580991744995,
      "learning_rate": 1.91147903277476e-05,
      "loss": 0.5607,
      "step": 8873
    },
    {
      "epoch": 0.27260160353884433,
      "grad_norm": 0.3667692542076111,
      "learning_rate": 1.911459152264519e-05,
      "loss": 0.615,
      "step": 8874
    },
    {
      "epoch": 0.2726323226737935,
      "grad_norm": 0.3691164255142212,
      "learning_rate": 1.9114392696255017e-05,
      "loss": 0.603,
      "step": 8875
    },
    {
      "epoch": 0.2726630418087427,
      "grad_norm": 0.42669859528541565,
      "learning_rate": 1.9114193848577544e-05,
      "loss": 0.6272,
      "step": 8876
    },
    {
      "epoch": 0.2726937609436918,
      "grad_norm": 0.35573604702949524,
      "learning_rate": 1.9113994979613235e-05,
      "loss": 0.5425,
      "step": 8877
    },
    {
      "epoch": 0.272724480078641,
      "grad_norm": 0.3659326136112213,
      "learning_rate": 1.9113796089362554e-05,
      "loss": 0.6159,
      "step": 8878
    },
    {
      "epoch": 0.27275519921359015,
      "grad_norm": 0.32208549976348877,
      "learning_rate": 1.9113597177825966e-05,
      "loss": 0.5808,
      "step": 8879
    },
    {
      "epoch": 0.2727859183485393,
      "grad_norm": 0.3187258541584015,
      "learning_rate": 1.9113398245003935e-05,
      "loss": 0.4718,
      "step": 8880
    },
    {
      "epoch": 0.27281663748348844,
      "grad_norm": 0.3943973481655121,
      "learning_rate": 1.911319929089692e-05,
      "loss": 0.5462,
      "step": 8881
    },
    {
      "epoch": 0.2728473566184376,
      "grad_norm": 0.36336538195610046,
      "learning_rate": 1.91130003155054e-05,
      "loss": 0.5962,
      "step": 8882
    },
    {
      "epoch": 0.2728780757533868,
      "grad_norm": 0.35019150376319885,
      "learning_rate": 1.911280131882983e-05,
      "loss": 0.6469,
      "step": 8883
    },
    {
      "epoch": 0.27290879488833597,
      "grad_norm": 0.34080177545547485,
      "learning_rate": 1.9112602300870673e-05,
      "loss": 0.5473,
      "step": 8884
    },
    {
      "epoch": 0.2729395140232851,
      "grad_norm": 0.33876243233680725,
      "learning_rate": 1.9112403261628398e-05,
      "loss": 0.604,
      "step": 8885
    },
    {
      "epoch": 0.27297023315823427,
      "grad_norm": 0.3503236472606659,
      "learning_rate": 1.9112204201103468e-05,
      "loss": 0.5638,
      "step": 8886
    },
    {
      "epoch": 0.27300095229318344,
      "grad_norm": 0.33791080117225647,
      "learning_rate": 1.9112005119296347e-05,
      "loss": 0.7053,
      "step": 8887
    },
    {
      "epoch": 0.27303167142813256,
      "grad_norm": 0.3821645677089691,
      "learning_rate": 1.9111806016207506e-05,
      "loss": 0.6307,
      "step": 8888
    },
    {
      "epoch": 0.27306239056308174,
      "grad_norm": 0.3523755669593811,
      "learning_rate": 1.9111606891837404e-05,
      "loss": 0.5899,
      "step": 8889
    },
    {
      "epoch": 0.2730931096980309,
      "grad_norm": 0.39738741517066956,
      "learning_rate": 1.9111407746186506e-05,
      "loss": 0.5879,
      "step": 8890
    },
    {
      "epoch": 0.2731238288329801,
      "grad_norm": 0.33360692858695984,
      "learning_rate": 1.911120857925528e-05,
      "loss": 0.6026,
      "step": 8891
    },
    {
      "epoch": 0.2731545479679292,
      "grad_norm": 0.38408562541007996,
      "learning_rate": 1.9111009391044197e-05,
      "loss": 0.5351,
      "step": 8892
    },
    {
      "epoch": 0.2731852671028784,
      "grad_norm": 0.34869739413261414,
      "learning_rate": 1.9110810181553703e-05,
      "loss": 0.6113,
      "step": 8893
    },
    {
      "epoch": 0.27321598623782756,
      "grad_norm": 0.956933319568634,
      "learning_rate": 1.9110610950784285e-05,
      "loss": 0.4808,
      "step": 8894
    },
    {
      "epoch": 0.2732467053727767,
      "grad_norm": 0.3162194490432739,
      "learning_rate": 1.9110411698736393e-05,
      "loss": 0.575,
      "step": 8895
    },
    {
      "epoch": 0.27327742450772585,
      "grad_norm": 0.33804410696029663,
      "learning_rate": 1.9110212425410502e-05,
      "loss": 0.4935,
      "step": 8896
    },
    {
      "epoch": 0.273308143642675,
      "grad_norm": 0.35966956615448,
      "learning_rate": 1.911001313080707e-05,
      "loss": 0.6304,
      "step": 8897
    },
    {
      "epoch": 0.2733388627776242,
      "grad_norm": 0.31171077489852905,
      "learning_rate": 1.910981381492657e-05,
      "loss": 0.6165,
      "step": 8898
    },
    {
      "epoch": 0.2733695819125733,
      "grad_norm": 0.3354741036891937,
      "learning_rate": 1.910961447776946e-05,
      "loss": 0.5143,
      "step": 8899
    },
    {
      "epoch": 0.2734003010475225,
      "grad_norm": 0.34670934081077576,
      "learning_rate": 1.9109415119336213e-05,
      "loss": 0.542,
      "step": 8900
    },
    {
      "epoch": 0.2734310201824717,
      "grad_norm": 0.36840805411338806,
      "learning_rate": 1.9109215739627287e-05,
      "loss": 0.5795,
      "step": 8901
    },
    {
      "epoch": 0.27346173931742085,
      "grad_norm": 0.40598446130752563,
      "learning_rate": 1.9109016338643152e-05,
      "loss": 0.5658,
      "step": 8902
    },
    {
      "epoch": 0.27349245845236997,
      "grad_norm": 0.3738972544670105,
      "learning_rate": 1.9108816916384278e-05,
      "loss": 0.605,
      "step": 8903
    },
    {
      "epoch": 0.27352317758731914,
      "grad_norm": 0.39003321528434753,
      "learning_rate": 1.910861747285112e-05,
      "loss": 0.6879,
      "step": 8904
    },
    {
      "epoch": 0.2735538967222683,
      "grad_norm": 0.34234437346458435,
      "learning_rate": 1.9108418008044154e-05,
      "loss": 0.5735,
      "step": 8905
    },
    {
      "epoch": 0.27358461585721744,
      "grad_norm": 0.3420734107494354,
      "learning_rate": 1.910821852196384e-05,
      "loss": 0.6142,
      "step": 8906
    },
    {
      "epoch": 0.2736153349921666,
      "grad_norm": 0.32506605982780457,
      "learning_rate": 1.9108019014610643e-05,
      "loss": 0.5248,
      "step": 8907
    },
    {
      "epoch": 0.2736460541271158,
      "grad_norm": 0.3793134093284607,
      "learning_rate": 1.9107819485985034e-05,
      "loss": 0.5833,
      "step": 8908
    },
    {
      "epoch": 0.27367677326206497,
      "grad_norm": 0.4484535753726959,
      "learning_rate": 1.910761993608748e-05,
      "loss": 0.5195,
      "step": 8909
    },
    {
      "epoch": 0.2737074923970141,
      "grad_norm": 0.3436616063117981,
      "learning_rate": 1.910742036491844e-05,
      "loss": 0.5764,
      "step": 8910
    },
    {
      "epoch": 0.27373821153196326,
      "grad_norm": 0.38640061020851135,
      "learning_rate": 1.910722077247838e-05,
      "loss": 0.6554,
      "step": 8911
    },
    {
      "epoch": 0.27376893066691244,
      "grad_norm": 0.35989174246788025,
      "learning_rate": 1.9107021158767774e-05,
      "loss": 0.6063,
      "step": 8912
    },
    {
      "epoch": 0.27379964980186156,
      "grad_norm": 0.37530404329299927,
      "learning_rate": 1.9106821523787084e-05,
      "loss": 0.5986,
      "step": 8913
    },
    {
      "epoch": 0.27383036893681073,
      "grad_norm": 0.30335140228271484,
      "learning_rate": 1.9106621867536774e-05,
      "loss": 0.5418,
      "step": 8914
    },
    {
      "epoch": 0.2738610880717599,
      "grad_norm": 0.34579136967658997,
      "learning_rate": 1.9106422190017318e-05,
      "loss": 0.5699,
      "step": 8915
    },
    {
      "epoch": 0.2738918072067091,
      "grad_norm": 0.3723529279232025,
      "learning_rate": 1.9106222491229172e-05,
      "loss": 0.5195,
      "step": 8916
    },
    {
      "epoch": 0.2739225263416582,
      "grad_norm": 0.39239197969436646,
      "learning_rate": 1.910602277117281e-05,
      "loss": 0.6141,
      "step": 8917
    },
    {
      "epoch": 0.2739532454766074,
      "grad_norm": 0.3132525682449341,
      "learning_rate": 1.910582302984869e-05,
      "loss": 0.6001,
      "step": 8918
    },
    {
      "epoch": 0.27398396461155655,
      "grad_norm": 0.36027947068214417,
      "learning_rate": 1.910562326725729e-05,
      "loss": 0.5879,
      "step": 8919
    },
    {
      "epoch": 0.27401468374650567,
      "grad_norm": 0.3734198808670044,
      "learning_rate": 1.9105423483399072e-05,
      "loss": 0.5794,
      "step": 8920
    },
    {
      "epoch": 0.27404540288145485,
      "grad_norm": 0.3293069005012512,
      "learning_rate": 1.9105223678274498e-05,
      "loss": 0.6303,
      "step": 8921
    },
    {
      "epoch": 0.274076122016404,
      "grad_norm": 0.3279346227645874,
      "learning_rate": 1.910502385188404e-05,
      "loss": 0.5793,
      "step": 8922
    },
    {
      "epoch": 0.2741068411513532,
      "grad_norm": 0.3261664807796478,
      "learning_rate": 1.9104824004228164e-05,
      "loss": 0.5587,
      "step": 8923
    },
    {
      "epoch": 0.2741375602863023,
      "grad_norm": 0.3696810007095337,
      "learning_rate": 1.9104624135307332e-05,
      "loss": 0.5782,
      "step": 8924
    },
    {
      "epoch": 0.2741682794212515,
      "grad_norm": 0.3383024036884308,
      "learning_rate": 1.9104424245122016e-05,
      "loss": 0.5871,
      "step": 8925
    },
    {
      "epoch": 0.27419899855620067,
      "grad_norm": 0.35828855633735657,
      "learning_rate": 1.9104224333672687e-05,
      "loss": 0.5553,
      "step": 8926
    },
    {
      "epoch": 0.27422971769114984,
      "grad_norm": 0.388014554977417,
      "learning_rate": 1.9104024400959798e-05,
      "loss": 0.6547,
      "step": 8927
    },
    {
      "epoch": 0.27426043682609896,
      "grad_norm": 0.355530709028244,
      "learning_rate": 1.910382444698383e-05,
      "loss": 0.5429,
      "step": 8928
    },
    {
      "epoch": 0.27429115596104814,
      "grad_norm": 0.3389267325401306,
      "learning_rate": 1.910362447174524e-05,
      "loss": 0.5981,
      "step": 8929
    },
    {
      "epoch": 0.2743218750959973,
      "grad_norm": 0.3831421732902527,
      "learning_rate": 1.91034244752445e-05,
      "loss": 0.6034,
      "step": 8930
    },
    {
      "epoch": 0.27435259423094643,
      "grad_norm": 0.4831177294254303,
      "learning_rate": 1.9103224457482077e-05,
      "loss": 0.6503,
      "step": 8931
    },
    {
      "epoch": 0.2743833133658956,
      "grad_norm": 0.36687353253364563,
      "learning_rate": 1.910302441845844e-05,
      "loss": 0.5822,
      "step": 8932
    },
    {
      "epoch": 0.2744140325008448,
      "grad_norm": 0.34491580724716187,
      "learning_rate": 1.910282435817405e-05,
      "loss": 0.6385,
      "step": 8933
    },
    {
      "epoch": 0.27444475163579396,
      "grad_norm": 0.3449207544326782,
      "learning_rate": 1.910262427662938e-05,
      "loss": 0.6804,
      "step": 8934
    },
    {
      "epoch": 0.2744754707707431,
      "grad_norm": 0.5267018675804138,
      "learning_rate": 1.9102424173824894e-05,
      "loss": 0.6248,
      "step": 8935
    },
    {
      "epoch": 0.27450618990569225,
      "grad_norm": 0.3400757312774658,
      "learning_rate": 1.9102224049761062e-05,
      "loss": 0.6319,
      "step": 8936
    },
    {
      "epoch": 0.27453690904064143,
      "grad_norm": 0.3299473524093628,
      "learning_rate": 1.910202390443835e-05,
      "loss": 0.577,
      "step": 8937
    },
    {
      "epoch": 0.27456762817559055,
      "grad_norm": 0.3763038218021393,
      "learning_rate": 1.9101823737857224e-05,
      "loss": 0.6289,
      "step": 8938
    },
    {
      "epoch": 0.2745983473105397,
      "grad_norm": 0.3190712630748749,
      "learning_rate": 1.9101623550018154e-05,
      "loss": 0.5398,
      "step": 8939
    },
    {
      "epoch": 0.2746290664454889,
      "grad_norm": 0.3233368992805481,
      "learning_rate": 1.910142334092161e-05,
      "loss": 0.5982,
      "step": 8940
    },
    {
      "epoch": 0.2746597855804381,
      "grad_norm": 0.36336877942085266,
      "learning_rate": 1.910122311056805e-05,
      "loss": 0.4736,
      "step": 8941
    },
    {
      "epoch": 0.2746905047153872,
      "grad_norm": 0.3668202757835388,
      "learning_rate": 1.910102285895795e-05,
      "loss": 0.6218,
      "step": 8942
    },
    {
      "epoch": 0.27472122385033637,
      "grad_norm": 0.3294389247894287,
      "learning_rate": 1.9100822586091775e-05,
      "loss": 0.5677,
      "step": 8943
    },
    {
      "epoch": 0.27475194298528555,
      "grad_norm": 0.43302157521247864,
      "learning_rate": 1.9100622291969995e-05,
      "loss": 0.5536,
      "step": 8944
    },
    {
      "epoch": 0.2747826621202347,
      "grad_norm": 0.35770484805107117,
      "learning_rate": 1.9100421976593076e-05,
      "loss": 0.5653,
      "step": 8945
    },
    {
      "epoch": 0.27481338125518384,
      "grad_norm": 0.32942259311676025,
      "learning_rate": 1.9100221639961484e-05,
      "loss": 0.5625,
      "step": 8946
    },
    {
      "epoch": 0.274844100390133,
      "grad_norm": 0.3709118068218231,
      "learning_rate": 1.910002128207569e-05,
      "loss": 0.5742,
      "step": 8947
    },
    {
      "epoch": 0.2748748195250822,
      "grad_norm": 0.3394337594509125,
      "learning_rate": 1.909982090293616e-05,
      "loss": 0.6551,
      "step": 8948
    },
    {
      "epoch": 0.2749055386600313,
      "grad_norm": 0.3434814214706421,
      "learning_rate": 1.9099620502543364e-05,
      "loss": 0.5231,
      "step": 8949
    },
    {
      "epoch": 0.2749362577949805,
      "grad_norm": 0.3574450612068176,
      "learning_rate": 1.909942008089777e-05,
      "loss": 0.5682,
      "step": 8950
    },
    {
      "epoch": 0.27496697692992966,
      "grad_norm": 0.33513689041137695,
      "learning_rate": 1.9099219637999843e-05,
      "loss": 0.5638,
      "step": 8951
    },
    {
      "epoch": 0.27499769606487884,
      "grad_norm": 0.3504103422164917,
      "learning_rate": 1.9099019173850053e-05,
      "loss": 0.5926,
      "step": 8952
    },
    {
      "epoch": 0.27502841519982796,
      "grad_norm": 0.3579115569591522,
      "learning_rate": 1.9098818688448867e-05,
      "loss": 0.5915,
      "step": 8953
    },
    {
      "epoch": 0.27505913433477713,
      "grad_norm": 0.39586082100868225,
      "learning_rate": 1.9098618181796757e-05,
      "loss": 0.5457,
      "step": 8954
    },
    {
      "epoch": 0.2750898534697263,
      "grad_norm": 0.3422037363052368,
      "learning_rate": 1.909841765389419e-05,
      "loss": 0.5574,
      "step": 8955
    },
    {
      "epoch": 0.27512057260467543,
      "grad_norm": 0.5863453149795532,
      "learning_rate": 1.909821710474163e-05,
      "loss": 0.6255,
      "step": 8956
    },
    {
      "epoch": 0.2751512917396246,
      "grad_norm": 0.37905779480934143,
      "learning_rate": 1.909801653433955e-05,
      "loss": 0.5849,
      "step": 8957
    },
    {
      "epoch": 0.2751820108745738,
      "grad_norm": 0.3327501714229584,
      "learning_rate": 1.9097815942688415e-05,
      "loss": 0.5834,
      "step": 8958
    },
    {
      "epoch": 0.27521273000952295,
      "grad_norm": 0.3520163595676422,
      "learning_rate": 1.9097615329788696e-05,
      "loss": 0.568,
      "step": 8959
    },
    {
      "epoch": 0.2752434491444721,
      "grad_norm": 0.3394906222820282,
      "learning_rate": 1.9097414695640864e-05,
      "loss": 0.545,
      "step": 8960
    },
    {
      "epoch": 0.27527416827942125,
      "grad_norm": 0.334539532661438,
      "learning_rate": 1.9097214040245384e-05,
      "loss": 0.5752,
      "step": 8961
    },
    {
      "epoch": 0.2753048874143704,
      "grad_norm": 0.3546842932701111,
      "learning_rate": 1.9097013363602722e-05,
      "loss": 0.6924,
      "step": 8962
    },
    {
      "epoch": 0.27533560654931954,
      "grad_norm": 0.32422614097595215,
      "learning_rate": 1.909681266571335e-05,
      "loss": 0.6054,
      "step": 8963
    },
    {
      "epoch": 0.2753663256842687,
      "grad_norm": 0.4164823591709137,
      "learning_rate": 1.909661194657774e-05,
      "loss": 0.5769,
      "step": 8964
    },
    {
      "epoch": 0.2753970448192179,
      "grad_norm": 0.3924878239631653,
      "learning_rate": 1.9096411206196357e-05,
      "loss": 0.6011,
      "step": 8965
    },
    {
      "epoch": 0.27542776395416707,
      "grad_norm": 0.3801572918891907,
      "learning_rate": 1.9096210444569666e-05,
      "loss": 0.6116,
      "step": 8966
    },
    {
      "epoch": 0.2754584830891162,
      "grad_norm": 0.37226173281669617,
      "learning_rate": 1.9096009661698147e-05,
      "loss": 0.6168,
      "step": 8967
    },
    {
      "epoch": 0.27548920222406537,
      "grad_norm": 0.34011054039001465,
      "learning_rate": 1.9095808857582258e-05,
      "loss": 0.5994,
      "step": 8968
    },
    {
      "epoch": 0.27551992135901454,
      "grad_norm": 0.3680865466594696,
      "learning_rate": 1.9095608032222474e-05,
      "loss": 0.6313,
      "step": 8969
    },
    {
      "epoch": 0.2755506404939637,
      "grad_norm": 0.3725404441356659,
      "learning_rate": 1.909540718561926e-05,
      "loss": 0.5479,
      "step": 8970
    },
    {
      "epoch": 0.27558135962891284,
      "grad_norm": 0.5812805891036987,
      "learning_rate": 1.909520631777309e-05,
      "loss": 0.5515,
      "step": 8971
    },
    {
      "epoch": 0.275612078763862,
      "grad_norm": 0.3492903411388397,
      "learning_rate": 1.9095005428684428e-05,
      "loss": 0.5824,
      "step": 8972
    },
    {
      "epoch": 0.2756427978988112,
      "grad_norm": 0.3500000536441803,
      "learning_rate": 1.9094804518353748e-05,
      "loss": 0.589,
      "step": 8973
    },
    {
      "epoch": 0.2756735170337603,
      "grad_norm": 0.3428811728954315,
      "learning_rate": 1.9094603586781515e-05,
      "loss": 0.5063,
      "step": 8974
    },
    {
      "epoch": 0.2757042361687095,
      "grad_norm": 0.4418536126613617,
      "learning_rate": 1.90944026339682e-05,
      "loss": 0.6844,
      "step": 8975
    },
    {
      "epoch": 0.27573495530365866,
      "grad_norm": 0.3432382345199585,
      "learning_rate": 1.9094201659914272e-05,
      "loss": 0.5618,
      "step": 8976
    },
    {
      "epoch": 0.27576567443860783,
      "grad_norm": 0.3306511640548706,
      "learning_rate": 1.90940006646202e-05,
      "loss": 0.519,
      "step": 8977
    },
    {
      "epoch": 0.27579639357355695,
      "grad_norm": 0.3258973956108093,
      "learning_rate": 1.909379964808646e-05,
      "loss": 0.6326,
      "step": 8978
    },
    {
      "epoch": 0.27582711270850613,
      "grad_norm": 0.3203446567058563,
      "learning_rate": 1.909359861031351e-05,
      "loss": 0.5378,
      "step": 8979
    },
    {
      "epoch": 0.2758578318434553,
      "grad_norm": 0.4642522931098938,
      "learning_rate": 1.9093397551301827e-05,
      "loss": 0.5933,
      "step": 8980
    },
    {
      "epoch": 0.2758885509784044,
      "grad_norm": 0.3560873568058014,
      "learning_rate": 1.909319647105188e-05,
      "loss": 0.6887,
      "step": 8981
    },
    {
      "epoch": 0.2759192701133536,
      "grad_norm": 0.47500696778297424,
      "learning_rate": 1.909299536956414e-05,
      "loss": 0.6705,
      "step": 8982
    },
    {
      "epoch": 0.2759499892483028,
      "grad_norm": 0.3600247800350189,
      "learning_rate": 1.909279424683907e-05,
      "loss": 0.5295,
      "step": 8983
    },
    {
      "epoch": 0.27598070838325195,
      "grad_norm": 0.3570362627506256,
      "learning_rate": 1.9092593102877144e-05,
      "loss": 0.5187,
      "step": 8984
    },
    {
      "epoch": 0.27601142751820107,
      "grad_norm": 0.31439149379730225,
      "learning_rate": 1.9092391937678834e-05,
      "loss": 0.6392,
      "step": 8985
    },
    {
      "epoch": 0.27604214665315024,
      "grad_norm": 0.36509600281715393,
      "learning_rate": 1.9092190751244606e-05,
      "loss": 0.6676,
      "step": 8986
    },
    {
      "epoch": 0.2760728657880994,
      "grad_norm": 0.3099333643913269,
      "learning_rate": 1.909198954357493e-05,
      "loss": 0.4955,
      "step": 8987
    },
    {
      "epoch": 0.27610358492304854,
      "grad_norm": 0.35008206963539124,
      "learning_rate": 1.909178831467028e-05,
      "loss": 0.5912,
      "step": 8988
    },
    {
      "epoch": 0.2761343040579977,
      "grad_norm": 0.34117862582206726,
      "learning_rate": 1.9091587064531127e-05,
      "loss": 0.6502,
      "step": 8989
    },
    {
      "epoch": 0.2761650231929469,
      "grad_norm": 0.33481520414352417,
      "learning_rate": 1.9091385793157932e-05,
      "loss": 0.5873,
      "step": 8990
    },
    {
      "epoch": 0.27619574232789607,
      "grad_norm": 0.3501184284687042,
      "learning_rate": 1.9091184500551173e-05,
      "loss": 0.5376,
      "step": 8991
    },
    {
      "epoch": 0.2762264614628452,
      "grad_norm": 0.32594314217567444,
      "learning_rate": 1.9090983186711318e-05,
      "loss": 0.6628,
      "step": 8992
    },
    {
      "epoch": 0.27625718059779436,
      "grad_norm": 0.36819323897361755,
      "learning_rate": 1.9090781851638833e-05,
      "loss": 0.6096,
      "step": 8993
    },
    {
      "epoch": 0.27628789973274354,
      "grad_norm": 0.33233359456062317,
      "learning_rate": 1.9090580495334193e-05,
      "loss": 0.6071,
      "step": 8994
    },
    {
      "epoch": 0.2763186188676927,
      "grad_norm": 0.3059450387954712,
      "learning_rate": 1.909037911779787e-05,
      "loss": 0.6026,
      "step": 8995
    },
    {
      "epoch": 0.27634933800264183,
      "grad_norm": 0.33230817317962646,
      "learning_rate": 1.909017771903033e-05,
      "loss": 0.5778,
      "step": 8996
    },
    {
      "epoch": 0.276380057137591,
      "grad_norm": 0.3581162989139557,
      "learning_rate": 1.9089976299032046e-05,
      "loss": 0.5676,
      "step": 8997
    },
    {
      "epoch": 0.2764107762725402,
      "grad_norm": 0.31263190507888794,
      "learning_rate": 1.908977485780349e-05,
      "loss": 0.6123,
      "step": 8998
    },
    {
      "epoch": 0.2764414954074893,
      "grad_norm": 0.34813234210014343,
      "learning_rate": 1.9089573395345127e-05,
      "loss": 0.5412,
      "step": 8999
    },
    {
      "epoch": 0.2764722145424385,
      "grad_norm": 0.46781453490257263,
      "learning_rate": 1.908937191165743e-05,
      "loss": 0.5505,
      "step": 9000
    },
    {
      "epoch": 0.27650293367738765,
      "grad_norm": 0.3854745328426361,
      "learning_rate": 1.9089170406740872e-05,
      "loss": 0.5897,
      "step": 9001
    },
    {
      "epoch": 0.2765336528123368,
      "grad_norm": 0.36361077427864075,
      "learning_rate": 1.9088968880595922e-05,
      "loss": 0.628,
      "step": 9002
    },
    {
      "epoch": 0.27656437194728595,
      "grad_norm": 0.3584422469139099,
      "learning_rate": 1.9088767333223045e-05,
      "loss": 0.5979,
      "step": 9003
    },
    {
      "epoch": 0.2765950910822351,
      "grad_norm": 0.3585317134857178,
      "learning_rate": 1.9088565764622723e-05,
      "loss": 0.6294,
      "step": 9004
    },
    {
      "epoch": 0.2766258102171843,
      "grad_norm": 0.41040074825286865,
      "learning_rate": 1.908836417479542e-05,
      "loss": 0.6446,
      "step": 9005
    },
    {
      "epoch": 0.2766565293521334,
      "grad_norm": 0.34213459491729736,
      "learning_rate": 1.9088162563741606e-05,
      "loss": 0.6356,
      "step": 9006
    },
    {
      "epoch": 0.2766872484870826,
      "grad_norm": 0.31852757930755615,
      "learning_rate": 1.9087960931461754e-05,
      "loss": 0.5922,
      "step": 9007
    },
    {
      "epoch": 0.27671796762203177,
      "grad_norm": 0.33009183406829834,
      "learning_rate": 1.9087759277956337e-05,
      "loss": 0.5775,
      "step": 9008
    },
    {
      "epoch": 0.27674868675698094,
      "grad_norm": 0.3288157880306244,
      "learning_rate": 1.9087557603225822e-05,
      "loss": 0.5656,
      "step": 9009
    },
    {
      "epoch": 0.27677940589193006,
      "grad_norm": 0.35060247778892517,
      "learning_rate": 1.9087355907270678e-05,
      "loss": 0.6007,
      "step": 9010
    },
    {
      "epoch": 0.27681012502687924,
      "grad_norm": 0.6472494602203369,
      "learning_rate": 1.9087154190091385e-05,
      "loss": 0.6286,
      "step": 9011
    },
    {
      "epoch": 0.2768408441618284,
      "grad_norm": 0.39090588688850403,
      "learning_rate": 1.9086952451688407e-05,
      "loss": 0.626,
      "step": 9012
    },
    {
      "epoch": 0.2768715632967776,
      "grad_norm": 0.3241627812385559,
      "learning_rate": 1.9086750692062216e-05,
      "loss": 0.5668,
      "step": 9013
    },
    {
      "epoch": 0.2769022824317267,
      "grad_norm": 0.3629131019115448,
      "learning_rate": 1.9086548911213286e-05,
      "loss": 0.5002,
      "step": 9014
    },
    {
      "epoch": 0.2769330015666759,
      "grad_norm": 0.3145436644554138,
      "learning_rate": 1.908634710914208e-05,
      "loss": 0.6012,
      "step": 9015
    },
    {
      "epoch": 0.27696372070162506,
      "grad_norm": 0.3382406532764435,
      "learning_rate": 1.9086145285849086e-05,
      "loss": 0.5573,
      "step": 9016
    },
    {
      "epoch": 0.2769944398365742,
      "grad_norm": 0.4025759696960449,
      "learning_rate": 1.908594344133476e-05,
      "loss": 0.5118,
      "step": 9017
    },
    {
      "epoch": 0.27702515897152336,
      "grad_norm": 0.3920857608318329,
      "learning_rate": 1.908574157559958e-05,
      "loss": 0.5965,
      "step": 9018
    },
    {
      "epoch": 0.27705587810647253,
      "grad_norm": 0.33328357338905334,
      "learning_rate": 1.9085539688644012e-05,
      "loss": 0.5735,
      "step": 9019
    },
    {
      "epoch": 0.2770865972414217,
      "grad_norm": 0.3722972869873047,
      "learning_rate": 1.9085337780468537e-05,
      "loss": 0.6733,
      "step": 9020
    },
    {
      "epoch": 0.2771173163763708,
      "grad_norm": 0.35463979840278625,
      "learning_rate": 1.9085135851073617e-05,
      "loss": 0.5368,
      "step": 9021
    },
    {
      "epoch": 0.27714803551132,
      "grad_norm": 0.7503504753112793,
      "learning_rate": 1.9084933900459724e-05,
      "loss": 0.4803,
      "step": 9022
    },
    {
      "epoch": 0.2771787546462692,
      "grad_norm": 0.35250139236450195,
      "learning_rate": 1.908473192862734e-05,
      "loss": 0.6552,
      "step": 9023
    },
    {
      "epoch": 0.2772094737812183,
      "grad_norm": 0.3554668128490448,
      "learning_rate": 1.908452993557693e-05,
      "loss": 0.5629,
      "step": 9024
    },
    {
      "epoch": 0.27724019291616747,
      "grad_norm": 0.35414043068885803,
      "learning_rate": 1.9084327921308965e-05,
      "loss": 0.5526,
      "step": 9025
    },
    {
      "epoch": 0.27727091205111665,
      "grad_norm": 0.33430102467536926,
      "learning_rate": 1.9084125885823916e-05,
      "loss": 0.5873,
      "step": 9026
    },
    {
      "epoch": 0.2773016311860658,
      "grad_norm": 0.3474169969558716,
      "learning_rate": 1.9083923829122258e-05,
      "loss": 0.5442,
      "step": 9027
    },
    {
      "epoch": 0.27733235032101494,
      "grad_norm": 0.32017382979393005,
      "learning_rate": 1.908372175120446e-05,
      "loss": 0.5905,
      "step": 9028
    },
    {
      "epoch": 0.2773630694559641,
      "grad_norm": 0.4072002172470093,
      "learning_rate": 1.9083519652070997e-05,
      "loss": 0.5705,
      "step": 9029
    },
    {
      "epoch": 0.2773937885909133,
      "grad_norm": 0.34388968348503113,
      "learning_rate": 1.9083317531722338e-05,
      "loss": 0.6537,
      "step": 9030
    },
    {
      "epoch": 0.2774245077258624,
      "grad_norm": 0.3410652279853821,
      "learning_rate": 1.908311539015896e-05,
      "loss": 0.5391,
      "step": 9031
    },
    {
      "epoch": 0.2774552268608116,
      "grad_norm": 0.3265860676765442,
      "learning_rate": 1.9082913227381325e-05,
      "loss": 0.6763,
      "step": 9032
    },
    {
      "epoch": 0.27748594599576076,
      "grad_norm": 0.32773032784461975,
      "learning_rate": 1.908271104338992e-05,
      "loss": 0.5321,
      "step": 9033
    },
    {
      "epoch": 0.27751666513070994,
      "grad_norm": 0.36354589462280273,
      "learning_rate": 1.9082508838185205e-05,
      "loss": 0.5701,
      "step": 9034
    },
    {
      "epoch": 0.27754738426565906,
      "grad_norm": 0.3671620190143585,
      "learning_rate": 1.9082306611767657e-05,
      "loss": 0.5136,
      "step": 9035
    },
    {
      "epoch": 0.27757810340060823,
      "grad_norm": 0.35858261585235596,
      "learning_rate": 1.9082104364137745e-05,
      "loss": 0.5851,
      "step": 9036
    },
    {
      "epoch": 0.2776088225355574,
      "grad_norm": 0.3182668685913086,
      "learning_rate": 1.9081902095295946e-05,
      "loss": 0.6237,
      "step": 9037
    },
    {
      "epoch": 0.2776395416705066,
      "grad_norm": 0.3546692132949829,
      "learning_rate": 1.908169980524273e-05,
      "loss": 0.5636,
      "step": 9038
    },
    {
      "epoch": 0.2776702608054557,
      "grad_norm": 0.2975437045097351,
      "learning_rate": 1.9081497493978568e-05,
      "loss": 0.4691,
      "step": 9039
    },
    {
      "epoch": 0.2777009799404049,
      "grad_norm": 0.33980146050453186,
      "learning_rate": 1.9081295161503937e-05,
      "loss": 0.585,
      "step": 9040
    },
    {
      "epoch": 0.27773169907535405,
      "grad_norm": 0.3226301670074463,
      "learning_rate": 1.9081092807819307e-05,
      "loss": 0.6345,
      "step": 9041
    },
    {
      "epoch": 0.2777624182103032,
      "grad_norm": 0.3364366292953491,
      "learning_rate": 1.908089043292515e-05,
      "loss": 0.6068,
      "step": 9042
    },
    {
      "epoch": 0.27779313734525235,
      "grad_norm": 0.4512809216976166,
      "learning_rate": 1.908068803682194e-05,
      "loss": 0.5981,
      "step": 9043
    },
    {
      "epoch": 0.2778238564802015,
      "grad_norm": 0.35016995668411255,
      "learning_rate": 1.9080485619510147e-05,
      "loss": 0.5707,
      "step": 9044
    },
    {
      "epoch": 0.2778545756151507,
      "grad_norm": 0.34459540247917175,
      "learning_rate": 1.9080283180990247e-05,
      "loss": 0.559,
      "step": 9045
    },
    {
      "epoch": 0.2778852947500998,
      "grad_norm": 0.3512503504753113,
      "learning_rate": 1.908008072126271e-05,
      "loss": 0.5704,
      "step": 9046
    },
    {
      "epoch": 0.277916013885049,
      "grad_norm": 0.35759225487709045,
      "learning_rate": 1.907987824032801e-05,
      "loss": 0.5564,
      "step": 9047
    },
    {
      "epoch": 0.27794673301999817,
      "grad_norm": 0.4252570867538452,
      "learning_rate": 1.9079675738186623e-05,
      "loss": 0.5988,
      "step": 9048
    },
    {
      "epoch": 0.2779774521549473,
      "grad_norm": 0.33365559577941895,
      "learning_rate": 1.907947321483902e-05,
      "loss": 0.6829,
      "step": 9049
    },
    {
      "epoch": 0.27800817128989647,
      "grad_norm": 0.4178057312965393,
      "learning_rate": 1.907927067028567e-05,
      "loss": 0.5362,
      "step": 9050
    },
    {
      "epoch": 0.27803889042484564,
      "grad_norm": 0.3512328863143921,
      "learning_rate": 1.907906810452705e-05,
      "loss": 0.5708,
      "step": 9051
    },
    {
      "epoch": 0.2780696095597948,
      "grad_norm": 0.37863969802856445,
      "learning_rate": 1.907886551756363e-05,
      "loss": 0.5807,
      "step": 9052
    },
    {
      "epoch": 0.27810032869474394,
      "grad_norm": 0.3397274911403656,
      "learning_rate": 1.907866290939589e-05,
      "loss": 0.6099,
      "step": 9053
    },
    {
      "epoch": 0.2781310478296931,
      "grad_norm": 0.4564332365989685,
      "learning_rate": 1.9078460280024296e-05,
      "loss": 0.5756,
      "step": 9054
    },
    {
      "epoch": 0.2781617669646423,
      "grad_norm": 0.358132004737854,
      "learning_rate": 1.9078257629449325e-05,
      "loss": 0.5948,
      "step": 9055
    },
    {
      "epoch": 0.27819248609959146,
      "grad_norm": 0.3633950650691986,
      "learning_rate": 1.907805495767145e-05,
      "loss": 0.5391,
      "step": 9056
    },
    {
      "epoch": 0.2782232052345406,
      "grad_norm": 0.32616159319877625,
      "learning_rate": 1.9077852264691143e-05,
      "loss": 0.5877,
      "step": 9057
    },
    {
      "epoch": 0.27825392436948976,
      "grad_norm": 0.49297791719436646,
      "learning_rate": 1.9077649550508877e-05,
      "loss": 0.5723,
      "step": 9058
    },
    {
      "epoch": 0.27828464350443893,
      "grad_norm": 0.32946455478668213,
      "learning_rate": 1.907744681512513e-05,
      "loss": 0.6174,
      "step": 9059
    },
    {
      "epoch": 0.27831536263938805,
      "grad_norm": 0.39921310544013977,
      "learning_rate": 1.9077244058540366e-05,
      "loss": 0.5907,
      "step": 9060
    },
    {
      "epoch": 0.27834608177433723,
      "grad_norm": 0.3172428607940674,
      "learning_rate": 1.907704128075507e-05,
      "loss": 0.5873,
      "step": 9061
    },
    {
      "epoch": 0.2783768009092864,
      "grad_norm": 0.34898245334625244,
      "learning_rate": 1.907683848176971e-05,
      "loss": 0.5857,
      "step": 9062
    },
    {
      "epoch": 0.2784075200442356,
      "grad_norm": 0.398285448551178,
      "learning_rate": 1.907663566158476e-05,
      "loss": 0.5958,
      "step": 9063
    },
    {
      "epoch": 0.2784382391791847,
      "grad_norm": 0.3771199584007263,
      "learning_rate": 1.907643282020069e-05,
      "loss": 0.5921,
      "step": 9064
    },
    {
      "epoch": 0.2784689583141339,
      "grad_norm": 0.337539404630661,
      "learning_rate": 1.9076229957617975e-05,
      "loss": 0.6756,
      "step": 9065
    },
    {
      "epoch": 0.27849967744908305,
      "grad_norm": 0.3611900806427002,
      "learning_rate": 1.9076027073837094e-05,
      "loss": 0.5611,
      "step": 9066
    },
    {
      "epoch": 0.27853039658403217,
      "grad_norm": 0.31272998452186584,
      "learning_rate": 1.907582416885852e-05,
      "loss": 0.6608,
      "step": 9067
    },
    {
      "epoch": 0.27856111571898134,
      "grad_norm": 0.4112411439418793,
      "learning_rate": 1.9075621242682724e-05,
      "loss": 0.6188,
      "step": 9068
    },
    {
      "epoch": 0.2785918348539305,
      "grad_norm": 0.40089571475982666,
      "learning_rate": 1.907541829531018e-05,
      "loss": 0.5852,
      "step": 9069
    },
    {
      "epoch": 0.2786225539888797,
      "grad_norm": 0.3860073983669281,
      "learning_rate": 1.9075215326741365e-05,
      "loss": 0.6317,
      "step": 9070
    },
    {
      "epoch": 0.2786532731238288,
      "grad_norm": 0.3245793879032135,
      "learning_rate": 1.9075012336976746e-05,
      "loss": 0.5854,
      "step": 9071
    },
    {
      "epoch": 0.278683992258778,
      "grad_norm": 0.36706921458244324,
      "learning_rate": 1.9074809326016805e-05,
      "loss": 0.6567,
      "step": 9072
    },
    {
      "epoch": 0.27871471139372717,
      "grad_norm": 0.36660969257354736,
      "learning_rate": 1.9074606293862013e-05,
      "loss": 0.5101,
      "step": 9073
    },
    {
      "epoch": 0.2787454305286763,
      "grad_norm": 0.4670531451702118,
      "learning_rate": 1.9074403240512843e-05,
      "loss": 0.6072,
      "step": 9074
    },
    {
      "epoch": 0.27877614966362546,
      "grad_norm": 0.3610023558139801,
      "learning_rate": 1.907420016596977e-05,
      "loss": 0.5562,
      "step": 9075
    },
    {
      "epoch": 0.27880686879857464,
      "grad_norm": 0.3565497398376465,
      "learning_rate": 1.907399707023327e-05,
      "loss": 0.5818,
      "step": 9076
    },
    {
      "epoch": 0.2788375879335238,
      "grad_norm": 0.34848126769065857,
      "learning_rate": 1.907379395330382e-05,
      "loss": 0.5453,
      "step": 9077
    },
    {
      "epoch": 0.27886830706847293,
      "grad_norm": 0.3282102644443512,
      "learning_rate": 1.9073590815181885e-05,
      "loss": 0.5333,
      "step": 9078
    },
    {
      "epoch": 0.2788990262034221,
      "grad_norm": 0.3239019513130188,
      "learning_rate": 1.907338765586795e-05,
      "loss": 0.5996,
      "step": 9079
    },
    {
      "epoch": 0.2789297453383713,
      "grad_norm": 0.33595916628837585,
      "learning_rate": 1.9073184475362478e-05,
      "loss": 0.6391,
      "step": 9080
    },
    {
      "epoch": 0.27896046447332046,
      "grad_norm": 0.3324783444404602,
      "learning_rate": 1.9072981273665954e-05,
      "loss": 0.6015,
      "step": 9081
    },
    {
      "epoch": 0.2789911836082696,
      "grad_norm": 0.31574615836143494,
      "learning_rate": 1.9072778050778847e-05,
      "loss": 0.5889,
      "step": 9082
    },
    {
      "epoch": 0.27902190274321875,
      "grad_norm": 0.32440051436424255,
      "learning_rate": 1.9072574806701633e-05,
      "loss": 0.6434,
      "step": 9083
    },
    {
      "epoch": 0.27905262187816793,
      "grad_norm": 0.4100591838359833,
      "learning_rate": 1.9072371541434788e-05,
      "loss": 0.6162,
      "step": 9084
    },
    {
      "epoch": 0.27908334101311705,
      "grad_norm": 0.3961588144302368,
      "learning_rate": 1.9072168254978787e-05,
      "loss": 0.5467,
      "step": 9085
    },
    {
      "epoch": 0.2791140601480662,
      "grad_norm": 0.3792514503002167,
      "learning_rate": 1.9071964947334104e-05,
      "loss": 0.5919,
      "step": 9086
    },
    {
      "epoch": 0.2791447792830154,
      "grad_norm": 0.362362265586853,
      "learning_rate": 1.9071761618501208e-05,
      "loss": 0.5418,
      "step": 9087
    },
    {
      "epoch": 0.2791754984179646,
      "grad_norm": 0.38976141810417175,
      "learning_rate": 1.9071558268480585e-05,
      "loss": 0.6041,
      "step": 9088
    },
    {
      "epoch": 0.2792062175529137,
      "grad_norm": 0.36411556601524353,
      "learning_rate": 1.90713548972727e-05,
      "loss": 0.6148,
      "step": 9089
    },
    {
      "epoch": 0.27923693668786287,
      "grad_norm": 0.39533731341362,
      "learning_rate": 1.9071151504878034e-05,
      "loss": 0.5414,
      "step": 9090
    },
    {
      "epoch": 0.27926765582281204,
      "grad_norm": 0.3917321264743805,
      "learning_rate": 1.907094809129706e-05,
      "loss": 0.5736,
      "step": 9091
    },
    {
      "epoch": 0.27929837495776116,
      "grad_norm": 0.3691883385181427,
      "learning_rate": 1.9070744656530254e-05,
      "loss": 0.5602,
      "step": 9092
    },
    {
      "epoch": 0.27932909409271034,
      "grad_norm": 0.3628910481929779,
      "learning_rate": 1.9070541200578088e-05,
      "loss": 0.5404,
      "step": 9093
    },
    {
      "epoch": 0.2793598132276595,
      "grad_norm": 0.5084805488586426,
      "learning_rate": 1.9070337723441042e-05,
      "loss": 0.6108,
      "step": 9094
    },
    {
      "epoch": 0.2793905323626087,
      "grad_norm": 0.4648604393005371,
      "learning_rate": 1.9070134225119584e-05,
      "loss": 0.5258,
      "step": 9095
    },
    {
      "epoch": 0.2794212514975578,
      "grad_norm": 0.3662586510181427,
      "learning_rate": 1.90699307056142e-05,
      "loss": 0.5614,
      "step": 9096
    },
    {
      "epoch": 0.279451970632507,
      "grad_norm": 0.32525962591171265,
      "learning_rate": 1.9069727164925357e-05,
      "loss": 0.5242,
      "step": 9097
    },
    {
      "epoch": 0.27948268976745616,
      "grad_norm": 0.3515898585319519,
      "learning_rate": 1.9069523603053534e-05,
      "loss": 0.5638,
      "step": 9098
    },
    {
      "epoch": 0.27951340890240534,
      "grad_norm": 0.34382545948028564,
      "learning_rate": 1.9069320019999205e-05,
      "loss": 0.6133,
      "step": 9099
    },
    {
      "epoch": 0.27954412803735446,
      "grad_norm": 0.35474342107772827,
      "learning_rate": 1.9069116415762843e-05,
      "loss": 0.5615,
      "step": 9100
    },
    {
      "epoch": 0.27957484717230363,
      "grad_norm": 0.3720458149909973,
      "learning_rate": 1.9068912790344928e-05,
      "loss": 0.5355,
      "step": 9101
    },
    {
      "epoch": 0.2796055663072528,
      "grad_norm": 0.3140740394592285,
      "learning_rate": 1.9068709143745937e-05,
      "loss": 0.5605,
      "step": 9102
    },
    {
      "epoch": 0.2796362854422019,
      "grad_norm": 0.32804426550865173,
      "learning_rate": 1.906850547596634e-05,
      "loss": 0.6037,
      "step": 9103
    },
    {
      "epoch": 0.2796670045771511,
      "grad_norm": 0.34563273191452026,
      "learning_rate": 1.9068301787006613e-05,
      "loss": 0.5979,
      "step": 9104
    },
    {
      "epoch": 0.2796977237121003,
      "grad_norm": 0.6360843777656555,
      "learning_rate": 1.9068098076867233e-05,
      "loss": 0.5531,
      "step": 9105
    },
    {
      "epoch": 0.27972844284704945,
      "grad_norm": 0.3664611876010895,
      "learning_rate": 1.906789434554868e-05,
      "loss": 0.5393,
      "step": 9106
    },
    {
      "epoch": 0.27975916198199857,
      "grad_norm": 0.33465975522994995,
      "learning_rate": 1.9067690593051426e-05,
      "loss": 0.6122,
      "step": 9107
    },
    {
      "epoch": 0.27978988111694775,
      "grad_norm": 0.3548470139503479,
      "learning_rate": 1.9067486819375948e-05,
      "loss": 0.6282,
      "step": 9108
    },
    {
      "epoch": 0.2798206002518969,
      "grad_norm": 0.33826085925102234,
      "learning_rate": 1.906728302452272e-05,
      "loss": 0.6089,
      "step": 9109
    },
    {
      "epoch": 0.27985131938684604,
      "grad_norm": 0.36325445771217346,
      "learning_rate": 1.906707920849222e-05,
      "loss": 0.6067,
      "step": 9110
    },
    {
      "epoch": 0.2798820385217952,
      "grad_norm": 0.3527682423591614,
      "learning_rate": 1.9066875371284922e-05,
      "loss": 0.5502,
      "step": 9111
    },
    {
      "epoch": 0.2799127576567444,
      "grad_norm": 0.5144418478012085,
      "learning_rate": 1.90666715129013e-05,
      "loss": 0.6132,
      "step": 9112
    },
    {
      "epoch": 0.27994347679169357,
      "grad_norm": 0.4337041676044464,
      "learning_rate": 1.906646763334184e-05,
      "loss": 0.5602,
      "step": 9113
    },
    {
      "epoch": 0.2799741959266427,
      "grad_norm": 0.41205838322639465,
      "learning_rate": 1.906626373260701e-05,
      "loss": 0.6153,
      "step": 9114
    },
    {
      "epoch": 0.28000491506159186,
      "grad_norm": 0.3950354754924774,
      "learning_rate": 1.9066059810697285e-05,
      "loss": 0.6055,
      "step": 9115
    },
    {
      "epoch": 0.28003563419654104,
      "grad_norm": 0.37157151103019714,
      "learning_rate": 1.9065855867613148e-05,
      "loss": 0.6045,
      "step": 9116
    },
    {
      "epoch": 0.28006635333149016,
      "grad_norm": 0.5323193073272705,
      "learning_rate": 1.906565190335507e-05,
      "loss": 0.5784,
      "step": 9117
    },
    {
      "epoch": 0.28009707246643933,
      "grad_norm": 0.3454533517360687,
      "learning_rate": 1.9065447917923527e-05,
      "loss": 0.5878,
      "step": 9118
    },
    {
      "epoch": 0.2801277916013885,
      "grad_norm": 0.38236916065216064,
      "learning_rate": 1.9065243911319e-05,
      "loss": 0.5991,
      "step": 9119
    },
    {
      "epoch": 0.2801585107363377,
      "grad_norm": 0.3339017629623413,
      "learning_rate": 1.9065039883541963e-05,
      "loss": 0.6436,
      "step": 9120
    },
    {
      "epoch": 0.2801892298712868,
      "grad_norm": 0.3213183581829071,
      "learning_rate": 1.9064835834592886e-05,
      "loss": 0.4852,
      "step": 9121
    },
    {
      "epoch": 0.280219949006236,
      "grad_norm": 0.3528851866722107,
      "learning_rate": 1.9064631764472258e-05,
      "loss": 0.5822,
      "step": 9122
    },
    {
      "epoch": 0.28025066814118516,
      "grad_norm": 0.37559354305267334,
      "learning_rate": 1.9064427673180547e-05,
      "loss": 0.5836,
      "step": 9123
    },
    {
      "epoch": 0.28028138727613433,
      "grad_norm": 0.3790963292121887,
      "learning_rate": 1.9064223560718233e-05,
      "loss": 0.5956,
      "step": 9124
    },
    {
      "epoch": 0.28031210641108345,
      "grad_norm": 0.36210086941719055,
      "learning_rate": 1.9064019427085794e-05,
      "loss": 0.5997,
      "step": 9125
    },
    {
      "epoch": 0.2803428255460326,
      "grad_norm": 0.37444207072257996,
      "learning_rate": 1.90638152722837e-05,
      "loss": 0.6471,
      "step": 9126
    },
    {
      "epoch": 0.2803735446809818,
      "grad_norm": 0.36174386739730835,
      "learning_rate": 1.906361109631244e-05,
      "loss": 0.5862,
      "step": 9127
    },
    {
      "epoch": 0.2804042638159309,
      "grad_norm": 0.38481345772743225,
      "learning_rate": 1.9063406899172478e-05,
      "loss": 0.663,
      "step": 9128
    },
    {
      "epoch": 0.2804349829508801,
      "grad_norm": 0.32650884985923767,
      "learning_rate": 1.9063202680864293e-05,
      "loss": 0.5601,
      "step": 9129
    },
    {
      "epoch": 0.28046570208582927,
      "grad_norm": 0.31207475066185,
      "learning_rate": 1.906299844138837e-05,
      "loss": 0.571,
      "step": 9130
    },
    {
      "epoch": 0.28049642122077845,
      "grad_norm": 0.3309776782989502,
      "learning_rate": 1.906279418074518e-05,
      "loss": 0.5732,
      "step": 9131
    },
    {
      "epoch": 0.28052714035572757,
      "grad_norm": 0.3705063462257385,
      "learning_rate": 1.90625898989352e-05,
      "loss": 0.5928,
      "step": 9132
    },
    {
      "epoch": 0.28055785949067674,
      "grad_norm": 0.31914445757865906,
      "learning_rate": 1.906238559595891e-05,
      "loss": 0.5602,
      "step": 9133
    },
    {
      "epoch": 0.2805885786256259,
      "grad_norm": 0.3247717022895813,
      "learning_rate": 1.9062181271816783e-05,
      "loss": 0.488,
      "step": 9134
    },
    {
      "epoch": 0.28061929776057504,
      "grad_norm": 0.4837476909160614,
      "learning_rate": 1.9061976926509302e-05,
      "loss": 0.5393,
      "step": 9135
    },
    {
      "epoch": 0.2806500168955242,
      "grad_norm": 0.36529341340065,
      "learning_rate": 1.906177256003694e-05,
      "loss": 0.5759,
      "step": 9136
    },
    {
      "epoch": 0.2806807360304734,
      "grad_norm": 0.3611502945423126,
      "learning_rate": 1.9061568172400176e-05,
      "loss": 0.5475,
      "step": 9137
    },
    {
      "epoch": 0.28071145516542256,
      "grad_norm": 0.308287113904953,
      "learning_rate": 1.9061363763599486e-05,
      "loss": 0.5794,
      "step": 9138
    },
    {
      "epoch": 0.2807421743003717,
      "grad_norm": 0.33967965841293335,
      "learning_rate": 1.9061159333635345e-05,
      "loss": 0.5654,
      "step": 9139
    },
    {
      "epoch": 0.28077289343532086,
      "grad_norm": 0.32252803444862366,
      "learning_rate": 1.906095488250824e-05,
      "loss": 0.638,
      "step": 9140
    },
    {
      "epoch": 0.28080361257027003,
      "grad_norm": 0.3256196975708008,
      "learning_rate": 1.9060750410218634e-05,
      "loss": 0.6142,
      "step": 9141
    },
    {
      "epoch": 0.28083433170521915,
      "grad_norm": 0.36493703722953796,
      "learning_rate": 1.906054591676702e-05,
      "loss": 0.6018,
      "step": 9142
    },
    {
      "epoch": 0.28086505084016833,
      "grad_norm": 0.39330241084098816,
      "learning_rate": 1.9060341402153866e-05,
      "loss": 0.6642,
      "step": 9143
    },
    {
      "epoch": 0.2808957699751175,
      "grad_norm": 0.3678169250488281,
      "learning_rate": 1.906013686637965e-05,
      "loss": 0.5573,
      "step": 9144
    },
    {
      "epoch": 0.2809264891100667,
      "grad_norm": 0.37946817278862,
      "learning_rate": 1.905993230944485e-05,
      "loss": 0.5951,
      "step": 9145
    },
    {
      "epoch": 0.2809572082450158,
      "grad_norm": 0.40081921219825745,
      "learning_rate": 1.905972773134995e-05,
      "loss": 0.5473,
      "step": 9146
    },
    {
      "epoch": 0.280987927379965,
      "grad_norm": 1.0911986827850342,
      "learning_rate": 1.905952313209542e-05,
      "loss": 0.4654,
      "step": 9147
    },
    {
      "epoch": 0.28101864651491415,
      "grad_norm": 0.3236619830131531,
      "learning_rate": 1.9059318511681743e-05,
      "loss": 0.5285,
      "step": 9148
    },
    {
      "epoch": 0.2810493656498633,
      "grad_norm": 0.3519318997859955,
      "learning_rate": 1.9059113870109395e-05,
      "loss": 0.5001,
      "step": 9149
    },
    {
      "epoch": 0.28108008478481245,
      "grad_norm": 0.3407547175884247,
      "learning_rate": 1.9058909207378852e-05,
      "loss": 0.5813,
      "step": 9150
    },
    {
      "epoch": 0.2811108039197616,
      "grad_norm": 0.5294622778892517,
      "learning_rate": 1.9058704523490595e-05,
      "loss": 0.5969,
      "step": 9151
    },
    {
      "epoch": 0.2811415230547108,
      "grad_norm": 0.3187311887741089,
      "learning_rate": 1.9058499818445102e-05,
      "loss": 0.5426,
      "step": 9152
    },
    {
      "epoch": 0.2811722421896599,
      "grad_norm": 0.3913319408893585,
      "learning_rate": 1.905829509224285e-05,
      "loss": 0.5602,
      "step": 9153
    },
    {
      "epoch": 0.2812029613246091,
      "grad_norm": 0.3923867642879486,
      "learning_rate": 1.9058090344884314e-05,
      "loss": 0.6527,
      "step": 9154
    },
    {
      "epoch": 0.28123368045955827,
      "grad_norm": 0.307500958442688,
      "learning_rate": 1.9057885576369978e-05,
      "loss": 0.5325,
      "step": 9155
    },
    {
      "epoch": 0.28126439959450744,
      "grad_norm": 0.37111952900886536,
      "learning_rate": 1.9057680786700316e-05,
      "loss": 0.5729,
      "step": 9156
    },
    {
      "epoch": 0.28129511872945656,
      "grad_norm": 0.3090234398841858,
      "learning_rate": 1.905747597587581e-05,
      "loss": 0.5922,
      "step": 9157
    },
    {
      "epoch": 0.28132583786440574,
      "grad_norm": 0.35042232275009155,
      "learning_rate": 1.9057271143896937e-05,
      "loss": 0.5552,
      "step": 9158
    },
    {
      "epoch": 0.2813565569993549,
      "grad_norm": 0.38807666301727295,
      "learning_rate": 1.9057066290764172e-05,
      "loss": 0.5498,
      "step": 9159
    },
    {
      "epoch": 0.28138727613430403,
      "grad_norm": 0.3417232036590576,
      "learning_rate": 1.9056861416477996e-05,
      "loss": 0.5724,
      "step": 9160
    },
    {
      "epoch": 0.2814179952692532,
      "grad_norm": 0.3571210205554962,
      "learning_rate": 1.905665652103889e-05,
      "loss": 0.564,
      "step": 9161
    },
    {
      "epoch": 0.2814487144042024,
      "grad_norm": 0.3851800560951233,
      "learning_rate": 1.905645160444733e-05,
      "loss": 0.6106,
      "step": 9162
    },
    {
      "epoch": 0.28147943353915156,
      "grad_norm": 0.34985366463661194,
      "learning_rate": 1.905624666670379e-05,
      "loss": 0.5324,
      "step": 9163
    },
    {
      "epoch": 0.2815101526741007,
      "grad_norm": 0.6735703945159912,
      "learning_rate": 1.905604170780876e-05,
      "loss": 0.6053,
      "step": 9164
    },
    {
      "epoch": 0.28154087180904985,
      "grad_norm": 0.36200132966041565,
      "learning_rate": 1.905583672776271e-05,
      "loss": 0.5965,
      "step": 9165
    },
    {
      "epoch": 0.28157159094399903,
      "grad_norm": 0.38071003556251526,
      "learning_rate": 1.9055631726566118e-05,
      "loss": 0.5241,
      "step": 9166
    },
    {
      "epoch": 0.2816023100789482,
      "grad_norm": 0.3446987569332123,
      "learning_rate": 1.9055426704219467e-05,
      "loss": 0.5087,
      "step": 9167
    },
    {
      "epoch": 0.2816330292138973,
      "grad_norm": 0.339468777179718,
      "learning_rate": 1.9055221660723237e-05,
      "loss": 0.584,
      "step": 9168
    },
    {
      "epoch": 0.2816637483488465,
      "grad_norm": 0.36629000306129456,
      "learning_rate": 1.9055016596077905e-05,
      "loss": 0.5384,
      "step": 9169
    },
    {
      "epoch": 0.2816944674837957,
      "grad_norm": 0.32118692994117737,
      "learning_rate": 1.9054811510283943e-05,
      "loss": 0.5814,
      "step": 9170
    },
    {
      "epoch": 0.2817251866187448,
      "grad_norm": 0.34915217757225037,
      "learning_rate": 1.905460640334184e-05,
      "loss": 0.5376,
      "step": 9171
    },
    {
      "epoch": 0.28175590575369397,
      "grad_norm": 0.37165379524230957,
      "learning_rate": 1.9054401275252075e-05,
      "loss": 0.5813,
      "step": 9172
    },
    {
      "epoch": 0.28178662488864314,
      "grad_norm": 0.3591201603412628,
      "learning_rate": 1.905419612601512e-05,
      "loss": 0.528,
      "step": 9173
    },
    {
      "epoch": 0.2818173440235923,
      "grad_norm": 0.32323089241981506,
      "learning_rate": 1.905399095563146e-05,
      "loss": 0.5508,
      "step": 9174
    },
    {
      "epoch": 0.28184806315854144,
      "grad_norm": 0.36700931191444397,
      "learning_rate": 1.905378576410157e-05,
      "loss": 0.6019,
      "step": 9175
    },
    {
      "epoch": 0.2818787822934906,
      "grad_norm": 0.34973546862602234,
      "learning_rate": 1.9053580551425928e-05,
      "loss": 0.592,
      "step": 9176
    },
    {
      "epoch": 0.2819095014284398,
      "grad_norm": 0.3601730763912201,
      "learning_rate": 1.905337531760502e-05,
      "loss": 0.6419,
      "step": 9177
    },
    {
      "epoch": 0.2819402205633889,
      "grad_norm": 1.3510164022445679,
      "learning_rate": 1.905317006263932e-05,
      "loss": 0.5087,
      "step": 9178
    },
    {
      "epoch": 0.2819709396983381,
      "grad_norm": 0.39943233132362366,
      "learning_rate": 1.905296478652931e-05,
      "loss": 0.5275,
      "step": 9179
    },
    {
      "epoch": 0.28200165883328726,
      "grad_norm": 0.43816235661506653,
      "learning_rate": 1.905275948927547e-05,
      "loss": 0.6043,
      "step": 9180
    },
    {
      "epoch": 0.28203237796823644,
      "grad_norm": 0.35390520095825195,
      "learning_rate": 1.9052554170878274e-05,
      "loss": 0.6551,
      "step": 9181
    },
    {
      "epoch": 0.28206309710318556,
      "grad_norm": 0.3542981743812561,
      "learning_rate": 1.905234883133821e-05,
      "loss": 0.5695,
      "step": 9182
    },
    {
      "epoch": 0.28209381623813473,
      "grad_norm": 0.331887811422348,
      "learning_rate": 1.9052143470655752e-05,
      "loss": 0.6555,
      "step": 9183
    },
    {
      "epoch": 0.2821245353730839,
      "grad_norm": 0.3267354667186737,
      "learning_rate": 1.9051938088831378e-05,
      "loss": 0.6066,
      "step": 9184
    },
    {
      "epoch": 0.282155254508033,
      "grad_norm": 0.3515908718109131,
      "learning_rate": 1.9051732685865573e-05,
      "loss": 0.6652,
      "step": 9185
    },
    {
      "epoch": 0.2821859736429822,
      "grad_norm": 0.3333424925804138,
      "learning_rate": 1.905152726175881e-05,
      "loss": 0.566,
      "step": 9186
    },
    {
      "epoch": 0.2822166927779314,
      "grad_norm": 0.3293896019458771,
      "learning_rate": 1.9051321816511578e-05,
      "loss": 0.5469,
      "step": 9187
    },
    {
      "epoch": 0.28224741191288055,
      "grad_norm": 0.33662623167037964,
      "learning_rate": 1.905111635012435e-05,
      "loss": 0.5345,
      "step": 9188
    },
    {
      "epoch": 0.2822781310478297,
      "grad_norm": 0.35640814900398254,
      "learning_rate": 1.9050910862597606e-05,
      "loss": 0.5894,
      "step": 9189
    },
    {
      "epoch": 0.28230885018277885,
      "grad_norm": 0.3821048438549042,
      "learning_rate": 1.905070535393183e-05,
      "loss": 0.5653,
      "step": 9190
    },
    {
      "epoch": 0.282339569317728,
      "grad_norm": 0.333499938249588,
      "learning_rate": 1.90504998241275e-05,
      "loss": 0.554,
      "step": 9191
    },
    {
      "epoch": 0.2823702884526772,
      "grad_norm": 0.3365623354911804,
      "learning_rate": 1.9050294273185093e-05,
      "loss": 0.6299,
      "step": 9192
    },
    {
      "epoch": 0.2824010075876263,
      "grad_norm": 0.4478514492511749,
      "learning_rate": 1.905008870110509e-05,
      "loss": 0.6032,
      "step": 9193
    },
    {
      "epoch": 0.2824317267225755,
      "grad_norm": 0.3897596001625061,
      "learning_rate": 1.9049883107887978e-05,
      "loss": 0.5846,
      "step": 9194
    },
    {
      "epoch": 0.28246244585752467,
      "grad_norm": 1.0069001913070679,
      "learning_rate": 1.9049677493534228e-05,
      "loss": 0.5139,
      "step": 9195
    },
    {
      "epoch": 0.2824931649924738,
      "grad_norm": 0.31660154461860657,
      "learning_rate": 1.904947185804433e-05,
      "loss": 0.5878,
      "step": 9196
    },
    {
      "epoch": 0.28252388412742296,
      "grad_norm": 0.36523911356925964,
      "learning_rate": 1.904926620141875e-05,
      "loss": 0.5316,
      "step": 9197
    },
    {
      "epoch": 0.28255460326237214,
      "grad_norm": 0.34745100140571594,
      "learning_rate": 1.904906052365798e-05,
      "loss": 0.5766,
      "step": 9198
    },
    {
      "epoch": 0.2825853223973213,
      "grad_norm": 0.3421125113964081,
      "learning_rate": 1.90488548247625e-05,
      "loss": 0.6279,
      "step": 9199
    },
    {
      "epoch": 0.28261604153227043,
      "grad_norm": 0.36627262830734253,
      "learning_rate": 1.9048649104732785e-05,
      "loss": 0.6297,
      "step": 9200
    },
    {
      "epoch": 0.2826467606672196,
      "grad_norm": 0.3289797008037567,
      "learning_rate": 1.904844336356932e-05,
      "loss": 0.5045,
      "step": 9201
    },
    {
      "epoch": 0.2826774798021688,
      "grad_norm": 0.3827930986881256,
      "learning_rate": 1.9048237601272585e-05,
      "loss": 0.6533,
      "step": 9202
    },
    {
      "epoch": 0.2827081989371179,
      "grad_norm": 0.39602360129356384,
      "learning_rate": 1.9048031817843053e-05,
      "loss": 0.5575,
      "step": 9203
    },
    {
      "epoch": 0.2827389180720671,
      "grad_norm": 0.3208671808242798,
      "learning_rate": 1.9047826013281218e-05,
      "loss": 0.4543,
      "step": 9204
    },
    {
      "epoch": 0.28276963720701626,
      "grad_norm": 0.3140404522418976,
      "learning_rate": 1.9047620187587547e-05,
      "loss": 0.5448,
      "step": 9205
    },
    {
      "epoch": 0.28280035634196543,
      "grad_norm": 0.3388734459877014,
      "learning_rate": 1.9047414340762532e-05,
      "loss": 0.5414,
      "step": 9206
    },
    {
      "epoch": 0.28283107547691455,
      "grad_norm": 0.3525868356227875,
      "learning_rate": 1.9047208472806647e-05,
      "loss": 0.5943,
      "step": 9207
    },
    {
      "epoch": 0.2828617946118637,
      "grad_norm": 0.35683268308639526,
      "learning_rate": 1.9047002583720373e-05,
      "loss": 0.5465,
      "step": 9208
    },
    {
      "epoch": 0.2828925137468129,
      "grad_norm": 0.34637200832366943,
      "learning_rate": 1.9046796673504195e-05,
      "loss": 0.5505,
      "step": 9209
    },
    {
      "epoch": 0.2829232328817621,
      "grad_norm": 0.404055655002594,
      "learning_rate": 1.904659074215859e-05,
      "loss": 0.5078,
      "step": 9210
    },
    {
      "epoch": 0.2829539520167112,
      "grad_norm": 0.3247663378715515,
      "learning_rate": 1.9046384789684044e-05,
      "loss": 0.499,
      "step": 9211
    },
    {
      "epoch": 0.28298467115166037,
      "grad_norm": 0.3425362706184387,
      "learning_rate": 1.9046178816081032e-05,
      "loss": 0.5904,
      "step": 9212
    },
    {
      "epoch": 0.28301539028660955,
      "grad_norm": 0.35069555044174194,
      "learning_rate": 1.9045972821350034e-05,
      "loss": 0.5522,
      "step": 9213
    },
    {
      "epoch": 0.28304610942155867,
      "grad_norm": 0.33017054200172424,
      "learning_rate": 1.904576680549154e-05,
      "loss": 0.5912,
      "step": 9214
    },
    {
      "epoch": 0.28307682855650784,
      "grad_norm": 0.3653112053871155,
      "learning_rate": 1.9045560768506024e-05,
      "loss": 0.5874,
      "step": 9215
    },
    {
      "epoch": 0.283107547691457,
      "grad_norm": 0.40580424666404724,
      "learning_rate": 1.904535471039397e-05,
      "loss": 0.536,
      "step": 9216
    },
    {
      "epoch": 0.2831382668264062,
      "grad_norm": 0.3198440670967102,
      "learning_rate": 1.9045148631155856e-05,
      "loss": 0.6434,
      "step": 9217
    },
    {
      "epoch": 0.2831689859613553,
      "grad_norm": 0.35780346393585205,
      "learning_rate": 1.904494253079217e-05,
      "loss": 0.6613,
      "step": 9218
    },
    {
      "epoch": 0.2831997050963045,
      "grad_norm": 0.337893545627594,
      "learning_rate": 1.9044736409303385e-05,
      "loss": 0.6066,
      "step": 9219
    },
    {
      "epoch": 0.28323042423125366,
      "grad_norm": 0.32627835869789124,
      "learning_rate": 1.904453026668999e-05,
      "loss": 0.6466,
      "step": 9220
    },
    {
      "epoch": 0.2832611433662028,
      "grad_norm": 0.3313881456851959,
      "learning_rate": 1.904432410295246e-05,
      "loss": 0.5575,
      "step": 9221
    },
    {
      "epoch": 0.28329186250115196,
      "grad_norm": 0.4146954417228699,
      "learning_rate": 1.904411791809128e-05,
      "loss": 0.573,
      "step": 9222
    },
    {
      "epoch": 0.28332258163610113,
      "grad_norm": 0.38519003987312317,
      "learning_rate": 1.9043911712106927e-05,
      "loss": 0.559,
      "step": 9223
    },
    {
      "epoch": 0.2833533007710503,
      "grad_norm": 0.35593336820602417,
      "learning_rate": 1.9043705484999894e-05,
      "loss": 0.6773,
      "step": 9224
    },
    {
      "epoch": 0.28338401990599943,
      "grad_norm": 0.3379130959510803,
      "learning_rate": 1.904349923677065e-05,
      "loss": 0.6276,
      "step": 9225
    },
    {
      "epoch": 0.2834147390409486,
      "grad_norm": 0.3275161385536194,
      "learning_rate": 1.9043292967419683e-05,
      "loss": 0.5958,
      "step": 9226
    },
    {
      "epoch": 0.2834454581758978,
      "grad_norm": 0.34059518575668335,
      "learning_rate": 1.9043086676947477e-05,
      "loss": 0.5753,
      "step": 9227
    },
    {
      "epoch": 0.2834761773108469,
      "grad_norm": 0.3282456696033478,
      "learning_rate": 1.9042880365354505e-05,
      "loss": 0.5503,
      "step": 9228
    },
    {
      "epoch": 0.2835068964457961,
      "grad_norm": 0.3477804958820343,
      "learning_rate": 1.904267403264126e-05,
      "loss": 0.5565,
      "step": 9229
    },
    {
      "epoch": 0.28353761558074525,
      "grad_norm": 0.36641037464141846,
      "learning_rate": 1.9042467678808215e-05,
      "loss": 0.4992,
      "step": 9230
    },
    {
      "epoch": 0.2835683347156944,
      "grad_norm": 0.3428441286087036,
      "learning_rate": 1.9042261303855857e-05,
      "loss": 0.5274,
      "step": 9231
    },
    {
      "epoch": 0.28359905385064355,
      "grad_norm": 0.35292333364486694,
      "learning_rate": 1.9042054907784664e-05,
      "loss": 0.6198,
      "step": 9232
    },
    {
      "epoch": 0.2836297729855927,
      "grad_norm": 0.41114139556884766,
      "learning_rate": 1.904184849059512e-05,
      "loss": 0.5293,
      "step": 9233
    },
    {
      "epoch": 0.2836604921205419,
      "grad_norm": 0.32805487513542175,
      "learning_rate": 1.904164205228771e-05,
      "loss": 0.5652,
      "step": 9234
    },
    {
      "epoch": 0.28369121125549107,
      "grad_norm": 0.8303053379058838,
      "learning_rate": 1.9041435592862913e-05,
      "loss": 0.5233,
      "step": 9235
    },
    {
      "epoch": 0.2837219303904402,
      "grad_norm": 0.36536163091659546,
      "learning_rate": 1.904122911232121e-05,
      "loss": 0.6481,
      "step": 9236
    },
    {
      "epoch": 0.28375264952538937,
      "grad_norm": 0.4073179364204407,
      "learning_rate": 1.9041022610663087e-05,
      "loss": 0.6435,
      "step": 9237
    },
    {
      "epoch": 0.28378336866033854,
      "grad_norm": 0.39240485429763794,
      "learning_rate": 1.9040816087889022e-05,
      "loss": 0.6058,
      "step": 9238
    },
    {
      "epoch": 0.28381408779528766,
      "grad_norm": 0.3746502697467804,
      "learning_rate": 1.90406095439995e-05,
      "loss": 0.6221,
      "step": 9239
    },
    {
      "epoch": 0.28384480693023684,
      "grad_norm": 0.34633976221084595,
      "learning_rate": 1.9040402978995006e-05,
      "loss": 0.5887,
      "step": 9240
    },
    {
      "epoch": 0.283875526065186,
      "grad_norm": 0.3711487650871277,
      "learning_rate": 1.9040196392876016e-05,
      "loss": 0.5934,
      "step": 9241
    },
    {
      "epoch": 0.2839062452001352,
      "grad_norm": 0.36307963728904724,
      "learning_rate": 1.903998978564302e-05,
      "loss": 0.5861,
      "step": 9242
    },
    {
      "epoch": 0.2839369643350843,
      "grad_norm": 0.3704046607017517,
      "learning_rate": 1.9039783157296492e-05,
      "loss": 0.579,
      "step": 9243
    },
    {
      "epoch": 0.2839676834700335,
      "grad_norm": 0.6482707858085632,
      "learning_rate": 1.903957650783692e-05,
      "loss": 0.7307,
      "step": 9244
    },
    {
      "epoch": 0.28399840260498266,
      "grad_norm": 0.32211390137672424,
      "learning_rate": 1.9039369837264785e-05,
      "loss": 0.5432,
      "step": 9245
    },
    {
      "epoch": 0.2840291217399318,
      "grad_norm": 0.33078062534332275,
      "learning_rate": 1.9039163145580574e-05,
      "loss": 0.525,
      "step": 9246
    },
    {
      "epoch": 0.28405984087488095,
      "grad_norm": 0.3394846022129059,
      "learning_rate": 1.9038956432784764e-05,
      "loss": 0.6028,
      "step": 9247
    },
    {
      "epoch": 0.28409056000983013,
      "grad_norm": 0.4098581373691559,
      "learning_rate": 1.903874969887784e-05,
      "loss": 0.6213,
      "step": 9248
    },
    {
      "epoch": 0.2841212791447793,
      "grad_norm": 0.3759462535381317,
      "learning_rate": 1.9038542943860284e-05,
      "loss": 0.5343,
      "step": 9249
    },
    {
      "epoch": 0.2841519982797284,
      "grad_norm": 0.3840775191783905,
      "learning_rate": 1.903833616773258e-05,
      "loss": 0.545,
      "step": 9250
    },
    {
      "epoch": 0.2841827174146776,
      "grad_norm": 0.3568432629108429,
      "learning_rate": 1.9038129370495212e-05,
      "loss": 0.5957,
      "step": 9251
    },
    {
      "epoch": 0.2842134365496268,
      "grad_norm": 0.3490675687789917,
      "learning_rate": 1.9037922552148662e-05,
      "loss": 0.5988,
      "step": 9252
    },
    {
      "epoch": 0.28424415568457595,
      "grad_norm": 0.35074281692504883,
      "learning_rate": 1.9037715712693413e-05,
      "loss": 0.5567,
      "step": 9253
    },
    {
      "epoch": 0.28427487481952507,
      "grad_norm": 0.3904297947883606,
      "learning_rate": 1.9037508852129948e-05,
      "loss": 0.5855,
      "step": 9254
    },
    {
      "epoch": 0.28430559395447424,
      "grad_norm": 0.3398498296737671,
      "learning_rate": 1.9037301970458747e-05,
      "loss": 0.6413,
      "step": 9255
    },
    {
      "epoch": 0.2843363130894234,
      "grad_norm": 0.35571521520614624,
      "learning_rate": 1.9037095067680295e-05,
      "loss": 0.6853,
      "step": 9256
    },
    {
      "epoch": 0.28436703222437254,
      "grad_norm": 0.38996225595474243,
      "learning_rate": 1.903688814379508e-05,
      "loss": 0.6284,
      "step": 9257
    },
    {
      "epoch": 0.2843977513593217,
      "grad_norm": 0.33855849504470825,
      "learning_rate": 1.903668119880358e-05,
      "loss": 0.6221,
      "step": 9258
    },
    {
      "epoch": 0.2844284704942709,
      "grad_norm": 0.3115846812725067,
      "learning_rate": 1.903647423270628e-05,
      "loss": 0.6095,
      "step": 9259
    },
    {
      "epoch": 0.28445918962922007,
      "grad_norm": 0.3606906235218048,
      "learning_rate": 1.9036267245503666e-05,
      "loss": 0.5904,
      "step": 9260
    },
    {
      "epoch": 0.2844899087641692,
      "grad_norm": 0.33507227897644043,
      "learning_rate": 1.9036060237196215e-05,
      "loss": 0.6039,
      "step": 9261
    },
    {
      "epoch": 0.28452062789911836,
      "grad_norm": 0.5059760808944702,
      "learning_rate": 1.9035853207784412e-05,
      "loss": 0.4953,
      "step": 9262
    },
    {
      "epoch": 0.28455134703406754,
      "grad_norm": 0.35479697585105896,
      "learning_rate": 1.903564615726875e-05,
      "loss": 0.5756,
      "step": 9263
    },
    {
      "epoch": 0.28458206616901666,
      "grad_norm": 0.6511971950531006,
      "learning_rate": 1.9035439085649702e-05,
      "loss": 0.5652,
      "step": 9264
    },
    {
      "epoch": 0.28461278530396583,
      "grad_norm": 0.3750301003456116,
      "learning_rate": 1.9035231992927757e-05,
      "loss": 0.6148,
      "step": 9265
    },
    {
      "epoch": 0.284643504438915,
      "grad_norm": 0.3578222692012787,
      "learning_rate": 1.9035024879103392e-05,
      "loss": 0.5647,
      "step": 9266
    },
    {
      "epoch": 0.2846742235738642,
      "grad_norm": 0.3476320505142212,
      "learning_rate": 1.90348177441771e-05,
      "loss": 0.6066,
      "step": 9267
    },
    {
      "epoch": 0.2847049427088133,
      "grad_norm": 0.35508644580841064,
      "learning_rate": 1.9034610588149354e-05,
      "loss": 0.5753,
      "step": 9268
    },
    {
      "epoch": 0.2847356618437625,
      "grad_norm": 0.3461879789829254,
      "learning_rate": 1.903440341102065e-05,
      "loss": 0.569,
      "step": 9269
    },
    {
      "epoch": 0.28476638097871165,
      "grad_norm": 0.3182808458805084,
      "learning_rate": 1.9034196212791465e-05,
      "loss": 0.5471,
      "step": 9270
    },
    {
      "epoch": 0.2847971001136608,
      "grad_norm": 0.37409618496894836,
      "learning_rate": 1.903398899346228e-05,
      "loss": 0.614,
      "step": 9271
    },
    {
      "epoch": 0.28482781924860995,
      "grad_norm": 0.3373118042945862,
      "learning_rate": 1.9033781753033587e-05,
      "loss": 0.5307,
      "step": 9272
    },
    {
      "epoch": 0.2848585383835591,
      "grad_norm": 0.3816783130168915,
      "learning_rate": 1.9033574491505863e-05,
      "loss": 0.5855,
      "step": 9273
    },
    {
      "epoch": 0.2848892575185083,
      "grad_norm": 0.4373297393321991,
      "learning_rate": 1.9033367208879598e-05,
      "loss": 0.5764,
      "step": 9274
    },
    {
      "epoch": 0.2849199766534574,
      "grad_norm": 0.39109355211257935,
      "learning_rate": 1.903315990515527e-05,
      "loss": 0.5369,
      "step": 9275
    },
    {
      "epoch": 0.2849506957884066,
      "grad_norm": 0.34315603971481323,
      "learning_rate": 1.903295258033337e-05,
      "loss": 0.5672,
      "step": 9276
    },
    {
      "epoch": 0.28498141492335577,
      "grad_norm": 0.35574328899383545,
      "learning_rate": 1.9032745234414374e-05,
      "loss": 0.6326,
      "step": 9277
    },
    {
      "epoch": 0.28501213405830494,
      "grad_norm": 0.7355232834815979,
      "learning_rate": 1.9032537867398773e-05,
      "loss": 0.4883,
      "step": 9278
    },
    {
      "epoch": 0.28504285319325406,
      "grad_norm": 0.325614333152771,
      "learning_rate": 1.903233047928705e-05,
      "loss": 0.5696,
      "step": 9279
    },
    {
      "epoch": 0.28507357232820324,
      "grad_norm": 0.35045966506004333,
      "learning_rate": 1.9032123070079684e-05,
      "loss": 0.5879,
      "step": 9280
    },
    {
      "epoch": 0.2851042914631524,
      "grad_norm": 0.32836273312568665,
      "learning_rate": 1.903191563977717e-05,
      "loss": 0.5151,
      "step": 9281
    },
    {
      "epoch": 0.28513501059810153,
      "grad_norm": 0.33084821701049805,
      "learning_rate": 1.903170818837998e-05,
      "loss": 0.5152,
      "step": 9282
    },
    {
      "epoch": 0.2851657297330507,
      "grad_norm": 0.37283238768577576,
      "learning_rate": 1.903150071588861e-05,
      "loss": 0.5749,
      "step": 9283
    },
    {
      "epoch": 0.2851964488679999,
      "grad_norm": 0.35400035977363586,
      "learning_rate": 1.9031293222303536e-05,
      "loss": 0.5763,
      "step": 9284
    },
    {
      "epoch": 0.28522716800294906,
      "grad_norm": 0.37130653858184814,
      "learning_rate": 1.9031085707625246e-05,
      "loss": 0.5864,
      "step": 9285
    },
    {
      "epoch": 0.2852578871378982,
      "grad_norm": 0.307373970746994,
      "learning_rate": 1.9030878171854224e-05,
      "loss": 0.5718,
      "step": 9286
    },
    {
      "epoch": 0.28528860627284736,
      "grad_norm": 0.338461697101593,
      "learning_rate": 1.9030670614990957e-05,
      "loss": 0.6098,
      "step": 9287
    },
    {
      "epoch": 0.28531932540779653,
      "grad_norm": 0.40855664014816284,
      "learning_rate": 1.903046303703593e-05,
      "loss": 0.6019,
      "step": 9288
    },
    {
      "epoch": 0.28535004454274565,
      "grad_norm": 0.35944223403930664,
      "learning_rate": 1.903025543798962e-05,
      "loss": 0.4941,
      "step": 9289
    },
    {
      "epoch": 0.2853807636776948,
      "grad_norm": 0.39662492275238037,
      "learning_rate": 1.9030047817852524e-05,
      "loss": 0.554,
      "step": 9290
    },
    {
      "epoch": 0.285411482812644,
      "grad_norm": 0.3280997574329376,
      "learning_rate": 1.9029840176625117e-05,
      "loss": 0.5401,
      "step": 9291
    },
    {
      "epoch": 0.2854422019475932,
      "grad_norm": 0.3458532691001892,
      "learning_rate": 1.902963251430789e-05,
      "loss": 0.627,
      "step": 9292
    },
    {
      "epoch": 0.2854729210825423,
      "grad_norm": 0.33751818537712097,
      "learning_rate": 1.9029424830901323e-05,
      "loss": 0.648,
      "step": 9293
    },
    {
      "epoch": 0.2855036402174915,
      "grad_norm": 0.42452800273895264,
      "learning_rate": 1.902921712640591e-05,
      "loss": 0.6276,
      "step": 9294
    },
    {
      "epoch": 0.28553435935244065,
      "grad_norm": 0.3729802370071411,
      "learning_rate": 1.902900940082212e-05,
      "loss": 0.5547,
      "step": 9295
    },
    {
      "epoch": 0.28556507848738977,
      "grad_norm": 0.36892151832580566,
      "learning_rate": 1.9028801654150456e-05,
      "loss": 0.5245,
      "step": 9296
    },
    {
      "epoch": 0.28559579762233894,
      "grad_norm": 0.37191852927207947,
      "learning_rate": 1.902859388639139e-05,
      "loss": 0.5353,
      "step": 9297
    },
    {
      "epoch": 0.2856265167572881,
      "grad_norm": 0.34723421931266785,
      "learning_rate": 1.9028386097545416e-05,
      "loss": 0.6368,
      "step": 9298
    },
    {
      "epoch": 0.2856572358922373,
      "grad_norm": 0.3488089442253113,
      "learning_rate": 1.9028178287613014e-05,
      "loss": 0.6932,
      "step": 9299
    },
    {
      "epoch": 0.2856879550271864,
      "grad_norm": 0.36049705743789673,
      "learning_rate": 1.902797045659467e-05,
      "loss": 0.5763,
      "step": 9300
    },
    {
      "epoch": 0.2857186741621356,
      "grad_norm": 0.3234849274158478,
      "learning_rate": 1.902776260449087e-05,
      "loss": 0.6412,
      "step": 9301
    },
    {
      "epoch": 0.28574939329708476,
      "grad_norm": 0.3377651274204254,
      "learning_rate": 1.9027554731302102e-05,
      "loss": 0.5445,
      "step": 9302
    },
    {
      "epoch": 0.28578011243203394,
      "grad_norm": 0.3206236660480499,
      "learning_rate": 1.9027346837028854e-05,
      "loss": 0.5307,
      "step": 9303
    },
    {
      "epoch": 0.28581083156698306,
      "grad_norm": 0.3338584303855896,
      "learning_rate": 1.90271389216716e-05,
      "loss": 0.6497,
      "step": 9304
    },
    {
      "epoch": 0.28584155070193223,
      "grad_norm": 0.37008991837501526,
      "learning_rate": 1.9026930985230833e-05,
      "loss": 0.5968,
      "step": 9305
    },
    {
      "epoch": 0.2858722698368814,
      "grad_norm": 0.3823692500591278,
      "learning_rate": 1.9026723027707042e-05,
      "loss": 0.5703,
      "step": 9306
    },
    {
      "epoch": 0.28590298897183053,
      "grad_norm": 0.3399040102958679,
      "learning_rate": 1.9026515049100707e-05,
      "loss": 0.5965,
      "step": 9307
    },
    {
      "epoch": 0.2859337081067797,
      "grad_norm": 0.34630969166755676,
      "learning_rate": 1.9026307049412314e-05,
      "loss": 0.6437,
      "step": 9308
    },
    {
      "epoch": 0.2859644272417289,
      "grad_norm": 0.35077065229415894,
      "learning_rate": 1.9026099028642353e-05,
      "loss": 0.5729,
      "step": 9309
    },
    {
      "epoch": 0.28599514637667806,
      "grad_norm": 0.33529430627822876,
      "learning_rate": 1.9025890986791306e-05,
      "loss": 0.6529,
      "step": 9310
    },
    {
      "epoch": 0.2860258655116272,
      "grad_norm": 0.38041603565216064,
      "learning_rate": 1.9025682923859663e-05,
      "loss": 0.5619,
      "step": 9311
    },
    {
      "epoch": 0.28605658464657635,
      "grad_norm": 0.3517540991306305,
      "learning_rate": 1.9025474839847904e-05,
      "loss": 0.5736,
      "step": 9312
    },
    {
      "epoch": 0.2860873037815255,
      "grad_norm": 0.44308212399482727,
      "learning_rate": 1.9025266734756517e-05,
      "loss": 0.7029,
      "step": 9313
    },
    {
      "epoch": 0.28611802291647465,
      "grad_norm": 0.31547999382019043,
      "learning_rate": 1.9025058608585993e-05,
      "loss": 0.5753,
      "step": 9314
    },
    {
      "epoch": 0.2861487420514238,
      "grad_norm": 0.3447605073451996,
      "learning_rate": 1.902485046133681e-05,
      "loss": 0.5373,
      "step": 9315
    },
    {
      "epoch": 0.286179461186373,
      "grad_norm": 0.41334059834480286,
      "learning_rate": 1.9024642293009465e-05,
      "loss": 0.5929,
      "step": 9316
    },
    {
      "epoch": 0.28621018032132217,
      "grad_norm": 0.42987290024757385,
      "learning_rate": 1.9024434103604432e-05,
      "loss": 0.6413,
      "step": 9317
    },
    {
      "epoch": 0.2862408994562713,
      "grad_norm": 0.41721147298812866,
      "learning_rate": 1.9024225893122207e-05,
      "loss": 0.5549,
      "step": 9318
    },
    {
      "epoch": 0.28627161859122047,
      "grad_norm": 0.31250229477882385,
      "learning_rate": 1.902401766156327e-05,
      "loss": 0.5685,
      "step": 9319
    },
    {
      "epoch": 0.28630233772616964,
      "grad_norm": 0.3770241439342499,
      "learning_rate": 1.902380940892811e-05,
      "loss": 0.5868,
      "step": 9320
    },
    {
      "epoch": 0.2863330568611188,
      "grad_norm": 0.3890383243560791,
      "learning_rate": 1.902360113521721e-05,
      "loss": 0.6166,
      "step": 9321
    },
    {
      "epoch": 0.28636377599606794,
      "grad_norm": 0.3839413523674011,
      "learning_rate": 1.902339284043106e-05,
      "loss": 0.576,
      "step": 9322
    },
    {
      "epoch": 0.2863944951310171,
      "grad_norm": 0.3640425205230713,
      "learning_rate": 1.9023184524570148e-05,
      "loss": 0.5935,
      "step": 9323
    },
    {
      "epoch": 0.2864252142659663,
      "grad_norm": 0.3006657361984253,
      "learning_rate": 1.9022976187634957e-05,
      "loss": 0.566,
      "step": 9324
    },
    {
      "epoch": 0.2864559334009154,
      "grad_norm": 0.32806137204170227,
      "learning_rate": 1.9022767829625976e-05,
      "loss": 0.5874,
      "step": 9325
    },
    {
      "epoch": 0.2864866525358646,
      "grad_norm": 0.448210209608078,
      "learning_rate": 1.9022559450543693e-05,
      "loss": 0.6282,
      "step": 9326
    },
    {
      "epoch": 0.28651737167081376,
      "grad_norm": 0.3499283492565155,
      "learning_rate": 1.902235105038859e-05,
      "loss": 0.5926,
      "step": 9327
    },
    {
      "epoch": 0.28654809080576293,
      "grad_norm": 0.36114048957824707,
      "learning_rate": 1.9022142629161156e-05,
      "loss": 0.6316,
      "step": 9328
    },
    {
      "epoch": 0.28657880994071205,
      "grad_norm": 0.39125198125839233,
      "learning_rate": 1.9021934186861876e-05,
      "loss": 0.6138,
      "step": 9329
    },
    {
      "epoch": 0.28660952907566123,
      "grad_norm": 0.511008083820343,
      "learning_rate": 1.902172572349124e-05,
      "loss": 0.6685,
      "step": 9330
    },
    {
      "epoch": 0.2866402482106104,
      "grad_norm": 0.4135851562023163,
      "learning_rate": 1.9021517239049734e-05,
      "loss": 0.6528,
      "step": 9331
    },
    {
      "epoch": 0.2866709673455595,
      "grad_norm": 0.33446189761161804,
      "learning_rate": 1.9021308733537843e-05,
      "loss": 0.5372,
      "step": 9332
    },
    {
      "epoch": 0.2867016864805087,
      "grad_norm": 0.334303081035614,
      "learning_rate": 1.9021100206956058e-05,
      "loss": 0.4858,
      "step": 9333
    },
    {
      "epoch": 0.2867324056154579,
      "grad_norm": 0.38410356640815735,
      "learning_rate": 1.902089165930486e-05,
      "loss": 0.5219,
      "step": 9334
    },
    {
      "epoch": 0.28676312475040705,
      "grad_norm": 0.3804892599582672,
      "learning_rate": 1.9020683090584745e-05,
      "loss": 0.6135,
      "step": 9335
    },
    {
      "epoch": 0.28679384388535617,
      "grad_norm": 0.3023620843887329,
      "learning_rate": 1.902047450079619e-05,
      "loss": 0.5603,
      "step": 9336
    },
    {
      "epoch": 0.28682456302030535,
      "grad_norm": 0.35357919335365295,
      "learning_rate": 1.9020265889939685e-05,
      "loss": 0.6175,
      "step": 9337
    },
    {
      "epoch": 0.2868552821552545,
      "grad_norm": 0.3368571102619171,
      "learning_rate": 1.9020057258015723e-05,
      "loss": 0.6156,
      "step": 9338
    },
    {
      "epoch": 0.28688600129020364,
      "grad_norm": 0.3990270793437958,
      "learning_rate": 1.9019848605024787e-05,
      "loss": 0.581,
      "step": 9339
    },
    {
      "epoch": 0.2869167204251528,
      "grad_norm": 0.3414308428764343,
      "learning_rate": 1.9019639930967363e-05,
      "loss": 0.6013,
      "step": 9340
    },
    {
      "epoch": 0.286947439560102,
      "grad_norm": 0.3435481786727905,
      "learning_rate": 1.901943123584394e-05,
      "loss": 0.6667,
      "step": 9341
    },
    {
      "epoch": 0.28697815869505117,
      "grad_norm": 0.35575971007347107,
      "learning_rate": 1.9019222519655007e-05,
      "loss": 0.655,
      "step": 9342
    },
    {
      "epoch": 0.2870088778300003,
      "grad_norm": 0.3572206199169159,
      "learning_rate": 1.901901378240105e-05,
      "loss": 0.6028,
      "step": 9343
    },
    {
      "epoch": 0.28703959696494946,
      "grad_norm": 0.34801185131073,
      "learning_rate": 1.9018805024082555e-05,
      "loss": 0.5665,
      "step": 9344
    },
    {
      "epoch": 0.28707031609989864,
      "grad_norm": 0.4003714621067047,
      "learning_rate": 1.9018596244700012e-05,
      "loss": 0.5772,
      "step": 9345
    },
    {
      "epoch": 0.2871010352348478,
      "grad_norm": 0.4205717146396637,
      "learning_rate": 1.901838744425391e-05,
      "loss": 0.5552,
      "step": 9346
    },
    {
      "epoch": 0.28713175436979693,
      "grad_norm": 0.33847397565841675,
      "learning_rate": 1.901817862274473e-05,
      "loss": 0.6187,
      "step": 9347
    },
    {
      "epoch": 0.2871624735047461,
      "grad_norm": 0.34234726428985596,
      "learning_rate": 1.9017969780172966e-05,
      "loss": 0.6485,
      "step": 9348
    },
    {
      "epoch": 0.2871931926396953,
      "grad_norm": 0.3132323920726776,
      "learning_rate": 1.9017760916539102e-05,
      "loss": 0.5419,
      "step": 9349
    },
    {
      "epoch": 0.2872239117746444,
      "grad_norm": 0.3304428160190582,
      "learning_rate": 1.901755203184363e-05,
      "loss": 0.5927,
      "step": 9350
    },
    {
      "epoch": 0.2872546309095936,
      "grad_norm": 0.3361068069934845,
      "learning_rate": 1.9017343126087033e-05,
      "loss": 0.6007,
      "step": 9351
    },
    {
      "epoch": 0.28728535004454275,
      "grad_norm": 0.34766003489494324,
      "learning_rate": 1.9017134199269804e-05,
      "loss": 0.5377,
      "step": 9352
    },
    {
      "epoch": 0.28731606917949193,
      "grad_norm": 0.33210045099258423,
      "learning_rate": 1.9016925251392425e-05,
      "loss": 0.5818,
      "step": 9353
    },
    {
      "epoch": 0.28734678831444105,
      "grad_norm": 1.606541633605957,
      "learning_rate": 1.9016716282455392e-05,
      "loss": 0.5621,
      "step": 9354
    },
    {
      "epoch": 0.2873775074493902,
      "grad_norm": 0.33201372623443604,
      "learning_rate": 1.9016507292459185e-05,
      "loss": 0.64,
      "step": 9355
    },
    {
      "epoch": 0.2874082265843394,
      "grad_norm": 0.3337506055831909,
      "learning_rate": 1.9016298281404295e-05,
      "loss": 0.5938,
      "step": 9356
    },
    {
      "epoch": 0.2874389457192885,
      "grad_norm": 0.3602793216705322,
      "learning_rate": 1.9016089249291214e-05,
      "loss": 0.5202,
      "step": 9357
    },
    {
      "epoch": 0.2874696648542377,
      "grad_norm": 0.32055869698524475,
      "learning_rate": 1.9015880196120424e-05,
      "loss": 0.5663,
      "step": 9358
    },
    {
      "epoch": 0.28750038398918687,
      "grad_norm": 0.36625251173973083,
      "learning_rate": 1.9015671121892417e-05,
      "loss": 0.6253,
      "step": 9359
    },
    {
      "epoch": 0.28753110312413604,
      "grad_norm": 0.3435142934322357,
      "learning_rate": 1.901546202660768e-05,
      "loss": 0.5318,
      "step": 9360
    },
    {
      "epoch": 0.28756182225908516,
      "grad_norm": 0.33965981006622314,
      "learning_rate": 1.9015252910266704e-05,
      "loss": 0.5699,
      "step": 9361
    },
    {
      "epoch": 0.28759254139403434,
      "grad_norm": 0.3194831907749176,
      "learning_rate": 1.9015043772869972e-05,
      "loss": 0.572,
      "step": 9362
    },
    {
      "epoch": 0.2876232605289835,
      "grad_norm": 0.34829676151275635,
      "learning_rate": 1.9014834614417977e-05,
      "loss": 0.5434,
      "step": 9363
    },
    {
      "epoch": 0.2876539796639327,
      "grad_norm": 0.33492106199264526,
      "learning_rate": 1.9014625434911206e-05,
      "loss": 0.6085,
      "step": 9364
    },
    {
      "epoch": 0.2876846987988818,
      "grad_norm": 0.33397242426872253,
      "learning_rate": 1.901441623435015e-05,
      "loss": 0.6381,
      "step": 9365
    },
    {
      "epoch": 0.287715417933831,
      "grad_norm": 0.477981299161911,
      "learning_rate": 1.901420701273529e-05,
      "loss": 0.5382,
      "step": 9366
    },
    {
      "epoch": 0.28774613706878016,
      "grad_norm": 0.3303143084049225,
      "learning_rate": 1.9013997770067125e-05,
      "loss": 0.5863,
      "step": 9367
    },
    {
      "epoch": 0.2877768562037293,
      "grad_norm": 0.3454250395298004,
      "learning_rate": 1.901378850634614e-05,
      "loss": 0.7058,
      "step": 9368
    },
    {
      "epoch": 0.28780757533867846,
      "grad_norm": 0.31945088505744934,
      "learning_rate": 1.9013579221572817e-05,
      "loss": 0.5837,
      "step": 9369
    },
    {
      "epoch": 0.28783829447362763,
      "grad_norm": 0.37382662296295166,
      "learning_rate": 1.9013369915747653e-05,
      "loss": 0.6121,
      "step": 9370
    },
    {
      "epoch": 0.2878690136085768,
      "grad_norm": 0.31966260075569153,
      "learning_rate": 1.9013160588871132e-05,
      "loss": 0.5455,
      "step": 9371
    },
    {
      "epoch": 0.2878997327435259,
      "grad_norm": 0.38057276606559753,
      "learning_rate": 1.9012951240943748e-05,
      "loss": 0.6135,
      "step": 9372
    },
    {
      "epoch": 0.2879304518784751,
      "grad_norm": 0.8911390900611877,
      "learning_rate": 1.9012741871965986e-05,
      "loss": 0.5589,
      "step": 9373
    },
    {
      "epoch": 0.2879611710134243,
      "grad_norm": 0.3580016791820526,
      "learning_rate": 1.9012532481938334e-05,
      "loss": 0.5436,
      "step": 9374
    },
    {
      "epoch": 0.2879918901483734,
      "grad_norm": 0.3633563816547394,
      "learning_rate": 1.9012323070861286e-05,
      "loss": 0.5991,
      "step": 9375
    },
    {
      "epoch": 0.2880226092833226,
      "grad_norm": 0.3777547776699066,
      "learning_rate": 1.9012113638735327e-05,
      "loss": 0.4652,
      "step": 9376
    },
    {
      "epoch": 0.28805332841827175,
      "grad_norm": 0.3117181360721588,
      "learning_rate": 1.9011904185560945e-05,
      "loss": 0.5646,
      "step": 9377
    },
    {
      "epoch": 0.2880840475532209,
      "grad_norm": 0.3774385452270508,
      "learning_rate": 1.9011694711338635e-05,
      "loss": 0.4911,
      "step": 9378
    },
    {
      "epoch": 0.28811476668817004,
      "grad_norm": 0.36549118161201477,
      "learning_rate": 1.901148521606888e-05,
      "loss": 0.5772,
      "step": 9379
    },
    {
      "epoch": 0.2881454858231192,
      "grad_norm": 0.3867574632167816,
      "learning_rate": 1.9011275699752173e-05,
      "loss": 0.6028,
      "step": 9380
    },
    {
      "epoch": 0.2881762049580684,
      "grad_norm": 0.30374130606651306,
      "learning_rate": 1.9011066162389e-05,
      "loss": 0.5147,
      "step": 9381
    },
    {
      "epoch": 0.2882069240930175,
      "grad_norm": 0.3855179250240326,
      "learning_rate": 1.9010856603979856e-05,
      "loss": 0.576,
      "step": 9382
    },
    {
      "epoch": 0.2882376432279667,
      "grad_norm": 0.3699890673160553,
      "learning_rate": 1.9010647024525225e-05,
      "loss": 0.6336,
      "step": 9383
    },
    {
      "epoch": 0.28826836236291586,
      "grad_norm": 0.34892505407333374,
      "learning_rate": 1.90104374240256e-05,
      "loss": 0.5234,
      "step": 9384
    },
    {
      "epoch": 0.28829908149786504,
      "grad_norm": 0.37301263213157654,
      "learning_rate": 1.9010227802481467e-05,
      "loss": 0.5508,
      "step": 9385
    },
    {
      "epoch": 0.28832980063281416,
      "grad_norm": 0.40849706530570984,
      "learning_rate": 1.901001815989332e-05,
      "loss": 0.644,
      "step": 9386
    },
    {
      "epoch": 0.28836051976776333,
      "grad_norm": 0.38499918580055237,
      "learning_rate": 1.900980849626165e-05,
      "loss": 0.5357,
      "step": 9387
    },
    {
      "epoch": 0.2883912389027125,
      "grad_norm": 0.36384740471839905,
      "learning_rate": 1.9009598811586935e-05,
      "loss": 0.6321,
      "step": 9388
    },
    {
      "epoch": 0.2884219580376617,
      "grad_norm": 0.30856820940971375,
      "learning_rate": 1.9009389105869677e-05,
      "loss": 0.5326,
      "step": 9389
    },
    {
      "epoch": 0.2884526771726108,
      "grad_norm": 0.35361042618751526,
      "learning_rate": 1.900917937911036e-05,
      "loss": 0.6199,
      "step": 9390
    },
    {
      "epoch": 0.28848339630756,
      "grad_norm": 0.3460847735404968,
      "learning_rate": 1.9008969631309474e-05,
      "loss": 0.5334,
      "step": 9391
    },
    {
      "epoch": 0.28851411544250916,
      "grad_norm": 0.3597692847251892,
      "learning_rate": 1.9008759862467515e-05,
      "loss": 0.6134,
      "step": 9392
    },
    {
      "epoch": 0.2885448345774583,
      "grad_norm": 0.34109750390052795,
      "learning_rate": 1.9008550072584967e-05,
      "loss": 0.5629,
      "step": 9393
    },
    {
      "epoch": 0.28857555371240745,
      "grad_norm": 0.335252583026886,
      "learning_rate": 1.9008340261662316e-05,
      "loss": 0.5537,
      "step": 9394
    },
    {
      "epoch": 0.2886062728473566,
      "grad_norm": 0.3669186532497406,
      "learning_rate": 1.9008130429700062e-05,
      "loss": 0.5853,
      "step": 9395
    },
    {
      "epoch": 0.2886369919823058,
      "grad_norm": 0.36158856749534607,
      "learning_rate": 1.9007920576698692e-05,
      "loss": 0.5612,
      "step": 9396
    },
    {
      "epoch": 0.2886677111172549,
      "grad_norm": 0.6757898330688477,
      "learning_rate": 1.900771070265869e-05,
      "loss": 0.5554,
      "step": 9397
    },
    {
      "epoch": 0.2886984302522041,
      "grad_norm": 0.3661435842514038,
      "learning_rate": 1.900750080758055e-05,
      "loss": 0.6394,
      "step": 9398
    },
    {
      "epoch": 0.28872914938715327,
      "grad_norm": 0.3476350009441376,
      "learning_rate": 1.9007290891464768e-05,
      "loss": 0.5459,
      "step": 9399
    },
    {
      "epoch": 0.2887598685221024,
      "grad_norm": 0.334116667509079,
      "learning_rate": 1.9007080954311827e-05,
      "loss": 0.5913,
      "step": 9400
    },
    {
      "epoch": 0.28879058765705157,
      "grad_norm": 0.35747507214546204,
      "learning_rate": 1.900687099612222e-05,
      "loss": 0.6345,
      "step": 9401
    },
    {
      "epoch": 0.28882130679200074,
      "grad_norm": 0.3479762673377991,
      "learning_rate": 1.9006661016896432e-05,
      "loss": 0.6165,
      "step": 9402
    },
    {
      "epoch": 0.2888520259269499,
      "grad_norm": 0.3553013801574707,
      "learning_rate": 1.900645101663496e-05,
      "loss": 0.608,
      "step": 9403
    },
    {
      "epoch": 0.28888274506189904,
      "grad_norm": 0.35640326142311096,
      "learning_rate": 1.9006240995338293e-05,
      "loss": 0.6227,
      "step": 9404
    },
    {
      "epoch": 0.2889134641968482,
      "grad_norm": 0.40772804617881775,
      "learning_rate": 1.9006030953006923e-05,
      "loss": 0.5666,
      "step": 9405
    },
    {
      "epoch": 0.2889441833317974,
      "grad_norm": 0.3512440621852875,
      "learning_rate": 1.900582088964134e-05,
      "loss": 0.6112,
      "step": 9406
    },
    {
      "epoch": 0.28897490246674656,
      "grad_norm": 0.38386377692222595,
      "learning_rate": 1.900561080524203e-05,
      "loss": 0.6801,
      "step": 9407
    },
    {
      "epoch": 0.2890056216016957,
      "grad_norm": 0.3171926438808441,
      "learning_rate": 1.9005400699809486e-05,
      "loss": 0.5791,
      "step": 9408
    },
    {
      "epoch": 0.28903634073664486,
      "grad_norm": 0.9443144202232361,
      "learning_rate": 1.9005190573344203e-05,
      "loss": 0.7347,
      "step": 9409
    },
    {
      "epoch": 0.28906705987159403,
      "grad_norm": 0.32842209935188293,
      "learning_rate": 1.900498042584667e-05,
      "loss": 0.5579,
      "step": 9410
    },
    {
      "epoch": 0.28909777900654315,
      "grad_norm": 0.3448334038257599,
      "learning_rate": 1.9004770257317374e-05,
      "loss": 0.6037,
      "step": 9411
    },
    {
      "epoch": 0.28912849814149233,
      "grad_norm": 0.31179970502853394,
      "learning_rate": 1.9004560067756806e-05,
      "loss": 0.626,
      "step": 9412
    },
    {
      "epoch": 0.2891592172764415,
      "grad_norm": 0.3652092218399048,
      "learning_rate": 1.900434985716546e-05,
      "loss": 0.5241,
      "step": 9413
    },
    {
      "epoch": 0.2891899364113907,
      "grad_norm": 0.6611483097076416,
      "learning_rate": 1.9004139625543826e-05,
      "loss": 0.6478,
      "step": 9414
    },
    {
      "epoch": 0.2892206555463398,
      "grad_norm": 0.36069566011428833,
      "learning_rate": 1.9003929372892396e-05,
      "loss": 0.6164,
      "step": 9415
    },
    {
      "epoch": 0.289251374681289,
      "grad_norm": 0.3264824151992798,
      "learning_rate": 1.9003719099211662e-05,
      "loss": 0.6144,
      "step": 9416
    },
    {
      "epoch": 0.28928209381623815,
      "grad_norm": 0.3639531135559082,
      "learning_rate": 1.9003508804502112e-05,
      "loss": 0.5656,
      "step": 9417
    },
    {
      "epoch": 0.28931281295118727,
      "grad_norm": 0.41040992736816406,
      "learning_rate": 1.9003298488764237e-05,
      "loss": 0.6215,
      "step": 9418
    },
    {
      "epoch": 0.28934353208613645,
      "grad_norm": 0.3587819039821625,
      "learning_rate": 1.900308815199853e-05,
      "loss": 0.5586,
      "step": 9419
    },
    {
      "epoch": 0.2893742512210856,
      "grad_norm": 0.3278818726539612,
      "learning_rate": 1.9002877794205482e-05,
      "loss": 0.595,
      "step": 9420
    },
    {
      "epoch": 0.2894049703560348,
      "grad_norm": 0.39501529932022095,
      "learning_rate": 1.9002667415385584e-05,
      "loss": 0.5116,
      "step": 9421
    },
    {
      "epoch": 0.2894356894909839,
      "grad_norm": 0.32418352365493774,
      "learning_rate": 1.900245701553933e-05,
      "loss": 0.6188,
      "step": 9422
    },
    {
      "epoch": 0.2894664086259331,
      "grad_norm": 0.3303264081478119,
      "learning_rate": 1.9002246594667207e-05,
      "loss": 0.5131,
      "step": 9423
    },
    {
      "epoch": 0.28949712776088227,
      "grad_norm": 0.39344894886016846,
      "learning_rate": 1.9002036152769708e-05,
      "loss": 0.6458,
      "step": 9424
    },
    {
      "epoch": 0.2895278468958314,
      "grad_norm": 0.4250757098197937,
      "learning_rate": 1.9001825689847325e-05,
      "loss": 0.5673,
      "step": 9425
    },
    {
      "epoch": 0.28955856603078056,
      "grad_norm": 0.3264045715332031,
      "learning_rate": 1.900161520590055e-05,
      "loss": 0.5979,
      "step": 9426
    },
    {
      "epoch": 0.28958928516572974,
      "grad_norm": 0.33560627698898315,
      "learning_rate": 1.9001404700929872e-05,
      "loss": 0.4424,
      "step": 9427
    },
    {
      "epoch": 0.2896200043006789,
      "grad_norm": 0.3638589680194855,
      "learning_rate": 1.9001194174935787e-05,
      "loss": 0.5966,
      "step": 9428
    },
    {
      "epoch": 0.28965072343562803,
      "grad_norm": 0.3742683231830597,
      "learning_rate": 1.900098362791878e-05,
      "loss": 0.5835,
      "step": 9429
    },
    {
      "epoch": 0.2896814425705772,
      "grad_norm": 0.33662042021751404,
      "learning_rate": 1.9000773059879357e-05,
      "loss": 0.5593,
      "step": 9430
    },
    {
      "epoch": 0.2897121617055264,
      "grad_norm": 0.3326091766357422,
      "learning_rate": 1.900056247081799e-05,
      "loss": 0.6441,
      "step": 9431
    },
    {
      "epoch": 0.28974288084047556,
      "grad_norm": 0.33163192868232727,
      "learning_rate": 1.9000351860735184e-05,
      "loss": 0.5076,
      "step": 9432
    },
    {
      "epoch": 0.2897735999754247,
      "grad_norm": 0.3366028070449829,
      "learning_rate": 1.900014122963143e-05,
      "loss": 0.622,
      "step": 9433
    },
    {
      "epoch": 0.28980431911037385,
      "grad_norm": 0.3558137118816376,
      "learning_rate": 1.8999930577507215e-05,
      "loss": 0.6605,
      "step": 9434
    },
    {
      "epoch": 0.28983503824532303,
      "grad_norm": 0.3563781678676605,
      "learning_rate": 1.8999719904363036e-05,
      "loss": 0.5989,
      "step": 9435
    },
    {
      "epoch": 0.28986575738027215,
      "grad_norm": 0.3242925703525543,
      "learning_rate": 1.899950921019938e-05,
      "loss": 0.5614,
      "step": 9436
    },
    {
      "epoch": 0.2898964765152213,
      "grad_norm": 0.424644410610199,
      "learning_rate": 1.899929849501674e-05,
      "loss": 0.6731,
      "step": 9437
    },
    {
      "epoch": 0.2899271956501705,
      "grad_norm": 0.3384351432323456,
      "learning_rate": 1.8999087758815615e-05,
      "loss": 0.5738,
      "step": 9438
    },
    {
      "epoch": 0.2899579147851197,
      "grad_norm": 0.3216378688812256,
      "learning_rate": 1.899887700159649e-05,
      "loss": 0.5417,
      "step": 9439
    },
    {
      "epoch": 0.2899886339200688,
      "grad_norm": 0.3223850727081299,
      "learning_rate": 1.899866622335986e-05,
      "loss": 0.6346,
      "step": 9440
    },
    {
      "epoch": 0.29001935305501797,
      "grad_norm": 0.3380982279777527,
      "learning_rate": 1.8998455424106213e-05,
      "loss": 0.6408,
      "step": 9441
    },
    {
      "epoch": 0.29005007218996715,
      "grad_norm": 0.45507633686065674,
      "learning_rate": 1.899824460383605e-05,
      "loss": 0.5965,
      "step": 9442
    },
    {
      "epoch": 0.29008079132491627,
      "grad_norm": 0.3227490186691284,
      "learning_rate": 1.8998033762549854e-05,
      "loss": 0.5883,
      "step": 9443
    },
    {
      "epoch": 0.29011151045986544,
      "grad_norm": 0.431487113237381,
      "learning_rate": 1.8997822900248124e-05,
      "loss": 0.5625,
      "step": 9444
    },
    {
      "epoch": 0.2901422295948146,
      "grad_norm": 0.3830277621746063,
      "learning_rate": 1.8997612016931347e-05,
      "loss": 0.5835,
      "step": 9445
    },
    {
      "epoch": 0.2901729487297638,
      "grad_norm": 0.35452818870544434,
      "learning_rate": 1.899740111260002e-05,
      "loss": 0.66,
      "step": 9446
    },
    {
      "epoch": 0.2902036678647129,
      "grad_norm": 0.3321070373058319,
      "learning_rate": 1.899719018725464e-05,
      "loss": 0.6534,
      "step": 9447
    },
    {
      "epoch": 0.2902343869996621,
      "grad_norm": 0.3561092019081116,
      "learning_rate": 1.8996979240895686e-05,
      "loss": 0.5855,
      "step": 9448
    },
    {
      "epoch": 0.29026510613461126,
      "grad_norm": 0.35406848788261414,
      "learning_rate": 1.8996768273523666e-05,
      "loss": 0.5919,
      "step": 9449
    },
    {
      "epoch": 0.29029582526956044,
      "grad_norm": 0.3625110685825348,
      "learning_rate": 1.899655728513906e-05,
      "loss": 0.5927,
      "step": 9450
    },
    {
      "epoch": 0.29032654440450956,
      "grad_norm": 0.35873591899871826,
      "learning_rate": 1.899634627574237e-05,
      "loss": 0.5385,
      "step": 9451
    },
    {
      "epoch": 0.29035726353945873,
      "grad_norm": 0.33755919337272644,
      "learning_rate": 1.899613524533408e-05,
      "loss": 0.5627,
      "step": 9452
    },
    {
      "epoch": 0.2903879826744079,
      "grad_norm": 0.3175421357154846,
      "learning_rate": 1.899592419391469e-05,
      "loss": 0.5211,
      "step": 9453
    },
    {
      "epoch": 0.290418701809357,
      "grad_norm": 0.353015273809433,
      "learning_rate": 1.8995713121484695e-05,
      "loss": 0.6106,
      "step": 9454
    },
    {
      "epoch": 0.2904494209443062,
      "grad_norm": 0.34359729290008545,
      "learning_rate": 1.8995502028044577e-05,
      "loss": 0.5667,
      "step": 9455
    },
    {
      "epoch": 0.2904801400792554,
      "grad_norm": 0.48201557993888855,
      "learning_rate": 1.899529091359484e-05,
      "loss": 0.5814,
      "step": 9456
    },
    {
      "epoch": 0.29051085921420455,
      "grad_norm": 0.3213118016719818,
      "learning_rate": 1.899507977813597e-05,
      "loss": 0.5919,
      "step": 9457
    },
    {
      "epoch": 0.2905415783491537,
      "grad_norm": 0.31962600350379944,
      "learning_rate": 1.8994868621668464e-05,
      "loss": 0.5529,
      "step": 9458
    },
    {
      "epoch": 0.29057229748410285,
      "grad_norm": 0.33782291412353516,
      "learning_rate": 1.8994657444192818e-05,
      "loss": 0.6445,
      "step": 9459
    },
    {
      "epoch": 0.290603016619052,
      "grad_norm": 0.3900882601737976,
      "learning_rate": 1.8994446245709518e-05,
      "loss": 0.5802,
      "step": 9460
    },
    {
      "epoch": 0.29063373575400114,
      "grad_norm": 0.3228319585323334,
      "learning_rate": 1.899423502621906e-05,
      "loss": 0.581,
      "step": 9461
    },
    {
      "epoch": 0.2906644548889503,
      "grad_norm": 0.4409694969654083,
      "learning_rate": 1.899402378572194e-05,
      "loss": 0.5947,
      "step": 9462
    },
    {
      "epoch": 0.2906951740238995,
      "grad_norm": 0.33868488669395447,
      "learning_rate": 1.8993812524218646e-05,
      "loss": 0.5513,
      "step": 9463
    },
    {
      "epoch": 0.29072589315884867,
      "grad_norm": 0.3501710891723633,
      "learning_rate": 1.8993601241709678e-05,
      "loss": 0.606,
      "step": 9464
    },
    {
      "epoch": 0.2907566122937978,
      "grad_norm": 0.33608150482177734,
      "learning_rate": 1.8993389938195522e-05,
      "loss": 0.6716,
      "step": 9465
    },
    {
      "epoch": 0.29078733142874696,
      "grad_norm": 0.3239777088165283,
      "learning_rate": 1.899317861367668e-05,
      "loss": 0.6297,
      "step": 9466
    },
    {
      "epoch": 0.29081805056369614,
      "grad_norm": 0.34961315989494324,
      "learning_rate": 1.8992967268153642e-05,
      "loss": 0.6624,
      "step": 9467
    },
    {
      "epoch": 0.29084876969864526,
      "grad_norm": 0.3577212691307068,
      "learning_rate": 1.89927559016269e-05,
      "loss": 0.5842,
      "step": 9468
    },
    {
      "epoch": 0.29087948883359444,
      "grad_norm": 0.30937889218330383,
      "learning_rate": 1.8992544514096946e-05,
      "loss": 0.5103,
      "step": 9469
    },
    {
      "epoch": 0.2909102079685436,
      "grad_norm": 0.3873792588710785,
      "learning_rate": 1.8992333105564274e-05,
      "loss": 0.6457,
      "step": 9470
    },
    {
      "epoch": 0.2909409271034928,
      "grad_norm": 0.33313965797424316,
      "learning_rate": 1.8992121676029387e-05,
      "loss": 0.5962,
      "step": 9471
    },
    {
      "epoch": 0.2909716462384419,
      "grad_norm": 0.33405938744544983,
      "learning_rate": 1.899191022549277e-05,
      "loss": 0.5539,
      "step": 9472
    },
    {
      "epoch": 0.2910023653733911,
      "grad_norm": 0.3451133966445923,
      "learning_rate": 1.8991698753954913e-05,
      "loss": 0.609,
      "step": 9473
    },
    {
      "epoch": 0.29103308450834026,
      "grad_norm": 0.3713354468345642,
      "learning_rate": 1.8991487261416323e-05,
      "loss": 0.5884,
      "step": 9474
    },
    {
      "epoch": 0.29106380364328943,
      "grad_norm": 0.35267654061317444,
      "learning_rate": 1.8991275747877482e-05,
      "loss": 0.6004,
      "step": 9475
    },
    {
      "epoch": 0.29109452277823855,
      "grad_norm": 0.34927988052368164,
      "learning_rate": 1.899106421333889e-05,
      "loss": 0.606,
      "step": 9476
    },
    {
      "epoch": 0.2911252419131877,
      "grad_norm": 0.3376772105693817,
      "learning_rate": 1.8990852657801037e-05,
      "loss": 0.5662,
      "step": 9477
    },
    {
      "epoch": 0.2911559610481369,
      "grad_norm": 0.3216066062450409,
      "learning_rate": 1.8990641081264422e-05,
      "loss": 0.5955,
      "step": 9478
    },
    {
      "epoch": 0.291186680183086,
      "grad_norm": 0.3336585462093353,
      "learning_rate": 1.8990429483729538e-05,
      "loss": 0.5374,
      "step": 9479
    },
    {
      "epoch": 0.2912173993180352,
      "grad_norm": 0.34971824288368225,
      "learning_rate": 1.8990217865196877e-05,
      "loss": 0.6124,
      "step": 9480
    },
    {
      "epoch": 0.2912481184529844,
      "grad_norm": 0.34529784321784973,
      "learning_rate": 1.8990006225666934e-05,
      "loss": 0.5933,
      "step": 9481
    },
    {
      "epoch": 0.29127883758793355,
      "grad_norm": 0.31069839000701904,
      "learning_rate": 1.8989794565140205e-05,
      "loss": 0.5733,
      "step": 9482
    },
    {
      "epoch": 0.29130955672288267,
      "grad_norm": 0.3323630094528198,
      "learning_rate": 1.898958288361718e-05,
      "loss": 0.5858,
      "step": 9483
    },
    {
      "epoch": 0.29134027585783184,
      "grad_norm": 0.32430770993232727,
      "learning_rate": 1.898937118109836e-05,
      "loss": 0.5012,
      "step": 9484
    },
    {
      "epoch": 0.291370994992781,
      "grad_norm": 0.3173278570175171,
      "learning_rate": 1.8989159457584233e-05,
      "loss": 0.5343,
      "step": 9485
    },
    {
      "epoch": 0.29140171412773014,
      "grad_norm": 0.37989574670791626,
      "learning_rate": 1.89889477130753e-05,
      "loss": 0.5884,
      "step": 9486
    },
    {
      "epoch": 0.2914324332626793,
      "grad_norm": 0.6298141479492188,
      "learning_rate": 1.898873594757205e-05,
      "loss": 0.6426,
      "step": 9487
    },
    {
      "epoch": 0.2914631523976285,
      "grad_norm": 0.335166871547699,
      "learning_rate": 1.898852416107498e-05,
      "loss": 0.5848,
      "step": 9488
    },
    {
      "epoch": 0.29149387153257766,
      "grad_norm": 0.34140294790267944,
      "learning_rate": 1.898831235358458e-05,
      "loss": 0.5958,
      "step": 9489
    },
    {
      "epoch": 0.2915245906675268,
      "grad_norm": 0.3721246123313904,
      "learning_rate": 1.898810052510135e-05,
      "loss": 0.5936,
      "step": 9490
    },
    {
      "epoch": 0.29155530980247596,
      "grad_norm": 0.3496953845024109,
      "learning_rate": 1.8987888675625787e-05,
      "loss": 0.6623,
      "step": 9491
    },
    {
      "epoch": 0.29158602893742513,
      "grad_norm": 0.33917510509490967,
      "learning_rate": 1.8987676805158378e-05,
      "loss": 0.5757,
      "step": 9492
    },
    {
      "epoch": 0.29161674807237425,
      "grad_norm": 0.3491023778915405,
      "learning_rate": 1.8987464913699626e-05,
      "loss": 0.5178,
      "step": 9493
    },
    {
      "epoch": 0.29164746720732343,
      "grad_norm": 0.34286242723464966,
      "learning_rate": 1.8987253001250022e-05,
      "loss": 0.613,
      "step": 9494
    },
    {
      "epoch": 0.2916781863422726,
      "grad_norm": 0.3346743881702423,
      "learning_rate": 1.8987041067810058e-05,
      "loss": 0.6061,
      "step": 9495
    },
    {
      "epoch": 0.2917089054772218,
      "grad_norm": 0.3325253427028656,
      "learning_rate": 1.8986829113380234e-05,
      "loss": 0.5592,
      "step": 9496
    },
    {
      "epoch": 0.2917396246121709,
      "grad_norm": 0.3663845956325531,
      "learning_rate": 1.8986617137961042e-05,
      "loss": 0.5225,
      "step": 9497
    },
    {
      "epoch": 0.2917703437471201,
      "grad_norm": 0.3396764099597931,
      "learning_rate": 1.8986405141552977e-05,
      "loss": 0.5059,
      "step": 9498
    },
    {
      "epoch": 0.29180106288206925,
      "grad_norm": 0.3335491120815277,
      "learning_rate": 1.8986193124156536e-05,
      "loss": 0.5336,
      "step": 9499
    },
    {
      "epoch": 0.2918317820170184,
      "grad_norm": 0.3298214375972748,
      "learning_rate": 1.8985981085772215e-05,
      "loss": 0.5862,
      "step": 9500
    },
    {
      "epoch": 0.29186250115196755,
      "grad_norm": 0.3363182544708252,
      "learning_rate": 1.8985769026400508e-05,
      "loss": 0.5339,
      "step": 9501
    },
    {
      "epoch": 0.2918932202869167,
      "grad_norm": 0.34193772077560425,
      "learning_rate": 1.8985556946041906e-05,
      "loss": 0.543,
      "step": 9502
    },
    {
      "epoch": 0.2919239394218659,
      "grad_norm": 0.4068673551082611,
      "learning_rate": 1.898534484469691e-05,
      "loss": 0.612,
      "step": 9503
    },
    {
      "epoch": 0.291954658556815,
      "grad_norm": 0.3414188623428345,
      "learning_rate": 1.8985132722366014e-05,
      "loss": 0.6004,
      "step": 9504
    },
    {
      "epoch": 0.2919853776917642,
      "grad_norm": 0.3507465720176697,
      "learning_rate": 1.8984920579049714e-05,
      "loss": 0.5875,
      "step": 9505
    },
    {
      "epoch": 0.29201609682671337,
      "grad_norm": 0.34816718101501465,
      "learning_rate": 1.8984708414748503e-05,
      "loss": 0.57,
      "step": 9506
    },
    {
      "epoch": 0.29204681596166254,
      "grad_norm": 0.39329907298088074,
      "learning_rate": 1.898449622946288e-05,
      "loss": 0.4667,
      "step": 9507
    },
    {
      "epoch": 0.29207753509661166,
      "grad_norm": 0.33350738883018494,
      "learning_rate": 1.8984284023193334e-05,
      "loss": 0.5795,
      "step": 9508
    },
    {
      "epoch": 0.29210825423156084,
      "grad_norm": 0.33408451080322266,
      "learning_rate": 1.8984071795940375e-05,
      "loss": 0.5423,
      "step": 9509
    },
    {
      "epoch": 0.29213897336651,
      "grad_norm": 0.3309657573699951,
      "learning_rate": 1.898385954770448e-05,
      "loss": 0.5992,
      "step": 9510
    },
    {
      "epoch": 0.29216969250145913,
      "grad_norm": 0.3400677442550659,
      "learning_rate": 1.8983647278486155e-05,
      "loss": 0.5075,
      "step": 9511
    },
    {
      "epoch": 0.2922004116364083,
      "grad_norm": 0.3487856090068817,
      "learning_rate": 1.8983434988285894e-05,
      "loss": 0.5478,
      "step": 9512
    },
    {
      "epoch": 0.2922311307713575,
      "grad_norm": 0.4834105372428894,
      "learning_rate": 1.8983222677104198e-05,
      "loss": 0.5457,
      "step": 9513
    },
    {
      "epoch": 0.29226184990630666,
      "grad_norm": 0.336187481880188,
      "learning_rate": 1.8983010344941552e-05,
      "loss": 0.5311,
      "step": 9514
    },
    {
      "epoch": 0.2922925690412558,
      "grad_norm": 0.35424697399139404,
      "learning_rate": 1.898279799179846e-05,
      "loss": 0.6245,
      "step": 9515
    },
    {
      "epoch": 0.29232328817620495,
      "grad_norm": 0.3801720440387726,
      "learning_rate": 1.8982585617675418e-05,
      "loss": 0.5803,
      "step": 9516
    },
    {
      "epoch": 0.29235400731115413,
      "grad_norm": 0.3366343379020691,
      "learning_rate": 1.898237322257292e-05,
      "loss": 0.5386,
      "step": 9517
    },
    {
      "epoch": 0.2923847264461033,
      "grad_norm": 0.6376914381980896,
      "learning_rate": 1.898216080649146e-05,
      "loss": 0.6246,
      "step": 9518
    },
    {
      "epoch": 0.2924154455810524,
      "grad_norm": 0.3457103967666626,
      "learning_rate": 1.8981948369431536e-05,
      "loss": 0.602,
      "step": 9519
    },
    {
      "epoch": 0.2924461647160016,
      "grad_norm": 0.41022199392318726,
      "learning_rate": 1.8981735911393645e-05,
      "loss": 0.5584,
      "step": 9520
    },
    {
      "epoch": 0.2924768838509508,
      "grad_norm": 0.43180036544799805,
      "learning_rate": 1.8981523432378282e-05,
      "loss": 0.5665,
      "step": 9521
    },
    {
      "epoch": 0.2925076029858999,
      "grad_norm": 0.4509851634502411,
      "learning_rate": 1.8981310932385945e-05,
      "loss": 0.5837,
      "step": 9522
    },
    {
      "epoch": 0.29253832212084907,
      "grad_norm": 0.35788509249687195,
      "learning_rate": 1.8981098411417128e-05,
      "loss": 0.5818,
      "step": 9523
    },
    {
      "epoch": 0.29256904125579825,
      "grad_norm": 0.3508554697036743,
      "learning_rate": 1.8980885869472326e-05,
      "loss": 0.6137,
      "step": 9524
    },
    {
      "epoch": 0.2925997603907474,
      "grad_norm": 0.38057956099510193,
      "learning_rate": 1.898067330655204e-05,
      "loss": 0.6173,
      "step": 9525
    },
    {
      "epoch": 0.29263047952569654,
      "grad_norm": 0.36012351512908936,
      "learning_rate": 1.8980460722656767e-05,
      "loss": 0.6551,
      "step": 9526
    },
    {
      "epoch": 0.2926611986606457,
      "grad_norm": 0.3516409397125244,
      "learning_rate": 1.8980248117787e-05,
      "loss": 0.5411,
      "step": 9527
    },
    {
      "epoch": 0.2926919177955949,
      "grad_norm": 0.32511675357818604,
      "learning_rate": 1.898003549194323e-05,
      "loss": 0.5465,
      "step": 9528
    },
    {
      "epoch": 0.292722636930544,
      "grad_norm": 0.3519776463508606,
      "learning_rate": 1.897982284512597e-05,
      "loss": 0.6168,
      "step": 9529
    },
    {
      "epoch": 0.2927533560654932,
      "grad_norm": 0.29429343342781067,
      "learning_rate": 1.89796101773357e-05,
      "loss": 0.544,
      "step": 9530
    },
    {
      "epoch": 0.29278407520044236,
      "grad_norm": 0.36166876554489136,
      "learning_rate": 1.8979397488572922e-05,
      "loss": 0.5988,
      "step": 9531
    },
    {
      "epoch": 0.29281479433539154,
      "grad_norm": 0.3069896101951599,
      "learning_rate": 1.8979184778838137e-05,
      "loss": 0.5335,
      "step": 9532
    },
    {
      "epoch": 0.29284551347034066,
      "grad_norm": 0.3235434591770172,
      "learning_rate": 1.897897204813184e-05,
      "loss": 0.5925,
      "step": 9533
    },
    {
      "epoch": 0.29287623260528983,
      "grad_norm": 0.36955368518829346,
      "learning_rate": 1.8978759296454525e-05,
      "loss": 0.6282,
      "step": 9534
    },
    {
      "epoch": 0.292906951740239,
      "grad_norm": 0.3482399582862854,
      "learning_rate": 1.8978546523806693e-05,
      "loss": 0.525,
      "step": 9535
    },
    {
      "epoch": 0.2929376708751881,
      "grad_norm": 0.3320288360118866,
      "learning_rate": 1.8978333730188833e-05,
      "loss": 0.5872,
      "step": 9536
    },
    {
      "epoch": 0.2929683900101373,
      "grad_norm": 0.3655318319797516,
      "learning_rate": 1.8978120915601455e-05,
      "loss": 0.6175,
      "step": 9537
    },
    {
      "epoch": 0.2929991091450865,
      "grad_norm": 0.3792562186717987,
      "learning_rate": 1.8977908080045042e-05,
      "loss": 0.5634,
      "step": 9538
    },
    {
      "epoch": 0.29302982828003565,
      "grad_norm": 0.3221607804298401,
      "learning_rate": 1.89776952235201e-05,
      "loss": 0.553,
      "step": 9539
    },
    {
      "epoch": 0.2930605474149848,
      "grad_norm": 0.8123154640197754,
      "learning_rate": 1.8977482346027125e-05,
      "loss": 0.6325,
      "step": 9540
    },
    {
      "epoch": 0.29309126654993395,
      "grad_norm": 0.3780273497104645,
      "learning_rate": 1.897726944756661e-05,
      "loss": 0.5688,
      "step": 9541
    },
    {
      "epoch": 0.2931219856848831,
      "grad_norm": 0.4373965859413147,
      "learning_rate": 1.897705652813906e-05,
      "loss": 0.6145,
      "step": 9542
    },
    {
      "epoch": 0.2931527048198323,
      "grad_norm": 0.3567352890968323,
      "learning_rate": 1.8976843587744963e-05,
      "loss": 0.6527,
      "step": 9543
    },
    {
      "epoch": 0.2931834239547814,
      "grad_norm": 0.33677729964256287,
      "learning_rate": 1.8976630626384824e-05,
      "loss": 0.5944,
      "step": 9544
    },
    {
      "epoch": 0.2932141430897306,
      "grad_norm": 0.33334919810295105,
      "learning_rate": 1.8976417644059137e-05,
      "loss": 0.5635,
      "step": 9545
    },
    {
      "epoch": 0.29324486222467977,
      "grad_norm": 0.4299328029155731,
      "learning_rate": 1.8976204640768397e-05,
      "loss": 0.6263,
      "step": 9546
    },
    {
      "epoch": 0.2932755813596289,
      "grad_norm": 0.31479552388191223,
      "learning_rate": 1.8975991616513108e-05,
      "loss": 0.496,
      "step": 9547
    },
    {
      "epoch": 0.29330630049457806,
      "grad_norm": 0.3650813102722168,
      "learning_rate": 1.897577857129376e-05,
      "loss": 0.6395,
      "step": 9548
    },
    {
      "epoch": 0.29333701962952724,
      "grad_norm": 0.323186457157135,
      "learning_rate": 1.8975565505110855e-05,
      "loss": 0.5124,
      "step": 9549
    },
    {
      "epoch": 0.2933677387644764,
      "grad_norm": 0.429595023393631,
      "learning_rate": 1.897535241796489e-05,
      "loss": 0.5703,
      "step": 9550
    },
    {
      "epoch": 0.29339845789942554,
      "grad_norm": 0.3061355650424957,
      "learning_rate": 1.8975139309856362e-05,
      "loss": 0.5919,
      "step": 9551
    },
    {
      "epoch": 0.2934291770343747,
      "grad_norm": 0.3978032171726227,
      "learning_rate": 1.8974926180785774e-05,
      "loss": 0.6421,
      "step": 9552
    },
    {
      "epoch": 0.2934598961693239,
      "grad_norm": 0.3311902582645416,
      "learning_rate": 1.8974713030753617e-05,
      "loss": 0.6024,
      "step": 9553
    },
    {
      "epoch": 0.293490615304273,
      "grad_norm": 0.34466949105262756,
      "learning_rate": 1.8974499859760386e-05,
      "loss": 0.624,
      "step": 9554
    },
    {
      "epoch": 0.2935213344392222,
      "grad_norm": 0.35075896978378296,
      "learning_rate": 1.897428666780659e-05,
      "loss": 0.6283,
      "step": 9555
    },
    {
      "epoch": 0.29355205357417136,
      "grad_norm": 0.36592888832092285,
      "learning_rate": 1.897407345489272e-05,
      "loss": 0.6165,
      "step": 9556
    },
    {
      "epoch": 0.29358277270912053,
      "grad_norm": 0.3629481792449951,
      "learning_rate": 1.897386022101927e-05,
      "loss": 0.6169,
      "step": 9557
    },
    {
      "epoch": 0.29361349184406965,
      "grad_norm": 0.3128698468208313,
      "learning_rate": 1.8973646966186746e-05,
      "loss": 0.6011,
      "step": 9558
    },
    {
      "epoch": 0.2936442109790188,
      "grad_norm": 0.3430546820163727,
      "learning_rate": 1.897343369039564e-05,
      "loss": 0.5418,
      "step": 9559
    },
    {
      "epoch": 0.293674930113968,
      "grad_norm": 0.3367222547531128,
      "learning_rate": 1.8973220393646458e-05,
      "loss": 0.4987,
      "step": 9560
    },
    {
      "epoch": 0.2937056492489172,
      "grad_norm": 0.32873091101646423,
      "learning_rate": 1.897300707593969e-05,
      "loss": 0.5395,
      "step": 9561
    },
    {
      "epoch": 0.2937363683838663,
      "grad_norm": 0.37361085414886475,
      "learning_rate": 1.8972793737275837e-05,
      "loss": 0.5489,
      "step": 9562
    },
    {
      "epoch": 0.2937670875188155,
      "grad_norm": 0.3759135901927948,
      "learning_rate": 1.89725803776554e-05,
      "loss": 0.6122,
      "step": 9563
    },
    {
      "epoch": 0.29379780665376465,
      "grad_norm": 0.3464308977127075,
      "learning_rate": 1.8972366997078873e-05,
      "loss": 0.5868,
      "step": 9564
    },
    {
      "epoch": 0.29382852578871377,
      "grad_norm": 0.3251703381538391,
      "learning_rate": 1.8972153595546757e-05,
      "loss": 0.545,
      "step": 9565
    },
    {
      "epoch": 0.29385924492366294,
      "grad_norm": 0.3920583426952362,
      "learning_rate": 1.8971940173059548e-05,
      "loss": 0.561,
      "step": 9566
    },
    {
      "epoch": 0.2938899640586121,
      "grad_norm": 0.2970030903816223,
      "learning_rate": 1.8971726729617746e-05,
      "loss": 0.5916,
      "step": 9567
    },
    {
      "epoch": 0.2939206831935613,
      "grad_norm": 0.42063599824905396,
      "learning_rate": 1.8971513265221854e-05,
      "loss": 0.7191,
      "step": 9568
    },
    {
      "epoch": 0.2939514023285104,
      "grad_norm": 0.33417123556137085,
      "learning_rate": 1.8971299779872362e-05,
      "loss": 0.5899,
      "step": 9569
    },
    {
      "epoch": 0.2939821214634596,
      "grad_norm": 0.33266299962997437,
      "learning_rate": 1.8971086273569775e-05,
      "loss": 0.5186,
      "step": 9570
    },
    {
      "epoch": 0.29401284059840876,
      "grad_norm": 0.3238975703716278,
      "learning_rate": 1.8970872746314585e-05,
      "loss": 0.5665,
      "step": 9571
    },
    {
      "epoch": 0.2940435597333579,
      "grad_norm": 0.3370126187801361,
      "learning_rate": 1.89706591981073e-05,
      "loss": 0.5685,
      "step": 9572
    },
    {
      "epoch": 0.29407427886830706,
      "grad_norm": 0.3486659824848175,
      "learning_rate": 1.897044562894841e-05,
      "loss": 0.5774,
      "step": 9573
    },
    {
      "epoch": 0.29410499800325623,
      "grad_norm": 0.3460404872894287,
      "learning_rate": 1.8970232038838423e-05,
      "loss": 0.5821,
      "step": 9574
    },
    {
      "epoch": 0.2941357171382054,
      "grad_norm": 0.36355626583099365,
      "learning_rate": 1.897001842777783e-05,
      "loss": 0.6359,
      "step": 9575
    },
    {
      "epoch": 0.29416643627315453,
      "grad_norm": 0.36081662774086,
      "learning_rate": 1.8969804795767132e-05,
      "loss": 0.5519,
      "step": 9576
    },
    {
      "epoch": 0.2941971554081037,
      "grad_norm": 0.33564263582229614,
      "learning_rate": 1.896959114280683e-05,
      "loss": 0.5773,
      "step": 9577
    },
    {
      "epoch": 0.2942278745430529,
      "grad_norm": 0.3374861180782318,
      "learning_rate": 1.896937746889742e-05,
      "loss": 0.5291,
      "step": 9578
    },
    {
      "epoch": 0.294258593678002,
      "grad_norm": 0.33552759885787964,
      "learning_rate": 1.8969163774039402e-05,
      "loss": 0.5894,
      "step": 9579
    },
    {
      "epoch": 0.2942893128129512,
      "grad_norm": 0.34528395533561707,
      "learning_rate": 1.8968950058233275e-05,
      "loss": 0.5608,
      "step": 9580
    },
    {
      "epoch": 0.29432003194790035,
      "grad_norm": 0.5486834049224854,
      "learning_rate": 1.8968736321479543e-05,
      "loss": 0.5766,
      "step": 9581
    },
    {
      "epoch": 0.2943507510828495,
      "grad_norm": 0.32925066351890564,
      "learning_rate": 1.89685225637787e-05,
      "loss": 0.6351,
      "step": 9582
    },
    {
      "epoch": 0.29438147021779865,
      "grad_norm": 0.4103151559829712,
      "learning_rate": 1.8968308785131242e-05,
      "loss": 0.6331,
      "step": 9583
    },
    {
      "epoch": 0.2944121893527478,
      "grad_norm": 0.36522626876831055,
      "learning_rate": 1.8968094985537677e-05,
      "loss": 0.6035,
      "step": 9584
    },
    {
      "epoch": 0.294442908487697,
      "grad_norm": 0.3412953019142151,
      "learning_rate": 1.8967881164998494e-05,
      "loss": 0.6852,
      "step": 9585
    },
    {
      "epoch": 0.2944736276226462,
      "grad_norm": 0.3408052921295166,
      "learning_rate": 1.8967667323514203e-05,
      "loss": 0.5393,
      "step": 9586
    },
    {
      "epoch": 0.2945043467575953,
      "grad_norm": 0.3126402497291565,
      "learning_rate": 1.8967453461085298e-05,
      "loss": 0.5609,
      "step": 9587
    },
    {
      "epoch": 0.29453506589254447,
      "grad_norm": 0.3628767430782318,
      "learning_rate": 1.8967239577712276e-05,
      "loss": 0.6448,
      "step": 9588
    },
    {
      "epoch": 0.29456578502749364,
      "grad_norm": 0.3629752993583679,
      "learning_rate": 1.8967025673395643e-05,
      "loss": 0.5778,
      "step": 9589
    },
    {
      "epoch": 0.29459650416244276,
      "grad_norm": 0.3381538987159729,
      "learning_rate": 1.8966811748135897e-05,
      "loss": 0.6197,
      "step": 9590
    },
    {
      "epoch": 0.29462722329739194,
      "grad_norm": 0.4506744146347046,
      "learning_rate": 1.8966597801933533e-05,
      "loss": 0.5235,
      "step": 9591
    },
    {
      "epoch": 0.2946579424323411,
      "grad_norm": 0.3358134627342224,
      "learning_rate": 1.8966383834789054e-05,
      "loss": 0.5198,
      "step": 9592
    },
    {
      "epoch": 0.2946886615672903,
      "grad_norm": 0.35360878705978394,
      "learning_rate": 1.896616984670296e-05,
      "loss": 0.6326,
      "step": 9593
    },
    {
      "epoch": 0.2947193807022394,
      "grad_norm": 0.32817041873931885,
      "learning_rate": 1.896595583767575e-05,
      "loss": 0.6663,
      "step": 9594
    },
    {
      "epoch": 0.2947500998371886,
      "grad_norm": 1.1207202672958374,
      "learning_rate": 1.8965741807707924e-05,
      "loss": 0.5035,
      "step": 9595
    },
    {
      "epoch": 0.29478081897213776,
      "grad_norm": 3.716357946395874,
      "learning_rate": 1.8965527756799978e-05,
      "loss": 0.6172,
      "step": 9596
    },
    {
      "epoch": 0.2948115381070869,
      "grad_norm": 0.3494524359703064,
      "learning_rate": 1.896531368495242e-05,
      "loss": 0.6362,
      "step": 9597
    },
    {
      "epoch": 0.29484225724203605,
      "grad_norm": 0.3531571924686432,
      "learning_rate": 1.8965099592165748e-05,
      "loss": 0.5716,
      "step": 9598
    },
    {
      "epoch": 0.29487297637698523,
      "grad_norm": 0.39642706513404846,
      "learning_rate": 1.8964885478440456e-05,
      "loss": 0.5422,
      "step": 9599
    },
    {
      "epoch": 0.2949036955119344,
      "grad_norm": 0.3277052342891693,
      "learning_rate": 1.896467134377705e-05,
      "loss": 0.6154,
      "step": 9600
    },
    {
      "epoch": 0.2949344146468835,
      "grad_norm": 0.40405479073524475,
      "learning_rate": 1.8964457188176023e-05,
      "loss": 0.5766,
      "step": 9601
    },
    {
      "epoch": 0.2949651337818327,
      "grad_norm": 0.45250841975212097,
      "learning_rate": 1.8964243011637885e-05,
      "loss": 0.6191,
      "step": 9602
    },
    {
      "epoch": 0.2949958529167819,
      "grad_norm": 0.3300922214984894,
      "learning_rate": 1.8964028814163132e-05,
      "loss": 0.5547,
      "step": 9603
    },
    {
      "epoch": 0.29502657205173105,
      "grad_norm": 0.34479033946990967,
      "learning_rate": 1.8963814595752263e-05,
      "loss": 0.5735,
      "step": 9604
    },
    {
      "epoch": 0.29505729118668017,
      "grad_norm": 0.30435702204704285,
      "learning_rate": 1.8963600356405775e-05,
      "loss": 0.5202,
      "step": 9605
    },
    {
      "epoch": 0.29508801032162935,
      "grad_norm": 0.33053603768348694,
      "learning_rate": 1.8963386096124176e-05,
      "loss": 0.5242,
      "step": 9606
    },
    {
      "epoch": 0.2951187294565785,
      "grad_norm": 0.566961944103241,
      "learning_rate": 1.896317181490796e-05,
      "loss": 0.6261,
      "step": 9607
    },
    {
      "epoch": 0.29514944859152764,
      "grad_norm": 0.3661292791366577,
      "learning_rate": 1.8962957512757632e-05,
      "loss": 0.6484,
      "step": 9608
    },
    {
      "epoch": 0.2951801677264768,
      "grad_norm": 0.32124316692352295,
      "learning_rate": 1.8962743189673694e-05,
      "loss": 0.6562,
      "step": 9609
    },
    {
      "epoch": 0.295210886861426,
      "grad_norm": 0.3607218563556671,
      "learning_rate": 1.896252884565664e-05,
      "loss": 0.6283,
      "step": 9610
    },
    {
      "epoch": 0.29524160599637517,
      "grad_norm": 0.3653939366340637,
      "learning_rate": 1.8962314480706974e-05,
      "loss": 0.605,
      "step": 9611
    },
    {
      "epoch": 0.2952723251313243,
      "grad_norm": 0.3272026479244232,
      "learning_rate": 1.89621000948252e-05,
      "loss": 0.5869,
      "step": 9612
    },
    {
      "epoch": 0.29530304426627346,
      "grad_norm": 0.34552496671676636,
      "learning_rate": 1.896188568801181e-05,
      "loss": 0.6614,
      "step": 9613
    },
    {
      "epoch": 0.29533376340122264,
      "grad_norm": 0.3519168496131897,
      "learning_rate": 1.896167126026731e-05,
      "loss": 0.588,
      "step": 9614
    },
    {
      "epoch": 0.29536448253617176,
      "grad_norm": 0.3311556279659271,
      "learning_rate": 1.8961456811592205e-05,
      "loss": 0.5872,
      "step": 9615
    },
    {
      "epoch": 0.29539520167112093,
      "grad_norm": 0.3169788420200348,
      "learning_rate": 1.896124234198699e-05,
      "loss": 0.5711,
      "step": 9616
    },
    {
      "epoch": 0.2954259208060701,
      "grad_norm": 0.3222866654396057,
      "learning_rate": 1.8961027851452166e-05,
      "loss": 0.5677,
      "step": 9617
    },
    {
      "epoch": 0.2954566399410193,
      "grad_norm": 0.34067559242248535,
      "learning_rate": 1.896081333998824e-05,
      "loss": 0.5206,
      "step": 9618
    },
    {
      "epoch": 0.2954873590759684,
      "grad_norm": 0.33663129806518555,
      "learning_rate": 1.8960598807595704e-05,
      "loss": 0.5706,
      "step": 9619
    },
    {
      "epoch": 0.2955180782109176,
      "grad_norm": 0.3504725694656372,
      "learning_rate": 1.8960384254275068e-05,
      "loss": 0.5916,
      "step": 9620
    },
    {
      "epoch": 0.29554879734586675,
      "grad_norm": 0.35444918274879456,
      "learning_rate": 1.8960169680026826e-05,
      "loss": 0.5963,
      "step": 9621
    },
    {
      "epoch": 0.2955795164808159,
      "grad_norm": 0.37759289145469666,
      "learning_rate": 1.895995508485148e-05,
      "loss": 0.6063,
      "step": 9622
    },
    {
      "epoch": 0.29561023561576505,
      "grad_norm": 0.37891051173210144,
      "learning_rate": 1.8959740468749538e-05,
      "loss": 0.648,
      "step": 9623
    },
    {
      "epoch": 0.2956409547507142,
      "grad_norm": 0.31931546330451965,
      "learning_rate": 1.8959525831721494e-05,
      "loss": 0.5298,
      "step": 9624
    },
    {
      "epoch": 0.2956716738856634,
      "grad_norm": 0.7510591149330139,
      "learning_rate": 1.895931117376785e-05,
      "loss": 0.5803,
      "step": 9625
    },
    {
      "epoch": 0.2957023930206125,
      "grad_norm": 0.36139360070228577,
      "learning_rate": 1.895909649488911e-05,
      "loss": 0.5806,
      "step": 9626
    },
    {
      "epoch": 0.2957331121555617,
      "grad_norm": 0.3351001441478729,
      "learning_rate": 1.8958881795085776e-05,
      "loss": 0.537,
      "step": 9627
    },
    {
      "epoch": 0.29576383129051087,
      "grad_norm": 0.3678440451622009,
      "learning_rate": 1.8958667074358348e-05,
      "loss": 0.6195,
      "step": 9628
    },
    {
      "epoch": 0.29579455042546005,
      "grad_norm": 0.32193076610565186,
      "learning_rate": 1.8958452332707325e-05,
      "loss": 0.5957,
      "step": 9629
    },
    {
      "epoch": 0.29582526956040917,
      "grad_norm": 0.3359934389591217,
      "learning_rate": 1.895823757013321e-05,
      "loss": 0.4976,
      "step": 9630
    },
    {
      "epoch": 0.29585598869535834,
      "grad_norm": 0.32972991466522217,
      "learning_rate": 1.895802278663651e-05,
      "loss": 0.576,
      "step": 9631
    },
    {
      "epoch": 0.2958867078303075,
      "grad_norm": 0.38143596053123474,
      "learning_rate": 1.895780798221772e-05,
      "loss": 0.6471,
      "step": 9632
    },
    {
      "epoch": 0.29591742696525664,
      "grad_norm": 0.39756229519844055,
      "learning_rate": 1.8957593156877343e-05,
      "loss": 0.5226,
      "step": 9633
    },
    {
      "epoch": 0.2959481461002058,
      "grad_norm": 0.35852378606796265,
      "learning_rate": 1.895737831061588e-05,
      "loss": 0.537,
      "step": 9634
    },
    {
      "epoch": 0.295978865235155,
      "grad_norm": 0.3557642102241516,
      "learning_rate": 1.8957163443433838e-05,
      "loss": 0.5717,
      "step": 9635
    },
    {
      "epoch": 0.29600958437010416,
      "grad_norm": 0.354401558637619,
      "learning_rate": 1.8956948555331717e-05,
      "loss": 0.642,
      "step": 9636
    },
    {
      "epoch": 0.2960403035050533,
      "grad_norm": 0.3682270348072052,
      "learning_rate": 1.8956733646310013e-05,
      "loss": 0.5635,
      "step": 9637
    },
    {
      "epoch": 0.29607102264000246,
      "grad_norm": 0.3520122468471527,
      "learning_rate": 1.895651871636923e-05,
      "loss": 0.5169,
      "step": 9638
    },
    {
      "epoch": 0.29610174177495163,
      "grad_norm": 0.4236225485801697,
      "learning_rate": 1.8956303765509877e-05,
      "loss": 0.6088,
      "step": 9639
    },
    {
      "epoch": 0.29613246090990075,
      "grad_norm": 0.30634164810180664,
      "learning_rate": 1.895608879373245e-05,
      "loss": 0.5855,
      "step": 9640
    },
    {
      "epoch": 0.2961631800448499,
      "grad_norm": 0.4158584177494049,
      "learning_rate": 1.895587380103745e-05,
      "loss": 0.6099,
      "step": 9641
    },
    {
      "epoch": 0.2961938991797991,
      "grad_norm": 0.5082555413246155,
      "learning_rate": 1.8955658787425383e-05,
      "loss": 0.6526,
      "step": 9642
    },
    {
      "epoch": 0.2962246183147483,
      "grad_norm": 0.33939340710639954,
      "learning_rate": 1.895544375289675e-05,
      "loss": 0.625,
      "step": 9643
    },
    {
      "epoch": 0.2962553374496974,
      "grad_norm": 0.35879603028297424,
      "learning_rate": 1.895522869745205e-05,
      "loss": 0.5382,
      "step": 9644
    },
    {
      "epoch": 0.2962860565846466,
      "grad_norm": 0.3787858188152313,
      "learning_rate": 1.895501362109179e-05,
      "loss": 0.6582,
      "step": 9645
    },
    {
      "epoch": 0.29631677571959575,
      "grad_norm": 0.3573126792907715,
      "learning_rate": 1.8954798523816472e-05,
      "loss": 0.6583,
      "step": 9646
    },
    {
      "epoch": 0.29634749485454487,
      "grad_norm": 0.4100559651851654,
      "learning_rate": 1.8954583405626596e-05,
      "loss": 0.639,
      "step": 9647
    },
    {
      "epoch": 0.29637821398949404,
      "grad_norm": 0.3965766727924347,
      "learning_rate": 1.895436826652266e-05,
      "loss": 0.6383,
      "step": 9648
    },
    {
      "epoch": 0.2964089331244432,
      "grad_norm": 0.36630764603614807,
      "learning_rate": 1.8954153106505178e-05,
      "loss": 0.5662,
      "step": 9649
    },
    {
      "epoch": 0.2964396522593924,
      "grad_norm": 0.3609057366847992,
      "learning_rate": 1.8953937925574643e-05,
      "loss": 0.54,
      "step": 9650
    },
    {
      "epoch": 0.2964703713943415,
      "grad_norm": 0.3224005401134491,
      "learning_rate": 1.8953722723731562e-05,
      "loss": 0.5115,
      "step": 9651
    },
    {
      "epoch": 0.2965010905292907,
      "grad_norm": 0.3513984680175781,
      "learning_rate": 1.8953507500976434e-05,
      "loss": 0.4943,
      "step": 9652
    },
    {
      "epoch": 0.29653180966423986,
      "grad_norm": 0.31077805161476135,
      "learning_rate": 1.8953292257309766e-05,
      "loss": 0.6143,
      "step": 9653
    },
    {
      "epoch": 0.29656252879918904,
      "grad_norm": 0.33379340171813965,
      "learning_rate": 1.8953076992732054e-05,
      "loss": 0.5687,
      "step": 9654
    },
    {
      "epoch": 0.29659324793413816,
      "grad_norm": 0.3536103665828705,
      "learning_rate": 1.895286170724381e-05,
      "loss": 0.6049,
      "step": 9655
    },
    {
      "epoch": 0.29662396706908734,
      "grad_norm": 1.3200701475143433,
      "learning_rate": 1.895264640084553e-05,
      "loss": 0.5471,
      "step": 9656
    },
    {
      "epoch": 0.2966546862040365,
      "grad_norm": 0.3239513635635376,
      "learning_rate": 1.8952431073537723e-05,
      "loss": 0.4842,
      "step": 9657
    },
    {
      "epoch": 0.29668540533898563,
      "grad_norm": 0.29912689328193665,
      "learning_rate": 1.8952215725320885e-05,
      "loss": 0.5429,
      "step": 9658
    },
    {
      "epoch": 0.2967161244739348,
      "grad_norm": 0.4870859682559967,
      "learning_rate": 1.8952000356195522e-05,
      "loss": 0.5589,
      "step": 9659
    },
    {
      "epoch": 0.296746843608884,
      "grad_norm": 0.38821282982826233,
      "learning_rate": 1.8951784966162138e-05,
      "loss": 0.5068,
      "step": 9660
    },
    {
      "epoch": 0.29677756274383316,
      "grad_norm": 0.3341291546821594,
      "learning_rate": 1.8951569555221235e-05,
      "loss": 0.602,
      "step": 9661
    },
    {
      "epoch": 0.2968082818787823,
      "grad_norm": 0.370922327041626,
      "learning_rate": 1.8951354123373317e-05,
      "loss": 0.6539,
      "step": 9662
    },
    {
      "epoch": 0.29683900101373145,
      "grad_norm": 0.42636317014694214,
      "learning_rate": 1.8951138670618884e-05,
      "loss": 0.6751,
      "step": 9663
    },
    {
      "epoch": 0.2968697201486806,
      "grad_norm": 0.3206750154495239,
      "learning_rate": 1.895092319695844e-05,
      "loss": 0.5513,
      "step": 9664
    },
    {
      "epoch": 0.29690043928362975,
      "grad_norm": 0.43418148159980774,
      "learning_rate": 1.8950707702392494e-05,
      "loss": 0.6398,
      "step": 9665
    },
    {
      "epoch": 0.2969311584185789,
      "grad_norm": 0.32011228799819946,
      "learning_rate": 1.895049218692154e-05,
      "loss": 0.599,
      "step": 9666
    },
    {
      "epoch": 0.2969618775535281,
      "grad_norm": 0.3483123481273651,
      "learning_rate": 1.8950276650546093e-05,
      "loss": 0.6033,
      "step": 9667
    },
    {
      "epoch": 0.2969925966884773,
      "grad_norm": 0.3314444124698639,
      "learning_rate": 1.8950061093266645e-05,
      "loss": 0.5796,
      "step": 9668
    },
    {
      "epoch": 0.2970233158234264,
      "grad_norm": 0.31698739528656006,
      "learning_rate": 1.8949845515083706e-05,
      "loss": 0.536,
      "step": 9669
    },
    {
      "epoch": 0.29705403495837557,
      "grad_norm": 0.4664519429206848,
      "learning_rate": 1.8949629915997775e-05,
      "loss": 0.5823,
      "step": 9670
    },
    {
      "epoch": 0.29708475409332474,
      "grad_norm": 0.5449690222740173,
      "learning_rate": 1.8949414296009362e-05,
      "loss": 0.5268,
      "step": 9671
    },
    {
      "epoch": 0.2971154732282739,
      "grad_norm": 0.3628597557544708,
      "learning_rate": 1.8949198655118967e-05,
      "loss": 0.4785,
      "step": 9672
    },
    {
      "epoch": 0.29714619236322304,
      "grad_norm": 0.32228782773017883,
      "learning_rate": 1.894898299332709e-05,
      "loss": 0.5391,
      "step": 9673
    },
    {
      "epoch": 0.2971769114981722,
      "grad_norm": 0.3507341742515564,
      "learning_rate": 1.8948767310634243e-05,
      "loss": 0.5636,
      "step": 9674
    },
    {
      "epoch": 0.2972076306331214,
      "grad_norm": 0.36541247367858887,
      "learning_rate": 1.894855160704092e-05,
      "loss": 0.5146,
      "step": 9675
    },
    {
      "epoch": 0.2972383497680705,
      "grad_norm": 0.3069060444831848,
      "learning_rate": 1.894833588254763e-05,
      "loss": 0.5857,
      "step": 9676
    },
    {
      "epoch": 0.2972690689030197,
      "grad_norm": 0.37467294931411743,
      "learning_rate": 1.8948120137154882e-05,
      "loss": 0.6485,
      "step": 9677
    },
    {
      "epoch": 0.29729978803796886,
      "grad_norm": 0.3611754775047302,
      "learning_rate": 1.894790437086317e-05,
      "loss": 0.5879,
      "step": 9678
    },
    {
      "epoch": 0.29733050717291803,
      "grad_norm": 0.35206878185272217,
      "learning_rate": 1.8947688583673005e-05,
      "loss": 0.59,
      "step": 9679
    },
    {
      "epoch": 0.29736122630786715,
      "grad_norm": 0.3507348895072937,
      "learning_rate": 1.8947472775584886e-05,
      "loss": 0.5969,
      "step": 9680
    },
    {
      "epoch": 0.29739194544281633,
      "grad_norm": 0.43686017394065857,
      "learning_rate": 1.8947256946599323e-05,
      "loss": 0.6193,
      "step": 9681
    },
    {
      "epoch": 0.2974226645777655,
      "grad_norm": 0.3680882155895233,
      "learning_rate": 1.8947041096716813e-05,
      "loss": 0.5458,
      "step": 9682
    },
    {
      "epoch": 0.2974533837127146,
      "grad_norm": 0.3411954343318939,
      "learning_rate": 1.894682522593786e-05,
      "loss": 0.5411,
      "step": 9683
    },
    {
      "epoch": 0.2974841028476638,
      "grad_norm": 0.3226383924484253,
      "learning_rate": 1.894660933426298e-05,
      "loss": 0.4761,
      "step": 9684
    },
    {
      "epoch": 0.297514821982613,
      "grad_norm": 0.3287183940410614,
      "learning_rate": 1.8946393421692666e-05,
      "loss": 0.5313,
      "step": 9685
    },
    {
      "epoch": 0.29754554111756215,
      "grad_norm": 0.36605122685432434,
      "learning_rate": 1.8946177488227425e-05,
      "loss": 0.6112,
      "step": 9686
    },
    {
      "epoch": 0.29757626025251127,
      "grad_norm": 0.341158002614975,
      "learning_rate": 1.8945961533867758e-05,
      "loss": 0.5711,
      "step": 9687
    },
    {
      "epoch": 0.29760697938746045,
      "grad_norm": 0.3511313199996948,
      "learning_rate": 1.894574555861418e-05,
      "loss": 0.5946,
      "step": 9688
    },
    {
      "epoch": 0.2976376985224096,
      "grad_norm": 0.3349838852882385,
      "learning_rate": 1.8945529562467183e-05,
      "loss": 0.5783,
      "step": 9689
    },
    {
      "epoch": 0.29766841765735874,
      "grad_norm": 0.33322975039482117,
      "learning_rate": 1.8945313545427278e-05,
      "loss": 0.5872,
      "step": 9690
    },
    {
      "epoch": 0.2976991367923079,
      "grad_norm": 0.3456408977508545,
      "learning_rate": 1.894509750749497e-05,
      "loss": 0.5115,
      "step": 9691
    },
    {
      "epoch": 0.2977298559272571,
      "grad_norm": 0.33262738585472107,
      "learning_rate": 1.8944881448670764e-05,
      "loss": 0.6059,
      "step": 9692
    },
    {
      "epoch": 0.29776057506220627,
      "grad_norm": 0.43280312418937683,
      "learning_rate": 1.894466536895516e-05,
      "loss": 0.5944,
      "step": 9693
    },
    {
      "epoch": 0.2977912941971554,
      "grad_norm": 0.373259961605072,
      "learning_rate": 1.8944449268348662e-05,
      "loss": 0.5739,
      "step": 9694
    },
    {
      "epoch": 0.29782201333210456,
      "grad_norm": 0.3306981921195984,
      "learning_rate": 1.8944233146851784e-05,
      "loss": 0.5369,
      "step": 9695
    },
    {
      "epoch": 0.29785273246705374,
      "grad_norm": 0.35690996050834656,
      "learning_rate": 1.8944017004465022e-05,
      "loss": 0.5134,
      "step": 9696
    },
    {
      "epoch": 0.2978834516020029,
      "grad_norm": 0.3423795998096466,
      "learning_rate": 1.8943800841188884e-05,
      "loss": 0.5529,
      "step": 9697
    },
    {
      "epoch": 0.29791417073695203,
      "grad_norm": 0.3673200309276581,
      "learning_rate": 1.8943584657023876e-05,
      "loss": 0.6672,
      "step": 9698
    },
    {
      "epoch": 0.2979448898719012,
      "grad_norm": 0.7449862957000732,
      "learning_rate": 1.8943368451970497e-05,
      "loss": 0.5315,
      "step": 9699
    },
    {
      "epoch": 0.2979756090068504,
      "grad_norm": 0.3451801538467407,
      "learning_rate": 1.8943152226029262e-05,
      "loss": 0.577,
      "step": 9700
    },
    {
      "epoch": 0.2980063281417995,
      "grad_norm": 0.35647618770599365,
      "learning_rate": 1.894293597920067e-05,
      "loss": 0.5921,
      "step": 9701
    },
    {
      "epoch": 0.2980370472767487,
      "grad_norm": 0.3581673800945282,
      "learning_rate": 1.8942719711485222e-05,
      "loss": 0.6615,
      "step": 9702
    },
    {
      "epoch": 0.29806776641169785,
      "grad_norm": 0.3532733917236328,
      "learning_rate": 1.894250342288343e-05,
      "loss": 0.6722,
      "step": 9703
    },
    {
      "epoch": 0.29809848554664703,
      "grad_norm": 0.3806120455265045,
      "learning_rate": 1.8942287113395795e-05,
      "loss": 0.6679,
      "step": 9704
    },
    {
      "epoch": 0.29812920468159615,
      "grad_norm": 0.38543716073036194,
      "learning_rate": 1.8942070783022827e-05,
      "loss": 0.5527,
      "step": 9705
    },
    {
      "epoch": 0.2981599238165453,
      "grad_norm": 0.42976677417755127,
      "learning_rate": 1.8941854431765026e-05,
      "loss": 0.6042,
      "step": 9706
    },
    {
      "epoch": 0.2981906429514945,
      "grad_norm": 0.36115238070487976,
      "learning_rate": 1.8941638059622902e-05,
      "loss": 0.6303,
      "step": 9707
    },
    {
      "epoch": 0.2982213620864436,
      "grad_norm": 0.34805527329444885,
      "learning_rate": 1.8941421666596954e-05,
      "loss": 0.5649,
      "step": 9708
    },
    {
      "epoch": 0.2982520812213928,
      "grad_norm": 0.30281224846839905,
      "learning_rate": 1.8941205252687697e-05,
      "loss": 0.5037,
      "step": 9709
    },
    {
      "epoch": 0.29828280035634197,
      "grad_norm": 0.3630819618701935,
      "learning_rate": 1.8940988817895625e-05,
      "loss": 0.5498,
      "step": 9710
    },
    {
      "epoch": 0.29831351949129115,
      "grad_norm": 0.5251935124397278,
      "learning_rate": 1.894077236222125e-05,
      "loss": 0.5154,
      "step": 9711
    },
    {
      "epoch": 0.29834423862624027,
      "grad_norm": 0.3680869936943054,
      "learning_rate": 1.894055588566508e-05,
      "loss": 0.4976,
      "step": 9712
    },
    {
      "epoch": 0.29837495776118944,
      "grad_norm": 0.4132069945335388,
      "learning_rate": 1.8940339388227613e-05,
      "loss": 0.5496,
      "step": 9713
    },
    {
      "epoch": 0.2984056768961386,
      "grad_norm": 0.31690049171447754,
      "learning_rate": 1.894012286990936e-05,
      "loss": 0.5123,
      "step": 9714
    },
    {
      "epoch": 0.2984363960310878,
      "grad_norm": 0.32258421182632446,
      "learning_rate": 1.893990633071083e-05,
      "loss": 0.5423,
      "step": 9715
    },
    {
      "epoch": 0.2984671151660369,
      "grad_norm": 0.38948675990104675,
      "learning_rate": 1.8939689770632518e-05,
      "loss": 0.5141,
      "step": 9716
    },
    {
      "epoch": 0.2984978343009861,
      "grad_norm": 0.40721848607063293,
      "learning_rate": 1.8939473189674943e-05,
      "loss": 0.5313,
      "step": 9717
    },
    {
      "epoch": 0.29852855343593526,
      "grad_norm": 0.46411463618278503,
      "learning_rate": 1.89392565878386e-05,
      "loss": 0.5724,
      "step": 9718
    },
    {
      "epoch": 0.2985592725708844,
      "grad_norm": 0.3649371862411499,
      "learning_rate": 1.8939039965123997e-05,
      "loss": 0.5826,
      "step": 9719
    },
    {
      "epoch": 0.29858999170583356,
      "grad_norm": 0.3373148441314697,
      "learning_rate": 1.8938823321531645e-05,
      "loss": 0.6442,
      "step": 9720
    },
    {
      "epoch": 0.29862071084078273,
      "grad_norm": 0.34521934390068054,
      "learning_rate": 1.8938606657062046e-05,
      "loss": 0.5778,
      "step": 9721
    },
    {
      "epoch": 0.2986514299757319,
      "grad_norm": 0.4534342885017395,
      "learning_rate": 1.8938389971715707e-05,
      "loss": 0.5956,
      "step": 9722
    },
    {
      "epoch": 0.29868214911068103,
      "grad_norm": 0.39713844656944275,
      "learning_rate": 1.8938173265493133e-05,
      "loss": 0.5674,
      "step": 9723
    },
    {
      "epoch": 0.2987128682456302,
      "grad_norm": 0.39545366168022156,
      "learning_rate": 1.8937956538394833e-05,
      "loss": 0.6148,
      "step": 9724
    },
    {
      "epoch": 0.2987435873805794,
      "grad_norm": 0.43316736817359924,
      "learning_rate": 1.893773979042131e-05,
      "loss": 0.5104,
      "step": 9725
    },
    {
      "epoch": 0.2987743065155285,
      "grad_norm": 0.35092291235923767,
      "learning_rate": 1.893752302157307e-05,
      "loss": 0.5924,
      "step": 9726
    },
    {
      "epoch": 0.2988050256504777,
      "grad_norm": 0.34616145491600037,
      "learning_rate": 1.8937306231850626e-05,
      "loss": 0.5936,
      "step": 9727
    },
    {
      "epoch": 0.29883574478542685,
      "grad_norm": 0.46127307415008545,
      "learning_rate": 1.8937089421254474e-05,
      "loss": 0.6318,
      "step": 9728
    },
    {
      "epoch": 0.298866463920376,
      "grad_norm": 0.321965754032135,
      "learning_rate": 1.893687258978513e-05,
      "loss": 0.5672,
      "step": 9729
    },
    {
      "epoch": 0.29889718305532514,
      "grad_norm": 0.35799023509025574,
      "learning_rate": 1.893665573744309e-05,
      "loss": 0.6111,
      "step": 9730
    },
    {
      "epoch": 0.2989279021902743,
      "grad_norm": 0.3644561767578125,
      "learning_rate": 1.893643886422887e-05,
      "loss": 0.5814,
      "step": 9731
    },
    {
      "epoch": 0.2989586213252235,
      "grad_norm": 0.32626402378082275,
      "learning_rate": 1.8936221970142973e-05,
      "loss": 0.6332,
      "step": 9732
    },
    {
      "epoch": 0.2989893404601726,
      "grad_norm": 0.37310850620269775,
      "learning_rate": 1.8936005055185904e-05,
      "loss": 0.5569,
      "step": 9733
    },
    {
      "epoch": 0.2990200595951218,
      "grad_norm": 0.3659583628177643,
      "learning_rate": 1.893578811935817e-05,
      "loss": 0.5864,
      "step": 9734
    },
    {
      "epoch": 0.29905077873007097,
      "grad_norm": 0.31997251510620117,
      "learning_rate": 1.8935571162660283e-05,
      "loss": 0.6191,
      "step": 9735
    },
    {
      "epoch": 0.29908149786502014,
      "grad_norm": 0.3536742031574249,
      "learning_rate": 1.8935354185092744e-05,
      "loss": 0.5276,
      "step": 9736
    },
    {
      "epoch": 0.29911221699996926,
      "grad_norm": 0.32654187083244324,
      "learning_rate": 1.8935137186656062e-05,
      "loss": 0.5148,
      "step": 9737
    },
    {
      "epoch": 0.29914293613491844,
      "grad_norm": 0.3629055619239807,
      "learning_rate": 1.893492016735074e-05,
      "loss": 0.6056,
      "step": 9738
    },
    {
      "epoch": 0.2991736552698676,
      "grad_norm": 0.35628142952919006,
      "learning_rate": 1.893470312717729e-05,
      "loss": 0.5945,
      "step": 9739
    },
    {
      "epoch": 0.2992043744048168,
      "grad_norm": 0.3607926368713379,
      "learning_rate": 1.8934486066136215e-05,
      "loss": 0.5968,
      "step": 9740
    },
    {
      "epoch": 0.2992350935397659,
      "grad_norm": 0.3886013627052307,
      "learning_rate": 1.8934268984228027e-05,
      "loss": 0.6821,
      "step": 9741
    },
    {
      "epoch": 0.2992658126747151,
      "grad_norm": 0.33939847350120544,
      "learning_rate": 1.8934051881453227e-05,
      "loss": 0.5894,
      "step": 9742
    },
    {
      "epoch": 0.29929653180966426,
      "grad_norm": 0.5812739729881287,
      "learning_rate": 1.893383475781233e-05,
      "loss": 0.6531,
      "step": 9743
    },
    {
      "epoch": 0.2993272509446134,
      "grad_norm": 0.3648979067802429,
      "learning_rate": 1.893361761330583e-05,
      "loss": 0.627,
      "step": 9744
    },
    {
      "epoch": 0.29935797007956255,
      "grad_norm": 0.3355835974216461,
      "learning_rate": 1.8933400447934245e-05,
      "loss": 0.5387,
      "step": 9745
    },
    {
      "epoch": 0.2993886892145117,
      "grad_norm": 0.32549765706062317,
      "learning_rate": 1.8933183261698083e-05,
      "loss": 0.6227,
      "step": 9746
    },
    {
      "epoch": 0.2994194083494609,
      "grad_norm": 0.3668591380119324,
      "learning_rate": 1.8932966054597847e-05,
      "loss": 0.5712,
      "step": 9747
    },
    {
      "epoch": 0.29945012748441,
      "grad_norm": 0.4148511290550232,
      "learning_rate": 1.8932748826634043e-05,
      "loss": 0.6631,
      "step": 9748
    },
    {
      "epoch": 0.2994808466193592,
      "grad_norm": 0.35653775930404663,
      "learning_rate": 1.8932531577807178e-05,
      "loss": 0.5603,
      "step": 9749
    },
    {
      "epoch": 0.2995115657543084,
      "grad_norm": 0.37883543968200684,
      "learning_rate": 1.8932314308117762e-05,
      "loss": 0.5792,
      "step": 9750
    },
    {
      "epoch": 0.2995422848892575,
      "grad_norm": 0.3593836724758148,
      "learning_rate": 1.8932097017566308e-05,
      "loss": 0.5799,
      "step": 9751
    },
    {
      "epoch": 0.29957300402420667,
      "grad_norm": 0.3820744752883911,
      "learning_rate": 1.893187970615331e-05,
      "loss": 0.506,
      "step": 9752
    },
    {
      "epoch": 0.29960372315915584,
      "grad_norm": 0.3519326448440552,
      "learning_rate": 1.893166237387929e-05,
      "loss": 0.5923,
      "step": 9753
    },
    {
      "epoch": 0.299634442294105,
      "grad_norm": 0.4042578637599945,
      "learning_rate": 1.8931445020744744e-05,
      "loss": 0.6344,
      "step": 9754
    },
    {
      "epoch": 0.29966516142905414,
      "grad_norm": 0.34212157130241394,
      "learning_rate": 1.8931227646750184e-05,
      "loss": 0.6168,
      "step": 9755
    },
    {
      "epoch": 0.2996958805640033,
      "grad_norm": 0.34083041548728943,
      "learning_rate": 1.8931010251896122e-05,
      "loss": 0.6382,
      "step": 9756
    },
    {
      "epoch": 0.2997265996989525,
      "grad_norm": 0.3626774251461029,
      "learning_rate": 1.893079283618306e-05,
      "loss": 0.6179,
      "step": 9757
    },
    {
      "epoch": 0.29975731883390166,
      "grad_norm": 0.3715450167655945,
      "learning_rate": 1.893057539961151e-05,
      "loss": 0.5738,
      "step": 9758
    },
    {
      "epoch": 0.2997880379688508,
      "grad_norm": 0.37936174869537354,
      "learning_rate": 1.8930357942181974e-05,
      "loss": 0.5287,
      "step": 9759
    },
    {
      "epoch": 0.29981875710379996,
      "grad_norm": 0.37417909502983093,
      "learning_rate": 1.8930140463894964e-05,
      "loss": 0.597,
      "step": 9760
    },
    {
      "epoch": 0.29984947623874914,
      "grad_norm": 0.406817764043808,
      "learning_rate": 1.8929922964750988e-05,
      "loss": 0.5499,
      "step": 9761
    },
    {
      "epoch": 0.29988019537369826,
      "grad_norm": 0.35832393169403076,
      "learning_rate": 1.892970544475055e-05,
      "loss": 0.5132,
      "step": 9762
    },
    {
      "epoch": 0.29991091450864743,
      "grad_norm": 0.3213738203048706,
      "learning_rate": 1.8929487903894164e-05,
      "loss": 0.528,
      "step": 9763
    },
    {
      "epoch": 0.2999416336435966,
      "grad_norm": 0.350562185049057,
      "learning_rate": 1.8929270342182337e-05,
      "loss": 0.6005,
      "step": 9764
    },
    {
      "epoch": 0.2999723527785458,
      "grad_norm": 0.401511549949646,
      "learning_rate": 1.8929052759615573e-05,
      "loss": 0.5994,
      "step": 9765
    },
    {
      "epoch": 0.3000030719134949,
      "grad_norm": 0.3740898668766022,
      "learning_rate": 1.8928835156194383e-05,
      "loss": 0.5572,
      "step": 9766
    },
    {
      "epoch": 0.3000337910484441,
      "grad_norm": 0.38960540294647217,
      "learning_rate": 1.8928617531919276e-05,
      "loss": 0.6311,
      "step": 9767
    },
    {
      "epoch": 0.30006451018339325,
      "grad_norm": 0.3660237491130829,
      "learning_rate": 1.892839988679076e-05,
      "loss": 0.5382,
      "step": 9768
    },
    {
      "epoch": 0.30009522931834237,
      "grad_norm": 0.3188658356666565,
      "learning_rate": 1.892818222080934e-05,
      "loss": 0.5701,
      "step": 9769
    },
    {
      "epoch": 0.30012594845329155,
      "grad_norm": 0.3346870541572571,
      "learning_rate": 1.892796453397553e-05,
      "loss": 0.6217,
      "step": 9770
    },
    {
      "epoch": 0.3001566675882407,
      "grad_norm": 0.42022961378097534,
      "learning_rate": 1.8927746826289833e-05,
      "loss": 0.5485,
      "step": 9771
    },
    {
      "epoch": 0.3001873867231899,
      "grad_norm": 0.3893304169178009,
      "learning_rate": 1.892752909775276e-05,
      "loss": 0.5919,
      "step": 9772
    },
    {
      "epoch": 0.300218105858139,
      "grad_norm": 0.3300955593585968,
      "learning_rate": 1.8927311348364818e-05,
      "loss": 0.5564,
      "step": 9773
    },
    {
      "epoch": 0.3002488249930882,
      "grad_norm": 0.3477356433868408,
      "learning_rate": 1.892709357812652e-05,
      "loss": 0.5877,
      "step": 9774
    },
    {
      "epoch": 0.30027954412803737,
      "grad_norm": 0.5334805250167847,
      "learning_rate": 1.892687578703837e-05,
      "loss": 0.5469,
      "step": 9775
    },
    {
      "epoch": 0.3003102632629865,
      "grad_norm": 0.3429693877696991,
      "learning_rate": 1.892665797510088e-05,
      "loss": 0.5195,
      "step": 9776
    },
    {
      "epoch": 0.30034098239793566,
      "grad_norm": 0.34982946515083313,
      "learning_rate": 1.8926440142314554e-05,
      "loss": 0.5623,
      "step": 9777
    },
    {
      "epoch": 0.30037170153288484,
      "grad_norm": 0.351254403591156,
      "learning_rate": 1.8926222288679903e-05,
      "loss": 0.5362,
      "step": 9778
    },
    {
      "epoch": 0.300402420667834,
      "grad_norm": 0.3713347911834717,
      "learning_rate": 1.892600441419744e-05,
      "loss": 0.622,
      "step": 9779
    },
    {
      "epoch": 0.30043313980278313,
      "grad_norm": 0.5005961060523987,
      "learning_rate": 1.8925786518867666e-05,
      "loss": 0.5601,
      "step": 9780
    },
    {
      "epoch": 0.3004638589377323,
      "grad_norm": 0.3979525566101074,
      "learning_rate": 1.8925568602691098e-05,
      "loss": 0.6036,
      "step": 9781
    },
    {
      "epoch": 0.3004945780726815,
      "grad_norm": 0.386653870344162,
      "learning_rate": 1.8925350665668238e-05,
      "loss": 0.591,
      "step": 9782
    },
    {
      "epoch": 0.30052529720763066,
      "grad_norm": 0.313401460647583,
      "learning_rate": 1.89251327077996e-05,
      "loss": 0.6257,
      "step": 9783
    },
    {
      "epoch": 0.3005560163425798,
      "grad_norm": 0.3643539845943451,
      "learning_rate": 1.892491472908569e-05,
      "loss": 0.6377,
      "step": 9784
    },
    {
      "epoch": 0.30058673547752895,
      "grad_norm": 0.3281020522117615,
      "learning_rate": 1.892469672952702e-05,
      "loss": 0.5528,
      "step": 9785
    },
    {
      "epoch": 0.30061745461247813,
      "grad_norm": 0.382314532995224,
      "learning_rate": 1.8924478709124096e-05,
      "loss": 0.6075,
      "step": 9786
    },
    {
      "epoch": 0.30064817374742725,
      "grad_norm": 0.32487237453460693,
      "learning_rate": 1.892426066787743e-05,
      "loss": 0.5783,
      "step": 9787
    },
    {
      "epoch": 0.3006788928823764,
      "grad_norm": 0.3571908473968506,
      "learning_rate": 1.892404260578753e-05,
      "loss": 0.5761,
      "step": 9788
    },
    {
      "epoch": 0.3007096120173256,
      "grad_norm": 0.3519640266895294,
      "learning_rate": 1.8923824522854904e-05,
      "loss": 0.6136,
      "step": 9789
    },
    {
      "epoch": 0.3007403311522748,
      "grad_norm": 0.5259837508201599,
      "learning_rate": 1.8923606419080067e-05,
      "loss": 0.7103,
      "step": 9790
    },
    {
      "epoch": 0.3007710502872239,
      "grad_norm": 0.3696957528591156,
      "learning_rate": 1.892338829446352e-05,
      "loss": 0.5925,
      "step": 9791
    },
    {
      "epoch": 0.30080176942217307,
      "grad_norm": 0.4547974169254303,
      "learning_rate": 1.8923170149005777e-05,
      "loss": 0.6638,
      "step": 9792
    },
    {
      "epoch": 0.30083248855712225,
      "grad_norm": 0.34266743063926697,
      "learning_rate": 1.8922951982707345e-05,
      "loss": 0.5936,
      "step": 9793
    },
    {
      "epoch": 0.30086320769207137,
      "grad_norm": 4.842319488525391,
      "learning_rate": 1.8922733795568738e-05,
      "loss": 0.5698,
      "step": 9794
    },
    {
      "epoch": 0.30089392682702054,
      "grad_norm": 0.3240568935871124,
      "learning_rate": 1.8922515587590464e-05,
      "loss": 0.598,
      "step": 9795
    },
    {
      "epoch": 0.3009246459619697,
      "grad_norm": 0.34860631823539734,
      "learning_rate": 1.8922297358773028e-05,
      "loss": 0.6358,
      "step": 9796
    },
    {
      "epoch": 0.3009553650969189,
      "grad_norm": 0.3302943706512451,
      "learning_rate": 1.8922079109116945e-05,
      "loss": 0.597,
      "step": 9797
    },
    {
      "epoch": 0.300986084231868,
      "grad_norm": 0.33245909214019775,
      "learning_rate": 1.8921860838622723e-05,
      "loss": 0.5513,
      "step": 9798
    },
    {
      "epoch": 0.3010168033668172,
      "grad_norm": 0.352185994386673,
      "learning_rate": 1.8921642547290874e-05,
      "loss": 0.6438,
      "step": 9799
    },
    {
      "epoch": 0.30104752250176636,
      "grad_norm": 0.32795363664627075,
      "learning_rate": 1.89214242351219e-05,
      "loss": 0.5527,
      "step": 9800
    },
    {
      "epoch": 0.3010782416367155,
      "grad_norm": 0.34153270721435547,
      "learning_rate": 1.8921205902116325e-05,
      "loss": 0.537,
      "step": 9801
    },
    {
      "epoch": 0.30110896077166466,
      "grad_norm": 0.3164662718772888,
      "learning_rate": 1.8920987548274644e-05,
      "loss": 0.5504,
      "step": 9802
    },
    {
      "epoch": 0.30113967990661383,
      "grad_norm": 0.36554601788520813,
      "learning_rate": 1.892076917359738e-05,
      "loss": 0.6489,
      "step": 9803
    },
    {
      "epoch": 0.301170399041563,
      "grad_norm": 0.4573613703250885,
      "learning_rate": 1.892055077808503e-05,
      "loss": 0.5672,
      "step": 9804
    },
    {
      "epoch": 0.30120111817651213,
      "grad_norm": 0.30034592747688293,
      "learning_rate": 1.8920332361738115e-05,
      "loss": 0.5158,
      "step": 9805
    },
    {
      "epoch": 0.3012318373114613,
      "grad_norm": 0.32124266028404236,
      "learning_rate": 1.8920113924557134e-05,
      "loss": 0.5972,
      "step": 9806
    },
    {
      "epoch": 0.3012625564464105,
      "grad_norm": 0.33118125796318054,
      "learning_rate": 1.891989546654261e-05,
      "loss": 0.5321,
      "step": 9807
    },
    {
      "epoch": 0.30129327558135965,
      "grad_norm": 0.39375749230384827,
      "learning_rate": 1.891967698769505e-05,
      "loss": 0.6092,
      "step": 9808
    },
    {
      "epoch": 0.3013239947163088,
      "grad_norm": 0.3627880811691284,
      "learning_rate": 1.8919458488014955e-05,
      "loss": 0.509,
      "step": 9809
    },
    {
      "epoch": 0.30135471385125795,
      "grad_norm": 0.4113309681415558,
      "learning_rate": 1.8919239967502845e-05,
      "loss": 0.6608,
      "step": 9810
    },
    {
      "epoch": 0.3013854329862071,
      "grad_norm": 0.3397701382637024,
      "learning_rate": 1.8919021426159227e-05,
      "loss": 0.5074,
      "step": 9811
    },
    {
      "epoch": 0.30141615212115624,
      "grad_norm": 0.36235353350639343,
      "learning_rate": 1.8918802863984612e-05,
      "loss": 0.552,
      "step": 9812
    },
    {
      "epoch": 0.3014468712561054,
      "grad_norm": 0.34509775042533875,
      "learning_rate": 1.8918584280979506e-05,
      "loss": 0.5753,
      "step": 9813
    },
    {
      "epoch": 0.3014775903910546,
      "grad_norm": 0.3207763433456421,
      "learning_rate": 1.891836567714443e-05,
      "loss": 0.5214,
      "step": 9814
    },
    {
      "epoch": 0.30150830952600377,
      "grad_norm": 0.48493248224258423,
      "learning_rate": 1.8918147052479884e-05,
      "loss": 0.6393,
      "step": 9815
    },
    {
      "epoch": 0.3015390286609529,
      "grad_norm": 0.33627498149871826,
      "learning_rate": 1.8917928406986382e-05,
      "loss": 0.6011,
      "step": 9816
    },
    {
      "epoch": 0.30156974779590207,
      "grad_norm": 0.3372403085231781,
      "learning_rate": 1.8917709740664435e-05,
      "loss": 0.5266,
      "step": 9817
    },
    {
      "epoch": 0.30160046693085124,
      "grad_norm": 1.3468095064163208,
      "learning_rate": 1.8917491053514557e-05,
      "loss": 0.5322,
      "step": 9818
    },
    {
      "epoch": 0.30163118606580036,
      "grad_norm": 0.35406410694122314,
      "learning_rate": 1.8917272345537254e-05,
      "loss": 0.5138,
      "step": 9819
    },
    {
      "epoch": 0.30166190520074954,
      "grad_norm": 0.34566235542297363,
      "learning_rate": 1.891705361673304e-05,
      "loss": 0.6013,
      "step": 9820
    },
    {
      "epoch": 0.3016926243356987,
      "grad_norm": 0.3499796390533447,
      "learning_rate": 1.8916834867102425e-05,
      "loss": 0.6188,
      "step": 9821
    },
    {
      "epoch": 0.3017233434706479,
      "grad_norm": 0.3265599310398102,
      "learning_rate": 1.891661609664592e-05,
      "loss": 0.4545,
      "step": 9822
    },
    {
      "epoch": 0.301754062605597,
      "grad_norm": 0.29185914993286133,
      "learning_rate": 1.891639730536403e-05,
      "loss": 0.5329,
      "step": 9823
    },
    {
      "epoch": 0.3017847817405462,
      "grad_norm": 0.33074602484703064,
      "learning_rate": 1.8916178493257277e-05,
      "loss": 0.6049,
      "step": 9824
    },
    {
      "epoch": 0.30181550087549536,
      "grad_norm": 0.35442373156547546,
      "learning_rate": 1.8915959660326165e-05,
      "loss": 0.5266,
      "step": 9825
    },
    {
      "epoch": 0.30184622001044453,
      "grad_norm": 0.39734819531440735,
      "learning_rate": 1.8915740806571205e-05,
      "loss": 0.6058,
      "step": 9826
    },
    {
      "epoch": 0.30187693914539365,
      "grad_norm": 4.812251091003418,
      "learning_rate": 1.891552193199291e-05,
      "loss": 0.5574,
      "step": 9827
    },
    {
      "epoch": 0.3019076582803428,
      "grad_norm": 0.3796232044696808,
      "learning_rate": 1.8915303036591793e-05,
      "loss": 0.6319,
      "step": 9828
    },
    {
      "epoch": 0.301938377415292,
      "grad_norm": 0.41651633381843567,
      "learning_rate": 1.891508412036836e-05,
      "loss": 0.5914,
      "step": 9829
    },
    {
      "epoch": 0.3019690965502411,
      "grad_norm": 0.3399599492549896,
      "learning_rate": 1.891486518332313e-05,
      "loss": 0.5971,
      "step": 9830
    },
    {
      "epoch": 0.3019998156851903,
      "grad_norm": 0.3675498366355896,
      "learning_rate": 1.8914646225456605e-05,
      "loss": 0.5656,
      "step": 9831
    },
    {
      "epoch": 0.3020305348201395,
      "grad_norm": 0.35865461826324463,
      "learning_rate": 1.8914427246769304e-05,
      "loss": 0.5999,
      "step": 9832
    },
    {
      "epoch": 0.30206125395508865,
      "grad_norm": 0.5465919971466064,
      "learning_rate": 1.8914208247261732e-05,
      "loss": 0.5834,
      "step": 9833
    },
    {
      "epoch": 0.30209197309003777,
      "grad_norm": 0.35263094305992126,
      "learning_rate": 1.891398922693441e-05,
      "loss": 0.6215,
      "step": 9834
    },
    {
      "epoch": 0.30212269222498694,
      "grad_norm": 0.3090915083885193,
      "learning_rate": 1.8913770185787837e-05,
      "loss": 0.5315,
      "step": 9835
    },
    {
      "epoch": 0.3021534113599361,
      "grad_norm": 0.3351338505744934,
      "learning_rate": 1.8913551123822536e-05,
      "loss": 0.5626,
      "step": 9836
    },
    {
      "epoch": 0.30218413049488524,
      "grad_norm": 0.3492033779621124,
      "learning_rate": 1.8913332041039016e-05,
      "loss": 0.6806,
      "step": 9837
    },
    {
      "epoch": 0.3022148496298344,
      "grad_norm": 0.446956068277359,
      "learning_rate": 1.891311293743778e-05,
      "loss": 0.6928,
      "step": 9838
    },
    {
      "epoch": 0.3022455687647836,
      "grad_norm": 0.3380007743835449,
      "learning_rate": 1.891289381301935e-05,
      "loss": 0.5004,
      "step": 9839
    },
    {
      "epoch": 0.30227628789973277,
      "grad_norm": 0.3815859258174896,
      "learning_rate": 1.8912674667784233e-05,
      "loss": 0.6452,
      "step": 9840
    },
    {
      "epoch": 0.3023070070346819,
      "grad_norm": 0.33512642979621887,
      "learning_rate": 1.8912455501732942e-05,
      "loss": 0.5905,
      "step": 9841
    },
    {
      "epoch": 0.30233772616963106,
      "grad_norm": 0.3482843041419983,
      "learning_rate": 1.891223631486599e-05,
      "loss": 0.5645,
      "step": 9842
    },
    {
      "epoch": 0.30236844530458024,
      "grad_norm": 0.34430447220802307,
      "learning_rate": 1.8912017107183886e-05,
      "loss": 0.5616,
      "step": 9843
    },
    {
      "epoch": 0.30239916443952936,
      "grad_norm": 2.0647683143615723,
      "learning_rate": 1.891179787868714e-05,
      "loss": 0.5531,
      "step": 9844
    },
    {
      "epoch": 0.30242988357447853,
      "grad_norm": 0.3844621479511261,
      "learning_rate": 1.8911578629376275e-05,
      "loss": 0.6194,
      "step": 9845
    },
    {
      "epoch": 0.3024606027094277,
      "grad_norm": 0.32170072197914124,
      "learning_rate": 1.891135935925179e-05,
      "loss": 0.5321,
      "step": 9846
    },
    {
      "epoch": 0.3024913218443769,
      "grad_norm": 0.3360769748687744,
      "learning_rate": 1.891114006831421e-05,
      "loss": 0.5887,
      "step": 9847
    },
    {
      "epoch": 0.302522040979326,
      "grad_norm": 0.46140265464782715,
      "learning_rate": 1.891092075656403e-05,
      "loss": 0.5637,
      "step": 9848
    },
    {
      "epoch": 0.3025527601142752,
      "grad_norm": 0.4348377585411072,
      "learning_rate": 1.891070142400178e-05,
      "loss": 0.575,
      "step": 9849
    },
    {
      "epoch": 0.30258347924922435,
      "grad_norm": 0.345496267080307,
      "learning_rate": 1.8910482070627964e-05,
      "loss": 0.4835,
      "step": 9850
    },
    {
      "epoch": 0.3026141983841735,
      "grad_norm": 0.35144153237342834,
      "learning_rate": 1.891026269644309e-05,
      "loss": 0.5694,
      "step": 9851
    },
    {
      "epoch": 0.30264491751912265,
      "grad_norm": 0.39945337176322937,
      "learning_rate": 1.8910043301447677e-05,
      "loss": 0.5902,
      "step": 9852
    },
    {
      "epoch": 0.3026756366540718,
      "grad_norm": 0.3443662226200104,
      "learning_rate": 1.8909823885642236e-05,
      "loss": 0.5363,
      "step": 9853
    },
    {
      "epoch": 0.302706355789021,
      "grad_norm": 0.35659876465797424,
      "learning_rate": 1.8909604449027283e-05,
      "loss": 0.577,
      "step": 9854
    },
    {
      "epoch": 0.3027370749239701,
      "grad_norm": 0.3273659348487854,
      "learning_rate": 1.8909384991603323e-05,
      "loss": 0.5568,
      "step": 9855
    },
    {
      "epoch": 0.3027677940589193,
      "grad_norm": 0.33538106083869934,
      "learning_rate": 1.8909165513370873e-05,
      "loss": 0.5809,
      "step": 9856
    },
    {
      "epoch": 0.30279851319386847,
      "grad_norm": 0.3387683629989624,
      "learning_rate": 1.8908946014330443e-05,
      "loss": 0.5514,
      "step": 9857
    },
    {
      "epoch": 0.30282923232881764,
      "grad_norm": 0.39087170362472534,
      "learning_rate": 1.890872649448255e-05,
      "loss": 0.6147,
      "step": 9858
    },
    {
      "epoch": 0.30285995146376676,
      "grad_norm": 0.34757962822914124,
      "learning_rate": 1.89085069538277e-05,
      "loss": 0.5368,
      "step": 9859
    },
    {
      "epoch": 0.30289067059871594,
      "grad_norm": 0.3617590665817261,
      "learning_rate": 1.8908287392366414e-05,
      "loss": 0.6018,
      "step": 9860
    },
    {
      "epoch": 0.3029213897336651,
      "grad_norm": 0.3540836572647095,
      "learning_rate": 1.89080678100992e-05,
      "loss": 0.6421,
      "step": 9861
    },
    {
      "epoch": 0.30295210886861423,
      "grad_norm": 0.4260205328464508,
      "learning_rate": 1.8907848207026572e-05,
      "loss": 0.6136,
      "step": 9862
    },
    {
      "epoch": 0.3029828280035634,
      "grad_norm": 0.5432726144790649,
      "learning_rate": 1.8907628583149036e-05,
      "loss": 0.5627,
      "step": 9863
    },
    {
      "epoch": 0.3030135471385126,
      "grad_norm": 0.3630073070526123,
      "learning_rate": 1.890740893846712e-05,
      "loss": 0.6272,
      "step": 9864
    },
    {
      "epoch": 0.30304426627346176,
      "grad_norm": 0.3523309826850891,
      "learning_rate": 1.8907189272981325e-05,
      "loss": 0.5886,
      "step": 9865
    },
    {
      "epoch": 0.3030749854084109,
      "grad_norm": 0.4383768141269684,
      "learning_rate": 1.890696958669217e-05,
      "loss": 0.5681,
      "step": 9866
    },
    {
      "epoch": 0.30310570454336005,
      "grad_norm": 0.4615125358104706,
      "learning_rate": 1.890674987960016e-05,
      "loss": 0.6566,
      "step": 9867
    },
    {
      "epoch": 0.30313642367830923,
      "grad_norm": 0.3570449948310852,
      "learning_rate": 1.8906530151705815e-05,
      "loss": 0.582,
      "step": 9868
    },
    {
      "epoch": 0.3031671428132584,
      "grad_norm": 0.42377203702926636,
      "learning_rate": 1.890631040300965e-05,
      "loss": 0.5363,
      "step": 9869
    },
    {
      "epoch": 0.3031978619482075,
      "grad_norm": 0.34619399905204773,
      "learning_rate": 1.890609063351217e-05,
      "loss": 0.5828,
      "step": 9870
    },
    {
      "epoch": 0.3032285810831567,
      "grad_norm": 0.3661535084247589,
      "learning_rate": 1.89058708432139e-05,
      "loss": 0.6161,
      "step": 9871
    },
    {
      "epoch": 0.3032593002181059,
      "grad_norm": 0.3999691903591156,
      "learning_rate": 1.8905651032115343e-05,
      "loss": 0.5907,
      "step": 9872
    },
    {
      "epoch": 0.303290019353055,
      "grad_norm": 0.5368747711181641,
      "learning_rate": 1.8905431200217015e-05,
      "loss": 0.5761,
      "step": 9873
    },
    {
      "epoch": 0.30332073848800417,
      "grad_norm": 0.4218517541885376,
      "learning_rate": 1.890521134751943e-05,
      "loss": 0.6385,
      "step": 9874
    },
    {
      "epoch": 0.30335145762295335,
      "grad_norm": 0.32408416271209717,
      "learning_rate": 1.8904991474023105e-05,
      "loss": 0.5681,
      "step": 9875
    },
    {
      "epoch": 0.3033821767579025,
      "grad_norm": 0.3015991151332855,
      "learning_rate": 1.890477157972855e-05,
      "loss": 0.5774,
      "step": 9876
    },
    {
      "epoch": 0.30341289589285164,
      "grad_norm": 0.3125377893447876,
      "learning_rate": 1.890455166463628e-05,
      "loss": 0.5334,
      "step": 9877
    },
    {
      "epoch": 0.3034436150278008,
      "grad_norm": 0.3599199950695038,
      "learning_rate": 1.8904331728746805e-05,
      "loss": 0.5616,
      "step": 9878
    },
    {
      "epoch": 0.30347433416275,
      "grad_norm": 0.39986562728881836,
      "learning_rate": 1.890411177206064e-05,
      "loss": 0.5864,
      "step": 9879
    },
    {
      "epoch": 0.3035050532976991,
      "grad_norm": 0.3243916928768158,
      "learning_rate": 1.8903891794578303e-05,
      "loss": 0.6336,
      "step": 9880
    },
    {
      "epoch": 0.3035357724326483,
      "grad_norm": 0.3348618745803833,
      "learning_rate": 1.8903671796300306e-05,
      "loss": 0.5309,
      "step": 9881
    },
    {
      "epoch": 0.30356649156759746,
      "grad_norm": 0.6293866634368896,
      "learning_rate": 1.890345177722716e-05,
      "loss": 0.5773,
      "step": 9882
    },
    {
      "epoch": 0.30359721070254664,
      "grad_norm": 0.39770057797431946,
      "learning_rate": 1.890323173735938e-05,
      "loss": 0.528,
      "step": 9883
    },
    {
      "epoch": 0.30362792983749576,
      "grad_norm": 0.3408668637275696,
      "learning_rate": 1.890301167669748e-05,
      "loss": 0.6154,
      "step": 9884
    },
    {
      "epoch": 0.30365864897244493,
      "grad_norm": 0.3378402590751648,
      "learning_rate": 1.8902791595241975e-05,
      "loss": 0.5815,
      "step": 9885
    },
    {
      "epoch": 0.3036893681073941,
      "grad_norm": 0.3075171113014221,
      "learning_rate": 1.8902571492993377e-05,
      "loss": 0.5143,
      "step": 9886
    },
    {
      "epoch": 0.30372008724234323,
      "grad_norm": 0.32091692090034485,
      "learning_rate": 1.8902351369952204e-05,
      "loss": 0.616,
      "step": 9887
    },
    {
      "epoch": 0.3037508063772924,
      "grad_norm": 0.3345976769924164,
      "learning_rate": 1.8902131226118967e-05,
      "loss": 0.6,
      "step": 9888
    },
    {
      "epoch": 0.3037815255122416,
      "grad_norm": 0.33128419518470764,
      "learning_rate": 1.890191106149418e-05,
      "loss": 0.5967,
      "step": 9889
    },
    {
      "epoch": 0.30381224464719075,
      "grad_norm": 0.3605402410030365,
      "learning_rate": 1.890169087607836e-05,
      "loss": 0.5244,
      "step": 9890
    },
    {
      "epoch": 0.3038429637821399,
      "grad_norm": 0.398389995098114,
      "learning_rate": 1.890147066987202e-05,
      "loss": 0.5616,
      "step": 9891
    },
    {
      "epoch": 0.30387368291708905,
      "grad_norm": 0.36818987131118774,
      "learning_rate": 1.890125044287567e-05,
      "loss": 0.5451,
      "step": 9892
    },
    {
      "epoch": 0.3039044020520382,
      "grad_norm": 0.5305724143981934,
      "learning_rate": 1.8901030195089827e-05,
      "loss": 0.6351,
      "step": 9893
    },
    {
      "epoch": 0.3039351211869874,
      "grad_norm": 0.3468591272830963,
      "learning_rate": 1.890080992651501e-05,
      "loss": 0.5988,
      "step": 9894
    },
    {
      "epoch": 0.3039658403219365,
      "grad_norm": 0.392211377620697,
      "learning_rate": 1.890058963715173e-05,
      "loss": 0.6237,
      "step": 9895
    },
    {
      "epoch": 0.3039965594568857,
      "grad_norm": 0.40877217054367065,
      "learning_rate": 1.89003693270005e-05,
      "loss": 0.5287,
      "step": 9896
    },
    {
      "epoch": 0.30402727859183487,
      "grad_norm": 0.311713308095932,
      "learning_rate": 1.8900148996061835e-05,
      "loss": 0.5368,
      "step": 9897
    },
    {
      "epoch": 0.304057997726784,
      "grad_norm": 0.340895414352417,
      "learning_rate": 1.889992864433625e-05,
      "loss": 0.5648,
      "step": 9898
    },
    {
      "epoch": 0.30408871686173317,
      "grad_norm": 0.40864527225494385,
      "learning_rate": 1.8899708271824264e-05,
      "loss": 0.6436,
      "step": 9899
    },
    {
      "epoch": 0.30411943599668234,
      "grad_norm": 0.3279697597026825,
      "learning_rate": 1.8899487878526383e-05,
      "loss": 0.6533,
      "step": 9900
    },
    {
      "epoch": 0.3041501551316315,
      "grad_norm": 0.36398983001708984,
      "learning_rate": 1.889926746444313e-05,
      "loss": 0.6985,
      "step": 9901
    },
    {
      "epoch": 0.30418087426658064,
      "grad_norm": 0.3686080276966095,
      "learning_rate": 1.8899047029575018e-05,
      "loss": 0.5568,
      "step": 9902
    },
    {
      "epoch": 0.3042115934015298,
      "grad_norm": 0.33880549669265747,
      "learning_rate": 1.8898826573922556e-05,
      "loss": 0.5993,
      "step": 9903
    },
    {
      "epoch": 0.304242312536479,
      "grad_norm": 0.32105740904808044,
      "learning_rate": 1.8898606097486264e-05,
      "loss": 0.5321,
      "step": 9904
    },
    {
      "epoch": 0.3042730316714281,
      "grad_norm": 0.35520651936531067,
      "learning_rate": 1.8898385600266657e-05,
      "loss": 0.545,
      "step": 9905
    },
    {
      "epoch": 0.3043037508063773,
      "grad_norm": 0.33155369758605957,
      "learning_rate": 1.8898165082264245e-05,
      "loss": 0.5629,
      "step": 9906
    },
    {
      "epoch": 0.30433446994132646,
      "grad_norm": 0.3769979476928711,
      "learning_rate": 1.8897944543479552e-05,
      "loss": 0.5596,
      "step": 9907
    },
    {
      "epoch": 0.30436518907627563,
      "grad_norm": 0.3615506589412689,
      "learning_rate": 1.8897723983913085e-05,
      "loss": 0.6341,
      "step": 9908
    },
    {
      "epoch": 0.30439590821122475,
      "grad_norm": 0.3326992988586426,
      "learning_rate": 1.8897503403565366e-05,
      "loss": 0.4492,
      "step": 9909
    },
    {
      "epoch": 0.30442662734617393,
      "grad_norm": 0.38371315598487854,
      "learning_rate": 1.8897282802436903e-05,
      "loss": 0.5841,
      "step": 9910
    },
    {
      "epoch": 0.3044573464811231,
      "grad_norm": 0.3910810053348541,
      "learning_rate": 1.8897062180528215e-05,
      "loss": 0.5869,
      "step": 9911
    },
    {
      "epoch": 0.3044880656160723,
      "grad_norm": 0.34559473395347595,
      "learning_rate": 1.8896841537839817e-05,
      "loss": 0.617,
      "step": 9912
    },
    {
      "epoch": 0.3045187847510214,
      "grad_norm": 0.34699463844299316,
      "learning_rate": 1.8896620874372226e-05,
      "loss": 0.621,
      "step": 9913
    },
    {
      "epoch": 0.3045495038859706,
      "grad_norm": 0.32255831360816956,
      "learning_rate": 1.8896400190125955e-05,
      "loss": 0.5442,
      "step": 9914
    },
    {
      "epoch": 0.30458022302091975,
      "grad_norm": 0.35639163851737976,
      "learning_rate": 1.8896179485101518e-05,
      "loss": 0.6233,
      "step": 9915
    },
    {
      "epoch": 0.30461094215586887,
      "grad_norm": 0.3640806972980499,
      "learning_rate": 1.8895958759299435e-05,
      "loss": 0.6905,
      "step": 9916
    },
    {
      "epoch": 0.30464166129081804,
      "grad_norm": 0.32711413502693176,
      "learning_rate": 1.8895738012720216e-05,
      "loss": 0.5743,
      "step": 9917
    },
    {
      "epoch": 0.3046723804257672,
      "grad_norm": 0.39371258020401,
      "learning_rate": 1.889551724536438e-05,
      "loss": 0.5752,
      "step": 9918
    },
    {
      "epoch": 0.3047030995607164,
      "grad_norm": 0.3582613468170166,
      "learning_rate": 1.8895296457232445e-05,
      "loss": 0.5562,
      "step": 9919
    },
    {
      "epoch": 0.3047338186956655,
      "grad_norm": 0.33960965275764465,
      "learning_rate": 1.8895075648324926e-05,
      "loss": 0.5751,
      "step": 9920
    },
    {
      "epoch": 0.3047645378306147,
      "grad_norm": 0.3630307614803314,
      "learning_rate": 1.8894854818642333e-05,
      "loss": 0.6625,
      "step": 9921
    },
    {
      "epoch": 0.30479525696556387,
      "grad_norm": 0.34760040044784546,
      "learning_rate": 1.889463396818518e-05,
      "loss": 0.6096,
      "step": 9922
    },
    {
      "epoch": 0.304825976100513,
      "grad_norm": 0.3874387741088867,
      "learning_rate": 1.8894413096954e-05,
      "loss": 0.5292,
      "step": 9923
    },
    {
      "epoch": 0.30485669523546216,
      "grad_norm": 0.3276844918727875,
      "learning_rate": 1.889419220494929e-05,
      "loss": 0.5229,
      "step": 9924
    },
    {
      "epoch": 0.30488741437041134,
      "grad_norm": 0.3395276367664337,
      "learning_rate": 1.8893971292171574e-05,
      "loss": 0.6243,
      "step": 9925
    },
    {
      "epoch": 0.3049181335053605,
      "grad_norm": 0.3286516070365906,
      "learning_rate": 1.8893750358621365e-05,
      "loss": 0.632,
      "step": 9926
    },
    {
      "epoch": 0.30494885264030963,
      "grad_norm": 0.3183748126029968,
      "learning_rate": 1.8893529404299184e-05,
      "loss": 0.6163,
      "step": 9927
    },
    {
      "epoch": 0.3049795717752588,
      "grad_norm": 0.33764857053756714,
      "learning_rate": 1.8893308429205543e-05,
      "loss": 0.596,
      "step": 9928
    },
    {
      "epoch": 0.305010290910208,
      "grad_norm": 0.32921215891838074,
      "learning_rate": 1.8893087433340956e-05,
      "loss": 0.5477,
      "step": 9929
    },
    {
      "epoch": 0.3050410100451571,
      "grad_norm": 0.329491525888443,
      "learning_rate": 1.8892866416705943e-05,
      "loss": 0.5129,
      "step": 9930
    },
    {
      "epoch": 0.3050717291801063,
      "grad_norm": 0.33389899134635925,
      "learning_rate": 1.889264537930102e-05,
      "loss": 0.5555,
      "step": 9931
    },
    {
      "epoch": 0.30510244831505545,
      "grad_norm": 0.35288867354393005,
      "learning_rate": 1.889242432112671e-05,
      "loss": 0.6272,
      "step": 9932
    },
    {
      "epoch": 0.3051331674500046,
      "grad_norm": 0.3469499349594116,
      "learning_rate": 1.8892203242183515e-05,
      "loss": 0.6328,
      "step": 9933
    },
    {
      "epoch": 0.30516388658495375,
      "grad_norm": 0.3566821813583374,
      "learning_rate": 1.8891982142471957e-05,
      "loss": 0.6506,
      "step": 9934
    },
    {
      "epoch": 0.3051946057199029,
      "grad_norm": 0.35370492935180664,
      "learning_rate": 1.8891761021992558e-05,
      "loss": 0.6303,
      "step": 9935
    },
    {
      "epoch": 0.3052253248548521,
      "grad_norm": 0.3763185441493988,
      "learning_rate": 1.8891539880745824e-05,
      "loss": 0.5715,
      "step": 9936
    },
    {
      "epoch": 0.3052560439898013,
      "grad_norm": 0.34496089816093445,
      "learning_rate": 1.8891318718732283e-05,
      "loss": 0.5301,
      "step": 9937
    },
    {
      "epoch": 0.3052867631247504,
      "grad_norm": 0.3579116463661194,
      "learning_rate": 1.8891097535952445e-05,
      "loss": 0.61,
      "step": 9938
    },
    {
      "epoch": 0.30531748225969957,
      "grad_norm": 0.4633854925632477,
      "learning_rate": 1.8890876332406828e-05,
      "loss": 0.595,
      "step": 9939
    },
    {
      "epoch": 0.30534820139464874,
      "grad_norm": 0.37265926599502563,
      "learning_rate": 1.8890655108095948e-05,
      "loss": 0.5301,
      "step": 9940
    },
    {
      "epoch": 0.30537892052959786,
      "grad_norm": 0.3488740622997284,
      "learning_rate": 1.8890433863020323e-05,
      "loss": 0.6332,
      "step": 9941
    },
    {
      "epoch": 0.30540963966454704,
      "grad_norm": 0.43392443656921387,
      "learning_rate": 1.8890212597180468e-05,
      "loss": 0.6091,
      "step": 9942
    },
    {
      "epoch": 0.3054403587994962,
      "grad_norm": 0.3420165479183197,
      "learning_rate": 1.8889991310576898e-05,
      "loss": 0.6326,
      "step": 9943
    },
    {
      "epoch": 0.3054710779344454,
      "grad_norm": 0.36513710021972656,
      "learning_rate": 1.8889770003210134e-05,
      "loss": 0.5935,
      "step": 9944
    },
    {
      "epoch": 0.3055017970693945,
      "grad_norm": 0.31938764452934265,
      "learning_rate": 1.8889548675080692e-05,
      "loss": 0.5705,
      "step": 9945
    },
    {
      "epoch": 0.3055325162043437,
      "grad_norm": 0.3531520366668701,
      "learning_rate": 1.8889327326189087e-05,
      "loss": 0.5895,
      "step": 9946
    },
    {
      "epoch": 0.30556323533929286,
      "grad_norm": 0.3799550533294678,
      "learning_rate": 1.888910595653584e-05,
      "loss": 0.6171,
      "step": 9947
    },
    {
      "epoch": 0.305593954474242,
      "grad_norm": 0.347092866897583,
      "learning_rate": 1.8888884566121464e-05,
      "loss": 0.5941,
      "step": 9948
    },
    {
      "epoch": 0.30562467360919116,
      "grad_norm": 0.41327041387557983,
      "learning_rate": 1.888866315494648e-05,
      "loss": 0.6435,
      "step": 9949
    },
    {
      "epoch": 0.30565539274414033,
      "grad_norm": 0.3668718934059143,
      "learning_rate": 1.88884417230114e-05,
      "loss": 0.557,
      "step": 9950
    },
    {
      "epoch": 0.3056861118790895,
      "grad_norm": 0.32888856530189514,
      "learning_rate": 1.8888220270316743e-05,
      "loss": 0.598,
      "step": 9951
    },
    {
      "epoch": 0.3057168310140386,
      "grad_norm": 0.38188689947128296,
      "learning_rate": 1.8887998796863024e-05,
      "loss": 0.6419,
      "step": 9952
    },
    {
      "epoch": 0.3057475501489878,
      "grad_norm": 0.3214038908481598,
      "learning_rate": 1.8887777302650767e-05,
      "loss": 0.5905,
      "step": 9953
    },
    {
      "epoch": 0.305778269283937,
      "grad_norm": 0.3435250222682953,
      "learning_rate": 1.8887555787680483e-05,
      "loss": 0.5726,
      "step": 9954
    },
    {
      "epoch": 0.30580898841888615,
      "grad_norm": 0.4776763319969177,
      "learning_rate": 1.8887334251952695e-05,
      "loss": 0.5335,
      "step": 9955
    },
    {
      "epoch": 0.30583970755383527,
      "grad_norm": 0.32121801376342773,
      "learning_rate": 1.8887112695467915e-05,
      "loss": 0.5696,
      "step": 9956
    },
    {
      "epoch": 0.30587042668878445,
      "grad_norm": 0.3925301134586334,
      "learning_rate": 1.8886891118226662e-05,
      "loss": 0.5791,
      "step": 9957
    },
    {
      "epoch": 0.3059011458237336,
      "grad_norm": 0.33178433775901794,
      "learning_rate": 1.8886669520229457e-05,
      "loss": 0.6259,
      "step": 9958
    },
    {
      "epoch": 0.30593186495868274,
      "grad_norm": 0.34174516797065735,
      "learning_rate": 1.888644790147681e-05,
      "loss": 0.5652,
      "step": 9959
    },
    {
      "epoch": 0.3059625840936319,
      "grad_norm": 0.41284656524658203,
      "learning_rate": 1.888622626196925e-05,
      "loss": 0.542,
      "step": 9960
    },
    {
      "epoch": 0.3059933032285811,
      "grad_norm": 0.313628613948822,
      "learning_rate": 1.8886004601707282e-05,
      "loss": 0.5397,
      "step": 9961
    },
    {
      "epoch": 0.30602402236353027,
      "grad_norm": 0.8357094526290894,
      "learning_rate": 1.8885782920691433e-05,
      "loss": 0.5804,
      "step": 9962
    },
    {
      "epoch": 0.3060547414984794,
      "grad_norm": 0.3251522183418274,
      "learning_rate": 1.8885561218922215e-05,
      "loss": 0.5301,
      "step": 9963
    },
    {
      "epoch": 0.30608546063342856,
      "grad_norm": 0.3312532305717468,
      "learning_rate": 1.888533949640015e-05,
      "loss": 0.5875,
      "step": 9964
    },
    {
      "epoch": 0.30611617976837774,
      "grad_norm": 0.3194107115268707,
      "learning_rate": 1.888511775312575e-05,
      "loss": 0.5937,
      "step": 9965
    },
    {
      "epoch": 0.30614689890332686,
      "grad_norm": 0.3785006105899811,
      "learning_rate": 1.888489598909954e-05,
      "loss": 0.6091,
      "step": 9966
    },
    {
      "epoch": 0.30617761803827603,
      "grad_norm": 0.2977648973464966,
      "learning_rate": 1.8884674204322038e-05,
      "loss": 0.497,
      "step": 9967
    },
    {
      "epoch": 0.3062083371732252,
      "grad_norm": 0.3456898033618927,
      "learning_rate": 1.8884452398793754e-05,
      "loss": 0.6084,
      "step": 9968
    },
    {
      "epoch": 0.3062390563081744,
      "grad_norm": 0.3789360523223877,
      "learning_rate": 1.8884230572515214e-05,
      "loss": 0.6294,
      "step": 9969
    },
    {
      "epoch": 0.3062697754431235,
      "grad_norm": 0.3968081772327423,
      "learning_rate": 1.8884008725486934e-05,
      "loss": 0.5075,
      "step": 9970
    },
    {
      "epoch": 0.3063004945780727,
      "grad_norm": 0.36105257272720337,
      "learning_rate": 1.8883786857709427e-05,
      "loss": 0.5815,
      "step": 9971
    },
    {
      "epoch": 0.30633121371302185,
      "grad_norm": 0.5641610622406006,
      "learning_rate": 1.8883564969183218e-05,
      "loss": 0.6045,
      "step": 9972
    },
    {
      "epoch": 0.306361932847971,
      "grad_norm": 0.33117684721946716,
      "learning_rate": 1.8883343059908825e-05,
      "loss": 0.6432,
      "step": 9973
    },
    {
      "epoch": 0.30639265198292015,
      "grad_norm": 0.34573259949684143,
      "learning_rate": 1.888312112988676e-05,
      "loss": 0.5487,
      "step": 9974
    },
    {
      "epoch": 0.3064233711178693,
      "grad_norm": 0.3382858633995056,
      "learning_rate": 1.8882899179117547e-05,
      "loss": 0.574,
      "step": 9975
    },
    {
      "epoch": 0.3064540902528185,
      "grad_norm": 0.31208863854408264,
      "learning_rate": 1.8882677207601702e-05,
      "loss": 0.5855,
      "step": 9976
    },
    {
      "epoch": 0.3064848093877676,
      "grad_norm": 0.3321830630302429,
      "learning_rate": 1.8882455215339744e-05,
      "loss": 0.6655,
      "step": 9977
    },
    {
      "epoch": 0.3065155285227168,
      "grad_norm": 0.41753196716308594,
      "learning_rate": 1.888223320233219e-05,
      "loss": 0.6121,
      "step": 9978
    },
    {
      "epoch": 0.30654624765766597,
      "grad_norm": 0.3487551212310791,
      "learning_rate": 1.888201116857956e-05,
      "loss": 0.6154,
      "step": 9979
    },
    {
      "epoch": 0.30657696679261515,
      "grad_norm": 0.32678884267807007,
      "learning_rate": 1.8881789114082378e-05,
      "loss": 0.6061,
      "step": 9980
    },
    {
      "epoch": 0.30660768592756427,
      "grad_norm": 0.3231872022151947,
      "learning_rate": 1.8881567038841152e-05,
      "loss": 0.5308,
      "step": 9981
    },
    {
      "epoch": 0.30663840506251344,
      "grad_norm": 0.43637797236442566,
      "learning_rate": 1.8881344942856404e-05,
      "loss": 0.5487,
      "step": 9982
    },
    {
      "epoch": 0.3066691241974626,
      "grad_norm": 0.32958486676216125,
      "learning_rate": 1.888112282612866e-05,
      "loss": 0.5043,
      "step": 9983
    },
    {
      "epoch": 0.30669984333241174,
      "grad_norm": 0.3088981807231903,
      "learning_rate": 1.888090068865843e-05,
      "loss": 0.5117,
      "step": 9984
    },
    {
      "epoch": 0.3067305624673609,
      "grad_norm": 0.37212008237838745,
      "learning_rate": 1.888067853044624e-05,
      "loss": 0.566,
      "step": 9985
    },
    {
      "epoch": 0.3067612816023101,
      "grad_norm": 0.3864917755126953,
      "learning_rate": 1.88804563514926e-05,
      "loss": 0.5928,
      "step": 9986
    },
    {
      "epoch": 0.30679200073725926,
      "grad_norm": 0.32944992184638977,
      "learning_rate": 1.8880234151798037e-05,
      "loss": 0.5172,
      "step": 9987
    },
    {
      "epoch": 0.3068227198722084,
      "grad_norm": 0.38873451948165894,
      "learning_rate": 1.888001193136307e-05,
      "loss": 0.6074,
      "step": 9988
    },
    {
      "epoch": 0.30685343900715756,
      "grad_norm": 0.3515758216381073,
      "learning_rate": 1.8879789690188207e-05,
      "loss": 0.5616,
      "step": 9989
    },
    {
      "epoch": 0.30688415814210673,
      "grad_norm": 0.33744922280311584,
      "learning_rate": 1.887956742827398e-05,
      "loss": 0.6179,
      "step": 9990
    },
    {
      "epoch": 0.30691487727705585,
      "grad_norm": 0.37170469760894775,
      "learning_rate": 1.8879345145620905e-05,
      "loss": 0.6421,
      "step": 9991
    },
    {
      "epoch": 0.30694559641200503,
      "grad_norm": 0.33720213174819946,
      "learning_rate": 1.8879122842229495e-05,
      "loss": 0.5433,
      "step": 9992
    },
    {
      "epoch": 0.3069763155469542,
      "grad_norm": 0.36064764857292175,
      "learning_rate": 1.8878900518100275e-05,
      "loss": 0.6484,
      "step": 9993
    },
    {
      "epoch": 0.3070070346819034,
      "grad_norm": 0.3280768394470215,
      "learning_rate": 1.8878678173233765e-05,
      "loss": 0.6127,
      "step": 9994
    },
    {
      "epoch": 0.3070377538168525,
      "grad_norm": 0.37556904554367065,
      "learning_rate": 1.887845580763048e-05,
      "loss": 0.587,
      "step": 9995
    },
    {
      "epoch": 0.3070684729518017,
      "grad_norm": 0.3739718496799469,
      "learning_rate": 1.887823342129094e-05,
      "loss": 0.6231,
      "step": 9996
    },
    {
      "epoch": 0.30709919208675085,
      "grad_norm": 0.38045257329940796,
      "learning_rate": 1.887801101421567e-05,
      "loss": 0.5637,
      "step": 9997
    },
    {
      "epoch": 0.30712991122169997,
      "grad_norm": 0.42614972591400146,
      "learning_rate": 1.887778858640518e-05,
      "loss": 0.6851,
      "step": 9998
    },
    {
      "epoch": 0.30716063035664914,
      "grad_norm": 0.3415154814720154,
      "learning_rate": 1.8877566137859997e-05,
      "loss": 0.5752,
      "step": 9999
    },
    {
      "epoch": 0.3071913494915983,
      "grad_norm": 0.3861374258995056,
      "learning_rate": 1.887734366858064e-05,
      "loss": 0.5641,
      "step": 10000
    },
    {
      "epoch": 0.3072220686265475,
      "grad_norm": 0.37221187353134155,
      "learning_rate": 1.8877121178567623e-05,
      "loss": 0.6766,
      "step": 10001
    },
    {
      "epoch": 0.3072527877614966,
      "grad_norm": 0.30903518199920654,
      "learning_rate": 1.8876898667821474e-05,
      "loss": 0.5787,
      "step": 10002
    },
    {
      "epoch": 0.3072835068964458,
      "grad_norm": 0.3347099721431732,
      "learning_rate": 1.8876676136342705e-05,
      "loss": 0.5643,
      "step": 10003
    },
    {
      "epoch": 0.30731422603139497,
      "grad_norm": 0.3674643635749817,
      "learning_rate": 1.8876453584131843e-05,
      "loss": 0.5903,
      "step": 10004
    },
    {
      "epoch": 0.30734494516634414,
      "grad_norm": 0.42166125774383545,
      "learning_rate": 1.8876231011189402e-05,
      "loss": 0.5661,
      "step": 10005
    },
    {
      "epoch": 0.30737566430129326,
      "grad_norm": 0.36162781715393066,
      "learning_rate": 1.8876008417515898e-05,
      "loss": 0.4917,
      "step": 10006
    },
    {
      "epoch": 0.30740638343624244,
      "grad_norm": 0.3370506167411804,
      "learning_rate": 1.8875785803111865e-05,
      "loss": 0.5598,
      "step": 10007
    },
    {
      "epoch": 0.3074371025711916,
      "grad_norm": 0.33867594599723816,
      "learning_rate": 1.8875563167977806e-05,
      "loss": 0.5801,
      "step": 10008
    },
    {
      "epoch": 0.30746782170614073,
      "grad_norm": 0.317330539226532,
      "learning_rate": 1.8875340512114255e-05,
      "loss": 0.6385,
      "step": 10009
    },
    {
      "epoch": 0.3074985408410899,
      "grad_norm": 0.29902172088623047,
      "learning_rate": 1.8875117835521727e-05,
      "loss": 0.519,
      "step": 10010
    },
    {
      "epoch": 0.3075292599760391,
      "grad_norm": 0.5451877117156982,
      "learning_rate": 1.8874895138200738e-05,
      "loss": 0.6542,
      "step": 10011
    },
    {
      "epoch": 0.30755997911098826,
      "grad_norm": 0.37885478138923645,
      "learning_rate": 1.8874672420151812e-05,
      "loss": 0.6242,
      "step": 10012
    },
    {
      "epoch": 0.3075906982459374,
      "grad_norm": 0.4138130247592926,
      "learning_rate": 1.8874449681375472e-05,
      "loss": 0.6446,
      "step": 10013
    },
    {
      "epoch": 0.30762141738088655,
      "grad_norm": 0.3593983054161072,
      "learning_rate": 1.8874226921872232e-05,
      "loss": 0.5621,
      "step": 10014
    },
    {
      "epoch": 0.30765213651583573,
      "grad_norm": 0.35434043407440186,
      "learning_rate": 1.8874004141642618e-05,
      "loss": 0.5065,
      "step": 10015
    },
    {
      "epoch": 0.30768285565078485,
      "grad_norm": 0.3308510482311249,
      "learning_rate": 1.887378134068714e-05,
      "loss": 0.5755,
      "step": 10016
    },
    {
      "epoch": 0.307713574785734,
      "grad_norm": 0.3736622631549835,
      "learning_rate": 1.8873558519006333e-05,
      "loss": 0.6554,
      "step": 10017
    },
    {
      "epoch": 0.3077442939206832,
      "grad_norm": 0.3409211337566376,
      "learning_rate": 1.887333567660071e-05,
      "loss": 0.6079,
      "step": 10018
    },
    {
      "epoch": 0.3077750130556324,
      "grad_norm": 0.37091508507728577,
      "learning_rate": 1.887311281347079e-05,
      "loss": 0.5837,
      "step": 10019
    },
    {
      "epoch": 0.3078057321905815,
      "grad_norm": 0.3164612650871277,
      "learning_rate": 1.8872889929617098e-05,
      "loss": 0.5393,
      "step": 10020
    },
    {
      "epoch": 0.30783645132553067,
      "grad_norm": 0.3782636523246765,
      "learning_rate": 1.887266702504015e-05,
      "loss": 0.6013,
      "step": 10021
    },
    {
      "epoch": 0.30786717046047984,
      "grad_norm": 0.3075632154941559,
      "learning_rate": 1.8872444099740467e-05,
      "loss": 0.6226,
      "step": 10022
    },
    {
      "epoch": 0.307897889595429,
      "grad_norm": 0.36339661478996277,
      "learning_rate": 1.8872221153718576e-05,
      "loss": 0.5415,
      "step": 10023
    },
    {
      "epoch": 0.30792860873037814,
      "grad_norm": 0.3364357054233551,
      "learning_rate": 1.8871998186974987e-05,
      "loss": 0.6786,
      "step": 10024
    },
    {
      "epoch": 0.3079593278653273,
      "grad_norm": 0.33377209305763245,
      "learning_rate": 1.8871775199510228e-05,
      "loss": 0.6022,
      "step": 10025
    },
    {
      "epoch": 0.3079900470002765,
      "grad_norm": 0.35578683018684387,
      "learning_rate": 1.887155219132482e-05,
      "loss": 0.6034,
      "step": 10026
    },
    {
      "epoch": 0.3080207661352256,
      "grad_norm": 0.4250582158565521,
      "learning_rate": 1.8871329162419282e-05,
      "loss": 0.5846,
      "step": 10027
    },
    {
      "epoch": 0.3080514852701748,
      "grad_norm": 0.30402323603630066,
      "learning_rate": 1.8871106112794136e-05,
      "loss": 0.581,
      "step": 10028
    },
    {
      "epoch": 0.30808220440512396,
      "grad_norm": 0.5473057627677917,
      "learning_rate": 1.8870883042449903e-05,
      "loss": 0.53,
      "step": 10029
    },
    {
      "epoch": 0.30811292354007314,
      "grad_norm": 0.35421037673950195,
      "learning_rate": 1.8870659951387098e-05,
      "loss": 0.5716,
      "step": 10030
    },
    {
      "epoch": 0.30814364267502226,
      "grad_norm": 0.3626708686351776,
      "learning_rate": 1.887043683960625e-05,
      "loss": 0.588,
      "step": 10031
    },
    {
      "epoch": 0.30817436180997143,
      "grad_norm": 0.3443436920642853,
      "learning_rate": 1.8870213707107878e-05,
      "loss": 0.4816,
      "step": 10032
    },
    {
      "epoch": 0.3082050809449206,
      "grad_norm": 0.40728700160980225,
      "learning_rate": 1.8869990553892503e-05,
      "loss": 0.6237,
      "step": 10033
    },
    {
      "epoch": 0.3082358000798697,
      "grad_norm": 0.8146523237228394,
      "learning_rate": 1.8869767379960643e-05,
      "loss": 0.6209,
      "step": 10034
    },
    {
      "epoch": 0.3082665192148189,
      "grad_norm": 0.3572864234447479,
      "learning_rate": 1.8869544185312825e-05,
      "loss": 0.5387,
      "step": 10035
    },
    {
      "epoch": 0.3082972383497681,
      "grad_norm": 0.33158814907073975,
      "learning_rate": 1.8869320969949565e-05,
      "loss": 0.5454,
      "step": 10036
    },
    {
      "epoch": 0.30832795748471725,
      "grad_norm": 0.3370170593261719,
      "learning_rate": 1.8869097733871386e-05,
      "loss": 0.5476,
      "step": 10037
    },
    {
      "epoch": 0.30835867661966637,
      "grad_norm": 0.3635900318622589,
      "learning_rate": 1.8868874477078813e-05,
      "loss": 0.6192,
      "step": 10038
    },
    {
      "epoch": 0.30838939575461555,
      "grad_norm": 0.3283371925354004,
      "learning_rate": 1.886865119957236e-05,
      "loss": 0.6255,
      "step": 10039
    },
    {
      "epoch": 0.3084201148895647,
      "grad_norm": 0.35886794328689575,
      "learning_rate": 1.8868427901352558e-05,
      "loss": 0.653,
      "step": 10040
    },
    {
      "epoch": 0.30845083402451384,
      "grad_norm": 0.35882341861724854,
      "learning_rate": 1.8868204582419917e-05,
      "loss": 0.5975,
      "step": 10041
    },
    {
      "epoch": 0.308481553159463,
      "grad_norm": 0.9218908548355103,
      "learning_rate": 1.886798124277497e-05,
      "loss": 0.6627,
      "step": 10042
    },
    {
      "epoch": 0.3085122722944122,
      "grad_norm": 0.34815147519111633,
      "learning_rate": 1.886775788241823e-05,
      "loss": 0.607,
      "step": 10043
    },
    {
      "epoch": 0.30854299142936137,
      "grad_norm": 0.3339928984642029,
      "learning_rate": 1.8867534501350224e-05,
      "loss": 0.5714,
      "step": 10044
    },
    {
      "epoch": 0.3085737105643105,
      "grad_norm": 0.3709262013435364,
      "learning_rate": 1.8867311099571472e-05,
      "loss": 0.5093,
      "step": 10045
    },
    {
      "epoch": 0.30860442969925966,
      "grad_norm": 0.5291286110877991,
      "learning_rate": 1.8867087677082497e-05,
      "loss": 0.6351,
      "step": 10046
    },
    {
      "epoch": 0.30863514883420884,
      "grad_norm": 0.3512604832649231,
      "learning_rate": 1.8866864233883814e-05,
      "loss": 0.6609,
      "step": 10047
    },
    {
      "epoch": 0.308665867969158,
      "grad_norm": 0.35419678688049316,
      "learning_rate": 1.8866640769975957e-05,
      "loss": 0.6043,
      "step": 10048
    },
    {
      "epoch": 0.30869658710410713,
      "grad_norm": 0.336814284324646,
      "learning_rate": 1.8866417285359436e-05,
      "loss": 0.5877,
      "step": 10049
    },
    {
      "epoch": 0.3087273062390563,
      "grad_norm": 0.43308067321777344,
      "learning_rate": 1.886619378003478e-05,
      "loss": 0.5061,
      "step": 10050
    },
    {
      "epoch": 0.3087580253740055,
      "grad_norm": 0.3544464409351349,
      "learning_rate": 1.886597025400251e-05,
      "loss": 0.6102,
      "step": 10051
    },
    {
      "epoch": 0.3087887445089546,
      "grad_norm": 0.34486865997314453,
      "learning_rate": 1.8865746707263147e-05,
      "loss": 0.671,
      "step": 10052
    },
    {
      "epoch": 0.3088194636439038,
      "grad_norm": 0.4074319303035736,
      "learning_rate": 1.886552313981721e-05,
      "loss": 0.6297,
      "step": 10053
    },
    {
      "epoch": 0.30885018277885296,
      "grad_norm": 0.35648417472839355,
      "learning_rate": 1.886529955166523e-05,
      "loss": 0.561,
      "step": 10054
    },
    {
      "epoch": 0.30888090191380213,
      "grad_norm": 0.3280024826526642,
      "learning_rate": 1.8865075942807723e-05,
      "loss": 0.5178,
      "step": 10055
    },
    {
      "epoch": 0.30891162104875125,
      "grad_norm": 0.31049469113349915,
      "learning_rate": 1.886485231324521e-05,
      "loss": 0.4671,
      "step": 10056
    },
    {
      "epoch": 0.3089423401837004,
      "grad_norm": 0.3374369740486145,
      "learning_rate": 1.8864628662978216e-05,
      "loss": 0.5848,
      "step": 10057
    },
    {
      "epoch": 0.3089730593186496,
      "grad_norm": 0.3599373996257782,
      "learning_rate": 1.886440499200726e-05,
      "loss": 0.596,
      "step": 10058
    },
    {
      "epoch": 0.3090037784535987,
      "grad_norm": 0.32661235332489014,
      "learning_rate": 1.8864181300332875e-05,
      "loss": 0.4915,
      "step": 10059
    },
    {
      "epoch": 0.3090344975885479,
      "grad_norm": 0.5037582516670227,
      "learning_rate": 1.8863957587955567e-05,
      "loss": 0.6571,
      "step": 10060
    },
    {
      "epoch": 0.30906521672349707,
      "grad_norm": 0.35929858684539795,
      "learning_rate": 1.8863733854875873e-05,
      "loss": 0.6282,
      "step": 10061
    },
    {
      "epoch": 0.30909593585844625,
      "grad_norm": 0.33099040389060974,
      "learning_rate": 1.8863510101094304e-05,
      "loss": 0.5739,
      "step": 10062
    },
    {
      "epoch": 0.30912665499339537,
      "grad_norm": 0.3487200438976288,
      "learning_rate": 1.886328632661139e-05,
      "loss": 0.5745,
      "step": 10063
    },
    {
      "epoch": 0.30915737412834454,
      "grad_norm": 0.34596195816993713,
      "learning_rate": 1.8863062531427653e-05,
      "loss": 0.6115,
      "step": 10064
    },
    {
      "epoch": 0.3091880932632937,
      "grad_norm": 0.30053335428237915,
      "learning_rate": 1.8862838715543614e-05,
      "loss": 0.6857,
      "step": 10065
    },
    {
      "epoch": 0.3092188123982429,
      "grad_norm": 0.43476206064224243,
      "learning_rate": 1.8862614878959797e-05,
      "loss": 0.5091,
      "step": 10066
    },
    {
      "epoch": 0.309249531533192,
      "grad_norm": 0.37464210391044617,
      "learning_rate": 1.8862391021676725e-05,
      "loss": 0.5727,
      "step": 10067
    },
    {
      "epoch": 0.3092802506681412,
      "grad_norm": 0.34806546568870544,
      "learning_rate": 1.8862167143694915e-05,
      "loss": 0.5247,
      "step": 10068
    },
    {
      "epoch": 0.30931096980309036,
      "grad_norm": 0.3702642023563385,
      "learning_rate": 1.88619432450149e-05,
      "loss": 0.6296,
      "step": 10069
    },
    {
      "epoch": 0.3093416889380395,
      "grad_norm": 0.346971333026886,
      "learning_rate": 1.8861719325637193e-05,
      "loss": 0.6063,
      "step": 10070
    },
    {
      "epoch": 0.30937240807298866,
      "grad_norm": 0.5474721193313599,
      "learning_rate": 1.8861495385562325e-05,
      "loss": 0.5756,
      "step": 10071
    },
    {
      "epoch": 0.30940312720793783,
      "grad_norm": 0.3258747458457947,
      "learning_rate": 1.8861271424790814e-05,
      "loss": 0.5888,
      "step": 10072
    },
    {
      "epoch": 0.309433846342887,
      "grad_norm": 0.34816378355026245,
      "learning_rate": 1.8861047443323187e-05,
      "loss": 0.6199,
      "step": 10073
    },
    {
      "epoch": 0.30946456547783613,
      "grad_norm": 0.333275705575943,
      "learning_rate": 1.8860823441159964e-05,
      "loss": 0.5874,
      "step": 10074
    },
    {
      "epoch": 0.3094952846127853,
      "grad_norm": 0.4470853805541992,
      "learning_rate": 1.886059941830167e-05,
      "loss": 0.5859,
      "step": 10075
    },
    {
      "epoch": 0.3095260037477345,
      "grad_norm": 0.3728362023830414,
      "learning_rate": 1.8860375374748824e-05,
      "loss": 0.5939,
      "step": 10076
    },
    {
      "epoch": 0.3095567228826836,
      "grad_norm": 0.3364766836166382,
      "learning_rate": 1.8860151310501952e-05,
      "loss": 0.4505,
      "step": 10077
    },
    {
      "epoch": 0.3095874420176328,
      "grad_norm": 0.3819984495639801,
      "learning_rate": 1.885992722556158e-05,
      "loss": 0.5895,
      "step": 10078
    },
    {
      "epoch": 0.30961816115258195,
      "grad_norm": 0.37821725010871887,
      "learning_rate": 1.8859703119928227e-05,
      "loss": 0.5896,
      "step": 10079
    },
    {
      "epoch": 0.3096488802875311,
      "grad_norm": 0.33330416679382324,
      "learning_rate": 1.885947899360242e-05,
      "loss": 0.6424,
      "step": 10080
    },
    {
      "epoch": 0.30967959942248025,
      "grad_norm": 0.3147616684436798,
      "learning_rate": 1.8859254846584686e-05,
      "loss": 0.5193,
      "step": 10081
    },
    {
      "epoch": 0.3097103185574294,
      "grad_norm": 0.38529089093208313,
      "learning_rate": 1.8859030678875537e-05,
      "loss": 0.5588,
      "step": 10082
    },
    {
      "epoch": 0.3097410376923786,
      "grad_norm": 0.3720923364162445,
      "learning_rate": 1.885880649047551e-05,
      "loss": 0.5961,
      "step": 10083
    },
    {
      "epoch": 0.3097717568273277,
      "grad_norm": 0.3209877908229828,
      "learning_rate": 1.8858582281385114e-05,
      "loss": 0.5233,
      "step": 10084
    },
    {
      "epoch": 0.3098024759622769,
      "grad_norm": 0.36094576120376587,
      "learning_rate": 1.8858358051604883e-05,
      "loss": 0.6017,
      "step": 10085
    },
    {
      "epoch": 0.30983319509722607,
      "grad_norm": 0.3370627164840698,
      "learning_rate": 1.8858133801135337e-05,
      "loss": 0.5723,
      "step": 10086
    },
    {
      "epoch": 0.30986391423217524,
      "grad_norm": 0.33130931854248047,
      "learning_rate": 1.8857909529977005e-05,
      "loss": 0.6039,
      "step": 10087
    },
    {
      "epoch": 0.30989463336712436,
      "grad_norm": 0.3265426754951477,
      "learning_rate": 1.8857685238130404e-05,
      "loss": 0.571,
      "step": 10088
    },
    {
      "epoch": 0.30992535250207354,
      "grad_norm": 0.3893640339374542,
      "learning_rate": 1.885746092559606e-05,
      "loss": 0.6045,
      "step": 10089
    },
    {
      "epoch": 0.3099560716370227,
      "grad_norm": 0.41857635974884033,
      "learning_rate": 1.8857236592374496e-05,
      "loss": 0.4607,
      "step": 10090
    },
    {
      "epoch": 0.3099867907719719,
      "grad_norm": 0.4230824410915375,
      "learning_rate": 1.885701223846624e-05,
      "loss": 0.6095,
      "step": 10091
    },
    {
      "epoch": 0.310017509906921,
      "grad_norm": 0.3286364674568176,
      "learning_rate": 1.8856787863871816e-05,
      "loss": 0.5408,
      "step": 10092
    },
    {
      "epoch": 0.3100482290418702,
      "grad_norm": 0.45589977502822876,
      "learning_rate": 1.885656346859174e-05,
      "loss": 0.6342,
      "step": 10093
    },
    {
      "epoch": 0.31007894817681936,
      "grad_norm": 0.3060173988342285,
      "learning_rate": 1.8856339052626544e-05,
      "loss": 0.6175,
      "step": 10094
    },
    {
      "epoch": 0.3101096673117685,
      "grad_norm": 0.3755647838115692,
      "learning_rate": 1.8856114615976748e-05,
      "loss": 0.5913,
      "step": 10095
    },
    {
      "epoch": 0.31014038644671765,
      "grad_norm": 0.37145721912384033,
      "learning_rate": 1.8855890158642884e-05,
      "loss": 0.6416,
      "step": 10096
    },
    {
      "epoch": 0.31017110558166683,
      "grad_norm": 0.37311220169067383,
      "learning_rate": 1.8855665680625465e-05,
      "loss": 0.5773,
      "step": 10097
    },
    {
      "epoch": 0.310201824716616,
      "grad_norm": 0.29805198311805725,
      "learning_rate": 1.8855441181925016e-05,
      "loss": 0.5409,
      "step": 10098
    },
    {
      "epoch": 0.3102325438515651,
      "grad_norm": 0.3259282410144806,
      "learning_rate": 1.8855216662542072e-05,
      "loss": 0.5376,
      "step": 10099
    },
    {
      "epoch": 0.3102632629865143,
      "grad_norm": 0.3848120868206024,
      "learning_rate": 1.885499212247715e-05,
      "loss": 0.5464,
      "step": 10100
    },
    {
      "epoch": 0.3102939821214635,
      "grad_norm": 0.33870917558670044,
      "learning_rate": 1.8854767561730774e-05,
      "loss": 0.5222,
      "step": 10101
    },
    {
      "epoch": 0.3103247012564126,
      "grad_norm": 0.38864636421203613,
      "learning_rate": 1.885454298030347e-05,
      "loss": 0.7,
      "step": 10102
    },
    {
      "epoch": 0.31035542039136177,
      "grad_norm": 0.3590394854545593,
      "learning_rate": 1.8854318378195765e-05,
      "loss": 0.6193,
      "step": 10103
    },
    {
      "epoch": 0.31038613952631094,
      "grad_norm": 0.3269961476325989,
      "learning_rate": 1.8854093755408177e-05,
      "loss": 0.6101,
      "step": 10104
    },
    {
      "epoch": 0.3104168586612601,
      "grad_norm": 0.3161408305168152,
      "learning_rate": 1.885386911194124e-05,
      "loss": 0.5529,
      "step": 10105
    },
    {
      "epoch": 0.31044757779620924,
      "grad_norm": 0.32937687635421753,
      "learning_rate": 1.8853644447795466e-05,
      "loss": 0.5541,
      "step": 10106
    },
    {
      "epoch": 0.3104782969311584,
      "grad_norm": 0.33331647515296936,
      "learning_rate": 1.8853419762971392e-05,
      "loss": 0.4693,
      "step": 10107
    },
    {
      "epoch": 0.3105090160661076,
      "grad_norm": 0.3682630956172943,
      "learning_rate": 1.8853195057469536e-05,
      "loss": 0.6209,
      "step": 10108
    },
    {
      "epoch": 0.31053973520105677,
      "grad_norm": 0.3355412781238556,
      "learning_rate": 1.8852970331290427e-05,
      "loss": 0.5694,
      "step": 10109
    },
    {
      "epoch": 0.3105704543360059,
      "grad_norm": 0.3648889362812042,
      "learning_rate": 1.8852745584434586e-05,
      "loss": 0.5443,
      "step": 10110
    },
    {
      "epoch": 0.31060117347095506,
      "grad_norm": 0.37513238191604614,
      "learning_rate": 1.8852520816902543e-05,
      "loss": 0.5213,
      "step": 10111
    },
    {
      "epoch": 0.31063189260590424,
      "grad_norm": 0.3685113191604614,
      "learning_rate": 1.8852296028694815e-05,
      "loss": 0.6206,
      "step": 10112
    },
    {
      "epoch": 0.31066261174085336,
      "grad_norm": 0.3165138065814972,
      "learning_rate": 1.885207121981193e-05,
      "loss": 0.638,
      "step": 10113
    },
    {
      "epoch": 0.31069333087580253,
      "grad_norm": 0.4087908864021301,
      "learning_rate": 1.885184639025442e-05,
      "loss": 0.5349,
      "step": 10114
    },
    {
      "epoch": 0.3107240500107517,
      "grad_norm": 0.41599997878074646,
      "learning_rate": 1.88516215400228e-05,
      "loss": 0.5389,
      "step": 10115
    },
    {
      "epoch": 0.3107547691457009,
      "grad_norm": 0.32947707176208496,
      "learning_rate": 1.88513966691176e-05,
      "loss": 0.499,
      "step": 10116
    },
    {
      "epoch": 0.31078548828065,
      "grad_norm": 0.4281942546367645,
      "learning_rate": 1.8851171777539346e-05,
      "loss": 0.5989,
      "step": 10117
    },
    {
      "epoch": 0.3108162074155992,
      "grad_norm": 0.3466014862060547,
      "learning_rate": 1.8850946865288562e-05,
      "loss": 0.6016,
      "step": 10118
    },
    {
      "epoch": 0.31084692655054835,
      "grad_norm": 0.37585967779159546,
      "learning_rate": 1.8850721932365774e-05,
      "loss": 0.5571,
      "step": 10119
    },
    {
      "epoch": 0.3108776456854975,
      "grad_norm": 0.33437803387641907,
      "learning_rate": 1.8850496978771505e-05,
      "loss": 0.4856,
      "step": 10120
    },
    {
      "epoch": 0.31090836482044665,
      "grad_norm": 0.34240373969078064,
      "learning_rate": 1.8850272004506288e-05,
      "loss": 0.6119,
      "step": 10121
    },
    {
      "epoch": 0.3109390839553958,
      "grad_norm": 0.3444538414478302,
      "learning_rate": 1.8850047009570635e-05,
      "loss": 0.5521,
      "step": 10122
    },
    {
      "epoch": 0.310969803090345,
      "grad_norm": 0.35504409670829773,
      "learning_rate": 1.8849821993965084e-05,
      "loss": 0.6462,
      "step": 10123
    },
    {
      "epoch": 0.3110005222252941,
      "grad_norm": 0.36577844619750977,
      "learning_rate": 1.8849596957690154e-05,
      "loss": 0.6359,
      "step": 10124
    },
    {
      "epoch": 0.3110312413602433,
      "grad_norm": 0.340678334236145,
      "learning_rate": 1.8849371900746373e-05,
      "loss": 0.5076,
      "step": 10125
    },
    {
      "epoch": 0.31106196049519247,
      "grad_norm": 0.344433456659317,
      "learning_rate": 1.8849146823134263e-05,
      "loss": 0.5591,
      "step": 10126
    },
    {
      "epoch": 0.3110926796301416,
      "grad_norm": 0.38046029210090637,
      "learning_rate": 1.8848921724854356e-05,
      "loss": 0.6157,
      "step": 10127
    },
    {
      "epoch": 0.31112339876509076,
      "grad_norm": 0.33657950162887573,
      "learning_rate": 1.8848696605907174e-05,
      "loss": 0.5147,
      "step": 10128
    },
    {
      "epoch": 0.31115411790003994,
      "grad_norm": 0.3590734601020813,
      "learning_rate": 1.884847146629324e-05,
      "loss": 0.5903,
      "step": 10129
    },
    {
      "epoch": 0.3111848370349891,
      "grad_norm": 0.37918850779533386,
      "learning_rate": 1.8848246306013088e-05,
      "loss": 0.5205,
      "step": 10130
    },
    {
      "epoch": 0.31121555616993823,
      "grad_norm": 0.38848331570625305,
      "learning_rate": 1.8848021125067234e-05,
      "loss": 0.5442,
      "step": 10131
    },
    {
      "epoch": 0.3112462753048874,
      "grad_norm": 0.35899046063423157,
      "learning_rate": 1.8847795923456213e-05,
      "loss": 0.5914,
      "step": 10132
    },
    {
      "epoch": 0.3112769944398366,
      "grad_norm": 0.4341716468334198,
      "learning_rate": 1.8847570701180542e-05,
      "loss": 0.5763,
      "step": 10133
    },
    {
      "epoch": 0.31130771357478576,
      "grad_norm": 0.3290901184082031,
      "learning_rate": 1.8847345458240753e-05,
      "loss": 0.5466,
      "step": 10134
    },
    {
      "epoch": 0.3113384327097349,
      "grad_norm": 0.6974817514419556,
      "learning_rate": 1.8847120194637373e-05,
      "loss": 0.6019,
      "step": 10135
    },
    {
      "epoch": 0.31136915184468406,
      "grad_norm": 0.3475024998188019,
      "learning_rate": 1.8846894910370925e-05,
      "loss": 0.5711,
      "step": 10136
    },
    {
      "epoch": 0.31139987097963323,
      "grad_norm": 0.35008350014686584,
      "learning_rate": 1.8846669605441934e-05,
      "loss": 0.6326,
      "step": 10137
    },
    {
      "epoch": 0.31143059011458235,
      "grad_norm": 0.3038123548030853,
      "learning_rate": 1.884644427985093e-05,
      "loss": 0.4606,
      "step": 10138
    },
    {
      "epoch": 0.3114613092495315,
      "grad_norm": 0.38448306918144226,
      "learning_rate": 1.884621893359844e-05,
      "loss": 0.6256,
      "step": 10139
    },
    {
      "epoch": 0.3114920283844807,
      "grad_norm": 0.34443485736846924,
      "learning_rate": 1.8845993566684987e-05,
      "loss": 0.5843,
      "step": 10140
    },
    {
      "epoch": 0.3115227475194299,
      "grad_norm": 0.36280083656311035,
      "learning_rate": 1.8845768179111094e-05,
      "loss": 0.5844,
      "step": 10141
    },
    {
      "epoch": 0.311553466654379,
      "grad_norm": 0.3561347723007202,
      "learning_rate": 1.8845542770877295e-05,
      "loss": 0.574,
      "step": 10142
    },
    {
      "epoch": 0.31158418578932817,
      "grad_norm": 0.38417309522628784,
      "learning_rate": 1.884531734198411e-05,
      "loss": 0.5898,
      "step": 10143
    },
    {
      "epoch": 0.31161490492427735,
      "grad_norm": 0.3686124384403229,
      "learning_rate": 1.8845091892432076e-05,
      "loss": 0.5914,
      "step": 10144
    },
    {
      "epoch": 0.31164562405922647,
      "grad_norm": 0.32857316732406616,
      "learning_rate": 1.8844866422221706e-05,
      "loss": 0.6424,
      "step": 10145
    },
    {
      "epoch": 0.31167634319417564,
      "grad_norm": 0.32416924834251404,
      "learning_rate": 1.8844640931353534e-05,
      "loss": 0.5488,
      "step": 10146
    },
    {
      "epoch": 0.3117070623291248,
      "grad_norm": 0.30492162704467773,
      "learning_rate": 1.8844415419828085e-05,
      "loss": 0.5608,
      "step": 10147
    },
    {
      "epoch": 0.311737781464074,
      "grad_norm": 0.3545151650905609,
      "learning_rate": 1.8844189887645885e-05,
      "loss": 0.6414,
      "step": 10148
    },
    {
      "epoch": 0.3117685005990231,
      "grad_norm": 0.39208006858825684,
      "learning_rate": 1.8843964334807465e-05,
      "loss": 0.5411,
      "step": 10149
    },
    {
      "epoch": 0.3117992197339723,
      "grad_norm": 0.36538007855415344,
      "learning_rate": 1.8843738761313346e-05,
      "loss": 0.5718,
      "step": 10150
    },
    {
      "epoch": 0.31182993886892146,
      "grad_norm": 0.32422593235969543,
      "learning_rate": 1.884351316716406e-05,
      "loss": 0.5763,
      "step": 10151
    },
    {
      "epoch": 0.3118606580038706,
      "grad_norm": 0.3490673899650574,
      "learning_rate": 1.884328755236013e-05,
      "loss": 0.5175,
      "step": 10152
    },
    {
      "epoch": 0.31189137713881976,
      "grad_norm": 0.3489876091480255,
      "learning_rate": 1.8843061916902082e-05,
      "loss": 0.6594,
      "step": 10153
    },
    {
      "epoch": 0.31192209627376893,
      "grad_norm": 0.5540232062339783,
      "learning_rate": 1.8842836260790447e-05,
      "loss": 0.7422,
      "step": 10154
    },
    {
      "epoch": 0.3119528154087181,
      "grad_norm": 0.38867658376693726,
      "learning_rate": 1.884261058402575e-05,
      "loss": 0.6033,
      "step": 10155
    },
    {
      "epoch": 0.31198353454366723,
      "grad_norm": 0.3383646011352539,
      "learning_rate": 1.8842384886608523e-05,
      "loss": 0.5329,
      "step": 10156
    },
    {
      "epoch": 0.3120142536786164,
      "grad_norm": 0.3349343240261078,
      "learning_rate": 1.8842159168539284e-05,
      "loss": 0.5855,
      "step": 10157
    },
    {
      "epoch": 0.3120449728135656,
      "grad_norm": 0.3391203284263611,
      "learning_rate": 1.8841933429818565e-05,
      "loss": 0.5312,
      "step": 10158
    },
    {
      "epoch": 0.31207569194851476,
      "grad_norm": 0.3235531449317932,
      "learning_rate": 1.8841707670446895e-05,
      "loss": 0.573,
      "step": 10159
    },
    {
      "epoch": 0.3121064110834639,
      "grad_norm": 0.3281766474246979,
      "learning_rate": 1.8841481890424796e-05,
      "loss": 0.5364,
      "step": 10160
    },
    {
      "epoch": 0.31213713021841305,
      "grad_norm": 0.3836991786956787,
      "learning_rate": 1.88412560897528e-05,
      "loss": 0.5795,
      "step": 10161
    },
    {
      "epoch": 0.3121678493533622,
      "grad_norm": 0.35236769914627075,
      "learning_rate": 1.8841030268431433e-05,
      "loss": 0.6746,
      "step": 10162
    },
    {
      "epoch": 0.31219856848831135,
      "grad_norm": 0.3586454391479492,
      "learning_rate": 1.884080442646122e-05,
      "loss": 0.5855,
      "step": 10163
    },
    {
      "epoch": 0.3122292876232605,
      "grad_norm": 0.3540007770061493,
      "learning_rate": 1.8840578563842694e-05,
      "loss": 0.5771,
      "step": 10164
    },
    {
      "epoch": 0.3122600067582097,
      "grad_norm": 0.3668319284915924,
      "learning_rate": 1.884035268057638e-05,
      "loss": 0.5725,
      "step": 10165
    },
    {
      "epoch": 0.31229072589315887,
      "grad_norm": 0.3228594958782196,
      "learning_rate": 1.8840126776662802e-05,
      "loss": 0.5348,
      "step": 10166
    },
    {
      "epoch": 0.312321445028108,
      "grad_norm": 0.36075928807258606,
      "learning_rate": 1.8839900852102496e-05,
      "loss": 0.5296,
      "step": 10167
    },
    {
      "epoch": 0.31235216416305717,
      "grad_norm": 0.33458513021469116,
      "learning_rate": 1.883967490689598e-05,
      "loss": 0.5741,
      "step": 10168
    },
    {
      "epoch": 0.31238288329800634,
      "grad_norm": 0.45339933037757874,
      "learning_rate": 1.8839448941043785e-05,
      "loss": 0.5772,
      "step": 10169
    },
    {
      "epoch": 0.31241360243295546,
      "grad_norm": 0.36477193236351013,
      "learning_rate": 1.883922295454644e-05,
      "loss": 0.5919,
      "step": 10170
    },
    {
      "epoch": 0.31244432156790464,
      "grad_norm": 0.351065993309021,
      "learning_rate": 1.8838996947404474e-05,
      "loss": 0.5727,
      "step": 10171
    },
    {
      "epoch": 0.3124750407028538,
      "grad_norm": 0.34001803398132324,
      "learning_rate": 1.8838770919618414e-05,
      "loss": 0.6192,
      "step": 10172
    },
    {
      "epoch": 0.312505759837803,
      "grad_norm": 0.3540021479129791,
      "learning_rate": 1.8838544871188785e-05,
      "loss": 0.5319,
      "step": 10173
    },
    {
      "epoch": 0.3125364789727521,
      "grad_norm": 0.38077518343925476,
      "learning_rate": 1.8838318802116116e-05,
      "loss": 0.6232,
      "step": 10174
    },
    {
      "epoch": 0.3125671981077013,
      "grad_norm": 0.36561235785484314,
      "learning_rate": 1.883809271240094e-05,
      "loss": 0.5059,
      "step": 10175
    },
    {
      "epoch": 0.31259791724265046,
      "grad_norm": 0.35212212800979614,
      "learning_rate": 1.883786660204378e-05,
      "loss": 0.6538,
      "step": 10176
    },
    {
      "epoch": 0.31262863637759963,
      "grad_norm": 0.3425794243812561,
      "learning_rate": 1.8837640471045163e-05,
      "loss": 0.6229,
      "step": 10177
    },
    {
      "epoch": 0.31265935551254875,
      "grad_norm": 0.3151055574417114,
      "learning_rate": 1.8837414319405623e-05,
      "loss": 0.5352,
      "step": 10178
    },
    {
      "epoch": 0.31269007464749793,
      "grad_norm": 0.35629838705062866,
      "learning_rate": 1.8837188147125683e-05,
      "loss": 0.5642,
      "step": 10179
    },
    {
      "epoch": 0.3127207937824471,
      "grad_norm": 0.39631232619285583,
      "learning_rate": 1.8836961954205874e-05,
      "loss": 0.5176,
      "step": 10180
    },
    {
      "epoch": 0.3127515129173962,
      "grad_norm": 0.34926873445510864,
      "learning_rate": 1.883673574064672e-05,
      "loss": 0.5469,
      "step": 10181
    },
    {
      "epoch": 0.3127822320523454,
      "grad_norm": 0.5440989136695862,
      "learning_rate": 1.8836509506448754e-05,
      "loss": 0.5191,
      "step": 10182
    },
    {
      "epoch": 0.3128129511872946,
      "grad_norm": 0.32009851932525635,
      "learning_rate": 1.8836283251612504e-05,
      "loss": 0.497,
      "step": 10183
    },
    {
      "epoch": 0.31284367032224375,
      "grad_norm": 0.33849743008613586,
      "learning_rate": 1.8836056976138496e-05,
      "loss": 0.5721,
      "step": 10184
    },
    {
      "epoch": 0.31287438945719287,
      "grad_norm": 0.3180125653743744,
      "learning_rate": 1.883583068002726e-05,
      "loss": 0.5259,
      "step": 10185
    },
    {
      "epoch": 0.31290510859214204,
      "grad_norm": 0.35506802797317505,
      "learning_rate": 1.8835604363279326e-05,
      "loss": 0.5361,
      "step": 10186
    },
    {
      "epoch": 0.3129358277270912,
      "grad_norm": 0.33124202489852905,
      "learning_rate": 1.8835378025895223e-05,
      "loss": 0.5457,
      "step": 10187
    },
    {
      "epoch": 0.31296654686204034,
      "grad_norm": 0.32262033224105835,
      "learning_rate": 1.8835151667875472e-05,
      "loss": 0.5292,
      "step": 10188
    },
    {
      "epoch": 0.3129972659969895,
      "grad_norm": 0.3302468955516815,
      "learning_rate": 1.883492528922061e-05,
      "loss": 0.5042,
      "step": 10189
    },
    {
      "epoch": 0.3130279851319387,
      "grad_norm": 0.3643263578414917,
      "learning_rate": 1.8834698889931164e-05,
      "loss": 0.5847,
      "step": 10190
    },
    {
      "epoch": 0.31305870426688787,
      "grad_norm": 0.3537326753139496,
      "learning_rate": 1.883447247000766e-05,
      "loss": 0.5985,
      "step": 10191
    },
    {
      "epoch": 0.313089423401837,
      "grad_norm": 0.3610600531101227,
      "learning_rate": 1.8834246029450627e-05,
      "loss": 0.5188,
      "step": 10192
    },
    {
      "epoch": 0.31312014253678616,
      "grad_norm": 0.3216906487941742,
      "learning_rate": 1.88340195682606e-05,
      "loss": 0.5984,
      "step": 10193
    },
    {
      "epoch": 0.31315086167173534,
      "grad_norm": 0.3426816761493683,
      "learning_rate": 1.88337930864381e-05,
      "loss": 0.5952,
      "step": 10194
    },
    {
      "epoch": 0.31318158080668446,
      "grad_norm": 0.3281533718109131,
      "learning_rate": 1.883356658398366e-05,
      "loss": 0.6029,
      "step": 10195
    },
    {
      "epoch": 0.31321229994163363,
      "grad_norm": 0.3344190716743469,
      "learning_rate": 1.8833340060897807e-05,
      "loss": 0.5476,
      "step": 10196
    },
    {
      "epoch": 0.3132430190765828,
      "grad_norm": 0.35871726274490356,
      "learning_rate": 1.8833113517181075e-05,
      "loss": 0.5423,
      "step": 10197
    },
    {
      "epoch": 0.313273738211532,
      "grad_norm": 0.37104782462120056,
      "learning_rate": 1.8832886952833985e-05,
      "loss": 0.5539,
      "step": 10198
    },
    {
      "epoch": 0.3133044573464811,
      "grad_norm": 0.3424052596092224,
      "learning_rate": 1.8832660367857075e-05,
      "loss": 0.5813,
      "step": 10199
    },
    {
      "epoch": 0.3133351764814303,
      "grad_norm": 0.34805747866630554,
      "learning_rate": 1.8832433762250865e-05,
      "loss": 0.618,
      "step": 10200
    },
    {
      "epoch": 0.31336589561637945,
      "grad_norm": 0.3593772053718567,
      "learning_rate": 1.883220713601589e-05,
      "loss": 0.6035,
      "step": 10201
    },
    {
      "epoch": 0.31339661475132863,
      "grad_norm": 0.3299776613712311,
      "learning_rate": 1.8831980489152685e-05,
      "loss": 0.509,
      "step": 10202
    },
    {
      "epoch": 0.31342733388627775,
      "grad_norm": 0.3468387722969055,
      "learning_rate": 1.8831753821661766e-05,
      "loss": 0.5912,
      "step": 10203
    },
    {
      "epoch": 0.3134580530212269,
      "grad_norm": 0.32769569754600525,
      "learning_rate": 1.8831527133543673e-05,
      "loss": 0.6339,
      "step": 10204
    },
    {
      "epoch": 0.3134887721561761,
      "grad_norm": 0.37946128845214844,
      "learning_rate": 1.883130042479893e-05,
      "loss": 0.5693,
      "step": 10205
    },
    {
      "epoch": 0.3135194912911252,
      "grad_norm": 0.3612501621246338,
      "learning_rate": 1.8831073695428066e-05,
      "loss": 0.6362,
      "step": 10206
    },
    {
      "epoch": 0.3135502104260744,
      "grad_norm": 0.3639802932739258,
      "learning_rate": 1.8830846945431615e-05,
      "loss": 0.5891,
      "step": 10207
    },
    {
      "epoch": 0.31358092956102357,
      "grad_norm": 0.3434635400772095,
      "learning_rate": 1.8830620174810104e-05,
      "loss": 0.6387,
      "step": 10208
    },
    {
      "epoch": 0.31361164869597274,
      "grad_norm": 0.3162698447704315,
      "learning_rate": 1.8830393383564063e-05,
      "loss": 0.5534,
      "step": 10209
    },
    {
      "epoch": 0.31364236783092186,
      "grad_norm": 0.3464967608451843,
      "learning_rate": 1.883016657169402e-05,
      "loss": 0.5822,
      "step": 10210
    },
    {
      "epoch": 0.31367308696587104,
      "grad_norm": 0.3357175290584564,
      "learning_rate": 1.882993973920051e-05,
      "loss": 0.602,
      "step": 10211
    },
    {
      "epoch": 0.3137038061008202,
      "grad_norm": 0.36601942777633667,
      "learning_rate": 1.8829712886084053e-05,
      "loss": 0.5831,
      "step": 10212
    },
    {
      "epoch": 0.31373452523576933,
      "grad_norm": 0.32678937911987305,
      "learning_rate": 1.8829486012345192e-05,
      "loss": 0.5382,
      "step": 10213
    },
    {
      "epoch": 0.3137652443707185,
      "grad_norm": 0.39790043234825134,
      "learning_rate": 1.8829259117984443e-05,
      "loss": 0.5868,
      "step": 10214
    },
    {
      "epoch": 0.3137959635056677,
      "grad_norm": 0.34391751885414124,
      "learning_rate": 1.8829032203002345e-05,
      "loss": 0.5651,
      "step": 10215
    },
    {
      "epoch": 0.31382668264061686,
      "grad_norm": 0.4029100835323334,
      "learning_rate": 1.8828805267399427e-05,
      "loss": 0.5559,
      "step": 10216
    },
    {
      "epoch": 0.313857401775566,
      "grad_norm": 0.3164682686328888,
      "learning_rate": 1.8828578311176216e-05,
      "loss": 0.6115,
      "step": 10217
    },
    {
      "epoch": 0.31388812091051516,
      "grad_norm": 0.41359400749206543,
      "learning_rate": 1.8828351334333246e-05,
      "loss": 0.655,
      "step": 10218
    },
    {
      "epoch": 0.31391884004546433,
      "grad_norm": 0.31845858693122864,
      "learning_rate": 1.8828124336871047e-05,
      "loss": 0.5347,
      "step": 10219
    },
    {
      "epoch": 0.3139495591804135,
      "grad_norm": 0.31494998931884766,
      "learning_rate": 1.882789731879014e-05,
      "loss": 0.6033,
      "step": 10220
    },
    {
      "epoch": 0.3139802783153626,
      "grad_norm": 0.3435204327106476,
      "learning_rate": 1.8827670280091065e-05,
      "loss": 0.5948,
      "step": 10221
    },
    {
      "epoch": 0.3140109974503118,
      "grad_norm": 0.35050079226493835,
      "learning_rate": 1.8827443220774353e-05,
      "loss": 0.5821,
      "step": 10222
    },
    {
      "epoch": 0.314041716585261,
      "grad_norm": 0.33773186802864075,
      "learning_rate": 1.8827216140840527e-05,
      "loss": 0.5756,
      "step": 10223
    },
    {
      "epoch": 0.3140724357202101,
      "grad_norm": 0.35729721188545227,
      "learning_rate": 1.8826989040290126e-05,
      "loss": 0.567,
      "step": 10224
    },
    {
      "epoch": 0.3141031548551593,
      "grad_norm": 0.34522542357444763,
      "learning_rate": 1.882676191912367e-05,
      "loss": 0.6538,
      "step": 10225
    },
    {
      "epoch": 0.31413387399010845,
      "grad_norm": 0.320198118686676,
      "learning_rate": 1.88265347773417e-05,
      "loss": 0.5461,
      "step": 10226
    },
    {
      "epoch": 0.3141645931250576,
      "grad_norm": 0.35079413652420044,
      "learning_rate": 1.8826307614944736e-05,
      "loss": 0.6021,
      "step": 10227
    },
    {
      "epoch": 0.31419531226000674,
      "grad_norm": 0.3602257966995239,
      "learning_rate": 1.882608043193332e-05,
      "loss": 0.5223,
      "step": 10228
    },
    {
      "epoch": 0.3142260313949559,
      "grad_norm": 0.3310004770755768,
      "learning_rate": 1.882585322830797e-05,
      "loss": 0.637,
      "step": 10229
    },
    {
      "epoch": 0.3142567505299051,
      "grad_norm": 0.3350307047367096,
      "learning_rate": 1.882562600406923e-05,
      "loss": 0.5737,
      "step": 10230
    },
    {
      "epoch": 0.3142874696648542,
      "grad_norm": 0.3511955440044403,
      "learning_rate": 1.8825398759217622e-05,
      "loss": 0.5773,
      "step": 10231
    },
    {
      "epoch": 0.3143181887998034,
      "grad_norm": 0.44921422004699707,
      "learning_rate": 1.8825171493753677e-05,
      "loss": 0.6087,
      "step": 10232
    },
    {
      "epoch": 0.31434890793475256,
      "grad_norm": 0.3474528193473816,
      "learning_rate": 1.882494420767793e-05,
      "loss": 0.5922,
      "step": 10233
    },
    {
      "epoch": 0.31437962706970174,
      "grad_norm": 0.36127743124961853,
      "learning_rate": 1.8824716900990908e-05,
      "loss": 0.4914,
      "step": 10234
    },
    {
      "epoch": 0.31441034620465086,
      "grad_norm": 0.33839255571365356,
      "learning_rate": 1.8824489573693144e-05,
      "loss": 0.5333,
      "step": 10235
    },
    {
      "epoch": 0.31444106533960003,
      "grad_norm": 0.37911146879196167,
      "learning_rate": 1.8824262225785168e-05,
      "loss": 0.5789,
      "step": 10236
    },
    {
      "epoch": 0.3144717844745492,
      "grad_norm": 0.33953458070755005,
      "learning_rate": 1.8824034857267512e-05,
      "loss": 0.6639,
      "step": 10237
    },
    {
      "epoch": 0.31450250360949833,
      "grad_norm": 0.3384494185447693,
      "learning_rate": 1.8823807468140704e-05,
      "loss": 0.5617,
      "step": 10238
    },
    {
      "epoch": 0.3145332227444475,
      "grad_norm": 0.33919548988342285,
      "learning_rate": 1.882358005840528e-05,
      "loss": 0.5423,
      "step": 10239
    },
    {
      "epoch": 0.3145639418793967,
      "grad_norm": 0.35729315876960754,
      "learning_rate": 1.882335262806177e-05,
      "loss": 0.6649,
      "step": 10240
    },
    {
      "epoch": 0.31459466101434586,
      "grad_norm": 0.3558410704135895,
      "learning_rate": 1.88231251771107e-05,
      "loss": 0.5773,
      "step": 10241
    },
    {
      "epoch": 0.314625380149295,
      "grad_norm": 0.3184834420681,
      "learning_rate": 1.8822897705552605e-05,
      "loss": 0.6452,
      "step": 10242
    },
    {
      "epoch": 0.31465609928424415,
      "grad_norm": 0.31638583540916443,
      "learning_rate": 1.8822670213388016e-05,
      "loss": 0.5753,
      "step": 10243
    },
    {
      "epoch": 0.3146868184191933,
      "grad_norm": 0.3459552824497223,
      "learning_rate": 1.8822442700617467e-05,
      "loss": 0.5833,
      "step": 10244
    },
    {
      "epoch": 0.3147175375541425,
      "grad_norm": 0.4149627387523651,
      "learning_rate": 1.8822215167241487e-05,
      "loss": 0.5332,
      "step": 10245
    },
    {
      "epoch": 0.3147482566890916,
      "grad_norm": 0.3723471760749817,
      "learning_rate": 1.8821987613260607e-05,
      "loss": 0.5846,
      "step": 10246
    },
    {
      "epoch": 0.3147789758240408,
      "grad_norm": 0.37196436524391174,
      "learning_rate": 1.8821760038675355e-05,
      "loss": 0.6206,
      "step": 10247
    },
    {
      "epoch": 0.31480969495898997,
      "grad_norm": 0.3790593445301056,
      "learning_rate": 1.882153244348627e-05,
      "loss": 0.5547,
      "step": 10248
    },
    {
      "epoch": 0.3148404140939391,
      "grad_norm": 0.4034518301486969,
      "learning_rate": 1.8821304827693884e-05,
      "loss": 0.619,
      "step": 10249
    },
    {
      "epoch": 0.31487113322888827,
      "grad_norm": 0.43165987730026245,
      "learning_rate": 1.8821077191298717e-05,
      "loss": 0.6153,
      "step": 10250
    },
    {
      "epoch": 0.31490185236383744,
      "grad_norm": 0.3570561707019806,
      "learning_rate": 1.882084953430131e-05,
      "loss": 0.5609,
      "step": 10251
    },
    {
      "epoch": 0.3149325714987866,
      "grad_norm": 0.3818589746952057,
      "learning_rate": 1.8820621856702196e-05,
      "loss": 0.5961,
      "step": 10252
    },
    {
      "epoch": 0.31496329063373574,
      "grad_norm": 0.36247026920318604,
      "learning_rate": 1.88203941585019e-05,
      "loss": 0.5274,
      "step": 10253
    },
    {
      "epoch": 0.3149940097686849,
      "grad_norm": 0.33482635021209717,
      "learning_rate": 1.882016643970096e-05,
      "loss": 0.5654,
      "step": 10254
    },
    {
      "epoch": 0.3150247289036341,
      "grad_norm": 0.33835846185684204,
      "learning_rate": 1.8819938700299905e-05,
      "loss": 0.5891,
      "step": 10255
    },
    {
      "epoch": 0.3150554480385832,
      "grad_norm": 0.39175713062286377,
      "learning_rate": 1.8819710940299263e-05,
      "loss": 0.6082,
      "step": 10256
    },
    {
      "epoch": 0.3150861671735324,
      "grad_norm": 0.32381680607795715,
      "learning_rate": 1.8819483159699573e-05,
      "loss": 0.6043,
      "step": 10257
    },
    {
      "epoch": 0.31511688630848156,
      "grad_norm": 0.314546138048172,
      "learning_rate": 1.8819255358501367e-05,
      "loss": 0.5411,
      "step": 10258
    },
    {
      "epoch": 0.31514760544343073,
      "grad_norm": 0.35210752487182617,
      "learning_rate": 1.8819027536705172e-05,
      "loss": 0.6301,
      "step": 10259
    },
    {
      "epoch": 0.31517832457837985,
      "grad_norm": 0.37179121375083923,
      "learning_rate": 1.8818799694311522e-05,
      "loss": 0.6221,
      "step": 10260
    },
    {
      "epoch": 0.31520904371332903,
      "grad_norm": 0.3643675148487091,
      "learning_rate": 1.881857183132095e-05,
      "loss": 0.5173,
      "step": 10261
    },
    {
      "epoch": 0.3152397628482782,
      "grad_norm": 0.3668730854988098,
      "learning_rate": 1.8818343947733987e-05,
      "loss": 0.6267,
      "step": 10262
    },
    {
      "epoch": 0.3152704819832274,
      "grad_norm": 0.3464733958244324,
      "learning_rate": 1.8818116043551167e-05,
      "loss": 0.5475,
      "step": 10263
    },
    {
      "epoch": 0.3153012011181765,
      "grad_norm": 0.3539682924747467,
      "learning_rate": 1.881788811877302e-05,
      "loss": 0.5906,
      "step": 10264
    },
    {
      "epoch": 0.3153319202531257,
      "grad_norm": 0.3298884928226471,
      "learning_rate": 1.8817660173400077e-05,
      "loss": 0.465,
      "step": 10265
    },
    {
      "epoch": 0.31536263938807485,
      "grad_norm": 0.31786584854125977,
      "learning_rate": 1.8817432207432878e-05,
      "loss": 0.6819,
      "step": 10266
    },
    {
      "epoch": 0.31539335852302397,
      "grad_norm": 0.3537514805793762,
      "learning_rate": 1.8817204220871946e-05,
      "loss": 0.5364,
      "step": 10267
    },
    {
      "epoch": 0.31542407765797315,
      "grad_norm": 0.34676802158355713,
      "learning_rate": 1.881697621371782e-05,
      "loss": 0.5893,
      "step": 10268
    },
    {
      "epoch": 0.3154547967929223,
      "grad_norm": 0.3786328434944153,
      "learning_rate": 1.881674818597103e-05,
      "loss": 0.6028,
      "step": 10269
    },
    {
      "epoch": 0.3154855159278715,
      "grad_norm": 0.34813159704208374,
      "learning_rate": 1.881652013763211e-05,
      "loss": 0.6062,
      "step": 10270
    },
    {
      "epoch": 0.3155162350628206,
      "grad_norm": 0.3288549780845642,
      "learning_rate": 1.8816292068701588e-05,
      "loss": 0.5435,
      "step": 10271
    },
    {
      "epoch": 0.3155469541977698,
      "grad_norm": 0.4264668822288513,
      "learning_rate": 1.8816063979180004e-05,
      "loss": 0.7402,
      "step": 10272
    },
    {
      "epoch": 0.31557767333271897,
      "grad_norm": 0.3753337562084198,
      "learning_rate": 1.8815835869067885e-05,
      "loss": 0.5026,
      "step": 10273
    },
    {
      "epoch": 0.3156083924676681,
      "grad_norm": 0.3764493465423584,
      "learning_rate": 1.8815607738365768e-05,
      "loss": 0.672,
      "step": 10274
    },
    {
      "epoch": 0.31563911160261726,
      "grad_norm": 0.32946935296058655,
      "learning_rate": 1.8815379587074177e-05,
      "loss": 0.5891,
      "step": 10275
    },
    {
      "epoch": 0.31566983073756644,
      "grad_norm": 0.3478465676307678,
      "learning_rate": 1.881515141519366e-05,
      "loss": 0.5777,
      "step": 10276
    },
    {
      "epoch": 0.3157005498725156,
      "grad_norm": 0.6545723080635071,
      "learning_rate": 1.8814923222724733e-05,
      "loss": 0.6545,
      "step": 10277
    },
    {
      "epoch": 0.31573126900746473,
      "grad_norm": 0.3580240309238434,
      "learning_rate": 1.8814695009667944e-05,
      "loss": 0.5796,
      "step": 10278
    },
    {
      "epoch": 0.3157619881424139,
      "grad_norm": 0.32342785596847534,
      "learning_rate": 1.8814466776023815e-05,
      "loss": 0.5825,
      "step": 10279
    },
    {
      "epoch": 0.3157927072773631,
      "grad_norm": 0.3625243604183197,
      "learning_rate": 1.8814238521792886e-05,
      "loss": 0.5491,
      "step": 10280
    },
    {
      "epoch": 0.3158234264123122,
      "grad_norm": 0.343291312456131,
      "learning_rate": 1.8814010246975685e-05,
      "loss": 0.5828,
      "step": 10281
    },
    {
      "epoch": 0.3158541455472614,
      "grad_norm": 0.3325168490409851,
      "learning_rate": 1.8813781951572748e-05,
      "loss": 0.6762,
      "step": 10282
    },
    {
      "epoch": 0.31588486468221055,
      "grad_norm": 0.537365734577179,
      "learning_rate": 1.8813553635584606e-05,
      "loss": 0.5699,
      "step": 10283
    },
    {
      "epoch": 0.31591558381715973,
      "grad_norm": 0.34361448884010315,
      "learning_rate": 1.8813325299011795e-05,
      "loss": 0.6247,
      "step": 10284
    },
    {
      "epoch": 0.31594630295210885,
      "grad_norm": 0.3684138357639313,
      "learning_rate": 1.881309694185485e-05,
      "loss": 0.6204,
      "step": 10285
    },
    {
      "epoch": 0.315977022087058,
      "grad_norm": 0.3150482177734375,
      "learning_rate": 1.88128685641143e-05,
      "loss": 0.4776,
      "step": 10286
    },
    {
      "epoch": 0.3160077412220072,
      "grad_norm": 0.3180637061595917,
      "learning_rate": 1.881264016579068e-05,
      "loss": 0.6006,
      "step": 10287
    },
    {
      "epoch": 0.3160384603569564,
      "grad_norm": 0.3347220718860626,
      "learning_rate": 1.881241174688452e-05,
      "loss": 0.5869,
      "step": 10288
    },
    {
      "epoch": 0.3160691794919055,
      "grad_norm": 0.3989174962043762,
      "learning_rate": 1.8812183307396364e-05,
      "loss": 0.6059,
      "step": 10289
    },
    {
      "epoch": 0.31609989862685467,
      "grad_norm": 0.345860093832016,
      "learning_rate": 1.8811954847326732e-05,
      "loss": 0.6257,
      "step": 10290
    },
    {
      "epoch": 0.31613061776180384,
      "grad_norm": 0.45442742109298706,
      "learning_rate": 1.8811726366676168e-05,
      "loss": 0.5705,
      "step": 10291
    },
    {
      "epoch": 0.31616133689675296,
      "grad_norm": 0.43948447704315186,
      "learning_rate": 1.88114978654452e-05,
      "loss": 0.6268,
      "step": 10292
    },
    {
      "epoch": 0.31619205603170214,
      "grad_norm": 0.37150612473487854,
      "learning_rate": 1.881126934363436e-05,
      "loss": 0.5584,
      "step": 10293
    },
    {
      "epoch": 0.3162227751666513,
      "grad_norm": 0.32819297909736633,
      "learning_rate": 1.8811040801244192e-05,
      "loss": 0.5496,
      "step": 10294
    },
    {
      "epoch": 0.3162534943016005,
      "grad_norm": 0.415400892496109,
      "learning_rate": 1.881081223827522e-05,
      "loss": 0.6886,
      "step": 10295
    },
    {
      "epoch": 0.3162842134365496,
      "grad_norm": 0.32257699966430664,
      "learning_rate": 1.881058365472798e-05,
      "loss": 0.5809,
      "step": 10296
    },
    {
      "epoch": 0.3163149325714988,
      "grad_norm": 0.3207363486289978,
      "learning_rate": 1.8810355050603008e-05,
      "loss": 0.4824,
      "step": 10297
    },
    {
      "epoch": 0.31634565170644796,
      "grad_norm": 0.35319289565086365,
      "learning_rate": 1.8810126425900833e-05,
      "loss": 0.6128,
      "step": 10298
    },
    {
      "epoch": 0.3163763708413971,
      "grad_norm": 0.35282081365585327,
      "learning_rate": 1.8809897780621996e-05,
      "loss": 0.5539,
      "step": 10299
    },
    {
      "epoch": 0.31640708997634626,
      "grad_norm": 0.3254168629646301,
      "learning_rate": 1.8809669114767027e-05,
      "loss": 0.5897,
      "step": 10300
    },
    {
      "epoch": 0.31643780911129543,
      "grad_norm": 0.4251907765865326,
      "learning_rate": 1.8809440428336456e-05,
      "loss": 0.6885,
      "step": 10301
    },
    {
      "epoch": 0.3164685282462446,
      "grad_norm": 0.39222365617752075,
      "learning_rate": 1.8809211721330828e-05,
      "loss": 0.5833,
      "step": 10302
    },
    {
      "epoch": 0.3164992473811937,
      "grad_norm": 0.3966994881629944,
      "learning_rate": 1.8808982993750668e-05,
      "loss": 0.6116,
      "step": 10303
    },
    {
      "epoch": 0.3165299665161429,
      "grad_norm": 0.4037255346775055,
      "learning_rate": 1.880875424559651e-05,
      "loss": 0.5746,
      "step": 10304
    },
    {
      "epoch": 0.3165606856510921,
      "grad_norm": 0.4391864538192749,
      "learning_rate": 1.8808525476868897e-05,
      "loss": 0.6623,
      "step": 10305
    },
    {
      "epoch": 0.31659140478604125,
      "grad_norm": 0.30929034948349,
      "learning_rate": 1.8808296687568356e-05,
      "loss": 0.6098,
      "step": 10306
    },
    {
      "epoch": 0.3166221239209904,
      "grad_norm": 0.35834476351737976,
      "learning_rate": 1.8808067877695418e-05,
      "loss": 0.6192,
      "step": 10307
    },
    {
      "epoch": 0.31665284305593955,
      "grad_norm": 0.37792113423347473,
      "learning_rate": 1.8807839047250628e-05,
      "loss": 0.6472,
      "step": 10308
    },
    {
      "epoch": 0.3166835621908887,
      "grad_norm": 0.3793802261352539,
      "learning_rate": 1.8807610196234515e-05,
      "loss": 0.5165,
      "step": 10309
    },
    {
      "epoch": 0.31671428132583784,
      "grad_norm": 0.40697750449180603,
      "learning_rate": 1.880738132464761e-05,
      "loss": 0.7193,
      "step": 10310
    },
    {
      "epoch": 0.316745000460787,
      "grad_norm": 0.35743093490600586,
      "learning_rate": 1.880715243249045e-05,
      "loss": 0.6725,
      "step": 10311
    },
    {
      "epoch": 0.3167757195957362,
      "grad_norm": 0.35486525297164917,
      "learning_rate": 1.8806923519763575e-05,
      "loss": 0.4943,
      "step": 10312
    },
    {
      "epoch": 0.31680643873068537,
      "grad_norm": 0.31848639249801636,
      "learning_rate": 1.880669458646751e-05,
      "loss": 0.5546,
      "step": 10313
    },
    {
      "epoch": 0.3168371578656345,
      "grad_norm": 0.37886863946914673,
      "learning_rate": 1.88064656326028e-05,
      "loss": 0.5135,
      "step": 10314
    },
    {
      "epoch": 0.31686787700058366,
      "grad_norm": 0.35622113943099976,
      "learning_rate": 1.8806236658169972e-05,
      "loss": 0.5169,
      "step": 10315
    },
    {
      "epoch": 0.31689859613553284,
      "grad_norm": 0.3233979046344757,
      "learning_rate": 1.880600766316956e-05,
      "loss": 0.5308,
      "step": 10316
    },
    {
      "epoch": 0.31692931527048196,
      "grad_norm": 0.3506705164909363,
      "learning_rate": 1.8805778647602108e-05,
      "loss": 0.5282,
      "step": 10317
    },
    {
      "epoch": 0.31696003440543113,
      "grad_norm": 0.3626779019832611,
      "learning_rate": 1.880554961146814e-05,
      "loss": 0.5135,
      "step": 10318
    },
    {
      "epoch": 0.3169907535403803,
      "grad_norm": 0.34216010570526123,
      "learning_rate": 1.88053205547682e-05,
      "loss": 0.5902,
      "step": 10319
    },
    {
      "epoch": 0.3170214726753295,
      "grad_norm": 0.3438121974468231,
      "learning_rate": 1.8805091477502816e-05,
      "loss": 0.5476,
      "step": 10320
    },
    {
      "epoch": 0.3170521918102786,
      "grad_norm": 0.3156261742115021,
      "learning_rate": 1.8804862379672527e-05,
      "loss": 0.5501,
      "step": 10321
    },
    {
      "epoch": 0.3170829109452278,
      "grad_norm": 0.3951742649078369,
      "learning_rate": 1.8804633261277866e-05,
      "loss": 0.5198,
      "step": 10322
    },
    {
      "epoch": 0.31711363008017696,
      "grad_norm": 0.38282960653305054,
      "learning_rate": 1.8804404122319367e-05,
      "loss": 0.5729,
      "step": 10323
    },
    {
      "epoch": 0.3171443492151261,
      "grad_norm": 0.4546809494495392,
      "learning_rate": 1.880417496279757e-05,
      "loss": 0.599,
      "step": 10324
    },
    {
      "epoch": 0.31717506835007525,
      "grad_norm": 0.3678719103336334,
      "learning_rate": 1.880394578271301e-05,
      "loss": 0.6741,
      "step": 10325
    },
    {
      "epoch": 0.3172057874850244,
      "grad_norm": 0.3521033227443695,
      "learning_rate": 1.8803716582066216e-05,
      "loss": 0.6208,
      "step": 10326
    },
    {
      "epoch": 0.3172365066199736,
      "grad_norm": 0.3485983908176422,
      "learning_rate": 1.880348736085773e-05,
      "loss": 0.5446,
      "step": 10327
    },
    {
      "epoch": 0.3172672257549227,
      "grad_norm": 0.3643217086791992,
      "learning_rate": 1.8803258119088084e-05,
      "loss": 0.6113,
      "step": 10328
    },
    {
      "epoch": 0.3172979448898719,
      "grad_norm": 0.33563220500946045,
      "learning_rate": 1.8803028856757813e-05,
      "loss": 0.6112,
      "step": 10329
    },
    {
      "epoch": 0.31732866402482107,
      "grad_norm": 0.3731679320335388,
      "learning_rate": 1.880279957386745e-05,
      "loss": 0.6095,
      "step": 10330
    },
    {
      "epoch": 0.31735938315977025,
      "grad_norm": 0.38268938660621643,
      "learning_rate": 1.8802570270417538e-05,
      "loss": 0.5826,
      "step": 10331
    },
    {
      "epoch": 0.31739010229471937,
      "grad_norm": 0.33716657757759094,
      "learning_rate": 1.880234094640861e-05,
      "loss": 0.5908,
      "step": 10332
    },
    {
      "epoch": 0.31742082142966854,
      "grad_norm": 0.35238581895828247,
      "learning_rate": 1.8802111601841196e-05,
      "loss": 0.6451,
      "step": 10333
    },
    {
      "epoch": 0.3174515405646177,
      "grad_norm": 0.3362695574760437,
      "learning_rate": 1.8801882236715837e-05,
      "loss": 0.5729,
      "step": 10334
    },
    {
      "epoch": 0.31748225969956684,
      "grad_norm": 0.4412815272808075,
      "learning_rate": 1.8801652851033066e-05,
      "loss": 0.5874,
      "step": 10335
    },
    {
      "epoch": 0.317512978834516,
      "grad_norm": 0.35605287551879883,
      "learning_rate": 1.8801423444793422e-05,
      "loss": 0.6101,
      "step": 10336
    },
    {
      "epoch": 0.3175436979694652,
      "grad_norm": 0.34616634249687195,
      "learning_rate": 1.8801194017997437e-05,
      "loss": 0.5173,
      "step": 10337
    },
    {
      "epoch": 0.31757441710441436,
      "grad_norm": 0.37092649936676025,
      "learning_rate": 1.880096457064565e-05,
      "loss": 0.5639,
      "step": 10338
    },
    {
      "epoch": 0.3176051362393635,
      "grad_norm": 0.4190486669540405,
      "learning_rate": 1.8800735102738595e-05,
      "loss": 0.7096,
      "step": 10339
    },
    {
      "epoch": 0.31763585537431266,
      "grad_norm": 0.3465522825717926,
      "learning_rate": 1.880050561427681e-05,
      "loss": 0.5528,
      "step": 10340
    },
    {
      "epoch": 0.31766657450926183,
      "grad_norm": 0.3458513617515564,
      "learning_rate": 1.880027610526083e-05,
      "loss": 0.6736,
      "step": 10341
    },
    {
      "epoch": 0.31769729364421095,
      "grad_norm": 0.33456161618232727,
      "learning_rate": 1.8800046575691186e-05,
      "loss": 0.5333,
      "step": 10342
    },
    {
      "epoch": 0.31772801277916013,
      "grad_norm": 0.33494603633880615,
      "learning_rate": 1.879981702556842e-05,
      "loss": 0.6157,
      "step": 10343
    },
    {
      "epoch": 0.3177587319141093,
      "grad_norm": 0.47835129499435425,
      "learning_rate": 1.879958745489307e-05,
      "loss": 0.6236,
      "step": 10344
    },
    {
      "epoch": 0.3177894510490585,
      "grad_norm": 0.3685917854309082,
      "learning_rate": 1.879935786366567e-05,
      "loss": 0.6129,
      "step": 10345
    },
    {
      "epoch": 0.3178201701840076,
      "grad_norm": 0.37018319964408875,
      "learning_rate": 1.879912825188675e-05,
      "loss": 0.6311,
      "step": 10346
    },
    {
      "epoch": 0.3178508893189568,
      "grad_norm": 0.651077389717102,
      "learning_rate": 1.8798898619556857e-05,
      "loss": 0.5351,
      "step": 10347
    },
    {
      "epoch": 0.31788160845390595,
      "grad_norm": 0.3516663610935211,
      "learning_rate": 1.8798668966676516e-05,
      "loss": 0.6577,
      "step": 10348
    },
    {
      "epoch": 0.31791232758885507,
      "grad_norm": 0.352861613035202,
      "learning_rate": 1.8798439293246272e-05,
      "loss": 0.4871,
      "step": 10349
    },
    {
      "epoch": 0.31794304672380425,
      "grad_norm": 0.3361690640449524,
      "learning_rate": 1.879820959926666e-05,
      "loss": 0.5524,
      "step": 10350
    },
    {
      "epoch": 0.3179737658587534,
      "grad_norm": 0.3244180977344513,
      "learning_rate": 1.879797988473821e-05,
      "loss": 0.5395,
      "step": 10351
    },
    {
      "epoch": 0.3180044849937026,
      "grad_norm": 0.36683109402656555,
      "learning_rate": 1.879775014966147e-05,
      "loss": 0.5757,
      "step": 10352
    },
    {
      "epoch": 0.3180352041286517,
      "grad_norm": 0.35545703768730164,
      "learning_rate": 1.8797520394036965e-05,
      "loss": 0.541,
      "step": 10353
    },
    {
      "epoch": 0.3180659232636009,
      "grad_norm": 0.33326125144958496,
      "learning_rate": 1.879729061786524e-05,
      "loss": 0.5288,
      "step": 10354
    },
    {
      "epoch": 0.31809664239855007,
      "grad_norm": 0.4097500145435333,
      "learning_rate": 1.8797060821146825e-05,
      "loss": 0.5245,
      "step": 10355
    },
    {
      "epoch": 0.31812736153349924,
      "grad_norm": 0.41521528363227844,
      "learning_rate": 1.8796831003882265e-05,
      "loss": 0.5278,
      "step": 10356
    },
    {
      "epoch": 0.31815808066844836,
      "grad_norm": 0.3441811501979828,
      "learning_rate": 1.8796601166072087e-05,
      "loss": 0.5887,
      "step": 10357
    },
    {
      "epoch": 0.31818879980339754,
      "grad_norm": 0.3411293029785156,
      "learning_rate": 1.8796371307716837e-05,
      "loss": 0.5671,
      "step": 10358
    },
    {
      "epoch": 0.3182195189383467,
      "grad_norm": 0.5855925679206848,
      "learning_rate": 1.8796141428817043e-05,
      "loss": 0.5489,
      "step": 10359
    },
    {
      "epoch": 0.31825023807329583,
      "grad_norm": 0.530379056930542,
      "learning_rate": 1.8795911529373248e-05,
      "loss": 0.6221,
      "step": 10360
    },
    {
      "epoch": 0.318280957208245,
      "grad_norm": 0.4495023190975189,
      "learning_rate": 1.879568160938599e-05,
      "loss": 0.6072,
      "step": 10361
    },
    {
      "epoch": 0.3183116763431942,
      "grad_norm": 0.37415197491645813,
      "learning_rate": 1.87954516688558e-05,
      "loss": 0.595,
      "step": 10362
    },
    {
      "epoch": 0.31834239547814336,
      "grad_norm": 0.3902260959148407,
      "learning_rate": 1.879522170778322e-05,
      "loss": 0.5869,
      "step": 10363
    },
    {
      "epoch": 0.3183731146130925,
      "grad_norm": 0.3843447268009186,
      "learning_rate": 1.8794991726168783e-05,
      "loss": 0.6294,
      "step": 10364
    },
    {
      "epoch": 0.31840383374804165,
      "grad_norm": 0.37625810503959656,
      "learning_rate": 1.879476172401303e-05,
      "loss": 0.6159,
      "step": 10365
    },
    {
      "epoch": 0.31843455288299083,
      "grad_norm": 0.38067394495010376,
      "learning_rate": 1.87945317013165e-05,
      "loss": 0.6003,
      "step": 10366
    },
    {
      "epoch": 0.31846527201793995,
      "grad_norm": 0.3400162160396576,
      "learning_rate": 1.8794301658079724e-05,
      "loss": 0.5277,
      "step": 10367
    },
    {
      "epoch": 0.3184959911528891,
      "grad_norm": 0.323940247297287,
      "learning_rate": 1.8794071594303243e-05,
      "loss": 0.5434,
      "step": 10368
    },
    {
      "epoch": 0.3185267102878383,
      "grad_norm": 0.3974185883998871,
      "learning_rate": 1.8793841509987592e-05,
      "loss": 0.6006,
      "step": 10369
    },
    {
      "epoch": 0.3185574294227875,
      "grad_norm": 0.3514109253883362,
      "learning_rate": 1.8793611405133313e-05,
      "loss": 0.4918,
      "step": 10370
    },
    {
      "epoch": 0.3185881485577366,
      "grad_norm": 0.3499881327152252,
      "learning_rate": 1.879338127974094e-05,
      "loss": 0.6489,
      "step": 10371
    },
    {
      "epoch": 0.31861886769268577,
      "grad_norm": 0.31905511021614075,
      "learning_rate": 1.8793151133811007e-05,
      "loss": 0.6239,
      "step": 10372
    },
    {
      "epoch": 0.31864958682763495,
      "grad_norm": 0.38234943151474,
      "learning_rate": 1.8792920967344056e-05,
      "loss": 0.6301,
      "step": 10373
    },
    {
      "epoch": 0.3186803059625841,
      "grad_norm": 0.3488442599773407,
      "learning_rate": 1.879269078034063e-05,
      "loss": 0.5856,
      "step": 10374
    },
    {
      "epoch": 0.31871102509753324,
      "grad_norm": 0.4142951965332031,
      "learning_rate": 1.8792460572801254e-05,
      "loss": 0.56,
      "step": 10375
    },
    {
      "epoch": 0.3187417442324824,
      "grad_norm": 0.33907902240753174,
      "learning_rate": 1.8792230344726477e-05,
      "loss": 0.5932,
      "step": 10376
    },
    {
      "epoch": 0.3187724633674316,
      "grad_norm": 0.3936256468296051,
      "learning_rate": 1.8792000096116825e-05,
      "loss": 0.6562,
      "step": 10377
    },
    {
      "epoch": 0.3188031825023807,
      "grad_norm": 0.34662601351737976,
      "learning_rate": 1.8791769826972853e-05,
      "loss": 0.5714,
      "step": 10378
    },
    {
      "epoch": 0.3188339016373299,
      "grad_norm": 0.36017748713493347,
      "learning_rate": 1.879153953729508e-05,
      "loss": 0.5935,
      "step": 10379
    },
    {
      "epoch": 0.31886462077227906,
      "grad_norm": 0.47439631819725037,
      "learning_rate": 1.8791309227084057e-05,
      "loss": 0.6551,
      "step": 10380
    },
    {
      "epoch": 0.31889533990722824,
      "grad_norm": 0.48930343985557556,
      "learning_rate": 1.8791078896340314e-05,
      "loss": 0.6614,
      "step": 10381
    },
    {
      "epoch": 0.31892605904217736,
      "grad_norm": 0.3326151371002197,
      "learning_rate": 1.8790848545064395e-05,
      "loss": 0.5371,
      "step": 10382
    },
    {
      "epoch": 0.31895677817712653,
      "grad_norm": 0.4107203781604767,
      "learning_rate": 1.8790618173256834e-05,
      "loss": 0.6163,
      "step": 10383
    },
    {
      "epoch": 0.3189874973120757,
      "grad_norm": 0.39710697531700134,
      "learning_rate": 1.879038778091817e-05,
      "loss": 0.6236,
      "step": 10384
    },
    {
      "epoch": 0.3190182164470248,
      "grad_norm": 0.35794708132743835,
      "learning_rate": 1.8790157368048945e-05,
      "loss": 0.5539,
      "step": 10385
    },
    {
      "epoch": 0.319048935581974,
      "grad_norm": 0.3403283953666687,
      "learning_rate": 1.878992693464969e-05,
      "loss": 0.5901,
      "step": 10386
    },
    {
      "epoch": 0.3190796547169232,
      "grad_norm": 0.3751843273639679,
      "learning_rate": 1.878969648072095e-05,
      "loss": 0.6975,
      "step": 10387
    },
    {
      "epoch": 0.31911037385187235,
      "grad_norm": 0.3646900951862335,
      "learning_rate": 1.8789466006263254e-05,
      "loss": 0.5511,
      "step": 10388
    },
    {
      "epoch": 0.3191410929868215,
      "grad_norm": 0.5699176788330078,
      "learning_rate": 1.878923551127715e-05,
      "loss": 0.5605,
      "step": 10389
    },
    {
      "epoch": 0.31917181212177065,
      "grad_norm": 0.4766837954521179,
      "learning_rate": 1.878900499576317e-05,
      "loss": 0.6373,
      "step": 10390
    },
    {
      "epoch": 0.3192025312567198,
      "grad_norm": 0.3415882885456085,
      "learning_rate": 1.878877445972186e-05,
      "loss": 0.5736,
      "step": 10391
    },
    {
      "epoch": 0.31923325039166894,
      "grad_norm": 0.48607170581817627,
      "learning_rate": 1.878854390315375e-05,
      "loss": 0.7226,
      "step": 10392
    },
    {
      "epoch": 0.3192639695266181,
      "grad_norm": 0.3539358377456665,
      "learning_rate": 1.8788313326059383e-05,
      "loss": 0.5621,
      "step": 10393
    },
    {
      "epoch": 0.3192946886615673,
      "grad_norm": 0.32131141424179077,
      "learning_rate": 1.8788082728439296e-05,
      "loss": 0.6331,
      "step": 10394
    },
    {
      "epoch": 0.31932540779651647,
      "grad_norm": 0.34996354579925537,
      "learning_rate": 1.878785211029403e-05,
      "loss": 0.5838,
      "step": 10395
    },
    {
      "epoch": 0.3193561269314656,
      "grad_norm": 0.3839188814163208,
      "learning_rate": 1.878762147162412e-05,
      "loss": 0.5793,
      "step": 10396
    },
    {
      "epoch": 0.31938684606641476,
      "grad_norm": 0.39505118131637573,
      "learning_rate": 1.8787390812430105e-05,
      "loss": 0.5602,
      "step": 10397
    },
    {
      "epoch": 0.31941756520136394,
      "grad_norm": 0.3634696304798126,
      "learning_rate": 1.878716013271253e-05,
      "loss": 0.519,
      "step": 10398
    },
    {
      "epoch": 0.3194482843363131,
      "grad_norm": 0.3570019602775574,
      "learning_rate": 1.878692943247192e-05,
      "loss": 0.635,
      "step": 10399
    },
    {
      "epoch": 0.31947900347126224,
      "grad_norm": 0.376730352640152,
      "learning_rate": 1.878669871170883e-05,
      "loss": 0.5809,
      "step": 10400
    },
    {
      "epoch": 0.3195097226062114,
      "grad_norm": 0.3459199368953705,
      "learning_rate": 1.878646797042379e-05,
      "loss": 0.5691,
      "step": 10401
    },
    {
      "epoch": 0.3195404417411606,
      "grad_norm": 0.3691335916519165,
      "learning_rate": 1.8786237208617338e-05,
      "loss": 0.5362,
      "step": 10402
    },
    {
      "epoch": 0.3195711608761097,
      "grad_norm": 0.3914206326007843,
      "learning_rate": 1.8786006426290018e-05,
      "loss": 0.6286,
      "step": 10403
    },
    {
      "epoch": 0.3196018800110589,
      "grad_norm": 0.3577726483345032,
      "learning_rate": 1.8785775623442365e-05,
      "loss": 0.5687,
      "step": 10404
    },
    {
      "epoch": 0.31963259914600806,
      "grad_norm": 0.42798563838005066,
      "learning_rate": 1.878554480007492e-05,
      "loss": 0.6102,
      "step": 10405
    },
    {
      "epoch": 0.31966331828095723,
      "grad_norm": 0.3485327363014221,
      "learning_rate": 1.8785313956188223e-05,
      "loss": 0.5635,
      "step": 10406
    },
    {
      "epoch": 0.31969403741590635,
      "grad_norm": 0.3698714077472687,
      "learning_rate": 1.878508309178281e-05,
      "loss": 0.5831,
      "step": 10407
    },
    {
      "epoch": 0.3197247565508555,
      "grad_norm": 0.37608012557029724,
      "learning_rate": 1.878485220685922e-05,
      "loss": 0.4726,
      "step": 10408
    },
    {
      "epoch": 0.3197554756858047,
      "grad_norm": 0.40061071515083313,
      "learning_rate": 1.8784621301418e-05,
      "loss": 0.5658,
      "step": 10409
    },
    {
      "epoch": 0.3197861948207538,
      "grad_norm": 0.35453954339027405,
      "learning_rate": 1.8784390375459675e-05,
      "loss": 0.5519,
      "step": 10410
    },
    {
      "epoch": 0.319816913955703,
      "grad_norm": 0.4018420875072479,
      "learning_rate": 1.87841594289848e-05,
      "loss": 0.5603,
      "step": 10411
    },
    {
      "epoch": 0.3198476330906522,
      "grad_norm": 0.34728437662124634,
      "learning_rate": 1.8783928461993906e-05,
      "loss": 0.6214,
      "step": 10412
    },
    {
      "epoch": 0.31987835222560135,
      "grad_norm": 0.3605533838272095,
      "learning_rate": 1.878369747448753e-05,
      "loss": 0.5732,
      "step": 10413
    },
    {
      "epoch": 0.31990907136055047,
      "grad_norm": 0.3274520933628082,
      "learning_rate": 1.878346646646622e-05,
      "loss": 0.6246,
      "step": 10414
    },
    {
      "epoch": 0.31993979049549964,
      "grad_norm": 0.5785011649131775,
      "learning_rate": 1.8783235437930507e-05,
      "loss": 0.659,
      "step": 10415
    },
    {
      "epoch": 0.3199705096304488,
      "grad_norm": 0.34852394461631775,
      "learning_rate": 1.8783004388880934e-05,
      "loss": 0.5732,
      "step": 10416
    },
    {
      "epoch": 0.320001228765398,
      "grad_norm": 0.3095927834510803,
      "learning_rate": 1.8782773319318043e-05,
      "loss": 0.5369,
      "step": 10417
    },
    {
      "epoch": 0.3200319479003471,
      "grad_norm": 0.3479742705821991,
      "learning_rate": 1.8782542229242372e-05,
      "loss": 0.5773,
      "step": 10418
    },
    {
      "epoch": 0.3200626670352963,
      "grad_norm": 0.3420276641845703,
      "learning_rate": 1.8782311118654457e-05,
      "loss": 0.5852,
      "step": 10419
    },
    {
      "epoch": 0.32009338617024546,
      "grad_norm": 0.3882110118865967,
      "learning_rate": 1.8782079987554843e-05,
      "loss": 0.5576,
      "step": 10420
    },
    {
      "epoch": 0.3201241053051946,
      "grad_norm": 0.34206265211105347,
      "learning_rate": 1.8781848835944068e-05,
      "loss": 0.5734,
      "step": 10421
    },
    {
      "epoch": 0.32015482444014376,
      "grad_norm": 0.35433822870254517,
      "learning_rate": 1.878161766382267e-05,
      "loss": 0.523,
      "step": 10422
    },
    {
      "epoch": 0.32018554357509293,
      "grad_norm": 0.3119700253009796,
      "learning_rate": 1.8781386471191192e-05,
      "loss": 0.5769,
      "step": 10423
    },
    {
      "epoch": 0.3202162627100421,
      "grad_norm": 0.3361133635044098,
      "learning_rate": 1.8781155258050176e-05,
      "loss": 0.5952,
      "step": 10424
    },
    {
      "epoch": 0.32024698184499123,
      "grad_norm": 0.34520527720451355,
      "learning_rate": 1.8780924024400154e-05,
      "loss": 0.6,
      "step": 10425
    },
    {
      "epoch": 0.3202777009799404,
      "grad_norm": 0.33207187056541443,
      "learning_rate": 1.878069277024167e-05,
      "loss": 0.608,
      "step": 10426
    },
    {
      "epoch": 0.3203084201148896,
      "grad_norm": 0.3994479775428772,
      "learning_rate": 1.8780461495575268e-05,
      "loss": 0.5091,
      "step": 10427
    },
    {
      "epoch": 0.3203391392498387,
      "grad_norm": 0.4845339357852936,
      "learning_rate": 1.8780230200401482e-05,
      "loss": 0.5907,
      "step": 10428
    },
    {
      "epoch": 0.3203698583847879,
      "grad_norm": 0.34427645802497864,
      "learning_rate": 1.877999888472086e-05,
      "loss": 0.5725,
      "step": 10429
    },
    {
      "epoch": 0.32040057751973705,
      "grad_norm": 0.3655513525009155,
      "learning_rate": 1.877976754853393e-05,
      "loss": 0.5663,
      "step": 10430
    },
    {
      "epoch": 0.3204312966546862,
      "grad_norm": 0.3395141363143921,
      "learning_rate": 1.8779536191841247e-05,
      "loss": 0.5686,
      "step": 10431
    },
    {
      "epoch": 0.32046201578963535,
      "grad_norm": 0.3447889983654022,
      "learning_rate": 1.8779304814643338e-05,
      "loss": 0.5495,
      "step": 10432
    },
    {
      "epoch": 0.3204927349245845,
      "grad_norm": 0.32104000449180603,
      "learning_rate": 1.8779073416940758e-05,
      "loss": 0.5361,
      "step": 10433
    },
    {
      "epoch": 0.3205234540595337,
      "grad_norm": 0.3978859782218933,
      "learning_rate": 1.8778841998734033e-05,
      "loss": 0.5736,
      "step": 10434
    },
    {
      "epoch": 0.3205541731944828,
      "grad_norm": 0.3821896016597748,
      "learning_rate": 1.8778610560023708e-05,
      "loss": 0.6077,
      "step": 10435
    },
    {
      "epoch": 0.320584892329432,
      "grad_norm": 0.37851133942604065,
      "learning_rate": 1.8778379100810326e-05,
      "loss": 0.5903,
      "step": 10436
    },
    {
      "epoch": 0.32061561146438117,
      "grad_norm": 0.36211201548576355,
      "learning_rate": 1.8778147621094428e-05,
      "loss": 0.6628,
      "step": 10437
    },
    {
      "epoch": 0.32064633059933034,
      "grad_norm": 0.6063089370727539,
      "learning_rate": 1.877791612087655e-05,
      "loss": 0.4477,
      "step": 10438
    },
    {
      "epoch": 0.32067704973427946,
      "grad_norm": 0.37523066997528076,
      "learning_rate": 1.877768460015724e-05,
      "loss": 0.5413,
      "step": 10439
    },
    {
      "epoch": 0.32070776886922864,
      "grad_norm": 0.3735823333263397,
      "learning_rate": 1.8777453058937033e-05,
      "loss": 0.5741,
      "step": 10440
    },
    {
      "epoch": 0.3207384880041778,
      "grad_norm": 0.3618384301662445,
      "learning_rate": 1.8777221497216473e-05,
      "loss": 0.5269,
      "step": 10441
    },
    {
      "epoch": 0.320769207139127,
      "grad_norm": 0.39149394631385803,
      "learning_rate": 1.87769899149961e-05,
      "loss": 0.5705,
      "step": 10442
    },
    {
      "epoch": 0.3207999262740761,
      "grad_norm": 0.3562537431716919,
      "learning_rate": 1.877675831227645e-05,
      "loss": 0.6048,
      "step": 10443
    },
    {
      "epoch": 0.3208306454090253,
      "grad_norm": 0.39754435420036316,
      "learning_rate": 1.8776526689058067e-05,
      "loss": 0.5982,
      "step": 10444
    },
    {
      "epoch": 0.32086136454397446,
      "grad_norm": 0.3652607798576355,
      "learning_rate": 1.8776295045341496e-05,
      "loss": 0.4592,
      "step": 10445
    },
    {
      "epoch": 0.3208920836789236,
      "grad_norm": 0.4440177083015442,
      "learning_rate": 1.8776063381127276e-05,
      "loss": 0.6217,
      "step": 10446
    },
    {
      "epoch": 0.32092280281387275,
      "grad_norm": 0.3403913974761963,
      "learning_rate": 1.8775831696415946e-05,
      "loss": 0.6246,
      "step": 10447
    },
    {
      "epoch": 0.32095352194882193,
      "grad_norm": 0.34125635027885437,
      "learning_rate": 1.8775599991208046e-05,
      "loss": 0.4942,
      "step": 10448
    },
    {
      "epoch": 0.3209842410837711,
      "grad_norm": 0.332894504070282,
      "learning_rate": 1.8775368265504123e-05,
      "loss": 0.5073,
      "step": 10449
    },
    {
      "epoch": 0.3210149602187202,
      "grad_norm": 0.34188079833984375,
      "learning_rate": 1.8775136519304713e-05,
      "loss": 0.5598,
      "step": 10450
    },
    {
      "epoch": 0.3210456793536694,
      "grad_norm": 0.30355602502822876,
      "learning_rate": 1.877490475261036e-05,
      "loss": 0.5501,
      "step": 10451
    },
    {
      "epoch": 0.3210763984886186,
      "grad_norm": 0.3346308767795563,
      "learning_rate": 1.8774672965421602e-05,
      "loss": 0.5969,
      "step": 10452
    },
    {
      "epoch": 0.3211071176235677,
      "grad_norm": 0.4474734365940094,
      "learning_rate": 1.877444115773898e-05,
      "loss": 0.5647,
      "step": 10453
    },
    {
      "epoch": 0.32113783675851687,
      "grad_norm": 0.36739033460617065,
      "learning_rate": 1.8774209329563042e-05,
      "loss": 0.5937,
      "step": 10454
    },
    {
      "epoch": 0.32116855589346605,
      "grad_norm": 0.3273799419403076,
      "learning_rate": 1.8773977480894327e-05,
      "loss": 0.6075,
      "step": 10455
    },
    {
      "epoch": 0.3211992750284152,
      "grad_norm": 0.40559348464012146,
      "learning_rate": 1.877374561173337e-05,
      "loss": 0.5578,
      "step": 10456
    },
    {
      "epoch": 0.32122999416336434,
      "grad_norm": 0.33529654145240784,
      "learning_rate": 1.8773513722080722e-05,
      "loss": 0.5062,
      "step": 10457
    },
    {
      "epoch": 0.3212607132983135,
      "grad_norm": 0.33447501063346863,
      "learning_rate": 1.8773281811936916e-05,
      "loss": 0.5716,
      "step": 10458
    },
    {
      "epoch": 0.3212914324332627,
      "grad_norm": 0.38884878158569336,
      "learning_rate": 1.87730498813025e-05,
      "loss": 0.5142,
      "step": 10459
    },
    {
      "epoch": 0.32132215156821187,
      "grad_norm": 0.39758390188217163,
      "learning_rate": 1.877281793017801e-05,
      "loss": 0.626,
      "step": 10460
    },
    {
      "epoch": 0.321352870703161,
      "grad_norm": 0.3643445670604706,
      "learning_rate": 1.8772585958563994e-05,
      "loss": 0.5609,
      "step": 10461
    },
    {
      "epoch": 0.32138358983811016,
      "grad_norm": 0.37395721673965454,
      "learning_rate": 1.877235396646099e-05,
      "loss": 0.5845,
      "step": 10462
    },
    {
      "epoch": 0.32141430897305934,
      "grad_norm": 0.34857746958732605,
      "learning_rate": 1.8772121953869542e-05,
      "loss": 0.6616,
      "step": 10463
    },
    {
      "epoch": 0.32144502810800846,
      "grad_norm": 0.3876510262489319,
      "learning_rate": 1.877188992079019e-05,
      "loss": 0.5812,
      "step": 10464
    },
    {
      "epoch": 0.32147574724295763,
      "grad_norm": 0.36043038964271545,
      "learning_rate": 1.8771657867223476e-05,
      "loss": 0.6066,
      "step": 10465
    },
    {
      "epoch": 0.3215064663779068,
      "grad_norm": 0.3366979956626892,
      "learning_rate": 1.8771425793169942e-05,
      "loss": 0.5796,
      "step": 10466
    },
    {
      "epoch": 0.321537185512856,
      "grad_norm": 0.33658766746520996,
      "learning_rate": 1.8771193698630134e-05,
      "loss": 0.5692,
      "step": 10467
    },
    {
      "epoch": 0.3215679046478051,
      "grad_norm": 0.3641218841075897,
      "learning_rate": 1.8770961583604586e-05,
      "loss": 0.6263,
      "step": 10468
    },
    {
      "epoch": 0.3215986237827543,
      "grad_norm": 0.33797866106033325,
      "learning_rate": 1.8770729448093845e-05,
      "loss": 0.6145,
      "step": 10469
    },
    {
      "epoch": 0.32162934291770345,
      "grad_norm": 0.38558706641197205,
      "learning_rate": 1.8770497292098456e-05,
      "loss": 0.6651,
      "step": 10470
    },
    {
      "epoch": 0.3216600620526526,
      "grad_norm": 0.38323575258255005,
      "learning_rate": 1.8770265115618957e-05,
      "loss": 0.6075,
      "step": 10471
    },
    {
      "epoch": 0.32169078118760175,
      "grad_norm": 0.3677614629268646,
      "learning_rate": 1.8770032918655887e-05,
      "loss": 0.6531,
      "step": 10472
    },
    {
      "epoch": 0.3217215003225509,
      "grad_norm": 0.3235359489917755,
      "learning_rate": 1.8769800701209796e-05,
      "loss": 0.5559,
      "step": 10473
    },
    {
      "epoch": 0.3217522194575001,
      "grad_norm": 0.3164503872394562,
      "learning_rate": 1.876956846328122e-05,
      "loss": 0.4915,
      "step": 10474
    },
    {
      "epoch": 0.3217829385924492,
      "grad_norm": 0.37993302941322327,
      "learning_rate": 1.876933620487071e-05,
      "loss": 0.6184,
      "step": 10475
    },
    {
      "epoch": 0.3218136577273984,
      "grad_norm": 0.4029066264629364,
      "learning_rate": 1.87691039259788e-05,
      "loss": 0.663,
      "step": 10476
    },
    {
      "epoch": 0.32184437686234757,
      "grad_norm": 0.3376162350177765,
      "learning_rate": 1.8768871626606036e-05,
      "loss": 0.5813,
      "step": 10477
    },
    {
      "epoch": 0.3218750959972967,
      "grad_norm": 0.35696524381637573,
      "learning_rate": 1.8768639306752957e-05,
      "loss": 0.5178,
      "step": 10478
    },
    {
      "epoch": 0.32190581513224586,
      "grad_norm": 0.34637251496315,
      "learning_rate": 1.8768406966420115e-05,
      "loss": 0.563,
      "step": 10479
    },
    {
      "epoch": 0.32193653426719504,
      "grad_norm": 0.3301503360271454,
      "learning_rate": 1.8768174605608042e-05,
      "loss": 0.5603,
      "step": 10480
    },
    {
      "epoch": 0.3219672534021442,
      "grad_norm": 0.31788602471351624,
      "learning_rate": 1.876794222431728e-05,
      "loss": 0.4902,
      "step": 10481
    },
    {
      "epoch": 0.32199797253709334,
      "grad_norm": 0.35312265157699585,
      "learning_rate": 1.8767709822548387e-05,
      "loss": 0.633,
      "step": 10482
    },
    {
      "epoch": 0.3220286916720425,
      "grad_norm": 0.4057193994522095,
      "learning_rate": 1.876747740030189e-05,
      "loss": 0.5948,
      "step": 10483
    },
    {
      "epoch": 0.3220594108069917,
      "grad_norm": 0.3522506654262543,
      "learning_rate": 1.8767244957578335e-05,
      "loss": 0.6292,
      "step": 10484
    },
    {
      "epoch": 0.32209012994194086,
      "grad_norm": 0.36108675599098206,
      "learning_rate": 1.876701249437827e-05,
      "loss": 0.5531,
      "step": 10485
    },
    {
      "epoch": 0.32212084907689,
      "grad_norm": 0.3845078647136688,
      "learning_rate": 1.8766780010702234e-05,
      "loss": 0.5234,
      "step": 10486
    },
    {
      "epoch": 0.32215156821183916,
      "grad_norm": 0.3433791697025299,
      "learning_rate": 1.876654750655077e-05,
      "loss": 0.5271,
      "step": 10487
    },
    {
      "epoch": 0.32218228734678833,
      "grad_norm": 0.3829619884490967,
      "learning_rate": 1.8766314981924423e-05,
      "loss": 0.5792,
      "step": 10488
    },
    {
      "epoch": 0.32221300648173745,
      "grad_norm": 0.34608232975006104,
      "learning_rate": 1.8766082436823734e-05,
      "loss": 0.6047,
      "step": 10489
    },
    {
      "epoch": 0.3222437256166866,
      "grad_norm": 0.307329386472702,
      "learning_rate": 1.876584987124925e-05,
      "loss": 0.5365,
      "step": 10490
    },
    {
      "epoch": 0.3222744447516358,
      "grad_norm": 0.3400796949863434,
      "learning_rate": 1.876561728520151e-05,
      "loss": 0.55,
      "step": 10491
    },
    {
      "epoch": 0.322305163886585,
      "grad_norm": 0.3400638699531555,
      "learning_rate": 1.8765384678681057e-05,
      "loss": 0.5602,
      "step": 10492
    },
    {
      "epoch": 0.3223358830215341,
      "grad_norm": 0.3324618637561798,
      "learning_rate": 1.876515205168844e-05,
      "loss": 0.5139,
      "step": 10493
    },
    {
      "epoch": 0.3223666021564833,
      "grad_norm": 0.3323565125465393,
      "learning_rate": 1.8764919404224196e-05,
      "loss": 0.6073,
      "step": 10494
    },
    {
      "epoch": 0.32239732129143245,
      "grad_norm": 0.3662666380405426,
      "learning_rate": 1.876468673628887e-05,
      "loss": 0.6019,
      "step": 10495
    },
    {
      "epoch": 0.32242804042638157,
      "grad_norm": 0.3799459934234619,
      "learning_rate": 1.8764454047883007e-05,
      "loss": 0.6777,
      "step": 10496
    },
    {
      "epoch": 0.32245875956133074,
      "grad_norm": 0.3329426646232605,
      "learning_rate": 1.876422133900715e-05,
      "loss": 0.5717,
      "step": 10497
    },
    {
      "epoch": 0.3224894786962799,
      "grad_norm": 0.3386916518211365,
      "learning_rate": 1.876398860966184e-05,
      "loss": 0.6117,
      "step": 10498
    },
    {
      "epoch": 0.3225201978312291,
      "grad_norm": 0.3396860361099243,
      "learning_rate": 1.8763755859847622e-05,
      "loss": 0.6002,
      "step": 10499
    },
    {
      "epoch": 0.3225509169661782,
      "grad_norm": 0.3209167718887329,
      "learning_rate": 1.8763523089565044e-05,
      "loss": 0.6198,
      "step": 10500
    },
    {
      "epoch": 0.3225816361011274,
      "grad_norm": 0.3563041090965271,
      "learning_rate": 1.8763290298814643e-05,
      "loss": 0.5286,
      "step": 10501
    },
    {
      "epoch": 0.32261235523607656,
      "grad_norm": 0.3484567701816559,
      "learning_rate": 1.8763057487596965e-05,
      "loss": 0.6303,
      "step": 10502
    },
    {
      "epoch": 0.3226430743710257,
      "grad_norm": 0.40856701135635376,
      "learning_rate": 1.8762824655912558e-05,
      "loss": 0.6375,
      "step": 10503
    },
    {
      "epoch": 0.32267379350597486,
      "grad_norm": 0.32248178124427795,
      "learning_rate": 1.8762591803761955e-05,
      "loss": 0.538,
      "step": 10504
    },
    {
      "epoch": 0.32270451264092403,
      "grad_norm": 0.3276817500591278,
      "learning_rate": 1.876235893114571e-05,
      "loss": 0.5806,
      "step": 10505
    },
    {
      "epoch": 0.3227352317758732,
      "grad_norm": 0.33032435178756714,
      "learning_rate": 1.876212603806437e-05,
      "loss": 0.6151,
      "step": 10506
    },
    {
      "epoch": 0.32276595091082233,
      "grad_norm": 0.40004220604896545,
      "learning_rate": 1.8761893124518463e-05,
      "loss": 0.5492,
      "step": 10507
    },
    {
      "epoch": 0.3227966700457715,
      "grad_norm": 0.45349806547164917,
      "learning_rate": 1.876166019050855e-05,
      "loss": 0.6354,
      "step": 10508
    },
    {
      "epoch": 0.3228273891807207,
      "grad_norm": 0.3451940715312958,
      "learning_rate": 1.8761427236035167e-05,
      "loss": 0.6564,
      "step": 10509
    },
    {
      "epoch": 0.32285810831566986,
      "grad_norm": 0.3290732204914093,
      "learning_rate": 1.8761194261098854e-05,
      "loss": 0.5813,
      "step": 10510
    },
    {
      "epoch": 0.322888827450619,
      "grad_norm": 0.34436333179473877,
      "learning_rate": 1.8760961265700163e-05,
      "loss": 0.5666,
      "step": 10511
    },
    {
      "epoch": 0.32291954658556815,
      "grad_norm": 0.3301370441913605,
      "learning_rate": 1.8760728249839633e-05,
      "loss": 0.4631,
      "step": 10512
    },
    {
      "epoch": 0.3229502657205173,
      "grad_norm": 0.3396921157836914,
      "learning_rate": 1.8760495213517813e-05,
      "loss": 0.5426,
      "step": 10513
    },
    {
      "epoch": 0.32298098485546645,
      "grad_norm": 0.3267461359500885,
      "learning_rate": 1.8760262156735244e-05,
      "loss": 0.5881,
      "step": 10514
    },
    {
      "epoch": 0.3230117039904156,
      "grad_norm": 0.3818013072013855,
      "learning_rate": 1.876002907949247e-05,
      "loss": 0.5576,
      "step": 10515
    },
    {
      "epoch": 0.3230424231253648,
      "grad_norm": 0.34604912996292114,
      "learning_rate": 1.875979598179004e-05,
      "loss": 0.5429,
      "step": 10516
    },
    {
      "epoch": 0.323073142260314,
      "grad_norm": 0.3351454436779022,
      "learning_rate": 1.875956286362849e-05,
      "loss": 0.5782,
      "step": 10517
    },
    {
      "epoch": 0.3231038613952631,
      "grad_norm": 0.3306818902492523,
      "learning_rate": 1.875932972500837e-05,
      "loss": 0.5823,
      "step": 10518
    },
    {
      "epoch": 0.32313458053021227,
      "grad_norm": 0.47395914793014526,
      "learning_rate": 1.8759096565930224e-05,
      "loss": 0.5885,
      "step": 10519
    },
    {
      "epoch": 0.32316529966516144,
      "grad_norm": 0.3053765892982483,
      "learning_rate": 1.8758863386394597e-05,
      "loss": 0.5549,
      "step": 10520
    },
    {
      "epoch": 0.32319601880011056,
      "grad_norm": 0.33267444372177124,
      "learning_rate": 1.875863018640203e-05,
      "loss": 0.5991,
      "step": 10521
    },
    {
      "epoch": 0.32322673793505974,
      "grad_norm": 0.338569700717926,
      "learning_rate": 1.8758396965953075e-05,
      "loss": 0.5707,
      "step": 10522
    },
    {
      "epoch": 0.3232574570700089,
      "grad_norm": 0.4039997458457947,
      "learning_rate": 1.875816372504827e-05,
      "loss": 0.6456,
      "step": 10523
    },
    {
      "epoch": 0.3232881762049581,
      "grad_norm": 0.3354153335094452,
      "learning_rate": 1.8757930463688164e-05,
      "loss": 0.5035,
      "step": 10524
    },
    {
      "epoch": 0.3233188953399072,
      "grad_norm": 0.3468908965587616,
      "learning_rate": 1.87576971818733e-05,
      "loss": 0.47,
      "step": 10525
    },
    {
      "epoch": 0.3233496144748564,
      "grad_norm": 0.3235833942890167,
      "learning_rate": 1.8757463879604217e-05,
      "loss": 0.5702,
      "step": 10526
    },
    {
      "epoch": 0.32338033360980556,
      "grad_norm": 0.38212302327156067,
      "learning_rate": 1.8757230556881468e-05,
      "loss": 0.6359,
      "step": 10527
    },
    {
      "epoch": 0.32341105274475473,
      "grad_norm": 0.3509364724159241,
      "learning_rate": 1.8756997213705598e-05,
      "loss": 0.6209,
      "step": 10528
    },
    {
      "epoch": 0.32344177187970385,
      "grad_norm": 0.3443186581134796,
      "learning_rate": 1.8756763850077145e-05,
      "loss": 0.7022,
      "step": 10529
    },
    {
      "epoch": 0.32347249101465303,
      "grad_norm": 0.3335057497024536,
      "learning_rate": 1.8756530465996664e-05,
      "loss": 0.5631,
      "step": 10530
    },
    {
      "epoch": 0.3235032101496022,
      "grad_norm": 0.37644749879837036,
      "learning_rate": 1.8756297061464692e-05,
      "loss": 0.5655,
      "step": 10531
    },
    {
      "epoch": 0.3235339292845513,
      "grad_norm": 0.32338613271713257,
      "learning_rate": 1.8756063636481777e-05,
      "loss": 0.5391,
      "step": 10532
    },
    {
      "epoch": 0.3235646484195005,
      "grad_norm": 0.36534014344215393,
      "learning_rate": 1.8755830191048464e-05,
      "loss": 0.5661,
      "step": 10533
    },
    {
      "epoch": 0.3235953675544497,
      "grad_norm": 0.3516930639743805,
      "learning_rate": 1.8755596725165295e-05,
      "loss": 0.5392,
      "step": 10534
    },
    {
      "epoch": 0.32362608668939885,
      "grad_norm": 0.398168683052063,
      "learning_rate": 1.8755363238832824e-05,
      "loss": 0.5855,
      "step": 10535
    },
    {
      "epoch": 0.32365680582434797,
      "grad_norm": 0.3500240743160248,
      "learning_rate": 1.8755129732051584e-05,
      "loss": 0.5494,
      "step": 10536
    },
    {
      "epoch": 0.32368752495929715,
      "grad_norm": 0.3421843945980072,
      "learning_rate": 1.8754896204822133e-05,
      "loss": 0.5977,
      "step": 10537
    },
    {
      "epoch": 0.3237182440942463,
      "grad_norm": 0.379447340965271,
      "learning_rate": 1.8754662657145008e-05,
      "loss": 0.5889,
      "step": 10538
    },
    {
      "epoch": 0.32374896322919544,
      "grad_norm": 0.38925641775131226,
      "learning_rate": 1.8754429089020754e-05,
      "loss": 0.5777,
      "step": 10539
    },
    {
      "epoch": 0.3237796823641446,
      "grad_norm": 0.353607177734375,
      "learning_rate": 1.8754195500449925e-05,
      "loss": 0.6063,
      "step": 10540
    },
    {
      "epoch": 0.3238104014990938,
      "grad_norm": 0.3793995678424835,
      "learning_rate": 1.875396189143306e-05,
      "loss": 0.5756,
      "step": 10541
    },
    {
      "epoch": 0.32384112063404297,
      "grad_norm": 0.6309292912483215,
      "learning_rate": 1.8753728261970702e-05,
      "loss": 0.5096,
      "step": 10542
    },
    {
      "epoch": 0.3238718397689921,
      "grad_norm": 0.34683921933174133,
      "learning_rate": 1.8753494612063402e-05,
      "loss": 0.604,
      "step": 10543
    },
    {
      "epoch": 0.32390255890394126,
      "grad_norm": 0.32761454582214355,
      "learning_rate": 1.8753260941711708e-05,
      "loss": 0.6437,
      "step": 10544
    },
    {
      "epoch": 0.32393327803889044,
      "grad_norm": 0.3088163435459137,
      "learning_rate": 1.8753027250916155e-05,
      "loss": 0.6332,
      "step": 10545
    },
    {
      "epoch": 0.32396399717383956,
      "grad_norm": 0.34737327694892883,
      "learning_rate": 1.87527935396773e-05,
      "loss": 0.5567,
      "step": 10546
    },
    {
      "epoch": 0.32399471630878873,
      "grad_norm": 0.3143158257007599,
      "learning_rate": 1.8752559807995684e-05,
      "loss": 0.5326,
      "step": 10547
    },
    {
      "epoch": 0.3240254354437379,
      "grad_norm": 0.31621211767196655,
      "learning_rate": 1.8752326055871853e-05,
      "loss": 0.5847,
      "step": 10548
    },
    {
      "epoch": 0.3240561545786871,
      "grad_norm": 0.3131178915500641,
      "learning_rate": 1.8752092283306352e-05,
      "loss": 0.5048,
      "step": 10549
    },
    {
      "epoch": 0.3240868737136362,
      "grad_norm": 0.3822215497493744,
      "learning_rate": 1.8751858490299727e-05,
      "loss": 0.5454,
      "step": 10550
    },
    {
      "epoch": 0.3241175928485854,
      "grad_norm": 0.3671550452709198,
      "learning_rate": 1.875162467685253e-05,
      "loss": 0.5033,
      "step": 10551
    },
    {
      "epoch": 0.32414831198353455,
      "grad_norm": 0.38618919253349304,
      "learning_rate": 1.87513908429653e-05,
      "loss": 0.5985,
      "step": 10552
    },
    {
      "epoch": 0.32417903111848373,
      "grad_norm": 0.3504545986652374,
      "learning_rate": 1.8751156988638584e-05,
      "loss": 0.652,
      "step": 10553
    },
    {
      "epoch": 0.32420975025343285,
      "grad_norm": 0.37287670373916626,
      "learning_rate": 1.875092311387293e-05,
      "loss": 0.622,
      "step": 10554
    },
    {
      "epoch": 0.324240469388382,
      "grad_norm": 0.3176255226135254,
      "learning_rate": 1.8750689218668884e-05,
      "loss": 0.5808,
      "step": 10555
    },
    {
      "epoch": 0.3242711885233312,
      "grad_norm": 0.33974918723106384,
      "learning_rate": 1.8750455303026992e-05,
      "loss": 0.6002,
      "step": 10556
    },
    {
      "epoch": 0.3243019076582803,
      "grad_norm": 0.3801966905593872,
      "learning_rate": 1.87502213669478e-05,
      "loss": 0.6014,
      "step": 10557
    },
    {
      "epoch": 0.3243326267932295,
      "grad_norm": 0.4835933744907379,
      "learning_rate": 1.8749987410431857e-05,
      "loss": 0.49,
      "step": 10558
    },
    {
      "epoch": 0.32436334592817867,
      "grad_norm": 0.3491896688938141,
      "learning_rate": 1.8749753433479708e-05,
      "loss": 0.5353,
      "step": 10559
    },
    {
      "epoch": 0.32439406506312785,
      "grad_norm": 0.34013205766677856,
      "learning_rate": 1.87495194360919e-05,
      "loss": 0.5387,
      "step": 10560
    },
    {
      "epoch": 0.32442478419807697,
      "grad_norm": 0.33870619535446167,
      "learning_rate": 1.8749285418268975e-05,
      "loss": 0.5817,
      "step": 10561
    },
    {
      "epoch": 0.32445550333302614,
      "grad_norm": 0.337568074464798,
      "learning_rate": 1.874905138001148e-05,
      "loss": 0.6003,
      "step": 10562
    },
    {
      "epoch": 0.3244862224679753,
      "grad_norm": 0.3554910123348236,
      "learning_rate": 1.8748817321319972e-05,
      "loss": 0.5299,
      "step": 10563
    },
    {
      "epoch": 0.32451694160292444,
      "grad_norm": 0.4804076850414276,
      "learning_rate": 1.8748583242194986e-05,
      "loss": 0.6233,
      "step": 10564
    },
    {
      "epoch": 0.3245476607378736,
      "grad_norm": 0.395429402589798,
      "learning_rate": 1.874834914263707e-05,
      "loss": 0.5888,
      "step": 10565
    },
    {
      "epoch": 0.3245783798728228,
      "grad_norm": 0.3135973811149597,
      "learning_rate": 1.8748115022646776e-05,
      "loss": 0.5589,
      "step": 10566
    },
    {
      "epoch": 0.32460909900777196,
      "grad_norm": 0.34097617864608765,
      "learning_rate": 1.874788088222465e-05,
      "loss": 0.5962,
      "step": 10567
    },
    {
      "epoch": 0.3246398181427211,
      "grad_norm": 0.31954723596572876,
      "learning_rate": 1.8747646721371238e-05,
      "loss": 0.5776,
      "step": 10568
    },
    {
      "epoch": 0.32467053727767026,
      "grad_norm": 0.32285502552986145,
      "learning_rate": 1.8747412540087085e-05,
      "loss": 0.5916,
      "step": 10569
    },
    {
      "epoch": 0.32470125641261943,
      "grad_norm": 0.4999246299266815,
      "learning_rate": 1.8747178338372738e-05,
      "loss": 0.5855,
      "step": 10570
    },
    {
      "epoch": 0.3247319755475686,
      "grad_norm": 0.3397347927093506,
      "learning_rate": 1.8746944116228745e-05,
      "loss": 0.5719,
      "step": 10571
    },
    {
      "epoch": 0.3247626946825177,
      "grad_norm": 0.3430301249027252,
      "learning_rate": 1.8746709873655656e-05,
      "loss": 0.55,
      "step": 10572
    },
    {
      "epoch": 0.3247934138174669,
      "grad_norm": 0.36109620332717896,
      "learning_rate": 1.874647561065401e-05,
      "loss": 0.5967,
      "step": 10573
    },
    {
      "epoch": 0.3248241329524161,
      "grad_norm": 0.40350741147994995,
      "learning_rate": 1.874624132722436e-05,
      "loss": 0.5382,
      "step": 10574
    },
    {
      "epoch": 0.3248548520873652,
      "grad_norm": 0.3613792061805725,
      "learning_rate": 1.874600702336726e-05,
      "loss": 0.6162,
      "step": 10575
    },
    {
      "epoch": 0.3248855712223144,
      "grad_norm": 0.41203629970550537,
      "learning_rate": 1.8745772699083243e-05,
      "loss": 0.626,
      "step": 10576
    },
    {
      "epoch": 0.32491629035726355,
      "grad_norm": 0.6378921270370483,
      "learning_rate": 1.8745538354372862e-05,
      "loss": 0.6058,
      "step": 10577
    },
    {
      "epoch": 0.3249470094922127,
      "grad_norm": 0.36279022693634033,
      "learning_rate": 1.874530398923667e-05,
      "loss": 0.5939,
      "step": 10578
    },
    {
      "epoch": 0.32497772862716184,
      "grad_norm": 0.36846721172332764,
      "learning_rate": 1.874506960367521e-05,
      "loss": 0.6337,
      "step": 10579
    },
    {
      "epoch": 0.325008447762111,
      "grad_norm": 0.3302701711654663,
      "learning_rate": 1.8744835197689023e-05,
      "loss": 0.5302,
      "step": 10580
    },
    {
      "epoch": 0.3250391668970602,
      "grad_norm": 0.39234647154808044,
      "learning_rate": 1.874460077127867e-05,
      "loss": 0.6003,
      "step": 10581
    },
    {
      "epoch": 0.3250698860320093,
      "grad_norm": 0.3444295823574066,
      "learning_rate": 1.8744366324444688e-05,
      "loss": 0.5851,
      "step": 10582
    },
    {
      "epoch": 0.3251006051669585,
      "grad_norm": 0.3630450665950775,
      "learning_rate": 1.8744131857187626e-05,
      "loss": 0.5542,
      "step": 10583
    },
    {
      "epoch": 0.32513132430190766,
      "grad_norm": 0.32693299651145935,
      "learning_rate": 1.8743897369508034e-05,
      "loss": 0.6134,
      "step": 10584
    },
    {
      "epoch": 0.32516204343685684,
      "grad_norm": 0.34906721115112305,
      "learning_rate": 1.8743662861406464e-05,
      "loss": 0.5319,
      "step": 10585
    },
    {
      "epoch": 0.32519276257180596,
      "grad_norm": 0.5232595205307007,
      "learning_rate": 1.8743428332883454e-05,
      "loss": 0.5143,
      "step": 10586
    },
    {
      "epoch": 0.32522348170675514,
      "grad_norm": 0.3465864062309265,
      "learning_rate": 1.8743193783939558e-05,
      "loss": 0.553,
      "step": 10587
    },
    {
      "epoch": 0.3252542008417043,
      "grad_norm": 0.38344210386276245,
      "learning_rate": 1.8742959214575317e-05,
      "loss": 0.6173,
      "step": 10588
    },
    {
      "epoch": 0.32528491997665343,
      "grad_norm": 0.3510704040527344,
      "learning_rate": 1.874272462479129e-05,
      "loss": 0.562,
      "step": 10589
    },
    {
      "epoch": 0.3253156391116026,
      "grad_norm": 0.33947932720184326,
      "learning_rate": 1.874249001458802e-05,
      "loss": 0.6487,
      "step": 10590
    },
    {
      "epoch": 0.3253463582465518,
      "grad_norm": 0.3177601099014282,
      "learning_rate": 1.874225538396605e-05,
      "loss": 0.6862,
      "step": 10591
    },
    {
      "epoch": 0.32537707738150096,
      "grad_norm": 0.38161271810531616,
      "learning_rate": 1.8742020732925933e-05,
      "loss": 0.5578,
      "step": 10592
    },
    {
      "epoch": 0.3254077965164501,
      "grad_norm": 0.34065550565719604,
      "learning_rate": 1.8741786061468218e-05,
      "loss": 0.5831,
      "step": 10593
    },
    {
      "epoch": 0.32543851565139925,
      "grad_norm": 0.3902231454849243,
      "learning_rate": 1.8741551369593448e-05,
      "loss": 0.6531,
      "step": 10594
    },
    {
      "epoch": 0.3254692347863484,
      "grad_norm": 0.4177478551864624,
      "learning_rate": 1.874131665730218e-05,
      "loss": 0.6114,
      "step": 10595
    },
    {
      "epoch": 0.3254999539212976,
      "grad_norm": 0.3598543405532837,
      "learning_rate": 1.8741081924594952e-05,
      "loss": 0.5709,
      "step": 10596
    },
    {
      "epoch": 0.3255306730562467,
      "grad_norm": 0.3625763952732086,
      "learning_rate": 1.8740847171472317e-05,
      "loss": 0.6235,
      "step": 10597
    },
    {
      "epoch": 0.3255613921911959,
      "grad_norm": 0.34656277298927307,
      "learning_rate": 1.8740612397934823e-05,
      "loss": 0.5941,
      "step": 10598
    },
    {
      "epoch": 0.3255921113261451,
      "grad_norm": 0.33417102694511414,
      "learning_rate": 1.8740377603983018e-05,
      "loss": 0.5924,
      "step": 10599
    },
    {
      "epoch": 0.3256228304610942,
      "grad_norm": 0.36694541573524475,
      "learning_rate": 1.874014278961745e-05,
      "loss": 0.6747,
      "step": 10600
    },
    {
      "epoch": 0.32565354959604337,
      "grad_norm": 0.3144792318344116,
      "learning_rate": 1.8739907954838668e-05,
      "loss": 0.5609,
      "step": 10601
    },
    {
      "epoch": 0.32568426873099254,
      "grad_norm": 0.33663344383239746,
      "learning_rate": 1.8739673099647225e-05,
      "loss": 0.5639,
      "step": 10602
    },
    {
      "epoch": 0.3257149878659417,
      "grad_norm": 0.3847487270832062,
      "learning_rate": 1.8739438224043663e-05,
      "loss": 0.549,
      "step": 10603
    },
    {
      "epoch": 0.32574570700089084,
      "grad_norm": 0.36885571479797363,
      "learning_rate": 1.8739203328028532e-05,
      "loss": 0.6118,
      "step": 10604
    },
    {
      "epoch": 0.32577642613584,
      "grad_norm": 0.357280969619751,
      "learning_rate": 1.873896841160238e-05,
      "loss": 0.544,
      "step": 10605
    },
    {
      "epoch": 0.3258071452707892,
      "grad_norm": 0.3556792438030243,
      "learning_rate": 1.873873347476576e-05,
      "loss": 0.5867,
      "step": 10606
    },
    {
      "epoch": 0.3258378644057383,
      "grad_norm": 0.3673684597015381,
      "learning_rate": 1.8738498517519216e-05,
      "loss": 0.6115,
      "step": 10607
    },
    {
      "epoch": 0.3258685835406875,
      "grad_norm": 0.3714742362499237,
      "learning_rate": 1.87382635398633e-05,
      "loss": 0.6725,
      "step": 10608
    },
    {
      "epoch": 0.32589930267563666,
      "grad_norm": 0.34037017822265625,
      "learning_rate": 1.8738028541798556e-05,
      "loss": 0.6613,
      "step": 10609
    },
    {
      "epoch": 0.32593002181058583,
      "grad_norm": 0.3501949906349182,
      "learning_rate": 1.8737793523325533e-05,
      "loss": 0.592,
      "step": 10610
    },
    {
      "epoch": 0.32596074094553495,
      "grad_norm": 0.37736231088638306,
      "learning_rate": 1.873755848444479e-05,
      "loss": 0.6664,
      "step": 10611
    },
    {
      "epoch": 0.32599146008048413,
      "grad_norm": 0.4172481894493103,
      "learning_rate": 1.8737323425156865e-05,
      "loss": 0.6545,
      "step": 10612
    },
    {
      "epoch": 0.3260221792154333,
      "grad_norm": 0.34072646498680115,
      "learning_rate": 1.8737088345462314e-05,
      "loss": 0.6501,
      "step": 10613
    },
    {
      "epoch": 0.3260528983503825,
      "grad_norm": 0.35689839720726013,
      "learning_rate": 1.8736853245361682e-05,
      "loss": 0.6019,
      "step": 10614
    },
    {
      "epoch": 0.3260836174853316,
      "grad_norm": 0.36337536573410034,
      "learning_rate": 1.8736618124855518e-05,
      "loss": 0.4636,
      "step": 10615
    },
    {
      "epoch": 0.3261143366202808,
      "grad_norm": 0.3420611619949341,
      "learning_rate": 1.873638298394437e-05,
      "loss": 0.5215,
      "step": 10616
    },
    {
      "epoch": 0.32614505575522995,
      "grad_norm": 0.37100815773010254,
      "learning_rate": 1.8736147822628793e-05,
      "loss": 0.5276,
      "step": 10617
    },
    {
      "epoch": 0.32617577489017907,
      "grad_norm": 0.38689830899238586,
      "learning_rate": 1.873591264090933e-05,
      "loss": 0.616,
      "step": 10618
    },
    {
      "epoch": 0.32620649402512825,
      "grad_norm": 0.40596750378608704,
      "learning_rate": 1.8735677438786538e-05,
      "loss": 0.5844,
      "step": 10619
    },
    {
      "epoch": 0.3262372131600774,
      "grad_norm": 0.3629716634750366,
      "learning_rate": 1.8735442216260957e-05,
      "loss": 0.5409,
      "step": 10620
    },
    {
      "epoch": 0.3262679322950266,
      "grad_norm": 0.3378835618495941,
      "learning_rate": 1.873520697333314e-05,
      "loss": 0.6169,
      "step": 10621
    },
    {
      "epoch": 0.3262986514299757,
      "grad_norm": 0.3328899145126343,
      "learning_rate": 1.873497171000364e-05,
      "loss": 0.5753,
      "step": 10622
    },
    {
      "epoch": 0.3263293705649249,
      "grad_norm": 0.3297642469406128,
      "learning_rate": 1.8734736426273e-05,
      "loss": 0.6285,
      "step": 10623
    },
    {
      "epoch": 0.32636008969987407,
      "grad_norm": 0.41585639119148254,
      "learning_rate": 1.8734501122141776e-05,
      "loss": 0.6763,
      "step": 10624
    },
    {
      "epoch": 0.3263908088348232,
      "grad_norm": 0.36052653193473816,
      "learning_rate": 1.8734265797610515e-05,
      "loss": 0.6174,
      "step": 10625
    },
    {
      "epoch": 0.32642152796977236,
      "grad_norm": 0.33579128980636597,
      "learning_rate": 1.8734030452679763e-05,
      "loss": 0.6374,
      "step": 10626
    },
    {
      "epoch": 0.32645224710472154,
      "grad_norm": 0.47292041778564453,
      "learning_rate": 1.8733795087350076e-05,
      "loss": 0.5936,
      "step": 10627
    },
    {
      "epoch": 0.3264829662396707,
      "grad_norm": 0.34830424189567566,
      "learning_rate": 1.8733559701622e-05,
      "loss": 0.5874,
      "step": 10628
    },
    {
      "epoch": 0.32651368537461983,
      "grad_norm": 0.3463381826877594,
      "learning_rate": 1.8733324295496085e-05,
      "loss": 0.6374,
      "step": 10629
    },
    {
      "epoch": 0.326544404509569,
      "grad_norm": 0.3429344594478607,
      "learning_rate": 1.873308886897288e-05,
      "loss": 0.5277,
      "step": 10630
    },
    {
      "epoch": 0.3265751236445182,
      "grad_norm": 0.37598368525505066,
      "learning_rate": 1.8732853422052936e-05,
      "loss": 0.5292,
      "step": 10631
    },
    {
      "epoch": 0.3266058427794673,
      "grad_norm": 0.34578216075897217,
      "learning_rate": 1.8732617954736806e-05,
      "loss": 0.5905,
      "step": 10632
    },
    {
      "epoch": 0.3266365619144165,
      "grad_norm": 0.32971879839897156,
      "learning_rate": 1.8732382467025034e-05,
      "loss": 0.5383,
      "step": 10633
    },
    {
      "epoch": 0.32666728104936565,
      "grad_norm": 0.3679504990577698,
      "learning_rate": 1.8732146958918175e-05,
      "loss": 0.6421,
      "step": 10634
    },
    {
      "epoch": 0.32669800018431483,
      "grad_norm": 0.39869388937950134,
      "learning_rate": 1.8731911430416776e-05,
      "loss": 0.5585,
      "step": 10635
    },
    {
      "epoch": 0.32672871931926395,
      "grad_norm": 0.3706117570400238,
      "learning_rate": 1.8731675881521385e-05,
      "loss": 0.5164,
      "step": 10636
    },
    {
      "epoch": 0.3267594384542131,
      "grad_norm": 0.366694837808609,
      "learning_rate": 1.8731440312232558e-05,
      "loss": 0.6436,
      "step": 10637
    },
    {
      "epoch": 0.3267901575891623,
      "grad_norm": 0.342157244682312,
      "learning_rate": 1.8731204722550843e-05,
      "loss": 0.562,
      "step": 10638
    },
    {
      "epoch": 0.3268208767241115,
      "grad_norm": 0.5613229870796204,
      "learning_rate": 1.873096911247679e-05,
      "loss": 0.5865,
      "step": 10639
    },
    {
      "epoch": 0.3268515958590606,
      "grad_norm": 0.3509702682495117,
      "learning_rate": 1.8730733482010946e-05,
      "loss": 0.6017,
      "step": 10640
    },
    {
      "epoch": 0.32688231499400977,
      "grad_norm": 0.3775944411754608,
      "learning_rate": 1.8730497831153866e-05,
      "loss": 0.5659,
      "step": 10641
    },
    {
      "epoch": 0.32691303412895895,
      "grad_norm": 0.4076125919818878,
      "learning_rate": 1.8730262159906097e-05,
      "loss": 0.5946,
      "step": 10642
    },
    {
      "epoch": 0.32694375326390807,
      "grad_norm": 0.3452241122722626,
      "learning_rate": 1.8730026468268195e-05,
      "loss": 0.5869,
      "step": 10643
    },
    {
      "epoch": 0.32697447239885724,
      "grad_norm": 0.33952343463897705,
      "learning_rate": 1.8729790756240703e-05,
      "loss": 0.6203,
      "step": 10644
    },
    {
      "epoch": 0.3270051915338064,
      "grad_norm": 0.36473217606544495,
      "learning_rate": 1.8729555023824175e-05,
      "loss": 0.571,
      "step": 10645
    },
    {
      "epoch": 0.3270359106687556,
      "grad_norm": 0.34806913137435913,
      "learning_rate": 1.872931927101916e-05,
      "loss": 0.6055,
      "step": 10646
    },
    {
      "epoch": 0.3270666298037047,
      "grad_norm": 0.3367176055908203,
      "learning_rate": 1.8729083497826213e-05,
      "loss": 0.6254,
      "step": 10647
    },
    {
      "epoch": 0.3270973489386539,
      "grad_norm": 0.3585708737373352,
      "learning_rate": 1.8728847704245884e-05,
      "loss": 0.6614,
      "step": 10648
    },
    {
      "epoch": 0.32712806807360306,
      "grad_norm": 0.3506544828414917,
      "learning_rate": 1.872861189027872e-05,
      "loss": 0.5887,
      "step": 10649
    },
    {
      "epoch": 0.3271587872085522,
      "grad_norm": 0.33110272884368896,
      "learning_rate": 1.8728376055925272e-05,
      "loss": 0.5391,
      "step": 10650
    },
    {
      "epoch": 0.32718950634350136,
      "grad_norm": 0.37524256110191345,
      "learning_rate": 1.8728140201186094e-05,
      "loss": 0.5168,
      "step": 10651
    },
    {
      "epoch": 0.32722022547845053,
      "grad_norm": 0.34931573271751404,
      "learning_rate": 1.8727904326061733e-05,
      "loss": 0.5146,
      "step": 10652
    },
    {
      "epoch": 0.3272509446133997,
      "grad_norm": 0.3322073817253113,
      "learning_rate": 1.8727668430552742e-05,
      "loss": 0.535,
      "step": 10653
    },
    {
      "epoch": 0.32728166374834883,
      "grad_norm": 0.36246514320373535,
      "learning_rate": 1.8727432514659672e-05,
      "loss": 0.5498,
      "step": 10654
    },
    {
      "epoch": 0.327312382883298,
      "grad_norm": 0.3730427920818329,
      "learning_rate": 1.8727196578383077e-05,
      "loss": 0.6042,
      "step": 10655
    },
    {
      "epoch": 0.3273431020182472,
      "grad_norm": 0.3390539884567261,
      "learning_rate": 1.87269606217235e-05,
      "loss": 0.5829,
      "step": 10656
    },
    {
      "epoch": 0.3273738211531963,
      "grad_norm": 0.37792879343032837,
      "learning_rate": 1.87267246446815e-05,
      "loss": 0.5645,
      "step": 10657
    },
    {
      "epoch": 0.3274045402881455,
      "grad_norm": 0.3017767369747162,
      "learning_rate": 1.8726488647257623e-05,
      "loss": 0.5857,
      "step": 10658
    },
    {
      "epoch": 0.32743525942309465,
      "grad_norm": 0.37412741780281067,
      "learning_rate": 1.8726252629452425e-05,
      "loss": 0.5453,
      "step": 10659
    },
    {
      "epoch": 0.3274659785580438,
      "grad_norm": 0.32777178287506104,
      "learning_rate": 1.872601659126645e-05,
      "loss": 0.5971,
      "step": 10660
    },
    {
      "epoch": 0.32749669769299294,
      "grad_norm": 0.40001529455184937,
      "learning_rate": 1.872578053270026e-05,
      "loss": 0.5927,
      "step": 10661
    },
    {
      "epoch": 0.3275274168279421,
      "grad_norm": 0.4078710675239563,
      "learning_rate": 1.8725544453754394e-05,
      "loss": 0.6445,
      "step": 10662
    },
    {
      "epoch": 0.3275581359628913,
      "grad_norm": 0.313996821641922,
      "learning_rate": 1.8725308354429414e-05,
      "loss": 0.5882,
      "step": 10663
    },
    {
      "epoch": 0.32758885509784047,
      "grad_norm": 0.3578588664531708,
      "learning_rate": 1.8725072234725865e-05,
      "loss": 0.5398,
      "step": 10664
    },
    {
      "epoch": 0.3276195742327896,
      "grad_norm": 0.36366888880729675,
      "learning_rate": 1.87248360946443e-05,
      "loss": 0.5992,
      "step": 10665
    },
    {
      "epoch": 0.32765029336773877,
      "grad_norm": 0.3819820284843445,
      "learning_rate": 1.8724599934185273e-05,
      "loss": 0.5472,
      "step": 10666
    },
    {
      "epoch": 0.32768101250268794,
      "grad_norm": 0.3554011583328247,
      "learning_rate": 1.8724363753349333e-05,
      "loss": 0.6054,
      "step": 10667
    },
    {
      "epoch": 0.32771173163763706,
      "grad_norm": 0.37807202339172363,
      "learning_rate": 1.872412755213703e-05,
      "loss": 0.5691,
      "step": 10668
    },
    {
      "epoch": 0.32774245077258624,
      "grad_norm": 0.4579107165336609,
      "learning_rate": 1.8723891330548923e-05,
      "loss": 0.5653,
      "step": 10669
    },
    {
      "epoch": 0.3277731699075354,
      "grad_norm": 0.36247122287750244,
      "learning_rate": 1.8723655088585554e-05,
      "loss": 0.5806,
      "step": 10670
    },
    {
      "epoch": 0.3278038890424846,
      "grad_norm": 0.42966148257255554,
      "learning_rate": 1.872341882624748e-05,
      "loss": 0.5778,
      "step": 10671
    },
    {
      "epoch": 0.3278346081774337,
      "grad_norm": 0.38631224632263184,
      "learning_rate": 1.8723182543535253e-05,
      "loss": 0.5904,
      "step": 10672
    },
    {
      "epoch": 0.3278653273123829,
      "grad_norm": 0.37173765897750854,
      "learning_rate": 1.8722946240449424e-05,
      "loss": 0.6373,
      "step": 10673
    },
    {
      "epoch": 0.32789604644733206,
      "grad_norm": 0.3452288806438446,
      "learning_rate": 1.872270991699054e-05,
      "loss": 0.549,
      "step": 10674
    },
    {
      "epoch": 0.3279267655822812,
      "grad_norm": 0.31921160221099854,
      "learning_rate": 1.8722473573159164e-05,
      "loss": 0.5176,
      "step": 10675
    },
    {
      "epoch": 0.32795748471723035,
      "grad_norm": 0.3393431305885315,
      "learning_rate": 1.872223720895584e-05,
      "loss": 0.5412,
      "step": 10676
    },
    {
      "epoch": 0.3279882038521795,
      "grad_norm": 0.33237138390541077,
      "learning_rate": 1.8722000824381123e-05,
      "loss": 0.5639,
      "step": 10677
    },
    {
      "epoch": 0.3280189229871287,
      "grad_norm": 0.38065606355667114,
      "learning_rate": 1.8721764419435563e-05,
      "loss": 0.683,
      "step": 10678
    },
    {
      "epoch": 0.3280496421220778,
      "grad_norm": 0.3393557667732239,
      "learning_rate": 1.872152799411971e-05,
      "loss": 0.5159,
      "step": 10679
    },
    {
      "epoch": 0.328080361257027,
      "grad_norm": 0.34869417548179626,
      "learning_rate": 1.8721291548434123e-05,
      "loss": 0.53,
      "step": 10680
    },
    {
      "epoch": 0.3281110803919762,
      "grad_norm": 0.3947012424468994,
      "learning_rate": 1.8721055082379348e-05,
      "loss": 0.6059,
      "step": 10681
    },
    {
      "epoch": 0.32814179952692535,
      "grad_norm": 0.3635810613632202,
      "learning_rate": 1.8720818595955944e-05,
      "loss": 0.5273,
      "step": 10682
    },
    {
      "epoch": 0.32817251866187447,
      "grad_norm": 0.3817093074321747,
      "learning_rate": 1.8720582089164457e-05,
      "loss": 0.5959,
      "step": 10683
    },
    {
      "epoch": 0.32820323779682364,
      "grad_norm": 0.33807286620140076,
      "learning_rate": 1.8720345562005436e-05,
      "loss": 0.5521,
      "step": 10684
    },
    {
      "epoch": 0.3282339569317728,
      "grad_norm": 0.3850533962249756,
      "learning_rate": 1.8720109014479447e-05,
      "loss": 0.5615,
      "step": 10685
    },
    {
      "epoch": 0.32826467606672194,
      "grad_norm": 0.35778698325157166,
      "learning_rate": 1.8719872446587032e-05,
      "loss": 0.6171,
      "step": 10686
    },
    {
      "epoch": 0.3282953952016711,
      "grad_norm": 0.43501678109169006,
      "learning_rate": 1.8719635858328743e-05,
      "loss": 0.5335,
      "step": 10687
    },
    {
      "epoch": 0.3283261143366203,
      "grad_norm": 0.3563230633735657,
      "learning_rate": 1.871939924970514e-05,
      "loss": 0.5446,
      "step": 10688
    },
    {
      "epoch": 0.32835683347156946,
      "grad_norm": 0.35284650325775146,
      "learning_rate": 1.8719162620716767e-05,
      "loss": 0.6584,
      "step": 10689
    },
    {
      "epoch": 0.3283875526065186,
      "grad_norm": 0.40835055708885193,
      "learning_rate": 1.871892597136418e-05,
      "loss": 0.6342,
      "step": 10690
    },
    {
      "epoch": 0.32841827174146776,
      "grad_norm": 0.3492220342159271,
      "learning_rate": 1.8718689301647935e-05,
      "loss": 0.5332,
      "step": 10691
    },
    {
      "epoch": 0.32844899087641694,
      "grad_norm": 0.4193934202194214,
      "learning_rate": 1.8718452611568585e-05,
      "loss": 0.6797,
      "step": 10692
    },
    {
      "epoch": 0.32847971001136606,
      "grad_norm": 0.3828330934047699,
      "learning_rate": 1.8718215901126674e-05,
      "loss": 0.5424,
      "step": 10693
    },
    {
      "epoch": 0.32851042914631523,
      "grad_norm": 0.3417256474494934,
      "learning_rate": 1.8717979170322766e-05,
      "loss": 0.5488,
      "step": 10694
    },
    {
      "epoch": 0.3285411482812644,
      "grad_norm": 0.41494297981262207,
      "learning_rate": 1.871774241915741e-05,
      "loss": 0.5957,
      "step": 10695
    },
    {
      "epoch": 0.3285718674162136,
      "grad_norm": 0.3286798894405365,
      "learning_rate": 1.871750564763115e-05,
      "loss": 0.5808,
      "step": 10696
    },
    {
      "epoch": 0.3286025865511627,
      "grad_norm": 0.3678062856197357,
      "learning_rate": 1.8717268855744553e-05,
      "loss": 0.5898,
      "step": 10697
    },
    {
      "epoch": 0.3286333056861119,
      "grad_norm": 0.36581316590309143,
      "learning_rate": 1.8717032043498165e-05,
      "loss": 0.5828,
      "step": 10698
    },
    {
      "epoch": 0.32866402482106105,
      "grad_norm": 0.34290972352027893,
      "learning_rate": 1.871679521089254e-05,
      "loss": 0.6835,
      "step": 10699
    },
    {
      "epoch": 0.32869474395601017,
      "grad_norm": 0.3774523437023163,
      "learning_rate": 1.8716558357928227e-05,
      "loss": 0.5638,
      "step": 10700
    },
    {
      "epoch": 0.32872546309095935,
      "grad_norm": 0.3280346691608429,
      "learning_rate": 1.8716321484605787e-05,
      "loss": 0.5972,
      "step": 10701
    },
    {
      "epoch": 0.3287561822259085,
      "grad_norm": 0.3625257611274719,
      "learning_rate": 1.8716084590925768e-05,
      "loss": 0.5455,
      "step": 10702
    },
    {
      "epoch": 0.3287869013608577,
      "grad_norm": 0.35756370425224304,
      "learning_rate": 1.8715847676888724e-05,
      "loss": 0.5806,
      "step": 10703
    },
    {
      "epoch": 0.3288176204958068,
      "grad_norm": 0.33832335472106934,
      "learning_rate": 1.8715610742495212e-05,
      "loss": 0.5511,
      "step": 10704
    },
    {
      "epoch": 0.328848339630756,
      "grad_norm": 0.3505648076534271,
      "learning_rate": 1.871537378774578e-05,
      "loss": 0.5068,
      "step": 10705
    },
    {
      "epoch": 0.32887905876570517,
      "grad_norm": 0.47498634457588196,
      "learning_rate": 1.8715136812640985e-05,
      "loss": 0.7084,
      "step": 10706
    },
    {
      "epoch": 0.32890977790065434,
      "grad_norm": 0.39254215359687805,
      "learning_rate": 1.871489981718138e-05,
      "loss": 0.6062,
      "step": 10707
    },
    {
      "epoch": 0.32894049703560346,
      "grad_norm": 0.35227489471435547,
      "learning_rate": 1.8714662801367516e-05,
      "loss": 0.5666,
      "step": 10708
    },
    {
      "epoch": 0.32897121617055264,
      "grad_norm": 0.35651397705078125,
      "learning_rate": 1.871442576519995e-05,
      "loss": 0.5654,
      "step": 10709
    },
    {
      "epoch": 0.3290019353055018,
      "grad_norm": 0.34810325503349304,
      "learning_rate": 1.871418870867923e-05,
      "loss": 0.4831,
      "step": 10710
    },
    {
      "epoch": 0.32903265444045093,
      "grad_norm": 0.35779282450675964,
      "learning_rate": 1.871395163180592e-05,
      "loss": 0.6215,
      "step": 10711
    },
    {
      "epoch": 0.3290633735754001,
      "grad_norm": 0.3724839985370636,
      "learning_rate": 1.8713714534580564e-05,
      "loss": 0.6107,
      "step": 10712
    },
    {
      "epoch": 0.3290940927103493,
      "grad_norm": 0.3303056061267853,
      "learning_rate": 1.871347741700372e-05,
      "loss": 0.5437,
      "step": 10713
    },
    {
      "epoch": 0.32912481184529846,
      "grad_norm": 0.4173175096511841,
      "learning_rate": 1.8713240279075938e-05,
      "loss": 0.5628,
      "step": 10714
    },
    {
      "epoch": 0.3291555309802476,
      "grad_norm": 0.3347472548484802,
      "learning_rate": 1.8713003120797778e-05,
      "loss": 0.5944,
      "step": 10715
    },
    {
      "epoch": 0.32918625011519675,
      "grad_norm": 0.3835369646549225,
      "learning_rate": 1.871276594216979e-05,
      "loss": 0.5688,
      "step": 10716
    },
    {
      "epoch": 0.32921696925014593,
      "grad_norm": 0.3942273259162903,
      "learning_rate": 1.871252874319253e-05,
      "loss": 0.6437,
      "step": 10717
    },
    {
      "epoch": 0.32924768838509505,
      "grad_norm": 0.3356528878211975,
      "learning_rate": 1.8712291523866546e-05,
      "loss": 0.594,
      "step": 10718
    },
    {
      "epoch": 0.3292784075200442,
      "grad_norm": 0.33523091673851013,
      "learning_rate": 1.87120542841924e-05,
      "loss": 0.4623,
      "step": 10719
    },
    {
      "epoch": 0.3293091266549934,
      "grad_norm": 0.3324328362941742,
      "learning_rate": 1.8711817024170643e-05,
      "loss": 0.5786,
      "step": 10720
    },
    {
      "epoch": 0.3293398457899426,
      "grad_norm": 0.3859851658344269,
      "learning_rate": 1.8711579743801828e-05,
      "loss": 0.5877,
      "step": 10721
    },
    {
      "epoch": 0.3293705649248917,
      "grad_norm": 0.3619343340396881,
      "learning_rate": 1.8711342443086512e-05,
      "loss": 0.6209,
      "step": 10722
    },
    {
      "epoch": 0.32940128405984087,
      "grad_norm": 0.3476257622241974,
      "learning_rate": 1.8711105122025245e-05,
      "loss": 0.5586,
      "step": 10723
    },
    {
      "epoch": 0.32943200319479005,
      "grad_norm": 0.350563645362854,
      "learning_rate": 1.8710867780618585e-05,
      "loss": 0.6027,
      "step": 10724
    },
    {
      "epoch": 0.3294627223297392,
      "grad_norm": 0.3395825922489166,
      "learning_rate": 1.8710630418867085e-05,
      "loss": 0.5832,
      "step": 10725
    },
    {
      "epoch": 0.32949344146468834,
      "grad_norm": 0.3227066993713379,
      "learning_rate": 1.87103930367713e-05,
      "loss": 0.5983,
      "step": 10726
    },
    {
      "epoch": 0.3295241605996375,
      "grad_norm": 0.46847808361053467,
      "learning_rate": 1.871015563433178e-05,
      "loss": 0.5409,
      "step": 10727
    },
    {
      "epoch": 0.3295548797345867,
      "grad_norm": 0.33713844418525696,
      "learning_rate": 1.870991821154909e-05,
      "loss": 0.6004,
      "step": 10728
    },
    {
      "epoch": 0.3295855988695358,
      "grad_norm": 0.29889196157455444,
      "learning_rate": 1.870968076842377e-05,
      "loss": 0.5445,
      "step": 10729
    },
    {
      "epoch": 0.329616318004485,
      "grad_norm": 0.3569268584251404,
      "learning_rate": 1.8709443304956386e-05,
      "loss": 0.5388,
      "step": 10730
    },
    {
      "epoch": 0.32964703713943416,
      "grad_norm": 0.4334929883480072,
      "learning_rate": 1.870920582114749e-05,
      "loss": 0.6189,
      "step": 10731
    },
    {
      "epoch": 0.32967775627438334,
      "grad_norm": 0.34755197167396545,
      "learning_rate": 1.870896831699763e-05,
      "loss": 0.5075,
      "step": 10732
    },
    {
      "epoch": 0.32970847540933246,
      "grad_norm": 0.4003734588623047,
      "learning_rate": 1.870873079250737e-05,
      "loss": 0.5331,
      "step": 10733
    },
    {
      "epoch": 0.32973919454428163,
      "grad_norm": 0.3313238024711609,
      "learning_rate": 1.8708493247677265e-05,
      "loss": 0.5068,
      "step": 10734
    },
    {
      "epoch": 0.3297699136792308,
      "grad_norm": 0.3736873269081116,
      "learning_rate": 1.870825568250786e-05,
      "loss": 0.5512,
      "step": 10735
    },
    {
      "epoch": 0.32980063281417993,
      "grad_norm": 0.30627554655075073,
      "learning_rate": 1.870801809699972e-05,
      "loss": 0.4557,
      "step": 10736
    },
    {
      "epoch": 0.3298313519491291,
      "grad_norm": 0.3260178565979004,
      "learning_rate": 1.8707780491153392e-05,
      "loss": 0.5973,
      "step": 10737
    },
    {
      "epoch": 0.3298620710840783,
      "grad_norm": 0.35606032609939575,
      "learning_rate": 1.8707542864969437e-05,
      "loss": 0.493,
      "step": 10738
    },
    {
      "epoch": 0.32989279021902745,
      "grad_norm": 0.36151257157325745,
      "learning_rate": 1.8707305218448405e-05,
      "loss": 0.5949,
      "step": 10739
    },
    {
      "epoch": 0.3299235093539766,
      "grad_norm": 0.3384949266910553,
      "learning_rate": 1.870706755159086e-05,
      "loss": 0.6118,
      "step": 10740
    },
    {
      "epoch": 0.32995422848892575,
      "grad_norm": 0.4093090295791626,
      "learning_rate": 1.870682986439734e-05,
      "loss": 0.6238,
      "step": 10741
    },
    {
      "epoch": 0.3299849476238749,
      "grad_norm": 0.3672820031642914,
      "learning_rate": 1.870659215686842e-05,
      "loss": 0.6648,
      "step": 10742
    },
    {
      "epoch": 0.33001566675882404,
      "grad_norm": 0.35856547951698303,
      "learning_rate": 1.870635442900464e-05,
      "loss": 0.61,
      "step": 10743
    },
    {
      "epoch": 0.3300463858937732,
      "grad_norm": 0.44638675451278687,
      "learning_rate": 1.8706116680806564e-05,
      "loss": 0.5886,
      "step": 10744
    },
    {
      "epoch": 0.3300771050287224,
      "grad_norm": 0.3471231460571289,
      "learning_rate": 1.8705878912274745e-05,
      "loss": 0.583,
      "step": 10745
    },
    {
      "epoch": 0.33010782416367157,
      "grad_norm": 0.36316269636154175,
      "learning_rate": 1.8705641123409737e-05,
      "loss": 0.6077,
      "step": 10746
    },
    {
      "epoch": 0.3301385432986207,
      "grad_norm": 0.3631818890571594,
      "learning_rate": 1.8705403314212097e-05,
      "loss": 0.5559,
      "step": 10747
    },
    {
      "epoch": 0.33016926243356987,
      "grad_norm": 0.3552229404449463,
      "learning_rate": 1.870516548468238e-05,
      "loss": 0.5778,
      "step": 10748
    },
    {
      "epoch": 0.33019998156851904,
      "grad_norm": 0.3626943528652191,
      "learning_rate": 1.8704927634821136e-05,
      "loss": 0.5475,
      "step": 10749
    },
    {
      "epoch": 0.3302307007034682,
      "grad_norm": 0.5007736682891846,
      "learning_rate": 1.870468976462893e-05,
      "loss": 0.5597,
      "step": 10750
    },
    {
      "epoch": 0.33026141983841734,
      "grad_norm": 0.3488624393939972,
      "learning_rate": 1.8704451874106312e-05,
      "loss": 0.6162,
      "step": 10751
    },
    {
      "epoch": 0.3302921389733665,
      "grad_norm": 0.3394465446472168,
      "learning_rate": 1.8704213963253842e-05,
      "loss": 0.549,
      "step": 10752
    },
    {
      "epoch": 0.3303228581083157,
      "grad_norm": 0.3779711425304413,
      "learning_rate": 1.870397603207207e-05,
      "loss": 0.537,
      "step": 10753
    },
    {
      "epoch": 0.3303535772432648,
      "grad_norm": 0.3807176649570465,
      "learning_rate": 1.8703738080561553e-05,
      "loss": 0.5852,
      "step": 10754
    },
    {
      "epoch": 0.330384296378214,
      "grad_norm": 0.43642377853393555,
      "learning_rate": 1.8703500108722847e-05,
      "loss": 0.5486,
      "step": 10755
    },
    {
      "epoch": 0.33041501551316316,
      "grad_norm": 0.3626044988632202,
      "learning_rate": 1.870326211655651e-05,
      "loss": 0.5495,
      "step": 10756
    },
    {
      "epoch": 0.33044573464811233,
      "grad_norm": 0.6367958784103394,
      "learning_rate": 1.8703024104063096e-05,
      "loss": 0.6783,
      "step": 10757
    },
    {
      "epoch": 0.33047645378306145,
      "grad_norm": 0.38847169280052185,
      "learning_rate": 1.8702786071243164e-05,
      "loss": 0.5973,
      "step": 10758
    },
    {
      "epoch": 0.3305071729180106,
      "grad_norm": 0.34670236706733704,
      "learning_rate": 1.8702548018097263e-05,
      "loss": 0.6137,
      "step": 10759
    },
    {
      "epoch": 0.3305378920529598,
      "grad_norm": 0.3769471049308777,
      "learning_rate": 1.870230994462596e-05,
      "loss": 0.5496,
      "step": 10760
    },
    {
      "epoch": 0.3305686111879089,
      "grad_norm": 0.3451610207557678,
      "learning_rate": 1.87020718508298e-05,
      "loss": 0.6665,
      "step": 10761
    },
    {
      "epoch": 0.3305993303228581,
      "grad_norm": 0.32633426785469055,
      "learning_rate": 1.8701833736709343e-05,
      "loss": 0.5424,
      "step": 10762
    },
    {
      "epoch": 0.3306300494578073,
      "grad_norm": 0.31399422883987427,
      "learning_rate": 1.8701595602265142e-05,
      "loss": 0.6208,
      "step": 10763
    },
    {
      "epoch": 0.33066076859275645,
      "grad_norm": 0.3511022627353668,
      "learning_rate": 1.8701357447497765e-05,
      "loss": 0.5727,
      "step": 10764
    },
    {
      "epoch": 0.33069148772770557,
      "grad_norm": 0.36166709661483765,
      "learning_rate": 1.8701119272407756e-05,
      "loss": 0.5813,
      "step": 10765
    },
    {
      "epoch": 0.33072220686265474,
      "grad_norm": 0.3299630582332611,
      "learning_rate": 1.870088107699567e-05,
      "loss": 0.5675,
      "step": 10766
    },
    {
      "epoch": 0.3307529259976039,
      "grad_norm": 0.35226187109947205,
      "learning_rate": 1.8700642861262074e-05,
      "loss": 0.5967,
      "step": 10767
    },
    {
      "epoch": 0.3307836451325531,
      "grad_norm": 0.37466368079185486,
      "learning_rate": 1.870040462520752e-05,
      "loss": 0.6119,
      "step": 10768
    },
    {
      "epoch": 0.3308143642675022,
      "grad_norm": 2.747154951095581,
      "learning_rate": 1.8700166368832563e-05,
      "loss": 0.5626,
      "step": 10769
    },
    {
      "epoch": 0.3308450834024514,
      "grad_norm": 0.3685750365257263,
      "learning_rate": 1.869992809213776e-05,
      "loss": 0.5871,
      "step": 10770
    },
    {
      "epoch": 0.33087580253740057,
      "grad_norm": 0.3678615093231201,
      "learning_rate": 1.8699689795123664e-05,
      "loss": 0.538,
      "step": 10771
    },
    {
      "epoch": 0.3309065216723497,
      "grad_norm": 0.33392995595932007,
      "learning_rate": 1.8699451477790837e-05,
      "loss": 0.5955,
      "step": 10772
    },
    {
      "epoch": 0.33093724080729886,
      "grad_norm": 0.34633758664131165,
      "learning_rate": 1.8699213140139837e-05,
      "loss": 0.6536,
      "step": 10773
    },
    {
      "epoch": 0.33096795994224804,
      "grad_norm": 0.38190239667892456,
      "learning_rate": 1.869897478217121e-05,
      "loss": 0.5923,
      "step": 10774
    },
    {
      "epoch": 0.3309986790771972,
      "grad_norm": 0.31362736225128174,
      "learning_rate": 1.8698736403885526e-05,
      "loss": 0.5561,
      "step": 10775
    },
    {
      "epoch": 0.33102939821214633,
      "grad_norm": 0.3279740512371063,
      "learning_rate": 1.8698498005283333e-05,
      "loss": 0.5015,
      "step": 10776
    },
    {
      "epoch": 0.3310601173470955,
      "grad_norm": 0.3533557653427124,
      "learning_rate": 1.869825958636519e-05,
      "loss": 0.6598,
      "step": 10777
    },
    {
      "epoch": 0.3310908364820447,
      "grad_norm": 0.37287917733192444,
      "learning_rate": 1.8698021147131656e-05,
      "loss": 0.6042,
      "step": 10778
    },
    {
      "epoch": 0.3311215556169938,
      "grad_norm": 0.30979570746421814,
      "learning_rate": 1.8697782687583284e-05,
      "loss": 0.6009,
      "step": 10779
    },
    {
      "epoch": 0.331152274751943,
      "grad_norm": 0.33390170335769653,
      "learning_rate": 1.8697544207720636e-05,
      "loss": 0.4967,
      "step": 10780
    },
    {
      "epoch": 0.33118299388689215,
      "grad_norm": 0.33535197377204895,
      "learning_rate": 1.869730570754426e-05,
      "loss": 0.5494,
      "step": 10781
    },
    {
      "epoch": 0.3312137130218413,
      "grad_norm": 0.3805495500564575,
      "learning_rate": 1.8697067187054725e-05,
      "loss": 0.6402,
      "step": 10782
    },
    {
      "epoch": 0.33124443215679045,
      "grad_norm": 0.32948389649391174,
      "learning_rate": 1.869682864625258e-05,
      "loss": 0.5782,
      "step": 10783
    },
    {
      "epoch": 0.3312751512917396,
      "grad_norm": 0.38789892196655273,
      "learning_rate": 1.8696590085138388e-05,
      "loss": 0.6276,
      "step": 10784
    },
    {
      "epoch": 0.3313058704266888,
      "grad_norm": 0.34525445103645325,
      "learning_rate": 1.8696351503712698e-05,
      "loss": 0.513,
      "step": 10785
    },
    {
      "epoch": 0.3313365895616379,
      "grad_norm": 0.35260438919067383,
      "learning_rate": 1.8696112901976073e-05,
      "loss": 0.571,
      "step": 10786
    },
    {
      "epoch": 0.3313673086965871,
      "grad_norm": 0.3353536128997803,
      "learning_rate": 1.869587427992907e-05,
      "loss": 0.5906,
      "step": 10787
    },
    {
      "epoch": 0.33139802783153627,
      "grad_norm": 0.33226028084754944,
      "learning_rate": 1.8695635637572243e-05,
      "loss": 0.5055,
      "step": 10788
    },
    {
      "epoch": 0.33142874696648544,
      "grad_norm": 0.3630063235759735,
      "learning_rate": 1.8695396974906153e-05,
      "loss": 0.5706,
      "step": 10789
    },
    {
      "epoch": 0.33145946610143456,
      "grad_norm": 0.3309083580970764,
      "learning_rate": 1.8695158291931354e-05,
      "loss": 0.5284,
      "step": 10790
    },
    {
      "epoch": 0.33149018523638374,
      "grad_norm": 0.3475259840488434,
      "learning_rate": 1.869491958864841e-05,
      "loss": 0.5758,
      "step": 10791
    },
    {
      "epoch": 0.3315209043713329,
      "grad_norm": 0.29768988490104675,
      "learning_rate": 1.869468086505787e-05,
      "loss": 0.5855,
      "step": 10792
    },
    {
      "epoch": 0.3315516235062821,
      "grad_norm": 0.34590888023376465,
      "learning_rate": 1.8694442121160298e-05,
      "loss": 0.5433,
      "step": 10793
    },
    {
      "epoch": 0.3315823426412312,
      "grad_norm": 0.36587777733802795,
      "learning_rate": 1.8694203356956248e-05,
      "loss": 0.5591,
      "step": 10794
    },
    {
      "epoch": 0.3316130617761804,
      "grad_norm": 0.3860008120536804,
      "learning_rate": 1.869396457244628e-05,
      "loss": 0.6475,
      "step": 10795
    },
    {
      "epoch": 0.33164378091112956,
      "grad_norm": 0.519795298576355,
      "learning_rate": 1.869372576763095e-05,
      "loss": 0.6711,
      "step": 10796
    },
    {
      "epoch": 0.3316745000460787,
      "grad_norm": 0.35144469141960144,
      "learning_rate": 1.8693486942510818e-05,
      "loss": 0.5992,
      "step": 10797
    },
    {
      "epoch": 0.33170521918102785,
      "grad_norm": 0.3557735085487366,
      "learning_rate": 1.8693248097086436e-05,
      "loss": 0.5739,
      "step": 10798
    },
    {
      "epoch": 0.33173593831597703,
      "grad_norm": 0.30258288979530334,
      "learning_rate": 1.869300923135837e-05,
      "loss": 0.545,
      "step": 10799
    },
    {
      "epoch": 0.3317666574509262,
      "grad_norm": 0.3355347514152527,
      "learning_rate": 1.869277034532717e-05,
      "loss": 0.4997,
      "step": 10800
    },
    {
      "epoch": 0.3317973765858753,
      "grad_norm": 0.3408590257167816,
      "learning_rate": 1.86925314389934e-05,
      "loss": 0.586,
      "step": 10801
    },
    {
      "epoch": 0.3318280957208245,
      "grad_norm": 12.224002838134766,
      "learning_rate": 1.8692292512357614e-05,
      "loss": 0.5359,
      "step": 10802
    },
    {
      "epoch": 0.3318588148557737,
      "grad_norm": 0.3779182732105255,
      "learning_rate": 1.8692053565420376e-05,
      "loss": 0.501,
      "step": 10803
    },
    {
      "epoch": 0.3318895339907228,
      "grad_norm": 0.35320040583610535,
      "learning_rate": 1.8691814598182238e-05,
      "loss": 0.6041,
      "step": 10804
    },
    {
      "epoch": 0.33192025312567197,
      "grad_norm": 0.3651285767555237,
      "learning_rate": 1.869157561064376e-05,
      "loss": 0.5444,
      "step": 10805
    },
    {
      "epoch": 0.33195097226062115,
      "grad_norm": 0.3797574043273926,
      "learning_rate": 1.86913366028055e-05,
      "loss": 0.6674,
      "step": 10806
    },
    {
      "epoch": 0.3319816913955703,
      "grad_norm": 0.34154045581817627,
      "learning_rate": 1.8691097574668012e-05,
      "loss": 0.5742,
      "step": 10807
    },
    {
      "epoch": 0.33201241053051944,
      "grad_norm": 0.3455929756164551,
      "learning_rate": 1.8690858526231866e-05,
      "loss": 0.6231,
      "step": 10808
    },
    {
      "epoch": 0.3320431296654686,
      "grad_norm": 0.314819872379303,
      "learning_rate": 1.8690619457497608e-05,
      "loss": 0.4538,
      "step": 10809
    },
    {
      "epoch": 0.3320738488004178,
      "grad_norm": 0.33903348445892334,
      "learning_rate": 1.8690380368465802e-05,
      "loss": 0.5933,
      "step": 10810
    },
    {
      "epoch": 0.33210456793536697,
      "grad_norm": 0.3888603746891022,
      "learning_rate": 1.8690141259137006e-05,
      "loss": 0.6127,
      "step": 10811
    },
    {
      "epoch": 0.3321352870703161,
      "grad_norm": 0.3223203122615814,
      "learning_rate": 1.868990212951178e-05,
      "loss": 0.5673,
      "step": 10812
    },
    {
      "epoch": 0.33216600620526526,
      "grad_norm": 0.3116982579231262,
      "learning_rate": 1.8689662979590677e-05,
      "loss": 0.5096,
      "step": 10813
    },
    {
      "epoch": 0.33219672534021444,
      "grad_norm": 0.35707351565361023,
      "learning_rate": 1.8689423809374263e-05,
      "loss": 0.6217,
      "step": 10814
    },
    {
      "epoch": 0.33222744447516356,
      "grad_norm": 0.37554264068603516,
      "learning_rate": 1.868918461886309e-05,
      "loss": 0.6583,
      "step": 10815
    },
    {
      "epoch": 0.33225816361011273,
      "grad_norm": 0.4192793667316437,
      "learning_rate": 1.8688945408057722e-05,
      "loss": 0.5947,
      "step": 10816
    },
    {
      "epoch": 0.3322888827450619,
      "grad_norm": 0.3308614492416382,
      "learning_rate": 1.8688706176958714e-05,
      "loss": 0.5444,
      "step": 10817
    },
    {
      "epoch": 0.3323196018800111,
      "grad_norm": 0.34052881598472595,
      "learning_rate": 1.8688466925566623e-05,
      "loss": 0.6079,
      "step": 10818
    },
    {
      "epoch": 0.3323503210149602,
      "grad_norm": 0.3226393461227417,
      "learning_rate": 1.8688227653882017e-05,
      "loss": 0.592,
      "step": 10819
    },
    {
      "epoch": 0.3323810401499094,
      "grad_norm": 0.4906481206417084,
      "learning_rate": 1.8687988361905444e-05,
      "loss": 0.5658,
      "step": 10820
    },
    {
      "epoch": 0.33241175928485855,
      "grad_norm": 0.38401439785957336,
      "learning_rate": 1.868774904963747e-05,
      "loss": 0.5879,
      "step": 10821
    },
    {
      "epoch": 0.3324424784198077,
      "grad_norm": 0.3387812376022339,
      "learning_rate": 1.868750971707865e-05,
      "loss": 0.6676,
      "step": 10822
    },
    {
      "epoch": 0.33247319755475685,
      "grad_norm": 0.32928329706192017,
      "learning_rate": 1.8687270364229545e-05,
      "loss": 0.492,
      "step": 10823
    },
    {
      "epoch": 0.332503916689706,
      "grad_norm": 0.34988105297088623,
      "learning_rate": 1.8687030991090708e-05,
      "loss": 0.4899,
      "step": 10824
    },
    {
      "epoch": 0.3325346358246552,
      "grad_norm": 0.3623489439487457,
      "learning_rate": 1.868679159766271e-05,
      "loss": 0.6367,
      "step": 10825
    },
    {
      "epoch": 0.3325653549596043,
      "grad_norm": 0.34259331226348877,
      "learning_rate": 1.86865521839461e-05,
      "loss": 0.6272,
      "step": 10826
    },
    {
      "epoch": 0.3325960740945535,
      "grad_norm": 0.37767159938812256,
      "learning_rate": 1.8686312749941444e-05,
      "loss": 0.5589,
      "step": 10827
    },
    {
      "epoch": 0.33262679322950267,
      "grad_norm": 0.32660403847694397,
      "learning_rate": 1.8686073295649295e-05,
      "loss": 0.4939,
      "step": 10828
    },
    {
      "epoch": 0.3326575123644518,
      "grad_norm": 0.3226092755794525,
      "learning_rate": 1.8685833821070215e-05,
      "loss": 0.5889,
      "step": 10829
    },
    {
      "epoch": 0.33268823149940097,
      "grad_norm": 0.3906758725643158,
      "learning_rate": 1.8685594326204768e-05,
      "loss": 0.681,
      "step": 10830
    },
    {
      "epoch": 0.33271895063435014,
      "grad_norm": 0.3242807686328888,
      "learning_rate": 1.8685354811053505e-05,
      "loss": 0.6347,
      "step": 10831
    },
    {
      "epoch": 0.3327496697692993,
      "grad_norm": 0.3344544470310211,
      "learning_rate": 1.868511527561699e-05,
      "loss": 0.6014,
      "step": 10832
    },
    {
      "epoch": 0.33278038890424844,
      "grad_norm": 0.3356534540653229,
      "learning_rate": 1.868487571989578e-05,
      "loss": 0.554,
      "step": 10833
    },
    {
      "epoch": 0.3328111080391976,
      "grad_norm": 0.373982310295105,
      "learning_rate": 1.868463614389044e-05,
      "loss": 0.6177,
      "step": 10834
    },
    {
      "epoch": 0.3328418271741468,
      "grad_norm": 0.4723977744579315,
      "learning_rate": 1.8684396547601524e-05,
      "loss": 0.5116,
      "step": 10835
    },
    {
      "epoch": 0.33287254630909596,
      "grad_norm": 0.4226072132587433,
      "learning_rate": 1.8684156931029592e-05,
      "loss": 0.6077,
      "step": 10836
    },
    {
      "epoch": 0.3329032654440451,
      "grad_norm": 0.3025416433811188,
      "learning_rate": 1.8683917294175206e-05,
      "loss": 0.5768,
      "step": 10837
    },
    {
      "epoch": 0.33293398457899426,
      "grad_norm": 0.3488057255744934,
      "learning_rate": 1.8683677637038923e-05,
      "loss": 0.6533,
      "step": 10838
    },
    {
      "epoch": 0.33296470371394343,
      "grad_norm": 0.333935022354126,
      "learning_rate": 1.8683437959621308e-05,
      "loss": 0.5826,
      "step": 10839
    },
    {
      "epoch": 0.33299542284889255,
      "grad_norm": 0.360336571931839,
      "learning_rate": 1.868319826192291e-05,
      "loss": 0.6315,
      "step": 10840
    },
    {
      "epoch": 0.33302614198384173,
      "grad_norm": 0.3025347888469696,
      "learning_rate": 1.8682958543944307e-05,
      "loss": 0.562,
      "step": 10841
    },
    {
      "epoch": 0.3330568611187909,
      "grad_norm": 0.3501327931880951,
      "learning_rate": 1.868271880568604e-05,
      "loss": 0.5515,
      "step": 10842
    },
    {
      "epoch": 0.3330875802537401,
      "grad_norm": 0.3521806597709656,
      "learning_rate": 1.868247904714868e-05,
      "loss": 0.5394,
      "step": 10843
    },
    {
      "epoch": 0.3331182993886892,
      "grad_norm": 0.35016387701034546,
      "learning_rate": 1.8682239268332782e-05,
      "loss": 0.5446,
      "step": 10844
    },
    {
      "epoch": 0.3331490185236384,
      "grad_norm": 0.32804715633392334,
      "learning_rate": 1.8681999469238908e-05,
      "loss": 0.5483,
      "step": 10845
    },
    {
      "epoch": 0.33317973765858755,
      "grad_norm": 0.3784356415271759,
      "learning_rate": 1.868175964986762e-05,
      "loss": 0.6144,
      "step": 10846
    },
    {
      "epoch": 0.33321045679353667,
      "grad_norm": 0.3240474760532379,
      "learning_rate": 1.8681519810219475e-05,
      "loss": 0.5551,
      "step": 10847
    },
    {
      "epoch": 0.33324117592848584,
      "grad_norm": 0.3785206973552704,
      "learning_rate": 1.868127995029503e-05,
      "loss": 0.5997,
      "step": 10848
    },
    {
      "epoch": 0.333271895063435,
      "grad_norm": 0.341886430978775,
      "learning_rate": 1.868104007009486e-05,
      "loss": 0.5829,
      "step": 10849
    },
    {
      "epoch": 0.3333026141983842,
      "grad_norm": 0.318952351808548,
      "learning_rate": 1.8680800169619506e-05,
      "loss": 0.5486,
      "step": 10850
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.3860340714454651,
      "learning_rate": 1.8680560248869538e-05,
      "loss": 0.6275,
      "step": 10851
    },
    {
      "epoch": 0.3333640524682825,
      "grad_norm": 0.34685030579566956,
      "learning_rate": 1.8680320307845515e-05,
      "loss": 0.5494,
      "step": 10852
    },
    {
      "epoch": 0.33339477160323167,
      "grad_norm": 0.31490716338157654,
      "learning_rate": 1.8680080346548e-05,
      "loss": 0.5663,
      "step": 10853
    },
    {
      "epoch": 0.3334254907381808,
      "grad_norm": 0.37204214930534363,
      "learning_rate": 1.867984036497755e-05,
      "loss": 0.5671,
      "step": 10854
    },
    {
      "epoch": 0.33345620987312996,
      "grad_norm": 0.3750583827495575,
      "learning_rate": 1.8679600363134724e-05,
      "loss": 0.5827,
      "step": 10855
    },
    {
      "epoch": 0.33348692900807914,
      "grad_norm": 0.34068822860717773,
      "learning_rate": 1.8679360341020086e-05,
      "loss": 0.5583,
      "step": 10856
    },
    {
      "epoch": 0.3335176481430283,
      "grad_norm": 0.3412506580352783,
      "learning_rate": 1.8679120298634198e-05,
      "loss": 0.5842,
      "step": 10857
    },
    {
      "epoch": 0.33354836727797743,
      "grad_norm": 0.33057186007499695,
      "learning_rate": 1.867888023597762e-05,
      "loss": 0.5407,
      "step": 10858
    },
    {
      "epoch": 0.3335790864129266,
      "grad_norm": 0.32028576731681824,
      "learning_rate": 1.867864015305091e-05,
      "loss": 0.5899,
      "step": 10859
    },
    {
      "epoch": 0.3336098055478758,
      "grad_norm": 0.34127864241600037,
      "learning_rate": 1.867840004985463e-05,
      "loss": 0.5967,
      "step": 10860
    },
    {
      "epoch": 0.33364052468282496,
      "grad_norm": 0.3202706277370453,
      "learning_rate": 1.8678159926389338e-05,
      "loss": 0.4617,
      "step": 10861
    },
    {
      "epoch": 0.3336712438177741,
      "grad_norm": 0.36463484168052673,
      "learning_rate": 1.86779197826556e-05,
      "loss": 0.554,
      "step": 10862
    },
    {
      "epoch": 0.33370196295272325,
      "grad_norm": 0.3657853901386261,
      "learning_rate": 1.867767961865397e-05,
      "loss": 0.5855,
      "step": 10863
    },
    {
      "epoch": 0.3337326820876724,
      "grad_norm": 0.34839653968811035,
      "learning_rate": 1.8677439434385016e-05,
      "loss": 0.594,
      "step": 10864
    },
    {
      "epoch": 0.33376340122262155,
      "grad_norm": 0.36807185411453247,
      "learning_rate": 1.8677199229849297e-05,
      "loss": 0.6144,
      "step": 10865
    },
    {
      "epoch": 0.3337941203575707,
      "grad_norm": 0.37034061551094055,
      "learning_rate": 1.8676959005047373e-05,
      "loss": 0.5769,
      "step": 10866
    },
    {
      "epoch": 0.3338248394925199,
      "grad_norm": 0.3780219256877899,
      "learning_rate": 1.8676718759979806e-05,
      "loss": 0.6318,
      "step": 10867
    },
    {
      "epoch": 0.3338555586274691,
      "grad_norm": 0.3350030183792114,
      "learning_rate": 1.8676478494647156e-05,
      "loss": 0.5824,
      "step": 10868
    },
    {
      "epoch": 0.3338862777624182,
      "grad_norm": 0.39518478512763977,
      "learning_rate": 1.867623820904998e-05,
      "loss": 0.4551,
      "step": 10869
    },
    {
      "epoch": 0.33391699689736737,
      "grad_norm": 0.6111534237861633,
      "learning_rate": 1.867599790318885e-05,
      "loss": 0.5592,
      "step": 10870
    },
    {
      "epoch": 0.33394771603231654,
      "grad_norm": 0.31226202845573425,
      "learning_rate": 1.8675757577064317e-05,
      "loss": 0.5408,
      "step": 10871
    },
    {
      "epoch": 0.33397843516726566,
      "grad_norm": 0.35071665048599243,
      "learning_rate": 1.867551723067695e-05,
      "loss": 0.5816,
      "step": 10872
    },
    {
      "epoch": 0.33400915430221484,
      "grad_norm": 0.32620468735694885,
      "learning_rate": 1.8675276864027303e-05,
      "loss": 0.6619,
      "step": 10873
    },
    {
      "epoch": 0.334039873437164,
      "grad_norm": 0.4871514141559601,
      "learning_rate": 1.867503647711594e-05,
      "loss": 0.6035,
      "step": 10874
    },
    {
      "epoch": 0.3340705925721132,
      "grad_norm": 0.336295485496521,
      "learning_rate": 1.867479606994343e-05,
      "loss": 0.5322,
      "step": 10875
    },
    {
      "epoch": 0.3341013117070623,
      "grad_norm": 0.3334338963031769,
      "learning_rate": 1.8674555642510323e-05,
      "loss": 0.5551,
      "step": 10876
    },
    {
      "epoch": 0.3341320308420115,
      "grad_norm": 0.3878858983516693,
      "learning_rate": 1.8674315194817184e-05,
      "loss": 0.5836,
      "step": 10877
    },
    {
      "epoch": 0.33416274997696066,
      "grad_norm": 0.3123989701271057,
      "learning_rate": 1.8674074726864576e-05,
      "loss": 0.5518,
      "step": 10878
    },
    {
      "epoch": 0.33419346911190984,
      "grad_norm": 0.36274293065071106,
      "learning_rate": 1.8673834238653065e-05,
      "loss": 0.6297,
      "step": 10879
    },
    {
      "epoch": 0.33422418824685896,
      "grad_norm": 0.3462165892124176,
      "learning_rate": 1.8673593730183208e-05,
      "loss": 0.5925,
      "step": 10880
    },
    {
      "epoch": 0.33425490738180813,
      "grad_norm": 0.36019420623779297,
      "learning_rate": 1.8673353201455563e-05,
      "loss": 0.584,
      "step": 10881
    },
    {
      "epoch": 0.3342856265167573,
      "grad_norm": 0.353059858083725,
      "learning_rate": 1.86731126524707e-05,
      "loss": 0.5714,
      "step": 10882
    },
    {
      "epoch": 0.3343163456517064,
      "grad_norm": 0.3824971616268158,
      "learning_rate": 1.8672872083229175e-05,
      "loss": 0.6061,
      "step": 10883
    },
    {
      "epoch": 0.3343470647866556,
      "grad_norm": 0.33549046516418457,
      "learning_rate": 1.867263149373155e-05,
      "loss": 0.5839,
      "step": 10884
    },
    {
      "epoch": 0.3343777839216048,
      "grad_norm": 0.3835899531841278,
      "learning_rate": 1.867239088397839e-05,
      "loss": 0.6295,
      "step": 10885
    },
    {
      "epoch": 0.33440850305655395,
      "grad_norm": 0.33937525749206543,
      "learning_rate": 1.8672150253970256e-05,
      "loss": 0.5181,
      "step": 10886
    },
    {
      "epoch": 0.33443922219150307,
      "grad_norm": 0.35673198103904724,
      "learning_rate": 1.8671909603707708e-05,
      "loss": 0.5745,
      "step": 10887
    },
    {
      "epoch": 0.33446994132645225,
      "grad_norm": 0.3678250312805176,
      "learning_rate": 1.8671668933191308e-05,
      "loss": 0.6088,
      "step": 10888
    },
    {
      "epoch": 0.3345006604614014,
      "grad_norm": 0.3162587285041809,
      "learning_rate": 1.8671428242421624e-05,
      "loss": 0.578,
      "step": 10889
    },
    {
      "epoch": 0.33453137959635054,
      "grad_norm": 0.3558366894721985,
      "learning_rate": 1.8671187531399214e-05,
      "loss": 0.5411,
      "step": 10890
    },
    {
      "epoch": 0.3345620987312997,
      "grad_norm": 0.36291614174842834,
      "learning_rate": 1.8670946800124636e-05,
      "loss": 0.5984,
      "step": 10891
    },
    {
      "epoch": 0.3345928178662489,
      "grad_norm": 0.34553563594818115,
      "learning_rate": 1.8670706048598458e-05,
      "loss": 0.5831,
      "step": 10892
    },
    {
      "epoch": 0.33462353700119807,
      "grad_norm": 0.3777993619441986,
      "learning_rate": 1.8670465276821237e-05,
      "loss": 0.5844,
      "step": 10893
    },
    {
      "epoch": 0.3346542561361472,
      "grad_norm": 0.3236714005470276,
      "learning_rate": 1.8670224484793543e-05,
      "loss": 0.5152,
      "step": 10894
    },
    {
      "epoch": 0.33468497527109636,
      "grad_norm": 0.3524039685726166,
      "learning_rate": 1.8669983672515933e-05,
      "loss": 0.4997,
      "step": 10895
    },
    {
      "epoch": 0.33471569440604554,
      "grad_norm": 0.36430954933166504,
      "learning_rate": 1.8669742839988974e-05,
      "loss": 0.6655,
      "step": 10896
    },
    {
      "epoch": 0.33474641354099466,
      "grad_norm": 0.3671779930591583,
      "learning_rate": 1.8669501987213218e-05,
      "loss": 0.5747,
      "step": 10897
    },
    {
      "epoch": 0.33477713267594383,
      "grad_norm": 0.34294915199279785,
      "learning_rate": 1.8669261114189238e-05,
      "loss": 0.5839,
      "step": 10898
    },
    {
      "epoch": 0.334807851810893,
      "grad_norm": 0.33036041259765625,
      "learning_rate": 1.86690202209176e-05,
      "loss": 0.5367,
      "step": 10899
    },
    {
      "epoch": 0.3348385709458422,
      "grad_norm": 0.3706984221935272,
      "learning_rate": 1.866877930739885e-05,
      "loss": 0.6118,
      "step": 10900
    },
    {
      "epoch": 0.3348692900807913,
      "grad_norm": 0.33208152651786804,
      "learning_rate": 1.8668538373633565e-05,
      "loss": 0.619,
      "step": 10901
    },
    {
      "epoch": 0.3349000092157405,
      "grad_norm": 0.4025624990463257,
      "learning_rate": 1.86682974196223e-05,
      "loss": 0.5615,
      "step": 10902
    },
    {
      "epoch": 0.33493072835068965,
      "grad_norm": 0.3630326986312866,
      "learning_rate": 1.8668056445365622e-05,
      "loss": 0.5889,
      "step": 10903
    },
    {
      "epoch": 0.33496144748563883,
      "grad_norm": 0.30965954065322876,
      "learning_rate": 1.8667815450864097e-05,
      "loss": 0.5818,
      "step": 10904
    },
    {
      "epoch": 0.33499216662058795,
      "grad_norm": 0.33696281909942627,
      "learning_rate": 1.866757443611828e-05,
      "loss": 0.5817,
      "step": 10905
    },
    {
      "epoch": 0.3350228857555371,
      "grad_norm": 0.9126240611076355,
      "learning_rate": 1.866733340112874e-05,
      "loss": 0.5708,
      "step": 10906
    },
    {
      "epoch": 0.3350536048904863,
      "grad_norm": 0.42187410593032837,
      "learning_rate": 1.8667092345896036e-05,
      "loss": 0.6849,
      "step": 10907
    },
    {
      "epoch": 0.3350843240254354,
      "grad_norm": 0.32993242144584656,
      "learning_rate": 1.866685127042073e-05,
      "loss": 0.6177,
      "step": 10908
    },
    {
      "epoch": 0.3351150431603846,
      "grad_norm": 0.34601879119873047,
      "learning_rate": 1.866661017470339e-05,
      "loss": 0.5594,
      "step": 10909
    },
    {
      "epoch": 0.33514576229533377,
      "grad_norm": 0.4783385694026947,
      "learning_rate": 1.8666369058744574e-05,
      "loss": 0.5806,
      "step": 10910
    },
    {
      "epoch": 0.33517648143028295,
      "grad_norm": 0.3539155125617981,
      "learning_rate": 1.866612792254485e-05,
      "loss": 0.544,
      "step": 10911
    },
    {
      "epoch": 0.33520720056523207,
      "grad_norm": 0.34251606464385986,
      "learning_rate": 1.8665886766104782e-05,
      "loss": 0.5475,
      "step": 10912
    },
    {
      "epoch": 0.33523791970018124,
      "grad_norm": 0.3415076732635498,
      "learning_rate": 1.8665645589424928e-05,
      "loss": 0.5813,
      "step": 10913
    },
    {
      "epoch": 0.3352686388351304,
      "grad_norm": 0.33746659755706787,
      "learning_rate": 1.8665404392505856e-05,
      "loss": 0.5616,
      "step": 10914
    },
    {
      "epoch": 0.33529935797007954,
      "grad_norm": 0.7081437110900879,
      "learning_rate": 1.8665163175348123e-05,
      "loss": 0.5666,
      "step": 10915
    },
    {
      "epoch": 0.3353300771050287,
      "grad_norm": 0.3497101962566376,
      "learning_rate": 1.8664921937952297e-05,
      "loss": 0.5869,
      "step": 10916
    },
    {
      "epoch": 0.3353607962399779,
      "grad_norm": 0.3300389349460602,
      "learning_rate": 1.866468068031894e-05,
      "loss": 0.5962,
      "step": 10917
    },
    {
      "epoch": 0.33539151537492706,
      "grad_norm": 0.33430016040802,
      "learning_rate": 1.8664439402448617e-05,
      "loss": 0.6818,
      "step": 10918
    },
    {
      "epoch": 0.3354222345098762,
      "grad_norm": 0.34055614471435547,
      "learning_rate": 1.866419810434189e-05,
      "loss": 0.5176,
      "step": 10919
    },
    {
      "epoch": 0.33545295364482536,
      "grad_norm": 0.3307061195373535,
      "learning_rate": 1.8663956785999323e-05,
      "loss": 0.5127,
      "step": 10920
    },
    {
      "epoch": 0.33548367277977453,
      "grad_norm": 0.3276344835758209,
      "learning_rate": 1.866371544742148e-05,
      "loss": 0.6273,
      "step": 10921
    },
    {
      "epoch": 0.3355143919147237,
      "grad_norm": 0.3619306683540344,
      "learning_rate": 1.8663474088608927e-05,
      "loss": 0.5606,
      "step": 10922
    },
    {
      "epoch": 0.33554511104967283,
      "grad_norm": 0.39632904529571533,
      "learning_rate": 1.8663232709562226e-05,
      "loss": 0.5379,
      "step": 10923
    },
    {
      "epoch": 0.335575830184622,
      "grad_norm": 0.3501565754413605,
      "learning_rate": 1.8662991310281934e-05,
      "loss": 0.5334,
      "step": 10924
    },
    {
      "epoch": 0.3356065493195712,
      "grad_norm": 0.37133729457855225,
      "learning_rate": 1.8662749890768627e-05,
      "loss": 0.5859,
      "step": 10925
    },
    {
      "epoch": 0.3356372684545203,
      "grad_norm": 0.3497900068759918,
      "learning_rate": 1.8662508451022857e-05,
      "loss": 0.5146,
      "step": 10926
    },
    {
      "epoch": 0.3356679875894695,
      "grad_norm": 0.36382007598876953,
      "learning_rate": 1.86622669910452e-05,
      "loss": 0.6073,
      "step": 10927
    },
    {
      "epoch": 0.33569870672441865,
      "grad_norm": 0.46482035517692566,
      "learning_rate": 1.866202551083621e-05,
      "loss": 0.6333,
      "step": 10928
    },
    {
      "epoch": 0.3357294258593678,
      "grad_norm": 0.3581355810165405,
      "learning_rate": 1.8661784010396453e-05,
      "loss": 0.6324,
      "step": 10929
    },
    {
      "epoch": 0.33576014499431694,
      "grad_norm": 0.40294739603996277,
      "learning_rate": 1.8661542489726497e-05,
      "loss": 0.6211,
      "step": 10930
    },
    {
      "epoch": 0.3357908641292661,
      "grad_norm": 0.36245110630989075,
      "learning_rate": 1.86613009488269e-05,
      "loss": 0.5247,
      "step": 10931
    },
    {
      "epoch": 0.3358215832642153,
      "grad_norm": 0.3166002035140991,
      "learning_rate": 1.8661059387698233e-05,
      "loss": 0.573,
      "step": 10932
    },
    {
      "epoch": 0.3358523023991644,
      "grad_norm": 0.3686404526233673,
      "learning_rate": 1.8660817806341053e-05,
      "loss": 0.6263,
      "step": 10933
    },
    {
      "epoch": 0.3358830215341136,
      "grad_norm": 0.3514450490474701,
      "learning_rate": 1.8660576204755934e-05,
      "loss": 0.5458,
      "step": 10934
    },
    {
      "epoch": 0.33591374066906277,
      "grad_norm": 0.32614681124687195,
      "learning_rate": 1.866033458294343e-05,
      "loss": 0.487,
      "step": 10935
    },
    {
      "epoch": 0.33594445980401194,
      "grad_norm": 0.3215641975402832,
      "learning_rate": 1.8660092940904112e-05,
      "loss": 0.5575,
      "step": 10936
    },
    {
      "epoch": 0.33597517893896106,
      "grad_norm": 0.35702359676361084,
      "learning_rate": 1.8659851278638542e-05,
      "loss": 0.5214,
      "step": 10937
    },
    {
      "epoch": 0.33600589807391024,
      "grad_norm": 0.3821672797203064,
      "learning_rate": 1.8659609596147285e-05,
      "loss": 0.6394,
      "step": 10938
    },
    {
      "epoch": 0.3360366172088594,
      "grad_norm": 0.381294310092926,
      "learning_rate": 1.8659367893430904e-05,
      "loss": 0.6423,
      "step": 10939
    },
    {
      "epoch": 0.33606733634380853,
      "grad_norm": 0.3565676212310791,
      "learning_rate": 1.865912617048996e-05,
      "loss": 0.6072,
      "step": 10940
    },
    {
      "epoch": 0.3360980554787577,
      "grad_norm": 0.3549792170524597,
      "learning_rate": 1.8658884427325033e-05,
      "loss": 0.5684,
      "step": 10941
    },
    {
      "epoch": 0.3361287746137069,
      "grad_norm": 0.38265424966812134,
      "learning_rate": 1.865864266393667e-05,
      "loss": 0.6225,
      "step": 10942
    },
    {
      "epoch": 0.33615949374865606,
      "grad_norm": 0.35470449924468994,
      "learning_rate": 1.865840088032544e-05,
      "loss": 0.5816,
      "step": 10943
    },
    {
      "epoch": 0.3361902128836052,
      "grad_norm": 0.3419837951660156,
      "learning_rate": 1.8658159076491915e-05,
      "loss": 0.5592,
      "step": 10944
    },
    {
      "epoch": 0.33622093201855435,
      "grad_norm": 0.3367605209350586,
      "learning_rate": 1.865791725243665e-05,
      "loss": 0.5645,
      "step": 10945
    },
    {
      "epoch": 0.33625165115350353,
      "grad_norm": 0.32456347346305847,
      "learning_rate": 1.8657675408160218e-05,
      "loss": 0.5555,
      "step": 10946
    },
    {
      "epoch": 0.3362823702884527,
      "grad_norm": 0.34183183312416077,
      "learning_rate": 1.865743354366318e-05,
      "loss": 0.5278,
      "step": 10947
    },
    {
      "epoch": 0.3363130894234018,
      "grad_norm": 0.34094947576522827,
      "learning_rate": 1.86571916589461e-05,
      "loss": 0.6778,
      "step": 10948
    },
    {
      "epoch": 0.336343808558351,
      "grad_norm": 0.36560675501823425,
      "learning_rate": 1.8656949754009548e-05,
      "loss": 0.5464,
      "step": 10949
    },
    {
      "epoch": 0.3363745276933002,
      "grad_norm": 0.3206081986427307,
      "learning_rate": 1.865670782885408e-05,
      "loss": 0.5567,
      "step": 10950
    },
    {
      "epoch": 0.3364052468282493,
      "grad_norm": 0.3212815225124359,
      "learning_rate": 1.865646588348027e-05,
      "loss": 0.5431,
      "step": 10951
    },
    {
      "epoch": 0.33643596596319847,
      "grad_norm": 0.36628374457359314,
      "learning_rate": 1.865622391788868e-05,
      "loss": 0.5209,
      "step": 10952
    },
    {
      "epoch": 0.33646668509814764,
      "grad_norm": 0.35054340958595276,
      "learning_rate": 1.865598193207987e-05,
      "loss": 0.6049,
      "step": 10953
    },
    {
      "epoch": 0.3364974042330968,
      "grad_norm": 0.3340693414211273,
      "learning_rate": 1.865573992605441e-05,
      "loss": 0.608,
      "step": 10954
    },
    {
      "epoch": 0.33652812336804594,
      "grad_norm": 0.36932793259620667,
      "learning_rate": 1.8655497899812867e-05,
      "loss": 0.6004,
      "step": 10955
    },
    {
      "epoch": 0.3365588425029951,
      "grad_norm": 0.37458693981170654,
      "learning_rate": 1.865525585335581e-05,
      "loss": 0.5845,
      "step": 10956
    },
    {
      "epoch": 0.3365895616379443,
      "grad_norm": 0.3339962661266327,
      "learning_rate": 1.865501378668379e-05,
      "loss": 0.6057,
      "step": 10957
    },
    {
      "epoch": 0.3366202807728934,
      "grad_norm": 0.3687262237071991,
      "learning_rate": 1.865477169979738e-05,
      "loss": 0.6378,
      "step": 10958
    },
    {
      "epoch": 0.3366509999078426,
      "grad_norm": 0.34732627868652344,
      "learning_rate": 1.865452959269715e-05,
      "loss": 0.6538,
      "step": 10959
    },
    {
      "epoch": 0.33668171904279176,
      "grad_norm": 0.494842529296875,
      "learning_rate": 1.8654287465383665e-05,
      "loss": 0.5504,
      "step": 10960
    },
    {
      "epoch": 0.33671243817774094,
      "grad_norm": 0.3244752585887909,
      "learning_rate": 1.8654045317857483e-05,
      "loss": 0.575,
      "step": 10961
    },
    {
      "epoch": 0.33674315731269006,
      "grad_norm": 0.4256282150745392,
      "learning_rate": 1.8653803150119177e-05,
      "loss": 0.6437,
      "step": 10962
    },
    {
      "epoch": 0.33677387644763923,
      "grad_norm": 0.3013494610786438,
      "learning_rate": 1.8653560962169307e-05,
      "loss": 0.5412,
      "step": 10963
    },
    {
      "epoch": 0.3368045955825884,
      "grad_norm": 0.3456588387489319,
      "learning_rate": 1.865331875400844e-05,
      "loss": 0.5643,
      "step": 10964
    },
    {
      "epoch": 0.3368353147175376,
      "grad_norm": 0.3726348578929901,
      "learning_rate": 1.8653076525637145e-05,
      "loss": 0.6001,
      "step": 10965
    },
    {
      "epoch": 0.3368660338524867,
      "grad_norm": 0.34074866771698,
      "learning_rate": 1.8652834277055985e-05,
      "loss": 0.6311,
      "step": 10966
    },
    {
      "epoch": 0.3368967529874359,
      "grad_norm": 0.3440648019313812,
      "learning_rate": 1.8652592008265523e-05,
      "loss": 0.506,
      "step": 10967
    },
    {
      "epoch": 0.33692747212238505,
      "grad_norm": 0.42854443192481995,
      "learning_rate": 1.8652349719266333e-05,
      "loss": 0.6239,
      "step": 10968
    },
    {
      "epoch": 0.33695819125733417,
      "grad_norm": 0.33472809195518494,
      "learning_rate": 1.865210741005897e-05,
      "loss": 0.6469,
      "step": 10969
    },
    {
      "epoch": 0.33698891039228335,
      "grad_norm": 0.3574744760990143,
      "learning_rate": 1.865186508064401e-05,
      "loss": 0.6638,
      "step": 10970
    },
    {
      "epoch": 0.3370196295272325,
      "grad_norm": 0.3538910150527954,
      "learning_rate": 1.8651622731022017e-05,
      "loss": 0.6148,
      "step": 10971
    },
    {
      "epoch": 0.3370503486621817,
      "grad_norm": 0.33094072341918945,
      "learning_rate": 1.865138036119355e-05,
      "loss": 0.5947,
      "step": 10972
    },
    {
      "epoch": 0.3370810677971308,
      "grad_norm": 0.45138198137283325,
      "learning_rate": 1.8651137971159184e-05,
      "loss": 0.5634,
      "step": 10973
    },
    {
      "epoch": 0.33711178693208,
      "grad_norm": 0.3563874363899231,
      "learning_rate": 1.8650895560919476e-05,
      "loss": 0.6736,
      "step": 10974
    },
    {
      "epoch": 0.33714250606702917,
      "grad_norm": 0.3239794075489044,
      "learning_rate": 1.8650653130475e-05,
      "loss": 0.5734,
      "step": 10975
    },
    {
      "epoch": 0.3371732252019783,
      "grad_norm": 0.370481014251709,
      "learning_rate": 1.8650410679826323e-05,
      "loss": 0.6031,
      "step": 10976
    },
    {
      "epoch": 0.33720394433692746,
      "grad_norm": 0.35725533962249756,
      "learning_rate": 1.8650168208974e-05,
      "loss": 0.5987,
      "step": 10977
    },
    {
      "epoch": 0.33723466347187664,
      "grad_norm": 0.3613501191139221,
      "learning_rate": 1.864992571791861e-05,
      "loss": 0.663,
      "step": 10978
    },
    {
      "epoch": 0.3372653826068258,
      "grad_norm": 0.35239166021347046,
      "learning_rate": 1.8649683206660717e-05,
      "loss": 0.6276,
      "step": 10979
    },
    {
      "epoch": 0.33729610174177493,
      "grad_norm": 0.3890765607357025,
      "learning_rate": 1.8649440675200883e-05,
      "loss": 0.6288,
      "step": 10980
    },
    {
      "epoch": 0.3373268208767241,
      "grad_norm": 0.34113267064094543,
      "learning_rate": 1.8649198123539673e-05,
      "loss": 0.5985,
      "step": 10981
    },
    {
      "epoch": 0.3373575400116733,
      "grad_norm": 0.44092419743537903,
      "learning_rate": 1.864895555167766e-05,
      "loss": 0.5744,
      "step": 10982
    },
    {
      "epoch": 0.3373882591466224,
      "grad_norm": 0.2994008958339691,
      "learning_rate": 1.8648712959615406e-05,
      "loss": 0.5526,
      "step": 10983
    },
    {
      "epoch": 0.3374189782815716,
      "grad_norm": 0.3473685681819916,
      "learning_rate": 1.8648470347353477e-05,
      "loss": 0.6463,
      "step": 10984
    },
    {
      "epoch": 0.33744969741652076,
      "grad_norm": 0.3143885135650635,
      "learning_rate": 1.8648227714892442e-05,
      "loss": 0.592,
      "step": 10985
    },
    {
      "epoch": 0.33748041655146993,
      "grad_norm": 0.37550538778305054,
      "learning_rate": 1.864798506223287e-05,
      "loss": 0.6264,
      "step": 10986
    },
    {
      "epoch": 0.33751113568641905,
      "grad_norm": 0.31911855936050415,
      "learning_rate": 1.8647742389375323e-05,
      "loss": 0.577,
      "step": 10987
    },
    {
      "epoch": 0.3375418548213682,
      "grad_norm": 0.35962316393852234,
      "learning_rate": 1.8647499696320373e-05,
      "loss": 0.6209,
      "step": 10988
    },
    {
      "epoch": 0.3375725739563174,
      "grad_norm": 0.3588690161705017,
      "learning_rate": 1.8647256983068576e-05,
      "loss": 0.5322,
      "step": 10989
    },
    {
      "epoch": 0.3376032930912666,
      "grad_norm": 0.3337661623954773,
      "learning_rate": 1.8647014249620516e-05,
      "loss": 0.5666,
      "step": 10990
    },
    {
      "epoch": 0.3376340122262157,
      "grad_norm": 0.41163039207458496,
      "learning_rate": 1.8646771495976744e-05,
      "loss": 0.6076,
      "step": 10991
    },
    {
      "epoch": 0.33766473136116487,
      "grad_norm": 0.69966721534729,
      "learning_rate": 1.8646528722137836e-05,
      "loss": 0.5944,
      "step": 10992
    },
    {
      "epoch": 0.33769545049611405,
      "grad_norm": 0.35384923219680786,
      "learning_rate": 1.864628592810435e-05,
      "loss": 0.5824,
      "step": 10993
    },
    {
      "epoch": 0.33772616963106317,
      "grad_norm": 2.094980478286743,
      "learning_rate": 1.864604311387687e-05,
      "loss": 0.5665,
      "step": 10994
    },
    {
      "epoch": 0.33775688876601234,
      "grad_norm": 0.3644348084926605,
      "learning_rate": 1.8645800279455946e-05,
      "loss": 0.5883,
      "step": 10995
    },
    {
      "epoch": 0.3377876079009615,
      "grad_norm": 0.3173195421695709,
      "learning_rate": 1.864555742484215e-05,
      "loss": 0.6402,
      "step": 10996
    },
    {
      "epoch": 0.3378183270359107,
      "grad_norm": 0.3439981937408447,
      "learning_rate": 1.8645314550036054e-05,
      "loss": 0.5555,
      "step": 10997
    },
    {
      "epoch": 0.3378490461708598,
      "grad_norm": 0.34280335903167725,
      "learning_rate": 1.864507165503822e-05,
      "loss": 0.6046,
      "step": 10998
    },
    {
      "epoch": 0.337879765305809,
      "grad_norm": 0.38314467668533325,
      "learning_rate": 1.864482873984922e-05,
      "loss": 0.5658,
      "step": 10999
    },
    {
      "epoch": 0.33791048444075816,
      "grad_norm": 0.3391181528568268,
      "learning_rate": 1.8644585804469616e-05,
      "loss": 0.6004,
      "step": 11000
    },
    {
      "epoch": 0.3379412035757073,
      "grad_norm": 0.3410094976425171,
      "learning_rate": 1.8644342848899983e-05,
      "loss": 0.6088,
      "step": 11001
    },
    {
      "epoch": 0.33797192271065646,
      "grad_norm": 0.30816569924354553,
      "learning_rate": 1.864409987314088e-05,
      "loss": 0.5516,
      "step": 11002
    },
    {
      "epoch": 0.33800264184560563,
      "grad_norm": 0.4419858157634735,
      "learning_rate": 1.8643856877192876e-05,
      "loss": 0.6223,
      "step": 11003
    },
    {
      "epoch": 0.3380333609805548,
      "grad_norm": 0.3581450879573822,
      "learning_rate": 1.8643613861056544e-05,
      "loss": 0.5593,
      "step": 11004
    },
    {
      "epoch": 0.33806408011550393,
      "grad_norm": 1.5918728113174438,
      "learning_rate": 1.8643370824732446e-05,
      "loss": 0.5961,
      "step": 11005
    },
    {
      "epoch": 0.3380947992504531,
      "grad_norm": 0.33549004793167114,
      "learning_rate": 1.864312776822115e-05,
      "loss": 0.5692,
      "step": 11006
    },
    {
      "epoch": 0.3381255183854023,
      "grad_norm": 0.33342182636260986,
      "learning_rate": 1.864288469152323e-05,
      "loss": 0.4973,
      "step": 11007
    },
    {
      "epoch": 0.3381562375203514,
      "grad_norm": 0.3189191222190857,
      "learning_rate": 1.864264159463925e-05,
      "loss": 0.5396,
      "step": 11008
    },
    {
      "epoch": 0.3381869566553006,
      "grad_norm": 0.4685843288898468,
      "learning_rate": 1.8642398477569774e-05,
      "loss": 0.5651,
      "step": 11009
    },
    {
      "epoch": 0.33821767579024975,
      "grad_norm": 0.34129664301872253,
      "learning_rate": 1.864215534031537e-05,
      "loss": 0.5725,
      "step": 11010
    },
    {
      "epoch": 0.3382483949251989,
      "grad_norm": 0.35004666447639465,
      "learning_rate": 1.8641912182876614e-05,
      "loss": 0.6296,
      "step": 11011
    },
    {
      "epoch": 0.33827911406014805,
      "grad_norm": 0.3638405203819275,
      "learning_rate": 1.8641669005254067e-05,
      "loss": 0.5628,
      "step": 11012
    },
    {
      "epoch": 0.3383098331950972,
      "grad_norm": 0.33280259370803833,
      "learning_rate": 1.8641425807448298e-05,
      "loss": 0.6158,
      "step": 11013
    },
    {
      "epoch": 0.3383405523300464,
      "grad_norm": 0.3526116609573364,
      "learning_rate": 1.8641182589459875e-05,
      "loss": 0.5496,
      "step": 11014
    },
    {
      "epoch": 0.33837127146499557,
      "grad_norm": 0.35919174551963806,
      "learning_rate": 1.8640939351289367e-05,
      "loss": 0.4933,
      "step": 11015
    },
    {
      "epoch": 0.3384019905999447,
      "grad_norm": 0.3377506136894226,
      "learning_rate": 1.864069609293734e-05,
      "loss": 0.5154,
      "step": 11016
    },
    {
      "epoch": 0.33843270973489387,
      "grad_norm": 0.33010929822921753,
      "learning_rate": 1.8640452814404368e-05,
      "loss": 0.5765,
      "step": 11017
    },
    {
      "epoch": 0.33846342886984304,
      "grad_norm": 0.38478830456733704,
      "learning_rate": 1.8640209515691012e-05,
      "loss": 0.5133,
      "step": 11018
    },
    {
      "epoch": 0.33849414800479216,
      "grad_norm": 0.3408884108066559,
      "learning_rate": 1.8639966196797844e-05,
      "loss": 0.5467,
      "step": 11019
    },
    {
      "epoch": 0.33852486713974134,
      "grad_norm": 0.49715012311935425,
      "learning_rate": 1.863972285772543e-05,
      "loss": 0.5156,
      "step": 11020
    },
    {
      "epoch": 0.3385555862746905,
      "grad_norm": 0.31690165400505066,
      "learning_rate": 1.8639479498474342e-05,
      "loss": 0.5857,
      "step": 11021
    },
    {
      "epoch": 0.3385863054096397,
      "grad_norm": 0.4242798388004303,
      "learning_rate": 1.8639236119045146e-05,
      "loss": 0.5237,
      "step": 11022
    },
    {
      "epoch": 0.3386170245445888,
      "grad_norm": 0.3345758020877838,
      "learning_rate": 1.8638992719438408e-05,
      "loss": 0.5842,
      "step": 11023
    },
    {
      "epoch": 0.338647743679538,
      "grad_norm": 0.32147929072380066,
      "learning_rate": 1.8638749299654702e-05,
      "loss": 0.5299,
      "step": 11024
    },
    {
      "epoch": 0.33867846281448716,
      "grad_norm": 0.35453954339027405,
      "learning_rate": 1.8638505859694594e-05,
      "loss": 0.6693,
      "step": 11025
    },
    {
      "epoch": 0.3387091819494363,
      "grad_norm": 0.47281602025032043,
      "learning_rate": 1.863826239955865e-05,
      "loss": 0.6733,
      "step": 11026
    },
    {
      "epoch": 0.33873990108438545,
      "grad_norm": 0.34411466121673584,
      "learning_rate": 1.8638018919247442e-05,
      "loss": 0.644,
      "step": 11027
    },
    {
      "epoch": 0.33877062021933463,
      "grad_norm": 0.35835275053977966,
      "learning_rate": 1.8637775418761537e-05,
      "loss": 0.6007,
      "step": 11028
    },
    {
      "epoch": 0.3388013393542838,
      "grad_norm": 0.3387131094932556,
      "learning_rate": 1.8637531898101503e-05,
      "loss": 0.6317,
      "step": 11029
    },
    {
      "epoch": 0.3388320584892329,
      "grad_norm": 0.3222666084766388,
      "learning_rate": 1.8637288357267915e-05,
      "loss": 0.5497,
      "step": 11030
    },
    {
      "epoch": 0.3388627776241821,
      "grad_norm": 0.3386552333831787,
      "learning_rate": 1.8637044796261333e-05,
      "loss": 0.5295,
      "step": 11031
    },
    {
      "epoch": 0.3388934967591313,
      "grad_norm": 0.38005682826042175,
      "learning_rate": 1.863680121508233e-05,
      "loss": 0.5673,
      "step": 11032
    },
    {
      "epoch": 0.33892421589408045,
      "grad_norm": 0.3063769042491913,
      "learning_rate": 1.8636557613731474e-05,
      "loss": 0.6039,
      "step": 11033
    },
    {
      "epoch": 0.33895493502902957,
      "grad_norm": 0.3599638342857361,
      "learning_rate": 1.8636313992209335e-05,
      "loss": 0.4753,
      "step": 11034
    },
    {
      "epoch": 0.33898565416397874,
      "grad_norm": 0.33506882190704346,
      "learning_rate": 1.8636070350516485e-05,
      "loss": 0.64,
      "step": 11035
    },
    {
      "epoch": 0.3390163732989279,
      "grad_norm": 0.33065932989120483,
      "learning_rate": 1.8635826688653487e-05,
      "loss": 0.5524,
      "step": 11036
    },
    {
      "epoch": 0.33904709243387704,
      "grad_norm": 0.40019503235816956,
      "learning_rate": 1.8635583006620913e-05,
      "loss": 0.6273,
      "step": 11037
    },
    {
      "epoch": 0.3390778115688262,
      "grad_norm": 0.3395794630050659,
      "learning_rate": 1.863533930441933e-05,
      "loss": 0.6404,
      "step": 11038
    },
    {
      "epoch": 0.3391085307037754,
      "grad_norm": 0.31555625796318054,
      "learning_rate": 1.8635095582049308e-05,
      "loss": 0.542,
      "step": 11039
    },
    {
      "epoch": 0.33913924983872457,
      "grad_norm": 0.3160875141620636,
      "learning_rate": 1.863485183951142e-05,
      "loss": 0.567,
      "step": 11040
    },
    {
      "epoch": 0.3391699689736737,
      "grad_norm": 0.332449734210968,
      "learning_rate": 1.8634608076806232e-05,
      "loss": 0.5305,
      "step": 11041
    },
    {
      "epoch": 0.33920068810862286,
      "grad_norm": 0.3688943684101105,
      "learning_rate": 1.8634364293934314e-05,
      "loss": 0.6316,
      "step": 11042
    },
    {
      "epoch": 0.33923140724357204,
      "grad_norm": 0.343375563621521,
      "learning_rate": 1.8634120490896233e-05,
      "loss": 0.4962,
      "step": 11043
    },
    {
      "epoch": 0.33926212637852116,
      "grad_norm": 0.2909402847290039,
      "learning_rate": 1.8633876667692564e-05,
      "loss": 0.5429,
      "step": 11044
    },
    {
      "epoch": 0.33929284551347033,
      "grad_norm": 0.35118696093559265,
      "learning_rate": 1.863363282432387e-05,
      "loss": 0.5873,
      "step": 11045
    },
    {
      "epoch": 0.3393235646484195,
      "grad_norm": 0.3540039360523224,
      "learning_rate": 1.8633388960790726e-05,
      "loss": 0.6079,
      "step": 11046
    },
    {
      "epoch": 0.3393542837833687,
      "grad_norm": 0.6016457676887512,
      "learning_rate": 1.8633145077093696e-05,
      "loss": 0.5813,
      "step": 11047
    },
    {
      "epoch": 0.3393850029183178,
      "grad_norm": 0.3109283745288849,
      "learning_rate": 1.8632901173233354e-05,
      "loss": 0.52,
      "step": 11048
    },
    {
      "epoch": 0.339415722053267,
      "grad_norm": 0.35506173968315125,
      "learning_rate": 1.863265724921027e-05,
      "loss": 0.6037,
      "step": 11049
    },
    {
      "epoch": 0.33944644118821615,
      "grad_norm": 0.3438050448894501,
      "learning_rate": 1.863241330502501e-05,
      "loss": 0.5872,
      "step": 11050
    },
    {
      "epoch": 0.3394771603231653,
      "grad_norm": 0.4035172760486603,
      "learning_rate": 1.863216934067815e-05,
      "loss": 0.6325,
      "step": 11051
    },
    {
      "epoch": 0.33950787945811445,
      "grad_norm": 0.3438054323196411,
      "learning_rate": 1.863192535617025e-05,
      "loss": 0.6495,
      "step": 11052
    },
    {
      "epoch": 0.3395385985930636,
      "grad_norm": 0.34196579456329346,
      "learning_rate": 1.863168135150189e-05,
      "loss": 0.6008,
      "step": 11053
    },
    {
      "epoch": 0.3395693177280128,
      "grad_norm": 0.349669486284256,
      "learning_rate": 1.8631437326673635e-05,
      "loss": 0.562,
      "step": 11054
    },
    {
      "epoch": 0.3396000368629619,
      "grad_norm": 0.3356345295906067,
      "learning_rate": 1.863119328168605e-05,
      "loss": 0.6225,
      "step": 11055
    },
    {
      "epoch": 0.3396307559979111,
      "grad_norm": 0.37015679478645325,
      "learning_rate": 1.8630949216539716e-05,
      "loss": 0.6329,
      "step": 11056
    },
    {
      "epoch": 0.33966147513286027,
      "grad_norm": 0.36511096358299255,
      "learning_rate": 1.8630705131235193e-05,
      "loss": 0.5771,
      "step": 11057
    },
    {
      "epoch": 0.33969219426780944,
      "grad_norm": 0.3766273856163025,
      "learning_rate": 1.8630461025773062e-05,
      "loss": 0.572,
      "step": 11058
    },
    {
      "epoch": 0.33972291340275856,
      "grad_norm": 0.3525831699371338,
      "learning_rate": 1.863021690015388e-05,
      "loss": 0.5089,
      "step": 11059
    },
    {
      "epoch": 0.33975363253770774,
      "grad_norm": 0.4090384840965271,
      "learning_rate": 1.862997275437823e-05,
      "loss": 0.6026,
      "step": 11060
    },
    {
      "epoch": 0.3397843516726569,
      "grad_norm": 0.3799320459365845,
      "learning_rate": 1.8629728588446666e-05,
      "loss": 0.6246,
      "step": 11061
    },
    {
      "epoch": 0.33981507080760603,
      "grad_norm": 0.33971408009529114,
      "learning_rate": 1.8629484402359777e-05,
      "loss": 0.5315,
      "step": 11062
    },
    {
      "epoch": 0.3398457899425552,
      "grad_norm": 0.349869042634964,
      "learning_rate": 1.8629240196118123e-05,
      "loss": 0.4634,
      "step": 11063
    },
    {
      "epoch": 0.3398765090775044,
      "grad_norm": 0.3581966757774353,
      "learning_rate": 1.8628995969722275e-05,
      "loss": 0.6208,
      "step": 11064
    },
    {
      "epoch": 0.33990722821245356,
      "grad_norm": 0.33979761600494385,
      "learning_rate": 1.8628751723172803e-05,
      "loss": 0.5982,
      "step": 11065
    },
    {
      "epoch": 0.3399379473474027,
      "grad_norm": 0.38578012585639954,
      "learning_rate": 1.8628507456470276e-05,
      "loss": 0.5067,
      "step": 11066
    },
    {
      "epoch": 0.33996866648235186,
      "grad_norm": 0.32075613737106323,
      "learning_rate": 1.8628263169615273e-05,
      "loss": 0.5767,
      "step": 11067
    },
    {
      "epoch": 0.33999938561730103,
      "grad_norm": 0.3237263858318329,
      "learning_rate": 1.8628018862608356e-05,
      "loss": 0.5462,
      "step": 11068
    },
    {
      "epoch": 0.34003010475225015,
      "grad_norm": 0.3333624005317688,
      "learning_rate": 1.86277745354501e-05,
      "loss": 0.5709,
      "step": 11069
    },
    {
      "epoch": 0.3400608238871993,
      "grad_norm": 0.353435218334198,
      "learning_rate": 1.8627530188141074e-05,
      "loss": 0.5212,
      "step": 11070
    },
    {
      "epoch": 0.3400915430221485,
      "grad_norm": 0.3702336549758911,
      "learning_rate": 1.8627285820681846e-05,
      "loss": 0.5122,
      "step": 11071
    },
    {
      "epoch": 0.3401222621570977,
      "grad_norm": 0.3219890892505646,
      "learning_rate": 1.8627041433072993e-05,
      "loss": 0.5975,
      "step": 11072
    },
    {
      "epoch": 0.3401529812920468,
      "grad_norm": 0.3582148551940918,
      "learning_rate": 1.8626797025315078e-05,
      "loss": 0.5776,
      "step": 11073
    },
    {
      "epoch": 0.34018370042699597,
      "grad_norm": 0.33101049065589905,
      "learning_rate": 1.862655259740868e-05,
      "loss": 0.6125,
      "step": 11074
    },
    {
      "epoch": 0.34021441956194515,
      "grad_norm": 0.3608841001987457,
      "learning_rate": 1.8626308149354365e-05,
      "loss": 0.6563,
      "step": 11075
    },
    {
      "epoch": 0.3402451386968943,
      "grad_norm": 0.37662819027900696,
      "learning_rate": 1.86260636811527e-05,
      "loss": 0.5603,
      "step": 11076
    },
    {
      "epoch": 0.34027585783184344,
      "grad_norm": 0.33038198947906494,
      "learning_rate": 1.8625819192804268e-05,
      "loss": 0.6225,
      "step": 11077
    },
    {
      "epoch": 0.3403065769667926,
      "grad_norm": 0.3986881375312805,
      "learning_rate": 1.862557468430963e-05,
      "loss": 0.6234,
      "step": 11078
    },
    {
      "epoch": 0.3403372961017418,
      "grad_norm": 0.3569243550300598,
      "learning_rate": 1.862533015566936e-05,
      "loss": 0.6045,
      "step": 11079
    },
    {
      "epoch": 0.3403680152366909,
      "grad_norm": 0.397916704416275,
      "learning_rate": 1.8625085606884027e-05,
      "loss": 0.6103,
      "step": 11080
    },
    {
      "epoch": 0.3403987343716401,
      "grad_norm": 0.3846897780895233,
      "learning_rate": 1.8624841037954205e-05,
      "loss": 0.5336,
      "step": 11081
    },
    {
      "epoch": 0.34042945350658926,
      "grad_norm": 0.3215053379535675,
      "learning_rate": 1.862459644888047e-05,
      "loss": 0.551,
      "step": 11082
    },
    {
      "epoch": 0.34046017264153844,
      "grad_norm": 0.3341764509677887,
      "learning_rate": 1.8624351839663378e-05,
      "loss": 0.5819,
      "step": 11083
    },
    {
      "epoch": 0.34049089177648756,
      "grad_norm": 0.3392646014690399,
      "learning_rate": 1.8624107210303518e-05,
      "loss": 0.5757,
      "step": 11084
    },
    {
      "epoch": 0.34052161091143673,
      "grad_norm": 0.38126063346862793,
      "learning_rate": 1.8623862560801452e-05,
      "loss": 0.6286,
      "step": 11085
    },
    {
      "epoch": 0.3405523300463859,
      "grad_norm": 0.43984255194664,
      "learning_rate": 1.8623617891157752e-05,
      "loss": 0.5892,
      "step": 11086
    },
    {
      "epoch": 0.34058304918133503,
      "grad_norm": 1.0877629518508911,
      "learning_rate": 1.8623373201372988e-05,
      "loss": 0.5688,
      "step": 11087
    },
    {
      "epoch": 0.3406137683162842,
      "grad_norm": 0.34341078996658325,
      "learning_rate": 1.8623128491447735e-05,
      "loss": 0.6009,
      "step": 11088
    },
    {
      "epoch": 0.3406444874512334,
      "grad_norm": 0.38723084330558777,
      "learning_rate": 1.8622883761382562e-05,
      "loss": 0.5808,
      "step": 11089
    },
    {
      "epoch": 0.34067520658618256,
      "grad_norm": 0.34634119272232056,
      "learning_rate": 1.862263901117804e-05,
      "loss": 0.5435,
      "step": 11090
    },
    {
      "epoch": 0.3407059257211317,
      "grad_norm": 0.36457398533821106,
      "learning_rate": 1.862239424083475e-05,
      "loss": 0.5423,
      "step": 11091
    },
    {
      "epoch": 0.34073664485608085,
      "grad_norm": 0.37311074137687683,
      "learning_rate": 1.862214945035325e-05,
      "loss": 0.6413,
      "step": 11092
    },
    {
      "epoch": 0.34076736399103,
      "grad_norm": 0.34568992257118225,
      "learning_rate": 1.862190463973412e-05,
      "loss": 0.5629,
      "step": 11093
    },
    {
      "epoch": 0.34079808312597915,
      "grad_norm": 0.34738636016845703,
      "learning_rate": 1.8621659808977925e-05,
      "loss": 0.5576,
      "step": 11094
    },
    {
      "epoch": 0.3408288022609283,
      "grad_norm": 0.32529547810554504,
      "learning_rate": 1.8621414958085247e-05,
      "loss": 0.5925,
      "step": 11095
    },
    {
      "epoch": 0.3408595213958775,
      "grad_norm": 0.3720070421695709,
      "learning_rate": 1.862117008705665e-05,
      "loss": 0.6468,
      "step": 11096
    },
    {
      "epoch": 0.34089024053082667,
      "grad_norm": 0.31440281867980957,
      "learning_rate": 1.8620925195892708e-05,
      "loss": 0.5314,
      "step": 11097
    },
    {
      "epoch": 0.3409209596657758,
      "grad_norm": 0.436015248298645,
      "learning_rate": 1.862068028459399e-05,
      "loss": 0.6796,
      "step": 11098
    },
    {
      "epoch": 0.34095167880072497,
      "grad_norm": 0.387199342250824,
      "learning_rate": 1.8620435353161078e-05,
      "loss": 0.5944,
      "step": 11099
    },
    {
      "epoch": 0.34098239793567414,
      "grad_norm": 0.3803299367427826,
      "learning_rate": 1.8620190401594534e-05,
      "loss": 0.6009,
      "step": 11100
    },
    {
      "epoch": 0.3410131170706233,
      "grad_norm": 0.3533187508583069,
      "learning_rate": 1.861994542989493e-05,
      "loss": 0.5797,
      "step": 11101
    },
    {
      "epoch": 0.34104383620557244,
      "grad_norm": 0.329806387424469,
      "learning_rate": 1.861970043806285e-05,
      "loss": 0.5087,
      "step": 11102
    },
    {
      "epoch": 0.3410745553405216,
      "grad_norm": 0.3524596393108368,
      "learning_rate": 1.861945542609885e-05,
      "loss": 0.6064,
      "step": 11103
    },
    {
      "epoch": 0.3411052744754708,
      "grad_norm": 0.32363978028297424,
      "learning_rate": 1.861921039400351e-05,
      "loss": 0.6324,
      "step": 11104
    },
    {
      "epoch": 0.3411359936104199,
      "grad_norm": 0.3449985384941101,
      "learning_rate": 1.8618965341777408e-05,
      "loss": 0.5818,
      "step": 11105
    },
    {
      "epoch": 0.3411667127453691,
      "grad_norm": 0.32888537645339966,
      "learning_rate": 1.8618720269421106e-05,
      "loss": 0.5699,
      "step": 11106
    },
    {
      "epoch": 0.34119743188031826,
      "grad_norm": 0.3665076196193695,
      "learning_rate": 1.861847517693518e-05,
      "loss": 0.5566,
      "step": 11107
    },
    {
      "epoch": 0.34122815101526743,
      "grad_norm": 0.31529533863067627,
      "learning_rate": 1.8618230064320205e-05,
      "loss": 0.6221,
      "step": 11108
    },
    {
      "epoch": 0.34125887015021655,
      "grad_norm": 0.3532223701477051,
      "learning_rate": 1.8617984931576752e-05,
      "loss": 0.618,
      "step": 11109
    },
    {
      "epoch": 0.34128958928516573,
      "grad_norm": 0.42688506841659546,
      "learning_rate": 1.861773977870539e-05,
      "loss": 0.5504,
      "step": 11110
    },
    {
      "epoch": 0.3413203084201149,
      "grad_norm": 0.37073132395744324,
      "learning_rate": 1.86174946057067e-05,
      "loss": 0.6374,
      "step": 11111
    },
    {
      "epoch": 0.341351027555064,
      "grad_norm": 0.3597749173641205,
      "learning_rate": 1.861724941258125e-05,
      "loss": 0.6309,
      "step": 11112
    },
    {
      "epoch": 0.3413817466900132,
      "grad_norm": 0.3593454658985138,
      "learning_rate": 1.861700419932961e-05,
      "loss": 0.5908,
      "step": 11113
    },
    {
      "epoch": 0.3414124658249624,
      "grad_norm": 0.37456005811691284,
      "learning_rate": 1.8616758965952354e-05,
      "loss": 0.579,
      "step": 11114
    },
    {
      "epoch": 0.34144318495991155,
      "grad_norm": 0.3402197062969208,
      "learning_rate": 1.8616513712450057e-05,
      "loss": 0.5968,
      "step": 11115
    },
    {
      "epoch": 0.34147390409486067,
      "grad_norm": 0.309853732585907,
      "learning_rate": 1.861626843882329e-05,
      "loss": 0.5528,
      "step": 11116
    },
    {
      "epoch": 0.34150462322980984,
      "grad_norm": 0.4240471422672272,
      "learning_rate": 1.8616023145072626e-05,
      "loss": 0.6023,
      "step": 11117
    },
    {
      "epoch": 0.341535342364759,
      "grad_norm": 0.41890910267829895,
      "learning_rate": 1.8615777831198635e-05,
      "loss": 0.5387,
      "step": 11118
    },
    {
      "epoch": 0.3415660614997082,
      "grad_norm": 0.3436014652252197,
      "learning_rate": 1.8615532497201898e-05,
      "loss": 0.4585,
      "step": 11119
    },
    {
      "epoch": 0.3415967806346573,
      "grad_norm": 0.35184210538864136,
      "learning_rate": 1.861528714308298e-05,
      "loss": 0.5669,
      "step": 11120
    },
    {
      "epoch": 0.3416274997696065,
      "grad_norm": 0.3153057098388672,
      "learning_rate": 1.861504176884246e-05,
      "loss": 0.6079,
      "step": 11121
    },
    {
      "epoch": 0.34165821890455567,
      "grad_norm": 0.35655996203422546,
      "learning_rate": 1.8614796374480905e-05,
      "loss": 0.6727,
      "step": 11122
    },
    {
      "epoch": 0.3416889380395048,
      "grad_norm": 0.353419691324234,
      "learning_rate": 1.8614550959998895e-05,
      "loss": 0.5936,
      "step": 11123
    },
    {
      "epoch": 0.34171965717445396,
      "grad_norm": 0.3351269066333771,
      "learning_rate": 1.8614305525397e-05,
      "loss": 0.5111,
      "step": 11124
    },
    {
      "epoch": 0.34175037630940314,
      "grad_norm": 0.3439008593559265,
      "learning_rate": 1.8614060070675788e-05,
      "loss": 0.5423,
      "step": 11125
    },
    {
      "epoch": 0.3417810954443523,
      "grad_norm": 0.35411331057548523,
      "learning_rate": 1.861381459583584e-05,
      "loss": 0.6396,
      "step": 11126
    },
    {
      "epoch": 0.34181181457930143,
      "grad_norm": 0.3278159201145172,
      "learning_rate": 1.8613569100877727e-05,
      "loss": 0.5909,
      "step": 11127
    },
    {
      "epoch": 0.3418425337142506,
      "grad_norm": 0.3639346659183502,
      "learning_rate": 1.861332358580202e-05,
      "loss": 0.5921,
      "step": 11128
    },
    {
      "epoch": 0.3418732528491998,
      "grad_norm": 0.384227454662323,
      "learning_rate": 1.8613078050609297e-05,
      "loss": 0.596,
      "step": 11129
    },
    {
      "epoch": 0.3419039719841489,
      "grad_norm": 0.37164050340652466,
      "learning_rate": 1.8612832495300127e-05,
      "loss": 0.5539,
      "step": 11130
    },
    {
      "epoch": 0.3419346911190981,
      "grad_norm": 0.3934893012046814,
      "learning_rate": 1.8612586919875088e-05,
      "loss": 0.6164,
      "step": 11131
    },
    {
      "epoch": 0.34196541025404725,
      "grad_norm": 0.33525359630584717,
      "learning_rate": 1.8612341324334747e-05,
      "loss": 0.6407,
      "step": 11132
    },
    {
      "epoch": 0.34199612938899643,
      "grad_norm": 0.32964587211608887,
      "learning_rate": 1.861209570867968e-05,
      "loss": 0.5533,
      "step": 11133
    },
    {
      "epoch": 0.34202684852394555,
      "grad_norm": 0.36004775762557983,
      "learning_rate": 1.8611850072910465e-05,
      "loss": 0.5956,
      "step": 11134
    },
    {
      "epoch": 0.3420575676588947,
      "grad_norm": 0.33482539653778076,
      "learning_rate": 1.8611604417027673e-05,
      "loss": 0.595,
      "step": 11135
    },
    {
      "epoch": 0.3420882867938439,
      "grad_norm": 0.3980102241039276,
      "learning_rate": 1.8611358741031874e-05,
      "loss": 0.6425,
      "step": 11136
    },
    {
      "epoch": 0.342119005928793,
      "grad_norm": 0.34282219409942627,
      "learning_rate": 1.861111304492365e-05,
      "loss": 0.5576,
      "step": 11137
    },
    {
      "epoch": 0.3421497250637422,
      "grad_norm": 0.34741151332855225,
      "learning_rate": 1.8610867328703568e-05,
      "loss": 0.5464,
      "step": 11138
    },
    {
      "epoch": 0.34218044419869137,
      "grad_norm": 0.3520882725715637,
      "learning_rate": 1.8610621592372202e-05,
      "loss": 0.5824,
      "step": 11139
    },
    {
      "epoch": 0.34221116333364054,
      "grad_norm": 0.47586777806282043,
      "learning_rate": 1.861037583593013e-05,
      "loss": 0.5916,
      "step": 11140
    },
    {
      "epoch": 0.34224188246858966,
      "grad_norm": 0.36276936531066895,
      "learning_rate": 1.8610130059377923e-05,
      "loss": 0.5722,
      "step": 11141
    },
    {
      "epoch": 0.34227260160353884,
      "grad_norm": 0.35634395480155945,
      "learning_rate": 1.8609884262716158e-05,
      "loss": 0.5475,
      "step": 11142
    },
    {
      "epoch": 0.342303320738488,
      "grad_norm": 0.4217076897621155,
      "learning_rate": 1.8609638445945407e-05,
      "loss": 0.5927,
      "step": 11143
    },
    {
      "epoch": 0.3423340398734372,
      "grad_norm": 0.3871571123600006,
      "learning_rate": 1.860939260906624e-05,
      "loss": 0.5914,
      "step": 11144
    },
    {
      "epoch": 0.3423647590083863,
      "grad_norm": 0.33531180024147034,
      "learning_rate": 1.860914675207924e-05,
      "loss": 0.5456,
      "step": 11145
    },
    {
      "epoch": 0.3423954781433355,
      "grad_norm": 0.48474451899528503,
      "learning_rate": 1.8608900874984974e-05,
      "loss": 0.5879,
      "step": 11146
    },
    {
      "epoch": 0.34242619727828466,
      "grad_norm": 0.3741089701652527,
      "learning_rate": 1.8608654977784017e-05,
      "loss": 0.548,
      "step": 11147
    },
    {
      "epoch": 0.3424569164132338,
      "grad_norm": 0.38475582003593445,
      "learning_rate": 1.8608409060476947e-05,
      "loss": 0.5686,
      "step": 11148
    },
    {
      "epoch": 0.34248763554818296,
      "grad_norm": 0.35391002893447876,
      "learning_rate": 1.860816312306434e-05,
      "loss": 0.5365,
      "step": 11149
    },
    {
      "epoch": 0.34251835468313213,
      "grad_norm": 0.33900707960128784,
      "learning_rate": 1.860791716554676e-05,
      "loss": 0.6506,
      "step": 11150
    },
    {
      "epoch": 0.3425490738180813,
      "grad_norm": 0.40120187401771545,
      "learning_rate": 1.8607671187924795e-05,
      "loss": 0.6486,
      "step": 11151
    },
    {
      "epoch": 0.3425797929530304,
      "grad_norm": 0.41863295435905457,
      "learning_rate": 1.8607425190199008e-05,
      "loss": 0.4805,
      "step": 11152
    },
    {
      "epoch": 0.3426105120879796,
      "grad_norm": 0.33172130584716797,
      "learning_rate": 1.860717917236998e-05,
      "loss": 0.6059,
      "step": 11153
    },
    {
      "epoch": 0.3426412312229288,
      "grad_norm": 0.36837539076805115,
      "learning_rate": 1.8606933134438284e-05,
      "loss": 0.5573,
      "step": 11154
    },
    {
      "epoch": 0.3426719503578779,
      "grad_norm": 2.698664903640747,
      "learning_rate": 1.8606687076404497e-05,
      "loss": 0.5937,
      "step": 11155
    },
    {
      "epoch": 0.3427026694928271,
      "grad_norm": 0.3552975654602051,
      "learning_rate": 1.8606440998269187e-05,
      "loss": 0.6694,
      "step": 11156
    },
    {
      "epoch": 0.34273338862777625,
      "grad_norm": 0.38292258977890015,
      "learning_rate": 1.8606194900032936e-05,
      "loss": 0.5444,
      "step": 11157
    },
    {
      "epoch": 0.3427641077627254,
      "grad_norm": 0.32747316360473633,
      "learning_rate": 1.860594878169631e-05,
      "loss": 0.6881,
      "step": 11158
    },
    {
      "epoch": 0.34279482689767454,
      "grad_norm": 0.3625706732273102,
      "learning_rate": 1.8605702643259896e-05,
      "loss": 0.6028,
      "step": 11159
    },
    {
      "epoch": 0.3428255460326237,
      "grad_norm": 0.34614983201026917,
      "learning_rate": 1.8605456484724263e-05,
      "loss": 0.6218,
      "step": 11160
    },
    {
      "epoch": 0.3428562651675729,
      "grad_norm": 0.3427746593952179,
      "learning_rate": 1.860521030608998e-05,
      "loss": 0.5447,
      "step": 11161
    },
    {
      "epoch": 0.34288698430252207,
      "grad_norm": 0.4864635169506073,
      "learning_rate": 1.8604964107357632e-05,
      "loss": 0.6335,
      "step": 11162
    },
    {
      "epoch": 0.3429177034374712,
      "grad_norm": 0.3370722532272339,
      "learning_rate": 1.860471788852779e-05,
      "loss": 0.6029,
      "step": 11163
    },
    {
      "epoch": 0.34294842257242036,
      "grad_norm": 0.4125654995441437,
      "learning_rate": 1.8604471649601024e-05,
      "loss": 0.5331,
      "step": 11164
    },
    {
      "epoch": 0.34297914170736954,
      "grad_norm": 0.3870820105075836,
      "learning_rate": 1.8604225390577916e-05,
      "loss": 0.6349,
      "step": 11165
    },
    {
      "epoch": 0.34300986084231866,
      "grad_norm": 0.376215398311615,
      "learning_rate": 1.8603979111459035e-05,
      "loss": 0.5467,
      "step": 11166
    },
    {
      "epoch": 0.34304057997726783,
      "grad_norm": 0.3559834659099579,
      "learning_rate": 1.8603732812244966e-05,
      "loss": 0.5686,
      "step": 11167
    },
    {
      "epoch": 0.343071299112217,
      "grad_norm": 0.5057979226112366,
      "learning_rate": 1.8603486492936276e-05,
      "loss": 0.604,
      "step": 11168
    },
    {
      "epoch": 0.3431020182471662,
      "grad_norm": 0.34592190384864807,
      "learning_rate": 1.8603240153533542e-05,
      "loss": 0.5617,
      "step": 11169
    },
    {
      "epoch": 0.3431327373821153,
      "grad_norm": 0.30156487226486206,
      "learning_rate": 1.8602993794037337e-05,
      "loss": 0.5494,
      "step": 11170
    },
    {
      "epoch": 0.3431634565170645,
      "grad_norm": 0.34259510040283203,
      "learning_rate": 1.8602747414448243e-05,
      "loss": 0.6202,
      "step": 11171
    },
    {
      "epoch": 0.34319417565201366,
      "grad_norm": 0.40559443831443787,
      "learning_rate": 1.860250101476683e-05,
      "loss": 0.5545,
      "step": 11172
    },
    {
      "epoch": 0.3432248947869628,
      "grad_norm": 0.3801218569278717,
      "learning_rate": 1.8602254594993673e-05,
      "loss": 0.513,
      "step": 11173
    },
    {
      "epoch": 0.34325561392191195,
      "grad_norm": 0.3341814875602722,
      "learning_rate": 1.8602008155129355e-05,
      "loss": 0.6334,
      "step": 11174
    },
    {
      "epoch": 0.3432863330568611,
      "grad_norm": 0.3737727403640747,
      "learning_rate": 1.8601761695174443e-05,
      "loss": 0.635,
      "step": 11175
    },
    {
      "epoch": 0.3433170521918103,
      "grad_norm": 0.45473435521125793,
      "learning_rate": 1.8601515215129515e-05,
      "loss": 0.4685,
      "step": 11176
    },
    {
      "epoch": 0.3433477713267594,
      "grad_norm": 0.3221685290336609,
      "learning_rate": 1.8601268714995148e-05,
      "loss": 0.5156,
      "step": 11177
    },
    {
      "epoch": 0.3433784904617086,
      "grad_norm": 0.34333279728889465,
      "learning_rate": 1.860102219477192e-05,
      "loss": 0.5286,
      "step": 11178
    },
    {
      "epoch": 0.34340920959665777,
      "grad_norm": 0.35848498344421387,
      "learning_rate": 1.8600775654460398e-05,
      "loss": 0.5283,
      "step": 11179
    },
    {
      "epoch": 0.3434399287316069,
      "grad_norm": 0.3704570531845093,
      "learning_rate": 1.860052909406117e-05,
      "loss": 0.5726,
      "step": 11180
    },
    {
      "epoch": 0.34347064786655607,
      "grad_norm": 0.3448808193206787,
      "learning_rate": 1.86002825135748e-05,
      "loss": 0.5344,
      "step": 11181
    },
    {
      "epoch": 0.34350136700150524,
      "grad_norm": 0.34196579456329346,
      "learning_rate": 1.8600035913001876e-05,
      "loss": 0.571,
      "step": 11182
    },
    {
      "epoch": 0.3435320861364544,
      "grad_norm": 0.34442174434661865,
      "learning_rate": 1.8599789292342964e-05,
      "loss": 0.6118,
      "step": 11183
    },
    {
      "epoch": 0.34356280527140354,
      "grad_norm": 0.3427630662918091,
      "learning_rate": 1.8599542651598643e-05,
      "loss": 0.5678,
      "step": 11184
    },
    {
      "epoch": 0.3435935244063527,
      "grad_norm": 0.3552021384239197,
      "learning_rate": 1.859929599076949e-05,
      "loss": 0.583,
      "step": 11185
    },
    {
      "epoch": 0.3436242435413019,
      "grad_norm": 0.35238149762153625,
      "learning_rate": 1.859904930985608e-05,
      "loss": 0.5585,
      "step": 11186
    },
    {
      "epoch": 0.34365496267625106,
      "grad_norm": 0.33924660086631775,
      "learning_rate": 1.8598802608858993e-05,
      "loss": 0.6018,
      "step": 11187
    },
    {
      "epoch": 0.3436856818112002,
      "grad_norm": 0.34806764125823975,
      "learning_rate": 1.85985558877788e-05,
      "loss": 0.6826,
      "step": 11188
    },
    {
      "epoch": 0.34371640094614936,
      "grad_norm": 0.33460476994514465,
      "learning_rate": 1.859830914661608e-05,
      "loss": 0.5426,
      "step": 11189
    },
    {
      "epoch": 0.34374712008109853,
      "grad_norm": 0.3422606587409973,
      "learning_rate": 1.8598062385371405e-05,
      "loss": 0.5795,
      "step": 11190
    },
    {
      "epoch": 0.34377783921604765,
      "grad_norm": 0.33373022079467773,
      "learning_rate": 1.8597815604045356e-05,
      "loss": 0.5494,
      "step": 11191
    },
    {
      "epoch": 0.34380855835099683,
      "grad_norm": 0.3859928846359253,
      "learning_rate": 1.859756880263851e-05,
      "loss": 0.6635,
      "step": 11192
    },
    {
      "epoch": 0.343839277485946,
      "grad_norm": 0.31303292512893677,
      "learning_rate": 1.8597321981151443e-05,
      "loss": 0.5164,
      "step": 11193
    },
    {
      "epoch": 0.3438699966208952,
      "grad_norm": 0.32232704758644104,
      "learning_rate": 1.8597075139584725e-05,
      "loss": 0.5215,
      "step": 11194
    },
    {
      "epoch": 0.3439007157558443,
      "grad_norm": 0.34424033761024475,
      "learning_rate": 1.859682827793894e-05,
      "loss": 0.5741,
      "step": 11195
    },
    {
      "epoch": 0.3439314348907935,
      "grad_norm": 0.34334006905555725,
      "learning_rate": 1.8596581396214666e-05,
      "loss": 0.5322,
      "step": 11196
    },
    {
      "epoch": 0.34396215402574265,
      "grad_norm": 0.439343124628067,
      "learning_rate": 1.859633449441247e-05,
      "loss": 0.619,
      "step": 11197
    },
    {
      "epoch": 0.34399287316069177,
      "grad_norm": 0.31768932938575745,
      "learning_rate": 1.8596087572532938e-05,
      "loss": 0.5914,
      "step": 11198
    },
    {
      "epoch": 0.34402359229564095,
      "grad_norm": 0.3302557170391083,
      "learning_rate": 1.8595840630576644e-05,
      "loss": 0.5807,
      "step": 11199
    },
    {
      "epoch": 0.3440543114305901,
      "grad_norm": 0.35169729590415955,
      "learning_rate": 1.8595593668544162e-05,
      "loss": 0.5746,
      "step": 11200
    },
    {
      "epoch": 0.3440850305655393,
      "grad_norm": 0.3714078962802887,
      "learning_rate": 1.859534668643607e-05,
      "loss": 0.592,
      "step": 11201
    },
    {
      "epoch": 0.3441157497004884,
      "grad_norm": 0.34859949350357056,
      "learning_rate": 1.8595099684252945e-05,
      "loss": 0.5723,
      "step": 11202
    },
    {
      "epoch": 0.3441464688354376,
      "grad_norm": 0.38575413823127747,
      "learning_rate": 1.8594852661995367e-05,
      "loss": 0.5724,
      "step": 11203
    },
    {
      "epoch": 0.34417718797038677,
      "grad_norm": 0.33201536536216736,
      "learning_rate": 1.8594605619663907e-05,
      "loss": 0.6505,
      "step": 11204
    },
    {
      "epoch": 0.3442079071053359,
      "grad_norm": 0.3625660240650177,
      "learning_rate": 1.859435855725915e-05,
      "loss": 0.5085,
      "step": 11205
    },
    {
      "epoch": 0.34423862624028506,
      "grad_norm": 0.36338937282562256,
      "learning_rate": 1.8594111474781664e-05,
      "loss": 0.5191,
      "step": 11206
    },
    {
      "epoch": 0.34426934537523424,
      "grad_norm": 0.36481937766075134,
      "learning_rate": 1.8593864372232034e-05,
      "loss": 0.6289,
      "step": 11207
    },
    {
      "epoch": 0.3443000645101834,
      "grad_norm": 0.33946773409843445,
      "learning_rate": 1.8593617249610832e-05,
      "loss": 0.5288,
      "step": 11208
    },
    {
      "epoch": 0.34433078364513253,
      "grad_norm": 0.3741496205329895,
      "learning_rate": 1.8593370106918636e-05,
      "loss": 0.546,
      "step": 11209
    },
    {
      "epoch": 0.3443615027800817,
      "grad_norm": 0.3364458680152893,
      "learning_rate": 1.8593122944156022e-05,
      "loss": 0.53,
      "step": 11210
    },
    {
      "epoch": 0.3443922219150309,
      "grad_norm": 0.32655152678489685,
      "learning_rate": 1.859287576132357e-05,
      "loss": 0.5286,
      "step": 11211
    },
    {
      "epoch": 0.34442294104998006,
      "grad_norm": 0.331542044878006,
      "learning_rate": 1.8592628558421858e-05,
      "loss": 0.5469,
      "step": 11212
    },
    {
      "epoch": 0.3444536601849292,
      "grad_norm": 0.34452229738235474,
      "learning_rate": 1.8592381335451468e-05,
      "loss": 0.4848,
      "step": 11213
    },
    {
      "epoch": 0.34448437931987835,
      "grad_norm": 0.3501024842262268,
      "learning_rate": 1.8592134092412962e-05,
      "loss": 0.5621,
      "step": 11214
    },
    {
      "epoch": 0.34451509845482753,
      "grad_norm": 0.3410688638687134,
      "learning_rate": 1.8591886829306932e-05,
      "loss": 0.5929,
      "step": 11215
    },
    {
      "epoch": 0.34454581758977665,
      "grad_norm": 0.41633424162864685,
      "learning_rate": 1.859163954613395e-05,
      "loss": 0.5701,
      "step": 11216
    },
    {
      "epoch": 0.3445765367247258,
      "grad_norm": 0.3624337315559387,
      "learning_rate": 1.859139224289459e-05,
      "loss": 0.7357,
      "step": 11217
    },
    {
      "epoch": 0.344607255859675,
      "grad_norm": 0.4070107340812683,
      "learning_rate": 1.8591144919589433e-05,
      "loss": 0.5536,
      "step": 11218
    },
    {
      "epoch": 0.3446379749946242,
      "grad_norm": 0.36096134781837463,
      "learning_rate": 1.8590897576219062e-05,
      "loss": 0.5927,
      "step": 11219
    },
    {
      "epoch": 0.3446686941295733,
      "grad_norm": 0.3674006462097168,
      "learning_rate": 1.8590650212784046e-05,
      "loss": 0.6853,
      "step": 11220
    },
    {
      "epoch": 0.34469941326452247,
      "grad_norm": 0.34657496213912964,
      "learning_rate": 1.8590402829284967e-05,
      "loss": 0.5833,
      "step": 11221
    },
    {
      "epoch": 0.34473013239947164,
      "grad_norm": 0.35482463240623474,
      "learning_rate": 1.8590155425722405e-05,
      "loss": 0.5512,
      "step": 11222
    },
    {
      "epoch": 0.34476085153442076,
      "grad_norm": 0.3270860016345978,
      "learning_rate": 1.8589908002096933e-05,
      "loss": 0.5893,
      "step": 11223
    },
    {
      "epoch": 0.34479157066936994,
      "grad_norm": 0.3118964433670044,
      "learning_rate": 1.858966055840913e-05,
      "loss": 0.5692,
      "step": 11224
    },
    {
      "epoch": 0.3448222898043191,
      "grad_norm": 0.32091259956359863,
      "learning_rate": 1.8589413094659575e-05,
      "loss": 0.6167,
      "step": 11225
    },
    {
      "epoch": 0.3448530089392683,
      "grad_norm": 0.38866788148880005,
      "learning_rate": 1.8589165610848848e-05,
      "loss": 0.6251,
      "step": 11226
    },
    {
      "epoch": 0.3448837280742174,
      "grad_norm": 0.3217463195323944,
      "learning_rate": 1.8588918106977524e-05,
      "loss": 0.5833,
      "step": 11227
    },
    {
      "epoch": 0.3449144472091666,
      "grad_norm": 0.36134350299835205,
      "learning_rate": 1.8588670583046183e-05,
      "loss": 0.6199,
      "step": 11228
    },
    {
      "epoch": 0.34494516634411576,
      "grad_norm": 0.3493403494358063,
      "learning_rate": 1.8588423039055398e-05,
      "loss": 0.63,
      "step": 11229
    },
    {
      "epoch": 0.34497588547906494,
      "grad_norm": 0.3260267674922943,
      "learning_rate": 1.8588175475005754e-05,
      "loss": 0.5485,
      "step": 11230
    },
    {
      "epoch": 0.34500660461401406,
      "grad_norm": 0.35145947337150574,
      "learning_rate": 1.858792789089783e-05,
      "loss": 0.601,
      "step": 11231
    },
    {
      "epoch": 0.34503732374896323,
      "grad_norm": 0.33157092332839966,
      "learning_rate": 1.8587680286732196e-05,
      "loss": 0.5897,
      "step": 11232
    },
    {
      "epoch": 0.3450680428839124,
      "grad_norm": 0.3617112338542938,
      "learning_rate": 1.8587432662509434e-05,
      "loss": 0.5532,
      "step": 11233
    },
    {
      "epoch": 0.3450987620188615,
      "grad_norm": 0.44221076369285583,
      "learning_rate": 1.8587185018230124e-05,
      "loss": 0.557,
      "step": 11234
    },
    {
      "epoch": 0.3451294811538107,
      "grad_norm": 0.33483797311782837,
      "learning_rate": 1.8586937353894846e-05,
      "loss": 0.5695,
      "step": 11235
    },
    {
      "epoch": 0.3451602002887599,
      "grad_norm": 0.3388766944408417,
      "learning_rate": 1.8586689669504175e-05,
      "loss": 0.5792,
      "step": 11236
    },
    {
      "epoch": 0.34519091942370905,
      "grad_norm": 0.3923039734363556,
      "learning_rate": 1.8586441965058692e-05,
      "loss": 0.5251,
      "step": 11237
    },
    {
      "epoch": 0.3452216385586582,
      "grad_norm": 0.3503727614879608,
      "learning_rate": 1.8586194240558972e-05,
      "loss": 0.5661,
      "step": 11238
    },
    {
      "epoch": 0.34525235769360735,
      "grad_norm": 0.33487585186958313,
      "learning_rate": 1.8585946496005594e-05,
      "loss": 0.5886,
      "step": 11239
    },
    {
      "epoch": 0.3452830768285565,
      "grad_norm": 0.4074653685092926,
      "learning_rate": 1.858569873139914e-05,
      "loss": 0.6235,
      "step": 11240
    },
    {
      "epoch": 0.34531379596350564,
      "grad_norm": 0.3628336787223816,
      "learning_rate": 1.8585450946740187e-05,
      "loss": 0.5189,
      "step": 11241
    },
    {
      "epoch": 0.3453445150984548,
      "grad_norm": 0.34823763370513916,
      "learning_rate": 1.8585203142029317e-05,
      "loss": 0.5449,
      "step": 11242
    },
    {
      "epoch": 0.345375234233404,
      "grad_norm": 0.3484329283237457,
      "learning_rate": 1.8584955317267103e-05,
      "loss": 0.5512,
      "step": 11243
    },
    {
      "epoch": 0.34540595336835317,
      "grad_norm": 0.34514352679252625,
      "learning_rate": 1.8584707472454125e-05,
      "loss": 0.5893,
      "step": 11244
    },
    {
      "epoch": 0.3454366725033023,
      "grad_norm": 0.4540562927722931,
      "learning_rate": 1.8584459607590966e-05,
      "loss": 0.5766,
      "step": 11245
    },
    {
      "epoch": 0.34546739163825146,
      "grad_norm": 0.3405349850654602,
      "learning_rate": 1.8584211722678198e-05,
      "loss": 0.658,
      "step": 11246
    },
    {
      "epoch": 0.34549811077320064,
      "grad_norm": 0.3715977966785431,
      "learning_rate": 1.8583963817716408e-05,
      "loss": 0.5637,
      "step": 11247
    },
    {
      "epoch": 0.34552882990814976,
      "grad_norm": 0.3134032189846039,
      "learning_rate": 1.8583715892706167e-05,
      "loss": 0.5459,
      "step": 11248
    },
    {
      "epoch": 0.34555954904309893,
      "grad_norm": 0.3011392056941986,
      "learning_rate": 1.8583467947648063e-05,
      "loss": 0.5599,
      "step": 11249
    },
    {
      "epoch": 0.3455902681780481,
      "grad_norm": 0.3482937514781952,
      "learning_rate": 1.8583219982542668e-05,
      "loss": 0.561,
      "step": 11250
    },
    {
      "epoch": 0.3456209873129973,
      "grad_norm": 0.34786826372146606,
      "learning_rate": 1.858297199739056e-05,
      "loss": 0.6864,
      "step": 11251
    },
    {
      "epoch": 0.3456517064479464,
      "grad_norm": 0.3709131181240082,
      "learning_rate": 1.8582723992192325e-05,
      "loss": 0.619,
      "step": 11252
    },
    {
      "epoch": 0.3456824255828956,
      "grad_norm": 0.3258141875267029,
      "learning_rate": 1.8582475966948535e-05,
      "loss": 0.5608,
      "step": 11253
    },
    {
      "epoch": 0.34571314471784476,
      "grad_norm": 0.5525398850440979,
      "learning_rate": 1.858222792165978e-05,
      "loss": 0.545,
      "step": 11254
    },
    {
      "epoch": 0.34574386385279393,
      "grad_norm": 0.3218780755996704,
      "learning_rate": 1.8581979856326625e-05,
      "loss": 0.5334,
      "step": 11255
    },
    {
      "epoch": 0.34577458298774305,
      "grad_norm": 0.3381626307964325,
      "learning_rate": 1.8581731770949663e-05,
      "loss": 0.5897,
      "step": 11256
    },
    {
      "epoch": 0.3458053021226922,
      "grad_norm": 0.3144895136356354,
      "learning_rate": 1.8581483665529462e-05,
      "loss": 0.5814,
      "step": 11257
    },
    {
      "epoch": 0.3458360212576414,
      "grad_norm": 0.36351871490478516,
      "learning_rate": 1.8581235540066608e-05,
      "loss": 0.551,
      "step": 11258
    },
    {
      "epoch": 0.3458667403925905,
      "grad_norm": 0.4331835210323334,
      "learning_rate": 1.858098739456168e-05,
      "loss": 0.5963,
      "step": 11259
    },
    {
      "epoch": 0.3458974595275397,
      "grad_norm": 0.33595946431159973,
      "learning_rate": 1.8580739229015256e-05,
      "loss": 0.5256,
      "step": 11260
    },
    {
      "epoch": 0.34592817866248887,
      "grad_norm": 0.33455654978752136,
      "learning_rate": 1.8580491043427916e-05,
      "loss": 0.5773,
      "step": 11261
    },
    {
      "epoch": 0.34595889779743805,
      "grad_norm": 0.32490256428718567,
      "learning_rate": 1.858024283780024e-05,
      "loss": 0.5742,
      "step": 11262
    },
    {
      "epoch": 0.34598961693238717,
      "grad_norm": 0.39453595876693726,
      "learning_rate": 1.857999461213281e-05,
      "loss": 0.5796,
      "step": 11263
    },
    {
      "epoch": 0.34602033606733634,
      "grad_norm": 0.31992843747138977,
      "learning_rate": 1.8579746366426202e-05,
      "loss": 0.5449,
      "step": 11264
    },
    {
      "epoch": 0.3460510552022855,
      "grad_norm": 0.3947654366493225,
      "learning_rate": 1.8579498100680994e-05,
      "loss": 0.5444,
      "step": 11265
    },
    {
      "epoch": 0.34608177433723464,
      "grad_norm": 0.35084033012390137,
      "learning_rate": 1.857924981489777e-05,
      "loss": 0.5085,
      "step": 11266
    },
    {
      "epoch": 0.3461124934721838,
      "grad_norm": 0.347378671169281,
      "learning_rate": 1.8579001509077114e-05,
      "loss": 0.5353,
      "step": 11267
    },
    {
      "epoch": 0.346143212607133,
      "grad_norm": 0.417138010263443,
      "learning_rate": 1.8578753183219597e-05,
      "loss": 0.6675,
      "step": 11268
    },
    {
      "epoch": 0.34617393174208216,
      "grad_norm": 0.3344566524028778,
      "learning_rate": 1.8578504837325803e-05,
      "loss": 0.5295,
      "step": 11269
    },
    {
      "epoch": 0.3462046508770313,
      "grad_norm": 0.3077961802482605,
      "learning_rate": 1.8578256471396313e-05,
      "loss": 0.5289,
      "step": 11270
    },
    {
      "epoch": 0.34623537001198046,
      "grad_norm": 0.47217461466789246,
      "learning_rate": 1.8578008085431705e-05,
      "loss": 0.5669,
      "step": 11271
    },
    {
      "epoch": 0.34626608914692963,
      "grad_norm": 0.35591238737106323,
      "learning_rate": 1.857775967943256e-05,
      "loss": 0.6573,
      "step": 11272
    },
    {
      "epoch": 0.3462968082818788,
      "grad_norm": 0.3537255525588989,
      "learning_rate": 1.8577511253399457e-05,
      "loss": 0.569,
      "step": 11273
    },
    {
      "epoch": 0.34632752741682793,
      "grad_norm": 0.35315176844596863,
      "learning_rate": 1.857726280733298e-05,
      "loss": 0.5449,
      "step": 11274
    },
    {
      "epoch": 0.3463582465517771,
      "grad_norm": 0.33679524064064026,
      "learning_rate": 1.8577014341233704e-05,
      "loss": 0.5971,
      "step": 11275
    },
    {
      "epoch": 0.3463889656867263,
      "grad_norm": 0.35834091901779175,
      "learning_rate": 1.8576765855102212e-05,
      "loss": 0.5032,
      "step": 11276
    },
    {
      "epoch": 0.3464196848216754,
      "grad_norm": 0.3583539128303528,
      "learning_rate": 1.8576517348939086e-05,
      "loss": 0.6096,
      "step": 11277
    },
    {
      "epoch": 0.3464504039566246,
      "grad_norm": 0.39821240305900574,
      "learning_rate": 1.8576268822744904e-05,
      "loss": 0.6257,
      "step": 11278
    },
    {
      "epoch": 0.34648112309157375,
      "grad_norm": 0.3785853683948517,
      "learning_rate": 1.857602027652025e-05,
      "loss": 0.551,
      "step": 11279
    },
    {
      "epoch": 0.3465118422265229,
      "grad_norm": 0.36794379353523254,
      "learning_rate": 1.85757717102657e-05,
      "loss": 0.5194,
      "step": 11280
    },
    {
      "epoch": 0.34654256136147205,
      "grad_norm": 0.3680347502231598,
      "learning_rate": 1.8575523123981834e-05,
      "loss": 0.6241,
      "step": 11281
    },
    {
      "epoch": 0.3465732804964212,
      "grad_norm": 0.39371201395988464,
      "learning_rate": 1.8575274517669234e-05,
      "loss": 0.4955,
      "step": 11282
    },
    {
      "epoch": 0.3466039996313704,
      "grad_norm": 0.36055275797843933,
      "learning_rate": 1.8575025891328487e-05,
      "loss": 0.5721,
      "step": 11283
    },
    {
      "epoch": 0.3466347187663195,
      "grad_norm": 0.3374411165714264,
      "learning_rate": 1.8574777244960164e-05,
      "loss": 0.5884,
      "step": 11284
    },
    {
      "epoch": 0.3466654379012687,
      "grad_norm": 0.33182451128959656,
      "learning_rate": 1.857452857856485e-05,
      "loss": 0.6147,
      "step": 11285
    },
    {
      "epoch": 0.34669615703621787,
      "grad_norm": 0.3455299139022827,
      "learning_rate": 1.8574279892143125e-05,
      "loss": 0.5635,
      "step": 11286
    },
    {
      "epoch": 0.34672687617116704,
      "grad_norm": 0.3219197690486908,
      "learning_rate": 1.8574031185695572e-05,
      "loss": 0.5795,
      "step": 11287
    },
    {
      "epoch": 0.34675759530611616,
      "grad_norm": 0.3226257264614105,
      "learning_rate": 1.857378245922277e-05,
      "loss": 0.6214,
      "step": 11288
    },
    {
      "epoch": 0.34678831444106534,
      "grad_norm": 0.37457162141799927,
      "learning_rate": 1.8573533712725304e-05,
      "loss": 0.5472,
      "step": 11289
    },
    {
      "epoch": 0.3468190335760145,
      "grad_norm": 0.3191659450531006,
      "learning_rate": 1.8573284946203748e-05,
      "loss": 0.6239,
      "step": 11290
    },
    {
      "epoch": 0.34684975271096363,
      "grad_norm": 0.38813430070877075,
      "learning_rate": 1.8573036159658685e-05,
      "loss": 0.5099,
      "step": 11291
    },
    {
      "epoch": 0.3468804718459128,
      "grad_norm": 0.32210323214530945,
      "learning_rate": 1.85727873530907e-05,
      "loss": 0.5163,
      "step": 11292
    },
    {
      "epoch": 0.346911190980862,
      "grad_norm": 0.35284456610679626,
      "learning_rate": 1.857253852650037e-05,
      "loss": 0.54,
      "step": 11293
    },
    {
      "epoch": 0.34694191011581116,
      "grad_norm": 0.3450183868408203,
      "learning_rate": 1.8572289679888276e-05,
      "loss": 0.6215,
      "step": 11294
    },
    {
      "epoch": 0.3469726292507603,
      "grad_norm": 0.36493393778800964,
      "learning_rate": 1.8572040813255002e-05,
      "loss": 0.6076,
      "step": 11295
    },
    {
      "epoch": 0.34700334838570945,
      "grad_norm": 0.32535120844841003,
      "learning_rate": 1.8571791926601128e-05,
      "loss": 0.5745,
      "step": 11296
    },
    {
      "epoch": 0.34703406752065863,
      "grad_norm": 0.32826805114746094,
      "learning_rate": 1.8571543019927234e-05,
      "loss": 0.5308,
      "step": 11297
    },
    {
      "epoch": 0.3470647866556078,
      "grad_norm": 0.3406274914741516,
      "learning_rate": 1.8571294093233906e-05,
      "loss": 0.5135,
      "step": 11298
    },
    {
      "epoch": 0.3470955057905569,
      "grad_norm": 0.3948979079723358,
      "learning_rate": 1.857104514652172e-05,
      "loss": 0.5909,
      "step": 11299
    },
    {
      "epoch": 0.3471262249255061,
      "grad_norm": 0.44431060552597046,
      "learning_rate": 1.857079617979126e-05,
      "loss": 0.5837,
      "step": 11300
    },
    {
      "epoch": 0.3471569440604553,
      "grad_norm": 0.3312034606933594,
      "learning_rate": 1.8570547193043108e-05,
      "loss": 0.5273,
      "step": 11301
    },
    {
      "epoch": 0.3471876631954044,
      "grad_norm": 0.3460303246974945,
      "learning_rate": 1.857029818627784e-05,
      "loss": 0.6054,
      "step": 11302
    },
    {
      "epoch": 0.34721838233035357,
      "grad_norm": 0.3718481659889221,
      "learning_rate": 1.8570049159496047e-05,
      "loss": 0.6351,
      "step": 11303
    },
    {
      "epoch": 0.34724910146530275,
      "grad_norm": 0.3493027985095978,
      "learning_rate": 1.8569800112698302e-05,
      "loss": 0.5778,
      "step": 11304
    },
    {
      "epoch": 0.3472798206002519,
      "grad_norm": 0.37516704201698303,
      "learning_rate": 1.8569551045885193e-05,
      "loss": 0.5555,
      "step": 11305
    },
    {
      "epoch": 0.34731053973520104,
      "grad_norm": 0.31815439462661743,
      "learning_rate": 1.8569301959057298e-05,
      "loss": 0.6083,
      "step": 11306
    },
    {
      "epoch": 0.3473412588701502,
      "grad_norm": 0.3229027986526489,
      "learning_rate": 1.85690528522152e-05,
      "loss": 0.571,
      "step": 11307
    },
    {
      "epoch": 0.3473719780050994,
      "grad_norm": 0.3448328673839569,
      "learning_rate": 1.8568803725359482e-05,
      "loss": 0.6108,
      "step": 11308
    },
    {
      "epoch": 0.3474026971400485,
      "grad_norm": 0.39303791522979736,
      "learning_rate": 1.856855457849072e-05,
      "loss": 0.5247,
      "step": 11309
    },
    {
      "epoch": 0.3474334162749977,
      "grad_norm": 0.3434562385082245,
      "learning_rate": 1.8568305411609505e-05,
      "loss": 0.6242,
      "step": 11310
    },
    {
      "epoch": 0.34746413540994686,
      "grad_norm": 0.3166676461696625,
      "learning_rate": 1.856805622471641e-05,
      "loss": 0.6165,
      "step": 11311
    },
    {
      "epoch": 0.34749485454489604,
      "grad_norm": 0.37675273418426514,
      "learning_rate": 1.8567807017812027e-05,
      "loss": 0.6063,
      "step": 11312
    },
    {
      "epoch": 0.34752557367984516,
      "grad_norm": 0.3328113853931427,
      "learning_rate": 1.8567557790896927e-05,
      "loss": 0.4963,
      "step": 11313
    },
    {
      "epoch": 0.34755629281479433,
      "grad_norm": 0.3584270477294922,
      "learning_rate": 1.8567308543971704e-05,
      "loss": 0.5822,
      "step": 11314
    },
    {
      "epoch": 0.3475870119497435,
      "grad_norm": 0.3785799443721771,
      "learning_rate": 1.8567059277036926e-05,
      "loss": 0.6188,
      "step": 11315
    },
    {
      "epoch": 0.3476177310846927,
      "grad_norm": 0.3279271125793457,
      "learning_rate": 1.8566809990093188e-05,
      "loss": 0.5432,
      "step": 11316
    },
    {
      "epoch": 0.3476484502196418,
      "grad_norm": 0.33291903138160706,
      "learning_rate": 1.8566560683141067e-05,
      "loss": 0.5421,
      "step": 11317
    },
    {
      "epoch": 0.347679169354591,
      "grad_norm": 0.32083624601364136,
      "learning_rate": 1.856631135618114e-05,
      "loss": 0.5139,
      "step": 11318
    },
    {
      "epoch": 0.34770988848954015,
      "grad_norm": 0.3569769561290741,
      "learning_rate": 1.8566062009214e-05,
      "loss": 0.6054,
      "step": 11319
    },
    {
      "epoch": 0.3477406076244893,
      "grad_norm": 0.4451017677783966,
      "learning_rate": 1.8565812642240222e-05,
      "loss": 0.5733,
      "step": 11320
    },
    {
      "epoch": 0.34777132675943845,
      "grad_norm": 0.5139105916023254,
      "learning_rate": 1.8565563255260388e-05,
      "loss": 0.5306,
      "step": 11321
    },
    {
      "epoch": 0.3478020458943876,
      "grad_norm": 0.3682486414909363,
      "learning_rate": 1.8565313848275086e-05,
      "loss": 0.6392,
      "step": 11322
    },
    {
      "epoch": 0.3478327650293368,
      "grad_norm": 0.31385675072669983,
      "learning_rate": 1.8565064421284895e-05,
      "loss": 0.5103,
      "step": 11323
    },
    {
      "epoch": 0.3478634841642859,
      "grad_norm": 0.32131722569465637,
      "learning_rate": 1.8564814974290395e-05,
      "loss": 0.6123,
      "step": 11324
    },
    {
      "epoch": 0.3478942032992351,
      "grad_norm": 0.32916051149368286,
      "learning_rate": 1.8564565507292175e-05,
      "loss": 0.5857,
      "step": 11325
    },
    {
      "epoch": 0.34792492243418427,
      "grad_norm": 0.3693629503250122,
      "learning_rate": 1.856431602029081e-05,
      "loss": 0.5967,
      "step": 11326
    },
    {
      "epoch": 0.3479556415691334,
      "grad_norm": 0.330618679523468,
      "learning_rate": 1.856406651328689e-05,
      "loss": 0.5569,
      "step": 11327
    },
    {
      "epoch": 0.34798636070408256,
      "grad_norm": 0.35617756843566895,
      "learning_rate": 1.8563816986280997e-05,
      "loss": 0.6025,
      "step": 11328
    },
    {
      "epoch": 0.34801707983903174,
      "grad_norm": 0.3227764368057251,
      "learning_rate": 1.8563567439273708e-05,
      "loss": 0.6119,
      "step": 11329
    },
    {
      "epoch": 0.3480477989739809,
      "grad_norm": 0.3970007002353668,
      "learning_rate": 1.856331787226561e-05,
      "loss": 0.5393,
      "step": 11330
    },
    {
      "epoch": 0.34807851810893004,
      "grad_norm": 0.35579559206962585,
      "learning_rate": 1.8563068285257282e-05,
      "loss": 0.511,
      "step": 11331
    },
    {
      "epoch": 0.3481092372438792,
      "grad_norm": 0.3367045223712921,
      "learning_rate": 1.8562818678249314e-05,
      "loss": 0.5178,
      "step": 11332
    },
    {
      "epoch": 0.3481399563788284,
      "grad_norm": 0.33038878440856934,
      "learning_rate": 1.8562569051242284e-05,
      "loss": 0.5467,
      "step": 11333
    },
    {
      "epoch": 0.3481706755137775,
      "grad_norm": 0.36526498198509216,
      "learning_rate": 1.8562319404236776e-05,
      "loss": 0.5896,
      "step": 11334
    },
    {
      "epoch": 0.3482013946487267,
      "grad_norm": 0.3464156985282898,
      "learning_rate": 1.856206973723337e-05,
      "loss": 0.5854,
      "step": 11335
    },
    {
      "epoch": 0.34823211378367586,
      "grad_norm": 0.4402366578578949,
      "learning_rate": 1.8561820050232656e-05,
      "loss": 0.5993,
      "step": 11336
    },
    {
      "epoch": 0.34826283291862503,
      "grad_norm": 0.397234171628952,
      "learning_rate": 1.8561570343235213e-05,
      "loss": 0.5778,
      "step": 11337
    },
    {
      "epoch": 0.34829355205357415,
      "grad_norm": 0.37768489122390747,
      "learning_rate": 1.8561320616241625e-05,
      "loss": 0.4939,
      "step": 11338
    },
    {
      "epoch": 0.3483242711885233,
      "grad_norm": 0.32640519738197327,
      "learning_rate": 1.856107086925247e-05,
      "loss": 0.5473,
      "step": 11339
    },
    {
      "epoch": 0.3483549903234725,
      "grad_norm": 0.3244088292121887,
      "learning_rate": 1.8560821102268343e-05,
      "loss": 0.5466,
      "step": 11340
    },
    {
      "epoch": 0.3483857094584217,
      "grad_norm": 0.3455619215965271,
      "learning_rate": 1.8560571315289814e-05,
      "loss": 0.6108,
      "step": 11341
    },
    {
      "epoch": 0.3484164285933708,
      "grad_norm": 0.34417280554771423,
      "learning_rate": 1.8560321508317475e-05,
      "loss": 0.5716,
      "step": 11342
    },
    {
      "epoch": 0.34844714772832,
      "grad_norm": 0.33532771468162537,
      "learning_rate": 1.856007168135191e-05,
      "loss": 0.5971,
      "step": 11343
    },
    {
      "epoch": 0.34847786686326915,
      "grad_norm": 0.34179261326789856,
      "learning_rate": 1.8559821834393697e-05,
      "loss": 0.6285,
      "step": 11344
    },
    {
      "epoch": 0.34850858599821827,
      "grad_norm": 0.34417346119880676,
      "learning_rate": 1.8559571967443422e-05,
      "loss": 0.5188,
      "step": 11345
    },
    {
      "epoch": 0.34853930513316744,
      "grad_norm": 0.3438042998313904,
      "learning_rate": 1.8559322080501673e-05,
      "loss": 0.6149,
      "step": 11346
    },
    {
      "epoch": 0.3485700242681166,
      "grad_norm": 0.37867894768714905,
      "learning_rate": 1.8559072173569025e-05,
      "loss": 0.5938,
      "step": 11347
    },
    {
      "epoch": 0.3486007434030658,
      "grad_norm": 0.3460482954978943,
      "learning_rate": 1.8558822246646066e-05,
      "loss": 0.6034,
      "step": 11348
    },
    {
      "epoch": 0.3486314625380149,
      "grad_norm": 0.3162902593612671,
      "learning_rate": 1.855857229973338e-05,
      "loss": 0.5812,
      "step": 11349
    },
    {
      "epoch": 0.3486621816729641,
      "grad_norm": 0.33971893787384033,
      "learning_rate": 1.8558322332831556e-05,
      "loss": 0.5433,
      "step": 11350
    },
    {
      "epoch": 0.34869290080791326,
      "grad_norm": 0.3647651672363281,
      "learning_rate": 1.8558072345941166e-05,
      "loss": 0.554,
      "step": 11351
    },
    {
      "epoch": 0.3487236199428624,
      "grad_norm": 0.9307363629341125,
      "learning_rate": 1.8557822339062807e-05,
      "loss": 0.5837,
      "step": 11352
    },
    {
      "epoch": 0.34875433907781156,
      "grad_norm": 0.327669233083725,
      "learning_rate": 1.855757231219705e-05,
      "loss": 0.591,
      "step": 11353
    },
    {
      "epoch": 0.34878505821276073,
      "grad_norm": 0.34422361850738525,
      "learning_rate": 1.8557322265344488e-05,
      "loss": 0.5592,
      "step": 11354
    },
    {
      "epoch": 0.3488157773477099,
      "grad_norm": 0.3470379710197449,
      "learning_rate": 1.85570721985057e-05,
      "loss": 0.5555,
      "step": 11355
    },
    {
      "epoch": 0.34884649648265903,
      "grad_norm": 0.33371609449386597,
      "learning_rate": 1.8556822111681276e-05,
      "loss": 0.6048,
      "step": 11356
    },
    {
      "epoch": 0.3488772156176082,
      "grad_norm": 0.30926525592803955,
      "learning_rate": 1.8556572004871793e-05,
      "loss": 0.5409,
      "step": 11357
    },
    {
      "epoch": 0.3489079347525574,
      "grad_norm": 0.3215295672416687,
      "learning_rate": 1.855632187807784e-05,
      "loss": 0.6052,
      "step": 11358
    },
    {
      "epoch": 0.3489386538875065,
      "grad_norm": 0.3876514136791229,
      "learning_rate": 1.85560717313e-05,
      "loss": 0.5042,
      "step": 11359
    },
    {
      "epoch": 0.3489693730224557,
      "grad_norm": 0.3220072388648987,
      "learning_rate": 1.8555821564538857e-05,
      "loss": 0.5836,
      "step": 11360
    },
    {
      "epoch": 0.34900009215740485,
      "grad_norm": 0.37900614738464355,
      "learning_rate": 1.8555571377794993e-05,
      "loss": 0.6616,
      "step": 11361
    },
    {
      "epoch": 0.349030811292354,
      "grad_norm": 0.37210026383399963,
      "learning_rate": 1.8555321171068996e-05,
      "loss": 0.6522,
      "step": 11362
    },
    {
      "epoch": 0.34906153042730315,
      "grad_norm": 0.40646421909332275,
      "learning_rate": 1.855507094436145e-05,
      "loss": 0.555,
      "step": 11363
    },
    {
      "epoch": 0.3490922495622523,
      "grad_norm": 0.709987461566925,
      "learning_rate": 1.8554820697672936e-05,
      "loss": 0.5895,
      "step": 11364
    },
    {
      "epoch": 0.3491229686972015,
      "grad_norm": 0.32982030510902405,
      "learning_rate": 1.8554570431004043e-05,
      "loss": 0.4806,
      "step": 11365
    },
    {
      "epoch": 0.34915368783215067,
      "grad_norm": 0.3467276096343994,
      "learning_rate": 1.8554320144355354e-05,
      "loss": 0.6252,
      "step": 11366
    },
    {
      "epoch": 0.3491844069670998,
      "grad_norm": 0.3455829620361328,
      "learning_rate": 1.855406983772745e-05,
      "loss": 0.6042,
      "step": 11367
    },
    {
      "epoch": 0.34921512610204897,
      "grad_norm": 0.33869993686676025,
      "learning_rate": 1.855381951112092e-05,
      "loss": 0.5617,
      "step": 11368
    },
    {
      "epoch": 0.34924584523699814,
      "grad_norm": 0.3459802269935608,
      "learning_rate": 1.855356916453635e-05,
      "loss": 0.5827,
      "step": 11369
    },
    {
      "epoch": 0.34927656437194726,
      "grad_norm": 0.36970004439353943,
      "learning_rate": 1.8553318797974317e-05,
      "loss": 0.6649,
      "step": 11370
    },
    {
      "epoch": 0.34930728350689644,
      "grad_norm": 0.3584221601486206,
      "learning_rate": 1.855306841143541e-05,
      "loss": 0.5953,
      "step": 11371
    },
    {
      "epoch": 0.3493380026418456,
      "grad_norm": 0.3171955645084381,
      "learning_rate": 1.855281800492022e-05,
      "loss": 0.6348,
      "step": 11372
    },
    {
      "epoch": 0.3493687217767948,
      "grad_norm": 0.329387366771698,
      "learning_rate": 1.8552567578429322e-05,
      "loss": 0.5438,
      "step": 11373
    },
    {
      "epoch": 0.3493994409117439,
      "grad_norm": 0.3319295048713684,
      "learning_rate": 1.8552317131963307e-05,
      "loss": 0.6549,
      "step": 11374
    },
    {
      "epoch": 0.3494301600466931,
      "grad_norm": 0.36993980407714844,
      "learning_rate": 1.8552066665522757e-05,
      "loss": 0.4858,
      "step": 11375
    },
    {
      "epoch": 0.34946087918164226,
      "grad_norm": 0.3740242123603821,
      "learning_rate": 1.855181617910826e-05,
      "loss": 0.6252,
      "step": 11376
    },
    {
      "epoch": 0.3494915983165914,
      "grad_norm": 0.2974475026130676,
      "learning_rate": 1.8551565672720395e-05,
      "loss": 0.5845,
      "step": 11377
    },
    {
      "epoch": 0.34952231745154055,
      "grad_norm": 0.3549022972583771,
      "learning_rate": 1.8551315146359755e-05,
      "loss": 0.5595,
      "step": 11378
    },
    {
      "epoch": 0.34955303658648973,
      "grad_norm": 0.3620690107345581,
      "learning_rate": 1.855106460002692e-05,
      "loss": 0.6163,
      "step": 11379
    },
    {
      "epoch": 0.3495837557214389,
      "grad_norm": 0.3406987190246582,
      "learning_rate": 1.8550814033722476e-05,
      "loss": 0.5375,
      "step": 11380
    },
    {
      "epoch": 0.349614474856388,
      "grad_norm": 0.36824026703834534,
      "learning_rate": 1.8550563447447008e-05,
      "loss": 0.5264,
      "step": 11381
    },
    {
      "epoch": 0.3496451939913372,
      "grad_norm": 0.34925124049186707,
      "learning_rate": 1.8550312841201102e-05,
      "loss": 0.612,
      "step": 11382
    },
    {
      "epoch": 0.3496759131262864,
      "grad_norm": 0.3438829779624939,
      "learning_rate": 1.8550062214985344e-05,
      "loss": 0.649,
      "step": 11383
    },
    {
      "epoch": 0.34970663226123555,
      "grad_norm": 0.3503747582435608,
      "learning_rate": 1.8549811568800317e-05,
      "loss": 0.4798,
      "step": 11384
    },
    {
      "epoch": 0.34973735139618467,
      "grad_norm": 0.409397691488266,
      "learning_rate": 1.854956090264661e-05,
      "loss": 0.5689,
      "step": 11385
    },
    {
      "epoch": 0.34976807053113385,
      "grad_norm": 0.3222496807575226,
      "learning_rate": 1.8549310216524806e-05,
      "loss": 0.4894,
      "step": 11386
    },
    {
      "epoch": 0.349798789666083,
      "grad_norm": 0.33247601985931396,
      "learning_rate": 1.854905951043549e-05,
      "loss": 0.5379,
      "step": 11387
    },
    {
      "epoch": 0.34982950880103214,
      "grad_norm": 0.4208299219608307,
      "learning_rate": 1.854880878437925e-05,
      "loss": 0.5376,
      "step": 11388
    },
    {
      "epoch": 0.3498602279359813,
      "grad_norm": 0.5223402380943298,
      "learning_rate": 1.854855803835667e-05,
      "loss": 0.5184,
      "step": 11389
    },
    {
      "epoch": 0.3498909470709305,
      "grad_norm": 0.40320107340812683,
      "learning_rate": 1.8548307272368332e-05,
      "loss": 0.6402,
      "step": 11390
    },
    {
      "epoch": 0.34992166620587967,
      "grad_norm": 0.3758806884288788,
      "learning_rate": 1.8548056486414832e-05,
      "loss": 0.6097,
      "step": 11391
    },
    {
      "epoch": 0.3499523853408288,
      "grad_norm": 0.4362967610359192,
      "learning_rate": 1.8547805680496745e-05,
      "loss": 0.5726,
      "step": 11392
    },
    {
      "epoch": 0.34998310447577796,
      "grad_norm": 0.3200242519378662,
      "learning_rate": 1.8547554854614664e-05,
      "loss": 0.6144,
      "step": 11393
    },
    {
      "epoch": 0.35001382361072714,
      "grad_norm": 0.3994579613208771,
      "learning_rate": 1.8547304008769168e-05,
      "loss": 0.5823,
      "step": 11394
    },
    {
      "epoch": 0.35004454274567626,
      "grad_norm": 0.3615278899669647,
      "learning_rate": 1.8547053142960844e-05,
      "loss": 0.5702,
      "step": 11395
    },
    {
      "epoch": 0.35007526188062543,
      "grad_norm": 0.33120134472846985,
      "learning_rate": 1.8546802257190288e-05,
      "loss": 0.6288,
      "step": 11396
    },
    {
      "epoch": 0.3501059810155746,
      "grad_norm": 0.36457139253616333,
      "learning_rate": 1.8546551351458072e-05,
      "loss": 0.6334,
      "step": 11397
    },
    {
      "epoch": 0.3501367001505238,
      "grad_norm": 0.35045766830444336,
      "learning_rate": 1.8546300425764793e-05,
      "loss": 0.6763,
      "step": 11398
    },
    {
      "epoch": 0.3501674192854729,
      "grad_norm": 0.3679502010345459,
      "learning_rate": 1.8546049480111026e-05,
      "loss": 0.5791,
      "step": 11399
    },
    {
      "epoch": 0.3501981384204221,
      "grad_norm": 0.5291891098022461,
      "learning_rate": 1.854579851449737e-05,
      "loss": 0.5257,
      "step": 11400
    },
    {
      "epoch": 0.35022885755537125,
      "grad_norm": 0.37934985756874084,
      "learning_rate": 1.8545547528924404e-05,
      "loss": 0.5747,
      "step": 11401
    },
    {
      "epoch": 0.3502595766903204,
      "grad_norm": 0.4006384015083313,
      "learning_rate": 1.854529652339271e-05,
      "loss": 0.543,
      "step": 11402
    },
    {
      "epoch": 0.35029029582526955,
      "grad_norm": 0.35804417729377747,
      "learning_rate": 1.8545045497902886e-05,
      "loss": 0.5736,
      "step": 11403
    },
    {
      "epoch": 0.3503210149602187,
      "grad_norm": 0.34525272250175476,
      "learning_rate": 1.854479445245551e-05,
      "loss": 0.5306,
      "step": 11404
    },
    {
      "epoch": 0.3503517340951679,
      "grad_norm": 0.32720622420310974,
      "learning_rate": 1.8544543387051166e-05,
      "loss": 0.567,
      "step": 11405
    },
    {
      "epoch": 0.350382453230117,
      "grad_norm": 0.3479689061641693,
      "learning_rate": 1.8544292301690445e-05,
      "loss": 0.4996,
      "step": 11406
    },
    {
      "epoch": 0.3504131723650662,
      "grad_norm": 0.4191547632217407,
      "learning_rate": 1.8544041196373933e-05,
      "loss": 0.5763,
      "step": 11407
    },
    {
      "epoch": 0.35044389150001537,
      "grad_norm": 0.32668542861938477,
      "learning_rate": 1.8543790071102215e-05,
      "loss": 0.5865,
      "step": 11408
    },
    {
      "epoch": 0.35047461063496455,
      "grad_norm": 0.3522021472454071,
      "learning_rate": 1.8543538925875882e-05,
      "loss": 0.6242,
      "step": 11409
    },
    {
      "epoch": 0.35050532976991366,
      "grad_norm": 0.3100605010986328,
      "learning_rate": 1.8543287760695516e-05,
      "loss": 0.5011,
      "step": 11410
    },
    {
      "epoch": 0.35053604890486284,
      "grad_norm": 0.3536990284919739,
      "learning_rate": 1.8543036575561704e-05,
      "loss": 0.5774,
      "step": 11411
    },
    {
      "epoch": 0.350566768039812,
      "grad_norm": 0.30476662516593933,
      "learning_rate": 1.8542785370475034e-05,
      "loss": 0.5256,
      "step": 11412
    },
    {
      "epoch": 0.35059748717476114,
      "grad_norm": 0.36229774355888367,
      "learning_rate": 1.8542534145436093e-05,
      "loss": 0.624,
      "step": 11413
    },
    {
      "epoch": 0.3506282063097103,
      "grad_norm": 0.33306655287742615,
      "learning_rate": 1.8542282900445464e-05,
      "loss": 0.5838,
      "step": 11414
    },
    {
      "epoch": 0.3506589254446595,
      "grad_norm": 0.38411885499954224,
      "learning_rate": 1.854203163550374e-05,
      "loss": 0.6649,
      "step": 11415
    },
    {
      "epoch": 0.35068964457960866,
      "grad_norm": 0.7171433568000793,
      "learning_rate": 1.8541780350611502e-05,
      "loss": 0.5477,
      "step": 11416
    },
    {
      "epoch": 0.3507203637145578,
      "grad_norm": 0.34940046072006226,
      "learning_rate": 1.8541529045769342e-05,
      "loss": 0.5472,
      "step": 11417
    },
    {
      "epoch": 0.35075108284950696,
      "grad_norm": 0.4714857041835785,
      "learning_rate": 1.854127772097784e-05,
      "loss": 0.5235,
      "step": 11418
    },
    {
      "epoch": 0.35078180198445613,
      "grad_norm": 0.3419811725616455,
      "learning_rate": 1.8541026376237594e-05,
      "loss": 0.5619,
      "step": 11419
    },
    {
      "epoch": 0.35081252111940525,
      "grad_norm": 0.32352641224861145,
      "learning_rate": 1.8540775011549178e-05,
      "loss": 0.4987,
      "step": 11420
    },
    {
      "epoch": 0.3508432402543544,
      "grad_norm": 0.3277982175350189,
      "learning_rate": 1.854052362691319e-05,
      "loss": 0.6212,
      "step": 11421
    },
    {
      "epoch": 0.3508739593893036,
      "grad_norm": 0.32353901863098145,
      "learning_rate": 1.854027222233021e-05,
      "loss": 0.5577,
      "step": 11422
    },
    {
      "epoch": 0.3509046785242528,
      "grad_norm": 0.36119136214256287,
      "learning_rate": 1.854002079780083e-05,
      "loss": 0.5652,
      "step": 11423
    },
    {
      "epoch": 0.3509353976592019,
      "grad_norm": 0.34616777300834656,
      "learning_rate": 1.8539769353325635e-05,
      "loss": 0.6008,
      "step": 11424
    },
    {
      "epoch": 0.3509661167941511,
      "grad_norm": 0.3428565561771393,
      "learning_rate": 1.853951788890521e-05,
      "loss": 0.5055,
      "step": 11425
    },
    {
      "epoch": 0.35099683592910025,
      "grad_norm": 0.3552015721797943,
      "learning_rate": 1.8539266404540145e-05,
      "loss": 0.5952,
      "step": 11426
    },
    {
      "epoch": 0.3510275550640494,
      "grad_norm": 0.3203696012496948,
      "learning_rate": 1.8539014900231026e-05,
      "loss": 0.5584,
      "step": 11427
    },
    {
      "epoch": 0.35105827419899854,
      "grad_norm": 0.48179933428764343,
      "learning_rate": 1.8538763375978445e-05,
      "loss": 0.5958,
      "step": 11428
    },
    {
      "epoch": 0.3510889933339477,
      "grad_norm": 0.3545813262462616,
      "learning_rate": 1.8538511831782982e-05,
      "loss": 0.4833,
      "step": 11429
    },
    {
      "epoch": 0.3511197124688969,
      "grad_norm": 0.3908509314060211,
      "learning_rate": 1.853826026764523e-05,
      "loss": 0.6058,
      "step": 11430
    },
    {
      "epoch": 0.351150431603846,
      "grad_norm": 0.3349266052246094,
      "learning_rate": 1.8538008683565776e-05,
      "loss": 0.5974,
      "step": 11431
    },
    {
      "epoch": 0.3511811507387952,
      "grad_norm": 0.356124609708786,
      "learning_rate": 1.8537757079545203e-05,
      "loss": 0.5624,
      "step": 11432
    },
    {
      "epoch": 0.35121186987374436,
      "grad_norm": 0.3393619954586029,
      "learning_rate": 1.8537505455584105e-05,
      "loss": 0.5769,
      "step": 11433
    },
    {
      "epoch": 0.35124258900869354,
      "grad_norm": 0.37571656703948975,
      "learning_rate": 1.853725381168307e-05,
      "loss": 0.6098,
      "step": 11434
    },
    {
      "epoch": 0.35127330814364266,
      "grad_norm": 0.33763784170150757,
      "learning_rate": 1.8537002147842673e-05,
      "loss": 0.6007,
      "step": 11435
    },
    {
      "epoch": 0.35130402727859183,
      "grad_norm": 0.34126365184783936,
      "learning_rate": 1.853675046406352e-05,
      "loss": 0.5798,
      "step": 11436
    },
    {
      "epoch": 0.351334746413541,
      "grad_norm": 0.3419937193393707,
      "learning_rate": 1.8536498760346185e-05,
      "loss": 0.5837,
      "step": 11437
    },
    {
      "epoch": 0.35136546554849013,
      "grad_norm": 0.3030388057231903,
      "learning_rate": 1.853624703669126e-05,
      "loss": 0.5001,
      "step": 11438
    },
    {
      "epoch": 0.3513961846834393,
      "grad_norm": 0.3724290430545807,
      "learning_rate": 1.853599529309934e-05,
      "loss": 0.5261,
      "step": 11439
    },
    {
      "epoch": 0.3514269038183885,
      "grad_norm": 0.3508874475955963,
      "learning_rate": 1.8535743529571003e-05,
      "loss": 0.6041,
      "step": 11440
    },
    {
      "epoch": 0.35145762295333766,
      "grad_norm": 0.4091031551361084,
      "learning_rate": 1.8535491746106838e-05,
      "loss": 0.5956,
      "step": 11441
    },
    {
      "epoch": 0.3514883420882868,
      "grad_norm": 0.3116965591907501,
      "learning_rate": 1.853523994270744e-05,
      "loss": 0.5343,
      "step": 11442
    },
    {
      "epoch": 0.35151906122323595,
      "grad_norm": 0.3288998603820801,
      "learning_rate": 1.8534988119373395e-05,
      "loss": 0.5692,
      "step": 11443
    },
    {
      "epoch": 0.3515497803581851,
      "grad_norm": 0.3593905568122864,
      "learning_rate": 1.8534736276105286e-05,
      "loss": 0.6196,
      "step": 11444
    },
    {
      "epoch": 0.35158049949313425,
      "grad_norm": 0.3350728154182434,
      "learning_rate": 1.8534484412903703e-05,
      "loss": 0.5877,
      "step": 11445
    },
    {
      "epoch": 0.3516112186280834,
      "grad_norm": 0.404083251953125,
      "learning_rate": 1.853423252976924e-05,
      "loss": 0.5913,
      "step": 11446
    },
    {
      "epoch": 0.3516419377630326,
      "grad_norm": 0.3559688627719879,
      "learning_rate": 1.8533980626702477e-05,
      "loss": 0.663,
      "step": 11447
    },
    {
      "epoch": 0.3516726568979818,
      "grad_norm": 0.3542003929615021,
      "learning_rate": 1.8533728703704007e-05,
      "loss": 0.5822,
      "step": 11448
    },
    {
      "epoch": 0.3517033760329309,
      "grad_norm": 0.3604080379009247,
      "learning_rate": 1.8533476760774418e-05,
      "loss": 0.5982,
      "step": 11449
    },
    {
      "epoch": 0.35173409516788007,
      "grad_norm": 0.35006746649742126,
      "learning_rate": 1.85332247979143e-05,
      "loss": 0.5279,
      "step": 11450
    },
    {
      "epoch": 0.35176481430282924,
      "grad_norm": 0.30903640389442444,
      "learning_rate": 1.8532972815124237e-05,
      "loss": 0.5206,
      "step": 11451
    },
    {
      "epoch": 0.3517955334377784,
      "grad_norm": 0.33051788806915283,
      "learning_rate": 1.8532720812404822e-05,
      "loss": 0.5449,
      "step": 11452
    },
    {
      "epoch": 0.35182625257272754,
      "grad_norm": 0.36778247356414795,
      "learning_rate": 1.853246878975664e-05,
      "loss": 0.5955,
      "step": 11453
    },
    {
      "epoch": 0.3518569717076767,
      "grad_norm": 0.34637144207954407,
      "learning_rate": 1.8532216747180277e-05,
      "loss": 0.4836,
      "step": 11454
    },
    {
      "epoch": 0.3518876908426259,
      "grad_norm": 0.3609873652458191,
      "learning_rate": 1.8531964684676335e-05,
      "loss": 0.5534,
      "step": 11455
    },
    {
      "epoch": 0.351918409977575,
      "grad_norm": 0.3656162917613983,
      "learning_rate": 1.8531712602245386e-05,
      "loss": 0.6411,
      "step": 11456
    },
    {
      "epoch": 0.3519491291125242,
      "grad_norm": 0.33143141865730286,
      "learning_rate": 1.853146049988803e-05,
      "loss": 0.5956,
      "step": 11457
    },
    {
      "epoch": 0.35197984824747336,
      "grad_norm": 0.3211456537246704,
      "learning_rate": 1.8531208377604853e-05,
      "loss": 0.5191,
      "step": 11458
    },
    {
      "epoch": 0.35201056738242253,
      "grad_norm": 0.3926007151603699,
      "learning_rate": 1.8530956235396442e-05,
      "loss": 0.6057,
      "step": 11459
    },
    {
      "epoch": 0.35204128651737165,
      "grad_norm": 0.3720177710056305,
      "learning_rate": 1.8530704073263386e-05,
      "loss": 0.5869,
      "step": 11460
    },
    {
      "epoch": 0.35207200565232083,
      "grad_norm": 0.41847288608551025,
      "learning_rate": 1.8530451891206275e-05,
      "loss": 0.6043,
      "step": 11461
    },
    {
      "epoch": 0.35210272478727,
      "grad_norm": 0.367041677236557,
      "learning_rate": 1.85301996892257e-05,
      "loss": 0.4682,
      "step": 11462
    },
    {
      "epoch": 0.3521334439222191,
      "grad_norm": 0.3595093786716461,
      "learning_rate": 1.8529947467322245e-05,
      "loss": 0.5884,
      "step": 11463
    },
    {
      "epoch": 0.3521641630571683,
      "grad_norm": 0.34937435388565063,
      "learning_rate": 1.85296952254965e-05,
      "loss": 0.5948,
      "step": 11464
    },
    {
      "epoch": 0.3521948821921175,
      "grad_norm": 0.3384823203086853,
      "learning_rate": 1.8529442963749064e-05,
      "loss": 0.6592,
      "step": 11465
    },
    {
      "epoch": 0.35222560132706665,
      "grad_norm": 0.35371148586273193,
      "learning_rate": 1.8529190682080512e-05,
      "loss": 0.5823,
      "step": 11466
    },
    {
      "epoch": 0.35225632046201577,
      "grad_norm": 0.3468400835990906,
      "learning_rate": 1.852893838049144e-05,
      "loss": 0.5768,
      "step": 11467
    },
    {
      "epoch": 0.35228703959696495,
      "grad_norm": 0.31745636463165283,
      "learning_rate": 1.8528686058982437e-05,
      "loss": 0.5729,
      "step": 11468
    },
    {
      "epoch": 0.3523177587319141,
      "grad_norm": 0.32052767276763916,
      "learning_rate": 1.8528433717554092e-05,
      "loss": 0.5325,
      "step": 11469
    },
    {
      "epoch": 0.3523484778668633,
      "grad_norm": 0.31184476613998413,
      "learning_rate": 1.8528181356207e-05,
      "loss": 0.5263,
      "step": 11470
    },
    {
      "epoch": 0.3523791970018124,
      "grad_norm": 0.36517980694770813,
      "learning_rate": 1.852792897494174e-05,
      "loss": 0.6142,
      "step": 11471
    },
    {
      "epoch": 0.3524099161367616,
      "grad_norm": 0.36476296186447144,
      "learning_rate": 1.8527676573758905e-05,
      "loss": 0.6372,
      "step": 11472
    },
    {
      "epoch": 0.35244063527171077,
      "grad_norm": 0.4000464975833893,
      "learning_rate": 1.8527424152659085e-05,
      "loss": 0.4544,
      "step": 11473
    },
    {
      "epoch": 0.3524713544066599,
      "grad_norm": 0.3541850447654724,
      "learning_rate": 1.8527171711642874e-05,
      "loss": 0.5383,
      "step": 11474
    },
    {
      "epoch": 0.35250207354160906,
      "grad_norm": 0.3406923711299896,
      "learning_rate": 1.852691925071086e-05,
      "loss": 0.6073,
      "step": 11475
    },
    {
      "epoch": 0.35253279267655824,
      "grad_norm": 0.339729905128479,
      "learning_rate": 1.8526666769863625e-05,
      "loss": 0.6065,
      "step": 11476
    },
    {
      "epoch": 0.3525635118115074,
      "grad_norm": 0.33906829357147217,
      "learning_rate": 1.8526414269101765e-05,
      "loss": 0.5372,
      "step": 11477
    },
    {
      "epoch": 0.35259423094645653,
      "grad_norm": 0.3264419436454773,
      "learning_rate": 1.852616174842587e-05,
      "loss": 0.5938,
      "step": 11478
    },
    {
      "epoch": 0.3526249500814057,
      "grad_norm": 0.33565816283226013,
      "learning_rate": 1.852590920783653e-05,
      "loss": 0.5895,
      "step": 11479
    },
    {
      "epoch": 0.3526556692163549,
      "grad_norm": 0.3542287349700928,
      "learning_rate": 1.8525656647334333e-05,
      "loss": 0.592,
      "step": 11480
    },
    {
      "epoch": 0.352686388351304,
      "grad_norm": 0.3261890411376953,
      "learning_rate": 1.8525404066919867e-05,
      "loss": 0.6024,
      "step": 11481
    },
    {
      "epoch": 0.3527171074862532,
      "grad_norm": 0.38986608386039734,
      "learning_rate": 1.8525151466593726e-05,
      "loss": 0.6664,
      "step": 11482
    },
    {
      "epoch": 0.35274782662120235,
      "grad_norm": 0.3316037654876709,
      "learning_rate": 1.85248988463565e-05,
      "loss": 0.585,
      "step": 11483
    },
    {
      "epoch": 0.35277854575615153,
      "grad_norm": 0.40001174807548523,
      "learning_rate": 1.852464620620878e-05,
      "loss": 0.557,
      "step": 11484
    },
    {
      "epoch": 0.35280926489110065,
      "grad_norm": 0.3321998715400696,
      "learning_rate": 1.8524393546151146e-05,
      "loss": 0.5267,
      "step": 11485
    },
    {
      "epoch": 0.3528399840260498,
      "grad_norm": 0.38968223333358765,
      "learning_rate": 1.85241408661842e-05,
      "loss": 0.6284,
      "step": 11486
    },
    {
      "epoch": 0.352870703160999,
      "grad_norm": 0.3427540361881256,
      "learning_rate": 1.8523888166308527e-05,
      "loss": 0.6477,
      "step": 11487
    },
    {
      "epoch": 0.3529014222959481,
      "grad_norm": 0.34098300337791443,
      "learning_rate": 1.8523635446524717e-05,
      "loss": 0.5267,
      "step": 11488
    },
    {
      "epoch": 0.3529321414308973,
      "grad_norm": 0.34810203313827515,
      "learning_rate": 1.8523382706833365e-05,
      "loss": 0.5821,
      "step": 11489
    },
    {
      "epoch": 0.35296286056584647,
      "grad_norm": 0.34803032875061035,
      "learning_rate": 1.8523129947235053e-05,
      "loss": 0.5048,
      "step": 11490
    },
    {
      "epoch": 0.35299357970079565,
      "grad_norm": 0.7327767610549927,
      "learning_rate": 1.8522877167730378e-05,
      "loss": 0.5974,
      "step": 11491
    },
    {
      "epoch": 0.35302429883574477,
      "grad_norm": 0.3427952229976654,
      "learning_rate": 1.8522624368319928e-05,
      "loss": 0.6301,
      "step": 11492
    },
    {
      "epoch": 0.35305501797069394,
      "grad_norm": 0.3678911030292511,
      "learning_rate": 1.852237154900429e-05,
      "loss": 0.5979,
      "step": 11493
    },
    {
      "epoch": 0.3530857371056431,
      "grad_norm": 0.369081974029541,
      "learning_rate": 1.852211870978406e-05,
      "loss": 0.6133,
      "step": 11494
    },
    {
      "epoch": 0.3531164562405923,
      "grad_norm": 0.34198662638664246,
      "learning_rate": 1.852186585065983e-05,
      "loss": 0.6056,
      "step": 11495
    },
    {
      "epoch": 0.3531471753755414,
      "grad_norm": 0.3411914110183716,
      "learning_rate": 1.8521612971632183e-05,
      "loss": 0.5445,
      "step": 11496
    },
    {
      "epoch": 0.3531778945104906,
      "grad_norm": 0.30093953013420105,
      "learning_rate": 1.8521360072701715e-05,
      "loss": 0.5369,
      "step": 11497
    },
    {
      "epoch": 0.35320861364543976,
      "grad_norm": 0.31739476323127747,
      "learning_rate": 1.8521107153869017e-05,
      "loss": 0.578,
      "step": 11498
    },
    {
      "epoch": 0.3532393327803889,
      "grad_norm": 0.3721875846385956,
      "learning_rate": 1.8520854215134678e-05,
      "loss": 0.6078,
      "step": 11499
    },
    {
      "epoch": 0.35327005191533806,
      "grad_norm": 0.3360198140144348,
      "learning_rate": 1.8520601256499286e-05,
      "loss": 0.6866,
      "step": 11500
    },
    {
      "epoch": 0.35330077105028723,
      "grad_norm": 0.3670846223831177,
      "learning_rate": 1.8520348277963437e-05,
      "loss": 0.5955,
      "step": 11501
    },
    {
      "epoch": 0.3533314901852364,
      "grad_norm": 0.33760786056518555,
      "learning_rate": 1.8520095279527722e-05,
      "loss": 0.575,
      "step": 11502
    },
    {
      "epoch": 0.3533622093201855,
      "grad_norm": 0.3524162769317627,
      "learning_rate": 1.8519842261192723e-05,
      "loss": 0.6122,
      "step": 11503
    },
    {
      "epoch": 0.3533929284551347,
      "grad_norm": 0.3725300431251526,
      "learning_rate": 1.8519589222959043e-05,
      "loss": 0.5406,
      "step": 11504
    },
    {
      "epoch": 0.3534236475900839,
      "grad_norm": 0.4205290675163269,
      "learning_rate": 1.8519336164827268e-05,
      "loss": 0.6016,
      "step": 11505
    },
    {
      "epoch": 0.353454366725033,
      "grad_norm": 0.38610199093818665,
      "learning_rate": 1.851908308679798e-05,
      "loss": 0.6052,
      "step": 11506
    },
    {
      "epoch": 0.3534850858599822,
      "grad_norm": 0.3163902461528778,
      "learning_rate": 1.8518829988871788e-05,
      "loss": 0.5759,
      "step": 11507
    },
    {
      "epoch": 0.35351580499493135,
      "grad_norm": 0.32458093762397766,
      "learning_rate": 1.851857687104927e-05,
      "loss": 0.4406,
      "step": 11508
    },
    {
      "epoch": 0.3535465241298805,
      "grad_norm": 0.3575226962566376,
      "learning_rate": 1.8518323733331017e-05,
      "loss": 0.6388,
      "step": 11509
    },
    {
      "epoch": 0.35357724326482964,
      "grad_norm": 0.343838632106781,
      "learning_rate": 1.851807057571763e-05,
      "loss": 0.5979,
      "step": 11510
    },
    {
      "epoch": 0.3536079623997788,
      "grad_norm": 0.31983163952827454,
      "learning_rate": 1.851781739820969e-05,
      "loss": 0.5195,
      "step": 11511
    },
    {
      "epoch": 0.353638681534728,
      "grad_norm": 0.37681853771209717,
      "learning_rate": 1.8517564200807797e-05,
      "loss": 0.5674,
      "step": 11512
    },
    {
      "epoch": 0.3536694006696771,
      "grad_norm": 0.38879549503326416,
      "learning_rate": 1.8517310983512534e-05,
      "loss": 0.5688,
      "step": 11513
    },
    {
      "epoch": 0.3537001198046263,
      "grad_norm": 0.3684677481651306,
      "learning_rate": 1.85170577463245e-05,
      "loss": 0.641,
      "step": 11514
    },
    {
      "epoch": 0.35373083893957546,
      "grad_norm": 0.5679585933685303,
      "learning_rate": 1.851680448924428e-05,
      "loss": 0.5682,
      "step": 11515
    },
    {
      "epoch": 0.35376155807452464,
      "grad_norm": 0.33732616901397705,
      "learning_rate": 1.8516551212272468e-05,
      "loss": 0.6082,
      "step": 11516
    },
    {
      "epoch": 0.35379227720947376,
      "grad_norm": 0.35099220275878906,
      "learning_rate": 1.8516297915409658e-05,
      "loss": 0.5703,
      "step": 11517
    },
    {
      "epoch": 0.35382299634442294,
      "grad_norm": 0.37042465806007385,
      "learning_rate": 1.8516044598656437e-05,
      "loss": 0.5875,
      "step": 11518
    },
    {
      "epoch": 0.3538537154793721,
      "grad_norm": 0.3431532680988312,
      "learning_rate": 1.85157912620134e-05,
      "loss": 0.4817,
      "step": 11519
    },
    {
      "epoch": 0.3538844346143213,
      "grad_norm": 0.356351763010025,
      "learning_rate": 1.8515537905481138e-05,
      "loss": 0.5867,
      "step": 11520
    },
    {
      "epoch": 0.3539151537492704,
      "grad_norm": 0.40702322125434875,
      "learning_rate": 1.8515284529060243e-05,
      "loss": 0.5282,
      "step": 11521
    },
    {
      "epoch": 0.3539458728842196,
      "grad_norm": 0.5621986985206604,
      "learning_rate": 1.8515031132751306e-05,
      "loss": 0.6001,
      "step": 11522
    },
    {
      "epoch": 0.35397659201916876,
      "grad_norm": 0.40977662801742554,
      "learning_rate": 1.8514777716554916e-05,
      "loss": 0.6062,
      "step": 11523
    },
    {
      "epoch": 0.3540073111541179,
      "grad_norm": 0.3304763436317444,
      "learning_rate": 1.8514524280471673e-05,
      "loss": 0.544,
      "step": 11524
    },
    {
      "epoch": 0.35403803028906705,
      "grad_norm": 0.3564305901527405,
      "learning_rate": 1.8514270824502163e-05,
      "loss": 0.5655,
      "step": 11525
    },
    {
      "epoch": 0.3540687494240162,
      "grad_norm": 0.32620295882225037,
      "learning_rate": 1.8514017348646976e-05,
      "loss": 0.5789,
      "step": 11526
    },
    {
      "epoch": 0.3540994685589654,
      "grad_norm": 0.3867633640766144,
      "learning_rate": 1.851376385290671e-05,
      "loss": 0.5793,
      "step": 11527
    },
    {
      "epoch": 0.3541301876939145,
      "grad_norm": 0.3682733178138733,
      "learning_rate": 1.8513510337281952e-05,
      "loss": 0.5924,
      "step": 11528
    },
    {
      "epoch": 0.3541609068288637,
      "grad_norm": 0.4305447041988373,
      "learning_rate": 1.8513256801773298e-05,
      "loss": 0.5872,
      "step": 11529
    },
    {
      "epoch": 0.3541916259638129,
      "grad_norm": 0.35685843229293823,
      "learning_rate": 1.8513003246381337e-05,
      "loss": 0.5464,
      "step": 11530
    },
    {
      "epoch": 0.354222345098762,
      "grad_norm": 0.3484806716442108,
      "learning_rate": 1.851274967110666e-05,
      "loss": 0.5674,
      "step": 11531
    },
    {
      "epoch": 0.35425306423371117,
      "grad_norm": 0.36485713720321655,
      "learning_rate": 1.8512496075949865e-05,
      "loss": 0.5934,
      "step": 11532
    },
    {
      "epoch": 0.35428378336866034,
      "grad_norm": 0.32841429114341736,
      "learning_rate": 1.851224246091154e-05,
      "loss": 0.564,
      "step": 11533
    },
    {
      "epoch": 0.3543145025036095,
      "grad_norm": 0.3329140245914459,
      "learning_rate": 1.851198882599228e-05,
      "loss": 0.6468,
      "step": 11534
    },
    {
      "epoch": 0.35434522163855864,
      "grad_norm": 0.33404651284217834,
      "learning_rate": 1.8511735171192667e-05,
      "loss": 0.4884,
      "step": 11535
    },
    {
      "epoch": 0.3543759407735078,
      "grad_norm": 0.512713611125946,
      "learning_rate": 1.8511481496513314e-05,
      "loss": 0.5211,
      "step": 11536
    },
    {
      "epoch": 0.354406659908457,
      "grad_norm": 0.37229400873184204,
      "learning_rate": 1.8511227801954793e-05,
      "loss": 0.6149,
      "step": 11537
    },
    {
      "epoch": 0.35443737904340616,
      "grad_norm": 0.8387864232063293,
      "learning_rate": 1.851097408751771e-05,
      "loss": 0.6292,
      "step": 11538
    },
    {
      "epoch": 0.3544680981783553,
      "grad_norm": 0.363537073135376,
      "learning_rate": 1.851072035320265e-05,
      "loss": 0.608,
      "step": 11539
    },
    {
      "epoch": 0.35449881731330446,
      "grad_norm": 0.39967870712280273,
      "learning_rate": 1.851046659901021e-05,
      "loss": 0.6181,
      "step": 11540
    },
    {
      "epoch": 0.35452953644825363,
      "grad_norm": 0.503963828086853,
      "learning_rate": 1.851021282494098e-05,
      "loss": 0.5306,
      "step": 11541
    },
    {
      "epoch": 0.35456025558320275,
      "grad_norm": 0.38950490951538086,
      "learning_rate": 1.850995903099555e-05,
      "loss": 0.6003,
      "step": 11542
    },
    {
      "epoch": 0.35459097471815193,
      "grad_norm": 0.35672727227211,
      "learning_rate": 1.850970521717452e-05,
      "loss": 0.6366,
      "step": 11543
    },
    {
      "epoch": 0.3546216938531011,
      "grad_norm": 0.5695829391479492,
      "learning_rate": 1.8509451383478482e-05,
      "loss": 0.5116,
      "step": 11544
    },
    {
      "epoch": 0.3546524129880503,
      "grad_norm": 0.6924694180488586,
      "learning_rate": 1.850919752990802e-05,
      "loss": 0.4818,
      "step": 11545
    },
    {
      "epoch": 0.3546831321229994,
      "grad_norm": 0.38127410411834717,
      "learning_rate": 1.8508943656463737e-05,
      "loss": 0.5358,
      "step": 11546
    },
    {
      "epoch": 0.3547138512579486,
      "grad_norm": 0.35982370376586914,
      "learning_rate": 1.850868976314622e-05,
      "loss": 0.6266,
      "step": 11547
    },
    {
      "epoch": 0.35474457039289775,
      "grad_norm": 0.341376394033432,
      "learning_rate": 1.8508435849956064e-05,
      "loss": 0.5238,
      "step": 11548
    },
    {
      "epoch": 0.35477528952784687,
      "grad_norm": 0.4522336423397064,
      "learning_rate": 1.8508181916893865e-05,
      "loss": 0.6384,
      "step": 11549
    },
    {
      "epoch": 0.35480600866279605,
      "grad_norm": 0.37664806842803955,
      "learning_rate": 1.8507927963960208e-05,
      "loss": 0.604,
      "step": 11550
    },
    {
      "epoch": 0.3548367277977452,
      "grad_norm": 0.3381824791431427,
      "learning_rate": 1.8507673991155693e-05,
      "loss": 0.6151,
      "step": 11551
    },
    {
      "epoch": 0.3548674469326944,
      "grad_norm": 0.37792062759399414,
      "learning_rate": 1.8507419998480914e-05,
      "loss": 0.5944,
      "step": 11552
    },
    {
      "epoch": 0.3548981660676435,
      "grad_norm": 0.31625279784202576,
      "learning_rate": 1.8507165985936456e-05,
      "loss": 0.6786,
      "step": 11553
    },
    {
      "epoch": 0.3549288852025927,
      "grad_norm": 0.4614350199699402,
      "learning_rate": 1.8506911953522923e-05,
      "loss": 0.5852,
      "step": 11554
    },
    {
      "epoch": 0.35495960433754187,
      "grad_norm": 0.31837478280067444,
      "learning_rate": 1.85066579012409e-05,
      "loss": 0.5849,
      "step": 11555
    },
    {
      "epoch": 0.354990323472491,
      "grad_norm": 0.3598499298095703,
      "learning_rate": 1.8506403829090985e-05,
      "loss": 0.5626,
      "step": 11556
    },
    {
      "epoch": 0.35502104260744016,
      "grad_norm": 0.3209093511104584,
      "learning_rate": 1.850614973707377e-05,
      "loss": 0.6366,
      "step": 11557
    },
    {
      "epoch": 0.35505176174238934,
      "grad_norm": 0.42452552914619446,
      "learning_rate": 1.8505895625189846e-05,
      "loss": 0.5825,
      "step": 11558
    },
    {
      "epoch": 0.3550824808773385,
      "grad_norm": 0.3284940719604492,
      "learning_rate": 1.850564149343981e-05,
      "loss": 0.4991,
      "step": 11559
    },
    {
      "epoch": 0.35511320001228763,
      "grad_norm": 0.32355445623397827,
      "learning_rate": 1.8505387341824254e-05,
      "loss": 0.5908,
      "step": 11560
    },
    {
      "epoch": 0.3551439191472368,
      "grad_norm": 0.3206007778644562,
      "learning_rate": 1.850513317034377e-05,
      "loss": 0.5376,
      "step": 11561
    },
    {
      "epoch": 0.355174638282186,
      "grad_norm": 0.37981000542640686,
      "learning_rate": 1.8504878978998955e-05,
      "loss": 0.519,
      "step": 11562
    },
    {
      "epoch": 0.35520535741713516,
      "grad_norm": 0.3483045995235443,
      "learning_rate": 1.85046247677904e-05,
      "loss": 0.5141,
      "step": 11563
    },
    {
      "epoch": 0.3552360765520843,
      "grad_norm": 0.35553765296936035,
      "learning_rate": 1.8504370536718707e-05,
      "loss": 0.539,
      "step": 11564
    },
    {
      "epoch": 0.35526679568703345,
      "grad_norm": 0.36032044887542725,
      "learning_rate": 1.8504116285784456e-05,
      "loss": 0.596,
      "step": 11565
    },
    {
      "epoch": 0.35529751482198263,
      "grad_norm": 0.37693607807159424,
      "learning_rate": 1.8503862014988248e-05,
      "loss": 0.5776,
      "step": 11566
    },
    {
      "epoch": 0.35532823395693175,
      "grad_norm": 0.3534729778766632,
      "learning_rate": 1.8503607724330676e-05,
      "loss": 0.6845,
      "step": 11567
    },
    {
      "epoch": 0.3553589530918809,
      "grad_norm": 0.3586033880710602,
      "learning_rate": 1.8503353413812333e-05,
      "loss": 0.5548,
      "step": 11568
    },
    {
      "epoch": 0.3553896722268301,
      "grad_norm": 0.6165415644645691,
      "learning_rate": 1.850309908343382e-05,
      "loss": 0.657,
      "step": 11569
    },
    {
      "epoch": 0.3554203913617793,
      "grad_norm": 0.38743531703948975,
      "learning_rate": 1.850284473319572e-05,
      "loss": 0.6361,
      "step": 11570
    },
    {
      "epoch": 0.3554511104967284,
      "grad_norm": 0.358366996049881,
      "learning_rate": 1.8502590363098637e-05,
      "loss": 0.5201,
      "step": 11571
    },
    {
      "epoch": 0.35548182963167757,
      "grad_norm": 0.3286268413066864,
      "learning_rate": 1.8502335973143156e-05,
      "loss": 0.429,
      "step": 11572
    },
    {
      "epoch": 0.35551254876662675,
      "grad_norm": 0.34214577078819275,
      "learning_rate": 1.8502081563329878e-05,
      "loss": 0.5651,
      "step": 11573
    },
    {
      "epoch": 0.35554326790157587,
      "grad_norm": 0.33934396505355835,
      "learning_rate": 1.850182713365939e-05,
      "loss": 0.5848,
      "step": 11574
    },
    {
      "epoch": 0.35557398703652504,
      "grad_norm": 0.33535683155059814,
      "learning_rate": 1.85015726841323e-05,
      "loss": 0.6079,
      "step": 11575
    },
    {
      "epoch": 0.3556047061714742,
      "grad_norm": 0.6228156685829163,
      "learning_rate": 1.8501318214749186e-05,
      "loss": 0.5165,
      "step": 11576
    },
    {
      "epoch": 0.3556354253064234,
      "grad_norm": 0.3579408824443817,
      "learning_rate": 1.8501063725510652e-05,
      "loss": 0.5282,
      "step": 11577
    },
    {
      "epoch": 0.3556661444413725,
      "grad_norm": 0.35360994935035706,
      "learning_rate": 1.850080921641729e-05,
      "loss": 0.5677,
      "step": 11578
    },
    {
      "epoch": 0.3556968635763217,
      "grad_norm": 0.3685913681983948,
      "learning_rate": 1.850055468746969e-05,
      "loss": 0.5281,
      "step": 11579
    },
    {
      "epoch": 0.35572758271127086,
      "grad_norm": 0.34141677618026733,
      "learning_rate": 1.8500300138668458e-05,
      "loss": 0.5444,
      "step": 11580
    },
    {
      "epoch": 0.35575830184622004,
      "grad_norm": 0.3426637351512909,
      "learning_rate": 1.850004557001418e-05,
      "loss": 0.5869,
      "step": 11581
    },
    {
      "epoch": 0.35578902098116916,
      "grad_norm": 0.3443811535835266,
      "learning_rate": 1.849979098150745e-05,
      "loss": 0.5148,
      "step": 11582
    },
    {
      "epoch": 0.35581974011611833,
      "grad_norm": 0.40011927485466003,
      "learning_rate": 1.8499536373148862e-05,
      "loss": 0.5776,
      "step": 11583
    },
    {
      "epoch": 0.3558504592510675,
      "grad_norm": 0.3567568361759186,
      "learning_rate": 1.8499281744939015e-05,
      "loss": 0.5705,
      "step": 11584
    },
    {
      "epoch": 0.35588117838601663,
      "grad_norm": 0.32651814818382263,
      "learning_rate": 1.84990270968785e-05,
      "loss": 0.5883,
      "step": 11585
    },
    {
      "epoch": 0.3559118975209658,
      "grad_norm": 0.35985854268074036,
      "learning_rate": 1.849877242896792e-05,
      "loss": 0.5879,
      "step": 11586
    },
    {
      "epoch": 0.355942616655915,
      "grad_norm": 0.36706897616386414,
      "learning_rate": 1.849851774120786e-05,
      "loss": 0.7047,
      "step": 11587
    },
    {
      "epoch": 0.35597333579086415,
      "grad_norm": 0.35213524103164673,
      "learning_rate": 1.8498263033598918e-05,
      "loss": 0.5813,
      "step": 11588
    },
    {
      "epoch": 0.3560040549258133,
      "grad_norm": 0.4593988358974457,
      "learning_rate": 1.849800830614169e-05,
      "loss": 0.6584,
      "step": 11589
    },
    {
      "epoch": 0.35603477406076245,
      "grad_norm": 0.3547353148460388,
      "learning_rate": 1.8497753558836766e-05,
      "loss": 0.5955,
      "step": 11590
    },
    {
      "epoch": 0.3560654931957116,
      "grad_norm": 0.42281806468963623,
      "learning_rate": 1.8497498791684753e-05,
      "loss": 0.6292,
      "step": 11591
    },
    {
      "epoch": 0.35609621233066074,
      "grad_norm": 0.3334449529647827,
      "learning_rate": 1.849724400468623e-05,
      "loss": 0.4666,
      "step": 11592
    },
    {
      "epoch": 0.3561269314656099,
      "grad_norm": 0.34311679005622864,
      "learning_rate": 1.8496989197841807e-05,
      "loss": 0.5764,
      "step": 11593
    },
    {
      "epoch": 0.3561576506005591,
      "grad_norm": 0.3677627444267273,
      "learning_rate": 1.8496734371152065e-05,
      "loss": 0.5919,
      "step": 11594
    },
    {
      "epoch": 0.35618836973550827,
      "grad_norm": 0.3686603903770447,
      "learning_rate": 1.8496479524617612e-05,
      "loss": 0.6146,
      "step": 11595
    },
    {
      "epoch": 0.3562190888704574,
      "grad_norm": 0.3793373703956604,
      "learning_rate": 1.8496224658239037e-05,
      "loss": 0.6876,
      "step": 11596
    },
    {
      "epoch": 0.35624980800540657,
      "grad_norm": 0.38275212049484253,
      "learning_rate": 1.8495969772016934e-05,
      "loss": 0.5018,
      "step": 11597
    },
    {
      "epoch": 0.35628052714035574,
      "grad_norm": 0.310195654630661,
      "learning_rate": 1.84957148659519e-05,
      "loss": 0.563,
      "step": 11598
    },
    {
      "epoch": 0.35631124627530486,
      "grad_norm": 0.3128136992454529,
      "learning_rate": 1.8495459940044535e-05,
      "loss": 0.6123,
      "step": 11599
    },
    {
      "epoch": 0.35634196541025404,
      "grad_norm": 0.34654533863067627,
      "learning_rate": 1.8495204994295425e-05,
      "loss": 0.6166,
      "step": 11600
    },
    {
      "epoch": 0.3563726845452032,
      "grad_norm": 0.33667364716529846,
      "learning_rate": 1.8494950028705176e-05,
      "loss": 0.5761,
      "step": 11601
    },
    {
      "epoch": 0.3564034036801524,
      "grad_norm": 0.3667745590209961,
      "learning_rate": 1.8494695043274372e-05,
      "loss": 0.5291,
      "step": 11602
    },
    {
      "epoch": 0.3564341228151015,
      "grad_norm": 0.39484214782714844,
      "learning_rate": 1.8494440038003617e-05,
      "loss": 0.5903,
      "step": 11603
    },
    {
      "epoch": 0.3564648419500507,
      "grad_norm": 0.347368448972702,
      "learning_rate": 1.84941850128935e-05,
      "loss": 0.5359,
      "step": 11604
    },
    {
      "epoch": 0.35649556108499986,
      "grad_norm": 0.3288450539112091,
      "learning_rate": 1.8493929967944626e-05,
      "loss": 0.5185,
      "step": 11605
    },
    {
      "epoch": 0.35652628021994903,
      "grad_norm": 0.39362528920173645,
      "learning_rate": 1.8493674903157585e-05,
      "loss": 0.6382,
      "step": 11606
    },
    {
      "epoch": 0.35655699935489815,
      "grad_norm": 0.3316851556301117,
      "learning_rate": 1.8493419818532976e-05,
      "loss": 0.5942,
      "step": 11607
    },
    {
      "epoch": 0.3565877184898473,
      "grad_norm": 0.46946170926094055,
      "learning_rate": 1.8493164714071383e-05,
      "loss": 0.67,
      "step": 11608
    },
    {
      "epoch": 0.3566184376247965,
      "grad_norm": 0.3725631833076477,
      "learning_rate": 1.8492909589773417e-05,
      "loss": 0.6534,
      "step": 11609
    },
    {
      "epoch": 0.3566491567597456,
      "grad_norm": 1.6233924627304077,
      "learning_rate": 1.8492654445639667e-05,
      "loss": 0.5559,
      "step": 11610
    },
    {
      "epoch": 0.3566798758946948,
      "grad_norm": 0.34608110785484314,
      "learning_rate": 1.8492399281670727e-05,
      "loss": 0.5992,
      "step": 11611
    },
    {
      "epoch": 0.356710595029644,
      "grad_norm": 0.3288954794406891,
      "learning_rate": 1.84921440978672e-05,
      "loss": 0.5372,
      "step": 11612
    },
    {
      "epoch": 0.35674131416459315,
      "grad_norm": 0.3373855948448181,
      "learning_rate": 1.849188889422967e-05,
      "loss": 0.5462,
      "step": 11613
    },
    {
      "epoch": 0.35677203329954227,
      "grad_norm": 0.5265805721282959,
      "learning_rate": 1.8491633670758745e-05,
      "loss": 0.5814,
      "step": 11614
    },
    {
      "epoch": 0.35680275243449144,
      "grad_norm": 0.39878928661346436,
      "learning_rate": 1.8491378427455018e-05,
      "loss": 0.6456,
      "step": 11615
    },
    {
      "epoch": 0.3568334715694406,
      "grad_norm": 0.4096943438053131,
      "learning_rate": 1.849112316431908e-05,
      "loss": 0.5835,
      "step": 11616
    },
    {
      "epoch": 0.35686419070438974,
      "grad_norm": 0.3363865911960602,
      "learning_rate": 1.8490867881351533e-05,
      "loss": 0.5008,
      "step": 11617
    },
    {
      "epoch": 0.3568949098393389,
      "grad_norm": 0.346894234418869,
      "learning_rate": 1.849061257855297e-05,
      "loss": 0.5403,
      "step": 11618
    },
    {
      "epoch": 0.3569256289742881,
      "grad_norm": 0.3581332564353943,
      "learning_rate": 1.849035725592399e-05,
      "loss": 0.5926,
      "step": 11619
    },
    {
      "epoch": 0.35695634810923726,
      "grad_norm": 0.3502283990383148,
      "learning_rate": 1.8490101913465186e-05,
      "loss": 0.5832,
      "step": 11620
    },
    {
      "epoch": 0.3569870672441864,
      "grad_norm": 0.3850718140602112,
      "learning_rate": 1.8489846551177156e-05,
      "loss": 0.6334,
      "step": 11621
    },
    {
      "epoch": 0.35701778637913556,
      "grad_norm": 0.3347374498844147,
      "learning_rate": 1.8489591169060497e-05,
      "loss": 0.6291,
      "step": 11622
    },
    {
      "epoch": 0.35704850551408474,
      "grad_norm": 0.3877977430820465,
      "learning_rate": 1.8489335767115807e-05,
      "loss": 0.6389,
      "step": 11623
    },
    {
      "epoch": 0.3570792246490339,
      "grad_norm": 0.3602772653102875,
      "learning_rate": 1.848908034534368e-05,
      "loss": 0.5769,
      "step": 11624
    },
    {
      "epoch": 0.35710994378398303,
      "grad_norm": 0.31323307752609253,
      "learning_rate": 1.8488824903744707e-05,
      "loss": 0.5221,
      "step": 11625
    },
    {
      "epoch": 0.3571406629189322,
      "grad_norm": 0.37536412477493286,
      "learning_rate": 1.8488569442319497e-05,
      "loss": 0.6052,
      "step": 11626
    },
    {
      "epoch": 0.3571713820538814,
      "grad_norm": 0.3558522164821625,
      "learning_rate": 1.8488313961068637e-05,
      "loss": 0.6148,
      "step": 11627
    },
    {
      "epoch": 0.3572021011888305,
      "grad_norm": 0.40029868483543396,
      "learning_rate": 1.848805845999273e-05,
      "loss": 0.5683,
      "step": 11628
    },
    {
      "epoch": 0.3572328203237797,
      "grad_norm": 0.40381908416748047,
      "learning_rate": 1.848780293909237e-05,
      "loss": 0.6395,
      "step": 11629
    },
    {
      "epoch": 0.35726353945872885,
      "grad_norm": 0.3321738541126251,
      "learning_rate": 1.8487547398368147e-05,
      "loss": 0.5362,
      "step": 11630
    },
    {
      "epoch": 0.357294258593678,
      "grad_norm": 0.3116963803768158,
      "learning_rate": 1.848729183782067e-05,
      "loss": 0.5794,
      "step": 11631
    },
    {
      "epoch": 0.35732497772862715,
      "grad_norm": 0.4029768705368042,
      "learning_rate": 1.8487036257450527e-05,
      "loss": 0.5798,
      "step": 11632
    },
    {
      "epoch": 0.3573556968635763,
      "grad_norm": 0.4539543390274048,
      "learning_rate": 1.848678065725832e-05,
      "loss": 0.6249,
      "step": 11633
    },
    {
      "epoch": 0.3573864159985255,
      "grad_norm": 0.35968858003616333,
      "learning_rate": 1.8486525037244643e-05,
      "loss": 0.5941,
      "step": 11634
    },
    {
      "epoch": 0.3574171351334746,
      "grad_norm": 0.3408176302909851,
      "learning_rate": 1.8486269397410096e-05,
      "loss": 0.6362,
      "step": 11635
    },
    {
      "epoch": 0.3574478542684238,
      "grad_norm": 0.344531387090683,
      "learning_rate": 1.8486013737755276e-05,
      "loss": 0.5188,
      "step": 11636
    },
    {
      "epoch": 0.35747857340337297,
      "grad_norm": 0.4240998327732086,
      "learning_rate": 1.8485758058280773e-05,
      "loss": 0.6627,
      "step": 11637
    },
    {
      "epoch": 0.35750929253832214,
      "grad_norm": 0.3494747281074524,
      "learning_rate": 1.8485502358987193e-05,
      "loss": 0.5536,
      "step": 11638
    },
    {
      "epoch": 0.35754001167327126,
      "grad_norm": 0.3498668074607849,
      "learning_rate": 1.848524663987513e-05,
      "loss": 0.52,
      "step": 11639
    },
    {
      "epoch": 0.35757073080822044,
      "grad_norm": 0.31525862216949463,
      "learning_rate": 1.8484990900945177e-05,
      "loss": 0.5196,
      "step": 11640
    },
    {
      "epoch": 0.3576014499431696,
      "grad_norm": 0.33531031012535095,
      "learning_rate": 1.8484735142197938e-05,
      "loss": 0.5601,
      "step": 11641
    },
    {
      "epoch": 0.35763216907811873,
      "grad_norm": 0.3574948310852051,
      "learning_rate": 1.8484479363634007e-05,
      "loss": 0.6111,
      "step": 11642
    },
    {
      "epoch": 0.3576628882130679,
      "grad_norm": 0.5686089992523193,
      "learning_rate": 1.848422356525398e-05,
      "loss": 0.5916,
      "step": 11643
    },
    {
      "epoch": 0.3576936073480171,
      "grad_norm": 0.36022162437438965,
      "learning_rate": 1.848396774705846e-05,
      "loss": 0.5763,
      "step": 11644
    },
    {
      "epoch": 0.35772432648296626,
      "grad_norm": 0.3505399227142334,
      "learning_rate": 1.8483711909048038e-05,
      "loss": 0.5939,
      "step": 11645
    },
    {
      "epoch": 0.3577550456179154,
      "grad_norm": 0.4645322859287262,
      "learning_rate": 1.8483456051223318e-05,
      "loss": 0.5793,
      "step": 11646
    },
    {
      "epoch": 0.35778576475286455,
      "grad_norm": 0.38813725113868713,
      "learning_rate": 1.848320017358489e-05,
      "loss": 0.5374,
      "step": 11647
    },
    {
      "epoch": 0.35781648388781373,
      "grad_norm": 0.3335341513156891,
      "learning_rate": 1.8482944276133357e-05,
      "loss": 0.651,
      "step": 11648
    },
    {
      "epoch": 0.3578472030227629,
      "grad_norm": 0.34052199125289917,
      "learning_rate": 1.8482688358869315e-05,
      "loss": 0.6361,
      "step": 11649
    },
    {
      "epoch": 0.357877922157712,
      "grad_norm": 0.34598883986473083,
      "learning_rate": 1.848243242179336e-05,
      "loss": 0.5734,
      "step": 11650
    },
    {
      "epoch": 0.3579086412926612,
      "grad_norm": 0.34892889857292175,
      "learning_rate": 1.8482176464906097e-05,
      "loss": 0.5903,
      "step": 11651
    },
    {
      "epoch": 0.3579393604276104,
      "grad_norm": 0.3182014524936676,
      "learning_rate": 1.8481920488208115e-05,
      "loss": 0.6114,
      "step": 11652
    },
    {
      "epoch": 0.3579700795625595,
      "grad_norm": 0.33331069350242615,
      "learning_rate": 1.8481664491700015e-05,
      "loss": 0.5851,
      "step": 11653
    },
    {
      "epoch": 0.35800079869750867,
      "grad_norm": 0.3161930739879608,
      "learning_rate": 1.8481408475382396e-05,
      "loss": 0.5569,
      "step": 11654
    },
    {
      "epoch": 0.35803151783245785,
      "grad_norm": 0.3309761583805084,
      "learning_rate": 1.8481152439255854e-05,
      "loss": 0.5772,
      "step": 11655
    },
    {
      "epoch": 0.358062236967407,
      "grad_norm": 0.4448913633823395,
      "learning_rate": 1.8480896383320986e-05,
      "loss": 0.6744,
      "step": 11656
    },
    {
      "epoch": 0.35809295610235614,
      "grad_norm": 0.548290491104126,
      "learning_rate": 1.84806403075784e-05,
      "loss": 0.5877,
      "step": 11657
    },
    {
      "epoch": 0.3581236752373053,
      "grad_norm": 0.36135393381118774,
      "learning_rate": 1.848038421202868e-05,
      "loss": 0.4878,
      "step": 11658
    },
    {
      "epoch": 0.3581543943722545,
      "grad_norm": 0.4675532579421997,
      "learning_rate": 1.848012809667243e-05,
      "loss": 0.61,
      "step": 11659
    },
    {
      "epoch": 0.3581851135072036,
      "grad_norm": 0.34075579047203064,
      "learning_rate": 1.8479871961510253e-05,
      "loss": 0.6245,
      "step": 11660
    },
    {
      "epoch": 0.3582158326421528,
      "grad_norm": 0.33287501335144043,
      "learning_rate": 1.847961580654274e-05,
      "loss": 0.5722,
      "step": 11661
    },
    {
      "epoch": 0.35824655177710196,
      "grad_norm": 0.3130570948123932,
      "learning_rate": 1.847935963177049e-05,
      "loss": 0.5991,
      "step": 11662
    },
    {
      "epoch": 0.35827727091205114,
      "grad_norm": 0.36148953437805176,
      "learning_rate": 1.8479103437194106e-05,
      "loss": 0.5638,
      "step": 11663
    },
    {
      "epoch": 0.35830799004700026,
      "grad_norm": 0.3345212936401367,
      "learning_rate": 1.8478847222814184e-05,
      "loss": 0.5441,
      "step": 11664
    },
    {
      "epoch": 0.35833870918194943,
      "grad_norm": 0.3704197406768799,
      "learning_rate": 1.8478590988631322e-05,
      "loss": 0.5402,
      "step": 11665
    },
    {
      "epoch": 0.3583694283168986,
      "grad_norm": 0.3576642572879791,
      "learning_rate": 1.8478334734646117e-05,
      "loss": 0.6156,
      "step": 11666
    },
    {
      "epoch": 0.3584001474518478,
      "grad_norm": 0.3286057710647583,
      "learning_rate": 1.847807846085917e-05,
      "loss": 0.5222,
      "step": 11667
    },
    {
      "epoch": 0.3584308665867969,
      "grad_norm": 0.3608143925666809,
      "learning_rate": 1.847782216727108e-05,
      "loss": 0.6025,
      "step": 11668
    },
    {
      "epoch": 0.3584615857217461,
      "grad_norm": 0.3678131103515625,
      "learning_rate": 1.8477565853882444e-05,
      "loss": 0.6068,
      "step": 11669
    },
    {
      "epoch": 0.35849230485669525,
      "grad_norm": 0.3440263569355011,
      "learning_rate": 1.847730952069386e-05,
      "loss": 0.6395,
      "step": 11670
    },
    {
      "epoch": 0.3585230239916444,
      "grad_norm": 0.36154410243034363,
      "learning_rate": 1.8477053167705928e-05,
      "loss": 0.5564,
      "step": 11671
    },
    {
      "epoch": 0.35855374312659355,
      "grad_norm": 0.3672161102294922,
      "learning_rate": 1.8476796794919247e-05,
      "loss": 0.6747,
      "step": 11672
    },
    {
      "epoch": 0.3585844622615427,
      "grad_norm": 0.3448673486709595,
      "learning_rate": 1.847654040233441e-05,
      "loss": 0.6132,
      "step": 11673
    },
    {
      "epoch": 0.3586151813964919,
      "grad_norm": 0.9930031299591064,
      "learning_rate": 1.8476283989952025e-05,
      "loss": 0.5749,
      "step": 11674
    },
    {
      "epoch": 0.358645900531441,
      "grad_norm": 0.34139832854270935,
      "learning_rate": 1.847602755777269e-05,
      "loss": 0.5917,
      "step": 11675
    },
    {
      "epoch": 0.3586766196663902,
      "grad_norm": 0.3703128695487976,
      "learning_rate": 1.8475771105796994e-05,
      "loss": 0.5882,
      "step": 11676
    },
    {
      "epoch": 0.35870733880133937,
      "grad_norm": 0.34542617201805115,
      "learning_rate": 1.8475514634025548e-05,
      "loss": 0.5805,
      "step": 11677
    },
    {
      "epoch": 0.3587380579362885,
      "grad_norm": 0.34635254740715027,
      "learning_rate": 1.8475258142458945e-05,
      "loss": 0.6125,
      "step": 11678
    },
    {
      "epoch": 0.35876877707123767,
      "grad_norm": 0.390459269285202,
      "learning_rate": 1.8475001631097786e-05,
      "loss": 0.5915,
      "step": 11679
    },
    {
      "epoch": 0.35879949620618684,
      "grad_norm": 0.5761540532112122,
      "learning_rate": 1.8474745099942662e-05,
      "loss": 0.5337,
      "step": 11680
    },
    {
      "epoch": 0.358830215341136,
      "grad_norm": 0.3574976623058319,
      "learning_rate": 1.8474488548994184e-05,
      "loss": 0.5338,
      "step": 11681
    },
    {
      "epoch": 0.35886093447608514,
      "grad_norm": 0.3608132600784302,
      "learning_rate": 1.8474231978252945e-05,
      "loss": 0.5725,
      "step": 11682
    },
    {
      "epoch": 0.3588916536110343,
      "grad_norm": 0.32292333245277405,
      "learning_rate": 1.8473975387719548e-05,
      "loss": 0.6122,
      "step": 11683
    },
    {
      "epoch": 0.3589223727459835,
      "grad_norm": 0.3710794150829315,
      "learning_rate": 1.8473718777394586e-05,
      "loss": 0.5591,
      "step": 11684
    },
    {
      "epoch": 0.3589530918809326,
      "grad_norm": 0.34265628457069397,
      "learning_rate": 1.847346214727866e-05,
      "loss": 0.4679,
      "step": 11685
    },
    {
      "epoch": 0.3589838110158818,
      "grad_norm": 0.3529175817966461,
      "learning_rate": 1.8473205497372378e-05,
      "loss": 0.5258,
      "step": 11686
    },
    {
      "epoch": 0.35901453015083096,
      "grad_norm": 0.4560835659503937,
      "learning_rate": 1.847294882767633e-05,
      "loss": 0.6576,
      "step": 11687
    },
    {
      "epoch": 0.35904524928578013,
      "grad_norm": 0.3602703809738159,
      "learning_rate": 1.8472692138191116e-05,
      "loss": 0.5805,
      "step": 11688
    },
    {
      "epoch": 0.35907596842072925,
      "grad_norm": 0.3633745610713959,
      "learning_rate": 1.847243542891734e-05,
      "loss": 0.5367,
      "step": 11689
    },
    {
      "epoch": 0.3591066875556784,
      "grad_norm": 0.3564493656158447,
      "learning_rate": 1.8472178699855598e-05,
      "loss": 0.6797,
      "step": 11690
    },
    {
      "epoch": 0.3591374066906276,
      "grad_norm": 0.3669878840446472,
      "learning_rate": 1.847192195100649e-05,
      "loss": 0.5921,
      "step": 11691
    },
    {
      "epoch": 0.3591681258255768,
      "grad_norm": 0.4042571783065796,
      "learning_rate": 1.847166518237062e-05,
      "loss": 0.5985,
      "step": 11692
    },
    {
      "epoch": 0.3591988449605259,
      "grad_norm": 0.33851373195648193,
      "learning_rate": 1.8471408393948586e-05,
      "loss": 0.516,
      "step": 11693
    },
    {
      "epoch": 0.3592295640954751,
      "grad_norm": 0.4881036579608917,
      "learning_rate": 1.8471151585740982e-05,
      "loss": 0.6427,
      "step": 11694
    },
    {
      "epoch": 0.35926028323042425,
      "grad_norm": 0.3767602741718292,
      "learning_rate": 1.8470894757748414e-05,
      "loss": 0.6679,
      "step": 11695
    },
    {
      "epoch": 0.35929100236537337,
      "grad_norm": 0.32512032985687256,
      "learning_rate": 1.8470637909971476e-05,
      "loss": 0.5773,
      "step": 11696
    },
    {
      "epoch": 0.35932172150032254,
      "grad_norm": 0.34986332058906555,
      "learning_rate": 1.8470381042410774e-05,
      "loss": 0.563,
      "step": 11697
    },
    {
      "epoch": 0.3593524406352717,
      "grad_norm": 0.3612254858016968,
      "learning_rate": 1.8470124155066905e-05,
      "loss": 0.5948,
      "step": 11698
    },
    {
      "epoch": 0.3593831597702209,
      "grad_norm": 0.330427885055542,
      "learning_rate": 1.846986724794047e-05,
      "loss": 0.6128,
      "step": 11699
    },
    {
      "epoch": 0.35941387890517,
      "grad_norm": 0.37628844380378723,
      "learning_rate": 1.8469610321032068e-05,
      "loss": 0.6784,
      "step": 11700
    },
    {
      "epoch": 0.3594445980401192,
      "grad_norm": 0.3277653753757477,
      "learning_rate": 1.8469353374342302e-05,
      "loss": 0.5736,
      "step": 11701
    },
    {
      "epoch": 0.35947531717506837,
      "grad_norm": 0.3490961194038391,
      "learning_rate": 1.8469096407871766e-05,
      "loss": 0.5704,
      "step": 11702
    },
    {
      "epoch": 0.3595060363100175,
      "grad_norm": 0.3874584138393402,
      "learning_rate": 1.8468839421621066e-05,
      "loss": 0.5958,
      "step": 11703
    },
    {
      "epoch": 0.35953675544496666,
      "grad_norm": 0.3736210763454437,
      "learning_rate": 1.8468582415590802e-05,
      "loss": 0.6311,
      "step": 11704
    },
    {
      "epoch": 0.35956747457991584,
      "grad_norm": 0.3222174048423767,
      "learning_rate": 1.846832538978157e-05,
      "loss": 0.5532,
      "step": 11705
    },
    {
      "epoch": 0.359598193714865,
      "grad_norm": 0.3440132737159729,
      "learning_rate": 1.8468068344193972e-05,
      "loss": 0.6094,
      "step": 11706
    },
    {
      "epoch": 0.35962891284981413,
      "grad_norm": 0.37193572521209717,
      "learning_rate": 1.846781127882861e-05,
      "loss": 0.5793,
      "step": 11707
    },
    {
      "epoch": 0.3596596319847633,
      "grad_norm": 0.4482770562171936,
      "learning_rate": 1.846755419368608e-05,
      "loss": 0.6265,
      "step": 11708
    },
    {
      "epoch": 0.3596903511197125,
      "grad_norm": 0.3558589220046997,
      "learning_rate": 1.846729708876699e-05,
      "loss": 0.6208,
      "step": 11709
    },
    {
      "epoch": 0.3597210702546616,
      "grad_norm": 0.40075141191482544,
      "learning_rate": 1.8467039964071936e-05,
      "loss": 0.5948,
      "step": 11710
    },
    {
      "epoch": 0.3597517893896108,
      "grad_norm": 0.345641553401947,
      "learning_rate": 1.846678281960152e-05,
      "loss": 0.5895,
      "step": 11711
    },
    {
      "epoch": 0.35978250852455995,
      "grad_norm": 0.376119464635849,
      "learning_rate": 1.846652565535634e-05,
      "loss": 0.5373,
      "step": 11712
    },
    {
      "epoch": 0.3598132276595091,
      "grad_norm": 0.34080782532691956,
      "learning_rate": 1.8466268471336995e-05,
      "loss": 0.6081,
      "step": 11713
    },
    {
      "epoch": 0.35984394679445825,
      "grad_norm": 0.31522583961486816,
      "learning_rate": 1.846601126754409e-05,
      "loss": 0.5593,
      "step": 11714
    },
    {
      "epoch": 0.3598746659294074,
      "grad_norm": 0.36093562841415405,
      "learning_rate": 1.8465754043978225e-05,
      "loss": 0.532,
      "step": 11715
    },
    {
      "epoch": 0.3599053850643566,
      "grad_norm": 0.37767502665519714,
      "learning_rate": 1.846549680064e-05,
      "loss": 0.5495,
      "step": 11716
    },
    {
      "epoch": 0.3599361041993058,
      "grad_norm": 0.34518328309059143,
      "learning_rate": 1.846523953753002e-05,
      "loss": 0.5695,
      "step": 11717
    },
    {
      "epoch": 0.3599668233342549,
      "grad_norm": 0.3545691967010498,
      "learning_rate": 1.846498225464888e-05,
      "loss": 0.5154,
      "step": 11718
    },
    {
      "epoch": 0.35999754246920407,
      "grad_norm": 0.3569391369819641,
      "learning_rate": 1.846472495199718e-05,
      "loss": 0.5872,
      "step": 11719
    },
    {
      "epoch": 0.36002826160415324,
      "grad_norm": 0.35374027490615845,
      "learning_rate": 1.8464467629575523e-05,
      "loss": 0.63,
      "step": 11720
    },
    {
      "epoch": 0.36005898073910236,
      "grad_norm": 0.4996431767940521,
      "learning_rate": 1.8464210287384516e-05,
      "loss": 0.636,
      "step": 11721
    },
    {
      "epoch": 0.36008969987405154,
      "grad_norm": 0.31261909008026123,
      "learning_rate": 1.846395292542475e-05,
      "loss": 0.5588,
      "step": 11722
    },
    {
      "epoch": 0.3601204190090007,
      "grad_norm": 0.34321102499961853,
      "learning_rate": 1.8463695543696832e-05,
      "loss": 0.5617,
      "step": 11723
    },
    {
      "epoch": 0.3601511381439499,
      "grad_norm": 0.3565045893192291,
      "learning_rate": 1.8463438142201362e-05,
      "loss": 0.5099,
      "step": 11724
    },
    {
      "epoch": 0.360181857278899,
      "grad_norm": 0.32138797640800476,
      "learning_rate": 1.8463180720938942e-05,
      "loss": 0.5709,
      "step": 11725
    },
    {
      "epoch": 0.3602125764138482,
      "grad_norm": 0.3534223437309265,
      "learning_rate": 1.846292327991017e-05,
      "loss": 0.6011,
      "step": 11726
    },
    {
      "epoch": 0.36024329554879736,
      "grad_norm": 0.42619574069976807,
      "learning_rate": 1.8462665819115652e-05,
      "loss": 0.6102,
      "step": 11727
    },
    {
      "epoch": 0.3602740146837465,
      "grad_norm": 0.46899691224098206,
      "learning_rate": 1.846240833855599e-05,
      "loss": 0.631,
      "step": 11728
    },
    {
      "epoch": 0.36030473381869565,
      "grad_norm": 0.4168407618999481,
      "learning_rate": 1.8462150838231778e-05,
      "loss": 0.5691,
      "step": 11729
    },
    {
      "epoch": 0.36033545295364483,
      "grad_norm": 0.34950071573257446,
      "learning_rate": 1.846189331814362e-05,
      "loss": 0.5858,
      "step": 11730
    },
    {
      "epoch": 0.360366172088594,
      "grad_norm": 0.3997926414012909,
      "learning_rate": 1.8461635778292123e-05,
      "loss": 0.5638,
      "step": 11731
    },
    {
      "epoch": 0.3603968912235431,
      "grad_norm": 0.32428717613220215,
      "learning_rate": 1.846137821867788e-05,
      "loss": 0.5547,
      "step": 11732
    },
    {
      "epoch": 0.3604276103584923,
      "grad_norm": 0.38384801149368286,
      "learning_rate": 1.84611206393015e-05,
      "loss": 0.566,
      "step": 11733
    },
    {
      "epoch": 0.3604583294934415,
      "grad_norm": 0.3421359062194824,
      "learning_rate": 1.8460863040163585e-05,
      "loss": 0.5948,
      "step": 11734
    },
    {
      "epoch": 0.36048904862839065,
      "grad_norm": 0.3239459693431854,
      "learning_rate": 1.846060542126473e-05,
      "loss": 0.5079,
      "step": 11735
    },
    {
      "epoch": 0.36051976776333977,
      "grad_norm": 0.3780747056007385,
      "learning_rate": 1.8460347782605543e-05,
      "loss": 0.5738,
      "step": 11736
    },
    {
      "epoch": 0.36055048689828895,
      "grad_norm": 0.3340228497982025,
      "learning_rate": 1.846009012418662e-05,
      "loss": 0.6009,
      "step": 11737
    },
    {
      "epoch": 0.3605812060332381,
      "grad_norm": 0.3393832743167877,
      "learning_rate": 1.8459832446008566e-05,
      "loss": 0.5689,
      "step": 11738
    },
    {
      "epoch": 0.36061192516818724,
      "grad_norm": 0.3381108343601227,
      "learning_rate": 1.8459574748071985e-05,
      "loss": 0.551,
      "step": 11739
    },
    {
      "epoch": 0.3606426443031364,
      "grad_norm": 0.33748963475227356,
      "learning_rate": 1.845931703037747e-05,
      "loss": 0.5666,
      "step": 11740
    },
    {
      "epoch": 0.3606733634380856,
      "grad_norm": 0.34414440393447876,
      "learning_rate": 1.8459059292925635e-05,
      "loss": 0.5919,
      "step": 11741
    },
    {
      "epoch": 0.36070408257303477,
      "grad_norm": 0.31701144576072693,
      "learning_rate": 1.8458801535717076e-05,
      "loss": 0.54,
      "step": 11742
    },
    {
      "epoch": 0.3607348017079839,
      "grad_norm": 0.3418810963630676,
      "learning_rate": 1.8458543758752396e-05,
      "loss": 0.523,
      "step": 11743
    },
    {
      "epoch": 0.36076552084293306,
      "grad_norm": 0.3167153298854828,
      "learning_rate": 1.8458285962032193e-05,
      "loss": 0.5438,
      "step": 11744
    },
    {
      "epoch": 0.36079623997788224,
      "grad_norm": 0.3444059193134308,
      "learning_rate": 1.8458028145557074e-05,
      "loss": 0.5843,
      "step": 11745
    },
    {
      "epoch": 0.36082695911283136,
      "grad_norm": 0.395694375038147,
      "learning_rate": 1.845777030932764e-05,
      "loss": 0.5315,
      "step": 11746
    },
    {
      "epoch": 0.36085767824778053,
      "grad_norm": 0.35943877696990967,
      "learning_rate": 1.8457512453344492e-05,
      "loss": 0.6575,
      "step": 11747
    },
    {
      "epoch": 0.3608883973827297,
      "grad_norm": 0.42896050214767456,
      "learning_rate": 1.8457254577608234e-05,
      "loss": 0.5875,
      "step": 11748
    },
    {
      "epoch": 0.3609191165176789,
      "grad_norm": 0.35356003046035767,
      "learning_rate": 1.8456996682119466e-05,
      "loss": 0.6081,
      "step": 11749
    },
    {
      "epoch": 0.360949835652628,
      "grad_norm": 0.3356860876083374,
      "learning_rate": 1.845673876687879e-05,
      "loss": 0.5833,
      "step": 11750
    },
    {
      "epoch": 0.3609805547875772,
      "grad_norm": 0.3371163606643677,
      "learning_rate": 1.8456480831886813e-05,
      "loss": 0.6341,
      "step": 11751
    },
    {
      "epoch": 0.36101127392252635,
      "grad_norm": 0.47714465856552124,
      "learning_rate": 1.8456222877144133e-05,
      "loss": 0.6423,
      "step": 11752
    },
    {
      "epoch": 0.3610419930574755,
      "grad_norm": 0.32031431794166565,
      "learning_rate": 1.8455964902651356e-05,
      "loss": 0.5327,
      "step": 11753
    },
    {
      "epoch": 0.36107271219242465,
      "grad_norm": 0.4019853174686432,
      "learning_rate": 1.845570690840908e-05,
      "loss": 0.649,
      "step": 11754
    },
    {
      "epoch": 0.3611034313273738,
      "grad_norm": 0.3390180468559265,
      "learning_rate": 1.8455448894417913e-05,
      "loss": 0.5607,
      "step": 11755
    },
    {
      "epoch": 0.361134150462323,
      "grad_norm": 0.34782758355140686,
      "learning_rate": 1.845519086067845e-05,
      "loss": 0.6434,
      "step": 11756
    },
    {
      "epoch": 0.3611648695972721,
      "grad_norm": 0.36065974831581116,
      "learning_rate": 1.8454932807191302e-05,
      "loss": 0.5498,
      "step": 11757
    },
    {
      "epoch": 0.3611955887322213,
      "grad_norm": 0.39988359808921814,
      "learning_rate": 1.8454674733957064e-05,
      "loss": 0.6454,
      "step": 11758
    },
    {
      "epoch": 0.36122630786717047,
      "grad_norm": 0.357385516166687,
      "learning_rate": 1.8454416640976348e-05,
      "loss": 0.5179,
      "step": 11759
    },
    {
      "epoch": 0.36125702700211965,
      "grad_norm": 0.48375433683395386,
      "learning_rate": 1.8454158528249748e-05,
      "loss": 0.5407,
      "step": 11760
    },
    {
      "epoch": 0.36128774613706877,
      "grad_norm": 0.34277579188346863,
      "learning_rate": 1.8453900395777872e-05,
      "loss": 0.6115,
      "step": 11761
    },
    {
      "epoch": 0.36131846527201794,
      "grad_norm": 0.4010598659515381,
      "learning_rate": 1.845364224356132e-05,
      "loss": 0.5794,
      "step": 11762
    },
    {
      "epoch": 0.3613491844069671,
      "grad_norm": 0.31356751918792725,
      "learning_rate": 1.8453384071600696e-05,
      "loss": 0.531,
      "step": 11763
    },
    {
      "epoch": 0.36137990354191624,
      "grad_norm": 0.37324443459510803,
      "learning_rate": 1.8453125879896605e-05,
      "loss": 0.6206,
      "step": 11764
    },
    {
      "epoch": 0.3614106226768654,
      "grad_norm": 0.3590243458747864,
      "learning_rate": 1.8452867668449644e-05,
      "loss": 0.6099,
      "step": 11765
    },
    {
      "epoch": 0.3614413418118146,
      "grad_norm": 0.35223227739334106,
      "learning_rate": 1.8452609437260425e-05,
      "loss": 0.5893,
      "step": 11766
    },
    {
      "epoch": 0.36147206094676376,
      "grad_norm": 0.3552345335483551,
      "learning_rate": 1.8452351186329544e-05,
      "loss": 0.7082,
      "step": 11767
    },
    {
      "epoch": 0.3615027800817129,
      "grad_norm": 0.510814368724823,
      "learning_rate": 1.8452092915657606e-05,
      "loss": 0.594,
      "step": 11768
    },
    {
      "epoch": 0.36153349921666206,
      "grad_norm": 0.3880462646484375,
      "learning_rate": 1.8451834625245215e-05,
      "loss": 0.5904,
      "step": 11769
    },
    {
      "epoch": 0.36156421835161123,
      "grad_norm": 0.3834557831287384,
      "learning_rate": 1.8451576315092972e-05,
      "loss": 0.609,
      "step": 11770
    },
    {
      "epoch": 0.36159493748656035,
      "grad_norm": 0.3290703296661377,
      "learning_rate": 1.8451317985201487e-05,
      "loss": 0.5858,
      "step": 11771
    },
    {
      "epoch": 0.36162565662150953,
      "grad_norm": 0.3098900318145752,
      "learning_rate": 1.8451059635571356e-05,
      "loss": 0.5548,
      "step": 11772
    },
    {
      "epoch": 0.3616563757564587,
      "grad_norm": 0.3525715172290802,
      "learning_rate": 1.8450801266203186e-05,
      "loss": 0.5924,
      "step": 11773
    },
    {
      "epoch": 0.3616870948914079,
      "grad_norm": 0.34760451316833496,
      "learning_rate": 1.8450542877097583e-05,
      "loss": 0.6714,
      "step": 11774
    },
    {
      "epoch": 0.361717814026357,
      "grad_norm": 0.4033433198928833,
      "learning_rate": 1.845028446825514e-05,
      "loss": 0.5357,
      "step": 11775
    },
    {
      "epoch": 0.3617485331613062,
      "grad_norm": 0.3559158444404602,
      "learning_rate": 1.845002603967647e-05,
      "loss": 0.5346,
      "step": 11776
    },
    {
      "epoch": 0.36177925229625535,
      "grad_norm": 0.37289223074913025,
      "learning_rate": 1.844976759136217e-05,
      "loss": 0.5718,
      "step": 11777
    },
    {
      "epoch": 0.3618099714312045,
      "grad_norm": 0.3542799651622772,
      "learning_rate": 1.8449509123312857e-05,
      "loss": 0.6234,
      "step": 11778
    },
    {
      "epoch": 0.36184069056615364,
      "grad_norm": 0.3097146451473236,
      "learning_rate": 1.8449250635529118e-05,
      "loss": 0.6243,
      "step": 11779
    },
    {
      "epoch": 0.3618714097011028,
      "grad_norm": 0.3591543436050415,
      "learning_rate": 1.8448992128011568e-05,
      "loss": 0.6352,
      "step": 11780
    },
    {
      "epoch": 0.361902128836052,
      "grad_norm": 0.36390185356140137,
      "learning_rate": 1.8448733600760803e-05,
      "loss": 0.5989,
      "step": 11781
    },
    {
      "epoch": 0.3619328479710011,
      "grad_norm": 0.3217698633670807,
      "learning_rate": 1.8448475053777434e-05,
      "loss": 0.5514,
      "step": 11782
    },
    {
      "epoch": 0.3619635671059503,
      "grad_norm": 0.5795149207115173,
      "learning_rate": 1.8448216487062062e-05,
      "loss": 0.6071,
      "step": 11783
    },
    {
      "epoch": 0.36199428624089947,
      "grad_norm": 0.31856992840766907,
      "learning_rate": 1.844795790061529e-05,
      "loss": 0.659,
      "step": 11784
    },
    {
      "epoch": 0.36202500537584864,
      "grad_norm": 0.35359975695610046,
      "learning_rate": 1.8447699294437716e-05,
      "loss": 0.5299,
      "step": 11785
    },
    {
      "epoch": 0.36205572451079776,
      "grad_norm": 0.34842702746391296,
      "learning_rate": 1.8447440668529958e-05,
      "loss": 0.5012,
      "step": 11786
    },
    {
      "epoch": 0.36208644364574694,
      "grad_norm": 0.41335752606391907,
      "learning_rate": 1.844718202289261e-05,
      "loss": 0.5535,
      "step": 11787
    },
    {
      "epoch": 0.3621171627806961,
      "grad_norm": 0.3241906762123108,
      "learning_rate": 1.844692335752628e-05,
      "loss": 0.5828,
      "step": 11788
    },
    {
      "epoch": 0.36214788191564523,
      "grad_norm": 0.3808067739009857,
      "learning_rate": 1.8446664672431565e-05,
      "loss": 0.5974,
      "step": 11789
    },
    {
      "epoch": 0.3621786010505944,
      "grad_norm": 0.36013904213905334,
      "learning_rate": 1.844640596760908e-05,
      "loss": 0.5634,
      "step": 11790
    },
    {
      "epoch": 0.3622093201855436,
      "grad_norm": 0.38249385356903076,
      "learning_rate": 1.844614724305942e-05,
      "loss": 0.6572,
      "step": 11791
    },
    {
      "epoch": 0.36224003932049276,
      "grad_norm": 0.36368465423583984,
      "learning_rate": 1.8445888498783197e-05,
      "loss": 0.5703,
      "step": 11792
    },
    {
      "epoch": 0.3622707584554419,
      "grad_norm": 0.3404916524887085,
      "learning_rate": 1.844562973478101e-05,
      "loss": 0.6509,
      "step": 11793
    },
    {
      "epoch": 0.36230147759039105,
      "grad_norm": 0.3582603931427002,
      "learning_rate": 1.8445370951053465e-05,
      "loss": 0.5179,
      "step": 11794
    },
    {
      "epoch": 0.3623321967253402,
      "grad_norm": 0.3905051648616791,
      "learning_rate": 1.8445112147601166e-05,
      "loss": 0.5509,
      "step": 11795
    },
    {
      "epoch": 0.36236291586028935,
      "grad_norm": 0.6167184710502625,
      "learning_rate": 1.8444853324424717e-05,
      "loss": 0.5896,
      "step": 11796
    },
    {
      "epoch": 0.3623936349952385,
      "grad_norm": 0.5049555897712708,
      "learning_rate": 1.8444594481524725e-05,
      "loss": 0.6538,
      "step": 11797
    },
    {
      "epoch": 0.3624243541301877,
      "grad_norm": 0.322294145822525,
      "learning_rate": 1.8444335618901795e-05,
      "loss": 0.6052,
      "step": 11798
    },
    {
      "epoch": 0.3624550732651369,
      "grad_norm": 0.33478739857673645,
      "learning_rate": 1.8444076736556523e-05,
      "loss": 0.5385,
      "step": 11799
    },
    {
      "epoch": 0.362485792400086,
      "grad_norm": 0.3377440273761749,
      "learning_rate": 1.8443817834489525e-05,
      "loss": 0.5185,
      "step": 11800
    },
    {
      "epoch": 0.36251651153503517,
      "grad_norm": 0.33605456352233887,
      "learning_rate": 1.84435589127014e-05,
      "loss": 0.545,
      "step": 11801
    },
    {
      "epoch": 0.36254723066998434,
      "grad_norm": 0.3490135967731476,
      "learning_rate": 1.8443299971192755e-05,
      "loss": 0.5185,
      "step": 11802
    },
    {
      "epoch": 0.3625779498049335,
      "grad_norm": 0.31062743067741394,
      "learning_rate": 1.844304100996419e-05,
      "loss": 0.5096,
      "step": 11803
    },
    {
      "epoch": 0.36260866893988264,
      "grad_norm": 0.3322119116783142,
      "learning_rate": 1.8442782029016313e-05,
      "loss": 0.5666,
      "step": 11804
    },
    {
      "epoch": 0.3626393880748318,
      "grad_norm": 0.3489355444908142,
      "learning_rate": 1.8442523028349726e-05,
      "loss": 0.5294,
      "step": 11805
    },
    {
      "epoch": 0.362670107209781,
      "grad_norm": 0.33937618136405945,
      "learning_rate": 1.8442264007965047e-05,
      "loss": 0.5422,
      "step": 11806
    },
    {
      "epoch": 0.3627008263447301,
      "grad_norm": 0.374136745929718,
      "learning_rate": 1.8442004967862863e-05,
      "loss": 0.6159,
      "step": 11807
    },
    {
      "epoch": 0.3627315454796793,
      "grad_norm": 0.310507208108902,
      "learning_rate": 1.8441745908043788e-05,
      "loss": 0.5868,
      "step": 11808
    },
    {
      "epoch": 0.36276226461462846,
      "grad_norm": 0.32051563262939453,
      "learning_rate": 1.844148682850843e-05,
      "loss": 0.5783,
      "step": 11809
    },
    {
      "epoch": 0.36279298374957764,
      "grad_norm": 0.34414660930633545,
      "learning_rate": 1.8441227729257383e-05,
      "loss": 0.6195,
      "step": 11810
    },
    {
      "epoch": 0.36282370288452676,
      "grad_norm": 0.34124505519866943,
      "learning_rate": 1.8440968610291265e-05,
      "loss": 0.5754,
      "step": 11811
    },
    {
      "epoch": 0.36285442201947593,
      "grad_norm": 0.3917175531387329,
      "learning_rate": 1.844070947161067e-05,
      "loss": 0.5983,
      "step": 11812
    },
    {
      "epoch": 0.3628851411544251,
      "grad_norm": 0.3770959675312042,
      "learning_rate": 1.8440450313216213e-05,
      "loss": 0.5566,
      "step": 11813
    },
    {
      "epoch": 0.3629158602893742,
      "grad_norm": 0.47437870502471924,
      "learning_rate": 1.8440191135108493e-05,
      "loss": 0.5853,
      "step": 11814
    },
    {
      "epoch": 0.3629465794243234,
      "grad_norm": 0.31868767738342285,
      "learning_rate": 1.8439931937288117e-05,
      "loss": 0.5575,
      "step": 11815
    },
    {
      "epoch": 0.3629772985592726,
      "grad_norm": 0.34456491470336914,
      "learning_rate": 1.843967271975569e-05,
      "loss": 0.6013,
      "step": 11816
    },
    {
      "epoch": 0.36300801769422175,
      "grad_norm": 0.35280242562294006,
      "learning_rate": 1.8439413482511818e-05,
      "loss": 0.5629,
      "step": 11817
    },
    {
      "epoch": 0.36303873682917087,
      "grad_norm": 0.3844134211540222,
      "learning_rate": 1.843915422555711e-05,
      "loss": 0.4704,
      "step": 11818
    },
    {
      "epoch": 0.36306945596412005,
      "grad_norm": 0.33375969529151917,
      "learning_rate": 1.8438894948892163e-05,
      "loss": 0.6177,
      "step": 11819
    },
    {
      "epoch": 0.3631001750990692,
      "grad_norm": 0.3329445421695709,
      "learning_rate": 1.843863565251759e-05,
      "loss": 0.5712,
      "step": 11820
    },
    {
      "epoch": 0.3631308942340184,
      "grad_norm": 0.319169282913208,
      "learning_rate": 1.8438376336433993e-05,
      "loss": 0.5459,
      "step": 11821
    },
    {
      "epoch": 0.3631616133689675,
      "grad_norm": 0.3861388564109802,
      "learning_rate": 1.843811700064198e-05,
      "loss": 0.5395,
      "step": 11822
    },
    {
      "epoch": 0.3631923325039167,
      "grad_norm": 0.38738569617271423,
      "learning_rate": 1.8437857645142157e-05,
      "loss": 0.5131,
      "step": 11823
    },
    {
      "epoch": 0.36322305163886587,
      "grad_norm": 0.34546878933906555,
      "learning_rate": 1.8437598269935125e-05,
      "loss": 0.5497,
      "step": 11824
    },
    {
      "epoch": 0.363253770773815,
      "grad_norm": 0.42154034972190857,
      "learning_rate": 1.8437338875021495e-05,
      "loss": 0.5665,
      "step": 11825
    },
    {
      "epoch": 0.36328448990876416,
      "grad_norm": 0.35521626472473145,
      "learning_rate": 1.843707946040187e-05,
      "loss": 0.5881,
      "step": 11826
    },
    {
      "epoch": 0.36331520904371334,
      "grad_norm": 0.33657553791999817,
      "learning_rate": 1.8436820026076855e-05,
      "loss": 0.5243,
      "step": 11827
    },
    {
      "epoch": 0.3633459281786625,
      "grad_norm": 0.33101460337638855,
      "learning_rate": 1.8436560572047058e-05,
      "loss": 0.4928,
      "step": 11828
    },
    {
      "epoch": 0.36337664731361163,
      "grad_norm": 0.5288845896720886,
      "learning_rate": 1.8436301098313086e-05,
      "loss": 0.5749,
      "step": 11829
    },
    {
      "epoch": 0.3634073664485608,
      "grad_norm": 0.32967710494995117,
      "learning_rate": 1.8436041604875545e-05,
      "loss": 0.4904,
      "step": 11830
    },
    {
      "epoch": 0.36343808558351,
      "grad_norm": 0.3471973240375519,
      "learning_rate": 1.843578209173504e-05,
      "loss": 0.6119,
      "step": 11831
    },
    {
      "epoch": 0.3634688047184591,
      "grad_norm": 0.3713919520378113,
      "learning_rate": 1.8435522558892173e-05,
      "loss": 0.5969,
      "step": 11832
    },
    {
      "epoch": 0.3634995238534083,
      "grad_norm": 0.35779061913490295,
      "learning_rate": 1.8435263006347558e-05,
      "loss": 0.6056,
      "step": 11833
    },
    {
      "epoch": 0.36353024298835745,
      "grad_norm": 0.3294345736503601,
      "learning_rate": 1.8435003434101794e-05,
      "loss": 0.5714,
      "step": 11834
    },
    {
      "epoch": 0.36356096212330663,
      "grad_norm": 0.3550017178058624,
      "learning_rate": 1.843474384215549e-05,
      "loss": 0.5344,
      "step": 11835
    },
    {
      "epoch": 0.36359168125825575,
      "grad_norm": 0.3302602469921112,
      "learning_rate": 1.8434484230509253e-05,
      "loss": 0.6095,
      "step": 11836
    },
    {
      "epoch": 0.3636224003932049,
      "grad_norm": 0.3615990877151489,
      "learning_rate": 1.843422459916369e-05,
      "loss": 0.5443,
      "step": 11837
    },
    {
      "epoch": 0.3636531195281541,
      "grad_norm": 0.3646582067012787,
      "learning_rate": 1.8433964948119406e-05,
      "loss": 0.5477,
      "step": 11838
    },
    {
      "epoch": 0.3636838386631032,
      "grad_norm": 0.3466217517852783,
      "learning_rate": 1.8433705277377008e-05,
      "loss": 0.7047,
      "step": 11839
    },
    {
      "epoch": 0.3637145577980524,
      "grad_norm": 0.34893137216567993,
      "learning_rate": 1.8433445586937103e-05,
      "loss": 0.5684,
      "step": 11840
    },
    {
      "epoch": 0.36374527693300157,
      "grad_norm": 0.3317178785800934,
      "learning_rate": 1.8433185876800298e-05,
      "loss": 0.5547,
      "step": 11841
    },
    {
      "epoch": 0.36377599606795075,
      "grad_norm": 0.3273610472679138,
      "learning_rate": 1.8432926146967195e-05,
      "loss": 0.533,
      "step": 11842
    },
    {
      "epoch": 0.36380671520289987,
      "grad_norm": 0.39357906579971313,
      "learning_rate": 1.8432666397438407e-05,
      "loss": 0.559,
      "step": 11843
    },
    {
      "epoch": 0.36383743433784904,
      "grad_norm": 0.33497288823127747,
      "learning_rate": 1.8432406628214538e-05,
      "loss": 0.5325,
      "step": 11844
    },
    {
      "epoch": 0.3638681534727982,
      "grad_norm": 0.34948399662971497,
      "learning_rate": 1.843214683929619e-05,
      "loss": 0.6687,
      "step": 11845
    },
    {
      "epoch": 0.3638988726077474,
      "grad_norm": 0.34257856011390686,
      "learning_rate": 1.843188703068398e-05,
      "loss": 0.5082,
      "step": 11846
    },
    {
      "epoch": 0.3639295917426965,
      "grad_norm": 0.32667967677116394,
      "learning_rate": 1.8431627202378504e-05,
      "loss": 0.6257,
      "step": 11847
    },
    {
      "epoch": 0.3639603108776457,
      "grad_norm": 0.37662214040756226,
      "learning_rate": 1.8431367354380375e-05,
      "loss": 0.5553,
      "step": 11848
    },
    {
      "epoch": 0.36399103001259486,
      "grad_norm": 0.3293911814689636,
      "learning_rate": 1.84311074866902e-05,
      "loss": 0.5481,
      "step": 11849
    },
    {
      "epoch": 0.364021749147544,
      "grad_norm": 0.3705604076385498,
      "learning_rate": 1.8430847599308585e-05,
      "loss": 0.5869,
      "step": 11850
    },
    {
      "epoch": 0.36405246828249316,
      "grad_norm": 0.3218510150909424,
      "learning_rate": 1.8430587692236135e-05,
      "loss": 0.5621,
      "step": 11851
    },
    {
      "epoch": 0.36408318741744233,
      "grad_norm": 0.3663003146648407,
      "learning_rate": 1.843032776547346e-05,
      "loss": 0.4907,
      "step": 11852
    },
    {
      "epoch": 0.3641139065523915,
      "grad_norm": 0.4038190245628357,
      "learning_rate": 1.8430067819021166e-05,
      "loss": 0.6114,
      "step": 11853
    },
    {
      "epoch": 0.36414462568734063,
      "grad_norm": 0.3271123766899109,
      "learning_rate": 1.8429807852879857e-05,
      "loss": 0.5277,
      "step": 11854
    },
    {
      "epoch": 0.3641753448222898,
      "grad_norm": 0.35887765884399414,
      "learning_rate": 1.8429547867050147e-05,
      "loss": 0.516,
      "step": 11855
    },
    {
      "epoch": 0.364206063957239,
      "grad_norm": 0.37054744362831116,
      "learning_rate": 1.8429287861532638e-05,
      "loss": 0.5826,
      "step": 11856
    },
    {
      "epoch": 0.3642367830921881,
      "grad_norm": 0.35418465733528137,
      "learning_rate": 1.8429027836327935e-05,
      "loss": 0.6142,
      "step": 11857
    },
    {
      "epoch": 0.3642675022271373,
      "grad_norm": 0.3547789752483368,
      "learning_rate": 1.8428767791436654e-05,
      "loss": 0.556,
      "step": 11858
    },
    {
      "epoch": 0.36429822136208645,
      "grad_norm": 0.36122819781303406,
      "learning_rate": 1.8428507726859393e-05,
      "loss": 0.6309,
      "step": 11859
    },
    {
      "epoch": 0.3643289404970356,
      "grad_norm": 0.4027959108352661,
      "learning_rate": 1.8428247642596768e-05,
      "loss": 0.4748,
      "step": 11860
    },
    {
      "epoch": 0.36435965963198474,
      "grad_norm": 0.3527657687664032,
      "learning_rate": 1.8427987538649378e-05,
      "loss": 0.5003,
      "step": 11861
    },
    {
      "epoch": 0.3643903787669339,
      "grad_norm": 0.3592173755168915,
      "learning_rate": 1.8427727415017837e-05,
      "loss": 0.6174,
      "step": 11862
    },
    {
      "epoch": 0.3644210979018831,
      "grad_norm": 0.36379390954971313,
      "learning_rate": 1.8427467271702747e-05,
      "loss": 0.6308,
      "step": 11863
    },
    {
      "epoch": 0.3644518170368322,
      "grad_norm": 0.3731750547885895,
      "learning_rate": 1.842720710870472e-05,
      "loss": 0.6338,
      "step": 11864
    },
    {
      "epoch": 0.3644825361717814,
      "grad_norm": 0.3795950412750244,
      "learning_rate": 1.8426946926024364e-05,
      "loss": 0.6134,
      "step": 11865
    },
    {
      "epoch": 0.36451325530673057,
      "grad_norm": 0.36661672592163086,
      "learning_rate": 1.8426686723662283e-05,
      "loss": 0.5935,
      "step": 11866
    },
    {
      "epoch": 0.36454397444167974,
      "grad_norm": 0.3783034682273865,
      "learning_rate": 1.842642650161909e-05,
      "loss": 0.5554,
      "step": 11867
    },
    {
      "epoch": 0.36457469357662886,
      "grad_norm": 0.37170377373695374,
      "learning_rate": 1.8426166259895387e-05,
      "loss": 0.5856,
      "step": 11868
    },
    {
      "epoch": 0.36460541271157804,
      "grad_norm": 0.30854669213294983,
      "learning_rate": 1.8425905998491782e-05,
      "loss": 0.5274,
      "step": 11869
    },
    {
      "epoch": 0.3646361318465272,
      "grad_norm": 0.3480738699436188,
      "learning_rate": 1.8425645717408888e-05,
      "loss": 0.624,
      "step": 11870
    },
    {
      "epoch": 0.3646668509814764,
      "grad_norm": 0.3386436402797699,
      "learning_rate": 1.8425385416647308e-05,
      "loss": 0.6266,
      "step": 11871
    },
    {
      "epoch": 0.3646975701164255,
      "grad_norm": 0.3255176246166229,
      "learning_rate": 1.8425125096207655e-05,
      "loss": 0.5877,
      "step": 11872
    },
    {
      "epoch": 0.3647282892513747,
      "grad_norm": 0.3033462166786194,
      "learning_rate": 1.8424864756090532e-05,
      "loss": 0.606,
      "step": 11873
    },
    {
      "epoch": 0.36475900838632386,
      "grad_norm": 0.3566072881221771,
      "learning_rate": 1.8424604396296545e-05,
      "loss": 0.6003,
      "step": 11874
    },
    {
      "epoch": 0.364789727521273,
      "grad_norm": 0.38538694381713867,
      "learning_rate": 1.8424344016826312e-05,
      "loss": 0.5856,
      "step": 11875
    },
    {
      "epoch": 0.36482044665622215,
      "grad_norm": 0.3610716164112091,
      "learning_rate": 1.8424083617680432e-05,
      "loss": 0.5368,
      "step": 11876
    },
    {
      "epoch": 0.36485116579117133,
      "grad_norm": 0.47198888659477234,
      "learning_rate": 1.842382319885952e-05,
      "loss": 0.6036,
      "step": 11877
    },
    {
      "epoch": 0.3648818849261205,
      "grad_norm": 0.33774733543395996,
      "learning_rate": 1.8423562760364174e-05,
      "loss": 0.581,
      "step": 11878
    },
    {
      "epoch": 0.3649126040610696,
      "grad_norm": 0.32840263843536377,
      "learning_rate": 1.8423302302195015e-05,
      "loss": 0.5502,
      "step": 11879
    },
    {
      "epoch": 0.3649433231960188,
      "grad_norm": 0.3575284779071808,
      "learning_rate": 1.8423041824352642e-05,
      "loss": 0.5695,
      "step": 11880
    },
    {
      "epoch": 0.364974042330968,
      "grad_norm": 0.38024014234542847,
      "learning_rate": 1.8422781326837672e-05,
      "loss": 0.636,
      "step": 11881
    },
    {
      "epoch": 0.3650047614659171,
      "grad_norm": 0.3673113286495209,
      "learning_rate": 1.84225208096507e-05,
      "loss": 0.6216,
      "step": 11882
    },
    {
      "epoch": 0.36503548060086627,
      "grad_norm": 0.3681805431842804,
      "learning_rate": 1.8422260272792346e-05,
      "loss": 0.5413,
      "step": 11883
    },
    {
      "epoch": 0.36506619973581544,
      "grad_norm": 0.3104393780231476,
      "learning_rate": 1.8421999716263218e-05,
      "loss": 0.5316,
      "step": 11884
    },
    {
      "epoch": 0.3650969188707646,
      "grad_norm": 0.4147748053073883,
      "learning_rate": 1.8421739140063918e-05,
      "loss": 0.5921,
      "step": 11885
    },
    {
      "epoch": 0.36512763800571374,
      "grad_norm": 0.4474312663078308,
      "learning_rate": 1.8421478544195056e-05,
      "loss": 0.5423,
      "step": 11886
    },
    {
      "epoch": 0.3651583571406629,
      "grad_norm": 0.36704373359680176,
      "learning_rate": 1.842121792865725e-05,
      "loss": 0.5402,
      "step": 11887
    },
    {
      "epoch": 0.3651890762756121,
      "grad_norm": 0.3954010307788849,
      "learning_rate": 1.8420957293451093e-05,
      "loss": 0.6846,
      "step": 11888
    },
    {
      "epoch": 0.36521979541056127,
      "grad_norm": 0.3363669216632843,
      "learning_rate": 1.8420696638577208e-05,
      "loss": 0.6263,
      "step": 11889
    },
    {
      "epoch": 0.3652505145455104,
      "grad_norm": 0.3122166693210602,
      "learning_rate": 1.8420435964036193e-05,
      "loss": 0.6427,
      "step": 11890
    },
    {
      "epoch": 0.36528123368045956,
      "grad_norm": 0.40260156989097595,
      "learning_rate": 1.8420175269828666e-05,
      "loss": 0.5464,
      "step": 11891
    },
    {
      "epoch": 0.36531195281540874,
      "grad_norm": 0.3528652489185333,
      "learning_rate": 1.841991455595523e-05,
      "loss": 0.5358,
      "step": 11892
    },
    {
      "epoch": 0.36534267195035786,
      "grad_norm": 0.3829364776611328,
      "learning_rate": 1.8419653822416497e-05,
      "loss": 0.5993,
      "step": 11893
    },
    {
      "epoch": 0.36537339108530703,
      "grad_norm": 0.363869845867157,
      "learning_rate": 1.841939306921307e-05,
      "loss": 0.5768,
      "step": 11894
    },
    {
      "epoch": 0.3654041102202562,
      "grad_norm": 0.36213886737823486,
      "learning_rate": 1.8419132296345568e-05,
      "loss": 0.5624,
      "step": 11895
    },
    {
      "epoch": 0.3654348293552054,
      "grad_norm": 0.3711516559123993,
      "learning_rate": 1.8418871503814592e-05,
      "loss": 0.6214,
      "step": 11896
    },
    {
      "epoch": 0.3654655484901545,
      "grad_norm": 0.3959082067012787,
      "learning_rate": 1.8418610691620756e-05,
      "loss": 0.5961,
      "step": 11897
    },
    {
      "epoch": 0.3654962676251037,
      "grad_norm": 0.3881227374076843,
      "learning_rate": 1.8418349859764662e-05,
      "loss": 0.5391,
      "step": 11898
    },
    {
      "epoch": 0.36552698676005285,
      "grad_norm": 0.32823678851127625,
      "learning_rate": 1.8418089008246925e-05,
      "loss": 0.62,
      "step": 11899
    },
    {
      "epoch": 0.36555770589500197,
      "grad_norm": 0.33642178773880005,
      "learning_rate": 1.8417828137068157e-05,
      "loss": 0.554,
      "step": 11900
    },
    {
      "epoch": 0.36558842502995115,
      "grad_norm": 0.5282217860221863,
      "learning_rate": 1.8417567246228962e-05,
      "loss": 0.5838,
      "step": 11901
    },
    {
      "epoch": 0.3656191441649003,
      "grad_norm": 0.34916791319847107,
      "learning_rate": 1.841730633572995e-05,
      "loss": 0.6438,
      "step": 11902
    },
    {
      "epoch": 0.3656498632998495,
      "grad_norm": 0.36850032210350037,
      "learning_rate": 1.8417045405571728e-05,
      "loss": 0.5725,
      "step": 11903
    },
    {
      "epoch": 0.3656805824347986,
      "grad_norm": 0.3249133229255676,
      "learning_rate": 1.8416784455754916e-05,
      "loss": 0.5929,
      "step": 11904
    },
    {
      "epoch": 0.3657113015697478,
      "grad_norm": 0.43784278631210327,
      "learning_rate": 1.841652348628011e-05,
      "loss": 0.574,
      "step": 11905
    },
    {
      "epoch": 0.36574202070469697,
      "grad_norm": 0.335622638463974,
      "learning_rate": 1.8416262497147928e-05,
      "loss": 0.5708,
      "step": 11906
    },
    {
      "epoch": 0.3657727398396461,
      "grad_norm": 0.33738917112350464,
      "learning_rate": 1.8416001488358977e-05,
      "loss": 0.5797,
      "step": 11907
    },
    {
      "epoch": 0.36580345897459526,
      "grad_norm": 0.4214390218257904,
      "learning_rate": 1.8415740459913866e-05,
      "loss": 0.6019,
      "step": 11908
    },
    {
      "epoch": 0.36583417810954444,
      "grad_norm": 0.37157219648361206,
      "learning_rate": 1.8415479411813205e-05,
      "loss": 0.5458,
      "step": 11909
    },
    {
      "epoch": 0.3658648972444936,
      "grad_norm": 0.381492018699646,
      "learning_rate": 1.8415218344057606e-05,
      "loss": 0.5507,
      "step": 11910
    },
    {
      "epoch": 0.36589561637944273,
      "grad_norm": 0.39769214391708374,
      "learning_rate": 1.8414957256647678e-05,
      "loss": 0.623,
      "step": 11911
    },
    {
      "epoch": 0.3659263355143919,
      "grad_norm": 0.35276323556900024,
      "learning_rate": 1.8414696149584027e-05,
      "loss": 0.5382,
      "step": 11912
    },
    {
      "epoch": 0.3659570546493411,
      "grad_norm": 0.3170086741447449,
      "learning_rate": 1.8414435022867264e-05,
      "loss": 0.667,
      "step": 11913
    },
    {
      "epoch": 0.36598777378429026,
      "grad_norm": 0.42976346611976624,
      "learning_rate": 1.8414173876498e-05,
      "loss": 0.5804,
      "step": 11914
    },
    {
      "epoch": 0.3660184929192394,
      "grad_norm": 0.35241779685020447,
      "learning_rate": 1.841391271047685e-05,
      "loss": 0.5729,
      "step": 11915
    },
    {
      "epoch": 0.36604921205418856,
      "grad_norm": 0.32764607667922974,
      "learning_rate": 1.8413651524804418e-05,
      "loss": 0.5341,
      "step": 11916
    },
    {
      "epoch": 0.36607993118913773,
      "grad_norm": 0.3538931906223297,
      "learning_rate": 1.8413390319481314e-05,
      "loss": 0.5807,
      "step": 11917
    },
    {
      "epoch": 0.36611065032408685,
      "grad_norm": 0.3512170612812042,
      "learning_rate": 1.841312909450815e-05,
      "loss": 0.5695,
      "step": 11918
    },
    {
      "epoch": 0.366141369459036,
      "grad_norm": 0.3725009262561798,
      "learning_rate": 1.841286784988553e-05,
      "loss": 0.5482,
      "step": 11919
    },
    {
      "epoch": 0.3661720885939852,
      "grad_norm": 0.40060776472091675,
      "learning_rate": 1.841260658561408e-05,
      "loss": 0.5652,
      "step": 11920
    },
    {
      "epoch": 0.3662028077289344,
      "grad_norm": 0.31050506234169006,
      "learning_rate": 1.8412345301694392e-05,
      "loss": 0.569,
      "step": 11921
    },
    {
      "epoch": 0.3662335268638835,
      "grad_norm": 0.35549959540367126,
      "learning_rate": 1.8412083998127087e-05,
      "loss": 0.6102,
      "step": 11922
    },
    {
      "epoch": 0.36626424599883267,
      "grad_norm": 0.35277268290519714,
      "learning_rate": 1.841182267491277e-05,
      "loss": 0.5471,
      "step": 11923
    },
    {
      "epoch": 0.36629496513378185,
      "grad_norm": 0.3853762149810791,
      "learning_rate": 1.8411561332052055e-05,
      "loss": 0.5033,
      "step": 11924
    },
    {
      "epoch": 0.36632568426873097,
      "grad_norm": 0.33365949988365173,
      "learning_rate": 1.841129996954555e-05,
      "loss": 0.532,
      "step": 11925
    },
    {
      "epoch": 0.36635640340368014,
      "grad_norm": 0.39100852608680725,
      "learning_rate": 1.8411038587393867e-05,
      "loss": 0.5928,
      "step": 11926
    },
    {
      "epoch": 0.3663871225386293,
      "grad_norm": 0.341845840215683,
      "learning_rate": 1.8410777185597618e-05,
      "loss": 0.5599,
      "step": 11927
    },
    {
      "epoch": 0.3664178416735785,
      "grad_norm": 0.4131210744380951,
      "learning_rate": 1.8410515764157414e-05,
      "loss": 0.5985,
      "step": 11928
    },
    {
      "epoch": 0.3664485608085276,
      "grad_norm": 0.5987859964370728,
      "learning_rate": 1.8410254323073856e-05,
      "loss": 0.4578,
      "step": 11929
    },
    {
      "epoch": 0.3664792799434768,
      "grad_norm": 0.3163631558418274,
      "learning_rate": 1.8409992862347567e-05,
      "loss": 0.5448,
      "step": 11930
    },
    {
      "epoch": 0.36650999907842596,
      "grad_norm": 0.3331263065338135,
      "learning_rate": 1.840973138197915e-05,
      "loss": 0.6215,
      "step": 11931
    },
    {
      "epoch": 0.36654071821337514,
      "grad_norm": 0.35286521911621094,
      "learning_rate": 1.8409469881969217e-05,
      "loss": 0.6529,
      "step": 11932
    },
    {
      "epoch": 0.36657143734832426,
      "grad_norm": 0.365863174200058,
      "learning_rate": 1.8409208362318382e-05,
      "loss": 0.5368,
      "step": 11933
    },
    {
      "epoch": 0.36660215648327343,
      "grad_norm": 0.3714585602283478,
      "learning_rate": 1.8408946823027253e-05,
      "loss": 0.6695,
      "step": 11934
    },
    {
      "epoch": 0.3666328756182226,
      "grad_norm": 0.33374840021133423,
      "learning_rate": 1.840868526409644e-05,
      "loss": 0.5222,
      "step": 11935
    },
    {
      "epoch": 0.36666359475317173,
      "grad_norm": 0.39832043647766113,
      "learning_rate": 1.8408423685526554e-05,
      "loss": 0.6443,
      "step": 11936
    },
    {
      "epoch": 0.3666943138881209,
      "grad_norm": 0.3028642237186432,
      "learning_rate": 1.840816208731821e-05,
      "loss": 0.4803,
      "step": 11937
    },
    {
      "epoch": 0.3667250330230701,
      "grad_norm": 0.3419438302516937,
      "learning_rate": 1.840790046947202e-05,
      "loss": 0.5777,
      "step": 11938
    },
    {
      "epoch": 0.36675575215801925,
      "grad_norm": 0.39224135875701904,
      "learning_rate": 1.8407638831988585e-05,
      "loss": 0.5276,
      "step": 11939
    },
    {
      "epoch": 0.3667864712929684,
      "grad_norm": 0.3401513397693634,
      "learning_rate": 1.8407377174868525e-05,
      "loss": 0.591,
      "step": 11940
    },
    {
      "epoch": 0.36681719042791755,
      "grad_norm": 0.3338383138179779,
      "learning_rate": 1.8407115498112446e-05,
      "loss": 0.5794,
      "step": 11941
    },
    {
      "epoch": 0.3668479095628667,
      "grad_norm": 0.3333677351474762,
      "learning_rate": 1.8406853801720963e-05,
      "loss": 0.5588,
      "step": 11942
    },
    {
      "epoch": 0.36687862869781585,
      "grad_norm": 0.34390443563461304,
      "learning_rate": 1.8406592085694688e-05,
      "loss": 0.5326,
      "step": 11943
    },
    {
      "epoch": 0.366909347832765,
      "grad_norm": 0.397388219833374,
      "learning_rate": 1.840633035003423e-05,
      "loss": 0.5649,
      "step": 11944
    },
    {
      "epoch": 0.3669400669677142,
      "grad_norm": 0.45031842589378357,
      "learning_rate": 1.8406068594740195e-05,
      "loss": 0.5734,
      "step": 11945
    },
    {
      "epoch": 0.36697078610266337,
      "grad_norm": 0.38525354862213135,
      "learning_rate": 1.8405806819813207e-05,
      "loss": 0.6441,
      "step": 11946
    },
    {
      "epoch": 0.3670015052376125,
      "grad_norm": 0.38057634234428406,
      "learning_rate": 1.8405545025253862e-05,
      "loss": 0.569,
      "step": 11947
    },
    {
      "epoch": 0.36703222437256167,
      "grad_norm": 0.36378416419029236,
      "learning_rate": 1.8405283211062787e-05,
      "loss": 0.6125,
      "step": 11948
    },
    {
      "epoch": 0.36706294350751084,
      "grad_norm": 0.34487470984458923,
      "learning_rate": 1.8405021377240585e-05,
      "loss": 0.585,
      "step": 11949
    },
    {
      "epoch": 0.36709366264245996,
      "grad_norm": 0.3296482264995575,
      "learning_rate": 1.8404759523787866e-05,
      "loss": 0.5667,
      "step": 11950
    },
    {
      "epoch": 0.36712438177740914,
      "grad_norm": 0.34236642718315125,
      "learning_rate": 1.8404497650705243e-05,
      "loss": 0.5921,
      "step": 11951
    },
    {
      "epoch": 0.3671551009123583,
      "grad_norm": 0.34392935037612915,
      "learning_rate": 1.8404235757993333e-05,
      "loss": 0.5941,
      "step": 11952
    },
    {
      "epoch": 0.3671858200473075,
      "grad_norm": 0.4271540343761444,
      "learning_rate": 1.840397384565274e-05,
      "loss": 0.5903,
      "step": 11953
    },
    {
      "epoch": 0.3672165391822566,
      "grad_norm": 0.3716713786125183,
      "learning_rate": 1.840371191368408e-05,
      "loss": 0.6328,
      "step": 11954
    },
    {
      "epoch": 0.3672472583172058,
      "grad_norm": 0.3413596749305725,
      "learning_rate": 1.8403449962087965e-05,
      "loss": 0.5658,
      "step": 11955
    },
    {
      "epoch": 0.36727797745215496,
      "grad_norm": 0.391269713640213,
      "learning_rate": 1.8403187990865005e-05,
      "loss": 0.5433,
      "step": 11956
    },
    {
      "epoch": 0.36730869658710413,
      "grad_norm": 0.35973289608955383,
      "learning_rate": 1.8402926000015813e-05,
      "loss": 0.6108,
      "step": 11957
    },
    {
      "epoch": 0.36733941572205325,
      "grad_norm": 0.34323906898498535,
      "learning_rate": 1.8402663989540997e-05,
      "loss": 0.5506,
      "step": 11958
    },
    {
      "epoch": 0.36737013485700243,
      "grad_norm": 0.380167692899704,
      "learning_rate": 1.8402401959441176e-05,
      "loss": 0.568,
      "step": 11959
    },
    {
      "epoch": 0.3674008539919516,
      "grad_norm": 0.33708688616752625,
      "learning_rate": 1.8402139909716958e-05,
      "loss": 0.5483,
      "step": 11960
    },
    {
      "epoch": 0.3674315731269007,
      "grad_norm": 0.34888654947280884,
      "learning_rate": 1.8401877840368957e-05,
      "loss": 0.6218,
      "step": 11961
    },
    {
      "epoch": 0.3674622922618499,
      "grad_norm": 0.33701956272125244,
      "learning_rate": 1.840161575139778e-05,
      "loss": 0.6179,
      "step": 11962
    },
    {
      "epoch": 0.3674930113967991,
      "grad_norm": 0.3968079388141632,
      "learning_rate": 1.840135364280404e-05,
      "loss": 0.5331,
      "step": 11963
    },
    {
      "epoch": 0.36752373053174825,
      "grad_norm": 0.5395948886871338,
      "learning_rate": 1.840109151458836e-05,
      "loss": 0.5712,
      "step": 11964
    },
    {
      "epoch": 0.36755444966669737,
      "grad_norm": 0.37396320700645447,
      "learning_rate": 1.8400829366751342e-05,
      "loss": 0.5465,
      "step": 11965
    },
    {
      "epoch": 0.36758516880164654,
      "grad_norm": 0.32626694440841675,
      "learning_rate": 1.8400567199293596e-05,
      "loss": 0.5008,
      "step": 11966
    },
    {
      "epoch": 0.3676158879365957,
      "grad_norm": 0.37863224744796753,
      "learning_rate": 1.840030501221574e-05,
      "loss": 0.5632,
      "step": 11967
    },
    {
      "epoch": 0.36764660707154484,
      "grad_norm": 0.3179282546043396,
      "learning_rate": 1.8400042805518387e-05,
      "loss": 0.5554,
      "step": 11968
    },
    {
      "epoch": 0.367677326206494,
      "grad_norm": 0.3494877219200134,
      "learning_rate": 1.8399780579202147e-05,
      "loss": 0.4554,
      "step": 11969
    },
    {
      "epoch": 0.3677080453414432,
      "grad_norm": 0.44056087732315063,
      "learning_rate": 1.8399518333267635e-05,
      "loss": 0.6037,
      "step": 11970
    },
    {
      "epoch": 0.36773876447639237,
      "grad_norm": 0.34568992257118225,
      "learning_rate": 1.8399256067715458e-05,
      "loss": 0.6008,
      "step": 11971
    },
    {
      "epoch": 0.3677694836113415,
      "grad_norm": 0.33962753415107727,
      "learning_rate": 1.8398993782546234e-05,
      "loss": 0.5965,
      "step": 11972
    },
    {
      "epoch": 0.36780020274629066,
      "grad_norm": 0.4204976558685303,
      "learning_rate": 1.839873147776057e-05,
      "loss": 0.5845,
      "step": 11973
    },
    {
      "epoch": 0.36783092188123984,
      "grad_norm": 0.2988635003566742,
      "learning_rate": 1.8398469153359085e-05,
      "loss": 0.4983,
      "step": 11974
    },
    {
      "epoch": 0.367861641016189,
      "grad_norm": 0.35543981194496155,
      "learning_rate": 1.8398206809342386e-05,
      "loss": 0.565,
      "step": 11975
    },
    {
      "epoch": 0.36789236015113813,
      "grad_norm": 0.34638211131095886,
      "learning_rate": 1.839794444571109e-05,
      "loss": 0.5649,
      "step": 11976
    },
    {
      "epoch": 0.3679230792860873,
      "grad_norm": 0.34254828095436096,
      "learning_rate": 1.839768206246581e-05,
      "loss": 0.6119,
      "step": 11977
    },
    {
      "epoch": 0.3679537984210365,
      "grad_norm": 0.467334508895874,
      "learning_rate": 1.8397419659607158e-05,
      "loss": 0.6525,
      "step": 11978
    },
    {
      "epoch": 0.3679845175559856,
      "grad_norm": 0.32235127687454224,
      "learning_rate": 1.839715723713574e-05,
      "loss": 0.5873,
      "step": 11979
    },
    {
      "epoch": 0.3680152366909348,
      "grad_norm": 0.3644038140773773,
      "learning_rate": 1.839689479505218e-05,
      "loss": 0.6374,
      "step": 11980
    },
    {
      "epoch": 0.36804595582588395,
      "grad_norm": 0.2973525822162628,
      "learning_rate": 1.8396632333357084e-05,
      "loss": 0.5347,
      "step": 11981
    },
    {
      "epoch": 0.36807667496083313,
      "grad_norm": 0.32197314500808716,
      "learning_rate": 1.8396369852051066e-05,
      "loss": 0.53,
      "step": 11982
    },
    {
      "epoch": 0.36810739409578225,
      "grad_norm": 0.3555222749710083,
      "learning_rate": 1.839610735113474e-05,
      "loss": 0.5819,
      "step": 11983
    },
    {
      "epoch": 0.3681381132307314,
      "grad_norm": 0.333900511264801,
      "learning_rate": 1.839584483060872e-05,
      "loss": 0.6135,
      "step": 11984
    },
    {
      "epoch": 0.3681688323656806,
      "grad_norm": 0.3176644742488861,
      "learning_rate": 1.839558229047362e-05,
      "loss": 0.5513,
      "step": 11985
    },
    {
      "epoch": 0.3681995515006297,
      "grad_norm": 0.32715582847595215,
      "learning_rate": 1.8395319730730047e-05,
      "loss": 0.6022,
      "step": 11986
    },
    {
      "epoch": 0.3682302706355789,
      "grad_norm": 0.38990506529808044,
      "learning_rate": 1.839505715137862e-05,
      "loss": 0.5066,
      "step": 11987
    },
    {
      "epoch": 0.36826098977052807,
      "grad_norm": 0.3567396104335785,
      "learning_rate": 1.839479455241995e-05,
      "loss": 0.5427,
      "step": 11988
    },
    {
      "epoch": 0.36829170890547724,
      "grad_norm": 0.361809104681015,
      "learning_rate": 1.8394531933854654e-05,
      "loss": 0.7245,
      "step": 11989
    },
    {
      "epoch": 0.36832242804042636,
      "grad_norm": 0.37100353837013245,
      "learning_rate": 1.839426929568334e-05,
      "loss": 0.6237,
      "step": 11990
    },
    {
      "epoch": 0.36835314717537554,
      "grad_norm": 0.3861450254917145,
      "learning_rate": 1.839400663790662e-05,
      "loss": 0.5637,
      "step": 11991
    },
    {
      "epoch": 0.3683838663103247,
      "grad_norm": 0.3342583477497101,
      "learning_rate": 1.839374396052512e-05,
      "loss": 0.5599,
      "step": 11992
    },
    {
      "epoch": 0.36841458544527383,
      "grad_norm": 0.32324764132499695,
      "learning_rate": 1.839348126353944e-05,
      "loss": 0.6011,
      "step": 11993
    },
    {
      "epoch": 0.368445304580223,
      "grad_norm": 0.33611488342285156,
      "learning_rate": 1.83932185469502e-05,
      "loss": 0.56,
      "step": 11994
    },
    {
      "epoch": 0.3684760237151722,
      "grad_norm": 0.32762402296066284,
      "learning_rate": 1.8392955810758008e-05,
      "loss": 0.5559,
      "step": 11995
    },
    {
      "epoch": 0.36850674285012136,
      "grad_norm": 1.0749499797821045,
      "learning_rate": 1.8392693054963485e-05,
      "loss": 0.5867,
      "step": 11996
    },
    {
      "epoch": 0.3685374619850705,
      "grad_norm": 0.33635398745536804,
      "learning_rate": 1.8392430279567238e-05,
      "loss": 0.5315,
      "step": 11997
    },
    {
      "epoch": 0.36856818112001966,
      "grad_norm": 0.34281662106513977,
      "learning_rate": 1.8392167484569886e-05,
      "loss": 0.6016,
      "step": 11998
    },
    {
      "epoch": 0.36859890025496883,
      "grad_norm": 0.35077184438705444,
      "learning_rate": 1.8391904669972043e-05,
      "loss": 0.6203,
      "step": 11999
    },
    {
      "epoch": 0.368629619389918,
      "grad_norm": 0.35605862736701965,
      "learning_rate": 1.8391641835774318e-05,
      "loss": 0.6185,
      "step": 12000
    },
    {
      "epoch": 0.3686603385248671,
      "grad_norm": 0.4318116307258606,
      "learning_rate": 1.839137898197733e-05,
      "loss": 0.5899,
      "step": 12001
    },
    {
      "epoch": 0.3686910576598163,
      "grad_norm": 0.4918050765991211,
      "learning_rate": 1.8391116108581687e-05,
      "loss": 0.6275,
      "step": 12002
    },
    {
      "epoch": 0.3687217767947655,
      "grad_norm": 0.3258839249610901,
      "learning_rate": 1.8390853215588007e-05,
      "loss": 0.5495,
      "step": 12003
    },
    {
      "epoch": 0.3687524959297146,
      "grad_norm": 0.5114021897315979,
      "learning_rate": 1.83905903029969e-05,
      "loss": 0.5244,
      "step": 12004
    },
    {
      "epoch": 0.36878321506466377,
      "grad_norm": 0.3305162787437439,
      "learning_rate": 1.839032737080899e-05,
      "loss": 0.5194,
      "step": 12005
    },
    {
      "epoch": 0.36881393419961295,
      "grad_norm": 0.3545305132865906,
      "learning_rate": 1.8390064419024882e-05,
      "loss": 0.6137,
      "step": 12006
    },
    {
      "epoch": 0.3688446533345621,
      "grad_norm": 0.32840293645858765,
      "learning_rate": 1.8389801447645194e-05,
      "loss": 0.5809,
      "step": 12007
    },
    {
      "epoch": 0.36887537246951124,
      "grad_norm": 0.5298738479614258,
      "learning_rate": 1.8389538456670534e-05,
      "loss": 0.5462,
      "step": 12008
    },
    {
      "epoch": 0.3689060916044604,
      "grad_norm": 0.37130317091941833,
      "learning_rate": 1.8389275446101528e-05,
      "loss": 0.5917,
      "step": 12009
    },
    {
      "epoch": 0.3689368107394096,
      "grad_norm": 0.3453938961029053,
      "learning_rate": 1.8389012415938777e-05,
      "loss": 0.6149,
      "step": 12010
    },
    {
      "epoch": 0.3689675298743587,
      "grad_norm": 0.4200533330440521,
      "learning_rate": 1.8388749366182904e-05,
      "loss": 0.5777,
      "step": 12011
    },
    {
      "epoch": 0.3689982490093079,
      "grad_norm": 0.44403308629989624,
      "learning_rate": 1.838848629683452e-05,
      "loss": 0.4966,
      "step": 12012
    },
    {
      "epoch": 0.36902896814425706,
      "grad_norm": 0.3414042890071869,
      "learning_rate": 1.8388223207894246e-05,
      "loss": 0.6445,
      "step": 12013
    },
    {
      "epoch": 0.36905968727920624,
      "grad_norm": 0.37806326150894165,
      "learning_rate": 1.8387960099362682e-05,
      "loss": 0.6239,
      "step": 12014
    },
    {
      "epoch": 0.36909040641415536,
      "grad_norm": 0.34608447551727295,
      "learning_rate": 1.8387696971240455e-05,
      "loss": 0.6066,
      "step": 12015
    },
    {
      "epoch": 0.36912112554910453,
      "grad_norm": 0.343478798866272,
      "learning_rate": 1.838743382352818e-05,
      "loss": 0.6067,
      "step": 12016
    },
    {
      "epoch": 0.3691518446840537,
      "grad_norm": 0.3560216724872589,
      "learning_rate": 1.8387170656226464e-05,
      "loss": 0.5338,
      "step": 12017
    },
    {
      "epoch": 0.36918256381900283,
      "grad_norm": 0.363333135843277,
      "learning_rate": 1.8386907469335926e-05,
      "loss": 0.5573,
      "step": 12018
    },
    {
      "epoch": 0.369213282953952,
      "grad_norm": 0.3826920986175537,
      "learning_rate": 1.8386644262857175e-05,
      "loss": 0.6275,
      "step": 12019
    },
    {
      "epoch": 0.3692440020889012,
      "grad_norm": 0.43314966559410095,
      "learning_rate": 1.8386381036790837e-05,
      "loss": 0.5778,
      "step": 12020
    },
    {
      "epoch": 0.36927472122385036,
      "grad_norm": 0.40674838423728943,
      "learning_rate": 1.8386117791137517e-05,
      "loss": 0.6079,
      "step": 12021
    },
    {
      "epoch": 0.3693054403587995,
      "grad_norm": 0.38697972893714905,
      "learning_rate": 1.8385854525897838e-05,
      "loss": 0.563,
      "step": 12022
    },
    {
      "epoch": 0.36933615949374865,
      "grad_norm": 0.9551025629043579,
      "learning_rate": 1.83855912410724e-05,
      "loss": 0.4944,
      "step": 12023
    },
    {
      "epoch": 0.3693668786286978,
      "grad_norm": 0.36853930354118347,
      "learning_rate": 1.838532793666184e-05,
      "loss": 0.4824,
      "step": 12024
    },
    {
      "epoch": 0.369397597763647,
      "grad_norm": 0.40153250098228455,
      "learning_rate": 1.8385064612666753e-05,
      "loss": 0.54,
      "step": 12025
    },
    {
      "epoch": 0.3694283168985961,
      "grad_norm": 0.31288498640060425,
      "learning_rate": 1.8384801269087768e-05,
      "loss": 0.5322,
      "step": 12026
    },
    {
      "epoch": 0.3694590360335453,
      "grad_norm": 0.3495669364929199,
      "learning_rate": 1.838453790592549e-05,
      "loss": 0.5502,
      "step": 12027
    },
    {
      "epoch": 0.36948975516849447,
      "grad_norm": 0.39413121342658997,
      "learning_rate": 1.8384274523180537e-05,
      "loss": 0.5501,
      "step": 12028
    },
    {
      "epoch": 0.3695204743034436,
      "grad_norm": 0.45310714840888977,
      "learning_rate": 1.8384011120853528e-05,
      "loss": 0.5683,
      "step": 12029
    },
    {
      "epoch": 0.36955119343839277,
      "grad_norm": 0.3582731783390045,
      "learning_rate": 1.8383747698945073e-05,
      "loss": 0.5006,
      "step": 12030
    },
    {
      "epoch": 0.36958191257334194,
      "grad_norm": 0.33134573698043823,
      "learning_rate": 1.8383484257455794e-05,
      "loss": 0.6329,
      "step": 12031
    },
    {
      "epoch": 0.3696126317082911,
      "grad_norm": 0.3443862497806549,
      "learning_rate": 1.8383220796386298e-05,
      "loss": 0.5999,
      "step": 12032
    },
    {
      "epoch": 0.36964335084324024,
      "grad_norm": 0.97184157371521,
      "learning_rate": 1.8382957315737205e-05,
      "loss": 0.5315,
      "step": 12033
    },
    {
      "epoch": 0.3696740699781894,
      "grad_norm": 0.32173559069633484,
      "learning_rate": 1.838269381550913e-05,
      "loss": 0.5395,
      "step": 12034
    },
    {
      "epoch": 0.3697047891131386,
      "grad_norm": 0.38673773407936096,
      "learning_rate": 1.838243029570269e-05,
      "loss": 0.6272,
      "step": 12035
    },
    {
      "epoch": 0.3697355082480877,
      "grad_norm": 0.3221803307533264,
      "learning_rate": 1.8382166756318492e-05,
      "loss": 0.6047,
      "step": 12036
    },
    {
      "epoch": 0.3697662273830369,
      "grad_norm": 0.33566808700561523,
      "learning_rate": 1.8381903197357168e-05,
      "loss": 0.5575,
      "step": 12037
    },
    {
      "epoch": 0.36979694651798606,
      "grad_norm": 0.3414601981639862,
      "learning_rate": 1.8381639618819317e-05,
      "loss": 0.6175,
      "step": 12038
    },
    {
      "epoch": 0.36982766565293523,
      "grad_norm": 0.36749696731567383,
      "learning_rate": 1.8381376020705562e-05,
      "loss": 0.6032,
      "step": 12039
    },
    {
      "epoch": 0.36985838478788435,
      "grad_norm": 0.3358899652957916,
      "learning_rate": 1.838111240301652e-05,
      "loss": 0.574,
      "step": 12040
    },
    {
      "epoch": 0.36988910392283353,
      "grad_norm": 0.35951241850852966,
      "learning_rate": 1.8380848765752804e-05,
      "loss": 0.6096,
      "step": 12041
    },
    {
      "epoch": 0.3699198230577827,
      "grad_norm": 0.3545386791229248,
      "learning_rate": 1.838058510891503e-05,
      "loss": 0.5044,
      "step": 12042
    },
    {
      "epoch": 0.3699505421927319,
      "grad_norm": 0.4061214029788971,
      "learning_rate": 1.8380321432503817e-05,
      "loss": 0.5446,
      "step": 12043
    },
    {
      "epoch": 0.369981261327681,
      "grad_norm": 0.3752491772174835,
      "learning_rate": 1.8380057736519772e-05,
      "loss": 0.6092,
      "step": 12044
    },
    {
      "epoch": 0.3700119804626302,
      "grad_norm": 0.4284396469593048,
      "learning_rate": 1.8379794020963523e-05,
      "loss": 0.5887,
      "step": 12045
    },
    {
      "epoch": 0.37004269959757935,
      "grad_norm": 0.32964760065078735,
      "learning_rate": 1.8379530285835677e-05,
      "loss": 0.5985,
      "step": 12046
    },
    {
      "epoch": 0.37007341873252847,
      "grad_norm": 0.3762403428554535,
      "learning_rate": 1.837926653113685e-05,
      "loss": 0.5995,
      "step": 12047
    },
    {
      "epoch": 0.37010413786747764,
      "grad_norm": 0.3639916777610779,
      "learning_rate": 1.8379002756867666e-05,
      "loss": 0.5983,
      "step": 12048
    },
    {
      "epoch": 0.3701348570024268,
      "grad_norm": 0.33791565895080566,
      "learning_rate": 1.8378738963028734e-05,
      "loss": 0.5314,
      "step": 12049
    },
    {
      "epoch": 0.370165576137376,
      "grad_norm": 0.3484160602092743,
      "learning_rate": 1.837847514962067e-05,
      "loss": 0.5704,
      "step": 12050
    },
    {
      "epoch": 0.3701962952723251,
      "grad_norm": 0.34674328565597534,
      "learning_rate": 1.8378211316644094e-05,
      "loss": 0.5477,
      "step": 12051
    },
    {
      "epoch": 0.3702270144072743,
      "grad_norm": 0.33115050196647644,
      "learning_rate": 1.8377947464099622e-05,
      "loss": 0.6283,
      "step": 12052
    },
    {
      "epoch": 0.37025773354222347,
      "grad_norm": 0.32590436935424805,
      "learning_rate": 1.8377683591987866e-05,
      "loss": 0.5039,
      "step": 12053
    },
    {
      "epoch": 0.3702884526771726,
      "grad_norm": 0.3400111496448517,
      "learning_rate": 1.8377419700309446e-05,
      "loss": 0.6171,
      "step": 12054
    },
    {
      "epoch": 0.37031917181212176,
      "grad_norm": 0.3587375581264496,
      "learning_rate": 1.8377155789064975e-05,
      "loss": 0.6204,
      "step": 12055
    },
    {
      "epoch": 0.37034989094707094,
      "grad_norm": 0.341569185256958,
      "learning_rate": 1.8376891858255072e-05,
      "loss": 0.6215,
      "step": 12056
    },
    {
      "epoch": 0.3703806100820201,
      "grad_norm": 0.3372836410999298,
      "learning_rate": 1.8376627907880355e-05,
      "loss": 0.4625,
      "step": 12057
    },
    {
      "epoch": 0.37041132921696923,
      "grad_norm": 0.32596638798713684,
      "learning_rate": 1.837636393794144e-05,
      "loss": 0.5592,
      "step": 12058
    },
    {
      "epoch": 0.3704420483519184,
      "grad_norm": 0.34708714485168457,
      "learning_rate": 1.8376099948438938e-05,
      "loss": 0.5813,
      "step": 12059
    },
    {
      "epoch": 0.3704727674868676,
      "grad_norm": 0.3296850621700287,
      "learning_rate": 1.8375835939373474e-05,
      "loss": 0.5515,
      "step": 12060
    },
    {
      "epoch": 0.3705034866218167,
      "grad_norm": 0.39669257402420044,
      "learning_rate": 1.8375571910745656e-05,
      "loss": 0.6139,
      "step": 12061
    },
    {
      "epoch": 0.3705342057567659,
      "grad_norm": 0.3574727773666382,
      "learning_rate": 1.8375307862556106e-05,
      "loss": 0.62,
      "step": 12062
    },
    {
      "epoch": 0.37056492489171505,
      "grad_norm": 0.30562087893486023,
      "learning_rate": 1.837504379480544e-05,
      "loss": 0.5216,
      "step": 12063
    },
    {
      "epoch": 0.37059564402666423,
      "grad_norm": 0.38799917697906494,
      "learning_rate": 1.8374779707494276e-05,
      "loss": 0.5348,
      "step": 12064
    },
    {
      "epoch": 0.37062636316161335,
      "grad_norm": 0.33592739701271057,
      "learning_rate": 1.8374515600623226e-05,
      "loss": 0.5987,
      "step": 12065
    },
    {
      "epoch": 0.3706570822965625,
      "grad_norm": 0.34963613748550415,
      "learning_rate": 1.8374251474192914e-05,
      "loss": 0.5602,
      "step": 12066
    },
    {
      "epoch": 0.3706878014315117,
      "grad_norm": 0.31579363346099854,
      "learning_rate": 1.837398732820395e-05,
      "loss": 0.5798,
      "step": 12067
    },
    {
      "epoch": 0.3707185205664609,
      "grad_norm": 0.4151420295238495,
      "learning_rate": 1.8373723162656953e-05,
      "loss": 0.6012,
      "step": 12068
    },
    {
      "epoch": 0.37074923970141,
      "grad_norm": 0.3305237293243408,
      "learning_rate": 1.8373458977552543e-05,
      "loss": 0.6396,
      "step": 12069
    },
    {
      "epoch": 0.37077995883635917,
      "grad_norm": 0.3695778548717499,
      "learning_rate": 1.8373194772891333e-05,
      "loss": 0.5591,
      "step": 12070
    },
    {
      "epoch": 0.37081067797130834,
      "grad_norm": 0.3590225279331207,
      "learning_rate": 1.837293054867394e-05,
      "loss": 0.5984,
      "step": 12071
    },
    {
      "epoch": 0.37084139710625746,
      "grad_norm": 0.3704279661178589,
      "learning_rate": 1.8372666304900986e-05,
      "loss": 0.573,
      "step": 12072
    },
    {
      "epoch": 0.37087211624120664,
      "grad_norm": 0.35881417989730835,
      "learning_rate": 1.8372402041573084e-05,
      "loss": 0.6496,
      "step": 12073
    },
    {
      "epoch": 0.3709028353761558,
      "grad_norm": 0.3786000609397888,
      "learning_rate": 1.8372137758690854e-05,
      "loss": 0.6485,
      "step": 12074
    },
    {
      "epoch": 0.370933554511105,
      "grad_norm": 0.3357364237308502,
      "learning_rate": 1.8371873456254913e-05,
      "loss": 0.5902,
      "step": 12075
    },
    {
      "epoch": 0.3709642736460541,
      "grad_norm": 0.35234999656677246,
      "learning_rate": 1.8371609134265873e-05,
      "loss": 0.6575,
      "step": 12076
    },
    {
      "epoch": 0.3709949927810033,
      "grad_norm": 0.5663955211639404,
      "learning_rate": 1.8371344792724354e-05,
      "loss": 0.6155,
      "step": 12077
    },
    {
      "epoch": 0.37102571191595246,
      "grad_norm": 0.37467503547668457,
      "learning_rate": 1.8371080431630978e-05,
      "loss": 0.6245,
      "step": 12078
    },
    {
      "epoch": 0.3710564310509016,
      "grad_norm": 0.3440595865249634,
      "learning_rate": 1.8370816050986356e-05,
      "loss": 0.6103,
      "step": 12079
    },
    {
      "epoch": 0.37108715018585076,
      "grad_norm": 0.3419538736343384,
      "learning_rate": 1.8370551650791113e-05,
      "loss": 0.5109,
      "step": 12080
    },
    {
      "epoch": 0.37111786932079993,
      "grad_norm": 0.3772508203983307,
      "learning_rate": 1.8370287231045862e-05,
      "loss": 0.5297,
      "step": 12081
    },
    {
      "epoch": 0.3711485884557491,
      "grad_norm": 0.3835662603378296,
      "learning_rate": 1.8370022791751215e-05,
      "loss": 0.6206,
      "step": 12082
    },
    {
      "epoch": 0.3711793075906982,
      "grad_norm": 0.41574904322624207,
      "learning_rate": 1.8369758332907797e-05,
      "loss": 0.6814,
      "step": 12083
    },
    {
      "epoch": 0.3712100267256474,
      "grad_norm": 0.3383312523365021,
      "learning_rate": 1.836949385451623e-05,
      "loss": 0.6115,
      "step": 12084
    },
    {
      "epoch": 0.3712407458605966,
      "grad_norm": 0.3310041129589081,
      "learning_rate": 1.836922935657712e-05,
      "loss": 0.4985,
      "step": 12085
    },
    {
      "epoch": 0.37127146499554575,
      "grad_norm": 0.348409503698349,
      "learning_rate": 1.836896483909109e-05,
      "loss": 0.6684,
      "step": 12086
    },
    {
      "epoch": 0.3713021841304949,
      "grad_norm": 0.36199697852134705,
      "learning_rate": 1.8368700302058758e-05,
      "loss": 0.5249,
      "step": 12087
    },
    {
      "epoch": 0.37133290326544405,
      "grad_norm": 0.33961331844329834,
      "learning_rate": 1.8368435745480745e-05,
      "loss": 0.5952,
      "step": 12088
    },
    {
      "epoch": 0.3713636224003932,
      "grad_norm": 0.3326971232891083,
      "learning_rate": 1.8368171169357664e-05,
      "loss": 0.5159,
      "step": 12089
    },
    {
      "epoch": 0.37139434153534234,
      "grad_norm": 0.31455743312835693,
      "learning_rate": 1.8367906573690134e-05,
      "loss": 0.4872,
      "step": 12090
    },
    {
      "epoch": 0.3714250606702915,
      "grad_norm": 0.31217148900032043,
      "learning_rate": 1.8367641958478775e-05,
      "loss": 0.5962,
      "step": 12091
    },
    {
      "epoch": 0.3714557798052407,
      "grad_norm": 0.36795228719711304,
      "learning_rate": 1.8367377323724205e-05,
      "loss": 0.5664,
      "step": 12092
    },
    {
      "epoch": 0.37148649894018987,
      "grad_norm": 0.39509469270706177,
      "learning_rate": 1.836711266942704e-05,
      "loss": 0.5785,
      "step": 12093
    },
    {
      "epoch": 0.371517218075139,
      "grad_norm": 0.3441612422466278,
      "learning_rate": 1.8366847995587897e-05,
      "loss": 0.5242,
      "step": 12094
    },
    {
      "epoch": 0.37154793721008816,
      "grad_norm": 0.3225632905960083,
      "learning_rate": 1.8366583302207398e-05,
      "loss": 0.643,
      "step": 12095
    },
    {
      "epoch": 0.37157865634503734,
      "grad_norm": 0.38300207257270813,
      "learning_rate": 1.8366318589286158e-05,
      "loss": 0.5196,
      "step": 12096
    },
    {
      "epoch": 0.37160937547998646,
      "grad_norm": 0.36712610721588135,
      "learning_rate": 1.83660538568248e-05,
      "loss": 0.5461,
      "step": 12097
    },
    {
      "epoch": 0.37164009461493563,
      "grad_norm": 0.34841737151145935,
      "learning_rate": 1.8365789104823935e-05,
      "loss": 0.5158,
      "step": 12098
    },
    {
      "epoch": 0.3716708137498848,
      "grad_norm": 0.3497195541858673,
      "learning_rate": 1.836552433328419e-05,
      "loss": 0.6449,
      "step": 12099
    },
    {
      "epoch": 0.371701532884834,
      "grad_norm": 0.35028520226478577,
      "learning_rate": 1.8365259542206172e-05,
      "loss": 0.559,
      "step": 12100
    },
    {
      "epoch": 0.3717322520197831,
      "grad_norm": 0.39131078124046326,
      "learning_rate": 1.836499473159051e-05,
      "loss": 0.5006,
      "step": 12101
    },
    {
      "epoch": 0.3717629711547323,
      "grad_norm": 0.36936435103416443,
      "learning_rate": 1.836472990143782e-05,
      "loss": 0.5908,
      "step": 12102
    },
    {
      "epoch": 0.37179369028968146,
      "grad_norm": 0.333901584148407,
      "learning_rate": 1.8364465051748713e-05,
      "loss": 0.6242,
      "step": 12103
    },
    {
      "epoch": 0.3718244094246306,
      "grad_norm": 0.31930941343307495,
      "learning_rate": 1.8364200182523822e-05,
      "loss": 0.527,
      "step": 12104
    },
    {
      "epoch": 0.37185512855957975,
      "grad_norm": 0.3666832149028778,
      "learning_rate": 1.8363935293763753e-05,
      "loss": 0.5751,
      "step": 12105
    },
    {
      "epoch": 0.3718858476945289,
      "grad_norm": 0.3177006244659424,
      "learning_rate": 1.836367038546913e-05,
      "loss": 0.573,
      "step": 12106
    },
    {
      "epoch": 0.3719165668294781,
      "grad_norm": 0.34941327571868896,
      "learning_rate": 1.836340545764057e-05,
      "loss": 0.5972,
      "step": 12107
    },
    {
      "epoch": 0.3719472859644272,
      "grad_norm": 0.3826427757740021,
      "learning_rate": 1.8363140510278692e-05,
      "loss": 0.6454,
      "step": 12108
    },
    {
      "epoch": 0.3719780050993764,
      "grad_norm": 0.3605712652206421,
      "learning_rate": 1.8362875543384116e-05,
      "loss": 0.544,
      "step": 12109
    },
    {
      "epoch": 0.37200872423432557,
      "grad_norm": 0.3211289048194885,
      "learning_rate": 1.8362610556957458e-05,
      "loss": 0.5274,
      "step": 12110
    },
    {
      "epoch": 0.37203944336927475,
      "grad_norm": 0.33158934116363525,
      "learning_rate": 1.8362345550999342e-05,
      "loss": 0.5928,
      "step": 12111
    },
    {
      "epoch": 0.37207016250422387,
      "grad_norm": 0.34741103649139404,
      "learning_rate": 1.8362080525510384e-05,
      "loss": 0.5559,
      "step": 12112
    },
    {
      "epoch": 0.37210088163917304,
      "grad_norm": 0.43731433153152466,
      "learning_rate": 1.83618154804912e-05,
      "loss": 0.6783,
      "step": 12113
    },
    {
      "epoch": 0.3721316007741222,
      "grad_norm": 0.3426723778247833,
      "learning_rate": 1.8361550415942414e-05,
      "loss": 0.6107,
      "step": 12114
    },
    {
      "epoch": 0.37216231990907134,
      "grad_norm": 0.3535725176334381,
      "learning_rate": 1.8361285331864645e-05,
      "loss": 0.6432,
      "step": 12115
    },
    {
      "epoch": 0.3721930390440205,
      "grad_norm": 0.3544923961162567,
      "learning_rate": 1.8361020228258507e-05,
      "loss": 0.5325,
      "step": 12116
    },
    {
      "epoch": 0.3722237581789697,
      "grad_norm": 0.3771418333053589,
      "learning_rate": 1.8360755105124625e-05,
      "loss": 0.6197,
      "step": 12117
    },
    {
      "epoch": 0.37225447731391886,
      "grad_norm": 0.3825949430465698,
      "learning_rate": 1.8360489962463614e-05,
      "loss": 0.5688,
      "step": 12118
    },
    {
      "epoch": 0.372285196448868,
      "grad_norm": 0.30727240443229675,
      "learning_rate": 1.836022480027609e-05,
      "loss": 0.5102,
      "step": 12119
    },
    {
      "epoch": 0.37231591558381716,
      "grad_norm": 0.32851701974868774,
      "learning_rate": 1.8359959618562688e-05,
      "loss": 0.6536,
      "step": 12120
    },
    {
      "epoch": 0.37234663471876633,
      "grad_norm": 0.36520758271217346,
      "learning_rate": 1.8359694417324005e-05,
      "loss": 0.5826,
      "step": 12121
    },
    {
      "epoch": 0.37237735385371545,
      "grad_norm": 0.35628077387809753,
      "learning_rate": 1.8359429196560682e-05,
      "loss": 0.4774,
      "step": 12122
    },
    {
      "epoch": 0.37240807298866463,
      "grad_norm": 0.36827102303504944,
      "learning_rate": 1.835916395627332e-05,
      "loss": 0.5758,
      "step": 12123
    },
    {
      "epoch": 0.3724387921236138,
      "grad_norm": 0.3304240107536316,
      "learning_rate": 1.835889869646255e-05,
      "loss": 0.5652,
      "step": 12124
    },
    {
      "epoch": 0.372469511258563,
      "grad_norm": 0.35485437512397766,
      "learning_rate": 1.835863341712899e-05,
      "loss": 0.569,
      "step": 12125
    },
    {
      "epoch": 0.3725002303935121,
      "grad_norm": 0.36710813641548157,
      "learning_rate": 1.8358368118273256e-05,
      "loss": 0.5787,
      "step": 12126
    },
    {
      "epoch": 0.3725309495284613,
      "grad_norm": 0.35038551688194275,
      "learning_rate": 1.835810279989597e-05,
      "loss": 0.5301,
      "step": 12127
    },
    {
      "epoch": 0.37256166866341045,
      "grad_norm": 0.32760778069496155,
      "learning_rate": 1.8357837461997753e-05,
      "loss": 0.6445,
      "step": 12128
    },
    {
      "epoch": 0.3725923877983596,
      "grad_norm": 0.34297558665275574,
      "learning_rate": 1.835757210457922e-05,
      "loss": 0.5798,
      "step": 12129
    },
    {
      "epoch": 0.37262310693330875,
      "grad_norm": 0.36310046911239624,
      "learning_rate": 1.8357306727640995e-05,
      "loss": 0.6175,
      "step": 12130
    },
    {
      "epoch": 0.3726538260682579,
      "grad_norm": 0.35917767882347107,
      "learning_rate": 1.8357041331183695e-05,
      "loss": 0.6458,
      "step": 12131
    },
    {
      "epoch": 0.3726845452032071,
      "grad_norm": 0.3614516258239746,
      "learning_rate": 1.8356775915207944e-05,
      "loss": 0.6375,
      "step": 12132
    },
    {
      "epoch": 0.3727152643381562,
      "grad_norm": 0.43099814653396606,
      "learning_rate": 1.8356510479714355e-05,
      "loss": 0.6258,
      "step": 12133
    },
    {
      "epoch": 0.3727459834731054,
      "grad_norm": 0.4001576006412506,
      "learning_rate": 1.8356245024703555e-05,
      "loss": 0.6313,
      "step": 12134
    },
    {
      "epoch": 0.37277670260805457,
      "grad_norm": 0.48225414752960205,
      "learning_rate": 1.835597955017616e-05,
      "loss": 0.5343,
      "step": 12135
    },
    {
      "epoch": 0.37280742174300374,
      "grad_norm": 0.3603494167327881,
      "learning_rate": 1.8355714056132795e-05,
      "loss": 0.598,
      "step": 12136
    },
    {
      "epoch": 0.37283814087795286,
      "grad_norm": 0.32561707496643066,
      "learning_rate": 1.835544854257407e-05,
      "loss": 0.5667,
      "step": 12137
    },
    {
      "epoch": 0.37286886001290204,
      "grad_norm": 0.3580394685268402,
      "learning_rate": 1.835518300950062e-05,
      "loss": 0.6682,
      "step": 12138
    },
    {
      "epoch": 0.3728995791478512,
      "grad_norm": 0.3784162700176239,
      "learning_rate": 1.8354917456913047e-05,
      "loss": 0.4936,
      "step": 12139
    },
    {
      "epoch": 0.37293029828280033,
      "grad_norm": 0.6742562055587769,
      "learning_rate": 1.8354651884811987e-05,
      "loss": 0.5912,
      "step": 12140
    },
    {
      "epoch": 0.3729610174177495,
      "grad_norm": 0.30308273434638977,
      "learning_rate": 1.8354386293198053e-05,
      "loss": 0.5175,
      "step": 12141
    },
    {
      "epoch": 0.3729917365526987,
      "grad_norm": 0.35824835300445557,
      "learning_rate": 1.8354120682071867e-05,
      "loss": 0.5945,
      "step": 12142
    },
    {
      "epoch": 0.37302245568764786,
      "grad_norm": 0.42936021089553833,
      "learning_rate": 1.8353855051434047e-05,
      "loss": 0.5476,
      "step": 12143
    },
    {
      "epoch": 0.373053174822597,
      "grad_norm": 0.49034327268600464,
      "learning_rate": 1.8353589401285213e-05,
      "loss": 0.5383,
      "step": 12144
    },
    {
      "epoch": 0.37308389395754615,
      "grad_norm": 0.36385759711265564,
      "learning_rate": 1.8353323731625988e-05,
      "loss": 0.6757,
      "step": 12145
    },
    {
      "epoch": 0.37311461309249533,
      "grad_norm": 0.32801076769828796,
      "learning_rate": 1.8353058042456995e-05,
      "loss": 0.5282,
      "step": 12146
    },
    {
      "epoch": 0.37314533222744445,
      "grad_norm": 0.347785085439682,
      "learning_rate": 1.8352792333778852e-05,
      "loss": 0.6478,
      "step": 12147
    },
    {
      "epoch": 0.3731760513623936,
      "grad_norm": 0.33968818187713623,
      "learning_rate": 1.8352526605592178e-05,
      "loss": 0.534,
      "step": 12148
    },
    {
      "epoch": 0.3732067704973428,
      "grad_norm": 0.30201780796051025,
      "learning_rate": 1.8352260857897596e-05,
      "loss": 0.5765,
      "step": 12149
    },
    {
      "epoch": 0.373237489632292,
      "grad_norm": 0.3151794970035553,
      "learning_rate": 1.8351995090695724e-05,
      "loss": 0.4809,
      "step": 12150
    },
    {
      "epoch": 0.3732682087672411,
      "grad_norm": 0.40291139483451843,
      "learning_rate": 1.8351729303987184e-05,
      "loss": 0.5356,
      "step": 12151
    },
    {
      "epoch": 0.37329892790219027,
      "grad_norm": 0.47956448793411255,
      "learning_rate": 1.8351463497772594e-05,
      "loss": 0.556,
      "step": 12152
    },
    {
      "epoch": 0.37332964703713944,
      "grad_norm": 0.32680588960647583,
      "learning_rate": 1.8351197672052583e-05,
      "loss": 0.5456,
      "step": 12153
    },
    {
      "epoch": 0.3733603661720886,
      "grad_norm": 0.32688695192337036,
      "learning_rate": 1.835093182682776e-05,
      "loss": 0.5388,
      "step": 12154
    },
    {
      "epoch": 0.37339108530703774,
      "grad_norm": 0.33203110098838806,
      "learning_rate": 1.8350665962098763e-05,
      "loss": 0.4935,
      "step": 12155
    },
    {
      "epoch": 0.3734218044419869,
      "grad_norm": 0.31248152256011963,
      "learning_rate": 1.8350400077866194e-05,
      "loss": 0.5707,
      "step": 12156
    },
    {
      "epoch": 0.3734525235769361,
      "grad_norm": 0.38916927576065063,
      "learning_rate": 1.8350134174130684e-05,
      "loss": 0.5909,
      "step": 12157
    },
    {
      "epoch": 0.3734832427118852,
      "grad_norm": 0.38977381587028503,
      "learning_rate": 1.8349868250892854e-05,
      "loss": 0.6137,
      "step": 12158
    },
    {
      "epoch": 0.3735139618468344,
      "grad_norm": 0.3384077548980713,
      "learning_rate": 1.8349602308153324e-05,
      "loss": 0.5917,
      "step": 12159
    },
    {
      "epoch": 0.37354468098178356,
      "grad_norm": 0.3522823452949524,
      "learning_rate": 1.834933634591271e-05,
      "loss": 0.5963,
      "step": 12160
    },
    {
      "epoch": 0.37357540011673274,
      "grad_norm": 0.5235410928726196,
      "learning_rate": 1.8349070364171643e-05,
      "loss": 0.5904,
      "step": 12161
    },
    {
      "epoch": 0.37360611925168186,
      "grad_norm": 0.3886731266975403,
      "learning_rate": 1.8348804362930735e-05,
      "loss": 0.5249,
      "step": 12162
    },
    {
      "epoch": 0.37363683838663103,
      "grad_norm": 0.3824404180049896,
      "learning_rate": 1.8348538342190617e-05,
      "loss": 0.5864,
      "step": 12163
    },
    {
      "epoch": 0.3736675575215802,
      "grad_norm": 0.33360669016838074,
      "learning_rate": 1.83482723019519e-05,
      "loss": 0.4577,
      "step": 12164
    },
    {
      "epoch": 0.3736982766565293,
      "grad_norm": 0.33303576707839966,
      "learning_rate": 1.834800624221521e-05,
      "loss": 0.5618,
      "step": 12165
    },
    {
      "epoch": 0.3737289957914785,
      "grad_norm": 0.317665159702301,
      "learning_rate": 1.834774016298117e-05,
      "loss": 0.5961,
      "step": 12166
    },
    {
      "epoch": 0.3737597149264277,
      "grad_norm": 0.3702441155910492,
      "learning_rate": 1.8347474064250402e-05,
      "loss": 0.6429,
      "step": 12167
    },
    {
      "epoch": 0.37379043406137685,
      "grad_norm": 0.36185023188591003,
      "learning_rate": 1.834720794602352e-05,
      "loss": 0.5761,
      "step": 12168
    },
    {
      "epoch": 0.373821153196326,
      "grad_norm": 0.36830878257751465,
      "learning_rate": 1.8346941808301154e-05,
      "loss": 0.589,
      "step": 12169
    },
    {
      "epoch": 0.37385187233127515,
      "grad_norm": 0.4464864134788513,
      "learning_rate": 1.8346675651083923e-05,
      "loss": 0.6566,
      "step": 12170
    },
    {
      "epoch": 0.3738825914662243,
      "grad_norm": 0.3220975995063782,
      "learning_rate": 1.834640947437245e-05,
      "loss": 0.5487,
      "step": 12171
    },
    {
      "epoch": 0.3739133106011735,
      "grad_norm": 0.3383484482765198,
      "learning_rate": 1.834614327816735e-05,
      "loss": 0.4977,
      "step": 12172
    },
    {
      "epoch": 0.3739440297361226,
      "grad_norm": 0.36472582817077637,
      "learning_rate": 1.834587706246925e-05,
      "loss": 0.668,
      "step": 12173
    },
    {
      "epoch": 0.3739747488710718,
      "grad_norm": 0.35959741473197937,
      "learning_rate": 1.8345610827278774e-05,
      "loss": 0.5763,
      "step": 12174
    },
    {
      "epoch": 0.37400546800602097,
      "grad_norm": 0.3130379915237427,
      "learning_rate": 1.834534457259654e-05,
      "loss": 0.5765,
      "step": 12175
    },
    {
      "epoch": 0.3740361871409701,
      "grad_norm": 0.33352312445640564,
      "learning_rate": 1.834507829842317e-05,
      "loss": 0.6405,
      "step": 12176
    },
    {
      "epoch": 0.37406690627591926,
      "grad_norm": 0.3498833179473877,
      "learning_rate": 1.834481200475929e-05,
      "loss": 0.553,
      "step": 12177
    },
    {
      "epoch": 0.37409762541086844,
      "grad_norm": 0.34850403666496277,
      "learning_rate": 1.8344545691605515e-05,
      "loss": 0.546,
      "step": 12178
    },
    {
      "epoch": 0.3741283445458176,
      "grad_norm": 0.4031921327114105,
      "learning_rate": 1.8344279358962472e-05,
      "loss": 0.6131,
      "step": 12179
    },
    {
      "epoch": 0.37415906368076673,
      "grad_norm": 0.3498925268650055,
      "learning_rate": 1.8344013006830783e-05,
      "loss": 0.6055,
      "step": 12180
    },
    {
      "epoch": 0.3741897828157159,
      "grad_norm": 0.30813440680503845,
      "learning_rate": 1.834374663521107e-05,
      "loss": 0.5787,
      "step": 12181
    },
    {
      "epoch": 0.3742205019506651,
      "grad_norm": 0.35841405391693115,
      "learning_rate": 1.8343480244103952e-05,
      "loss": 0.5454,
      "step": 12182
    },
    {
      "epoch": 0.3742512210856142,
      "grad_norm": 0.37997815012931824,
      "learning_rate": 1.834321383351005e-05,
      "loss": 0.5847,
      "step": 12183
    },
    {
      "epoch": 0.3742819402205634,
      "grad_norm": 0.3278006613254547,
      "learning_rate": 1.8342947403429994e-05,
      "loss": 0.5827,
      "step": 12184
    },
    {
      "epoch": 0.37431265935551256,
      "grad_norm": 0.35353365540504456,
      "learning_rate": 1.83426809538644e-05,
      "loss": 0.5689,
      "step": 12185
    },
    {
      "epoch": 0.37434337849046173,
      "grad_norm": 0.43014392256736755,
      "learning_rate": 1.834241448481389e-05,
      "loss": 0.6889,
      "step": 12186
    },
    {
      "epoch": 0.37437409762541085,
      "grad_norm": 0.35883089900016785,
      "learning_rate": 1.8342147996279092e-05,
      "loss": 0.5655,
      "step": 12187
    },
    {
      "epoch": 0.37440481676036,
      "grad_norm": 0.35833460092544556,
      "learning_rate": 1.8341881488260626e-05,
      "loss": 0.5541,
      "step": 12188
    },
    {
      "epoch": 0.3744355358953092,
      "grad_norm": 0.47719982266426086,
      "learning_rate": 1.8341614960759107e-05,
      "loss": 0.4914,
      "step": 12189
    },
    {
      "epoch": 0.3744662550302583,
      "grad_norm": 0.3193550705909729,
      "learning_rate": 1.834134841377517e-05,
      "loss": 0.6092,
      "step": 12190
    },
    {
      "epoch": 0.3744969741652075,
      "grad_norm": 0.3602188527584076,
      "learning_rate": 1.8341081847309427e-05,
      "loss": 0.6532,
      "step": 12191
    },
    {
      "epoch": 0.37452769330015667,
      "grad_norm": 0.3811357021331787,
      "learning_rate": 1.8340815261362506e-05,
      "loss": 0.5229,
      "step": 12192
    },
    {
      "epoch": 0.37455841243510585,
      "grad_norm": 0.3277207911014557,
      "learning_rate": 1.834054865593503e-05,
      "loss": 0.6291,
      "step": 12193
    },
    {
      "epoch": 0.37458913157005497,
      "grad_norm": 0.35268351435661316,
      "learning_rate": 1.834028203102762e-05,
      "loss": 0.6667,
      "step": 12194
    },
    {
      "epoch": 0.37461985070500414,
      "grad_norm": 0.37715986371040344,
      "learning_rate": 1.8340015386640896e-05,
      "loss": 0.5744,
      "step": 12195
    },
    {
      "epoch": 0.3746505698399533,
      "grad_norm": 0.37921687960624695,
      "learning_rate": 1.8339748722775485e-05,
      "loss": 0.5626,
      "step": 12196
    },
    {
      "epoch": 0.3746812889749025,
      "grad_norm": 0.3399159908294678,
      "learning_rate": 1.8339482039432006e-05,
      "loss": 0.5818,
      "step": 12197
    },
    {
      "epoch": 0.3747120081098516,
      "grad_norm": 0.35199815034866333,
      "learning_rate": 1.833921533661109e-05,
      "loss": 0.6163,
      "step": 12198
    },
    {
      "epoch": 0.3747427272448008,
      "grad_norm": 0.39986518025398254,
      "learning_rate": 1.8338948614313348e-05,
      "loss": 0.5911,
      "step": 12199
    },
    {
      "epoch": 0.37477344637974996,
      "grad_norm": 0.33342307806015015,
      "learning_rate": 1.8338681872539412e-05,
      "loss": 0.6115,
      "step": 12200
    },
    {
      "epoch": 0.3748041655146991,
      "grad_norm": 0.3572082221508026,
      "learning_rate": 1.8338415111289905e-05,
      "loss": 0.6001,
      "step": 12201
    },
    {
      "epoch": 0.37483488464964826,
      "grad_norm": 0.3955007791519165,
      "learning_rate": 1.833814833056544e-05,
      "loss": 0.5873,
      "step": 12202
    },
    {
      "epoch": 0.37486560378459743,
      "grad_norm": 0.3476649522781372,
      "learning_rate": 1.8337881530366655e-05,
      "loss": 0.5941,
      "step": 12203
    },
    {
      "epoch": 0.3748963229195466,
      "grad_norm": 0.33300742506980896,
      "learning_rate": 1.8337614710694162e-05,
      "loss": 0.5674,
      "step": 12204
    },
    {
      "epoch": 0.37492704205449573,
      "grad_norm": 0.3491385877132416,
      "learning_rate": 1.8337347871548588e-05,
      "loss": 0.518,
      "step": 12205
    },
    {
      "epoch": 0.3749577611894449,
      "grad_norm": 0.36407026648521423,
      "learning_rate": 1.8337081012930557e-05,
      "loss": 0.6407,
      "step": 12206
    },
    {
      "epoch": 0.3749884803243941,
      "grad_norm": 0.32493725419044495,
      "learning_rate": 1.8336814134840688e-05,
      "loss": 0.5763,
      "step": 12207
    },
    {
      "epoch": 0.3750191994593432,
      "grad_norm": 0.350605845451355,
      "learning_rate": 1.833654723727961e-05,
      "loss": 0.5448,
      "step": 12208
    },
    {
      "epoch": 0.3750499185942924,
      "grad_norm": 0.3420524299144745,
      "learning_rate": 1.8336280320247942e-05,
      "loss": 0.4771,
      "step": 12209
    },
    {
      "epoch": 0.37508063772924155,
      "grad_norm": 0.3285476565361023,
      "learning_rate": 1.833601338374631e-05,
      "loss": 0.5749,
      "step": 12210
    },
    {
      "epoch": 0.3751113568641907,
      "grad_norm": 0.34891006350517273,
      "learning_rate": 1.8335746427775335e-05,
      "loss": 0.5635,
      "step": 12211
    },
    {
      "epoch": 0.37514207599913985,
      "grad_norm": 0.3430192768573761,
      "learning_rate": 1.833547945233564e-05,
      "loss": 0.6914,
      "step": 12212
    },
    {
      "epoch": 0.375172795134089,
      "grad_norm": 0.3761206269264221,
      "learning_rate": 1.8335212457427854e-05,
      "loss": 0.546,
      "step": 12213
    },
    {
      "epoch": 0.3752035142690382,
      "grad_norm": 0.33406171202659607,
      "learning_rate": 1.83349454430526e-05,
      "loss": 0.5788,
      "step": 12214
    },
    {
      "epoch": 0.3752342334039873,
      "grad_norm": 0.36322659254074097,
      "learning_rate": 1.8334678409210496e-05,
      "loss": 0.5319,
      "step": 12215
    },
    {
      "epoch": 0.3752649525389365,
      "grad_norm": 0.320654034614563,
      "learning_rate": 1.8334411355902165e-05,
      "loss": 0.5831,
      "step": 12216
    },
    {
      "epoch": 0.37529567167388567,
      "grad_norm": 0.376638799905777,
      "learning_rate": 1.833414428312824e-05,
      "loss": 0.5615,
      "step": 12217
    },
    {
      "epoch": 0.37532639080883484,
      "grad_norm": 0.3476390838623047,
      "learning_rate": 1.8333877190889335e-05,
      "loss": 0.6579,
      "step": 12218
    },
    {
      "epoch": 0.37535710994378396,
      "grad_norm": 0.34455347061157227,
      "learning_rate": 1.8333610079186082e-05,
      "loss": 0.5141,
      "step": 12219
    },
    {
      "epoch": 0.37538782907873314,
      "grad_norm": 0.31734928488731384,
      "learning_rate": 1.8333342948019096e-05,
      "loss": 0.5177,
      "step": 12220
    },
    {
      "epoch": 0.3754185482136823,
      "grad_norm": 0.3605869710445404,
      "learning_rate": 1.8333075797389008e-05,
      "loss": 0.6287,
      "step": 12221
    },
    {
      "epoch": 0.3754492673486315,
      "grad_norm": 0.331885427236557,
      "learning_rate": 1.833280862729644e-05,
      "loss": 0.5015,
      "step": 12222
    },
    {
      "epoch": 0.3754799864835806,
      "grad_norm": 0.3089179992675781,
      "learning_rate": 1.8332541437742012e-05,
      "loss": 0.6035,
      "step": 12223
    },
    {
      "epoch": 0.3755107056185298,
      "grad_norm": 0.35665327310562134,
      "learning_rate": 1.8332274228726356e-05,
      "loss": 0.5682,
      "step": 12224
    },
    {
      "epoch": 0.37554142475347896,
      "grad_norm": 0.34247732162475586,
      "learning_rate": 1.833200700025009e-05,
      "loss": 0.6383,
      "step": 12225
    },
    {
      "epoch": 0.3755721438884281,
      "grad_norm": 0.34006834030151367,
      "learning_rate": 1.8331739752313836e-05,
      "loss": 0.5504,
      "step": 12226
    },
    {
      "epoch": 0.37560286302337725,
      "grad_norm": 0.34427472949028015,
      "learning_rate": 1.8331472484918226e-05,
      "loss": 0.5539,
      "step": 12227
    },
    {
      "epoch": 0.37563358215832643,
      "grad_norm": 0.3650262951850891,
      "learning_rate": 1.833120519806388e-05,
      "loss": 0.5047,
      "step": 12228
    },
    {
      "epoch": 0.3756643012932756,
      "grad_norm": 0.43642282485961914,
      "learning_rate": 1.8330937891751424e-05,
      "loss": 0.6229,
      "step": 12229
    },
    {
      "epoch": 0.3756950204282247,
      "grad_norm": 0.36465150117874146,
      "learning_rate": 1.8330670565981478e-05,
      "loss": 0.6171,
      "step": 12230
    },
    {
      "epoch": 0.3757257395631739,
      "grad_norm": 0.3769433796405792,
      "learning_rate": 1.833040322075467e-05,
      "loss": 0.5922,
      "step": 12231
    },
    {
      "epoch": 0.3757564586981231,
      "grad_norm": 0.34797239303588867,
      "learning_rate": 1.8330135856071624e-05,
      "loss": 0.5924,
      "step": 12232
    },
    {
      "epoch": 0.3757871778330722,
      "grad_norm": 0.32304349541664124,
      "learning_rate": 1.832986847193296e-05,
      "loss": 0.5858,
      "step": 12233
    },
    {
      "epoch": 0.37581789696802137,
      "grad_norm": 0.404876708984375,
      "learning_rate": 1.832960106833931e-05,
      "loss": 0.6114,
      "step": 12234
    },
    {
      "epoch": 0.37584861610297055,
      "grad_norm": 0.3882769048213959,
      "learning_rate": 1.8329333645291293e-05,
      "loss": 0.5448,
      "step": 12235
    },
    {
      "epoch": 0.3758793352379197,
      "grad_norm": 0.3431379795074463,
      "learning_rate": 1.832906620278954e-05,
      "loss": 0.5621,
      "step": 12236
    },
    {
      "epoch": 0.37591005437286884,
      "grad_norm": 0.3420567214488983,
      "learning_rate": 1.8328798740834668e-05,
      "loss": 0.6311,
      "step": 12237
    },
    {
      "epoch": 0.375940773507818,
      "grad_norm": 0.3867284655570984,
      "learning_rate": 1.8328531259427303e-05,
      "loss": 0.6216,
      "step": 12238
    },
    {
      "epoch": 0.3759714926427672,
      "grad_norm": 0.32543623447418213,
      "learning_rate": 1.8328263758568075e-05,
      "loss": 0.5391,
      "step": 12239
    },
    {
      "epoch": 0.37600221177771637,
      "grad_norm": 0.3603736162185669,
      "learning_rate": 1.8327996238257605e-05,
      "loss": 0.5528,
      "step": 12240
    },
    {
      "epoch": 0.3760329309126655,
      "grad_norm": 0.3343682885169983,
      "learning_rate": 1.832772869849652e-05,
      "loss": 0.4703,
      "step": 12241
    },
    {
      "epoch": 0.37606365004761466,
      "grad_norm": 0.3669746220111847,
      "learning_rate": 1.8327461139285437e-05,
      "loss": 0.5953,
      "step": 12242
    },
    {
      "epoch": 0.37609436918256384,
      "grad_norm": 0.3647971451282501,
      "learning_rate": 1.832719356062499e-05,
      "loss": 0.6329,
      "step": 12243
    },
    {
      "epoch": 0.37612508831751296,
      "grad_norm": 0.3334681987762451,
      "learning_rate": 1.83269259625158e-05,
      "loss": 0.4784,
      "step": 12244
    },
    {
      "epoch": 0.37615580745246213,
      "grad_norm": 0.35470861196517944,
      "learning_rate": 1.8326658344958495e-05,
      "loss": 0.5535,
      "step": 12245
    },
    {
      "epoch": 0.3761865265874113,
      "grad_norm": 0.3255474269390106,
      "learning_rate": 1.8326390707953695e-05,
      "loss": 0.5369,
      "step": 12246
    },
    {
      "epoch": 0.3762172457223605,
      "grad_norm": 0.36783820390701294,
      "learning_rate": 1.8326123051502033e-05,
      "loss": 0.5435,
      "step": 12247
    },
    {
      "epoch": 0.3762479648573096,
      "grad_norm": 0.28256264328956604,
      "learning_rate": 1.8325855375604123e-05,
      "loss": 0.5514,
      "step": 12248
    },
    {
      "epoch": 0.3762786839922588,
      "grad_norm": 0.3693925440311432,
      "learning_rate": 1.83255876802606e-05,
      "loss": 0.5731,
      "step": 12249
    },
    {
      "epoch": 0.37630940312720795,
      "grad_norm": 0.35602855682373047,
      "learning_rate": 1.8325319965472085e-05,
      "loss": 0.5093,
      "step": 12250
    },
    {
      "epoch": 0.3763401222621571,
      "grad_norm": 0.3890112638473511,
      "learning_rate": 1.8325052231239202e-05,
      "loss": 0.5474,
      "step": 12251
    },
    {
      "epoch": 0.37637084139710625,
      "grad_norm": 0.36882302165031433,
      "learning_rate": 1.832478447756258e-05,
      "loss": 0.5475,
      "step": 12252
    },
    {
      "epoch": 0.3764015605320554,
      "grad_norm": 0.37117791175842285,
      "learning_rate": 1.8324516704442846e-05,
      "loss": 0.5519,
      "step": 12253
    },
    {
      "epoch": 0.3764322796670046,
      "grad_norm": 0.31239303946495056,
      "learning_rate": 1.8324248911880615e-05,
      "loss": 0.5461,
      "step": 12254
    },
    {
      "epoch": 0.3764629988019537,
      "grad_norm": 0.3671448826789856,
      "learning_rate": 1.8323981099876525e-05,
      "loss": 0.5876,
      "step": 12255
    },
    {
      "epoch": 0.3764937179369029,
      "grad_norm": 0.33763256669044495,
      "learning_rate": 1.8323713268431193e-05,
      "loss": 0.5879,
      "step": 12256
    },
    {
      "epoch": 0.37652443707185207,
      "grad_norm": 0.3515906035900116,
      "learning_rate": 1.8323445417545245e-05,
      "loss": 0.5867,
      "step": 12257
    },
    {
      "epoch": 0.3765551562068012,
      "grad_norm": 0.31756818294525146,
      "learning_rate": 1.832317754721931e-05,
      "loss": 0.5532,
      "step": 12258
    },
    {
      "epoch": 0.37658587534175036,
      "grad_norm": 0.34266868233680725,
      "learning_rate": 1.8322909657454016e-05,
      "loss": 0.6109,
      "step": 12259
    },
    {
      "epoch": 0.37661659447669954,
      "grad_norm": 0.3945513367652893,
      "learning_rate": 1.832264174824998e-05,
      "loss": 0.6049,
      "step": 12260
    },
    {
      "epoch": 0.3766473136116487,
      "grad_norm": 0.3704911470413208,
      "learning_rate": 1.832237381960784e-05,
      "loss": 0.5637,
      "step": 12261
    },
    {
      "epoch": 0.37667803274659784,
      "grad_norm": 0.3803843557834625,
      "learning_rate": 1.832210587152821e-05,
      "loss": 0.551,
      "step": 12262
    },
    {
      "epoch": 0.376708751881547,
      "grad_norm": 0.3391750752925873,
      "learning_rate": 1.832183790401172e-05,
      "loss": 0.583,
      "step": 12263
    },
    {
      "epoch": 0.3767394710164962,
      "grad_norm": 0.3558330833911896,
      "learning_rate": 1.8321569917059e-05,
      "loss": 0.5817,
      "step": 12264
    },
    {
      "epoch": 0.37677019015144536,
      "grad_norm": 0.3763715624809265,
      "learning_rate": 1.832130191067067e-05,
      "loss": 0.5738,
      "step": 12265
    },
    {
      "epoch": 0.3768009092863945,
      "grad_norm": 0.3503153920173645,
      "learning_rate": 1.8321033884847357e-05,
      "loss": 0.5716,
      "step": 12266
    },
    {
      "epoch": 0.37683162842134366,
      "grad_norm": 0.34974613785743713,
      "learning_rate": 1.832076583958969e-05,
      "loss": 0.5238,
      "step": 12267
    },
    {
      "epoch": 0.37686234755629283,
      "grad_norm": 0.33951810002326965,
      "learning_rate": 1.832049777489829e-05,
      "loss": 0.5393,
      "step": 12268
    },
    {
      "epoch": 0.37689306669124195,
      "grad_norm": 0.32719266414642334,
      "learning_rate": 1.832022969077379e-05,
      "loss": 0.5787,
      "step": 12269
    },
    {
      "epoch": 0.3769237858261911,
      "grad_norm": 0.33814293146133423,
      "learning_rate": 1.8319961587216813e-05,
      "loss": 0.4609,
      "step": 12270
    },
    {
      "epoch": 0.3769545049611403,
      "grad_norm": 0.3077945411205292,
      "learning_rate": 1.8319693464227985e-05,
      "loss": 0.5449,
      "step": 12271
    },
    {
      "epoch": 0.3769852240960895,
      "grad_norm": 0.3228076100349426,
      "learning_rate": 1.8319425321807926e-05,
      "loss": 0.5372,
      "step": 12272
    },
    {
      "epoch": 0.3770159432310386,
      "grad_norm": 1.9420766830444336,
      "learning_rate": 1.8319157159957274e-05,
      "loss": 0.6256,
      "step": 12273
    },
    {
      "epoch": 0.3770466623659878,
      "grad_norm": 0.29438912868499756,
      "learning_rate": 1.831888897867665e-05,
      "loss": 0.5874,
      "step": 12274
    },
    {
      "epoch": 0.37707738150093695,
      "grad_norm": 0.35462504625320435,
      "learning_rate": 1.8318620777966676e-05,
      "loss": 0.5284,
      "step": 12275
    },
    {
      "epoch": 0.37710810063588607,
      "grad_norm": 0.33981436491012573,
      "learning_rate": 1.8318352557827984e-05,
      "loss": 0.6187,
      "step": 12276
    },
    {
      "epoch": 0.37713881977083524,
      "grad_norm": 0.3738057315349579,
      "learning_rate": 1.8318084318261195e-05,
      "loss": 0.5732,
      "step": 12277
    },
    {
      "epoch": 0.3771695389057844,
      "grad_norm": 0.34464284777641296,
      "learning_rate": 1.8317816059266943e-05,
      "loss": 0.6318,
      "step": 12278
    },
    {
      "epoch": 0.3772002580407336,
      "grad_norm": 0.38084378838539124,
      "learning_rate": 1.831754778084585e-05,
      "loss": 0.6736,
      "step": 12279
    },
    {
      "epoch": 0.3772309771756827,
      "grad_norm": 0.34842315316200256,
      "learning_rate": 1.8317279482998547e-05,
      "loss": 0.5591,
      "step": 12280
    },
    {
      "epoch": 0.3772616963106319,
      "grad_norm": 0.3528923988342285,
      "learning_rate": 1.831701116572565e-05,
      "loss": 0.5739,
      "step": 12281
    },
    {
      "epoch": 0.37729241544558106,
      "grad_norm": 0.31411728262901306,
      "learning_rate": 1.8316742829027797e-05,
      "loss": 0.5719,
      "step": 12282
    },
    {
      "epoch": 0.37732313458053024,
      "grad_norm": 0.3332708179950714,
      "learning_rate": 1.8316474472905608e-05,
      "loss": 0.5521,
      "step": 12283
    },
    {
      "epoch": 0.37735385371547936,
      "grad_norm": 0.32694488763809204,
      "learning_rate": 1.8316206097359714e-05,
      "loss": 0.54,
      "step": 12284
    },
    {
      "epoch": 0.37738457285042853,
      "grad_norm": 0.32313162088394165,
      "learning_rate": 1.8315937702390738e-05,
      "loss": 0.5221,
      "step": 12285
    },
    {
      "epoch": 0.3774152919853777,
      "grad_norm": 0.3670596778392792,
      "learning_rate": 1.831566928799931e-05,
      "loss": 0.5687,
      "step": 12286
    },
    {
      "epoch": 0.37744601112032683,
      "grad_norm": 0.3882518410682678,
      "learning_rate": 1.8315400854186057e-05,
      "loss": 0.5635,
      "step": 12287
    },
    {
      "epoch": 0.377476730255276,
      "grad_norm": 0.34982070326805115,
      "learning_rate": 1.8315132400951602e-05,
      "loss": 0.607,
      "step": 12288
    },
    {
      "epoch": 0.3775074493902252,
      "grad_norm": 0.3151768743991852,
      "learning_rate": 1.831486392829658e-05,
      "loss": 0.6262,
      "step": 12289
    },
    {
      "epoch": 0.37753816852517436,
      "grad_norm": 0.3885985016822815,
      "learning_rate": 1.8314595436221604e-05,
      "loss": 0.639,
      "step": 12290
    },
    {
      "epoch": 0.3775688876601235,
      "grad_norm": 0.34915247559547424,
      "learning_rate": 1.8314326924727315e-05,
      "loss": 0.5698,
      "step": 12291
    },
    {
      "epoch": 0.37759960679507265,
      "grad_norm": 0.328635036945343,
      "learning_rate": 1.8314058393814335e-05,
      "loss": 0.5221,
      "step": 12292
    },
    {
      "epoch": 0.3776303259300218,
      "grad_norm": 0.3257386088371277,
      "learning_rate": 1.8313789843483287e-05,
      "loss": 0.4915,
      "step": 12293
    },
    {
      "epoch": 0.37766104506497095,
      "grad_norm": 0.39388802647590637,
      "learning_rate": 1.831352127373481e-05,
      "loss": 0.5509,
      "step": 12294
    },
    {
      "epoch": 0.3776917641999201,
      "grad_norm": 0.361794650554657,
      "learning_rate": 1.8313252684569512e-05,
      "loss": 0.5246,
      "step": 12295
    },
    {
      "epoch": 0.3777224833348693,
      "grad_norm": 0.35145822167396545,
      "learning_rate": 1.831298407598804e-05,
      "loss": 0.5464,
      "step": 12296
    },
    {
      "epoch": 0.37775320246981847,
      "grad_norm": 0.569258451461792,
      "learning_rate": 1.8312715447991012e-05,
      "loss": 0.4746,
      "step": 12297
    },
    {
      "epoch": 0.3777839216047676,
      "grad_norm": 0.3518896996974945,
      "learning_rate": 1.8312446800579055e-05,
      "loss": 0.5619,
      "step": 12298
    },
    {
      "epoch": 0.37781464073971677,
      "grad_norm": 0.3691684901714325,
      "learning_rate": 1.8312178133752798e-05,
      "loss": 0.5389,
      "step": 12299
    },
    {
      "epoch": 0.37784535987466594,
      "grad_norm": 0.3202275037765503,
      "learning_rate": 1.831190944751287e-05,
      "loss": 0.489,
      "step": 12300
    },
    {
      "epoch": 0.37787607900961506,
      "grad_norm": 0.34359675645828247,
      "learning_rate": 1.8311640741859894e-05,
      "loss": 0.5976,
      "step": 12301
    },
    {
      "epoch": 0.37790679814456424,
      "grad_norm": 0.356679767370224,
      "learning_rate": 1.83113720167945e-05,
      "loss": 0.5898,
      "step": 12302
    },
    {
      "epoch": 0.3779375172795134,
      "grad_norm": 0.35042378306388855,
      "learning_rate": 1.8311103272317325e-05,
      "loss": 0.5827,
      "step": 12303
    },
    {
      "epoch": 0.3779682364144626,
      "grad_norm": 0.3414706289768219,
      "learning_rate": 1.831083450842898e-05,
      "loss": 0.6057,
      "step": 12304
    },
    {
      "epoch": 0.3779989555494117,
      "grad_norm": 0.3747488558292389,
      "learning_rate": 1.83105657251301e-05,
      "loss": 0.5883,
      "step": 12305
    },
    {
      "epoch": 0.3780296746843609,
      "grad_norm": 0.3635494112968445,
      "learning_rate": 1.8310296922421318e-05,
      "loss": 0.5527,
      "step": 12306
    },
    {
      "epoch": 0.37806039381931006,
      "grad_norm": 0.34734907746315,
      "learning_rate": 1.8310028100303255e-05,
      "loss": 0.5355,
      "step": 12307
    },
    {
      "epoch": 0.37809111295425923,
      "grad_norm": 0.3484237790107727,
      "learning_rate": 1.8309759258776538e-05,
      "loss": 0.6709,
      "step": 12308
    },
    {
      "epoch": 0.37812183208920835,
      "grad_norm": 0.42232149839401245,
      "learning_rate": 1.83094903978418e-05,
      "loss": 0.5363,
      "step": 12309
    },
    {
      "epoch": 0.37815255122415753,
      "grad_norm": 0.3293205201625824,
      "learning_rate": 1.830922151749967e-05,
      "loss": 0.5688,
      "step": 12310
    },
    {
      "epoch": 0.3781832703591067,
      "grad_norm": 0.3235052227973938,
      "learning_rate": 1.8308952617750767e-05,
      "loss": 0.5726,
      "step": 12311
    },
    {
      "epoch": 0.3782139894940558,
      "grad_norm": 0.3150380551815033,
      "learning_rate": 1.830868369859573e-05,
      "loss": 0.5779,
      "step": 12312
    },
    {
      "epoch": 0.378244708629005,
      "grad_norm": 0.4560126066207886,
      "learning_rate": 1.830841476003518e-05,
      "loss": 0.6344,
      "step": 12313
    },
    {
      "epoch": 0.3782754277639542,
      "grad_norm": 0.33381712436676025,
      "learning_rate": 1.8308145802069746e-05,
      "loss": 0.5632,
      "step": 12314
    },
    {
      "epoch": 0.37830614689890335,
      "grad_norm": 0.3752351999282837,
      "learning_rate": 1.830787682470006e-05,
      "loss": 0.6707,
      "step": 12315
    },
    {
      "epoch": 0.37833686603385247,
      "grad_norm": 0.37942636013031006,
      "learning_rate": 1.8307607827926747e-05,
      "loss": 0.5702,
      "step": 12316
    },
    {
      "epoch": 0.37836758516880165,
      "grad_norm": 0.6934341192245483,
      "learning_rate": 1.8307338811750434e-05,
      "loss": 0.6794,
      "step": 12317
    },
    {
      "epoch": 0.3783983043037508,
      "grad_norm": 0.35013946890830994,
      "learning_rate": 1.830706977617175e-05,
      "loss": 0.5833,
      "step": 12318
    },
    {
      "epoch": 0.37842902343869994,
      "grad_norm": 0.35414832830429077,
      "learning_rate": 1.8306800721191328e-05,
      "loss": 0.6106,
      "step": 12319
    },
    {
      "epoch": 0.3784597425736491,
      "grad_norm": 0.3600907325744629,
      "learning_rate": 1.830653164680979e-05,
      "loss": 0.6142,
      "step": 12320
    },
    {
      "epoch": 0.3784904617085983,
      "grad_norm": 0.3922841250896454,
      "learning_rate": 1.8306262553027768e-05,
      "loss": 0.5566,
      "step": 12321
    },
    {
      "epoch": 0.37852118084354747,
      "grad_norm": 0.3489941358566284,
      "learning_rate": 1.830599343984589e-05,
      "loss": 0.6065,
      "step": 12322
    },
    {
      "epoch": 0.3785518999784966,
      "grad_norm": 0.3441988527774811,
      "learning_rate": 1.8305724307264785e-05,
      "loss": 0.6007,
      "step": 12323
    },
    {
      "epoch": 0.37858261911344576,
      "grad_norm": 0.315552681684494,
      "learning_rate": 1.830545515528508e-05,
      "loss": 0.6127,
      "step": 12324
    },
    {
      "epoch": 0.37861333824839494,
      "grad_norm": 0.3315088748931885,
      "learning_rate": 1.8305185983907405e-05,
      "loss": 0.5901,
      "step": 12325
    },
    {
      "epoch": 0.3786440573833441,
      "grad_norm": 0.42870375514030457,
      "learning_rate": 1.8304916793132387e-05,
      "loss": 0.6313,
      "step": 12326
    },
    {
      "epoch": 0.37867477651829323,
      "grad_norm": 0.4204654097557068,
      "learning_rate": 1.8304647582960654e-05,
      "loss": 0.6295,
      "step": 12327
    },
    {
      "epoch": 0.3787054956532424,
      "grad_norm": 0.3144787847995758,
      "learning_rate": 1.830437835339284e-05,
      "loss": 0.5384,
      "step": 12328
    },
    {
      "epoch": 0.3787362147881916,
      "grad_norm": 0.40037837624549866,
      "learning_rate": 1.830410910442957e-05,
      "loss": 0.7496,
      "step": 12329
    },
    {
      "epoch": 0.3787669339231407,
      "grad_norm": 0.41805723309516907,
      "learning_rate": 1.8303839836071473e-05,
      "loss": 0.6229,
      "step": 12330
    },
    {
      "epoch": 0.3787976530580899,
      "grad_norm": 0.32610806822776794,
      "learning_rate": 1.8303570548319175e-05,
      "loss": 0.5828,
      "step": 12331
    },
    {
      "epoch": 0.37882837219303905,
      "grad_norm": 0.35919129848480225,
      "learning_rate": 1.8303301241173313e-05,
      "loss": 0.5577,
      "step": 12332
    },
    {
      "epoch": 0.37885909132798823,
      "grad_norm": 0.41950199007987976,
      "learning_rate": 1.8303031914634507e-05,
      "loss": 0.6215,
      "step": 12333
    },
    {
      "epoch": 0.37888981046293735,
      "grad_norm": 0.3801644444465637,
      "learning_rate": 1.8302762568703392e-05,
      "loss": 0.641,
      "step": 12334
    },
    {
      "epoch": 0.3789205295978865,
      "grad_norm": 0.42439576983451843,
      "learning_rate": 1.8302493203380597e-05,
      "loss": 0.5549,
      "step": 12335
    },
    {
      "epoch": 0.3789512487328357,
      "grad_norm": 0.3466308116912842,
      "learning_rate": 1.8302223818666744e-05,
      "loss": 0.5846,
      "step": 12336
    },
    {
      "epoch": 0.3789819678677848,
      "grad_norm": 0.34697139263153076,
      "learning_rate": 1.830195441456247e-05,
      "loss": 0.5192,
      "step": 12337
    },
    {
      "epoch": 0.379012687002734,
      "grad_norm": 0.3268202245235443,
      "learning_rate": 1.8301684991068404e-05,
      "loss": 0.564,
      "step": 12338
    },
    {
      "epoch": 0.37904340613768317,
      "grad_norm": 0.36887508630752563,
      "learning_rate": 1.830141554818517e-05,
      "loss": 0.6393,
      "step": 12339
    },
    {
      "epoch": 0.37907412527263235,
      "grad_norm": 0.3782278597354889,
      "learning_rate": 1.8301146085913402e-05,
      "loss": 0.6397,
      "step": 12340
    },
    {
      "epoch": 0.37910484440758146,
      "grad_norm": 0.338249146938324,
      "learning_rate": 1.830087660425373e-05,
      "loss": 0.5529,
      "step": 12341
    },
    {
      "epoch": 0.37913556354253064,
      "grad_norm": 0.3579395115375519,
      "learning_rate": 1.8300607103206775e-05,
      "loss": 0.5812,
      "step": 12342
    },
    {
      "epoch": 0.3791662826774798,
      "grad_norm": 0.3726062774658203,
      "learning_rate": 1.8300337582773175e-05,
      "loss": 0.5527,
      "step": 12343
    },
    {
      "epoch": 0.37919700181242894,
      "grad_norm": 0.3763701915740967,
      "learning_rate": 1.830006804295356e-05,
      "loss": 0.6381,
      "step": 12344
    },
    {
      "epoch": 0.3792277209473781,
      "grad_norm": 0.45430079102516174,
      "learning_rate": 1.829979848374855e-05,
      "loss": 0.5851,
      "step": 12345
    },
    {
      "epoch": 0.3792584400823273,
      "grad_norm": 0.32820263504981995,
      "learning_rate": 1.8299528905158784e-05,
      "loss": 0.5388,
      "step": 12346
    },
    {
      "epoch": 0.37928915921727646,
      "grad_norm": 0.3412542939186096,
      "learning_rate": 1.829925930718489e-05,
      "loss": 0.655,
      "step": 12347
    },
    {
      "epoch": 0.3793198783522256,
      "grad_norm": 0.3783092796802521,
      "learning_rate": 1.8298989689827497e-05,
      "loss": 0.6041,
      "step": 12348
    },
    {
      "epoch": 0.37935059748717476,
      "grad_norm": 0.360632985830307,
      "learning_rate": 1.8298720053087234e-05,
      "loss": 0.5895,
      "step": 12349
    },
    {
      "epoch": 0.37938131662212393,
      "grad_norm": 0.3429313600063324,
      "learning_rate": 1.8298450396964726e-05,
      "loss": 0.6101,
      "step": 12350
    },
    {
      "epoch": 0.3794120357570731,
      "grad_norm": 0.30949389934539795,
      "learning_rate": 1.8298180721460613e-05,
      "loss": 0.6204,
      "step": 12351
    },
    {
      "epoch": 0.3794427548920222,
      "grad_norm": 0.3796344995498657,
      "learning_rate": 1.8297911026575516e-05,
      "loss": 0.5681,
      "step": 12352
    },
    {
      "epoch": 0.3794734740269714,
      "grad_norm": 0.32479795813560486,
      "learning_rate": 1.829764131231007e-05,
      "loss": 0.5388,
      "step": 12353
    },
    {
      "epoch": 0.3795041931619206,
      "grad_norm": 0.32565009593963623,
      "learning_rate": 1.8297371578664903e-05,
      "loss": 0.561,
      "step": 12354
    },
    {
      "epoch": 0.3795349122968697,
      "grad_norm": 0.3914946913719177,
      "learning_rate": 1.8297101825640643e-05,
      "loss": 0.5644,
      "step": 12355
    },
    {
      "epoch": 0.3795656314318189,
      "grad_norm": 0.34023961424827576,
      "learning_rate": 1.8296832053237926e-05,
      "loss": 0.6234,
      "step": 12356
    },
    {
      "epoch": 0.37959635056676805,
      "grad_norm": 0.41376346349716187,
      "learning_rate": 1.8296562261457376e-05,
      "loss": 0.6247,
      "step": 12357
    },
    {
      "epoch": 0.3796270697017172,
      "grad_norm": 0.3933202922344208,
      "learning_rate": 1.8296292450299626e-05,
      "loss": 0.6511,
      "step": 12358
    },
    {
      "epoch": 0.37965778883666634,
      "grad_norm": 0.32662689685821533,
      "learning_rate": 1.8296022619765306e-05,
      "loss": 0.5613,
      "step": 12359
    },
    {
      "epoch": 0.3796885079716155,
      "grad_norm": 0.30137085914611816,
      "learning_rate": 1.8295752769855046e-05,
      "loss": 0.4673,
      "step": 12360
    },
    {
      "epoch": 0.3797192271065647,
      "grad_norm": 0.39787188172340393,
      "learning_rate": 1.8295482900569474e-05,
      "loss": 0.5249,
      "step": 12361
    },
    {
      "epoch": 0.3797499462415138,
      "grad_norm": 0.3400951623916626,
      "learning_rate": 1.8295213011909222e-05,
      "loss": 0.5861,
      "step": 12362
    },
    {
      "epoch": 0.379780665376463,
      "grad_norm": 0.4007326662540436,
      "learning_rate": 1.8294943103874924e-05,
      "loss": 0.5687,
      "step": 12363
    },
    {
      "epoch": 0.37981138451141216,
      "grad_norm": 0.45836809277534485,
      "learning_rate": 1.8294673176467204e-05,
      "loss": 0.4778,
      "step": 12364
    },
    {
      "epoch": 0.37984210364636134,
      "grad_norm": 0.3908834755420685,
      "learning_rate": 1.8294403229686696e-05,
      "loss": 0.5474,
      "step": 12365
    },
    {
      "epoch": 0.37987282278131046,
      "grad_norm": 0.3474871814250946,
      "learning_rate": 1.8294133263534032e-05,
      "loss": 0.5613,
      "step": 12366
    },
    {
      "epoch": 0.37990354191625963,
      "grad_norm": 0.4676002264022827,
      "learning_rate": 1.829386327800984e-05,
      "loss": 0.5845,
      "step": 12367
    },
    {
      "epoch": 0.3799342610512088,
      "grad_norm": 0.3514297306537628,
      "learning_rate": 1.829359327311475e-05,
      "loss": 0.6441,
      "step": 12368
    },
    {
      "epoch": 0.37996498018615793,
      "grad_norm": 0.3677128553390503,
      "learning_rate": 1.8293323248849396e-05,
      "loss": 0.5586,
      "step": 12369
    },
    {
      "epoch": 0.3799956993211071,
      "grad_norm": 0.3888852000236511,
      "learning_rate": 1.8293053205214403e-05,
      "loss": 0.5456,
      "step": 12370
    },
    {
      "epoch": 0.3800264184560563,
      "grad_norm": 0.341880202293396,
      "learning_rate": 1.8292783142210407e-05,
      "loss": 0.515,
      "step": 12371
    },
    {
      "epoch": 0.38005713759100546,
      "grad_norm": 0.3894100487232208,
      "learning_rate": 1.8292513059838036e-05,
      "loss": 0.636,
      "step": 12372
    },
    {
      "epoch": 0.3800878567259546,
      "grad_norm": 0.6547061800956726,
      "learning_rate": 1.8292242958097922e-05,
      "loss": 0.5806,
      "step": 12373
    },
    {
      "epoch": 0.38011857586090375,
      "grad_norm": 0.3474220633506775,
      "learning_rate": 1.8291972836990694e-05,
      "loss": 0.5733,
      "step": 12374
    },
    {
      "epoch": 0.3801492949958529,
      "grad_norm": 0.35453158617019653,
      "learning_rate": 1.8291702696516987e-05,
      "loss": 0.628,
      "step": 12375
    },
    {
      "epoch": 0.3801800141308021,
      "grad_norm": 0.3710530698299408,
      "learning_rate": 1.8291432536677426e-05,
      "loss": 0.6085,
      "step": 12376
    },
    {
      "epoch": 0.3802107332657512,
      "grad_norm": 0.3311328589916229,
      "learning_rate": 1.829116235747265e-05,
      "loss": 0.4868,
      "step": 12377
    },
    {
      "epoch": 0.3802414524007004,
      "grad_norm": 0.3517089784145355,
      "learning_rate": 1.8290892158903282e-05,
      "loss": 0.6586,
      "step": 12378
    },
    {
      "epoch": 0.3802721715356496,
      "grad_norm": 0.31486776471138,
      "learning_rate": 1.8290621940969956e-05,
      "loss": 0.5589,
      "step": 12379
    },
    {
      "epoch": 0.3803028906705987,
      "grad_norm": 0.3229255974292755,
      "learning_rate": 1.8290351703673305e-05,
      "loss": 0.5912,
      "step": 12380
    },
    {
      "epoch": 0.38033360980554787,
      "grad_norm": 0.3366328477859497,
      "learning_rate": 1.8290081447013958e-05,
      "loss": 0.6163,
      "step": 12381
    },
    {
      "epoch": 0.38036432894049704,
      "grad_norm": 0.32260873913764954,
      "learning_rate": 1.8289811170992546e-05,
      "loss": 0.579,
      "step": 12382
    },
    {
      "epoch": 0.3803950480754462,
      "grad_norm": 0.3857443928718567,
      "learning_rate": 1.8289540875609702e-05,
      "loss": 0.6517,
      "step": 12383
    },
    {
      "epoch": 0.38042576721039534,
      "grad_norm": 0.5314890742301941,
      "learning_rate": 1.8289270560866053e-05,
      "loss": 0.5289,
      "step": 12384
    },
    {
      "epoch": 0.3804564863453445,
      "grad_norm": 0.34102991223335266,
      "learning_rate": 1.828900022676224e-05,
      "loss": 0.5651,
      "step": 12385
    },
    {
      "epoch": 0.3804872054802937,
      "grad_norm": 0.38710248470306396,
      "learning_rate": 1.8288729873298883e-05,
      "loss": 0.489,
      "step": 12386
    },
    {
      "epoch": 0.3805179246152428,
      "grad_norm": 0.3744886815547943,
      "learning_rate": 1.8288459500476624e-05,
      "loss": 0.5346,
      "step": 12387
    },
    {
      "epoch": 0.380548643750192,
      "grad_norm": 0.3526829779148102,
      "learning_rate": 1.828818910829608e-05,
      "loss": 0.6013,
      "step": 12388
    },
    {
      "epoch": 0.38057936288514116,
      "grad_norm": 0.3706074059009552,
      "learning_rate": 1.82879186967579e-05,
      "loss": 0.5019,
      "step": 12389
    },
    {
      "epoch": 0.38061008202009033,
      "grad_norm": 0.34045615792274475,
      "learning_rate": 1.8287648265862702e-05,
      "loss": 0.6031,
      "step": 12390
    },
    {
      "epoch": 0.38064080115503945,
      "grad_norm": 0.3795492351055145,
      "learning_rate": 1.8287377815611126e-05,
      "loss": 0.517,
      "step": 12391
    },
    {
      "epoch": 0.38067152028998863,
      "grad_norm": 0.4329891502857208,
      "learning_rate": 1.82871073460038e-05,
      "loss": 0.5124,
      "step": 12392
    },
    {
      "epoch": 0.3807022394249378,
      "grad_norm": 0.3825784921646118,
      "learning_rate": 1.8286836857041354e-05,
      "loss": 0.659,
      "step": 12393
    },
    {
      "epoch": 0.380732958559887,
      "grad_norm": 0.3097206950187683,
      "learning_rate": 1.8286566348724422e-05,
      "loss": 0.5129,
      "step": 12394
    },
    {
      "epoch": 0.3807636776948361,
      "grad_norm": 0.3424071669578552,
      "learning_rate": 1.8286295821053638e-05,
      "loss": 0.5257,
      "step": 12395
    },
    {
      "epoch": 0.3807943968297853,
      "grad_norm": 0.3581220209598541,
      "learning_rate": 1.8286025274029628e-05,
      "loss": 0.6034,
      "step": 12396
    },
    {
      "epoch": 0.38082511596473445,
      "grad_norm": 0.2963148057460785,
      "learning_rate": 1.8285754707653026e-05,
      "loss": 0.4981,
      "step": 12397
    },
    {
      "epoch": 0.38085583509968357,
      "grad_norm": 0.3590690493583679,
      "learning_rate": 1.828548412192447e-05,
      "loss": 0.684,
      "step": 12398
    },
    {
      "epoch": 0.38088655423463275,
      "grad_norm": 0.3720987141132355,
      "learning_rate": 1.8285213516844584e-05,
      "loss": 0.5948,
      "step": 12399
    },
    {
      "epoch": 0.3809172733695819,
      "grad_norm": 0.345813512802124,
      "learning_rate": 1.8284942892414005e-05,
      "loss": 0.546,
      "step": 12400
    },
    {
      "epoch": 0.3809479925045311,
      "grad_norm": 0.3558904230594635,
      "learning_rate": 1.8284672248633364e-05,
      "loss": 0.5574,
      "step": 12401
    },
    {
      "epoch": 0.3809787116394802,
      "grad_norm": 0.33116671442985535,
      "learning_rate": 1.828440158550329e-05,
      "loss": 0.5963,
      "step": 12402
    },
    {
      "epoch": 0.3810094307744294,
      "grad_norm": 0.37790828943252563,
      "learning_rate": 1.828413090302442e-05,
      "loss": 0.5221,
      "step": 12403
    },
    {
      "epoch": 0.38104014990937857,
      "grad_norm": 0.33549293875694275,
      "learning_rate": 1.828386020119738e-05,
      "loss": 0.5376,
      "step": 12404
    },
    {
      "epoch": 0.3810708690443277,
      "grad_norm": 0.34645259380340576,
      "learning_rate": 1.828358948002281e-05,
      "loss": 0.5768,
      "step": 12405
    },
    {
      "epoch": 0.38110158817927686,
      "grad_norm": 0.31862109899520874,
      "learning_rate": 1.8283318739501336e-05,
      "loss": 0.5494,
      "step": 12406
    },
    {
      "epoch": 0.38113230731422604,
      "grad_norm": 0.3225826919078827,
      "learning_rate": 1.8283047979633593e-05,
      "loss": 0.5675,
      "step": 12407
    },
    {
      "epoch": 0.3811630264491752,
      "grad_norm": 0.3359171450138092,
      "learning_rate": 1.8282777200420214e-05,
      "loss": 0.5471,
      "step": 12408
    },
    {
      "epoch": 0.38119374558412433,
      "grad_norm": 1.259356141090393,
      "learning_rate": 1.8282506401861832e-05,
      "loss": 0.6143,
      "step": 12409
    },
    {
      "epoch": 0.3812244647190735,
      "grad_norm": 0.35441625118255615,
      "learning_rate": 1.8282235583959074e-05,
      "loss": 0.5481,
      "step": 12410
    },
    {
      "epoch": 0.3812551838540227,
      "grad_norm": 0.34135913848876953,
      "learning_rate": 1.8281964746712578e-05,
      "loss": 0.5165,
      "step": 12411
    },
    {
      "epoch": 0.3812859029889718,
      "grad_norm": 0.36771783232688904,
      "learning_rate": 1.8281693890122973e-05,
      "loss": 0.5723,
      "step": 12412
    },
    {
      "epoch": 0.381316622123921,
      "grad_norm": 0.3559032082557678,
      "learning_rate": 1.8281423014190896e-05,
      "loss": 0.6204,
      "step": 12413
    },
    {
      "epoch": 0.38134734125887015,
      "grad_norm": 0.35515573620796204,
      "learning_rate": 1.8281152118916977e-05,
      "loss": 0.582,
      "step": 12414
    },
    {
      "epoch": 0.38137806039381933,
      "grad_norm": 0.35190266370773315,
      "learning_rate": 1.8280881204301848e-05,
      "loss": 0.5082,
      "step": 12415
    },
    {
      "epoch": 0.38140877952876845,
      "grad_norm": 0.4026683270931244,
      "learning_rate": 1.8280610270346144e-05,
      "loss": 0.5873,
      "step": 12416
    },
    {
      "epoch": 0.3814394986637176,
      "grad_norm": 0.3289724588394165,
      "learning_rate": 1.8280339317050492e-05,
      "loss": 0.4993,
      "step": 12417
    },
    {
      "epoch": 0.3814702177986668,
      "grad_norm": 0.3902246654033661,
      "learning_rate": 1.8280068344415533e-05,
      "loss": 0.5838,
      "step": 12418
    },
    {
      "epoch": 0.381500936933616,
      "grad_norm": 0.3594312071800232,
      "learning_rate": 1.8279797352441898e-05,
      "loss": 0.6356,
      "step": 12419
    },
    {
      "epoch": 0.3815316560685651,
      "grad_norm": 0.33250874280929565,
      "learning_rate": 1.8279526341130215e-05,
      "loss": 0.5111,
      "step": 12420
    },
    {
      "epoch": 0.38156237520351427,
      "grad_norm": 0.31848347187042236,
      "learning_rate": 1.827925531048112e-05,
      "loss": 0.548,
      "step": 12421
    },
    {
      "epoch": 0.38159309433846345,
      "grad_norm": 0.49604910612106323,
      "learning_rate": 1.8278984260495247e-05,
      "loss": 0.632,
      "step": 12422
    },
    {
      "epoch": 0.38162381347341257,
      "grad_norm": 0.33975714445114136,
      "learning_rate": 1.8278713191173226e-05,
      "loss": 0.6094,
      "step": 12423
    },
    {
      "epoch": 0.38165453260836174,
      "grad_norm": 0.3154648542404175,
      "learning_rate": 1.8278442102515696e-05,
      "loss": 0.5726,
      "step": 12424
    },
    {
      "epoch": 0.3816852517433109,
      "grad_norm": 0.41615650057792664,
      "learning_rate": 1.8278170994523283e-05,
      "loss": 0.6467,
      "step": 12425
    },
    {
      "epoch": 0.3817159708782601,
      "grad_norm": 0.3693624436855316,
      "learning_rate": 1.8277899867196625e-05,
      "loss": 0.5881,
      "step": 12426
    },
    {
      "epoch": 0.3817466900132092,
      "grad_norm": 0.3295789361000061,
      "learning_rate": 1.8277628720536355e-05,
      "loss": 0.5597,
      "step": 12427
    },
    {
      "epoch": 0.3817774091481584,
      "grad_norm": 0.3298072814941406,
      "learning_rate": 1.82773575545431e-05,
      "loss": 0.5785,
      "step": 12428
    },
    {
      "epoch": 0.38180812828310756,
      "grad_norm": 0.3639981746673584,
      "learning_rate": 1.82770863692175e-05,
      "loss": 0.596,
      "step": 12429
    },
    {
      "epoch": 0.3818388474180567,
      "grad_norm": 0.3479153513908386,
      "learning_rate": 1.827681516456019e-05,
      "loss": 0.5113,
      "step": 12430
    },
    {
      "epoch": 0.38186956655300586,
      "grad_norm": 0.3758121132850647,
      "learning_rate": 1.82765439405718e-05,
      "loss": 0.557,
      "step": 12431
    },
    {
      "epoch": 0.38190028568795503,
      "grad_norm": 0.38112229108810425,
      "learning_rate": 1.827627269725296e-05,
      "loss": 0.6299,
      "step": 12432
    },
    {
      "epoch": 0.3819310048229042,
      "grad_norm": 0.37707117199897766,
      "learning_rate": 1.827600143460431e-05,
      "loss": 0.5969,
      "step": 12433
    },
    {
      "epoch": 0.3819617239578533,
      "grad_norm": 0.40666666626930237,
      "learning_rate": 1.8275730152626485e-05,
      "loss": 0.4996,
      "step": 12434
    },
    {
      "epoch": 0.3819924430928025,
      "grad_norm": 0.3341124653816223,
      "learning_rate": 1.8275458851320106e-05,
      "loss": 0.592,
      "step": 12435
    },
    {
      "epoch": 0.3820231622277517,
      "grad_norm": 0.35151275992393494,
      "learning_rate": 1.8275187530685818e-05,
      "loss": 0.5838,
      "step": 12436
    },
    {
      "epoch": 0.38205388136270085,
      "grad_norm": 0.3511669933795929,
      "learning_rate": 1.827491619072425e-05,
      "loss": 0.5396,
      "step": 12437
    },
    {
      "epoch": 0.38208460049765,
      "grad_norm": 0.42465558648109436,
      "learning_rate": 1.827464483143604e-05,
      "loss": 0.6208,
      "step": 12438
    },
    {
      "epoch": 0.38211531963259915,
      "grad_norm": 0.3420940935611725,
      "learning_rate": 1.827437345282182e-05,
      "loss": 0.5498,
      "step": 12439
    },
    {
      "epoch": 0.3821460387675483,
      "grad_norm": 0.3813416659832001,
      "learning_rate": 1.827410205488222e-05,
      "loss": 0.5688,
      "step": 12440
    },
    {
      "epoch": 0.38217675790249744,
      "grad_norm": 0.3514685332775116,
      "learning_rate": 1.8273830637617878e-05,
      "loss": 0.5483,
      "step": 12441
    },
    {
      "epoch": 0.3822074770374466,
      "grad_norm": 0.36479029059410095,
      "learning_rate": 1.8273559201029428e-05,
      "loss": 0.5737,
      "step": 12442
    },
    {
      "epoch": 0.3822381961723958,
      "grad_norm": 0.3082675635814667,
      "learning_rate": 1.82732877451175e-05,
      "loss": 0.5001,
      "step": 12443
    },
    {
      "epoch": 0.38226891530734497,
      "grad_norm": 0.6483739614486694,
      "learning_rate": 1.8273016269882732e-05,
      "loss": 0.6368,
      "step": 12444
    },
    {
      "epoch": 0.3822996344422941,
      "grad_norm": 0.3641391098499298,
      "learning_rate": 1.8272744775325756e-05,
      "loss": 0.6137,
      "step": 12445
    },
    {
      "epoch": 0.38233035357724326,
      "grad_norm": 0.3451610803604126,
      "learning_rate": 1.8272473261447207e-05,
      "loss": 0.5424,
      "step": 12446
    },
    {
      "epoch": 0.38236107271219244,
      "grad_norm": 0.3365713059902191,
      "learning_rate": 1.827220172824772e-05,
      "loss": 0.5607,
      "step": 12447
    },
    {
      "epoch": 0.38239179184714156,
      "grad_norm": 0.3374975323677063,
      "learning_rate": 1.827193017572793e-05,
      "loss": 0.6426,
      "step": 12448
    },
    {
      "epoch": 0.38242251098209074,
      "grad_norm": 0.38479918241500854,
      "learning_rate": 1.8271658603888465e-05,
      "loss": 0.5797,
      "step": 12449
    },
    {
      "epoch": 0.3824532301170399,
      "grad_norm": 0.33594679832458496,
      "learning_rate": 1.8271387012729967e-05,
      "loss": 0.5914,
      "step": 12450
    },
    {
      "epoch": 0.3824839492519891,
      "grad_norm": 0.3578900396823883,
      "learning_rate": 1.8271115402253063e-05,
      "loss": 0.6092,
      "step": 12451
    },
    {
      "epoch": 0.3825146683869382,
      "grad_norm": 0.38242432475090027,
      "learning_rate": 1.8270843772458397e-05,
      "loss": 0.5227,
      "step": 12452
    },
    {
      "epoch": 0.3825453875218874,
      "grad_norm": 0.3277205526828766,
      "learning_rate": 1.8270572123346592e-05,
      "loss": 0.6124,
      "step": 12453
    },
    {
      "epoch": 0.38257610665683656,
      "grad_norm": 0.35765892267227173,
      "learning_rate": 1.8270300454918293e-05,
      "loss": 0.6041,
      "step": 12454
    },
    {
      "epoch": 0.3826068257917857,
      "grad_norm": 0.37759754061698914,
      "learning_rate": 1.8270028767174125e-05,
      "loss": 0.5749,
      "step": 12455
    },
    {
      "epoch": 0.38263754492673485,
      "grad_norm": 0.39725714921951294,
      "learning_rate": 1.826975706011473e-05,
      "loss": 0.6548,
      "step": 12456
    },
    {
      "epoch": 0.382668264061684,
      "grad_norm": 0.33941659331321716,
      "learning_rate": 1.8269485333740743e-05,
      "loss": 0.5315,
      "step": 12457
    },
    {
      "epoch": 0.3826989831966332,
      "grad_norm": 0.3304234743118286,
      "learning_rate": 1.826921358805279e-05,
      "loss": 0.5332,
      "step": 12458
    },
    {
      "epoch": 0.3827297023315823,
      "grad_norm": 0.36464959383010864,
      "learning_rate": 1.8268941823051513e-05,
      "loss": 0.5335,
      "step": 12459
    },
    {
      "epoch": 0.3827604214665315,
      "grad_norm": 0.37228673696517944,
      "learning_rate": 1.8268670038737542e-05,
      "loss": 0.559,
      "step": 12460
    },
    {
      "epoch": 0.3827911406014807,
      "grad_norm": 0.366207480430603,
      "learning_rate": 1.826839823511152e-05,
      "loss": 0.612,
      "step": 12461
    },
    {
      "epoch": 0.38282185973642985,
      "grad_norm": 1.8842573165893555,
      "learning_rate": 1.8268126412174076e-05,
      "loss": 0.5912,
      "step": 12462
    },
    {
      "epoch": 0.38285257887137897,
      "grad_norm": 0.34351053833961487,
      "learning_rate": 1.8267854569925843e-05,
      "loss": 0.6122,
      "step": 12463
    },
    {
      "epoch": 0.38288329800632814,
      "grad_norm": 0.35536447167396545,
      "learning_rate": 1.826758270836746e-05,
      "loss": 0.5453,
      "step": 12464
    },
    {
      "epoch": 0.3829140171412773,
      "grad_norm": 0.34506046772003174,
      "learning_rate": 1.8267310827499555e-05,
      "loss": 0.5737,
      "step": 12465
    },
    {
      "epoch": 0.38294473627622644,
      "grad_norm": 0.37127652764320374,
      "learning_rate": 1.8267038927322774e-05,
      "loss": 0.5221,
      "step": 12466
    },
    {
      "epoch": 0.3829754554111756,
      "grad_norm": 0.40456151962280273,
      "learning_rate": 1.8266767007837744e-05,
      "loss": 0.534,
      "step": 12467
    },
    {
      "epoch": 0.3830061745461248,
      "grad_norm": 0.34588170051574707,
      "learning_rate": 1.8266495069045103e-05,
      "loss": 0.5955,
      "step": 12468
    },
    {
      "epoch": 0.38303689368107396,
      "grad_norm": 0.3151595890522003,
      "learning_rate": 1.8266223110945484e-05,
      "loss": 0.5168,
      "step": 12469
    },
    {
      "epoch": 0.3830676128160231,
      "grad_norm": 0.3256661593914032,
      "learning_rate": 1.8265951133539525e-05,
      "loss": 0.5534,
      "step": 12470
    },
    {
      "epoch": 0.38309833195097226,
      "grad_norm": 0.328845739364624,
      "learning_rate": 1.826567913682786e-05,
      "loss": 0.545,
      "step": 12471
    },
    {
      "epoch": 0.38312905108592143,
      "grad_norm": 0.3939554691314697,
      "learning_rate": 1.8265407120811126e-05,
      "loss": 0.6589,
      "step": 12472
    },
    {
      "epoch": 0.38315977022087055,
      "grad_norm": 0.36683887243270874,
      "learning_rate": 1.8265135085489953e-05,
      "loss": 0.5687,
      "step": 12473
    },
    {
      "epoch": 0.38319048935581973,
      "grad_norm": 0.3698396384716034,
      "learning_rate": 1.826486303086498e-05,
      "loss": 0.5398,
      "step": 12474
    },
    {
      "epoch": 0.3832212084907689,
      "grad_norm": 0.42733725905418396,
      "learning_rate": 1.826459095693684e-05,
      "loss": 0.6386,
      "step": 12475
    },
    {
      "epoch": 0.3832519276257181,
      "grad_norm": 0.3789157569408417,
      "learning_rate": 1.8264318863706177e-05,
      "loss": 0.5649,
      "step": 12476
    },
    {
      "epoch": 0.3832826467606672,
      "grad_norm": 0.3699917197227478,
      "learning_rate": 1.8264046751173618e-05,
      "loss": 0.5957,
      "step": 12477
    },
    {
      "epoch": 0.3833133658956164,
      "grad_norm": 0.37079936265945435,
      "learning_rate": 1.8263774619339796e-05,
      "loss": 0.6074,
      "step": 12478
    },
    {
      "epoch": 0.38334408503056555,
      "grad_norm": 0.36780497431755066,
      "learning_rate": 1.8263502468205357e-05,
      "loss": 0.5369,
      "step": 12479
    },
    {
      "epoch": 0.3833748041655147,
      "grad_norm": 0.35342663526535034,
      "learning_rate": 1.826323029777093e-05,
      "loss": 0.6175,
      "step": 12480
    },
    {
      "epoch": 0.38340552330046385,
      "grad_norm": 0.7856476306915283,
      "learning_rate": 1.8262958108037148e-05,
      "loss": 0.6333,
      "step": 12481
    },
    {
      "epoch": 0.383436242435413,
      "grad_norm": 0.381039023399353,
      "learning_rate": 1.8262685899004652e-05,
      "loss": 0.6376,
      "step": 12482
    },
    {
      "epoch": 0.3834669615703622,
      "grad_norm": 0.3668991029262543,
      "learning_rate": 1.8262413670674076e-05,
      "loss": 0.5678,
      "step": 12483
    },
    {
      "epoch": 0.3834976807053113,
      "grad_norm": 0.3295508623123169,
      "learning_rate": 1.8262141423046057e-05,
      "loss": 0.6732,
      "step": 12484
    },
    {
      "epoch": 0.3835283998402605,
      "grad_norm": 0.3315221667289734,
      "learning_rate": 1.826186915612123e-05,
      "loss": 0.6211,
      "step": 12485
    },
    {
      "epoch": 0.38355911897520967,
      "grad_norm": 0.3829135298728943,
      "learning_rate": 1.826159686990023e-05,
      "loss": 0.7124,
      "step": 12486
    },
    {
      "epoch": 0.38358983811015884,
      "grad_norm": 0.34257301688194275,
      "learning_rate": 1.826132456438369e-05,
      "loss": 0.5864,
      "step": 12487
    },
    {
      "epoch": 0.38362055724510796,
      "grad_norm": 0.34599801898002625,
      "learning_rate": 1.8261052239572253e-05,
      "loss": 0.5316,
      "step": 12488
    },
    {
      "epoch": 0.38365127638005714,
      "grad_norm": 0.3911677300930023,
      "learning_rate": 1.826077989546655e-05,
      "loss": 0.6485,
      "step": 12489
    },
    {
      "epoch": 0.3836819955150063,
      "grad_norm": 0.4145345985889435,
      "learning_rate": 1.8260507532067224e-05,
      "loss": 0.569,
      "step": 12490
    },
    {
      "epoch": 0.38371271464995543,
      "grad_norm": 0.3638071119785309,
      "learning_rate": 1.8260235149374898e-05,
      "loss": 0.6113,
      "step": 12491
    },
    {
      "epoch": 0.3837434337849046,
      "grad_norm": 0.3615020215511322,
      "learning_rate": 1.825996274739022e-05,
      "loss": 0.5831,
      "step": 12492
    },
    {
      "epoch": 0.3837741529198538,
      "grad_norm": 0.37993040680885315,
      "learning_rate": 1.8259690326113824e-05,
      "loss": 0.5772,
      "step": 12493
    },
    {
      "epoch": 0.38380487205480296,
      "grad_norm": 0.3406311869621277,
      "learning_rate": 1.825941788554634e-05,
      "loss": 0.5729,
      "step": 12494
    },
    {
      "epoch": 0.3838355911897521,
      "grad_norm": 0.32828986644744873,
      "learning_rate": 1.825914542568841e-05,
      "loss": 0.5849,
      "step": 12495
    },
    {
      "epoch": 0.38386631032470125,
      "grad_norm": 0.33082377910614014,
      "learning_rate": 1.825887294654067e-05,
      "loss": 0.6066,
      "step": 12496
    },
    {
      "epoch": 0.38389702945965043,
      "grad_norm": 0.35999399423599243,
      "learning_rate": 1.8258600448103755e-05,
      "loss": 0.6451,
      "step": 12497
    },
    {
      "epoch": 0.38392774859459955,
      "grad_norm": 0.34958627820014954,
      "learning_rate": 1.82583279303783e-05,
      "loss": 0.5788,
      "step": 12498
    },
    {
      "epoch": 0.3839584677295487,
      "grad_norm": 0.33796072006225586,
      "learning_rate": 1.8258055393364948e-05,
      "loss": 0.6101,
      "step": 12499
    },
    {
      "epoch": 0.3839891868644979,
      "grad_norm": 0.35148563981056213,
      "learning_rate": 1.825778283706433e-05,
      "loss": 0.6054,
      "step": 12500
    },
    {
      "epoch": 0.3840199059994471,
      "grad_norm": 0.3636520206928253,
      "learning_rate": 1.8257510261477082e-05,
      "loss": 0.6673,
      "step": 12501
    },
    {
      "epoch": 0.3840506251343962,
      "grad_norm": 0.3795004189014435,
      "learning_rate": 1.8257237666603837e-05,
      "loss": 0.5938,
      "step": 12502
    },
    {
      "epoch": 0.38408134426934537,
      "grad_norm": 0.36040982604026794,
      "learning_rate": 1.8256965052445243e-05,
      "loss": 0.6078,
      "step": 12503
    },
    {
      "epoch": 0.38411206340429455,
      "grad_norm": 0.3564394414424896,
      "learning_rate": 1.825669241900193e-05,
      "loss": 0.5765,
      "step": 12504
    },
    {
      "epoch": 0.3841427825392437,
      "grad_norm": 0.350304514169693,
      "learning_rate": 1.8256419766274535e-05,
      "loss": 0.5475,
      "step": 12505
    },
    {
      "epoch": 0.38417350167419284,
      "grad_norm": 0.3423313796520233,
      "learning_rate": 1.8256147094263693e-05,
      "loss": 0.5995,
      "step": 12506
    },
    {
      "epoch": 0.384204220809142,
      "grad_norm": 0.35372355580329895,
      "learning_rate": 1.8255874402970044e-05,
      "loss": 0.608,
      "step": 12507
    },
    {
      "epoch": 0.3842349399440912,
      "grad_norm": 0.35223588347435,
      "learning_rate": 1.8255601692394226e-05,
      "loss": 0.643,
      "step": 12508
    },
    {
      "epoch": 0.3842656590790403,
      "grad_norm": 0.3667507469654083,
      "learning_rate": 1.8255328962536868e-05,
      "loss": 0.5396,
      "step": 12509
    },
    {
      "epoch": 0.3842963782139895,
      "grad_norm": 0.32116207480430603,
      "learning_rate": 1.8255056213398615e-05,
      "loss": 0.6022,
      "step": 12510
    },
    {
      "epoch": 0.38432709734893866,
      "grad_norm": 0.34404775500297546,
      "learning_rate": 1.8254783444980106e-05,
      "loss": 0.5023,
      "step": 12511
    },
    {
      "epoch": 0.38435781648388784,
      "grad_norm": 0.3752647638320923,
      "learning_rate": 1.8254510657281968e-05,
      "loss": 0.6055,
      "step": 12512
    },
    {
      "epoch": 0.38438853561883696,
      "grad_norm": 0.36894550919532776,
      "learning_rate": 1.825423785030485e-05,
      "loss": 0.6737,
      "step": 12513
    },
    {
      "epoch": 0.38441925475378613,
      "grad_norm": 0.5027132034301758,
      "learning_rate": 1.825396502404938e-05,
      "loss": 0.5753,
      "step": 12514
    },
    {
      "epoch": 0.3844499738887353,
      "grad_norm": 0.38310930132865906,
      "learning_rate": 1.8253692178516194e-05,
      "loss": 0.5908,
      "step": 12515
    },
    {
      "epoch": 0.38448069302368443,
      "grad_norm": 0.4100963771343231,
      "learning_rate": 1.825341931370594e-05,
      "loss": 0.5544,
      "step": 12516
    },
    {
      "epoch": 0.3845114121586336,
      "grad_norm": 0.48629865050315857,
      "learning_rate": 1.8253146429619243e-05,
      "loss": 0.5398,
      "step": 12517
    },
    {
      "epoch": 0.3845421312935828,
      "grad_norm": 0.3458899259567261,
      "learning_rate": 1.825287352625675e-05,
      "loss": 0.602,
      "step": 12518
    },
    {
      "epoch": 0.38457285042853195,
      "grad_norm": 0.3250167667865753,
      "learning_rate": 1.8252600603619096e-05,
      "loss": 0.6394,
      "step": 12519
    },
    {
      "epoch": 0.3846035695634811,
      "grad_norm": 0.3800830841064453,
      "learning_rate": 1.825232766170691e-05,
      "loss": 0.6271,
      "step": 12520
    },
    {
      "epoch": 0.38463428869843025,
      "grad_norm": 0.29448482394218445,
      "learning_rate": 1.8252054700520844e-05,
      "loss": 0.4642,
      "step": 12521
    },
    {
      "epoch": 0.3846650078333794,
      "grad_norm": 0.3643339276313782,
      "learning_rate": 1.8251781720061524e-05,
      "loss": 0.5223,
      "step": 12522
    },
    {
      "epoch": 0.3846957269683286,
      "grad_norm": 0.3806588351726532,
      "learning_rate": 1.8251508720329593e-05,
      "loss": 0.5914,
      "step": 12523
    },
    {
      "epoch": 0.3847264461032777,
      "grad_norm": 0.35798561573028564,
      "learning_rate": 1.8251235701325687e-05,
      "loss": 0.5536,
      "step": 12524
    },
    {
      "epoch": 0.3847571652382269,
      "grad_norm": 0.352384477853775,
      "learning_rate": 1.8250962663050443e-05,
      "loss": 0.507,
      "step": 12525
    },
    {
      "epoch": 0.38478788437317607,
      "grad_norm": 0.34223881363868713,
      "learning_rate": 1.82506896055045e-05,
      "loss": 0.5982,
      "step": 12526
    },
    {
      "epoch": 0.3848186035081252,
      "grad_norm": 0.35657501220703125,
      "learning_rate": 1.8250416528688493e-05,
      "loss": 0.4805,
      "step": 12527
    },
    {
      "epoch": 0.38484932264307437,
      "grad_norm": 0.3812239468097687,
      "learning_rate": 1.8250143432603065e-05,
      "loss": 0.5144,
      "step": 12528
    },
    {
      "epoch": 0.38488004177802354,
      "grad_norm": 0.4678243100643158,
      "learning_rate": 1.824987031724885e-05,
      "loss": 0.5898,
      "step": 12529
    },
    {
      "epoch": 0.3849107609129727,
      "grad_norm": 0.3616114556789398,
      "learning_rate": 1.8249597182626487e-05,
      "loss": 0.5854,
      "step": 12530
    },
    {
      "epoch": 0.38494148004792184,
      "grad_norm": 0.37845513224601746,
      "learning_rate": 1.8249324028736613e-05,
      "loss": 0.6666,
      "step": 12531
    },
    {
      "epoch": 0.384972199182871,
      "grad_norm": 0.34575942158699036,
      "learning_rate": 1.8249050855579867e-05,
      "loss": 0.5913,
      "step": 12532
    },
    {
      "epoch": 0.3850029183178202,
      "grad_norm": 0.3278485834598541,
      "learning_rate": 1.8248777663156888e-05,
      "loss": 0.6036,
      "step": 12533
    },
    {
      "epoch": 0.3850336374527693,
      "grad_norm": 0.3435664772987366,
      "learning_rate": 1.824850445146831e-05,
      "loss": 0.5456,
      "step": 12534
    },
    {
      "epoch": 0.3850643565877185,
      "grad_norm": 0.3955530822277069,
      "learning_rate": 1.8248231220514773e-05,
      "loss": 0.6106,
      "step": 12535
    },
    {
      "epoch": 0.38509507572266766,
      "grad_norm": 0.3794417679309845,
      "learning_rate": 1.824795797029692e-05,
      "loss": 0.5403,
      "step": 12536
    },
    {
      "epoch": 0.38512579485761683,
      "grad_norm": 0.38597509264945984,
      "learning_rate": 1.824768470081538e-05,
      "loss": 0.5876,
      "step": 12537
    },
    {
      "epoch": 0.38515651399256595,
      "grad_norm": 0.3223658502101898,
      "learning_rate": 1.82474114120708e-05,
      "loss": 0.4958,
      "step": 12538
    },
    {
      "epoch": 0.3851872331275151,
      "grad_norm": 0.320223867893219,
      "learning_rate": 1.8247138104063812e-05,
      "loss": 0.5557,
      "step": 12539
    },
    {
      "epoch": 0.3852179522624643,
      "grad_norm": 0.36716386675834656,
      "learning_rate": 1.8246864776795062e-05,
      "loss": 0.6315,
      "step": 12540
    },
    {
      "epoch": 0.3852486713974134,
      "grad_norm": 0.3415415585041046,
      "learning_rate": 1.824659143026518e-05,
      "loss": 0.533,
      "step": 12541
    },
    {
      "epoch": 0.3852793905323626,
      "grad_norm": 0.3268398940563202,
      "learning_rate": 1.8246318064474807e-05,
      "loss": 0.5729,
      "step": 12542
    },
    {
      "epoch": 0.3853101096673118,
      "grad_norm": 0.32457059621810913,
      "learning_rate": 1.8246044679424583e-05,
      "loss": 0.586,
      "step": 12543
    },
    {
      "epoch": 0.38534082880226095,
      "grad_norm": 0.37338271737098694,
      "learning_rate": 1.8245771275115147e-05,
      "loss": 0.6591,
      "step": 12544
    },
    {
      "epoch": 0.38537154793721007,
      "grad_norm": 0.3164200186729431,
      "learning_rate": 1.8245497851547137e-05,
      "loss": 0.5579,
      "step": 12545
    },
    {
      "epoch": 0.38540226707215924,
      "grad_norm": 0.3411218822002411,
      "learning_rate": 1.8245224408721188e-05,
      "loss": 0.5335,
      "step": 12546
    },
    {
      "epoch": 0.3854329862071084,
      "grad_norm": 0.3222665786743164,
      "learning_rate": 1.8244950946637942e-05,
      "loss": 0.6107,
      "step": 12547
    },
    {
      "epoch": 0.3854637053420576,
      "grad_norm": 0.37485384941101074,
      "learning_rate": 1.8244677465298036e-05,
      "loss": 0.5286,
      "step": 12548
    },
    {
      "epoch": 0.3854944244770067,
      "grad_norm": 0.41882604360580444,
      "learning_rate": 1.8244403964702116e-05,
      "loss": 0.5547,
      "step": 12549
    },
    {
      "epoch": 0.3855251436119559,
      "grad_norm": 0.3479151129722595,
      "learning_rate": 1.824413044485081e-05,
      "loss": 0.6554,
      "step": 12550
    },
    {
      "epoch": 0.38555586274690506,
      "grad_norm": 0.31809598207473755,
      "learning_rate": 1.824385690574476e-05,
      "loss": 0.5974,
      "step": 12551
    },
    {
      "epoch": 0.3855865818818542,
      "grad_norm": 0.3832273483276367,
      "learning_rate": 1.824358334738461e-05,
      "loss": 0.5875,
      "step": 12552
    },
    {
      "epoch": 0.38561730101680336,
      "grad_norm": 0.354560524225235,
      "learning_rate": 1.8243309769770993e-05,
      "loss": 0.519,
      "step": 12553
    },
    {
      "epoch": 0.38564802015175254,
      "grad_norm": 0.31683942675590515,
      "learning_rate": 1.8243036172904554e-05,
      "loss": 0.5443,
      "step": 12554
    },
    {
      "epoch": 0.3856787392867017,
      "grad_norm": 0.3471749722957611,
      "learning_rate": 1.8242762556785924e-05,
      "loss": 0.6028,
      "step": 12555
    },
    {
      "epoch": 0.38570945842165083,
      "grad_norm": 0.3327770531177521,
      "learning_rate": 1.824248892141575e-05,
      "loss": 0.5966,
      "step": 12556
    },
    {
      "epoch": 0.3857401775566,
      "grad_norm": 0.44045311212539673,
      "learning_rate": 1.8242215266794664e-05,
      "loss": 0.5093,
      "step": 12557
    },
    {
      "epoch": 0.3857708966915492,
      "grad_norm": 0.37221333384513855,
      "learning_rate": 1.8241941592923308e-05,
      "loss": 0.5908,
      "step": 12558
    },
    {
      "epoch": 0.3858016158264983,
      "grad_norm": 1.5145132541656494,
      "learning_rate": 1.8241667899802326e-05,
      "loss": 0.5676,
      "step": 12559
    },
    {
      "epoch": 0.3858323349614475,
      "grad_norm": 0.34485527873039246,
      "learning_rate": 1.824139418743235e-05,
      "loss": 0.5665,
      "step": 12560
    },
    {
      "epoch": 0.38586305409639665,
      "grad_norm": 0.3353272080421448,
      "learning_rate": 1.8241120455814025e-05,
      "loss": 0.587,
      "step": 12561
    },
    {
      "epoch": 0.3858937732313458,
      "grad_norm": 0.34558624029159546,
      "learning_rate": 1.8240846704947984e-05,
      "loss": 0.6153,
      "step": 12562
    },
    {
      "epoch": 0.38592449236629495,
      "grad_norm": 0.31225183606147766,
      "learning_rate": 1.824057293483487e-05,
      "loss": 0.5887,
      "step": 12563
    },
    {
      "epoch": 0.3859552115012441,
      "grad_norm": 0.35261857509613037,
      "learning_rate": 1.824029914547533e-05,
      "loss": 0.5642,
      "step": 12564
    },
    {
      "epoch": 0.3859859306361933,
      "grad_norm": 0.32524487376213074,
      "learning_rate": 1.8240025336869987e-05,
      "loss": 0.5713,
      "step": 12565
    },
    {
      "epoch": 0.3860166497711424,
      "grad_norm": 0.4254744350910187,
      "learning_rate": 1.8239751509019493e-05,
      "loss": 0.6143,
      "step": 12566
    },
    {
      "epoch": 0.3860473689060916,
      "grad_norm": 0.3446838855743408,
      "learning_rate": 1.8239477661924485e-05,
      "loss": 0.62,
      "step": 12567
    },
    {
      "epoch": 0.38607808804104077,
      "grad_norm": 0.3490721881389618,
      "learning_rate": 1.82392037955856e-05,
      "loss": 0.6338,
      "step": 12568
    },
    {
      "epoch": 0.38610880717598994,
      "grad_norm": 0.3527669608592987,
      "learning_rate": 1.823892991000348e-05,
      "loss": 0.5526,
      "step": 12569
    },
    {
      "epoch": 0.38613952631093906,
      "grad_norm": 0.3690575063228607,
      "learning_rate": 1.823865600517876e-05,
      "loss": 0.6621,
      "step": 12570
    },
    {
      "epoch": 0.38617024544588824,
      "grad_norm": 0.34031978249549866,
      "learning_rate": 1.8238382081112087e-05,
      "loss": 0.5835,
      "step": 12571
    },
    {
      "epoch": 0.3862009645808374,
      "grad_norm": 0.336273193359375,
      "learning_rate": 1.8238108137804098e-05,
      "loss": 0.5697,
      "step": 12572
    },
    {
      "epoch": 0.3862316837157866,
      "grad_norm": 0.3537152409553528,
      "learning_rate": 1.823783417525543e-05,
      "loss": 0.6215,
      "step": 12573
    },
    {
      "epoch": 0.3862624028507357,
      "grad_norm": 0.31179773807525635,
      "learning_rate": 1.8237560193466727e-05,
      "loss": 0.5675,
      "step": 12574
    },
    {
      "epoch": 0.3862931219856849,
      "grad_norm": 0.3109518587589264,
      "learning_rate": 1.8237286192438626e-05,
      "loss": 0.6076,
      "step": 12575
    },
    {
      "epoch": 0.38632384112063406,
      "grad_norm": 0.3008643388748169,
      "learning_rate": 1.8237012172171767e-05,
      "loss": 0.5632,
      "step": 12576
    },
    {
      "epoch": 0.3863545602555832,
      "grad_norm": 0.43880778551101685,
      "learning_rate": 1.8236738132666788e-05,
      "loss": 0.5864,
      "step": 12577
    },
    {
      "epoch": 0.38638527939053235,
      "grad_norm": 0.35843607783317566,
      "learning_rate": 1.823646407392434e-05,
      "loss": 0.5756,
      "step": 12578
    },
    {
      "epoch": 0.38641599852548153,
      "grad_norm": 0.387682169675827,
      "learning_rate": 1.823618999594505e-05,
      "loss": 0.5441,
      "step": 12579
    },
    {
      "epoch": 0.3864467176604307,
      "grad_norm": 0.34428897500038147,
      "learning_rate": 1.823591589872956e-05,
      "loss": 0.6873,
      "step": 12580
    },
    {
      "epoch": 0.3864774367953798,
      "grad_norm": 0.3445190191268921,
      "learning_rate": 1.8235641782278516e-05,
      "loss": 0.6076,
      "step": 12581
    },
    {
      "epoch": 0.386508155930329,
      "grad_norm": 0.35933130979537964,
      "learning_rate": 1.8235367646592556e-05,
      "loss": 0.5999,
      "step": 12582
    },
    {
      "epoch": 0.3865388750652782,
      "grad_norm": 0.35630905628204346,
      "learning_rate": 1.823509349167232e-05,
      "loss": 0.6546,
      "step": 12583
    },
    {
      "epoch": 0.3865695942002273,
      "grad_norm": 0.327798455953598,
      "learning_rate": 1.8234819317518448e-05,
      "loss": 0.7173,
      "step": 12584
    },
    {
      "epoch": 0.38660031333517647,
      "grad_norm": 0.35514917969703674,
      "learning_rate": 1.823454512413158e-05,
      "loss": 0.6475,
      "step": 12585
    },
    {
      "epoch": 0.38663103247012565,
      "grad_norm": 0.481374591588974,
      "learning_rate": 1.823427091151236e-05,
      "loss": 0.52,
      "step": 12586
    },
    {
      "epoch": 0.3866617516050748,
      "grad_norm": 0.34858188033103943,
      "learning_rate": 1.823399667966142e-05,
      "loss": 0.5959,
      "step": 12587
    },
    {
      "epoch": 0.38669247074002394,
      "grad_norm": 0.35031187534332275,
      "learning_rate": 1.8233722428579404e-05,
      "loss": 0.5532,
      "step": 12588
    },
    {
      "epoch": 0.3867231898749731,
      "grad_norm": 0.3554961383342743,
      "learning_rate": 1.823344815826696e-05,
      "loss": 0.6438,
      "step": 12589
    },
    {
      "epoch": 0.3867539090099223,
      "grad_norm": 0.35448774695396423,
      "learning_rate": 1.823317386872472e-05,
      "loss": 0.5836,
      "step": 12590
    },
    {
      "epoch": 0.38678462814487147,
      "grad_norm": 0.3457255959510803,
      "learning_rate": 1.823289955995333e-05,
      "loss": 0.5888,
      "step": 12591
    },
    {
      "epoch": 0.3868153472798206,
      "grad_norm": 0.35012921690940857,
      "learning_rate": 1.8232625231953424e-05,
      "loss": 0.5594,
      "step": 12592
    },
    {
      "epoch": 0.38684606641476976,
      "grad_norm": 0.33400118350982666,
      "learning_rate": 1.823235088472565e-05,
      "loss": 0.5469,
      "step": 12593
    },
    {
      "epoch": 0.38687678554971894,
      "grad_norm": 0.38483765721321106,
      "learning_rate": 1.8232076518270647e-05,
      "loss": 0.5661,
      "step": 12594
    },
    {
      "epoch": 0.38690750468466806,
      "grad_norm": 0.3188033401966095,
      "learning_rate": 1.8231802132589048e-05,
      "loss": 0.4892,
      "step": 12595
    },
    {
      "epoch": 0.38693822381961723,
      "grad_norm": 0.3661021292209625,
      "learning_rate": 1.8231527727681503e-05,
      "loss": 0.5735,
      "step": 12596
    },
    {
      "epoch": 0.3869689429545664,
      "grad_norm": 0.332582026720047,
      "learning_rate": 1.8231253303548654e-05,
      "loss": 0.5923,
      "step": 12597
    },
    {
      "epoch": 0.3869996620895156,
      "grad_norm": 0.3867836594581604,
      "learning_rate": 1.8230978860191135e-05,
      "loss": 0.5717,
      "step": 12598
    },
    {
      "epoch": 0.3870303812244647,
      "grad_norm": 0.388803094625473,
      "learning_rate": 1.8230704397609587e-05,
      "loss": 0.5266,
      "step": 12599
    },
    {
      "epoch": 0.3870611003594139,
      "grad_norm": 0.39410752058029175,
      "learning_rate": 1.823042991580466e-05,
      "loss": 0.5644,
      "step": 12600
    },
    {
      "epoch": 0.38709181949436305,
      "grad_norm": 1.0480247735977173,
      "learning_rate": 1.8230155414776988e-05,
      "loss": 0.5318,
      "step": 12601
    },
    {
      "epoch": 0.3871225386293122,
      "grad_norm": 0.47047552466392517,
      "learning_rate": 1.822988089452721e-05,
      "loss": 0.6461,
      "step": 12602
    },
    {
      "epoch": 0.38715325776426135,
      "grad_norm": 0.4002799391746521,
      "learning_rate": 1.822960635505597e-05,
      "loss": 0.6364,
      "step": 12603
    },
    {
      "epoch": 0.3871839768992105,
      "grad_norm": 0.3314950466156006,
      "learning_rate": 1.822933179636391e-05,
      "loss": 0.5238,
      "step": 12604
    },
    {
      "epoch": 0.3872146960341597,
      "grad_norm": 0.3827502429485321,
      "learning_rate": 1.8229057218451675e-05,
      "loss": 0.6534,
      "step": 12605
    },
    {
      "epoch": 0.3872454151691088,
      "grad_norm": 0.330681174993515,
      "learning_rate": 1.8228782621319902e-05,
      "loss": 0.5655,
      "step": 12606
    },
    {
      "epoch": 0.387276134304058,
      "grad_norm": 0.3372170925140381,
      "learning_rate": 1.822850800496923e-05,
      "loss": 0.6349,
      "step": 12607
    },
    {
      "epoch": 0.38730685343900717,
      "grad_norm": 0.32247716188430786,
      "learning_rate": 1.82282333694003e-05,
      "loss": 0.4862,
      "step": 12608
    },
    {
      "epoch": 0.3873375725739563,
      "grad_norm": 0.35790520906448364,
      "learning_rate": 1.822795871461376e-05,
      "loss": 0.6222,
      "step": 12609
    },
    {
      "epoch": 0.38736829170890547,
      "grad_norm": 0.3275488615036011,
      "learning_rate": 1.8227684040610247e-05,
      "loss": 0.5709,
      "step": 12610
    },
    {
      "epoch": 0.38739901084385464,
      "grad_norm": 0.37938183546066284,
      "learning_rate": 1.8227409347390406e-05,
      "loss": 0.6276,
      "step": 12611
    },
    {
      "epoch": 0.3874297299788038,
      "grad_norm": 0.3475094735622406,
      "learning_rate": 1.8227134634954874e-05,
      "loss": 0.6084,
      "step": 12612
    },
    {
      "epoch": 0.38746044911375294,
      "grad_norm": 0.5625912547111511,
      "learning_rate": 1.822685990330429e-05,
      "loss": 0.5804,
      "step": 12613
    },
    {
      "epoch": 0.3874911682487021,
      "grad_norm": 0.3835003674030304,
      "learning_rate": 1.8226585152439308e-05,
      "loss": 0.5929,
      "step": 12614
    },
    {
      "epoch": 0.3875218873836513,
      "grad_norm": 0.3280009329319,
      "learning_rate": 1.8226310382360558e-05,
      "loss": 0.5503,
      "step": 12615
    },
    {
      "epoch": 0.38755260651860046,
      "grad_norm": 0.3386102318763733,
      "learning_rate": 1.8226035593068682e-05,
      "loss": 0.6189,
      "step": 12616
    },
    {
      "epoch": 0.3875833256535496,
      "grad_norm": 0.3466804325580597,
      "learning_rate": 1.8225760784564326e-05,
      "loss": 0.5311,
      "step": 12617
    },
    {
      "epoch": 0.38761404478849876,
      "grad_norm": 0.3681892454624176,
      "learning_rate": 1.822548595684814e-05,
      "loss": 0.5629,
      "step": 12618
    },
    {
      "epoch": 0.38764476392344793,
      "grad_norm": 0.3753035366535187,
      "learning_rate": 1.822521110992075e-05,
      "loss": 0.6091,
      "step": 12619
    },
    {
      "epoch": 0.38767548305839705,
      "grad_norm": 0.3478451073169708,
      "learning_rate": 1.8224936243782805e-05,
      "loss": 0.6083,
      "step": 12620
    },
    {
      "epoch": 0.3877062021933462,
      "grad_norm": 0.3551974594593048,
      "learning_rate": 1.8224661358434946e-05,
      "loss": 0.5753,
      "step": 12621
    },
    {
      "epoch": 0.3877369213282954,
      "grad_norm": 0.3498266637325287,
      "learning_rate": 1.822438645387782e-05,
      "loss": 0.5313,
      "step": 12622
    },
    {
      "epoch": 0.3877676404632446,
      "grad_norm": 0.3587892949581146,
      "learning_rate": 1.8224111530112064e-05,
      "loss": 0.59,
      "step": 12623
    },
    {
      "epoch": 0.3877983595981937,
      "grad_norm": 0.3525114357471466,
      "learning_rate": 1.8223836587138318e-05,
      "loss": 0.5994,
      "step": 12624
    },
    {
      "epoch": 0.3878290787331429,
      "grad_norm": 0.36976346373558044,
      "learning_rate": 1.8223561624957232e-05,
      "loss": 0.5768,
      "step": 12625
    },
    {
      "epoch": 0.38785979786809205,
      "grad_norm": 0.34399881958961487,
      "learning_rate": 1.822328664356944e-05,
      "loss": 0.5306,
      "step": 12626
    },
    {
      "epoch": 0.38789051700304117,
      "grad_norm": 0.3104521930217743,
      "learning_rate": 1.8223011642975587e-05,
      "loss": 0.5502,
      "step": 12627
    },
    {
      "epoch": 0.38792123613799034,
      "grad_norm": 0.4279651343822479,
      "learning_rate": 1.822273662317632e-05,
      "loss": 0.5645,
      "step": 12628
    },
    {
      "epoch": 0.3879519552729395,
      "grad_norm": 0.3398714065551758,
      "learning_rate": 1.8222461584172275e-05,
      "loss": 0.5795,
      "step": 12629
    },
    {
      "epoch": 0.3879826744078887,
      "grad_norm": 0.38412904739379883,
      "learning_rate": 1.8222186525964097e-05,
      "loss": 0.6275,
      "step": 12630
    },
    {
      "epoch": 0.3880133935428378,
      "grad_norm": 0.3591623902320862,
      "learning_rate": 1.822191144855243e-05,
      "loss": 0.6308,
      "step": 12631
    },
    {
      "epoch": 0.388044112677787,
      "grad_norm": 0.3525063395500183,
      "learning_rate": 1.822163635193791e-05,
      "loss": 0.5869,
      "step": 12632
    },
    {
      "epoch": 0.38807483181273617,
      "grad_norm": 0.33502039313316345,
      "learning_rate": 1.822136123612119e-05,
      "loss": 0.5427,
      "step": 12633
    },
    {
      "epoch": 0.38810555094768534,
      "grad_norm": 0.4441884756088257,
      "learning_rate": 1.8221086101102902e-05,
      "loss": 0.5386,
      "step": 12634
    },
    {
      "epoch": 0.38813627008263446,
      "grad_norm": 0.3710276484489441,
      "learning_rate": 1.8220810946883692e-05,
      "loss": 0.5722,
      "step": 12635
    },
    {
      "epoch": 0.38816698921758364,
      "grad_norm": 0.3922441899776459,
      "learning_rate": 1.8220535773464207e-05,
      "loss": 0.6631,
      "step": 12636
    },
    {
      "epoch": 0.3881977083525328,
      "grad_norm": 0.3683168590068817,
      "learning_rate": 1.8220260580845088e-05,
      "loss": 0.5638,
      "step": 12637
    },
    {
      "epoch": 0.38822842748748193,
      "grad_norm": 0.3635037839412689,
      "learning_rate": 1.8219985369026974e-05,
      "loss": 0.5169,
      "step": 12638
    },
    {
      "epoch": 0.3882591466224311,
      "grad_norm": 0.3238923251628876,
      "learning_rate": 1.821971013801051e-05,
      "loss": 0.5533,
      "step": 12639
    },
    {
      "epoch": 0.3882898657573803,
      "grad_norm": 0.3708910644054413,
      "learning_rate": 1.821943488779634e-05,
      "loss": 0.5889,
      "step": 12640
    },
    {
      "epoch": 0.38832058489232946,
      "grad_norm": 0.34931379556655884,
      "learning_rate": 1.8219159618385105e-05,
      "loss": 0.5781,
      "step": 12641
    },
    {
      "epoch": 0.3883513040272786,
      "grad_norm": 0.46294674277305603,
      "learning_rate": 1.8218884329777447e-05,
      "loss": 0.5903,
      "step": 12642
    },
    {
      "epoch": 0.38838202316222775,
      "grad_norm": 0.3967902958393097,
      "learning_rate": 1.8218609021974013e-05,
      "loss": 0.5951,
      "step": 12643
    },
    {
      "epoch": 0.3884127422971769,
      "grad_norm": 0.36157310009002686,
      "learning_rate": 1.8218333694975444e-05,
      "loss": 0.6217,
      "step": 12644
    },
    {
      "epoch": 0.38844346143212605,
      "grad_norm": 0.319477379322052,
      "learning_rate": 1.821805834878238e-05,
      "loss": 0.5267,
      "step": 12645
    },
    {
      "epoch": 0.3884741805670752,
      "grad_norm": 0.29840320348739624,
      "learning_rate": 1.821778298339547e-05,
      "loss": 0.4383,
      "step": 12646
    },
    {
      "epoch": 0.3885048997020244,
      "grad_norm": 0.33364129066467285,
      "learning_rate": 1.8217507598815355e-05,
      "loss": 0.5822,
      "step": 12647
    },
    {
      "epoch": 0.3885356188369736,
      "grad_norm": 0.43391337990760803,
      "learning_rate": 1.8217232195042675e-05,
      "loss": 0.5327,
      "step": 12648
    },
    {
      "epoch": 0.3885663379719227,
      "grad_norm": 0.34249475598335266,
      "learning_rate": 1.8216956772078075e-05,
      "loss": 0.6602,
      "step": 12649
    },
    {
      "epoch": 0.38859705710687187,
      "grad_norm": 0.3727380931377411,
      "learning_rate": 1.8216681329922195e-05,
      "loss": 0.5645,
      "step": 12650
    },
    {
      "epoch": 0.38862777624182104,
      "grad_norm": 0.31060948967933655,
      "learning_rate": 1.821640586857569e-05,
      "loss": 0.6005,
      "step": 12651
    },
    {
      "epoch": 0.38865849537677016,
      "grad_norm": 0.6430467367172241,
      "learning_rate": 1.821613038803919e-05,
      "loss": 0.5118,
      "step": 12652
    },
    {
      "epoch": 0.38868921451171934,
      "grad_norm": 0.3430403769016266,
      "learning_rate": 1.8215854888313342e-05,
      "loss": 0.6108,
      "step": 12653
    },
    {
      "epoch": 0.3887199336466685,
      "grad_norm": 0.36365172266960144,
      "learning_rate": 1.8215579369398795e-05,
      "loss": 0.6208,
      "step": 12654
    },
    {
      "epoch": 0.3887506527816177,
      "grad_norm": 0.3203742504119873,
      "learning_rate": 1.8215303831296186e-05,
      "loss": 0.5474,
      "step": 12655
    },
    {
      "epoch": 0.3887813719165668,
      "grad_norm": 0.38130345940589905,
      "learning_rate": 1.8215028274006164e-05,
      "loss": 0.5796,
      "step": 12656
    },
    {
      "epoch": 0.388812091051516,
      "grad_norm": 0.3599478006362915,
      "learning_rate": 1.8214752697529365e-05,
      "loss": 0.5189,
      "step": 12657
    },
    {
      "epoch": 0.38884281018646516,
      "grad_norm": 0.3450779616832733,
      "learning_rate": 1.8214477101866442e-05,
      "loss": 0.5428,
      "step": 12658
    },
    {
      "epoch": 0.38887352932141434,
      "grad_norm": 0.37221449613571167,
      "learning_rate": 1.8214201487018034e-05,
      "loss": 0.5446,
      "step": 12659
    },
    {
      "epoch": 0.38890424845636345,
      "grad_norm": 0.3363869786262512,
      "learning_rate": 1.821392585298478e-05,
      "loss": 0.53,
      "step": 12660
    },
    {
      "epoch": 0.38893496759131263,
      "grad_norm": 0.32831862568855286,
      "learning_rate": 1.8213650199767335e-05,
      "loss": 0.5952,
      "step": 12661
    },
    {
      "epoch": 0.3889656867262618,
      "grad_norm": 0.3702086806297302,
      "learning_rate": 1.821337452736633e-05,
      "loss": 0.5675,
      "step": 12662
    },
    {
      "epoch": 0.3889964058612109,
      "grad_norm": 0.3556568920612335,
      "learning_rate": 1.821309883578242e-05,
      "loss": 0.5848,
      "step": 12663
    },
    {
      "epoch": 0.3890271249961601,
      "grad_norm": 0.42274361848831177,
      "learning_rate": 1.8212823125016245e-05,
      "loss": 0.5553,
      "step": 12664
    },
    {
      "epoch": 0.3890578441311093,
      "grad_norm": 0.3151712715625763,
      "learning_rate": 1.821254739506844e-05,
      "loss": 0.5322,
      "step": 12665
    },
    {
      "epoch": 0.38908856326605845,
      "grad_norm": 0.3515087366104126,
      "learning_rate": 1.8212271645939664e-05,
      "loss": 0.5441,
      "step": 12666
    },
    {
      "epoch": 0.38911928240100757,
      "grad_norm": 0.37466102838516235,
      "learning_rate": 1.8211995877630553e-05,
      "loss": 0.4664,
      "step": 12667
    },
    {
      "epoch": 0.38915000153595675,
      "grad_norm": 0.280686616897583,
      "learning_rate": 1.821172009014175e-05,
      "loss": 0.4895,
      "step": 12668
    },
    {
      "epoch": 0.3891807206709059,
      "grad_norm": 0.35638198256492615,
      "learning_rate": 1.8211444283473904e-05,
      "loss": 0.6151,
      "step": 12669
    },
    {
      "epoch": 0.38921143980585504,
      "grad_norm": 0.3691403865814209,
      "learning_rate": 1.8211168457627658e-05,
      "loss": 0.6106,
      "step": 12670
    },
    {
      "epoch": 0.3892421589408042,
      "grad_norm": 0.3384265601634979,
      "learning_rate": 1.8210892612603647e-05,
      "loss": 0.6251,
      "step": 12671
    },
    {
      "epoch": 0.3892728780757534,
      "grad_norm": 0.33641737699508667,
      "learning_rate": 1.821061674840253e-05,
      "loss": 0.5209,
      "step": 12672
    },
    {
      "epoch": 0.38930359721070257,
      "grad_norm": 0.33943793177604675,
      "learning_rate": 1.8210340865024944e-05,
      "loss": 0.5374,
      "step": 12673
    },
    {
      "epoch": 0.3893343163456517,
      "grad_norm": 0.32559552788734436,
      "learning_rate": 1.821006496247153e-05,
      "loss": 0.5673,
      "step": 12674
    },
    {
      "epoch": 0.38936503548060086,
      "grad_norm": 0.3333324193954468,
      "learning_rate": 1.8209789040742935e-05,
      "loss": 0.6223,
      "step": 12675
    },
    {
      "epoch": 0.38939575461555004,
      "grad_norm": 0.3348560035228729,
      "learning_rate": 1.820951309983981e-05,
      "loss": 0.555,
      "step": 12676
    },
    {
      "epoch": 0.3894264737504992,
      "grad_norm": 0.3359452784061432,
      "learning_rate": 1.8209237139762787e-05,
      "loss": 0.5636,
      "step": 12677
    },
    {
      "epoch": 0.38945719288544833,
      "grad_norm": 0.3419310748577118,
      "learning_rate": 1.820896116051252e-05,
      "loss": 0.5992,
      "step": 12678
    },
    {
      "epoch": 0.3894879120203975,
      "grad_norm": 0.44843193888664246,
      "learning_rate": 1.8208685162089654e-05,
      "loss": 0.4806,
      "step": 12679
    },
    {
      "epoch": 0.3895186311553467,
      "grad_norm": 0.3336940407752991,
      "learning_rate": 1.8208409144494827e-05,
      "loss": 0.5459,
      "step": 12680
    },
    {
      "epoch": 0.3895493502902958,
      "grad_norm": 0.3577467203140259,
      "learning_rate": 1.8208133107728686e-05,
      "loss": 0.5985,
      "step": 12681
    },
    {
      "epoch": 0.389580069425245,
      "grad_norm": 0.36254003643989563,
      "learning_rate": 1.820785705179188e-05,
      "loss": 0.5833,
      "step": 12682
    },
    {
      "epoch": 0.38961078856019415,
      "grad_norm": 0.3472042679786682,
      "learning_rate": 1.8207580976685052e-05,
      "loss": 0.4822,
      "step": 12683
    },
    {
      "epoch": 0.38964150769514333,
      "grad_norm": 0.38242363929748535,
      "learning_rate": 1.8207304882408843e-05,
      "loss": 0.5576,
      "step": 12684
    },
    {
      "epoch": 0.38967222683009245,
      "grad_norm": 0.36178305745124817,
      "learning_rate": 1.8207028768963903e-05,
      "loss": 0.6008,
      "step": 12685
    },
    {
      "epoch": 0.3897029459650416,
      "grad_norm": 0.40467602014541626,
      "learning_rate": 1.8206752636350868e-05,
      "loss": 0.6016,
      "step": 12686
    },
    {
      "epoch": 0.3897336650999908,
      "grad_norm": 0.39130914211273193,
      "learning_rate": 1.8206476484570395e-05,
      "loss": 0.5561,
      "step": 12687
    },
    {
      "epoch": 0.3897643842349399,
      "grad_norm": 0.3460814356803894,
      "learning_rate": 1.820620031362312e-05,
      "loss": 0.5792,
      "step": 12688
    },
    {
      "epoch": 0.3897951033698891,
      "grad_norm": 0.4139222800731659,
      "learning_rate": 1.820592412350969e-05,
      "loss": 0.6563,
      "step": 12689
    },
    {
      "epoch": 0.38982582250483827,
      "grad_norm": 0.36775991320610046,
      "learning_rate": 1.8205647914230754e-05,
      "loss": 0.6707,
      "step": 12690
    },
    {
      "epoch": 0.38985654163978745,
      "grad_norm": 0.3293814957141876,
      "learning_rate": 1.820537168578695e-05,
      "loss": 0.5259,
      "step": 12691
    },
    {
      "epoch": 0.38988726077473657,
      "grad_norm": 0.31520891189575195,
      "learning_rate": 1.820509543817893e-05,
      "loss": 0.5712,
      "step": 12692
    },
    {
      "epoch": 0.38991797990968574,
      "grad_norm": 0.3852525055408478,
      "learning_rate": 1.820481917140734e-05,
      "loss": 0.5564,
      "step": 12693
    },
    {
      "epoch": 0.3899486990446349,
      "grad_norm": 0.3378998041152954,
      "learning_rate": 1.8204542885472817e-05,
      "loss": 0.639,
      "step": 12694
    },
    {
      "epoch": 0.38997941817958404,
      "grad_norm": 0.38546907901763916,
      "learning_rate": 1.8204266580376013e-05,
      "loss": 0.5849,
      "step": 12695
    },
    {
      "epoch": 0.3900101373145332,
      "grad_norm": 0.3532363176345825,
      "learning_rate": 1.8203990256117572e-05,
      "loss": 0.6712,
      "step": 12696
    },
    {
      "epoch": 0.3900408564494824,
      "grad_norm": 0.34957534074783325,
      "learning_rate": 1.820371391269814e-05,
      "loss": 0.561,
      "step": 12697
    },
    {
      "epoch": 0.39007157558443156,
      "grad_norm": 0.33232951164245605,
      "learning_rate": 1.820343755011836e-05,
      "loss": 0.5989,
      "step": 12698
    },
    {
      "epoch": 0.3901022947193807,
      "grad_norm": 0.37336111068725586,
      "learning_rate": 1.8203161168378876e-05,
      "loss": 0.5462,
      "step": 12699
    },
    {
      "epoch": 0.39013301385432986,
      "grad_norm": 0.3531326353549957,
      "learning_rate": 1.820288476748034e-05,
      "loss": 0.5156,
      "step": 12700
    },
    {
      "epoch": 0.39016373298927903,
      "grad_norm": 0.3059805929660797,
      "learning_rate": 1.820260834742339e-05,
      "loss": 0.5214,
      "step": 12701
    },
    {
      "epoch": 0.3901944521242282,
      "grad_norm": 0.5658020377159119,
      "learning_rate": 1.8202331908208677e-05,
      "loss": 0.5368,
      "step": 12702
    },
    {
      "epoch": 0.39022517125917733,
      "grad_norm": 0.310506135225296,
      "learning_rate": 1.8202055449836847e-05,
      "loss": 0.4948,
      "step": 12703
    },
    {
      "epoch": 0.3902558903941265,
      "grad_norm": 0.33393508195877075,
      "learning_rate": 1.820177897230854e-05,
      "loss": 0.5965,
      "step": 12704
    },
    {
      "epoch": 0.3902866095290757,
      "grad_norm": 0.3950824737548828,
      "learning_rate": 1.820150247562441e-05,
      "loss": 0.6352,
      "step": 12705
    },
    {
      "epoch": 0.3903173286640248,
      "grad_norm": 0.36537185311317444,
      "learning_rate": 1.8201225959785094e-05,
      "loss": 0.5616,
      "step": 12706
    },
    {
      "epoch": 0.390348047798974,
      "grad_norm": 0.41239434480667114,
      "learning_rate": 1.8200949424791243e-05,
      "loss": 0.5785,
      "step": 12707
    },
    {
      "epoch": 0.39037876693392315,
      "grad_norm": 0.32685980200767517,
      "learning_rate": 1.82006728706435e-05,
      "loss": 0.5821,
      "step": 12708
    },
    {
      "epoch": 0.3904094860688723,
      "grad_norm": 0.35476619005203247,
      "learning_rate": 1.8200396297342515e-05,
      "loss": 0.5998,
      "step": 12709
    },
    {
      "epoch": 0.39044020520382144,
      "grad_norm": 0.39550358057022095,
      "learning_rate": 1.8200119704888934e-05,
      "loss": 0.6401,
      "step": 12710
    },
    {
      "epoch": 0.3904709243387706,
      "grad_norm": 0.32102224230766296,
      "learning_rate": 1.81998430932834e-05,
      "loss": 0.4706,
      "step": 12711
    },
    {
      "epoch": 0.3905016434737198,
      "grad_norm": 0.35520726442337036,
      "learning_rate": 1.8199566462526557e-05,
      "loss": 0.5761,
      "step": 12712
    },
    {
      "epoch": 0.3905323626086689,
      "grad_norm": 0.3713115155696869,
      "learning_rate": 1.8199289812619053e-05,
      "loss": 0.5066,
      "step": 12713
    },
    {
      "epoch": 0.3905630817436181,
      "grad_norm": 0.3835351765155792,
      "learning_rate": 1.819901314356154e-05,
      "loss": 0.5583,
      "step": 12714
    },
    {
      "epoch": 0.39059380087856727,
      "grad_norm": 0.32299384474754333,
      "learning_rate": 1.8198736455354654e-05,
      "loss": 0.4925,
      "step": 12715
    },
    {
      "epoch": 0.39062452001351644,
      "grad_norm": 0.36355462670326233,
      "learning_rate": 1.8198459747999048e-05,
      "loss": 0.5966,
      "step": 12716
    },
    {
      "epoch": 0.39065523914846556,
      "grad_norm": 0.3784339427947998,
      "learning_rate": 1.8198183021495367e-05,
      "loss": 0.5937,
      "step": 12717
    },
    {
      "epoch": 0.39068595828341474,
      "grad_norm": 0.3324376940727234,
      "learning_rate": 1.8197906275844262e-05,
      "loss": 0.5457,
      "step": 12718
    },
    {
      "epoch": 0.3907166774183639,
      "grad_norm": 0.34337347745895386,
      "learning_rate": 1.8197629511046367e-05,
      "loss": 0.5747,
      "step": 12719
    },
    {
      "epoch": 0.39074739655331303,
      "grad_norm": 0.398963987827301,
      "learning_rate": 1.819735272710234e-05,
      "loss": 0.5742,
      "step": 12720
    },
    {
      "epoch": 0.3907781156882622,
      "grad_norm": 0.3766856789588928,
      "learning_rate": 1.819707592401282e-05,
      "loss": 0.6441,
      "step": 12721
    },
    {
      "epoch": 0.3908088348232114,
      "grad_norm": 0.3609825670719147,
      "learning_rate": 1.8196799101778458e-05,
      "loss": 0.5527,
      "step": 12722
    },
    {
      "epoch": 0.39083955395816056,
      "grad_norm": 0.37928688526153564,
      "learning_rate": 1.81965222603999e-05,
      "loss": 0.6831,
      "step": 12723
    },
    {
      "epoch": 0.3908702730931097,
      "grad_norm": 0.3854934871196747,
      "learning_rate": 1.8196245399877793e-05,
      "loss": 0.5154,
      "step": 12724
    },
    {
      "epoch": 0.39090099222805885,
      "grad_norm": 0.40799617767333984,
      "learning_rate": 1.8195968520212785e-05,
      "loss": 0.6198,
      "step": 12725
    },
    {
      "epoch": 0.390931711363008,
      "grad_norm": 0.3382120430469513,
      "learning_rate": 1.8195691621405513e-05,
      "loss": 0.4915,
      "step": 12726
    },
    {
      "epoch": 0.3909624304979572,
      "grad_norm": 0.3693837523460388,
      "learning_rate": 1.8195414703456635e-05,
      "loss": 0.5754,
      "step": 12727
    },
    {
      "epoch": 0.3909931496329063,
      "grad_norm": 0.4385649263858795,
      "learning_rate": 1.8195137766366794e-05,
      "loss": 0.4908,
      "step": 12728
    },
    {
      "epoch": 0.3910238687678555,
      "grad_norm": 0.3332604765892029,
      "learning_rate": 1.8194860810136634e-05,
      "loss": 0.5262,
      "step": 12729
    },
    {
      "epoch": 0.3910545879028047,
      "grad_norm": 0.3272441327571869,
      "learning_rate": 1.8194583834766803e-05,
      "loss": 0.501,
      "step": 12730
    },
    {
      "epoch": 0.3910853070377538,
      "grad_norm": 0.32544565200805664,
      "learning_rate": 1.8194306840257954e-05,
      "loss": 0.5124,
      "step": 12731
    },
    {
      "epoch": 0.39111602617270297,
      "grad_norm": 0.3259119987487793,
      "learning_rate": 1.8194029826610727e-05,
      "loss": 0.5403,
      "step": 12732
    },
    {
      "epoch": 0.39114674530765214,
      "grad_norm": 0.3998487889766693,
      "learning_rate": 1.819375279382577e-05,
      "loss": 0.6223,
      "step": 12733
    },
    {
      "epoch": 0.3911774644426013,
      "grad_norm": 0.3864685893058777,
      "learning_rate": 1.8193475741903734e-05,
      "loss": 0.5657,
      "step": 12734
    },
    {
      "epoch": 0.39120818357755044,
      "grad_norm": 0.44996100664138794,
      "learning_rate": 1.8193198670845258e-05,
      "loss": 0.5494,
      "step": 12735
    },
    {
      "epoch": 0.3912389027124996,
      "grad_norm": 0.37049680948257446,
      "learning_rate": 1.8192921580650996e-05,
      "loss": 0.5465,
      "step": 12736
    },
    {
      "epoch": 0.3912696218474488,
      "grad_norm": 0.3206457197666168,
      "learning_rate": 1.8192644471321597e-05,
      "loss": 0.5586,
      "step": 12737
    },
    {
      "epoch": 0.3913003409823979,
      "grad_norm": 0.34707027673721313,
      "learning_rate": 1.8192367342857702e-05,
      "loss": 0.5771,
      "step": 12738
    },
    {
      "epoch": 0.3913310601173471,
      "grad_norm": 0.3418354094028473,
      "learning_rate": 1.819209019525996e-05,
      "loss": 0.678,
      "step": 12739
    },
    {
      "epoch": 0.39136177925229626,
      "grad_norm": 0.39108923077583313,
      "learning_rate": 1.819181302852902e-05,
      "loss": 0.5458,
      "step": 12740
    },
    {
      "epoch": 0.39139249838724544,
      "grad_norm": 0.4312012493610382,
      "learning_rate": 1.819153584266553e-05,
      "loss": 0.537,
      "step": 12741
    },
    {
      "epoch": 0.39142321752219456,
      "grad_norm": 0.34393349289894104,
      "learning_rate": 1.8191258637670135e-05,
      "loss": 0.5602,
      "step": 12742
    },
    {
      "epoch": 0.39145393665714373,
      "grad_norm": 0.3418145179748535,
      "learning_rate": 1.819098141354348e-05,
      "loss": 0.5741,
      "step": 12743
    },
    {
      "epoch": 0.3914846557920929,
      "grad_norm": 0.32313355803489685,
      "learning_rate": 1.8190704170286222e-05,
      "loss": 0.4797,
      "step": 12744
    },
    {
      "epoch": 0.3915153749270421,
      "grad_norm": 0.518947184085846,
      "learning_rate": 1.8190426907899002e-05,
      "loss": 0.4963,
      "step": 12745
    },
    {
      "epoch": 0.3915460940619912,
      "grad_norm": 0.3358088731765747,
      "learning_rate": 1.819014962638246e-05,
      "loss": 0.5919,
      "step": 12746
    },
    {
      "epoch": 0.3915768131969404,
      "grad_norm": 0.31682321429252625,
      "learning_rate": 1.818987232573726e-05,
      "loss": 0.53,
      "step": 12747
    },
    {
      "epoch": 0.39160753233188955,
      "grad_norm": 0.3594593405723572,
      "learning_rate": 1.818959500596404e-05,
      "loss": 0.5066,
      "step": 12748
    },
    {
      "epoch": 0.39163825146683867,
      "grad_norm": 0.3678840100765228,
      "learning_rate": 1.8189317667063446e-05,
      "loss": 0.603,
      "step": 12749
    },
    {
      "epoch": 0.39166897060178785,
      "grad_norm": 0.3709924817085266,
      "learning_rate": 1.818904030903613e-05,
      "loss": 0.6268,
      "step": 12750
    },
    {
      "epoch": 0.391699689736737,
      "grad_norm": 0.32755231857299805,
      "learning_rate": 1.818876293188274e-05,
      "loss": 0.5134,
      "step": 12751
    },
    {
      "epoch": 0.3917304088716862,
      "grad_norm": 0.3151247203350067,
      "learning_rate": 1.818848553560392e-05,
      "loss": 0.5864,
      "step": 12752
    },
    {
      "epoch": 0.3917611280066353,
      "grad_norm": 0.34476086497306824,
      "learning_rate": 1.818820812020032e-05,
      "loss": 0.5775,
      "step": 12753
    },
    {
      "epoch": 0.3917918471415845,
      "grad_norm": 0.3425072133541107,
      "learning_rate": 1.818793068567259e-05,
      "loss": 0.6099,
      "step": 12754
    },
    {
      "epoch": 0.39182256627653367,
      "grad_norm": 0.44688543677330017,
      "learning_rate": 1.8187653232021372e-05,
      "loss": 0.5141,
      "step": 12755
    },
    {
      "epoch": 0.3918532854114828,
      "grad_norm": 0.38633593916893005,
      "learning_rate": 1.8187375759247323e-05,
      "loss": 0.5836,
      "step": 12756
    },
    {
      "epoch": 0.39188400454643196,
      "grad_norm": 0.3630231022834778,
      "learning_rate": 1.8187098267351085e-05,
      "loss": 0.5679,
      "step": 12757
    },
    {
      "epoch": 0.39191472368138114,
      "grad_norm": 0.33725807070732117,
      "learning_rate": 1.8186820756333304e-05,
      "loss": 0.5209,
      "step": 12758
    },
    {
      "epoch": 0.3919454428163303,
      "grad_norm": 0.3213243782520294,
      "learning_rate": 1.8186543226194636e-05,
      "loss": 0.5229,
      "step": 12759
    },
    {
      "epoch": 0.39197616195127943,
      "grad_norm": 0.32613253593444824,
      "learning_rate": 1.818626567693572e-05,
      "loss": 0.5251,
      "step": 12760
    },
    {
      "epoch": 0.3920068810862286,
      "grad_norm": 0.37759166955947876,
      "learning_rate": 1.8185988108557212e-05,
      "loss": 0.5723,
      "step": 12761
    },
    {
      "epoch": 0.3920376002211778,
      "grad_norm": 0.3797167241573334,
      "learning_rate": 1.8185710521059756e-05,
      "loss": 0.592,
      "step": 12762
    },
    {
      "epoch": 0.3920683193561269,
      "grad_norm": 0.2890707552433014,
      "learning_rate": 1.8185432914444005e-05,
      "loss": 0.5347,
      "step": 12763
    },
    {
      "epoch": 0.3920990384910761,
      "grad_norm": 0.34908726811408997,
      "learning_rate": 1.8185155288710598e-05,
      "loss": 0.5438,
      "step": 12764
    },
    {
      "epoch": 0.39212975762602525,
      "grad_norm": 0.31697121262550354,
      "learning_rate": 1.818487764386019e-05,
      "loss": 0.5825,
      "step": 12765
    },
    {
      "epoch": 0.39216047676097443,
      "grad_norm": 0.34345513582229614,
      "learning_rate": 1.8184599979893432e-05,
      "loss": 0.5913,
      "step": 12766
    },
    {
      "epoch": 0.39219119589592355,
      "grad_norm": 0.3325057029724121,
      "learning_rate": 1.8184322296810965e-05,
      "loss": 0.5837,
      "step": 12767
    },
    {
      "epoch": 0.3922219150308727,
      "grad_norm": 0.330489844083786,
      "learning_rate": 1.8184044594613444e-05,
      "loss": 0.6159,
      "step": 12768
    },
    {
      "epoch": 0.3922526341658219,
      "grad_norm": 0.35868802666664124,
      "learning_rate": 1.8183766873301516e-05,
      "loss": 0.5653,
      "step": 12769
    },
    {
      "epoch": 0.3922833533007711,
      "grad_norm": 0.32376763224601746,
      "learning_rate": 1.818348913287583e-05,
      "loss": 0.5002,
      "step": 12770
    },
    {
      "epoch": 0.3923140724357202,
      "grad_norm": 0.3798137605190277,
      "learning_rate": 1.8183211373337028e-05,
      "loss": 0.6331,
      "step": 12771
    },
    {
      "epoch": 0.39234479157066937,
      "grad_norm": 0.3545227348804474,
      "learning_rate": 1.818293359468577e-05,
      "loss": 0.5668,
      "step": 12772
    },
    {
      "epoch": 0.39237551070561855,
      "grad_norm": 0.3300997018814087,
      "learning_rate": 1.8182655796922696e-05,
      "loss": 0.5462,
      "step": 12773
    },
    {
      "epoch": 0.39240622984056767,
      "grad_norm": 0.31555670499801636,
      "learning_rate": 1.818237798004846e-05,
      "loss": 0.5162,
      "step": 12774
    },
    {
      "epoch": 0.39243694897551684,
      "grad_norm": 0.356912761926651,
      "learning_rate": 1.818210014406371e-05,
      "loss": 0.5584,
      "step": 12775
    },
    {
      "epoch": 0.392467668110466,
      "grad_norm": 0.4127078056335449,
      "learning_rate": 1.8181822288969088e-05,
      "loss": 0.5959,
      "step": 12776
    },
    {
      "epoch": 0.3924983872454152,
      "grad_norm": 0.31994518637657166,
      "learning_rate": 1.8181544414765253e-05,
      "loss": 0.58,
      "step": 12777
    },
    {
      "epoch": 0.3925291063803643,
      "grad_norm": 0.34047064185142517,
      "learning_rate": 1.818126652145285e-05,
      "loss": 0.6357,
      "step": 12778
    },
    {
      "epoch": 0.3925598255153135,
      "grad_norm": 0.35640543699264526,
      "learning_rate": 1.8180988609032523e-05,
      "loss": 0.6334,
      "step": 12779
    },
    {
      "epoch": 0.39259054465026266,
      "grad_norm": 0.820229172706604,
      "learning_rate": 1.818071067750493e-05,
      "loss": 0.621,
      "step": 12780
    },
    {
      "epoch": 0.3926212637852118,
      "grad_norm": 0.32395482063293457,
      "learning_rate": 1.8180432726870716e-05,
      "loss": 0.5785,
      "step": 12781
    },
    {
      "epoch": 0.39265198292016096,
      "grad_norm": 0.3598460257053375,
      "learning_rate": 1.818015475713053e-05,
      "loss": 0.5449,
      "step": 12782
    },
    {
      "epoch": 0.39268270205511013,
      "grad_norm": 0.36322563886642456,
      "learning_rate": 1.817987676828502e-05,
      "loss": 0.5021,
      "step": 12783
    },
    {
      "epoch": 0.3927134211900593,
      "grad_norm": 0.32324206829071045,
      "learning_rate": 1.8179598760334838e-05,
      "loss": 0.4786,
      "step": 12784
    },
    {
      "epoch": 0.39274414032500843,
      "grad_norm": 0.38048267364501953,
      "learning_rate": 1.817932073328063e-05,
      "loss": 0.6279,
      "step": 12785
    },
    {
      "epoch": 0.3927748594599576,
      "grad_norm": 0.3299476206302643,
      "learning_rate": 1.817904268712305e-05,
      "loss": 0.5258,
      "step": 12786
    },
    {
      "epoch": 0.3928055785949068,
      "grad_norm": 0.3179298937320709,
      "learning_rate": 1.8178764621862738e-05,
      "loss": 0.5131,
      "step": 12787
    },
    {
      "epoch": 0.39283629772985595,
      "grad_norm": 0.33918771147727966,
      "learning_rate": 1.8178486537500356e-05,
      "loss": 0.5305,
      "step": 12788
    },
    {
      "epoch": 0.3928670168648051,
      "grad_norm": 0.37182340025901794,
      "learning_rate": 1.8178208434036545e-05,
      "loss": 0.5377,
      "step": 12789
    },
    {
      "epoch": 0.39289773599975425,
      "grad_norm": 0.3483932614326477,
      "learning_rate": 1.817793031147196e-05,
      "loss": 0.5729,
      "step": 12790
    },
    {
      "epoch": 0.3929284551347034,
      "grad_norm": 0.3446057140827179,
      "learning_rate": 1.8177652169807245e-05,
      "loss": 0.6093,
      "step": 12791
    },
    {
      "epoch": 0.39295917426965254,
      "grad_norm": 0.3477858603000641,
      "learning_rate": 1.817737400904305e-05,
      "loss": 0.6666,
      "step": 12792
    },
    {
      "epoch": 0.3929898934046017,
      "grad_norm": 0.32864198088645935,
      "learning_rate": 1.8177095829180033e-05,
      "loss": 0.6043,
      "step": 12793
    },
    {
      "epoch": 0.3930206125395509,
      "grad_norm": 0.32323840260505676,
      "learning_rate": 1.8176817630218833e-05,
      "loss": 0.5216,
      "step": 12794
    },
    {
      "epoch": 0.39305133167450007,
      "grad_norm": 0.3462378978729248,
      "learning_rate": 1.8176539412160104e-05,
      "loss": 0.5652,
      "step": 12795
    },
    {
      "epoch": 0.3930820508094492,
      "grad_norm": 0.3513031303882599,
      "learning_rate": 1.8176261175004502e-05,
      "loss": 0.5571,
      "step": 12796
    },
    {
      "epoch": 0.39311276994439837,
      "grad_norm": 0.3849570155143738,
      "learning_rate": 1.8175982918752664e-05,
      "loss": 0.5354,
      "step": 12797
    },
    {
      "epoch": 0.39314348907934754,
      "grad_norm": 0.34383028745651245,
      "learning_rate": 1.817570464340525e-05,
      "loss": 0.5594,
      "step": 12798
    },
    {
      "epoch": 0.39317420821429666,
      "grad_norm": 0.32246312499046326,
      "learning_rate": 1.8175426348962907e-05,
      "loss": 0.5994,
      "step": 12799
    },
    {
      "epoch": 0.39320492734924584,
      "grad_norm": 0.3417467176914215,
      "learning_rate": 1.8175148035426285e-05,
      "loss": 0.5983,
      "step": 12800
    },
    {
      "epoch": 0.393235646484195,
      "grad_norm": 0.3139697313308716,
      "learning_rate": 1.8174869702796033e-05,
      "loss": 0.5056,
      "step": 12801
    },
    {
      "epoch": 0.3932663656191442,
      "grad_norm": 0.3582741320133209,
      "learning_rate": 1.8174591351072804e-05,
      "loss": 0.5483,
      "step": 12802
    },
    {
      "epoch": 0.3932970847540933,
      "grad_norm": 0.35488972067832947,
      "learning_rate": 1.8174312980257243e-05,
      "loss": 0.5782,
      "step": 12803
    },
    {
      "epoch": 0.3933278038890425,
      "grad_norm": 0.5101213455200195,
      "learning_rate": 1.8174034590350006e-05,
      "loss": 0.6004,
      "step": 12804
    },
    {
      "epoch": 0.39335852302399166,
      "grad_norm": 0.4329844117164612,
      "learning_rate": 1.8173756181351734e-05,
      "loss": 0.5745,
      "step": 12805
    },
    {
      "epoch": 0.3933892421589408,
      "grad_norm": 0.37905266880989075,
      "learning_rate": 1.8173477753263095e-05,
      "loss": 0.5228,
      "step": 12806
    },
    {
      "epoch": 0.39341996129388995,
      "grad_norm": 0.3561650216579437,
      "learning_rate": 1.8173199306084718e-05,
      "loss": 0.6219,
      "step": 12807
    },
    {
      "epoch": 0.39345068042883913,
      "grad_norm": 0.35827162861824036,
      "learning_rate": 1.8172920839817268e-05,
      "loss": 0.586,
      "step": 12808
    },
    {
      "epoch": 0.3934813995637883,
      "grad_norm": 0.5302042365074158,
      "learning_rate": 1.817264235446139e-05,
      "loss": 0.6714,
      "step": 12809
    },
    {
      "epoch": 0.3935121186987374,
      "grad_norm": 0.34511616826057434,
      "learning_rate": 1.817236385001773e-05,
      "loss": 0.5356,
      "step": 12810
    },
    {
      "epoch": 0.3935428378336866,
      "grad_norm": 0.32790037989616394,
      "learning_rate": 1.817208532648695e-05,
      "loss": 0.586,
      "step": 12811
    },
    {
      "epoch": 0.3935735569686358,
      "grad_norm": 0.3022743761539459,
      "learning_rate": 1.817180678386969e-05,
      "loss": 0.5883,
      "step": 12812
    },
    {
      "epoch": 0.39360427610358495,
      "grad_norm": 0.3409270942211151,
      "learning_rate": 1.8171528222166605e-05,
      "loss": 0.5757,
      "step": 12813
    },
    {
      "epoch": 0.39363499523853407,
      "grad_norm": 0.34028932452201843,
      "learning_rate": 1.817124964137835e-05,
      "loss": 0.547,
      "step": 12814
    },
    {
      "epoch": 0.39366571437348324,
      "grad_norm": 0.3532288372516632,
      "learning_rate": 1.8170971041505563e-05,
      "loss": 0.5544,
      "step": 12815
    },
    {
      "epoch": 0.3936964335084324,
      "grad_norm": 0.3446268141269684,
      "learning_rate": 1.8170692422548908e-05,
      "loss": 0.5593,
      "step": 12816
    },
    {
      "epoch": 0.39372715264338154,
      "grad_norm": 0.3573243021965027,
      "learning_rate": 1.8170413784509028e-05,
      "loss": 0.5803,
      "step": 12817
    },
    {
      "epoch": 0.3937578717783307,
      "grad_norm": 0.3697608709335327,
      "learning_rate": 1.8170135127386576e-05,
      "loss": 0.6204,
      "step": 12818
    },
    {
      "epoch": 0.3937885909132799,
      "grad_norm": 0.3816118538379669,
      "learning_rate": 1.8169856451182203e-05,
      "loss": 0.6476,
      "step": 12819
    },
    {
      "epoch": 0.39381931004822907,
      "grad_norm": 0.35307908058166504,
      "learning_rate": 1.8169577755896563e-05,
      "loss": 0.5093,
      "step": 12820
    },
    {
      "epoch": 0.3938500291831782,
      "grad_norm": 0.33663007616996765,
      "learning_rate": 1.81692990415303e-05,
      "loss": 0.5727,
      "step": 12821
    },
    {
      "epoch": 0.39388074831812736,
      "grad_norm": 0.33210235834121704,
      "learning_rate": 1.816902030808407e-05,
      "loss": 0.5897,
      "step": 12822
    },
    {
      "epoch": 0.39391146745307654,
      "grad_norm": 0.3522430956363678,
      "learning_rate": 1.816874155555852e-05,
      "loss": 0.5285,
      "step": 12823
    },
    {
      "epoch": 0.39394218658802566,
      "grad_norm": 0.35440826416015625,
      "learning_rate": 1.8168462783954305e-05,
      "loss": 0.6236,
      "step": 12824
    },
    {
      "epoch": 0.39397290572297483,
      "grad_norm": 0.33583495020866394,
      "learning_rate": 1.8168183993272074e-05,
      "loss": 0.573,
      "step": 12825
    },
    {
      "epoch": 0.394003624857924,
      "grad_norm": 0.33631300926208496,
      "learning_rate": 1.816790518351248e-05,
      "loss": 0.5664,
      "step": 12826
    },
    {
      "epoch": 0.3940343439928732,
      "grad_norm": 0.3489297926425934,
      "learning_rate": 1.8167626354676175e-05,
      "loss": 0.5994,
      "step": 12827
    },
    {
      "epoch": 0.3940650631278223,
      "grad_norm": 0.36632487177848816,
      "learning_rate": 1.8167347506763807e-05,
      "loss": 0.6102,
      "step": 12828
    },
    {
      "epoch": 0.3940957822627715,
      "grad_norm": 0.36638349294662476,
      "learning_rate": 1.8167068639776023e-05,
      "loss": 0.5882,
      "step": 12829
    },
    {
      "epoch": 0.39412650139772065,
      "grad_norm": 0.35900527238845825,
      "learning_rate": 1.8166789753713488e-05,
      "loss": 0.5919,
      "step": 12830
    },
    {
      "epoch": 0.3941572205326698,
      "grad_norm": 0.34766098856925964,
      "learning_rate": 1.8166510848576838e-05,
      "loss": 0.6314,
      "step": 12831
    },
    {
      "epoch": 0.39418793966761895,
      "grad_norm": 0.3395267426967621,
      "learning_rate": 1.8166231924366737e-05,
      "loss": 0.5284,
      "step": 12832
    },
    {
      "epoch": 0.3942186588025681,
      "grad_norm": 0.33809995651245117,
      "learning_rate": 1.816595298108383e-05,
      "loss": 0.6269,
      "step": 12833
    },
    {
      "epoch": 0.3942493779375173,
      "grad_norm": 0.33063483238220215,
      "learning_rate": 1.816567401872877e-05,
      "loss": 0.5149,
      "step": 12834
    },
    {
      "epoch": 0.3942800970724664,
      "grad_norm": 0.3420949876308441,
      "learning_rate": 1.8165395037302206e-05,
      "loss": 0.6006,
      "step": 12835
    },
    {
      "epoch": 0.3943108162074156,
      "grad_norm": 0.29784148931503296,
      "learning_rate": 1.816511603680479e-05,
      "loss": 0.5505,
      "step": 12836
    },
    {
      "epoch": 0.39434153534236477,
      "grad_norm": 0.34664586186408997,
      "learning_rate": 1.816483701723718e-05,
      "loss": 0.5986,
      "step": 12837
    },
    {
      "epoch": 0.39437225447731394,
      "grad_norm": 0.3633562922477722,
      "learning_rate": 1.8164557978600018e-05,
      "loss": 0.5881,
      "step": 12838
    },
    {
      "epoch": 0.39440297361226306,
      "grad_norm": 0.3667909502983093,
      "learning_rate": 1.8164278920893964e-05,
      "loss": 0.5754,
      "step": 12839
    },
    {
      "epoch": 0.39443369274721224,
      "grad_norm": 0.3740542232990265,
      "learning_rate": 1.8163999844119667e-05,
      "loss": 0.6192,
      "step": 12840
    },
    {
      "epoch": 0.3944644118821614,
      "grad_norm": 0.34725409746170044,
      "learning_rate": 1.8163720748277774e-05,
      "loss": 0.5522,
      "step": 12841
    },
    {
      "epoch": 0.39449513101711053,
      "grad_norm": 0.3728778660297394,
      "learning_rate": 1.8163441633368946e-05,
      "loss": 0.5428,
      "step": 12842
    },
    {
      "epoch": 0.3945258501520597,
      "grad_norm": 0.34048062562942505,
      "learning_rate": 1.8163162499393826e-05,
      "loss": 0.6324,
      "step": 12843
    },
    {
      "epoch": 0.3945565692870089,
      "grad_norm": 0.34225714206695557,
      "learning_rate": 1.8162883346353072e-05,
      "loss": 0.5711,
      "step": 12844
    },
    {
      "epoch": 0.39458728842195806,
      "grad_norm": 0.3218097984790802,
      "learning_rate": 1.8162604174247334e-05,
      "loss": 0.5685,
      "step": 12845
    },
    {
      "epoch": 0.3946180075569072,
      "grad_norm": 0.4195527136325836,
      "learning_rate": 1.8162324983077263e-05,
      "loss": 0.5393,
      "step": 12846
    },
    {
      "epoch": 0.39464872669185636,
      "grad_norm": 0.39020389318466187,
      "learning_rate": 1.8162045772843513e-05,
      "loss": 0.639,
      "step": 12847
    },
    {
      "epoch": 0.39467944582680553,
      "grad_norm": 0.3705294728279114,
      "learning_rate": 1.8161766543546734e-05,
      "loss": 0.5228,
      "step": 12848
    },
    {
      "epoch": 0.39471016496175465,
      "grad_norm": 0.41043511033058167,
      "learning_rate": 1.816148729518758e-05,
      "loss": 0.621,
      "step": 12849
    },
    {
      "epoch": 0.3947408840967038,
      "grad_norm": 0.33246028423309326,
      "learning_rate": 1.8161208027766702e-05,
      "loss": 0.587,
      "step": 12850
    },
    {
      "epoch": 0.394771603231653,
      "grad_norm": 0.44218236207962036,
      "learning_rate": 1.8160928741284754e-05,
      "loss": 0.5573,
      "step": 12851
    },
    {
      "epoch": 0.3948023223666022,
      "grad_norm": 0.3847273290157318,
      "learning_rate": 1.8160649435742382e-05,
      "loss": 0.5746,
      "step": 12852
    },
    {
      "epoch": 0.3948330415015513,
      "grad_norm": 0.36323902010917664,
      "learning_rate": 1.816037011114025e-05,
      "loss": 0.5719,
      "step": 12853
    },
    {
      "epoch": 0.39486376063650047,
      "grad_norm": 0.32781165838241577,
      "learning_rate": 1.8160090767478998e-05,
      "loss": 0.5866,
      "step": 12854
    },
    {
      "epoch": 0.39489447977144965,
      "grad_norm": 0.3807957172393799,
      "learning_rate": 1.815981140475929e-05,
      "loss": 0.6243,
      "step": 12855
    },
    {
      "epoch": 0.3949251989063988,
      "grad_norm": 0.3364047110080719,
      "learning_rate": 1.815953202298177e-05,
      "loss": 0.5713,
      "step": 12856
    },
    {
      "epoch": 0.39495591804134794,
      "grad_norm": 0.346954882144928,
      "learning_rate": 1.8159252622147092e-05,
      "loss": 0.5691,
      "step": 12857
    },
    {
      "epoch": 0.3949866371762971,
      "grad_norm": 0.37489521503448486,
      "learning_rate": 1.8158973202255906e-05,
      "loss": 0.6934,
      "step": 12858
    },
    {
      "epoch": 0.3950173563112463,
      "grad_norm": 0.33791032433509827,
      "learning_rate": 1.8158693763308877e-05,
      "loss": 0.5436,
      "step": 12859
    },
    {
      "epoch": 0.3950480754461954,
      "grad_norm": 0.31310659646987915,
      "learning_rate": 1.8158414305306643e-05,
      "loss": 0.5959,
      "step": 12860
    },
    {
      "epoch": 0.3950787945811446,
      "grad_norm": 0.35715073347091675,
      "learning_rate": 1.8158134828249864e-05,
      "loss": 0.5547,
      "step": 12861
    },
    {
      "epoch": 0.39510951371609376,
      "grad_norm": 0.3391798734664917,
      "learning_rate": 1.815785533213919e-05,
      "loss": 0.535,
      "step": 12862
    },
    {
      "epoch": 0.39514023285104294,
      "grad_norm": 0.47078198194503784,
      "learning_rate": 1.8157575816975277e-05,
      "loss": 0.6161,
      "step": 12863
    },
    {
      "epoch": 0.39517095198599206,
      "grad_norm": 0.30335533618927,
      "learning_rate": 1.8157296282758773e-05,
      "loss": 0.5496,
      "step": 12864
    },
    {
      "epoch": 0.39520167112094123,
      "grad_norm": 0.4036659300327301,
      "learning_rate": 1.8157016729490337e-05,
      "loss": 0.5343,
      "step": 12865
    },
    {
      "epoch": 0.3952323902558904,
      "grad_norm": 0.34383928775787354,
      "learning_rate": 1.8156737157170622e-05,
      "loss": 0.5497,
      "step": 12866
    },
    {
      "epoch": 0.39526310939083953,
      "grad_norm": 0.3330143988132477,
      "learning_rate": 1.8156457565800272e-05,
      "loss": 0.5975,
      "step": 12867
    },
    {
      "epoch": 0.3952938285257887,
      "grad_norm": 0.4451829791069031,
      "learning_rate": 1.8156177955379948e-05,
      "loss": 0.6473,
      "step": 12868
    },
    {
      "epoch": 0.3953245476607379,
      "grad_norm": 0.40778782963752747,
      "learning_rate": 1.81558983259103e-05,
      "loss": 0.5485,
      "step": 12869
    },
    {
      "epoch": 0.39535526679568705,
      "grad_norm": 0.36082887649536133,
      "learning_rate": 1.8155618677391982e-05,
      "loss": 0.6561,
      "step": 12870
    },
    {
      "epoch": 0.3953859859306362,
      "grad_norm": 0.4530898332595825,
      "learning_rate": 1.8155339009825645e-05,
      "loss": 0.5971,
      "step": 12871
    },
    {
      "epoch": 0.39541670506558535,
      "grad_norm": 0.32219329476356506,
      "learning_rate": 1.8155059323211946e-05,
      "loss": 0.6365,
      "step": 12872
    },
    {
      "epoch": 0.3954474242005345,
      "grad_norm": 0.34637799859046936,
      "learning_rate": 1.815477961755154e-05,
      "loss": 0.613,
      "step": 12873
    },
    {
      "epoch": 0.39547814333548365,
      "grad_norm": 0.3677693009376526,
      "learning_rate": 1.815449989284507e-05,
      "loss": 0.6246,
      "step": 12874
    },
    {
      "epoch": 0.3955088624704328,
      "grad_norm": 0.3725658357143402,
      "learning_rate": 1.81542201490932e-05,
      "loss": 0.6072,
      "step": 12875
    },
    {
      "epoch": 0.395539581605382,
      "grad_norm": 0.3616657555103302,
      "learning_rate": 1.8153940386296577e-05,
      "loss": 0.516,
      "step": 12876
    },
    {
      "epoch": 0.39557030074033117,
      "grad_norm": 0.40663278102874756,
      "learning_rate": 1.815366060445586e-05,
      "loss": 0.6543,
      "step": 12877
    },
    {
      "epoch": 0.3956010198752803,
      "grad_norm": 0.33798497915267944,
      "learning_rate": 1.8153380803571697e-05,
      "loss": 0.5473,
      "step": 12878
    },
    {
      "epoch": 0.39563173901022947,
      "grad_norm": 0.3357340395450592,
      "learning_rate": 1.8153100983644746e-05,
      "loss": 0.6258,
      "step": 12879
    },
    {
      "epoch": 0.39566245814517864,
      "grad_norm": 0.3790649473667145,
      "learning_rate": 1.8152821144675658e-05,
      "loss": 0.6035,
      "step": 12880
    },
    {
      "epoch": 0.3956931772801278,
      "grad_norm": 0.3645251989364624,
      "learning_rate": 1.8152541286665082e-05,
      "loss": 0.588,
      "step": 12881
    },
    {
      "epoch": 0.39572389641507694,
      "grad_norm": 0.35480886697769165,
      "learning_rate": 1.815226140961368e-05,
      "loss": 0.5451,
      "step": 12882
    },
    {
      "epoch": 0.3957546155500261,
      "grad_norm": 0.38754212856292725,
      "learning_rate": 1.8151981513522103e-05,
      "loss": 0.5949,
      "step": 12883
    },
    {
      "epoch": 0.3957853346849753,
      "grad_norm": 0.35579872131347656,
      "learning_rate": 1.8151701598391003e-05,
      "loss": 0.6425,
      "step": 12884
    },
    {
      "epoch": 0.3958160538199244,
      "grad_norm": 0.3870236575603485,
      "learning_rate": 1.8151421664221033e-05,
      "loss": 0.5924,
      "step": 12885
    },
    {
      "epoch": 0.3958467729548736,
      "grad_norm": 0.36626720428466797,
      "learning_rate": 1.815114171101285e-05,
      "loss": 0.5537,
      "step": 12886
    },
    {
      "epoch": 0.39587749208982276,
      "grad_norm": 0.3443355858325958,
      "learning_rate": 1.815086173876711e-05,
      "loss": 0.6449,
      "step": 12887
    },
    {
      "epoch": 0.39590821122477193,
      "grad_norm": 0.3456527590751648,
      "learning_rate": 1.8150581747484458e-05,
      "loss": 0.5743,
      "step": 12888
    },
    {
      "epoch": 0.39593893035972105,
      "grad_norm": 0.42168915271759033,
      "learning_rate": 1.815030173716555e-05,
      "loss": 0.5891,
      "step": 12889
    },
    {
      "epoch": 0.39596964949467023,
      "grad_norm": 0.346948504447937,
      "learning_rate": 1.8150021707811053e-05,
      "loss": 0.6291,
      "step": 12890
    },
    {
      "epoch": 0.3960003686296194,
      "grad_norm": 0.3424777686595917,
      "learning_rate": 1.8149741659421603e-05,
      "loss": 0.5888,
      "step": 12891
    },
    {
      "epoch": 0.3960310877645685,
      "grad_norm": 0.33735302090644836,
      "learning_rate": 1.8149461591997862e-05,
      "loss": 0.5812,
      "step": 12892
    },
    {
      "epoch": 0.3960618068995177,
      "grad_norm": 0.39985591173171997,
      "learning_rate": 1.8149181505540488e-05,
      "loss": 0.503,
      "step": 12893
    },
    {
      "epoch": 0.3960925260344669,
      "grad_norm": 0.3446309566497803,
      "learning_rate": 1.814890140005013e-05,
      "loss": 0.6132,
      "step": 12894
    },
    {
      "epoch": 0.39612324516941605,
      "grad_norm": 0.3279944062232971,
      "learning_rate": 1.8148621275527446e-05,
      "loss": 0.5081,
      "step": 12895
    },
    {
      "epoch": 0.39615396430436517,
      "grad_norm": 0.37307870388031006,
      "learning_rate": 1.814834113197309e-05,
      "loss": 0.5897,
      "step": 12896
    },
    {
      "epoch": 0.39618468343931434,
      "grad_norm": 0.3299659192562103,
      "learning_rate": 1.8148060969387707e-05,
      "loss": 0.5808,
      "step": 12897
    },
    {
      "epoch": 0.3962154025742635,
      "grad_norm": 0.3435394763946533,
      "learning_rate": 1.8147780787771962e-05,
      "loss": 0.6662,
      "step": 12898
    },
    {
      "epoch": 0.3962461217092127,
      "grad_norm": 0.3639402389526367,
      "learning_rate": 1.8147500587126507e-05,
      "loss": 0.5665,
      "step": 12899
    },
    {
      "epoch": 0.3962768408441618,
      "grad_norm": 0.40050485730171204,
      "learning_rate": 1.8147220367451992e-05,
      "loss": 0.5963,
      "step": 12900
    },
    {
      "epoch": 0.396307559979111,
      "grad_norm": 0.3918745815753937,
      "learning_rate": 1.814694012874908e-05,
      "loss": 0.5457,
      "step": 12901
    },
    {
      "epoch": 0.39633827911406017,
      "grad_norm": 0.3358967900276184,
      "learning_rate": 1.8146659871018415e-05,
      "loss": 0.6053,
      "step": 12902
    },
    {
      "epoch": 0.3963689982490093,
      "grad_norm": 0.34041520953178406,
      "learning_rate": 1.8146379594260662e-05,
      "loss": 0.5844,
      "step": 12903
    },
    {
      "epoch": 0.39639971738395846,
      "grad_norm": 0.3292492628097534,
      "learning_rate": 1.8146099298476467e-05,
      "loss": 0.5626,
      "step": 12904
    },
    {
      "epoch": 0.39643043651890764,
      "grad_norm": 0.3562423884868622,
      "learning_rate": 1.8145818983666488e-05,
      "loss": 0.5742,
      "step": 12905
    },
    {
      "epoch": 0.3964611556538568,
      "grad_norm": 0.37773001194000244,
      "learning_rate": 1.814553864983138e-05,
      "loss": 0.5169,
      "step": 12906
    },
    {
      "epoch": 0.39649187478880593,
      "grad_norm": 0.3469577431678772,
      "learning_rate": 1.81452582969718e-05,
      "loss": 0.5393,
      "step": 12907
    },
    {
      "epoch": 0.3965225939237551,
      "grad_norm": 0.42746174335479736,
      "learning_rate": 1.81449779250884e-05,
      "loss": 0.5372,
      "step": 12908
    },
    {
      "epoch": 0.3965533130587043,
      "grad_norm": 0.34618517756462097,
      "learning_rate": 1.814469753418183e-05,
      "loss": 0.5973,
      "step": 12909
    },
    {
      "epoch": 0.3965840321936534,
      "grad_norm": 0.3625010848045349,
      "learning_rate": 1.8144417124252756e-05,
      "loss": 0.6264,
      "step": 12910
    },
    {
      "epoch": 0.3966147513286026,
      "grad_norm": 0.35739457607269287,
      "learning_rate": 1.8144136695301824e-05,
      "loss": 0.5551,
      "step": 12911
    },
    {
      "epoch": 0.39664547046355175,
      "grad_norm": 0.33814677596092224,
      "learning_rate": 1.8143856247329694e-05,
      "loss": 0.5772,
      "step": 12912
    },
    {
      "epoch": 0.39667618959850093,
      "grad_norm": 0.363502562046051,
      "learning_rate": 1.8143575780337016e-05,
      "loss": 0.5652,
      "step": 12913
    },
    {
      "epoch": 0.39670690873345005,
      "grad_norm": 0.4577622413635254,
      "learning_rate": 1.8143295294324453e-05,
      "loss": 0.6406,
      "step": 12914
    },
    {
      "epoch": 0.3967376278683992,
      "grad_norm": 0.31255558133125305,
      "learning_rate": 1.8143014789292653e-05,
      "loss": 0.5962,
      "step": 12915
    },
    {
      "epoch": 0.3967683470033484,
      "grad_norm": 0.38728344440460205,
      "learning_rate": 1.8142734265242273e-05,
      "loss": 0.5985,
      "step": 12916
    },
    {
      "epoch": 0.3967990661382975,
      "grad_norm": 0.44451674818992615,
      "learning_rate": 1.8142453722173964e-05,
      "loss": 0.5792,
      "step": 12917
    },
    {
      "epoch": 0.3968297852732467,
      "grad_norm": 0.3660999834537506,
      "learning_rate": 1.814217316008839e-05,
      "loss": 0.6376,
      "step": 12918
    },
    {
      "epoch": 0.39686050440819587,
      "grad_norm": 0.3361862301826477,
      "learning_rate": 1.81418925789862e-05,
      "loss": 0.5774,
      "step": 12919
    },
    {
      "epoch": 0.39689122354314504,
      "grad_norm": 0.37523892521858215,
      "learning_rate": 1.8141611978868058e-05,
      "loss": 0.546,
      "step": 12920
    },
    {
      "epoch": 0.39692194267809416,
      "grad_norm": 0.32210540771484375,
      "learning_rate": 1.8141331359734605e-05,
      "loss": 0.4972,
      "step": 12921
    },
    {
      "epoch": 0.39695266181304334,
      "grad_norm": 0.42029455304145813,
      "learning_rate": 1.8141050721586505e-05,
      "loss": 0.7231,
      "step": 12922
    },
    {
      "epoch": 0.3969833809479925,
      "grad_norm": 0.37349945306777954,
      "learning_rate": 1.8140770064424417e-05,
      "loss": 0.5858,
      "step": 12923
    },
    {
      "epoch": 0.3970141000829417,
      "grad_norm": 0.37552574276924133,
      "learning_rate": 1.8140489388248986e-05,
      "loss": 0.6078,
      "step": 12924
    },
    {
      "epoch": 0.3970448192178908,
      "grad_norm": 0.35673609375953674,
      "learning_rate": 1.814020869306088e-05,
      "loss": 0.5942,
      "step": 12925
    },
    {
      "epoch": 0.39707553835284,
      "grad_norm": 0.3872948884963989,
      "learning_rate": 1.813992797886074e-05,
      "loss": 0.5885,
      "step": 12926
    },
    {
      "epoch": 0.39710625748778916,
      "grad_norm": 0.542278528213501,
      "learning_rate": 1.8139647245649238e-05,
      "loss": 0.5257,
      "step": 12927
    },
    {
      "epoch": 0.3971369766227383,
      "grad_norm": 0.4214458465576172,
      "learning_rate": 1.8139366493427014e-05,
      "loss": 0.6455,
      "step": 12928
    },
    {
      "epoch": 0.39716769575768746,
      "grad_norm": 0.36166608333587646,
      "learning_rate": 1.8139085722194737e-05,
      "loss": 0.595,
      "step": 12929
    },
    {
      "epoch": 0.39719841489263663,
      "grad_norm": 0.347302109003067,
      "learning_rate": 1.8138804931953053e-05,
      "loss": 0.6402,
      "step": 12930
    },
    {
      "epoch": 0.3972291340275858,
      "grad_norm": 0.3700729310512543,
      "learning_rate": 1.8138524122702624e-05,
      "loss": 0.6183,
      "step": 12931
    },
    {
      "epoch": 0.3972598531625349,
      "grad_norm": 0.33718588948249817,
      "learning_rate": 1.8138243294444105e-05,
      "loss": 0.6764,
      "step": 12932
    },
    {
      "epoch": 0.3972905722974841,
      "grad_norm": 0.3395189344882965,
      "learning_rate": 1.8137962447178147e-05,
      "loss": 0.4761,
      "step": 12933
    },
    {
      "epoch": 0.3973212914324333,
      "grad_norm": 0.3912227153778076,
      "learning_rate": 1.813768158090541e-05,
      "loss": 0.6083,
      "step": 12934
    },
    {
      "epoch": 0.3973520105673824,
      "grad_norm": 0.3656686544418335,
      "learning_rate": 1.813740069562655e-05,
      "loss": 0.5115,
      "step": 12935
    },
    {
      "epoch": 0.39738272970233157,
      "grad_norm": 0.3566579222679138,
      "learning_rate": 1.813711979134222e-05,
      "loss": 0.6267,
      "step": 12936
    },
    {
      "epoch": 0.39741344883728075,
      "grad_norm": 0.3447688817977905,
      "learning_rate": 1.8136838868053082e-05,
      "loss": 0.5729,
      "step": 12937
    },
    {
      "epoch": 0.3974441679722299,
      "grad_norm": 0.363421231508255,
      "learning_rate": 1.813655792575979e-05,
      "loss": 0.5107,
      "step": 12938
    },
    {
      "epoch": 0.39747488710717904,
      "grad_norm": 0.3633897602558136,
      "learning_rate": 1.8136276964462992e-05,
      "loss": 0.5343,
      "step": 12939
    },
    {
      "epoch": 0.3975056062421282,
      "grad_norm": 0.3049306273460388,
      "learning_rate": 1.8135995984163357e-05,
      "loss": 0.4934,
      "step": 12940
    },
    {
      "epoch": 0.3975363253770774,
      "grad_norm": 0.3804556131362915,
      "learning_rate": 1.8135714984861533e-05,
      "loss": 0.5812,
      "step": 12941
    },
    {
      "epoch": 0.39756704451202657,
      "grad_norm": 0.32398805022239685,
      "learning_rate": 1.813543396655818e-05,
      "loss": 0.5237,
      "step": 12942
    },
    {
      "epoch": 0.3975977636469757,
      "grad_norm": 0.3800413906574249,
      "learning_rate": 1.813515292925395e-05,
      "loss": 0.5722,
      "step": 12943
    },
    {
      "epoch": 0.39762848278192486,
      "grad_norm": 0.4092594385147095,
      "learning_rate": 1.81348718729495e-05,
      "loss": 0.5407,
      "step": 12944
    },
    {
      "epoch": 0.39765920191687404,
      "grad_norm": 0.33835622668266296,
      "learning_rate": 1.8134590797645495e-05,
      "loss": 0.6099,
      "step": 12945
    },
    {
      "epoch": 0.39768992105182316,
      "grad_norm": 0.3506392240524292,
      "learning_rate": 1.8134309703342584e-05,
      "loss": 0.5724,
      "step": 12946
    },
    {
      "epoch": 0.39772064018677233,
      "grad_norm": 0.36245647072792053,
      "learning_rate": 1.8134028590041423e-05,
      "loss": 0.6049,
      "step": 12947
    },
    {
      "epoch": 0.3977513593217215,
      "grad_norm": 0.3553200960159302,
      "learning_rate": 1.8133747457742667e-05,
      "loss": 0.5835,
      "step": 12948
    },
    {
      "epoch": 0.3977820784566707,
      "grad_norm": 0.33084797859191895,
      "learning_rate": 1.813346630644698e-05,
      "loss": 0.5713,
      "step": 12949
    },
    {
      "epoch": 0.3978127975916198,
      "grad_norm": 0.3255881369113922,
      "learning_rate": 1.813318513615501e-05,
      "loss": 0.6323,
      "step": 12950
    },
    {
      "epoch": 0.397843516726569,
      "grad_norm": 0.3158280551433563,
      "learning_rate": 1.8132903946867424e-05,
      "loss": 0.5413,
      "step": 12951
    },
    {
      "epoch": 0.39787423586151816,
      "grad_norm": 0.33184319734573364,
      "learning_rate": 1.813262273858487e-05,
      "loss": 0.516,
      "step": 12952
    },
    {
      "epoch": 0.3979049549964673,
      "grad_norm": 0.3346373438835144,
      "learning_rate": 1.8132341511308008e-05,
      "loss": 0.5777,
      "step": 12953
    },
    {
      "epoch": 0.39793567413141645,
      "grad_norm": 0.336779922246933,
      "learning_rate": 1.8132060265037493e-05,
      "loss": 0.564,
      "step": 12954
    },
    {
      "epoch": 0.3979663932663656,
      "grad_norm": 0.381418913602829,
      "learning_rate": 1.8131778999773985e-05,
      "loss": 0.5736,
      "step": 12955
    },
    {
      "epoch": 0.3979971124013148,
      "grad_norm": 0.34984034299850464,
      "learning_rate": 1.813149771551814e-05,
      "loss": 0.5311,
      "step": 12956
    },
    {
      "epoch": 0.3980278315362639,
      "grad_norm": 0.33968305587768555,
      "learning_rate": 1.813121641227061e-05,
      "loss": 0.5717,
      "step": 12957
    },
    {
      "epoch": 0.3980585506712131,
      "grad_norm": 0.3671490550041199,
      "learning_rate": 1.813093509003206e-05,
      "loss": 0.6126,
      "step": 12958
    },
    {
      "epoch": 0.39808926980616227,
      "grad_norm": 1.060914158821106,
      "learning_rate": 1.8130653748803143e-05,
      "loss": 0.5419,
      "step": 12959
    },
    {
      "epoch": 0.3981199889411114,
      "grad_norm": 0.3911992013454437,
      "learning_rate": 1.8130372388584515e-05,
      "loss": 0.5598,
      "step": 12960
    },
    {
      "epoch": 0.39815070807606057,
      "grad_norm": 0.34417155385017395,
      "learning_rate": 1.8130091009376834e-05,
      "loss": 0.5563,
      "step": 12961
    },
    {
      "epoch": 0.39818142721100974,
      "grad_norm": 0.33973246812820435,
      "learning_rate": 1.812980961118076e-05,
      "loss": 0.6055,
      "step": 12962
    },
    {
      "epoch": 0.3982121463459589,
      "grad_norm": 0.34577494859695435,
      "learning_rate": 1.8129528193996945e-05,
      "loss": 0.5788,
      "step": 12963
    },
    {
      "epoch": 0.39824286548090804,
      "grad_norm": 0.365262895822525,
      "learning_rate": 1.8129246757826055e-05,
      "loss": 0.5954,
      "step": 12964
    },
    {
      "epoch": 0.3982735846158572,
      "grad_norm": 0.3435237407684326,
      "learning_rate": 1.8128965302668734e-05,
      "loss": 0.6537,
      "step": 12965
    },
    {
      "epoch": 0.3983043037508064,
      "grad_norm": 0.31961965560913086,
      "learning_rate": 1.812868382852565e-05,
      "loss": 0.5742,
      "step": 12966
    },
    {
      "epoch": 0.39833502288575556,
      "grad_norm": 0.35584908723831177,
      "learning_rate": 1.8128402335397457e-05,
      "loss": 0.6003,
      "step": 12967
    },
    {
      "epoch": 0.3983657420207047,
      "grad_norm": 0.3422880172729492,
      "learning_rate": 1.8128120823284815e-05,
      "loss": 0.6184,
      "step": 12968
    },
    {
      "epoch": 0.39839646115565386,
      "grad_norm": 0.44394099712371826,
      "learning_rate": 1.8127839292188375e-05,
      "loss": 0.5651,
      "step": 12969
    },
    {
      "epoch": 0.39842718029060303,
      "grad_norm": 0.4173397719860077,
      "learning_rate": 1.8127557742108802e-05,
      "loss": 0.5659,
      "step": 12970
    },
    {
      "epoch": 0.39845789942555215,
      "grad_norm": 0.3696073889732361,
      "learning_rate": 1.8127276173046747e-05,
      "loss": 0.6117,
      "step": 12971
    },
    {
      "epoch": 0.39848861856050133,
      "grad_norm": 0.48497119545936584,
      "learning_rate": 1.8126994585002873e-05,
      "loss": 0.5606,
      "step": 12972
    },
    {
      "epoch": 0.3985193376954505,
      "grad_norm": 0.34101182222366333,
      "learning_rate": 1.8126712977977837e-05,
      "loss": 0.6356,
      "step": 12973
    },
    {
      "epoch": 0.3985500568303997,
      "grad_norm": 0.3321332037448883,
      "learning_rate": 1.8126431351972294e-05,
      "loss": 0.5802,
      "step": 12974
    },
    {
      "epoch": 0.3985807759653488,
      "grad_norm": 0.3778130114078522,
      "learning_rate": 1.81261497069869e-05,
      "loss": 0.5595,
      "step": 12975
    },
    {
      "epoch": 0.398611495100298,
      "grad_norm": 0.32816267013549805,
      "learning_rate": 1.8125868043022322e-05,
      "loss": 0.578,
      "step": 12976
    },
    {
      "epoch": 0.39864221423524715,
      "grad_norm": 0.3848414421081543,
      "learning_rate": 1.8125586360079208e-05,
      "loss": 0.5779,
      "step": 12977
    },
    {
      "epoch": 0.39867293337019627,
      "grad_norm": 0.326799213886261,
      "learning_rate": 1.812530465815822e-05,
      "loss": 0.5103,
      "step": 12978
    },
    {
      "epoch": 0.39870365250514544,
      "grad_norm": 0.3200840950012207,
      "learning_rate": 1.8125022937260012e-05,
      "loss": 0.5084,
      "step": 12979
    },
    {
      "epoch": 0.3987343716400946,
      "grad_norm": 0.35580867528915405,
      "learning_rate": 1.8124741197385248e-05,
      "loss": 0.5687,
      "step": 12980
    },
    {
      "epoch": 0.3987650907750438,
      "grad_norm": 0.35510948300361633,
      "learning_rate": 1.8124459438534585e-05,
      "loss": 0.5602,
      "step": 12981
    },
    {
      "epoch": 0.3987958099099929,
      "grad_norm": 0.36603158712387085,
      "learning_rate": 1.8124177660708683e-05,
      "loss": 0.6027,
      "step": 12982
    },
    {
      "epoch": 0.3988265290449421,
      "grad_norm": 0.391293466091156,
      "learning_rate": 1.8123895863908192e-05,
      "loss": 0.5766,
      "step": 12983
    },
    {
      "epoch": 0.39885724817989127,
      "grad_norm": 0.3561176061630249,
      "learning_rate": 1.8123614048133774e-05,
      "loss": 0.5856,
      "step": 12984
    },
    {
      "epoch": 0.39888796731484044,
      "grad_norm": 0.3451213836669922,
      "learning_rate": 1.812333221338609e-05,
      "loss": 0.5784,
      "step": 12985
    },
    {
      "epoch": 0.39891868644978956,
      "grad_norm": 0.3281084895133972,
      "learning_rate": 1.8123050359665794e-05,
      "loss": 0.5726,
      "step": 12986
    },
    {
      "epoch": 0.39894940558473874,
      "grad_norm": 0.328919380903244,
      "learning_rate": 1.812276848697355e-05,
      "loss": 0.6129,
      "step": 12987
    },
    {
      "epoch": 0.3989801247196879,
      "grad_norm": 0.3612845838069916,
      "learning_rate": 1.812248659531001e-05,
      "loss": 0.5469,
      "step": 12988
    },
    {
      "epoch": 0.39901084385463703,
      "grad_norm": 0.3562816381454468,
      "learning_rate": 1.812220468467584e-05,
      "loss": 0.5638,
      "step": 12989
    },
    {
      "epoch": 0.3990415629895862,
      "grad_norm": 0.3571195602416992,
      "learning_rate": 1.812192275507169e-05,
      "loss": 0.5827,
      "step": 12990
    },
    {
      "epoch": 0.3990722821245354,
      "grad_norm": 0.45717182755470276,
      "learning_rate": 1.8121640806498218e-05,
      "loss": 0.5398,
      "step": 12991
    },
    {
      "epoch": 0.39910300125948456,
      "grad_norm": 0.3124993145465851,
      "learning_rate": 1.8121358838956092e-05,
      "loss": 0.5303,
      "step": 12992
    },
    {
      "epoch": 0.3991337203944337,
      "grad_norm": 0.3760831356048584,
      "learning_rate": 1.8121076852445965e-05,
      "loss": 0.499,
      "step": 12993
    },
    {
      "epoch": 0.39916443952938285,
      "grad_norm": 0.35389119386672974,
      "learning_rate": 1.8120794846968496e-05,
      "loss": 0.6036,
      "step": 12994
    },
    {
      "epoch": 0.39919515866433203,
      "grad_norm": 0.34164535999298096,
      "learning_rate": 1.8120512822524344e-05,
      "loss": 0.5769,
      "step": 12995
    },
    {
      "epoch": 0.39922587779928115,
      "grad_norm": 0.366719126701355,
      "learning_rate": 1.8120230779114164e-05,
      "loss": 0.5296,
      "step": 12996
    },
    {
      "epoch": 0.3992565969342303,
      "grad_norm": 0.3573869466781616,
      "learning_rate": 1.811994871673862e-05,
      "loss": 0.5846,
      "step": 12997
    },
    {
      "epoch": 0.3992873160691795,
      "grad_norm": 0.4543416500091553,
      "learning_rate": 1.811966663539837e-05,
      "loss": 0.4933,
      "step": 12998
    },
    {
      "epoch": 0.3993180352041287,
      "grad_norm": 0.3431367874145508,
      "learning_rate": 1.8119384535094068e-05,
      "loss": 0.5689,
      "step": 12999
    },
    {
      "epoch": 0.3993487543390778,
      "grad_norm": 0.4150281548500061,
      "learning_rate": 1.8119102415826376e-05,
      "loss": 0.4885,
      "step": 13000
    },
    {
      "epoch": 0.39937947347402697,
      "grad_norm": 0.33836331963539124,
      "learning_rate": 1.8118820277595958e-05,
      "loss": 0.6382,
      "step": 13001
    },
    {
      "epoch": 0.39941019260897614,
      "grad_norm": 0.39145365357398987,
      "learning_rate": 1.8118538120403467e-05,
      "loss": 0.5356,
      "step": 13002
    },
    {
      "epoch": 0.39944091174392526,
      "grad_norm": 0.379238486289978,
      "learning_rate": 1.811825594424956e-05,
      "loss": 0.5709,
      "step": 13003
    },
    {
      "epoch": 0.39947163087887444,
      "grad_norm": 0.3587002456188202,
      "learning_rate": 1.8117973749134903e-05,
      "loss": 0.6635,
      "step": 13004
    },
    {
      "epoch": 0.3995023500138236,
      "grad_norm": 0.44223320484161377,
      "learning_rate": 1.811769153506015e-05,
      "loss": 0.5841,
      "step": 13005
    },
    {
      "epoch": 0.3995330691487728,
      "grad_norm": 0.34275391697883606,
      "learning_rate": 1.811740930202596e-05,
      "loss": 0.6025,
      "step": 13006
    },
    {
      "epoch": 0.3995637882837219,
      "grad_norm": 0.3236602246761322,
      "learning_rate": 1.8117127050032993e-05,
      "loss": 0.5707,
      "step": 13007
    },
    {
      "epoch": 0.3995945074186711,
      "grad_norm": 0.3650473952293396,
      "learning_rate": 1.8116844779081914e-05,
      "loss": 0.6648,
      "step": 13008
    },
    {
      "epoch": 0.39962522655362026,
      "grad_norm": 0.35549506545066833,
      "learning_rate": 1.8116562489173373e-05,
      "loss": 0.6596,
      "step": 13009
    },
    {
      "epoch": 0.39965594568856944,
      "grad_norm": 0.4076179563999176,
      "learning_rate": 1.8116280180308036e-05,
      "loss": 0.6282,
      "step": 13010
    },
    {
      "epoch": 0.39968666482351856,
      "grad_norm": 0.35554876923561096,
      "learning_rate": 1.8115997852486558e-05,
      "loss": 0.5583,
      "step": 13011
    },
    {
      "epoch": 0.39971738395846773,
      "grad_norm": 0.37644362449645996,
      "learning_rate": 1.8115715505709597e-05,
      "loss": 0.6106,
      "step": 13012
    },
    {
      "epoch": 0.3997481030934169,
      "grad_norm": 0.33263808488845825,
      "learning_rate": 1.8115433139977822e-05,
      "loss": 0.5097,
      "step": 13013
    },
    {
      "epoch": 0.399778822228366,
      "grad_norm": 0.40367427468299866,
      "learning_rate": 1.811515075529188e-05,
      "loss": 0.6519,
      "step": 13014
    },
    {
      "epoch": 0.3998095413633152,
      "grad_norm": 0.35062751173973083,
      "learning_rate": 1.811486835165244e-05,
      "loss": 0.5069,
      "step": 13015
    },
    {
      "epoch": 0.3998402604982644,
      "grad_norm": 0.3653094470500946,
      "learning_rate": 1.811458592906016e-05,
      "loss": 0.6169,
      "step": 13016
    },
    {
      "epoch": 0.39987097963321355,
      "grad_norm": 0.4211580753326416,
      "learning_rate": 1.8114303487515697e-05,
      "loss": 0.5862,
      "step": 13017
    },
    {
      "epoch": 0.3999016987681627,
      "grad_norm": 0.348274827003479,
      "learning_rate": 1.8114021027019708e-05,
      "loss": 0.6253,
      "step": 13018
    },
    {
      "epoch": 0.39993241790311185,
      "grad_norm": 0.33451783657073975,
      "learning_rate": 1.8113738547572858e-05,
      "loss": 0.5177,
      "step": 13019
    },
    {
      "epoch": 0.399963137038061,
      "grad_norm": 0.36390310525894165,
      "learning_rate": 1.8113456049175807e-05,
      "loss": 0.6111,
      "step": 13020
    },
    {
      "epoch": 0.39999385617301014,
      "grad_norm": 0.3350619077682495,
      "learning_rate": 1.811317353182921e-05,
      "loss": 0.5928,
      "step": 13021
    },
    {
      "epoch": 0.4000245753079593,
      "grad_norm": 0.3923126757144928,
      "learning_rate": 1.811289099553373e-05,
      "loss": 0.5497,
      "step": 13022
    },
    {
      "epoch": 0.4000552944429085,
      "grad_norm": 0.34330451488494873,
      "learning_rate": 1.811260844029003e-05,
      "loss": 0.5161,
      "step": 13023
    },
    {
      "epoch": 0.40008601357785767,
      "grad_norm": 0.3216344118118286,
      "learning_rate": 1.8112325866098762e-05,
      "loss": 0.5008,
      "step": 13024
    },
    {
      "epoch": 0.4001167327128068,
      "grad_norm": 0.3841245174407959,
      "learning_rate": 1.8112043272960592e-05,
      "loss": 0.6009,
      "step": 13025
    },
    {
      "epoch": 0.40014745184775596,
      "grad_norm": 0.3680126667022705,
      "learning_rate": 1.811176066087618e-05,
      "loss": 0.5813,
      "step": 13026
    },
    {
      "epoch": 0.40017817098270514,
      "grad_norm": 0.32905346155166626,
      "learning_rate": 1.8111478029846182e-05,
      "loss": 0.453,
      "step": 13027
    },
    {
      "epoch": 0.4002088901176543,
      "grad_norm": 0.38026511669158936,
      "learning_rate": 1.811119537987126e-05,
      "loss": 0.6061,
      "step": 13028
    },
    {
      "epoch": 0.40023960925260343,
      "grad_norm": 0.3490017354488373,
      "learning_rate": 1.811091271095208e-05,
      "loss": 0.5985,
      "step": 13029
    },
    {
      "epoch": 0.4002703283875526,
      "grad_norm": 0.37698471546173096,
      "learning_rate": 1.811063002308929e-05,
      "loss": 0.5882,
      "step": 13030
    },
    {
      "epoch": 0.4003010475225018,
      "grad_norm": 0.3300102651119232,
      "learning_rate": 1.811034731628356e-05,
      "loss": 0.5263,
      "step": 13031
    },
    {
      "epoch": 0.4003317666574509,
      "grad_norm": 0.34968727827072144,
      "learning_rate": 1.8110064590535548e-05,
      "loss": 0.5895,
      "step": 13032
    },
    {
      "epoch": 0.4003624857924001,
      "grad_norm": 0.36806586384773254,
      "learning_rate": 1.8109781845845914e-05,
      "loss": 0.5727,
      "step": 13033
    },
    {
      "epoch": 0.40039320492734926,
      "grad_norm": 0.37422826886177063,
      "learning_rate": 1.810949908221532e-05,
      "loss": 0.6813,
      "step": 13034
    },
    {
      "epoch": 0.40042392406229843,
      "grad_norm": 0.3682180643081665,
      "learning_rate": 1.810921629964442e-05,
      "loss": 0.5142,
      "step": 13035
    },
    {
      "epoch": 0.40045464319724755,
      "grad_norm": 0.3092144727706909,
      "learning_rate": 1.8108933498133882e-05,
      "loss": 0.5226,
      "step": 13036
    },
    {
      "epoch": 0.4004853623321967,
      "grad_norm": 0.3458704352378845,
      "learning_rate": 1.810865067768436e-05,
      "loss": 0.5385,
      "step": 13037
    },
    {
      "epoch": 0.4005160814671459,
      "grad_norm": 0.3322073221206665,
      "learning_rate": 1.810836783829652e-05,
      "loss": 0.5132,
      "step": 13038
    },
    {
      "epoch": 0.400546800602095,
      "grad_norm": 0.35289859771728516,
      "learning_rate": 1.8108084979971024e-05,
      "loss": 0.6306,
      "step": 13039
    },
    {
      "epoch": 0.4005775197370442,
      "grad_norm": 0.317409873008728,
      "learning_rate": 1.8107802102708527e-05,
      "loss": 0.4718,
      "step": 13040
    },
    {
      "epoch": 0.40060823887199337,
      "grad_norm": 0.3947815001010895,
      "learning_rate": 1.8107519206509693e-05,
      "loss": 0.6558,
      "step": 13041
    },
    {
      "epoch": 0.40063895800694255,
      "grad_norm": 0.3502882719039917,
      "learning_rate": 1.8107236291375177e-05,
      "loss": 0.5903,
      "step": 13042
    },
    {
      "epoch": 0.40066967714189167,
      "grad_norm": 0.3418857157230377,
      "learning_rate": 1.810695335730565e-05,
      "loss": 0.5836,
      "step": 13043
    },
    {
      "epoch": 0.40070039627684084,
      "grad_norm": 0.3470628559589386,
      "learning_rate": 1.8106670404301764e-05,
      "loss": 0.5701,
      "step": 13044
    },
    {
      "epoch": 0.40073111541179,
      "grad_norm": 0.3345760405063629,
      "learning_rate": 1.8106387432364184e-05,
      "loss": 0.5742,
      "step": 13045
    },
    {
      "epoch": 0.40076183454673914,
      "grad_norm": 0.3489665687084198,
      "learning_rate": 1.810610444149357e-05,
      "loss": 0.5245,
      "step": 13046
    },
    {
      "epoch": 0.4007925536816883,
      "grad_norm": 0.3301171064376831,
      "learning_rate": 1.810582143169058e-05,
      "loss": 0.6005,
      "step": 13047
    },
    {
      "epoch": 0.4008232728166375,
      "grad_norm": 0.3442883789539337,
      "learning_rate": 1.8105538402955886e-05,
      "loss": 0.5649,
      "step": 13048
    },
    {
      "epoch": 0.40085399195158666,
      "grad_norm": 0.42283299565315247,
      "learning_rate": 1.8105255355290136e-05,
      "loss": 0.5352,
      "step": 13049
    },
    {
      "epoch": 0.4008847110865358,
      "grad_norm": 0.359520822763443,
      "learning_rate": 1.8104972288693992e-05,
      "loss": 0.5711,
      "step": 13050
    },
    {
      "epoch": 0.40091543022148496,
      "grad_norm": 0.3355616331100464,
      "learning_rate": 1.8104689203168123e-05,
      "loss": 0.6387,
      "step": 13051
    },
    {
      "epoch": 0.40094614935643413,
      "grad_norm": 0.3579041063785553,
      "learning_rate": 1.8104406098713188e-05,
      "loss": 0.599,
      "step": 13052
    },
    {
      "epoch": 0.4009768684913833,
      "grad_norm": 0.3391491174697876,
      "learning_rate": 1.8104122975329845e-05,
      "loss": 0.57,
      "step": 13053
    },
    {
      "epoch": 0.40100758762633243,
      "grad_norm": 0.37575003504753113,
      "learning_rate": 1.8103839833018754e-05,
      "loss": 0.5682,
      "step": 13054
    },
    {
      "epoch": 0.4010383067612816,
      "grad_norm": 0.3149512708187103,
      "learning_rate": 1.8103556671780584e-05,
      "loss": 0.4729,
      "step": 13055
    },
    {
      "epoch": 0.4010690258962308,
      "grad_norm": 0.38076773285865784,
      "learning_rate": 1.810327349161599e-05,
      "loss": 0.6419,
      "step": 13056
    },
    {
      "epoch": 0.4010997450311799,
      "grad_norm": 0.364455908536911,
      "learning_rate": 1.8102990292525632e-05,
      "loss": 0.6077,
      "step": 13057
    },
    {
      "epoch": 0.4011304641661291,
      "grad_norm": 0.3282911479473114,
      "learning_rate": 1.8102707074510176e-05,
      "loss": 0.5812,
      "step": 13058
    },
    {
      "epoch": 0.40116118330107825,
      "grad_norm": 0.3234592080116272,
      "learning_rate": 1.8102423837570286e-05,
      "loss": 0.53,
      "step": 13059
    },
    {
      "epoch": 0.4011919024360274,
      "grad_norm": 0.3652111291885376,
      "learning_rate": 1.8102140581706612e-05,
      "loss": 0.5384,
      "step": 13060
    },
    {
      "epoch": 0.40122262157097655,
      "grad_norm": 0.3186188042163849,
      "learning_rate": 1.8101857306919826e-05,
      "loss": 0.5428,
      "step": 13061
    },
    {
      "epoch": 0.4012533407059257,
      "grad_norm": 0.34593990445137024,
      "learning_rate": 1.810157401321059e-05,
      "loss": 0.5753,
      "step": 13062
    },
    {
      "epoch": 0.4012840598408749,
      "grad_norm": 0.3296295702457428,
      "learning_rate": 1.8101290700579556e-05,
      "loss": 0.5742,
      "step": 13063
    },
    {
      "epoch": 0.401314778975824,
      "grad_norm": 0.4416889548301697,
      "learning_rate": 1.8101007369027397e-05,
      "loss": 0.7115,
      "step": 13064
    },
    {
      "epoch": 0.4013454981107732,
      "grad_norm": 0.3627316951751709,
      "learning_rate": 1.8100724018554765e-05,
      "loss": 0.508,
      "step": 13065
    },
    {
      "epoch": 0.40137621724572237,
      "grad_norm": 0.3624752163887024,
      "learning_rate": 1.810044064916233e-05,
      "loss": 0.5349,
      "step": 13066
    },
    {
      "epoch": 0.40140693638067154,
      "grad_norm": 0.41776421666145325,
      "learning_rate": 1.8100157260850748e-05,
      "loss": 0.5973,
      "step": 13067
    },
    {
      "epoch": 0.40143765551562066,
      "grad_norm": 0.35225096344947815,
      "learning_rate": 1.809987385362068e-05,
      "loss": 0.5706,
      "step": 13068
    },
    {
      "epoch": 0.40146837465056984,
      "grad_norm": 0.36620867252349854,
      "learning_rate": 1.8099590427472796e-05,
      "loss": 0.5726,
      "step": 13069
    },
    {
      "epoch": 0.401499093785519,
      "grad_norm": 0.3512287735939026,
      "learning_rate": 1.8099306982407753e-05,
      "loss": 0.504,
      "step": 13070
    },
    {
      "epoch": 0.40152981292046813,
      "grad_norm": 0.3456054925918579,
      "learning_rate": 1.809902351842621e-05,
      "loss": 0.6203,
      "step": 13071
    },
    {
      "epoch": 0.4015605320554173,
      "grad_norm": 0.34405654668807983,
      "learning_rate": 1.8098740035528834e-05,
      "loss": 0.5068,
      "step": 13072
    },
    {
      "epoch": 0.4015912511903665,
      "grad_norm": 0.3305802047252655,
      "learning_rate": 1.8098456533716283e-05,
      "loss": 0.6143,
      "step": 13073
    },
    {
      "epoch": 0.40162197032531566,
      "grad_norm": 0.692613422870636,
      "learning_rate": 1.8098173012989225e-05,
      "loss": 0.549,
      "step": 13074
    },
    {
      "epoch": 0.4016526894602648,
      "grad_norm": 0.384886234998703,
      "learning_rate": 1.8097889473348315e-05,
      "loss": 0.5992,
      "step": 13075
    },
    {
      "epoch": 0.40168340859521395,
      "grad_norm": 0.31406688690185547,
      "learning_rate": 1.809760591479422e-05,
      "loss": 0.628,
      "step": 13076
    },
    {
      "epoch": 0.40171412773016313,
      "grad_norm": 0.346515953540802,
      "learning_rate": 1.80973223373276e-05,
      "loss": 0.5939,
      "step": 13077
    },
    {
      "epoch": 0.4017448468651123,
      "grad_norm": 0.34516391158103943,
      "learning_rate": 1.8097038740949118e-05,
      "loss": 0.5423,
      "step": 13078
    },
    {
      "epoch": 0.4017755660000614,
      "grad_norm": 0.47109633684158325,
      "learning_rate": 1.8096755125659434e-05,
      "loss": 0.5872,
      "step": 13079
    },
    {
      "epoch": 0.4018062851350106,
      "grad_norm": 0.3405253291130066,
      "learning_rate": 1.809647149145922e-05,
      "loss": 0.6094,
      "step": 13080
    },
    {
      "epoch": 0.4018370042699598,
      "grad_norm": 0.343245267868042,
      "learning_rate": 1.8096187838349127e-05,
      "loss": 0.6193,
      "step": 13081
    },
    {
      "epoch": 0.4018677234049089,
      "grad_norm": 0.33914852142333984,
      "learning_rate": 1.8095904166329822e-05,
      "loss": 0.6095,
      "step": 13082
    },
    {
      "epoch": 0.40189844253985807,
      "grad_norm": 0.35435816645622253,
      "learning_rate": 1.8095620475401966e-05,
      "loss": 0.6413,
      "step": 13083
    },
    {
      "epoch": 0.40192916167480724,
      "grad_norm": 0.3293165862560272,
      "learning_rate": 1.8095336765566224e-05,
      "loss": 0.5686,
      "step": 13084
    },
    {
      "epoch": 0.4019598808097564,
      "grad_norm": 0.36999669671058655,
      "learning_rate": 1.8095053036823257e-05,
      "loss": 0.5861,
      "step": 13085
    },
    {
      "epoch": 0.40199059994470554,
      "grad_norm": 0.30673325061798096,
      "learning_rate": 1.809476928917373e-05,
      "loss": 0.5587,
      "step": 13086
    },
    {
      "epoch": 0.4020213190796547,
      "grad_norm": 0.3096969425678253,
      "learning_rate": 1.8094485522618305e-05,
      "loss": 0.5659,
      "step": 13087
    },
    {
      "epoch": 0.4020520382146039,
      "grad_norm": 0.36580365896224976,
      "learning_rate": 1.8094201737157642e-05,
      "loss": 0.5569,
      "step": 13088
    },
    {
      "epoch": 0.402082757349553,
      "grad_norm": 0.46562474966049194,
      "learning_rate": 1.8093917932792403e-05,
      "loss": 0.6061,
      "step": 13089
    },
    {
      "epoch": 0.4021134764845022,
      "grad_norm": 0.3400559723377228,
      "learning_rate": 1.809363410952326e-05,
      "loss": 0.5647,
      "step": 13090
    },
    {
      "epoch": 0.40214419561945136,
      "grad_norm": 0.3582642674446106,
      "learning_rate": 1.809335026735086e-05,
      "loss": 0.6268,
      "step": 13091
    },
    {
      "epoch": 0.40217491475440054,
      "grad_norm": 0.344508558511734,
      "learning_rate": 1.8093066406275882e-05,
      "loss": 0.4923,
      "step": 13092
    },
    {
      "epoch": 0.40220563388934966,
      "grad_norm": 0.33267149329185486,
      "learning_rate": 1.8092782526298983e-05,
      "loss": 0.4997,
      "step": 13093
    },
    {
      "epoch": 0.40223635302429883,
      "grad_norm": 0.3526279032230377,
      "learning_rate": 1.8092498627420822e-05,
      "loss": 0.6235,
      "step": 13094
    },
    {
      "epoch": 0.402267072159248,
      "grad_norm": 0.34682610630989075,
      "learning_rate": 1.8092214709642066e-05,
      "loss": 0.4992,
      "step": 13095
    },
    {
      "epoch": 0.4022977912941972,
      "grad_norm": 1.0744670629501343,
      "learning_rate": 1.809193077296338e-05,
      "loss": 0.5784,
      "step": 13096
    },
    {
      "epoch": 0.4023285104291463,
      "grad_norm": 0.32341837882995605,
      "learning_rate": 1.8091646817385422e-05,
      "loss": 0.5039,
      "step": 13097
    },
    {
      "epoch": 0.4023592295640955,
      "grad_norm": 0.36430105566978455,
      "learning_rate": 1.8091362842908856e-05,
      "loss": 0.5389,
      "step": 13098
    },
    {
      "epoch": 0.40238994869904465,
      "grad_norm": 0.35660237073898315,
      "learning_rate": 1.809107884953435e-05,
      "loss": 0.5998,
      "step": 13099
    },
    {
      "epoch": 0.4024206678339938,
      "grad_norm": 0.3508598506450653,
      "learning_rate": 1.809079483726256e-05,
      "loss": 0.5567,
      "step": 13100
    },
    {
      "epoch": 0.40245138696894295,
      "grad_norm": 0.3341028094291687,
      "learning_rate": 1.809051080609416e-05,
      "loss": 0.5633,
      "step": 13101
    },
    {
      "epoch": 0.4024821061038921,
      "grad_norm": 0.41753479838371277,
      "learning_rate": 1.8090226756029804e-05,
      "loss": 0.5252,
      "step": 13102
    },
    {
      "epoch": 0.4025128252388413,
      "grad_norm": 0.3819064497947693,
      "learning_rate": 1.8089942687070158e-05,
      "loss": 0.6748,
      "step": 13103
    },
    {
      "epoch": 0.4025435443737904,
      "grad_norm": 0.5630823969841003,
      "learning_rate": 1.8089658599215883e-05,
      "loss": 0.5255,
      "step": 13104
    },
    {
      "epoch": 0.4025742635087396,
      "grad_norm": 0.39077112078666687,
      "learning_rate": 1.808937449246765e-05,
      "loss": 0.6823,
      "step": 13105
    },
    {
      "epoch": 0.40260498264368877,
      "grad_norm": 0.342196524143219,
      "learning_rate": 1.8089090366826116e-05,
      "loss": 0.6251,
      "step": 13106
    },
    {
      "epoch": 0.4026357017786379,
      "grad_norm": 0.3390013873577118,
      "learning_rate": 1.8088806222291947e-05,
      "loss": 0.4902,
      "step": 13107
    },
    {
      "epoch": 0.40266642091358706,
      "grad_norm": 0.3660273253917694,
      "learning_rate": 1.8088522058865806e-05,
      "loss": 0.5683,
      "step": 13108
    },
    {
      "epoch": 0.40269714004853624,
      "grad_norm": 0.3340429961681366,
      "learning_rate": 1.8088237876548354e-05,
      "loss": 0.6137,
      "step": 13109
    },
    {
      "epoch": 0.4027278591834854,
      "grad_norm": 0.3554539382457733,
      "learning_rate": 1.8087953675340265e-05,
      "loss": 0.6379,
      "step": 13110
    },
    {
      "epoch": 0.40275857831843453,
      "grad_norm": 0.3949281871318817,
      "learning_rate": 1.808766945524219e-05,
      "loss": 0.4897,
      "step": 13111
    },
    {
      "epoch": 0.4027892974533837,
      "grad_norm": 0.3407707214355469,
      "learning_rate": 1.8087385216254797e-05,
      "loss": 0.6516,
      "step": 13112
    },
    {
      "epoch": 0.4028200165883329,
      "grad_norm": 0.3528645634651184,
      "learning_rate": 1.8087100958378754e-05,
      "loss": 0.6398,
      "step": 13113
    },
    {
      "epoch": 0.402850735723282,
      "grad_norm": 0.3908250033855438,
      "learning_rate": 1.808681668161472e-05,
      "loss": 0.6355,
      "step": 13114
    },
    {
      "epoch": 0.4028814548582312,
      "grad_norm": 0.34136149287223816,
      "learning_rate": 1.8086532385963364e-05,
      "loss": 0.4587,
      "step": 13115
    },
    {
      "epoch": 0.40291217399318036,
      "grad_norm": 0.352906733751297,
      "learning_rate": 1.8086248071425343e-05,
      "loss": 0.5613,
      "step": 13116
    },
    {
      "epoch": 0.40294289312812953,
      "grad_norm": 0.4742562174797058,
      "learning_rate": 1.8085963738001326e-05,
      "loss": 0.6108,
      "step": 13117
    },
    {
      "epoch": 0.40297361226307865,
      "grad_norm": 0.3818645775318146,
      "learning_rate": 1.8085679385691978e-05,
      "loss": 0.6136,
      "step": 13118
    },
    {
      "epoch": 0.4030043313980278,
      "grad_norm": 0.38420817255973816,
      "learning_rate": 1.8085395014497956e-05,
      "loss": 0.6033,
      "step": 13119
    },
    {
      "epoch": 0.403035050532977,
      "grad_norm": 0.7938624024391174,
      "learning_rate": 1.8085110624419934e-05,
      "loss": 0.5879,
      "step": 13120
    },
    {
      "epoch": 0.4030657696679262,
      "grad_norm": 0.3185769021511078,
      "learning_rate": 1.808482621545857e-05,
      "loss": 0.493,
      "step": 13121
    },
    {
      "epoch": 0.4030964888028753,
      "grad_norm": 0.3845197558403015,
      "learning_rate": 1.8084541787614533e-05,
      "loss": 0.5477,
      "step": 13122
    },
    {
      "epoch": 0.40312720793782447,
      "grad_norm": 0.3443424105644226,
      "learning_rate": 1.808425734088848e-05,
      "loss": 0.5691,
      "step": 13123
    },
    {
      "epoch": 0.40315792707277365,
      "grad_norm": 0.31963735818862915,
      "learning_rate": 1.808397287528108e-05,
      "loss": 0.5041,
      "step": 13124
    },
    {
      "epoch": 0.40318864620772277,
      "grad_norm": 0.3439933955669403,
      "learning_rate": 1.8083688390792997e-05,
      "loss": 0.5301,
      "step": 13125
    },
    {
      "epoch": 0.40321936534267194,
      "grad_norm": 0.3794308304786682,
      "learning_rate": 1.8083403887424894e-05,
      "loss": 0.5228,
      "step": 13126
    },
    {
      "epoch": 0.4032500844776211,
      "grad_norm": 0.3233562707901001,
      "learning_rate": 1.8083119365177437e-05,
      "loss": 0.5732,
      "step": 13127
    },
    {
      "epoch": 0.4032808036125703,
      "grad_norm": 0.40932291746139526,
      "learning_rate": 1.8082834824051292e-05,
      "loss": 0.5267,
      "step": 13128
    },
    {
      "epoch": 0.4033115227475194,
      "grad_norm": 0.3801185190677643,
      "learning_rate": 1.8082550264047124e-05,
      "loss": 0.5715,
      "step": 13129
    },
    {
      "epoch": 0.4033422418824686,
      "grad_norm": 0.30947035551071167,
      "learning_rate": 1.808226568516559e-05,
      "loss": 0.5258,
      "step": 13130
    },
    {
      "epoch": 0.40337296101741776,
      "grad_norm": 0.35159894824028015,
      "learning_rate": 1.8081981087407365e-05,
      "loss": 0.5422,
      "step": 13131
    },
    {
      "epoch": 0.4034036801523669,
      "grad_norm": 0.3544352352619171,
      "learning_rate": 1.8081696470773105e-05,
      "loss": 0.5649,
      "step": 13132
    },
    {
      "epoch": 0.40343439928731606,
      "grad_norm": 0.3628195524215698,
      "learning_rate": 1.808141183526348e-05,
      "loss": 0.5882,
      "step": 13133
    },
    {
      "epoch": 0.40346511842226523,
      "grad_norm": 0.3386306166648865,
      "learning_rate": 1.8081127180879152e-05,
      "loss": 0.5189,
      "step": 13134
    },
    {
      "epoch": 0.4034958375572144,
      "grad_norm": 0.31472495198249817,
      "learning_rate": 1.8080842507620787e-05,
      "loss": 0.5085,
      "step": 13135
    },
    {
      "epoch": 0.40352655669216353,
      "grad_norm": 0.3493591248989105,
      "learning_rate": 1.8080557815489054e-05,
      "loss": 0.5232,
      "step": 13136
    },
    {
      "epoch": 0.4035572758271127,
      "grad_norm": 0.29173317551612854,
      "learning_rate": 1.808027310448461e-05,
      "loss": 0.4888,
      "step": 13137
    },
    {
      "epoch": 0.4035879949620619,
      "grad_norm": 0.3375170826911926,
      "learning_rate": 1.8079988374608124e-05,
      "loss": 0.6249,
      "step": 13138
    },
    {
      "epoch": 0.40361871409701106,
      "grad_norm": 0.33546194434165955,
      "learning_rate": 1.807970362586026e-05,
      "loss": 0.531,
      "step": 13139
    },
    {
      "epoch": 0.4036494332319602,
      "grad_norm": 0.38059037923812866,
      "learning_rate": 1.8079418858241688e-05,
      "loss": 0.5872,
      "step": 13140
    },
    {
      "epoch": 0.40368015236690935,
      "grad_norm": 0.3443724811077118,
      "learning_rate": 1.8079134071753063e-05,
      "loss": 0.5038,
      "step": 13141
    },
    {
      "epoch": 0.4037108715018585,
      "grad_norm": 0.3287619650363922,
      "learning_rate": 1.807884926639506e-05,
      "loss": 0.5912,
      "step": 13142
    },
    {
      "epoch": 0.40374159063680765,
      "grad_norm": 0.33632469177246094,
      "learning_rate": 1.807856444216834e-05,
      "loss": 0.527,
      "step": 13143
    },
    {
      "epoch": 0.4037723097717568,
      "grad_norm": 0.3910737931728363,
      "learning_rate": 1.8078279599073568e-05,
      "loss": 0.6193,
      "step": 13144
    },
    {
      "epoch": 0.403803028906706,
      "grad_norm": 0.3915809690952301,
      "learning_rate": 1.8077994737111414e-05,
      "loss": 0.5735,
      "step": 13145
    },
    {
      "epoch": 0.40383374804165517,
      "grad_norm": 0.36712706089019775,
      "learning_rate": 1.8077709856282533e-05,
      "loss": 0.5165,
      "step": 13146
    },
    {
      "epoch": 0.4038644671766043,
      "grad_norm": 0.36657610535621643,
      "learning_rate": 1.8077424956587595e-05,
      "loss": 0.5609,
      "step": 13147
    },
    {
      "epoch": 0.40389518631155347,
      "grad_norm": 0.3505792021751404,
      "learning_rate": 1.8077140038027276e-05,
      "loss": 0.6915,
      "step": 13148
    },
    {
      "epoch": 0.40392590544650264,
      "grad_norm": 0.3357135057449341,
      "learning_rate": 1.8076855100602225e-05,
      "loss": 0.535,
      "step": 13149
    },
    {
      "epoch": 0.40395662458145176,
      "grad_norm": 0.3678404986858368,
      "learning_rate": 1.8076570144313117e-05,
      "loss": 0.5422,
      "step": 13150
    },
    {
      "epoch": 0.40398734371640094,
      "grad_norm": 0.3309127390384674,
      "learning_rate": 1.8076285169160615e-05,
      "loss": 0.5758,
      "step": 13151
    },
    {
      "epoch": 0.4040180628513501,
      "grad_norm": 0.6444262266159058,
      "learning_rate": 1.8076000175145388e-05,
      "loss": 0.6048,
      "step": 13152
    },
    {
      "epoch": 0.4040487819862993,
      "grad_norm": 0.34198930859565735,
      "learning_rate": 1.8075715162268092e-05,
      "loss": 0.5817,
      "step": 13153
    },
    {
      "epoch": 0.4040795011212484,
      "grad_norm": 0.41887524724006653,
      "learning_rate": 1.8075430130529405e-05,
      "loss": 0.5956,
      "step": 13154
    },
    {
      "epoch": 0.4041102202561976,
      "grad_norm": 0.34593990445137024,
      "learning_rate": 1.8075145079929982e-05,
      "loss": 0.6437,
      "step": 13155
    },
    {
      "epoch": 0.40414093939114676,
      "grad_norm": 0.3388037383556366,
      "learning_rate": 1.80748600104705e-05,
      "loss": 0.5456,
      "step": 13156
    },
    {
      "epoch": 0.4041716585260959,
      "grad_norm": 0.4230838119983673,
      "learning_rate": 1.8074574922151614e-05,
      "loss": 0.5796,
      "step": 13157
    },
    {
      "epoch": 0.40420237766104505,
      "grad_norm": 0.3585130274295807,
      "learning_rate": 1.8074289814973994e-05,
      "loss": 0.5915,
      "step": 13158
    },
    {
      "epoch": 0.40423309679599423,
      "grad_norm": 0.32813316583633423,
      "learning_rate": 1.8074004688938308e-05,
      "loss": 0.4987,
      "step": 13159
    },
    {
      "epoch": 0.4042638159309434,
      "grad_norm": 0.3809431195259094,
      "learning_rate": 1.807371954404522e-05,
      "loss": 0.6116,
      "step": 13160
    },
    {
      "epoch": 0.4042945350658925,
      "grad_norm": 0.38213789463043213,
      "learning_rate": 1.80734343802954e-05,
      "loss": 0.5793,
      "step": 13161
    },
    {
      "epoch": 0.4043252542008417,
      "grad_norm": 0.42334070801734924,
      "learning_rate": 1.8073149197689503e-05,
      "loss": 0.5628,
      "step": 13162
    },
    {
      "epoch": 0.4043559733357909,
      "grad_norm": 0.3533456027507782,
      "learning_rate": 1.8072863996228206e-05,
      "loss": 0.5361,
      "step": 13163
    },
    {
      "epoch": 0.40438669247074005,
      "grad_norm": 0.3332694470882416,
      "learning_rate": 1.807257877591217e-05,
      "loss": 0.5325,
      "step": 13164
    },
    {
      "epoch": 0.40441741160568917,
      "grad_norm": 0.35352230072021484,
      "learning_rate": 1.8072293536742065e-05,
      "loss": 0.5829,
      "step": 13165
    },
    {
      "epoch": 0.40444813074063835,
      "grad_norm": 0.35988345742225647,
      "learning_rate": 1.807200827871855e-05,
      "loss": 0.5713,
      "step": 13166
    },
    {
      "epoch": 0.4044788498755875,
      "grad_norm": 0.3468203842639923,
      "learning_rate": 1.80717230018423e-05,
      "loss": 0.5332,
      "step": 13167
    },
    {
      "epoch": 0.40450956901053664,
      "grad_norm": 0.3855845034122467,
      "learning_rate": 1.8071437706113976e-05,
      "loss": 0.5687,
      "step": 13168
    },
    {
      "epoch": 0.4045402881454858,
      "grad_norm": 0.36016398668289185,
      "learning_rate": 1.8071152391534247e-05,
      "loss": 0.5293,
      "step": 13169
    },
    {
      "epoch": 0.404571007280435,
      "grad_norm": 0.34679076075553894,
      "learning_rate": 1.8070867058103777e-05,
      "loss": 0.6441,
      "step": 13170
    },
    {
      "epoch": 0.40460172641538417,
      "grad_norm": 0.33859869837760925,
      "learning_rate": 1.807058170582323e-05,
      "loss": 0.6504,
      "step": 13171
    },
    {
      "epoch": 0.4046324455503333,
      "grad_norm": 0.33596837520599365,
      "learning_rate": 1.807029633469328e-05,
      "loss": 0.6154,
      "step": 13172
    },
    {
      "epoch": 0.40466316468528246,
      "grad_norm": 0.3812282085418701,
      "learning_rate": 1.8070010944714588e-05,
      "loss": 0.6115,
      "step": 13173
    },
    {
      "epoch": 0.40469388382023164,
      "grad_norm": 0.48419860005378723,
      "learning_rate": 1.806972553588782e-05,
      "loss": 0.603,
      "step": 13174
    },
    {
      "epoch": 0.40472460295518076,
      "grad_norm": 0.329866498708725,
      "learning_rate": 1.806944010821365e-05,
      "loss": 0.5379,
      "step": 13175
    },
    {
      "epoch": 0.40475532209012993,
      "grad_norm": 0.3842249810695648,
      "learning_rate": 1.8069154661692734e-05,
      "loss": 0.5509,
      "step": 13176
    },
    {
      "epoch": 0.4047860412250791,
      "grad_norm": 0.3235860764980316,
      "learning_rate": 1.8068869196325745e-05,
      "loss": 0.5332,
      "step": 13177
    },
    {
      "epoch": 0.4048167603600283,
      "grad_norm": 0.34518513083457947,
      "learning_rate": 1.8068583712113347e-05,
      "loss": 0.5758,
      "step": 13178
    },
    {
      "epoch": 0.4048474794949774,
      "grad_norm": 0.3528963625431061,
      "learning_rate": 1.806829820905621e-05,
      "loss": 0.6104,
      "step": 13179
    },
    {
      "epoch": 0.4048781986299266,
      "grad_norm": 0.40236401557922363,
      "learning_rate": 1.8068012687154997e-05,
      "loss": 0.5414,
      "step": 13180
    },
    {
      "epoch": 0.40490891776487575,
      "grad_norm": 0.33451542258262634,
      "learning_rate": 1.806772714641038e-05,
      "loss": 0.5945,
      "step": 13181
    },
    {
      "epoch": 0.40493963689982493,
      "grad_norm": 0.3600684106349945,
      "learning_rate": 1.806744158682302e-05,
      "loss": 0.5468,
      "step": 13182
    },
    {
      "epoch": 0.40497035603477405,
      "grad_norm": 0.6209030151367188,
      "learning_rate": 1.806715600839359e-05,
      "loss": 0.6892,
      "step": 13183
    },
    {
      "epoch": 0.4050010751697232,
      "grad_norm": 0.3815654516220093,
      "learning_rate": 1.806687041112275e-05,
      "loss": 0.5629,
      "step": 13184
    },
    {
      "epoch": 0.4050317943046724,
      "grad_norm": 0.3354444205760956,
      "learning_rate": 1.8066584795011176e-05,
      "loss": 0.5661,
      "step": 13185
    },
    {
      "epoch": 0.4050625134396215,
      "grad_norm": 0.33996134996414185,
      "learning_rate": 1.8066299160059527e-05,
      "loss": 0.5429,
      "step": 13186
    },
    {
      "epoch": 0.4050932325745707,
      "grad_norm": 0.3763646185398102,
      "learning_rate": 1.806601350626847e-05,
      "loss": 0.5809,
      "step": 13187
    },
    {
      "epoch": 0.40512395170951987,
      "grad_norm": 0.3652627170085907,
      "learning_rate": 1.806572783363868e-05,
      "loss": 0.5475,
      "step": 13188
    },
    {
      "epoch": 0.40515467084446904,
      "grad_norm": 0.3331427276134491,
      "learning_rate": 1.8065442142170817e-05,
      "loss": 0.5889,
      "step": 13189
    },
    {
      "epoch": 0.40518538997941816,
      "grad_norm": 0.38037094473838806,
      "learning_rate": 1.806515643186555e-05,
      "loss": 0.5615,
      "step": 13190
    },
    {
      "epoch": 0.40521610911436734,
      "grad_norm": 0.33297911286354065,
      "learning_rate": 1.8064870702723546e-05,
      "loss": 0.6163,
      "step": 13191
    },
    {
      "epoch": 0.4052468282493165,
      "grad_norm": 0.3599946200847626,
      "learning_rate": 1.8064584954745478e-05,
      "loss": 0.6525,
      "step": 13192
    },
    {
      "epoch": 0.40527754738426564,
      "grad_norm": 0.3462601602077484,
      "learning_rate": 1.8064299187932003e-05,
      "loss": 0.5379,
      "step": 13193
    },
    {
      "epoch": 0.4053082665192148,
      "grad_norm": 0.3725699186325073,
      "learning_rate": 1.8064013402283794e-05,
      "loss": 0.5853,
      "step": 13194
    },
    {
      "epoch": 0.405338985654164,
      "grad_norm": 0.42260104417800903,
      "learning_rate": 1.8063727597801524e-05,
      "loss": 0.5819,
      "step": 13195
    },
    {
      "epoch": 0.40536970478911316,
      "grad_norm": 0.33267802000045776,
      "learning_rate": 1.8063441774485852e-05,
      "loss": 0.5583,
      "step": 13196
    },
    {
      "epoch": 0.4054004239240623,
      "grad_norm": 0.3613864481449127,
      "learning_rate": 1.806315593233745e-05,
      "loss": 0.6477,
      "step": 13197
    },
    {
      "epoch": 0.40543114305901146,
      "grad_norm": 0.32758575677871704,
      "learning_rate": 1.806287007135698e-05,
      "loss": 0.5787,
      "step": 13198
    },
    {
      "epoch": 0.40546186219396063,
      "grad_norm": 0.3378181457519531,
      "learning_rate": 1.806258419154512e-05,
      "loss": 0.533,
      "step": 13199
    },
    {
      "epoch": 0.40549258132890975,
      "grad_norm": 0.38123273849487305,
      "learning_rate": 1.8062298292902525e-05,
      "loss": 0.5713,
      "step": 13200
    },
    {
      "epoch": 0.4055233004638589,
      "grad_norm": 0.35432228446006775,
      "learning_rate": 1.8062012375429875e-05,
      "loss": 0.5416,
      "step": 13201
    },
    {
      "epoch": 0.4055540195988081,
      "grad_norm": 0.40621235966682434,
      "learning_rate": 1.8061726439127828e-05,
      "loss": 0.6668,
      "step": 13202
    },
    {
      "epoch": 0.4055847387337573,
      "grad_norm": 0.39514318108558655,
      "learning_rate": 1.8061440483997058e-05,
      "loss": 0.6575,
      "step": 13203
    },
    {
      "epoch": 0.4056154578687064,
      "grad_norm": 0.3433992564678192,
      "learning_rate": 1.806115451003823e-05,
      "loss": 0.5665,
      "step": 13204
    },
    {
      "epoch": 0.4056461770036556,
      "grad_norm": 0.40002697706222534,
      "learning_rate": 1.8060868517252014e-05,
      "loss": 0.5396,
      "step": 13205
    },
    {
      "epoch": 0.40567689613860475,
      "grad_norm": 0.37661364674568176,
      "learning_rate": 1.806058250563907e-05,
      "loss": 0.5882,
      "step": 13206
    },
    {
      "epoch": 0.4057076152735539,
      "grad_norm": 0.35503414273262024,
      "learning_rate": 1.8060296475200082e-05,
      "loss": 0.5415,
      "step": 13207
    },
    {
      "epoch": 0.40573833440850304,
      "grad_norm": 0.3804701268672943,
      "learning_rate": 1.8060010425935702e-05,
      "loss": 0.6116,
      "step": 13208
    },
    {
      "epoch": 0.4057690535434522,
      "grad_norm": 0.3633003234863281,
      "learning_rate": 1.8059724357846607e-05,
      "loss": 0.6884,
      "step": 13209
    },
    {
      "epoch": 0.4057997726784014,
      "grad_norm": 0.3466537892818451,
      "learning_rate": 1.8059438270933465e-05,
      "loss": 0.537,
      "step": 13210
    },
    {
      "epoch": 0.4058304918133505,
      "grad_norm": 0.3750211000442505,
      "learning_rate": 1.805915216519694e-05,
      "loss": 0.5972,
      "step": 13211
    },
    {
      "epoch": 0.4058612109482997,
      "grad_norm": 0.3553035259246826,
      "learning_rate": 1.8058866040637704e-05,
      "loss": 0.5616,
      "step": 13212
    },
    {
      "epoch": 0.40589193008324886,
      "grad_norm": 0.33633631467819214,
      "learning_rate": 1.805857989725642e-05,
      "loss": 0.5278,
      "step": 13213
    },
    {
      "epoch": 0.40592264921819804,
      "grad_norm": 0.34713441133499146,
      "learning_rate": 1.8058293735053762e-05,
      "loss": 0.5607,
      "step": 13214
    },
    {
      "epoch": 0.40595336835314716,
      "grad_norm": 0.3524875342845917,
      "learning_rate": 1.8058007554030398e-05,
      "loss": 0.5122,
      "step": 13215
    },
    {
      "epoch": 0.40598408748809633,
      "grad_norm": 0.3367280662059784,
      "learning_rate": 1.8057721354186992e-05,
      "loss": 0.6163,
      "step": 13216
    },
    {
      "epoch": 0.4060148066230455,
      "grad_norm": 0.4530256688594818,
      "learning_rate": 1.8057435135524214e-05,
      "loss": 0.5602,
      "step": 13217
    },
    {
      "epoch": 0.40604552575799463,
      "grad_norm": 0.42189085483551025,
      "learning_rate": 1.8057148898042737e-05,
      "loss": 0.5712,
      "step": 13218
    },
    {
      "epoch": 0.4060762448929438,
      "grad_norm": 0.3343675136566162,
      "learning_rate": 1.8056862641743222e-05,
      "loss": 0.6297,
      "step": 13219
    },
    {
      "epoch": 0.406106964027893,
      "grad_norm": 0.3363408148288727,
      "learning_rate": 1.8056576366626343e-05,
      "loss": 0.5987,
      "step": 13220
    },
    {
      "epoch": 0.40613768316284216,
      "grad_norm": 0.3495791256427765,
      "learning_rate": 1.8056290072692772e-05,
      "loss": 0.6063,
      "step": 13221
    },
    {
      "epoch": 0.4061684022977913,
      "grad_norm": 0.33670029044151306,
      "learning_rate": 1.8056003759943167e-05,
      "loss": 0.5258,
      "step": 13222
    },
    {
      "epoch": 0.40619912143274045,
      "grad_norm": 0.3376031517982483,
      "learning_rate": 1.8055717428378203e-05,
      "loss": 0.6161,
      "step": 13223
    },
    {
      "epoch": 0.4062298405676896,
      "grad_norm": 0.3932039737701416,
      "learning_rate": 1.805543107799855e-05,
      "loss": 0.5609,
      "step": 13224
    },
    {
      "epoch": 0.40626055970263875,
      "grad_norm": 0.37044891715049744,
      "learning_rate": 1.8055144708804878e-05,
      "loss": 0.5876,
      "step": 13225
    },
    {
      "epoch": 0.4062912788375879,
      "grad_norm": 0.3538510501384735,
      "learning_rate": 1.805485832079785e-05,
      "loss": 0.6034,
      "step": 13226
    },
    {
      "epoch": 0.4063219979725371,
      "grad_norm": 0.32308897376060486,
      "learning_rate": 1.8054571913978138e-05,
      "loss": 0.5295,
      "step": 13227
    },
    {
      "epoch": 0.40635271710748627,
      "grad_norm": 0.34119364619255066,
      "learning_rate": 1.805428548834641e-05,
      "loss": 0.6046,
      "step": 13228
    },
    {
      "epoch": 0.4063834362424354,
      "grad_norm": 0.44343268871307373,
      "learning_rate": 1.8053999043903335e-05,
      "loss": 0.6128,
      "step": 13229
    },
    {
      "epoch": 0.40641415537738457,
      "grad_norm": 0.37357407808303833,
      "learning_rate": 1.8053712580649585e-05,
      "loss": 0.6185,
      "step": 13230
    },
    {
      "epoch": 0.40644487451233374,
      "grad_norm": 0.33704420924186707,
      "learning_rate": 1.8053426098585826e-05,
      "loss": 0.6191,
      "step": 13231
    },
    {
      "epoch": 0.4064755936472829,
      "grad_norm": 0.41252601146698,
      "learning_rate": 1.8053139597712728e-05,
      "loss": 0.635,
      "step": 13232
    },
    {
      "epoch": 0.40650631278223204,
      "grad_norm": 0.36471667885780334,
      "learning_rate": 1.805285307803096e-05,
      "loss": 0.5965,
      "step": 13233
    },
    {
      "epoch": 0.4065370319171812,
      "grad_norm": 0.35035908222198486,
      "learning_rate": 1.805256653954119e-05,
      "loss": 0.5594,
      "step": 13234
    },
    {
      "epoch": 0.4065677510521304,
      "grad_norm": 0.3217068016529083,
      "learning_rate": 1.805227998224409e-05,
      "loss": 0.5772,
      "step": 13235
    },
    {
      "epoch": 0.4065984701870795,
      "grad_norm": 0.6090555787086487,
      "learning_rate": 1.8051993406140328e-05,
      "loss": 0.6203,
      "step": 13236
    },
    {
      "epoch": 0.4066291893220287,
      "grad_norm": 0.3153019845485687,
      "learning_rate": 1.805170681123057e-05,
      "loss": 0.571,
      "step": 13237
    },
    {
      "epoch": 0.40665990845697786,
      "grad_norm": 0.3324664235115051,
      "learning_rate": 1.8051420197515496e-05,
      "loss": 0.5393,
      "step": 13238
    },
    {
      "epoch": 0.40669062759192703,
      "grad_norm": 0.3292078673839569,
      "learning_rate": 1.805113356499576e-05,
      "loss": 0.6137,
      "step": 13239
    },
    {
      "epoch": 0.40672134672687615,
      "grad_norm": 0.3431033790111542,
      "learning_rate": 1.805084691367204e-05,
      "loss": 0.5802,
      "step": 13240
    },
    {
      "epoch": 0.40675206586182533,
      "grad_norm": 0.35035669803619385,
      "learning_rate": 1.805056024354501e-05,
      "loss": 0.4901,
      "step": 13241
    },
    {
      "epoch": 0.4067827849967745,
      "grad_norm": 0.3236664831638336,
      "learning_rate": 1.805027355461533e-05,
      "loss": 0.4737,
      "step": 13242
    },
    {
      "epoch": 0.4068135041317236,
      "grad_norm": 0.39731061458587646,
      "learning_rate": 1.8049986846883673e-05,
      "loss": 0.5591,
      "step": 13243
    },
    {
      "epoch": 0.4068442232666728,
      "grad_norm": 0.3950156569480896,
      "learning_rate": 1.804970012035071e-05,
      "loss": 0.5975,
      "step": 13244
    },
    {
      "epoch": 0.406874942401622,
      "grad_norm": 0.3723045885562897,
      "learning_rate": 1.8049413375017115e-05,
      "loss": 0.626,
      "step": 13245
    },
    {
      "epoch": 0.40690566153657115,
      "grad_norm": 0.3053271770477295,
      "learning_rate": 1.8049126610883547e-05,
      "loss": 0.558,
      "step": 13246
    },
    {
      "epoch": 0.40693638067152027,
      "grad_norm": 0.34489768743515015,
      "learning_rate": 1.8048839827950687e-05,
      "loss": 0.6384,
      "step": 13247
    },
    {
      "epoch": 0.40696709980646945,
      "grad_norm": 0.3326824903488159,
      "learning_rate": 1.8048553026219197e-05,
      "loss": 0.6656,
      "step": 13248
    },
    {
      "epoch": 0.4069978189414186,
      "grad_norm": 0.3346917927265167,
      "learning_rate": 1.804826620568975e-05,
      "loss": 0.5154,
      "step": 13249
    },
    {
      "epoch": 0.4070285380763678,
      "grad_norm": 0.3566778898239136,
      "learning_rate": 1.804797936636301e-05,
      "loss": 0.4848,
      "step": 13250
    },
    {
      "epoch": 0.4070592572113169,
      "grad_norm": 0.37307843565940857,
      "learning_rate": 1.8047692508239658e-05,
      "loss": 0.6664,
      "step": 13251
    },
    {
      "epoch": 0.4070899763462661,
      "grad_norm": 0.3397893011569977,
      "learning_rate": 1.8047405631320357e-05,
      "loss": 0.656,
      "step": 13252
    },
    {
      "epoch": 0.40712069548121527,
      "grad_norm": 0.34122607111930847,
      "learning_rate": 1.8047118735605775e-05,
      "loss": 0.5509,
      "step": 13253
    },
    {
      "epoch": 0.4071514146161644,
      "grad_norm": 0.3375268876552582,
      "learning_rate": 1.8046831821096588e-05,
      "loss": 0.5689,
      "step": 13254
    },
    {
      "epoch": 0.40718213375111356,
      "grad_norm": 0.335317999124527,
      "learning_rate": 1.804654488779346e-05,
      "loss": 0.5572,
      "step": 13255
    },
    {
      "epoch": 0.40721285288606274,
      "grad_norm": 0.31614312529563904,
      "learning_rate": 1.8046257935697072e-05,
      "loss": 0.5791,
      "step": 13256
    },
    {
      "epoch": 0.4072435720210119,
      "grad_norm": 0.37284180521965027,
      "learning_rate": 1.8045970964808082e-05,
      "loss": 0.5955,
      "step": 13257
    },
    {
      "epoch": 0.40727429115596103,
      "grad_norm": 0.3438921272754669,
      "learning_rate": 1.8045683975127164e-05,
      "loss": 0.5316,
      "step": 13258
    },
    {
      "epoch": 0.4073050102909102,
      "grad_norm": 0.30290886759757996,
      "learning_rate": 1.804539696665499e-05,
      "loss": 0.4196,
      "step": 13259
    },
    {
      "epoch": 0.4073357294258594,
      "grad_norm": 0.33215951919555664,
      "learning_rate": 1.8045109939392233e-05,
      "loss": 0.5516,
      "step": 13260
    },
    {
      "epoch": 0.4073664485608085,
      "grad_norm": 0.32777801156044006,
      "learning_rate": 1.8044822893339555e-05,
      "loss": 0.5778,
      "step": 13261
    },
    {
      "epoch": 0.4073971676957577,
      "grad_norm": 0.41430842876434326,
      "learning_rate": 1.8044535828497632e-05,
      "loss": 0.5779,
      "step": 13262
    },
    {
      "epoch": 0.40742788683070685,
      "grad_norm": 0.34821897745132446,
      "learning_rate": 1.8044248744867134e-05,
      "loss": 0.5796,
      "step": 13263
    },
    {
      "epoch": 0.40745860596565603,
      "grad_norm": 0.3759816288948059,
      "learning_rate": 1.804396164244873e-05,
      "loss": 0.6099,
      "step": 13264
    },
    {
      "epoch": 0.40748932510060515,
      "grad_norm": 0.33857786655426025,
      "learning_rate": 1.8043674521243097e-05,
      "loss": 0.532,
      "step": 13265
    },
    {
      "epoch": 0.4075200442355543,
      "grad_norm": 0.37014079093933105,
      "learning_rate": 1.8043387381250893e-05,
      "loss": 0.6462,
      "step": 13266
    },
    {
      "epoch": 0.4075507633705035,
      "grad_norm": 0.40906351804733276,
      "learning_rate": 1.8043100222472804e-05,
      "loss": 0.5497,
      "step": 13267
    },
    {
      "epoch": 0.4075814825054526,
      "grad_norm": 0.3239123523235321,
      "learning_rate": 1.8042813044909485e-05,
      "loss": 0.5066,
      "step": 13268
    },
    {
      "epoch": 0.4076122016404018,
      "grad_norm": 0.38072434067726135,
      "learning_rate": 1.804252584856162e-05,
      "loss": 0.5961,
      "step": 13269
    },
    {
      "epoch": 0.40764292077535097,
      "grad_norm": 0.3282376229763031,
      "learning_rate": 1.804223863342987e-05,
      "loss": 0.5276,
      "step": 13270
    },
    {
      "epoch": 0.40767363991030015,
      "grad_norm": 0.31671142578125,
      "learning_rate": 1.8041951399514915e-05,
      "loss": 0.6033,
      "step": 13271
    },
    {
      "epoch": 0.40770435904524926,
      "grad_norm": 0.356025755405426,
      "learning_rate": 1.8041664146817415e-05,
      "loss": 0.5688,
      "step": 13272
    },
    {
      "epoch": 0.40773507818019844,
      "grad_norm": 0.3766225576400757,
      "learning_rate": 1.804137687533805e-05,
      "loss": 0.5852,
      "step": 13273
    },
    {
      "epoch": 0.4077657973151476,
      "grad_norm": 0.33130133152008057,
      "learning_rate": 1.804108958507749e-05,
      "loss": 0.5311,
      "step": 13274
    },
    {
      "epoch": 0.4077965164500968,
      "grad_norm": 0.34380489587783813,
      "learning_rate": 1.80408022760364e-05,
      "loss": 0.5969,
      "step": 13275
    },
    {
      "epoch": 0.4078272355850459,
      "grad_norm": 0.3910300135612488,
      "learning_rate": 1.8040514948215457e-05,
      "loss": 0.5807,
      "step": 13276
    },
    {
      "epoch": 0.4078579547199951,
      "grad_norm": 0.34354084730148315,
      "learning_rate": 1.8040227601615326e-05,
      "loss": 0.5621,
      "step": 13277
    },
    {
      "epoch": 0.40788867385494426,
      "grad_norm": 0.36970123648643494,
      "learning_rate": 1.803994023623669e-05,
      "loss": 0.7063,
      "step": 13278
    },
    {
      "epoch": 0.4079193929898934,
      "grad_norm": 0.36374717950820923,
      "learning_rate": 1.80396528520802e-05,
      "loss": 0.584,
      "step": 13279
    },
    {
      "epoch": 0.40795011212484256,
      "grad_norm": 0.35005778074264526,
      "learning_rate": 1.8039365449146552e-05,
      "loss": 0.5467,
      "step": 13280
    },
    {
      "epoch": 0.40798083125979173,
      "grad_norm": 0.41552814841270447,
      "learning_rate": 1.8039078027436398e-05,
      "loss": 0.5856,
      "step": 13281
    },
    {
      "epoch": 0.4080115503947409,
      "grad_norm": 0.3755143880844116,
      "learning_rate": 1.8038790586950417e-05,
      "loss": 0.4838,
      "step": 13282
    },
    {
      "epoch": 0.40804226952969,
      "grad_norm": 0.3313836455345154,
      "learning_rate": 1.8038503127689277e-05,
      "loss": 0.5163,
      "step": 13283
    },
    {
      "epoch": 0.4080729886646392,
      "grad_norm": 0.4111133813858032,
      "learning_rate": 1.8038215649653654e-05,
      "loss": 0.5678,
      "step": 13284
    },
    {
      "epoch": 0.4081037077995884,
      "grad_norm": 0.35680222511291504,
      "learning_rate": 1.8037928152844214e-05,
      "loss": 0.5383,
      "step": 13285
    },
    {
      "epoch": 0.4081344269345375,
      "grad_norm": 0.3705424666404724,
      "learning_rate": 1.8037640637261634e-05,
      "loss": 0.6008,
      "step": 13286
    },
    {
      "epoch": 0.4081651460694867,
      "grad_norm": 0.3411761224269867,
      "learning_rate": 1.8037353102906584e-05,
      "loss": 0.5767,
      "step": 13287
    },
    {
      "epoch": 0.40819586520443585,
      "grad_norm": 0.3526240587234497,
      "learning_rate": 1.8037065549779733e-05,
      "loss": 0.5595,
      "step": 13288
    },
    {
      "epoch": 0.408226584339385,
      "grad_norm": 0.3399559557437897,
      "learning_rate": 1.8036777977881754e-05,
      "loss": 0.5718,
      "step": 13289
    },
    {
      "epoch": 0.40825730347433414,
      "grad_norm": 0.32839441299438477,
      "learning_rate": 1.8036490387213318e-05,
      "loss": 0.5579,
      "step": 13290
    },
    {
      "epoch": 0.4082880226092833,
      "grad_norm": 0.3611079156398773,
      "learning_rate": 1.80362027777751e-05,
      "loss": 0.5418,
      "step": 13291
    },
    {
      "epoch": 0.4083187417442325,
      "grad_norm": 0.34611862897872925,
      "learning_rate": 1.8035915149567766e-05,
      "loss": 0.5117,
      "step": 13292
    },
    {
      "epoch": 0.40834946087918167,
      "grad_norm": 0.3515903651714325,
      "learning_rate": 1.803562750259199e-05,
      "loss": 0.5453,
      "step": 13293
    },
    {
      "epoch": 0.4083801800141308,
      "grad_norm": 0.3842042088508606,
      "learning_rate": 1.803533983684845e-05,
      "loss": 0.6688,
      "step": 13294
    },
    {
      "epoch": 0.40841089914907996,
      "grad_norm": 0.36423954367637634,
      "learning_rate": 1.803505215233781e-05,
      "loss": 0.5455,
      "step": 13295
    },
    {
      "epoch": 0.40844161828402914,
      "grad_norm": 0.3952051103115082,
      "learning_rate": 1.8034764449060745e-05,
      "loss": 0.5482,
      "step": 13296
    },
    {
      "epoch": 0.40847233741897826,
      "grad_norm": 0.5053848624229431,
      "learning_rate": 1.8034476727017926e-05,
      "loss": 0.5751,
      "step": 13297
    },
    {
      "epoch": 0.40850305655392743,
      "grad_norm": 0.33920490741729736,
      "learning_rate": 1.8034188986210023e-05,
      "loss": 0.5279,
      "step": 13298
    },
    {
      "epoch": 0.4085337756888766,
      "grad_norm": 0.38294529914855957,
      "learning_rate": 1.8033901226637715e-05,
      "loss": 0.4926,
      "step": 13299
    },
    {
      "epoch": 0.4085644948238258,
      "grad_norm": 0.34102192521095276,
      "learning_rate": 1.803361344830167e-05,
      "loss": 0.6414,
      "step": 13300
    },
    {
      "epoch": 0.4085952139587749,
      "grad_norm": 0.3494352102279663,
      "learning_rate": 1.8033325651202552e-05,
      "loss": 0.6115,
      "step": 13301
    },
    {
      "epoch": 0.4086259330937241,
      "grad_norm": 1.5121268033981323,
      "learning_rate": 1.803303783534105e-05,
      "loss": 0.5572,
      "step": 13302
    },
    {
      "epoch": 0.40865665222867326,
      "grad_norm": 0.42827755212783813,
      "learning_rate": 1.803275000071782e-05,
      "loss": 0.5825,
      "step": 13303
    },
    {
      "epoch": 0.4086873713636224,
      "grad_norm": 0.3109184205532074,
      "learning_rate": 1.8032462147333544e-05,
      "loss": 0.5441,
      "step": 13304
    },
    {
      "epoch": 0.40871809049857155,
      "grad_norm": 0.34212058782577515,
      "learning_rate": 1.8032174275188894e-05,
      "loss": 0.5435,
      "step": 13305
    },
    {
      "epoch": 0.4087488096335207,
      "grad_norm": 0.3654639720916748,
      "learning_rate": 1.8031886384284538e-05,
      "loss": 0.6191,
      "step": 13306
    },
    {
      "epoch": 0.4087795287684699,
      "grad_norm": 0.3273680508136749,
      "learning_rate": 1.8031598474621153e-05,
      "loss": 0.575,
      "step": 13307
    },
    {
      "epoch": 0.408810247903419,
      "grad_norm": 0.3898259699344635,
      "learning_rate": 1.8031310546199406e-05,
      "loss": 0.8062,
      "step": 13308
    },
    {
      "epoch": 0.4088409670383682,
      "grad_norm": 0.6514219641685486,
      "learning_rate": 1.8031022599019973e-05,
      "loss": 0.6056,
      "step": 13309
    },
    {
      "epoch": 0.4088716861733174,
      "grad_norm": 0.35000869631767273,
      "learning_rate": 1.8030734633083524e-05,
      "loss": 0.5175,
      "step": 13310
    },
    {
      "epoch": 0.4089024053082665,
      "grad_norm": 0.3438626229763031,
      "learning_rate": 1.8030446648390736e-05,
      "loss": 0.5504,
      "step": 13311
    },
    {
      "epoch": 0.40893312444321567,
      "grad_norm": 0.35130393505096436,
      "learning_rate": 1.8030158644942278e-05,
      "loss": 0.6448,
      "step": 13312
    },
    {
      "epoch": 0.40896384357816484,
      "grad_norm": 0.6816607713699341,
      "learning_rate": 1.8029870622738822e-05,
      "loss": 0.5428,
      "step": 13313
    },
    {
      "epoch": 0.408994562713114,
      "grad_norm": 0.7303506135940552,
      "learning_rate": 1.8029582581781048e-05,
      "loss": 0.5898,
      "step": 13314
    },
    {
      "epoch": 0.40902528184806314,
      "grad_norm": 0.3346390128135681,
      "learning_rate": 1.8029294522069615e-05,
      "loss": 0.5541,
      "step": 13315
    },
    {
      "epoch": 0.4090560009830123,
      "grad_norm": 0.33808669447898865,
      "learning_rate": 1.802900644360521e-05,
      "loss": 0.6048,
      "step": 13316
    },
    {
      "epoch": 0.4090867201179615,
      "grad_norm": 0.4064679741859436,
      "learning_rate": 1.8028718346388498e-05,
      "loss": 0.6017,
      "step": 13317
    },
    {
      "epoch": 0.40911743925291066,
      "grad_norm": 0.863000214099884,
      "learning_rate": 1.8028430230420152e-05,
      "loss": 0.6029,
      "step": 13318
    },
    {
      "epoch": 0.4091481583878598,
      "grad_norm": 0.42155924439430237,
      "learning_rate": 1.8028142095700848e-05,
      "loss": 0.6161,
      "step": 13319
    },
    {
      "epoch": 0.40917887752280896,
      "grad_norm": 0.3434848487377167,
      "learning_rate": 1.802785394223126e-05,
      "loss": 0.5664,
      "step": 13320
    },
    {
      "epoch": 0.40920959665775813,
      "grad_norm": 0.3420056700706482,
      "learning_rate": 1.8027565770012056e-05,
      "loss": 0.5686,
      "step": 13321
    },
    {
      "epoch": 0.40924031579270725,
      "grad_norm": 0.3669591546058655,
      "learning_rate": 1.802727757904391e-05,
      "loss": 0.5722,
      "step": 13322
    },
    {
      "epoch": 0.40927103492765643,
      "grad_norm": 0.3542930781841278,
      "learning_rate": 1.8026989369327495e-05,
      "loss": 0.6528,
      "step": 13323
    },
    {
      "epoch": 0.4093017540626056,
      "grad_norm": 0.3773088753223419,
      "learning_rate": 1.802670114086349e-05,
      "loss": 0.5931,
      "step": 13324
    },
    {
      "epoch": 0.4093324731975548,
      "grad_norm": 0.34135720133781433,
      "learning_rate": 1.8026412893652563e-05,
      "loss": 0.5468,
      "step": 13325
    },
    {
      "epoch": 0.4093631923325039,
      "grad_norm": 0.4171135425567627,
      "learning_rate": 1.8026124627695388e-05,
      "loss": 0.6527,
      "step": 13326
    },
    {
      "epoch": 0.4093939114674531,
      "grad_norm": 0.31659573316574097,
      "learning_rate": 1.8025836342992637e-05,
      "loss": 0.5751,
      "step": 13327
    },
    {
      "epoch": 0.40942463060240225,
      "grad_norm": 0.3256969153881073,
      "learning_rate": 1.8025548039544987e-05,
      "loss": 0.5755,
      "step": 13328
    },
    {
      "epoch": 0.40945534973735137,
      "grad_norm": 0.35562482476234436,
      "learning_rate": 1.8025259717353107e-05,
      "loss": 0.5561,
      "step": 13329
    },
    {
      "epoch": 0.40948606887230055,
      "grad_norm": 0.34955406188964844,
      "learning_rate": 1.8024971376417673e-05,
      "loss": 0.6456,
      "step": 13330
    },
    {
      "epoch": 0.4095167880072497,
      "grad_norm": 0.34488391876220703,
      "learning_rate": 1.802468301673936e-05,
      "loss": 0.5838,
      "step": 13331
    },
    {
      "epoch": 0.4095475071421989,
      "grad_norm": 0.3290219306945801,
      "learning_rate": 1.8024394638318835e-05,
      "loss": 0.5632,
      "step": 13332
    },
    {
      "epoch": 0.409578226277148,
      "grad_norm": 0.32421875,
      "learning_rate": 1.802410624115678e-05,
      "loss": 0.5589,
      "step": 13333
    },
    {
      "epoch": 0.4096089454120972,
      "grad_norm": 0.34710243344306946,
      "learning_rate": 1.8023817825253865e-05,
      "loss": 0.6044,
      "step": 13334
    },
    {
      "epoch": 0.40963966454704637,
      "grad_norm": 0.3590364456176758,
      "learning_rate": 1.8023529390610762e-05,
      "loss": 0.6611,
      "step": 13335
    },
    {
      "epoch": 0.40967038368199554,
      "grad_norm": 0.36385223269462585,
      "learning_rate": 1.8023240937228143e-05,
      "loss": 0.5473,
      "step": 13336
    },
    {
      "epoch": 0.40970110281694466,
      "grad_norm": 0.3431869149208069,
      "learning_rate": 1.8022952465106685e-05,
      "loss": 0.5697,
      "step": 13337
    },
    {
      "epoch": 0.40973182195189384,
      "grad_norm": 0.3227713406085968,
      "learning_rate": 1.8022663974247062e-05,
      "loss": 0.5742,
      "step": 13338
    },
    {
      "epoch": 0.409762541086843,
      "grad_norm": 0.3400222957134247,
      "learning_rate": 1.802237546464995e-05,
      "loss": 0.5843,
      "step": 13339
    },
    {
      "epoch": 0.40979326022179213,
      "grad_norm": 0.3274899423122406,
      "learning_rate": 1.8022086936316013e-05,
      "loss": 0.6178,
      "step": 13340
    },
    {
      "epoch": 0.4098239793567413,
      "grad_norm": 0.3146752119064331,
      "learning_rate": 1.8021798389245936e-05,
      "loss": 0.5623,
      "step": 13341
    },
    {
      "epoch": 0.4098546984916905,
      "grad_norm": 0.35686931014060974,
      "learning_rate": 1.8021509823440394e-05,
      "loss": 0.5595,
      "step": 13342
    },
    {
      "epoch": 0.40988541762663966,
      "grad_norm": 0.406803697347641,
      "learning_rate": 1.802122123890005e-05,
      "loss": 0.6071,
      "step": 13343
    },
    {
      "epoch": 0.4099161367615888,
      "grad_norm": 0.44267651438713074,
      "learning_rate": 1.8020932635625582e-05,
      "loss": 0.6204,
      "step": 13344
    },
    {
      "epoch": 0.40994685589653795,
      "grad_norm": 0.35030630230903625,
      "learning_rate": 1.8020644013617666e-05,
      "loss": 0.5992,
      "step": 13345
    },
    {
      "epoch": 0.40997757503148713,
      "grad_norm": 0.5320367217063904,
      "learning_rate": 1.8020355372876976e-05,
      "loss": 0.5301,
      "step": 13346
    },
    {
      "epoch": 0.41000829416643625,
      "grad_norm": 0.38668292760849,
      "learning_rate": 1.802006671340419e-05,
      "loss": 0.5461,
      "step": 13347
    },
    {
      "epoch": 0.4100390133013854,
      "grad_norm": 0.35920238494873047,
      "learning_rate": 1.801977803519997e-05,
      "loss": 0.552,
      "step": 13348
    },
    {
      "epoch": 0.4100697324363346,
      "grad_norm": 0.33744069933891296,
      "learning_rate": 1.8019489338265005e-05,
      "loss": 0.5512,
      "step": 13349
    },
    {
      "epoch": 0.4101004515712838,
      "grad_norm": 0.4004199504852295,
      "learning_rate": 1.8019200622599965e-05,
      "loss": 0.6286,
      "step": 13350
    },
    {
      "epoch": 0.4101311707062329,
      "grad_norm": 0.4518113136291504,
      "learning_rate": 1.8018911888205516e-05,
      "loss": 0.4756,
      "step": 13351
    },
    {
      "epoch": 0.41016188984118207,
      "grad_norm": 0.36341455578804016,
      "learning_rate": 1.801862313508234e-05,
      "loss": 0.6375,
      "step": 13352
    },
    {
      "epoch": 0.41019260897613125,
      "grad_norm": 0.3458767235279083,
      "learning_rate": 1.801833436323111e-05,
      "loss": 0.5817,
      "step": 13353
    },
    {
      "epoch": 0.41022332811108037,
      "grad_norm": 0.3540935218334198,
      "learning_rate": 1.80180455726525e-05,
      "loss": 0.6826,
      "step": 13354
    },
    {
      "epoch": 0.41025404724602954,
      "grad_norm": 0.36973273754119873,
      "learning_rate": 1.801775676334718e-05,
      "loss": 0.5811,
      "step": 13355
    },
    {
      "epoch": 0.4102847663809787,
      "grad_norm": 0.34720316529273987,
      "learning_rate": 1.801746793531584e-05,
      "loss": 0.5031,
      "step": 13356
    },
    {
      "epoch": 0.4103154855159279,
      "grad_norm": 0.35198694467544556,
      "learning_rate": 1.8017179088559135e-05,
      "loss": 0.6159,
      "step": 13357
    },
    {
      "epoch": 0.410346204650877,
      "grad_norm": 0.35134315490722656,
      "learning_rate": 1.801689022307775e-05,
      "loss": 0.6007,
      "step": 13358
    },
    {
      "epoch": 0.4103769237858262,
      "grad_norm": 0.3622816205024719,
      "learning_rate": 1.801660133887236e-05,
      "loss": 0.5915,
      "step": 13359
    },
    {
      "epoch": 0.41040764292077536,
      "grad_norm": 0.3385726809501648,
      "learning_rate": 1.8016312435943638e-05,
      "loss": 0.633,
      "step": 13360
    },
    {
      "epoch": 0.41043836205572454,
      "grad_norm": 0.3584575653076172,
      "learning_rate": 1.8016023514292257e-05,
      "loss": 0.5789,
      "step": 13361
    },
    {
      "epoch": 0.41046908119067366,
      "grad_norm": 0.3935995101928711,
      "learning_rate": 1.8015734573918894e-05,
      "loss": 0.6129,
      "step": 13362
    },
    {
      "epoch": 0.41049980032562283,
      "grad_norm": 0.3636106550693512,
      "learning_rate": 1.8015445614824218e-05,
      "loss": 0.6219,
      "step": 13363
    },
    {
      "epoch": 0.410530519460572,
      "grad_norm": 0.3081815540790558,
      "learning_rate": 1.8015156637008915e-05,
      "loss": 0.5358,
      "step": 13364
    },
    {
      "epoch": 0.4105612385955211,
      "grad_norm": 0.3335350453853607,
      "learning_rate": 1.8014867640473652e-05,
      "loss": 0.4897,
      "step": 13365
    },
    {
      "epoch": 0.4105919577304703,
      "grad_norm": 0.378714382648468,
      "learning_rate": 1.8014578625219106e-05,
      "loss": 0.5607,
      "step": 13366
    },
    {
      "epoch": 0.4106226768654195,
      "grad_norm": 0.37269750237464905,
      "learning_rate": 1.801428959124595e-05,
      "loss": 0.5511,
      "step": 13367
    },
    {
      "epoch": 0.41065339600036865,
      "grad_norm": 0.3774247169494629,
      "learning_rate": 1.8014000538554865e-05,
      "loss": 0.5782,
      "step": 13368
    },
    {
      "epoch": 0.4106841151353178,
      "grad_norm": 0.33441925048828125,
      "learning_rate": 1.801371146714652e-05,
      "loss": 0.5417,
      "step": 13369
    },
    {
      "epoch": 0.41071483427026695,
      "grad_norm": 0.3476141393184662,
      "learning_rate": 1.801342237702159e-05,
      "loss": 0.5688,
      "step": 13370
    },
    {
      "epoch": 0.4107455534052161,
      "grad_norm": 0.41763246059417725,
      "learning_rate": 1.8013133268180757e-05,
      "loss": 0.6408,
      "step": 13371
    },
    {
      "epoch": 0.41077627254016524,
      "grad_norm": 0.33434662222862244,
      "learning_rate": 1.801284414062469e-05,
      "loss": 0.555,
      "step": 13372
    },
    {
      "epoch": 0.4108069916751144,
      "grad_norm": 0.9210301041603088,
      "learning_rate": 1.8012554994354062e-05,
      "loss": 0.7642,
      "step": 13373
    },
    {
      "epoch": 0.4108377108100636,
      "grad_norm": 0.34701699018478394,
      "learning_rate": 1.8012265829369554e-05,
      "loss": 0.6015,
      "step": 13374
    },
    {
      "epoch": 0.41086842994501277,
      "grad_norm": 0.3850666880607605,
      "learning_rate": 1.8011976645671844e-05,
      "loss": 0.5254,
      "step": 13375
    },
    {
      "epoch": 0.4108991490799619,
      "grad_norm": 0.35702842473983765,
      "learning_rate": 1.8011687443261598e-05,
      "loss": 0.5641,
      "step": 13376
    },
    {
      "epoch": 0.41092986821491106,
      "grad_norm": 0.35126301646232605,
      "learning_rate": 1.80113982221395e-05,
      "loss": 0.5878,
      "step": 13377
    },
    {
      "epoch": 0.41096058734986024,
      "grad_norm": 0.36517664790153503,
      "learning_rate": 1.801110898230622e-05,
      "loss": 0.5665,
      "step": 13378
    },
    {
      "epoch": 0.4109913064848094,
      "grad_norm": 0.5095042586326599,
      "learning_rate": 1.8010819723762432e-05,
      "loss": 0.6057,
      "step": 13379
    },
    {
      "epoch": 0.41102202561975854,
      "grad_norm": 0.3582266867160797,
      "learning_rate": 1.801053044650882e-05,
      "loss": 0.5922,
      "step": 13380
    },
    {
      "epoch": 0.4110527447547077,
      "grad_norm": 0.3832608163356781,
      "learning_rate": 1.8010241150546054e-05,
      "loss": 0.5406,
      "step": 13381
    },
    {
      "epoch": 0.4110834638896569,
      "grad_norm": 0.3821364939212799,
      "learning_rate": 1.8009951835874807e-05,
      "loss": 0.5684,
      "step": 13382
    },
    {
      "epoch": 0.411114183024606,
      "grad_norm": 0.5626112222671509,
      "learning_rate": 1.800966250249576e-05,
      "loss": 0.6063,
      "step": 13383
    },
    {
      "epoch": 0.4111449021595552,
      "grad_norm": 0.354559063911438,
      "learning_rate": 1.800937315040959e-05,
      "loss": 0.5979,
      "step": 13384
    },
    {
      "epoch": 0.41117562129450436,
      "grad_norm": 0.3662196695804596,
      "learning_rate": 1.800908377961697e-05,
      "loss": 0.5996,
      "step": 13385
    },
    {
      "epoch": 0.41120634042945353,
      "grad_norm": 0.4314398169517517,
      "learning_rate": 1.800879439011857e-05,
      "loss": 0.6215,
      "step": 13386
    },
    {
      "epoch": 0.41123705956440265,
      "grad_norm": 0.3626413941383362,
      "learning_rate": 1.8008504981915073e-05,
      "loss": 0.5881,
      "step": 13387
    },
    {
      "epoch": 0.4112677786993518,
      "grad_norm": 0.3779001235961914,
      "learning_rate": 1.8008215555007157e-05,
      "loss": 0.5951,
      "step": 13388
    },
    {
      "epoch": 0.411298497834301,
      "grad_norm": 0.3261342942714691,
      "learning_rate": 1.8007926109395493e-05,
      "loss": 0.5862,
      "step": 13389
    },
    {
      "epoch": 0.4113292169692501,
      "grad_norm": 0.4207363724708557,
      "learning_rate": 1.8007636645080755e-05,
      "loss": 0.594,
      "step": 13390
    },
    {
      "epoch": 0.4113599361041993,
      "grad_norm": 0.3282261788845062,
      "learning_rate": 1.8007347162063625e-05,
      "loss": 0.5531,
      "step": 13391
    },
    {
      "epoch": 0.4113906552391485,
      "grad_norm": 0.31070226430892944,
      "learning_rate": 1.8007057660344776e-05,
      "loss": 0.5048,
      "step": 13392
    },
    {
      "epoch": 0.41142137437409765,
      "grad_norm": 0.3748149275779724,
      "learning_rate": 1.8006768139924884e-05,
      "loss": 0.587,
      "step": 13393
    },
    {
      "epoch": 0.41145209350904677,
      "grad_norm": 0.3548424541950226,
      "learning_rate": 1.8006478600804628e-05,
      "loss": 0.5898,
      "step": 13394
    },
    {
      "epoch": 0.41148281264399594,
      "grad_norm": 0.3877282738685608,
      "learning_rate": 1.800618904298468e-05,
      "loss": 0.5201,
      "step": 13395
    },
    {
      "epoch": 0.4115135317789451,
      "grad_norm": 0.35842517018318176,
      "learning_rate": 1.8005899466465717e-05,
      "loss": 0.6257,
      "step": 13396
    },
    {
      "epoch": 0.41154425091389424,
      "grad_norm": 0.34570077061653137,
      "learning_rate": 1.800560987124842e-05,
      "loss": 0.5621,
      "step": 13397
    },
    {
      "epoch": 0.4115749700488434,
      "grad_norm": 0.35815566778182983,
      "learning_rate": 1.8005320257333458e-05,
      "loss": 0.5763,
      "step": 13398
    },
    {
      "epoch": 0.4116056891837926,
      "grad_norm": 0.401619553565979,
      "learning_rate": 1.8005030624721517e-05,
      "loss": 0.6326,
      "step": 13399
    },
    {
      "epoch": 0.41163640831874176,
      "grad_norm": 0.366493821144104,
      "learning_rate": 1.800474097341326e-05,
      "loss": 0.5188,
      "step": 13400
    },
    {
      "epoch": 0.4116671274536909,
      "grad_norm": 0.32717084884643555,
      "learning_rate": 1.800445130340938e-05,
      "loss": 0.5047,
      "step": 13401
    },
    {
      "epoch": 0.41169784658864006,
      "grad_norm": 0.34303492307662964,
      "learning_rate": 1.800416161471054e-05,
      "loss": 0.5046,
      "step": 13402
    },
    {
      "epoch": 0.41172856572358923,
      "grad_norm": 0.38064152002334595,
      "learning_rate": 1.8003871907317423e-05,
      "loss": 0.5602,
      "step": 13403
    },
    {
      "epoch": 0.4117592848585384,
      "grad_norm": 0.34689226746559143,
      "learning_rate": 1.8003582181230704e-05,
      "loss": 0.5749,
      "step": 13404
    },
    {
      "epoch": 0.41179000399348753,
      "grad_norm": 0.38675081729888916,
      "learning_rate": 1.8003292436451062e-05,
      "loss": 0.568,
      "step": 13405
    },
    {
      "epoch": 0.4118207231284367,
      "grad_norm": 0.32017284631729126,
      "learning_rate": 1.8003002672979165e-05,
      "loss": 0.5632,
      "step": 13406
    },
    {
      "epoch": 0.4118514422633859,
      "grad_norm": 0.36230817437171936,
      "learning_rate": 1.8002712890815703e-05,
      "loss": 0.6522,
      "step": 13407
    },
    {
      "epoch": 0.411882161398335,
      "grad_norm": 0.3519146740436554,
      "learning_rate": 1.8002423089961342e-05,
      "loss": 0.5931,
      "step": 13408
    },
    {
      "epoch": 0.4119128805332842,
      "grad_norm": 0.37563830614089966,
      "learning_rate": 1.8002133270416765e-05,
      "loss": 0.6461,
      "step": 13409
    },
    {
      "epoch": 0.41194359966823335,
      "grad_norm": 0.3450593054294586,
      "learning_rate": 1.8001843432182646e-05,
      "loss": 0.4857,
      "step": 13410
    },
    {
      "epoch": 0.4119743188031825,
      "grad_norm": 0.4909997880458832,
      "learning_rate": 1.8001553575259663e-05,
      "loss": 0.571,
      "step": 13411
    },
    {
      "epoch": 0.41200503793813165,
      "grad_norm": 0.44551292061805725,
      "learning_rate": 1.8001263699648495e-05,
      "loss": 0.6264,
      "step": 13412
    },
    {
      "epoch": 0.4120357570730808,
      "grad_norm": 0.3315099775791168,
      "learning_rate": 1.8000973805349814e-05,
      "loss": 0.5051,
      "step": 13413
    },
    {
      "epoch": 0.41206647620803,
      "grad_norm": 0.3375314772129059,
      "learning_rate": 1.8000683892364303e-05,
      "loss": 0.5464,
      "step": 13414
    },
    {
      "epoch": 0.4120971953429791,
      "grad_norm": 0.35366058349609375,
      "learning_rate": 1.800039396069263e-05,
      "loss": 0.5322,
      "step": 13415
    },
    {
      "epoch": 0.4121279144779283,
      "grad_norm": 0.3705359101295471,
      "learning_rate": 1.8000104010335487e-05,
      "loss": 0.6015,
      "step": 13416
    },
    {
      "epoch": 0.41215863361287747,
      "grad_norm": 0.348046213388443,
      "learning_rate": 1.7999814041293535e-05,
      "loss": 0.6326,
      "step": 13417
    },
    {
      "epoch": 0.41218935274782664,
      "grad_norm": 0.3741365969181061,
      "learning_rate": 1.7999524053567463e-05,
      "loss": 0.5641,
      "step": 13418
    },
    {
      "epoch": 0.41222007188277576,
      "grad_norm": 0.3592749238014221,
      "learning_rate": 1.799923404715794e-05,
      "loss": 0.6061,
      "step": 13419
    },
    {
      "epoch": 0.41225079101772494,
      "grad_norm": 0.3400217294692993,
      "learning_rate": 1.799894402206565e-05,
      "loss": 0.6096,
      "step": 13420
    },
    {
      "epoch": 0.4122815101526741,
      "grad_norm": 0.3532443940639496,
      "learning_rate": 1.7998653978291266e-05,
      "loss": 0.5705,
      "step": 13421
    },
    {
      "epoch": 0.41231222928762323,
      "grad_norm": 0.3382752239704132,
      "learning_rate": 1.799836391583547e-05,
      "loss": 0.5834,
      "step": 13422
    },
    {
      "epoch": 0.4123429484225724,
      "grad_norm": 0.3300535976886749,
      "learning_rate": 1.7998073834698934e-05,
      "loss": 0.5238,
      "step": 13423
    },
    {
      "epoch": 0.4123736675575216,
      "grad_norm": 0.3445984721183777,
      "learning_rate": 1.799778373488234e-05,
      "loss": 0.4673,
      "step": 13424
    },
    {
      "epoch": 0.41240438669247076,
      "grad_norm": 0.35489359498023987,
      "learning_rate": 1.799749361638636e-05,
      "loss": 0.6336,
      "step": 13425
    },
    {
      "epoch": 0.4124351058274199,
      "grad_norm": 0.34575605392456055,
      "learning_rate": 1.7997203479211678e-05,
      "loss": 0.5109,
      "step": 13426
    },
    {
      "epoch": 0.41246582496236905,
      "grad_norm": 0.3383218050003052,
      "learning_rate": 1.7996913323358967e-05,
      "loss": 0.6087,
      "step": 13427
    },
    {
      "epoch": 0.41249654409731823,
      "grad_norm": 0.33458301424980164,
      "learning_rate": 1.7996623148828906e-05,
      "loss": 0.5998,
      "step": 13428
    },
    {
      "epoch": 0.4125272632322674,
      "grad_norm": 0.37094035744667053,
      "learning_rate": 1.7996332955622175e-05,
      "loss": 0.5889,
      "step": 13429
    },
    {
      "epoch": 0.4125579823672165,
      "grad_norm": 0.3577995002269745,
      "learning_rate": 1.799604274373945e-05,
      "loss": 0.5978,
      "step": 13430
    },
    {
      "epoch": 0.4125887015021657,
      "grad_norm": 0.3698597252368927,
      "learning_rate": 1.7995752513181406e-05,
      "loss": 0.5251,
      "step": 13431
    },
    {
      "epoch": 0.4126194206371149,
      "grad_norm": 0.3546057343482971,
      "learning_rate": 1.7995462263948728e-05,
      "loss": 0.5888,
      "step": 13432
    },
    {
      "epoch": 0.412650139772064,
      "grad_norm": 0.44069668650627136,
      "learning_rate": 1.7995171996042086e-05,
      "loss": 0.541,
      "step": 13433
    },
    {
      "epoch": 0.41268085890701317,
      "grad_norm": 0.3702760934829712,
      "learning_rate": 1.7994881709462163e-05,
      "loss": 0.5884,
      "step": 13434
    },
    {
      "epoch": 0.41271157804196235,
      "grad_norm": 0.3380815386772156,
      "learning_rate": 1.7994591404209632e-05,
      "loss": 0.5646,
      "step": 13435
    },
    {
      "epoch": 0.4127422971769115,
      "grad_norm": 0.3412424325942993,
      "learning_rate": 1.799430108028518e-05,
      "loss": 0.5543,
      "step": 13436
    },
    {
      "epoch": 0.41277301631186064,
      "grad_norm": 0.3341761827468872,
      "learning_rate": 1.7994010737689476e-05,
      "loss": 0.6314,
      "step": 13437
    },
    {
      "epoch": 0.4128037354468098,
      "grad_norm": 0.40015873312950134,
      "learning_rate": 1.7993720376423202e-05,
      "loss": 0.6146,
      "step": 13438
    },
    {
      "epoch": 0.412834454581759,
      "grad_norm": 0.36581161618232727,
      "learning_rate": 1.7993429996487038e-05,
      "loss": 0.5966,
      "step": 13439
    },
    {
      "epoch": 0.4128651737167081,
      "grad_norm": 0.3178241550922394,
      "learning_rate": 1.7993139597881657e-05,
      "loss": 0.5407,
      "step": 13440
    },
    {
      "epoch": 0.4128958928516573,
      "grad_norm": 0.3412364423274994,
      "learning_rate": 1.7992849180607742e-05,
      "loss": 0.6614,
      "step": 13441
    },
    {
      "epoch": 0.41292661198660646,
      "grad_norm": 0.3445812165737152,
      "learning_rate": 1.799255874466597e-05,
      "loss": 0.4987,
      "step": 13442
    },
    {
      "epoch": 0.41295733112155564,
      "grad_norm": 0.38411086797714233,
      "learning_rate": 1.7992268290057017e-05,
      "loss": 0.5462,
      "step": 13443
    },
    {
      "epoch": 0.41298805025650476,
      "grad_norm": 0.37098950147628784,
      "learning_rate": 1.7991977816781562e-05,
      "loss": 0.5813,
      "step": 13444
    },
    {
      "epoch": 0.41301876939145393,
      "grad_norm": 0.33148059248924255,
      "learning_rate": 1.7991687324840287e-05,
      "loss": 0.5671,
      "step": 13445
    },
    {
      "epoch": 0.4130494885264031,
      "grad_norm": 0.3676229417324066,
      "learning_rate": 1.799139681423387e-05,
      "loss": 0.5351,
      "step": 13446
    },
    {
      "epoch": 0.4130802076613523,
      "grad_norm": 0.37273865938186646,
      "learning_rate": 1.7991106284962986e-05,
      "loss": 0.558,
      "step": 13447
    },
    {
      "epoch": 0.4131109267963014,
      "grad_norm": 0.3445177972316742,
      "learning_rate": 1.7990815737028312e-05,
      "loss": 0.61,
      "step": 13448
    },
    {
      "epoch": 0.4131416459312506,
      "grad_norm": 0.34974682331085205,
      "learning_rate": 1.7990525170430535e-05,
      "loss": 0.5742,
      "step": 13449
    },
    {
      "epoch": 0.41317236506619975,
      "grad_norm": 0.3356606662273407,
      "learning_rate": 1.7990234585170325e-05,
      "loss": 0.5263,
      "step": 13450
    },
    {
      "epoch": 0.4132030842011489,
      "grad_norm": 0.39067623019218445,
      "learning_rate": 1.7989943981248363e-05,
      "loss": 0.6215,
      "step": 13451
    },
    {
      "epoch": 0.41323380333609805,
      "grad_norm": 0.4276455044746399,
      "learning_rate": 1.7989653358665334e-05,
      "loss": 0.5612,
      "step": 13452
    },
    {
      "epoch": 0.4132645224710472,
      "grad_norm": 0.42444127798080444,
      "learning_rate": 1.7989362717421904e-05,
      "loss": 0.537,
      "step": 13453
    },
    {
      "epoch": 0.4132952416059964,
      "grad_norm": 0.31514284014701843,
      "learning_rate": 1.7989072057518765e-05,
      "loss": 0.5642,
      "step": 13454
    },
    {
      "epoch": 0.4133259607409455,
      "grad_norm": 0.33914822340011597,
      "learning_rate": 1.798878137895659e-05,
      "loss": 0.5104,
      "step": 13455
    },
    {
      "epoch": 0.4133566798758947,
      "grad_norm": 0.3853336274623871,
      "learning_rate": 1.7988490681736058e-05,
      "loss": 0.6215,
      "step": 13456
    },
    {
      "epoch": 0.41338739901084387,
      "grad_norm": 0.3371196389198303,
      "learning_rate": 1.7988199965857845e-05,
      "loss": 0.5803,
      "step": 13457
    },
    {
      "epoch": 0.413418118145793,
      "grad_norm": 0.33220669627189636,
      "learning_rate": 1.7987909231322637e-05,
      "loss": 0.563,
      "step": 13458
    },
    {
      "epoch": 0.41344883728074217,
      "grad_norm": 0.309817910194397,
      "learning_rate": 1.7987618478131108e-05,
      "loss": 0.5207,
      "step": 13459
    },
    {
      "epoch": 0.41347955641569134,
      "grad_norm": 0.38921141624450684,
      "learning_rate": 1.7987327706283936e-05,
      "loss": 0.4965,
      "step": 13460
    },
    {
      "epoch": 0.4135102755506405,
      "grad_norm": 0.35291197896003723,
      "learning_rate": 1.7987036915781805e-05,
      "loss": 0.711,
      "step": 13461
    },
    {
      "epoch": 0.41354099468558964,
      "grad_norm": 0.6277258992195129,
      "learning_rate": 1.798674610662539e-05,
      "loss": 0.6558,
      "step": 13462
    },
    {
      "epoch": 0.4135717138205388,
      "grad_norm": 0.3130023181438446,
      "learning_rate": 1.7986455278815374e-05,
      "loss": 0.5429,
      "step": 13463
    },
    {
      "epoch": 0.413602432955488,
      "grad_norm": 0.42266830801963806,
      "learning_rate": 1.7986164432352432e-05,
      "loss": 0.5708,
      "step": 13464
    },
    {
      "epoch": 0.4136331520904371,
      "grad_norm": 0.3828681409358978,
      "learning_rate": 1.7985873567237246e-05,
      "loss": 0.5414,
      "step": 13465
    },
    {
      "epoch": 0.4136638712253863,
      "grad_norm": 0.3780165910720825,
      "learning_rate": 1.7985582683470492e-05,
      "loss": 0.5613,
      "step": 13466
    },
    {
      "epoch": 0.41369459036033546,
      "grad_norm": 0.3308892548084259,
      "learning_rate": 1.7985291781052852e-05,
      "loss": 0.6101,
      "step": 13467
    },
    {
      "epoch": 0.41372530949528463,
      "grad_norm": 0.3487844467163086,
      "learning_rate": 1.7985000859985007e-05,
      "loss": 0.605,
      "step": 13468
    },
    {
      "epoch": 0.41375602863023375,
      "grad_norm": 0.3884526491165161,
      "learning_rate": 1.7984709920267635e-05,
      "loss": 0.5381,
      "step": 13469
    },
    {
      "epoch": 0.4137867477651829,
      "grad_norm": 0.3837454319000244,
      "learning_rate": 1.798441896190142e-05,
      "loss": 0.645,
      "step": 13470
    },
    {
      "epoch": 0.4138174669001321,
      "grad_norm": 0.3347581624984741,
      "learning_rate": 1.798412798488703e-05,
      "loss": 0.6185,
      "step": 13471
    },
    {
      "epoch": 0.4138481860350813,
      "grad_norm": 0.33069300651550293,
      "learning_rate": 1.7983836989225155e-05,
      "loss": 0.5933,
      "step": 13472
    },
    {
      "epoch": 0.4138789051700304,
      "grad_norm": 0.33278778195381165,
      "learning_rate": 1.798354597491647e-05,
      "loss": 0.5312,
      "step": 13473
    },
    {
      "epoch": 0.4139096243049796,
      "grad_norm": 0.3195437490940094,
      "learning_rate": 1.7983254941961653e-05,
      "loss": 0.6161,
      "step": 13474
    },
    {
      "epoch": 0.41394034343992875,
      "grad_norm": 0.3487446904182434,
      "learning_rate": 1.7982963890361392e-05,
      "loss": 0.5015,
      "step": 13475
    },
    {
      "epoch": 0.41397106257487787,
      "grad_norm": 0.3408828377723694,
      "learning_rate": 1.7982672820116354e-05,
      "loss": 0.5428,
      "step": 13476
    },
    {
      "epoch": 0.41400178170982704,
      "grad_norm": 0.3633253872394562,
      "learning_rate": 1.7982381731227233e-05,
      "loss": 0.5982,
      "step": 13477
    },
    {
      "epoch": 0.4140325008447762,
      "grad_norm": 0.37097978591918945,
      "learning_rate": 1.79820906236947e-05,
      "loss": 0.5949,
      "step": 13478
    },
    {
      "epoch": 0.4140632199797254,
      "grad_norm": 0.36620303988456726,
      "learning_rate": 1.7981799497519437e-05,
      "loss": 0.5652,
      "step": 13479
    },
    {
      "epoch": 0.4140939391146745,
      "grad_norm": 0.31966632604599,
      "learning_rate": 1.7981508352702123e-05,
      "loss": 0.5522,
      "step": 13480
    },
    {
      "epoch": 0.4141246582496237,
      "grad_norm": 0.377055287361145,
      "learning_rate": 1.7981217189243437e-05,
      "loss": 0.6299,
      "step": 13481
    },
    {
      "epoch": 0.41415537738457286,
      "grad_norm": 0.2899676263332367,
      "learning_rate": 1.7980926007144063e-05,
      "loss": 0.4797,
      "step": 13482
    },
    {
      "epoch": 0.414186096519522,
      "grad_norm": 0.32399389147758484,
      "learning_rate": 1.798063480640468e-05,
      "loss": 0.5897,
      "step": 13483
    },
    {
      "epoch": 0.41421681565447116,
      "grad_norm": 0.33974161744117737,
      "learning_rate": 1.7980343587025964e-05,
      "loss": 0.5951,
      "step": 13484
    },
    {
      "epoch": 0.41424753478942034,
      "grad_norm": 0.32968106865882874,
      "learning_rate": 1.7980052349008602e-05,
      "loss": 0.5818,
      "step": 13485
    },
    {
      "epoch": 0.4142782539243695,
      "grad_norm": 0.37111541628837585,
      "learning_rate": 1.797976109235327e-05,
      "loss": 0.6293,
      "step": 13486
    },
    {
      "epoch": 0.41430897305931863,
      "grad_norm": 0.3460269868373871,
      "learning_rate": 1.7979469817060647e-05,
      "loss": 0.5263,
      "step": 13487
    },
    {
      "epoch": 0.4143396921942678,
      "grad_norm": 0.3377259075641632,
      "learning_rate": 1.7979178523131416e-05,
      "loss": 0.5952,
      "step": 13488
    },
    {
      "epoch": 0.414370411329217,
      "grad_norm": 0.3228611648082733,
      "learning_rate": 1.7978887210566258e-05,
      "loss": 0.5664,
      "step": 13489
    },
    {
      "epoch": 0.41440113046416616,
      "grad_norm": 0.3422519266605377,
      "learning_rate": 1.7978595879365845e-05,
      "loss": 0.5747,
      "step": 13490
    },
    {
      "epoch": 0.4144318495991153,
      "grad_norm": 0.31227001547813416,
      "learning_rate": 1.797830452953087e-05,
      "loss": 0.5432,
      "step": 13491
    },
    {
      "epoch": 0.41446256873406445,
      "grad_norm": 0.3392178416252136,
      "learning_rate": 1.7978013161062006e-05,
      "loss": 0.5684,
      "step": 13492
    },
    {
      "epoch": 0.4144932878690136,
      "grad_norm": 0.33658236265182495,
      "learning_rate": 1.7977721773959933e-05,
      "loss": 0.6458,
      "step": 13493
    },
    {
      "epoch": 0.41452400700396275,
      "grad_norm": 0.3575741946697235,
      "learning_rate": 1.7977430368225338e-05,
      "loss": 0.66,
      "step": 13494
    },
    {
      "epoch": 0.4145547261389119,
      "grad_norm": 0.3159225583076477,
      "learning_rate": 1.7977138943858895e-05,
      "loss": 0.4922,
      "step": 13495
    },
    {
      "epoch": 0.4145854452738611,
      "grad_norm": 0.3650193512439728,
      "learning_rate": 1.7976847500861284e-05,
      "loss": 0.5475,
      "step": 13496
    },
    {
      "epoch": 0.4146161644088103,
      "grad_norm": 0.3506503701210022,
      "learning_rate": 1.7976556039233194e-05,
      "loss": 0.6262,
      "step": 13497
    },
    {
      "epoch": 0.4146468835437594,
      "grad_norm": 0.3729051947593689,
      "learning_rate": 1.7976264558975295e-05,
      "loss": 0.5932,
      "step": 13498
    },
    {
      "epoch": 0.41467760267870857,
      "grad_norm": 0.38548117876052856,
      "learning_rate": 1.7975973060088275e-05,
      "loss": 0.6515,
      "step": 13499
    },
    {
      "epoch": 0.41470832181365774,
      "grad_norm": 0.34316256642341614,
      "learning_rate": 1.7975681542572815e-05,
      "loss": 0.602,
      "step": 13500
    },
    {
      "epoch": 0.41473904094860686,
      "grad_norm": 0.38326403498649597,
      "learning_rate": 1.797539000642959e-05,
      "loss": 0.6084,
      "step": 13501
    },
    {
      "epoch": 0.41476976008355604,
      "grad_norm": 0.3802562355995178,
      "learning_rate": 1.7975098451659287e-05,
      "loss": 0.5411,
      "step": 13502
    },
    {
      "epoch": 0.4148004792185052,
      "grad_norm": 0.35803282260894775,
      "learning_rate": 1.7974806878262584e-05,
      "loss": 0.578,
      "step": 13503
    },
    {
      "epoch": 0.4148311983534544,
      "grad_norm": 0.34899741411209106,
      "learning_rate": 1.7974515286240165e-05,
      "loss": 0.4997,
      "step": 13504
    },
    {
      "epoch": 0.4148619174884035,
      "grad_norm": 0.3400305211544037,
      "learning_rate": 1.7974223675592707e-05,
      "loss": 0.5757,
      "step": 13505
    },
    {
      "epoch": 0.4148926366233527,
      "grad_norm": 0.3617069721221924,
      "learning_rate": 1.7973932046320893e-05,
      "loss": 0.5044,
      "step": 13506
    },
    {
      "epoch": 0.41492335575830186,
      "grad_norm": 0.31433746218681335,
      "learning_rate": 1.7973640398425402e-05,
      "loss": 0.5134,
      "step": 13507
    },
    {
      "epoch": 0.414954074893251,
      "grad_norm": 0.31475383043289185,
      "learning_rate": 1.797334873190692e-05,
      "loss": 0.474,
      "step": 13508
    },
    {
      "epoch": 0.41498479402820015,
      "grad_norm": 0.6247244477272034,
      "learning_rate": 1.7973057046766124e-05,
      "loss": 0.4803,
      "step": 13509
    },
    {
      "epoch": 0.41501551316314933,
      "grad_norm": 0.3455808758735657,
      "learning_rate": 1.7972765343003694e-05,
      "loss": 0.5525,
      "step": 13510
    },
    {
      "epoch": 0.4150462322980985,
      "grad_norm": 0.32530826330184937,
      "learning_rate": 1.7972473620620316e-05,
      "loss": 0.552,
      "step": 13511
    },
    {
      "epoch": 0.4150769514330476,
      "grad_norm": 0.3750620186328888,
      "learning_rate": 1.7972181879616667e-05,
      "loss": 0.5045,
      "step": 13512
    },
    {
      "epoch": 0.4151076705679968,
      "grad_norm": 0.34242960810661316,
      "learning_rate": 1.7971890119993434e-05,
      "loss": 0.5449,
      "step": 13513
    },
    {
      "epoch": 0.415138389702946,
      "grad_norm": 0.36084040999412537,
      "learning_rate": 1.7971598341751293e-05,
      "loss": 0.593,
      "step": 13514
    },
    {
      "epoch": 0.41516910883789515,
      "grad_norm": 0.33685389161109924,
      "learning_rate": 1.7971306544890926e-05,
      "loss": 0.5122,
      "step": 13515
    },
    {
      "epoch": 0.41519982797284427,
      "grad_norm": 0.44419145584106445,
      "learning_rate": 1.797101472941302e-05,
      "loss": 0.5394,
      "step": 13516
    },
    {
      "epoch": 0.41523054710779345,
      "grad_norm": 0.43860355019569397,
      "learning_rate": 1.7970722895318248e-05,
      "loss": 0.5701,
      "step": 13517
    },
    {
      "epoch": 0.4152612662427426,
      "grad_norm": 0.33094528317451477,
      "learning_rate": 1.7970431042607297e-05,
      "loss": 0.4797,
      "step": 13518
    },
    {
      "epoch": 0.41529198537769174,
      "grad_norm": 0.35538312792778015,
      "learning_rate": 1.797013917128085e-05,
      "loss": 0.5483,
      "step": 13519
    },
    {
      "epoch": 0.4153227045126409,
      "grad_norm": 0.39709800481796265,
      "learning_rate": 1.796984728133958e-05,
      "loss": 0.5626,
      "step": 13520
    },
    {
      "epoch": 0.4153534236475901,
      "grad_norm": 0.34902703762054443,
      "learning_rate": 1.7969555372784182e-05,
      "loss": 0.5128,
      "step": 13521
    },
    {
      "epoch": 0.41538414278253927,
      "grad_norm": 0.4764990508556366,
      "learning_rate": 1.796926344561533e-05,
      "loss": 0.5446,
      "step": 13522
    },
    {
      "epoch": 0.4154148619174884,
      "grad_norm": 0.37706974148750305,
      "learning_rate": 1.7968971499833703e-05,
      "loss": 0.5934,
      "step": 13523
    },
    {
      "epoch": 0.41544558105243756,
      "grad_norm": 0.337767630815506,
      "learning_rate": 1.7968679535439987e-05,
      "loss": 0.4944,
      "step": 13524
    },
    {
      "epoch": 0.41547630018738674,
      "grad_norm": 0.39806538820266724,
      "learning_rate": 1.7968387552434868e-05,
      "loss": 0.5633,
      "step": 13525
    },
    {
      "epoch": 0.41550701932233586,
      "grad_norm": 0.3465985953807831,
      "learning_rate": 1.7968095550819022e-05,
      "loss": 0.5908,
      "step": 13526
    },
    {
      "epoch": 0.41553773845728503,
      "grad_norm": 0.36597657203674316,
      "learning_rate": 1.796780353059313e-05,
      "loss": 0.6231,
      "step": 13527
    },
    {
      "epoch": 0.4155684575922342,
      "grad_norm": 0.310036838054657,
      "learning_rate": 1.7967511491757877e-05,
      "loss": 0.6672,
      "step": 13528
    },
    {
      "epoch": 0.4155991767271834,
      "grad_norm": 0.321611225605011,
      "learning_rate": 1.7967219434313943e-05,
      "loss": 0.5916,
      "step": 13529
    },
    {
      "epoch": 0.4156298958621325,
      "grad_norm": 0.34464773535728455,
      "learning_rate": 1.7966927358262014e-05,
      "loss": 0.5873,
      "step": 13530
    },
    {
      "epoch": 0.4156606149970817,
      "grad_norm": 0.3694591522216797,
      "learning_rate": 1.796663526360277e-05,
      "loss": 0.5928,
      "step": 13531
    },
    {
      "epoch": 0.41569133413203085,
      "grad_norm": 0.40424680709838867,
      "learning_rate": 1.796634315033689e-05,
      "loss": 0.5985,
      "step": 13532
    },
    {
      "epoch": 0.41572205326698003,
      "grad_norm": 0.7059298753738403,
      "learning_rate": 1.796605101846506e-05,
      "loss": 0.6104,
      "step": 13533
    },
    {
      "epoch": 0.41575277240192915,
      "grad_norm": 0.3214164674282074,
      "learning_rate": 1.7965758867987965e-05,
      "loss": 0.5547,
      "step": 13534
    },
    {
      "epoch": 0.4157834915368783,
      "grad_norm": 0.3449247479438782,
      "learning_rate": 1.796546669890628e-05,
      "loss": 0.5493,
      "step": 13535
    },
    {
      "epoch": 0.4158142106718275,
      "grad_norm": 0.31372910737991333,
      "learning_rate": 1.7965174511220692e-05,
      "loss": 0.5489,
      "step": 13536
    },
    {
      "epoch": 0.4158449298067766,
      "grad_norm": 0.36073338985443115,
      "learning_rate": 1.7964882304931887e-05,
      "loss": 0.6611,
      "step": 13537
    },
    {
      "epoch": 0.4158756489417258,
      "grad_norm": 0.35527417063713074,
      "learning_rate": 1.7964590080040534e-05,
      "loss": 0.5621,
      "step": 13538
    },
    {
      "epoch": 0.41590636807667497,
      "grad_norm": 0.41904664039611816,
      "learning_rate": 1.7964297836547332e-05,
      "loss": 0.5974,
      "step": 13539
    },
    {
      "epoch": 0.41593708721162415,
      "grad_norm": 0.3420105278491974,
      "learning_rate": 1.7964005574452957e-05,
      "loss": 0.5853,
      "step": 13540
    },
    {
      "epoch": 0.41596780634657327,
      "grad_norm": 0.3496705889701843,
      "learning_rate": 1.7963713293758088e-05,
      "loss": 0.6053,
      "step": 13541
    },
    {
      "epoch": 0.41599852548152244,
      "grad_norm": 0.3533177375793457,
      "learning_rate": 1.796342099446341e-05,
      "loss": 0.6432,
      "step": 13542
    },
    {
      "epoch": 0.4160292446164716,
      "grad_norm": 0.37544897198677063,
      "learning_rate": 1.7963128676569607e-05,
      "loss": 0.6036,
      "step": 13543
    },
    {
      "epoch": 0.41605996375142074,
      "grad_norm": 0.32714641094207764,
      "learning_rate": 1.7962836340077357e-05,
      "loss": 0.5422,
      "step": 13544
    },
    {
      "epoch": 0.4160906828863699,
      "grad_norm": 0.3831726908683777,
      "learning_rate": 1.7962543984987354e-05,
      "loss": 0.5831,
      "step": 13545
    },
    {
      "epoch": 0.4161214020213191,
      "grad_norm": 0.4031693935394287,
      "learning_rate": 1.7962251611300268e-05,
      "loss": 0.5046,
      "step": 13546
    },
    {
      "epoch": 0.41615212115626826,
      "grad_norm": 0.3283339738845825,
      "learning_rate": 1.7961959219016787e-05,
      "loss": 0.5789,
      "step": 13547
    },
    {
      "epoch": 0.4161828402912174,
      "grad_norm": 0.3421998918056488,
      "learning_rate": 1.7961666808137596e-05,
      "loss": 0.5778,
      "step": 13548
    },
    {
      "epoch": 0.41621355942616656,
      "grad_norm": 0.34212225675582886,
      "learning_rate": 1.7961374378663378e-05,
      "loss": 0.6241,
      "step": 13549
    },
    {
      "epoch": 0.41624427856111573,
      "grad_norm": 0.37136203050613403,
      "learning_rate": 1.7961081930594812e-05,
      "loss": 0.5787,
      "step": 13550
    },
    {
      "epoch": 0.41627499769606485,
      "grad_norm": 0.35251137614250183,
      "learning_rate": 1.7960789463932582e-05,
      "loss": 0.6317,
      "step": 13551
    },
    {
      "epoch": 0.416305716831014,
      "grad_norm": 0.3322385847568512,
      "learning_rate": 1.7960496978677376e-05,
      "loss": 0.5743,
      "step": 13552
    },
    {
      "epoch": 0.4163364359659632,
      "grad_norm": 0.37494999170303345,
      "learning_rate": 1.796020447482987e-05,
      "loss": 0.5574,
      "step": 13553
    },
    {
      "epoch": 0.4163671551009124,
      "grad_norm": 0.3462819755077362,
      "learning_rate": 1.795991195239075e-05,
      "loss": 0.5526,
      "step": 13554
    },
    {
      "epoch": 0.4163978742358615,
      "grad_norm": 0.3660653829574585,
      "learning_rate": 1.7959619411360702e-05,
      "loss": 0.6614,
      "step": 13555
    },
    {
      "epoch": 0.4164285933708107,
      "grad_norm": 0.33216071128845215,
      "learning_rate": 1.7959326851740404e-05,
      "loss": 0.5356,
      "step": 13556
    },
    {
      "epoch": 0.41645931250575985,
      "grad_norm": 0.36338868737220764,
      "learning_rate": 1.7959034273530545e-05,
      "loss": 0.4419,
      "step": 13557
    },
    {
      "epoch": 0.416490031640709,
      "grad_norm": 0.35737144947052,
      "learning_rate": 1.7958741676731806e-05,
      "loss": 0.5619,
      "step": 13558
    },
    {
      "epoch": 0.41652075077565814,
      "grad_norm": 0.35395118594169617,
      "learning_rate": 1.795844906134487e-05,
      "loss": 0.6009,
      "step": 13559
    },
    {
      "epoch": 0.4165514699106073,
      "grad_norm": 0.3729795515537262,
      "learning_rate": 1.7958156427370416e-05,
      "loss": 0.6318,
      "step": 13560
    },
    {
      "epoch": 0.4165821890455565,
      "grad_norm": 0.32066863775253296,
      "learning_rate": 1.795786377480914e-05,
      "loss": 0.3948,
      "step": 13561
    },
    {
      "epoch": 0.4166129081805056,
      "grad_norm": 0.338638573884964,
      "learning_rate": 1.795757110366171e-05,
      "loss": 0.4851,
      "step": 13562
    },
    {
      "epoch": 0.4166436273154548,
      "grad_norm": 0.36284223198890686,
      "learning_rate": 1.795727841392882e-05,
      "loss": 0.6327,
      "step": 13563
    },
    {
      "epoch": 0.41667434645040397,
      "grad_norm": 0.3716714680194855,
      "learning_rate": 1.795698570561115e-05,
      "loss": 0.6808,
      "step": 13564
    },
    {
      "epoch": 0.41670506558535314,
      "grad_norm": 0.32993242144584656,
      "learning_rate": 1.7956692978709384e-05,
      "loss": 0.5534,
      "step": 13565
    },
    {
      "epoch": 0.41673578472030226,
      "grad_norm": 0.33987265825271606,
      "learning_rate": 1.7956400233224206e-05,
      "loss": 0.5773,
      "step": 13566
    },
    {
      "epoch": 0.41676650385525144,
      "grad_norm": 0.3732895851135254,
      "learning_rate": 1.7956107469156298e-05,
      "loss": 0.6399,
      "step": 13567
    },
    {
      "epoch": 0.4167972229902006,
      "grad_norm": 0.35777533054351807,
      "learning_rate": 1.7955814686506346e-05,
      "loss": 0.5717,
      "step": 13568
    },
    {
      "epoch": 0.41682794212514973,
      "grad_norm": 1.4428119659423828,
      "learning_rate": 1.7955521885275037e-05,
      "loss": 0.523,
      "step": 13569
    },
    {
      "epoch": 0.4168586612600989,
      "grad_norm": 0.3417584300041199,
      "learning_rate": 1.795522906546305e-05,
      "loss": 0.5962,
      "step": 13570
    },
    {
      "epoch": 0.4168893803950481,
      "grad_norm": 0.37208259105682373,
      "learning_rate": 1.7954936227071066e-05,
      "loss": 0.6072,
      "step": 13571
    },
    {
      "epoch": 0.41692009952999726,
      "grad_norm": 0.35172322392463684,
      "learning_rate": 1.7954643370099778e-05,
      "loss": 0.6008,
      "step": 13572
    },
    {
      "epoch": 0.4169508186649464,
      "grad_norm": 0.35454341769218445,
      "learning_rate": 1.7954350494549858e-05,
      "loss": 0.588,
      "step": 13573
    },
    {
      "epoch": 0.41698153779989555,
      "grad_norm": 0.482441246509552,
      "learning_rate": 1.7954057600422002e-05,
      "loss": 0.5889,
      "step": 13574
    },
    {
      "epoch": 0.4170122569348447,
      "grad_norm": 0.35916849970817566,
      "learning_rate": 1.7953764687716887e-05,
      "loss": 0.6162,
      "step": 13575
    },
    {
      "epoch": 0.41704297606979385,
      "grad_norm": 0.3558606207370758,
      "learning_rate": 1.7953471756435202e-05,
      "loss": 0.6089,
      "step": 13576
    },
    {
      "epoch": 0.417073695204743,
      "grad_norm": 0.3777182996273041,
      "learning_rate": 1.7953178806577626e-05,
      "loss": 0.6223,
      "step": 13577
    },
    {
      "epoch": 0.4171044143396922,
      "grad_norm": 0.3695099651813507,
      "learning_rate": 1.7952885838144845e-05,
      "loss": 0.5704,
      "step": 13578
    },
    {
      "epoch": 0.4171351334746414,
      "grad_norm": 0.3485008478164673,
      "learning_rate": 1.7952592851137543e-05,
      "loss": 0.4994,
      "step": 13579
    },
    {
      "epoch": 0.4171658526095905,
      "grad_norm": 0.3708656132221222,
      "learning_rate": 1.7952299845556408e-05,
      "loss": 0.5228,
      "step": 13580
    },
    {
      "epoch": 0.41719657174453967,
      "grad_norm": 0.34526345133781433,
      "learning_rate": 1.795200682140212e-05,
      "loss": 0.5411,
      "step": 13581
    },
    {
      "epoch": 0.41722729087948884,
      "grad_norm": 0.32994213700294495,
      "learning_rate": 1.7951713778675364e-05,
      "loss": 0.6141,
      "step": 13582
    },
    {
      "epoch": 0.417258010014438,
      "grad_norm": 0.35332897305488586,
      "learning_rate": 1.7951420717376825e-05,
      "loss": 0.4986,
      "step": 13583
    },
    {
      "epoch": 0.41728872914938714,
      "grad_norm": 0.3248617947101593,
      "learning_rate": 1.795112763750719e-05,
      "loss": 0.4671,
      "step": 13584
    },
    {
      "epoch": 0.4173194482843363,
      "grad_norm": 0.34700703620910645,
      "learning_rate": 1.7950834539067137e-05,
      "loss": 0.6358,
      "step": 13585
    },
    {
      "epoch": 0.4173501674192855,
      "grad_norm": 0.33503881096839905,
      "learning_rate": 1.7950541422057357e-05,
      "loss": 0.5616,
      "step": 13586
    },
    {
      "epoch": 0.4173808865542346,
      "grad_norm": 0.4057067036628723,
      "learning_rate": 1.7950248286478534e-05,
      "loss": 0.5768,
      "step": 13587
    },
    {
      "epoch": 0.4174116056891838,
      "grad_norm": 0.37507200241088867,
      "learning_rate": 1.794995513233135e-05,
      "loss": 0.5647,
      "step": 13588
    },
    {
      "epoch": 0.41744232482413296,
      "grad_norm": 0.3448200821876526,
      "learning_rate": 1.794966195961649e-05,
      "loss": 0.5901,
      "step": 13589
    },
    {
      "epoch": 0.41747304395908214,
      "grad_norm": 0.3658061623573303,
      "learning_rate": 1.7949368768334635e-05,
      "loss": 0.5476,
      "step": 13590
    },
    {
      "epoch": 0.41750376309403125,
      "grad_norm": 0.3874819874763489,
      "learning_rate": 1.794907555848648e-05,
      "loss": 0.5931,
      "step": 13591
    },
    {
      "epoch": 0.41753448222898043,
      "grad_norm": 0.35941797494888306,
      "learning_rate": 1.79487823300727e-05,
      "loss": 0.574,
      "step": 13592
    },
    {
      "epoch": 0.4175652013639296,
      "grad_norm": 0.3364095389842987,
      "learning_rate": 1.7948489083093986e-05,
      "loss": 0.5898,
      "step": 13593
    },
    {
      "epoch": 0.4175959204988787,
      "grad_norm": 0.36332714557647705,
      "learning_rate": 1.794819581755102e-05,
      "loss": 0.5447,
      "step": 13594
    },
    {
      "epoch": 0.4176266396338279,
      "grad_norm": 0.33720535039901733,
      "learning_rate": 1.7947902533444488e-05,
      "loss": 0.5736,
      "step": 13595
    },
    {
      "epoch": 0.4176573587687771,
      "grad_norm": 0.3926407992839813,
      "learning_rate": 1.7947609230775074e-05,
      "loss": 0.5658,
      "step": 13596
    },
    {
      "epoch": 0.41768807790372625,
      "grad_norm": 0.36118948459625244,
      "learning_rate": 1.7947315909543465e-05,
      "loss": 0.5158,
      "step": 13597
    },
    {
      "epoch": 0.41771879703867537,
      "grad_norm": 0.32338815927505493,
      "learning_rate": 1.7947022569750342e-05,
      "loss": 0.6306,
      "step": 13598
    },
    {
      "epoch": 0.41774951617362455,
      "grad_norm": 0.37669607996940613,
      "learning_rate": 1.7946729211396396e-05,
      "loss": 0.5429,
      "step": 13599
    },
    {
      "epoch": 0.4177802353085737,
      "grad_norm": 0.32195034623146057,
      "learning_rate": 1.7946435834482305e-05,
      "loss": 0.5912,
      "step": 13600
    },
    {
      "epoch": 0.4178109544435229,
      "grad_norm": 0.40909096598625183,
      "learning_rate": 1.7946142439008763e-05,
      "loss": 0.6446,
      "step": 13601
    },
    {
      "epoch": 0.417841673578472,
      "grad_norm": 0.3417479693889618,
      "learning_rate": 1.7945849024976444e-05,
      "loss": 0.551,
      "step": 13602
    },
    {
      "epoch": 0.4178723927134212,
      "grad_norm": 0.32102376222610474,
      "learning_rate": 1.7945555592386044e-05,
      "loss": 0.5504,
      "step": 13603
    },
    {
      "epoch": 0.41790311184837037,
      "grad_norm": 0.38472631573677063,
      "learning_rate": 1.7945262141238243e-05,
      "loss": 0.6013,
      "step": 13604
    },
    {
      "epoch": 0.4179338309833195,
      "grad_norm": 0.376674085855484,
      "learning_rate": 1.794496867153373e-05,
      "loss": 0.5286,
      "step": 13605
    },
    {
      "epoch": 0.41796455011826866,
      "grad_norm": 0.35689863562583923,
      "learning_rate": 1.7944675183273186e-05,
      "loss": 0.5944,
      "step": 13606
    },
    {
      "epoch": 0.41799526925321784,
      "grad_norm": 0.32555097341537476,
      "learning_rate": 1.79443816764573e-05,
      "loss": 0.594,
      "step": 13607
    },
    {
      "epoch": 0.418025988388167,
      "grad_norm": 0.3898604214191437,
      "learning_rate": 1.794408815108675e-05,
      "loss": 0.6333,
      "step": 13608
    },
    {
      "epoch": 0.41805670752311613,
      "grad_norm": 0.34341856837272644,
      "learning_rate": 1.7943794607162232e-05,
      "loss": 0.6153,
      "step": 13609
    },
    {
      "epoch": 0.4180874266580653,
      "grad_norm": 0.5007764101028442,
      "learning_rate": 1.7943501044684425e-05,
      "loss": 0.6583,
      "step": 13610
    },
    {
      "epoch": 0.4181181457930145,
      "grad_norm": 0.3256283104419708,
      "learning_rate": 1.7943207463654015e-05,
      "loss": 0.5324,
      "step": 13611
    },
    {
      "epoch": 0.4181488649279636,
      "grad_norm": 0.3469979763031006,
      "learning_rate": 1.7942913864071692e-05,
      "loss": 0.5369,
      "step": 13612
    },
    {
      "epoch": 0.4181795840629128,
      "grad_norm": 0.42277806997299194,
      "learning_rate": 1.7942620245938142e-05,
      "loss": 0.5726,
      "step": 13613
    },
    {
      "epoch": 0.41821030319786195,
      "grad_norm": 0.3402706980705261,
      "learning_rate": 1.7942326609254045e-05,
      "loss": 0.5892,
      "step": 13614
    },
    {
      "epoch": 0.41824102233281113,
      "grad_norm": 0.5751505494117737,
      "learning_rate": 1.794203295402009e-05,
      "loss": 0.5407,
      "step": 13615
    },
    {
      "epoch": 0.41827174146776025,
      "grad_norm": 0.3614290654659271,
      "learning_rate": 1.794173928023696e-05,
      "loss": 0.6417,
      "step": 13616
    },
    {
      "epoch": 0.4183024606027094,
      "grad_norm": 0.32762113213539124,
      "learning_rate": 1.7941445587905342e-05,
      "loss": 0.5223,
      "step": 13617
    },
    {
      "epoch": 0.4183331797376586,
      "grad_norm": 0.33942264318466187,
      "learning_rate": 1.7941151877025926e-05,
      "loss": 0.5183,
      "step": 13618
    },
    {
      "epoch": 0.4183638988726077,
      "grad_norm": 0.3226116895675659,
      "learning_rate": 1.7940858147599396e-05,
      "loss": 0.6253,
      "step": 13619
    },
    {
      "epoch": 0.4183946180075569,
      "grad_norm": 0.3390662968158722,
      "learning_rate": 1.794056439962643e-05,
      "loss": 0.5788,
      "step": 13620
    },
    {
      "epoch": 0.41842533714250607,
      "grad_norm": 0.5941289663314819,
      "learning_rate": 1.794027063310773e-05,
      "loss": 0.5576,
      "step": 13621
    },
    {
      "epoch": 0.41845605627745525,
      "grad_norm": 0.34264469146728516,
      "learning_rate": 1.793997684804397e-05,
      "loss": 0.5428,
      "step": 13622
    },
    {
      "epoch": 0.41848677541240437,
      "grad_norm": 0.3591174781322479,
      "learning_rate": 1.7939683044435844e-05,
      "loss": 0.5643,
      "step": 13623
    },
    {
      "epoch": 0.41851749454735354,
      "grad_norm": 0.3255631625652313,
      "learning_rate": 1.793938922228403e-05,
      "loss": 0.6051,
      "step": 13624
    },
    {
      "epoch": 0.4185482136823027,
      "grad_norm": 0.3723742365837097,
      "learning_rate": 1.793909538158922e-05,
      "loss": 0.609,
      "step": 13625
    },
    {
      "epoch": 0.4185789328172519,
      "grad_norm": 0.3429974615573883,
      "learning_rate": 1.793880152235209e-05,
      "loss": 0.5792,
      "step": 13626
    },
    {
      "epoch": 0.418609651952201,
      "grad_norm": 0.37104251980781555,
      "learning_rate": 1.7938507644573344e-05,
      "loss": 0.6058,
      "step": 13627
    },
    {
      "epoch": 0.4186403710871502,
      "grad_norm": 0.353971928358078,
      "learning_rate": 1.7938213748253655e-05,
      "loss": 0.5561,
      "step": 13628
    },
    {
      "epoch": 0.41867109022209936,
      "grad_norm": 0.31816691160202026,
      "learning_rate": 1.7937919833393716e-05,
      "loss": 0.6292,
      "step": 13629
    },
    {
      "epoch": 0.4187018093570485,
      "grad_norm": 0.34023699164390564,
      "learning_rate": 1.7937625899994205e-05,
      "loss": 0.5482,
      "step": 13630
    },
    {
      "epoch": 0.41873252849199766,
      "grad_norm": 0.353531152009964,
      "learning_rate": 1.793733194805582e-05,
      "loss": 0.6116,
      "step": 13631
    },
    {
      "epoch": 0.41876324762694683,
      "grad_norm": 0.38691550493240356,
      "learning_rate": 1.7937037977579243e-05,
      "loss": 0.5999,
      "step": 13632
    },
    {
      "epoch": 0.418793966761896,
      "grad_norm": 0.3443091809749603,
      "learning_rate": 1.7936743988565154e-05,
      "loss": 0.6196,
      "step": 13633
    },
    {
      "epoch": 0.41882468589684513,
      "grad_norm": 0.3432387709617615,
      "learning_rate": 1.7936449981014248e-05,
      "loss": 0.5823,
      "step": 13634
    },
    {
      "epoch": 0.4188554050317943,
      "grad_norm": 0.3404443562030792,
      "learning_rate": 1.793615595492721e-05,
      "loss": 0.5339,
      "step": 13635
    },
    {
      "epoch": 0.4188861241667435,
      "grad_norm": 0.3803689479827881,
      "learning_rate": 1.7935861910304725e-05,
      "loss": 0.5305,
      "step": 13636
    },
    {
      "epoch": 0.4189168433016926,
      "grad_norm": 0.3441116213798523,
      "learning_rate": 1.7935567847147478e-05,
      "loss": 0.5908,
      "step": 13637
    },
    {
      "epoch": 0.4189475624366418,
      "grad_norm": 0.3414524793624878,
      "learning_rate": 1.7935273765456157e-05,
      "loss": 0.5477,
      "step": 13638
    },
    {
      "epoch": 0.41897828157159095,
      "grad_norm": 0.31987109780311584,
      "learning_rate": 1.7934979665231456e-05,
      "loss": 0.6083,
      "step": 13639
    },
    {
      "epoch": 0.4190090007065401,
      "grad_norm": 0.32376378774642944,
      "learning_rate": 1.793468554647405e-05,
      "loss": 0.5406,
      "step": 13640
    },
    {
      "epoch": 0.41903971984148924,
      "grad_norm": 0.3340388834476471,
      "learning_rate": 1.7934391409184636e-05,
      "loss": 0.5935,
      "step": 13641
    },
    {
      "epoch": 0.4190704389764384,
      "grad_norm": 0.41424229741096497,
      "learning_rate": 1.7934097253363892e-05,
      "loss": 0.5941,
      "step": 13642
    },
    {
      "epoch": 0.4191011581113876,
      "grad_norm": 0.7332278490066528,
      "learning_rate": 1.7933803079012517e-05,
      "loss": 0.6073,
      "step": 13643
    },
    {
      "epoch": 0.41913187724633677,
      "grad_norm": 0.35454562306404114,
      "learning_rate": 1.7933508886131187e-05,
      "loss": 0.6386,
      "step": 13644
    },
    {
      "epoch": 0.4191625963812859,
      "grad_norm": 0.35108429193496704,
      "learning_rate": 1.7933214674720592e-05,
      "loss": 0.5677,
      "step": 13645
    },
    {
      "epoch": 0.41919331551623507,
      "grad_norm": 0.32668834924697876,
      "learning_rate": 1.793292044478142e-05,
      "loss": 0.5938,
      "step": 13646
    },
    {
      "epoch": 0.41922403465118424,
      "grad_norm": 0.3612866699695587,
      "learning_rate": 1.7932626196314356e-05,
      "loss": 0.5778,
      "step": 13647
    },
    {
      "epoch": 0.41925475378613336,
      "grad_norm": 0.36457982659339905,
      "learning_rate": 1.7932331929320093e-05,
      "loss": 0.5553,
      "step": 13648
    },
    {
      "epoch": 0.41928547292108254,
      "grad_norm": 0.3209291994571686,
      "learning_rate": 1.7932037643799313e-05,
      "loss": 0.5526,
      "step": 13649
    },
    {
      "epoch": 0.4193161920560317,
      "grad_norm": 0.34314507246017456,
      "learning_rate": 1.793174333975271e-05,
      "loss": 0.4912,
      "step": 13650
    },
    {
      "epoch": 0.4193469111909809,
      "grad_norm": 0.327249675989151,
      "learning_rate": 1.793144901718096e-05,
      "loss": 0.5638,
      "step": 13651
    },
    {
      "epoch": 0.41937763032593,
      "grad_norm": 0.3582034409046173,
      "learning_rate": 1.7931154676084757e-05,
      "loss": 0.6339,
      "step": 13652
    },
    {
      "epoch": 0.4194083494608792,
      "grad_norm": 0.4138329029083252,
      "learning_rate": 1.7930860316464793e-05,
      "loss": 0.6428,
      "step": 13653
    },
    {
      "epoch": 0.41943906859582836,
      "grad_norm": 0.32892557978630066,
      "learning_rate": 1.793056593832175e-05,
      "loss": 0.5238,
      "step": 13654
    },
    {
      "epoch": 0.4194697877307775,
      "grad_norm": 0.3319656252861023,
      "learning_rate": 1.7930271541656313e-05,
      "loss": 0.575,
      "step": 13655
    },
    {
      "epoch": 0.41950050686572665,
      "grad_norm": 0.3682383894920349,
      "learning_rate": 1.7929977126469175e-05,
      "loss": 0.5883,
      "step": 13656
    },
    {
      "epoch": 0.4195312260006758,
      "grad_norm": 0.3587525486946106,
      "learning_rate": 1.792968269276102e-05,
      "loss": 0.6299,
      "step": 13657
    },
    {
      "epoch": 0.419561945135625,
      "grad_norm": 0.3337033689022064,
      "learning_rate": 1.792938824053254e-05,
      "loss": 0.5149,
      "step": 13658
    },
    {
      "epoch": 0.4195926642705741,
      "grad_norm": 0.34074416756629944,
      "learning_rate": 1.7929093769784422e-05,
      "loss": 0.5373,
      "step": 13659
    },
    {
      "epoch": 0.4196233834055233,
      "grad_norm": 0.3872559070587158,
      "learning_rate": 1.7928799280517347e-05,
      "loss": 0.5729,
      "step": 13660
    },
    {
      "epoch": 0.4196541025404725,
      "grad_norm": 0.3326333463191986,
      "learning_rate": 1.7928504772732007e-05,
      "loss": 0.5145,
      "step": 13661
    },
    {
      "epoch": 0.4196848216754216,
      "grad_norm": 0.4156367778778076,
      "learning_rate": 1.7928210246429094e-05,
      "loss": 0.536,
      "step": 13662
    },
    {
      "epoch": 0.41971554081037077,
      "grad_norm": 0.36305302381515503,
      "learning_rate": 1.7927915701609292e-05,
      "loss": 0.5531,
      "step": 13663
    },
    {
      "epoch": 0.41974625994531994,
      "grad_norm": 0.37955349683761597,
      "learning_rate": 1.792762113827329e-05,
      "loss": 0.5388,
      "step": 13664
    },
    {
      "epoch": 0.4197769790802691,
      "grad_norm": 0.3581618666648865,
      "learning_rate": 1.7927326556421772e-05,
      "loss": 0.5982,
      "step": 13665
    },
    {
      "epoch": 0.41980769821521824,
      "grad_norm": 0.36039426922798157,
      "learning_rate": 1.792703195605543e-05,
      "loss": 0.5587,
      "step": 13666
    },
    {
      "epoch": 0.4198384173501674,
      "grad_norm": 0.3172575831413269,
      "learning_rate": 1.792673733717495e-05,
      "loss": 0.5558,
      "step": 13667
    },
    {
      "epoch": 0.4198691364851166,
      "grad_norm": 0.34876832365989685,
      "learning_rate": 1.7926442699781023e-05,
      "loss": 0.5615,
      "step": 13668
    },
    {
      "epoch": 0.41989985562006577,
      "grad_norm": 0.36051225662231445,
      "learning_rate": 1.7926148043874337e-05,
      "loss": 0.6303,
      "step": 13669
    },
    {
      "epoch": 0.4199305747550149,
      "grad_norm": 0.3494899272918701,
      "learning_rate": 1.7925853369455577e-05,
      "loss": 0.5273,
      "step": 13670
    },
    {
      "epoch": 0.41996129388996406,
      "grad_norm": 0.3630965054035187,
      "learning_rate": 1.7925558676525434e-05,
      "loss": 0.5454,
      "step": 13671
    },
    {
      "epoch": 0.41999201302491324,
      "grad_norm": 0.389550119638443,
      "learning_rate": 1.792526396508459e-05,
      "loss": 0.5881,
      "step": 13672
    },
    {
      "epoch": 0.42002273215986236,
      "grad_norm": 0.3366812765598297,
      "learning_rate": 1.7924969235133745e-05,
      "loss": 0.5479,
      "step": 13673
    },
    {
      "epoch": 0.42005345129481153,
      "grad_norm": 0.3666175901889801,
      "learning_rate": 1.7924674486673578e-05,
      "loss": 0.5763,
      "step": 13674
    },
    {
      "epoch": 0.4200841704297607,
      "grad_norm": 0.41260164976119995,
      "learning_rate": 1.792437971970478e-05,
      "loss": 0.6065,
      "step": 13675
    },
    {
      "epoch": 0.4201148895647099,
      "grad_norm": 0.3445298373699188,
      "learning_rate": 1.792408493422804e-05,
      "loss": 0.5096,
      "step": 13676
    },
    {
      "epoch": 0.420145608699659,
      "grad_norm": 0.36334577202796936,
      "learning_rate": 1.7923790130244047e-05,
      "loss": 0.5815,
      "step": 13677
    },
    {
      "epoch": 0.4201763278346082,
      "grad_norm": 0.32935258746147156,
      "learning_rate": 1.792349530775349e-05,
      "loss": 0.5225,
      "step": 13678
    },
    {
      "epoch": 0.42020704696955735,
      "grad_norm": 0.5830272436141968,
      "learning_rate": 1.7923200466757056e-05,
      "loss": 0.6324,
      "step": 13679
    },
    {
      "epoch": 0.42023776610450647,
      "grad_norm": 0.42957785725593567,
      "learning_rate": 1.792290560725543e-05,
      "loss": 0.6082,
      "step": 13680
    },
    {
      "epoch": 0.42026848523945565,
      "grad_norm": 0.33713382482528687,
      "learning_rate": 1.792261072924931e-05,
      "loss": 0.4777,
      "step": 13681
    },
    {
      "epoch": 0.4202992043744048,
      "grad_norm": 0.4984355568885803,
      "learning_rate": 1.7922315832739375e-05,
      "loss": 0.533,
      "step": 13682
    },
    {
      "epoch": 0.420329923509354,
      "grad_norm": 0.3821815848350525,
      "learning_rate": 1.792202091772632e-05,
      "loss": 0.5236,
      "step": 13683
    },
    {
      "epoch": 0.4203606426443031,
      "grad_norm": 0.34014126658439636,
      "learning_rate": 1.7921725984210834e-05,
      "loss": 0.5947,
      "step": 13684
    },
    {
      "epoch": 0.4203913617792523,
      "grad_norm": 0.3237806558609009,
      "learning_rate": 1.79214310321936e-05,
      "loss": 0.5233,
      "step": 13685
    },
    {
      "epoch": 0.42042208091420147,
      "grad_norm": 0.47360095381736755,
      "learning_rate": 1.7921136061675314e-05,
      "loss": 0.6246,
      "step": 13686
    },
    {
      "epoch": 0.42045280004915064,
      "grad_norm": 0.34132441878318787,
      "learning_rate": 1.792084107265666e-05,
      "loss": 0.5752,
      "step": 13687
    },
    {
      "epoch": 0.42048351918409976,
      "grad_norm": 0.3260282278060913,
      "learning_rate": 1.792054606513833e-05,
      "loss": 0.6344,
      "step": 13688
    },
    {
      "epoch": 0.42051423831904894,
      "grad_norm": 0.5223171710968018,
      "learning_rate": 1.7920251039121007e-05,
      "loss": 0.6555,
      "step": 13689
    },
    {
      "epoch": 0.4205449574539981,
      "grad_norm": 0.33805039525032043,
      "learning_rate": 1.7919955994605387e-05,
      "loss": 0.5556,
      "step": 13690
    },
    {
      "epoch": 0.42057567658894723,
      "grad_norm": 4.592628479003906,
      "learning_rate": 1.7919660931592156e-05,
      "loss": 0.6508,
      "step": 13691
    },
    {
      "epoch": 0.4206063957238964,
      "grad_norm": 0.36188623309135437,
      "learning_rate": 1.7919365850082006e-05,
      "loss": 0.557,
      "step": 13692
    },
    {
      "epoch": 0.4206371148588456,
      "grad_norm": 0.32571834325790405,
      "learning_rate": 1.791907075007562e-05,
      "loss": 0.5247,
      "step": 13693
    },
    {
      "epoch": 0.42066783399379476,
      "grad_norm": 0.3364171087741852,
      "learning_rate": 1.79187756315737e-05,
      "loss": 0.5377,
      "step": 13694
    },
    {
      "epoch": 0.4206985531287439,
      "grad_norm": 0.40245988965034485,
      "learning_rate": 1.7918480494576917e-05,
      "loss": 0.5398,
      "step": 13695
    },
    {
      "epoch": 0.42072927226369305,
      "grad_norm": 0.3849131166934967,
      "learning_rate": 1.791818533908597e-05,
      "loss": 0.6926,
      "step": 13696
    },
    {
      "epoch": 0.42075999139864223,
      "grad_norm": 0.33267951011657715,
      "learning_rate": 1.7917890165101554e-05,
      "loss": 0.6074,
      "step": 13697
    },
    {
      "epoch": 0.42079071053359135,
      "grad_norm": 0.34417226910591125,
      "learning_rate": 1.791759497262435e-05,
      "loss": 0.598,
      "step": 13698
    },
    {
      "epoch": 0.4208214296685405,
      "grad_norm": 0.34117186069488525,
      "learning_rate": 1.7917299761655048e-05,
      "loss": 0.586,
      "step": 13699
    },
    {
      "epoch": 0.4208521488034897,
      "grad_norm": 0.34811827540397644,
      "learning_rate": 1.791700453219434e-05,
      "loss": 0.5981,
      "step": 13700
    },
    {
      "epoch": 0.4208828679384389,
      "grad_norm": 0.41498133540153503,
      "learning_rate": 1.791670928424292e-05,
      "loss": 0.5933,
      "step": 13701
    },
    {
      "epoch": 0.420913587073388,
      "grad_norm": 0.3517075479030609,
      "learning_rate": 1.791641401780147e-05,
      "loss": 0.5674,
      "step": 13702
    },
    {
      "epoch": 0.42094430620833717,
      "grad_norm": 0.38625842332839966,
      "learning_rate": 1.791611873287068e-05,
      "loss": 0.6397,
      "step": 13703
    },
    {
      "epoch": 0.42097502534328635,
      "grad_norm": 0.41680026054382324,
      "learning_rate": 1.7915823429451242e-05,
      "loss": 0.6019,
      "step": 13704
    },
    {
      "epoch": 0.42100574447823547,
      "grad_norm": 0.3878123462200165,
      "learning_rate": 1.7915528107543845e-05,
      "loss": 0.5023,
      "step": 13705
    },
    {
      "epoch": 0.42103646361318464,
      "grad_norm": 0.37448152899742126,
      "learning_rate": 1.7915232767149184e-05,
      "loss": 0.5887,
      "step": 13706
    },
    {
      "epoch": 0.4210671827481338,
      "grad_norm": 0.32517001032829285,
      "learning_rate": 1.7914937408267937e-05,
      "loss": 0.5848,
      "step": 13707
    },
    {
      "epoch": 0.421097901883083,
      "grad_norm": 0.4219764471054077,
      "learning_rate": 1.7914642030900807e-05,
      "loss": 0.6808,
      "step": 13708
    },
    {
      "epoch": 0.4211286210180321,
      "grad_norm": 0.3752448856830597,
      "learning_rate": 1.7914346635048473e-05,
      "loss": 0.6385,
      "step": 13709
    },
    {
      "epoch": 0.4211593401529813,
      "grad_norm": 0.33976268768310547,
      "learning_rate": 1.7914051220711634e-05,
      "loss": 0.6001,
      "step": 13710
    },
    {
      "epoch": 0.42119005928793046,
      "grad_norm": 0.33098405599594116,
      "learning_rate": 1.7913755787890974e-05,
      "loss": 0.5613,
      "step": 13711
    },
    {
      "epoch": 0.42122077842287964,
      "grad_norm": 0.3375484347343445,
      "learning_rate": 1.7913460336587184e-05,
      "loss": 0.5124,
      "step": 13712
    },
    {
      "epoch": 0.42125149755782876,
      "grad_norm": 0.3898363411426544,
      "learning_rate": 1.7913164866800956e-05,
      "loss": 0.6343,
      "step": 13713
    },
    {
      "epoch": 0.42128221669277793,
      "grad_norm": 0.34963560104370117,
      "learning_rate": 1.7912869378532977e-05,
      "loss": 0.575,
      "step": 13714
    },
    {
      "epoch": 0.4213129358277271,
      "grad_norm": 0.3601008951663971,
      "learning_rate": 1.791257387178394e-05,
      "loss": 0.4188,
      "step": 13715
    },
    {
      "epoch": 0.42134365496267623,
      "grad_norm": 0.3715578019618988,
      "learning_rate": 1.7912278346554536e-05,
      "loss": 0.5887,
      "step": 13716
    },
    {
      "epoch": 0.4213743740976254,
      "grad_norm": 0.3555755913257599,
      "learning_rate": 1.7911982802845452e-05,
      "loss": 0.6467,
      "step": 13717
    },
    {
      "epoch": 0.4214050932325746,
      "grad_norm": 0.3835761249065399,
      "learning_rate": 1.7911687240657376e-05,
      "loss": 0.5794,
      "step": 13718
    },
    {
      "epoch": 0.42143581236752375,
      "grad_norm": 0.4941348433494568,
      "learning_rate": 1.7911391659991008e-05,
      "loss": 0.4622,
      "step": 13719
    },
    {
      "epoch": 0.4214665315024729,
      "grad_norm": 0.3184669017791748,
      "learning_rate": 1.7911096060847026e-05,
      "loss": 0.523,
      "step": 13720
    },
    {
      "epoch": 0.42149725063742205,
      "grad_norm": 0.3106752634048462,
      "learning_rate": 1.7910800443226132e-05,
      "loss": 0.58,
      "step": 13721
    },
    {
      "epoch": 0.4215279697723712,
      "grad_norm": 0.3704081177711487,
      "learning_rate": 1.7910504807129007e-05,
      "loss": 0.4773,
      "step": 13722
    },
    {
      "epoch": 0.42155868890732034,
      "grad_norm": 0.33200156688690186,
      "learning_rate": 1.7910209152556348e-05,
      "loss": 0.538,
      "step": 13723
    },
    {
      "epoch": 0.4215894080422695,
      "grad_norm": 0.3723933696746826,
      "learning_rate": 1.7909913479508843e-05,
      "loss": 0.6219,
      "step": 13724
    },
    {
      "epoch": 0.4216201271772187,
      "grad_norm": 0.3450648784637451,
      "learning_rate": 1.790961778798718e-05,
      "loss": 0.5886,
      "step": 13725
    },
    {
      "epoch": 0.42165084631216787,
      "grad_norm": 0.34337374567985535,
      "learning_rate": 1.7909322077992058e-05,
      "loss": 0.5239,
      "step": 13726
    },
    {
      "epoch": 0.421681565447117,
      "grad_norm": 0.34349292516708374,
      "learning_rate": 1.7909026349524156e-05,
      "loss": 0.5812,
      "step": 13727
    },
    {
      "epoch": 0.42171228458206617,
      "grad_norm": 0.3317430317401886,
      "learning_rate": 1.7908730602584174e-05,
      "loss": 0.5533,
      "step": 13728
    },
    {
      "epoch": 0.42174300371701534,
      "grad_norm": 0.3458785116672516,
      "learning_rate": 1.79084348371728e-05,
      "loss": 0.6051,
      "step": 13729
    },
    {
      "epoch": 0.42177372285196446,
      "grad_norm": 0.33519697189331055,
      "learning_rate": 1.7908139053290718e-05,
      "loss": 0.585,
      "step": 13730
    },
    {
      "epoch": 0.42180444198691364,
      "grad_norm": 0.33924561738967896,
      "learning_rate": 1.790784325093863e-05,
      "loss": 0.5019,
      "step": 13731
    },
    {
      "epoch": 0.4218351611218628,
      "grad_norm": 0.339887410402298,
      "learning_rate": 1.790754743011722e-05,
      "loss": 0.6072,
      "step": 13732
    },
    {
      "epoch": 0.421865880256812,
      "grad_norm": 0.3477778434753418,
      "learning_rate": 1.7907251590827185e-05,
      "loss": 0.5948,
      "step": 13733
    },
    {
      "epoch": 0.4218965993917611,
      "grad_norm": 0.35875001549720764,
      "learning_rate": 1.7906955733069208e-05,
      "loss": 0.5566,
      "step": 13734
    },
    {
      "epoch": 0.4219273185267103,
      "grad_norm": 0.3578559160232544,
      "learning_rate": 1.7906659856843985e-05,
      "loss": 0.5084,
      "step": 13735
    },
    {
      "epoch": 0.42195803766165946,
      "grad_norm": 0.4151288568973541,
      "learning_rate": 1.7906363962152203e-05,
      "loss": 0.685,
      "step": 13736
    },
    {
      "epoch": 0.42198875679660863,
      "grad_norm": 0.7790361046791077,
      "learning_rate": 1.7906068048994558e-05,
      "loss": 0.5286,
      "step": 13737
    },
    {
      "epoch": 0.42201947593155775,
      "grad_norm": 0.33154648542404175,
      "learning_rate": 1.790577211737174e-05,
      "loss": 0.5743,
      "step": 13738
    },
    {
      "epoch": 0.42205019506650693,
      "grad_norm": 0.3580038249492645,
      "learning_rate": 1.7905476167284437e-05,
      "loss": 0.5479,
      "step": 13739
    },
    {
      "epoch": 0.4220809142014561,
      "grad_norm": 0.37286561727523804,
      "learning_rate": 1.790518019873334e-05,
      "loss": 0.5785,
      "step": 13740
    },
    {
      "epoch": 0.4221116333364052,
      "grad_norm": 0.4099390506744385,
      "learning_rate": 1.7904884211719146e-05,
      "loss": 0.6801,
      "step": 13741
    },
    {
      "epoch": 0.4221423524713544,
      "grad_norm": 0.6702728867530823,
      "learning_rate": 1.7904588206242546e-05,
      "loss": 0.72,
      "step": 13742
    },
    {
      "epoch": 0.4221730716063036,
      "grad_norm": 0.30737969279289246,
      "learning_rate": 1.7904292182304223e-05,
      "loss": 0.5612,
      "step": 13743
    },
    {
      "epoch": 0.42220379074125275,
      "grad_norm": 0.48112356662750244,
      "learning_rate": 1.7903996139904875e-05,
      "loss": 0.5503,
      "step": 13744
    },
    {
      "epoch": 0.42223450987620187,
      "grad_norm": 0.3694402873516083,
      "learning_rate": 1.7903700079045192e-05,
      "loss": 0.5531,
      "step": 13745
    },
    {
      "epoch": 0.42226522901115104,
      "grad_norm": 0.33446431159973145,
      "learning_rate": 1.790340399972587e-05,
      "loss": 0.6088,
      "step": 13746
    },
    {
      "epoch": 0.4222959481461002,
      "grad_norm": 0.3637501001358032,
      "learning_rate": 1.7903107901947588e-05,
      "loss": 0.5618,
      "step": 13747
    },
    {
      "epoch": 0.42232666728104934,
      "grad_norm": 0.32040029764175415,
      "learning_rate": 1.790281178571105e-05,
      "loss": 0.5255,
      "step": 13748
    },
    {
      "epoch": 0.4223573864159985,
      "grad_norm": 0.35006412863731384,
      "learning_rate": 1.790251565101694e-05,
      "loss": 0.5808,
      "step": 13749
    },
    {
      "epoch": 0.4223881055509477,
      "grad_norm": 0.35866519808769226,
      "learning_rate": 1.7902219497865954e-05,
      "loss": 0.5727,
      "step": 13750
    },
    {
      "epoch": 0.42241882468589687,
      "grad_norm": 0.4016134738922119,
      "learning_rate": 1.7901923326258787e-05,
      "loss": 0.5764,
      "step": 13751
    },
    {
      "epoch": 0.422449543820846,
      "grad_norm": 0.32082512974739075,
      "learning_rate": 1.7901627136196124e-05,
      "loss": 0.527,
      "step": 13752
    },
    {
      "epoch": 0.42248026295579516,
      "grad_norm": 0.3548704981803894,
      "learning_rate": 1.7901330927678656e-05,
      "loss": 0.5864,
      "step": 13753
    },
    {
      "epoch": 0.42251098209074434,
      "grad_norm": 0.4126437306404114,
      "learning_rate": 1.790103470070708e-05,
      "loss": 0.5662,
      "step": 13754
    },
    {
      "epoch": 0.4225417012256935,
      "grad_norm": 0.37354904413223267,
      "learning_rate": 1.7900738455282086e-05,
      "loss": 0.5818,
      "step": 13755
    },
    {
      "epoch": 0.42257242036064263,
      "grad_norm": 0.3807099759578705,
      "learning_rate": 1.7900442191404364e-05,
      "loss": 0.5424,
      "step": 13756
    },
    {
      "epoch": 0.4226031394955918,
      "grad_norm": 0.32012489438056946,
      "learning_rate": 1.7900145909074605e-05,
      "loss": 0.5058,
      "step": 13757
    },
    {
      "epoch": 0.422633858630541,
      "grad_norm": 0.35646292567253113,
      "learning_rate": 1.7899849608293508e-05,
      "loss": 0.5515,
      "step": 13758
    },
    {
      "epoch": 0.4226645777654901,
      "grad_norm": 0.33858591318130493,
      "learning_rate": 1.7899553289061762e-05,
      "loss": 0.5376,
      "step": 13759
    },
    {
      "epoch": 0.4226952969004393,
      "grad_norm": 0.3398784399032593,
      "learning_rate": 1.7899256951380054e-05,
      "loss": 0.5179,
      "step": 13760
    },
    {
      "epoch": 0.42272601603538845,
      "grad_norm": 0.3417968153953552,
      "learning_rate": 1.789896059524908e-05,
      "loss": 0.5265,
      "step": 13761
    },
    {
      "epoch": 0.4227567351703376,
      "grad_norm": 0.36332687735557556,
      "learning_rate": 1.7898664220669535e-05,
      "loss": 0.5535,
      "step": 13762
    },
    {
      "epoch": 0.42278745430528675,
      "grad_norm": 0.35556676983833313,
      "learning_rate": 1.78983678276421e-05,
      "loss": 0.5196,
      "step": 13763
    },
    {
      "epoch": 0.4228181734402359,
      "grad_norm": 0.3212848901748657,
      "learning_rate": 1.7898071416167485e-05,
      "loss": 0.5644,
      "step": 13764
    },
    {
      "epoch": 0.4228488925751851,
      "grad_norm": 0.3373847007751465,
      "learning_rate": 1.789777498624637e-05,
      "loss": 0.6212,
      "step": 13765
    },
    {
      "epoch": 0.4228796117101342,
      "grad_norm": 0.39276811480522156,
      "learning_rate": 1.7897478537879446e-05,
      "loss": 0.6439,
      "step": 13766
    },
    {
      "epoch": 0.4229103308450834,
      "grad_norm": 0.32682663202285767,
      "learning_rate": 1.7897182071067412e-05,
      "loss": 0.6086,
      "step": 13767
    },
    {
      "epoch": 0.42294104998003257,
      "grad_norm": 0.3236887753009796,
      "learning_rate": 1.7896885585810958e-05,
      "loss": 0.5627,
      "step": 13768
    },
    {
      "epoch": 0.42297176911498174,
      "grad_norm": 0.32789716124534607,
      "learning_rate": 1.7896589082110775e-05,
      "loss": 0.5789,
      "step": 13769
    },
    {
      "epoch": 0.42300248824993086,
      "grad_norm": 0.3284471333026886,
      "learning_rate": 1.7896292559967557e-05,
      "loss": 0.4842,
      "step": 13770
    },
    {
      "epoch": 0.42303320738488004,
      "grad_norm": 0.3239450752735138,
      "learning_rate": 1.7895996019382e-05,
      "loss": 0.539,
      "step": 13771
    },
    {
      "epoch": 0.4230639265198292,
      "grad_norm": 0.3479504883289337,
      "learning_rate": 1.7895699460354786e-05,
      "loss": 0.6007,
      "step": 13772
    },
    {
      "epoch": 0.42309464565477833,
      "grad_norm": 0.4570083022117615,
      "learning_rate": 1.7895402882886622e-05,
      "loss": 0.6111,
      "step": 13773
    },
    {
      "epoch": 0.4231253647897275,
      "grad_norm": 0.36839213967323303,
      "learning_rate": 1.789510628697819e-05,
      "loss": 0.5951,
      "step": 13774
    },
    {
      "epoch": 0.4231560839246767,
      "grad_norm": 0.34120622277259827,
      "learning_rate": 1.7894809672630183e-05,
      "loss": 0.5515,
      "step": 13775
    },
    {
      "epoch": 0.42318680305962586,
      "grad_norm": 0.32537826895713806,
      "learning_rate": 1.7894513039843297e-05,
      "loss": 0.6204,
      "step": 13776
    },
    {
      "epoch": 0.423217522194575,
      "grad_norm": 0.34834304451942444,
      "learning_rate": 1.7894216388618228e-05,
      "loss": 0.5699,
      "step": 13777
    },
    {
      "epoch": 0.42324824132952416,
      "grad_norm": 0.3385746479034424,
      "learning_rate": 1.789391971895566e-05,
      "loss": 0.5187,
      "step": 13778
    },
    {
      "epoch": 0.42327896046447333,
      "grad_norm": 0.34506675601005554,
      "learning_rate": 1.7893623030856296e-05,
      "loss": 0.6329,
      "step": 13779
    },
    {
      "epoch": 0.4233096795994225,
      "grad_norm": 0.46552422642707825,
      "learning_rate": 1.7893326324320823e-05,
      "loss": 0.6198,
      "step": 13780
    },
    {
      "epoch": 0.4233403987343716,
      "grad_norm": 0.38379573822021484,
      "learning_rate": 1.7893029599349935e-05,
      "loss": 0.6119,
      "step": 13781
    },
    {
      "epoch": 0.4233711178693208,
      "grad_norm": 0.3566911518573761,
      "learning_rate": 1.7892732855944327e-05,
      "loss": 0.6218,
      "step": 13782
    },
    {
      "epoch": 0.42340183700427,
      "grad_norm": 0.3546522855758667,
      "learning_rate": 1.789243609410469e-05,
      "loss": 0.6074,
      "step": 13783
    },
    {
      "epoch": 0.4234325561392191,
      "grad_norm": 0.3452991545200348,
      "learning_rate": 1.7892139313831712e-05,
      "loss": 0.5498,
      "step": 13784
    },
    {
      "epoch": 0.42346327527416827,
      "grad_norm": 0.38666659593582153,
      "learning_rate": 1.7891842515126097e-05,
      "loss": 0.5796,
      "step": 13785
    },
    {
      "epoch": 0.42349399440911745,
      "grad_norm": 0.3420117199420929,
      "learning_rate": 1.7891545697988528e-05,
      "loss": 0.5806,
      "step": 13786
    },
    {
      "epoch": 0.4235247135440666,
      "grad_norm": 0.34679973125457764,
      "learning_rate": 1.7891248862419704e-05,
      "loss": 0.4715,
      "step": 13787
    },
    {
      "epoch": 0.42355543267901574,
      "grad_norm": 0.34394583106040955,
      "learning_rate": 1.789095200842032e-05,
      "loss": 0.547,
      "step": 13788
    },
    {
      "epoch": 0.4235861518139649,
      "grad_norm": 0.4138399362564087,
      "learning_rate": 1.7890655135991067e-05,
      "loss": 0.5666,
      "step": 13789
    },
    {
      "epoch": 0.4236168709489141,
      "grad_norm": 0.39537495374679565,
      "learning_rate": 1.7890358245132635e-05,
      "loss": 0.5847,
      "step": 13790
    },
    {
      "epoch": 0.4236475900838632,
      "grad_norm": 0.3495256304740906,
      "learning_rate": 1.789006133584572e-05,
      "loss": 0.5249,
      "step": 13791
    },
    {
      "epoch": 0.4236783092188124,
      "grad_norm": 0.3657526969909668,
      "learning_rate": 1.788976440813102e-05,
      "loss": 0.5574,
      "step": 13792
    },
    {
      "epoch": 0.42370902835376156,
      "grad_norm": 0.36745157837867737,
      "learning_rate": 1.788946746198922e-05,
      "loss": 0.5079,
      "step": 13793
    },
    {
      "epoch": 0.42373974748871074,
      "grad_norm": 0.37793049216270447,
      "learning_rate": 1.788917049742102e-05,
      "loss": 0.5867,
      "step": 13794
    },
    {
      "epoch": 0.42377046662365986,
      "grad_norm": 0.3281875252723694,
      "learning_rate": 1.788887351442711e-05,
      "loss": 0.5308,
      "step": 13795
    },
    {
      "epoch": 0.42380118575860903,
      "grad_norm": 0.31238216161727905,
      "learning_rate": 1.7888576513008186e-05,
      "loss": 0.5438,
      "step": 13796
    },
    {
      "epoch": 0.4238319048935582,
      "grad_norm": 0.3507313132286072,
      "learning_rate": 1.788827949316494e-05,
      "loss": 0.5928,
      "step": 13797
    },
    {
      "epoch": 0.4238626240285074,
      "grad_norm": 0.35526421666145325,
      "learning_rate": 1.788798245489806e-05,
      "loss": 0.6649,
      "step": 13798
    },
    {
      "epoch": 0.4238933431634565,
      "grad_norm": 0.42792749404907227,
      "learning_rate": 1.7887685398208258e-05,
      "loss": 0.5833,
      "step": 13799
    },
    {
      "epoch": 0.4239240622984057,
      "grad_norm": 0.36928436160087585,
      "learning_rate": 1.788738832309621e-05,
      "loss": 0.5722,
      "step": 13800
    },
    {
      "epoch": 0.42395478143335485,
      "grad_norm": 0.33646953105926514,
      "learning_rate": 1.7887091229562614e-05,
      "loss": 0.637,
      "step": 13801
    },
    {
      "epoch": 0.423985500568304,
      "grad_norm": 0.3504921793937683,
      "learning_rate": 1.788679411760817e-05,
      "loss": 0.4832,
      "step": 13802
    },
    {
      "epoch": 0.42401621970325315,
      "grad_norm": 0.3138941526412964,
      "learning_rate": 1.788649698723356e-05,
      "loss": 0.5838,
      "step": 13803
    },
    {
      "epoch": 0.4240469388382023,
      "grad_norm": 0.35928037762641907,
      "learning_rate": 1.7886199838439492e-05,
      "loss": 0.5626,
      "step": 13804
    },
    {
      "epoch": 0.4240776579731515,
      "grad_norm": 0.33818739652633667,
      "learning_rate": 1.788590267122665e-05,
      "loss": 0.6512,
      "step": 13805
    },
    {
      "epoch": 0.4241083771081006,
      "grad_norm": 0.36346733570098877,
      "learning_rate": 1.7885605485595736e-05,
      "loss": 0.5408,
      "step": 13806
    },
    {
      "epoch": 0.4241390962430498,
      "grad_norm": 0.38370373845100403,
      "learning_rate": 1.7885308281547438e-05,
      "loss": 0.6361,
      "step": 13807
    },
    {
      "epoch": 0.42416981537799897,
      "grad_norm": 0.3630296289920807,
      "learning_rate": 1.788501105908245e-05,
      "loss": 0.6639,
      "step": 13808
    },
    {
      "epoch": 0.4242005345129481,
      "grad_norm": 0.45626309514045715,
      "learning_rate": 1.788471381820147e-05,
      "loss": 0.58,
      "step": 13809
    },
    {
      "epoch": 0.42423125364789727,
      "grad_norm": 0.3506886661052704,
      "learning_rate": 1.788441655890519e-05,
      "loss": 0.5829,
      "step": 13810
    },
    {
      "epoch": 0.42426197278284644,
      "grad_norm": 0.34192296862602234,
      "learning_rate": 1.7884119281194304e-05,
      "loss": 0.5756,
      "step": 13811
    },
    {
      "epoch": 0.4242926919177956,
      "grad_norm": 0.8025415539741516,
      "learning_rate": 1.7883821985069506e-05,
      "loss": 0.6448,
      "step": 13812
    },
    {
      "epoch": 0.42432341105274474,
      "grad_norm": 0.35355284810066223,
      "learning_rate": 1.788352467053149e-05,
      "loss": 0.5391,
      "step": 13813
    },
    {
      "epoch": 0.4243541301876939,
      "grad_norm": 0.4945549964904785,
      "learning_rate": 1.788322733758095e-05,
      "loss": 0.6177,
      "step": 13814
    },
    {
      "epoch": 0.4243848493226431,
      "grad_norm": 0.36303314566612244,
      "learning_rate": 1.7882929986218587e-05,
      "loss": 0.5845,
      "step": 13815
    },
    {
      "epoch": 0.4244155684575922,
      "grad_norm": 0.4005300998687744,
      "learning_rate": 1.788263261644509e-05,
      "loss": 0.5893,
      "step": 13816
    },
    {
      "epoch": 0.4244462875925414,
      "grad_norm": 0.46209731698036194,
      "learning_rate": 1.7882335228261155e-05,
      "loss": 0.5431,
      "step": 13817
    },
    {
      "epoch": 0.42447700672749056,
      "grad_norm": 0.3015206754207611,
      "learning_rate": 1.7882037821667472e-05,
      "loss": 0.5566,
      "step": 13818
    },
    {
      "epoch": 0.42450772586243973,
      "grad_norm": 0.3406355679035187,
      "learning_rate": 1.788174039666474e-05,
      "loss": 0.616,
      "step": 13819
    },
    {
      "epoch": 0.42453844499738885,
      "grad_norm": 0.37871766090393066,
      "learning_rate": 1.7881442953253653e-05,
      "loss": 0.6068,
      "step": 13820
    },
    {
      "epoch": 0.42456916413233803,
      "grad_norm": 0.35765329003334045,
      "learning_rate": 1.7881145491434906e-05,
      "loss": 0.6055,
      "step": 13821
    },
    {
      "epoch": 0.4245998832672872,
      "grad_norm": 0.7031141519546509,
      "learning_rate": 1.788084801120919e-05,
      "loss": 0.6109,
      "step": 13822
    },
    {
      "epoch": 0.4246306024022364,
      "grad_norm": 0.3503846824169159,
      "learning_rate": 1.7880550512577207e-05,
      "loss": 0.6006,
      "step": 13823
    },
    {
      "epoch": 0.4246613215371855,
      "grad_norm": 0.33871448040008545,
      "learning_rate": 1.788025299553965e-05,
      "loss": 0.5532,
      "step": 13824
    },
    {
      "epoch": 0.4246920406721347,
      "grad_norm": 0.3547748327255249,
      "learning_rate": 1.787995546009721e-05,
      "loss": 0.5721,
      "step": 13825
    },
    {
      "epoch": 0.42472275980708385,
      "grad_norm": 0.41906583309173584,
      "learning_rate": 1.7879657906250582e-05,
      "loss": 0.5833,
      "step": 13826
    },
    {
      "epoch": 0.42475347894203297,
      "grad_norm": 0.3963031768798828,
      "learning_rate": 1.787936033400046e-05,
      "loss": 0.6165,
      "step": 13827
    },
    {
      "epoch": 0.42478419807698214,
      "grad_norm": 0.37570592761039734,
      "learning_rate": 1.787906274334755e-05,
      "loss": 0.5633,
      "step": 13828
    },
    {
      "epoch": 0.4248149172119313,
      "grad_norm": 0.4359897971153259,
      "learning_rate": 1.7878765134292534e-05,
      "loss": 0.6408,
      "step": 13829
    },
    {
      "epoch": 0.4248456363468805,
      "grad_norm": 0.4180382788181305,
      "learning_rate": 1.787846750683611e-05,
      "loss": 0.5975,
      "step": 13830
    },
    {
      "epoch": 0.4248763554818296,
      "grad_norm": 0.5160223245620728,
      "learning_rate": 1.7878169860978975e-05,
      "loss": 0.5835,
      "step": 13831
    },
    {
      "epoch": 0.4249070746167788,
      "grad_norm": 0.34342968463897705,
      "learning_rate": 1.7877872196721827e-05,
      "loss": 0.5107,
      "step": 13832
    },
    {
      "epoch": 0.42493779375172797,
      "grad_norm": 0.344064861536026,
      "learning_rate": 1.7877574514065355e-05,
      "loss": 0.5219,
      "step": 13833
    },
    {
      "epoch": 0.4249685128866771,
      "grad_norm": 0.3588239550590515,
      "learning_rate": 1.787727681301026e-05,
      "loss": 0.577,
      "step": 13834
    },
    {
      "epoch": 0.42499923202162626,
      "grad_norm": 0.3423170745372772,
      "learning_rate": 1.7876979093557233e-05,
      "loss": 0.5615,
      "step": 13835
    },
    {
      "epoch": 0.42502995115657544,
      "grad_norm": 0.4581453800201416,
      "learning_rate": 1.7876681355706972e-05,
      "loss": 0.5396,
      "step": 13836
    },
    {
      "epoch": 0.4250606702915246,
      "grad_norm": 0.33521413803100586,
      "learning_rate": 1.7876383599460173e-05,
      "loss": 0.5637,
      "step": 13837
    },
    {
      "epoch": 0.42509138942647373,
      "grad_norm": 0.6350281238555908,
      "learning_rate": 1.787608582481753e-05,
      "loss": 0.533,
      "step": 13838
    },
    {
      "epoch": 0.4251221085614229,
      "grad_norm": 0.35194724798202515,
      "learning_rate": 1.7875788031779734e-05,
      "loss": 0.5942,
      "step": 13839
    },
    {
      "epoch": 0.4251528276963721,
      "grad_norm": 0.37574461102485657,
      "learning_rate": 1.787549022034749e-05,
      "loss": 0.6013,
      "step": 13840
    },
    {
      "epoch": 0.42518354683132126,
      "grad_norm": 0.3320836126804352,
      "learning_rate": 1.7875192390521487e-05,
      "loss": 0.5144,
      "step": 13841
    },
    {
      "epoch": 0.4252142659662704,
      "grad_norm": 0.3225395679473877,
      "learning_rate": 1.7874894542302423e-05,
      "loss": 0.5597,
      "step": 13842
    },
    {
      "epoch": 0.42524498510121955,
      "grad_norm": 0.3692372441291809,
      "learning_rate": 1.7874596675690995e-05,
      "loss": 0.5598,
      "step": 13843
    },
    {
      "epoch": 0.42527570423616873,
      "grad_norm": 0.3461536169052124,
      "learning_rate": 1.787429879068789e-05,
      "loss": 0.6576,
      "step": 13844
    },
    {
      "epoch": 0.42530642337111785,
      "grad_norm": 0.36904603242874146,
      "learning_rate": 1.7874000887293814e-05,
      "loss": 0.6715,
      "step": 13845
    },
    {
      "epoch": 0.425337142506067,
      "grad_norm": 0.3753088116645813,
      "learning_rate": 1.7873702965509458e-05,
      "loss": 0.4214,
      "step": 13846
    },
    {
      "epoch": 0.4253678616410162,
      "grad_norm": 0.33823350071907043,
      "learning_rate": 1.7873405025335522e-05,
      "loss": 0.6334,
      "step": 13847
    },
    {
      "epoch": 0.4253985807759654,
      "grad_norm": 0.3643438220024109,
      "learning_rate": 1.7873107066772694e-05,
      "loss": 0.5443,
      "step": 13848
    },
    {
      "epoch": 0.4254292999109145,
      "grad_norm": 0.38709792494773865,
      "learning_rate": 1.787280908982168e-05,
      "loss": 0.6528,
      "step": 13849
    },
    {
      "epoch": 0.42546001904586367,
      "grad_norm": 0.41475656628608704,
      "learning_rate": 1.7872511094483166e-05,
      "loss": 0.6021,
      "step": 13850
    },
    {
      "epoch": 0.42549073818081284,
      "grad_norm": 0.36581259965896606,
      "learning_rate": 1.7872213080757853e-05,
      "loss": 0.6114,
      "step": 13851
    },
    {
      "epoch": 0.42552145731576196,
      "grad_norm": 0.3382721245288849,
      "learning_rate": 1.787191504864644e-05,
      "loss": 0.6362,
      "step": 13852
    },
    {
      "epoch": 0.42555217645071114,
      "grad_norm": 0.43712174892425537,
      "learning_rate": 1.7871616998149616e-05,
      "loss": 0.5322,
      "step": 13853
    },
    {
      "epoch": 0.4255828955856603,
      "grad_norm": 0.36466825008392334,
      "learning_rate": 1.787131892926808e-05,
      "loss": 0.6119,
      "step": 13854
    },
    {
      "epoch": 0.4256136147206095,
      "grad_norm": 0.36450842022895813,
      "learning_rate": 1.787102084200253e-05,
      "loss": 0.6173,
      "step": 13855
    },
    {
      "epoch": 0.4256443338555586,
      "grad_norm": 0.33186736702919006,
      "learning_rate": 1.7870722736353664e-05,
      "loss": 0.5676,
      "step": 13856
    },
    {
      "epoch": 0.4256750529905078,
      "grad_norm": 0.3334033191204071,
      "learning_rate": 1.7870424612322174e-05,
      "loss": 0.5547,
      "step": 13857
    },
    {
      "epoch": 0.42570577212545696,
      "grad_norm": 0.3444192111492157,
      "learning_rate": 1.7870126469908754e-05,
      "loss": 0.6417,
      "step": 13858
    },
    {
      "epoch": 0.4257364912604061,
      "grad_norm": 0.3518643081188202,
      "learning_rate": 1.786982830911411e-05,
      "loss": 0.6009,
      "step": 13859
    },
    {
      "epoch": 0.42576721039535526,
      "grad_norm": 0.32228201627731323,
      "learning_rate": 1.7869530129938928e-05,
      "loss": 0.5404,
      "step": 13860
    },
    {
      "epoch": 0.42579792953030443,
      "grad_norm": 0.7894916534423828,
      "learning_rate": 1.786923193238391e-05,
      "loss": 0.5982,
      "step": 13861
    },
    {
      "epoch": 0.4258286486652536,
      "grad_norm": 0.4025440216064453,
      "learning_rate": 1.786893371644975e-05,
      "loss": 0.5749,
      "step": 13862
    },
    {
      "epoch": 0.4258593678002027,
      "grad_norm": 0.3339258134365082,
      "learning_rate": 1.786863548213715e-05,
      "loss": 0.5354,
      "step": 13863
    },
    {
      "epoch": 0.4258900869351519,
      "grad_norm": 0.3260866701602936,
      "learning_rate": 1.78683372294468e-05,
      "loss": 0.5923,
      "step": 13864
    },
    {
      "epoch": 0.4259208060701011,
      "grad_norm": 0.34091079235076904,
      "learning_rate": 1.7868038958379395e-05,
      "loss": 0.5953,
      "step": 13865
    },
    {
      "epoch": 0.42595152520505025,
      "grad_norm": 0.46686244010925293,
      "learning_rate": 1.786774066893564e-05,
      "loss": 0.6154,
      "step": 13866
    },
    {
      "epoch": 0.42598224433999937,
      "grad_norm": 0.3384016752243042,
      "learning_rate": 1.7867442361116227e-05,
      "loss": 0.5214,
      "step": 13867
    },
    {
      "epoch": 0.42601296347494855,
      "grad_norm": 0.32860657572746277,
      "learning_rate": 1.786714403492185e-05,
      "loss": 0.5949,
      "step": 13868
    },
    {
      "epoch": 0.4260436826098977,
      "grad_norm": 0.32303205132484436,
      "learning_rate": 1.786684569035321e-05,
      "loss": 0.5627,
      "step": 13869
    },
    {
      "epoch": 0.42607440174484684,
      "grad_norm": 0.33524858951568604,
      "learning_rate": 1.7866547327411005e-05,
      "loss": 0.6097,
      "step": 13870
    },
    {
      "epoch": 0.426105120879796,
      "grad_norm": 0.4093991219997406,
      "learning_rate": 1.7866248946095927e-05,
      "loss": 0.504,
      "step": 13871
    },
    {
      "epoch": 0.4261358400147452,
      "grad_norm": 0.34276220202445984,
      "learning_rate": 1.7865950546408677e-05,
      "loss": 0.5617,
      "step": 13872
    },
    {
      "epoch": 0.42616655914969437,
      "grad_norm": 0.3908942639827728,
      "learning_rate": 1.7865652128349946e-05,
      "loss": 0.5855,
      "step": 13873
    },
    {
      "epoch": 0.4261972782846435,
      "grad_norm": 0.4023450016975403,
      "learning_rate": 1.786535369192044e-05,
      "loss": 0.5331,
      "step": 13874
    },
    {
      "epoch": 0.42622799741959266,
      "grad_norm": 0.36015960574150085,
      "learning_rate": 1.786505523712085e-05,
      "loss": 0.5556,
      "step": 13875
    },
    {
      "epoch": 0.42625871655454184,
      "grad_norm": 0.3130751848220825,
      "learning_rate": 1.7864756763951868e-05,
      "loss": 0.5191,
      "step": 13876
    },
    {
      "epoch": 0.42628943568949096,
      "grad_norm": 0.34965598583221436,
      "learning_rate": 1.7864458272414205e-05,
      "loss": 0.6517,
      "step": 13877
    },
    {
      "epoch": 0.42632015482444013,
      "grad_norm": 0.3311425745487213,
      "learning_rate": 1.7864159762508548e-05,
      "loss": 0.5197,
      "step": 13878
    },
    {
      "epoch": 0.4263508739593893,
      "grad_norm": 0.48655128479003906,
      "learning_rate": 1.7863861234235598e-05,
      "loss": 0.6654,
      "step": 13879
    },
    {
      "epoch": 0.4263815930943385,
      "grad_norm": 0.33261197805404663,
      "learning_rate": 1.786356268759605e-05,
      "loss": 0.5531,
      "step": 13880
    },
    {
      "epoch": 0.4264123122292876,
      "grad_norm": 0.342721551656723,
      "learning_rate": 1.78632641225906e-05,
      "loss": 0.6044,
      "step": 13881
    },
    {
      "epoch": 0.4264430313642368,
      "grad_norm": 0.38254448771476746,
      "learning_rate": 1.786296553921995e-05,
      "loss": 0.5286,
      "step": 13882
    },
    {
      "epoch": 0.42647375049918596,
      "grad_norm": 0.3640389144420624,
      "learning_rate": 1.7862666937484795e-05,
      "loss": 0.5128,
      "step": 13883
    },
    {
      "epoch": 0.42650446963413513,
      "grad_norm": 0.3872791528701782,
      "learning_rate": 1.786236831738583e-05,
      "loss": 0.5975,
      "step": 13884
    },
    {
      "epoch": 0.42653518876908425,
      "grad_norm": 0.3666490614414215,
      "learning_rate": 1.7862069678923756e-05,
      "loss": 0.6286,
      "step": 13885
    },
    {
      "epoch": 0.4265659079040334,
      "grad_norm": 0.32976633310317993,
      "learning_rate": 1.786177102209927e-05,
      "loss": 0.5523,
      "step": 13886
    },
    {
      "epoch": 0.4265966270389826,
      "grad_norm": 0.3494909107685089,
      "learning_rate": 1.7861472346913065e-05,
      "loss": 0.5962,
      "step": 13887
    },
    {
      "epoch": 0.4266273461739317,
      "grad_norm": 0.3578147292137146,
      "learning_rate": 1.7861173653365847e-05,
      "loss": 0.5257,
      "step": 13888
    },
    {
      "epoch": 0.4266580653088809,
      "grad_norm": 0.7444906234741211,
      "learning_rate": 1.7860874941458306e-05,
      "loss": 0.5738,
      "step": 13889
    },
    {
      "epoch": 0.42668878444383007,
      "grad_norm": 0.3363628089427948,
      "learning_rate": 1.7860576211191146e-05,
      "loss": 0.5111,
      "step": 13890
    },
    {
      "epoch": 0.42671950357877925,
      "grad_norm": 0.3665574789047241,
      "learning_rate": 1.7860277462565058e-05,
      "loss": 0.6165,
      "step": 13891
    },
    {
      "epoch": 0.42675022271372837,
      "grad_norm": 0.3505662679672241,
      "learning_rate": 1.785997869558074e-05,
      "loss": 0.5262,
      "step": 13892
    },
    {
      "epoch": 0.42678094184867754,
      "grad_norm": 0.3557291328907013,
      "learning_rate": 1.7859679910238902e-05,
      "loss": 0.5836,
      "step": 13893
    },
    {
      "epoch": 0.4268116609836267,
      "grad_norm": 0.36337944865226746,
      "learning_rate": 1.7859381106540223e-05,
      "loss": 0.5963,
      "step": 13894
    },
    {
      "epoch": 0.42684238011857584,
      "grad_norm": 0.32715341448783875,
      "learning_rate": 1.7859082284485415e-05,
      "loss": 0.5439,
      "step": 13895
    },
    {
      "epoch": 0.426873099253525,
      "grad_norm": 0.3451557755470276,
      "learning_rate": 1.7858783444075172e-05,
      "loss": 0.5141,
      "step": 13896
    },
    {
      "epoch": 0.4269038183884742,
      "grad_norm": 0.35858291387557983,
      "learning_rate": 1.7858484585310193e-05,
      "loss": 0.6078,
      "step": 13897
    },
    {
      "epoch": 0.42693453752342336,
      "grad_norm": 0.3377326428890228,
      "learning_rate": 1.7858185708191173e-05,
      "loss": 0.5615,
      "step": 13898
    },
    {
      "epoch": 0.4269652566583725,
      "grad_norm": 0.3551117777824402,
      "learning_rate": 1.785788681271881e-05,
      "loss": 0.5614,
      "step": 13899
    },
    {
      "epoch": 0.42699597579332166,
      "grad_norm": 0.34750765562057495,
      "learning_rate": 1.78575878988938e-05,
      "loss": 0.5422,
      "step": 13900
    },
    {
      "epoch": 0.42702669492827083,
      "grad_norm": 0.3729635179042816,
      "learning_rate": 1.7857288966716853e-05,
      "loss": 0.5549,
      "step": 13901
    },
    {
      "epoch": 0.42705741406321995,
      "grad_norm": 0.3750109374523163,
      "learning_rate": 1.7856990016188654e-05,
      "loss": 0.6019,
      "step": 13902
    },
    {
      "epoch": 0.42708813319816913,
      "grad_norm": 0.314452201128006,
      "learning_rate": 1.7856691047309907e-05,
      "loss": 0.6033,
      "step": 13903
    },
    {
      "epoch": 0.4271188523331183,
      "grad_norm": 0.33650660514831543,
      "learning_rate": 1.785639206008131e-05,
      "loss": 0.6413,
      "step": 13904
    },
    {
      "epoch": 0.4271495714680675,
      "grad_norm": 0.3828151226043701,
      "learning_rate": 1.785609305450356e-05,
      "loss": 0.5187,
      "step": 13905
    },
    {
      "epoch": 0.4271802906030166,
      "grad_norm": 0.40795302391052246,
      "learning_rate": 1.7855794030577357e-05,
      "loss": 0.5258,
      "step": 13906
    },
    {
      "epoch": 0.4272110097379658,
      "grad_norm": 0.32419028878211975,
      "learning_rate": 1.7855494988303395e-05,
      "loss": 0.606,
      "step": 13907
    },
    {
      "epoch": 0.42724172887291495,
      "grad_norm": 0.6918889284133911,
      "learning_rate": 1.7855195927682377e-05,
      "loss": 0.6443,
      "step": 13908
    },
    {
      "epoch": 0.4272724480078641,
      "grad_norm": 0.3365534245967865,
      "learning_rate": 1.7854896848715002e-05,
      "loss": 0.564,
      "step": 13909
    },
    {
      "epoch": 0.42730316714281324,
      "grad_norm": 0.3904309868812561,
      "learning_rate": 1.7854597751401964e-05,
      "loss": 0.6227,
      "step": 13910
    },
    {
      "epoch": 0.4273338862777624,
      "grad_norm": 0.4170694351196289,
      "learning_rate": 1.785429863574397e-05,
      "loss": 0.6137,
      "step": 13911
    },
    {
      "epoch": 0.4273646054127116,
      "grad_norm": 0.35710933804512024,
      "learning_rate": 1.785399950174171e-05,
      "loss": 0.5698,
      "step": 13912
    },
    {
      "epoch": 0.4273953245476607,
      "grad_norm": 0.3696695566177368,
      "learning_rate": 1.7853700349395885e-05,
      "loss": 0.5886,
      "step": 13913
    },
    {
      "epoch": 0.4274260436826099,
      "grad_norm": 0.3560411334037781,
      "learning_rate": 1.785340117870719e-05,
      "loss": 0.5281,
      "step": 13914
    },
    {
      "epoch": 0.42745676281755907,
      "grad_norm": 0.36582276225090027,
      "learning_rate": 1.7853101989676334e-05,
      "loss": 0.6458,
      "step": 13915
    },
    {
      "epoch": 0.42748748195250824,
      "grad_norm": 0.3169812262058258,
      "learning_rate": 1.785280278230401e-05,
      "loss": 0.5259,
      "step": 13916
    },
    {
      "epoch": 0.42751820108745736,
      "grad_norm": 0.36424052715301514,
      "learning_rate": 1.7852503556590917e-05,
      "loss": 0.6169,
      "step": 13917
    },
    {
      "epoch": 0.42754892022240654,
      "grad_norm": 0.3553009331226349,
      "learning_rate": 1.7852204312537752e-05,
      "loss": 0.5784,
      "step": 13918
    },
    {
      "epoch": 0.4275796393573557,
      "grad_norm": 0.3858945667743683,
      "learning_rate": 1.7851905050145216e-05,
      "loss": 0.6102,
      "step": 13919
    },
    {
      "epoch": 0.42761035849230483,
      "grad_norm": 0.33275553584098816,
      "learning_rate": 1.7851605769414003e-05,
      "loss": 0.5952,
      "step": 13920
    },
    {
      "epoch": 0.427641077627254,
      "grad_norm": 0.3383229374885559,
      "learning_rate": 1.785130647034482e-05,
      "loss": 0.5442,
      "step": 13921
    },
    {
      "epoch": 0.4276717967622032,
      "grad_norm": 0.3414721190929413,
      "learning_rate": 1.7851007152938363e-05,
      "loss": 0.5651,
      "step": 13922
    },
    {
      "epoch": 0.42770251589715236,
      "grad_norm": 0.3289460837841034,
      "learning_rate": 1.7850707817195328e-05,
      "loss": 0.6455,
      "step": 13923
    },
    {
      "epoch": 0.4277332350321015,
      "grad_norm": 0.3715989887714386,
      "learning_rate": 1.7850408463116422e-05,
      "loss": 0.5413,
      "step": 13924
    },
    {
      "epoch": 0.42776395416705065,
      "grad_norm": 0.3330579102039337,
      "learning_rate": 1.7850109090702333e-05,
      "loss": 0.5225,
      "step": 13925
    },
    {
      "epoch": 0.42779467330199983,
      "grad_norm": 0.350081205368042,
      "learning_rate": 1.784980969995377e-05,
      "loss": 0.54,
      "step": 13926
    },
    {
      "epoch": 0.42782539243694895,
      "grad_norm": 0.3623183071613312,
      "learning_rate": 1.7849510290871426e-05,
      "loss": 0.7043,
      "step": 13927
    },
    {
      "epoch": 0.4278561115718981,
      "grad_norm": 0.3611922860145569,
      "learning_rate": 1.7849210863456004e-05,
      "loss": 0.5613,
      "step": 13928
    },
    {
      "epoch": 0.4278868307068473,
      "grad_norm": 0.3615553379058838,
      "learning_rate": 1.78489114177082e-05,
      "loss": 0.6552,
      "step": 13929
    },
    {
      "epoch": 0.4279175498417965,
      "grad_norm": 0.33187663555145264,
      "learning_rate": 1.7848611953628717e-05,
      "loss": 0.5787,
      "step": 13930
    },
    {
      "epoch": 0.4279482689767456,
      "grad_norm": 0.37295347452163696,
      "learning_rate": 1.784831247121825e-05,
      "loss": 0.5773,
      "step": 13931
    },
    {
      "epoch": 0.42797898811169477,
      "grad_norm": 0.37032562494277954,
      "learning_rate": 1.7848012970477505e-05,
      "loss": 0.5985,
      "step": 13932
    },
    {
      "epoch": 0.42800970724664394,
      "grad_norm": 0.3726099729537964,
      "learning_rate": 1.7847713451407172e-05,
      "loss": 0.6176,
      "step": 13933
    },
    {
      "epoch": 0.4280404263815931,
      "grad_norm": 0.32461023330688477,
      "learning_rate": 1.784741391400796e-05,
      "loss": 0.5649,
      "step": 13934
    },
    {
      "epoch": 0.42807114551654224,
      "grad_norm": 0.34349778294563293,
      "learning_rate": 1.7847114358280567e-05,
      "loss": 0.6081,
      "step": 13935
    },
    {
      "epoch": 0.4281018646514914,
      "grad_norm": 0.33179178833961487,
      "learning_rate": 1.7846814784225686e-05,
      "loss": 0.5552,
      "step": 13936
    },
    {
      "epoch": 0.4281325837864406,
      "grad_norm": 0.3529262840747833,
      "learning_rate": 1.784651519184402e-05,
      "loss": 0.6003,
      "step": 13937
    },
    {
      "epoch": 0.4281633029213897,
      "grad_norm": 0.35609281063079834,
      "learning_rate": 1.7846215581136274e-05,
      "loss": 0.5081,
      "step": 13938
    },
    {
      "epoch": 0.4281940220563389,
      "grad_norm": 0.3329264223575592,
      "learning_rate": 1.7845915952103145e-05,
      "loss": 0.5957,
      "step": 13939
    },
    {
      "epoch": 0.42822474119128806,
      "grad_norm": 0.3495156168937683,
      "learning_rate": 1.784561630474533e-05,
      "loss": 0.5797,
      "step": 13940
    },
    {
      "epoch": 0.42825546032623724,
      "grad_norm": 0.40278106927871704,
      "learning_rate": 1.7845316639063527e-05,
      "loss": 0.6065,
      "step": 13941
    },
    {
      "epoch": 0.42828617946118636,
      "grad_norm": 0.3306826055049896,
      "learning_rate": 1.7845016955058437e-05,
      "loss": 0.5288,
      "step": 13942
    },
    {
      "epoch": 0.42831689859613553,
      "grad_norm": 0.3385336697101593,
      "learning_rate": 1.7844717252730767e-05,
      "loss": 0.5607,
      "step": 13943
    },
    {
      "epoch": 0.4283476177310847,
      "grad_norm": 0.36988621950149536,
      "learning_rate": 1.784441753208121e-05,
      "loss": 0.6185,
      "step": 13944
    },
    {
      "epoch": 0.4283783368660338,
      "grad_norm": 0.37286874651908875,
      "learning_rate": 1.7844117793110468e-05,
      "loss": 0.65,
      "step": 13945
    },
    {
      "epoch": 0.428409056000983,
      "grad_norm": 0.3061349093914032,
      "learning_rate": 1.7843818035819244e-05,
      "loss": 0.5427,
      "step": 13946
    },
    {
      "epoch": 0.4284397751359322,
      "grad_norm": 0.3115340769290924,
      "learning_rate": 1.7843518260208232e-05,
      "loss": 0.6125,
      "step": 13947
    },
    {
      "epoch": 0.42847049427088135,
      "grad_norm": 0.33794912695884705,
      "learning_rate": 1.7843218466278137e-05,
      "loss": 0.6479,
      "step": 13948
    },
    {
      "epoch": 0.4285012134058305,
      "grad_norm": 0.35065948963165283,
      "learning_rate": 1.7842918654029654e-05,
      "loss": 0.6292,
      "step": 13949
    },
    {
      "epoch": 0.42853193254077965,
      "grad_norm": 0.383851021528244,
      "learning_rate": 1.784261882346349e-05,
      "loss": 0.5666,
      "step": 13950
    },
    {
      "epoch": 0.4285626516757288,
      "grad_norm": 0.376465380191803,
      "learning_rate": 1.7842318974580344e-05,
      "loss": 0.6093,
      "step": 13951
    },
    {
      "epoch": 0.428593370810678,
      "grad_norm": 0.34331902861595154,
      "learning_rate": 1.784201910738091e-05,
      "loss": 0.6231,
      "step": 13952
    },
    {
      "epoch": 0.4286240899456271,
      "grad_norm": 0.3490898311138153,
      "learning_rate": 1.7841719221865895e-05,
      "loss": 0.5111,
      "step": 13953
    },
    {
      "epoch": 0.4286548090805763,
      "grad_norm": 0.36792081594467163,
      "learning_rate": 1.7841419318035996e-05,
      "loss": 0.5455,
      "step": 13954
    },
    {
      "epoch": 0.42868552821552547,
      "grad_norm": 0.34153249859809875,
      "learning_rate": 1.7841119395891917e-05,
      "loss": 0.5317,
      "step": 13955
    },
    {
      "epoch": 0.4287162473504746,
      "grad_norm": 0.35032087564468384,
      "learning_rate": 1.784081945543435e-05,
      "loss": 0.5625,
      "step": 13956
    },
    {
      "epoch": 0.42874696648542376,
      "grad_norm": 0.3295805752277374,
      "learning_rate": 1.7840519496664008e-05,
      "loss": 0.5313,
      "step": 13957
    },
    {
      "epoch": 0.42877768562037294,
      "grad_norm": 0.4071832299232483,
      "learning_rate": 1.784021951958158e-05,
      "loss": 0.6667,
      "step": 13958
    },
    {
      "epoch": 0.4288084047553221,
      "grad_norm": 0.42279133200645447,
      "learning_rate": 1.7839919524187776e-05,
      "loss": 0.6256,
      "step": 13959
    },
    {
      "epoch": 0.42883912389027123,
      "grad_norm": 0.3264189064502716,
      "learning_rate": 1.7839619510483294e-05,
      "loss": 0.4911,
      "step": 13960
    },
    {
      "epoch": 0.4288698430252204,
      "grad_norm": 0.3696635365486145,
      "learning_rate": 1.783931947846883e-05,
      "loss": 0.5474,
      "step": 13961
    },
    {
      "epoch": 0.4289005621601696,
      "grad_norm": 0.3753335773944855,
      "learning_rate": 1.7839019428145087e-05,
      "loss": 0.5745,
      "step": 13962
    },
    {
      "epoch": 0.4289312812951187,
      "grad_norm": 0.654650866985321,
      "learning_rate": 1.7838719359512768e-05,
      "loss": 0.5674,
      "step": 13963
    },
    {
      "epoch": 0.4289620004300679,
      "grad_norm": 0.3590349555015564,
      "learning_rate": 1.783841927257257e-05,
      "loss": 0.6742,
      "step": 13964
    },
    {
      "epoch": 0.42899271956501706,
      "grad_norm": 0.3972882032394409,
      "learning_rate": 1.7838119167325202e-05,
      "loss": 0.6364,
      "step": 13965
    },
    {
      "epoch": 0.42902343869996623,
      "grad_norm": 0.34892600774765015,
      "learning_rate": 1.7837819043771355e-05,
      "loss": 0.5852,
      "step": 13966
    },
    {
      "epoch": 0.42905415783491535,
      "grad_norm": 0.30990341305732727,
      "learning_rate": 1.7837518901911733e-05,
      "loss": 0.5306,
      "step": 13967
    },
    {
      "epoch": 0.4290848769698645,
      "grad_norm": 0.3437008857727051,
      "learning_rate": 1.7837218741747042e-05,
      "loss": 0.6164,
      "step": 13968
    },
    {
      "epoch": 0.4291155961048137,
      "grad_norm": 0.33658692240715027,
      "learning_rate": 1.783691856327798e-05,
      "loss": 0.5304,
      "step": 13969
    },
    {
      "epoch": 0.4291463152397628,
      "grad_norm": 0.40659305453300476,
      "learning_rate": 1.783661836650524e-05,
      "loss": 0.5619,
      "step": 13970
    },
    {
      "epoch": 0.429177034374712,
      "grad_norm": 0.337517648935318,
      "learning_rate": 1.7836318151429538e-05,
      "loss": 0.5341,
      "step": 13971
    },
    {
      "epoch": 0.42920775350966117,
      "grad_norm": 0.3652278482913971,
      "learning_rate": 1.7836017918051564e-05,
      "loss": 0.4903,
      "step": 13972
    },
    {
      "epoch": 0.42923847264461035,
      "grad_norm": 0.39821022748947144,
      "learning_rate": 1.7835717666372027e-05,
      "loss": 0.457,
      "step": 13973
    },
    {
      "epoch": 0.42926919177955947,
      "grad_norm": 0.3859250247478485,
      "learning_rate": 1.7835417396391618e-05,
      "loss": 0.6715,
      "step": 13974
    },
    {
      "epoch": 0.42929991091450864,
      "grad_norm": 0.44490766525268555,
      "learning_rate": 1.7835117108111048e-05,
      "loss": 0.6299,
      "step": 13975
    },
    {
      "epoch": 0.4293306300494578,
      "grad_norm": 0.3350333273410797,
      "learning_rate": 1.7834816801531013e-05,
      "loss": 0.5278,
      "step": 13976
    },
    {
      "epoch": 0.429361349184407,
      "grad_norm": 0.5774491429328918,
      "learning_rate": 1.783451647665222e-05,
      "loss": 0.5214,
      "step": 13977
    },
    {
      "epoch": 0.4293920683193561,
      "grad_norm": 0.34992581605911255,
      "learning_rate": 1.7834216133475364e-05,
      "loss": 0.5964,
      "step": 13978
    },
    {
      "epoch": 0.4294227874543053,
      "grad_norm": 0.36204203963279724,
      "learning_rate": 1.783391577200115e-05,
      "loss": 0.5945,
      "step": 13979
    },
    {
      "epoch": 0.42945350658925446,
      "grad_norm": 0.3479914367198944,
      "learning_rate": 1.7833615392230278e-05,
      "loss": 0.6297,
      "step": 13980
    },
    {
      "epoch": 0.4294842257242036,
      "grad_norm": 0.3648708462715149,
      "learning_rate": 1.783331499416345e-05,
      "loss": 0.542,
      "step": 13981
    },
    {
      "epoch": 0.42951494485915276,
      "grad_norm": 0.3821769952774048,
      "learning_rate": 1.7833014577801365e-05,
      "loss": 0.6162,
      "step": 13982
    },
    {
      "epoch": 0.42954566399410193,
      "grad_norm": 0.33578070998191833,
      "learning_rate": 1.783271414314473e-05,
      "loss": 0.5741,
      "step": 13983
    },
    {
      "epoch": 0.4295763831290511,
      "grad_norm": 0.37099674344062805,
      "learning_rate": 1.7832413690194248e-05,
      "loss": 0.446,
      "step": 13984
    },
    {
      "epoch": 0.42960710226400023,
      "grad_norm": 0.6847054958343506,
      "learning_rate": 1.783211321895061e-05,
      "loss": 0.4707,
      "step": 13985
    },
    {
      "epoch": 0.4296378213989494,
      "grad_norm": 0.36954277753829956,
      "learning_rate": 1.783181272941453e-05,
      "loss": 0.5655,
      "step": 13986
    },
    {
      "epoch": 0.4296685405338986,
      "grad_norm": 0.35731831192970276,
      "learning_rate": 1.78315122215867e-05,
      "loss": 0.628,
      "step": 13987
    },
    {
      "epoch": 0.4296992596688477,
      "grad_norm": 0.3683944046497345,
      "learning_rate": 1.783121169546783e-05,
      "loss": 0.556,
      "step": 13988
    },
    {
      "epoch": 0.4297299788037969,
      "grad_norm": 0.332460880279541,
      "learning_rate": 1.7830911151058615e-05,
      "loss": 0.5305,
      "step": 13989
    },
    {
      "epoch": 0.42976069793874605,
      "grad_norm": 0.3102289140224457,
      "learning_rate": 1.7830610588359764e-05,
      "loss": 0.491,
      "step": 13990
    },
    {
      "epoch": 0.4297914170736952,
      "grad_norm": 0.3946370482444763,
      "learning_rate": 1.783031000737197e-05,
      "loss": 0.5545,
      "step": 13991
    },
    {
      "epoch": 0.42982213620864435,
      "grad_norm": 0.368053138256073,
      "learning_rate": 1.7830009408095942e-05,
      "loss": 0.5299,
      "step": 13992
    },
    {
      "epoch": 0.4298528553435935,
      "grad_norm": 0.357835054397583,
      "learning_rate": 1.7829708790532382e-05,
      "loss": 0.5666,
      "step": 13993
    },
    {
      "epoch": 0.4298835744785427,
      "grad_norm": 0.342983603477478,
      "learning_rate": 1.782940815468199e-05,
      "loss": 0.5049,
      "step": 13994
    },
    {
      "epoch": 0.42991429361349187,
      "grad_norm": 0.4189978837966919,
      "learning_rate": 1.7829107500545468e-05,
      "loss": 0.6186,
      "step": 13995
    },
    {
      "epoch": 0.429945012748441,
      "grad_norm": 0.3367140591144562,
      "learning_rate": 1.7828806828123517e-05,
      "loss": 0.5704,
      "step": 13996
    },
    {
      "epoch": 0.42997573188339017,
      "grad_norm": 0.35388699173927307,
      "learning_rate": 1.7828506137416842e-05,
      "loss": 0.4919,
      "step": 13997
    },
    {
      "epoch": 0.43000645101833934,
      "grad_norm": 0.3542553782463074,
      "learning_rate": 1.7828205428426148e-05,
      "loss": 0.52,
      "step": 13998
    },
    {
      "epoch": 0.43003717015328846,
      "grad_norm": 0.3440512716770172,
      "learning_rate": 1.782790470115213e-05,
      "loss": 0.5698,
      "step": 13999
    },
    {
      "epoch": 0.43006788928823764,
      "grad_norm": 0.36703255772590637,
      "learning_rate": 1.7827603955595493e-05,
      "loss": 0.5762,
      "step": 14000
    },
    {
      "epoch": 0.4300986084231868,
      "grad_norm": 0.3736492693424225,
      "learning_rate": 1.782730319175694e-05,
      "loss": 0.5963,
      "step": 14001
    },
    {
      "epoch": 0.430129327558136,
      "grad_norm": 0.36219048500061035,
      "learning_rate": 1.7827002409637174e-05,
      "loss": 0.6045,
      "step": 14002
    },
    {
      "epoch": 0.4301600466930851,
      "grad_norm": 0.3576197326183319,
      "learning_rate": 1.7826701609236897e-05,
      "loss": 0.4269,
      "step": 14003
    },
    {
      "epoch": 0.4301907658280343,
      "grad_norm": 0.4546017646789551,
      "learning_rate": 1.7826400790556815e-05,
      "loss": 0.5766,
      "step": 14004
    },
    {
      "epoch": 0.43022148496298346,
      "grad_norm": 0.32744723558425903,
      "learning_rate": 1.7826099953597623e-05,
      "loss": 0.5788,
      "step": 14005
    },
    {
      "epoch": 0.4302522040979326,
      "grad_norm": 0.364206463098526,
      "learning_rate": 1.7825799098360033e-05,
      "loss": 0.5645,
      "step": 14006
    },
    {
      "epoch": 0.43028292323288175,
      "grad_norm": 0.32736027240753174,
      "learning_rate": 1.782549822484474e-05,
      "loss": 0.5397,
      "step": 14007
    },
    {
      "epoch": 0.43031364236783093,
      "grad_norm": 0.3680122196674347,
      "learning_rate": 1.782519733305245e-05,
      "loss": 0.5549,
      "step": 14008
    },
    {
      "epoch": 0.4303443615027801,
      "grad_norm": 0.3656328618526459,
      "learning_rate": 1.782489642298386e-05,
      "loss": 0.5142,
      "step": 14009
    },
    {
      "epoch": 0.4303750806377292,
      "grad_norm": 0.3467338979244232,
      "learning_rate": 1.7824595494639684e-05,
      "loss": 0.4972,
      "step": 14010
    },
    {
      "epoch": 0.4304057997726784,
      "grad_norm": 0.3757704794406891,
      "learning_rate": 1.782429454802062e-05,
      "loss": 0.5745,
      "step": 14011
    },
    {
      "epoch": 0.4304365189076276,
      "grad_norm": 0.32824987173080444,
      "learning_rate": 1.7823993583127362e-05,
      "loss": 0.4919,
      "step": 14012
    },
    {
      "epoch": 0.4304672380425767,
      "grad_norm": 0.4591667056083679,
      "learning_rate": 1.7823692599960628e-05,
      "loss": 0.5816,
      "step": 14013
    },
    {
      "epoch": 0.43049795717752587,
      "grad_norm": 0.33681610226631165,
      "learning_rate": 1.7823391598521112e-05,
      "loss": 0.5571,
      "step": 14014
    },
    {
      "epoch": 0.43052867631247504,
      "grad_norm": 0.3204104006290436,
      "learning_rate": 1.7823090578809517e-05,
      "loss": 0.5941,
      "step": 14015
    },
    {
      "epoch": 0.4305593954474242,
      "grad_norm": 0.35368356108665466,
      "learning_rate": 1.7822789540826547e-05,
      "loss": 0.6106,
      "step": 14016
    },
    {
      "epoch": 0.43059011458237334,
      "grad_norm": 0.3433784544467926,
      "learning_rate": 1.7822488484572907e-05,
      "loss": 0.5726,
      "step": 14017
    },
    {
      "epoch": 0.4306208337173225,
      "grad_norm": 0.3323821723461151,
      "learning_rate": 1.7822187410049298e-05,
      "loss": 0.5974,
      "step": 14018
    },
    {
      "epoch": 0.4306515528522717,
      "grad_norm": 0.3336169719696045,
      "learning_rate": 1.7821886317256425e-05,
      "loss": 0.4815,
      "step": 14019
    },
    {
      "epoch": 0.43068227198722087,
      "grad_norm": 0.34214162826538086,
      "learning_rate": 1.782158520619499e-05,
      "loss": 0.55,
      "step": 14020
    },
    {
      "epoch": 0.43071299112217,
      "grad_norm": 0.3206334710121155,
      "learning_rate": 1.7821284076865697e-05,
      "loss": 0.4738,
      "step": 14021
    },
    {
      "epoch": 0.43074371025711916,
      "grad_norm": 0.36164259910583496,
      "learning_rate": 1.7820982929269247e-05,
      "loss": 0.5811,
      "step": 14022
    },
    {
      "epoch": 0.43077442939206834,
      "grad_norm": 0.37583765387535095,
      "learning_rate": 1.7820681763406345e-05,
      "loss": 0.6295,
      "step": 14023
    },
    {
      "epoch": 0.43080514852701746,
      "grad_norm": 0.3614848554134369,
      "learning_rate": 1.7820380579277696e-05,
      "loss": 0.6356,
      "step": 14024
    },
    {
      "epoch": 0.43083586766196663,
      "grad_norm": 0.418822318315506,
      "learning_rate": 1.7820079376884e-05,
      "loss": 0.5472,
      "step": 14025
    },
    {
      "epoch": 0.4308665867969158,
      "grad_norm": 0.4004127085208893,
      "learning_rate": 1.7819778156225966e-05,
      "loss": 0.5911,
      "step": 14026
    },
    {
      "epoch": 0.430897305931865,
      "grad_norm": 0.31576067209243774,
      "learning_rate": 1.7819476917304293e-05,
      "loss": 0.5224,
      "step": 14027
    },
    {
      "epoch": 0.4309280250668141,
      "grad_norm": 0.3303540349006653,
      "learning_rate": 1.7819175660119686e-05,
      "loss": 0.535,
      "step": 14028
    },
    {
      "epoch": 0.4309587442017633,
      "grad_norm": 0.3555672764778137,
      "learning_rate": 1.7818874384672846e-05,
      "loss": 0.5914,
      "step": 14029
    },
    {
      "epoch": 0.43098946333671245,
      "grad_norm": 0.3350389301776886,
      "learning_rate": 1.781857309096448e-05,
      "loss": 0.5667,
      "step": 14030
    },
    {
      "epoch": 0.4310201824716616,
      "grad_norm": 0.3363313674926758,
      "learning_rate": 1.781827177899529e-05,
      "loss": 0.6035,
      "step": 14031
    },
    {
      "epoch": 0.43105090160661075,
      "grad_norm": 0.352491557598114,
      "learning_rate": 1.781797044876598e-05,
      "loss": 0.5453,
      "step": 14032
    },
    {
      "epoch": 0.4310816207415599,
      "grad_norm": 0.3529573380947113,
      "learning_rate": 1.7817669100277255e-05,
      "loss": 0.5096,
      "step": 14033
    },
    {
      "epoch": 0.4311123398765091,
      "grad_norm": 0.3337060213088989,
      "learning_rate": 1.7817367733529817e-05,
      "loss": 0.4639,
      "step": 14034
    },
    {
      "epoch": 0.4311430590114582,
      "grad_norm": 0.3545793890953064,
      "learning_rate": 1.7817066348524374e-05,
      "loss": 0.5838,
      "step": 14035
    },
    {
      "epoch": 0.4311737781464074,
      "grad_norm": 0.3472176790237427,
      "learning_rate": 1.781676494526162e-05,
      "loss": 0.5551,
      "step": 14036
    },
    {
      "epoch": 0.43120449728135657,
      "grad_norm": 3.9404070377349854,
      "learning_rate": 1.781646352374227e-05,
      "loss": 0.6578,
      "step": 14037
    },
    {
      "epoch": 0.43123521641630574,
      "grad_norm": 0.3509845733642578,
      "learning_rate": 1.7816162083967023e-05,
      "loss": 0.5259,
      "step": 14038
    },
    {
      "epoch": 0.43126593555125486,
      "grad_norm": 0.3957943618297577,
      "learning_rate": 1.7815860625936583e-05,
      "loss": 0.5651,
      "step": 14039
    },
    {
      "epoch": 0.43129665468620404,
      "grad_norm": 0.3421042561531067,
      "learning_rate": 1.7815559149651654e-05,
      "loss": 0.5591,
      "step": 14040
    },
    {
      "epoch": 0.4313273738211532,
      "grad_norm": 0.3734426498413086,
      "learning_rate": 1.781525765511294e-05,
      "loss": 0.672,
      "step": 14041
    },
    {
      "epoch": 0.43135809295610233,
      "grad_norm": 0.3344945013523102,
      "learning_rate": 1.781495614232115e-05,
      "loss": 0.5299,
      "step": 14042
    },
    {
      "epoch": 0.4313888120910515,
      "grad_norm": 0.3785218298435211,
      "learning_rate": 1.781465461127698e-05,
      "loss": 0.554,
      "step": 14043
    },
    {
      "epoch": 0.4314195312260007,
      "grad_norm": 0.3682476580142975,
      "learning_rate": 1.7814353061981143e-05,
      "loss": 0.5271,
      "step": 14044
    },
    {
      "epoch": 0.43145025036094986,
      "grad_norm": 0.3543630838394165,
      "learning_rate": 1.7814051494434333e-05,
      "loss": 0.4966,
      "step": 14045
    },
    {
      "epoch": 0.431480969495899,
      "grad_norm": 0.39185863733291626,
      "learning_rate": 1.7813749908637263e-05,
      "loss": 0.648,
      "step": 14046
    },
    {
      "epoch": 0.43151168863084816,
      "grad_norm": 0.30123528838157654,
      "learning_rate": 1.7813448304590638e-05,
      "loss": 0.5836,
      "step": 14047
    },
    {
      "epoch": 0.43154240776579733,
      "grad_norm": 0.33181896805763245,
      "learning_rate": 1.7813146682295152e-05,
      "loss": 0.5904,
      "step": 14048
    },
    {
      "epoch": 0.43157312690074645,
      "grad_norm": 0.436411052942276,
      "learning_rate": 1.7812845041751517e-05,
      "loss": 0.6115,
      "step": 14049
    },
    {
      "epoch": 0.4316038460356956,
      "grad_norm": 0.34418633580207825,
      "learning_rate": 1.7812543382960445e-05,
      "loss": 0.6063,
      "step": 14050
    },
    {
      "epoch": 0.4316345651706448,
      "grad_norm": 0.36330944299697876,
      "learning_rate": 1.7812241705922622e-05,
      "loss": 0.5133,
      "step": 14051
    },
    {
      "epoch": 0.431665284305594,
      "grad_norm": 0.3952060341835022,
      "learning_rate": 1.781194001063877e-05,
      "loss": 0.6001,
      "step": 14052
    },
    {
      "epoch": 0.4316960034405431,
      "grad_norm": 0.3745608925819397,
      "learning_rate": 1.781163829710958e-05,
      "loss": 0.5869,
      "step": 14053
    },
    {
      "epoch": 0.43172672257549227,
      "grad_norm": 0.3405171036720276,
      "learning_rate": 1.781133656533577e-05,
      "loss": 0.5846,
      "step": 14054
    },
    {
      "epoch": 0.43175744171044145,
      "grad_norm": 0.3398650288581848,
      "learning_rate": 1.7811034815318034e-05,
      "loss": 0.4699,
      "step": 14055
    },
    {
      "epoch": 0.43178816084539057,
      "grad_norm": 0.33874982595443726,
      "learning_rate": 1.7810733047057084e-05,
      "loss": 0.5377,
      "step": 14056
    },
    {
      "epoch": 0.43181887998033974,
      "grad_norm": 0.3904070258140564,
      "learning_rate": 1.781043126055362e-05,
      "loss": 0.6461,
      "step": 14057
    },
    {
      "epoch": 0.4318495991152889,
      "grad_norm": 0.3501852750778198,
      "learning_rate": 1.781012945580834e-05,
      "loss": 0.4952,
      "step": 14058
    },
    {
      "epoch": 0.4318803182502381,
      "grad_norm": 0.3335086405277252,
      "learning_rate": 1.780982763282197e-05,
      "loss": 0.5933,
      "step": 14059
    },
    {
      "epoch": 0.4319110373851872,
      "grad_norm": 0.359163373708725,
      "learning_rate": 1.7809525791595198e-05,
      "loss": 0.6267,
      "step": 14060
    },
    {
      "epoch": 0.4319417565201364,
      "grad_norm": 0.34758326411247253,
      "learning_rate": 1.780922393212873e-05,
      "loss": 0.6013,
      "step": 14061
    },
    {
      "epoch": 0.43197247565508556,
      "grad_norm": 0.34582433104515076,
      "learning_rate": 1.7808922054423275e-05,
      "loss": 0.6195,
      "step": 14062
    },
    {
      "epoch": 0.43200319479003474,
      "grad_norm": 0.37053945660591125,
      "learning_rate": 1.7808620158479538e-05,
      "loss": 0.6155,
      "step": 14063
    },
    {
      "epoch": 0.43203391392498386,
      "grad_norm": 0.32199084758758545,
      "learning_rate": 1.7808318244298223e-05,
      "loss": 0.5255,
      "step": 14064
    },
    {
      "epoch": 0.43206463305993303,
      "grad_norm": 0.34385210275650024,
      "learning_rate": 1.7808016311880035e-05,
      "loss": 0.588,
      "step": 14065
    },
    {
      "epoch": 0.4320953521948822,
      "grad_norm": 0.3364744782447815,
      "learning_rate": 1.780771436122568e-05,
      "loss": 0.5194,
      "step": 14066
    },
    {
      "epoch": 0.43212607132983133,
      "grad_norm": 0.3476884961128235,
      "learning_rate": 1.7807412392335864e-05,
      "loss": 0.5379,
      "step": 14067
    },
    {
      "epoch": 0.4321567904647805,
      "grad_norm": 0.3295537829399109,
      "learning_rate": 1.780711040521129e-05,
      "loss": 0.5437,
      "step": 14068
    },
    {
      "epoch": 0.4321875095997297,
      "grad_norm": 0.3496818542480469,
      "learning_rate": 1.7806808399852666e-05,
      "loss": 0.6457,
      "step": 14069
    },
    {
      "epoch": 0.43221822873467886,
      "grad_norm": 0.35949525237083435,
      "learning_rate": 1.7806506376260695e-05,
      "loss": 0.5075,
      "step": 14070
    },
    {
      "epoch": 0.432248947869628,
      "grad_norm": 0.3994367718696594,
      "learning_rate": 1.7806204334436082e-05,
      "loss": 0.5983,
      "step": 14071
    },
    {
      "epoch": 0.43227966700457715,
      "grad_norm": 0.33497360348701477,
      "learning_rate": 1.7805902274379536e-05,
      "loss": 0.528,
      "step": 14072
    },
    {
      "epoch": 0.4323103861395263,
      "grad_norm": 0.3600756824016571,
      "learning_rate": 1.7805600196091757e-05,
      "loss": 0.461,
      "step": 14073
    },
    {
      "epoch": 0.43234110527447545,
      "grad_norm": 0.3500407040119171,
      "learning_rate": 1.7805298099573454e-05,
      "loss": 0.5921,
      "step": 14074
    },
    {
      "epoch": 0.4323718244094246,
      "grad_norm": 0.3436615765094757,
      "learning_rate": 1.7804995984825332e-05,
      "loss": 0.5546,
      "step": 14075
    },
    {
      "epoch": 0.4324025435443738,
      "grad_norm": 0.3904936611652374,
      "learning_rate": 1.78046938518481e-05,
      "loss": 0.5561,
      "step": 14076
    },
    {
      "epoch": 0.43243326267932297,
      "grad_norm": 0.3782128393650055,
      "learning_rate": 1.780439170064246e-05,
      "loss": 0.584,
      "step": 14077
    },
    {
      "epoch": 0.4324639818142721,
      "grad_norm": 0.3535205125808716,
      "learning_rate": 1.7804089531209114e-05,
      "loss": 0.5545,
      "step": 14078
    },
    {
      "epoch": 0.43249470094922127,
      "grad_norm": 0.42000874876976013,
      "learning_rate": 1.7803787343548776e-05,
      "loss": 0.6064,
      "step": 14079
    },
    {
      "epoch": 0.43252542008417044,
      "grad_norm": 0.34127211570739746,
      "learning_rate": 1.7803485137662148e-05,
      "loss": 0.5054,
      "step": 14080
    },
    {
      "epoch": 0.43255613921911956,
      "grad_norm": 0.38031402230262756,
      "learning_rate": 1.780318291354993e-05,
      "loss": 0.5975,
      "step": 14081
    },
    {
      "epoch": 0.43258685835406874,
      "grad_norm": 0.4616107940673828,
      "learning_rate": 1.7802880671212835e-05,
      "loss": 0.5863,
      "step": 14082
    },
    {
      "epoch": 0.4326175774890179,
      "grad_norm": 0.37628796696662903,
      "learning_rate": 1.780257841065157e-05,
      "loss": 0.4712,
      "step": 14083
    },
    {
      "epoch": 0.4326482966239671,
      "grad_norm": 0.3431304097175598,
      "learning_rate": 1.780227613186684e-05,
      "loss": 0.5703,
      "step": 14084
    },
    {
      "epoch": 0.4326790157589162,
      "grad_norm": 0.3855423629283905,
      "learning_rate": 1.7801973834859345e-05,
      "loss": 0.5352,
      "step": 14085
    },
    {
      "epoch": 0.4327097348938654,
      "grad_norm": 0.35889288783073425,
      "learning_rate": 1.7801671519629793e-05,
      "loss": 0.6124,
      "step": 14086
    },
    {
      "epoch": 0.43274045402881456,
      "grad_norm": 0.32931676506996155,
      "learning_rate": 1.78013691861789e-05,
      "loss": 0.5326,
      "step": 14087
    },
    {
      "epoch": 0.43277117316376373,
      "grad_norm": 0.3353606164455414,
      "learning_rate": 1.7801066834507358e-05,
      "loss": 0.5406,
      "step": 14088
    },
    {
      "epoch": 0.43280189229871285,
      "grad_norm": 0.323148250579834,
      "learning_rate": 1.7800764464615883e-05,
      "loss": 0.6221,
      "step": 14089
    },
    {
      "epoch": 0.43283261143366203,
      "grad_norm": 0.3337446451187134,
      "learning_rate": 1.7800462076505177e-05,
      "loss": 0.4909,
      "step": 14090
    },
    {
      "epoch": 0.4328633305686112,
      "grad_norm": 0.3643101751804352,
      "learning_rate": 1.7800159670175948e-05,
      "loss": 0.6364,
      "step": 14091
    },
    {
      "epoch": 0.4328940497035603,
      "grad_norm": 0.3274995684623718,
      "learning_rate": 1.7799857245628897e-05,
      "loss": 0.5392,
      "step": 14092
    },
    {
      "epoch": 0.4329247688385095,
      "grad_norm": 0.3249182105064392,
      "learning_rate": 1.7799554802864742e-05,
      "loss": 0.5483,
      "step": 14093
    },
    {
      "epoch": 0.4329554879734587,
      "grad_norm": 0.3623753488063812,
      "learning_rate": 1.7799252341884178e-05,
      "loss": 0.5827,
      "step": 14094
    },
    {
      "epoch": 0.43298620710840785,
      "grad_norm": 0.352922260761261,
      "learning_rate": 1.7798949862687913e-05,
      "loss": 0.6414,
      "step": 14095
    },
    {
      "epoch": 0.43301692624335697,
      "grad_norm": 0.3454199433326721,
      "learning_rate": 1.7798647365276654e-05,
      "loss": 0.5856,
      "step": 14096
    },
    {
      "epoch": 0.43304764537830615,
      "grad_norm": 0.3610476851463318,
      "learning_rate": 1.779834484965112e-05,
      "loss": 0.6194,
      "step": 14097
    },
    {
      "epoch": 0.4330783645132553,
      "grad_norm": 0.4210748076438904,
      "learning_rate": 1.7798042315811995e-05,
      "loss": 0.596,
      "step": 14098
    },
    {
      "epoch": 0.43310908364820444,
      "grad_norm": 0.38875463604927063,
      "learning_rate": 1.7797739763760007e-05,
      "loss": 0.6318,
      "step": 14099
    },
    {
      "epoch": 0.4331398027831536,
      "grad_norm": 0.36456891894340515,
      "learning_rate": 1.779743719349585e-05,
      "loss": 0.5859,
      "step": 14100
    },
    {
      "epoch": 0.4331705219181028,
      "grad_norm": 0.39892101287841797,
      "learning_rate": 1.779713460502023e-05,
      "loss": 0.5571,
      "step": 14101
    },
    {
      "epoch": 0.43320124105305197,
      "grad_norm": 0.32761135697364807,
      "learning_rate": 1.7796831998333862e-05,
      "loss": 0.5396,
      "step": 14102
    },
    {
      "epoch": 0.4332319601880011,
      "grad_norm": 0.3717096745967865,
      "learning_rate": 1.7796529373437447e-05,
      "loss": 0.5945,
      "step": 14103
    },
    {
      "epoch": 0.43326267932295026,
      "grad_norm": 0.3694019317626953,
      "learning_rate": 1.7796226730331694e-05,
      "loss": 0.5795,
      "step": 14104
    },
    {
      "epoch": 0.43329339845789944,
      "grad_norm": 0.3513898551464081,
      "learning_rate": 1.7795924069017308e-05,
      "loss": 0.5542,
      "step": 14105
    },
    {
      "epoch": 0.4333241175928486,
      "grad_norm": 0.34485021233558655,
      "learning_rate": 1.7795621389494996e-05,
      "loss": 0.5944,
      "step": 14106
    },
    {
      "epoch": 0.43335483672779773,
      "grad_norm": 0.3408079147338867,
      "learning_rate": 1.7795318691765467e-05,
      "loss": 0.628,
      "step": 14107
    },
    {
      "epoch": 0.4333855558627469,
      "grad_norm": 0.415396511554718,
      "learning_rate": 1.779501597582943e-05,
      "loss": 0.5824,
      "step": 14108
    },
    {
      "epoch": 0.4334162749976961,
      "grad_norm": 0.3730771243572235,
      "learning_rate": 1.7794713241687583e-05,
      "loss": 0.5455,
      "step": 14109
    },
    {
      "epoch": 0.4334469941326452,
      "grad_norm": 0.30827391147613525,
      "learning_rate": 1.7794410489340645e-05,
      "loss": 0.5552,
      "step": 14110
    },
    {
      "epoch": 0.4334777132675944,
      "grad_norm": 0.39067542552948,
      "learning_rate": 1.7794107718789312e-05,
      "loss": 0.6153,
      "step": 14111
    },
    {
      "epoch": 0.43350843240254355,
      "grad_norm": 0.4319620430469513,
      "learning_rate": 1.7793804930034295e-05,
      "loss": 0.5631,
      "step": 14112
    },
    {
      "epoch": 0.43353915153749273,
      "grad_norm": 0.35792991518974304,
      "learning_rate": 1.7793502123076303e-05,
      "loss": 0.5773,
      "step": 14113
    },
    {
      "epoch": 0.43356987067244185,
      "grad_norm": 0.4077709913253784,
      "learning_rate": 1.7793199297916045e-05,
      "loss": 0.5724,
      "step": 14114
    },
    {
      "epoch": 0.433600589807391,
      "grad_norm": 0.3254302144050598,
      "learning_rate": 1.7792896454554223e-05,
      "loss": 0.5487,
      "step": 14115
    },
    {
      "epoch": 0.4336313089423402,
      "grad_norm": 0.3333504796028137,
      "learning_rate": 1.779259359299155e-05,
      "loss": 0.5782,
      "step": 14116
    },
    {
      "epoch": 0.4336620280772893,
      "grad_norm": 0.3515288233757019,
      "learning_rate": 1.779229071322873e-05,
      "loss": 0.5173,
      "step": 14117
    },
    {
      "epoch": 0.4336927472122385,
      "grad_norm": 0.35341939330101013,
      "learning_rate": 1.779198781526647e-05,
      "loss": 0.6481,
      "step": 14118
    },
    {
      "epoch": 0.43372346634718767,
      "grad_norm": 0.3244360089302063,
      "learning_rate": 1.779168489910548e-05,
      "loss": 0.5018,
      "step": 14119
    },
    {
      "epoch": 0.43375418548213684,
      "grad_norm": 0.38168272376060486,
      "learning_rate": 1.7791381964746466e-05,
      "loss": 0.5838,
      "step": 14120
    },
    {
      "epoch": 0.43378490461708596,
      "grad_norm": 0.37901026010513306,
      "learning_rate": 1.779107901219013e-05,
      "loss": 0.5706,
      "step": 14121
    },
    {
      "epoch": 0.43381562375203514,
      "grad_norm": 1.8165149688720703,
      "learning_rate": 1.779077604143719e-05,
      "loss": 0.5345,
      "step": 14122
    },
    {
      "epoch": 0.4338463428869843,
      "grad_norm": 0.41119998693466187,
      "learning_rate": 1.779047305248835e-05,
      "loss": 0.6311,
      "step": 14123
    },
    {
      "epoch": 0.43387706202193344,
      "grad_norm": 0.3407804071903229,
      "learning_rate": 1.7790170045344312e-05,
      "loss": 0.5509,
      "step": 14124
    },
    {
      "epoch": 0.4339077811568826,
      "grad_norm": 0.3709058463573456,
      "learning_rate": 1.778986702000579e-05,
      "loss": 0.6314,
      "step": 14125
    },
    {
      "epoch": 0.4339385002918318,
      "grad_norm": 0.32058826088905334,
      "learning_rate": 1.7789563976473485e-05,
      "loss": 0.5289,
      "step": 14126
    },
    {
      "epoch": 0.43396921942678096,
      "grad_norm": 0.3521212339401245,
      "learning_rate": 1.7789260914748112e-05,
      "loss": 0.6386,
      "step": 14127
    },
    {
      "epoch": 0.4339999385617301,
      "grad_norm": 0.4155852794647217,
      "learning_rate": 1.7788957834830378e-05,
      "loss": 0.5375,
      "step": 14128
    },
    {
      "epoch": 0.43403065769667926,
      "grad_norm": 0.4325881004333496,
      "learning_rate": 1.7788654736720986e-05,
      "loss": 0.6083,
      "step": 14129
    },
    {
      "epoch": 0.43406137683162843,
      "grad_norm": 0.32859671115875244,
      "learning_rate": 1.7788351620420653e-05,
      "loss": 0.596,
      "step": 14130
    },
    {
      "epoch": 0.4340920959665776,
      "grad_norm": 0.32109612226486206,
      "learning_rate": 1.7788048485930077e-05,
      "loss": 0.5518,
      "step": 14131
    },
    {
      "epoch": 0.4341228151015267,
      "grad_norm": 0.3376460373401642,
      "learning_rate": 1.7787745333249967e-05,
      "loss": 0.6468,
      "step": 14132
    },
    {
      "epoch": 0.4341535342364759,
      "grad_norm": 0.36458465456962585,
      "learning_rate": 1.7787442162381037e-05,
      "loss": 0.6563,
      "step": 14133
    },
    {
      "epoch": 0.4341842533714251,
      "grad_norm": 0.361511766910553,
      "learning_rate": 1.778713897332399e-05,
      "loss": 0.4513,
      "step": 14134
    },
    {
      "epoch": 0.4342149725063742,
      "grad_norm": 0.35300761461257935,
      "learning_rate": 1.7786835766079538e-05,
      "loss": 0.5864,
      "step": 14135
    },
    {
      "epoch": 0.4342456916413234,
      "grad_norm": 0.3205384910106659,
      "learning_rate": 1.7786532540648388e-05,
      "loss": 0.623,
      "step": 14136
    },
    {
      "epoch": 0.43427641077627255,
      "grad_norm": 0.35529613494873047,
      "learning_rate": 1.7786229297031244e-05,
      "loss": 0.5181,
      "step": 14137
    },
    {
      "epoch": 0.4343071299112217,
      "grad_norm": 0.35337451100349426,
      "learning_rate": 1.7785926035228818e-05,
      "loss": 0.5473,
      "step": 14138
    },
    {
      "epoch": 0.43433784904617084,
      "grad_norm": 0.37767311930656433,
      "learning_rate": 1.778562275524182e-05,
      "loss": 0.5599,
      "step": 14139
    },
    {
      "epoch": 0.43436856818112,
      "grad_norm": 0.3489845097064972,
      "learning_rate": 1.7785319457070958e-05,
      "loss": 0.6391,
      "step": 14140
    },
    {
      "epoch": 0.4343992873160692,
      "grad_norm": 0.3840947151184082,
      "learning_rate": 1.7785016140716937e-05,
      "loss": 0.5665,
      "step": 14141
    },
    {
      "epoch": 0.4344300064510183,
      "grad_norm": 0.4219222962856293,
      "learning_rate": 1.7784712806180466e-05,
      "loss": 0.5258,
      "step": 14142
    },
    {
      "epoch": 0.4344607255859675,
      "grad_norm": 0.37674856185913086,
      "learning_rate": 1.7784409453462256e-05,
      "loss": 0.5358,
      "step": 14143
    },
    {
      "epoch": 0.43449144472091666,
      "grad_norm": 0.36477482318878174,
      "learning_rate": 1.7784106082563013e-05,
      "loss": 0.6023,
      "step": 14144
    },
    {
      "epoch": 0.43452216385586584,
      "grad_norm": 0.3386416435241699,
      "learning_rate": 1.7783802693483448e-05,
      "loss": 0.646,
      "step": 14145
    },
    {
      "epoch": 0.43455288299081496,
      "grad_norm": 0.4059995114803314,
      "learning_rate": 1.7783499286224265e-05,
      "loss": 0.6579,
      "step": 14146
    },
    {
      "epoch": 0.43458360212576413,
      "grad_norm": 0.32824641466140747,
      "learning_rate": 1.778319586078618e-05,
      "loss": 0.565,
      "step": 14147
    },
    {
      "epoch": 0.4346143212607133,
      "grad_norm": 0.3500811457633972,
      "learning_rate": 1.7782892417169893e-05,
      "loss": 0.5379,
      "step": 14148
    },
    {
      "epoch": 0.4346450403956625,
      "grad_norm": 0.3675687611103058,
      "learning_rate": 1.7782588955376124e-05,
      "loss": 0.5982,
      "step": 14149
    },
    {
      "epoch": 0.4346757595306116,
      "grad_norm": 0.3126089870929718,
      "learning_rate": 1.778228547540557e-05,
      "loss": 0.5784,
      "step": 14150
    },
    {
      "epoch": 0.4347064786655608,
      "grad_norm": 0.3648272156715393,
      "learning_rate": 1.7781981977258945e-05,
      "loss": 0.6872,
      "step": 14151
    },
    {
      "epoch": 0.43473719780050996,
      "grad_norm": 0.34676945209503174,
      "learning_rate": 1.778167846093696e-05,
      "loss": 0.6091,
      "step": 14152
    },
    {
      "epoch": 0.4347679169354591,
      "grad_norm": 0.37069517374038696,
      "learning_rate": 1.7781374926440315e-05,
      "loss": 0.5269,
      "step": 14153
    },
    {
      "epoch": 0.43479863607040825,
      "grad_norm": 0.33704468607902527,
      "learning_rate": 1.7781071373769733e-05,
      "loss": 0.6143,
      "step": 14154
    },
    {
      "epoch": 0.4348293552053574,
      "grad_norm": 0.37161785364151,
      "learning_rate": 1.7780767802925913e-05,
      "loss": 0.5632,
      "step": 14155
    },
    {
      "epoch": 0.4348600743403066,
      "grad_norm": 0.3203677237033844,
      "learning_rate": 1.7780464213909563e-05,
      "loss": 0.5582,
      "step": 14156
    },
    {
      "epoch": 0.4348907934752557,
      "grad_norm": 0.32953810691833496,
      "learning_rate": 1.77801606067214e-05,
      "loss": 0.5769,
      "step": 14157
    },
    {
      "epoch": 0.4349215126102049,
      "grad_norm": 0.3666595220565796,
      "learning_rate": 1.7779856981362126e-05,
      "loss": 0.6176,
      "step": 14158
    },
    {
      "epoch": 0.43495223174515407,
      "grad_norm": 0.3485622704029083,
      "learning_rate": 1.777955333783245e-05,
      "loss": 0.6037,
      "step": 14159
    },
    {
      "epoch": 0.4349829508801032,
      "grad_norm": 0.34679925441741943,
      "learning_rate": 1.777924967613309e-05,
      "loss": 0.584,
      "step": 14160
    },
    {
      "epoch": 0.43501367001505237,
      "grad_norm": 0.36865296959877014,
      "learning_rate": 1.7778945996264747e-05,
      "loss": 0.5707,
      "step": 14161
    },
    {
      "epoch": 0.43504438915000154,
      "grad_norm": 0.34387657046318054,
      "learning_rate": 1.777864229822813e-05,
      "loss": 0.5766,
      "step": 14162
    },
    {
      "epoch": 0.4350751082849507,
      "grad_norm": 0.3513590097427368,
      "learning_rate": 1.7778338582023954e-05,
      "loss": 0.5421,
      "step": 14163
    },
    {
      "epoch": 0.43510582741989984,
      "grad_norm": 0.43151214718818665,
      "learning_rate": 1.7778034847652922e-05,
      "loss": 0.6009,
      "step": 14164
    },
    {
      "epoch": 0.435136546554849,
      "grad_norm": 0.40378648042678833,
      "learning_rate": 1.7777731095115748e-05,
      "loss": 0.6232,
      "step": 14165
    },
    {
      "epoch": 0.4351672656897982,
      "grad_norm": 0.3418087959289551,
      "learning_rate": 1.7777427324413142e-05,
      "loss": 0.5737,
      "step": 14166
    },
    {
      "epoch": 0.4351979848247473,
      "grad_norm": 0.35335269570350647,
      "learning_rate": 1.7777123535545806e-05,
      "loss": 0.5589,
      "step": 14167
    },
    {
      "epoch": 0.4352287039596965,
      "grad_norm": 0.3550027906894684,
      "learning_rate": 1.7776819728514462e-05,
      "loss": 0.573,
      "step": 14168
    },
    {
      "epoch": 0.43525942309464566,
      "grad_norm": 0.33285048604011536,
      "learning_rate": 1.7776515903319804e-05,
      "loss": 0.54,
      "step": 14169
    },
    {
      "epoch": 0.43529014222959483,
      "grad_norm": 0.3957229256629944,
      "learning_rate": 1.7776212059962557e-05,
      "loss": 0.6433,
      "step": 14170
    },
    {
      "epoch": 0.43532086136454395,
      "grad_norm": 0.3049108386039734,
      "learning_rate": 1.777590819844342e-05,
      "loss": 0.4789,
      "step": 14171
    },
    {
      "epoch": 0.43535158049949313,
      "grad_norm": 0.33933356404304504,
      "learning_rate": 1.7775604318763107e-05,
      "loss": 0.5636,
      "step": 14172
    },
    {
      "epoch": 0.4353822996344423,
      "grad_norm": 0.3896392285823822,
      "learning_rate": 1.7775300420922326e-05,
      "loss": 0.584,
      "step": 14173
    },
    {
      "epoch": 0.4354130187693915,
      "grad_norm": 0.49082276225090027,
      "learning_rate": 1.7774996504921792e-05,
      "loss": 0.495,
      "step": 14174
    },
    {
      "epoch": 0.4354437379043406,
      "grad_norm": 0.3327676057815552,
      "learning_rate": 1.7774692570762207e-05,
      "loss": 0.5894,
      "step": 14175
    },
    {
      "epoch": 0.4354744570392898,
      "grad_norm": 0.3611638844013214,
      "learning_rate": 1.7774388618444285e-05,
      "loss": 0.6036,
      "step": 14176
    },
    {
      "epoch": 0.43550517617423895,
      "grad_norm": 0.41548240184783936,
      "learning_rate": 1.7774084647968735e-05,
      "loss": 0.5336,
      "step": 14177
    },
    {
      "epoch": 0.43553589530918807,
      "grad_norm": 0.33642345666885376,
      "learning_rate": 1.7773780659336268e-05,
      "loss": 0.5838,
      "step": 14178
    },
    {
      "epoch": 0.43556661444413725,
      "grad_norm": 0.39118537306785583,
      "learning_rate": 1.7773476652547592e-05,
      "loss": 0.5286,
      "step": 14179
    },
    {
      "epoch": 0.4355973335790864,
      "grad_norm": 0.35646969079971313,
      "learning_rate": 1.7773172627603422e-05,
      "loss": 0.5319,
      "step": 14180
    },
    {
      "epoch": 0.4356280527140356,
      "grad_norm": 0.35202494263648987,
      "learning_rate": 1.777286858450446e-05,
      "loss": 0.6109,
      "step": 14181
    },
    {
      "epoch": 0.4356587718489847,
      "grad_norm": 0.36491599678993225,
      "learning_rate": 1.7772564523251423e-05,
      "loss": 0.628,
      "step": 14182
    },
    {
      "epoch": 0.4356894909839339,
      "grad_norm": 0.36916038393974304,
      "learning_rate": 1.777226044384502e-05,
      "loss": 0.5616,
      "step": 14183
    },
    {
      "epoch": 0.43572021011888307,
      "grad_norm": 0.35997137427330017,
      "learning_rate": 1.777195634628596e-05,
      "loss": 0.6086,
      "step": 14184
    },
    {
      "epoch": 0.4357509292538322,
      "grad_norm": 0.3545610010623932,
      "learning_rate": 1.777165223057495e-05,
      "loss": 0.6037,
      "step": 14185
    },
    {
      "epoch": 0.43578164838878136,
      "grad_norm": 0.8912855386734009,
      "learning_rate": 1.7771348096712702e-05,
      "loss": 0.5368,
      "step": 14186
    },
    {
      "epoch": 0.43581236752373054,
      "grad_norm": 0.3654244840145111,
      "learning_rate": 1.7771043944699933e-05,
      "loss": 0.5713,
      "step": 14187
    },
    {
      "epoch": 0.4358430866586797,
      "grad_norm": 0.33516934514045715,
      "learning_rate": 1.7770739774537348e-05,
      "loss": 0.6269,
      "step": 14188
    },
    {
      "epoch": 0.43587380579362883,
      "grad_norm": 0.3412504494190216,
      "learning_rate": 1.7770435586225656e-05,
      "loss": 0.5419,
      "step": 14189
    },
    {
      "epoch": 0.435904524928578,
      "grad_norm": 0.3467404842376709,
      "learning_rate": 1.7770131379765568e-05,
      "loss": 0.5868,
      "step": 14190
    },
    {
      "epoch": 0.4359352440635272,
      "grad_norm": 0.33678242564201355,
      "learning_rate": 1.7769827155157795e-05,
      "loss": 0.5608,
      "step": 14191
    },
    {
      "epoch": 0.43596596319847636,
      "grad_norm": 0.34189653396606445,
      "learning_rate": 1.776952291240305e-05,
      "loss": 0.5627,
      "step": 14192
    },
    {
      "epoch": 0.4359966823334255,
      "grad_norm": 0.3240010440349579,
      "learning_rate": 1.776921865150204e-05,
      "loss": 0.556,
      "step": 14193
    },
    {
      "epoch": 0.43602740146837465,
      "grad_norm": 0.3834017515182495,
      "learning_rate": 1.7768914372455478e-05,
      "loss": 0.6739,
      "step": 14194
    },
    {
      "epoch": 0.43605812060332383,
      "grad_norm": 0.33283960819244385,
      "learning_rate": 1.7768610075264073e-05,
      "loss": 0.559,
      "step": 14195
    },
    {
      "epoch": 0.43608883973827295,
      "grad_norm": 0.4497429430484772,
      "learning_rate": 1.776830575992854e-05,
      "loss": 0.5669,
      "step": 14196
    },
    {
      "epoch": 0.4361195588732221,
      "grad_norm": 0.3447738587856293,
      "learning_rate": 1.7768001426449582e-05,
      "loss": 0.5653,
      "step": 14197
    },
    {
      "epoch": 0.4361502780081713,
      "grad_norm": 0.34786882996559143,
      "learning_rate": 1.7767697074827915e-05,
      "loss": 0.5077,
      "step": 14198
    },
    {
      "epoch": 0.4361809971431205,
      "grad_norm": 0.33079618215560913,
      "learning_rate": 1.776739270506425e-05,
      "loss": 0.6603,
      "step": 14199
    },
    {
      "epoch": 0.4362117162780696,
      "grad_norm": 0.3275967836380005,
      "learning_rate": 1.77670883171593e-05,
      "loss": 0.5526,
      "step": 14200
    },
    {
      "epoch": 0.43624243541301877,
      "grad_norm": 0.3224526643753052,
      "learning_rate": 1.776678391111377e-05,
      "loss": 0.5275,
      "step": 14201
    },
    {
      "epoch": 0.43627315454796795,
      "grad_norm": 0.4158262610435486,
      "learning_rate": 1.776647948692837e-05,
      "loss": 0.5599,
      "step": 14202
    },
    {
      "epoch": 0.43630387368291706,
      "grad_norm": 0.34095528721809387,
      "learning_rate": 1.776617504460382e-05,
      "loss": 0.4922,
      "step": 14203
    },
    {
      "epoch": 0.43633459281786624,
      "grad_norm": 0.3436516523361206,
      "learning_rate": 1.7765870584140822e-05,
      "loss": 0.5973,
      "step": 14204
    },
    {
      "epoch": 0.4363653119528154,
      "grad_norm": 0.34132513403892517,
      "learning_rate": 1.7765566105540094e-05,
      "loss": 0.6132,
      "step": 14205
    },
    {
      "epoch": 0.4363960310877646,
      "grad_norm": 0.3520374000072479,
      "learning_rate": 1.7765261608802343e-05,
      "loss": 0.5781,
      "step": 14206
    },
    {
      "epoch": 0.4364267502227137,
      "grad_norm": 0.35770121216773987,
      "learning_rate": 1.7764957093928282e-05,
      "loss": 0.5763,
      "step": 14207
    },
    {
      "epoch": 0.4364574693576629,
      "grad_norm": 0.35713455080986023,
      "learning_rate": 1.776465256091862e-05,
      "loss": 0.5689,
      "step": 14208
    },
    {
      "epoch": 0.43648818849261206,
      "grad_norm": 0.37546348571777344,
      "learning_rate": 1.776434800977407e-05,
      "loss": 0.5492,
      "step": 14209
    },
    {
      "epoch": 0.4365189076275612,
      "grad_norm": 0.35421621799468994,
      "learning_rate": 1.7764043440495343e-05,
      "loss": 0.6074,
      "step": 14210
    },
    {
      "epoch": 0.43654962676251036,
      "grad_norm": 0.34438377618789673,
      "learning_rate": 1.7763738853083152e-05,
      "loss": 0.4985,
      "step": 14211
    },
    {
      "epoch": 0.43658034589745953,
      "grad_norm": 0.3532830774784088,
      "learning_rate": 1.7763434247538206e-05,
      "loss": 0.4865,
      "step": 14212
    },
    {
      "epoch": 0.4366110650324087,
      "grad_norm": 0.37198832631111145,
      "learning_rate": 1.7763129623861215e-05,
      "loss": 0.5437,
      "step": 14213
    },
    {
      "epoch": 0.4366417841673578,
      "grad_norm": 0.31544315814971924,
      "learning_rate": 1.7762824982052894e-05,
      "loss": 0.5304,
      "step": 14214
    },
    {
      "epoch": 0.436672503302307,
      "grad_norm": 0.33390846848487854,
      "learning_rate": 1.776252032211395e-05,
      "loss": 0.5407,
      "step": 14215
    },
    {
      "epoch": 0.4367032224372562,
      "grad_norm": 0.38420671224594116,
      "learning_rate": 1.7762215644045105e-05,
      "loss": 0.6147,
      "step": 14216
    },
    {
      "epoch": 0.43673394157220535,
      "grad_norm": 0.3537635803222656,
      "learning_rate": 1.7761910947847057e-05,
      "loss": 0.5994,
      "step": 14217
    },
    {
      "epoch": 0.4367646607071545,
      "grad_norm": 0.38762685656547546,
      "learning_rate": 1.7761606233520525e-05,
      "loss": 0.5836,
      "step": 14218
    },
    {
      "epoch": 0.43679537984210365,
      "grad_norm": 0.3135058581829071,
      "learning_rate": 1.776130150106622e-05,
      "loss": 0.5881,
      "step": 14219
    },
    {
      "epoch": 0.4368260989770528,
      "grad_norm": 0.34566715359687805,
      "learning_rate": 1.7760996750484856e-05,
      "loss": 0.5912,
      "step": 14220
    },
    {
      "epoch": 0.43685681811200194,
      "grad_norm": 1.158207654953003,
      "learning_rate": 1.7760691981777142e-05,
      "loss": 0.525,
      "step": 14221
    },
    {
      "epoch": 0.4368875372469511,
      "grad_norm": 0.36657896637916565,
      "learning_rate": 1.7760387194943784e-05,
      "loss": 0.5789,
      "step": 14222
    },
    {
      "epoch": 0.4369182563819003,
      "grad_norm": 0.3606001138687134,
      "learning_rate": 1.7760082389985506e-05,
      "loss": 0.6178,
      "step": 14223
    },
    {
      "epoch": 0.43694897551684947,
      "grad_norm": 0.32222068309783936,
      "learning_rate": 1.775977756690301e-05,
      "loss": 0.5607,
      "step": 14224
    },
    {
      "epoch": 0.4369796946517986,
      "grad_norm": 0.36108943819999695,
      "learning_rate": 1.775947272569701e-05,
      "loss": 0.6129,
      "step": 14225
    },
    {
      "epoch": 0.43701041378674776,
      "grad_norm": 0.3425448536872864,
      "learning_rate": 1.7759167866368223e-05,
      "loss": 0.5115,
      "step": 14226
    },
    {
      "epoch": 0.43704113292169694,
      "grad_norm": 0.36817580461502075,
      "learning_rate": 1.7758862988917356e-05,
      "loss": 0.536,
      "step": 14227
    },
    {
      "epoch": 0.43707185205664606,
      "grad_norm": 0.3567482829093933,
      "learning_rate": 1.7758558093345123e-05,
      "loss": 0.6773,
      "step": 14228
    },
    {
      "epoch": 0.43710257119159523,
      "grad_norm": 0.48154836893081665,
      "learning_rate": 1.775825317965224e-05,
      "loss": 0.5214,
      "step": 14229
    },
    {
      "epoch": 0.4371332903265444,
      "grad_norm": 0.334797203540802,
      "learning_rate": 1.7757948247839407e-05,
      "loss": 0.5026,
      "step": 14230
    },
    {
      "epoch": 0.4371640094614936,
      "grad_norm": 0.35755568742752075,
      "learning_rate": 1.7757643297907347e-05,
      "loss": 0.5759,
      "step": 14231
    },
    {
      "epoch": 0.4371947285964427,
      "grad_norm": 0.5552546977996826,
      "learning_rate": 1.7757338329856772e-05,
      "loss": 0.48,
      "step": 14232
    },
    {
      "epoch": 0.4372254477313919,
      "grad_norm": 0.3797314465045929,
      "learning_rate": 1.775703334368839e-05,
      "loss": 0.5319,
      "step": 14233
    },
    {
      "epoch": 0.43725616686634106,
      "grad_norm": 0.34438809752464294,
      "learning_rate": 1.7756728339402913e-05,
      "loss": 0.6046,
      "step": 14234
    },
    {
      "epoch": 0.4372868860012902,
      "grad_norm": 0.4181865155696869,
      "learning_rate": 1.775642331700106e-05,
      "loss": 0.5711,
      "step": 14235
    },
    {
      "epoch": 0.43731760513623935,
      "grad_norm": 0.31704065203666687,
      "learning_rate": 1.775611827648353e-05,
      "loss": 0.5373,
      "step": 14236
    },
    {
      "epoch": 0.4373483242711885,
      "grad_norm": 0.3285945653915405,
      "learning_rate": 1.7755813217851052e-05,
      "loss": 0.632,
      "step": 14237
    },
    {
      "epoch": 0.4373790434061377,
      "grad_norm": 0.3679514229297638,
      "learning_rate": 1.775550814110433e-05,
      "loss": 0.5437,
      "step": 14238
    },
    {
      "epoch": 0.4374097625410868,
      "grad_norm": 0.39210349321365356,
      "learning_rate": 1.7755203046244073e-05,
      "loss": 0.5316,
      "step": 14239
    },
    {
      "epoch": 0.437440481676036,
      "grad_norm": 0.5005276203155518,
      "learning_rate": 1.7754897933271e-05,
      "loss": 0.6263,
      "step": 14240
    },
    {
      "epoch": 0.4374712008109852,
      "grad_norm": 0.34972837567329407,
      "learning_rate": 1.775459280218582e-05,
      "loss": 0.5653,
      "step": 14241
    },
    {
      "epoch": 0.43750191994593435,
      "grad_norm": 0.37817996740341187,
      "learning_rate": 1.775428765298925e-05,
      "loss": 0.6414,
      "step": 14242
    },
    {
      "epoch": 0.43753263908088347,
      "grad_norm": 0.35831791162490845,
      "learning_rate": 1.7753982485681998e-05,
      "loss": 0.5781,
      "step": 14243
    },
    {
      "epoch": 0.43756335821583264,
      "grad_norm": 0.3686431646347046,
      "learning_rate": 1.7753677300264777e-05,
      "loss": 0.6753,
      "step": 14244
    },
    {
      "epoch": 0.4375940773507818,
      "grad_norm": 0.3821297585964203,
      "learning_rate": 1.7753372096738303e-05,
      "loss": 0.587,
      "step": 14245
    },
    {
      "epoch": 0.43762479648573094,
      "grad_norm": 0.33246541023254395,
      "learning_rate": 1.7753066875103285e-05,
      "loss": 0.6368,
      "step": 14246
    },
    {
      "epoch": 0.4376555156206801,
      "grad_norm": 0.35600319504737854,
      "learning_rate": 1.7752761635360444e-05,
      "loss": 0.688,
      "step": 14247
    },
    {
      "epoch": 0.4376862347556293,
      "grad_norm": 0.35839492082595825,
      "learning_rate": 1.7752456377510478e-05,
      "loss": 0.5808,
      "step": 14248
    },
    {
      "epoch": 0.43771695389057846,
      "grad_norm": 0.3427979350090027,
      "learning_rate": 1.7752151101554112e-05,
      "loss": 0.5082,
      "step": 14249
    },
    {
      "epoch": 0.4377476730255276,
      "grad_norm": 0.5108407139778137,
      "learning_rate": 1.7751845807492055e-05,
      "loss": 0.5359,
      "step": 14250
    },
    {
      "epoch": 0.43777839216047676,
      "grad_norm": 0.35261499881744385,
      "learning_rate": 1.7751540495325024e-05,
      "loss": 0.5538,
      "step": 14251
    },
    {
      "epoch": 0.43780911129542593,
      "grad_norm": 0.369702011346817,
      "learning_rate": 1.7751235165053727e-05,
      "loss": 0.4815,
      "step": 14252
    },
    {
      "epoch": 0.43783983043037505,
      "grad_norm": 0.36828210949897766,
      "learning_rate": 1.775092981667888e-05,
      "loss": 0.5719,
      "step": 14253
    },
    {
      "epoch": 0.43787054956532423,
      "grad_norm": 0.34233590960502625,
      "learning_rate": 1.775062445020119e-05,
      "loss": 0.5407,
      "step": 14254
    },
    {
      "epoch": 0.4379012687002734,
      "grad_norm": 0.31937241554260254,
      "learning_rate": 1.775031906562138e-05,
      "loss": 0.5333,
      "step": 14255
    },
    {
      "epoch": 0.4379319878352226,
      "grad_norm": 0.45620062947273254,
      "learning_rate": 1.775001366294016e-05,
      "loss": 0.5866,
      "step": 14256
    },
    {
      "epoch": 0.4379627069701717,
      "grad_norm": 0.3589589297771454,
      "learning_rate": 1.7749708242158238e-05,
      "loss": 0.595,
      "step": 14257
    },
    {
      "epoch": 0.4379934261051209,
      "grad_norm": 0.32726746797561646,
      "learning_rate": 1.7749402803276335e-05,
      "loss": 0.5217,
      "step": 14258
    },
    {
      "epoch": 0.43802414524007005,
      "grad_norm": 0.35578712821006775,
      "learning_rate": 1.7749097346295157e-05,
      "loss": 0.6111,
      "step": 14259
    },
    {
      "epoch": 0.4380548643750192,
      "grad_norm": 0.34946709871292114,
      "learning_rate": 1.7748791871215423e-05,
      "loss": 0.6107,
      "step": 14260
    },
    {
      "epoch": 0.43808558350996835,
      "grad_norm": 0.3259239196777344,
      "learning_rate": 1.774848637803784e-05,
      "loss": 0.5499,
      "step": 14261
    },
    {
      "epoch": 0.4381163026449175,
      "grad_norm": 0.44467243552207947,
      "learning_rate": 1.7748180866763132e-05,
      "loss": 0.603,
      "step": 14262
    },
    {
      "epoch": 0.4381470217798667,
      "grad_norm": 0.36500421166419983,
      "learning_rate": 1.7747875337392005e-05,
      "loss": 0.5784,
      "step": 14263
    },
    {
      "epoch": 0.4381777409148158,
      "grad_norm": 0.33670860528945923,
      "learning_rate": 1.774756978992517e-05,
      "loss": 0.5465,
      "step": 14264
    },
    {
      "epoch": 0.438208460049765,
      "grad_norm": 0.3340592086315155,
      "learning_rate": 1.774726422436335e-05,
      "loss": 0.5326,
      "step": 14265
    },
    {
      "epoch": 0.43823917918471417,
      "grad_norm": 0.31837770342826843,
      "learning_rate": 1.774695864070725e-05,
      "loss": 0.5278,
      "step": 14266
    },
    {
      "epoch": 0.43826989831966334,
      "grad_norm": 0.3197746276855469,
      "learning_rate": 1.7746653038957592e-05,
      "loss": 0.6102,
      "step": 14267
    },
    {
      "epoch": 0.43830061745461246,
      "grad_norm": 0.35229936242103577,
      "learning_rate": 1.774634741911508e-05,
      "loss": 0.6001,
      "step": 14268
    },
    {
      "epoch": 0.43833133658956164,
      "grad_norm": 0.30653634667396545,
      "learning_rate": 1.7746041781180433e-05,
      "loss": 0.5343,
      "step": 14269
    },
    {
      "epoch": 0.4383620557245108,
      "grad_norm": 0.3498680293560028,
      "learning_rate": 1.7745736125154363e-05,
      "loss": 0.5474,
      "step": 14270
    },
    {
      "epoch": 0.43839277485945993,
      "grad_norm": 0.3348331153392792,
      "learning_rate": 1.7745430451037587e-05,
      "loss": 0.593,
      "step": 14271
    },
    {
      "epoch": 0.4384234939944091,
      "grad_norm": 0.35992082953453064,
      "learning_rate": 1.7745124758830816e-05,
      "loss": 0.5638,
      "step": 14272
    },
    {
      "epoch": 0.4384542131293583,
      "grad_norm": 0.32295194268226624,
      "learning_rate": 1.774481904853477e-05,
      "loss": 0.5006,
      "step": 14273
    },
    {
      "epoch": 0.43848493226430746,
      "grad_norm": 0.34848153591156006,
      "learning_rate": 1.7744513320150155e-05,
      "loss": 0.5628,
      "step": 14274
    },
    {
      "epoch": 0.4385156513992566,
      "grad_norm": 7.059569358825684,
      "learning_rate": 1.7744207573677686e-05,
      "loss": 0.6619,
      "step": 14275
    },
    {
      "epoch": 0.43854637053420575,
      "grad_norm": 0.3423803448677063,
      "learning_rate": 1.7743901809118083e-05,
      "loss": 0.6147,
      "step": 14276
    },
    {
      "epoch": 0.43857708966915493,
      "grad_norm": 0.34741172194480896,
      "learning_rate": 1.7743596026472053e-05,
      "loss": 0.6077,
      "step": 14277
    },
    {
      "epoch": 0.43860780880410405,
      "grad_norm": 0.3526429831981659,
      "learning_rate": 1.7743290225740317e-05,
      "loss": 0.5595,
      "step": 14278
    },
    {
      "epoch": 0.4386385279390532,
      "grad_norm": 0.427121102809906,
      "learning_rate": 1.7742984406923585e-05,
      "loss": 0.5831,
      "step": 14279
    },
    {
      "epoch": 0.4386692470740024,
      "grad_norm": 0.3596748113632202,
      "learning_rate": 1.774267857002257e-05,
      "loss": 0.5694,
      "step": 14280
    },
    {
      "epoch": 0.4386999662089516,
      "grad_norm": 0.34419772028923035,
      "learning_rate": 1.7742372715037992e-05,
      "loss": 0.5466,
      "step": 14281
    },
    {
      "epoch": 0.4387306853439007,
      "grad_norm": 0.33897197246551514,
      "learning_rate": 1.774206684197056e-05,
      "loss": 0.6009,
      "step": 14282
    },
    {
      "epoch": 0.43876140447884987,
      "grad_norm": 0.30232781171798706,
      "learning_rate": 1.774176095082099e-05,
      "loss": 0.5444,
      "step": 14283
    },
    {
      "epoch": 0.43879212361379905,
      "grad_norm": 0.35238775610923767,
      "learning_rate": 1.7741455041589995e-05,
      "loss": 0.6259,
      "step": 14284
    },
    {
      "epoch": 0.4388228427487482,
      "grad_norm": 0.3369317948818207,
      "learning_rate": 1.7741149114278296e-05,
      "loss": 0.5902,
      "step": 14285
    },
    {
      "epoch": 0.43885356188369734,
      "grad_norm": 0.36147332191467285,
      "learning_rate": 1.7740843168886598e-05,
      "loss": 0.5429,
      "step": 14286
    },
    {
      "epoch": 0.4388842810186465,
      "grad_norm": 0.36988022923469543,
      "learning_rate": 1.774053720541562e-05,
      "loss": 0.6789,
      "step": 14287
    },
    {
      "epoch": 0.4389150001535957,
      "grad_norm": 0.383041650056839,
      "learning_rate": 1.774023122386608e-05,
      "loss": 0.6354,
      "step": 14288
    },
    {
      "epoch": 0.4389457192885448,
      "grad_norm": 0.3515559732913971,
      "learning_rate": 1.773992522423869e-05,
      "loss": 0.5958,
      "step": 14289
    },
    {
      "epoch": 0.438976438423494,
      "grad_norm": 0.3988370895385742,
      "learning_rate": 1.7739619206534162e-05,
      "loss": 0.5714,
      "step": 14290
    },
    {
      "epoch": 0.43900715755844316,
      "grad_norm": 0.3688338100910187,
      "learning_rate": 1.7739313170753213e-05,
      "loss": 0.5677,
      "step": 14291
    },
    {
      "epoch": 0.43903787669339234,
      "grad_norm": 0.33290618658065796,
      "learning_rate": 1.7739007116896557e-05,
      "loss": 0.554,
      "step": 14292
    },
    {
      "epoch": 0.43906859582834146,
      "grad_norm": 0.41673341393470764,
      "learning_rate": 1.7738701044964906e-05,
      "loss": 0.5526,
      "step": 14293
    },
    {
      "epoch": 0.43909931496329063,
      "grad_norm": 0.3694443702697754,
      "learning_rate": 1.7738394954958985e-05,
      "loss": 0.5749,
      "step": 14294
    },
    {
      "epoch": 0.4391300340982398,
      "grad_norm": 0.34277305006980896,
      "learning_rate": 1.7738088846879498e-05,
      "loss": 0.6033,
      "step": 14295
    },
    {
      "epoch": 0.4391607532331889,
      "grad_norm": 0.3422392010688782,
      "learning_rate": 1.7737782720727167e-05,
      "loss": 0.5299,
      "step": 14296
    },
    {
      "epoch": 0.4391914723681381,
      "grad_norm": 0.34064429998397827,
      "learning_rate": 1.77374765765027e-05,
      "loss": 0.625,
      "step": 14297
    },
    {
      "epoch": 0.4392221915030873,
      "grad_norm": 0.34688007831573486,
      "learning_rate": 1.773717041420682e-05,
      "loss": 0.5782,
      "step": 14298
    },
    {
      "epoch": 0.43925291063803645,
      "grad_norm": 0.3510338366031647,
      "learning_rate": 1.7736864233840238e-05,
      "loss": 0.6232,
      "step": 14299
    },
    {
      "epoch": 0.4392836297729856,
      "grad_norm": 0.3520839512348175,
      "learning_rate": 1.7736558035403667e-05,
      "loss": 0.612,
      "step": 14300
    },
    {
      "epoch": 0.43931434890793475,
      "grad_norm": 0.37809768319129944,
      "learning_rate": 1.7736251818897824e-05,
      "loss": 0.5998,
      "step": 14301
    },
    {
      "epoch": 0.4393450680428839,
      "grad_norm": 0.361564964056015,
      "learning_rate": 1.7735945584323423e-05,
      "loss": 0.5373,
      "step": 14302
    },
    {
      "epoch": 0.4393757871778331,
      "grad_norm": 0.34981024265289307,
      "learning_rate": 1.773563933168119e-05,
      "loss": 0.5242,
      "step": 14303
    },
    {
      "epoch": 0.4394065063127822,
      "grad_norm": 0.36069369316101074,
      "learning_rate": 1.773533306097182e-05,
      "loss": 0.5692,
      "step": 14304
    },
    {
      "epoch": 0.4394372254477314,
      "grad_norm": 0.46777164936065674,
      "learning_rate": 1.7735026772196045e-05,
      "loss": 0.5395,
      "step": 14305
    },
    {
      "epoch": 0.43946794458268057,
      "grad_norm": 0.32218876481056213,
      "learning_rate": 1.7734720465354575e-05,
      "loss": 0.5374,
      "step": 14306
    },
    {
      "epoch": 0.4394986637176297,
      "grad_norm": 0.36235660314559937,
      "learning_rate": 1.773441414044812e-05,
      "loss": 0.5549,
      "step": 14307
    },
    {
      "epoch": 0.43952938285257886,
      "grad_norm": 0.39947476983070374,
      "learning_rate": 1.7734107797477406e-05,
      "loss": 0.5998,
      "step": 14308
    },
    {
      "epoch": 0.43956010198752804,
      "grad_norm": 0.35265904664993286,
      "learning_rate": 1.7733801436443144e-05,
      "loss": 0.5829,
      "step": 14309
    },
    {
      "epoch": 0.4395908211224772,
      "grad_norm": 0.3486497700214386,
      "learning_rate": 1.7733495057346047e-05,
      "loss": 0.5804,
      "step": 14310
    },
    {
      "epoch": 0.43962154025742634,
      "grad_norm": 0.33972474932670593,
      "learning_rate": 1.773318866018683e-05,
      "loss": 0.5638,
      "step": 14311
    },
    {
      "epoch": 0.4396522593923755,
      "grad_norm": 0.3620332181453705,
      "learning_rate": 1.7732882244966213e-05,
      "loss": 0.5837,
      "step": 14312
    },
    {
      "epoch": 0.4396829785273247,
      "grad_norm": 0.3649156987667084,
      "learning_rate": 1.773257581168491e-05,
      "loss": 0.6011,
      "step": 14313
    },
    {
      "epoch": 0.4397136976622738,
      "grad_norm": 0.3722979426383972,
      "learning_rate": 1.7732269360343633e-05,
      "loss": 0.5675,
      "step": 14314
    },
    {
      "epoch": 0.439744416797223,
      "grad_norm": 0.3626846969127655,
      "learning_rate": 1.7731962890943103e-05,
      "loss": 0.6391,
      "step": 14315
    },
    {
      "epoch": 0.43977513593217216,
      "grad_norm": 0.3222985863685608,
      "learning_rate": 1.7731656403484034e-05,
      "loss": 0.5525,
      "step": 14316
    },
    {
      "epoch": 0.43980585506712133,
      "grad_norm": 0.38590696454048157,
      "learning_rate": 1.7731349897967137e-05,
      "loss": 0.5347,
      "step": 14317
    },
    {
      "epoch": 0.43983657420207045,
      "grad_norm": 0.39328327775001526,
      "learning_rate": 1.773104337439314e-05,
      "loss": 0.5976,
      "step": 14318
    },
    {
      "epoch": 0.4398672933370196,
      "grad_norm": 0.6778598427772522,
      "learning_rate": 1.7730736832762747e-05,
      "loss": 0.5411,
      "step": 14319
    },
    {
      "epoch": 0.4398980124719688,
      "grad_norm": 0.33849629759788513,
      "learning_rate": 1.7730430273076677e-05,
      "loss": 0.5407,
      "step": 14320
    },
    {
      "epoch": 0.4399287316069179,
      "grad_norm": 0.3427720367908478,
      "learning_rate": 1.773012369533565e-05,
      "loss": 0.6532,
      "step": 14321
    },
    {
      "epoch": 0.4399594507418671,
      "grad_norm": 0.3153238594532013,
      "learning_rate": 1.772981709954038e-05,
      "loss": 0.5607,
      "step": 14322
    },
    {
      "epoch": 0.4399901698768163,
      "grad_norm": 0.32733747363090515,
      "learning_rate": 1.772951048569158e-05,
      "loss": 0.5729,
      "step": 14323
    },
    {
      "epoch": 0.44002088901176545,
      "grad_norm": 0.3308362066745758,
      "learning_rate": 1.772920385378997e-05,
      "loss": 0.6273,
      "step": 14324
    },
    {
      "epoch": 0.44005160814671457,
      "grad_norm": 0.32945436239242554,
      "learning_rate": 1.772889720383626e-05,
      "loss": 0.5634,
      "step": 14325
    },
    {
      "epoch": 0.44008232728166374,
      "grad_norm": 0.3711308538913727,
      "learning_rate": 1.7728590535831177e-05,
      "loss": 0.6482,
      "step": 14326
    },
    {
      "epoch": 0.4401130464166129,
      "grad_norm": 0.33745384216308594,
      "learning_rate": 1.7728283849775428e-05,
      "loss": 0.5576,
      "step": 14327
    },
    {
      "epoch": 0.4401437655515621,
      "grad_norm": 0.335204154253006,
      "learning_rate": 1.7727977145669732e-05,
      "loss": 0.6098,
      "step": 14328
    },
    {
      "epoch": 0.4401744846865112,
      "grad_norm": 0.3913590908050537,
      "learning_rate": 1.7727670423514808e-05,
      "loss": 0.6038,
      "step": 14329
    },
    {
      "epoch": 0.4402052038214604,
      "grad_norm": 0.3532904386520386,
      "learning_rate": 1.7727363683311366e-05,
      "loss": 0.5481,
      "step": 14330
    },
    {
      "epoch": 0.44023592295640956,
      "grad_norm": 0.35673898458480835,
      "learning_rate": 1.772705692506013e-05,
      "loss": 0.6292,
      "step": 14331
    },
    {
      "epoch": 0.4402666420913587,
      "grad_norm": 0.33524149656295776,
      "learning_rate": 1.7726750148761812e-05,
      "loss": 0.5767,
      "step": 14332
    },
    {
      "epoch": 0.44029736122630786,
      "grad_norm": 0.3363966941833496,
      "learning_rate": 1.772644335441713e-05,
      "loss": 0.533,
      "step": 14333
    },
    {
      "epoch": 0.44032808036125703,
      "grad_norm": 0.3357883393764496,
      "learning_rate": 1.77261365420268e-05,
      "loss": 0.6125,
      "step": 14334
    },
    {
      "epoch": 0.4403587994962062,
      "grad_norm": 0.33486440777778625,
      "learning_rate": 1.7725829711591537e-05,
      "loss": 0.5189,
      "step": 14335
    },
    {
      "epoch": 0.44038951863115533,
      "grad_norm": 0.3394237160682678,
      "learning_rate": 1.772552286311206e-05,
      "loss": 0.583,
      "step": 14336
    },
    {
      "epoch": 0.4404202377661045,
      "grad_norm": 0.35431161522865295,
      "learning_rate": 1.772521599658908e-05,
      "loss": 0.5666,
      "step": 14337
    },
    {
      "epoch": 0.4404509569010537,
      "grad_norm": 0.3571116030216217,
      "learning_rate": 1.7724909112023328e-05,
      "loss": 0.5714,
      "step": 14338
    },
    {
      "epoch": 0.4404816760360028,
      "grad_norm": 0.3483213186264038,
      "learning_rate": 1.7724602209415508e-05,
      "loss": 0.6332,
      "step": 14339
    },
    {
      "epoch": 0.440512395170952,
      "grad_norm": 0.31724298000335693,
      "learning_rate": 1.7724295288766334e-05,
      "loss": 0.5886,
      "step": 14340
    },
    {
      "epoch": 0.44054311430590115,
      "grad_norm": 0.3776123821735382,
      "learning_rate": 1.7723988350076534e-05,
      "loss": 0.5305,
      "step": 14341
    },
    {
      "epoch": 0.4405738334408503,
      "grad_norm": 0.42954614758491516,
      "learning_rate": 1.7723681393346823e-05,
      "loss": 0.5804,
      "step": 14342
    },
    {
      "epoch": 0.44060455257579945,
      "grad_norm": 0.37006157636642456,
      "learning_rate": 1.7723374418577908e-05,
      "loss": 0.5753,
      "step": 14343
    },
    {
      "epoch": 0.4406352717107486,
      "grad_norm": 0.4082850217819214,
      "learning_rate": 1.7723067425770516e-05,
      "loss": 0.6435,
      "step": 14344
    },
    {
      "epoch": 0.4406659908456978,
      "grad_norm": 0.3574734926223755,
      "learning_rate": 1.772276041492536e-05,
      "loss": 0.593,
      "step": 14345
    },
    {
      "epoch": 0.440696709980647,
      "grad_norm": 0.3490654528141022,
      "learning_rate": 1.7722453386043157e-05,
      "loss": 0.5184,
      "step": 14346
    },
    {
      "epoch": 0.4407274291155961,
      "grad_norm": 0.5093880891799927,
      "learning_rate": 1.7722146339124626e-05,
      "loss": 0.6313,
      "step": 14347
    },
    {
      "epoch": 0.44075814825054527,
      "grad_norm": 0.3430178165435791,
      "learning_rate": 1.772183927417048e-05,
      "loss": 0.5773,
      "step": 14348
    },
    {
      "epoch": 0.44078886738549444,
      "grad_norm": 0.3318985402584076,
      "learning_rate": 1.7721532191181446e-05,
      "loss": 0.5849,
      "step": 14349
    },
    {
      "epoch": 0.44081958652044356,
      "grad_norm": 0.5787627100944519,
      "learning_rate": 1.7721225090158228e-05,
      "loss": 0.6288,
      "step": 14350
    },
    {
      "epoch": 0.44085030565539274,
      "grad_norm": 0.38112467527389526,
      "learning_rate": 1.772091797110155e-05,
      "loss": 0.6097,
      "step": 14351
    },
    {
      "epoch": 0.4408810247903419,
      "grad_norm": 0.3537488281726837,
      "learning_rate": 1.772061083401213e-05,
      "loss": 0.6533,
      "step": 14352
    },
    {
      "epoch": 0.4409117439252911,
      "grad_norm": 0.44130390882492065,
      "learning_rate": 1.7720303678890685e-05,
      "loss": 0.5872,
      "step": 14353
    },
    {
      "epoch": 0.4409424630602402,
      "grad_norm": 0.37117642164230347,
      "learning_rate": 1.7719996505737934e-05,
      "loss": 0.5507,
      "step": 14354
    },
    {
      "epoch": 0.4409731821951894,
      "grad_norm": 0.34680962562561035,
      "learning_rate": 1.7719689314554588e-05,
      "loss": 0.5966,
      "step": 14355
    },
    {
      "epoch": 0.44100390133013856,
      "grad_norm": 0.40280216932296753,
      "learning_rate": 1.771938210534137e-05,
      "loss": 0.5082,
      "step": 14356
    },
    {
      "epoch": 0.4410346204650877,
      "grad_norm": 0.3178340494632721,
      "learning_rate": 1.7719074878098995e-05,
      "loss": 0.5424,
      "step": 14357
    },
    {
      "epoch": 0.44106533960003685,
      "grad_norm": 0.5011940002441406,
      "learning_rate": 1.771876763282818e-05,
      "loss": 0.5588,
      "step": 14358
    },
    {
      "epoch": 0.44109605873498603,
      "grad_norm": 0.431881844997406,
      "learning_rate": 1.771846036952965e-05,
      "loss": 0.564,
      "step": 14359
    },
    {
      "epoch": 0.4411267778699352,
      "grad_norm": 0.34585338830947876,
      "learning_rate": 1.7718153088204113e-05,
      "loss": 0.6633,
      "step": 14360
    },
    {
      "epoch": 0.4411574970048843,
      "grad_norm": 0.3224860429763794,
      "learning_rate": 1.7717845788852292e-05,
      "loss": 0.5625,
      "step": 14361
    },
    {
      "epoch": 0.4411882161398335,
      "grad_norm": 0.3466618061065674,
      "learning_rate": 1.77175384714749e-05,
      "loss": 0.5572,
      "step": 14362
    },
    {
      "epoch": 0.4412189352747827,
      "grad_norm": 0.30919936299324036,
      "learning_rate": 1.7717231136072657e-05,
      "loss": 0.5754,
      "step": 14363
    },
    {
      "epoch": 0.4412496544097318,
      "grad_norm": 0.3743022084236145,
      "learning_rate": 1.7716923782646286e-05,
      "loss": 0.5681,
      "step": 14364
    },
    {
      "epoch": 0.44128037354468097,
      "grad_norm": 0.4315684735774994,
      "learning_rate": 1.7716616411196498e-05,
      "loss": 0.5852,
      "step": 14365
    },
    {
      "epoch": 0.44131109267963015,
      "grad_norm": 0.39862287044525146,
      "learning_rate": 1.7716309021724013e-05,
      "loss": 0.5552,
      "step": 14366
    },
    {
      "epoch": 0.4413418118145793,
      "grad_norm": 0.3255908787250519,
      "learning_rate": 1.771600161422955e-05,
      "loss": 0.5491,
      "step": 14367
    },
    {
      "epoch": 0.44137253094952844,
      "grad_norm": 0.6014980673789978,
      "learning_rate": 1.771569418871383e-05,
      "loss": 0.6642,
      "step": 14368
    },
    {
      "epoch": 0.4414032500844776,
      "grad_norm": 0.3889240324497223,
      "learning_rate": 1.7715386745177562e-05,
      "loss": 0.6616,
      "step": 14369
    },
    {
      "epoch": 0.4414339692194268,
      "grad_norm": 0.3290168046951294,
      "learning_rate": 1.7715079283621473e-05,
      "loss": 0.5199,
      "step": 14370
    },
    {
      "epoch": 0.44146468835437597,
      "grad_norm": 0.39319276809692383,
      "learning_rate": 1.7714771804046275e-05,
      "loss": 0.5042,
      "step": 14371
    },
    {
      "epoch": 0.4414954074893251,
      "grad_norm": 0.3477868139743805,
      "learning_rate": 1.771446430645269e-05,
      "loss": 0.4988,
      "step": 14372
    },
    {
      "epoch": 0.44152612662427426,
      "grad_norm": 0.3516961932182312,
      "learning_rate": 1.7714156790841436e-05,
      "loss": 0.5517,
      "step": 14373
    },
    {
      "epoch": 0.44155684575922344,
      "grad_norm": 0.4396090805530548,
      "learning_rate": 1.7713849257213227e-05,
      "loss": 0.6114,
      "step": 14374
    },
    {
      "epoch": 0.44158756489417256,
      "grad_norm": 0.4446621239185333,
      "learning_rate": 1.7713541705568787e-05,
      "loss": 0.5545,
      "step": 14375
    },
    {
      "epoch": 0.44161828402912173,
      "grad_norm": 0.3547326624393463,
      "learning_rate": 1.7713234135908833e-05,
      "loss": 0.6002,
      "step": 14376
    },
    {
      "epoch": 0.4416490031640709,
      "grad_norm": 0.3308441638946533,
      "learning_rate": 1.7712926548234078e-05,
      "loss": 0.5999,
      "step": 14377
    },
    {
      "epoch": 0.4416797222990201,
      "grad_norm": 0.3283008635044098,
      "learning_rate": 1.7712618942545246e-05,
      "loss": 0.5698,
      "step": 14378
    },
    {
      "epoch": 0.4417104414339692,
      "grad_norm": 0.34067362546920776,
      "learning_rate": 1.7712311318843052e-05,
      "loss": 0.5987,
      "step": 14379
    },
    {
      "epoch": 0.4417411605689184,
      "grad_norm": 0.3517695963382721,
      "learning_rate": 1.771200367712822e-05,
      "loss": 0.6379,
      "step": 14380
    },
    {
      "epoch": 0.44177187970386755,
      "grad_norm": 0.3319064974784851,
      "learning_rate": 1.7711696017401463e-05,
      "loss": 0.6053,
      "step": 14381
    },
    {
      "epoch": 0.4418025988388167,
      "grad_norm": 0.34226247668266296,
      "learning_rate": 1.7711388339663503e-05,
      "loss": 0.5165,
      "step": 14382
    },
    {
      "epoch": 0.44183331797376585,
      "grad_norm": 0.33781927824020386,
      "learning_rate": 1.7711080643915056e-05,
      "loss": 0.5895,
      "step": 14383
    },
    {
      "epoch": 0.441864037108715,
      "grad_norm": 0.33314603567123413,
      "learning_rate": 1.7710772930156837e-05,
      "loss": 0.5603,
      "step": 14384
    },
    {
      "epoch": 0.4418947562436642,
      "grad_norm": 0.39530614018440247,
      "learning_rate": 1.7710465198389574e-05,
      "loss": 0.6072,
      "step": 14385
    },
    {
      "epoch": 0.4419254753786133,
      "grad_norm": 0.35518336296081543,
      "learning_rate": 1.7710157448613983e-05,
      "loss": 0.5753,
      "step": 14386
    },
    {
      "epoch": 0.4419561945135625,
      "grad_norm": 0.3127215802669525,
      "learning_rate": 1.7709849680830777e-05,
      "loss": 0.5615,
      "step": 14387
    },
    {
      "epoch": 0.44198691364851167,
      "grad_norm": 0.3844248652458191,
      "learning_rate": 1.770954189504068e-05,
      "loss": 0.6431,
      "step": 14388
    },
    {
      "epoch": 0.44201763278346085,
      "grad_norm": 0.312347412109375,
      "learning_rate": 1.7709234091244408e-05,
      "loss": 0.5864,
      "step": 14389
    },
    {
      "epoch": 0.44204835191840997,
      "grad_norm": 0.33770477771759033,
      "learning_rate": 1.7708926269442685e-05,
      "loss": 0.5577,
      "step": 14390
    },
    {
      "epoch": 0.44207907105335914,
      "grad_norm": 0.40297818183898926,
      "learning_rate": 1.7708618429636223e-05,
      "loss": 0.6169,
      "step": 14391
    },
    {
      "epoch": 0.4421097901883083,
      "grad_norm": 0.32883283495903015,
      "learning_rate": 1.7708310571825748e-05,
      "loss": 0.5745,
      "step": 14392
    },
    {
      "epoch": 0.44214050932325744,
      "grad_norm": 0.4138140082359314,
      "learning_rate": 1.770800269601197e-05,
      "loss": 0.613,
      "step": 14393
    },
    {
      "epoch": 0.4421712284582066,
      "grad_norm": 0.33626285195350647,
      "learning_rate": 1.7707694802195617e-05,
      "loss": 0.5874,
      "step": 14394
    },
    {
      "epoch": 0.4422019475931558,
      "grad_norm": 0.3760296106338501,
      "learning_rate": 1.7707386890377403e-05,
      "loss": 0.5143,
      "step": 14395
    },
    {
      "epoch": 0.44223266672810496,
      "grad_norm": 0.34088101983070374,
      "learning_rate": 1.7707078960558048e-05,
      "loss": 0.5952,
      "step": 14396
    },
    {
      "epoch": 0.4422633858630541,
      "grad_norm": 0.3247789740562439,
      "learning_rate": 1.7706771012738273e-05,
      "loss": 0.5437,
      "step": 14397
    },
    {
      "epoch": 0.44229410499800326,
      "grad_norm": 0.3649034798145294,
      "learning_rate": 1.7706463046918798e-05,
      "loss": 0.579,
      "step": 14398
    },
    {
      "epoch": 0.44232482413295243,
      "grad_norm": 0.36861708760261536,
      "learning_rate": 1.7706155063100336e-05,
      "loss": 0.5821,
      "step": 14399
    },
    {
      "epoch": 0.44235554326790155,
      "grad_norm": 0.38890573382377625,
      "learning_rate": 1.770584706128361e-05,
      "loss": 0.622,
      "step": 14400
    },
    {
      "epoch": 0.4423862624028507,
      "grad_norm": 0.3418840169906616,
      "learning_rate": 1.7705539041469346e-05,
      "loss": 0.5426,
      "step": 14401
    },
    {
      "epoch": 0.4424169815377999,
      "grad_norm": 0.38287848234176636,
      "learning_rate": 1.7705231003658253e-05,
      "loss": 0.619,
      "step": 14402
    },
    {
      "epoch": 0.4424477006727491,
      "grad_norm": 0.34152477979660034,
      "learning_rate": 1.7704922947851058e-05,
      "loss": 0.5123,
      "step": 14403
    },
    {
      "epoch": 0.4424784198076982,
      "grad_norm": 0.3509504795074463,
      "learning_rate": 1.7704614874048475e-05,
      "loss": 0.5844,
      "step": 14404
    },
    {
      "epoch": 0.4425091389426474,
      "grad_norm": 0.36065199971199036,
      "learning_rate": 1.7704306782251226e-05,
      "loss": 0.5344,
      "step": 14405
    },
    {
      "epoch": 0.44253985807759655,
      "grad_norm": 0.3357742130756378,
      "learning_rate": 1.7703998672460033e-05,
      "loss": 0.5864,
      "step": 14406
    },
    {
      "epoch": 0.44257057721254567,
      "grad_norm": 0.3335370421409607,
      "learning_rate": 1.770369054467561e-05,
      "loss": 0.5715,
      "step": 14407
    },
    {
      "epoch": 0.44260129634749484,
      "grad_norm": 0.4311310052871704,
      "learning_rate": 1.7703382398898682e-05,
      "loss": 0.5512,
      "step": 14408
    },
    {
      "epoch": 0.442632015482444,
      "grad_norm": 0.3526076078414917,
      "learning_rate": 1.7703074235129965e-05,
      "loss": 0.575,
      "step": 14409
    },
    {
      "epoch": 0.4426627346173932,
      "grad_norm": 0.3444397449493408,
      "learning_rate": 1.770276605337018e-05,
      "loss": 0.5156,
      "step": 14410
    },
    {
      "epoch": 0.4426934537523423,
      "grad_norm": 0.3343066871166229,
      "learning_rate": 1.7702457853620046e-05,
      "loss": 0.5155,
      "step": 14411
    },
    {
      "epoch": 0.4427241728872915,
      "grad_norm": 0.41618362069129944,
      "learning_rate": 1.7702149635880287e-05,
      "loss": 0.4983,
      "step": 14412
    },
    {
      "epoch": 0.44275489202224066,
      "grad_norm": 0.39311859011650085,
      "learning_rate": 1.7701841400151615e-05,
      "loss": 0.6126,
      "step": 14413
    },
    {
      "epoch": 0.44278561115718984,
      "grad_norm": 0.39372608065605164,
      "learning_rate": 1.7701533146434758e-05,
      "loss": 0.6333,
      "step": 14414
    },
    {
      "epoch": 0.44281633029213896,
      "grad_norm": 0.35354864597320557,
      "learning_rate": 1.770122487473043e-05,
      "loss": 0.5943,
      "step": 14415
    },
    {
      "epoch": 0.44284704942708814,
      "grad_norm": 0.3821197748184204,
      "learning_rate": 1.7700916585039357e-05,
      "loss": 0.6857,
      "step": 14416
    },
    {
      "epoch": 0.4428777685620373,
      "grad_norm": 0.328844279050827,
      "learning_rate": 1.7700608277362253e-05,
      "loss": 0.5147,
      "step": 14417
    },
    {
      "epoch": 0.44290848769698643,
      "grad_norm": 0.3554466664791107,
      "learning_rate": 1.770029995169984e-05,
      "loss": 0.4796,
      "step": 14418
    },
    {
      "epoch": 0.4429392068319356,
      "grad_norm": 0.35396063327789307,
      "learning_rate": 1.7699991608052842e-05,
      "loss": 0.5542,
      "step": 14419
    },
    {
      "epoch": 0.4429699259668848,
      "grad_norm": 0.3436600863933563,
      "learning_rate": 1.7699683246421972e-05,
      "loss": 0.6363,
      "step": 14420
    },
    {
      "epoch": 0.44300064510183396,
      "grad_norm": 0.36035022139549255,
      "learning_rate": 1.7699374866807955e-05,
      "loss": 0.5646,
      "step": 14421
    },
    {
      "epoch": 0.4430313642367831,
      "grad_norm": 0.33530282974243164,
      "learning_rate": 1.769906646921151e-05,
      "loss": 0.619,
      "step": 14422
    },
    {
      "epoch": 0.44306208337173225,
      "grad_norm": 0.3621293306350708,
      "learning_rate": 1.769875805363336e-05,
      "loss": 0.5642,
      "step": 14423
    },
    {
      "epoch": 0.4430928025066814,
      "grad_norm": 0.34471067786216736,
      "learning_rate": 1.7698449620074224e-05,
      "loss": 0.5634,
      "step": 14424
    },
    {
      "epoch": 0.44312352164163055,
      "grad_norm": 0.4045447111129761,
      "learning_rate": 1.7698141168534818e-05,
      "loss": 0.6635,
      "step": 14425
    },
    {
      "epoch": 0.4431542407765797,
      "grad_norm": 0.355633944272995,
      "learning_rate": 1.7697832699015864e-05,
      "loss": 0.5933,
      "step": 14426
    },
    {
      "epoch": 0.4431849599115289,
      "grad_norm": 0.33961841464042664,
      "learning_rate": 1.7697524211518086e-05,
      "loss": 0.5367,
      "step": 14427
    },
    {
      "epoch": 0.4432156790464781,
      "grad_norm": 0.357686311006546,
      "learning_rate": 1.7697215706042204e-05,
      "loss": 0.6368,
      "step": 14428
    },
    {
      "epoch": 0.4432463981814272,
      "grad_norm": 0.34730127453804016,
      "learning_rate": 1.7696907182588935e-05,
      "loss": 0.604,
      "step": 14429
    },
    {
      "epoch": 0.44327711731637637,
      "grad_norm": 0.35805749893188477,
      "learning_rate": 1.7696598641159005e-05,
      "loss": 0.636,
      "step": 14430
    },
    {
      "epoch": 0.44330783645132554,
      "grad_norm": 0.3320354223251343,
      "learning_rate": 1.7696290081753128e-05,
      "loss": 0.5497,
      "step": 14431
    },
    {
      "epoch": 0.44333855558627466,
      "grad_norm": 0.37473922967910767,
      "learning_rate": 1.769598150437203e-05,
      "loss": 0.6409,
      "step": 14432
    },
    {
      "epoch": 0.44336927472122384,
      "grad_norm": 0.32529258728027344,
      "learning_rate": 1.7695672909016427e-05,
      "loss": 0.5962,
      "step": 14433
    },
    {
      "epoch": 0.443399993856173,
      "grad_norm": 0.34258878231048584,
      "learning_rate": 1.7695364295687047e-05,
      "loss": 0.5617,
      "step": 14434
    },
    {
      "epoch": 0.4434307129911222,
      "grad_norm": 0.3777921497821808,
      "learning_rate": 1.7695055664384603e-05,
      "loss": 0.6416,
      "step": 14435
    },
    {
      "epoch": 0.4434614321260713,
      "grad_norm": 0.3296549320220947,
      "learning_rate": 1.769474701510982e-05,
      "loss": 0.4582,
      "step": 14436
    },
    {
      "epoch": 0.4434921512610205,
      "grad_norm": 0.3402400016784668,
      "learning_rate": 1.769443834786342e-05,
      "loss": 0.5641,
      "step": 14437
    },
    {
      "epoch": 0.44352287039596966,
      "grad_norm": 0.36236947774887085,
      "learning_rate": 1.769412966264612e-05,
      "loss": 0.5869,
      "step": 14438
    },
    {
      "epoch": 0.44355358953091883,
      "grad_norm": 0.3429669439792633,
      "learning_rate": 1.7693820959458642e-05,
      "loss": 0.6266,
      "step": 14439
    },
    {
      "epoch": 0.44358430866586795,
      "grad_norm": 0.3691180646419525,
      "learning_rate": 1.7693512238301707e-05,
      "loss": 0.522,
      "step": 14440
    },
    {
      "epoch": 0.44361502780081713,
      "grad_norm": 0.43263405561447144,
      "learning_rate": 1.769320349917604e-05,
      "loss": 0.6892,
      "step": 14441
    },
    {
      "epoch": 0.4436457469357663,
      "grad_norm": 0.577573299407959,
      "learning_rate": 1.7692894742082355e-05,
      "loss": 0.5721,
      "step": 14442
    },
    {
      "epoch": 0.4436764660707154,
      "grad_norm": 0.5038996338844299,
      "learning_rate": 1.7692585967021378e-05,
      "loss": 0.6109,
      "step": 14443
    },
    {
      "epoch": 0.4437071852056646,
      "grad_norm": 0.32382866740226746,
      "learning_rate": 1.769227717399383e-05,
      "loss": 0.4721,
      "step": 14444
    },
    {
      "epoch": 0.4437379043406138,
      "grad_norm": 0.3490365445613861,
      "learning_rate": 1.769196836300043e-05,
      "loss": 0.6404,
      "step": 14445
    },
    {
      "epoch": 0.44376862347556295,
      "grad_norm": 0.32229188084602356,
      "learning_rate": 1.7691659534041906e-05,
      "loss": 0.5726,
      "step": 14446
    },
    {
      "epoch": 0.44379934261051207,
      "grad_norm": 0.3198053538799286,
      "learning_rate": 1.7691350687118973e-05,
      "loss": 0.5774,
      "step": 14447
    },
    {
      "epoch": 0.44383006174546125,
      "grad_norm": 0.36743035912513733,
      "learning_rate": 1.769104182223235e-05,
      "loss": 0.5829,
      "step": 14448
    },
    {
      "epoch": 0.4438607808804104,
      "grad_norm": 0.3117993474006653,
      "learning_rate": 1.769073293938276e-05,
      "loss": 0.4982,
      "step": 14449
    },
    {
      "epoch": 0.44389150001535954,
      "grad_norm": 0.3494184911251068,
      "learning_rate": 1.7690424038570928e-05,
      "loss": 0.6244,
      "step": 14450
    },
    {
      "epoch": 0.4439222191503087,
      "grad_norm": 0.3165338337421417,
      "learning_rate": 1.7690115119797574e-05,
      "loss": 0.5485,
      "step": 14451
    },
    {
      "epoch": 0.4439529382852579,
      "grad_norm": 0.3749319911003113,
      "learning_rate": 1.7689806183063418e-05,
      "loss": 0.5326,
      "step": 14452
    },
    {
      "epoch": 0.44398365742020707,
      "grad_norm": 0.3382202684879303,
      "learning_rate": 1.7689497228369186e-05,
      "loss": 0.5421,
      "step": 14453
    },
    {
      "epoch": 0.4440143765551562,
      "grad_norm": 0.463530957698822,
      "learning_rate": 1.7689188255715595e-05,
      "loss": 0.643,
      "step": 14454
    },
    {
      "epoch": 0.44404509569010536,
      "grad_norm": 0.38087329268455505,
      "learning_rate": 1.7688879265103364e-05,
      "loss": 0.5614,
      "step": 14455
    },
    {
      "epoch": 0.44407581482505454,
      "grad_norm": 0.3366742432117462,
      "learning_rate": 1.7688570256533225e-05,
      "loss": 0.5622,
      "step": 14456
    },
    {
      "epoch": 0.4441065339600037,
      "grad_norm": 0.39341115951538086,
      "learning_rate": 1.7688261230005886e-05,
      "loss": 0.658,
      "step": 14457
    },
    {
      "epoch": 0.44413725309495283,
      "grad_norm": 0.4516869783401489,
      "learning_rate": 1.7687952185522082e-05,
      "loss": 0.5871,
      "step": 14458
    },
    {
      "epoch": 0.444167972229902,
      "grad_norm": 1.0472359657287598,
      "learning_rate": 1.7687643123082524e-05,
      "loss": 0.4992,
      "step": 14459
    },
    {
      "epoch": 0.4441986913648512,
      "grad_norm": 0.35419365763664246,
      "learning_rate": 1.7687334042687942e-05,
      "loss": 0.5208,
      "step": 14460
    },
    {
      "epoch": 0.4442294104998003,
      "grad_norm": 0.3995177745819092,
      "learning_rate": 1.7687024944339053e-05,
      "loss": 0.6178,
      "step": 14461
    },
    {
      "epoch": 0.4442601296347495,
      "grad_norm": 0.3688625991344452,
      "learning_rate": 1.768671582803658e-05,
      "loss": 0.4923,
      "step": 14462
    },
    {
      "epoch": 0.44429084876969865,
      "grad_norm": 0.33791232109069824,
      "learning_rate": 1.7686406693781245e-05,
      "loss": 0.5565,
      "step": 14463
    },
    {
      "epoch": 0.44432156790464783,
      "grad_norm": 0.37763020396232605,
      "learning_rate": 1.7686097541573773e-05,
      "loss": 0.4946,
      "step": 14464
    },
    {
      "epoch": 0.44435228703959695,
      "grad_norm": 0.33691805601119995,
      "learning_rate": 1.768578837141488e-05,
      "loss": 0.5827,
      "step": 14465
    },
    {
      "epoch": 0.4443830061745461,
      "grad_norm": 0.3628377914428711,
      "learning_rate": 1.7685479183305293e-05,
      "loss": 0.5699,
      "step": 14466
    },
    {
      "epoch": 0.4444137253094953,
      "grad_norm": 0.3813329041004181,
      "learning_rate": 1.7685169977245736e-05,
      "loss": 0.6511,
      "step": 14467
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.37670478224754333,
      "learning_rate": 1.7684860753236925e-05,
      "loss": 0.5641,
      "step": 14468
    },
    {
      "epoch": 0.4444751635793936,
      "grad_norm": 0.3357093930244446,
      "learning_rate": 1.7684551511279583e-05,
      "loss": 0.5507,
      "step": 14469
    },
    {
      "epoch": 0.44450588271434277,
      "grad_norm": 0.4183429181575775,
      "learning_rate": 1.7684242251374436e-05,
      "loss": 0.5735,
      "step": 14470
    },
    {
      "epoch": 0.44453660184929195,
      "grad_norm": 0.40480169653892517,
      "learning_rate": 1.7683932973522203e-05,
      "loss": 0.5874,
      "step": 14471
    },
    {
      "epoch": 0.44456732098424107,
      "grad_norm": 0.4052973985671997,
      "learning_rate": 1.7683623677723608e-05,
      "loss": 0.5392,
      "step": 14472
    },
    {
      "epoch": 0.44459804011919024,
      "grad_norm": 0.335418701171875,
      "learning_rate": 1.7683314363979377e-05,
      "loss": 0.617,
      "step": 14473
    },
    {
      "epoch": 0.4446287592541394,
      "grad_norm": 0.3877299129962921,
      "learning_rate": 1.7683005032290224e-05,
      "loss": 0.5653,
      "step": 14474
    },
    {
      "epoch": 0.44465947838908854,
      "grad_norm": 0.5879667401313782,
      "learning_rate": 1.7682695682656882e-05,
      "loss": 0.4518,
      "step": 14475
    },
    {
      "epoch": 0.4446901975240377,
      "grad_norm": 0.35718315839767456,
      "learning_rate": 1.7682386315080065e-05,
      "loss": 0.5177,
      "step": 14476
    },
    {
      "epoch": 0.4447209166589869,
      "grad_norm": 0.3779819905757904,
      "learning_rate": 1.7682076929560498e-05,
      "loss": 0.5974,
      "step": 14477
    },
    {
      "epoch": 0.44475163579393606,
      "grad_norm": 0.3239845633506775,
      "learning_rate": 1.76817675260989e-05,
      "loss": 0.5209,
      "step": 14478
    },
    {
      "epoch": 0.4447823549288852,
      "grad_norm": 0.35350364446640015,
      "learning_rate": 1.7681458104696e-05,
      "loss": 0.5594,
      "step": 14479
    },
    {
      "epoch": 0.44481307406383436,
      "grad_norm": 0.3465787172317505,
      "learning_rate": 1.7681148665352522e-05,
      "loss": 0.5663,
      "step": 14480
    },
    {
      "epoch": 0.44484379319878353,
      "grad_norm": 0.3453620970249176,
      "learning_rate": 1.768083920806918e-05,
      "loss": 0.5587,
      "step": 14481
    },
    {
      "epoch": 0.4448745123337327,
      "grad_norm": 0.4374029040336609,
      "learning_rate": 1.7680529732846703e-05,
      "loss": 0.6008,
      "step": 14482
    },
    {
      "epoch": 0.4449052314686818,
      "grad_norm": 0.35281476378440857,
      "learning_rate": 1.7680220239685813e-05,
      "loss": 0.5821,
      "step": 14483
    },
    {
      "epoch": 0.444935950603631,
      "grad_norm": 0.3403327465057373,
      "learning_rate": 1.7679910728587232e-05,
      "loss": 0.5764,
      "step": 14484
    },
    {
      "epoch": 0.4449666697385802,
      "grad_norm": 0.3224913775920868,
      "learning_rate": 1.7679601199551684e-05,
      "loss": 0.6342,
      "step": 14485
    },
    {
      "epoch": 0.4449973888735293,
      "grad_norm": 0.36708948016166687,
      "learning_rate": 1.767929165257989e-05,
      "loss": 0.6848,
      "step": 14486
    },
    {
      "epoch": 0.4450281080084785,
      "grad_norm": 0.35330089926719666,
      "learning_rate": 1.7678982087672574e-05,
      "loss": 0.5947,
      "step": 14487
    },
    {
      "epoch": 0.44505882714342765,
      "grad_norm": 0.3859032094478607,
      "learning_rate": 1.7678672504830458e-05,
      "loss": 0.5774,
      "step": 14488
    },
    {
      "epoch": 0.4450895462783768,
      "grad_norm": 0.3687684237957001,
      "learning_rate": 1.767836290405427e-05,
      "loss": 0.6309,
      "step": 14489
    },
    {
      "epoch": 0.44512026541332594,
      "grad_norm": 0.37691372632980347,
      "learning_rate": 1.7678053285344726e-05,
      "loss": 0.504,
      "step": 14490
    },
    {
      "epoch": 0.4451509845482751,
      "grad_norm": 0.3886066675186157,
      "learning_rate": 1.7677743648702554e-05,
      "loss": 0.5779,
      "step": 14491
    },
    {
      "epoch": 0.4451817036832243,
      "grad_norm": 0.32917094230651855,
      "learning_rate": 1.7677433994128474e-05,
      "loss": 0.5488,
      "step": 14492
    },
    {
      "epoch": 0.4452124228181734,
      "grad_norm": 0.3439317047595978,
      "learning_rate": 1.767712432162321e-05,
      "loss": 0.5755,
      "step": 14493
    },
    {
      "epoch": 0.4452431419531226,
      "grad_norm": 0.31596508622169495,
      "learning_rate": 1.7676814631187487e-05,
      "loss": 0.5506,
      "step": 14494
    },
    {
      "epoch": 0.44527386108807177,
      "grad_norm": 0.33660900592803955,
      "learning_rate": 1.7676504922822027e-05,
      "loss": 0.5834,
      "step": 14495
    },
    {
      "epoch": 0.44530458022302094,
      "grad_norm": 0.36636632680892944,
      "learning_rate": 1.7676195196527556e-05,
      "loss": 0.56,
      "step": 14496
    },
    {
      "epoch": 0.44533529935797006,
      "grad_norm": 0.33357831835746765,
      "learning_rate": 1.767588545230479e-05,
      "loss": 0.6151,
      "step": 14497
    },
    {
      "epoch": 0.44536601849291924,
      "grad_norm": 0.325295627117157,
      "learning_rate": 1.7675575690154462e-05,
      "loss": 0.569,
      "step": 14498
    },
    {
      "epoch": 0.4453967376278684,
      "grad_norm": 0.3227526545524597,
      "learning_rate": 1.767526591007729e-05,
      "loss": 0.5686,
      "step": 14499
    },
    {
      "epoch": 0.4454274567628176,
      "grad_norm": 0.4261064827442169,
      "learning_rate": 1.7674956112073994e-05,
      "loss": 0.5913,
      "step": 14500
    },
    {
      "epoch": 0.4454581758977667,
      "grad_norm": 0.3343321979045868,
      "learning_rate": 1.7674646296145308e-05,
      "loss": 0.5884,
      "step": 14501
    },
    {
      "epoch": 0.4454888950327159,
      "grad_norm": 0.3269988000392914,
      "learning_rate": 1.7674336462291948e-05,
      "loss": 0.5771,
      "step": 14502
    },
    {
      "epoch": 0.44551961416766506,
      "grad_norm": 0.37660086154937744,
      "learning_rate": 1.7674026610514638e-05,
      "loss": 0.5609,
      "step": 14503
    },
    {
      "epoch": 0.4455503333026142,
      "grad_norm": 0.35835233330726624,
      "learning_rate": 1.76737167408141e-05,
      "loss": 0.5795,
      "step": 14504
    },
    {
      "epoch": 0.44558105243756335,
      "grad_norm": 0.33055150508880615,
      "learning_rate": 1.767340685319107e-05,
      "loss": 0.5502,
      "step": 14505
    },
    {
      "epoch": 0.4456117715725125,
      "grad_norm": 0.3358340263366699,
      "learning_rate": 1.7673096947646253e-05,
      "loss": 0.591,
      "step": 14506
    },
    {
      "epoch": 0.4456424907074617,
      "grad_norm": 0.3528597950935364,
      "learning_rate": 1.7672787024180387e-05,
      "loss": 0.5686,
      "step": 14507
    },
    {
      "epoch": 0.4456732098424108,
      "grad_norm": 0.33811014890670776,
      "learning_rate": 1.767247708279419e-05,
      "loss": 0.5873,
      "step": 14508
    },
    {
      "epoch": 0.44570392897736,
      "grad_norm": 0.36651870608329773,
      "learning_rate": 1.7672167123488388e-05,
      "loss": 0.5495,
      "step": 14509
    },
    {
      "epoch": 0.4457346481123092,
      "grad_norm": 0.39970284700393677,
      "learning_rate": 1.7671857146263703e-05,
      "loss": 0.5405,
      "step": 14510
    },
    {
      "epoch": 0.4457653672472583,
      "grad_norm": 0.3306867778301239,
      "learning_rate": 1.767154715112086e-05,
      "loss": 0.6268,
      "step": 14511
    },
    {
      "epoch": 0.44579608638220747,
      "grad_norm": 0.2905316948890686,
      "learning_rate": 1.767123713806058e-05,
      "loss": 0.485,
      "step": 14512
    },
    {
      "epoch": 0.44582680551715664,
      "grad_norm": 0.34061872959136963,
      "learning_rate": 1.7670927107083594e-05,
      "loss": 0.6034,
      "step": 14513
    },
    {
      "epoch": 0.4458575246521058,
      "grad_norm": 0.3769204616546631,
      "learning_rate": 1.7670617058190614e-05,
      "loss": 0.5478,
      "step": 14514
    },
    {
      "epoch": 0.44588824378705494,
      "grad_norm": 0.3645727038383484,
      "learning_rate": 1.7670306991382383e-05,
      "loss": 0.4971,
      "step": 14515
    },
    {
      "epoch": 0.4459189629220041,
      "grad_norm": 0.3683595657348633,
      "learning_rate": 1.766999690665961e-05,
      "loss": 0.5963,
      "step": 14516
    },
    {
      "epoch": 0.4459496820569533,
      "grad_norm": 0.3500445783138275,
      "learning_rate": 1.766968680402302e-05,
      "loss": 0.6167,
      "step": 14517
    },
    {
      "epoch": 0.4459804011919024,
      "grad_norm": 0.3325667083263397,
      "learning_rate": 1.7669376683473347e-05,
      "loss": 0.6296,
      "step": 14518
    },
    {
      "epoch": 0.4460111203268516,
      "grad_norm": 0.3168543875217438,
      "learning_rate": 1.7669066545011305e-05,
      "loss": 0.5949,
      "step": 14519
    },
    {
      "epoch": 0.44604183946180076,
      "grad_norm": 0.36013907194137573,
      "learning_rate": 1.766875638863762e-05,
      "loss": 0.5768,
      "step": 14520
    },
    {
      "epoch": 0.44607255859674994,
      "grad_norm": 0.32453230023384094,
      "learning_rate": 1.7668446214353025e-05,
      "loss": 0.6236,
      "step": 14521
    },
    {
      "epoch": 0.44610327773169905,
      "grad_norm": 0.3510715365409851,
      "learning_rate": 1.7668136022158236e-05,
      "loss": 0.5393,
      "step": 14522
    },
    {
      "epoch": 0.44613399686664823,
      "grad_norm": 0.33518102765083313,
      "learning_rate": 1.766782581205398e-05,
      "loss": 0.5664,
      "step": 14523
    },
    {
      "epoch": 0.4461647160015974,
      "grad_norm": 0.3735114336013794,
      "learning_rate": 1.7667515584040978e-05,
      "loss": 0.5912,
      "step": 14524
    },
    {
      "epoch": 0.4461954351365466,
      "grad_norm": 0.3990814983844757,
      "learning_rate": 1.7667205338119963e-05,
      "loss": 0.5338,
      "step": 14525
    },
    {
      "epoch": 0.4462261542714957,
      "grad_norm": 0.3400079011917114,
      "learning_rate": 1.7666895074291652e-05,
      "loss": 0.6007,
      "step": 14526
    },
    {
      "epoch": 0.4462568734064449,
      "grad_norm": 0.3165518343448639,
      "learning_rate": 1.7666584792556773e-05,
      "loss": 0.4777,
      "step": 14527
    },
    {
      "epoch": 0.44628759254139405,
      "grad_norm": 0.3399011492729187,
      "learning_rate": 1.7666274492916047e-05,
      "loss": 0.5186,
      "step": 14528
    },
    {
      "epoch": 0.44631831167634317,
      "grad_norm": 0.3606298565864563,
      "learning_rate": 1.7665964175370204e-05,
      "loss": 0.5621,
      "step": 14529
    },
    {
      "epoch": 0.44634903081129235,
      "grad_norm": 0.32291704416275024,
      "learning_rate": 1.766565383991997e-05,
      "loss": 0.5884,
      "step": 14530
    },
    {
      "epoch": 0.4463797499462415,
      "grad_norm": 0.37435853481292725,
      "learning_rate": 1.766534348656606e-05,
      "loss": 0.6658,
      "step": 14531
    },
    {
      "epoch": 0.4464104690811907,
      "grad_norm": 0.32451504468917847,
      "learning_rate": 1.7665033115309205e-05,
      "loss": 0.5097,
      "step": 14532
    },
    {
      "epoch": 0.4464411882161398,
      "grad_norm": 0.34154096245765686,
      "learning_rate": 1.766472272615013e-05,
      "loss": 0.5272,
      "step": 14533
    },
    {
      "epoch": 0.446471907351089,
      "grad_norm": 0.3158506155014038,
      "learning_rate": 1.7664412319089565e-05,
      "loss": 0.5724,
      "step": 14534
    },
    {
      "epoch": 0.44650262648603817,
      "grad_norm": 0.3471941649913788,
      "learning_rate": 1.7664101894128225e-05,
      "loss": 0.5706,
      "step": 14535
    },
    {
      "epoch": 0.4465333456209873,
      "grad_norm": 0.3755855858325958,
      "learning_rate": 1.7663791451266842e-05,
      "loss": 0.6149,
      "step": 14536
    },
    {
      "epoch": 0.44656406475593646,
      "grad_norm": 0.4016554653644562,
      "learning_rate": 1.766348099050614e-05,
      "loss": 0.6122,
      "step": 14537
    },
    {
      "epoch": 0.44659478389088564,
      "grad_norm": 0.40238261222839355,
      "learning_rate": 1.766317051184684e-05,
      "loss": 0.5851,
      "step": 14538
    },
    {
      "epoch": 0.4466255030258348,
      "grad_norm": 0.3415824770927429,
      "learning_rate": 1.766286001528967e-05,
      "loss": 0.4549,
      "step": 14539
    },
    {
      "epoch": 0.44665622216078393,
      "grad_norm": 0.3512069880962372,
      "learning_rate": 1.7662549500835355e-05,
      "loss": 0.5321,
      "step": 14540
    },
    {
      "epoch": 0.4466869412957331,
      "grad_norm": 0.3830816447734833,
      "learning_rate": 1.7662238968484623e-05,
      "loss": 0.6255,
      "step": 14541
    },
    {
      "epoch": 0.4467176604306823,
      "grad_norm": 0.40642398595809937,
      "learning_rate": 1.7661928418238196e-05,
      "loss": 0.4874,
      "step": 14542
    },
    {
      "epoch": 0.44674837956563146,
      "grad_norm": 0.36085155606269836,
      "learning_rate": 1.7661617850096798e-05,
      "loss": 0.6411,
      "step": 14543
    },
    {
      "epoch": 0.4467790987005806,
      "grad_norm": 0.36699268221855164,
      "learning_rate": 1.7661307264061158e-05,
      "loss": 0.6217,
      "step": 14544
    },
    {
      "epoch": 0.44680981783552975,
      "grad_norm": 0.35000157356262207,
      "learning_rate": 1.7660996660132e-05,
      "loss": 0.5703,
      "step": 14545
    },
    {
      "epoch": 0.44684053697047893,
      "grad_norm": 0.34919920563697815,
      "learning_rate": 1.766068603831005e-05,
      "loss": 0.5583,
      "step": 14546
    },
    {
      "epoch": 0.44687125610542805,
      "grad_norm": 0.40133655071258545,
      "learning_rate": 1.7660375398596032e-05,
      "loss": 0.5302,
      "step": 14547
    },
    {
      "epoch": 0.4469019752403772,
      "grad_norm": 0.36922842264175415,
      "learning_rate": 1.7660064740990672e-05,
      "loss": 0.5926,
      "step": 14548
    },
    {
      "epoch": 0.4469326943753264,
      "grad_norm": 0.3412439525127411,
      "learning_rate": 1.7659754065494696e-05,
      "loss": 0.5513,
      "step": 14549
    },
    {
      "epoch": 0.4469634135102756,
      "grad_norm": 0.4693240523338318,
      "learning_rate": 1.7659443372108828e-05,
      "loss": 0.5439,
      "step": 14550
    },
    {
      "epoch": 0.4469941326452247,
      "grad_norm": 0.3350710868835449,
      "learning_rate": 1.7659132660833797e-05,
      "loss": 0.549,
      "step": 14551
    },
    {
      "epoch": 0.44702485178017387,
      "grad_norm": 0.36688852310180664,
      "learning_rate": 1.7658821931670328e-05,
      "loss": 0.5687,
      "step": 14552
    },
    {
      "epoch": 0.44705557091512305,
      "grad_norm": 0.34582966566085815,
      "learning_rate": 1.7658511184619142e-05,
      "loss": 0.6105,
      "step": 14553
    },
    {
      "epoch": 0.44708629005007217,
      "grad_norm": 0.3220674395561218,
      "learning_rate": 1.765820041968097e-05,
      "loss": 0.6121,
      "step": 14554
    },
    {
      "epoch": 0.44711700918502134,
      "grad_norm": 0.3510936200618744,
      "learning_rate": 1.7657889636856537e-05,
      "loss": 0.5622,
      "step": 14555
    },
    {
      "epoch": 0.4471477283199705,
      "grad_norm": 0.3531995713710785,
      "learning_rate": 1.7657578836146566e-05,
      "loss": 0.5852,
      "step": 14556
    },
    {
      "epoch": 0.4471784474549197,
      "grad_norm": 0.40028756856918335,
      "learning_rate": 1.7657268017551787e-05,
      "loss": 0.6036,
      "step": 14557
    },
    {
      "epoch": 0.4472091665898688,
      "grad_norm": 0.40450119972229004,
      "learning_rate": 1.765695718107292e-05,
      "loss": 0.5329,
      "step": 14558
    },
    {
      "epoch": 0.447239885724818,
      "grad_norm": 0.315731018781662,
      "learning_rate": 1.7656646326710696e-05,
      "loss": 0.5243,
      "step": 14559
    },
    {
      "epoch": 0.44727060485976716,
      "grad_norm": 0.37794724106788635,
      "learning_rate": 1.7656335454465843e-05,
      "loss": 0.5627,
      "step": 14560
    },
    {
      "epoch": 0.4473013239947163,
      "grad_norm": 0.3782263398170471,
      "learning_rate": 1.765602456433908e-05,
      "loss": 0.5219,
      "step": 14561
    },
    {
      "epoch": 0.44733204312966546,
      "grad_norm": 0.3534214198589325,
      "learning_rate": 1.7655713656331143e-05,
      "loss": 0.4584,
      "step": 14562
    },
    {
      "epoch": 0.44736276226461463,
      "grad_norm": 0.4122005105018616,
      "learning_rate": 1.7655402730442744e-05,
      "loss": 0.5435,
      "step": 14563
    },
    {
      "epoch": 0.4473934813995638,
      "grad_norm": 0.4781878888607025,
      "learning_rate": 1.765509178667462e-05,
      "loss": 0.4806,
      "step": 14564
    },
    {
      "epoch": 0.44742420053451293,
      "grad_norm": 0.3651675581932068,
      "learning_rate": 1.76547808250275e-05,
      "loss": 0.5207,
      "step": 14565
    },
    {
      "epoch": 0.4474549196694621,
      "grad_norm": 0.4997875392436981,
      "learning_rate": 1.7654469845502098e-05,
      "loss": 0.6394,
      "step": 14566
    },
    {
      "epoch": 0.4474856388044113,
      "grad_norm": 0.39089369773864746,
      "learning_rate": 1.765415884809915e-05,
      "loss": 0.6243,
      "step": 14567
    },
    {
      "epoch": 0.44751635793936045,
      "grad_norm": 0.34501081705093384,
      "learning_rate": 1.765384783281938e-05,
      "loss": 0.5732,
      "step": 14568
    },
    {
      "epoch": 0.4475470770743096,
      "grad_norm": 0.42848825454711914,
      "learning_rate": 1.7653536799663512e-05,
      "loss": 0.5084,
      "step": 14569
    },
    {
      "epoch": 0.44757779620925875,
      "grad_norm": 0.3647865056991577,
      "learning_rate": 1.7653225748632273e-05,
      "loss": 0.6216,
      "step": 14570
    },
    {
      "epoch": 0.4476085153442079,
      "grad_norm": 0.3179760277271271,
      "learning_rate": 1.7652914679726393e-05,
      "loss": 0.5214,
      "step": 14571
    },
    {
      "epoch": 0.44763923447915704,
      "grad_norm": 0.3342128098011017,
      "learning_rate": 1.76526035929466e-05,
      "loss": 0.5685,
      "step": 14572
    },
    {
      "epoch": 0.4476699536141062,
      "grad_norm": 0.391663134098053,
      "learning_rate": 1.765229248829361e-05,
      "loss": 0.5536,
      "step": 14573
    },
    {
      "epoch": 0.4477006727490554,
      "grad_norm": 0.3587493598461151,
      "learning_rate": 1.765198136576816e-05,
      "loss": 0.5077,
      "step": 14574
    },
    {
      "epoch": 0.44773139188400457,
      "grad_norm": 0.3560161292552948,
      "learning_rate": 1.7651670225370975e-05,
      "loss": 0.6576,
      "step": 14575
    },
    {
      "epoch": 0.4477621110189537,
      "grad_norm": 0.35324323177337646,
      "learning_rate": 1.7651359067102776e-05,
      "loss": 0.566,
      "step": 14576
    },
    {
      "epoch": 0.44779283015390287,
      "grad_norm": 0.36529064178466797,
      "learning_rate": 1.7651047890964297e-05,
      "loss": 0.5551,
      "step": 14577
    },
    {
      "epoch": 0.44782354928885204,
      "grad_norm": 0.3382253050804138,
      "learning_rate": 1.7650736696956258e-05,
      "loss": 0.5987,
      "step": 14578
    },
    {
      "epoch": 0.44785426842380116,
      "grad_norm": 0.5261014699935913,
      "learning_rate": 1.765042548507939e-05,
      "loss": 0.6349,
      "step": 14579
    },
    {
      "epoch": 0.44788498755875034,
      "grad_norm": 0.35101914405822754,
      "learning_rate": 1.765011425533442e-05,
      "loss": 0.616,
      "step": 14580
    },
    {
      "epoch": 0.4479157066936995,
      "grad_norm": 0.3530002534389496,
      "learning_rate": 1.7649803007722074e-05,
      "loss": 0.5617,
      "step": 14581
    },
    {
      "epoch": 0.4479464258286487,
      "grad_norm": 0.3710082173347473,
      "learning_rate": 1.7649491742243076e-05,
      "loss": 0.5991,
      "step": 14582
    },
    {
      "epoch": 0.4479771449635978,
      "grad_norm": 0.36374491453170776,
      "learning_rate": 1.7649180458898157e-05,
      "loss": 0.6251,
      "step": 14583
    },
    {
      "epoch": 0.448007864098547,
      "grad_norm": 0.37365466356277466,
      "learning_rate": 1.7648869157688046e-05,
      "loss": 0.6179,
      "step": 14584
    },
    {
      "epoch": 0.44803858323349616,
      "grad_norm": 0.3989616632461548,
      "learning_rate": 1.7648557838613465e-05,
      "loss": 0.6517,
      "step": 14585
    },
    {
      "epoch": 0.4480693023684453,
      "grad_norm": 0.3215179443359375,
      "learning_rate": 1.7648246501675142e-05,
      "loss": 0.5616,
      "step": 14586
    },
    {
      "epoch": 0.44810002150339445,
      "grad_norm": 0.49504348635673523,
      "learning_rate": 1.7647935146873805e-05,
      "loss": 0.5023,
      "step": 14587
    },
    {
      "epoch": 0.4481307406383436,
      "grad_norm": 0.3509659469127655,
      "learning_rate": 1.7647623774210184e-05,
      "loss": 0.5642,
      "step": 14588
    },
    {
      "epoch": 0.4481614597732928,
      "grad_norm": 2.6187334060668945,
      "learning_rate": 1.7647312383685e-05,
      "loss": 0.586,
      "step": 14589
    },
    {
      "epoch": 0.4481921789082419,
      "grad_norm": 0.3609037697315216,
      "learning_rate": 1.7647000975298986e-05,
      "loss": 0.6448,
      "step": 14590
    },
    {
      "epoch": 0.4482228980431911,
      "grad_norm": 0.41279155015945435,
      "learning_rate": 1.7646689549052863e-05,
      "loss": 0.5348,
      "step": 14591
    },
    {
      "epoch": 0.4482536171781403,
      "grad_norm": 0.4316806495189667,
      "learning_rate": 1.764637810494737e-05,
      "loss": 0.6497,
      "step": 14592
    },
    {
      "epoch": 0.44828433631308945,
      "grad_norm": 0.3354444205760956,
      "learning_rate": 1.7646066642983223e-05,
      "loss": 0.5668,
      "step": 14593
    },
    {
      "epoch": 0.44831505544803857,
      "grad_norm": 0.6927863955497742,
      "learning_rate": 1.764575516316115e-05,
      "loss": 0.5994,
      "step": 14594
    },
    {
      "epoch": 0.44834577458298774,
      "grad_norm": 0.44309791922569275,
      "learning_rate": 1.7645443665481887e-05,
      "loss": 0.6003,
      "step": 14595
    },
    {
      "epoch": 0.4483764937179369,
      "grad_norm": 0.3199245035648346,
      "learning_rate": 1.7645132149946156e-05,
      "loss": 0.5172,
      "step": 14596
    },
    {
      "epoch": 0.44840721285288604,
      "grad_norm": 0.40287402272224426,
      "learning_rate": 1.764482061655468e-05,
      "loss": 0.582,
      "step": 14597
    },
    {
      "epoch": 0.4484379319878352,
      "grad_norm": 0.34839561581611633,
      "learning_rate": 1.76445090653082e-05,
      "loss": 0.5908,
      "step": 14598
    },
    {
      "epoch": 0.4484686511227844,
      "grad_norm": 0.32405781745910645,
      "learning_rate": 1.7644197496207426e-05,
      "loss": 0.5695,
      "step": 14599
    },
    {
      "epoch": 0.44849937025773357,
      "grad_norm": 0.3710947632789612,
      "learning_rate": 1.76438859092531e-05,
      "loss": 0.5989,
      "step": 14600
    },
    {
      "epoch": 0.4485300893926827,
      "grad_norm": 0.31610697507858276,
      "learning_rate": 1.7643574304445946e-05,
      "loss": 0.5547,
      "step": 14601
    },
    {
      "epoch": 0.44856080852763186,
      "grad_norm": 0.3428916335105896,
      "learning_rate": 1.764326268178669e-05,
      "loss": 0.5492,
      "step": 14602
    },
    {
      "epoch": 0.44859152766258104,
      "grad_norm": 0.31076595187187195,
      "learning_rate": 1.7642951041276054e-05,
      "loss": 0.5831,
      "step": 14603
    },
    {
      "epoch": 0.44862224679753016,
      "grad_norm": 0.4130495488643646,
      "learning_rate": 1.7642639382914775e-05,
      "loss": 0.583,
      "step": 14604
    },
    {
      "epoch": 0.44865296593247933,
      "grad_norm": 0.4093203544616699,
      "learning_rate": 1.7642327706703582e-05,
      "loss": 0.512,
      "step": 14605
    },
    {
      "epoch": 0.4486836850674285,
      "grad_norm": 0.3227510452270508,
      "learning_rate": 1.76420160126432e-05,
      "loss": 0.5877,
      "step": 14606
    },
    {
      "epoch": 0.4487144042023777,
      "grad_norm": 0.41135093569755554,
      "learning_rate": 1.7641704300734347e-05,
      "loss": 0.5996,
      "step": 14607
    },
    {
      "epoch": 0.4487451233373268,
      "grad_norm": 0.35143789649009705,
      "learning_rate": 1.7641392570977766e-05,
      "loss": 0.6484,
      "step": 14608
    },
    {
      "epoch": 0.448775842472276,
      "grad_norm": 0.32897576689720154,
      "learning_rate": 1.764108082337418e-05,
      "loss": 0.5958,
      "step": 14609
    },
    {
      "epoch": 0.44880656160722515,
      "grad_norm": 0.3982601761817932,
      "learning_rate": 1.7640769057924315e-05,
      "loss": 0.5222,
      "step": 14610
    },
    {
      "epoch": 0.4488372807421743,
      "grad_norm": 1.812828779220581,
      "learning_rate": 1.76404572746289e-05,
      "loss": 0.5391,
      "step": 14611
    },
    {
      "epoch": 0.44886799987712345,
      "grad_norm": 0.33562928438186646,
      "learning_rate": 1.764014547348866e-05,
      "loss": 0.574,
      "step": 14612
    },
    {
      "epoch": 0.4488987190120726,
      "grad_norm": 0.36209362745285034,
      "learning_rate": 1.7639833654504334e-05,
      "loss": 0.5672,
      "step": 14613
    },
    {
      "epoch": 0.4489294381470218,
      "grad_norm": 0.35998642444610596,
      "learning_rate": 1.7639521817676635e-05,
      "loss": 0.524,
      "step": 14614
    },
    {
      "epoch": 0.4489601572819709,
      "grad_norm": 0.3280092477798462,
      "learning_rate": 1.7639209963006303e-05,
      "loss": 0.55,
      "step": 14615
    },
    {
      "epoch": 0.4489908764169201,
      "grad_norm": 0.368806391954422,
      "learning_rate": 1.7638898090494062e-05,
      "loss": 0.4653,
      "step": 14616
    },
    {
      "epoch": 0.44902159555186927,
      "grad_norm": 0.351606547832489,
      "learning_rate": 1.763858620014064e-05,
      "loss": 0.613,
      "step": 14617
    },
    {
      "epoch": 0.44905231468681844,
      "grad_norm": 0.38613951206207275,
      "learning_rate": 1.7638274291946767e-05,
      "loss": 0.586,
      "step": 14618
    },
    {
      "epoch": 0.44908303382176756,
      "grad_norm": 0.351244181394577,
      "learning_rate": 1.7637962365913174e-05,
      "loss": 0.5527,
      "step": 14619
    },
    {
      "epoch": 0.44911375295671674,
      "grad_norm": 0.3361966907978058,
      "learning_rate": 1.7637650422040585e-05,
      "loss": 0.593,
      "step": 14620
    },
    {
      "epoch": 0.4491444720916659,
      "grad_norm": 0.3209379017353058,
      "learning_rate": 1.763733846032973e-05,
      "loss": 0.5623,
      "step": 14621
    },
    {
      "epoch": 0.44917519122661503,
      "grad_norm": 0.35527583956718445,
      "learning_rate": 1.7637026480781337e-05,
      "loss": 0.5743,
      "step": 14622
    },
    {
      "epoch": 0.4492059103615642,
      "grad_norm": 0.41673552989959717,
      "learning_rate": 1.7636714483396135e-05,
      "loss": 0.6192,
      "step": 14623
    },
    {
      "epoch": 0.4492366294965134,
      "grad_norm": 0.37408727407455444,
      "learning_rate": 1.7636402468174854e-05,
      "loss": 0.6088,
      "step": 14624
    },
    {
      "epoch": 0.44926734863146256,
      "grad_norm": 0.36594337224960327,
      "learning_rate": 1.763609043511822e-05,
      "loss": 0.5952,
      "step": 14625
    },
    {
      "epoch": 0.4492980677664117,
      "grad_norm": 0.34434813261032104,
      "learning_rate": 1.7635778384226963e-05,
      "loss": 0.6034,
      "step": 14626
    },
    {
      "epoch": 0.44932878690136085,
      "grad_norm": 0.35090628266334534,
      "learning_rate": 1.7635466315501814e-05,
      "loss": 0.5864,
      "step": 14627
    },
    {
      "epoch": 0.44935950603631003,
      "grad_norm": 0.3258262872695923,
      "learning_rate": 1.76351542289435e-05,
      "loss": 0.4915,
      "step": 14628
    },
    {
      "epoch": 0.44939022517125915,
      "grad_norm": 0.3040028512477875,
      "learning_rate": 1.763484212455275e-05,
      "loss": 0.5325,
      "step": 14629
    },
    {
      "epoch": 0.4494209443062083,
      "grad_norm": 0.45368489623069763,
      "learning_rate": 1.7634530002330293e-05,
      "loss": 0.6308,
      "step": 14630
    },
    {
      "epoch": 0.4494516634411575,
      "grad_norm": 0.5585698485374451,
      "learning_rate": 1.7634217862276858e-05,
      "loss": 0.5739,
      "step": 14631
    },
    {
      "epoch": 0.4494823825761067,
      "grad_norm": 0.520238995552063,
      "learning_rate": 1.7633905704393176e-05,
      "loss": 0.5898,
      "step": 14632
    },
    {
      "epoch": 0.4495131017110558,
      "grad_norm": 1.4467670917510986,
      "learning_rate": 1.7633593528679972e-05,
      "loss": 0.5842,
      "step": 14633
    },
    {
      "epoch": 0.44954382084600497,
      "grad_norm": 0.35766932368278503,
      "learning_rate": 1.7633281335137975e-05,
      "loss": 0.4861,
      "step": 14634
    },
    {
      "epoch": 0.44957453998095415,
      "grad_norm": 0.31568828225135803,
      "learning_rate": 1.763296912376792e-05,
      "loss": 0.5322,
      "step": 14635
    },
    {
      "epoch": 0.4496052591159033,
      "grad_norm": 0.3698199689388275,
      "learning_rate": 1.763265689457053e-05,
      "loss": 0.5517,
      "step": 14636
    },
    {
      "epoch": 0.44963597825085244,
      "grad_norm": 0.329062283039093,
      "learning_rate": 1.7632344647546538e-05,
      "loss": 0.5417,
      "step": 14637
    },
    {
      "epoch": 0.4496666973858016,
      "grad_norm": 0.39632275700569153,
      "learning_rate": 1.7632032382696673e-05,
      "loss": 0.6803,
      "step": 14638
    },
    {
      "epoch": 0.4496974165207508,
      "grad_norm": 0.3501470983028412,
      "learning_rate": 1.763172010002166e-05,
      "loss": 0.6155,
      "step": 14639
    },
    {
      "epoch": 0.4497281356556999,
      "grad_norm": 0.4525614380836487,
      "learning_rate": 1.7631407799522237e-05,
      "loss": 0.5782,
      "step": 14640
    },
    {
      "epoch": 0.4497588547906491,
      "grad_norm": 0.3361092805862427,
      "learning_rate": 1.7631095481199124e-05,
      "loss": 0.5527,
      "step": 14641
    },
    {
      "epoch": 0.44978957392559826,
      "grad_norm": 0.42806243896484375,
      "learning_rate": 1.7630783145053058e-05,
      "loss": 0.5914,
      "step": 14642
    },
    {
      "epoch": 0.44982029306054744,
      "grad_norm": 0.4150003492832184,
      "learning_rate": 1.763047079108476e-05,
      "loss": 0.603,
      "step": 14643
    },
    {
      "epoch": 0.44985101219549656,
      "grad_norm": 0.364383339881897,
      "learning_rate": 1.7630158419294968e-05,
      "loss": 0.5472,
      "step": 14644
    },
    {
      "epoch": 0.44988173133044573,
      "grad_norm": 0.3281328082084656,
      "learning_rate": 1.7629846029684406e-05,
      "loss": 0.4991,
      "step": 14645
    },
    {
      "epoch": 0.4499124504653949,
      "grad_norm": 0.32557401061058044,
      "learning_rate": 1.7629533622253806e-05,
      "loss": 0.5996,
      "step": 14646
    },
    {
      "epoch": 0.44994316960034403,
      "grad_norm": 0.3677683472633362,
      "learning_rate": 1.76292211970039e-05,
      "loss": 0.605,
      "step": 14647
    },
    {
      "epoch": 0.4499738887352932,
      "grad_norm": 0.3465220332145691,
      "learning_rate": 1.7628908753935416e-05,
      "loss": 0.5707,
      "step": 14648
    },
    {
      "epoch": 0.4500046078702424,
      "grad_norm": 0.3369542062282562,
      "learning_rate": 1.7628596293049075e-05,
      "loss": 0.554,
      "step": 14649
    },
    {
      "epoch": 0.45003532700519155,
      "grad_norm": 0.3415788412094116,
      "learning_rate": 1.7628283814345623e-05,
      "loss": 0.5747,
      "step": 14650
    },
    {
      "epoch": 0.4500660461401407,
      "grad_norm": 0.5039899349212646,
      "learning_rate": 1.7627971317825778e-05,
      "loss": 0.5788,
      "step": 14651
    },
    {
      "epoch": 0.45009676527508985,
      "grad_norm": 0.4049831032752991,
      "learning_rate": 1.7627658803490272e-05,
      "loss": 0.6636,
      "step": 14652
    },
    {
      "epoch": 0.450127484410039,
      "grad_norm": 0.39964428544044495,
      "learning_rate": 1.762734627133984e-05,
      "loss": 0.5516,
      "step": 14653
    },
    {
      "epoch": 0.4501582035449882,
      "grad_norm": 0.3761940896511078,
      "learning_rate": 1.7627033721375206e-05,
      "loss": 0.5651,
      "step": 14654
    },
    {
      "epoch": 0.4501889226799373,
      "grad_norm": 0.34671202301979065,
      "learning_rate": 1.76267211535971e-05,
      "loss": 0.5619,
      "step": 14655
    },
    {
      "epoch": 0.4502196418148865,
      "grad_norm": 0.3564152717590332,
      "learning_rate": 1.7626408568006257e-05,
      "loss": 0.5361,
      "step": 14656
    },
    {
      "epoch": 0.45025036094983567,
      "grad_norm": 0.39534419775009155,
      "learning_rate": 1.7626095964603404e-05,
      "loss": 0.583,
      "step": 14657
    },
    {
      "epoch": 0.4502810800847848,
      "grad_norm": 0.34327054023742676,
      "learning_rate": 1.7625783343389268e-05,
      "loss": 0.6214,
      "step": 14658
    },
    {
      "epoch": 0.45031179921973397,
      "grad_norm": 0.34277549386024475,
      "learning_rate": 1.7625470704364586e-05,
      "loss": 0.5562,
      "step": 14659
    },
    {
      "epoch": 0.45034251835468314,
      "grad_norm": 0.43000638484954834,
      "learning_rate": 1.7625158047530085e-05,
      "loss": 0.5628,
      "step": 14660
    },
    {
      "epoch": 0.4503732374896323,
      "grad_norm": 0.46507853269577026,
      "learning_rate": 1.7624845372886493e-05,
      "loss": 0.538,
      "step": 14661
    },
    {
      "epoch": 0.45040395662458144,
      "grad_norm": 0.40938612818717957,
      "learning_rate": 1.762453268043454e-05,
      "loss": 0.5555,
      "step": 14662
    },
    {
      "epoch": 0.4504346757595306,
      "grad_norm": 0.553307831287384,
      "learning_rate": 1.762421997017496e-05,
      "loss": 0.568,
      "step": 14663
    },
    {
      "epoch": 0.4504653948944798,
      "grad_norm": 0.4095250368118286,
      "learning_rate": 1.7623907242108486e-05,
      "loss": 0.5014,
      "step": 14664
    },
    {
      "epoch": 0.4504961140294289,
      "grad_norm": 0.3502374589443207,
      "learning_rate": 1.762359449623584e-05,
      "loss": 0.5931,
      "step": 14665
    },
    {
      "epoch": 0.4505268331643781,
      "grad_norm": 0.323743999004364,
      "learning_rate": 1.7623281732557758e-05,
      "loss": 0.5804,
      "step": 14666
    },
    {
      "epoch": 0.45055755229932726,
      "grad_norm": 0.3815695643424988,
      "learning_rate": 1.762296895107497e-05,
      "loss": 0.5109,
      "step": 14667
    },
    {
      "epoch": 0.45058827143427643,
      "grad_norm": 0.32901710271835327,
      "learning_rate": 1.7622656151788202e-05,
      "loss": 0.6471,
      "step": 14668
    },
    {
      "epoch": 0.45061899056922555,
      "grad_norm": 0.39116477966308594,
      "learning_rate": 1.762234333469819e-05,
      "loss": 0.6286,
      "step": 14669
    },
    {
      "epoch": 0.45064970970417473,
      "grad_norm": 0.33530768752098083,
      "learning_rate": 1.7622030499805665e-05,
      "loss": 0.4921,
      "step": 14670
    },
    {
      "epoch": 0.4506804288391239,
      "grad_norm": 0.33936721086502075,
      "learning_rate": 1.7621717647111353e-05,
      "loss": 0.6457,
      "step": 14671
    },
    {
      "epoch": 0.450711147974073,
      "grad_norm": 0.35841304063796997,
      "learning_rate": 1.762140477661599e-05,
      "loss": 0.4566,
      "step": 14672
    },
    {
      "epoch": 0.4507418671090222,
      "grad_norm": 0.34048306941986084,
      "learning_rate": 1.76210918883203e-05,
      "loss": 0.5837,
      "step": 14673
    },
    {
      "epoch": 0.4507725862439714,
      "grad_norm": 0.3594250977039337,
      "learning_rate": 1.762077898222502e-05,
      "loss": 0.594,
      "step": 14674
    },
    {
      "epoch": 0.45080330537892055,
      "grad_norm": 0.3369969129562378,
      "learning_rate": 1.7620466058330875e-05,
      "loss": 0.5684,
      "step": 14675
    },
    {
      "epoch": 0.45083402451386967,
      "grad_norm": 0.41737985610961914,
      "learning_rate": 1.7620153116638604e-05,
      "loss": 0.646,
      "step": 14676
    },
    {
      "epoch": 0.45086474364881884,
      "grad_norm": 0.3636126220226288,
      "learning_rate": 1.761984015714893e-05,
      "loss": 0.5288,
      "step": 14677
    },
    {
      "epoch": 0.450895462783768,
      "grad_norm": 0.3746907114982605,
      "learning_rate": 1.761952717986259e-05,
      "loss": 0.5852,
      "step": 14678
    },
    {
      "epoch": 0.4509261819187172,
      "grad_norm": 0.9287598133087158,
      "learning_rate": 1.7619214184780313e-05,
      "loss": 0.602,
      "step": 14679
    },
    {
      "epoch": 0.4509569010536663,
      "grad_norm": 0.34421584010124207,
      "learning_rate": 1.7618901171902824e-05,
      "loss": 0.5444,
      "step": 14680
    },
    {
      "epoch": 0.4509876201886155,
      "grad_norm": 0.4049091637134552,
      "learning_rate": 1.761858814123086e-05,
      "loss": 0.5352,
      "step": 14681
    },
    {
      "epoch": 0.45101833932356467,
      "grad_norm": 0.3336898982524872,
      "learning_rate": 1.7618275092765156e-05,
      "loss": 0.5906,
      "step": 14682
    },
    {
      "epoch": 0.4510490584585138,
      "grad_norm": 0.3777966797351837,
      "learning_rate": 1.7617962026506435e-05,
      "loss": 0.5896,
      "step": 14683
    },
    {
      "epoch": 0.45107977759346296,
      "grad_norm": 0.35507166385650635,
      "learning_rate": 1.7617648942455434e-05,
      "loss": 0.4673,
      "step": 14684
    },
    {
      "epoch": 0.45111049672841214,
      "grad_norm": 0.39237406849861145,
      "learning_rate": 1.761733584061288e-05,
      "loss": 0.602,
      "step": 14685
    },
    {
      "epoch": 0.4511412158633613,
      "grad_norm": 0.3521982729434967,
      "learning_rate": 1.7617022720979508e-05,
      "loss": 0.5939,
      "step": 14686
    },
    {
      "epoch": 0.45117193499831043,
      "grad_norm": 0.3830109238624573,
      "learning_rate": 1.7616709583556046e-05,
      "loss": 0.5976,
      "step": 14687
    },
    {
      "epoch": 0.4512026541332596,
      "grad_norm": 0.36372435092926025,
      "learning_rate": 1.7616396428343225e-05,
      "loss": 0.4328,
      "step": 14688
    },
    {
      "epoch": 0.4512333732682088,
      "grad_norm": 0.3342306613922119,
      "learning_rate": 1.7616083255341777e-05,
      "loss": 0.58,
      "step": 14689
    },
    {
      "epoch": 0.4512640924031579,
      "grad_norm": 0.8010926842689514,
      "learning_rate": 1.761577006455244e-05,
      "loss": 0.5886,
      "step": 14690
    },
    {
      "epoch": 0.4512948115381071,
      "grad_norm": 0.3348539173603058,
      "learning_rate": 1.761545685597594e-05,
      "loss": 0.6187,
      "step": 14691
    },
    {
      "epoch": 0.45132553067305625,
      "grad_norm": 0.48828890919685364,
      "learning_rate": 1.7615143629613004e-05,
      "loss": 0.6604,
      "step": 14692
    },
    {
      "epoch": 0.4513562498080054,
      "grad_norm": 0.42751824855804443,
      "learning_rate": 1.761483038546437e-05,
      "loss": 0.5743,
      "step": 14693
    },
    {
      "epoch": 0.45138696894295455,
      "grad_norm": 0.3485841155052185,
      "learning_rate": 1.761451712353077e-05,
      "loss": 0.5388,
      "step": 14694
    },
    {
      "epoch": 0.4514176880779037,
      "grad_norm": 0.3946281969547272,
      "learning_rate": 1.761420384381293e-05,
      "loss": 0.6387,
      "step": 14695
    },
    {
      "epoch": 0.4514484072128529,
      "grad_norm": 0.35686057806015015,
      "learning_rate": 1.761389054631159e-05,
      "loss": 0.4854,
      "step": 14696
    },
    {
      "epoch": 0.4514791263478021,
      "grad_norm": 0.35842210054397583,
      "learning_rate": 1.761357723102747e-05,
      "loss": 0.4847,
      "step": 14697
    },
    {
      "epoch": 0.4515098454827512,
      "grad_norm": 0.34427908062934875,
      "learning_rate": 1.7613263897961313e-05,
      "loss": 0.5763,
      "step": 14698
    },
    {
      "epoch": 0.45154056461770037,
      "grad_norm": 0.33906134963035583,
      "learning_rate": 1.761295054711385e-05,
      "loss": 0.6735,
      "step": 14699
    },
    {
      "epoch": 0.45157128375264954,
      "grad_norm": 0.3573475778102875,
      "learning_rate": 1.7612637178485803e-05,
      "loss": 0.6079,
      "step": 14700
    },
    {
      "epoch": 0.45160200288759866,
      "grad_norm": 0.3679570257663727,
      "learning_rate": 1.761232379207791e-05,
      "loss": 0.5329,
      "step": 14701
    },
    {
      "epoch": 0.45163272202254784,
      "grad_norm": 0.3498518466949463,
      "learning_rate": 1.761201038789091e-05,
      "loss": 0.5867,
      "step": 14702
    },
    {
      "epoch": 0.451663441157497,
      "grad_norm": 0.37355297803878784,
      "learning_rate": 1.7611696965925526e-05,
      "loss": 0.595,
      "step": 14703
    },
    {
      "epoch": 0.4516941602924462,
      "grad_norm": 0.3685338497161865,
      "learning_rate": 1.7611383526182487e-05,
      "loss": 0.5552,
      "step": 14704
    },
    {
      "epoch": 0.4517248794273953,
      "grad_norm": 0.3283860683441162,
      "learning_rate": 1.7611070068662533e-05,
      "loss": 0.5421,
      "step": 14705
    },
    {
      "epoch": 0.4517555985623445,
      "grad_norm": 0.3737379014492035,
      "learning_rate": 1.7610756593366394e-05,
      "loss": 0.6216,
      "step": 14706
    },
    {
      "epoch": 0.45178631769729366,
      "grad_norm": 0.3656452000141144,
      "learning_rate": 1.76104431002948e-05,
      "loss": 0.6094,
      "step": 14707
    },
    {
      "epoch": 0.4518170368322428,
      "grad_norm": 0.3365270495414734,
      "learning_rate": 1.7610129589448485e-05,
      "loss": 0.5847,
      "step": 14708
    },
    {
      "epoch": 0.45184775596719196,
      "grad_norm": 0.470643550157547,
      "learning_rate": 1.7609816060828183e-05,
      "loss": 0.5899,
      "step": 14709
    },
    {
      "epoch": 0.45187847510214113,
      "grad_norm": 0.346583753824234,
      "learning_rate": 1.7609502514434622e-05,
      "loss": 0.5049,
      "step": 14710
    },
    {
      "epoch": 0.4519091942370903,
      "grad_norm": 0.3707916736602783,
      "learning_rate": 1.7609188950268538e-05,
      "loss": 0.5964,
      "step": 14711
    },
    {
      "epoch": 0.4519399133720394,
      "grad_norm": 0.35933446884155273,
      "learning_rate": 1.760887536833066e-05,
      "loss": 0.6334,
      "step": 14712
    },
    {
      "epoch": 0.4519706325069886,
      "grad_norm": 0.36831361055374146,
      "learning_rate": 1.7608561768621724e-05,
      "loss": 0.5583,
      "step": 14713
    },
    {
      "epoch": 0.4520013516419378,
      "grad_norm": 0.4090663492679596,
      "learning_rate": 1.760824815114246e-05,
      "loss": 0.5698,
      "step": 14714
    },
    {
      "epoch": 0.4520320707768869,
      "grad_norm": 0.4253503084182739,
      "learning_rate": 1.76079345158936e-05,
      "loss": 0.5676,
      "step": 14715
    },
    {
      "epoch": 0.45206278991183607,
      "grad_norm": 0.6666960120201111,
      "learning_rate": 1.7607620862875877e-05,
      "loss": 0.5328,
      "step": 14716
    },
    {
      "epoch": 0.45209350904678525,
      "grad_norm": 0.33213210105895996,
      "learning_rate": 1.7607307192090026e-05,
      "loss": 0.5736,
      "step": 14717
    },
    {
      "epoch": 0.4521242281817344,
      "grad_norm": 0.37527552247047424,
      "learning_rate": 1.7606993503536774e-05,
      "loss": 0.6435,
      "step": 14718
    },
    {
      "epoch": 0.45215494731668354,
      "grad_norm": 0.38226738572120667,
      "learning_rate": 1.7606679797216864e-05,
      "loss": 0.566,
      "step": 14719
    },
    {
      "epoch": 0.4521856664516327,
      "grad_norm": 0.3939184546470642,
      "learning_rate": 1.7606366073131017e-05,
      "loss": 0.5601,
      "step": 14720
    },
    {
      "epoch": 0.4522163855865819,
      "grad_norm": 0.40327689051628113,
      "learning_rate": 1.7606052331279976e-05,
      "loss": 0.573,
      "step": 14721
    },
    {
      "epoch": 0.45224710472153107,
      "grad_norm": 0.35520294308662415,
      "learning_rate": 1.7605738571664464e-05,
      "loss": 0.6318,
      "step": 14722
    },
    {
      "epoch": 0.4522778238564802,
      "grad_norm": 0.3091677725315094,
      "learning_rate": 1.760542479428522e-05,
      "loss": 0.541,
      "step": 14723
    },
    {
      "epoch": 0.45230854299142936,
      "grad_norm": 0.40154436230659485,
      "learning_rate": 1.7605110999142974e-05,
      "loss": 0.6535,
      "step": 14724
    },
    {
      "epoch": 0.45233926212637854,
      "grad_norm": 0.3543560802936554,
      "learning_rate": 1.7604797186238462e-05,
      "loss": 0.584,
      "step": 14725
    },
    {
      "epoch": 0.45236998126132766,
      "grad_norm": 0.39388057589530945,
      "learning_rate": 1.760448335557241e-05,
      "loss": 0.5411,
      "step": 14726
    },
    {
      "epoch": 0.45240070039627683,
      "grad_norm": 0.3948739469051361,
      "learning_rate": 1.7604169507145563e-05,
      "loss": 0.6182,
      "step": 14727
    },
    {
      "epoch": 0.452431419531226,
      "grad_norm": 0.39936211705207825,
      "learning_rate": 1.7603855640958643e-05,
      "loss": 0.5069,
      "step": 14728
    },
    {
      "epoch": 0.4524621386661752,
      "grad_norm": 0.3140372633934021,
      "learning_rate": 1.760354175701239e-05,
      "loss": 0.5096,
      "step": 14729
    },
    {
      "epoch": 0.4524928578011243,
      "grad_norm": 0.37498196959495544,
      "learning_rate": 1.760322785530753e-05,
      "loss": 0.5659,
      "step": 14730
    },
    {
      "epoch": 0.4525235769360735,
      "grad_norm": 0.361552894115448,
      "learning_rate": 1.7602913935844802e-05,
      "loss": 0.5645,
      "step": 14731
    },
    {
      "epoch": 0.45255429607102265,
      "grad_norm": 0.346391499042511,
      "learning_rate": 1.760259999862494e-05,
      "loss": 0.5815,
      "step": 14732
    },
    {
      "epoch": 0.4525850152059718,
      "grad_norm": 0.3138768672943115,
      "learning_rate": 1.7602286043648673e-05,
      "loss": 0.5841,
      "step": 14733
    },
    {
      "epoch": 0.45261573434092095,
      "grad_norm": 0.4010869562625885,
      "learning_rate": 1.7601972070916734e-05,
      "loss": 0.589,
      "step": 14734
    },
    {
      "epoch": 0.4526464534758701,
      "grad_norm": 0.3154456615447998,
      "learning_rate": 1.760165808042986e-05,
      "loss": 0.507,
      "step": 14735
    },
    {
      "epoch": 0.4526771726108193,
      "grad_norm": 0.3401024639606476,
      "learning_rate": 1.7601344072188783e-05,
      "loss": 0.5675,
      "step": 14736
    },
    {
      "epoch": 0.4527078917457684,
      "grad_norm": 0.36966732144355774,
      "learning_rate": 1.7601030046194238e-05,
      "loss": 0.5803,
      "step": 14737
    },
    {
      "epoch": 0.4527386108807176,
      "grad_norm": 0.4297854006290436,
      "learning_rate": 1.7600716002446952e-05,
      "loss": 0.5426,
      "step": 14738
    },
    {
      "epoch": 0.45276933001566677,
      "grad_norm": 0.35616594552993774,
      "learning_rate": 1.7600401940947665e-05,
      "loss": 0.5951,
      "step": 14739
    },
    {
      "epoch": 0.45280004915061595,
      "grad_norm": 0.3660380244255066,
      "learning_rate": 1.7600087861697113e-05,
      "loss": 0.5358,
      "step": 14740
    },
    {
      "epoch": 0.45283076828556507,
      "grad_norm": 0.353437215089798,
      "learning_rate": 1.759977376469602e-05,
      "loss": 0.5779,
      "step": 14741
    },
    {
      "epoch": 0.45286148742051424,
      "grad_norm": 0.3488626480102539,
      "learning_rate": 1.7599459649945126e-05,
      "loss": 0.5871,
      "step": 14742
    },
    {
      "epoch": 0.4528922065554634,
      "grad_norm": 0.3275333642959595,
      "learning_rate": 1.7599145517445162e-05,
      "loss": 0.5889,
      "step": 14743
    },
    {
      "epoch": 0.45292292569041254,
      "grad_norm": 0.34206753969192505,
      "learning_rate": 1.7598831367196863e-05,
      "loss": 0.6233,
      "step": 14744
    },
    {
      "epoch": 0.4529536448253617,
      "grad_norm": 0.31300365924835205,
      "learning_rate": 1.7598517199200964e-05,
      "loss": 0.5673,
      "step": 14745
    },
    {
      "epoch": 0.4529843639603109,
      "grad_norm": 0.33142104744911194,
      "learning_rate": 1.7598203013458193e-05,
      "loss": 0.5358,
      "step": 14746
    },
    {
      "epoch": 0.45301508309526006,
      "grad_norm": 0.31612086296081543,
      "learning_rate": 1.7597888809969296e-05,
      "loss": 0.486,
      "step": 14747
    },
    {
      "epoch": 0.4530458022302092,
      "grad_norm": 0.36908385157585144,
      "learning_rate": 1.7597574588734995e-05,
      "loss": 0.5313,
      "step": 14748
    },
    {
      "epoch": 0.45307652136515836,
      "grad_norm": 0.36004775762557983,
      "learning_rate": 1.7597260349756027e-05,
      "loss": 0.5428,
      "step": 14749
    },
    {
      "epoch": 0.45310724050010753,
      "grad_norm": 0.3703804910182953,
      "learning_rate": 1.759694609303313e-05,
      "loss": 0.5339,
      "step": 14750
    },
    {
      "epoch": 0.45313795963505665,
      "grad_norm": 0.39009618759155273,
      "learning_rate": 1.7596631818567028e-05,
      "loss": 0.5497,
      "step": 14751
    },
    {
      "epoch": 0.45316867877000583,
      "grad_norm": 0.35303637385368347,
      "learning_rate": 1.759631752635847e-05,
      "loss": 0.6286,
      "step": 14752
    },
    {
      "epoch": 0.453199397904955,
      "grad_norm": 0.34755733609199524,
      "learning_rate": 1.7596003216408174e-05,
      "loss": 0.6485,
      "step": 14753
    },
    {
      "epoch": 0.4532301170399042,
      "grad_norm": 0.3399241268634796,
      "learning_rate": 1.7595688888716887e-05,
      "loss": 0.532,
      "step": 14754
    },
    {
      "epoch": 0.4532608361748533,
      "grad_norm": 0.36805614829063416,
      "learning_rate": 1.759537454328534e-05,
      "loss": 0.6116,
      "step": 14755
    },
    {
      "epoch": 0.4532915553098025,
      "grad_norm": 0.34877872467041016,
      "learning_rate": 1.7595060180114262e-05,
      "loss": 0.5789,
      "step": 14756
    },
    {
      "epoch": 0.45332227444475165,
      "grad_norm": 0.33930259943008423,
      "learning_rate": 1.759474579920439e-05,
      "loss": 0.5195,
      "step": 14757
    },
    {
      "epoch": 0.45335299357970077,
      "grad_norm": 0.48760148882865906,
      "learning_rate": 1.7594431400556463e-05,
      "loss": 0.5917,
      "step": 14758
    },
    {
      "epoch": 0.45338371271464994,
      "grad_norm": 0.3429584503173828,
      "learning_rate": 1.759411698417121e-05,
      "loss": 0.5629,
      "step": 14759
    },
    {
      "epoch": 0.4534144318495991,
      "grad_norm": 0.36942026019096375,
      "learning_rate": 1.7593802550049362e-05,
      "loss": 0.5722,
      "step": 14760
    },
    {
      "epoch": 0.4534451509845483,
      "grad_norm": 0.356810986995697,
      "learning_rate": 1.7593488098191658e-05,
      "loss": 0.6008,
      "step": 14761
    },
    {
      "epoch": 0.4534758701194974,
      "grad_norm": 0.30681416392326355,
      "learning_rate": 1.7593173628598833e-05,
      "loss": 0.5444,
      "step": 14762
    },
    {
      "epoch": 0.4535065892544466,
      "grad_norm": 0.38577985763549805,
      "learning_rate": 1.7592859141271624e-05,
      "loss": 0.529,
      "step": 14763
    },
    {
      "epoch": 0.45353730838939577,
      "grad_norm": 0.37435266375541687,
      "learning_rate": 1.759254463621076e-05,
      "loss": 0.5455,
      "step": 14764
    },
    {
      "epoch": 0.45356802752434494,
      "grad_norm": 0.33314743638038635,
      "learning_rate": 1.759223011341698e-05,
      "loss": 0.5857,
      "step": 14765
    },
    {
      "epoch": 0.45359874665929406,
      "grad_norm": 0.32554998993873596,
      "learning_rate": 1.7591915572891013e-05,
      "loss": 0.5701,
      "step": 14766
    },
    {
      "epoch": 0.45362946579424324,
      "grad_norm": 0.3387303054332733,
      "learning_rate": 1.75916010146336e-05,
      "loss": 0.5834,
      "step": 14767
    },
    {
      "epoch": 0.4536601849291924,
      "grad_norm": 0.36572393774986267,
      "learning_rate": 1.7591286438645472e-05,
      "loss": 0.5689,
      "step": 14768
    },
    {
      "epoch": 0.45369090406414153,
      "grad_norm": 0.3605833649635315,
      "learning_rate": 1.759097184492736e-05,
      "loss": 0.6464,
      "step": 14769
    },
    {
      "epoch": 0.4537216231990907,
      "grad_norm": 0.34780094027519226,
      "learning_rate": 1.7590657233480007e-05,
      "loss": 0.6044,
      "step": 14770
    },
    {
      "epoch": 0.4537523423340399,
      "grad_norm": 0.364944726228714,
      "learning_rate": 1.7590342604304145e-05,
      "loss": 0.6232,
      "step": 14771
    },
    {
      "epoch": 0.45378306146898906,
      "grad_norm": 0.3233402371406555,
      "learning_rate": 1.7590027957400507e-05,
      "loss": 0.5588,
      "step": 14772
    },
    {
      "epoch": 0.4538137806039382,
      "grad_norm": 0.32655465602874756,
      "learning_rate": 1.7589713292769827e-05,
      "loss": 0.4942,
      "step": 14773
    },
    {
      "epoch": 0.45384449973888735,
      "grad_norm": 0.36105531454086304,
      "learning_rate": 1.7589398610412846e-05,
      "loss": 0.5474,
      "step": 14774
    },
    {
      "epoch": 0.45387521887383653,
      "grad_norm": 0.3568357527256012,
      "learning_rate": 1.7589083910330287e-05,
      "loss": 0.5741,
      "step": 14775
    },
    {
      "epoch": 0.45390593800878565,
      "grad_norm": 0.36982589960098267,
      "learning_rate": 1.75887691925229e-05,
      "loss": 0.4824,
      "step": 14776
    },
    {
      "epoch": 0.4539366571437348,
      "grad_norm": 0.33987388014793396,
      "learning_rate": 1.7588454456991406e-05,
      "loss": 0.5823,
      "step": 14777
    },
    {
      "epoch": 0.453967376278684,
      "grad_norm": 0.6266050338745117,
      "learning_rate": 1.758813970373655e-05,
      "loss": 0.4933,
      "step": 14778
    },
    {
      "epoch": 0.4539980954136332,
      "grad_norm": 0.3435169756412506,
      "learning_rate": 1.758782493275906e-05,
      "loss": 0.5577,
      "step": 14779
    },
    {
      "epoch": 0.4540288145485823,
      "grad_norm": 0.3395032286643982,
      "learning_rate": 1.7587510144059682e-05,
      "loss": 0.6532,
      "step": 14780
    },
    {
      "epoch": 0.45405953368353147,
      "grad_norm": 0.368660569190979,
      "learning_rate": 1.758719533763914e-05,
      "loss": 0.5385,
      "step": 14781
    },
    {
      "epoch": 0.45409025281848064,
      "grad_norm": 0.5005515217781067,
      "learning_rate": 1.7586880513498174e-05,
      "loss": 0.4494,
      "step": 14782
    },
    {
      "epoch": 0.45412097195342976,
      "grad_norm": 0.39519476890563965,
      "learning_rate": 1.758656567163752e-05,
      "loss": 0.64,
      "step": 14783
    },
    {
      "epoch": 0.45415169108837894,
      "grad_norm": 0.34761038422584534,
      "learning_rate": 1.758625081205791e-05,
      "loss": 0.6484,
      "step": 14784
    },
    {
      "epoch": 0.4541824102233281,
      "grad_norm": 0.3295415937900543,
      "learning_rate": 1.758593593476008e-05,
      "loss": 0.6081,
      "step": 14785
    },
    {
      "epoch": 0.4542131293582773,
      "grad_norm": 0.35725101828575134,
      "learning_rate": 1.7585621039744772e-05,
      "loss": 0.5848,
      "step": 14786
    },
    {
      "epoch": 0.4542438484932264,
      "grad_norm": 0.3419910669326782,
      "learning_rate": 1.758530612701271e-05,
      "loss": 0.6219,
      "step": 14787
    },
    {
      "epoch": 0.4542745676281756,
      "grad_norm": 0.7743199467658997,
      "learning_rate": 1.758499119656464e-05,
      "loss": 0.5589,
      "step": 14788
    },
    {
      "epoch": 0.45430528676312476,
      "grad_norm": 0.3317103981971741,
      "learning_rate": 1.758467624840129e-05,
      "loss": 0.598,
      "step": 14789
    },
    {
      "epoch": 0.45433600589807394,
      "grad_norm": 0.3548225462436676,
      "learning_rate": 1.7584361282523405e-05,
      "loss": 0.5315,
      "step": 14790
    },
    {
      "epoch": 0.45436672503302306,
      "grad_norm": 0.30635207891464233,
      "learning_rate": 1.758404629893171e-05,
      "loss": 0.5058,
      "step": 14791
    },
    {
      "epoch": 0.45439744416797223,
      "grad_norm": 0.3996305763721466,
      "learning_rate": 1.7583731297626944e-05,
      "loss": 0.5754,
      "step": 14792
    },
    {
      "epoch": 0.4544281633029214,
      "grad_norm": 0.33714714646339417,
      "learning_rate": 1.7583416278609847e-05,
      "loss": 0.5332,
      "step": 14793
    },
    {
      "epoch": 0.4544588824378705,
      "grad_norm": 0.33379510045051575,
      "learning_rate": 1.758310124188115e-05,
      "loss": 0.5678,
      "step": 14794
    },
    {
      "epoch": 0.4544896015728197,
      "grad_norm": 0.4315635859966278,
      "learning_rate": 1.758278618744159e-05,
      "loss": 0.5427,
      "step": 14795
    },
    {
      "epoch": 0.4545203207077689,
      "grad_norm": 0.36857613921165466,
      "learning_rate": 1.7582471115291905e-05,
      "loss": 0.6229,
      "step": 14796
    },
    {
      "epoch": 0.45455103984271805,
      "grad_norm": 0.3525790572166443,
      "learning_rate": 1.7582156025432827e-05,
      "loss": 0.6351,
      "step": 14797
    },
    {
      "epoch": 0.45458175897766717,
      "grad_norm": 0.3383762836456299,
      "learning_rate": 1.7581840917865096e-05,
      "loss": 0.6126,
      "step": 14798
    },
    {
      "epoch": 0.45461247811261635,
      "grad_norm": 0.3619092106819153,
      "learning_rate": 1.7581525792589447e-05,
      "loss": 0.5603,
      "step": 14799
    },
    {
      "epoch": 0.4546431972475655,
      "grad_norm": 0.3275085985660553,
      "learning_rate": 1.7581210649606614e-05,
      "loss": 0.5719,
      "step": 14800
    },
    {
      "epoch": 0.45467391638251464,
      "grad_norm": 0.3604305684566498,
      "learning_rate": 1.7580895488917334e-05,
      "loss": 0.6195,
      "step": 14801
    },
    {
      "epoch": 0.4547046355174638,
      "grad_norm": 0.3329273760318756,
      "learning_rate": 1.758058031052234e-05,
      "loss": 0.5715,
      "step": 14802
    },
    {
      "epoch": 0.454735354652413,
      "grad_norm": 0.40876078605651855,
      "learning_rate": 1.7580265114422377e-05,
      "loss": 0.5808,
      "step": 14803
    },
    {
      "epoch": 0.45476607378736217,
      "grad_norm": 0.3279174268245697,
      "learning_rate": 1.757994990061817e-05,
      "loss": 0.5513,
      "step": 14804
    },
    {
      "epoch": 0.4547967929223113,
      "grad_norm": 0.4939618408679962,
      "learning_rate": 1.7579634669110465e-05,
      "loss": 0.4538,
      "step": 14805
    },
    {
      "epoch": 0.45482751205726046,
      "grad_norm": 0.3662663400173187,
      "learning_rate": 1.757931941989999e-05,
      "loss": 0.5512,
      "step": 14806
    },
    {
      "epoch": 0.45485823119220964,
      "grad_norm": 0.3453003466129303,
      "learning_rate": 1.7579004152987486e-05,
      "loss": 0.5102,
      "step": 14807
    },
    {
      "epoch": 0.4548889503271588,
      "grad_norm": 0.3408786952495575,
      "learning_rate": 1.7578688868373694e-05,
      "loss": 0.6323,
      "step": 14808
    },
    {
      "epoch": 0.45491966946210793,
      "grad_norm": 0.40161749720573425,
      "learning_rate": 1.7578373566059336e-05,
      "loss": 0.6289,
      "step": 14809
    },
    {
      "epoch": 0.4549503885970571,
      "grad_norm": 0.3815045952796936,
      "learning_rate": 1.7578058246045164e-05,
      "loss": 0.6258,
      "step": 14810
    },
    {
      "epoch": 0.4549811077320063,
      "grad_norm": 0.3351389765739441,
      "learning_rate": 1.7577742908331906e-05,
      "loss": 0.4604,
      "step": 14811
    },
    {
      "epoch": 0.4550118268669554,
      "grad_norm": 0.37020763754844666,
      "learning_rate": 1.75774275529203e-05,
      "loss": 0.5461,
      "step": 14812
    },
    {
      "epoch": 0.4550425460019046,
      "grad_norm": 0.3447721302509308,
      "learning_rate": 1.757711217981108e-05,
      "loss": 0.5591,
      "step": 14813
    },
    {
      "epoch": 0.45507326513685376,
      "grad_norm": 0.45211368799209595,
      "learning_rate": 1.757679678900499e-05,
      "loss": 0.6562,
      "step": 14814
    },
    {
      "epoch": 0.45510398427180293,
      "grad_norm": 0.32899636030197144,
      "learning_rate": 1.757648138050276e-05,
      "loss": 0.5418,
      "step": 14815
    },
    {
      "epoch": 0.45513470340675205,
      "grad_norm": 0.35579565167427063,
      "learning_rate": 1.7576165954305127e-05,
      "loss": 0.5667,
      "step": 14816
    },
    {
      "epoch": 0.4551654225417012,
      "grad_norm": 0.39517873525619507,
      "learning_rate": 1.757585051041283e-05,
      "loss": 0.5706,
      "step": 14817
    },
    {
      "epoch": 0.4551961416766504,
      "grad_norm": 0.33052220940589905,
      "learning_rate": 1.7575535048826605e-05,
      "loss": 0.5376,
      "step": 14818
    },
    {
      "epoch": 0.4552268608115995,
      "grad_norm": 0.3311185836791992,
      "learning_rate": 1.757521956954719e-05,
      "loss": 0.5643,
      "step": 14819
    },
    {
      "epoch": 0.4552575799465487,
      "grad_norm": 0.39226725697517395,
      "learning_rate": 1.7574904072575322e-05,
      "loss": 0.5786,
      "step": 14820
    },
    {
      "epoch": 0.45528829908149787,
      "grad_norm": 0.3479754328727722,
      "learning_rate": 1.7574588557911732e-05,
      "loss": 0.593,
      "step": 14821
    },
    {
      "epoch": 0.45531901821644705,
      "grad_norm": 0.32683905959129333,
      "learning_rate": 1.7574273025557164e-05,
      "loss": 0.5539,
      "step": 14822
    },
    {
      "epoch": 0.45534973735139617,
      "grad_norm": 0.3613910377025604,
      "learning_rate": 1.7573957475512354e-05,
      "loss": 0.5281,
      "step": 14823
    },
    {
      "epoch": 0.45538045648634534,
      "grad_norm": 0.33554190397262573,
      "learning_rate": 1.7573641907778033e-05,
      "loss": 0.5942,
      "step": 14824
    },
    {
      "epoch": 0.4554111756212945,
      "grad_norm": 0.3428145945072174,
      "learning_rate": 1.7573326322354947e-05,
      "loss": 0.5757,
      "step": 14825
    },
    {
      "epoch": 0.45544189475624364,
      "grad_norm": 0.3339780867099762,
      "learning_rate": 1.7573010719243827e-05,
      "loss": 0.5269,
      "step": 14826
    },
    {
      "epoch": 0.4554726138911928,
      "grad_norm": 0.3802330195903778,
      "learning_rate": 1.757269509844541e-05,
      "loss": 0.5683,
      "step": 14827
    },
    {
      "epoch": 0.455503333026142,
      "grad_norm": 0.34515050053596497,
      "learning_rate": 1.757237945996044e-05,
      "loss": 0.5556,
      "step": 14828
    },
    {
      "epoch": 0.45553405216109116,
      "grad_norm": 0.35292544960975647,
      "learning_rate": 1.757206380378964e-05,
      "loss": 0.5606,
      "step": 14829
    },
    {
      "epoch": 0.4555647712960403,
      "grad_norm": 0.34009286761283875,
      "learning_rate": 1.7571748129933764e-05,
      "loss": 0.5568,
      "step": 14830
    },
    {
      "epoch": 0.45559549043098946,
      "grad_norm": 0.40338024497032166,
      "learning_rate": 1.7571432438393537e-05,
      "loss": 0.5823,
      "step": 14831
    },
    {
      "epoch": 0.45562620956593863,
      "grad_norm": 0.3686307966709137,
      "learning_rate": 1.75711167291697e-05,
      "loss": 0.567,
      "step": 14832
    },
    {
      "epoch": 0.4556569287008878,
      "grad_norm": 0.3606644868850708,
      "learning_rate": 1.7570801002262995e-05,
      "loss": 0.6015,
      "step": 14833
    },
    {
      "epoch": 0.45568764783583693,
      "grad_norm": 0.42062658071517944,
      "learning_rate": 1.757048525767415e-05,
      "loss": 0.6453,
      "step": 14834
    },
    {
      "epoch": 0.4557183669707861,
      "grad_norm": 0.3746088147163391,
      "learning_rate": 1.7570169495403914e-05,
      "loss": 0.5045,
      "step": 14835
    },
    {
      "epoch": 0.4557490861057353,
      "grad_norm": 0.3008498251438141,
      "learning_rate": 1.7569853715453017e-05,
      "loss": 0.5022,
      "step": 14836
    },
    {
      "epoch": 0.4557798052406844,
      "grad_norm": 0.3292538821697235,
      "learning_rate": 1.7569537917822197e-05,
      "loss": 0.5356,
      "step": 14837
    },
    {
      "epoch": 0.4558105243756336,
      "grad_norm": 0.33369964361190796,
      "learning_rate": 1.7569222102512194e-05,
      "loss": 0.5758,
      "step": 14838
    },
    {
      "epoch": 0.45584124351058275,
      "grad_norm": 0.3226816952228546,
      "learning_rate": 1.7568906269523743e-05,
      "loss": 0.5592,
      "step": 14839
    },
    {
      "epoch": 0.4558719626455319,
      "grad_norm": 0.35098299384117126,
      "learning_rate": 1.756859041885758e-05,
      "loss": 0.5322,
      "step": 14840
    },
    {
      "epoch": 0.45590268178048104,
      "grad_norm": 0.3510268032550812,
      "learning_rate": 1.756827455051445e-05,
      "loss": 0.5734,
      "step": 14841
    },
    {
      "epoch": 0.4559334009154302,
      "grad_norm": 0.3882661759853363,
      "learning_rate": 1.7567958664495088e-05,
      "loss": 0.5497,
      "step": 14842
    },
    {
      "epoch": 0.4559641200503794,
      "grad_norm": 0.394694447517395,
      "learning_rate": 1.7567642760800222e-05,
      "loss": 0.67,
      "step": 14843
    },
    {
      "epoch": 0.4559948391853285,
      "grad_norm": 0.33559751510620117,
      "learning_rate": 1.7567326839430604e-05,
      "loss": 0.6244,
      "step": 14844
    },
    {
      "epoch": 0.4560255583202777,
      "grad_norm": 0.3713327646255493,
      "learning_rate": 1.7567010900386963e-05,
      "loss": 0.5745,
      "step": 14845
    },
    {
      "epoch": 0.45605627745522687,
      "grad_norm": 0.3466780185699463,
      "learning_rate": 1.756669494367004e-05,
      "loss": 0.5849,
      "step": 14846
    },
    {
      "epoch": 0.45608699659017604,
      "grad_norm": 0.3614327907562256,
      "learning_rate": 1.7566378969280572e-05,
      "loss": 0.6031,
      "step": 14847
    },
    {
      "epoch": 0.45611771572512516,
      "grad_norm": 0.331123024225235,
      "learning_rate": 1.75660629772193e-05,
      "loss": 0.561,
      "step": 14848
    },
    {
      "epoch": 0.45614843486007434,
      "grad_norm": 0.3737928867340088,
      "learning_rate": 1.7565746967486958e-05,
      "loss": 0.6026,
      "step": 14849
    },
    {
      "epoch": 0.4561791539950235,
      "grad_norm": 0.3417396545410156,
      "learning_rate": 1.7565430940084285e-05,
      "loss": 0.5618,
      "step": 14850
    },
    {
      "epoch": 0.4562098731299727,
      "grad_norm": 0.3488541841506958,
      "learning_rate": 1.756511489501202e-05,
      "loss": 0.567,
      "step": 14851
    },
    {
      "epoch": 0.4562405922649218,
      "grad_norm": 0.3534490168094635,
      "learning_rate": 1.75647988322709e-05,
      "loss": 0.5846,
      "step": 14852
    },
    {
      "epoch": 0.456271311399871,
      "grad_norm": 0.320895254611969,
      "learning_rate": 1.7564482751861665e-05,
      "loss": 0.579,
      "step": 14853
    },
    {
      "epoch": 0.45630203053482016,
      "grad_norm": 0.37051814794540405,
      "learning_rate": 1.7564166653785054e-05,
      "loss": 0.554,
      "step": 14854
    },
    {
      "epoch": 0.4563327496697693,
      "grad_norm": 0.37271347641944885,
      "learning_rate": 1.7563850538041802e-05,
      "loss": 0.5825,
      "step": 14855
    },
    {
      "epoch": 0.45636346880471845,
      "grad_norm": 0.3426390588283539,
      "learning_rate": 1.756353440463265e-05,
      "loss": 0.5516,
      "step": 14856
    },
    {
      "epoch": 0.45639418793966763,
      "grad_norm": 0.3523322343826294,
      "learning_rate": 1.756321825355833e-05,
      "loss": 0.6199,
      "step": 14857
    },
    {
      "epoch": 0.4564249070746168,
      "grad_norm": 0.3579956591129303,
      "learning_rate": 1.7562902084819592e-05,
      "loss": 0.6005,
      "step": 14858
    },
    {
      "epoch": 0.4564556262095659,
      "grad_norm": 0.33915185928344727,
      "learning_rate": 1.7562585898417163e-05,
      "loss": 0.5016,
      "step": 14859
    },
    {
      "epoch": 0.4564863453445151,
      "grad_norm": 0.4568637013435364,
      "learning_rate": 1.756226969435179e-05,
      "loss": 0.5837,
      "step": 14860
    },
    {
      "epoch": 0.4565170644794643,
      "grad_norm": 0.3499954044818878,
      "learning_rate": 1.756195347262421e-05,
      "loss": 0.5244,
      "step": 14861
    },
    {
      "epoch": 0.4565477836144134,
      "grad_norm": 0.3435781002044678,
      "learning_rate": 1.7561637233235153e-05,
      "loss": 0.561,
      "step": 14862
    },
    {
      "epoch": 0.45657850274936257,
      "grad_norm": 0.3518495559692383,
      "learning_rate": 1.756132097618537e-05,
      "loss": 0.6242,
      "step": 14863
    },
    {
      "epoch": 0.45660922188431174,
      "grad_norm": 0.32434141635894775,
      "learning_rate": 1.7561004701475588e-05,
      "loss": 0.5147,
      "step": 14864
    },
    {
      "epoch": 0.4566399410192609,
      "grad_norm": 0.3508748412132263,
      "learning_rate": 1.7560688409106556e-05,
      "loss": 0.6141,
      "step": 14865
    },
    {
      "epoch": 0.45667066015421004,
      "grad_norm": 0.33934295177459717,
      "learning_rate": 1.7560372099079005e-05,
      "loss": 0.5306,
      "step": 14866
    },
    {
      "epoch": 0.4567013792891592,
      "grad_norm": 0.34875357151031494,
      "learning_rate": 1.756005577139368e-05,
      "loss": 0.5648,
      "step": 14867
    },
    {
      "epoch": 0.4567320984241084,
      "grad_norm": 0.35613417625427246,
      "learning_rate": 1.7559739426051315e-05,
      "loss": 0.4906,
      "step": 14868
    },
    {
      "epoch": 0.4567628175590575,
      "grad_norm": 0.44192421436309814,
      "learning_rate": 1.755942306305265e-05,
      "loss": 0.549,
      "step": 14869
    },
    {
      "epoch": 0.4567935366940067,
      "grad_norm": 0.43918323516845703,
      "learning_rate": 1.755910668239843e-05,
      "loss": 0.5201,
      "step": 14870
    },
    {
      "epoch": 0.45682425582895586,
      "grad_norm": 0.6091206073760986,
      "learning_rate": 1.7558790284089383e-05,
      "loss": 0.5686,
      "step": 14871
    },
    {
      "epoch": 0.45685497496390504,
      "grad_norm": 0.36402517557144165,
      "learning_rate": 1.7558473868126254e-05,
      "loss": 0.5314,
      "step": 14872
    },
    {
      "epoch": 0.45688569409885416,
      "grad_norm": 0.35422322154045105,
      "learning_rate": 1.755815743450978e-05,
      "loss": 0.5273,
      "step": 14873
    },
    {
      "epoch": 0.45691641323380333,
      "grad_norm": 0.34074053168296814,
      "learning_rate": 1.7557840983240703e-05,
      "loss": 0.5345,
      "step": 14874
    },
    {
      "epoch": 0.4569471323687525,
      "grad_norm": 0.3740515112876892,
      "learning_rate": 1.7557524514319762e-05,
      "loss": 0.6278,
      "step": 14875
    },
    {
      "epoch": 0.4569778515037017,
      "grad_norm": 0.6121364831924438,
      "learning_rate": 1.7557208027747692e-05,
      "loss": 0.5265,
      "step": 14876
    },
    {
      "epoch": 0.4570085706386508,
      "grad_norm": 0.3226225674152374,
      "learning_rate": 1.755689152352524e-05,
      "loss": 0.6067,
      "step": 14877
    },
    {
      "epoch": 0.4570392897736,
      "grad_norm": 0.323478639125824,
      "learning_rate": 1.7556575001653136e-05,
      "loss": 0.5323,
      "step": 14878
    },
    {
      "epoch": 0.45707000890854915,
      "grad_norm": 0.3535043001174927,
      "learning_rate": 1.7556258462132125e-05,
      "loss": 0.6066,
      "step": 14879
    },
    {
      "epoch": 0.4571007280434983,
      "grad_norm": 0.32660573720932007,
      "learning_rate": 1.755594190496294e-05,
      "loss": 0.5383,
      "step": 14880
    },
    {
      "epoch": 0.45713144717844745,
      "grad_norm": 0.3388632833957672,
      "learning_rate": 1.7555625330146328e-05,
      "loss": 0.7079,
      "step": 14881
    },
    {
      "epoch": 0.4571621663133966,
      "grad_norm": 0.3633915185928345,
      "learning_rate": 1.7555308737683026e-05,
      "loss": 0.5709,
      "step": 14882
    },
    {
      "epoch": 0.4571928854483458,
      "grad_norm": 0.3545389771461487,
      "learning_rate": 1.7554992127573772e-05,
      "loss": 0.6435,
      "step": 14883
    },
    {
      "epoch": 0.4572236045832949,
      "grad_norm": 0.3471790850162506,
      "learning_rate": 1.7554675499819307e-05,
      "loss": 0.589,
      "step": 14884
    },
    {
      "epoch": 0.4572543237182441,
      "grad_norm": 0.37680748105049133,
      "learning_rate": 1.755435885442037e-05,
      "loss": 0.5615,
      "step": 14885
    },
    {
      "epoch": 0.45728504285319327,
      "grad_norm": 0.35151341557502747,
      "learning_rate": 1.7554042191377702e-05,
      "loss": 0.6009,
      "step": 14886
    },
    {
      "epoch": 0.4573157619881424,
      "grad_norm": 0.35122454166412354,
      "learning_rate": 1.7553725510692037e-05,
      "loss": 0.5911,
      "step": 14887
    },
    {
      "epoch": 0.45734648112309156,
      "grad_norm": 0.3701283931732178,
      "learning_rate": 1.755340881236412e-05,
      "loss": 0.6167,
      "step": 14888
    },
    {
      "epoch": 0.45737720025804074,
      "grad_norm": 0.42722538113594055,
      "learning_rate": 1.7553092096394692e-05,
      "loss": 0.5699,
      "step": 14889
    },
    {
      "epoch": 0.4574079193929899,
      "grad_norm": 0.45421740412712097,
      "learning_rate": 1.7552775362784486e-05,
      "loss": 0.5998,
      "step": 14890
    },
    {
      "epoch": 0.45743863852793903,
      "grad_norm": 0.5588492155075073,
      "learning_rate": 1.7552458611534247e-05,
      "loss": 0.6178,
      "step": 14891
    },
    {
      "epoch": 0.4574693576628882,
      "grad_norm": 0.5668898224830627,
      "learning_rate": 1.7552141842644713e-05,
      "loss": 0.5635,
      "step": 14892
    },
    {
      "epoch": 0.4575000767978374,
      "grad_norm": 0.37723931670188904,
      "learning_rate": 1.7551825056116626e-05,
      "loss": 0.5893,
      "step": 14893
    },
    {
      "epoch": 0.45753079593278656,
      "grad_norm": 0.37540265917778015,
      "learning_rate": 1.7551508251950724e-05,
      "loss": 0.5535,
      "step": 14894
    },
    {
      "epoch": 0.4575615150677357,
      "grad_norm": 0.334349125623703,
      "learning_rate": 1.7551191430147746e-05,
      "loss": 0.5615,
      "step": 14895
    },
    {
      "epoch": 0.45759223420268486,
      "grad_norm": 0.35603782534599304,
      "learning_rate": 1.755087459070843e-05,
      "loss": 0.6242,
      "step": 14896
    },
    {
      "epoch": 0.45762295333763403,
      "grad_norm": 0.3564946949481964,
      "learning_rate": 1.7550557733633525e-05,
      "loss": 0.6469,
      "step": 14897
    },
    {
      "epoch": 0.45765367247258315,
      "grad_norm": 0.3363029360771179,
      "learning_rate": 1.755024085892376e-05,
      "loss": 0.5711,
      "step": 14898
    },
    {
      "epoch": 0.4576843916075323,
      "grad_norm": 0.37370792031288147,
      "learning_rate": 1.7549923966579883e-05,
      "loss": 0.5756,
      "step": 14899
    },
    {
      "epoch": 0.4577151107424815,
      "grad_norm": 0.4230613708496094,
      "learning_rate": 1.7549607056602632e-05,
      "loss": 0.5749,
      "step": 14900
    },
    {
      "epoch": 0.4577458298774307,
      "grad_norm": 0.30758658051490784,
      "learning_rate": 1.7549290128992744e-05,
      "loss": 0.5068,
      "step": 14901
    },
    {
      "epoch": 0.4577765490123798,
      "grad_norm": 0.32288849353790283,
      "learning_rate": 1.7548973183750964e-05,
      "loss": 0.5122,
      "step": 14902
    },
    {
      "epoch": 0.45780726814732897,
      "grad_norm": 0.34583914279937744,
      "learning_rate": 1.754865622087803e-05,
      "loss": 0.5887,
      "step": 14903
    },
    {
      "epoch": 0.45783798728227815,
      "grad_norm": 0.3827151358127594,
      "learning_rate": 1.7548339240374682e-05,
      "loss": 0.5925,
      "step": 14904
    },
    {
      "epoch": 0.45786870641722727,
      "grad_norm": 0.32615333795547485,
      "learning_rate": 1.7548022242241657e-05,
      "loss": 0.5622,
      "step": 14905
    },
    {
      "epoch": 0.45789942555217644,
      "grad_norm": 0.4096027612686157,
      "learning_rate": 1.7547705226479702e-05,
      "loss": 0.5535,
      "step": 14906
    },
    {
      "epoch": 0.4579301446871256,
      "grad_norm": 0.33866146206855774,
      "learning_rate": 1.754738819308955e-05,
      "loss": 0.5368,
      "step": 14907
    },
    {
      "epoch": 0.4579608638220748,
      "grad_norm": 0.3856838345527649,
      "learning_rate": 1.7547071142071953e-05,
      "loss": 0.6375,
      "step": 14908
    },
    {
      "epoch": 0.4579915829570239,
      "grad_norm": 0.334995836019516,
      "learning_rate": 1.754675407342764e-05,
      "loss": 0.5137,
      "step": 14909
    },
    {
      "epoch": 0.4580223020919731,
      "grad_norm": 0.5355144143104553,
      "learning_rate": 1.7546436987157357e-05,
      "loss": 0.5362,
      "step": 14910
    },
    {
      "epoch": 0.45805302122692226,
      "grad_norm": 0.3374653458595276,
      "learning_rate": 1.7546119883261844e-05,
      "loss": 0.5874,
      "step": 14911
    },
    {
      "epoch": 0.4580837403618714,
      "grad_norm": 0.38145512342453003,
      "learning_rate": 1.7545802761741838e-05,
      "loss": 0.6004,
      "step": 14912
    },
    {
      "epoch": 0.45811445949682056,
      "grad_norm": 0.3533911108970642,
      "learning_rate": 1.7545485622598085e-05,
      "loss": 0.6404,
      "step": 14913
    },
    {
      "epoch": 0.45814517863176973,
      "grad_norm": 0.3750940263271332,
      "learning_rate": 1.7545168465831324e-05,
      "loss": 0.539,
      "step": 14914
    },
    {
      "epoch": 0.4581758977667189,
      "grad_norm": 0.37020593881607056,
      "learning_rate": 1.7544851291442297e-05,
      "loss": 0.5717,
      "step": 14915
    },
    {
      "epoch": 0.45820661690166803,
      "grad_norm": 0.31016111373901367,
      "learning_rate": 1.7544534099431735e-05,
      "loss": 0.5788,
      "step": 14916
    },
    {
      "epoch": 0.4582373360366172,
      "grad_norm": 0.3931322693824768,
      "learning_rate": 1.7544216889800394e-05,
      "loss": 0.6035,
      "step": 14917
    },
    {
      "epoch": 0.4582680551715664,
      "grad_norm": 0.33466702699661255,
      "learning_rate": 1.7543899662549006e-05,
      "loss": 0.5676,
      "step": 14918
    },
    {
      "epoch": 0.45829877430651556,
      "grad_norm": 0.3280591368675232,
      "learning_rate": 1.7543582417678313e-05,
      "loss": 0.5407,
      "step": 14919
    },
    {
      "epoch": 0.4583294934414647,
      "grad_norm": 0.3598901033401489,
      "learning_rate": 1.7543265155189053e-05,
      "loss": 0.6052,
      "step": 14920
    },
    {
      "epoch": 0.45836021257641385,
      "grad_norm": 0.3527345061302185,
      "learning_rate": 1.7542947875081975e-05,
      "loss": 0.662,
      "step": 14921
    },
    {
      "epoch": 0.458390931711363,
      "grad_norm": 0.41162171959877014,
      "learning_rate": 1.7542630577357815e-05,
      "loss": 0.6154,
      "step": 14922
    },
    {
      "epoch": 0.45842165084631215,
      "grad_norm": 0.3654109239578247,
      "learning_rate": 1.7542313262017315e-05,
      "loss": 0.4905,
      "step": 14923
    },
    {
      "epoch": 0.4584523699812613,
      "grad_norm": 0.5760310292243958,
      "learning_rate": 1.7541995929061212e-05,
      "loss": 0.6116,
      "step": 14924
    },
    {
      "epoch": 0.4584830891162105,
      "grad_norm": 0.36771395802497864,
      "learning_rate": 1.7541678578490253e-05,
      "loss": 0.6434,
      "step": 14925
    },
    {
      "epoch": 0.45851380825115967,
      "grad_norm": 0.36297619342803955,
      "learning_rate": 1.7541361210305177e-05,
      "loss": 0.5816,
      "step": 14926
    },
    {
      "epoch": 0.4585445273861088,
      "grad_norm": 0.347223162651062,
      "learning_rate": 1.7541043824506724e-05,
      "loss": 0.5967,
      "step": 14927
    },
    {
      "epoch": 0.45857524652105797,
      "grad_norm": 0.3490247130393982,
      "learning_rate": 1.7540726421095637e-05,
      "loss": 0.6237,
      "step": 14928
    },
    {
      "epoch": 0.45860596565600714,
      "grad_norm": 0.3637227416038513,
      "learning_rate": 1.754040900007266e-05,
      "loss": 0.5485,
      "step": 14929
    },
    {
      "epoch": 0.45863668479095626,
      "grad_norm": 0.3685954213142395,
      "learning_rate": 1.7540091561438527e-05,
      "loss": 0.5714,
      "step": 14930
    },
    {
      "epoch": 0.45866740392590544,
      "grad_norm": 0.34634625911712646,
      "learning_rate": 1.7539774105193984e-05,
      "loss": 0.5468,
      "step": 14931
    },
    {
      "epoch": 0.4586981230608546,
      "grad_norm": 0.3964401185512543,
      "learning_rate": 1.7539456631339775e-05,
      "loss": 0.5354,
      "step": 14932
    },
    {
      "epoch": 0.4587288421958038,
      "grad_norm": 1.3535985946655273,
      "learning_rate": 1.753913913987664e-05,
      "loss": 0.5269,
      "step": 14933
    },
    {
      "epoch": 0.4587595613307529,
      "grad_norm": 0.3245680630207062,
      "learning_rate": 1.7538821630805314e-05,
      "loss": 0.5721,
      "step": 14934
    },
    {
      "epoch": 0.4587902804657021,
      "grad_norm": 0.3759658932685852,
      "learning_rate": 1.7538504104126542e-05,
      "loss": 0.5471,
      "step": 14935
    },
    {
      "epoch": 0.45882099960065126,
      "grad_norm": 0.4034577012062073,
      "learning_rate": 1.753818655984107e-05,
      "loss": 0.6558,
      "step": 14936
    },
    {
      "epoch": 0.4588517187356004,
      "grad_norm": 0.32194286584854126,
      "learning_rate": 1.7537868997949637e-05,
      "loss": 0.4624,
      "step": 14937
    },
    {
      "epoch": 0.45888243787054955,
      "grad_norm": 0.3612785339355469,
      "learning_rate": 1.7537551418452987e-05,
      "loss": 0.5782,
      "step": 14938
    },
    {
      "epoch": 0.45891315700549873,
      "grad_norm": 0.3218516409397125,
      "learning_rate": 1.753723382135186e-05,
      "loss": 0.5331,
      "step": 14939
    },
    {
      "epoch": 0.4589438761404479,
      "grad_norm": 0.363787442445755,
      "learning_rate": 1.753691620664699e-05,
      "loss": 0.5032,
      "step": 14940
    },
    {
      "epoch": 0.458974595275397,
      "grad_norm": 0.3287619948387146,
      "learning_rate": 1.7536598574339132e-05,
      "loss": 0.561,
      "step": 14941
    },
    {
      "epoch": 0.4590053144103462,
      "grad_norm": 0.3187781274318695,
      "learning_rate": 1.753628092442902e-05,
      "loss": 0.5481,
      "step": 14942
    },
    {
      "epoch": 0.4590360335452954,
      "grad_norm": 0.4004264771938324,
      "learning_rate": 1.7535963256917393e-05,
      "loss": 0.635,
      "step": 14943
    },
    {
      "epoch": 0.45906675268024455,
      "grad_norm": 0.43304935097694397,
      "learning_rate": 1.7535645571805005e-05,
      "loss": 0.5569,
      "step": 14944
    },
    {
      "epoch": 0.45909747181519367,
      "grad_norm": 0.36263129115104675,
      "learning_rate": 1.7535327869092587e-05,
      "loss": 0.6444,
      "step": 14945
    },
    {
      "epoch": 0.45912819095014284,
      "grad_norm": 0.3390050232410431,
      "learning_rate": 1.753501014878088e-05,
      "loss": 0.6889,
      "step": 14946
    },
    {
      "epoch": 0.459158910085092,
      "grad_norm": 0.31136438250541687,
      "learning_rate": 1.7534692410870636e-05,
      "loss": 0.6272,
      "step": 14947
    },
    {
      "epoch": 0.45918962922004114,
      "grad_norm": 0.32567089796066284,
      "learning_rate": 1.7534374655362593e-05,
      "loss": 0.5816,
      "step": 14948
    },
    {
      "epoch": 0.4592203483549903,
      "grad_norm": 0.39119428396224976,
      "learning_rate": 1.7534056882257492e-05,
      "loss": 0.5947,
      "step": 14949
    },
    {
      "epoch": 0.4592510674899395,
      "grad_norm": 0.3525576591491699,
      "learning_rate": 1.7533739091556074e-05,
      "loss": 0.6033,
      "step": 14950
    },
    {
      "epoch": 0.45928178662488867,
      "grad_norm": 0.35392841696739197,
      "learning_rate": 1.7533421283259078e-05,
      "loss": 0.5157,
      "step": 14951
    },
    {
      "epoch": 0.4593125057598378,
      "grad_norm": 0.3410913050174713,
      "learning_rate": 1.7533103457367252e-05,
      "loss": 0.5943,
      "step": 14952
    },
    {
      "epoch": 0.45934322489478696,
      "grad_norm": 0.3890867233276367,
      "learning_rate": 1.7532785613881336e-05,
      "loss": 0.5841,
      "step": 14953
    },
    {
      "epoch": 0.45937394402973614,
      "grad_norm": 0.3270435333251953,
      "learning_rate": 1.753246775280208e-05,
      "loss": 0.5219,
      "step": 14954
    },
    {
      "epoch": 0.45940466316468526,
      "grad_norm": 0.3465689718723297,
      "learning_rate": 1.753214987413021e-05,
      "loss": 0.559,
      "step": 14955
    },
    {
      "epoch": 0.45943538229963443,
      "grad_norm": 0.34675613045692444,
      "learning_rate": 1.7531831977866485e-05,
      "loss": 0.5828,
      "step": 14956
    },
    {
      "epoch": 0.4594661014345836,
      "grad_norm": 0.33259934186935425,
      "learning_rate": 1.753151406401164e-05,
      "loss": 0.5814,
      "step": 14957
    },
    {
      "epoch": 0.4594968205695328,
      "grad_norm": 0.3885191082954407,
      "learning_rate": 1.7531196132566414e-05,
      "loss": 0.6061,
      "step": 14958
    },
    {
      "epoch": 0.4595275397044819,
      "grad_norm": 0.3273746371269226,
      "learning_rate": 1.7530878183531553e-05,
      "loss": 0.5998,
      "step": 14959
    },
    {
      "epoch": 0.4595582588394311,
      "grad_norm": 0.4218716025352478,
      "learning_rate": 1.7530560216907806e-05,
      "loss": 0.5709,
      "step": 14960
    },
    {
      "epoch": 0.45958897797438025,
      "grad_norm": 0.33008357882499695,
      "learning_rate": 1.7530242232695904e-05,
      "loss": 0.4888,
      "step": 14961
    },
    {
      "epoch": 0.45961969710932943,
      "grad_norm": 0.35682862997055054,
      "learning_rate": 1.75299242308966e-05,
      "loss": 0.5728,
      "step": 14962
    },
    {
      "epoch": 0.45965041624427855,
      "grad_norm": 0.34896549582481384,
      "learning_rate": 1.7529606211510627e-05,
      "loss": 0.57,
      "step": 14963
    },
    {
      "epoch": 0.4596811353792277,
      "grad_norm": 0.6465823650360107,
      "learning_rate": 1.7529288174538734e-05,
      "loss": 0.6176,
      "step": 14964
    },
    {
      "epoch": 0.4597118545141769,
      "grad_norm": 0.37932538986206055,
      "learning_rate": 1.7528970119981664e-05,
      "loss": 0.6198,
      "step": 14965
    },
    {
      "epoch": 0.459742573649126,
      "grad_norm": 0.3673594295978546,
      "learning_rate": 1.752865204784016e-05,
      "loss": 0.5377,
      "step": 14966
    },
    {
      "epoch": 0.4597732927840752,
      "grad_norm": 0.35222306847572327,
      "learning_rate": 1.7528333958114962e-05,
      "loss": 0.532,
      "step": 14967
    },
    {
      "epoch": 0.45980401191902437,
      "grad_norm": 0.4675556719303131,
      "learning_rate": 1.7528015850806818e-05,
      "loss": 0.4967,
      "step": 14968
    },
    {
      "epoch": 0.45983473105397354,
      "grad_norm": 0.3285087049007416,
      "learning_rate": 1.7527697725916462e-05,
      "loss": 0.5379,
      "step": 14969
    },
    {
      "epoch": 0.45986545018892266,
      "grad_norm": 0.3432493209838867,
      "learning_rate": 1.7527379583444643e-05,
      "loss": 0.5832,
      "step": 14970
    },
    {
      "epoch": 0.45989616932387184,
      "grad_norm": 0.3686516582965851,
      "learning_rate": 1.7527061423392102e-05,
      "loss": 0.5489,
      "step": 14971
    },
    {
      "epoch": 0.459926888458821,
      "grad_norm": 0.3398393988609314,
      "learning_rate": 1.7526743245759586e-05,
      "loss": 0.5415,
      "step": 14972
    },
    {
      "epoch": 0.45995760759377013,
      "grad_norm": 0.3922847509384155,
      "learning_rate": 1.7526425050547833e-05,
      "loss": 0.6031,
      "step": 14973
    },
    {
      "epoch": 0.4599883267287193,
      "grad_norm": 0.3710283637046814,
      "learning_rate": 1.7526106837757592e-05,
      "loss": 0.5965,
      "step": 14974
    },
    {
      "epoch": 0.4600190458636685,
      "grad_norm": 0.42710816860198975,
      "learning_rate": 1.75257886073896e-05,
      "loss": 0.5612,
      "step": 14975
    },
    {
      "epoch": 0.46004976499861766,
      "grad_norm": 0.3521771728992462,
      "learning_rate": 1.7525470359444606e-05,
      "loss": 0.5708,
      "step": 14976
    },
    {
      "epoch": 0.4600804841335668,
      "grad_norm": 0.3011832535266876,
      "learning_rate": 1.7525152093923348e-05,
      "loss": 0.52,
      "step": 14977
    },
    {
      "epoch": 0.46011120326851596,
      "grad_norm": 0.3888145685195923,
      "learning_rate": 1.7524833810826574e-05,
      "loss": 0.5614,
      "step": 14978
    },
    {
      "epoch": 0.46014192240346513,
      "grad_norm": 0.362020879983902,
      "learning_rate": 1.752451551015502e-05,
      "loss": 0.5802,
      "step": 14979
    },
    {
      "epoch": 0.46017264153841425,
      "grad_norm": 0.3551254868507385,
      "learning_rate": 1.752419719190944e-05,
      "loss": 0.6016,
      "step": 14980
    },
    {
      "epoch": 0.4602033606733634,
      "grad_norm": 0.4265778958797455,
      "learning_rate": 1.7523878856090572e-05,
      "loss": 0.5478,
      "step": 14981
    },
    {
      "epoch": 0.4602340798083126,
      "grad_norm": 1.3012709617614746,
      "learning_rate": 1.7523560502699153e-05,
      "loss": 0.5658,
      "step": 14982
    },
    {
      "epoch": 0.4602647989432618,
      "grad_norm": 0.4265270233154297,
      "learning_rate": 1.7523242131735938e-05,
      "loss": 0.678,
      "step": 14983
    },
    {
      "epoch": 0.4602955180782109,
      "grad_norm": 0.4003060460090637,
      "learning_rate": 1.7522923743201667e-05,
      "loss": 0.4192,
      "step": 14984
    },
    {
      "epoch": 0.46032623721316007,
      "grad_norm": 0.3987058699131012,
      "learning_rate": 1.7522605337097078e-05,
      "loss": 0.5728,
      "step": 14985
    },
    {
      "epoch": 0.46035695634810925,
      "grad_norm": 0.38765034079551697,
      "learning_rate": 1.7522286913422924e-05,
      "loss": 0.5066,
      "step": 14986
    },
    {
      "epoch": 0.4603876754830584,
      "grad_norm": 0.39925310015678406,
      "learning_rate": 1.752196847217994e-05,
      "loss": 0.5065,
      "step": 14987
    },
    {
      "epoch": 0.46041839461800754,
      "grad_norm": 0.3321259319782257,
      "learning_rate": 1.7521650013368875e-05,
      "loss": 0.5677,
      "step": 14988
    },
    {
      "epoch": 0.4604491137529567,
      "grad_norm": 0.4296007454395294,
      "learning_rate": 1.7521331536990468e-05,
      "loss": 0.5136,
      "step": 14989
    },
    {
      "epoch": 0.4604798328879059,
      "grad_norm": 0.3290773630142212,
      "learning_rate": 1.752101304304547e-05,
      "loss": 0.5882,
      "step": 14990
    },
    {
      "epoch": 0.460510552022855,
      "grad_norm": 0.3107479214668274,
      "learning_rate": 1.7520694531534618e-05,
      "loss": 0.4692,
      "step": 14991
    },
    {
      "epoch": 0.4605412711578042,
      "grad_norm": 0.33969900012016296,
      "learning_rate": 1.752037600245866e-05,
      "loss": 0.5355,
      "step": 14992
    },
    {
      "epoch": 0.46057199029275336,
      "grad_norm": 0.3866717517375946,
      "learning_rate": 1.7520057455818337e-05,
      "loss": 0.5334,
      "step": 14993
    },
    {
      "epoch": 0.46060270942770254,
      "grad_norm": 0.3429889678955078,
      "learning_rate": 1.7519738891614397e-05,
      "loss": 0.651,
      "step": 14994
    },
    {
      "epoch": 0.46063342856265166,
      "grad_norm": 0.3592424988746643,
      "learning_rate": 1.7519420309847578e-05,
      "loss": 0.5188,
      "step": 14995
    },
    {
      "epoch": 0.46066414769760083,
      "grad_norm": 0.3526012599468231,
      "learning_rate": 1.751910171051863e-05,
      "loss": 0.5125,
      "step": 14996
    },
    {
      "epoch": 0.46069486683255,
      "grad_norm": 0.3529806435108185,
      "learning_rate": 1.7518783093628297e-05,
      "loss": 0.6407,
      "step": 14997
    },
    {
      "epoch": 0.46072558596749913,
      "grad_norm": 0.3347106873989105,
      "learning_rate": 1.7518464459177316e-05,
      "loss": 0.5496,
      "step": 14998
    },
    {
      "epoch": 0.4607563051024483,
      "grad_norm": 0.3469483554363251,
      "learning_rate": 1.751814580716644e-05,
      "loss": 0.5195,
      "step": 14999
    },
    {
      "epoch": 0.4607870242373975,
      "grad_norm": 0.3423756957054138,
      "learning_rate": 1.7517827137596407e-05,
      "loss": 0.5799,
      "step": 15000
    },
    {
      "epoch": 0.46081774337234666,
      "grad_norm": 0.3763512969017029,
      "learning_rate": 1.7517508450467966e-05,
      "loss": 0.5622,
      "step": 15001
    },
    {
      "epoch": 0.4608484625072958,
      "grad_norm": 0.3555516004562378,
      "learning_rate": 1.751718974578186e-05,
      "loss": 0.4256,
      "step": 15002
    },
    {
      "epoch": 0.46087918164224495,
      "grad_norm": 0.33605489134788513,
      "learning_rate": 1.751687102353883e-05,
      "loss": 0.4706,
      "step": 15003
    },
    {
      "epoch": 0.4609099007771941,
      "grad_norm": 0.3154623210430145,
      "learning_rate": 1.751655228373962e-05,
      "loss": 0.587,
      "step": 15004
    },
    {
      "epoch": 0.4609406199121433,
      "grad_norm": 0.33751019835472107,
      "learning_rate": 1.7516233526384983e-05,
      "loss": 0.5623,
      "step": 15005
    },
    {
      "epoch": 0.4609713390470924,
      "grad_norm": 0.39987844228744507,
      "learning_rate": 1.7515914751475655e-05,
      "loss": 0.6252,
      "step": 15006
    },
    {
      "epoch": 0.4610020581820416,
      "grad_norm": 0.34484097361564636,
      "learning_rate": 1.7515595959012385e-05,
      "loss": 0.6,
      "step": 15007
    },
    {
      "epoch": 0.46103277731699077,
      "grad_norm": 0.33656638860702515,
      "learning_rate": 1.7515277148995913e-05,
      "loss": 0.5846,
      "step": 15008
    },
    {
      "epoch": 0.4610634964519399,
      "grad_norm": 0.3522637188434601,
      "learning_rate": 1.7514958321426987e-05,
      "loss": 0.579,
      "step": 15009
    },
    {
      "epoch": 0.46109421558688907,
      "grad_norm": 0.3216972053050995,
      "learning_rate": 1.7514639476306352e-05,
      "loss": 0.6024,
      "step": 15010
    },
    {
      "epoch": 0.46112493472183824,
      "grad_norm": 0.44168075919151306,
      "learning_rate": 1.751432061363475e-05,
      "loss": 0.5436,
      "step": 15011
    },
    {
      "epoch": 0.4611556538567874,
      "grad_norm": 0.3661257326602936,
      "learning_rate": 1.751400173341293e-05,
      "loss": 0.5597,
      "step": 15012
    },
    {
      "epoch": 0.46118637299173654,
      "grad_norm": 0.35021716356277466,
      "learning_rate": 1.7513682835641634e-05,
      "loss": 0.5738,
      "step": 15013
    },
    {
      "epoch": 0.4612170921266857,
      "grad_norm": 0.3283958435058594,
      "learning_rate": 1.7513363920321605e-05,
      "loss": 0.4848,
      "step": 15014
    },
    {
      "epoch": 0.4612478112616349,
      "grad_norm": 0.3549174666404724,
      "learning_rate": 1.751304498745359e-05,
      "loss": 0.5874,
      "step": 15015
    },
    {
      "epoch": 0.461278530396584,
      "grad_norm": 0.31910598278045654,
      "learning_rate": 1.7512726037038335e-05,
      "loss": 0.5498,
      "step": 15016
    },
    {
      "epoch": 0.4613092495315332,
      "grad_norm": 0.328264981508255,
      "learning_rate": 1.751240706907658e-05,
      "loss": 0.5718,
      "step": 15017
    },
    {
      "epoch": 0.46133996866648236,
      "grad_norm": 0.3728581964969635,
      "learning_rate": 1.751208808356908e-05,
      "loss": 0.5135,
      "step": 15018
    },
    {
      "epoch": 0.46137068780143153,
      "grad_norm": 0.3672035336494446,
      "learning_rate": 1.7511769080516566e-05,
      "loss": 0.5397,
      "step": 15019
    },
    {
      "epoch": 0.46140140693638065,
      "grad_norm": 0.36930862069129944,
      "learning_rate": 1.75114500599198e-05,
      "loss": 0.5635,
      "step": 15020
    },
    {
      "epoch": 0.46143212607132983,
      "grad_norm": 0.4263584613800049,
      "learning_rate": 1.7511131021779508e-05,
      "loss": 0.5529,
      "step": 15021
    },
    {
      "epoch": 0.461462845206279,
      "grad_norm": 0.40738645195961,
      "learning_rate": 1.7510811966096454e-05,
      "loss": 0.5871,
      "step": 15022
    },
    {
      "epoch": 0.4614935643412281,
      "grad_norm": 0.32516762614250183,
      "learning_rate": 1.7510492892871368e-05,
      "loss": 0.5884,
      "step": 15023
    },
    {
      "epoch": 0.4615242834761773,
      "grad_norm": 0.3572433590888977,
      "learning_rate": 1.7510173802105002e-05,
      "loss": 0.5987,
      "step": 15024
    },
    {
      "epoch": 0.4615550026111265,
      "grad_norm": 0.3289932310581207,
      "learning_rate": 1.75098546937981e-05,
      "loss": 0.5942,
      "step": 15025
    },
    {
      "epoch": 0.46158572174607565,
      "grad_norm": 0.3523715138435364,
      "learning_rate": 1.7509535567951412e-05,
      "loss": 0.5079,
      "step": 15026
    },
    {
      "epoch": 0.46161644088102477,
      "grad_norm": 0.3423430919647217,
      "learning_rate": 1.7509216424565675e-05,
      "loss": 0.5953,
      "step": 15027
    },
    {
      "epoch": 0.46164716001597395,
      "grad_norm": 0.3147362470626831,
      "learning_rate": 1.750889726364164e-05,
      "loss": 0.6107,
      "step": 15028
    },
    {
      "epoch": 0.4616778791509231,
      "grad_norm": 0.3728281259536743,
      "learning_rate": 1.7508578085180053e-05,
      "loss": 0.5692,
      "step": 15029
    },
    {
      "epoch": 0.4617085982858723,
      "grad_norm": 0.3653053939342499,
      "learning_rate": 1.7508258889181654e-05,
      "loss": 0.6088,
      "step": 15030
    },
    {
      "epoch": 0.4617393174208214,
      "grad_norm": 0.4072294533252716,
      "learning_rate": 1.7507939675647193e-05,
      "loss": 0.5832,
      "step": 15031
    },
    {
      "epoch": 0.4617700365557706,
      "grad_norm": 0.3860301673412323,
      "learning_rate": 1.750762044457742e-05,
      "loss": 0.4962,
      "step": 15032
    },
    {
      "epoch": 0.46180075569071977,
      "grad_norm": 0.35495525598526,
      "learning_rate": 1.7507301195973067e-05,
      "loss": 0.5423,
      "step": 15033
    },
    {
      "epoch": 0.4618314748256689,
      "grad_norm": 0.31472501158714294,
      "learning_rate": 1.7506981929834892e-05,
      "loss": 0.5926,
      "step": 15034
    },
    {
      "epoch": 0.46186219396061806,
      "grad_norm": 0.35317564010620117,
      "learning_rate": 1.7506662646163633e-05,
      "loss": 0.5524,
      "step": 15035
    },
    {
      "epoch": 0.46189291309556724,
      "grad_norm": 0.3853405714035034,
      "learning_rate": 1.7506343344960042e-05,
      "loss": 0.6111,
      "step": 15036
    },
    {
      "epoch": 0.4619236322305164,
      "grad_norm": 0.43699702620506287,
      "learning_rate": 1.7506024026224862e-05,
      "loss": 0.5828,
      "step": 15037
    },
    {
      "epoch": 0.46195435136546553,
      "grad_norm": 0.3564210534095764,
      "learning_rate": 1.750570468995884e-05,
      "loss": 0.5776,
      "step": 15038
    },
    {
      "epoch": 0.4619850705004147,
      "grad_norm": 0.3246304392814636,
      "learning_rate": 1.750538533616272e-05,
      "loss": 0.4745,
      "step": 15039
    },
    {
      "epoch": 0.4620157896353639,
      "grad_norm": 0.4104432463645935,
      "learning_rate": 1.7505065964837246e-05,
      "loss": 0.6043,
      "step": 15040
    },
    {
      "epoch": 0.462046508770313,
      "grad_norm": 0.37187686562538147,
      "learning_rate": 1.7504746575983168e-05,
      "loss": 0.5863,
      "step": 15041
    },
    {
      "epoch": 0.4620772279052622,
      "grad_norm": 0.40208783745765686,
      "learning_rate": 1.750442716960123e-05,
      "loss": 0.5953,
      "step": 15042
    },
    {
      "epoch": 0.46210794704021135,
      "grad_norm": 0.393187552690506,
      "learning_rate": 1.7504107745692177e-05,
      "loss": 0.5493,
      "step": 15043
    },
    {
      "epoch": 0.46213866617516053,
      "grad_norm": 0.34870779514312744,
      "learning_rate": 1.750378830425676e-05,
      "loss": 0.6438,
      "step": 15044
    },
    {
      "epoch": 0.46216938531010965,
      "grad_norm": 0.35420823097229004,
      "learning_rate": 1.750346884529572e-05,
      "loss": 0.5098,
      "step": 15045
    },
    {
      "epoch": 0.4622001044450588,
      "grad_norm": 0.36294931173324585,
      "learning_rate": 1.75031493688098e-05,
      "loss": 0.5864,
      "step": 15046
    },
    {
      "epoch": 0.462230823580008,
      "grad_norm": 0.3392777442932129,
      "learning_rate": 1.7502829874799755e-05,
      "loss": 0.5106,
      "step": 15047
    },
    {
      "epoch": 0.4622615427149572,
      "grad_norm": 0.3675919771194458,
      "learning_rate": 1.7502510363266327e-05,
      "loss": 0.6076,
      "step": 15048
    },
    {
      "epoch": 0.4622922618499063,
      "grad_norm": 0.3371598720550537,
      "learning_rate": 1.7502190834210257e-05,
      "loss": 0.6014,
      "step": 15049
    },
    {
      "epoch": 0.46232298098485547,
      "grad_norm": 0.34554463624954224,
      "learning_rate": 1.75018712876323e-05,
      "loss": 0.5316,
      "step": 15050
    },
    {
      "epoch": 0.46235370011980464,
      "grad_norm": 0.38676148653030396,
      "learning_rate": 1.75015517235332e-05,
      "loss": 0.5589,
      "step": 15051
    },
    {
      "epoch": 0.46238441925475376,
      "grad_norm": 0.35091301798820496,
      "learning_rate": 1.75012321419137e-05,
      "loss": 0.572,
      "step": 15052
    },
    {
      "epoch": 0.46241513838970294,
      "grad_norm": 0.35504066944122314,
      "learning_rate": 1.7500912542774552e-05,
      "loss": 0.6727,
      "step": 15053
    },
    {
      "epoch": 0.4624458575246521,
      "grad_norm": 0.32074254751205444,
      "learning_rate": 1.7500592926116495e-05,
      "loss": 0.5949,
      "step": 15054
    },
    {
      "epoch": 0.4624765766596013,
      "grad_norm": 0.3243458867073059,
      "learning_rate": 1.750027329194028e-05,
      "loss": 0.5358,
      "step": 15055
    },
    {
      "epoch": 0.4625072957945504,
      "grad_norm": 0.36217111349105835,
      "learning_rate": 1.749995364024665e-05,
      "loss": 0.5549,
      "step": 15056
    },
    {
      "epoch": 0.4625380149294996,
      "grad_norm": 0.35141074657440186,
      "learning_rate": 1.749963397103636e-05,
      "loss": 0.6285,
      "step": 15057
    },
    {
      "epoch": 0.46256873406444876,
      "grad_norm": 0.34706398844718933,
      "learning_rate": 1.7499314284310148e-05,
      "loss": 0.5816,
      "step": 15058
    },
    {
      "epoch": 0.4625994531993979,
      "grad_norm": 0.3664652109146118,
      "learning_rate": 1.7498994580068765e-05,
      "loss": 0.5482,
      "step": 15059
    },
    {
      "epoch": 0.46263017233434706,
      "grad_norm": 0.3815475106239319,
      "learning_rate": 1.7498674858312957e-05,
      "loss": 0.5974,
      "step": 15060
    },
    {
      "epoch": 0.46266089146929623,
      "grad_norm": 0.35861366987228394,
      "learning_rate": 1.749835511904347e-05,
      "loss": 0.6207,
      "step": 15061
    },
    {
      "epoch": 0.4626916106042454,
      "grad_norm": 0.516350269317627,
      "learning_rate": 1.749803536226105e-05,
      "loss": 0.5951,
      "step": 15062
    },
    {
      "epoch": 0.4627223297391945,
      "grad_norm": 0.3613710403442383,
      "learning_rate": 1.7497715587966444e-05,
      "loss": 0.6417,
      "step": 15063
    },
    {
      "epoch": 0.4627530488741437,
      "grad_norm": 0.40708261728286743,
      "learning_rate": 1.7497395796160402e-05,
      "loss": 0.6,
      "step": 15064
    },
    {
      "epoch": 0.4627837680090929,
      "grad_norm": 0.39028021693229675,
      "learning_rate": 1.7497075986843667e-05,
      "loss": 0.5655,
      "step": 15065
    },
    {
      "epoch": 0.462814487144042,
      "grad_norm": 0.37652525305747986,
      "learning_rate": 1.7496756160016987e-05,
      "loss": 0.6009,
      "step": 15066
    },
    {
      "epoch": 0.4628452062789912,
      "grad_norm": 0.3639780282974243,
      "learning_rate": 1.7496436315681108e-05,
      "loss": 0.5678,
      "step": 15067
    },
    {
      "epoch": 0.46287592541394035,
      "grad_norm": 0.3541998267173767,
      "learning_rate": 1.749611645383678e-05,
      "loss": 0.5582,
      "step": 15068
    },
    {
      "epoch": 0.4629066445488895,
      "grad_norm": 0.40462344884872437,
      "learning_rate": 1.749579657448475e-05,
      "loss": 0.5663,
      "step": 15069
    },
    {
      "epoch": 0.46293736368383864,
      "grad_norm": 0.3566315472126007,
      "learning_rate": 1.749547667762576e-05,
      "loss": 0.5003,
      "step": 15070
    },
    {
      "epoch": 0.4629680828187878,
      "grad_norm": 0.34842565655708313,
      "learning_rate": 1.7495156763260567e-05,
      "loss": 0.5908,
      "step": 15071
    },
    {
      "epoch": 0.462998801953737,
      "grad_norm": 0.3843683898448944,
      "learning_rate": 1.7494836831389908e-05,
      "loss": 0.5468,
      "step": 15072
    },
    {
      "epoch": 0.46302952108868617,
      "grad_norm": 0.38187551498413086,
      "learning_rate": 1.7494516882014534e-05,
      "loss": 0.5245,
      "step": 15073
    },
    {
      "epoch": 0.4630602402236353,
      "grad_norm": 0.36740607023239136,
      "learning_rate": 1.7494196915135194e-05,
      "loss": 0.5823,
      "step": 15074
    },
    {
      "epoch": 0.46309095935858446,
      "grad_norm": 0.32930728793144226,
      "learning_rate": 1.749387693075263e-05,
      "loss": 0.5777,
      "step": 15075
    },
    {
      "epoch": 0.46312167849353364,
      "grad_norm": 0.3276188373565674,
      "learning_rate": 1.7493556928867597e-05,
      "loss": 0.5752,
      "step": 15076
    },
    {
      "epoch": 0.46315239762848276,
      "grad_norm": 0.35650742053985596,
      "learning_rate": 1.7493236909480836e-05,
      "loss": 0.5487,
      "step": 15077
    },
    {
      "epoch": 0.46318311676343193,
      "grad_norm": 0.6112621426582336,
      "learning_rate": 1.74929168725931e-05,
      "loss": 0.575,
      "step": 15078
    },
    {
      "epoch": 0.4632138358983811,
      "grad_norm": 0.33477744460105896,
      "learning_rate": 1.749259681820513e-05,
      "loss": 0.4576,
      "step": 15079
    },
    {
      "epoch": 0.4632445550333303,
      "grad_norm": 0.35465744137763977,
      "learning_rate": 1.7492276746317677e-05,
      "loss": 0.5286,
      "step": 15080
    },
    {
      "epoch": 0.4632752741682794,
      "grad_norm": 0.449050635099411,
      "learning_rate": 1.749195665693149e-05,
      "loss": 0.6035,
      "step": 15081
    },
    {
      "epoch": 0.4633059933032286,
      "grad_norm": 0.3368692696094513,
      "learning_rate": 1.7491636550047315e-05,
      "loss": 0.4526,
      "step": 15082
    },
    {
      "epoch": 0.46333671243817776,
      "grad_norm": 0.3351900279521942,
      "learning_rate": 1.7491316425665898e-05,
      "loss": 0.5761,
      "step": 15083
    },
    {
      "epoch": 0.4633674315731269,
      "grad_norm": 0.34053584933280945,
      "learning_rate": 1.7490996283787992e-05,
      "loss": 0.5836,
      "step": 15084
    },
    {
      "epoch": 0.46339815070807605,
      "grad_norm": 0.4583267569541931,
      "learning_rate": 1.7490676124414337e-05,
      "loss": 0.6679,
      "step": 15085
    },
    {
      "epoch": 0.4634288698430252,
      "grad_norm": 0.34589558839797974,
      "learning_rate": 1.7490355947545686e-05,
      "loss": 0.6653,
      "step": 15086
    },
    {
      "epoch": 0.4634595889779744,
      "grad_norm": 0.37623822689056396,
      "learning_rate": 1.7490035753182787e-05,
      "loss": 0.5978,
      "step": 15087
    },
    {
      "epoch": 0.4634903081129235,
      "grad_norm": 0.3566945791244507,
      "learning_rate": 1.748971554132638e-05,
      "loss": 0.5583,
      "step": 15088
    },
    {
      "epoch": 0.4635210272478727,
      "grad_norm": 0.3129368722438812,
      "learning_rate": 1.748939531197723e-05,
      "loss": 0.5496,
      "step": 15089
    },
    {
      "epoch": 0.46355174638282187,
      "grad_norm": 0.37627917528152466,
      "learning_rate": 1.7489075065136068e-05,
      "loss": 0.517,
      "step": 15090
    },
    {
      "epoch": 0.463582465517771,
      "grad_norm": 0.4804825484752655,
      "learning_rate": 1.7488754800803646e-05,
      "loss": 0.5651,
      "step": 15091
    },
    {
      "epoch": 0.46361318465272017,
      "grad_norm": 0.35902753472328186,
      "learning_rate": 1.748843451898072e-05,
      "loss": 0.5889,
      "step": 15092
    },
    {
      "epoch": 0.46364390378766934,
      "grad_norm": 0.33882755041122437,
      "learning_rate": 1.7488114219668028e-05,
      "loss": 0.5341,
      "step": 15093
    },
    {
      "epoch": 0.4636746229226185,
      "grad_norm": 0.3482252061367035,
      "learning_rate": 1.7487793902866323e-05,
      "loss": 0.5646,
      "step": 15094
    },
    {
      "epoch": 0.46370534205756764,
      "grad_norm": 0.3154295086860657,
      "learning_rate": 1.7487473568576352e-05,
      "loss": 0.5565,
      "step": 15095
    },
    {
      "epoch": 0.4637360611925168,
      "grad_norm": 0.3413528800010681,
      "learning_rate": 1.7487153216798864e-05,
      "loss": 0.523,
      "step": 15096
    },
    {
      "epoch": 0.463766780327466,
      "grad_norm": 0.35352572798728943,
      "learning_rate": 1.748683284753461e-05,
      "loss": 0.5779,
      "step": 15097
    },
    {
      "epoch": 0.46379749946241516,
      "grad_norm": 0.32871922850608826,
      "learning_rate": 1.748651246078433e-05,
      "loss": 0.5846,
      "step": 15098
    },
    {
      "epoch": 0.4638282185973643,
      "grad_norm": 0.36766594648361206,
      "learning_rate": 1.7486192056548777e-05,
      "loss": 0.5511,
      "step": 15099
    },
    {
      "epoch": 0.46385893773231346,
      "grad_norm": 0.3402208983898163,
      "learning_rate": 1.7485871634828702e-05,
      "loss": 0.5607,
      "step": 15100
    },
    {
      "epoch": 0.46388965686726263,
      "grad_norm": 0.3490822911262512,
      "learning_rate": 1.7485551195624855e-05,
      "loss": 0.5323,
      "step": 15101
    },
    {
      "epoch": 0.46392037600221175,
      "grad_norm": 0.37798061966896057,
      "learning_rate": 1.7485230738937976e-05,
      "loss": 0.6239,
      "step": 15102
    },
    {
      "epoch": 0.46395109513716093,
      "grad_norm": 0.3951759338378906,
      "learning_rate": 1.7484910264768818e-05,
      "loss": 0.5648,
      "step": 15103
    },
    {
      "epoch": 0.4639818142721101,
      "grad_norm": 0.37493181228637695,
      "learning_rate": 1.7484589773118127e-05,
      "loss": 0.6052,
      "step": 15104
    },
    {
      "epoch": 0.4640125334070593,
      "grad_norm": 0.39984196424484253,
      "learning_rate": 1.7484269263986657e-05,
      "loss": 0.4754,
      "step": 15105
    },
    {
      "epoch": 0.4640432525420084,
      "grad_norm": 0.6800329685211182,
      "learning_rate": 1.7483948737375152e-05,
      "loss": 0.545,
      "step": 15106
    },
    {
      "epoch": 0.4640739716769576,
      "grad_norm": 0.32180270552635193,
      "learning_rate": 1.7483628193284367e-05,
      "loss": 0.5699,
      "step": 15107
    },
    {
      "epoch": 0.46410469081190675,
      "grad_norm": 0.3560450077056885,
      "learning_rate": 1.748330763171504e-05,
      "loss": 0.6114,
      "step": 15108
    },
    {
      "epoch": 0.46413540994685587,
      "grad_norm": 0.3579772114753723,
      "learning_rate": 1.748298705266793e-05,
      "loss": 0.5937,
      "step": 15109
    },
    {
      "epoch": 0.46416612908180505,
      "grad_norm": 0.3183712661266327,
      "learning_rate": 1.7482666456143774e-05,
      "loss": 0.5608,
      "step": 15110
    },
    {
      "epoch": 0.4641968482167542,
      "grad_norm": 0.3678797781467438,
      "learning_rate": 1.748234584214333e-05,
      "loss": 0.5926,
      "step": 15111
    },
    {
      "epoch": 0.4642275673517034,
      "grad_norm": 0.33418789505958557,
      "learning_rate": 1.7482025210667348e-05,
      "loss": 0.6211,
      "step": 15112
    },
    {
      "epoch": 0.4642582864866525,
      "grad_norm": 0.3380526304244995,
      "learning_rate": 1.7481704561716574e-05,
      "loss": 0.5834,
      "step": 15113
    },
    {
      "epoch": 0.4642890056216017,
      "grad_norm": 0.36274921894073486,
      "learning_rate": 1.7481383895291753e-05,
      "loss": 0.6581,
      "step": 15114
    },
    {
      "epoch": 0.46431972475655087,
      "grad_norm": 0.3203476667404175,
      "learning_rate": 1.748106321139364e-05,
      "loss": 0.4972,
      "step": 15115
    },
    {
      "epoch": 0.46435044389150004,
      "grad_norm": 0.3548239469528198,
      "learning_rate": 1.748074251002298e-05,
      "loss": 0.5914,
      "step": 15116
    },
    {
      "epoch": 0.46438116302644916,
      "grad_norm": 0.3879430592060089,
      "learning_rate": 1.7480421791180527e-05,
      "loss": 0.5576,
      "step": 15117
    },
    {
      "epoch": 0.46441188216139834,
      "grad_norm": 0.374919056892395,
      "learning_rate": 1.748010105486702e-05,
      "loss": 0.5701,
      "step": 15118
    },
    {
      "epoch": 0.4644426012963475,
      "grad_norm": 0.36940738558769226,
      "learning_rate": 1.747978030108322e-05,
      "loss": 0.5908,
      "step": 15119
    },
    {
      "epoch": 0.46447332043129663,
      "grad_norm": 0.36034899950027466,
      "learning_rate": 1.747945952982987e-05,
      "loss": 0.5448,
      "step": 15120
    },
    {
      "epoch": 0.4645040395662458,
      "grad_norm": 0.38456836342811584,
      "learning_rate": 1.747913874110772e-05,
      "loss": 0.5984,
      "step": 15121
    },
    {
      "epoch": 0.464534758701195,
      "grad_norm": 0.3516639471054077,
      "learning_rate": 1.7478817934917517e-05,
      "loss": 0.562,
      "step": 15122
    },
    {
      "epoch": 0.46456547783614416,
      "grad_norm": 0.3458364009857178,
      "learning_rate": 1.7478497111260014e-05,
      "loss": 0.5103,
      "step": 15123
    },
    {
      "epoch": 0.4645961969710933,
      "grad_norm": 0.37188270688056946,
      "learning_rate": 1.7478176270135957e-05,
      "loss": 0.5391,
      "step": 15124
    },
    {
      "epoch": 0.46462691610604245,
      "grad_norm": 0.34533023834228516,
      "learning_rate": 1.74778554115461e-05,
      "loss": 0.5586,
      "step": 15125
    },
    {
      "epoch": 0.46465763524099163,
      "grad_norm": 0.34897857904434204,
      "learning_rate": 1.7477534535491186e-05,
      "loss": 0.546,
      "step": 15126
    },
    {
      "epoch": 0.46468835437594075,
      "grad_norm": 0.3389512598514557,
      "learning_rate": 1.7477213641971968e-05,
      "loss": 0.55,
      "step": 15127
    },
    {
      "epoch": 0.4647190735108899,
      "grad_norm": 0.3915907144546509,
      "learning_rate": 1.74768927309892e-05,
      "loss": 0.5452,
      "step": 15128
    },
    {
      "epoch": 0.4647497926458391,
      "grad_norm": 0.37128928303718567,
      "learning_rate": 1.747657180254362e-05,
      "loss": 0.6162,
      "step": 15129
    },
    {
      "epoch": 0.4647805117807883,
      "grad_norm": 0.4151308834552765,
      "learning_rate": 1.7476250856635987e-05,
      "loss": 0.6249,
      "step": 15130
    },
    {
      "epoch": 0.4648112309157374,
      "grad_norm": 0.3289475739002228,
      "learning_rate": 1.747592989326705e-05,
      "loss": 0.5773,
      "step": 15131
    },
    {
      "epoch": 0.46484195005068657,
      "grad_norm": 0.3350173830986023,
      "learning_rate": 1.7475608912437556e-05,
      "loss": 0.4872,
      "step": 15132
    },
    {
      "epoch": 0.46487266918563575,
      "grad_norm": 0.35706743597984314,
      "learning_rate": 1.7475287914148256e-05,
      "loss": 0.5096,
      "step": 15133
    },
    {
      "epoch": 0.46490338832058486,
      "grad_norm": 0.3954257667064667,
      "learning_rate": 1.7474966898399897e-05,
      "loss": 0.6365,
      "step": 15134
    },
    {
      "epoch": 0.46493410745553404,
      "grad_norm": 0.3492475152015686,
      "learning_rate": 1.7474645865193232e-05,
      "loss": 0.6,
      "step": 15135
    },
    {
      "epoch": 0.4649648265904832,
      "grad_norm": 0.34497517347335815,
      "learning_rate": 1.747432481452901e-05,
      "loss": 0.6018,
      "step": 15136
    },
    {
      "epoch": 0.4649955457254324,
      "grad_norm": 0.36866170167922974,
      "learning_rate": 1.7474003746407978e-05,
      "loss": 0.624,
      "step": 15137
    },
    {
      "epoch": 0.4650262648603815,
      "grad_norm": 0.3482343554496765,
      "learning_rate": 1.747368266083089e-05,
      "loss": 0.6397,
      "step": 15138
    },
    {
      "epoch": 0.4650569839953307,
      "grad_norm": 0.3666715919971466,
      "learning_rate": 1.7473361557798495e-05,
      "loss": 0.531,
      "step": 15139
    },
    {
      "epoch": 0.46508770313027986,
      "grad_norm": 0.38273510336875916,
      "learning_rate": 1.747304043731154e-05,
      "loss": 0.5447,
      "step": 15140
    },
    {
      "epoch": 0.46511842226522904,
      "grad_norm": 0.3599989116191864,
      "learning_rate": 1.747271929937078e-05,
      "loss": 0.5381,
      "step": 15141
    },
    {
      "epoch": 0.46514914140017816,
      "grad_norm": 0.3552003502845764,
      "learning_rate": 1.747239814397696e-05,
      "loss": 0.6233,
      "step": 15142
    },
    {
      "epoch": 0.46517986053512733,
      "grad_norm": 0.3514392077922821,
      "learning_rate": 1.7472076971130832e-05,
      "loss": 0.6007,
      "step": 15143
    },
    {
      "epoch": 0.4652105796700765,
      "grad_norm": 0.46120914816856384,
      "learning_rate": 1.7471755780833146e-05,
      "loss": 0.5072,
      "step": 15144
    },
    {
      "epoch": 0.4652412988050256,
      "grad_norm": 0.3423146903514862,
      "learning_rate": 1.7471434573084657e-05,
      "loss": 0.5895,
      "step": 15145
    },
    {
      "epoch": 0.4652720179399748,
      "grad_norm": 0.3601244390010834,
      "learning_rate": 1.7471113347886106e-05,
      "loss": 0.5584,
      "step": 15146
    },
    {
      "epoch": 0.465302737074924,
      "grad_norm": 0.34826943278312683,
      "learning_rate": 1.747079210523825e-05,
      "loss": 0.5135,
      "step": 15147
    },
    {
      "epoch": 0.46533345620987315,
      "grad_norm": 0.4933094084262848,
      "learning_rate": 1.7470470845141837e-05,
      "loss": 0.5825,
      "step": 15148
    },
    {
      "epoch": 0.4653641753448223,
      "grad_norm": 0.3589712679386139,
      "learning_rate": 1.747014956759762e-05,
      "loss": 0.5514,
      "step": 15149
    },
    {
      "epoch": 0.46539489447977145,
      "grad_norm": 0.327723890542984,
      "learning_rate": 1.7469828272606343e-05,
      "loss": 0.5845,
      "step": 15150
    },
    {
      "epoch": 0.4654256136147206,
      "grad_norm": 0.35572993755340576,
      "learning_rate": 1.7469506960168762e-05,
      "loss": 0.6729,
      "step": 15151
    },
    {
      "epoch": 0.46545633274966974,
      "grad_norm": 0.36295169591903687,
      "learning_rate": 1.7469185630285626e-05,
      "loss": 0.6093,
      "step": 15152
    },
    {
      "epoch": 0.4654870518846189,
      "grad_norm": 0.33789241313934326,
      "learning_rate": 1.746886428295768e-05,
      "loss": 0.5104,
      "step": 15153
    },
    {
      "epoch": 0.4655177710195681,
      "grad_norm": 0.3676663935184479,
      "learning_rate": 1.7468542918185685e-05,
      "loss": 0.651,
      "step": 15154
    },
    {
      "epoch": 0.46554849015451727,
      "grad_norm": 0.35232865810394287,
      "learning_rate": 1.7468221535970388e-05,
      "loss": 0.5563,
      "step": 15155
    },
    {
      "epoch": 0.4655792092894664,
      "grad_norm": 0.3533463776111603,
      "learning_rate": 1.7467900136312537e-05,
      "loss": 0.5845,
      "step": 15156
    },
    {
      "epoch": 0.46560992842441556,
      "grad_norm": 0.3538619577884674,
      "learning_rate": 1.7467578719212882e-05,
      "loss": 0.5243,
      "step": 15157
    },
    {
      "epoch": 0.46564064755936474,
      "grad_norm": 0.3469616174697876,
      "learning_rate": 1.7467257284672175e-05,
      "loss": 0.6121,
      "step": 15158
    },
    {
      "epoch": 0.4656713666943139,
      "grad_norm": 0.3317453861236572,
      "learning_rate": 1.746693583269117e-05,
      "loss": 0.6073,
      "step": 15159
    },
    {
      "epoch": 0.46570208582926303,
      "grad_norm": 0.349765807390213,
      "learning_rate": 1.7466614363270613e-05,
      "loss": 0.6371,
      "step": 15160
    },
    {
      "epoch": 0.4657328049642122,
      "grad_norm": 0.38808029890060425,
      "learning_rate": 1.7466292876411256e-05,
      "loss": 0.6297,
      "step": 15161
    },
    {
      "epoch": 0.4657635240991614,
      "grad_norm": 0.3559630215167999,
      "learning_rate": 1.746597137211385e-05,
      "loss": 0.608,
      "step": 15162
    },
    {
      "epoch": 0.4657942432341105,
      "grad_norm": 0.3407887816429138,
      "learning_rate": 1.7465649850379153e-05,
      "loss": 0.5416,
      "step": 15163
    },
    {
      "epoch": 0.4658249623690597,
      "grad_norm": 0.44187670946121216,
      "learning_rate": 1.7465328311207904e-05,
      "loss": 0.6258,
      "step": 15164
    },
    {
      "epoch": 0.46585568150400886,
      "grad_norm": 0.4043227434158325,
      "learning_rate": 1.7465006754600856e-05,
      "loss": 0.6137,
      "step": 15165
    },
    {
      "epoch": 0.46588640063895803,
      "grad_norm": 0.37306439876556396,
      "learning_rate": 1.746468518055877e-05,
      "loss": 0.5262,
      "step": 15166
    },
    {
      "epoch": 0.46591711977390715,
      "grad_norm": 0.3654891550540924,
      "learning_rate": 1.7464363589082386e-05,
      "loss": 0.5415,
      "step": 15167
    },
    {
      "epoch": 0.4659478389088563,
      "grad_norm": 0.3746562898159027,
      "learning_rate": 1.7464041980172462e-05,
      "loss": 0.6117,
      "step": 15168
    },
    {
      "epoch": 0.4659785580438055,
      "grad_norm": 0.40146467089653015,
      "learning_rate": 1.7463720353829746e-05,
      "loss": 0.4936,
      "step": 15169
    },
    {
      "epoch": 0.4660092771787546,
      "grad_norm": 0.3937714695930481,
      "learning_rate": 1.7463398710054988e-05,
      "loss": 0.6054,
      "step": 15170
    },
    {
      "epoch": 0.4660399963137038,
      "grad_norm": 0.3870045840740204,
      "learning_rate": 1.7463077048848945e-05,
      "loss": 0.6131,
      "step": 15171
    },
    {
      "epoch": 0.466070715448653,
      "grad_norm": 0.36773884296417236,
      "learning_rate": 1.746275537021236e-05,
      "loss": 0.5301,
      "step": 15172
    },
    {
      "epoch": 0.46610143458360215,
      "grad_norm": 0.3215831518173218,
      "learning_rate": 1.7462433674145992e-05,
      "loss": 0.5216,
      "step": 15173
    },
    {
      "epoch": 0.46613215371855127,
      "grad_norm": 0.3669358193874359,
      "learning_rate": 1.7462111960650586e-05,
      "loss": 0.6133,
      "step": 15174
    },
    {
      "epoch": 0.46616287285350044,
      "grad_norm": 0.34286028146743774,
      "learning_rate": 1.7461790229726898e-05,
      "loss": 0.4966,
      "step": 15175
    },
    {
      "epoch": 0.4661935919884496,
      "grad_norm": 0.4131510555744171,
      "learning_rate": 1.746146848137568e-05,
      "loss": 0.6388,
      "step": 15176
    },
    {
      "epoch": 0.46622431112339874,
      "grad_norm": 0.3755442202091217,
      "learning_rate": 1.746114671559768e-05,
      "loss": 0.578,
      "step": 15177
    },
    {
      "epoch": 0.4662550302583479,
      "grad_norm": 0.45600154995918274,
      "learning_rate": 1.7460824932393648e-05,
      "loss": 0.5211,
      "step": 15178
    },
    {
      "epoch": 0.4662857493932971,
      "grad_norm": 0.3173108994960785,
      "learning_rate": 1.746050313176434e-05,
      "loss": 0.5938,
      "step": 15179
    },
    {
      "epoch": 0.46631646852824626,
      "grad_norm": 0.3853795826435089,
      "learning_rate": 1.7460181313710504e-05,
      "loss": 0.5195,
      "step": 15180
    },
    {
      "epoch": 0.4663471876631954,
      "grad_norm": 0.3663421869277954,
      "learning_rate": 1.7459859478232894e-05,
      "loss": 0.5964,
      "step": 15181
    },
    {
      "epoch": 0.46637790679814456,
      "grad_norm": 0.33931228518486023,
      "learning_rate": 1.7459537625332267e-05,
      "loss": 0.5258,
      "step": 15182
    },
    {
      "epoch": 0.46640862593309373,
      "grad_norm": 0.32092925906181335,
      "learning_rate": 1.745921575500936e-05,
      "loss": 0.5611,
      "step": 15183
    },
    {
      "epoch": 0.4664393450680429,
      "grad_norm": 0.3394658863544464,
      "learning_rate": 1.745889386726494e-05,
      "loss": 0.5516,
      "step": 15184
    },
    {
      "epoch": 0.46647006420299203,
      "grad_norm": 0.341662734746933,
      "learning_rate": 1.745857196209975e-05,
      "loss": 0.4938,
      "step": 15185
    },
    {
      "epoch": 0.4665007833379412,
      "grad_norm": 0.4204656779766083,
      "learning_rate": 1.745825003951455e-05,
      "loss": 0.5744,
      "step": 15186
    },
    {
      "epoch": 0.4665315024728904,
      "grad_norm": 0.3704216480255127,
      "learning_rate": 1.745792809951008e-05,
      "loss": 0.4843,
      "step": 15187
    },
    {
      "epoch": 0.4665622216078395,
      "grad_norm": 0.3445076644420624,
      "learning_rate": 1.7457606142087097e-05,
      "loss": 0.503,
      "step": 15188
    },
    {
      "epoch": 0.4665929407427887,
      "grad_norm": 0.38017070293426514,
      "learning_rate": 1.7457284167246357e-05,
      "loss": 0.5861,
      "step": 15189
    },
    {
      "epoch": 0.46662365987773785,
      "grad_norm": 0.3213556408882141,
      "learning_rate": 1.7456962174988606e-05,
      "loss": 0.5253,
      "step": 15190
    },
    {
      "epoch": 0.466654379012687,
      "grad_norm": 0.353863000869751,
      "learning_rate": 1.74566401653146e-05,
      "loss": 0.5023,
      "step": 15191
    },
    {
      "epoch": 0.46668509814763615,
      "grad_norm": 0.36468854546546936,
      "learning_rate": 1.7456318138225094e-05,
      "loss": 0.5525,
      "step": 15192
    },
    {
      "epoch": 0.4667158172825853,
      "grad_norm": 0.44338807463645935,
      "learning_rate": 1.7455996093720834e-05,
      "loss": 0.5456,
      "step": 15193
    },
    {
      "epoch": 0.4667465364175345,
      "grad_norm": 0.4711027443408966,
      "learning_rate": 1.7455674031802576e-05,
      "loss": 0.5583,
      "step": 15194
    },
    {
      "epoch": 0.4667772555524836,
      "grad_norm": 0.3705287277698517,
      "learning_rate": 1.7455351952471068e-05,
      "loss": 0.6584,
      "step": 15195
    },
    {
      "epoch": 0.4668079746874328,
      "grad_norm": 0.3871898949146271,
      "learning_rate": 1.7455029855727064e-05,
      "loss": 0.5748,
      "step": 15196
    },
    {
      "epoch": 0.46683869382238197,
      "grad_norm": 0.4193970263004303,
      "learning_rate": 1.745470774157132e-05,
      "loss": 0.544,
      "step": 15197
    },
    {
      "epoch": 0.46686941295733114,
      "grad_norm": 0.39517489075660706,
      "learning_rate": 1.7454385610004583e-05,
      "loss": 0.563,
      "step": 15198
    },
    {
      "epoch": 0.46690013209228026,
      "grad_norm": 0.3505682051181793,
      "learning_rate": 1.7454063461027607e-05,
      "loss": 0.544,
      "step": 15199
    },
    {
      "epoch": 0.46693085122722944,
      "grad_norm": 0.3354949951171875,
      "learning_rate": 1.745374129464115e-05,
      "loss": 0.5592,
      "step": 15200
    },
    {
      "epoch": 0.4669615703621786,
      "grad_norm": 0.4253388047218323,
      "learning_rate": 1.7453419110845954e-05,
      "loss": 0.4677,
      "step": 15201
    },
    {
      "epoch": 0.4669922894971278,
      "grad_norm": 0.4756682813167572,
      "learning_rate": 1.7453096909642783e-05,
      "loss": 0.6168,
      "step": 15202
    },
    {
      "epoch": 0.4670230086320769,
      "grad_norm": 0.38148006796836853,
      "learning_rate": 1.7452774691032378e-05,
      "loss": 0.5274,
      "step": 15203
    },
    {
      "epoch": 0.4670537277670261,
      "grad_norm": 0.3887532651424408,
      "learning_rate": 1.74524524550155e-05,
      "loss": 0.5458,
      "step": 15204
    },
    {
      "epoch": 0.46708444690197526,
      "grad_norm": 0.3874104917049408,
      "learning_rate": 1.74521302015929e-05,
      "loss": 0.5857,
      "step": 15205
    },
    {
      "epoch": 0.4671151660369244,
      "grad_norm": 0.3933415710926056,
      "learning_rate": 1.745180793076533e-05,
      "loss": 0.6115,
      "step": 15206
    },
    {
      "epoch": 0.46714588517187355,
      "grad_norm": 0.3427456021308899,
      "learning_rate": 1.745148564253354e-05,
      "loss": 0.5692,
      "step": 15207
    },
    {
      "epoch": 0.46717660430682273,
      "grad_norm": 0.3112364113330841,
      "learning_rate": 1.7451163336898283e-05,
      "loss": 0.5216,
      "step": 15208
    },
    {
      "epoch": 0.4672073234417719,
      "grad_norm": 0.3043906092643738,
      "learning_rate": 1.7450841013860316e-05,
      "loss": 0.5586,
      "step": 15209
    },
    {
      "epoch": 0.467238042576721,
      "grad_norm": 0.33489498496055603,
      "learning_rate": 1.745051867342039e-05,
      "loss": 0.5464,
      "step": 15210
    },
    {
      "epoch": 0.4672687617116702,
      "grad_norm": 0.40852952003479004,
      "learning_rate": 1.745019631557925e-05,
      "loss": 0.6345,
      "step": 15211
    },
    {
      "epoch": 0.4672994808466194,
      "grad_norm": 0.38891974091529846,
      "learning_rate": 1.744987394033767e-05,
      "loss": 0.5907,
      "step": 15212
    },
    {
      "epoch": 0.4673301999815685,
      "grad_norm": 0.4153209924697876,
      "learning_rate": 1.7449551547696378e-05,
      "loss": 0.6519,
      "step": 15213
    },
    {
      "epoch": 0.46736091911651767,
      "grad_norm": 0.42603862285614014,
      "learning_rate": 1.7449229137656144e-05,
      "loss": 0.6679,
      "step": 15214
    },
    {
      "epoch": 0.46739163825146685,
      "grad_norm": 0.3691406846046448,
      "learning_rate": 1.7448906710217714e-05,
      "loss": 0.5229,
      "step": 15215
    },
    {
      "epoch": 0.467422357386416,
      "grad_norm": 0.37575843930244446,
      "learning_rate": 1.7448584265381837e-05,
      "loss": 0.5511,
      "step": 15216
    },
    {
      "epoch": 0.46745307652136514,
      "grad_norm": 0.3647887706756592,
      "learning_rate": 1.744826180314928e-05,
      "loss": 0.695,
      "step": 15217
    },
    {
      "epoch": 0.4674837956563143,
      "grad_norm": 0.36543455719947815,
      "learning_rate": 1.744793932352078e-05,
      "loss": 0.5484,
      "step": 15218
    },
    {
      "epoch": 0.4675145147912635,
      "grad_norm": 0.3195529878139496,
      "learning_rate": 1.7447616826497097e-05,
      "loss": 0.5425,
      "step": 15219
    },
    {
      "epoch": 0.4675452339262126,
      "grad_norm": 0.3481314778327942,
      "learning_rate": 1.744729431207899e-05,
      "loss": 0.481,
      "step": 15220
    },
    {
      "epoch": 0.4675759530611618,
      "grad_norm": 0.33704105019569397,
      "learning_rate": 1.7446971780267206e-05,
      "loss": 0.5655,
      "step": 15221
    },
    {
      "epoch": 0.46760667219611096,
      "grad_norm": 0.4021010100841522,
      "learning_rate": 1.7446649231062498e-05,
      "loss": 0.6044,
      "step": 15222
    },
    {
      "epoch": 0.46763739133106014,
      "grad_norm": 2.205193281173706,
      "learning_rate": 1.744632666446562e-05,
      "loss": 0.626,
      "step": 15223
    },
    {
      "epoch": 0.46766811046600926,
      "grad_norm": 0.3273734748363495,
      "learning_rate": 1.744600408047733e-05,
      "loss": 0.553,
      "step": 15224
    },
    {
      "epoch": 0.46769882960095843,
      "grad_norm": 0.3629317581653595,
      "learning_rate": 1.7445681479098372e-05,
      "loss": 0.5214,
      "step": 15225
    },
    {
      "epoch": 0.4677295487359076,
      "grad_norm": 0.3555382490158081,
      "learning_rate": 1.7445358860329507e-05,
      "loss": 0.5452,
      "step": 15226
    },
    {
      "epoch": 0.4677602678708568,
      "grad_norm": 0.40340808033943176,
      "learning_rate": 1.7445036224171486e-05,
      "loss": 0.5904,
      "step": 15227
    },
    {
      "epoch": 0.4677909870058059,
      "grad_norm": 0.34748902916908264,
      "learning_rate": 1.7444713570625064e-05,
      "loss": 0.5874,
      "step": 15228
    },
    {
      "epoch": 0.4678217061407551,
      "grad_norm": 0.33446264266967773,
      "learning_rate": 1.7444390899690995e-05,
      "loss": 0.5423,
      "step": 15229
    },
    {
      "epoch": 0.46785242527570425,
      "grad_norm": 0.32036179304122925,
      "learning_rate": 1.7444068211370032e-05,
      "loss": 0.4863,
      "step": 15230
    },
    {
      "epoch": 0.4678831444106534,
      "grad_norm": 0.34019848704338074,
      "learning_rate": 1.7443745505662925e-05,
      "loss": 0.6146,
      "step": 15231
    },
    {
      "epoch": 0.46791386354560255,
      "grad_norm": 0.32779327034950256,
      "learning_rate": 1.744342278257043e-05,
      "loss": 0.5833,
      "step": 15232
    },
    {
      "epoch": 0.4679445826805517,
      "grad_norm": 0.3636252284049988,
      "learning_rate": 1.7443100042093298e-05,
      "loss": 0.5466,
      "step": 15233
    },
    {
      "epoch": 0.4679753018155009,
      "grad_norm": 0.3531205952167511,
      "learning_rate": 1.7442777284232292e-05,
      "loss": 0.5561,
      "step": 15234
    },
    {
      "epoch": 0.46800602095045,
      "grad_norm": 0.4053487777709961,
      "learning_rate": 1.7442454508988155e-05,
      "loss": 0.6501,
      "step": 15235
    },
    {
      "epoch": 0.4680367400853992,
      "grad_norm": 0.39670121669769287,
      "learning_rate": 1.744213171636165e-05,
      "loss": 0.5674,
      "step": 15236
    },
    {
      "epoch": 0.46806745922034837,
      "grad_norm": 0.3441225290298462,
      "learning_rate": 1.7441808906353526e-05,
      "loss": 0.5852,
      "step": 15237
    },
    {
      "epoch": 0.4680981783552975,
      "grad_norm": 0.3644164502620697,
      "learning_rate": 1.744148607896454e-05,
      "loss": 0.546,
      "step": 15238
    },
    {
      "epoch": 0.46812889749024666,
      "grad_norm": 0.357755184173584,
      "learning_rate": 1.744116323419544e-05,
      "loss": 0.5753,
      "step": 15239
    },
    {
      "epoch": 0.46815961662519584,
      "grad_norm": 0.39328598976135254,
      "learning_rate": 1.744084037204698e-05,
      "loss": 0.653,
      "step": 15240
    },
    {
      "epoch": 0.468190335760145,
      "grad_norm": 0.3690771758556366,
      "learning_rate": 1.7440517492519925e-05,
      "loss": 0.607,
      "step": 15241
    },
    {
      "epoch": 0.46822105489509414,
      "grad_norm": 0.33504247665405273,
      "learning_rate": 1.7440194595615015e-05,
      "loss": 0.5466,
      "step": 15242
    },
    {
      "epoch": 0.4682517740300433,
      "grad_norm": 0.3672151565551758,
      "learning_rate": 1.7439871681333018e-05,
      "loss": 0.6,
      "step": 15243
    },
    {
      "epoch": 0.4682824931649925,
      "grad_norm": 0.3523682951927185,
      "learning_rate": 1.7439548749674675e-05,
      "loss": 0.6853,
      "step": 15244
    },
    {
      "epoch": 0.46831321229994166,
      "grad_norm": 0.36045971512794495,
      "learning_rate": 1.7439225800640745e-05,
      "loss": 0.6592,
      "step": 15245
    },
    {
      "epoch": 0.4683439314348908,
      "grad_norm": 0.3483760952949524,
      "learning_rate": 1.743890283423199e-05,
      "loss": 0.5969,
      "step": 15246
    },
    {
      "epoch": 0.46837465056983996,
      "grad_norm": 0.34445443749427795,
      "learning_rate": 1.7438579850449155e-05,
      "loss": 0.6136,
      "step": 15247
    },
    {
      "epoch": 0.46840536970478913,
      "grad_norm": 0.30732402205467224,
      "learning_rate": 1.7438256849293e-05,
      "loss": 0.5944,
      "step": 15248
    },
    {
      "epoch": 0.46843608883973825,
      "grad_norm": 0.36761805415153503,
      "learning_rate": 1.743793383076427e-05,
      "loss": 0.5694,
      "step": 15249
    },
    {
      "epoch": 0.4684668079746874,
      "grad_norm": 0.33591607213020325,
      "learning_rate": 1.7437610794863732e-05,
      "loss": 0.5372,
      "step": 15250
    },
    {
      "epoch": 0.4684975271096366,
      "grad_norm": 0.3615039885044098,
      "learning_rate": 1.7437287741592132e-05,
      "loss": 0.5287,
      "step": 15251
    },
    {
      "epoch": 0.4685282462445858,
      "grad_norm": 0.29399213194847107,
      "learning_rate": 1.7436964670950228e-05,
      "loss": 0.5423,
      "step": 15252
    },
    {
      "epoch": 0.4685589653795349,
      "grad_norm": 0.4320829510688782,
      "learning_rate": 1.7436641582938775e-05,
      "loss": 0.5594,
      "step": 15253
    },
    {
      "epoch": 0.4685896845144841,
      "grad_norm": 0.3440847396850586,
      "learning_rate": 1.743631847755852e-05,
      "loss": 0.5951,
      "step": 15254
    },
    {
      "epoch": 0.46862040364943325,
      "grad_norm": 0.37401899695396423,
      "learning_rate": 1.7435995354810233e-05,
      "loss": 0.6045,
      "step": 15255
    },
    {
      "epoch": 0.46865112278438237,
      "grad_norm": 0.3436407148838043,
      "learning_rate": 1.7435672214694656e-05,
      "loss": 0.5933,
      "step": 15256
    },
    {
      "epoch": 0.46868184191933154,
      "grad_norm": 0.3635391592979431,
      "learning_rate": 1.7435349057212545e-05,
      "loss": 0.5822,
      "step": 15257
    },
    {
      "epoch": 0.4687125610542807,
      "grad_norm": 0.39782479405403137,
      "learning_rate": 1.7435025882364657e-05,
      "loss": 0.5331,
      "step": 15258
    },
    {
      "epoch": 0.4687432801892299,
      "grad_norm": 0.34352582693099976,
      "learning_rate": 1.743470269015175e-05,
      "loss": 0.5754,
      "step": 15259
    },
    {
      "epoch": 0.468773999324179,
      "grad_norm": 0.3317194879055023,
      "learning_rate": 1.7434379480574574e-05,
      "loss": 0.5793,
      "step": 15260
    },
    {
      "epoch": 0.4688047184591282,
      "grad_norm": 0.32368239760398865,
      "learning_rate": 1.7434056253633885e-05,
      "loss": 0.5821,
      "step": 15261
    },
    {
      "epoch": 0.46883543759407736,
      "grad_norm": 0.33947303891181946,
      "learning_rate": 1.7433733009330436e-05,
      "loss": 0.6215,
      "step": 15262
    },
    {
      "epoch": 0.4688661567290265,
      "grad_norm": 0.3037901520729065,
      "learning_rate": 1.7433409747664987e-05,
      "loss": 0.494,
      "step": 15263
    },
    {
      "epoch": 0.46889687586397566,
      "grad_norm": 0.3486025035381317,
      "learning_rate": 1.743308646863829e-05,
      "loss": 0.6336,
      "step": 15264
    },
    {
      "epoch": 0.46892759499892483,
      "grad_norm": 0.32500913739204407,
      "learning_rate": 1.74327631722511e-05,
      "loss": 0.5801,
      "step": 15265
    },
    {
      "epoch": 0.468958314133874,
      "grad_norm": 0.35308313369750977,
      "learning_rate": 1.7432439858504175e-05,
      "loss": 0.554,
      "step": 15266
    },
    {
      "epoch": 0.46898903326882313,
      "grad_norm": 0.39290860295295715,
      "learning_rate": 1.7432116527398264e-05,
      "loss": 0.6761,
      "step": 15267
    },
    {
      "epoch": 0.4690197524037723,
      "grad_norm": 0.35500627756118774,
      "learning_rate": 1.743179317893413e-05,
      "loss": 0.5729,
      "step": 15268
    },
    {
      "epoch": 0.4690504715387215,
      "grad_norm": 0.3482816815376282,
      "learning_rate": 1.743146981311252e-05,
      "loss": 0.6146,
      "step": 15269
    },
    {
      "epoch": 0.46908119067367066,
      "grad_norm": 0.40450194478034973,
      "learning_rate": 1.7431146429934197e-05,
      "loss": 0.5505,
      "step": 15270
    },
    {
      "epoch": 0.4691119098086198,
      "grad_norm": 0.32359185814857483,
      "learning_rate": 1.743082302939991e-05,
      "loss": 0.5259,
      "step": 15271
    },
    {
      "epoch": 0.46914262894356895,
      "grad_norm": 0.3848201334476471,
      "learning_rate": 1.7430499611510418e-05,
      "loss": 0.6152,
      "step": 15272
    },
    {
      "epoch": 0.4691733480785181,
      "grad_norm": 0.35029691457748413,
      "learning_rate": 1.7430176176266474e-05,
      "loss": 0.5363,
      "step": 15273
    },
    {
      "epoch": 0.46920406721346725,
      "grad_norm": 0.35482972860336304,
      "learning_rate": 1.7429852723668835e-05,
      "loss": 0.5567,
      "step": 15274
    },
    {
      "epoch": 0.4692347863484164,
      "grad_norm": 0.3562295138835907,
      "learning_rate": 1.7429529253718252e-05,
      "loss": 0.6454,
      "step": 15275
    },
    {
      "epoch": 0.4692655054833656,
      "grad_norm": 0.5990108251571655,
      "learning_rate": 1.742920576641549e-05,
      "loss": 0.5533,
      "step": 15276
    },
    {
      "epoch": 0.4692962246183148,
      "grad_norm": 0.3691100478172302,
      "learning_rate": 1.7428882261761298e-05,
      "loss": 0.595,
      "step": 15277
    },
    {
      "epoch": 0.4693269437532639,
      "grad_norm": 0.4669521749019623,
      "learning_rate": 1.7428558739756438e-05,
      "loss": 0.5794,
      "step": 15278
    },
    {
      "epoch": 0.46935766288821307,
      "grad_norm": 0.39610689878463745,
      "learning_rate": 1.7428235200401652e-05,
      "loss": 0.6119,
      "step": 15279
    },
    {
      "epoch": 0.46938838202316224,
      "grad_norm": 0.34193655848503113,
      "learning_rate": 1.7427911643697707e-05,
      "loss": 0.5013,
      "step": 15280
    },
    {
      "epoch": 0.46941910115811136,
      "grad_norm": 0.4000982344150543,
      "learning_rate": 1.7427588069645352e-05,
      "loss": 0.5702,
      "step": 15281
    },
    {
      "epoch": 0.46944982029306054,
      "grad_norm": 0.3355148136615753,
      "learning_rate": 1.7427264478245353e-05,
      "loss": 0.5401,
      "step": 15282
    },
    {
      "epoch": 0.4694805394280097,
      "grad_norm": 0.370853453874588,
      "learning_rate": 1.7426940869498453e-05,
      "loss": 0.5816,
      "step": 15283
    },
    {
      "epoch": 0.4695112585629589,
      "grad_norm": 0.31844350695610046,
      "learning_rate": 1.742661724340542e-05,
      "loss": 0.5665,
      "step": 15284
    },
    {
      "epoch": 0.469541977697908,
      "grad_norm": 0.34829646348953247,
      "learning_rate": 1.7426293599966996e-05,
      "loss": 0.5409,
      "step": 15285
    },
    {
      "epoch": 0.4695726968328572,
      "grad_norm": 0.3407652974128723,
      "learning_rate": 1.742596993918395e-05,
      "loss": 0.5604,
      "step": 15286
    },
    {
      "epoch": 0.46960341596780636,
      "grad_norm": 0.3789529800415039,
      "learning_rate": 1.7425646261057032e-05,
      "loss": 0.5709,
      "step": 15287
    },
    {
      "epoch": 0.4696341351027555,
      "grad_norm": 0.37514784932136536,
      "learning_rate": 1.7425322565587e-05,
      "loss": 0.6046,
      "step": 15288
    },
    {
      "epoch": 0.46966485423770465,
      "grad_norm": 0.31911760568618774,
      "learning_rate": 1.7424998852774605e-05,
      "loss": 0.594,
      "step": 15289
    },
    {
      "epoch": 0.46969557337265383,
      "grad_norm": 0.3476778268814087,
      "learning_rate": 1.742467512262061e-05,
      "loss": 0.558,
      "step": 15290
    },
    {
      "epoch": 0.469726292507603,
      "grad_norm": 0.3762684166431427,
      "learning_rate": 1.7424351375125764e-05,
      "loss": 0.6216,
      "step": 15291
    },
    {
      "epoch": 0.4697570116425521,
      "grad_norm": 0.39758408069610596,
      "learning_rate": 1.742402761029083e-05,
      "loss": 0.603,
      "step": 15292
    },
    {
      "epoch": 0.4697877307775013,
      "grad_norm": 0.3249804377555847,
      "learning_rate": 1.742370382811656e-05,
      "loss": 0.5367,
      "step": 15293
    },
    {
      "epoch": 0.4698184499124505,
      "grad_norm": 0.3834912180900574,
      "learning_rate": 1.742338002860371e-05,
      "loss": 0.5795,
      "step": 15294
    },
    {
      "epoch": 0.46984916904739965,
      "grad_norm": 0.3593645989894867,
      "learning_rate": 1.7423056211753038e-05,
      "loss": 0.5836,
      "step": 15295
    },
    {
      "epoch": 0.46987988818234877,
      "grad_norm": 0.32722145318984985,
      "learning_rate": 1.74227323775653e-05,
      "loss": 0.6014,
      "step": 15296
    },
    {
      "epoch": 0.46991060731729795,
      "grad_norm": 0.32020458579063416,
      "learning_rate": 1.7422408526041253e-05,
      "loss": 0.5382,
      "step": 15297
    },
    {
      "epoch": 0.4699413264522471,
      "grad_norm": 0.35709813237190247,
      "learning_rate": 1.7422084657181652e-05,
      "loss": 0.5873,
      "step": 15298
    },
    {
      "epoch": 0.46997204558719624,
      "grad_norm": 0.3579193353652954,
      "learning_rate": 1.7421760770987255e-05,
      "loss": 0.5302,
      "step": 15299
    },
    {
      "epoch": 0.4700027647221454,
      "grad_norm": 0.35152876377105713,
      "learning_rate": 1.7421436867458815e-05,
      "loss": 0.6017,
      "step": 15300
    },
    {
      "epoch": 0.4700334838570946,
      "grad_norm": 0.33050861954689026,
      "learning_rate": 1.7421112946597097e-05,
      "loss": 0.5791,
      "step": 15301
    },
    {
      "epoch": 0.47006420299204377,
      "grad_norm": 0.3487630784511566,
      "learning_rate": 1.7420789008402846e-05,
      "loss": 0.6117,
      "step": 15302
    },
    {
      "epoch": 0.4700949221269929,
      "grad_norm": 0.3623282015323639,
      "learning_rate": 1.7420465052876822e-05,
      "loss": 0.5141,
      "step": 15303
    },
    {
      "epoch": 0.47012564126194206,
      "grad_norm": 0.3954010009765625,
      "learning_rate": 1.7420141080019787e-05,
      "loss": 0.659,
      "step": 15304
    },
    {
      "epoch": 0.47015636039689124,
      "grad_norm": 0.34622788429260254,
      "learning_rate": 1.7419817089832495e-05,
      "loss": 0.6316,
      "step": 15305
    },
    {
      "epoch": 0.47018707953184036,
      "grad_norm": 0.323954701423645,
      "learning_rate": 1.74194930823157e-05,
      "loss": 0.5222,
      "step": 15306
    },
    {
      "epoch": 0.47021779866678953,
      "grad_norm": 0.3590388298034668,
      "learning_rate": 1.741916905747016e-05,
      "loss": 0.5765,
      "step": 15307
    },
    {
      "epoch": 0.4702485178017387,
      "grad_norm": 0.3885011076927185,
      "learning_rate": 1.7418845015296636e-05,
      "loss": 0.498,
      "step": 15308
    },
    {
      "epoch": 0.4702792369366879,
      "grad_norm": 0.36577433347702026,
      "learning_rate": 1.7418520955795878e-05,
      "loss": 0.5543,
      "step": 15309
    },
    {
      "epoch": 0.470309956071637,
      "grad_norm": 0.408633291721344,
      "learning_rate": 1.741819687896865e-05,
      "loss": 0.4945,
      "step": 15310
    },
    {
      "epoch": 0.4703406752065862,
      "grad_norm": 0.3728128969669342,
      "learning_rate": 1.74178727848157e-05,
      "loss": 0.579,
      "step": 15311
    },
    {
      "epoch": 0.47037139434153535,
      "grad_norm": 0.37763017416000366,
      "learning_rate": 1.7417548673337795e-05,
      "loss": 0.6617,
      "step": 15312
    },
    {
      "epoch": 0.47040211347648453,
      "grad_norm": 0.35760852694511414,
      "learning_rate": 1.7417224544535685e-05,
      "loss": 0.498,
      "step": 15313
    },
    {
      "epoch": 0.47043283261143365,
      "grad_norm": 0.343004047870636,
      "learning_rate": 1.7416900398410125e-05,
      "loss": 0.5362,
      "step": 15314
    },
    {
      "epoch": 0.4704635517463828,
      "grad_norm": 0.339054673910141,
      "learning_rate": 1.741657623496188e-05,
      "loss": 0.5511,
      "step": 15315
    },
    {
      "epoch": 0.470494270881332,
      "grad_norm": 0.3606122136116028,
      "learning_rate": 1.7416252054191704e-05,
      "loss": 0.5679,
      "step": 15316
    },
    {
      "epoch": 0.4705249900162811,
      "grad_norm": 0.35711488127708435,
      "learning_rate": 1.741592785610035e-05,
      "loss": 0.5644,
      "step": 15317
    },
    {
      "epoch": 0.4705557091512303,
      "grad_norm": 0.36628398299217224,
      "learning_rate": 1.7415603640688584e-05,
      "loss": 0.5793,
      "step": 15318
    },
    {
      "epoch": 0.47058642828617947,
      "grad_norm": 0.3806704580783844,
      "learning_rate": 1.7415279407957154e-05,
      "loss": 0.6053,
      "step": 15319
    },
    {
      "epoch": 0.47061714742112865,
      "grad_norm": 0.39401543140411377,
      "learning_rate": 1.741495515790682e-05,
      "loss": 0.4859,
      "step": 15320
    },
    {
      "epoch": 0.47064786655607777,
      "grad_norm": 0.34477099776268005,
      "learning_rate": 1.7414630890538348e-05,
      "loss": 0.613,
      "step": 15321
    },
    {
      "epoch": 0.47067858569102694,
      "grad_norm": 0.3804318606853485,
      "learning_rate": 1.741430660585248e-05,
      "loss": 0.5649,
      "step": 15322
    },
    {
      "epoch": 0.4707093048259761,
      "grad_norm": 0.3644489347934723,
      "learning_rate": 1.741398230384998e-05,
      "loss": 0.5647,
      "step": 15323
    },
    {
      "epoch": 0.47074002396092524,
      "grad_norm": 0.331885427236557,
      "learning_rate": 1.741365798453161e-05,
      "loss": 0.5959,
      "step": 15324
    },
    {
      "epoch": 0.4707707430958744,
      "grad_norm": 0.38938108086586,
      "learning_rate": 1.741333364789813e-05,
      "loss": 0.5793,
      "step": 15325
    },
    {
      "epoch": 0.4708014622308236,
      "grad_norm": 0.3644320070743561,
      "learning_rate": 1.741300929395028e-05,
      "loss": 0.5639,
      "step": 15326
    },
    {
      "epoch": 0.47083218136577276,
      "grad_norm": 0.35625073313713074,
      "learning_rate": 1.7412684922688835e-05,
      "loss": 0.6127,
      "step": 15327
    },
    {
      "epoch": 0.4708629005007219,
      "grad_norm": 0.3974081575870514,
      "learning_rate": 1.7412360534114548e-05,
      "loss": 0.6112,
      "step": 15328
    },
    {
      "epoch": 0.47089361963567106,
      "grad_norm": 0.35002923011779785,
      "learning_rate": 1.741203612822817e-05,
      "loss": 0.5888,
      "step": 15329
    },
    {
      "epoch": 0.47092433877062023,
      "grad_norm": 0.3566001355648041,
      "learning_rate": 1.741171170503047e-05,
      "loss": 0.6191,
      "step": 15330
    },
    {
      "epoch": 0.47095505790556935,
      "grad_norm": 0.3353597819805145,
      "learning_rate": 1.7411387264522198e-05,
      "loss": 0.5727,
      "step": 15331
    },
    {
      "epoch": 0.4709857770405185,
      "grad_norm": 0.3826921880245209,
      "learning_rate": 1.741106280670411e-05,
      "loss": 0.5885,
      "step": 15332
    },
    {
      "epoch": 0.4710164961754677,
      "grad_norm": 0.45124170184135437,
      "learning_rate": 1.741073833157697e-05,
      "loss": 0.5848,
      "step": 15333
    },
    {
      "epoch": 0.4710472153104169,
      "grad_norm": 0.35391658544540405,
      "learning_rate": 1.7410413839141532e-05,
      "loss": 0.5403,
      "step": 15334
    },
    {
      "epoch": 0.471077934445366,
      "grad_norm": 0.3340965509414673,
      "learning_rate": 1.7410089329398558e-05,
      "loss": 0.5217,
      "step": 15335
    },
    {
      "epoch": 0.4711086535803152,
      "grad_norm": 0.6232472062110901,
      "learning_rate": 1.74097648023488e-05,
      "loss": 0.5552,
      "step": 15336
    },
    {
      "epoch": 0.47113937271526435,
      "grad_norm": 0.33544471859931946,
      "learning_rate": 1.7409440257993018e-05,
      "loss": 0.632,
      "step": 15337
    },
    {
      "epoch": 0.4711700918502135,
      "grad_norm": 0.3478744626045227,
      "learning_rate": 1.7409115696331973e-05,
      "loss": 0.5717,
      "step": 15338
    },
    {
      "epoch": 0.47120081098516264,
      "grad_norm": 0.3837464153766632,
      "learning_rate": 1.740879111736642e-05,
      "loss": 0.5558,
      "step": 15339
    },
    {
      "epoch": 0.4712315301201118,
      "grad_norm": 0.34578627347946167,
      "learning_rate": 1.7408466521097117e-05,
      "loss": 0.6185,
      "step": 15340
    },
    {
      "epoch": 0.471262249255061,
      "grad_norm": 0.3589742183685303,
      "learning_rate": 1.7408141907524824e-05,
      "loss": 0.6259,
      "step": 15341
    },
    {
      "epoch": 0.4712929683900101,
      "grad_norm": 0.3176213204860687,
      "learning_rate": 1.7407817276650298e-05,
      "loss": 0.5577,
      "step": 15342
    },
    {
      "epoch": 0.4713236875249593,
      "grad_norm": 0.357126921415329,
      "learning_rate": 1.74074926284743e-05,
      "loss": 0.5417,
      "step": 15343
    },
    {
      "epoch": 0.47135440665990846,
      "grad_norm": 0.4538467824459076,
      "learning_rate": 1.7407167962997583e-05,
      "loss": 0.5456,
      "step": 15344
    },
    {
      "epoch": 0.47138512579485764,
      "grad_norm": 0.3514200448989868,
      "learning_rate": 1.7406843280220903e-05,
      "loss": 0.5387,
      "step": 15345
    },
    {
      "epoch": 0.47141584492980676,
      "grad_norm": 0.3799632489681244,
      "learning_rate": 1.740651858014503e-05,
      "loss": 0.5909,
      "step": 15346
    },
    {
      "epoch": 0.47144656406475594,
      "grad_norm": 0.32820528745651245,
      "learning_rate": 1.7406193862770715e-05,
      "loss": 0.5233,
      "step": 15347
    },
    {
      "epoch": 0.4714772831997051,
      "grad_norm": 0.33566027879714966,
      "learning_rate": 1.7405869128098714e-05,
      "loss": 0.4723,
      "step": 15348
    },
    {
      "epoch": 0.47150800233465423,
      "grad_norm": 0.3658502399921417,
      "learning_rate": 1.7405544376129793e-05,
      "loss": 0.528,
      "step": 15349
    },
    {
      "epoch": 0.4715387214696034,
      "grad_norm": 0.3867243528366089,
      "learning_rate": 1.7405219606864703e-05,
      "loss": 0.6594,
      "step": 15350
    },
    {
      "epoch": 0.4715694406045526,
      "grad_norm": 0.45039427280426025,
      "learning_rate": 1.7404894820304203e-05,
      "loss": 0.5655,
      "step": 15351
    },
    {
      "epoch": 0.47160015973950176,
      "grad_norm": 0.35454899072647095,
      "learning_rate": 1.740457001644906e-05,
      "loss": 0.5764,
      "step": 15352
    },
    {
      "epoch": 0.4716308788744509,
      "grad_norm": 0.3163306415081024,
      "learning_rate": 1.7404245195300022e-05,
      "loss": 0.6119,
      "step": 15353
    },
    {
      "epoch": 0.47166159800940005,
      "grad_norm": 0.33900687098503113,
      "learning_rate": 1.740392035685785e-05,
      "loss": 0.5472,
      "step": 15354
    },
    {
      "epoch": 0.4716923171443492,
      "grad_norm": 0.3471027612686157,
      "learning_rate": 1.7403595501123313e-05,
      "loss": 0.5136,
      "step": 15355
    },
    {
      "epoch": 0.4717230362792984,
      "grad_norm": 0.4253346621990204,
      "learning_rate": 1.7403270628097154e-05,
      "loss": 0.573,
      "step": 15356
    },
    {
      "epoch": 0.4717537554142475,
      "grad_norm": 0.41095292568206787,
      "learning_rate": 1.7402945737780143e-05,
      "loss": 0.5619,
      "step": 15357
    },
    {
      "epoch": 0.4717844745491967,
      "grad_norm": 0.3558420240879059,
      "learning_rate": 1.7402620830173034e-05,
      "loss": 0.5648,
      "step": 15358
    },
    {
      "epoch": 0.4718151936841459,
      "grad_norm": 0.32900944352149963,
      "learning_rate": 1.7402295905276587e-05,
      "loss": 0.5073,
      "step": 15359
    },
    {
      "epoch": 0.471845912819095,
      "grad_norm": 0.40555018186569214,
      "learning_rate": 1.740197096309156e-05,
      "loss": 0.6127,
      "step": 15360
    },
    {
      "epoch": 0.47187663195404417,
      "grad_norm": 0.3589453101158142,
      "learning_rate": 1.7401646003618717e-05,
      "loss": 0.5772,
      "step": 15361
    },
    {
      "epoch": 0.47190735108899334,
      "grad_norm": 0.34511032700538635,
      "learning_rate": 1.740132102685881e-05,
      "loss": 0.6069,
      "step": 15362
    },
    {
      "epoch": 0.4719380702239425,
      "grad_norm": 0.3218221664428711,
      "learning_rate": 1.74009960328126e-05,
      "loss": 0.5878,
      "step": 15363
    },
    {
      "epoch": 0.47196878935889164,
      "grad_norm": 0.3963966369628906,
      "learning_rate": 1.7400671021480852e-05,
      "loss": 0.5272,
      "step": 15364
    },
    {
      "epoch": 0.4719995084938408,
      "grad_norm": 0.331624835729599,
      "learning_rate": 1.7400345992864312e-05,
      "loss": 0.5608,
      "step": 15365
    },
    {
      "epoch": 0.47203022762879,
      "grad_norm": 0.3387339115142822,
      "learning_rate": 1.7400020946963754e-05,
      "loss": 0.5184,
      "step": 15366
    },
    {
      "epoch": 0.4720609467637391,
      "grad_norm": 0.3463359475135803,
      "learning_rate": 1.7399695883779925e-05,
      "loss": 0.5516,
      "step": 15367
    },
    {
      "epoch": 0.4720916658986883,
      "grad_norm": 0.3713415563106537,
      "learning_rate": 1.7399370803313592e-05,
      "loss": 0.64,
      "step": 15368
    },
    {
      "epoch": 0.47212238503363746,
      "grad_norm": 0.36474600434303284,
      "learning_rate": 1.7399045705565513e-05,
      "loss": 0.5268,
      "step": 15369
    },
    {
      "epoch": 0.47215310416858663,
      "grad_norm": 0.3478292226791382,
      "learning_rate": 1.7398720590536444e-05,
      "loss": 0.6496,
      "step": 15370
    },
    {
      "epoch": 0.47218382330353575,
      "grad_norm": 0.4192321002483368,
      "learning_rate": 1.7398395458227148e-05,
      "loss": 0.5663,
      "step": 15371
    },
    {
      "epoch": 0.47221454243848493,
      "grad_norm": 0.34683674573898315,
      "learning_rate": 1.7398070308638382e-05,
      "loss": 0.5462,
      "step": 15372
    },
    {
      "epoch": 0.4722452615734341,
      "grad_norm": 0.3588685989379883,
      "learning_rate": 1.7397745141770904e-05,
      "loss": 0.4931,
      "step": 15373
    },
    {
      "epoch": 0.4722759807083832,
      "grad_norm": 0.3438624143600464,
      "learning_rate": 1.7397419957625478e-05,
      "loss": 0.5519,
      "step": 15374
    },
    {
      "epoch": 0.4723066998433324,
      "grad_norm": 0.3559296727180481,
      "learning_rate": 1.739709475620286e-05,
      "loss": 0.5946,
      "step": 15375
    },
    {
      "epoch": 0.4723374189782816,
      "grad_norm": 0.3427197337150574,
      "learning_rate": 1.7396769537503813e-05,
      "loss": 0.5045,
      "step": 15376
    },
    {
      "epoch": 0.47236813811323075,
      "grad_norm": 0.3533492386341095,
      "learning_rate": 1.739644430152909e-05,
      "loss": 0.5435,
      "step": 15377
    },
    {
      "epoch": 0.47239885724817987,
      "grad_norm": 0.34056904911994934,
      "learning_rate": 1.7396119048279455e-05,
      "loss": 0.5711,
      "step": 15378
    },
    {
      "epoch": 0.47242957638312905,
      "grad_norm": 0.329437792301178,
      "learning_rate": 1.7395793777755676e-05,
      "loss": 0.5524,
      "step": 15379
    },
    {
      "epoch": 0.4724602955180782,
      "grad_norm": 0.360853910446167,
      "learning_rate": 1.7395468489958492e-05,
      "loss": 0.5532,
      "step": 15380
    },
    {
      "epoch": 0.4724910146530274,
      "grad_norm": 0.33704832196235657,
      "learning_rate": 1.739514318488868e-05,
      "loss": 0.6089,
      "step": 15381
    },
    {
      "epoch": 0.4725217337879765,
      "grad_norm": 0.41825735569000244,
      "learning_rate": 1.7394817862546997e-05,
      "loss": 0.5251,
      "step": 15382
    },
    {
      "epoch": 0.4725524529229257,
      "grad_norm": 0.35778966546058655,
      "learning_rate": 1.7394492522934197e-05,
      "loss": 0.5291,
      "step": 15383
    },
    {
      "epoch": 0.47258317205787487,
      "grad_norm": 0.3360001742839813,
      "learning_rate": 1.7394167166051045e-05,
      "loss": 0.5417,
      "step": 15384
    },
    {
      "epoch": 0.472613891192824,
      "grad_norm": 0.35137075185775757,
      "learning_rate": 1.73938417918983e-05,
      "loss": 0.5746,
      "step": 15385
    },
    {
      "epoch": 0.47264461032777316,
      "grad_norm": 0.31396105885505676,
      "learning_rate": 1.739351640047672e-05,
      "loss": 0.601,
      "step": 15386
    },
    {
      "epoch": 0.47267532946272234,
      "grad_norm": 0.3746577799320221,
      "learning_rate": 1.7393190991787067e-05,
      "loss": 0.5979,
      "step": 15387
    },
    {
      "epoch": 0.4727060485976715,
      "grad_norm": 0.3909800350666046,
      "learning_rate": 1.73928655658301e-05,
      "loss": 0.5798,
      "step": 15388
    },
    {
      "epoch": 0.47273676773262063,
      "grad_norm": 0.3468107581138611,
      "learning_rate": 1.7392540122606575e-05,
      "loss": 0.5636,
      "step": 15389
    },
    {
      "epoch": 0.4727674868675698,
      "grad_norm": 0.32917284965515137,
      "learning_rate": 1.739221466211726e-05,
      "loss": 0.5569,
      "step": 15390
    },
    {
      "epoch": 0.472798206002519,
      "grad_norm": 0.3897896111011505,
      "learning_rate": 1.739188918436291e-05,
      "loss": 0.5705,
      "step": 15391
    },
    {
      "epoch": 0.4728289251374681,
      "grad_norm": 0.3404683470726013,
      "learning_rate": 1.739156368934429e-05,
      "loss": 0.6007,
      "step": 15392
    },
    {
      "epoch": 0.4728596442724173,
      "grad_norm": 0.4632088541984558,
      "learning_rate": 1.7391238177062152e-05,
      "loss": 0.596,
      "step": 15393
    },
    {
      "epoch": 0.47289036340736645,
      "grad_norm": 0.35257378220558167,
      "learning_rate": 1.7390912647517263e-05,
      "loss": 0.5708,
      "step": 15394
    },
    {
      "epoch": 0.47292108254231563,
      "grad_norm": 0.40153005719184875,
      "learning_rate": 1.7390587100710385e-05,
      "loss": 0.5677,
      "step": 15395
    },
    {
      "epoch": 0.47295180167726475,
      "grad_norm": 0.32786792516708374,
      "learning_rate": 1.739026153664227e-05,
      "loss": 0.5583,
      "step": 15396
    },
    {
      "epoch": 0.4729825208122139,
      "grad_norm": 0.37363845109939575,
      "learning_rate": 1.7389935955313685e-05,
      "loss": 0.5815,
      "step": 15397
    },
    {
      "epoch": 0.4730132399471631,
      "grad_norm": 0.3570508360862732,
      "learning_rate": 1.7389610356725386e-05,
      "loss": 0.5681,
      "step": 15398
    },
    {
      "epoch": 0.4730439590821123,
      "grad_norm": 0.3244105875492096,
      "learning_rate": 1.738928474087814e-05,
      "loss": 0.5336,
      "step": 15399
    },
    {
      "epoch": 0.4730746782170614,
      "grad_norm": 0.3286208510398865,
      "learning_rate": 1.73889591077727e-05,
      "loss": 0.528,
      "step": 15400
    },
    {
      "epoch": 0.47310539735201057,
      "grad_norm": 0.34112223982810974,
      "learning_rate": 1.7388633457409828e-05,
      "loss": 0.5789,
      "step": 15401
    },
    {
      "epoch": 0.47313611648695975,
      "grad_norm": 0.3537975549697876,
      "learning_rate": 1.738830778979029e-05,
      "loss": 0.5086,
      "step": 15402
    },
    {
      "epoch": 0.47316683562190887,
      "grad_norm": 0.3271577060222626,
      "learning_rate": 1.7387982104914844e-05,
      "loss": 0.4894,
      "step": 15403
    },
    {
      "epoch": 0.47319755475685804,
      "grad_norm": 0.3944144546985626,
      "learning_rate": 1.738765640278425e-05,
      "loss": 0.647,
      "step": 15404
    },
    {
      "epoch": 0.4732282738918072,
      "grad_norm": 0.33719468116760254,
      "learning_rate": 1.7387330683399268e-05,
      "loss": 0.4425,
      "step": 15405
    },
    {
      "epoch": 0.4732589930267564,
      "grad_norm": 0.31243443489074707,
      "learning_rate": 1.7387004946760657e-05,
      "loss": 0.5578,
      "step": 15406
    },
    {
      "epoch": 0.4732897121617055,
      "grad_norm": 0.35303404927253723,
      "learning_rate": 1.7386679192869182e-05,
      "loss": 0.5627,
      "step": 15407
    },
    {
      "epoch": 0.4733204312966547,
      "grad_norm": 0.36785897612571716,
      "learning_rate": 1.73863534217256e-05,
      "loss": 0.647,
      "step": 15408
    },
    {
      "epoch": 0.47335115043160386,
      "grad_norm": 0.377309113740921,
      "learning_rate": 1.7386027633330678e-05,
      "loss": 0.5362,
      "step": 15409
    },
    {
      "epoch": 0.473381869566553,
      "grad_norm": 0.4327535331249237,
      "learning_rate": 1.7385701827685168e-05,
      "loss": 0.5643,
      "step": 15410
    },
    {
      "epoch": 0.47341258870150216,
      "grad_norm": 0.37282103300094604,
      "learning_rate": 1.7385376004789838e-05,
      "loss": 0.59,
      "step": 15411
    },
    {
      "epoch": 0.47344330783645133,
      "grad_norm": 0.3619648516178131,
      "learning_rate": 1.7385050164645445e-05,
      "loss": 0.5509,
      "step": 15412
    },
    {
      "epoch": 0.4734740269714005,
      "grad_norm": 0.42223024368286133,
      "learning_rate": 1.7384724307252754e-05,
      "loss": 0.5923,
      "step": 15413
    },
    {
      "epoch": 0.4735047461063496,
      "grad_norm": 0.3543432354927063,
      "learning_rate": 1.738439843261252e-05,
      "loss": 0.6084,
      "step": 15414
    },
    {
      "epoch": 0.4735354652412988,
      "grad_norm": 0.34810566902160645,
      "learning_rate": 1.7384072540725513e-05,
      "loss": 0.5863,
      "step": 15415
    },
    {
      "epoch": 0.473566184376248,
      "grad_norm": 0.3524484634399414,
      "learning_rate": 1.7383746631592486e-05,
      "loss": 0.5153,
      "step": 15416
    },
    {
      "epoch": 0.4735969035111971,
      "grad_norm": 0.3708361089229584,
      "learning_rate": 1.7383420705214202e-05,
      "loss": 0.6095,
      "step": 15417
    },
    {
      "epoch": 0.4736276226461463,
      "grad_norm": 0.35317492485046387,
      "learning_rate": 1.7383094761591423e-05,
      "loss": 0.4745,
      "step": 15418
    },
    {
      "epoch": 0.47365834178109545,
      "grad_norm": 0.5683931708335876,
      "learning_rate": 1.738276880072491e-05,
      "loss": 0.567,
      "step": 15419
    },
    {
      "epoch": 0.4736890609160446,
      "grad_norm": 0.33836662769317627,
      "learning_rate": 1.7382442822615427e-05,
      "loss": 0.5194,
      "step": 15420
    },
    {
      "epoch": 0.47371978005099374,
      "grad_norm": 0.41718798875808716,
      "learning_rate": 1.738211682726373e-05,
      "loss": 0.5154,
      "step": 15421
    },
    {
      "epoch": 0.4737504991859429,
      "grad_norm": 0.3242138922214508,
      "learning_rate": 1.738179081467059e-05,
      "loss": 0.5382,
      "step": 15422
    },
    {
      "epoch": 0.4737812183208921,
      "grad_norm": 0.3555530309677124,
      "learning_rate": 1.738146478483676e-05,
      "loss": 0.5064,
      "step": 15423
    },
    {
      "epoch": 0.47381193745584127,
      "grad_norm": 0.32245007157325745,
      "learning_rate": 1.7381138737763003e-05,
      "loss": 0.5564,
      "step": 15424
    },
    {
      "epoch": 0.4738426565907904,
      "grad_norm": 0.33517858386039734,
      "learning_rate": 1.738081267345008e-05,
      "loss": 0.5411,
      "step": 15425
    },
    {
      "epoch": 0.47387337572573957,
      "grad_norm": 0.36820682883262634,
      "learning_rate": 1.7380486591898752e-05,
      "loss": 0.5689,
      "step": 15426
    },
    {
      "epoch": 0.47390409486068874,
      "grad_norm": 0.33861497044563293,
      "learning_rate": 1.7380160493109782e-05,
      "loss": 0.5269,
      "step": 15427
    },
    {
      "epoch": 0.47393481399563786,
      "grad_norm": 0.3603004813194275,
      "learning_rate": 1.7379834377083932e-05,
      "loss": 0.6129,
      "step": 15428
    },
    {
      "epoch": 0.47396553313058704,
      "grad_norm": 0.3664097487926483,
      "learning_rate": 1.7379508243821965e-05,
      "loss": 0.5917,
      "step": 15429
    },
    {
      "epoch": 0.4739962522655362,
      "grad_norm": 3.2881994247436523,
      "learning_rate": 1.737918209332464e-05,
      "loss": 0.6012,
      "step": 15430
    },
    {
      "epoch": 0.4740269714004854,
      "grad_norm": 0.31972256302833557,
      "learning_rate": 1.7378855925592723e-05,
      "loss": 0.5462,
      "step": 15431
    },
    {
      "epoch": 0.4740576905354345,
      "grad_norm": 0.3096390962600708,
      "learning_rate": 1.737852974062697e-05,
      "loss": 0.5317,
      "step": 15432
    },
    {
      "epoch": 0.4740884096703837,
      "grad_norm": 0.33041590452194214,
      "learning_rate": 1.7378203538428145e-05,
      "loss": 0.5623,
      "step": 15433
    },
    {
      "epoch": 0.47411912880533286,
      "grad_norm": 0.35450103878974915,
      "learning_rate": 1.7377877318997008e-05,
      "loss": 0.5921,
      "step": 15434
    },
    {
      "epoch": 0.474149847940282,
      "grad_norm": 0.35953226685523987,
      "learning_rate": 1.737755108233433e-05,
      "loss": 0.5699,
      "step": 15435
    },
    {
      "epoch": 0.47418056707523115,
      "grad_norm": 0.3646673560142517,
      "learning_rate": 1.7377224828440858e-05,
      "loss": 0.6024,
      "step": 15436
    },
    {
      "epoch": 0.4742112862101803,
      "grad_norm": 0.36138322949409485,
      "learning_rate": 1.737689855731737e-05,
      "loss": 0.5128,
      "step": 15437
    },
    {
      "epoch": 0.4742420053451295,
      "grad_norm": 0.35722148418426514,
      "learning_rate": 1.737657226896462e-05,
      "loss": 0.5279,
      "step": 15438
    },
    {
      "epoch": 0.4742727244800786,
      "grad_norm": 0.33894839882850647,
      "learning_rate": 1.7376245963383366e-05,
      "loss": 0.5808,
      "step": 15439
    },
    {
      "epoch": 0.4743034436150278,
      "grad_norm": 0.43053486943244934,
      "learning_rate": 1.737591964057437e-05,
      "loss": 0.5822,
      "step": 15440
    },
    {
      "epoch": 0.474334162749977,
      "grad_norm": 0.3565564453601837,
      "learning_rate": 1.737559330053841e-05,
      "loss": 0.5848,
      "step": 15441
    },
    {
      "epoch": 0.4743648818849261,
      "grad_norm": 0.3573339283466339,
      "learning_rate": 1.737526694327623e-05,
      "loss": 0.6071,
      "step": 15442
    },
    {
      "epoch": 0.47439560101987527,
      "grad_norm": 0.3496690094470978,
      "learning_rate": 1.73749405687886e-05,
      "loss": 0.5908,
      "step": 15443
    },
    {
      "epoch": 0.47442632015482444,
      "grad_norm": 0.3777221441268921,
      "learning_rate": 1.737461417707628e-05,
      "loss": 0.5115,
      "step": 15444
    },
    {
      "epoch": 0.4744570392897736,
      "grad_norm": 0.4103451669216156,
      "learning_rate": 1.7374287768140036e-05,
      "loss": 0.5845,
      "step": 15445
    },
    {
      "epoch": 0.47448775842472274,
      "grad_norm": 0.3451443612575531,
      "learning_rate": 1.7373961341980625e-05,
      "loss": 0.5935,
      "step": 15446
    },
    {
      "epoch": 0.4745184775596719,
      "grad_norm": 0.3928951323032379,
      "learning_rate": 1.7373634898598814e-05,
      "loss": 0.5371,
      "step": 15447
    },
    {
      "epoch": 0.4745491966946211,
      "grad_norm": 0.43516427278518677,
      "learning_rate": 1.737330843799536e-05,
      "loss": 0.5686,
      "step": 15448
    },
    {
      "epoch": 0.47457991582957026,
      "grad_norm": 0.3772067129611969,
      "learning_rate": 1.7372981960171036e-05,
      "loss": 0.6182,
      "step": 15449
    },
    {
      "epoch": 0.4746106349645194,
      "grad_norm": 0.44056281447410583,
      "learning_rate": 1.7372655465126595e-05,
      "loss": 0.6052,
      "step": 15450
    },
    {
      "epoch": 0.47464135409946856,
      "grad_norm": 0.3694130778312683,
      "learning_rate": 1.7372328952862802e-05,
      "loss": 0.55,
      "step": 15451
    },
    {
      "epoch": 0.47467207323441774,
      "grad_norm": 0.37444737553596497,
      "learning_rate": 1.7372002423380418e-05,
      "loss": 0.54,
      "step": 15452
    },
    {
      "epoch": 0.47470279236936685,
      "grad_norm": 0.34410399198532104,
      "learning_rate": 1.737167587668021e-05,
      "loss": 0.5607,
      "step": 15453
    },
    {
      "epoch": 0.47473351150431603,
      "grad_norm": 0.3485325574874878,
      "learning_rate": 1.7371349312762936e-05,
      "loss": 0.534,
      "step": 15454
    },
    {
      "epoch": 0.4747642306392652,
      "grad_norm": 0.31502020359039307,
      "learning_rate": 1.737102273162936e-05,
      "loss": 0.562,
      "step": 15455
    },
    {
      "epoch": 0.4747949497742144,
      "grad_norm": 0.3495251536369324,
      "learning_rate": 1.737069613328025e-05,
      "loss": 0.5428,
      "step": 15456
    },
    {
      "epoch": 0.4748256689091635,
      "grad_norm": 0.32383665442466736,
      "learning_rate": 1.7370369517716364e-05,
      "loss": 0.6065,
      "step": 15457
    },
    {
      "epoch": 0.4748563880441127,
      "grad_norm": 0.3613456189632416,
      "learning_rate": 1.7370042884938464e-05,
      "loss": 0.4792,
      "step": 15458
    },
    {
      "epoch": 0.47488710717906185,
      "grad_norm": 0.32448649406433105,
      "learning_rate": 1.736971623494731e-05,
      "loss": 0.5584,
      "step": 15459
    },
    {
      "epoch": 0.47491782631401097,
      "grad_norm": 0.3634085953235626,
      "learning_rate": 1.7369389567743674e-05,
      "loss": 0.6018,
      "step": 15460
    },
    {
      "epoch": 0.47494854544896015,
      "grad_norm": 0.3299083709716797,
      "learning_rate": 1.7369062883328315e-05,
      "loss": 0.5265,
      "step": 15461
    },
    {
      "epoch": 0.4749792645839093,
      "grad_norm": 0.3562838137149811,
      "learning_rate": 1.736873618170199e-05,
      "loss": 0.5947,
      "step": 15462
    },
    {
      "epoch": 0.4750099837188585,
      "grad_norm": 0.3531027138233185,
      "learning_rate": 1.736840946286547e-05,
      "loss": 0.5737,
      "step": 15463
    },
    {
      "epoch": 0.4750407028538076,
      "grad_norm": 0.3587208390235901,
      "learning_rate": 1.7368082726819512e-05,
      "loss": 0.5661,
      "step": 15464
    },
    {
      "epoch": 0.4750714219887568,
      "grad_norm": 0.34445270895957947,
      "learning_rate": 1.7367755973564887e-05,
      "loss": 0.5997,
      "step": 15465
    },
    {
      "epoch": 0.47510214112370597,
      "grad_norm": 0.3432323932647705,
      "learning_rate": 1.736742920310235e-05,
      "loss": 0.5105,
      "step": 15466
    },
    {
      "epoch": 0.47513286025865514,
      "grad_norm": 0.3533845841884613,
      "learning_rate": 1.736710241543267e-05,
      "loss": 0.6384,
      "step": 15467
    },
    {
      "epoch": 0.47516357939360426,
      "grad_norm": 0.4978148341178894,
      "learning_rate": 1.7366775610556608e-05,
      "loss": 0.6828,
      "step": 15468
    },
    {
      "epoch": 0.47519429852855344,
      "grad_norm": 0.3501807153224945,
      "learning_rate": 1.7366448788474925e-05,
      "loss": 0.5218,
      "step": 15469
    },
    {
      "epoch": 0.4752250176635026,
      "grad_norm": 0.3370748460292816,
      "learning_rate": 1.7366121949188387e-05,
      "loss": 0.5536,
      "step": 15470
    },
    {
      "epoch": 0.47525573679845173,
      "grad_norm": 0.3426799178123474,
      "learning_rate": 1.7365795092697756e-05,
      "loss": 0.4973,
      "step": 15471
    },
    {
      "epoch": 0.4752864559334009,
      "grad_norm": 0.33971211314201355,
      "learning_rate": 1.7365468219003795e-05,
      "loss": 0.528,
      "step": 15472
    },
    {
      "epoch": 0.4753171750683501,
      "grad_norm": 0.35255709290504456,
      "learning_rate": 1.736514132810727e-05,
      "loss": 0.5769,
      "step": 15473
    },
    {
      "epoch": 0.47534789420329926,
      "grad_norm": 0.6923590302467346,
      "learning_rate": 1.7364814420008946e-05,
      "loss": 0.5776,
      "step": 15474
    },
    {
      "epoch": 0.4753786133382484,
      "grad_norm": 0.32761672139167786,
      "learning_rate": 1.736448749470958e-05,
      "loss": 0.6439,
      "step": 15475
    },
    {
      "epoch": 0.47540933247319755,
      "grad_norm": 0.36152154207229614,
      "learning_rate": 1.7364160552209943e-05,
      "loss": 0.5368,
      "step": 15476
    },
    {
      "epoch": 0.47544005160814673,
      "grad_norm": 0.39028510451316833,
      "learning_rate": 1.7363833592510793e-05,
      "loss": 0.525,
      "step": 15477
    },
    {
      "epoch": 0.47547077074309585,
      "grad_norm": 0.3498074412345886,
      "learning_rate": 1.7363506615612894e-05,
      "loss": 0.586,
      "step": 15478
    },
    {
      "epoch": 0.475501489878045,
      "grad_norm": 0.3765280544757843,
      "learning_rate": 1.736317962151701e-05,
      "loss": 0.4832,
      "step": 15479
    },
    {
      "epoch": 0.4755322090129942,
      "grad_norm": 0.3340771794319153,
      "learning_rate": 1.7362852610223906e-05,
      "loss": 0.4542,
      "step": 15480
    },
    {
      "epoch": 0.4755629281479434,
      "grad_norm": 0.3544197082519531,
      "learning_rate": 1.7362525581734348e-05,
      "loss": 0.615,
      "step": 15481
    },
    {
      "epoch": 0.4755936472828925,
      "grad_norm": 0.44871070981025696,
      "learning_rate": 1.7362198536049096e-05,
      "loss": 0.6306,
      "step": 15482
    },
    {
      "epoch": 0.47562436641784167,
      "grad_norm": 0.33035537600517273,
      "learning_rate": 1.7361871473168913e-05,
      "loss": 0.5436,
      "step": 15483
    },
    {
      "epoch": 0.47565508555279085,
      "grad_norm": 0.4565214216709137,
      "learning_rate": 1.736154439309457e-05,
      "loss": 0.4984,
      "step": 15484
    },
    {
      "epoch": 0.47568580468773997,
      "grad_norm": 0.4872463345527649,
      "learning_rate": 1.736121729582682e-05,
      "loss": 0.6539,
      "step": 15485
    },
    {
      "epoch": 0.47571652382268914,
      "grad_norm": 0.3396097421646118,
      "learning_rate": 1.7360890181366438e-05,
      "loss": 0.4875,
      "step": 15486
    },
    {
      "epoch": 0.4757472429576383,
      "grad_norm": 0.3498178720474243,
      "learning_rate": 1.736056304971418e-05,
      "loss": 0.5335,
      "step": 15487
    },
    {
      "epoch": 0.4757779620925875,
      "grad_norm": 0.3377169966697693,
      "learning_rate": 1.7360235900870815e-05,
      "loss": 0.6058,
      "step": 15488
    },
    {
      "epoch": 0.4758086812275366,
      "grad_norm": 0.341140478849411,
      "learning_rate": 1.7359908734837106e-05,
      "loss": 0.6038,
      "step": 15489
    },
    {
      "epoch": 0.4758394003624858,
      "grad_norm": 0.3533953130245209,
      "learning_rate": 1.7359581551613812e-05,
      "loss": 0.4922,
      "step": 15490
    },
    {
      "epoch": 0.47587011949743496,
      "grad_norm": 0.37248048186302185,
      "learning_rate": 1.7359254351201702e-05,
      "loss": 0.6141,
      "step": 15491
    },
    {
      "epoch": 0.47590083863238414,
      "grad_norm": 0.3305078446865082,
      "learning_rate": 1.7358927133601542e-05,
      "loss": 0.5955,
      "step": 15492
    },
    {
      "epoch": 0.47593155776733326,
      "grad_norm": 0.385486364364624,
      "learning_rate": 1.735859989881409e-05,
      "loss": 0.5165,
      "step": 15493
    },
    {
      "epoch": 0.47596227690228243,
      "grad_norm": 0.3364427089691162,
      "learning_rate": 1.7358272646840118e-05,
      "loss": 0.5742,
      "step": 15494
    },
    {
      "epoch": 0.4759929960372316,
      "grad_norm": 0.36814379692077637,
      "learning_rate": 1.7357945377680385e-05,
      "loss": 0.5584,
      "step": 15495
    },
    {
      "epoch": 0.47602371517218073,
      "grad_norm": 0.32925596833229065,
      "learning_rate": 1.7357618091335658e-05,
      "loss": 0.5296,
      "step": 15496
    },
    {
      "epoch": 0.4760544343071299,
      "grad_norm": 0.35337576270103455,
      "learning_rate": 1.73572907878067e-05,
      "loss": 0.5746,
      "step": 15497
    },
    {
      "epoch": 0.4760851534420791,
      "grad_norm": 0.37300413846969604,
      "learning_rate": 1.735696346709427e-05,
      "loss": 0.6244,
      "step": 15498
    },
    {
      "epoch": 0.47611587257702825,
      "grad_norm": 0.36432334780693054,
      "learning_rate": 1.7356636129199146e-05,
      "loss": 0.4879,
      "step": 15499
    },
    {
      "epoch": 0.4761465917119774,
      "grad_norm": 0.3723975419998169,
      "learning_rate": 1.735630877412208e-05,
      "loss": 0.591,
      "step": 15500
    },
    {
      "epoch": 0.47617731084692655,
      "grad_norm": 0.33878466486930847,
      "learning_rate": 1.735598140186384e-05,
      "loss": 0.5512,
      "step": 15501
    },
    {
      "epoch": 0.4762080299818757,
      "grad_norm": 0.3155069649219513,
      "learning_rate": 1.7355654012425195e-05,
      "loss": 0.4979,
      "step": 15502
    },
    {
      "epoch": 0.47623874911682484,
      "grad_norm": 0.3724271357059479,
      "learning_rate": 1.7355326605806903e-05,
      "loss": 0.4522,
      "step": 15503
    },
    {
      "epoch": 0.476269468251774,
      "grad_norm": 0.41059738397598267,
      "learning_rate": 1.7354999182009735e-05,
      "loss": 0.6705,
      "step": 15504
    },
    {
      "epoch": 0.4763001873867232,
      "grad_norm": 0.34528741240501404,
      "learning_rate": 1.7354671741034454e-05,
      "loss": 0.5977,
      "step": 15505
    },
    {
      "epoch": 0.47633090652167237,
      "grad_norm": 0.37746959924697876,
      "learning_rate": 1.735434428288182e-05,
      "loss": 0.5277,
      "step": 15506
    },
    {
      "epoch": 0.4763616256566215,
      "grad_norm": 0.3260432779788971,
      "learning_rate": 1.7354016807552603e-05,
      "loss": 0.5848,
      "step": 15507
    },
    {
      "epoch": 0.47639234479157067,
      "grad_norm": 0.4086877107620239,
      "learning_rate": 1.7353689315047565e-05,
      "loss": 0.5444,
      "step": 15508
    },
    {
      "epoch": 0.47642306392651984,
      "grad_norm": 0.32031816244125366,
      "learning_rate": 1.7353361805367473e-05,
      "loss": 0.4838,
      "step": 15509
    },
    {
      "epoch": 0.476453783061469,
      "grad_norm": 0.30442360043525696,
      "learning_rate": 1.735303427851309e-05,
      "loss": 0.5809,
      "step": 15510
    },
    {
      "epoch": 0.47648450219641814,
      "grad_norm": 0.32364585995674133,
      "learning_rate": 1.7352706734485183e-05,
      "loss": 0.642,
      "step": 15511
    },
    {
      "epoch": 0.4765152213313673,
      "grad_norm": 0.3506607413291931,
      "learning_rate": 1.7352379173284516e-05,
      "loss": 0.5361,
      "step": 15512
    },
    {
      "epoch": 0.4765459404663165,
      "grad_norm": 0.3446476459503174,
      "learning_rate": 1.735205159491185e-05,
      "loss": 0.5515,
      "step": 15513
    },
    {
      "epoch": 0.4765766596012656,
      "grad_norm": 0.36923685669898987,
      "learning_rate": 1.735172399936796e-05,
      "loss": 0.5728,
      "step": 15514
    },
    {
      "epoch": 0.4766073787362148,
      "grad_norm": 0.3805038034915924,
      "learning_rate": 1.73513963866536e-05,
      "loss": 0.5902,
      "step": 15515
    },
    {
      "epoch": 0.47663809787116396,
      "grad_norm": 0.4298056662082672,
      "learning_rate": 1.7351068756769545e-05,
      "loss": 0.5331,
      "step": 15516
    },
    {
      "epoch": 0.47666881700611313,
      "grad_norm": 0.40244024991989136,
      "learning_rate": 1.7350741109716552e-05,
      "loss": 0.6518,
      "step": 15517
    },
    {
      "epoch": 0.47669953614106225,
      "grad_norm": 0.4099474251270294,
      "learning_rate": 1.735041344549539e-05,
      "loss": 0.5545,
      "step": 15518
    },
    {
      "epoch": 0.4767302552760114,
      "grad_norm": 0.36238330602645874,
      "learning_rate": 1.7350085764106827e-05,
      "loss": 0.5716,
      "step": 15519
    },
    {
      "epoch": 0.4767609744109606,
      "grad_norm": 0.34830427169799805,
      "learning_rate": 1.7349758065551622e-05,
      "loss": 0.5524,
      "step": 15520
    },
    {
      "epoch": 0.4767916935459097,
      "grad_norm": 0.35460561513900757,
      "learning_rate": 1.7349430349830546e-05,
      "loss": 0.533,
      "step": 15521
    },
    {
      "epoch": 0.4768224126808589,
      "grad_norm": 0.7615846991539001,
      "learning_rate": 1.7349102616944364e-05,
      "loss": 0.5596,
      "step": 15522
    },
    {
      "epoch": 0.4768531318158081,
      "grad_norm": 0.35641202330589294,
      "learning_rate": 1.7348774866893835e-05,
      "loss": 0.5862,
      "step": 15523
    },
    {
      "epoch": 0.47688385095075725,
      "grad_norm": 0.356607586145401,
      "learning_rate": 1.7348447099679732e-05,
      "loss": 0.6011,
      "step": 15524
    },
    {
      "epoch": 0.47691457008570637,
      "grad_norm": 0.39400485157966614,
      "learning_rate": 1.7348119315302817e-05,
      "loss": 0.5555,
      "step": 15525
    },
    {
      "epoch": 0.47694528922065554,
      "grad_norm": 0.33883944153785706,
      "learning_rate": 1.7347791513763855e-05,
      "loss": 0.5038,
      "step": 15526
    },
    {
      "epoch": 0.4769760083556047,
      "grad_norm": 0.32018017768859863,
      "learning_rate": 1.7347463695063617e-05,
      "loss": 0.503,
      "step": 15527
    },
    {
      "epoch": 0.47700672749055384,
      "grad_norm": 0.3719457685947418,
      "learning_rate": 1.734713585920286e-05,
      "loss": 0.6017,
      "step": 15528
    },
    {
      "epoch": 0.477037446625503,
      "grad_norm": 0.35656479001045227,
      "learning_rate": 1.7346808006182354e-05,
      "loss": 0.5756,
      "step": 15529
    },
    {
      "epoch": 0.4770681657604522,
      "grad_norm": 0.36224791407585144,
      "learning_rate": 1.7346480136002865e-05,
      "loss": 0.5556,
      "step": 15530
    },
    {
      "epoch": 0.47709888489540137,
      "grad_norm": 0.3198019862174988,
      "learning_rate": 1.734615224866516e-05,
      "loss": 0.5666,
      "step": 15531
    },
    {
      "epoch": 0.4771296040303505,
      "grad_norm": 0.3308795392513275,
      "learning_rate": 1.7345824344170003e-05,
      "loss": 0.4819,
      "step": 15532
    },
    {
      "epoch": 0.47716032316529966,
      "grad_norm": 0.39748963713645935,
      "learning_rate": 1.734549642251816e-05,
      "loss": 0.5292,
      "step": 15533
    },
    {
      "epoch": 0.47719104230024884,
      "grad_norm": 0.3615792989730835,
      "learning_rate": 1.7345168483710396e-05,
      "loss": 0.6319,
      "step": 15534
    },
    {
      "epoch": 0.477221761435198,
      "grad_norm": 0.34500452876091003,
      "learning_rate": 1.734484052774748e-05,
      "loss": 0.5686,
      "step": 15535
    },
    {
      "epoch": 0.47725248057014713,
      "grad_norm": 0.32462650537490845,
      "learning_rate": 1.7344512554630177e-05,
      "loss": 0.5136,
      "step": 15536
    },
    {
      "epoch": 0.4772831997050963,
      "grad_norm": 0.6345045566558838,
      "learning_rate": 1.734418456435925e-05,
      "loss": 0.5988,
      "step": 15537
    },
    {
      "epoch": 0.4773139188400455,
      "grad_norm": 0.317025750875473,
      "learning_rate": 1.7343856556935467e-05,
      "loss": 0.5295,
      "step": 15538
    },
    {
      "epoch": 0.4773446379749946,
      "grad_norm": 0.32173606753349304,
      "learning_rate": 1.734352853235959e-05,
      "loss": 0.5458,
      "step": 15539
    },
    {
      "epoch": 0.4773753571099438,
      "grad_norm": 0.33228832483291626,
      "learning_rate": 1.7343200490632397e-05,
      "loss": 0.5765,
      "step": 15540
    },
    {
      "epoch": 0.47740607624489295,
      "grad_norm": 0.33370694518089294,
      "learning_rate": 1.7342872431754645e-05,
      "loss": 0.4812,
      "step": 15541
    },
    {
      "epoch": 0.4774367953798421,
      "grad_norm": 0.3632431626319885,
      "learning_rate": 1.73425443557271e-05,
      "loss": 0.5558,
      "step": 15542
    },
    {
      "epoch": 0.47746751451479125,
      "grad_norm": 0.3835834860801697,
      "learning_rate": 1.7342216262550525e-05,
      "loss": 0.5274,
      "step": 15543
    },
    {
      "epoch": 0.4774982336497404,
      "grad_norm": 0.34986671805381775,
      "learning_rate": 1.73418881522257e-05,
      "loss": 0.63,
      "step": 15544
    },
    {
      "epoch": 0.4775289527846896,
      "grad_norm": 0.4356629550457001,
      "learning_rate": 1.7341560024753376e-05,
      "loss": 0.614,
      "step": 15545
    },
    {
      "epoch": 0.4775596719196387,
      "grad_norm": 0.36890482902526855,
      "learning_rate": 1.7341231880134328e-05,
      "loss": 0.5676,
      "step": 15546
    },
    {
      "epoch": 0.4775903910545879,
      "grad_norm": 0.36310893297195435,
      "learning_rate": 1.734090371836932e-05,
      "loss": 0.5643,
      "step": 15547
    },
    {
      "epoch": 0.47762111018953707,
      "grad_norm": 0.3365352749824524,
      "learning_rate": 1.734057553945912e-05,
      "loss": 0.6023,
      "step": 15548
    },
    {
      "epoch": 0.47765182932448624,
      "grad_norm": 0.34148409962654114,
      "learning_rate": 1.7340247343404493e-05,
      "loss": 0.5787,
      "step": 15549
    },
    {
      "epoch": 0.47768254845943536,
      "grad_norm": 0.42471635341644287,
      "learning_rate": 1.73399191302062e-05,
      "loss": 0.5867,
      "step": 15550
    },
    {
      "epoch": 0.47771326759438454,
      "grad_norm": 0.40844249725341797,
      "learning_rate": 1.7339590899865023e-05,
      "loss": 0.5728,
      "step": 15551
    },
    {
      "epoch": 0.4777439867293337,
      "grad_norm": 0.36694976687431335,
      "learning_rate": 1.733926265238171e-05,
      "loss": 0.6207,
      "step": 15552
    },
    {
      "epoch": 0.4777747058642829,
      "grad_norm": 0.35196033120155334,
      "learning_rate": 1.7338934387757044e-05,
      "loss": 0.5868,
      "step": 15553
    },
    {
      "epoch": 0.477805424999232,
      "grad_norm": 0.33903130888938904,
      "learning_rate": 1.733860610599178e-05,
      "loss": 0.5904,
      "step": 15554
    },
    {
      "epoch": 0.4778361441341812,
      "grad_norm": 0.3848533630371094,
      "learning_rate": 1.7338277807086687e-05,
      "loss": 0.5236,
      "step": 15555
    },
    {
      "epoch": 0.47786686326913036,
      "grad_norm": 0.355689138174057,
      "learning_rate": 1.733794949104254e-05,
      "loss": 0.5313,
      "step": 15556
    },
    {
      "epoch": 0.4778975824040795,
      "grad_norm": 0.3349611163139343,
      "learning_rate": 1.7337621157860093e-05,
      "loss": 0.5969,
      "step": 15557
    },
    {
      "epoch": 0.47792830153902865,
      "grad_norm": 0.3639744520187378,
      "learning_rate": 1.7337292807540123e-05,
      "loss": 0.6318,
      "step": 15558
    },
    {
      "epoch": 0.47795902067397783,
      "grad_norm": 0.3650461733341217,
      "learning_rate": 1.7336964440083393e-05,
      "loss": 0.5988,
      "step": 15559
    },
    {
      "epoch": 0.477989739808927,
      "grad_norm": 0.3726778030395508,
      "learning_rate": 1.7336636055490668e-05,
      "loss": 0.5469,
      "step": 15560
    },
    {
      "epoch": 0.4780204589438761,
      "grad_norm": 0.33550629019737244,
      "learning_rate": 1.7336307653762717e-05,
      "loss": 0.5445,
      "step": 15561
    },
    {
      "epoch": 0.4780511780788253,
      "grad_norm": 0.36267101764678955,
      "learning_rate": 1.733597923490031e-05,
      "loss": 0.663,
      "step": 15562
    },
    {
      "epoch": 0.4780818972137745,
      "grad_norm": 0.3375217616558075,
      "learning_rate": 1.733565079890421e-05,
      "loss": 0.6398,
      "step": 15563
    },
    {
      "epoch": 0.4781126163487236,
      "grad_norm": 0.3433980643749237,
      "learning_rate": 1.7335322345775187e-05,
      "loss": 0.4885,
      "step": 15564
    },
    {
      "epoch": 0.47814333548367277,
      "grad_norm": 0.3828219473361969,
      "learning_rate": 1.7334993875514e-05,
      "loss": 0.6184,
      "step": 15565
    },
    {
      "epoch": 0.47817405461862195,
      "grad_norm": 0.4106205701828003,
      "learning_rate": 1.733466538812143e-05,
      "loss": 0.6139,
      "step": 15566
    },
    {
      "epoch": 0.4782047737535711,
      "grad_norm": 0.3172977864742279,
      "learning_rate": 1.7334336883598234e-05,
      "loss": 0.5434,
      "step": 15567
    },
    {
      "epoch": 0.47823549288852024,
      "grad_norm": 0.36794474720954895,
      "learning_rate": 1.733400836194518e-05,
      "loss": 0.5874,
      "step": 15568
    },
    {
      "epoch": 0.4782662120234694,
      "grad_norm": 0.31145453453063965,
      "learning_rate": 1.733367982316304e-05,
      "loss": 0.4875,
      "step": 15569
    },
    {
      "epoch": 0.4782969311584186,
      "grad_norm": 0.3452140986919403,
      "learning_rate": 1.7333351267252574e-05,
      "loss": 0.5303,
      "step": 15570
    },
    {
      "epoch": 0.4783276502933677,
      "grad_norm": 0.3451298177242279,
      "learning_rate": 1.733302269421456e-05,
      "loss": 0.5658,
      "step": 15571
    },
    {
      "epoch": 0.4783583694283169,
      "grad_norm": 0.31771114468574524,
      "learning_rate": 1.7332694104049755e-05,
      "loss": 0.5669,
      "step": 15572
    },
    {
      "epoch": 0.47838908856326606,
      "grad_norm": 0.3339412808418274,
      "learning_rate": 1.7332365496758933e-05,
      "loss": 0.5252,
      "step": 15573
    },
    {
      "epoch": 0.47841980769821524,
      "grad_norm": 0.3589840829372406,
      "learning_rate": 1.7332036872342862e-05,
      "loss": 0.5849,
      "step": 15574
    },
    {
      "epoch": 0.47845052683316436,
      "grad_norm": 0.34008628129959106,
      "learning_rate": 1.7331708230802303e-05,
      "loss": 0.5053,
      "step": 15575
    },
    {
      "epoch": 0.47848124596811353,
      "grad_norm": 0.339419424533844,
      "learning_rate": 1.7331379572138027e-05,
      "loss": 0.5722,
      "step": 15576
    },
    {
      "epoch": 0.4785119651030627,
      "grad_norm": 0.3015213906764984,
      "learning_rate": 1.7331050896350804e-05,
      "loss": 0.5297,
      "step": 15577
    },
    {
      "epoch": 0.4785426842380119,
      "grad_norm": 0.36969149112701416,
      "learning_rate": 1.73307222034414e-05,
      "loss": 0.5679,
      "step": 15578
    },
    {
      "epoch": 0.478573403372961,
      "grad_norm": 0.33238035440444946,
      "learning_rate": 1.7330393493410576e-05,
      "loss": 0.5208,
      "step": 15579
    },
    {
      "epoch": 0.4786041225079102,
      "grad_norm": 0.42245933413505554,
      "learning_rate": 1.7330064766259113e-05,
      "loss": 0.6127,
      "step": 15580
    },
    {
      "epoch": 0.47863484164285935,
      "grad_norm": 0.3486548662185669,
      "learning_rate": 1.7329736021987772e-05,
      "loss": 0.5675,
      "step": 15581
    },
    {
      "epoch": 0.4786655607778085,
      "grad_norm": 0.3555736243724823,
      "learning_rate": 1.7329407260597316e-05,
      "loss": 0.5216,
      "step": 15582
    },
    {
      "epoch": 0.47869627991275765,
      "grad_norm": 0.35806798934936523,
      "learning_rate": 1.732907848208852e-05,
      "loss": 0.5915,
      "step": 15583
    },
    {
      "epoch": 0.4787269990477068,
      "grad_norm": 0.4145442843437195,
      "learning_rate": 1.732874968646215e-05,
      "loss": 0.6514,
      "step": 15584
    },
    {
      "epoch": 0.478757718182656,
      "grad_norm": 0.3206360638141632,
      "learning_rate": 1.732842087371897e-05,
      "loss": 0.5593,
      "step": 15585
    },
    {
      "epoch": 0.4787884373176051,
      "grad_norm": 0.3387293517589569,
      "learning_rate": 1.7328092043859758e-05,
      "loss": 0.5423,
      "step": 15586
    },
    {
      "epoch": 0.4788191564525543,
      "grad_norm": 0.3330969214439392,
      "learning_rate": 1.732776319688527e-05,
      "loss": 0.5814,
      "step": 15587
    },
    {
      "epoch": 0.47884987558750347,
      "grad_norm": 0.36168035864830017,
      "learning_rate": 1.732743433279628e-05,
      "loss": 0.5738,
      "step": 15588
    },
    {
      "epoch": 0.4788805947224526,
      "grad_norm": 0.35744935274124146,
      "learning_rate": 1.7327105451593555e-05,
      "loss": 0.5268,
      "step": 15589
    },
    {
      "epoch": 0.47891131385740177,
      "grad_norm": 0.34030646085739136,
      "learning_rate": 1.7326776553277868e-05,
      "loss": 0.515,
      "step": 15590
    },
    {
      "epoch": 0.47894203299235094,
      "grad_norm": 0.4648550748825073,
      "learning_rate": 1.7326447637849978e-05,
      "loss": 0.559,
      "step": 15591
    },
    {
      "epoch": 0.4789727521273001,
      "grad_norm": 0.34286704659461975,
      "learning_rate": 1.7326118705310657e-05,
      "loss": 0.5494,
      "step": 15592
    },
    {
      "epoch": 0.47900347126224924,
      "grad_norm": 0.32803720235824585,
      "learning_rate": 1.7325789755660677e-05,
      "loss": 0.5424,
      "step": 15593
    },
    {
      "epoch": 0.4790341903971984,
      "grad_norm": 0.35223308205604553,
      "learning_rate": 1.73254607889008e-05,
      "loss": 0.5252,
      "step": 15594
    },
    {
      "epoch": 0.4790649095321476,
      "grad_norm": 0.39793962240219116,
      "learning_rate": 1.73251318050318e-05,
      "loss": 0.5671,
      "step": 15595
    },
    {
      "epoch": 0.4790956286670967,
      "grad_norm": 0.3672584295272827,
      "learning_rate": 1.7324802804054447e-05,
      "loss": 0.5433,
      "step": 15596
    },
    {
      "epoch": 0.4791263478020459,
      "grad_norm": 0.3914015293121338,
      "learning_rate": 1.73244737859695e-05,
      "loss": 0.5224,
      "step": 15597
    },
    {
      "epoch": 0.47915706693699506,
      "grad_norm": 0.3070962131023407,
      "learning_rate": 1.7324144750777735e-05,
      "loss": 0.5346,
      "step": 15598
    },
    {
      "epoch": 0.47918778607194423,
      "grad_norm": 0.3557225167751312,
      "learning_rate": 1.732381569847992e-05,
      "loss": 0.6141,
      "step": 15599
    },
    {
      "epoch": 0.47921850520689335,
      "grad_norm": 0.3362705409526825,
      "learning_rate": 1.7323486629076817e-05,
      "loss": 0.5333,
      "step": 15600
    },
    {
      "epoch": 0.47924922434184253,
      "grad_norm": 0.3504515588283539,
      "learning_rate": 1.7323157542569204e-05,
      "loss": 0.5322,
      "step": 15601
    },
    {
      "epoch": 0.4792799434767917,
      "grad_norm": 0.35242152214050293,
      "learning_rate": 1.7322828438957843e-05,
      "loss": 0.539,
      "step": 15602
    },
    {
      "epoch": 0.4793106626117409,
      "grad_norm": 0.3624297082424164,
      "learning_rate": 1.73224993182435e-05,
      "loss": 0.5646,
      "step": 15603
    },
    {
      "epoch": 0.47934138174669,
      "grad_norm": 0.33676859736442566,
      "learning_rate": 1.732217018042696e-05,
      "loss": 0.5818,
      "step": 15604
    },
    {
      "epoch": 0.4793721008816392,
      "grad_norm": 0.3213867247104645,
      "learning_rate": 1.732184102550897e-05,
      "loss": 0.5668,
      "step": 15605
    },
    {
      "epoch": 0.47940282001658835,
      "grad_norm": 0.3640679717063904,
      "learning_rate": 1.7321511853490313e-05,
      "loss": 0.5232,
      "step": 15606
    },
    {
      "epoch": 0.47943353915153747,
      "grad_norm": 2.695023775100708,
      "learning_rate": 1.7321182664371753e-05,
      "loss": 0.5115,
      "step": 15607
    },
    {
      "epoch": 0.47946425828648664,
      "grad_norm": 0.34890151023864746,
      "learning_rate": 1.7320853458154063e-05,
      "loss": 0.7063,
      "step": 15608
    },
    {
      "epoch": 0.4794949774214358,
      "grad_norm": 0.5789188742637634,
      "learning_rate": 1.7320524234838004e-05,
      "loss": 0.5945,
      "step": 15609
    },
    {
      "epoch": 0.479525696556385,
      "grad_norm": 0.3746485114097595,
      "learning_rate": 1.732019499442435e-05,
      "loss": 0.6292,
      "step": 15610
    },
    {
      "epoch": 0.4795564156913341,
      "grad_norm": 0.3128478527069092,
      "learning_rate": 1.731986573691387e-05,
      "loss": 0.5149,
      "step": 15611
    },
    {
      "epoch": 0.4795871348262833,
      "grad_norm": 0.3518771529197693,
      "learning_rate": 1.7319536462307334e-05,
      "loss": 0.5543,
      "step": 15612
    },
    {
      "epoch": 0.47961785396123247,
      "grad_norm": 0.35659435391426086,
      "learning_rate": 1.7319207170605508e-05,
      "loss": 0.5237,
      "step": 15613
    },
    {
      "epoch": 0.4796485730961816,
      "grad_norm": 0.3587920665740967,
      "learning_rate": 1.7318877861809164e-05,
      "loss": 0.5303,
      "step": 15614
    },
    {
      "epoch": 0.47967929223113076,
      "grad_norm": 0.42373526096343994,
      "learning_rate": 1.731854853591907e-05,
      "loss": 0.5338,
      "step": 15615
    },
    {
      "epoch": 0.47971001136607994,
      "grad_norm": 0.38490405678749084,
      "learning_rate": 1.731821919293599e-05,
      "loss": 0.5507,
      "step": 15616
    },
    {
      "epoch": 0.4797407305010291,
      "grad_norm": 0.32971012592315674,
      "learning_rate": 1.7317889832860703e-05,
      "loss": 0.6029,
      "step": 15617
    },
    {
      "epoch": 0.47977144963597823,
      "grad_norm": 0.3246597349643707,
      "learning_rate": 1.731756045569397e-05,
      "loss": 0.5256,
      "step": 15618
    },
    {
      "epoch": 0.4798021687709274,
      "grad_norm": 0.3797847032546997,
      "learning_rate": 1.7317231061436562e-05,
      "loss": 0.6221,
      "step": 15619
    },
    {
      "epoch": 0.4798328879058766,
      "grad_norm": 0.35837382078170776,
      "learning_rate": 1.7316901650089255e-05,
      "loss": 0.5673,
      "step": 15620
    },
    {
      "epoch": 0.47986360704082576,
      "grad_norm": 0.35814476013183594,
      "learning_rate": 1.731657222165281e-05,
      "loss": 0.5321,
      "step": 15621
    },
    {
      "epoch": 0.4798943261757749,
      "grad_norm": 0.37409883737564087,
      "learning_rate": 1.7316242776128e-05,
      "loss": 0.584,
      "step": 15622
    },
    {
      "epoch": 0.47992504531072405,
      "grad_norm": 0.3886256515979767,
      "learning_rate": 1.7315913313515595e-05,
      "loss": 0.5904,
      "step": 15623
    },
    {
      "epoch": 0.4799557644456732,
      "grad_norm": 0.3207681179046631,
      "learning_rate": 1.7315583833816364e-05,
      "loss": 0.5696,
      "step": 15624
    },
    {
      "epoch": 0.47998648358062235,
      "grad_norm": 0.46518924832344055,
      "learning_rate": 1.7315254337031073e-05,
      "loss": 0.682,
      "step": 15625
    },
    {
      "epoch": 0.4800172027155715,
      "grad_norm": 0.31617146730422974,
      "learning_rate": 1.7314924823160497e-05,
      "loss": 0.5584,
      "step": 15626
    },
    {
      "epoch": 0.4800479218505207,
      "grad_norm": 0.3801088333129883,
      "learning_rate": 1.7314595292205406e-05,
      "loss": 0.5757,
      "step": 15627
    },
    {
      "epoch": 0.4800786409854699,
      "grad_norm": 0.32563695311546326,
      "learning_rate": 1.731426574416656e-05,
      "loss": 0.5555,
      "step": 15628
    },
    {
      "epoch": 0.480109360120419,
      "grad_norm": 0.33472543954849243,
      "learning_rate": 1.731393617904474e-05,
      "loss": 0.4885,
      "step": 15629
    },
    {
      "epoch": 0.48014007925536817,
      "grad_norm": 0.3942820131778717,
      "learning_rate": 1.7313606596840712e-05,
      "loss": 0.646,
      "step": 15630
    },
    {
      "epoch": 0.48017079839031734,
      "grad_norm": 0.4719225764274597,
      "learning_rate": 1.7313276997555242e-05,
      "loss": 0.5954,
      "step": 15631
    },
    {
      "epoch": 0.48020151752526646,
      "grad_norm": 0.3505592346191406,
      "learning_rate": 1.7312947381189102e-05,
      "loss": 0.5503,
      "step": 15632
    },
    {
      "epoch": 0.48023223666021564,
      "grad_norm": 0.34374257922172546,
      "learning_rate": 1.7312617747743065e-05,
      "loss": 0.4728,
      "step": 15633
    },
    {
      "epoch": 0.4802629557951648,
      "grad_norm": 0.41130590438842773,
      "learning_rate": 1.73122880972179e-05,
      "loss": 0.6454,
      "step": 15634
    },
    {
      "epoch": 0.480293674930114,
      "grad_norm": 0.3677595555782318,
      "learning_rate": 1.7311958429614374e-05,
      "loss": 0.5642,
      "step": 15635
    },
    {
      "epoch": 0.4803243940650631,
      "grad_norm": 0.40935736894607544,
      "learning_rate": 1.7311628744933258e-05,
      "loss": 0.5125,
      "step": 15636
    },
    {
      "epoch": 0.4803551132000123,
      "grad_norm": 0.36335334181785583,
      "learning_rate": 1.731129904317532e-05,
      "loss": 0.6007,
      "step": 15637
    },
    {
      "epoch": 0.48038583233496146,
      "grad_norm": 0.32127419114112854,
      "learning_rate": 1.731096932434134e-05,
      "loss": 0.5481,
      "step": 15638
    },
    {
      "epoch": 0.4804165514699106,
      "grad_norm": 0.3516536355018616,
      "learning_rate": 1.7310639588432074e-05,
      "loss": 0.5392,
      "step": 15639
    },
    {
      "epoch": 0.48044727060485976,
      "grad_norm": 0.36510005593299866,
      "learning_rate": 1.7310309835448302e-05,
      "loss": 0.6244,
      "step": 15640
    },
    {
      "epoch": 0.48047798973980893,
      "grad_norm": 0.3016154170036316,
      "learning_rate": 1.7309980065390788e-05,
      "loss": 0.5196,
      "step": 15641
    },
    {
      "epoch": 0.4805087088747581,
      "grad_norm": 0.33173680305480957,
      "learning_rate": 1.7309650278260306e-05,
      "loss": 0.5837,
      "step": 15642
    },
    {
      "epoch": 0.4805394280097072,
      "grad_norm": 0.34379899501800537,
      "learning_rate": 1.7309320474057627e-05,
      "loss": 0.6197,
      "step": 15643
    },
    {
      "epoch": 0.4805701471446564,
      "grad_norm": 0.33790817856788635,
      "learning_rate": 1.7308990652783518e-05,
      "loss": 0.5661,
      "step": 15644
    },
    {
      "epoch": 0.4806008662796056,
      "grad_norm": 0.4911993443965912,
      "learning_rate": 1.730866081443875e-05,
      "loss": 0.5832,
      "step": 15645
    },
    {
      "epoch": 0.48063158541455475,
      "grad_norm": 0.39675939083099365,
      "learning_rate": 1.7308330959024093e-05,
      "loss": 0.6151,
      "step": 15646
    },
    {
      "epoch": 0.48066230454950387,
      "grad_norm": 0.3755030930042267,
      "learning_rate": 1.730800108654032e-05,
      "loss": 0.5576,
      "step": 15647
    },
    {
      "epoch": 0.48069302368445305,
      "grad_norm": 0.32469770312309265,
      "learning_rate": 1.7307671196988202e-05,
      "loss": 0.5801,
      "step": 15648
    },
    {
      "epoch": 0.4807237428194022,
      "grad_norm": 0.37333357334136963,
      "learning_rate": 1.7307341290368507e-05,
      "loss": 0.5473,
      "step": 15649
    },
    {
      "epoch": 0.48075446195435134,
      "grad_norm": 0.33648401498794556,
      "learning_rate": 1.730701136668201e-05,
      "loss": 0.504,
      "step": 15650
    },
    {
      "epoch": 0.4807851810893005,
      "grad_norm": 0.36116909980773926,
      "learning_rate": 1.730668142592947e-05,
      "loss": 0.6167,
      "step": 15651
    },
    {
      "epoch": 0.4808159002242497,
      "grad_norm": 0.3578149974346161,
      "learning_rate": 1.7306351468111667e-05,
      "loss": 0.6443,
      "step": 15652
    },
    {
      "epoch": 0.48084661935919887,
      "grad_norm": 0.32502132654190063,
      "learning_rate": 1.7306021493229373e-05,
      "loss": 0.566,
      "step": 15653
    },
    {
      "epoch": 0.480877338494148,
      "grad_norm": 0.32410433888435364,
      "learning_rate": 1.7305691501283353e-05,
      "loss": 0.4995,
      "step": 15654
    },
    {
      "epoch": 0.48090805762909716,
      "grad_norm": 0.33389967679977417,
      "learning_rate": 1.730536149227438e-05,
      "loss": 0.5578,
      "step": 15655
    },
    {
      "epoch": 0.48093877676404634,
      "grad_norm": 0.3605579435825348,
      "learning_rate": 1.7305031466203227e-05,
      "loss": 0.6456,
      "step": 15656
    },
    {
      "epoch": 0.48096949589899546,
      "grad_norm": 0.33562013506889343,
      "learning_rate": 1.7304701423070663e-05,
      "loss": 0.5362,
      "step": 15657
    },
    {
      "epoch": 0.48100021503394463,
      "grad_norm": 0.4555802643299103,
      "learning_rate": 1.7304371362877457e-05,
      "loss": 0.5913,
      "step": 15658
    },
    {
      "epoch": 0.4810309341688938,
      "grad_norm": 0.3416529595851898,
      "learning_rate": 1.7304041285624383e-05,
      "loss": 0.5352,
      "step": 15659
    },
    {
      "epoch": 0.481061653303843,
      "grad_norm": 0.34348368644714355,
      "learning_rate": 1.730371119131221e-05,
      "loss": 0.5316,
      "step": 15660
    },
    {
      "epoch": 0.4810923724387921,
      "grad_norm": 0.33694422245025635,
      "learning_rate": 1.7303381079941708e-05,
      "loss": 0.5997,
      "step": 15661
    },
    {
      "epoch": 0.4811230915737413,
      "grad_norm": 0.3710257411003113,
      "learning_rate": 1.7303050951513652e-05,
      "loss": 0.5799,
      "step": 15662
    },
    {
      "epoch": 0.48115381070869045,
      "grad_norm": 0.3852437734603882,
      "learning_rate": 1.7302720806028808e-05,
      "loss": 0.5481,
      "step": 15663
    },
    {
      "epoch": 0.48118452984363963,
      "grad_norm": 0.3510846793651581,
      "learning_rate": 1.730239064348795e-05,
      "loss": 0.5731,
      "step": 15664
    },
    {
      "epoch": 0.48121524897858875,
      "grad_norm": 0.34345823526382446,
      "learning_rate": 1.730206046389185e-05,
      "loss": 0.5924,
      "step": 15665
    },
    {
      "epoch": 0.4812459681135379,
      "grad_norm": 0.3569084703922272,
      "learning_rate": 1.7301730267241276e-05,
      "loss": 0.5446,
      "step": 15666
    },
    {
      "epoch": 0.4812766872484871,
      "grad_norm": 0.35493287444114685,
      "learning_rate": 1.7301400053537002e-05,
      "loss": 0.604,
      "step": 15667
    },
    {
      "epoch": 0.4813074063834362,
      "grad_norm": 0.35209769010543823,
      "learning_rate": 1.73010698227798e-05,
      "loss": 0.528,
      "step": 15668
    },
    {
      "epoch": 0.4813381255183854,
      "grad_norm": 0.3469630479812622,
      "learning_rate": 1.7300739574970435e-05,
      "loss": 0.6455,
      "step": 15669
    },
    {
      "epoch": 0.48136884465333457,
      "grad_norm": 0.4557953476905823,
      "learning_rate": 1.7300409310109688e-05,
      "loss": 0.5819,
      "step": 15670
    },
    {
      "epoch": 0.48139956378828375,
      "grad_norm": 0.3378516137599945,
      "learning_rate": 1.7300079028198323e-05,
      "loss": 0.5689,
      "step": 15671
    },
    {
      "epoch": 0.48143028292323287,
      "grad_norm": 0.331480473279953,
      "learning_rate": 1.729974872923711e-05,
      "loss": 0.5584,
      "step": 15672
    },
    {
      "epoch": 0.48146100205818204,
      "grad_norm": 0.31670403480529785,
      "learning_rate": 1.729941841322683e-05,
      "loss": 0.5494,
      "step": 15673
    },
    {
      "epoch": 0.4814917211931312,
      "grad_norm": 0.37127986550331116,
      "learning_rate": 1.7299088080168245e-05,
      "loss": 0.6027,
      "step": 15674
    },
    {
      "epoch": 0.48152244032808034,
      "grad_norm": 0.353407084941864,
      "learning_rate": 1.7298757730062132e-05,
      "loss": 0.5948,
      "step": 15675
    },
    {
      "epoch": 0.4815531594630295,
      "grad_norm": 0.349269300699234,
      "learning_rate": 1.7298427362909258e-05,
      "loss": 0.5589,
      "step": 15676
    },
    {
      "epoch": 0.4815838785979787,
      "grad_norm": 0.3471521735191345,
      "learning_rate": 1.72980969787104e-05,
      "loss": 0.5337,
      "step": 15677
    },
    {
      "epoch": 0.48161459773292786,
      "grad_norm": 0.39009249210357666,
      "learning_rate": 1.7297766577466327e-05,
      "loss": 0.6091,
      "step": 15678
    },
    {
      "epoch": 0.481645316867877,
      "grad_norm": 0.3752479553222656,
      "learning_rate": 1.729743615917781e-05,
      "loss": 0.6151,
      "step": 15679
    },
    {
      "epoch": 0.48167603600282616,
      "grad_norm": 0.34029144048690796,
      "learning_rate": 1.729710572384562e-05,
      "loss": 0.6054,
      "step": 15680
    },
    {
      "epoch": 0.48170675513777533,
      "grad_norm": 0.35930585861206055,
      "learning_rate": 1.729677527147053e-05,
      "loss": 0.5155,
      "step": 15681
    },
    {
      "epoch": 0.48173747427272445,
      "grad_norm": 0.3410246670246124,
      "learning_rate": 1.7296444802053312e-05,
      "loss": 0.585,
      "step": 15682
    },
    {
      "epoch": 0.48176819340767363,
      "grad_norm": 0.3528454303741455,
      "learning_rate": 1.7296114315594736e-05,
      "loss": 0.6136,
      "step": 15683
    },
    {
      "epoch": 0.4817989125426228,
      "grad_norm": 0.3451441824436188,
      "learning_rate": 1.7295783812095577e-05,
      "loss": 0.5562,
      "step": 15684
    },
    {
      "epoch": 0.481829631677572,
      "grad_norm": 0.3526017665863037,
      "learning_rate": 1.7295453291556606e-05,
      "loss": 0.5809,
      "step": 15685
    },
    {
      "epoch": 0.4818603508125211,
      "grad_norm": 0.359002947807312,
      "learning_rate": 1.7295122753978595e-05,
      "loss": 0.6447,
      "step": 15686
    },
    {
      "epoch": 0.4818910699474703,
      "grad_norm": 0.34475526213645935,
      "learning_rate": 1.729479219936231e-05,
      "loss": 0.6218,
      "step": 15687
    },
    {
      "epoch": 0.48192178908241945,
      "grad_norm": 0.3351697325706482,
      "learning_rate": 1.7294461627708536e-05,
      "loss": 0.5989,
      "step": 15688
    },
    {
      "epoch": 0.4819525082173686,
      "grad_norm": 0.35583412647247314,
      "learning_rate": 1.7294131039018033e-05,
      "loss": 0.5933,
      "step": 15689
    },
    {
      "epoch": 0.48198322735231774,
      "grad_norm": 0.33511096239089966,
      "learning_rate": 1.729380043329158e-05,
      "loss": 0.5617,
      "step": 15690
    },
    {
      "epoch": 0.4820139464872669,
      "grad_norm": 0.33694690465927124,
      "learning_rate": 1.7293469810529942e-05,
      "loss": 0.5414,
      "step": 15691
    },
    {
      "epoch": 0.4820446656222161,
      "grad_norm": 0.3298153281211853,
      "learning_rate": 1.7293139170733902e-05,
      "loss": 0.5156,
      "step": 15692
    },
    {
      "epoch": 0.4820753847571652,
      "grad_norm": 0.32541871070861816,
      "learning_rate": 1.729280851390422e-05,
      "loss": 0.5028,
      "step": 15693
    },
    {
      "epoch": 0.4821061038921144,
      "grad_norm": 0.4098460078239441,
      "learning_rate": 1.729247784004168e-05,
      "loss": 0.5811,
      "step": 15694
    },
    {
      "epoch": 0.48213682302706357,
      "grad_norm": 0.34444573521614075,
      "learning_rate": 1.7292147149147044e-05,
      "loss": 0.601,
      "step": 15695
    },
    {
      "epoch": 0.48216754216201274,
      "grad_norm": 0.4556410610675812,
      "learning_rate": 1.7291816441221092e-05,
      "loss": 0.5423,
      "step": 15696
    },
    {
      "epoch": 0.48219826129696186,
      "grad_norm": 0.42567893862724304,
      "learning_rate": 1.7291485716264593e-05,
      "loss": 0.5658,
      "step": 15697
    },
    {
      "epoch": 0.48222898043191104,
      "grad_norm": 0.38303226232528687,
      "learning_rate": 1.729115497427832e-05,
      "loss": 0.5345,
      "step": 15698
    },
    {
      "epoch": 0.4822596995668602,
      "grad_norm": 0.34839552640914917,
      "learning_rate": 1.7290824215263045e-05,
      "loss": 0.4974,
      "step": 15699
    },
    {
      "epoch": 0.48229041870180933,
      "grad_norm": 0.503210723400116,
      "learning_rate": 1.729049343921954e-05,
      "loss": 0.5184,
      "step": 15700
    },
    {
      "epoch": 0.4823211378367585,
      "grad_norm": 0.3348735272884369,
      "learning_rate": 1.729016264614858e-05,
      "loss": 0.5717,
      "step": 15701
    },
    {
      "epoch": 0.4823518569717077,
      "grad_norm": 0.3471105396747589,
      "learning_rate": 1.7289831836050935e-05,
      "loss": 0.5545,
      "step": 15702
    },
    {
      "epoch": 0.48238257610665686,
      "grad_norm": 0.32524940371513367,
      "learning_rate": 1.7289501008927382e-05,
      "loss": 0.5922,
      "step": 15703
    },
    {
      "epoch": 0.482413295241606,
      "grad_norm": 0.44928690791130066,
      "learning_rate": 1.7289170164778684e-05,
      "loss": 0.5341,
      "step": 15704
    },
    {
      "epoch": 0.48244401437655515,
      "grad_norm": 0.37953445315361023,
      "learning_rate": 1.7288839303605624e-05,
      "loss": 0.5616,
      "step": 15705
    },
    {
      "epoch": 0.48247473351150433,
      "grad_norm": 0.34424787759780884,
      "learning_rate": 1.728850842540897e-05,
      "loss": 0.5933,
      "step": 15706
    },
    {
      "epoch": 0.4825054526464535,
      "grad_norm": 0.6616065502166748,
      "learning_rate": 1.7288177530189494e-05,
      "loss": 0.6061,
      "step": 15707
    },
    {
      "epoch": 0.4825361717814026,
      "grad_norm": 0.34685584902763367,
      "learning_rate": 1.728784661794797e-05,
      "loss": 0.6059,
      "step": 15708
    },
    {
      "epoch": 0.4825668909163518,
      "grad_norm": 0.33918502926826477,
      "learning_rate": 1.7287515688685177e-05,
      "loss": 0.5006,
      "step": 15709
    },
    {
      "epoch": 0.482597610051301,
      "grad_norm": 0.3459092080593109,
      "learning_rate": 1.7287184742401873e-05,
      "loss": 0.5729,
      "step": 15710
    },
    {
      "epoch": 0.4826283291862501,
      "grad_norm": 0.3541657030582428,
      "learning_rate": 1.728685377909885e-05,
      "loss": 0.6045,
      "step": 15711
    },
    {
      "epoch": 0.48265904832119927,
      "grad_norm": 0.32489603757858276,
      "learning_rate": 1.7286522798776865e-05,
      "loss": 0.5002,
      "step": 15712
    },
    {
      "epoch": 0.48268976745614844,
      "grad_norm": 0.3707578182220459,
      "learning_rate": 1.72861918014367e-05,
      "loss": 0.5721,
      "step": 15713
    },
    {
      "epoch": 0.4827204865910976,
      "grad_norm": 0.4014342725276947,
      "learning_rate": 1.7285860787079122e-05,
      "loss": 0.5388,
      "step": 15714
    },
    {
      "epoch": 0.48275120572604674,
      "grad_norm": 0.6813092827796936,
      "learning_rate": 1.7285529755704908e-05,
      "loss": 0.5699,
      "step": 15715
    },
    {
      "epoch": 0.4827819248609959,
      "grad_norm": 0.3397083580493927,
      "learning_rate": 1.7285198707314835e-05,
      "loss": 0.4955,
      "step": 15716
    },
    {
      "epoch": 0.4828126439959451,
      "grad_norm": 0.363910436630249,
      "learning_rate": 1.7284867641909666e-05,
      "loss": 0.5255,
      "step": 15717
    },
    {
      "epoch": 0.4828433631308942,
      "grad_norm": 0.36017531156539917,
      "learning_rate": 1.7284536559490183e-05,
      "loss": 0.6335,
      "step": 15718
    },
    {
      "epoch": 0.4828740822658434,
      "grad_norm": 3.620467185974121,
      "learning_rate": 1.7284205460057153e-05,
      "loss": 0.6221,
      "step": 15719
    },
    {
      "epoch": 0.48290480140079256,
      "grad_norm": 0.3365199863910675,
      "learning_rate": 1.7283874343611357e-05,
      "loss": 0.6097,
      "step": 15720
    },
    {
      "epoch": 0.48293552053574174,
      "grad_norm": 0.3482273817062378,
      "learning_rate": 1.7283543210153562e-05,
      "loss": 0.5941,
      "step": 15721
    },
    {
      "epoch": 0.48296623967069086,
      "grad_norm": 0.3374534845352173,
      "learning_rate": 1.728321205968454e-05,
      "loss": 0.5191,
      "step": 15722
    },
    {
      "epoch": 0.48299695880564003,
      "grad_norm": 0.3843139111995697,
      "learning_rate": 1.728288089220507e-05,
      "loss": 0.6495,
      "step": 15723
    },
    {
      "epoch": 0.4830276779405892,
      "grad_norm": 0.3482626974582672,
      "learning_rate": 1.7282549707715923e-05,
      "loss": 0.5355,
      "step": 15724
    },
    {
      "epoch": 0.4830583970755383,
      "grad_norm": 0.341667115688324,
      "learning_rate": 1.7282218506217875e-05,
      "loss": 0.5006,
      "step": 15725
    },
    {
      "epoch": 0.4830891162104875,
      "grad_norm": 0.33193090558052063,
      "learning_rate": 1.728188728771169e-05,
      "loss": 0.4926,
      "step": 15726
    },
    {
      "epoch": 0.4831198353454367,
      "grad_norm": 0.335126668214798,
      "learning_rate": 1.7281556052198155e-05,
      "loss": 0.6337,
      "step": 15727
    },
    {
      "epoch": 0.48315055448038585,
      "grad_norm": 0.36640891432762146,
      "learning_rate": 1.7281224799678034e-05,
      "loss": 0.6125,
      "step": 15728
    },
    {
      "epoch": 0.48318127361533497,
      "grad_norm": 0.33153435587882996,
      "learning_rate": 1.7280893530152108e-05,
      "loss": 0.594,
      "step": 15729
    },
    {
      "epoch": 0.48321199275028415,
      "grad_norm": 0.352229505777359,
      "learning_rate": 1.7280562243621144e-05,
      "loss": 0.5155,
      "step": 15730
    },
    {
      "epoch": 0.4832427118852333,
      "grad_norm": 0.3764321804046631,
      "learning_rate": 1.728023094008592e-05,
      "loss": 0.4888,
      "step": 15731
    },
    {
      "epoch": 0.4832734310201825,
      "grad_norm": 0.4096474051475525,
      "learning_rate": 1.7279899619547207e-05,
      "loss": 0.48,
      "step": 15732
    },
    {
      "epoch": 0.4833041501551316,
      "grad_norm": 0.3503411114215851,
      "learning_rate": 1.7279568282005778e-05,
      "loss": 0.5856,
      "step": 15733
    },
    {
      "epoch": 0.4833348692900808,
      "grad_norm": 0.3748670816421509,
      "learning_rate": 1.7279236927462413e-05,
      "loss": 0.5734,
      "step": 15734
    },
    {
      "epoch": 0.48336558842502997,
      "grad_norm": 0.36833611130714417,
      "learning_rate": 1.7278905555917876e-05,
      "loss": 0.6121,
      "step": 15735
    },
    {
      "epoch": 0.4833963075599791,
      "grad_norm": 0.36095795035362244,
      "learning_rate": 1.727857416737295e-05,
      "loss": 0.5843,
      "step": 15736
    },
    {
      "epoch": 0.48342702669492826,
      "grad_norm": 0.3149845004081726,
      "learning_rate": 1.7278242761828407e-05,
      "loss": 0.537,
      "step": 15737
    },
    {
      "epoch": 0.48345774582987744,
      "grad_norm": 0.3402508795261383,
      "learning_rate": 1.727791133928502e-05,
      "loss": 0.5216,
      "step": 15738
    },
    {
      "epoch": 0.4834884649648266,
      "grad_norm": 0.3475918471813202,
      "learning_rate": 1.7277579899743565e-05,
      "loss": 0.6108,
      "step": 15739
    },
    {
      "epoch": 0.48351918409977573,
      "grad_norm": 0.3776262700557709,
      "learning_rate": 1.727724844320481e-05,
      "loss": 0.626,
      "step": 15740
    },
    {
      "epoch": 0.4835499032347249,
      "grad_norm": 0.39229580760002136,
      "learning_rate": 1.7276916969669533e-05,
      "loss": 0.5744,
      "step": 15741
    },
    {
      "epoch": 0.4835806223696741,
      "grad_norm": 0.38276296854019165,
      "learning_rate": 1.7276585479138507e-05,
      "loss": 0.5381,
      "step": 15742
    },
    {
      "epoch": 0.4836113415046232,
      "grad_norm": 0.37546786665916443,
      "learning_rate": 1.7276253971612507e-05,
      "loss": 0.6214,
      "step": 15743
    },
    {
      "epoch": 0.4836420606395724,
      "grad_norm": 0.3588554859161377,
      "learning_rate": 1.7275922447092313e-05,
      "loss": 0.5721,
      "step": 15744
    },
    {
      "epoch": 0.48367277977452156,
      "grad_norm": 0.35103628039360046,
      "learning_rate": 1.727559090557869e-05,
      "loss": 0.6166,
      "step": 15745
    },
    {
      "epoch": 0.48370349890947073,
      "grad_norm": 0.44209036231040955,
      "learning_rate": 1.7275259347072416e-05,
      "loss": 0.6163,
      "step": 15746
    },
    {
      "epoch": 0.48373421804441985,
      "grad_norm": 0.35991838574409485,
      "learning_rate": 1.727492777157427e-05,
      "loss": 0.4842,
      "step": 15747
    },
    {
      "epoch": 0.483764937179369,
      "grad_norm": 0.33891910314559937,
      "learning_rate": 1.7274596179085016e-05,
      "loss": 0.5582,
      "step": 15748
    },
    {
      "epoch": 0.4837956563143182,
      "grad_norm": 0.349960058927536,
      "learning_rate": 1.7274264569605435e-05,
      "loss": 0.5847,
      "step": 15749
    },
    {
      "epoch": 0.4838263754492674,
      "grad_norm": 0.36290282011032104,
      "learning_rate": 1.7273932943136308e-05,
      "loss": 0.6041,
      "step": 15750
    },
    {
      "epoch": 0.4838570945842165,
      "grad_norm": 0.3306903839111328,
      "learning_rate": 1.7273601299678396e-05,
      "loss": 0.507,
      "step": 15751
    },
    {
      "epoch": 0.48388781371916567,
      "grad_norm": 0.3445807695388794,
      "learning_rate": 1.727326963923248e-05,
      "loss": 0.5412,
      "step": 15752
    },
    {
      "epoch": 0.48391853285411485,
      "grad_norm": 0.36060070991516113,
      "learning_rate": 1.7272937961799342e-05,
      "loss": 0.6137,
      "step": 15753
    },
    {
      "epoch": 0.48394925198906397,
      "grad_norm": 0.3841051161289215,
      "learning_rate": 1.7272606267379744e-05,
      "loss": 0.5883,
      "step": 15754
    },
    {
      "epoch": 0.48397997112401314,
      "grad_norm": 0.3660743534564972,
      "learning_rate": 1.7272274555974466e-05,
      "loss": 0.5967,
      "step": 15755
    },
    {
      "epoch": 0.4840106902589623,
      "grad_norm": 0.46666836738586426,
      "learning_rate": 1.7271942827584283e-05,
      "loss": 0.4829,
      "step": 15756
    },
    {
      "epoch": 0.4840414093939115,
      "grad_norm": 0.463594526052475,
      "learning_rate": 1.7271611082209968e-05,
      "loss": 0.6161,
      "step": 15757
    },
    {
      "epoch": 0.4840721285288606,
      "grad_norm": 0.34602001309394836,
      "learning_rate": 1.72712793198523e-05,
      "loss": 0.5772,
      "step": 15758
    },
    {
      "epoch": 0.4841028476638098,
      "grad_norm": 0.33482825756073,
      "learning_rate": 1.7270947540512052e-05,
      "loss": 0.5389,
      "step": 15759
    },
    {
      "epoch": 0.48413356679875896,
      "grad_norm": 0.39361247420310974,
      "learning_rate": 1.7270615744189996e-05,
      "loss": 0.5367,
      "step": 15760
    },
    {
      "epoch": 0.4841642859337081,
      "grad_norm": 0.3324570655822754,
      "learning_rate": 1.727028393088691e-05,
      "loss": 0.6058,
      "step": 15761
    },
    {
      "epoch": 0.48419500506865726,
      "grad_norm": 0.3352911174297333,
      "learning_rate": 1.7269952100603568e-05,
      "loss": 0.5404,
      "step": 15762
    },
    {
      "epoch": 0.48422572420360643,
      "grad_norm": 0.3528735339641571,
      "learning_rate": 1.7269620253340747e-05,
      "loss": 0.5703,
      "step": 15763
    },
    {
      "epoch": 0.4842564433385556,
      "grad_norm": 0.38353613018989563,
      "learning_rate": 1.726928838909922e-05,
      "loss": 0.6298,
      "step": 15764
    },
    {
      "epoch": 0.48428716247350473,
      "grad_norm": 0.3631245195865631,
      "learning_rate": 1.726895650787976e-05,
      "loss": 0.6384,
      "step": 15765
    },
    {
      "epoch": 0.4843178816084539,
      "grad_norm": 0.363518089056015,
      "learning_rate": 1.7268624609683146e-05,
      "loss": 0.6306,
      "step": 15766
    },
    {
      "epoch": 0.4843486007434031,
      "grad_norm": 0.3514781892299652,
      "learning_rate": 1.726829269451015e-05,
      "loss": 0.6773,
      "step": 15767
    },
    {
      "epoch": 0.4843793198783522,
      "grad_norm": 0.3805536925792694,
      "learning_rate": 1.726796076236155e-05,
      "loss": 0.544,
      "step": 15768
    },
    {
      "epoch": 0.4844100390133014,
      "grad_norm": 0.3302455544471741,
      "learning_rate": 1.7267628813238122e-05,
      "loss": 0.4611,
      "step": 15769
    },
    {
      "epoch": 0.48444075814825055,
      "grad_norm": 0.36925774812698364,
      "learning_rate": 1.7267296847140635e-05,
      "loss": 0.5526,
      "step": 15770
    },
    {
      "epoch": 0.4844714772831997,
      "grad_norm": 0.3502638041973114,
      "learning_rate": 1.7266964864069874e-05,
      "loss": 0.5608,
      "step": 15771
    },
    {
      "epoch": 0.48450219641814884,
      "grad_norm": 0.42221349477767944,
      "learning_rate": 1.7266632864026606e-05,
      "loss": 0.5414,
      "step": 15772
    },
    {
      "epoch": 0.484532915553098,
      "grad_norm": 0.34654757380485535,
      "learning_rate": 1.726630084701161e-05,
      "loss": 0.5668,
      "step": 15773
    },
    {
      "epoch": 0.4845636346880472,
      "grad_norm": 0.40870317816734314,
      "learning_rate": 1.7265968813025658e-05,
      "loss": 0.6065,
      "step": 15774
    },
    {
      "epoch": 0.48459435382299637,
      "grad_norm": 0.4163627624511719,
      "learning_rate": 1.7265636762069533e-05,
      "loss": 0.5836,
      "step": 15775
    },
    {
      "epoch": 0.4846250729579455,
      "grad_norm": 0.3859894573688507,
      "learning_rate": 1.7265304694144e-05,
      "loss": 0.5896,
      "step": 15776
    },
    {
      "epoch": 0.48465579209289467,
      "grad_norm": 0.38113853335380554,
      "learning_rate": 1.7264972609249845e-05,
      "loss": 0.5832,
      "step": 15777
    },
    {
      "epoch": 0.48468651122784384,
      "grad_norm": 0.3458234369754791,
      "learning_rate": 1.726464050738784e-05,
      "loss": 0.6286,
      "step": 15778
    },
    {
      "epoch": 0.48471723036279296,
      "grad_norm": 0.3912731111049652,
      "learning_rate": 1.726430838855876e-05,
      "loss": 0.5832,
      "step": 15779
    },
    {
      "epoch": 0.48474794949774214,
      "grad_norm": 0.38349103927612305,
      "learning_rate": 1.7263976252763373e-05,
      "loss": 0.6625,
      "step": 15780
    },
    {
      "epoch": 0.4847786686326913,
      "grad_norm": 0.8195056915283203,
      "learning_rate": 1.726364410000247e-05,
      "loss": 0.5266,
      "step": 15781
    },
    {
      "epoch": 0.4848093877676405,
      "grad_norm": 0.3457338213920593,
      "learning_rate": 1.7263311930276816e-05,
      "loss": 0.5633,
      "step": 15782
    },
    {
      "epoch": 0.4848401069025896,
      "grad_norm": 0.34510424733161926,
      "learning_rate": 1.726297974358719e-05,
      "loss": 0.6204,
      "step": 15783
    },
    {
      "epoch": 0.4848708260375388,
      "grad_norm": 0.4285133183002472,
      "learning_rate": 1.726264753993437e-05,
      "loss": 0.5696,
      "step": 15784
    },
    {
      "epoch": 0.48490154517248796,
      "grad_norm": 0.35409116744995117,
      "learning_rate": 1.7262315319319126e-05,
      "loss": 0.5452,
      "step": 15785
    },
    {
      "epoch": 0.4849322643074371,
      "grad_norm": 0.39601361751556396,
      "learning_rate": 1.726198308174224e-05,
      "loss": 0.6167,
      "step": 15786
    },
    {
      "epoch": 0.48496298344238625,
      "grad_norm": 0.3748704493045807,
      "learning_rate": 1.7261650827204483e-05,
      "loss": 0.6055,
      "step": 15787
    },
    {
      "epoch": 0.48499370257733543,
      "grad_norm": 0.37444350123405457,
      "learning_rate": 1.7261318555706634e-05,
      "loss": 0.5965,
      "step": 15788
    },
    {
      "epoch": 0.4850244217122846,
      "grad_norm": 0.3443230092525482,
      "learning_rate": 1.7260986267249467e-05,
      "loss": 0.5417,
      "step": 15789
    },
    {
      "epoch": 0.4850551408472337,
      "grad_norm": 0.3777427077293396,
      "learning_rate": 1.7260653961833762e-05,
      "loss": 0.5501,
      "step": 15790
    },
    {
      "epoch": 0.4850858599821829,
      "grad_norm": 0.34792765974998474,
      "learning_rate": 1.7260321639460292e-05,
      "loss": 0.559,
      "step": 15791
    },
    {
      "epoch": 0.4851165791171321,
      "grad_norm": 0.33857953548431396,
      "learning_rate": 1.7259989300129832e-05,
      "loss": 0.5298,
      "step": 15792
    },
    {
      "epoch": 0.4851472982520812,
      "grad_norm": 0.399840384721756,
      "learning_rate": 1.7259656943843165e-05,
      "loss": 0.5639,
      "step": 15793
    },
    {
      "epoch": 0.48517801738703037,
      "grad_norm": 0.34694674611091614,
      "learning_rate": 1.7259324570601056e-05,
      "loss": 0.6122,
      "step": 15794
    },
    {
      "epoch": 0.48520873652197954,
      "grad_norm": 0.3557078242301941,
      "learning_rate": 1.7258992180404292e-05,
      "loss": 0.5542,
      "step": 15795
    },
    {
      "epoch": 0.4852394556569287,
      "grad_norm": 0.342525452375412,
      "learning_rate": 1.7258659773253642e-05,
      "loss": 0.5707,
      "step": 15796
    },
    {
      "epoch": 0.48527017479187784,
      "grad_norm": 0.347680926322937,
      "learning_rate": 1.7258327349149885e-05,
      "loss": 0.5873,
      "step": 15797
    },
    {
      "epoch": 0.485300893926827,
      "grad_norm": 0.35126835107803345,
      "learning_rate": 1.7257994908093804e-05,
      "loss": 0.5092,
      "step": 15798
    },
    {
      "epoch": 0.4853316130617762,
      "grad_norm": 0.40541672706604004,
      "learning_rate": 1.7257662450086158e-05,
      "loss": 0.6287,
      "step": 15799
    },
    {
      "epoch": 0.48536233219672537,
      "grad_norm": 0.3587082028388977,
      "learning_rate": 1.7257329975127742e-05,
      "loss": 0.6221,
      "step": 15800
    },
    {
      "epoch": 0.4853930513316745,
      "grad_norm": 0.4093378186225891,
      "learning_rate": 1.7256997483219323e-05,
      "loss": 0.5865,
      "step": 15801
    },
    {
      "epoch": 0.48542377046662366,
      "grad_norm": 0.3812684416770935,
      "learning_rate": 1.725666497436168e-05,
      "loss": 0.5463,
      "step": 15802
    },
    {
      "epoch": 0.48545448960157284,
      "grad_norm": 0.373402863740921,
      "learning_rate": 1.7256332448555588e-05,
      "loss": 0.5813,
      "step": 15803
    },
    {
      "epoch": 0.48548520873652196,
      "grad_norm": 0.33486655354499817,
      "learning_rate": 1.7255999905801827e-05,
      "loss": 0.5027,
      "step": 15804
    },
    {
      "epoch": 0.48551592787147113,
      "grad_norm": 0.3703971803188324,
      "learning_rate": 1.725566734610117e-05,
      "loss": 0.571,
      "step": 15805
    },
    {
      "epoch": 0.4855466470064203,
      "grad_norm": 0.33081409335136414,
      "learning_rate": 1.7255334769454396e-05,
      "loss": 0.5629,
      "step": 15806
    },
    {
      "epoch": 0.4855773661413695,
      "grad_norm": 0.38928934931755066,
      "learning_rate": 1.725500217586228e-05,
      "loss": 0.5497,
      "step": 15807
    },
    {
      "epoch": 0.4856080852763186,
      "grad_norm": 0.3432006537914276,
      "learning_rate": 1.72546695653256e-05,
      "loss": 0.6426,
      "step": 15808
    },
    {
      "epoch": 0.4856388044112678,
      "grad_norm": 0.34252241253852844,
      "learning_rate": 1.7254336937845132e-05,
      "loss": 0.5296,
      "step": 15809
    },
    {
      "epoch": 0.48566952354621695,
      "grad_norm": 0.33474284410476685,
      "learning_rate": 1.7254004293421654e-05,
      "loss": 0.5654,
      "step": 15810
    },
    {
      "epoch": 0.4857002426811661,
      "grad_norm": 0.3339325785636902,
      "learning_rate": 1.7253671632055942e-05,
      "loss": 0.5835,
      "step": 15811
    },
    {
      "epoch": 0.48573096181611525,
      "grad_norm": 0.3814123868942261,
      "learning_rate": 1.7253338953748775e-05,
      "loss": 0.6117,
      "step": 15812
    },
    {
      "epoch": 0.4857616809510644,
      "grad_norm": 0.3390401601791382,
      "learning_rate": 1.7253006258500925e-05,
      "loss": 0.5743,
      "step": 15813
    },
    {
      "epoch": 0.4857924000860136,
      "grad_norm": 0.3994074761867523,
      "learning_rate": 1.7252673546313176e-05,
      "loss": 0.5634,
      "step": 15814
    },
    {
      "epoch": 0.4858231192209627,
      "grad_norm": 0.37351563572883606,
      "learning_rate": 1.7252340817186298e-05,
      "loss": 0.5656,
      "step": 15815
    },
    {
      "epoch": 0.4858538383559119,
      "grad_norm": 0.3309897184371948,
      "learning_rate": 1.7252008071121076e-05,
      "loss": 0.5493,
      "step": 15816
    },
    {
      "epoch": 0.48588455749086107,
      "grad_norm": 0.33505818247795105,
      "learning_rate": 1.7251675308118278e-05,
      "loss": 0.476,
      "step": 15817
    },
    {
      "epoch": 0.48591527662581024,
      "grad_norm": 0.39564138650894165,
      "learning_rate": 1.725134252817869e-05,
      "loss": 0.488,
      "step": 15818
    },
    {
      "epoch": 0.48594599576075936,
      "grad_norm": 0.33468788862228394,
      "learning_rate": 1.7251009731303082e-05,
      "loss": 0.5829,
      "step": 15819
    },
    {
      "epoch": 0.48597671489570854,
      "grad_norm": 0.32793134450912476,
      "learning_rate": 1.7250676917492236e-05,
      "loss": 0.5156,
      "step": 15820
    },
    {
      "epoch": 0.4860074340306577,
      "grad_norm": 0.35537654161453247,
      "learning_rate": 1.7250344086746925e-05,
      "loss": 0.5442,
      "step": 15821
    },
    {
      "epoch": 0.48603815316560683,
      "grad_norm": 0.33686569333076477,
      "learning_rate": 1.7250011239067934e-05,
      "loss": 0.5242,
      "step": 15822
    },
    {
      "epoch": 0.486068872300556,
      "grad_norm": 0.33361124992370605,
      "learning_rate": 1.7249678374456032e-05,
      "loss": 0.5339,
      "step": 15823
    },
    {
      "epoch": 0.4860995914355052,
      "grad_norm": 0.31749603152275085,
      "learning_rate": 1.7249345492912e-05,
      "loss": 0.5874,
      "step": 15824
    },
    {
      "epoch": 0.48613031057045436,
      "grad_norm": 0.35321488976478577,
      "learning_rate": 1.7249012594436613e-05,
      "loss": 0.5806,
      "step": 15825
    },
    {
      "epoch": 0.4861610297054035,
      "grad_norm": 2.367567777633667,
      "learning_rate": 1.7248679679030656e-05,
      "loss": 0.5039,
      "step": 15826
    },
    {
      "epoch": 0.48619174884035266,
      "grad_norm": 0.3937743306159973,
      "learning_rate": 1.7248346746694896e-05,
      "loss": 0.61,
      "step": 15827
    },
    {
      "epoch": 0.48622246797530183,
      "grad_norm": 0.3079245090484619,
      "learning_rate": 1.7248013797430122e-05,
      "loss": 0.4906,
      "step": 15828
    },
    {
      "epoch": 0.48625318711025095,
      "grad_norm": 0.35592636466026306,
      "learning_rate": 1.72476808312371e-05,
      "loss": 0.5336,
      "step": 15829
    },
    {
      "epoch": 0.4862839062452001,
      "grad_norm": 0.32471057772636414,
      "learning_rate": 1.7247347848116616e-05,
      "loss": 0.5375,
      "step": 15830
    },
    {
      "epoch": 0.4863146253801493,
      "grad_norm": 0.3378676772117615,
      "learning_rate": 1.7247014848069442e-05,
      "loss": 0.5836,
      "step": 15831
    },
    {
      "epoch": 0.4863453445150985,
      "grad_norm": 0.3423118591308594,
      "learning_rate": 1.7246681831096365e-05,
      "loss": 0.5357,
      "step": 15832
    },
    {
      "epoch": 0.4863760636500476,
      "grad_norm": 0.3314421772956848,
      "learning_rate": 1.724634879719815e-05,
      "loss": 0.6007,
      "step": 15833
    },
    {
      "epoch": 0.48640678278499677,
      "grad_norm": 0.324759304523468,
      "learning_rate": 1.7246015746375585e-05,
      "loss": 0.6213,
      "step": 15834
    },
    {
      "epoch": 0.48643750191994595,
      "grad_norm": 0.4024566411972046,
      "learning_rate": 1.7245682678629442e-05,
      "loss": 0.5202,
      "step": 15835
    },
    {
      "epoch": 0.48646822105489507,
      "grad_norm": 0.36835235357284546,
      "learning_rate": 1.7245349593960502e-05,
      "loss": 0.5685,
      "step": 15836
    },
    {
      "epoch": 0.48649894018984424,
      "grad_norm": 0.3754670321941376,
      "learning_rate": 1.724501649236954e-05,
      "loss": 0.5762,
      "step": 15837
    },
    {
      "epoch": 0.4865296593247934,
      "grad_norm": 0.3638819456100464,
      "learning_rate": 1.7244683373857342e-05,
      "loss": 0.5912,
      "step": 15838
    },
    {
      "epoch": 0.4865603784597426,
      "grad_norm": 0.37446022033691406,
      "learning_rate": 1.7244350238424674e-05,
      "loss": 0.5361,
      "step": 15839
    },
    {
      "epoch": 0.4865910975946917,
      "grad_norm": 0.3881780207157135,
      "learning_rate": 1.7244017086072323e-05,
      "loss": 0.603,
      "step": 15840
    },
    {
      "epoch": 0.4866218167296409,
      "grad_norm": 0.35924190282821655,
      "learning_rate": 1.7243683916801065e-05,
      "loss": 0.597,
      "step": 15841
    },
    {
      "epoch": 0.48665253586459006,
      "grad_norm": 0.39396539330482483,
      "learning_rate": 1.7243350730611675e-05,
      "loss": 0.6064,
      "step": 15842
    },
    {
      "epoch": 0.48668325499953924,
      "grad_norm": 0.4001755714416504,
      "learning_rate": 1.7243017527504934e-05,
      "loss": 0.5345,
      "step": 15843
    },
    {
      "epoch": 0.48671397413448836,
      "grad_norm": 0.3800857961177826,
      "learning_rate": 1.724268430748162e-05,
      "loss": 0.6216,
      "step": 15844
    },
    {
      "epoch": 0.48674469326943753,
      "grad_norm": 0.3597661554813385,
      "learning_rate": 1.7242351070542512e-05,
      "loss": 0.65,
      "step": 15845
    },
    {
      "epoch": 0.4867754124043867,
      "grad_norm": 0.3634174168109894,
      "learning_rate": 1.7242017816688387e-05,
      "loss": 0.6721,
      "step": 15846
    },
    {
      "epoch": 0.48680613153933583,
      "grad_norm": 0.38375216722488403,
      "learning_rate": 1.724168454592002e-05,
      "loss": 0.4762,
      "step": 15847
    },
    {
      "epoch": 0.486836850674285,
      "grad_norm": 0.3416902422904968,
      "learning_rate": 1.7241351258238197e-05,
      "loss": 0.57,
      "step": 15848
    },
    {
      "epoch": 0.4868675698092342,
      "grad_norm": 0.3577231466770172,
      "learning_rate": 1.724101795364369e-05,
      "loss": 0.5936,
      "step": 15849
    },
    {
      "epoch": 0.48689828894418336,
      "grad_norm": 0.38180527091026306,
      "learning_rate": 1.7240684632137282e-05,
      "loss": 0.6069,
      "step": 15850
    },
    {
      "epoch": 0.4869290080791325,
      "grad_norm": 0.3200504183769226,
      "learning_rate": 1.7240351293719748e-05,
      "loss": 0.5219,
      "step": 15851
    },
    {
      "epoch": 0.48695972721408165,
      "grad_norm": 0.3919501006603241,
      "learning_rate": 1.724001793839187e-05,
      "loss": 0.499,
      "step": 15852
    },
    {
      "epoch": 0.4869904463490308,
      "grad_norm": 0.4576396942138672,
      "learning_rate": 1.7239684566154423e-05,
      "loss": 0.5513,
      "step": 15853
    },
    {
      "epoch": 0.48702116548397995,
      "grad_norm": 0.32999634742736816,
      "learning_rate": 1.7239351177008187e-05,
      "loss": 0.5103,
      "step": 15854
    },
    {
      "epoch": 0.4870518846189291,
      "grad_norm": 0.33031463623046875,
      "learning_rate": 1.723901777095394e-05,
      "loss": 0.5188,
      "step": 15855
    },
    {
      "epoch": 0.4870826037538783,
      "grad_norm": 0.35687682032585144,
      "learning_rate": 1.723868434799246e-05,
      "loss": 0.5422,
      "step": 15856
    },
    {
      "epoch": 0.48711332288882747,
      "grad_norm": 0.32782912254333496,
      "learning_rate": 1.7238350908124532e-05,
      "loss": 0.4894,
      "step": 15857
    },
    {
      "epoch": 0.4871440420237766,
      "grad_norm": 0.37107110023498535,
      "learning_rate": 1.7238017451350928e-05,
      "loss": 0.5679,
      "step": 15858
    },
    {
      "epoch": 0.48717476115872577,
      "grad_norm": 0.3334061801433563,
      "learning_rate": 1.7237683977672427e-05,
      "loss": 0.5554,
      "step": 15859
    },
    {
      "epoch": 0.48720548029367494,
      "grad_norm": 0.35647809505462646,
      "learning_rate": 1.7237350487089812e-05,
      "loss": 0.534,
      "step": 15860
    },
    {
      "epoch": 0.4872361994286241,
      "grad_norm": 0.48343425989151,
      "learning_rate": 1.7237016979603854e-05,
      "loss": 0.5783,
      "step": 15861
    },
    {
      "epoch": 0.48726691856357324,
      "grad_norm": 0.3353699743747711,
      "learning_rate": 1.7236683455215344e-05,
      "loss": 0.5133,
      "step": 15862
    },
    {
      "epoch": 0.4872976376985224,
      "grad_norm": 0.34549129009246826,
      "learning_rate": 1.7236349913925054e-05,
      "loss": 0.5441,
      "step": 15863
    },
    {
      "epoch": 0.4873283568334716,
      "grad_norm": 0.3315117657184601,
      "learning_rate": 1.723601635573376e-05,
      "loss": 0.5424,
      "step": 15864
    },
    {
      "epoch": 0.4873590759684207,
      "grad_norm": 0.43855223059654236,
      "learning_rate": 1.7235682780642243e-05,
      "loss": 0.5976,
      "step": 15865
    },
    {
      "epoch": 0.4873897951033699,
      "grad_norm": 0.3304395079612732,
      "learning_rate": 1.7235349188651288e-05,
      "loss": 0.5031,
      "step": 15866
    },
    {
      "epoch": 0.48742051423831906,
      "grad_norm": 0.3741317391395569,
      "learning_rate": 1.7235015579761666e-05,
      "loss": 0.564,
      "step": 15867
    },
    {
      "epoch": 0.48745123337326823,
      "grad_norm": 0.3207203447818756,
      "learning_rate": 1.723468195397416e-05,
      "loss": 0.642,
      "step": 15868
    },
    {
      "epoch": 0.48748195250821735,
      "grad_norm": 0.3352016806602478,
      "learning_rate": 1.723434831128955e-05,
      "loss": 0.5412,
      "step": 15869
    },
    {
      "epoch": 0.48751267164316653,
      "grad_norm": 0.32562097907066345,
      "learning_rate": 1.723401465170862e-05,
      "loss": 0.4793,
      "step": 15870
    },
    {
      "epoch": 0.4875433907781157,
      "grad_norm": 0.40395215153694153,
      "learning_rate": 1.723368097523214e-05,
      "loss": 0.6683,
      "step": 15871
    },
    {
      "epoch": 0.4875741099130648,
      "grad_norm": 0.3444645404815674,
      "learning_rate": 1.7233347281860888e-05,
      "loss": 0.6402,
      "step": 15872
    },
    {
      "epoch": 0.487604829048014,
      "grad_norm": 0.7463846802711487,
      "learning_rate": 1.7233013571595652e-05,
      "loss": 0.5668,
      "step": 15873
    },
    {
      "epoch": 0.4876355481829632,
      "grad_norm": 0.35682377219200134,
      "learning_rate": 1.723267984443721e-05,
      "loss": 0.5809,
      "step": 15874
    },
    {
      "epoch": 0.48766626731791235,
      "grad_norm": 0.3387852907180786,
      "learning_rate": 1.7232346100386334e-05,
      "loss": 0.5198,
      "step": 15875
    },
    {
      "epoch": 0.48769698645286147,
      "grad_norm": 0.3553810119628906,
      "learning_rate": 1.7232012339443812e-05,
      "loss": 0.5289,
      "step": 15876
    },
    {
      "epoch": 0.48772770558781064,
      "grad_norm": 0.40099355578422546,
      "learning_rate": 1.723167856161042e-05,
      "loss": 0.5984,
      "step": 15877
    },
    {
      "epoch": 0.4877584247227598,
      "grad_norm": 0.36618998646736145,
      "learning_rate": 1.7231344766886936e-05,
      "loss": 0.6132,
      "step": 15878
    },
    {
      "epoch": 0.48778914385770894,
      "grad_norm": 0.36621296405792236,
      "learning_rate": 1.723101095527414e-05,
      "loss": 0.5477,
      "step": 15879
    },
    {
      "epoch": 0.4878198629926581,
      "grad_norm": 0.46913957595825195,
      "learning_rate": 1.7230677126772817e-05,
      "loss": 0.5443,
      "step": 15880
    },
    {
      "epoch": 0.4878505821276073,
      "grad_norm": 0.35819774866104126,
      "learning_rate": 1.723034328138374e-05,
      "loss": 0.6582,
      "step": 15881
    },
    {
      "epoch": 0.48788130126255647,
      "grad_norm": 0.5940369367599487,
      "learning_rate": 1.723000941910769e-05,
      "loss": 0.653,
      "step": 15882
    },
    {
      "epoch": 0.4879120203975056,
      "grad_norm": 0.3511312007904053,
      "learning_rate": 1.7229675539945452e-05,
      "loss": 0.488,
      "step": 15883
    },
    {
      "epoch": 0.48794273953245476,
      "grad_norm": 0.36265674233436584,
      "learning_rate": 1.72293416438978e-05,
      "loss": 0.5873,
      "step": 15884
    },
    {
      "epoch": 0.48797345866740394,
      "grad_norm": 0.35298094153404236,
      "learning_rate": 1.7229007730965513e-05,
      "loss": 0.4741,
      "step": 15885
    },
    {
      "epoch": 0.4880041778023531,
      "grad_norm": 0.32671990990638733,
      "learning_rate": 1.722867380114938e-05,
      "loss": 0.548,
      "step": 15886
    },
    {
      "epoch": 0.48803489693730223,
      "grad_norm": 0.40459007024765015,
      "learning_rate": 1.722833985445017e-05,
      "loss": 0.5353,
      "step": 15887
    },
    {
      "epoch": 0.4880656160722514,
      "grad_norm": 0.3142535090446472,
      "learning_rate": 1.7228005890868666e-05,
      "loss": 0.5382,
      "step": 15888
    },
    {
      "epoch": 0.4880963352072006,
      "grad_norm": 0.3559851050376892,
      "learning_rate": 1.7227671910405654e-05,
      "loss": 0.6412,
      "step": 15889
    },
    {
      "epoch": 0.4881270543421497,
      "grad_norm": 0.34887343645095825,
      "learning_rate": 1.7227337913061905e-05,
      "loss": 0.6142,
      "step": 15890
    },
    {
      "epoch": 0.4881577734770989,
      "grad_norm": 0.3352544903755188,
      "learning_rate": 1.7227003898838205e-05,
      "loss": 0.5521,
      "step": 15891
    },
    {
      "epoch": 0.48818849261204805,
      "grad_norm": 0.39563021063804626,
      "learning_rate": 1.722666986773533e-05,
      "loss": 0.5544,
      "step": 15892
    },
    {
      "epoch": 0.48821921174699723,
      "grad_norm": 0.3448066711425781,
      "learning_rate": 1.722633581975407e-05,
      "loss": 0.5261,
      "step": 15893
    },
    {
      "epoch": 0.48824993088194635,
      "grad_norm": 0.3542270362377167,
      "learning_rate": 1.7226001754895194e-05,
      "loss": 0.5841,
      "step": 15894
    },
    {
      "epoch": 0.4882806500168955,
      "grad_norm": 0.32017868757247925,
      "learning_rate": 1.7225667673159485e-05,
      "loss": 0.4991,
      "step": 15895
    },
    {
      "epoch": 0.4883113691518447,
      "grad_norm": 0.3435508608818054,
      "learning_rate": 1.7225333574547723e-05,
      "loss": 0.6109,
      "step": 15896
    },
    {
      "epoch": 0.4883420882867938,
      "grad_norm": 0.37082090973854065,
      "learning_rate": 1.7224999459060696e-05,
      "loss": 0.6194,
      "step": 15897
    },
    {
      "epoch": 0.488372807421743,
      "grad_norm": 0.3775657117366791,
      "learning_rate": 1.7224665326699173e-05,
      "loss": 0.5796,
      "step": 15898
    },
    {
      "epoch": 0.48840352655669217,
      "grad_norm": 0.33849036693573,
      "learning_rate": 1.722433117746394e-05,
      "loss": 0.5733,
      "step": 15899
    },
    {
      "epoch": 0.48843424569164134,
      "grad_norm": 0.34664633870124817,
      "learning_rate": 1.722399701135578e-05,
      "loss": 0.6114,
      "step": 15900
    },
    {
      "epoch": 0.48846496482659046,
      "grad_norm": 0.38498640060424805,
      "learning_rate": 1.722366282837547e-05,
      "loss": 0.5479,
      "step": 15901
    },
    {
      "epoch": 0.48849568396153964,
      "grad_norm": 0.3946678042411804,
      "learning_rate": 1.7223328628523788e-05,
      "loss": 0.5543,
      "step": 15902
    },
    {
      "epoch": 0.4885264030964888,
      "grad_norm": 0.39596956968307495,
      "learning_rate": 1.722299441180152e-05,
      "loss": 0.605,
      "step": 15903
    },
    {
      "epoch": 0.488557122231438,
      "grad_norm": 0.3837408125400543,
      "learning_rate": 1.722266017820944e-05,
      "loss": 0.5431,
      "step": 15904
    },
    {
      "epoch": 0.4885878413663871,
      "grad_norm": 0.3592754006385803,
      "learning_rate": 1.722232592774834e-05,
      "loss": 0.5169,
      "step": 15905
    },
    {
      "epoch": 0.4886185605013363,
      "grad_norm": 0.3656991124153137,
      "learning_rate": 1.722199166041899e-05,
      "loss": 0.53,
      "step": 15906
    },
    {
      "epoch": 0.48864927963628546,
      "grad_norm": 0.34409329295158386,
      "learning_rate": 1.7221657376222173e-05,
      "loss": 0.5773,
      "step": 15907
    },
    {
      "epoch": 0.4886799987712346,
      "grad_norm": 0.37829023599624634,
      "learning_rate": 1.722132307515867e-05,
      "loss": 0.6214,
      "step": 15908
    },
    {
      "epoch": 0.48871071790618376,
      "grad_norm": 0.3640749752521515,
      "learning_rate": 1.7220988757229268e-05,
      "loss": 0.5434,
      "step": 15909
    },
    {
      "epoch": 0.48874143704113293,
      "grad_norm": 0.4148114323616028,
      "learning_rate": 1.7220654422434738e-05,
      "loss": 0.6619,
      "step": 15910
    },
    {
      "epoch": 0.4887721561760821,
      "grad_norm": 0.34272676706314087,
      "learning_rate": 1.7220320070775864e-05,
      "loss": 0.5431,
      "step": 15911
    },
    {
      "epoch": 0.4888028753110312,
      "grad_norm": 0.3647187352180481,
      "learning_rate": 1.7219985702253427e-05,
      "loss": 0.6327,
      "step": 15912
    },
    {
      "epoch": 0.4888335944459804,
      "grad_norm": 0.35863637924194336,
      "learning_rate": 1.7219651316868215e-05,
      "loss": 0.5217,
      "step": 15913
    },
    {
      "epoch": 0.4888643135809296,
      "grad_norm": 0.356777161359787,
      "learning_rate": 1.7219316914621e-05,
      "loss": 0.6392,
      "step": 15914
    },
    {
      "epoch": 0.4888950327158787,
      "grad_norm": 0.33717381954193115,
      "learning_rate": 1.7218982495512566e-05,
      "loss": 0.5728,
      "step": 15915
    },
    {
      "epoch": 0.48892575185082787,
      "grad_norm": 0.35855066776275635,
      "learning_rate": 1.72186480595437e-05,
      "loss": 0.5042,
      "step": 15916
    },
    {
      "epoch": 0.48895647098577705,
      "grad_norm": 0.35962846875190735,
      "learning_rate": 1.7218313606715168e-05,
      "loss": 0.5168,
      "step": 15917
    },
    {
      "epoch": 0.4889871901207262,
      "grad_norm": 0.36661437153816223,
      "learning_rate": 1.721797913702776e-05,
      "loss": 0.5577,
      "step": 15918
    },
    {
      "epoch": 0.48901790925567534,
      "grad_norm": 0.3442879915237427,
      "learning_rate": 1.7217644650482265e-05,
      "loss": 0.5781,
      "step": 15919
    },
    {
      "epoch": 0.4890486283906245,
      "grad_norm": 0.35320672392845154,
      "learning_rate": 1.7217310147079454e-05,
      "loss": 0.4955,
      "step": 15920
    },
    {
      "epoch": 0.4890793475255737,
      "grad_norm": 0.33456552028656006,
      "learning_rate": 1.721697562682011e-05,
      "loss": 0.578,
      "step": 15921
    },
    {
      "epoch": 0.4891100666605228,
      "grad_norm": 0.3923182785511017,
      "learning_rate": 1.7216641089705017e-05,
      "loss": 0.6727,
      "step": 15922
    },
    {
      "epoch": 0.489140785795472,
      "grad_norm": 0.3443708121776581,
      "learning_rate": 1.7216306535734956e-05,
      "loss": 0.5877,
      "step": 15923
    },
    {
      "epoch": 0.48917150493042116,
      "grad_norm": 0.3277374804019928,
      "learning_rate": 1.7215971964910704e-05,
      "loss": 0.5307,
      "step": 15924
    },
    {
      "epoch": 0.48920222406537034,
      "grad_norm": 0.31702080368995667,
      "learning_rate": 1.7215637377233048e-05,
      "loss": 0.6148,
      "step": 15925
    },
    {
      "epoch": 0.48923294320031946,
      "grad_norm": 0.34553202986717224,
      "learning_rate": 1.7215302772702767e-05,
      "loss": 0.6023,
      "step": 15926
    },
    {
      "epoch": 0.48926366233526863,
      "grad_norm": 0.32214611768722534,
      "learning_rate": 1.721496815132064e-05,
      "loss": 0.5307,
      "step": 15927
    },
    {
      "epoch": 0.4892943814702178,
      "grad_norm": 0.3310830891132355,
      "learning_rate": 1.721463351308745e-05,
      "loss": 0.6052,
      "step": 15928
    },
    {
      "epoch": 0.489325100605167,
      "grad_norm": 0.3420695960521698,
      "learning_rate": 1.7214298858003982e-05,
      "loss": 0.5951,
      "step": 15929
    },
    {
      "epoch": 0.4893558197401161,
      "grad_norm": 0.35022222995758057,
      "learning_rate": 1.7213964186071014e-05,
      "loss": 0.5641,
      "step": 15930
    },
    {
      "epoch": 0.4893865388750653,
      "grad_norm": 0.5096449851989746,
      "learning_rate": 1.721362949728933e-05,
      "loss": 0.5798,
      "step": 15931
    },
    {
      "epoch": 0.48941725801001446,
      "grad_norm": 0.35328882932662964,
      "learning_rate": 1.7213294791659714e-05,
      "loss": 0.5417,
      "step": 15932
    },
    {
      "epoch": 0.4894479771449636,
      "grad_norm": 0.34181421995162964,
      "learning_rate": 1.7212960069182937e-05,
      "loss": 0.6821,
      "step": 15933
    },
    {
      "epoch": 0.48947869627991275,
      "grad_norm": 0.35211294889450073,
      "learning_rate": 1.7212625329859794e-05,
      "loss": 0.6489,
      "step": 15934
    },
    {
      "epoch": 0.4895094154148619,
      "grad_norm": 0.3599916100502014,
      "learning_rate": 1.721229057369106e-05,
      "loss": 0.5301,
      "step": 15935
    },
    {
      "epoch": 0.4895401345498111,
      "grad_norm": 0.36995020508766174,
      "learning_rate": 1.7211955800677515e-05,
      "loss": 0.547,
      "step": 15936
    },
    {
      "epoch": 0.4895708536847602,
      "grad_norm": 0.33658236265182495,
      "learning_rate": 1.7211621010819942e-05,
      "loss": 0.5695,
      "step": 15937
    },
    {
      "epoch": 0.4896015728197094,
      "grad_norm": 0.35510754585266113,
      "learning_rate": 1.721128620411913e-05,
      "loss": 0.5609,
      "step": 15938
    },
    {
      "epoch": 0.48963229195465857,
      "grad_norm": 0.39970526099205017,
      "learning_rate": 1.721095138057585e-05,
      "loss": 0.6374,
      "step": 15939
    },
    {
      "epoch": 0.4896630110896077,
      "grad_norm": 0.3594372868537903,
      "learning_rate": 1.7210616540190893e-05,
      "loss": 0.5748,
      "step": 15940
    },
    {
      "epoch": 0.48969373022455687,
      "grad_norm": 0.40590742230415344,
      "learning_rate": 1.7210281682965035e-05,
      "loss": 0.5243,
      "step": 15941
    },
    {
      "epoch": 0.48972444935950604,
      "grad_norm": 0.3372746407985687,
      "learning_rate": 1.720994680889906e-05,
      "loss": 0.5931,
      "step": 15942
    },
    {
      "epoch": 0.4897551684944552,
      "grad_norm": 0.3546251952648163,
      "learning_rate": 1.7209611917993755e-05,
      "loss": 0.5209,
      "step": 15943
    },
    {
      "epoch": 0.48978588762940434,
      "grad_norm": 0.33368533849716187,
      "learning_rate": 1.7209277010249897e-05,
      "loss": 0.5773,
      "step": 15944
    },
    {
      "epoch": 0.4898166067643535,
      "grad_norm": 0.37039169669151306,
      "learning_rate": 1.7208942085668264e-05,
      "loss": 0.5738,
      "step": 15945
    },
    {
      "epoch": 0.4898473258993027,
      "grad_norm": 0.3568626344203949,
      "learning_rate": 1.720860714424965e-05,
      "loss": 0.5345,
      "step": 15946
    },
    {
      "epoch": 0.4898780450342518,
      "grad_norm": 0.3629536032676697,
      "learning_rate": 1.7208272185994824e-05,
      "loss": 0.5345,
      "step": 15947
    },
    {
      "epoch": 0.489908764169201,
      "grad_norm": 0.3982233703136444,
      "learning_rate": 1.7207937210904583e-05,
      "loss": 0.5649,
      "step": 15948
    },
    {
      "epoch": 0.48993948330415016,
      "grad_norm": 0.3747924268245697,
      "learning_rate": 1.7207602218979694e-05,
      "loss": 0.5651,
      "step": 15949
    },
    {
      "epoch": 0.48997020243909933,
      "grad_norm": 0.3655373156070709,
      "learning_rate": 1.720726721022095e-05,
      "loss": 0.5777,
      "step": 15950
    },
    {
      "epoch": 0.49000092157404845,
      "grad_norm": 0.3832170069217682,
      "learning_rate": 1.720693218462913e-05,
      "loss": 0.6228,
      "step": 15951
    },
    {
      "epoch": 0.49003164070899763,
      "grad_norm": 0.3464858829975128,
      "learning_rate": 1.7206597142205015e-05,
      "loss": 0.5214,
      "step": 15952
    },
    {
      "epoch": 0.4900623598439468,
      "grad_norm": 0.40284985303878784,
      "learning_rate": 1.720626208294939e-05,
      "loss": 0.5047,
      "step": 15953
    },
    {
      "epoch": 0.490093078978896,
      "grad_norm": 0.3703502118587494,
      "learning_rate": 1.7205927006863038e-05,
      "loss": 0.5994,
      "step": 15954
    },
    {
      "epoch": 0.4901237981138451,
      "grad_norm": 0.33234894275665283,
      "learning_rate": 1.7205591913946736e-05,
      "loss": 0.5281,
      "step": 15955
    },
    {
      "epoch": 0.4901545172487943,
      "grad_norm": 0.404691219329834,
      "learning_rate": 1.7205256804201275e-05,
      "loss": 0.5725,
      "step": 15956
    },
    {
      "epoch": 0.49018523638374345,
      "grad_norm": 0.31443357467651367,
      "learning_rate": 1.720492167762743e-05,
      "loss": 0.576,
      "step": 15957
    },
    {
      "epoch": 0.49021595551869257,
      "grad_norm": 0.4067179560661316,
      "learning_rate": 1.720458653422599e-05,
      "loss": 0.5589,
      "step": 15958
    },
    {
      "epoch": 0.49024667465364175,
      "grad_norm": 0.3446801006793976,
      "learning_rate": 1.7204251373997735e-05,
      "loss": 0.5724,
      "step": 15959
    },
    {
      "epoch": 0.4902773937885909,
      "grad_norm": 0.34321707487106323,
      "learning_rate": 1.7203916196943448e-05,
      "loss": 0.5256,
      "step": 15960
    },
    {
      "epoch": 0.4903081129235401,
      "grad_norm": 0.384342759847641,
      "learning_rate": 1.720358100306391e-05,
      "loss": 0.5995,
      "step": 15961
    },
    {
      "epoch": 0.4903388320584892,
      "grad_norm": 0.3465743660926819,
      "learning_rate": 1.7203245792359906e-05,
      "loss": 0.6071,
      "step": 15962
    },
    {
      "epoch": 0.4903695511934384,
      "grad_norm": 0.46132174134254456,
      "learning_rate": 1.7202910564832217e-05,
      "loss": 0.6063,
      "step": 15963
    },
    {
      "epoch": 0.49040027032838757,
      "grad_norm": 0.32500776648521423,
      "learning_rate": 1.7202575320481633e-05,
      "loss": 0.5509,
      "step": 15964
    },
    {
      "epoch": 0.4904309894633367,
      "grad_norm": 0.3419919013977051,
      "learning_rate": 1.7202240059308924e-05,
      "loss": 0.5071,
      "step": 15965
    },
    {
      "epoch": 0.49046170859828586,
      "grad_norm": 0.3790881037712097,
      "learning_rate": 1.7201904781314883e-05,
      "loss": 0.6765,
      "step": 15966
    },
    {
      "epoch": 0.49049242773323504,
      "grad_norm": 0.314590185880661,
      "learning_rate": 1.7201569486500292e-05,
      "loss": 0.5918,
      "step": 15967
    },
    {
      "epoch": 0.4905231468681842,
      "grad_norm": 0.3656451404094696,
      "learning_rate": 1.720123417486593e-05,
      "loss": 0.6002,
      "step": 15968
    },
    {
      "epoch": 0.49055386600313333,
      "grad_norm": 0.3239993453025818,
      "learning_rate": 1.7200898846412585e-05,
      "loss": 0.528,
      "step": 15969
    },
    {
      "epoch": 0.4905845851380825,
      "grad_norm": 0.387391597032547,
      "learning_rate": 1.7200563501141038e-05,
      "loss": 0.5873,
      "step": 15970
    },
    {
      "epoch": 0.4906153042730317,
      "grad_norm": 0.32247036695480347,
      "learning_rate": 1.720022813905207e-05,
      "loss": 0.5477,
      "step": 15971
    },
    {
      "epoch": 0.49064602340798086,
      "grad_norm": 0.3978271782398224,
      "learning_rate": 1.719989276014647e-05,
      "loss": 0.5197,
      "step": 15972
    },
    {
      "epoch": 0.49067674254293,
      "grad_norm": 0.3417639136314392,
      "learning_rate": 1.7199557364425015e-05,
      "loss": 0.5747,
      "step": 15973
    },
    {
      "epoch": 0.49070746167787915,
      "grad_norm": 0.38877373933792114,
      "learning_rate": 1.719922195188849e-05,
      "loss": 0.5572,
      "step": 15974
    },
    {
      "epoch": 0.49073818081282833,
      "grad_norm": 0.41728532314300537,
      "learning_rate": 1.7198886522537682e-05,
      "loss": 0.5796,
      "step": 15975
    },
    {
      "epoch": 0.49076889994777745,
      "grad_norm": 2.6907005310058594,
      "learning_rate": 1.719855107637337e-05,
      "loss": 0.5486,
      "step": 15976
    },
    {
      "epoch": 0.4907996190827266,
      "grad_norm": 0.638908863067627,
      "learning_rate": 1.7198215613396336e-05,
      "loss": 0.5757,
      "step": 15977
    },
    {
      "epoch": 0.4908303382176758,
      "grad_norm": 0.3629932403564453,
      "learning_rate": 1.719788013360737e-05,
      "loss": 0.6705,
      "step": 15978
    },
    {
      "epoch": 0.490861057352625,
      "grad_norm": 0.33054065704345703,
      "learning_rate": 1.7197544637007255e-05,
      "loss": 0.4825,
      "step": 15979
    },
    {
      "epoch": 0.4908917764875741,
      "grad_norm": 0.34882745146751404,
      "learning_rate": 1.7197209123596767e-05,
      "loss": 0.5753,
      "step": 15980
    },
    {
      "epoch": 0.49092249562252327,
      "grad_norm": 0.3333929479122162,
      "learning_rate": 1.7196873593376697e-05,
      "loss": 0.4786,
      "step": 15981
    },
    {
      "epoch": 0.49095321475747244,
      "grad_norm": 0.37686389684677124,
      "learning_rate": 1.7196538046347825e-05,
      "loss": 0.5443,
      "step": 15982
    },
    {
      "epoch": 0.49098393389242156,
      "grad_norm": 0.39397892355918884,
      "learning_rate": 1.7196202482510938e-05,
      "loss": 0.5786,
      "step": 15983
    },
    {
      "epoch": 0.49101465302737074,
      "grad_norm": 0.34501469135284424,
      "learning_rate": 1.7195866901866817e-05,
      "loss": 0.5406,
      "step": 15984
    },
    {
      "epoch": 0.4910453721623199,
      "grad_norm": 0.34266284108161926,
      "learning_rate": 1.7195531304416245e-05,
      "loss": 0.4599,
      "step": 15985
    },
    {
      "epoch": 0.4910760912972691,
      "grad_norm": 0.33105459809303284,
      "learning_rate": 1.7195195690160007e-05,
      "loss": 0.56,
      "step": 15986
    },
    {
      "epoch": 0.4911068104322182,
      "grad_norm": 0.5027540922164917,
      "learning_rate": 1.7194860059098886e-05,
      "loss": 0.4995,
      "step": 15987
    },
    {
      "epoch": 0.4911375295671674,
      "grad_norm": 0.3897055983543396,
      "learning_rate": 1.7194524411233668e-05,
      "loss": 0.5434,
      "step": 15988
    },
    {
      "epoch": 0.49116824870211656,
      "grad_norm": 0.3765660524368286,
      "learning_rate": 1.7194188746565135e-05,
      "loss": 0.587,
      "step": 15989
    },
    {
      "epoch": 0.4911989678370657,
      "grad_norm": 0.3867647647857666,
      "learning_rate": 1.719385306509407e-05,
      "loss": 0.6191,
      "step": 15990
    },
    {
      "epoch": 0.49122968697201486,
      "grad_norm": 0.3250269293785095,
      "learning_rate": 1.7193517366821266e-05,
      "loss": 0.581,
      "step": 15991
    },
    {
      "epoch": 0.49126040610696403,
      "grad_norm": 0.3176504373550415,
      "learning_rate": 1.7193181651747493e-05,
      "loss": 0.641,
      "step": 15992
    },
    {
      "epoch": 0.4912911252419132,
      "grad_norm": 0.36668869853019714,
      "learning_rate": 1.7192845919873548e-05,
      "loss": 0.4744,
      "step": 15993
    },
    {
      "epoch": 0.4913218443768623,
      "grad_norm": 0.3366771936416626,
      "learning_rate": 1.7192510171200205e-05,
      "loss": 0.4658,
      "step": 15994
    },
    {
      "epoch": 0.4913525635118115,
      "grad_norm": 0.3701540231704712,
      "learning_rate": 1.719217440572825e-05,
      "loss": 0.5502,
      "step": 15995
    },
    {
      "epoch": 0.4913832826467607,
      "grad_norm": 0.38739246129989624,
      "learning_rate": 1.7191838623458473e-05,
      "loss": 0.673,
      "step": 15996
    },
    {
      "epoch": 0.49141400178170985,
      "grad_norm": 0.4320903420448303,
      "learning_rate": 1.7191502824391653e-05,
      "loss": 0.5727,
      "step": 15997
    },
    {
      "epoch": 0.491444720916659,
      "grad_norm": 0.3210753798484802,
      "learning_rate": 1.7191167008528577e-05,
      "loss": 0.6042,
      "step": 15998
    },
    {
      "epoch": 0.49147544005160815,
      "grad_norm": 0.33243492245674133,
      "learning_rate": 1.7190831175870026e-05,
      "loss": 0.5327,
      "step": 15999
    },
    {
      "epoch": 0.4915061591865573,
      "grad_norm": 0.35336172580718994,
      "learning_rate": 1.719049532641679e-05,
      "loss": 0.5363,
      "step": 16000
    },
    {
      "epoch": 0.49153687832150644,
      "grad_norm": 0.40095287561416626,
      "learning_rate": 1.7190159460169647e-05,
      "loss": 0.654,
      "step": 16001
    },
    {
      "epoch": 0.4915675974564556,
      "grad_norm": 0.3448103964328766,
      "learning_rate": 1.7189823577129384e-05,
      "loss": 0.536,
      "step": 16002
    },
    {
      "epoch": 0.4915983165914048,
      "grad_norm": 0.3580012917518616,
      "learning_rate": 1.7189487677296787e-05,
      "loss": 0.618,
      "step": 16003
    },
    {
      "epoch": 0.49162903572635397,
      "grad_norm": 0.36454641819000244,
      "learning_rate": 1.718915176067264e-05,
      "loss": 0.6052,
      "step": 16004
    },
    {
      "epoch": 0.4916597548613031,
      "grad_norm": 0.35853850841522217,
      "learning_rate": 1.7188815827257728e-05,
      "loss": 0.5319,
      "step": 16005
    },
    {
      "epoch": 0.49169047399625226,
      "grad_norm": 0.3889722228050232,
      "learning_rate": 1.7188479877052834e-05,
      "loss": 0.5022,
      "step": 16006
    },
    {
      "epoch": 0.49172119313120144,
      "grad_norm": 0.34823039174079895,
      "learning_rate": 1.718814391005874e-05,
      "loss": 0.5774,
      "step": 16007
    },
    {
      "epoch": 0.49175191226615056,
      "grad_norm": 2.135704517364502,
      "learning_rate": 1.7187807926276238e-05,
      "loss": 0.6254,
      "step": 16008
    },
    {
      "epoch": 0.49178263140109973,
      "grad_norm": 0.344096302986145,
      "learning_rate": 1.7187471925706108e-05,
      "loss": 0.5091,
      "step": 16009
    },
    {
      "epoch": 0.4918133505360489,
      "grad_norm": 0.36905211210250854,
      "learning_rate": 1.7187135908349133e-05,
      "loss": 0.6049,
      "step": 16010
    },
    {
      "epoch": 0.4918440696709981,
      "grad_norm": 0.3473510444164276,
      "learning_rate": 1.7186799874206103e-05,
      "loss": 0.5902,
      "step": 16011
    },
    {
      "epoch": 0.4918747888059472,
      "grad_norm": 0.35697996616363525,
      "learning_rate": 1.7186463823277797e-05,
      "loss": 0.576,
      "step": 16012
    },
    {
      "epoch": 0.4919055079408964,
      "grad_norm": 0.32782480120658875,
      "learning_rate": 1.7186127755565002e-05,
      "loss": 0.6106,
      "step": 16013
    },
    {
      "epoch": 0.49193622707584556,
      "grad_norm": 0.38466644287109375,
      "learning_rate": 1.718579167106851e-05,
      "loss": 0.574,
      "step": 16014
    },
    {
      "epoch": 0.49196694621079473,
      "grad_norm": 0.3448604941368103,
      "learning_rate": 1.7185455569789096e-05,
      "loss": 0.6363,
      "step": 16015
    },
    {
      "epoch": 0.49199766534574385,
      "grad_norm": 0.35466739535331726,
      "learning_rate": 1.7185119451727547e-05,
      "loss": 0.5555,
      "step": 16016
    },
    {
      "epoch": 0.492028384480693,
      "grad_norm": 0.3831886947154999,
      "learning_rate": 1.718478331688465e-05,
      "loss": 0.5152,
      "step": 16017
    },
    {
      "epoch": 0.4920591036156422,
      "grad_norm": 0.4321788251399994,
      "learning_rate": 1.7184447165261193e-05,
      "loss": 0.5393,
      "step": 16018
    },
    {
      "epoch": 0.4920898227505913,
      "grad_norm": 0.3472183048725128,
      "learning_rate": 1.7184110996857955e-05,
      "loss": 0.5427,
      "step": 16019
    },
    {
      "epoch": 0.4921205418855405,
      "grad_norm": 0.37314435839653015,
      "learning_rate": 1.7183774811675724e-05,
      "loss": 0.5798,
      "step": 16020
    },
    {
      "epoch": 0.49215126102048967,
      "grad_norm": 0.3447956442832947,
      "learning_rate": 1.7183438609715287e-05,
      "loss": 0.5507,
      "step": 16021
    },
    {
      "epoch": 0.49218198015543885,
      "grad_norm": 0.39391323924064636,
      "learning_rate": 1.7183102390977425e-05,
      "loss": 0.5768,
      "step": 16022
    },
    {
      "epoch": 0.49221269929038797,
      "grad_norm": 0.34334754943847656,
      "learning_rate": 1.7182766155462927e-05,
      "loss": 0.4469,
      "step": 16023
    },
    {
      "epoch": 0.49224341842533714,
      "grad_norm": 0.35707321763038635,
      "learning_rate": 1.718242990317258e-05,
      "loss": 0.6259,
      "step": 16024
    },
    {
      "epoch": 0.4922741375602863,
      "grad_norm": 0.31464534997940063,
      "learning_rate": 1.718209363410716e-05,
      "loss": 0.5927,
      "step": 16025
    },
    {
      "epoch": 0.49230485669523544,
      "grad_norm": 0.4825928509235382,
      "learning_rate": 1.7181757348267464e-05,
      "loss": 0.6371,
      "step": 16026
    },
    {
      "epoch": 0.4923355758301846,
      "grad_norm": 0.33679071068763733,
      "learning_rate": 1.718142104565427e-05,
      "loss": 0.521,
      "step": 16027
    },
    {
      "epoch": 0.4923662949651338,
      "grad_norm": 0.39400866627693176,
      "learning_rate": 1.718108472626837e-05,
      "loss": 0.5891,
      "step": 16028
    },
    {
      "epoch": 0.49239701410008296,
      "grad_norm": 0.40643712878227234,
      "learning_rate": 1.718074839011054e-05,
      "loss": 0.5879,
      "step": 16029
    },
    {
      "epoch": 0.4924277332350321,
      "grad_norm": 0.36848461627960205,
      "learning_rate": 1.718041203718157e-05,
      "loss": 0.6275,
      "step": 16030
    },
    {
      "epoch": 0.49245845236998126,
      "grad_norm": 0.38838720321655273,
      "learning_rate": 1.718007566748225e-05,
      "loss": 0.5839,
      "step": 16031
    },
    {
      "epoch": 0.49248917150493043,
      "grad_norm": 0.34465518593788147,
      "learning_rate": 1.717973928101336e-05,
      "loss": 0.6502,
      "step": 16032
    },
    {
      "epoch": 0.49251989063987955,
      "grad_norm": 0.34617599844932556,
      "learning_rate": 1.7179402877775685e-05,
      "loss": 0.5916,
      "step": 16033
    },
    {
      "epoch": 0.49255060977482873,
      "grad_norm": 0.352142333984375,
      "learning_rate": 1.7179066457770015e-05,
      "loss": 0.5434,
      "step": 16034
    },
    {
      "epoch": 0.4925813289097779,
      "grad_norm": 0.4902478754520416,
      "learning_rate": 1.7178730020997138e-05,
      "loss": 0.6307,
      "step": 16035
    },
    {
      "epoch": 0.4926120480447271,
      "grad_norm": 0.9816870093345642,
      "learning_rate": 1.717839356745783e-05,
      "loss": 0.5148,
      "step": 16036
    },
    {
      "epoch": 0.4926427671796762,
      "grad_norm": 0.3303186893463135,
      "learning_rate": 1.7178057097152887e-05,
      "loss": 0.4978,
      "step": 16037
    },
    {
      "epoch": 0.4926734863146254,
      "grad_norm": 0.4133071005344391,
      "learning_rate": 1.7177720610083085e-05,
      "loss": 0.5698,
      "step": 16038
    },
    {
      "epoch": 0.49270420544957455,
      "grad_norm": 0.46532776951789856,
      "learning_rate": 1.717738410624922e-05,
      "loss": 0.5392,
      "step": 16039
    },
    {
      "epoch": 0.4927349245845237,
      "grad_norm": 0.5220268368721008,
      "learning_rate": 1.717704758565207e-05,
      "loss": 0.5472,
      "step": 16040
    },
    {
      "epoch": 0.49276564371947285,
      "grad_norm": 0.32274192571640015,
      "learning_rate": 1.7176711048292426e-05,
      "loss": 0.5716,
      "step": 16041
    },
    {
      "epoch": 0.492796362854422,
      "grad_norm": 0.3315335810184479,
      "learning_rate": 1.7176374494171072e-05,
      "loss": 0.5312,
      "step": 16042
    },
    {
      "epoch": 0.4928270819893712,
      "grad_norm": 0.34962522983551025,
      "learning_rate": 1.7176037923288793e-05,
      "loss": 0.6082,
      "step": 16043
    },
    {
      "epoch": 0.4928578011243203,
      "grad_norm": 0.37167149782180786,
      "learning_rate": 1.7175701335646375e-05,
      "loss": 0.6236,
      "step": 16044
    },
    {
      "epoch": 0.4928885202592695,
      "grad_norm": 0.43113940954208374,
      "learning_rate": 1.717536473124461e-05,
      "loss": 0.6023,
      "step": 16045
    },
    {
      "epoch": 0.49291923939421867,
      "grad_norm": 0.3376847803592682,
      "learning_rate": 1.717502811008428e-05,
      "loss": 0.5826,
      "step": 16046
    },
    {
      "epoch": 0.49294995852916784,
      "grad_norm": 0.3770450949668884,
      "learning_rate": 1.7174691472166162e-05,
      "loss": 0.5372,
      "step": 16047
    },
    {
      "epoch": 0.49298067766411696,
      "grad_norm": 0.3559330105781555,
      "learning_rate": 1.717435481749106e-05,
      "loss": 0.5777,
      "step": 16048
    },
    {
      "epoch": 0.49301139679906614,
      "grad_norm": 0.3275180757045746,
      "learning_rate": 1.7174018146059747e-05,
      "loss": 0.5757,
      "step": 16049
    },
    {
      "epoch": 0.4930421159340153,
      "grad_norm": 0.35165905952453613,
      "learning_rate": 1.7173681457873014e-05,
      "loss": 0.5506,
      "step": 16050
    },
    {
      "epoch": 0.49307283506896443,
      "grad_norm": 0.45063549280166626,
      "learning_rate": 1.7173344752931647e-05,
      "loss": 0.5324,
      "step": 16051
    },
    {
      "epoch": 0.4931035542039136,
      "grad_norm": 0.36685696244239807,
      "learning_rate": 1.7173008031236432e-05,
      "loss": 0.4984,
      "step": 16052
    },
    {
      "epoch": 0.4931342733388628,
      "grad_norm": 0.3967823386192322,
      "learning_rate": 1.717267129278816e-05,
      "loss": 0.6595,
      "step": 16053
    },
    {
      "epoch": 0.49316499247381196,
      "grad_norm": 0.3795524835586548,
      "learning_rate": 1.7172334537587608e-05,
      "loss": 0.5214,
      "step": 16054
    },
    {
      "epoch": 0.4931957116087611,
      "grad_norm": 0.3710382878780365,
      "learning_rate": 1.717199776563557e-05,
      "loss": 0.6455,
      "step": 16055
    },
    {
      "epoch": 0.49322643074371025,
      "grad_norm": 0.3118261396884918,
      "learning_rate": 1.717166097693283e-05,
      "loss": 0.5051,
      "step": 16056
    },
    {
      "epoch": 0.49325714987865943,
      "grad_norm": 0.3151918649673462,
      "learning_rate": 1.7171324171480175e-05,
      "loss": 0.4948,
      "step": 16057
    },
    {
      "epoch": 0.4932878690136086,
      "grad_norm": 0.3697718381881714,
      "learning_rate": 1.7170987349278393e-05,
      "loss": 0.6015,
      "step": 16058
    },
    {
      "epoch": 0.4933185881485577,
      "grad_norm": 0.4274137020111084,
      "learning_rate": 1.7170650510328265e-05,
      "loss": 0.6054,
      "step": 16059
    },
    {
      "epoch": 0.4933493072835069,
      "grad_norm": 0.401314914226532,
      "learning_rate": 1.7170313654630585e-05,
      "loss": 0.5725,
      "step": 16060
    },
    {
      "epoch": 0.4933800264184561,
      "grad_norm": 0.35845813155174255,
      "learning_rate": 1.716997678218614e-05,
      "loss": 0.5674,
      "step": 16061
    },
    {
      "epoch": 0.4934107455534052,
      "grad_norm": 0.40052810311317444,
      "learning_rate": 1.7169639892995705e-05,
      "loss": 0.5766,
      "step": 16062
    },
    {
      "epoch": 0.49344146468835437,
      "grad_norm": 0.33729133009910583,
      "learning_rate": 1.716930298706008e-05,
      "loss": 0.5981,
      "step": 16063
    },
    {
      "epoch": 0.49347218382330355,
      "grad_norm": 0.37705668807029724,
      "learning_rate": 1.7168966064380052e-05,
      "loss": 0.553,
      "step": 16064
    },
    {
      "epoch": 0.4935029029582527,
      "grad_norm": 0.34886062145233154,
      "learning_rate": 1.7168629124956394e-05,
      "loss": 0.5247,
      "step": 16065
    },
    {
      "epoch": 0.49353362209320184,
      "grad_norm": 0.3646026849746704,
      "learning_rate": 1.716829216878991e-05,
      "loss": 0.5737,
      "step": 16066
    },
    {
      "epoch": 0.493564341228151,
      "grad_norm": 0.3678354322910309,
      "learning_rate": 1.7167955195881372e-05,
      "loss": 0.5171,
      "step": 16067
    },
    {
      "epoch": 0.4935950603631002,
      "grad_norm": 0.36062222719192505,
      "learning_rate": 1.716761820623158e-05,
      "loss": 0.6057,
      "step": 16068
    },
    {
      "epoch": 0.4936257794980493,
      "grad_norm": 0.35474568605422974,
      "learning_rate": 1.716728119984131e-05,
      "loss": 0.5549,
      "step": 16069
    },
    {
      "epoch": 0.4936564986329985,
      "grad_norm": 0.35734543204307556,
      "learning_rate": 1.716694417671136e-05,
      "loss": 0.5149,
      "step": 16070
    },
    {
      "epoch": 0.49368721776794766,
      "grad_norm": 0.3781082034111023,
      "learning_rate": 1.7166607136842504e-05,
      "loss": 0.555,
      "step": 16071
    },
    {
      "epoch": 0.49371793690289684,
      "grad_norm": 0.42131608724594116,
      "learning_rate": 1.716627008023554e-05,
      "loss": 0.5474,
      "step": 16072
    },
    {
      "epoch": 0.49374865603784596,
      "grad_norm": 0.32663312554359436,
      "learning_rate": 1.7165933006891258e-05,
      "loss": 0.5163,
      "step": 16073
    },
    {
      "epoch": 0.49377937517279513,
      "grad_norm": 0.38046297430992126,
      "learning_rate": 1.716559591681043e-05,
      "loss": 0.5158,
      "step": 16074
    },
    {
      "epoch": 0.4938100943077443,
      "grad_norm": 0.416147917509079,
      "learning_rate": 1.7165258809993858e-05,
      "loss": 0.5547,
      "step": 16075
    },
    {
      "epoch": 0.4938408134426934,
      "grad_norm": 0.34778517484664917,
      "learning_rate": 1.716492168644232e-05,
      "loss": 0.5739,
      "step": 16076
    },
    {
      "epoch": 0.4938715325776426,
      "grad_norm": 0.3457213044166565,
      "learning_rate": 1.716458454615661e-05,
      "loss": 0.6156,
      "step": 16077
    },
    {
      "epoch": 0.4939022517125918,
      "grad_norm": 0.3516850173473358,
      "learning_rate": 1.716424738913751e-05,
      "loss": 0.5882,
      "step": 16078
    },
    {
      "epoch": 0.49393297084754095,
      "grad_norm": 0.37466177344322205,
      "learning_rate": 1.7163910215385812e-05,
      "loss": 0.5476,
      "step": 16079
    },
    {
      "epoch": 0.4939636899824901,
      "grad_norm": 0.3767796754837036,
      "learning_rate": 1.7163573024902297e-05,
      "loss": 0.5446,
      "step": 16080
    },
    {
      "epoch": 0.49399440911743925,
      "grad_norm": 0.44943153858184814,
      "learning_rate": 1.716323581768776e-05,
      "loss": 0.66,
      "step": 16081
    },
    {
      "epoch": 0.4940251282523884,
      "grad_norm": 0.3208168148994446,
      "learning_rate": 1.7162898593742987e-05,
      "loss": 0.5191,
      "step": 16082
    },
    {
      "epoch": 0.4940558473873376,
      "grad_norm": 0.36784353852272034,
      "learning_rate": 1.716256135306876e-05,
      "loss": 0.6083,
      "step": 16083
    },
    {
      "epoch": 0.4940865665222867,
      "grad_norm": 0.39920157194137573,
      "learning_rate": 1.7162224095665875e-05,
      "loss": 0.5462,
      "step": 16084
    },
    {
      "epoch": 0.4941172856572359,
      "grad_norm": 0.355293869972229,
      "learning_rate": 1.7161886821535115e-05,
      "loss": 0.4973,
      "step": 16085
    },
    {
      "epoch": 0.49414800479218507,
      "grad_norm": 0.32970768213272095,
      "learning_rate": 1.7161549530677267e-05,
      "loss": 0.4866,
      "step": 16086
    },
    {
      "epoch": 0.4941787239271342,
      "grad_norm": 0.3696924149990082,
      "learning_rate": 1.7161212223093117e-05,
      "loss": 0.5848,
      "step": 16087
    },
    {
      "epoch": 0.49420944306208336,
      "grad_norm": 0.3471986651420593,
      "learning_rate": 1.716087489878346e-05,
      "loss": 0.5317,
      "step": 16088
    },
    {
      "epoch": 0.49424016219703254,
      "grad_norm": 0.3719319701194763,
      "learning_rate": 1.716053755774908e-05,
      "loss": 0.6401,
      "step": 16089
    },
    {
      "epoch": 0.4942708813319817,
      "grad_norm": 0.33937063813209534,
      "learning_rate": 1.7160200199990763e-05,
      "loss": 0.4947,
      "step": 16090
    },
    {
      "epoch": 0.49430160046693083,
      "grad_norm": 0.5480024814605713,
      "learning_rate": 1.7159862825509295e-05,
      "loss": 0.509,
      "step": 16091
    },
    {
      "epoch": 0.49433231960188,
      "grad_norm": 0.3286420702934265,
      "learning_rate": 1.715952543430547e-05,
      "loss": 0.572,
      "step": 16092
    },
    {
      "epoch": 0.4943630387368292,
      "grad_norm": 0.3450336456298828,
      "learning_rate": 1.7159188026380073e-05,
      "loss": 0.5834,
      "step": 16093
    },
    {
      "epoch": 0.4943937578717783,
      "grad_norm": 0.33128631114959717,
      "learning_rate": 1.7158850601733892e-05,
      "loss": 0.5377,
      "step": 16094
    },
    {
      "epoch": 0.4944244770067275,
      "grad_norm": 0.33700403571128845,
      "learning_rate": 1.715851316036772e-05,
      "loss": 0.4692,
      "step": 16095
    },
    {
      "epoch": 0.49445519614167666,
      "grad_norm": 0.3744939863681793,
      "learning_rate": 1.7158175702282334e-05,
      "loss": 0.6211,
      "step": 16096
    },
    {
      "epoch": 0.49448591527662583,
      "grad_norm": 0.3428981900215149,
      "learning_rate": 1.7157838227478532e-05,
      "loss": 0.6094,
      "step": 16097
    },
    {
      "epoch": 0.49451663441157495,
      "grad_norm": 0.3690149188041687,
      "learning_rate": 1.71575007359571e-05,
      "loss": 0.5549,
      "step": 16098
    },
    {
      "epoch": 0.4945473535465241,
      "grad_norm": 0.34965240955352783,
      "learning_rate": 1.7157163227718822e-05,
      "loss": 0.6032,
      "step": 16099
    },
    {
      "epoch": 0.4945780726814733,
      "grad_norm": 0.4417994022369385,
      "learning_rate": 1.715682570276449e-05,
      "loss": 0.5995,
      "step": 16100
    },
    {
      "epoch": 0.4946087918164225,
      "grad_norm": 0.36217060685157776,
      "learning_rate": 1.7156488161094894e-05,
      "loss": 0.5355,
      "step": 16101
    },
    {
      "epoch": 0.4946395109513716,
      "grad_norm": 0.3584793508052826,
      "learning_rate": 1.7156150602710817e-05,
      "loss": 0.5402,
      "step": 16102
    },
    {
      "epoch": 0.4946702300863208,
      "grad_norm": 0.3597504496574402,
      "learning_rate": 1.7155813027613052e-05,
      "loss": 0.5762,
      "step": 16103
    },
    {
      "epoch": 0.49470094922126995,
      "grad_norm": 0.38149338960647583,
      "learning_rate": 1.7155475435802385e-05,
      "loss": 0.576,
      "step": 16104
    },
    {
      "epoch": 0.49473166835621907,
      "grad_norm": 0.3648521900177002,
      "learning_rate": 1.715513782727961e-05,
      "loss": 0.5698,
      "step": 16105
    },
    {
      "epoch": 0.49476238749116824,
      "grad_norm": 0.3678721785545349,
      "learning_rate": 1.7154800202045507e-05,
      "loss": 0.5719,
      "step": 16106
    },
    {
      "epoch": 0.4947931066261174,
      "grad_norm": 0.3797542154788971,
      "learning_rate": 1.715446256010087e-05,
      "loss": 0.6289,
      "step": 16107
    },
    {
      "epoch": 0.4948238257610666,
      "grad_norm": 0.34845229983329773,
      "learning_rate": 1.7154124901446484e-05,
      "loss": 0.5184,
      "step": 16108
    },
    {
      "epoch": 0.4948545448960157,
      "grad_norm": 0.3655673563480377,
      "learning_rate": 1.7153787226083142e-05,
      "loss": 0.5185,
      "step": 16109
    },
    {
      "epoch": 0.4948852640309649,
      "grad_norm": 0.382609486579895,
      "learning_rate": 1.7153449534011632e-05,
      "loss": 0.547,
      "step": 16110
    },
    {
      "epoch": 0.49491598316591406,
      "grad_norm": 0.3145591616630554,
      "learning_rate": 1.7153111825232732e-05,
      "loss": 0.527,
      "step": 16111
    },
    {
      "epoch": 0.4949467023008632,
      "grad_norm": 0.39271795749664307,
      "learning_rate": 1.715277409974725e-05,
      "loss": 0.6052,
      "step": 16112
    },
    {
      "epoch": 0.49497742143581236,
      "grad_norm": 0.34911495447158813,
      "learning_rate": 1.715243635755596e-05,
      "loss": 0.6011,
      "step": 16113
    },
    {
      "epoch": 0.49500814057076153,
      "grad_norm": 0.3439100384712219,
      "learning_rate": 1.7152098598659654e-05,
      "loss": 0.6112,
      "step": 16114
    },
    {
      "epoch": 0.4950388597057107,
      "grad_norm": 0.3450501561164856,
      "learning_rate": 1.7151760823059124e-05,
      "loss": 0.6309,
      "step": 16115
    },
    {
      "epoch": 0.49506957884065983,
      "grad_norm": 0.38133254647254944,
      "learning_rate": 1.7151423030755156e-05,
      "loss": 0.6096,
      "step": 16116
    },
    {
      "epoch": 0.495100297975609,
      "grad_norm": 0.35599085688591003,
      "learning_rate": 1.7151085221748545e-05,
      "loss": 0.5788,
      "step": 16117
    },
    {
      "epoch": 0.4951310171105582,
      "grad_norm": 0.32541441917419434,
      "learning_rate": 1.715074739604007e-05,
      "loss": 0.4408,
      "step": 16118
    },
    {
      "epoch": 0.4951617362455073,
      "grad_norm": 0.3311357796192169,
      "learning_rate": 1.7150409553630525e-05,
      "loss": 0.5301,
      "step": 16119
    },
    {
      "epoch": 0.4951924553804565,
      "grad_norm": 0.3449161648750305,
      "learning_rate": 1.71500716945207e-05,
      "loss": 0.5945,
      "step": 16120
    },
    {
      "epoch": 0.49522317451540565,
      "grad_norm": 0.3509666323661804,
      "learning_rate": 1.7149733818711384e-05,
      "loss": 0.475,
      "step": 16121
    },
    {
      "epoch": 0.4952538936503548,
      "grad_norm": 0.37429752945899963,
      "learning_rate": 1.7149395926203364e-05,
      "loss": 0.5978,
      "step": 16122
    },
    {
      "epoch": 0.49528461278530395,
      "grad_norm": 0.36888429522514343,
      "learning_rate": 1.714905801699743e-05,
      "loss": 0.5358,
      "step": 16123
    },
    {
      "epoch": 0.4953153319202531,
      "grad_norm": 0.5444343686103821,
      "learning_rate": 1.7148720091094374e-05,
      "loss": 0.6178,
      "step": 16124
    },
    {
      "epoch": 0.4953460510552023,
      "grad_norm": 0.35884007811546326,
      "learning_rate": 1.7148382148494983e-05,
      "loss": 0.4773,
      "step": 16125
    },
    {
      "epoch": 0.49537677019015147,
      "grad_norm": 0.34825074672698975,
      "learning_rate": 1.7148044189200045e-05,
      "loss": 0.5269,
      "step": 16126
    },
    {
      "epoch": 0.4954074893251006,
      "grad_norm": 0.3232600688934326,
      "learning_rate": 1.7147706213210354e-05,
      "loss": 0.5016,
      "step": 16127
    },
    {
      "epoch": 0.49543820846004977,
      "grad_norm": 0.38211506605148315,
      "learning_rate": 1.7147368220526692e-05,
      "loss": 0.5622,
      "step": 16128
    },
    {
      "epoch": 0.49546892759499894,
      "grad_norm": 0.3782847821712494,
      "learning_rate": 1.714703021114985e-05,
      "loss": 0.6019,
      "step": 16129
    },
    {
      "epoch": 0.49549964672994806,
      "grad_norm": 0.386857271194458,
      "learning_rate": 1.7146692185080624e-05,
      "loss": 0.6399,
      "step": 16130
    },
    {
      "epoch": 0.49553036586489724,
      "grad_norm": 0.33477017283439636,
      "learning_rate": 1.71463541423198e-05,
      "loss": 0.6053,
      "step": 16131
    },
    {
      "epoch": 0.4955610849998464,
      "grad_norm": 0.34124788641929626,
      "learning_rate": 1.7146016082868166e-05,
      "loss": 0.5582,
      "step": 16132
    },
    {
      "epoch": 0.4955918041347956,
      "grad_norm": 0.3470323085784912,
      "learning_rate": 1.7145678006726513e-05,
      "loss": 0.5648,
      "step": 16133
    },
    {
      "epoch": 0.4956225232697447,
      "grad_norm": 0.40263572335243225,
      "learning_rate": 1.7145339913895624e-05,
      "loss": 0.5413,
      "step": 16134
    },
    {
      "epoch": 0.4956532424046939,
      "grad_norm": 0.4672381579875946,
      "learning_rate": 1.71450018043763e-05,
      "loss": 0.6231,
      "step": 16135
    },
    {
      "epoch": 0.49568396153964306,
      "grad_norm": 0.3611113131046295,
      "learning_rate": 1.7144663678169324e-05,
      "loss": 0.5536,
      "step": 16136
    },
    {
      "epoch": 0.4957146806745922,
      "grad_norm": 0.337490051984787,
      "learning_rate": 1.7144325535275488e-05,
      "loss": 0.5541,
      "step": 16137
    },
    {
      "epoch": 0.49574539980954135,
      "grad_norm": 0.3622978925704956,
      "learning_rate": 1.714398737569558e-05,
      "loss": 0.6305,
      "step": 16138
    },
    {
      "epoch": 0.49577611894449053,
      "grad_norm": 0.3460816442966461,
      "learning_rate": 1.714364919943039e-05,
      "loss": 0.5686,
      "step": 16139
    },
    {
      "epoch": 0.4958068380794397,
      "grad_norm": 0.3648105263710022,
      "learning_rate": 1.714331100648071e-05,
      "loss": 0.6393,
      "step": 16140
    },
    {
      "epoch": 0.4958375572143888,
      "grad_norm": 0.3274463713169098,
      "learning_rate": 1.7142972796847324e-05,
      "loss": 0.4825,
      "step": 16141
    },
    {
      "epoch": 0.495868276349338,
      "grad_norm": 0.3044370412826538,
      "learning_rate": 1.7142634570531033e-05,
      "loss": 0.5528,
      "step": 16142
    },
    {
      "epoch": 0.4958989954842872,
      "grad_norm": 0.39903002977371216,
      "learning_rate": 1.7142296327532614e-05,
      "loss": 0.6012,
      "step": 16143
    },
    {
      "epoch": 0.4959297146192363,
      "grad_norm": 0.3569788932800293,
      "learning_rate": 1.714195806785287e-05,
      "loss": 0.562,
      "step": 16144
    },
    {
      "epoch": 0.49596043375418547,
      "grad_norm": 0.3397604525089264,
      "learning_rate": 1.7141619791492577e-05,
      "loss": 0.5701,
      "step": 16145
    },
    {
      "epoch": 0.49599115288913465,
      "grad_norm": 0.41729697585105896,
      "learning_rate": 1.7141281498452536e-05,
      "loss": 0.5376,
      "step": 16146
    },
    {
      "epoch": 0.4960218720240838,
      "grad_norm": 0.33528459072113037,
      "learning_rate": 1.714094318873353e-05,
      "loss": 0.5371,
      "step": 16147
    },
    {
      "epoch": 0.49605259115903294,
      "grad_norm": 0.34427887201309204,
      "learning_rate": 1.7140604862336357e-05,
      "loss": 0.4686,
      "step": 16148
    },
    {
      "epoch": 0.4960833102939821,
      "grad_norm": 0.329799085855484,
      "learning_rate": 1.7140266519261798e-05,
      "loss": 0.6136,
      "step": 16149
    },
    {
      "epoch": 0.4961140294289313,
      "grad_norm": 0.34208717942237854,
      "learning_rate": 1.713992815951065e-05,
      "loss": 0.5686,
      "step": 16150
    },
    {
      "epoch": 0.49614474856388047,
      "grad_norm": 0.3535095453262329,
      "learning_rate": 1.7139589783083702e-05,
      "loss": 0.5286,
      "step": 16151
    },
    {
      "epoch": 0.4961754676988296,
      "grad_norm": 0.5538643002510071,
      "learning_rate": 1.7139251389981744e-05,
      "loss": 0.5537,
      "step": 16152
    },
    {
      "epoch": 0.49620618683377876,
      "grad_norm": 0.4334535598754883,
      "learning_rate": 1.7138912980205567e-05,
      "loss": 0.5685,
      "step": 16153
    },
    {
      "epoch": 0.49623690596872794,
      "grad_norm": 0.34803977608680725,
      "learning_rate": 1.713857455375596e-05,
      "loss": 0.5357,
      "step": 16154
    },
    {
      "epoch": 0.49626762510367706,
      "grad_norm": 0.6416824460029602,
      "learning_rate": 1.7138236110633707e-05,
      "loss": 0.5432,
      "step": 16155
    },
    {
      "epoch": 0.49629834423862623,
      "grad_norm": 0.35345712304115295,
      "learning_rate": 1.713789765083961e-05,
      "loss": 0.5441,
      "step": 16156
    },
    {
      "epoch": 0.4963290633735754,
      "grad_norm": 0.3570508360862732,
      "learning_rate": 1.7137559174374452e-05,
      "loss": 0.5411,
      "step": 16157
    },
    {
      "epoch": 0.4963597825085246,
      "grad_norm": 0.3510949909687042,
      "learning_rate": 1.7137220681239032e-05,
      "loss": 0.543,
      "step": 16158
    },
    {
      "epoch": 0.4963905016434737,
      "grad_norm": 0.34698042273521423,
      "learning_rate": 1.713688217143413e-05,
      "loss": 0.6281,
      "step": 16159
    },
    {
      "epoch": 0.4964212207784229,
      "grad_norm": 0.2928002178668976,
      "learning_rate": 1.713654364496054e-05,
      "loss": 0.5355,
      "step": 16160
    },
    {
      "epoch": 0.49645193991337205,
      "grad_norm": 0.3539695739746094,
      "learning_rate": 1.713620510181906e-05,
      "loss": 0.6011,
      "step": 16161
    },
    {
      "epoch": 0.4964826590483212,
      "grad_norm": 0.38938942551612854,
      "learning_rate": 1.7135866542010467e-05,
      "loss": 0.589,
      "step": 16162
    },
    {
      "epoch": 0.49651337818327035,
      "grad_norm": 0.3361605703830719,
      "learning_rate": 1.7135527965535566e-05,
      "loss": 0.4858,
      "step": 16163
    },
    {
      "epoch": 0.4965440973182195,
      "grad_norm": 0.3446982800960541,
      "learning_rate": 1.7135189372395136e-05,
      "loss": 0.5482,
      "step": 16164
    },
    {
      "epoch": 0.4965748164531687,
      "grad_norm": 0.34511733055114746,
      "learning_rate": 1.7134850762589974e-05,
      "loss": 0.5856,
      "step": 16165
    },
    {
      "epoch": 0.4966055355881178,
      "grad_norm": 0.29298555850982666,
      "learning_rate": 1.713451213612087e-05,
      "loss": 0.5721,
      "step": 16166
    },
    {
      "epoch": 0.496636254723067,
      "grad_norm": 0.3356286883354187,
      "learning_rate": 1.7134173492988617e-05,
      "loss": 0.519,
      "step": 16167
    },
    {
      "epoch": 0.49666697385801617,
      "grad_norm": 0.332584410905838,
      "learning_rate": 1.7133834833194e-05,
      "loss": 0.6366,
      "step": 16168
    },
    {
      "epoch": 0.49669769299296535,
      "grad_norm": 0.35788118839263916,
      "learning_rate": 1.7133496156737816e-05,
      "loss": 0.5662,
      "step": 16169
    },
    {
      "epoch": 0.49672841212791446,
      "grad_norm": 0.3622240722179413,
      "learning_rate": 1.7133157463620854e-05,
      "loss": 0.6091,
      "step": 16170
    },
    {
      "epoch": 0.49675913126286364,
      "grad_norm": 0.3872944414615631,
      "learning_rate": 1.7132818753843903e-05,
      "loss": 0.6681,
      "step": 16171
    },
    {
      "epoch": 0.4967898503978128,
      "grad_norm": 0.370185524225235,
      "learning_rate": 1.7132480027407758e-05,
      "loss": 0.6052,
      "step": 16172
    },
    {
      "epoch": 0.49682056953276194,
      "grad_norm": 0.350319504737854,
      "learning_rate": 1.7132141284313202e-05,
      "loss": 0.5724,
      "step": 16173
    },
    {
      "epoch": 0.4968512886677111,
      "grad_norm": 0.3784218430519104,
      "learning_rate": 1.7131802524561036e-05,
      "loss": 0.6018,
      "step": 16174
    },
    {
      "epoch": 0.4968820078026603,
      "grad_norm": 0.35377180576324463,
      "learning_rate": 1.7131463748152048e-05,
      "loss": 0.5757,
      "step": 16175
    },
    {
      "epoch": 0.49691272693760946,
      "grad_norm": 0.3753320574760437,
      "learning_rate": 1.7131124955087028e-05,
      "loss": 0.6798,
      "step": 16176
    },
    {
      "epoch": 0.4969434460725586,
      "grad_norm": 0.38605985045433044,
      "learning_rate": 1.7130786145366768e-05,
      "loss": 0.5655,
      "step": 16177
    },
    {
      "epoch": 0.49697416520750776,
      "grad_norm": 0.33640769124031067,
      "learning_rate": 1.7130447318992055e-05,
      "loss": 0.5832,
      "step": 16178
    },
    {
      "epoch": 0.49700488434245693,
      "grad_norm": 0.36033812165260315,
      "learning_rate": 1.713010847596369e-05,
      "loss": 0.6028,
      "step": 16179
    },
    {
      "epoch": 0.49703560347740605,
      "grad_norm": 0.3410463333129883,
      "learning_rate": 1.7129769616282455e-05,
      "loss": 0.6281,
      "step": 16180
    },
    {
      "epoch": 0.4970663226123552,
      "grad_norm": 0.32996660470962524,
      "learning_rate": 1.7129430739949146e-05,
      "loss": 0.4989,
      "step": 16181
    },
    {
      "epoch": 0.4970970417473044,
      "grad_norm": 0.33075594902038574,
      "learning_rate": 1.7129091846964555e-05,
      "loss": 0.572,
      "step": 16182
    },
    {
      "epoch": 0.4971277608822536,
      "grad_norm": 0.35805004835128784,
      "learning_rate": 1.7128752937329468e-05,
      "loss": 0.5878,
      "step": 16183
    },
    {
      "epoch": 0.4971584800172027,
      "grad_norm": 0.3230906128883362,
      "learning_rate": 1.712841401104468e-05,
      "loss": 0.5008,
      "step": 16184
    },
    {
      "epoch": 0.4971891991521519,
      "grad_norm": 0.36431145668029785,
      "learning_rate": 1.712807506811099e-05,
      "loss": 0.6811,
      "step": 16185
    },
    {
      "epoch": 0.49721991828710105,
      "grad_norm": 0.3858392536640167,
      "learning_rate": 1.712773610852918e-05,
      "loss": 0.5549,
      "step": 16186
    },
    {
      "epoch": 0.49725063742205017,
      "grad_norm": 0.3759765326976776,
      "learning_rate": 1.7127397132300044e-05,
      "loss": 0.6106,
      "step": 16187
    },
    {
      "epoch": 0.49728135655699934,
      "grad_norm": 0.3876376748085022,
      "learning_rate": 1.7127058139424373e-05,
      "loss": 0.5963,
      "step": 16188
    },
    {
      "epoch": 0.4973120756919485,
      "grad_norm": 0.3510383367538452,
      "learning_rate": 1.7126719129902963e-05,
      "loss": 0.5508,
      "step": 16189
    },
    {
      "epoch": 0.4973427948268977,
      "grad_norm": 0.37122195959091187,
      "learning_rate": 1.71263801037366e-05,
      "loss": 0.5811,
      "step": 16190
    },
    {
      "epoch": 0.4973735139618468,
      "grad_norm": 0.3569961190223694,
      "learning_rate": 1.712604106092608e-05,
      "loss": 0.5663,
      "step": 16191
    },
    {
      "epoch": 0.497404233096796,
      "grad_norm": 0.3956550359725952,
      "learning_rate": 1.7125702001472194e-05,
      "loss": 0.613,
      "step": 16192
    },
    {
      "epoch": 0.49743495223174516,
      "grad_norm": 0.4119057059288025,
      "learning_rate": 1.712536292537573e-05,
      "loss": 0.5824,
      "step": 16193
    },
    {
      "epoch": 0.49746567136669434,
      "grad_norm": 0.340414434671402,
      "learning_rate": 1.7125023832637486e-05,
      "loss": 0.5869,
      "step": 16194
    },
    {
      "epoch": 0.49749639050164346,
      "grad_norm": 0.386564165353775,
      "learning_rate": 1.712468472325825e-05,
      "loss": 0.5277,
      "step": 16195
    },
    {
      "epoch": 0.49752710963659263,
      "grad_norm": 0.33003583550453186,
      "learning_rate": 1.7124345597238816e-05,
      "loss": 0.5449,
      "step": 16196
    },
    {
      "epoch": 0.4975578287715418,
      "grad_norm": 0.36396098136901855,
      "learning_rate": 1.7124006454579974e-05,
      "loss": 0.5994,
      "step": 16197
    },
    {
      "epoch": 0.49758854790649093,
      "grad_norm": 0.3917171359062195,
      "learning_rate": 1.712366729528252e-05,
      "loss": 0.5923,
      "step": 16198
    },
    {
      "epoch": 0.4976192670414401,
      "grad_norm": 0.33746424317359924,
      "learning_rate": 1.7123328119347243e-05,
      "loss": 0.6029,
      "step": 16199
    },
    {
      "epoch": 0.4976499861763893,
      "grad_norm": 0.36788761615753174,
      "learning_rate": 1.7122988926774935e-05,
      "loss": 0.6127,
      "step": 16200
    },
    {
      "epoch": 0.49768070531133846,
      "grad_norm": 0.3541843593120575,
      "learning_rate": 1.7122649717566386e-05,
      "loss": 0.6154,
      "step": 16201
    },
    {
      "epoch": 0.4977114244462876,
      "grad_norm": 0.37091901898384094,
      "learning_rate": 1.7122310491722393e-05,
      "loss": 0.5658,
      "step": 16202
    },
    {
      "epoch": 0.49774214358123675,
      "grad_norm": 0.33512431383132935,
      "learning_rate": 1.7121971249243748e-05,
      "loss": 0.5845,
      "step": 16203
    },
    {
      "epoch": 0.4977728627161859,
      "grad_norm": 0.39528974890708923,
      "learning_rate": 1.7121631990131243e-05,
      "loss": 0.5655,
      "step": 16204
    },
    {
      "epoch": 0.49780358185113505,
      "grad_norm": 0.3828268349170685,
      "learning_rate": 1.7121292714385666e-05,
      "loss": 0.5883,
      "step": 16205
    },
    {
      "epoch": 0.4978343009860842,
      "grad_norm": 0.5199773907661438,
      "learning_rate": 1.7120953422007812e-05,
      "loss": 0.6736,
      "step": 16206
    },
    {
      "epoch": 0.4978650201210334,
      "grad_norm": 0.40562018752098083,
      "learning_rate": 1.712061411299848e-05,
      "loss": 0.5539,
      "step": 16207
    },
    {
      "epoch": 0.4978957392559826,
      "grad_norm": 0.37321192026138306,
      "learning_rate": 1.7120274787358448e-05,
      "loss": 0.6218,
      "step": 16208
    },
    {
      "epoch": 0.4979264583909317,
      "grad_norm": 0.31321245431900024,
      "learning_rate": 1.7119935445088523e-05,
      "loss": 0.5484,
      "step": 16209
    },
    {
      "epoch": 0.49795717752588087,
      "grad_norm": 0.34904488921165466,
      "learning_rate": 1.711959608618949e-05,
      "loss": 0.6333,
      "step": 16210
    },
    {
      "epoch": 0.49798789666083004,
      "grad_norm": 0.3702452480792999,
      "learning_rate": 1.711925671066214e-05,
      "loss": 0.5488,
      "step": 16211
    },
    {
      "epoch": 0.4980186157957792,
      "grad_norm": 0.35153141617774963,
      "learning_rate": 1.7118917318507275e-05,
      "loss": 0.5431,
      "step": 16212
    },
    {
      "epoch": 0.49804933493072834,
      "grad_norm": 0.3307999074459076,
      "learning_rate": 1.7118577909725677e-05,
      "loss": 0.519,
      "step": 16213
    },
    {
      "epoch": 0.4980800540656775,
      "grad_norm": 0.3239724040031433,
      "learning_rate": 1.7118238484318144e-05,
      "loss": 0.5123,
      "step": 16214
    },
    {
      "epoch": 0.4981107732006267,
      "grad_norm": 0.355420857667923,
      "learning_rate": 1.711789904228547e-05,
      "loss": 0.5595,
      "step": 16215
    },
    {
      "epoch": 0.4981414923355758,
      "grad_norm": 0.32512855529785156,
      "learning_rate": 1.711755958362844e-05,
      "loss": 0.5722,
      "step": 16216
    },
    {
      "epoch": 0.498172211470525,
      "grad_norm": 0.7446301579475403,
      "learning_rate": 1.7117220108347858e-05,
      "loss": 0.6138,
      "step": 16217
    },
    {
      "epoch": 0.49820293060547416,
      "grad_norm": 0.3186052441596985,
      "learning_rate": 1.7116880616444508e-05,
      "loss": 0.547,
      "step": 16218
    },
    {
      "epoch": 0.49823364974042333,
      "grad_norm": 0.3891338109970093,
      "learning_rate": 1.7116541107919187e-05,
      "loss": 0.5015,
      "step": 16219
    },
    {
      "epoch": 0.49826436887537245,
      "grad_norm": 0.3479968309402466,
      "learning_rate": 1.7116201582772688e-05,
      "loss": 0.4802,
      "step": 16220
    },
    {
      "epoch": 0.49829508801032163,
      "grad_norm": 0.3687351644039154,
      "learning_rate": 1.7115862041005803e-05,
      "loss": 0.603,
      "step": 16221
    },
    {
      "epoch": 0.4983258071452708,
      "grad_norm": 0.40630993247032166,
      "learning_rate": 1.711552248261933e-05,
      "loss": 0.5663,
      "step": 16222
    },
    {
      "epoch": 0.4983565262802199,
      "grad_norm": 0.3254249691963196,
      "learning_rate": 1.7115182907614047e-05,
      "loss": 0.5442,
      "step": 16223
    },
    {
      "epoch": 0.4983872454151691,
      "grad_norm": 0.3433317542076111,
      "learning_rate": 1.7114843315990762e-05,
      "loss": 0.5237,
      "step": 16224
    },
    {
      "epoch": 0.4984179645501183,
      "grad_norm": 0.3494336009025574,
      "learning_rate": 1.7114503707750266e-05,
      "loss": 0.4909,
      "step": 16225
    },
    {
      "epoch": 0.49844868368506745,
      "grad_norm": 0.39335402846336365,
      "learning_rate": 1.711416408289335e-05,
      "loss": 0.5194,
      "step": 16226
    },
    {
      "epoch": 0.49847940282001657,
      "grad_norm": 0.3675476014614105,
      "learning_rate": 1.7113824441420806e-05,
      "loss": 0.6027,
      "step": 16227
    },
    {
      "epoch": 0.49851012195496575,
      "grad_norm": 0.3598644435405731,
      "learning_rate": 1.7113484783333424e-05,
      "loss": 0.576,
      "step": 16228
    },
    {
      "epoch": 0.4985408410899149,
      "grad_norm": 0.340298056602478,
      "learning_rate": 1.7113145108632006e-05,
      "loss": 0.5527,
      "step": 16229
    },
    {
      "epoch": 0.49857156022486404,
      "grad_norm": 0.2931026518344879,
      "learning_rate": 1.711280541731734e-05,
      "loss": 0.4913,
      "step": 16230
    },
    {
      "epoch": 0.4986022793598132,
      "grad_norm": 0.415555864572525,
      "learning_rate": 1.711246570939022e-05,
      "loss": 0.6168,
      "step": 16231
    },
    {
      "epoch": 0.4986329984947624,
      "grad_norm": 0.3646012842655182,
      "learning_rate": 1.711212598485144e-05,
      "loss": 0.6026,
      "step": 16232
    },
    {
      "epoch": 0.49866371762971157,
      "grad_norm": 0.3278540074825287,
      "learning_rate": 1.7111786243701793e-05,
      "loss": 0.5854,
      "step": 16233
    },
    {
      "epoch": 0.4986944367646607,
      "grad_norm": 0.3585405945777893,
      "learning_rate": 1.7111446485942073e-05,
      "loss": 0.5386,
      "step": 16234
    },
    {
      "epoch": 0.49872515589960986,
      "grad_norm": 0.3623751401901245,
      "learning_rate": 1.7111106711573073e-05,
      "loss": 0.5619,
      "step": 16235
    },
    {
      "epoch": 0.49875587503455904,
      "grad_norm": 0.40888792276382446,
      "learning_rate": 1.7110766920595586e-05,
      "loss": 0.6784,
      "step": 16236
    },
    {
      "epoch": 0.4987865941695082,
      "grad_norm": 0.3498009443283081,
      "learning_rate": 1.7110427113010403e-05,
      "loss": 0.5596,
      "step": 16237
    },
    {
      "epoch": 0.49881731330445733,
      "grad_norm": 0.35903069376945496,
      "learning_rate": 1.7110087288818325e-05,
      "loss": 0.5916,
      "step": 16238
    },
    {
      "epoch": 0.4988480324394065,
      "grad_norm": 0.3619460463523865,
      "learning_rate": 1.7109747448020142e-05,
      "loss": 0.541,
      "step": 16239
    },
    {
      "epoch": 0.4988787515743557,
      "grad_norm": 0.40022918581962585,
      "learning_rate": 1.7109407590616648e-05,
      "loss": 0.5089,
      "step": 16240
    },
    {
      "epoch": 0.4989094707093048,
      "grad_norm": 0.35492241382598877,
      "learning_rate": 1.7109067716608632e-05,
      "loss": 0.5506,
      "step": 16241
    },
    {
      "epoch": 0.498940189844254,
      "grad_norm": 0.3719565272331238,
      "learning_rate": 1.7108727825996892e-05,
      "loss": 0.5386,
      "step": 16242
    },
    {
      "epoch": 0.49897090897920315,
      "grad_norm": 0.36096644401550293,
      "learning_rate": 1.7108387918782226e-05,
      "loss": 0.6313,
      "step": 16243
    },
    {
      "epoch": 0.49900162811415233,
      "grad_norm": 0.34093451499938965,
      "learning_rate": 1.710804799496542e-05,
      "loss": 0.5459,
      "step": 16244
    },
    {
      "epoch": 0.49903234724910145,
      "grad_norm": 0.3954748213291168,
      "learning_rate": 1.7107708054547273e-05,
      "loss": 0.6104,
      "step": 16245
    },
    {
      "epoch": 0.4990630663840506,
      "grad_norm": 0.31720325350761414,
      "learning_rate": 1.7107368097528577e-05,
      "loss": 0.5322,
      "step": 16246
    },
    {
      "epoch": 0.4990937855189998,
      "grad_norm": 0.3855191171169281,
      "learning_rate": 1.7107028123910126e-05,
      "loss": 0.5174,
      "step": 16247
    },
    {
      "epoch": 0.4991245046539489,
      "grad_norm": 0.38203349709510803,
      "learning_rate": 1.7106688133692716e-05,
      "loss": 0.5581,
      "step": 16248
    },
    {
      "epoch": 0.4991552237888981,
      "grad_norm": 0.5216809511184692,
      "learning_rate": 1.7106348126877137e-05,
      "loss": 0.5637,
      "step": 16249
    },
    {
      "epoch": 0.49918594292384727,
      "grad_norm": 0.34286627173423767,
      "learning_rate": 1.7106008103464187e-05,
      "loss": 0.5356,
      "step": 16250
    },
    {
      "epoch": 0.49921666205879645,
      "grad_norm": 0.33497512340545654,
      "learning_rate": 1.710566806345466e-05,
      "loss": 0.56,
      "step": 16251
    },
    {
      "epoch": 0.49924738119374557,
      "grad_norm": 0.3284938633441925,
      "learning_rate": 1.7105328006849346e-05,
      "loss": 0.5255,
      "step": 16252
    },
    {
      "epoch": 0.49927810032869474,
      "grad_norm": 0.3722510039806366,
      "learning_rate": 1.7104987933649043e-05,
      "loss": 0.5401,
      "step": 16253
    },
    {
      "epoch": 0.4993088194636439,
      "grad_norm": 0.3595581352710724,
      "learning_rate": 1.710464784385455e-05,
      "loss": 0.549,
      "step": 16254
    },
    {
      "epoch": 0.4993395385985931,
      "grad_norm": 0.35912302136421204,
      "learning_rate": 1.7104307737466648e-05,
      "loss": 0.5309,
      "step": 16255
    },
    {
      "epoch": 0.4993702577335422,
      "grad_norm": 0.3236071765422821,
      "learning_rate": 1.7103967614486144e-05,
      "loss": 0.5425,
      "step": 16256
    },
    {
      "epoch": 0.4994009768684914,
      "grad_norm": 0.3829495906829834,
      "learning_rate": 1.7103627474913827e-05,
      "loss": 0.6198,
      "step": 16257
    },
    {
      "epoch": 0.49943169600344056,
      "grad_norm": 0.433328241109848,
      "learning_rate": 1.710328731875049e-05,
      "loss": 0.5892,
      "step": 16258
    },
    {
      "epoch": 0.4994624151383897,
      "grad_norm": 0.35081401467323303,
      "learning_rate": 1.710294714599693e-05,
      "loss": 0.5865,
      "step": 16259
    },
    {
      "epoch": 0.49949313427333886,
      "grad_norm": 0.3352569043636322,
      "learning_rate": 1.7102606956653943e-05,
      "loss": 0.5175,
      "step": 16260
    },
    {
      "epoch": 0.49952385340828803,
      "grad_norm": 0.3555446267127991,
      "learning_rate": 1.7102266750722317e-05,
      "loss": 0.5411,
      "step": 16261
    },
    {
      "epoch": 0.4995545725432372,
      "grad_norm": 0.33151715993881226,
      "learning_rate": 1.7101926528202852e-05,
      "loss": 0.5789,
      "step": 16262
    },
    {
      "epoch": 0.4995852916781863,
      "grad_norm": 0.3409734070301056,
      "learning_rate": 1.7101586289096347e-05,
      "loss": 0.6021,
      "step": 16263
    },
    {
      "epoch": 0.4996160108131355,
      "grad_norm": 0.41606980562210083,
      "learning_rate": 1.7101246033403585e-05,
      "loss": 0.5548,
      "step": 16264
    },
    {
      "epoch": 0.4996467299480847,
      "grad_norm": 0.32631856203079224,
      "learning_rate": 1.710090576112537e-05,
      "loss": 0.5583,
      "step": 16265
    },
    {
      "epoch": 0.4996774490830338,
      "grad_norm": 0.411122590303421,
      "learning_rate": 1.7100565472262492e-05,
      "loss": 0.518,
      "step": 16266
    },
    {
      "epoch": 0.499708168217983,
      "grad_norm": 0.35872939229011536,
      "learning_rate": 1.710022516681575e-05,
      "loss": 0.5328,
      "step": 16267
    },
    {
      "epoch": 0.49973888735293215,
      "grad_norm": 0.38322392106056213,
      "learning_rate": 1.7099884844785933e-05,
      "loss": 0.5845,
      "step": 16268
    },
    {
      "epoch": 0.4997696064878813,
      "grad_norm": 0.36310213804244995,
      "learning_rate": 1.7099544506173843e-05,
      "loss": 0.5563,
      "step": 16269
    },
    {
      "epoch": 0.49980032562283044,
      "grad_norm": 0.3127036392688751,
      "learning_rate": 1.7099204150980267e-05,
      "loss": 0.4914,
      "step": 16270
    },
    {
      "epoch": 0.4998310447577796,
      "grad_norm": 0.35355547070503235,
      "learning_rate": 1.7098863779206007e-05,
      "loss": 0.5829,
      "step": 16271
    },
    {
      "epoch": 0.4998617638927288,
      "grad_norm": 0.3392949104309082,
      "learning_rate": 1.7098523390851853e-05,
      "loss": 0.6026,
      "step": 16272
    },
    {
      "epoch": 0.4998924830276779,
      "grad_norm": 0.32968395948410034,
      "learning_rate": 1.70981829859186e-05,
      "loss": 0.5372,
      "step": 16273
    },
    {
      "epoch": 0.4999232021626271,
      "grad_norm": 0.3403926193714142,
      "learning_rate": 1.7097842564407047e-05,
      "loss": 0.6052,
      "step": 16274
    },
    {
      "epoch": 0.49995392129757626,
      "grad_norm": 0.34779444336891174,
      "learning_rate": 1.7097502126317992e-05,
      "loss": 0.5185,
      "step": 16275
    },
    {
      "epoch": 0.49998464043252544,
      "grad_norm": 0.33226656913757324,
      "learning_rate": 1.7097161671652217e-05,
      "loss": 0.611,
      "step": 16276
    },
    {
      "epoch": 0.5000153595674746,
      "grad_norm": 0.3588397204875946,
      "learning_rate": 1.709682120041053e-05,
      "loss": 0.5196,
      "step": 16277
    },
    {
      "epoch": 0.5000460787024238,
      "grad_norm": 0.36176252365112305,
      "learning_rate": 1.709648071259372e-05,
      "loss": 0.5746,
      "step": 16278
    },
    {
      "epoch": 0.5000767978373729,
      "grad_norm": 0.3723160922527313,
      "learning_rate": 1.7096140208202582e-05,
      "loss": 0.5529,
      "step": 16279
    },
    {
      "epoch": 0.500107516972322,
      "grad_norm": 0.3814859390258789,
      "learning_rate": 1.709579968723792e-05,
      "loss": 0.5405,
      "step": 16280
    },
    {
      "epoch": 0.5001382361072713,
      "grad_norm": 0.3503668010234833,
      "learning_rate": 1.7095459149700514e-05,
      "loss": 0.6461,
      "step": 16281
    },
    {
      "epoch": 0.5001689552422204,
      "grad_norm": 0.3376065492630005,
      "learning_rate": 1.709511859559117e-05,
      "loss": 0.5349,
      "step": 16282
    },
    {
      "epoch": 0.5001996743771695,
      "grad_norm": 0.3207961916923523,
      "learning_rate": 1.709477802491068e-05,
      "loss": 0.5273,
      "step": 16283
    },
    {
      "epoch": 0.5002303935121187,
      "grad_norm": 0.7023917436599731,
      "learning_rate": 1.709443743765984e-05,
      "loss": 0.5573,
      "step": 16284
    },
    {
      "epoch": 0.5002611126470679,
      "grad_norm": 0.4817909002304077,
      "learning_rate": 1.7094096833839452e-05,
      "loss": 0.6578,
      "step": 16285
    },
    {
      "epoch": 0.500291831782017,
      "grad_norm": 0.3280881345272064,
      "learning_rate": 1.7093756213450302e-05,
      "loss": 0.5813,
      "step": 16286
    },
    {
      "epoch": 0.5003225509169662,
      "grad_norm": 0.34191077947616577,
      "learning_rate": 1.7093415576493188e-05,
      "loss": 0.5565,
      "step": 16287
    },
    {
      "epoch": 0.5003532700519153,
      "grad_norm": 0.3441908657550812,
      "learning_rate": 1.7093074922968905e-05,
      "loss": 0.5521,
      "step": 16288
    },
    {
      "epoch": 0.5003839891868646,
      "grad_norm": 0.3314736783504486,
      "learning_rate": 1.709273425287825e-05,
      "loss": 0.7059,
      "step": 16289
    },
    {
      "epoch": 0.5004147083218137,
      "grad_norm": 0.37093719840049744,
      "learning_rate": 1.7092393566222023e-05,
      "loss": 0.6595,
      "step": 16290
    },
    {
      "epoch": 0.5004454274567628,
      "grad_norm": 0.44469448924064636,
      "learning_rate": 1.7092052863001013e-05,
      "loss": 0.5725,
      "step": 16291
    },
    {
      "epoch": 0.500476146591712,
      "grad_norm": 2.4237515926361084,
      "learning_rate": 1.709171214321602e-05,
      "loss": 0.5474,
      "step": 16292
    },
    {
      "epoch": 0.5005068657266611,
      "grad_norm": 0.40841248631477356,
      "learning_rate": 1.7091371406867835e-05,
      "loss": 0.5578,
      "step": 16293
    },
    {
      "epoch": 0.5005375848616103,
      "grad_norm": 0.34654390811920166,
      "learning_rate": 1.709103065395726e-05,
      "loss": 0.5695,
      "step": 16294
    },
    {
      "epoch": 0.5005683039965595,
      "grad_norm": 0.3386409878730774,
      "learning_rate": 1.7090689884485087e-05,
      "loss": 0.6114,
      "step": 16295
    },
    {
      "epoch": 0.5005990231315086,
      "grad_norm": 0.3363141119480133,
      "learning_rate": 1.709034909845211e-05,
      "loss": 0.4811,
      "step": 16296
    },
    {
      "epoch": 0.5006297422664577,
      "grad_norm": 0.36815038323402405,
      "learning_rate": 1.7090008295859128e-05,
      "loss": 0.6178,
      "step": 16297
    },
    {
      "epoch": 0.500660461401407,
      "grad_norm": 0.3621724843978882,
      "learning_rate": 1.7089667476706937e-05,
      "loss": 0.5253,
      "step": 16298
    },
    {
      "epoch": 0.5006911805363561,
      "grad_norm": 0.3667140305042267,
      "learning_rate": 1.7089326640996337e-05,
      "loss": 0.4966,
      "step": 16299
    },
    {
      "epoch": 0.5007218996713052,
      "grad_norm": 0.3399885296821594,
      "learning_rate": 1.7088985788728113e-05,
      "loss": 0.4638,
      "step": 16300
    },
    {
      "epoch": 0.5007526188062544,
      "grad_norm": 0.4036417007446289,
      "learning_rate": 1.708864491990307e-05,
      "loss": 0.6322,
      "step": 16301
    },
    {
      "epoch": 0.5007833379412036,
      "grad_norm": 0.36664333939552307,
      "learning_rate": 1.7088304034522e-05,
      "loss": 0.5237,
      "step": 16302
    },
    {
      "epoch": 0.5008140570761528,
      "grad_norm": 0.3786278963088989,
      "learning_rate": 1.7087963132585703e-05,
      "loss": 0.5767,
      "step": 16303
    },
    {
      "epoch": 0.5008447762111019,
      "grad_norm": 0.41454869508743286,
      "learning_rate": 1.7087622214094973e-05,
      "loss": 0.5245,
      "step": 16304
    },
    {
      "epoch": 0.500875495346051,
      "grad_norm": 0.3532162606716156,
      "learning_rate": 1.7087281279050606e-05,
      "loss": 0.505,
      "step": 16305
    },
    {
      "epoch": 0.5009062144810003,
      "grad_norm": 0.3434602618217468,
      "learning_rate": 1.70869403274534e-05,
      "loss": 0.5293,
      "step": 16306
    },
    {
      "epoch": 0.5009369336159494,
      "grad_norm": 0.5159266591072083,
      "learning_rate": 1.708659935930415e-05,
      "loss": 0.5565,
      "step": 16307
    },
    {
      "epoch": 0.5009676527508985,
      "grad_norm": 0.39007171988487244,
      "learning_rate": 1.708625837460365e-05,
      "loss": 0.5321,
      "step": 16308
    },
    {
      "epoch": 0.5009983718858477,
      "grad_norm": 0.3637964725494385,
      "learning_rate": 1.70859173733527e-05,
      "loss": 0.5267,
      "step": 16309
    },
    {
      "epoch": 0.5010290910207968,
      "grad_norm": 0.3788507580757141,
      "learning_rate": 1.7085576355552094e-05,
      "loss": 0.5727,
      "step": 16310
    },
    {
      "epoch": 0.501059810155746,
      "grad_norm": 0.3969140648841858,
      "learning_rate": 1.708523532120263e-05,
      "loss": 0.5088,
      "step": 16311
    },
    {
      "epoch": 0.5010905292906952,
      "grad_norm": 0.38724640011787415,
      "learning_rate": 1.7084894270305103e-05,
      "loss": 0.5723,
      "step": 16312
    },
    {
      "epoch": 0.5011212484256443,
      "grad_norm": 0.47763657569885254,
      "learning_rate": 1.7084553202860315e-05,
      "loss": 0.6443,
      "step": 16313
    },
    {
      "epoch": 0.5011519675605935,
      "grad_norm": 0.4860011637210846,
      "learning_rate": 1.7084212118869054e-05,
      "loss": 0.5346,
      "step": 16314
    },
    {
      "epoch": 0.5011826866955427,
      "grad_norm": 0.5435155630111694,
      "learning_rate": 1.7083871018332122e-05,
      "loss": 0.7084,
      "step": 16315
    },
    {
      "epoch": 0.5012134058304918,
      "grad_norm": 0.36341339349746704,
      "learning_rate": 1.7083529901250316e-05,
      "loss": 0.5799,
      "step": 16316
    },
    {
      "epoch": 0.501244124965441,
      "grad_norm": 0.3250170946121216,
      "learning_rate": 1.7083188767624428e-05,
      "loss": 0.4741,
      "step": 16317
    },
    {
      "epoch": 0.5012748441003901,
      "grad_norm": 0.3602892756462097,
      "learning_rate": 1.7082847617455262e-05,
      "loss": 0.6095,
      "step": 16318
    },
    {
      "epoch": 0.5013055632353393,
      "grad_norm": 0.38007640838623047,
      "learning_rate": 1.7082506450743607e-05,
      "loss": 0.6418,
      "step": 16319
    },
    {
      "epoch": 0.5013362823702885,
      "grad_norm": 0.319638192653656,
      "learning_rate": 1.7082165267490265e-05,
      "loss": 0.5116,
      "step": 16320
    },
    {
      "epoch": 0.5013670015052376,
      "grad_norm": 0.3660510182380676,
      "learning_rate": 1.708182406769603e-05,
      "loss": 0.5749,
      "step": 16321
    },
    {
      "epoch": 0.5013977206401867,
      "grad_norm": 0.3154148459434509,
      "learning_rate": 1.7081482851361702e-05,
      "loss": 0.6107,
      "step": 16322
    },
    {
      "epoch": 0.501428439775136,
      "grad_norm": 0.36342787742614746,
      "learning_rate": 1.7081141618488076e-05,
      "loss": 0.6379,
      "step": 16323
    },
    {
      "epoch": 0.5014591589100851,
      "grad_norm": 0.35049375891685486,
      "learning_rate": 1.708080036907595e-05,
      "loss": 0.5416,
      "step": 16324
    },
    {
      "epoch": 0.5014898780450342,
      "grad_norm": 0.3397506773471832,
      "learning_rate": 1.708045910312612e-05,
      "loss": 0.5356,
      "step": 16325
    },
    {
      "epoch": 0.5015205971799834,
      "grad_norm": 0.3801797032356262,
      "learning_rate": 1.7080117820639383e-05,
      "loss": 0.5614,
      "step": 16326
    },
    {
      "epoch": 0.5015513163149325,
      "grad_norm": 0.3901551067829132,
      "learning_rate": 1.7079776521616533e-05,
      "loss": 0.4895,
      "step": 16327
    },
    {
      "epoch": 0.5015820354498818,
      "grad_norm": 0.3401913344860077,
      "learning_rate": 1.7079435206058376e-05,
      "loss": 0.5431,
      "step": 16328
    },
    {
      "epoch": 0.5016127545848309,
      "grad_norm": 0.4118620753288269,
      "learning_rate": 1.70790938739657e-05,
      "loss": 0.5893,
      "step": 16329
    },
    {
      "epoch": 0.50164347371978,
      "grad_norm": 0.33327195048332214,
      "learning_rate": 1.7078752525339306e-05,
      "loss": 0.5012,
      "step": 16330
    },
    {
      "epoch": 0.5016741928547293,
      "grad_norm": 0.33898305892944336,
      "learning_rate": 1.7078411160179994e-05,
      "loss": 0.4425,
      "step": 16331
    },
    {
      "epoch": 0.5017049119896784,
      "grad_norm": 0.384173184633255,
      "learning_rate": 1.7078069778488554e-05,
      "loss": 0.5307,
      "step": 16332
    },
    {
      "epoch": 0.5017356311246275,
      "grad_norm": 0.40704891085624695,
      "learning_rate": 1.7077728380265793e-05,
      "loss": 0.5736,
      "step": 16333
    },
    {
      "epoch": 0.5017663502595767,
      "grad_norm": 0.333587646484375,
      "learning_rate": 1.7077386965512496e-05,
      "loss": 0.563,
      "step": 16334
    },
    {
      "epoch": 0.5017970693945258,
      "grad_norm": 0.3925175368785858,
      "learning_rate": 1.7077045534229473e-05,
      "loss": 0.6195,
      "step": 16335
    },
    {
      "epoch": 0.501827788529475,
      "grad_norm": 0.3436698317527771,
      "learning_rate": 1.7076704086417516e-05,
      "loss": 0.5196,
      "step": 16336
    },
    {
      "epoch": 0.5018585076644242,
      "grad_norm": 0.34620893001556396,
      "learning_rate": 1.7076362622077423e-05,
      "loss": 0.5655,
      "step": 16337
    },
    {
      "epoch": 0.5018892267993733,
      "grad_norm": 0.32041582465171814,
      "learning_rate": 1.7076021141209985e-05,
      "loss": 0.558,
      "step": 16338
    },
    {
      "epoch": 0.5019199459343225,
      "grad_norm": 0.3410366177558899,
      "learning_rate": 1.707567964381601e-05,
      "loss": 0.5291,
      "step": 16339
    },
    {
      "epoch": 0.5019506650692717,
      "grad_norm": 0.383606880903244,
      "learning_rate": 1.707533812989629e-05,
      "loss": 0.5616,
      "step": 16340
    },
    {
      "epoch": 0.5019813842042208,
      "grad_norm": 0.3422068953514099,
      "learning_rate": 1.7074996599451624e-05,
      "loss": 0.6607,
      "step": 16341
    },
    {
      "epoch": 0.50201210333917,
      "grad_norm": 0.3503864109516144,
      "learning_rate": 1.707465505248281e-05,
      "loss": 0.5833,
      "step": 16342
    },
    {
      "epoch": 0.5020428224741191,
      "grad_norm": 0.3243504464626312,
      "learning_rate": 1.7074313488990646e-05,
      "loss": 0.5902,
      "step": 16343
    },
    {
      "epoch": 0.5020735416090683,
      "grad_norm": 0.5102798938751221,
      "learning_rate": 1.7073971908975928e-05,
      "loss": 0.5057,
      "step": 16344
    },
    {
      "epoch": 0.5021042607440175,
      "grad_norm": 0.32992905378341675,
      "learning_rate": 1.7073630312439454e-05,
      "loss": 0.5559,
      "step": 16345
    },
    {
      "epoch": 0.5021349798789666,
      "grad_norm": 0.7724525332450867,
      "learning_rate": 1.707328869938202e-05,
      "loss": 0.618,
      "step": 16346
    },
    {
      "epoch": 0.5021656990139157,
      "grad_norm": 0.5333803296089172,
      "learning_rate": 1.7072947069804428e-05,
      "loss": 0.5663,
      "step": 16347
    },
    {
      "epoch": 0.502196418148865,
      "grad_norm": 0.38434794545173645,
      "learning_rate": 1.7072605423707473e-05,
      "loss": 0.5207,
      "step": 16348
    },
    {
      "epoch": 0.5022271372838141,
      "grad_norm": 0.3617023825645447,
      "learning_rate": 1.707226376109196e-05,
      "loss": 0.6022,
      "step": 16349
    },
    {
      "epoch": 0.5022578564187632,
      "grad_norm": 0.3876306116580963,
      "learning_rate": 1.7071922081958673e-05,
      "loss": 0.6925,
      "step": 16350
    },
    {
      "epoch": 0.5022885755537124,
      "grad_norm": 0.44163450598716736,
      "learning_rate": 1.7071580386308423e-05,
      "loss": 0.668,
      "step": 16351
    },
    {
      "epoch": 0.5023192946886615,
      "grad_norm": 0.36485928297042847,
      "learning_rate": 1.7071238674142e-05,
      "loss": 0.6295,
      "step": 16352
    },
    {
      "epoch": 0.5023500138236108,
      "grad_norm": 0.3317892253398895,
      "learning_rate": 1.7070896945460207e-05,
      "loss": 0.5184,
      "step": 16353
    },
    {
      "epoch": 0.5023807329585599,
      "grad_norm": 0.38474875688552856,
      "learning_rate": 1.7070555200263843e-05,
      "loss": 0.5816,
      "step": 16354
    },
    {
      "epoch": 0.502411452093509,
      "grad_norm": 0.36048623919487,
      "learning_rate": 1.70702134385537e-05,
      "loss": 0.5992,
      "step": 16355
    },
    {
      "epoch": 0.5024421712284582,
      "grad_norm": 0.33131593465805054,
      "learning_rate": 1.706987166033058e-05,
      "loss": 0.6509,
      "step": 16356
    },
    {
      "epoch": 0.5024728903634074,
      "grad_norm": 0.34296703338623047,
      "learning_rate": 1.7069529865595284e-05,
      "loss": 0.6338,
      "step": 16357
    },
    {
      "epoch": 0.5025036094983565,
      "grad_norm": 0.36345380544662476,
      "learning_rate": 1.70691880543486e-05,
      "loss": 0.5947,
      "step": 16358
    },
    {
      "epoch": 0.5025343286333057,
      "grad_norm": 0.3285859227180481,
      "learning_rate": 1.7068846226591343e-05,
      "loss": 0.5439,
      "step": 16359
    },
    {
      "epoch": 0.5025650477682548,
      "grad_norm": 0.3811939060688019,
      "learning_rate": 1.7068504382324294e-05,
      "loss": 0.5398,
      "step": 16360
    },
    {
      "epoch": 0.502595766903204,
      "grad_norm": 0.35813403129577637,
      "learning_rate": 1.7068162521548265e-05,
      "loss": 0.5987,
      "step": 16361
    },
    {
      "epoch": 0.5026264860381532,
      "grad_norm": 0.383483350276947,
      "learning_rate": 1.706782064426405e-05,
      "loss": 0.6249,
      "step": 16362
    },
    {
      "epoch": 0.5026572051731023,
      "grad_norm": 0.38100990653038025,
      "learning_rate": 1.706747875047244e-05,
      "loss": 0.6143,
      "step": 16363
    },
    {
      "epoch": 0.5026879243080515,
      "grad_norm": 0.3434688150882721,
      "learning_rate": 1.7067136840174243e-05,
      "loss": 0.5646,
      "step": 16364
    },
    {
      "epoch": 0.5027186434430007,
      "grad_norm": 0.4042685031890869,
      "learning_rate": 1.706679491337025e-05,
      "loss": 0.6102,
      "step": 16365
    },
    {
      "epoch": 0.5027493625779498,
      "grad_norm": 0.3473168909549713,
      "learning_rate": 1.7066452970061273e-05,
      "loss": 0.6315,
      "step": 16366
    },
    {
      "epoch": 0.502780081712899,
      "grad_norm": 0.3217310309410095,
      "learning_rate": 1.7066111010248095e-05,
      "loss": 0.6224,
      "step": 16367
    },
    {
      "epoch": 0.5028108008478481,
      "grad_norm": 0.34870442748069763,
      "learning_rate": 1.7065769033931524e-05,
      "loss": 0.6149,
      "step": 16368
    },
    {
      "epoch": 0.5028415199827972,
      "grad_norm": 0.43693414330482483,
      "learning_rate": 1.7065427041112355e-05,
      "loss": 0.6062,
      "step": 16369
    },
    {
      "epoch": 0.5028722391177465,
      "grad_norm": 0.32666924595832825,
      "learning_rate": 1.706508503179139e-05,
      "loss": 0.5673,
      "step": 16370
    },
    {
      "epoch": 0.5029029582526956,
      "grad_norm": 0.34299221634864807,
      "learning_rate": 1.706474300596942e-05,
      "loss": 0.6193,
      "step": 16371
    },
    {
      "epoch": 0.5029336773876447,
      "grad_norm": 0.4202262759208679,
      "learning_rate": 1.706440096364725e-05,
      "loss": 0.5704,
      "step": 16372
    },
    {
      "epoch": 0.502964396522594,
      "grad_norm": 0.33028385043144226,
      "learning_rate": 1.7064058904825683e-05,
      "loss": 0.5435,
      "step": 16373
    },
    {
      "epoch": 0.5029951156575431,
      "grad_norm": 0.3666762709617615,
      "learning_rate": 1.706371682950551e-05,
      "loss": 0.6267,
      "step": 16374
    },
    {
      "epoch": 0.5030258347924922,
      "grad_norm": 0.3302522599697113,
      "learning_rate": 1.706337473768753e-05,
      "loss": 0.5767,
      "step": 16375
    },
    {
      "epoch": 0.5030565539274414,
      "grad_norm": 0.3537541925907135,
      "learning_rate": 1.706303262937255e-05,
      "loss": 0.5963,
      "step": 16376
    },
    {
      "epoch": 0.5030872730623905,
      "grad_norm": 0.37116751074790955,
      "learning_rate": 1.7062690504561366e-05,
      "loss": 0.6369,
      "step": 16377
    },
    {
      "epoch": 0.5031179921973398,
      "grad_norm": 0.35066941380500793,
      "learning_rate": 1.7062348363254767e-05,
      "loss": 0.6159,
      "step": 16378
    },
    {
      "epoch": 0.5031487113322889,
      "grad_norm": 0.34383609890937805,
      "learning_rate": 1.706200620545357e-05,
      "loss": 0.5847,
      "step": 16379
    },
    {
      "epoch": 0.503179430467238,
      "grad_norm": 0.3428250551223755,
      "learning_rate": 1.706166403115856e-05,
      "loss": 0.6162,
      "step": 16380
    },
    {
      "epoch": 0.5032101496021872,
      "grad_norm": 0.3963924050331116,
      "learning_rate": 1.7061321840370538e-05,
      "loss": 0.6142,
      "step": 16381
    },
    {
      "epoch": 0.5032408687371364,
      "grad_norm": 0.3643445074558258,
      "learning_rate": 1.7060979633090308e-05,
      "loss": 0.6086,
      "step": 16382
    },
    {
      "epoch": 0.5032715878720855,
      "grad_norm": 0.35429614782333374,
      "learning_rate": 1.7060637409318665e-05,
      "loss": 0.5447,
      "step": 16383
    },
    {
      "epoch": 0.5033023070070347,
      "grad_norm": 0.3518892228603363,
      "learning_rate": 1.7060295169056412e-05,
      "loss": 0.5656,
      "step": 16384
    },
    {
      "epoch": 0.5033330261419838,
      "grad_norm": 0.3703662157058716,
      "learning_rate": 1.7059952912304345e-05,
      "loss": 0.5563,
      "step": 16385
    },
    {
      "epoch": 0.503363745276933,
      "grad_norm": 0.46895894408226013,
      "learning_rate": 1.7059610639063268e-05,
      "loss": 0.5786,
      "step": 16386
    },
    {
      "epoch": 0.5033944644118822,
      "grad_norm": 0.33008161187171936,
      "learning_rate": 1.7059268349333972e-05,
      "loss": 0.4909,
      "step": 16387
    },
    {
      "epoch": 0.5034251835468313,
      "grad_norm": 0.3269476890563965,
      "learning_rate": 1.7058926043117265e-05,
      "loss": 0.6055,
      "step": 16388
    },
    {
      "epoch": 0.5034559026817805,
      "grad_norm": 0.40903931856155396,
      "learning_rate": 1.7058583720413942e-05,
      "loss": 0.6764,
      "step": 16389
    },
    {
      "epoch": 0.5034866218167297,
      "grad_norm": 0.3345228433609009,
      "learning_rate": 1.7058241381224804e-05,
      "loss": 0.5237,
      "step": 16390
    },
    {
      "epoch": 0.5035173409516788,
      "grad_norm": 0.47206416726112366,
      "learning_rate": 1.7057899025550653e-05,
      "loss": 0.5167,
      "step": 16391
    },
    {
      "epoch": 0.503548060086628,
      "grad_norm": 0.3585769236087799,
      "learning_rate": 1.7057556653392285e-05,
      "loss": 0.5604,
      "step": 16392
    },
    {
      "epoch": 0.5035787792215771,
      "grad_norm": 0.35749754309654236,
      "learning_rate": 1.70572142647505e-05,
      "loss": 0.5232,
      "step": 16393
    },
    {
      "epoch": 0.5036094983565262,
      "grad_norm": 0.3526688814163208,
      "learning_rate": 1.7056871859626098e-05,
      "loss": 0.5636,
      "step": 16394
    },
    {
      "epoch": 0.5036402174914755,
      "grad_norm": 0.3424634337425232,
      "learning_rate": 1.705652943801988e-05,
      "loss": 0.5107,
      "step": 16395
    },
    {
      "epoch": 0.5036709366264246,
      "grad_norm": 0.3279346525669098,
      "learning_rate": 1.7056186999932643e-05,
      "loss": 0.5991,
      "step": 16396
    },
    {
      "epoch": 0.5037016557613737,
      "grad_norm": 0.3407623767852783,
      "learning_rate": 1.705584454536519e-05,
      "loss": 0.5388,
      "step": 16397
    },
    {
      "epoch": 0.5037323748963229,
      "grad_norm": 0.3133019506931305,
      "learning_rate": 1.7055502074318317e-05,
      "loss": 0.4657,
      "step": 16398
    },
    {
      "epoch": 0.5037630940312721,
      "grad_norm": 0.4142535924911499,
      "learning_rate": 1.7055159586792828e-05,
      "loss": 0.4905,
      "step": 16399
    },
    {
      "epoch": 0.5037938131662213,
      "grad_norm": 0.3813423216342926,
      "learning_rate": 1.705481708278952e-05,
      "loss": 0.6615,
      "step": 16400
    },
    {
      "epoch": 0.5038245323011704,
      "grad_norm": 0.3572133183479309,
      "learning_rate": 1.7054474562309195e-05,
      "loss": 0.5411,
      "step": 16401
    },
    {
      "epoch": 0.5038552514361195,
      "grad_norm": 0.3718344271183014,
      "learning_rate": 1.7054132025352652e-05,
      "loss": 0.5306,
      "step": 16402
    },
    {
      "epoch": 0.5038859705710688,
      "grad_norm": 0.3569242060184479,
      "learning_rate": 1.705378947192069e-05,
      "loss": 0.6128,
      "step": 16403
    },
    {
      "epoch": 0.5039166897060179,
      "grad_norm": 0.3474127948284149,
      "learning_rate": 1.705344690201411e-05,
      "loss": 0.5932,
      "step": 16404
    },
    {
      "epoch": 0.503947408840967,
      "grad_norm": 0.3522145450115204,
      "learning_rate": 1.7053104315633714e-05,
      "loss": 0.5878,
      "step": 16405
    },
    {
      "epoch": 0.5039781279759162,
      "grad_norm": 0.3605780303478241,
      "learning_rate": 1.7052761712780296e-05,
      "loss": 0.4993,
      "step": 16406
    },
    {
      "epoch": 0.5040088471108654,
      "grad_norm": 0.3623238503932953,
      "learning_rate": 1.7052419093454668e-05,
      "loss": 0.5157,
      "step": 16407
    },
    {
      "epoch": 0.5040395662458145,
      "grad_norm": 0.3330104351043701,
      "learning_rate": 1.7052076457657617e-05,
      "loss": 0.5209,
      "step": 16408
    },
    {
      "epoch": 0.5040702853807637,
      "grad_norm": 0.3678736388683319,
      "learning_rate": 1.7051733805389946e-05,
      "loss": 0.5931,
      "step": 16409
    },
    {
      "epoch": 0.5041010045157128,
      "grad_norm": 0.3685755431652069,
      "learning_rate": 1.7051391136652465e-05,
      "loss": 0.7043,
      "step": 16410
    },
    {
      "epoch": 0.504131723650662,
      "grad_norm": 0.37114784121513367,
      "learning_rate": 1.7051048451445963e-05,
      "loss": 0.51,
      "step": 16411
    },
    {
      "epoch": 0.5041624427856112,
      "grad_norm": 0.3353554606437683,
      "learning_rate": 1.7050705749771247e-05,
      "loss": 0.5389,
      "step": 16412
    },
    {
      "epoch": 0.5041931619205603,
      "grad_norm": 0.3774676024913788,
      "learning_rate": 1.7050363031629116e-05,
      "loss": 0.5719,
      "step": 16413
    },
    {
      "epoch": 0.5042238810555095,
      "grad_norm": 0.3296366035938263,
      "learning_rate": 1.705002029702037e-05,
      "loss": 0.5705,
      "step": 16414
    },
    {
      "epoch": 0.5042546001904586,
      "grad_norm": 0.38162505626678467,
      "learning_rate": 1.7049677545945807e-05,
      "loss": 0.6149,
      "step": 16415
    },
    {
      "epoch": 0.5042853193254078,
      "grad_norm": 0.3594629466533661,
      "learning_rate": 1.704933477840623e-05,
      "loss": 0.6046,
      "step": 16416
    },
    {
      "epoch": 0.504316038460357,
      "grad_norm": 0.3698381781578064,
      "learning_rate": 1.704899199440244e-05,
      "loss": 0.5289,
      "step": 16417
    },
    {
      "epoch": 0.5043467575953061,
      "grad_norm": 0.3399701416492462,
      "learning_rate": 1.704864919393524e-05,
      "loss": 0.5217,
      "step": 16418
    },
    {
      "epoch": 0.5043774767302552,
      "grad_norm": 0.3488036096096039,
      "learning_rate": 1.704830637700542e-05,
      "loss": 0.5267,
      "step": 16419
    },
    {
      "epoch": 0.5044081958652045,
      "grad_norm": 0.35212236642837524,
      "learning_rate": 1.7047963543613794e-05,
      "loss": 0.535,
      "step": 16420
    },
    {
      "epoch": 0.5044389150001536,
      "grad_norm": 0.36171719431877136,
      "learning_rate": 1.7047620693761157e-05,
      "loss": 0.5713,
      "step": 16421
    },
    {
      "epoch": 0.5044696341351027,
      "grad_norm": 0.33248424530029297,
      "learning_rate": 1.7047277827448308e-05,
      "loss": 0.5458,
      "step": 16422
    },
    {
      "epoch": 0.5045003532700519,
      "grad_norm": 0.3476414084434509,
      "learning_rate": 1.704693494467605e-05,
      "loss": 0.4922,
      "step": 16423
    },
    {
      "epoch": 0.5045310724050011,
      "grad_norm": 0.40512871742248535,
      "learning_rate": 1.7046592045445183e-05,
      "loss": 0.6601,
      "step": 16424
    },
    {
      "epoch": 0.5045617915399503,
      "grad_norm": 0.3696553707122803,
      "learning_rate": 1.7046249129756506e-05,
      "loss": 0.618,
      "step": 16425
    },
    {
      "epoch": 0.5045925106748994,
      "grad_norm": 0.33864113688468933,
      "learning_rate": 1.7045906197610823e-05,
      "loss": 0.5726,
      "step": 16426
    },
    {
      "epoch": 0.5046232298098485,
      "grad_norm": 0.36879199743270874,
      "learning_rate": 1.7045563249008937e-05,
      "loss": 0.6177,
      "step": 16427
    },
    {
      "epoch": 0.5046539489447978,
      "grad_norm": 0.37027937173843384,
      "learning_rate": 1.7045220283951643e-05,
      "loss": 0.5627,
      "step": 16428
    },
    {
      "epoch": 0.5046846680797469,
      "grad_norm": 0.38616907596588135,
      "learning_rate": 1.7044877302439745e-05,
      "loss": 0.5572,
      "step": 16429
    },
    {
      "epoch": 0.504715387214696,
      "grad_norm": 0.4441499710083008,
      "learning_rate": 1.704453430447405e-05,
      "loss": 0.5796,
      "step": 16430
    },
    {
      "epoch": 0.5047461063496452,
      "grad_norm": 0.34404057264328003,
      "learning_rate": 1.7044191290055344e-05,
      "loss": 0.5914,
      "step": 16431
    },
    {
      "epoch": 0.5047768254845943,
      "grad_norm": 0.41086524724960327,
      "learning_rate": 1.7043848259184444e-05,
      "loss": 0.5631,
      "step": 16432
    },
    {
      "epoch": 0.5048075446195435,
      "grad_norm": 0.3904730975627899,
      "learning_rate": 1.704350521186214e-05,
      "loss": 0.603,
      "step": 16433
    },
    {
      "epoch": 0.5048382637544927,
      "grad_norm": 0.33796146512031555,
      "learning_rate": 1.704316214808924e-05,
      "loss": 0.5691,
      "step": 16434
    },
    {
      "epoch": 0.5048689828894418,
      "grad_norm": 0.3419289290904999,
      "learning_rate": 1.7042819067866544e-05,
      "loss": 0.5779,
      "step": 16435
    },
    {
      "epoch": 0.5048997020243909,
      "grad_norm": 0.3246111571788788,
      "learning_rate": 1.704247597119485e-05,
      "loss": 0.5118,
      "step": 16436
    },
    {
      "epoch": 0.5049304211593402,
      "grad_norm": 0.3854599595069885,
      "learning_rate": 1.7042132858074965e-05,
      "loss": 0.6525,
      "step": 16437
    },
    {
      "epoch": 0.5049611402942893,
      "grad_norm": 0.3631216287612915,
      "learning_rate": 1.704178972850768e-05,
      "loss": 0.6141,
      "step": 16438
    },
    {
      "epoch": 0.5049918594292385,
      "grad_norm": 0.34499746561050415,
      "learning_rate": 1.7041446582493812e-05,
      "loss": 0.5586,
      "step": 16439
    },
    {
      "epoch": 0.5050225785641876,
      "grad_norm": 0.3533022403717041,
      "learning_rate": 1.704110342003415e-05,
      "loss": 0.5963,
      "step": 16440
    },
    {
      "epoch": 0.5050532976991368,
      "grad_norm": 0.39058423042297363,
      "learning_rate": 1.7040760241129496e-05,
      "loss": 0.5693,
      "step": 16441
    },
    {
      "epoch": 0.505084016834086,
      "grad_norm": 0.35843124985694885,
      "learning_rate": 1.704041704578066e-05,
      "loss": 0.5843,
      "step": 16442
    },
    {
      "epoch": 0.5051147359690351,
      "grad_norm": 0.3417917788028717,
      "learning_rate": 1.7040073833988432e-05,
      "loss": 0.6039,
      "step": 16443
    },
    {
      "epoch": 0.5051454551039842,
      "grad_norm": 0.3495767116546631,
      "learning_rate": 1.7039730605753628e-05,
      "loss": 0.5098,
      "step": 16444
    },
    {
      "epoch": 0.5051761742389335,
      "grad_norm": 0.38381117582321167,
      "learning_rate": 1.7039387361077033e-05,
      "loss": 0.4761,
      "step": 16445
    },
    {
      "epoch": 0.5052068933738826,
      "grad_norm": 0.38330212235450745,
      "learning_rate": 1.7039044099959464e-05,
      "loss": 0.4926,
      "step": 16446
    },
    {
      "epoch": 0.5052376125088317,
      "grad_norm": 0.3325798809528351,
      "learning_rate": 1.703870082240171e-05,
      "loss": 0.5459,
      "step": 16447
    },
    {
      "epoch": 0.5052683316437809,
      "grad_norm": 0.43798038363456726,
      "learning_rate": 1.7038357528404582e-05,
      "loss": 0.5128,
      "step": 16448
    },
    {
      "epoch": 0.50529905077873,
      "grad_norm": 0.3683296740055084,
      "learning_rate": 1.703801421796888e-05,
      "loss": 0.5675,
      "step": 16449
    },
    {
      "epoch": 0.5053297699136793,
      "grad_norm": 0.33793550729751587,
      "learning_rate": 1.70376708910954e-05,
      "loss": 0.5519,
      "step": 16450
    },
    {
      "epoch": 0.5053604890486284,
      "grad_norm": 0.3584577143192291,
      "learning_rate": 1.7037327547784953e-05,
      "loss": 0.5808,
      "step": 16451
    },
    {
      "epoch": 0.5053912081835775,
      "grad_norm": 0.3837217390537262,
      "learning_rate": 1.7036984188038332e-05,
      "loss": 0.5666,
      "step": 16452
    },
    {
      "epoch": 0.5054219273185268,
      "grad_norm": 0.3687877953052521,
      "learning_rate": 1.7036640811856345e-05,
      "loss": 0.6112,
      "step": 16453
    },
    {
      "epoch": 0.5054526464534759,
      "grad_norm": 0.35973477363586426,
      "learning_rate": 1.703629741923979e-05,
      "loss": 0.6549,
      "step": 16454
    },
    {
      "epoch": 0.505483365588425,
      "grad_norm": 0.3848072290420532,
      "learning_rate": 1.7035954010189476e-05,
      "loss": 0.524,
      "step": 16455
    },
    {
      "epoch": 0.5055140847233742,
      "grad_norm": 0.3415275514125824,
      "learning_rate": 1.7035610584706194e-05,
      "loss": 0.5611,
      "step": 16456
    },
    {
      "epoch": 0.5055448038583233,
      "grad_norm": 0.3626692295074463,
      "learning_rate": 1.7035267142790757e-05,
      "loss": 0.5475,
      "step": 16457
    },
    {
      "epoch": 0.5055755229932725,
      "grad_norm": 0.3294049799442291,
      "learning_rate": 1.7034923684443958e-05,
      "loss": 0.5732,
      "step": 16458
    },
    {
      "epoch": 0.5056062421282217,
      "grad_norm": 0.3277556598186493,
      "learning_rate": 1.7034580209666604e-05,
      "loss": 0.5703,
      "step": 16459
    },
    {
      "epoch": 0.5056369612631708,
      "grad_norm": 0.3649975061416626,
      "learning_rate": 1.70342367184595e-05,
      "loss": 0.5079,
      "step": 16460
    },
    {
      "epoch": 0.5056676803981199,
      "grad_norm": 0.3199576735496521,
      "learning_rate": 1.7033893210823445e-05,
      "loss": 0.5876,
      "step": 16461
    },
    {
      "epoch": 0.5056983995330692,
      "grad_norm": 0.3362707495689392,
      "learning_rate": 1.7033549686759236e-05,
      "loss": 0.5803,
      "step": 16462
    },
    {
      "epoch": 0.5057291186680183,
      "grad_norm": 0.38490909337997437,
      "learning_rate": 1.7033206146267683e-05,
      "loss": 0.5633,
      "step": 16463
    },
    {
      "epoch": 0.5057598378029675,
      "grad_norm": 0.3471192419528961,
      "learning_rate": 1.7032862589349587e-05,
      "loss": 0.5909,
      "step": 16464
    },
    {
      "epoch": 0.5057905569379166,
      "grad_norm": 0.3443561792373657,
      "learning_rate": 1.703251901600575e-05,
      "loss": 0.6178,
      "step": 16465
    },
    {
      "epoch": 0.5058212760728658,
      "grad_norm": 0.33409011363983154,
      "learning_rate": 1.703217542623697e-05,
      "loss": 0.47,
      "step": 16466
    },
    {
      "epoch": 0.505851995207815,
      "grad_norm": 0.37545517086982727,
      "learning_rate": 1.7031831820044055e-05,
      "loss": 0.556,
      "step": 16467
    },
    {
      "epoch": 0.5058827143427641,
      "grad_norm": 0.31932613253593445,
      "learning_rate": 1.7031488197427806e-05,
      "loss": 0.6073,
      "step": 16468
    },
    {
      "epoch": 0.5059134334777132,
      "grad_norm": 0.43556147813796997,
      "learning_rate": 1.703114455838903e-05,
      "loss": 0.5462,
      "step": 16469
    },
    {
      "epoch": 0.5059441526126625,
      "grad_norm": 0.3497317135334015,
      "learning_rate": 1.7030800902928516e-05,
      "loss": 0.53,
      "step": 16470
    },
    {
      "epoch": 0.5059748717476116,
      "grad_norm": 0.33984193205833435,
      "learning_rate": 1.7030457231047083e-05,
      "loss": 0.568,
      "step": 16471
    },
    {
      "epoch": 0.5060055908825607,
      "grad_norm": 0.3311612606048584,
      "learning_rate": 1.703011354274552e-05,
      "loss": 0.5524,
      "step": 16472
    },
    {
      "epoch": 0.5060363100175099,
      "grad_norm": 0.3687147796154022,
      "learning_rate": 1.7029769838024643e-05,
      "loss": 0.5267,
      "step": 16473
    },
    {
      "epoch": 0.506067029152459,
      "grad_norm": 0.3366023302078247,
      "learning_rate": 1.7029426116885242e-05,
      "loss": 0.5742,
      "step": 16474
    },
    {
      "epoch": 0.5060977482874083,
      "grad_norm": 0.34957531094551086,
      "learning_rate": 1.7029082379328127e-05,
      "loss": 0.5393,
      "step": 16475
    },
    {
      "epoch": 0.5061284674223574,
      "grad_norm": 0.34707367420196533,
      "learning_rate": 1.7028738625354097e-05,
      "loss": 0.5188,
      "step": 16476
    },
    {
      "epoch": 0.5061591865573065,
      "grad_norm": 0.34074804186820984,
      "learning_rate": 1.702839485496396e-05,
      "loss": 0.6297,
      "step": 16477
    },
    {
      "epoch": 0.5061899056922557,
      "grad_norm": 0.3912140429019928,
      "learning_rate": 1.7028051068158515e-05,
      "loss": 0.5263,
      "step": 16478
    },
    {
      "epoch": 0.5062206248272049,
      "grad_norm": 0.33555325865745544,
      "learning_rate": 1.7027707264938566e-05,
      "loss": 0.5269,
      "step": 16479
    },
    {
      "epoch": 0.506251343962154,
      "grad_norm": 0.33788001537323,
      "learning_rate": 1.7027363445304913e-05,
      "loss": 0.5072,
      "step": 16480
    },
    {
      "epoch": 0.5062820630971032,
      "grad_norm": 0.36641332507133484,
      "learning_rate": 1.7027019609258365e-05,
      "loss": 0.6188,
      "step": 16481
    },
    {
      "epoch": 0.5063127822320523,
      "grad_norm": 0.34242090582847595,
      "learning_rate": 1.7026675756799722e-05,
      "loss": 0.6141,
      "step": 16482
    },
    {
      "epoch": 0.5063435013670015,
      "grad_norm": 0.33258190751075745,
      "learning_rate": 1.7026331887929786e-05,
      "loss": 0.5069,
      "step": 16483
    },
    {
      "epoch": 0.5063742205019507,
      "grad_norm": 0.40084341168403625,
      "learning_rate": 1.7025988002649363e-05,
      "loss": 0.5587,
      "step": 16484
    },
    {
      "epoch": 0.5064049396368998,
      "grad_norm": 0.5045223832130432,
      "learning_rate": 1.702564410095925e-05,
      "loss": 0.559,
      "step": 16485
    },
    {
      "epoch": 0.506435658771849,
      "grad_norm": 0.35669848322868347,
      "learning_rate": 1.702530018286026e-05,
      "loss": 0.6015,
      "step": 16486
    },
    {
      "epoch": 0.5064663779067982,
      "grad_norm": 0.41286545991897583,
      "learning_rate": 1.7024956248353187e-05,
      "loss": 0.5481,
      "step": 16487
    },
    {
      "epoch": 0.5064970970417473,
      "grad_norm": 0.3313335180282593,
      "learning_rate": 1.702461229743884e-05,
      "loss": 0.5588,
      "step": 16488
    },
    {
      "epoch": 0.5065278161766965,
      "grad_norm": 0.3453749120235443,
      "learning_rate": 1.7024268330118018e-05,
      "loss": 0.4875,
      "step": 16489
    },
    {
      "epoch": 0.5065585353116456,
      "grad_norm": 0.40341249108314514,
      "learning_rate": 1.702392434639153e-05,
      "loss": 0.4888,
      "step": 16490
    },
    {
      "epoch": 0.5065892544465948,
      "grad_norm": 0.3324063718318939,
      "learning_rate": 1.7023580346260177e-05,
      "loss": 0.5344,
      "step": 16491
    },
    {
      "epoch": 0.506619973581544,
      "grad_norm": 0.39296022057533264,
      "learning_rate": 1.7023236329724758e-05,
      "loss": 0.6248,
      "step": 16492
    },
    {
      "epoch": 0.5066506927164931,
      "grad_norm": 0.34492865204811096,
      "learning_rate": 1.702289229678608e-05,
      "loss": 0.5899,
      "step": 16493
    },
    {
      "epoch": 0.5066814118514422,
      "grad_norm": 0.34118467569351196,
      "learning_rate": 1.7022548247444948e-05,
      "loss": 0.5851,
      "step": 16494
    },
    {
      "epoch": 0.5067121309863915,
      "grad_norm": 0.35659393668174744,
      "learning_rate": 1.7022204181702166e-05,
      "loss": 0.5573,
      "step": 16495
    },
    {
      "epoch": 0.5067428501213406,
      "grad_norm": 0.3251129686832428,
      "learning_rate": 1.7021860099558532e-05,
      "loss": 0.5619,
      "step": 16496
    },
    {
      "epoch": 0.5067735692562897,
      "grad_norm": 0.33572420477867126,
      "learning_rate": 1.7021516001014854e-05,
      "loss": 0.54,
      "step": 16497
    },
    {
      "epoch": 0.5068042883912389,
      "grad_norm": 0.35621002316474915,
      "learning_rate": 1.7021171886071936e-05,
      "loss": 0.5312,
      "step": 16498
    },
    {
      "epoch": 0.506835007526188,
      "grad_norm": 0.4112642705440521,
      "learning_rate": 1.702082775473058e-05,
      "loss": 0.6723,
      "step": 16499
    },
    {
      "epoch": 0.5068657266611373,
      "grad_norm": 0.38374510407447815,
      "learning_rate": 1.702048360699159e-05,
      "loss": 0.629,
      "step": 16500
    },
    {
      "epoch": 0.5068964457960864,
      "grad_norm": 0.35273492336273193,
      "learning_rate": 1.7020139442855774e-05,
      "loss": 0.5724,
      "step": 16501
    },
    {
      "epoch": 0.5069271649310355,
      "grad_norm": 0.3725540041923523,
      "learning_rate": 1.7019795262323927e-05,
      "loss": 0.5231,
      "step": 16502
    },
    {
      "epoch": 0.5069578840659847,
      "grad_norm": 0.3546208441257477,
      "learning_rate": 1.701945106539686e-05,
      "loss": 0.5191,
      "step": 16503
    },
    {
      "epoch": 0.5069886032009339,
      "grad_norm": 0.3423897922039032,
      "learning_rate": 1.701910685207538e-05,
      "loss": 0.5534,
      "step": 16504
    },
    {
      "epoch": 0.507019322335883,
      "grad_norm": 0.3417624235153198,
      "learning_rate": 1.7018762622360277e-05,
      "loss": 0.6085,
      "step": 16505
    },
    {
      "epoch": 0.5070500414708322,
      "grad_norm": 0.34936320781707764,
      "learning_rate": 1.701841837625237e-05,
      "loss": 0.5393,
      "step": 16506
    },
    {
      "epoch": 0.5070807606057813,
      "grad_norm": 0.36458614468574524,
      "learning_rate": 1.7018074113752453e-05,
      "loss": 0.6269,
      "step": 16507
    },
    {
      "epoch": 0.5071114797407305,
      "grad_norm": 0.3504768908023834,
      "learning_rate": 1.7017729834861335e-05,
      "loss": 0.5898,
      "step": 16508
    },
    {
      "epoch": 0.5071421988756797,
      "grad_norm": 0.3580353856086731,
      "learning_rate": 1.7017385539579818e-05,
      "loss": 0.5806,
      "step": 16509
    },
    {
      "epoch": 0.5071729180106288,
      "grad_norm": 0.3759450316429138,
      "learning_rate": 1.7017041227908708e-05,
      "loss": 0.5853,
      "step": 16510
    },
    {
      "epoch": 0.507203637145578,
      "grad_norm": 0.3542855679988861,
      "learning_rate": 1.7016696899848807e-05,
      "loss": 0.5178,
      "step": 16511
    },
    {
      "epoch": 0.5072343562805272,
      "grad_norm": 0.3236028254032135,
      "learning_rate": 1.7016352555400924e-05,
      "loss": 0.5292,
      "step": 16512
    },
    {
      "epoch": 0.5072650754154763,
      "grad_norm": 0.34643203020095825,
      "learning_rate": 1.701600819456586e-05,
      "loss": 0.5693,
      "step": 16513
    },
    {
      "epoch": 0.5072957945504255,
      "grad_norm": 0.40425342321395874,
      "learning_rate": 1.701566381734441e-05,
      "loss": 0.6089,
      "step": 16514
    },
    {
      "epoch": 0.5073265136853746,
      "grad_norm": 0.33668088912963867,
      "learning_rate": 1.7015319423737395e-05,
      "loss": 0.5504,
      "step": 16515
    },
    {
      "epoch": 0.5073572328203237,
      "grad_norm": 0.3519352376461029,
      "learning_rate": 1.701497501374561e-05,
      "loss": 0.6254,
      "step": 16516
    },
    {
      "epoch": 0.507387951955273,
      "grad_norm": 0.3565995991230011,
      "learning_rate": 1.701463058736986e-05,
      "loss": 0.533,
      "step": 16517
    },
    {
      "epoch": 0.5074186710902221,
      "grad_norm": 0.3550094962120056,
      "learning_rate": 1.701428614461095e-05,
      "loss": 0.5279,
      "step": 16518
    },
    {
      "epoch": 0.5074493902251712,
      "grad_norm": 0.37985143065452576,
      "learning_rate": 1.7013941685469685e-05,
      "loss": 0.6099,
      "step": 16519
    },
    {
      "epoch": 0.5074801093601204,
      "grad_norm": 0.3506864011287689,
      "learning_rate": 1.701359720994687e-05,
      "loss": 0.5438,
      "step": 16520
    },
    {
      "epoch": 0.5075108284950696,
      "grad_norm": 0.34166571497917175,
      "learning_rate": 1.7013252718043308e-05,
      "loss": 0.5004,
      "step": 16521
    },
    {
      "epoch": 0.5075415476300187,
      "grad_norm": 0.4985184669494629,
      "learning_rate": 1.7012908209759808e-05,
      "loss": 0.6115,
      "step": 16522
    },
    {
      "epoch": 0.5075722667649679,
      "grad_norm": 0.36283382773399353,
      "learning_rate": 1.701256368509717e-05,
      "loss": 0.6274,
      "step": 16523
    },
    {
      "epoch": 0.507602985899917,
      "grad_norm": 0.32661452889442444,
      "learning_rate": 1.7012219144056196e-05,
      "loss": 0.5975,
      "step": 16524
    },
    {
      "epoch": 0.5076337050348663,
      "grad_norm": 0.3278598189353943,
      "learning_rate": 1.7011874586637697e-05,
      "loss": 0.4983,
      "step": 16525
    },
    {
      "epoch": 0.5076644241698154,
      "grad_norm": 0.3805789351463318,
      "learning_rate": 1.7011530012842476e-05,
      "loss": 0.5972,
      "step": 16526
    },
    {
      "epoch": 0.5076951433047645,
      "grad_norm": 0.36597609519958496,
      "learning_rate": 1.7011185422671338e-05,
      "loss": 0.6036,
      "step": 16527
    },
    {
      "epoch": 0.5077258624397137,
      "grad_norm": 0.31508883833885193,
      "learning_rate": 1.7010840816125084e-05,
      "loss": 0.4418,
      "step": 16528
    },
    {
      "epoch": 0.5077565815746629,
      "grad_norm": 0.3727176785469055,
      "learning_rate": 1.701049619320452e-05,
      "loss": 0.5442,
      "step": 16529
    },
    {
      "epoch": 0.507787300709612,
      "grad_norm": 0.41083505749702454,
      "learning_rate": 1.7010151553910458e-05,
      "loss": 0.644,
      "step": 16530
    },
    {
      "epoch": 0.5078180198445612,
      "grad_norm": 0.351976215839386,
      "learning_rate": 1.7009806898243693e-05,
      "loss": 0.4919,
      "step": 16531
    },
    {
      "epoch": 0.5078487389795103,
      "grad_norm": 0.3763429522514343,
      "learning_rate": 1.7009462226205037e-05,
      "loss": 0.5411,
      "step": 16532
    },
    {
      "epoch": 0.5078794581144594,
      "grad_norm": 0.3278643488883972,
      "learning_rate": 1.700911753779529e-05,
      "loss": 0.5606,
      "step": 16533
    },
    {
      "epoch": 0.5079101772494087,
      "grad_norm": 0.3524758219718933,
      "learning_rate": 1.7008772833015262e-05,
      "loss": 0.5302,
      "step": 16534
    },
    {
      "epoch": 0.5079408963843578,
      "grad_norm": 0.3800450563430786,
      "learning_rate": 1.7008428111865752e-05,
      "loss": 0.6034,
      "step": 16535
    },
    {
      "epoch": 0.507971615519307,
      "grad_norm": 0.34616830945014954,
      "learning_rate": 1.700808337434757e-05,
      "loss": 0.5771,
      "step": 16536
    },
    {
      "epoch": 0.5080023346542561,
      "grad_norm": 0.3379976153373718,
      "learning_rate": 1.700773862046152e-05,
      "loss": 0.6564,
      "step": 16537
    },
    {
      "epoch": 0.5080330537892053,
      "grad_norm": 0.3312512934207916,
      "learning_rate": 1.7007393850208413e-05,
      "loss": 0.5826,
      "step": 16538
    },
    {
      "epoch": 0.5080637729241545,
      "grad_norm": 0.36482739448547363,
      "learning_rate": 1.700704906358904e-05,
      "loss": 0.6349,
      "step": 16539
    },
    {
      "epoch": 0.5080944920591036,
      "grad_norm": 0.42604655027389526,
      "learning_rate": 1.700670426060422e-05,
      "loss": 0.562,
      "step": 16540
    },
    {
      "epoch": 0.5081252111940527,
      "grad_norm": 0.3218283951282501,
      "learning_rate": 1.700635944125475e-05,
      "loss": 0.5664,
      "step": 16541
    },
    {
      "epoch": 0.508155930329002,
      "grad_norm": 0.3398570716381073,
      "learning_rate": 1.7006014605541436e-05,
      "loss": 0.5877,
      "step": 16542
    },
    {
      "epoch": 0.5081866494639511,
      "grad_norm": 0.3439332842826843,
      "learning_rate": 1.7005669753465088e-05,
      "loss": 0.5683,
      "step": 16543
    },
    {
      "epoch": 0.5082173685989002,
      "grad_norm": 0.3246372938156128,
      "learning_rate": 1.7005324885026512e-05,
      "loss": 0.5209,
      "step": 16544
    },
    {
      "epoch": 0.5082480877338494,
      "grad_norm": 0.30856677889823914,
      "learning_rate": 1.7004980000226506e-05,
      "loss": 0.5152,
      "step": 16545
    },
    {
      "epoch": 0.5082788068687986,
      "grad_norm": 0.3446982502937317,
      "learning_rate": 1.7004635099065882e-05,
      "loss": 0.5353,
      "step": 16546
    },
    {
      "epoch": 0.5083095260037477,
      "grad_norm": 0.3335891366004944,
      "learning_rate": 1.7004290181545444e-05,
      "loss": 0.6602,
      "step": 16547
    },
    {
      "epoch": 0.5083402451386969,
      "grad_norm": 0.5275238752365112,
      "learning_rate": 1.7003945247665998e-05,
      "loss": 0.5435,
      "step": 16548
    },
    {
      "epoch": 0.508370964273646,
      "grad_norm": 0.3776610493659973,
      "learning_rate": 1.7003600297428346e-05,
      "loss": 0.5884,
      "step": 16549
    },
    {
      "epoch": 0.5084016834085953,
      "grad_norm": 0.3592738211154938,
      "learning_rate": 1.7003255330833296e-05,
      "loss": 0.5517,
      "step": 16550
    },
    {
      "epoch": 0.5084324025435444,
      "grad_norm": 0.34127503633499146,
      "learning_rate": 1.700291034788166e-05,
      "loss": 0.61,
      "step": 16551
    },
    {
      "epoch": 0.5084631216784935,
      "grad_norm": 0.3552951514720917,
      "learning_rate": 1.700256534857423e-05,
      "loss": 0.5733,
      "step": 16552
    },
    {
      "epoch": 0.5084938408134427,
      "grad_norm": 0.3729267716407776,
      "learning_rate": 1.7002220332911825e-05,
      "loss": 0.6105,
      "step": 16553
    },
    {
      "epoch": 0.5085245599483919,
      "grad_norm": 0.3680780529975891,
      "learning_rate": 1.700187530089524e-05,
      "loss": 0.5125,
      "step": 16554
    },
    {
      "epoch": 0.508555279083341,
      "grad_norm": 0.3215462267398834,
      "learning_rate": 1.700153025252529e-05,
      "loss": 0.563,
      "step": 16555
    },
    {
      "epoch": 0.5085859982182902,
      "grad_norm": 0.43576905131340027,
      "learning_rate": 1.7001185187802778e-05,
      "loss": 0.6403,
      "step": 16556
    },
    {
      "epoch": 0.5086167173532393,
      "grad_norm": 0.3311092257499695,
      "learning_rate": 1.7000840106728507e-05,
      "loss": 0.5606,
      "step": 16557
    },
    {
      "epoch": 0.5086474364881884,
      "grad_norm": 0.30111387372016907,
      "learning_rate": 1.7000495009303285e-05,
      "loss": 0.585,
      "step": 16558
    },
    {
      "epoch": 0.5086781556231377,
      "grad_norm": 0.3332185447216034,
      "learning_rate": 1.700014989552792e-05,
      "loss": 0.5936,
      "step": 16559
    },
    {
      "epoch": 0.5087088747580868,
      "grad_norm": 0.3910095691680908,
      "learning_rate": 1.6999804765403217e-05,
      "loss": 0.6717,
      "step": 16560
    },
    {
      "epoch": 0.508739593893036,
      "grad_norm": 0.3740534782409668,
      "learning_rate": 1.6999459618929976e-05,
      "loss": 0.5542,
      "step": 16561
    },
    {
      "epoch": 0.5087703130279851,
      "grad_norm": 0.3581983149051666,
      "learning_rate": 1.699911445610901e-05,
      "loss": 0.5072,
      "step": 16562
    },
    {
      "epoch": 0.5088010321629343,
      "grad_norm": 0.3699452877044678,
      "learning_rate": 1.6998769276941124e-05,
      "loss": 0.5923,
      "step": 16563
    },
    {
      "epoch": 0.5088317512978835,
      "grad_norm": 0.3641567528247833,
      "learning_rate": 1.6998424081427126e-05,
      "loss": 0.5949,
      "step": 16564
    },
    {
      "epoch": 0.5088624704328326,
      "grad_norm": 0.3402317762374878,
      "learning_rate": 1.6998078869567817e-05,
      "loss": 0.4606,
      "step": 16565
    },
    {
      "epoch": 0.5088931895677817,
      "grad_norm": 0.3457868695259094,
      "learning_rate": 1.699773364136401e-05,
      "loss": 0.5849,
      "step": 16566
    },
    {
      "epoch": 0.508923908702731,
      "grad_norm": 0.3810103237628937,
      "learning_rate": 1.6997388396816502e-05,
      "loss": 0.5326,
      "step": 16567
    },
    {
      "epoch": 0.5089546278376801,
      "grad_norm": 0.36601266264915466,
      "learning_rate": 1.699704313592611e-05,
      "loss": 0.5288,
      "step": 16568
    },
    {
      "epoch": 0.5089853469726292,
      "grad_norm": 0.3424490690231323,
      "learning_rate": 1.699669785869363e-05,
      "loss": 0.5464,
      "step": 16569
    },
    {
      "epoch": 0.5090160661075784,
      "grad_norm": 0.36186596751213074,
      "learning_rate": 1.6996352565119875e-05,
      "loss": 0.5384,
      "step": 16570
    },
    {
      "epoch": 0.5090467852425276,
      "grad_norm": 0.35276007652282715,
      "learning_rate": 1.699600725520565e-05,
      "loss": 0.647,
      "step": 16571
    },
    {
      "epoch": 0.5090775043774767,
      "grad_norm": 0.32069772481918335,
      "learning_rate": 1.6995661928951764e-05,
      "loss": 0.5597,
      "step": 16572
    },
    {
      "epoch": 0.5091082235124259,
      "grad_norm": 0.3806896209716797,
      "learning_rate": 1.699531658635902e-05,
      "loss": 0.5934,
      "step": 16573
    },
    {
      "epoch": 0.509138942647375,
      "grad_norm": 0.35602137446403503,
      "learning_rate": 1.6994971227428224e-05,
      "loss": 0.5884,
      "step": 16574
    },
    {
      "epoch": 0.5091696617823243,
      "grad_norm": 0.37929409742355347,
      "learning_rate": 1.6994625852160183e-05,
      "loss": 0.5003,
      "step": 16575
    },
    {
      "epoch": 0.5092003809172734,
      "grad_norm": 0.33972299098968506,
      "learning_rate": 1.6994280460555706e-05,
      "loss": 0.5715,
      "step": 16576
    },
    {
      "epoch": 0.5092311000522225,
      "grad_norm": 0.3628424406051636,
      "learning_rate": 1.69939350526156e-05,
      "loss": 0.628,
      "step": 16577
    },
    {
      "epoch": 0.5092618191871717,
      "grad_norm": 0.3933625817298889,
      "learning_rate": 1.699358962834067e-05,
      "loss": 0.6152,
      "step": 16578
    },
    {
      "epoch": 0.5092925383221208,
      "grad_norm": 0.310471773147583,
      "learning_rate": 1.6993244187731723e-05,
      "loss": 0.5319,
      "step": 16579
    },
    {
      "epoch": 0.50932325745707,
      "grad_norm": 0.3259899616241455,
      "learning_rate": 1.6992898730789563e-05,
      "loss": 0.5453,
      "step": 16580
    },
    {
      "epoch": 0.5093539765920192,
      "grad_norm": 0.35241934657096863,
      "learning_rate": 1.6992553257515003e-05,
      "loss": 0.592,
      "step": 16581
    },
    {
      "epoch": 0.5093846957269683,
      "grad_norm": 0.3511350750923157,
      "learning_rate": 1.6992207767908847e-05,
      "loss": 0.6085,
      "step": 16582
    },
    {
      "epoch": 0.5094154148619174,
      "grad_norm": 0.555147111415863,
      "learning_rate": 1.6991862261971897e-05,
      "loss": 0.6108,
      "step": 16583
    },
    {
      "epoch": 0.5094461339968667,
      "grad_norm": 0.37142276763916016,
      "learning_rate": 1.6991516739704967e-05,
      "loss": 0.5715,
      "step": 16584
    },
    {
      "epoch": 0.5094768531318158,
      "grad_norm": 0.5098720192909241,
      "learning_rate": 1.6991171201108862e-05,
      "loss": 0.524,
      "step": 16585
    },
    {
      "epoch": 0.509507572266765,
      "grad_norm": 0.36604177951812744,
      "learning_rate": 1.6990825646184388e-05,
      "loss": 0.5551,
      "step": 16586
    },
    {
      "epoch": 0.5095382914017141,
      "grad_norm": 0.34208497405052185,
      "learning_rate": 1.699048007493235e-05,
      "loss": 0.5692,
      "step": 16587
    },
    {
      "epoch": 0.5095690105366633,
      "grad_norm": 0.5650104880332947,
      "learning_rate": 1.6990134487353564e-05,
      "loss": 0.6239,
      "step": 16588
    },
    {
      "epoch": 0.5095997296716125,
      "grad_norm": 0.4907754063606262,
      "learning_rate": 1.6989788883448827e-05,
      "loss": 0.6235,
      "step": 16589
    },
    {
      "epoch": 0.5096304488065616,
      "grad_norm": 0.39810892939567566,
      "learning_rate": 1.6989443263218946e-05,
      "loss": 0.4855,
      "step": 16590
    },
    {
      "epoch": 0.5096611679415107,
      "grad_norm": 0.41098353266716003,
      "learning_rate": 1.6989097626664737e-05,
      "loss": 0.6319,
      "step": 16591
    },
    {
      "epoch": 0.50969188707646,
      "grad_norm": 0.35269778966903687,
      "learning_rate": 1.6988751973786998e-05,
      "loss": 0.5338,
      "step": 16592
    },
    {
      "epoch": 0.5097226062114091,
      "grad_norm": 0.33485308289527893,
      "learning_rate": 1.6988406304586544e-05,
      "loss": 0.4269,
      "step": 16593
    },
    {
      "epoch": 0.5097533253463582,
      "grad_norm": 0.35952529311180115,
      "learning_rate": 1.6988060619064182e-05,
      "loss": 0.4667,
      "step": 16594
    },
    {
      "epoch": 0.5097840444813074,
      "grad_norm": 0.36237633228302,
      "learning_rate": 1.698771491722071e-05,
      "loss": 0.5932,
      "step": 16595
    },
    {
      "epoch": 0.5098147636162565,
      "grad_norm": 0.3396117389202118,
      "learning_rate": 1.6987369199056945e-05,
      "loss": 0.5494,
      "step": 16596
    },
    {
      "epoch": 0.5098454827512058,
      "grad_norm": 0.3029267191886902,
      "learning_rate": 1.698702346457369e-05,
      "loss": 0.5473,
      "step": 16597
    },
    {
      "epoch": 0.5098762018861549,
      "grad_norm": 0.3591664135456085,
      "learning_rate": 1.698667771377176e-05,
      "loss": 0.5307,
      "step": 16598
    },
    {
      "epoch": 0.509906921021104,
      "grad_norm": 0.34584006667137146,
      "learning_rate": 1.698633194665195e-05,
      "loss": 0.493,
      "step": 16599
    },
    {
      "epoch": 0.5099376401560533,
      "grad_norm": 0.33521080017089844,
      "learning_rate": 1.6985986163215075e-05,
      "loss": 0.5111,
      "step": 16600
    },
    {
      "epoch": 0.5099683592910024,
      "grad_norm": 0.3228515088558197,
      "learning_rate": 1.698564036346194e-05,
      "loss": 0.5253,
      "step": 16601
    },
    {
      "epoch": 0.5099990784259515,
      "grad_norm": 0.3443116843700409,
      "learning_rate": 1.6985294547393357e-05,
      "loss": 0.5533,
      "step": 16602
    },
    {
      "epoch": 0.5100297975609007,
      "grad_norm": 0.30474478006362915,
      "learning_rate": 1.698494871501013e-05,
      "loss": 0.5177,
      "step": 16603
    },
    {
      "epoch": 0.5100605166958498,
      "grad_norm": 0.35691675543785095,
      "learning_rate": 1.6984602866313066e-05,
      "loss": 0.5344,
      "step": 16604
    },
    {
      "epoch": 0.510091235830799,
      "grad_norm": 0.3305722177028656,
      "learning_rate": 1.6984257001302972e-05,
      "loss": 0.5095,
      "step": 16605
    },
    {
      "epoch": 0.5101219549657482,
      "grad_norm": 0.33528611063957214,
      "learning_rate": 1.698391111998066e-05,
      "loss": 0.5492,
      "step": 16606
    },
    {
      "epoch": 0.5101526741006973,
      "grad_norm": 0.32127898931503296,
      "learning_rate": 1.6983565222346937e-05,
      "loss": 0.5715,
      "step": 16607
    },
    {
      "epoch": 0.5101833932356464,
      "grad_norm": 0.40661752223968506,
      "learning_rate": 1.698321930840261e-05,
      "loss": 0.6242,
      "step": 16608
    },
    {
      "epoch": 0.5102141123705957,
      "grad_norm": 0.33474403619766235,
      "learning_rate": 1.6982873378148487e-05,
      "loss": 0.4877,
      "step": 16609
    },
    {
      "epoch": 0.5102448315055448,
      "grad_norm": 0.39441296458244324,
      "learning_rate": 1.6982527431585373e-05,
      "loss": 0.5638,
      "step": 16610
    },
    {
      "epoch": 0.510275550640494,
      "grad_norm": 0.362701952457428,
      "learning_rate": 1.698218146871408e-05,
      "loss": 0.6066,
      "step": 16611
    },
    {
      "epoch": 0.5103062697754431,
      "grad_norm": 0.33609259128570557,
      "learning_rate": 1.6981835489535417e-05,
      "loss": 0.5503,
      "step": 16612
    },
    {
      "epoch": 0.5103369889103923,
      "grad_norm": 0.46907398104667664,
      "learning_rate": 1.6981489494050184e-05,
      "loss": 0.5766,
      "step": 16613
    },
    {
      "epoch": 0.5103677080453415,
      "grad_norm": 0.3569093942642212,
      "learning_rate": 1.6981143482259198e-05,
      "loss": 0.6049,
      "step": 16614
    },
    {
      "epoch": 0.5103984271802906,
      "grad_norm": 0.35034283995628357,
      "learning_rate": 1.6980797454163264e-05,
      "loss": 0.5916,
      "step": 16615
    },
    {
      "epoch": 0.5104291463152397,
      "grad_norm": 0.3477635085582733,
      "learning_rate": 1.6980451409763193e-05,
      "loss": 0.5629,
      "step": 16616
    },
    {
      "epoch": 0.510459865450189,
      "grad_norm": 0.3356991112232208,
      "learning_rate": 1.6980105349059785e-05,
      "loss": 0.5819,
      "step": 16617
    },
    {
      "epoch": 0.5104905845851381,
      "grad_norm": 0.3352585434913635,
      "learning_rate": 1.6979759272053854e-05,
      "loss": 0.496,
      "step": 16618
    },
    {
      "epoch": 0.5105213037200872,
      "grad_norm": 0.5206630825996399,
      "learning_rate": 1.6979413178746213e-05,
      "loss": 0.5815,
      "step": 16619
    },
    {
      "epoch": 0.5105520228550364,
      "grad_norm": 0.44878262281417847,
      "learning_rate": 1.697906706913766e-05,
      "loss": 0.6708,
      "step": 16620
    },
    {
      "epoch": 0.5105827419899855,
      "grad_norm": 0.3649146258831024,
      "learning_rate": 1.697872094322901e-05,
      "loss": 0.5386,
      "step": 16621
    },
    {
      "epoch": 0.5106134611249348,
      "grad_norm": 0.42647942900657654,
      "learning_rate": 1.697837480102107e-05,
      "loss": 0.6145,
      "step": 16622
    },
    {
      "epoch": 0.5106441802598839,
      "grad_norm": 0.34919002652168274,
      "learning_rate": 1.6978028642514646e-05,
      "loss": 0.5623,
      "step": 16623
    },
    {
      "epoch": 0.510674899394833,
      "grad_norm": 0.36301660537719727,
      "learning_rate": 1.6977682467710552e-05,
      "loss": 0.6447,
      "step": 16624
    },
    {
      "epoch": 0.5107056185297822,
      "grad_norm": 0.3542923033237457,
      "learning_rate": 1.697733627660959e-05,
      "loss": 0.569,
      "step": 16625
    },
    {
      "epoch": 0.5107363376647314,
      "grad_norm": 0.3932088017463684,
      "learning_rate": 1.6976990069212576e-05,
      "loss": 0.6549,
      "step": 16626
    },
    {
      "epoch": 0.5107670567996805,
      "grad_norm": 0.35032373666763306,
      "learning_rate": 1.697664384552031e-05,
      "loss": 0.5239,
      "step": 16627
    },
    {
      "epoch": 0.5107977759346297,
      "grad_norm": 0.3904242217540741,
      "learning_rate": 1.6976297605533605e-05,
      "loss": 0.5529,
      "step": 16628
    },
    {
      "epoch": 0.5108284950695788,
      "grad_norm": 0.4251341223716736,
      "learning_rate": 1.6975951349253274e-05,
      "loss": 0.5938,
      "step": 16629
    },
    {
      "epoch": 0.510859214204528,
      "grad_norm": 0.36328569054603577,
      "learning_rate": 1.6975605076680118e-05,
      "loss": 0.6062,
      "step": 16630
    },
    {
      "epoch": 0.5108899333394772,
      "grad_norm": 0.3420049846172333,
      "learning_rate": 1.697525878781495e-05,
      "loss": 0.6471,
      "step": 16631
    },
    {
      "epoch": 0.5109206524744263,
      "grad_norm": 0.3844349682331085,
      "learning_rate": 1.6974912482658583e-05,
      "loss": 0.5773,
      "step": 16632
    },
    {
      "epoch": 0.5109513716093754,
      "grad_norm": 0.3497650921344757,
      "learning_rate": 1.6974566161211815e-05,
      "loss": 0.5652,
      "step": 16633
    },
    {
      "epoch": 0.5109820907443247,
      "grad_norm": 0.3486821949481964,
      "learning_rate": 1.6974219823475463e-05,
      "loss": 0.5743,
      "step": 16634
    },
    {
      "epoch": 0.5110128098792738,
      "grad_norm": 0.34332311153411865,
      "learning_rate": 1.697387346945033e-05,
      "loss": 0.4702,
      "step": 16635
    },
    {
      "epoch": 0.511043529014223,
      "grad_norm": 0.42813539505004883,
      "learning_rate": 1.697352709913723e-05,
      "loss": 0.5612,
      "step": 16636
    },
    {
      "epoch": 0.5110742481491721,
      "grad_norm": 0.35816460847854614,
      "learning_rate": 1.6973180712536974e-05,
      "loss": 0.6247,
      "step": 16637
    },
    {
      "epoch": 0.5111049672841212,
      "grad_norm": 0.35438984632492065,
      "learning_rate": 1.6972834309650364e-05,
      "loss": 0.5936,
      "step": 16638
    },
    {
      "epoch": 0.5111356864190705,
      "grad_norm": 0.3786731958389282,
      "learning_rate": 1.6972487890478214e-05,
      "loss": 0.6174,
      "step": 16639
    },
    {
      "epoch": 0.5111664055540196,
      "grad_norm": 0.34212014079093933,
      "learning_rate": 1.697214145502133e-05,
      "loss": 0.5363,
      "step": 16640
    },
    {
      "epoch": 0.5111971246889687,
      "grad_norm": 0.3320932686328888,
      "learning_rate": 1.6971795003280523e-05,
      "loss": 0.5141,
      "step": 16641
    },
    {
      "epoch": 0.511227843823918,
      "grad_norm": 0.4228461980819702,
      "learning_rate": 1.6971448535256602e-05,
      "loss": 0.5524,
      "step": 16642
    },
    {
      "epoch": 0.5112585629588671,
      "grad_norm": 0.34028616547584534,
      "learning_rate": 1.6971102050950377e-05,
      "loss": 0.5677,
      "step": 16643
    },
    {
      "epoch": 0.5112892820938162,
      "grad_norm": 0.3198191523551941,
      "learning_rate": 1.6970755550362656e-05,
      "loss": 0.5258,
      "step": 16644
    },
    {
      "epoch": 0.5113200012287654,
      "grad_norm": 0.3764500617980957,
      "learning_rate": 1.6970409033494245e-05,
      "loss": 0.4929,
      "step": 16645
    },
    {
      "epoch": 0.5113507203637145,
      "grad_norm": 0.36218371987342834,
      "learning_rate": 1.697006250034596e-05,
      "loss": 0.5786,
      "step": 16646
    },
    {
      "epoch": 0.5113814394986638,
      "grad_norm": 0.4005981981754303,
      "learning_rate": 1.696971595091861e-05,
      "loss": 0.57,
      "step": 16647
    },
    {
      "epoch": 0.5114121586336129,
      "grad_norm": 0.4015752375125885,
      "learning_rate": 1.6969369385213e-05,
      "loss": 0.5934,
      "step": 16648
    },
    {
      "epoch": 0.511442877768562,
      "grad_norm": 0.35343825817108154,
      "learning_rate": 1.696902280322994e-05,
      "loss": 0.6164,
      "step": 16649
    },
    {
      "epoch": 0.5114735969035112,
      "grad_norm": 0.33493572473526,
      "learning_rate": 1.696867620497024e-05,
      "loss": 0.4864,
      "step": 16650
    },
    {
      "epoch": 0.5115043160384604,
      "grad_norm": 0.3339483439922333,
      "learning_rate": 1.696832959043471e-05,
      "loss": 0.5568,
      "step": 16651
    },
    {
      "epoch": 0.5115350351734095,
      "grad_norm": 0.40932753682136536,
      "learning_rate": 1.6967982959624163e-05,
      "loss": 0.6107,
      "step": 16652
    },
    {
      "epoch": 0.5115657543083587,
      "grad_norm": 0.3513936698436737,
      "learning_rate": 1.69676363125394e-05,
      "loss": 0.617,
      "step": 16653
    },
    {
      "epoch": 0.5115964734433078,
      "grad_norm": 0.3761894106864929,
      "learning_rate": 1.696728964918124e-05,
      "loss": 0.5426,
      "step": 16654
    },
    {
      "epoch": 0.511627192578257,
      "grad_norm": 3.8293540477752686,
      "learning_rate": 1.6966942969550486e-05,
      "loss": 0.5799,
      "step": 16655
    },
    {
      "epoch": 0.5116579117132062,
      "grad_norm": 0.3690864145755768,
      "learning_rate": 1.6966596273647953e-05,
      "loss": 0.5719,
      "step": 16656
    },
    {
      "epoch": 0.5116886308481553,
      "grad_norm": 0.37039461731910706,
      "learning_rate": 1.6966249561474445e-05,
      "loss": 0.5845,
      "step": 16657
    },
    {
      "epoch": 0.5117193499831044,
      "grad_norm": 0.3504750728607178,
      "learning_rate": 1.6965902833030773e-05,
      "loss": 0.5643,
      "step": 16658
    },
    {
      "epoch": 0.5117500691180537,
      "grad_norm": 0.3745456635951996,
      "learning_rate": 1.6965556088317752e-05,
      "loss": 0.6245,
      "step": 16659
    },
    {
      "epoch": 0.5117807882530028,
      "grad_norm": 0.3564121127128601,
      "learning_rate": 1.6965209327336187e-05,
      "loss": 0.588,
      "step": 16660
    },
    {
      "epoch": 0.511811507387952,
      "grad_norm": 0.3532083034515381,
      "learning_rate": 1.696486255008689e-05,
      "loss": 0.5241,
      "step": 16661
    },
    {
      "epoch": 0.5118422265229011,
      "grad_norm": 0.3636507987976074,
      "learning_rate": 1.696451575657067e-05,
      "loss": 0.4768,
      "step": 16662
    },
    {
      "epoch": 0.5118729456578502,
      "grad_norm": 0.4212581217288971,
      "learning_rate": 1.6964168946788334e-05,
      "loss": 0.6142,
      "step": 16663
    },
    {
      "epoch": 0.5119036647927995,
      "grad_norm": 0.31851837038993835,
      "learning_rate": 1.69638221207407e-05,
      "loss": 0.5458,
      "step": 16664
    },
    {
      "epoch": 0.5119343839277486,
      "grad_norm": 0.3447488248348236,
      "learning_rate": 1.696347527842857e-05,
      "loss": 0.5855,
      "step": 16665
    },
    {
      "epoch": 0.5119651030626977,
      "grad_norm": 0.3802010118961334,
      "learning_rate": 1.6963128419852758e-05,
      "loss": 0.5475,
      "step": 16666
    },
    {
      "epoch": 0.5119958221976469,
      "grad_norm": 0.383621484041214,
      "learning_rate": 1.696278154501407e-05,
      "loss": 0.5464,
      "step": 16667
    },
    {
      "epoch": 0.5120265413325961,
      "grad_norm": 0.3533349335193634,
      "learning_rate": 1.6962434653913323e-05,
      "loss": 0.6001,
      "step": 16668
    },
    {
      "epoch": 0.5120572604675452,
      "grad_norm": 0.32003799080848694,
      "learning_rate": 1.6962087746551325e-05,
      "loss": 0.6459,
      "step": 16669
    },
    {
      "epoch": 0.5120879796024944,
      "grad_norm": 0.3225225508213043,
      "learning_rate": 1.6961740822928883e-05,
      "loss": 0.5144,
      "step": 16670
    },
    {
      "epoch": 0.5121186987374435,
      "grad_norm": 0.5116333365440369,
      "learning_rate": 1.6961393883046807e-05,
      "loss": 0.5362,
      "step": 16671
    },
    {
      "epoch": 0.5121494178723928,
      "grad_norm": 0.35582539439201355,
      "learning_rate": 1.6961046926905913e-05,
      "loss": 0.6131,
      "step": 16672
    },
    {
      "epoch": 0.5121801370073419,
      "grad_norm": 0.353527307510376,
      "learning_rate": 1.6960699954507004e-05,
      "loss": 0.618,
      "step": 16673
    },
    {
      "epoch": 0.512210856142291,
      "grad_norm": 0.386699378490448,
      "learning_rate": 1.6960352965850897e-05,
      "loss": 0.6192,
      "step": 16674
    },
    {
      "epoch": 0.5122415752772402,
      "grad_norm": 0.363334983587265,
      "learning_rate": 1.6960005960938398e-05,
      "loss": 0.5257,
      "step": 16675
    },
    {
      "epoch": 0.5122722944121894,
      "grad_norm": 0.3261290192604065,
      "learning_rate": 1.6959658939770324e-05,
      "loss": 0.6184,
      "step": 16676
    },
    {
      "epoch": 0.5123030135471385,
      "grad_norm": 0.3607628345489502,
      "learning_rate": 1.6959311902347474e-05,
      "loss": 0.5981,
      "step": 16677
    },
    {
      "epoch": 0.5123337326820877,
      "grad_norm": 0.33964887261390686,
      "learning_rate": 1.6958964848670668e-05,
      "loss": 0.5831,
      "step": 16678
    },
    {
      "epoch": 0.5123644518170368,
      "grad_norm": 0.36008843779563904,
      "learning_rate": 1.6958617778740713e-05,
      "loss": 0.558,
      "step": 16679
    },
    {
      "epoch": 0.512395170951986,
      "grad_norm": 0.34126725792884827,
      "learning_rate": 1.695827069255842e-05,
      "loss": 0.5519,
      "step": 16680
    },
    {
      "epoch": 0.5124258900869352,
      "grad_norm": 0.3816923201084137,
      "learning_rate": 1.6957923590124597e-05,
      "loss": 0.6596,
      "step": 16681
    },
    {
      "epoch": 0.5124566092218843,
      "grad_norm": 0.37047278881073,
      "learning_rate": 1.695757647144006e-05,
      "loss": 0.5614,
      "step": 16682
    },
    {
      "epoch": 0.5124873283568335,
      "grad_norm": 0.3346508741378784,
      "learning_rate": 1.6957229336505617e-05,
      "loss": 0.5637,
      "step": 16683
    },
    {
      "epoch": 0.5125180474917826,
      "grad_norm": 0.34559327363967896,
      "learning_rate": 1.6956882185322082e-05,
      "loss": 0.58,
      "step": 16684
    },
    {
      "epoch": 0.5125487666267318,
      "grad_norm": 1.048160433769226,
      "learning_rate": 1.6956535017890263e-05,
      "loss": 0.5769,
      "step": 16685
    },
    {
      "epoch": 0.512579485761681,
      "grad_norm": 0.3450837731361389,
      "learning_rate": 1.6956187834210966e-05,
      "loss": 0.6527,
      "step": 16686
    },
    {
      "epoch": 0.5126102048966301,
      "grad_norm": 0.37714633345603943,
      "learning_rate": 1.6955840634285007e-05,
      "loss": 0.5471,
      "step": 16687
    },
    {
      "epoch": 0.5126409240315792,
      "grad_norm": 0.3184656798839569,
      "learning_rate": 1.69554934181132e-05,
      "loss": 0.5278,
      "step": 16688
    },
    {
      "epoch": 0.5126716431665285,
      "grad_norm": 0.39198580384254456,
      "learning_rate": 1.695514618569635e-05,
      "loss": 0.5426,
      "step": 16689
    },
    {
      "epoch": 0.5127023623014776,
      "grad_norm": 0.34338462352752686,
      "learning_rate": 1.695479893703527e-05,
      "loss": 0.5943,
      "step": 16690
    },
    {
      "epoch": 0.5127330814364267,
      "grad_norm": 0.3583843410015106,
      "learning_rate": 1.6954451672130772e-05,
      "loss": 0.5353,
      "step": 16691
    },
    {
      "epoch": 0.5127638005713759,
      "grad_norm": 0.3869650363922119,
      "learning_rate": 1.6954104390983665e-05,
      "loss": 0.5729,
      "step": 16692
    },
    {
      "epoch": 0.5127945197063251,
      "grad_norm": 0.3351300060749054,
      "learning_rate": 1.6953757093594765e-05,
      "loss": 0.5193,
      "step": 16693
    },
    {
      "epoch": 0.5128252388412742,
      "grad_norm": 0.4005741775035858,
      "learning_rate": 1.695340977996488e-05,
      "loss": 0.6275,
      "step": 16694
    },
    {
      "epoch": 0.5128559579762234,
      "grad_norm": 0.33736610412597656,
      "learning_rate": 1.6953062450094817e-05,
      "loss": 0.5373,
      "step": 16695
    },
    {
      "epoch": 0.5128866771111725,
      "grad_norm": 0.4764644205570221,
      "learning_rate": 1.6952715103985392e-05,
      "loss": 0.6726,
      "step": 16696
    },
    {
      "epoch": 0.5129173962461218,
      "grad_norm": 0.411628782749176,
      "learning_rate": 1.6952367741637417e-05,
      "loss": 0.5026,
      "step": 16697
    },
    {
      "epoch": 0.5129481153810709,
      "grad_norm": 0.3281288146972656,
      "learning_rate": 1.69520203630517e-05,
      "loss": 0.6327,
      "step": 16698
    },
    {
      "epoch": 0.51297883451602,
      "grad_norm": 0.37892505526542664,
      "learning_rate": 1.6951672968229053e-05,
      "loss": 0.6564,
      "step": 16699
    },
    {
      "epoch": 0.5130095536509692,
      "grad_norm": 0.33556225895881653,
      "learning_rate": 1.695132555717029e-05,
      "loss": 0.5855,
      "step": 16700
    },
    {
      "epoch": 0.5130402727859183,
      "grad_norm": 0.4660538136959076,
      "learning_rate": 1.695097812987622e-05,
      "loss": 0.5614,
      "step": 16701
    },
    {
      "epoch": 0.5130709919208675,
      "grad_norm": 0.33185625076293945,
      "learning_rate": 1.695063068634765e-05,
      "loss": 0.5156,
      "step": 16702
    },
    {
      "epoch": 0.5131017110558167,
      "grad_norm": 0.3260880410671234,
      "learning_rate": 1.6950283226585406e-05,
      "loss": 0.6095,
      "step": 16703
    },
    {
      "epoch": 0.5131324301907658,
      "grad_norm": 0.4438531696796417,
      "learning_rate": 1.694993575059029e-05,
      "loss": 0.6293,
      "step": 16704
    },
    {
      "epoch": 0.5131631493257149,
      "grad_norm": 0.343718558549881,
      "learning_rate": 1.694958825836311e-05,
      "loss": 0.5842,
      "step": 16705
    },
    {
      "epoch": 0.5131938684606642,
      "grad_norm": 0.3888421952724457,
      "learning_rate": 1.694924074990468e-05,
      "loss": 0.5594,
      "step": 16706
    },
    {
      "epoch": 0.5132245875956133,
      "grad_norm": 0.391339510679245,
      "learning_rate": 1.6948893225215815e-05,
      "loss": 0.6535,
      "step": 16707
    },
    {
      "epoch": 0.5132553067305625,
      "grad_norm": 0.36790093779563904,
      "learning_rate": 1.694854568429732e-05,
      "loss": 0.4911,
      "step": 16708
    },
    {
      "epoch": 0.5132860258655116,
      "grad_norm": 0.3338550925254822,
      "learning_rate": 1.6948198127150016e-05,
      "loss": 0.4755,
      "step": 16709
    },
    {
      "epoch": 0.5133167450004608,
      "grad_norm": 0.32875150442123413,
      "learning_rate": 1.694785055377471e-05,
      "loss": 0.4978,
      "step": 16710
    },
    {
      "epoch": 0.51334746413541,
      "grad_norm": 0.3542599678039551,
      "learning_rate": 1.6947502964172212e-05,
      "loss": 0.5715,
      "step": 16711
    },
    {
      "epoch": 0.5133781832703591,
      "grad_norm": 0.3634461760520935,
      "learning_rate": 1.6947155358343336e-05,
      "loss": 0.6191,
      "step": 16712
    },
    {
      "epoch": 0.5134089024053082,
      "grad_norm": 0.38945358991622925,
      "learning_rate": 1.6946807736288896e-05,
      "loss": 0.5375,
      "step": 16713
    },
    {
      "epoch": 0.5134396215402575,
      "grad_norm": 0.3486246168613434,
      "learning_rate": 1.69464600980097e-05,
      "loss": 0.574,
      "step": 16714
    },
    {
      "epoch": 0.5134703406752066,
      "grad_norm": 0.32793331146240234,
      "learning_rate": 1.694611244350656e-05,
      "loss": 0.5267,
      "step": 16715
    },
    {
      "epoch": 0.5135010598101557,
      "grad_norm": 0.35192015767097473,
      "learning_rate": 1.694576477278029e-05,
      "loss": 0.5666,
      "step": 16716
    },
    {
      "epoch": 0.5135317789451049,
      "grad_norm": 0.3883066773414612,
      "learning_rate": 1.69454170858317e-05,
      "loss": 0.569,
      "step": 16717
    },
    {
      "epoch": 0.513562498080054,
      "grad_norm": 0.3757852613925934,
      "learning_rate": 1.69450693826616e-05,
      "loss": 0.5849,
      "step": 16718
    },
    {
      "epoch": 0.5135932172150032,
      "grad_norm": 0.3494272828102112,
      "learning_rate": 1.694472166327081e-05,
      "loss": 0.5228,
      "step": 16719
    },
    {
      "epoch": 0.5136239363499524,
      "grad_norm": 0.391877144575119,
      "learning_rate": 1.694437392766014e-05,
      "loss": 0.6339,
      "step": 16720
    },
    {
      "epoch": 0.5136546554849015,
      "grad_norm": 0.35454073548316956,
      "learning_rate": 1.6944026175830396e-05,
      "loss": 0.599,
      "step": 16721
    },
    {
      "epoch": 0.5136853746198508,
      "grad_norm": 0.3764244019985199,
      "learning_rate": 1.6943678407782394e-05,
      "loss": 0.5572,
      "step": 16722
    },
    {
      "epoch": 0.5137160937547999,
      "grad_norm": 0.37299492955207825,
      "learning_rate": 1.694333062351695e-05,
      "loss": 0.5272,
      "step": 16723
    },
    {
      "epoch": 0.513746812889749,
      "grad_norm": 0.32180583477020264,
      "learning_rate": 1.694298282303487e-05,
      "loss": 0.6249,
      "step": 16724
    },
    {
      "epoch": 0.5137775320246982,
      "grad_norm": 0.36046692728996277,
      "learning_rate": 1.6942635006336967e-05,
      "loss": 0.5788,
      "step": 16725
    },
    {
      "epoch": 0.5138082511596473,
      "grad_norm": 0.31389111280441284,
      "learning_rate": 1.6942287173424053e-05,
      "loss": 0.57,
      "step": 16726
    },
    {
      "epoch": 0.5138389702945965,
      "grad_norm": 0.35290399193763733,
      "learning_rate": 1.6941939324296946e-05,
      "loss": 0.5987,
      "step": 16727
    },
    {
      "epoch": 0.5138696894295457,
      "grad_norm": 0.31776899099349976,
      "learning_rate": 1.6941591458956457e-05,
      "loss": 0.5347,
      "step": 16728
    },
    {
      "epoch": 0.5139004085644948,
      "grad_norm": 0.4290764033794403,
      "learning_rate": 1.6941243577403394e-05,
      "loss": 0.5338,
      "step": 16729
    },
    {
      "epoch": 0.5139311276994439,
      "grad_norm": 0.37578025460243225,
      "learning_rate": 1.694089567963857e-05,
      "loss": 0.5828,
      "step": 16730
    },
    {
      "epoch": 0.5139618468343932,
      "grad_norm": 0.35659554600715637,
      "learning_rate": 1.6940547765662802e-05,
      "loss": 0.5372,
      "step": 16731
    },
    {
      "epoch": 0.5139925659693423,
      "grad_norm": 0.37390056252479553,
      "learning_rate": 1.6940199835476902e-05,
      "loss": 0.5973,
      "step": 16732
    },
    {
      "epoch": 0.5140232851042915,
      "grad_norm": 0.37303999066352844,
      "learning_rate": 1.6939851889081675e-05,
      "loss": 0.5576,
      "step": 16733
    },
    {
      "epoch": 0.5140540042392406,
      "grad_norm": 0.710156261920929,
      "learning_rate": 1.6939503926477944e-05,
      "loss": 0.6178,
      "step": 16734
    },
    {
      "epoch": 0.5140847233741898,
      "grad_norm": 0.7671505808830261,
      "learning_rate": 1.6939155947666515e-05,
      "loss": 0.5463,
      "step": 16735
    },
    {
      "epoch": 0.514115442509139,
      "grad_norm": 0.34734830260276794,
      "learning_rate": 1.6938807952648198e-05,
      "loss": 0.5437,
      "step": 16736
    },
    {
      "epoch": 0.5141461616440881,
      "grad_norm": 0.34151190519332886,
      "learning_rate": 1.693845994142382e-05,
      "loss": 0.5139,
      "step": 16737
    },
    {
      "epoch": 0.5141768807790372,
      "grad_norm": 0.37832415103912354,
      "learning_rate": 1.6938111913994178e-05,
      "loss": 0.5613,
      "step": 16738
    },
    {
      "epoch": 0.5142075999139865,
      "grad_norm": 0.3420490622520447,
      "learning_rate": 1.6937763870360093e-05,
      "loss": 0.5601,
      "step": 16739
    },
    {
      "epoch": 0.5142383190489356,
      "grad_norm": 0.36457395553588867,
      "learning_rate": 1.6937415810522374e-05,
      "loss": 0.6239,
      "step": 16740
    },
    {
      "epoch": 0.5142690381838847,
      "grad_norm": 0.3755052983760834,
      "learning_rate": 1.693706773448184e-05,
      "loss": 0.5781,
      "step": 16741
    },
    {
      "epoch": 0.5142997573188339,
      "grad_norm": 0.37688466906547546,
      "learning_rate": 1.6936719642239295e-05,
      "loss": 0.5651,
      "step": 16742
    },
    {
      "epoch": 0.514330476453783,
      "grad_norm": 0.3332737684249878,
      "learning_rate": 1.6936371533795556e-05,
      "loss": 0.5583,
      "step": 16743
    },
    {
      "epoch": 0.5143611955887322,
      "grad_norm": 0.318699449300766,
      "learning_rate": 1.693602340915144e-05,
      "loss": 0.5523,
      "step": 16744
    },
    {
      "epoch": 0.5143919147236814,
      "grad_norm": 0.34614473581314087,
      "learning_rate": 1.693567526830776e-05,
      "loss": 0.5761,
      "step": 16745
    },
    {
      "epoch": 0.5144226338586305,
      "grad_norm": 0.3639524579048157,
      "learning_rate": 1.6935327111265324e-05,
      "loss": 0.6084,
      "step": 16746
    },
    {
      "epoch": 0.5144533529935797,
      "grad_norm": 0.3081194758415222,
      "learning_rate": 1.6934978938024943e-05,
      "loss": 0.5183,
      "step": 16747
    },
    {
      "epoch": 0.5144840721285289,
      "grad_norm": 0.32443010807037354,
      "learning_rate": 1.6934630748587438e-05,
      "loss": 0.5114,
      "step": 16748
    },
    {
      "epoch": 0.514514791263478,
      "grad_norm": 0.34718477725982666,
      "learning_rate": 1.6934282542953617e-05,
      "loss": 0.5563,
      "step": 16749
    },
    {
      "epoch": 0.5145455103984272,
      "grad_norm": 0.34371715784072876,
      "learning_rate": 1.6933934321124295e-05,
      "loss": 0.5972,
      "step": 16750
    },
    {
      "epoch": 0.5145762295333763,
      "grad_norm": 0.34512755274772644,
      "learning_rate": 1.6933586083100287e-05,
      "loss": 0.5174,
      "step": 16751
    },
    {
      "epoch": 0.5146069486683255,
      "grad_norm": 0.38403502106666565,
      "learning_rate": 1.6933237828882404e-05,
      "loss": 0.5674,
      "step": 16752
    },
    {
      "epoch": 0.5146376678032747,
      "grad_norm": 0.3877411186695099,
      "learning_rate": 1.693288955847146e-05,
      "loss": 0.5824,
      "step": 16753
    },
    {
      "epoch": 0.5146683869382238,
      "grad_norm": 0.3396456837654114,
      "learning_rate": 1.6932541271868265e-05,
      "loss": 0.5953,
      "step": 16754
    },
    {
      "epoch": 0.5146991060731729,
      "grad_norm": 0.33729681372642517,
      "learning_rate": 1.693219296907364e-05,
      "loss": 0.5362,
      "step": 16755
    },
    {
      "epoch": 0.5147298252081222,
      "grad_norm": 0.340252161026001,
      "learning_rate": 1.6931844650088388e-05,
      "loss": 0.5738,
      "step": 16756
    },
    {
      "epoch": 0.5147605443430713,
      "grad_norm": 0.360125869512558,
      "learning_rate": 1.6931496314913336e-05,
      "loss": 0.4947,
      "step": 16757
    },
    {
      "epoch": 0.5147912634780205,
      "grad_norm": 0.3776156008243561,
      "learning_rate": 1.6931147963549285e-05,
      "loss": 0.5643,
      "step": 16758
    },
    {
      "epoch": 0.5148219826129696,
      "grad_norm": 0.35319605469703674,
      "learning_rate": 1.6930799595997055e-05,
      "loss": 0.5578,
      "step": 16759
    },
    {
      "epoch": 0.5148527017479188,
      "grad_norm": 0.4239419996738434,
      "learning_rate": 1.693045121225746e-05,
      "loss": 0.5461,
      "step": 16760
    },
    {
      "epoch": 0.514883420882868,
      "grad_norm": 0.38139548897743225,
      "learning_rate": 1.6930102812331313e-05,
      "loss": 0.5857,
      "step": 16761
    },
    {
      "epoch": 0.5149141400178171,
      "grad_norm": 0.3269401788711548,
      "learning_rate": 1.6929754396219427e-05,
      "loss": 0.5766,
      "step": 16762
    },
    {
      "epoch": 0.5149448591527662,
      "grad_norm": 0.39696016907691956,
      "learning_rate": 1.692940596392261e-05,
      "loss": 0.5925,
      "step": 16763
    },
    {
      "epoch": 0.5149755782877155,
      "grad_norm": 0.364874929189682,
      "learning_rate": 1.692905751544169e-05,
      "loss": 0.5621,
      "step": 16764
    },
    {
      "epoch": 0.5150062974226646,
      "grad_norm": 0.33001261949539185,
      "learning_rate": 1.6928709050777464e-05,
      "loss": 0.5268,
      "step": 16765
    },
    {
      "epoch": 0.5150370165576137,
      "grad_norm": 0.372519850730896,
      "learning_rate": 1.692836056993076e-05,
      "loss": 0.5591,
      "step": 16766
    },
    {
      "epoch": 0.5150677356925629,
      "grad_norm": 0.34122616052627563,
      "learning_rate": 1.6928012072902385e-05,
      "loss": 0.5842,
      "step": 16767
    },
    {
      "epoch": 0.515098454827512,
      "grad_norm": 0.3584970235824585,
      "learning_rate": 1.6927663559693154e-05,
      "loss": 0.5364,
      "step": 16768
    },
    {
      "epoch": 0.5151291739624612,
      "grad_norm": 0.3666256368160248,
      "learning_rate": 1.692731503030388e-05,
      "loss": 0.6244,
      "step": 16769
    },
    {
      "epoch": 0.5151598930974104,
      "grad_norm": 0.3299579918384552,
      "learning_rate": 1.6926966484735376e-05,
      "loss": 0.5669,
      "step": 16770
    },
    {
      "epoch": 0.5151906122323595,
      "grad_norm": 0.34387531876564026,
      "learning_rate": 1.692661792298846e-05,
      "loss": 0.5563,
      "step": 16771
    },
    {
      "epoch": 0.5152213313673087,
      "grad_norm": 0.3681296706199646,
      "learning_rate": 1.6926269345063943e-05,
      "loss": 0.5912,
      "step": 16772
    },
    {
      "epoch": 0.5152520505022579,
      "grad_norm": 0.34074661135673523,
      "learning_rate": 1.692592075096264e-05,
      "loss": 0.6132,
      "step": 16773
    },
    {
      "epoch": 0.515282769637207,
      "grad_norm": 0.35199445486068726,
      "learning_rate": 1.6925572140685365e-05,
      "loss": 0.5703,
      "step": 16774
    },
    {
      "epoch": 0.5153134887721562,
      "grad_norm": 0.3495255410671234,
      "learning_rate": 1.6925223514232935e-05,
      "loss": 0.584,
      "step": 16775
    },
    {
      "epoch": 0.5153442079071053,
      "grad_norm": 0.334765762090683,
      "learning_rate": 1.6924874871606163e-05,
      "loss": 0.5612,
      "step": 16776
    },
    {
      "epoch": 0.5153749270420545,
      "grad_norm": 0.31781908869743347,
      "learning_rate": 1.6924526212805862e-05,
      "loss": 0.5565,
      "step": 16777
    },
    {
      "epoch": 0.5154056461770037,
      "grad_norm": 0.5656083822250366,
      "learning_rate": 1.6924177537832843e-05,
      "loss": 0.5516,
      "step": 16778
    },
    {
      "epoch": 0.5154363653119528,
      "grad_norm": 0.37646326422691345,
      "learning_rate": 1.6923828846687926e-05,
      "loss": 0.6374,
      "step": 16779
    },
    {
      "epoch": 0.5154670844469019,
      "grad_norm": 0.34485021233558655,
      "learning_rate": 1.692348013937192e-05,
      "loss": 0.5945,
      "step": 16780
    },
    {
      "epoch": 0.5154978035818512,
      "grad_norm": 0.3592008352279663,
      "learning_rate": 1.6923131415885644e-05,
      "loss": 0.6411,
      "step": 16781
    },
    {
      "epoch": 0.5155285227168003,
      "grad_norm": 0.3680160343647003,
      "learning_rate": 1.6922782676229913e-05,
      "loss": 0.663,
      "step": 16782
    },
    {
      "epoch": 0.5155592418517495,
      "grad_norm": 0.40018248558044434,
      "learning_rate": 1.6922433920405543e-05,
      "loss": 0.574,
      "step": 16783
    },
    {
      "epoch": 0.5155899609866986,
      "grad_norm": 0.3929399847984314,
      "learning_rate": 1.692208514841334e-05,
      "loss": 0.6505,
      "step": 16784
    },
    {
      "epoch": 0.5156206801216477,
      "grad_norm": 0.34230560064315796,
      "learning_rate": 1.6921736360254123e-05,
      "loss": 0.5674,
      "step": 16785
    },
    {
      "epoch": 0.515651399256597,
      "grad_norm": 0.36263343691825867,
      "learning_rate": 1.692138755592871e-05,
      "loss": 0.5167,
      "step": 16786
    },
    {
      "epoch": 0.5156821183915461,
      "grad_norm": 0.3682510256767273,
      "learning_rate": 1.692103873543791e-05,
      "loss": 0.6476,
      "step": 16787
    },
    {
      "epoch": 0.5157128375264952,
      "grad_norm": 0.45946425199508667,
      "learning_rate": 1.6920689898782542e-05,
      "loss": 0.5792,
      "step": 16788
    },
    {
      "epoch": 0.5157435566614444,
      "grad_norm": 0.38014769554138184,
      "learning_rate": 1.692034104596342e-05,
      "loss": 0.5888,
      "step": 16789
    },
    {
      "epoch": 0.5157742757963936,
      "grad_norm": 0.37714138627052307,
      "learning_rate": 1.691999217698136e-05,
      "loss": 0.5969,
      "step": 16790
    },
    {
      "epoch": 0.5158049949313427,
      "grad_norm": 0.36176612973213196,
      "learning_rate": 1.691964329183717e-05,
      "loss": 0.4887,
      "step": 16791
    },
    {
      "epoch": 0.5158357140662919,
      "grad_norm": 0.35487279295921326,
      "learning_rate": 1.6919294390531672e-05,
      "loss": 0.5391,
      "step": 16792
    },
    {
      "epoch": 0.515866433201241,
      "grad_norm": 0.3985297679901123,
      "learning_rate": 1.6918945473065683e-05,
      "loss": 0.5748,
      "step": 16793
    },
    {
      "epoch": 0.5158971523361903,
      "grad_norm": 0.3560030460357666,
      "learning_rate": 1.691859653944001e-05,
      "loss": 0.5643,
      "step": 16794
    },
    {
      "epoch": 0.5159278714711394,
      "grad_norm": 0.3487459421157837,
      "learning_rate": 1.691824758965547e-05,
      "loss": 0.5281,
      "step": 16795
    },
    {
      "epoch": 0.5159585906060885,
      "grad_norm": 0.3482080399990082,
      "learning_rate": 1.6917898623712884e-05,
      "loss": 0.5298,
      "step": 16796
    },
    {
      "epoch": 0.5159893097410377,
      "grad_norm": 0.45495715737342834,
      "learning_rate": 1.6917549641613057e-05,
      "loss": 0.4896,
      "step": 16797
    },
    {
      "epoch": 0.5160200288759869,
      "grad_norm": 0.4351052939891815,
      "learning_rate": 1.6917200643356815e-05,
      "loss": 0.5967,
      "step": 16798
    },
    {
      "epoch": 0.516050748010936,
      "grad_norm": 0.3340330719947815,
      "learning_rate": 1.6916851628944965e-05,
      "loss": 0.6251,
      "step": 16799
    },
    {
      "epoch": 0.5160814671458852,
      "grad_norm": 0.44640395045280457,
      "learning_rate": 1.6916502598378323e-05,
      "loss": 0.588,
      "step": 16800
    },
    {
      "epoch": 0.5161121862808343,
      "grad_norm": 0.35083943605422974,
      "learning_rate": 1.6916153551657712e-05,
      "loss": 0.5447,
      "step": 16801
    },
    {
      "epoch": 0.5161429054157834,
      "grad_norm": 0.37524840235710144,
      "learning_rate": 1.691580448878394e-05,
      "loss": 0.5903,
      "step": 16802
    },
    {
      "epoch": 0.5161736245507327,
      "grad_norm": 0.34428420662879944,
      "learning_rate": 1.691545540975782e-05,
      "loss": 0.5634,
      "step": 16803
    },
    {
      "epoch": 0.5162043436856818,
      "grad_norm": 0.40962865948677063,
      "learning_rate": 1.6915106314580173e-05,
      "loss": 0.6335,
      "step": 16804
    },
    {
      "epoch": 0.5162350628206309,
      "grad_norm": 0.3637882173061371,
      "learning_rate": 1.6914757203251812e-05,
      "loss": 0.6031,
      "step": 16805
    },
    {
      "epoch": 0.5162657819555801,
      "grad_norm": 0.3537442088127136,
      "learning_rate": 1.691440807577355e-05,
      "loss": 0.5618,
      "step": 16806
    },
    {
      "epoch": 0.5162965010905293,
      "grad_norm": 0.34722432494163513,
      "learning_rate": 1.6914058932146206e-05,
      "loss": 0.5969,
      "step": 16807
    },
    {
      "epoch": 0.5163272202254785,
      "grad_norm": 0.5048168897628784,
      "learning_rate": 1.69137097723706e-05,
      "loss": 0.5201,
      "step": 16808
    },
    {
      "epoch": 0.5163579393604276,
      "grad_norm": 0.3416930139064789,
      "learning_rate": 1.6913360596447534e-05,
      "loss": 0.543,
      "step": 16809
    },
    {
      "epoch": 0.5163886584953767,
      "grad_norm": 0.34718453884124756,
      "learning_rate": 1.6913011404377838e-05,
      "loss": 0.6756,
      "step": 16810
    },
    {
      "epoch": 0.516419377630326,
      "grad_norm": 0.5435742735862732,
      "learning_rate": 1.6912662196162318e-05,
      "loss": 0.6037,
      "step": 16811
    },
    {
      "epoch": 0.5164500967652751,
      "grad_norm": 0.33784911036491394,
      "learning_rate": 1.691231297180179e-05,
      "loss": 0.6271,
      "step": 16812
    },
    {
      "epoch": 0.5164808159002242,
      "grad_norm": 0.3416939079761505,
      "learning_rate": 1.6911963731297078e-05,
      "loss": 0.5019,
      "step": 16813
    },
    {
      "epoch": 0.5165115350351734,
      "grad_norm": 0.3516436517238617,
      "learning_rate": 1.691161447464899e-05,
      "loss": 0.5759,
      "step": 16814
    },
    {
      "epoch": 0.5165422541701226,
      "grad_norm": 0.35791081190109253,
      "learning_rate": 1.6911265201858342e-05,
      "loss": 0.5808,
      "step": 16815
    },
    {
      "epoch": 0.5165729733050717,
      "grad_norm": 0.36817410588264465,
      "learning_rate": 1.6910915912925953e-05,
      "loss": 0.5406,
      "step": 16816
    },
    {
      "epoch": 0.5166036924400209,
      "grad_norm": 0.3548276424407959,
      "learning_rate": 1.6910566607852636e-05,
      "loss": 0.6484,
      "step": 16817
    },
    {
      "epoch": 0.51663441157497,
      "grad_norm": 0.3789390027523041,
      "learning_rate": 1.691021728663921e-05,
      "loss": 0.5795,
      "step": 16818
    },
    {
      "epoch": 0.5166651307099193,
      "grad_norm": 0.3552594780921936,
      "learning_rate": 1.690986794928649e-05,
      "loss": 0.6073,
      "step": 16819
    },
    {
      "epoch": 0.5166958498448684,
      "grad_norm": 0.3495624363422394,
      "learning_rate": 1.6909518595795288e-05,
      "loss": 0.5491,
      "step": 16820
    },
    {
      "epoch": 0.5167265689798175,
      "grad_norm": 0.3555338382720947,
      "learning_rate": 1.6909169226166422e-05,
      "loss": 0.5251,
      "step": 16821
    },
    {
      "epoch": 0.5167572881147667,
      "grad_norm": 0.2991284132003784,
      "learning_rate": 1.6908819840400708e-05,
      "loss": 0.5276,
      "step": 16822
    },
    {
      "epoch": 0.5167880072497159,
      "grad_norm": 0.34769490361213684,
      "learning_rate": 1.6908470438498966e-05,
      "loss": 0.494,
      "step": 16823
    },
    {
      "epoch": 0.516818726384665,
      "grad_norm": 0.35056766867637634,
      "learning_rate": 1.6908121020462008e-05,
      "loss": 0.5988,
      "step": 16824
    },
    {
      "epoch": 0.5168494455196142,
      "grad_norm": 0.44386231899261475,
      "learning_rate": 1.690777158629065e-05,
      "loss": 0.6203,
      "step": 16825
    },
    {
      "epoch": 0.5168801646545633,
      "grad_norm": 0.38168448209762573,
      "learning_rate": 1.6907422135985712e-05,
      "loss": 0.5179,
      "step": 16826
    },
    {
      "epoch": 0.5169108837895124,
      "grad_norm": 0.5198469758033752,
      "learning_rate": 1.6907072669548004e-05,
      "loss": 0.5536,
      "step": 16827
    },
    {
      "epoch": 0.5169416029244617,
      "grad_norm": 0.32893773913383484,
      "learning_rate": 1.6906723186978347e-05,
      "loss": 0.5267,
      "step": 16828
    },
    {
      "epoch": 0.5169723220594108,
      "grad_norm": 0.36757341027259827,
      "learning_rate": 1.6906373688277554e-05,
      "loss": 0.5095,
      "step": 16829
    },
    {
      "epoch": 0.5170030411943599,
      "grad_norm": 0.34942182898521423,
      "learning_rate": 1.690602417344644e-05,
      "loss": 0.6221,
      "step": 16830
    },
    {
      "epoch": 0.5170337603293091,
      "grad_norm": 0.36688265204429626,
      "learning_rate": 1.690567464248583e-05,
      "loss": 0.5881,
      "step": 16831
    },
    {
      "epoch": 0.5170644794642583,
      "grad_norm": 0.3469028174877167,
      "learning_rate": 1.6905325095396534e-05,
      "loss": 0.5976,
      "step": 16832
    },
    {
      "epoch": 0.5170951985992075,
      "grad_norm": 0.4199966788291931,
      "learning_rate": 1.6904975532179366e-05,
      "loss": 0.6247,
      "step": 16833
    },
    {
      "epoch": 0.5171259177341566,
      "grad_norm": 0.39662599563598633,
      "learning_rate": 1.6904625952835147e-05,
      "loss": 0.56,
      "step": 16834
    },
    {
      "epoch": 0.5171566368691057,
      "grad_norm": 0.3766920864582062,
      "learning_rate": 1.6904276357364692e-05,
      "loss": 0.5618,
      "step": 16835
    },
    {
      "epoch": 0.517187356004055,
      "grad_norm": 0.3832724690437317,
      "learning_rate": 1.690392674576882e-05,
      "loss": 0.5537,
      "step": 16836
    },
    {
      "epoch": 0.5172180751390041,
      "grad_norm": 0.3481455445289612,
      "learning_rate": 1.690357711804834e-05,
      "loss": 0.5973,
      "step": 16837
    },
    {
      "epoch": 0.5172487942739532,
      "grad_norm": 0.34409916400909424,
      "learning_rate": 1.6903227474204075e-05,
      "loss": 0.5437,
      "step": 16838
    },
    {
      "epoch": 0.5172795134089024,
      "grad_norm": 0.32271841168403625,
      "learning_rate": 1.6902877814236842e-05,
      "loss": 0.5246,
      "step": 16839
    },
    {
      "epoch": 0.5173102325438516,
      "grad_norm": 0.44427311420440674,
      "learning_rate": 1.6902528138147455e-05,
      "loss": 0.6639,
      "step": 16840
    },
    {
      "epoch": 0.5173409516788007,
      "grad_norm": 0.37140724062919617,
      "learning_rate": 1.690217844593673e-05,
      "loss": 0.5616,
      "step": 16841
    },
    {
      "epoch": 0.5173716708137499,
      "grad_norm": 0.3378331661224365,
      "learning_rate": 1.6901828737605487e-05,
      "loss": 0.6175,
      "step": 16842
    },
    {
      "epoch": 0.517402389948699,
      "grad_norm": 0.3738175928592682,
      "learning_rate": 1.690147901315454e-05,
      "loss": 0.5603,
      "step": 16843
    },
    {
      "epoch": 0.5174331090836483,
      "grad_norm": 0.3359449505805969,
      "learning_rate": 1.6901129272584705e-05,
      "loss": 0.5313,
      "step": 16844
    },
    {
      "epoch": 0.5174638282185974,
      "grad_norm": 0.34995123744010925,
      "learning_rate": 1.6900779515896806e-05,
      "loss": 0.5721,
      "step": 16845
    },
    {
      "epoch": 0.5174945473535465,
      "grad_norm": 0.34810128808021545,
      "learning_rate": 1.6900429743091648e-05,
      "loss": 0.5176,
      "step": 16846
    },
    {
      "epoch": 0.5175252664884957,
      "grad_norm": 0.32599228620529175,
      "learning_rate": 1.690007995417006e-05,
      "loss": 0.6169,
      "step": 16847
    },
    {
      "epoch": 0.5175559856234448,
      "grad_norm": 0.3794202506542206,
      "learning_rate": 1.6899730149132848e-05,
      "loss": 0.5977,
      "step": 16848
    },
    {
      "epoch": 0.517586704758394,
      "grad_norm": 0.3580975830554962,
      "learning_rate": 1.689938032798084e-05,
      "loss": 0.6034,
      "step": 16849
    },
    {
      "epoch": 0.5176174238933432,
      "grad_norm": 0.3803461492061615,
      "learning_rate": 1.6899030490714844e-05,
      "loss": 0.5433,
      "step": 16850
    },
    {
      "epoch": 0.5176481430282923,
      "grad_norm": 0.44161686301231384,
      "learning_rate": 1.689868063733568e-05,
      "loss": 0.5659,
      "step": 16851
    },
    {
      "epoch": 0.5176788621632414,
      "grad_norm": 0.34753090143203735,
      "learning_rate": 1.6898330767844168e-05,
      "loss": 0.5813,
      "step": 16852
    },
    {
      "epoch": 0.5177095812981907,
      "grad_norm": 0.33147913217544556,
      "learning_rate": 1.689798088224112e-05,
      "loss": 0.5502,
      "step": 16853
    },
    {
      "epoch": 0.5177403004331398,
      "grad_norm": 0.32355964183807373,
      "learning_rate": 1.6897630980527357e-05,
      "loss": 0.4747,
      "step": 16854
    },
    {
      "epoch": 0.5177710195680889,
      "grad_norm": 0.36041638255119324,
      "learning_rate": 1.6897281062703697e-05,
      "loss": 0.5974,
      "step": 16855
    },
    {
      "epoch": 0.5178017387030381,
      "grad_norm": 0.3622611165046692,
      "learning_rate": 1.6896931128770955e-05,
      "loss": 0.523,
      "step": 16856
    },
    {
      "epoch": 0.5178324578379873,
      "grad_norm": 0.5533674359321594,
      "learning_rate": 1.6896581178729947e-05,
      "loss": 0.5166,
      "step": 16857
    },
    {
      "epoch": 0.5178631769729365,
      "grad_norm": 0.3452061414718628,
      "learning_rate": 1.689623121258149e-05,
      "loss": 0.5574,
      "step": 16858
    },
    {
      "epoch": 0.5178938961078856,
      "grad_norm": 0.3490562438964844,
      "learning_rate": 1.689588123032641e-05,
      "loss": 0.5631,
      "step": 16859
    },
    {
      "epoch": 0.5179246152428347,
      "grad_norm": 0.36015602946281433,
      "learning_rate": 1.6895531231965508e-05,
      "loss": 0.6026,
      "step": 16860
    },
    {
      "epoch": 0.517955334377784,
      "grad_norm": 0.35246896743774414,
      "learning_rate": 1.6895181217499618e-05,
      "loss": 0.5834,
      "step": 16861
    },
    {
      "epoch": 0.5179860535127331,
      "grad_norm": 0.4592823088169098,
      "learning_rate": 1.689483118692955e-05,
      "loss": 0.548,
      "step": 16862
    },
    {
      "epoch": 0.5180167726476822,
      "grad_norm": 0.3734976649284363,
      "learning_rate": 1.6894481140256124e-05,
      "loss": 0.5941,
      "step": 16863
    },
    {
      "epoch": 0.5180474917826314,
      "grad_norm": 0.3542463481426239,
      "learning_rate": 1.6894131077480153e-05,
      "loss": 0.5732,
      "step": 16864
    },
    {
      "epoch": 0.5180782109175806,
      "grad_norm": 0.4083467423915863,
      "learning_rate": 1.6893780998602455e-05,
      "loss": 0.5305,
      "step": 16865
    },
    {
      "epoch": 0.5181089300525297,
      "grad_norm": 0.37347739934921265,
      "learning_rate": 1.6893430903623854e-05,
      "loss": 0.5556,
      "step": 16866
    },
    {
      "epoch": 0.5181396491874789,
      "grad_norm": 0.3479328155517578,
      "learning_rate": 1.6893080792545162e-05,
      "loss": 0.5089,
      "step": 16867
    },
    {
      "epoch": 0.518170368322428,
      "grad_norm": 0.3486272394657135,
      "learning_rate": 1.68927306653672e-05,
      "loss": 0.5815,
      "step": 16868
    },
    {
      "epoch": 0.5182010874573773,
      "grad_norm": 0.3589964807033539,
      "learning_rate": 1.6892380522090783e-05,
      "loss": 0.5839,
      "step": 16869
    },
    {
      "epoch": 0.5182318065923264,
      "grad_norm": 0.34772592782974243,
      "learning_rate": 1.689203036271673e-05,
      "loss": 0.5376,
      "step": 16870
    },
    {
      "epoch": 0.5182625257272755,
      "grad_norm": 0.39980581402778625,
      "learning_rate": 1.689168018724586e-05,
      "loss": 0.6183,
      "step": 16871
    },
    {
      "epoch": 0.5182932448622247,
      "grad_norm": 0.3472137749195099,
      "learning_rate": 1.6891329995678988e-05,
      "loss": 0.5594,
      "step": 16872
    },
    {
      "epoch": 0.5183239639971738,
      "grad_norm": 0.3448159992694855,
      "learning_rate": 1.6890979788016934e-05,
      "loss": 0.5356,
      "step": 16873
    },
    {
      "epoch": 0.518354683132123,
      "grad_norm": 0.34003347158432007,
      "learning_rate": 1.689062956426052e-05,
      "loss": 0.5005,
      "step": 16874
    },
    {
      "epoch": 0.5183854022670722,
      "grad_norm": 0.3658064305782318,
      "learning_rate": 1.689027932441055e-05,
      "loss": 0.4495,
      "step": 16875
    },
    {
      "epoch": 0.5184161214020213,
      "grad_norm": 0.35784146189689636,
      "learning_rate": 1.6889929068467857e-05,
      "loss": 0.5258,
      "step": 16876
    },
    {
      "epoch": 0.5184468405369704,
      "grad_norm": 0.38624462485313416,
      "learning_rate": 1.6889578796433254e-05,
      "loss": 0.5654,
      "step": 16877
    },
    {
      "epoch": 0.5184775596719197,
      "grad_norm": 0.4351441562175751,
      "learning_rate": 1.6889228508307556e-05,
      "loss": 0.5507,
      "step": 16878
    },
    {
      "epoch": 0.5185082788068688,
      "grad_norm": 0.36362960934638977,
      "learning_rate": 1.6888878204091582e-05,
      "loss": 0.6008,
      "step": 16879
    },
    {
      "epoch": 0.5185389979418179,
      "grad_norm": 0.32950130105018616,
      "learning_rate": 1.6888527883786157e-05,
      "loss": 0.5382,
      "step": 16880
    },
    {
      "epoch": 0.5185697170767671,
      "grad_norm": 0.333372563123703,
      "learning_rate": 1.6888177547392094e-05,
      "loss": 0.533,
      "step": 16881
    },
    {
      "epoch": 0.5186004362117163,
      "grad_norm": 0.40802568197250366,
      "learning_rate": 1.6887827194910208e-05,
      "loss": 0.5434,
      "step": 16882
    },
    {
      "epoch": 0.5186311553466655,
      "grad_norm": 0.3635513484477997,
      "learning_rate": 1.688747682634132e-05,
      "loss": 0.5895,
      "step": 16883
    },
    {
      "epoch": 0.5186618744816146,
      "grad_norm": 0.3572397530078888,
      "learning_rate": 1.688712644168625e-05,
      "loss": 0.5948,
      "step": 16884
    },
    {
      "epoch": 0.5186925936165637,
      "grad_norm": 0.32358619570732117,
      "learning_rate": 1.6886776040945817e-05,
      "loss": 0.6186,
      "step": 16885
    },
    {
      "epoch": 0.518723312751513,
      "grad_norm": 0.3245325982570648,
      "learning_rate": 1.6886425624120838e-05,
      "loss": 0.5615,
      "step": 16886
    },
    {
      "epoch": 0.5187540318864621,
      "grad_norm": 0.38820531964302063,
      "learning_rate": 1.6886075191212127e-05,
      "loss": 0.5553,
      "step": 16887
    },
    {
      "epoch": 0.5187847510214112,
      "grad_norm": 0.3819673955440521,
      "learning_rate": 1.688572474222051e-05,
      "loss": 0.5545,
      "step": 16888
    },
    {
      "epoch": 0.5188154701563604,
      "grad_norm": 0.3826281726360321,
      "learning_rate": 1.68853742771468e-05,
      "loss": 0.5542,
      "step": 16889
    },
    {
      "epoch": 0.5188461892913095,
      "grad_norm": 0.3335113525390625,
      "learning_rate": 1.688502379599182e-05,
      "loss": 0.5543,
      "step": 16890
    },
    {
      "epoch": 0.5188769084262587,
      "grad_norm": 0.34980344772338867,
      "learning_rate": 1.6884673298756385e-05,
      "loss": 0.5348,
      "step": 16891
    },
    {
      "epoch": 0.5189076275612079,
      "grad_norm": 0.4170517921447754,
      "learning_rate": 1.6884322785441313e-05,
      "loss": 0.532,
      "step": 16892
    },
    {
      "epoch": 0.518938346696157,
      "grad_norm": 0.33596232533454895,
      "learning_rate": 1.6883972256047424e-05,
      "loss": 0.5464,
      "step": 16893
    },
    {
      "epoch": 0.5189690658311062,
      "grad_norm": 0.3239094018936157,
      "learning_rate": 1.688362171057554e-05,
      "loss": 0.5291,
      "step": 16894
    },
    {
      "epoch": 0.5189997849660554,
      "grad_norm": 0.332608699798584,
      "learning_rate": 1.6883271149026477e-05,
      "loss": 0.6059,
      "step": 16895
    },
    {
      "epoch": 0.5190305041010045,
      "grad_norm": 0.38629743456840515,
      "learning_rate": 1.688292057140105e-05,
      "loss": 0.6373,
      "step": 16896
    },
    {
      "epoch": 0.5190612232359537,
      "grad_norm": 0.3575364053249359,
      "learning_rate": 1.6882569977700084e-05,
      "loss": 0.5755,
      "step": 16897
    },
    {
      "epoch": 0.5190919423709028,
      "grad_norm": 0.366165429353714,
      "learning_rate": 1.6882219367924395e-05,
      "loss": 0.5719,
      "step": 16898
    },
    {
      "epoch": 0.519122661505852,
      "grad_norm": 0.372437983751297,
      "learning_rate": 1.68818687420748e-05,
      "loss": 0.5658,
      "step": 16899
    },
    {
      "epoch": 0.5191533806408012,
      "grad_norm": 0.338128000497818,
      "learning_rate": 1.688151810015212e-05,
      "loss": 0.5593,
      "step": 16900
    },
    {
      "epoch": 0.5191840997757503,
      "grad_norm": 0.34777066111564636,
      "learning_rate": 1.6881167442157175e-05,
      "loss": 0.5448,
      "step": 16901
    },
    {
      "epoch": 0.5192148189106994,
      "grad_norm": 0.3538271486759186,
      "learning_rate": 1.688081676809078e-05,
      "loss": 0.5532,
      "step": 16902
    },
    {
      "epoch": 0.5192455380456487,
      "grad_norm": 0.3656678795814514,
      "learning_rate": 1.6880466077953763e-05,
      "loss": 0.5721,
      "step": 16903
    },
    {
      "epoch": 0.5192762571805978,
      "grad_norm": 0.34716346859931946,
      "learning_rate": 1.6880115371746933e-05,
      "loss": 0.6076,
      "step": 16904
    },
    {
      "epoch": 0.519306976315547,
      "grad_norm": 0.3391806185245514,
      "learning_rate": 1.6879764649471117e-05,
      "loss": 0.4824,
      "step": 16905
    },
    {
      "epoch": 0.5193376954504961,
      "grad_norm": 0.34734049439430237,
      "learning_rate": 1.6879413911127126e-05,
      "loss": 0.5049,
      "step": 16906
    },
    {
      "epoch": 0.5193684145854452,
      "grad_norm": 0.36875206232070923,
      "learning_rate": 1.6879063156715784e-05,
      "loss": 0.5401,
      "step": 16907
    },
    {
      "epoch": 0.5193991337203945,
      "grad_norm": 0.34010687470436096,
      "learning_rate": 1.6878712386237908e-05,
      "loss": 0.545,
      "step": 16908
    },
    {
      "epoch": 0.5194298528553436,
      "grad_norm": 0.33894413709640503,
      "learning_rate": 1.687836159969432e-05,
      "loss": 0.485,
      "step": 16909
    },
    {
      "epoch": 0.5194605719902927,
      "grad_norm": 0.4353002905845642,
      "learning_rate": 1.687801079708584e-05,
      "loss": 0.5587,
      "step": 16910
    },
    {
      "epoch": 0.519491291125242,
      "grad_norm": 0.3429238796234131,
      "learning_rate": 1.6877659978413284e-05,
      "loss": 0.5109,
      "step": 16911
    },
    {
      "epoch": 0.5195220102601911,
      "grad_norm": 0.714683473110199,
      "learning_rate": 1.6877309143677472e-05,
      "loss": 0.5588,
      "step": 16912
    },
    {
      "epoch": 0.5195527293951402,
      "grad_norm": 0.37196892499923706,
      "learning_rate": 1.6876958292879226e-05,
      "loss": 0.6097,
      "step": 16913
    },
    {
      "epoch": 0.5195834485300894,
      "grad_norm": 0.3704656958580017,
      "learning_rate": 1.6876607426019364e-05,
      "loss": 0.537,
      "step": 16914
    },
    {
      "epoch": 0.5196141676650385,
      "grad_norm": 0.36958956718444824,
      "learning_rate": 1.68762565430987e-05,
      "loss": 0.5922,
      "step": 16915
    },
    {
      "epoch": 0.5196448867999877,
      "grad_norm": 0.3997191786766052,
      "learning_rate": 1.6875905644118066e-05,
      "loss": 0.5931,
      "step": 16916
    },
    {
      "epoch": 0.5196756059349369,
      "grad_norm": 0.3780432343482971,
      "learning_rate": 1.687555472907827e-05,
      "loss": 0.5446,
      "step": 16917
    },
    {
      "epoch": 0.519706325069886,
      "grad_norm": 0.4208686053752899,
      "learning_rate": 1.6875203797980136e-05,
      "loss": 0.5318,
      "step": 16918
    },
    {
      "epoch": 0.5197370442048352,
      "grad_norm": 0.3829532563686371,
      "learning_rate": 1.6874852850824482e-05,
      "loss": 0.5402,
      "step": 16919
    },
    {
      "epoch": 0.5197677633397844,
      "grad_norm": 0.3220531642436981,
      "learning_rate": 1.6874501887612133e-05,
      "loss": 0.513,
      "step": 16920
    },
    {
      "epoch": 0.5197984824747335,
      "grad_norm": 0.4278983473777771,
      "learning_rate": 1.68741509083439e-05,
      "loss": 0.6001,
      "step": 16921
    },
    {
      "epoch": 0.5198292016096827,
      "grad_norm": 0.4044554829597473,
      "learning_rate": 1.6873799913020614e-05,
      "loss": 0.6131,
      "step": 16922
    },
    {
      "epoch": 0.5198599207446318,
      "grad_norm": 0.36180683970451355,
      "learning_rate": 1.687344890164308e-05,
      "loss": 0.6583,
      "step": 16923
    },
    {
      "epoch": 0.519890639879581,
      "grad_norm": 0.3557491600513458,
      "learning_rate": 1.6873097874212132e-05,
      "loss": 0.5606,
      "step": 16924
    },
    {
      "epoch": 0.5199213590145302,
      "grad_norm": 0.38648468255996704,
      "learning_rate": 1.6872746830728584e-05,
      "loss": 0.5832,
      "step": 16925
    },
    {
      "epoch": 0.5199520781494793,
      "grad_norm": 0.3683575689792633,
      "learning_rate": 1.6872395771193254e-05,
      "loss": 0.6611,
      "step": 16926
    },
    {
      "epoch": 0.5199827972844284,
      "grad_norm": 0.3857043981552124,
      "learning_rate": 1.687204469560696e-05,
      "loss": 0.6165,
      "step": 16927
    },
    {
      "epoch": 0.5200135164193777,
      "grad_norm": 0.32639026641845703,
      "learning_rate": 1.687169360397053e-05,
      "loss": 0.6023,
      "step": 16928
    },
    {
      "epoch": 0.5200442355543268,
      "grad_norm": 0.3478180766105652,
      "learning_rate": 1.6871342496284783e-05,
      "loss": 0.5539,
      "step": 16929
    },
    {
      "epoch": 0.520074954689276,
      "grad_norm": 0.36171942949295044,
      "learning_rate": 1.6870991372550532e-05,
      "loss": 0.5591,
      "step": 16930
    },
    {
      "epoch": 0.5201056738242251,
      "grad_norm": 0.35941675305366516,
      "learning_rate": 1.68706402327686e-05,
      "loss": 0.5325,
      "step": 16931
    },
    {
      "epoch": 0.5201363929591742,
      "grad_norm": 0.3493078649044037,
      "learning_rate": 1.6870289076939807e-05,
      "loss": 0.5939,
      "step": 16932
    },
    {
      "epoch": 0.5201671120941235,
      "grad_norm": 0.347795695066452,
      "learning_rate": 1.6869937905064977e-05,
      "loss": 0.5756,
      "step": 16933
    },
    {
      "epoch": 0.5201978312290726,
      "grad_norm": 0.34277352690696716,
      "learning_rate": 1.6869586717144924e-05,
      "loss": 0.5312,
      "step": 16934
    },
    {
      "epoch": 0.5202285503640217,
      "grad_norm": 0.4316260814666748,
      "learning_rate": 1.6869235513180475e-05,
      "loss": 0.5882,
      "step": 16935
    },
    {
      "epoch": 0.5202592694989709,
      "grad_norm": 0.3243025541305542,
      "learning_rate": 1.686888429317244e-05,
      "loss": 0.558,
      "step": 16936
    },
    {
      "epoch": 0.5202899886339201,
      "grad_norm": 0.3828491270542145,
      "learning_rate": 1.6868533057121652e-05,
      "loss": 0.6157,
      "step": 16937
    },
    {
      "epoch": 0.5203207077688692,
      "grad_norm": 0.3846838176250458,
      "learning_rate": 1.6868181805028926e-05,
      "loss": 0.5072,
      "step": 16938
    },
    {
      "epoch": 0.5203514269038184,
      "grad_norm": 0.34277665615081787,
      "learning_rate": 1.686783053689508e-05,
      "loss": 0.6285,
      "step": 16939
    },
    {
      "epoch": 0.5203821460387675,
      "grad_norm": 0.36519262194633484,
      "learning_rate": 1.6867479252720936e-05,
      "loss": 0.5326,
      "step": 16940
    },
    {
      "epoch": 0.5204128651737167,
      "grad_norm": 0.3713577389717102,
      "learning_rate": 1.6867127952507316e-05,
      "loss": 0.5544,
      "step": 16941
    },
    {
      "epoch": 0.5204435843086659,
      "grad_norm": 0.33492225408554077,
      "learning_rate": 1.686677663625504e-05,
      "loss": 0.5611,
      "step": 16942
    },
    {
      "epoch": 0.520474303443615,
      "grad_norm": 0.3499731123447418,
      "learning_rate": 1.6866425303964922e-05,
      "loss": 0.5617,
      "step": 16943
    },
    {
      "epoch": 0.5205050225785642,
      "grad_norm": 0.3846389949321747,
      "learning_rate": 1.686607395563779e-05,
      "loss": 0.5702,
      "step": 16944
    },
    {
      "epoch": 0.5205357417135134,
      "grad_norm": 0.3085474371910095,
      "learning_rate": 1.6865722591274466e-05,
      "loss": 0.4783,
      "step": 16945
    },
    {
      "epoch": 0.5205664608484625,
      "grad_norm": 0.3684687614440918,
      "learning_rate": 1.6865371210875764e-05,
      "loss": 0.5818,
      "step": 16946
    },
    {
      "epoch": 0.5205971799834117,
      "grad_norm": 0.3433871865272522,
      "learning_rate": 1.686501981444251e-05,
      "loss": 0.5765,
      "step": 16947
    },
    {
      "epoch": 0.5206278991183608,
      "grad_norm": 0.40262746810913086,
      "learning_rate": 1.6864668401975525e-05,
      "loss": 0.5775,
      "step": 16948
    },
    {
      "epoch": 0.52065861825331,
      "grad_norm": 0.3261570334434509,
      "learning_rate": 1.6864316973475624e-05,
      "loss": 0.551,
      "step": 16949
    },
    {
      "epoch": 0.5206893373882592,
      "grad_norm": 0.35952991247177124,
      "learning_rate": 1.6863965528943633e-05,
      "loss": 0.5682,
      "step": 16950
    },
    {
      "epoch": 0.5207200565232083,
      "grad_norm": 0.36623886227607727,
      "learning_rate": 1.686361406838037e-05,
      "loss": 0.6039,
      "step": 16951
    },
    {
      "epoch": 0.5207507756581574,
      "grad_norm": 0.42833971977233887,
      "learning_rate": 1.686326259178666e-05,
      "loss": 0.4913,
      "step": 16952
    },
    {
      "epoch": 0.5207814947931066,
      "grad_norm": 0.3281848132610321,
      "learning_rate": 1.6862911099163317e-05,
      "loss": 0.5293,
      "step": 16953
    },
    {
      "epoch": 0.5208122139280558,
      "grad_norm": 0.3349824845790863,
      "learning_rate": 1.686255959051117e-05,
      "loss": 0.5572,
      "step": 16954
    },
    {
      "epoch": 0.520842933063005,
      "grad_norm": 0.35325729846954346,
      "learning_rate": 1.686220806583103e-05,
      "loss": 0.5125,
      "step": 16955
    },
    {
      "epoch": 0.5208736521979541,
      "grad_norm": 0.33830541372299194,
      "learning_rate": 1.6861856525123725e-05,
      "loss": 0.5141,
      "step": 16956
    },
    {
      "epoch": 0.5209043713329032,
      "grad_norm": 0.42788803577423096,
      "learning_rate": 1.686150496839008e-05,
      "loss": 0.6117,
      "step": 16957
    },
    {
      "epoch": 0.5209350904678525,
      "grad_norm": 0.31900009512901306,
      "learning_rate": 1.6861153395630907e-05,
      "loss": 0.5688,
      "step": 16958
    },
    {
      "epoch": 0.5209658096028016,
      "grad_norm": 0.38910242915153503,
      "learning_rate": 1.686080180684703e-05,
      "loss": 0.5301,
      "step": 16959
    },
    {
      "epoch": 0.5209965287377507,
      "grad_norm": 0.3732011914253235,
      "learning_rate": 1.6860450202039275e-05,
      "loss": 0.5644,
      "step": 16960
    },
    {
      "epoch": 0.5210272478726999,
      "grad_norm": 0.36476150155067444,
      "learning_rate": 1.6860098581208454e-05,
      "loss": 0.5467,
      "step": 16961
    },
    {
      "epoch": 0.5210579670076491,
      "grad_norm": 0.40151071548461914,
      "learning_rate": 1.68597469443554e-05,
      "loss": 0.6213,
      "step": 16962
    },
    {
      "epoch": 0.5210886861425982,
      "grad_norm": 0.35775765776634216,
      "learning_rate": 1.6859395291480923e-05,
      "loss": 0.5589,
      "step": 16963
    },
    {
      "epoch": 0.5211194052775474,
      "grad_norm": 0.3478066623210907,
      "learning_rate": 1.6859043622585852e-05,
      "loss": 0.5746,
      "step": 16964
    },
    {
      "epoch": 0.5211501244124965,
      "grad_norm": 0.3766174018383026,
      "learning_rate": 1.6858691937671006e-05,
      "loss": 0.4787,
      "step": 16965
    },
    {
      "epoch": 0.5211808435474456,
      "grad_norm": 0.3188716173171997,
      "learning_rate": 1.68583402367372e-05,
      "loss": 0.5876,
      "step": 16966
    },
    {
      "epoch": 0.5212115626823949,
      "grad_norm": 0.37398219108581543,
      "learning_rate": 1.6857988519785272e-05,
      "loss": 0.6133,
      "step": 16967
    },
    {
      "epoch": 0.521242281817344,
      "grad_norm": 0.3600437641143799,
      "learning_rate": 1.6857636786816028e-05,
      "loss": 0.5337,
      "step": 16968
    },
    {
      "epoch": 0.5212730009522932,
      "grad_norm": 0.36625558137893677,
      "learning_rate": 1.685728503783029e-05,
      "loss": 0.6704,
      "step": 16969
    },
    {
      "epoch": 0.5213037200872424,
      "grad_norm": 0.3559701144695282,
      "learning_rate": 1.6856933272828887e-05,
      "loss": 0.5653,
      "step": 16970
    },
    {
      "epoch": 0.5213344392221915,
      "grad_norm": 0.3403119444847107,
      "learning_rate": 1.685658149181264e-05,
      "loss": 0.5825,
      "step": 16971
    },
    {
      "epoch": 0.5213651583571407,
      "grad_norm": 0.3746093809604645,
      "learning_rate": 1.6856229694782365e-05,
      "loss": 0.6002,
      "step": 16972
    },
    {
      "epoch": 0.5213958774920898,
      "grad_norm": 0.3462832570075989,
      "learning_rate": 1.6855877881738885e-05,
      "loss": 0.6065,
      "step": 16973
    },
    {
      "epoch": 0.5214265966270389,
      "grad_norm": 0.3605060577392578,
      "learning_rate": 1.6855526052683026e-05,
      "loss": 0.5834,
      "step": 16974
    },
    {
      "epoch": 0.5214573157619882,
      "grad_norm": 0.3825274109840393,
      "learning_rate": 1.685517420761561e-05,
      "loss": 0.5964,
      "step": 16975
    },
    {
      "epoch": 0.5214880348969373,
      "grad_norm": 0.3755330741405487,
      "learning_rate": 1.6854822346537452e-05,
      "loss": 0.6465,
      "step": 16976
    },
    {
      "epoch": 0.5215187540318864,
      "grad_norm": 0.34237492084503174,
      "learning_rate": 1.6854470469449377e-05,
      "loss": 0.6334,
      "step": 16977
    },
    {
      "epoch": 0.5215494731668356,
      "grad_norm": 0.35686227679252625,
      "learning_rate": 1.685411857635221e-05,
      "loss": 0.6071,
      "step": 16978
    },
    {
      "epoch": 0.5215801923017848,
      "grad_norm": 0.3531419038772583,
      "learning_rate": 1.685376666724677e-05,
      "loss": 0.5165,
      "step": 16979
    },
    {
      "epoch": 0.521610911436734,
      "grad_norm": 0.3582116961479187,
      "learning_rate": 1.685341474213388e-05,
      "loss": 0.5823,
      "step": 16980
    },
    {
      "epoch": 0.5216416305716831,
      "grad_norm": 0.34741565585136414,
      "learning_rate": 1.6853062801014358e-05,
      "loss": 0.499,
      "step": 16981
    },
    {
      "epoch": 0.5216723497066322,
      "grad_norm": 0.42128199338912964,
      "learning_rate": 1.685271084388903e-05,
      "loss": 0.6327,
      "step": 16982
    },
    {
      "epoch": 0.5217030688415815,
      "grad_norm": 0.44916656613349915,
      "learning_rate": 1.685235887075872e-05,
      "loss": 0.5346,
      "step": 16983
    },
    {
      "epoch": 0.5217337879765306,
      "grad_norm": 0.3657461106777191,
      "learning_rate": 1.6852006881624245e-05,
      "loss": 0.5707,
      "step": 16984
    },
    {
      "epoch": 0.5217645071114797,
      "grad_norm": 0.38636189699172974,
      "learning_rate": 1.685165487648643e-05,
      "loss": 0.5808,
      "step": 16985
    },
    {
      "epoch": 0.5217952262464289,
      "grad_norm": 0.3958852291107178,
      "learning_rate": 1.68513028553461e-05,
      "loss": 0.6171,
      "step": 16986
    },
    {
      "epoch": 0.521825945381378,
      "grad_norm": 0.3313107490539551,
      "learning_rate": 1.6850950818204067e-05,
      "loss": 0.5803,
      "step": 16987
    },
    {
      "epoch": 0.5218566645163272,
      "grad_norm": 0.42999449372291565,
      "learning_rate": 1.6850598765061167e-05,
      "loss": 0.5738,
      "step": 16988
    },
    {
      "epoch": 0.5218873836512764,
      "grad_norm": 0.3561694920063019,
      "learning_rate": 1.685024669591821e-05,
      "loss": 0.5463,
      "step": 16989
    },
    {
      "epoch": 0.5219181027862255,
      "grad_norm": 0.3587033450603485,
      "learning_rate": 1.6849894610776024e-05,
      "loss": 0.599,
      "step": 16990
    },
    {
      "epoch": 0.5219488219211748,
      "grad_norm": 0.37614309787750244,
      "learning_rate": 1.684954250963543e-05,
      "loss": 0.6714,
      "step": 16991
    },
    {
      "epoch": 0.5219795410561239,
      "grad_norm": 0.34565868973731995,
      "learning_rate": 1.6849190392497254e-05,
      "loss": 0.5676,
      "step": 16992
    },
    {
      "epoch": 0.522010260191073,
      "grad_norm": 0.35557326674461365,
      "learning_rate": 1.6848838259362313e-05,
      "loss": 0.537,
      "step": 16993
    },
    {
      "epoch": 0.5220409793260222,
      "grad_norm": 0.40558934211730957,
      "learning_rate": 1.6848486110231436e-05,
      "loss": 0.5685,
      "step": 16994
    },
    {
      "epoch": 0.5220716984609713,
      "grad_norm": 0.6206150650978088,
      "learning_rate": 1.6848133945105436e-05,
      "loss": 0.5792,
      "step": 16995
    },
    {
      "epoch": 0.5221024175959205,
      "grad_norm": 0.316119909286499,
      "learning_rate": 1.6847781763985144e-05,
      "loss": 0.545,
      "step": 16996
    },
    {
      "epoch": 0.5221331367308697,
      "grad_norm": 0.39058175683021545,
      "learning_rate": 1.6847429566871376e-05,
      "loss": 0.6173,
      "step": 16997
    },
    {
      "epoch": 0.5221638558658188,
      "grad_norm": 0.3297182321548462,
      "learning_rate": 1.684707735376496e-05,
      "loss": 0.5269,
      "step": 16998
    },
    {
      "epoch": 0.5221945750007679,
      "grad_norm": 0.3731611669063568,
      "learning_rate": 1.684672512466672e-05,
      "loss": 0.6077,
      "step": 16999
    },
    {
      "epoch": 0.5222252941357172,
      "grad_norm": 0.34547197818756104,
      "learning_rate": 1.6846372879577473e-05,
      "loss": 0.5396,
      "step": 17000
    },
    {
      "epoch": 0.5222560132706663,
      "grad_norm": 0.34885069727897644,
      "learning_rate": 1.6846020618498046e-05,
      "loss": 0.6104,
      "step": 17001
    },
    {
      "epoch": 0.5222867324056154,
      "grad_norm": 0.3566843271255493,
      "learning_rate": 1.6845668341429257e-05,
      "loss": 0.5738,
      "step": 17002
    },
    {
      "epoch": 0.5223174515405646,
      "grad_norm": 0.36021339893341064,
      "learning_rate": 1.684531604837193e-05,
      "loss": 0.5716,
      "step": 17003
    },
    {
      "epoch": 0.5223481706755138,
      "grad_norm": 0.3277444839477539,
      "learning_rate": 1.684496373932689e-05,
      "loss": 0.5328,
      "step": 17004
    },
    {
      "epoch": 0.522378889810463,
      "grad_norm": 0.3278258442878723,
      "learning_rate": 1.6844611414294963e-05,
      "loss": 0.5896,
      "step": 17005
    },
    {
      "epoch": 0.5224096089454121,
      "grad_norm": 0.331222265958786,
      "learning_rate": 1.6844259073276964e-05,
      "loss": 0.4809,
      "step": 17006
    },
    {
      "epoch": 0.5224403280803612,
      "grad_norm": 0.3197587728500366,
      "learning_rate": 1.6843906716273723e-05,
      "loss": 0.5716,
      "step": 17007
    },
    {
      "epoch": 0.5224710472153105,
      "grad_norm": 0.3345125615596771,
      "learning_rate": 1.684355434328606e-05,
      "loss": 0.5017,
      "step": 17008
    },
    {
      "epoch": 0.5225017663502596,
      "grad_norm": 0.43626952171325684,
      "learning_rate": 1.6843201954314794e-05,
      "loss": 0.5622,
      "step": 17009
    },
    {
      "epoch": 0.5225324854852087,
      "grad_norm": 0.34691140055656433,
      "learning_rate": 1.6842849549360753e-05,
      "loss": 0.5633,
      "step": 17010
    },
    {
      "epoch": 0.5225632046201579,
      "grad_norm": 0.3570665717124939,
      "learning_rate": 1.6842497128424762e-05,
      "loss": 0.5644,
      "step": 17011
    },
    {
      "epoch": 0.522593923755107,
      "grad_norm": 0.33646267652511597,
      "learning_rate": 1.6842144691507635e-05,
      "loss": 0.5615,
      "step": 17012
    },
    {
      "epoch": 0.5226246428900562,
      "grad_norm": 0.424877792596817,
      "learning_rate": 1.6841792238610208e-05,
      "loss": 0.5486,
      "step": 17013
    },
    {
      "epoch": 0.5226553620250054,
      "grad_norm": 0.33947062492370605,
      "learning_rate": 1.6841439769733294e-05,
      "loss": 0.4839,
      "step": 17014
    },
    {
      "epoch": 0.5226860811599545,
      "grad_norm": 0.3338967561721802,
      "learning_rate": 1.684108728487772e-05,
      "loss": 0.5302,
      "step": 17015
    },
    {
      "epoch": 0.5227168002949037,
      "grad_norm": 0.3788968026638031,
      "learning_rate": 1.684073478404431e-05,
      "loss": 0.4468,
      "step": 17016
    },
    {
      "epoch": 0.5227475194298529,
      "grad_norm": 0.35224372148513794,
      "learning_rate": 1.6840382267233887e-05,
      "loss": 0.5635,
      "step": 17017
    },
    {
      "epoch": 0.522778238564802,
      "grad_norm": 0.32737284898757935,
      "learning_rate": 1.6840029734447273e-05,
      "loss": 0.5019,
      "step": 17018
    },
    {
      "epoch": 0.5228089576997512,
      "grad_norm": 0.3843417465686798,
      "learning_rate": 1.6839677185685287e-05,
      "loss": 0.5262,
      "step": 17019
    },
    {
      "epoch": 0.5228396768347003,
      "grad_norm": 0.4036490321159363,
      "learning_rate": 1.6839324620948763e-05,
      "loss": 0.6196,
      "step": 17020
    },
    {
      "epoch": 0.5228703959696495,
      "grad_norm": 0.3500337600708008,
      "learning_rate": 1.6838972040238516e-05,
      "loss": 0.4893,
      "step": 17021
    },
    {
      "epoch": 0.5229011151045987,
      "grad_norm": 0.33354461193084717,
      "learning_rate": 1.6838619443555373e-05,
      "loss": 0.507,
      "step": 17022
    },
    {
      "epoch": 0.5229318342395478,
      "grad_norm": 0.3402877151966095,
      "learning_rate": 1.6838266830900156e-05,
      "loss": 0.5305,
      "step": 17023
    },
    {
      "epoch": 0.5229625533744969,
      "grad_norm": 0.3978286385536194,
      "learning_rate": 1.6837914202273692e-05,
      "loss": 0.5574,
      "step": 17024
    },
    {
      "epoch": 0.5229932725094462,
      "grad_norm": 0.37840959429740906,
      "learning_rate": 1.68375615576768e-05,
      "loss": 0.5919,
      "step": 17025
    },
    {
      "epoch": 0.5230239916443953,
      "grad_norm": 0.33036983013153076,
      "learning_rate": 1.6837208897110305e-05,
      "loss": 0.563,
      "step": 17026
    },
    {
      "epoch": 0.5230547107793444,
      "grad_norm": 0.4242558181285858,
      "learning_rate": 1.683685622057503e-05,
      "loss": 0.5913,
      "step": 17027
    },
    {
      "epoch": 0.5230854299142936,
      "grad_norm": 0.34995847940444946,
      "learning_rate": 1.68365035280718e-05,
      "loss": 0.5389,
      "step": 17028
    },
    {
      "epoch": 0.5231161490492428,
      "grad_norm": 0.36726057529449463,
      "learning_rate": 1.683615081960144e-05,
      "loss": 0.68,
      "step": 17029
    },
    {
      "epoch": 0.523146868184192,
      "grad_norm": 0.3720272481441498,
      "learning_rate": 1.6835798095164772e-05,
      "loss": 0.6107,
      "step": 17030
    },
    {
      "epoch": 0.5231775873191411,
      "grad_norm": 0.3911034166812897,
      "learning_rate": 1.683544535476262e-05,
      "loss": 0.6119,
      "step": 17031
    },
    {
      "epoch": 0.5232083064540902,
      "grad_norm": 0.34101951122283936,
      "learning_rate": 1.6835092598395806e-05,
      "loss": 0.5264,
      "step": 17032
    },
    {
      "epoch": 0.5232390255890395,
      "grad_norm": 0.3836565315723419,
      "learning_rate": 1.683473982606516e-05,
      "loss": 0.6001,
      "step": 17033
    },
    {
      "epoch": 0.5232697447239886,
      "grad_norm": 0.33784154057502747,
      "learning_rate": 1.6834387037771497e-05,
      "loss": 0.5281,
      "step": 17034
    },
    {
      "epoch": 0.5233004638589377,
      "grad_norm": 0.4979386627674103,
      "learning_rate": 1.6834034233515652e-05,
      "loss": 0.5818,
      "step": 17035
    },
    {
      "epoch": 0.5233311829938869,
      "grad_norm": 0.3309781849384308,
      "learning_rate": 1.6833681413298436e-05,
      "loss": 0.5717,
      "step": 17036
    },
    {
      "epoch": 0.523361902128836,
      "grad_norm": 0.4058310091495514,
      "learning_rate": 1.6833328577120684e-05,
      "loss": 0.5795,
      "step": 17037
    },
    {
      "epoch": 0.5233926212637852,
      "grad_norm": 0.36721697449684143,
      "learning_rate": 1.6832975724983216e-05,
      "loss": 0.6181,
      "step": 17038
    },
    {
      "epoch": 0.5234233403987344,
      "grad_norm": 0.3339841365814209,
      "learning_rate": 1.6832622856886857e-05,
      "loss": 0.4881,
      "step": 17039
    },
    {
      "epoch": 0.5234540595336835,
      "grad_norm": 0.3896107077598572,
      "learning_rate": 1.6832269972832427e-05,
      "loss": 0.6401,
      "step": 17040
    },
    {
      "epoch": 0.5234847786686327,
      "grad_norm": 0.381781667470932,
      "learning_rate": 1.6831917072820754e-05,
      "loss": 0.5913,
      "step": 17041
    },
    {
      "epoch": 0.5235154978035819,
      "grad_norm": 0.3288511037826538,
      "learning_rate": 1.683156415685266e-05,
      "loss": 0.5902,
      "step": 17042
    },
    {
      "epoch": 0.523546216938531,
      "grad_norm": 0.3789781630039215,
      "learning_rate": 1.6831211224928975e-05,
      "loss": 0.5117,
      "step": 17043
    },
    {
      "epoch": 0.5235769360734802,
      "grad_norm": 0.3657667338848114,
      "learning_rate": 1.6830858277050515e-05,
      "loss": 0.542,
      "step": 17044
    },
    {
      "epoch": 0.5236076552084293,
      "grad_norm": 0.34633079171180725,
      "learning_rate": 1.683050531321811e-05,
      "loss": 0.5978,
      "step": 17045
    },
    {
      "epoch": 0.5236383743433785,
      "grad_norm": 0.3415851294994354,
      "learning_rate": 1.6830152333432584e-05,
      "loss": 0.6379,
      "step": 17046
    },
    {
      "epoch": 0.5236690934783277,
      "grad_norm": 0.3510061204433441,
      "learning_rate": 1.682979933769476e-05,
      "loss": 0.5593,
      "step": 17047
    },
    {
      "epoch": 0.5236998126132768,
      "grad_norm": 0.3762488067150116,
      "learning_rate": 1.6829446326005462e-05,
      "loss": 0.5288,
      "step": 17048
    },
    {
      "epoch": 0.5237305317482259,
      "grad_norm": 0.35678631067276,
      "learning_rate": 1.6829093298365515e-05,
      "loss": 0.6431,
      "step": 17049
    },
    {
      "epoch": 0.5237612508831752,
      "grad_norm": 0.34033167362213135,
      "learning_rate": 1.6828740254775743e-05,
      "loss": 0.5396,
      "step": 17050
    },
    {
      "epoch": 0.5237919700181243,
      "grad_norm": 0.35504046082496643,
      "learning_rate": 1.6828387195236972e-05,
      "loss": 0.5073,
      "step": 17051
    },
    {
      "epoch": 0.5238226891530734,
      "grad_norm": 0.40559282898902893,
      "learning_rate": 1.6828034119750027e-05,
      "loss": 0.5516,
      "step": 17052
    },
    {
      "epoch": 0.5238534082880226,
      "grad_norm": 0.33925294876098633,
      "learning_rate": 1.6827681028315728e-05,
      "loss": 0.5396,
      "step": 17053
    },
    {
      "epoch": 0.5238841274229717,
      "grad_norm": 0.39518648386001587,
      "learning_rate": 1.6827327920934906e-05,
      "loss": 0.5252,
      "step": 17054
    },
    {
      "epoch": 0.523914846557921,
      "grad_norm": 0.8231386542320251,
      "learning_rate": 1.682697479760838e-05,
      "loss": 0.4944,
      "step": 17055
    },
    {
      "epoch": 0.5239455656928701,
      "grad_norm": 0.3694082498550415,
      "learning_rate": 1.682662165833698e-05,
      "loss": 0.64,
      "step": 17056
    },
    {
      "epoch": 0.5239762848278192,
      "grad_norm": 0.33403003215789795,
      "learning_rate": 1.682626850312153e-05,
      "loss": 0.5866,
      "step": 17057
    },
    {
      "epoch": 0.5240070039627684,
      "grad_norm": 0.34937113523483276,
      "learning_rate": 1.682591533196285e-05,
      "loss": 0.5931,
      "step": 17058
    },
    {
      "epoch": 0.5240377230977176,
      "grad_norm": 0.34221670031547546,
      "learning_rate": 1.682556214486177e-05,
      "loss": 0.5528,
      "step": 17059
    },
    {
      "epoch": 0.5240684422326667,
      "grad_norm": 0.41811633110046387,
      "learning_rate": 1.682520894181911e-05,
      "loss": 0.6055,
      "step": 17060
    },
    {
      "epoch": 0.5240991613676159,
      "grad_norm": 0.3672974109649658,
      "learning_rate": 1.6824855722835704e-05,
      "loss": 0.5434,
      "step": 17061
    },
    {
      "epoch": 0.524129880502565,
      "grad_norm": 0.3748646676540375,
      "learning_rate": 1.6824502487912364e-05,
      "loss": 0.5889,
      "step": 17062
    },
    {
      "epoch": 0.5241605996375142,
      "grad_norm": 0.3802797794342041,
      "learning_rate": 1.6824149237049927e-05,
      "loss": 0.5637,
      "step": 17063
    },
    {
      "epoch": 0.5241913187724634,
      "grad_norm": 0.3865649998188019,
      "learning_rate": 1.6823795970249207e-05,
      "loss": 0.6136,
      "step": 17064
    },
    {
      "epoch": 0.5242220379074125,
      "grad_norm": 0.35641229152679443,
      "learning_rate": 1.682344268751104e-05,
      "loss": 0.5515,
      "step": 17065
    },
    {
      "epoch": 0.5242527570423617,
      "grad_norm": 0.3443400263786316,
      "learning_rate": 1.6823089388836246e-05,
      "loss": 0.549,
      "step": 17066
    },
    {
      "epoch": 0.5242834761773109,
      "grad_norm": 0.35518044233322144,
      "learning_rate": 1.682273607422565e-05,
      "loss": 0.5435,
      "step": 17067
    },
    {
      "epoch": 0.52431419531226,
      "grad_norm": 0.38310033082962036,
      "learning_rate": 1.6822382743680075e-05,
      "loss": 0.6578,
      "step": 17068
    },
    {
      "epoch": 0.5243449144472092,
      "grad_norm": 0.3200690746307373,
      "learning_rate": 1.6822029397200348e-05,
      "loss": 0.5587,
      "step": 17069
    },
    {
      "epoch": 0.5243756335821583,
      "grad_norm": 0.36321598291397095,
      "learning_rate": 1.6821676034787294e-05,
      "loss": 0.487,
      "step": 17070
    },
    {
      "epoch": 0.5244063527171074,
      "grad_norm": 0.3308059871196747,
      "learning_rate": 1.6821322656441747e-05,
      "loss": 0.5262,
      "step": 17071
    },
    {
      "epoch": 0.5244370718520567,
      "grad_norm": 0.6699589490890503,
      "learning_rate": 1.6820969262164516e-05,
      "loss": 0.5159,
      "step": 17072
    },
    {
      "epoch": 0.5244677909870058,
      "grad_norm": 0.32767120003700256,
      "learning_rate": 1.6820615851956442e-05,
      "loss": 0.4905,
      "step": 17073
    },
    {
      "epoch": 0.5244985101219549,
      "grad_norm": 0.3290756046772003,
      "learning_rate": 1.6820262425818338e-05,
      "loss": 0.4843,
      "step": 17074
    },
    {
      "epoch": 0.5245292292569042,
      "grad_norm": 0.3248766362667084,
      "learning_rate": 1.6819908983751038e-05,
      "loss": 0.5175,
      "step": 17075
    },
    {
      "epoch": 0.5245599483918533,
      "grad_norm": 0.39445191621780396,
      "learning_rate": 1.681955552575536e-05,
      "loss": 0.7507,
      "step": 17076
    },
    {
      "epoch": 0.5245906675268024,
      "grad_norm": 0.3601611256599426,
      "learning_rate": 1.6819202051832137e-05,
      "loss": 0.5639,
      "step": 17077
    },
    {
      "epoch": 0.5246213866617516,
      "grad_norm": 0.35583359003067017,
      "learning_rate": 1.6818848561982193e-05,
      "loss": 0.6172,
      "step": 17078
    },
    {
      "epoch": 0.5246521057967007,
      "grad_norm": 0.33599722385406494,
      "learning_rate": 1.681849505620635e-05,
      "loss": 0.4503,
      "step": 17079
    },
    {
      "epoch": 0.52468282493165,
      "grad_norm": 0.42901018261909485,
      "learning_rate": 1.6818141534505433e-05,
      "loss": 0.6479,
      "step": 17080
    },
    {
      "epoch": 0.5247135440665991,
      "grad_norm": 0.3691801130771637,
      "learning_rate": 1.6817787996880273e-05,
      "loss": 0.5486,
      "step": 17081
    },
    {
      "epoch": 0.5247442632015482,
      "grad_norm": 0.35644280910491943,
      "learning_rate": 1.6817434443331694e-05,
      "loss": 0.5424,
      "step": 17082
    },
    {
      "epoch": 0.5247749823364974,
      "grad_norm": 0.3439689874649048,
      "learning_rate": 1.6817080873860518e-05,
      "loss": 0.5422,
      "step": 17083
    },
    {
      "epoch": 0.5248057014714466,
      "grad_norm": 0.35254383087158203,
      "learning_rate": 1.6816727288467575e-05,
      "loss": 0.5866,
      "step": 17084
    },
    {
      "epoch": 0.5248364206063957,
      "grad_norm": 0.329396516084671,
      "learning_rate": 1.681637368715369e-05,
      "loss": 0.5482,
      "step": 17085
    },
    {
      "epoch": 0.5248671397413449,
      "grad_norm": 0.37809279561042786,
      "learning_rate": 1.6816020069919687e-05,
      "loss": 0.5528,
      "step": 17086
    },
    {
      "epoch": 0.524897858876294,
      "grad_norm": 0.33065804839134216,
      "learning_rate": 1.6815666436766392e-05,
      "loss": 0.5902,
      "step": 17087
    },
    {
      "epoch": 0.5249285780112432,
      "grad_norm": 0.3368861973285675,
      "learning_rate": 1.6815312787694634e-05,
      "loss": 0.4963,
      "step": 17088
    },
    {
      "epoch": 0.5249592971461924,
      "grad_norm": 0.3674563467502594,
      "learning_rate": 1.6814959122705237e-05,
      "loss": 0.6464,
      "step": 17089
    },
    {
      "epoch": 0.5249900162811415,
      "grad_norm": 0.7560603022575378,
      "learning_rate": 1.681460544179903e-05,
      "loss": 0.592,
      "step": 17090
    },
    {
      "epoch": 0.5250207354160907,
      "grad_norm": 0.3467411398887634,
      "learning_rate": 1.681425174497683e-05,
      "loss": 0.572,
      "step": 17091
    },
    {
      "epoch": 0.5250514545510399,
      "grad_norm": 0.3432554006576538,
      "learning_rate": 1.6813898032239473e-05,
      "loss": 0.5942,
      "step": 17092
    },
    {
      "epoch": 0.525082173685989,
      "grad_norm": 0.41013067960739136,
      "learning_rate": 1.681354430358778e-05,
      "loss": 0.5462,
      "step": 17093
    },
    {
      "epoch": 0.5251128928209382,
      "grad_norm": 0.3512915372848511,
      "learning_rate": 1.6813190559022578e-05,
      "loss": 0.5992,
      "step": 17094
    },
    {
      "epoch": 0.5251436119558873,
      "grad_norm": 0.37173476815223694,
      "learning_rate": 1.6812836798544693e-05,
      "loss": 0.4904,
      "step": 17095
    },
    {
      "epoch": 0.5251743310908364,
      "grad_norm": 0.3629993796348572,
      "learning_rate": 1.6812483022154955e-05,
      "loss": 0.5263,
      "step": 17096
    },
    {
      "epoch": 0.5252050502257857,
      "grad_norm": 0.35085248947143555,
      "learning_rate": 1.6812129229854185e-05,
      "loss": 0.5631,
      "step": 17097
    },
    {
      "epoch": 0.5252357693607348,
      "grad_norm": 0.3560388684272766,
      "learning_rate": 1.681177542164321e-05,
      "loss": 0.5807,
      "step": 17098
    },
    {
      "epoch": 0.5252664884956839,
      "grad_norm": 0.36230018734931946,
      "learning_rate": 1.6811421597522862e-05,
      "loss": 0.5876,
      "step": 17099
    },
    {
      "epoch": 0.5252972076306331,
      "grad_norm": 0.3489912450313568,
      "learning_rate": 1.6811067757493957e-05,
      "loss": 0.5989,
      "step": 17100
    },
    {
      "epoch": 0.5253279267655823,
      "grad_norm": 0.3433593511581421,
      "learning_rate": 1.6810713901557333e-05,
      "loss": 0.5358,
      "step": 17101
    },
    {
      "epoch": 0.5253586459005315,
      "grad_norm": 0.383026659488678,
      "learning_rate": 1.681036002971381e-05,
      "loss": 0.5591,
      "step": 17102
    },
    {
      "epoch": 0.5253893650354806,
      "grad_norm": 0.31588584184646606,
      "learning_rate": 1.6810006141964212e-05,
      "loss": 0.564,
      "step": 17103
    },
    {
      "epoch": 0.5254200841704297,
      "grad_norm": 0.3804260194301605,
      "learning_rate": 1.680965223830937e-05,
      "loss": 0.6288,
      "step": 17104
    },
    {
      "epoch": 0.525450803305379,
      "grad_norm": 0.3919837772846222,
      "learning_rate": 1.6809298318750112e-05,
      "loss": 0.6319,
      "step": 17105
    },
    {
      "epoch": 0.5254815224403281,
      "grad_norm": 0.3651268482208252,
      "learning_rate": 1.6808944383287262e-05,
      "loss": 0.5533,
      "step": 17106
    },
    {
      "epoch": 0.5255122415752772,
      "grad_norm": 0.32521557807922363,
      "learning_rate": 1.680859043192165e-05,
      "loss": 0.653,
      "step": 17107
    },
    {
      "epoch": 0.5255429607102264,
      "grad_norm": 0.4215928912162781,
      "learning_rate": 1.6808236464654094e-05,
      "loss": 0.5441,
      "step": 17108
    },
    {
      "epoch": 0.5255736798451756,
      "grad_norm": 0.35680341720581055,
      "learning_rate": 1.680788248148543e-05,
      "loss": 0.5528,
      "step": 17109
    },
    {
      "epoch": 0.5256043989801247,
      "grad_norm": 0.3291541337966919,
      "learning_rate": 1.6807528482416476e-05,
      "loss": 0.5102,
      "step": 17110
    },
    {
      "epoch": 0.5256351181150739,
      "grad_norm": 0.3145633935928345,
      "learning_rate": 1.6807174467448067e-05,
      "loss": 0.5461,
      "step": 17111
    },
    {
      "epoch": 0.525665837250023,
      "grad_norm": 0.34818947315216064,
      "learning_rate": 1.680682043658103e-05,
      "loss": 0.5259,
      "step": 17112
    },
    {
      "epoch": 0.5256965563849721,
      "grad_norm": 0.38091984391212463,
      "learning_rate": 1.6806466389816183e-05,
      "loss": 0.5797,
      "step": 17113
    },
    {
      "epoch": 0.5257272755199214,
      "grad_norm": 0.3784688115119934,
      "learning_rate": 1.680611232715436e-05,
      "loss": 0.532,
      "step": 17114
    },
    {
      "epoch": 0.5257579946548705,
      "grad_norm": 0.33728086948394775,
      "learning_rate": 1.6805758248596387e-05,
      "loss": 0.6208,
      "step": 17115
    },
    {
      "epoch": 0.5257887137898197,
      "grad_norm": 0.36286550760269165,
      "learning_rate": 1.680540415414309e-05,
      "loss": 0.4759,
      "step": 17116
    },
    {
      "epoch": 0.5258194329247688,
      "grad_norm": 0.36745908856391907,
      "learning_rate": 1.6805050043795296e-05,
      "loss": 0.4678,
      "step": 17117
    },
    {
      "epoch": 0.525850152059718,
      "grad_norm": 0.4414336681365967,
      "learning_rate": 1.6804695917553836e-05,
      "loss": 0.492,
      "step": 17118
    },
    {
      "epoch": 0.5258808711946672,
      "grad_norm": 0.40542227029800415,
      "learning_rate": 1.6804341775419527e-05,
      "loss": 0.5805,
      "step": 17119
    },
    {
      "epoch": 0.5259115903296163,
      "grad_norm": 0.36446017026901245,
      "learning_rate": 1.6803987617393206e-05,
      "loss": 0.5484,
      "step": 17120
    },
    {
      "epoch": 0.5259423094645654,
      "grad_norm": 0.3984276056289673,
      "learning_rate": 1.6803633443475697e-05,
      "loss": 0.529,
      "step": 17121
    },
    {
      "epoch": 0.5259730285995147,
      "grad_norm": 0.3370259702205658,
      "learning_rate": 1.6803279253667826e-05,
      "loss": 0.5649,
      "step": 17122
    },
    {
      "epoch": 0.5260037477344638,
      "grad_norm": 0.39394018054008484,
      "learning_rate": 1.6802925047970423e-05,
      "loss": 0.6288,
      "step": 17123
    },
    {
      "epoch": 0.5260344668694129,
      "grad_norm": 0.41116461157798767,
      "learning_rate": 1.680257082638431e-05,
      "loss": 0.6123,
      "step": 17124
    },
    {
      "epoch": 0.5260651860043621,
      "grad_norm": 0.3367462158203125,
      "learning_rate": 1.680221658891032e-05,
      "loss": 0.6059,
      "step": 17125
    },
    {
      "epoch": 0.5260959051393113,
      "grad_norm": 0.31517907977104187,
      "learning_rate": 1.6801862335549278e-05,
      "loss": 0.5631,
      "step": 17126
    },
    {
      "epoch": 0.5261266242742605,
      "grad_norm": 0.33315861225128174,
      "learning_rate": 1.6801508066302012e-05,
      "loss": 0.5814,
      "step": 17127
    },
    {
      "epoch": 0.5261573434092096,
      "grad_norm": 0.363689124584198,
      "learning_rate": 1.680115378116935e-05,
      "loss": 0.6403,
      "step": 17128
    },
    {
      "epoch": 0.5261880625441587,
      "grad_norm": 0.35932451486587524,
      "learning_rate": 1.6800799480152116e-05,
      "loss": 0.5567,
      "step": 17129
    },
    {
      "epoch": 0.526218781679108,
      "grad_norm": 0.3761639893054962,
      "learning_rate": 1.680044516325114e-05,
      "loss": 0.5427,
      "step": 17130
    },
    {
      "epoch": 0.5262495008140571,
      "grad_norm": 0.3722704350948334,
      "learning_rate": 1.680009083046725e-05,
      "loss": 0.5947,
      "step": 17131
    },
    {
      "epoch": 0.5262802199490062,
      "grad_norm": 0.3661996126174927,
      "learning_rate": 1.6799736481801274e-05,
      "loss": 0.5687,
      "step": 17132
    },
    {
      "epoch": 0.5263109390839554,
      "grad_norm": 0.36639007925987244,
      "learning_rate": 1.6799382117254034e-05,
      "loss": 0.5593,
      "step": 17133
    },
    {
      "epoch": 0.5263416582189046,
      "grad_norm": 0.3621130883693695,
      "learning_rate": 1.6799027736826368e-05,
      "loss": 0.6137,
      "step": 17134
    },
    {
      "epoch": 0.5263723773538537,
      "grad_norm": 0.3885907828807831,
      "learning_rate": 1.6798673340519095e-05,
      "loss": 0.568,
      "step": 17135
    },
    {
      "epoch": 0.5264030964888029,
      "grad_norm": 0.372795432806015,
      "learning_rate": 1.6798318928333047e-05,
      "loss": 0.6053,
      "step": 17136
    },
    {
      "epoch": 0.526433815623752,
      "grad_norm": 0.36231786012649536,
      "learning_rate": 1.679796450026905e-05,
      "loss": 0.5695,
      "step": 17137
    },
    {
      "epoch": 0.5264645347587011,
      "grad_norm": 0.414518803358078,
      "learning_rate": 1.6797610056327932e-05,
      "loss": 0.5727,
      "step": 17138
    },
    {
      "epoch": 0.5264952538936504,
      "grad_norm": 0.3515462577342987,
      "learning_rate": 1.6797255596510518e-05,
      "loss": 0.6362,
      "step": 17139
    },
    {
      "epoch": 0.5265259730285995,
      "grad_norm": 0.4642738997936249,
      "learning_rate": 1.679690112081764e-05,
      "loss": 0.6037,
      "step": 17140
    },
    {
      "epoch": 0.5265566921635487,
      "grad_norm": 0.5408658981323242,
      "learning_rate": 1.6796546629250128e-05,
      "loss": 0.4395,
      "step": 17141
    },
    {
      "epoch": 0.5265874112984978,
      "grad_norm": 0.36373570561408997,
      "learning_rate": 1.6796192121808805e-05,
      "loss": 0.563,
      "step": 17142
    },
    {
      "epoch": 0.526618130433447,
      "grad_norm": 0.37874433398246765,
      "learning_rate": 1.67958375984945e-05,
      "loss": 0.5595,
      "step": 17143
    },
    {
      "epoch": 0.5266488495683962,
      "grad_norm": 0.3226058781147003,
      "learning_rate": 1.6795483059308043e-05,
      "loss": 0.5904,
      "step": 17144
    },
    {
      "epoch": 0.5266795687033453,
      "grad_norm": 0.3525058329105377,
      "learning_rate": 1.679512850425026e-05,
      "loss": 0.5854,
      "step": 17145
    },
    {
      "epoch": 0.5267102878382944,
      "grad_norm": 0.5663449764251709,
      "learning_rate": 1.679477393332198e-05,
      "loss": 0.5683,
      "step": 17146
    },
    {
      "epoch": 0.5267410069732437,
      "grad_norm": 0.35064855217933655,
      "learning_rate": 1.679441934652403e-05,
      "loss": 0.5706,
      "step": 17147
    },
    {
      "epoch": 0.5267717261081928,
      "grad_norm": 0.3384571671485901,
      "learning_rate": 1.679406474385724e-05,
      "loss": 0.5562,
      "step": 17148
    },
    {
      "epoch": 0.5268024452431419,
      "grad_norm": 0.3863227367401123,
      "learning_rate": 1.6793710125322437e-05,
      "loss": 0.506,
      "step": 17149
    },
    {
      "epoch": 0.5268331643780911,
      "grad_norm": 0.3727254569530487,
      "learning_rate": 1.679335549092045e-05,
      "loss": 0.605,
      "step": 17150
    },
    {
      "epoch": 0.5268638835130403,
      "grad_norm": 0.350010484457016,
      "learning_rate": 1.6793000840652106e-05,
      "loss": 0.5494,
      "step": 17151
    },
    {
      "epoch": 0.5268946026479895,
      "grad_norm": 0.35676905512809753,
      "learning_rate": 1.6792646174518235e-05,
      "loss": 0.569,
      "step": 17152
    },
    {
      "epoch": 0.5269253217829386,
      "grad_norm": 0.36581313610076904,
      "learning_rate": 1.6792291492519664e-05,
      "loss": 0.5224,
      "step": 17153
    },
    {
      "epoch": 0.5269560409178877,
      "grad_norm": 0.3375585675239563,
      "learning_rate": 1.6791936794657223e-05,
      "loss": 0.6125,
      "step": 17154
    },
    {
      "epoch": 0.526986760052837,
      "grad_norm": 0.354994535446167,
      "learning_rate": 1.6791582080931736e-05,
      "loss": 0.547,
      "step": 17155
    },
    {
      "epoch": 0.5270174791877861,
      "grad_norm": 0.33246690034866333,
      "learning_rate": 1.679122735134404e-05,
      "loss": 0.578,
      "step": 17156
    },
    {
      "epoch": 0.5270481983227352,
      "grad_norm": 0.3281761109828949,
      "learning_rate": 1.679087260589495e-05,
      "loss": 0.4781,
      "step": 17157
    },
    {
      "epoch": 0.5270789174576844,
      "grad_norm": 0.41937902569770813,
      "learning_rate": 1.679051784458531e-05,
      "loss": 0.5262,
      "step": 17158
    },
    {
      "epoch": 0.5271096365926335,
      "grad_norm": 0.3445090651512146,
      "learning_rate": 1.6790163067415938e-05,
      "loss": 0.585,
      "step": 17159
    },
    {
      "epoch": 0.5271403557275827,
      "grad_norm": 0.5087087750434875,
      "learning_rate": 1.6789808274387668e-05,
      "loss": 0.5709,
      "step": 17160
    },
    {
      "epoch": 0.5271710748625319,
      "grad_norm": 0.36174920201301575,
      "learning_rate": 1.6789453465501326e-05,
      "loss": 0.4982,
      "step": 17161
    },
    {
      "epoch": 0.527201793997481,
      "grad_norm": 0.3528594970703125,
      "learning_rate": 1.678909864075774e-05,
      "loss": 0.609,
      "step": 17162
    },
    {
      "epoch": 0.5272325131324301,
      "grad_norm": 0.3272199332714081,
      "learning_rate": 1.678874380015774e-05,
      "loss": 0.474,
      "step": 17163
    },
    {
      "epoch": 0.5272632322673794,
      "grad_norm": 0.3676362931728363,
      "learning_rate": 1.6788388943702155e-05,
      "loss": 0.5694,
      "step": 17164
    },
    {
      "epoch": 0.5272939514023285,
      "grad_norm": 0.3519970178604126,
      "learning_rate": 1.6788034071391815e-05,
      "loss": 0.5714,
      "step": 17165
    },
    {
      "epoch": 0.5273246705372777,
      "grad_norm": 0.39924296736717224,
      "learning_rate": 1.678767918322755e-05,
      "loss": 0.65,
      "step": 17166
    },
    {
      "epoch": 0.5273553896722268,
      "grad_norm": 0.35354843735694885,
      "learning_rate": 1.678732427921018e-05,
      "loss": 0.5457,
      "step": 17167
    },
    {
      "epoch": 0.527386108807176,
      "grad_norm": 0.32218921184539795,
      "learning_rate": 1.6786969359340544e-05,
      "loss": 0.5536,
      "step": 17168
    },
    {
      "epoch": 0.5274168279421252,
      "grad_norm": 0.3908005356788635,
      "learning_rate": 1.6786614423619464e-05,
      "loss": 0.503,
      "step": 17169
    },
    {
      "epoch": 0.5274475470770743,
      "grad_norm": 0.373963326215744,
      "learning_rate": 1.6786259472047775e-05,
      "loss": 0.7026,
      "step": 17170
    },
    {
      "epoch": 0.5274782662120234,
      "grad_norm": 0.3467302620410919,
      "learning_rate": 1.67859045046263e-05,
      "loss": 0.5639,
      "step": 17171
    },
    {
      "epoch": 0.5275089853469727,
      "grad_norm": 0.44806304574012756,
      "learning_rate": 1.6785549521355875e-05,
      "loss": 0.5422,
      "step": 17172
    },
    {
      "epoch": 0.5275397044819218,
      "grad_norm": 0.41792675852775574,
      "learning_rate": 1.6785194522237323e-05,
      "loss": 0.5978,
      "step": 17173
    },
    {
      "epoch": 0.5275704236168709,
      "grad_norm": 0.32205939292907715,
      "learning_rate": 1.6784839507271477e-05,
      "loss": 0.4508,
      "step": 17174
    },
    {
      "epoch": 0.5276011427518201,
      "grad_norm": 0.4237225651741028,
      "learning_rate": 1.678448447645916e-05,
      "loss": 0.6218,
      "step": 17175
    },
    {
      "epoch": 0.5276318618867692,
      "grad_norm": 0.3637480139732361,
      "learning_rate": 1.678412942980121e-05,
      "loss": 0.5659,
      "step": 17176
    },
    {
      "epoch": 0.5276625810217185,
      "grad_norm": 0.33216169476509094,
      "learning_rate": 1.6783774367298452e-05,
      "loss": 0.4662,
      "step": 17177
    },
    {
      "epoch": 0.5276933001566676,
      "grad_norm": 0.35738667845726013,
      "learning_rate": 1.678341928895171e-05,
      "loss": 0.5922,
      "step": 17178
    },
    {
      "epoch": 0.5277240192916167,
      "grad_norm": 0.38096049427986145,
      "learning_rate": 1.6783064194761826e-05,
      "loss": 0.546,
      "step": 17179
    },
    {
      "epoch": 0.527754738426566,
      "grad_norm": 0.3508017957210541,
      "learning_rate": 1.678270908472962e-05,
      "loss": 0.5715,
      "step": 17180
    },
    {
      "epoch": 0.5277854575615151,
      "grad_norm": 0.370608389377594,
      "learning_rate": 1.6782353958855918e-05,
      "loss": 0.5696,
      "step": 17181
    },
    {
      "epoch": 0.5278161766964642,
      "grad_norm": 0.3483356833457947,
      "learning_rate": 1.6781998817141562e-05,
      "loss": 0.5114,
      "step": 17182
    },
    {
      "epoch": 0.5278468958314134,
      "grad_norm": 0.3458460867404938,
      "learning_rate": 1.678164365958737e-05,
      "loss": 0.5616,
      "step": 17183
    },
    {
      "epoch": 0.5278776149663625,
      "grad_norm": 0.35562390089035034,
      "learning_rate": 1.6781288486194173e-05,
      "loss": 0.5978,
      "step": 17184
    },
    {
      "epoch": 0.5279083341013117,
      "grad_norm": 0.346993088722229,
      "learning_rate": 1.6780933296962806e-05,
      "loss": 0.6147,
      "step": 17185
    },
    {
      "epoch": 0.5279390532362609,
      "grad_norm": 0.33619773387908936,
      "learning_rate": 1.6780578091894096e-05,
      "loss": 0.6066,
      "step": 17186
    },
    {
      "epoch": 0.52796977237121,
      "grad_norm": 0.33275073766708374,
      "learning_rate": 1.6780222870988875e-05,
      "loss": 0.5516,
      "step": 17187
    },
    {
      "epoch": 0.5280004915061592,
      "grad_norm": 0.383171409368515,
      "learning_rate": 1.6779867634247966e-05,
      "loss": 0.544,
      "step": 17188
    },
    {
      "epoch": 0.5280312106411084,
      "grad_norm": 0.36273008584976196,
      "learning_rate": 1.6779512381672206e-05,
      "loss": 0.6582,
      "step": 17189
    },
    {
      "epoch": 0.5280619297760575,
      "grad_norm": 0.33993959426879883,
      "learning_rate": 1.6779157113262416e-05,
      "loss": 0.6521,
      "step": 17190
    },
    {
      "epoch": 0.5280926489110067,
      "grad_norm": 0.3776061534881592,
      "learning_rate": 1.6778801829019435e-05,
      "loss": 0.5655,
      "step": 17191
    },
    {
      "epoch": 0.5281233680459558,
      "grad_norm": 0.3637588918209076,
      "learning_rate": 1.6778446528944087e-05,
      "loss": 0.5753,
      "step": 17192
    },
    {
      "epoch": 0.528154087180905,
      "grad_norm": 0.3536960184574127,
      "learning_rate": 1.6778091213037206e-05,
      "loss": 0.6567,
      "step": 17193
    },
    {
      "epoch": 0.5281848063158542,
      "grad_norm": 0.38684070110321045,
      "learning_rate": 1.6777735881299617e-05,
      "loss": 0.6059,
      "step": 17194
    },
    {
      "epoch": 0.5282155254508033,
      "grad_norm": 0.37449198961257935,
      "learning_rate": 1.6777380533732155e-05,
      "loss": 0.6539,
      "step": 17195
    },
    {
      "epoch": 0.5282462445857524,
      "grad_norm": 0.30988872051239014,
      "learning_rate": 1.6777025170335646e-05,
      "loss": 0.528,
      "step": 17196
    },
    {
      "epoch": 0.5282769637207017,
      "grad_norm": 0.38072454929351807,
      "learning_rate": 1.677666979111092e-05,
      "loss": 0.613,
      "step": 17197
    },
    {
      "epoch": 0.5283076828556508,
      "grad_norm": 0.3558870255947113,
      "learning_rate": 1.6776314396058812e-05,
      "loss": 0.6197,
      "step": 17198
    },
    {
      "epoch": 0.5283384019905999,
      "grad_norm": 0.34503185749053955,
      "learning_rate": 1.6775958985180147e-05,
      "loss": 0.5401,
      "step": 17199
    },
    {
      "epoch": 0.5283691211255491,
      "grad_norm": 0.3353354036808014,
      "learning_rate": 1.6775603558475755e-05,
      "loss": 0.55,
      "step": 17200
    },
    {
      "epoch": 0.5283998402604982,
      "grad_norm": 0.47175419330596924,
      "learning_rate": 1.6775248115946467e-05,
      "loss": 0.5725,
      "step": 17201
    },
    {
      "epoch": 0.5284305593954475,
      "grad_norm": 0.35500669479370117,
      "learning_rate": 1.6774892657593116e-05,
      "loss": 0.6688,
      "step": 17202
    },
    {
      "epoch": 0.5284612785303966,
      "grad_norm": 0.3812509775161743,
      "learning_rate": 1.677453718341653e-05,
      "loss": 0.664,
      "step": 17203
    },
    {
      "epoch": 0.5284919976653457,
      "grad_norm": 0.3242207467556,
      "learning_rate": 1.677418169341754e-05,
      "loss": 0.4736,
      "step": 17204
    },
    {
      "epoch": 0.528522716800295,
      "grad_norm": 0.35710349678993225,
      "learning_rate": 1.6773826187596974e-05,
      "loss": 0.4571,
      "step": 17205
    },
    {
      "epoch": 0.5285534359352441,
      "grad_norm": 0.31059250235557556,
      "learning_rate": 1.6773470665955666e-05,
      "loss": 0.5243,
      "step": 17206
    },
    {
      "epoch": 0.5285841550701932,
      "grad_norm": 0.33832621574401855,
      "learning_rate": 1.6773115128494442e-05,
      "loss": 0.5305,
      "step": 17207
    },
    {
      "epoch": 0.5286148742051424,
      "grad_norm": 0.3478144109249115,
      "learning_rate": 1.6772759575214136e-05,
      "loss": 0.6311,
      "step": 17208
    },
    {
      "epoch": 0.5286455933400915,
      "grad_norm": 0.3306460976600647,
      "learning_rate": 1.6772404006115578e-05,
      "loss": 0.5135,
      "step": 17209
    },
    {
      "epoch": 0.5286763124750407,
      "grad_norm": 0.368017315864563,
      "learning_rate": 1.6772048421199594e-05,
      "loss": 0.5473,
      "step": 17210
    },
    {
      "epoch": 0.5287070316099899,
      "grad_norm": 0.343172550201416,
      "learning_rate": 1.6771692820467018e-05,
      "loss": 0.5949,
      "step": 17211
    },
    {
      "epoch": 0.528737750744939,
      "grad_norm": 0.36456000804901123,
      "learning_rate": 1.677133720391868e-05,
      "loss": 0.5375,
      "step": 17212
    },
    {
      "epoch": 0.5287684698798882,
      "grad_norm": 0.32627618312835693,
      "learning_rate": 1.6770981571555417e-05,
      "loss": 0.607,
      "step": 17213
    },
    {
      "epoch": 0.5287991890148374,
      "grad_norm": 0.39072856307029724,
      "learning_rate": 1.6770625923378046e-05,
      "loss": 0.6264,
      "step": 17214
    },
    {
      "epoch": 0.5288299081497865,
      "grad_norm": 0.35281720757484436,
      "learning_rate": 1.677027025938741e-05,
      "loss": 0.6063,
      "step": 17215
    },
    {
      "epoch": 0.5288606272847357,
      "grad_norm": 0.3935064673423767,
      "learning_rate": 1.6769914579584336e-05,
      "loss": 0.598,
      "step": 17216
    },
    {
      "epoch": 0.5288913464196848,
      "grad_norm": 0.4175238609313965,
      "learning_rate": 1.676955888396965e-05,
      "loss": 0.5549,
      "step": 17217
    },
    {
      "epoch": 0.528922065554634,
      "grad_norm": 0.321268767118454,
      "learning_rate": 1.676920317254419e-05,
      "loss": 0.5368,
      "step": 17218
    },
    {
      "epoch": 0.5289527846895832,
      "grad_norm": 0.36270490288734436,
      "learning_rate": 1.676884744530878e-05,
      "loss": 0.5783,
      "step": 17219
    },
    {
      "epoch": 0.5289835038245323,
      "grad_norm": 0.3529336750507355,
      "learning_rate": 1.676849170226426e-05,
      "loss": 0.6008,
      "step": 17220
    },
    {
      "epoch": 0.5290142229594814,
      "grad_norm": 0.36654698848724365,
      "learning_rate": 1.6768135943411445e-05,
      "loss": 0.5495,
      "step": 17221
    },
    {
      "epoch": 0.5290449420944306,
      "grad_norm": 0.35879987478256226,
      "learning_rate": 1.6767780168751183e-05,
      "loss": 0.5969,
      "step": 17222
    },
    {
      "epoch": 0.5290756612293798,
      "grad_norm": 0.43403923511505127,
      "learning_rate": 1.6767424378284295e-05,
      "loss": 0.4011,
      "step": 17223
    },
    {
      "epoch": 0.5291063803643289,
      "grad_norm": 0.3810604512691498,
      "learning_rate": 1.676706857201162e-05,
      "loss": 0.5711,
      "step": 17224
    },
    {
      "epoch": 0.5291370994992781,
      "grad_norm": 0.3474650979042053,
      "learning_rate": 1.676671274993398e-05,
      "loss": 0.5608,
      "step": 17225
    },
    {
      "epoch": 0.5291678186342272,
      "grad_norm": 0.3809007406234741,
      "learning_rate": 1.6766356912052208e-05,
      "loss": 0.5728,
      "step": 17226
    },
    {
      "epoch": 0.5291985377691765,
      "grad_norm": 0.3907526433467865,
      "learning_rate": 1.6766001058367137e-05,
      "loss": 0.5858,
      "step": 17227
    },
    {
      "epoch": 0.5292292569041256,
      "grad_norm": 0.3540938198566437,
      "learning_rate": 1.6765645188879596e-05,
      "loss": 0.5301,
      "step": 17228
    },
    {
      "epoch": 0.5292599760390747,
      "grad_norm": 0.37664374709129333,
      "learning_rate": 1.6765289303590425e-05,
      "loss": 0.5033,
      "step": 17229
    },
    {
      "epoch": 0.5292906951740239,
      "grad_norm": 0.3645837604999542,
      "learning_rate": 1.6764933402500444e-05,
      "loss": 0.5716,
      "step": 17230
    },
    {
      "epoch": 0.5293214143089731,
      "grad_norm": 0.3708764910697937,
      "learning_rate": 1.676457748561049e-05,
      "loss": 0.5062,
      "step": 17231
    },
    {
      "epoch": 0.5293521334439222,
      "grad_norm": 0.33386680483818054,
      "learning_rate": 1.6764221552921392e-05,
      "loss": 0.521,
      "step": 17232
    },
    {
      "epoch": 0.5293828525788714,
      "grad_norm": 0.38108786940574646,
      "learning_rate": 1.676386560443398e-05,
      "loss": 0.5899,
      "step": 17233
    },
    {
      "epoch": 0.5294135717138205,
      "grad_norm": 0.33968815207481384,
      "learning_rate": 1.676350964014909e-05,
      "loss": 0.5367,
      "step": 17234
    },
    {
      "epoch": 0.5294442908487696,
      "grad_norm": 0.3630366027355194,
      "learning_rate": 1.676315366006755e-05,
      "loss": 0.5171,
      "step": 17235
    },
    {
      "epoch": 0.5294750099837189,
      "grad_norm": 0.3717157244682312,
      "learning_rate": 1.6762797664190196e-05,
      "loss": 0.6048,
      "step": 17236
    },
    {
      "epoch": 0.529505729118668,
      "grad_norm": 0.4420836865901947,
      "learning_rate": 1.676244165251785e-05,
      "loss": 0.6137,
      "step": 17237
    },
    {
      "epoch": 0.5295364482536172,
      "grad_norm": 0.36189961433410645,
      "learning_rate": 1.6762085625051354e-05,
      "loss": 0.6351,
      "step": 17238
    },
    {
      "epoch": 0.5295671673885664,
      "grad_norm": 0.34608232975006104,
      "learning_rate": 1.6761729581791534e-05,
      "loss": 0.6374,
      "step": 17239
    },
    {
      "epoch": 0.5295978865235155,
      "grad_norm": 0.3361964821815491,
      "learning_rate": 1.676137352273922e-05,
      "loss": 0.5305,
      "step": 17240
    },
    {
      "epoch": 0.5296286056584647,
      "grad_norm": 0.4377133250236511,
      "learning_rate": 1.6761017447895248e-05,
      "loss": 0.6076,
      "step": 17241
    },
    {
      "epoch": 0.5296593247934138,
      "grad_norm": 0.3038196563720703,
      "learning_rate": 1.6760661357260442e-05,
      "loss": 0.5404,
      "step": 17242
    },
    {
      "epoch": 0.5296900439283629,
      "grad_norm": 0.3467174172401428,
      "learning_rate": 1.6760305250835648e-05,
      "loss": 0.5812,
      "step": 17243
    },
    {
      "epoch": 0.5297207630633122,
      "grad_norm": 0.33301252126693726,
      "learning_rate": 1.6759949128621685e-05,
      "loss": 0.5702,
      "step": 17244
    },
    {
      "epoch": 0.5297514821982613,
      "grad_norm": 0.6793193221092224,
      "learning_rate": 1.6759592990619387e-05,
      "loss": 0.502,
      "step": 17245
    },
    {
      "epoch": 0.5297822013332104,
      "grad_norm": 0.43540146946907043,
      "learning_rate": 1.6759236836829587e-05,
      "loss": 0.5768,
      "step": 17246
    },
    {
      "epoch": 0.5298129204681596,
      "grad_norm": 0.34679651260375977,
      "learning_rate": 1.675888066725312e-05,
      "loss": 0.5685,
      "step": 17247
    },
    {
      "epoch": 0.5298436396031088,
      "grad_norm": 0.34440675377845764,
      "learning_rate": 1.6758524481890814e-05,
      "loss": 0.5676,
      "step": 17248
    },
    {
      "epoch": 0.5298743587380579,
      "grad_norm": 0.35088053345680237,
      "learning_rate": 1.6758168280743504e-05,
      "loss": 0.5987,
      "step": 17249
    },
    {
      "epoch": 0.5299050778730071,
      "grad_norm": 0.34457749128341675,
      "learning_rate": 1.6757812063812017e-05,
      "loss": 0.4646,
      "step": 17250
    },
    {
      "epoch": 0.5299357970079562,
      "grad_norm": 0.3695155382156372,
      "learning_rate": 1.6757455831097188e-05,
      "loss": 0.6013,
      "step": 17251
    },
    {
      "epoch": 0.5299665161429055,
      "grad_norm": 0.34640997648239136,
      "learning_rate": 1.6757099582599852e-05,
      "loss": 0.6374,
      "step": 17252
    },
    {
      "epoch": 0.5299972352778546,
      "grad_norm": 0.3437354266643524,
      "learning_rate": 1.6756743318320836e-05,
      "loss": 0.5743,
      "step": 17253
    },
    {
      "epoch": 0.5300279544128037,
      "grad_norm": 0.4554313123226166,
      "learning_rate": 1.6756387038260975e-05,
      "loss": 0.5717,
      "step": 17254
    },
    {
      "epoch": 0.5300586735477529,
      "grad_norm": 0.3293493986129761,
      "learning_rate": 1.67560307424211e-05,
      "loss": 0.4945,
      "step": 17255
    },
    {
      "epoch": 0.530089392682702,
      "grad_norm": 0.3792603313922882,
      "learning_rate": 1.6755674430802043e-05,
      "loss": 0.6984,
      "step": 17256
    },
    {
      "epoch": 0.5301201118176512,
      "grad_norm": 0.36618632078170776,
      "learning_rate": 1.6755318103404635e-05,
      "loss": 0.5724,
      "step": 17257
    },
    {
      "epoch": 0.5301508309526004,
      "grad_norm": 0.32332542538642883,
      "learning_rate": 1.6754961760229714e-05,
      "loss": 0.561,
      "step": 17258
    },
    {
      "epoch": 0.5301815500875495,
      "grad_norm": 0.3638613522052765,
      "learning_rate": 1.6754605401278106e-05,
      "loss": 0.5153,
      "step": 17259
    },
    {
      "epoch": 0.5302122692224986,
      "grad_norm": 0.3504585027694702,
      "learning_rate": 1.6754249026550644e-05,
      "loss": 0.5625,
      "step": 17260
    },
    {
      "epoch": 0.5302429883574479,
      "grad_norm": 0.3430297076702118,
      "learning_rate": 1.6753892636048164e-05,
      "loss": 0.5458,
      "step": 17261
    },
    {
      "epoch": 0.530273707492397,
      "grad_norm": 0.33634695410728455,
      "learning_rate": 1.6753536229771493e-05,
      "loss": 0.5092,
      "step": 17262
    },
    {
      "epoch": 0.5303044266273462,
      "grad_norm": 0.3930884003639221,
      "learning_rate": 1.675317980772147e-05,
      "loss": 0.6019,
      "step": 17263
    },
    {
      "epoch": 0.5303351457622953,
      "grad_norm": 0.4015962481498718,
      "learning_rate": 1.675282336989892e-05,
      "loss": 0.5244,
      "step": 17264
    },
    {
      "epoch": 0.5303658648972445,
      "grad_norm": 0.4321385622024536,
      "learning_rate": 1.675246691630468e-05,
      "loss": 0.5352,
      "step": 17265
    },
    {
      "epoch": 0.5303965840321937,
      "grad_norm": 0.3691467344760895,
      "learning_rate": 1.6752110446939583e-05,
      "loss": 0.5187,
      "step": 17266
    },
    {
      "epoch": 0.5304273031671428,
      "grad_norm": 0.34569254517555237,
      "learning_rate": 1.675175396180446e-05,
      "loss": 0.5548,
      "step": 17267
    },
    {
      "epoch": 0.5304580223020919,
      "grad_norm": 0.3645572066307068,
      "learning_rate": 1.6751397460900146e-05,
      "loss": 0.5538,
      "step": 17268
    },
    {
      "epoch": 0.5304887414370412,
      "grad_norm": 0.33556920289993286,
      "learning_rate": 1.6751040944227473e-05,
      "loss": 0.5351,
      "step": 17269
    },
    {
      "epoch": 0.5305194605719903,
      "grad_norm": 0.3323725461959839,
      "learning_rate": 1.6750684411787268e-05,
      "loss": 0.543,
      "step": 17270
    },
    {
      "epoch": 0.5305501797069394,
      "grad_norm": 0.36526861786842346,
      "learning_rate": 1.6750327863580368e-05,
      "loss": 0.6461,
      "step": 17271
    },
    {
      "epoch": 0.5305808988418886,
      "grad_norm": 0.37965187430381775,
      "learning_rate": 1.674997129960761e-05,
      "loss": 0.6308,
      "step": 17272
    },
    {
      "epoch": 0.5306116179768378,
      "grad_norm": 0.3410053849220276,
      "learning_rate": 1.6749614719869823e-05,
      "loss": 0.5559,
      "step": 17273
    },
    {
      "epoch": 0.5306423371117869,
      "grad_norm": 0.4290660321712494,
      "learning_rate": 1.6749258124367833e-05,
      "loss": 0.5977,
      "step": 17274
    },
    {
      "epoch": 0.5306730562467361,
      "grad_norm": 0.32674309611320496,
      "learning_rate": 1.6748901513102484e-05,
      "loss": 0.5163,
      "step": 17275
    },
    {
      "epoch": 0.5307037753816852,
      "grad_norm": 0.3867798447608948,
      "learning_rate": 1.6748544886074604e-05,
      "loss": 0.5755,
      "step": 17276
    },
    {
      "epoch": 0.5307344945166345,
      "grad_norm": 0.33389073610305786,
      "learning_rate": 1.6748188243285027e-05,
      "loss": 0.5582,
      "step": 17277
    },
    {
      "epoch": 0.5307652136515836,
      "grad_norm": 0.3941335082054138,
      "learning_rate": 1.6747831584734583e-05,
      "loss": 0.6333,
      "step": 17278
    },
    {
      "epoch": 0.5307959327865327,
      "grad_norm": 0.36234936118125916,
      "learning_rate": 1.6747474910424108e-05,
      "loss": 0.5888,
      "step": 17279
    },
    {
      "epoch": 0.5308266519214819,
      "grad_norm": 0.354898065328598,
      "learning_rate": 1.6747118220354432e-05,
      "loss": 0.5881,
      "step": 17280
    },
    {
      "epoch": 0.530857371056431,
      "grad_norm": 0.4172767400741577,
      "learning_rate": 1.6746761514526393e-05,
      "loss": 0.4912,
      "step": 17281
    },
    {
      "epoch": 0.5308880901913802,
      "grad_norm": 0.374140202999115,
      "learning_rate": 1.674640479294082e-05,
      "loss": 0.5177,
      "step": 17282
    },
    {
      "epoch": 0.5309188093263294,
      "grad_norm": 0.30899038910865784,
      "learning_rate": 1.6746048055598548e-05,
      "loss": 0.4708,
      "step": 17283
    },
    {
      "epoch": 0.5309495284612785,
      "grad_norm": 0.3286052644252777,
      "learning_rate": 1.674569130250041e-05,
      "loss": 0.5595,
      "step": 17284
    },
    {
      "epoch": 0.5309802475962276,
      "grad_norm": 0.3817119300365448,
      "learning_rate": 1.6745334533647237e-05,
      "loss": 0.6325,
      "step": 17285
    },
    {
      "epoch": 0.5310109667311769,
      "grad_norm": 0.43117228150367737,
      "learning_rate": 1.6744977749039865e-05,
      "loss": 0.6356,
      "step": 17286
    },
    {
      "epoch": 0.531041685866126,
      "grad_norm": 0.3622561991214752,
      "learning_rate": 1.6744620948679127e-05,
      "loss": 0.5582,
      "step": 17287
    },
    {
      "epoch": 0.5310724050010752,
      "grad_norm": 0.43353569507598877,
      "learning_rate": 1.6744264132565853e-05,
      "loss": 0.5387,
      "step": 17288
    },
    {
      "epoch": 0.5311031241360243,
      "grad_norm": 0.4620560109615326,
      "learning_rate": 1.6743907300700884e-05,
      "loss": 0.5068,
      "step": 17289
    },
    {
      "epoch": 0.5311338432709735,
      "grad_norm": 0.35169586539268494,
      "learning_rate": 1.6743550453085045e-05,
      "loss": 0.5344,
      "step": 17290
    },
    {
      "epoch": 0.5311645624059227,
      "grad_norm": 0.37219780683517456,
      "learning_rate": 1.6743193589719175e-05,
      "loss": 0.5771,
      "step": 17291
    },
    {
      "epoch": 0.5311952815408718,
      "grad_norm": 0.39778387546539307,
      "learning_rate": 1.6742836710604105e-05,
      "loss": 0.5542,
      "step": 17292
    },
    {
      "epoch": 0.5312260006758209,
      "grad_norm": 0.37781190872192383,
      "learning_rate": 1.6742479815740667e-05,
      "loss": 0.5783,
      "step": 17293
    },
    {
      "epoch": 0.5312567198107702,
      "grad_norm": 0.35347846150398254,
      "learning_rate": 1.67421229051297e-05,
      "loss": 0.6053,
      "step": 17294
    },
    {
      "epoch": 0.5312874389457193,
      "grad_norm": 0.37462326884269714,
      "learning_rate": 1.674176597877203e-05,
      "loss": 0.5432,
      "step": 17295
    },
    {
      "epoch": 0.5313181580806684,
      "grad_norm": 0.3665309250354767,
      "learning_rate": 1.67414090366685e-05,
      "loss": 0.6412,
      "step": 17296
    },
    {
      "epoch": 0.5313488772156176,
      "grad_norm": 0.34918949007987976,
      "learning_rate": 1.6741052078819936e-05,
      "loss": 0.5878,
      "step": 17297
    },
    {
      "epoch": 0.5313795963505668,
      "grad_norm": 0.3538622260093689,
      "learning_rate": 1.674069510522717e-05,
      "loss": 0.5097,
      "step": 17298
    },
    {
      "epoch": 0.531410315485516,
      "grad_norm": 0.3396088182926178,
      "learning_rate": 1.6740338115891045e-05,
      "loss": 0.5415,
      "step": 17299
    },
    {
      "epoch": 0.5314410346204651,
      "grad_norm": 0.3678450882434845,
      "learning_rate": 1.6739981110812388e-05,
      "loss": 0.6431,
      "step": 17300
    },
    {
      "epoch": 0.5314717537554142,
      "grad_norm": 0.3718957006931305,
      "learning_rate": 1.673962408999203e-05,
      "loss": 0.559,
      "step": 17301
    },
    {
      "epoch": 0.5315024728903635,
      "grad_norm": 0.35013312101364136,
      "learning_rate": 1.6739267053430815e-05,
      "loss": 0.5796,
      "step": 17302
    },
    {
      "epoch": 0.5315331920253126,
      "grad_norm": 0.3530600070953369,
      "learning_rate": 1.6738910001129567e-05,
      "loss": 0.5251,
      "step": 17303
    },
    {
      "epoch": 0.5315639111602617,
      "grad_norm": 0.3594443202018738,
      "learning_rate": 1.6738552933089128e-05,
      "loss": 0.6741,
      "step": 17304
    },
    {
      "epoch": 0.5315946302952109,
      "grad_norm": 0.3446805775165558,
      "learning_rate": 1.6738195849310326e-05,
      "loss": 0.6204,
      "step": 17305
    },
    {
      "epoch": 0.53162534943016,
      "grad_norm": 0.35248494148254395,
      "learning_rate": 1.6737838749793997e-05,
      "loss": 0.6445,
      "step": 17306
    },
    {
      "epoch": 0.5316560685651092,
      "grad_norm": 0.34697791934013367,
      "learning_rate": 1.6737481634540978e-05,
      "loss": 0.6351,
      "step": 17307
    },
    {
      "epoch": 0.5316867877000584,
      "grad_norm": 0.36272725462913513,
      "learning_rate": 1.6737124503552097e-05,
      "loss": 0.577,
      "step": 17308
    },
    {
      "epoch": 0.5317175068350075,
      "grad_norm": 0.3346388041973114,
      "learning_rate": 1.6736767356828193e-05,
      "loss": 0.5919,
      "step": 17309
    },
    {
      "epoch": 0.5317482259699566,
      "grad_norm": 0.3537120223045349,
      "learning_rate": 1.6736410194370096e-05,
      "loss": 0.5379,
      "step": 17310
    },
    {
      "epoch": 0.5317789451049059,
      "grad_norm": 0.3835258185863495,
      "learning_rate": 1.6736053016178643e-05,
      "loss": 0.6287,
      "step": 17311
    },
    {
      "epoch": 0.531809664239855,
      "grad_norm": 0.36293575167655945,
      "learning_rate": 1.6735695822254668e-05,
      "loss": 0.6345,
      "step": 17312
    },
    {
      "epoch": 0.5318403833748042,
      "grad_norm": 0.4310011863708496,
      "learning_rate": 1.6735338612599004e-05,
      "loss": 0.6199,
      "step": 17313
    },
    {
      "epoch": 0.5318711025097533,
      "grad_norm": 0.32151293754577637,
      "learning_rate": 1.673498138721249e-05,
      "loss": 0.4659,
      "step": 17314
    },
    {
      "epoch": 0.5319018216447025,
      "grad_norm": 0.3638944923877716,
      "learning_rate": 1.6734624146095954e-05,
      "loss": 0.6306,
      "step": 17315
    },
    {
      "epoch": 0.5319325407796517,
      "grad_norm": 0.36964356899261475,
      "learning_rate": 1.6734266889250232e-05,
      "loss": 0.5329,
      "step": 17316
    },
    {
      "epoch": 0.5319632599146008,
      "grad_norm": 0.34486687183380127,
      "learning_rate": 1.673390961667616e-05,
      "loss": 0.5728,
      "step": 17317
    },
    {
      "epoch": 0.5319939790495499,
      "grad_norm": 0.5779333710670471,
      "learning_rate": 1.6733552328374572e-05,
      "loss": 0.5817,
      "step": 17318
    },
    {
      "epoch": 0.5320246981844992,
      "grad_norm": 0.33269450068473816,
      "learning_rate": 1.6733195024346303e-05,
      "loss": 0.5292,
      "step": 17319
    },
    {
      "epoch": 0.5320554173194483,
      "grad_norm": 0.48717200756073,
      "learning_rate": 1.6732837704592185e-05,
      "loss": 0.635,
      "step": 17320
    },
    {
      "epoch": 0.5320861364543974,
      "grad_norm": 0.39030301570892334,
      "learning_rate": 1.6732480369113057e-05,
      "loss": 0.6454,
      "step": 17321
    },
    {
      "epoch": 0.5321168555893466,
      "grad_norm": 0.42183101177215576,
      "learning_rate": 1.673212301790975e-05,
      "loss": 0.7039,
      "step": 17322
    },
    {
      "epoch": 0.5321475747242957,
      "grad_norm": 0.3666004240512848,
      "learning_rate": 1.6731765650983098e-05,
      "loss": 0.6086,
      "step": 17323
    },
    {
      "epoch": 0.532178293859245,
      "grad_norm": 0.3422590494155884,
      "learning_rate": 1.6731408268333938e-05,
      "loss": 0.523,
      "step": 17324
    },
    {
      "epoch": 0.5322090129941941,
      "grad_norm": 1.6792553663253784,
      "learning_rate": 1.6731050869963105e-05,
      "loss": 0.5859,
      "step": 17325
    },
    {
      "epoch": 0.5322397321291432,
      "grad_norm": 0.3990066349506378,
      "learning_rate": 1.673069345587143e-05,
      "loss": 0.6208,
      "step": 17326
    },
    {
      "epoch": 0.5322704512640924,
      "grad_norm": 0.34617915749549866,
      "learning_rate": 1.6730336026059755e-05,
      "loss": 0.6322,
      "step": 17327
    },
    {
      "epoch": 0.5323011703990416,
      "grad_norm": 0.32512417435646057,
      "learning_rate": 1.6729978580528908e-05,
      "loss": 0.5075,
      "step": 17328
    },
    {
      "epoch": 0.5323318895339907,
      "grad_norm": 0.3258800208568573,
      "learning_rate": 1.6729621119279726e-05,
      "loss": 0.5371,
      "step": 17329
    },
    {
      "epoch": 0.5323626086689399,
      "grad_norm": 0.3864729404449463,
      "learning_rate": 1.6729263642313044e-05,
      "loss": 0.5984,
      "step": 17330
    },
    {
      "epoch": 0.532393327803889,
      "grad_norm": 0.3683992922306061,
      "learning_rate": 1.6728906149629693e-05,
      "loss": 0.5555,
      "step": 17331
    },
    {
      "epoch": 0.5324240469388382,
      "grad_norm": 0.34229734539985657,
      "learning_rate": 1.6728548641230516e-05,
      "loss": 0.5962,
      "step": 17332
    },
    {
      "epoch": 0.5324547660737874,
      "grad_norm": 0.3372699022293091,
      "learning_rate": 1.6728191117116344e-05,
      "loss": 0.5534,
      "step": 17333
    },
    {
      "epoch": 0.5324854852087365,
      "grad_norm": 0.3725792169570923,
      "learning_rate": 1.672783357728801e-05,
      "loss": 0.629,
      "step": 17334
    },
    {
      "epoch": 0.5325162043436856,
      "grad_norm": 0.36258333921432495,
      "learning_rate": 1.672747602174635e-05,
      "loss": 0.4956,
      "step": 17335
    },
    {
      "epoch": 0.5325469234786349,
      "grad_norm": 0.34343135356903076,
      "learning_rate": 1.67271184504922e-05,
      "loss": 0.5175,
      "step": 17336
    },
    {
      "epoch": 0.532577642613584,
      "grad_norm": 0.4418194591999054,
      "learning_rate": 1.6726760863526398e-05,
      "loss": 0.5264,
      "step": 17337
    },
    {
      "epoch": 0.5326083617485332,
      "grad_norm": 0.34815558791160583,
      "learning_rate": 1.6726403260849774e-05,
      "loss": 0.4914,
      "step": 17338
    },
    {
      "epoch": 0.5326390808834823,
      "grad_norm": 0.37168148159980774,
      "learning_rate": 1.6726045642463162e-05,
      "loss": 0.5499,
      "step": 17339
    },
    {
      "epoch": 0.5326698000184314,
      "grad_norm": 0.4095971882343292,
      "learning_rate": 1.6725688008367407e-05,
      "loss": 0.5947,
      "step": 17340
    },
    {
      "epoch": 0.5327005191533807,
      "grad_norm": 0.4383649230003357,
      "learning_rate": 1.6725330358563334e-05,
      "loss": 0.5271,
      "step": 17341
    },
    {
      "epoch": 0.5327312382883298,
      "grad_norm": 0.40236011147499084,
      "learning_rate": 1.6724972693051783e-05,
      "loss": 0.5704,
      "step": 17342
    },
    {
      "epoch": 0.5327619574232789,
      "grad_norm": 0.35946041345596313,
      "learning_rate": 1.6724615011833593e-05,
      "loss": 0.5714,
      "step": 17343
    },
    {
      "epoch": 0.5327926765582282,
      "grad_norm": 0.38009390234947205,
      "learning_rate": 1.6724257314909588e-05,
      "loss": 0.6199,
      "step": 17344
    },
    {
      "epoch": 0.5328233956931773,
      "grad_norm": 0.34332039952278137,
      "learning_rate": 1.6723899602280617e-05,
      "loss": 0.5795,
      "step": 17345
    },
    {
      "epoch": 0.5328541148281264,
      "grad_norm": 0.402311235666275,
      "learning_rate": 1.6723541873947503e-05,
      "loss": 0.5834,
      "step": 17346
    },
    {
      "epoch": 0.5328848339630756,
      "grad_norm": 0.4167317748069763,
      "learning_rate": 1.672318412991109e-05,
      "loss": 0.6181,
      "step": 17347
    },
    {
      "epoch": 0.5329155530980247,
      "grad_norm": 0.40620142221450806,
      "learning_rate": 1.672282637017221e-05,
      "loss": 0.6049,
      "step": 17348
    },
    {
      "epoch": 0.532946272232974,
      "grad_norm": 0.38681524991989136,
      "learning_rate": 1.67224685947317e-05,
      "loss": 0.4987,
      "step": 17349
    },
    {
      "epoch": 0.5329769913679231,
      "grad_norm": 0.35705694556236267,
      "learning_rate": 1.6722110803590397e-05,
      "loss": 0.5056,
      "step": 17350
    },
    {
      "epoch": 0.5330077105028722,
      "grad_norm": 0.31814438104629517,
      "learning_rate": 1.6721752996749133e-05,
      "loss": 0.596,
      "step": 17351
    },
    {
      "epoch": 0.5330384296378214,
      "grad_norm": 0.4494929909706116,
      "learning_rate": 1.6721395174208743e-05,
      "loss": 0.7133,
      "step": 17352
    },
    {
      "epoch": 0.5330691487727706,
      "grad_norm": 0.38571465015411377,
      "learning_rate": 1.6721037335970068e-05,
      "loss": 0.5558,
      "step": 17353
    },
    {
      "epoch": 0.5330998679077197,
      "grad_norm": 0.35353201627731323,
      "learning_rate": 1.6720679482033945e-05,
      "loss": 0.5312,
      "step": 17354
    },
    {
      "epoch": 0.5331305870426689,
      "grad_norm": 0.361712783575058,
      "learning_rate": 1.67203216124012e-05,
      "loss": 0.586,
      "step": 17355
    },
    {
      "epoch": 0.533161306177618,
      "grad_norm": 0.3359939157962799,
      "learning_rate": 1.6719963727072673e-05,
      "loss": 0.5412,
      "step": 17356
    },
    {
      "epoch": 0.5331920253125672,
      "grad_norm": 0.40301960706710815,
      "learning_rate": 1.6719605826049202e-05,
      "loss": 0.5697,
      "step": 17357
    },
    {
      "epoch": 0.5332227444475164,
      "grad_norm": 0.36025378108024597,
      "learning_rate": 1.6719247909331627e-05,
      "loss": 0.5077,
      "step": 17358
    },
    {
      "epoch": 0.5332534635824655,
      "grad_norm": 0.39578837156295776,
      "learning_rate": 1.6718889976920774e-05,
      "loss": 0.6615,
      "step": 17359
    },
    {
      "epoch": 0.5332841827174146,
      "grad_norm": 0.33421778678894043,
      "learning_rate": 1.6718532028817487e-05,
      "loss": 0.5702,
      "step": 17360
    },
    {
      "epoch": 0.5333149018523639,
      "grad_norm": 0.38005849719047546,
      "learning_rate": 1.6718174065022604e-05,
      "loss": 0.6207,
      "step": 17361
    },
    {
      "epoch": 0.533345620987313,
      "grad_norm": 0.3307769000530243,
      "learning_rate": 1.671781608553695e-05,
      "loss": 0.4898,
      "step": 17362
    },
    {
      "epoch": 0.5333763401222622,
      "grad_norm": 0.34856104850769043,
      "learning_rate": 1.671745809036137e-05,
      "loss": 0.4946,
      "step": 17363
    },
    {
      "epoch": 0.5334070592572113,
      "grad_norm": 0.33593735098838806,
      "learning_rate": 1.6717100079496695e-05,
      "loss": 0.528,
      "step": 17364
    },
    {
      "epoch": 0.5334377783921604,
      "grad_norm": 0.3310040235519409,
      "learning_rate": 1.6716742052943768e-05,
      "loss": 0.4961,
      "step": 17365
    },
    {
      "epoch": 0.5334684975271097,
      "grad_norm": 0.35519418120384216,
      "learning_rate": 1.6716384010703418e-05,
      "loss": 0.4964,
      "step": 17366
    },
    {
      "epoch": 0.5334992166620588,
      "grad_norm": 0.3398650288581848,
      "learning_rate": 1.6716025952776482e-05,
      "loss": 0.5031,
      "step": 17367
    },
    {
      "epoch": 0.5335299357970079,
      "grad_norm": 0.32115644216537476,
      "learning_rate": 1.67156678791638e-05,
      "loss": 0.4853,
      "step": 17368
    },
    {
      "epoch": 0.5335606549319571,
      "grad_norm": 0.3403930366039276,
      "learning_rate": 1.6715309789866206e-05,
      "loss": 0.5816,
      "step": 17369
    },
    {
      "epoch": 0.5335913740669063,
      "grad_norm": 0.37326541543006897,
      "learning_rate": 1.6714951684884537e-05,
      "loss": 0.5489,
      "step": 17370
    },
    {
      "epoch": 0.5336220932018554,
      "grad_norm": 0.3665692210197449,
      "learning_rate": 1.6714593564219632e-05,
      "loss": 0.6713,
      "step": 17371
    },
    {
      "epoch": 0.5336528123368046,
      "grad_norm": 0.3653124272823334,
      "learning_rate": 1.6714235427872323e-05,
      "loss": 0.5717,
      "step": 17372
    },
    {
      "epoch": 0.5336835314717537,
      "grad_norm": 0.4197884798049927,
      "learning_rate": 1.671387727584345e-05,
      "loss": 0.5873,
      "step": 17373
    },
    {
      "epoch": 0.533714250606703,
      "grad_norm": 0.3606233596801758,
      "learning_rate": 1.6713519108133846e-05,
      "loss": 0.5823,
      "step": 17374
    },
    {
      "epoch": 0.5337449697416521,
      "grad_norm": 0.361645370721817,
      "learning_rate": 1.6713160924744346e-05,
      "loss": 0.5362,
      "step": 17375
    },
    {
      "epoch": 0.5337756888766012,
      "grad_norm": 0.37010568380355835,
      "learning_rate": 1.6712802725675795e-05,
      "loss": 0.6036,
      "step": 17376
    },
    {
      "epoch": 0.5338064080115504,
      "grad_norm": 0.3705853819847107,
      "learning_rate": 1.671244451092902e-05,
      "loss": 0.5532,
      "step": 17377
    },
    {
      "epoch": 0.5338371271464996,
      "grad_norm": 0.36408179998397827,
      "learning_rate": 1.6712086280504865e-05,
      "loss": 0.5617,
      "step": 17378
    },
    {
      "epoch": 0.5338678462814487,
      "grad_norm": 0.35713061690330505,
      "learning_rate": 1.6711728034404165e-05,
      "loss": 0.6148,
      "step": 17379
    },
    {
      "epoch": 0.5338985654163979,
      "grad_norm": 0.3740946650505066,
      "learning_rate": 1.6711369772627756e-05,
      "loss": 0.5139,
      "step": 17380
    },
    {
      "epoch": 0.533929284551347,
      "grad_norm": 0.38650232553482056,
      "learning_rate": 1.671101149517647e-05,
      "loss": 0.497,
      "step": 17381
    },
    {
      "epoch": 0.5339600036862961,
      "grad_norm": 0.3612997531890869,
      "learning_rate": 1.6710653202051152e-05,
      "loss": 0.6006,
      "step": 17382
    },
    {
      "epoch": 0.5339907228212454,
      "grad_norm": 0.6732011437416077,
      "learning_rate": 1.671029489325263e-05,
      "loss": 0.548,
      "step": 17383
    },
    {
      "epoch": 0.5340214419561945,
      "grad_norm": 0.314237117767334,
      "learning_rate": 1.670993656878175e-05,
      "loss": 0.4935,
      "step": 17384
    },
    {
      "epoch": 0.5340521610911436,
      "grad_norm": 0.34440383315086365,
      "learning_rate": 1.670957822863934e-05,
      "loss": 0.5296,
      "step": 17385
    },
    {
      "epoch": 0.5340828802260928,
      "grad_norm": 0.33470332622528076,
      "learning_rate": 1.6709219872826247e-05,
      "loss": 0.5841,
      "step": 17386
    },
    {
      "epoch": 0.534113599361042,
      "grad_norm": 0.4175652861595154,
      "learning_rate": 1.67088615013433e-05,
      "loss": 0.5627,
      "step": 17387
    },
    {
      "epoch": 0.5341443184959912,
      "grad_norm": 0.36672502756118774,
      "learning_rate": 1.6708503114191337e-05,
      "loss": 0.583,
      "step": 17388
    },
    {
      "epoch": 0.5341750376309403,
      "grad_norm": 0.35693374276161194,
      "learning_rate": 1.6708144711371196e-05,
      "loss": 0.5674,
      "step": 17389
    },
    {
      "epoch": 0.5342057567658894,
      "grad_norm": 0.40570878982543945,
      "learning_rate": 1.670778629288372e-05,
      "loss": 0.5438,
      "step": 17390
    },
    {
      "epoch": 0.5342364759008387,
      "grad_norm": 0.37775933742523193,
      "learning_rate": 1.6707427858729733e-05,
      "loss": 0.5909,
      "step": 17391
    },
    {
      "epoch": 0.5342671950357878,
      "grad_norm": 0.4309457242488861,
      "learning_rate": 1.6707069408910085e-05,
      "loss": 0.5804,
      "step": 17392
    },
    {
      "epoch": 0.5342979141707369,
      "grad_norm": 0.3182259500026703,
      "learning_rate": 1.6706710943425606e-05,
      "loss": 0.5845,
      "step": 17393
    },
    {
      "epoch": 0.5343286333056861,
      "grad_norm": 0.4706096351146698,
      "learning_rate": 1.6706352462277137e-05,
      "loss": 0.6041,
      "step": 17394
    },
    {
      "epoch": 0.5343593524406353,
      "grad_norm": 0.3578329384326935,
      "learning_rate": 1.670599396546551e-05,
      "loss": 0.5897,
      "step": 17395
    },
    {
      "epoch": 0.5343900715755844,
      "grad_norm": 0.31993716955184937,
      "learning_rate": 1.6705635452991567e-05,
      "loss": 0.5523,
      "step": 17396
    },
    {
      "epoch": 0.5344207907105336,
      "grad_norm": 0.3375912308692932,
      "learning_rate": 1.6705276924856148e-05,
      "loss": 0.5023,
      "step": 17397
    },
    {
      "epoch": 0.5344515098454827,
      "grad_norm": 0.3382474482059479,
      "learning_rate": 1.670491838106008e-05,
      "loss": 0.5565,
      "step": 17398
    },
    {
      "epoch": 0.534482228980432,
      "grad_norm": 0.3502212166786194,
      "learning_rate": 1.6704559821604212e-05,
      "loss": 0.6227,
      "step": 17399
    },
    {
      "epoch": 0.5345129481153811,
      "grad_norm": 0.3692356050014496,
      "learning_rate": 1.6704201246489374e-05,
      "loss": 0.5695,
      "step": 17400
    },
    {
      "epoch": 0.5345436672503302,
      "grad_norm": 0.3879462778568268,
      "learning_rate": 1.6703842655716406e-05,
      "loss": 0.6345,
      "step": 17401
    },
    {
      "epoch": 0.5345743863852794,
      "grad_norm": 0.3533160090446472,
      "learning_rate": 1.670348404928615e-05,
      "loss": 0.5336,
      "step": 17402
    },
    {
      "epoch": 0.5346051055202286,
      "grad_norm": 0.32270899415016174,
      "learning_rate": 1.6703125427199435e-05,
      "loss": 0.5899,
      "step": 17403
    },
    {
      "epoch": 0.5346358246551777,
      "grad_norm": 0.3640224039554596,
      "learning_rate": 1.6702766789457098e-05,
      "loss": 0.5888,
      "step": 17404
    },
    {
      "epoch": 0.5346665437901269,
      "grad_norm": 0.34903961420059204,
      "learning_rate": 1.6702408136059986e-05,
      "loss": 0.5984,
      "step": 17405
    },
    {
      "epoch": 0.534697262925076,
      "grad_norm": 0.3514820337295532,
      "learning_rate": 1.670204946700893e-05,
      "loss": 0.5821,
      "step": 17406
    },
    {
      "epoch": 0.5347279820600251,
      "grad_norm": 0.3930802643299103,
      "learning_rate": 1.6701690782304772e-05,
      "loss": 0.542,
      "step": 17407
    },
    {
      "epoch": 0.5347587011949744,
      "grad_norm": 0.32450130581855774,
      "learning_rate": 1.6701332081948343e-05,
      "loss": 0.5566,
      "step": 17408
    },
    {
      "epoch": 0.5347894203299235,
      "grad_norm": 0.4071666896343231,
      "learning_rate": 1.670097336594049e-05,
      "loss": 0.5304,
      "step": 17409
    },
    {
      "epoch": 0.5348201394648727,
      "grad_norm": 0.33368319272994995,
      "learning_rate": 1.670061463428204e-05,
      "loss": 0.5804,
      "step": 17410
    },
    {
      "epoch": 0.5348508585998218,
      "grad_norm": 0.40081658959388733,
      "learning_rate": 1.670025588697384e-05,
      "loss": 0.6111,
      "step": 17411
    },
    {
      "epoch": 0.534881577734771,
      "grad_norm": 0.31729602813720703,
      "learning_rate": 1.6699897124016724e-05,
      "loss": 0.5012,
      "step": 17412
    },
    {
      "epoch": 0.5349122968697202,
      "grad_norm": 0.3350316882133484,
      "learning_rate": 1.669953834541153e-05,
      "loss": 0.5719,
      "step": 17413
    },
    {
      "epoch": 0.5349430160046693,
      "grad_norm": 0.32096046209335327,
      "learning_rate": 1.6699179551159098e-05,
      "loss": 0.4632,
      "step": 17414
    },
    {
      "epoch": 0.5349737351396184,
      "grad_norm": 0.3821983337402344,
      "learning_rate": 1.6698820741260262e-05,
      "loss": 0.523,
      "step": 17415
    },
    {
      "epoch": 0.5350044542745677,
      "grad_norm": 0.3619576096534729,
      "learning_rate": 1.6698461915715863e-05,
      "loss": 0.6406,
      "step": 17416
    },
    {
      "epoch": 0.5350351734095168,
      "grad_norm": 0.30501607060432434,
      "learning_rate": 1.669810307452674e-05,
      "loss": 0.515,
      "step": 17417
    },
    {
      "epoch": 0.5350658925444659,
      "grad_norm": 0.362920343875885,
      "learning_rate": 1.6697744217693727e-05,
      "loss": 0.5741,
      "step": 17418
    },
    {
      "epoch": 0.5350966116794151,
      "grad_norm": 0.36480507254600525,
      "learning_rate": 1.6697385345217666e-05,
      "loss": 0.561,
      "step": 17419
    },
    {
      "epoch": 0.5351273308143643,
      "grad_norm": 0.34038621187210083,
      "learning_rate": 1.6697026457099396e-05,
      "loss": 0.4985,
      "step": 17420
    },
    {
      "epoch": 0.5351580499493134,
      "grad_norm": 0.34532275795936584,
      "learning_rate": 1.669666755333975e-05,
      "loss": 0.5668,
      "step": 17421
    },
    {
      "epoch": 0.5351887690842626,
      "grad_norm": 0.3461824059486389,
      "learning_rate": 1.6696308633939566e-05,
      "loss": 0.5896,
      "step": 17422
    },
    {
      "epoch": 0.5352194882192117,
      "grad_norm": 0.31141337752342224,
      "learning_rate": 1.669594969889969e-05,
      "loss": 0.5509,
      "step": 17423
    },
    {
      "epoch": 0.535250207354161,
      "grad_norm": 0.3643421232700348,
      "learning_rate": 1.6695590748220953e-05,
      "loss": 0.5943,
      "step": 17424
    },
    {
      "epoch": 0.5352809264891101,
      "grad_norm": 0.35991278290748596,
      "learning_rate": 1.66952317819042e-05,
      "loss": 0.6218,
      "step": 17425
    },
    {
      "epoch": 0.5353116456240592,
      "grad_norm": 0.3475857973098755,
      "learning_rate": 1.6694872799950267e-05,
      "loss": 0.5424,
      "step": 17426
    },
    {
      "epoch": 0.5353423647590084,
      "grad_norm": 0.34299635887145996,
      "learning_rate": 1.6694513802359985e-05,
      "loss": 0.5528,
      "step": 17427
    },
    {
      "epoch": 0.5353730838939575,
      "grad_norm": 0.3556605577468872,
      "learning_rate": 1.66941547891342e-05,
      "loss": 0.5862,
      "step": 17428
    },
    {
      "epoch": 0.5354038030289067,
      "grad_norm": 0.35763034224510193,
      "learning_rate": 1.6693795760273753e-05,
      "loss": 0.504,
      "step": 17429
    },
    {
      "epoch": 0.5354345221638559,
      "grad_norm": 0.3220345377922058,
      "learning_rate": 1.6693436715779473e-05,
      "loss": 0.5525,
      "step": 17430
    },
    {
      "epoch": 0.535465241298805,
      "grad_norm": 0.36392125487327576,
      "learning_rate": 1.6693077655652207e-05,
      "loss": 0.6029,
      "step": 17431
    },
    {
      "epoch": 0.5354959604337541,
      "grad_norm": 0.36986324191093445,
      "learning_rate": 1.669271857989279e-05,
      "loss": 0.6288,
      "step": 17432
    },
    {
      "epoch": 0.5355266795687034,
      "grad_norm": 0.34235048294067383,
      "learning_rate": 1.6692359488502062e-05,
      "loss": 0.4214,
      "step": 17433
    },
    {
      "epoch": 0.5355573987036525,
      "grad_norm": 0.32794204354286194,
      "learning_rate": 1.6692000381480863e-05,
      "loss": 0.5649,
      "step": 17434
    },
    {
      "epoch": 0.5355881178386017,
      "grad_norm": 0.3520791530609131,
      "learning_rate": 1.6691641258830026e-05,
      "loss": 0.5238,
      "step": 17435
    },
    {
      "epoch": 0.5356188369735508,
      "grad_norm": 0.31993839144706726,
      "learning_rate": 1.6691282120550395e-05,
      "loss": 0.4927,
      "step": 17436
    },
    {
      "epoch": 0.5356495561085,
      "grad_norm": 0.3604786992073059,
      "learning_rate": 1.669092296664281e-05,
      "loss": 0.5346,
      "step": 17437
    },
    {
      "epoch": 0.5356802752434492,
      "grad_norm": 0.42127901315689087,
      "learning_rate": 1.6690563797108105e-05,
      "loss": 0.5127,
      "step": 17438
    },
    {
      "epoch": 0.5357109943783983,
      "grad_norm": 0.3421512246131897,
      "learning_rate": 1.6690204611947117e-05,
      "loss": 0.6,
      "step": 17439
    },
    {
      "epoch": 0.5357417135133474,
      "grad_norm": 0.32104647159576416,
      "learning_rate": 1.6689845411160696e-05,
      "loss": 0.5328,
      "step": 17440
    },
    {
      "epoch": 0.5357724326482967,
      "grad_norm": 0.3563134968280792,
      "learning_rate": 1.6689486194749668e-05,
      "loss": 0.6145,
      "step": 17441
    },
    {
      "epoch": 0.5358031517832458,
      "grad_norm": 0.3526926338672638,
      "learning_rate": 1.668912696271488e-05,
      "loss": 0.6114,
      "step": 17442
    },
    {
      "epoch": 0.5358338709181949,
      "grad_norm": 0.33706140518188477,
      "learning_rate": 1.668876771505717e-05,
      "loss": 0.6081,
      "step": 17443
    },
    {
      "epoch": 0.5358645900531441,
      "grad_norm": 0.4655609726905823,
      "learning_rate": 1.6688408451777375e-05,
      "loss": 0.5956,
      "step": 17444
    },
    {
      "epoch": 0.5358953091880932,
      "grad_norm": 0.3340607285499573,
      "learning_rate": 1.6688049172876332e-05,
      "loss": 0.5971,
      "step": 17445
    },
    {
      "epoch": 0.5359260283230424,
      "grad_norm": 0.34313178062438965,
      "learning_rate": 1.6687689878354887e-05,
      "loss": 0.5317,
      "step": 17446
    },
    {
      "epoch": 0.5359567474579916,
      "grad_norm": 0.3619050681591034,
      "learning_rate": 1.6687330568213876e-05,
      "loss": 0.6113,
      "step": 17447
    },
    {
      "epoch": 0.5359874665929407,
      "grad_norm": 0.38130950927734375,
      "learning_rate": 1.6686971242454133e-05,
      "loss": 0.6176,
      "step": 17448
    },
    {
      "epoch": 0.53601818572789,
      "grad_norm": 0.34545356035232544,
      "learning_rate": 1.6686611901076503e-05,
      "loss": 0.5687,
      "step": 17449
    },
    {
      "epoch": 0.5360489048628391,
      "grad_norm": 0.4210030436515808,
      "learning_rate": 1.6686252544081827e-05,
      "loss": 0.5981,
      "step": 17450
    },
    {
      "epoch": 0.5360796239977882,
      "grad_norm": 0.3470647633075714,
      "learning_rate": 1.668589317147094e-05,
      "loss": 0.5464,
      "step": 17451
    },
    {
      "epoch": 0.5361103431327374,
      "grad_norm": 0.37976348400115967,
      "learning_rate": 1.668553378324468e-05,
      "loss": 0.5376,
      "step": 17452
    },
    {
      "epoch": 0.5361410622676865,
      "grad_norm": 0.32590770721435547,
      "learning_rate": 1.668517437940389e-05,
      "loss": 0.5874,
      "step": 17453
    },
    {
      "epoch": 0.5361717814026357,
      "grad_norm": 0.3775072991847992,
      "learning_rate": 1.668481495994941e-05,
      "loss": 0.5365,
      "step": 17454
    },
    {
      "epoch": 0.5362025005375849,
      "grad_norm": 0.39779552817344666,
      "learning_rate": 1.6684455524882078e-05,
      "loss": 0.6436,
      "step": 17455
    },
    {
      "epoch": 0.536233219672534,
      "grad_norm": 0.3469092845916748,
      "learning_rate": 1.668409607420273e-05,
      "loss": 0.5604,
      "step": 17456
    },
    {
      "epoch": 0.5362639388074831,
      "grad_norm": 0.3661600649356842,
      "learning_rate": 1.668373660791221e-05,
      "loss": 0.5934,
      "step": 17457
    },
    {
      "epoch": 0.5362946579424324,
      "grad_norm": 0.34565863013267517,
      "learning_rate": 1.668337712601136e-05,
      "loss": 0.5968,
      "step": 17458
    },
    {
      "epoch": 0.5363253770773815,
      "grad_norm": 0.33999308943748474,
      "learning_rate": 1.6683017628501014e-05,
      "loss": 0.5569,
      "step": 17459
    },
    {
      "epoch": 0.5363560962123307,
      "grad_norm": 0.34559324383735657,
      "learning_rate": 1.6682658115382012e-05,
      "loss": 0.5448,
      "step": 17460
    },
    {
      "epoch": 0.5363868153472798,
      "grad_norm": 0.3643296957015991,
      "learning_rate": 1.6682298586655198e-05,
      "loss": 0.631,
      "step": 17461
    },
    {
      "epoch": 0.536417534482229,
      "grad_norm": 0.33204761147499084,
      "learning_rate": 1.6681939042321405e-05,
      "loss": 0.5426,
      "step": 17462
    },
    {
      "epoch": 0.5364482536171782,
      "grad_norm": 0.3624633550643921,
      "learning_rate": 1.668157948238148e-05,
      "loss": 0.5699,
      "step": 17463
    },
    {
      "epoch": 0.5364789727521273,
      "grad_norm": 0.3800508379936218,
      "learning_rate": 1.6681219906836256e-05,
      "loss": 0.5481,
      "step": 17464
    },
    {
      "epoch": 0.5365096918870764,
      "grad_norm": 0.3647020161151886,
      "learning_rate": 1.668086031568658e-05,
      "loss": 0.5046,
      "step": 17465
    },
    {
      "epoch": 0.5365404110220257,
      "grad_norm": 0.37407469749450684,
      "learning_rate": 1.6680500708933286e-05,
      "loss": 0.5804,
      "step": 17466
    },
    {
      "epoch": 0.5365711301569748,
      "grad_norm": 0.3517841398715973,
      "learning_rate": 1.6680141086577215e-05,
      "loss": 0.501,
      "step": 17467
    },
    {
      "epoch": 0.5366018492919239,
      "grad_norm": 0.35199084877967834,
      "learning_rate": 1.667978144861921e-05,
      "loss": 0.5736,
      "step": 17468
    },
    {
      "epoch": 0.5366325684268731,
      "grad_norm": 0.37125641107559204,
      "learning_rate": 1.6679421795060113e-05,
      "loss": 0.4839,
      "step": 17469
    },
    {
      "epoch": 0.5366632875618222,
      "grad_norm": 0.32552993297576904,
      "learning_rate": 1.6679062125900755e-05,
      "loss": 0.5487,
      "step": 17470
    },
    {
      "epoch": 0.5366940066967714,
      "grad_norm": 0.34504759311676025,
      "learning_rate": 1.667870244114198e-05,
      "loss": 0.5211,
      "step": 17471
    },
    {
      "epoch": 0.5367247258317206,
      "grad_norm": 0.3499925136566162,
      "learning_rate": 1.6678342740784628e-05,
      "loss": 0.5728,
      "step": 17472
    },
    {
      "epoch": 0.5367554449666697,
      "grad_norm": 0.34153813123703003,
      "learning_rate": 1.6677983024829543e-05,
      "loss": 0.5588,
      "step": 17473
    },
    {
      "epoch": 0.536786164101619,
      "grad_norm": 0.34554675221443176,
      "learning_rate": 1.6677623293277562e-05,
      "loss": 0.6038,
      "step": 17474
    },
    {
      "epoch": 0.5368168832365681,
      "grad_norm": 0.4533258378505707,
      "learning_rate": 1.6677263546129527e-05,
      "loss": 0.5079,
      "step": 17475
    },
    {
      "epoch": 0.5368476023715172,
      "grad_norm": 0.7510029673576355,
      "learning_rate": 1.6676903783386276e-05,
      "loss": 0.5578,
      "step": 17476
    },
    {
      "epoch": 0.5368783215064664,
      "grad_norm": 0.34514036774635315,
      "learning_rate": 1.6676544005048647e-05,
      "loss": 0.5506,
      "step": 17477
    },
    {
      "epoch": 0.5369090406414155,
      "grad_norm": 0.3369775712490082,
      "learning_rate": 1.6676184211117484e-05,
      "loss": 0.602,
      "step": 17478
    },
    {
      "epoch": 0.5369397597763647,
      "grad_norm": 0.4107666611671448,
      "learning_rate": 1.667582440159363e-05,
      "loss": 0.5674,
      "step": 17479
    },
    {
      "epoch": 0.5369704789113139,
      "grad_norm": 0.3495771884918213,
      "learning_rate": 1.667546457647792e-05,
      "loss": 0.5497,
      "step": 17480
    },
    {
      "epoch": 0.537001198046263,
      "grad_norm": 0.42126885056495667,
      "learning_rate": 1.6675104735771195e-05,
      "loss": 0.626,
      "step": 17481
    },
    {
      "epoch": 0.5370319171812121,
      "grad_norm": 0.33243638277053833,
      "learning_rate": 1.6674744879474297e-05,
      "loss": 0.5235,
      "step": 17482
    },
    {
      "epoch": 0.5370626363161614,
      "grad_norm": 0.3541898727416992,
      "learning_rate": 1.6674385007588066e-05,
      "loss": 0.553,
      "step": 17483
    },
    {
      "epoch": 0.5370933554511105,
      "grad_norm": 0.5091285109519958,
      "learning_rate": 1.6674025120113343e-05,
      "loss": 0.647,
      "step": 17484
    },
    {
      "epoch": 0.5371240745860597,
      "grad_norm": 0.35725879669189453,
      "learning_rate": 1.667366521705097e-05,
      "loss": 0.4944,
      "step": 17485
    },
    {
      "epoch": 0.5371547937210088,
      "grad_norm": 0.3168172538280487,
      "learning_rate": 1.667330529840178e-05,
      "loss": 0.5639,
      "step": 17486
    },
    {
      "epoch": 0.537185512855958,
      "grad_norm": 0.4096253216266632,
      "learning_rate": 1.6672945364166627e-05,
      "loss": 0.4721,
      "step": 17487
    },
    {
      "epoch": 0.5372162319909072,
      "grad_norm": 0.34546902775764465,
      "learning_rate": 1.667258541434634e-05,
      "loss": 0.5996,
      "step": 17488
    },
    {
      "epoch": 0.5372469511258563,
      "grad_norm": 0.35846972465515137,
      "learning_rate": 1.6672225448941764e-05,
      "loss": 0.6337,
      "step": 17489
    },
    {
      "epoch": 0.5372776702608054,
      "grad_norm": 0.4331517517566681,
      "learning_rate": 1.667186546795374e-05,
      "loss": 0.5017,
      "step": 17490
    },
    {
      "epoch": 0.5373083893957546,
      "grad_norm": 0.33076971769332886,
      "learning_rate": 1.667150547138311e-05,
      "loss": 0.6222,
      "step": 17491
    },
    {
      "epoch": 0.5373391085307038,
      "grad_norm": 0.3383631110191345,
      "learning_rate": 1.667114545923071e-05,
      "loss": 0.614,
      "step": 17492
    },
    {
      "epoch": 0.5373698276656529,
      "grad_norm": 0.32763010263442993,
      "learning_rate": 1.6670785431497386e-05,
      "loss": 0.5599,
      "step": 17493
    },
    {
      "epoch": 0.5374005468006021,
      "grad_norm": 0.7026676535606384,
      "learning_rate": 1.6670425388183975e-05,
      "loss": 0.6055,
      "step": 17494
    },
    {
      "epoch": 0.5374312659355512,
      "grad_norm": 0.346204549074173,
      "learning_rate": 1.667006532929132e-05,
      "loss": 0.4517,
      "step": 17495
    },
    {
      "epoch": 0.5374619850705005,
      "grad_norm": 0.3904145658016205,
      "learning_rate": 1.6669705254820265e-05,
      "loss": 0.5446,
      "step": 17496
    },
    {
      "epoch": 0.5374927042054496,
      "grad_norm": 0.3680364787578583,
      "learning_rate": 1.6669345164771645e-05,
      "loss": 0.5923,
      "step": 17497
    },
    {
      "epoch": 0.5375234233403987,
      "grad_norm": 0.3575509190559387,
      "learning_rate": 1.66689850591463e-05,
      "loss": 0.5699,
      "step": 17498
    },
    {
      "epoch": 0.5375541424753479,
      "grad_norm": 0.3986164331436157,
      "learning_rate": 1.6668624937945082e-05,
      "loss": 0.5695,
      "step": 17499
    },
    {
      "epoch": 0.5375848616102971,
      "grad_norm": 0.43428489565849304,
      "learning_rate": 1.666826480116882e-05,
      "loss": 0.5459,
      "step": 17500
    },
    {
      "epoch": 0.5376155807452462,
      "grad_norm": 0.48966655135154724,
      "learning_rate": 1.6667904648818362e-05,
      "loss": 0.554,
      "step": 17501
    },
    {
      "epoch": 0.5376462998801954,
      "grad_norm": 0.4934186339378357,
      "learning_rate": 1.6667544480894543e-05,
      "loss": 0.4671,
      "step": 17502
    },
    {
      "epoch": 0.5376770190151445,
      "grad_norm": 0.33992844820022583,
      "learning_rate": 1.6667184297398213e-05,
      "loss": 0.5838,
      "step": 17503
    },
    {
      "epoch": 0.5377077381500937,
      "grad_norm": 0.3237183392047882,
      "learning_rate": 1.66668240983302e-05,
      "loss": 0.6286,
      "step": 17504
    },
    {
      "epoch": 0.5377384572850429,
      "grad_norm": 0.3196732699871063,
      "learning_rate": 1.666646388369136e-05,
      "loss": 0.4761,
      "step": 17505
    },
    {
      "epoch": 0.537769176419992,
      "grad_norm": 0.3409876823425293,
      "learning_rate": 1.6666103653482532e-05,
      "loss": 0.5837,
      "step": 17506
    },
    {
      "epoch": 0.5377998955549411,
      "grad_norm": 0.36396101117134094,
      "learning_rate": 1.666574340770455e-05,
      "loss": 0.4895,
      "step": 17507
    },
    {
      "epoch": 0.5378306146898904,
      "grad_norm": 0.34790855646133423,
      "learning_rate": 1.6665383146358255e-05,
      "loss": 0.5399,
      "step": 17508
    },
    {
      "epoch": 0.5378613338248395,
      "grad_norm": 0.3589848577976227,
      "learning_rate": 1.6665022869444494e-05,
      "loss": 0.5682,
      "step": 17509
    },
    {
      "epoch": 0.5378920529597887,
      "grad_norm": 0.3531658947467804,
      "learning_rate": 1.666466257696411e-05,
      "loss": 0.5612,
      "step": 17510
    },
    {
      "epoch": 0.5379227720947378,
      "grad_norm": 0.33020463585853577,
      "learning_rate": 1.666430226891794e-05,
      "loss": 0.4518,
      "step": 17511
    },
    {
      "epoch": 0.5379534912296869,
      "grad_norm": 0.3554821014404297,
      "learning_rate": 1.6663941945306825e-05,
      "loss": 0.5995,
      "step": 17512
    },
    {
      "epoch": 0.5379842103646362,
      "grad_norm": 0.3487411439418793,
      "learning_rate": 1.666358160613161e-05,
      "loss": 0.6267,
      "step": 17513
    },
    {
      "epoch": 0.5380149294995853,
      "grad_norm": 0.524196445941925,
      "learning_rate": 1.6663221251393135e-05,
      "loss": 0.6397,
      "step": 17514
    },
    {
      "epoch": 0.5380456486345344,
      "grad_norm": 0.3321971893310547,
      "learning_rate": 1.6662860881092237e-05,
      "loss": 0.5723,
      "step": 17515
    },
    {
      "epoch": 0.5380763677694836,
      "grad_norm": 0.3662353754043579,
      "learning_rate": 1.6662500495229764e-05,
      "loss": 0.5746,
      "step": 17516
    },
    {
      "epoch": 0.5381070869044328,
      "grad_norm": 0.39048105478286743,
      "learning_rate": 1.6662140093806558e-05,
      "loss": 0.5846,
      "step": 17517
    },
    {
      "epoch": 0.5381378060393819,
      "grad_norm": 0.3405389189720154,
      "learning_rate": 1.6661779676823458e-05,
      "loss": 0.5822,
      "step": 17518
    },
    {
      "epoch": 0.5381685251743311,
      "grad_norm": 0.36540213227272034,
      "learning_rate": 1.6661419244281305e-05,
      "loss": 0.5826,
      "step": 17519
    },
    {
      "epoch": 0.5381992443092802,
      "grad_norm": 0.4035775363445282,
      "learning_rate": 1.6661058796180945e-05,
      "loss": 0.5623,
      "step": 17520
    },
    {
      "epoch": 0.5382299634442295,
      "grad_norm": 0.3582201600074768,
      "learning_rate": 1.6660698332523213e-05,
      "loss": 0.4953,
      "step": 17521
    },
    {
      "epoch": 0.5382606825791786,
      "grad_norm": 0.35023367404937744,
      "learning_rate": 1.6660337853308958e-05,
      "loss": 0.5562,
      "step": 17522
    },
    {
      "epoch": 0.5382914017141277,
      "grad_norm": 0.33650290966033936,
      "learning_rate": 1.6659977358539014e-05,
      "loss": 0.5495,
      "step": 17523
    },
    {
      "epoch": 0.5383221208490769,
      "grad_norm": 0.39224186539649963,
      "learning_rate": 1.6659616848214232e-05,
      "loss": 0.5281,
      "step": 17524
    },
    {
      "epoch": 0.538352839984026,
      "grad_norm": 0.35957908630371094,
      "learning_rate": 1.665925632233545e-05,
      "loss": 0.5671,
      "step": 17525
    },
    {
      "epoch": 0.5383835591189752,
      "grad_norm": 0.4133070707321167,
      "learning_rate": 1.6658895780903507e-05,
      "loss": 0.4645,
      "step": 17526
    },
    {
      "epoch": 0.5384142782539244,
      "grad_norm": 0.4309268891811371,
      "learning_rate": 1.665853522391925e-05,
      "loss": 0.6573,
      "step": 17527
    },
    {
      "epoch": 0.5384449973888735,
      "grad_norm": 0.3621964454650879,
      "learning_rate": 1.665817465138352e-05,
      "loss": 0.5604,
      "step": 17528
    },
    {
      "epoch": 0.5384757165238226,
      "grad_norm": 0.4107750952243805,
      "learning_rate": 1.6657814063297156e-05,
      "loss": 0.5961,
      "step": 17529
    },
    {
      "epoch": 0.5385064356587719,
      "grad_norm": 0.3455018699169159,
      "learning_rate": 1.6657453459661e-05,
      "loss": 0.5542,
      "step": 17530
    },
    {
      "epoch": 0.538537154793721,
      "grad_norm": 0.4200392961502075,
      "learning_rate": 1.66570928404759e-05,
      "loss": 0.5926,
      "step": 17531
    },
    {
      "epoch": 0.5385678739286701,
      "grad_norm": 0.35290437936782837,
      "learning_rate": 1.6656732205742697e-05,
      "loss": 0.5816,
      "step": 17532
    },
    {
      "epoch": 0.5385985930636193,
      "grad_norm": 0.34654656052589417,
      "learning_rate": 1.6656371555462227e-05,
      "loss": 0.5928,
      "step": 17533
    },
    {
      "epoch": 0.5386293121985685,
      "grad_norm": 2.0377073287963867,
      "learning_rate": 1.6656010889635335e-05,
      "loss": 0.5839,
      "step": 17534
    },
    {
      "epoch": 0.5386600313335177,
      "grad_norm": 0.37239354848861694,
      "learning_rate": 1.665565020826287e-05,
      "loss": 0.4912,
      "step": 17535
    },
    {
      "epoch": 0.5386907504684668,
      "grad_norm": 0.3409408926963806,
      "learning_rate": 1.6655289511345665e-05,
      "loss": 0.471,
      "step": 17536
    },
    {
      "epoch": 0.5387214696034159,
      "grad_norm": 0.3470422327518463,
      "learning_rate": 1.6654928798884568e-05,
      "loss": 0.5386,
      "step": 17537
    },
    {
      "epoch": 0.5387521887383652,
      "grad_norm": 0.4229872226715088,
      "learning_rate": 1.6654568070880422e-05,
      "loss": 0.5376,
      "step": 17538
    },
    {
      "epoch": 0.5387829078733143,
      "grad_norm": 0.4485396444797516,
      "learning_rate": 1.6654207327334063e-05,
      "loss": 0.5555,
      "step": 17539
    },
    {
      "epoch": 0.5388136270082634,
      "grad_norm": 0.351500004529953,
      "learning_rate": 1.665384656824634e-05,
      "loss": 0.5435,
      "step": 17540
    },
    {
      "epoch": 0.5388443461432126,
      "grad_norm": 0.38810205459594727,
      "learning_rate": 1.6653485793618096e-05,
      "loss": 0.4844,
      "step": 17541
    },
    {
      "epoch": 0.5388750652781618,
      "grad_norm": 0.36079293489456177,
      "learning_rate": 1.665312500345017e-05,
      "loss": 0.5946,
      "step": 17542
    },
    {
      "epoch": 0.5389057844131109,
      "grad_norm": 0.34850555658340454,
      "learning_rate": 1.66527641977434e-05,
      "loss": 0.5332,
      "step": 17543
    },
    {
      "epoch": 0.5389365035480601,
      "grad_norm": 0.40027981996536255,
      "learning_rate": 1.6652403376498642e-05,
      "loss": 0.5993,
      "step": 17544
    },
    {
      "epoch": 0.5389672226830092,
      "grad_norm": 0.40111109614372253,
      "learning_rate": 1.665204253971673e-05,
      "loss": 0.6055,
      "step": 17545
    },
    {
      "epoch": 0.5389979418179585,
      "grad_norm": 0.3748756945133209,
      "learning_rate": 1.665168168739851e-05,
      "loss": 0.5875,
      "step": 17546
    },
    {
      "epoch": 0.5390286609529076,
      "grad_norm": 0.3782269358634949,
      "learning_rate": 1.665132081954482e-05,
      "loss": 0.5531,
      "step": 17547
    },
    {
      "epoch": 0.5390593800878567,
      "grad_norm": 0.32752782106399536,
      "learning_rate": 1.6650959936156502e-05,
      "loss": 0.5649,
      "step": 17548
    },
    {
      "epoch": 0.5390900992228059,
      "grad_norm": 0.32788509130477905,
      "learning_rate": 1.665059903723441e-05,
      "loss": 0.5965,
      "step": 17549
    },
    {
      "epoch": 0.539120818357755,
      "grad_norm": 0.37002843618392944,
      "learning_rate": 1.6650238122779373e-05,
      "loss": 0.6153,
      "step": 17550
    },
    {
      "epoch": 0.5391515374927042,
      "grad_norm": 0.3457208275794983,
      "learning_rate": 1.6649877192792243e-05,
      "loss": 0.5623,
      "step": 17551
    },
    {
      "epoch": 0.5391822566276534,
      "grad_norm": 0.35760167241096497,
      "learning_rate": 1.664951624727386e-05,
      "loss": 0.545,
      "step": 17552
    },
    {
      "epoch": 0.5392129757626025,
      "grad_norm": 0.37083151936531067,
      "learning_rate": 1.664915528622507e-05,
      "loss": 0.5938,
      "step": 17553
    },
    {
      "epoch": 0.5392436948975516,
      "grad_norm": 0.3456827998161316,
      "learning_rate": 1.6648794309646713e-05,
      "loss": 0.5543,
      "step": 17554
    },
    {
      "epoch": 0.5392744140325009,
      "grad_norm": 0.34073343873023987,
      "learning_rate": 1.664843331753963e-05,
      "loss": 0.5595,
      "step": 17555
    },
    {
      "epoch": 0.53930513316745,
      "grad_norm": 0.35285404324531555,
      "learning_rate": 1.6648072309904667e-05,
      "loss": 0.5677,
      "step": 17556
    },
    {
      "epoch": 0.5393358523023991,
      "grad_norm": 0.366821825504303,
      "learning_rate": 1.664771128674267e-05,
      "loss": 0.6053,
      "step": 17557
    },
    {
      "epoch": 0.5393665714373483,
      "grad_norm": 0.41547510027885437,
      "learning_rate": 1.6647350248054475e-05,
      "loss": 0.664,
      "step": 17558
    },
    {
      "epoch": 0.5393972905722975,
      "grad_norm": 0.38729190826416016,
      "learning_rate": 1.664698919384093e-05,
      "loss": 0.569,
      "step": 17559
    },
    {
      "epoch": 0.5394280097072467,
      "grad_norm": 0.34708932042121887,
      "learning_rate": 1.664662812410288e-05,
      "loss": 0.567,
      "step": 17560
    },
    {
      "epoch": 0.5394587288421958,
      "grad_norm": 0.3449181020259857,
      "learning_rate": 1.6646267038841163e-05,
      "loss": 0.5653,
      "step": 17561
    },
    {
      "epoch": 0.5394894479771449,
      "grad_norm": 0.35874566435813904,
      "learning_rate": 1.6645905938056625e-05,
      "loss": 0.5953,
      "step": 17562
    },
    {
      "epoch": 0.5395201671120942,
      "grad_norm": 0.44349902868270874,
      "learning_rate": 1.664554482175011e-05,
      "loss": 0.5746,
      "step": 17563
    },
    {
      "epoch": 0.5395508862470433,
      "grad_norm": 0.3381945788860321,
      "learning_rate": 1.6645183689922465e-05,
      "loss": 0.6157,
      "step": 17564
    },
    {
      "epoch": 0.5395816053819924,
      "grad_norm": 0.3923344910144806,
      "learning_rate": 1.6644822542574527e-05,
      "loss": 0.5819,
      "step": 17565
    },
    {
      "epoch": 0.5396123245169416,
      "grad_norm": 0.3672839105129242,
      "learning_rate": 1.664446137970714e-05,
      "loss": 0.4886,
      "step": 17566
    },
    {
      "epoch": 0.5396430436518908,
      "grad_norm": 0.4246094524860382,
      "learning_rate": 1.664410020132115e-05,
      "loss": 0.5741,
      "step": 17567
    },
    {
      "epoch": 0.5396737627868399,
      "grad_norm": 0.35157305002212524,
      "learning_rate": 1.6643739007417398e-05,
      "loss": 0.53,
      "step": 17568
    },
    {
      "epoch": 0.5397044819217891,
      "grad_norm": 0.34374549984931946,
      "learning_rate": 1.6643377797996737e-05,
      "loss": 0.5002,
      "step": 17569
    },
    {
      "epoch": 0.5397352010567382,
      "grad_norm": 0.3689754605293274,
      "learning_rate": 1.6643016573059995e-05,
      "loss": 0.4104,
      "step": 17570
    },
    {
      "epoch": 0.5397659201916875,
      "grad_norm": 0.3624507784843445,
      "learning_rate": 1.6642655332608025e-05,
      "loss": 0.6544,
      "step": 17571
    },
    {
      "epoch": 0.5397966393266366,
      "grad_norm": 0.4240308701992035,
      "learning_rate": 1.6642294076641674e-05,
      "loss": 0.5501,
      "step": 17572
    },
    {
      "epoch": 0.5398273584615857,
      "grad_norm": 0.32863783836364746,
      "learning_rate": 1.664193280516178e-05,
      "loss": 0.5269,
      "step": 17573
    },
    {
      "epoch": 0.5398580775965349,
      "grad_norm": 0.34537166357040405,
      "learning_rate": 1.6641571518169187e-05,
      "loss": 0.4673,
      "step": 17574
    },
    {
      "epoch": 0.539888796731484,
      "grad_norm": 0.36700010299682617,
      "learning_rate": 1.664121021566474e-05,
      "loss": 0.6223,
      "step": 17575
    },
    {
      "epoch": 0.5399195158664332,
      "grad_norm": 0.402723491191864,
      "learning_rate": 1.664084889764928e-05,
      "loss": 0.5851,
      "step": 17576
    },
    {
      "epoch": 0.5399502350013824,
      "grad_norm": 0.3402990996837616,
      "learning_rate": 1.6640487564123654e-05,
      "loss": 0.6047,
      "step": 17577
    },
    {
      "epoch": 0.5399809541363315,
      "grad_norm": 0.37228086590766907,
      "learning_rate": 1.664012621508871e-05,
      "loss": 0.5643,
      "step": 17578
    },
    {
      "epoch": 0.5400116732712806,
      "grad_norm": 0.3415141999721527,
      "learning_rate": 1.6639764850545286e-05,
      "loss": 0.549,
      "step": 17579
    },
    {
      "epoch": 0.5400423924062299,
      "grad_norm": 0.34738689661026,
      "learning_rate": 1.6639403470494225e-05,
      "loss": 0.5962,
      "step": 17580
    },
    {
      "epoch": 0.540073111541179,
      "grad_norm": 0.42042967677116394,
      "learning_rate": 1.6639042074936377e-05,
      "loss": 0.6317,
      "step": 17581
    },
    {
      "epoch": 0.5401038306761281,
      "grad_norm": 0.37628498673439026,
      "learning_rate": 1.6638680663872578e-05,
      "loss": 0.6049,
      "step": 17582
    },
    {
      "epoch": 0.5401345498110773,
      "grad_norm": 0.33361613750457764,
      "learning_rate": 1.6638319237303685e-05,
      "loss": 0.5497,
      "step": 17583
    },
    {
      "epoch": 0.5401652689460265,
      "grad_norm": 0.37521812319755554,
      "learning_rate": 1.6637957795230524e-05,
      "loss": 0.6509,
      "step": 17584
    },
    {
      "epoch": 0.5401959880809757,
      "grad_norm": 0.34697389602661133,
      "learning_rate": 1.6637596337653957e-05,
      "loss": 0.5503,
      "step": 17585
    },
    {
      "epoch": 0.5402267072159248,
      "grad_norm": 0.38327091932296753,
      "learning_rate": 1.6637234864574813e-05,
      "loss": 0.5747,
      "step": 17586
    },
    {
      "epoch": 0.5402574263508739,
      "grad_norm": 0.35492706298828125,
      "learning_rate": 1.6636873375993947e-05,
      "loss": 0.5662,
      "step": 17587
    },
    {
      "epoch": 0.5402881454858232,
      "grad_norm": 0.3484227657318115,
      "learning_rate": 1.66365118719122e-05,
      "loss": 0.4732,
      "step": 17588
    },
    {
      "epoch": 0.5403188646207723,
      "grad_norm": 0.36518797278404236,
      "learning_rate": 1.6636150352330417e-05,
      "loss": 0.6116,
      "step": 17589
    },
    {
      "epoch": 0.5403495837557214,
      "grad_norm": 0.38551533222198486,
      "learning_rate": 1.6635788817249437e-05,
      "loss": 0.663,
      "step": 17590
    },
    {
      "epoch": 0.5403803028906706,
      "grad_norm": 0.351563036441803,
      "learning_rate": 1.6635427266670113e-05,
      "loss": 0.5146,
      "step": 17591
    },
    {
      "epoch": 0.5404110220256197,
      "grad_norm": 0.3550795018672943,
      "learning_rate": 1.6635065700593287e-05,
      "loss": 0.5542,
      "step": 17592
    },
    {
      "epoch": 0.5404417411605689,
      "grad_norm": 0.3744320273399353,
      "learning_rate": 1.6634704119019794e-05,
      "loss": 0.6057,
      "step": 17593
    },
    {
      "epoch": 0.5404724602955181,
      "grad_norm": 0.36780059337615967,
      "learning_rate": 1.663434252195049e-05,
      "loss": 0.64,
      "step": 17594
    },
    {
      "epoch": 0.5405031794304672,
      "grad_norm": 0.40136444568634033,
      "learning_rate": 1.663398090938622e-05,
      "loss": 0.5192,
      "step": 17595
    },
    {
      "epoch": 0.5405338985654164,
      "grad_norm": 0.3708445131778717,
      "learning_rate": 1.663361928132782e-05,
      "loss": 0.5596,
      "step": 17596
    },
    {
      "epoch": 0.5405646177003656,
      "grad_norm": 0.325363427400589,
      "learning_rate": 1.663325763777614e-05,
      "loss": 0.5462,
      "step": 17597
    },
    {
      "epoch": 0.5405953368353147,
      "grad_norm": 0.3905683755874634,
      "learning_rate": 1.6632895978732023e-05,
      "loss": 0.6222,
      "step": 17598
    },
    {
      "epoch": 0.5406260559702639,
      "grad_norm": 0.36278441548347473,
      "learning_rate": 1.663253430419631e-05,
      "loss": 0.5249,
      "step": 17599
    },
    {
      "epoch": 0.540656775105213,
      "grad_norm": 0.514239490032196,
      "learning_rate": 1.6632172614169858e-05,
      "loss": 0.6539,
      "step": 17600
    },
    {
      "epoch": 0.5406874942401622,
      "grad_norm": 0.366150826215744,
      "learning_rate": 1.66318109086535e-05,
      "loss": 0.5673,
      "step": 17601
    },
    {
      "epoch": 0.5407182133751114,
      "grad_norm": 0.34579068422317505,
      "learning_rate": 1.6631449187648086e-05,
      "loss": 0.5865,
      "step": 17602
    },
    {
      "epoch": 0.5407489325100605,
      "grad_norm": 0.38088536262512207,
      "learning_rate": 1.6631087451154456e-05,
      "loss": 0.567,
      "step": 17603
    },
    {
      "epoch": 0.5407796516450096,
      "grad_norm": 0.4064445495605469,
      "learning_rate": 1.663072569917346e-05,
      "loss": 0.5694,
      "step": 17604
    },
    {
      "epoch": 0.5408103707799589,
      "grad_norm": 0.34901660680770874,
      "learning_rate": 1.6630363931705943e-05,
      "loss": 0.5515,
      "step": 17605
    },
    {
      "epoch": 0.540841089914908,
      "grad_norm": 0.38060522079467773,
      "learning_rate": 1.6630002148752745e-05,
      "loss": 0.4988,
      "step": 17606
    },
    {
      "epoch": 0.5408718090498572,
      "grad_norm": 0.3706704080104828,
      "learning_rate": 1.6629640350314714e-05,
      "loss": 0.5031,
      "step": 17607
    },
    {
      "epoch": 0.5409025281848063,
      "grad_norm": 0.3617754578590393,
      "learning_rate": 1.6629278536392694e-05,
      "loss": 0.5439,
      "step": 17608
    },
    {
      "epoch": 0.5409332473197555,
      "grad_norm": 0.4844091534614563,
      "learning_rate": 1.662891670698754e-05,
      "loss": 0.6969,
      "step": 17609
    },
    {
      "epoch": 0.5409639664547047,
      "grad_norm": 0.3364875018596649,
      "learning_rate": 1.6628554862100074e-05,
      "loss": 0.5,
      "step": 17610
    },
    {
      "epoch": 0.5409946855896538,
      "grad_norm": 0.34483766555786133,
      "learning_rate": 1.6628193001731165e-05,
      "loss": 0.57,
      "step": 17611
    },
    {
      "epoch": 0.5410254047246029,
      "grad_norm": 0.39760875701904297,
      "learning_rate": 1.6627831125881644e-05,
      "loss": 0.6504,
      "step": 17612
    },
    {
      "epoch": 0.5410561238595522,
      "grad_norm": 0.33580029010772705,
      "learning_rate": 1.6627469234552363e-05,
      "loss": 0.5689,
      "step": 17613
    },
    {
      "epoch": 0.5410868429945013,
      "grad_norm": 0.34415000677108765,
      "learning_rate": 1.662710732774416e-05,
      "loss": 0.5784,
      "step": 17614
    },
    {
      "epoch": 0.5411175621294504,
      "grad_norm": 0.35400399565696716,
      "learning_rate": 1.662674540545789e-05,
      "loss": 0.6165,
      "step": 17615
    },
    {
      "epoch": 0.5411482812643996,
      "grad_norm": 0.3292425274848938,
      "learning_rate": 1.6626383467694393e-05,
      "loss": 0.5407,
      "step": 17616
    },
    {
      "epoch": 0.5411790003993487,
      "grad_norm": 0.3426227867603302,
      "learning_rate": 1.6626021514454514e-05,
      "loss": 0.4984,
      "step": 17617
    },
    {
      "epoch": 0.5412097195342979,
      "grad_norm": 0.35087811946868896,
      "learning_rate": 1.6625659545739096e-05,
      "loss": 0.4484,
      "step": 17618
    },
    {
      "epoch": 0.5412404386692471,
      "grad_norm": 0.34681200981140137,
      "learning_rate": 1.6625297561548993e-05,
      "loss": 0.5283,
      "step": 17619
    },
    {
      "epoch": 0.5412711578041962,
      "grad_norm": 0.3534158170223236,
      "learning_rate": 1.662493556188504e-05,
      "loss": 0.5916,
      "step": 17620
    },
    {
      "epoch": 0.5413018769391454,
      "grad_norm": 0.3580128848552704,
      "learning_rate": 1.662457354674809e-05,
      "loss": 0.5068,
      "step": 17621
    },
    {
      "epoch": 0.5413325960740946,
      "grad_norm": 0.37682992219924927,
      "learning_rate": 1.6624211516138987e-05,
      "loss": 0.5656,
      "step": 17622
    },
    {
      "epoch": 0.5413633152090437,
      "grad_norm": 0.3845697343349457,
      "learning_rate": 1.662384947005857e-05,
      "loss": 0.5761,
      "step": 17623
    },
    {
      "epoch": 0.5413940343439929,
      "grad_norm": 0.397361695766449,
      "learning_rate": 1.6623487408507696e-05,
      "loss": 0.5401,
      "step": 17624
    },
    {
      "epoch": 0.541424753478942,
      "grad_norm": 0.39270031452178955,
      "learning_rate": 1.66231253314872e-05,
      "loss": 0.4891,
      "step": 17625
    },
    {
      "epoch": 0.5414554726138912,
      "grad_norm": 0.37781867384910583,
      "learning_rate": 1.6622763238997934e-05,
      "loss": 0.5915,
      "step": 17626
    },
    {
      "epoch": 0.5414861917488404,
      "grad_norm": 0.3806750774383545,
      "learning_rate": 1.6622401131040745e-05,
      "loss": 0.4639,
      "step": 17627
    },
    {
      "epoch": 0.5415169108837895,
      "grad_norm": 0.3516782224178314,
      "learning_rate": 1.662203900761647e-05,
      "loss": 0.6189,
      "step": 17628
    },
    {
      "epoch": 0.5415476300187386,
      "grad_norm": 0.36958298087120056,
      "learning_rate": 1.6621676868725964e-05,
      "loss": 0.6009,
      "step": 17629
    },
    {
      "epoch": 0.5415783491536879,
      "grad_norm": 0.3412788510322571,
      "learning_rate": 1.6621314714370066e-05,
      "loss": 0.5161,
      "step": 17630
    },
    {
      "epoch": 0.541609068288637,
      "grad_norm": 0.3584352135658264,
      "learning_rate": 1.662095254454963e-05,
      "loss": 0.6555,
      "step": 17631
    },
    {
      "epoch": 0.5416397874235862,
      "grad_norm": 0.3615007698535919,
      "learning_rate": 1.662059035926549e-05,
      "loss": 0.5179,
      "step": 17632
    },
    {
      "epoch": 0.5416705065585353,
      "grad_norm": 0.3270239531993866,
      "learning_rate": 1.6620228158518507e-05,
      "loss": 0.5346,
      "step": 17633
    },
    {
      "epoch": 0.5417012256934844,
      "grad_norm": 0.3632640838623047,
      "learning_rate": 1.6619865942309515e-05,
      "loss": 0.5556,
      "step": 17634
    },
    {
      "epoch": 0.5417319448284337,
      "grad_norm": 0.36114057898521423,
      "learning_rate": 1.6619503710639362e-05,
      "loss": 0.5544,
      "step": 17635
    },
    {
      "epoch": 0.5417626639633828,
      "grad_norm": 0.3875245749950409,
      "learning_rate": 1.6619141463508897e-05,
      "loss": 0.6187,
      "step": 17636
    },
    {
      "epoch": 0.5417933830983319,
      "grad_norm": 0.38266149163246155,
      "learning_rate": 1.6618779200918966e-05,
      "loss": 0.5354,
      "step": 17637
    },
    {
      "epoch": 0.5418241022332811,
      "grad_norm": 0.34363865852355957,
      "learning_rate": 1.6618416922870416e-05,
      "loss": 0.5564,
      "step": 17638
    },
    {
      "epoch": 0.5418548213682303,
      "grad_norm": 0.3867649734020233,
      "learning_rate": 1.6618054629364088e-05,
      "loss": 0.616,
      "step": 17639
    },
    {
      "epoch": 0.5418855405031794,
      "grad_norm": 0.34328681230545044,
      "learning_rate": 1.6617692320400827e-05,
      "loss": 0.5566,
      "step": 17640
    },
    {
      "epoch": 0.5419162596381286,
      "grad_norm": 0.3303239643573761,
      "learning_rate": 1.661732999598149e-05,
      "loss": 0.5923,
      "step": 17641
    },
    {
      "epoch": 0.5419469787730777,
      "grad_norm": 0.31894564628601074,
      "learning_rate": 1.6616967656106913e-05,
      "loss": 0.4898,
      "step": 17642
    },
    {
      "epoch": 0.5419776979080269,
      "grad_norm": 0.3708004951477051,
      "learning_rate": 1.661660530077795e-05,
      "loss": 0.5373,
      "step": 17643
    },
    {
      "epoch": 0.5420084170429761,
      "grad_norm": 0.365610808134079,
      "learning_rate": 1.661624292999544e-05,
      "loss": 0.5819,
      "step": 17644
    },
    {
      "epoch": 0.5420391361779252,
      "grad_norm": 0.40150147676467896,
      "learning_rate": 1.6615880543760234e-05,
      "loss": 0.6135,
      "step": 17645
    },
    {
      "epoch": 0.5420698553128744,
      "grad_norm": 0.3388419449329376,
      "learning_rate": 1.6615518142073178e-05,
      "loss": 0.5355,
      "step": 17646
    },
    {
      "epoch": 0.5421005744478236,
      "grad_norm": 0.34792622923851013,
      "learning_rate": 1.6615155724935116e-05,
      "loss": 0.531,
      "step": 17647
    },
    {
      "epoch": 0.5421312935827727,
      "grad_norm": 0.3535044491291046,
      "learning_rate": 1.6614793292346893e-05,
      "loss": 0.547,
      "step": 17648
    },
    {
      "epoch": 0.5421620127177219,
      "grad_norm": 0.3867039978504181,
      "learning_rate": 1.661443084430936e-05,
      "loss": 0.5928,
      "step": 17649
    },
    {
      "epoch": 0.542192731852671,
      "grad_norm": 0.7360907196998596,
      "learning_rate": 1.661406838082336e-05,
      "loss": 0.4711,
      "step": 17650
    },
    {
      "epoch": 0.5422234509876201,
      "grad_norm": 0.3535214066505432,
      "learning_rate": 1.6613705901889745e-05,
      "loss": 0.573,
      "step": 17651
    },
    {
      "epoch": 0.5422541701225694,
      "grad_norm": 0.33429551124572754,
      "learning_rate": 1.6613343407509357e-05,
      "loss": 0.598,
      "step": 17652
    },
    {
      "epoch": 0.5422848892575185,
      "grad_norm": 0.39646944403648376,
      "learning_rate": 1.6612980897683044e-05,
      "loss": 0.5936,
      "step": 17653
    },
    {
      "epoch": 0.5423156083924676,
      "grad_norm": 0.36002078652381897,
      "learning_rate": 1.6612618372411652e-05,
      "loss": 0.5592,
      "step": 17654
    },
    {
      "epoch": 0.5423463275274168,
      "grad_norm": 0.3753989338874817,
      "learning_rate": 1.661225583169603e-05,
      "loss": 0.5446,
      "step": 17655
    },
    {
      "epoch": 0.542377046662366,
      "grad_norm": 0.33321306109428406,
      "learning_rate": 1.661189327553702e-05,
      "loss": 0.4801,
      "step": 17656
    },
    {
      "epoch": 0.5424077657973152,
      "grad_norm": 0.36795276403427124,
      "learning_rate": 1.661153070393547e-05,
      "loss": 0.5984,
      "step": 17657
    },
    {
      "epoch": 0.5424384849322643,
      "grad_norm": 0.35949185490608215,
      "learning_rate": 1.661116811689223e-05,
      "loss": 0.5911,
      "step": 17658
    },
    {
      "epoch": 0.5424692040672134,
      "grad_norm": 0.3341417908668518,
      "learning_rate": 1.6610805514408144e-05,
      "loss": 0.5,
      "step": 17659
    },
    {
      "epoch": 0.5424999232021627,
      "grad_norm": 0.3760957717895508,
      "learning_rate": 1.6610442896484063e-05,
      "loss": 0.4989,
      "step": 17660
    },
    {
      "epoch": 0.5425306423371118,
      "grad_norm": 0.3503108024597168,
      "learning_rate": 1.6610080263120828e-05,
      "loss": 0.5492,
      "step": 17661
    },
    {
      "epoch": 0.5425613614720609,
      "grad_norm": 0.3976658582687378,
      "learning_rate": 1.6609717614319293e-05,
      "loss": 0.6234,
      "step": 17662
    },
    {
      "epoch": 0.5425920806070101,
      "grad_norm": 0.3299378752708435,
      "learning_rate": 1.6609354950080297e-05,
      "loss": 0.5452,
      "step": 17663
    },
    {
      "epoch": 0.5426227997419593,
      "grad_norm": 0.35478919744491577,
      "learning_rate": 1.6608992270404692e-05,
      "loss": 0.5582,
      "step": 17664
    },
    {
      "epoch": 0.5426535188769084,
      "grad_norm": 0.420798122882843,
      "learning_rate": 1.6608629575293324e-05,
      "loss": 0.5389,
      "step": 17665
    },
    {
      "epoch": 0.5426842380118576,
      "grad_norm": 0.35608747601509094,
      "learning_rate": 1.660826686474704e-05,
      "loss": 0.4795,
      "step": 17666
    },
    {
      "epoch": 0.5427149571468067,
      "grad_norm": 0.43351176381111145,
      "learning_rate": 1.6607904138766685e-05,
      "loss": 0.6064,
      "step": 17667
    },
    {
      "epoch": 0.5427456762817559,
      "grad_norm": 0.3550818860530853,
      "learning_rate": 1.6607541397353112e-05,
      "loss": 0.5738,
      "step": 17668
    },
    {
      "epoch": 0.5427763954167051,
      "grad_norm": 0.39188385009765625,
      "learning_rate": 1.6607178640507164e-05,
      "loss": 0.5003,
      "step": 17669
    },
    {
      "epoch": 0.5428071145516542,
      "grad_norm": 0.5626742243766785,
      "learning_rate": 1.660681586822969e-05,
      "loss": 0.5521,
      "step": 17670
    },
    {
      "epoch": 0.5428378336866034,
      "grad_norm": 0.374032586812973,
      "learning_rate": 1.6606453080521533e-05,
      "loss": 0.5349,
      "step": 17671
    },
    {
      "epoch": 0.5428685528215526,
      "grad_norm": 0.34837019443511963,
      "learning_rate": 1.6606090277383544e-05,
      "loss": 0.5547,
      "step": 17672
    },
    {
      "epoch": 0.5428992719565017,
      "grad_norm": 0.32095804810523987,
      "learning_rate": 1.660572745881657e-05,
      "loss": 0.5579,
      "step": 17673
    },
    {
      "epoch": 0.5429299910914509,
      "grad_norm": 0.3471071124076843,
      "learning_rate": 1.660536462482146e-05,
      "loss": 0.5704,
      "step": 17674
    },
    {
      "epoch": 0.5429607102264,
      "grad_norm": 0.3762083947658539,
      "learning_rate": 1.660500177539906e-05,
      "loss": 0.4882,
      "step": 17675
    },
    {
      "epoch": 0.5429914293613491,
      "grad_norm": 0.37276262044906616,
      "learning_rate": 1.6604638910550214e-05,
      "loss": 0.4726,
      "step": 17676
    },
    {
      "epoch": 0.5430221484962984,
      "grad_norm": 0.3400457799434662,
      "learning_rate": 1.6604276030275774e-05,
      "loss": 0.5341,
      "step": 17677
    },
    {
      "epoch": 0.5430528676312475,
      "grad_norm": 0.3349197208881378,
      "learning_rate": 1.6603913134576582e-05,
      "loss": 0.5823,
      "step": 17678
    },
    {
      "epoch": 0.5430835867661966,
      "grad_norm": 0.38008198142051697,
      "learning_rate": 1.6603550223453496e-05,
      "loss": 0.4911,
      "step": 17679
    },
    {
      "epoch": 0.5431143059011458,
      "grad_norm": 0.36963891983032227,
      "learning_rate": 1.6603187296907357e-05,
      "loss": 0.6017,
      "step": 17680
    },
    {
      "epoch": 0.543145025036095,
      "grad_norm": 0.327671080827713,
      "learning_rate": 1.660282435493901e-05,
      "loss": 0.5574,
      "step": 17681
    },
    {
      "epoch": 0.5431757441710442,
      "grad_norm": 0.4918424189090729,
      "learning_rate": 1.660246139754931e-05,
      "loss": 0.5626,
      "step": 17682
    },
    {
      "epoch": 0.5432064633059933,
      "grad_norm": 0.3699384331703186,
      "learning_rate": 1.6602098424739094e-05,
      "loss": 0.5825,
      "step": 17683
    },
    {
      "epoch": 0.5432371824409424,
      "grad_norm": 0.3416949510574341,
      "learning_rate": 1.6601735436509217e-05,
      "loss": 0.556,
      "step": 17684
    },
    {
      "epoch": 0.5432679015758917,
      "grad_norm": 0.3889096677303314,
      "learning_rate": 1.6601372432860528e-05,
      "loss": 0.598,
      "step": 17685
    },
    {
      "epoch": 0.5432986207108408,
      "grad_norm": 0.3543693721294403,
      "learning_rate": 1.660100941379387e-05,
      "loss": 0.5521,
      "step": 17686
    },
    {
      "epoch": 0.5433293398457899,
      "grad_norm": 0.3668806552886963,
      "learning_rate": 1.6600646379310096e-05,
      "loss": 0.5614,
      "step": 17687
    },
    {
      "epoch": 0.5433600589807391,
      "grad_norm": 0.3333626985549927,
      "learning_rate": 1.660028332941005e-05,
      "loss": 0.5118,
      "step": 17688
    },
    {
      "epoch": 0.5433907781156883,
      "grad_norm": 0.35499387979507446,
      "learning_rate": 1.6599920264094588e-05,
      "loss": 0.5679,
      "step": 17689
    },
    {
      "epoch": 0.5434214972506374,
      "grad_norm": 0.35176828503608704,
      "learning_rate": 1.6599557183364542e-05,
      "loss": 0.5689,
      "step": 17690
    },
    {
      "epoch": 0.5434522163855866,
      "grad_norm": 0.3457180857658386,
      "learning_rate": 1.6599194087220774e-05,
      "loss": 0.5644,
      "step": 17691
    },
    {
      "epoch": 0.5434829355205357,
      "grad_norm": 0.3658696711063385,
      "learning_rate": 1.6598830975664126e-05,
      "loss": 0.574,
      "step": 17692
    },
    {
      "epoch": 0.543513654655485,
      "grad_norm": 0.34223872423171997,
      "learning_rate": 1.6598467848695446e-05,
      "loss": 0.5918,
      "step": 17693
    },
    {
      "epoch": 0.5435443737904341,
      "grad_norm": 0.3816506266593933,
      "learning_rate": 1.6598104706315588e-05,
      "loss": 0.5527,
      "step": 17694
    },
    {
      "epoch": 0.5435750929253832,
      "grad_norm": 0.3838176131248474,
      "learning_rate": 1.659774154852539e-05,
      "loss": 0.6843,
      "step": 17695
    },
    {
      "epoch": 0.5436058120603324,
      "grad_norm": 0.3773840069770813,
      "learning_rate": 1.659737837532571e-05,
      "loss": 0.5488,
      "step": 17696
    },
    {
      "epoch": 0.5436365311952815,
      "grad_norm": 0.3666813373565674,
      "learning_rate": 1.659701518671739e-05,
      "loss": 0.5196,
      "step": 17697
    },
    {
      "epoch": 0.5436672503302307,
      "grad_norm": 0.3734922409057617,
      "learning_rate": 1.6596651982701285e-05,
      "loss": 0.6018,
      "step": 17698
    },
    {
      "epoch": 0.5436979694651799,
      "grad_norm": 0.3823114037513733,
      "learning_rate": 1.6596288763278234e-05,
      "loss": 0.5604,
      "step": 17699
    },
    {
      "epoch": 0.543728688600129,
      "grad_norm": 0.32001426815986633,
      "learning_rate": 1.659592552844909e-05,
      "loss": 0.5254,
      "step": 17700
    },
    {
      "epoch": 0.5437594077350781,
      "grad_norm": 0.3313305675983429,
      "learning_rate": 1.65955622782147e-05,
      "loss": 0.5026,
      "step": 17701
    },
    {
      "epoch": 0.5437901268700274,
      "grad_norm": 0.39203909039497375,
      "learning_rate": 1.659519901257592e-05,
      "loss": 0.5642,
      "step": 17702
    },
    {
      "epoch": 0.5438208460049765,
      "grad_norm": 0.34227433800697327,
      "learning_rate": 1.6594835731533586e-05,
      "loss": 0.5424,
      "step": 17703
    },
    {
      "epoch": 0.5438515651399256,
      "grad_norm": 0.35318708419799805,
      "learning_rate": 1.659447243508855e-05,
      "loss": 0.5879,
      "step": 17704
    },
    {
      "epoch": 0.5438822842748748,
      "grad_norm": 0.38673678040504456,
      "learning_rate": 1.659410912324167e-05,
      "loss": 0.538,
      "step": 17705
    },
    {
      "epoch": 0.543913003409824,
      "grad_norm": 0.35573431849479675,
      "learning_rate": 1.6593745795993784e-05,
      "loss": 0.5107,
      "step": 17706
    },
    {
      "epoch": 0.5439437225447732,
      "grad_norm": 0.35469236969947815,
      "learning_rate": 1.6593382453345745e-05,
      "loss": 0.6649,
      "step": 17707
    },
    {
      "epoch": 0.5439744416797223,
      "grad_norm": 0.5138862133026123,
      "learning_rate": 1.65930190952984e-05,
      "loss": 0.5278,
      "step": 17708
    },
    {
      "epoch": 0.5440051608146714,
      "grad_norm": 0.3462706506252289,
      "learning_rate": 1.6592655721852602e-05,
      "loss": 0.6077,
      "step": 17709
    },
    {
      "epoch": 0.5440358799496207,
      "grad_norm": 0.3589460551738739,
      "learning_rate": 1.6592292333009192e-05,
      "loss": 0.5494,
      "step": 17710
    },
    {
      "epoch": 0.5440665990845698,
      "grad_norm": 0.33556926250457764,
      "learning_rate": 1.6591928928769024e-05,
      "loss": 0.6503,
      "step": 17711
    },
    {
      "epoch": 0.5440973182195189,
      "grad_norm": 0.39089855551719666,
      "learning_rate": 1.6591565509132944e-05,
      "loss": 0.5511,
      "step": 17712
    },
    {
      "epoch": 0.5441280373544681,
      "grad_norm": 0.4295934736728668,
      "learning_rate": 1.659120207410181e-05,
      "loss": 0.5983,
      "step": 17713
    },
    {
      "epoch": 0.5441587564894173,
      "grad_norm": 0.37466973066329956,
      "learning_rate": 1.6590838623676455e-05,
      "loss": 0.6408,
      "step": 17714
    },
    {
      "epoch": 0.5441894756243664,
      "grad_norm": 0.33733561635017395,
      "learning_rate": 1.659047515785774e-05,
      "loss": 0.5591,
      "step": 17715
    },
    {
      "epoch": 0.5442201947593156,
      "grad_norm": 0.387408047914505,
      "learning_rate": 1.659011167664651e-05,
      "loss": 0.6131,
      "step": 17716
    },
    {
      "epoch": 0.5442509138942647,
      "grad_norm": 0.37652677297592163,
      "learning_rate": 1.658974818004361e-05,
      "loss": 0.4631,
      "step": 17717
    },
    {
      "epoch": 0.544281633029214,
      "grad_norm": 0.33413195610046387,
      "learning_rate": 1.6589384668049895e-05,
      "loss": 0.5817,
      "step": 17718
    },
    {
      "epoch": 0.5443123521641631,
      "grad_norm": 0.35954052209854126,
      "learning_rate": 1.6589021140666213e-05,
      "loss": 0.5504,
      "step": 17719
    },
    {
      "epoch": 0.5443430712991122,
      "grad_norm": 0.33819445967674255,
      "learning_rate": 1.658865759789341e-05,
      "loss": 0.5699,
      "step": 17720
    },
    {
      "epoch": 0.5443737904340614,
      "grad_norm": 0.3741539716720581,
      "learning_rate": 1.658829403973234e-05,
      "loss": 0.5774,
      "step": 17721
    },
    {
      "epoch": 0.5444045095690105,
      "grad_norm": 0.3450431823730469,
      "learning_rate": 1.6587930466183847e-05,
      "loss": 0.4765,
      "step": 17722
    },
    {
      "epoch": 0.5444352287039597,
      "grad_norm": 0.39633411169052124,
      "learning_rate": 1.6587566877248785e-05,
      "loss": 0.6436,
      "step": 17723
    },
    {
      "epoch": 0.5444659478389089,
      "grad_norm": 0.35573041439056396,
      "learning_rate": 1.6587203272927996e-05,
      "loss": 0.6095,
      "step": 17724
    },
    {
      "epoch": 0.544496666973858,
      "grad_norm": 0.35813626646995544,
      "learning_rate": 1.6586839653222338e-05,
      "loss": 0.5942,
      "step": 17725
    },
    {
      "epoch": 0.5445273861088071,
      "grad_norm": 0.33719462156295776,
      "learning_rate": 1.6586476018132653e-05,
      "loss": 0.5664,
      "step": 17726
    },
    {
      "epoch": 0.5445581052437564,
      "grad_norm": 0.3577592968940735,
      "learning_rate": 1.6586112367659794e-05,
      "loss": 0.5293,
      "step": 17727
    },
    {
      "epoch": 0.5445888243787055,
      "grad_norm": 0.32969745993614197,
      "learning_rate": 1.658574870180461e-05,
      "loss": 0.5069,
      "step": 17728
    },
    {
      "epoch": 0.5446195435136546,
      "grad_norm": 0.34583529829978943,
      "learning_rate": 1.658538502056795e-05,
      "loss": 0.5372,
      "step": 17729
    },
    {
      "epoch": 0.5446502626486038,
      "grad_norm": 0.8097785711288452,
      "learning_rate": 1.6585021323950663e-05,
      "loss": 0.6521,
      "step": 17730
    },
    {
      "epoch": 0.544680981783553,
      "grad_norm": 0.312434583902359,
      "learning_rate": 1.65846576119536e-05,
      "loss": 0.5352,
      "step": 17731
    },
    {
      "epoch": 0.5447117009185022,
      "grad_norm": 0.34326574206352234,
      "learning_rate": 1.6584293884577605e-05,
      "loss": 0.5044,
      "step": 17732
    },
    {
      "epoch": 0.5447424200534513,
      "grad_norm": 0.3642909824848175,
      "learning_rate": 1.658393014182354e-05,
      "loss": 0.5921,
      "step": 17733
    },
    {
      "epoch": 0.5447731391884004,
      "grad_norm": 0.40556713938713074,
      "learning_rate": 1.658356638369224e-05,
      "loss": 0.5428,
      "step": 17734
    },
    {
      "epoch": 0.5448038583233497,
      "grad_norm": 0.4519590735435486,
      "learning_rate": 1.658320261018456e-05,
      "loss": 0.6814,
      "step": 17735
    },
    {
      "epoch": 0.5448345774582988,
      "grad_norm": 0.34088268876075745,
      "learning_rate": 1.6582838821301354e-05,
      "loss": 0.538,
      "step": 17736
    },
    {
      "epoch": 0.5448652965932479,
      "grad_norm": 0.3594852685928345,
      "learning_rate": 1.658247501704347e-05,
      "loss": 0.6328,
      "step": 17737
    },
    {
      "epoch": 0.5448960157281971,
      "grad_norm": 0.35510939359664917,
      "learning_rate": 1.658211119741175e-05,
      "loss": 0.553,
      "step": 17738
    },
    {
      "epoch": 0.5449267348631462,
      "grad_norm": 0.40275833010673523,
      "learning_rate": 1.6581747362407054e-05,
      "loss": 0.5699,
      "step": 17739
    },
    {
      "epoch": 0.5449574539980954,
      "grad_norm": 0.38424280285835266,
      "learning_rate": 1.6581383512030224e-05,
      "loss": 0.633,
      "step": 17740
    },
    {
      "epoch": 0.5449881731330446,
      "grad_norm": 0.324897438287735,
      "learning_rate": 1.6581019646282115e-05,
      "loss": 0.5069,
      "step": 17741
    },
    {
      "epoch": 0.5450188922679937,
      "grad_norm": 0.3672373294830322,
      "learning_rate": 1.6580655765163576e-05,
      "loss": 0.5625,
      "step": 17742
    },
    {
      "epoch": 0.545049611402943,
      "grad_norm": 0.3235056400299072,
      "learning_rate": 1.6580291868675455e-05,
      "loss": 0.5871,
      "step": 17743
    },
    {
      "epoch": 0.5450803305378921,
      "grad_norm": 0.3985832929611206,
      "learning_rate": 1.6579927956818603e-05,
      "loss": 0.5648,
      "step": 17744
    },
    {
      "epoch": 0.5451110496728412,
      "grad_norm": 0.41424521803855896,
      "learning_rate": 1.657956402959387e-05,
      "loss": 0.6031,
      "step": 17745
    },
    {
      "epoch": 0.5451417688077904,
      "grad_norm": 0.4279395639896393,
      "learning_rate": 1.6579200087002104e-05,
      "loss": 0.564,
      "step": 17746
    },
    {
      "epoch": 0.5451724879427395,
      "grad_norm": 0.38417840003967285,
      "learning_rate": 1.6578836129044158e-05,
      "loss": 0.574,
      "step": 17747
    },
    {
      "epoch": 0.5452032070776887,
      "grad_norm": 0.3529137074947357,
      "learning_rate": 1.6578472155720882e-05,
      "loss": 0.6298,
      "step": 17748
    },
    {
      "epoch": 0.5452339262126379,
      "grad_norm": 0.34810489416122437,
      "learning_rate": 1.6578108167033123e-05,
      "loss": 0.5248,
      "step": 17749
    },
    {
      "epoch": 0.545264645347587,
      "grad_norm": 0.36843615770339966,
      "learning_rate": 1.6577744162981732e-05,
      "loss": 0.5091,
      "step": 17750
    },
    {
      "epoch": 0.5452953644825361,
      "grad_norm": 0.4092557430267334,
      "learning_rate": 1.657738014356756e-05,
      "loss": 0.5608,
      "step": 17751
    },
    {
      "epoch": 0.5453260836174854,
      "grad_norm": 0.366543173789978,
      "learning_rate": 1.6577016108791463e-05,
      "loss": 0.5577,
      "step": 17752
    },
    {
      "epoch": 0.5453568027524345,
      "grad_norm": 0.36111441254615784,
      "learning_rate": 1.6576652058654283e-05,
      "loss": 0.5915,
      "step": 17753
    },
    {
      "epoch": 0.5453875218873836,
      "grad_norm": 0.4382053315639496,
      "learning_rate": 1.657628799315687e-05,
      "loss": 0.553,
      "step": 17754
    },
    {
      "epoch": 0.5454182410223328,
      "grad_norm": 0.438309907913208,
      "learning_rate": 1.657592391230008e-05,
      "loss": 0.5703,
      "step": 17755
    },
    {
      "epoch": 0.545448960157282,
      "grad_norm": 0.3420596718788147,
      "learning_rate": 1.6575559816084758e-05,
      "loss": 0.536,
      "step": 17756
    },
    {
      "epoch": 0.5454796792922312,
      "grad_norm": 0.38722237944602966,
      "learning_rate": 1.6575195704511756e-05,
      "loss": 0.607,
      "step": 17757
    },
    {
      "epoch": 0.5455103984271803,
      "grad_norm": 0.4006425440311432,
      "learning_rate": 1.6574831577581925e-05,
      "loss": 0.5089,
      "step": 17758
    },
    {
      "epoch": 0.5455411175621294,
      "grad_norm": 0.34805455803871155,
      "learning_rate": 1.657446743529612e-05,
      "loss": 0.5862,
      "step": 17759
    },
    {
      "epoch": 0.5455718366970786,
      "grad_norm": 0.39740148186683655,
      "learning_rate": 1.6574103277655184e-05,
      "loss": 0.6019,
      "step": 17760
    },
    {
      "epoch": 0.5456025558320278,
      "grad_norm": 0.35048773884773254,
      "learning_rate": 1.657373910465997e-05,
      "loss": 0.5948,
      "step": 17761
    },
    {
      "epoch": 0.5456332749669769,
      "grad_norm": 0.3629768192768097,
      "learning_rate": 1.657337491631133e-05,
      "loss": 0.5447,
      "step": 17762
    },
    {
      "epoch": 0.5456639941019261,
      "grad_norm": 0.3450331389904022,
      "learning_rate": 1.6573010712610116e-05,
      "loss": 0.6083,
      "step": 17763
    },
    {
      "epoch": 0.5456947132368752,
      "grad_norm": 0.33820632100105286,
      "learning_rate": 1.6572646493557174e-05,
      "loss": 0.6043,
      "step": 17764
    },
    {
      "epoch": 0.5457254323718244,
      "grad_norm": 0.35275179147720337,
      "learning_rate": 1.6572282259153357e-05,
      "loss": 0.4757,
      "step": 17765
    },
    {
      "epoch": 0.5457561515067736,
      "grad_norm": 0.37016719579696655,
      "learning_rate": 1.657191800939952e-05,
      "loss": 0.5427,
      "step": 17766
    },
    {
      "epoch": 0.5457868706417227,
      "grad_norm": 0.35285046696662903,
      "learning_rate": 1.6571553744296505e-05,
      "loss": 0.5212,
      "step": 17767
    },
    {
      "epoch": 0.5458175897766719,
      "grad_norm": 0.34526240825653076,
      "learning_rate": 1.6571189463845167e-05,
      "loss": 0.5141,
      "step": 17768
    },
    {
      "epoch": 0.5458483089116211,
      "grad_norm": 0.3409665822982788,
      "learning_rate": 1.6570825168046362e-05,
      "loss": 0.5838,
      "step": 17769
    },
    {
      "epoch": 0.5458790280465702,
      "grad_norm": 0.3328840732574463,
      "learning_rate": 1.6570460856900932e-05,
      "loss": 0.5362,
      "step": 17770
    },
    {
      "epoch": 0.5459097471815194,
      "grad_norm": 0.36654531955718994,
      "learning_rate": 1.657009653040973e-05,
      "loss": 0.6168,
      "step": 17771
    },
    {
      "epoch": 0.5459404663164685,
      "grad_norm": 0.3876456022262573,
      "learning_rate": 1.656973218857361e-05,
      "loss": 0.6167,
      "step": 17772
    },
    {
      "epoch": 0.5459711854514177,
      "grad_norm": 0.5172316431999207,
      "learning_rate": 1.6569367831393423e-05,
      "loss": 0.5795,
      "step": 17773
    },
    {
      "epoch": 0.5460019045863669,
      "grad_norm": 0.3343391418457031,
      "learning_rate": 1.6569003458870018e-05,
      "loss": 0.6207,
      "step": 17774
    },
    {
      "epoch": 0.546032623721316,
      "grad_norm": 0.31789860129356384,
      "learning_rate": 1.6568639071004247e-05,
      "loss": 0.5345,
      "step": 17775
    },
    {
      "epoch": 0.5460633428562651,
      "grad_norm": 0.34435585141181946,
      "learning_rate": 1.656827466779696e-05,
      "loss": 0.5905,
      "step": 17776
    },
    {
      "epoch": 0.5460940619912144,
      "grad_norm": 0.5723513960838318,
      "learning_rate": 1.656791024924901e-05,
      "loss": 0.5979,
      "step": 17777
    },
    {
      "epoch": 0.5461247811261635,
      "grad_norm": 0.4134824872016907,
      "learning_rate": 1.6567545815361247e-05,
      "loss": 0.5565,
      "step": 17778
    },
    {
      "epoch": 0.5461555002611126,
      "grad_norm": 0.5177611112594604,
      "learning_rate": 1.656718136613452e-05,
      "loss": 0.5211,
      "step": 17779
    },
    {
      "epoch": 0.5461862193960618,
      "grad_norm": 0.4397880733013153,
      "learning_rate": 1.6566816901569684e-05,
      "loss": 0.6033,
      "step": 17780
    },
    {
      "epoch": 0.5462169385310109,
      "grad_norm": 0.33246564865112305,
      "learning_rate": 1.656645242166759e-05,
      "loss": 0.5332,
      "step": 17781
    },
    {
      "epoch": 0.5462476576659602,
      "grad_norm": 0.4321861267089844,
      "learning_rate": 1.6566087926429084e-05,
      "loss": 0.6416,
      "step": 17782
    },
    {
      "epoch": 0.5462783768009093,
      "grad_norm": 0.33753177523612976,
      "learning_rate": 1.6565723415855023e-05,
      "loss": 0.5415,
      "step": 17783
    },
    {
      "epoch": 0.5463090959358584,
      "grad_norm": 0.3512771725654602,
      "learning_rate": 1.656535888994626e-05,
      "loss": 0.58,
      "step": 17784
    },
    {
      "epoch": 0.5463398150708076,
      "grad_norm": 0.36695167422294617,
      "learning_rate": 1.6564994348703635e-05,
      "loss": 0.5052,
      "step": 17785
    },
    {
      "epoch": 0.5463705342057568,
      "grad_norm": 0.34553104639053345,
      "learning_rate": 1.6564629792128014e-05,
      "loss": 0.5513,
      "step": 17786
    },
    {
      "epoch": 0.5464012533407059,
      "grad_norm": 0.381276935338974,
      "learning_rate": 1.6564265220220236e-05,
      "loss": 0.5865,
      "step": 17787
    },
    {
      "epoch": 0.5464319724756551,
      "grad_norm": 0.4641372263431549,
      "learning_rate": 1.656390063298116e-05,
      "loss": 0.55,
      "step": 17788
    },
    {
      "epoch": 0.5464626916106042,
      "grad_norm": 0.4088456928730011,
      "learning_rate": 1.656353603041164e-05,
      "loss": 0.5478,
      "step": 17789
    },
    {
      "epoch": 0.5464934107455534,
      "grad_norm": 0.3531017601490021,
      "learning_rate": 1.656317141251252e-05,
      "loss": 0.5759,
      "step": 17790
    },
    {
      "epoch": 0.5465241298805026,
      "grad_norm": 0.343704491853714,
      "learning_rate": 1.6562806779284657e-05,
      "loss": 0.6104,
      "step": 17791
    },
    {
      "epoch": 0.5465548490154517,
      "grad_norm": 0.42058125138282776,
      "learning_rate": 1.6562442130728897e-05,
      "loss": 0.533,
      "step": 17792
    },
    {
      "epoch": 0.5465855681504009,
      "grad_norm": 0.3446334898471832,
      "learning_rate": 1.6562077466846097e-05,
      "loss": 0.5998,
      "step": 17793
    },
    {
      "epoch": 0.54661628728535,
      "grad_norm": 0.33991238474845886,
      "learning_rate": 1.6561712787637107e-05,
      "loss": 0.537,
      "step": 17794
    },
    {
      "epoch": 0.5466470064202992,
      "grad_norm": 0.4118923246860504,
      "learning_rate": 1.6561348093102773e-05,
      "loss": 0.5436,
      "step": 17795
    },
    {
      "epoch": 0.5466777255552484,
      "grad_norm": 0.8692225813865662,
      "learning_rate": 1.656098338324396e-05,
      "loss": 0.5485,
      "step": 17796
    },
    {
      "epoch": 0.5467084446901975,
      "grad_norm": 0.32533422112464905,
      "learning_rate": 1.6560618658061507e-05,
      "loss": 0.5098,
      "step": 17797
    },
    {
      "epoch": 0.5467391638251466,
      "grad_norm": 0.34816521406173706,
      "learning_rate": 1.6560253917556273e-05,
      "loss": 0.5524,
      "step": 17798
    },
    {
      "epoch": 0.5467698829600959,
      "grad_norm": 0.32880067825317383,
      "learning_rate": 1.6559889161729107e-05,
      "loss": 0.5804,
      "step": 17799
    },
    {
      "epoch": 0.546800602095045,
      "grad_norm": 0.47061675786972046,
      "learning_rate": 1.6559524390580867e-05,
      "loss": 0.5791,
      "step": 17800
    },
    {
      "epoch": 0.5468313212299941,
      "grad_norm": 0.33728039264678955,
      "learning_rate": 1.6559159604112392e-05,
      "loss": 0.5861,
      "step": 17801
    },
    {
      "epoch": 0.5468620403649433,
      "grad_norm": 0.33636409044265747,
      "learning_rate": 1.6558794802324544e-05,
      "loss": 0.5244,
      "step": 17802
    },
    {
      "epoch": 0.5468927594998925,
      "grad_norm": 0.38391658663749695,
      "learning_rate": 1.6558429985218177e-05,
      "loss": 0.5896,
      "step": 17803
    },
    {
      "epoch": 0.5469234786348417,
      "grad_norm": 0.37696588039398193,
      "learning_rate": 1.6558065152794133e-05,
      "loss": 0.6145,
      "step": 17804
    },
    {
      "epoch": 0.5469541977697908,
      "grad_norm": 0.4099494218826294,
      "learning_rate": 1.6557700305053274e-05,
      "loss": 0.6259,
      "step": 17805
    },
    {
      "epoch": 0.5469849169047399,
      "grad_norm": 0.3631151616573334,
      "learning_rate": 1.6557335441996446e-05,
      "loss": 0.5859,
      "step": 17806
    },
    {
      "epoch": 0.5470156360396892,
      "grad_norm": 0.34597212076187134,
      "learning_rate": 1.6556970563624504e-05,
      "loss": 0.598,
      "step": 17807
    },
    {
      "epoch": 0.5470463551746383,
      "grad_norm": 0.3382669687271118,
      "learning_rate": 1.6556605669938298e-05,
      "loss": 0.5866,
      "step": 17808
    },
    {
      "epoch": 0.5470770743095874,
      "grad_norm": 0.31504184007644653,
      "learning_rate": 1.655624076093868e-05,
      "loss": 0.5533,
      "step": 17809
    },
    {
      "epoch": 0.5471077934445366,
      "grad_norm": 1.3177824020385742,
      "learning_rate": 1.6555875836626507e-05,
      "loss": 0.5463,
      "step": 17810
    },
    {
      "epoch": 0.5471385125794858,
      "grad_norm": 0.32278066873550415,
      "learning_rate": 1.6555510897002628e-05,
      "loss": 0.5443,
      "step": 17811
    },
    {
      "epoch": 0.5471692317144349,
      "grad_norm": 0.3601195216178894,
      "learning_rate": 1.6555145942067892e-05,
      "loss": 0.5563,
      "step": 17812
    },
    {
      "epoch": 0.5471999508493841,
      "grad_norm": 0.35071420669555664,
      "learning_rate": 1.6554780971823155e-05,
      "loss": 0.5379,
      "step": 17813
    },
    {
      "epoch": 0.5472306699843332,
      "grad_norm": 0.38742586970329285,
      "learning_rate": 1.6554415986269273e-05,
      "loss": 0.5732,
      "step": 17814
    },
    {
      "epoch": 0.5472613891192823,
      "grad_norm": 0.3576367199420929,
      "learning_rate": 1.6554050985407097e-05,
      "loss": 0.5502,
      "step": 17815
    },
    {
      "epoch": 0.5472921082542316,
      "grad_norm": 0.3470524251461029,
      "learning_rate": 1.6553685969237473e-05,
      "loss": 0.5694,
      "step": 17816
    },
    {
      "epoch": 0.5473228273891807,
      "grad_norm": 0.32977530360221863,
      "learning_rate": 1.6553320937761256e-05,
      "loss": 0.5671,
      "step": 17817
    },
    {
      "epoch": 0.5473535465241299,
      "grad_norm": 0.34287333488464355,
      "learning_rate": 1.6552955890979303e-05,
      "loss": 0.5198,
      "step": 17818
    },
    {
      "epoch": 0.547384265659079,
      "grad_norm": 0.3206973075866699,
      "learning_rate": 1.6552590828892463e-05,
      "loss": 0.5377,
      "step": 17819
    },
    {
      "epoch": 0.5474149847940282,
      "grad_norm": 0.31568801403045654,
      "learning_rate": 1.655222575150159e-05,
      "loss": 0.5543,
      "step": 17820
    },
    {
      "epoch": 0.5474457039289774,
      "grad_norm": 0.3582233190536499,
      "learning_rate": 1.6551860658807536e-05,
      "loss": 0.5912,
      "step": 17821
    },
    {
      "epoch": 0.5474764230639265,
      "grad_norm": 0.4754795432090759,
      "learning_rate": 1.6551495550811155e-05,
      "loss": 0.5989,
      "step": 17822
    },
    {
      "epoch": 0.5475071421988756,
      "grad_norm": 0.3693186938762665,
      "learning_rate": 1.6551130427513297e-05,
      "loss": 0.6958,
      "step": 17823
    },
    {
      "epoch": 0.5475378613338249,
      "grad_norm": 0.3545594811439514,
      "learning_rate": 1.6550765288914815e-05,
      "loss": 0.6579,
      "step": 17824
    },
    {
      "epoch": 0.547568580468774,
      "grad_norm": 0.34710490703582764,
      "learning_rate": 1.6550400135016567e-05,
      "loss": 0.5311,
      "step": 17825
    },
    {
      "epoch": 0.5475992996037231,
      "grad_norm": 0.40857669711112976,
      "learning_rate": 1.65500349658194e-05,
      "loss": 0.5931,
      "step": 17826
    },
    {
      "epoch": 0.5476300187386723,
      "grad_norm": 0.3268378674983978,
      "learning_rate": 1.654966978132417e-05,
      "loss": 0.5878,
      "step": 17827
    },
    {
      "epoch": 0.5476607378736215,
      "grad_norm": 0.3292548656463623,
      "learning_rate": 1.6549304581531725e-05,
      "loss": 0.4826,
      "step": 17828
    },
    {
      "epoch": 0.5476914570085707,
      "grad_norm": 0.34110596776008606,
      "learning_rate": 1.6548939366442926e-05,
      "loss": 0.5498,
      "step": 17829
    },
    {
      "epoch": 0.5477221761435198,
      "grad_norm": 0.3000625967979431,
      "learning_rate": 1.654857413605862e-05,
      "loss": 0.5418,
      "step": 17830
    },
    {
      "epoch": 0.5477528952784689,
      "grad_norm": 0.3351806402206421,
      "learning_rate": 1.654820889037966e-05,
      "loss": 0.632,
      "step": 17831
    },
    {
      "epoch": 0.5477836144134182,
      "grad_norm": 0.33575963973999023,
      "learning_rate": 1.6547843629406902e-05,
      "loss": 0.4862,
      "step": 17832
    },
    {
      "epoch": 0.5478143335483673,
      "grad_norm": 0.3593653738498688,
      "learning_rate": 1.65474783531412e-05,
      "loss": 0.5274,
      "step": 17833
    },
    {
      "epoch": 0.5478450526833164,
      "grad_norm": 0.339646577835083,
      "learning_rate": 1.6547113061583403e-05,
      "loss": 0.5285,
      "step": 17834
    },
    {
      "epoch": 0.5478757718182656,
      "grad_norm": 0.36409562826156616,
      "learning_rate": 1.6546747754734366e-05,
      "loss": 0.5754,
      "step": 17835
    },
    {
      "epoch": 0.5479064909532148,
      "grad_norm": 0.39288946986198425,
      "learning_rate": 1.6546382432594944e-05,
      "loss": 0.5877,
      "step": 17836
    },
    {
      "epoch": 0.5479372100881639,
      "grad_norm": 0.3896755576133728,
      "learning_rate": 1.654601709516599e-05,
      "loss": 0.6159,
      "step": 17837
    },
    {
      "epoch": 0.5479679292231131,
      "grad_norm": 0.37969663739204407,
      "learning_rate": 1.6545651742448355e-05,
      "loss": 0.6028,
      "step": 17838
    },
    {
      "epoch": 0.5479986483580622,
      "grad_norm": 0.3571425974369049,
      "learning_rate": 1.6545286374442892e-05,
      "loss": 0.5943,
      "step": 17839
    },
    {
      "epoch": 0.5480293674930113,
      "grad_norm": 0.3501509726047516,
      "learning_rate": 1.6544920991150456e-05,
      "loss": 0.5218,
      "step": 17840
    },
    {
      "epoch": 0.5480600866279606,
      "grad_norm": 0.40619730949401855,
      "learning_rate": 1.6544555592571894e-05,
      "loss": 0.5512,
      "step": 17841
    },
    {
      "epoch": 0.5480908057629097,
      "grad_norm": 0.3890797197818756,
      "learning_rate": 1.6544190178708074e-05,
      "loss": 0.6059,
      "step": 17842
    },
    {
      "epoch": 0.5481215248978589,
      "grad_norm": 0.3417879641056061,
      "learning_rate": 1.6543824749559836e-05,
      "loss": 0.584,
      "step": 17843
    },
    {
      "epoch": 0.548152244032808,
      "grad_norm": 0.45473459362983704,
      "learning_rate": 1.654345930512804e-05,
      "loss": 0.5691,
      "step": 17844
    },
    {
      "epoch": 0.5481829631677572,
      "grad_norm": 0.3158077597618103,
      "learning_rate": 1.654309384541354e-05,
      "loss": 0.532,
      "step": 17845
    },
    {
      "epoch": 0.5482136823027064,
      "grad_norm": 0.3588064908981323,
      "learning_rate": 1.6542728370417184e-05,
      "loss": 0.574,
      "step": 17846
    },
    {
      "epoch": 0.5482444014376555,
      "grad_norm": 0.3702642619609833,
      "learning_rate": 1.6542362880139832e-05,
      "loss": 0.5914,
      "step": 17847
    },
    {
      "epoch": 0.5482751205726046,
      "grad_norm": 0.3724825084209442,
      "learning_rate": 1.654199737458233e-05,
      "loss": 0.5673,
      "step": 17848
    },
    {
      "epoch": 0.5483058397075539,
      "grad_norm": 0.37141385674476624,
      "learning_rate": 1.654163185374554e-05,
      "loss": 0.5671,
      "step": 17849
    },
    {
      "epoch": 0.548336558842503,
      "grad_norm": 0.3366224765777588,
      "learning_rate": 1.654126631763031e-05,
      "loss": 0.6299,
      "step": 17850
    },
    {
      "epoch": 0.5483672779774521,
      "grad_norm": 0.3561117649078369,
      "learning_rate": 1.6540900766237496e-05,
      "loss": 0.6305,
      "step": 17851
    },
    {
      "epoch": 0.5483979971124013,
      "grad_norm": 0.31687578558921814,
      "learning_rate": 1.6540535199567953e-05,
      "loss": 0.6041,
      "step": 17852
    },
    {
      "epoch": 0.5484287162473505,
      "grad_norm": 0.3243749439716339,
      "learning_rate": 1.6540169617622533e-05,
      "loss": 0.6098,
      "step": 17853
    },
    {
      "epoch": 0.5484594353822997,
      "grad_norm": 0.34132450819015503,
      "learning_rate": 1.6539804020402088e-05,
      "loss": 0.5112,
      "step": 17854
    },
    {
      "epoch": 0.5484901545172488,
      "grad_norm": 0.3644148111343384,
      "learning_rate": 1.6539438407907476e-05,
      "loss": 0.5671,
      "step": 17855
    },
    {
      "epoch": 0.5485208736521979,
      "grad_norm": 0.33963823318481445,
      "learning_rate": 1.653907278013955e-05,
      "loss": 0.6374,
      "step": 17856
    },
    {
      "epoch": 0.5485515927871472,
      "grad_norm": 0.33696845173835754,
      "learning_rate": 1.6538707137099158e-05,
      "loss": 0.4949,
      "step": 17857
    },
    {
      "epoch": 0.5485823119220963,
      "grad_norm": 0.6348381638526917,
      "learning_rate": 1.6538341478787162e-05,
      "loss": 0.5855,
      "step": 17858
    },
    {
      "epoch": 0.5486130310570454,
      "grad_norm": 0.3773930072784424,
      "learning_rate": 1.6537975805204412e-05,
      "loss": 0.5527,
      "step": 17859
    },
    {
      "epoch": 0.5486437501919946,
      "grad_norm": 0.4112347662448883,
      "learning_rate": 1.6537610116351762e-05,
      "loss": 0.5406,
      "step": 17860
    },
    {
      "epoch": 0.5486744693269437,
      "grad_norm": 0.33259260654449463,
      "learning_rate": 1.653724441223007e-05,
      "loss": 0.4508,
      "step": 17861
    },
    {
      "epoch": 0.5487051884618929,
      "grad_norm": 0.3755553960800171,
      "learning_rate": 1.6536878692840188e-05,
      "loss": 0.518,
      "step": 17862
    },
    {
      "epoch": 0.5487359075968421,
      "grad_norm": 0.3710494637489319,
      "learning_rate": 1.6536512958182965e-05,
      "loss": 0.6035,
      "step": 17863
    },
    {
      "epoch": 0.5487666267317912,
      "grad_norm": 0.45756807923316956,
      "learning_rate": 1.6536147208259263e-05,
      "loss": 0.6148,
      "step": 17864
    },
    {
      "epoch": 0.5487973458667403,
      "grad_norm": 0.3563537001609802,
      "learning_rate": 1.653578144306993e-05,
      "loss": 0.6049,
      "step": 17865
    },
    {
      "epoch": 0.5488280650016896,
      "grad_norm": 0.3613763153553009,
      "learning_rate": 1.6535415662615825e-05,
      "loss": 0.5418,
      "step": 17866
    },
    {
      "epoch": 0.5488587841366387,
      "grad_norm": 0.3676871359348297,
      "learning_rate": 1.6535049866897802e-05,
      "loss": 0.5338,
      "step": 17867
    },
    {
      "epoch": 0.5488895032715879,
      "grad_norm": 0.3553885817527771,
      "learning_rate": 1.6534684055916706e-05,
      "loss": 0.5386,
      "step": 17868
    },
    {
      "epoch": 0.548920222406537,
      "grad_norm": 0.42028558254241943,
      "learning_rate": 1.6534318229673405e-05,
      "loss": 0.5,
      "step": 17869
    },
    {
      "epoch": 0.5489509415414862,
      "grad_norm": 0.3791741132736206,
      "learning_rate": 1.6533952388168745e-05,
      "loss": 0.6775,
      "step": 17870
    },
    {
      "epoch": 0.5489816606764354,
      "grad_norm": 0.36319777369499207,
      "learning_rate": 1.6533586531403587e-05,
      "loss": 0.623,
      "step": 17871
    },
    {
      "epoch": 0.5490123798113845,
      "grad_norm": 0.3763711154460907,
      "learning_rate": 1.6533220659378775e-05,
      "loss": 0.565,
      "step": 17872
    },
    {
      "epoch": 0.5490430989463336,
      "grad_norm": 0.3383457362651825,
      "learning_rate": 1.6532854772095176e-05,
      "loss": 0.5733,
      "step": 17873
    },
    {
      "epoch": 0.5490738180812829,
      "grad_norm": 0.3896760642528534,
      "learning_rate": 1.6532488869553634e-05,
      "loss": 0.5032,
      "step": 17874
    },
    {
      "epoch": 0.549104537216232,
      "grad_norm": 0.34761855006217957,
      "learning_rate": 1.6532122951755013e-05,
      "loss": 0.6048,
      "step": 17875
    },
    {
      "epoch": 0.5491352563511811,
      "grad_norm": 0.3611413836479187,
      "learning_rate": 1.6531757018700162e-05,
      "loss": 0.5993,
      "step": 17876
    },
    {
      "epoch": 0.5491659754861303,
      "grad_norm": 0.36839333176612854,
      "learning_rate": 1.6531391070389933e-05,
      "loss": 0.5411,
      "step": 17877
    },
    {
      "epoch": 0.5491966946210795,
      "grad_norm": 0.3564799726009369,
      "learning_rate": 1.6531025106825183e-05,
      "loss": 0.5473,
      "step": 17878
    },
    {
      "epoch": 0.5492274137560287,
      "grad_norm": 0.3468804359436035,
      "learning_rate": 1.653065912800677e-05,
      "loss": 0.5977,
      "step": 17879
    },
    {
      "epoch": 0.5492581328909778,
      "grad_norm": 0.3907046914100647,
      "learning_rate": 1.6530293133935547e-05,
      "loss": 0.6376,
      "step": 17880
    },
    {
      "epoch": 0.5492888520259269,
      "grad_norm": 0.34149959683418274,
      "learning_rate": 1.652992712461237e-05,
      "loss": 0.5975,
      "step": 17881
    },
    {
      "epoch": 0.5493195711608762,
      "grad_norm": 0.33303728699684143,
      "learning_rate": 1.6529561100038086e-05,
      "loss": 0.545,
      "step": 17882
    },
    {
      "epoch": 0.5493502902958253,
      "grad_norm": 0.3381478786468506,
      "learning_rate": 1.652919506021356e-05,
      "loss": 0.5697,
      "step": 17883
    },
    {
      "epoch": 0.5493810094307744,
      "grad_norm": 0.3225345015525818,
      "learning_rate": 1.6528829005139643e-05,
      "loss": 0.5712,
      "step": 17884
    },
    {
      "epoch": 0.5494117285657236,
      "grad_norm": 0.3625480532646179,
      "learning_rate": 1.652846293481719e-05,
      "loss": 0.5357,
      "step": 17885
    },
    {
      "epoch": 0.5494424477006727,
      "grad_norm": 0.33722615242004395,
      "learning_rate": 1.6528096849247055e-05,
      "loss": 0.5659,
      "step": 17886
    },
    {
      "epoch": 0.5494731668356219,
      "grad_norm": 0.3693940341472626,
      "learning_rate": 1.6527730748430096e-05,
      "loss": 0.5532,
      "step": 17887
    },
    {
      "epoch": 0.5495038859705711,
      "grad_norm": 0.3462417423725128,
      "learning_rate": 1.6527364632367163e-05,
      "loss": 0.6064,
      "step": 17888
    },
    {
      "epoch": 0.5495346051055202,
      "grad_norm": 0.3416949212551117,
      "learning_rate": 1.6526998501059115e-05,
      "loss": 0.599,
      "step": 17889
    },
    {
      "epoch": 0.5495653242404694,
      "grad_norm": 0.4237491488456726,
      "learning_rate": 1.6526632354506805e-05,
      "loss": 0.5892,
      "step": 17890
    },
    {
      "epoch": 0.5495960433754186,
      "grad_norm": 0.35294491052627563,
      "learning_rate": 1.6526266192711093e-05,
      "loss": 0.5713,
      "step": 17891
    },
    {
      "epoch": 0.5496267625103677,
      "grad_norm": 0.8422199487686157,
      "learning_rate": 1.6525900015672827e-05,
      "loss": 0.6202,
      "step": 17892
    },
    {
      "epoch": 0.5496574816453169,
      "grad_norm": 0.3258680999279022,
      "learning_rate": 1.6525533823392867e-05,
      "loss": 0.4557,
      "step": 17893
    },
    {
      "epoch": 0.549688200780266,
      "grad_norm": 0.3699376583099365,
      "learning_rate": 1.6525167615872068e-05,
      "loss": 0.6167,
      "step": 17894
    },
    {
      "epoch": 0.5497189199152152,
      "grad_norm": 0.36217713356018066,
      "learning_rate": 1.652480139311128e-05,
      "loss": 0.5665,
      "step": 17895
    },
    {
      "epoch": 0.5497496390501644,
      "grad_norm": 0.3964667022228241,
      "learning_rate": 1.652443515511137e-05,
      "loss": 0.5195,
      "step": 17896
    },
    {
      "epoch": 0.5497803581851135,
      "grad_norm": 0.4052218794822693,
      "learning_rate": 1.6524068901873183e-05,
      "loss": 0.571,
      "step": 17897
    },
    {
      "epoch": 0.5498110773200626,
      "grad_norm": 0.5183062553405762,
      "learning_rate": 1.6523702633397575e-05,
      "loss": 0.5704,
      "step": 17898
    },
    {
      "epoch": 0.5498417964550119,
      "grad_norm": 0.38971054553985596,
      "learning_rate": 1.6523336349685406e-05,
      "loss": 0.5719,
      "step": 17899
    },
    {
      "epoch": 0.549872515589961,
      "grad_norm": 0.36778315901756287,
      "learning_rate": 1.652297005073753e-05,
      "loss": 0.536,
      "step": 17900
    },
    {
      "epoch": 0.5499032347249101,
      "grad_norm": 0.36975592374801636,
      "learning_rate": 1.65226037365548e-05,
      "loss": 0.5444,
      "step": 17901
    },
    {
      "epoch": 0.5499339538598593,
      "grad_norm": 0.4615325927734375,
      "learning_rate": 1.6522237407138076e-05,
      "loss": 0.612,
      "step": 17902
    },
    {
      "epoch": 0.5499646729948084,
      "grad_norm": 0.38011297583580017,
      "learning_rate": 1.6521871062488205e-05,
      "loss": 0.6006,
      "step": 17903
    },
    {
      "epoch": 0.5499953921297577,
      "grad_norm": 0.4380514621734619,
      "learning_rate": 1.6521504702606053e-05,
      "loss": 0.4949,
      "step": 17904
    },
    {
      "epoch": 0.5500261112647068,
      "grad_norm": 0.37127354741096497,
      "learning_rate": 1.6521138327492472e-05,
      "loss": 0.5691,
      "step": 17905
    },
    {
      "epoch": 0.5500568303996559,
      "grad_norm": 0.36025527119636536,
      "learning_rate": 1.6520771937148315e-05,
      "loss": 0.5497,
      "step": 17906
    },
    {
      "epoch": 0.5500875495346051,
      "grad_norm": 0.3407958745956421,
      "learning_rate": 1.652040553157444e-05,
      "loss": 0.5305,
      "step": 17907
    },
    {
      "epoch": 0.5501182686695543,
      "grad_norm": 0.3159032166004181,
      "learning_rate": 1.6520039110771704e-05,
      "loss": 0.5124,
      "step": 17908
    },
    {
      "epoch": 0.5501489878045034,
      "grad_norm": 0.3294544219970703,
      "learning_rate": 1.6519672674740964e-05,
      "loss": 0.4605,
      "step": 17909
    },
    {
      "epoch": 0.5501797069394526,
      "grad_norm": 0.36503270268440247,
      "learning_rate": 1.651930622348307e-05,
      "loss": 0.5466,
      "step": 17910
    },
    {
      "epoch": 0.5502104260744017,
      "grad_norm": 0.36371394991874695,
      "learning_rate": 1.651893975699888e-05,
      "loss": 0.5324,
      "step": 17911
    },
    {
      "epoch": 0.5502411452093509,
      "grad_norm": 0.3435885012149811,
      "learning_rate": 1.6518573275289253e-05,
      "loss": 0.5789,
      "step": 17912
    },
    {
      "epoch": 0.5502718643443001,
      "grad_norm": 0.4175232946872711,
      "learning_rate": 1.651820677835504e-05,
      "loss": 0.4827,
      "step": 17913
    },
    {
      "epoch": 0.5503025834792492,
      "grad_norm": 0.7273060083389282,
      "learning_rate": 1.65178402661971e-05,
      "loss": 0.5125,
      "step": 17914
    },
    {
      "epoch": 0.5503333026141984,
      "grad_norm": 0.45545849204063416,
      "learning_rate": 1.651747373881629e-05,
      "loss": 0.482,
      "step": 17915
    },
    {
      "epoch": 0.5503640217491476,
      "grad_norm": 0.4573293626308441,
      "learning_rate": 1.6517107196213465e-05,
      "loss": 0.5604,
      "step": 17916
    },
    {
      "epoch": 0.5503947408840967,
      "grad_norm": 0.3910965919494629,
      "learning_rate": 1.6516740638389484e-05,
      "loss": 0.4967,
      "step": 17917
    },
    {
      "epoch": 0.5504254600190459,
      "grad_norm": 0.337507426738739,
      "learning_rate": 1.6516374065345196e-05,
      "loss": 0.5635,
      "step": 17918
    },
    {
      "epoch": 0.550456179153995,
      "grad_norm": 0.3612883985042572,
      "learning_rate": 1.6516007477081463e-05,
      "loss": 0.5303,
      "step": 17919
    },
    {
      "epoch": 0.5504868982889441,
      "grad_norm": 0.3509572446346283,
      "learning_rate": 1.651564087359914e-05,
      "loss": 0.4575,
      "step": 17920
    },
    {
      "epoch": 0.5505176174238934,
      "grad_norm": 0.3373236358165741,
      "learning_rate": 1.651527425489908e-05,
      "loss": 0.5164,
      "step": 17921
    },
    {
      "epoch": 0.5505483365588425,
      "grad_norm": 0.41804465651512146,
      "learning_rate": 1.6514907620982143e-05,
      "loss": 0.5658,
      "step": 17922
    },
    {
      "epoch": 0.5505790556937916,
      "grad_norm": 0.3752017617225647,
      "learning_rate": 1.6514540971849187e-05,
      "loss": 0.5438,
      "step": 17923
    },
    {
      "epoch": 0.5506097748287408,
      "grad_norm": 0.37419381737709045,
      "learning_rate": 1.6514174307501062e-05,
      "loss": 0.5966,
      "step": 17924
    },
    {
      "epoch": 0.55064049396369,
      "grad_norm": 0.3528817892074585,
      "learning_rate": 1.651380762793863e-05,
      "loss": 0.5934,
      "step": 17925
    },
    {
      "epoch": 0.5506712130986391,
      "grad_norm": 0.3814813494682312,
      "learning_rate": 1.6513440933162743e-05,
      "loss": 0.6219,
      "step": 17926
    },
    {
      "epoch": 0.5507019322335883,
      "grad_norm": 0.3692583441734314,
      "learning_rate": 1.6513074223174264e-05,
      "loss": 0.5543,
      "step": 17927
    },
    {
      "epoch": 0.5507326513685374,
      "grad_norm": 0.3530328869819641,
      "learning_rate": 1.6512707497974042e-05,
      "loss": 0.599,
      "step": 17928
    },
    {
      "epoch": 0.5507633705034867,
      "grad_norm": 0.3384045958518982,
      "learning_rate": 1.6512340757562938e-05,
      "loss": 0.5718,
      "step": 17929
    },
    {
      "epoch": 0.5507940896384358,
      "grad_norm": 0.3112022578716278,
      "learning_rate": 1.651197400194181e-05,
      "loss": 0.5521,
      "step": 17930
    },
    {
      "epoch": 0.5508248087733849,
      "grad_norm": 0.3793368637561798,
      "learning_rate": 1.6511607231111505e-05,
      "loss": 0.5327,
      "step": 17931
    },
    {
      "epoch": 0.5508555279083341,
      "grad_norm": 0.3697839677333832,
      "learning_rate": 1.651124044507289e-05,
      "loss": 0.5127,
      "step": 17932
    },
    {
      "epoch": 0.5508862470432833,
      "grad_norm": 0.3692989945411682,
      "learning_rate": 1.651087364382682e-05,
      "loss": 0.5774,
      "step": 17933
    },
    {
      "epoch": 0.5509169661782324,
      "grad_norm": 0.45082300901412964,
      "learning_rate": 1.651050682737415e-05,
      "loss": 0.5764,
      "step": 17934
    },
    {
      "epoch": 0.5509476853131816,
      "grad_norm": 0.36269861459732056,
      "learning_rate": 1.6510139995715734e-05,
      "loss": 0.5354,
      "step": 17935
    },
    {
      "epoch": 0.5509784044481307,
      "grad_norm": 0.36267802119255066,
      "learning_rate": 1.6509773148852436e-05,
      "loss": 0.5406,
      "step": 17936
    },
    {
      "epoch": 0.5510091235830799,
      "grad_norm": 0.35712772607803345,
      "learning_rate": 1.65094062867851e-05,
      "loss": 0.6389,
      "step": 17937
    },
    {
      "epoch": 0.5510398427180291,
      "grad_norm": 0.32744428515434265,
      "learning_rate": 1.65090394095146e-05,
      "loss": 0.5717,
      "step": 17938
    },
    {
      "epoch": 0.5510705618529782,
      "grad_norm": 0.35781407356262207,
      "learning_rate": 1.650867251704178e-05,
      "loss": 0.6213,
      "step": 17939
    },
    {
      "epoch": 0.5511012809879274,
      "grad_norm": 0.34238412976264954,
      "learning_rate": 1.65083056093675e-05,
      "loss": 0.594,
      "step": 17940
    },
    {
      "epoch": 0.5511320001228766,
      "grad_norm": 0.5031593441963196,
      "learning_rate": 1.6507938686492616e-05,
      "loss": 0.5486,
      "step": 17941
    },
    {
      "epoch": 0.5511627192578257,
      "grad_norm": 0.3509288728237152,
      "learning_rate": 1.650757174841799e-05,
      "loss": 0.5623,
      "step": 17942
    },
    {
      "epoch": 0.5511934383927749,
      "grad_norm": 0.3697925806045532,
      "learning_rate": 1.6507204795144472e-05,
      "loss": 0.5478,
      "step": 17943
    },
    {
      "epoch": 0.551224157527724,
      "grad_norm": 0.47042933106422424,
      "learning_rate": 1.650683782667293e-05,
      "loss": 0.5423,
      "step": 17944
    },
    {
      "epoch": 0.5512548766626731,
      "grad_norm": 0.3620114326477051,
      "learning_rate": 1.6506470843004208e-05,
      "loss": 0.5438,
      "step": 17945
    },
    {
      "epoch": 0.5512855957976224,
      "grad_norm": 0.3470032513141632,
      "learning_rate": 1.6506103844139167e-05,
      "loss": 0.6023,
      "step": 17946
    },
    {
      "epoch": 0.5513163149325715,
      "grad_norm": 0.3540189862251282,
      "learning_rate": 1.650573683007867e-05,
      "loss": 0.5408,
      "step": 17947
    },
    {
      "epoch": 0.5513470340675206,
      "grad_norm": 0.3788972496986389,
      "learning_rate": 1.650536980082357e-05,
      "loss": 0.5886,
      "step": 17948
    },
    {
      "epoch": 0.5513777532024698,
      "grad_norm": 0.3602831959724426,
      "learning_rate": 1.6505002756374724e-05,
      "loss": 0.5746,
      "step": 17949
    },
    {
      "epoch": 0.551408472337419,
      "grad_norm": 0.502042829990387,
      "learning_rate": 1.6504635696732992e-05,
      "loss": 0.5573,
      "step": 17950
    },
    {
      "epoch": 0.5514391914723681,
      "grad_norm": 0.35111406445503235,
      "learning_rate": 1.6504268621899226e-05,
      "loss": 0.5843,
      "step": 17951
    },
    {
      "epoch": 0.5514699106073173,
      "grad_norm": 0.35634422302246094,
      "learning_rate": 1.6503901531874287e-05,
      "loss": 0.6438,
      "step": 17952
    },
    {
      "epoch": 0.5515006297422664,
      "grad_norm": 0.3504487872123718,
      "learning_rate": 1.6503534426659032e-05,
      "loss": 0.5555,
      "step": 17953
    },
    {
      "epoch": 0.5515313488772157,
      "grad_norm": 0.35313940048217773,
      "learning_rate": 1.6503167306254318e-05,
      "loss": 0.554,
      "step": 17954
    },
    {
      "epoch": 0.5515620680121648,
      "grad_norm": 0.3352429270744324,
      "learning_rate": 1.6502800170661002e-05,
      "loss": 0.5558,
      "step": 17955
    },
    {
      "epoch": 0.5515927871471139,
      "grad_norm": 0.35531893372535706,
      "learning_rate": 1.6502433019879945e-05,
      "loss": 0.5585,
      "step": 17956
    },
    {
      "epoch": 0.5516235062820631,
      "grad_norm": 0.33617955446243286,
      "learning_rate": 1.6502065853911997e-05,
      "loss": 0.5634,
      "step": 17957
    },
    {
      "epoch": 0.5516542254170123,
      "grad_norm": 0.32530298829078674,
      "learning_rate": 1.6501698672758022e-05,
      "loss": 0.5145,
      "step": 17958
    },
    {
      "epoch": 0.5516849445519614,
      "grad_norm": 0.37184685468673706,
      "learning_rate": 1.6501331476418877e-05,
      "loss": 0.6321,
      "step": 17959
    },
    {
      "epoch": 0.5517156636869106,
      "grad_norm": 0.3637303411960602,
      "learning_rate": 1.6500964264895417e-05,
      "loss": 0.6084,
      "step": 17960
    },
    {
      "epoch": 0.5517463828218597,
      "grad_norm": 0.3975439965724945,
      "learning_rate": 1.6500597038188502e-05,
      "loss": 0.6418,
      "step": 17961
    },
    {
      "epoch": 0.5517771019568088,
      "grad_norm": 0.3827633261680603,
      "learning_rate": 1.6500229796298985e-05,
      "loss": 0.5514,
      "step": 17962
    },
    {
      "epoch": 0.5518078210917581,
      "grad_norm": 0.385158509016037,
      "learning_rate": 1.649986253922773e-05,
      "loss": 0.5725,
      "step": 17963
    },
    {
      "epoch": 0.5518385402267072,
      "grad_norm": 0.37808895111083984,
      "learning_rate": 1.6499495266975593e-05,
      "loss": 0.5948,
      "step": 17964
    },
    {
      "epoch": 0.5518692593616564,
      "grad_norm": 0.4545128047466278,
      "learning_rate": 1.649912797954343e-05,
      "loss": 0.6164,
      "step": 17965
    },
    {
      "epoch": 0.5518999784966055,
      "grad_norm": 0.3740076720714569,
      "learning_rate": 1.6498760676932102e-05,
      "loss": 0.6176,
      "step": 17966
    },
    {
      "epoch": 0.5519306976315547,
      "grad_norm": 0.38371187448501587,
      "learning_rate": 1.649839335914246e-05,
      "loss": 0.5716,
      "step": 17967
    },
    {
      "epoch": 0.5519614167665039,
      "grad_norm": 0.34170669317245483,
      "learning_rate": 1.6498026026175373e-05,
      "loss": 0.5933,
      "step": 17968
    },
    {
      "epoch": 0.551992135901453,
      "grad_norm": 0.3537026345729828,
      "learning_rate": 1.6497658678031685e-05,
      "loss": 0.5636,
      "step": 17969
    },
    {
      "epoch": 0.5520228550364021,
      "grad_norm": 0.43965739011764526,
      "learning_rate": 1.6497291314712267e-05,
      "loss": 0.6337,
      "step": 17970
    },
    {
      "epoch": 0.5520535741713514,
      "grad_norm": 0.3640703856945038,
      "learning_rate": 1.649692393621797e-05,
      "loss": 0.5745,
      "step": 17971
    },
    {
      "epoch": 0.5520842933063005,
      "grad_norm": 0.4630148708820343,
      "learning_rate": 1.649655654254965e-05,
      "loss": 0.6414,
      "step": 17972
    },
    {
      "epoch": 0.5521150124412496,
      "grad_norm": 0.36114972829818726,
      "learning_rate": 1.6496189133708172e-05,
      "loss": 0.6063,
      "step": 17973
    },
    {
      "epoch": 0.5521457315761988,
      "grad_norm": 0.36431121826171875,
      "learning_rate": 1.6495821709694388e-05,
      "loss": 0.5808,
      "step": 17974
    },
    {
      "epoch": 0.552176450711148,
      "grad_norm": 0.338574081659317,
      "learning_rate": 1.6495454270509163e-05,
      "loss": 0.5853,
      "step": 17975
    },
    {
      "epoch": 0.5522071698460971,
      "grad_norm": 0.42442944645881653,
      "learning_rate": 1.6495086816153344e-05,
      "loss": 0.5447,
      "step": 17976
    },
    {
      "epoch": 0.5522378889810463,
      "grad_norm": 0.3278902769088745,
      "learning_rate": 1.64947193466278e-05,
      "loss": 0.5532,
      "step": 17977
    },
    {
      "epoch": 0.5522686081159954,
      "grad_norm": 0.37699246406555176,
      "learning_rate": 1.6494351861933387e-05,
      "loss": 0.5902,
      "step": 17978
    },
    {
      "epoch": 0.5522993272509447,
      "grad_norm": 0.36531922221183777,
      "learning_rate": 1.649398436207096e-05,
      "loss": 0.5684,
      "step": 17979
    },
    {
      "epoch": 0.5523300463858938,
      "grad_norm": 0.3895452320575714,
      "learning_rate": 1.649361684704138e-05,
      "loss": 0.5522,
      "step": 17980
    },
    {
      "epoch": 0.5523607655208429,
      "grad_norm": 0.37074753642082214,
      "learning_rate": 1.6493249316845502e-05,
      "loss": 0.599,
      "step": 17981
    },
    {
      "epoch": 0.5523914846557921,
      "grad_norm": 0.353380411863327,
      "learning_rate": 1.6492881771484192e-05,
      "loss": 0.542,
      "step": 17982
    },
    {
      "epoch": 0.5524222037907413,
      "grad_norm": 0.34879082441329956,
      "learning_rate": 1.64925142109583e-05,
      "loss": 0.5332,
      "step": 17983
    },
    {
      "epoch": 0.5524529229256904,
      "grad_norm": 0.3733726739883423,
      "learning_rate": 1.6492146635268683e-05,
      "loss": 0.5556,
      "step": 17984
    },
    {
      "epoch": 0.5524836420606396,
      "grad_norm": 0.4090191721916199,
      "learning_rate": 1.649177904441621e-05,
      "loss": 0.6297,
      "step": 17985
    },
    {
      "epoch": 0.5525143611955887,
      "grad_norm": 0.3826545774936676,
      "learning_rate": 1.6491411438401735e-05,
      "loss": 0.671,
      "step": 17986
    },
    {
      "epoch": 0.5525450803305378,
      "grad_norm": 0.4285891056060791,
      "learning_rate": 1.6491043817226108e-05,
      "loss": 0.5623,
      "step": 17987
    },
    {
      "epoch": 0.5525757994654871,
      "grad_norm": 0.3469213545322418,
      "learning_rate": 1.64906761808902e-05,
      "loss": 0.5899,
      "step": 17988
    },
    {
      "epoch": 0.5526065186004362,
      "grad_norm": 0.3562980890274048,
      "learning_rate": 1.6490308529394866e-05,
      "loss": 0.549,
      "step": 17989
    },
    {
      "epoch": 0.5526372377353854,
      "grad_norm": 0.34952667355537415,
      "learning_rate": 1.6489940862740962e-05,
      "loss": 0.6062,
      "step": 17990
    },
    {
      "epoch": 0.5526679568703345,
      "grad_norm": 0.370668888092041,
      "learning_rate": 1.6489573180929346e-05,
      "loss": 0.5621,
      "step": 17991
    },
    {
      "epoch": 0.5526986760052837,
      "grad_norm": 0.36219051480293274,
      "learning_rate": 1.648920548396088e-05,
      "loss": 0.5397,
      "step": 17992
    },
    {
      "epoch": 0.5527293951402329,
      "grad_norm": 0.3857770264148712,
      "learning_rate": 1.6488837771836417e-05,
      "loss": 0.5713,
      "step": 17993
    },
    {
      "epoch": 0.552760114275182,
      "grad_norm": 0.3422977328300476,
      "learning_rate": 1.6488470044556824e-05,
      "loss": 0.5745,
      "step": 17994
    },
    {
      "epoch": 0.5527908334101311,
      "grad_norm": 0.414061576128006,
      "learning_rate": 1.648810230212296e-05,
      "loss": 0.5861,
      "step": 17995
    },
    {
      "epoch": 0.5528215525450804,
      "grad_norm": 0.3965770900249481,
      "learning_rate": 1.6487734544535673e-05,
      "loss": 0.5479,
      "step": 17996
    },
    {
      "epoch": 0.5528522716800295,
      "grad_norm": 0.3686218857765198,
      "learning_rate": 1.6487366771795833e-05,
      "loss": 0.5543,
      "step": 17997
    },
    {
      "epoch": 0.5528829908149786,
      "grad_norm": 0.3542101979255676,
      "learning_rate": 1.648699898390429e-05,
      "loss": 0.5423,
      "step": 17998
    },
    {
      "epoch": 0.5529137099499278,
      "grad_norm": 0.34118229150772095,
      "learning_rate": 1.648663118086191e-05,
      "loss": 0.5695,
      "step": 17999
    },
    {
      "epoch": 0.552944429084877,
      "grad_norm": 0.370038777589798,
      "learning_rate": 1.6486263362669554e-05,
      "loss": 0.5708,
      "step": 18000
    },
    {
      "epoch": 0.5529751482198262,
      "grad_norm": 0.34807291626930237,
      "learning_rate": 1.6485895529328074e-05,
      "loss": 0.61,
      "step": 18001
    },
    {
      "epoch": 0.5530058673547753,
      "grad_norm": 0.33801597356796265,
      "learning_rate": 1.648552768083833e-05,
      "loss": 0.534,
      "step": 18002
    },
    {
      "epoch": 0.5530365864897244,
      "grad_norm": 0.31639260053634644,
      "learning_rate": 1.648515981720119e-05,
      "loss": 0.6056,
      "step": 18003
    },
    {
      "epoch": 0.5530673056246737,
      "grad_norm": 0.342925488948822,
      "learning_rate": 1.64847919384175e-05,
      "loss": 0.5402,
      "step": 18004
    },
    {
      "epoch": 0.5530980247596228,
      "grad_norm": 0.3372143805027008,
      "learning_rate": 1.6484424044488125e-05,
      "loss": 0.6199,
      "step": 18005
    },
    {
      "epoch": 0.5531287438945719,
      "grad_norm": 0.4069660007953644,
      "learning_rate": 1.6484056135413927e-05,
      "loss": 0.6368,
      "step": 18006
    },
    {
      "epoch": 0.5531594630295211,
      "grad_norm": 0.3762266933917999,
      "learning_rate": 1.6483688211195766e-05,
      "loss": 0.6625,
      "step": 18007
    },
    {
      "epoch": 0.5531901821644702,
      "grad_norm": 0.3324330449104309,
      "learning_rate": 1.6483320271834492e-05,
      "loss": 0.5715,
      "step": 18008
    },
    {
      "epoch": 0.5532209012994194,
      "grad_norm": 0.38232681155204773,
      "learning_rate": 1.6482952317330977e-05,
      "loss": 0.5526,
      "step": 18009
    },
    {
      "epoch": 0.5532516204343686,
      "grad_norm": 0.3661487102508545,
      "learning_rate": 1.648258434768607e-05,
      "loss": 0.6058,
      "step": 18010
    },
    {
      "epoch": 0.5532823395693177,
      "grad_norm": 0.4109456539154053,
      "learning_rate": 1.6482216362900638e-05,
      "loss": 0.5695,
      "step": 18011
    },
    {
      "epoch": 0.5533130587042668,
      "grad_norm": 0.33979228138923645,
      "learning_rate": 1.6481848362975532e-05,
      "loss": 0.6009,
      "step": 18012
    },
    {
      "epoch": 0.5533437778392161,
      "grad_norm": 0.49084925651550293,
      "learning_rate": 1.648148034791162e-05,
      "loss": 0.5544,
      "step": 18013
    },
    {
      "epoch": 0.5533744969741652,
      "grad_norm": 0.3432353436946869,
      "learning_rate": 1.6481112317709756e-05,
      "loss": 0.5838,
      "step": 18014
    },
    {
      "epoch": 0.5534052161091144,
      "grad_norm": 0.4049654006958008,
      "learning_rate": 1.6480744272370803e-05,
      "loss": 0.5214,
      "step": 18015
    },
    {
      "epoch": 0.5534359352440635,
      "grad_norm": 0.35836079716682434,
      "learning_rate": 1.6480376211895615e-05,
      "loss": 0.5907,
      "step": 18016
    },
    {
      "epoch": 0.5534666543790127,
      "grad_norm": 0.8291093111038208,
      "learning_rate": 1.648000813628506e-05,
      "loss": 0.6375,
      "step": 18017
    },
    {
      "epoch": 0.5534973735139619,
      "grad_norm": 0.3273581564426422,
      "learning_rate": 1.6479640045539995e-05,
      "loss": 0.5299,
      "step": 18018
    },
    {
      "epoch": 0.553528092648911,
      "grad_norm": 0.5420558452606201,
      "learning_rate": 1.6479271939661276e-05,
      "loss": 0.5353,
      "step": 18019
    },
    {
      "epoch": 0.5535588117838601,
      "grad_norm": 0.43158918619155884,
      "learning_rate": 1.6478903818649765e-05,
      "loss": 0.5551,
      "step": 18020
    },
    {
      "epoch": 0.5535895309188094,
      "grad_norm": 0.37662720680236816,
      "learning_rate": 1.6478535682506325e-05,
      "loss": 0.5393,
      "step": 18021
    },
    {
      "epoch": 0.5536202500537585,
      "grad_norm": 0.3826872706413269,
      "learning_rate": 1.6478167531231804e-05,
      "loss": 0.6277,
      "step": 18022
    },
    {
      "epoch": 0.5536509691887076,
      "grad_norm": 0.3610899746417999,
      "learning_rate": 1.647779936482708e-05,
      "loss": 0.5334,
      "step": 18023
    },
    {
      "epoch": 0.5536816883236568,
      "grad_norm": 0.3746196925640106,
      "learning_rate": 1.6477431183292997e-05,
      "loss": 0.5622,
      "step": 18024
    },
    {
      "epoch": 0.553712407458606,
      "grad_norm": 0.33936890959739685,
      "learning_rate": 1.6477062986630422e-05,
      "loss": 0.5927,
      "step": 18025
    },
    {
      "epoch": 0.5537431265935552,
      "grad_norm": 0.32986265420913696,
      "learning_rate": 1.6476694774840215e-05,
      "loss": 0.5847,
      "step": 18026
    },
    {
      "epoch": 0.5537738457285043,
      "grad_norm": 0.37801727652549744,
      "learning_rate": 1.6476326547923236e-05,
      "loss": 0.5217,
      "step": 18027
    },
    {
      "epoch": 0.5538045648634534,
      "grad_norm": 0.4452407956123352,
      "learning_rate": 1.6475958305880343e-05,
      "loss": 0.6024,
      "step": 18028
    },
    {
      "epoch": 0.5538352839984026,
      "grad_norm": 0.44289934635162354,
      "learning_rate": 1.64755900487124e-05,
      "loss": 0.6098,
      "step": 18029
    },
    {
      "epoch": 0.5538660031333518,
      "grad_norm": 0.382323294878006,
      "learning_rate": 1.6475221776420258e-05,
      "loss": 0.5926,
      "step": 18030
    },
    {
      "epoch": 0.5538967222683009,
      "grad_norm": 0.3203197419643402,
      "learning_rate": 1.6474853489004784e-05,
      "loss": 0.6111,
      "step": 18031
    },
    {
      "epoch": 0.5539274414032501,
      "grad_norm": 0.36737388372421265,
      "learning_rate": 1.647448518646684e-05,
      "loss": 0.6032,
      "step": 18032
    },
    {
      "epoch": 0.5539581605381992,
      "grad_norm": 0.34248343110084534,
      "learning_rate": 1.6474116868807284e-05,
      "loss": 0.5362,
      "step": 18033
    },
    {
      "epoch": 0.5539888796731484,
      "grad_norm": 0.36715924739837646,
      "learning_rate": 1.6473748536026978e-05,
      "loss": 0.537,
      "step": 18034
    },
    {
      "epoch": 0.5540195988080976,
      "grad_norm": 0.4749939739704132,
      "learning_rate": 1.6473380188126776e-05,
      "loss": 0.5891,
      "step": 18035
    },
    {
      "epoch": 0.5540503179430467,
      "grad_norm": 0.3676639199256897,
      "learning_rate": 1.6473011825107543e-05,
      "loss": 0.5485,
      "step": 18036
    },
    {
      "epoch": 0.5540810370779958,
      "grad_norm": 0.3352046608924866,
      "learning_rate": 1.647264344697014e-05,
      "loss": 0.557,
      "step": 18037
    },
    {
      "epoch": 0.5541117562129451,
      "grad_norm": 0.3171288073062897,
      "learning_rate": 1.6472275053715428e-05,
      "loss": 0.4696,
      "step": 18038
    },
    {
      "epoch": 0.5541424753478942,
      "grad_norm": 0.3696851134300232,
      "learning_rate": 1.6471906645344266e-05,
      "loss": 0.553,
      "step": 18039
    },
    {
      "epoch": 0.5541731944828434,
      "grad_norm": 0.32081520557403564,
      "learning_rate": 1.647153822185751e-05,
      "loss": 0.5258,
      "step": 18040
    },
    {
      "epoch": 0.5542039136177925,
      "grad_norm": 0.3922933340072632,
      "learning_rate": 1.6471169783256026e-05,
      "loss": 0.5341,
      "step": 18041
    },
    {
      "epoch": 0.5542346327527417,
      "grad_norm": 0.42852094769477844,
      "learning_rate": 1.6470801329540673e-05,
      "loss": 0.4933,
      "step": 18042
    },
    {
      "epoch": 0.5542653518876909,
      "grad_norm": 0.3755708932876587,
      "learning_rate": 1.647043286071231e-05,
      "loss": 0.56,
      "step": 18043
    },
    {
      "epoch": 0.55429607102264,
      "grad_norm": 0.34481075406074524,
      "learning_rate": 1.64700643767718e-05,
      "loss": 0.5747,
      "step": 18044
    },
    {
      "epoch": 0.5543267901575891,
      "grad_norm": 0.33457884192466736,
      "learning_rate": 1.6469695877720008e-05,
      "loss": 0.5925,
      "step": 18045
    },
    {
      "epoch": 0.5543575092925384,
      "grad_norm": 0.39829161763191223,
      "learning_rate": 1.646932736355778e-05,
      "loss": 0.5388,
      "step": 18046
    },
    {
      "epoch": 0.5543882284274875,
      "grad_norm": 0.38678058981895447,
      "learning_rate": 1.6468958834285995e-05,
      "loss": 0.6458,
      "step": 18047
    },
    {
      "epoch": 0.5544189475624366,
      "grad_norm": 0.3805958330631256,
      "learning_rate": 1.6468590289905503e-05,
      "loss": 0.6031,
      "step": 18048
    },
    {
      "epoch": 0.5544496666973858,
      "grad_norm": 0.3324504792690277,
      "learning_rate": 1.6468221730417165e-05,
      "loss": 0.6399,
      "step": 18049
    },
    {
      "epoch": 0.5544803858323349,
      "grad_norm": 0.31636732816696167,
      "learning_rate": 1.646785315582184e-05,
      "loss": 0.5028,
      "step": 18050
    },
    {
      "epoch": 0.5545111049672842,
      "grad_norm": 0.3241938054561615,
      "learning_rate": 1.6467484566120397e-05,
      "loss": 0.5594,
      "step": 18051
    },
    {
      "epoch": 0.5545418241022333,
      "grad_norm": 0.36225005984306335,
      "learning_rate": 1.6467115961313692e-05,
      "loss": 0.5298,
      "step": 18052
    },
    {
      "epoch": 0.5545725432371824,
      "grad_norm": 0.36613234877586365,
      "learning_rate": 1.6466747341402584e-05,
      "loss": 0.5231,
      "step": 18053
    },
    {
      "epoch": 0.5546032623721316,
      "grad_norm": 0.30728545784950256,
      "learning_rate": 1.6466378706387933e-05,
      "loss": 0.4806,
      "step": 18054
    },
    {
      "epoch": 0.5546339815070808,
      "grad_norm": 0.3686978816986084,
      "learning_rate": 1.646601005627061e-05,
      "loss": 0.5617,
      "step": 18055
    },
    {
      "epoch": 0.5546647006420299,
      "grad_norm": 0.3388842046260834,
      "learning_rate": 1.6465641391051462e-05,
      "loss": 0.5935,
      "step": 18056
    },
    {
      "epoch": 0.5546954197769791,
      "grad_norm": 0.39687085151672363,
      "learning_rate": 1.6465272710731363e-05,
      "loss": 0.6073,
      "step": 18057
    },
    {
      "epoch": 0.5547261389119282,
      "grad_norm": 0.3743288218975067,
      "learning_rate": 1.6464904015311164e-05,
      "loss": 0.5516,
      "step": 18058
    },
    {
      "epoch": 0.5547568580468774,
      "grad_norm": 0.3594745099544525,
      "learning_rate": 1.646453530479173e-05,
      "loss": 0.4765,
      "step": 18059
    },
    {
      "epoch": 0.5547875771818266,
      "grad_norm": 0.38174283504486084,
      "learning_rate": 1.6464166579173927e-05,
      "loss": 0.5998,
      "step": 18060
    },
    {
      "epoch": 0.5548182963167757,
      "grad_norm": 0.3640986979007721,
      "learning_rate": 1.6463797838458607e-05,
      "loss": 0.6256,
      "step": 18061
    },
    {
      "epoch": 0.5548490154517248,
      "grad_norm": 0.36679190397262573,
      "learning_rate": 1.646342908264664e-05,
      "loss": 0.6886,
      "step": 18062
    },
    {
      "epoch": 0.5548797345866741,
      "grad_norm": 0.37264320254325867,
      "learning_rate": 1.6463060311738878e-05,
      "loss": 0.5261,
      "step": 18063
    },
    {
      "epoch": 0.5549104537216232,
      "grad_norm": 0.4239799380302429,
      "learning_rate": 1.646269152573619e-05,
      "loss": 0.5879,
      "step": 18064
    },
    {
      "epoch": 0.5549411728565724,
      "grad_norm": 0.4692404568195343,
      "learning_rate": 1.6462322724639434e-05,
      "loss": 0.4979,
      "step": 18065
    },
    {
      "epoch": 0.5549718919915215,
      "grad_norm": 0.34827038645744324,
      "learning_rate": 1.6461953908449474e-05,
      "loss": 0.4961,
      "step": 18066
    },
    {
      "epoch": 0.5550026111264706,
      "grad_norm": 0.3667001724243164,
      "learning_rate": 1.6461585077167165e-05,
      "loss": 0.5956,
      "step": 18067
    },
    {
      "epoch": 0.5550333302614199,
      "grad_norm": 0.31638917326927185,
      "learning_rate": 1.6461216230793376e-05,
      "loss": 0.5447,
      "step": 18068
    },
    {
      "epoch": 0.555064049396369,
      "grad_norm": 0.3821481168270111,
      "learning_rate": 1.6460847369328962e-05,
      "loss": 0.6417,
      "step": 18069
    },
    {
      "epoch": 0.5550947685313181,
      "grad_norm": 0.3495928943157196,
      "learning_rate": 1.6460478492774793e-05,
      "loss": 0.5113,
      "step": 18070
    },
    {
      "epoch": 0.5551254876662673,
      "grad_norm": 0.35703957080841064,
      "learning_rate": 1.6460109601131724e-05,
      "loss": 0.5108,
      "step": 18071
    },
    {
      "epoch": 0.5551562068012165,
      "grad_norm": 0.361086905002594,
      "learning_rate": 1.6459740694400616e-05,
      "loss": 0.4977,
      "step": 18072
    },
    {
      "epoch": 0.5551869259361656,
      "grad_norm": 0.3744036555290222,
      "learning_rate": 1.645937177258233e-05,
      "loss": 0.5426,
      "step": 18073
    },
    {
      "epoch": 0.5552176450711148,
      "grad_norm": 0.36260131001472473,
      "learning_rate": 1.6459002835677734e-05,
      "loss": 0.4426,
      "step": 18074
    },
    {
      "epoch": 0.5552483642060639,
      "grad_norm": 0.3505665957927704,
      "learning_rate": 1.6458633883687684e-05,
      "loss": 0.5504,
      "step": 18075
    },
    {
      "epoch": 0.5552790833410132,
      "grad_norm": 0.3240140974521637,
      "learning_rate": 1.6458264916613044e-05,
      "loss": 0.6133,
      "step": 18076
    },
    {
      "epoch": 0.5553098024759623,
      "grad_norm": 0.3162482678890228,
      "learning_rate": 1.6457895934454676e-05,
      "loss": 0.5551,
      "step": 18077
    },
    {
      "epoch": 0.5553405216109114,
      "grad_norm": 0.3891441822052002,
      "learning_rate": 1.645752693721344e-05,
      "loss": 0.6449,
      "step": 18078
    },
    {
      "epoch": 0.5553712407458606,
      "grad_norm": 0.32309237122535706,
      "learning_rate": 1.6457157924890198e-05,
      "loss": 0.5754,
      "step": 18079
    },
    {
      "epoch": 0.5554019598808098,
      "grad_norm": 0.3514380156993866,
      "learning_rate": 1.6456788897485813e-05,
      "loss": 0.5328,
      "step": 18080
    },
    {
      "epoch": 0.5554326790157589,
      "grad_norm": 0.3570708632469177,
      "learning_rate": 1.6456419855001148e-05,
      "loss": 0.6132,
      "step": 18081
    },
    {
      "epoch": 0.5554633981507081,
      "grad_norm": 0.3780149221420288,
      "learning_rate": 1.6456050797437064e-05,
      "loss": 0.658,
      "step": 18082
    },
    {
      "epoch": 0.5554941172856572,
      "grad_norm": 0.32998964190483093,
      "learning_rate": 1.6455681724794425e-05,
      "loss": 0.4901,
      "step": 18083
    },
    {
      "epoch": 0.5555248364206063,
      "grad_norm": 0.3374941647052765,
      "learning_rate": 1.6455312637074087e-05,
      "loss": 0.519,
      "step": 18084
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.37378427386283875,
      "learning_rate": 1.6454943534276916e-05,
      "loss": 0.588,
      "step": 18085
    },
    {
      "epoch": 0.5555862746905047,
      "grad_norm": 0.3448309898376465,
      "learning_rate": 1.645457441640377e-05,
      "loss": 0.5139,
      "step": 18086
    },
    {
      "epoch": 0.5556169938254538,
      "grad_norm": 0.3666008412837982,
      "learning_rate": 1.6454205283455516e-05,
      "loss": 0.6277,
      "step": 18087
    },
    {
      "epoch": 0.555647712960403,
      "grad_norm": 0.37824520468711853,
      "learning_rate": 1.6453836135433016e-05,
      "loss": 0.5886,
      "step": 18088
    },
    {
      "epoch": 0.5556784320953522,
      "grad_norm": 0.3514859080314636,
      "learning_rate": 1.6453466972337135e-05,
      "loss": 0.4816,
      "step": 18089
    },
    {
      "epoch": 0.5557091512303014,
      "grad_norm": 0.414920449256897,
      "learning_rate": 1.6453097794168725e-05,
      "loss": 0.5651,
      "step": 18090
    },
    {
      "epoch": 0.5557398703652505,
      "grad_norm": 0.4304389953613281,
      "learning_rate": 1.645272860092866e-05,
      "loss": 0.5541,
      "step": 18091
    },
    {
      "epoch": 0.5557705895001996,
      "grad_norm": 0.3533284366130829,
      "learning_rate": 1.6452359392617792e-05,
      "loss": 0.4494,
      "step": 18092
    },
    {
      "epoch": 0.5558013086351489,
      "grad_norm": 0.4192480444908142,
      "learning_rate": 1.645199016923699e-05,
      "loss": 0.5975,
      "step": 18093
    },
    {
      "epoch": 0.555832027770098,
      "grad_norm": 0.4062107503414154,
      "learning_rate": 1.6451620930787116e-05,
      "loss": 0.5245,
      "step": 18094
    },
    {
      "epoch": 0.5558627469050471,
      "grad_norm": 0.3516167998313904,
      "learning_rate": 1.6451251677269027e-05,
      "loss": 0.5843,
      "step": 18095
    },
    {
      "epoch": 0.5558934660399963,
      "grad_norm": 0.3633265793323517,
      "learning_rate": 1.645088240868359e-05,
      "loss": 0.5449,
      "step": 18096
    },
    {
      "epoch": 0.5559241851749455,
      "grad_norm": 0.3878440260887146,
      "learning_rate": 1.645051312503167e-05,
      "loss": 0.5007,
      "step": 18097
    },
    {
      "epoch": 0.5559549043098946,
      "grad_norm": 0.33819565176963806,
      "learning_rate": 1.6450143826314123e-05,
      "loss": 0.6283,
      "step": 18098
    },
    {
      "epoch": 0.5559856234448438,
      "grad_norm": 0.4877866804599762,
      "learning_rate": 1.6449774512531815e-05,
      "loss": 0.6247,
      "step": 18099
    },
    {
      "epoch": 0.5560163425797929,
      "grad_norm": 0.37979239225387573,
      "learning_rate": 1.6449405183685606e-05,
      "loss": 0.613,
      "step": 18100
    },
    {
      "epoch": 0.5560470617147422,
      "grad_norm": 0.34859177470207214,
      "learning_rate": 1.644903583977637e-05,
      "loss": 0.5699,
      "step": 18101
    },
    {
      "epoch": 0.5560777808496913,
      "grad_norm": 0.3174418807029724,
      "learning_rate": 1.644866648080495e-05,
      "loss": 0.6464,
      "step": 18102
    },
    {
      "epoch": 0.5561084999846404,
      "grad_norm": 0.3643397390842438,
      "learning_rate": 1.6448297106772225e-05,
      "loss": 0.5244,
      "step": 18103
    },
    {
      "epoch": 0.5561392191195896,
      "grad_norm": 0.33690184354782104,
      "learning_rate": 1.644792771767905e-05,
      "loss": 0.6037,
      "step": 18104
    },
    {
      "epoch": 0.5561699382545388,
      "grad_norm": 0.45900076627731323,
      "learning_rate": 1.6447558313526288e-05,
      "loss": 0.5602,
      "step": 18105
    },
    {
      "epoch": 0.5562006573894879,
      "grad_norm": 0.33045345544815063,
      "learning_rate": 1.6447188894314802e-05,
      "loss": 0.5654,
      "step": 18106
    },
    {
      "epoch": 0.5562313765244371,
      "grad_norm": 0.37989968061447144,
      "learning_rate": 1.644681946004546e-05,
      "loss": 0.6272,
      "step": 18107
    },
    {
      "epoch": 0.5562620956593862,
      "grad_norm": 0.3749091327190399,
      "learning_rate": 1.6446450010719116e-05,
      "loss": 0.5666,
      "step": 18108
    },
    {
      "epoch": 0.5562928147943353,
      "grad_norm": 0.3636021316051483,
      "learning_rate": 1.644608054633664e-05,
      "loss": 0.5309,
      "step": 18109
    },
    {
      "epoch": 0.5563235339292846,
      "grad_norm": 0.34137076139450073,
      "learning_rate": 1.6445711066898897e-05,
      "loss": 0.4802,
      "step": 18110
    },
    {
      "epoch": 0.5563542530642337,
      "grad_norm": 0.3303718566894531,
      "learning_rate": 1.6445341572406745e-05,
      "loss": 0.5244,
      "step": 18111
    },
    {
      "epoch": 0.5563849721991829,
      "grad_norm": 0.3544222414493561,
      "learning_rate": 1.6444972062861042e-05,
      "loss": 0.5407,
      "step": 18112
    },
    {
      "epoch": 0.556415691334132,
      "grad_norm": 0.3696824908256531,
      "learning_rate": 1.644460253826266e-05,
      "loss": 0.6244,
      "step": 18113
    },
    {
      "epoch": 0.5564464104690812,
      "grad_norm": 0.3947255313396454,
      "learning_rate": 1.644423299861246e-05,
      "loss": 0.6131,
      "step": 18114
    },
    {
      "epoch": 0.5564771296040304,
      "grad_norm": 0.3669195771217346,
      "learning_rate": 1.64438634439113e-05,
      "loss": 0.5853,
      "step": 18115
    },
    {
      "epoch": 0.5565078487389795,
      "grad_norm": 0.36843934655189514,
      "learning_rate": 1.6443493874160052e-05,
      "loss": 0.5899,
      "step": 18116
    },
    {
      "epoch": 0.5565385678739286,
      "grad_norm": 0.3622927665710449,
      "learning_rate": 1.6443124289359568e-05,
      "loss": 0.5526,
      "step": 18117
    },
    {
      "epoch": 0.5565692870088779,
      "grad_norm": 0.36338430643081665,
      "learning_rate": 1.6442754689510723e-05,
      "loss": 0.5883,
      "step": 18118
    },
    {
      "epoch": 0.556600006143827,
      "grad_norm": 0.34312906861305237,
      "learning_rate": 1.644238507461437e-05,
      "loss": 0.6484,
      "step": 18119
    },
    {
      "epoch": 0.5566307252787761,
      "grad_norm": 0.37810587882995605,
      "learning_rate": 1.644201544467138e-05,
      "loss": 0.5762,
      "step": 18120
    },
    {
      "epoch": 0.5566614444137253,
      "grad_norm": 0.34684544801712036,
      "learning_rate": 1.644164579968261e-05,
      "loss": 0.5435,
      "step": 18121
    },
    {
      "epoch": 0.5566921635486745,
      "grad_norm": 0.36880791187286377,
      "learning_rate": 1.644127613964893e-05,
      "loss": 0.5331,
      "step": 18122
    },
    {
      "epoch": 0.5567228826836236,
      "grad_norm": 0.3571726083755493,
      "learning_rate": 1.6440906464571195e-05,
      "loss": 0.5974,
      "step": 18123
    },
    {
      "epoch": 0.5567536018185728,
      "grad_norm": 0.3532472848892212,
      "learning_rate": 1.644053677445028e-05,
      "loss": 0.5871,
      "step": 18124
    },
    {
      "epoch": 0.5567843209535219,
      "grad_norm": 0.3901354670524597,
      "learning_rate": 1.6440167069287033e-05,
      "loss": 0.563,
      "step": 18125
    },
    {
      "epoch": 0.5568150400884712,
      "grad_norm": 0.3383614718914032,
      "learning_rate": 1.6439797349082332e-05,
      "loss": 0.5223,
      "step": 18126
    },
    {
      "epoch": 0.5568457592234203,
      "grad_norm": 0.3414274752140045,
      "learning_rate": 1.6439427613837033e-05,
      "loss": 0.4746,
      "step": 18127
    },
    {
      "epoch": 0.5568764783583694,
      "grad_norm": 0.3449627757072449,
      "learning_rate": 1.6439057863552e-05,
      "loss": 0.6166,
      "step": 18128
    },
    {
      "epoch": 0.5569071974933186,
      "grad_norm": 0.36452627182006836,
      "learning_rate": 1.64386880982281e-05,
      "loss": 0.582,
      "step": 18129
    },
    {
      "epoch": 0.5569379166282677,
      "grad_norm": 0.34187355637550354,
      "learning_rate": 1.6438318317866194e-05,
      "loss": 0.5516,
      "step": 18130
    },
    {
      "epoch": 0.5569686357632169,
      "grad_norm": 0.34251707792282104,
      "learning_rate": 1.6437948522467146e-05,
      "loss": 0.517,
      "step": 18131
    },
    {
      "epoch": 0.5569993548981661,
      "grad_norm": 0.3362055718898773,
      "learning_rate": 1.6437578712031816e-05,
      "loss": 0.5141,
      "step": 18132
    },
    {
      "epoch": 0.5570300740331152,
      "grad_norm": 0.3587389886379242,
      "learning_rate": 1.6437208886561072e-05,
      "loss": 0.6346,
      "step": 18133
    },
    {
      "epoch": 0.5570607931680643,
      "grad_norm": 0.3970523178577423,
      "learning_rate": 1.6436839046055778e-05,
      "loss": 0.6119,
      "step": 18134
    },
    {
      "epoch": 0.5570915123030136,
      "grad_norm": 0.35949409008026123,
      "learning_rate": 1.64364691905168e-05,
      "loss": 0.5855,
      "step": 18135
    },
    {
      "epoch": 0.5571222314379627,
      "grad_norm": 0.36410772800445557,
      "learning_rate": 1.6436099319944996e-05,
      "loss": 0.6194,
      "step": 18136
    },
    {
      "epoch": 0.5571529505729119,
      "grad_norm": 0.32069629430770874,
      "learning_rate": 1.6435729434341235e-05,
      "loss": 0.5219,
      "step": 18137
    },
    {
      "epoch": 0.557183669707861,
      "grad_norm": 0.36733824014663696,
      "learning_rate": 1.6435359533706376e-05,
      "loss": 0.5605,
      "step": 18138
    },
    {
      "epoch": 0.5572143888428102,
      "grad_norm": 0.328702449798584,
      "learning_rate": 1.6434989618041287e-05,
      "loss": 0.5886,
      "step": 18139
    },
    {
      "epoch": 0.5572451079777594,
      "grad_norm": 0.3309843838214874,
      "learning_rate": 1.6434619687346825e-05,
      "loss": 0.57,
      "step": 18140
    },
    {
      "epoch": 0.5572758271127085,
      "grad_norm": 0.3251156210899353,
      "learning_rate": 1.6434249741623864e-05,
      "loss": 0.5651,
      "step": 18141
    },
    {
      "epoch": 0.5573065462476576,
      "grad_norm": 0.3991723656654358,
      "learning_rate": 1.6433879780873265e-05,
      "loss": 0.5802,
      "step": 18142
    },
    {
      "epoch": 0.5573372653826069,
      "grad_norm": 0.3539898693561554,
      "learning_rate": 1.6433509805095888e-05,
      "loss": 0.4768,
      "step": 18143
    },
    {
      "epoch": 0.557367984517556,
      "grad_norm": 0.36886066198349,
      "learning_rate": 1.6433139814292597e-05,
      "loss": 0.6009,
      "step": 18144
    },
    {
      "epoch": 0.5573987036525051,
      "grad_norm": 0.3185298442840576,
      "learning_rate": 1.6432769808464262e-05,
      "loss": 0.6039,
      "step": 18145
    },
    {
      "epoch": 0.5574294227874543,
      "grad_norm": 0.37571555376052856,
      "learning_rate": 1.6432399787611742e-05,
      "loss": 0.5296,
      "step": 18146
    },
    {
      "epoch": 0.5574601419224035,
      "grad_norm": 0.38762977719306946,
      "learning_rate": 1.6432029751735907e-05,
      "loss": 0.6063,
      "step": 18147
    },
    {
      "epoch": 0.5574908610573526,
      "grad_norm": 0.3807118833065033,
      "learning_rate": 1.6431659700837614e-05,
      "loss": 0.6131,
      "step": 18148
    },
    {
      "epoch": 0.5575215801923018,
      "grad_norm": 0.344454824924469,
      "learning_rate": 1.643128963491773e-05,
      "loss": 0.5795,
      "step": 18149
    },
    {
      "epoch": 0.5575522993272509,
      "grad_norm": 0.36965569853782654,
      "learning_rate": 1.6430919553977123e-05,
      "loss": 0.466,
      "step": 18150
    },
    {
      "epoch": 0.5575830184622002,
      "grad_norm": 0.3372235596179962,
      "learning_rate": 1.6430549458016653e-05,
      "loss": 0.5424,
      "step": 18151
    },
    {
      "epoch": 0.5576137375971493,
      "grad_norm": 0.34868597984313965,
      "learning_rate": 1.6430179347037184e-05,
      "loss": 0.5525,
      "step": 18152
    },
    {
      "epoch": 0.5576444567320984,
      "grad_norm": 0.3582879602909088,
      "learning_rate": 1.6429809221039585e-05,
      "loss": 0.5281,
      "step": 18153
    },
    {
      "epoch": 0.5576751758670476,
      "grad_norm": 0.4008615016937256,
      "learning_rate": 1.6429439080024714e-05,
      "loss": 0.5341,
      "step": 18154
    },
    {
      "epoch": 0.5577058950019967,
      "grad_norm": 0.35551801323890686,
      "learning_rate": 1.6429068923993443e-05,
      "loss": 0.5328,
      "step": 18155
    },
    {
      "epoch": 0.5577366141369459,
      "grad_norm": 0.42726704478263855,
      "learning_rate": 1.6428698752946627e-05,
      "loss": 0.5126,
      "step": 18156
    },
    {
      "epoch": 0.5577673332718951,
      "grad_norm": 0.4363044202327728,
      "learning_rate": 1.642832856688514e-05,
      "loss": 0.4937,
      "step": 18157
    },
    {
      "epoch": 0.5577980524068442,
      "grad_norm": 0.3768385350704193,
      "learning_rate": 1.642795836580984e-05,
      "loss": 0.5943,
      "step": 18158
    },
    {
      "epoch": 0.5578287715417933,
      "grad_norm": 0.3888286054134369,
      "learning_rate": 1.6427588149721597e-05,
      "loss": 0.6453,
      "step": 18159
    },
    {
      "epoch": 0.5578594906767426,
      "grad_norm": 0.3555689752101898,
      "learning_rate": 1.6427217918621276e-05,
      "loss": 0.4996,
      "step": 18160
    },
    {
      "epoch": 0.5578902098116917,
      "grad_norm": 0.4131220579147339,
      "learning_rate": 1.6426847672509732e-05,
      "loss": 0.5601,
      "step": 18161
    },
    {
      "epoch": 0.5579209289466409,
      "grad_norm": 0.3446046710014343,
      "learning_rate": 1.642647741138784e-05,
      "loss": 0.6065,
      "step": 18162
    },
    {
      "epoch": 0.55795164808159,
      "grad_norm": 0.38040891289711,
      "learning_rate": 1.642610713525646e-05,
      "loss": 0.6107,
      "step": 18163
    },
    {
      "epoch": 0.5579823672165392,
      "grad_norm": 0.39905956387519836,
      "learning_rate": 1.6425736844116456e-05,
      "loss": 0.4956,
      "step": 18164
    },
    {
      "epoch": 0.5580130863514884,
      "grad_norm": 0.3566291928291321,
      "learning_rate": 1.6425366537968698e-05,
      "loss": 0.5593,
      "step": 18165
    },
    {
      "epoch": 0.5580438054864375,
      "grad_norm": 0.41945379972457886,
      "learning_rate": 1.642499621681405e-05,
      "loss": 0.5395,
      "step": 18166
    },
    {
      "epoch": 0.5580745246213866,
      "grad_norm": 0.4910784661769867,
      "learning_rate": 1.6424625880653373e-05,
      "loss": 0.6251,
      "step": 18167
    },
    {
      "epoch": 0.5581052437563359,
      "grad_norm": 0.3586128354072571,
      "learning_rate": 1.642425552948753e-05,
      "loss": 0.5674,
      "step": 18168
    },
    {
      "epoch": 0.558135962891285,
      "grad_norm": 0.34144243597984314,
      "learning_rate": 1.642388516331739e-05,
      "loss": 0.5413,
      "step": 18169
    },
    {
      "epoch": 0.5581666820262341,
      "grad_norm": 0.33174246549606323,
      "learning_rate": 1.642351478214382e-05,
      "loss": 0.5836,
      "step": 18170
    },
    {
      "epoch": 0.5581974011611833,
      "grad_norm": 0.3666834235191345,
      "learning_rate": 1.642314438596768e-05,
      "loss": 0.631,
      "step": 18171
    },
    {
      "epoch": 0.5582281202961324,
      "grad_norm": 0.3504158556461334,
      "learning_rate": 1.6422773974789843e-05,
      "loss": 0.6092,
      "step": 18172
    },
    {
      "epoch": 0.5582588394310816,
      "grad_norm": 0.3692774176597595,
      "learning_rate": 1.6422403548611167e-05,
      "loss": 0.5086,
      "step": 18173
    },
    {
      "epoch": 0.5582895585660308,
      "grad_norm": 0.39314061403274536,
      "learning_rate": 1.6422033107432516e-05,
      "loss": 0.5678,
      "step": 18174
    },
    {
      "epoch": 0.5583202777009799,
      "grad_norm": 0.3757001757621765,
      "learning_rate": 1.6421662651254758e-05,
      "loss": 0.6384,
      "step": 18175
    },
    {
      "epoch": 0.5583509968359291,
      "grad_norm": 0.38963937759399414,
      "learning_rate": 1.642129218007876e-05,
      "loss": 0.6559,
      "step": 18176
    },
    {
      "epoch": 0.5583817159708783,
      "grad_norm": 0.35618260502815247,
      "learning_rate": 1.6420921693905387e-05,
      "loss": 0.5789,
      "step": 18177
    },
    {
      "epoch": 0.5584124351058274,
      "grad_norm": 0.3812629282474518,
      "learning_rate": 1.6420551192735502e-05,
      "loss": 0.6191,
      "step": 18178
    },
    {
      "epoch": 0.5584431542407766,
      "grad_norm": 0.3535442352294922,
      "learning_rate": 1.642018067656997e-05,
      "loss": 0.5636,
      "step": 18179
    },
    {
      "epoch": 0.5584738733757257,
      "grad_norm": 0.41114184260368347,
      "learning_rate": 1.6419810145409657e-05,
      "loss": 0.6276,
      "step": 18180
    },
    {
      "epoch": 0.5585045925106749,
      "grad_norm": 0.37413156032562256,
      "learning_rate": 1.641943959925543e-05,
      "loss": 0.5398,
      "step": 18181
    },
    {
      "epoch": 0.5585353116456241,
      "grad_norm": 0.3655870258808136,
      "learning_rate": 1.6419069038108157e-05,
      "loss": 0.5466,
      "step": 18182
    },
    {
      "epoch": 0.5585660307805732,
      "grad_norm": 0.3902820348739624,
      "learning_rate": 1.6418698461968697e-05,
      "loss": 0.5538,
      "step": 18183
    },
    {
      "epoch": 0.5585967499155223,
      "grad_norm": 0.4353218376636505,
      "learning_rate": 1.6418327870837916e-05,
      "loss": 0.6711,
      "step": 18184
    },
    {
      "epoch": 0.5586274690504716,
      "grad_norm": 0.36239686608314514,
      "learning_rate": 1.6417957264716685e-05,
      "loss": 0.5433,
      "step": 18185
    },
    {
      "epoch": 0.5586581881854207,
      "grad_norm": 0.3538099229335785,
      "learning_rate": 1.6417586643605868e-05,
      "loss": 0.5504,
      "step": 18186
    },
    {
      "epoch": 0.5586889073203699,
      "grad_norm": 0.323838472366333,
      "learning_rate": 1.6417216007506324e-05,
      "loss": 0.5601,
      "step": 18187
    },
    {
      "epoch": 0.558719626455319,
      "grad_norm": 0.36410993337631226,
      "learning_rate": 1.641684535641893e-05,
      "loss": 0.5533,
      "step": 18188
    },
    {
      "epoch": 0.5587503455902681,
      "grad_norm": 0.35782501101493835,
      "learning_rate": 1.6416474690344544e-05,
      "loss": 0.6808,
      "step": 18189
    },
    {
      "epoch": 0.5587810647252174,
      "grad_norm": 0.5148554444313049,
      "learning_rate": 1.641610400928403e-05,
      "loss": 0.5293,
      "step": 18190
    },
    {
      "epoch": 0.5588117838601665,
      "grad_norm": 0.3458652198314667,
      "learning_rate": 1.641573331323826e-05,
      "loss": 0.5483,
      "step": 18191
    },
    {
      "epoch": 0.5588425029951156,
      "grad_norm": 0.3390131890773773,
      "learning_rate": 1.6415362602208094e-05,
      "loss": 0.5424,
      "step": 18192
    },
    {
      "epoch": 0.5588732221300649,
      "grad_norm": 0.347152441740036,
      "learning_rate": 1.64149918761944e-05,
      "loss": 0.5581,
      "step": 18193
    },
    {
      "epoch": 0.558903941265014,
      "grad_norm": 0.39561134576797485,
      "learning_rate": 1.641462113519805e-05,
      "loss": 0.5492,
      "step": 18194
    },
    {
      "epoch": 0.5589346603999631,
      "grad_norm": 0.3736646771430969,
      "learning_rate": 1.64142503792199e-05,
      "loss": 0.599,
      "step": 18195
    },
    {
      "epoch": 0.5589653795349123,
      "grad_norm": 0.40045326948165894,
      "learning_rate": 1.6413879608260822e-05,
      "loss": 0.5662,
      "step": 18196
    },
    {
      "epoch": 0.5589960986698614,
      "grad_norm": 0.335266649723053,
      "learning_rate": 1.641350882232168e-05,
      "loss": 0.5537,
      "step": 18197
    },
    {
      "epoch": 0.5590268178048107,
      "grad_norm": 0.3653803765773773,
      "learning_rate": 1.6413138021403338e-05,
      "loss": 0.5705,
      "step": 18198
    },
    {
      "epoch": 0.5590575369397598,
      "grad_norm": 0.32527318596839905,
      "learning_rate": 1.641276720550667e-05,
      "loss": 0.55,
      "step": 18199
    },
    {
      "epoch": 0.5590882560747089,
      "grad_norm": 0.34172680974006653,
      "learning_rate": 1.641239637463253e-05,
      "loss": 0.5657,
      "step": 18200
    },
    {
      "epoch": 0.5591189752096581,
      "grad_norm": 0.4386487901210785,
      "learning_rate": 1.641202552878179e-05,
      "loss": 0.5677,
      "step": 18201
    },
    {
      "epoch": 0.5591496943446073,
      "grad_norm": 0.36914634704589844,
      "learning_rate": 1.641165466795532e-05,
      "loss": 0.6215,
      "step": 18202
    },
    {
      "epoch": 0.5591804134795564,
      "grad_norm": 0.3624131381511688,
      "learning_rate": 1.6411283792153984e-05,
      "loss": 0.5296,
      "step": 18203
    },
    {
      "epoch": 0.5592111326145056,
      "grad_norm": 0.3696311116218567,
      "learning_rate": 1.6410912901378644e-05,
      "loss": 0.6148,
      "step": 18204
    },
    {
      "epoch": 0.5592418517494547,
      "grad_norm": 0.37843847274780273,
      "learning_rate": 1.641054199563017e-05,
      "loss": 0.5699,
      "step": 18205
    },
    {
      "epoch": 0.5592725708844039,
      "grad_norm": 0.3409684896469116,
      "learning_rate": 1.641017107490943e-05,
      "loss": 0.4868,
      "step": 18206
    },
    {
      "epoch": 0.5593032900193531,
      "grad_norm": 0.3667132258415222,
      "learning_rate": 1.6409800139217285e-05,
      "loss": 0.5583,
      "step": 18207
    },
    {
      "epoch": 0.5593340091543022,
      "grad_norm": 0.3611859977245331,
      "learning_rate": 1.6409429188554605e-05,
      "loss": 0.5325,
      "step": 18208
    },
    {
      "epoch": 0.5593647282892513,
      "grad_norm": 0.36242538690567017,
      "learning_rate": 1.6409058222922253e-05,
      "loss": 0.5743,
      "step": 18209
    },
    {
      "epoch": 0.5593954474242006,
      "grad_norm": 0.3478143811225891,
      "learning_rate": 1.6408687242321102e-05,
      "loss": 0.5363,
      "step": 18210
    },
    {
      "epoch": 0.5594261665591497,
      "grad_norm": 0.3512100875377655,
      "learning_rate": 1.640831624675201e-05,
      "loss": 0.4839,
      "step": 18211
    },
    {
      "epoch": 0.5594568856940989,
      "grad_norm": 0.32411709427833557,
      "learning_rate": 1.640794523621585e-05,
      "loss": 0.4938,
      "step": 18212
    },
    {
      "epoch": 0.559487604829048,
      "grad_norm": 0.3498245179653168,
      "learning_rate": 1.6407574210713487e-05,
      "loss": 0.5151,
      "step": 18213
    },
    {
      "epoch": 0.5595183239639971,
      "grad_norm": 0.4278414845466614,
      "learning_rate": 1.6407203170245788e-05,
      "loss": 0.5924,
      "step": 18214
    },
    {
      "epoch": 0.5595490430989464,
      "grad_norm": 0.3493061065673828,
      "learning_rate": 1.6406832114813616e-05,
      "loss": 0.5136,
      "step": 18215
    },
    {
      "epoch": 0.5595797622338955,
      "grad_norm": 0.3669366240501404,
      "learning_rate": 1.640646104441784e-05,
      "loss": 0.6091,
      "step": 18216
    },
    {
      "epoch": 0.5596104813688446,
      "grad_norm": 0.3359493911266327,
      "learning_rate": 1.6406089959059328e-05,
      "loss": 0.5568,
      "step": 18217
    },
    {
      "epoch": 0.5596412005037938,
      "grad_norm": 0.46759530901908875,
      "learning_rate": 1.640571885873895e-05,
      "loss": 0.5256,
      "step": 18218
    },
    {
      "epoch": 0.559671919638743,
      "grad_norm": 0.5210440158843994,
      "learning_rate": 1.640534774345756e-05,
      "loss": 0.4767,
      "step": 18219
    },
    {
      "epoch": 0.5597026387736921,
      "grad_norm": 0.3605891466140747,
      "learning_rate": 1.640497661321604e-05,
      "loss": 0.5753,
      "step": 18220
    },
    {
      "epoch": 0.5597333579086413,
      "grad_norm": 0.33855172991752625,
      "learning_rate": 1.6404605468015244e-05,
      "loss": 0.5327,
      "step": 18221
    },
    {
      "epoch": 0.5597640770435904,
      "grad_norm": 0.32920607924461365,
      "learning_rate": 1.640423430785605e-05,
      "loss": 0.5929,
      "step": 18222
    },
    {
      "epoch": 0.5597947961785397,
      "grad_norm": 0.39223313331604004,
      "learning_rate": 1.6403863132739315e-05,
      "loss": 0.6098,
      "step": 18223
    },
    {
      "epoch": 0.5598255153134888,
      "grad_norm": 1.3575190305709839,
      "learning_rate": 1.6403491942665913e-05,
      "loss": 0.6937,
      "step": 18224
    },
    {
      "epoch": 0.5598562344484379,
      "grad_norm": 0.3290095925331116,
      "learning_rate": 1.6403120737636708e-05,
      "loss": 0.5255,
      "step": 18225
    },
    {
      "epoch": 0.5598869535833871,
      "grad_norm": 0.42775648832321167,
      "learning_rate": 1.6402749517652567e-05,
      "loss": 0.528,
      "step": 18226
    },
    {
      "epoch": 0.5599176727183363,
      "grad_norm": 0.3124074637889862,
      "learning_rate": 1.6402378282714357e-05,
      "loss": 0.5176,
      "step": 18227
    },
    {
      "epoch": 0.5599483918532854,
      "grad_norm": 0.37547728419303894,
      "learning_rate": 1.6402007032822946e-05,
      "loss": 0.5624,
      "step": 18228
    },
    {
      "epoch": 0.5599791109882346,
      "grad_norm": 0.4067326784133911,
      "learning_rate": 1.6401635767979198e-05,
      "loss": 0.5871,
      "step": 18229
    },
    {
      "epoch": 0.5600098301231837,
      "grad_norm": 0.32499584555625916,
      "learning_rate": 1.6401264488183986e-05,
      "loss": 0.4691,
      "step": 18230
    },
    {
      "epoch": 0.5600405492581328,
      "grad_norm": 0.33055633306503296,
      "learning_rate": 1.640089319343817e-05,
      "loss": 0.5161,
      "step": 18231
    },
    {
      "epoch": 0.5600712683930821,
      "grad_norm": 0.33913561701774597,
      "learning_rate": 1.6400521883742624e-05,
      "loss": 0.5544,
      "step": 18232
    },
    {
      "epoch": 0.5601019875280312,
      "grad_norm": 0.3364281952381134,
      "learning_rate": 1.6400150559098208e-05,
      "loss": 0.4905,
      "step": 18233
    },
    {
      "epoch": 0.5601327066629803,
      "grad_norm": 0.32342082262039185,
      "learning_rate": 1.63997792195058e-05,
      "loss": 0.5809,
      "step": 18234
    },
    {
      "epoch": 0.5601634257979295,
      "grad_norm": 0.34555554389953613,
      "learning_rate": 1.6399407864966254e-05,
      "loss": 0.5726,
      "step": 18235
    },
    {
      "epoch": 0.5601941449328787,
      "grad_norm": 0.39152103662490845,
      "learning_rate": 1.639903649548045e-05,
      "loss": 0.5785,
      "step": 18236
    },
    {
      "epoch": 0.5602248640678279,
      "grad_norm": 0.3774889409542084,
      "learning_rate": 1.639866511104925e-05,
      "loss": 0.4759,
      "step": 18237
    },
    {
      "epoch": 0.560255583202777,
      "grad_norm": 0.34826338291168213,
      "learning_rate": 1.6398293711673514e-05,
      "loss": 0.5455,
      "step": 18238
    },
    {
      "epoch": 0.5602863023377261,
      "grad_norm": 0.3539230227470398,
      "learning_rate": 1.639792229735412e-05,
      "loss": 0.6053,
      "step": 18239
    },
    {
      "epoch": 0.5603170214726754,
      "grad_norm": 0.3673689067363739,
      "learning_rate": 1.639755086809193e-05,
      "loss": 0.5566,
      "step": 18240
    },
    {
      "epoch": 0.5603477406076245,
      "grad_norm": 0.34748345613479614,
      "learning_rate": 1.639717942388782e-05,
      "loss": 0.5952,
      "step": 18241
    },
    {
      "epoch": 0.5603784597425736,
      "grad_norm": 0.323214590549469,
      "learning_rate": 1.6396807964742644e-05,
      "loss": 0.537,
      "step": 18242
    },
    {
      "epoch": 0.5604091788775228,
      "grad_norm": 0.3709036409854889,
      "learning_rate": 1.6396436490657275e-05,
      "loss": 0.611,
      "step": 18243
    },
    {
      "epoch": 0.560439898012472,
      "grad_norm": 0.6865405440330505,
      "learning_rate": 1.6396065001632583e-05,
      "loss": 0.5612,
      "step": 18244
    },
    {
      "epoch": 0.5604706171474211,
      "grad_norm": 0.3535831868648529,
      "learning_rate": 1.6395693497669438e-05,
      "loss": 0.6486,
      "step": 18245
    },
    {
      "epoch": 0.5605013362823703,
      "grad_norm": 0.36926111578941345,
      "learning_rate": 1.63953219787687e-05,
      "loss": 0.617,
      "step": 18246
    },
    {
      "epoch": 0.5605320554173194,
      "grad_norm": 0.3667214810848236,
      "learning_rate": 1.6394950444931243e-05,
      "loss": 0.6052,
      "step": 18247
    },
    {
      "epoch": 0.5605627745522687,
      "grad_norm": 0.3207518458366394,
      "learning_rate": 1.6394578896157935e-05,
      "loss": 0.6041,
      "step": 18248
    },
    {
      "epoch": 0.5605934936872178,
      "grad_norm": 0.39291703701019287,
      "learning_rate": 1.6394207332449636e-05,
      "loss": 0.5558,
      "step": 18249
    },
    {
      "epoch": 0.5606242128221669,
      "grad_norm": 0.38127240538597107,
      "learning_rate": 1.6393835753807225e-05,
      "loss": 0.4745,
      "step": 18250
    },
    {
      "epoch": 0.5606549319571161,
      "grad_norm": 0.3397308886051178,
      "learning_rate": 1.639346416023156e-05,
      "loss": 0.6014,
      "step": 18251
    },
    {
      "epoch": 0.5606856510920653,
      "grad_norm": 0.35461941361427307,
      "learning_rate": 1.639309255172351e-05,
      "loss": 0.5679,
      "step": 18252
    },
    {
      "epoch": 0.5607163702270144,
      "grad_norm": 0.37306392192840576,
      "learning_rate": 1.639272092828395e-05,
      "loss": 0.5295,
      "step": 18253
    },
    {
      "epoch": 0.5607470893619636,
      "grad_norm": 0.34354424476623535,
      "learning_rate": 1.6392349289913746e-05,
      "loss": 0.5114,
      "step": 18254
    },
    {
      "epoch": 0.5607778084969127,
      "grad_norm": 0.3535819351673126,
      "learning_rate": 1.6391977636613763e-05,
      "loss": 0.5737,
      "step": 18255
    },
    {
      "epoch": 0.5608085276318618,
      "grad_norm": 0.3559393584728241,
      "learning_rate": 1.639160596838487e-05,
      "loss": 0.6027,
      "step": 18256
    },
    {
      "epoch": 0.5608392467668111,
      "grad_norm": 0.39871057868003845,
      "learning_rate": 1.639123428522793e-05,
      "loss": 0.5607,
      "step": 18257
    },
    {
      "epoch": 0.5608699659017602,
      "grad_norm": 0.36241641640663147,
      "learning_rate": 1.639086258714382e-05,
      "loss": 0.4846,
      "step": 18258
    },
    {
      "epoch": 0.5609006850367093,
      "grad_norm": 0.35196876525878906,
      "learning_rate": 1.63904908741334e-05,
      "loss": 0.6541,
      "step": 18259
    },
    {
      "epoch": 0.5609314041716585,
      "grad_norm": 0.39547646045684814,
      "learning_rate": 1.6390119146197547e-05,
      "loss": 0.5826,
      "step": 18260
    },
    {
      "epoch": 0.5609621233066077,
      "grad_norm": 0.3569241166114807,
      "learning_rate": 1.6389747403337125e-05,
      "loss": 0.5899,
      "step": 18261
    },
    {
      "epoch": 0.5609928424415569,
      "grad_norm": 0.34032267332077026,
      "learning_rate": 1.6389375645553e-05,
      "loss": 0.5511,
      "step": 18262
    },
    {
      "epoch": 0.561023561576506,
      "grad_norm": 0.33130836486816406,
      "learning_rate": 1.6389003872846043e-05,
      "loss": 0.533,
      "step": 18263
    },
    {
      "epoch": 0.5610542807114551,
      "grad_norm": 0.3252285420894623,
      "learning_rate": 1.6388632085217117e-05,
      "loss": 0.5985,
      "step": 18264
    },
    {
      "epoch": 0.5610849998464044,
      "grad_norm": 0.49088340997695923,
      "learning_rate": 1.63882602826671e-05,
      "loss": 0.5152,
      "step": 18265
    },
    {
      "epoch": 0.5611157189813535,
      "grad_norm": 0.34332042932510376,
      "learning_rate": 1.638788846519685e-05,
      "loss": 0.5864,
      "step": 18266
    },
    {
      "epoch": 0.5611464381163026,
      "grad_norm": 0.35154619812965393,
      "learning_rate": 1.6387516632807245e-05,
      "loss": 0.6297,
      "step": 18267
    },
    {
      "epoch": 0.5611771572512518,
      "grad_norm": 0.32828062772750854,
      "learning_rate": 1.6387144785499146e-05,
      "loss": 0.5539,
      "step": 18268
    },
    {
      "epoch": 0.561207876386201,
      "grad_norm": 0.37525415420532227,
      "learning_rate": 1.6386772923273424e-05,
      "loss": 0.5017,
      "step": 18269
    },
    {
      "epoch": 0.5612385955211501,
      "grad_norm": 0.3517823815345764,
      "learning_rate": 1.6386401046130948e-05,
      "loss": 0.5508,
      "step": 18270
    },
    {
      "epoch": 0.5612693146560993,
      "grad_norm": 0.33707189559936523,
      "learning_rate": 1.6386029154072587e-05,
      "loss": 0.5631,
      "step": 18271
    },
    {
      "epoch": 0.5613000337910484,
      "grad_norm": 0.3309095501899719,
      "learning_rate": 1.638565724709921e-05,
      "loss": 0.4992,
      "step": 18272
    },
    {
      "epoch": 0.5613307529259977,
      "grad_norm": 0.32127001881599426,
      "learning_rate": 1.6385285325211683e-05,
      "loss": 0.4751,
      "step": 18273
    },
    {
      "epoch": 0.5613614720609468,
      "grad_norm": 0.5863350033760071,
      "learning_rate": 1.6384913388410873e-05,
      "loss": 0.6004,
      "step": 18274
    },
    {
      "epoch": 0.5613921911958959,
      "grad_norm": 0.41985172033309937,
      "learning_rate": 1.638454143669766e-05,
      "loss": 0.5394,
      "step": 18275
    },
    {
      "epoch": 0.5614229103308451,
      "grad_norm": 0.4216601550579071,
      "learning_rate": 1.63841694700729e-05,
      "loss": 0.5651,
      "step": 18276
    },
    {
      "epoch": 0.5614536294657942,
      "grad_norm": 0.5192256569862366,
      "learning_rate": 1.6383797488537466e-05,
      "loss": 0.5273,
      "step": 18277
    },
    {
      "epoch": 0.5614843486007434,
      "grad_norm": 0.3898274898529053,
      "learning_rate": 1.6383425492092225e-05,
      "loss": 0.5111,
      "step": 18278
    },
    {
      "epoch": 0.5615150677356926,
      "grad_norm": 0.3738938868045807,
      "learning_rate": 1.6383053480738053e-05,
      "loss": 0.5814,
      "step": 18279
    },
    {
      "epoch": 0.5615457868706417,
      "grad_norm": 0.40917128324508667,
      "learning_rate": 1.6382681454475812e-05,
      "loss": 0.574,
      "step": 18280
    },
    {
      "epoch": 0.5615765060055908,
      "grad_norm": 0.38891077041625977,
      "learning_rate": 1.638230941330637e-05,
      "loss": 0.5714,
      "step": 18281
    },
    {
      "epoch": 0.5616072251405401,
      "grad_norm": 0.3454788327217102,
      "learning_rate": 1.63819373572306e-05,
      "loss": 0.4987,
      "step": 18282
    },
    {
      "epoch": 0.5616379442754892,
      "grad_norm": 0.3409501910209656,
      "learning_rate": 1.6381565286249374e-05,
      "loss": 0.4977,
      "step": 18283
    },
    {
      "epoch": 0.5616686634104383,
      "grad_norm": 0.36741289496421814,
      "learning_rate": 1.638119320036355e-05,
      "loss": 0.5559,
      "step": 18284
    },
    {
      "epoch": 0.5616993825453875,
      "grad_norm": 0.4043771028518677,
      "learning_rate": 1.6380821099574003e-05,
      "loss": 0.6091,
      "step": 18285
    },
    {
      "epoch": 0.5617301016803367,
      "grad_norm": 0.3646406829357147,
      "learning_rate": 1.638044898388161e-05,
      "loss": 0.5962,
      "step": 18286
    },
    {
      "epoch": 0.5617608208152859,
      "grad_norm": 0.33014020323753357,
      "learning_rate": 1.638007685328723e-05,
      "loss": 0.5619,
      "step": 18287
    },
    {
      "epoch": 0.561791539950235,
      "grad_norm": 0.36028778553009033,
      "learning_rate": 1.637970470779173e-05,
      "loss": 0.6179,
      "step": 18288
    },
    {
      "epoch": 0.5618222590851841,
      "grad_norm": 0.3770008087158203,
      "learning_rate": 1.637933254739599e-05,
      "loss": 0.5381,
      "step": 18289
    },
    {
      "epoch": 0.5618529782201334,
      "grad_norm": 0.34158238768577576,
      "learning_rate": 1.6378960372100873e-05,
      "loss": 0.5514,
      "step": 18290
    },
    {
      "epoch": 0.5618836973550825,
      "grad_norm": 0.37825217843055725,
      "learning_rate": 1.6378588181907244e-05,
      "loss": 0.566,
      "step": 18291
    },
    {
      "epoch": 0.5619144164900316,
      "grad_norm": 0.3243420720100403,
      "learning_rate": 1.6378215976815982e-05,
      "loss": 0.5483,
      "step": 18292
    },
    {
      "epoch": 0.5619451356249808,
      "grad_norm": 0.3592986464500427,
      "learning_rate": 1.637784375682795e-05,
      "loss": 0.5846,
      "step": 18293
    },
    {
      "epoch": 0.56197585475993,
      "grad_norm": 0.6025839447975159,
      "learning_rate": 1.6377471521944014e-05,
      "loss": 0.4927,
      "step": 18294
    },
    {
      "epoch": 0.5620065738948791,
      "grad_norm": 0.4292632043361664,
      "learning_rate": 1.6377099272165052e-05,
      "loss": 0.5326,
      "step": 18295
    },
    {
      "epoch": 0.5620372930298283,
      "grad_norm": 0.804132342338562,
      "learning_rate": 1.6376727007491928e-05,
      "loss": 0.497,
      "step": 18296
    },
    {
      "epoch": 0.5620680121647774,
      "grad_norm": 0.38239943981170654,
      "learning_rate": 1.6376354727925514e-05,
      "loss": 0.5781,
      "step": 18297
    },
    {
      "epoch": 0.5620987312997267,
      "grad_norm": 0.36316099762916565,
      "learning_rate": 1.6375982433466676e-05,
      "loss": 0.6191,
      "step": 18298
    },
    {
      "epoch": 0.5621294504346758,
      "grad_norm": 0.3502183258533478,
      "learning_rate": 1.6375610124116287e-05,
      "loss": 0.4801,
      "step": 18299
    },
    {
      "epoch": 0.5621601695696249,
      "grad_norm": 0.35420987010002136,
      "learning_rate": 1.6375237799875218e-05,
      "loss": 0.5412,
      "step": 18300
    },
    {
      "epoch": 0.5621908887045741,
      "grad_norm": 0.3302285373210907,
      "learning_rate": 1.6374865460744333e-05,
      "loss": 0.5919,
      "step": 18301
    },
    {
      "epoch": 0.5622216078395232,
      "grad_norm": 0.4001822769641876,
      "learning_rate": 1.6374493106724503e-05,
      "loss": 0.5605,
      "step": 18302
    },
    {
      "epoch": 0.5622523269744724,
      "grad_norm": 0.3733326196670532,
      "learning_rate": 1.63741207378166e-05,
      "loss": 0.5395,
      "step": 18303
    },
    {
      "epoch": 0.5622830461094216,
      "grad_norm": 0.35609152913093567,
      "learning_rate": 1.6373748354021496e-05,
      "loss": 0.5867,
      "step": 18304
    },
    {
      "epoch": 0.5623137652443707,
      "grad_norm": 0.3737259805202484,
      "learning_rate": 1.6373375955340055e-05,
      "loss": 0.5433,
      "step": 18305
    },
    {
      "epoch": 0.5623444843793198,
      "grad_norm": 0.43974149227142334,
      "learning_rate": 1.6373003541773148e-05,
      "loss": 0.5299,
      "step": 18306
    },
    {
      "epoch": 0.5623752035142691,
      "grad_norm": 0.39898762106895447,
      "learning_rate": 1.637263111332165e-05,
      "loss": 0.5153,
      "step": 18307
    },
    {
      "epoch": 0.5624059226492182,
      "grad_norm": 0.37221604585647583,
      "learning_rate": 1.6372258669986423e-05,
      "loss": 0.5965,
      "step": 18308
    },
    {
      "epoch": 0.5624366417841674,
      "grad_norm": 0.36592745780944824,
      "learning_rate": 1.6371886211768344e-05,
      "loss": 0.4937,
      "step": 18309
    },
    {
      "epoch": 0.5624673609191165,
      "grad_norm": 0.38017022609710693,
      "learning_rate": 1.6371513738668278e-05,
      "loss": 0.5082,
      "step": 18310
    },
    {
      "epoch": 0.5624980800540657,
      "grad_norm": 0.3409700393676758,
      "learning_rate": 1.6371141250687097e-05,
      "loss": 0.5166,
      "step": 18311
    },
    {
      "epoch": 0.5625287991890149,
      "grad_norm": 0.32671815156936646,
      "learning_rate": 1.637076874782567e-05,
      "loss": 0.5226,
      "step": 18312
    },
    {
      "epoch": 0.562559518323964,
      "grad_norm": 0.3445340394973755,
      "learning_rate": 1.637039623008487e-05,
      "loss": 0.616,
      "step": 18313
    },
    {
      "epoch": 0.5625902374589131,
      "grad_norm": 0.4900410771369934,
      "learning_rate": 1.637002369746556e-05,
      "loss": 0.5577,
      "step": 18314
    },
    {
      "epoch": 0.5626209565938624,
      "grad_norm": 0.3900837302207947,
      "learning_rate": 1.636965114996862e-05,
      "loss": 0.5768,
      "step": 18315
    },
    {
      "epoch": 0.5626516757288115,
      "grad_norm": 0.36559098958969116,
      "learning_rate": 1.6369278587594913e-05,
      "loss": 0.4857,
      "step": 18316
    },
    {
      "epoch": 0.5626823948637606,
      "grad_norm": 0.33089950680732727,
      "learning_rate": 1.636890601034531e-05,
      "loss": 0.5643,
      "step": 18317
    },
    {
      "epoch": 0.5627131139987098,
      "grad_norm": 0.36032840609550476,
      "learning_rate": 1.6368533418220683e-05,
      "loss": 0.6311,
      "step": 18318
    },
    {
      "epoch": 0.5627438331336589,
      "grad_norm": 0.3527620732784271,
      "learning_rate": 1.63681608112219e-05,
      "loss": 0.5433,
      "step": 18319
    },
    {
      "epoch": 0.5627745522686081,
      "grad_norm": 0.35205933451652527,
      "learning_rate": 1.6367788189349834e-05,
      "loss": 0.5494,
      "step": 18320
    },
    {
      "epoch": 0.5628052714035573,
      "grad_norm": 0.4122970700263977,
      "learning_rate": 1.6367415552605358e-05,
      "loss": 0.5542,
      "step": 18321
    },
    {
      "epoch": 0.5628359905385064,
      "grad_norm": 0.3394835293292999,
      "learning_rate": 1.636704290098933e-05,
      "loss": 0.6103,
      "step": 18322
    },
    {
      "epoch": 0.5628667096734556,
      "grad_norm": 0.3474261164665222,
      "learning_rate": 1.6366670234502635e-05,
      "loss": 0.587,
      "step": 18323
    },
    {
      "epoch": 0.5628974288084048,
      "grad_norm": 0.35180899500846863,
      "learning_rate": 1.6366297553146133e-05,
      "loss": 0.5867,
      "step": 18324
    },
    {
      "epoch": 0.5629281479433539,
      "grad_norm": 0.34738799929618835,
      "learning_rate": 1.63659248569207e-05,
      "loss": 0.4909,
      "step": 18325
    },
    {
      "epoch": 0.5629588670783031,
      "grad_norm": 0.40920522809028625,
      "learning_rate": 1.6365552145827205e-05,
      "loss": 0.6172,
      "step": 18326
    },
    {
      "epoch": 0.5629895862132522,
      "grad_norm": 0.3677544891834259,
      "learning_rate": 1.636517941986652e-05,
      "loss": 0.5793,
      "step": 18327
    },
    {
      "epoch": 0.5630203053482014,
      "grad_norm": 0.36154717206954956,
      "learning_rate": 1.6364806679039513e-05,
      "loss": 0.5286,
      "step": 18328
    },
    {
      "epoch": 0.5630510244831506,
      "grad_norm": 0.339495986700058,
      "learning_rate": 1.6364433923347057e-05,
      "loss": 0.5833,
      "step": 18329
    },
    {
      "epoch": 0.5630817436180997,
      "grad_norm": 0.33638235926628113,
      "learning_rate": 1.6364061152790017e-05,
      "loss": 0.5753,
      "step": 18330
    },
    {
      "epoch": 0.5631124627530488,
      "grad_norm": 0.34079185128211975,
      "learning_rate": 1.636368836736927e-05,
      "loss": 0.6193,
      "step": 18331
    },
    {
      "epoch": 0.5631431818879981,
      "grad_norm": 0.3555673360824585,
      "learning_rate": 1.6363315567085686e-05,
      "loss": 0.5249,
      "step": 18332
    },
    {
      "epoch": 0.5631739010229472,
      "grad_norm": 0.3546343147754669,
      "learning_rate": 1.636294275194013e-05,
      "loss": 0.5579,
      "step": 18333
    },
    {
      "epoch": 0.5632046201578964,
      "grad_norm": 0.36554425954818726,
      "learning_rate": 1.636256992193348e-05,
      "loss": 0.5696,
      "step": 18334
    },
    {
      "epoch": 0.5632353392928455,
      "grad_norm": 0.37100115418434143,
      "learning_rate": 1.63621970770666e-05,
      "loss": 0.5673,
      "step": 18335
    },
    {
      "epoch": 0.5632660584277946,
      "grad_norm": 0.370244562625885,
      "learning_rate": 1.636182421734037e-05,
      "loss": 0.5673,
      "step": 18336
    },
    {
      "epoch": 0.5632967775627439,
      "grad_norm": 0.41678300499916077,
      "learning_rate": 1.6361451342755655e-05,
      "loss": 0.6675,
      "step": 18337
    },
    {
      "epoch": 0.563327496697693,
      "grad_norm": 0.43331196904182434,
      "learning_rate": 1.6361078453313322e-05,
      "loss": 0.4927,
      "step": 18338
    },
    {
      "epoch": 0.5633582158326421,
      "grad_norm": 0.3736661970615387,
      "learning_rate": 1.6360705549014245e-05,
      "loss": 0.5859,
      "step": 18339
    },
    {
      "epoch": 0.5633889349675913,
      "grad_norm": 0.3862769901752472,
      "learning_rate": 1.63603326298593e-05,
      "loss": 0.5801,
      "step": 18340
    },
    {
      "epoch": 0.5634196541025405,
      "grad_norm": 0.3941037952899933,
      "learning_rate": 1.6359959695849354e-05,
      "loss": 0.5996,
      "step": 18341
    },
    {
      "epoch": 0.5634503732374896,
      "grad_norm": 0.3958321809768677,
      "learning_rate": 1.6359586746985275e-05,
      "loss": 0.5008,
      "step": 18342
    },
    {
      "epoch": 0.5634810923724388,
      "grad_norm": 0.3775223195552826,
      "learning_rate": 1.6359213783267937e-05,
      "loss": 0.5812,
      "step": 18343
    },
    {
      "epoch": 0.5635118115073879,
      "grad_norm": 0.3158891499042511,
      "learning_rate": 1.6358840804698216e-05,
      "loss": 0.5439,
      "step": 18344
    },
    {
      "epoch": 0.5635425306423371,
      "grad_norm": 0.3401861786842346,
      "learning_rate": 1.6358467811276972e-05,
      "loss": 0.5752,
      "step": 18345
    },
    {
      "epoch": 0.5635732497772863,
      "grad_norm": 0.3778954744338989,
      "learning_rate": 1.6358094803005085e-05,
      "loss": 0.5906,
      "step": 18346
    },
    {
      "epoch": 0.5636039689122354,
      "grad_norm": 0.36840522289276123,
      "learning_rate": 1.6357721779883423e-05,
      "loss": 0.6347,
      "step": 18347
    },
    {
      "epoch": 0.5636346880471846,
      "grad_norm": 0.33897602558135986,
      "learning_rate": 1.635734874191286e-05,
      "loss": 0.5288,
      "step": 18348
    },
    {
      "epoch": 0.5636654071821338,
      "grad_norm": 0.35562437772750854,
      "learning_rate": 1.6356975689094263e-05,
      "loss": 0.6115,
      "step": 18349
    },
    {
      "epoch": 0.5636961263170829,
      "grad_norm": 0.35669034719467163,
      "learning_rate": 1.6356602621428508e-05,
      "loss": 0.5604,
      "step": 18350
    },
    {
      "epoch": 0.5637268454520321,
      "grad_norm": 0.3694695830345154,
      "learning_rate": 1.635622953891646e-05,
      "loss": 0.6527,
      "step": 18351
    },
    {
      "epoch": 0.5637575645869812,
      "grad_norm": 0.38557761907577515,
      "learning_rate": 1.6355856441558994e-05,
      "loss": 0.5612,
      "step": 18352
    },
    {
      "epoch": 0.5637882837219304,
      "grad_norm": 0.3418016731739044,
      "learning_rate": 1.6355483329356984e-05,
      "loss": 0.5952,
      "step": 18353
    },
    {
      "epoch": 0.5638190028568796,
      "grad_norm": 0.34491029381752014,
      "learning_rate": 1.6355110202311298e-05,
      "loss": 0.5773,
      "step": 18354
    },
    {
      "epoch": 0.5638497219918287,
      "grad_norm": 0.3440345227718353,
      "learning_rate": 1.635473706042281e-05,
      "loss": 0.5565,
      "step": 18355
    },
    {
      "epoch": 0.5638804411267778,
      "grad_norm": 0.32607266306877136,
      "learning_rate": 1.6354363903692386e-05,
      "loss": 0.538,
      "step": 18356
    },
    {
      "epoch": 0.563911160261727,
      "grad_norm": 0.35243359208106995,
      "learning_rate": 1.6353990732120902e-05,
      "loss": 0.4848,
      "step": 18357
    },
    {
      "epoch": 0.5639418793966762,
      "grad_norm": 0.35149046778678894,
      "learning_rate": 1.6353617545709232e-05,
      "loss": 0.6614,
      "step": 18358
    },
    {
      "epoch": 0.5639725985316254,
      "grad_norm": 0.3383082449436188,
      "learning_rate": 1.6353244344458242e-05,
      "loss": 0.5484,
      "step": 18359
    },
    {
      "epoch": 0.5640033176665745,
      "grad_norm": 0.3731682598590851,
      "learning_rate": 1.6352871128368803e-05,
      "loss": 0.6652,
      "step": 18360
    },
    {
      "epoch": 0.5640340368015236,
      "grad_norm": 0.3385595381259918,
      "learning_rate": 1.6352497897441794e-05,
      "loss": 0.5815,
      "step": 18361
    },
    {
      "epoch": 0.5640647559364729,
      "grad_norm": 0.36295071244239807,
      "learning_rate": 1.6352124651678084e-05,
      "loss": 0.6232,
      "step": 18362
    },
    {
      "epoch": 0.564095475071422,
      "grad_norm": 0.3658522963523865,
      "learning_rate": 1.635175139107854e-05,
      "loss": 0.5892,
      "step": 18363
    },
    {
      "epoch": 0.5641261942063711,
      "grad_norm": 0.3504900336265564,
      "learning_rate": 1.6351378115644037e-05,
      "loss": 0.5935,
      "step": 18364
    },
    {
      "epoch": 0.5641569133413203,
      "grad_norm": 0.33465462923049927,
      "learning_rate": 1.6351004825375447e-05,
      "loss": 0.5118,
      "step": 18365
    },
    {
      "epoch": 0.5641876324762695,
      "grad_norm": 0.4116058647632599,
      "learning_rate": 1.6350631520273644e-05,
      "loss": 0.6338,
      "step": 18366
    },
    {
      "epoch": 0.5642183516112186,
      "grad_norm": 0.36104387044906616,
      "learning_rate": 1.6350258200339494e-05,
      "loss": 0.5465,
      "step": 18367
    },
    {
      "epoch": 0.5642490707461678,
      "grad_norm": 0.33789175748825073,
      "learning_rate": 1.634988486557388e-05,
      "loss": 0.5409,
      "step": 18368
    },
    {
      "epoch": 0.5642797898811169,
      "grad_norm": 0.4201701283454895,
      "learning_rate": 1.6349511515977655e-05,
      "loss": 0.6504,
      "step": 18369
    },
    {
      "epoch": 0.564310509016066,
      "grad_norm": 0.3484180271625519,
      "learning_rate": 1.634913815155171e-05,
      "loss": 0.58,
      "step": 18370
    },
    {
      "epoch": 0.5643412281510153,
      "grad_norm": 0.34339022636413574,
      "learning_rate": 1.634876477229691e-05,
      "loss": 0.5763,
      "step": 18371
    },
    {
      "epoch": 0.5643719472859644,
      "grad_norm": 0.37331631779670715,
      "learning_rate": 1.6348391378214126e-05,
      "loss": 0.5555,
      "step": 18372
    },
    {
      "epoch": 0.5644026664209136,
      "grad_norm": 0.39279964566230774,
      "learning_rate": 1.6348017969304227e-05,
      "loss": 0.6137,
      "step": 18373
    },
    {
      "epoch": 0.5644333855558628,
      "grad_norm": 0.3233543932437897,
      "learning_rate": 1.634764454556809e-05,
      "loss": 0.5569,
      "step": 18374
    },
    {
      "epoch": 0.5644641046908119,
      "grad_norm": 0.328966349363327,
      "learning_rate": 1.634727110700659e-05,
      "loss": 0.5078,
      "step": 18375
    },
    {
      "epoch": 0.5644948238257611,
      "grad_norm": 0.3366200625896454,
      "learning_rate": 1.634689765362059e-05,
      "loss": 0.5665,
      "step": 18376
    },
    {
      "epoch": 0.5645255429607102,
      "grad_norm": 0.37178662419319153,
      "learning_rate": 1.6346524185410968e-05,
      "loss": 0.5209,
      "step": 18377
    },
    {
      "epoch": 0.5645562620956593,
      "grad_norm": 0.3387007713317871,
      "learning_rate": 1.6346150702378594e-05,
      "loss": 0.5593,
      "step": 18378
    },
    {
      "epoch": 0.5645869812306086,
      "grad_norm": 0.3427676558494568,
      "learning_rate": 1.6345777204524344e-05,
      "loss": 0.5426,
      "step": 18379
    },
    {
      "epoch": 0.5646177003655577,
      "grad_norm": 0.37182164192199707,
      "learning_rate": 1.6345403691849087e-05,
      "loss": 0.6068,
      "step": 18380
    },
    {
      "epoch": 0.5646484195005068,
      "grad_norm": 0.35725677013397217,
      "learning_rate": 1.63450301643537e-05,
      "loss": 0.5999,
      "step": 18381
    },
    {
      "epoch": 0.564679138635456,
      "grad_norm": 0.3324580788612366,
      "learning_rate": 1.634465662203905e-05,
      "loss": 0.5622,
      "step": 18382
    },
    {
      "epoch": 0.5647098577704052,
      "grad_norm": 0.40253207087516785,
      "learning_rate": 1.6344283064906013e-05,
      "loss": 0.6138,
      "step": 18383
    },
    {
      "epoch": 0.5647405769053544,
      "grad_norm": 0.3496708869934082,
      "learning_rate": 1.6343909492955458e-05,
      "loss": 0.5449,
      "step": 18384
    },
    {
      "epoch": 0.5647712960403035,
      "grad_norm": 0.36960190534591675,
      "learning_rate": 1.6343535906188257e-05,
      "loss": 0.5909,
      "step": 18385
    },
    {
      "epoch": 0.5648020151752526,
      "grad_norm": 0.3361191153526306,
      "learning_rate": 1.6343162304605288e-05,
      "loss": 0.5413,
      "step": 18386
    },
    {
      "epoch": 0.5648327343102019,
      "grad_norm": 0.3286413550376892,
      "learning_rate": 1.6342788688207418e-05,
      "loss": 0.5596,
      "step": 18387
    },
    {
      "epoch": 0.564863453445151,
      "grad_norm": 0.3907976746559143,
      "learning_rate": 1.6342415056995525e-05,
      "loss": 0.5269,
      "step": 18388
    },
    {
      "epoch": 0.5648941725801001,
      "grad_norm": 0.3687365651130676,
      "learning_rate": 1.634204141097048e-05,
      "loss": 0.5715,
      "step": 18389
    },
    {
      "epoch": 0.5649248917150493,
      "grad_norm": 0.34356755018234253,
      "learning_rate": 1.634166775013315e-05,
      "loss": 0.5431,
      "step": 18390
    },
    {
      "epoch": 0.5649556108499985,
      "grad_norm": 0.42226478457450867,
      "learning_rate": 1.6341294074484414e-05,
      "loss": 0.5838,
      "step": 18391
    },
    {
      "epoch": 0.5649863299849476,
      "grad_norm": 0.42827296257019043,
      "learning_rate": 1.634092038402514e-05,
      "loss": 0.5552,
      "step": 18392
    },
    {
      "epoch": 0.5650170491198968,
      "grad_norm": 0.3516594469547272,
      "learning_rate": 1.6340546678756205e-05,
      "loss": 0.5925,
      "step": 18393
    },
    {
      "epoch": 0.5650477682548459,
      "grad_norm": 0.39151760935783386,
      "learning_rate": 1.6340172958678483e-05,
      "loss": 0.6711,
      "step": 18394
    },
    {
      "epoch": 0.5650784873897952,
      "grad_norm": 0.36479905247688293,
      "learning_rate": 1.6339799223792843e-05,
      "loss": 0.5024,
      "step": 18395
    },
    {
      "epoch": 0.5651092065247443,
      "grad_norm": 0.3435215950012207,
      "learning_rate": 1.633942547410016e-05,
      "loss": 0.5305,
      "step": 18396
    },
    {
      "epoch": 0.5651399256596934,
      "grad_norm": 0.3453041911125183,
      "learning_rate": 1.6339051709601306e-05,
      "loss": 0.5228,
      "step": 18397
    },
    {
      "epoch": 0.5651706447946426,
      "grad_norm": 0.3844829499721527,
      "learning_rate": 1.633867793029715e-05,
      "loss": 0.5208,
      "step": 18398
    },
    {
      "epoch": 0.5652013639295917,
      "grad_norm": 0.3488744795322418,
      "learning_rate": 1.6338304136188573e-05,
      "loss": 0.5562,
      "step": 18399
    },
    {
      "epoch": 0.5652320830645409,
      "grad_norm": 0.34757906198501587,
      "learning_rate": 1.6337930327276445e-05,
      "loss": 0.586,
      "step": 18400
    },
    {
      "epoch": 0.5652628021994901,
      "grad_norm": 0.34940725564956665,
      "learning_rate": 1.6337556503561637e-05,
      "loss": 0.6193,
      "step": 18401
    },
    {
      "epoch": 0.5652935213344392,
      "grad_norm": 0.32208865880966187,
      "learning_rate": 1.633718266504502e-05,
      "loss": 0.5025,
      "step": 18402
    },
    {
      "epoch": 0.5653242404693883,
      "grad_norm": 0.3581107258796692,
      "learning_rate": 1.6336808811727473e-05,
      "loss": 0.5356,
      "step": 18403
    },
    {
      "epoch": 0.5653549596043376,
      "grad_norm": 0.3596915304660797,
      "learning_rate": 1.6336434943609866e-05,
      "loss": 0.5661,
      "step": 18404
    },
    {
      "epoch": 0.5653856787392867,
      "grad_norm": 0.426533579826355,
      "learning_rate": 1.6336061060693073e-05,
      "loss": 0.5823,
      "step": 18405
    },
    {
      "epoch": 0.5654163978742358,
      "grad_norm": 0.37538960576057434,
      "learning_rate": 1.6335687162977966e-05,
      "loss": 0.5956,
      "step": 18406
    },
    {
      "epoch": 0.565447117009185,
      "grad_norm": 0.41970929503440857,
      "learning_rate": 1.6335313250465418e-05,
      "loss": 0.6228,
      "step": 18407
    },
    {
      "epoch": 0.5654778361441342,
      "grad_norm": 0.3565661609172821,
      "learning_rate": 1.633493932315631e-05,
      "loss": 0.6332,
      "step": 18408
    },
    {
      "epoch": 0.5655085552790834,
      "grad_norm": 0.4081978499889374,
      "learning_rate": 1.6334565381051502e-05,
      "loss": 0.5699,
      "step": 18409
    },
    {
      "epoch": 0.5655392744140325,
      "grad_norm": 0.3515836000442505,
      "learning_rate": 1.6334191424151876e-05,
      "loss": 0.4904,
      "step": 18410
    },
    {
      "epoch": 0.5655699935489816,
      "grad_norm": 0.3288431763648987,
      "learning_rate": 1.6333817452458305e-05,
      "loss": 0.5829,
      "step": 18411
    },
    {
      "epoch": 0.5656007126839309,
      "grad_norm": 0.334730863571167,
      "learning_rate": 1.633344346597166e-05,
      "loss": 0.6002,
      "step": 18412
    },
    {
      "epoch": 0.56563143181888,
      "grad_norm": 0.4157460033893585,
      "learning_rate": 1.6333069464692815e-05,
      "loss": 0.561,
      "step": 18413
    },
    {
      "epoch": 0.5656621509538291,
      "grad_norm": 0.3340742290019989,
      "learning_rate": 1.6332695448622642e-05,
      "loss": 0.5803,
      "step": 18414
    },
    {
      "epoch": 0.5656928700887783,
      "grad_norm": 0.35722947120666504,
      "learning_rate": 1.6332321417762017e-05,
      "loss": 0.5602,
      "step": 18415
    },
    {
      "epoch": 0.5657235892237275,
      "grad_norm": 0.3258823752403259,
      "learning_rate": 1.6331947372111817e-05,
      "loss": 0.4593,
      "step": 18416
    },
    {
      "epoch": 0.5657543083586766,
      "grad_norm": 0.34310483932495117,
      "learning_rate": 1.633157331167291e-05,
      "loss": 0.6172,
      "step": 18417
    },
    {
      "epoch": 0.5657850274936258,
      "grad_norm": 0.33784595131874084,
      "learning_rate": 1.633119923644617e-05,
      "loss": 0.6088,
      "step": 18418
    },
    {
      "epoch": 0.5658157466285749,
      "grad_norm": 0.3596440553665161,
      "learning_rate": 1.6330825146432472e-05,
      "loss": 0.5769,
      "step": 18419
    },
    {
      "epoch": 0.5658464657635242,
      "grad_norm": 0.356621652841568,
      "learning_rate": 1.6330451041632687e-05,
      "loss": 0.5925,
      "step": 18420
    },
    {
      "epoch": 0.5658771848984733,
      "grad_norm": 0.3570275604724884,
      "learning_rate": 1.63300769220477e-05,
      "loss": 0.4696,
      "step": 18421
    },
    {
      "epoch": 0.5659079040334224,
      "grad_norm": 0.34841397404670715,
      "learning_rate": 1.632970278767837e-05,
      "loss": 0.4879,
      "step": 18422
    },
    {
      "epoch": 0.5659386231683716,
      "grad_norm": 0.37062734365463257,
      "learning_rate": 1.632932863852558e-05,
      "loss": 0.5602,
      "step": 18423
    },
    {
      "epoch": 0.5659693423033207,
      "grad_norm": 0.367774099111557,
      "learning_rate": 1.63289544745902e-05,
      "loss": 0.6062,
      "step": 18424
    },
    {
      "epoch": 0.5660000614382699,
      "grad_norm": 0.34777167439460754,
      "learning_rate": 1.63285802958731e-05,
      "loss": 0.5084,
      "step": 18425
    },
    {
      "epoch": 0.5660307805732191,
      "grad_norm": 0.3855191171169281,
      "learning_rate": 1.6328206102375164e-05,
      "loss": 0.5173,
      "step": 18426
    },
    {
      "epoch": 0.5660614997081682,
      "grad_norm": 0.32774490118026733,
      "learning_rate": 1.632783189409726e-05,
      "loss": 0.5427,
      "step": 18427
    },
    {
      "epoch": 0.5660922188431173,
      "grad_norm": 0.38868188858032227,
      "learning_rate": 1.632745767104026e-05,
      "loss": 0.5903,
      "step": 18428
    },
    {
      "epoch": 0.5661229379780666,
      "grad_norm": 0.33221951127052307,
      "learning_rate": 1.6327083433205045e-05,
      "loss": 0.5784,
      "step": 18429
    },
    {
      "epoch": 0.5661536571130157,
      "grad_norm": 0.37033548951148987,
      "learning_rate": 1.6326709180592485e-05,
      "loss": 0.5541,
      "step": 18430
    },
    {
      "epoch": 0.5661843762479648,
      "grad_norm": 0.36146485805511475,
      "learning_rate": 1.632633491320345e-05,
      "loss": 0.5426,
      "step": 18431
    },
    {
      "epoch": 0.566215095382914,
      "grad_norm": 0.3077166676521301,
      "learning_rate": 1.6325960631038817e-05,
      "loss": 0.4943,
      "step": 18432
    },
    {
      "epoch": 0.5662458145178632,
      "grad_norm": 0.531947910785675,
      "learning_rate": 1.6325586334099464e-05,
      "loss": 0.5367,
      "step": 18433
    },
    {
      "epoch": 0.5662765336528124,
      "grad_norm": 0.4820996820926666,
      "learning_rate": 1.6325212022386265e-05,
      "loss": 0.5558,
      "step": 18434
    },
    {
      "epoch": 0.5663072527877615,
      "grad_norm": 0.35819360613822937,
      "learning_rate": 1.6324837695900085e-05,
      "loss": 0.5809,
      "step": 18435
    },
    {
      "epoch": 0.5663379719227106,
      "grad_norm": 0.590408205986023,
      "learning_rate": 1.6324463354641807e-05,
      "loss": 0.5705,
      "step": 18436
    },
    {
      "epoch": 0.5663686910576599,
      "grad_norm": 0.4039843678474426,
      "learning_rate": 1.6324088998612308e-05,
      "loss": 0.5515,
      "step": 18437
    },
    {
      "epoch": 0.566399410192609,
      "grad_norm": 0.3265235722064972,
      "learning_rate": 1.6323714627812454e-05,
      "loss": 0.5663,
      "step": 18438
    },
    {
      "epoch": 0.5664301293275581,
      "grad_norm": 0.4028032422065735,
      "learning_rate": 1.632334024224312e-05,
      "loss": 0.562,
      "step": 18439
    },
    {
      "epoch": 0.5664608484625073,
      "grad_norm": 0.4061766564846039,
      "learning_rate": 1.632296584190519e-05,
      "loss": 0.5949,
      "step": 18440
    },
    {
      "epoch": 0.5664915675974564,
      "grad_norm": 0.3689662516117096,
      "learning_rate": 1.6322591426799527e-05,
      "loss": 0.5792,
      "step": 18441
    },
    {
      "epoch": 0.5665222867324056,
      "grad_norm": 0.3227826654911041,
      "learning_rate": 1.6322216996927013e-05,
      "loss": 0.4884,
      "step": 18442
    },
    {
      "epoch": 0.5665530058673548,
      "grad_norm": 0.3354160189628601,
      "learning_rate": 1.6321842552288516e-05,
      "loss": 0.5648,
      "step": 18443
    },
    {
      "epoch": 0.5665837250023039,
      "grad_norm": 0.3569202721118927,
      "learning_rate": 1.6321468092884917e-05,
      "loss": 0.5141,
      "step": 18444
    },
    {
      "epoch": 0.5666144441372531,
      "grad_norm": 0.38462719321250916,
      "learning_rate": 1.6321093618717086e-05,
      "loss": 0.6428,
      "step": 18445
    },
    {
      "epoch": 0.5666451632722023,
      "grad_norm": 0.37963882088661194,
      "learning_rate": 1.63207191297859e-05,
      "loss": 0.5792,
      "step": 18446
    },
    {
      "epoch": 0.5666758824071514,
      "grad_norm": 0.3348693251609802,
      "learning_rate": 1.632034462609223e-05,
      "loss": 0.5604,
      "step": 18447
    },
    {
      "epoch": 0.5667066015421006,
      "grad_norm": 0.3506665527820587,
      "learning_rate": 1.631997010763696e-05,
      "loss": 0.5687,
      "step": 18448
    },
    {
      "epoch": 0.5667373206770497,
      "grad_norm": 0.36115312576293945,
      "learning_rate": 1.6319595574420955e-05,
      "loss": 0.5692,
      "step": 18449
    },
    {
      "epoch": 0.5667680398119989,
      "grad_norm": 0.3541623651981354,
      "learning_rate": 1.6319221026445092e-05,
      "loss": 0.5391,
      "step": 18450
    },
    {
      "epoch": 0.5667987589469481,
      "grad_norm": 0.4037734866142273,
      "learning_rate": 1.6318846463710246e-05,
      "loss": 0.6475,
      "step": 18451
    },
    {
      "epoch": 0.5668294780818972,
      "grad_norm": 0.31899842619895935,
      "learning_rate": 1.6318471886217295e-05,
      "loss": 0.5237,
      "step": 18452
    },
    {
      "epoch": 0.5668601972168463,
      "grad_norm": 0.3606996238231659,
      "learning_rate": 1.631809729396711e-05,
      "loss": 0.593,
      "step": 18453
    },
    {
      "epoch": 0.5668909163517956,
      "grad_norm": 0.35009342432022095,
      "learning_rate": 1.6317722686960574e-05,
      "loss": 0.4769,
      "step": 18454
    },
    {
      "epoch": 0.5669216354867447,
      "grad_norm": 0.38225266337394714,
      "learning_rate": 1.6317348065198547e-05,
      "loss": 0.5687,
      "step": 18455
    },
    {
      "epoch": 0.5669523546216938,
      "grad_norm": 0.3832692503929138,
      "learning_rate": 1.6316973428681917e-05,
      "loss": 0.6208,
      "step": 18456
    },
    {
      "epoch": 0.566983073756643,
      "grad_norm": 0.3487228453159332,
      "learning_rate": 1.6316598777411555e-05,
      "loss": 0.5153,
      "step": 18457
    },
    {
      "epoch": 0.5670137928915921,
      "grad_norm": 0.3436364531517029,
      "learning_rate": 1.6316224111388336e-05,
      "loss": 0.5684,
      "step": 18458
    },
    {
      "epoch": 0.5670445120265414,
      "grad_norm": 0.3434727191925049,
      "learning_rate": 1.631584943061313e-05,
      "loss": 0.5181,
      "step": 18459
    },
    {
      "epoch": 0.5670752311614905,
      "grad_norm": 0.38151484727859497,
      "learning_rate": 1.6315474735086822e-05,
      "loss": 0.6317,
      "step": 18460
    },
    {
      "epoch": 0.5671059502964396,
      "grad_norm": 0.4732713997364044,
      "learning_rate": 1.6315100024810275e-05,
      "loss": 0.4998,
      "step": 18461
    },
    {
      "epoch": 0.5671366694313889,
      "grad_norm": 0.49807262420654297,
      "learning_rate": 1.6314725299784374e-05,
      "loss": 0.5766,
      "step": 18462
    },
    {
      "epoch": 0.567167388566338,
      "grad_norm": 0.34161123633384705,
      "learning_rate": 1.6314350560009993e-05,
      "loss": 0.5975,
      "step": 18463
    },
    {
      "epoch": 0.5671981077012871,
      "grad_norm": 0.350522518157959,
      "learning_rate": 1.6313975805488006e-05,
      "loss": 0.5525,
      "step": 18464
    },
    {
      "epoch": 0.5672288268362363,
      "grad_norm": 0.35436901450157166,
      "learning_rate": 1.6313601036219283e-05,
      "loss": 0.598,
      "step": 18465
    },
    {
      "epoch": 0.5672595459711854,
      "grad_norm": 0.3457684814929962,
      "learning_rate": 1.6313226252204707e-05,
      "loss": 0.5244,
      "step": 18466
    },
    {
      "epoch": 0.5672902651061346,
      "grad_norm": 0.3453342914581299,
      "learning_rate": 1.631285145344515e-05,
      "loss": 0.6043,
      "step": 18467
    },
    {
      "epoch": 0.5673209842410838,
      "grad_norm": 0.46679455041885376,
      "learning_rate": 1.6312476639941487e-05,
      "loss": 0.6115,
      "step": 18468
    },
    {
      "epoch": 0.5673517033760329,
      "grad_norm": 0.3173770010471344,
      "learning_rate": 1.6312101811694592e-05,
      "loss": 0.626,
      "step": 18469
    },
    {
      "epoch": 0.5673824225109821,
      "grad_norm": 0.43651318550109863,
      "learning_rate": 1.6311726968705343e-05,
      "loss": 0.5398,
      "step": 18470
    },
    {
      "epoch": 0.5674131416459313,
      "grad_norm": 0.34936270117759705,
      "learning_rate": 1.6311352110974618e-05,
      "loss": 0.6677,
      "step": 18471
    },
    {
      "epoch": 0.5674438607808804,
      "grad_norm": 0.3361052870750427,
      "learning_rate": 1.6310977238503286e-05,
      "loss": 0.5578,
      "step": 18472
    },
    {
      "epoch": 0.5674745799158296,
      "grad_norm": 0.366376668214798,
      "learning_rate": 1.6310602351292225e-05,
      "loss": 0.651,
      "step": 18473
    },
    {
      "epoch": 0.5675052990507787,
      "grad_norm": 0.35087132453918457,
      "learning_rate": 1.6310227449342314e-05,
      "loss": 0.5255,
      "step": 18474
    },
    {
      "epoch": 0.5675360181857279,
      "grad_norm": 0.3548397123813629,
      "learning_rate": 1.630985253265443e-05,
      "loss": 0.5424,
      "step": 18475
    },
    {
      "epoch": 0.5675667373206771,
      "grad_norm": 0.3995503783226013,
      "learning_rate": 1.6309477601229438e-05,
      "loss": 0.5747,
      "step": 18476
    },
    {
      "epoch": 0.5675974564556262,
      "grad_norm": 0.34618204832077026,
      "learning_rate": 1.6309102655068225e-05,
      "loss": 0.4252,
      "step": 18477
    },
    {
      "epoch": 0.5676281755905753,
      "grad_norm": 0.35286128520965576,
      "learning_rate": 1.630872769417166e-05,
      "loss": 0.4756,
      "step": 18478
    },
    {
      "epoch": 0.5676588947255246,
      "grad_norm": 0.34012794494628906,
      "learning_rate": 1.630835271854062e-05,
      "loss": 0.4895,
      "step": 18479
    },
    {
      "epoch": 0.5676896138604737,
      "grad_norm": 0.3305014967918396,
      "learning_rate": 1.6307977728175984e-05,
      "loss": 0.5569,
      "step": 18480
    },
    {
      "epoch": 0.5677203329954228,
      "grad_norm": 0.34344324469566345,
      "learning_rate": 1.6307602723078625e-05,
      "loss": 0.5125,
      "step": 18481
    },
    {
      "epoch": 0.567751052130372,
      "grad_norm": 0.3233770728111267,
      "learning_rate": 1.630722770324942e-05,
      "loss": 0.4381,
      "step": 18482
    },
    {
      "epoch": 0.5677817712653211,
      "grad_norm": 0.3676961064338684,
      "learning_rate": 1.6306852668689242e-05,
      "loss": 0.5046,
      "step": 18483
    },
    {
      "epoch": 0.5678124904002704,
      "grad_norm": 0.3465898931026459,
      "learning_rate": 1.630647761939897e-05,
      "loss": 0.5488,
      "step": 18484
    },
    {
      "epoch": 0.5678432095352195,
      "grad_norm": 0.35473549365997314,
      "learning_rate": 1.6306102555379478e-05,
      "loss": 0.5528,
      "step": 18485
    },
    {
      "epoch": 0.5678739286701686,
      "grad_norm": 0.3850688636302948,
      "learning_rate": 1.6305727476631642e-05,
      "loss": 0.556,
      "step": 18486
    },
    {
      "epoch": 0.5679046478051178,
      "grad_norm": 0.3968769609928131,
      "learning_rate": 1.630535238315634e-05,
      "loss": 0.595,
      "step": 18487
    },
    {
      "epoch": 0.567935366940067,
      "grad_norm": 0.33974820375442505,
      "learning_rate": 1.630497727495445e-05,
      "loss": 0.4989,
      "step": 18488
    },
    {
      "epoch": 0.5679660860750161,
      "grad_norm": 0.3499108850955963,
      "learning_rate": 1.6304602152026844e-05,
      "loss": 0.5624,
      "step": 18489
    },
    {
      "epoch": 0.5679968052099653,
      "grad_norm": 0.34994038939476013,
      "learning_rate": 1.63042270143744e-05,
      "loss": 0.5463,
      "step": 18490
    },
    {
      "epoch": 0.5680275243449144,
      "grad_norm": 0.3708800673484802,
      "learning_rate": 1.630385186199799e-05,
      "loss": 0.5748,
      "step": 18491
    },
    {
      "epoch": 0.5680582434798636,
      "grad_norm": 0.383782297372818,
      "learning_rate": 1.6303476694898496e-05,
      "loss": 0.5595,
      "step": 18492
    },
    {
      "epoch": 0.5680889626148128,
      "grad_norm": 0.3683859407901764,
      "learning_rate": 1.630310151307679e-05,
      "loss": 0.5968,
      "step": 18493
    },
    {
      "epoch": 0.5681196817497619,
      "grad_norm": 0.3788955807685852,
      "learning_rate": 1.6302726316533756e-05,
      "loss": 0.5349,
      "step": 18494
    },
    {
      "epoch": 0.5681504008847111,
      "grad_norm": 0.33946800231933594,
      "learning_rate": 1.6302351105270262e-05,
      "loss": 0.5312,
      "step": 18495
    },
    {
      "epoch": 0.5681811200196603,
      "grad_norm": 0.3686537742614746,
      "learning_rate": 1.6301975879287185e-05,
      "loss": 0.5923,
      "step": 18496
    },
    {
      "epoch": 0.5682118391546094,
      "grad_norm": 0.3537122309207916,
      "learning_rate": 1.6301600638585403e-05,
      "loss": 0.5909,
      "step": 18497
    },
    {
      "epoch": 0.5682425582895586,
      "grad_norm": 0.35387542843818665,
      "learning_rate": 1.6301225383165793e-05,
      "loss": 0.5887,
      "step": 18498
    },
    {
      "epoch": 0.5682732774245077,
      "grad_norm": 0.39186903834342957,
      "learning_rate": 1.6300850113029233e-05,
      "loss": 0.5979,
      "step": 18499
    },
    {
      "epoch": 0.5683039965594568,
      "grad_norm": 0.3483748137950897,
      "learning_rate": 1.6300474828176594e-05,
      "loss": 0.5533,
      "step": 18500
    },
    {
      "epoch": 0.5683347156944061,
      "grad_norm": 0.40103352069854736,
      "learning_rate": 1.630009952860876e-05,
      "loss": 0.5895,
      "step": 18501
    },
    {
      "epoch": 0.5683654348293552,
      "grad_norm": 0.36064159870147705,
      "learning_rate": 1.62997242143266e-05,
      "loss": 0.5883,
      "step": 18502
    },
    {
      "epoch": 0.5683961539643043,
      "grad_norm": 0.33095458149909973,
      "learning_rate": 1.6299348885330996e-05,
      "loss": 0.4987,
      "step": 18503
    },
    {
      "epoch": 0.5684268730992535,
      "grad_norm": 0.3890676498413086,
      "learning_rate": 1.629897354162282e-05,
      "loss": 0.5462,
      "step": 18504
    },
    {
      "epoch": 0.5684575922342027,
      "grad_norm": 0.37567824125289917,
      "learning_rate": 1.629859818320296e-05,
      "loss": 0.5356,
      "step": 18505
    },
    {
      "epoch": 0.5684883113691519,
      "grad_norm": 0.3888941705226898,
      "learning_rate": 1.6298222810072274e-05,
      "loss": 0.5359,
      "step": 18506
    },
    {
      "epoch": 0.568519030504101,
      "grad_norm": 0.367683470249176,
      "learning_rate": 1.629784742223165e-05,
      "loss": 0.572,
      "step": 18507
    },
    {
      "epoch": 0.5685497496390501,
      "grad_norm": 0.3650810420513153,
      "learning_rate": 1.6297472019681967e-05,
      "loss": 0.5629,
      "step": 18508
    },
    {
      "epoch": 0.5685804687739994,
      "grad_norm": 0.4467988610267639,
      "learning_rate": 1.62970966024241e-05,
      "loss": 0.6019,
      "step": 18509
    },
    {
      "epoch": 0.5686111879089485,
      "grad_norm": 0.35212597250938416,
      "learning_rate": 1.629672117045892e-05,
      "loss": 0.5495,
      "step": 18510
    },
    {
      "epoch": 0.5686419070438976,
      "grad_norm": 0.35216352343559265,
      "learning_rate": 1.629634572378731e-05,
      "loss": 0.4968,
      "step": 18511
    },
    {
      "epoch": 0.5686726261788468,
      "grad_norm": 0.38319772481918335,
      "learning_rate": 1.6295970262410142e-05,
      "loss": 0.5514,
      "step": 18512
    },
    {
      "epoch": 0.568703345313796,
      "grad_norm": 0.3395565450191498,
      "learning_rate": 1.62955947863283e-05,
      "loss": 0.6262,
      "step": 18513
    },
    {
      "epoch": 0.5687340644487451,
      "grad_norm": 0.5375403761863708,
      "learning_rate": 1.6295219295542658e-05,
      "loss": 0.6019,
      "step": 18514
    },
    {
      "epoch": 0.5687647835836943,
      "grad_norm": 0.36044496297836304,
      "learning_rate": 1.6294843790054087e-05,
      "loss": 0.5326,
      "step": 18515
    },
    {
      "epoch": 0.5687955027186434,
      "grad_norm": 0.3723022937774658,
      "learning_rate": 1.6294468269863468e-05,
      "loss": 0.5478,
      "step": 18516
    },
    {
      "epoch": 0.5688262218535926,
      "grad_norm": 0.33779534697532654,
      "learning_rate": 1.629409273497168e-05,
      "loss": 0.5759,
      "step": 18517
    },
    {
      "epoch": 0.5688569409885418,
      "grad_norm": 0.3429974615573883,
      "learning_rate": 1.6293717185379604e-05,
      "loss": 0.5911,
      "step": 18518
    },
    {
      "epoch": 0.5688876601234909,
      "grad_norm": 0.3394705653190613,
      "learning_rate": 1.6293341621088105e-05,
      "loss": 0.562,
      "step": 18519
    },
    {
      "epoch": 0.5689183792584401,
      "grad_norm": 0.3492768704891205,
      "learning_rate": 1.6292966042098068e-05,
      "loss": 0.6331,
      "step": 18520
    },
    {
      "epoch": 0.5689490983933893,
      "grad_norm": 0.3389914333820343,
      "learning_rate": 1.6292590448410375e-05,
      "loss": 0.5719,
      "step": 18521
    },
    {
      "epoch": 0.5689798175283384,
      "grad_norm": 0.3727606534957886,
      "learning_rate": 1.6292214840025892e-05,
      "loss": 0.6005,
      "step": 18522
    },
    {
      "epoch": 0.5690105366632876,
      "grad_norm": 0.38132616877555847,
      "learning_rate": 1.6291839216945503e-05,
      "loss": 0.5711,
      "step": 18523
    },
    {
      "epoch": 0.5690412557982367,
      "grad_norm": 0.36159706115722656,
      "learning_rate": 1.6291463579170088e-05,
      "loss": 0.5209,
      "step": 18524
    },
    {
      "epoch": 0.5690719749331858,
      "grad_norm": 0.32526007294654846,
      "learning_rate": 1.6291087926700514e-05,
      "loss": 0.5329,
      "step": 18525
    },
    {
      "epoch": 0.5691026940681351,
      "grad_norm": 0.3696666657924652,
      "learning_rate": 1.6290712259537667e-05,
      "loss": 0.5601,
      "step": 18526
    },
    {
      "epoch": 0.5691334132030842,
      "grad_norm": 0.3396947383880615,
      "learning_rate": 1.6290336577682424e-05,
      "loss": 0.5452,
      "step": 18527
    },
    {
      "epoch": 0.5691641323380333,
      "grad_norm": 0.33747339248657227,
      "learning_rate": 1.6289960881135658e-05,
      "loss": 0.5602,
      "step": 18528
    },
    {
      "epoch": 0.5691948514729825,
      "grad_norm": 0.3500919044017792,
      "learning_rate": 1.628958516989825e-05,
      "loss": 0.6491,
      "step": 18529
    },
    {
      "epoch": 0.5692255706079317,
      "grad_norm": 0.4276183843612671,
      "learning_rate": 1.628920944397108e-05,
      "loss": 0.5568,
      "step": 18530
    },
    {
      "epoch": 0.5692562897428809,
      "grad_norm": 0.3758138418197632,
      "learning_rate": 1.6288833703355017e-05,
      "loss": 0.5442,
      "step": 18531
    },
    {
      "epoch": 0.56928700887783,
      "grad_norm": 0.32477331161499023,
      "learning_rate": 1.6288457948050948e-05,
      "loss": 0.4658,
      "step": 18532
    },
    {
      "epoch": 0.5693177280127791,
      "grad_norm": 0.33165568113327026,
      "learning_rate": 1.6288082178059744e-05,
      "loss": 0.5865,
      "step": 18533
    },
    {
      "epoch": 0.5693484471477284,
      "grad_norm": 0.39695221185684204,
      "learning_rate": 1.6287706393382287e-05,
      "loss": 0.6534,
      "step": 18534
    },
    {
      "epoch": 0.5693791662826775,
      "grad_norm": 0.5125012397766113,
      "learning_rate": 1.6287330594019447e-05,
      "loss": 0.5076,
      "step": 18535
    },
    {
      "epoch": 0.5694098854176266,
      "grad_norm": 0.4320628046989441,
      "learning_rate": 1.628695477997211e-05,
      "loss": 0.5799,
      "step": 18536
    },
    {
      "epoch": 0.5694406045525758,
      "grad_norm": 0.3617112338542938,
      "learning_rate": 1.6286578951241155e-05,
      "loss": 0.6002,
      "step": 18537
    },
    {
      "epoch": 0.569471323687525,
      "grad_norm": 0.3900090754032135,
      "learning_rate": 1.628620310782745e-05,
      "loss": 0.6448,
      "step": 18538
    },
    {
      "epoch": 0.5695020428224741,
      "grad_norm": 0.3588487505912781,
      "learning_rate": 1.6285827249731886e-05,
      "loss": 0.6179,
      "step": 18539
    },
    {
      "epoch": 0.5695327619574233,
      "grad_norm": 0.31975531578063965,
      "learning_rate": 1.6285451376955328e-05,
      "loss": 0.5393,
      "step": 18540
    },
    {
      "epoch": 0.5695634810923724,
      "grad_norm": 0.3461657762527466,
      "learning_rate": 1.6285075489498662e-05,
      "loss": 0.4784,
      "step": 18541
    },
    {
      "epoch": 0.5695942002273215,
      "grad_norm": 0.3526533246040344,
      "learning_rate": 1.628469958736276e-05,
      "loss": 0.5421,
      "step": 18542
    },
    {
      "epoch": 0.5696249193622708,
      "grad_norm": 0.3546167314052582,
      "learning_rate": 1.6284323670548502e-05,
      "loss": 0.5595,
      "step": 18543
    },
    {
      "epoch": 0.5696556384972199,
      "grad_norm": 0.3444017469882965,
      "learning_rate": 1.6283947739056772e-05,
      "loss": 0.5238,
      "step": 18544
    },
    {
      "epoch": 0.5696863576321691,
      "grad_norm": 0.3595964014530182,
      "learning_rate": 1.6283571792888438e-05,
      "loss": 0.562,
      "step": 18545
    },
    {
      "epoch": 0.5697170767671182,
      "grad_norm": 0.35225722193717957,
      "learning_rate": 1.628319583204439e-05,
      "loss": 0.5159,
      "step": 18546
    },
    {
      "epoch": 0.5697477959020674,
      "grad_norm": 0.5331439971923828,
      "learning_rate": 1.6282819856525494e-05,
      "loss": 0.5318,
      "step": 18547
    },
    {
      "epoch": 0.5697785150370166,
      "grad_norm": 0.34449800848960876,
      "learning_rate": 1.6282443866332636e-05,
      "loss": 0.5612,
      "step": 18548
    },
    {
      "epoch": 0.5698092341719657,
      "grad_norm": 0.36048829555511475,
      "learning_rate": 1.628206786146669e-05,
      "loss": 0.4965,
      "step": 18549
    },
    {
      "epoch": 0.5698399533069148,
      "grad_norm": 0.3393063545227051,
      "learning_rate": 1.6281691841928536e-05,
      "loss": 0.5524,
      "step": 18550
    },
    {
      "epoch": 0.5698706724418641,
      "grad_norm": 0.5216580629348755,
      "learning_rate": 1.6281315807719055e-05,
      "loss": 0.5348,
      "step": 18551
    },
    {
      "epoch": 0.5699013915768132,
      "grad_norm": 0.3404894769191742,
      "learning_rate": 1.628093975883912e-05,
      "loss": 0.5204,
      "step": 18552
    },
    {
      "epoch": 0.5699321107117623,
      "grad_norm": 0.41619744896888733,
      "learning_rate": 1.6280563695289607e-05,
      "loss": 0.5614,
      "step": 18553
    },
    {
      "epoch": 0.5699628298467115,
      "grad_norm": 0.5130864381790161,
      "learning_rate": 1.6280187617071405e-05,
      "loss": 0.5956,
      "step": 18554
    },
    {
      "epoch": 0.5699935489816607,
      "grad_norm": 0.3500940203666687,
      "learning_rate": 1.6279811524185384e-05,
      "loss": 0.6278,
      "step": 18555
    },
    {
      "epoch": 0.5700242681166099,
      "grad_norm": 0.36983123421669006,
      "learning_rate": 1.6279435416632425e-05,
      "loss": 0.5444,
      "step": 18556
    },
    {
      "epoch": 0.570054987251559,
      "grad_norm": 0.32242050766944885,
      "learning_rate": 1.627905929441341e-05,
      "loss": 0.603,
      "step": 18557
    },
    {
      "epoch": 0.5700857063865081,
      "grad_norm": 0.3627101480960846,
      "learning_rate": 1.6278683157529206e-05,
      "loss": 0.5846,
      "step": 18558
    },
    {
      "epoch": 0.5701164255214574,
      "grad_norm": 0.32383015751838684,
      "learning_rate": 1.6278307005980702e-05,
      "loss": 0.5512,
      "step": 18559
    },
    {
      "epoch": 0.5701471446564065,
      "grad_norm": 0.31931072473526,
      "learning_rate": 1.6277930839768777e-05,
      "loss": 0.503,
      "step": 18560
    },
    {
      "epoch": 0.5701778637913556,
      "grad_norm": 0.3385072648525238,
      "learning_rate": 1.6277554658894298e-05,
      "loss": 0.5248,
      "step": 18561
    },
    {
      "epoch": 0.5702085829263048,
      "grad_norm": 0.362024188041687,
      "learning_rate": 1.627717846335816e-05,
      "loss": 0.5756,
      "step": 18562
    },
    {
      "epoch": 0.570239302061254,
      "grad_norm": 0.3571580648422241,
      "learning_rate": 1.627680225316123e-05,
      "loss": 0.5751,
      "step": 18563
    },
    {
      "epoch": 0.5702700211962031,
      "grad_norm": 0.4122377932071686,
      "learning_rate": 1.6276426028304392e-05,
      "loss": 0.5543,
      "step": 18564
    },
    {
      "epoch": 0.5703007403311523,
      "grad_norm": 0.37549063563346863,
      "learning_rate": 1.627604978878852e-05,
      "loss": 0.5346,
      "step": 18565
    },
    {
      "epoch": 0.5703314594661014,
      "grad_norm": 0.345047265291214,
      "learning_rate": 1.6275673534614494e-05,
      "loss": 0.5643,
      "step": 18566
    },
    {
      "epoch": 0.5703621786010505,
      "grad_norm": 0.34737274050712585,
      "learning_rate": 1.62752972657832e-05,
      "loss": 0.5286,
      "step": 18567
    },
    {
      "epoch": 0.5703928977359998,
      "grad_norm": 0.3173574209213257,
      "learning_rate": 1.6274920982295507e-05,
      "loss": 0.6034,
      "step": 18568
    },
    {
      "epoch": 0.5704236168709489,
      "grad_norm": 0.4336109459400177,
      "learning_rate": 1.6274544684152294e-05,
      "loss": 0.587,
      "step": 18569
    },
    {
      "epoch": 0.5704543360058981,
      "grad_norm": 0.36054527759552,
      "learning_rate": 1.627416837135445e-05,
      "loss": 0.526,
      "step": 18570
    },
    {
      "epoch": 0.5704850551408472,
      "grad_norm": 0.3328697979450226,
      "learning_rate": 1.6273792043902844e-05,
      "loss": 0.5755,
      "step": 18571
    },
    {
      "epoch": 0.5705157742757964,
      "grad_norm": 0.3387073874473572,
      "learning_rate": 1.627341570179836e-05,
      "loss": 0.5652,
      "step": 18572
    },
    {
      "epoch": 0.5705464934107456,
      "grad_norm": 0.32929855585098267,
      "learning_rate": 1.6273039345041875e-05,
      "loss": 0.5348,
      "step": 18573
    },
    {
      "epoch": 0.5705772125456947,
      "grad_norm": 0.4238332211971283,
      "learning_rate": 1.627266297363427e-05,
      "loss": 0.5455,
      "step": 18574
    },
    {
      "epoch": 0.5706079316806438,
      "grad_norm": 0.405169814825058,
      "learning_rate": 1.6272286587576423e-05,
      "loss": 0.6036,
      "step": 18575
    },
    {
      "epoch": 0.5706386508155931,
      "grad_norm": 0.3687654733657837,
      "learning_rate": 1.627191018686921e-05,
      "loss": 0.5145,
      "step": 18576
    },
    {
      "epoch": 0.5706693699505422,
      "grad_norm": 0.36385637521743774,
      "learning_rate": 1.6271533771513514e-05,
      "loss": 0.5674,
      "step": 18577
    },
    {
      "epoch": 0.5707000890854913,
      "grad_norm": 0.4080851674079895,
      "learning_rate": 1.6271157341510213e-05,
      "loss": 0.5795,
      "step": 18578
    },
    {
      "epoch": 0.5707308082204405,
      "grad_norm": 0.3734418451786041,
      "learning_rate": 1.6270780896860184e-05,
      "loss": 0.5936,
      "step": 18579
    },
    {
      "epoch": 0.5707615273553897,
      "grad_norm": 0.3693806827068329,
      "learning_rate": 1.627040443756431e-05,
      "loss": 0.5994,
      "step": 18580
    },
    {
      "epoch": 0.5707922464903389,
      "grad_norm": 0.3374244272708893,
      "learning_rate": 1.627002796362347e-05,
      "loss": 0.5909,
      "step": 18581
    },
    {
      "epoch": 0.570822965625288,
      "grad_norm": 0.33277493715286255,
      "learning_rate": 1.626965147503854e-05,
      "loss": 0.5,
      "step": 18582
    },
    {
      "epoch": 0.5708536847602371,
      "grad_norm": 0.3404451906681061,
      "learning_rate": 1.62692749718104e-05,
      "loss": 0.5915,
      "step": 18583
    },
    {
      "epoch": 0.5708844038951864,
      "grad_norm": 0.36378929018974304,
      "learning_rate": 1.6268898453939933e-05,
      "loss": 0.5899,
      "step": 18584
    },
    {
      "epoch": 0.5709151230301355,
      "grad_norm": 0.32406672835350037,
      "learning_rate": 1.6268521921428013e-05,
      "loss": 0.5075,
      "step": 18585
    },
    {
      "epoch": 0.5709458421650846,
      "grad_norm": 0.33781862258911133,
      "learning_rate": 1.6268145374275525e-05,
      "loss": 0.5817,
      "step": 18586
    },
    {
      "epoch": 0.5709765613000338,
      "grad_norm": 0.438236266374588,
      "learning_rate": 1.6267768812483344e-05,
      "loss": 0.5734,
      "step": 18587
    },
    {
      "epoch": 0.571007280434983,
      "grad_norm": 0.3334810435771942,
      "learning_rate": 1.6267392236052352e-05,
      "loss": 0.5705,
      "step": 18588
    },
    {
      "epoch": 0.5710379995699321,
      "grad_norm": 0.34775686264038086,
      "learning_rate": 1.626701564498343e-05,
      "loss": 0.548,
      "step": 18589
    },
    {
      "epoch": 0.5710687187048813,
      "grad_norm": 0.34610697627067566,
      "learning_rate": 1.626663903927745e-05,
      "loss": 0.5318,
      "step": 18590
    },
    {
      "epoch": 0.5710994378398304,
      "grad_norm": 0.3462832272052765,
      "learning_rate": 1.6266262418935303e-05,
      "loss": 0.5357,
      "step": 18591
    },
    {
      "epoch": 0.5711301569747795,
      "grad_norm": 0.34309685230255127,
      "learning_rate": 1.6265885783957858e-05,
      "loss": 0.5331,
      "step": 18592
    },
    {
      "epoch": 0.5711608761097288,
      "grad_norm": 0.5741856098175049,
      "learning_rate": 1.6265509134346002e-05,
      "loss": 0.5819,
      "step": 18593
    },
    {
      "epoch": 0.5711915952446779,
      "grad_norm": 0.3486904203891754,
      "learning_rate": 1.6265132470100608e-05,
      "loss": 0.5514,
      "step": 18594
    },
    {
      "epoch": 0.5712223143796271,
      "grad_norm": 0.37018436193466187,
      "learning_rate": 1.626475579122256e-05,
      "loss": 0.5362,
      "step": 18595
    },
    {
      "epoch": 0.5712530335145762,
      "grad_norm": 0.38518476486206055,
      "learning_rate": 1.626437909771274e-05,
      "loss": 0.6076,
      "step": 18596
    },
    {
      "epoch": 0.5712837526495254,
      "grad_norm": 0.3626132011413574,
      "learning_rate": 1.6264002389572026e-05,
      "loss": 0.551,
      "step": 18597
    },
    {
      "epoch": 0.5713144717844746,
      "grad_norm": 0.31683069467544556,
      "learning_rate": 1.6263625666801293e-05,
      "loss": 0.5582,
      "step": 18598
    },
    {
      "epoch": 0.5713451909194237,
      "grad_norm": 0.35297679901123047,
      "learning_rate": 1.6263248929401428e-05,
      "loss": 0.5661,
      "step": 18599
    },
    {
      "epoch": 0.5713759100543728,
      "grad_norm": 0.339578241109848,
      "learning_rate": 1.6262872177373307e-05,
      "loss": 0.5783,
      "step": 18600
    },
    {
      "epoch": 0.5714066291893221,
      "grad_norm": 0.34174975752830505,
      "learning_rate": 1.6262495410717808e-05,
      "loss": 0.5011,
      "step": 18601
    },
    {
      "epoch": 0.5714373483242712,
      "grad_norm": 0.35658085346221924,
      "learning_rate": 1.6262118629435818e-05,
      "loss": 0.5368,
      "step": 18602
    },
    {
      "epoch": 0.5714680674592203,
      "grad_norm": 0.34784653782844543,
      "learning_rate": 1.626174183352821e-05,
      "loss": 0.5443,
      "step": 18603
    },
    {
      "epoch": 0.5714987865941695,
      "grad_norm": 0.49554935097694397,
      "learning_rate": 1.6261365022995868e-05,
      "loss": 0.5505,
      "step": 18604
    },
    {
      "epoch": 0.5715295057291186,
      "grad_norm": 0.34560489654541016,
      "learning_rate": 1.626098819783967e-05,
      "loss": 0.5717,
      "step": 18605
    },
    {
      "epoch": 0.5715602248640679,
      "grad_norm": 0.37658578157424927,
      "learning_rate": 1.6260611358060496e-05,
      "loss": 0.5363,
      "step": 18606
    },
    {
      "epoch": 0.571590943999017,
      "grad_norm": 0.32990190386772156,
      "learning_rate": 1.6260234503659228e-05,
      "loss": 0.5183,
      "step": 18607
    },
    {
      "epoch": 0.5716216631339661,
      "grad_norm": 0.3565095067024231,
      "learning_rate": 1.6259857634636745e-05,
      "loss": 0.5549,
      "step": 18608
    },
    {
      "epoch": 0.5716523822689153,
      "grad_norm": 0.35965749621391296,
      "learning_rate": 1.6259480750993927e-05,
      "loss": 0.5902,
      "step": 18609
    },
    {
      "epoch": 0.5716831014038645,
      "grad_norm": 0.3262888491153717,
      "learning_rate": 1.6259103852731656e-05,
      "loss": 0.5062,
      "step": 18610
    },
    {
      "epoch": 0.5717138205388136,
      "grad_norm": 0.3550766706466675,
      "learning_rate": 1.625872693985081e-05,
      "loss": 0.5531,
      "step": 18611
    },
    {
      "epoch": 0.5717445396737628,
      "grad_norm": 0.5054039359092712,
      "learning_rate": 1.6258350012352268e-05,
      "loss": 0.6118,
      "step": 18612
    },
    {
      "epoch": 0.5717752588087119,
      "grad_norm": 0.33931323885917664,
      "learning_rate": 1.6257973070236916e-05,
      "loss": 0.5545,
      "step": 18613
    },
    {
      "epoch": 0.5718059779436611,
      "grad_norm": 0.3925960659980774,
      "learning_rate": 1.6257596113505628e-05,
      "loss": 0.5666,
      "step": 18614
    },
    {
      "epoch": 0.5718366970786103,
      "grad_norm": 0.34758448600769043,
      "learning_rate": 1.6257219142159287e-05,
      "loss": 0.6286,
      "step": 18615
    },
    {
      "epoch": 0.5718674162135594,
      "grad_norm": 0.40007108449935913,
      "learning_rate": 1.6256842156198772e-05,
      "loss": 0.5378,
      "step": 18616
    },
    {
      "epoch": 0.5718981353485086,
      "grad_norm": 0.32914209365844727,
      "learning_rate": 1.625646515562497e-05,
      "loss": 0.5811,
      "step": 18617
    },
    {
      "epoch": 0.5719288544834578,
      "grad_norm": 0.3489319086074829,
      "learning_rate": 1.6256088140438753e-05,
      "loss": 0.5315,
      "step": 18618
    },
    {
      "epoch": 0.5719595736184069,
      "grad_norm": 0.3583638370037079,
      "learning_rate": 1.6255711110641007e-05,
      "loss": 0.5183,
      "step": 18619
    },
    {
      "epoch": 0.5719902927533561,
      "grad_norm": 0.4039992690086365,
      "learning_rate": 1.6255334066232613e-05,
      "loss": 0.5255,
      "step": 18620
    },
    {
      "epoch": 0.5720210118883052,
      "grad_norm": 0.3218268156051636,
      "learning_rate": 1.6254957007214446e-05,
      "loss": 0.549,
      "step": 18621
    },
    {
      "epoch": 0.5720517310232544,
      "grad_norm": 0.3251972794532776,
      "learning_rate": 1.625457993358739e-05,
      "loss": 0.5423,
      "step": 18622
    },
    {
      "epoch": 0.5720824501582036,
      "grad_norm": 0.3921094834804535,
      "learning_rate": 1.625420284535233e-05,
      "loss": 0.5474,
      "step": 18623
    },
    {
      "epoch": 0.5721131692931527,
      "grad_norm": 0.39150720834732056,
      "learning_rate": 1.6253825742510137e-05,
      "loss": 0.6117,
      "step": 18624
    },
    {
      "epoch": 0.5721438884281018,
      "grad_norm": 0.3475719094276428,
      "learning_rate": 1.62534486250617e-05,
      "loss": 0.5811,
      "step": 18625
    },
    {
      "epoch": 0.572174607563051,
      "grad_norm": 0.39377453923225403,
      "learning_rate": 1.6253071493007896e-05,
      "loss": 0.5463,
      "step": 18626
    },
    {
      "epoch": 0.5722053266980002,
      "grad_norm": 0.3276136517524719,
      "learning_rate": 1.625269434634961e-05,
      "loss": 0.5135,
      "step": 18627
    },
    {
      "epoch": 0.5722360458329493,
      "grad_norm": 0.38513705134391785,
      "learning_rate": 1.6252317185087717e-05,
      "loss": 0.5334,
      "step": 18628
    },
    {
      "epoch": 0.5722667649678985,
      "grad_norm": 0.3966918885707855,
      "learning_rate": 1.62519400092231e-05,
      "loss": 0.6013,
      "step": 18629
    },
    {
      "epoch": 0.5722974841028476,
      "grad_norm": 0.3635323643684387,
      "learning_rate": 1.6251562818756638e-05,
      "loss": 0.5516,
      "step": 18630
    },
    {
      "epoch": 0.5723282032377969,
      "grad_norm": 0.35124123096466064,
      "learning_rate": 1.625118561368922e-05,
      "loss": 0.5962,
      "step": 18631
    },
    {
      "epoch": 0.572358922372746,
      "grad_norm": 0.34515300393104553,
      "learning_rate": 1.625080839402172e-05,
      "loss": 0.5786,
      "step": 18632
    },
    {
      "epoch": 0.5723896415076951,
      "grad_norm": 0.354108989238739,
      "learning_rate": 1.625043115975502e-05,
      "loss": 0.5957,
      "step": 18633
    },
    {
      "epoch": 0.5724203606426443,
      "grad_norm": 0.40924009680747986,
      "learning_rate": 1.625005391089e-05,
      "loss": 0.6134,
      "step": 18634
    },
    {
      "epoch": 0.5724510797775935,
      "grad_norm": 0.3657691478729248,
      "learning_rate": 1.6249676647427542e-05,
      "loss": 0.6134,
      "step": 18635
    },
    {
      "epoch": 0.5724817989125426,
      "grad_norm": 0.39996910095214844,
      "learning_rate": 1.6249299369368528e-05,
      "loss": 0.6298,
      "step": 18636
    },
    {
      "epoch": 0.5725125180474918,
      "grad_norm": 0.4261462390422821,
      "learning_rate": 1.6248922076713843e-05,
      "loss": 0.6365,
      "step": 18637
    },
    {
      "epoch": 0.5725432371824409,
      "grad_norm": 0.3339628577232361,
      "learning_rate": 1.624854476946436e-05,
      "loss": 0.576,
      "step": 18638
    },
    {
      "epoch": 0.57257395631739,
      "grad_norm": 0.4541527330875397,
      "learning_rate": 1.6248167447620966e-05,
      "loss": 0.5776,
      "step": 18639
    },
    {
      "epoch": 0.5726046754523393,
      "grad_norm": 0.3371785581111908,
      "learning_rate": 1.624779011118454e-05,
      "loss": 0.5545,
      "step": 18640
    },
    {
      "epoch": 0.5726353945872884,
      "grad_norm": 0.32801690697669983,
      "learning_rate": 1.6247412760155962e-05,
      "loss": 0.5219,
      "step": 18641
    },
    {
      "epoch": 0.5726661137222376,
      "grad_norm": 0.39489197731018066,
      "learning_rate": 1.624703539453612e-05,
      "loss": 0.6733,
      "step": 18642
    },
    {
      "epoch": 0.5726968328571868,
      "grad_norm": 0.3575400710105896,
      "learning_rate": 1.6246658014325885e-05,
      "loss": 0.5752,
      "step": 18643
    },
    {
      "epoch": 0.5727275519921359,
      "grad_norm": 0.33559542894363403,
      "learning_rate": 1.6246280619526148e-05,
      "loss": 0.6283,
      "step": 18644
    },
    {
      "epoch": 0.5727582711270851,
      "grad_norm": 0.3501774072647095,
      "learning_rate": 1.6245903210137783e-05,
      "loss": 0.5664,
      "step": 18645
    },
    {
      "epoch": 0.5727889902620342,
      "grad_norm": 0.37980398535728455,
      "learning_rate": 1.624552578616168e-05,
      "loss": 0.5386,
      "step": 18646
    },
    {
      "epoch": 0.5728197093969833,
      "grad_norm": 0.3772927224636078,
      "learning_rate": 1.6245148347598712e-05,
      "loss": 0.4677,
      "step": 18647
    },
    {
      "epoch": 0.5728504285319326,
      "grad_norm": 0.35028988122940063,
      "learning_rate": 1.6244770894449762e-05,
      "loss": 0.524,
      "step": 18648
    },
    {
      "epoch": 0.5728811476668817,
      "grad_norm": 0.3794916272163391,
      "learning_rate": 1.6244393426715714e-05,
      "loss": 0.543,
      "step": 18649
    },
    {
      "epoch": 0.5729118668018308,
      "grad_norm": 0.4925001263618469,
      "learning_rate": 1.6244015944397453e-05,
      "loss": 0.6312,
      "step": 18650
    },
    {
      "epoch": 0.57294258593678,
      "grad_norm": 0.38604047894477844,
      "learning_rate": 1.6243638447495853e-05,
      "loss": 0.6122,
      "step": 18651
    },
    {
      "epoch": 0.5729733050717292,
      "grad_norm": 0.34329164028167725,
      "learning_rate": 1.62432609360118e-05,
      "loss": 0.5679,
      "step": 18652
    },
    {
      "epoch": 0.5730040242066783,
      "grad_norm": 0.3516058921813965,
      "learning_rate": 1.6242883409946176e-05,
      "loss": 0.5437,
      "step": 18653
    },
    {
      "epoch": 0.5730347433416275,
      "grad_norm": 0.32062873244285583,
      "learning_rate": 1.624250586929986e-05,
      "loss": 0.4946,
      "step": 18654
    },
    {
      "epoch": 0.5730654624765766,
      "grad_norm": 0.40793290734291077,
      "learning_rate": 1.6242128314073737e-05,
      "loss": 0.5873,
      "step": 18655
    },
    {
      "epoch": 0.5730961816115259,
      "grad_norm": 0.3274938762187958,
      "learning_rate": 1.6241750744268688e-05,
      "loss": 0.6076,
      "step": 18656
    },
    {
      "epoch": 0.573126900746475,
      "grad_norm": 0.3930993974208832,
      "learning_rate": 1.6241373159885593e-05,
      "loss": 0.5592,
      "step": 18657
    },
    {
      "epoch": 0.5731576198814241,
      "grad_norm": 0.3768773674964905,
      "learning_rate": 1.6240995560925335e-05,
      "loss": 0.5478,
      "step": 18658
    },
    {
      "epoch": 0.5731883390163733,
      "grad_norm": 0.38371172547340393,
      "learning_rate": 1.62406179473888e-05,
      "loss": 0.5955,
      "step": 18659
    },
    {
      "epoch": 0.5732190581513225,
      "grad_norm": 0.3587949872016907,
      "learning_rate": 1.6240240319276862e-05,
      "loss": 0.553,
      "step": 18660
    },
    {
      "epoch": 0.5732497772862716,
      "grad_norm": 0.34745723009109497,
      "learning_rate": 1.623986267659041e-05,
      "loss": 0.5764,
      "step": 18661
    },
    {
      "epoch": 0.5732804964212208,
      "grad_norm": 0.390171080827713,
      "learning_rate": 1.6239485019330317e-05,
      "loss": 0.5419,
      "step": 18662
    },
    {
      "epoch": 0.5733112155561699,
      "grad_norm": 0.3745688199996948,
      "learning_rate": 1.6239107347497473e-05,
      "loss": 0.5788,
      "step": 18663
    },
    {
      "epoch": 0.573341934691119,
      "grad_norm": 0.35593512654304504,
      "learning_rate": 1.6238729661092763e-05,
      "loss": 0.5301,
      "step": 18664
    },
    {
      "epoch": 0.5733726538260683,
      "grad_norm": 0.8453759551048279,
      "learning_rate": 1.623835196011706e-05,
      "loss": 0.6181,
      "step": 18665
    },
    {
      "epoch": 0.5734033729610174,
      "grad_norm": 0.36497762799263,
      "learning_rate": 1.623797424457125e-05,
      "loss": 0.58,
      "step": 18666
    },
    {
      "epoch": 0.5734340920959666,
      "grad_norm": 0.34396815299987793,
      "learning_rate": 1.623759651445622e-05,
      "loss": 0.5972,
      "step": 18667
    },
    {
      "epoch": 0.5734648112309157,
      "grad_norm": 0.43795397877693176,
      "learning_rate": 1.623721876977284e-05,
      "loss": 0.5768,
      "step": 18668
    },
    {
      "epoch": 0.5734955303658649,
      "grad_norm": 0.35937249660491943,
      "learning_rate": 1.6236841010522005e-05,
      "loss": 0.576,
      "step": 18669
    },
    {
      "epoch": 0.5735262495008141,
      "grad_norm": 0.3851487338542938,
      "learning_rate": 1.6236463236704592e-05,
      "loss": 0.5846,
      "step": 18670
    },
    {
      "epoch": 0.5735569686357632,
      "grad_norm": 0.3805106282234192,
      "learning_rate": 1.6236085448321482e-05,
      "loss": 0.5846,
      "step": 18671
    },
    {
      "epoch": 0.5735876877707123,
      "grad_norm": 0.3520281910896301,
      "learning_rate": 1.623570764537356e-05,
      "loss": 0.6039,
      "step": 18672
    },
    {
      "epoch": 0.5736184069056616,
      "grad_norm": 0.453770250082016,
      "learning_rate": 1.6235329827861708e-05,
      "loss": 0.5083,
      "step": 18673
    },
    {
      "epoch": 0.5736491260406107,
      "grad_norm": 0.3853272795677185,
      "learning_rate": 1.6234951995786806e-05,
      "loss": 0.4535,
      "step": 18674
    },
    {
      "epoch": 0.5736798451755598,
      "grad_norm": 0.33838319778442383,
      "learning_rate": 1.6234574149149736e-05,
      "loss": 0.6002,
      "step": 18675
    },
    {
      "epoch": 0.573710564310509,
      "grad_norm": 0.32554852962493896,
      "learning_rate": 1.623419628795139e-05,
      "loss": 0.4688,
      "step": 18676
    },
    {
      "epoch": 0.5737412834454582,
      "grad_norm": 0.36140841245651245,
      "learning_rate": 1.6233818412192635e-05,
      "loss": 0.5517,
      "step": 18677
    },
    {
      "epoch": 0.5737720025804073,
      "grad_norm": 0.37955453991889954,
      "learning_rate": 1.6233440521874365e-05,
      "loss": 0.5802,
      "step": 18678
    },
    {
      "epoch": 0.5738027217153565,
      "grad_norm": 0.34169620275497437,
      "learning_rate": 1.6233062616997462e-05,
      "loss": 0.5281,
      "step": 18679
    },
    {
      "epoch": 0.5738334408503056,
      "grad_norm": 0.3528349995613098,
      "learning_rate": 1.6232684697562807e-05,
      "loss": 0.6387,
      "step": 18680
    },
    {
      "epoch": 0.5738641599852549,
      "grad_norm": 0.3304068446159363,
      "learning_rate": 1.6232306763571278e-05,
      "loss": 0.579,
      "step": 18681
    },
    {
      "epoch": 0.573894879120204,
      "grad_norm": 0.40643003582954407,
      "learning_rate": 1.623192881502376e-05,
      "loss": 0.5901,
      "step": 18682
    },
    {
      "epoch": 0.5739255982551531,
      "grad_norm": 0.5732483863830566,
      "learning_rate": 1.623155085192114e-05,
      "loss": 0.5694,
      "step": 18683
    },
    {
      "epoch": 0.5739563173901023,
      "grad_norm": 0.3250564634799957,
      "learning_rate": 1.6231172874264296e-05,
      "loss": 0.5273,
      "step": 18684
    },
    {
      "epoch": 0.5739870365250515,
      "grad_norm": 0.3352609872817993,
      "learning_rate": 1.623079488205411e-05,
      "loss": 0.5767,
      "step": 18685
    },
    {
      "epoch": 0.5740177556600006,
      "grad_norm": 0.3382619321346283,
      "learning_rate": 1.6230416875291474e-05,
      "loss": 0.5032,
      "step": 18686
    },
    {
      "epoch": 0.5740484747949498,
      "grad_norm": 0.39252081513404846,
      "learning_rate": 1.623003885397726e-05,
      "loss": 0.6051,
      "step": 18687
    },
    {
      "epoch": 0.5740791939298989,
      "grad_norm": 0.4138123691082001,
      "learning_rate": 1.6229660818112354e-05,
      "loss": 0.5577,
      "step": 18688
    },
    {
      "epoch": 0.574109913064848,
      "grad_norm": 0.33530667424201965,
      "learning_rate": 1.6229282767697644e-05,
      "loss": 0.5466,
      "step": 18689
    },
    {
      "epoch": 0.5741406321997973,
      "grad_norm": 0.3418010175228119,
      "learning_rate": 1.6228904702734007e-05,
      "loss": 0.5607,
      "step": 18690
    },
    {
      "epoch": 0.5741713513347464,
      "grad_norm": 0.36101147532463074,
      "learning_rate": 1.6228526623222326e-05,
      "loss": 0.5445,
      "step": 18691
    },
    {
      "epoch": 0.5742020704696956,
      "grad_norm": 0.3940165638923645,
      "learning_rate": 1.622814852916349e-05,
      "loss": 0.5857,
      "step": 18692
    },
    {
      "epoch": 0.5742327896046447,
      "grad_norm": 0.39226025342941284,
      "learning_rate": 1.622777042055838e-05,
      "loss": 0.6096,
      "step": 18693
    },
    {
      "epoch": 0.5742635087395939,
      "grad_norm": 0.3640338182449341,
      "learning_rate": 1.6227392297407872e-05,
      "loss": 0.5227,
      "step": 18694
    },
    {
      "epoch": 0.5742942278745431,
      "grad_norm": 0.3476230502128601,
      "learning_rate": 1.6227014159712854e-05,
      "loss": 0.5257,
      "step": 18695
    },
    {
      "epoch": 0.5743249470094922,
      "grad_norm": 0.34315627813339233,
      "learning_rate": 1.6226636007474212e-05,
      "loss": 0.6103,
      "step": 18696
    },
    {
      "epoch": 0.5743556661444413,
      "grad_norm": 0.33580124378204346,
      "learning_rate": 1.6226257840692828e-05,
      "loss": 0.6139,
      "step": 18697
    },
    {
      "epoch": 0.5743863852793906,
      "grad_norm": 0.3489450216293335,
      "learning_rate": 1.622587965936958e-05,
      "loss": 0.5593,
      "step": 18698
    },
    {
      "epoch": 0.5744171044143397,
      "grad_norm": 0.33579131960868835,
      "learning_rate": 1.622550146350536e-05,
      "loss": 0.5641,
      "step": 18699
    },
    {
      "epoch": 0.5744478235492888,
      "grad_norm": 0.3397985100746155,
      "learning_rate": 1.6225123253101042e-05,
      "loss": 0.5931,
      "step": 18700
    },
    {
      "epoch": 0.574478542684238,
      "grad_norm": 0.36184966564178467,
      "learning_rate": 1.6224745028157517e-05,
      "loss": 0.5246,
      "step": 18701
    },
    {
      "epoch": 0.5745092618191872,
      "grad_norm": 0.3642197549343109,
      "learning_rate": 1.6224366788675664e-05,
      "loss": 0.6029,
      "step": 18702
    },
    {
      "epoch": 0.5745399809541364,
      "grad_norm": 0.32161563634872437,
      "learning_rate": 1.6223988534656368e-05,
      "loss": 0.5118,
      "step": 18703
    },
    {
      "epoch": 0.5745707000890855,
      "grad_norm": 0.37086978554725647,
      "learning_rate": 1.6223610266100512e-05,
      "loss": 0.5694,
      "step": 18704
    },
    {
      "epoch": 0.5746014192240346,
      "grad_norm": 0.3472151458263397,
      "learning_rate": 1.6223231983008978e-05,
      "loss": 0.6241,
      "step": 18705
    },
    {
      "epoch": 0.5746321383589839,
      "grad_norm": 0.3481108546257019,
      "learning_rate": 1.622285368538265e-05,
      "loss": 0.4542,
      "step": 18706
    },
    {
      "epoch": 0.574662857493933,
      "grad_norm": 0.3721689283847809,
      "learning_rate": 1.6222475373222416e-05,
      "loss": 0.6105,
      "step": 18707
    },
    {
      "epoch": 0.5746935766288821,
      "grad_norm": 0.3569241762161255,
      "learning_rate": 1.6222097046529156e-05,
      "loss": 0.4812,
      "step": 18708
    },
    {
      "epoch": 0.5747242957638313,
      "grad_norm": 0.3740188479423523,
      "learning_rate": 1.6221718705303752e-05,
      "loss": 0.5658,
      "step": 18709
    },
    {
      "epoch": 0.5747550148987804,
      "grad_norm": 0.43307948112487793,
      "learning_rate": 1.622134034954709e-05,
      "loss": 0.6029,
      "step": 18710
    },
    {
      "epoch": 0.5747857340337296,
      "grad_norm": 0.36401525139808655,
      "learning_rate": 1.6220961979260055e-05,
      "loss": 0.5472,
      "step": 18711
    },
    {
      "epoch": 0.5748164531686788,
      "grad_norm": 0.5649749040603638,
      "learning_rate": 1.622058359444353e-05,
      "loss": 0.484,
      "step": 18712
    },
    {
      "epoch": 0.5748471723036279,
      "grad_norm": 0.36324408650398254,
      "learning_rate": 1.6220205195098394e-05,
      "loss": 0.5597,
      "step": 18713
    },
    {
      "epoch": 0.574877891438577,
      "grad_norm": 0.34888529777526855,
      "learning_rate": 1.6219826781225536e-05,
      "loss": 0.5431,
      "step": 18714
    },
    {
      "epoch": 0.5749086105735263,
      "grad_norm": 0.33821412920951843,
      "learning_rate": 1.621944835282584e-05,
      "loss": 0.5242,
      "step": 18715
    },
    {
      "epoch": 0.5749393297084754,
      "grad_norm": 0.7103124260902405,
      "learning_rate": 1.6219069909900184e-05,
      "loss": 0.5343,
      "step": 18716
    },
    {
      "epoch": 0.5749700488434246,
      "grad_norm": 0.36167284846305847,
      "learning_rate": 1.621869145244946e-05,
      "loss": 0.5251,
      "step": 18717
    },
    {
      "epoch": 0.5750007679783737,
      "grad_norm": 0.3212277591228485,
      "learning_rate": 1.621831298047454e-05,
      "loss": 0.5418,
      "step": 18718
    },
    {
      "epoch": 0.5750314871133229,
      "grad_norm": 0.3764103949069977,
      "learning_rate": 1.6217934493976326e-05,
      "loss": 0.6094,
      "step": 18719
    },
    {
      "epoch": 0.5750622062482721,
      "grad_norm": 0.35084661841392517,
      "learning_rate": 1.6217555992955686e-05,
      "loss": 0.5404,
      "step": 18720
    },
    {
      "epoch": 0.5750929253832212,
      "grad_norm": 0.37007930874824524,
      "learning_rate": 1.621717747741351e-05,
      "loss": 0.6568,
      "step": 18721
    },
    {
      "epoch": 0.5751236445181703,
      "grad_norm": 0.3603229522705078,
      "learning_rate": 1.6216798947350683e-05,
      "loss": 0.5516,
      "step": 18722
    },
    {
      "epoch": 0.5751543636531196,
      "grad_norm": 0.4276076555252075,
      "learning_rate": 1.6216420402768087e-05,
      "loss": 0.6244,
      "step": 18723
    },
    {
      "epoch": 0.5751850827880687,
      "grad_norm": 0.35440686345100403,
      "learning_rate": 1.6216041843666605e-05,
      "loss": 0.5863,
      "step": 18724
    },
    {
      "epoch": 0.5752158019230178,
      "grad_norm": 0.3826444745063782,
      "learning_rate": 1.6215663270047124e-05,
      "loss": 0.5444,
      "step": 18725
    },
    {
      "epoch": 0.575246521057967,
      "grad_norm": 0.31441643834114075,
      "learning_rate": 1.6215284681910532e-05,
      "loss": 0.5238,
      "step": 18726
    },
    {
      "epoch": 0.5752772401929162,
      "grad_norm": 0.45617833733558655,
      "learning_rate": 1.6214906079257706e-05,
      "loss": 0.5156,
      "step": 18727
    },
    {
      "epoch": 0.5753079593278654,
      "grad_norm": 0.3434596061706543,
      "learning_rate": 1.621452746208953e-05,
      "loss": 0.5248,
      "step": 18728
    },
    {
      "epoch": 0.5753386784628145,
      "grad_norm": 0.3699931204319,
      "learning_rate": 1.6214148830406892e-05,
      "loss": 0.5651,
      "step": 18729
    },
    {
      "epoch": 0.5753693975977636,
      "grad_norm": 0.3360949158668518,
      "learning_rate": 1.6213770184210677e-05,
      "loss": 0.5683,
      "step": 18730
    },
    {
      "epoch": 0.5754001167327129,
      "grad_norm": 0.37315335869789124,
      "learning_rate": 1.621339152350177e-05,
      "loss": 0.6176,
      "step": 18731
    },
    {
      "epoch": 0.575430835867662,
      "grad_norm": 0.3956177830696106,
      "learning_rate": 1.6213012848281052e-05,
      "loss": 0.564,
      "step": 18732
    },
    {
      "epoch": 0.5754615550026111,
      "grad_norm": 0.49973708391189575,
      "learning_rate": 1.6212634158549407e-05,
      "loss": 0.6615,
      "step": 18733
    },
    {
      "epoch": 0.5754922741375603,
      "grad_norm": 0.31259554624557495,
      "learning_rate": 1.6212255454307718e-05,
      "loss": 0.532,
      "step": 18734
    },
    {
      "epoch": 0.5755229932725094,
      "grad_norm": 0.3788837492465973,
      "learning_rate": 1.6211876735556876e-05,
      "loss": 0.5292,
      "step": 18735
    },
    {
      "epoch": 0.5755537124074586,
      "grad_norm": 0.3642123341560364,
      "learning_rate": 1.6211498002297763e-05,
      "loss": 0.5683,
      "step": 18736
    },
    {
      "epoch": 0.5755844315424078,
      "grad_norm": 0.39181193709373474,
      "learning_rate": 1.6211119254531263e-05,
      "loss": 0.5117,
      "step": 18737
    },
    {
      "epoch": 0.5756151506773569,
      "grad_norm": 0.3465396761894226,
      "learning_rate": 1.6210740492258256e-05,
      "loss": 0.552,
      "step": 18738
    },
    {
      "epoch": 0.575645869812306,
      "grad_norm": 0.39285534620285034,
      "learning_rate": 1.6210361715479633e-05,
      "loss": 0.5591,
      "step": 18739
    },
    {
      "epoch": 0.5756765889472553,
      "grad_norm": 0.34312763810157776,
      "learning_rate": 1.620998292419628e-05,
      "loss": 0.491,
      "step": 18740
    },
    {
      "epoch": 0.5757073080822044,
      "grad_norm": 0.37707674503326416,
      "learning_rate": 1.6209604118409073e-05,
      "loss": 0.5798,
      "step": 18741
    },
    {
      "epoch": 0.5757380272171536,
      "grad_norm": 0.38113152980804443,
      "learning_rate": 1.6209225298118906e-05,
      "loss": 0.5516,
      "step": 18742
    },
    {
      "epoch": 0.5757687463521027,
      "grad_norm": 0.35153815150260925,
      "learning_rate": 1.6208846463326655e-05,
      "loss": 0.5533,
      "step": 18743
    },
    {
      "epoch": 0.5757994654870519,
      "grad_norm": 0.35808083415031433,
      "learning_rate": 1.6208467614033213e-05,
      "loss": 0.6152,
      "step": 18744
    },
    {
      "epoch": 0.5758301846220011,
      "grad_norm": 0.36403751373291016,
      "learning_rate": 1.620808875023946e-05,
      "loss": 0.6289,
      "step": 18745
    },
    {
      "epoch": 0.5758609037569502,
      "grad_norm": 0.34637418389320374,
      "learning_rate": 1.6207709871946282e-05,
      "loss": 0.5449,
      "step": 18746
    },
    {
      "epoch": 0.5758916228918993,
      "grad_norm": 0.34893879294395447,
      "learning_rate": 1.6207330979154565e-05,
      "loss": 0.5594,
      "step": 18747
    },
    {
      "epoch": 0.5759223420268486,
      "grad_norm": 0.4037153720855713,
      "learning_rate": 1.620695207186519e-05,
      "loss": 0.5995,
      "step": 18748
    },
    {
      "epoch": 0.5759530611617977,
      "grad_norm": 0.39426353573799133,
      "learning_rate": 1.620657315007905e-05,
      "loss": 0.5881,
      "step": 18749
    },
    {
      "epoch": 0.5759837802967468,
      "grad_norm": 0.3705660104751587,
      "learning_rate": 1.6206194213797022e-05,
      "loss": 0.5981,
      "step": 18750
    },
    {
      "epoch": 0.576014499431696,
      "grad_norm": 0.37692415714263916,
      "learning_rate": 1.6205815263019994e-05,
      "loss": 0.5755,
      "step": 18751
    },
    {
      "epoch": 0.5760452185666451,
      "grad_norm": 0.34310707449913025,
      "learning_rate": 1.6205436297748853e-05,
      "loss": 0.5729,
      "step": 18752
    },
    {
      "epoch": 0.5760759377015944,
      "grad_norm": 0.36306455731391907,
      "learning_rate": 1.620505731798448e-05,
      "loss": 0.5911,
      "step": 18753
    },
    {
      "epoch": 0.5761066568365435,
      "grad_norm": 0.41170477867126465,
      "learning_rate": 1.6204678323727763e-05,
      "loss": 0.5847,
      "step": 18754
    },
    {
      "epoch": 0.5761373759714926,
      "grad_norm": 0.3478248715400696,
      "learning_rate": 1.6204299314979587e-05,
      "loss": 0.5105,
      "step": 18755
    },
    {
      "epoch": 0.5761680951064418,
      "grad_norm": 0.33027487993240356,
      "learning_rate": 1.6203920291740835e-05,
      "loss": 0.5792,
      "step": 18756
    },
    {
      "epoch": 0.576198814241391,
      "grad_norm": 0.3462214767932892,
      "learning_rate": 1.6203541254012395e-05,
      "loss": 0.5829,
      "step": 18757
    },
    {
      "epoch": 0.5762295333763401,
      "grad_norm": 0.3485485315322876,
      "learning_rate": 1.620316220179515e-05,
      "loss": 0.6103,
      "step": 18758
    },
    {
      "epoch": 0.5762602525112893,
      "grad_norm": 0.37667056918144226,
      "learning_rate": 1.620278313508999e-05,
      "loss": 0.4725,
      "step": 18759
    },
    {
      "epoch": 0.5762909716462384,
      "grad_norm": 0.3620540201663971,
      "learning_rate": 1.6202404053897794e-05,
      "loss": 0.5426,
      "step": 18760
    },
    {
      "epoch": 0.5763216907811876,
      "grad_norm": 0.3446927070617676,
      "learning_rate": 1.620202495821945e-05,
      "loss": 0.5768,
      "step": 18761
    },
    {
      "epoch": 0.5763524099161368,
      "grad_norm": 0.385452538728714,
      "learning_rate": 1.6201645848055845e-05,
      "loss": 0.5874,
      "step": 18762
    },
    {
      "epoch": 0.5763831290510859,
      "grad_norm": 0.35888656973838806,
      "learning_rate": 1.620126672340786e-05,
      "loss": 0.5078,
      "step": 18763
    },
    {
      "epoch": 0.576413848186035,
      "grad_norm": 0.37871697545051575,
      "learning_rate": 1.6200887584276385e-05,
      "loss": 0.5425,
      "step": 18764
    },
    {
      "epoch": 0.5764445673209843,
      "grad_norm": 0.32593321800231934,
      "learning_rate": 1.6200508430662305e-05,
      "loss": 0.6552,
      "step": 18765
    },
    {
      "epoch": 0.5764752864559334,
      "grad_norm": 0.696624755859375,
      "learning_rate": 1.6200129262566506e-05,
      "loss": 0.5027,
      "step": 18766
    },
    {
      "epoch": 0.5765060055908826,
      "grad_norm": 0.3338969051837921,
      "learning_rate": 1.6199750079989868e-05,
      "loss": 0.5333,
      "step": 18767
    },
    {
      "epoch": 0.5765367247258317,
      "grad_norm": 0.3524090349674225,
      "learning_rate": 1.6199370882933284e-05,
      "loss": 0.5563,
      "step": 18768
    },
    {
      "epoch": 0.5765674438607808,
      "grad_norm": 0.3561571538448334,
      "learning_rate": 1.6198991671397634e-05,
      "loss": 0.5719,
      "step": 18769
    },
    {
      "epoch": 0.5765981629957301,
      "grad_norm": 0.31751763820648193,
      "learning_rate": 1.619861244538381e-05,
      "loss": 0.5776,
      "step": 18770
    },
    {
      "epoch": 0.5766288821306792,
      "grad_norm": 0.3544142544269562,
      "learning_rate": 1.619823320489269e-05,
      "loss": 0.5745,
      "step": 18771
    },
    {
      "epoch": 0.5766596012656283,
      "grad_norm": 0.3811413645744324,
      "learning_rate": 1.6197853949925164e-05,
      "loss": 0.543,
      "step": 18772
    },
    {
      "epoch": 0.5766903204005775,
      "grad_norm": 0.32830533385276794,
      "learning_rate": 1.6197474680482117e-05,
      "loss": 0.4842,
      "step": 18773
    },
    {
      "epoch": 0.5767210395355267,
      "grad_norm": 0.41295990347862244,
      "learning_rate": 1.6197095396564435e-05,
      "loss": 0.5897,
      "step": 18774
    },
    {
      "epoch": 0.5767517586704758,
      "grad_norm": 0.3483271896839142,
      "learning_rate": 1.6196716098173007e-05,
      "loss": 0.6099,
      "step": 18775
    },
    {
      "epoch": 0.576782477805425,
      "grad_norm": 0.4491732120513916,
      "learning_rate": 1.619633678530871e-05,
      "loss": 0.5792,
      "step": 18776
    },
    {
      "epoch": 0.5768131969403741,
      "grad_norm": 0.379768431186676,
      "learning_rate": 1.6195957457972444e-05,
      "loss": 0.6456,
      "step": 18777
    },
    {
      "epoch": 0.5768439160753234,
      "grad_norm": 0.35413846373558044,
      "learning_rate": 1.6195578116165078e-05,
      "loss": 0.531,
      "step": 18778
    },
    {
      "epoch": 0.5768746352102725,
      "grad_norm": 0.3800845742225647,
      "learning_rate": 1.6195198759887512e-05,
      "loss": 0.5754,
      "step": 18779
    },
    {
      "epoch": 0.5769053543452216,
      "grad_norm": 0.3535778820514679,
      "learning_rate": 1.6194819389140622e-05,
      "loss": 0.5248,
      "step": 18780
    },
    {
      "epoch": 0.5769360734801708,
      "grad_norm": 0.3578692376613617,
      "learning_rate": 1.61944400039253e-05,
      "loss": 0.54,
      "step": 18781
    },
    {
      "epoch": 0.57696679261512,
      "grad_norm": 0.3912733793258667,
      "learning_rate": 1.6194060604242437e-05,
      "loss": 0.5377,
      "step": 18782
    },
    {
      "epoch": 0.5769975117500691,
      "grad_norm": 0.313044935464859,
      "learning_rate": 1.6193681190092908e-05,
      "loss": 0.5145,
      "step": 18783
    },
    {
      "epoch": 0.5770282308850183,
      "grad_norm": 0.3722119927406311,
      "learning_rate": 1.61933017614776e-05,
      "loss": 0.5599,
      "step": 18784
    },
    {
      "epoch": 0.5770589500199674,
      "grad_norm": 0.33461326360702515,
      "learning_rate": 1.619292231839741e-05,
      "loss": 0.5119,
      "step": 18785
    },
    {
      "epoch": 0.5770896691549166,
      "grad_norm": 0.3662077784538269,
      "learning_rate": 1.6192542860853214e-05,
      "loss": 0.6783,
      "step": 18786
    },
    {
      "epoch": 0.5771203882898658,
      "grad_norm": 0.38602524995803833,
      "learning_rate": 1.6192163388845907e-05,
      "loss": 0.5986,
      "step": 18787
    },
    {
      "epoch": 0.5771511074248149,
      "grad_norm": 0.34127989411354065,
      "learning_rate": 1.6191783902376362e-05,
      "loss": 0.5785,
      "step": 18788
    },
    {
      "epoch": 0.577181826559764,
      "grad_norm": 0.32867735624313354,
      "learning_rate": 1.6191404401445478e-05,
      "loss": 0.6077,
      "step": 18789
    },
    {
      "epoch": 0.5772125456947133,
      "grad_norm": 0.40325626730918884,
      "learning_rate": 1.6191024886054133e-05,
      "loss": 0.5655,
      "step": 18790
    },
    {
      "epoch": 0.5772432648296624,
      "grad_norm": 0.3586740493774414,
      "learning_rate": 1.619064535620322e-05,
      "loss": 0.5332,
      "step": 18791
    },
    {
      "epoch": 0.5772739839646116,
      "grad_norm": 0.37204572558403015,
      "learning_rate": 1.6190265811893624e-05,
      "loss": 0.5588,
      "step": 18792
    },
    {
      "epoch": 0.5773047030995607,
      "grad_norm": 0.3496866822242737,
      "learning_rate": 1.6189886253126225e-05,
      "loss": 0.651,
      "step": 18793
    },
    {
      "epoch": 0.5773354222345098,
      "grad_norm": 0.33767223358154297,
      "learning_rate": 1.618950667990192e-05,
      "loss": 0.5814,
      "step": 18794
    },
    {
      "epoch": 0.5773661413694591,
      "grad_norm": 0.3795228898525238,
      "learning_rate": 1.6189127092221587e-05,
      "loss": 0.6123,
      "step": 18795
    },
    {
      "epoch": 0.5773968605044082,
      "grad_norm": 0.47575458884239197,
      "learning_rate": 1.6188747490086113e-05,
      "loss": 0.6661,
      "step": 18796
    },
    {
      "epoch": 0.5774275796393573,
      "grad_norm": 0.33075186610221863,
      "learning_rate": 1.618836787349639e-05,
      "loss": 0.5891,
      "step": 18797
    },
    {
      "epoch": 0.5774582987743065,
      "grad_norm": 0.4080420732498169,
      "learning_rate": 1.61879882424533e-05,
      "loss": 0.5587,
      "step": 18798
    },
    {
      "epoch": 0.5774890179092557,
      "grad_norm": 0.36786890029907227,
      "learning_rate": 1.6187608596957734e-05,
      "loss": 0.5069,
      "step": 18799
    },
    {
      "epoch": 0.5775197370442048,
      "grad_norm": 0.3230457007884979,
      "learning_rate": 1.6187228937010574e-05,
      "loss": 0.5427,
      "step": 18800
    },
    {
      "epoch": 0.577550456179154,
      "grad_norm": 0.39028722047805786,
      "learning_rate": 1.618684926261271e-05,
      "loss": 0.5863,
      "step": 18801
    },
    {
      "epoch": 0.5775811753141031,
      "grad_norm": 0.36895135045051575,
      "learning_rate": 1.6186469573765024e-05,
      "loss": 0.5286,
      "step": 18802
    },
    {
      "epoch": 0.5776118944490524,
      "grad_norm": 0.32970213890075684,
      "learning_rate": 1.6186089870468408e-05,
      "loss": 0.5107,
      "step": 18803
    },
    {
      "epoch": 0.5776426135840015,
      "grad_norm": 0.3333958685398102,
      "learning_rate": 1.6185710152723748e-05,
      "loss": 0.5754,
      "step": 18804
    },
    {
      "epoch": 0.5776733327189506,
      "grad_norm": 0.44436973333358765,
      "learning_rate": 1.6185330420531934e-05,
      "loss": 0.5812,
      "step": 18805
    },
    {
      "epoch": 0.5777040518538998,
      "grad_norm": 0.3294956088066101,
      "learning_rate": 1.618495067389384e-05,
      "loss": 0.6528,
      "step": 18806
    },
    {
      "epoch": 0.577734770988849,
      "grad_norm": 0.3259119689464569,
      "learning_rate": 1.618457091281037e-05,
      "loss": 0.5942,
      "step": 18807
    },
    {
      "epoch": 0.5777654901237981,
      "grad_norm": 0.3551010489463806,
      "learning_rate": 1.6184191137282396e-05,
      "loss": 0.4964,
      "step": 18808
    },
    {
      "epoch": 0.5777962092587473,
      "grad_norm": 0.3533056378364563,
      "learning_rate": 1.6183811347310816e-05,
      "loss": 0.5695,
      "step": 18809
    },
    {
      "epoch": 0.5778269283936964,
      "grad_norm": 0.36802375316619873,
      "learning_rate": 1.6183431542896514e-05,
      "loss": 0.6048,
      "step": 18810
    },
    {
      "epoch": 0.5778576475286455,
      "grad_norm": 0.3264409303665161,
      "learning_rate": 1.6183051724040372e-05,
      "loss": 0.563,
      "step": 18811
    },
    {
      "epoch": 0.5778883666635948,
      "grad_norm": 0.34600958228111267,
      "learning_rate": 1.6182671890743284e-05,
      "loss": 0.6413,
      "step": 18812
    },
    {
      "epoch": 0.5779190857985439,
      "grad_norm": 0.3268650770187378,
      "learning_rate": 1.618229204300613e-05,
      "loss": 0.5851,
      "step": 18813
    },
    {
      "epoch": 0.5779498049334931,
      "grad_norm": 0.34858980774879456,
      "learning_rate": 1.6181912180829802e-05,
      "loss": 0.5669,
      "step": 18814
    },
    {
      "epoch": 0.5779805240684422,
      "grad_norm": 0.3676437437534332,
      "learning_rate": 1.6181532304215188e-05,
      "loss": 0.5313,
      "step": 18815
    },
    {
      "epoch": 0.5780112432033914,
      "grad_norm": 0.3700445592403412,
      "learning_rate": 1.6181152413163172e-05,
      "loss": 0.602,
      "step": 18816
    },
    {
      "epoch": 0.5780419623383406,
      "grad_norm": 0.3302961587905884,
      "learning_rate": 1.618077250767464e-05,
      "loss": 0.5279,
      "step": 18817
    },
    {
      "epoch": 0.5780726814732897,
      "grad_norm": 0.5040359497070312,
      "learning_rate": 1.618039258775049e-05,
      "loss": 0.6057,
      "step": 18818
    },
    {
      "epoch": 0.5781034006082388,
      "grad_norm": 0.33811497688293457,
      "learning_rate": 1.61800126533916e-05,
      "loss": 0.5176,
      "step": 18819
    },
    {
      "epoch": 0.5781341197431881,
      "grad_norm": 0.33863353729248047,
      "learning_rate": 1.6179632704598856e-05,
      "loss": 0.612,
      "step": 18820
    },
    {
      "epoch": 0.5781648388781372,
      "grad_norm": 0.35844627022743225,
      "learning_rate": 1.6179252741373147e-05,
      "loss": 0.5473,
      "step": 18821
    },
    {
      "epoch": 0.5781955580130863,
      "grad_norm": 0.3673538565635681,
      "learning_rate": 1.6178872763715367e-05,
      "loss": 0.5145,
      "step": 18822
    },
    {
      "epoch": 0.5782262771480355,
      "grad_norm": 0.34238138794898987,
      "learning_rate": 1.6178492771626394e-05,
      "loss": 0.5803,
      "step": 18823
    },
    {
      "epoch": 0.5782569962829847,
      "grad_norm": 0.356260746717453,
      "learning_rate": 1.617811276510712e-05,
      "loss": 0.5408,
      "step": 18824
    },
    {
      "epoch": 0.5782877154179338,
      "grad_norm": 0.3031003475189209,
      "learning_rate": 1.617773274415843e-05,
      "loss": 0.5657,
      "step": 18825
    },
    {
      "epoch": 0.578318434552883,
      "grad_norm": 0.35450607538223267,
      "learning_rate": 1.6177352708781216e-05,
      "loss": 0.6304,
      "step": 18826
    },
    {
      "epoch": 0.5783491536878321,
      "grad_norm": 0.3741878271102905,
      "learning_rate": 1.6176972658976364e-05,
      "loss": 0.6123,
      "step": 18827
    },
    {
      "epoch": 0.5783798728227814,
      "grad_norm": 0.3748418688774109,
      "learning_rate": 1.617659259474476e-05,
      "loss": 0.6367,
      "step": 18828
    },
    {
      "epoch": 0.5784105919577305,
      "grad_norm": 0.4654434621334076,
      "learning_rate": 1.6176212516087294e-05,
      "loss": 0.5922,
      "step": 18829
    },
    {
      "epoch": 0.5784413110926796,
      "grad_norm": 0.33575382828712463,
      "learning_rate": 1.617583242300485e-05,
      "loss": 0.5619,
      "step": 18830
    },
    {
      "epoch": 0.5784720302276288,
      "grad_norm": 0.3497731685638428,
      "learning_rate": 1.6175452315498323e-05,
      "loss": 0.5261,
      "step": 18831
    },
    {
      "epoch": 0.578502749362578,
      "grad_norm": 0.3579937219619751,
      "learning_rate": 1.617507219356859e-05,
      "loss": 0.5941,
      "step": 18832
    },
    {
      "epoch": 0.5785334684975271,
      "grad_norm": 0.5210243463516235,
      "learning_rate": 1.6174692057216548e-05,
      "loss": 0.6277,
      "step": 18833
    },
    {
      "epoch": 0.5785641876324763,
      "grad_norm": 0.3668278157711029,
      "learning_rate": 1.6174311906443078e-05,
      "loss": 0.6036,
      "step": 18834
    },
    {
      "epoch": 0.5785949067674254,
      "grad_norm": 0.3548945188522339,
      "learning_rate": 1.6173931741249075e-05,
      "loss": 0.5723,
      "step": 18835
    },
    {
      "epoch": 0.5786256259023745,
      "grad_norm": 0.3330089747905731,
      "learning_rate": 1.617355156163542e-05,
      "loss": 0.5329,
      "step": 18836
    },
    {
      "epoch": 0.5786563450373238,
      "grad_norm": 0.369961142539978,
      "learning_rate": 1.6173171367603006e-05,
      "loss": 0.4428,
      "step": 18837
    },
    {
      "epoch": 0.5786870641722729,
      "grad_norm": 0.36173194646835327,
      "learning_rate": 1.617279115915272e-05,
      "loss": 0.5695,
      "step": 18838
    },
    {
      "epoch": 0.5787177833072221,
      "grad_norm": 0.4311367869377136,
      "learning_rate": 1.617241093628545e-05,
      "loss": 0.5593,
      "step": 18839
    },
    {
      "epoch": 0.5787485024421712,
      "grad_norm": 0.3472992777824402,
      "learning_rate": 1.617203069900208e-05,
      "loss": 0.5065,
      "step": 18840
    },
    {
      "epoch": 0.5787792215771204,
      "grad_norm": 0.34410610795021057,
      "learning_rate": 1.6171650447303503e-05,
      "loss": 0.5415,
      "step": 18841
    },
    {
      "epoch": 0.5788099407120696,
      "grad_norm": 0.40099573135375977,
      "learning_rate": 1.6171270181190607e-05,
      "loss": 0.6,
      "step": 18842
    },
    {
      "epoch": 0.5788406598470187,
      "grad_norm": 0.3751898407936096,
      "learning_rate": 1.6170889900664276e-05,
      "loss": 0.5445,
      "step": 18843
    },
    {
      "epoch": 0.5788713789819678,
      "grad_norm": 0.38884446024894714,
      "learning_rate": 1.61705096057254e-05,
      "loss": 0.6046,
      "step": 18844
    },
    {
      "epoch": 0.5789020981169171,
      "grad_norm": 0.31922009587287903,
      "learning_rate": 1.617012929637487e-05,
      "loss": 0.4967,
      "step": 18845
    },
    {
      "epoch": 0.5789328172518662,
      "grad_norm": 0.32105231285095215,
      "learning_rate": 1.616974897261357e-05,
      "loss": 0.5358,
      "step": 18846
    },
    {
      "epoch": 0.5789635363868153,
      "grad_norm": 0.40902188420295715,
      "learning_rate": 1.6169368634442393e-05,
      "loss": 0.6126,
      "step": 18847
    },
    {
      "epoch": 0.5789942555217645,
      "grad_norm": 0.3469145596027374,
      "learning_rate": 1.6168988281862222e-05,
      "loss": 0.5473,
      "step": 18848
    },
    {
      "epoch": 0.5790249746567137,
      "grad_norm": 0.37456271052360535,
      "learning_rate": 1.616860791487395e-05,
      "loss": 0.5737,
      "step": 18849
    },
    {
      "epoch": 0.5790556937916628,
      "grad_norm": 0.39213326573371887,
      "learning_rate": 1.6168227533478463e-05,
      "loss": 0.5595,
      "step": 18850
    },
    {
      "epoch": 0.579086412926612,
      "grad_norm": 0.42411842942237854,
      "learning_rate": 1.616784713767665e-05,
      "loss": 0.5145,
      "step": 18851
    },
    {
      "epoch": 0.5791171320615611,
      "grad_norm": 0.3456067144870758,
      "learning_rate": 1.61674667274694e-05,
      "loss": 0.536,
      "step": 18852
    },
    {
      "epoch": 0.5791478511965104,
      "grad_norm": 0.3453506827354431,
      "learning_rate": 1.6167086302857597e-05,
      "loss": 0.5398,
      "step": 18853
    },
    {
      "epoch": 0.5791785703314595,
      "grad_norm": 0.3491151034832001,
      "learning_rate": 1.6166705863842136e-05,
      "loss": 0.5264,
      "step": 18854
    },
    {
      "epoch": 0.5792092894664086,
      "grad_norm": 0.35424548387527466,
      "learning_rate": 1.6166325410423902e-05,
      "loss": 0.5147,
      "step": 18855
    },
    {
      "epoch": 0.5792400086013578,
      "grad_norm": 0.40120360255241394,
      "learning_rate": 1.6165944942603787e-05,
      "loss": 0.6242,
      "step": 18856
    },
    {
      "epoch": 0.579270727736307,
      "grad_norm": 0.3103204667568207,
      "learning_rate": 1.6165564460382676e-05,
      "loss": 0.5351,
      "step": 18857
    },
    {
      "epoch": 0.5793014468712561,
      "grad_norm": 0.35477447509765625,
      "learning_rate": 1.6165183963761456e-05,
      "loss": 0.5373,
      "step": 18858
    },
    {
      "epoch": 0.5793321660062053,
      "grad_norm": 0.4424416422843933,
      "learning_rate": 1.616480345274102e-05,
      "loss": 0.5326,
      "step": 18859
    },
    {
      "epoch": 0.5793628851411544,
      "grad_norm": 0.3362339437007904,
      "learning_rate": 1.6164422927322256e-05,
      "loss": 0.5682,
      "step": 18860
    },
    {
      "epoch": 0.5793936042761035,
      "grad_norm": 0.3626258373260498,
      "learning_rate": 1.6164042387506048e-05,
      "loss": 0.5776,
      "step": 18861
    },
    {
      "epoch": 0.5794243234110528,
      "grad_norm": 0.33086422085762024,
      "learning_rate": 1.6163661833293293e-05,
      "loss": 0.5348,
      "step": 18862
    },
    {
      "epoch": 0.5794550425460019,
      "grad_norm": 0.35275375843048096,
      "learning_rate": 1.616328126468487e-05,
      "loss": 0.5971,
      "step": 18863
    },
    {
      "epoch": 0.5794857616809511,
      "grad_norm": 0.3760519027709961,
      "learning_rate": 1.6162900681681678e-05,
      "loss": 0.6057,
      "step": 18864
    },
    {
      "epoch": 0.5795164808159002,
      "grad_norm": 0.385963499546051,
      "learning_rate": 1.61625200842846e-05,
      "loss": 0.5098,
      "step": 18865
    },
    {
      "epoch": 0.5795471999508494,
      "grad_norm": 0.3653593063354492,
      "learning_rate": 1.6162139472494523e-05,
      "loss": 0.5234,
      "step": 18866
    },
    {
      "epoch": 0.5795779190857986,
      "grad_norm": 0.37149664759635925,
      "learning_rate": 1.6161758846312343e-05,
      "loss": 0.5467,
      "step": 18867
    },
    {
      "epoch": 0.5796086382207477,
      "grad_norm": 0.5922569036483765,
      "learning_rate": 1.6161378205738943e-05,
      "loss": 0.6017,
      "step": 18868
    },
    {
      "epoch": 0.5796393573556968,
      "grad_norm": 0.3427928686141968,
      "learning_rate": 1.6160997550775217e-05,
      "loss": 0.5897,
      "step": 18869
    },
    {
      "epoch": 0.5796700764906461,
      "grad_norm": 0.40089136362075806,
      "learning_rate": 1.6160616881422047e-05,
      "loss": 0.6159,
      "step": 18870
    },
    {
      "epoch": 0.5797007956255952,
      "grad_norm": 0.41690593957901,
      "learning_rate": 1.616023619768033e-05,
      "loss": 0.5747,
      "step": 18871
    },
    {
      "epoch": 0.5797315147605443,
      "grad_norm": 0.3503185212612152,
      "learning_rate": 1.6159855499550946e-05,
      "loss": 0.6595,
      "step": 18872
    },
    {
      "epoch": 0.5797622338954935,
      "grad_norm": 0.3392617106437683,
      "learning_rate": 1.615947478703479e-05,
      "loss": 0.5658,
      "step": 18873
    },
    {
      "epoch": 0.5797929530304426,
      "grad_norm": 0.3437831997871399,
      "learning_rate": 1.6159094060132756e-05,
      "loss": 0.5416,
      "step": 18874
    },
    {
      "epoch": 0.5798236721653918,
      "grad_norm": 0.3289218246936798,
      "learning_rate": 1.615871331884572e-05,
      "loss": 0.5669,
      "step": 18875
    },
    {
      "epoch": 0.579854391300341,
      "grad_norm": 1.2300713062286377,
      "learning_rate": 1.6158332563174583e-05,
      "loss": 0.6635,
      "step": 18876
    },
    {
      "epoch": 0.5798851104352901,
      "grad_norm": 0.5557264089584351,
      "learning_rate": 1.615795179312023e-05,
      "loss": 0.474,
      "step": 18877
    },
    {
      "epoch": 0.5799158295702393,
      "grad_norm": 0.34251248836517334,
      "learning_rate": 1.615757100868355e-05,
      "loss": 0.6341,
      "step": 18878
    },
    {
      "epoch": 0.5799465487051885,
      "grad_norm": 0.3457905352115631,
      "learning_rate": 1.615719020986543e-05,
      "loss": 0.5604,
      "step": 18879
    },
    {
      "epoch": 0.5799772678401376,
      "grad_norm": 0.38809001445770264,
      "learning_rate": 1.6156809396666768e-05,
      "loss": 0.5922,
      "step": 18880
    },
    {
      "epoch": 0.5800079869750868,
      "grad_norm": 0.4572273790836334,
      "learning_rate": 1.6156428569088447e-05,
      "loss": 0.5492,
      "step": 18881
    },
    {
      "epoch": 0.5800387061100359,
      "grad_norm": 0.3456781208515167,
      "learning_rate": 1.6156047727131355e-05,
      "loss": 0.5896,
      "step": 18882
    },
    {
      "epoch": 0.5800694252449851,
      "grad_norm": 0.36042070388793945,
      "learning_rate": 1.6155666870796384e-05,
      "loss": 0.5628,
      "step": 18883
    },
    {
      "epoch": 0.5801001443799343,
      "grad_norm": 0.3679330348968506,
      "learning_rate": 1.615528600008442e-05,
      "loss": 0.5854,
      "step": 18884
    },
    {
      "epoch": 0.5801308635148834,
      "grad_norm": 0.3331673741340637,
      "learning_rate": 1.615490511499636e-05,
      "loss": 0.5282,
      "step": 18885
    },
    {
      "epoch": 0.5801615826498325,
      "grad_norm": 0.3532065451145172,
      "learning_rate": 1.6154524215533088e-05,
      "loss": 0.5361,
      "step": 18886
    },
    {
      "epoch": 0.5801923017847818,
      "grad_norm": 0.37271955609321594,
      "learning_rate": 1.6154143301695497e-05,
      "loss": 0.5825,
      "step": 18887
    },
    {
      "epoch": 0.5802230209197309,
      "grad_norm": 0.34911587834358215,
      "learning_rate": 1.615376237348447e-05,
      "loss": 0.5225,
      "step": 18888
    },
    {
      "epoch": 0.5802537400546801,
      "grad_norm": 0.38360849022865295,
      "learning_rate": 1.6153381430900905e-05,
      "loss": 0.5249,
      "step": 18889
    },
    {
      "epoch": 0.5802844591896292,
      "grad_norm": 0.334821879863739,
      "learning_rate": 1.6153000473945687e-05,
      "loss": 0.5208,
      "step": 18890
    },
    {
      "epoch": 0.5803151783245784,
      "grad_norm": 0.3743862509727478,
      "learning_rate": 1.6152619502619705e-05,
      "loss": 0.5757,
      "step": 18891
    },
    {
      "epoch": 0.5803458974595276,
      "grad_norm": 0.3756842017173767,
      "learning_rate": 1.615223851692385e-05,
      "loss": 0.5225,
      "step": 18892
    },
    {
      "epoch": 0.5803766165944767,
      "grad_norm": 0.4077881872653961,
      "learning_rate": 1.6151857516859016e-05,
      "loss": 0.5227,
      "step": 18893
    },
    {
      "epoch": 0.5804073357294258,
      "grad_norm": 0.34889301657676697,
      "learning_rate": 1.6151476502426087e-05,
      "loss": 0.5081,
      "step": 18894
    },
    {
      "epoch": 0.580438054864375,
      "grad_norm": 0.3917873799800873,
      "learning_rate": 1.615109547362595e-05,
      "loss": 0.6005,
      "step": 18895
    },
    {
      "epoch": 0.5804687739993242,
      "grad_norm": 0.38822609186172485,
      "learning_rate": 1.6150714430459507e-05,
      "loss": 0.6095,
      "step": 18896
    },
    {
      "epoch": 0.5804994931342733,
      "grad_norm": 0.33713874220848083,
      "learning_rate": 1.615033337292764e-05,
      "loss": 0.5759,
      "step": 18897
    },
    {
      "epoch": 0.5805302122692225,
      "grad_norm": 0.3814067244529724,
      "learning_rate": 1.614995230103124e-05,
      "loss": 0.5229,
      "step": 18898
    },
    {
      "epoch": 0.5805609314041716,
      "grad_norm": 0.6469272375106812,
      "learning_rate": 1.6149571214771197e-05,
      "loss": 0.5529,
      "step": 18899
    },
    {
      "epoch": 0.5805916505391209,
      "grad_norm": 0.3742387592792511,
      "learning_rate": 1.61491901141484e-05,
      "loss": 0.6958,
      "step": 18900
    },
    {
      "epoch": 0.58062236967407,
      "grad_norm": 0.4063176214694977,
      "learning_rate": 1.614880899916374e-05,
      "loss": 0.6893,
      "step": 18901
    },
    {
      "epoch": 0.5806530888090191,
      "grad_norm": 0.3602615296840668,
      "learning_rate": 1.6148427869818103e-05,
      "loss": 0.5353,
      "step": 18902
    },
    {
      "epoch": 0.5806838079439683,
      "grad_norm": 0.36213287711143494,
      "learning_rate": 1.6148046726112388e-05,
      "loss": 0.5942,
      "step": 18903
    },
    {
      "epoch": 0.5807145270789175,
      "grad_norm": 0.3511231243610382,
      "learning_rate": 1.6147665568047483e-05,
      "loss": 0.5319,
      "step": 18904
    },
    {
      "epoch": 0.5807452462138666,
      "grad_norm": 0.3646296560764313,
      "learning_rate": 1.6147284395624268e-05,
      "loss": 0.6071,
      "step": 18905
    },
    {
      "epoch": 0.5807759653488158,
      "grad_norm": 0.3375126123428345,
      "learning_rate": 1.6146903208843645e-05,
      "loss": 0.5318,
      "step": 18906
    },
    {
      "epoch": 0.5808066844837649,
      "grad_norm": 0.4156622290611267,
      "learning_rate": 1.61465220077065e-05,
      "loss": 0.5428,
      "step": 18907
    },
    {
      "epoch": 0.580837403618714,
      "grad_norm": 0.38175061345100403,
      "learning_rate": 1.6146140792213724e-05,
      "loss": 0.6388,
      "step": 18908
    },
    {
      "epoch": 0.5808681227536633,
      "grad_norm": 0.3644830584526062,
      "learning_rate": 1.614575956236621e-05,
      "loss": 0.5643,
      "step": 18909
    },
    {
      "epoch": 0.5808988418886124,
      "grad_norm": 0.3547399938106537,
      "learning_rate": 1.6145378318164843e-05,
      "loss": 0.5593,
      "step": 18910
    },
    {
      "epoch": 0.5809295610235615,
      "grad_norm": 0.3944936990737915,
      "learning_rate": 1.6144997059610513e-05,
      "loss": 0.5601,
      "step": 18911
    },
    {
      "epoch": 0.5809602801585108,
      "grad_norm": 0.3314049541950226,
      "learning_rate": 1.6144615786704115e-05,
      "loss": 0.5055,
      "step": 18912
    },
    {
      "epoch": 0.5809909992934599,
      "grad_norm": 0.37169530987739563,
      "learning_rate": 1.6144234499446537e-05,
      "loss": 0.562,
      "step": 18913
    },
    {
      "epoch": 0.5810217184284091,
      "grad_norm": 0.3556937575340271,
      "learning_rate": 1.614385319783867e-05,
      "loss": 0.6693,
      "step": 18914
    },
    {
      "epoch": 0.5810524375633582,
      "grad_norm": 0.3831900358200073,
      "learning_rate": 1.6143471881881407e-05,
      "loss": 0.5688,
      "step": 18915
    },
    {
      "epoch": 0.5810831566983073,
      "grad_norm": 0.329112708568573,
      "learning_rate": 1.6143090551575635e-05,
      "loss": 0.5015,
      "step": 18916
    },
    {
      "epoch": 0.5811138758332566,
      "grad_norm": 0.3324778378009796,
      "learning_rate": 1.6142709206922246e-05,
      "loss": 0.5809,
      "step": 18917
    },
    {
      "epoch": 0.5811445949682057,
      "grad_norm": 0.43133509159088135,
      "learning_rate": 1.6142327847922132e-05,
      "loss": 0.5364,
      "step": 18918
    },
    {
      "epoch": 0.5811753141031548,
      "grad_norm": 0.39036184549331665,
      "learning_rate": 1.6141946474576183e-05,
      "loss": 0.5772,
      "step": 18919
    },
    {
      "epoch": 0.581206033238104,
      "grad_norm": 0.314384788274765,
      "learning_rate": 1.6141565086885288e-05,
      "loss": 0.5415,
      "step": 18920
    },
    {
      "epoch": 0.5812367523730532,
      "grad_norm": 0.3623393476009369,
      "learning_rate": 1.6141183684850337e-05,
      "loss": 0.5912,
      "step": 18921
    },
    {
      "epoch": 0.5812674715080023,
      "grad_norm": 0.3768017292022705,
      "learning_rate": 1.6140802268472224e-05,
      "loss": 0.5676,
      "step": 18922
    },
    {
      "epoch": 0.5812981906429515,
      "grad_norm": 0.3708040714263916,
      "learning_rate": 1.6140420837751838e-05,
      "loss": 0.5178,
      "step": 18923
    },
    {
      "epoch": 0.5813289097779006,
      "grad_norm": 0.45041000843048096,
      "learning_rate": 1.614003939269007e-05,
      "loss": 0.5158,
      "step": 18924
    },
    {
      "epoch": 0.5813596289128499,
      "grad_norm": 0.37570178508758545,
      "learning_rate": 1.613965793328781e-05,
      "loss": 0.6378,
      "step": 18925
    },
    {
      "epoch": 0.581390348047799,
      "grad_norm": 0.34976744651794434,
      "learning_rate": 1.6139276459545953e-05,
      "loss": 0.5611,
      "step": 18926
    },
    {
      "epoch": 0.5814210671827481,
      "grad_norm": 0.4059438407421112,
      "learning_rate": 1.6138894971465386e-05,
      "loss": 0.6385,
      "step": 18927
    },
    {
      "epoch": 0.5814517863176973,
      "grad_norm": 0.36650049686431885,
      "learning_rate": 1.6138513469047002e-05,
      "loss": 0.5607,
      "step": 18928
    },
    {
      "epoch": 0.5814825054526465,
      "grad_norm": 0.3687934875488281,
      "learning_rate": 1.613813195229169e-05,
      "loss": 0.6127,
      "step": 18929
    },
    {
      "epoch": 0.5815132245875956,
      "grad_norm": 0.3556056320667267,
      "learning_rate": 1.613775042120034e-05,
      "loss": 0.5258,
      "step": 18930
    },
    {
      "epoch": 0.5815439437225448,
      "grad_norm": 0.3405482769012451,
      "learning_rate": 1.6137368875773847e-05,
      "loss": 0.5908,
      "step": 18931
    },
    {
      "epoch": 0.5815746628574939,
      "grad_norm": 0.32699477672576904,
      "learning_rate": 1.61369873160131e-05,
      "loss": 0.4733,
      "step": 18932
    },
    {
      "epoch": 0.581605381992443,
      "grad_norm": 0.3423696458339691,
      "learning_rate": 1.6136605741918992e-05,
      "loss": 0.5243,
      "step": 18933
    },
    {
      "epoch": 0.5816361011273923,
      "grad_norm": 0.3569898307323456,
      "learning_rate": 1.613622415349241e-05,
      "loss": 0.6324,
      "step": 18934
    },
    {
      "epoch": 0.5816668202623414,
      "grad_norm": 0.32030242681503296,
      "learning_rate": 1.6135842550734253e-05,
      "loss": 0.5623,
      "step": 18935
    },
    {
      "epoch": 0.5816975393972905,
      "grad_norm": 0.3403686583042145,
      "learning_rate": 1.6135460933645406e-05,
      "loss": 0.5473,
      "step": 18936
    },
    {
      "epoch": 0.5817282585322398,
      "grad_norm": 0.3277445137500763,
      "learning_rate": 1.6135079302226756e-05,
      "loss": 0.5803,
      "step": 18937
    },
    {
      "epoch": 0.5817589776671889,
      "grad_norm": 0.36106860637664795,
      "learning_rate": 1.6134697656479206e-05,
      "loss": 0.5937,
      "step": 18938
    },
    {
      "epoch": 0.5817896968021381,
      "grad_norm": 0.4025826156139374,
      "learning_rate": 1.6134315996403636e-05,
      "loss": 0.6442,
      "step": 18939
    },
    {
      "epoch": 0.5818204159370872,
      "grad_norm": 0.3456144630908966,
      "learning_rate": 1.6133934322000948e-05,
      "loss": 0.5313,
      "step": 18940
    },
    {
      "epoch": 0.5818511350720363,
      "grad_norm": 0.3459492623806,
      "learning_rate": 1.6133552633272026e-05,
      "loss": 0.5328,
      "step": 18941
    },
    {
      "epoch": 0.5818818542069856,
      "grad_norm": 0.35957154631614685,
      "learning_rate": 1.613317093021776e-05,
      "loss": 0.5298,
      "step": 18942
    },
    {
      "epoch": 0.5819125733419347,
      "grad_norm": 0.33445683121681213,
      "learning_rate": 1.613278921283905e-05,
      "loss": 0.607,
      "step": 18943
    },
    {
      "epoch": 0.5819432924768838,
      "grad_norm": 0.34493276476860046,
      "learning_rate": 1.6132407481136778e-05,
      "loss": 0.5441,
      "step": 18944
    },
    {
      "epoch": 0.581974011611833,
      "grad_norm": 0.34767770767211914,
      "learning_rate": 1.6132025735111844e-05,
      "loss": 0.5969,
      "step": 18945
    },
    {
      "epoch": 0.5820047307467822,
      "grad_norm": 0.32150211930274963,
      "learning_rate": 1.6131643974765134e-05,
      "loss": 0.5107,
      "step": 18946
    },
    {
      "epoch": 0.5820354498817313,
      "grad_norm": 0.39940693974494934,
      "learning_rate": 1.613126220009754e-05,
      "loss": 0.504,
      "step": 18947
    },
    {
      "epoch": 0.5820661690166805,
      "grad_norm": 0.3278278708457947,
      "learning_rate": 1.6130880411109955e-05,
      "loss": 0.5658,
      "step": 18948
    },
    {
      "epoch": 0.5820968881516296,
      "grad_norm": 0.38490453362464905,
      "learning_rate": 1.6130498607803272e-05,
      "loss": 0.5223,
      "step": 18949
    },
    {
      "epoch": 0.5821276072865789,
      "grad_norm": 0.3711799085140228,
      "learning_rate": 1.6130116790178382e-05,
      "loss": 0.5988,
      "step": 18950
    },
    {
      "epoch": 0.582158326421528,
      "grad_norm": 0.32307231426239014,
      "learning_rate": 1.6129734958236175e-05,
      "loss": 0.5903,
      "step": 18951
    },
    {
      "epoch": 0.5821890455564771,
      "grad_norm": 0.35098716616630554,
      "learning_rate": 1.6129353111977542e-05,
      "loss": 0.5689,
      "step": 18952
    },
    {
      "epoch": 0.5822197646914263,
      "grad_norm": 0.3820827603340149,
      "learning_rate": 1.6128971251403382e-05,
      "loss": 0.5667,
      "step": 18953
    },
    {
      "epoch": 0.5822504838263755,
      "grad_norm": 0.3602457344532013,
      "learning_rate": 1.6128589376514575e-05,
      "loss": 0.551,
      "step": 18954
    },
    {
      "epoch": 0.5822812029613246,
      "grad_norm": 0.39277252554893494,
      "learning_rate": 1.6128207487312026e-05,
      "loss": 0.5138,
      "step": 18955
    },
    {
      "epoch": 0.5823119220962738,
      "grad_norm": 0.40706920623779297,
      "learning_rate": 1.6127825583796615e-05,
      "loss": 0.6099,
      "step": 18956
    },
    {
      "epoch": 0.5823426412312229,
      "grad_norm": 0.38212189078330994,
      "learning_rate": 1.612744366596924e-05,
      "loss": 0.5387,
      "step": 18957
    },
    {
      "epoch": 0.582373360366172,
      "grad_norm": 0.3487694561481476,
      "learning_rate": 1.6127061733830795e-05,
      "loss": 0.5331,
      "step": 18958
    },
    {
      "epoch": 0.5824040795011213,
      "grad_norm": 0.3821548521518707,
      "learning_rate": 1.6126679787382168e-05,
      "loss": 0.6034,
      "step": 18959
    },
    {
      "epoch": 0.5824347986360704,
      "grad_norm": 0.33604681491851807,
      "learning_rate": 1.6126297826624254e-05,
      "loss": 0.5656,
      "step": 18960
    },
    {
      "epoch": 0.5824655177710195,
      "grad_norm": 0.3678250014781952,
      "learning_rate": 1.612591585155794e-05,
      "loss": 0.5449,
      "step": 18961
    },
    {
      "epoch": 0.5824962369059687,
      "grad_norm": 0.3517409861087799,
      "learning_rate": 1.6125533862184127e-05,
      "loss": 0.5042,
      "step": 18962
    },
    {
      "epoch": 0.5825269560409179,
      "grad_norm": 0.4236067831516266,
      "learning_rate": 1.6125151858503696e-05,
      "loss": 0.5829,
      "step": 18963
    },
    {
      "epoch": 0.5825576751758671,
      "grad_norm": 0.32931479811668396,
      "learning_rate": 1.612476984051755e-05,
      "loss": 0.5642,
      "step": 18964
    },
    {
      "epoch": 0.5825883943108162,
      "grad_norm": 0.31634753942489624,
      "learning_rate": 1.6124387808226575e-05,
      "loss": 0.474,
      "step": 18965
    },
    {
      "epoch": 0.5826191134457653,
      "grad_norm": 0.35424908995628357,
      "learning_rate": 1.6124005761631664e-05,
      "loss": 0.5646,
      "step": 18966
    },
    {
      "epoch": 0.5826498325807146,
      "grad_norm": 0.3520033657550812,
      "learning_rate": 1.6123623700733707e-05,
      "loss": 0.5553,
      "step": 18967
    },
    {
      "epoch": 0.5826805517156637,
      "grad_norm": 0.3246608078479767,
      "learning_rate": 1.6123241625533602e-05,
      "loss": 0.5702,
      "step": 18968
    },
    {
      "epoch": 0.5827112708506128,
      "grad_norm": 0.35558274388313293,
      "learning_rate": 1.612285953603224e-05,
      "loss": 0.5601,
      "step": 18969
    },
    {
      "epoch": 0.582741989985562,
      "grad_norm": 0.3763192892074585,
      "learning_rate": 1.6122477432230512e-05,
      "loss": 0.5546,
      "step": 18970
    },
    {
      "epoch": 0.5827727091205112,
      "grad_norm": 0.32860663533210754,
      "learning_rate": 1.6122095314129306e-05,
      "loss": 0.5405,
      "step": 18971
    },
    {
      "epoch": 0.5828034282554603,
      "grad_norm": 0.3427245616912842,
      "learning_rate": 1.6121713181729524e-05,
      "loss": 0.5015,
      "step": 18972
    },
    {
      "epoch": 0.5828341473904095,
      "grad_norm": 0.3535906970500946,
      "learning_rate": 1.6121331035032052e-05,
      "loss": 0.5506,
      "step": 18973
    },
    {
      "epoch": 0.5828648665253586,
      "grad_norm": 0.31702300906181335,
      "learning_rate": 1.6120948874037782e-05,
      "loss": 0.452,
      "step": 18974
    },
    {
      "epoch": 0.5828955856603079,
      "grad_norm": 0.4061774015426636,
      "learning_rate": 1.612056669874761e-05,
      "loss": 0.4999,
      "step": 18975
    },
    {
      "epoch": 0.582926304795257,
      "grad_norm": 0.39382776618003845,
      "learning_rate": 1.6120184509162426e-05,
      "loss": 0.5279,
      "step": 18976
    },
    {
      "epoch": 0.5829570239302061,
      "grad_norm": 0.3564707636833191,
      "learning_rate": 1.6119802305283122e-05,
      "loss": 0.5413,
      "step": 18977
    },
    {
      "epoch": 0.5829877430651553,
      "grad_norm": 0.35049471259117126,
      "learning_rate": 1.6119420087110594e-05,
      "loss": 0.6168,
      "step": 18978
    },
    {
      "epoch": 0.5830184622001044,
      "grad_norm": 0.3694213330745697,
      "learning_rate": 1.6119037854645734e-05,
      "loss": 0.5237,
      "step": 18979
    },
    {
      "epoch": 0.5830491813350536,
      "grad_norm": 0.3432502746582031,
      "learning_rate": 1.6118655607889433e-05,
      "loss": 0.5853,
      "step": 18980
    },
    {
      "epoch": 0.5830799004700028,
      "grad_norm": 0.46064865589141846,
      "learning_rate": 1.6118273346842584e-05,
      "loss": 0.5245,
      "step": 18981
    },
    {
      "epoch": 0.5831106196049519,
      "grad_norm": 0.330211341381073,
      "learning_rate": 1.611789107150608e-05,
      "loss": 0.5057,
      "step": 18982
    },
    {
      "epoch": 0.583141338739901,
      "grad_norm": 0.3600941300392151,
      "learning_rate": 1.6117508781880814e-05,
      "loss": 0.5862,
      "step": 18983
    },
    {
      "epoch": 0.5831720578748503,
      "grad_norm": 0.35416343808174133,
      "learning_rate": 1.611712647796768e-05,
      "loss": 0.509,
      "step": 18984
    },
    {
      "epoch": 0.5832027770097994,
      "grad_norm": 0.3909826874732971,
      "learning_rate": 1.6116744159767573e-05,
      "loss": 0.5536,
      "step": 18985
    },
    {
      "epoch": 0.5832334961447485,
      "grad_norm": 0.42188331484794617,
      "learning_rate": 1.611636182728138e-05,
      "loss": 0.5876,
      "step": 18986
    },
    {
      "epoch": 0.5832642152796977,
      "grad_norm": 0.3779236674308777,
      "learning_rate": 1.6115979480509992e-05,
      "loss": 0.5519,
      "step": 18987
    },
    {
      "epoch": 0.5832949344146469,
      "grad_norm": 0.3578627407550812,
      "learning_rate": 1.6115597119454313e-05,
      "loss": 0.5584,
      "step": 18988
    },
    {
      "epoch": 0.5833256535495961,
      "grad_norm": 0.3765947222709656,
      "learning_rate": 1.6115214744115228e-05,
      "loss": 0.5615,
      "step": 18989
    },
    {
      "epoch": 0.5833563726845452,
      "grad_norm": 0.377760112285614,
      "learning_rate": 1.6114832354493634e-05,
      "loss": 0.5837,
      "step": 18990
    },
    {
      "epoch": 0.5833870918194943,
      "grad_norm": 0.4344131648540497,
      "learning_rate": 1.611444995059042e-05,
      "loss": 0.5486,
      "step": 18991
    },
    {
      "epoch": 0.5834178109544436,
      "grad_norm": 0.3417031764984131,
      "learning_rate": 1.6114067532406478e-05,
      "loss": 0.5871,
      "step": 18992
    },
    {
      "epoch": 0.5834485300893927,
      "grad_norm": 0.35007360577583313,
      "learning_rate": 1.6113685099942712e-05,
      "loss": 0.5642,
      "step": 18993
    },
    {
      "epoch": 0.5834792492243418,
      "grad_norm": 0.40038278698921204,
      "learning_rate": 1.61133026532e-05,
      "loss": 0.5236,
      "step": 18994
    },
    {
      "epoch": 0.583509968359291,
      "grad_norm": 0.34329017996788025,
      "learning_rate": 1.6112920192179244e-05,
      "loss": 0.5919,
      "step": 18995
    },
    {
      "epoch": 0.5835406874942402,
      "grad_norm": 0.35686659812927246,
      "learning_rate": 1.611253771688134e-05,
      "loss": 0.595,
      "step": 18996
    },
    {
      "epoch": 0.5835714066291893,
      "grad_norm": 0.35144317150115967,
      "learning_rate": 1.6112155227307175e-05,
      "loss": 0.5142,
      "step": 18997
    },
    {
      "epoch": 0.5836021257641385,
      "grad_norm": 0.35510706901550293,
      "learning_rate": 1.6111772723457644e-05,
      "loss": 0.5517,
      "step": 18998
    },
    {
      "epoch": 0.5836328448990876,
      "grad_norm": 0.3650219440460205,
      "learning_rate": 1.611139020533364e-05,
      "loss": 0.5531,
      "step": 18999
    },
    {
      "epoch": 0.5836635640340369,
      "grad_norm": 0.3402097225189209,
      "learning_rate": 1.6111007672936056e-05,
      "loss": 0.493,
      "step": 19000
    },
    {
      "epoch": 0.583694283168986,
      "grad_norm": 0.3984505832195282,
      "learning_rate": 1.611062512626579e-05,
      "loss": 0.5156,
      "step": 19001
    },
    {
      "epoch": 0.5837250023039351,
      "grad_norm": 0.34309014678001404,
      "learning_rate": 1.6110242565323733e-05,
      "loss": 0.6032,
      "step": 19002
    },
    {
      "epoch": 0.5837557214388843,
      "grad_norm": 1.4810490608215332,
      "learning_rate": 1.6109859990110775e-05,
      "loss": 0.5682,
      "step": 19003
    },
    {
      "epoch": 0.5837864405738334,
      "grad_norm": 0.46906769275665283,
      "learning_rate": 1.6109477400627816e-05,
      "loss": 0.5337,
      "step": 19004
    },
    {
      "epoch": 0.5838171597087826,
      "grad_norm": 0.33647677302360535,
      "learning_rate": 1.610909479687574e-05,
      "loss": 0.5536,
      "step": 19005
    },
    {
      "epoch": 0.5838478788437318,
      "grad_norm": 0.32075753808021545,
      "learning_rate": 1.6108712178855452e-05,
      "loss": 0.5307,
      "step": 19006
    },
    {
      "epoch": 0.5838785979786809,
      "grad_norm": 0.32426828145980835,
      "learning_rate": 1.610832954656784e-05,
      "loss": 0.4726,
      "step": 19007
    },
    {
      "epoch": 0.58390931711363,
      "grad_norm": 0.36429303884506226,
      "learning_rate": 1.6107946900013795e-05,
      "loss": 0.3638,
      "step": 19008
    },
    {
      "epoch": 0.5839400362485793,
      "grad_norm": 0.3632923662662506,
      "learning_rate": 1.6107564239194213e-05,
      "loss": 0.5926,
      "step": 19009
    },
    {
      "epoch": 0.5839707553835284,
      "grad_norm": 0.34860867261886597,
      "learning_rate": 1.610718156410999e-05,
      "loss": 0.5226,
      "step": 19010
    },
    {
      "epoch": 0.5840014745184776,
      "grad_norm": 0.3156141936779022,
      "learning_rate": 1.610679887476202e-05,
      "loss": 0.5794,
      "step": 19011
    },
    {
      "epoch": 0.5840321936534267,
      "grad_norm": 0.32957735657691956,
      "learning_rate": 1.610641617115119e-05,
      "loss": 0.5328,
      "step": 19012
    },
    {
      "epoch": 0.5840629127883759,
      "grad_norm": 0.6255026459693909,
      "learning_rate": 1.61060334532784e-05,
      "loss": 0.5764,
      "step": 19013
    },
    {
      "epoch": 0.5840936319233251,
      "grad_norm": 0.4045165777206421,
      "learning_rate": 1.6105650721144543e-05,
      "loss": 0.5837,
      "step": 19014
    },
    {
      "epoch": 0.5841243510582742,
      "grad_norm": 0.3273485600948334,
      "learning_rate": 1.6105267974750516e-05,
      "loss": 0.5284,
      "step": 19015
    },
    {
      "epoch": 0.5841550701932233,
      "grad_norm": 0.32644984126091003,
      "learning_rate": 1.6104885214097204e-05,
      "loss": 0.5259,
      "step": 19016
    },
    {
      "epoch": 0.5841857893281726,
      "grad_norm": 0.38079768419265747,
      "learning_rate": 1.6104502439185506e-05,
      "loss": 0.4965,
      "step": 19017
    },
    {
      "epoch": 0.5842165084631217,
      "grad_norm": 0.3429318964481354,
      "learning_rate": 1.6104119650016315e-05,
      "loss": 0.5425,
      "step": 19018
    },
    {
      "epoch": 0.5842472275980708,
      "grad_norm": 0.30511152744293213,
      "learning_rate": 1.6103736846590533e-05,
      "loss": 0.515,
      "step": 19019
    },
    {
      "epoch": 0.58427794673302,
      "grad_norm": 0.3672880530357361,
      "learning_rate": 1.6103354028909045e-05,
      "loss": 0.6116,
      "step": 19020
    },
    {
      "epoch": 0.5843086658679691,
      "grad_norm": 0.3771500885486603,
      "learning_rate": 1.6102971196972747e-05,
      "loss": 0.5102,
      "step": 19021
    },
    {
      "epoch": 0.5843393850029183,
      "grad_norm": 0.3312995135784149,
      "learning_rate": 1.610258835078253e-05,
      "loss": 0.5425,
      "step": 19022
    },
    {
      "epoch": 0.5843701041378675,
      "grad_norm": 0.36316317319869995,
      "learning_rate": 1.6102205490339296e-05,
      "loss": 0.566,
      "step": 19023
    },
    {
      "epoch": 0.5844008232728166,
      "grad_norm": 0.571011483669281,
      "learning_rate": 1.6101822615643935e-05,
      "loss": 0.686,
      "step": 19024
    },
    {
      "epoch": 0.5844315424077658,
      "grad_norm": 0.3829183876514435,
      "learning_rate": 1.6101439726697336e-05,
      "loss": 0.5374,
      "step": 19025
    },
    {
      "epoch": 0.584462261542715,
      "grad_norm": 0.34561651945114136,
      "learning_rate": 1.6101056823500404e-05,
      "loss": 0.5436,
      "step": 19026
    },
    {
      "epoch": 0.5844929806776641,
      "grad_norm": 0.36981499195098877,
      "learning_rate": 1.6100673906054023e-05,
      "loss": 0.5887,
      "step": 19027
    },
    {
      "epoch": 0.5845236998126133,
      "grad_norm": 0.3518851697444916,
      "learning_rate": 1.6100290974359097e-05,
      "loss": 0.5665,
      "step": 19028
    },
    {
      "epoch": 0.5845544189475624,
      "grad_norm": 0.3686752915382385,
      "learning_rate": 1.6099908028416512e-05,
      "loss": 0.5925,
      "step": 19029
    },
    {
      "epoch": 0.5845851380825116,
      "grad_norm": 0.4019148051738739,
      "learning_rate": 1.6099525068227168e-05,
      "loss": 0.5956,
      "step": 19030
    },
    {
      "epoch": 0.5846158572174608,
      "grad_norm": 0.38044822216033936,
      "learning_rate": 1.6099142093791956e-05,
      "loss": 0.5818,
      "step": 19031
    },
    {
      "epoch": 0.5846465763524099,
      "grad_norm": 0.43839797377586365,
      "learning_rate": 1.609875910511177e-05,
      "loss": 0.6613,
      "step": 19032
    },
    {
      "epoch": 0.584677295487359,
      "grad_norm": 0.36122357845306396,
      "learning_rate": 1.609837610218751e-05,
      "loss": 0.5762,
      "step": 19033
    },
    {
      "epoch": 0.5847080146223083,
      "grad_norm": 0.6398884057998657,
      "learning_rate": 1.6097993085020063e-05,
      "loss": 0.5458,
      "step": 19034
    },
    {
      "epoch": 0.5847387337572574,
      "grad_norm": 0.5717496871948242,
      "learning_rate": 1.609761005361033e-05,
      "loss": 0.6293,
      "step": 19035
    },
    {
      "epoch": 0.5847694528922066,
      "grad_norm": 0.35525357723236084,
      "learning_rate": 1.60972270079592e-05,
      "loss": 0.5586,
      "step": 19036
    },
    {
      "epoch": 0.5848001720271557,
      "grad_norm": 0.324018269777298,
      "learning_rate": 1.609684394806757e-05,
      "loss": 0.6402,
      "step": 19037
    },
    {
      "epoch": 0.5848308911621048,
      "grad_norm": 0.36993589997291565,
      "learning_rate": 1.6096460873936338e-05,
      "loss": 0.5766,
      "step": 19038
    },
    {
      "epoch": 0.5848616102970541,
      "grad_norm": 0.3744373619556427,
      "learning_rate": 1.6096077785566396e-05,
      "loss": 0.5769,
      "step": 19039
    },
    {
      "epoch": 0.5848923294320032,
      "grad_norm": 0.33012309670448303,
      "learning_rate": 1.6095694682958636e-05,
      "loss": 0.5565,
      "step": 19040
    },
    {
      "epoch": 0.5849230485669523,
      "grad_norm": 0.32912009954452515,
      "learning_rate": 1.6095311566113957e-05,
      "loss": 0.5447,
      "step": 19041
    },
    {
      "epoch": 0.5849537677019016,
      "grad_norm": 0.37907981872558594,
      "learning_rate": 1.6094928435033256e-05,
      "loss": 0.5152,
      "step": 19042
    },
    {
      "epoch": 0.5849844868368507,
      "grad_norm": 0.369662880897522,
      "learning_rate": 1.6094545289717418e-05,
      "loss": 0.564,
      "step": 19043
    },
    {
      "epoch": 0.5850152059717998,
      "grad_norm": 0.34219950437545776,
      "learning_rate": 1.6094162130167346e-05,
      "loss": 0.6216,
      "step": 19044
    },
    {
      "epoch": 0.585045925106749,
      "grad_norm": 0.3508072793483734,
      "learning_rate": 1.6093778956383933e-05,
      "loss": 0.541,
      "step": 19045
    },
    {
      "epoch": 0.5850766442416981,
      "grad_norm": 0.4366646409034729,
      "learning_rate": 1.6093395768368073e-05,
      "loss": 0.665,
      "step": 19046
    },
    {
      "epoch": 0.5851073633766473,
      "grad_norm": 0.33086130023002625,
      "learning_rate": 1.6093012566120663e-05,
      "loss": 0.5197,
      "step": 19047
    },
    {
      "epoch": 0.5851380825115965,
      "grad_norm": 0.31960979104042053,
      "learning_rate": 1.6092629349642595e-05,
      "loss": 0.5761,
      "step": 19048
    },
    {
      "epoch": 0.5851688016465456,
      "grad_norm": 0.33051595091819763,
      "learning_rate": 1.6092246118934767e-05,
      "loss": 0.4663,
      "step": 19049
    },
    {
      "epoch": 0.5851995207814948,
      "grad_norm": 0.36196425557136536,
      "learning_rate": 1.6091862873998072e-05,
      "loss": 0.5794,
      "step": 19050
    },
    {
      "epoch": 0.585230239916444,
      "grad_norm": 0.6424837112426758,
      "learning_rate": 1.6091479614833406e-05,
      "loss": 0.6294,
      "step": 19051
    },
    {
      "epoch": 0.5852609590513931,
      "grad_norm": 0.38559800386428833,
      "learning_rate": 1.6091096341441663e-05,
      "loss": 0.56,
      "step": 19052
    },
    {
      "epoch": 0.5852916781863423,
      "grad_norm": 0.32812055945396423,
      "learning_rate": 1.609071305382374e-05,
      "loss": 0.566,
      "step": 19053
    },
    {
      "epoch": 0.5853223973212914,
      "grad_norm": 0.3585057854652405,
      "learning_rate": 1.6090329751980533e-05,
      "loss": 0.5641,
      "step": 19054
    },
    {
      "epoch": 0.5853531164562406,
      "grad_norm": 0.33682316541671753,
      "learning_rate": 1.6089946435912932e-05,
      "loss": 0.5765,
      "step": 19055
    },
    {
      "epoch": 0.5853838355911898,
      "grad_norm": 0.4531397223472595,
      "learning_rate": 1.608956310562184e-05,
      "loss": 0.5441,
      "step": 19056
    },
    {
      "epoch": 0.5854145547261389,
      "grad_norm": 0.38367101550102234,
      "learning_rate": 1.6089179761108144e-05,
      "loss": 0.5858,
      "step": 19057
    },
    {
      "epoch": 0.585445273861088,
      "grad_norm": 0.3378032147884369,
      "learning_rate": 1.6088796402372742e-05,
      "loss": 0.4711,
      "step": 19058
    },
    {
      "epoch": 0.5854759929960373,
      "grad_norm": 0.34020471572875977,
      "learning_rate": 1.6088413029416535e-05,
      "loss": 0.4874,
      "step": 19059
    },
    {
      "epoch": 0.5855067121309864,
      "grad_norm": 0.34142088890075684,
      "learning_rate": 1.6088029642240413e-05,
      "loss": 0.5398,
      "step": 19060
    },
    {
      "epoch": 0.5855374312659356,
      "grad_norm": 0.3250628709793091,
      "learning_rate": 1.608764624084527e-05,
      "loss": 0.5025,
      "step": 19061
    },
    {
      "epoch": 0.5855681504008847,
      "grad_norm": 0.4266628623008728,
      "learning_rate": 1.6087262825232007e-05,
      "loss": 0.5492,
      "step": 19062
    },
    {
      "epoch": 0.5855988695358338,
      "grad_norm": 0.35039564967155457,
      "learning_rate": 1.6086879395401518e-05,
      "loss": 0.5554,
      "step": 19063
    },
    {
      "epoch": 0.5856295886707831,
      "grad_norm": 0.3411007225513458,
      "learning_rate": 1.6086495951354696e-05,
      "loss": 0.5645,
      "step": 19064
    },
    {
      "epoch": 0.5856603078057322,
      "grad_norm": 0.3412201404571533,
      "learning_rate": 1.6086112493092435e-05,
      "loss": 0.5654,
      "step": 19065
    },
    {
      "epoch": 0.5856910269406813,
      "grad_norm": 0.48150551319122314,
      "learning_rate": 1.6085729020615634e-05,
      "loss": 0.6063,
      "step": 19066
    },
    {
      "epoch": 0.5857217460756305,
      "grad_norm": 0.35922932624816895,
      "learning_rate": 1.6085345533925192e-05,
      "loss": 0.5384,
      "step": 19067
    },
    {
      "epoch": 0.5857524652105797,
      "grad_norm": 0.48187899589538574,
      "learning_rate": 1.6084962033021998e-05,
      "loss": 0.6292,
      "step": 19068
    },
    {
      "epoch": 0.5857831843455288,
      "grad_norm": 0.37217429280281067,
      "learning_rate": 1.6084578517906947e-05,
      "loss": 0.601,
      "step": 19069
    },
    {
      "epoch": 0.585813903480478,
      "grad_norm": 0.43105393648147583,
      "learning_rate": 1.6084194988580943e-05,
      "loss": 0.5614,
      "step": 19070
    },
    {
      "epoch": 0.5858446226154271,
      "grad_norm": 0.36954379081726074,
      "learning_rate": 1.6083811445044873e-05,
      "loss": 0.5761,
      "step": 19071
    },
    {
      "epoch": 0.5858753417503763,
      "grad_norm": 0.3685623109340668,
      "learning_rate": 1.6083427887299636e-05,
      "loss": 0.5503,
      "step": 19072
    },
    {
      "epoch": 0.5859060608853255,
      "grad_norm": 0.35402241349220276,
      "learning_rate": 1.608304431534613e-05,
      "loss": 0.5381,
      "step": 19073
    },
    {
      "epoch": 0.5859367800202746,
      "grad_norm": 0.5184417963027954,
      "learning_rate": 1.6082660729185248e-05,
      "loss": 0.5912,
      "step": 19074
    },
    {
      "epoch": 0.5859674991552238,
      "grad_norm": 0.37338802218437195,
      "learning_rate": 1.608227712881789e-05,
      "loss": 0.5821,
      "step": 19075
    },
    {
      "epoch": 0.585998218290173,
      "grad_norm": 0.39683887362480164,
      "learning_rate": 1.6081893514244948e-05,
      "loss": 0.5734,
      "step": 19076
    },
    {
      "epoch": 0.5860289374251221,
      "grad_norm": 0.3625904321670532,
      "learning_rate": 1.6081509885467318e-05,
      "loss": 0.5201,
      "step": 19077
    },
    {
      "epoch": 0.5860596565600713,
      "grad_norm": 0.37982505559921265,
      "learning_rate": 1.6081126242485897e-05,
      "loss": 0.5012,
      "step": 19078
    },
    {
      "epoch": 0.5860903756950204,
      "grad_norm": 0.4268046021461487,
      "learning_rate": 1.608074258530158e-05,
      "loss": 0.6026,
      "step": 19079
    },
    {
      "epoch": 0.5861210948299695,
      "grad_norm": 0.3464762270450592,
      "learning_rate": 1.6080358913915266e-05,
      "loss": 0.6172,
      "step": 19080
    },
    {
      "epoch": 0.5861518139649188,
      "grad_norm": 0.39469924569129944,
      "learning_rate": 1.6079975228327848e-05,
      "loss": 0.6251,
      "step": 19081
    },
    {
      "epoch": 0.5861825330998679,
      "grad_norm": 0.3567555546760559,
      "learning_rate": 1.607959152854022e-05,
      "loss": 0.5507,
      "step": 19082
    },
    {
      "epoch": 0.586213252234817,
      "grad_norm": 0.3669044077396393,
      "learning_rate": 1.607920781455329e-05,
      "loss": 0.5761,
      "step": 19083
    },
    {
      "epoch": 0.5862439713697662,
      "grad_norm": 0.4852367639541626,
      "learning_rate": 1.607882408636794e-05,
      "loss": 0.6,
      "step": 19084
    },
    {
      "epoch": 0.5862746905047154,
      "grad_norm": 0.4034809470176697,
      "learning_rate": 1.607844034398507e-05,
      "loss": 0.5873,
      "step": 19085
    },
    {
      "epoch": 0.5863054096396646,
      "grad_norm": 0.34965547919273376,
      "learning_rate": 1.6078056587405583e-05,
      "loss": 0.6418,
      "step": 19086
    },
    {
      "epoch": 0.5863361287746137,
      "grad_norm": 0.38951101899147034,
      "learning_rate": 1.6077672816630367e-05,
      "loss": 0.6104,
      "step": 19087
    },
    {
      "epoch": 0.5863668479095628,
      "grad_norm": 0.3380931317806244,
      "learning_rate": 1.6077289031660322e-05,
      "loss": 0.5491,
      "step": 19088
    },
    {
      "epoch": 0.5863975670445121,
      "grad_norm": 0.36132800579071045,
      "learning_rate": 1.6076905232496343e-05,
      "loss": 0.5849,
      "step": 19089
    },
    {
      "epoch": 0.5864282861794612,
      "grad_norm": 0.34591689705848694,
      "learning_rate": 1.6076521419139328e-05,
      "loss": 0.6311,
      "step": 19090
    },
    {
      "epoch": 0.5864590053144103,
      "grad_norm": 0.34233900904655457,
      "learning_rate": 1.6076137591590173e-05,
      "loss": 0.5039,
      "step": 19091
    },
    {
      "epoch": 0.5864897244493595,
      "grad_norm": 0.3701699376106262,
      "learning_rate": 1.6075753749849775e-05,
      "loss": 0.5426,
      "step": 19092
    },
    {
      "epoch": 0.5865204435843087,
      "grad_norm": 0.3397296369075775,
      "learning_rate": 1.6075369893919027e-05,
      "loss": 0.5301,
      "step": 19093
    },
    {
      "epoch": 0.5865511627192578,
      "grad_norm": 0.4406123757362366,
      "learning_rate": 1.6074986023798833e-05,
      "loss": 0.608,
      "step": 19094
    },
    {
      "epoch": 0.586581881854207,
      "grad_norm": 0.3586703836917877,
      "learning_rate": 1.6074602139490083e-05,
      "loss": 0.5941,
      "step": 19095
    },
    {
      "epoch": 0.5866126009891561,
      "grad_norm": 0.36415624618530273,
      "learning_rate": 1.6074218240993676e-05,
      "loss": 0.6751,
      "step": 19096
    },
    {
      "epoch": 0.5866433201241052,
      "grad_norm": 0.5277320742607117,
      "learning_rate": 1.6073834328310507e-05,
      "loss": 0.5993,
      "step": 19097
    },
    {
      "epoch": 0.5866740392590545,
      "grad_norm": 0.3294694125652313,
      "learning_rate": 1.607345040144147e-05,
      "loss": 0.6167,
      "step": 19098
    },
    {
      "epoch": 0.5867047583940036,
      "grad_norm": 0.365997850894928,
      "learning_rate": 1.6073066460387473e-05,
      "loss": 0.5665,
      "step": 19099
    },
    {
      "epoch": 0.5867354775289528,
      "grad_norm": 0.3466934263706207,
      "learning_rate": 1.6072682505149403e-05,
      "loss": 0.6779,
      "step": 19100
    },
    {
      "epoch": 0.586766196663902,
      "grad_norm": 0.3510375916957855,
      "learning_rate": 1.6072298535728156e-05,
      "loss": 0.5749,
      "step": 19101
    },
    {
      "epoch": 0.5867969157988511,
      "grad_norm": 0.3861817717552185,
      "learning_rate": 1.6071914552124633e-05,
      "loss": 0.6305,
      "step": 19102
    },
    {
      "epoch": 0.5868276349338003,
      "grad_norm": 0.9334580302238464,
      "learning_rate": 1.607153055433973e-05,
      "loss": 0.6308,
      "step": 19103
    },
    {
      "epoch": 0.5868583540687494,
      "grad_norm": 0.3455761969089508,
      "learning_rate": 1.6071146542374344e-05,
      "loss": 0.5362,
      "step": 19104
    },
    {
      "epoch": 0.5868890732036985,
      "grad_norm": 0.44324833154678345,
      "learning_rate": 1.607076251622937e-05,
      "loss": 0.4975,
      "step": 19105
    },
    {
      "epoch": 0.5869197923386478,
      "grad_norm": 0.3366246521472931,
      "learning_rate": 1.6070378475905706e-05,
      "loss": 0.4941,
      "step": 19106
    },
    {
      "epoch": 0.5869505114735969,
      "grad_norm": 0.34425127506256104,
      "learning_rate": 1.606999442140425e-05,
      "loss": 0.5938,
      "step": 19107
    },
    {
      "epoch": 0.586981230608546,
      "grad_norm": 0.34955912828445435,
      "learning_rate": 1.60696103527259e-05,
      "loss": 0.5533,
      "step": 19108
    },
    {
      "epoch": 0.5870119497434952,
      "grad_norm": 0.38867515325546265,
      "learning_rate": 1.6069226269871547e-05,
      "loss": 0.6486,
      "step": 19109
    },
    {
      "epoch": 0.5870426688784444,
      "grad_norm": 0.34522056579589844,
      "learning_rate": 1.6068842172842093e-05,
      "loss": 0.6087,
      "step": 19110
    },
    {
      "epoch": 0.5870733880133936,
      "grad_norm": 0.3990427553653717,
      "learning_rate": 1.6068458061638437e-05,
      "loss": 0.6691,
      "step": 19111
    },
    {
      "epoch": 0.5871041071483427,
      "grad_norm": 0.3730733096599579,
      "learning_rate": 1.606807393626147e-05,
      "loss": 0.6424,
      "step": 19112
    },
    {
      "epoch": 0.5871348262832918,
      "grad_norm": 0.444256454706192,
      "learning_rate": 1.6067689796712094e-05,
      "loss": 0.6047,
      "step": 19113
    },
    {
      "epoch": 0.5871655454182411,
      "grad_norm": 0.33453741669654846,
      "learning_rate": 1.6067305642991206e-05,
      "loss": 0.518,
      "step": 19114
    },
    {
      "epoch": 0.5871962645531902,
      "grad_norm": 0.34972748160362244,
      "learning_rate": 1.60669214750997e-05,
      "loss": 0.5132,
      "step": 19115
    },
    {
      "epoch": 0.5872269836881393,
      "grad_norm": 0.3265587091445923,
      "learning_rate": 1.6066537293038476e-05,
      "loss": 0.653,
      "step": 19116
    },
    {
      "epoch": 0.5872577028230885,
      "grad_norm": 0.347818523645401,
      "learning_rate": 1.606615309680843e-05,
      "loss": 0.5971,
      "step": 19117
    },
    {
      "epoch": 0.5872884219580377,
      "grad_norm": 0.36993634700775146,
      "learning_rate": 1.6065768886410462e-05,
      "loss": 0.6109,
      "step": 19118
    },
    {
      "epoch": 0.5873191410929868,
      "grad_norm": 0.31703031063079834,
      "learning_rate": 1.6065384661845463e-05,
      "loss": 0.4957,
      "step": 19119
    },
    {
      "epoch": 0.587349860227936,
      "grad_norm": 0.3522335886955261,
      "learning_rate": 1.606500042311434e-05,
      "loss": 0.5455,
      "step": 19120
    },
    {
      "epoch": 0.5873805793628851,
      "grad_norm": 0.34472930431365967,
      "learning_rate": 1.6064616170217982e-05,
      "loss": 0.5877,
      "step": 19121
    },
    {
      "epoch": 0.5874112984978344,
      "grad_norm": 0.4011450707912445,
      "learning_rate": 1.606423190315729e-05,
      "loss": 0.5875,
      "step": 19122
    },
    {
      "epoch": 0.5874420176327835,
      "grad_norm": 0.3291957378387451,
      "learning_rate": 1.606384762193316e-05,
      "loss": 0.5181,
      "step": 19123
    },
    {
      "epoch": 0.5874727367677326,
      "grad_norm": 0.43271785974502563,
      "learning_rate": 1.606346332654649e-05,
      "loss": 0.5577,
      "step": 19124
    },
    {
      "epoch": 0.5875034559026818,
      "grad_norm": 0.3600936532020569,
      "learning_rate": 1.6063079016998177e-05,
      "loss": 0.5442,
      "step": 19125
    },
    {
      "epoch": 0.587534175037631,
      "grad_norm": 0.34845757484436035,
      "learning_rate": 1.606269469328912e-05,
      "loss": 0.5265,
      "step": 19126
    },
    {
      "epoch": 0.5875648941725801,
      "grad_norm": 0.3550962507724762,
      "learning_rate": 1.6062310355420216e-05,
      "loss": 0.5707,
      "step": 19127
    },
    {
      "epoch": 0.5875956133075293,
      "grad_norm": 0.36195915937423706,
      "learning_rate": 1.6061926003392364e-05,
      "loss": 0.6134,
      "step": 19128
    },
    {
      "epoch": 0.5876263324424784,
      "grad_norm": 0.3260451853275299,
      "learning_rate": 1.606154163720646e-05,
      "loss": 0.5395,
      "step": 19129
    },
    {
      "epoch": 0.5876570515774275,
      "grad_norm": 0.3350355327129364,
      "learning_rate": 1.6061157256863406e-05,
      "loss": 0.5073,
      "step": 19130
    },
    {
      "epoch": 0.5876877707123768,
      "grad_norm": 0.3599681258201599,
      "learning_rate": 1.6060772862364088e-05,
      "loss": 0.5746,
      "step": 19131
    },
    {
      "epoch": 0.5877184898473259,
      "grad_norm": 0.4266717731952667,
      "learning_rate": 1.6060388453709417e-05,
      "loss": 0.6299,
      "step": 19132
    },
    {
      "epoch": 0.587749208982275,
      "grad_norm": 0.3448694944381714,
      "learning_rate": 1.6060004030900283e-05,
      "loss": 0.5343,
      "step": 19133
    },
    {
      "epoch": 0.5877799281172242,
      "grad_norm": 0.44789358973503113,
      "learning_rate": 1.605961959393759e-05,
      "loss": 0.5668,
      "step": 19134
    },
    {
      "epoch": 0.5878106472521734,
      "grad_norm": 0.3688737750053406,
      "learning_rate": 1.6059235142822233e-05,
      "loss": 0.5276,
      "step": 19135
    },
    {
      "epoch": 0.5878413663871226,
      "grad_norm": 0.40513965487480164,
      "learning_rate": 1.6058850677555105e-05,
      "loss": 0.6592,
      "step": 19136
    },
    {
      "epoch": 0.5878720855220717,
      "grad_norm": 0.4523657262325287,
      "learning_rate": 1.605846619813711e-05,
      "loss": 0.6034,
      "step": 19137
    },
    {
      "epoch": 0.5879028046570208,
      "grad_norm": 0.36143743991851807,
      "learning_rate": 1.6058081704569144e-05,
      "loss": 0.5846,
      "step": 19138
    },
    {
      "epoch": 0.5879335237919701,
      "grad_norm": 0.3621264398097992,
      "learning_rate": 1.6057697196852106e-05,
      "loss": 0.6215,
      "step": 19139
    },
    {
      "epoch": 0.5879642429269192,
      "grad_norm": 0.33505383133888245,
      "learning_rate": 1.605731267498689e-05,
      "loss": 0.5923,
      "step": 19140
    },
    {
      "epoch": 0.5879949620618683,
      "grad_norm": 0.5563961267471313,
      "learning_rate": 1.60569281389744e-05,
      "loss": 0.4953,
      "step": 19141
    },
    {
      "epoch": 0.5880256811968175,
      "grad_norm": 0.3295603394508362,
      "learning_rate": 1.6056543588815528e-05,
      "loss": 0.521,
      "step": 19142
    },
    {
      "epoch": 0.5880564003317666,
      "grad_norm": 0.33285078406333923,
      "learning_rate": 1.6056159024511177e-05,
      "loss": 0.5866,
      "step": 19143
    },
    {
      "epoch": 0.5880871194667158,
      "grad_norm": 0.36311811208724976,
      "learning_rate": 1.6055774446062246e-05,
      "loss": 0.5551,
      "step": 19144
    },
    {
      "epoch": 0.588117838601665,
      "grad_norm": 0.37847599387168884,
      "learning_rate": 1.605538985346963e-05,
      "loss": 0.558,
      "step": 19145
    },
    {
      "epoch": 0.5881485577366141,
      "grad_norm": 0.42490532994270325,
      "learning_rate": 1.6055005246734228e-05,
      "loss": 0.5767,
      "step": 19146
    },
    {
      "epoch": 0.5881792768715634,
      "grad_norm": 0.32640963792800903,
      "learning_rate": 1.6054620625856936e-05,
      "loss": 0.5352,
      "step": 19147
    },
    {
      "epoch": 0.5882099960065125,
      "grad_norm": 0.3491404056549072,
      "learning_rate": 1.605423599083866e-05,
      "loss": 0.6439,
      "step": 19148
    },
    {
      "epoch": 0.5882407151414616,
      "grad_norm": 0.4169277250766754,
      "learning_rate": 1.6053851341680285e-05,
      "loss": 0.5455,
      "step": 19149
    },
    {
      "epoch": 0.5882714342764108,
      "grad_norm": 0.344644159078598,
      "learning_rate": 1.6053466678382723e-05,
      "loss": 0.5895,
      "step": 19150
    },
    {
      "epoch": 0.5883021534113599,
      "grad_norm": 0.3487234115600586,
      "learning_rate": 1.6053082000946866e-05,
      "loss": 0.5616,
      "step": 19151
    },
    {
      "epoch": 0.5883328725463091,
      "grad_norm": 0.3601098656654358,
      "learning_rate": 1.6052697309373612e-05,
      "loss": 0.5963,
      "step": 19152
    },
    {
      "epoch": 0.5883635916812583,
      "grad_norm": 0.38001981377601624,
      "learning_rate": 1.6052312603663863e-05,
      "loss": 0.5324,
      "step": 19153
    },
    {
      "epoch": 0.5883943108162074,
      "grad_norm": 0.4760858416557312,
      "learning_rate": 1.6051927883818513e-05,
      "loss": 0.6038,
      "step": 19154
    },
    {
      "epoch": 0.5884250299511565,
      "grad_norm": 0.3445979058742523,
      "learning_rate": 1.6051543149838463e-05,
      "loss": 0.575,
      "step": 19155
    },
    {
      "epoch": 0.5884557490861058,
      "grad_norm": 4.230015754699707,
      "learning_rate": 1.605115840172461e-05,
      "loss": 0.5299,
      "step": 19156
    },
    {
      "epoch": 0.5884864682210549,
      "grad_norm": 0.38857021927833557,
      "learning_rate": 1.605077363947786e-05,
      "loss": 0.6449,
      "step": 19157
    },
    {
      "epoch": 0.588517187356004,
      "grad_norm": 0.4077652096748352,
      "learning_rate": 1.60503888630991e-05,
      "loss": 0.6077,
      "step": 19158
    },
    {
      "epoch": 0.5885479064909532,
      "grad_norm": 0.3129008710384369,
      "learning_rate": 1.6050004072589234e-05,
      "loss": 0.6503,
      "step": 19159
    },
    {
      "epoch": 0.5885786256259024,
      "grad_norm": 0.3571508228778839,
      "learning_rate": 1.6049619267949164e-05,
      "loss": 0.5803,
      "step": 19160
    },
    {
      "epoch": 0.5886093447608516,
      "grad_norm": 0.395611435174942,
      "learning_rate": 1.6049234449179785e-05,
      "loss": 0.5839,
      "step": 19161
    },
    {
      "epoch": 0.5886400638958007,
      "grad_norm": 0.34334996342658997,
      "learning_rate": 1.6048849616281998e-05,
      "loss": 0.6517,
      "step": 19162
    },
    {
      "epoch": 0.5886707830307498,
      "grad_norm": 0.3403235673904419,
      "learning_rate": 1.6048464769256697e-05,
      "loss": 0.5242,
      "step": 19163
    },
    {
      "epoch": 0.588701502165699,
      "grad_norm": 0.30748116970062256,
      "learning_rate": 1.6048079908104784e-05,
      "loss": 0.4414,
      "step": 19164
    },
    {
      "epoch": 0.5887322213006482,
      "grad_norm": 0.42470091581344604,
      "learning_rate": 1.6047695032827157e-05,
      "loss": 0.5092,
      "step": 19165
    },
    {
      "epoch": 0.5887629404355973,
      "grad_norm": 0.4006432592868805,
      "learning_rate": 1.604731014342472e-05,
      "loss": 0.5312,
      "step": 19166
    },
    {
      "epoch": 0.5887936595705465,
      "grad_norm": 0.38505518436431885,
      "learning_rate": 1.6046925239898364e-05,
      "loss": 0.6367,
      "step": 19167
    },
    {
      "epoch": 0.5888243787054956,
      "grad_norm": 0.3136414885520935,
      "learning_rate": 1.6046540322248995e-05,
      "loss": 0.5282,
      "step": 19168
    },
    {
      "epoch": 0.5888550978404448,
      "grad_norm": 0.3501688241958618,
      "learning_rate": 1.604615539047751e-05,
      "loss": 0.5206,
      "step": 19169
    },
    {
      "epoch": 0.588885816975394,
      "grad_norm": 0.36391979455947876,
      "learning_rate": 1.60457704445848e-05,
      "loss": 0.594,
      "step": 19170
    },
    {
      "epoch": 0.5889165361103431,
      "grad_norm": 0.3559848964214325,
      "learning_rate": 1.6045385484571777e-05,
      "loss": 0.5658,
      "step": 19171
    },
    {
      "epoch": 0.5889472552452923,
      "grad_norm": 0.3706744313240051,
      "learning_rate": 1.6045000510439333e-05,
      "loss": 0.6279,
      "step": 19172
    },
    {
      "epoch": 0.5889779743802415,
      "grad_norm": 0.4004368185997009,
      "learning_rate": 1.6044615522188368e-05,
      "loss": 0.5581,
      "step": 19173
    },
    {
      "epoch": 0.5890086935151906,
      "grad_norm": 0.3403806686401367,
      "learning_rate": 1.604423051981978e-05,
      "loss": 0.5935,
      "step": 19174
    },
    {
      "epoch": 0.5890394126501398,
      "grad_norm": 0.3670117259025574,
      "learning_rate": 1.604384550333447e-05,
      "loss": 0.538,
      "step": 19175
    },
    {
      "epoch": 0.5890701317850889,
      "grad_norm": 0.33607217669487,
      "learning_rate": 1.604346047273334e-05,
      "loss": 0.5849,
      "step": 19176
    },
    {
      "epoch": 0.589100850920038,
      "grad_norm": 0.33237749338150024,
      "learning_rate": 1.6043075428017282e-05,
      "loss": 0.5591,
      "step": 19177
    },
    {
      "epoch": 0.5891315700549873,
      "grad_norm": 0.3990505635738373,
      "learning_rate": 1.60426903691872e-05,
      "loss": 0.6165,
      "step": 19178
    },
    {
      "epoch": 0.5891622891899364,
      "grad_norm": 0.4320217967033386,
      "learning_rate": 1.604230529624399e-05,
      "loss": 0.5332,
      "step": 19179
    },
    {
      "epoch": 0.5891930083248855,
      "grad_norm": 0.3693620562553406,
      "learning_rate": 1.604192020918856e-05,
      "loss": 0.6275,
      "step": 19180
    },
    {
      "epoch": 0.5892237274598348,
      "grad_norm": 0.3757578134536743,
      "learning_rate": 1.6041535108021798e-05,
      "loss": 0.5562,
      "step": 19181
    },
    {
      "epoch": 0.5892544465947839,
      "grad_norm": 0.3804378807544708,
      "learning_rate": 1.6041149992744612e-05,
      "loss": 0.5933,
      "step": 19182
    },
    {
      "epoch": 0.589285165729733,
      "grad_norm": 0.4815181791782379,
      "learning_rate": 1.6040764863357897e-05,
      "loss": 0.5288,
      "step": 19183
    },
    {
      "epoch": 0.5893158848646822,
      "grad_norm": 0.340792179107666,
      "learning_rate": 1.604037971986255e-05,
      "loss": 0.6009,
      "step": 19184
    },
    {
      "epoch": 0.5893466039996313,
      "grad_norm": 0.3687705099582672,
      "learning_rate": 1.6039994562259484e-05,
      "loss": 0.5459,
      "step": 19185
    },
    {
      "epoch": 0.5893773231345806,
      "grad_norm": 0.38099876046180725,
      "learning_rate": 1.603960939054958e-05,
      "loss": 0.5873,
      "step": 19186
    },
    {
      "epoch": 0.5894080422695297,
      "grad_norm": 0.3369413912296295,
      "learning_rate": 1.603922420473375e-05,
      "loss": 0.6065,
      "step": 19187
    },
    {
      "epoch": 0.5894387614044788,
      "grad_norm": 0.37255752086639404,
      "learning_rate": 1.603883900481289e-05,
      "loss": 0.622,
      "step": 19188
    },
    {
      "epoch": 0.589469480539428,
      "grad_norm": 0.3669999837875366,
      "learning_rate": 1.60384537907879e-05,
      "loss": 0.6137,
      "step": 19189
    },
    {
      "epoch": 0.5895001996743772,
      "grad_norm": 0.3657234311103821,
      "learning_rate": 1.6038068562659678e-05,
      "loss": 0.4754,
      "step": 19190
    },
    {
      "epoch": 0.5895309188093263,
      "grad_norm": 0.3680228590965271,
      "learning_rate": 1.6037683320429126e-05,
      "loss": 0.5434,
      "step": 19191
    },
    {
      "epoch": 0.5895616379442755,
      "grad_norm": 0.3365907371044159,
      "learning_rate": 1.6037298064097146e-05,
      "loss": 0.5598,
      "step": 19192
    },
    {
      "epoch": 0.5895923570792246,
      "grad_norm": 0.3276981711387634,
      "learning_rate": 1.603691279366463e-05,
      "loss": 0.6287,
      "step": 19193
    },
    {
      "epoch": 0.5896230762141738,
      "grad_norm": 0.4141208827495575,
      "learning_rate": 1.6036527509132486e-05,
      "loss": 0.5106,
      "step": 19194
    },
    {
      "epoch": 0.589653795349123,
      "grad_norm": 0.380124568939209,
      "learning_rate": 1.6036142210501608e-05,
      "loss": 0.5283,
      "step": 19195
    },
    {
      "epoch": 0.5896845144840721,
      "grad_norm": 0.3881632387638092,
      "learning_rate": 1.6035756897772897e-05,
      "loss": 0.5712,
      "step": 19196
    },
    {
      "epoch": 0.5897152336190213,
      "grad_norm": 0.4712063670158386,
      "learning_rate": 1.6035371570947257e-05,
      "loss": 0.5036,
      "step": 19197
    },
    {
      "epoch": 0.5897459527539705,
      "grad_norm": 0.34177762269973755,
      "learning_rate": 1.6034986230025586e-05,
      "loss": 0.5716,
      "step": 19198
    },
    {
      "epoch": 0.5897766718889196,
      "grad_norm": 0.41399797797203064,
      "learning_rate": 1.6034600875008783e-05,
      "loss": 0.6233,
      "step": 19199
    },
    {
      "epoch": 0.5898073910238688,
      "grad_norm": 0.35270261764526367,
      "learning_rate": 1.6034215505897744e-05,
      "loss": 0.486,
      "step": 19200
    },
    {
      "epoch": 0.5898381101588179,
      "grad_norm": 0.34697434306144714,
      "learning_rate": 1.6033830122693377e-05,
      "loss": 0.5736,
      "step": 19201
    },
    {
      "epoch": 0.589868829293767,
      "grad_norm": 0.32443496584892273,
      "learning_rate": 1.6033444725396575e-05,
      "loss": 0.5116,
      "step": 19202
    },
    {
      "epoch": 0.5898995484287163,
      "grad_norm": 0.4106752574443817,
      "learning_rate": 1.6033059314008244e-05,
      "loss": 0.59,
      "step": 19203
    },
    {
      "epoch": 0.5899302675636654,
      "grad_norm": 0.339203804731369,
      "learning_rate": 1.6032673888529284e-05,
      "loss": 0.526,
      "step": 19204
    },
    {
      "epoch": 0.5899609866986145,
      "grad_norm": 0.4364751875400543,
      "learning_rate": 1.603228844896059e-05,
      "loss": 0.5797,
      "step": 19205
    },
    {
      "epoch": 0.5899917058335638,
      "grad_norm": 0.3689621686935425,
      "learning_rate": 1.6031902995303066e-05,
      "loss": 0.5641,
      "step": 19206
    },
    {
      "epoch": 0.5900224249685129,
      "grad_norm": 0.3282196819782257,
      "learning_rate": 1.603151752755761e-05,
      "loss": 0.59,
      "step": 19207
    },
    {
      "epoch": 0.5900531441034621,
      "grad_norm": 0.3863656222820282,
      "learning_rate": 1.6031132045725123e-05,
      "loss": 0.5697,
      "step": 19208
    },
    {
      "epoch": 0.5900838632384112,
      "grad_norm": 0.39933210611343384,
      "learning_rate": 1.603074654980651e-05,
      "loss": 0.6219,
      "step": 19209
    },
    {
      "epoch": 0.5901145823733603,
      "grad_norm": 0.7663844227790833,
      "learning_rate": 1.6030361039802666e-05,
      "loss": 0.5485,
      "step": 19210
    },
    {
      "epoch": 0.5901453015083096,
      "grad_norm": 0.46287813782691956,
      "learning_rate": 1.6029975515714488e-05,
      "loss": 0.5974,
      "step": 19211
    },
    {
      "epoch": 0.5901760206432587,
      "grad_norm": 0.35972902178764343,
      "learning_rate": 1.6029589977542886e-05,
      "loss": 0.5378,
      "step": 19212
    },
    {
      "epoch": 0.5902067397782078,
      "grad_norm": 0.3376941680908203,
      "learning_rate": 1.6029204425288754e-05,
      "loss": 0.5305,
      "step": 19213
    },
    {
      "epoch": 0.590237458913157,
      "grad_norm": 0.3320756256580353,
      "learning_rate": 1.6028818858952992e-05,
      "loss": 0.5044,
      "step": 19214
    },
    {
      "epoch": 0.5902681780481062,
      "grad_norm": 0.3839505910873413,
      "learning_rate": 1.6028433278536506e-05,
      "loss": 0.5888,
      "step": 19215
    },
    {
      "epoch": 0.5902988971830553,
      "grad_norm": 0.4184506833553314,
      "learning_rate": 1.602804768404019e-05,
      "loss": 0.512,
      "step": 19216
    },
    {
      "epoch": 0.5903296163180045,
      "grad_norm": 0.3642100691795349,
      "learning_rate": 1.6027662075464952e-05,
      "loss": 0.5315,
      "step": 19217
    },
    {
      "epoch": 0.5903603354529536,
      "grad_norm": 0.34609290957450867,
      "learning_rate": 1.6027276452811683e-05,
      "loss": 0.5544,
      "step": 19218
    },
    {
      "epoch": 0.5903910545879028,
      "grad_norm": 0.3579016327857971,
      "learning_rate": 1.602689081608129e-05,
      "loss": 0.5581,
      "step": 19219
    },
    {
      "epoch": 0.590421773722852,
      "grad_norm": 0.3420396149158478,
      "learning_rate": 1.602650516527467e-05,
      "loss": 0.6092,
      "step": 19220
    },
    {
      "epoch": 0.5904524928578011,
      "grad_norm": 0.3440295457839966,
      "learning_rate": 1.602611950039273e-05,
      "loss": 0.561,
      "step": 19221
    },
    {
      "epoch": 0.5904832119927503,
      "grad_norm": 0.3693169951438904,
      "learning_rate": 1.6025733821436372e-05,
      "loss": 0.5444,
      "step": 19222
    },
    {
      "epoch": 0.5905139311276995,
      "grad_norm": 0.44674068689346313,
      "learning_rate": 1.6025348128406487e-05,
      "loss": 0.5549,
      "step": 19223
    },
    {
      "epoch": 0.5905446502626486,
      "grad_norm": 0.30887359380722046,
      "learning_rate": 1.602496242130398e-05,
      "loss": 0.4905,
      "step": 19224
    },
    {
      "epoch": 0.5905753693975978,
      "grad_norm": 0.394621878862381,
      "learning_rate": 1.6024576700129753e-05,
      "loss": 0.6176,
      "step": 19225
    },
    {
      "epoch": 0.5906060885325469,
      "grad_norm": 0.3359978199005127,
      "learning_rate": 1.6024190964884704e-05,
      "loss": 0.5469,
      "step": 19226
    },
    {
      "epoch": 0.590636807667496,
      "grad_norm": 0.39687079191207886,
      "learning_rate": 1.602380521556974e-05,
      "loss": 0.6574,
      "step": 19227
    },
    {
      "epoch": 0.5906675268024453,
      "grad_norm": 0.35068628191947937,
      "learning_rate": 1.6023419452185756e-05,
      "loss": 0.5152,
      "step": 19228
    },
    {
      "epoch": 0.5906982459373944,
      "grad_norm": 0.31275051832199097,
      "learning_rate": 1.6023033674733658e-05,
      "loss": 0.4605,
      "step": 19229
    },
    {
      "epoch": 0.5907289650723435,
      "grad_norm": 0.36968111991882324,
      "learning_rate": 1.6022647883214342e-05,
      "loss": 0.5561,
      "step": 19230
    },
    {
      "epoch": 0.5907596842072927,
      "grad_norm": 0.3330898582935333,
      "learning_rate": 1.602226207762871e-05,
      "loss": 0.5858,
      "step": 19231
    },
    {
      "epoch": 0.5907904033422419,
      "grad_norm": 0.3563777208328247,
      "learning_rate": 1.6021876257977668e-05,
      "loss": 0.6225,
      "step": 19232
    },
    {
      "epoch": 0.5908211224771911,
      "grad_norm": 0.37471804022789,
      "learning_rate": 1.6021490424262108e-05,
      "loss": 0.559,
      "step": 19233
    },
    {
      "epoch": 0.5908518416121402,
      "grad_norm": 0.4101230502128601,
      "learning_rate": 1.6021104576482942e-05,
      "loss": 0.6605,
      "step": 19234
    },
    {
      "epoch": 0.5908825607470893,
      "grad_norm": 0.40303608775138855,
      "learning_rate": 1.6020718714641064e-05,
      "loss": 0.5649,
      "step": 19235
    },
    {
      "epoch": 0.5909132798820386,
      "grad_norm": 0.352078378200531,
      "learning_rate": 1.6020332838737375e-05,
      "loss": 0.6291,
      "step": 19236
    },
    {
      "epoch": 0.5909439990169877,
      "grad_norm": 0.31379687786102295,
      "learning_rate": 1.601994694877278e-05,
      "loss": 0.5222,
      "step": 19237
    },
    {
      "epoch": 0.5909747181519368,
      "grad_norm": 0.3683655560016632,
      "learning_rate": 1.6019561044748176e-05,
      "loss": 0.5231,
      "step": 19238
    },
    {
      "epoch": 0.591005437286886,
      "grad_norm": 0.3601285219192505,
      "learning_rate": 1.601917512666447e-05,
      "loss": 0.5328,
      "step": 19239
    },
    {
      "epoch": 0.5910361564218352,
      "grad_norm": 0.3455623388290405,
      "learning_rate": 1.601878919452256e-05,
      "loss": 0.6189,
      "step": 19240
    },
    {
      "epoch": 0.5910668755567843,
      "grad_norm": 0.3334978222846985,
      "learning_rate": 1.6018403248323345e-05,
      "loss": 0.5036,
      "step": 19241
    },
    {
      "epoch": 0.5910975946917335,
      "grad_norm": 0.3630285859107971,
      "learning_rate": 1.6018017288067734e-05,
      "loss": 0.5839,
      "step": 19242
    },
    {
      "epoch": 0.5911283138266826,
      "grad_norm": 0.35371050238609314,
      "learning_rate": 1.6017631313756618e-05,
      "loss": 0.6134,
      "step": 19243
    },
    {
      "epoch": 0.5911590329616317,
      "grad_norm": 0.32165825366973877,
      "learning_rate": 1.6017245325390908e-05,
      "loss": 0.6425,
      "step": 19244
    },
    {
      "epoch": 0.591189752096581,
      "grad_norm": 0.3615274727344513,
      "learning_rate": 1.6016859322971498e-05,
      "loss": 0.5917,
      "step": 19245
    },
    {
      "epoch": 0.5912204712315301,
      "grad_norm": 0.3757474422454834,
      "learning_rate": 1.6016473306499293e-05,
      "loss": 0.5378,
      "step": 19246
    },
    {
      "epoch": 0.5912511903664793,
      "grad_norm": 0.4002845883369446,
      "learning_rate": 1.6016087275975194e-05,
      "loss": 0.5872,
      "step": 19247
    },
    {
      "epoch": 0.5912819095014284,
      "grad_norm": 0.6013129353523254,
      "learning_rate": 1.6015701231400103e-05,
      "loss": 0.5111,
      "step": 19248
    },
    {
      "epoch": 0.5913126286363776,
      "grad_norm": 0.36723750829696655,
      "learning_rate": 1.6015315172774924e-05,
      "loss": 0.5274,
      "step": 19249
    },
    {
      "epoch": 0.5913433477713268,
      "grad_norm": 0.3332446217536926,
      "learning_rate": 1.6014929100100555e-05,
      "loss": 0.5405,
      "step": 19250
    },
    {
      "epoch": 0.5913740669062759,
      "grad_norm": 0.3154708445072174,
      "learning_rate": 1.60145430133779e-05,
      "loss": 0.5182,
      "step": 19251
    },
    {
      "epoch": 0.591404786041225,
      "grad_norm": 0.40841516852378845,
      "learning_rate": 1.601415691260786e-05,
      "loss": 0.586,
      "step": 19252
    },
    {
      "epoch": 0.5914355051761743,
      "grad_norm": 0.3574203848838806,
      "learning_rate": 1.6013770797791334e-05,
      "loss": 0.5557,
      "step": 19253
    },
    {
      "epoch": 0.5914662243111234,
      "grad_norm": 0.38576656579971313,
      "learning_rate": 1.6013384668929228e-05,
      "loss": 0.5219,
      "step": 19254
    },
    {
      "epoch": 0.5914969434460725,
      "grad_norm": 0.3841092586517334,
      "learning_rate": 1.601299852602244e-05,
      "loss": 0.6341,
      "step": 19255
    },
    {
      "epoch": 0.5915276625810217,
      "grad_norm": 0.38109660148620605,
      "learning_rate": 1.601261236907188e-05,
      "loss": 0.5856,
      "step": 19256
    },
    {
      "epoch": 0.5915583817159709,
      "grad_norm": 0.3726730942726135,
      "learning_rate": 1.6012226198078438e-05,
      "loss": 0.5626,
      "step": 19257
    },
    {
      "epoch": 0.5915891008509201,
      "grad_norm": 0.3247823119163513,
      "learning_rate": 1.6011840013043024e-05,
      "loss": 0.5085,
      "step": 19258
    },
    {
      "epoch": 0.5916198199858692,
      "grad_norm": 0.3163151741027832,
      "learning_rate": 1.6011453813966538e-05,
      "loss": 0.5599,
      "step": 19259
    },
    {
      "epoch": 0.5916505391208183,
      "grad_norm": 0.3472658395767212,
      "learning_rate": 1.6011067600849878e-05,
      "loss": 0.6513,
      "step": 19260
    },
    {
      "epoch": 0.5916812582557676,
      "grad_norm": 0.35683494806289673,
      "learning_rate": 1.6010681373693955e-05,
      "loss": 0.5643,
      "step": 19261
    },
    {
      "epoch": 0.5917119773907167,
      "grad_norm": 0.3440124988555908,
      "learning_rate": 1.601029513249966e-05,
      "loss": 0.5916,
      "step": 19262
    },
    {
      "epoch": 0.5917426965256658,
      "grad_norm": 0.48546740412712097,
      "learning_rate": 1.600990887726791e-05,
      "loss": 0.4889,
      "step": 19263
    },
    {
      "epoch": 0.591773415660615,
      "grad_norm": 0.5301685333251953,
      "learning_rate": 1.600952260799959e-05,
      "loss": 0.602,
      "step": 19264
    },
    {
      "epoch": 0.5918041347955642,
      "grad_norm": 0.35059770941734314,
      "learning_rate": 1.6009136324695614e-05,
      "loss": 0.5502,
      "step": 19265
    },
    {
      "epoch": 0.5918348539305133,
      "grad_norm": 0.39798352122306824,
      "learning_rate": 1.6008750027356882e-05,
      "loss": 0.5413,
      "step": 19266
    },
    {
      "epoch": 0.5918655730654625,
      "grad_norm": 0.3356948792934418,
      "learning_rate": 1.600836371598429e-05,
      "loss": 0.5554,
      "step": 19267
    },
    {
      "epoch": 0.5918962922004116,
      "grad_norm": 0.3579341471195221,
      "learning_rate": 1.6007977390578747e-05,
      "loss": 0.505,
      "step": 19268
    },
    {
      "epoch": 0.5919270113353607,
      "grad_norm": 0.39246848225593567,
      "learning_rate": 1.6007591051141153e-05,
      "loss": 0.5817,
      "step": 19269
    },
    {
      "epoch": 0.59195773047031,
      "grad_norm": 0.3265687823295593,
      "learning_rate": 1.600720469767241e-05,
      "loss": 0.643,
      "step": 19270
    },
    {
      "epoch": 0.5919884496052591,
      "grad_norm": 0.3336569666862488,
      "learning_rate": 1.6006818330173422e-05,
      "loss": 0.5828,
      "step": 19271
    },
    {
      "epoch": 0.5920191687402083,
      "grad_norm": 0.3668178915977478,
      "learning_rate": 1.600643194864509e-05,
      "loss": 0.5763,
      "step": 19272
    },
    {
      "epoch": 0.5920498878751574,
      "grad_norm": 0.33128488063812256,
      "learning_rate": 1.6006045553088315e-05,
      "loss": 0.5825,
      "step": 19273
    },
    {
      "epoch": 0.5920806070101066,
      "grad_norm": 0.34235134720802307,
      "learning_rate": 1.6005659143504003e-05,
      "loss": 0.5572,
      "step": 19274
    },
    {
      "epoch": 0.5921113261450558,
      "grad_norm": 0.37000060081481934,
      "learning_rate": 1.6005272719893055e-05,
      "loss": 0.5526,
      "step": 19275
    },
    {
      "epoch": 0.5921420452800049,
      "grad_norm": 0.3954235911369324,
      "learning_rate": 1.6004886282256374e-05,
      "loss": 0.5919,
      "step": 19276
    },
    {
      "epoch": 0.592172764414954,
      "grad_norm": 0.4259476661682129,
      "learning_rate": 1.6004499830594863e-05,
      "loss": 0.5845,
      "step": 19277
    },
    {
      "epoch": 0.5922034835499033,
      "grad_norm": 0.4111291170120239,
      "learning_rate": 1.6004113364909417e-05,
      "loss": 0.5538,
      "step": 19278
    },
    {
      "epoch": 0.5922342026848524,
      "grad_norm": 0.37739330530166626,
      "learning_rate": 1.6003726885200948e-05,
      "loss": 0.5394,
      "step": 19279
    },
    {
      "epoch": 0.5922649218198015,
      "grad_norm": 0.32633981108665466,
      "learning_rate": 1.6003340391470357e-05,
      "loss": 0.5232,
      "step": 19280
    },
    {
      "epoch": 0.5922956409547507,
      "grad_norm": 0.3619232475757599,
      "learning_rate": 1.6002953883718544e-05,
      "loss": 0.5786,
      "step": 19281
    },
    {
      "epoch": 0.5923263600896999,
      "grad_norm": 0.4002396762371063,
      "learning_rate": 1.6002567361946416e-05,
      "loss": 0.582,
      "step": 19282
    },
    {
      "epoch": 0.5923570792246491,
      "grad_norm": 0.3951985836029053,
      "learning_rate": 1.600218082615487e-05,
      "loss": 0.5596,
      "step": 19283
    },
    {
      "epoch": 0.5923877983595982,
      "grad_norm": 0.35461243987083435,
      "learning_rate": 1.600179427634481e-05,
      "loss": 0.5219,
      "step": 19284
    },
    {
      "epoch": 0.5924185174945473,
      "grad_norm": 0.40092140436172485,
      "learning_rate": 1.6001407712517144e-05,
      "loss": 0.5664,
      "step": 19285
    },
    {
      "epoch": 0.5924492366294966,
      "grad_norm": 0.3842078149318695,
      "learning_rate": 1.6001021134672766e-05,
      "loss": 0.5372,
      "step": 19286
    },
    {
      "epoch": 0.5924799557644457,
      "grad_norm": 0.45095011591911316,
      "learning_rate": 1.600063454281259e-05,
      "loss": 0.6565,
      "step": 19287
    },
    {
      "epoch": 0.5925106748993948,
      "grad_norm": 0.3898492455482483,
      "learning_rate": 1.600024793693751e-05,
      "loss": 0.6408,
      "step": 19288
    },
    {
      "epoch": 0.592541394034344,
      "grad_norm": 0.36950138211250305,
      "learning_rate": 1.599986131704843e-05,
      "loss": 0.6899,
      "step": 19289
    },
    {
      "epoch": 0.5925721131692931,
      "grad_norm": 0.38936054706573486,
      "learning_rate": 1.599947468314626e-05,
      "loss": 0.6176,
      "step": 19290
    },
    {
      "epoch": 0.5926028323042423,
      "grad_norm": 0.356499046087265,
      "learning_rate": 1.5999088035231893e-05,
      "loss": 0.5484,
      "step": 19291
    },
    {
      "epoch": 0.5926335514391915,
      "grad_norm": 0.35601773858070374,
      "learning_rate": 1.5998701373306237e-05,
      "loss": 0.6212,
      "step": 19292
    },
    {
      "epoch": 0.5926642705741406,
      "grad_norm": 0.4337078630924225,
      "learning_rate": 1.5998314697370195e-05,
      "loss": 0.5913,
      "step": 19293
    },
    {
      "epoch": 0.5926949897090897,
      "grad_norm": 0.33639830350875854,
      "learning_rate": 1.5997928007424675e-05,
      "loss": 0.5098,
      "step": 19294
    },
    {
      "epoch": 0.592725708844039,
      "grad_norm": 0.3699624240398407,
      "learning_rate": 1.5997541303470573e-05,
      "loss": 0.5107,
      "step": 19295
    },
    {
      "epoch": 0.5927564279789881,
      "grad_norm": 0.3939288854598999,
      "learning_rate": 1.599715458550879e-05,
      "loss": 0.5202,
      "step": 19296
    },
    {
      "epoch": 0.5927871471139373,
      "grad_norm": 0.34713053703308105,
      "learning_rate": 1.599676785354024e-05,
      "loss": 0.5877,
      "step": 19297
    },
    {
      "epoch": 0.5928178662488864,
      "grad_norm": 0.3266112804412842,
      "learning_rate": 1.5996381107565815e-05,
      "loss": 0.519,
      "step": 19298
    },
    {
      "epoch": 0.5928485853838356,
      "grad_norm": 0.30991309881210327,
      "learning_rate": 1.5995994347586425e-05,
      "loss": 0.5408,
      "step": 19299
    },
    {
      "epoch": 0.5928793045187848,
      "grad_norm": 0.3322933614253998,
      "learning_rate": 1.5995607573602972e-05,
      "loss": 0.5491,
      "step": 19300
    },
    {
      "epoch": 0.5929100236537339,
      "grad_norm": 0.33362510800361633,
      "learning_rate": 1.5995220785616357e-05,
      "loss": 0.5323,
      "step": 19301
    },
    {
      "epoch": 0.592940742788683,
      "grad_norm": 0.3545125424861908,
      "learning_rate": 1.5994833983627488e-05,
      "loss": 0.616,
      "step": 19302
    },
    {
      "epoch": 0.5929714619236323,
      "grad_norm": 0.3495185971260071,
      "learning_rate": 1.5994447167637262e-05,
      "loss": 0.6062,
      "step": 19303
    },
    {
      "epoch": 0.5930021810585814,
      "grad_norm": 0.35838645696640015,
      "learning_rate": 1.5994060337646588e-05,
      "loss": 0.5381,
      "step": 19304
    },
    {
      "epoch": 0.5930329001935305,
      "grad_norm": 0.37456998229026794,
      "learning_rate": 1.599367349365637e-05,
      "loss": 0.5701,
      "step": 19305
    },
    {
      "epoch": 0.5930636193284797,
      "grad_norm": 0.3691597282886505,
      "learning_rate": 1.5993286635667503e-05,
      "loss": 0.6091,
      "step": 19306
    },
    {
      "epoch": 0.5930943384634288,
      "grad_norm": 0.3367885947227478,
      "learning_rate": 1.5992899763680902e-05,
      "loss": 0.5459,
      "step": 19307
    },
    {
      "epoch": 0.5931250575983781,
      "grad_norm": 0.3539595305919647,
      "learning_rate": 1.5992512877697464e-05,
      "loss": 0.5135,
      "step": 19308
    },
    {
      "epoch": 0.5931557767333272,
      "grad_norm": 0.34208106994628906,
      "learning_rate": 1.599212597771809e-05,
      "loss": 0.5843,
      "step": 19309
    },
    {
      "epoch": 0.5931864958682763,
      "grad_norm": 0.38329675793647766,
      "learning_rate": 1.599173906374369e-05,
      "loss": 0.5373,
      "step": 19310
    },
    {
      "epoch": 0.5932172150032256,
      "grad_norm": 0.36502987146377563,
      "learning_rate": 1.5991352135775166e-05,
      "loss": 0.6107,
      "step": 19311
    },
    {
      "epoch": 0.5932479341381747,
      "grad_norm": 0.33045077323913574,
      "learning_rate": 1.5990965193813418e-05,
      "loss": 0.6691,
      "step": 19312
    },
    {
      "epoch": 0.5932786532731238,
      "grad_norm": 0.3736932873725891,
      "learning_rate": 1.5990578237859356e-05,
      "loss": 0.6008,
      "step": 19313
    },
    {
      "epoch": 0.593309372408073,
      "grad_norm": 0.3784506916999817,
      "learning_rate": 1.599019126791388e-05,
      "loss": 0.6381,
      "step": 19314
    },
    {
      "epoch": 0.5933400915430221,
      "grad_norm": 0.37355944514274597,
      "learning_rate": 1.598980428397789e-05,
      "loss": 0.5454,
      "step": 19315
    },
    {
      "epoch": 0.5933708106779713,
      "grad_norm": 0.3459323048591614,
      "learning_rate": 1.5989417286052296e-05,
      "loss": 0.4831,
      "step": 19316
    },
    {
      "epoch": 0.5934015298129205,
      "grad_norm": 0.3421623110771179,
      "learning_rate": 1.5989030274137996e-05,
      "loss": 0.5138,
      "step": 19317
    },
    {
      "epoch": 0.5934322489478696,
      "grad_norm": 0.3537704348564148,
      "learning_rate": 1.5988643248235903e-05,
      "loss": 0.564,
      "step": 19318
    },
    {
      "epoch": 0.5934629680828188,
      "grad_norm": 0.39815521240234375,
      "learning_rate": 1.5988256208346914e-05,
      "loss": 0.6109,
      "step": 19319
    },
    {
      "epoch": 0.593493687217768,
      "grad_norm": 0.328481525182724,
      "learning_rate": 1.5987869154471933e-05,
      "loss": 0.509,
      "step": 19320
    },
    {
      "epoch": 0.5935244063527171,
      "grad_norm": 0.396294504404068,
      "learning_rate": 1.5987482086611866e-05,
      "loss": 0.5892,
      "step": 19321
    },
    {
      "epoch": 0.5935551254876663,
      "grad_norm": 0.33556777238845825,
      "learning_rate": 1.5987095004767618e-05,
      "loss": 0.5625,
      "step": 19322
    },
    {
      "epoch": 0.5935858446226154,
      "grad_norm": 0.3741730749607086,
      "learning_rate": 1.5986707908940088e-05,
      "loss": 0.5097,
      "step": 19323
    },
    {
      "epoch": 0.5936165637575646,
      "grad_norm": 0.33968105912208557,
      "learning_rate": 1.598632079913019e-05,
      "loss": 0.5381,
      "step": 19324
    },
    {
      "epoch": 0.5936472828925138,
      "grad_norm": 0.46215569972991943,
      "learning_rate": 1.5985933675338812e-05,
      "loss": 0.7077,
      "step": 19325
    },
    {
      "epoch": 0.5936780020274629,
      "grad_norm": 0.3681497275829315,
      "learning_rate": 1.5985546537566875e-05,
      "loss": 0.5873,
      "step": 19326
    },
    {
      "epoch": 0.593708721162412,
      "grad_norm": 0.3190513551235199,
      "learning_rate": 1.5985159385815276e-05,
      "loss": 0.5637,
      "step": 19327
    },
    {
      "epoch": 0.5937394402973613,
      "grad_norm": 0.4325663447380066,
      "learning_rate": 1.5984772220084916e-05,
      "loss": 0.5809,
      "step": 19328
    },
    {
      "epoch": 0.5937701594323104,
      "grad_norm": 0.3291528820991516,
      "learning_rate": 1.5984385040376703e-05,
      "loss": 0.5873,
      "step": 19329
    },
    {
      "epoch": 0.5938008785672595,
      "grad_norm": 0.3456628620624542,
      "learning_rate": 1.5983997846691542e-05,
      "loss": 0.5304,
      "step": 19330
    },
    {
      "epoch": 0.5938315977022087,
      "grad_norm": 0.35486331582069397,
      "learning_rate": 1.5983610639030337e-05,
      "loss": 0.5042,
      "step": 19331
    },
    {
      "epoch": 0.5938623168371578,
      "grad_norm": 0.4078337848186493,
      "learning_rate": 1.598322341739399e-05,
      "loss": 0.5841,
      "step": 19332
    },
    {
      "epoch": 0.5938930359721071,
      "grad_norm": 0.3735998570919037,
      "learning_rate": 1.5982836181783405e-05,
      "loss": 0.6353,
      "step": 19333
    },
    {
      "epoch": 0.5939237551070562,
      "grad_norm": 0.41082003712654114,
      "learning_rate": 1.5982448932199494e-05,
      "loss": 0.5753,
      "step": 19334
    },
    {
      "epoch": 0.5939544742420053,
      "grad_norm": 0.3484957218170166,
      "learning_rate": 1.598206166864315e-05,
      "loss": 0.5398,
      "step": 19335
    },
    {
      "epoch": 0.5939851933769545,
      "grad_norm": 0.36360836029052734,
      "learning_rate": 1.5981674391115287e-05,
      "loss": 0.5504,
      "step": 19336
    },
    {
      "epoch": 0.5940159125119037,
      "grad_norm": 0.37756314873695374,
      "learning_rate": 1.5981287099616804e-05,
      "loss": 0.5703,
      "step": 19337
    },
    {
      "epoch": 0.5940466316468528,
      "grad_norm": 0.36489471793174744,
      "learning_rate": 1.5980899794148606e-05,
      "loss": 0.5756,
      "step": 19338
    },
    {
      "epoch": 0.594077350781802,
      "grad_norm": 0.358417272567749,
      "learning_rate": 1.59805124747116e-05,
      "loss": 0.5622,
      "step": 19339
    },
    {
      "epoch": 0.5941080699167511,
      "grad_norm": 0.3928965628147125,
      "learning_rate": 1.598012514130669e-05,
      "loss": 0.6718,
      "step": 19340
    },
    {
      "epoch": 0.5941387890517003,
      "grad_norm": 0.36069533228874207,
      "learning_rate": 1.597973779393478e-05,
      "loss": 0.5794,
      "step": 19341
    },
    {
      "epoch": 0.5941695081866495,
      "grad_norm": 0.3934551775455475,
      "learning_rate": 1.5979350432596773e-05,
      "loss": 0.55,
      "step": 19342
    },
    {
      "epoch": 0.5942002273215986,
      "grad_norm": 0.3488169014453888,
      "learning_rate": 1.597896305729358e-05,
      "loss": 0.5905,
      "step": 19343
    },
    {
      "epoch": 0.5942309464565478,
      "grad_norm": 0.36372920870780945,
      "learning_rate": 1.5978575668026098e-05,
      "loss": 0.5027,
      "step": 19344
    },
    {
      "epoch": 0.594261665591497,
      "grad_norm": 0.36539432406425476,
      "learning_rate": 1.5978188264795235e-05,
      "loss": 0.5464,
      "step": 19345
    },
    {
      "epoch": 0.5942923847264461,
      "grad_norm": 0.3769056797027588,
      "learning_rate": 1.5977800847601894e-05,
      "loss": 0.6023,
      "step": 19346
    },
    {
      "epoch": 0.5943231038613953,
      "grad_norm": 0.4286012649536133,
      "learning_rate": 1.5977413416446984e-05,
      "loss": 0.5543,
      "step": 19347
    },
    {
      "epoch": 0.5943538229963444,
      "grad_norm": 0.36897438764572144,
      "learning_rate": 1.597702597133141e-05,
      "loss": 0.5369,
      "step": 19348
    },
    {
      "epoch": 0.5943845421312935,
      "grad_norm": 0.3078899085521698,
      "learning_rate": 1.597663851225607e-05,
      "loss": 0.5301,
      "step": 19349
    },
    {
      "epoch": 0.5944152612662428,
      "grad_norm": 0.32975298166275024,
      "learning_rate": 1.597625103922187e-05,
      "loss": 0.534,
      "step": 19350
    },
    {
      "epoch": 0.5944459804011919,
      "grad_norm": 0.33969250321388245,
      "learning_rate": 1.5975863552229726e-05,
      "loss": 0.5707,
      "step": 19351
    },
    {
      "epoch": 0.594476699536141,
      "grad_norm": 0.35825541615486145,
      "learning_rate": 1.597547605128053e-05,
      "loss": 0.568,
      "step": 19352
    },
    {
      "epoch": 0.5945074186710902,
      "grad_norm": 0.3468765616416931,
      "learning_rate": 1.5975088536375197e-05,
      "loss": 0.5732,
      "step": 19353
    },
    {
      "epoch": 0.5945381378060394,
      "grad_norm": 0.5485103130340576,
      "learning_rate": 1.5974701007514626e-05,
      "loss": 0.5629,
      "step": 19354
    },
    {
      "epoch": 0.5945688569409885,
      "grad_norm": 0.40568608045578003,
      "learning_rate": 1.5974313464699723e-05,
      "loss": 0.5472,
      "step": 19355
    },
    {
      "epoch": 0.5945995760759377,
      "grad_norm": 0.3163728713989258,
      "learning_rate": 1.5973925907931392e-05,
      "loss": 0.5451,
      "step": 19356
    },
    {
      "epoch": 0.5946302952108868,
      "grad_norm": 0.3666117191314697,
      "learning_rate": 1.597353833721054e-05,
      "loss": 0.6404,
      "step": 19357
    },
    {
      "epoch": 0.5946610143458361,
      "grad_norm": 0.34055402874946594,
      "learning_rate": 1.5973150752538075e-05,
      "loss": 0.5612,
      "step": 19358
    },
    {
      "epoch": 0.5946917334807852,
      "grad_norm": 0.37029626965522766,
      "learning_rate": 1.59727631539149e-05,
      "loss": 0.5165,
      "step": 19359
    },
    {
      "epoch": 0.5947224526157343,
      "grad_norm": 0.3291531205177307,
      "learning_rate": 1.5972375541341916e-05,
      "loss": 0.5522,
      "step": 19360
    },
    {
      "epoch": 0.5947531717506835,
      "grad_norm": 0.3694935739040375,
      "learning_rate": 1.5971987914820032e-05,
      "loss": 0.5795,
      "step": 19361
    },
    {
      "epoch": 0.5947838908856327,
      "grad_norm": 0.37608832120895386,
      "learning_rate": 1.5971600274350155e-05,
      "loss": 0.5602,
      "step": 19362
    },
    {
      "epoch": 0.5948146100205818,
      "grad_norm": 0.3728635907173157,
      "learning_rate": 1.597121261993319e-05,
      "loss": 0.549,
      "step": 19363
    },
    {
      "epoch": 0.594845329155531,
      "grad_norm": 0.543639063835144,
      "learning_rate": 1.5970824951570035e-05,
      "loss": 0.5512,
      "step": 19364
    },
    {
      "epoch": 0.5948760482904801,
      "grad_norm": 0.3835147023200989,
      "learning_rate": 1.5970437269261606e-05,
      "loss": 0.5459,
      "step": 19365
    },
    {
      "epoch": 0.5949067674254293,
      "grad_norm": 0.34439709782600403,
      "learning_rate": 1.5970049573008802e-05,
      "loss": 0.5376,
      "step": 19366
    },
    {
      "epoch": 0.5949374865603785,
      "grad_norm": 0.42755138874053955,
      "learning_rate": 1.5969661862812528e-05,
      "loss": 0.5314,
      "step": 19367
    },
    {
      "epoch": 0.5949682056953276,
      "grad_norm": 0.3454504609107971,
      "learning_rate": 1.5969274138673695e-05,
      "loss": 0.6028,
      "step": 19368
    },
    {
      "epoch": 0.5949989248302768,
      "grad_norm": 0.3711286783218384,
      "learning_rate": 1.5968886400593208e-05,
      "loss": 0.5205,
      "step": 19369
    },
    {
      "epoch": 0.595029643965226,
      "grad_norm": 0.3256004750728607,
      "learning_rate": 1.5968498648571965e-05,
      "loss": 0.5525,
      "step": 19370
    },
    {
      "epoch": 0.5950603631001751,
      "grad_norm": 0.35665425658226013,
      "learning_rate": 1.596811088261088e-05,
      "loss": 0.5796,
      "step": 19371
    },
    {
      "epoch": 0.5950910822351243,
      "grad_norm": 0.38774681091308594,
      "learning_rate": 1.5967723102710855e-05,
      "loss": 0.6361,
      "step": 19372
    },
    {
      "epoch": 0.5951218013700734,
      "grad_norm": 0.3702642321586609,
      "learning_rate": 1.5967335308872795e-05,
      "loss": 0.5879,
      "step": 19373
    },
    {
      "epoch": 0.5951525205050225,
      "grad_norm": 0.3696678578853607,
      "learning_rate": 1.5966947501097603e-05,
      "loss": 0.5661,
      "step": 19374
    },
    {
      "epoch": 0.5951832396399718,
      "grad_norm": 0.4024767577648163,
      "learning_rate": 1.5966559679386193e-05,
      "loss": 0.5499,
      "step": 19375
    },
    {
      "epoch": 0.5952139587749209,
      "grad_norm": 0.3787553906440735,
      "learning_rate": 1.5966171843739467e-05,
      "loss": 0.644,
      "step": 19376
    },
    {
      "epoch": 0.59524467790987,
      "grad_norm": 0.39395782351493835,
      "learning_rate": 1.5965783994158327e-05,
      "loss": 0.5573,
      "step": 19377
    },
    {
      "epoch": 0.5952753970448192,
      "grad_norm": 0.43377450108528137,
      "learning_rate": 1.5965396130643682e-05,
      "loss": 0.535,
      "step": 19378
    },
    {
      "epoch": 0.5953061161797684,
      "grad_norm": 0.31680646538734436,
      "learning_rate": 1.5965008253196436e-05,
      "loss": 0.5527,
      "step": 19379
    },
    {
      "epoch": 0.5953368353147175,
      "grad_norm": 0.5360217690467834,
      "learning_rate": 1.59646203618175e-05,
      "loss": 0.5209,
      "step": 19380
    },
    {
      "epoch": 0.5953675544496667,
      "grad_norm": 0.3608631193637848,
      "learning_rate": 1.5964232456507776e-05,
      "loss": 0.5827,
      "step": 19381
    },
    {
      "epoch": 0.5953982735846158,
      "grad_norm": 0.3350711166858673,
      "learning_rate": 1.596384453726817e-05,
      "loss": 0.5856,
      "step": 19382
    },
    {
      "epoch": 0.5954289927195651,
      "grad_norm": 0.3783625066280365,
      "learning_rate": 1.596345660409959e-05,
      "loss": 0.5098,
      "step": 19383
    },
    {
      "epoch": 0.5954597118545142,
      "grad_norm": 0.3237423598766327,
      "learning_rate": 1.5963068657002937e-05,
      "loss": 0.5727,
      "step": 19384
    },
    {
      "epoch": 0.5954904309894633,
      "grad_norm": 0.3689960539340973,
      "learning_rate": 1.5962680695979123e-05,
      "loss": 0.4661,
      "step": 19385
    },
    {
      "epoch": 0.5955211501244125,
      "grad_norm": 0.42060428857803345,
      "learning_rate": 1.5962292721029054e-05,
      "loss": 0.6383,
      "step": 19386
    },
    {
      "epoch": 0.5955518692593617,
      "grad_norm": 0.5782510042190552,
      "learning_rate": 1.596190473215363e-05,
      "loss": 0.5626,
      "step": 19387
    },
    {
      "epoch": 0.5955825883943108,
      "grad_norm": 0.3611844480037689,
      "learning_rate": 1.5961516729353762e-05,
      "loss": 0.5326,
      "step": 19388
    },
    {
      "epoch": 0.59561330752926,
      "grad_norm": 0.36223089694976807,
      "learning_rate": 1.596112871263036e-05,
      "loss": 0.5486,
      "step": 19389
    },
    {
      "epoch": 0.5956440266642091,
      "grad_norm": 0.3270007371902466,
      "learning_rate": 1.5960740681984323e-05,
      "loss": 0.5099,
      "step": 19390
    },
    {
      "epoch": 0.5956747457991582,
      "grad_norm": 0.39997607469558716,
      "learning_rate": 1.5960352637416554e-05,
      "loss": 0.5971,
      "step": 19391
    },
    {
      "epoch": 0.5957054649341075,
      "grad_norm": 0.3451806604862213,
      "learning_rate": 1.5959964578927973e-05,
      "loss": 0.4902,
      "step": 19392
    },
    {
      "epoch": 0.5957361840690566,
      "grad_norm": 0.38417574763298035,
      "learning_rate": 1.5959576506519475e-05,
      "loss": 0.573,
      "step": 19393
    },
    {
      "epoch": 0.5957669032040058,
      "grad_norm": 0.44434601068496704,
      "learning_rate": 1.595918842019197e-05,
      "loss": 0.5383,
      "step": 19394
    },
    {
      "epoch": 0.595797622338955,
      "grad_norm": 0.38195866346359253,
      "learning_rate": 1.5958800319946364e-05,
      "loss": 0.6022,
      "step": 19395
    },
    {
      "epoch": 0.5958283414739041,
      "grad_norm": 0.3542909622192383,
      "learning_rate": 1.5958412205783564e-05,
      "loss": 0.4747,
      "step": 19396
    },
    {
      "epoch": 0.5958590606088533,
      "grad_norm": 0.35853907465934753,
      "learning_rate": 1.5958024077704476e-05,
      "loss": 0.5702,
      "step": 19397
    },
    {
      "epoch": 0.5958897797438024,
      "grad_norm": 0.310473769903183,
      "learning_rate": 1.5957635935710006e-05,
      "loss": 0.5284,
      "step": 19398
    },
    {
      "epoch": 0.5959204988787515,
      "grad_norm": 0.3660898208618164,
      "learning_rate": 1.5957247779801065e-05,
      "loss": 0.5399,
      "step": 19399
    },
    {
      "epoch": 0.5959512180137008,
      "grad_norm": 0.33408379554748535,
      "learning_rate": 1.595685960997855e-05,
      "loss": 0.5643,
      "step": 19400
    },
    {
      "epoch": 0.5959819371486499,
      "grad_norm": 0.3565502166748047,
      "learning_rate": 1.5956471426243377e-05,
      "loss": 0.5078,
      "step": 19401
    },
    {
      "epoch": 0.596012656283599,
      "grad_norm": 0.32802027463912964,
      "learning_rate": 1.5956083228596447e-05,
      "loss": 0.5199,
      "step": 19402
    },
    {
      "epoch": 0.5960433754185482,
      "grad_norm": 0.3303773105144501,
      "learning_rate": 1.595569501703867e-05,
      "loss": 0.5182,
      "step": 19403
    },
    {
      "epoch": 0.5960740945534974,
      "grad_norm": 0.3500034809112549,
      "learning_rate": 1.5955306791570954e-05,
      "loss": 0.5887,
      "step": 19404
    },
    {
      "epoch": 0.5961048136884466,
      "grad_norm": 0.36049652099609375,
      "learning_rate": 1.59549185521942e-05,
      "loss": 0.5461,
      "step": 19405
    },
    {
      "epoch": 0.5961355328233957,
      "grad_norm": 0.3547614514827728,
      "learning_rate": 1.5954530298909318e-05,
      "loss": 0.5341,
      "step": 19406
    },
    {
      "epoch": 0.5961662519583448,
      "grad_norm": 0.35513198375701904,
      "learning_rate": 1.595414203171721e-05,
      "loss": 0.5113,
      "step": 19407
    },
    {
      "epoch": 0.5961969710932941,
      "grad_norm": 0.3563268482685089,
      "learning_rate": 1.5953753750618796e-05,
      "loss": 0.5341,
      "step": 19408
    },
    {
      "epoch": 0.5962276902282432,
      "grad_norm": 0.33120062947273254,
      "learning_rate": 1.595336545561497e-05,
      "loss": 0.6422,
      "step": 19409
    },
    {
      "epoch": 0.5962584093631923,
      "grad_norm": 0.346703439950943,
      "learning_rate": 1.5952977146706647e-05,
      "loss": 0.5077,
      "step": 19410
    },
    {
      "epoch": 0.5962891284981415,
      "grad_norm": 0.4519638419151306,
      "learning_rate": 1.5952588823894722e-05,
      "loss": 0.6006,
      "step": 19411
    },
    {
      "epoch": 0.5963198476330906,
      "grad_norm": 0.3553495407104492,
      "learning_rate": 1.5952200487180117e-05,
      "loss": 0.5868,
      "step": 19412
    },
    {
      "epoch": 0.5963505667680398,
      "grad_norm": 0.3689003884792328,
      "learning_rate": 1.595181213656373e-05,
      "loss": 0.582,
      "step": 19413
    },
    {
      "epoch": 0.596381285902989,
      "grad_norm": 0.39063119888305664,
      "learning_rate": 1.595142377204647e-05,
      "loss": 0.6596,
      "step": 19414
    },
    {
      "epoch": 0.5964120050379381,
      "grad_norm": 0.3508763909339905,
      "learning_rate": 1.5951035393629244e-05,
      "loss": 0.6047,
      "step": 19415
    },
    {
      "epoch": 0.5964427241728872,
      "grad_norm": 0.3537028729915619,
      "learning_rate": 1.595064700131296e-05,
      "loss": 0.5211,
      "step": 19416
    },
    {
      "epoch": 0.5964734433078365,
      "grad_norm": 0.35449978709220886,
      "learning_rate": 1.5950258595098525e-05,
      "loss": 0.4647,
      "step": 19417
    },
    {
      "epoch": 0.5965041624427856,
      "grad_norm": 0.325618714094162,
      "learning_rate": 1.5949870174986845e-05,
      "loss": 0.5705,
      "step": 19418
    },
    {
      "epoch": 0.5965348815777348,
      "grad_norm": 0.40347597002983093,
      "learning_rate": 1.5949481740978823e-05,
      "loss": 0.5418,
      "step": 19419
    },
    {
      "epoch": 0.5965656007126839,
      "grad_norm": 0.5935251116752625,
      "learning_rate": 1.5949093293075375e-05,
      "loss": 0.5518,
      "step": 19420
    },
    {
      "epoch": 0.5965963198476331,
      "grad_norm": 0.4928579032421112,
      "learning_rate": 1.5948704831277406e-05,
      "loss": 0.5124,
      "step": 19421
    },
    {
      "epoch": 0.5966270389825823,
      "grad_norm": 0.33877480030059814,
      "learning_rate": 1.594831635558582e-05,
      "loss": 0.5261,
      "step": 19422
    },
    {
      "epoch": 0.5966577581175314,
      "grad_norm": 0.4171619415283203,
      "learning_rate": 1.5947927866001522e-05,
      "loss": 0.5519,
      "step": 19423
    },
    {
      "epoch": 0.5966884772524805,
      "grad_norm": 0.373649001121521,
      "learning_rate": 1.594753936252543e-05,
      "loss": 0.5172,
      "step": 19424
    },
    {
      "epoch": 0.5967191963874298,
      "grad_norm": 0.41560202836990356,
      "learning_rate": 1.5947150845158438e-05,
      "loss": 0.5843,
      "step": 19425
    },
    {
      "epoch": 0.5967499155223789,
      "grad_norm": 0.34785234928131104,
      "learning_rate": 1.5946762313901463e-05,
      "loss": 0.5806,
      "step": 19426
    },
    {
      "epoch": 0.596780634657328,
      "grad_norm": 0.3622877299785614,
      "learning_rate": 1.5946373768755407e-05,
      "loss": 0.5061,
      "step": 19427
    },
    {
      "epoch": 0.5968113537922772,
      "grad_norm": 0.3564468026161194,
      "learning_rate": 1.5945985209721185e-05,
      "loss": 0.5058,
      "step": 19428
    },
    {
      "epoch": 0.5968420729272264,
      "grad_norm": 0.34875187277793884,
      "learning_rate": 1.5945596636799693e-05,
      "loss": 0.5142,
      "step": 19429
    },
    {
      "epoch": 0.5968727920621756,
      "grad_norm": 0.35888105630874634,
      "learning_rate": 1.594520804999185e-05,
      "loss": 0.5794,
      "step": 19430
    },
    {
      "epoch": 0.5969035111971247,
      "grad_norm": 0.3730042576789856,
      "learning_rate": 1.5944819449298553e-05,
      "loss": 0.5403,
      "step": 19431
    },
    {
      "epoch": 0.5969342303320738,
      "grad_norm": 0.4047829210758209,
      "learning_rate": 1.5944430834720722e-05,
      "loss": 0.565,
      "step": 19432
    },
    {
      "epoch": 0.596964949467023,
      "grad_norm": 0.3604030907154083,
      "learning_rate": 1.594404220625925e-05,
      "loss": 0.55,
      "step": 19433
    },
    {
      "epoch": 0.5969956686019722,
      "grad_norm": 0.44642189145088196,
      "learning_rate": 1.5943653563915057e-05,
      "loss": 0.5519,
      "step": 19434
    },
    {
      "epoch": 0.5970263877369213,
      "grad_norm": 0.35048708319664,
      "learning_rate": 1.5943264907689046e-05,
      "loss": 0.615,
      "step": 19435
    },
    {
      "epoch": 0.5970571068718705,
      "grad_norm": 0.3370307385921478,
      "learning_rate": 1.5942876237582124e-05,
      "loss": 0.5101,
      "step": 19436
    },
    {
      "epoch": 0.5970878260068196,
      "grad_norm": 0.37070542573928833,
      "learning_rate": 1.5942487553595198e-05,
      "loss": 0.5828,
      "step": 19437
    },
    {
      "epoch": 0.5971185451417688,
      "grad_norm": 0.3838955760002136,
      "learning_rate": 1.594209885572918e-05,
      "loss": 0.5202,
      "step": 19438
    },
    {
      "epoch": 0.597149264276718,
      "grad_norm": 0.38030537962913513,
      "learning_rate": 1.5941710143984973e-05,
      "loss": 0.5977,
      "step": 19439
    },
    {
      "epoch": 0.5971799834116671,
      "grad_norm": 0.37394019961357117,
      "learning_rate": 1.5941321418363488e-05,
      "loss": 0.6158,
      "step": 19440
    },
    {
      "epoch": 0.5972107025466162,
      "grad_norm": 0.3157587945461273,
      "learning_rate": 1.5940932678865627e-05,
      "loss": 0.494,
      "step": 19441
    },
    {
      "epoch": 0.5972414216815655,
      "grad_norm": 0.3622080981731415,
      "learning_rate": 1.594054392549231e-05,
      "loss": 0.4821,
      "step": 19442
    },
    {
      "epoch": 0.5972721408165146,
      "grad_norm": 0.41837725043296814,
      "learning_rate": 1.5940155158244434e-05,
      "loss": 0.6397,
      "step": 19443
    },
    {
      "epoch": 0.5973028599514638,
      "grad_norm": 0.34028303623199463,
      "learning_rate": 1.5939766377122914e-05,
      "loss": 0.5973,
      "step": 19444
    },
    {
      "epoch": 0.5973335790864129,
      "grad_norm": 0.34651872515678406,
      "learning_rate": 1.5939377582128654e-05,
      "loss": 0.4918,
      "step": 19445
    },
    {
      "epoch": 0.5973642982213621,
      "grad_norm": 0.3477226793766022,
      "learning_rate": 1.593898877326256e-05,
      "loss": 0.5568,
      "step": 19446
    },
    {
      "epoch": 0.5973950173563113,
      "grad_norm": 0.3637239634990692,
      "learning_rate": 1.5938599950525544e-05,
      "loss": 0.586,
      "step": 19447
    },
    {
      "epoch": 0.5974257364912604,
      "grad_norm": 0.4042789936065674,
      "learning_rate": 1.5938211113918514e-05,
      "loss": 0.5529,
      "step": 19448
    },
    {
      "epoch": 0.5974564556262095,
      "grad_norm": 0.3374525010585785,
      "learning_rate": 1.5937822263442377e-05,
      "loss": 0.5102,
      "step": 19449
    },
    {
      "epoch": 0.5974871747611588,
      "grad_norm": 0.32946062088012695,
      "learning_rate": 1.593743339909804e-05,
      "loss": 0.5733,
      "step": 19450
    },
    {
      "epoch": 0.5975178938961079,
      "grad_norm": 0.3583781123161316,
      "learning_rate": 1.5937044520886415e-05,
      "loss": 0.603,
      "step": 19451
    },
    {
      "epoch": 0.597548613031057,
      "grad_norm": 0.3819290101528168,
      "learning_rate": 1.5936655628808406e-05,
      "loss": 0.5937,
      "step": 19452
    },
    {
      "epoch": 0.5975793321660062,
      "grad_norm": 0.3218579888343811,
      "learning_rate": 1.5936266722864923e-05,
      "loss": 0.5729,
      "step": 19453
    },
    {
      "epoch": 0.5976100513009553,
      "grad_norm": 0.3782792389392853,
      "learning_rate": 1.5935877803056875e-05,
      "loss": 0.6092,
      "step": 19454
    },
    {
      "epoch": 0.5976407704359046,
      "grad_norm": 2.5513217449188232,
      "learning_rate": 1.593548886938517e-05,
      "loss": 0.5821,
      "step": 19455
    },
    {
      "epoch": 0.5976714895708537,
      "grad_norm": 0.3869505822658539,
      "learning_rate": 1.5935099921850717e-05,
      "loss": 0.5201,
      "step": 19456
    },
    {
      "epoch": 0.5977022087058028,
      "grad_norm": 0.35041344165802,
      "learning_rate": 1.5934710960454426e-05,
      "loss": 0.5748,
      "step": 19457
    },
    {
      "epoch": 0.597732927840752,
      "grad_norm": 0.33245256543159485,
      "learning_rate": 1.59343219851972e-05,
      "loss": 0.5163,
      "step": 19458
    },
    {
      "epoch": 0.5977636469757012,
      "grad_norm": 0.3445160388946533,
      "learning_rate": 1.593393299607995e-05,
      "loss": 0.5483,
      "step": 19459
    },
    {
      "epoch": 0.5977943661106503,
      "grad_norm": 0.3344051241874695,
      "learning_rate": 1.5933543993103583e-05,
      "loss": 0.4976,
      "step": 19460
    },
    {
      "epoch": 0.5978250852455995,
      "grad_norm": 0.37686511874198914,
      "learning_rate": 1.5933154976269015e-05,
      "loss": 0.5833,
      "step": 19461
    },
    {
      "epoch": 0.5978558043805486,
      "grad_norm": 0.34298238158226013,
      "learning_rate": 1.5932765945577145e-05,
      "loss": 0.5575,
      "step": 19462
    },
    {
      "epoch": 0.5978865235154978,
      "grad_norm": 0.32611843943595886,
      "learning_rate": 1.5932376901028886e-05,
      "loss": 0.5231,
      "step": 19463
    },
    {
      "epoch": 0.597917242650447,
      "grad_norm": 0.40259721875190735,
      "learning_rate": 1.593198784262515e-05,
      "loss": 0.5281,
      "step": 19464
    },
    {
      "epoch": 0.5979479617853961,
      "grad_norm": 0.3927069306373596,
      "learning_rate": 1.593159877036684e-05,
      "loss": 0.5943,
      "step": 19465
    },
    {
      "epoch": 0.5979786809203452,
      "grad_norm": 0.4234201908111572,
      "learning_rate": 1.5931209684254867e-05,
      "loss": 0.5324,
      "step": 19466
    },
    {
      "epoch": 0.5980094000552945,
      "grad_norm": 0.3608892858028412,
      "learning_rate": 1.593082058429014e-05,
      "loss": 0.4547,
      "step": 19467
    },
    {
      "epoch": 0.5980401191902436,
      "grad_norm": 0.3717694878578186,
      "learning_rate": 1.5930431470473565e-05,
      "loss": 0.5587,
      "step": 19468
    },
    {
      "epoch": 0.5980708383251928,
      "grad_norm": 0.31921806931495667,
      "learning_rate": 1.5930042342806055e-05,
      "loss": 0.5303,
      "step": 19469
    },
    {
      "epoch": 0.5981015574601419,
      "grad_norm": 0.37309640645980835,
      "learning_rate": 1.592965320128852e-05,
      "loss": 0.5934,
      "step": 19470
    },
    {
      "epoch": 0.598132276595091,
      "grad_norm": 0.38161543011665344,
      "learning_rate": 1.592926404592186e-05,
      "loss": 0.5019,
      "step": 19471
    },
    {
      "epoch": 0.5981629957300403,
      "grad_norm": 0.3574732840061188,
      "learning_rate": 1.5928874876706993e-05,
      "loss": 0.5527,
      "step": 19472
    },
    {
      "epoch": 0.5981937148649894,
      "grad_norm": 0.3310537338256836,
      "learning_rate": 1.5928485693644826e-05,
      "loss": 0.4965,
      "step": 19473
    },
    {
      "epoch": 0.5982244339999385,
      "grad_norm": 0.3321588635444641,
      "learning_rate": 1.592809649673626e-05,
      "loss": 0.4906,
      "step": 19474
    },
    {
      "epoch": 0.5982551531348878,
      "grad_norm": 0.34403035044670105,
      "learning_rate": 1.5927707285982215e-05,
      "loss": 0.4533,
      "step": 19475
    },
    {
      "epoch": 0.5982858722698369,
      "grad_norm": 0.37050917744636536,
      "learning_rate": 1.5927318061383595e-05,
      "loss": 0.5959,
      "step": 19476
    },
    {
      "epoch": 0.598316591404786,
      "grad_norm": 0.36326029896736145,
      "learning_rate": 1.5926928822941312e-05,
      "loss": 0.5337,
      "step": 19477
    },
    {
      "epoch": 0.5983473105397352,
      "grad_norm": 0.38365069031715393,
      "learning_rate": 1.5926539570656272e-05,
      "loss": 0.6059,
      "step": 19478
    },
    {
      "epoch": 0.5983780296746843,
      "grad_norm": 0.3418891727924347,
      "learning_rate": 1.5926150304529385e-05,
      "loss": 0.569,
      "step": 19479
    },
    {
      "epoch": 0.5984087488096336,
      "grad_norm": 0.333897203207016,
      "learning_rate": 1.592576102456156e-05,
      "loss": 0.5407,
      "step": 19480
    },
    {
      "epoch": 0.5984394679445827,
      "grad_norm": 0.3380824029445648,
      "learning_rate": 1.5925371730753703e-05,
      "loss": 0.4528,
      "step": 19481
    },
    {
      "epoch": 0.5984701870795318,
      "grad_norm": 0.427156537771225,
      "learning_rate": 1.5924982423106728e-05,
      "loss": 0.6738,
      "step": 19482
    },
    {
      "epoch": 0.598500906214481,
      "grad_norm": 0.3595770299434662,
      "learning_rate": 1.5924593101621545e-05,
      "loss": 0.5176,
      "step": 19483
    },
    {
      "epoch": 0.5985316253494302,
      "grad_norm": 0.40811100602149963,
      "learning_rate": 1.592420376629906e-05,
      "loss": 0.604,
      "step": 19484
    },
    {
      "epoch": 0.5985623444843793,
      "grad_norm": 0.3422069847583771,
      "learning_rate": 1.5923814417140186e-05,
      "loss": 0.5382,
      "step": 19485
    },
    {
      "epoch": 0.5985930636193285,
      "grad_norm": 0.41692590713500977,
      "learning_rate": 1.592342505414582e-05,
      "loss": 0.5839,
      "step": 19486
    },
    {
      "epoch": 0.5986237827542776,
      "grad_norm": 0.3491307497024536,
      "learning_rate": 1.592303567731689e-05,
      "loss": 0.546,
      "step": 19487
    },
    {
      "epoch": 0.5986545018892268,
      "grad_norm": 0.9688826203346252,
      "learning_rate": 1.5922646286654298e-05,
      "loss": 0.6247,
      "step": 19488
    },
    {
      "epoch": 0.598685221024176,
      "grad_norm": 0.3704121708869934,
      "learning_rate": 1.5922256882158948e-05,
      "loss": 0.5347,
      "step": 19489
    },
    {
      "epoch": 0.5987159401591251,
      "grad_norm": 0.32912978529930115,
      "learning_rate": 1.5921867463831753e-05,
      "loss": 0.5429,
      "step": 19490
    },
    {
      "epoch": 0.5987466592940742,
      "grad_norm": 0.32064101099967957,
      "learning_rate": 1.592147803167362e-05,
      "loss": 0.6633,
      "step": 19491
    },
    {
      "epoch": 0.5987773784290235,
      "grad_norm": 0.3497718572616577,
      "learning_rate": 1.5921088585685468e-05,
      "loss": 0.5762,
      "step": 19492
    },
    {
      "epoch": 0.5988080975639726,
      "grad_norm": 0.33952605724334717,
      "learning_rate": 1.5920699125868197e-05,
      "loss": 0.5167,
      "step": 19493
    },
    {
      "epoch": 0.5988388166989218,
      "grad_norm": 0.3658501207828522,
      "learning_rate": 1.5920309652222724e-05,
      "loss": 0.6027,
      "step": 19494
    },
    {
      "epoch": 0.5988695358338709,
      "grad_norm": 0.4256591200828552,
      "learning_rate": 1.5919920164749946e-05,
      "loss": 0.5599,
      "step": 19495
    },
    {
      "epoch": 0.59890025496882,
      "grad_norm": 0.4202582538127899,
      "learning_rate": 1.5919530663450785e-05,
      "loss": 0.5792,
      "step": 19496
    },
    {
      "epoch": 0.5989309741037693,
      "grad_norm": 0.3854195177555084,
      "learning_rate": 1.5919141148326152e-05,
      "loss": 0.5196,
      "step": 19497
    },
    {
      "epoch": 0.5989616932387184,
      "grad_norm": 0.3967524766921997,
      "learning_rate": 1.5918751619376946e-05,
      "loss": 0.5563,
      "step": 19498
    },
    {
      "epoch": 0.5989924123736675,
      "grad_norm": 0.41796550154685974,
      "learning_rate": 1.591836207660408e-05,
      "loss": 0.5763,
      "step": 19499
    },
    {
      "epoch": 0.5990231315086167,
      "grad_norm": 0.3295767605304718,
      "learning_rate": 1.591797252000847e-05,
      "loss": 0.5165,
      "step": 19500
    },
    {
      "epoch": 0.5990538506435659,
      "grad_norm": 0.3308233320713043,
      "learning_rate": 1.591758294959102e-05,
      "loss": 0.5383,
      "step": 19501
    },
    {
      "epoch": 0.599084569778515,
      "grad_norm": 0.33869725465774536,
      "learning_rate": 1.5917193365352647e-05,
      "loss": 0.6054,
      "step": 19502
    },
    {
      "epoch": 0.5991152889134642,
      "grad_norm": 0.44373536109924316,
      "learning_rate": 1.591680376729425e-05,
      "loss": 0.54,
      "step": 19503
    },
    {
      "epoch": 0.5991460080484133,
      "grad_norm": 0.36836227774620056,
      "learning_rate": 1.5916414155416743e-05,
      "loss": 0.5924,
      "step": 19504
    },
    {
      "epoch": 0.5991767271833626,
      "grad_norm": 0.3327288031578064,
      "learning_rate": 1.5916024529721043e-05,
      "loss": 0.5444,
      "step": 19505
    },
    {
      "epoch": 0.5992074463183117,
      "grad_norm": 0.32884112000465393,
      "learning_rate": 1.5915634890208053e-05,
      "loss": 0.5171,
      "step": 19506
    },
    {
      "epoch": 0.5992381654532608,
      "grad_norm": 0.5821641683578491,
      "learning_rate": 1.591524523687868e-05,
      "loss": 0.5357,
      "step": 19507
    },
    {
      "epoch": 0.59926888458821,
      "grad_norm": 0.37584060430526733,
      "learning_rate": 1.5914855569733845e-05,
      "loss": 0.6236,
      "step": 19508
    },
    {
      "epoch": 0.5992996037231592,
      "grad_norm": 0.4199647009372711,
      "learning_rate": 1.5914465888774445e-05,
      "loss": 0.5443,
      "step": 19509
    },
    {
      "epoch": 0.5993303228581083,
      "grad_norm": 0.41374093294143677,
      "learning_rate": 1.59140761940014e-05,
      "loss": 0.5446,
      "step": 19510
    },
    {
      "epoch": 0.5993610419930575,
      "grad_norm": 0.376899391412735,
      "learning_rate": 1.591368648541562e-05,
      "loss": 0.5147,
      "step": 19511
    },
    {
      "epoch": 0.5993917611280066,
      "grad_norm": 0.36680424213409424,
      "learning_rate": 1.591329676301801e-05,
      "loss": 0.475,
      "step": 19512
    },
    {
      "epoch": 0.5994224802629557,
      "grad_norm": 0.48222753405570984,
      "learning_rate": 1.591290702680948e-05,
      "loss": 0.5485,
      "step": 19513
    },
    {
      "epoch": 0.599453199397905,
      "grad_norm": 0.3725198209285736,
      "learning_rate": 1.5912517276790947e-05,
      "loss": 0.5536,
      "step": 19514
    },
    {
      "epoch": 0.5994839185328541,
      "grad_norm": 0.3388107419013977,
      "learning_rate": 1.5912127512963316e-05,
      "loss": 0.5519,
      "step": 19515
    },
    {
      "epoch": 0.5995146376678033,
      "grad_norm": 0.35696518421173096,
      "learning_rate": 1.5911737735327496e-05,
      "loss": 0.6336,
      "step": 19516
    },
    {
      "epoch": 0.5995453568027524,
      "grad_norm": 0.351314902305603,
      "learning_rate": 1.5911347943884402e-05,
      "loss": 0.5607,
      "step": 19517
    },
    {
      "epoch": 0.5995760759377016,
      "grad_norm": 0.37799492478370667,
      "learning_rate": 1.5910958138634942e-05,
      "loss": 0.527,
      "step": 19518
    },
    {
      "epoch": 0.5996067950726508,
      "grad_norm": 0.34950292110443115,
      "learning_rate": 1.5910568319580024e-05,
      "loss": 0.5218,
      "step": 19519
    },
    {
      "epoch": 0.5996375142075999,
      "grad_norm": 0.3978697955608368,
      "learning_rate": 1.5910178486720563e-05,
      "loss": 0.6401,
      "step": 19520
    },
    {
      "epoch": 0.599668233342549,
      "grad_norm": 0.3663484454154968,
      "learning_rate": 1.5909788640057467e-05,
      "loss": 0.5437,
      "step": 19521
    },
    {
      "epoch": 0.5996989524774983,
      "grad_norm": 0.36812081933021545,
      "learning_rate": 1.5909398779591647e-05,
      "loss": 0.5682,
      "step": 19522
    },
    {
      "epoch": 0.5997296716124474,
      "grad_norm": 0.3493898808956146,
      "learning_rate": 1.590900890532401e-05,
      "loss": 0.5566,
      "step": 19523
    },
    {
      "epoch": 0.5997603907473965,
      "grad_norm": 0.36044541001319885,
      "learning_rate": 1.5908619017255475e-05,
      "loss": 0.6347,
      "step": 19524
    },
    {
      "epoch": 0.5997911098823457,
      "grad_norm": 0.34203091263771057,
      "learning_rate": 1.5908229115386945e-05,
      "loss": 0.4968,
      "step": 19525
    },
    {
      "epoch": 0.5998218290172949,
      "grad_norm": 0.3907161056995392,
      "learning_rate": 1.5907839199719334e-05,
      "loss": 0.5701,
      "step": 19526
    },
    {
      "epoch": 0.599852548152244,
      "grad_norm": 0.3466881215572357,
      "learning_rate": 1.5907449270253553e-05,
      "loss": 0.5321,
      "step": 19527
    },
    {
      "epoch": 0.5998832672871932,
      "grad_norm": 0.33413711190223694,
      "learning_rate": 1.590705932699051e-05,
      "loss": 0.4807,
      "step": 19528
    },
    {
      "epoch": 0.5999139864221423,
      "grad_norm": 0.3419716954231262,
      "learning_rate": 1.590666936993112e-05,
      "loss": 0.6148,
      "step": 19529
    },
    {
      "epoch": 0.5999447055570916,
      "grad_norm": 0.3156024217605591,
      "learning_rate": 1.5906279399076286e-05,
      "loss": 0.5531,
      "step": 19530
    },
    {
      "epoch": 0.5999754246920407,
      "grad_norm": 0.3905488848686218,
      "learning_rate": 1.590588941442693e-05,
      "loss": 0.6032,
      "step": 19531
    },
    {
      "epoch": 0.6000061438269898,
      "grad_norm": 0.37016335129737854,
      "learning_rate": 1.590549941598395e-05,
      "loss": 0.5946,
      "step": 19532
    },
    {
      "epoch": 0.600036862961939,
      "grad_norm": 0.3995557725429535,
      "learning_rate": 1.5905109403748272e-05,
      "loss": 0.6376,
      "step": 19533
    },
    {
      "epoch": 0.6000675820968882,
      "grad_norm": 0.34126079082489014,
      "learning_rate": 1.5904719377720793e-05,
      "loss": 0.5066,
      "step": 19534
    },
    {
      "epoch": 0.6000983012318373,
      "grad_norm": 0.3695078194141388,
      "learning_rate": 1.5904329337902428e-05,
      "loss": 0.5835,
      "step": 19535
    },
    {
      "epoch": 0.6001290203667865,
      "grad_norm": 0.35126134753227234,
      "learning_rate": 1.590393928429409e-05,
      "loss": 0.5955,
      "step": 19536
    },
    {
      "epoch": 0.6001597395017356,
      "grad_norm": 0.4138120114803314,
      "learning_rate": 1.5903549216896696e-05,
      "loss": 0.5145,
      "step": 19537
    },
    {
      "epoch": 0.6001904586366847,
      "grad_norm": 0.37094202637672424,
      "learning_rate": 1.5903159135711146e-05,
      "loss": 0.531,
      "step": 19538
    },
    {
      "epoch": 0.600221177771634,
      "grad_norm": 0.32772138714790344,
      "learning_rate": 1.5902769040738356e-05,
      "loss": 0.5379,
      "step": 19539
    },
    {
      "epoch": 0.6002518969065831,
      "grad_norm": 0.36894676089286804,
      "learning_rate": 1.5902378931979237e-05,
      "loss": 0.5902,
      "step": 19540
    },
    {
      "epoch": 0.6002826160415323,
      "grad_norm": 0.3961254060268402,
      "learning_rate": 1.5901988809434698e-05,
      "loss": 0.6143,
      "step": 19541
    },
    {
      "epoch": 0.6003133351764814,
      "grad_norm": 0.36286818981170654,
      "learning_rate": 1.5901598673105653e-05,
      "loss": 0.5715,
      "step": 19542
    },
    {
      "epoch": 0.6003440543114306,
      "grad_norm": 0.40156176686286926,
      "learning_rate": 1.5901208522993014e-05,
      "loss": 0.5668,
      "step": 19543
    },
    {
      "epoch": 0.6003747734463798,
      "grad_norm": 0.3763079047203064,
      "learning_rate": 1.5900818359097688e-05,
      "loss": 0.5753,
      "step": 19544
    },
    {
      "epoch": 0.6004054925813289,
      "grad_norm": 0.41827788949012756,
      "learning_rate": 1.5900428181420587e-05,
      "loss": 0.5596,
      "step": 19545
    },
    {
      "epoch": 0.600436211716278,
      "grad_norm": 0.3603114187717438,
      "learning_rate": 1.590003798996263e-05,
      "loss": 0.6693,
      "step": 19546
    },
    {
      "epoch": 0.6004669308512273,
      "grad_norm": 0.36478447914123535,
      "learning_rate": 1.5899647784724717e-05,
      "loss": 0.5656,
      "step": 19547
    },
    {
      "epoch": 0.6004976499861764,
      "grad_norm": 0.36018648743629456,
      "learning_rate": 1.5899257565707763e-05,
      "loss": 0.5831,
      "step": 19548
    },
    {
      "epoch": 0.6005283691211255,
      "grad_norm": 0.34253913164138794,
      "learning_rate": 1.5898867332912687e-05,
      "loss": 0.5968,
      "step": 19549
    },
    {
      "epoch": 0.6005590882560747,
      "grad_norm": 0.37522199749946594,
      "learning_rate": 1.589847708634039e-05,
      "loss": 0.5932,
      "step": 19550
    },
    {
      "epoch": 0.6005898073910239,
      "grad_norm": 0.36543136835098267,
      "learning_rate": 1.5898086825991786e-05,
      "loss": 0.6357,
      "step": 19551
    },
    {
      "epoch": 0.600620526525973,
      "grad_norm": 0.35073959827423096,
      "learning_rate": 1.5897696551867794e-05,
      "loss": 0.5716,
      "step": 19552
    },
    {
      "epoch": 0.6006512456609222,
      "grad_norm": 0.42632871866226196,
      "learning_rate": 1.5897306263969318e-05,
      "loss": 0.5469,
      "step": 19553
    },
    {
      "epoch": 0.6006819647958713,
      "grad_norm": 0.363543838262558,
      "learning_rate": 1.589691596229727e-05,
      "loss": 0.5557,
      "step": 19554
    },
    {
      "epoch": 0.6007126839308206,
      "grad_norm": 0.3618170917034149,
      "learning_rate": 1.5896525646852564e-05,
      "loss": 0.5822,
      "step": 19555
    },
    {
      "epoch": 0.6007434030657697,
      "grad_norm": 0.348664790391922,
      "learning_rate": 1.589613531763611e-05,
      "loss": 0.5973,
      "step": 19556
    },
    {
      "epoch": 0.6007741222007188,
      "grad_norm": 0.34390124678611755,
      "learning_rate": 1.589574497464882e-05,
      "loss": 0.4447,
      "step": 19557
    },
    {
      "epoch": 0.600804841335668,
      "grad_norm": 0.39013803005218506,
      "learning_rate": 1.5895354617891607e-05,
      "loss": 0.5581,
      "step": 19558
    },
    {
      "epoch": 0.6008355604706171,
      "grad_norm": 0.3361425995826721,
      "learning_rate": 1.5894964247365382e-05,
      "loss": 0.5006,
      "step": 19559
    },
    {
      "epoch": 0.6008662796055663,
      "grad_norm": 0.3458382487297058,
      "learning_rate": 1.5894573863071053e-05,
      "loss": 0.4997,
      "step": 19560
    },
    {
      "epoch": 0.6008969987405155,
      "grad_norm": 0.3913351893424988,
      "learning_rate": 1.5894183465009536e-05,
      "loss": 0.6045,
      "step": 19561
    },
    {
      "epoch": 0.6009277178754646,
      "grad_norm": 0.3635474145412445,
      "learning_rate": 1.5893793053181744e-05,
      "loss": 0.6039,
      "step": 19562
    },
    {
      "epoch": 0.6009584370104137,
      "grad_norm": 0.374327152967453,
      "learning_rate": 1.5893402627588586e-05,
      "loss": 0.5744,
      "step": 19563
    },
    {
      "epoch": 0.600989156145363,
      "grad_norm": 0.33798420429229736,
      "learning_rate": 1.5893012188230973e-05,
      "loss": 0.5633,
      "step": 19564
    },
    {
      "epoch": 0.6010198752803121,
      "grad_norm": 0.3624313771724701,
      "learning_rate": 1.589262173510982e-05,
      "loss": 0.5634,
      "step": 19565
    },
    {
      "epoch": 0.6010505944152613,
      "grad_norm": 0.6231707334518433,
      "learning_rate": 1.589223126822604e-05,
      "loss": 0.5174,
      "step": 19566
    },
    {
      "epoch": 0.6010813135502104,
      "grad_norm": 0.3626222610473633,
      "learning_rate": 1.5891840787580533e-05,
      "loss": 0.5515,
      "step": 19567
    },
    {
      "epoch": 0.6011120326851596,
      "grad_norm": 0.3414170742034912,
      "learning_rate": 1.589145029317423e-05,
      "loss": 0.5605,
      "step": 19568
    },
    {
      "epoch": 0.6011427518201088,
      "grad_norm": 0.3681817054748535,
      "learning_rate": 1.589105978500803e-05,
      "loss": 0.5338,
      "step": 19569
    },
    {
      "epoch": 0.6011734709550579,
      "grad_norm": 0.3049899935722351,
      "learning_rate": 1.589066926308285e-05,
      "loss": 0.5539,
      "step": 19570
    },
    {
      "epoch": 0.601204190090007,
      "grad_norm": 0.43711522221565247,
      "learning_rate": 1.58902787273996e-05,
      "loss": 0.6416,
      "step": 19571
    },
    {
      "epoch": 0.6012349092249563,
      "grad_norm": 0.33012062311172485,
      "learning_rate": 1.588988817795919e-05,
      "loss": 0.5598,
      "step": 19572
    },
    {
      "epoch": 0.6012656283599054,
      "grad_norm": 0.47111645340919495,
      "learning_rate": 1.5889497614762536e-05,
      "loss": 0.5347,
      "step": 19573
    },
    {
      "epoch": 0.6012963474948545,
      "grad_norm": 0.34404662251472473,
      "learning_rate": 1.588910703781055e-05,
      "loss": 0.573,
      "step": 19574
    },
    {
      "epoch": 0.6013270666298037,
      "grad_norm": 0.3304150104522705,
      "learning_rate": 1.5888716447104142e-05,
      "loss": 0.5799,
      "step": 19575
    },
    {
      "epoch": 0.6013577857647529,
      "grad_norm": 0.3609777092933655,
      "learning_rate": 1.588832584264423e-05,
      "loss": 0.5968,
      "step": 19576
    },
    {
      "epoch": 0.601388504899702,
      "grad_norm": 0.3994951546192169,
      "learning_rate": 1.5887935224431713e-05,
      "loss": 0.6007,
      "step": 19577
    },
    {
      "epoch": 0.6014192240346512,
      "grad_norm": 0.30830270051956177,
      "learning_rate": 1.588754459246752e-05,
      "loss": 0.5572,
      "step": 19578
    },
    {
      "epoch": 0.6014499431696003,
      "grad_norm": 0.4771658778190613,
      "learning_rate": 1.588715394675255e-05,
      "loss": 0.5028,
      "step": 19579
    },
    {
      "epoch": 0.6014806623045496,
      "grad_norm": 0.3539998531341553,
      "learning_rate": 1.5886763287287725e-05,
      "loss": 0.5999,
      "step": 19580
    },
    {
      "epoch": 0.6015113814394987,
      "grad_norm": 0.3429117202758789,
      "learning_rate": 1.588637261407395e-05,
      "loss": 0.493,
      "step": 19581
    },
    {
      "epoch": 0.6015421005744478,
      "grad_norm": 0.3613777458667755,
      "learning_rate": 1.5885981927112145e-05,
      "loss": 0.6046,
      "step": 19582
    },
    {
      "epoch": 0.601572819709397,
      "grad_norm": 0.38133755326271057,
      "learning_rate": 1.588559122640321e-05,
      "loss": 0.6053,
      "step": 19583
    },
    {
      "epoch": 0.6016035388443461,
      "grad_norm": 0.3817594349384308,
      "learning_rate": 1.5885200511948077e-05,
      "loss": 0.4458,
      "step": 19584
    },
    {
      "epoch": 0.6016342579792953,
      "grad_norm": 0.3266666531562805,
      "learning_rate": 1.5884809783747638e-05,
      "loss": 0.5418,
      "step": 19585
    },
    {
      "epoch": 0.6016649771142445,
      "grad_norm": 0.32851642370224,
      "learning_rate": 1.588441904180282e-05,
      "loss": 0.508,
      "step": 19586
    },
    {
      "epoch": 0.6016956962491936,
      "grad_norm": 0.3258872926235199,
      "learning_rate": 1.588402828611453e-05,
      "loss": 0.5443,
      "step": 19587
    },
    {
      "epoch": 0.6017264153841427,
      "grad_norm": 0.35090503096580505,
      "learning_rate": 1.5883637516683677e-05,
      "loss": 0.4993,
      "step": 19588
    },
    {
      "epoch": 0.601757134519092,
      "grad_norm": 0.3413984477519989,
      "learning_rate": 1.588324673351118e-05,
      "loss": 0.5158,
      "step": 19589
    },
    {
      "epoch": 0.6017878536540411,
      "grad_norm": 0.3647646903991699,
      "learning_rate": 1.5882855936597947e-05,
      "loss": 0.607,
      "step": 19590
    },
    {
      "epoch": 0.6018185727889903,
      "grad_norm": 0.3940635621547699,
      "learning_rate": 1.5882465125944895e-05,
      "loss": 0.6178,
      "step": 19591
    },
    {
      "epoch": 0.6018492919239394,
      "grad_norm": 0.3580094873905182,
      "learning_rate": 1.588207430155294e-05,
      "loss": 0.5693,
      "step": 19592
    },
    {
      "epoch": 0.6018800110588886,
      "grad_norm": 0.3632410168647766,
      "learning_rate": 1.5881683463422982e-05,
      "loss": 0.5473,
      "step": 19593
    },
    {
      "epoch": 0.6019107301938378,
      "grad_norm": 0.33120229840278625,
      "learning_rate": 1.5881292611555946e-05,
      "loss": 0.584,
      "step": 19594
    },
    {
      "epoch": 0.6019414493287869,
      "grad_norm": 0.3559219241142273,
      "learning_rate": 1.5880901745952736e-05,
      "loss": 0.6186,
      "step": 19595
    },
    {
      "epoch": 0.601972168463736,
      "grad_norm": 0.4880407750606537,
      "learning_rate": 1.5880510866614278e-05,
      "loss": 0.4769,
      "step": 19596
    },
    {
      "epoch": 0.6020028875986853,
      "grad_norm": 0.3619921803474426,
      "learning_rate": 1.5880119973541468e-05,
      "loss": 0.5059,
      "step": 19597
    },
    {
      "epoch": 0.6020336067336344,
      "grad_norm": 0.3507855236530304,
      "learning_rate": 1.5879729066735228e-05,
      "loss": 0.5427,
      "step": 19598
    },
    {
      "epoch": 0.6020643258685835,
      "grad_norm": 0.3435400128364563,
      "learning_rate": 1.5879338146196473e-05,
      "loss": 0.5941,
      "step": 19599
    },
    {
      "epoch": 0.6020950450035327,
      "grad_norm": 0.40415143966674805,
      "learning_rate": 1.587894721192611e-05,
      "loss": 0.6236,
      "step": 19600
    },
    {
      "epoch": 0.6021257641384818,
      "grad_norm": 0.3205101191997528,
      "learning_rate": 1.587855626392506e-05,
      "loss": 0.5234,
      "step": 19601
    },
    {
      "epoch": 0.602156483273431,
      "grad_norm": 0.3605336844921112,
      "learning_rate": 1.5878165302194224e-05,
      "loss": 0.5874,
      "step": 19602
    },
    {
      "epoch": 0.6021872024083802,
      "grad_norm": 0.36998528242111206,
      "learning_rate": 1.5877774326734528e-05,
      "loss": 0.5658,
      "step": 19603
    },
    {
      "epoch": 0.6022179215433293,
      "grad_norm": 0.4074169099330902,
      "learning_rate": 1.587738333754688e-05,
      "loss": 0.5593,
      "step": 19604
    },
    {
      "epoch": 0.6022486406782785,
      "grad_norm": 0.35767021775245667,
      "learning_rate": 1.587699233463219e-05,
      "loss": 0.525,
      "step": 19605
    },
    {
      "epoch": 0.6022793598132277,
      "grad_norm": 0.3320155739784241,
      "learning_rate": 1.5876601317991373e-05,
      "loss": 0.5022,
      "step": 19606
    },
    {
      "epoch": 0.6023100789481768,
      "grad_norm": 0.33550047874450684,
      "learning_rate": 1.5876210287625348e-05,
      "loss": 0.5386,
      "step": 19607
    },
    {
      "epoch": 0.602340798083126,
      "grad_norm": 0.34095141291618347,
      "learning_rate": 1.5875819243535017e-05,
      "loss": 0.4935,
      "step": 19608
    },
    {
      "epoch": 0.6023715172180751,
      "grad_norm": 0.3117285668849945,
      "learning_rate": 1.5875428185721305e-05,
      "loss": 0.503,
      "step": 19609
    },
    {
      "epoch": 0.6024022363530243,
      "grad_norm": 0.3561420440673828,
      "learning_rate": 1.5875037114185118e-05,
      "loss": 0.5481,
      "step": 19610
    },
    {
      "epoch": 0.6024329554879735,
      "grad_norm": 0.3460310697555542,
      "learning_rate": 1.5874646028927372e-05,
      "loss": 0.5116,
      "step": 19611
    },
    {
      "epoch": 0.6024636746229226,
      "grad_norm": 0.34081321954727173,
      "learning_rate": 1.587425492994898e-05,
      "loss": 0.5275,
      "step": 19612
    },
    {
      "epoch": 0.6024943937578717,
      "grad_norm": 0.3533998727798462,
      "learning_rate": 1.5873863817250855e-05,
      "loss": 0.5028,
      "step": 19613
    },
    {
      "epoch": 0.602525112892821,
      "grad_norm": 0.3379310369491577,
      "learning_rate": 1.5873472690833912e-05,
      "loss": 0.5448,
      "step": 19614
    },
    {
      "epoch": 0.6025558320277701,
      "grad_norm": 0.3325033485889435,
      "learning_rate": 1.5873081550699064e-05,
      "loss": 0.5603,
      "step": 19615
    },
    {
      "epoch": 0.6025865511627193,
      "grad_norm": 0.4163253903388977,
      "learning_rate": 1.5872690396847222e-05,
      "loss": 0.5615,
      "step": 19616
    },
    {
      "epoch": 0.6026172702976684,
      "grad_norm": 0.37373730540275574,
      "learning_rate": 1.58722992292793e-05,
      "loss": 0.5699,
      "step": 19617
    },
    {
      "epoch": 0.6026479894326175,
      "grad_norm": 0.3341946005821228,
      "learning_rate": 1.5871908047996215e-05,
      "loss": 0.5342,
      "step": 19618
    },
    {
      "epoch": 0.6026787085675668,
      "grad_norm": 0.352104514837265,
      "learning_rate": 1.587151685299888e-05,
      "loss": 0.5699,
      "step": 19619
    },
    {
      "epoch": 0.6027094277025159,
      "grad_norm": 0.3575037717819214,
      "learning_rate": 1.5871125644288204e-05,
      "loss": 0.5101,
      "step": 19620
    },
    {
      "epoch": 0.602740146837465,
      "grad_norm": 0.34641531109809875,
      "learning_rate": 1.5870734421865105e-05,
      "loss": 0.5001,
      "step": 19621
    },
    {
      "epoch": 0.6027708659724142,
      "grad_norm": 0.35123884677886963,
      "learning_rate": 1.5870343185730497e-05,
      "loss": 0.5285,
      "step": 19622
    },
    {
      "epoch": 0.6028015851073634,
      "grad_norm": 0.32900580763816833,
      "learning_rate": 1.5869951935885292e-05,
      "loss": 0.5685,
      "step": 19623
    },
    {
      "epoch": 0.6028323042423125,
      "grad_norm": 0.4103802740573883,
      "learning_rate": 1.5869560672330405e-05,
      "loss": 0.6335,
      "step": 19624
    },
    {
      "epoch": 0.6028630233772617,
      "grad_norm": 0.3774985373020172,
      "learning_rate": 1.5869169395066747e-05,
      "loss": 0.6651,
      "step": 19625
    },
    {
      "epoch": 0.6028937425122108,
      "grad_norm": 0.35895925760269165,
      "learning_rate": 1.5868778104095236e-05,
      "loss": 0.6081,
      "step": 19626
    },
    {
      "epoch": 0.6029244616471601,
      "grad_norm": 0.412117063999176,
      "learning_rate": 1.5868386799416784e-05,
      "loss": 0.5418,
      "step": 19627
    },
    {
      "epoch": 0.6029551807821092,
      "grad_norm": 0.37072139978408813,
      "learning_rate": 1.5867995481032305e-05,
      "loss": 0.5829,
      "step": 19628
    },
    {
      "epoch": 0.6029858999170583,
      "grad_norm": 0.35745006799697876,
      "learning_rate": 1.5867604148942712e-05,
      "loss": 0.5327,
      "step": 19629
    },
    {
      "epoch": 0.6030166190520075,
      "grad_norm": 0.38440951704978943,
      "learning_rate": 1.5867212803148918e-05,
      "loss": 0.5424,
      "step": 19630
    },
    {
      "epoch": 0.6030473381869567,
      "grad_norm": 0.3669082224369049,
      "learning_rate": 1.5866821443651842e-05,
      "loss": 0.5644,
      "step": 19631
    },
    {
      "epoch": 0.6030780573219058,
      "grad_norm": 0.3516797423362732,
      "learning_rate": 1.5866430070452392e-05,
      "loss": 0.5373,
      "step": 19632
    },
    {
      "epoch": 0.603108776456855,
      "grad_norm": 0.33965370059013367,
      "learning_rate": 1.5866038683551486e-05,
      "loss": 0.672,
      "step": 19633
    },
    {
      "epoch": 0.6031394955918041,
      "grad_norm": 0.36765801906585693,
      "learning_rate": 1.5865647282950036e-05,
      "loss": 0.4798,
      "step": 19634
    },
    {
      "epoch": 0.6031702147267533,
      "grad_norm": 0.350129097700119,
      "learning_rate": 1.586525586864896e-05,
      "loss": 0.57,
      "step": 19635
    },
    {
      "epoch": 0.6032009338617025,
      "grad_norm": 0.40640467405319214,
      "learning_rate": 1.5864864440649168e-05,
      "loss": 0.5708,
      "step": 19636
    },
    {
      "epoch": 0.6032316529966516,
      "grad_norm": 0.7209264039993286,
      "learning_rate": 1.5864472998951573e-05,
      "loss": 0.6466,
      "step": 19637
    },
    {
      "epoch": 0.6032623721316007,
      "grad_norm": 0.4318600594997406,
      "learning_rate": 1.5864081543557093e-05,
      "loss": 0.6151,
      "step": 19638
    },
    {
      "epoch": 0.60329309126655,
      "grad_norm": 0.35024645924568176,
      "learning_rate": 1.5863690074466642e-05,
      "loss": 0.5403,
      "step": 19639
    },
    {
      "epoch": 0.6033238104014991,
      "grad_norm": 0.34964507818222046,
      "learning_rate": 1.5863298591681132e-05,
      "loss": 0.6392,
      "step": 19640
    },
    {
      "epoch": 0.6033545295364483,
      "grad_norm": 0.34097084403038025,
      "learning_rate": 1.586290709520148e-05,
      "loss": 0.5382,
      "step": 19641
    },
    {
      "epoch": 0.6033852486713974,
      "grad_norm": 0.33768364787101746,
      "learning_rate": 1.5862515585028598e-05,
      "loss": 0.5138,
      "step": 19642
    },
    {
      "epoch": 0.6034159678063465,
      "grad_norm": 0.3855282962322235,
      "learning_rate": 1.5862124061163403e-05,
      "loss": 0.6025,
      "step": 19643
    },
    {
      "epoch": 0.6034466869412958,
      "grad_norm": 0.3261837661266327,
      "learning_rate": 1.586173252360681e-05,
      "loss": 0.4902,
      "step": 19644
    },
    {
      "epoch": 0.6034774060762449,
      "grad_norm": 0.3382112681865692,
      "learning_rate": 1.5861340972359728e-05,
      "loss": 0.5376,
      "step": 19645
    },
    {
      "epoch": 0.603508125211194,
      "grad_norm": 0.33056193590164185,
      "learning_rate": 1.5860949407423075e-05,
      "loss": 0.5376,
      "step": 19646
    },
    {
      "epoch": 0.6035388443461432,
      "grad_norm": 0.34258076548576355,
      "learning_rate": 1.5860557828797762e-05,
      "loss": 0.5832,
      "step": 19647
    },
    {
      "epoch": 0.6035695634810924,
      "grad_norm": 0.4458651840686798,
      "learning_rate": 1.5860166236484712e-05,
      "loss": 0.5757,
      "step": 19648
    },
    {
      "epoch": 0.6036002826160415,
      "grad_norm": 0.35673975944519043,
      "learning_rate": 1.5859774630484833e-05,
      "loss": 0.5359,
      "step": 19649
    },
    {
      "epoch": 0.6036310017509907,
      "grad_norm": 0.35447192192077637,
      "learning_rate": 1.585938301079904e-05,
      "loss": 0.6055,
      "step": 19650
    },
    {
      "epoch": 0.6036617208859398,
      "grad_norm": 0.42689234018325806,
      "learning_rate": 1.585899137742825e-05,
      "loss": 0.6134,
      "step": 19651
    },
    {
      "epoch": 0.6036924400208891,
      "grad_norm": 0.319844514131546,
      "learning_rate": 1.5858599730373378e-05,
      "loss": 0.5495,
      "step": 19652
    },
    {
      "epoch": 0.6037231591558382,
      "grad_norm": 0.37136343121528625,
      "learning_rate": 1.5858208069635336e-05,
      "loss": 0.5257,
      "step": 19653
    },
    {
      "epoch": 0.6037538782907873,
      "grad_norm": 0.3340265452861786,
      "learning_rate": 1.585781639521504e-05,
      "loss": 0.5064,
      "step": 19654
    },
    {
      "epoch": 0.6037845974257365,
      "grad_norm": 0.37029388546943665,
      "learning_rate": 1.58574247071134e-05,
      "loss": 0.6018,
      "step": 19655
    },
    {
      "epoch": 0.6038153165606857,
      "grad_norm": 0.3776484429836273,
      "learning_rate": 1.5857033005331338e-05,
      "loss": 0.5457,
      "step": 19656
    },
    {
      "epoch": 0.6038460356956348,
      "grad_norm": 0.32486724853515625,
      "learning_rate": 1.5856641289869767e-05,
      "loss": 0.5688,
      "step": 19657
    },
    {
      "epoch": 0.603876754830584,
      "grad_norm": 0.3557395935058594,
      "learning_rate": 1.58562495607296e-05,
      "loss": 0.5164,
      "step": 19658
    },
    {
      "epoch": 0.6039074739655331,
      "grad_norm": 0.34721335768699646,
      "learning_rate": 1.585585781791176e-05,
      "loss": 0.49,
      "step": 19659
    },
    {
      "epoch": 0.6039381931004822,
      "grad_norm": 0.33351588249206543,
      "learning_rate": 1.5855466061417147e-05,
      "loss": 0.5781,
      "step": 19660
    },
    {
      "epoch": 0.6039689122354315,
      "grad_norm": 0.3405664563179016,
      "learning_rate": 1.585507429124669e-05,
      "loss": 0.5524,
      "step": 19661
    },
    {
      "epoch": 0.6039996313703806,
      "grad_norm": 0.3538987934589386,
      "learning_rate": 1.5854682507401294e-05,
      "loss": 0.635,
      "step": 19662
    },
    {
      "epoch": 0.6040303505053297,
      "grad_norm": 0.37324070930480957,
      "learning_rate": 1.585429070988188e-05,
      "loss": 0.5697,
      "step": 19663
    },
    {
      "epoch": 0.604061069640279,
      "grad_norm": 0.36579573154449463,
      "learning_rate": 1.5853898898689362e-05,
      "loss": 0.6163,
      "step": 19664
    },
    {
      "epoch": 0.6040917887752281,
      "grad_norm": 0.38179725408554077,
      "learning_rate": 1.5853507073824653e-05,
      "loss": 0.5609,
      "step": 19665
    },
    {
      "epoch": 0.6041225079101773,
      "grad_norm": 0.3891889452934265,
      "learning_rate": 1.585311523528867e-05,
      "loss": 0.6334,
      "step": 19666
    },
    {
      "epoch": 0.6041532270451264,
      "grad_norm": 0.4114670157432556,
      "learning_rate": 1.5852723383082324e-05,
      "loss": 0.6413,
      "step": 19667
    },
    {
      "epoch": 0.6041839461800755,
      "grad_norm": 0.3764037787914276,
      "learning_rate": 1.585233151720654e-05,
      "loss": 0.5872,
      "step": 19668
    },
    {
      "epoch": 0.6042146653150248,
      "grad_norm": 0.40786388516426086,
      "learning_rate": 1.5851939637662225e-05,
      "loss": 0.5961,
      "step": 19669
    },
    {
      "epoch": 0.6042453844499739,
      "grad_norm": 0.36487334966659546,
      "learning_rate": 1.5851547744450292e-05,
      "loss": 0.5098,
      "step": 19670
    },
    {
      "epoch": 0.604276103584923,
      "grad_norm": 0.3727163076400757,
      "learning_rate": 1.5851155837571662e-05,
      "loss": 0.695,
      "step": 19671
    },
    {
      "epoch": 0.6043068227198722,
      "grad_norm": 0.3500899374485016,
      "learning_rate": 1.5850763917027254e-05,
      "loss": 0.5534,
      "step": 19672
    },
    {
      "epoch": 0.6043375418548214,
      "grad_norm": 0.3572900891304016,
      "learning_rate": 1.5850371982817974e-05,
      "loss": 0.5395,
      "step": 19673
    },
    {
      "epoch": 0.6043682609897705,
      "grad_norm": 0.3445829451084137,
      "learning_rate": 1.584998003494474e-05,
      "loss": 0.5593,
      "step": 19674
    },
    {
      "epoch": 0.6043989801247197,
      "grad_norm": 0.3858060836791992,
      "learning_rate": 1.584958807340847e-05,
      "loss": 0.5569,
      "step": 19675
    },
    {
      "epoch": 0.6044296992596688,
      "grad_norm": 0.303276389837265,
      "learning_rate": 1.5849196098210082e-05,
      "loss": 0.4732,
      "step": 19676
    },
    {
      "epoch": 0.6044604183946181,
      "grad_norm": 0.36313676834106445,
      "learning_rate": 1.5848804109350487e-05,
      "loss": 0.5803,
      "step": 19677
    },
    {
      "epoch": 0.6044911375295672,
      "grad_norm": 0.34246817231178284,
      "learning_rate": 1.58484121068306e-05,
      "loss": 0.589,
      "step": 19678
    },
    {
      "epoch": 0.6045218566645163,
      "grad_norm": 0.3809898793697357,
      "learning_rate": 1.584802009065134e-05,
      "loss": 0.6228,
      "step": 19679
    },
    {
      "epoch": 0.6045525757994655,
      "grad_norm": 0.3211471438407898,
      "learning_rate": 1.584762806081362e-05,
      "loss": 0.5541,
      "step": 19680
    },
    {
      "epoch": 0.6045832949344147,
      "grad_norm": 0.3397151231765747,
      "learning_rate": 1.5847236017318356e-05,
      "loss": 0.5935,
      "step": 19681
    },
    {
      "epoch": 0.6046140140693638,
      "grad_norm": 0.3576836585998535,
      "learning_rate": 1.584684396016646e-05,
      "loss": 0.566,
      "step": 19682
    },
    {
      "epoch": 0.604644733204313,
      "grad_norm": 0.3393116891384125,
      "learning_rate": 1.584645188935886e-05,
      "loss": 0.5906,
      "step": 19683
    },
    {
      "epoch": 0.6046754523392621,
      "grad_norm": 0.3868539035320282,
      "learning_rate": 1.5846059804896455e-05,
      "loss": 0.5442,
      "step": 19684
    },
    {
      "epoch": 0.6047061714742112,
      "grad_norm": 0.38078856468200684,
      "learning_rate": 1.584566770678017e-05,
      "loss": 0.6168,
      "step": 19685
    },
    {
      "epoch": 0.6047368906091605,
      "grad_norm": 0.4008997976779938,
      "learning_rate": 1.5845275595010925e-05,
      "loss": 0.5832,
      "step": 19686
    },
    {
      "epoch": 0.6047676097441096,
      "grad_norm": 0.36542171239852905,
      "learning_rate": 1.584488346958963e-05,
      "loss": 0.5246,
      "step": 19687
    },
    {
      "epoch": 0.6047983288790587,
      "grad_norm": 0.34593698382377625,
      "learning_rate": 1.58444913305172e-05,
      "loss": 0.5538,
      "step": 19688
    },
    {
      "epoch": 0.6048290480140079,
      "grad_norm": 0.48420464992523193,
      "learning_rate": 1.5844099177794547e-05,
      "loss": 0.612,
      "step": 19689
    },
    {
      "epoch": 0.6048597671489571,
      "grad_norm": 0.378679096698761,
      "learning_rate": 1.58437070114226e-05,
      "loss": 0.5027,
      "step": 19690
    },
    {
      "epoch": 0.6048904862839063,
      "grad_norm": 0.3393810987472534,
      "learning_rate": 1.5843314831402265e-05,
      "loss": 0.5311,
      "step": 19691
    },
    {
      "epoch": 0.6049212054188554,
      "grad_norm": 0.34903600811958313,
      "learning_rate": 1.584292263773446e-05,
      "loss": 0.4976,
      "step": 19692
    },
    {
      "epoch": 0.6049519245538045,
      "grad_norm": 0.3171023428440094,
      "learning_rate": 1.5842530430420095e-05,
      "loss": 0.5475,
      "step": 19693
    },
    {
      "epoch": 0.6049826436887538,
      "grad_norm": 0.3400307297706604,
      "learning_rate": 1.5842138209460097e-05,
      "loss": 0.4604,
      "step": 19694
    },
    {
      "epoch": 0.6050133628237029,
      "grad_norm": 0.3605404794216156,
      "learning_rate": 1.584174597485538e-05,
      "loss": 0.6156,
      "step": 19695
    },
    {
      "epoch": 0.605044081958652,
      "grad_norm": 0.3385610282421112,
      "learning_rate": 1.5841353726606853e-05,
      "loss": 0.5179,
      "step": 19696
    },
    {
      "epoch": 0.6050748010936012,
      "grad_norm": 0.35225188732147217,
      "learning_rate": 1.584096146471544e-05,
      "loss": 0.5564,
      "step": 19697
    },
    {
      "epoch": 0.6051055202285504,
      "grad_norm": 0.3628232181072235,
      "learning_rate": 1.584056918918205e-05,
      "loss": 0.5658,
      "step": 19698
    },
    {
      "epoch": 0.6051362393634995,
      "grad_norm": 0.4675293564796448,
      "learning_rate": 1.5840176900007606e-05,
      "loss": 0.5701,
      "step": 19699
    },
    {
      "epoch": 0.6051669584984487,
      "grad_norm": 0.3717822730541229,
      "learning_rate": 1.583978459719302e-05,
      "loss": 0.5623,
      "step": 19700
    },
    {
      "epoch": 0.6051976776333978,
      "grad_norm": 0.35834774374961853,
      "learning_rate": 1.583939228073921e-05,
      "loss": 0.5364,
      "step": 19701
    },
    {
      "epoch": 0.605228396768347,
      "grad_norm": 0.32229188084602356,
      "learning_rate": 1.583899995064709e-05,
      "loss": 0.5072,
      "step": 19702
    },
    {
      "epoch": 0.6052591159032962,
      "grad_norm": 0.37704983353614807,
      "learning_rate": 1.583860760691758e-05,
      "loss": 0.5591,
      "step": 19703
    },
    {
      "epoch": 0.6052898350382453,
      "grad_norm": 0.417023628950119,
      "learning_rate": 1.5838215249551588e-05,
      "loss": 0.5824,
      "step": 19704
    },
    {
      "epoch": 0.6053205541731945,
      "grad_norm": 0.3586321771144867,
      "learning_rate": 1.5837822878550043e-05,
      "loss": 0.5689,
      "step": 19705
    },
    {
      "epoch": 0.6053512733081436,
      "grad_norm": 0.31763002276420593,
      "learning_rate": 1.5837430493913853e-05,
      "loss": 0.5219,
      "step": 19706
    },
    {
      "epoch": 0.6053819924430928,
      "grad_norm": 0.41796398162841797,
      "learning_rate": 1.5837038095643936e-05,
      "loss": 0.5492,
      "step": 19707
    },
    {
      "epoch": 0.605412711578042,
      "grad_norm": 0.355555921792984,
      "learning_rate": 1.583664568374121e-05,
      "loss": 0.5076,
      "step": 19708
    },
    {
      "epoch": 0.6054434307129911,
      "grad_norm": 0.4371371269226074,
      "learning_rate": 1.583625325820659e-05,
      "loss": 0.5382,
      "step": 19709
    },
    {
      "epoch": 0.6054741498479402,
      "grad_norm": 0.3483518064022064,
      "learning_rate": 1.583586081904099e-05,
      "loss": 0.5949,
      "step": 19710
    },
    {
      "epoch": 0.6055048689828895,
      "grad_norm": 0.33098793029785156,
      "learning_rate": 1.5835468366245334e-05,
      "loss": 0.5457,
      "step": 19711
    },
    {
      "epoch": 0.6055355881178386,
      "grad_norm": 0.38949963450431824,
      "learning_rate": 1.583507589982053e-05,
      "loss": 0.4652,
      "step": 19712
    },
    {
      "epoch": 0.6055663072527878,
      "grad_norm": 0.3467639982700348,
      "learning_rate": 1.5834683419767502e-05,
      "loss": 0.595,
      "step": 19713
    },
    {
      "epoch": 0.6055970263877369,
      "grad_norm": 0.35216203331947327,
      "learning_rate": 1.583429092608716e-05,
      "loss": 0.6236,
      "step": 19714
    },
    {
      "epoch": 0.6056277455226861,
      "grad_norm": 0.3715200126171112,
      "learning_rate": 1.583389841878043e-05,
      "loss": 0.5936,
      "step": 19715
    },
    {
      "epoch": 0.6056584646576353,
      "grad_norm": 0.3459460437297821,
      "learning_rate": 1.583350589784822e-05,
      "loss": 0.5539,
      "step": 19716
    },
    {
      "epoch": 0.6056891837925844,
      "grad_norm": 0.34611955285072327,
      "learning_rate": 1.5833113363291443e-05,
      "loss": 0.5107,
      "step": 19717
    },
    {
      "epoch": 0.6057199029275335,
      "grad_norm": 0.32056716084480286,
      "learning_rate": 1.583272081511103e-05,
      "loss": 0.5678,
      "step": 19718
    },
    {
      "epoch": 0.6057506220624828,
      "grad_norm": 0.38228464126586914,
      "learning_rate": 1.583232825330789e-05,
      "loss": 0.5646,
      "step": 19719
    },
    {
      "epoch": 0.6057813411974319,
      "grad_norm": 0.417367160320282,
      "learning_rate": 1.5831935677882933e-05,
      "loss": 0.6463,
      "step": 19720
    },
    {
      "epoch": 0.605812060332381,
      "grad_norm": 0.3455538749694824,
      "learning_rate": 1.583154308883709e-05,
      "loss": 0.5744,
      "step": 19721
    },
    {
      "epoch": 0.6058427794673302,
      "grad_norm": 0.3226395547389984,
      "learning_rate": 1.5831150486171272e-05,
      "loss": 0.6349,
      "step": 19722
    },
    {
      "epoch": 0.6058734986022793,
      "grad_norm": 0.3261832892894745,
      "learning_rate": 1.5830757869886387e-05,
      "loss": 0.5536,
      "step": 19723
    },
    {
      "epoch": 0.6059042177372285,
      "grad_norm": 0.34588393568992615,
      "learning_rate": 1.5830365239983368e-05,
      "loss": 0.5531,
      "step": 19724
    },
    {
      "epoch": 0.6059349368721777,
      "grad_norm": 0.35835081338882446,
      "learning_rate": 1.5829972596463118e-05,
      "loss": 0.4721,
      "step": 19725
    },
    {
      "epoch": 0.6059656560071268,
      "grad_norm": 0.34687235951423645,
      "learning_rate": 1.5829579939326566e-05,
      "loss": 0.5383,
      "step": 19726
    },
    {
      "epoch": 0.605996375142076,
      "grad_norm": 0.3995806872844696,
      "learning_rate": 1.5829187268574617e-05,
      "loss": 0.5043,
      "step": 19727
    },
    {
      "epoch": 0.6060270942770252,
      "grad_norm": 0.34178483486175537,
      "learning_rate": 1.58287945842082e-05,
      "loss": 0.5144,
      "step": 19728
    },
    {
      "epoch": 0.6060578134119743,
      "grad_norm": 0.38269978761672974,
      "learning_rate": 1.5828401886228216e-05,
      "loss": 0.5412,
      "step": 19729
    },
    {
      "epoch": 0.6060885325469235,
      "grad_norm": 0.33733657002449036,
      "learning_rate": 1.58280091746356e-05,
      "loss": 0.6582,
      "step": 19730
    },
    {
      "epoch": 0.6061192516818726,
      "grad_norm": 0.3263873755931854,
      "learning_rate": 1.582761644943126e-05,
      "loss": 0.6196,
      "step": 19731
    },
    {
      "epoch": 0.6061499708168218,
      "grad_norm": 0.36087653040885925,
      "learning_rate": 1.5827223710616115e-05,
      "loss": 0.5211,
      "step": 19732
    },
    {
      "epoch": 0.606180689951771,
      "grad_norm": 0.35976606607437134,
      "learning_rate": 1.582683095819108e-05,
      "loss": 0.5664,
      "step": 19733
    },
    {
      "epoch": 0.6062114090867201,
      "grad_norm": 0.38893425464630127,
      "learning_rate": 1.582643819215708e-05,
      "loss": 0.6081,
      "step": 19734
    },
    {
      "epoch": 0.6062421282216692,
      "grad_norm": 0.34804660081863403,
      "learning_rate": 1.5826045412515024e-05,
      "loss": 0.5427,
      "step": 19735
    },
    {
      "epoch": 0.6062728473566185,
      "grad_norm": 0.32780927419662476,
      "learning_rate": 1.582565261926583e-05,
      "loss": 0.5011,
      "step": 19736
    },
    {
      "epoch": 0.6063035664915676,
      "grad_norm": 0.38502931594848633,
      "learning_rate": 1.5825259812410418e-05,
      "loss": 0.6648,
      "step": 19737
    },
    {
      "epoch": 0.6063342856265168,
      "grad_norm": 0.33615604043006897,
      "learning_rate": 1.5824866991949702e-05,
      "loss": 0.5624,
      "step": 19738
    },
    {
      "epoch": 0.6063650047614659,
      "grad_norm": 0.3423157036304474,
      "learning_rate": 1.582447415788461e-05,
      "loss": 0.6433,
      "step": 19739
    },
    {
      "epoch": 0.606395723896415,
      "grad_norm": 0.40935060381889343,
      "learning_rate": 1.5824081310216047e-05,
      "loss": 0.5507,
      "step": 19740
    },
    {
      "epoch": 0.6064264430313643,
      "grad_norm": 0.3377135694026947,
      "learning_rate": 1.5823688448944934e-05,
      "loss": 0.5957,
      "step": 19741
    },
    {
      "epoch": 0.6064571621663134,
      "grad_norm": 0.40993282198905945,
      "learning_rate": 1.5823295574072193e-05,
      "loss": 0.5616,
      "step": 19742
    },
    {
      "epoch": 0.6064878813012625,
      "grad_norm": 0.4279015362262726,
      "learning_rate": 1.5822902685598736e-05,
      "loss": 0.5451,
      "step": 19743
    },
    {
      "epoch": 0.6065186004362118,
      "grad_norm": 0.5883047580718994,
      "learning_rate": 1.5822509783525488e-05,
      "loss": 0.576,
      "step": 19744
    },
    {
      "epoch": 0.6065493195711609,
      "grad_norm": 0.36939364671707153,
      "learning_rate": 1.5822116867853355e-05,
      "loss": 0.5796,
      "step": 19745
    },
    {
      "epoch": 0.60658003870611,
      "grad_norm": 0.3599061071872711,
      "learning_rate": 1.5821723938583268e-05,
      "loss": 0.5957,
      "step": 19746
    },
    {
      "epoch": 0.6066107578410592,
      "grad_norm": 0.349224716424942,
      "learning_rate": 1.582133099571613e-05,
      "loss": 0.4662,
      "step": 19747
    },
    {
      "epoch": 0.6066414769760083,
      "grad_norm": 0.3611404597759247,
      "learning_rate": 1.5820938039252872e-05,
      "loss": 0.5619,
      "step": 19748
    },
    {
      "epoch": 0.6066721961109575,
      "grad_norm": 0.6689884662628174,
      "learning_rate": 1.5820545069194408e-05,
      "loss": 0.5362,
      "step": 19749
    },
    {
      "epoch": 0.6067029152459067,
      "grad_norm": 0.36642390489578247,
      "learning_rate": 1.5820152085541654e-05,
      "loss": 0.4928,
      "step": 19750
    },
    {
      "epoch": 0.6067336343808558,
      "grad_norm": 0.3209627866744995,
      "learning_rate": 1.5819759088295526e-05,
      "loss": 0.5359,
      "step": 19751
    },
    {
      "epoch": 0.606764353515805,
      "grad_norm": 0.35106751322746277,
      "learning_rate": 1.5819366077456945e-05,
      "loss": 0.6167,
      "step": 19752
    },
    {
      "epoch": 0.6067950726507542,
      "grad_norm": 0.33478984236717224,
      "learning_rate": 1.581897305302683e-05,
      "loss": 0.5321,
      "step": 19753
    },
    {
      "epoch": 0.6068257917857033,
      "grad_norm": 0.3575763702392578,
      "learning_rate": 1.5818580015006097e-05,
      "loss": 0.5615,
      "step": 19754
    },
    {
      "epoch": 0.6068565109206525,
      "grad_norm": 0.3838667869567871,
      "learning_rate": 1.581818696339566e-05,
      "loss": 0.544,
      "step": 19755
    },
    {
      "epoch": 0.6068872300556016,
      "grad_norm": 0.4412974417209625,
      "learning_rate": 1.581779389819644e-05,
      "loss": 0.5198,
      "step": 19756
    },
    {
      "epoch": 0.6069179491905508,
      "grad_norm": 0.32985755801200867,
      "learning_rate": 1.5817400819409362e-05,
      "loss": 0.4984,
      "step": 19757
    },
    {
      "epoch": 0.6069486683255,
      "grad_norm": 0.33730363845825195,
      "learning_rate": 1.581700772703534e-05,
      "loss": 0.5301,
      "step": 19758
    },
    {
      "epoch": 0.6069793874604491,
      "grad_norm": 0.3722679316997528,
      "learning_rate": 1.5816614621075282e-05,
      "loss": 0.539,
      "step": 19759
    },
    {
      "epoch": 0.6070101065953982,
      "grad_norm": 0.37636712193489075,
      "learning_rate": 1.581622150153012e-05,
      "loss": 0.5549,
      "step": 19760
    },
    {
      "epoch": 0.6070408257303475,
      "grad_norm": 0.34745413064956665,
      "learning_rate": 1.5815828368400767e-05,
      "loss": 0.4613,
      "step": 19761
    },
    {
      "epoch": 0.6070715448652966,
      "grad_norm": 0.3982921242713928,
      "learning_rate": 1.5815435221688136e-05,
      "loss": 0.6005,
      "step": 19762
    },
    {
      "epoch": 0.6071022640002458,
      "grad_norm": 0.3420640826225281,
      "learning_rate": 1.5815042061393153e-05,
      "loss": 0.5858,
      "step": 19763
    },
    {
      "epoch": 0.6071329831351949,
      "grad_norm": 0.3569534718990326,
      "learning_rate": 1.5814648887516732e-05,
      "loss": 0.544,
      "step": 19764
    },
    {
      "epoch": 0.607163702270144,
      "grad_norm": 0.3505745530128479,
      "learning_rate": 1.5814255700059794e-05,
      "loss": 0.5601,
      "step": 19765
    },
    {
      "epoch": 0.6071944214050933,
      "grad_norm": 0.48391300439834595,
      "learning_rate": 1.581386249902325e-05,
      "loss": 0.5423,
      "step": 19766
    },
    {
      "epoch": 0.6072251405400424,
      "grad_norm": 0.3519800007343292,
      "learning_rate": 1.5813469284408028e-05,
      "loss": 0.5898,
      "step": 19767
    },
    {
      "epoch": 0.6072558596749915,
      "grad_norm": 0.34945523738861084,
      "learning_rate": 1.5813076056215043e-05,
      "loss": 0.5162,
      "step": 19768
    },
    {
      "epoch": 0.6072865788099407,
      "grad_norm": 0.33413073420524597,
      "learning_rate": 1.5812682814445217e-05,
      "loss": 0.5215,
      "step": 19769
    },
    {
      "epoch": 0.6073172979448899,
      "grad_norm": 0.3683869242668152,
      "learning_rate": 1.581228955909946e-05,
      "loss": 0.643,
      "step": 19770
    },
    {
      "epoch": 0.607348017079839,
      "grad_norm": 0.4410287141799927,
      "learning_rate": 1.5811896290178694e-05,
      "loss": 0.5491,
      "step": 19771
    },
    {
      "epoch": 0.6073787362147882,
      "grad_norm": 0.35006460547447205,
      "learning_rate": 1.581150300768384e-05,
      "loss": 0.5371,
      "step": 19772
    },
    {
      "epoch": 0.6074094553497373,
      "grad_norm": 0.7770568132400513,
      "learning_rate": 1.5811109711615814e-05,
      "loss": 0.5649,
      "step": 19773
    },
    {
      "epoch": 0.6074401744846865,
      "grad_norm": 0.3541722297668457,
      "learning_rate": 1.5810716401975536e-05,
      "loss": 0.4831,
      "step": 19774
    },
    {
      "epoch": 0.6074708936196357,
      "grad_norm": 0.36694714426994324,
      "learning_rate": 1.5810323078763926e-05,
      "loss": 0.5889,
      "step": 19775
    },
    {
      "epoch": 0.6075016127545848,
      "grad_norm": 0.34842827916145325,
      "learning_rate": 1.5809929741981897e-05,
      "loss": 0.6275,
      "step": 19776
    },
    {
      "epoch": 0.607532331889534,
      "grad_norm": 0.3350789248943329,
      "learning_rate": 1.5809536391630372e-05,
      "loss": 0.6149,
      "step": 19777
    },
    {
      "epoch": 0.6075630510244832,
      "grad_norm": 0.3613494634628296,
      "learning_rate": 1.580914302771027e-05,
      "loss": 0.6079,
      "step": 19778
    },
    {
      "epoch": 0.6075937701594323,
      "grad_norm": 0.3529644012451172,
      "learning_rate": 1.5808749650222508e-05,
      "loss": 0.5147,
      "step": 19779
    },
    {
      "epoch": 0.6076244892943815,
      "grad_norm": 0.364911824464798,
      "learning_rate": 1.5808356259168008e-05,
      "loss": 0.5877,
      "step": 19780
    },
    {
      "epoch": 0.6076552084293306,
      "grad_norm": 0.46895480155944824,
      "learning_rate": 1.5807962854547682e-05,
      "loss": 0.5505,
      "step": 19781
    },
    {
      "epoch": 0.6076859275642797,
      "grad_norm": 0.30724653601646423,
      "learning_rate": 1.5807569436362456e-05,
      "loss": 0.5419,
      "step": 19782
    },
    {
      "epoch": 0.607716646699229,
      "grad_norm": 0.36756470799446106,
      "learning_rate": 1.5807176004613247e-05,
      "loss": 0.5357,
      "step": 19783
    },
    {
      "epoch": 0.6077473658341781,
      "grad_norm": 0.565044105052948,
      "learning_rate": 1.580678255930097e-05,
      "loss": 0.476,
      "step": 19784
    },
    {
      "epoch": 0.6077780849691272,
      "grad_norm": 0.31421878933906555,
      "learning_rate": 1.580638910042655e-05,
      "loss": 0.5016,
      "step": 19785
    },
    {
      "epoch": 0.6078088041040764,
      "grad_norm": 0.37179315090179443,
      "learning_rate": 1.58059956279909e-05,
      "loss": 0.6395,
      "step": 19786
    },
    {
      "epoch": 0.6078395232390256,
      "grad_norm": 0.3237500488758087,
      "learning_rate": 1.5805602141994942e-05,
      "loss": 0.6021,
      "step": 19787
    },
    {
      "epoch": 0.6078702423739748,
      "grad_norm": 0.35266607999801636,
      "learning_rate": 1.5805208642439597e-05,
      "loss": 0.5587,
      "step": 19788
    },
    {
      "epoch": 0.6079009615089239,
      "grad_norm": 0.3380683660507202,
      "learning_rate": 1.580481512932578e-05,
      "loss": 0.5044,
      "step": 19789
    },
    {
      "epoch": 0.607931680643873,
      "grad_norm": 0.4284604787826538,
      "learning_rate": 1.5804421602654413e-05,
      "loss": 0.6295,
      "step": 19790
    },
    {
      "epoch": 0.6079623997788223,
      "grad_norm": 0.3612566292285919,
      "learning_rate": 1.580402806242641e-05,
      "loss": 0.5322,
      "step": 19791
    },
    {
      "epoch": 0.6079931189137714,
      "grad_norm": 0.3554583191871643,
      "learning_rate": 1.5803634508642697e-05,
      "loss": 0.5159,
      "step": 19792
    },
    {
      "epoch": 0.6080238380487205,
      "grad_norm": 0.38387542963027954,
      "learning_rate": 1.580324094130419e-05,
      "loss": 0.4771,
      "step": 19793
    },
    {
      "epoch": 0.6080545571836697,
      "grad_norm": 0.3524211645126343,
      "learning_rate": 1.5802847360411813e-05,
      "loss": 0.553,
      "step": 19794
    },
    {
      "epoch": 0.6080852763186189,
      "grad_norm": 0.3502418100833893,
      "learning_rate": 1.5802453765966475e-05,
      "loss": 0.4896,
      "step": 19795
    },
    {
      "epoch": 0.608115995453568,
      "grad_norm": 0.3509482443332672,
      "learning_rate": 1.58020601579691e-05,
      "loss": 0.5681,
      "step": 19796
    },
    {
      "epoch": 0.6081467145885172,
      "grad_norm": 0.3629661798477173,
      "learning_rate": 1.580166653642061e-05,
      "loss": 0.5896,
      "step": 19797
    },
    {
      "epoch": 0.6081774337234663,
      "grad_norm": 0.35665059089660645,
      "learning_rate": 1.5801272901321926e-05,
      "loss": 0.5407,
      "step": 19798
    },
    {
      "epoch": 0.6082081528584155,
      "grad_norm": 0.34110361337661743,
      "learning_rate": 1.5800879252673962e-05,
      "loss": 0.5509,
      "step": 19799
    },
    {
      "epoch": 0.6082388719933647,
      "grad_norm": 0.38904085755348206,
      "learning_rate": 1.580048559047764e-05,
      "loss": 0.5334,
      "step": 19800
    },
    {
      "epoch": 0.6082695911283138,
      "grad_norm": 0.38293707370758057,
      "learning_rate": 1.580009191473388e-05,
      "loss": 0.6344,
      "step": 19801
    },
    {
      "epoch": 0.608300310263263,
      "grad_norm": 0.3594493269920349,
      "learning_rate": 1.5799698225443594e-05,
      "loss": 0.5369,
      "step": 19802
    },
    {
      "epoch": 0.6083310293982122,
      "grad_norm": 0.3906310200691223,
      "learning_rate": 1.579930452260771e-05,
      "loss": 0.5431,
      "step": 19803
    },
    {
      "epoch": 0.6083617485331613,
      "grad_norm": 0.3557775318622589,
      "learning_rate": 1.5798910806227148e-05,
      "loss": 0.545,
      "step": 19804
    },
    {
      "epoch": 0.6083924676681105,
      "grad_norm": 0.36759063601493835,
      "learning_rate": 1.5798517076302823e-05,
      "loss": 0.5397,
      "step": 19805
    },
    {
      "epoch": 0.6084231868030596,
      "grad_norm": 0.3393675684928894,
      "learning_rate": 1.5798123332835657e-05,
      "loss": 0.5649,
      "step": 19806
    },
    {
      "epoch": 0.6084539059380087,
      "grad_norm": 0.41923341155052185,
      "learning_rate": 1.579772957582657e-05,
      "loss": 0.5796,
      "step": 19807
    },
    {
      "epoch": 0.608484625072958,
      "grad_norm": 0.3500669598579407,
      "learning_rate": 1.579733580527648e-05,
      "loss": 0.5829,
      "step": 19808
    },
    {
      "epoch": 0.6085153442079071,
      "grad_norm": 0.3766281306743622,
      "learning_rate": 1.579694202118631e-05,
      "loss": 0.5653,
      "step": 19809
    },
    {
      "epoch": 0.6085460633428562,
      "grad_norm": 0.3366462290287018,
      "learning_rate": 1.579654822355697e-05,
      "loss": 0.4908,
      "step": 19810
    },
    {
      "epoch": 0.6085767824778054,
      "grad_norm": 0.36889857053756714,
      "learning_rate": 1.5796154412389392e-05,
      "loss": 0.5332,
      "step": 19811
    },
    {
      "epoch": 0.6086075016127546,
      "grad_norm": 0.3871638774871826,
      "learning_rate": 1.5795760587684492e-05,
      "loss": 0.5968,
      "step": 19812
    },
    {
      "epoch": 0.6086382207477038,
      "grad_norm": 0.3424086570739746,
      "learning_rate": 1.5795366749443183e-05,
      "loss": 0.5617,
      "step": 19813
    },
    {
      "epoch": 0.6086689398826529,
      "grad_norm": 0.3721122741699219,
      "learning_rate": 1.5794972897666395e-05,
      "loss": 0.595,
      "step": 19814
    },
    {
      "epoch": 0.608699659017602,
      "grad_norm": 0.34665486216545105,
      "learning_rate": 1.579457903235504e-05,
      "loss": 0.6471,
      "step": 19815
    },
    {
      "epoch": 0.6087303781525513,
      "grad_norm": 0.35875269770622253,
      "learning_rate": 1.5794185153510045e-05,
      "loss": 0.5603,
      "step": 19816
    },
    {
      "epoch": 0.6087610972875004,
      "grad_norm": 0.32894447445869446,
      "learning_rate": 1.5793791261132322e-05,
      "loss": 0.5575,
      "step": 19817
    },
    {
      "epoch": 0.6087918164224495,
      "grad_norm": 0.3417474627494812,
      "learning_rate": 1.5793397355222798e-05,
      "loss": 0.5387,
      "step": 19818
    },
    {
      "epoch": 0.6088225355573987,
      "grad_norm": 0.32956233620643616,
      "learning_rate": 1.579300343578239e-05,
      "loss": 0.5942,
      "step": 19819
    },
    {
      "epoch": 0.6088532546923479,
      "grad_norm": 0.3468533754348755,
      "learning_rate": 1.579260950281201e-05,
      "loss": 0.5102,
      "step": 19820
    },
    {
      "epoch": 0.608883973827297,
      "grad_norm": 0.3534393012523651,
      "learning_rate": 1.5792215556312594e-05,
      "loss": 0.5683,
      "step": 19821
    },
    {
      "epoch": 0.6089146929622462,
      "grad_norm": 0.3607156276702881,
      "learning_rate": 1.579182159628505e-05,
      "loss": 0.6761,
      "step": 19822
    },
    {
      "epoch": 0.6089454120971953,
      "grad_norm": 0.38264086842536926,
      "learning_rate": 1.5791427622730308e-05,
      "loss": 0.5794,
      "step": 19823
    },
    {
      "epoch": 0.6089761312321446,
      "grad_norm": 0.34277036786079407,
      "learning_rate": 1.5791033635649274e-05,
      "loss": 0.5512,
      "step": 19824
    },
    {
      "epoch": 0.6090068503670937,
      "grad_norm": 0.36320945620536804,
      "learning_rate": 1.5790639635042882e-05,
      "loss": 0.4809,
      "step": 19825
    },
    {
      "epoch": 0.6090375695020428,
      "grad_norm": 0.675413191318512,
      "learning_rate": 1.5790245620912047e-05,
      "loss": 0.6218,
      "step": 19826
    },
    {
      "epoch": 0.609068288636992,
      "grad_norm": 0.3330702483654022,
      "learning_rate": 1.5789851593257687e-05,
      "loss": 0.6029,
      "step": 19827
    },
    {
      "epoch": 0.6090990077719411,
      "grad_norm": 0.3688007891178131,
      "learning_rate": 1.578945755208072e-05,
      "loss": 0.5675,
      "step": 19828
    },
    {
      "epoch": 0.6091297269068903,
      "grad_norm": 1.106933832168579,
      "learning_rate": 1.578906349738208e-05,
      "loss": 0.542,
      "step": 19829
    },
    {
      "epoch": 0.6091604460418395,
      "grad_norm": 0.40283748507499695,
      "learning_rate": 1.5788669429162672e-05,
      "loss": 0.502,
      "step": 19830
    },
    {
      "epoch": 0.6091911651767886,
      "grad_norm": 0.3739638328552246,
      "learning_rate": 1.5788275347423426e-05,
      "loss": 0.5436,
      "step": 19831
    },
    {
      "epoch": 0.6092218843117377,
      "grad_norm": 0.3684109151363373,
      "learning_rate": 1.5787881252165256e-05,
      "loss": 0.5922,
      "step": 19832
    },
    {
      "epoch": 0.609252603446687,
      "grad_norm": 0.39276060461997986,
      "learning_rate": 1.5787487143389083e-05,
      "loss": 0.6168,
      "step": 19833
    },
    {
      "epoch": 0.6092833225816361,
      "grad_norm": 0.37226665019989014,
      "learning_rate": 1.578709302109583e-05,
      "loss": 0.6223,
      "step": 19834
    },
    {
      "epoch": 0.6093140417165852,
      "grad_norm": 0.3413839638233185,
      "learning_rate": 1.5786698885286423e-05,
      "loss": 0.5495,
      "step": 19835
    },
    {
      "epoch": 0.6093447608515344,
      "grad_norm": 0.3321729004383087,
      "learning_rate": 1.578630473596177e-05,
      "loss": 0.6389,
      "step": 19836
    },
    {
      "epoch": 0.6093754799864836,
      "grad_norm": 0.4061351716518402,
      "learning_rate": 1.5785910573122802e-05,
      "loss": 0.5728,
      "step": 19837
    },
    {
      "epoch": 0.6094061991214328,
      "grad_norm": 0.3650919795036316,
      "learning_rate": 1.5785516396770436e-05,
      "loss": 0.6158,
      "step": 19838
    },
    {
      "epoch": 0.6094369182563819,
      "grad_norm": 0.38190916180610657,
      "learning_rate": 1.5785122206905588e-05,
      "loss": 0.6092,
      "step": 19839
    },
    {
      "epoch": 0.609467637391331,
      "grad_norm": 0.3649922013282776,
      "learning_rate": 1.5784728003529188e-05,
      "loss": 0.5472,
      "step": 19840
    },
    {
      "epoch": 0.6094983565262803,
      "grad_norm": 0.35533496737480164,
      "learning_rate": 1.578433378664215e-05,
      "loss": 0.6253,
      "step": 19841
    },
    {
      "epoch": 0.6095290756612294,
      "grad_norm": 0.382029265165329,
      "learning_rate": 1.5783939556245394e-05,
      "loss": 0.5635,
      "step": 19842
    },
    {
      "epoch": 0.6095597947961785,
      "grad_norm": 0.3371339440345764,
      "learning_rate": 1.5783545312339844e-05,
      "loss": 0.5406,
      "step": 19843
    },
    {
      "epoch": 0.6095905139311277,
      "grad_norm": 0.3823716938495636,
      "learning_rate": 1.578315105492642e-05,
      "loss": 0.5633,
      "step": 19844
    },
    {
      "epoch": 0.6096212330660769,
      "grad_norm": 0.3692004382610321,
      "learning_rate": 1.578275678400605e-05,
      "loss": 0.5513,
      "step": 19845
    },
    {
      "epoch": 0.609651952201026,
      "grad_norm": 0.33973750472068787,
      "learning_rate": 1.5782362499579642e-05,
      "loss": 0.5601,
      "step": 19846
    },
    {
      "epoch": 0.6096826713359752,
      "grad_norm": 0.39466920495033264,
      "learning_rate": 1.578196820164812e-05,
      "loss": 0.5738,
      "step": 19847
    },
    {
      "epoch": 0.6097133904709243,
      "grad_norm": 0.34401455521583557,
      "learning_rate": 1.578157389021241e-05,
      "loss": 0.4981,
      "step": 19848
    },
    {
      "epoch": 0.6097441096058736,
      "grad_norm": 0.3082047402858734,
      "learning_rate": 1.578117956527343e-05,
      "loss": 0.5179,
      "step": 19849
    },
    {
      "epoch": 0.6097748287408227,
      "grad_norm": 0.3996541202068329,
      "learning_rate": 1.57807852268321e-05,
      "loss": 0.6074,
      "step": 19850
    },
    {
      "epoch": 0.6098055478757718,
      "grad_norm": 0.3881242871284485,
      "learning_rate": 1.578039087488935e-05,
      "loss": 0.5689,
      "step": 19851
    },
    {
      "epoch": 0.609836267010721,
      "grad_norm": 0.35472625494003296,
      "learning_rate": 1.5779996509446086e-05,
      "loss": 0.5011,
      "step": 19852
    },
    {
      "epoch": 0.6098669861456701,
      "grad_norm": 0.34079527854919434,
      "learning_rate": 1.5779602130503236e-05,
      "loss": 0.5118,
      "step": 19853
    },
    {
      "epoch": 0.6098977052806193,
      "grad_norm": 0.34223851561546326,
      "learning_rate": 1.5779207738061724e-05,
      "loss": 0.6276,
      "step": 19854
    },
    {
      "epoch": 0.6099284244155685,
      "grad_norm": 0.3362572491168976,
      "learning_rate": 1.577881333212247e-05,
      "loss": 0.5835,
      "step": 19855
    },
    {
      "epoch": 0.6099591435505176,
      "grad_norm": 0.34296995401382446,
      "learning_rate": 1.577841891268639e-05,
      "loss": 0.6094,
      "step": 19856
    },
    {
      "epoch": 0.6099898626854667,
      "grad_norm": 0.34161829948425293,
      "learning_rate": 1.577802447975441e-05,
      "loss": 0.6221,
      "step": 19857
    },
    {
      "epoch": 0.610020581820416,
      "grad_norm": 0.3522222936153412,
      "learning_rate": 1.5777630033327455e-05,
      "loss": 0.6403,
      "step": 19858
    },
    {
      "epoch": 0.6100513009553651,
      "grad_norm": 0.35925522446632385,
      "learning_rate": 1.5777235573406436e-05,
      "loss": 0.5845,
      "step": 19859
    },
    {
      "epoch": 0.6100820200903142,
      "grad_norm": 0.6133700013160706,
      "learning_rate": 1.577684109999228e-05,
      "loss": 0.5949,
      "step": 19860
    },
    {
      "epoch": 0.6101127392252634,
      "grad_norm": 0.3830329477787018,
      "learning_rate": 1.577644661308591e-05,
      "loss": 0.5553,
      "step": 19861
    },
    {
      "epoch": 0.6101434583602126,
      "grad_norm": 0.3425469994544983,
      "learning_rate": 1.5776052112688245e-05,
      "loss": 0.4779,
      "step": 19862
    },
    {
      "epoch": 0.6101741774951618,
      "grad_norm": 0.38654065132141113,
      "learning_rate": 1.5775657598800212e-05,
      "loss": 0.4757,
      "step": 19863
    },
    {
      "epoch": 0.6102048966301109,
      "grad_norm": 0.40215864777565,
      "learning_rate": 1.577526307142272e-05,
      "loss": 0.6452,
      "step": 19864
    },
    {
      "epoch": 0.61023561576506,
      "grad_norm": 0.336574912071228,
      "learning_rate": 1.57748685305567e-05,
      "loss": 0.4808,
      "step": 19865
    },
    {
      "epoch": 0.6102663349000093,
      "grad_norm": 0.3824908435344696,
      "learning_rate": 1.5774473976203072e-05,
      "loss": 0.5365,
      "step": 19866
    },
    {
      "epoch": 0.6102970540349584,
      "grad_norm": 0.3559548854827881,
      "learning_rate": 1.5774079408362757e-05,
      "loss": 0.6324,
      "step": 19867
    },
    {
      "epoch": 0.6103277731699075,
      "grad_norm": 1.0108847618103027,
      "learning_rate": 1.577368482703668e-05,
      "loss": 0.5943,
      "step": 19868
    },
    {
      "epoch": 0.6103584923048567,
      "grad_norm": 0.43300172686576843,
      "learning_rate": 1.577329023222575e-05,
      "loss": 0.5444,
      "step": 19869
    },
    {
      "epoch": 0.6103892114398058,
      "grad_norm": 0.3527476489543915,
      "learning_rate": 1.5772895623930905e-05,
      "loss": 0.5266,
      "step": 19870
    },
    {
      "epoch": 0.610419930574755,
      "grad_norm": 0.36126962304115295,
      "learning_rate": 1.5772501002153054e-05,
      "loss": 0.5455,
      "step": 19871
    },
    {
      "epoch": 0.6104506497097042,
      "grad_norm": 0.357204794883728,
      "learning_rate": 1.5772106366893125e-05,
      "loss": 0.5535,
      "step": 19872
    },
    {
      "epoch": 0.6104813688446533,
      "grad_norm": 0.3657701909542084,
      "learning_rate": 1.577171171815204e-05,
      "loss": 0.549,
      "step": 19873
    },
    {
      "epoch": 0.6105120879796025,
      "grad_norm": 0.37166136503219604,
      "learning_rate": 1.577131705593072e-05,
      "loss": 0.5666,
      "step": 19874
    },
    {
      "epoch": 0.6105428071145517,
      "grad_norm": 0.364071249961853,
      "learning_rate": 1.5770922380230083e-05,
      "loss": 0.6377,
      "step": 19875
    },
    {
      "epoch": 0.6105735262495008,
      "grad_norm": 0.3653603792190552,
      "learning_rate": 1.5770527691051056e-05,
      "loss": 0.543,
      "step": 19876
    },
    {
      "epoch": 0.61060424538445,
      "grad_norm": 0.46002912521362305,
      "learning_rate": 1.5770132988394555e-05,
      "loss": 0.5482,
      "step": 19877
    },
    {
      "epoch": 0.6106349645193991,
      "grad_norm": 0.33316266536712646,
      "learning_rate": 1.576973827226151e-05,
      "loss": 0.5217,
      "step": 19878
    },
    {
      "epoch": 0.6106656836543483,
      "grad_norm": 0.41018831729888916,
      "learning_rate": 1.5769343542652836e-05,
      "loss": 0.5601,
      "step": 19879
    },
    {
      "epoch": 0.6106964027892975,
      "grad_norm": 0.3519958257675171,
      "learning_rate": 1.5768948799569458e-05,
      "loss": 0.5064,
      "step": 19880
    },
    {
      "epoch": 0.6107271219242466,
      "grad_norm": 0.3893750309944153,
      "learning_rate": 1.57685540430123e-05,
      "loss": 0.5267,
      "step": 19881
    },
    {
      "epoch": 0.6107578410591957,
      "grad_norm": 0.3630312979221344,
      "learning_rate": 1.5768159272982277e-05,
      "loss": 0.5201,
      "step": 19882
    },
    {
      "epoch": 0.610788560194145,
      "grad_norm": 0.36598706245422363,
      "learning_rate": 1.5767764489480316e-05,
      "loss": 0.5862,
      "step": 19883
    },
    {
      "epoch": 0.6108192793290941,
      "grad_norm": 0.36506620049476624,
      "learning_rate": 1.576736969250734e-05,
      "loss": 0.5199,
      "step": 19884
    },
    {
      "epoch": 0.6108499984640432,
      "grad_norm": 0.3354564607143402,
      "learning_rate": 1.5766974882064267e-05,
      "loss": 0.5803,
      "step": 19885
    },
    {
      "epoch": 0.6108807175989924,
      "grad_norm": 0.3472549319267273,
      "learning_rate": 1.576658005815202e-05,
      "loss": 0.5085,
      "step": 19886
    },
    {
      "epoch": 0.6109114367339415,
      "grad_norm": 0.39523881673812866,
      "learning_rate": 1.5766185220771525e-05,
      "loss": 0.6209,
      "step": 19887
    },
    {
      "epoch": 0.6109421558688908,
      "grad_norm": 0.3443721830844879,
      "learning_rate": 1.5765790369923703e-05,
      "loss": 0.6493,
      "step": 19888
    },
    {
      "epoch": 0.6109728750038399,
      "grad_norm": 0.40198472142219543,
      "learning_rate": 1.5765395505609473e-05,
      "loss": 0.6031,
      "step": 19889
    },
    {
      "epoch": 0.611003594138789,
      "grad_norm": 0.32337382435798645,
      "learning_rate": 1.576500062782976e-05,
      "loss": 0.4997,
      "step": 19890
    },
    {
      "epoch": 0.6110343132737382,
      "grad_norm": 0.4124335050582886,
      "learning_rate": 1.5764605736585484e-05,
      "loss": 0.6136,
      "step": 19891
    },
    {
      "epoch": 0.6110650324086874,
      "grad_norm": 0.356300950050354,
      "learning_rate": 1.576421083187757e-05,
      "loss": 0.57,
      "step": 19892
    },
    {
      "epoch": 0.6110957515436365,
      "grad_norm": 0.33871734142303467,
      "learning_rate": 1.576381591370694e-05,
      "loss": 0.5786,
      "step": 19893
    },
    {
      "epoch": 0.6111264706785857,
      "grad_norm": 0.34623876214027405,
      "learning_rate": 1.5763420982074512e-05,
      "loss": 0.6579,
      "step": 19894
    },
    {
      "epoch": 0.6111571898135348,
      "grad_norm": 0.3643794357776642,
      "learning_rate": 1.5763026036981214e-05,
      "loss": 0.65,
      "step": 19895
    },
    {
      "epoch": 0.611187908948484,
      "grad_norm": 0.3172047734260559,
      "learning_rate": 1.5762631078427965e-05,
      "loss": 0.529,
      "step": 19896
    },
    {
      "epoch": 0.6112186280834332,
      "grad_norm": 0.3470968008041382,
      "learning_rate": 1.576223610641569e-05,
      "loss": 0.5496,
      "step": 19897
    },
    {
      "epoch": 0.6112493472183823,
      "grad_norm": 0.33341002464294434,
      "learning_rate": 1.576184112094531e-05,
      "loss": 0.5849,
      "step": 19898
    },
    {
      "epoch": 0.6112800663533315,
      "grad_norm": 0.4321824014186859,
      "learning_rate": 1.576144612201775e-05,
      "loss": 0.5552,
      "step": 19899
    },
    {
      "epoch": 0.6113107854882807,
      "grad_norm": 0.3325037658214569,
      "learning_rate": 1.5761051109633927e-05,
      "loss": 0.5957,
      "step": 19900
    },
    {
      "epoch": 0.6113415046232298,
      "grad_norm": 0.33826586604118347,
      "learning_rate": 1.5760656083794767e-05,
      "loss": 0.561,
      "step": 19901
    },
    {
      "epoch": 0.611372223758179,
      "grad_norm": 0.4060676693916321,
      "learning_rate": 1.5760261044501196e-05,
      "loss": 0.5316,
      "step": 19902
    },
    {
      "epoch": 0.6114029428931281,
      "grad_norm": 0.3196074962615967,
      "learning_rate": 1.575986599175413e-05,
      "loss": 0.5367,
      "step": 19903
    },
    {
      "epoch": 0.6114336620280773,
      "grad_norm": 0.3730468153953552,
      "learning_rate": 1.5759470925554492e-05,
      "loss": 0.6211,
      "step": 19904
    },
    {
      "epoch": 0.6114643811630265,
      "grad_norm": 0.357700914144516,
      "learning_rate": 1.575907584590321e-05,
      "loss": 0.5842,
      "step": 19905
    },
    {
      "epoch": 0.6114951002979756,
      "grad_norm": 0.339065819978714,
      "learning_rate": 1.5758680752801207e-05,
      "loss": 0.531,
      "step": 19906
    },
    {
      "epoch": 0.6115258194329247,
      "grad_norm": 0.34992748498916626,
      "learning_rate": 1.5758285646249398e-05,
      "loss": 0.5637,
      "step": 19907
    },
    {
      "epoch": 0.611556538567874,
      "grad_norm": 0.40914684534072876,
      "learning_rate": 1.5757890526248712e-05,
      "loss": 0.5787,
      "step": 19908
    },
    {
      "epoch": 0.6115872577028231,
      "grad_norm": 0.36202892661094666,
      "learning_rate": 1.5757495392800073e-05,
      "loss": 0.5974,
      "step": 19909
    },
    {
      "epoch": 0.6116179768377723,
      "grad_norm": 0.36433157324790955,
      "learning_rate": 1.57571002459044e-05,
      "loss": 0.555,
      "step": 19910
    },
    {
      "epoch": 0.6116486959727214,
      "grad_norm": 0.317096084356308,
      "learning_rate": 1.5756705085562618e-05,
      "loss": 0.5562,
      "step": 19911
    },
    {
      "epoch": 0.6116794151076705,
      "grad_norm": 0.33264651894569397,
      "learning_rate": 1.5756309911775644e-05,
      "loss": 0.5804,
      "step": 19912
    },
    {
      "epoch": 0.6117101342426198,
      "grad_norm": 0.37515613436698914,
      "learning_rate": 1.575591472454441e-05,
      "loss": 0.526,
      "step": 19913
    },
    {
      "epoch": 0.6117408533775689,
      "grad_norm": 0.3323467969894409,
      "learning_rate": 1.575551952386984e-05,
      "loss": 0.514,
      "step": 19914
    },
    {
      "epoch": 0.611771572512518,
      "grad_norm": 0.4672061800956726,
      "learning_rate": 1.5755124309752847e-05,
      "loss": 0.5755,
      "step": 19915
    },
    {
      "epoch": 0.6118022916474672,
      "grad_norm": 0.34963905811309814,
      "learning_rate": 1.575472908219436e-05,
      "loss": 0.5649,
      "step": 19916
    },
    {
      "epoch": 0.6118330107824164,
      "grad_norm": 0.3521571755409241,
      "learning_rate": 1.57543338411953e-05,
      "loss": 0.5748,
      "step": 19917
    },
    {
      "epoch": 0.6118637299173655,
      "grad_norm": 0.8136649131774902,
      "learning_rate": 1.5753938586756598e-05,
      "loss": 0.4901,
      "step": 19918
    },
    {
      "epoch": 0.6118944490523147,
      "grad_norm": 0.3494507372379303,
      "learning_rate": 1.575354331887916e-05,
      "loss": 0.6635,
      "step": 19919
    },
    {
      "epoch": 0.6119251681872638,
      "grad_norm": 0.5848416090011597,
      "learning_rate": 1.5753148037563927e-05,
      "loss": 0.4647,
      "step": 19920
    },
    {
      "epoch": 0.611955887322213,
      "grad_norm": 0.34671348333358765,
      "learning_rate": 1.5752752742811816e-05,
      "loss": 0.562,
      "step": 19921
    },
    {
      "epoch": 0.6119866064571622,
      "grad_norm": 0.48257046937942505,
      "learning_rate": 1.5752357434623743e-05,
      "loss": 0.6218,
      "step": 19922
    },
    {
      "epoch": 0.6120173255921113,
      "grad_norm": 0.3560166358947754,
      "learning_rate": 1.5751962113000643e-05,
      "loss": 0.5497,
      "step": 19923
    },
    {
      "epoch": 0.6120480447270605,
      "grad_norm": 0.3286709785461426,
      "learning_rate": 1.575156677794343e-05,
      "loss": 0.5683,
      "step": 19924
    },
    {
      "epoch": 0.6120787638620097,
      "grad_norm": 0.3781934380531311,
      "learning_rate": 1.5751171429453033e-05,
      "loss": 0.594,
      "step": 19925
    },
    {
      "epoch": 0.6121094829969588,
      "grad_norm": 0.3823683559894562,
      "learning_rate": 1.5750776067530375e-05,
      "loss": 0.5114,
      "step": 19926
    },
    {
      "epoch": 0.612140202131908,
      "grad_norm": 0.38837921619415283,
      "learning_rate": 1.5750380692176378e-05,
      "loss": 0.5676,
      "step": 19927
    },
    {
      "epoch": 0.6121709212668571,
      "grad_norm": 0.33566924929618835,
      "learning_rate": 1.574998530339196e-05,
      "loss": 0.5284,
      "step": 19928
    },
    {
      "epoch": 0.6122016404018062,
      "grad_norm": 0.3519568145275116,
      "learning_rate": 1.5749589901178054e-05,
      "loss": 0.5389,
      "step": 19929
    },
    {
      "epoch": 0.6122323595367555,
      "grad_norm": 0.3531639575958252,
      "learning_rate": 1.5749194485535577e-05,
      "loss": 0.6047,
      "step": 19930
    },
    {
      "epoch": 0.6122630786717046,
      "grad_norm": 0.4201236367225647,
      "learning_rate": 1.5748799056465457e-05,
      "loss": 0.5381,
      "step": 19931
    },
    {
      "epoch": 0.6122937978066537,
      "grad_norm": 0.3444674015045166,
      "learning_rate": 1.5748403613968615e-05,
      "loss": 0.6067,
      "step": 19932
    },
    {
      "epoch": 0.612324516941603,
      "grad_norm": 0.4024088382720947,
      "learning_rate": 1.5748008158045974e-05,
      "loss": 0.6003,
      "step": 19933
    },
    {
      "epoch": 0.6123552360765521,
      "grad_norm": 0.37967559695243835,
      "learning_rate": 1.574761268869846e-05,
      "loss": 0.6122,
      "step": 19934
    },
    {
      "epoch": 0.6123859552115013,
      "grad_norm": 0.35605645179748535,
      "learning_rate": 1.574721720592699e-05,
      "loss": 0.5816,
      "step": 19935
    },
    {
      "epoch": 0.6124166743464504,
      "grad_norm": 0.35675400495529175,
      "learning_rate": 1.5746821709732502e-05,
      "loss": 0.604,
      "step": 19936
    },
    {
      "epoch": 0.6124473934813995,
      "grad_norm": 0.3573191165924072,
      "learning_rate": 1.5746426200115904e-05,
      "loss": 0.5383,
      "step": 19937
    },
    {
      "epoch": 0.6124781126163488,
      "grad_norm": 0.806117594242096,
      "learning_rate": 1.5746030677078124e-05,
      "loss": 0.5321,
      "step": 19938
    },
    {
      "epoch": 0.6125088317512979,
      "grad_norm": 0.6000556945800781,
      "learning_rate": 1.5745635140620096e-05,
      "loss": 0.5234,
      "step": 19939
    },
    {
      "epoch": 0.612539550886247,
      "grad_norm": 0.4902452230453491,
      "learning_rate": 1.5745239590742732e-05,
      "loss": 0.62,
      "step": 19940
    },
    {
      "epoch": 0.6125702700211962,
      "grad_norm": 0.3083290457725525,
      "learning_rate": 1.574484402744696e-05,
      "loss": 0.4604,
      "step": 19941
    },
    {
      "epoch": 0.6126009891561454,
      "grad_norm": 0.3228245973587036,
      "learning_rate": 1.57444484507337e-05,
      "loss": 0.5655,
      "step": 19942
    },
    {
      "epoch": 0.6126317082910945,
      "grad_norm": 0.3698170483112335,
      "learning_rate": 1.5744052860603885e-05,
      "loss": 0.6088,
      "step": 19943
    },
    {
      "epoch": 0.6126624274260437,
      "grad_norm": 0.34574347734451294,
      "learning_rate": 1.574365725705843e-05,
      "loss": 0.5729,
      "step": 19944
    },
    {
      "epoch": 0.6126931465609928,
      "grad_norm": 0.5571406483650208,
      "learning_rate": 1.5743261640098264e-05,
      "loss": 0.601,
      "step": 19945
    },
    {
      "epoch": 0.612723865695942,
      "grad_norm": 0.43689531087875366,
      "learning_rate": 1.5742866009724306e-05,
      "loss": 0.5274,
      "step": 19946
    },
    {
      "epoch": 0.6127545848308912,
      "grad_norm": 0.3343958258628845,
      "learning_rate": 1.5742470365937486e-05,
      "loss": 0.531,
      "step": 19947
    },
    {
      "epoch": 0.6127853039658403,
      "grad_norm": 0.3979825973510742,
      "learning_rate": 1.5742074708738723e-05,
      "loss": 0.5469,
      "step": 19948
    },
    {
      "epoch": 0.6128160231007895,
      "grad_norm": 0.34698253870010376,
      "learning_rate": 1.574167903812895e-05,
      "loss": 0.5612,
      "step": 19949
    },
    {
      "epoch": 0.6128467422357387,
      "grad_norm": 0.31067365407943726,
      "learning_rate": 1.5741283354109077e-05,
      "loss": 0.5876,
      "step": 19950
    },
    {
      "epoch": 0.6128774613706878,
      "grad_norm": 0.3723515570163727,
      "learning_rate": 1.574088765668004e-05,
      "loss": 0.5097,
      "step": 19951
    },
    {
      "epoch": 0.612908180505637,
      "grad_norm": 0.370000958442688,
      "learning_rate": 1.574049194584276e-05,
      "loss": 0.5183,
      "step": 19952
    },
    {
      "epoch": 0.6129388996405861,
      "grad_norm": 0.35642749071121216,
      "learning_rate": 1.5740096221598155e-05,
      "loss": 0.5713,
      "step": 19953
    },
    {
      "epoch": 0.6129696187755352,
      "grad_norm": 0.33782655000686646,
      "learning_rate": 1.573970048394716e-05,
      "loss": 0.5323,
      "step": 19954
    },
    {
      "epoch": 0.6130003379104845,
      "grad_norm": 0.3753032982349396,
      "learning_rate": 1.573930473289069e-05,
      "loss": 0.5382,
      "step": 19955
    },
    {
      "epoch": 0.6130310570454336,
      "grad_norm": 0.41736266016960144,
      "learning_rate": 1.5738908968429677e-05,
      "loss": 0.5728,
      "step": 19956
    },
    {
      "epoch": 0.6130617761803827,
      "grad_norm": 0.3491252064704895,
      "learning_rate": 1.5738513190565036e-05,
      "loss": 0.6229,
      "step": 19957
    },
    {
      "epoch": 0.6130924953153319,
      "grad_norm": 0.39773958921432495,
      "learning_rate": 1.57381173992977e-05,
      "loss": 0.604,
      "step": 19958
    },
    {
      "epoch": 0.6131232144502811,
      "grad_norm": 0.38413313031196594,
      "learning_rate": 1.573772159462859e-05,
      "loss": 0.561,
      "step": 19959
    },
    {
      "epoch": 0.6131539335852303,
      "grad_norm": 0.3457111418247223,
      "learning_rate": 1.5737325776558628e-05,
      "loss": 0.6013,
      "step": 19960
    },
    {
      "epoch": 0.6131846527201794,
      "grad_norm": 0.3455888628959656,
      "learning_rate": 1.5736929945088745e-05,
      "loss": 0.5794,
      "step": 19961
    },
    {
      "epoch": 0.6132153718551285,
      "grad_norm": 0.3261467218399048,
      "learning_rate": 1.5736534100219855e-05,
      "loss": 0.4006,
      "step": 19962
    },
    {
      "epoch": 0.6132460909900778,
      "grad_norm": 0.37541282176971436,
      "learning_rate": 1.5736138241952895e-05,
      "loss": 0.5394,
      "step": 19963
    },
    {
      "epoch": 0.6132768101250269,
      "grad_norm": 0.3303651809692383,
      "learning_rate": 1.573574237028878e-05,
      "loss": 0.5378,
      "step": 19964
    },
    {
      "epoch": 0.613307529259976,
      "grad_norm": 0.3823045790195465,
      "learning_rate": 1.5735346485228442e-05,
      "loss": 0.6751,
      "step": 19965
    },
    {
      "epoch": 0.6133382483949252,
      "grad_norm": 0.39475372433662415,
      "learning_rate": 1.57349505867728e-05,
      "loss": 0.5493,
      "step": 19966
    },
    {
      "epoch": 0.6133689675298744,
      "grad_norm": 0.3741797208786011,
      "learning_rate": 1.573455467492278e-05,
      "loss": 0.597,
      "step": 19967
    },
    {
      "epoch": 0.6133996866648235,
      "grad_norm": 0.3579210340976715,
      "learning_rate": 1.5734158749679305e-05,
      "loss": 0.4737,
      "step": 19968
    },
    {
      "epoch": 0.6134304057997727,
      "grad_norm": 0.33073604106903076,
      "learning_rate": 1.57337628110433e-05,
      "loss": 0.535,
      "step": 19969
    },
    {
      "epoch": 0.6134611249347218,
      "grad_norm": 0.3171059787273407,
      "learning_rate": 1.5733366859015697e-05,
      "loss": 0.6,
      "step": 19970
    },
    {
      "epoch": 0.6134918440696709,
      "grad_norm": 0.3644452393054962,
      "learning_rate": 1.5732970893597416e-05,
      "loss": 0.4964,
      "step": 19971
    },
    {
      "epoch": 0.6135225632046202,
      "grad_norm": 0.34469467401504517,
      "learning_rate": 1.5732574914789377e-05,
      "loss": 0.4496,
      "step": 19972
    },
    {
      "epoch": 0.6135532823395693,
      "grad_norm": 0.3425200283527374,
      "learning_rate": 1.5732178922592513e-05,
      "loss": 0.5259,
      "step": 19973
    },
    {
      "epoch": 0.6135840014745185,
      "grad_norm": 0.3572368323802948,
      "learning_rate": 1.573178291700774e-05,
      "loss": 0.5738,
      "step": 19974
    },
    {
      "epoch": 0.6136147206094676,
      "grad_norm": 0.3848574757575989,
      "learning_rate": 1.573138689803599e-05,
      "loss": 0.5502,
      "step": 19975
    },
    {
      "epoch": 0.6136454397444168,
      "grad_norm": 0.35092154145240784,
      "learning_rate": 1.5730990865678187e-05,
      "loss": 0.4939,
      "step": 19976
    },
    {
      "epoch": 0.613676158879366,
      "grad_norm": 0.3639199137687683,
      "learning_rate": 1.5730594819935254e-05,
      "loss": 0.504,
      "step": 19977
    },
    {
      "epoch": 0.6137068780143151,
      "grad_norm": 0.6488158106803894,
      "learning_rate": 1.5730198760808116e-05,
      "loss": 0.5043,
      "step": 19978
    },
    {
      "epoch": 0.6137375971492642,
      "grad_norm": 0.34508103132247925,
      "learning_rate": 1.5729802688297698e-05,
      "loss": 0.4959,
      "step": 19979
    },
    {
      "epoch": 0.6137683162842135,
      "grad_norm": 0.3514493405818939,
      "learning_rate": 1.5729406602404925e-05,
      "loss": 0.5173,
      "step": 19980
    },
    {
      "epoch": 0.6137990354191626,
      "grad_norm": 0.3800249397754669,
      "learning_rate": 1.5729010503130725e-05,
      "loss": 0.5628,
      "step": 19981
    },
    {
      "epoch": 0.6138297545541117,
      "grad_norm": 0.3495163917541504,
      "learning_rate": 1.572861439047602e-05,
      "loss": 0.5311,
      "step": 19982
    },
    {
      "epoch": 0.6138604736890609,
      "grad_norm": 0.36389702558517456,
      "learning_rate": 1.5728218264441733e-05,
      "loss": 0.5586,
      "step": 19983
    },
    {
      "epoch": 0.6138911928240101,
      "grad_norm": 0.3634556233882904,
      "learning_rate": 1.5727822125028794e-05,
      "loss": 0.5621,
      "step": 19984
    },
    {
      "epoch": 0.6139219119589593,
      "grad_norm": 0.4390878975391388,
      "learning_rate": 1.5727425972238128e-05,
      "loss": 0.4798,
      "step": 19985
    },
    {
      "epoch": 0.6139526310939084,
      "grad_norm": 0.3315463960170746,
      "learning_rate": 1.572702980607066e-05,
      "loss": 0.4953,
      "step": 19986
    },
    {
      "epoch": 0.6139833502288575,
      "grad_norm": 0.35774537920951843,
      "learning_rate": 1.572663362652731e-05,
      "loss": 0.5277,
      "step": 19987
    },
    {
      "epoch": 0.6140140693638068,
      "grad_norm": 0.5335140228271484,
      "learning_rate": 1.572623743360901e-05,
      "loss": 0.5237,
      "step": 19988
    },
    {
      "epoch": 0.6140447884987559,
      "grad_norm": 0.32507818937301636,
      "learning_rate": 1.572584122731668e-05,
      "loss": 0.5666,
      "step": 19989
    },
    {
      "epoch": 0.614075507633705,
      "grad_norm": 0.37318718433380127,
      "learning_rate": 1.572544500765125e-05,
      "loss": 0.5034,
      "step": 19990
    },
    {
      "epoch": 0.6141062267686542,
      "grad_norm": 0.388094037771225,
      "learning_rate": 1.5725048774613644e-05,
      "loss": 0.5632,
      "step": 19991
    },
    {
      "epoch": 0.6141369459036033,
      "grad_norm": 0.35396715998649597,
      "learning_rate": 1.5724652528204783e-05,
      "loss": 0.5362,
      "step": 19992
    },
    {
      "epoch": 0.6141676650385525,
      "grad_norm": 0.34719449281692505,
      "learning_rate": 1.5724256268425602e-05,
      "loss": 0.5286,
      "step": 19993
    },
    {
      "epoch": 0.6141983841735017,
      "grad_norm": 0.37881559133529663,
      "learning_rate": 1.5723859995277016e-05,
      "loss": 0.619,
      "step": 19994
    },
    {
      "epoch": 0.6142291033084508,
      "grad_norm": 0.3377190828323364,
      "learning_rate": 1.5723463708759957e-05,
      "loss": 0.5534,
      "step": 19995
    },
    {
      "epoch": 0.6142598224433999,
      "grad_norm": 0.3332573473453522,
      "learning_rate": 1.5723067408875348e-05,
      "loss": 0.5538,
      "step": 19996
    },
    {
      "epoch": 0.6142905415783492,
      "grad_norm": 0.38024193048477173,
      "learning_rate": 1.572267109562412e-05,
      "loss": 0.5582,
      "step": 19997
    },
    {
      "epoch": 0.6143212607132983,
      "grad_norm": 0.6023377180099487,
      "learning_rate": 1.5722274769007185e-05,
      "loss": 0.5158,
      "step": 19998
    },
    {
      "epoch": 0.6143519798482475,
      "grad_norm": 0.4823945164680481,
      "learning_rate": 1.5721878429025484e-05,
      "loss": 0.5783,
      "step": 19999
    },
    {
      "epoch": 0.6143826989831966,
      "grad_norm": 0.3267231583595276,
      "learning_rate": 1.5721482075679933e-05,
      "loss": 0.4951,
      "step": 20000
    },
    {
      "epoch": 0.6144134181181458,
      "grad_norm": 0.33363470435142517,
      "learning_rate": 1.5721085708971462e-05,
      "loss": 0.5473,
      "step": 20001
    },
    {
      "epoch": 0.614444137253095,
      "grad_norm": 0.36676302552223206,
      "learning_rate": 1.5720689328900996e-05,
      "loss": 0.555,
      "step": 20002
    },
    {
      "epoch": 0.6144748563880441,
      "grad_norm": 0.35385662317276,
      "learning_rate": 1.5720292935469462e-05,
      "loss": 0.5679,
      "step": 20003
    },
    {
      "epoch": 0.6145055755229932,
      "grad_norm": 0.3523530960083008,
      "learning_rate": 1.5719896528677787e-05,
      "loss": 0.5981,
      "step": 20004
    },
    {
      "epoch": 0.6145362946579425,
      "grad_norm": 0.3575359582901001,
      "learning_rate": 1.5719500108526887e-05,
      "loss": 0.5462,
      "step": 20005
    },
    {
      "epoch": 0.6145670137928916,
      "grad_norm": 0.3873613476753235,
      "learning_rate": 1.57191036750177e-05,
      "loss": 0.5478,
      "step": 20006
    },
    {
      "epoch": 0.6145977329278407,
      "grad_norm": 0.5025413036346436,
      "learning_rate": 1.5718707228151145e-05,
      "loss": 0.5482,
      "step": 20007
    },
    {
      "epoch": 0.6146284520627899,
      "grad_norm": 0.5378583073616028,
      "learning_rate": 1.5718310767928153e-05,
      "loss": 0.5503,
      "step": 20008
    },
    {
      "epoch": 0.614659171197739,
      "grad_norm": 0.5225047469139099,
      "learning_rate": 1.5717914294349644e-05,
      "loss": 0.5811,
      "step": 20009
    },
    {
      "epoch": 0.6146898903326883,
      "grad_norm": 0.3624952435493469,
      "learning_rate": 1.571751780741655e-05,
      "loss": 0.6126,
      "step": 20010
    },
    {
      "epoch": 0.6147206094676374,
      "grad_norm": 0.35226601362228394,
      "learning_rate": 1.571712130712979e-05,
      "loss": 0.5659,
      "step": 20011
    },
    {
      "epoch": 0.6147513286025865,
      "grad_norm": 0.354672372341156,
      "learning_rate": 1.571672479349029e-05,
      "loss": 0.562,
      "step": 20012
    },
    {
      "epoch": 0.6147820477375358,
      "grad_norm": 0.33172741532325745,
      "learning_rate": 1.571632826649899e-05,
      "loss": 0.5389,
      "step": 20013
    },
    {
      "epoch": 0.6148127668724849,
      "grad_norm": 0.32504263520240784,
      "learning_rate": 1.57159317261568e-05,
      "loss": 0.5824,
      "step": 20014
    },
    {
      "epoch": 0.614843486007434,
      "grad_norm": 0.325534462928772,
      "learning_rate": 1.5715535172464654e-05,
      "loss": 0.5676,
      "step": 20015
    },
    {
      "epoch": 0.6148742051423832,
      "grad_norm": 0.39362186193466187,
      "learning_rate": 1.5715138605423476e-05,
      "loss": 0.5926,
      "step": 20016
    },
    {
      "epoch": 0.6149049242773323,
      "grad_norm": 0.35501164197921753,
      "learning_rate": 1.571474202503419e-05,
      "loss": 0.5959,
      "step": 20017
    },
    {
      "epoch": 0.6149356434122815,
      "grad_norm": 0.3957788050174713,
      "learning_rate": 1.5714345431297728e-05,
      "loss": 0.5461,
      "step": 20018
    },
    {
      "epoch": 0.6149663625472307,
      "grad_norm": 0.3934948444366455,
      "learning_rate": 1.571394882421501e-05,
      "loss": 0.5535,
      "step": 20019
    },
    {
      "epoch": 0.6149970816821798,
      "grad_norm": 0.36712780594825745,
      "learning_rate": 1.571355220378697e-05,
      "loss": 0.5452,
      "step": 20020
    },
    {
      "epoch": 0.615027800817129,
      "grad_norm": 0.3699999451637268,
      "learning_rate": 1.571315557001453e-05,
      "loss": 0.5911,
      "step": 20021
    },
    {
      "epoch": 0.6150585199520782,
      "grad_norm": 0.3840087652206421,
      "learning_rate": 1.5712758922898613e-05,
      "loss": 0.4885,
      "step": 20022
    },
    {
      "epoch": 0.6150892390870273,
      "grad_norm": 0.40485963225364685,
      "learning_rate": 1.571236226244015e-05,
      "loss": 0.5149,
      "step": 20023
    },
    {
      "epoch": 0.6151199582219765,
      "grad_norm": 0.3650969862937927,
      "learning_rate": 1.5711965588640064e-05,
      "loss": 0.5385,
      "step": 20024
    },
    {
      "epoch": 0.6151506773569256,
      "grad_norm": 0.3590003550052643,
      "learning_rate": 1.5711568901499283e-05,
      "loss": 0.5079,
      "step": 20025
    },
    {
      "epoch": 0.6151813964918748,
      "grad_norm": 0.3837849795818329,
      "learning_rate": 1.571117220101874e-05,
      "loss": 0.5272,
      "step": 20026
    },
    {
      "epoch": 0.615212115626824,
      "grad_norm": 0.37979063391685486,
      "learning_rate": 1.571077548719935e-05,
      "loss": 0.5975,
      "step": 20027
    },
    {
      "epoch": 0.6152428347617731,
      "grad_norm": 0.35939693450927734,
      "learning_rate": 1.5710378760042045e-05,
      "loss": 0.5255,
      "step": 20028
    },
    {
      "epoch": 0.6152735538967222,
      "grad_norm": 0.8815918564796448,
      "learning_rate": 1.5709982019547753e-05,
      "loss": 0.5488,
      "step": 20029
    },
    {
      "epoch": 0.6153042730316715,
      "grad_norm": 0.36259591579437256,
      "learning_rate": 1.57095852657174e-05,
      "loss": 0.5557,
      "step": 20030
    },
    {
      "epoch": 0.6153349921666206,
      "grad_norm": 0.4119247496128082,
      "learning_rate": 1.570918849855191e-05,
      "loss": 0.5654,
      "step": 20031
    },
    {
      "epoch": 0.6153657113015697,
      "grad_norm": 0.5384522080421448,
      "learning_rate": 1.5708791718052215e-05,
      "loss": 0.448,
      "step": 20032
    },
    {
      "epoch": 0.6153964304365189,
      "grad_norm": 0.34670814871788025,
      "learning_rate": 1.5708394924219235e-05,
      "loss": 0.5591,
      "step": 20033
    },
    {
      "epoch": 0.615427149571468,
      "grad_norm": 0.3570784330368042,
      "learning_rate": 1.57079981170539e-05,
      "loss": 0.5255,
      "step": 20034
    },
    {
      "epoch": 0.6154578687064173,
      "grad_norm": 0.40354785323143005,
      "learning_rate": 1.570760129655714e-05,
      "loss": 0.5965,
      "step": 20035
    },
    {
      "epoch": 0.6154885878413664,
      "grad_norm": 0.3293945789337158,
      "learning_rate": 1.5707204462729873e-05,
      "loss": 0.5957,
      "step": 20036
    },
    {
      "epoch": 0.6155193069763155,
      "grad_norm": 0.36629441380500793,
      "learning_rate": 1.5706807615573035e-05,
      "loss": 0.516,
      "step": 20037
    },
    {
      "epoch": 0.6155500261112647,
      "grad_norm": 0.4048144817352295,
      "learning_rate": 1.5706410755087548e-05,
      "loss": 0.6246,
      "step": 20038
    },
    {
      "epoch": 0.6155807452462139,
      "grad_norm": 0.36063429713249207,
      "learning_rate": 1.5706013881274343e-05,
      "loss": 0.5827,
      "step": 20039
    },
    {
      "epoch": 0.615611464381163,
      "grad_norm": 0.3235717713832855,
      "learning_rate": 1.570561699413434e-05,
      "loss": 0.4724,
      "step": 20040
    },
    {
      "epoch": 0.6156421835161122,
      "grad_norm": 0.3705417215824127,
      "learning_rate": 1.5705220093668472e-05,
      "loss": 0.5425,
      "step": 20041
    },
    {
      "epoch": 0.6156729026510613,
      "grad_norm": 0.3352258503437042,
      "learning_rate": 1.5704823179877664e-05,
      "loss": 0.5893,
      "step": 20042
    },
    {
      "epoch": 0.6157036217860105,
      "grad_norm": 0.34131917357444763,
      "learning_rate": 1.5704426252762844e-05,
      "loss": 0.6585,
      "step": 20043
    },
    {
      "epoch": 0.6157343409209597,
      "grad_norm": 0.4153641164302826,
      "learning_rate": 1.5704029312324934e-05,
      "loss": 0.6488,
      "step": 20044
    },
    {
      "epoch": 0.6157650600559088,
      "grad_norm": 0.35076287388801575,
      "learning_rate": 1.570363235856487e-05,
      "loss": 0.5646,
      "step": 20045
    },
    {
      "epoch": 0.615795779190858,
      "grad_norm": 0.36791232228279114,
      "learning_rate": 1.5703235391483573e-05,
      "loss": 0.5416,
      "step": 20046
    },
    {
      "epoch": 0.6158264983258072,
      "grad_norm": 0.3328336477279663,
      "learning_rate": 1.570283841108197e-05,
      "loss": 0.5232,
      "step": 20047
    },
    {
      "epoch": 0.6158572174607563,
      "grad_norm": 0.34191474318504333,
      "learning_rate": 1.5702441417360993e-05,
      "loss": 0.5364,
      "step": 20048
    },
    {
      "epoch": 0.6158879365957055,
      "grad_norm": 0.34130430221557617,
      "learning_rate": 1.570204441032156e-05,
      "loss": 0.4932,
      "step": 20049
    },
    {
      "epoch": 0.6159186557306546,
      "grad_norm": 0.3539690673351288,
      "learning_rate": 1.5701647389964612e-05,
      "loss": 0.5926,
      "step": 20050
    },
    {
      "epoch": 0.6159493748656037,
      "grad_norm": 0.37565550208091736,
      "learning_rate": 1.570125035629106e-05,
      "loss": 0.4949,
      "step": 20051
    },
    {
      "epoch": 0.615980094000553,
      "grad_norm": 0.3752390444278717,
      "learning_rate": 1.5700853309301845e-05,
      "loss": 0.5439,
      "step": 20052
    },
    {
      "epoch": 0.6160108131355021,
      "grad_norm": 0.3942031264305115,
      "learning_rate": 1.5700456248997887e-05,
      "loss": 0.546,
      "step": 20053
    },
    {
      "epoch": 0.6160415322704512,
      "grad_norm": 0.3656398057937622,
      "learning_rate": 1.5700059175380117e-05,
      "loss": 0.5503,
      "step": 20054
    },
    {
      "epoch": 0.6160722514054005,
      "grad_norm": 0.3633913993835449,
      "learning_rate": 1.5699662088449458e-05,
      "loss": 0.5114,
      "step": 20055
    },
    {
      "epoch": 0.6161029705403496,
      "grad_norm": 0.34658706188201904,
      "learning_rate": 1.5699264988206843e-05,
      "loss": 0.4909,
      "step": 20056
    },
    {
      "epoch": 0.6161336896752987,
      "grad_norm": 0.38993069529533386,
      "learning_rate": 1.5698867874653197e-05,
      "loss": 0.6057,
      "step": 20057
    },
    {
      "epoch": 0.6161644088102479,
      "grad_norm": 0.41222715377807617,
      "learning_rate": 1.569847074778944e-05,
      "loss": 0.5977,
      "step": 20058
    },
    {
      "epoch": 0.616195127945197,
      "grad_norm": 0.4034956395626068,
      "learning_rate": 1.5698073607616514e-05,
      "loss": 0.5837,
      "step": 20059
    },
    {
      "epoch": 0.6162258470801463,
      "grad_norm": 0.4304681122303009,
      "learning_rate": 1.5697676454135337e-05,
      "loss": 0.6142,
      "step": 20060
    },
    {
      "epoch": 0.6162565662150954,
      "grad_norm": 0.34312090277671814,
      "learning_rate": 1.569727928734684e-05,
      "loss": 0.5667,
      "step": 20061
    },
    {
      "epoch": 0.6162872853500445,
      "grad_norm": 0.375232458114624,
      "learning_rate": 1.5696882107251948e-05,
      "loss": 0.4916,
      "step": 20062
    },
    {
      "epoch": 0.6163180044849937,
      "grad_norm": 0.39199256896972656,
      "learning_rate": 1.569648491385159e-05,
      "loss": 0.6329,
      "step": 20063
    },
    {
      "epoch": 0.6163487236199429,
      "grad_norm": 0.4091860353946686,
      "learning_rate": 1.569608770714669e-05,
      "loss": 0.4965,
      "step": 20064
    },
    {
      "epoch": 0.616379442754892,
      "grad_norm": 0.40206378698349,
      "learning_rate": 1.5695690487138184e-05,
      "loss": 0.5083,
      "step": 20065
    },
    {
      "epoch": 0.6164101618898412,
      "grad_norm": 0.4098055958747864,
      "learning_rate": 1.5695293253827e-05,
      "loss": 0.5579,
      "step": 20066
    },
    {
      "epoch": 0.6164408810247903,
      "grad_norm": 0.43076208233833313,
      "learning_rate": 1.569489600721405e-05,
      "loss": 0.5797,
      "step": 20067
    },
    {
      "epoch": 0.6164716001597395,
      "grad_norm": 0.31374025344848633,
      "learning_rate": 1.569449874730028e-05,
      "loss": 0.621,
      "step": 20068
    },
    {
      "epoch": 0.6165023192946887,
      "grad_norm": 0.3453384339809418,
      "learning_rate": 1.5694101474086606e-05,
      "loss": 0.5119,
      "step": 20069
    },
    {
      "epoch": 0.6165330384296378,
      "grad_norm": 0.3184613883495331,
      "learning_rate": 1.5693704187573965e-05,
      "loss": 0.5192,
      "step": 20070
    },
    {
      "epoch": 0.616563757564587,
      "grad_norm": 0.3263596296310425,
      "learning_rate": 1.5693306887763276e-05,
      "loss": 0.5996,
      "step": 20071
    },
    {
      "epoch": 0.6165944766995362,
      "grad_norm": 0.33698633313179016,
      "learning_rate": 1.5692909574655474e-05,
      "loss": 0.5505,
      "step": 20072
    },
    {
      "epoch": 0.6166251958344853,
      "grad_norm": 0.45911043882369995,
      "learning_rate": 1.569251224825148e-05,
      "loss": 0.6072,
      "step": 20073
    },
    {
      "epoch": 0.6166559149694345,
      "grad_norm": 0.48256418108940125,
      "learning_rate": 1.569211490855223e-05,
      "loss": 0.5244,
      "step": 20074
    },
    {
      "epoch": 0.6166866341043836,
      "grad_norm": 0.3918696939945221,
      "learning_rate": 1.5691717555558648e-05,
      "loss": 0.4473,
      "step": 20075
    },
    {
      "epoch": 0.6167173532393327,
      "grad_norm": 0.40557125210762024,
      "learning_rate": 1.5691320189271658e-05,
      "loss": 0.5768,
      "step": 20076
    },
    {
      "epoch": 0.616748072374282,
      "grad_norm": 0.3452286422252655,
      "learning_rate": 1.5690922809692197e-05,
      "loss": 0.556,
      "step": 20077
    },
    {
      "epoch": 0.6167787915092311,
      "grad_norm": 0.3621424734592438,
      "learning_rate": 1.5690525416821186e-05,
      "loss": 0.5931,
      "step": 20078
    },
    {
      "epoch": 0.6168095106441802,
      "grad_norm": 0.34673982858657837,
      "learning_rate": 1.5690128010659558e-05,
      "loss": 0.5616,
      "step": 20079
    },
    {
      "epoch": 0.6168402297791294,
      "grad_norm": 0.3507561981678009,
      "learning_rate": 1.5689730591208237e-05,
      "loss": 0.5735,
      "step": 20080
    },
    {
      "epoch": 0.6168709489140786,
      "grad_norm": 0.3650291860103607,
      "learning_rate": 1.568933315846815e-05,
      "loss": 0.5143,
      "step": 20081
    },
    {
      "epoch": 0.6169016680490277,
      "grad_norm": 0.377253919839859,
      "learning_rate": 1.5688935712440236e-05,
      "loss": 0.5821,
      "step": 20082
    },
    {
      "epoch": 0.6169323871839769,
      "grad_norm": 0.370964378118515,
      "learning_rate": 1.568853825312541e-05,
      "loss": 0.5806,
      "step": 20083
    },
    {
      "epoch": 0.616963106318926,
      "grad_norm": 0.380140095949173,
      "learning_rate": 1.5688140780524604e-05,
      "loss": 0.5195,
      "step": 20084
    },
    {
      "epoch": 0.6169938254538753,
      "grad_norm": 0.37320399284362793,
      "learning_rate": 1.5687743294638747e-05,
      "loss": 0.5185,
      "step": 20085
    },
    {
      "epoch": 0.6170245445888244,
      "grad_norm": 0.3763851523399353,
      "learning_rate": 1.5687345795468774e-05,
      "loss": 0.5326,
      "step": 20086
    },
    {
      "epoch": 0.6170552637237735,
      "grad_norm": 0.36061838269233704,
      "learning_rate": 1.5686948283015604e-05,
      "loss": 0.5645,
      "step": 20087
    },
    {
      "epoch": 0.6170859828587227,
      "grad_norm": 0.3443211317062378,
      "learning_rate": 1.568655075728017e-05,
      "loss": 0.5614,
      "step": 20088
    },
    {
      "epoch": 0.6171167019936719,
      "grad_norm": 0.3644794821739197,
      "learning_rate": 1.56861532182634e-05,
      "loss": 0.5322,
      "step": 20089
    },
    {
      "epoch": 0.617147421128621,
      "grad_norm": 0.3591267168521881,
      "learning_rate": 1.568575566596622e-05,
      "loss": 0.4729,
      "step": 20090
    },
    {
      "epoch": 0.6171781402635702,
      "grad_norm": 0.3833564817905426,
      "learning_rate": 1.568535810038956e-05,
      "loss": 0.5952,
      "step": 20091
    },
    {
      "epoch": 0.6172088593985193,
      "grad_norm": 0.370572566986084,
      "learning_rate": 1.5684960521534354e-05,
      "loss": 0.5313,
      "step": 20092
    },
    {
      "epoch": 0.6172395785334684,
      "grad_norm": 0.3982078731060028,
      "learning_rate": 1.5684562929401523e-05,
      "loss": 0.5766,
      "step": 20093
    },
    {
      "epoch": 0.6172702976684177,
      "grad_norm": 0.8025742769241333,
      "learning_rate": 1.5684165323991995e-05,
      "loss": 0.616,
      "step": 20094
    },
    {
      "epoch": 0.6173010168033668,
      "grad_norm": 0.3218934237957001,
      "learning_rate": 1.5683767705306707e-05,
      "loss": 0.584,
      "step": 20095
    },
    {
      "epoch": 0.617331735938316,
      "grad_norm": 0.3523132801055908,
      "learning_rate": 1.568337007334658e-05,
      "loss": 0.5709,
      "step": 20096
    },
    {
      "epoch": 0.6173624550732651,
      "grad_norm": 0.394745409488678,
      "learning_rate": 1.5682972428112548e-05,
      "loss": 0.6346,
      "step": 20097
    },
    {
      "epoch": 0.6173931742082143,
      "grad_norm": 0.40425875782966614,
      "learning_rate": 1.5682574769605534e-05,
      "loss": 0.5423,
      "step": 20098
    },
    {
      "epoch": 0.6174238933431635,
      "grad_norm": 0.40671876072883606,
      "learning_rate": 1.568217709782647e-05,
      "loss": 0.6354,
      "step": 20099
    },
    {
      "epoch": 0.6174546124781126,
      "grad_norm": 0.5964885354042053,
      "learning_rate": 1.5681779412776284e-05,
      "loss": 0.5168,
      "step": 20100
    },
    {
      "epoch": 0.6174853316130617,
      "grad_norm": 0.3435389995574951,
      "learning_rate": 1.5681381714455906e-05,
      "loss": 0.5486,
      "step": 20101
    },
    {
      "epoch": 0.617516050748011,
      "grad_norm": 0.3771516680717468,
      "learning_rate": 1.5680984002866265e-05,
      "loss": 0.6155,
      "step": 20102
    },
    {
      "epoch": 0.6175467698829601,
      "grad_norm": 0.35459277033805847,
      "learning_rate": 1.568058627800829e-05,
      "loss": 0.5525,
      "step": 20103
    },
    {
      "epoch": 0.6175774890179092,
      "grad_norm": 0.3624761700630188,
      "learning_rate": 1.5680188539882907e-05,
      "loss": 0.5567,
      "step": 20104
    },
    {
      "epoch": 0.6176082081528584,
      "grad_norm": 0.354975163936615,
      "learning_rate": 1.5679790788491046e-05,
      "loss": 0.4782,
      "step": 20105
    },
    {
      "epoch": 0.6176389272878076,
      "grad_norm": 0.3419898450374603,
      "learning_rate": 1.567939302383364e-05,
      "loss": 0.6445,
      "step": 20106
    },
    {
      "epoch": 0.6176696464227568,
      "grad_norm": 1.0901061296463013,
      "learning_rate": 1.5678995245911615e-05,
      "loss": 0.462,
      "step": 20107
    },
    {
      "epoch": 0.6177003655577059,
      "grad_norm": 0.431669682264328,
      "learning_rate": 1.56785974547259e-05,
      "loss": 0.5823,
      "step": 20108
    },
    {
      "epoch": 0.617731084692655,
      "grad_norm": 0.3622507154941559,
      "learning_rate": 1.5678199650277418e-05,
      "loss": 0.5962,
      "step": 20109
    },
    {
      "epoch": 0.6177618038276043,
      "grad_norm": 0.34497302770614624,
      "learning_rate": 1.5677801832567112e-05,
      "loss": 0.5079,
      "step": 20110
    },
    {
      "epoch": 0.6177925229625534,
      "grad_norm": 0.35605427622795105,
      "learning_rate": 1.56774040015959e-05,
      "loss": 0.5183,
      "step": 20111
    },
    {
      "epoch": 0.6178232420975025,
      "grad_norm": 0.3840530812740326,
      "learning_rate": 1.567700615736471e-05,
      "loss": 0.5885,
      "step": 20112
    },
    {
      "epoch": 0.6178539612324517,
      "grad_norm": 0.3348402678966522,
      "learning_rate": 1.567660829987448e-05,
      "loss": 0.5793,
      "step": 20113
    },
    {
      "epoch": 0.6178846803674009,
      "grad_norm": 0.38123592734336853,
      "learning_rate": 1.5676210429126137e-05,
      "loss": 0.457,
      "step": 20114
    },
    {
      "epoch": 0.61791539950235,
      "grad_norm": 0.3448537290096283,
      "learning_rate": 1.5675812545120606e-05,
      "loss": 0.5992,
      "step": 20115
    },
    {
      "epoch": 0.6179461186372992,
      "grad_norm": 0.345031201839447,
      "learning_rate": 1.567541464785882e-05,
      "loss": 0.5651,
      "step": 20116
    },
    {
      "epoch": 0.6179768377722483,
      "grad_norm": 0.37656369805336,
      "learning_rate": 1.5675016737341705e-05,
      "loss": 0.5795,
      "step": 20117
    },
    {
      "epoch": 0.6180075569071974,
      "grad_norm": 0.37120091915130615,
      "learning_rate": 1.5674618813570192e-05,
      "loss": 0.6912,
      "step": 20118
    },
    {
      "epoch": 0.6180382760421467,
      "grad_norm": 0.39015480875968933,
      "learning_rate": 1.5674220876545213e-05,
      "loss": 0.5651,
      "step": 20119
    },
    {
      "epoch": 0.6180689951770958,
      "grad_norm": 0.36776962876319885,
      "learning_rate": 1.567382292626769e-05,
      "loss": 0.6012,
      "step": 20120
    },
    {
      "epoch": 0.618099714312045,
      "grad_norm": 0.49045488238334656,
      "learning_rate": 1.5673424962738563e-05,
      "loss": 0.5896,
      "step": 20121
    },
    {
      "epoch": 0.6181304334469941,
      "grad_norm": 0.3635050654411316,
      "learning_rate": 1.5673026985958753e-05,
      "loss": 0.6022,
      "step": 20122
    },
    {
      "epoch": 0.6181611525819433,
      "grad_norm": 0.3433187007904053,
      "learning_rate": 1.567262899592919e-05,
      "loss": 0.5518,
      "step": 20123
    },
    {
      "epoch": 0.6181918717168925,
      "grad_norm": 0.5578868389129639,
      "learning_rate": 1.567223099265081e-05,
      "loss": 0.6872,
      "step": 20124
    },
    {
      "epoch": 0.6182225908518416,
      "grad_norm": 0.5959756970405579,
      "learning_rate": 1.5671832976124535e-05,
      "loss": 0.552,
      "step": 20125
    },
    {
      "epoch": 0.6182533099867907,
      "grad_norm": 0.3548046946525574,
      "learning_rate": 1.5671434946351298e-05,
      "loss": 0.5806,
      "step": 20126
    },
    {
      "epoch": 0.61828402912174,
      "grad_norm": 0.396415114402771,
      "learning_rate": 1.567103690333203e-05,
      "loss": 0.644,
      "step": 20127
    },
    {
      "epoch": 0.6183147482566891,
      "grad_norm": 0.4397309720516205,
      "learning_rate": 1.5670638847067658e-05,
      "loss": 0.6087,
      "step": 20128
    },
    {
      "epoch": 0.6183454673916382,
      "grad_norm": 0.38220444321632385,
      "learning_rate": 1.5670240777559116e-05,
      "loss": 0.5407,
      "step": 20129
    },
    {
      "epoch": 0.6183761865265874,
      "grad_norm": 0.45391401648521423,
      "learning_rate": 1.566984269480733e-05,
      "loss": 0.5807,
      "step": 20130
    },
    {
      "epoch": 0.6184069056615366,
      "grad_norm": 0.34300467371940613,
      "learning_rate": 1.5669444598813225e-05,
      "loss": 0.5637,
      "step": 20131
    },
    {
      "epoch": 0.6184376247964858,
      "grad_norm": 0.3176201581954956,
      "learning_rate": 1.5669046489577743e-05,
      "loss": 0.5296,
      "step": 20132
    },
    {
      "epoch": 0.6184683439314349,
      "grad_norm": 0.3482523262500763,
      "learning_rate": 1.56686483671018e-05,
      "loss": 0.5529,
      "step": 20133
    },
    {
      "epoch": 0.618499063066384,
      "grad_norm": 0.349398136138916,
      "learning_rate": 1.566825023138634e-05,
      "loss": 0.5601,
      "step": 20134
    },
    {
      "epoch": 0.6185297822013333,
      "grad_norm": 0.3518083989620209,
      "learning_rate": 1.5667852082432286e-05,
      "loss": 0.56,
      "step": 20135
    },
    {
      "epoch": 0.6185605013362824,
      "grad_norm": 0.34431517124176025,
      "learning_rate": 1.566745392024056e-05,
      "loss": 0.6052,
      "step": 20136
    },
    {
      "epoch": 0.6185912204712315,
      "grad_norm": 0.3580375015735626,
      "learning_rate": 1.5667055744812105e-05,
      "loss": 0.5873,
      "step": 20137
    },
    {
      "epoch": 0.6186219396061807,
      "grad_norm": 0.39282166957855225,
      "learning_rate": 1.5666657556147846e-05,
      "loss": 0.6058,
      "step": 20138
    },
    {
      "epoch": 0.6186526587411298,
      "grad_norm": 0.37852203845977783,
      "learning_rate": 1.5666259354248712e-05,
      "loss": 0.5803,
      "step": 20139
    },
    {
      "epoch": 0.618683377876079,
      "grad_norm": 0.43533265590667725,
      "learning_rate": 1.566586113911563e-05,
      "loss": 0.5092,
      "step": 20140
    },
    {
      "epoch": 0.6187140970110282,
      "grad_norm": 0.4160943031311035,
      "learning_rate": 1.5665462910749537e-05,
      "loss": 0.6051,
      "step": 20141
    },
    {
      "epoch": 0.6187448161459773,
      "grad_norm": 0.3570893704891205,
      "learning_rate": 1.566506466915136e-05,
      "loss": 0.5907,
      "step": 20142
    },
    {
      "epoch": 0.6187755352809264,
      "grad_norm": 0.36415818333625793,
      "learning_rate": 1.566466641432203e-05,
      "loss": 0.562,
      "step": 20143
    },
    {
      "epoch": 0.6188062544158757,
      "grad_norm": 0.3558482527732849,
      "learning_rate": 1.566426814626247e-05,
      "loss": 0.6093,
      "step": 20144
    },
    {
      "epoch": 0.6188369735508248,
      "grad_norm": 0.5197294354438782,
      "learning_rate": 1.566386986497362e-05,
      "loss": 0.5488,
      "step": 20145
    },
    {
      "epoch": 0.618867692685774,
      "grad_norm": 0.5130001902580261,
      "learning_rate": 1.566347157045641e-05,
      "loss": 0.5588,
      "step": 20146
    },
    {
      "epoch": 0.6188984118207231,
      "grad_norm": 0.3367644250392914,
      "learning_rate": 1.566307326271176e-05,
      "loss": 0.5467,
      "step": 20147
    },
    {
      "epoch": 0.6189291309556723,
      "grad_norm": 0.3580525815486908,
      "learning_rate": 1.566267494174061e-05,
      "loss": 0.5723,
      "step": 20148
    },
    {
      "epoch": 0.6189598500906215,
      "grad_norm": 0.39101073145866394,
      "learning_rate": 1.5662276607543884e-05,
      "loss": 0.5939,
      "step": 20149
    },
    {
      "epoch": 0.6189905692255706,
      "grad_norm": 0.3471052348613739,
      "learning_rate": 1.5661878260122517e-05,
      "loss": 0.5278,
      "step": 20150
    },
    {
      "epoch": 0.6190212883605197,
      "grad_norm": 0.4418967366218567,
      "learning_rate": 1.5661479899477444e-05,
      "loss": 0.5853,
      "step": 20151
    },
    {
      "epoch": 0.619052007495469,
      "grad_norm": 0.35835859179496765,
      "learning_rate": 1.566108152560958e-05,
      "loss": 0.5465,
      "step": 20152
    },
    {
      "epoch": 0.6190827266304181,
      "grad_norm": 0.33837372064590454,
      "learning_rate": 1.5660683138519873e-05,
      "loss": 0.5337,
      "step": 20153
    },
    {
      "epoch": 0.6191134457653672,
      "grad_norm": 0.4967881739139557,
      "learning_rate": 1.566028473820924e-05,
      "loss": 0.6301,
      "step": 20154
    },
    {
      "epoch": 0.6191441649003164,
      "grad_norm": 0.3260073661804199,
      "learning_rate": 1.565988632467862e-05,
      "loss": 0.6086,
      "step": 20155
    },
    {
      "epoch": 0.6191748840352655,
      "grad_norm": 0.3598198890686035,
      "learning_rate": 1.5659487897928937e-05,
      "loss": 0.5364,
      "step": 20156
    },
    {
      "epoch": 0.6192056031702148,
      "grad_norm": 0.39631494879722595,
      "learning_rate": 1.5659089457961126e-05,
      "loss": 0.5162,
      "step": 20157
    },
    {
      "epoch": 0.6192363223051639,
      "grad_norm": 0.33622583746910095,
      "learning_rate": 1.565869100477612e-05,
      "loss": 0.6353,
      "step": 20158
    },
    {
      "epoch": 0.619267041440113,
      "grad_norm": 0.32688531279563904,
      "learning_rate": 1.565829253837484e-05,
      "loss": 0.5558,
      "step": 20159
    },
    {
      "epoch": 0.6192977605750623,
      "grad_norm": 0.345709890127182,
      "learning_rate": 1.5657894058758227e-05,
      "loss": 0.576,
      "step": 20160
    },
    {
      "epoch": 0.6193284797100114,
      "grad_norm": 0.3592391014099121,
      "learning_rate": 1.56574955659272e-05,
      "loss": 0.5741,
      "step": 20161
    },
    {
      "epoch": 0.6193591988449605,
      "grad_norm": 0.36095279455184937,
      "learning_rate": 1.5657097059882707e-05,
      "loss": 0.6151,
      "step": 20162
    },
    {
      "epoch": 0.6193899179799097,
      "grad_norm": 0.36710911989212036,
      "learning_rate": 1.5656698540625663e-05,
      "loss": 0.553,
      "step": 20163
    },
    {
      "epoch": 0.6194206371148588,
      "grad_norm": 0.3597314655780792,
      "learning_rate": 1.5656300008157006e-05,
      "loss": 0.5314,
      "step": 20164
    },
    {
      "epoch": 0.619451356249808,
      "grad_norm": 0.5139023661613464,
      "learning_rate": 1.5655901462477668e-05,
      "loss": 0.5154,
      "step": 20165
    },
    {
      "epoch": 0.6194820753847572,
      "grad_norm": 0.3389265835285187,
      "learning_rate": 1.565550290358857e-05,
      "loss": 0.5364,
      "step": 20166
    },
    {
      "epoch": 0.6195127945197063,
      "grad_norm": 0.3534304201602936,
      "learning_rate": 1.5655104331490653e-05,
      "loss": 0.5359,
      "step": 20167
    },
    {
      "epoch": 0.6195435136546554,
      "grad_norm": 0.33933448791503906,
      "learning_rate": 1.5654705746184847e-05,
      "loss": 0.552,
      "step": 20168
    },
    {
      "epoch": 0.6195742327896047,
      "grad_norm": 0.4696357548236847,
      "learning_rate": 1.565430714767208e-05,
      "loss": 0.5586,
      "step": 20169
    },
    {
      "epoch": 0.6196049519245538,
      "grad_norm": 0.4026802182197571,
      "learning_rate": 1.5653908535953285e-05,
      "loss": 0.5399,
      "step": 20170
    },
    {
      "epoch": 0.619635671059503,
      "grad_norm": 0.411404550075531,
      "learning_rate": 1.565350991102939e-05,
      "loss": 0.5476,
      "step": 20171
    },
    {
      "epoch": 0.6196663901944521,
      "grad_norm": 0.3969603478908539,
      "learning_rate": 1.5653111272901328e-05,
      "loss": 0.6429,
      "step": 20172
    },
    {
      "epoch": 0.6196971093294013,
      "grad_norm": 0.3882073163986206,
      "learning_rate": 1.565271262157003e-05,
      "loss": 0.6163,
      "step": 20173
    },
    {
      "epoch": 0.6197278284643505,
      "grad_norm": 0.3656962811946869,
      "learning_rate": 1.5652313957036426e-05,
      "loss": 0.5671,
      "step": 20174
    },
    {
      "epoch": 0.6197585475992996,
      "grad_norm": 0.3866586983203888,
      "learning_rate": 1.565191527930145e-05,
      "loss": 0.6067,
      "step": 20175
    },
    {
      "epoch": 0.6197892667342487,
      "grad_norm": 0.32495298981666565,
      "learning_rate": 1.565151658836603e-05,
      "loss": 0.5555,
      "step": 20176
    },
    {
      "epoch": 0.619819985869198,
      "grad_norm": 0.3638238310813904,
      "learning_rate": 1.5651117884231097e-05,
      "loss": 0.5678,
      "step": 20177
    },
    {
      "epoch": 0.6198507050041471,
      "grad_norm": 0.32121720910072327,
      "learning_rate": 1.5650719166897584e-05,
      "loss": 0.5281,
      "step": 20178
    },
    {
      "epoch": 0.6198814241390962,
      "grad_norm": 0.3461604714393616,
      "learning_rate": 1.5650320436366424e-05,
      "loss": 0.5656,
      "step": 20179
    },
    {
      "epoch": 0.6199121432740454,
      "grad_norm": 0.37883663177490234,
      "learning_rate": 1.5649921692638544e-05,
      "loss": 0.625,
      "step": 20180
    },
    {
      "epoch": 0.6199428624089945,
      "grad_norm": 0.3576296865940094,
      "learning_rate": 1.5649522935714878e-05,
      "loss": 0.5826,
      "step": 20181
    },
    {
      "epoch": 0.6199735815439438,
      "grad_norm": 0.3389306962490082,
      "learning_rate": 1.5649124165596355e-05,
      "loss": 0.5896,
      "step": 20182
    },
    {
      "epoch": 0.6200043006788929,
      "grad_norm": 0.34850698709487915,
      "learning_rate": 1.5648725382283912e-05,
      "loss": 0.6494,
      "step": 20183
    },
    {
      "epoch": 0.620035019813842,
      "grad_norm": 0.3684212565422058,
      "learning_rate": 1.5648326585778474e-05,
      "loss": 0.6418,
      "step": 20184
    },
    {
      "epoch": 0.6200657389487912,
      "grad_norm": 0.3488147258758545,
      "learning_rate": 1.5647927776080972e-05,
      "loss": 0.6171,
      "step": 20185
    },
    {
      "epoch": 0.6200964580837404,
      "grad_norm": 0.3521983325481415,
      "learning_rate": 1.5647528953192344e-05,
      "loss": 0.6471,
      "step": 20186
    },
    {
      "epoch": 0.6201271772186895,
      "grad_norm": 0.3362077474594116,
      "learning_rate": 1.5647130117113513e-05,
      "loss": 0.5526,
      "step": 20187
    },
    {
      "epoch": 0.6201578963536387,
      "grad_norm": 0.35070887207984924,
      "learning_rate": 1.564673126784542e-05,
      "loss": 0.5474,
      "step": 20188
    },
    {
      "epoch": 0.6201886154885878,
      "grad_norm": 0.3778250217437744,
      "learning_rate": 1.564633240538899e-05,
      "loss": 0.5252,
      "step": 20189
    },
    {
      "epoch": 0.620219334623537,
      "grad_norm": 0.3441431522369385,
      "learning_rate": 1.5645933529745158e-05,
      "loss": 0.5587,
      "step": 20190
    },
    {
      "epoch": 0.6202500537584862,
      "grad_norm": 0.42282599210739136,
      "learning_rate": 1.5645534640914853e-05,
      "loss": 0.6173,
      "step": 20191
    },
    {
      "epoch": 0.6202807728934353,
      "grad_norm": 0.35542169213294983,
      "learning_rate": 1.5645135738899006e-05,
      "loss": 0.5444,
      "step": 20192
    },
    {
      "epoch": 0.6203114920283844,
      "grad_norm": 0.3258785009384155,
      "learning_rate": 1.5644736823698553e-05,
      "loss": 0.5479,
      "step": 20193
    },
    {
      "epoch": 0.6203422111633337,
      "grad_norm": 0.33711665868759155,
      "learning_rate": 1.564433789531442e-05,
      "loss": 0.6132,
      "step": 20194
    },
    {
      "epoch": 0.6203729302982828,
      "grad_norm": 0.3751281499862671,
      "learning_rate": 1.5643938953747543e-05,
      "loss": 0.5575,
      "step": 20195
    },
    {
      "epoch": 0.620403649433232,
      "grad_norm": 0.3692573606967926,
      "learning_rate": 1.5643539998998854e-05,
      "loss": 0.5503,
      "step": 20196
    },
    {
      "epoch": 0.6204343685681811,
      "grad_norm": 0.5115947723388672,
      "learning_rate": 1.564314103106928e-05,
      "loss": 0.6041,
      "step": 20197
    },
    {
      "epoch": 0.6204650877031302,
      "grad_norm": 0.3514859974384308,
      "learning_rate": 1.5642742049959762e-05,
      "loss": 0.5288,
      "step": 20198
    },
    {
      "epoch": 0.6204958068380795,
      "grad_norm": 0.34153345227241516,
      "learning_rate": 1.564234305567122e-05,
      "loss": 0.5687,
      "step": 20199
    },
    {
      "epoch": 0.6205265259730286,
      "grad_norm": 0.33640673756599426,
      "learning_rate": 1.564194404820459e-05,
      "loss": 0.5644,
      "step": 20200
    },
    {
      "epoch": 0.6205572451079777,
      "grad_norm": 0.3776742219924927,
      "learning_rate": 1.564154502756081e-05,
      "loss": 0.5475,
      "step": 20201
    },
    {
      "epoch": 0.620587964242927,
      "grad_norm": 0.3747698664665222,
      "learning_rate": 1.5641145993740807e-05,
      "loss": 0.5111,
      "step": 20202
    },
    {
      "epoch": 0.6206186833778761,
      "grad_norm": 0.38643911480903625,
      "learning_rate": 1.5640746946745517e-05,
      "loss": 0.5966,
      "step": 20203
    },
    {
      "epoch": 0.6206494025128252,
      "grad_norm": 0.3718632459640503,
      "learning_rate": 1.564034788657586e-05,
      "loss": 0.5391,
      "step": 20204
    },
    {
      "epoch": 0.6206801216477744,
      "grad_norm": 0.3459409475326538,
      "learning_rate": 1.5639948813232782e-05,
      "loss": 0.6171,
      "step": 20205
    },
    {
      "epoch": 0.6207108407827235,
      "grad_norm": 0.34201887249946594,
      "learning_rate": 1.563954972671721e-05,
      "loss": 0.4609,
      "step": 20206
    },
    {
      "epoch": 0.6207415599176728,
      "grad_norm": 0.359014630317688,
      "learning_rate": 1.5639150627030072e-05,
      "loss": 0.6096,
      "step": 20207
    },
    {
      "epoch": 0.6207722790526219,
      "grad_norm": 0.3277183175086975,
      "learning_rate": 1.563875151417231e-05,
      "loss": 0.5548,
      "step": 20208
    },
    {
      "epoch": 0.620802998187571,
      "grad_norm": 0.4222385883331299,
      "learning_rate": 1.5638352388144843e-05,
      "loss": 0.5677,
      "step": 20209
    },
    {
      "epoch": 0.6208337173225202,
      "grad_norm": 0.377604216337204,
      "learning_rate": 1.5637953248948617e-05,
      "loss": 0.4852,
      "step": 20210
    },
    {
      "epoch": 0.6208644364574694,
      "grad_norm": 0.33904320001602173,
      "learning_rate": 1.5637554096584553e-05,
      "loss": 0.5241,
      "step": 20211
    },
    {
      "epoch": 0.6208951555924185,
      "grad_norm": 0.36126917600631714,
      "learning_rate": 1.563715493105359e-05,
      "loss": 0.493,
      "step": 20212
    },
    {
      "epoch": 0.6209258747273677,
      "grad_norm": 0.3615190088748932,
      "learning_rate": 1.5636755752356655e-05,
      "loss": 0.5712,
      "step": 20213
    },
    {
      "epoch": 0.6209565938623168,
      "grad_norm": 0.3198011517524719,
      "learning_rate": 1.5636356560494686e-05,
      "loss": 0.5367,
      "step": 20214
    },
    {
      "epoch": 0.620987312997266,
      "grad_norm": 0.3472548723220825,
      "learning_rate": 1.563595735546861e-05,
      "loss": 0.5113,
      "step": 20215
    },
    {
      "epoch": 0.6210180321322152,
      "grad_norm": 0.3611818850040436,
      "learning_rate": 1.5635558137279367e-05,
      "loss": 0.5673,
      "step": 20216
    },
    {
      "epoch": 0.6210487512671643,
      "grad_norm": 0.3708208203315735,
      "learning_rate": 1.5635158905927877e-05,
      "loss": 0.5742,
      "step": 20217
    },
    {
      "epoch": 0.6210794704021135,
      "grad_norm": 0.42246297001838684,
      "learning_rate": 1.5634759661415085e-05,
      "loss": 0.6142,
      "step": 20218
    },
    {
      "epoch": 0.6211101895370627,
      "grad_norm": 0.3573817312717438,
      "learning_rate": 1.5634360403741918e-05,
      "loss": 0.5202,
      "step": 20219
    },
    {
      "epoch": 0.6211409086720118,
      "grad_norm": 0.3912177085876465,
      "learning_rate": 1.5633961132909308e-05,
      "loss": 0.5782,
      "step": 20220
    },
    {
      "epoch": 0.621171627806961,
      "grad_norm": 0.3656556010246277,
      "learning_rate": 1.563356184891819e-05,
      "loss": 0.5967,
      "step": 20221
    },
    {
      "epoch": 0.6212023469419101,
      "grad_norm": 0.37438473105430603,
      "learning_rate": 1.563316255176949e-05,
      "loss": 0.5639,
      "step": 20222
    },
    {
      "epoch": 0.6212330660768592,
      "grad_norm": 0.40562841296195984,
      "learning_rate": 1.563276324146415e-05,
      "loss": 0.6079,
      "step": 20223
    },
    {
      "epoch": 0.6212637852118085,
      "grad_norm": 0.38282981514930725,
      "learning_rate": 1.56323639180031e-05,
      "loss": 0.5595,
      "step": 20224
    },
    {
      "epoch": 0.6212945043467576,
      "grad_norm": 0.33911892771720886,
      "learning_rate": 1.5631964581387264e-05,
      "loss": 0.5984,
      "step": 20225
    },
    {
      "epoch": 0.6213252234817067,
      "grad_norm": 0.43060222268104553,
      "learning_rate": 1.5631565231617584e-05,
      "loss": 0.4811,
      "step": 20226
    },
    {
      "epoch": 0.6213559426166559,
      "grad_norm": 0.4229173958301544,
      "learning_rate": 1.5631165868694993e-05,
      "loss": 0.5411,
      "step": 20227
    },
    {
      "epoch": 0.6213866617516051,
      "grad_norm": 0.39340540766716003,
      "learning_rate": 1.5630766492620416e-05,
      "loss": 0.5321,
      "step": 20228
    },
    {
      "epoch": 0.6214173808865542,
      "grad_norm": 0.3778016269207001,
      "learning_rate": 1.5630367103394796e-05,
      "loss": 0.5537,
      "step": 20229
    },
    {
      "epoch": 0.6214481000215034,
      "grad_norm": 0.35572168231010437,
      "learning_rate": 1.5629967701019054e-05,
      "loss": 0.488,
      "step": 20230
    },
    {
      "epoch": 0.6214788191564525,
      "grad_norm": 0.33956265449523926,
      "learning_rate": 1.5629568285494135e-05,
      "loss": 0.5827,
      "step": 20231
    },
    {
      "epoch": 0.6215095382914018,
      "grad_norm": 0.3832680881023407,
      "learning_rate": 1.5629168856820964e-05,
      "loss": 0.62,
      "step": 20232
    },
    {
      "epoch": 0.6215402574263509,
      "grad_norm": 0.42909902334213257,
      "learning_rate": 1.562876941500048e-05,
      "loss": 0.5778,
      "step": 20233
    },
    {
      "epoch": 0.6215709765613,
      "grad_norm": 0.37452277541160583,
      "learning_rate": 1.5628369960033606e-05,
      "loss": 0.6099,
      "step": 20234
    },
    {
      "epoch": 0.6216016956962492,
      "grad_norm": 0.33592885732650757,
      "learning_rate": 1.5627970491921284e-05,
      "loss": 0.5607,
      "step": 20235
    },
    {
      "epoch": 0.6216324148311984,
      "grad_norm": 0.37904301285743713,
      "learning_rate": 1.5627571010664443e-05,
      "loss": 0.5695,
      "step": 20236
    },
    {
      "epoch": 0.6216631339661475,
      "grad_norm": 0.3290107250213623,
      "learning_rate": 1.5627171516264016e-05,
      "loss": 0.5369,
      "step": 20237
    },
    {
      "epoch": 0.6216938531010967,
      "grad_norm": 0.4227602183818817,
      "learning_rate": 1.5626772008720937e-05,
      "loss": 0.5292,
      "step": 20238
    },
    {
      "epoch": 0.6217245722360458,
      "grad_norm": 0.33521002531051636,
      "learning_rate": 1.562637248803614e-05,
      "loss": 0.5744,
      "step": 20239
    },
    {
      "epoch": 0.621755291370995,
      "grad_norm": 0.34605687856674194,
      "learning_rate": 1.5625972954210556e-05,
      "loss": 0.5463,
      "step": 20240
    },
    {
      "epoch": 0.6217860105059442,
      "grad_norm": 0.3886035680770874,
      "learning_rate": 1.5625573407245118e-05,
      "loss": 0.577,
      "step": 20241
    },
    {
      "epoch": 0.6218167296408933,
      "grad_norm": 0.38744834065437317,
      "learning_rate": 1.562517384714076e-05,
      "loss": 0.5234,
      "step": 20242
    },
    {
      "epoch": 0.6218474487758425,
      "grad_norm": 0.32925546169281006,
      "learning_rate": 1.562477427389842e-05,
      "loss": 0.561,
      "step": 20243
    },
    {
      "epoch": 0.6218781679107916,
      "grad_norm": 0.3692215383052826,
      "learning_rate": 1.5624374687519023e-05,
      "loss": 0.5563,
      "step": 20244
    },
    {
      "epoch": 0.6219088870457408,
      "grad_norm": 0.38909897208213806,
      "learning_rate": 1.562397508800351e-05,
      "loss": 0.6325,
      "step": 20245
    },
    {
      "epoch": 0.62193960618069,
      "grad_norm": 0.401996374130249,
      "learning_rate": 1.562357547535281e-05,
      "loss": 0.5966,
      "step": 20246
    },
    {
      "epoch": 0.6219703253156391,
      "grad_norm": 0.3626191318035126,
      "learning_rate": 1.5623175849567854e-05,
      "loss": 0.4666,
      "step": 20247
    },
    {
      "epoch": 0.6220010444505882,
      "grad_norm": 0.4817671775817871,
      "learning_rate": 1.5622776210649576e-05,
      "loss": 0.6384,
      "step": 20248
    },
    {
      "epoch": 0.6220317635855375,
      "grad_norm": 0.3484368920326233,
      "learning_rate": 1.562237655859892e-05,
      "loss": 0.6332,
      "step": 20249
    },
    {
      "epoch": 0.6220624827204866,
      "grad_norm": 0.35054945945739746,
      "learning_rate": 1.5621976893416805e-05,
      "loss": 0.534,
      "step": 20250
    },
    {
      "epoch": 0.6220932018554357,
      "grad_norm": 0.3210464417934418,
      "learning_rate": 1.562157721510417e-05,
      "loss": 0.51,
      "step": 20251
    },
    {
      "epoch": 0.6221239209903849,
      "grad_norm": 0.4582434892654419,
      "learning_rate": 1.562117752366195e-05,
      "loss": 0.5289,
      "step": 20252
    },
    {
      "epoch": 0.6221546401253341,
      "grad_norm": 0.3635072410106659,
      "learning_rate": 1.5620777819091077e-05,
      "loss": 0.532,
      "step": 20253
    },
    {
      "epoch": 0.6221853592602832,
      "grad_norm": 0.3709373474121094,
      "learning_rate": 1.5620378101392483e-05,
      "loss": 0.6439,
      "step": 20254
    },
    {
      "epoch": 0.6222160783952324,
      "grad_norm": 0.36763226985931396,
      "learning_rate": 1.5619978370567105e-05,
      "loss": 0.5919,
      "step": 20255
    },
    {
      "epoch": 0.6222467975301815,
      "grad_norm": 0.36122146248817444,
      "learning_rate": 1.5619578626615877e-05,
      "loss": 0.5491,
      "step": 20256
    },
    {
      "epoch": 0.6222775166651308,
      "grad_norm": 0.36009296774864197,
      "learning_rate": 1.561917886953973e-05,
      "loss": 0.6079,
      "step": 20257
    },
    {
      "epoch": 0.6223082358000799,
      "grad_norm": 0.36087119579315186,
      "learning_rate": 1.5618779099339593e-05,
      "loss": 0.5413,
      "step": 20258
    },
    {
      "epoch": 0.622338954935029,
      "grad_norm": 0.38777151703834534,
      "learning_rate": 1.561837931601641e-05,
      "loss": 0.5624,
      "step": 20259
    },
    {
      "epoch": 0.6223696740699782,
      "grad_norm": 0.38642266392707825,
      "learning_rate": 1.561797951957111e-05,
      "loss": 0.5813,
      "step": 20260
    },
    {
      "epoch": 0.6224003932049273,
      "grad_norm": 0.40504777431488037,
      "learning_rate": 1.5617579710004626e-05,
      "loss": 0.5746,
      "step": 20261
    },
    {
      "epoch": 0.6224311123398765,
      "grad_norm": 0.37294527888298035,
      "learning_rate": 1.561717988731789e-05,
      "loss": 0.5642,
      "step": 20262
    },
    {
      "epoch": 0.6224618314748257,
      "grad_norm": 0.3473112881183624,
      "learning_rate": 1.5616780051511842e-05,
      "loss": 0.6123,
      "step": 20263
    },
    {
      "epoch": 0.6224925506097748,
      "grad_norm": 0.34021830558776855,
      "learning_rate": 1.5616380202587408e-05,
      "loss": 0.6057,
      "step": 20264
    },
    {
      "epoch": 0.6225232697447239,
      "grad_norm": 0.37240070104599,
      "learning_rate": 1.5615980340545527e-05,
      "loss": 0.5767,
      "step": 20265
    },
    {
      "epoch": 0.6225539888796732,
      "grad_norm": 0.330222487449646,
      "learning_rate": 1.5615580465387134e-05,
      "loss": 0.5613,
      "step": 20266
    },
    {
      "epoch": 0.6225847080146223,
      "grad_norm": 0.34180399775505066,
      "learning_rate": 1.5615180577113157e-05,
      "loss": 0.5532,
      "step": 20267
    },
    {
      "epoch": 0.6226154271495715,
      "grad_norm": 0.3683977425098419,
      "learning_rate": 1.5614780675724535e-05,
      "loss": 0.5788,
      "step": 20268
    },
    {
      "epoch": 0.6226461462845206,
      "grad_norm": 0.3937702775001526,
      "learning_rate": 1.56143807612222e-05,
      "loss": 0.5392,
      "step": 20269
    },
    {
      "epoch": 0.6226768654194698,
      "grad_norm": 0.3747239410877228,
      "learning_rate": 1.561398083360709e-05,
      "loss": 0.5085,
      "step": 20270
    },
    {
      "epoch": 0.622707584554419,
      "grad_norm": 0.37120485305786133,
      "learning_rate": 1.5613580892880135e-05,
      "loss": 0.5837,
      "step": 20271
    },
    {
      "epoch": 0.6227383036893681,
      "grad_norm": 0.36735910177230835,
      "learning_rate": 1.5613180939042267e-05,
      "loss": 0.6175,
      "step": 20272
    },
    {
      "epoch": 0.6227690228243172,
      "grad_norm": 0.3447132110595703,
      "learning_rate": 1.5612780972094424e-05,
      "loss": 0.5629,
      "step": 20273
    },
    {
      "epoch": 0.6227997419592665,
      "grad_norm": 0.36704298853874207,
      "learning_rate": 1.5612380992037536e-05,
      "loss": 0.5354,
      "step": 20274
    },
    {
      "epoch": 0.6228304610942156,
      "grad_norm": 0.3546651005744934,
      "learning_rate": 1.5611980998872545e-05,
      "loss": 0.5573,
      "step": 20275
    },
    {
      "epoch": 0.6228611802291647,
      "grad_norm": 0.3663739562034607,
      "learning_rate": 1.561158099260038e-05,
      "loss": 0.6658,
      "step": 20276
    },
    {
      "epoch": 0.6228918993641139,
      "grad_norm": 1.7424795627593994,
      "learning_rate": 1.5611180973221973e-05,
      "loss": 0.4956,
      "step": 20277
    },
    {
      "epoch": 0.622922618499063,
      "grad_norm": 0.41066089272499084,
      "learning_rate": 1.5610780940738262e-05,
      "loss": 0.5854,
      "step": 20278
    },
    {
      "epoch": 0.6229533376340122,
      "grad_norm": 0.3640250265598297,
      "learning_rate": 1.5610380895150183e-05,
      "loss": 0.631,
      "step": 20279
    },
    {
      "epoch": 0.6229840567689614,
      "grad_norm": 0.36628273129463196,
      "learning_rate": 1.5609980836458662e-05,
      "loss": 0.5503,
      "step": 20280
    },
    {
      "epoch": 0.6230147759039105,
      "grad_norm": 0.3494238257408142,
      "learning_rate": 1.5609580764664644e-05,
      "loss": 0.6163,
      "step": 20281
    },
    {
      "epoch": 0.6230454950388598,
      "grad_norm": 0.3752349615097046,
      "learning_rate": 1.5609180679769055e-05,
      "loss": 0.5398,
      "step": 20282
    },
    {
      "epoch": 0.6230762141738089,
      "grad_norm": 0.33498701453208923,
      "learning_rate": 1.5608780581772834e-05,
      "loss": 0.4901,
      "step": 20283
    },
    {
      "epoch": 0.623106933308758,
      "grad_norm": 0.4469001889228821,
      "learning_rate": 1.5608380470676917e-05,
      "loss": 0.5571,
      "step": 20284
    },
    {
      "epoch": 0.6231376524437072,
      "grad_norm": 0.38199135661125183,
      "learning_rate": 1.560798034648223e-05,
      "loss": 0.585,
      "step": 20285
    },
    {
      "epoch": 0.6231683715786563,
      "grad_norm": 0.3607659935951233,
      "learning_rate": 1.560758020918972e-05,
      "loss": 0.6686,
      "step": 20286
    },
    {
      "epoch": 0.6231990907136055,
      "grad_norm": 0.34624844789505005,
      "learning_rate": 1.560718005880031e-05,
      "loss": 0.5034,
      "step": 20287
    },
    {
      "epoch": 0.6232298098485547,
      "grad_norm": 0.4342850148677826,
      "learning_rate": 1.560677989531494e-05,
      "loss": 0.5739,
      "step": 20288
    },
    {
      "epoch": 0.6232605289835038,
      "grad_norm": 0.37431398034095764,
      "learning_rate": 1.5606379718734547e-05,
      "loss": 0.5642,
      "step": 20289
    },
    {
      "epoch": 0.6232912481184529,
      "grad_norm": 0.33282822370529175,
      "learning_rate": 1.5605979529060057e-05,
      "loss": 0.5553,
      "step": 20290
    },
    {
      "epoch": 0.6233219672534022,
      "grad_norm": 0.3502263128757477,
      "learning_rate": 1.5605579326292413e-05,
      "loss": 0.4899,
      "step": 20291
    },
    {
      "epoch": 0.6233526863883513,
      "grad_norm": 0.41162538528442383,
      "learning_rate": 1.560517911043255e-05,
      "loss": 0.5702,
      "step": 20292
    },
    {
      "epoch": 0.6233834055233005,
      "grad_norm": 0.35347771644592285,
      "learning_rate": 1.5604778881481398e-05,
      "loss": 0.4785,
      "step": 20293
    },
    {
      "epoch": 0.6234141246582496,
      "grad_norm": 0.36461132764816284,
      "learning_rate": 1.5604378639439892e-05,
      "loss": 0.5028,
      "step": 20294
    },
    {
      "epoch": 0.6234448437931988,
      "grad_norm": 0.41234779357910156,
      "learning_rate": 1.560397838430897e-05,
      "loss": 0.5289,
      "step": 20295
    },
    {
      "epoch": 0.623475562928148,
      "grad_norm": 0.36615824699401855,
      "learning_rate": 1.5603578116089563e-05,
      "loss": 0.5258,
      "step": 20296
    },
    {
      "epoch": 0.6235062820630971,
      "grad_norm": 0.34095320105552673,
      "learning_rate": 1.5603177834782608e-05,
      "loss": 0.5942,
      "step": 20297
    },
    {
      "epoch": 0.6235370011980462,
      "grad_norm": 0.3924514353275299,
      "learning_rate": 1.560277754038904e-05,
      "loss": 0.5511,
      "step": 20298
    },
    {
      "epoch": 0.6235677203329955,
      "grad_norm": 0.3572743535041809,
      "learning_rate": 1.5602377232909797e-05,
      "loss": 0.5148,
      "step": 20299
    },
    {
      "epoch": 0.6235984394679446,
      "grad_norm": 0.4173939526081085,
      "learning_rate": 1.560197691234581e-05,
      "loss": 0.4636,
      "step": 20300
    },
    {
      "epoch": 0.6236291586028937,
      "grad_norm": 0.39687275886535645,
      "learning_rate": 1.560157657869801e-05,
      "loss": 0.5942,
      "step": 20301
    },
    {
      "epoch": 0.6236598777378429,
      "grad_norm": 0.36986595392227173,
      "learning_rate": 1.560117623196734e-05,
      "loss": 0.5624,
      "step": 20302
    },
    {
      "epoch": 0.623690596872792,
      "grad_norm": 0.33975210785865784,
      "learning_rate": 1.560077587215473e-05,
      "loss": 0.5591,
      "step": 20303
    },
    {
      "epoch": 0.6237213160077412,
      "grad_norm": 0.33342888951301575,
      "learning_rate": 1.5600375499261123e-05,
      "loss": 0.5366,
      "step": 20304
    },
    {
      "epoch": 0.6237520351426904,
      "grad_norm": 0.3406507968902588,
      "learning_rate": 1.559997511328744e-05,
      "loss": 0.5705,
      "step": 20305
    },
    {
      "epoch": 0.6237827542776395,
      "grad_norm": 0.3446168005466461,
      "learning_rate": 1.5599574714234628e-05,
      "loss": 0.575,
      "step": 20306
    },
    {
      "epoch": 0.6238134734125887,
      "grad_norm": 0.39808762073516846,
      "learning_rate": 1.5599174302103618e-05,
      "loss": 0.5534,
      "step": 20307
    },
    {
      "epoch": 0.6238441925475379,
      "grad_norm": 0.37941062450408936,
      "learning_rate": 1.5598773876895344e-05,
      "loss": 0.6134,
      "step": 20308
    },
    {
      "epoch": 0.623874911682487,
      "grad_norm": 0.386218786239624,
      "learning_rate": 1.5598373438610742e-05,
      "loss": 0.6606,
      "step": 20309
    },
    {
      "epoch": 0.6239056308174362,
      "grad_norm": 0.3606838583946228,
      "learning_rate": 1.559797298725075e-05,
      "loss": 0.5695,
      "step": 20310
    },
    {
      "epoch": 0.6239363499523853,
      "grad_norm": 0.37791499495506287,
      "learning_rate": 1.5597572522816302e-05,
      "loss": 0.5424,
      "step": 20311
    },
    {
      "epoch": 0.6239670690873345,
      "grad_norm": 0.3469729721546173,
      "learning_rate": 1.559717204530833e-05,
      "loss": 0.5734,
      "step": 20312
    },
    {
      "epoch": 0.6239977882222837,
      "grad_norm": 0.3574044406414032,
      "learning_rate": 1.5596771554727773e-05,
      "loss": 0.5986,
      "step": 20313
    },
    {
      "epoch": 0.6240285073572328,
      "grad_norm": 0.346773236989975,
      "learning_rate": 1.5596371051075564e-05,
      "loss": 0.5852,
      "step": 20314
    },
    {
      "epoch": 0.6240592264921819,
      "grad_norm": 0.4272225797176361,
      "learning_rate": 1.559597053435264e-05,
      "loss": 0.5713,
      "step": 20315
    },
    {
      "epoch": 0.6240899456271312,
      "grad_norm": 0.34396475553512573,
      "learning_rate": 1.5595570004559936e-05,
      "loss": 0.6551,
      "step": 20316
    },
    {
      "epoch": 0.6241206647620803,
      "grad_norm": 0.3303702473640442,
      "learning_rate": 1.559516946169839e-05,
      "loss": 0.5962,
      "step": 20317
    },
    {
      "epoch": 0.6241513838970295,
      "grad_norm": 0.3556104600429535,
      "learning_rate": 1.559476890576893e-05,
      "loss": 0.6011,
      "step": 20318
    },
    {
      "epoch": 0.6241821030319786,
      "grad_norm": 0.3486095070838928,
      "learning_rate": 1.55943683367725e-05,
      "loss": 0.4926,
      "step": 20319
    },
    {
      "epoch": 0.6242128221669277,
      "grad_norm": 0.39561527967453003,
      "learning_rate": 1.5593967754710032e-05,
      "loss": 0.5444,
      "step": 20320
    },
    {
      "epoch": 0.624243541301877,
      "grad_norm": 0.3853559195995331,
      "learning_rate": 1.559356715958246e-05,
      "loss": 0.5784,
      "step": 20321
    },
    {
      "epoch": 0.6242742604368261,
      "grad_norm": 0.38690152764320374,
      "learning_rate": 1.5593166551390722e-05,
      "loss": 0.525,
      "step": 20322
    },
    {
      "epoch": 0.6243049795717752,
      "grad_norm": 0.5880854725837708,
      "learning_rate": 1.5592765930135755e-05,
      "loss": 0.5461,
      "step": 20323
    },
    {
      "epoch": 0.6243356987067245,
      "grad_norm": 0.3164910674095154,
      "learning_rate": 1.559236529581849e-05,
      "loss": 0.5702,
      "step": 20324
    },
    {
      "epoch": 0.6243664178416736,
      "grad_norm": 0.3293531537055969,
      "learning_rate": 1.5591964648439866e-05,
      "loss": 0.639,
      "step": 20325
    },
    {
      "epoch": 0.6243971369766227,
      "grad_norm": 0.3801756799221039,
      "learning_rate": 1.5591563988000816e-05,
      "loss": 0.4494,
      "step": 20326
    },
    {
      "epoch": 0.6244278561115719,
      "grad_norm": 0.34833499789237976,
      "learning_rate": 1.5591163314502283e-05,
      "loss": 0.5045,
      "step": 20327
    },
    {
      "epoch": 0.624458575246521,
      "grad_norm": 0.3804747760295868,
      "learning_rate": 1.559076262794519e-05,
      "loss": 0.5596,
      "step": 20328
    },
    {
      "epoch": 0.6244892943814703,
      "grad_norm": 0.3530394732952118,
      "learning_rate": 1.5590361928330487e-05,
      "loss": 0.5817,
      "step": 20329
    },
    {
      "epoch": 0.6245200135164194,
      "grad_norm": 0.3381734788417816,
      "learning_rate": 1.5589961215659103e-05,
      "loss": 0.4873,
      "step": 20330
    },
    {
      "epoch": 0.6245507326513685,
      "grad_norm": 0.35292479395866394,
      "learning_rate": 1.558956048993197e-05,
      "loss": 0.5822,
      "step": 20331
    },
    {
      "epoch": 0.6245814517863177,
      "grad_norm": 0.33589720726013184,
      "learning_rate": 1.5589159751150028e-05,
      "loss": 0.5516,
      "step": 20332
    },
    {
      "epoch": 0.6246121709212669,
      "grad_norm": 0.4186857044696808,
      "learning_rate": 1.558875899931422e-05,
      "loss": 0.5724,
      "step": 20333
    },
    {
      "epoch": 0.624642890056216,
      "grad_norm": 0.3641681969165802,
      "learning_rate": 1.558835823442547e-05,
      "loss": 0.5258,
      "step": 20334
    },
    {
      "epoch": 0.6246736091911652,
      "grad_norm": 0.36163365840911865,
      "learning_rate": 1.558795745648472e-05,
      "loss": 0.5774,
      "step": 20335
    },
    {
      "epoch": 0.6247043283261143,
      "grad_norm": 0.4218415319919586,
      "learning_rate": 1.55875566654929e-05,
      "loss": 0.5487,
      "step": 20336
    },
    {
      "epoch": 0.6247350474610635,
      "grad_norm": 0.3333381116390228,
      "learning_rate": 1.558715586145096e-05,
      "loss": 0.6728,
      "step": 20337
    },
    {
      "epoch": 0.6247657665960127,
      "grad_norm": 0.3613649010658264,
      "learning_rate": 1.558675504435982e-05,
      "loss": 0.4685,
      "step": 20338
    },
    {
      "epoch": 0.6247964857309618,
      "grad_norm": 0.31287825107574463,
      "learning_rate": 1.558635421422043e-05,
      "loss": 0.4974,
      "step": 20339
    },
    {
      "epoch": 0.6248272048659109,
      "grad_norm": 0.36588823795318604,
      "learning_rate": 1.5585953371033717e-05,
      "loss": 0.5454,
      "step": 20340
    },
    {
      "epoch": 0.6248579240008602,
      "grad_norm": 0.4029732942581177,
      "learning_rate": 1.5585552514800615e-05,
      "loss": 0.6342,
      "step": 20341
    },
    {
      "epoch": 0.6248886431358093,
      "grad_norm": 0.349438339471817,
      "learning_rate": 1.5585151645522068e-05,
      "loss": 0.5102,
      "step": 20342
    },
    {
      "epoch": 0.6249193622707585,
      "grad_norm": 0.36874547600746155,
      "learning_rate": 1.5584750763199013e-05,
      "loss": 0.6263,
      "step": 20343
    },
    {
      "epoch": 0.6249500814057076,
      "grad_norm": 0.39016738533973694,
      "learning_rate": 1.558434986783238e-05,
      "loss": 0.611,
      "step": 20344
    },
    {
      "epoch": 0.6249808005406567,
      "grad_norm": 0.4183611273765564,
      "learning_rate": 1.5583948959423106e-05,
      "loss": 0.5467,
      "step": 20345
    },
    {
      "epoch": 0.625011519675606,
      "grad_norm": 0.3780514597892761,
      "learning_rate": 1.558354803797213e-05,
      "loss": 0.5429,
      "step": 20346
    },
    {
      "epoch": 0.6250422388105551,
      "grad_norm": 0.34606581926345825,
      "learning_rate": 1.558314710348039e-05,
      "loss": 0.5278,
      "step": 20347
    },
    {
      "epoch": 0.6250729579455042,
      "grad_norm": 0.3839844763278961,
      "learning_rate": 1.5582746155948816e-05,
      "loss": 0.4788,
      "step": 20348
    },
    {
      "epoch": 0.6251036770804534,
      "grad_norm": 0.34468334913253784,
      "learning_rate": 1.5582345195378356e-05,
      "loss": 0.5722,
      "step": 20349
    },
    {
      "epoch": 0.6251343962154026,
      "grad_norm": 0.7304366230964661,
      "learning_rate": 1.558194422176993e-05,
      "loss": 0.5452,
      "step": 20350
    },
    {
      "epoch": 0.6251651153503517,
      "grad_norm": 0.67729651927948,
      "learning_rate": 1.558154323512449e-05,
      "loss": 0.5696,
      "step": 20351
    },
    {
      "epoch": 0.6251958344853009,
      "grad_norm": 0.326732873916626,
      "learning_rate": 1.5581142235442962e-05,
      "loss": 0.6293,
      "step": 20352
    },
    {
      "epoch": 0.62522655362025,
      "grad_norm": 0.3587125539779663,
      "learning_rate": 1.5580741222726287e-05,
      "loss": 0.5842,
      "step": 20353
    },
    {
      "epoch": 0.6252572727551993,
      "grad_norm": 0.38662803173065186,
      "learning_rate": 1.55803401969754e-05,
      "loss": 0.618,
      "step": 20354
    },
    {
      "epoch": 0.6252879918901484,
      "grad_norm": 0.3704102337360382,
      "learning_rate": 1.5579939158191243e-05,
      "loss": 0.5068,
      "step": 20355
    },
    {
      "epoch": 0.6253187110250975,
      "grad_norm": 0.36692318320274353,
      "learning_rate": 1.5579538106374744e-05,
      "loss": 0.6086,
      "step": 20356
    },
    {
      "epoch": 0.6253494301600467,
      "grad_norm": 0.3747425377368927,
      "learning_rate": 1.557913704152685e-05,
      "loss": 0.5509,
      "step": 20357
    },
    {
      "epoch": 0.6253801492949959,
      "grad_norm": 0.36989927291870117,
      "learning_rate": 1.5578735963648486e-05,
      "loss": 0.548,
      "step": 20358
    },
    {
      "epoch": 0.625410868429945,
      "grad_norm": 0.45083093643188477,
      "learning_rate": 1.5578334872740596e-05,
      "loss": 0.5441,
      "step": 20359
    },
    {
      "epoch": 0.6254415875648942,
      "grad_norm": 0.3696020841598511,
      "learning_rate": 1.5577933768804117e-05,
      "loss": 0.5545,
      "step": 20360
    },
    {
      "epoch": 0.6254723066998433,
      "grad_norm": 0.32543450593948364,
      "learning_rate": 1.557753265183998e-05,
      "loss": 0.578,
      "step": 20361
    },
    {
      "epoch": 0.6255030258347924,
      "grad_norm": 0.3693821132183075,
      "learning_rate": 1.557713152184913e-05,
      "loss": 0.5607,
      "step": 20362
    },
    {
      "epoch": 0.6255337449697417,
      "grad_norm": 0.388360857963562,
      "learning_rate": 1.55767303788325e-05,
      "loss": 0.5603,
      "step": 20363
    },
    {
      "epoch": 0.6255644641046908,
      "grad_norm": 0.3571040630340576,
      "learning_rate": 1.5576329222791025e-05,
      "loss": 0.5965,
      "step": 20364
    },
    {
      "epoch": 0.6255951832396399,
      "grad_norm": 0.3314792513847351,
      "learning_rate": 1.5575928053725644e-05,
      "loss": 0.5526,
      "step": 20365
    },
    {
      "epoch": 0.6256259023745891,
      "grad_norm": 0.3671272397041321,
      "learning_rate": 1.5575526871637294e-05,
      "loss": 0.5595,
      "step": 20366
    },
    {
      "epoch": 0.6256566215095383,
      "grad_norm": 0.3597525954246521,
      "learning_rate": 1.5575125676526914e-05,
      "loss": 0.5451,
      "step": 20367
    },
    {
      "epoch": 0.6256873406444875,
      "grad_norm": 0.42397505044937134,
      "learning_rate": 1.557472446839543e-05,
      "loss": 0.5394,
      "step": 20368
    },
    {
      "epoch": 0.6257180597794366,
      "grad_norm": 0.39243772625923157,
      "learning_rate": 1.5574323247243795e-05,
      "loss": 0.5,
      "step": 20369
    },
    {
      "epoch": 0.6257487789143857,
      "grad_norm": 0.322532057762146,
      "learning_rate": 1.5573922013072937e-05,
      "loss": 0.5168,
      "step": 20370
    },
    {
      "epoch": 0.625779498049335,
      "grad_norm": 0.40949758887290955,
      "learning_rate": 1.5573520765883797e-05,
      "loss": 0.5877,
      "step": 20371
    },
    {
      "epoch": 0.6258102171842841,
      "grad_norm": 0.3303810656070709,
      "learning_rate": 1.5573119505677308e-05,
      "loss": 0.6063,
      "step": 20372
    },
    {
      "epoch": 0.6258409363192332,
      "grad_norm": 0.3624688982963562,
      "learning_rate": 1.557271823245441e-05,
      "loss": 0.5611,
      "step": 20373
    },
    {
      "epoch": 0.6258716554541824,
      "grad_norm": 0.3398160934448242,
      "learning_rate": 1.5572316946216037e-05,
      "loss": 0.5886,
      "step": 20374
    },
    {
      "epoch": 0.6259023745891316,
      "grad_norm": 0.32726097106933594,
      "learning_rate": 1.5571915646963128e-05,
      "loss": 0.4545,
      "step": 20375
    },
    {
      "epoch": 0.6259330937240807,
      "grad_norm": 0.3664303421974182,
      "learning_rate": 1.5571514334696626e-05,
      "loss": 0.6124,
      "step": 20376
    },
    {
      "epoch": 0.6259638128590299,
      "grad_norm": 0.3315085470676422,
      "learning_rate": 1.557111300941746e-05,
      "loss": 0.497,
      "step": 20377
    },
    {
      "epoch": 0.625994531993979,
      "grad_norm": 0.3742835223674774,
      "learning_rate": 1.557071167112657e-05,
      "loss": 0.6066,
      "step": 20378
    },
    {
      "epoch": 0.6260252511289283,
      "grad_norm": 0.48858344554901123,
      "learning_rate": 1.5570310319824895e-05,
      "loss": 0.5968,
      "step": 20379
    },
    {
      "epoch": 0.6260559702638774,
      "grad_norm": 0.45883843302726746,
      "learning_rate": 1.556990895551337e-05,
      "loss": 0.5385,
      "step": 20380
    },
    {
      "epoch": 0.6260866893988265,
      "grad_norm": 0.3296858072280884,
      "learning_rate": 1.5569507578192936e-05,
      "loss": 0.5691,
      "step": 20381
    },
    {
      "epoch": 0.6261174085337757,
      "grad_norm": 0.3481998145580292,
      "learning_rate": 1.5569106187864528e-05,
      "loss": 0.5321,
      "step": 20382
    },
    {
      "epoch": 0.6261481276687249,
      "grad_norm": 0.37513676285743713,
      "learning_rate": 1.556870478452908e-05,
      "loss": 0.5585,
      "step": 20383
    },
    {
      "epoch": 0.626178846803674,
      "grad_norm": 0.3349640667438507,
      "learning_rate": 1.5568303368187536e-05,
      "loss": 0.5661,
      "step": 20384
    },
    {
      "epoch": 0.6262095659386232,
      "grad_norm": 0.36723998188972473,
      "learning_rate": 1.556790193884083e-05,
      "loss": 0.6002,
      "step": 20385
    },
    {
      "epoch": 0.6262402850735723,
      "grad_norm": 0.4949514865875244,
      "learning_rate": 1.55675004964899e-05,
      "loss": 0.5483,
      "step": 20386
    },
    {
      "epoch": 0.6262710042085214,
      "grad_norm": 0.37252646684646606,
      "learning_rate": 1.5567099041135683e-05,
      "loss": 0.5546,
      "step": 20387
    },
    {
      "epoch": 0.6263017233434707,
      "grad_norm": 0.35027769207954407,
      "learning_rate": 1.556669757277912e-05,
      "loss": 0.5778,
      "step": 20388
    },
    {
      "epoch": 0.6263324424784198,
      "grad_norm": 0.34808480739593506,
      "learning_rate": 1.5566296091421143e-05,
      "loss": 0.5997,
      "step": 20389
    },
    {
      "epoch": 0.6263631616133689,
      "grad_norm": 0.35844239592552185,
      "learning_rate": 1.5565894597062692e-05,
      "loss": 0.4572,
      "step": 20390
    },
    {
      "epoch": 0.6263938807483181,
      "grad_norm": 0.3405925929546356,
      "learning_rate": 1.556549308970471e-05,
      "loss": 0.5414,
      "step": 20391
    },
    {
      "epoch": 0.6264245998832673,
      "grad_norm": 0.37571245431900024,
      "learning_rate": 1.5565091569348127e-05,
      "loss": 0.6482,
      "step": 20392
    },
    {
      "epoch": 0.6264553190182165,
      "grad_norm": 0.36241674423217773,
      "learning_rate": 1.5564690035993882e-05,
      "loss": 0.4692,
      "step": 20393
    },
    {
      "epoch": 0.6264860381531656,
      "grad_norm": 0.3588320314884186,
      "learning_rate": 1.556428848964292e-05,
      "loss": 0.5839,
      "step": 20394
    },
    {
      "epoch": 0.6265167572881147,
      "grad_norm": 0.37929967045783997,
      "learning_rate": 1.556388693029617e-05,
      "loss": 0.5599,
      "step": 20395
    },
    {
      "epoch": 0.626547476423064,
      "grad_norm": 0.3708060383796692,
      "learning_rate": 1.5563485357954572e-05,
      "loss": 0.5297,
      "step": 20396
    },
    {
      "epoch": 0.6265781955580131,
      "grad_norm": 0.38552412390708923,
      "learning_rate": 1.556308377261907e-05,
      "loss": 0.6319,
      "step": 20397
    },
    {
      "epoch": 0.6266089146929622,
      "grad_norm": 0.3585259020328522,
      "learning_rate": 1.5562682174290595e-05,
      "loss": 0.5436,
      "step": 20398
    },
    {
      "epoch": 0.6266396338279114,
      "grad_norm": 0.3690339922904968,
      "learning_rate": 1.5562280562970088e-05,
      "loss": 0.6288,
      "step": 20399
    },
    {
      "epoch": 0.6266703529628606,
      "grad_norm": 0.46102777123451233,
      "learning_rate": 1.5561878938658487e-05,
      "loss": 0.6163,
      "step": 20400
    },
    {
      "epoch": 0.6267010720978097,
      "grad_norm": 0.323840469121933,
      "learning_rate": 1.5561477301356725e-05,
      "loss": 0.5162,
      "step": 20401
    },
    {
      "epoch": 0.6267317912327589,
      "grad_norm": 0.3887838125228882,
      "learning_rate": 1.556107565106575e-05,
      "loss": 0.5217,
      "step": 20402
    },
    {
      "epoch": 0.626762510367708,
      "grad_norm": 0.36207377910614014,
      "learning_rate": 1.5560673987786494e-05,
      "loss": 0.6146,
      "step": 20403
    },
    {
      "epoch": 0.6267932295026573,
      "grad_norm": 0.34619376063346863,
      "learning_rate": 1.556027231151989e-05,
      "loss": 0.5619,
      "step": 20404
    },
    {
      "epoch": 0.6268239486376064,
      "grad_norm": 0.439299076795578,
      "learning_rate": 1.5559870622266884e-05,
      "loss": 0.5694,
      "step": 20405
    },
    {
      "epoch": 0.6268546677725555,
      "grad_norm": 0.3564947843551636,
      "learning_rate": 1.5559468920028412e-05,
      "loss": 0.5128,
      "step": 20406
    },
    {
      "epoch": 0.6268853869075047,
      "grad_norm": 0.3430590033531189,
      "learning_rate": 1.5559067204805412e-05,
      "loss": 0.6248,
      "step": 20407
    },
    {
      "epoch": 0.6269161060424538,
      "grad_norm": 0.4377790689468384,
      "learning_rate": 1.5558665476598827e-05,
      "loss": 0.556,
      "step": 20408
    },
    {
      "epoch": 0.626946825177403,
      "grad_norm": 0.3764573931694031,
      "learning_rate": 1.5558263735409585e-05,
      "loss": 0.4679,
      "step": 20409
    },
    {
      "epoch": 0.6269775443123522,
      "grad_norm": 0.3445410430431366,
      "learning_rate": 1.5557861981238632e-05,
      "loss": 0.5216,
      "step": 20410
    },
    {
      "epoch": 0.6270082634473013,
      "grad_norm": 0.3749435842037201,
      "learning_rate": 1.5557460214086905e-05,
      "loss": 0.5705,
      "step": 20411
    },
    {
      "epoch": 0.6270389825822504,
      "grad_norm": 0.3365252614021301,
      "learning_rate": 1.555705843395534e-05,
      "loss": 0.5454,
      "step": 20412
    },
    {
      "epoch": 0.6270697017171997,
      "grad_norm": 0.33961358666419983,
      "learning_rate": 1.555665664084488e-05,
      "loss": 0.5425,
      "step": 20413
    },
    {
      "epoch": 0.6271004208521488,
      "grad_norm": 0.38736483454704285,
      "learning_rate": 1.5556254834756455e-05,
      "loss": 0.5602,
      "step": 20414
    },
    {
      "epoch": 0.627131139987098,
      "grad_norm": 0.3686889111995697,
      "learning_rate": 1.555585301569101e-05,
      "loss": 0.5088,
      "step": 20415
    },
    {
      "epoch": 0.6271618591220471,
      "grad_norm": 0.3708992004394531,
      "learning_rate": 1.5555451183649485e-05,
      "loss": 0.5923,
      "step": 20416
    },
    {
      "epoch": 0.6271925782569963,
      "grad_norm": 0.3533540368080139,
      "learning_rate": 1.5555049338632815e-05,
      "loss": 0.5337,
      "step": 20417
    },
    {
      "epoch": 0.6272232973919455,
      "grad_norm": 0.3432773947715759,
      "learning_rate": 1.555464748064194e-05,
      "loss": 0.5947,
      "step": 20418
    },
    {
      "epoch": 0.6272540165268946,
      "grad_norm": 0.32339704036712646,
      "learning_rate": 1.5554245609677796e-05,
      "loss": 0.5675,
      "step": 20419
    },
    {
      "epoch": 0.6272847356618437,
      "grad_norm": 0.35667115449905396,
      "learning_rate": 1.5553843725741323e-05,
      "loss": 0.5159,
      "step": 20420
    },
    {
      "epoch": 0.627315454796793,
      "grad_norm": 0.6666114926338196,
      "learning_rate": 1.5553441828833463e-05,
      "loss": 0.5435,
      "step": 20421
    },
    {
      "epoch": 0.6273461739317421,
      "grad_norm": 0.3649226725101471,
      "learning_rate": 1.555303991895515e-05,
      "loss": 0.6304,
      "step": 20422
    },
    {
      "epoch": 0.6273768930666912,
      "grad_norm": 0.3630847930908203,
      "learning_rate": 1.5552637996107323e-05,
      "loss": 0.5141,
      "step": 20423
    },
    {
      "epoch": 0.6274076122016404,
      "grad_norm": 0.31804391741752625,
      "learning_rate": 1.5552236060290923e-05,
      "loss": 0.5937,
      "step": 20424
    },
    {
      "epoch": 0.6274383313365895,
      "grad_norm": 0.32584747672080994,
      "learning_rate": 1.5551834111506892e-05,
      "loss": 0.5879,
      "step": 20425
    },
    {
      "epoch": 0.6274690504715387,
      "grad_norm": 0.33412402868270874,
      "learning_rate": 1.555143214975616e-05,
      "loss": 0.5278,
      "step": 20426
    },
    {
      "epoch": 0.6274997696064879,
      "grad_norm": 0.3993333876132965,
      "learning_rate": 1.5551030175039673e-05,
      "loss": 0.5245,
      "step": 20427
    },
    {
      "epoch": 0.627530488741437,
      "grad_norm": 0.33502545952796936,
      "learning_rate": 1.5550628187358365e-05,
      "loss": 0.5657,
      "step": 20428
    },
    {
      "epoch": 0.6275612078763863,
      "grad_norm": 0.3404931426048279,
      "learning_rate": 1.5550226186713177e-05,
      "loss": 0.6055,
      "step": 20429
    },
    {
      "epoch": 0.6275919270113354,
      "grad_norm": 0.37626227736473083,
      "learning_rate": 1.554982417310505e-05,
      "loss": 0.5641,
      "step": 20430
    },
    {
      "epoch": 0.6276226461462845,
      "grad_norm": 0.41799941658973694,
      "learning_rate": 1.5549422146534922e-05,
      "loss": 0.5933,
      "step": 20431
    },
    {
      "epoch": 0.6276533652812337,
      "grad_norm": 0.3484961986541748,
      "learning_rate": 1.554902010700373e-05,
      "loss": 0.6127,
      "step": 20432
    },
    {
      "epoch": 0.6276840844161828,
      "grad_norm": 0.3641349673271179,
      "learning_rate": 1.5548618054512413e-05,
      "loss": 0.5556,
      "step": 20433
    },
    {
      "epoch": 0.627714803551132,
      "grad_norm": 0.41515618562698364,
      "learning_rate": 1.554821598906191e-05,
      "loss": 0.566,
      "step": 20434
    },
    {
      "epoch": 0.6277455226860812,
      "grad_norm": 0.3398890793323517,
      "learning_rate": 1.5547813910653164e-05,
      "loss": 0.5135,
      "step": 20435
    },
    {
      "epoch": 0.6277762418210303,
      "grad_norm": 0.3732627034187317,
      "learning_rate": 1.554741181928711e-05,
      "loss": 0.6581,
      "step": 20436
    },
    {
      "epoch": 0.6278069609559794,
      "grad_norm": 0.3755606710910797,
      "learning_rate": 1.5547009714964688e-05,
      "loss": 0.6143,
      "step": 20437
    },
    {
      "epoch": 0.6278376800909287,
      "grad_norm": 0.339266300201416,
      "learning_rate": 1.5546607597686838e-05,
      "loss": 0.5982,
      "step": 20438
    },
    {
      "epoch": 0.6278683992258778,
      "grad_norm": 0.3711911737918854,
      "learning_rate": 1.55462054674545e-05,
      "loss": 0.6118,
      "step": 20439
    },
    {
      "epoch": 0.627899118360827,
      "grad_norm": 0.37741419672966003,
      "learning_rate": 1.5545803324268608e-05,
      "loss": 0.5943,
      "step": 20440
    },
    {
      "epoch": 0.6279298374957761,
      "grad_norm": 0.3734387457370758,
      "learning_rate": 1.5545401168130102e-05,
      "loss": 0.6435,
      "step": 20441
    },
    {
      "epoch": 0.6279605566307253,
      "grad_norm": 0.35493794083595276,
      "learning_rate": 1.554499899903993e-05,
      "loss": 0.5139,
      "step": 20442
    },
    {
      "epoch": 0.6279912757656745,
      "grad_norm": 0.3818681538105011,
      "learning_rate": 1.554459681699903e-05,
      "loss": 0.5976,
      "step": 20443
    },
    {
      "epoch": 0.6280219949006236,
      "grad_norm": 0.3543015420436859,
      "learning_rate": 1.5544194622008328e-05,
      "loss": 0.5883,
      "step": 20444
    },
    {
      "epoch": 0.6280527140355727,
      "grad_norm": 0.3577049970626831,
      "learning_rate": 1.5543792414068776e-05,
      "loss": 0.6056,
      "step": 20445
    },
    {
      "epoch": 0.628083433170522,
      "grad_norm": 0.37554576992988586,
      "learning_rate": 1.554339019318131e-05,
      "loss": 0.516,
      "step": 20446
    },
    {
      "epoch": 0.6281141523054711,
      "grad_norm": 0.3587116301059723,
      "learning_rate": 1.5542987959346868e-05,
      "loss": 0.6028,
      "step": 20447
    },
    {
      "epoch": 0.6281448714404202,
      "grad_norm": 0.35254475474357605,
      "learning_rate": 1.554258571256639e-05,
      "loss": 0.584,
      "step": 20448
    },
    {
      "epoch": 0.6281755905753694,
      "grad_norm": 0.3810597062110901,
      "learning_rate": 1.554218345284082e-05,
      "loss": 0.5963,
      "step": 20449
    },
    {
      "epoch": 0.6282063097103185,
      "grad_norm": 0.33081164956092834,
      "learning_rate": 1.554178118017109e-05,
      "loss": 0.5702,
      "step": 20450
    },
    {
      "epoch": 0.6282370288452677,
      "grad_norm": 0.4131650924682617,
      "learning_rate": 1.5541378894558143e-05,
      "loss": 0.5955,
      "step": 20451
    },
    {
      "epoch": 0.6282677479802169,
      "grad_norm": 0.3811388313770294,
      "learning_rate": 1.554097659600292e-05,
      "loss": 0.5149,
      "step": 20452
    },
    {
      "epoch": 0.628298467115166,
      "grad_norm": 0.35823890566825867,
      "learning_rate": 1.5540574284506357e-05,
      "loss": 0.4822,
      "step": 20453
    },
    {
      "epoch": 0.6283291862501152,
      "grad_norm": 0.3847796618938446,
      "learning_rate": 1.55401719600694e-05,
      "loss": 0.5763,
      "step": 20454
    },
    {
      "epoch": 0.6283599053850644,
      "grad_norm": 0.3444887399673462,
      "learning_rate": 1.5539769622692983e-05,
      "loss": 0.5415,
      "step": 20455
    },
    {
      "epoch": 0.6283906245200135,
      "grad_norm": 0.37655991315841675,
      "learning_rate": 1.5539367272378042e-05,
      "loss": 0.5341,
      "step": 20456
    },
    {
      "epoch": 0.6284213436549627,
      "grad_norm": 0.3359065055847168,
      "learning_rate": 1.5538964909125527e-05,
      "loss": 0.544,
      "step": 20457
    },
    {
      "epoch": 0.6284520627899118,
      "grad_norm": 0.4218202531337738,
      "learning_rate": 1.553856253293637e-05,
      "loss": 0.59,
      "step": 20458
    },
    {
      "epoch": 0.628482781924861,
      "grad_norm": 0.35771822929382324,
      "learning_rate": 1.5538160143811514e-05,
      "loss": 0.53,
      "step": 20459
    },
    {
      "epoch": 0.6285135010598102,
      "grad_norm": 0.3386017084121704,
      "learning_rate": 1.55377577417519e-05,
      "loss": 0.5285,
      "step": 20460
    },
    {
      "epoch": 0.6285442201947593,
      "grad_norm": 0.37595507502555847,
      "learning_rate": 1.5537355326758462e-05,
      "loss": 0.568,
      "step": 20461
    },
    {
      "epoch": 0.6285749393297084,
      "grad_norm": 0.3615695536136627,
      "learning_rate": 1.553695289883215e-05,
      "loss": 0.5724,
      "step": 20462
    },
    {
      "epoch": 0.6286056584646577,
      "grad_norm": 0.4047395884990692,
      "learning_rate": 1.5536550457973892e-05,
      "loss": 0.6522,
      "step": 20463
    },
    {
      "epoch": 0.6286363775996068,
      "grad_norm": 0.35092693567276,
      "learning_rate": 1.5536148004184637e-05,
      "loss": 0.579,
      "step": 20464
    },
    {
      "epoch": 0.628667096734556,
      "grad_norm": 0.3631301820278168,
      "learning_rate": 1.553574553746532e-05,
      "loss": 0.5929,
      "step": 20465
    },
    {
      "epoch": 0.6286978158695051,
      "grad_norm": 0.47979989647865295,
      "learning_rate": 1.5535343057816884e-05,
      "loss": 0.5533,
      "step": 20466
    },
    {
      "epoch": 0.6287285350044542,
      "grad_norm": 0.34637317061424255,
      "learning_rate": 1.553494056524027e-05,
      "loss": 0.5101,
      "step": 20467
    },
    {
      "epoch": 0.6287592541394035,
      "grad_norm": 0.3926982879638672,
      "learning_rate": 1.553453805973641e-05,
      "loss": 0.559,
      "step": 20468
    },
    {
      "epoch": 0.6287899732743526,
      "grad_norm": 0.35731396079063416,
      "learning_rate": 1.5534135541306254e-05,
      "loss": 0.6466,
      "step": 20469
    },
    {
      "epoch": 0.6288206924093017,
      "grad_norm": 0.3476036787033081,
      "learning_rate": 1.553373300995074e-05,
      "loss": 0.5451,
      "step": 20470
    },
    {
      "epoch": 0.628851411544251,
      "grad_norm": 0.3408403992652893,
      "learning_rate": 1.5533330465670804e-05,
      "loss": 0.5345,
      "step": 20471
    },
    {
      "epoch": 0.6288821306792001,
      "grad_norm": 0.35337403416633606,
      "learning_rate": 1.5532927908467385e-05,
      "loss": 0.5299,
      "step": 20472
    },
    {
      "epoch": 0.6289128498141492,
      "grad_norm": 0.3565610349178314,
      "learning_rate": 1.5532525338341428e-05,
      "loss": 0.5219,
      "step": 20473
    },
    {
      "epoch": 0.6289435689490984,
      "grad_norm": 0.35909876227378845,
      "learning_rate": 1.5532122755293875e-05,
      "loss": 0.5764,
      "step": 20474
    },
    {
      "epoch": 0.6289742880840475,
      "grad_norm": 0.3503480851650238,
      "learning_rate": 1.553172015932566e-05,
      "loss": 0.5685,
      "step": 20475
    },
    {
      "epoch": 0.6290050072189967,
      "grad_norm": 0.37346675992012024,
      "learning_rate": 1.5531317550437725e-05,
      "loss": 0.6063,
      "step": 20476
    },
    {
      "epoch": 0.6290357263539459,
      "grad_norm": 0.3576838970184326,
      "learning_rate": 1.5530914928631015e-05,
      "loss": 0.5226,
      "step": 20477
    },
    {
      "epoch": 0.629066445488895,
      "grad_norm": 0.3738254904747009,
      "learning_rate": 1.5530512293906463e-05,
      "loss": 0.5713,
      "step": 20478
    },
    {
      "epoch": 0.6290971646238442,
      "grad_norm": 0.3547265827655792,
      "learning_rate": 1.5530109646265014e-05,
      "loss": 0.5057,
      "step": 20479
    },
    {
      "epoch": 0.6291278837587934,
      "grad_norm": 0.3845902383327484,
      "learning_rate": 1.552970698570761e-05,
      "loss": 0.5571,
      "step": 20480
    },
    {
      "epoch": 0.6291586028937425,
      "grad_norm": 0.303670734167099,
      "learning_rate": 1.552930431223519e-05,
      "loss": 0.4697,
      "step": 20481
    },
    {
      "epoch": 0.6291893220286917,
      "grad_norm": 0.35287436842918396,
      "learning_rate": 1.552890162584869e-05,
      "loss": 0.554,
      "step": 20482
    },
    {
      "epoch": 0.6292200411636408,
      "grad_norm": 0.37689483165740967,
      "learning_rate": 1.552849892654906e-05,
      "loss": 0.5305,
      "step": 20483
    },
    {
      "epoch": 0.62925076029859,
      "grad_norm": 0.341313898563385,
      "learning_rate": 1.5528096214337225e-05,
      "loss": 0.5409,
      "step": 20484
    },
    {
      "epoch": 0.6292814794335392,
      "grad_norm": 0.3480125367641449,
      "learning_rate": 1.5527693489214143e-05,
      "loss": 0.5502,
      "step": 20485
    },
    {
      "epoch": 0.6293121985684883,
      "grad_norm": 0.3598208427429199,
      "learning_rate": 1.5527290751180746e-05,
      "loss": 0.5825,
      "step": 20486
    },
    {
      "epoch": 0.6293429177034374,
      "grad_norm": 0.3815525770187378,
      "learning_rate": 1.5526888000237975e-05,
      "loss": 0.5199,
      "step": 20487
    },
    {
      "epoch": 0.6293736368383867,
      "grad_norm": 0.3319852948188782,
      "learning_rate": 1.552648523638677e-05,
      "loss": 0.5464,
      "step": 20488
    },
    {
      "epoch": 0.6294043559733358,
      "grad_norm": 0.3767613470554352,
      "learning_rate": 1.5526082459628074e-05,
      "loss": 0.5666,
      "step": 20489
    },
    {
      "epoch": 0.629435075108285,
      "grad_norm": 0.35610392689704895,
      "learning_rate": 1.5525679669962826e-05,
      "loss": 0.5492,
      "step": 20490
    },
    {
      "epoch": 0.6294657942432341,
      "grad_norm": 0.39223989844322205,
      "learning_rate": 1.5525276867391963e-05,
      "loss": 0.5672,
      "step": 20491
    },
    {
      "epoch": 0.6294965133781832,
      "grad_norm": 0.3839449882507324,
      "learning_rate": 1.5524874051916435e-05,
      "loss": 0.5421,
      "step": 20492
    },
    {
      "epoch": 0.6295272325131325,
      "grad_norm": 0.40603959560394287,
      "learning_rate": 1.5524471223537176e-05,
      "loss": 0.5817,
      "step": 20493
    },
    {
      "epoch": 0.6295579516480816,
      "grad_norm": 0.3871927857398987,
      "learning_rate": 1.5524068382255132e-05,
      "loss": 0.5378,
      "step": 20494
    },
    {
      "epoch": 0.6295886707830307,
      "grad_norm": 0.3058789074420929,
      "learning_rate": 1.5523665528071235e-05,
      "loss": 0.4918,
      "step": 20495
    },
    {
      "epoch": 0.6296193899179799,
      "grad_norm": 0.35998424887657166,
      "learning_rate": 1.5523262660986433e-05,
      "loss": 0.4836,
      "step": 20496
    },
    {
      "epoch": 0.6296501090529291,
      "grad_norm": 0.33925777673721313,
      "learning_rate": 1.552285978100167e-05,
      "loss": 0.5455,
      "step": 20497
    },
    {
      "epoch": 0.6296808281878782,
      "grad_norm": 0.436638206243515,
      "learning_rate": 1.5522456888117873e-05,
      "loss": 0.5888,
      "step": 20498
    },
    {
      "epoch": 0.6297115473228274,
      "grad_norm": 0.3938359022140503,
      "learning_rate": 1.5522053982335998e-05,
      "loss": 0.5956,
      "step": 20499
    },
    {
      "epoch": 0.6297422664577765,
      "grad_norm": 0.3435802757740021,
      "learning_rate": 1.5521651063656982e-05,
      "loss": 0.4817,
      "step": 20500
    },
    {
      "epoch": 0.6297729855927257,
      "grad_norm": 0.4295613467693329,
      "learning_rate": 1.5521248132081762e-05,
      "loss": 0.5625,
      "step": 20501
    },
    {
      "epoch": 0.6298037047276749,
      "grad_norm": 0.3144241273403168,
      "learning_rate": 1.552084518761128e-05,
      "loss": 0.5148,
      "step": 20502
    },
    {
      "epoch": 0.629834423862624,
      "grad_norm": 0.3551277816295624,
      "learning_rate": 1.5520442230246482e-05,
      "loss": 0.5358,
      "step": 20503
    },
    {
      "epoch": 0.6298651429975732,
      "grad_norm": 0.37462595105171204,
      "learning_rate": 1.5520039259988303e-05,
      "loss": 0.5539,
      "step": 20504
    },
    {
      "epoch": 0.6298958621325224,
      "grad_norm": 0.358066588640213,
      "learning_rate": 1.5519636276837687e-05,
      "loss": 0.5693,
      "step": 20505
    },
    {
      "epoch": 0.6299265812674715,
      "grad_norm": 0.40625783801078796,
      "learning_rate": 1.5519233280795578e-05,
      "loss": 0.5331,
      "step": 20506
    },
    {
      "epoch": 0.6299573004024207,
      "grad_norm": 0.3592485189437866,
      "learning_rate": 1.5518830271862912e-05,
      "loss": 0.4918,
      "step": 20507
    },
    {
      "epoch": 0.6299880195373698,
      "grad_norm": 0.3648546636104584,
      "learning_rate": 1.5518427250040634e-05,
      "loss": 0.6228,
      "step": 20508
    },
    {
      "epoch": 0.630018738672319,
      "grad_norm": 0.3484272360801697,
      "learning_rate": 1.5518024215329682e-05,
      "loss": 0.4928,
      "step": 20509
    },
    {
      "epoch": 0.6300494578072682,
      "grad_norm": 0.3424433469772339,
      "learning_rate": 1.5517621167731e-05,
      "loss": 0.5676,
      "step": 20510
    },
    {
      "epoch": 0.6300801769422173,
      "grad_norm": 0.3437756299972534,
      "learning_rate": 1.5517218107245525e-05,
      "loss": 0.5268,
      "step": 20511
    },
    {
      "epoch": 0.6301108960771664,
      "grad_norm": 0.3439585268497467,
      "learning_rate": 1.5516815033874207e-05,
      "loss": 0.5521,
      "step": 20512
    },
    {
      "epoch": 0.6301416152121156,
      "grad_norm": 0.3851661682128906,
      "learning_rate": 1.5516411947617977e-05,
      "loss": 0.5861,
      "step": 20513
    },
    {
      "epoch": 0.6301723343470648,
      "grad_norm": 0.390421986579895,
      "learning_rate": 1.5516008848477783e-05,
      "loss": 0.6113,
      "step": 20514
    },
    {
      "epoch": 0.630203053482014,
      "grad_norm": 0.35814282298088074,
      "learning_rate": 1.5515605736454566e-05,
      "loss": 0.5465,
      "step": 20515
    },
    {
      "epoch": 0.6302337726169631,
      "grad_norm": 0.3719334900379181,
      "learning_rate": 1.5515202611549266e-05,
      "loss": 0.5643,
      "step": 20516
    },
    {
      "epoch": 0.6302644917519122,
      "grad_norm": 0.4079569876194,
      "learning_rate": 1.551479947376283e-05,
      "loss": 0.5831,
      "step": 20517
    },
    {
      "epoch": 0.6302952108868615,
      "grad_norm": 0.3554408550262451,
      "learning_rate": 1.551439632309619e-05,
      "loss": 0.539,
      "step": 20518
    },
    {
      "epoch": 0.6303259300218106,
      "grad_norm": 0.3844473958015442,
      "learning_rate": 1.5513993159550292e-05,
      "loss": 0.4966,
      "step": 20519
    },
    {
      "epoch": 0.6303566491567597,
      "grad_norm": 0.35590845346450806,
      "learning_rate": 1.551358998312608e-05,
      "loss": 0.5315,
      "step": 20520
    },
    {
      "epoch": 0.6303873682917089,
      "grad_norm": 0.40069684386253357,
      "learning_rate": 1.551318679382449e-05,
      "loss": 0.5953,
      "step": 20521
    },
    {
      "epoch": 0.6304180874266581,
      "grad_norm": 0.3644263446331024,
      "learning_rate": 1.551278359164647e-05,
      "loss": 0.5808,
      "step": 20522
    },
    {
      "epoch": 0.6304488065616072,
      "grad_norm": 0.3472433090209961,
      "learning_rate": 1.551238037659296e-05,
      "loss": 0.5225,
      "step": 20523
    },
    {
      "epoch": 0.6304795256965564,
      "grad_norm": 0.36197564005851746,
      "learning_rate": 1.5511977148664898e-05,
      "loss": 0.5737,
      "step": 20524
    },
    {
      "epoch": 0.6305102448315055,
      "grad_norm": 0.3834817111492157,
      "learning_rate": 1.551157390786323e-05,
      "loss": 0.5373,
      "step": 20525
    },
    {
      "epoch": 0.6305409639664548,
      "grad_norm": 0.3339015543460846,
      "learning_rate": 1.5511170654188895e-05,
      "loss": 0.5751,
      "step": 20526
    },
    {
      "epoch": 0.6305716831014039,
      "grad_norm": 0.3716455399990082,
      "learning_rate": 1.5510767387642836e-05,
      "loss": 0.5389,
      "step": 20527
    },
    {
      "epoch": 0.630602402236353,
      "grad_norm": 0.3447161912918091,
      "learning_rate": 1.5510364108226e-05,
      "loss": 0.5445,
      "step": 20528
    },
    {
      "epoch": 0.6306331213713022,
      "grad_norm": 0.34782522916793823,
      "learning_rate": 1.550996081593932e-05,
      "loss": 0.5392,
      "step": 20529
    },
    {
      "epoch": 0.6306638405062513,
      "grad_norm": 0.39493536949157715,
      "learning_rate": 1.550955751078374e-05,
      "loss": 0.623,
      "step": 20530
    },
    {
      "epoch": 0.6306945596412005,
      "grad_norm": 0.339934378862381,
      "learning_rate": 1.5509154192760204e-05,
      "loss": 0.5161,
      "step": 20531
    },
    {
      "epoch": 0.6307252787761497,
      "grad_norm": 0.3500380516052246,
      "learning_rate": 1.5508750861869654e-05,
      "loss": 0.5597,
      "step": 20532
    },
    {
      "epoch": 0.6307559979110988,
      "grad_norm": 0.3801518380641937,
      "learning_rate": 1.5508347518113032e-05,
      "loss": 0.5706,
      "step": 20533
    },
    {
      "epoch": 0.6307867170460479,
      "grad_norm": 0.3735102117061615,
      "learning_rate": 1.5507944161491278e-05,
      "loss": 0.5597,
      "step": 20534
    },
    {
      "epoch": 0.6308174361809972,
      "grad_norm": 0.3631405234336853,
      "learning_rate": 1.5507540792005336e-05,
      "loss": 0.571,
      "step": 20535
    },
    {
      "epoch": 0.6308481553159463,
      "grad_norm": 0.34059038758277893,
      "learning_rate": 1.5507137409656152e-05,
      "loss": 0.5472,
      "step": 20536
    },
    {
      "epoch": 0.6308788744508954,
      "grad_norm": 0.36077627539634705,
      "learning_rate": 1.550673401444466e-05,
      "loss": 0.5555,
      "step": 20537
    },
    {
      "epoch": 0.6309095935858446,
      "grad_norm": 0.33515822887420654,
      "learning_rate": 1.5506330606371808e-05,
      "loss": 0.5767,
      "step": 20538
    },
    {
      "epoch": 0.6309403127207938,
      "grad_norm": 0.37249404191970825,
      "learning_rate": 1.550592718543854e-05,
      "loss": 0.5508,
      "step": 20539
    },
    {
      "epoch": 0.630971031855743,
      "grad_norm": 0.3659844994544983,
      "learning_rate": 1.5505523751645788e-05,
      "loss": 0.4624,
      "step": 20540
    },
    {
      "epoch": 0.6310017509906921,
      "grad_norm": 0.34699442982673645,
      "learning_rate": 1.5505120304994504e-05,
      "loss": 0.5236,
      "step": 20541
    },
    {
      "epoch": 0.6310324701256412,
      "grad_norm": 0.34897685050964355,
      "learning_rate": 1.5504716845485626e-05,
      "loss": 0.5076,
      "step": 20542
    },
    {
      "epoch": 0.6310631892605905,
      "grad_norm": 0.38492971658706665,
      "learning_rate": 1.5504313373120096e-05,
      "loss": 0.5784,
      "step": 20543
    },
    {
      "epoch": 0.6310939083955396,
      "grad_norm": 0.37766900658607483,
      "learning_rate": 1.5503909887898862e-05,
      "loss": 0.5803,
      "step": 20544
    },
    {
      "epoch": 0.6311246275304887,
      "grad_norm": 0.34090855717658997,
      "learning_rate": 1.5503506389822856e-05,
      "loss": 0.6352,
      "step": 20545
    },
    {
      "epoch": 0.6311553466654379,
      "grad_norm": 0.34887561202049255,
      "learning_rate": 1.550310287889303e-05,
      "loss": 0.5511,
      "step": 20546
    },
    {
      "epoch": 0.631186065800387,
      "grad_norm": 0.34751734137535095,
      "learning_rate": 1.5502699355110324e-05,
      "loss": 0.5395,
      "step": 20547
    },
    {
      "epoch": 0.6312167849353362,
      "grad_norm": 0.37066540122032166,
      "learning_rate": 1.5502295818475677e-05,
      "loss": 0.5522,
      "step": 20548
    },
    {
      "epoch": 0.6312475040702854,
      "grad_norm": 0.40714436769485474,
      "learning_rate": 1.5501892268990037e-05,
      "loss": 0.6063,
      "step": 20549
    },
    {
      "epoch": 0.6312782232052345,
      "grad_norm": 0.4499944746494293,
      "learning_rate": 1.5501488706654337e-05,
      "loss": 0.5403,
      "step": 20550
    },
    {
      "epoch": 0.6313089423401838,
      "grad_norm": 0.3475160598754883,
      "learning_rate": 1.5501085131469534e-05,
      "loss": 0.6034,
      "step": 20551
    },
    {
      "epoch": 0.6313396614751329,
      "grad_norm": 0.35442328453063965,
      "learning_rate": 1.550068154343656e-05,
      "loss": 0.5222,
      "step": 20552
    },
    {
      "epoch": 0.631370380610082,
      "grad_norm": 0.4465176463127136,
      "learning_rate": 1.5500277942556354e-05,
      "loss": 0.5367,
      "step": 20553
    },
    {
      "epoch": 0.6314010997450312,
      "grad_norm": 0.3562955856323242,
      "learning_rate": 1.5499874328829872e-05,
      "loss": 0.5194,
      "step": 20554
    },
    {
      "epoch": 0.6314318188799803,
      "grad_norm": 0.3731214106082916,
      "learning_rate": 1.5499470702258043e-05,
      "loss": 0.6273,
      "step": 20555
    },
    {
      "epoch": 0.6314625380149295,
      "grad_norm": 0.3472862243652344,
      "learning_rate": 1.549906706284182e-05,
      "loss": 0.591,
      "step": 20556
    },
    {
      "epoch": 0.6314932571498787,
      "grad_norm": 0.3627469539642334,
      "learning_rate": 1.5498663410582145e-05,
      "loss": 0.4968,
      "step": 20557
    },
    {
      "epoch": 0.6315239762848278,
      "grad_norm": 0.449040025472641,
      "learning_rate": 1.5498259745479956e-05,
      "loss": 0.605,
      "step": 20558
    },
    {
      "epoch": 0.6315546954197769,
      "grad_norm": 0.3526633679866791,
      "learning_rate": 1.5497856067536196e-05,
      "loss": 0.5785,
      "step": 20559
    },
    {
      "epoch": 0.6315854145547262,
      "grad_norm": 0.40549594163894653,
      "learning_rate": 1.5497452376751806e-05,
      "loss": 0.6682,
      "step": 20560
    },
    {
      "epoch": 0.6316161336896753,
      "grad_norm": 0.857367992401123,
      "learning_rate": 1.5497048673127734e-05,
      "loss": 0.5702,
      "step": 20561
    },
    {
      "epoch": 0.6316468528246244,
      "grad_norm": 0.29835548996925354,
      "learning_rate": 1.5496644956664923e-05,
      "loss": 0.4883,
      "step": 20562
    },
    {
      "epoch": 0.6316775719595736,
      "grad_norm": 0.36649906635284424,
      "learning_rate": 1.5496241227364312e-05,
      "loss": 0.5498,
      "step": 20563
    },
    {
      "epoch": 0.6317082910945228,
      "grad_norm": 0.4365297853946686,
      "learning_rate": 1.5495837485226845e-05,
      "loss": 0.5465,
      "step": 20564
    },
    {
      "epoch": 0.631739010229472,
      "grad_norm": 0.36736178398132324,
      "learning_rate": 1.549543373025347e-05,
      "loss": 0.5937,
      "step": 20565
    },
    {
      "epoch": 0.6317697293644211,
      "grad_norm": 0.37375736236572266,
      "learning_rate": 1.5495029962445123e-05,
      "loss": 0.5368,
      "step": 20566
    },
    {
      "epoch": 0.6318004484993702,
      "grad_norm": 0.3342702388763428,
      "learning_rate": 1.5494626181802747e-05,
      "loss": 0.5033,
      "step": 20567
    },
    {
      "epoch": 0.6318311676343195,
      "grad_norm": 0.3606123626232147,
      "learning_rate": 1.5494222388327295e-05,
      "loss": 0.5195,
      "step": 20568
    },
    {
      "epoch": 0.6318618867692686,
      "grad_norm": 0.34914031624794006,
      "learning_rate": 1.5493818582019696e-05,
      "loss": 0.5355,
      "step": 20569
    },
    {
      "epoch": 0.6318926059042177,
      "grad_norm": 0.3298788368701935,
      "learning_rate": 1.54934147628809e-05,
      "loss": 0.5568,
      "step": 20570
    },
    {
      "epoch": 0.6319233250391669,
      "grad_norm": 0.31659412384033203,
      "learning_rate": 1.5493010930911855e-05,
      "loss": 0.5819,
      "step": 20571
    },
    {
      "epoch": 0.631954044174116,
      "grad_norm": 0.37260058522224426,
      "learning_rate": 1.5492607086113497e-05,
      "loss": 0.5815,
      "step": 20572
    },
    {
      "epoch": 0.6319847633090652,
      "grad_norm": 0.31667935848236084,
      "learning_rate": 1.5492203228486767e-05,
      "loss": 0.5884,
      "step": 20573
    },
    {
      "epoch": 0.6320154824440144,
      "grad_norm": 0.44548648595809937,
      "learning_rate": 1.549179935803262e-05,
      "loss": 0.6191,
      "step": 20574
    },
    {
      "epoch": 0.6320462015789635,
      "grad_norm": 0.3704669177532196,
      "learning_rate": 1.549139547475199e-05,
      "loss": 0.6566,
      "step": 20575
    },
    {
      "epoch": 0.6320769207139127,
      "grad_norm": 0.3571530878543854,
      "learning_rate": 1.549099157864582e-05,
      "loss": 0.5079,
      "step": 20576
    },
    {
      "epoch": 0.6321076398488619,
      "grad_norm": 0.3359098434448242,
      "learning_rate": 1.549058766971506e-05,
      "loss": 0.5531,
      "step": 20577
    },
    {
      "epoch": 0.632138358983811,
      "grad_norm": 0.3299316167831421,
      "learning_rate": 1.5490183747960646e-05,
      "loss": 0.5926,
      "step": 20578
    },
    {
      "epoch": 0.6321690781187602,
      "grad_norm": 0.3441930413246155,
      "learning_rate": 1.5489779813383525e-05,
      "loss": 0.5216,
      "step": 20579
    },
    {
      "epoch": 0.6321997972537093,
      "grad_norm": 0.36515337228775024,
      "learning_rate": 1.5489375865984638e-05,
      "loss": 0.5052,
      "step": 20580
    },
    {
      "epoch": 0.6322305163886585,
      "grad_norm": 0.34651175141334534,
      "learning_rate": 1.5488971905764932e-05,
      "loss": 0.489,
      "step": 20581
    },
    {
      "epoch": 0.6322612355236077,
      "grad_norm": 0.3564282953739166,
      "learning_rate": 1.548856793272535e-05,
      "loss": 0.5234,
      "step": 20582
    },
    {
      "epoch": 0.6322919546585568,
      "grad_norm": 0.3526737689971924,
      "learning_rate": 1.5488163946866833e-05,
      "loss": 0.5859,
      "step": 20583
    },
    {
      "epoch": 0.6323226737935059,
      "grad_norm": 0.36250051856040955,
      "learning_rate": 1.5487759948190323e-05,
      "loss": 0.4706,
      "step": 20584
    },
    {
      "epoch": 0.6323533929284552,
      "grad_norm": 0.3842659890651703,
      "learning_rate": 1.5487355936696772e-05,
      "loss": 0.553,
      "step": 20585
    },
    {
      "epoch": 0.6323841120634043,
      "grad_norm": 0.384400337934494,
      "learning_rate": 1.5486951912387115e-05,
      "loss": 0.6371,
      "step": 20586
    },
    {
      "epoch": 0.6324148311983534,
      "grad_norm": 0.4381459951400757,
      "learning_rate": 1.5486547875262296e-05,
      "loss": 0.601,
      "step": 20587
    },
    {
      "epoch": 0.6324455503333026,
      "grad_norm": 0.35756537318229675,
      "learning_rate": 1.5486143825323264e-05,
      "loss": 0.5774,
      "step": 20588
    },
    {
      "epoch": 0.6324762694682518,
      "grad_norm": 0.4041038155555725,
      "learning_rate": 1.548573976257096e-05,
      "loss": 0.5921,
      "step": 20589
    },
    {
      "epoch": 0.632506988603201,
      "grad_norm": 0.3591277301311493,
      "learning_rate": 1.5485335687006328e-05,
      "loss": 0.5234,
      "step": 20590
    },
    {
      "epoch": 0.6325377077381501,
      "grad_norm": 0.33940356969833374,
      "learning_rate": 1.548493159863031e-05,
      "loss": 0.532,
      "step": 20591
    },
    {
      "epoch": 0.6325684268730992,
      "grad_norm": 0.3424537479877472,
      "learning_rate": 1.5484527497443857e-05,
      "loss": 0.6378,
      "step": 20592
    },
    {
      "epoch": 0.6325991460080485,
      "grad_norm": 0.3633648455142975,
      "learning_rate": 1.54841233834479e-05,
      "loss": 0.5446,
      "step": 20593
    },
    {
      "epoch": 0.6326298651429976,
      "grad_norm": 0.39615964889526367,
      "learning_rate": 1.548371925664339e-05,
      "loss": 0.5463,
      "step": 20594
    },
    {
      "epoch": 0.6326605842779467,
      "grad_norm": 0.3161156475543976,
      "learning_rate": 1.5483315117031272e-05,
      "loss": 0.6039,
      "step": 20595
    },
    {
      "epoch": 0.6326913034128959,
      "grad_norm": 0.3578416705131531,
      "learning_rate": 1.5482910964612492e-05,
      "loss": 0.5133,
      "step": 20596
    },
    {
      "epoch": 0.632722022547845,
      "grad_norm": 0.36269715428352356,
      "learning_rate": 1.5482506799387987e-05,
      "loss": 0.4781,
      "step": 20597
    },
    {
      "epoch": 0.6327527416827942,
      "grad_norm": 0.32749316096305847,
      "learning_rate": 1.5482102621358705e-05,
      "loss": 0.598,
      "step": 20598
    },
    {
      "epoch": 0.6327834608177434,
      "grad_norm": 0.39082032442092896,
      "learning_rate": 1.5481698430525592e-05,
      "loss": 0.5036,
      "step": 20599
    },
    {
      "epoch": 0.6328141799526925,
      "grad_norm": 0.35259172320365906,
      "learning_rate": 1.5481294226889587e-05,
      "loss": 0.6591,
      "step": 20600
    },
    {
      "epoch": 0.6328448990876417,
      "grad_norm": 0.3608958423137665,
      "learning_rate": 1.5480890010451633e-05,
      "loss": 0.5696,
      "step": 20601
    },
    {
      "epoch": 0.6328756182225909,
      "grad_norm": 0.38871926069259644,
      "learning_rate": 1.5480485781212684e-05,
      "loss": 0.4914,
      "step": 20602
    },
    {
      "epoch": 0.63290633735754,
      "grad_norm": 0.3707088828086853,
      "learning_rate": 1.5480081539173675e-05,
      "loss": 0.541,
      "step": 20603
    },
    {
      "epoch": 0.6329370564924892,
      "grad_norm": 0.3155675232410431,
      "learning_rate": 1.5479677284335554e-05,
      "loss": 0.4528,
      "step": 20604
    },
    {
      "epoch": 0.6329677756274383,
      "grad_norm": 0.366276353597641,
      "learning_rate": 1.547927301669926e-05,
      "loss": 0.489,
      "step": 20605
    },
    {
      "epoch": 0.6329984947623875,
      "grad_norm": 0.37932366132736206,
      "learning_rate": 1.5478868736265745e-05,
      "loss": 0.6015,
      "step": 20606
    },
    {
      "epoch": 0.6330292138973367,
      "grad_norm": 0.6573251485824585,
      "learning_rate": 1.5478464443035947e-05,
      "loss": 0.5772,
      "step": 20607
    },
    {
      "epoch": 0.6330599330322858,
      "grad_norm": 0.3410279154777527,
      "learning_rate": 1.5478060137010816e-05,
      "loss": 0.4437,
      "step": 20608
    },
    {
      "epoch": 0.6330906521672349,
      "grad_norm": 0.3760042190551758,
      "learning_rate": 1.5477655818191292e-05,
      "loss": 0.6057,
      "step": 20609
    },
    {
      "epoch": 0.6331213713021842,
      "grad_norm": 0.4065687358379364,
      "learning_rate": 1.5477251486578318e-05,
      "loss": 0.5809,
      "step": 20610
    },
    {
      "epoch": 0.6331520904371333,
      "grad_norm": 0.4009949862957001,
      "learning_rate": 1.5476847142172843e-05,
      "loss": 0.583,
      "step": 20611
    },
    {
      "epoch": 0.6331828095720825,
      "grad_norm": 0.49443402886390686,
      "learning_rate": 1.5476442784975808e-05,
      "loss": 0.5558,
      "step": 20612
    },
    {
      "epoch": 0.6332135287070316,
      "grad_norm": 0.3432754576206207,
      "learning_rate": 1.5476038414988156e-05,
      "loss": 0.5381,
      "step": 20613
    },
    {
      "epoch": 0.6332442478419807,
      "grad_norm": 0.3635360896587372,
      "learning_rate": 1.547563403221084e-05,
      "loss": 0.5932,
      "step": 20614
    },
    {
      "epoch": 0.63327496697693,
      "grad_norm": 0.36128470301628113,
      "learning_rate": 1.5475229636644793e-05,
      "loss": 0.6386,
      "step": 20615
    },
    {
      "epoch": 0.6333056861118791,
      "grad_norm": 0.3623252213001251,
      "learning_rate": 1.5474825228290966e-05,
      "loss": 0.5906,
      "step": 20616
    },
    {
      "epoch": 0.6333364052468282,
      "grad_norm": 0.4556536078453064,
      "learning_rate": 1.5474420807150303e-05,
      "loss": 0.6126,
      "step": 20617
    },
    {
      "epoch": 0.6333671243817774,
      "grad_norm": 0.335367351770401,
      "learning_rate": 1.547401637322375e-05,
      "loss": 0.4873,
      "step": 20618
    },
    {
      "epoch": 0.6333978435167266,
      "grad_norm": 0.31407225131988525,
      "learning_rate": 1.5473611926512245e-05,
      "loss": 0.5533,
      "step": 20619
    },
    {
      "epoch": 0.6334285626516757,
      "grad_norm": 0.3477489650249481,
      "learning_rate": 1.547320746701674e-05,
      "loss": 0.5822,
      "step": 20620
    },
    {
      "epoch": 0.6334592817866249,
      "grad_norm": 0.3763788938522339,
      "learning_rate": 1.5472802994738177e-05,
      "loss": 0.5807,
      "step": 20621
    },
    {
      "epoch": 0.633490000921574,
      "grad_norm": 0.35665056109428406,
      "learning_rate": 1.54723985096775e-05,
      "loss": 0.5802,
      "step": 20622
    },
    {
      "epoch": 0.6335207200565232,
      "grad_norm": 0.3646020293235779,
      "learning_rate": 1.547199401183565e-05,
      "loss": 0.5779,
      "step": 20623
    },
    {
      "epoch": 0.6335514391914724,
      "grad_norm": 0.3318079113960266,
      "learning_rate": 1.547158950121358e-05,
      "loss": 0.5059,
      "step": 20624
    },
    {
      "epoch": 0.6335821583264215,
      "grad_norm": 0.3685024678707123,
      "learning_rate": 1.5471184977812227e-05,
      "loss": 0.5975,
      "step": 20625
    },
    {
      "epoch": 0.6336128774613707,
      "grad_norm": 0.38560864329338074,
      "learning_rate": 1.5470780441632546e-05,
      "loss": 0.628,
      "step": 20626
    },
    {
      "epoch": 0.6336435965963199,
      "grad_norm": 0.386865496635437,
      "learning_rate": 1.547037589267547e-05,
      "loss": 0.558,
      "step": 20627
    },
    {
      "epoch": 0.633674315731269,
      "grad_norm": 0.3806707561016083,
      "learning_rate": 1.5469971330941952e-05,
      "loss": 0.5495,
      "step": 20628
    },
    {
      "epoch": 0.6337050348662182,
      "grad_norm": 0.36128732562065125,
      "learning_rate": 1.5469566756432933e-05,
      "loss": 0.4458,
      "step": 20629
    },
    {
      "epoch": 0.6337357540011673,
      "grad_norm": 0.3996214270591736,
      "learning_rate": 1.5469162169149356e-05,
      "loss": 0.4925,
      "step": 20630
    },
    {
      "epoch": 0.6337664731361164,
      "grad_norm": 0.32999929785728455,
      "learning_rate": 1.5468757569092173e-05,
      "loss": 0.5267,
      "step": 20631
    },
    {
      "epoch": 0.6337971922710657,
      "grad_norm": 0.3447803854942322,
      "learning_rate": 1.5468352956262323e-05,
      "loss": 0.5373,
      "step": 20632
    },
    {
      "epoch": 0.6338279114060148,
      "grad_norm": 0.3750666677951813,
      "learning_rate": 1.546794833066075e-05,
      "loss": 0.5645,
      "step": 20633
    },
    {
      "epoch": 0.6338586305409639,
      "grad_norm": 0.3979819416999817,
      "learning_rate": 1.5467543692288405e-05,
      "loss": 0.5475,
      "step": 20634
    },
    {
      "epoch": 0.6338893496759131,
      "grad_norm": 0.35353389382362366,
      "learning_rate": 1.5467139041146228e-05,
      "loss": 0.5866,
      "step": 20635
    },
    {
      "epoch": 0.6339200688108623,
      "grad_norm": 0.3958336412906647,
      "learning_rate": 1.5466734377235168e-05,
      "loss": 0.5522,
      "step": 20636
    },
    {
      "epoch": 0.6339507879458115,
      "grad_norm": 0.44844740629196167,
      "learning_rate": 1.5466329700556167e-05,
      "loss": 0.5976,
      "step": 20637
    },
    {
      "epoch": 0.6339815070807606,
      "grad_norm": 0.3868013620376587,
      "learning_rate": 1.546592501111017e-05,
      "loss": 0.5218,
      "step": 20638
    },
    {
      "epoch": 0.6340122262157097,
      "grad_norm": 0.3436957895755768,
      "learning_rate": 1.5465520308898128e-05,
      "loss": 0.5532,
      "step": 20639
    },
    {
      "epoch": 0.634042945350659,
      "grad_norm": 0.3283960223197937,
      "learning_rate": 1.546511559392098e-05,
      "loss": 0.4995,
      "step": 20640
    },
    {
      "epoch": 0.6340736644856081,
      "grad_norm": 0.35345005989074707,
      "learning_rate": 1.5464710866179668e-05,
      "loss": 0.5297,
      "step": 20641
    },
    {
      "epoch": 0.6341043836205572,
      "grad_norm": 0.3709981441497803,
      "learning_rate": 1.5464306125675146e-05,
      "loss": 0.5042,
      "step": 20642
    },
    {
      "epoch": 0.6341351027555064,
      "grad_norm": 0.3927631378173828,
      "learning_rate": 1.5463901372408354e-05,
      "loss": 0.5698,
      "step": 20643
    },
    {
      "epoch": 0.6341658218904556,
      "grad_norm": 0.34704309701919556,
      "learning_rate": 1.546349660638024e-05,
      "loss": 0.5325,
      "step": 20644
    },
    {
      "epoch": 0.6341965410254047,
      "grad_norm": 0.35497593879699707,
      "learning_rate": 1.546309182759175e-05,
      "loss": 0.5556,
      "step": 20645
    },
    {
      "epoch": 0.6342272601603539,
      "grad_norm": 0.34287047386169434,
      "learning_rate": 1.5462687036043825e-05,
      "loss": 0.504,
      "step": 20646
    },
    {
      "epoch": 0.634257979295303,
      "grad_norm": 0.32989874482154846,
      "learning_rate": 1.546228223173741e-05,
      "loss": 0.5294,
      "step": 20647
    },
    {
      "epoch": 0.6342886984302522,
      "grad_norm": 0.3911438286304474,
      "learning_rate": 1.5461877414673455e-05,
      "loss": 0.5963,
      "step": 20648
    },
    {
      "epoch": 0.6343194175652014,
      "grad_norm": 0.35218244791030884,
      "learning_rate": 1.5461472584852907e-05,
      "loss": 0.6245,
      "step": 20649
    },
    {
      "epoch": 0.6343501367001505,
      "grad_norm": 0.3385533094406128,
      "learning_rate": 1.5461067742276706e-05,
      "loss": 0.5378,
      "step": 20650
    },
    {
      "epoch": 0.6343808558350997,
      "grad_norm": 0.33788207173347473,
      "learning_rate": 1.5460662886945802e-05,
      "loss": 0.5953,
      "step": 20651
    },
    {
      "epoch": 0.6344115749700489,
      "grad_norm": 0.3946107029914856,
      "learning_rate": 1.5460258018861137e-05,
      "loss": 0.6214,
      "step": 20652
    },
    {
      "epoch": 0.634442294104998,
      "grad_norm": 0.38215965032577515,
      "learning_rate": 1.545985313802366e-05,
      "loss": 0.5225,
      "step": 20653
    },
    {
      "epoch": 0.6344730132399472,
      "grad_norm": 0.3689245283603668,
      "learning_rate": 1.545944824443431e-05,
      "loss": 0.5024,
      "step": 20654
    },
    {
      "epoch": 0.6345037323748963,
      "grad_norm": 0.35270994901657104,
      "learning_rate": 1.545904333809404e-05,
      "loss": 0.5439,
      "step": 20655
    },
    {
      "epoch": 0.6345344515098454,
      "grad_norm": 0.3805410861968994,
      "learning_rate": 1.5458638419003796e-05,
      "loss": 0.6138,
      "step": 20656
    },
    {
      "epoch": 0.6345651706447947,
      "grad_norm": 0.3736203908920288,
      "learning_rate": 1.545823348716452e-05,
      "loss": 0.5606,
      "step": 20657
    },
    {
      "epoch": 0.6345958897797438,
      "grad_norm": 0.35092538595199585,
      "learning_rate": 1.5457828542577152e-05,
      "loss": 0.5277,
      "step": 20658
    },
    {
      "epoch": 0.6346266089146929,
      "grad_norm": 0.3583061099052429,
      "learning_rate": 1.5457423585242648e-05,
      "loss": 0.525,
      "step": 20659
    },
    {
      "epoch": 0.6346573280496421,
      "grad_norm": 0.4489299952983856,
      "learning_rate": 1.545701861516195e-05,
      "loss": 0.5438,
      "step": 20660
    },
    {
      "epoch": 0.6346880471845913,
      "grad_norm": 0.34606486558914185,
      "learning_rate": 1.5456613632336007e-05,
      "loss": 0.6309,
      "step": 20661
    },
    {
      "epoch": 0.6347187663195405,
      "grad_norm": 0.349439799785614,
      "learning_rate": 1.5456208636765758e-05,
      "loss": 0.5612,
      "step": 20662
    },
    {
      "epoch": 0.6347494854544896,
      "grad_norm": 0.33288678526878357,
      "learning_rate": 1.5455803628452155e-05,
      "loss": 0.5209,
      "step": 20663
    },
    {
      "epoch": 0.6347802045894387,
      "grad_norm": 0.36087116599082947,
      "learning_rate": 1.545539860739614e-05,
      "loss": 0.5118,
      "step": 20664
    },
    {
      "epoch": 0.634810923724388,
      "grad_norm": 0.3262404501438141,
      "learning_rate": 1.545499357359866e-05,
      "loss": 0.5718,
      "step": 20665
    },
    {
      "epoch": 0.6348416428593371,
      "grad_norm": 0.33213570713996887,
      "learning_rate": 1.5454588527060664e-05,
      "loss": 0.5872,
      "step": 20666
    },
    {
      "epoch": 0.6348723619942862,
      "grad_norm": 0.3270513117313385,
      "learning_rate": 1.5454183467783095e-05,
      "loss": 0.5468,
      "step": 20667
    },
    {
      "epoch": 0.6349030811292354,
      "grad_norm": 0.3904571235179901,
      "learning_rate": 1.54537783957669e-05,
      "loss": 0.5836,
      "step": 20668
    },
    {
      "epoch": 0.6349338002641846,
      "grad_norm": 0.4107714891433716,
      "learning_rate": 1.5453373311013022e-05,
      "loss": 0.4721,
      "step": 20669
    },
    {
      "epoch": 0.6349645193991337,
      "grad_norm": 0.36879709362983704,
      "learning_rate": 1.5452968213522412e-05,
      "loss": 0.6164,
      "step": 20670
    },
    {
      "epoch": 0.6349952385340829,
      "grad_norm": 0.5524283051490784,
      "learning_rate": 1.545256310329601e-05,
      "loss": 0.5657,
      "step": 20671
    },
    {
      "epoch": 0.635025957669032,
      "grad_norm": 0.345878541469574,
      "learning_rate": 1.545215798033477e-05,
      "loss": 0.5574,
      "step": 20672
    },
    {
      "epoch": 0.6350566768039811,
      "grad_norm": 1.4070717096328735,
      "learning_rate": 1.5451752844639637e-05,
      "loss": 0.5322,
      "step": 20673
    },
    {
      "epoch": 0.6350873959389304,
      "grad_norm": 0.36917844414711,
      "learning_rate": 1.545134769621155e-05,
      "loss": 0.6207,
      "step": 20674
    },
    {
      "epoch": 0.6351181150738795,
      "grad_norm": 0.3268089294433594,
      "learning_rate": 1.545094253505146e-05,
      "loss": 0.5618,
      "step": 20675
    },
    {
      "epoch": 0.6351488342088287,
      "grad_norm": 0.3683381974697113,
      "learning_rate": 1.5450537361160315e-05,
      "loss": 0.5882,
      "step": 20676
    },
    {
      "epoch": 0.6351795533437778,
      "grad_norm": 0.5048633813858032,
      "learning_rate": 1.5450132174539057e-05,
      "loss": 0.6077,
      "step": 20677
    },
    {
      "epoch": 0.635210272478727,
      "grad_norm": 0.3426235020160675,
      "learning_rate": 1.5449726975188636e-05,
      "loss": 0.5075,
      "step": 20678
    },
    {
      "epoch": 0.6352409916136762,
      "grad_norm": 0.48833996057510376,
      "learning_rate": 1.5449321763109996e-05,
      "loss": 0.5382,
      "step": 20679
    },
    {
      "epoch": 0.6352717107486253,
      "grad_norm": 0.3817489743232727,
      "learning_rate": 1.5448916538304086e-05,
      "loss": 0.5356,
      "step": 20680
    },
    {
      "epoch": 0.6353024298835744,
      "grad_norm": 0.32480886578559875,
      "learning_rate": 1.544851130077185e-05,
      "loss": 0.537,
      "step": 20681
    },
    {
      "epoch": 0.6353331490185237,
      "grad_norm": 0.3687842786312103,
      "learning_rate": 1.5448106050514235e-05,
      "loss": 0.5925,
      "step": 20682
    },
    {
      "epoch": 0.6353638681534728,
      "grad_norm": 0.35520657896995544,
      "learning_rate": 1.544770078753219e-05,
      "loss": 0.5778,
      "step": 20683
    },
    {
      "epoch": 0.6353945872884219,
      "grad_norm": 0.4000779390335083,
      "learning_rate": 1.5447295511826658e-05,
      "loss": 0.6062,
      "step": 20684
    },
    {
      "epoch": 0.6354253064233711,
      "grad_norm": 0.3560211658477783,
      "learning_rate": 1.5446890223398586e-05,
      "loss": 0.6061,
      "step": 20685
    },
    {
      "epoch": 0.6354560255583203,
      "grad_norm": 0.3718532919883728,
      "learning_rate": 1.5446484922248922e-05,
      "loss": 0.5723,
      "step": 20686
    },
    {
      "epoch": 0.6354867446932695,
      "grad_norm": 0.34510546922683716,
      "learning_rate": 1.544607960837861e-05,
      "loss": 0.5603,
      "step": 20687
    },
    {
      "epoch": 0.6355174638282186,
      "grad_norm": 0.4259403944015503,
      "learning_rate": 1.5445674281788602e-05,
      "loss": 0.5856,
      "step": 20688
    },
    {
      "epoch": 0.6355481829631677,
      "grad_norm": 0.3514156639575958,
      "learning_rate": 1.544526894247984e-05,
      "loss": 0.6007,
      "step": 20689
    },
    {
      "epoch": 0.635578902098117,
      "grad_norm": 0.34669044613838196,
      "learning_rate": 1.5444863590453275e-05,
      "loss": 0.5555,
      "step": 20690
    },
    {
      "epoch": 0.6356096212330661,
      "grad_norm": 0.40064260363578796,
      "learning_rate": 1.5444458225709848e-05,
      "loss": 0.6062,
      "step": 20691
    },
    {
      "epoch": 0.6356403403680152,
      "grad_norm": 0.3235289752483368,
      "learning_rate": 1.544405284825051e-05,
      "loss": 0.5803,
      "step": 20692
    },
    {
      "epoch": 0.6356710595029644,
      "grad_norm": 0.38601207733154297,
      "learning_rate": 1.54436474580762e-05,
      "loss": 0.5844,
      "step": 20693
    },
    {
      "epoch": 0.6357017786379136,
      "grad_norm": 0.35080596804618835,
      "learning_rate": 1.544324205518788e-05,
      "loss": 0.548,
      "step": 20694
    },
    {
      "epoch": 0.6357324977728627,
      "grad_norm": 0.3823280930519104,
      "learning_rate": 1.5442836639586483e-05,
      "loss": 0.5961,
      "step": 20695
    },
    {
      "epoch": 0.6357632169078119,
      "grad_norm": 0.40195712447166443,
      "learning_rate": 1.5442431211272963e-05,
      "loss": 0.5391,
      "step": 20696
    },
    {
      "epoch": 0.635793936042761,
      "grad_norm": 0.3560311198234558,
      "learning_rate": 1.5442025770248263e-05,
      "loss": 0.6462,
      "step": 20697
    },
    {
      "epoch": 0.6358246551777101,
      "grad_norm": 0.35367000102996826,
      "learning_rate": 1.5441620316513332e-05,
      "loss": 0.5506,
      "step": 20698
    },
    {
      "epoch": 0.6358553743126594,
      "grad_norm": 0.4651823937892914,
      "learning_rate": 1.544121485006912e-05,
      "loss": 0.5981,
      "step": 20699
    },
    {
      "epoch": 0.6358860934476085,
      "grad_norm": 0.3703811764717102,
      "learning_rate": 1.5440809370916565e-05,
      "loss": 0.5399,
      "step": 20700
    },
    {
      "epoch": 0.6359168125825577,
      "grad_norm": 0.8316811323165894,
      "learning_rate": 1.5440403879056624e-05,
      "loss": 0.5265,
      "step": 20701
    },
    {
      "epoch": 0.6359475317175068,
      "grad_norm": 0.39461830258369446,
      "learning_rate": 1.543999837449024e-05,
      "loss": 0.5181,
      "step": 20702
    },
    {
      "epoch": 0.635978250852456,
      "grad_norm": 0.36780497431755066,
      "learning_rate": 1.5439592857218358e-05,
      "loss": 0.5954,
      "step": 20703
    },
    {
      "epoch": 0.6360089699874052,
      "grad_norm": 0.5289907455444336,
      "learning_rate": 1.5439187327241927e-05,
      "loss": 0.5227,
      "step": 20704
    },
    {
      "epoch": 0.6360396891223543,
      "grad_norm": 0.3992893695831299,
      "learning_rate": 1.5438781784561896e-05,
      "loss": 0.5889,
      "step": 20705
    },
    {
      "epoch": 0.6360704082573034,
      "grad_norm": 0.3405161499977112,
      "learning_rate": 1.543837622917921e-05,
      "loss": 0.4899,
      "step": 20706
    },
    {
      "epoch": 0.6361011273922527,
      "grad_norm": 0.3286382555961609,
      "learning_rate": 1.5437970661094814e-05,
      "loss": 0.5427,
      "step": 20707
    },
    {
      "epoch": 0.6361318465272018,
      "grad_norm": 0.40151527523994446,
      "learning_rate": 1.543756508030966e-05,
      "loss": 0.6525,
      "step": 20708
    },
    {
      "epoch": 0.6361625656621509,
      "grad_norm": 0.416187584400177,
      "learning_rate": 1.543715948682469e-05,
      "loss": 0.4958,
      "step": 20709
    },
    {
      "epoch": 0.6361932847971001,
      "grad_norm": 0.3576178550720215,
      "learning_rate": 1.543675388064086e-05,
      "loss": 0.5564,
      "step": 20710
    },
    {
      "epoch": 0.6362240039320493,
      "grad_norm": 0.3249701261520386,
      "learning_rate": 1.5436348261759108e-05,
      "loss": 0.5354,
      "step": 20711
    },
    {
      "epoch": 0.6362547230669985,
      "grad_norm": 0.4750104248523712,
      "learning_rate": 1.5435942630180384e-05,
      "loss": 0.5314,
      "step": 20712
    },
    {
      "epoch": 0.6362854422019476,
      "grad_norm": 0.35425230860710144,
      "learning_rate": 1.543553698590564e-05,
      "loss": 0.5812,
      "step": 20713
    },
    {
      "epoch": 0.6363161613368967,
      "grad_norm": 0.8439845442771912,
      "learning_rate": 1.5435131328935815e-05,
      "loss": 0.557,
      "step": 20714
    },
    {
      "epoch": 0.636346880471846,
      "grad_norm": 0.3976151943206787,
      "learning_rate": 1.5434725659271863e-05,
      "loss": 0.6146,
      "step": 20715
    },
    {
      "epoch": 0.6363775996067951,
      "grad_norm": 0.43389877676963806,
      "learning_rate": 1.543431997691473e-05,
      "loss": 0.6527,
      "step": 20716
    },
    {
      "epoch": 0.6364083187417442,
      "grad_norm": 0.3755555748939514,
      "learning_rate": 1.5433914281865365e-05,
      "loss": 0.5669,
      "step": 20717
    },
    {
      "epoch": 0.6364390378766934,
      "grad_norm": 0.3850994408130646,
      "learning_rate": 1.543350857412471e-05,
      "loss": 0.5758,
      "step": 20718
    },
    {
      "epoch": 0.6364697570116425,
      "grad_norm": 0.32519200444221497,
      "learning_rate": 1.5433102853693718e-05,
      "loss": 0.5734,
      "step": 20719
    },
    {
      "epoch": 0.6365004761465917,
      "grad_norm": 0.35938090085983276,
      "learning_rate": 1.5432697120573338e-05,
      "loss": 0.5271,
      "step": 20720
    },
    {
      "epoch": 0.6365311952815409,
      "grad_norm": 0.354297012090683,
      "learning_rate": 1.543229137476451e-05,
      "loss": 0.5496,
      "step": 20721
    },
    {
      "epoch": 0.63656191441649,
      "grad_norm": 0.3233354091644287,
      "learning_rate": 1.543188561626819e-05,
      "loss": 0.5185,
      "step": 20722
    },
    {
      "epoch": 0.6365926335514392,
      "grad_norm": 0.3785257339477539,
      "learning_rate": 1.5431479845085316e-05,
      "loss": 0.6376,
      "step": 20723
    },
    {
      "epoch": 0.6366233526863884,
      "grad_norm": 0.3564755916595459,
      "learning_rate": 1.5431074061216844e-05,
      "loss": 0.5143,
      "step": 20724
    },
    {
      "epoch": 0.6366540718213375,
      "grad_norm": 0.32328638434410095,
      "learning_rate": 1.5430668264663722e-05,
      "loss": 0.4431,
      "step": 20725
    },
    {
      "epoch": 0.6366847909562867,
      "grad_norm": 0.3565138280391693,
      "learning_rate": 1.543026245542689e-05,
      "loss": 0.5393,
      "step": 20726
    },
    {
      "epoch": 0.6367155100912358,
      "grad_norm": 0.3640054166316986,
      "learning_rate": 1.5429856633507307e-05,
      "loss": 0.5501,
      "step": 20727
    },
    {
      "epoch": 0.636746229226185,
      "grad_norm": 0.3780773878097534,
      "learning_rate": 1.5429450798905913e-05,
      "loss": 0.6163,
      "step": 20728
    },
    {
      "epoch": 0.6367769483611342,
      "grad_norm": 0.3750295341014862,
      "learning_rate": 1.5429044951623655e-05,
      "loss": 0.5645,
      "step": 20729
    },
    {
      "epoch": 0.6368076674960833,
      "grad_norm": 0.36474609375,
      "learning_rate": 1.5428639091661484e-05,
      "loss": 0.5589,
      "step": 20730
    },
    {
      "epoch": 0.6368383866310324,
      "grad_norm": 0.38259291648864746,
      "learning_rate": 1.5428233219020348e-05,
      "loss": 0.6142,
      "step": 20731
    },
    {
      "epoch": 0.6368691057659817,
      "grad_norm": 0.3590189516544342,
      "learning_rate": 1.542782733370119e-05,
      "loss": 0.5284,
      "step": 20732
    },
    {
      "epoch": 0.6368998249009308,
      "grad_norm": 0.375313401222229,
      "learning_rate": 1.5427421435704968e-05,
      "loss": 0.5501,
      "step": 20733
    },
    {
      "epoch": 0.6369305440358799,
      "grad_norm": 0.33337441086769104,
      "learning_rate": 1.542701552503262e-05,
      "loss": 0.5717,
      "step": 20734
    },
    {
      "epoch": 0.6369612631708291,
      "grad_norm": 0.3405343294143677,
      "learning_rate": 1.5426609601685104e-05,
      "loss": 0.5309,
      "step": 20735
    },
    {
      "epoch": 0.6369919823057782,
      "grad_norm": 0.4539313316345215,
      "learning_rate": 1.542620366566336e-05,
      "loss": 0.5388,
      "step": 20736
    },
    {
      "epoch": 0.6370227014407275,
      "grad_norm": 0.3602193593978882,
      "learning_rate": 1.5425797716968337e-05,
      "loss": 0.5627,
      "step": 20737
    },
    {
      "epoch": 0.6370534205756766,
      "grad_norm": 0.37307775020599365,
      "learning_rate": 1.5425391755600984e-05,
      "loss": 0.5472,
      "step": 20738
    },
    {
      "epoch": 0.6370841397106257,
      "grad_norm": 0.34480804204940796,
      "learning_rate": 1.5424985781562248e-05,
      "loss": 0.4821,
      "step": 20739
    },
    {
      "epoch": 0.637114858845575,
      "grad_norm": 0.3704259693622589,
      "learning_rate": 1.5424579794853082e-05,
      "loss": 0.5804,
      "step": 20740
    },
    {
      "epoch": 0.6371455779805241,
      "grad_norm": 0.3935807943344116,
      "learning_rate": 1.5424173795474428e-05,
      "loss": 0.4997,
      "step": 20741
    },
    {
      "epoch": 0.6371762971154732,
      "grad_norm": 0.3182840347290039,
      "learning_rate": 1.542376778342724e-05,
      "loss": 0.5532,
      "step": 20742
    },
    {
      "epoch": 0.6372070162504224,
      "grad_norm": 0.31924566626548767,
      "learning_rate": 1.5423361758712465e-05,
      "loss": 0.5298,
      "step": 20743
    },
    {
      "epoch": 0.6372377353853715,
      "grad_norm": 0.3846641182899475,
      "learning_rate": 1.5422955721331047e-05,
      "loss": 0.6265,
      "step": 20744
    },
    {
      "epoch": 0.6372684545203207,
      "grad_norm": 0.334900438785553,
      "learning_rate": 1.542254967128394e-05,
      "loss": 0.5522,
      "step": 20745
    },
    {
      "epoch": 0.6372991736552699,
      "grad_norm": 0.39805877208709717,
      "learning_rate": 1.5422143608572085e-05,
      "loss": 0.5738,
      "step": 20746
    },
    {
      "epoch": 0.637329892790219,
      "grad_norm": 0.3536311089992523,
      "learning_rate": 1.542173753319644e-05,
      "loss": 0.6673,
      "step": 20747
    },
    {
      "epoch": 0.6373606119251682,
      "grad_norm": 0.34713104367256165,
      "learning_rate": 1.5421331445157944e-05,
      "loss": 0.6164,
      "step": 20748
    },
    {
      "epoch": 0.6373913310601174,
      "grad_norm": 0.33841443061828613,
      "learning_rate": 1.542092534445755e-05,
      "loss": 0.5898,
      "step": 20749
    },
    {
      "epoch": 0.6374220501950665,
      "grad_norm": 0.39818644523620605,
      "learning_rate": 1.542051923109621e-05,
      "loss": 0.5448,
      "step": 20750
    },
    {
      "epoch": 0.6374527693300157,
      "grad_norm": 0.3755238652229309,
      "learning_rate": 1.5420113105074865e-05,
      "loss": 0.5395,
      "step": 20751
    },
    {
      "epoch": 0.6374834884649648,
      "grad_norm": 0.35733336210250854,
      "learning_rate": 1.541970696639447e-05,
      "loss": 0.5338,
      "step": 20752
    },
    {
      "epoch": 0.637514207599914,
      "grad_norm": 0.32510673999786377,
      "learning_rate": 1.541930081505597e-05,
      "loss": 0.5563,
      "step": 20753
    },
    {
      "epoch": 0.6375449267348632,
      "grad_norm": 0.3711097240447998,
      "learning_rate": 1.5418894651060314e-05,
      "loss": 0.5849,
      "step": 20754
    },
    {
      "epoch": 0.6375756458698123,
      "grad_norm": 0.34897685050964355,
      "learning_rate": 1.541848847440845e-05,
      "loss": 0.5304,
      "step": 20755
    },
    {
      "epoch": 0.6376063650047614,
      "grad_norm": 0.42798200249671936,
      "learning_rate": 1.541808228510133e-05,
      "loss": 0.5718,
      "step": 20756
    },
    {
      "epoch": 0.6376370841397107,
      "grad_norm": 2.154426336288452,
      "learning_rate": 1.54176760831399e-05,
      "loss": 0.546,
      "step": 20757
    },
    {
      "epoch": 0.6376678032746598,
      "grad_norm": 0.4037649929523468,
      "learning_rate": 1.5417269868525108e-05,
      "loss": 0.5783,
      "step": 20758
    },
    {
      "epoch": 0.6376985224096089,
      "grad_norm": 0.41507789492607117,
      "learning_rate": 1.5416863641257904e-05,
      "loss": 0.5569,
      "step": 20759
    },
    {
      "epoch": 0.6377292415445581,
      "grad_norm": 0.3546105921268463,
      "learning_rate": 1.541645740133924e-05,
      "loss": 0.5439,
      "step": 20760
    },
    {
      "epoch": 0.6377599606795072,
      "grad_norm": 0.374881774187088,
      "learning_rate": 1.5416051148770057e-05,
      "loss": 0.5702,
      "step": 20761
    },
    {
      "epoch": 0.6377906798144565,
      "grad_norm": 0.420716792345047,
      "learning_rate": 1.541564488355131e-05,
      "loss": 0.5774,
      "step": 20762
    },
    {
      "epoch": 0.6378213989494056,
      "grad_norm": 0.3426470160484314,
      "learning_rate": 1.5415238605683948e-05,
      "loss": 0.5308,
      "step": 20763
    },
    {
      "epoch": 0.6378521180843547,
      "grad_norm": 0.3916623592376709,
      "learning_rate": 1.5414832315168916e-05,
      "loss": 0.6849,
      "step": 20764
    },
    {
      "epoch": 0.6378828372193039,
      "grad_norm": 0.3270256817340851,
      "learning_rate": 1.5414426012007163e-05,
      "loss": 0.5459,
      "step": 20765
    },
    {
      "epoch": 0.6379135563542531,
      "grad_norm": 0.3480682075023651,
      "learning_rate": 1.5414019696199643e-05,
      "loss": 0.4922,
      "step": 20766
    },
    {
      "epoch": 0.6379442754892022,
      "grad_norm": 0.40008991956710815,
      "learning_rate": 1.5413613367747302e-05,
      "loss": 0.5978,
      "step": 20767
    },
    {
      "epoch": 0.6379749946241514,
      "grad_norm": 0.35763034224510193,
      "learning_rate": 1.5413207026651088e-05,
      "loss": 0.5022,
      "step": 20768
    },
    {
      "epoch": 0.6380057137591005,
      "grad_norm": 0.47359034419059753,
      "learning_rate": 1.5412800672911948e-05,
      "loss": 0.5115,
      "step": 20769
    },
    {
      "epoch": 0.6380364328940497,
      "grad_norm": 0.34236940741539,
      "learning_rate": 1.5412394306530834e-05,
      "loss": 0.5682,
      "step": 20770
    },
    {
      "epoch": 0.6380671520289989,
      "grad_norm": 0.38796931505203247,
      "learning_rate": 1.54119879275087e-05,
      "loss": 0.6241,
      "step": 20771
    },
    {
      "epoch": 0.638097871163948,
      "grad_norm": 0.3342176675796509,
      "learning_rate": 1.5411581535846488e-05,
      "loss": 0.5712,
      "step": 20772
    },
    {
      "epoch": 0.6381285902988972,
      "grad_norm": 0.3565404415130615,
      "learning_rate": 1.541117513154515e-05,
      "loss": 0.5355,
      "step": 20773
    },
    {
      "epoch": 0.6381593094338464,
      "grad_norm": 0.42896947264671326,
      "learning_rate": 1.541076871460563e-05,
      "loss": 0.587,
      "step": 20774
    },
    {
      "epoch": 0.6381900285687955,
      "grad_norm": 0.3301527202129364,
      "learning_rate": 1.541036228502889e-05,
      "loss": 0.4794,
      "step": 20775
    },
    {
      "epoch": 0.6382207477037447,
      "grad_norm": 0.35773420333862305,
      "learning_rate": 1.540995584281587e-05,
      "loss": 0.5426,
      "step": 20776
    },
    {
      "epoch": 0.6382514668386938,
      "grad_norm": 0.35400286316871643,
      "learning_rate": 1.5409549387967517e-05,
      "loss": 0.4602,
      "step": 20777
    },
    {
      "epoch": 0.638282185973643,
      "grad_norm": 0.35787689685821533,
      "learning_rate": 1.5409142920484784e-05,
      "loss": 0.5616,
      "step": 20778
    },
    {
      "epoch": 0.6383129051085922,
      "grad_norm": 0.6055699586868286,
      "learning_rate": 1.5408736440368616e-05,
      "loss": 0.5556,
      "step": 20779
    },
    {
      "epoch": 0.6383436242435413,
      "grad_norm": 0.38203462958335876,
      "learning_rate": 1.5408329947619972e-05,
      "loss": 0.6023,
      "step": 20780
    },
    {
      "epoch": 0.6383743433784904,
      "grad_norm": 0.3609989285469055,
      "learning_rate": 1.5407923442239793e-05,
      "loss": 0.6627,
      "step": 20781
    },
    {
      "epoch": 0.6384050625134396,
      "grad_norm": 0.4683116674423218,
      "learning_rate": 1.5407516924229035e-05,
      "loss": 0.5121,
      "step": 20782
    },
    {
      "epoch": 0.6384357816483888,
      "grad_norm": 0.39630070328712463,
      "learning_rate": 1.540711039358864e-05,
      "loss": 0.7149,
      "step": 20783
    },
    {
      "epoch": 0.6384665007833379,
      "grad_norm": 0.3756365478038788,
      "learning_rate": 1.5406703850319558e-05,
      "loss": 0.5426,
      "step": 20784
    },
    {
      "epoch": 0.6384972199182871,
      "grad_norm": 0.5582771897315979,
      "learning_rate": 1.5406297294422744e-05,
      "loss": 0.5218,
      "step": 20785
    },
    {
      "epoch": 0.6385279390532362,
      "grad_norm": 0.38374239206314087,
      "learning_rate": 1.540589072589915e-05,
      "loss": 0.589,
      "step": 20786
    },
    {
      "epoch": 0.6385586581881855,
      "grad_norm": 0.35624638199806213,
      "learning_rate": 1.5405484144749718e-05,
      "loss": 0.5646,
      "step": 20787
    },
    {
      "epoch": 0.6385893773231346,
      "grad_norm": 0.4281298518180847,
      "learning_rate": 1.5405077550975396e-05,
      "loss": 0.5883,
      "step": 20788
    },
    {
      "epoch": 0.6386200964580837,
      "grad_norm": 0.3845742344856262,
      "learning_rate": 1.540467094457714e-05,
      "loss": 0.6353,
      "step": 20789
    },
    {
      "epoch": 0.6386508155930329,
      "grad_norm": 0.5202739834785461,
      "learning_rate": 1.5404264325555896e-05,
      "loss": 0.5497,
      "step": 20790
    },
    {
      "epoch": 0.6386815347279821,
      "grad_norm": 0.3463848829269409,
      "learning_rate": 1.5403857693912622e-05,
      "loss": 0.5718,
      "step": 20791
    },
    {
      "epoch": 0.6387122538629312,
      "grad_norm": 0.35784783959388733,
      "learning_rate": 1.5403451049648252e-05,
      "loss": 0.5668,
      "step": 20792
    },
    {
      "epoch": 0.6387429729978804,
      "grad_norm": 0.3366399109363556,
      "learning_rate": 1.540304439276375e-05,
      "loss": 0.5938,
      "step": 20793
    },
    {
      "epoch": 0.6387736921328295,
      "grad_norm": 0.3377671241760254,
      "learning_rate": 1.540263772326006e-05,
      "loss": 0.6155,
      "step": 20794
    },
    {
      "epoch": 0.6388044112677786,
      "grad_norm": 0.3631085753440857,
      "learning_rate": 1.5402231041138135e-05,
      "loss": 0.5054,
      "step": 20795
    },
    {
      "epoch": 0.6388351304027279,
      "grad_norm": 0.3519534468650818,
      "learning_rate": 1.5401824346398916e-05,
      "loss": 0.5655,
      "step": 20796
    },
    {
      "epoch": 0.638865849537677,
      "grad_norm": 0.4018741250038147,
      "learning_rate": 1.5401417639043364e-05,
      "loss": 0.6043,
      "step": 20797
    },
    {
      "epoch": 0.6388965686726262,
      "grad_norm": 0.36169248819351196,
      "learning_rate": 1.540101091907242e-05,
      "loss": 0.6538,
      "step": 20798
    },
    {
      "epoch": 0.6389272878075754,
      "grad_norm": 0.3719204068183899,
      "learning_rate": 1.5400604186487043e-05,
      "loss": 0.6352,
      "step": 20799
    },
    {
      "epoch": 0.6389580069425245,
      "grad_norm": 0.3760837912559509,
      "learning_rate": 1.5400197441288174e-05,
      "loss": 0.5543,
      "step": 20800
    },
    {
      "epoch": 0.6389887260774737,
      "grad_norm": 0.4423889219760895,
      "learning_rate": 1.5399790683476767e-05,
      "loss": 0.5414,
      "step": 20801
    },
    {
      "epoch": 0.6390194452124228,
      "grad_norm": 0.3917571008205414,
      "learning_rate": 1.5399383913053772e-05,
      "loss": 0.6224,
      "step": 20802
    },
    {
      "epoch": 0.6390501643473719,
      "grad_norm": 0.3391745388507843,
      "learning_rate": 1.539897713002014e-05,
      "loss": 0.583,
      "step": 20803
    },
    {
      "epoch": 0.6390808834823212,
      "grad_norm": 0.41930949687957764,
      "learning_rate": 1.539857033437682e-05,
      "loss": 0.5317,
      "step": 20804
    },
    {
      "epoch": 0.6391116026172703,
      "grad_norm": 0.407981276512146,
      "learning_rate": 1.5398163526124757e-05,
      "loss": 0.5955,
      "step": 20805
    },
    {
      "epoch": 0.6391423217522194,
      "grad_norm": 0.3955775201320648,
      "learning_rate": 1.539775670526491e-05,
      "loss": 0.6376,
      "step": 20806
    },
    {
      "epoch": 0.6391730408871686,
      "grad_norm": 0.3503192663192749,
      "learning_rate": 1.5397349871798225e-05,
      "loss": 0.6108,
      "step": 20807
    },
    {
      "epoch": 0.6392037600221178,
      "grad_norm": 0.34872543811798096,
      "learning_rate": 1.5396943025725654e-05,
      "loss": 0.5565,
      "step": 20808
    },
    {
      "epoch": 0.6392344791570669,
      "grad_norm": 0.3625309467315674,
      "learning_rate": 1.5396536167048144e-05,
      "loss": 0.5641,
      "step": 20809
    },
    {
      "epoch": 0.6392651982920161,
      "grad_norm": 0.3512546718120575,
      "learning_rate": 1.5396129295766645e-05,
      "loss": 0.648,
      "step": 20810
    },
    {
      "epoch": 0.6392959174269652,
      "grad_norm": 0.380602091550827,
      "learning_rate": 1.5395722411882113e-05,
      "loss": 0.5424,
      "step": 20811
    },
    {
      "epoch": 0.6393266365619145,
      "grad_norm": 0.3533155620098114,
      "learning_rate": 1.5395315515395492e-05,
      "loss": 0.5646,
      "step": 20812
    },
    {
      "epoch": 0.6393573556968636,
      "grad_norm": 0.4151459336280823,
      "learning_rate": 1.5394908606307738e-05,
      "loss": 0.464,
      "step": 20813
    },
    {
      "epoch": 0.6393880748318127,
      "grad_norm": 0.37673863768577576,
      "learning_rate": 1.5394501684619793e-05,
      "loss": 0.5918,
      "step": 20814
    },
    {
      "epoch": 0.6394187939667619,
      "grad_norm": 0.35735154151916504,
      "learning_rate": 1.5394094750332616e-05,
      "loss": 0.5879,
      "step": 20815
    },
    {
      "epoch": 0.639449513101711,
      "grad_norm": 0.32787731289863586,
      "learning_rate": 1.539368780344715e-05,
      "loss": 0.5694,
      "step": 20816
    },
    {
      "epoch": 0.6394802322366602,
      "grad_norm": 0.38867661356925964,
      "learning_rate": 1.5393280843964356e-05,
      "loss": 0.6178,
      "step": 20817
    },
    {
      "epoch": 0.6395109513716094,
      "grad_norm": 0.3139607310295105,
      "learning_rate": 1.5392873871885174e-05,
      "loss": 0.5276,
      "step": 20818
    },
    {
      "epoch": 0.6395416705065585,
      "grad_norm": 0.8744598627090454,
      "learning_rate": 1.5392466887210558e-05,
      "loss": 0.6235,
      "step": 20819
    },
    {
      "epoch": 0.6395723896415076,
      "grad_norm": 0.36900168657302856,
      "learning_rate": 1.5392059889941464e-05,
      "loss": 0.5813,
      "step": 20820
    },
    {
      "epoch": 0.6396031087764569,
      "grad_norm": 0.39651721715927124,
      "learning_rate": 1.5391652880078832e-05,
      "loss": 0.6226,
      "step": 20821
    },
    {
      "epoch": 0.639633827911406,
      "grad_norm": 0.4150601327419281,
      "learning_rate": 1.539124585762362e-05,
      "loss": 0.4746,
      "step": 20822
    },
    {
      "epoch": 0.6396645470463552,
      "grad_norm": 0.3916657269001007,
      "learning_rate": 1.5390838822576774e-05,
      "loss": 0.6371,
      "step": 20823
    },
    {
      "epoch": 0.6396952661813043,
      "grad_norm": 0.3985803723335266,
      "learning_rate": 1.5390431774939248e-05,
      "loss": 0.6138,
      "step": 20824
    },
    {
      "epoch": 0.6397259853162535,
      "grad_norm": 0.38621610403060913,
      "learning_rate": 1.5390024714711994e-05,
      "loss": 0.6171,
      "step": 20825
    },
    {
      "epoch": 0.6397567044512027,
      "grad_norm": 0.35168588161468506,
      "learning_rate": 1.5389617641895963e-05,
      "loss": 0.6149,
      "step": 20826
    },
    {
      "epoch": 0.6397874235861518,
      "grad_norm": 0.3802066147327423,
      "learning_rate": 1.53892105564921e-05,
      "loss": 0.4938,
      "step": 20827
    },
    {
      "epoch": 0.6398181427211009,
      "grad_norm": 0.38327112793922424,
      "learning_rate": 1.538880345850136e-05,
      "loss": 0.5722,
      "step": 20828
    },
    {
      "epoch": 0.6398488618560502,
      "grad_norm": 0.35668909549713135,
      "learning_rate": 1.5388396347924698e-05,
      "loss": 0.5104,
      "step": 20829
    },
    {
      "epoch": 0.6398795809909993,
      "grad_norm": 0.324063241481781,
      "learning_rate": 1.538798922476305e-05,
      "loss": 0.4872,
      "step": 20830
    },
    {
      "epoch": 0.6399103001259484,
      "grad_norm": 0.3448141813278198,
      "learning_rate": 1.538758208901739e-05,
      "loss": 0.5741,
      "step": 20831
    },
    {
      "epoch": 0.6399410192608976,
      "grad_norm": 0.36655572056770325,
      "learning_rate": 1.538717494068864e-05,
      "loss": 0.5778,
      "step": 20832
    },
    {
      "epoch": 0.6399717383958468,
      "grad_norm": 0.31668636202812195,
      "learning_rate": 1.5386767779777782e-05,
      "loss": 0.5966,
      "step": 20833
    },
    {
      "epoch": 0.640002457530796,
      "grad_norm": 0.3346656858921051,
      "learning_rate": 1.5386360606285743e-05,
      "loss": 0.5643,
      "step": 20834
    },
    {
      "epoch": 0.6400331766657451,
      "grad_norm": 0.5087994337081909,
      "learning_rate": 1.5385953420213485e-05,
      "loss": 0.6153,
      "step": 20835
    },
    {
      "epoch": 0.6400638958006942,
      "grad_norm": 0.36429840326309204,
      "learning_rate": 1.5385546221561955e-05,
      "loss": 0.5531,
      "step": 20836
    },
    {
      "epoch": 0.6400946149356435,
      "grad_norm": 0.4043413996696472,
      "learning_rate": 1.5385139010332107e-05,
      "loss": 0.4874,
      "step": 20837
    },
    {
      "epoch": 0.6401253340705926,
      "grad_norm": 0.36924898624420166,
      "learning_rate": 1.538473178652489e-05,
      "loss": 0.4554,
      "step": 20838
    },
    {
      "epoch": 0.6401560532055417,
      "grad_norm": 0.3485294282436371,
      "learning_rate": 1.538432455014126e-05,
      "loss": 0.6355,
      "step": 20839
    },
    {
      "epoch": 0.6401867723404909,
      "grad_norm": 0.353496789932251,
      "learning_rate": 1.5383917301182158e-05,
      "loss": 0.5197,
      "step": 20840
    },
    {
      "epoch": 0.64021749147544,
      "grad_norm": 0.3431825041770935,
      "learning_rate": 1.5383510039648545e-05,
      "loss": 0.4991,
      "step": 20841
    },
    {
      "epoch": 0.6402482106103892,
      "grad_norm": 0.3692113757133484,
      "learning_rate": 1.5383102765541365e-05,
      "loss": 0.5504,
      "step": 20842
    },
    {
      "epoch": 0.6402789297453384,
      "grad_norm": 0.36240479350090027,
      "learning_rate": 1.5382695478861577e-05,
      "loss": 0.5895,
      "step": 20843
    },
    {
      "epoch": 0.6403096488802875,
      "grad_norm": 0.5612323880195618,
      "learning_rate": 1.5382288179610122e-05,
      "loss": 0.6117,
      "step": 20844
    },
    {
      "epoch": 0.6403403680152366,
      "grad_norm": 0.4030100107192993,
      "learning_rate": 1.5381880867787963e-05,
      "loss": 0.5857,
      "step": 20845
    },
    {
      "epoch": 0.6403710871501859,
      "grad_norm": 0.3628098666667938,
      "learning_rate": 1.5381473543396038e-05,
      "loss": 0.5478,
      "step": 20846
    },
    {
      "epoch": 0.640401806285135,
      "grad_norm": 0.34048354625701904,
      "learning_rate": 1.5381066206435314e-05,
      "loss": 0.5063,
      "step": 20847
    },
    {
      "epoch": 0.6404325254200842,
      "grad_norm": 0.34463179111480713,
      "learning_rate": 1.538065885690673e-05,
      "loss": 0.5652,
      "step": 20848
    },
    {
      "epoch": 0.6404632445550333,
      "grad_norm": 0.3524990975856781,
      "learning_rate": 1.5380251494811242e-05,
      "loss": 0.5592,
      "step": 20849
    },
    {
      "epoch": 0.6404939636899825,
      "grad_norm": 0.3656536638736725,
      "learning_rate": 1.53798441201498e-05,
      "loss": 0.6148,
      "step": 20850
    },
    {
      "epoch": 0.6405246828249317,
      "grad_norm": 0.32302892208099365,
      "learning_rate": 1.5379436732923358e-05,
      "loss": 0.5275,
      "step": 20851
    },
    {
      "epoch": 0.6405554019598808,
      "grad_norm": 0.4332520067691803,
      "learning_rate": 1.5379029333132866e-05,
      "loss": 0.5539,
      "step": 20852
    },
    {
      "epoch": 0.6405861210948299,
      "grad_norm": 0.3678499758243561,
      "learning_rate": 1.537862192077927e-05,
      "loss": 0.5246,
      "step": 20853
    },
    {
      "epoch": 0.6406168402297792,
      "grad_norm": 0.6043170690536499,
      "learning_rate": 1.5378214495863536e-05,
      "loss": 0.5469,
      "step": 20854
    },
    {
      "epoch": 0.6406475593647283,
      "grad_norm": 0.38966259360313416,
      "learning_rate": 1.5377807058386597e-05,
      "loss": 0.5233,
      "step": 20855
    },
    {
      "epoch": 0.6406782784996774,
      "grad_norm": 0.3550439178943634,
      "learning_rate": 1.537739960834942e-05,
      "loss": 0.5986,
      "step": 20856
    },
    {
      "epoch": 0.6407089976346266,
      "grad_norm": 0.3994467854499817,
      "learning_rate": 1.537699214575295e-05,
      "loss": 0.6188,
      "step": 20857
    },
    {
      "epoch": 0.6407397167695758,
      "grad_norm": 0.33483171463012695,
      "learning_rate": 1.537658467059814e-05,
      "loss": 0.5402,
      "step": 20858
    },
    {
      "epoch": 0.640770435904525,
      "grad_norm": 0.3513179123401642,
      "learning_rate": 1.5376177182885937e-05,
      "loss": 0.4559,
      "step": 20859
    },
    {
      "epoch": 0.6408011550394741,
      "grad_norm": 0.36502605676651,
      "learning_rate": 1.53757696826173e-05,
      "loss": 0.62,
      "step": 20860
    },
    {
      "epoch": 0.6408318741744232,
      "grad_norm": 0.3467021584510803,
      "learning_rate": 1.5375362169793177e-05,
      "loss": 0.5364,
      "step": 20861
    },
    {
      "epoch": 0.6408625933093725,
      "grad_norm": 0.38371577858924866,
      "learning_rate": 1.537495464441452e-05,
      "loss": 0.5055,
      "step": 20862
    },
    {
      "epoch": 0.6408933124443216,
      "grad_norm": 0.3472099006175995,
      "learning_rate": 1.537454710648228e-05,
      "loss": 0.6678,
      "step": 20863
    },
    {
      "epoch": 0.6409240315792707,
      "grad_norm": 0.3693546950817108,
      "learning_rate": 1.5374139555997413e-05,
      "loss": 0.5687,
      "step": 20864
    },
    {
      "epoch": 0.6409547507142199,
      "grad_norm": 0.36298009753227234,
      "learning_rate": 1.5373731992960864e-05,
      "loss": 0.5841,
      "step": 20865
    },
    {
      "epoch": 0.640985469849169,
      "grad_norm": 0.3719865679740906,
      "learning_rate": 1.537332441737359e-05,
      "loss": 0.6207,
      "step": 20866
    },
    {
      "epoch": 0.6410161889841182,
      "grad_norm": 0.36504945158958435,
      "learning_rate": 1.5372916829236545e-05,
      "loss": 0.6039,
      "step": 20867
    },
    {
      "epoch": 0.6410469081190674,
      "grad_norm": 0.3743671178817749,
      "learning_rate": 1.537250922855067e-05,
      "loss": 0.5676,
      "step": 20868
    },
    {
      "epoch": 0.6410776272540165,
      "grad_norm": 0.3298199474811554,
      "learning_rate": 1.537210161531693e-05,
      "loss": 0.5368,
      "step": 20869
    },
    {
      "epoch": 0.6411083463889656,
      "grad_norm": 0.3886088728904724,
      "learning_rate": 1.537169398953627e-05,
      "loss": 0.543,
      "step": 20870
    },
    {
      "epoch": 0.6411390655239149,
      "grad_norm": 0.3698728680610657,
      "learning_rate": 1.5371286351209643e-05,
      "loss": 0.5459,
      "step": 20871
    },
    {
      "epoch": 0.641169784658864,
      "grad_norm": 0.3116261661052704,
      "learning_rate": 1.5370878700338003e-05,
      "loss": 0.5102,
      "step": 20872
    },
    {
      "epoch": 0.6412005037938132,
      "grad_norm": 0.34786030650138855,
      "learning_rate": 1.53704710369223e-05,
      "loss": 0.5471,
      "step": 20873
    },
    {
      "epoch": 0.6412312229287623,
      "grad_norm": 0.3540440797805786,
      "learning_rate": 1.537006336096349e-05,
      "loss": 0.5652,
      "step": 20874
    },
    {
      "epoch": 0.6412619420637115,
      "grad_norm": 0.36045390367507935,
      "learning_rate": 1.536965567246252e-05,
      "loss": 0.5836,
      "step": 20875
    },
    {
      "epoch": 0.6412926611986607,
      "grad_norm": 0.35088762640953064,
      "learning_rate": 1.5369247971420342e-05,
      "loss": 0.5743,
      "step": 20876
    },
    {
      "epoch": 0.6413233803336098,
      "grad_norm": 0.4171912372112274,
      "learning_rate": 1.536884025783791e-05,
      "loss": 0.5131,
      "step": 20877
    },
    {
      "epoch": 0.6413540994685589,
      "grad_norm": 0.4174949526786804,
      "learning_rate": 1.536843253171618e-05,
      "loss": 0.599,
      "step": 20878
    },
    {
      "epoch": 0.6413848186035082,
      "grad_norm": 0.38767898082733154,
      "learning_rate": 1.5368024793056096e-05,
      "loss": 0.4437,
      "step": 20879
    },
    {
      "epoch": 0.6414155377384573,
      "grad_norm": 0.3775469660758972,
      "learning_rate": 1.5367617041858618e-05,
      "loss": 0.5954,
      "step": 20880
    },
    {
      "epoch": 0.6414462568734064,
      "grad_norm": 0.3442866802215576,
      "learning_rate": 1.5367209278124693e-05,
      "loss": 0.4426,
      "step": 20881
    },
    {
      "epoch": 0.6414769760083556,
      "grad_norm": 0.3539390563964844,
      "learning_rate": 1.536680150185528e-05,
      "loss": 0.5028,
      "step": 20882
    },
    {
      "epoch": 0.6415076951433047,
      "grad_norm": 0.32517609000205994,
      "learning_rate": 1.5366393713051325e-05,
      "loss": 0.5355,
      "step": 20883
    },
    {
      "epoch": 0.641538414278254,
      "grad_norm": 0.3497147858142853,
      "learning_rate": 1.5365985911713786e-05,
      "loss": 0.5731,
      "step": 20884
    },
    {
      "epoch": 0.6415691334132031,
      "grad_norm": 0.3645322322845459,
      "learning_rate": 1.536557809784361e-05,
      "loss": 0.534,
      "step": 20885
    },
    {
      "epoch": 0.6415998525481522,
      "grad_norm": 0.3056846857070923,
      "learning_rate": 1.5365170271441755e-05,
      "loss": 0.4847,
      "step": 20886
    },
    {
      "epoch": 0.6416305716831014,
      "grad_norm": 0.36134231090545654,
      "learning_rate": 1.5364762432509163e-05,
      "loss": 0.5569,
      "step": 20887
    },
    {
      "epoch": 0.6416612908180506,
      "grad_norm": 0.32816246151924133,
      "learning_rate": 1.53643545810468e-05,
      "loss": 0.557,
      "step": 20888
    },
    {
      "epoch": 0.6416920099529997,
      "grad_norm": 0.3362811803817749,
      "learning_rate": 1.5363946717055606e-05,
      "loss": 0.5905,
      "step": 20889
    },
    {
      "epoch": 0.6417227290879489,
      "grad_norm": 0.3576391339302063,
      "learning_rate": 1.5363538840536544e-05,
      "loss": 0.599,
      "step": 20890
    },
    {
      "epoch": 0.641753448222898,
      "grad_norm": 0.34165647625923157,
      "learning_rate": 1.5363130951490562e-05,
      "loss": 0.5034,
      "step": 20891
    },
    {
      "epoch": 0.6417841673578472,
      "grad_norm": 0.39356979727745056,
      "learning_rate": 1.5362723049918614e-05,
      "loss": 0.4751,
      "step": 20892
    },
    {
      "epoch": 0.6418148864927964,
      "grad_norm": 0.35495203733444214,
      "learning_rate": 1.536231513582165e-05,
      "loss": 0.5561,
      "step": 20893
    },
    {
      "epoch": 0.6418456056277455,
      "grad_norm": 0.35927629470825195,
      "learning_rate": 1.5361907209200623e-05,
      "loss": 0.5392,
      "step": 20894
    },
    {
      "epoch": 0.6418763247626946,
      "grad_norm": 0.4135212004184723,
      "learning_rate": 1.536149927005649e-05,
      "loss": 0.4691,
      "step": 20895
    },
    {
      "epoch": 0.6419070438976439,
      "grad_norm": 0.33481723070144653,
      "learning_rate": 1.53610913183902e-05,
      "loss": 0.5204,
      "step": 20896
    },
    {
      "epoch": 0.641937763032593,
      "grad_norm": 0.39213618636131287,
      "learning_rate": 1.5360683354202707e-05,
      "loss": 0.6237,
      "step": 20897
    },
    {
      "epoch": 0.6419684821675422,
      "grad_norm": 0.3819192349910736,
      "learning_rate": 1.5360275377494965e-05,
      "loss": 0.5602,
      "step": 20898
    },
    {
      "epoch": 0.6419992013024913,
      "grad_norm": 0.44466233253479004,
      "learning_rate": 1.5359867388267924e-05,
      "loss": 0.5725,
      "step": 20899
    },
    {
      "epoch": 0.6420299204374404,
      "grad_norm": 0.3888411521911621,
      "learning_rate": 1.535945938652254e-05,
      "loss": 0.5982,
      "step": 20900
    },
    {
      "epoch": 0.6420606395723897,
      "grad_norm": 0.4260590672492981,
      "learning_rate": 1.535905137225976e-05,
      "loss": 0.4823,
      "step": 20901
    },
    {
      "epoch": 0.6420913587073388,
      "grad_norm": 0.36727961897850037,
      "learning_rate": 1.5358643345480544e-05,
      "loss": 0.6115,
      "step": 20902
    },
    {
      "epoch": 0.6421220778422879,
      "grad_norm": 0.36011600494384766,
      "learning_rate": 1.5358235306185846e-05,
      "loss": 0.5766,
      "step": 20903
    },
    {
      "epoch": 0.6421527969772372,
      "grad_norm": 0.3337893784046173,
      "learning_rate": 1.535782725437661e-05,
      "loss": 0.5962,
      "step": 20904
    },
    {
      "epoch": 0.6421835161121863,
      "grad_norm": 0.3691105544567108,
      "learning_rate": 1.53574191900538e-05,
      "loss": 0.6058,
      "step": 20905
    },
    {
      "epoch": 0.6422142352471354,
      "grad_norm": 0.35306116938591003,
      "learning_rate": 1.5357011113218353e-05,
      "loss": 0.5731,
      "step": 20906
    },
    {
      "epoch": 0.6422449543820846,
      "grad_norm": 0.3464304804801941,
      "learning_rate": 1.5356603023871238e-05,
      "loss": 0.5436,
      "step": 20907
    },
    {
      "epoch": 0.6422756735170337,
      "grad_norm": 0.3951212465763092,
      "learning_rate": 1.535619492201341e-05,
      "loss": 0.5562,
      "step": 20908
    },
    {
      "epoch": 0.642306392651983,
      "grad_norm": 0.32665568590164185,
      "learning_rate": 1.5355786807645805e-05,
      "loss": 0.5791,
      "step": 20909
    },
    {
      "epoch": 0.6423371117869321,
      "grad_norm": 0.3780112862586975,
      "learning_rate": 1.5355378680769387e-05,
      "loss": 0.5513,
      "step": 20910
    },
    {
      "epoch": 0.6423678309218812,
      "grad_norm": 0.3381659984588623,
      "learning_rate": 1.535497054138511e-05,
      "loss": 0.5473,
      "step": 20911
    },
    {
      "epoch": 0.6423985500568304,
      "grad_norm": 0.3771618604660034,
      "learning_rate": 1.5354562389493928e-05,
      "loss": 0.5769,
      "step": 20912
    },
    {
      "epoch": 0.6424292691917796,
      "grad_norm": 0.3657260239124298,
      "learning_rate": 1.5354154225096783e-05,
      "loss": 0.5345,
      "step": 20913
    },
    {
      "epoch": 0.6424599883267287,
      "grad_norm": 0.3492717146873474,
      "learning_rate": 1.5353746048194648e-05,
      "loss": 0.5194,
      "step": 20914
    },
    {
      "epoch": 0.6424907074616779,
      "grad_norm": 0.3742915987968445,
      "learning_rate": 1.535333785878846e-05,
      "loss": 0.572,
      "step": 20915
    },
    {
      "epoch": 0.642521426596627,
      "grad_norm": 0.3834552466869354,
      "learning_rate": 1.5352929656879173e-05,
      "loss": 0.5389,
      "step": 20916
    },
    {
      "epoch": 0.6425521457315762,
      "grad_norm": 0.4887505769729614,
      "learning_rate": 1.535252144246775e-05,
      "loss": 0.625,
      "step": 20917
    },
    {
      "epoch": 0.6425828648665254,
      "grad_norm": 0.37432119250297546,
      "learning_rate": 1.5352113215555137e-05,
      "loss": 0.5669,
      "step": 20918
    },
    {
      "epoch": 0.6426135840014745,
      "grad_norm": 0.35921257734298706,
      "learning_rate": 1.5351704976142295e-05,
      "loss": 0.565,
      "step": 20919
    },
    {
      "epoch": 0.6426443031364237,
      "grad_norm": 0.4020228683948517,
      "learning_rate": 1.5351296724230167e-05,
      "loss": 0.5776,
      "step": 20920
    },
    {
      "epoch": 0.6426750222713729,
      "grad_norm": 0.3747492730617523,
      "learning_rate": 1.5350888459819712e-05,
      "loss": 0.5728,
      "step": 20921
    },
    {
      "epoch": 0.642705741406322,
      "grad_norm": 0.368836373090744,
      "learning_rate": 1.535048018291189e-05,
      "loss": 0.5963,
      "step": 20922
    },
    {
      "epoch": 0.6427364605412712,
      "grad_norm": 0.3211019039154053,
      "learning_rate": 1.5350071893507637e-05,
      "loss": 0.5372,
      "step": 20923
    },
    {
      "epoch": 0.6427671796762203,
      "grad_norm": 0.3805239796638489,
      "learning_rate": 1.5349663591607928e-05,
      "loss": 0.5645,
      "step": 20924
    },
    {
      "epoch": 0.6427978988111694,
      "grad_norm": 0.3502267301082611,
      "learning_rate": 1.53492552772137e-05,
      "loss": 0.5388,
      "step": 20925
    },
    {
      "epoch": 0.6428286179461187,
      "grad_norm": 0.34087899327278137,
      "learning_rate": 1.5348846950325915e-05,
      "loss": 0.5452,
      "step": 20926
    },
    {
      "epoch": 0.6428593370810678,
      "grad_norm": 0.3199111223220825,
      "learning_rate": 1.5348438610945523e-05,
      "loss": 0.4818,
      "step": 20927
    },
    {
      "epoch": 0.6428900562160169,
      "grad_norm": 0.3485901653766632,
      "learning_rate": 1.534803025907348e-05,
      "loss": 0.6056,
      "step": 20928
    },
    {
      "epoch": 0.6429207753509661,
      "grad_norm": 0.3199564516544342,
      "learning_rate": 1.5347621894710737e-05,
      "loss": 0.5179,
      "step": 20929
    },
    {
      "epoch": 0.6429514944859153,
      "grad_norm": 0.40650683641433716,
      "learning_rate": 1.534721351785825e-05,
      "loss": 0.5352,
      "step": 20930
    },
    {
      "epoch": 0.6429822136208644,
      "grad_norm": 0.3668935000896454,
      "learning_rate": 1.5346805128516972e-05,
      "loss": 0.532,
      "step": 20931
    },
    {
      "epoch": 0.6430129327558136,
      "grad_norm": 0.36821943521499634,
      "learning_rate": 1.534639672668786e-05,
      "loss": 0.5684,
      "step": 20932
    },
    {
      "epoch": 0.6430436518907627,
      "grad_norm": 0.35517168045043945,
      "learning_rate": 1.5345988312371865e-05,
      "loss": 0.5325,
      "step": 20933
    },
    {
      "epoch": 0.643074371025712,
      "grad_norm": 0.3482302725315094,
      "learning_rate": 1.5345579885569938e-05,
      "loss": 0.5399,
      "step": 20934
    },
    {
      "epoch": 0.6431050901606611,
      "grad_norm": 0.3526201546192169,
      "learning_rate": 1.5345171446283036e-05,
      "loss": 0.5457,
      "step": 20935
    },
    {
      "epoch": 0.6431358092956102,
      "grad_norm": 0.36651378870010376,
      "learning_rate": 1.5344762994512112e-05,
      "loss": 0.6171,
      "step": 20936
    },
    {
      "epoch": 0.6431665284305594,
      "grad_norm": 0.41763150691986084,
      "learning_rate": 1.5344354530258125e-05,
      "loss": 0.6012,
      "step": 20937
    },
    {
      "epoch": 0.6431972475655086,
      "grad_norm": 0.3550092577934265,
      "learning_rate": 1.5343946053522023e-05,
      "loss": 0.5514,
      "step": 20938
    },
    {
      "epoch": 0.6432279667004577,
      "grad_norm": 0.33637434244155884,
      "learning_rate": 1.534353756430476e-05,
      "loss": 0.6186,
      "step": 20939
    },
    {
      "epoch": 0.6432586858354069,
      "grad_norm": 0.3596220314502716,
      "learning_rate": 1.5343129062607297e-05,
      "loss": 0.5342,
      "step": 20940
    },
    {
      "epoch": 0.643289404970356,
      "grad_norm": 0.3487268090248108,
      "learning_rate": 1.5342720548430573e-05,
      "loss": 0.5348,
      "step": 20941
    },
    {
      "epoch": 0.6433201241053051,
      "grad_norm": 0.4124956429004669,
      "learning_rate": 1.5342312021775564e-05,
      "loss": 0.6236,
      "step": 20942
    },
    {
      "epoch": 0.6433508432402544,
      "grad_norm": 0.3736782670021057,
      "learning_rate": 1.5341903482643203e-05,
      "loss": 0.5236,
      "step": 20943
    },
    {
      "epoch": 0.6433815623752035,
      "grad_norm": 0.4179568290710449,
      "learning_rate": 1.5341494931034457e-05,
      "loss": 0.657,
      "step": 20944
    },
    {
      "epoch": 0.6434122815101527,
      "grad_norm": 0.37498927116394043,
      "learning_rate": 1.5341086366950275e-05,
      "loss": 0.5836,
      "step": 20945
    },
    {
      "epoch": 0.6434430006451018,
      "grad_norm": 0.3792065978050232,
      "learning_rate": 1.5340677790391614e-05,
      "loss": 0.5367,
      "step": 20946
    },
    {
      "epoch": 0.643473719780051,
      "grad_norm": 0.3634234368801117,
      "learning_rate": 1.5340269201359428e-05,
      "loss": 0.5228,
      "step": 20947
    },
    {
      "epoch": 0.6435044389150002,
      "grad_norm": 0.3433651626110077,
      "learning_rate": 1.533986059985467e-05,
      "loss": 0.5879,
      "step": 20948
    },
    {
      "epoch": 0.6435351580499493,
      "grad_norm": 0.3351402282714844,
      "learning_rate": 1.5339451985878297e-05,
      "loss": 0.542,
      "step": 20949
    },
    {
      "epoch": 0.6435658771848984,
      "grad_norm": 0.31583377718925476,
      "learning_rate": 1.5339043359431253e-05,
      "loss": 0.5073,
      "step": 20950
    },
    {
      "epoch": 0.6435965963198477,
      "grad_norm": 0.34151533246040344,
      "learning_rate": 1.5338634720514508e-05,
      "loss": 0.6071,
      "step": 20951
    },
    {
      "epoch": 0.6436273154547968,
      "grad_norm": 0.340353786945343,
      "learning_rate": 1.5338226069129004e-05,
      "loss": 0.6473,
      "step": 20952
    },
    {
      "epoch": 0.6436580345897459,
      "grad_norm": 0.3504771888256073,
      "learning_rate": 1.53378174052757e-05,
      "loss": 0.5377,
      "step": 20953
    },
    {
      "epoch": 0.6436887537246951,
      "grad_norm": 0.4145713448524475,
      "learning_rate": 1.5337408728955553e-05,
      "loss": 0.6044,
      "step": 20954
    },
    {
      "epoch": 0.6437194728596443,
      "grad_norm": 0.4213389456272125,
      "learning_rate": 1.5337000040169517e-05,
      "loss": 0.5941,
      "step": 20955
    },
    {
      "epoch": 0.6437501919945934,
      "grad_norm": 0.3491220474243164,
      "learning_rate": 1.5336591338918543e-05,
      "loss": 0.56,
      "step": 20956
    },
    {
      "epoch": 0.6437809111295426,
      "grad_norm": 0.32232803106307983,
      "learning_rate": 1.5336182625203585e-05,
      "loss": 0.5392,
      "step": 20957
    },
    {
      "epoch": 0.6438116302644917,
      "grad_norm": 0.4804140329360962,
      "learning_rate": 1.5335773899025604e-05,
      "loss": 0.5981,
      "step": 20958
    },
    {
      "epoch": 0.643842349399441,
      "grad_norm": 0.3941435217857361,
      "learning_rate": 1.5335365160385546e-05,
      "loss": 0.5443,
      "step": 20959
    },
    {
      "epoch": 0.6438730685343901,
      "grad_norm": 0.32931315898895264,
      "learning_rate": 1.5334956409284373e-05,
      "loss": 0.5901,
      "step": 20960
    },
    {
      "epoch": 0.6439037876693392,
      "grad_norm": 0.3866810202598572,
      "learning_rate": 1.5334547645723037e-05,
      "loss": 0.5797,
      "step": 20961
    },
    {
      "epoch": 0.6439345068042884,
      "grad_norm": 0.375496506690979,
      "learning_rate": 1.533413886970249e-05,
      "loss": 0.4977,
      "step": 20962
    },
    {
      "epoch": 0.6439652259392376,
      "grad_norm": 0.35723400115966797,
      "learning_rate": 1.533373008122369e-05,
      "loss": 0.571,
      "step": 20963
    },
    {
      "epoch": 0.6439959450741867,
      "grad_norm": 0.5616766810417175,
      "learning_rate": 1.5333321280287595e-05,
      "loss": 0.5447,
      "step": 20964
    },
    {
      "epoch": 0.6440266642091359,
      "grad_norm": 0.4586467444896698,
      "learning_rate": 1.5332912466895148e-05,
      "loss": 0.6426,
      "step": 20965
    },
    {
      "epoch": 0.644057383344085,
      "grad_norm": 0.36803698539733887,
      "learning_rate": 1.5332503641047315e-05,
      "loss": 0.6273,
      "step": 20966
    },
    {
      "epoch": 0.6440881024790341,
      "grad_norm": 0.36828169226646423,
      "learning_rate": 1.533209480274505e-05,
      "loss": 0.4956,
      "step": 20967
    },
    {
      "epoch": 0.6441188216139834,
      "grad_norm": 0.37871161103248596,
      "learning_rate": 1.53316859519893e-05,
      "loss": 0.5496,
      "step": 20968
    },
    {
      "epoch": 0.6441495407489325,
      "grad_norm": 0.3682262599468231,
      "learning_rate": 1.5331277088781034e-05,
      "loss": 0.5923,
      "step": 20969
    },
    {
      "epoch": 0.6441802598838817,
      "grad_norm": 0.3739127218723297,
      "learning_rate": 1.533086821312119e-05,
      "loss": 0.5535,
      "step": 20970
    },
    {
      "epoch": 0.6442109790188308,
      "grad_norm": 0.36176133155822754,
      "learning_rate": 1.5330459325010732e-05,
      "loss": 0.5567,
      "step": 20971
    },
    {
      "epoch": 0.64424169815378,
      "grad_norm": 0.3365798592567444,
      "learning_rate": 1.5330050424450613e-05,
      "loss": 0.5749,
      "step": 20972
    },
    {
      "epoch": 0.6442724172887292,
      "grad_norm": 0.38414496183395386,
      "learning_rate": 1.5329641511441792e-05,
      "loss": 0.4606,
      "step": 20973
    },
    {
      "epoch": 0.6443031364236783,
      "grad_norm": 0.38018038868904114,
      "learning_rate": 1.532923258598522e-05,
      "loss": 0.5871,
      "step": 20974
    },
    {
      "epoch": 0.6443338555586274,
      "grad_norm": 0.3654167950153351,
      "learning_rate": 1.5328823648081853e-05,
      "loss": 0.5692,
      "step": 20975
    },
    {
      "epoch": 0.6443645746935767,
      "grad_norm": 0.4189678728580475,
      "learning_rate": 1.532841469773265e-05,
      "loss": 0.566,
      "step": 20976
    },
    {
      "epoch": 0.6443952938285258,
      "grad_norm": 0.3532921373844147,
      "learning_rate": 1.5328005734938555e-05,
      "loss": 0.5512,
      "step": 20977
    },
    {
      "epoch": 0.6444260129634749,
      "grad_norm": 0.4898541271686554,
      "learning_rate": 1.5327596759700535e-05,
      "loss": 0.5924,
      "step": 20978
    },
    {
      "epoch": 0.6444567320984241,
      "grad_norm": 0.3392971158027649,
      "learning_rate": 1.532718777201954e-05,
      "loss": 0.6062,
      "step": 20979
    },
    {
      "epoch": 0.6444874512333733,
      "grad_norm": 0.35596346855163574,
      "learning_rate": 1.5326778771896527e-05,
      "loss": 0.6037,
      "step": 20980
    },
    {
      "epoch": 0.6445181703683224,
      "grad_norm": 0.34132859110832214,
      "learning_rate": 1.5326369759332448e-05,
      "loss": 0.5471,
      "step": 20981
    },
    {
      "epoch": 0.6445488895032716,
      "grad_norm": 0.3714083433151245,
      "learning_rate": 1.5325960734328264e-05,
      "loss": 0.6321,
      "step": 20982
    },
    {
      "epoch": 0.6445796086382207,
      "grad_norm": 0.348080575466156,
      "learning_rate": 1.5325551696884923e-05,
      "loss": 0.5503,
      "step": 20983
    },
    {
      "epoch": 0.64461032777317,
      "grad_norm": 0.35637056827545166,
      "learning_rate": 1.5325142647003388e-05,
      "loss": 0.5492,
      "step": 20984
    },
    {
      "epoch": 0.6446410469081191,
      "grad_norm": 0.3944288194179535,
      "learning_rate": 1.5324733584684607e-05,
      "loss": 0.5675,
      "step": 20985
    },
    {
      "epoch": 0.6446717660430682,
      "grad_norm": 0.40230047702789307,
      "learning_rate": 1.532432450992954e-05,
      "loss": 0.5545,
      "step": 20986
    },
    {
      "epoch": 0.6447024851780174,
      "grad_norm": 0.3403817415237427,
      "learning_rate": 1.532391542273914e-05,
      "loss": 0.5691,
      "step": 20987
    },
    {
      "epoch": 0.6447332043129665,
      "grad_norm": 0.3405209481716156,
      "learning_rate": 1.532350632311436e-05,
      "loss": 0.5402,
      "step": 20988
    },
    {
      "epoch": 0.6447639234479157,
      "grad_norm": 0.3776181638240814,
      "learning_rate": 1.5323097211056163e-05,
      "loss": 0.5386,
      "step": 20989
    },
    {
      "epoch": 0.6447946425828649,
      "grad_norm": 0.38848719000816345,
      "learning_rate": 1.5322688086565505e-05,
      "loss": 0.5229,
      "step": 20990
    },
    {
      "epoch": 0.644825361717814,
      "grad_norm": 0.3658437430858612,
      "learning_rate": 1.5322278949643332e-05,
      "loss": 0.5875,
      "step": 20991
    },
    {
      "epoch": 0.6448560808527631,
      "grad_norm": 0.4088321328163147,
      "learning_rate": 1.5321869800290608e-05,
      "loss": 0.4693,
      "step": 20992
    },
    {
      "epoch": 0.6448867999877124,
      "grad_norm": 0.35241207480430603,
      "learning_rate": 1.5321460638508282e-05,
      "loss": 0.5631,
      "step": 20993
    },
    {
      "epoch": 0.6449175191226615,
      "grad_norm": 0.41194894909858704,
      "learning_rate": 1.5321051464297316e-05,
      "loss": 0.5396,
      "step": 20994
    },
    {
      "epoch": 0.6449482382576107,
      "grad_norm": 0.37471991777420044,
      "learning_rate": 1.5320642277658662e-05,
      "loss": 0.4863,
      "step": 20995
    },
    {
      "epoch": 0.6449789573925598,
      "grad_norm": 0.3904237151145935,
      "learning_rate": 1.5320233078593276e-05,
      "loss": 0.585,
      "step": 20996
    },
    {
      "epoch": 0.645009676527509,
      "grad_norm": 0.4080604314804077,
      "learning_rate": 1.5319823867102114e-05,
      "loss": 0.6125,
      "step": 20997
    },
    {
      "epoch": 0.6450403956624582,
      "grad_norm": 0.3524417281150818,
      "learning_rate": 1.5319414643186133e-05,
      "loss": 0.5139,
      "step": 20998
    },
    {
      "epoch": 0.6450711147974073,
      "grad_norm": 0.39282363653182983,
      "learning_rate": 1.5319005406846286e-05,
      "loss": 0.5862,
      "step": 20999
    },
    {
      "epoch": 0.6451018339323564,
      "grad_norm": 0.37743422389030457,
      "learning_rate": 1.5318596158083533e-05,
      "loss": 0.5646,
      "step": 21000
    },
    {
      "epoch": 0.6451325530673057,
      "grad_norm": 0.34742310643196106,
      "learning_rate": 1.5318186896898824e-05,
      "loss": 0.5233,
      "step": 21001
    },
    {
      "epoch": 0.6451632722022548,
      "grad_norm": 0.35940808057785034,
      "learning_rate": 1.531777762329312e-05,
      "loss": 0.4975,
      "step": 21002
    },
    {
      "epoch": 0.6451939913372039,
      "grad_norm": 0.36026981472969055,
      "learning_rate": 1.5317368337267373e-05,
      "loss": 0.4613,
      "step": 21003
    },
    {
      "epoch": 0.6452247104721531,
      "grad_norm": 0.38685715198516846,
      "learning_rate": 1.531695903882254e-05,
      "loss": 0.5905,
      "step": 21004
    },
    {
      "epoch": 0.6452554296071022,
      "grad_norm": 0.36566805839538574,
      "learning_rate": 1.5316549727959582e-05,
      "loss": 0.552,
      "step": 21005
    },
    {
      "epoch": 0.6452861487420514,
      "grad_norm": 0.3765190541744232,
      "learning_rate": 1.531614040467945e-05,
      "loss": 0.5634,
      "step": 21006
    },
    {
      "epoch": 0.6453168678770006,
      "grad_norm": 0.42519429326057434,
      "learning_rate": 1.5315731068983096e-05,
      "loss": 0.5338,
      "step": 21007
    },
    {
      "epoch": 0.6453475870119497,
      "grad_norm": 0.3869919180870056,
      "learning_rate": 1.5315321720871486e-05,
      "loss": 0.5041,
      "step": 21008
    },
    {
      "epoch": 0.645378306146899,
      "grad_norm": 0.36877205967903137,
      "learning_rate": 1.5314912360345567e-05,
      "loss": 0.5554,
      "step": 21009
    },
    {
      "epoch": 0.6454090252818481,
      "grad_norm": 0.3693174719810486,
      "learning_rate": 1.5314502987406303e-05,
      "loss": 0.5226,
      "step": 21010
    },
    {
      "epoch": 0.6454397444167972,
      "grad_norm": 0.38518235087394714,
      "learning_rate": 1.531409360205464e-05,
      "loss": 0.6441,
      "step": 21011
    },
    {
      "epoch": 0.6454704635517464,
      "grad_norm": 0.3417920172214508,
      "learning_rate": 1.5313684204291548e-05,
      "loss": 0.5518,
      "step": 21012
    },
    {
      "epoch": 0.6455011826866955,
      "grad_norm": 0.32412490248680115,
      "learning_rate": 1.5313274794117972e-05,
      "loss": 0.5029,
      "step": 21013
    },
    {
      "epoch": 0.6455319018216447,
      "grad_norm": 0.36117231845855713,
      "learning_rate": 1.5312865371534873e-05,
      "loss": 0.63,
      "step": 21014
    },
    {
      "epoch": 0.6455626209565939,
      "grad_norm": 0.40169623494148254,
      "learning_rate": 1.53124559365432e-05,
      "loss": 0.63,
      "step": 21015
    },
    {
      "epoch": 0.645593340091543,
      "grad_norm": 0.390857070684433,
      "learning_rate": 1.5312046489143923e-05,
      "loss": 0.6665,
      "step": 21016
    },
    {
      "epoch": 0.6456240592264921,
      "grad_norm": 0.442899614572525,
      "learning_rate": 1.5311637029337988e-05,
      "loss": 0.5241,
      "step": 21017
    },
    {
      "epoch": 0.6456547783614414,
      "grad_norm": 0.35355377197265625,
      "learning_rate": 1.5311227557126354e-05,
      "loss": 0.5393,
      "step": 21018
    },
    {
      "epoch": 0.6456854974963905,
      "grad_norm": 0.35533440113067627,
      "learning_rate": 1.5310818072509976e-05,
      "loss": 0.5431,
      "step": 21019
    },
    {
      "epoch": 0.6457162166313397,
      "grad_norm": 0.359896183013916,
      "learning_rate": 1.531040857548981e-05,
      "loss": 0.5569,
      "step": 21020
    },
    {
      "epoch": 0.6457469357662888,
      "grad_norm": 0.3652799129486084,
      "learning_rate": 1.530999906606682e-05,
      "loss": 0.5601,
      "step": 21021
    },
    {
      "epoch": 0.645777654901238,
      "grad_norm": 0.40050986409187317,
      "learning_rate": 1.5309589544241948e-05,
      "loss": 0.5816,
      "step": 21022
    },
    {
      "epoch": 0.6458083740361872,
      "grad_norm": 0.36075711250305176,
      "learning_rate": 1.5309180010016166e-05,
      "loss": 0.5801,
      "step": 21023
    },
    {
      "epoch": 0.6458390931711363,
      "grad_norm": 0.383246511220932,
      "learning_rate": 1.5308770463390417e-05,
      "loss": 0.5274,
      "step": 21024
    },
    {
      "epoch": 0.6458698123060854,
      "grad_norm": 0.33581051230430603,
      "learning_rate": 1.5308360904365664e-05,
      "loss": 0.5112,
      "step": 21025
    },
    {
      "epoch": 0.6459005314410347,
      "grad_norm": 0.37318626046180725,
      "learning_rate": 1.5307951332942867e-05,
      "loss": 0.575,
      "step": 21026
    },
    {
      "epoch": 0.6459312505759838,
      "grad_norm": 0.3774493634700775,
      "learning_rate": 1.530754174912298e-05,
      "loss": 0.5493,
      "step": 21027
    },
    {
      "epoch": 0.6459619697109329,
      "grad_norm": 0.3477663993835449,
      "learning_rate": 1.5307132152906956e-05,
      "loss": 0.6598,
      "step": 21028
    },
    {
      "epoch": 0.6459926888458821,
      "grad_norm": 0.39382797479629517,
      "learning_rate": 1.5306722544295753e-05,
      "loss": 0.6182,
      "step": 21029
    },
    {
      "epoch": 0.6460234079808312,
      "grad_norm": 0.34387707710266113,
      "learning_rate": 1.5306312923290333e-05,
      "loss": 0.57,
      "step": 21030
    },
    {
      "epoch": 0.6460541271157805,
      "grad_norm": 0.3556790351867676,
      "learning_rate": 1.5305903289891643e-05,
      "loss": 0.4468,
      "step": 21031
    },
    {
      "epoch": 0.6460848462507296,
      "grad_norm": 0.3460606038570404,
      "learning_rate": 1.530549364410065e-05,
      "loss": 0.5962,
      "step": 21032
    },
    {
      "epoch": 0.6461155653856787,
      "grad_norm": 0.3530220687389374,
      "learning_rate": 1.5305083985918304e-05,
      "loss": 0.5943,
      "step": 21033
    },
    {
      "epoch": 0.646146284520628,
      "grad_norm": 0.341777503490448,
      "learning_rate": 1.5304674315345563e-05,
      "loss": 0.4825,
      "step": 21034
    },
    {
      "epoch": 0.6461770036555771,
      "grad_norm": 0.34201759099960327,
      "learning_rate": 1.5304264632383387e-05,
      "loss": 0.4961,
      "step": 21035
    },
    {
      "epoch": 0.6462077227905262,
      "grad_norm": 0.38698264956474304,
      "learning_rate": 1.530385493703273e-05,
      "loss": 0.5735,
      "step": 21036
    },
    {
      "epoch": 0.6462384419254754,
      "grad_norm": 0.3451104462146759,
      "learning_rate": 1.5303445229294553e-05,
      "loss": 0.5428,
      "step": 21037
    },
    {
      "epoch": 0.6462691610604245,
      "grad_norm": 0.4078007638454437,
      "learning_rate": 1.5303035509169802e-05,
      "loss": 0.5225,
      "step": 21038
    },
    {
      "epoch": 0.6462998801953737,
      "grad_norm": 0.3543389141559601,
      "learning_rate": 1.5302625776659444e-05,
      "loss": 0.6107,
      "step": 21039
    },
    {
      "epoch": 0.6463305993303229,
      "grad_norm": 0.35852688550949097,
      "learning_rate": 1.5302216031764438e-05,
      "loss": 0.5434,
      "step": 21040
    },
    {
      "epoch": 0.646361318465272,
      "grad_norm": 0.3610747754573822,
      "learning_rate": 1.530180627448573e-05,
      "loss": 0.5789,
      "step": 21041
    },
    {
      "epoch": 0.6463920376002211,
      "grad_norm": 0.34643131494522095,
      "learning_rate": 1.5301396504824286e-05,
      "loss": 0.6153,
      "step": 21042
    },
    {
      "epoch": 0.6464227567351704,
      "grad_norm": 0.3491239547729492,
      "learning_rate": 1.5300986722781054e-05,
      "loss": 0.5323,
      "step": 21043
    },
    {
      "epoch": 0.6464534758701195,
      "grad_norm": 0.33727267384529114,
      "learning_rate": 1.5300576928357006e-05,
      "loss": 0.6049,
      "step": 21044
    },
    {
      "epoch": 0.6464841950050687,
      "grad_norm": 0.3956087827682495,
      "learning_rate": 1.5300167121553083e-05,
      "loss": 0.531,
      "step": 21045
    },
    {
      "epoch": 0.6465149141400178,
      "grad_norm": 0.38314035534858704,
      "learning_rate": 1.5299757302370255e-05,
      "loss": 0.5321,
      "step": 21046
    },
    {
      "epoch": 0.646545633274967,
      "grad_norm": 0.3673381209373474,
      "learning_rate": 1.5299347470809474e-05,
      "loss": 0.6051,
      "step": 21047
    },
    {
      "epoch": 0.6465763524099162,
      "grad_norm": 0.34769871830940247,
      "learning_rate": 1.5298937626871694e-05,
      "loss": 0.5119,
      "step": 21048
    },
    {
      "epoch": 0.6466070715448653,
      "grad_norm": 0.3635618984699249,
      "learning_rate": 1.5298527770557876e-05,
      "loss": 0.5631,
      "step": 21049
    },
    {
      "epoch": 0.6466377906798144,
      "grad_norm": 0.3592568635940552,
      "learning_rate": 1.5298117901868978e-05,
      "loss": 0.6246,
      "step": 21050
    },
    {
      "epoch": 0.6466685098147636,
      "grad_norm": 0.44311055541038513,
      "learning_rate": 1.529770802080595e-05,
      "loss": 0.6018,
      "step": 21051
    },
    {
      "epoch": 0.6466992289497128,
      "grad_norm": 0.32642507553100586,
      "learning_rate": 1.5297298127369762e-05,
      "loss": 0.5602,
      "step": 21052
    },
    {
      "epoch": 0.6467299480846619,
      "grad_norm": 0.34433677792549133,
      "learning_rate": 1.529688822156136e-05,
      "loss": 0.4747,
      "step": 21053
    },
    {
      "epoch": 0.6467606672196111,
      "grad_norm": 0.36533817648887634,
      "learning_rate": 1.529647830338171e-05,
      "loss": 0.543,
      "step": 21054
    },
    {
      "epoch": 0.6467913863545602,
      "grad_norm": 0.3118935823440552,
      "learning_rate": 1.529606837283176e-05,
      "loss": 0.6023,
      "step": 21055
    },
    {
      "epoch": 0.6468221054895095,
      "grad_norm": 0.3961502015590668,
      "learning_rate": 1.5295658429912475e-05,
      "loss": 0.5481,
      "step": 21056
    },
    {
      "epoch": 0.6468528246244586,
      "grad_norm": 0.37988021969795227,
      "learning_rate": 1.5295248474624812e-05,
      "loss": 0.6167,
      "step": 21057
    },
    {
      "epoch": 0.6468835437594077,
      "grad_norm": 0.3486245274543762,
      "learning_rate": 1.529483850696972e-05,
      "loss": 0.5175,
      "step": 21058
    },
    {
      "epoch": 0.6469142628943569,
      "grad_norm": 0.3644658029079437,
      "learning_rate": 1.5294428526948165e-05,
      "loss": 0.5458,
      "step": 21059
    },
    {
      "epoch": 0.6469449820293061,
      "grad_norm": 0.3319699466228485,
      "learning_rate": 1.5294018534561106e-05,
      "loss": 0.5899,
      "step": 21060
    },
    {
      "epoch": 0.6469757011642552,
      "grad_norm": 0.35019388794898987,
      "learning_rate": 1.5293608529809494e-05,
      "loss": 0.5093,
      "step": 21061
    },
    {
      "epoch": 0.6470064202992044,
      "grad_norm": 0.34817495942115784,
      "learning_rate": 1.529319851269429e-05,
      "loss": 0.6231,
      "step": 21062
    },
    {
      "epoch": 0.6470371394341535,
      "grad_norm": 0.35597026348114014,
      "learning_rate": 1.529278848321645e-05,
      "loss": 0.4674,
      "step": 21063
    },
    {
      "epoch": 0.6470678585691026,
      "grad_norm": 0.46832388639450073,
      "learning_rate": 1.529237844137694e-05,
      "loss": 0.4954,
      "step": 21064
    },
    {
      "epoch": 0.6470985777040519,
      "grad_norm": 0.3815400302410126,
      "learning_rate": 1.52919683871767e-05,
      "loss": 0.5408,
      "step": 21065
    },
    {
      "epoch": 0.647129296839001,
      "grad_norm": 0.35776036977767944,
      "learning_rate": 1.5291558320616705e-05,
      "loss": 0.5501,
      "step": 21066
    },
    {
      "epoch": 0.6471600159739501,
      "grad_norm": 0.3446243107318878,
      "learning_rate": 1.5291148241697905e-05,
      "loss": 0.569,
      "step": 21067
    },
    {
      "epoch": 0.6471907351088994,
      "grad_norm": 0.3718982934951782,
      "learning_rate": 1.5290738150421257e-05,
      "loss": 0.5225,
      "step": 21068
    },
    {
      "epoch": 0.6472214542438485,
      "grad_norm": 0.33712413907051086,
      "learning_rate": 1.529032804678772e-05,
      "loss": 0.5125,
      "step": 21069
    },
    {
      "epoch": 0.6472521733787977,
      "grad_norm": 0.4483018219470978,
      "learning_rate": 1.528991793079826e-05,
      "loss": 0.5148,
      "step": 21070
    },
    {
      "epoch": 0.6472828925137468,
      "grad_norm": 0.41643697023391724,
      "learning_rate": 1.528950780245382e-05,
      "loss": 0.6332,
      "step": 21071
    },
    {
      "epoch": 0.6473136116486959,
      "grad_norm": 0.3428291082382202,
      "learning_rate": 1.5289097661755367e-05,
      "loss": 0.5674,
      "step": 21072
    },
    {
      "epoch": 0.6473443307836452,
      "grad_norm": 0.43564745783805847,
      "learning_rate": 1.5288687508703854e-05,
      "loss": 0.5165,
      "step": 21073
    },
    {
      "epoch": 0.6473750499185943,
      "grad_norm": 1.7530477046966553,
      "learning_rate": 1.5288277343300246e-05,
      "loss": 0.6084,
      "step": 21074
    },
    {
      "epoch": 0.6474057690535434,
      "grad_norm": 0.4651877284049988,
      "learning_rate": 1.5287867165545494e-05,
      "loss": 0.5259,
      "step": 21075
    },
    {
      "epoch": 0.6474364881884926,
      "grad_norm": 0.35585036873817444,
      "learning_rate": 1.528745697544056e-05,
      "loss": 0.6144,
      "step": 21076
    },
    {
      "epoch": 0.6474672073234418,
      "grad_norm": 0.3212881088256836,
      "learning_rate": 1.52870467729864e-05,
      "loss": 0.5196,
      "step": 21077
    },
    {
      "epoch": 0.6474979264583909,
      "grad_norm": 0.36482104659080505,
      "learning_rate": 1.5286636558183974e-05,
      "loss": 0.532,
      "step": 21078
    },
    {
      "epoch": 0.6475286455933401,
      "grad_norm": 0.3578993082046509,
      "learning_rate": 1.528622633103424e-05,
      "loss": 0.6466,
      "step": 21079
    },
    {
      "epoch": 0.6475593647282892,
      "grad_norm": 0.34349480271339417,
      "learning_rate": 1.5285816091538155e-05,
      "loss": 0.5535,
      "step": 21080
    },
    {
      "epoch": 0.6475900838632385,
      "grad_norm": 0.505435049533844,
      "learning_rate": 1.5285405839696674e-05,
      "loss": 0.5909,
      "step": 21081
    },
    {
      "epoch": 0.6476208029981876,
      "grad_norm": 0.351590633392334,
      "learning_rate": 1.5284995575510762e-05,
      "loss": 0.583,
      "step": 21082
    },
    {
      "epoch": 0.6476515221331367,
      "grad_norm": 0.3633093535900116,
      "learning_rate": 1.5284585298981375e-05,
      "loss": 0.564,
      "step": 21083
    },
    {
      "epoch": 0.6476822412680859,
      "grad_norm": 0.40705040097236633,
      "learning_rate": 1.5284175010109467e-05,
      "loss": 0.5188,
      "step": 21084
    },
    {
      "epoch": 0.647712960403035,
      "grad_norm": 0.3733178973197937,
      "learning_rate": 1.5283764708896e-05,
      "loss": 0.5606,
      "step": 21085
    },
    {
      "epoch": 0.6477436795379842,
      "grad_norm": 0.38366010785102844,
      "learning_rate": 1.5283354395341933e-05,
      "loss": 0.5804,
      "step": 21086
    },
    {
      "epoch": 0.6477743986729334,
      "grad_norm": 0.352815717458725,
      "learning_rate": 1.528294406944822e-05,
      "loss": 0.5702,
      "step": 21087
    },
    {
      "epoch": 0.6478051178078825,
      "grad_norm": 0.35607782006263733,
      "learning_rate": 1.5282533731215823e-05,
      "loss": 0.6011,
      "step": 21088
    },
    {
      "epoch": 0.6478358369428316,
      "grad_norm": 0.3563075661659241,
      "learning_rate": 1.52821233806457e-05,
      "loss": 0.5646,
      "step": 21089
    },
    {
      "epoch": 0.6478665560777809,
      "grad_norm": 0.37785565853118896,
      "learning_rate": 1.528171301773881e-05,
      "loss": 0.5322,
      "step": 21090
    },
    {
      "epoch": 0.64789727521273,
      "grad_norm": 0.5396628975868225,
      "learning_rate": 1.528130264249611e-05,
      "loss": 0.5781,
      "step": 21091
    },
    {
      "epoch": 0.6479279943476791,
      "grad_norm": 0.38104113936424255,
      "learning_rate": 1.528089225491856e-05,
      "loss": 0.6065,
      "step": 21092
    },
    {
      "epoch": 0.6479587134826283,
      "grad_norm": 0.3751753270626068,
      "learning_rate": 1.5280481855007117e-05,
      "loss": 0.5791,
      "step": 21093
    },
    {
      "epoch": 0.6479894326175775,
      "grad_norm": 0.3350427448749542,
      "learning_rate": 1.528007144276274e-05,
      "loss": 0.5738,
      "step": 21094
    },
    {
      "epoch": 0.6480201517525267,
      "grad_norm": 0.4106416404247284,
      "learning_rate": 1.5279661018186382e-05,
      "loss": 0.5113,
      "step": 21095
    },
    {
      "epoch": 0.6480508708874758,
      "grad_norm": 0.34743404388427734,
      "learning_rate": 1.527925058127901e-05,
      "loss": 0.5549,
      "step": 21096
    },
    {
      "epoch": 0.6480815900224249,
      "grad_norm": 0.3584442734718323,
      "learning_rate": 1.5278840132041584e-05,
      "loss": 0.5575,
      "step": 21097
    },
    {
      "epoch": 0.6481123091573742,
      "grad_norm": 1.0756334066390991,
      "learning_rate": 1.5278429670475054e-05,
      "loss": 0.6611,
      "step": 21098
    },
    {
      "epoch": 0.6481430282923233,
      "grad_norm": 0.36513200402259827,
      "learning_rate": 1.527801919658038e-05,
      "loss": 0.5914,
      "step": 21099
    },
    {
      "epoch": 0.6481737474272724,
      "grad_norm": 0.33125272393226624,
      "learning_rate": 1.5277608710358533e-05,
      "loss": 0.5564,
      "step": 21100
    },
    {
      "epoch": 0.6482044665622216,
      "grad_norm": 0.3366023600101471,
      "learning_rate": 1.5277198211810453e-05,
      "loss": 0.5452,
      "step": 21101
    },
    {
      "epoch": 0.6482351856971708,
      "grad_norm": 0.34793949127197266,
      "learning_rate": 1.527678770093711e-05,
      "loss": 0.5389,
      "step": 21102
    },
    {
      "epoch": 0.6482659048321199,
      "grad_norm": 0.3430945575237274,
      "learning_rate": 1.5276377177739465e-05,
      "loss": 0.5772,
      "step": 21103
    },
    {
      "epoch": 0.6482966239670691,
      "grad_norm": 0.32431560754776,
      "learning_rate": 1.527596664221847e-05,
      "loss": 0.506,
      "step": 21104
    },
    {
      "epoch": 0.6483273431020182,
      "grad_norm": 0.3477567732334137,
      "learning_rate": 1.5275556094375086e-05,
      "loss": 0.5228,
      "step": 21105
    },
    {
      "epoch": 0.6483580622369675,
      "grad_norm": 0.36967164278030396,
      "learning_rate": 1.527514553421027e-05,
      "loss": 0.6038,
      "step": 21106
    },
    {
      "epoch": 0.6483887813719166,
      "grad_norm": 0.34005457162857056,
      "learning_rate": 1.5274734961724987e-05,
      "loss": 0.4552,
      "step": 21107
    },
    {
      "epoch": 0.6484195005068657,
      "grad_norm": 0.3599511682987213,
      "learning_rate": 1.5274324376920195e-05,
      "loss": 0.5516,
      "step": 21108
    },
    {
      "epoch": 0.6484502196418149,
      "grad_norm": 0.32037338614463806,
      "learning_rate": 1.5273913779796843e-05,
      "loss": 0.5481,
      "step": 21109
    },
    {
      "epoch": 0.648480938776764,
      "grad_norm": 0.433799684047699,
      "learning_rate": 1.52735031703559e-05,
      "loss": 0.5316,
      "step": 21110
    },
    {
      "epoch": 0.6485116579117132,
      "grad_norm": 0.3411268889904022,
      "learning_rate": 1.5273092548598323e-05,
      "loss": 0.6092,
      "step": 21111
    },
    {
      "epoch": 0.6485423770466624,
      "grad_norm": 0.37603479623794556,
      "learning_rate": 1.5272681914525066e-05,
      "loss": 0.598,
      "step": 21112
    },
    {
      "epoch": 0.6485730961816115,
      "grad_norm": 0.3470586836338043,
      "learning_rate": 1.52722712681371e-05,
      "loss": 0.5358,
      "step": 21113
    },
    {
      "epoch": 0.6486038153165606,
      "grad_norm": 0.38413700461387634,
      "learning_rate": 1.527186060943537e-05,
      "loss": 0.6116,
      "step": 21114
    },
    {
      "epoch": 0.6486345344515099,
      "grad_norm": 0.35378944873809814,
      "learning_rate": 1.527144993842084e-05,
      "loss": 0.5722,
      "step": 21115
    },
    {
      "epoch": 0.648665253586459,
      "grad_norm": 0.3735957741737366,
      "learning_rate": 1.5271039255094475e-05,
      "loss": 0.5657,
      "step": 21116
    },
    {
      "epoch": 0.6486959727214082,
      "grad_norm": 0.33983147144317627,
      "learning_rate": 1.5270628559457227e-05,
      "loss": 0.5065,
      "step": 21117
    },
    {
      "epoch": 0.6487266918563573,
      "grad_norm": 0.35105741024017334,
      "learning_rate": 1.527021785151006e-05,
      "loss": 0.5303,
      "step": 21118
    },
    {
      "epoch": 0.6487574109913065,
      "grad_norm": 0.35426560044288635,
      "learning_rate": 1.526980713125393e-05,
      "loss": 0.5777,
      "step": 21119
    },
    {
      "epoch": 0.6487881301262557,
      "grad_norm": 0.37125492095947266,
      "learning_rate": 1.5269396398689798e-05,
      "loss": 0.4753,
      "step": 21120
    },
    {
      "epoch": 0.6488188492612048,
      "grad_norm": 0.40633946657180786,
      "learning_rate": 1.526898565381862e-05,
      "loss": 0.5954,
      "step": 21121
    },
    {
      "epoch": 0.6488495683961539,
      "grad_norm": 0.35663580894470215,
      "learning_rate": 1.526857489664136e-05,
      "loss": 0.5367,
      "step": 21122
    },
    {
      "epoch": 0.6488802875311032,
      "grad_norm": 0.3527800738811493,
      "learning_rate": 1.526816412715898e-05,
      "loss": 0.553,
      "step": 21123
    },
    {
      "epoch": 0.6489110066660523,
      "grad_norm": 0.3627687692642212,
      "learning_rate": 1.526775334537243e-05,
      "loss": 0.5455,
      "step": 21124
    },
    {
      "epoch": 0.6489417258010014,
      "grad_norm": 0.3883250653743744,
      "learning_rate": 1.5267342551282673e-05,
      "loss": 0.5409,
      "step": 21125
    },
    {
      "epoch": 0.6489724449359506,
      "grad_norm": 0.5203734636306763,
      "learning_rate": 1.5266931744890673e-05,
      "loss": 0.6979,
      "step": 21126
    },
    {
      "epoch": 0.6490031640708998,
      "grad_norm": 0.333779513835907,
      "learning_rate": 1.5266520926197383e-05,
      "loss": 0.5519,
      "step": 21127
    },
    {
      "epoch": 0.6490338832058489,
      "grad_norm": 0.3810933232307434,
      "learning_rate": 1.5266110095203766e-05,
      "loss": 0.5758,
      "step": 21128
    },
    {
      "epoch": 0.6490646023407981,
      "grad_norm": 0.35956528782844543,
      "learning_rate": 1.5265699251910782e-05,
      "loss": 0.5832,
      "step": 21129
    },
    {
      "epoch": 0.6490953214757472,
      "grad_norm": 0.3597363531589508,
      "learning_rate": 1.5265288396319392e-05,
      "loss": 0.4548,
      "step": 21130
    },
    {
      "epoch": 0.6491260406106965,
      "grad_norm": 0.5373230576515198,
      "learning_rate": 1.526487752843055e-05,
      "loss": 0.5914,
      "step": 21131
    },
    {
      "epoch": 0.6491567597456456,
      "grad_norm": 0.3682372272014618,
      "learning_rate": 1.5264466648245217e-05,
      "loss": 0.5942,
      "step": 21132
    },
    {
      "epoch": 0.6491874788805947,
      "grad_norm": 0.3866724371910095,
      "learning_rate": 1.526405575576436e-05,
      "loss": 0.6074,
      "step": 21133
    },
    {
      "epoch": 0.6492181980155439,
      "grad_norm": 0.3760939836502075,
      "learning_rate": 1.5263644850988928e-05,
      "loss": 0.5538,
      "step": 21134
    },
    {
      "epoch": 0.649248917150493,
      "grad_norm": 0.39537909626960754,
      "learning_rate": 1.5263233933919886e-05,
      "loss": 0.5886,
      "step": 21135
    },
    {
      "epoch": 0.6492796362854422,
      "grad_norm": 0.3362131714820862,
      "learning_rate": 1.5262823004558198e-05,
      "loss": 0.5293,
      "step": 21136
    },
    {
      "epoch": 0.6493103554203914,
      "grad_norm": 0.3889015018939972,
      "learning_rate": 1.5262412062904818e-05,
      "loss": 0.6232,
      "step": 21137
    },
    {
      "epoch": 0.6493410745553405,
      "grad_norm": 0.3733552098274231,
      "learning_rate": 1.5262001108960706e-05,
      "loss": 0.5098,
      "step": 21138
    },
    {
      "epoch": 0.6493717936902896,
      "grad_norm": 0.36628004908561707,
      "learning_rate": 1.5261590142726823e-05,
      "loss": 0.5179,
      "step": 21139
    },
    {
      "epoch": 0.6494025128252389,
      "grad_norm": 0.4027087688446045,
      "learning_rate": 1.5261179164204128e-05,
      "loss": 0.56,
      "step": 21140
    },
    {
      "epoch": 0.649433231960188,
      "grad_norm": 0.3608711361885071,
      "learning_rate": 1.5260768173393584e-05,
      "loss": 0.5189,
      "step": 21141
    },
    {
      "epoch": 0.6494639510951372,
      "grad_norm": 0.34560272097587585,
      "learning_rate": 1.5260357170296146e-05,
      "loss": 0.5644,
      "step": 21142
    },
    {
      "epoch": 0.6494946702300863,
      "grad_norm": 0.428324431180954,
      "learning_rate": 1.525994615491278e-05,
      "loss": 0.5665,
      "step": 21143
    },
    {
      "epoch": 0.6495253893650355,
      "grad_norm": 0.3784872591495514,
      "learning_rate": 1.5259535127244438e-05,
      "loss": 0.5886,
      "step": 21144
    },
    {
      "epoch": 0.6495561084999847,
      "grad_norm": 0.4633501470088959,
      "learning_rate": 1.5259124087292088e-05,
      "loss": 0.5553,
      "step": 21145
    },
    {
      "epoch": 0.6495868276349338,
      "grad_norm": 0.37394100427627563,
      "learning_rate": 1.5258713035056682e-05,
      "loss": 0.5901,
      "step": 21146
    },
    {
      "epoch": 0.6496175467698829,
      "grad_norm": 0.3423556089401245,
      "learning_rate": 1.5258301970539186e-05,
      "loss": 0.5744,
      "step": 21147
    },
    {
      "epoch": 0.6496482659048322,
      "grad_norm": 0.40909406542778015,
      "learning_rate": 1.525789089374056e-05,
      "loss": 0.5686,
      "step": 21148
    },
    {
      "epoch": 0.6496789850397813,
      "grad_norm": 0.36684271693229675,
      "learning_rate": 1.5257479804661764e-05,
      "loss": 0.4966,
      "step": 21149
    },
    {
      "epoch": 0.6497097041747304,
      "grad_norm": 0.3600979745388031,
      "learning_rate": 1.5257068703303754e-05,
      "loss": 0.5424,
      "step": 21150
    },
    {
      "epoch": 0.6497404233096796,
      "grad_norm": 0.36789947748184204,
      "learning_rate": 1.5256657589667493e-05,
      "loss": 0.5976,
      "step": 21151
    },
    {
      "epoch": 0.6497711424446287,
      "grad_norm": 0.3653792142868042,
      "learning_rate": 1.5256246463753943e-05,
      "loss": 0.4861,
      "step": 21152
    },
    {
      "epoch": 0.6498018615795779,
      "grad_norm": 0.35519087314605713,
      "learning_rate": 1.5255835325564059e-05,
      "loss": 0.5723,
      "step": 21153
    },
    {
      "epoch": 0.6498325807145271,
      "grad_norm": 0.3895490765571594,
      "learning_rate": 1.5255424175098807e-05,
      "loss": 0.6271,
      "step": 21154
    },
    {
      "epoch": 0.6498632998494762,
      "grad_norm": 0.399873286485672,
      "learning_rate": 1.5255013012359143e-05,
      "loss": 0.5207,
      "step": 21155
    },
    {
      "epoch": 0.6498940189844254,
      "grad_norm": 0.33470451831817627,
      "learning_rate": 1.5254601837346032e-05,
      "loss": 0.5508,
      "step": 21156
    },
    {
      "epoch": 0.6499247381193746,
      "grad_norm": 0.44321173429489136,
      "learning_rate": 1.525419065006043e-05,
      "loss": 0.6064,
      "step": 21157
    },
    {
      "epoch": 0.6499554572543237,
      "grad_norm": 0.3807515501976013,
      "learning_rate": 1.52537794505033e-05,
      "loss": 0.5958,
      "step": 21158
    },
    {
      "epoch": 0.6499861763892729,
      "grad_norm": 0.34488555788993835,
      "learning_rate": 1.5253368238675602e-05,
      "loss": 0.4996,
      "step": 21159
    },
    {
      "epoch": 0.650016895524222,
      "grad_norm": 0.37688541412353516,
      "learning_rate": 1.5252957014578291e-05,
      "loss": 0.6285,
      "step": 21160
    },
    {
      "epoch": 0.6500476146591712,
      "grad_norm": 0.3827815055847168,
      "learning_rate": 1.5252545778212335e-05,
      "loss": 0.5656,
      "step": 21161
    },
    {
      "epoch": 0.6500783337941204,
      "grad_norm": 0.384733647108078,
      "learning_rate": 1.525213452957869e-05,
      "loss": 0.5602,
      "step": 21162
    },
    {
      "epoch": 0.6501090529290695,
      "grad_norm": 0.36378607153892517,
      "learning_rate": 1.525172326867832e-05,
      "loss": 0.5124,
      "step": 21163
    },
    {
      "epoch": 0.6501397720640186,
      "grad_norm": 0.33082979917526245,
      "learning_rate": 1.5251311995512184e-05,
      "loss": 0.4463,
      "step": 21164
    },
    {
      "epoch": 0.6501704911989679,
      "grad_norm": 0.3333810567855835,
      "learning_rate": 1.525090071008124e-05,
      "loss": 0.5209,
      "step": 21165
    },
    {
      "epoch": 0.650201210333917,
      "grad_norm": 0.3513714373111725,
      "learning_rate": 1.525048941238645e-05,
      "loss": 0.5693,
      "step": 21166
    },
    {
      "epoch": 0.6502319294688662,
      "grad_norm": 0.3698136806488037,
      "learning_rate": 1.5250078102428779e-05,
      "loss": 0.586,
      "step": 21167
    },
    {
      "epoch": 0.6502626486038153,
      "grad_norm": 0.36513081192970276,
      "learning_rate": 1.524966678020918e-05,
      "loss": 0.5535,
      "step": 21168
    },
    {
      "epoch": 0.6502933677387644,
      "grad_norm": 0.36800143122673035,
      "learning_rate": 1.5249255445728622e-05,
      "loss": 0.5564,
      "step": 21169
    },
    {
      "epoch": 0.6503240868737137,
      "grad_norm": 0.31189021468162537,
      "learning_rate": 1.5248844098988059e-05,
      "loss": 0.46,
      "step": 21170
    },
    {
      "epoch": 0.6503548060086628,
      "grad_norm": 0.38094401359558105,
      "learning_rate": 1.5248432739988447e-05,
      "loss": 0.6047,
      "step": 21171
    },
    {
      "epoch": 0.6503855251436119,
      "grad_norm": 0.35802143812179565,
      "learning_rate": 1.5248021368730763e-05,
      "loss": 0.6221,
      "step": 21172
    },
    {
      "epoch": 0.6504162442785612,
      "grad_norm": 0.3509170114994049,
      "learning_rate": 1.5247609985215955e-05,
      "loss": 0.5095,
      "step": 21173
    },
    {
      "epoch": 0.6504469634135103,
      "grad_norm": 0.3608590364456177,
      "learning_rate": 1.524719858944499e-05,
      "loss": 0.6339,
      "step": 21174
    },
    {
      "epoch": 0.6504776825484594,
      "grad_norm": 0.34945669770240784,
      "learning_rate": 1.5246787181418825e-05,
      "loss": 0.552,
      "step": 21175
    },
    {
      "epoch": 0.6505084016834086,
      "grad_norm": 0.3786931335926056,
      "learning_rate": 1.5246375761138421e-05,
      "loss": 0.5368,
      "step": 21176
    },
    {
      "epoch": 0.6505391208183577,
      "grad_norm": 0.35752072930336,
      "learning_rate": 1.524596432860474e-05,
      "loss": 0.5962,
      "step": 21177
    },
    {
      "epoch": 0.6505698399533069,
      "grad_norm": 0.3636552691459656,
      "learning_rate": 1.5245552883818743e-05,
      "loss": 0.6091,
      "step": 21178
    },
    {
      "epoch": 0.6506005590882561,
      "grad_norm": 0.4017771780490875,
      "learning_rate": 1.5245141426781394e-05,
      "loss": 0.5984,
      "step": 21179
    },
    {
      "epoch": 0.6506312782232052,
      "grad_norm": 0.4169272482395172,
      "learning_rate": 1.5244729957493647e-05,
      "loss": 0.5848,
      "step": 21180
    },
    {
      "epoch": 0.6506619973581544,
      "grad_norm": 0.3711049258708954,
      "learning_rate": 1.524431847595647e-05,
      "loss": 0.6139,
      "step": 21181
    },
    {
      "epoch": 0.6506927164931036,
      "grad_norm": 0.38444459438323975,
      "learning_rate": 1.5243906982170818e-05,
      "loss": 0.6079,
      "step": 21182
    },
    {
      "epoch": 0.6507234356280527,
      "grad_norm": 0.39567333459854126,
      "learning_rate": 1.5243495476137655e-05,
      "loss": 0.5967,
      "step": 21183
    },
    {
      "epoch": 0.6507541547630019,
      "grad_norm": 0.34809330105781555,
      "learning_rate": 1.5243083957857945e-05,
      "loss": 0.4426,
      "step": 21184
    },
    {
      "epoch": 0.650784873897951,
      "grad_norm": 0.45033055543899536,
      "learning_rate": 1.5242672427332642e-05,
      "loss": 0.5408,
      "step": 21185
    },
    {
      "epoch": 0.6508155930329002,
      "grad_norm": 0.4507579207420349,
      "learning_rate": 1.524226088456272e-05,
      "loss": 0.6388,
      "step": 21186
    },
    {
      "epoch": 0.6508463121678494,
      "grad_norm": 0.37707382440567017,
      "learning_rate": 1.5241849329549121e-05,
      "loss": 0.5986,
      "step": 21187
    },
    {
      "epoch": 0.6508770313027985,
      "grad_norm": 0.39538252353668213,
      "learning_rate": 1.5241437762292823e-05,
      "loss": 0.6042,
      "step": 21188
    },
    {
      "epoch": 0.6509077504377476,
      "grad_norm": 0.33935999870300293,
      "learning_rate": 1.5241026182794777e-05,
      "loss": 0.5264,
      "step": 21189
    },
    {
      "epoch": 0.6509384695726969,
      "grad_norm": 0.3221813440322876,
      "learning_rate": 1.5240614591055951e-05,
      "loss": 0.4949,
      "step": 21190
    },
    {
      "epoch": 0.650969188707646,
      "grad_norm": 0.46106764674186707,
      "learning_rate": 1.5240202987077305e-05,
      "loss": 0.597,
      "step": 21191
    },
    {
      "epoch": 0.6509999078425952,
      "grad_norm": 0.345548540353775,
      "learning_rate": 1.5239791370859796e-05,
      "loss": 0.6411,
      "step": 21192
    },
    {
      "epoch": 0.6510306269775443,
      "grad_norm": 0.36963701248168945,
      "learning_rate": 1.523937974240439e-05,
      "loss": 0.5271,
      "step": 21193
    },
    {
      "epoch": 0.6510613461124934,
      "grad_norm": 0.33349621295928955,
      "learning_rate": 1.5238968101712047e-05,
      "loss": 0.5589,
      "step": 21194
    },
    {
      "epoch": 0.6510920652474427,
      "grad_norm": 0.3784375488758087,
      "learning_rate": 1.5238556448783727e-05,
      "loss": 0.5654,
      "step": 21195
    },
    {
      "epoch": 0.6511227843823918,
      "grad_norm": 0.4361644983291626,
      "learning_rate": 1.5238144783620393e-05,
      "loss": 0.5511,
      "step": 21196
    },
    {
      "epoch": 0.6511535035173409,
      "grad_norm": 0.3269464373588562,
      "learning_rate": 1.5237733106223007e-05,
      "loss": 0.5356,
      "step": 21197
    },
    {
      "epoch": 0.6511842226522901,
      "grad_norm": 0.33510851860046387,
      "learning_rate": 1.5237321416592528e-05,
      "loss": 0.5017,
      "step": 21198
    },
    {
      "epoch": 0.6512149417872393,
      "grad_norm": 0.38178780674934387,
      "learning_rate": 1.5236909714729919e-05,
      "loss": 0.5973,
      "step": 21199
    },
    {
      "epoch": 0.6512456609221884,
      "grad_norm": 0.3066851496696472,
      "learning_rate": 1.5236498000636142e-05,
      "loss": 0.5665,
      "step": 21200
    },
    {
      "epoch": 0.6512763800571376,
      "grad_norm": 0.3607138693332672,
      "learning_rate": 1.5236086274312158e-05,
      "loss": 0.6057,
      "step": 21201
    },
    {
      "epoch": 0.6513070991920867,
      "grad_norm": 0.3537081480026245,
      "learning_rate": 1.5235674535758928e-05,
      "loss": 0.623,
      "step": 21202
    },
    {
      "epoch": 0.6513378183270359,
      "grad_norm": 0.4000770151615143,
      "learning_rate": 1.5235262784977419e-05,
      "loss": 0.6122,
      "step": 21203
    },
    {
      "epoch": 0.6513685374619851,
      "grad_norm": 0.38868939876556396,
      "learning_rate": 1.5234851021968584e-05,
      "loss": 0.5906,
      "step": 21204
    },
    {
      "epoch": 0.6513992565969342,
      "grad_norm": 0.3384988605976105,
      "learning_rate": 1.5234439246733389e-05,
      "loss": 0.5657,
      "step": 21205
    },
    {
      "epoch": 0.6514299757318834,
      "grad_norm": 0.3289218544960022,
      "learning_rate": 1.5234027459272798e-05,
      "loss": 0.4906,
      "step": 21206
    },
    {
      "epoch": 0.6514606948668326,
      "grad_norm": 0.3533121347427368,
      "learning_rate": 1.5233615659587763e-05,
      "loss": 0.6142,
      "step": 21207
    },
    {
      "epoch": 0.6514914140017817,
      "grad_norm": 0.3462236523628235,
      "learning_rate": 1.523320384767926e-05,
      "loss": 0.509,
      "step": 21208
    },
    {
      "epoch": 0.6515221331367309,
      "grad_norm": 0.3846917450428009,
      "learning_rate": 1.5232792023548243e-05,
      "loss": 0.494,
      "step": 21209
    },
    {
      "epoch": 0.65155285227168,
      "grad_norm": 0.3785015642642975,
      "learning_rate": 1.5232380187195674e-05,
      "loss": 0.5748,
      "step": 21210
    },
    {
      "epoch": 0.6515835714066291,
      "grad_norm": 0.3926629424095154,
      "learning_rate": 1.5231968338622519e-05,
      "loss": 0.5207,
      "step": 21211
    },
    {
      "epoch": 0.6516142905415784,
      "grad_norm": 0.40358924865722656,
      "learning_rate": 1.5231556477829732e-05,
      "loss": 0.607,
      "step": 21212
    },
    {
      "epoch": 0.6516450096765275,
      "grad_norm": 0.374072790145874,
      "learning_rate": 1.5231144604818285e-05,
      "loss": 0.5213,
      "step": 21213
    },
    {
      "epoch": 0.6516757288114766,
      "grad_norm": 0.3935735821723938,
      "learning_rate": 1.5230732719589128e-05,
      "loss": 0.5309,
      "step": 21214
    },
    {
      "epoch": 0.6517064479464258,
      "grad_norm": 0.3700404465198517,
      "learning_rate": 1.5230320822143232e-05,
      "loss": 0.5491,
      "step": 21215
    },
    {
      "epoch": 0.651737167081375,
      "grad_norm": 0.33136528730392456,
      "learning_rate": 1.5229908912481555e-05,
      "loss": 0.5275,
      "step": 21216
    },
    {
      "epoch": 0.6517678862163242,
      "grad_norm": 0.34724855422973633,
      "learning_rate": 1.5229496990605064e-05,
      "loss": 0.6178,
      "step": 21217
    },
    {
      "epoch": 0.6517986053512733,
      "grad_norm": 0.37827226519584656,
      "learning_rate": 1.5229085056514714e-05,
      "loss": 0.5618,
      "step": 21218
    },
    {
      "epoch": 0.6518293244862224,
      "grad_norm": 0.3388160169124603,
      "learning_rate": 1.5228673110211473e-05,
      "loss": 0.5478,
      "step": 21219
    },
    {
      "epoch": 0.6518600436211717,
      "grad_norm": 0.34789344668388367,
      "learning_rate": 1.5228261151696297e-05,
      "loss": 0.5348,
      "step": 21220
    },
    {
      "epoch": 0.6518907627561208,
      "grad_norm": 0.3379877507686615,
      "learning_rate": 1.5227849180970157e-05,
      "loss": 0.5215,
      "step": 21221
    },
    {
      "epoch": 0.6519214818910699,
      "grad_norm": 0.3299976885318756,
      "learning_rate": 1.522743719803401e-05,
      "loss": 0.4988,
      "step": 21222
    },
    {
      "epoch": 0.6519522010260191,
      "grad_norm": 0.38278698921203613,
      "learning_rate": 1.5227025202888814e-05,
      "loss": 0.6276,
      "step": 21223
    },
    {
      "epoch": 0.6519829201609683,
      "grad_norm": 0.36548030376434326,
      "learning_rate": 1.5226613195535538e-05,
      "loss": 0.5138,
      "step": 21224
    },
    {
      "epoch": 0.6520136392959174,
      "grad_norm": 0.36305928230285645,
      "learning_rate": 1.5226201175975143e-05,
      "loss": 0.5087,
      "step": 21225
    },
    {
      "epoch": 0.6520443584308666,
      "grad_norm": 0.3938352167606354,
      "learning_rate": 1.5225789144208587e-05,
      "loss": 0.5316,
      "step": 21226
    },
    {
      "epoch": 0.6520750775658157,
      "grad_norm": 0.42634835839271545,
      "learning_rate": 1.5225377100236838e-05,
      "loss": 0.6,
      "step": 21227
    },
    {
      "epoch": 0.652105796700765,
      "grad_norm": 0.326777845621109,
      "learning_rate": 1.5224965044060853e-05,
      "loss": 0.6054,
      "step": 21228
    },
    {
      "epoch": 0.6521365158357141,
      "grad_norm": 0.3648871183395386,
      "learning_rate": 1.5224552975681604e-05,
      "loss": 0.5507,
      "step": 21229
    },
    {
      "epoch": 0.6521672349706632,
      "grad_norm": 0.3970741331577301,
      "learning_rate": 1.5224140895100039e-05,
      "loss": 0.5987,
      "step": 21230
    },
    {
      "epoch": 0.6521979541056124,
      "grad_norm": 0.5752553343772888,
      "learning_rate": 1.5223728802317132e-05,
      "loss": 0.5753,
      "step": 21231
    },
    {
      "epoch": 0.6522286732405616,
      "grad_norm": 0.34485694766044617,
      "learning_rate": 1.5223316697333839e-05,
      "loss": 0.5643,
      "step": 21232
    },
    {
      "epoch": 0.6522593923755107,
      "grad_norm": 0.39095208048820496,
      "learning_rate": 1.522290458015113e-05,
      "loss": 0.621,
      "step": 21233
    },
    {
      "epoch": 0.6522901115104599,
      "grad_norm": 0.3806520998477936,
      "learning_rate": 1.5222492450769957e-05,
      "loss": 0.5274,
      "step": 21234
    },
    {
      "epoch": 0.652320830645409,
      "grad_norm": 0.3421679437160492,
      "learning_rate": 1.5222080309191291e-05,
      "loss": 0.5138,
      "step": 21235
    },
    {
      "epoch": 0.6523515497803581,
      "grad_norm": 0.3755084276199341,
      "learning_rate": 1.5221668155416091e-05,
      "loss": 0.493,
      "step": 21236
    },
    {
      "epoch": 0.6523822689153074,
      "grad_norm": 0.3706680238246918,
      "learning_rate": 1.5221255989445323e-05,
      "loss": 0.6324,
      "step": 21237
    },
    {
      "epoch": 0.6524129880502565,
      "grad_norm": 0.3706282079219818,
      "learning_rate": 1.5220843811279943e-05,
      "loss": 0.5624,
      "step": 21238
    },
    {
      "epoch": 0.6524437071852056,
      "grad_norm": 0.36842653155326843,
      "learning_rate": 1.522043162092092e-05,
      "loss": 0.6023,
      "step": 21239
    },
    {
      "epoch": 0.6524744263201548,
      "grad_norm": 0.38241443037986755,
      "learning_rate": 1.5220019418369214e-05,
      "loss": 0.5162,
      "step": 21240
    },
    {
      "epoch": 0.652505145455104,
      "grad_norm": 0.3187280297279358,
      "learning_rate": 1.5219607203625785e-05,
      "loss": 0.4879,
      "step": 21241
    },
    {
      "epoch": 0.6525358645900532,
      "grad_norm": 0.34186357259750366,
      "learning_rate": 1.5219194976691604e-05,
      "loss": 0.5547,
      "step": 21242
    },
    {
      "epoch": 0.6525665837250023,
      "grad_norm": 0.4546814560890198,
      "learning_rate": 1.5218782737567625e-05,
      "loss": 0.5406,
      "step": 21243
    },
    {
      "epoch": 0.6525973028599514,
      "grad_norm": 0.36709558963775635,
      "learning_rate": 1.5218370486254816e-05,
      "loss": 0.5475,
      "step": 21244
    },
    {
      "epoch": 0.6526280219949007,
      "grad_norm": 0.35779911279678345,
      "learning_rate": 1.5217958222754136e-05,
      "loss": 0.5281,
      "step": 21245
    },
    {
      "epoch": 0.6526587411298498,
      "grad_norm": 0.34381788969039917,
      "learning_rate": 1.5217545947066552e-05,
      "loss": 0.6097,
      "step": 21246
    },
    {
      "epoch": 0.6526894602647989,
      "grad_norm": 0.3810712397098541,
      "learning_rate": 1.5217133659193026e-05,
      "loss": 0.6026,
      "step": 21247
    },
    {
      "epoch": 0.6527201793997481,
      "grad_norm": 0.38310810923576355,
      "learning_rate": 1.521672135913452e-05,
      "loss": 0.6051,
      "step": 21248
    },
    {
      "epoch": 0.6527508985346973,
      "grad_norm": 0.3571401536464691,
      "learning_rate": 1.5216309046891998e-05,
      "loss": 0.6091,
      "step": 21249
    },
    {
      "epoch": 0.6527816176696464,
      "grad_norm": 0.3265821039676666,
      "learning_rate": 1.5215896722466417e-05,
      "loss": 0.5606,
      "step": 21250
    },
    {
      "epoch": 0.6528123368045956,
      "grad_norm": 0.3505452871322632,
      "learning_rate": 1.5215484385858749e-05,
      "loss": 0.5649,
      "step": 21251
    },
    {
      "epoch": 0.6528430559395447,
      "grad_norm": 0.2990560829639435,
      "learning_rate": 1.5215072037069951e-05,
      "loss": 0.4978,
      "step": 21252
    },
    {
      "epoch": 0.652873775074494,
      "grad_norm": 0.35248392820358276,
      "learning_rate": 1.5214659676100988e-05,
      "loss": 0.5824,
      "step": 21253
    },
    {
      "epoch": 0.6529044942094431,
      "grad_norm": 0.3761134743690491,
      "learning_rate": 1.5214247302952825e-05,
      "loss": 0.5814,
      "step": 21254
    },
    {
      "epoch": 0.6529352133443922,
      "grad_norm": 0.3670865595340729,
      "learning_rate": 1.5213834917626424e-05,
      "loss": 0.537,
      "step": 21255
    },
    {
      "epoch": 0.6529659324793414,
      "grad_norm": 0.3877096474170685,
      "learning_rate": 1.5213422520122746e-05,
      "loss": 0.5634,
      "step": 21256
    },
    {
      "epoch": 0.6529966516142905,
      "grad_norm": 0.3734114170074463,
      "learning_rate": 1.5213010110442755e-05,
      "loss": 0.5622,
      "step": 21257
    },
    {
      "epoch": 0.6530273707492397,
      "grad_norm": 0.3824617266654968,
      "learning_rate": 1.5212597688587416e-05,
      "loss": 0.5786,
      "step": 21258
    },
    {
      "epoch": 0.6530580898841889,
      "grad_norm": 0.3273296356201172,
      "learning_rate": 1.521218525455769e-05,
      "loss": 0.5034,
      "step": 21259
    },
    {
      "epoch": 0.653088809019138,
      "grad_norm": 0.44981035590171814,
      "learning_rate": 1.5211772808354542e-05,
      "loss": 0.573,
      "step": 21260
    },
    {
      "epoch": 0.6531195281540871,
      "grad_norm": 0.36316850781440735,
      "learning_rate": 1.5211360349978932e-05,
      "loss": 0.5088,
      "step": 21261
    },
    {
      "epoch": 0.6531502472890364,
      "grad_norm": 0.3592377007007599,
      "learning_rate": 1.5210947879431828e-05,
      "loss": 0.5363,
      "step": 21262
    },
    {
      "epoch": 0.6531809664239855,
      "grad_norm": 0.36521923542022705,
      "learning_rate": 1.5210535396714191e-05,
      "loss": 0.5729,
      "step": 21263
    },
    {
      "epoch": 0.6532116855589346,
      "grad_norm": 0.3922928273677826,
      "learning_rate": 1.5210122901826984e-05,
      "loss": 0.5619,
      "step": 21264
    },
    {
      "epoch": 0.6532424046938838,
      "grad_norm": 0.32539695501327515,
      "learning_rate": 1.5209710394771176e-05,
      "loss": 0.5049,
      "step": 21265
    },
    {
      "epoch": 0.653273123828833,
      "grad_norm": 0.3704848885536194,
      "learning_rate": 1.5209297875547719e-05,
      "loss": 0.4964,
      "step": 21266
    },
    {
      "epoch": 0.6533038429637822,
      "grad_norm": 0.38023149967193604,
      "learning_rate": 1.5208885344157587e-05,
      "loss": 0.6916,
      "step": 21267
    },
    {
      "epoch": 0.6533345620987313,
      "grad_norm": 0.3372463285923004,
      "learning_rate": 1.5208472800601737e-05,
      "loss": 0.5244,
      "step": 21268
    },
    {
      "epoch": 0.6533652812336804,
      "grad_norm": 0.3408006429672241,
      "learning_rate": 1.5208060244881138e-05,
      "loss": 0.5001,
      "step": 21269
    },
    {
      "epoch": 0.6533960003686297,
      "grad_norm": 0.3811284303665161,
      "learning_rate": 1.5207647676996746e-05,
      "loss": 0.5898,
      "step": 21270
    },
    {
      "epoch": 0.6534267195035788,
      "grad_norm": 0.34707513451576233,
      "learning_rate": 1.5207235096949533e-05,
      "loss": 0.5367,
      "step": 21271
    },
    {
      "epoch": 0.6534574386385279,
      "grad_norm": 0.3497793674468994,
      "learning_rate": 1.5206822504740457e-05,
      "loss": 0.4749,
      "step": 21272
    },
    {
      "epoch": 0.6534881577734771,
      "grad_norm": 0.36589452624320984,
      "learning_rate": 1.5206409900370487e-05,
      "loss": 0.6019,
      "step": 21273
    },
    {
      "epoch": 0.6535188769084262,
      "grad_norm": 0.39004573225975037,
      "learning_rate": 1.520599728384058e-05,
      "loss": 0.5042,
      "step": 21274
    },
    {
      "epoch": 0.6535495960433754,
      "grad_norm": 0.3582098186016083,
      "learning_rate": 1.5205584655151702e-05,
      "loss": 0.5993,
      "step": 21275
    },
    {
      "epoch": 0.6535803151783246,
      "grad_norm": 0.32554054260253906,
      "learning_rate": 1.520517201430482e-05,
      "loss": 0.4254,
      "step": 21276
    },
    {
      "epoch": 0.6536110343132737,
      "grad_norm": 0.38111183047294617,
      "learning_rate": 1.5204759361300892e-05,
      "loss": 0.5358,
      "step": 21277
    },
    {
      "epoch": 0.653641753448223,
      "grad_norm": 0.38375672698020935,
      "learning_rate": 1.5204346696140886e-05,
      "loss": 0.5679,
      "step": 21278
    },
    {
      "epoch": 0.6536724725831721,
      "grad_norm": 0.37328851222991943,
      "learning_rate": 1.5203934018825766e-05,
      "loss": 0.5343,
      "step": 21279
    },
    {
      "epoch": 0.6537031917181212,
      "grad_norm": 0.33833566308021545,
      "learning_rate": 1.5203521329356492e-05,
      "loss": 0.6177,
      "step": 21280
    },
    {
      "epoch": 0.6537339108530704,
      "grad_norm": 0.456587016582489,
      "learning_rate": 1.5203108627734034e-05,
      "loss": 0.5771,
      "step": 21281
    },
    {
      "epoch": 0.6537646299880195,
      "grad_norm": 0.4157136082649231,
      "learning_rate": 1.5202695913959349e-05,
      "loss": 0.5732,
      "step": 21282
    },
    {
      "epoch": 0.6537953491229687,
      "grad_norm": 0.34203657507896423,
      "learning_rate": 1.5202283188033408e-05,
      "loss": 0.6026,
      "step": 21283
    },
    {
      "epoch": 0.6538260682579179,
      "grad_norm": 0.3782574534416199,
      "learning_rate": 1.520187044995717e-05,
      "loss": 0.5549,
      "step": 21284
    },
    {
      "epoch": 0.653856787392867,
      "grad_norm": 0.3188110589981079,
      "learning_rate": 1.52014576997316e-05,
      "loss": 0.5532,
      "step": 21285
    },
    {
      "epoch": 0.6538875065278161,
      "grad_norm": 0.40121740102767944,
      "learning_rate": 1.520104493735766e-05,
      "loss": 0.6014,
      "step": 21286
    },
    {
      "epoch": 0.6539182256627654,
      "grad_norm": 0.362213671207428,
      "learning_rate": 1.520063216283632e-05,
      "loss": 0.6257,
      "step": 21287
    },
    {
      "epoch": 0.6539489447977145,
      "grad_norm": 0.33908703923225403,
      "learning_rate": 1.5200219376168539e-05,
      "loss": 0.615,
      "step": 21288
    },
    {
      "epoch": 0.6539796639326636,
      "grad_norm": 0.38679787516593933,
      "learning_rate": 1.5199806577355283e-05,
      "loss": 0.5819,
      "step": 21289
    },
    {
      "epoch": 0.6540103830676128,
      "grad_norm": 0.33308082818984985,
      "learning_rate": 1.5199393766397514e-05,
      "loss": 0.5402,
      "step": 21290
    },
    {
      "epoch": 0.654041102202562,
      "grad_norm": 0.4583079218864441,
      "learning_rate": 1.51989809432962e-05,
      "loss": 0.6401,
      "step": 21291
    },
    {
      "epoch": 0.6540718213375112,
      "grad_norm": 0.4423460066318512,
      "learning_rate": 1.5198568108052303e-05,
      "loss": 0.597,
      "step": 21292
    },
    {
      "epoch": 0.6541025404724603,
      "grad_norm": 0.3427680432796478,
      "learning_rate": 1.5198155260666785e-05,
      "loss": 0.5168,
      "step": 21293
    },
    {
      "epoch": 0.6541332596074094,
      "grad_norm": 0.3829866945743561,
      "learning_rate": 1.5197742401140614e-05,
      "loss": 0.5833,
      "step": 21294
    },
    {
      "epoch": 0.6541639787423587,
      "grad_norm": 0.3797175884246826,
      "learning_rate": 1.5197329529474751e-05,
      "loss": 0.5674,
      "step": 21295
    },
    {
      "epoch": 0.6541946978773078,
      "grad_norm": 0.37866777181625366,
      "learning_rate": 1.5196916645670163e-05,
      "loss": 0.5696,
      "step": 21296
    },
    {
      "epoch": 0.6542254170122569,
      "grad_norm": 0.35549554228782654,
      "learning_rate": 1.5196503749727814e-05,
      "loss": 0.5515,
      "step": 21297
    },
    {
      "epoch": 0.6542561361472061,
      "grad_norm": 0.3419491946697235,
      "learning_rate": 1.5196090841648665e-05,
      "loss": 0.5257,
      "step": 21298
    },
    {
      "epoch": 0.6542868552821552,
      "grad_norm": 0.34124502539634705,
      "learning_rate": 1.5195677921433683e-05,
      "loss": 0.5131,
      "step": 21299
    },
    {
      "epoch": 0.6543175744171044,
      "grad_norm": 0.36015501618385315,
      "learning_rate": 1.5195264989083833e-05,
      "loss": 0.6274,
      "step": 21300
    },
    {
      "epoch": 0.6543482935520536,
      "grad_norm": 0.4206088185310364,
      "learning_rate": 1.519485204460008e-05,
      "loss": 0.6502,
      "step": 21301
    },
    {
      "epoch": 0.6543790126870027,
      "grad_norm": 0.39417484402656555,
      "learning_rate": 1.5194439087983389e-05,
      "loss": 0.6225,
      "step": 21302
    },
    {
      "epoch": 0.654409731821952,
      "grad_norm": 0.4232264459133148,
      "learning_rate": 1.5194026119234719e-05,
      "loss": 0.604,
      "step": 21303
    },
    {
      "epoch": 0.6544404509569011,
      "grad_norm": 0.3604901134967804,
      "learning_rate": 1.519361313835504e-05,
      "loss": 0.5869,
      "step": 21304
    },
    {
      "epoch": 0.6544711700918502,
      "grad_norm": 0.4860617220401764,
      "learning_rate": 1.5193200145345315e-05,
      "loss": 0.654,
      "step": 21305
    },
    {
      "epoch": 0.6545018892267994,
      "grad_norm": 0.552847683429718,
      "learning_rate": 1.5192787140206507e-05,
      "loss": 0.6204,
      "step": 21306
    },
    {
      "epoch": 0.6545326083617485,
      "grad_norm": 0.33214879035949707,
      "learning_rate": 1.5192374122939581e-05,
      "loss": 0.5637,
      "step": 21307
    },
    {
      "epoch": 0.6545633274966977,
      "grad_norm": 0.3869237005710602,
      "learning_rate": 1.5191961093545508e-05,
      "loss": 0.5709,
      "step": 21308
    },
    {
      "epoch": 0.6545940466316469,
      "grad_norm": 0.33624953031539917,
      "learning_rate": 1.5191548052025243e-05,
      "loss": 0.5412,
      "step": 21309
    },
    {
      "epoch": 0.654624765766596,
      "grad_norm": 0.4052075743675232,
      "learning_rate": 1.5191134998379755e-05,
      "loss": 0.6068,
      "step": 21310
    },
    {
      "epoch": 0.6546554849015451,
      "grad_norm": 0.38116681575775146,
      "learning_rate": 1.5190721932610012e-05,
      "loss": 0.5822,
      "step": 21311
    },
    {
      "epoch": 0.6546862040364944,
      "grad_norm": 0.3540833592414856,
      "learning_rate": 1.519030885471697e-05,
      "loss": 0.5364,
      "step": 21312
    },
    {
      "epoch": 0.6547169231714435,
      "grad_norm": 0.44599059224128723,
      "learning_rate": 1.51898957647016e-05,
      "loss": 0.503,
      "step": 21313
    },
    {
      "epoch": 0.6547476423063926,
      "grad_norm": 0.35608598589897156,
      "learning_rate": 1.5189482662564872e-05,
      "loss": 0.5945,
      "step": 21314
    },
    {
      "epoch": 0.6547783614413418,
      "grad_norm": 0.3844536542892456,
      "learning_rate": 1.518906954830774e-05,
      "loss": 0.4812,
      "step": 21315
    },
    {
      "epoch": 0.654809080576291,
      "grad_norm": 0.3706144690513611,
      "learning_rate": 1.5188656421931174e-05,
      "loss": 0.5512,
      "step": 21316
    },
    {
      "epoch": 0.6548397997112402,
      "grad_norm": 0.3958333730697632,
      "learning_rate": 1.5188243283436137e-05,
      "loss": 0.5213,
      "step": 21317
    },
    {
      "epoch": 0.6548705188461893,
      "grad_norm": 0.3822380304336548,
      "learning_rate": 1.5187830132823598e-05,
      "loss": 0.5795,
      "step": 21318
    },
    {
      "epoch": 0.6549012379811384,
      "grad_norm": 0.3616386651992798,
      "learning_rate": 1.5187416970094519e-05,
      "loss": 0.6099,
      "step": 21319
    },
    {
      "epoch": 0.6549319571160876,
      "grad_norm": 0.4148938059806824,
      "learning_rate": 1.5187003795249866e-05,
      "loss": 0.5945,
      "step": 21320
    },
    {
      "epoch": 0.6549626762510368,
      "grad_norm": 0.3439237177371979,
      "learning_rate": 1.5186590608290601e-05,
      "loss": 0.6031,
      "step": 21321
    },
    {
      "epoch": 0.6549933953859859,
      "grad_norm": 0.3367989659309387,
      "learning_rate": 1.5186177409217693e-05,
      "loss": 0.5675,
      "step": 21322
    },
    {
      "epoch": 0.6550241145209351,
      "grad_norm": 0.3483068645000458,
      "learning_rate": 1.5185764198032106e-05,
      "loss": 0.549,
      "step": 21323
    },
    {
      "epoch": 0.6550548336558842,
      "grad_norm": 0.3423927426338196,
      "learning_rate": 1.5185350974734804e-05,
      "loss": 0.5682,
      "step": 21324
    },
    {
      "epoch": 0.6550855527908334,
      "grad_norm": 0.4201408624649048,
      "learning_rate": 1.5184937739326752e-05,
      "loss": 0.5283,
      "step": 21325
    },
    {
      "epoch": 0.6551162719257826,
      "grad_norm": 0.4295091927051544,
      "learning_rate": 1.518452449180892e-05,
      "loss": 0.5266,
      "step": 21326
    },
    {
      "epoch": 0.6551469910607317,
      "grad_norm": 0.3739658296108246,
      "learning_rate": 1.5184111232182264e-05,
      "loss": 0.5916,
      "step": 21327
    },
    {
      "epoch": 0.6551777101956809,
      "grad_norm": 0.354027658700943,
      "learning_rate": 1.5183697960447757e-05,
      "loss": 0.5962,
      "step": 21328
    },
    {
      "epoch": 0.6552084293306301,
      "grad_norm": 0.3570646643638611,
      "learning_rate": 1.5183284676606358e-05,
      "loss": 0.587,
      "step": 21329
    },
    {
      "epoch": 0.6552391484655792,
      "grad_norm": 0.4249320328235626,
      "learning_rate": 1.5182871380659038e-05,
      "loss": 0.5683,
      "step": 21330
    },
    {
      "epoch": 0.6552698676005284,
      "grad_norm": 0.32747507095336914,
      "learning_rate": 1.518245807260676e-05,
      "loss": 0.6393,
      "step": 21331
    },
    {
      "epoch": 0.6553005867354775,
      "grad_norm": 0.3451526463031769,
      "learning_rate": 1.518204475245049e-05,
      "loss": 0.5564,
      "step": 21332
    },
    {
      "epoch": 0.6553313058704267,
      "grad_norm": 0.3794431984424591,
      "learning_rate": 1.518163142019119e-05,
      "loss": 0.5298,
      "step": 21333
    },
    {
      "epoch": 0.6553620250053759,
      "grad_norm": 0.42740288376808167,
      "learning_rate": 1.518121807582983e-05,
      "loss": 0.5005,
      "step": 21334
    },
    {
      "epoch": 0.655392744140325,
      "grad_norm": 0.42671099305152893,
      "learning_rate": 1.5180804719367372e-05,
      "loss": 0.5742,
      "step": 21335
    },
    {
      "epoch": 0.6554234632752741,
      "grad_norm": 0.32646438479423523,
      "learning_rate": 1.5180391350804783e-05,
      "loss": 0.5607,
      "step": 21336
    },
    {
      "epoch": 0.6554541824102234,
      "grad_norm": 0.34121397137641907,
      "learning_rate": 1.5179977970143029e-05,
      "loss": 0.5349,
      "step": 21337
    },
    {
      "epoch": 0.6554849015451725,
      "grad_norm": 0.3382683992385864,
      "learning_rate": 1.5179564577383072e-05,
      "loss": 0.5635,
      "step": 21338
    },
    {
      "epoch": 0.6555156206801217,
      "grad_norm": 0.42304089665412903,
      "learning_rate": 1.5179151172525886e-05,
      "loss": 0.5801,
      "step": 21339
    },
    {
      "epoch": 0.6555463398150708,
      "grad_norm": 0.3641531467437744,
      "learning_rate": 1.5178737755572424e-05,
      "loss": 0.5277,
      "step": 21340
    },
    {
      "epoch": 0.6555770589500199,
      "grad_norm": 0.402485728263855,
      "learning_rate": 1.5178324326523663e-05,
      "loss": 0.5766,
      "step": 21341
    },
    {
      "epoch": 0.6556077780849692,
      "grad_norm": 0.43885186314582825,
      "learning_rate": 1.5177910885380563e-05,
      "loss": 0.6454,
      "step": 21342
    },
    {
      "epoch": 0.6556384972199183,
      "grad_norm": 0.37003961205482483,
      "learning_rate": 1.517749743214409e-05,
      "loss": 0.5419,
      "step": 21343
    },
    {
      "epoch": 0.6556692163548674,
      "grad_norm": 0.34169864654541016,
      "learning_rate": 1.517708396681521e-05,
      "loss": 0.5698,
      "step": 21344
    },
    {
      "epoch": 0.6556999354898166,
      "grad_norm": 0.3646971881389618,
      "learning_rate": 1.517667048939489e-05,
      "loss": 0.5374,
      "step": 21345
    },
    {
      "epoch": 0.6557306546247658,
      "grad_norm": 0.37150439620018005,
      "learning_rate": 1.5176256999884093e-05,
      "loss": 0.5694,
      "step": 21346
    },
    {
      "epoch": 0.6557613737597149,
      "grad_norm": 0.4174787700176239,
      "learning_rate": 1.5175843498283786e-05,
      "loss": 0.5069,
      "step": 21347
    },
    {
      "epoch": 0.6557920928946641,
      "grad_norm": 0.31925278902053833,
      "learning_rate": 1.5175429984594936e-05,
      "loss": 0.5447,
      "step": 21348
    },
    {
      "epoch": 0.6558228120296132,
      "grad_norm": 0.32446563243865967,
      "learning_rate": 1.5175016458818506e-05,
      "loss": 0.482,
      "step": 21349
    },
    {
      "epoch": 0.6558535311645624,
      "grad_norm": 0.33477210998535156,
      "learning_rate": 1.5174602920955468e-05,
      "loss": 0.6458,
      "step": 21350
    },
    {
      "epoch": 0.6558842502995116,
      "grad_norm": 0.38155731558799744,
      "learning_rate": 1.5174189371006778e-05,
      "loss": 0.5897,
      "step": 21351
    },
    {
      "epoch": 0.6559149694344607,
      "grad_norm": 0.3606787323951721,
      "learning_rate": 1.5173775808973413e-05,
      "loss": 0.5602,
      "step": 21352
    },
    {
      "epoch": 0.6559456885694099,
      "grad_norm": 0.3643347918987274,
      "learning_rate": 1.5173362234856328e-05,
      "loss": 0.6095,
      "step": 21353
    },
    {
      "epoch": 0.655976407704359,
      "grad_norm": 0.38778337836265564,
      "learning_rate": 1.5172948648656496e-05,
      "loss": 0.5164,
      "step": 21354
    },
    {
      "epoch": 0.6560071268393082,
      "grad_norm": 0.397091269493103,
      "learning_rate": 1.517253505037488e-05,
      "loss": 0.5621,
      "step": 21355
    },
    {
      "epoch": 0.6560378459742574,
      "grad_norm": 0.3706255257129669,
      "learning_rate": 1.5172121440012451e-05,
      "loss": 0.5083,
      "step": 21356
    },
    {
      "epoch": 0.6560685651092065,
      "grad_norm": 0.36097967624664307,
      "learning_rate": 1.517170781757017e-05,
      "loss": 0.5223,
      "step": 21357
    },
    {
      "epoch": 0.6560992842441556,
      "grad_norm": 0.3413541615009308,
      "learning_rate": 1.5171294183049e-05,
      "loss": 0.5218,
      "step": 21358
    },
    {
      "epoch": 0.6561300033791049,
      "grad_norm": 0.3670789897441864,
      "learning_rate": 1.5170880536449917e-05,
      "loss": 0.5455,
      "step": 21359
    },
    {
      "epoch": 0.656160722514054,
      "grad_norm": 0.36502763628959656,
      "learning_rate": 1.5170466877773879e-05,
      "loss": 0.5231,
      "step": 21360
    },
    {
      "epoch": 0.6561914416490031,
      "grad_norm": 0.3550271689891815,
      "learning_rate": 1.5170053207021856e-05,
      "loss": 0.501,
      "step": 21361
    },
    {
      "epoch": 0.6562221607839523,
      "grad_norm": 0.3810182511806488,
      "learning_rate": 1.5169639524194811e-05,
      "loss": 0.5058,
      "step": 21362
    },
    {
      "epoch": 0.6562528799189015,
      "grad_norm": 0.33492833375930786,
      "learning_rate": 1.516922582929371e-05,
      "loss": 0.5493,
      "step": 21363
    },
    {
      "epoch": 0.6562835990538507,
      "grad_norm": 0.334085077047348,
      "learning_rate": 1.5168812122319522e-05,
      "loss": 0.5119,
      "step": 21364
    },
    {
      "epoch": 0.6563143181887998,
      "grad_norm": 0.3719846308231354,
      "learning_rate": 1.5168398403273214e-05,
      "loss": 0.5219,
      "step": 21365
    },
    {
      "epoch": 0.6563450373237489,
      "grad_norm": 0.3981349766254425,
      "learning_rate": 1.516798467215575e-05,
      "loss": 0.5098,
      "step": 21366
    },
    {
      "epoch": 0.6563757564586982,
      "grad_norm": 0.37250784039497375,
      "learning_rate": 1.5167570928968096e-05,
      "loss": 0.5796,
      "step": 21367
    },
    {
      "epoch": 0.6564064755936473,
      "grad_norm": 0.3397180438041687,
      "learning_rate": 1.5167157173711223e-05,
      "loss": 0.5512,
      "step": 21368
    },
    {
      "epoch": 0.6564371947285964,
      "grad_norm": 0.4083602726459503,
      "learning_rate": 1.5166743406386087e-05,
      "loss": 0.5605,
      "step": 21369
    },
    {
      "epoch": 0.6564679138635456,
      "grad_norm": 0.32612818479537964,
      "learning_rate": 1.5166329626993666e-05,
      "loss": 0.5256,
      "step": 21370
    },
    {
      "epoch": 0.6564986329984948,
      "grad_norm": 0.41936948895454407,
      "learning_rate": 1.5165915835534922e-05,
      "loss": 0.5875,
      "step": 21371
    },
    {
      "epoch": 0.6565293521334439,
      "grad_norm": 0.44222545623779297,
      "learning_rate": 1.5165502032010815e-05,
      "loss": 0.5521,
      "step": 21372
    },
    {
      "epoch": 0.6565600712683931,
      "grad_norm": 0.34852221608161926,
      "learning_rate": 1.516508821642232e-05,
      "loss": 0.5653,
      "step": 21373
    },
    {
      "epoch": 0.6565907904033422,
      "grad_norm": 0.33705440163612366,
      "learning_rate": 1.5164674388770402e-05,
      "loss": 0.5569,
      "step": 21374
    },
    {
      "epoch": 0.6566215095382913,
      "grad_norm": 0.37520697712898254,
      "learning_rate": 1.5164260549056025e-05,
      "loss": 0.5301,
      "step": 21375
    },
    {
      "epoch": 0.6566522286732406,
      "grad_norm": 0.4241773188114166,
      "learning_rate": 1.5163846697280158e-05,
      "loss": 0.5811,
      "step": 21376
    },
    {
      "epoch": 0.6566829478081897,
      "grad_norm": 0.34913191199302673,
      "learning_rate": 1.5163432833443766e-05,
      "loss": 0.5661,
      "step": 21377
    },
    {
      "epoch": 0.6567136669431389,
      "grad_norm": 0.3589656949043274,
      "learning_rate": 1.5163018957547819e-05,
      "loss": 0.5697,
      "step": 21378
    },
    {
      "epoch": 0.656744386078088,
      "grad_norm": 0.3666149377822876,
      "learning_rate": 1.5162605069593275e-05,
      "loss": 0.5653,
      "step": 21379
    },
    {
      "epoch": 0.6567751052130372,
      "grad_norm": 0.33648064732551575,
      "learning_rate": 1.516219116958111e-05,
      "loss": 0.5913,
      "step": 21380
    },
    {
      "epoch": 0.6568058243479864,
      "grad_norm": 0.35224977135658264,
      "learning_rate": 1.5161777257512285e-05,
      "loss": 0.4804,
      "step": 21381
    },
    {
      "epoch": 0.6568365434829355,
      "grad_norm": 0.3747677206993103,
      "learning_rate": 1.5161363333387771e-05,
      "loss": 0.6009,
      "step": 21382
    },
    {
      "epoch": 0.6568672626178846,
      "grad_norm": 0.3011206388473511,
      "learning_rate": 1.5160949397208531e-05,
      "loss": 0.4922,
      "step": 21383
    },
    {
      "epoch": 0.6568979817528339,
      "grad_norm": 0.31312501430511475,
      "learning_rate": 1.5160535448975534e-05,
      "loss": 0.4839,
      "step": 21384
    },
    {
      "epoch": 0.656928700887783,
      "grad_norm": 0.3819100558757782,
      "learning_rate": 1.5160121488689745e-05,
      "loss": 0.5523,
      "step": 21385
    },
    {
      "epoch": 0.6569594200227321,
      "grad_norm": 0.347486674785614,
      "learning_rate": 1.515970751635213e-05,
      "loss": 0.6206,
      "step": 21386
    },
    {
      "epoch": 0.6569901391576813,
      "grad_norm": 0.3591974973678589,
      "learning_rate": 1.5159293531963662e-05,
      "loss": 0.5763,
      "step": 21387
    },
    {
      "epoch": 0.6570208582926305,
      "grad_norm": 0.4106321334838867,
      "learning_rate": 1.51588795355253e-05,
      "loss": 0.6494,
      "step": 21388
    },
    {
      "epoch": 0.6570515774275797,
      "grad_norm": 0.41878724098205566,
      "learning_rate": 1.5158465527038018e-05,
      "loss": 0.6044,
      "step": 21389
    },
    {
      "epoch": 0.6570822965625288,
      "grad_norm": 0.45128133893013,
      "learning_rate": 1.5158051506502776e-05,
      "loss": 0.5811,
      "step": 21390
    },
    {
      "epoch": 0.6571130156974779,
      "grad_norm": 0.33213844895362854,
      "learning_rate": 1.5157637473920548e-05,
      "loss": 0.4924,
      "step": 21391
    },
    {
      "epoch": 0.6571437348324272,
      "grad_norm": 0.3574727773666382,
      "learning_rate": 1.5157223429292294e-05,
      "loss": 0.6311,
      "step": 21392
    },
    {
      "epoch": 0.6571744539673763,
      "grad_norm": 0.34079107642173767,
      "learning_rate": 1.5156809372618985e-05,
      "loss": 0.5239,
      "step": 21393
    },
    {
      "epoch": 0.6572051731023254,
      "grad_norm": 0.34001481533050537,
      "learning_rate": 1.5156395303901587e-05,
      "loss": 0.5005,
      "step": 21394
    },
    {
      "epoch": 0.6572358922372746,
      "grad_norm": 0.3560900092124939,
      "learning_rate": 1.5155981223141072e-05,
      "loss": 0.5807,
      "step": 21395
    },
    {
      "epoch": 0.6572666113722238,
      "grad_norm": 0.37193045020103455,
      "learning_rate": 1.5155567130338402e-05,
      "loss": 0.6064,
      "step": 21396
    },
    {
      "epoch": 0.6572973305071729,
      "grad_norm": 0.35850316286087036,
      "learning_rate": 1.5155153025494543e-05,
      "loss": 0.5276,
      "step": 21397
    },
    {
      "epoch": 0.6573280496421221,
      "grad_norm": 0.5291918516159058,
      "learning_rate": 1.5154738908610465e-05,
      "loss": 0.5162,
      "step": 21398
    },
    {
      "epoch": 0.6573587687770712,
      "grad_norm": 0.4553773105144501,
      "learning_rate": 1.515432477968713e-05,
      "loss": 0.5663,
      "step": 21399
    },
    {
      "epoch": 0.6573894879120203,
      "grad_norm": 0.37874406576156616,
      "learning_rate": 1.5153910638725516e-05,
      "loss": 0.5667,
      "step": 21400
    },
    {
      "epoch": 0.6574202070469696,
      "grad_norm": 0.35394057631492615,
      "learning_rate": 1.515349648572658e-05,
      "loss": 0.4824,
      "step": 21401
    },
    {
      "epoch": 0.6574509261819187,
      "grad_norm": 0.38720422983169556,
      "learning_rate": 1.5153082320691295e-05,
      "loss": 0.5867,
      "step": 21402
    },
    {
      "epoch": 0.6574816453168679,
      "grad_norm": 0.37196874618530273,
      "learning_rate": 1.5152668143620624e-05,
      "loss": 0.5795,
      "step": 21403
    },
    {
      "epoch": 0.657512364451817,
      "grad_norm": 0.3900143504142761,
      "learning_rate": 1.5152253954515537e-05,
      "loss": 0.5065,
      "step": 21404
    },
    {
      "epoch": 0.6575430835867662,
      "grad_norm": 0.40589484572410583,
      "learning_rate": 1.5151839753377e-05,
      "loss": 0.5513,
      "step": 21405
    },
    {
      "epoch": 0.6575738027217154,
      "grad_norm": 0.368908166885376,
      "learning_rate": 1.5151425540205984e-05,
      "loss": 0.616,
      "step": 21406
    },
    {
      "epoch": 0.6576045218566645,
      "grad_norm": 0.3660963773727417,
      "learning_rate": 1.5151011315003455e-05,
      "loss": 0.5618,
      "step": 21407
    },
    {
      "epoch": 0.6576352409916136,
      "grad_norm": 0.3742905557155609,
      "learning_rate": 1.5150597077770374e-05,
      "loss": 0.5235,
      "step": 21408
    },
    {
      "epoch": 0.6576659601265629,
      "grad_norm": 0.3400203585624695,
      "learning_rate": 1.5150182828507719e-05,
      "loss": 0.5459,
      "step": 21409
    },
    {
      "epoch": 0.657696679261512,
      "grad_norm": 0.35715004801750183,
      "learning_rate": 1.514976856721645e-05,
      "loss": 0.5893,
      "step": 21410
    },
    {
      "epoch": 0.6577273983964611,
      "grad_norm": 0.3420814871788025,
      "learning_rate": 1.5149354293897538e-05,
      "loss": 0.5797,
      "step": 21411
    },
    {
      "epoch": 0.6577581175314103,
      "grad_norm": 0.40958234667778015,
      "learning_rate": 1.514894000855195e-05,
      "loss": 0.6128,
      "step": 21412
    },
    {
      "epoch": 0.6577888366663595,
      "grad_norm": 0.41843804717063904,
      "learning_rate": 1.514852571118065e-05,
      "loss": 0.6083,
      "step": 21413
    },
    {
      "epoch": 0.6578195558013087,
      "grad_norm": 0.37203067541122437,
      "learning_rate": 1.5148111401784613e-05,
      "loss": 0.5738,
      "step": 21414
    },
    {
      "epoch": 0.6578502749362578,
      "grad_norm": 0.3540958762168884,
      "learning_rate": 1.5147697080364798e-05,
      "loss": 0.6415,
      "step": 21415
    },
    {
      "epoch": 0.6578809940712069,
      "grad_norm": 0.39587607979774475,
      "learning_rate": 1.5147282746922178e-05,
      "loss": 0.5833,
      "step": 21416
    },
    {
      "epoch": 0.6579117132061562,
      "grad_norm": 0.347836971282959,
      "learning_rate": 1.5146868401457721e-05,
      "loss": 0.5804,
      "step": 21417
    },
    {
      "epoch": 0.6579424323411053,
      "grad_norm": 0.39250636100769043,
      "learning_rate": 1.5146454043972395e-05,
      "loss": 0.5471,
      "step": 21418
    },
    {
      "epoch": 0.6579731514760544,
      "grad_norm": 0.368876576423645,
      "learning_rate": 1.5146039674467164e-05,
      "loss": 0.5734,
      "step": 21419
    },
    {
      "epoch": 0.6580038706110036,
      "grad_norm": 0.3617180585861206,
      "learning_rate": 1.5145625292942999e-05,
      "loss": 0.5985,
      "step": 21420
    },
    {
      "epoch": 0.6580345897459527,
      "grad_norm": 0.44370341300964355,
      "learning_rate": 1.5145210899400864e-05,
      "loss": 0.6021,
      "step": 21421
    },
    {
      "epoch": 0.6580653088809019,
      "grad_norm": 0.3637896478176117,
      "learning_rate": 1.5144796493841731e-05,
      "loss": 0.6323,
      "step": 21422
    },
    {
      "epoch": 0.6580960280158511,
      "grad_norm": 0.3441605269908905,
      "learning_rate": 1.5144382076266568e-05,
      "loss": 0.6214,
      "step": 21423
    },
    {
      "epoch": 0.6581267471508002,
      "grad_norm": 0.7899920344352722,
      "learning_rate": 1.5143967646676339e-05,
      "loss": 0.6146,
      "step": 21424
    },
    {
      "epoch": 0.6581574662857494,
      "grad_norm": 0.42392557859420776,
      "learning_rate": 1.5143553205072016e-05,
      "loss": 0.6125,
      "step": 21425
    },
    {
      "epoch": 0.6581881854206986,
      "grad_norm": 0.3676445782184601,
      "learning_rate": 1.5143138751454562e-05,
      "loss": 0.5234,
      "step": 21426
    },
    {
      "epoch": 0.6582189045556477,
      "grad_norm": 0.3689061403274536,
      "learning_rate": 1.5142724285824953e-05,
      "loss": 0.5382,
      "step": 21427
    },
    {
      "epoch": 0.6582496236905969,
      "grad_norm": 0.36866438388824463,
      "learning_rate": 1.5142309808184147e-05,
      "loss": 0.5926,
      "step": 21428
    },
    {
      "epoch": 0.658280342825546,
      "grad_norm": 0.4071403741836548,
      "learning_rate": 1.5141895318533123e-05,
      "loss": 0.643,
      "step": 21429
    },
    {
      "epoch": 0.6583110619604952,
      "grad_norm": 0.44519367814064026,
      "learning_rate": 1.5141480816872843e-05,
      "loss": 0.5567,
      "step": 21430
    },
    {
      "epoch": 0.6583417810954444,
      "grad_norm": 0.354015052318573,
      "learning_rate": 1.514106630320427e-05,
      "loss": 0.5278,
      "step": 21431
    },
    {
      "epoch": 0.6583725002303935,
      "grad_norm": 0.3890515863895416,
      "learning_rate": 1.5140651777528383e-05,
      "loss": 0.5562,
      "step": 21432
    },
    {
      "epoch": 0.6584032193653426,
      "grad_norm": 0.3459175229072571,
      "learning_rate": 1.514023723984614e-05,
      "loss": 0.5879,
      "step": 21433
    },
    {
      "epoch": 0.6584339385002919,
      "grad_norm": 0.37181705236434937,
      "learning_rate": 1.5139822690158519e-05,
      "loss": 0.5838,
      "step": 21434
    },
    {
      "epoch": 0.658464657635241,
      "grad_norm": 0.4267209470272064,
      "learning_rate": 1.5139408128466481e-05,
      "loss": 0.5512,
      "step": 21435
    },
    {
      "epoch": 0.6584953767701901,
      "grad_norm": 0.39904215931892395,
      "learning_rate": 1.5138993554770998e-05,
      "loss": 0.581,
      "step": 21436
    },
    {
      "epoch": 0.6585260959051393,
      "grad_norm": 0.33324140310287476,
      "learning_rate": 1.5138578969073032e-05,
      "loss": 0.5296,
      "step": 21437
    },
    {
      "epoch": 0.6585568150400885,
      "grad_norm": 0.35187578201293945,
      "learning_rate": 1.513816437137356e-05,
      "loss": 0.5413,
      "step": 21438
    },
    {
      "epoch": 0.6585875341750377,
      "grad_norm": 0.36013263463974,
      "learning_rate": 1.5137749761673544e-05,
      "loss": 0.5316,
      "step": 21439
    },
    {
      "epoch": 0.6586182533099868,
      "grad_norm": 0.3480548858642578,
      "learning_rate": 1.5137335139973957e-05,
      "loss": 0.5678,
      "step": 21440
    },
    {
      "epoch": 0.6586489724449359,
      "grad_norm": 0.35707542300224304,
      "learning_rate": 1.5136920506275765e-05,
      "loss": 0.6635,
      "step": 21441
    },
    {
      "epoch": 0.6586796915798852,
      "grad_norm": 0.5650831460952759,
      "learning_rate": 1.5136505860579935e-05,
      "loss": 0.5524,
      "step": 21442
    },
    {
      "epoch": 0.6587104107148343,
      "grad_norm": 0.3627931773662567,
      "learning_rate": 1.5136091202887438e-05,
      "loss": 0.6128,
      "step": 21443
    },
    {
      "epoch": 0.6587411298497834,
      "grad_norm": 0.36739397048950195,
      "learning_rate": 1.5135676533199237e-05,
      "loss": 0.5079,
      "step": 21444
    },
    {
      "epoch": 0.6587718489847326,
      "grad_norm": 0.37765148282051086,
      "learning_rate": 1.5135261851516307e-05,
      "loss": 0.6047,
      "step": 21445
    },
    {
      "epoch": 0.6588025681196817,
      "grad_norm": 0.37004679441452026,
      "learning_rate": 1.5134847157839616e-05,
      "loss": 0.6279,
      "step": 21446
    },
    {
      "epoch": 0.6588332872546309,
      "grad_norm": 0.3430337905883789,
      "learning_rate": 1.513443245217013e-05,
      "loss": 0.4933,
      "step": 21447
    },
    {
      "epoch": 0.6588640063895801,
      "grad_norm": 0.34481894969940186,
      "learning_rate": 1.513401773450882e-05,
      "loss": 0.5713,
      "step": 21448
    },
    {
      "epoch": 0.6588947255245292,
      "grad_norm": 0.34981468319892883,
      "learning_rate": 1.513360300485665e-05,
      "loss": 0.6,
      "step": 21449
    },
    {
      "epoch": 0.6589254446594784,
      "grad_norm": 0.38890519738197327,
      "learning_rate": 1.5133188263214595e-05,
      "loss": 0.5689,
      "step": 21450
    },
    {
      "epoch": 0.6589561637944276,
      "grad_norm": 0.36562806367874146,
      "learning_rate": 1.5132773509583618e-05,
      "loss": 0.5704,
      "step": 21451
    },
    {
      "epoch": 0.6589868829293767,
      "grad_norm": 0.3667706549167633,
      "learning_rate": 1.513235874396469e-05,
      "loss": 0.5444,
      "step": 21452
    },
    {
      "epoch": 0.6590176020643259,
      "grad_norm": 0.32318028807640076,
      "learning_rate": 1.5131943966358779e-05,
      "loss": 0.5362,
      "step": 21453
    },
    {
      "epoch": 0.659048321199275,
      "grad_norm": 0.33237916231155396,
      "learning_rate": 1.5131529176766857e-05,
      "loss": 0.6092,
      "step": 21454
    },
    {
      "epoch": 0.6590790403342242,
      "grad_norm": 0.35832616686820984,
      "learning_rate": 1.513111437518989e-05,
      "loss": 0.5556,
      "step": 21455
    },
    {
      "epoch": 0.6591097594691734,
      "grad_norm": 0.320765882730484,
      "learning_rate": 1.5130699561628848e-05,
      "loss": 0.5916,
      "step": 21456
    },
    {
      "epoch": 0.6591404786041225,
      "grad_norm": 0.35263916850090027,
      "learning_rate": 1.5130284736084693e-05,
      "loss": 0.5543,
      "step": 21457
    },
    {
      "epoch": 0.6591711977390716,
      "grad_norm": 0.32966575026512146,
      "learning_rate": 1.5129869898558406e-05,
      "loss": 0.4536,
      "step": 21458
    },
    {
      "epoch": 0.6592019168740209,
      "grad_norm": 0.377752423286438,
      "learning_rate": 1.512945504905095e-05,
      "loss": 0.618,
      "step": 21459
    },
    {
      "epoch": 0.65923263600897,
      "grad_norm": 0.32686948776245117,
      "learning_rate": 1.512904018756329e-05,
      "loss": 0.4796,
      "step": 21460
    },
    {
      "epoch": 0.6592633551439191,
      "grad_norm": 0.3874197006225586,
      "learning_rate": 1.5128625314096396e-05,
      "loss": 0.5212,
      "step": 21461
    },
    {
      "epoch": 0.6592940742788683,
      "grad_norm": 0.32616671919822693,
      "learning_rate": 1.5128210428651243e-05,
      "loss": 0.5218,
      "step": 21462
    },
    {
      "epoch": 0.6593247934138174,
      "grad_norm": 0.36737462878227234,
      "learning_rate": 1.5127795531228796e-05,
      "loss": 0.5372,
      "step": 21463
    },
    {
      "epoch": 0.6593555125487667,
      "grad_norm": 0.4097331166267395,
      "learning_rate": 1.5127380621830026e-05,
      "loss": 0.585,
      "step": 21464
    },
    {
      "epoch": 0.6593862316837158,
      "grad_norm": 0.3632565140724182,
      "learning_rate": 1.5126965700455895e-05,
      "loss": 0.5499,
      "step": 21465
    },
    {
      "epoch": 0.6594169508186649,
      "grad_norm": 0.4267031252384186,
      "learning_rate": 1.5126550767107384e-05,
      "loss": 0.5868,
      "step": 21466
    },
    {
      "epoch": 0.6594476699536141,
      "grad_norm": 0.5180332660675049,
      "learning_rate": 1.512613582178545e-05,
      "loss": 0.5838,
      "step": 21467
    },
    {
      "epoch": 0.6594783890885633,
      "grad_norm": 0.32962167263031006,
      "learning_rate": 1.5125720864491072e-05,
      "loss": 0.4804,
      "step": 21468
    },
    {
      "epoch": 0.6595091082235124,
      "grad_norm": 0.36834126710891724,
      "learning_rate": 1.5125305895225215e-05,
      "loss": 0.5709,
      "step": 21469
    },
    {
      "epoch": 0.6595398273584616,
      "grad_norm": 0.3667164146900177,
      "learning_rate": 1.5124890913988846e-05,
      "loss": 0.5428,
      "step": 21470
    },
    {
      "epoch": 0.6595705464934107,
      "grad_norm": 0.44555899500846863,
      "learning_rate": 1.5124475920782934e-05,
      "loss": 0.5359,
      "step": 21471
    },
    {
      "epoch": 0.6596012656283599,
      "grad_norm": 0.36030012369155884,
      "learning_rate": 1.5124060915608455e-05,
      "loss": 0.4663,
      "step": 21472
    },
    {
      "epoch": 0.6596319847633091,
      "grad_norm": 0.3763372600078583,
      "learning_rate": 1.5123645898466372e-05,
      "loss": 0.5758,
      "step": 21473
    },
    {
      "epoch": 0.6596627038982582,
      "grad_norm": 0.34288156032562256,
      "learning_rate": 1.5123230869357661e-05,
      "loss": 0.537,
      "step": 21474
    },
    {
      "epoch": 0.6596934230332074,
      "grad_norm": 0.33631911873817444,
      "learning_rate": 1.5122815828283281e-05,
      "loss": 0.559,
      "step": 21475
    },
    {
      "epoch": 0.6597241421681566,
      "grad_norm": 0.4178950786590576,
      "learning_rate": 1.5122400775244207e-05,
      "loss": 0.5422,
      "step": 21476
    },
    {
      "epoch": 0.6597548613031057,
      "grad_norm": 0.5344930291175842,
      "learning_rate": 1.5121985710241411e-05,
      "loss": 0.5794,
      "step": 21477
    },
    {
      "epoch": 0.6597855804380549,
      "grad_norm": 0.3561966121196747,
      "learning_rate": 1.5121570633275857e-05,
      "loss": 0.5308,
      "step": 21478
    },
    {
      "epoch": 0.659816299573004,
      "grad_norm": 0.3865406811237335,
      "learning_rate": 1.5121155544348521e-05,
      "loss": 0.5534,
      "step": 21479
    },
    {
      "epoch": 0.6598470187079531,
      "grad_norm": 0.3584230840206146,
      "learning_rate": 1.5120740443460364e-05,
      "loss": 0.5832,
      "step": 21480
    },
    {
      "epoch": 0.6598777378429024,
      "grad_norm": 0.3842792510986328,
      "learning_rate": 1.512032533061236e-05,
      "loss": 0.4825,
      "step": 21481
    },
    {
      "epoch": 0.6599084569778515,
      "grad_norm": 0.3396380841732025,
      "learning_rate": 1.5119910205805482e-05,
      "loss": 0.5423,
      "step": 21482
    },
    {
      "epoch": 0.6599391761128006,
      "grad_norm": 0.3795052170753479,
      "learning_rate": 1.5119495069040693e-05,
      "loss": 0.5786,
      "step": 21483
    },
    {
      "epoch": 0.6599698952477498,
      "grad_norm": 0.3311948776245117,
      "learning_rate": 1.5119079920318968e-05,
      "loss": 0.5828,
      "step": 21484
    },
    {
      "epoch": 0.660000614382699,
      "grad_norm": 0.34203943610191345,
      "learning_rate": 1.5118664759641273e-05,
      "loss": 0.5361,
      "step": 21485
    },
    {
      "epoch": 0.6600313335176481,
      "grad_norm": 0.3582075834274292,
      "learning_rate": 1.5118249587008582e-05,
      "loss": 0.5407,
      "step": 21486
    },
    {
      "epoch": 0.6600620526525973,
      "grad_norm": 0.34971901774406433,
      "learning_rate": 1.5117834402421858e-05,
      "loss": 0.5561,
      "step": 21487
    },
    {
      "epoch": 0.6600927717875464,
      "grad_norm": 0.476724773645401,
      "learning_rate": 1.5117419205882075e-05,
      "loss": 0.5831,
      "step": 21488
    },
    {
      "epoch": 0.6601234909224957,
      "grad_norm": 0.40123459696769714,
      "learning_rate": 1.51170039973902e-05,
      "loss": 0.5032,
      "step": 21489
    },
    {
      "epoch": 0.6601542100574448,
      "grad_norm": 0.3576597571372986,
      "learning_rate": 1.511658877694721e-05,
      "loss": 0.5312,
      "step": 21490
    },
    {
      "epoch": 0.6601849291923939,
      "grad_norm": 0.3642289638519287,
      "learning_rate": 1.5116173544554067e-05,
      "loss": 0.5875,
      "step": 21491
    },
    {
      "epoch": 0.6602156483273431,
      "grad_norm": 0.32313698530197144,
      "learning_rate": 1.5115758300211743e-05,
      "loss": 0.4595,
      "step": 21492
    },
    {
      "epoch": 0.6602463674622923,
      "grad_norm": 0.3468239903450012,
      "learning_rate": 1.5115343043921211e-05,
      "loss": 0.632,
      "step": 21493
    },
    {
      "epoch": 0.6602770865972414,
      "grad_norm": 0.34924691915512085,
      "learning_rate": 1.5114927775683432e-05,
      "loss": 0.6122,
      "step": 21494
    },
    {
      "epoch": 0.6603078057321906,
      "grad_norm": 0.3270723521709442,
      "learning_rate": 1.5114512495499387e-05,
      "loss": 0.5633,
      "step": 21495
    },
    {
      "epoch": 0.6603385248671397,
      "grad_norm": 0.3391047716140747,
      "learning_rate": 1.5114097203370039e-05,
      "loss": 0.6022,
      "step": 21496
    },
    {
      "epoch": 0.6603692440020889,
      "grad_norm": 0.6554144024848938,
      "learning_rate": 1.5113681899296361e-05,
      "loss": 0.5499,
      "step": 21497
    },
    {
      "epoch": 0.6603999631370381,
      "grad_norm": 0.3462245464324951,
      "learning_rate": 1.5113266583279322e-05,
      "loss": 0.5023,
      "step": 21498
    },
    {
      "epoch": 0.6604306822719872,
      "grad_norm": 0.6329216361045837,
      "learning_rate": 1.511285125531989e-05,
      "loss": 0.4611,
      "step": 21499
    },
    {
      "epoch": 0.6604614014069364,
      "grad_norm": 0.3910367786884308,
      "learning_rate": 1.5112435915419037e-05,
      "loss": 0.5845,
      "step": 21500
    },
    {
      "epoch": 0.6604921205418856,
      "grad_norm": 0.33518749475479126,
      "learning_rate": 1.5112020563577732e-05,
      "loss": 0.5734,
      "step": 21501
    },
    {
      "epoch": 0.6605228396768347,
      "grad_norm": 0.3216128945350647,
      "learning_rate": 1.5111605199796949e-05,
      "loss": 0.5047,
      "step": 21502
    },
    {
      "epoch": 0.6605535588117839,
      "grad_norm": 0.36419418454170227,
      "learning_rate": 1.5111189824077652e-05,
      "loss": 0.5297,
      "step": 21503
    },
    {
      "epoch": 0.660584277946733,
      "grad_norm": 0.34529975056648254,
      "learning_rate": 1.5110774436420817e-05,
      "loss": 0.6229,
      "step": 21504
    },
    {
      "epoch": 0.6606149970816821,
      "grad_norm": 0.3820805549621582,
      "learning_rate": 1.5110359036827408e-05,
      "loss": 0.6057,
      "step": 21505
    },
    {
      "epoch": 0.6606457162166314,
      "grad_norm": 0.3473156988620758,
      "learning_rate": 1.5109943625298402e-05,
      "loss": 0.5177,
      "step": 21506
    },
    {
      "epoch": 0.6606764353515805,
      "grad_norm": 0.4181376099586487,
      "learning_rate": 1.5109528201834765e-05,
      "loss": 0.5444,
      "step": 21507
    },
    {
      "epoch": 0.6607071544865296,
      "grad_norm": 0.3636975586414337,
      "learning_rate": 1.5109112766437468e-05,
      "loss": 0.6047,
      "step": 21508
    },
    {
      "epoch": 0.6607378736214788,
      "grad_norm": 0.3657945692539215,
      "learning_rate": 1.510869731910748e-05,
      "loss": 0.5486,
      "step": 21509
    },
    {
      "epoch": 0.660768592756428,
      "grad_norm": 0.45839935541152954,
      "learning_rate": 1.5108281859845774e-05,
      "loss": 0.4623,
      "step": 21510
    },
    {
      "epoch": 0.6607993118913771,
      "grad_norm": 0.3842880129814148,
      "learning_rate": 1.5107866388653318e-05,
      "loss": 0.5302,
      "step": 21511
    },
    {
      "epoch": 0.6608300310263263,
      "grad_norm": 0.352143257856369,
      "learning_rate": 1.5107450905531084e-05,
      "loss": 0.6085,
      "step": 21512
    },
    {
      "epoch": 0.6608607501612754,
      "grad_norm": 0.3804492950439453,
      "learning_rate": 1.5107035410480042e-05,
      "loss": 0.5967,
      "step": 21513
    },
    {
      "epoch": 0.6608914692962247,
      "grad_norm": 0.3281829059123993,
      "learning_rate": 1.510661990350116e-05,
      "loss": 0.6196,
      "step": 21514
    },
    {
      "epoch": 0.6609221884311738,
      "grad_norm": 0.6636606454849243,
      "learning_rate": 1.5106204384595415e-05,
      "loss": 0.5403,
      "step": 21515
    },
    {
      "epoch": 0.6609529075661229,
      "grad_norm": 0.34422165155410767,
      "learning_rate": 1.510578885376377e-05,
      "loss": 0.5328,
      "step": 21516
    },
    {
      "epoch": 0.6609836267010721,
      "grad_norm": 0.644050121307373,
      "learning_rate": 1.5105373311007199e-05,
      "loss": 0.6059,
      "step": 21517
    },
    {
      "epoch": 0.6610143458360213,
      "grad_norm": 0.35089996457099915,
      "learning_rate": 1.510495775632667e-05,
      "loss": 0.5824,
      "step": 21518
    },
    {
      "epoch": 0.6610450649709704,
      "grad_norm": 0.40813079476356506,
      "learning_rate": 1.5104542189723157e-05,
      "loss": 0.4322,
      "step": 21519
    },
    {
      "epoch": 0.6610757841059196,
      "grad_norm": 0.3864327371120453,
      "learning_rate": 1.5104126611197632e-05,
      "loss": 0.6251,
      "step": 21520
    },
    {
      "epoch": 0.6611065032408687,
      "grad_norm": 0.34733736515045166,
      "learning_rate": 1.5103711020751058e-05,
      "loss": 0.6066,
      "step": 21521
    },
    {
      "epoch": 0.6611372223758178,
      "grad_norm": 0.3628052771091461,
      "learning_rate": 1.5103295418384414e-05,
      "loss": 0.5451,
      "step": 21522
    },
    {
      "epoch": 0.6611679415107671,
      "grad_norm": 0.3566264510154724,
      "learning_rate": 1.5102879804098665e-05,
      "loss": 0.5392,
      "step": 21523
    },
    {
      "epoch": 0.6611986606457162,
      "grad_norm": 0.38928407430648804,
      "learning_rate": 1.5102464177894786e-05,
      "loss": 0.5276,
      "step": 21524
    },
    {
      "epoch": 0.6612293797806654,
      "grad_norm": 0.40123140811920166,
      "learning_rate": 1.5102048539773743e-05,
      "loss": 0.5468,
      "step": 21525
    },
    {
      "epoch": 0.6612600989156145,
      "grad_norm": 0.3632533848285675,
      "learning_rate": 1.5101632889736514e-05,
      "loss": 0.5972,
      "step": 21526
    },
    {
      "epoch": 0.6612908180505637,
      "grad_norm": 0.3901345133781433,
      "learning_rate": 1.510121722778406e-05,
      "loss": 0.5456,
      "step": 21527
    },
    {
      "epoch": 0.6613215371855129,
      "grad_norm": 0.4128034710884094,
      "learning_rate": 1.5100801553917359e-05,
      "loss": 0.5467,
      "step": 21528
    },
    {
      "epoch": 0.661352256320462,
      "grad_norm": 0.3460666537284851,
      "learning_rate": 1.5100385868137379e-05,
      "loss": 0.5532,
      "step": 21529
    },
    {
      "epoch": 0.6613829754554111,
      "grad_norm": 0.3721611797809601,
      "learning_rate": 1.5099970170445093e-05,
      "loss": 0.5464,
      "step": 21530
    },
    {
      "epoch": 0.6614136945903604,
      "grad_norm": 0.38341841101646423,
      "learning_rate": 1.509955446084147e-05,
      "loss": 0.599,
      "step": 21531
    },
    {
      "epoch": 0.6614444137253095,
      "grad_norm": 0.3615029454231262,
      "learning_rate": 1.5099138739327482e-05,
      "loss": 0.5446,
      "step": 21532
    },
    {
      "epoch": 0.6614751328602586,
      "grad_norm": 0.3712552785873413,
      "learning_rate": 1.5098723005904097e-05,
      "loss": 0.5463,
      "step": 21533
    },
    {
      "epoch": 0.6615058519952078,
      "grad_norm": 0.3422149121761322,
      "learning_rate": 1.509830726057229e-05,
      "loss": 0.5177,
      "step": 21534
    },
    {
      "epoch": 0.661536571130157,
      "grad_norm": 0.33942079544067383,
      "learning_rate": 1.5097891503333029e-05,
      "loss": 0.5657,
      "step": 21535
    },
    {
      "epoch": 0.6615672902651062,
      "grad_norm": 0.36343878507614136,
      "learning_rate": 1.5097475734187288e-05,
      "loss": 0.5677,
      "step": 21536
    },
    {
      "epoch": 0.6615980094000553,
      "grad_norm": 0.368473082780838,
      "learning_rate": 1.5097059953136036e-05,
      "loss": 0.5664,
      "step": 21537
    },
    {
      "epoch": 0.6616287285350044,
      "grad_norm": 0.3874472379684448,
      "learning_rate": 1.5096644160180245e-05,
      "loss": 0.5684,
      "step": 21538
    },
    {
      "epoch": 0.6616594476699537,
      "grad_norm": 0.4110534191131592,
      "learning_rate": 1.5096228355320883e-05,
      "loss": 0.5265,
      "step": 21539
    },
    {
      "epoch": 0.6616901668049028,
      "grad_norm": 0.35469913482666016,
      "learning_rate": 1.5095812538558926e-05,
      "loss": 0.5981,
      "step": 21540
    },
    {
      "epoch": 0.6617208859398519,
      "grad_norm": 0.3796463906764984,
      "learning_rate": 1.5095396709895342e-05,
      "loss": 0.5732,
      "step": 21541
    },
    {
      "epoch": 0.6617516050748011,
      "grad_norm": 0.38311338424682617,
      "learning_rate": 1.5094980869331104e-05,
      "loss": 0.5554,
      "step": 21542
    },
    {
      "epoch": 0.6617823242097503,
      "grad_norm": 0.3557189106941223,
      "learning_rate": 1.5094565016867183e-05,
      "loss": 0.5043,
      "step": 21543
    },
    {
      "epoch": 0.6618130433446994,
      "grad_norm": 0.352128267288208,
      "learning_rate": 1.5094149152504547e-05,
      "loss": 0.5257,
      "step": 21544
    },
    {
      "epoch": 0.6618437624796486,
      "grad_norm": 0.5612567663192749,
      "learning_rate": 1.5093733276244174e-05,
      "loss": 0.5631,
      "step": 21545
    },
    {
      "epoch": 0.6618744816145977,
      "grad_norm": 0.36795616149902344,
      "learning_rate": 1.5093317388087028e-05,
      "loss": 0.545,
      "step": 21546
    },
    {
      "epoch": 0.6619052007495468,
      "grad_norm": 0.35727813839912415,
      "learning_rate": 1.5092901488034084e-05,
      "loss": 0.5668,
      "step": 21547
    },
    {
      "epoch": 0.6619359198844961,
      "grad_norm": 0.3263242244720459,
      "learning_rate": 1.5092485576086314e-05,
      "loss": 0.4948,
      "step": 21548
    },
    {
      "epoch": 0.6619666390194452,
      "grad_norm": 0.3677486777305603,
      "learning_rate": 1.5092069652244688e-05,
      "loss": 0.4949,
      "step": 21549
    },
    {
      "epoch": 0.6619973581543944,
      "grad_norm": 0.3929874002933502,
      "learning_rate": 1.5091653716510176e-05,
      "loss": 0.5939,
      "step": 21550
    },
    {
      "epoch": 0.6620280772893435,
      "grad_norm": 0.37451937794685364,
      "learning_rate": 1.5091237768883753e-05,
      "loss": 0.5494,
      "step": 21551
    },
    {
      "epoch": 0.6620587964242927,
      "grad_norm": 0.3882429301738739,
      "learning_rate": 1.5090821809366387e-05,
      "loss": 0.6649,
      "step": 21552
    },
    {
      "epoch": 0.6620895155592419,
      "grad_norm": 0.35535311698913574,
      "learning_rate": 1.5090405837959052e-05,
      "loss": 0.5668,
      "step": 21553
    },
    {
      "epoch": 0.662120234694191,
      "grad_norm": 0.383810818195343,
      "learning_rate": 1.508998985466272e-05,
      "loss": 0.6452,
      "step": 21554
    },
    {
      "epoch": 0.6621509538291401,
      "grad_norm": 0.36246246099472046,
      "learning_rate": 1.5089573859478356e-05,
      "loss": 0.6017,
      "step": 21555
    },
    {
      "epoch": 0.6621816729640894,
      "grad_norm": 0.3712989389896393,
      "learning_rate": 1.5089157852406945e-05,
      "loss": 0.5307,
      "step": 21556
    },
    {
      "epoch": 0.6622123920990385,
      "grad_norm": 0.333763986825943,
      "learning_rate": 1.5088741833449443e-05,
      "loss": 0.5459,
      "step": 21557
    },
    {
      "epoch": 0.6622431112339876,
      "grad_norm": 0.3229312598705292,
      "learning_rate": 1.5088325802606836e-05,
      "loss": 0.5292,
      "step": 21558
    },
    {
      "epoch": 0.6622738303689368,
      "grad_norm": 0.3811585009098053,
      "learning_rate": 1.5087909759880082e-05,
      "loss": 0.5832,
      "step": 21559
    },
    {
      "epoch": 0.662304549503886,
      "grad_norm": 0.3944050371646881,
      "learning_rate": 1.5087493705270162e-05,
      "loss": 0.554,
      "step": 21560
    },
    {
      "epoch": 0.6623352686388352,
      "grad_norm": 0.33598533272743225,
      "learning_rate": 1.5087077638778044e-05,
      "loss": 0.6026,
      "step": 21561
    },
    {
      "epoch": 0.6623659877737843,
      "grad_norm": 0.37476402521133423,
      "learning_rate": 1.5086661560404705e-05,
      "loss": 0.6106,
      "step": 21562
    },
    {
      "epoch": 0.6623967069087334,
      "grad_norm": 0.35951852798461914,
      "learning_rate": 1.5086245470151114e-05,
      "loss": 0.6211,
      "step": 21563
    },
    {
      "epoch": 0.6624274260436827,
      "grad_norm": 0.357248455286026,
      "learning_rate": 1.5085829368018234e-05,
      "loss": 0.5287,
      "step": 21564
    },
    {
      "epoch": 0.6624581451786318,
      "grad_norm": 0.3782288730144501,
      "learning_rate": 1.5085413254007048e-05,
      "loss": 0.5353,
      "step": 21565
    },
    {
      "epoch": 0.6624888643135809,
      "grad_norm": 0.3370269238948822,
      "learning_rate": 1.5084997128118523e-05,
      "loss": 0.5482,
      "step": 21566
    },
    {
      "epoch": 0.6625195834485301,
      "grad_norm": 0.3584156930446625,
      "learning_rate": 1.5084580990353637e-05,
      "loss": 0.5758,
      "step": 21567
    },
    {
      "epoch": 0.6625503025834792,
      "grad_norm": 0.3736041486263275,
      "learning_rate": 1.5084164840713352e-05,
      "loss": 0.5827,
      "step": 21568
    },
    {
      "epoch": 0.6625810217184284,
      "grad_norm": 0.412290096282959,
      "learning_rate": 1.5083748679198645e-05,
      "loss": 0.617,
      "step": 21569
    },
    {
      "epoch": 0.6626117408533776,
      "grad_norm": 0.33453238010406494,
      "learning_rate": 1.5083332505810489e-05,
      "loss": 0.5543,
      "step": 21570
    },
    {
      "epoch": 0.6626424599883267,
      "grad_norm": 0.355253666639328,
      "learning_rate": 1.5082916320549856e-05,
      "loss": 0.5821,
      "step": 21571
    },
    {
      "epoch": 0.6626731791232758,
      "grad_norm": 0.3291566073894501,
      "learning_rate": 1.5082500123417713e-05,
      "loss": 0.506,
      "step": 21572
    },
    {
      "epoch": 0.6627038982582251,
      "grad_norm": 0.3212006688117981,
      "learning_rate": 1.508208391441504e-05,
      "loss": 0.5476,
      "step": 21573
    },
    {
      "epoch": 0.6627346173931742,
      "grad_norm": 0.3448812663555145,
      "learning_rate": 1.5081667693542805e-05,
      "loss": 0.5605,
      "step": 21574
    },
    {
      "epoch": 0.6627653365281234,
      "grad_norm": 0.41192397475242615,
      "learning_rate": 1.5081251460801976e-05,
      "loss": 0.576,
      "step": 21575
    },
    {
      "epoch": 0.6627960556630725,
      "grad_norm": 0.349031001329422,
      "learning_rate": 1.5080835216193534e-05,
      "loss": 0.5835,
      "step": 21576
    },
    {
      "epoch": 0.6628267747980217,
      "grad_norm": 0.42823368310928345,
      "learning_rate": 1.5080418959718444e-05,
      "loss": 0.6146,
      "step": 21577
    },
    {
      "epoch": 0.6628574939329709,
      "grad_norm": 0.36819255352020264,
      "learning_rate": 1.5080002691377682e-05,
      "loss": 0.5851,
      "step": 21578
    },
    {
      "epoch": 0.66288821306792,
      "grad_norm": 0.34732291102409363,
      "learning_rate": 1.507958641117222e-05,
      "loss": 0.5752,
      "step": 21579
    },
    {
      "epoch": 0.6629189322028691,
      "grad_norm": 0.35374489426612854,
      "learning_rate": 1.5079170119103028e-05,
      "loss": 0.5308,
      "step": 21580
    },
    {
      "epoch": 0.6629496513378184,
      "grad_norm": 0.4164109528064728,
      "learning_rate": 1.5078753815171081e-05,
      "loss": 0.551,
      "step": 21581
    },
    {
      "epoch": 0.6629803704727675,
      "grad_norm": 0.3827609717845917,
      "learning_rate": 1.5078337499377345e-05,
      "loss": 0.6196,
      "step": 21582
    },
    {
      "epoch": 0.6630110896077166,
      "grad_norm": 0.4115902781486511,
      "learning_rate": 1.5077921171722802e-05,
      "loss": 0.5881,
      "step": 21583
    },
    {
      "epoch": 0.6630418087426658,
      "grad_norm": 0.3617217242717743,
      "learning_rate": 1.5077504832208419e-05,
      "loss": 0.6296,
      "step": 21584
    },
    {
      "epoch": 0.663072527877615,
      "grad_norm": 0.37603461742401123,
      "learning_rate": 1.5077088480835165e-05,
      "loss": 0.5163,
      "step": 21585
    },
    {
      "epoch": 0.6631032470125642,
      "grad_norm": 0.6554247736930847,
      "learning_rate": 1.5076672117604019e-05,
      "loss": 0.549,
      "step": 21586
    },
    {
      "epoch": 0.6631339661475133,
      "grad_norm": 0.36480477452278137,
      "learning_rate": 1.5076255742515953e-05,
      "loss": 0.5725,
      "step": 21587
    },
    {
      "epoch": 0.6631646852824624,
      "grad_norm": 0.3351720869541168,
      "learning_rate": 1.5075839355571931e-05,
      "loss": 0.5371,
      "step": 21588
    },
    {
      "epoch": 0.6631954044174116,
      "grad_norm": 0.320401668548584,
      "learning_rate": 1.5075422956772938e-05,
      "loss": 0.5172,
      "step": 21589
    },
    {
      "epoch": 0.6632261235523608,
      "grad_norm": 0.33446434140205383,
      "learning_rate": 1.5075006546119934e-05,
      "loss": 0.5315,
      "step": 21590
    },
    {
      "epoch": 0.6632568426873099,
      "grad_norm": 0.35716623067855835,
      "learning_rate": 1.5074590123613902e-05,
      "loss": 0.5455,
      "step": 21591
    },
    {
      "epoch": 0.6632875618222591,
      "grad_norm": 0.4136248528957367,
      "learning_rate": 1.5074173689255812e-05,
      "loss": 0.5756,
      "step": 21592
    },
    {
      "epoch": 0.6633182809572082,
      "grad_norm": 0.34331175684928894,
      "learning_rate": 1.5073757243046631e-05,
      "loss": 0.5459,
      "step": 21593
    },
    {
      "epoch": 0.6633490000921574,
      "grad_norm": 0.39397427439689636,
      "learning_rate": 1.5073340784987338e-05,
      "loss": 0.5662,
      "step": 21594
    },
    {
      "epoch": 0.6633797192271066,
      "grad_norm": 0.3501124382019043,
      "learning_rate": 1.50729243150789e-05,
      "loss": 0.4766,
      "step": 21595
    },
    {
      "epoch": 0.6634104383620557,
      "grad_norm": 0.5666484832763672,
      "learning_rate": 1.5072507833322299e-05,
      "loss": 0.5312,
      "step": 21596
    },
    {
      "epoch": 0.6634411574970048,
      "grad_norm": 0.3735029697418213,
      "learning_rate": 1.5072091339718497e-05,
      "loss": 0.6209,
      "step": 21597
    },
    {
      "epoch": 0.6634718766319541,
      "grad_norm": 0.3322620689868927,
      "learning_rate": 1.5071674834268475e-05,
      "loss": 0.5336,
      "step": 21598
    },
    {
      "epoch": 0.6635025957669032,
      "grad_norm": 0.3423052132129669,
      "learning_rate": 1.50712583169732e-05,
      "loss": 0.5875,
      "step": 21599
    },
    {
      "epoch": 0.6635333149018524,
      "grad_norm": 0.3563271164894104,
      "learning_rate": 1.5070841787833645e-05,
      "loss": 0.5209,
      "step": 21600
    },
    {
      "epoch": 0.6635640340368015,
      "grad_norm": 0.33694881200790405,
      "learning_rate": 1.5070425246850789e-05,
      "loss": 0.5113,
      "step": 21601
    },
    {
      "epoch": 0.6635947531717507,
      "grad_norm": 0.33374300599098206,
      "learning_rate": 1.5070008694025595e-05,
      "loss": 0.5505,
      "step": 21602
    },
    {
      "epoch": 0.6636254723066999,
      "grad_norm": 0.3436729311943054,
      "learning_rate": 1.5069592129359048e-05,
      "loss": 0.533,
      "step": 21603
    },
    {
      "epoch": 0.663656191441649,
      "grad_norm": 0.36643296480178833,
      "learning_rate": 1.5069175552852109e-05,
      "loss": 0.6328,
      "step": 21604
    },
    {
      "epoch": 0.6636869105765981,
      "grad_norm": 0.35808756947517395,
      "learning_rate": 1.506875896450576e-05,
      "loss": 0.5481,
      "step": 21605
    },
    {
      "epoch": 0.6637176297115474,
      "grad_norm": 0.3508319854736328,
      "learning_rate": 1.506834236432097e-05,
      "loss": 0.5693,
      "step": 21606
    },
    {
      "epoch": 0.6637483488464965,
      "grad_norm": 0.3835712671279907,
      "learning_rate": 1.5067925752298713e-05,
      "loss": 0.5093,
      "step": 21607
    },
    {
      "epoch": 0.6637790679814456,
      "grad_norm": 0.3622341752052307,
      "learning_rate": 1.5067509128439962e-05,
      "loss": 0.6029,
      "step": 21608
    },
    {
      "epoch": 0.6638097871163948,
      "grad_norm": 0.34362319111824036,
      "learning_rate": 1.5067092492745686e-05,
      "loss": 0.545,
      "step": 21609
    },
    {
      "epoch": 0.6638405062513439,
      "grad_norm": 0.3492479622364044,
      "learning_rate": 1.5066675845216862e-05,
      "loss": 0.541,
      "step": 21610
    },
    {
      "epoch": 0.6638712253862932,
      "grad_norm": 0.337037056684494,
      "learning_rate": 1.5066259185854465e-05,
      "loss": 0.5497,
      "step": 21611
    },
    {
      "epoch": 0.6639019445212423,
      "grad_norm": 0.4026355743408203,
      "learning_rate": 1.5065842514659466e-05,
      "loss": 0.5216,
      "step": 21612
    },
    {
      "epoch": 0.6639326636561914,
      "grad_norm": 0.36301618814468384,
      "learning_rate": 1.5065425831632836e-05,
      "loss": 0.5869,
      "step": 21613
    },
    {
      "epoch": 0.6639633827911406,
      "grad_norm": 0.34598711133003235,
      "learning_rate": 1.5065009136775552e-05,
      "loss": 0.5923,
      "step": 21614
    },
    {
      "epoch": 0.6639941019260898,
      "grad_norm": 0.3762885630130768,
      "learning_rate": 1.5064592430088585e-05,
      "loss": 0.6073,
      "step": 21615
    },
    {
      "epoch": 0.6640248210610389,
      "grad_norm": 0.38768115639686584,
      "learning_rate": 1.5064175711572908e-05,
      "loss": 0.545,
      "step": 21616
    },
    {
      "epoch": 0.6640555401959881,
      "grad_norm": 0.3569813370704651,
      "learning_rate": 1.5063758981229497e-05,
      "loss": 0.4813,
      "step": 21617
    },
    {
      "epoch": 0.6640862593309372,
      "grad_norm": 0.40241539478302,
      "learning_rate": 1.506334223905932e-05,
      "loss": 0.6126,
      "step": 21618
    },
    {
      "epoch": 0.6641169784658864,
      "grad_norm": 0.3639895021915436,
      "learning_rate": 1.5062925485063357e-05,
      "loss": 0.5452,
      "step": 21619
    },
    {
      "epoch": 0.6641476976008356,
      "grad_norm": 0.3397344946861267,
      "learning_rate": 1.5062508719242574e-05,
      "loss": 0.5878,
      "step": 21620
    },
    {
      "epoch": 0.6641784167357847,
      "grad_norm": 0.4240603744983673,
      "learning_rate": 1.5062091941597952e-05,
      "loss": 0.5348,
      "step": 21621
    },
    {
      "epoch": 0.6642091358707339,
      "grad_norm": 0.3661581575870514,
      "learning_rate": 1.5061675152130456e-05,
      "loss": 0.6315,
      "step": 21622
    },
    {
      "epoch": 0.664239855005683,
      "grad_norm": 0.3687221109867096,
      "learning_rate": 1.5061258350841073e-05,
      "loss": 0.5309,
      "step": 21623
    },
    {
      "epoch": 0.6642705741406322,
      "grad_norm": 0.3438507914543152,
      "learning_rate": 1.5060841537730759e-05,
      "loss": 0.5149,
      "step": 21624
    },
    {
      "epoch": 0.6643012932755814,
      "grad_norm": 0.39039236307144165,
      "learning_rate": 1.5060424712800502e-05,
      "loss": 0.4969,
      "step": 21625
    },
    {
      "epoch": 0.6643320124105305,
      "grad_norm": 0.34760305285453796,
      "learning_rate": 1.5060007876051265e-05,
      "loss": 0.5042,
      "step": 21626
    },
    {
      "epoch": 0.6643627315454796,
      "grad_norm": 0.3589724004268646,
      "learning_rate": 1.5059591027484026e-05,
      "loss": 0.5096,
      "step": 21627
    },
    {
      "epoch": 0.6643934506804289,
      "grad_norm": 0.36252009868621826,
      "learning_rate": 1.5059174167099762e-05,
      "loss": 0.6162,
      "step": 21628
    },
    {
      "epoch": 0.664424169815378,
      "grad_norm": 0.4116900563240051,
      "learning_rate": 1.5058757294899441e-05,
      "loss": 0.5358,
      "step": 21629
    },
    {
      "epoch": 0.6644548889503271,
      "grad_norm": 0.4957659840583801,
      "learning_rate": 1.505834041088404e-05,
      "loss": 0.5205,
      "step": 21630
    },
    {
      "epoch": 0.6644856080852763,
      "grad_norm": 0.3651176989078522,
      "learning_rate": 1.5057923515054533e-05,
      "loss": 0.5058,
      "step": 21631
    },
    {
      "epoch": 0.6645163272202255,
      "grad_norm": 0.4462648630142212,
      "learning_rate": 1.5057506607411893e-05,
      "loss": 0.5434,
      "step": 21632
    },
    {
      "epoch": 0.6645470463551746,
      "grad_norm": 0.31999707221984863,
      "learning_rate": 1.5057089687957092e-05,
      "loss": 0.5257,
      "step": 21633
    },
    {
      "epoch": 0.6645777654901238,
      "grad_norm": 0.3676610291004181,
      "learning_rate": 1.5056672756691103e-05,
      "loss": 0.5752,
      "step": 21634
    },
    {
      "epoch": 0.6646084846250729,
      "grad_norm": 0.6018003225326538,
      "learning_rate": 1.5056255813614904e-05,
      "loss": 0.6288,
      "step": 21635
    },
    {
      "epoch": 0.6646392037600222,
      "grad_norm": 0.4123040437698364,
      "learning_rate": 1.5055838858729464e-05,
      "loss": 0.5427,
      "step": 21636
    },
    {
      "epoch": 0.6646699228949713,
      "grad_norm": 0.3513493537902832,
      "learning_rate": 1.5055421892035763e-05,
      "loss": 0.4983,
      "step": 21637
    },
    {
      "epoch": 0.6647006420299204,
      "grad_norm": 0.5258155465126038,
      "learning_rate": 1.5055004913534768e-05,
      "loss": 0.4856,
      "step": 21638
    },
    {
      "epoch": 0.6647313611648696,
      "grad_norm": 0.679106593132019,
      "learning_rate": 1.5054587923227456e-05,
      "loss": 0.5823,
      "step": 21639
    },
    {
      "epoch": 0.6647620802998188,
      "grad_norm": 0.38326624035835266,
      "learning_rate": 1.5054170921114801e-05,
      "loss": 0.5694,
      "step": 21640
    },
    {
      "epoch": 0.6647927994347679,
      "grad_norm": 0.3624212443828583,
      "learning_rate": 1.5053753907197778e-05,
      "loss": 0.5434,
      "step": 21641
    },
    {
      "epoch": 0.6648235185697171,
      "grad_norm": 0.38261833786964417,
      "learning_rate": 1.5053336881477361e-05,
      "loss": 0.533,
      "step": 21642
    },
    {
      "epoch": 0.6648542377046662,
      "grad_norm": 0.3750227391719818,
      "learning_rate": 1.5052919843954521e-05,
      "loss": 0.6285,
      "step": 21643
    },
    {
      "epoch": 0.6648849568396153,
      "grad_norm": 0.3817739486694336,
      "learning_rate": 1.5052502794630233e-05,
      "loss": 0.6018,
      "step": 21644
    },
    {
      "epoch": 0.6649156759745646,
      "grad_norm": 0.33327579498291016,
      "learning_rate": 1.5052085733505472e-05,
      "loss": 0.4935,
      "step": 21645
    },
    {
      "epoch": 0.6649463951095137,
      "grad_norm": 0.37058955430984497,
      "learning_rate": 1.5051668660581213e-05,
      "loss": 0.5271,
      "step": 21646
    },
    {
      "epoch": 0.6649771142444629,
      "grad_norm": 0.35666996240615845,
      "learning_rate": 1.5051251575858428e-05,
      "loss": 0.6061,
      "step": 21647
    },
    {
      "epoch": 0.665007833379412,
      "grad_norm": 0.3766808807849884,
      "learning_rate": 1.5050834479338093e-05,
      "loss": 0.581,
      "step": 21648
    },
    {
      "epoch": 0.6650385525143612,
      "grad_norm": 0.33393359184265137,
      "learning_rate": 1.5050417371021184e-05,
      "loss": 0.5227,
      "step": 21649
    },
    {
      "epoch": 0.6650692716493104,
      "grad_norm": 0.3431656062602997,
      "learning_rate": 1.5050000250908667e-05,
      "loss": 0.5618,
      "step": 21650
    },
    {
      "epoch": 0.6650999907842595,
      "grad_norm": 0.3742406368255615,
      "learning_rate": 1.5049583119001528e-05,
      "loss": 0.5448,
      "step": 21651
    },
    {
      "epoch": 0.6651307099192086,
      "grad_norm": 0.3461693227291107,
      "learning_rate": 1.5049165975300728e-05,
      "loss": 0.5487,
      "step": 21652
    },
    {
      "epoch": 0.6651614290541579,
      "grad_norm": 0.41576817631721497,
      "learning_rate": 1.5048748819807253e-05,
      "loss": 0.5659,
      "step": 21653
    },
    {
      "epoch": 0.665192148189107,
      "grad_norm": 0.3280407786369324,
      "learning_rate": 1.5048331652522071e-05,
      "loss": 0.5495,
      "step": 21654
    },
    {
      "epoch": 0.6652228673240561,
      "grad_norm": 0.33416685461997986,
      "learning_rate": 1.5047914473446157e-05,
      "loss": 0.5906,
      "step": 21655
    },
    {
      "epoch": 0.6652535864590053,
      "grad_norm": 0.3554842472076416,
      "learning_rate": 1.5047497282580487e-05,
      "loss": 0.6461,
      "step": 21656
    },
    {
      "epoch": 0.6652843055939545,
      "grad_norm": 0.34325146675109863,
      "learning_rate": 1.5047080079926035e-05,
      "loss": 0.4978,
      "step": 21657
    },
    {
      "epoch": 0.6653150247289036,
      "grad_norm": 0.4154335856437683,
      "learning_rate": 1.5046662865483775e-05,
      "loss": 0.5873,
      "step": 21658
    },
    {
      "epoch": 0.6653457438638528,
      "grad_norm": 0.35909712314605713,
      "learning_rate": 1.5046245639254684e-05,
      "loss": 0.5293,
      "step": 21659
    },
    {
      "epoch": 0.6653764629988019,
      "grad_norm": 0.409972220659256,
      "learning_rate": 1.504582840123973e-05,
      "loss": 0.6084,
      "step": 21660
    },
    {
      "epoch": 0.6654071821337512,
      "grad_norm": 0.36478105187416077,
      "learning_rate": 1.5045411151439892e-05,
      "loss": 0.5628,
      "step": 21661
    },
    {
      "epoch": 0.6654379012687003,
      "grad_norm": 0.3946358263492584,
      "learning_rate": 1.5044993889856145e-05,
      "loss": 0.7012,
      "step": 21662
    },
    {
      "epoch": 0.6654686204036494,
      "grad_norm": 0.3686845302581787,
      "learning_rate": 1.5044576616489462e-05,
      "loss": 0.5984,
      "step": 21663
    },
    {
      "epoch": 0.6654993395385986,
      "grad_norm": 0.3810825049877167,
      "learning_rate": 1.5044159331340815e-05,
      "loss": 0.6059,
      "step": 21664
    },
    {
      "epoch": 0.6655300586735478,
      "grad_norm": 0.35699236392974854,
      "learning_rate": 1.5043742034411186e-05,
      "loss": 0.509,
      "step": 21665
    },
    {
      "epoch": 0.6655607778084969,
      "grad_norm": 0.3459860682487488,
      "learning_rate": 1.5043324725701545e-05,
      "loss": 0.5643,
      "step": 21666
    },
    {
      "epoch": 0.6655914969434461,
      "grad_norm": 0.34433501958847046,
      "learning_rate": 1.5042907405212866e-05,
      "loss": 0.5793,
      "step": 21667
    },
    {
      "epoch": 0.6656222160783952,
      "grad_norm": 0.3607727885246277,
      "learning_rate": 1.5042490072946123e-05,
      "loss": 0.5596,
      "step": 21668
    },
    {
      "epoch": 0.6656529352133443,
      "grad_norm": 0.3364073634147644,
      "learning_rate": 1.5042072728902293e-05,
      "loss": 0.5173,
      "step": 21669
    },
    {
      "epoch": 0.6656836543482936,
      "grad_norm": 0.3266844153404236,
      "learning_rate": 1.5041655373082349e-05,
      "loss": 0.5471,
      "step": 21670
    },
    {
      "epoch": 0.6657143734832427,
      "grad_norm": 0.37523025274276733,
      "learning_rate": 1.5041238005487269e-05,
      "loss": 0.6243,
      "step": 21671
    },
    {
      "epoch": 0.6657450926181919,
      "grad_norm": 0.33527135848999023,
      "learning_rate": 1.5040820626118025e-05,
      "loss": 0.5947,
      "step": 21672
    },
    {
      "epoch": 0.665775811753141,
      "grad_norm": 0.3366093337535858,
      "learning_rate": 1.5040403234975594e-05,
      "loss": 0.5776,
      "step": 21673
    },
    {
      "epoch": 0.6658065308880902,
      "grad_norm": 0.33059191703796387,
      "learning_rate": 1.5039985832060946e-05,
      "loss": 0.4785,
      "step": 21674
    },
    {
      "epoch": 0.6658372500230394,
      "grad_norm": 0.39183685183525085,
      "learning_rate": 1.5039568417375061e-05,
      "loss": 0.5937,
      "step": 21675
    },
    {
      "epoch": 0.6658679691579885,
      "grad_norm": 0.4475761651992798,
      "learning_rate": 1.503915099091891e-05,
      "loss": 0.5392,
      "step": 21676
    },
    {
      "epoch": 0.6658986882929376,
      "grad_norm": 0.42780929803848267,
      "learning_rate": 1.5038733552693475e-05,
      "loss": 0.6717,
      "step": 21677
    },
    {
      "epoch": 0.6659294074278869,
      "grad_norm": 0.3453823924064636,
      "learning_rate": 1.503831610269972e-05,
      "loss": 0.6271,
      "step": 21678
    },
    {
      "epoch": 0.665960126562836,
      "grad_norm": 0.45835667848587036,
      "learning_rate": 1.5037898640938628e-05,
      "loss": 0.6258,
      "step": 21679
    },
    {
      "epoch": 0.6659908456977851,
      "grad_norm": 0.37534379959106445,
      "learning_rate": 1.5037481167411172e-05,
      "loss": 0.6343,
      "step": 21680
    },
    {
      "epoch": 0.6660215648327343,
      "grad_norm": 0.34359586238861084,
      "learning_rate": 1.5037063682118327e-05,
      "loss": 0.5571,
      "step": 21681
    },
    {
      "epoch": 0.6660522839676835,
      "grad_norm": 0.34556257724761963,
      "learning_rate": 1.5036646185061066e-05,
      "loss": 0.501,
      "step": 21682
    },
    {
      "epoch": 0.6660830031026326,
      "grad_norm": 0.33729276061058044,
      "learning_rate": 1.5036228676240368e-05,
      "loss": 0.5216,
      "step": 21683
    },
    {
      "epoch": 0.6661137222375818,
      "grad_norm": 0.32963991165161133,
      "learning_rate": 1.5035811155657208e-05,
      "loss": 0.4839,
      "step": 21684
    },
    {
      "epoch": 0.6661444413725309,
      "grad_norm": 0.38368701934814453,
      "learning_rate": 1.5035393623312558e-05,
      "loss": 0.6033,
      "step": 21685
    },
    {
      "epoch": 0.6661751605074802,
      "grad_norm": 0.40855297446250916,
      "learning_rate": 1.5034976079207393e-05,
      "loss": 0.6373,
      "step": 21686
    },
    {
      "epoch": 0.6662058796424293,
      "grad_norm": 0.37873756885528564,
      "learning_rate": 1.5034558523342693e-05,
      "loss": 0.5647,
      "step": 21687
    },
    {
      "epoch": 0.6662365987773784,
      "grad_norm": 0.3444276750087738,
      "learning_rate": 1.5034140955719426e-05,
      "loss": 0.4988,
      "step": 21688
    },
    {
      "epoch": 0.6662673179123276,
      "grad_norm": 0.3572183847427368,
      "learning_rate": 1.5033723376338574e-05,
      "loss": 0.5558,
      "step": 21689
    },
    {
      "epoch": 0.6662980370472767,
      "grad_norm": 0.36273282766342163,
      "learning_rate": 1.5033305785201107e-05,
      "loss": 0.488,
      "step": 21690
    },
    {
      "epoch": 0.6663287561822259,
      "grad_norm": 0.3687743842601776,
      "learning_rate": 1.5032888182308006e-05,
      "loss": 0.5985,
      "step": 21691
    },
    {
      "epoch": 0.6663594753171751,
      "grad_norm": 0.38204535841941833,
      "learning_rate": 1.503247056766024e-05,
      "loss": 0.546,
      "step": 21692
    },
    {
      "epoch": 0.6663901944521242,
      "grad_norm": 0.3436932861804962,
      "learning_rate": 1.5032052941258788e-05,
      "loss": 0.5472,
      "step": 21693
    },
    {
      "epoch": 0.6664209135870733,
      "grad_norm": 0.5076892375946045,
      "learning_rate": 1.5031635303104626e-05,
      "loss": 0.5907,
      "step": 21694
    },
    {
      "epoch": 0.6664516327220226,
      "grad_norm": 0.5274530053138733,
      "learning_rate": 1.5031217653198731e-05,
      "loss": 0.5656,
      "step": 21695
    },
    {
      "epoch": 0.6664823518569717,
      "grad_norm": 0.40041810274124146,
      "learning_rate": 1.5030799991542071e-05,
      "loss": 0.5624,
      "step": 21696
    },
    {
      "epoch": 0.6665130709919209,
      "grad_norm": 0.4410339295864105,
      "learning_rate": 1.5030382318135627e-05,
      "loss": 0.5284,
      "step": 21697
    },
    {
      "epoch": 0.66654379012687,
      "grad_norm": 0.33938995003700256,
      "learning_rate": 1.5029964632980378e-05,
      "loss": 0.5628,
      "step": 21698
    },
    {
      "epoch": 0.6665745092618192,
      "grad_norm": 0.33439287543296814,
      "learning_rate": 1.502954693607729e-05,
      "loss": 0.5518,
      "step": 21699
    },
    {
      "epoch": 0.6666052283967684,
      "grad_norm": 0.34746503829956055,
      "learning_rate": 1.5029129227427346e-05,
      "loss": 0.5578,
      "step": 21700
    },
    {
      "epoch": 0.6666359475317175,
      "grad_norm": 0.3382933437824249,
      "learning_rate": 1.502871150703152e-05,
      "loss": 0.4721,
      "step": 21701
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3578824996948242,
      "learning_rate": 1.5028293774890788e-05,
      "loss": 0.5597,
      "step": 21702
    },
    {
      "epoch": 0.6666973858016159,
      "grad_norm": 0.4088318943977356,
      "learning_rate": 1.5027876031006124e-05,
      "loss": 0.5942,
      "step": 21703
    },
    {
      "epoch": 0.666728104936565,
      "grad_norm": 0.37355363368988037,
      "learning_rate": 1.5027458275378504e-05,
      "loss": 0.586,
      "step": 21704
    },
    {
      "epoch": 0.6667588240715141,
      "grad_norm": 0.3585800230503082,
      "learning_rate": 1.5027040508008903e-05,
      "loss": 0.5087,
      "step": 21705
    },
    {
      "epoch": 0.6667895432064633,
      "grad_norm": 0.33573850989341736,
      "learning_rate": 1.5026622728898298e-05,
      "loss": 0.4794,
      "step": 21706
    },
    {
      "epoch": 0.6668202623414125,
      "grad_norm": 0.3794483244419098,
      "learning_rate": 1.5026204938047669e-05,
      "loss": 0.5396,
      "step": 21707
    },
    {
      "epoch": 0.6668509814763616,
      "grad_norm": 0.4079286754131317,
      "learning_rate": 1.502578713545798e-05,
      "loss": 0.6279,
      "step": 21708
    },
    {
      "epoch": 0.6668817006113108,
      "grad_norm": 0.4086962044239044,
      "learning_rate": 1.5025369321130221e-05,
      "loss": 0.5956,
      "step": 21709
    },
    {
      "epoch": 0.6669124197462599,
      "grad_norm": 0.369299978017807,
      "learning_rate": 1.5024951495065354e-05,
      "loss": 0.5852,
      "step": 21710
    },
    {
      "epoch": 0.6669431388812092,
      "grad_norm": 0.33618709444999695,
      "learning_rate": 1.5024533657264369e-05,
      "loss": 0.5621,
      "step": 21711
    },
    {
      "epoch": 0.6669738580161583,
      "grad_norm": 0.3600922226905823,
      "learning_rate": 1.5024115807728232e-05,
      "loss": 0.5149,
      "step": 21712
    },
    {
      "epoch": 0.6670045771511074,
      "grad_norm": 0.3525899052619934,
      "learning_rate": 1.5023697946457919e-05,
      "loss": 0.4314,
      "step": 21713
    },
    {
      "epoch": 0.6670352962860566,
      "grad_norm": 0.370338499546051,
      "learning_rate": 1.5023280073454412e-05,
      "loss": 0.5703,
      "step": 21714
    },
    {
      "epoch": 0.6670660154210057,
      "grad_norm": 0.33940330147743225,
      "learning_rate": 1.502286218871868e-05,
      "loss": 0.4854,
      "step": 21715
    },
    {
      "epoch": 0.6670967345559549,
      "grad_norm": 0.3449198603630066,
      "learning_rate": 1.5022444292251707e-05,
      "loss": 0.5629,
      "step": 21716
    },
    {
      "epoch": 0.6671274536909041,
      "grad_norm": 0.34013885259628296,
      "learning_rate": 1.502202638405446e-05,
      "loss": 0.5578,
      "step": 21717
    },
    {
      "epoch": 0.6671581728258532,
      "grad_norm": 0.3264106214046478,
      "learning_rate": 1.5021608464127923e-05,
      "loss": 0.531,
      "step": 21718
    },
    {
      "epoch": 0.6671888919608023,
      "grad_norm": 0.4003428816795349,
      "learning_rate": 1.5021190532473068e-05,
      "loss": 0.5657,
      "step": 21719
    },
    {
      "epoch": 0.6672196110957516,
      "grad_norm": 0.38584426045417786,
      "learning_rate": 1.5020772589090871e-05,
      "loss": 0.5488,
      "step": 21720
    },
    {
      "epoch": 0.6672503302307007,
      "grad_norm": 0.37046703696250916,
      "learning_rate": 1.502035463398231e-05,
      "loss": 0.5607,
      "step": 21721
    },
    {
      "epoch": 0.6672810493656499,
      "grad_norm": 0.3687343895435333,
      "learning_rate": 1.501993666714836e-05,
      "loss": 0.5513,
      "step": 21722
    },
    {
      "epoch": 0.667311768500599,
      "grad_norm": 0.36429670453071594,
      "learning_rate": 1.5019518688589997e-05,
      "loss": 0.6065,
      "step": 21723
    },
    {
      "epoch": 0.6673424876355482,
      "grad_norm": 0.3768196403980255,
      "learning_rate": 1.5019100698308195e-05,
      "loss": 0.6075,
      "step": 21724
    },
    {
      "epoch": 0.6673732067704974,
      "grad_norm": 0.3622683882713318,
      "learning_rate": 1.5018682696303937e-05,
      "loss": 0.5044,
      "step": 21725
    },
    {
      "epoch": 0.6674039259054465,
      "grad_norm": 0.34609630703926086,
      "learning_rate": 1.5018264682578193e-05,
      "loss": 0.5593,
      "step": 21726
    },
    {
      "epoch": 0.6674346450403956,
      "grad_norm": 0.35423561930656433,
      "learning_rate": 1.5017846657131943e-05,
      "loss": 0.5165,
      "step": 21727
    },
    {
      "epoch": 0.6674653641753449,
      "grad_norm": 0.33571431040763855,
      "learning_rate": 1.5017428619966162e-05,
      "loss": 0.546,
      "step": 21728
    },
    {
      "epoch": 0.667496083310294,
      "grad_norm": 0.363196462392807,
      "learning_rate": 1.5017010571081825e-05,
      "loss": 0.5924,
      "step": 21729
    },
    {
      "epoch": 0.6675268024452431,
      "grad_norm": 0.3292766213417053,
      "learning_rate": 1.5016592510479907e-05,
      "loss": 0.5594,
      "step": 21730
    },
    {
      "epoch": 0.6675575215801923,
      "grad_norm": 0.3669489324092865,
      "learning_rate": 1.5016174438161391e-05,
      "loss": 0.5542,
      "step": 21731
    },
    {
      "epoch": 0.6675882407151414,
      "grad_norm": 0.3560146689414978,
      "learning_rate": 1.5015756354127247e-05,
      "loss": 0.521,
      "step": 21732
    },
    {
      "epoch": 0.6676189598500907,
      "grad_norm": 0.3333108425140381,
      "learning_rate": 1.5015338258378451e-05,
      "loss": 0.4795,
      "step": 21733
    },
    {
      "epoch": 0.6676496789850398,
      "grad_norm": 0.5607941746711731,
      "learning_rate": 1.5014920150915986e-05,
      "loss": 0.5856,
      "step": 21734
    },
    {
      "epoch": 0.6676803981199889,
      "grad_norm": 0.34721919894218445,
      "learning_rate": 1.5014502031740824e-05,
      "loss": 0.5259,
      "step": 21735
    },
    {
      "epoch": 0.6677111172549381,
      "grad_norm": 0.3745097219944,
      "learning_rate": 1.5014083900853943e-05,
      "loss": 0.5869,
      "step": 21736
    },
    {
      "epoch": 0.6677418363898873,
      "grad_norm": 0.3787437677383423,
      "learning_rate": 1.5013665758256318e-05,
      "loss": 0.6489,
      "step": 21737
    },
    {
      "epoch": 0.6677725555248364,
      "grad_norm": 0.35840171575546265,
      "learning_rate": 1.5013247603948924e-05,
      "loss": 0.537,
      "step": 21738
    },
    {
      "epoch": 0.6678032746597856,
      "grad_norm": 0.3575096130371094,
      "learning_rate": 1.5012829437932743e-05,
      "loss": 0.5817,
      "step": 21739
    },
    {
      "epoch": 0.6678339937947347,
      "grad_norm": 0.37597915530204773,
      "learning_rate": 1.5012411260208747e-05,
      "loss": 0.5285,
      "step": 21740
    },
    {
      "epoch": 0.6678647129296839,
      "grad_norm": 0.367623895406723,
      "learning_rate": 1.5011993070777918e-05,
      "loss": 0.4941,
      "step": 21741
    },
    {
      "epoch": 0.6678954320646331,
      "grad_norm": 0.35672321915626526,
      "learning_rate": 1.5011574869641225e-05,
      "loss": 0.6337,
      "step": 21742
    },
    {
      "epoch": 0.6679261511995822,
      "grad_norm": 0.3565579652786255,
      "learning_rate": 1.5011156656799653e-05,
      "loss": 0.5415,
      "step": 21743
    },
    {
      "epoch": 0.6679568703345313,
      "grad_norm": 0.33502480387687683,
      "learning_rate": 1.501073843225417e-05,
      "loss": 0.4422,
      "step": 21744
    },
    {
      "epoch": 0.6679875894694806,
      "grad_norm": 0.5020123720169067,
      "learning_rate": 1.501032019600576e-05,
      "loss": 0.6403,
      "step": 21745
    },
    {
      "epoch": 0.6680183086044297,
      "grad_norm": 0.33876320719718933,
      "learning_rate": 1.5009901948055397e-05,
      "loss": 0.5043,
      "step": 21746
    },
    {
      "epoch": 0.6680490277393789,
      "grad_norm": 0.5350170135498047,
      "learning_rate": 1.500948368840406e-05,
      "loss": 0.5482,
      "step": 21747
    },
    {
      "epoch": 0.668079746874328,
      "grad_norm": 0.389327734708786,
      "learning_rate": 1.5009065417052724e-05,
      "loss": 0.5366,
      "step": 21748
    },
    {
      "epoch": 0.6681104660092771,
      "grad_norm": 0.36329859495162964,
      "learning_rate": 1.5008647134002363e-05,
      "loss": 0.6022,
      "step": 21749
    },
    {
      "epoch": 0.6681411851442264,
      "grad_norm": 0.41659992933273315,
      "learning_rate": 1.5008228839253957e-05,
      "loss": 0.5494,
      "step": 21750
    },
    {
      "epoch": 0.6681719042791755,
      "grad_norm": 0.3734131455421448,
      "learning_rate": 1.5007810532808482e-05,
      "loss": 0.5063,
      "step": 21751
    },
    {
      "epoch": 0.6682026234141246,
      "grad_norm": 0.34192565083503723,
      "learning_rate": 1.500739221466692e-05,
      "loss": 0.6118,
      "step": 21752
    },
    {
      "epoch": 0.6682333425490738,
      "grad_norm": 0.341243177652359,
      "learning_rate": 1.500697388483024e-05,
      "loss": 0.5535,
      "step": 21753
    },
    {
      "epoch": 0.668264061684023,
      "grad_norm": 0.35031405091285706,
      "learning_rate": 1.5006555543299426e-05,
      "loss": 0.5992,
      "step": 21754
    },
    {
      "epoch": 0.6682947808189721,
      "grad_norm": 0.3425159156322479,
      "learning_rate": 1.5006137190075447e-05,
      "loss": 0.56,
      "step": 21755
    },
    {
      "epoch": 0.6683254999539213,
      "grad_norm": 0.41344985365867615,
      "learning_rate": 1.5005718825159287e-05,
      "loss": 0.6072,
      "step": 21756
    },
    {
      "epoch": 0.6683562190888704,
      "grad_norm": 0.6898861527442932,
      "learning_rate": 1.5005300448551925e-05,
      "loss": 0.641,
      "step": 21757
    },
    {
      "epoch": 0.6683869382238197,
      "grad_norm": 0.4472046196460724,
      "learning_rate": 1.500488206025433e-05,
      "loss": 0.5943,
      "step": 21758
    },
    {
      "epoch": 0.6684176573587688,
      "grad_norm": 0.36931687593460083,
      "learning_rate": 1.5004463660267485e-05,
      "loss": 0.577,
      "step": 21759
    },
    {
      "epoch": 0.6684483764937179,
      "grad_norm": 0.3610285520553589,
      "learning_rate": 1.5004045248592363e-05,
      "loss": 0.52,
      "step": 21760
    },
    {
      "epoch": 0.6684790956286671,
      "grad_norm": 0.36286208033561707,
      "learning_rate": 1.5003626825229947e-05,
      "loss": 0.5752,
      "step": 21761
    },
    {
      "epoch": 0.6685098147636163,
      "grad_norm": 0.3811629116535187,
      "learning_rate": 1.5003208390181212e-05,
      "loss": 0.5677,
      "step": 21762
    },
    {
      "epoch": 0.6685405338985654,
      "grad_norm": 0.35765811800956726,
      "learning_rate": 1.5002789943447131e-05,
      "loss": 0.4894,
      "step": 21763
    },
    {
      "epoch": 0.6685712530335146,
      "grad_norm": 0.364870548248291,
      "learning_rate": 1.5002371485028689e-05,
      "loss": 0.5523,
      "step": 21764
    },
    {
      "epoch": 0.6686019721684637,
      "grad_norm": 0.36567142605781555,
      "learning_rate": 1.5001953014926853e-05,
      "loss": 0.5942,
      "step": 21765
    },
    {
      "epoch": 0.6686326913034129,
      "grad_norm": 0.3593689203262329,
      "learning_rate": 1.5001534533142612e-05,
      "loss": 0.579,
      "step": 21766
    },
    {
      "epoch": 0.6686634104383621,
      "grad_norm": 0.3108760118484497,
      "learning_rate": 1.5001116039676936e-05,
      "loss": 0.506,
      "step": 21767
    },
    {
      "epoch": 0.6686941295733112,
      "grad_norm": 0.3535699248313904,
      "learning_rate": 1.5000697534530804e-05,
      "loss": 0.5828,
      "step": 21768
    },
    {
      "epoch": 0.6687248487082603,
      "grad_norm": 0.34123626351356506,
      "learning_rate": 1.5000279017705191e-05,
      "loss": 0.61,
      "step": 21769
    },
    {
      "epoch": 0.6687555678432096,
      "grad_norm": 0.35584235191345215,
      "learning_rate": 1.499986048920108e-05,
      "loss": 0.5795,
      "step": 21770
    },
    {
      "epoch": 0.6687862869781587,
      "grad_norm": 0.4122330844402313,
      "learning_rate": 1.4999441949019446e-05,
      "loss": 0.6153,
      "step": 21771
    },
    {
      "epoch": 0.6688170061131079,
      "grad_norm": 0.3653135299682617,
      "learning_rate": 1.4999023397161265e-05,
      "loss": 0.6013,
      "step": 21772
    },
    {
      "epoch": 0.668847725248057,
      "grad_norm": 0.41242989897727966,
      "learning_rate": 1.4998604833627517e-05,
      "loss": 0.5865,
      "step": 21773
    },
    {
      "epoch": 0.6688784443830061,
      "grad_norm": 0.394336074590683,
      "learning_rate": 1.4998186258419174e-05,
      "loss": 0.5328,
      "step": 21774
    },
    {
      "epoch": 0.6689091635179554,
      "grad_norm": 0.3939213752746582,
      "learning_rate": 1.4997767671537223e-05,
      "loss": 0.5484,
      "step": 21775
    },
    {
      "epoch": 0.6689398826529045,
      "grad_norm": 0.46171364188194275,
      "learning_rate": 1.4997349072982634e-05,
      "loss": 0.5277,
      "step": 21776
    },
    {
      "epoch": 0.6689706017878536,
      "grad_norm": 0.4208122491836548,
      "learning_rate": 1.4996930462756389e-05,
      "loss": 0.5446,
      "step": 21777
    },
    {
      "epoch": 0.6690013209228028,
      "grad_norm": 0.38486745953559875,
      "learning_rate": 1.4996511840859462e-05,
      "loss": 0.5771,
      "step": 21778
    },
    {
      "epoch": 0.669032040057752,
      "grad_norm": 0.35256117582321167,
      "learning_rate": 1.4996093207292834e-05,
      "loss": 0.4941,
      "step": 21779
    },
    {
      "epoch": 0.6690627591927011,
      "grad_norm": 0.39707016944885254,
      "learning_rate": 1.499567456205748e-05,
      "loss": 0.5577,
      "step": 21780
    },
    {
      "epoch": 0.6690934783276503,
      "grad_norm": 0.38282251358032227,
      "learning_rate": 1.4995255905154382e-05,
      "loss": 0.7034,
      "step": 21781
    },
    {
      "epoch": 0.6691241974625994,
      "grad_norm": 0.33049169182777405,
      "learning_rate": 1.4994837236584514e-05,
      "loss": 0.5427,
      "step": 21782
    },
    {
      "epoch": 0.6691549165975487,
      "grad_norm": 0.32842907309532166,
      "learning_rate": 1.4994418556348854e-05,
      "loss": 0.5423,
      "step": 21783
    },
    {
      "epoch": 0.6691856357324978,
      "grad_norm": 0.3443058431148529,
      "learning_rate": 1.4993999864448381e-05,
      "loss": 0.5238,
      "step": 21784
    },
    {
      "epoch": 0.6692163548674469,
      "grad_norm": 0.35747402906417847,
      "learning_rate": 1.499358116088407e-05,
      "loss": 0.5104,
      "step": 21785
    },
    {
      "epoch": 0.6692470740023961,
      "grad_norm": 0.6501975655555725,
      "learning_rate": 1.4993162445656905e-05,
      "loss": 0.4955,
      "step": 21786
    },
    {
      "epoch": 0.6692777931373453,
      "grad_norm": 0.3517424762248993,
      "learning_rate": 1.499274371876786e-05,
      "loss": 0.5777,
      "step": 21787
    },
    {
      "epoch": 0.6693085122722944,
      "grad_norm": 0.40006858110427856,
      "learning_rate": 1.4992324980217912e-05,
      "loss": 0.6148,
      "step": 21788
    },
    {
      "epoch": 0.6693392314072436,
      "grad_norm": 0.37253817915916443,
      "learning_rate": 1.499190623000804e-05,
      "loss": 0.6133,
      "step": 21789
    },
    {
      "epoch": 0.6693699505421927,
      "grad_norm": 0.40567854046821594,
      "learning_rate": 1.4991487468139223e-05,
      "loss": 0.5105,
      "step": 21790
    },
    {
      "epoch": 0.6694006696771418,
      "grad_norm": 0.38822075724601746,
      "learning_rate": 1.4991068694612438e-05,
      "loss": 0.5973,
      "step": 21791
    },
    {
      "epoch": 0.6694313888120911,
      "grad_norm": 0.3723812997341156,
      "learning_rate": 1.4990649909428663e-05,
      "loss": 0.5247,
      "step": 21792
    },
    {
      "epoch": 0.6694621079470402,
      "grad_norm": 0.35154983401298523,
      "learning_rate": 1.4990231112588877e-05,
      "loss": 0.5693,
      "step": 21793
    },
    {
      "epoch": 0.6694928270819893,
      "grad_norm": 0.35957157611846924,
      "learning_rate": 1.498981230409406e-05,
      "loss": 0.4811,
      "step": 21794
    },
    {
      "epoch": 0.6695235462169385,
      "grad_norm": 0.3814113736152649,
      "learning_rate": 1.4989393483945186e-05,
      "loss": 0.6171,
      "step": 21795
    },
    {
      "epoch": 0.6695542653518877,
      "grad_norm": 0.36948996782302856,
      "learning_rate": 1.4988974652143235e-05,
      "loss": 0.5859,
      "step": 21796
    },
    {
      "epoch": 0.6695849844868369,
      "grad_norm": 0.3916812837123871,
      "learning_rate": 1.4988555808689186e-05,
      "loss": 0.5954,
      "step": 21797
    },
    {
      "epoch": 0.669615703621786,
      "grad_norm": 0.3475976884365082,
      "learning_rate": 1.4988136953584013e-05,
      "loss": 0.5099,
      "step": 21798
    },
    {
      "epoch": 0.6696464227567351,
      "grad_norm": 0.3409101963043213,
      "learning_rate": 1.4987718086828703e-05,
      "loss": 0.5395,
      "step": 21799
    },
    {
      "epoch": 0.6696771418916844,
      "grad_norm": 0.37721702456474304,
      "learning_rate": 1.4987299208424229e-05,
      "loss": 0.6263,
      "step": 21800
    },
    {
      "epoch": 0.6697078610266335,
      "grad_norm": 0.3559037148952484,
      "learning_rate": 1.4986880318371566e-05,
      "loss": 0.3815,
      "step": 21801
    },
    {
      "epoch": 0.6697385801615826,
      "grad_norm": 0.3871418535709381,
      "learning_rate": 1.4986461416671698e-05,
      "loss": 0.5912,
      "step": 21802
    },
    {
      "epoch": 0.6697692992965318,
      "grad_norm": 0.3460095524787903,
      "learning_rate": 1.49860425033256e-05,
      "loss": 0.5368,
      "step": 21803
    },
    {
      "epoch": 0.669800018431481,
      "grad_norm": 0.37192922830581665,
      "learning_rate": 1.4985623578334253e-05,
      "loss": 0.5891,
      "step": 21804
    },
    {
      "epoch": 0.6698307375664301,
      "grad_norm": 0.38272279500961304,
      "learning_rate": 1.498520464169863e-05,
      "loss": 0.5964,
      "step": 21805
    },
    {
      "epoch": 0.6698614567013793,
      "grad_norm": 0.36618033051490784,
      "learning_rate": 1.4984785693419717e-05,
      "loss": 0.5457,
      "step": 21806
    },
    {
      "epoch": 0.6698921758363284,
      "grad_norm": 0.3672919273376465,
      "learning_rate": 1.4984366733498488e-05,
      "loss": 0.5463,
      "step": 21807
    },
    {
      "epoch": 0.6699228949712777,
      "grad_norm": 0.3146987557411194,
      "learning_rate": 1.4983947761935922e-05,
      "loss": 0.5283,
      "step": 21808
    },
    {
      "epoch": 0.6699536141062268,
      "grad_norm": 0.3271990418434143,
      "learning_rate": 1.4983528778732996e-05,
      "loss": 0.5741,
      "step": 21809
    },
    {
      "epoch": 0.6699843332411759,
      "grad_norm": 0.3811798393726349,
      "learning_rate": 1.4983109783890692e-05,
      "loss": 0.5312,
      "step": 21810
    },
    {
      "epoch": 0.6700150523761251,
      "grad_norm": 0.33606886863708496,
      "learning_rate": 1.4982690777409989e-05,
      "loss": 0.5879,
      "step": 21811
    },
    {
      "epoch": 0.6700457715110743,
      "grad_norm": 0.3319818675518036,
      "learning_rate": 1.4982271759291862e-05,
      "loss": 0.5648,
      "step": 21812
    },
    {
      "epoch": 0.6700764906460234,
      "grad_norm": 0.37068116664886475,
      "learning_rate": 1.4981852729537294e-05,
      "loss": 0.5777,
      "step": 21813
    },
    {
      "epoch": 0.6701072097809726,
      "grad_norm": 0.3822195827960968,
      "learning_rate": 1.4981433688147258e-05,
      "loss": 0.6525,
      "step": 21814
    },
    {
      "epoch": 0.6701379289159217,
      "grad_norm": 0.3225240409374237,
      "learning_rate": 1.4981014635122737e-05,
      "loss": 0.4856,
      "step": 21815
    },
    {
      "epoch": 0.6701686480508708,
      "grad_norm": 0.36982864141464233,
      "learning_rate": 1.498059557046471e-05,
      "loss": 0.4751,
      "step": 21816
    },
    {
      "epoch": 0.6701993671858201,
      "grad_norm": 0.3358457684516907,
      "learning_rate": 1.498017649417415e-05,
      "loss": 0.508,
      "step": 21817
    },
    {
      "epoch": 0.6702300863207692,
      "grad_norm": 0.3784545063972473,
      "learning_rate": 1.4979757406252042e-05,
      "loss": 0.57,
      "step": 21818
    },
    {
      "epoch": 0.6702608054557183,
      "grad_norm": 0.3468027412891388,
      "learning_rate": 1.4979338306699363e-05,
      "loss": 0.5397,
      "step": 21819
    },
    {
      "epoch": 0.6702915245906675,
      "grad_norm": 0.45492056012153625,
      "learning_rate": 1.4978919195517092e-05,
      "loss": 0.594,
      "step": 21820
    },
    {
      "epoch": 0.6703222437256167,
      "grad_norm": 0.33153235912323,
      "learning_rate": 1.4978500072706205e-05,
      "loss": 0.5363,
      "step": 21821
    },
    {
      "epoch": 0.6703529628605659,
      "grad_norm": 0.3736344277858734,
      "learning_rate": 1.4978080938267688e-05,
      "loss": 0.489,
      "step": 21822
    },
    {
      "epoch": 0.670383681995515,
      "grad_norm": 0.6026903390884399,
      "learning_rate": 1.4977661792202511e-05,
      "loss": 0.5089,
      "step": 21823
    },
    {
      "epoch": 0.6704144011304641,
      "grad_norm": 0.3650552034378052,
      "learning_rate": 1.497724263451166e-05,
      "loss": 0.5141,
      "step": 21824
    },
    {
      "epoch": 0.6704451202654134,
      "grad_norm": 0.3497178554534912,
      "learning_rate": 1.4976823465196109e-05,
      "loss": 0.567,
      "step": 21825
    },
    {
      "epoch": 0.6704758394003625,
      "grad_norm": 0.35937079787254333,
      "learning_rate": 1.4976404284256843e-05,
      "loss": 0.6388,
      "step": 21826
    },
    {
      "epoch": 0.6705065585353116,
      "grad_norm": 0.36280468106269836,
      "learning_rate": 1.4975985091694831e-05,
      "loss": 0.61,
      "step": 21827
    },
    {
      "epoch": 0.6705372776702608,
      "grad_norm": 0.36528778076171875,
      "learning_rate": 1.4975565887511063e-05,
      "loss": 0.5428,
      "step": 21828
    },
    {
      "epoch": 0.67056799680521,
      "grad_norm": 0.36561641097068787,
      "learning_rate": 1.4975146671706513e-05,
      "loss": 0.5456,
      "step": 21829
    },
    {
      "epoch": 0.6705987159401591,
      "grad_norm": 0.5630608797073364,
      "learning_rate": 1.4974727444282159e-05,
      "loss": 0.4733,
      "step": 21830
    },
    {
      "epoch": 0.6706294350751083,
      "grad_norm": 0.3779500722885132,
      "learning_rate": 1.4974308205238984e-05,
      "loss": 0.5519,
      "step": 21831
    },
    {
      "epoch": 0.6706601542100574,
      "grad_norm": 0.3415282368659973,
      "learning_rate": 1.4973888954577962e-05,
      "loss": 0.4875,
      "step": 21832
    },
    {
      "epoch": 0.6706908733450067,
      "grad_norm": 0.3942824602127075,
      "learning_rate": 1.4973469692300077e-05,
      "loss": 0.6109,
      "step": 21833
    },
    {
      "epoch": 0.6707215924799558,
      "grad_norm": 0.3671298325061798,
      "learning_rate": 1.4973050418406306e-05,
      "loss": 0.5652,
      "step": 21834
    },
    {
      "epoch": 0.6707523116149049,
      "grad_norm": 0.3818517029285431,
      "learning_rate": 1.4972631132897627e-05,
      "loss": 0.5009,
      "step": 21835
    },
    {
      "epoch": 0.6707830307498541,
      "grad_norm": 0.3498857915401459,
      "learning_rate": 1.4972211835775023e-05,
      "loss": 0.5232,
      "step": 21836
    },
    {
      "epoch": 0.6708137498848032,
      "grad_norm": 0.3200263977050781,
      "learning_rate": 1.4971792527039468e-05,
      "loss": 0.522,
      "step": 21837
    },
    {
      "epoch": 0.6708444690197524,
      "grad_norm": 0.3588224947452545,
      "learning_rate": 1.4971373206691948e-05,
      "loss": 0.5043,
      "step": 21838
    },
    {
      "epoch": 0.6708751881547016,
      "grad_norm": 0.35425055027008057,
      "learning_rate": 1.4970953874733436e-05,
      "loss": 0.5411,
      "step": 21839
    },
    {
      "epoch": 0.6709059072896507,
      "grad_norm": 0.36200302839279175,
      "learning_rate": 1.4970534531164915e-05,
      "loss": 0.5579,
      "step": 21840
    },
    {
      "epoch": 0.6709366264245998,
      "grad_norm": 0.41114452481269836,
      "learning_rate": 1.4970115175987361e-05,
      "loss": 0.4858,
      "step": 21841
    },
    {
      "epoch": 0.6709673455595491,
      "grad_norm": 0.3624226152896881,
      "learning_rate": 1.496969580920176e-05,
      "loss": 0.5445,
      "step": 21842
    },
    {
      "epoch": 0.6709980646944982,
      "grad_norm": 0.3647700846195221,
      "learning_rate": 1.4969276430809084e-05,
      "loss": 0.5729,
      "step": 21843
    },
    {
      "epoch": 0.6710287838294474,
      "grad_norm": 0.4315674602985382,
      "learning_rate": 1.4968857040810319e-05,
      "loss": 0.5385,
      "step": 21844
    },
    {
      "epoch": 0.6710595029643965,
      "grad_norm": 0.3766828775405884,
      "learning_rate": 1.496843763920644e-05,
      "loss": 0.5549,
      "step": 21845
    },
    {
      "epoch": 0.6710902220993457,
      "grad_norm": 0.3474023640155792,
      "learning_rate": 1.4968018225998425e-05,
      "loss": 0.571,
      "step": 21846
    },
    {
      "epoch": 0.6711209412342949,
      "grad_norm": 0.35568177700042725,
      "learning_rate": 1.496759880118726e-05,
      "loss": 0.5642,
      "step": 21847
    },
    {
      "epoch": 0.671151660369244,
      "grad_norm": 0.46426820755004883,
      "learning_rate": 1.4967179364773918e-05,
      "loss": 0.5285,
      "step": 21848
    },
    {
      "epoch": 0.6711823795041931,
      "grad_norm": 0.3894895315170288,
      "learning_rate": 1.4966759916759387e-05,
      "loss": 0.5148,
      "step": 21849
    },
    {
      "epoch": 0.6712130986391424,
      "grad_norm": 0.36672693490982056,
      "learning_rate": 1.4966340457144634e-05,
      "loss": 0.6858,
      "step": 21850
    },
    {
      "epoch": 0.6712438177740915,
      "grad_norm": 0.41600480675697327,
      "learning_rate": 1.4965920985930652e-05,
      "loss": 0.5883,
      "step": 21851
    },
    {
      "epoch": 0.6712745369090406,
      "grad_norm": 0.49586841464042664,
      "learning_rate": 1.4965501503118413e-05,
      "loss": 0.5237,
      "step": 21852
    },
    {
      "epoch": 0.6713052560439898,
      "grad_norm": 0.34260469675064087,
      "learning_rate": 1.4965082008708897e-05,
      "loss": 0.5355,
      "step": 21853
    },
    {
      "epoch": 0.671335975178939,
      "grad_norm": 0.3998924195766449,
      "learning_rate": 1.4964662502703089e-05,
      "loss": 0.5634,
      "step": 21854
    },
    {
      "epoch": 0.6713666943138881,
      "grad_norm": 0.3667650818824768,
      "learning_rate": 1.496424298510196e-05,
      "loss": 0.5272,
      "step": 21855
    },
    {
      "epoch": 0.6713974134488373,
      "grad_norm": 0.3857392966747284,
      "learning_rate": 1.4963823455906499e-05,
      "loss": 0.5467,
      "step": 21856
    },
    {
      "epoch": 0.6714281325837864,
      "grad_norm": 0.4109492003917694,
      "learning_rate": 1.496340391511768e-05,
      "loss": 0.574,
      "step": 21857
    },
    {
      "epoch": 0.6714588517187356,
      "grad_norm": 0.3473782241344452,
      "learning_rate": 1.4962984362736483e-05,
      "loss": 0.5469,
      "step": 21858
    },
    {
      "epoch": 0.6714895708536848,
      "grad_norm": 0.3486780822277069,
      "learning_rate": 1.4962564798763892e-05,
      "loss": 0.5288,
      "step": 21859
    },
    {
      "epoch": 0.6715202899886339,
      "grad_norm": 0.3672081530094147,
      "learning_rate": 1.4962145223200883e-05,
      "loss": 0.5937,
      "step": 21860
    },
    {
      "epoch": 0.6715510091235831,
      "grad_norm": 0.43399733304977417,
      "learning_rate": 1.4961725636048437e-05,
      "loss": 0.6297,
      "step": 21861
    },
    {
      "epoch": 0.6715817282585322,
      "grad_norm": 0.34485486149787903,
      "learning_rate": 1.4961306037307534e-05,
      "loss": 0.6229,
      "step": 21862
    },
    {
      "epoch": 0.6716124473934814,
      "grad_norm": 0.4011688530445099,
      "learning_rate": 1.4960886426979157e-05,
      "loss": 0.5065,
      "step": 21863
    },
    {
      "epoch": 0.6716431665284306,
      "grad_norm": 0.3807830214500427,
      "learning_rate": 1.496046680506428e-05,
      "loss": 0.5837,
      "step": 21864
    },
    {
      "epoch": 0.6716738856633797,
      "grad_norm": 0.3692626655101776,
      "learning_rate": 1.4960047171563887e-05,
      "loss": 0.5179,
      "step": 21865
    },
    {
      "epoch": 0.6717046047983288,
      "grad_norm": 0.3689953088760376,
      "learning_rate": 1.4959627526478956e-05,
      "loss": 0.5501,
      "step": 21866
    },
    {
      "epoch": 0.6717353239332781,
      "grad_norm": 0.3764823377132416,
      "learning_rate": 1.4959207869810473e-05,
      "loss": 0.5762,
      "step": 21867
    },
    {
      "epoch": 0.6717660430682272,
      "grad_norm": 0.3269963264465332,
      "learning_rate": 1.4958788201559408e-05,
      "loss": 0.53,
      "step": 21868
    },
    {
      "epoch": 0.6717967622031764,
      "grad_norm": 0.34063270688056946,
      "learning_rate": 1.4958368521726754e-05,
      "loss": 0.5416,
      "step": 21869
    },
    {
      "epoch": 0.6718274813381255,
      "grad_norm": 0.3388739824295044,
      "learning_rate": 1.495794883031348e-05,
      "loss": 0.5515,
      "step": 21870
    },
    {
      "epoch": 0.6718582004730747,
      "grad_norm": 0.3790370523929596,
      "learning_rate": 1.495752912732057e-05,
      "loss": 0.5823,
      "step": 21871
    },
    {
      "epoch": 0.6718889196080239,
      "grad_norm": 0.3345538377761841,
      "learning_rate": 1.4957109412749005e-05,
      "loss": 0.5536,
      "step": 21872
    },
    {
      "epoch": 0.671919638742973,
      "grad_norm": 0.36834093928337097,
      "learning_rate": 1.4956689686599764e-05,
      "loss": 0.6051,
      "step": 21873
    },
    {
      "epoch": 0.6719503578779221,
      "grad_norm": 0.3695923089981079,
      "learning_rate": 1.4956269948873829e-05,
      "loss": 0.5466,
      "step": 21874
    },
    {
      "epoch": 0.6719810770128714,
      "grad_norm": 0.40504056215286255,
      "learning_rate": 1.4955850199572179e-05,
      "loss": 0.5909,
      "step": 21875
    },
    {
      "epoch": 0.6720117961478205,
      "grad_norm": 0.5484756827354431,
      "learning_rate": 1.4955430438695795e-05,
      "loss": 0.5632,
      "step": 21876
    },
    {
      "epoch": 0.6720425152827696,
      "grad_norm": 0.3953056037425995,
      "learning_rate": 1.4955010666245654e-05,
      "loss": 0.5631,
      "step": 21877
    },
    {
      "epoch": 0.6720732344177188,
      "grad_norm": 0.38316425681114197,
      "learning_rate": 1.4954590882222746e-05,
      "loss": 0.5196,
      "step": 21878
    },
    {
      "epoch": 0.6721039535526679,
      "grad_norm": 0.4177243113517761,
      "learning_rate": 1.495417108662804e-05,
      "loss": 0.5492,
      "step": 21879
    },
    {
      "epoch": 0.6721346726876171,
      "grad_norm": 0.35973554849624634,
      "learning_rate": 1.4953751279462526e-05,
      "loss": 0.6413,
      "step": 21880
    },
    {
      "epoch": 0.6721653918225663,
      "grad_norm": 0.3249121904373169,
      "learning_rate": 1.4953331460727176e-05,
      "loss": 0.4898,
      "step": 21881
    },
    {
      "epoch": 0.6721961109575154,
      "grad_norm": 0.341777503490448,
      "learning_rate": 1.4952911630422976e-05,
      "loss": 0.4997,
      "step": 21882
    },
    {
      "epoch": 0.6722268300924646,
      "grad_norm": 0.36944061517715454,
      "learning_rate": 1.4952491788550902e-05,
      "loss": 0.5157,
      "step": 21883
    },
    {
      "epoch": 0.6722575492274138,
      "grad_norm": 0.3697746992111206,
      "learning_rate": 1.4952071935111939e-05,
      "loss": 0.58,
      "step": 21884
    },
    {
      "epoch": 0.6722882683623629,
      "grad_norm": 0.3673689067363739,
      "learning_rate": 1.4951652070107065e-05,
      "loss": 0.5972,
      "step": 21885
    },
    {
      "epoch": 0.6723189874973121,
      "grad_norm": 0.3601202368736267,
      "learning_rate": 1.4951232193537267e-05,
      "loss": 0.5738,
      "step": 21886
    },
    {
      "epoch": 0.6723497066322612,
      "grad_norm": 0.3280943036079407,
      "learning_rate": 1.4950812305403515e-05,
      "loss": 0.5529,
      "step": 21887
    },
    {
      "epoch": 0.6723804257672104,
      "grad_norm": 0.3702241778373718,
      "learning_rate": 1.49503924057068e-05,
      "loss": 0.6007,
      "step": 21888
    },
    {
      "epoch": 0.6724111449021596,
      "grad_norm": 0.357453316450119,
      "learning_rate": 1.4949972494448093e-05,
      "loss": 0.5214,
      "step": 21889
    },
    {
      "epoch": 0.6724418640371087,
      "grad_norm": 0.3648562729358673,
      "learning_rate": 1.4949552571628382e-05,
      "loss": 0.5628,
      "step": 21890
    },
    {
      "epoch": 0.6724725831720578,
      "grad_norm": 0.37655097246170044,
      "learning_rate": 1.4949132637248644e-05,
      "loss": 0.572,
      "step": 21891
    },
    {
      "epoch": 0.6725033023070071,
      "grad_norm": 0.37352022528648376,
      "learning_rate": 1.4948712691309864e-05,
      "loss": 0.4803,
      "step": 21892
    },
    {
      "epoch": 0.6725340214419562,
      "grad_norm": 0.36312398314476013,
      "learning_rate": 1.4948292733813015e-05,
      "loss": 0.6125,
      "step": 21893
    },
    {
      "epoch": 0.6725647405769054,
      "grad_norm": 0.3802487552165985,
      "learning_rate": 1.4947872764759087e-05,
      "loss": 0.5973,
      "step": 21894
    },
    {
      "epoch": 0.6725954597118545,
      "grad_norm": 0.3438098728656769,
      "learning_rate": 1.4947452784149054e-05,
      "loss": 0.5228,
      "step": 21895
    },
    {
      "epoch": 0.6726261788468036,
      "grad_norm": 0.36823153495788574,
      "learning_rate": 1.4947032791983902e-05,
      "loss": 0.5678,
      "step": 21896
    },
    {
      "epoch": 0.6726568979817529,
      "grad_norm": 0.40206441283226013,
      "learning_rate": 1.494661278826461e-05,
      "loss": 0.5055,
      "step": 21897
    },
    {
      "epoch": 0.672687617116702,
      "grad_norm": 0.4220505356788635,
      "learning_rate": 1.4946192772992155e-05,
      "loss": 0.5943,
      "step": 21898
    },
    {
      "epoch": 0.6727183362516511,
      "grad_norm": 0.3443201780319214,
      "learning_rate": 1.4945772746167524e-05,
      "loss": 0.5297,
      "step": 21899
    },
    {
      "epoch": 0.6727490553866003,
      "grad_norm": 0.4021417796611786,
      "learning_rate": 1.4945352707791691e-05,
      "loss": 0.5652,
      "step": 21900
    },
    {
      "epoch": 0.6727797745215495,
      "grad_norm": 0.3758036494255066,
      "learning_rate": 1.4944932657865646e-05,
      "loss": 0.5682,
      "step": 21901
    },
    {
      "epoch": 0.6728104936564986,
      "grad_norm": 0.34770312905311584,
      "learning_rate": 1.4944512596390362e-05,
      "loss": 0.5556,
      "step": 21902
    },
    {
      "epoch": 0.6728412127914478,
      "grad_norm": 0.3889213502407074,
      "learning_rate": 1.4944092523366826e-05,
      "loss": 0.5112,
      "step": 21903
    },
    {
      "epoch": 0.6728719319263969,
      "grad_norm": 0.39988040924072266,
      "learning_rate": 1.4943672438796017e-05,
      "loss": 0.5631,
      "step": 21904
    },
    {
      "epoch": 0.6729026510613461,
      "grad_norm": 0.3434937596321106,
      "learning_rate": 1.4943252342678914e-05,
      "loss": 0.5266,
      "step": 21905
    },
    {
      "epoch": 0.6729333701962953,
      "grad_norm": 0.30382752418518066,
      "learning_rate": 1.4942832235016502e-05,
      "loss": 0.5203,
      "step": 21906
    },
    {
      "epoch": 0.6729640893312444,
      "grad_norm": 0.35641032457351685,
      "learning_rate": 1.4942412115809757e-05,
      "loss": 0.4929,
      "step": 21907
    },
    {
      "epoch": 0.6729948084661936,
      "grad_norm": 0.44042426347732544,
      "learning_rate": 1.4941991985059667e-05,
      "loss": 0.64,
      "step": 21908
    },
    {
      "epoch": 0.6730255276011428,
      "grad_norm": 0.39741331338882446,
      "learning_rate": 1.4941571842767206e-05,
      "loss": 0.5509,
      "step": 21909
    },
    {
      "epoch": 0.6730562467360919,
      "grad_norm": 0.40061479806900024,
      "learning_rate": 1.4941151688933361e-05,
      "loss": 0.612,
      "step": 21910
    },
    {
      "epoch": 0.6730869658710411,
      "grad_norm": 0.3666587769985199,
      "learning_rate": 1.494073152355911e-05,
      "loss": 0.5336,
      "step": 21911
    },
    {
      "epoch": 0.6731176850059902,
      "grad_norm": 0.347756028175354,
      "learning_rate": 1.4940311346645437e-05,
      "loss": 0.5707,
      "step": 21912
    },
    {
      "epoch": 0.6731484041409393,
      "grad_norm": 0.3638160526752472,
      "learning_rate": 1.4939891158193321e-05,
      "loss": 0.5078,
      "step": 21913
    },
    {
      "epoch": 0.6731791232758886,
      "grad_norm": 0.36156684160232544,
      "learning_rate": 1.4939470958203746e-05,
      "loss": 0.566,
      "step": 21914
    },
    {
      "epoch": 0.6732098424108377,
      "grad_norm": 0.3524653911590576,
      "learning_rate": 1.493905074667769e-05,
      "loss": 0.5814,
      "step": 21915
    },
    {
      "epoch": 0.6732405615457868,
      "grad_norm": 0.3495686650276184,
      "learning_rate": 1.4938630523616135e-05,
      "loss": 0.5015,
      "step": 21916
    },
    {
      "epoch": 0.673271280680736,
      "grad_norm": 0.3950243294239044,
      "learning_rate": 1.4938210289020065e-05,
      "loss": 0.5554,
      "step": 21917
    },
    {
      "epoch": 0.6733019998156852,
      "grad_norm": 0.37011972069740295,
      "learning_rate": 1.4937790042890459e-05,
      "loss": 0.5089,
      "step": 21918
    },
    {
      "epoch": 0.6733327189506344,
      "grad_norm": 0.34794119000434875,
      "learning_rate": 1.4937369785228298e-05,
      "loss": 0.5411,
      "step": 21919
    },
    {
      "epoch": 0.6733634380855835,
      "grad_norm": 0.35719773173332214,
      "learning_rate": 1.4936949516034567e-05,
      "loss": 0.5777,
      "step": 21920
    },
    {
      "epoch": 0.6733941572205326,
      "grad_norm": 0.3707546591758728,
      "learning_rate": 1.4936529235310246e-05,
      "loss": 0.5258,
      "step": 21921
    },
    {
      "epoch": 0.6734248763554819,
      "grad_norm": 0.37664976716041565,
      "learning_rate": 1.4936108943056315e-05,
      "loss": 0.5095,
      "step": 21922
    },
    {
      "epoch": 0.673455595490431,
      "grad_norm": 0.3792751431465149,
      "learning_rate": 1.4935688639273758e-05,
      "loss": 0.5924,
      "step": 21923
    },
    {
      "epoch": 0.6734863146253801,
      "grad_norm": 0.36416709423065186,
      "learning_rate": 1.4935268323963556e-05,
      "loss": 0.497,
      "step": 21924
    },
    {
      "epoch": 0.6735170337603293,
      "grad_norm": 0.386753648519516,
      "learning_rate": 1.4934847997126687e-05,
      "loss": 0.549,
      "step": 21925
    },
    {
      "epoch": 0.6735477528952785,
      "grad_norm": 0.3501449525356293,
      "learning_rate": 1.493442765876414e-05,
      "loss": 0.5246,
      "step": 21926
    },
    {
      "epoch": 0.6735784720302276,
      "grad_norm": 0.3628770112991333,
      "learning_rate": 1.493400730887689e-05,
      "loss": 0.5809,
      "step": 21927
    },
    {
      "epoch": 0.6736091911651768,
      "grad_norm": 0.3720833361148834,
      "learning_rate": 1.493358694746592e-05,
      "loss": 0.5293,
      "step": 21928
    },
    {
      "epoch": 0.6736399103001259,
      "grad_norm": 0.3926211893558502,
      "learning_rate": 1.4933166574532216e-05,
      "loss": 0.5458,
      "step": 21929
    },
    {
      "epoch": 0.6736706294350752,
      "grad_norm": 0.44198694825172424,
      "learning_rate": 1.493274619007676e-05,
      "loss": 0.4841,
      "step": 21930
    },
    {
      "epoch": 0.6737013485700243,
      "grad_norm": 0.4014030992984772,
      "learning_rate": 1.4932325794100525e-05,
      "loss": 0.5954,
      "step": 21931
    },
    {
      "epoch": 0.6737320677049734,
      "grad_norm": 0.37059536576271057,
      "learning_rate": 1.49319053866045e-05,
      "loss": 0.5696,
      "step": 21932
    },
    {
      "epoch": 0.6737627868399226,
      "grad_norm": 0.4080284833908081,
      "learning_rate": 1.4931484967589667e-05,
      "loss": 0.5529,
      "step": 21933
    },
    {
      "epoch": 0.6737935059748718,
      "grad_norm": 0.4272373914718628,
      "learning_rate": 1.4931064537057005e-05,
      "loss": 0.503,
      "step": 21934
    },
    {
      "epoch": 0.6738242251098209,
      "grad_norm": 0.3457905054092407,
      "learning_rate": 1.4930644095007499e-05,
      "loss": 0.6019,
      "step": 21935
    },
    {
      "epoch": 0.6738549442447701,
      "grad_norm": 0.37062689661979675,
      "learning_rate": 1.4930223641442126e-05,
      "loss": 0.5697,
      "step": 21936
    },
    {
      "epoch": 0.6738856633797192,
      "grad_norm": 0.38152849674224854,
      "learning_rate": 1.4929803176361872e-05,
      "loss": 0.5684,
      "step": 21937
    },
    {
      "epoch": 0.6739163825146683,
      "grad_norm": 0.35052046179771423,
      "learning_rate": 1.4929382699767723e-05,
      "loss": 0.5678,
      "step": 21938
    },
    {
      "epoch": 0.6739471016496176,
      "grad_norm": 0.3200049102306366,
      "learning_rate": 1.4928962211660652e-05,
      "loss": 0.5267,
      "step": 21939
    },
    {
      "epoch": 0.6739778207845667,
      "grad_norm": 0.35475748777389526,
      "learning_rate": 1.4928541712041647e-05,
      "loss": 0.6058,
      "step": 21940
    },
    {
      "epoch": 0.6740085399195158,
      "grad_norm": 0.3759993016719818,
      "learning_rate": 1.4928121200911688e-05,
      "loss": 0.525,
      "step": 21941
    },
    {
      "epoch": 0.674039259054465,
      "grad_norm": 0.37516549229621887,
      "learning_rate": 1.4927700678271759e-05,
      "loss": 0.5718,
      "step": 21942
    },
    {
      "epoch": 0.6740699781894142,
      "grad_norm": 0.3706417381763458,
      "learning_rate": 1.492728014412284e-05,
      "loss": 0.517,
      "step": 21943
    },
    {
      "epoch": 0.6741006973243634,
      "grad_norm": 0.3344963490962982,
      "learning_rate": 1.4926859598465915e-05,
      "loss": 0.5091,
      "step": 21944
    },
    {
      "epoch": 0.6741314164593125,
      "grad_norm": 0.34625300765037537,
      "learning_rate": 1.4926439041301963e-05,
      "loss": 0.5404,
      "step": 21945
    },
    {
      "epoch": 0.6741621355942616,
      "grad_norm": 0.33875221014022827,
      "learning_rate": 1.492601847263197e-05,
      "loss": 0.5638,
      "step": 21946
    },
    {
      "epoch": 0.6741928547292109,
      "grad_norm": 0.35900476574897766,
      "learning_rate": 1.4925597892456919e-05,
      "loss": 0.5569,
      "step": 21947
    },
    {
      "epoch": 0.67422357386416,
      "grad_norm": 0.383734792470932,
      "learning_rate": 1.4925177300777787e-05,
      "loss": 0.601,
      "step": 21948
    },
    {
      "epoch": 0.6742542929991091,
      "grad_norm": 0.4184529483318329,
      "learning_rate": 1.4924756697595562e-05,
      "loss": 0.6112,
      "step": 21949
    },
    {
      "epoch": 0.6742850121340583,
      "grad_norm": 0.3358507454395294,
      "learning_rate": 1.4924336082911221e-05,
      "loss": 0.5324,
      "step": 21950
    },
    {
      "epoch": 0.6743157312690075,
      "grad_norm": 0.42552074790000916,
      "learning_rate": 1.4923915456725753e-05,
      "loss": 0.5867,
      "step": 21951
    },
    {
      "epoch": 0.6743464504039566,
      "grad_norm": 0.3441917896270752,
      "learning_rate": 1.4923494819040132e-05,
      "loss": 0.5644,
      "step": 21952
    },
    {
      "epoch": 0.6743771695389058,
      "grad_norm": 0.3634584844112396,
      "learning_rate": 1.4923074169855348e-05,
      "loss": 0.5581,
      "step": 21953
    },
    {
      "epoch": 0.6744078886738549,
      "grad_norm": 0.5366572737693787,
      "learning_rate": 1.4922653509172377e-05,
      "loss": 0.5898,
      "step": 21954
    },
    {
      "epoch": 0.6744386078088042,
      "grad_norm": 0.3975207209587097,
      "learning_rate": 1.492223283699221e-05,
      "loss": 0.597,
      "step": 21955
    },
    {
      "epoch": 0.6744693269437533,
      "grad_norm": 0.37039101123809814,
      "learning_rate": 1.492181215331582e-05,
      "loss": 0.5928,
      "step": 21956
    },
    {
      "epoch": 0.6745000460787024,
      "grad_norm": 0.3359372019767761,
      "learning_rate": 1.4921391458144196e-05,
      "loss": 0.6435,
      "step": 21957
    },
    {
      "epoch": 0.6745307652136516,
      "grad_norm": 0.3487991690635681,
      "learning_rate": 1.4920970751478318e-05,
      "loss": 0.5747,
      "step": 21958
    },
    {
      "epoch": 0.6745614843486007,
      "grad_norm": 0.36599844694137573,
      "learning_rate": 1.492055003331917e-05,
      "loss": 0.595,
      "step": 21959
    },
    {
      "epoch": 0.6745922034835499,
      "grad_norm": 0.3594282865524292,
      "learning_rate": 1.4920129303667734e-05,
      "loss": 0.5295,
      "step": 21960
    },
    {
      "epoch": 0.6746229226184991,
      "grad_norm": 0.3228270411491394,
      "learning_rate": 1.4919708562524991e-05,
      "loss": 0.5278,
      "step": 21961
    },
    {
      "epoch": 0.6746536417534482,
      "grad_norm": 0.40170028805732727,
      "learning_rate": 1.4919287809891927e-05,
      "loss": 0.6406,
      "step": 21962
    },
    {
      "epoch": 0.6746843608883973,
      "grad_norm": 0.3816932737827301,
      "learning_rate": 1.491886704576952e-05,
      "loss": 0.518,
      "step": 21963
    },
    {
      "epoch": 0.6747150800233466,
      "grad_norm": 0.3733949363231659,
      "learning_rate": 1.4918446270158757e-05,
      "loss": 0.5932,
      "step": 21964
    },
    {
      "epoch": 0.6747457991582957,
      "grad_norm": 0.35410141944885254,
      "learning_rate": 1.4918025483060618e-05,
      "loss": 0.4947,
      "step": 21965
    },
    {
      "epoch": 0.6747765182932448,
      "grad_norm": 0.3735851049423218,
      "learning_rate": 1.491760468447609e-05,
      "loss": 0.617,
      "step": 21966
    },
    {
      "epoch": 0.674807237428194,
      "grad_norm": 0.35266318917274475,
      "learning_rate": 1.4917183874406154e-05,
      "loss": 0.5322,
      "step": 21967
    },
    {
      "epoch": 0.6748379565631432,
      "grad_norm": 0.33741629123687744,
      "learning_rate": 1.4916763052851786e-05,
      "loss": 0.5491,
      "step": 21968
    },
    {
      "epoch": 0.6748686756980924,
      "grad_norm": 0.3796861171722412,
      "learning_rate": 1.4916342219813977e-05,
      "loss": 0.5263,
      "step": 21969
    },
    {
      "epoch": 0.6748993948330415,
      "grad_norm": 0.3536703586578369,
      "learning_rate": 1.4915921375293709e-05,
      "loss": 0.5279,
      "step": 21970
    },
    {
      "epoch": 0.6749301139679906,
      "grad_norm": 0.3972707986831665,
      "learning_rate": 1.4915500519291963e-05,
      "loss": 0.6131,
      "step": 21971
    },
    {
      "epoch": 0.6749608331029399,
      "grad_norm": 0.4502725303173065,
      "learning_rate": 1.491507965180972e-05,
      "loss": 0.5785,
      "step": 21972
    },
    {
      "epoch": 0.674991552237889,
      "grad_norm": 0.3894447684288025,
      "learning_rate": 1.4914658772847967e-05,
      "loss": 0.5937,
      "step": 21973
    },
    {
      "epoch": 0.6750222713728381,
      "grad_norm": 0.40534600615501404,
      "learning_rate": 1.4914237882407682e-05,
      "loss": 0.5238,
      "step": 21974
    },
    {
      "epoch": 0.6750529905077873,
      "grad_norm": 0.37768471240997314,
      "learning_rate": 1.4913816980489854e-05,
      "loss": 0.5944,
      "step": 21975
    },
    {
      "epoch": 0.6750837096427365,
      "grad_norm": 0.34300222992897034,
      "learning_rate": 1.4913396067095464e-05,
      "loss": 0.4815,
      "step": 21976
    },
    {
      "epoch": 0.6751144287776856,
      "grad_norm": 0.373392790555954,
      "learning_rate": 1.4912975142225491e-05,
      "loss": 0.591,
      "step": 21977
    },
    {
      "epoch": 0.6751451479126348,
      "grad_norm": 0.37239471077919006,
      "learning_rate": 1.4912554205880927e-05,
      "loss": 0.6172,
      "step": 21978
    },
    {
      "epoch": 0.6751758670475839,
      "grad_norm": 0.3485792875289917,
      "learning_rate": 1.4912133258062744e-05,
      "loss": 0.5133,
      "step": 21979
    },
    {
      "epoch": 0.6752065861825332,
      "grad_norm": 0.3725620210170746,
      "learning_rate": 1.4911712298771934e-05,
      "loss": 0.5452,
      "step": 21980
    },
    {
      "epoch": 0.6752373053174823,
      "grad_norm": 0.3273075222969055,
      "learning_rate": 1.4911291328009476e-05,
      "loss": 0.5583,
      "step": 21981
    },
    {
      "epoch": 0.6752680244524314,
      "grad_norm": 0.364582896232605,
      "learning_rate": 1.4910870345776357e-05,
      "loss": 0.5009,
      "step": 21982
    },
    {
      "epoch": 0.6752987435873806,
      "grad_norm": 0.31916651129722595,
      "learning_rate": 1.4910449352073552e-05,
      "loss": 0.4682,
      "step": 21983
    },
    {
      "epoch": 0.6753294627223297,
      "grad_norm": 0.655091404914856,
      "learning_rate": 1.4910028346902052e-05,
      "loss": 0.5204,
      "step": 21984
    },
    {
      "epoch": 0.6753601818572789,
      "grad_norm": 0.3338433802127838,
      "learning_rate": 1.4909607330262842e-05,
      "loss": 0.5349,
      "step": 21985
    },
    {
      "epoch": 0.6753909009922281,
      "grad_norm": 0.38108620047569275,
      "learning_rate": 1.4909186302156893e-05,
      "loss": 0.529,
      "step": 21986
    },
    {
      "epoch": 0.6754216201271772,
      "grad_norm": 0.35736867785453796,
      "learning_rate": 1.4908765262585202e-05,
      "loss": 0.5344,
      "step": 21987
    },
    {
      "epoch": 0.6754523392621263,
      "grad_norm": 0.3761395215988159,
      "learning_rate": 1.4908344211548747e-05,
      "loss": 0.5391,
      "step": 21988
    },
    {
      "epoch": 0.6754830583970756,
      "grad_norm": 0.3662125766277313,
      "learning_rate": 1.490792314904851e-05,
      "loss": 0.4397,
      "step": 21989
    },
    {
      "epoch": 0.6755137775320247,
      "grad_norm": 0.3439617156982422,
      "learning_rate": 1.4907502075085474e-05,
      "loss": 0.5308,
      "step": 21990
    },
    {
      "epoch": 0.6755444966669738,
      "grad_norm": 0.34499675035476685,
      "learning_rate": 1.4907080989660628e-05,
      "loss": 0.5873,
      "step": 21991
    },
    {
      "epoch": 0.675575215801923,
      "grad_norm": 0.4523753821849823,
      "learning_rate": 1.4906659892774946e-05,
      "loss": 0.4978,
      "step": 21992
    },
    {
      "epoch": 0.6756059349368722,
      "grad_norm": 0.3327869772911072,
      "learning_rate": 1.4906238784429422e-05,
      "loss": 0.6029,
      "step": 21993
    },
    {
      "epoch": 0.6756366540718214,
      "grad_norm": 0.3492189645767212,
      "learning_rate": 1.4905817664625033e-05,
      "loss": 0.5125,
      "step": 21994
    },
    {
      "epoch": 0.6756673732067705,
      "grad_norm": 0.3759780824184418,
      "learning_rate": 1.4905396533362764e-05,
      "loss": 0.5728,
      "step": 21995
    },
    {
      "epoch": 0.6756980923417196,
      "grad_norm": 0.3445685803890228,
      "learning_rate": 1.49049753906436e-05,
      "loss": 0.5216,
      "step": 21996
    },
    {
      "epoch": 0.6757288114766689,
      "grad_norm": 0.3378606140613556,
      "learning_rate": 1.4904554236468523e-05,
      "loss": 0.5527,
      "step": 21997
    },
    {
      "epoch": 0.675759530611618,
      "grad_norm": 0.3522692322731018,
      "learning_rate": 1.4904133070838516e-05,
      "loss": 0.5508,
      "step": 21998
    },
    {
      "epoch": 0.6757902497465671,
      "grad_norm": 0.47690990567207336,
      "learning_rate": 1.4903711893754564e-05,
      "loss": 0.5499,
      "step": 21999
    },
    {
      "epoch": 0.6758209688815163,
      "grad_norm": 0.3717408776283264,
      "learning_rate": 1.490329070521765e-05,
      "loss": 0.5064,
      "step": 22000
    },
    {
      "epoch": 0.6758516880164654,
      "grad_norm": 0.29992109537124634,
      "learning_rate": 1.490286950522876e-05,
      "loss": 0.5479,
      "step": 22001
    },
    {
      "epoch": 0.6758824071514146,
      "grad_norm": 0.34636056423187256,
      "learning_rate": 1.4902448293788876e-05,
      "loss": 0.6443,
      "step": 22002
    },
    {
      "epoch": 0.6759131262863638,
      "grad_norm": 0.35563305020332336,
      "learning_rate": 1.4902027070898981e-05,
      "loss": 0.5228,
      "step": 22003
    },
    {
      "epoch": 0.6759438454213129,
      "grad_norm": 0.39106741547584534,
      "learning_rate": 1.4901605836560058e-05,
      "loss": 0.6054,
      "step": 22004
    },
    {
      "epoch": 0.6759745645562621,
      "grad_norm": 0.3728815019130707,
      "learning_rate": 1.4901184590773094e-05,
      "loss": 0.5574,
      "step": 22005
    },
    {
      "epoch": 0.6760052836912113,
      "grad_norm": 0.4282878637313843,
      "learning_rate": 1.490076333353907e-05,
      "loss": 0.6158,
      "step": 22006
    },
    {
      "epoch": 0.6760360028261604,
      "grad_norm": 0.33841943740844727,
      "learning_rate": 1.490034206485897e-05,
      "loss": 0.6216,
      "step": 22007
    },
    {
      "epoch": 0.6760667219611096,
      "grad_norm": 0.3763122260570526,
      "learning_rate": 1.4899920784733782e-05,
      "loss": 0.5562,
      "step": 22008
    },
    {
      "epoch": 0.6760974410960587,
      "grad_norm": 0.785895586013794,
      "learning_rate": 1.4899499493164484e-05,
      "loss": 0.6146,
      "step": 22009
    },
    {
      "epoch": 0.6761281602310079,
      "grad_norm": 0.39162376523017883,
      "learning_rate": 1.4899078190152064e-05,
      "loss": 0.5529,
      "step": 22010
    },
    {
      "epoch": 0.6761588793659571,
      "grad_norm": 0.3615739643573761,
      "learning_rate": 1.48986568756975e-05,
      "loss": 0.5247,
      "step": 22011
    },
    {
      "epoch": 0.6761895985009062,
      "grad_norm": 0.3341018855571747,
      "learning_rate": 1.4898235549801788e-05,
      "loss": 0.5847,
      "step": 22012
    },
    {
      "epoch": 0.6762203176358553,
      "grad_norm": 0.3398255407810211,
      "learning_rate": 1.48978142124659e-05,
      "loss": 0.5842,
      "step": 22013
    },
    {
      "epoch": 0.6762510367708046,
      "grad_norm": 0.3261178135871887,
      "learning_rate": 1.489739286369083e-05,
      "loss": 0.5295,
      "step": 22014
    },
    {
      "epoch": 0.6762817559057537,
      "grad_norm": 0.35671305656433105,
      "learning_rate": 1.4896971503477552e-05,
      "loss": 0.5536,
      "step": 22015
    },
    {
      "epoch": 0.6763124750407028,
      "grad_norm": 0.38038477301597595,
      "learning_rate": 1.4896550131827057e-05,
      "loss": 0.4416,
      "step": 22016
    },
    {
      "epoch": 0.676343194175652,
      "grad_norm": 0.4290097951889038,
      "learning_rate": 1.4896128748740326e-05,
      "loss": 0.6288,
      "step": 22017
    },
    {
      "epoch": 0.6763739133106011,
      "grad_norm": 0.3331545889377594,
      "learning_rate": 1.4895707354218348e-05,
      "loss": 0.5328,
      "step": 22018
    },
    {
      "epoch": 0.6764046324455504,
      "grad_norm": 0.34939754009246826,
      "learning_rate": 1.4895285948262099e-05,
      "loss": 0.5378,
      "step": 22019
    },
    {
      "epoch": 0.6764353515804995,
      "grad_norm": 0.3516475260257721,
      "learning_rate": 1.489486453087257e-05,
      "loss": 0.5061,
      "step": 22020
    },
    {
      "epoch": 0.6764660707154486,
      "grad_norm": 0.3165721595287323,
      "learning_rate": 1.4894443102050745e-05,
      "loss": 0.527,
      "step": 22021
    },
    {
      "epoch": 0.6764967898503979,
      "grad_norm": 0.37126755714416504,
      "learning_rate": 1.4894021661797602e-05,
      "loss": 0.5453,
      "step": 22022
    },
    {
      "epoch": 0.676527508985347,
      "grad_norm": 0.4275590479373932,
      "learning_rate": 1.4893600210114131e-05,
      "loss": 0.507,
      "step": 22023
    },
    {
      "epoch": 0.6765582281202961,
      "grad_norm": 0.41957661509513855,
      "learning_rate": 1.4893178747001316e-05,
      "loss": 0.6138,
      "step": 22024
    },
    {
      "epoch": 0.6765889472552453,
      "grad_norm": 0.3699117600917816,
      "learning_rate": 1.489275727246014e-05,
      "loss": 0.6002,
      "step": 22025
    },
    {
      "epoch": 0.6766196663901944,
      "grad_norm": 0.3787708580493927,
      "learning_rate": 1.4892335786491585e-05,
      "loss": 0.5015,
      "step": 22026
    },
    {
      "epoch": 0.6766503855251436,
      "grad_norm": 0.3470847010612488,
      "learning_rate": 1.4891914289096643e-05,
      "loss": 0.5485,
      "step": 22027
    },
    {
      "epoch": 0.6766811046600928,
      "grad_norm": 0.4015912413597107,
      "learning_rate": 1.4891492780276291e-05,
      "loss": 0.6577,
      "step": 22028
    },
    {
      "epoch": 0.6767118237950419,
      "grad_norm": 0.43208736181259155,
      "learning_rate": 1.4891071260031513e-05,
      "loss": 0.6261,
      "step": 22029
    },
    {
      "epoch": 0.6767425429299911,
      "grad_norm": 0.34447383880615234,
      "learning_rate": 1.4890649728363303e-05,
      "loss": 0.5354,
      "step": 22030
    },
    {
      "epoch": 0.6767732620649403,
      "grad_norm": 0.3563314974308014,
      "learning_rate": 1.4890228185272633e-05,
      "loss": 0.5184,
      "step": 22031
    },
    {
      "epoch": 0.6768039811998894,
      "grad_norm": 0.35011857748031616,
      "learning_rate": 1.4889806630760497e-05,
      "loss": 0.5792,
      "step": 22032
    },
    {
      "epoch": 0.6768347003348386,
      "grad_norm": 0.36940446496009827,
      "learning_rate": 1.4889385064827874e-05,
      "loss": 0.6201,
      "step": 22033
    },
    {
      "epoch": 0.6768654194697877,
      "grad_norm": 0.375895231962204,
      "learning_rate": 1.4888963487475753e-05,
      "loss": 0.6249,
      "step": 22034
    },
    {
      "epoch": 0.6768961386047369,
      "grad_norm": 0.3702835142612457,
      "learning_rate": 1.4888541898705115e-05,
      "loss": 0.5728,
      "step": 22035
    },
    {
      "epoch": 0.6769268577396861,
      "grad_norm": 0.4068738520145416,
      "learning_rate": 1.4888120298516949e-05,
      "loss": 0.5439,
      "step": 22036
    },
    {
      "epoch": 0.6769575768746352,
      "grad_norm": 0.36504966020584106,
      "learning_rate": 1.4887698686912234e-05,
      "loss": 0.5757,
      "step": 22037
    },
    {
      "epoch": 0.6769882960095843,
      "grad_norm": 0.42260459065437317,
      "learning_rate": 1.4887277063891955e-05,
      "loss": 0.611,
      "step": 22038
    },
    {
      "epoch": 0.6770190151445336,
      "grad_norm": 0.43044397234916687,
      "learning_rate": 1.4886855429457104e-05,
      "loss": 0.5111,
      "step": 22039
    },
    {
      "epoch": 0.6770497342794827,
      "grad_norm": 0.34634727239608765,
      "learning_rate": 1.4886433783608656e-05,
      "loss": 0.5027,
      "step": 22040
    },
    {
      "epoch": 0.6770804534144319,
      "grad_norm": 0.39839503169059753,
      "learning_rate": 1.4886012126347604e-05,
      "loss": 0.5025,
      "step": 22041
    },
    {
      "epoch": 0.677111172549381,
      "grad_norm": 0.37853187322616577,
      "learning_rate": 1.4885590457674928e-05,
      "loss": 0.593,
      "step": 22042
    },
    {
      "epoch": 0.6771418916843301,
      "grad_norm": 0.4178082048892975,
      "learning_rate": 1.4885168777591616e-05,
      "loss": 0.7145,
      "step": 22043
    },
    {
      "epoch": 0.6771726108192794,
      "grad_norm": 0.33137279748916626,
      "learning_rate": 1.4884747086098648e-05,
      "loss": 0.6007,
      "step": 22044
    },
    {
      "epoch": 0.6772033299542285,
      "grad_norm": 0.3378792107105255,
      "learning_rate": 1.4884325383197015e-05,
      "loss": 0.5545,
      "step": 22045
    },
    {
      "epoch": 0.6772340490891776,
      "grad_norm": 0.36839744448661804,
      "learning_rate": 1.4883903668887697e-05,
      "loss": 0.5727,
      "step": 22046
    },
    {
      "epoch": 0.6772647682241268,
      "grad_norm": 0.4636010229587555,
      "learning_rate": 1.488348194317168e-05,
      "loss": 0.5866,
      "step": 22047
    },
    {
      "epoch": 0.677295487359076,
      "grad_norm": 0.42446765303611755,
      "learning_rate": 1.4883060206049953e-05,
      "loss": 0.5507,
      "step": 22048
    },
    {
      "epoch": 0.6773262064940251,
      "grad_norm": 0.36833158135414124,
      "learning_rate": 1.4882638457523496e-05,
      "loss": 0.6148,
      "step": 22049
    },
    {
      "epoch": 0.6773569256289743,
      "grad_norm": 0.38636332750320435,
      "learning_rate": 1.4882216697593296e-05,
      "loss": 0.5501,
      "step": 22050
    },
    {
      "epoch": 0.6773876447639234,
      "grad_norm": 0.3685530424118042,
      "learning_rate": 1.4881794926260337e-05,
      "loss": 0.558,
      "step": 22051
    },
    {
      "epoch": 0.6774183638988726,
      "grad_norm": 0.3602665066719055,
      "learning_rate": 1.4881373143525609e-05,
      "loss": 0.5897,
      "step": 22052
    },
    {
      "epoch": 0.6774490830338218,
      "grad_norm": 0.3439449369907379,
      "learning_rate": 1.4880951349390089e-05,
      "loss": 0.517,
      "step": 22053
    },
    {
      "epoch": 0.6774798021687709,
      "grad_norm": 0.39522913098335266,
      "learning_rate": 1.4880529543854767e-05,
      "loss": 0.5498,
      "step": 22054
    },
    {
      "epoch": 0.6775105213037201,
      "grad_norm": 0.3335849642753601,
      "learning_rate": 1.488010772692063e-05,
      "loss": 0.5869,
      "step": 22055
    },
    {
      "epoch": 0.6775412404386693,
      "grad_norm": 0.39707332849502563,
      "learning_rate": 1.4879685898588658e-05,
      "loss": 0.5557,
      "step": 22056
    },
    {
      "epoch": 0.6775719595736184,
      "grad_norm": 0.36184823513031006,
      "learning_rate": 1.487926405885984e-05,
      "loss": 0.494,
      "step": 22057
    },
    {
      "epoch": 0.6776026787085676,
      "grad_norm": 0.35812410712242126,
      "learning_rate": 1.4878842207735158e-05,
      "loss": 0.4948,
      "step": 22058
    },
    {
      "epoch": 0.6776333978435167,
      "grad_norm": 0.37705615162849426,
      "learning_rate": 1.48784203452156e-05,
      "loss": 0.5516,
      "step": 22059
    },
    {
      "epoch": 0.6776641169784658,
      "grad_norm": 0.4065684676170349,
      "learning_rate": 1.4877998471302152e-05,
      "loss": 0.5342,
      "step": 22060
    },
    {
      "epoch": 0.6776948361134151,
      "grad_norm": 0.3690575659275055,
      "learning_rate": 1.48775765859958e-05,
      "loss": 0.5672,
      "step": 22061
    },
    {
      "epoch": 0.6777255552483642,
      "grad_norm": 0.36962929368019104,
      "learning_rate": 1.4877154689297521e-05,
      "loss": 0.4878,
      "step": 22062
    },
    {
      "epoch": 0.6777562743833133,
      "grad_norm": 0.4202807545661926,
      "learning_rate": 1.4876732781208311e-05,
      "loss": 0.6179,
      "step": 22063
    },
    {
      "epoch": 0.6777869935182625,
      "grad_norm": 0.3546825647354126,
      "learning_rate": 1.4876310861729151e-05,
      "loss": 0.5451,
      "step": 22064
    },
    {
      "epoch": 0.6778177126532117,
      "grad_norm": 0.3424154222011566,
      "learning_rate": 1.4875888930861023e-05,
      "loss": 0.5797,
      "step": 22065
    },
    {
      "epoch": 0.6778484317881609,
      "grad_norm": 0.3719116151332855,
      "learning_rate": 1.4875466988604918e-05,
      "loss": 0.6302,
      "step": 22066
    },
    {
      "epoch": 0.67787915092311,
      "grad_norm": 0.3858247995376587,
      "learning_rate": 1.4875045034961819e-05,
      "loss": 0.4758,
      "step": 22067
    },
    {
      "epoch": 0.6779098700580591,
      "grad_norm": 0.3224858045578003,
      "learning_rate": 1.4874623069932715e-05,
      "loss": 0.606,
      "step": 22068
    },
    {
      "epoch": 0.6779405891930084,
      "grad_norm": 0.3494868576526642,
      "learning_rate": 1.4874201093518584e-05,
      "loss": 0.5202,
      "step": 22069
    },
    {
      "epoch": 0.6779713083279575,
      "grad_norm": 0.3432576358318329,
      "learning_rate": 1.4873779105720419e-05,
      "loss": 0.5347,
      "step": 22070
    },
    {
      "epoch": 0.6780020274629066,
      "grad_norm": 0.34298667311668396,
      "learning_rate": 1.48733571065392e-05,
      "loss": 0.5191,
      "step": 22071
    },
    {
      "epoch": 0.6780327465978558,
      "grad_norm": 0.3300562798976898,
      "learning_rate": 1.4872935095975918e-05,
      "loss": 0.5551,
      "step": 22072
    },
    {
      "epoch": 0.678063465732805,
      "grad_norm": 0.35696059465408325,
      "learning_rate": 1.4872513074031553e-05,
      "loss": 0.6009,
      "step": 22073
    },
    {
      "epoch": 0.6780941848677541,
      "grad_norm": 0.38155168294906616,
      "learning_rate": 1.4872091040707095e-05,
      "loss": 0.5421,
      "step": 22074
    },
    {
      "epoch": 0.6781249040027033,
      "grad_norm": 0.407748281955719,
      "learning_rate": 1.4871668996003528e-05,
      "loss": 0.5752,
      "step": 22075
    },
    {
      "epoch": 0.6781556231376524,
      "grad_norm": 0.3444710969924927,
      "learning_rate": 1.4871246939921838e-05,
      "loss": 0.5926,
      "step": 22076
    },
    {
      "epoch": 0.6781863422726016,
      "grad_norm": 0.3999914526939392,
      "learning_rate": 1.487082487246301e-05,
      "loss": 0.5738,
      "step": 22077
    },
    {
      "epoch": 0.6782170614075508,
      "grad_norm": 0.3425615131855011,
      "learning_rate": 1.487040279362803e-05,
      "loss": 0.5416,
      "step": 22078
    },
    {
      "epoch": 0.6782477805424999,
      "grad_norm": 0.37862515449523926,
      "learning_rate": 1.4869980703417886e-05,
      "loss": 0.5082,
      "step": 22079
    },
    {
      "epoch": 0.6782784996774491,
      "grad_norm": 0.3513711094856262,
      "learning_rate": 1.4869558601833557e-05,
      "loss": 0.5622,
      "step": 22080
    },
    {
      "epoch": 0.6783092188123983,
      "grad_norm": 0.35556334257125854,
      "learning_rate": 1.4869136488876041e-05,
      "loss": 0.5974,
      "step": 22081
    },
    {
      "epoch": 0.6783399379473474,
      "grad_norm": 0.35760143399238586,
      "learning_rate": 1.4868714364546313e-05,
      "loss": 0.5676,
      "step": 22082
    },
    {
      "epoch": 0.6783706570822966,
      "grad_norm": 0.39501118659973145,
      "learning_rate": 1.486829222884536e-05,
      "loss": 0.5663,
      "step": 22083
    },
    {
      "epoch": 0.6784013762172457,
      "grad_norm": 0.46661633253097534,
      "learning_rate": 1.4867870081774173e-05,
      "loss": 0.5456,
      "step": 22084
    },
    {
      "epoch": 0.6784320953521948,
      "grad_norm": 0.40184640884399414,
      "learning_rate": 1.4867447923333736e-05,
      "loss": 0.5752,
      "step": 22085
    },
    {
      "epoch": 0.6784628144871441,
      "grad_norm": 0.4102281332015991,
      "learning_rate": 1.4867025753525035e-05,
      "loss": 0.5721,
      "step": 22086
    },
    {
      "epoch": 0.6784935336220932,
      "grad_norm": 0.35518795251846313,
      "learning_rate": 1.4866603572349054e-05,
      "loss": 0.5175,
      "step": 22087
    },
    {
      "epoch": 0.6785242527570423,
      "grad_norm": 0.35827556252479553,
      "learning_rate": 1.4866181379806781e-05,
      "loss": 0.6128,
      "step": 22088
    },
    {
      "epoch": 0.6785549718919915,
      "grad_norm": 0.3861767649650574,
      "learning_rate": 1.48657591758992e-05,
      "loss": 0.5446,
      "step": 22089
    },
    {
      "epoch": 0.6785856910269407,
      "grad_norm": 0.37139710783958435,
      "learning_rate": 1.48653369606273e-05,
      "loss": 0.622,
      "step": 22090
    },
    {
      "epoch": 0.6786164101618899,
      "grad_norm": 0.38762643933296204,
      "learning_rate": 1.486491473399207e-05,
      "loss": 0.4933,
      "step": 22091
    },
    {
      "epoch": 0.678647129296839,
      "grad_norm": 0.3300459384918213,
      "learning_rate": 1.4864492495994485e-05,
      "loss": 0.5641,
      "step": 22092
    },
    {
      "epoch": 0.6786778484317881,
      "grad_norm": 0.3642865717411041,
      "learning_rate": 1.4864070246635542e-05,
      "loss": 0.5273,
      "step": 22093
    },
    {
      "epoch": 0.6787085675667374,
      "grad_norm": 0.3671911656856537,
      "learning_rate": 1.4863647985916221e-05,
      "loss": 0.5956,
      "step": 22094
    },
    {
      "epoch": 0.6787392867016865,
      "grad_norm": 1.3949490785598755,
      "learning_rate": 1.4863225713837513e-05,
      "loss": 0.5867,
      "step": 22095
    },
    {
      "epoch": 0.6787700058366356,
      "grad_norm": 0.3950279653072357,
      "learning_rate": 1.48628034304004e-05,
      "loss": 0.6068,
      "step": 22096
    },
    {
      "epoch": 0.6788007249715848,
      "grad_norm": 0.43435680866241455,
      "learning_rate": 1.486238113560587e-05,
      "loss": 0.5242,
      "step": 22097
    },
    {
      "epoch": 0.678831444106534,
      "grad_norm": 0.352478951215744,
      "learning_rate": 1.4861958829454907e-05,
      "loss": 0.5038,
      "step": 22098
    },
    {
      "epoch": 0.6788621632414831,
      "grad_norm": 0.36525556445121765,
      "learning_rate": 1.4861536511948504e-05,
      "loss": 0.5749,
      "step": 22099
    },
    {
      "epoch": 0.6788928823764323,
      "grad_norm": 0.3951285183429718,
      "learning_rate": 1.4861114183087641e-05,
      "loss": 0.5331,
      "step": 22100
    },
    {
      "epoch": 0.6789236015113814,
      "grad_norm": 0.3826413154602051,
      "learning_rate": 1.4860691842873304e-05,
      "loss": 0.5408,
      "step": 22101
    },
    {
      "epoch": 0.6789543206463305,
      "grad_norm": 0.38105905055999756,
      "learning_rate": 1.4860269491306485e-05,
      "loss": 0.536,
      "step": 22102
    },
    {
      "epoch": 0.6789850397812798,
      "grad_norm": 0.3793348968029022,
      "learning_rate": 1.4859847128388165e-05,
      "loss": 0.6254,
      "step": 22103
    },
    {
      "epoch": 0.6790157589162289,
      "grad_norm": 0.3544193506240845,
      "learning_rate": 1.4859424754119334e-05,
      "loss": 0.5156,
      "step": 22104
    },
    {
      "epoch": 0.6790464780511781,
      "grad_norm": 0.39324551820755005,
      "learning_rate": 1.4859002368500977e-05,
      "loss": 0.5053,
      "step": 22105
    },
    {
      "epoch": 0.6790771971861272,
      "grad_norm": 0.35126134753227234,
      "learning_rate": 1.4858579971534081e-05,
      "loss": 0.5595,
      "step": 22106
    },
    {
      "epoch": 0.6791079163210764,
      "grad_norm": 0.3784853518009186,
      "learning_rate": 1.4858157563219632e-05,
      "loss": 0.5381,
      "step": 22107
    },
    {
      "epoch": 0.6791386354560256,
      "grad_norm": 0.33681240677833557,
      "learning_rate": 1.4857735143558616e-05,
      "loss": 0.5426,
      "step": 22108
    },
    {
      "epoch": 0.6791693545909747,
      "grad_norm": 0.3299916088581085,
      "learning_rate": 1.4857312712552022e-05,
      "loss": 0.559,
      "step": 22109
    },
    {
      "epoch": 0.6792000737259238,
      "grad_norm": 0.43774479627609253,
      "learning_rate": 1.4856890270200833e-05,
      "loss": 0.5921,
      "step": 22110
    },
    {
      "epoch": 0.6792307928608731,
      "grad_norm": 0.9641984701156616,
      "learning_rate": 1.4856467816506038e-05,
      "loss": 0.5802,
      "step": 22111
    },
    {
      "epoch": 0.6792615119958222,
      "grad_norm": 0.3762319087982178,
      "learning_rate": 1.4856045351468621e-05,
      "loss": 0.5702,
      "step": 22112
    },
    {
      "epoch": 0.6792922311307713,
      "grad_norm": 0.4951172471046448,
      "learning_rate": 1.4855622875089574e-05,
      "loss": 0.6075,
      "step": 22113
    },
    {
      "epoch": 0.6793229502657205,
      "grad_norm": 0.40628930926322937,
      "learning_rate": 1.4855200387369881e-05,
      "loss": 0.5483,
      "step": 22114
    },
    {
      "epoch": 0.6793536694006697,
      "grad_norm": 0.35693085193634033,
      "learning_rate": 1.4854777888310527e-05,
      "loss": 0.5006,
      "step": 22115
    },
    {
      "epoch": 0.6793843885356189,
      "grad_norm": 0.46579375863075256,
      "learning_rate": 1.48543553779125e-05,
      "loss": 0.5678,
      "step": 22116
    },
    {
      "epoch": 0.679415107670568,
      "grad_norm": 0.4174996614456177,
      "learning_rate": 1.485393285617679e-05,
      "loss": 0.551,
      "step": 22117
    },
    {
      "epoch": 0.6794458268055171,
      "grad_norm": 0.36591702699661255,
      "learning_rate": 1.4853510323104379e-05,
      "loss": 0.6163,
      "step": 22118
    },
    {
      "epoch": 0.6794765459404664,
      "grad_norm": 0.35869690775871277,
      "learning_rate": 1.4853087778696253e-05,
      "loss": 0.5581,
      "step": 22119
    },
    {
      "epoch": 0.6795072650754155,
      "grad_norm": 0.38964685797691345,
      "learning_rate": 1.4852665222953404e-05,
      "loss": 0.6359,
      "step": 22120
    },
    {
      "epoch": 0.6795379842103646,
      "grad_norm": 0.36953893303871155,
      "learning_rate": 1.4852242655876815e-05,
      "loss": 0.5004,
      "step": 22121
    },
    {
      "epoch": 0.6795687033453138,
      "grad_norm": 0.47858649492263794,
      "learning_rate": 1.4851820077467476e-05,
      "loss": 0.5282,
      "step": 22122
    },
    {
      "epoch": 0.679599422480263,
      "grad_norm": 0.4109785556793213,
      "learning_rate": 1.4851397487726374e-05,
      "loss": 0.4915,
      "step": 22123
    },
    {
      "epoch": 0.6796301416152121,
      "grad_norm": 0.3261522352695465,
      "learning_rate": 1.485097488665449e-05,
      "loss": 0.5368,
      "step": 22124
    },
    {
      "epoch": 0.6796608607501613,
      "grad_norm": 0.36818981170654297,
      "learning_rate": 1.4850552274252819e-05,
      "loss": 0.5734,
      "step": 22125
    },
    {
      "epoch": 0.6796915798851104,
      "grad_norm": 0.37101539969444275,
      "learning_rate": 1.4850129650522342e-05,
      "loss": 0.6249,
      "step": 22126
    },
    {
      "epoch": 0.6797222990200597,
      "grad_norm": 0.35864776372909546,
      "learning_rate": 1.484970701546405e-05,
      "loss": 0.5758,
      "step": 22127
    },
    {
      "epoch": 0.6797530181550088,
      "grad_norm": 0.349310964345932,
      "learning_rate": 1.4849284369078926e-05,
      "loss": 0.5472,
      "step": 22128
    },
    {
      "epoch": 0.6797837372899579,
      "grad_norm": 0.3612159490585327,
      "learning_rate": 1.4848861711367964e-05,
      "loss": 0.6167,
      "step": 22129
    },
    {
      "epoch": 0.6798144564249071,
      "grad_norm": 0.35629311203956604,
      "learning_rate": 1.4848439042332144e-05,
      "loss": 0.5174,
      "step": 22130
    },
    {
      "epoch": 0.6798451755598562,
      "grad_norm": 0.44505611062049866,
      "learning_rate": 1.4848016361972457e-05,
      "loss": 0.4916,
      "step": 22131
    },
    {
      "epoch": 0.6798758946948054,
      "grad_norm": 0.4399089217185974,
      "learning_rate": 1.4847593670289888e-05,
      "loss": 0.4548,
      "step": 22132
    },
    {
      "epoch": 0.6799066138297546,
      "grad_norm": 0.33396437764167786,
      "learning_rate": 1.4847170967285427e-05,
      "loss": 0.4833,
      "step": 22133
    },
    {
      "epoch": 0.6799373329647037,
      "grad_norm": 0.37625035643577576,
      "learning_rate": 1.484674825296006e-05,
      "loss": 0.5843,
      "step": 22134
    },
    {
      "epoch": 0.6799680520996528,
      "grad_norm": 0.4175543487071991,
      "learning_rate": 1.4846325527314771e-05,
      "loss": 0.5639,
      "step": 22135
    },
    {
      "epoch": 0.6799987712346021,
      "grad_norm": 0.37658369541168213,
      "learning_rate": 1.4845902790350555e-05,
      "loss": 0.5273,
      "step": 22136
    },
    {
      "epoch": 0.6800294903695512,
      "grad_norm": 0.42550191283226013,
      "learning_rate": 1.484548004206839e-05,
      "loss": 0.5923,
      "step": 22137
    },
    {
      "epoch": 0.6800602095045003,
      "grad_norm": 0.3247193992137909,
      "learning_rate": 1.484505728246927e-05,
      "loss": 0.5517,
      "step": 22138
    },
    {
      "epoch": 0.6800909286394495,
      "grad_norm": 0.34617891907691956,
      "learning_rate": 1.4844634511554176e-05,
      "loss": 0.5397,
      "step": 22139
    },
    {
      "epoch": 0.6801216477743987,
      "grad_norm": 0.3463086783885956,
      "learning_rate": 1.4844211729324105e-05,
      "loss": 0.5716,
      "step": 22140
    },
    {
      "epoch": 0.6801523669093479,
      "grad_norm": 0.38315537571907043,
      "learning_rate": 1.484378893578004e-05,
      "loss": 0.5841,
      "step": 22141
    },
    {
      "epoch": 0.680183086044297,
      "grad_norm": 0.35016703605651855,
      "learning_rate": 1.4843366130922965e-05,
      "loss": 0.5333,
      "step": 22142
    },
    {
      "epoch": 0.6802138051792461,
      "grad_norm": 0.3545159101486206,
      "learning_rate": 1.4842943314753871e-05,
      "loss": 0.5501,
      "step": 22143
    },
    {
      "epoch": 0.6802445243141954,
      "grad_norm": 0.43917107582092285,
      "learning_rate": 1.4842520487273743e-05,
      "loss": 0.5548,
      "step": 22144
    },
    {
      "epoch": 0.6802752434491445,
      "grad_norm": 0.32861924171447754,
      "learning_rate": 1.4842097648483572e-05,
      "loss": 0.506,
      "step": 22145
    },
    {
      "epoch": 0.6803059625840936,
      "grad_norm": 0.3602423369884491,
      "learning_rate": 1.4841674798384345e-05,
      "loss": 0.5807,
      "step": 22146
    },
    {
      "epoch": 0.6803366817190428,
      "grad_norm": 0.38858675956726074,
      "learning_rate": 1.4841251936977047e-05,
      "loss": 0.5573,
      "step": 22147
    },
    {
      "epoch": 0.6803674008539919,
      "grad_norm": 0.4082488715648651,
      "learning_rate": 1.4840829064262665e-05,
      "loss": 0.563,
      "step": 22148
    },
    {
      "epoch": 0.6803981199889411,
      "grad_norm": 0.37086814641952515,
      "learning_rate": 1.4840406180242193e-05,
      "loss": 0.5837,
      "step": 22149
    },
    {
      "epoch": 0.6804288391238903,
      "grad_norm": 0.3493087887763977,
      "learning_rate": 1.483998328491661e-05,
      "loss": 0.5697,
      "step": 22150
    },
    {
      "epoch": 0.6804595582588394,
      "grad_norm": 0.33861762285232544,
      "learning_rate": 1.483956037828691e-05,
      "loss": 0.592,
      "step": 22151
    },
    {
      "epoch": 0.6804902773937886,
      "grad_norm": 0.3955620527267456,
      "learning_rate": 1.483913746035408e-05,
      "loss": 0.5215,
      "step": 22152
    },
    {
      "epoch": 0.6805209965287378,
      "grad_norm": 0.38833898305892944,
      "learning_rate": 1.4838714531119105e-05,
      "loss": 0.5411,
      "step": 22153
    },
    {
      "epoch": 0.6805517156636869,
      "grad_norm": 0.3675617575645447,
      "learning_rate": 1.4838291590582974e-05,
      "loss": 0.5551,
      "step": 22154
    },
    {
      "epoch": 0.6805824347986361,
      "grad_norm": 0.3962963819503784,
      "learning_rate": 1.4837868638746673e-05,
      "loss": 0.542,
      "step": 22155
    },
    {
      "epoch": 0.6806131539335852,
      "grad_norm": 0.37194663286209106,
      "learning_rate": 1.4837445675611195e-05,
      "loss": 0.5595,
      "step": 22156
    },
    {
      "epoch": 0.6806438730685344,
      "grad_norm": 0.3636319041252136,
      "learning_rate": 1.4837022701177523e-05,
      "loss": 0.5857,
      "step": 22157
    },
    {
      "epoch": 0.6806745922034836,
      "grad_norm": 0.40092724561691284,
      "learning_rate": 1.4836599715446648e-05,
      "loss": 0.631,
      "step": 22158
    },
    {
      "epoch": 0.6807053113384327,
      "grad_norm": 0.33721405267715454,
      "learning_rate": 1.4836176718419557e-05,
      "loss": 0.5273,
      "step": 22159
    },
    {
      "epoch": 0.6807360304733818,
      "grad_norm": 0.37753498554229736,
      "learning_rate": 1.4835753710097236e-05,
      "loss": 0.6287,
      "step": 22160
    },
    {
      "epoch": 0.6807667496083311,
      "grad_norm": 0.35327214002609253,
      "learning_rate": 1.4835330690480676e-05,
      "loss": 0.5957,
      "step": 22161
    },
    {
      "epoch": 0.6807974687432802,
      "grad_norm": 0.43082863092422485,
      "learning_rate": 1.4834907659570863e-05,
      "loss": 0.5198,
      "step": 22162
    },
    {
      "epoch": 0.6808281878782293,
      "grad_norm": 0.37729859352111816,
      "learning_rate": 1.4834484617368786e-05,
      "loss": 0.5864,
      "step": 22163
    },
    {
      "epoch": 0.6808589070131785,
      "grad_norm": 0.3935149013996124,
      "learning_rate": 1.4834061563875431e-05,
      "loss": 0.5474,
      "step": 22164
    },
    {
      "epoch": 0.6808896261481276,
      "grad_norm": 0.37700724601745605,
      "learning_rate": 1.483363849909179e-05,
      "loss": 0.5837,
      "step": 22165
    },
    {
      "epoch": 0.6809203452830769,
      "grad_norm": 0.3355126678943634,
      "learning_rate": 1.4833215423018845e-05,
      "loss": 0.5207,
      "step": 22166
    },
    {
      "epoch": 0.680951064418026,
      "grad_norm": 0.38831827044487,
      "learning_rate": 1.4832792335657591e-05,
      "loss": 0.5219,
      "step": 22167
    },
    {
      "epoch": 0.6809817835529751,
      "grad_norm": 0.33946067094802856,
      "learning_rate": 1.483236923700901e-05,
      "loss": 0.5658,
      "step": 22168
    },
    {
      "epoch": 0.6810125026879243,
      "grad_norm": 0.39119675755500793,
      "learning_rate": 1.4831946127074097e-05,
      "loss": 0.5625,
      "step": 22169
    },
    {
      "epoch": 0.6810432218228735,
      "grad_norm": 0.3245536983013153,
      "learning_rate": 1.4831523005853836e-05,
      "loss": 0.5771,
      "step": 22170
    },
    {
      "epoch": 0.6810739409578226,
      "grad_norm": 0.3521042764186859,
      "learning_rate": 1.4831099873349212e-05,
      "loss": 0.574,
      "step": 22171
    },
    {
      "epoch": 0.6811046600927718,
      "grad_norm": 0.4059060215950012,
      "learning_rate": 1.483067672956122e-05,
      "loss": 0.615,
      "step": 22172
    },
    {
      "epoch": 0.6811353792277209,
      "grad_norm": 0.3792570233345032,
      "learning_rate": 1.4830253574490843e-05,
      "loss": 0.5603,
      "step": 22173
    },
    {
      "epoch": 0.6811660983626701,
      "grad_norm": 0.3655550479888916,
      "learning_rate": 1.4829830408139074e-05,
      "loss": 0.5132,
      "step": 22174
    },
    {
      "epoch": 0.6811968174976193,
      "grad_norm": 0.3231363296508789,
      "learning_rate": 1.4829407230506896e-05,
      "loss": 0.4987,
      "step": 22175
    },
    {
      "epoch": 0.6812275366325684,
      "grad_norm": 0.3765471279621124,
      "learning_rate": 1.48289840415953e-05,
      "loss": 0.5764,
      "step": 22176
    },
    {
      "epoch": 0.6812582557675176,
      "grad_norm": 0.36155396699905396,
      "learning_rate": 1.4828560841405277e-05,
      "loss": 0.5342,
      "step": 22177
    },
    {
      "epoch": 0.6812889749024668,
      "grad_norm": 0.3669131398200989,
      "learning_rate": 1.482813762993781e-05,
      "loss": 0.5438,
      "step": 22178
    },
    {
      "epoch": 0.6813196940374159,
      "grad_norm": 0.7130789756774902,
      "learning_rate": 1.4827714407193893e-05,
      "loss": 0.5511,
      "step": 22179
    },
    {
      "epoch": 0.6813504131723651,
      "grad_norm": 0.40458452701568604,
      "learning_rate": 1.4827291173174512e-05,
      "loss": 0.5676,
      "step": 22180
    },
    {
      "epoch": 0.6813811323073142,
      "grad_norm": 0.3640938997268677,
      "learning_rate": 1.4826867927880655e-05,
      "loss": 0.4875,
      "step": 22181
    },
    {
      "epoch": 0.6814118514422633,
      "grad_norm": 0.39882224798202515,
      "learning_rate": 1.4826444671313309e-05,
      "loss": 0.5493,
      "step": 22182
    },
    {
      "epoch": 0.6814425705772126,
      "grad_norm": 0.3683452606201172,
      "learning_rate": 1.4826021403473468e-05,
      "loss": 0.5725,
      "step": 22183
    },
    {
      "epoch": 0.6814732897121617,
      "grad_norm": 0.38578706979751587,
      "learning_rate": 1.4825598124362113e-05,
      "loss": 0.5526,
      "step": 22184
    },
    {
      "epoch": 0.6815040088471108,
      "grad_norm": 0.36815759539604187,
      "learning_rate": 1.4825174833980238e-05,
      "loss": 0.5357,
      "step": 22185
    },
    {
      "epoch": 0.68153472798206,
      "grad_norm": 0.32993149757385254,
      "learning_rate": 1.4824751532328832e-05,
      "loss": 0.602,
      "step": 22186
    },
    {
      "epoch": 0.6815654471170092,
      "grad_norm": 0.3609321415424347,
      "learning_rate": 1.4824328219408879e-05,
      "loss": 0.5709,
      "step": 22187
    },
    {
      "epoch": 0.6815961662519583,
      "grad_norm": 0.3687096834182739,
      "learning_rate": 1.4823904895221373e-05,
      "loss": 0.5898,
      "step": 22188
    },
    {
      "epoch": 0.6816268853869075,
      "grad_norm": 0.3951222896575928,
      "learning_rate": 1.4823481559767296e-05,
      "loss": 0.6349,
      "step": 22189
    },
    {
      "epoch": 0.6816576045218566,
      "grad_norm": 0.3481368124485016,
      "learning_rate": 1.4823058213047645e-05,
      "loss": 0.5876,
      "step": 22190
    },
    {
      "epoch": 0.6816883236568059,
      "grad_norm": 0.3755500316619873,
      "learning_rate": 1.4822634855063403e-05,
      "loss": 0.5774,
      "step": 22191
    },
    {
      "epoch": 0.681719042791755,
      "grad_norm": 0.3498498499393463,
      "learning_rate": 1.4822211485815562e-05,
      "loss": 0.5526,
      "step": 22192
    },
    {
      "epoch": 0.6817497619267041,
      "grad_norm": 0.36222022771835327,
      "learning_rate": 1.4821788105305108e-05,
      "loss": 0.561,
      "step": 22193
    },
    {
      "epoch": 0.6817804810616533,
      "grad_norm": 0.37609559297561646,
      "learning_rate": 1.4821364713533031e-05,
      "loss": 0.5953,
      "step": 22194
    },
    {
      "epoch": 0.6818112001966025,
      "grad_norm": 0.34140267968177795,
      "learning_rate": 1.4820941310500321e-05,
      "loss": 0.5005,
      "step": 22195
    },
    {
      "epoch": 0.6818419193315516,
      "grad_norm": 0.4103870689868927,
      "learning_rate": 1.4820517896207965e-05,
      "loss": 0.6046,
      "step": 22196
    },
    {
      "epoch": 0.6818726384665008,
      "grad_norm": 0.3942112624645233,
      "learning_rate": 1.4820094470656953e-05,
      "loss": 0.7537,
      "step": 22197
    },
    {
      "epoch": 0.6819033576014499,
      "grad_norm": 0.3822396397590637,
      "learning_rate": 1.4819671033848272e-05,
      "loss": 0.5579,
      "step": 22198
    },
    {
      "epoch": 0.681934076736399,
      "grad_norm": 0.41991814970970154,
      "learning_rate": 1.4819247585782916e-05,
      "loss": 0.6714,
      "step": 22199
    },
    {
      "epoch": 0.6819647958713483,
      "grad_norm": 0.36395299434661865,
      "learning_rate": 1.4818824126461868e-05,
      "loss": 0.5357,
      "step": 22200
    },
    {
      "epoch": 0.6819955150062974,
      "grad_norm": 0.4017806053161621,
      "learning_rate": 1.4818400655886122e-05,
      "loss": 0.5972,
      "step": 22201
    },
    {
      "epoch": 0.6820262341412466,
      "grad_norm": 0.37514379620552063,
      "learning_rate": 1.4817977174056663e-05,
      "loss": 0.5416,
      "step": 22202
    },
    {
      "epoch": 0.6820569532761958,
      "grad_norm": 0.41145485639572144,
      "learning_rate": 1.4817553680974484e-05,
      "loss": 0.5539,
      "step": 22203
    },
    {
      "epoch": 0.6820876724111449,
      "grad_norm": 0.5077033638954163,
      "learning_rate": 1.481713017664057e-05,
      "loss": 0.4546,
      "step": 22204
    },
    {
      "epoch": 0.6821183915460941,
      "grad_norm": 0.35223135352134705,
      "learning_rate": 1.4816706661055913e-05,
      "loss": 0.6412,
      "step": 22205
    },
    {
      "epoch": 0.6821491106810432,
      "grad_norm": 0.36534014344215393,
      "learning_rate": 1.4816283134221502e-05,
      "loss": 0.5827,
      "step": 22206
    },
    {
      "epoch": 0.6821798298159923,
      "grad_norm": 0.35061728954315186,
      "learning_rate": 1.4815859596138322e-05,
      "loss": 0.5458,
      "step": 22207
    },
    {
      "epoch": 0.6822105489509416,
      "grad_norm": 0.34773802757263184,
      "learning_rate": 1.481543604680737e-05,
      "loss": 0.5485,
      "step": 22208
    },
    {
      "epoch": 0.6822412680858907,
      "grad_norm": 0.3850644826889038,
      "learning_rate": 1.4815012486229627e-05,
      "loss": 0.5964,
      "step": 22209
    },
    {
      "epoch": 0.6822719872208398,
      "grad_norm": 0.3674179017543793,
      "learning_rate": 1.481458891440609e-05,
      "loss": 0.5002,
      "step": 22210
    },
    {
      "epoch": 0.682302706355789,
      "grad_norm": 0.3804352581501007,
      "learning_rate": 1.481416533133774e-05,
      "loss": 0.5598,
      "step": 22211
    },
    {
      "epoch": 0.6823334254907382,
      "grad_norm": 0.5574365258216858,
      "learning_rate": 1.481374173702557e-05,
      "loss": 0.54,
      "step": 22212
    },
    {
      "epoch": 0.6823641446256873,
      "grad_norm": 0.35065412521362305,
      "learning_rate": 1.4813318131470572e-05,
      "loss": 0.5554,
      "step": 22213
    },
    {
      "epoch": 0.6823948637606365,
      "grad_norm": 0.343891978263855,
      "learning_rate": 1.4812894514673735e-05,
      "loss": 0.5602,
      "step": 22214
    },
    {
      "epoch": 0.6824255828955856,
      "grad_norm": 0.3854948878288269,
      "learning_rate": 1.4812470886636048e-05,
      "loss": 0.5233,
      "step": 22215
    },
    {
      "epoch": 0.6824563020305349,
      "grad_norm": 0.3765072822570801,
      "learning_rate": 1.4812047247358495e-05,
      "loss": 0.6034,
      "step": 22216
    },
    {
      "epoch": 0.682487021165484,
      "grad_norm": 0.3754224181175232,
      "learning_rate": 1.4811623596842073e-05,
      "loss": 0.561,
      "step": 22217
    },
    {
      "epoch": 0.6825177403004331,
      "grad_norm": 0.3579805791378021,
      "learning_rate": 1.4811199935087764e-05,
      "loss": 0.5979,
      "step": 22218
    },
    {
      "epoch": 0.6825484594353823,
      "grad_norm": 0.3612287938594818,
      "learning_rate": 1.4810776262096565e-05,
      "loss": 0.5857,
      "step": 22219
    },
    {
      "epoch": 0.6825791785703315,
      "grad_norm": 0.4651626944541931,
      "learning_rate": 1.481035257786946e-05,
      "loss": 0.5721,
      "step": 22220
    },
    {
      "epoch": 0.6826098977052806,
      "grad_norm": 0.33850157260894775,
      "learning_rate": 1.4809928882407442e-05,
      "loss": 0.5379,
      "step": 22221
    },
    {
      "epoch": 0.6826406168402298,
      "grad_norm": 0.4019697606563568,
      "learning_rate": 1.4809505175711501e-05,
      "loss": 0.5744,
      "step": 22222
    },
    {
      "epoch": 0.6826713359751789,
      "grad_norm": 0.3800772726535797,
      "learning_rate": 1.4809081457782622e-05,
      "loss": 0.59,
      "step": 22223
    },
    {
      "epoch": 0.682702055110128,
      "grad_norm": 0.3500741422176361,
      "learning_rate": 1.4808657728621799e-05,
      "loss": 0.5555,
      "step": 22224
    },
    {
      "epoch": 0.6827327742450773,
      "grad_norm": 0.3243032395839691,
      "learning_rate": 1.4808233988230016e-05,
      "loss": 0.5556,
      "step": 22225
    },
    {
      "epoch": 0.6827634933800264,
      "grad_norm": 0.3588520586490631,
      "learning_rate": 1.480781023660827e-05,
      "loss": 0.545,
      "step": 22226
    },
    {
      "epoch": 0.6827942125149756,
      "grad_norm": 0.40104860067367554,
      "learning_rate": 1.4807386473757548e-05,
      "loss": 0.5169,
      "step": 22227
    },
    {
      "epoch": 0.6828249316499247,
      "grad_norm": 0.3433799147605896,
      "learning_rate": 1.480696269967884e-05,
      "loss": 0.5169,
      "step": 22228
    },
    {
      "epoch": 0.6828556507848739,
      "grad_norm": 0.346200168132782,
      "learning_rate": 1.4806538914373132e-05,
      "loss": 0.5942,
      "step": 22229
    },
    {
      "epoch": 0.6828863699198231,
      "grad_norm": 0.37860584259033203,
      "learning_rate": 1.4806115117841416e-05,
      "loss": 0.5297,
      "step": 22230
    },
    {
      "epoch": 0.6829170890547722,
      "grad_norm": 0.3422708213329315,
      "learning_rate": 1.4805691310084684e-05,
      "loss": 0.4955,
      "step": 22231
    },
    {
      "epoch": 0.6829478081897213,
      "grad_norm": 0.356072336435318,
      "learning_rate": 1.4805267491103924e-05,
      "loss": 0.5867,
      "step": 22232
    },
    {
      "epoch": 0.6829785273246706,
      "grad_norm": 0.35442855954170227,
      "learning_rate": 1.4804843660900127e-05,
      "loss": 0.4711,
      "step": 22233
    },
    {
      "epoch": 0.6830092464596197,
      "grad_norm": 0.34832268953323364,
      "learning_rate": 1.4804419819474283e-05,
      "loss": 0.5151,
      "step": 22234
    },
    {
      "epoch": 0.6830399655945688,
      "grad_norm": 0.3589058518409729,
      "learning_rate": 1.4803995966827381e-05,
      "loss": 0.5061,
      "step": 22235
    },
    {
      "epoch": 0.683070684729518,
      "grad_norm": 0.36883097887039185,
      "learning_rate": 1.4803572102960409e-05,
      "loss": 0.6039,
      "step": 22236
    },
    {
      "epoch": 0.6831014038644672,
      "grad_norm": 0.3689591586589813,
      "learning_rate": 1.480314822787436e-05,
      "loss": 0.575,
      "step": 22237
    },
    {
      "epoch": 0.6831321229994164,
      "grad_norm": 0.37607231736183167,
      "learning_rate": 1.4802724341570222e-05,
      "loss": 0.6259,
      "step": 22238
    },
    {
      "epoch": 0.6831628421343655,
      "grad_norm": 0.36341506242752075,
      "learning_rate": 1.4802300444048987e-05,
      "loss": 0.5016,
      "step": 22239
    },
    {
      "epoch": 0.6831935612693146,
      "grad_norm": 0.3764829933643341,
      "learning_rate": 1.4801876535311644e-05,
      "loss": 0.5596,
      "step": 22240
    },
    {
      "epoch": 0.6832242804042639,
      "grad_norm": 0.39373353123664856,
      "learning_rate": 1.4801452615359181e-05,
      "loss": 0.5507,
      "step": 22241
    },
    {
      "epoch": 0.683254999539213,
      "grad_norm": 0.41016581654548645,
      "learning_rate": 1.4801028684192594e-05,
      "loss": 0.6361,
      "step": 22242
    },
    {
      "epoch": 0.6832857186741621,
      "grad_norm": 0.34405845403671265,
      "learning_rate": 1.4800604741812862e-05,
      "loss": 0.5253,
      "step": 22243
    },
    {
      "epoch": 0.6833164378091113,
      "grad_norm": 0.39178839325904846,
      "learning_rate": 1.480018078822099e-05,
      "loss": 0.5305,
      "step": 22244
    },
    {
      "epoch": 0.6833471569440605,
      "grad_norm": 0.34684786200523376,
      "learning_rate": 1.4799756823417956e-05,
      "loss": 0.4938,
      "step": 22245
    },
    {
      "epoch": 0.6833778760790096,
      "grad_norm": 0.41800457239151,
      "learning_rate": 1.4799332847404757e-05,
      "loss": 0.6106,
      "step": 22246
    },
    {
      "epoch": 0.6834085952139588,
      "grad_norm": 0.41450586915016174,
      "learning_rate": 1.479890886018238e-05,
      "loss": 0.5652,
      "step": 22247
    },
    {
      "epoch": 0.6834393143489079,
      "grad_norm": 0.3535746932029724,
      "learning_rate": 1.4798484861751817e-05,
      "loss": 0.5841,
      "step": 22248
    },
    {
      "epoch": 0.683470033483857,
      "grad_norm": 0.4018350839614868,
      "learning_rate": 1.4798060852114056e-05,
      "loss": 0.5545,
      "step": 22249
    },
    {
      "epoch": 0.6835007526188063,
      "grad_norm": 0.3481876850128174,
      "learning_rate": 1.4797636831270088e-05,
      "loss": 0.5666,
      "step": 22250
    },
    {
      "epoch": 0.6835314717537554,
      "grad_norm": 0.3334049880504608,
      "learning_rate": 1.4797212799220908e-05,
      "loss": 0.5201,
      "step": 22251
    },
    {
      "epoch": 0.6835621908887046,
      "grad_norm": 0.38042202591896057,
      "learning_rate": 1.4796788755967497e-05,
      "loss": 0.5854,
      "step": 22252
    },
    {
      "epoch": 0.6835929100236537,
      "grad_norm": 0.384789377450943,
      "learning_rate": 1.4796364701510857e-05,
      "loss": 0.5371,
      "step": 22253
    },
    {
      "epoch": 0.6836236291586029,
      "grad_norm": 0.3517173230648041,
      "learning_rate": 1.4795940635851968e-05,
      "loss": 0.4959,
      "step": 22254
    },
    {
      "epoch": 0.6836543482935521,
      "grad_norm": 0.33009183406829834,
      "learning_rate": 1.4795516558991827e-05,
      "loss": 0.4779,
      "step": 22255
    },
    {
      "epoch": 0.6836850674285012,
      "grad_norm": 0.3506251275539398,
      "learning_rate": 1.4795092470931423e-05,
      "loss": 0.5585,
      "step": 22256
    },
    {
      "epoch": 0.6837157865634503,
      "grad_norm": 0.3336748480796814,
      "learning_rate": 1.4794668371671743e-05,
      "loss": 0.5779,
      "step": 22257
    },
    {
      "epoch": 0.6837465056983996,
      "grad_norm": 0.4002193510532379,
      "learning_rate": 1.4794244261213782e-05,
      "loss": 0.5897,
      "step": 22258
    },
    {
      "epoch": 0.6837772248333487,
      "grad_norm": 0.38220927119255066,
      "learning_rate": 1.4793820139558526e-05,
      "loss": 0.4615,
      "step": 22259
    },
    {
      "epoch": 0.6838079439682978,
      "grad_norm": 0.347542941570282,
      "learning_rate": 1.479339600670697e-05,
      "loss": 0.5394,
      "step": 22260
    },
    {
      "epoch": 0.683838663103247,
      "grad_norm": 0.3968759775161743,
      "learning_rate": 1.4792971862660102e-05,
      "loss": 0.4995,
      "step": 22261
    },
    {
      "epoch": 0.6838693822381962,
      "grad_norm": 0.3786665201187134,
      "learning_rate": 1.4792547707418917e-05,
      "loss": 0.555,
      "step": 22262
    },
    {
      "epoch": 0.6839001013731454,
      "grad_norm": 0.32154178619384766,
      "learning_rate": 1.4792123540984398e-05,
      "loss": 0.5566,
      "step": 22263
    },
    {
      "epoch": 0.6839308205080945,
      "grad_norm": 0.3642008304595947,
      "learning_rate": 1.479169936335754e-05,
      "loss": 0.5194,
      "step": 22264
    },
    {
      "epoch": 0.6839615396430436,
      "grad_norm": 0.32767942547798157,
      "learning_rate": 1.4791275174539335e-05,
      "loss": 0.5782,
      "step": 22265
    },
    {
      "epoch": 0.6839922587779929,
      "grad_norm": 0.35843732953071594,
      "learning_rate": 1.479085097453077e-05,
      "loss": 0.5592,
      "step": 22266
    },
    {
      "epoch": 0.684022977912942,
      "grad_norm": 0.3200001120567322,
      "learning_rate": 1.4790426763332842e-05,
      "loss": 0.5301,
      "step": 22267
    },
    {
      "epoch": 0.6840536970478911,
      "grad_norm": 0.38590767979621887,
      "learning_rate": 1.4790002540946536e-05,
      "loss": 0.5899,
      "step": 22268
    },
    {
      "epoch": 0.6840844161828403,
      "grad_norm": 0.35063958168029785,
      "learning_rate": 1.4789578307372842e-05,
      "loss": 0.4849,
      "step": 22269
    },
    {
      "epoch": 0.6841151353177894,
      "grad_norm": 0.35643404722213745,
      "learning_rate": 1.4789154062612757e-05,
      "loss": 0.5792,
      "step": 22270
    },
    {
      "epoch": 0.6841458544527386,
      "grad_norm": 0.33064237236976624,
      "learning_rate": 1.4788729806667266e-05,
      "loss": 0.5279,
      "step": 22271
    },
    {
      "epoch": 0.6841765735876878,
      "grad_norm": 0.3766935467720032,
      "learning_rate": 1.4788305539537362e-05,
      "loss": 0.4976,
      "step": 22272
    },
    {
      "epoch": 0.6842072927226369,
      "grad_norm": 0.3716386556625366,
      "learning_rate": 1.478788126122404e-05,
      "loss": 0.5359,
      "step": 22273
    },
    {
      "epoch": 0.684238011857586,
      "grad_norm": 0.3464394807815552,
      "learning_rate": 1.4787456971728284e-05,
      "loss": 0.5225,
      "step": 22274
    },
    {
      "epoch": 0.6842687309925353,
      "grad_norm": 0.3254960775375366,
      "learning_rate": 1.4787032671051087e-05,
      "loss": 0.5565,
      "step": 22275
    },
    {
      "epoch": 0.6842994501274844,
      "grad_norm": 0.37534868717193604,
      "learning_rate": 1.4786608359193442e-05,
      "loss": 0.5125,
      "step": 22276
    },
    {
      "epoch": 0.6843301692624336,
      "grad_norm": 0.3865952789783478,
      "learning_rate": 1.4786184036156337e-05,
      "loss": 0.544,
      "step": 22277
    },
    {
      "epoch": 0.6843608883973827,
      "grad_norm": 0.35770416259765625,
      "learning_rate": 1.4785759701940767e-05,
      "loss": 0.5685,
      "step": 22278
    },
    {
      "epoch": 0.6843916075323319,
      "grad_norm": 0.34681347012519836,
      "learning_rate": 1.4785335356547719e-05,
      "loss": 0.5804,
      "step": 22279
    },
    {
      "epoch": 0.6844223266672811,
      "grad_norm": 0.40937232971191406,
      "learning_rate": 1.4784910999978189e-05,
      "loss": 0.5749,
      "step": 22280
    },
    {
      "epoch": 0.6844530458022302,
      "grad_norm": 0.3323512077331543,
      "learning_rate": 1.4784486632233161e-05,
      "loss": 0.5181,
      "step": 22281
    },
    {
      "epoch": 0.6844837649371793,
      "grad_norm": 0.4001200497150421,
      "learning_rate": 1.4784062253313635e-05,
      "loss": 0.5718,
      "step": 22282
    },
    {
      "epoch": 0.6845144840721286,
      "grad_norm": 0.41735535860061646,
      "learning_rate": 1.4783637863220595e-05,
      "loss": 0.5937,
      "step": 22283
    },
    {
      "epoch": 0.6845452032070777,
      "grad_norm": 0.3670138120651245,
      "learning_rate": 1.4783213461955032e-05,
      "loss": 0.6421,
      "step": 22284
    },
    {
      "epoch": 0.6845759223420268,
      "grad_norm": 0.4336550235748291,
      "learning_rate": 1.4782789049517944e-05,
      "loss": 0.5967,
      "step": 22285
    },
    {
      "epoch": 0.684606641476976,
      "grad_norm": 0.3548167943954468,
      "learning_rate": 1.4782364625910316e-05,
      "loss": 0.5894,
      "step": 22286
    },
    {
      "epoch": 0.6846373606119251,
      "grad_norm": 0.435347318649292,
      "learning_rate": 1.4781940191133146e-05,
      "loss": 0.5318,
      "step": 22287
    },
    {
      "epoch": 0.6846680797468744,
      "grad_norm": 0.3556582033634186,
      "learning_rate": 1.4781515745187415e-05,
      "loss": 0.5668,
      "step": 22288
    },
    {
      "epoch": 0.6846987988818235,
      "grad_norm": 0.3755463659763336,
      "learning_rate": 1.4781091288074123e-05,
      "loss": 0.5674,
      "step": 22289
    },
    {
      "epoch": 0.6847295180167726,
      "grad_norm": 0.3355221748352051,
      "learning_rate": 1.4780666819794261e-05,
      "loss": 0.4824,
      "step": 22290
    },
    {
      "epoch": 0.6847602371517219,
      "grad_norm": 0.3381446301937103,
      "learning_rate": 1.4780242340348812e-05,
      "loss": 0.5293,
      "step": 22291
    },
    {
      "epoch": 0.684790956286671,
      "grad_norm": 0.3731398284435272,
      "learning_rate": 1.4779817849738777e-05,
      "loss": 0.5788,
      "step": 22292
    },
    {
      "epoch": 0.6848216754216201,
      "grad_norm": 0.39404022693634033,
      "learning_rate": 1.4779393347965142e-05,
      "loss": 0.589,
      "step": 22293
    },
    {
      "epoch": 0.6848523945565693,
      "grad_norm": 0.33856692910194397,
      "learning_rate": 1.4778968835028899e-05,
      "loss": 0.5579,
      "step": 22294
    },
    {
      "epoch": 0.6848831136915184,
      "grad_norm": 0.3255302608013153,
      "learning_rate": 1.4778544310931043e-05,
      "loss": 0.5106,
      "step": 22295
    },
    {
      "epoch": 0.6849138328264676,
      "grad_norm": 0.34864169359207153,
      "learning_rate": 1.4778119775672561e-05,
      "loss": 0.5566,
      "step": 22296
    },
    {
      "epoch": 0.6849445519614168,
      "grad_norm": 0.3541164994239807,
      "learning_rate": 1.4777695229254447e-05,
      "loss": 0.4879,
      "step": 22297
    },
    {
      "epoch": 0.6849752710963659,
      "grad_norm": 0.36169862747192383,
      "learning_rate": 1.4777270671677694e-05,
      "loss": 0.5486,
      "step": 22298
    },
    {
      "epoch": 0.685005990231315,
      "grad_norm": 0.3894304037094116,
      "learning_rate": 1.477684610294329e-05,
      "loss": 0.5268,
      "step": 22299
    },
    {
      "epoch": 0.6850367093662643,
      "grad_norm": 0.34811967611312866,
      "learning_rate": 1.4776421523052229e-05,
      "loss": 0.5462,
      "step": 22300
    },
    {
      "epoch": 0.6850674285012134,
      "grad_norm": 0.4495047926902771,
      "learning_rate": 1.4775996932005501e-05,
      "loss": 0.5674,
      "step": 22301
    },
    {
      "epoch": 0.6850981476361626,
      "grad_norm": 0.3368246257305145,
      "learning_rate": 1.4775572329804097e-05,
      "loss": 0.4841,
      "step": 22302
    },
    {
      "epoch": 0.6851288667711117,
      "grad_norm": 0.37233966588974,
      "learning_rate": 1.4775147716449014e-05,
      "loss": 0.5522,
      "step": 22303
    },
    {
      "epoch": 0.6851595859060609,
      "grad_norm": 0.6251071691513062,
      "learning_rate": 1.4774723091941236e-05,
      "loss": 0.5913,
      "step": 22304
    },
    {
      "epoch": 0.6851903050410101,
      "grad_norm": 0.36423981189727783,
      "learning_rate": 1.4774298456281764e-05,
      "loss": 0.5519,
      "step": 22305
    },
    {
      "epoch": 0.6852210241759592,
      "grad_norm": 0.3686211109161377,
      "learning_rate": 1.477387380947158e-05,
      "loss": 0.4992,
      "step": 22306
    },
    {
      "epoch": 0.6852517433109083,
      "grad_norm": 0.3721068501472473,
      "learning_rate": 1.4773449151511682e-05,
      "loss": 0.531,
      "step": 22307
    },
    {
      "epoch": 0.6852824624458576,
      "grad_norm": 0.43197715282440186,
      "learning_rate": 1.4773024482403063e-05,
      "loss": 0.6337,
      "step": 22308
    },
    {
      "epoch": 0.6853131815808067,
      "grad_norm": 0.4323098957538605,
      "learning_rate": 1.4772599802146708e-05,
      "loss": 0.5893,
      "step": 22309
    },
    {
      "epoch": 0.6853439007157558,
      "grad_norm": 0.36336231231689453,
      "learning_rate": 1.4772175110743614e-05,
      "loss": 0.5851,
      "step": 22310
    },
    {
      "epoch": 0.685374619850705,
      "grad_norm": 0.3443112075328827,
      "learning_rate": 1.4771750408194772e-05,
      "loss": 0.5561,
      "step": 22311
    },
    {
      "epoch": 0.6854053389856541,
      "grad_norm": 0.3817789852619171,
      "learning_rate": 1.4771325694501172e-05,
      "loss": 0.6055,
      "step": 22312
    },
    {
      "epoch": 0.6854360581206034,
      "grad_norm": 0.346361368894577,
      "learning_rate": 1.4770900969663809e-05,
      "loss": 0.482,
      "step": 22313
    },
    {
      "epoch": 0.6854667772555525,
      "grad_norm": 0.36099985241889954,
      "learning_rate": 1.4770476233683674e-05,
      "loss": 0.5278,
      "step": 22314
    },
    {
      "epoch": 0.6854974963905016,
      "grad_norm": 0.4062071144580841,
      "learning_rate": 1.4770051486561758e-05,
      "loss": 0.5235,
      "step": 22315
    },
    {
      "epoch": 0.6855282155254508,
      "grad_norm": 0.3940903842449188,
      "learning_rate": 1.4769626728299056e-05,
      "loss": 0.5417,
      "step": 22316
    },
    {
      "epoch": 0.6855589346604,
      "grad_norm": 0.3900858759880066,
      "learning_rate": 1.4769201958896554e-05,
      "loss": 0.5621,
      "step": 22317
    },
    {
      "epoch": 0.6855896537953491,
      "grad_norm": 0.5134332180023193,
      "learning_rate": 1.4768777178355249e-05,
      "loss": 0.5572,
      "step": 22318
    },
    {
      "epoch": 0.6856203729302983,
      "grad_norm": 0.37263745069503784,
      "learning_rate": 1.4768352386676132e-05,
      "loss": 0.4788,
      "step": 22319
    },
    {
      "epoch": 0.6856510920652474,
      "grad_norm": 0.4311971068382263,
      "learning_rate": 1.4767927583860195e-05,
      "loss": 0.6085,
      "step": 22320
    },
    {
      "epoch": 0.6856818112001966,
      "grad_norm": 0.38544154167175293,
      "learning_rate": 1.4767502769908428e-05,
      "loss": 0.576,
      "step": 22321
    },
    {
      "epoch": 0.6857125303351458,
      "grad_norm": 0.44126421213150024,
      "learning_rate": 1.4767077944821829e-05,
      "loss": 0.5586,
      "step": 22322
    },
    {
      "epoch": 0.6857432494700949,
      "grad_norm": 0.39214202761650085,
      "learning_rate": 1.4766653108601386e-05,
      "loss": 0.5284,
      "step": 22323
    },
    {
      "epoch": 0.6857739686050441,
      "grad_norm": 0.3679179847240448,
      "learning_rate": 1.476622826124809e-05,
      "loss": 0.5344,
      "step": 22324
    },
    {
      "epoch": 0.6858046877399933,
      "grad_norm": 0.3631734848022461,
      "learning_rate": 1.4765803402762935e-05,
      "loss": 0.5351,
      "step": 22325
    },
    {
      "epoch": 0.6858354068749424,
      "grad_norm": 0.3324226140975952,
      "learning_rate": 1.4765378533146915e-05,
      "loss": 0.536,
      "step": 22326
    },
    {
      "epoch": 0.6858661260098916,
      "grad_norm": 0.36465033888816833,
      "learning_rate": 1.476495365240102e-05,
      "loss": 0.5581,
      "step": 22327
    },
    {
      "epoch": 0.6858968451448407,
      "grad_norm": 0.33881503343582153,
      "learning_rate": 1.4764528760526244e-05,
      "loss": 0.5393,
      "step": 22328
    },
    {
      "epoch": 0.6859275642797898,
      "grad_norm": 0.37398549914360046,
      "learning_rate": 1.4764103857523575e-05,
      "loss": 0.5427,
      "step": 22329
    },
    {
      "epoch": 0.6859582834147391,
      "grad_norm": 0.39993977546691895,
      "learning_rate": 1.4763678943394011e-05,
      "loss": 0.5407,
      "step": 22330
    },
    {
      "epoch": 0.6859890025496882,
      "grad_norm": 0.3893808126449585,
      "learning_rate": 1.4763254018138542e-05,
      "loss": 0.5853,
      "step": 22331
    },
    {
      "epoch": 0.6860197216846373,
      "grad_norm": 0.3862139880657196,
      "learning_rate": 1.476282908175816e-05,
      "loss": 0.5498,
      "step": 22332
    },
    {
      "epoch": 0.6860504408195865,
      "grad_norm": 0.3720901310443878,
      "learning_rate": 1.4762404134253859e-05,
      "loss": 0.5615,
      "step": 22333
    },
    {
      "epoch": 0.6860811599545357,
      "grad_norm": 0.3489682674407959,
      "learning_rate": 1.4761979175626631e-05,
      "loss": 0.5308,
      "step": 22334
    },
    {
      "epoch": 0.6861118790894848,
      "grad_norm": 0.4014577269554138,
      "learning_rate": 1.4761554205877467e-05,
      "loss": 0.5744,
      "step": 22335
    },
    {
      "epoch": 0.686142598224434,
      "grad_norm": 0.40987345576286316,
      "learning_rate": 1.476112922500736e-05,
      "loss": 0.5706,
      "step": 22336
    },
    {
      "epoch": 0.6861733173593831,
      "grad_norm": 0.37753501534461975,
      "learning_rate": 1.4760704233017307e-05,
      "loss": 0.5785,
      "step": 22337
    },
    {
      "epoch": 0.6862040364943324,
      "grad_norm": 0.5889684557914734,
      "learning_rate": 1.4760279229908292e-05,
      "loss": 0.5153,
      "step": 22338
    },
    {
      "epoch": 0.6862347556292815,
      "grad_norm": 0.42323732376098633,
      "learning_rate": 1.4759854215681312e-05,
      "loss": 0.5657,
      "step": 22339
    },
    {
      "epoch": 0.6862654747642306,
      "grad_norm": 0.3398694396018982,
      "learning_rate": 1.4759429190337362e-05,
      "loss": 0.5085,
      "step": 22340
    },
    {
      "epoch": 0.6862961938991798,
      "grad_norm": 0.3879204988479614,
      "learning_rate": 1.4759004153877434e-05,
      "loss": 0.5734,
      "step": 22341
    },
    {
      "epoch": 0.686326913034129,
      "grad_norm": 0.3882334530353546,
      "learning_rate": 1.475857910630252e-05,
      "loss": 0.4921,
      "step": 22342
    },
    {
      "epoch": 0.6863576321690781,
      "grad_norm": 0.3473150134086609,
      "learning_rate": 1.4758154047613609e-05,
      "loss": 0.5583,
      "step": 22343
    },
    {
      "epoch": 0.6863883513040273,
      "grad_norm": 0.345386803150177,
      "learning_rate": 1.4757728977811698e-05,
      "loss": 0.5745,
      "step": 22344
    },
    {
      "epoch": 0.6864190704389764,
      "grad_norm": 0.35682782530784607,
      "learning_rate": 1.4757303896897779e-05,
      "loss": 0.5647,
      "step": 22345
    },
    {
      "epoch": 0.6864497895739256,
      "grad_norm": 0.3969445824623108,
      "learning_rate": 1.4756878804872845e-05,
      "loss": 0.5764,
      "step": 22346
    },
    {
      "epoch": 0.6864805087088748,
      "grad_norm": 0.4185381233692169,
      "learning_rate": 1.4756453701737887e-05,
      "loss": 0.5992,
      "step": 22347
    },
    {
      "epoch": 0.6865112278438239,
      "grad_norm": 0.3749343752861023,
      "learning_rate": 1.4756028587493903e-05,
      "loss": 0.5768,
      "step": 22348
    },
    {
      "epoch": 0.6865419469787731,
      "grad_norm": 0.3482033610343933,
      "learning_rate": 1.4755603462141877e-05,
      "loss": 0.5251,
      "step": 22349
    },
    {
      "epoch": 0.6865726661137223,
      "grad_norm": 0.4630645513534546,
      "learning_rate": 1.475517832568281e-05,
      "loss": 0.5183,
      "step": 22350
    },
    {
      "epoch": 0.6866033852486714,
      "grad_norm": 0.3697907030582428,
      "learning_rate": 1.475475317811769e-05,
      "loss": 0.5781,
      "step": 22351
    },
    {
      "epoch": 0.6866341043836206,
      "grad_norm": 0.3608085811138153,
      "learning_rate": 1.4754328019447514e-05,
      "loss": 0.513,
      "step": 22352
    },
    {
      "epoch": 0.6866648235185697,
      "grad_norm": 0.3353351056575775,
      "learning_rate": 1.4753902849673271e-05,
      "loss": 0.5338,
      "step": 22353
    },
    {
      "epoch": 0.6866955426535188,
      "grad_norm": 0.336324542760849,
      "learning_rate": 1.4753477668795957e-05,
      "loss": 0.5581,
      "step": 22354
    },
    {
      "epoch": 0.6867262617884681,
      "grad_norm": 0.3491520881652832,
      "learning_rate": 1.4753052476816565e-05,
      "loss": 0.5609,
      "step": 22355
    },
    {
      "epoch": 0.6867569809234172,
      "grad_norm": 0.3609473705291748,
      "learning_rate": 1.4752627273736084e-05,
      "loss": 0.4806,
      "step": 22356
    },
    {
      "epoch": 0.6867877000583663,
      "grad_norm": 0.3369573652744293,
      "learning_rate": 1.4752202059555511e-05,
      "loss": 0.5395,
      "step": 22357
    },
    {
      "epoch": 0.6868184191933155,
      "grad_norm": 0.36505231261253357,
      "learning_rate": 1.475177683427584e-05,
      "loss": 0.5871,
      "step": 22358
    },
    {
      "epoch": 0.6868491383282647,
      "grad_norm": 0.382931113243103,
      "learning_rate": 1.475135159789806e-05,
      "loss": 0.5042,
      "step": 22359
    },
    {
      "epoch": 0.6868798574632138,
      "grad_norm": 0.3991295397281647,
      "learning_rate": 1.4750926350423169e-05,
      "loss": 0.5804,
      "step": 22360
    },
    {
      "epoch": 0.686910576598163,
      "grad_norm": 0.41785621643066406,
      "learning_rate": 1.4750501091852156e-05,
      "loss": 0.5193,
      "step": 22361
    },
    {
      "epoch": 0.6869412957331121,
      "grad_norm": 0.3722258508205414,
      "learning_rate": 1.4750075822186018e-05,
      "loss": 0.5708,
      "step": 22362
    },
    {
      "epoch": 0.6869720148680614,
      "grad_norm": 0.3718307316303253,
      "learning_rate": 1.4749650541425744e-05,
      "loss": 0.6225,
      "step": 22363
    },
    {
      "epoch": 0.6870027340030105,
      "grad_norm": 0.3465326130390167,
      "learning_rate": 1.4749225249572331e-05,
      "loss": 0.4983,
      "step": 22364
    },
    {
      "epoch": 0.6870334531379596,
      "grad_norm": 0.34115779399871826,
      "learning_rate": 1.4748799946626769e-05,
      "loss": 0.5223,
      "step": 22365
    },
    {
      "epoch": 0.6870641722729088,
      "grad_norm": 0.3741704523563385,
      "learning_rate": 1.4748374632590055e-05,
      "loss": 0.6011,
      "step": 22366
    },
    {
      "epoch": 0.687094891407858,
      "grad_norm": 0.3747040927410126,
      "learning_rate": 1.4747949307463179e-05,
      "loss": 0.6059,
      "step": 22367
    },
    {
      "epoch": 0.6871256105428071,
      "grad_norm": 0.43832188844680786,
      "learning_rate": 1.4747523971247136e-05,
      "loss": 0.5371,
      "step": 22368
    },
    {
      "epoch": 0.6871563296777563,
      "grad_norm": 0.31273186206817627,
      "learning_rate": 1.474709862394292e-05,
      "loss": 0.4413,
      "step": 22369
    },
    {
      "epoch": 0.6871870488127054,
      "grad_norm": 0.5333507657051086,
      "learning_rate": 1.474667326555152e-05,
      "loss": 0.5738,
      "step": 22370
    },
    {
      "epoch": 0.6872177679476545,
      "grad_norm": 0.37260785698890686,
      "learning_rate": 1.474624789607394e-05,
      "loss": 0.5573,
      "step": 22371
    },
    {
      "epoch": 0.6872484870826038,
      "grad_norm": 0.3530086278915405,
      "learning_rate": 1.474582251551116e-05,
      "loss": 0.5542,
      "step": 22372
    },
    {
      "epoch": 0.6872792062175529,
      "grad_norm": 0.3579792082309723,
      "learning_rate": 1.4745397123864184e-05,
      "loss": 0.5868,
      "step": 22373
    },
    {
      "epoch": 0.6873099253525021,
      "grad_norm": 0.5266643166542053,
      "learning_rate": 1.4744971721134001e-05,
      "loss": 0.5519,
      "step": 22374
    },
    {
      "epoch": 0.6873406444874512,
      "grad_norm": 0.37177756428718567,
      "learning_rate": 1.4744546307321602e-05,
      "loss": 0.6035,
      "step": 22375
    },
    {
      "epoch": 0.6873713636224004,
      "grad_norm": 0.4077036678791046,
      "learning_rate": 1.4744120882427986e-05,
      "loss": 0.5275,
      "step": 22376
    },
    {
      "epoch": 0.6874020827573496,
      "grad_norm": 0.3727896809577942,
      "learning_rate": 1.4743695446454145e-05,
      "loss": 0.6031,
      "step": 22377
    },
    {
      "epoch": 0.6874328018922987,
      "grad_norm": 0.39038312435150146,
      "learning_rate": 1.4743269999401073e-05,
      "loss": 0.543,
      "step": 22378
    },
    {
      "epoch": 0.6874635210272478,
      "grad_norm": 0.37423965334892273,
      "learning_rate": 1.474284454126976e-05,
      "loss": 0.6125,
      "step": 22379
    },
    {
      "epoch": 0.6874942401621971,
      "grad_norm": 0.39887017011642456,
      "learning_rate": 1.4742419072061204e-05,
      "loss": 0.533,
      "step": 22380
    },
    {
      "epoch": 0.6875249592971462,
      "grad_norm": 0.33520635962486267,
      "learning_rate": 1.4741993591776395e-05,
      "loss": 0.566,
      "step": 22381
    },
    {
      "epoch": 0.6875556784320953,
      "grad_norm": 0.36356282234191895,
      "learning_rate": 1.4741568100416332e-05,
      "loss": 0.5403,
      "step": 22382
    },
    {
      "epoch": 0.6875863975670445,
      "grad_norm": 0.36575838923454285,
      "learning_rate": 1.4741142597982003e-05,
      "loss": 0.5699,
      "step": 22383
    },
    {
      "epoch": 0.6876171167019937,
      "grad_norm": 0.36901339888572693,
      "learning_rate": 1.4740717084474407e-05,
      "loss": 0.5662,
      "step": 22384
    },
    {
      "epoch": 0.6876478358369428,
      "grad_norm": 0.3753169775009155,
      "learning_rate": 1.4740291559894533e-05,
      "loss": 0.5556,
      "step": 22385
    },
    {
      "epoch": 0.687678554971892,
      "grad_norm": 0.3644852042198181,
      "learning_rate": 1.4739866024243377e-05,
      "loss": 0.5332,
      "step": 22386
    },
    {
      "epoch": 0.6877092741068411,
      "grad_norm": 0.3406446874141693,
      "learning_rate": 1.4739440477521933e-05,
      "loss": 0.5407,
      "step": 22387
    },
    {
      "epoch": 0.6877399932417904,
      "grad_norm": 0.34284546971321106,
      "learning_rate": 1.4739014919731196e-05,
      "loss": 0.5613,
      "step": 22388
    },
    {
      "epoch": 0.6877707123767395,
      "grad_norm": 0.3722798526287079,
      "learning_rate": 1.4738589350872156e-05,
      "loss": 0.5416,
      "step": 22389
    },
    {
      "epoch": 0.6878014315116886,
      "grad_norm": 0.33350932598114014,
      "learning_rate": 1.4738163770945813e-05,
      "loss": 0.5595,
      "step": 22390
    },
    {
      "epoch": 0.6878321506466378,
      "grad_norm": 0.3624928891658783,
      "learning_rate": 1.4737738179953156e-05,
      "loss": 0.5203,
      "step": 22391
    },
    {
      "epoch": 0.687862869781587,
      "grad_norm": 0.36742350459098816,
      "learning_rate": 1.473731257789518e-05,
      "loss": 0.5475,
      "step": 22392
    },
    {
      "epoch": 0.6878935889165361,
      "grad_norm": 0.34641027450561523,
      "learning_rate": 1.4736886964772881e-05,
      "loss": 0.6441,
      "step": 22393
    },
    {
      "epoch": 0.6879243080514853,
      "grad_norm": 0.42731547355651855,
      "learning_rate": 1.4736461340587247e-05,
      "loss": 0.5197,
      "step": 22394
    },
    {
      "epoch": 0.6879550271864344,
      "grad_norm": 0.37275049090385437,
      "learning_rate": 1.4736035705339282e-05,
      "loss": 0.4977,
      "step": 22395
    },
    {
      "epoch": 0.6879857463213835,
      "grad_norm": 0.3233494162559509,
      "learning_rate": 1.4735610059029974e-05,
      "loss": 0.5202,
      "step": 22396
    },
    {
      "epoch": 0.6880164654563328,
      "grad_norm": 0.4228224456310272,
      "learning_rate": 1.4735184401660317e-05,
      "loss": 0.5778,
      "step": 22397
    },
    {
      "epoch": 0.6880471845912819,
      "grad_norm": 0.38391566276550293,
      "learning_rate": 1.473475873323131e-05,
      "loss": 0.5191,
      "step": 22398
    },
    {
      "epoch": 0.6880779037262311,
      "grad_norm": 0.3771548569202423,
      "learning_rate": 1.4734333053743936e-05,
      "loss": 0.5421,
      "step": 22399
    },
    {
      "epoch": 0.6881086228611802,
      "grad_norm": 0.3270934224128723,
      "learning_rate": 1.4733907363199202e-05,
      "loss": 0.5733,
      "step": 22400
    },
    {
      "epoch": 0.6881393419961294,
      "grad_norm": 0.3983690142631531,
      "learning_rate": 1.4733481661598094e-05,
      "loss": 0.533,
      "step": 22401
    },
    {
      "epoch": 0.6881700611310786,
      "grad_norm": 0.3734649419784546,
      "learning_rate": 1.473305594894161e-05,
      "loss": 0.5793,
      "step": 22402
    },
    {
      "epoch": 0.6882007802660277,
      "grad_norm": 0.34604260325431824,
      "learning_rate": 1.4732630225230744e-05,
      "loss": 0.4953,
      "step": 22403
    },
    {
      "epoch": 0.6882314994009768,
      "grad_norm": 0.42020168900489807,
      "learning_rate": 1.473220449046649e-05,
      "loss": 0.5222,
      "step": 22404
    },
    {
      "epoch": 0.6882622185359261,
      "grad_norm": 0.3245352804660797,
      "learning_rate": 1.473177874464984e-05,
      "loss": 0.5263,
      "step": 22405
    },
    {
      "epoch": 0.6882929376708752,
      "grad_norm": 0.46783024072647095,
      "learning_rate": 1.4731352987781793e-05,
      "loss": 0.4438,
      "step": 22406
    },
    {
      "epoch": 0.6883236568058243,
      "grad_norm": 0.3699895739555359,
      "learning_rate": 1.4730927219863338e-05,
      "loss": 0.482,
      "step": 22407
    },
    {
      "epoch": 0.6883543759407735,
      "grad_norm": 0.36012160778045654,
      "learning_rate": 1.4730501440895472e-05,
      "loss": 0.5542,
      "step": 22408
    },
    {
      "epoch": 0.6883850950757227,
      "grad_norm": 0.6355479955673218,
      "learning_rate": 1.4730075650879192e-05,
      "loss": 0.6191,
      "step": 22409
    },
    {
      "epoch": 0.6884158142106718,
      "grad_norm": 0.34529560804367065,
      "learning_rate": 1.4729649849815489e-05,
      "loss": 0.5903,
      "step": 22410
    },
    {
      "epoch": 0.688446533345621,
      "grad_norm": 0.37414464354515076,
      "learning_rate": 1.4729224037705358e-05,
      "loss": 0.5932,
      "step": 22411
    },
    {
      "epoch": 0.6884772524805701,
      "grad_norm": 0.3626275956630707,
      "learning_rate": 1.4728798214549793e-05,
      "loss": 0.5665,
      "step": 22412
    },
    {
      "epoch": 0.6885079716155194,
      "grad_norm": 0.5061477422714233,
      "learning_rate": 1.4728372380349789e-05,
      "loss": 0.5599,
      "step": 22413
    },
    {
      "epoch": 0.6885386907504685,
      "grad_norm": 0.35348477959632874,
      "learning_rate": 1.4727946535106343e-05,
      "loss": 0.5862,
      "step": 22414
    },
    {
      "epoch": 0.6885694098854176,
      "grad_norm": 0.416599303483963,
      "learning_rate": 1.4727520678820446e-05,
      "loss": 0.5552,
      "step": 22415
    },
    {
      "epoch": 0.6886001290203668,
      "grad_norm": 0.382624089717865,
      "learning_rate": 1.4727094811493097e-05,
      "loss": 0.5434,
      "step": 22416
    },
    {
      "epoch": 0.6886308481553159,
      "grad_norm": 0.38113531470298767,
      "learning_rate": 1.4726668933125286e-05,
      "loss": 0.5368,
      "step": 22417
    },
    {
      "epoch": 0.6886615672902651,
      "grad_norm": 0.33062174916267395,
      "learning_rate": 1.4726243043718009e-05,
      "loss": 0.5089,
      "step": 22418
    },
    {
      "epoch": 0.6886922864252143,
      "grad_norm": 0.4165412187576294,
      "learning_rate": 1.4725817143272262e-05,
      "loss": 0.6295,
      "step": 22419
    },
    {
      "epoch": 0.6887230055601634,
      "grad_norm": 0.4092147946357727,
      "learning_rate": 1.472539123178904e-05,
      "loss": 0.6866,
      "step": 22420
    },
    {
      "epoch": 0.6887537246951125,
      "grad_norm": 0.4185231328010559,
      "learning_rate": 1.4724965309269337e-05,
      "loss": 0.6615,
      "step": 22421
    },
    {
      "epoch": 0.6887844438300618,
      "grad_norm": 0.38640981912612915,
      "learning_rate": 1.4724539375714147e-05,
      "loss": 0.6161,
      "step": 22422
    },
    {
      "epoch": 0.6888151629650109,
      "grad_norm": 0.32950088381767273,
      "learning_rate": 1.4724113431124465e-05,
      "loss": 0.4975,
      "step": 22423
    },
    {
      "epoch": 0.6888458820999601,
      "grad_norm": 0.39729154109954834,
      "learning_rate": 1.4723687475501285e-05,
      "loss": 0.5964,
      "step": 22424
    },
    {
      "epoch": 0.6888766012349092,
      "grad_norm": 0.5031489133834839,
      "learning_rate": 1.4723261508845606e-05,
      "loss": 0.6257,
      "step": 22425
    },
    {
      "epoch": 0.6889073203698584,
      "grad_norm": 0.36117419600486755,
      "learning_rate": 1.4722835531158416e-05,
      "loss": 0.5753,
      "step": 22426
    },
    {
      "epoch": 0.6889380395048076,
      "grad_norm": 0.38206082582473755,
      "learning_rate": 1.4722409542440717e-05,
      "loss": 0.5541,
      "step": 22427
    },
    {
      "epoch": 0.6889687586397567,
      "grad_norm": 0.37291306257247925,
      "learning_rate": 1.4721983542693497e-05,
      "loss": 0.5927,
      "step": 22428
    },
    {
      "epoch": 0.6889994777747058,
      "grad_norm": 0.3247329592704773,
      "learning_rate": 1.4721557531917759e-05,
      "loss": 0.5214,
      "step": 22429
    },
    {
      "epoch": 0.6890301969096551,
      "grad_norm": 0.35901784896850586,
      "learning_rate": 1.472113151011449e-05,
      "loss": 0.5397,
      "step": 22430
    },
    {
      "epoch": 0.6890609160446042,
      "grad_norm": 0.3870009779930115,
      "learning_rate": 1.4720705477284688e-05,
      "loss": 0.4573,
      "step": 22431
    },
    {
      "epoch": 0.6890916351795533,
      "grad_norm": 0.3321213126182556,
      "learning_rate": 1.4720279433429354e-05,
      "loss": 0.4979,
      "step": 22432
    },
    {
      "epoch": 0.6891223543145025,
      "grad_norm": 0.3658146858215332,
      "learning_rate": 1.4719853378549474e-05,
      "loss": 0.5717,
      "step": 22433
    },
    {
      "epoch": 0.6891530734494516,
      "grad_norm": 0.3413306474685669,
      "learning_rate": 1.4719427312646048e-05,
      "loss": 0.6051,
      "step": 22434
    },
    {
      "epoch": 0.6891837925844009,
      "grad_norm": 0.5235626697540283,
      "learning_rate": 1.4719001235720067e-05,
      "loss": 0.6196,
      "step": 22435
    },
    {
      "epoch": 0.68921451171935,
      "grad_norm": 0.4190088212490082,
      "learning_rate": 1.4718575147772534e-05,
      "loss": 0.6052,
      "step": 22436
    },
    {
      "epoch": 0.6892452308542991,
      "grad_norm": 0.3714768588542938,
      "learning_rate": 1.4718149048804435e-05,
      "loss": 0.605,
      "step": 22437
    },
    {
      "epoch": 0.6892759499892483,
      "grad_norm": 0.3650296628475189,
      "learning_rate": 1.4717722938816772e-05,
      "loss": 0.5053,
      "step": 22438
    },
    {
      "epoch": 0.6893066691241975,
      "grad_norm": 0.3445107638835907,
      "learning_rate": 1.4717296817810535e-05,
      "loss": 0.5426,
      "step": 22439
    },
    {
      "epoch": 0.6893373882591466,
      "grad_norm": 0.31515902280807495,
      "learning_rate": 1.4716870685786727e-05,
      "loss": 0.5096,
      "step": 22440
    },
    {
      "epoch": 0.6893681073940958,
      "grad_norm": 0.4794255793094635,
      "learning_rate": 1.4716444542746335e-05,
      "loss": 0.585,
      "step": 22441
    },
    {
      "epoch": 0.6893988265290449,
      "grad_norm": 0.3724626302719116,
      "learning_rate": 1.4716018388690353e-05,
      "loss": 0.5421,
      "step": 22442
    },
    {
      "epoch": 0.6894295456639941,
      "grad_norm": 0.36503490805625916,
      "learning_rate": 1.4715592223619788e-05,
      "loss": 0.5692,
      "step": 22443
    },
    {
      "epoch": 0.6894602647989433,
      "grad_norm": 0.3977644145488739,
      "learning_rate": 1.4715166047535622e-05,
      "loss": 0.6244,
      "step": 22444
    },
    {
      "epoch": 0.6894909839338924,
      "grad_norm": 0.3643122911453247,
      "learning_rate": 1.4714739860438863e-05,
      "loss": 0.4547,
      "step": 22445
    },
    {
      "epoch": 0.6895217030688415,
      "grad_norm": 0.41290467977523804,
      "learning_rate": 1.4714313662330492e-05,
      "loss": 0.494,
      "step": 22446
    },
    {
      "epoch": 0.6895524222037908,
      "grad_norm": 0.3722561001777649,
      "learning_rate": 1.4713887453211517e-05,
      "loss": 0.5384,
      "step": 22447
    },
    {
      "epoch": 0.6895831413387399,
      "grad_norm": 0.36090177297592163,
      "learning_rate": 1.4713461233082929e-05,
      "loss": 0.5796,
      "step": 22448
    },
    {
      "epoch": 0.6896138604736891,
      "grad_norm": 0.37591812014579773,
      "learning_rate": 1.471303500194572e-05,
      "loss": 0.5929,
      "step": 22449
    },
    {
      "epoch": 0.6896445796086382,
      "grad_norm": 0.3979642391204834,
      "learning_rate": 1.471260875980089e-05,
      "loss": 0.6125,
      "step": 22450
    },
    {
      "epoch": 0.6896752987435874,
      "grad_norm": 0.3705897927284241,
      "learning_rate": 1.4712182506649432e-05,
      "loss": 0.6706,
      "step": 22451
    },
    {
      "epoch": 0.6897060178785366,
      "grad_norm": 0.3809659481048584,
      "learning_rate": 1.4711756242492348e-05,
      "loss": 0.6062,
      "step": 22452
    },
    {
      "epoch": 0.6897367370134857,
      "grad_norm": 0.33459922671318054,
      "learning_rate": 1.4711329967330623e-05,
      "loss": 0.5582,
      "step": 22453
    },
    {
      "epoch": 0.6897674561484348,
      "grad_norm": 0.4103931188583374,
      "learning_rate": 1.4710903681165261e-05,
      "loss": 0.6159,
      "step": 22454
    },
    {
      "epoch": 0.689798175283384,
      "grad_norm": 0.3766176104545593,
      "learning_rate": 1.471047738399725e-05,
      "loss": 0.5685,
      "step": 22455
    },
    {
      "epoch": 0.6898288944183332,
      "grad_norm": 0.36424872279167175,
      "learning_rate": 1.4710051075827593e-05,
      "loss": 0.5453,
      "step": 22456
    },
    {
      "epoch": 0.6898596135532823,
      "grad_norm": 0.3448154926300049,
      "learning_rate": 1.470962475665728e-05,
      "loss": 0.565,
      "step": 22457
    },
    {
      "epoch": 0.6898903326882315,
      "grad_norm": 0.40862980484962463,
      "learning_rate": 1.4709198426487314e-05,
      "loss": 0.5954,
      "step": 22458
    },
    {
      "epoch": 0.6899210518231806,
      "grad_norm": 0.3622902035713196,
      "learning_rate": 1.4708772085318685e-05,
      "loss": 0.5507,
      "step": 22459
    },
    {
      "epoch": 0.6899517709581299,
      "grad_norm": 0.3741076588630676,
      "learning_rate": 1.4708345733152389e-05,
      "loss": 0.6218,
      "step": 22460
    },
    {
      "epoch": 0.689982490093079,
      "grad_norm": 0.41968396306037903,
      "learning_rate": 1.4707919369989423e-05,
      "loss": 0.5705,
      "step": 22461
    },
    {
      "epoch": 0.6900132092280281,
      "grad_norm": 0.6588703393936157,
      "learning_rate": 1.4707492995830784e-05,
      "loss": 0.5694,
      "step": 22462
    },
    {
      "epoch": 0.6900439283629773,
      "grad_norm": 0.36038774251937866,
      "learning_rate": 1.4707066610677464e-05,
      "loss": 0.5875,
      "step": 22463
    },
    {
      "epoch": 0.6900746474979265,
      "grad_norm": 0.4661013185977936,
      "learning_rate": 1.470664021453046e-05,
      "loss": 0.5682,
      "step": 22464
    },
    {
      "epoch": 0.6901053666328756,
      "grad_norm": 0.3658093214035034,
      "learning_rate": 1.4706213807390772e-05,
      "loss": 0.5843,
      "step": 22465
    },
    {
      "epoch": 0.6901360857678248,
      "grad_norm": 0.34051448106765747,
      "learning_rate": 1.4705787389259392e-05,
      "loss": 0.588,
      "step": 22466
    },
    {
      "epoch": 0.6901668049027739,
      "grad_norm": 0.3446017801761627,
      "learning_rate": 1.4705360960137316e-05,
      "loss": 0.5528,
      "step": 22467
    },
    {
      "epoch": 0.690197524037723,
      "grad_norm": 0.3833146393299103,
      "learning_rate": 1.4704934520025543e-05,
      "loss": 0.5567,
      "step": 22468
    },
    {
      "epoch": 0.6902282431726723,
      "grad_norm": 0.37998130917549133,
      "learning_rate": 1.4704508068925063e-05,
      "loss": 0.5044,
      "step": 22469
    },
    {
      "epoch": 0.6902589623076214,
      "grad_norm": 0.3520967960357666,
      "learning_rate": 1.470408160683688e-05,
      "loss": 0.542,
      "step": 22470
    },
    {
      "epoch": 0.6902896814425705,
      "grad_norm": 0.34321096539497375,
      "learning_rate": 1.4703655133761982e-05,
      "loss": 0.5128,
      "step": 22471
    },
    {
      "epoch": 0.6903204005775198,
      "grad_norm": 0.34290727972984314,
      "learning_rate": 1.4703228649701374e-05,
      "loss": 0.5452,
      "step": 22472
    },
    {
      "epoch": 0.6903511197124689,
      "grad_norm": 0.32775747776031494,
      "learning_rate": 1.4702802154656044e-05,
      "loss": 0.5196,
      "step": 22473
    },
    {
      "epoch": 0.6903818388474181,
      "grad_norm": 0.3545583188533783,
      "learning_rate": 1.470237564862699e-05,
      "loss": 0.5062,
      "step": 22474
    },
    {
      "epoch": 0.6904125579823672,
      "grad_norm": 0.37747952342033386,
      "learning_rate": 1.4701949131615211e-05,
      "loss": 0.6614,
      "step": 22475
    },
    {
      "epoch": 0.6904432771173163,
      "grad_norm": 0.36417070031166077,
      "learning_rate": 1.4701522603621702e-05,
      "loss": 0.5551,
      "step": 22476
    },
    {
      "epoch": 0.6904739962522656,
      "grad_norm": 0.36601394414901733,
      "learning_rate": 1.4701096064647458e-05,
      "loss": 0.5547,
      "step": 22477
    },
    {
      "epoch": 0.6905047153872147,
      "grad_norm": 0.3987535834312439,
      "learning_rate": 1.4700669514693475e-05,
      "loss": 0.5157,
      "step": 22478
    },
    {
      "epoch": 0.6905354345221638,
      "grad_norm": 0.37859460711479187,
      "learning_rate": 1.470024295376075e-05,
      "loss": 0.5519,
      "step": 22479
    },
    {
      "epoch": 0.690566153657113,
      "grad_norm": 0.349500834941864,
      "learning_rate": 1.469981638185028e-05,
      "loss": 0.4946,
      "step": 22480
    },
    {
      "epoch": 0.6905968727920622,
      "grad_norm": 0.39733606576919556,
      "learning_rate": 1.4699389798963062e-05,
      "loss": 0.4854,
      "step": 22481
    },
    {
      "epoch": 0.6906275919270113,
      "grad_norm": 0.38659775257110596,
      "learning_rate": 1.4698963205100087e-05,
      "loss": 0.6318,
      "step": 22482
    },
    {
      "epoch": 0.6906583110619605,
      "grad_norm": 0.3505514860153198,
      "learning_rate": 1.4698536600262358e-05,
      "loss": 0.5349,
      "step": 22483
    },
    {
      "epoch": 0.6906890301969096,
      "grad_norm": 0.36934563517570496,
      "learning_rate": 1.4698109984450869e-05,
      "loss": 0.5288,
      "step": 22484
    },
    {
      "epoch": 0.6907197493318589,
      "grad_norm": 0.4001167416572571,
      "learning_rate": 1.4697683357666614e-05,
      "loss": 0.5064,
      "step": 22485
    },
    {
      "epoch": 0.690750468466808,
      "grad_norm": 0.36179304122924805,
      "learning_rate": 1.4697256719910594e-05,
      "loss": 0.5552,
      "step": 22486
    },
    {
      "epoch": 0.6907811876017571,
      "grad_norm": 0.35671380162239075,
      "learning_rate": 1.46968300711838e-05,
      "loss": 0.5151,
      "step": 22487
    },
    {
      "epoch": 0.6908119067367063,
      "grad_norm": 0.3864904046058655,
      "learning_rate": 1.4696403411487234e-05,
      "loss": 0.5231,
      "step": 22488
    },
    {
      "epoch": 0.6908426258716555,
      "grad_norm": 0.3146601915359497,
      "learning_rate": 1.4695976740821887e-05,
      "loss": 0.4916,
      "step": 22489
    },
    {
      "epoch": 0.6908733450066046,
      "grad_norm": 0.3671146631240845,
      "learning_rate": 1.4695550059188762e-05,
      "loss": 0.5271,
      "step": 22490
    },
    {
      "epoch": 0.6909040641415538,
      "grad_norm": 0.35593509674072266,
      "learning_rate": 1.4695123366588848e-05,
      "loss": 0.5725,
      "step": 22491
    },
    {
      "epoch": 0.6909347832765029,
      "grad_norm": 0.35483115911483765,
      "learning_rate": 1.469469666302315e-05,
      "loss": 0.5977,
      "step": 22492
    },
    {
      "epoch": 0.690965502411452,
      "grad_norm": 0.35014358162879944,
      "learning_rate": 1.4694269948492657e-05,
      "loss": 0.5414,
      "step": 22493
    },
    {
      "epoch": 0.6909962215464013,
      "grad_norm": 0.33750632405281067,
      "learning_rate": 1.469384322299837e-05,
      "loss": 0.6034,
      "step": 22494
    },
    {
      "epoch": 0.6910269406813504,
      "grad_norm": 0.39207449555397034,
      "learning_rate": 1.4693416486541283e-05,
      "loss": 0.6193,
      "step": 22495
    },
    {
      "epoch": 0.6910576598162995,
      "grad_norm": 0.3887064456939697,
      "learning_rate": 1.4692989739122394e-05,
      "loss": 0.5891,
      "step": 22496
    },
    {
      "epoch": 0.6910883789512487,
      "grad_norm": 0.4805712103843689,
      "learning_rate": 1.4692562980742702e-05,
      "loss": 0.6063,
      "step": 22497
    },
    {
      "epoch": 0.6911190980861979,
      "grad_norm": 0.3715360164642334,
      "learning_rate": 1.46921362114032e-05,
      "loss": 0.5666,
      "step": 22498
    },
    {
      "epoch": 0.6911498172211471,
      "grad_norm": 0.3495534360408783,
      "learning_rate": 1.4691709431104886e-05,
      "loss": 0.619,
      "step": 22499
    },
    {
      "epoch": 0.6911805363560962,
      "grad_norm": 0.3215441405773163,
      "learning_rate": 1.4691282639848755e-05,
      "loss": 0.5745,
      "step": 22500
    },
    {
      "epoch": 0.6912112554910453,
      "grad_norm": 0.36030057072639465,
      "learning_rate": 1.4690855837635808e-05,
      "loss": 0.5049,
      "step": 22501
    },
    {
      "epoch": 0.6912419746259946,
      "grad_norm": 0.3544063866138458,
      "learning_rate": 1.4690429024467038e-05,
      "loss": 0.5462,
      "step": 22502
    },
    {
      "epoch": 0.6912726937609437,
      "grad_norm": 0.32455918192863464,
      "learning_rate": 1.4690002200343445e-05,
      "loss": 0.4127,
      "step": 22503
    },
    {
      "epoch": 0.6913034128958928,
      "grad_norm": 0.38817670941352844,
      "learning_rate": 1.4689575365266024e-05,
      "loss": 0.5416,
      "step": 22504
    },
    {
      "epoch": 0.691334132030842,
      "grad_norm": 0.34178704023361206,
      "learning_rate": 1.4689148519235772e-05,
      "loss": 0.5777,
      "step": 22505
    },
    {
      "epoch": 0.6913648511657912,
      "grad_norm": 0.3447449207305908,
      "learning_rate": 1.4688721662253687e-05,
      "loss": 0.5994,
      "step": 22506
    },
    {
      "epoch": 0.6913955703007403,
      "grad_norm": 0.36484840512275696,
      "learning_rate": 1.4688294794320764e-05,
      "loss": 0.5322,
      "step": 22507
    },
    {
      "epoch": 0.6914262894356895,
      "grad_norm": 0.36023157835006714,
      "learning_rate": 1.4687867915438002e-05,
      "loss": 0.5327,
      "step": 22508
    },
    {
      "epoch": 0.6914570085706386,
      "grad_norm": 0.3442690968513489,
      "learning_rate": 1.4687441025606395e-05,
      "loss": 0.5063,
      "step": 22509
    },
    {
      "epoch": 0.6914877277055879,
      "grad_norm": 0.34606507420539856,
      "learning_rate": 1.4687014124826946e-05,
      "loss": 0.6503,
      "step": 22510
    },
    {
      "epoch": 0.691518446840537,
      "grad_norm": 0.407153457403183,
      "learning_rate": 1.4686587213100647e-05,
      "loss": 0.5836,
      "step": 22511
    },
    {
      "epoch": 0.6915491659754861,
      "grad_norm": 0.34317201375961304,
      "learning_rate": 1.4686160290428493e-05,
      "loss": 0.5248,
      "step": 22512
    },
    {
      "epoch": 0.6915798851104353,
      "grad_norm": 0.4040686786174774,
      "learning_rate": 1.4685733356811488e-05,
      "loss": 0.5582,
      "step": 22513
    },
    {
      "epoch": 0.6916106042453845,
      "grad_norm": 0.39815759658813477,
      "learning_rate": 1.4685306412250623e-05,
      "loss": 0.4964,
      "step": 22514
    },
    {
      "epoch": 0.6916413233803336,
      "grad_norm": 0.32357627153396606,
      "learning_rate": 1.4684879456746899e-05,
      "loss": 0.466,
      "step": 22515
    },
    {
      "epoch": 0.6916720425152828,
      "grad_norm": 0.3549063503742218,
      "learning_rate": 1.4684452490301312e-05,
      "loss": 0.4976,
      "step": 22516
    },
    {
      "epoch": 0.6917027616502319,
      "grad_norm": 0.36181050539016724,
      "learning_rate": 1.4684025512914859e-05,
      "loss": 0.5323,
      "step": 22517
    },
    {
      "epoch": 0.691733480785181,
      "grad_norm": 0.3314193785190582,
      "learning_rate": 1.4683598524588537e-05,
      "loss": 0.5433,
      "step": 22518
    },
    {
      "epoch": 0.6917641999201303,
      "grad_norm": 0.33947011828422546,
      "learning_rate": 1.4683171525323343e-05,
      "loss": 0.5855,
      "step": 22519
    },
    {
      "epoch": 0.6917949190550794,
      "grad_norm": 0.4131937325000763,
      "learning_rate": 1.4682744515120276e-05,
      "loss": 0.5967,
      "step": 22520
    },
    {
      "epoch": 0.6918256381900285,
      "grad_norm": 0.3657763600349426,
      "learning_rate": 1.468231749398033e-05,
      "loss": 0.5616,
      "step": 22521
    },
    {
      "epoch": 0.6918563573249777,
      "grad_norm": 0.3908522427082062,
      "learning_rate": 1.4681890461904505e-05,
      "loss": 0.6054,
      "step": 22522
    },
    {
      "epoch": 0.6918870764599269,
      "grad_norm": 0.3501698970794678,
      "learning_rate": 1.4681463418893799e-05,
      "loss": 0.5656,
      "step": 22523
    },
    {
      "epoch": 0.6919177955948761,
      "grad_norm": 0.3811292052268982,
      "learning_rate": 1.4681036364949208e-05,
      "loss": 0.523,
      "step": 22524
    },
    {
      "epoch": 0.6919485147298252,
      "grad_norm": 0.41629523038864136,
      "learning_rate": 1.468060930007173e-05,
      "loss": 0.594,
      "step": 22525
    },
    {
      "epoch": 0.6919792338647743,
      "grad_norm": 0.37718406319618225,
      "learning_rate": 1.468018222426236e-05,
      "loss": 0.5789,
      "step": 22526
    },
    {
      "epoch": 0.6920099529997236,
      "grad_norm": 0.3482378423213959,
      "learning_rate": 1.4679755137522102e-05,
      "loss": 0.5183,
      "step": 22527
    },
    {
      "epoch": 0.6920406721346727,
      "grad_norm": 0.37830743193626404,
      "learning_rate": 1.4679328039851945e-05,
      "loss": 0.575,
      "step": 22528
    },
    {
      "epoch": 0.6920713912696218,
      "grad_norm": 0.4054834544658661,
      "learning_rate": 1.4678900931252892e-05,
      "loss": 0.6109,
      "step": 22529
    },
    {
      "epoch": 0.692102110404571,
      "grad_norm": 0.36062583327293396,
      "learning_rate": 1.4678473811725939e-05,
      "loss": 0.4959,
      "step": 22530
    },
    {
      "epoch": 0.6921328295395202,
      "grad_norm": 0.3512282967567444,
      "learning_rate": 1.4678046681272084e-05,
      "loss": 0.5233,
      "step": 22531
    },
    {
      "epoch": 0.6921635486744693,
      "grad_norm": 0.36497050523757935,
      "learning_rate": 1.4677619539892323e-05,
      "loss": 0.5708,
      "step": 22532
    },
    {
      "epoch": 0.6921942678094185,
      "grad_norm": 0.3306076228618622,
      "learning_rate": 1.4677192387587657e-05,
      "loss": 0.4927,
      "step": 22533
    },
    {
      "epoch": 0.6922249869443676,
      "grad_norm": 0.43176382780075073,
      "learning_rate": 1.467676522435908e-05,
      "loss": 0.4998,
      "step": 22534
    },
    {
      "epoch": 0.6922557060793169,
      "grad_norm": 0.3248539865016937,
      "learning_rate": 1.4676338050207593e-05,
      "loss": 0.5084,
      "step": 22535
    },
    {
      "epoch": 0.692286425214266,
      "grad_norm": 0.38297298550605774,
      "learning_rate": 1.4675910865134189e-05,
      "loss": 0.5661,
      "step": 22536
    },
    {
      "epoch": 0.6923171443492151,
      "grad_norm": 0.3519614040851593,
      "learning_rate": 1.467548366913987e-05,
      "loss": 0.5414,
      "step": 22537
    },
    {
      "epoch": 0.6923478634841643,
      "grad_norm": 0.3854628801345825,
      "learning_rate": 1.4675056462225633e-05,
      "loss": 0.587,
      "step": 22538
    },
    {
      "epoch": 0.6923785826191134,
      "grad_norm": 0.337139368057251,
      "learning_rate": 1.4674629244392473e-05,
      "loss": 0.596,
      "step": 22539
    },
    {
      "epoch": 0.6924093017540626,
      "grad_norm": 0.34613510966300964,
      "learning_rate": 1.467420201564139e-05,
      "loss": 0.5255,
      "step": 22540
    },
    {
      "epoch": 0.6924400208890118,
      "grad_norm": 0.3370524048805237,
      "learning_rate": 1.4673774775973384e-05,
      "loss": 0.5704,
      "step": 22541
    },
    {
      "epoch": 0.6924707400239609,
      "grad_norm": 0.37837934494018555,
      "learning_rate": 1.4673347525389449e-05,
      "loss": 0.5237,
      "step": 22542
    },
    {
      "epoch": 0.69250145915891,
      "grad_norm": 0.3654174208641052,
      "learning_rate": 1.4672920263890587e-05,
      "loss": 0.5441,
      "step": 22543
    },
    {
      "epoch": 0.6925321782938593,
      "grad_norm": 0.4050576686859131,
      "learning_rate": 1.4672492991477791e-05,
      "loss": 0.5638,
      "step": 22544
    },
    {
      "epoch": 0.6925628974288084,
      "grad_norm": 0.3716464936733246,
      "learning_rate": 1.4672065708152064e-05,
      "loss": 0.5198,
      "step": 22545
    },
    {
      "epoch": 0.6925936165637576,
      "grad_norm": 0.40844935178756714,
      "learning_rate": 1.4671638413914397e-05,
      "loss": 0.5508,
      "step": 22546
    },
    {
      "epoch": 0.6926243356987067,
      "grad_norm": 0.32956022024154663,
      "learning_rate": 1.4671211108765794e-05,
      "loss": 0.5552,
      "step": 22547
    },
    {
      "epoch": 0.6926550548336559,
      "grad_norm": 0.39809873700141907,
      "learning_rate": 1.4670783792707253e-05,
      "loss": 0.5297,
      "step": 22548
    },
    {
      "epoch": 0.6926857739686051,
      "grad_norm": 0.43176162242889404,
      "learning_rate": 1.4670356465739767e-05,
      "loss": 0.6391,
      "step": 22549
    },
    {
      "epoch": 0.6927164931035542,
      "grad_norm": 0.3664095401763916,
      "learning_rate": 1.4669929127864339e-05,
      "loss": 0.586,
      "step": 22550
    },
    {
      "epoch": 0.6927472122385033,
      "grad_norm": 0.3541267514228821,
      "learning_rate": 1.4669501779081967e-05,
      "loss": 0.5522,
      "step": 22551
    },
    {
      "epoch": 0.6927779313734526,
      "grad_norm": 0.34257569909095764,
      "learning_rate": 1.4669074419393645e-05,
      "loss": 0.5439,
      "step": 22552
    },
    {
      "epoch": 0.6928086505084017,
      "grad_norm": 0.3385346531867981,
      "learning_rate": 1.4668647048800378e-05,
      "loss": 0.5745,
      "step": 22553
    },
    {
      "epoch": 0.6928393696433508,
      "grad_norm": 0.3551054298877716,
      "learning_rate": 1.4668219667303154e-05,
      "loss": 0.6038,
      "step": 22554
    },
    {
      "epoch": 0.6928700887783,
      "grad_norm": 0.4258062243461609,
      "learning_rate": 1.4667792274902981e-05,
      "loss": 0.5051,
      "step": 22555
    },
    {
      "epoch": 0.6929008079132492,
      "grad_norm": 0.3770347535610199,
      "learning_rate": 1.4667364871600851e-05,
      "loss": 0.552,
      "step": 22556
    },
    {
      "epoch": 0.6929315270481983,
      "grad_norm": 0.44987303018569946,
      "learning_rate": 1.4666937457397766e-05,
      "loss": 0.6039,
      "step": 22557
    },
    {
      "epoch": 0.6929622461831475,
      "grad_norm": 0.3540380597114563,
      "learning_rate": 1.4666510032294718e-05,
      "loss": 0.6019,
      "step": 22558
    },
    {
      "epoch": 0.6929929653180966,
      "grad_norm": 0.34906822443008423,
      "learning_rate": 1.4666082596292712e-05,
      "loss": 0.5306,
      "step": 22559
    },
    {
      "epoch": 0.6930236844530459,
      "grad_norm": 0.3426465690135956,
      "learning_rate": 1.4665655149392749e-05,
      "loss": 0.5237,
      "step": 22560
    },
    {
      "epoch": 0.693054403587995,
      "grad_norm": 0.34698736667633057,
      "learning_rate": 1.4665227691595819e-05,
      "loss": 0.4998,
      "step": 22561
    },
    {
      "epoch": 0.6930851227229441,
      "grad_norm": 0.3700084984302521,
      "learning_rate": 1.4664800222902923e-05,
      "loss": 0.5698,
      "step": 22562
    },
    {
      "epoch": 0.6931158418578933,
      "grad_norm": 0.3820263147354126,
      "learning_rate": 1.4664372743315064e-05,
      "loss": 0.5721,
      "step": 22563
    },
    {
      "epoch": 0.6931465609928424,
      "grad_norm": 0.3521619439125061,
      "learning_rate": 1.4663945252833231e-05,
      "loss": 0.5731,
      "step": 22564
    },
    {
      "epoch": 0.6931772801277916,
      "grad_norm": 0.3536050021648407,
      "learning_rate": 1.4663517751458431e-05,
      "loss": 0.5496,
      "step": 22565
    },
    {
      "epoch": 0.6932079992627408,
      "grad_norm": 0.340120792388916,
      "learning_rate": 1.466309023919166e-05,
      "loss": 0.5224,
      "step": 22566
    },
    {
      "epoch": 0.6932387183976899,
      "grad_norm": 0.362618088722229,
      "learning_rate": 1.4662662716033917e-05,
      "loss": 0.5888,
      "step": 22567
    },
    {
      "epoch": 0.693269437532639,
      "grad_norm": 0.3578249216079712,
      "learning_rate": 1.4662235181986197e-05,
      "loss": 0.5574,
      "step": 22568
    },
    {
      "epoch": 0.6933001566675883,
      "grad_norm": 0.34848397970199585,
      "learning_rate": 1.4661807637049504e-05,
      "loss": 0.508,
      "step": 22569
    },
    {
      "epoch": 0.6933308758025374,
      "grad_norm": 0.34799882769584656,
      "learning_rate": 1.4661380081224832e-05,
      "loss": 0.6142,
      "step": 22570
    },
    {
      "epoch": 0.6933615949374866,
      "grad_norm": 0.3645077049732208,
      "learning_rate": 1.4660952514513182e-05,
      "loss": 0.5519,
      "step": 22571
    },
    {
      "epoch": 0.6933923140724357,
      "grad_norm": 0.41492921113967896,
      "learning_rate": 1.466052493691555e-05,
      "loss": 0.5442,
      "step": 22572
    },
    {
      "epoch": 0.6934230332073849,
      "grad_norm": 0.38530921936035156,
      "learning_rate": 1.466009734843294e-05,
      "loss": 0.5774,
      "step": 22573
    },
    {
      "epoch": 0.6934537523423341,
      "grad_norm": 0.36865004897117615,
      "learning_rate": 1.4659669749066345e-05,
      "loss": 0.5307,
      "step": 22574
    },
    {
      "epoch": 0.6934844714772832,
      "grad_norm": 0.3915439248085022,
      "learning_rate": 1.4659242138816765e-05,
      "loss": 0.536,
      "step": 22575
    },
    {
      "epoch": 0.6935151906122323,
      "grad_norm": 0.390075147151947,
      "learning_rate": 1.46588145176852e-05,
      "loss": 0.5315,
      "step": 22576
    },
    {
      "epoch": 0.6935459097471816,
      "grad_norm": 0.32660725712776184,
      "learning_rate": 1.4658386885672649e-05,
      "loss": 0.5708,
      "step": 22577
    },
    {
      "epoch": 0.6935766288821307,
      "grad_norm": 0.35460761189460754,
      "learning_rate": 1.465795924278011e-05,
      "loss": 0.5565,
      "step": 22578
    },
    {
      "epoch": 0.6936073480170798,
      "grad_norm": 0.43957608938217163,
      "learning_rate": 1.4657531589008583e-05,
      "loss": 0.5815,
      "step": 22579
    },
    {
      "epoch": 0.693638067152029,
      "grad_norm": 0.34490275382995605,
      "learning_rate": 1.4657103924359063e-05,
      "loss": 0.545,
      "step": 22580
    },
    {
      "epoch": 0.6936687862869781,
      "grad_norm": 0.414168119430542,
      "learning_rate": 1.4656676248832555e-05,
      "loss": 0.5657,
      "step": 22581
    },
    {
      "epoch": 0.6936995054219273,
      "grad_norm": 0.5001202821731567,
      "learning_rate": 1.4656248562430051e-05,
      "loss": 0.6548,
      "step": 22582
    },
    {
      "epoch": 0.6937302245568765,
      "grad_norm": 0.6297950148582458,
      "learning_rate": 1.4655820865152555e-05,
      "loss": 0.5864,
      "step": 22583
    },
    {
      "epoch": 0.6937609436918256,
      "grad_norm": 0.377959668636322,
      "learning_rate": 1.4655393157001063e-05,
      "loss": 0.5584,
      "step": 22584
    },
    {
      "epoch": 0.6937916628267748,
      "grad_norm": 0.3610199987888336,
      "learning_rate": 1.4654965437976578e-05,
      "loss": 0.6301,
      "step": 22585
    },
    {
      "epoch": 0.693822381961724,
      "grad_norm": 0.3828895688056946,
      "learning_rate": 1.4654537708080092e-05,
      "loss": 0.5294,
      "step": 22586
    },
    {
      "epoch": 0.6938531010966731,
      "grad_norm": 3.4689910411834717,
      "learning_rate": 1.4654109967312614e-05,
      "loss": 0.4999,
      "step": 22587
    },
    {
      "epoch": 0.6938838202316223,
      "grad_norm": 0.38492006063461304,
      "learning_rate": 1.4653682215675131e-05,
      "loss": 0.5897,
      "step": 22588
    },
    {
      "epoch": 0.6939145393665714,
      "grad_norm": 0.39945968985557556,
      "learning_rate": 1.4653254453168653e-05,
      "loss": 0.5371,
      "step": 22589
    },
    {
      "epoch": 0.6939452585015206,
      "grad_norm": 0.3768009841442108,
      "learning_rate": 1.4652826679794172e-05,
      "loss": 0.6031,
      "step": 22590
    },
    {
      "epoch": 0.6939759776364698,
      "grad_norm": 0.39094969630241394,
      "learning_rate": 1.4652398895552689e-05,
      "loss": 0.5588,
      "step": 22591
    },
    {
      "epoch": 0.6940066967714189,
      "grad_norm": 0.3754323720932007,
      "learning_rate": 1.4651971100445204e-05,
      "loss": 0.5579,
      "step": 22592
    },
    {
      "epoch": 0.694037415906368,
      "grad_norm": 0.363925576210022,
      "learning_rate": 1.4651543294472715e-05,
      "loss": 0.5404,
      "step": 22593
    },
    {
      "epoch": 0.6940681350413173,
      "grad_norm": 0.3391965329647064,
      "learning_rate": 1.465111547763622e-05,
      "loss": 0.513,
      "step": 22594
    },
    {
      "epoch": 0.6940988541762664,
      "grad_norm": 0.3773689866065979,
      "learning_rate": 1.4650687649936722e-05,
      "loss": 0.5075,
      "step": 22595
    },
    {
      "epoch": 0.6941295733112156,
      "grad_norm": 0.3840753436088562,
      "learning_rate": 1.4650259811375219e-05,
      "loss": 0.5683,
      "step": 22596
    },
    {
      "epoch": 0.6941602924461647,
      "grad_norm": 0.4615083634853363,
      "learning_rate": 1.4649831961952709e-05,
      "loss": 0.5693,
      "step": 22597
    },
    {
      "epoch": 0.6941910115811138,
      "grad_norm": 0.37923750281333923,
      "learning_rate": 1.464940410167019e-05,
      "loss": 0.5496,
      "step": 22598
    },
    {
      "epoch": 0.6942217307160631,
      "grad_norm": 0.38672181963920593,
      "learning_rate": 1.4648976230528666e-05,
      "loss": 0.607,
      "step": 22599
    },
    {
      "epoch": 0.6942524498510122,
      "grad_norm": 0.39665624499320984,
      "learning_rate": 1.4648548348529133e-05,
      "loss": 0.5727,
      "step": 22600
    },
    {
      "epoch": 0.6942831689859613,
      "grad_norm": 0.33314213156700134,
      "learning_rate": 1.464812045567259e-05,
      "loss": 0.5076,
      "step": 22601
    },
    {
      "epoch": 0.6943138881209105,
      "grad_norm": 0.3515544533729553,
      "learning_rate": 1.4647692551960035e-05,
      "loss": 0.6,
      "step": 22602
    },
    {
      "epoch": 0.6943446072558597,
      "grad_norm": 0.3775416612625122,
      "learning_rate": 1.4647264637392473e-05,
      "loss": 0.5295,
      "step": 22603
    },
    {
      "epoch": 0.6943753263908088,
      "grad_norm": 0.3529481887817383,
      "learning_rate": 1.4646836711970896e-05,
      "loss": 0.4984,
      "step": 22604
    },
    {
      "epoch": 0.694406045525758,
      "grad_norm": 0.3400987982749939,
      "learning_rate": 1.464640877569631e-05,
      "loss": 0.6149,
      "step": 22605
    },
    {
      "epoch": 0.6944367646607071,
      "grad_norm": 0.35183417797088623,
      "learning_rate": 1.464598082856971e-05,
      "loss": 0.5823,
      "step": 22606
    },
    {
      "epoch": 0.6944674837956563,
      "grad_norm": 0.3908868432044983,
      "learning_rate": 1.46455528705921e-05,
      "loss": 0.5019,
      "step": 22607
    },
    {
      "epoch": 0.6944982029306055,
      "grad_norm": 0.3601454794406891,
      "learning_rate": 1.4645124901764476e-05,
      "loss": 0.5654,
      "step": 22608
    },
    {
      "epoch": 0.6945289220655546,
      "grad_norm": 0.3777960538864136,
      "learning_rate": 1.4644696922087835e-05,
      "loss": 0.5624,
      "step": 22609
    },
    {
      "epoch": 0.6945596412005038,
      "grad_norm": 0.36064577102661133,
      "learning_rate": 1.4644268931563183e-05,
      "loss": 0.519,
      "step": 22610
    },
    {
      "epoch": 0.694590360335453,
      "grad_norm": 0.3440132141113281,
      "learning_rate": 1.4643840930191514e-05,
      "loss": 0.5612,
      "step": 22611
    },
    {
      "epoch": 0.6946210794704021,
      "grad_norm": 0.36056798696517944,
      "learning_rate": 1.4643412917973836e-05,
      "loss": 0.5336,
      "step": 22612
    },
    {
      "epoch": 0.6946517986053513,
      "grad_norm": 0.3198976516723633,
      "learning_rate": 1.4642984894911137e-05,
      "loss": 0.522,
      "step": 22613
    },
    {
      "epoch": 0.6946825177403004,
      "grad_norm": 0.3693627715110779,
      "learning_rate": 1.4642556861004424e-05,
      "loss": 0.5736,
      "step": 22614
    },
    {
      "epoch": 0.6947132368752496,
      "grad_norm": 0.38909587264060974,
      "learning_rate": 1.4642128816254697e-05,
      "loss": 0.6043,
      "step": 22615
    },
    {
      "epoch": 0.6947439560101988,
      "grad_norm": 0.3908487558364868,
      "learning_rate": 1.4641700760662952e-05,
      "loss": 0.5861,
      "step": 22616
    },
    {
      "epoch": 0.6947746751451479,
      "grad_norm": 0.38308629393577576,
      "learning_rate": 1.4641272694230192e-05,
      "loss": 0.6003,
      "step": 22617
    },
    {
      "epoch": 0.694805394280097,
      "grad_norm": 0.3647722899913788,
      "learning_rate": 1.4640844616957415e-05,
      "loss": 0.5829,
      "step": 22618
    },
    {
      "epoch": 0.6948361134150463,
      "grad_norm": 0.36078202724456787,
      "learning_rate": 1.464041652884562e-05,
      "loss": 0.579,
      "step": 22619
    },
    {
      "epoch": 0.6948668325499954,
      "grad_norm": 0.3492617607116699,
      "learning_rate": 1.463998842989581e-05,
      "loss": 0.572,
      "step": 22620
    },
    {
      "epoch": 0.6948975516849446,
      "grad_norm": 0.41127699613571167,
      "learning_rate": 1.4639560320108982e-05,
      "loss": 0.5581,
      "step": 22621
    },
    {
      "epoch": 0.6949282708198937,
      "grad_norm": 0.4190850257873535,
      "learning_rate": 1.4639132199486137e-05,
      "loss": 0.5591,
      "step": 22622
    },
    {
      "epoch": 0.6949589899548428,
      "grad_norm": 0.3685346841812134,
      "learning_rate": 1.4638704068028276e-05,
      "loss": 0.5567,
      "step": 22623
    },
    {
      "epoch": 0.6949897090897921,
      "grad_norm": 0.33703821897506714,
      "learning_rate": 1.4638275925736396e-05,
      "loss": 0.5537,
      "step": 22624
    },
    {
      "epoch": 0.6950204282247412,
      "grad_norm": 0.3973979353904724,
      "learning_rate": 1.46378477726115e-05,
      "loss": 0.574,
      "step": 22625
    },
    {
      "epoch": 0.6950511473596903,
      "grad_norm": 0.3690866231918335,
      "learning_rate": 1.4637419608654586e-05,
      "loss": 0.5562,
      "step": 22626
    },
    {
      "epoch": 0.6950818664946395,
      "grad_norm": 0.4480339586734772,
      "learning_rate": 1.4636991433866655e-05,
      "loss": 0.5726,
      "step": 22627
    },
    {
      "epoch": 0.6951125856295887,
      "grad_norm": 0.40986064076423645,
      "learning_rate": 1.4636563248248704e-05,
      "loss": 0.5311,
      "step": 22628
    },
    {
      "epoch": 0.6951433047645378,
      "grad_norm": 0.33583909273147583,
      "learning_rate": 1.463613505180174e-05,
      "loss": 0.5422,
      "step": 22629
    },
    {
      "epoch": 0.695174023899487,
      "grad_norm": 0.4453539252281189,
      "learning_rate": 1.4635706844526757e-05,
      "loss": 0.5664,
      "step": 22630
    },
    {
      "epoch": 0.6952047430344361,
      "grad_norm": 0.37374526262283325,
      "learning_rate": 1.4635278626424754e-05,
      "loss": 0.6012,
      "step": 22631
    },
    {
      "epoch": 0.6952354621693854,
      "grad_norm": 0.40841931104660034,
      "learning_rate": 1.4634850397496739e-05,
      "loss": 0.634,
      "step": 22632
    },
    {
      "epoch": 0.6952661813043345,
      "grad_norm": 0.3801027834415436,
      "learning_rate": 1.4634422157743703e-05,
      "loss": 0.5034,
      "step": 22633
    },
    {
      "epoch": 0.6952969004392836,
      "grad_norm": 0.374788373708725,
      "learning_rate": 1.4633993907166652e-05,
      "loss": 0.6216,
      "step": 22634
    },
    {
      "epoch": 0.6953276195742328,
      "grad_norm": 0.43774136900901794,
      "learning_rate": 1.4633565645766585e-05,
      "loss": 0.5648,
      "step": 22635
    },
    {
      "epoch": 0.695358338709182,
      "grad_norm": 0.8645035028457642,
      "learning_rate": 1.4633137373544501e-05,
      "loss": 0.5345,
      "step": 22636
    },
    {
      "epoch": 0.6953890578441311,
      "grad_norm": 0.3564022183418274,
      "learning_rate": 1.4632709090501402e-05,
      "loss": 0.5277,
      "step": 22637
    },
    {
      "epoch": 0.6954197769790803,
      "grad_norm": 0.3500881791114807,
      "learning_rate": 1.4632280796638287e-05,
      "loss": 0.5864,
      "step": 22638
    },
    {
      "epoch": 0.6954504961140294,
      "grad_norm": 0.45170027017593384,
      "learning_rate": 1.4631852491956158e-05,
      "loss": 0.5914,
      "step": 22639
    },
    {
      "epoch": 0.6954812152489785,
      "grad_norm": 0.3891288638114929,
      "learning_rate": 1.4631424176456014e-05,
      "loss": 0.4952,
      "step": 22640
    },
    {
      "epoch": 0.6955119343839278,
      "grad_norm": 0.3670620918273926,
      "learning_rate": 1.4630995850138853e-05,
      "loss": 0.526,
      "step": 22641
    },
    {
      "epoch": 0.6955426535188769,
      "grad_norm": 0.43476542830467224,
      "learning_rate": 1.4630567513005677e-05,
      "loss": 0.5713,
      "step": 22642
    },
    {
      "epoch": 0.695573372653826,
      "grad_norm": 0.3358655571937561,
      "learning_rate": 1.4630139165057491e-05,
      "loss": 0.5453,
      "step": 22643
    },
    {
      "epoch": 0.6956040917887752,
      "grad_norm": 0.3949541449546814,
      "learning_rate": 1.462971080629529e-05,
      "loss": 0.5975,
      "step": 22644
    },
    {
      "epoch": 0.6956348109237244,
      "grad_norm": 0.3688315153121948,
      "learning_rate": 1.4629282436720075e-05,
      "loss": 0.5138,
      "step": 22645
    },
    {
      "epoch": 0.6956655300586736,
      "grad_norm": 0.3279627859592438,
      "learning_rate": 1.462885405633285e-05,
      "loss": 0.5312,
      "step": 22646
    },
    {
      "epoch": 0.6956962491936227,
      "grad_norm": 0.3474194407463074,
      "learning_rate": 1.4628425665134611e-05,
      "loss": 0.4573,
      "step": 22647
    },
    {
      "epoch": 0.6957269683285718,
      "grad_norm": 0.3881056606769562,
      "learning_rate": 1.4627997263126362e-05,
      "loss": 0.5562,
      "step": 22648
    },
    {
      "epoch": 0.6957576874635211,
      "grad_norm": 0.3973795175552368,
      "learning_rate": 1.4627568850309099e-05,
      "loss": 0.5698,
      "step": 22649
    },
    {
      "epoch": 0.6957884065984702,
      "grad_norm": 0.33754873275756836,
      "learning_rate": 1.4627140426683828e-05,
      "loss": 0.5117,
      "step": 22650
    },
    {
      "epoch": 0.6958191257334193,
      "grad_norm": 0.3602282404899597,
      "learning_rate": 1.4626711992251547e-05,
      "loss": 0.64,
      "step": 22651
    },
    {
      "epoch": 0.6958498448683685,
      "grad_norm": 0.3646886944770813,
      "learning_rate": 1.4626283547013258e-05,
      "loss": 0.601,
      "step": 22652
    },
    {
      "epoch": 0.6958805640033177,
      "grad_norm": 0.34893548488616943,
      "learning_rate": 1.462585509096996e-05,
      "loss": 0.5388,
      "step": 22653
    },
    {
      "epoch": 0.6959112831382668,
      "grad_norm": 0.3727281987667084,
      "learning_rate": 1.4625426624122654e-05,
      "loss": 0.5669,
      "step": 22654
    },
    {
      "epoch": 0.695942002273216,
      "grad_norm": 0.3622271716594696,
      "learning_rate": 1.4624998146472342e-05,
      "loss": 0.4585,
      "step": 22655
    },
    {
      "epoch": 0.6959727214081651,
      "grad_norm": 0.43568500876426697,
      "learning_rate": 1.4624569658020023e-05,
      "loss": 0.5503,
      "step": 22656
    },
    {
      "epoch": 0.6960034405431144,
      "grad_norm": 0.37510064244270325,
      "learning_rate": 1.46241411587667e-05,
      "loss": 0.4584,
      "step": 22657
    },
    {
      "epoch": 0.6960341596780635,
      "grad_norm": 0.3743645250797272,
      "learning_rate": 1.462371264871337e-05,
      "loss": 0.4818,
      "step": 22658
    },
    {
      "epoch": 0.6960648788130126,
      "grad_norm": 0.34617379307746887,
      "learning_rate": 1.4623284127861039e-05,
      "loss": 0.5958,
      "step": 22659
    },
    {
      "epoch": 0.6960955979479618,
      "grad_norm": 0.3243817985057831,
      "learning_rate": 1.4622855596210705e-05,
      "loss": 0.5426,
      "step": 22660
    },
    {
      "epoch": 0.696126317082911,
      "grad_norm": 0.36599379777908325,
      "learning_rate": 1.4622427053763366e-05,
      "loss": 0.6229,
      "step": 22661
    },
    {
      "epoch": 0.6961570362178601,
      "grad_norm": 0.46805647015571594,
      "learning_rate": 1.4621998500520027e-05,
      "loss": 0.5551,
      "step": 22662
    },
    {
      "epoch": 0.6961877553528093,
      "grad_norm": 0.35179540514945984,
      "learning_rate": 1.4621569936481687e-05,
      "loss": 0.5514,
      "step": 22663
    },
    {
      "epoch": 0.6962184744877584,
      "grad_norm": 0.3547077775001526,
      "learning_rate": 1.4621141361649352e-05,
      "loss": 0.5203,
      "step": 22664
    },
    {
      "epoch": 0.6962491936227075,
      "grad_norm": 0.381740540266037,
      "learning_rate": 1.4620712776024014e-05,
      "loss": 0.6441,
      "step": 22665
    },
    {
      "epoch": 0.6962799127576568,
      "grad_norm": 0.38753247261047363,
      "learning_rate": 1.4620284179606681e-05,
      "loss": 0.5477,
      "step": 22666
    },
    {
      "epoch": 0.6963106318926059,
      "grad_norm": 0.3449159264564514,
      "learning_rate": 1.4619855572398347e-05,
      "loss": 0.6103,
      "step": 22667
    },
    {
      "epoch": 0.696341351027555,
      "grad_norm": 0.4511210024356842,
      "learning_rate": 1.4619426954400022e-05,
      "loss": 0.5512,
      "step": 22668
    },
    {
      "epoch": 0.6963720701625042,
      "grad_norm": 0.42165133357048035,
      "learning_rate": 1.46189983256127e-05,
      "loss": 0.5097,
      "step": 22669
    },
    {
      "epoch": 0.6964027892974534,
      "grad_norm": 0.3627742528915405,
      "learning_rate": 1.4618569686037388e-05,
      "loss": 0.5565,
      "step": 22670
    },
    {
      "epoch": 0.6964335084324026,
      "grad_norm": 0.3561030328273773,
      "learning_rate": 1.4618141035675083e-05,
      "loss": 0.4741,
      "step": 22671
    },
    {
      "epoch": 0.6964642275673517,
      "grad_norm": 0.4159592390060425,
      "learning_rate": 1.4617712374526787e-05,
      "loss": 0.6798,
      "step": 22672
    },
    {
      "epoch": 0.6964949467023008,
      "grad_norm": 0.34796103835105896,
      "learning_rate": 1.4617283702593501e-05,
      "loss": 0.5387,
      "step": 22673
    },
    {
      "epoch": 0.6965256658372501,
      "grad_norm": 0.41253191232681274,
      "learning_rate": 1.4616855019876225e-05,
      "loss": 0.4672,
      "step": 22674
    },
    {
      "epoch": 0.6965563849721992,
      "grad_norm": 0.36490434408187866,
      "learning_rate": 1.4616426326375966e-05,
      "loss": 0.5496,
      "step": 22675
    },
    {
      "epoch": 0.6965871041071483,
      "grad_norm": 0.3856409788131714,
      "learning_rate": 1.4615997622093716e-05,
      "loss": 0.524,
      "step": 22676
    },
    {
      "epoch": 0.6966178232420975,
      "grad_norm": 0.3623887002468109,
      "learning_rate": 1.4615568907030483e-05,
      "loss": 0.517,
      "step": 22677
    },
    {
      "epoch": 0.6966485423770467,
      "grad_norm": 0.42046162486076355,
      "learning_rate": 1.4615140181187269e-05,
      "loss": 0.5462,
      "step": 22678
    },
    {
      "epoch": 0.6966792615119958,
      "grad_norm": 0.40576061606407166,
      "learning_rate": 1.4614711444565069e-05,
      "loss": 0.5509,
      "step": 22679
    },
    {
      "epoch": 0.696709980646945,
      "grad_norm": 0.37258023023605347,
      "learning_rate": 1.461428269716489e-05,
      "loss": 0.5448,
      "step": 22680
    },
    {
      "epoch": 0.6967406997818941,
      "grad_norm": 0.32836076617240906,
      "learning_rate": 1.461385393898773e-05,
      "loss": 0.5534,
      "step": 22681
    },
    {
      "epoch": 0.6967714189168434,
      "grad_norm": 0.35674309730529785,
      "learning_rate": 1.4613425170034595e-05,
      "loss": 0.4538,
      "step": 22682
    },
    {
      "epoch": 0.6968021380517925,
      "grad_norm": 0.3475133776664734,
      "learning_rate": 1.461299639030648e-05,
      "loss": 0.563,
      "step": 22683
    },
    {
      "epoch": 0.6968328571867416,
      "grad_norm": 0.36239194869995117,
      "learning_rate": 1.461256759980439e-05,
      "loss": 0.5308,
      "step": 22684
    },
    {
      "epoch": 0.6968635763216908,
      "grad_norm": 0.38623562455177307,
      "learning_rate": 1.4612138798529328e-05,
      "loss": 0.5961,
      "step": 22685
    },
    {
      "epoch": 0.69689429545664,
      "grad_norm": 0.3760462999343872,
      "learning_rate": 1.4611709986482293e-05,
      "loss": 0.5703,
      "step": 22686
    },
    {
      "epoch": 0.6969250145915891,
      "grad_norm": 0.3478698432445526,
      "learning_rate": 1.4611281163664285e-05,
      "loss": 0.5445,
      "step": 22687
    },
    {
      "epoch": 0.6969557337265383,
      "grad_norm": 0.37650299072265625,
      "learning_rate": 1.461085233007631e-05,
      "loss": 0.5201,
      "step": 22688
    },
    {
      "epoch": 0.6969864528614874,
      "grad_norm": 0.3581222891807556,
      "learning_rate": 1.461042348571937e-05,
      "loss": 0.6268,
      "step": 22689
    },
    {
      "epoch": 0.6970171719964365,
      "grad_norm": 0.41234371066093445,
      "learning_rate": 1.460999463059446e-05,
      "loss": 0.577,
      "step": 22690
    },
    {
      "epoch": 0.6970478911313858,
      "grad_norm": 0.36291590332984924,
      "learning_rate": 1.4609565764702587e-05,
      "loss": 0.5668,
      "step": 22691
    },
    {
      "epoch": 0.6970786102663349,
      "grad_norm": 0.35234665870666504,
      "learning_rate": 1.460913688804475e-05,
      "loss": 0.5672,
      "step": 22692
    },
    {
      "epoch": 0.697109329401284,
      "grad_norm": 0.34655192494392395,
      "learning_rate": 1.4608708000621954e-05,
      "loss": 0.5324,
      "step": 22693
    },
    {
      "epoch": 0.6971400485362332,
      "grad_norm": 0.35953179001808167,
      "learning_rate": 1.4608279102435197e-05,
      "loss": 0.5237,
      "step": 22694
    },
    {
      "epoch": 0.6971707676711824,
      "grad_norm": 0.3643888533115387,
      "learning_rate": 1.4607850193485484e-05,
      "loss": 0.6192,
      "step": 22695
    },
    {
      "epoch": 0.6972014868061316,
      "grad_norm": 0.39024725556373596,
      "learning_rate": 1.4607421273773814e-05,
      "loss": 0.5714,
      "step": 22696
    },
    {
      "epoch": 0.6972322059410807,
      "grad_norm": 0.39870572090148926,
      "learning_rate": 1.4606992343301189e-05,
      "loss": 0.6163,
      "step": 22697
    },
    {
      "epoch": 0.6972629250760298,
      "grad_norm": 0.3589004874229431,
      "learning_rate": 1.4606563402068614e-05,
      "loss": 0.5551,
      "step": 22698
    },
    {
      "epoch": 0.6972936442109791,
      "grad_norm": 0.3622085154056549,
      "learning_rate": 1.4606134450077086e-05,
      "loss": 0.5284,
      "step": 22699
    },
    {
      "epoch": 0.6973243633459282,
      "grad_norm": 0.333213746547699,
      "learning_rate": 1.4605705487327611e-05,
      "loss": 0.646,
      "step": 22700
    },
    {
      "epoch": 0.6973550824808773,
      "grad_norm": 0.4033159613609314,
      "learning_rate": 1.4605276513821187e-05,
      "loss": 0.6714,
      "step": 22701
    },
    {
      "epoch": 0.6973858016158265,
      "grad_norm": 0.35060158371925354,
      "learning_rate": 1.4604847529558822e-05,
      "loss": 0.5904,
      "step": 22702
    },
    {
      "epoch": 0.6974165207507756,
      "grad_norm": 0.36272892355918884,
      "learning_rate": 1.460441853454151e-05,
      "loss": 0.5895,
      "step": 22703
    },
    {
      "epoch": 0.6974472398857248,
      "grad_norm": 0.3695494532585144,
      "learning_rate": 1.4603989528770257e-05,
      "loss": 0.5151,
      "step": 22704
    },
    {
      "epoch": 0.697477959020674,
      "grad_norm": 0.3459913730621338,
      "learning_rate": 1.4603560512246067e-05,
      "loss": 0.5662,
      "step": 22705
    },
    {
      "epoch": 0.6975086781556231,
      "grad_norm": 0.43500953912734985,
      "learning_rate": 1.460313148496994e-05,
      "loss": 0.5876,
      "step": 22706
    },
    {
      "epoch": 0.6975393972905723,
      "grad_norm": 0.4001953899860382,
      "learning_rate": 1.4602702446942876e-05,
      "loss": 0.5203,
      "step": 22707
    },
    {
      "epoch": 0.6975701164255215,
      "grad_norm": 0.36471763253211975,
      "learning_rate": 1.460227339816588e-05,
      "loss": 0.5722,
      "step": 22708
    },
    {
      "epoch": 0.6976008355604706,
      "grad_norm": 0.38705340027809143,
      "learning_rate": 1.4601844338639954e-05,
      "loss": 0.5281,
      "step": 22709
    },
    {
      "epoch": 0.6976315546954198,
      "grad_norm": 0.3929666578769684,
      "learning_rate": 1.4601415268366097e-05,
      "loss": 0.5084,
      "step": 22710
    },
    {
      "epoch": 0.6976622738303689,
      "grad_norm": 0.39036452770233154,
      "learning_rate": 1.4600986187345315e-05,
      "loss": 0.5137,
      "step": 22711
    },
    {
      "epoch": 0.6976929929653181,
      "grad_norm": 0.37625637650489807,
      "learning_rate": 1.4600557095578611e-05,
      "loss": 0.6306,
      "step": 22712
    },
    {
      "epoch": 0.6977237121002673,
      "grad_norm": 0.3698633909225464,
      "learning_rate": 1.4600127993066982e-05,
      "loss": 0.4965,
      "step": 22713
    },
    {
      "epoch": 0.6977544312352164,
      "grad_norm": 0.4145824611186981,
      "learning_rate": 1.4599698879811433e-05,
      "loss": 0.5887,
      "step": 22714
    },
    {
      "epoch": 0.6977851503701655,
      "grad_norm": 0.337420791387558,
      "learning_rate": 1.4599269755812963e-05,
      "loss": 0.5894,
      "step": 22715
    },
    {
      "epoch": 0.6978158695051148,
      "grad_norm": 0.36152786016464233,
      "learning_rate": 1.4598840621072581e-05,
      "loss": 0.5191,
      "step": 22716
    },
    {
      "epoch": 0.6978465886400639,
      "grad_norm": 0.4189799427986145,
      "learning_rate": 1.4598411475591282e-05,
      "loss": 0.5077,
      "step": 22717
    },
    {
      "epoch": 0.697877307775013,
      "grad_norm": 0.3214954435825348,
      "learning_rate": 1.4597982319370077e-05,
      "loss": 0.4541,
      "step": 22718
    },
    {
      "epoch": 0.6979080269099622,
      "grad_norm": 0.371396005153656,
      "learning_rate": 1.459755315240996e-05,
      "loss": 0.5131,
      "step": 22719
    },
    {
      "epoch": 0.6979387460449114,
      "grad_norm": 0.4219970107078552,
      "learning_rate": 1.4597123974711938e-05,
      "loss": 0.4771,
      "step": 22720
    },
    {
      "epoch": 0.6979694651798606,
      "grad_norm": 0.47350507974624634,
      "learning_rate": 1.4596694786277008e-05,
      "loss": 0.5853,
      "step": 22721
    },
    {
      "epoch": 0.6980001843148097,
      "grad_norm": 0.39622002840042114,
      "learning_rate": 1.459626558710618e-05,
      "loss": 0.5746,
      "step": 22722
    },
    {
      "epoch": 0.6980309034497588,
      "grad_norm": 0.37910422682762146,
      "learning_rate": 1.4595836377200451e-05,
      "loss": 0.4909,
      "step": 22723
    },
    {
      "epoch": 0.698061622584708,
      "grad_norm": 0.35066360235214233,
      "learning_rate": 1.4595407156560825e-05,
      "loss": 0.5154,
      "step": 22724
    },
    {
      "epoch": 0.6980923417196572,
      "grad_norm": 0.3384469449520111,
      "learning_rate": 1.4594977925188307e-05,
      "loss": 0.5187,
      "step": 22725
    },
    {
      "epoch": 0.6981230608546063,
      "grad_norm": 0.3225082755088806,
      "learning_rate": 1.4594548683083896e-05,
      "loss": 0.4921,
      "step": 22726
    },
    {
      "epoch": 0.6981537799895555,
      "grad_norm": 0.3471711575984955,
      "learning_rate": 1.4594119430248595e-05,
      "loss": 0.5922,
      "step": 22727
    },
    {
      "epoch": 0.6981844991245046,
      "grad_norm": 0.3799887001514435,
      "learning_rate": 1.4593690166683407e-05,
      "loss": 0.5803,
      "step": 22728
    },
    {
      "epoch": 0.6982152182594538,
      "grad_norm": 0.37447619438171387,
      "learning_rate": 1.4593260892389336e-05,
      "loss": 0.5482,
      "step": 22729
    },
    {
      "epoch": 0.698245937394403,
      "grad_norm": 0.3833891451358795,
      "learning_rate": 1.4592831607367384e-05,
      "loss": 0.5519,
      "step": 22730
    },
    {
      "epoch": 0.6982766565293521,
      "grad_norm": 0.3514619469642639,
      "learning_rate": 1.4592402311618552e-05,
      "loss": 0.5101,
      "step": 22731
    },
    {
      "epoch": 0.6983073756643013,
      "grad_norm": 0.4710066318511963,
      "learning_rate": 1.4591973005143844e-05,
      "loss": 0.6288,
      "step": 22732
    },
    {
      "epoch": 0.6983380947992505,
      "grad_norm": 0.3788207173347473,
      "learning_rate": 1.4591543687944261e-05,
      "loss": 0.5027,
      "step": 22733
    },
    {
      "epoch": 0.6983688139341996,
      "grad_norm": 0.39718058705329895,
      "learning_rate": 1.4591114360020809e-05,
      "loss": 0.4857,
      "step": 22734
    },
    {
      "epoch": 0.6983995330691488,
      "grad_norm": 0.4206257164478302,
      "learning_rate": 1.4590685021374486e-05,
      "loss": 0.5265,
      "step": 22735
    },
    {
      "epoch": 0.6984302522040979,
      "grad_norm": 0.3568282127380371,
      "learning_rate": 1.4590255672006301e-05,
      "loss": 0.5334,
      "step": 22736
    },
    {
      "epoch": 0.698460971339047,
      "grad_norm": 0.35557031631469727,
      "learning_rate": 1.458982631191725e-05,
      "loss": 0.5345,
      "step": 22737
    },
    {
      "epoch": 0.6984916904739963,
      "grad_norm": 0.35913217067718506,
      "learning_rate": 1.4589396941108342e-05,
      "loss": 0.537,
      "step": 22738
    },
    {
      "epoch": 0.6985224096089454,
      "grad_norm": 0.34377211332321167,
      "learning_rate": 1.4588967559580575e-05,
      "loss": 0.5028,
      "step": 22739
    },
    {
      "epoch": 0.6985531287438945,
      "grad_norm": 1.811585545539856,
      "learning_rate": 1.4588538167334953e-05,
      "loss": 0.645,
      "step": 22740
    },
    {
      "epoch": 0.6985838478788438,
      "grad_norm": 0.36952003836631775,
      "learning_rate": 1.4588108764372481e-05,
      "loss": 0.5584,
      "step": 22741
    },
    {
      "epoch": 0.6986145670137929,
      "grad_norm": 0.40020951628685,
      "learning_rate": 1.4587679350694161e-05,
      "loss": 0.5715,
      "step": 22742
    },
    {
      "epoch": 0.6986452861487421,
      "grad_norm": 0.38662219047546387,
      "learning_rate": 1.4587249926300996e-05,
      "loss": 0.5613,
      "step": 22743
    },
    {
      "epoch": 0.6986760052836912,
      "grad_norm": 0.3830729126930237,
      "learning_rate": 1.4586820491193986e-05,
      "loss": 0.6042,
      "step": 22744
    },
    {
      "epoch": 0.6987067244186403,
      "grad_norm": 0.37623271346092224,
      "learning_rate": 1.4586391045374139e-05,
      "loss": 0.5591,
      "step": 22745
    },
    {
      "epoch": 0.6987374435535896,
      "grad_norm": 0.33460864424705505,
      "learning_rate": 1.4585961588842454e-05,
      "loss": 0.5312,
      "step": 22746
    },
    {
      "epoch": 0.6987681626885387,
      "grad_norm": 0.33594751358032227,
      "learning_rate": 1.4585532121599937e-05,
      "loss": 0.6072,
      "step": 22747
    },
    {
      "epoch": 0.6987988818234878,
      "grad_norm": 0.35574600100517273,
      "learning_rate": 1.4585102643647588e-05,
      "loss": 0.5482,
      "step": 22748
    },
    {
      "epoch": 0.698829600958437,
      "grad_norm": 0.32053011655807495,
      "learning_rate": 1.4584673154986411e-05,
      "loss": 0.5801,
      "step": 22749
    },
    {
      "epoch": 0.6988603200933862,
      "grad_norm": 0.3883623480796814,
      "learning_rate": 1.4584243655617412e-05,
      "loss": 0.5921,
      "step": 22750
    },
    {
      "epoch": 0.6988910392283353,
      "grad_norm": 0.3597763180732727,
      "learning_rate": 1.4583814145541588e-05,
      "loss": 0.61,
      "step": 22751
    },
    {
      "epoch": 0.6989217583632845,
      "grad_norm": 0.3303324282169342,
      "learning_rate": 1.4583384624759948e-05,
      "loss": 0.526,
      "step": 22752
    },
    {
      "epoch": 0.6989524774982336,
      "grad_norm": 0.44304364919662476,
      "learning_rate": 1.4582955093273494e-05,
      "loss": 0.5677,
      "step": 22753
    },
    {
      "epoch": 0.6989831966331828,
      "grad_norm": 0.38638606667518616,
      "learning_rate": 1.4582525551083228e-05,
      "loss": 0.5361,
      "step": 22754
    },
    {
      "epoch": 0.699013915768132,
      "grad_norm": 0.40742993354797363,
      "learning_rate": 1.4582095998190153e-05,
      "loss": 0.606,
      "step": 22755
    },
    {
      "epoch": 0.6990446349030811,
      "grad_norm": 0.36934345960617065,
      "learning_rate": 1.4581666434595275e-05,
      "loss": 0.5567,
      "step": 22756
    },
    {
      "epoch": 0.6990753540380303,
      "grad_norm": 0.3469395935535431,
      "learning_rate": 1.458123686029959e-05,
      "loss": 0.5246,
      "step": 22757
    },
    {
      "epoch": 0.6991060731729795,
      "grad_norm": 0.38465774059295654,
      "learning_rate": 1.4580807275304109e-05,
      "loss": 0.578,
      "step": 22758
    },
    {
      "epoch": 0.6991367923079286,
      "grad_norm": 0.4461408853530884,
      "learning_rate": 1.4580377679609833e-05,
      "loss": 0.4305,
      "step": 22759
    },
    {
      "epoch": 0.6991675114428778,
      "grad_norm": 0.35109037160873413,
      "learning_rate": 1.4579948073217764e-05,
      "loss": 0.5945,
      "step": 22760
    },
    {
      "epoch": 0.6991982305778269,
      "grad_norm": 0.3634200692176819,
      "learning_rate": 1.457951845612891e-05,
      "loss": 0.5184,
      "step": 22761
    },
    {
      "epoch": 0.699228949712776,
      "grad_norm": 0.32850730419158936,
      "learning_rate": 1.4579088828344266e-05,
      "loss": 0.4596,
      "step": 22762
    },
    {
      "epoch": 0.6992596688477253,
      "grad_norm": 0.3327782154083252,
      "learning_rate": 1.4578659189864843e-05,
      "loss": 0.5689,
      "step": 22763
    },
    {
      "epoch": 0.6992903879826744,
      "grad_norm": 0.4195777475833893,
      "learning_rate": 1.4578229540691644e-05,
      "loss": 0.6031,
      "step": 22764
    },
    {
      "epoch": 0.6993211071176235,
      "grad_norm": 0.3556104600429535,
      "learning_rate": 1.4577799880825666e-05,
      "loss": 0.5753,
      "step": 22765
    },
    {
      "epoch": 0.6993518262525728,
      "grad_norm": 0.3481832444667816,
      "learning_rate": 1.4577370210267918e-05,
      "loss": 0.522,
      "step": 22766
    },
    {
      "epoch": 0.6993825453875219,
      "grad_norm": 0.401644766330719,
      "learning_rate": 1.4576940529019401e-05,
      "loss": 0.6031,
      "step": 22767
    },
    {
      "epoch": 0.6994132645224711,
      "grad_norm": 0.3711177408695221,
      "learning_rate": 1.4576510837081124e-05,
      "loss": 0.5714,
      "step": 22768
    },
    {
      "epoch": 0.6994439836574202,
      "grad_norm": 0.35169747471809387,
      "learning_rate": 1.457608113445408e-05,
      "loss": 0.606,
      "step": 22769
    },
    {
      "epoch": 0.6994747027923693,
      "grad_norm": 0.3524141013622284,
      "learning_rate": 1.4575651421139283e-05,
      "loss": 0.5871,
      "step": 22770
    },
    {
      "epoch": 0.6995054219273186,
      "grad_norm": 0.3903377950191498,
      "learning_rate": 1.4575221697137731e-05,
      "loss": 0.5026,
      "step": 22771
    },
    {
      "epoch": 0.6995361410622677,
      "grad_norm": 0.3366168141365051,
      "learning_rate": 1.4574791962450433e-05,
      "loss": 0.524,
      "step": 22772
    },
    {
      "epoch": 0.6995668601972168,
      "grad_norm": 0.4615647494792938,
      "learning_rate": 1.4574362217078385e-05,
      "loss": 0.4752,
      "step": 22773
    },
    {
      "epoch": 0.699597579332166,
      "grad_norm": 0.39390432834625244,
      "learning_rate": 1.4573932461022595e-05,
      "loss": 0.4422,
      "step": 22774
    },
    {
      "epoch": 0.6996282984671152,
      "grad_norm": 0.3640400767326355,
      "learning_rate": 1.4573502694284068e-05,
      "loss": 0.5003,
      "step": 22775
    },
    {
      "epoch": 0.6996590176020643,
      "grad_norm": 0.3844768702983856,
      "learning_rate": 1.4573072916863802e-05,
      "loss": 0.5448,
      "step": 22776
    },
    {
      "epoch": 0.6996897367370135,
      "grad_norm": 0.4461835026741028,
      "learning_rate": 1.4572643128762809e-05,
      "loss": 0.5445,
      "step": 22777
    },
    {
      "epoch": 0.6997204558719626,
      "grad_norm": 0.3705158531665802,
      "learning_rate": 1.4572213329982083e-05,
      "loss": 0.4626,
      "step": 22778
    },
    {
      "epoch": 0.6997511750069118,
      "grad_norm": 0.33157867193222046,
      "learning_rate": 1.4571783520522639e-05,
      "loss": 0.5471,
      "step": 22779
    },
    {
      "epoch": 0.699781894141861,
      "grad_norm": 0.3805142641067505,
      "learning_rate": 1.4571353700385475e-05,
      "loss": 0.593,
      "step": 22780
    },
    {
      "epoch": 0.6998126132768101,
      "grad_norm": 0.37049517035484314,
      "learning_rate": 1.4570923869571594e-05,
      "loss": 0.5478,
      "step": 22781
    },
    {
      "epoch": 0.6998433324117593,
      "grad_norm": 0.41099077463150024,
      "learning_rate": 1.4570494028082003e-05,
      "loss": 0.5382,
      "step": 22782
    },
    {
      "epoch": 0.6998740515467085,
      "grad_norm": 0.4122641682624817,
      "learning_rate": 1.4570064175917699e-05,
      "loss": 0.5214,
      "step": 22783
    },
    {
      "epoch": 0.6999047706816576,
      "grad_norm": 0.3480283319950104,
      "learning_rate": 1.4569634313079696e-05,
      "loss": 0.5508,
      "step": 22784
    },
    {
      "epoch": 0.6999354898166068,
      "grad_norm": 0.35131773352622986,
      "learning_rate": 1.4569204439568992e-05,
      "loss": 0.568,
      "step": 22785
    },
    {
      "epoch": 0.6999662089515559,
      "grad_norm": 0.3923819065093994,
      "learning_rate": 1.456877455538659e-05,
      "loss": 0.6411,
      "step": 22786
    },
    {
      "epoch": 0.699996928086505,
      "grad_norm": 0.3571188747882843,
      "learning_rate": 1.4568344660533495e-05,
      "loss": 0.5781,
      "step": 22787
    },
    {
      "epoch": 0.7000276472214543,
      "grad_norm": 0.3507484495639801,
      "learning_rate": 1.4567914755010717e-05,
      "loss": 0.5243,
      "step": 22788
    },
    {
      "epoch": 0.7000583663564034,
      "grad_norm": 0.38164252042770386,
      "learning_rate": 1.456748483881925e-05,
      "loss": 0.5827,
      "step": 22789
    },
    {
      "epoch": 0.7000890854913525,
      "grad_norm": 0.3348979353904724,
      "learning_rate": 1.4567054911960105e-05,
      "loss": 0.605,
      "step": 22790
    },
    {
      "epoch": 0.7001198046263017,
      "grad_norm": 0.39877113699913025,
      "learning_rate": 1.4566624974434285e-05,
      "loss": 0.5981,
      "step": 22791
    },
    {
      "epoch": 0.7001505237612509,
      "grad_norm": 0.32018035650253296,
      "learning_rate": 1.4566195026242793e-05,
      "loss": 0.521,
      "step": 22792
    },
    {
      "epoch": 0.7001812428962001,
      "grad_norm": 0.3418984115123749,
      "learning_rate": 1.4565765067386634e-05,
      "loss": 0.4489,
      "step": 22793
    },
    {
      "epoch": 0.7002119620311492,
      "grad_norm": 0.3393201529979706,
      "learning_rate": 1.4565335097866814e-05,
      "loss": 0.53,
      "step": 22794
    },
    {
      "epoch": 0.7002426811660983,
      "grad_norm": 0.399614542722702,
      "learning_rate": 1.4564905117684329e-05,
      "loss": 0.5276,
      "step": 22795
    },
    {
      "epoch": 0.7002734003010476,
      "grad_norm": 0.36597326397895813,
      "learning_rate": 1.4564475126840191e-05,
      "loss": 0.5979,
      "step": 22796
    },
    {
      "epoch": 0.7003041194359967,
      "grad_norm": 0.4022495448589325,
      "learning_rate": 1.4564045125335407e-05,
      "loss": 0.5682,
      "step": 22797
    },
    {
      "epoch": 0.7003348385709458,
      "grad_norm": 0.3792642652988434,
      "learning_rate": 1.4563615113170973e-05,
      "loss": 0.5116,
      "step": 22798
    },
    {
      "epoch": 0.700365557705895,
      "grad_norm": 0.44367289543151855,
      "learning_rate": 1.4563185090347897e-05,
      "loss": 0.4908,
      "step": 22799
    },
    {
      "epoch": 0.7003962768408442,
      "grad_norm": 0.3650529384613037,
      "learning_rate": 1.4562755056867186e-05,
      "loss": 0.5907,
      "step": 22800
    },
    {
      "epoch": 0.7004269959757933,
      "grad_norm": 0.4542345702648163,
      "learning_rate": 1.4562325012729841e-05,
      "loss": 0.6416,
      "step": 22801
    },
    {
      "epoch": 0.7004577151107425,
      "grad_norm": 0.37634986639022827,
      "learning_rate": 1.4561894957936869e-05,
      "loss": 0.5926,
      "step": 22802
    },
    {
      "epoch": 0.7004884342456916,
      "grad_norm": 0.34997987747192383,
      "learning_rate": 1.4561464892489268e-05,
      "loss": 0.5422,
      "step": 22803
    },
    {
      "epoch": 0.7005191533806407,
      "grad_norm": 0.3954198360443115,
      "learning_rate": 1.456103481638805e-05,
      "loss": 0.5067,
      "step": 22804
    },
    {
      "epoch": 0.70054987251559,
      "grad_norm": 0.35792744159698486,
      "learning_rate": 1.4560604729634216e-05,
      "loss": 0.6043,
      "step": 22805
    },
    {
      "epoch": 0.7005805916505391,
      "grad_norm": 0.36221078038215637,
      "learning_rate": 1.4560174632228772e-05,
      "loss": 0.6149,
      "step": 22806
    },
    {
      "epoch": 0.7006113107854883,
      "grad_norm": 0.4583247900009155,
      "learning_rate": 1.4559744524172722e-05,
      "loss": 0.6383,
      "step": 22807
    },
    {
      "epoch": 0.7006420299204374,
      "grad_norm": 0.5182620286941528,
      "learning_rate": 1.4559314405467069e-05,
      "loss": 0.5604,
      "step": 22808
    },
    {
      "epoch": 0.7006727490553866,
      "grad_norm": 0.35575294494628906,
      "learning_rate": 1.4558884276112819e-05,
      "loss": 0.6677,
      "step": 22809
    },
    {
      "epoch": 0.7007034681903358,
      "grad_norm": 0.37107419967651367,
      "learning_rate": 1.4558454136110978e-05,
      "loss": 0.5814,
      "step": 22810
    },
    {
      "epoch": 0.7007341873252849,
      "grad_norm": 0.3991928696632385,
      "learning_rate": 1.4558023985462549e-05,
      "loss": 0.587,
      "step": 22811
    },
    {
      "epoch": 0.700764906460234,
      "grad_norm": 0.3345324993133545,
      "learning_rate": 1.4557593824168535e-05,
      "loss": 0.5672,
      "step": 22812
    },
    {
      "epoch": 0.7007956255951833,
      "grad_norm": 0.32378995418548584,
      "learning_rate": 1.4557163652229939e-05,
      "loss": 0.5433,
      "step": 22813
    },
    {
      "epoch": 0.7008263447301324,
      "grad_norm": 0.3526691496372223,
      "learning_rate": 1.4556733469647774e-05,
      "loss": 0.5685,
      "step": 22814
    },
    {
      "epoch": 0.7008570638650815,
      "grad_norm": 0.3523760735988617,
      "learning_rate": 1.4556303276423039e-05,
      "loss": 0.5508,
      "step": 22815
    },
    {
      "epoch": 0.7008877830000307,
      "grad_norm": 0.3563656806945801,
      "learning_rate": 1.4555873072556739e-05,
      "loss": 0.53,
      "step": 22816
    },
    {
      "epoch": 0.7009185021349799,
      "grad_norm": 0.3406163454055786,
      "learning_rate": 1.4555442858049879e-05,
      "loss": 0.5111,
      "step": 22817
    },
    {
      "epoch": 0.7009492212699291,
      "grad_norm": 0.3340211510658264,
      "learning_rate": 1.4555012632903465e-05,
      "loss": 0.5744,
      "step": 22818
    },
    {
      "epoch": 0.7009799404048782,
      "grad_norm": 0.34135255217552185,
      "learning_rate": 1.4554582397118499e-05,
      "loss": 0.4669,
      "step": 22819
    },
    {
      "epoch": 0.7010106595398273,
      "grad_norm": 0.3994549810886383,
      "learning_rate": 1.455415215069599e-05,
      "loss": 0.5663,
      "step": 22820
    },
    {
      "epoch": 0.7010413786747766,
      "grad_norm": 0.37170448899269104,
      "learning_rate": 1.4553721893636939e-05,
      "loss": 0.602,
      "step": 22821
    },
    {
      "epoch": 0.7010720978097257,
      "grad_norm": 0.3449903428554535,
      "learning_rate": 1.4553291625942354e-05,
      "loss": 0.471,
      "step": 22822
    },
    {
      "epoch": 0.7011028169446748,
      "grad_norm": 0.39861395955085754,
      "learning_rate": 1.4552861347613237e-05,
      "loss": 0.6054,
      "step": 22823
    },
    {
      "epoch": 0.701133536079624,
      "grad_norm": 0.35048165917396545,
      "learning_rate": 1.4552431058650595e-05,
      "loss": 0.5259,
      "step": 22824
    },
    {
      "epoch": 0.7011642552145732,
      "grad_norm": 0.362206369638443,
      "learning_rate": 1.4552000759055432e-05,
      "loss": 0.5865,
      "step": 22825
    },
    {
      "epoch": 0.7011949743495223,
      "grad_norm": 0.4684704542160034,
      "learning_rate": 1.4551570448828753e-05,
      "loss": 0.5496,
      "step": 22826
    },
    {
      "epoch": 0.7012256934844715,
      "grad_norm": 0.4203329086303711,
      "learning_rate": 1.4551140127971565e-05,
      "loss": 0.5822,
      "step": 22827
    },
    {
      "epoch": 0.7012564126194206,
      "grad_norm": 0.33440643548965454,
      "learning_rate": 1.455070979648487e-05,
      "loss": 0.588,
      "step": 22828
    },
    {
      "epoch": 0.7012871317543699,
      "grad_norm": 0.3653399348258972,
      "learning_rate": 1.4550279454369674e-05,
      "loss": 0.5762,
      "step": 22829
    },
    {
      "epoch": 0.701317850889319,
      "grad_norm": 0.34714943170547485,
      "learning_rate": 1.4549849101626982e-05,
      "loss": 0.5624,
      "step": 22830
    },
    {
      "epoch": 0.7013485700242681,
      "grad_norm": 0.3877015709877014,
      "learning_rate": 1.4549418738257804e-05,
      "loss": 0.5676,
      "step": 22831
    },
    {
      "epoch": 0.7013792891592173,
      "grad_norm": 0.46675246953964233,
      "learning_rate": 1.4548988364263132e-05,
      "loss": 0.6039,
      "step": 22832
    },
    {
      "epoch": 0.7014100082941664,
      "grad_norm": 0.42267102003097534,
      "learning_rate": 1.4548557979643987e-05,
      "loss": 0.6298,
      "step": 22833
    },
    {
      "epoch": 0.7014407274291156,
      "grad_norm": 0.3524516820907593,
      "learning_rate": 1.4548127584401369e-05,
      "loss": 0.4845,
      "step": 22834
    },
    {
      "epoch": 0.7014714465640648,
      "grad_norm": 0.40826621651649475,
      "learning_rate": 1.4547697178536275e-05,
      "loss": 0.5527,
      "step": 22835
    },
    {
      "epoch": 0.7015021656990139,
      "grad_norm": 0.34316056966781616,
      "learning_rate": 1.454726676204972e-05,
      "loss": 0.5728,
      "step": 22836
    },
    {
      "epoch": 0.701532884833963,
      "grad_norm": 0.3711056411266327,
      "learning_rate": 1.4546836334942707e-05,
      "loss": 0.6091,
      "step": 22837
    },
    {
      "epoch": 0.7015636039689123,
      "grad_norm": 0.36259299516677856,
      "learning_rate": 1.4546405897216238e-05,
      "loss": 0.519,
      "step": 22838
    },
    {
      "epoch": 0.7015943231038614,
      "grad_norm": 0.42987483739852905,
      "learning_rate": 1.4545975448871322e-05,
      "loss": 0.5318,
      "step": 22839
    },
    {
      "epoch": 0.7016250422388105,
      "grad_norm": 0.3637450337409973,
      "learning_rate": 1.4545544989908962e-05,
      "loss": 0.5022,
      "step": 22840
    },
    {
      "epoch": 0.7016557613737597,
      "grad_norm": 0.3284754157066345,
      "learning_rate": 1.4545114520330163e-05,
      "loss": 0.5285,
      "step": 22841
    },
    {
      "epoch": 0.7016864805087089,
      "grad_norm": 0.34325510263442993,
      "learning_rate": 1.4544684040135934e-05,
      "loss": 0.6378,
      "step": 22842
    },
    {
      "epoch": 0.7017171996436581,
      "grad_norm": 0.3790234923362732,
      "learning_rate": 1.4544253549327276e-05,
      "loss": 0.5986,
      "step": 22843
    },
    {
      "epoch": 0.7017479187786072,
      "grad_norm": 0.35839441418647766,
      "learning_rate": 1.45438230479052e-05,
      "loss": 0.5774,
      "step": 22844
    },
    {
      "epoch": 0.7017786379135563,
      "grad_norm": 0.35159096121788025,
      "learning_rate": 1.4543392535870707e-05,
      "loss": 0.6064,
      "step": 22845
    },
    {
      "epoch": 0.7018093570485056,
      "grad_norm": 0.38188284635543823,
      "learning_rate": 1.4542962013224799e-05,
      "loss": 0.6005,
      "step": 22846
    },
    {
      "epoch": 0.7018400761834547,
      "grad_norm": 0.3862486481666565,
      "learning_rate": 1.4542531479968492e-05,
      "loss": 0.6091,
      "step": 22847
    },
    {
      "epoch": 0.7018707953184038,
      "grad_norm": 0.35040998458862305,
      "learning_rate": 1.4542100936102779e-05,
      "loss": 0.5351,
      "step": 22848
    },
    {
      "epoch": 0.701901514453353,
      "grad_norm": 0.3530709147453308,
      "learning_rate": 1.4541670381628676e-05,
      "loss": 0.5549,
      "step": 22849
    },
    {
      "epoch": 0.7019322335883021,
      "grad_norm": 0.34579047560691833,
      "learning_rate": 1.4541239816547182e-05,
      "loss": 0.569,
      "step": 22850
    },
    {
      "epoch": 0.7019629527232513,
      "grad_norm": 0.3199346363544464,
      "learning_rate": 1.4540809240859308e-05,
      "loss": 0.5376,
      "step": 22851
    },
    {
      "epoch": 0.7019936718582005,
      "grad_norm": 0.3645905554294586,
      "learning_rate": 1.4540378654566056e-05,
      "loss": 0.6191,
      "step": 22852
    },
    {
      "epoch": 0.7020243909931496,
      "grad_norm": 0.3461923897266388,
      "learning_rate": 1.4539948057668433e-05,
      "loss": 0.5687,
      "step": 22853
    },
    {
      "epoch": 0.7020551101280988,
      "grad_norm": 0.367147833108902,
      "learning_rate": 1.4539517450167444e-05,
      "loss": 0.5374,
      "step": 22854
    },
    {
      "epoch": 0.702085829263048,
      "grad_norm": 0.36126935482025146,
      "learning_rate": 1.4539086832064096e-05,
      "loss": 0.5573,
      "step": 22855
    },
    {
      "epoch": 0.7021165483979971,
      "grad_norm": 0.4113994538784027,
      "learning_rate": 1.4538656203359392e-05,
      "loss": 0.6018,
      "step": 22856
    },
    {
      "epoch": 0.7021472675329463,
      "grad_norm": 0.37532272934913635,
      "learning_rate": 1.453822556405434e-05,
      "loss": 0.5511,
      "step": 22857
    },
    {
      "epoch": 0.7021779866678954,
      "grad_norm": 0.3709590435028076,
      "learning_rate": 1.4537794914149946e-05,
      "loss": 0.5519,
      "step": 22858
    },
    {
      "epoch": 0.7022087058028446,
      "grad_norm": 0.34410595893859863,
      "learning_rate": 1.4537364253647213e-05,
      "loss": 0.5382,
      "step": 22859
    },
    {
      "epoch": 0.7022394249377938,
      "grad_norm": 0.4175748825073242,
      "learning_rate": 1.4536933582547152e-05,
      "loss": 0.6161,
      "step": 22860
    },
    {
      "epoch": 0.7022701440727429,
      "grad_norm": 0.3591126799583435,
      "learning_rate": 1.4536502900850762e-05,
      "loss": 0.4591,
      "step": 22861
    },
    {
      "epoch": 0.702300863207692,
      "grad_norm": 0.362669438123703,
      "learning_rate": 1.4536072208559056e-05,
      "loss": 0.5418,
      "step": 22862
    },
    {
      "epoch": 0.7023315823426413,
      "grad_norm": 0.35969310998916626,
      "learning_rate": 1.4535641505673037e-05,
      "loss": 0.4883,
      "step": 22863
    },
    {
      "epoch": 0.7023623014775904,
      "grad_norm": 0.36475974321365356,
      "learning_rate": 1.4535210792193705e-05,
      "loss": 0.5679,
      "step": 22864
    },
    {
      "epoch": 0.7023930206125395,
      "grad_norm": 0.5045778155326843,
      "learning_rate": 1.4534780068122078e-05,
      "loss": 0.628,
      "step": 22865
    },
    {
      "epoch": 0.7024237397474887,
      "grad_norm": 0.3466109335422516,
      "learning_rate": 1.4534349333459153e-05,
      "loss": 0.5564,
      "step": 22866
    },
    {
      "epoch": 0.7024544588824378,
      "grad_norm": 0.36826038360595703,
      "learning_rate": 1.4533918588205937e-05,
      "loss": 0.5724,
      "step": 22867
    },
    {
      "epoch": 0.7024851780173871,
      "grad_norm": 0.3973080813884735,
      "learning_rate": 1.4533487832363438e-05,
      "loss": 0.5572,
      "step": 22868
    },
    {
      "epoch": 0.7025158971523362,
      "grad_norm": 0.4098432660102844,
      "learning_rate": 1.453305706593266e-05,
      "loss": 0.4874,
      "step": 22869
    },
    {
      "epoch": 0.7025466162872853,
      "grad_norm": 0.3438859283924103,
      "learning_rate": 1.4532626288914615e-05,
      "loss": 0.5352,
      "step": 22870
    },
    {
      "epoch": 0.7025773354222346,
      "grad_norm": 0.7508162260055542,
      "learning_rate": 1.4532195501310303e-05,
      "loss": 0.5436,
      "step": 22871
    },
    {
      "epoch": 0.7026080545571837,
      "grad_norm": 0.38775455951690674,
      "learning_rate": 1.453176470312073e-05,
      "loss": 0.5897,
      "step": 22872
    },
    {
      "epoch": 0.7026387736921328,
      "grad_norm": 0.3522389233112335,
      "learning_rate": 1.4531333894346906e-05,
      "loss": 0.6297,
      "step": 22873
    },
    {
      "epoch": 0.702669492827082,
      "grad_norm": 0.3602699041366577,
      "learning_rate": 1.4530903074989834e-05,
      "loss": 0.5262,
      "step": 22874
    },
    {
      "epoch": 0.7027002119620311,
      "grad_norm": 0.3567761480808258,
      "learning_rate": 1.4530472245050522e-05,
      "loss": 0.5896,
      "step": 22875
    },
    {
      "epoch": 0.7027309310969803,
      "grad_norm": 0.33409062027931213,
      "learning_rate": 1.4530041404529978e-05,
      "loss": 0.5944,
      "step": 22876
    },
    {
      "epoch": 0.7027616502319295,
      "grad_norm": 0.3584613502025604,
      "learning_rate": 1.4529610553429201e-05,
      "loss": 0.5264,
      "step": 22877
    },
    {
      "epoch": 0.7027923693668786,
      "grad_norm": 0.376620888710022,
      "learning_rate": 1.4529179691749206e-05,
      "loss": 0.6141,
      "step": 22878
    },
    {
      "epoch": 0.7028230885018278,
      "grad_norm": 0.37028026580810547,
      "learning_rate": 1.4528748819490995e-05,
      "loss": 0.5862,
      "step": 22879
    },
    {
      "epoch": 0.702853807636777,
      "grad_norm": 0.35160723328590393,
      "learning_rate": 1.4528317936655573e-05,
      "loss": 0.5425,
      "step": 22880
    },
    {
      "epoch": 0.7028845267717261,
      "grad_norm": 0.3856756389141083,
      "learning_rate": 1.452788704324395e-05,
      "loss": 0.532,
      "step": 22881
    },
    {
      "epoch": 0.7029152459066753,
      "grad_norm": 0.3472043573856354,
      "learning_rate": 1.452745613925713e-05,
      "loss": 0.5192,
      "step": 22882
    },
    {
      "epoch": 0.7029459650416244,
      "grad_norm": 0.35238853096961975,
      "learning_rate": 1.4527025224696121e-05,
      "loss": 0.5844,
      "step": 22883
    },
    {
      "epoch": 0.7029766841765736,
      "grad_norm": 0.33087438344955444,
      "learning_rate": 1.4526594299561927e-05,
      "loss": 0.5084,
      "step": 22884
    },
    {
      "epoch": 0.7030074033115228,
      "grad_norm": 0.5001827478408813,
      "learning_rate": 1.4526163363855556e-05,
      "loss": 0.6223,
      "step": 22885
    },
    {
      "epoch": 0.7030381224464719,
      "grad_norm": 0.3765128254890442,
      "learning_rate": 1.4525732417578015e-05,
      "loss": 0.6107,
      "step": 22886
    },
    {
      "epoch": 0.703068841581421,
      "grad_norm": 0.6044362783432007,
      "learning_rate": 1.452530146073031e-05,
      "loss": 0.5021,
      "step": 22887
    },
    {
      "epoch": 0.7030995607163703,
      "grad_norm": 0.33248814940452576,
      "learning_rate": 1.4524870493313445e-05,
      "loss": 0.5462,
      "step": 22888
    },
    {
      "epoch": 0.7031302798513194,
      "grad_norm": 0.3634447753429413,
      "learning_rate": 1.4524439515328432e-05,
      "loss": 0.6231,
      "step": 22889
    },
    {
      "epoch": 0.7031609989862685,
      "grad_norm": 0.374244749546051,
      "learning_rate": 1.4524008526776274e-05,
      "loss": 0.594,
      "step": 22890
    },
    {
      "epoch": 0.7031917181212177,
      "grad_norm": 0.33760565519332886,
      "learning_rate": 1.4523577527657977e-05,
      "loss": 0.493,
      "step": 22891
    },
    {
      "epoch": 0.7032224372561668,
      "grad_norm": 0.3910742998123169,
      "learning_rate": 1.4523146517974551e-05,
      "loss": 0.5394,
      "step": 22892
    },
    {
      "epoch": 0.7032531563911161,
      "grad_norm": 0.4323113262653351,
      "learning_rate": 1.4522715497726995e-05,
      "loss": 0.6098,
      "step": 22893
    },
    {
      "epoch": 0.7032838755260652,
      "grad_norm": 0.39593246579170227,
      "learning_rate": 1.4522284466916327e-05,
      "loss": 0.5296,
      "step": 22894
    },
    {
      "epoch": 0.7033145946610143,
      "grad_norm": 0.40132763981819153,
      "learning_rate": 1.4521853425543544e-05,
      "loss": 0.5909,
      "step": 22895
    },
    {
      "epoch": 0.7033453137959635,
      "grad_norm": 0.36575061082839966,
      "learning_rate": 1.452142237360966e-05,
      "loss": 0.5082,
      "step": 22896
    },
    {
      "epoch": 0.7033760329309127,
      "grad_norm": 0.3814242482185364,
      "learning_rate": 1.4520991311115678e-05,
      "loss": 0.5063,
      "step": 22897
    },
    {
      "epoch": 0.7034067520658618,
      "grad_norm": 0.3461247682571411,
      "learning_rate": 1.4520560238062603e-05,
      "loss": 0.4621,
      "step": 22898
    },
    {
      "epoch": 0.703437471200811,
      "grad_norm": 0.7017604112625122,
      "learning_rate": 1.4520129154451446e-05,
      "loss": 0.5633,
      "step": 22899
    },
    {
      "epoch": 0.7034681903357601,
      "grad_norm": 0.34799906611442566,
      "learning_rate": 1.4519698060283207e-05,
      "loss": 0.567,
      "step": 22900
    },
    {
      "epoch": 0.7034989094707093,
      "grad_norm": 0.3295420706272125,
      "learning_rate": 1.4519266955558902e-05,
      "loss": 0.4975,
      "step": 22901
    },
    {
      "epoch": 0.7035296286056585,
      "grad_norm": 0.34889882802963257,
      "learning_rate": 1.4518835840279531e-05,
      "loss": 0.5304,
      "step": 22902
    },
    {
      "epoch": 0.7035603477406076,
      "grad_norm": 0.35680997371673584,
      "learning_rate": 1.4518404714446107e-05,
      "loss": 0.5517,
      "step": 22903
    },
    {
      "epoch": 0.7035910668755568,
      "grad_norm": 0.48517128825187683,
      "learning_rate": 1.4517973578059627e-05,
      "loss": 0.7004,
      "step": 22904
    },
    {
      "epoch": 0.703621786010506,
      "grad_norm": 0.38378679752349854,
      "learning_rate": 1.4517542431121108e-05,
      "loss": 0.6202,
      "step": 22905
    },
    {
      "epoch": 0.7036525051454551,
      "grad_norm": 0.3723198175430298,
      "learning_rate": 1.4517111273631553e-05,
      "loss": 0.6375,
      "step": 22906
    },
    {
      "epoch": 0.7036832242804043,
      "grad_norm": 0.33538419008255005,
      "learning_rate": 1.4516680105591969e-05,
      "loss": 0.5534,
      "step": 22907
    },
    {
      "epoch": 0.7037139434153534,
      "grad_norm": 0.3618636429309845,
      "learning_rate": 1.4516248927003362e-05,
      "loss": 0.5257,
      "step": 22908
    },
    {
      "epoch": 0.7037446625503025,
      "grad_norm": 0.3583250343799591,
      "learning_rate": 1.4515817737866742e-05,
      "loss": 0.4774,
      "step": 22909
    },
    {
      "epoch": 0.7037753816852518,
      "grad_norm": 0.3656419813632965,
      "learning_rate": 1.4515386538183113e-05,
      "loss": 0.5058,
      "step": 22910
    },
    {
      "epoch": 0.7038061008202009,
      "grad_norm": 0.4133569300174713,
      "learning_rate": 1.4514955327953484e-05,
      "loss": 0.6443,
      "step": 22911
    },
    {
      "epoch": 0.70383681995515,
      "grad_norm": 0.37801286578178406,
      "learning_rate": 1.4514524107178862e-05,
      "loss": 0.5583,
      "step": 22912
    },
    {
      "epoch": 0.7038675390900992,
      "grad_norm": 0.4066169559955597,
      "learning_rate": 1.4514092875860254e-05,
      "loss": 0.6102,
      "step": 22913
    },
    {
      "epoch": 0.7038982582250484,
      "grad_norm": 0.3291459381580353,
      "learning_rate": 1.4513661633998665e-05,
      "loss": 0.5656,
      "step": 22914
    },
    {
      "epoch": 0.7039289773599975,
      "grad_norm": 0.37486839294433594,
      "learning_rate": 1.4513230381595108e-05,
      "loss": 0.4848,
      "step": 22915
    },
    {
      "epoch": 0.7039596964949467,
      "grad_norm": 0.40638071298599243,
      "learning_rate": 1.4512799118650583e-05,
      "loss": 0.4745,
      "step": 22916
    },
    {
      "epoch": 0.7039904156298958,
      "grad_norm": 0.3672785460948944,
      "learning_rate": 1.45123678451661e-05,
      "loss": 0.5006,
      "step": 22917
    },
    {
      "epoch": 0.7040211347648451,
      "grad_norm": 0.36186274886131287,
      "learning_rate": 1.4511936561142666e-05,
      "loss": 0.6069,
      "step": 22918
    },
    {
      "epoch": 0.7040518538997942,
      "grad_norm": 0.3022129535675049,
      "learning_rate": 1.4511505266581291e-05,
      "loss": 0.5065,
      "step": 22919
    },
    {
      "epoch": 0.7040825730347433,
      "grad_norm": 0.3470118045806885,
      "learning_rate": 1.451107396148298e-05,
      "loss": 0.5365,
      "step": 22920
    },
    {
      "epoch": 0.7041132921696925,
      "grad_norm": 0.3656608760356903,
      "learning_rate": 1.4510642645848742e-05,
      "loss": 0.5703,
      "step": 22921
    },
    {
      "epoch": 0.7041440113046417,
      "grad_norm": 0.39742743968963623,
      "learning_rate": 1.4510211319679581e-05,
      "loss": 0.523,
      "step": 22922
    },
    {
      "epoch": 0.7041747304395908,
      "grad_norm": 0.36146119236946106,
      "learning_rate": 1.4509779982976506e-05,
      "loss": 0.5925,
      "step": 22923
    },
    {
      "epoch": 0.70420544957454,
      "grad_norm": 0.3478795289993286,
      "learning_rate": 1.4509348635740526e-05,
      "loss": 0.4523,
      "step": 22924
    },
    {
      "epoch": 0.7042361687094891,
      "grad_norm": 0.38213062286376953,
      "learning_rate": 1.4508917277972648e-05,
      "loss": 0.5897,
      "step": 22925
    },
    {
      "epoch": 0.7042668878444382,
      "grad_norm": 0.3770413398742676,
      "learning_rate": 1.4508485909673877e-05,
      "loss": 0.5582,
      "step": 22926
    },
    {
      "epoch": 0.7042976069793875,
      "grad_norm": 0.35741207003593445,
      "learning_rate": 1.4508054530845223e-05,
      "loss": 0.6169,
      "step": 22927
    },
    {
      "epoch": 0.7043283261143366,
      "grad_norm": 0.3622036874294281,
      "learning_rate": 1.4507623141487695e-05,
      "loss": 0.5258,
      "step": 22928
    },
    {
      "epoch": 0.7043590452492858,
      "grad_norm": 0.36808347702026367,
      "learning_rate": 1.4507191741602295e-05,
      "loss": 0.548,
      "step": 22929
    },
    {
      "epoch": 0.704389764384235,
      "grad_norm": 0.4170840382575989,
      "learning_rate": 1.4506760331190037e-05,
      "loss": 0.5714,
      "step": 22930
    },
    {
      "epoch": 0.7044204835191841,
      "grad_norm": 0.3949587345123291,
      "learning_rate": 1.4506328910251924e-05,
      "loss": 0.5574,
      "step": 22931
    },
    {
      "epoch": 0.7044512026541333,
      "grad_norm": 0.38205835223197937,
      "learning_rate": 1.4505897478788966e-05,
      "loss": 0.5369,
      "step": 22932
    },
    {
      "epoch": 0.7044819217890824,
      "grad_norm": 0.4511113166809082,
      "learning_rate": 1.450546603680217e-05,
      "loss": 0.5814,
      "step": 22933
    },
    {
      "epoch": 0.7045126409240315,
      "grad_norm": 0.33401328325271606,
      "learning_rate": 1.4505034584292542e-05,
      "loss": 0.5537,
      "step": 22934
    },
    {
      "epoch": 0.7045433600589808,
      "grad_norm": 0.3885745406150818,
      "learning_rate": 1.4504603121261091e-05,
      "loss": 0.577,
      "step": 22935
    },
    {
      "epoch": 0.7045740791939299,
      "grad_norm": 0.47954118251800537,
      "learning_rate": 1.4504171647708825e-05,
      "loss": 0.5082,
      "step": 22936
    },
    {
      "epoch": 0.704604798328879,
      "grad_norm": 0.35205787420272827,
      "learning_rate": 1.4503740163636753e-05,
      "loss": 0.5606,
      "step": 22937
    },
    {
      "epoch": 0.7046355174638282,
      "grad_norm": 0.4279021918773651,
      "learning_rate": 1.450330866904588e-05,
      "loss": 0.4761,
      "step": 22938
    },
    {
      "epoch": 0.7046662365987774,
      "grad_norm": 0.3461022973060608,
      "learning_rate": 1.4502877163937215e-05,
      "loss": 0.5838,
      "step": 22939
    },
    {
      "epoch": 0.7046969557337266,
      "grad_norm": 0.356644868850708,
      "learning_rate": 1.4502445648311766e-05,
      "loss": 0.5312,
      "step": 22940
    },
    {
      "epoch": 0.7047276748686757,
      "grad_norm": 0.4335714876651764,
      "learning_rate": 1.4502014122170538e-05,
      "loss": 0.5502,
      "step": 22941
    },
    {
      "epoch": 0.7047583940036248,
      "grad_norm": 0.3494728207588196,
      "learning_rate": 1.4501582585514546e-05,
      "loss": 0.5425,
      "step": 22942
    },
    {
      "epoch": 0.7047891131385741,
      "grad_norm": 0.3605012893676758,
      "learning_rate": 1.4501151038344792e-05,
      "loss": 0.5999,
      "step": 22943
    },
    {
      "epoch": 0.7048198322735232,
      "grad_norm": 0.37797683477401733,
      "learning_rate": 1.4500719480662287e-05,
      "loss": 0.6105,
      "step": 22944
    },
    {
      "epoch": 0.7048505514084723,
      "grad_norm": 0.36745724081993103,
      "learning_rate": 1.4500287912468033e-05,
      "loss": 0.599,
      "step": 22945
    },
    {
      "epoch": 0.7048812705434215,
      "grad_norm": 0.45699360966682434,
      "learning_rate": 1.4499856333763048e-05,
      "loss": 0.5068,
      "step": 22946
    },
    {
      "epoch": 0.7049119896783707,
      "grad_norm": 0.4207497239112854,
      "learning_rate": 1.449942474454833e-05,
      "loss": 0.5546,
      "step": 22947
    },
    {
      "epoch": 0.7049427088133198,
      "grad_norm": 0.3816334903240204,
      "learning_rate": 1.4498993144824892e-05,
      "loss": 0.5659,
      "step": 22948
    },
    {
      "epoch": 0.704973427948269,
      "grad_norm": 0.35515984892845154,
      "learning_rate": 1.4498561534593742e-05,
      "loss": 0.5113,
      "step": 22949
    },
    {
      "epoch": 0.7050041470832181,
      "grad_norm": 0.3735414445400238,
      "learning_rate": 1.4498129913855887e-05,
      "loss": 0.5629,
      "step": 22950
    },
    {
      "epoch": 0.7050348662181672,
      "grad_norm": 0.3675881028175354,
      "learning_rate": 1.4497698282612338e-05,
      "loss": 0.5413,
      "step": 22951
    },
    {
      "epoch": 0.7050655853531165,
      "grad_norm": 0.36824753880500793,
      "learning_rate": 1.4497266640864096e-05,
      "loss": 0.5926,
      "step": 22952
    },
    {
      "epoch": 0.7050963044880656,
      "grad_norm": 0.36849790811538696,
      "learning_rate": 1.4496834988612176e-05,
      "loss": 0.5333,
      "step": 22953
    },
    {
      "epoch": 0.7051270236230148,
      "grad_norm": 0.3632769286632538,
      "learning_rate": 1.4496403325857584e-05,
      "loss": 0.5991,
      "step": 22954
    },
    {
      "epoch": 0.705157742757964,
      "grad_norm": 0.3138526380062103,
      "learning_rate": 1.4495971652601329e-05,
      "loss": 0.4977,
      "step": 22955
    },
    {
      "epoch": 0.7051884618929131,
      "grad_norm": 0.3490069806575775,
      "learning_rate": 1.4495539968844414e-05,
      "loss": 0.509,
      "step": 22956
    },
    {
      "epoch": 0.7052191810278623,
      "grad_norm": 0.3515849709510803,
      "learning_rate": 1.4495108274587857e-05,
      "loss": 0.558,
      "step": 22957
    },
    {
      "epoch": 0.7052499001628114,
      "grad_norm": 0.3448316156864166,
      "learning_rate": 1.4494676569832655e-05,
      "loss": 0.586,
      "step": 22958
    },
    {
      "epoch": 0.7052806192977605,
      "grad_norm": 0.3816393315792084,
      "learning_rate": 1.4494244854579824e-05,
      "loss": 0.6575,
      "step": 22959
    },
    {
      "epoch": 0.7053113384327098,
      "grad_norm": 0.39507728815078735,
      "learning_rate": 1.4493813128830375e-05,
      "loss": 0.466,
      "step": 22960
    },
    {
      "epoch": 0.7053420575676589,
      "grad_norm": 0.3625277876853943,
      "learning_rate": 1.4493381392585306e-05,
      "loss": 0.5433,
      "step": 22961
    },
    {
      "epoch": 0.705372776702608,
      "grad_norm": 0.7628723978996277,
      "learning_rate": 1.4492949645845633e-05,
      "loss": 0.5923,
      "step": 22962
    },
    {
      "epoch": 0.7054034958375572,
      "grad_norm": 0.40936988592147827,
      "learning_rate": 1.449251788861236e-05,
      "loss": 0.5445,
      "step": 22963
    },
    {
      "epoch": 0.7054342149725064,
      "grad_norm": 0.3470347821712494,
      "learning_rate": 1.4492086120886502e-05,
      "loss": 0.5657,
      "step": 22964
    },
    {
      "epoch": 0.7054649341074556,
      "grad_norm": 0.3826867640018463,
      "learning_rate": 1.4491654342669059e-05,
      "loss": 0.5645,
      "step": 22965
    },
    {
      "epoch": 0.7054956532424047,
      "grad_norm": 0.37732645869255066,
      "learning_rate": 1.4491222553961048e-05,
      "loss": 0.5472,
      "step": 22966
    },
    {
      "epoch": 0.7055263723773538,
      "grad_norm": 0.4038812518119812,
      "learning_rate": 1.4490790754763471e-05,
      "loss": 0.5691,
      "step": 22967
    },
    {
      "epoch": 0.7055570915123031,
      "grad_norm": 0.4108286201953888,
      "learning_rate": 1.4490358945077336e-05,
      "loss": 0.5304,
      "step": 22968
    },
    {
      "epoch": 0.7055878106472522,
      "grad_norm": 0.3603500425815582,
      "learning_rate": 1.4489927124903658e-05,
      "loss": 0.5431,
      "step": 22969
    },
    {
      "epoch": 0.7056185297822013,
      "grad_norm": 0.352876752614975,
      "learning_rate": 1.4489495294243439e-05,
      "loss": 0.5293,
      "step": 22970
    },
    {
      "epoch": 0.7056492489171505,
      "grad_norm": 0.5635542869567871,
      "learning_rate": 1.4489063453097694e-05,
      "loss": 0.6368,
      "step": 22971
    },
    {
      "epoch": 0.7056799680520996,
      "grad_norm": 0.45358970761299133,
      "learning_rate": 1.4488631601467422e-05,
      "loss": 0.5735,
      "step": 22972
    },
    {
      "epoch": 0.7057106871870488,
      "grad_norm": 0.34158214926719666,
      "learning_rate": 1.4488199739353642e-05,
      "loss": 0.5782,
      "step": 22973
    },
    {
      "epoch": 0.705741406321998,
      "grad_norm": 0.3507739305496216,
      "learning_rate": 1.4487767866757355e-05,
      "loss": 0.4917,
      "step": 22974
    },
    {
      "epoch": 0.7057721254569471,
      "grad_norm": 0.32589250802993774,
      "learning_rate": 1.4487335983679575e-05,
      "loss": 0.5702,
      "step": 22975
    },
    {
      "epoch": 0.7058028445918962,
      "grad_norm": 0.4101223349571228,
      "learning_rate": 1.4486904090121305e-05,
      "loss": 0.5611,
      "step": 22976
    },
    {
      "epoch": 0.7058335637268455,
      "grad_norm": 0.3555884063243866,
      "learning_rate": 1.4486472186083563e-05,
      "loss": 0.4975,
      "step": 22977
    },
    {
      "epoch": 0.7058642828617946,
      "grad_norm": 0.47983866930007935,
      "learning_rate": 1.4486040271567348e-05,
      "loss": 0.5309,
      "step": 22978
    },
    {
      "epoch": 0.7058950019967438,
      "grad_norm": 0.35189497470855713,
      "learning_rate": 1.448560834657367e-05,
      "loss": 0.6225,
      "step": 22979
    },
    {
      "epoch": 0.7059257211316929,
      "grad_norm": 0.3749738335609436,
      "learning_rate": 1.4485176411103545e-05,
      "loss": 0.48,
      "step": 22980
    },
    {
      "epoch": 0.7059564402666421,
      "grad_norm": 0.3425863981246948,
      "learning_rate": 1.4484744465157974e-05,
      "loss": 0.5836,
      "step": 22981
    },
    {
      "epoch": 0.7059871594015913,
      "grad_norm": 0.3295155167579651,
      "learning_rate": 1.4484312508737972e-05,
      "loss": 0.5395,
      "step": 22982
    },
    {
      "epoch": 0.7060178785365404,
      "grad_norm": 0.4169027507305145,
      "learning_rate": 1.4483880541844544e-05,
      "loss": 0.5578,
      "step": 22983
    },
    {
      "epoch": 0.7060485976714895,
      "grad_norm": 0.37750154733657837,
      "learning_rate": 1.4483448564478701e-05,
      "loss": 0.5738,
      "step": 22984
    },
    {
      "epoch": 0.7060793168064388,
      "grad_norm": 0.3774126172065735,
      "learning_rate": 1.4483016576641449e-05,
      "loss": 0.5118,
      "step": 22985
    },
    {
      "epoch": 0.7061100359413879,
      "grad_norm": 0.33417850732803345,
      "learning_rate": 1.4482584578333799e-05,
      "loss": 0.526,
      "step": 22986
    },
    {
      "epoch": 0.706140755076337,
      "grad_norm": 0.3588663637638092,
      "learning_rate": 1.4482152569556762e-05,
      "loss": 0.5721,
      "step": 22987
    },
    {
      "epoch": 0.7061714742112862,
      "grad_norm": 0.3736327290534973,
      "learning_rate": 1.448172055031134e-05,
      "loss": 0.5525,
      "step": 22988
    },
    {
      "epoch": 0.7062021933462354,
      "grad_norm": 0.3529767692089081,
      "learning_rate": 1.448128852059855e-05,
      "loss": 0.5801,
      "step": 22989
    },
    {
      "epoch": 0.7062329124811846,
      "grad_norm": 1.4871511459350586,
      "learning_rate": 1.4480856480419397e-05,
      "loss": 0.5723,
      "step": 22990
    },
    {
      "epoch": 0.7062636316161337,
      "grad_norm": 0.48468926548957825,
      "learning_rate": 1.448042442977489e-05,
      "loss": 0.4697,
      "step": 22991
    },
    {
      "epoch": 0.7062943507510828,
      "grad_norm": 0.3315890431404114,
      "learning_rate": 1.447999236866604e-05,
      "loss": 0.4556,
      "step": 22992
    },
    {
      "epoch": 0.706325069886032,
      "grad_norm": 0.3729872405529022,
      "learning_rate": 1.4479560297093853e-05,
      "loss": 0.523,
      "step": 22993
    },
    {
      "epoch": 0.7063557890209812,
      "grad_norm": 0.3324905335903168,
      "learning_rate": 1.4479128215059341e-05,
      "loss": 0.5137,
      "step": 22994
    },
    {
      "epoch": 0.7063865081559303,
      "grad_norm": 0.42850205302238464,
      "learning_rate": 1.4478696122563514e-05,
      "loss": 0.5165,
      "step": 22995
    },
    {
      "epoch": 0.7064172272908795,
      "grad_norm": 0.3482384979724884,
      "learning_rate": 1.4478264019607378e-05,
      "loss": 0.5408,
      "step": 22996
    },
    {
      "epoch": 0.7064479464258286,
      "grad_norm": 0.3566868305206299,
      "learning_rate": 1.4477831906191941e-05,
      "loss": 0.6102,
      "step": 22997
    },
    {
      "epoch": 0.7064786655607778,
      "grad_norm": 0.39712342619895935,
      "learning_rate": 1.447739978231822e-05,
      "loss": 0.4705,
      "step": 22998
    },
    {
      "epoch": 0.706509384695727,
      "grad_norm": 0.4323369860649109,
      "learning_rate": 1.4476967647987215e-05,
      "loss": 0.566,
      "step": 22999
    },
    {
      "epoch": 0.7065401038306761,
      "grad_norm": 0.4160631597042084,
      "learning_rate": 1.4476535503199943e-05,
      "loss": 0.5477,
      "step": 23000
    },
    {
      "epoch": 0.7065708229656252,
      "grad_norm": 0.4066062569618225,
      "learning_rate": 1.4476103347957408e-05,
      "loss": 0.5424,
      "step": 23001
    },
    {
      "epoch": 0.7066015421005745,
      "grad_norm": 0.5372565984725952,
      "learning_rate": 1.447567118226062e-05,
      "loss": 0.48,
      "step": 23002
    },
    {
      "epoch": 0.7066322612355236,
      "grad_norm": 0.3195563554763794,
      "learning_rate": 1.447523900611059e-05,
      "loss": 0.5714,
      "step": 23003
    },
    {
      "epoch": 0.7066629803704728,
      "grad_norm": 0.385177344083786,
      "learning_rate": 1.4474806819508328e-05,
      "loss": 0.6046,
      "step": 23004
    },
    {
      "epoch": 0.7066936995054219,
      "grad_norm": 0.7284210324287415,
      "learning_rate": 1.447437462245484e-05,
      "loss": 0.5183,
      "step": 23005
    },
    {
      "epoch": 0.706724418640371,
      "grad_norm": 0.4066028594970703,
      "learning_rate": 1.4473942414951138e-05,
      "loss": 0.5204,
      "step": 23006
    },
    {
      "epoch": 0.7067551377753203,
      "grad_norm": 0.37680259346961975,
      "learning_rate": 1.4473510196998232e-05,
      "loss": 0.6599,
      "step": 23007
    },
    {
      "epoch": 0.7067858569102694,
      "grad_norm": 0.3801862299442291,
      "learning_rate": 1.4473077968597131e-05,
      "loss": 0.5724,
      "step": 23008
    },
    {
      "epoch": 0.7068165760452185,
      "grad_norm": 0.511515736579895,
      "learning_rate": 1.4472645729748844e-05,
      "loss": 0.5988,
      "step": 23009
    },
    {
      "epoch": 0.7068472951801678,
      "grad_norm": 0.35925593972206116,
      "learning_rate": 1.4472213480454378e-05,
      "loss": 0.5337,
      "step": 23010
    },
    {
      "epoch": 0.7068780143151169,
      "grad_norm": 0.3943916857242584,
      "learning_rate": 1.4471781220714749e-05,
      "loss": 0.6478,
      "step": 23011
    },
    {
      "epoch": 0.706908733450066,
      "grad_norm": 0.4322599172592163,
      "learning_rate": 1.447134895053096e-05,
      "loss": 0.5424,
      "step": 23012
    },
    {
      "epoch": 0.7069394525850152,
      "grad_norm": 0.4154728651046753,
      "learning_rate": 1.4470916669904022e-05,
      "loss": 0.5452,
      "step": 23013
    },
    {
      "epoch": 0.7069701717199643,
      "grad_norm": 0.588262140750885,
      "learning_rate": 1.4470484378834948e-05,
      "loss": 0.4878,
      "step": 23014
    },
    {
      "epoch": 0.7070008908549136,
      "grad_norm": 0.3484846353530884,
      "learning_rate": 1.4470052077324743e-05,
      "loss": 0.5419,
      "step": 23015
    },
    {
      "epoch": 0.7070316099898627,
      "grad_norm": 0.39448282122612,
      "learning_rate": 1.4469619765374422e-05,
      "loss": 0.5385,
      "step": 23016
    },
    {
      "epoch": 0.7070623291248118,
      "grad_norm": 0.3779955208301544,
      "learning_rate": 1.446918744298499e-05,
      "loss": 0.5498,
      "step": 23017
    },
    {
      "epoch": 0.707093048259761,
      "grad_norm": 0.3844943642616272,
      "learning_rate": 1.4468755110157461e-05,
      "loss": 0.614,
      "step": 23018
    },
    {
      "epoch": 0.7071237673947102,
      "grad_norm": 0.3402717113494873,
      "learning_rate": 1.4468322766892845e-05,
      "loss": 0.59,
      "step": 23019
    },
    {
      "epoch": 0.7071544865296593,
      "grad_norm": 0.43103745579719543,
      "learning_rate": 1.4467890413192143e-05,
      "loss": 0.5966,
      "step": 23020
    },
    {
      "epoch": 0.7071852056646085,
      "grad_norm": 0.3776431977748871,
      "learning_rate": 1.4467458049056374e-05,
      "loss": 0.5401,
      "step": 23021
    },
    {
      "epoch": 0.7072159247995576,
      "grad_norm": 0.37983769178390503,
      "learning_rate": 1.4467025674486541e-05,
      "loss": 0.6152,
      "step": 23022
    },
    {
      "epoch": 0.7072466439345068,
      "grad_norm": 0.3602312505245209,
      "learning_rate": 1.4466593289483663e-05,
      "loss": 0.5822,
      "step": 23023
    },
    {
      "epoch": 0.707277363069456,
      "grad_norm": 0.3617551028728485,
      "learning_rate": 1.446616089404874e-05,
      "loss": 0.6186,
      "step": 23024
    },
    {
      "epoch": 0.7073080822044051,
      "grad_norm": 0.34657007455825806,
      "learning_rate": 1.4465728488182792e-05,
      "loss": 0.5291,
      "step": 23025
    },
    {
      "epoch": 0.7073388013393542,
      "grad_norm": 0.35015618801116943,
      "learning_rate": 1.4465296071886816e-05,
      "loss": 0.6574,
      "step": 23026
    },
    {
      "epoch": 0.7073695204743035,
      "grad_norm": 0.37855157256126404,
      "learning_rate": 1.4464863645161833e-05,
      "loss": 0.5433,
      "step": 23027
    },
    {
      "epoch": 0.7074002396092526,
      "grad_norm": 0.40738242864608765,
      "learning_rate": 1.4464431208008849e-05,
      "loss": 0.5633,
      "step": 23028
    },
    {
      "epoch": 0.7074309587442018,
      "grad_norm": 0.33447393774986267,
      "learning_rate": 1.4463998760428875e-05,
      "loss": 0.5109,
      "step": 23029
    },
    {
      "epoch": 0.7074616778791509,
      "grad_norm": 0.6916822791099548,
      "learning_rate": 1.446356630242292e-05,
      "loss": 0.5482,
      "step": 23030
    },
    {
      "epoch": 0.7074923970141,
      "grad_norm": 0.3667564392089844,
      "learning_rate": 1.4463133833991991e-05,
      "loss": 0.5876,
      "step": 23031
    },
    {
      "epoch": 0.7075231161490493,
      "grad_norm": 0.39976921677589417,
      "learning_rate": 1.4462701355137104e-05,
      "loss": 0.5807,
      "step": 23032
    },
    {
      "epoch": 0.7075538352839984,
      "grad_norm": 0.36124712228775024,
      "learning_rate": 1.4462268865859264e-05,
      "loss": 0.5624,
      "step": 23033
    },
    {
      "epoch": 0.7075845544189475,
      "grad_norm": 0.36961832642555237,
      "learning_rate": 1.4461836366159485e-05,
      "loss": 0.5676,
      "step": 23034
    },
    {
      "epoch": 0.7076152735538968,
      "grad_norm": 0.3493576943874359,
      "learning_rate": 1.4461403856038776e-05,
      "loss": 0.5501,
      "step": 23035
    },
    {
      "epoch": 0.7076459926888459,
      "grad_norm": 0.33467769622802734,
      "learning_rate": 1.4460971335498146e-05,
      "loss": 0.5462,
      "step": 23036
    },
    {
      "epoch": 0.707676711823795,
      "grad_norm": 0.3930888772010803,
      "learning_rate": 1.4460538804538606e-05,
      "loss": 0.5743,
      "step": 23037
    },
    {
      "epoch": 0.7077074309587442,
      "grad_norm": 0.3731018900871277,
      "learning_rate": 1.4460106263161167e-05,
      "loss": 0.5403,
      "step": 23038
    },
    {
      "epoch": 0.7077381500936933,
      "grad_norm": 0.8386621475219727,
      "learning_rate": 1.4459673711366837e-05,
      "loss": 0.4738,
      "step": 23039
    },
    {
      "epoch": 0.7077688692286426,
      "grad_norm": 0.35183101892471313,
      "learning_rate": 1.4459241149156628e-05,
      "loss": 0.5392,
      "step": 23040
    },
    {
      "epoch": 0.7077995883635917,
      "grad_norm": 0.40955692529678345,
      "learning_rate": 1.445880857653155e-05,
      "loss": 0.5261,
      "step": 23041
    },
    {
      "epoch": 0.7078303074985408,
      "grad_norm": 0.3801997900009155,
      "learning_rate": 1.4458375993492615e-05,
      "loss": 0.5549,
      "step": 23042
    },
    {
      "epoch": 0.70786102663349,
      "grad_norm": 0.3660202920436859,
      "learning_rate": 1.445794340004083e-05,
      "loss": 0.5269,
      "step": 23043
    },
    {
      "epoch": 0.7078917457684392,
      "grad_norm": 0.36117592453956604,
      "learning_rate": 1.4457510796177205e-05,
      "loss": 0.5596,
      "step": 23044
    },
    {
      "epoch": 0.7079224649033883,
      "grad_norm": 0.3861066401004791,
      "learning_rate": 1.4457078181902755e-05,
      "loss": 0.4393,
      "step": 23045
    },
    {
      "epoch": 0.7079531840383375,
      "grad_norm": 0.4105859100818634,
      "learning_rate": 1.4456645557218484e-05,
      "loss": 0.5627,
      "step": 23046
    },
    {
      "epoch": 0.7079839031732866,
      "grad_norm": 0.3678833544254303,
      "learning_rate": 1.4456212922125412e-05,
      "loss": 0.5278,
      "step": 23047
    },
    {
      "epoch": 0.7080146223082358,
      "grad_norm": 0.33302041888237,
      "learning_rate": 1.445578027662454e-05,
      "loss": 0.5385,
      "step": 23048
    },
    {
      "epoch": 0.708045341443185,
      "grad_norm": 0.4505271911621094,
      "learning_rate": 1.4455347620716881e-05,
      "loss": 0.5007,
      "step": 23049
    },
    {
      "epoch": 0.7080760605781341,
      "grad_norm": 0.4627983868122101,
      "learning_rate": 1.445491495440345e-05,
      "loss": 0.6179,
      "step": 23050
    },
    {
      "epoch": 0.7081067797130833,
      "grad_norm": 0.46214690804481506,
      "learning_rate": 1.4454482277685248e-05,
      "loss": 0.5513,
      "step": 23051
    },
    {
      "epoch": 0.7081374988480325,
      "grad_norm": 0.3707757890224457,
      "learning_rate": 1.4454049590563295e-05,
      "loss": 0.592,
      "step": 23052
    },
    {
      "epoch": 0.7081682179829816,
      "grad_norm": 0.42383474111557007,
      "learning_rate": 1.44536168930386e-05,
      "loss": 0.5093,
      "step": 23053
    },
    {
      "epoch": 0.7081989371179308,
      "grad_norm": 0.4326099753379822,
      "learning_rate": 1.4453184185112168e-05,
      "loss": 0.5773,
      "step": 23054
    },
    {
      "epoch": 0.7082296562528799,
      "grad_norm": 0.4413365125656128,
      "learning_rate": 1.4452751466785018e-05,
      "loss": 0.6201,
      "step": 23055
    },
    {
      "epoch": 0.708260375387829,
      "grad_norm": 0.32307571172714233,
      "learning_rate": 1.445231873805815e-05,
      "loss": 0.507,
      "step": 23056
    },
    {
      "epoch": 0.7082910945227783,
      "grad_norm": 0.3526722192764282,
      "learning_rate": 1.4451885998932587e-05,
      "loss": 0.5219,
      "step": 23057
    },
    {
      "epoch": 0.7083218136577274,
      "grad_norm": 0.333835244178772,
      "learning_rate": 1.445145324940933e-05,
      "loss": 0.5549,
      "step": 23058
    },
    {
      "epoch": 0.7083525327926765,
      "grad_norm": 0.3434488773345947,
      "learning_rate": 1.445102048948939e-05,
      "loss": 0.5314,
      "step": 23059
    },
    {
      "epoch": 0.7083832519276257,
      "grad_norm": 0.34878432750701904,
      "learning_rate": 1.4450587719173786e-05,
      "loss": 0.5195,
      "step": 23060
    },
    {
      "epoch": 0.7084139710625749,
      "grad_norm": 0.39832648634910583,
      "learning_rate": 1.445015493846352e-05,
      "loss": 0.5439,
      "step": 23061
    },
    {
      "epoch": 0.708444690197524,
      "grad_norm": 0.36931538581848145,
      "learning_rate": 1.4449722147359608e-05,
      "loss": 0.4577,
      "step": 23062
    },
    {
      "epoch": 0.7084754093324732,
      "grad_norm": 0.35550153255462646,
      "learning_rate": 1.4449289345863062e-05,
      "loss": 0.5684,
      "step": 23063
    },
    {
      "epoch": 0.7085061284674223,
      "grad_norm": 0.4660094976425171,
      "learning_rate": 1.4448856533974887e-05,
      "loss": 0.5414,
      "step": 23064
    },
    {
      "epoch": 0.7085368476023716,
      "grad_norm": 0.3434155285358429,
      "learning_rate": 1.4448423711696096e-05,
      "loss": 0.5671,
      "step": 23065
    },
    {
      "epoch": 0.7085675667373207,
      "grad_norm": 0.39096999168395996,
      "learning_rate": 1.4447990879027703e-05,
      "loss": 0.5399,
      "step": 23066
    },
    {
      "epoch": 0.7085982858722698,
      "grad_norm": 0.3465670943260193,
      "learning_rate": 1.4447558035970715e-05,
      "loss": 0.5601,
      "step": 23067
    },
    {
      "epoch": 0.708629005007219,
      "grad_norm": 0.41028523445129395,
      "learning_rate": 1.4447125182526145e-05,
      "loss": 0.5139,
      "step": 23068
    },
    {
      "epoch": 0.7086597241421682,
      "grad_norm": 0.3677568733692169,
      "learning_rate": 1.4446692318695e-05,
      "loss": 0.6041,
      "step": 23069
    },
    {
      "epoch": 0.7086904432771173,
      "grad_norm": 0.40022456645965576,
      "learning_rate": 1.4446259444478298e-05,
      "loss": 0.6552,
      "step": 23070
    },
    {
      "epoch": 0.7087211624120665,
      "grad_norm": 0.372785359621048,
      "learning_rate": 1.4445826559877048e-05,
      "loss": 0.5191,
      "step": 23071
    },
    {
      "epoch": 0.7087518815470156,
      "grad_norm": 0.4220815896987915,
      "learning_rate": 1.4445393664892257e-05,
      "loss": 0.5863,
      "step": 23072
    },
    {
      "epoch": 0.7087826006819647,
      "grad_norm": 0.3445606231689453,
      "learning_rate": 1.4444960759524942e-05,
      "loss": 0.4955,
      "step": 23073
    },
    {
      "epoch": 0.708813319816914,
      "grad_norm": 0.36066901683807373,
      "learning_rate": 1.4444527843776106e-05,
      "loss": 0.5742,
      "step": 23074
    },
    {
      "epoch": 0.7088440389518631,
      "grad_norm": 0.4167182743549347,
      "learning_rate": 1.4444094917646769e-05,
      "loss": 0.5154,
      "step": 23075
    },
    {
      "epoch": 0.7088747580868123,
      "grad_norm": 0.3348700702190399,
      "learning_rate": 1.4443661981137935e-05,
      "loss": 0.5178,
      "step": 23076
    },
    {
      "epoch": 0.7089054772217614,
      "grad_norm": 0.35245281457901,
      "learning_rate": 1.4443229034250621e-05,
      "loss": 0.5752,
      "step": 23077
    },
    {
      "epoch": 0.7089361963567106,
      "grad_norm": 0.3634800612926483,
      "learning_rate": 1.4442796076985833e-05,
      "loss": 0.5037,
      "step": 23078
    },
    {
      "epoch": 0.7089669154916598,
      "grad_norm": 0.3458399474620819,
      "learning_rate": 1.4442363109344586e-05,
      "loss": 0.5571,
      "step": 23079
    },
    {
      "epoch": 0.7089976346266089,
      "grad_norm": 0.3611626625061035,
      "learning_rate": 1.4441930131327888e-05,
      "loss": 0.6063,
      "step": 23080
    },
    {
      "epoch": 0.709028353761558,
      "grad_norm": 0.41884487867355347,
      "learning_rate": 1.4441497142936753e-05,
      "loss": 0.4847,
      "step": 23081
    },
    {
      "epoch": 0.7090590728965073,
      "grad_norm": 0.48781508207321167,
      "learning_rate": 1.4441064144172192e-05,
      "loss": 0.5834,
      "step": 23082
    },
    {
      "epoch": 0.7090897920314564,
      "grad_norm": 0.3499770760536194,
      "learning_rate": 1.4440631135035212e-05,
      "loss": 0.5017,
      "step": 23083
    },
    {
      "epoch": 0.7091205111664055,
      "grad_norm": 0.3855915367603302,
      "learning_rate": 1.4440198115526833e-05,
      "loss": 0.6076,
      "step": 23084
    },
    {
      "epoch": 0.7091512303013547,
      "grad_norm": 0.34242692589759827,
      "learning_rate": 1.4439765085648056e-05,
      "loss": 0.5193,
      "step": 23085
    },
    {
      "epoch": 0.7091819494363039,
      "grad_norm": 0.36987176537513733,
      "learning_rate": 1.4439332045399904e-05,
      "loss": 0.632,
      "step": 23086
    },
    {
      "epoch": 0.709212668571253,
      "grad_norm": 0.3636292517185211,
      "learning_rate": 1.4438898994783375e-05,
      "loss": 0.5667,
      "step": 23087
    },
    {
      "epoch": 0.7092433877062022,
      "grad_norm": 0.39753931760787964,
      "learning_rate": 1.443846593379949e-05,
      "loss": 0.6015,
      "step": 23088
    },
    {
      "epoch": 0.7092741068411513,
      "grad_norm": 0.3583000600337982,
      "learning_rate": 1.443803286244926e-05,
      "loss": 0.5412,
      "step": 23089
    },
    {
      "epoch": 0.7093048259761006,
      "grad_norm": 0.33592551946640015,
      "learning_rate": 1.443759978073369e-05,
      "loss": 0.5773,
      "step": 23090
    },
    {
      "epoch": 0.7093355451110497,
      "grad_norm": 0.3573514521121979,
      "learning_rate": 1.44371666886538e-05,
      "loss": 0.5359,
      "step": 23091
    },
    {
      "epoch": 0.7093662642459988,
      "grad_norm": 0.8026015162467957,
      "learning_rate": 1.4436733586210597e-05,
      "loss": 0.6404,
      "step": 23092
    },
    {
      "epoch": 0.709396983380948,
      "grad_norm": 0.3329825699329376,
      "learning_rate": 1.4436300473405092e-05,
      "loss": 0.5301,
      "step": 23093
    },
    {
      "epoch": 0.7094277025158972,
      "grad_norm": 0.38807255029678345,
      "learning_rate": 1.4435867350238295e-05,
      "loss": 0.625,
      "step": 23094
    },
    {
      "epoch": 0.7094584216508463,
      "grad_norm": 0.34749889373779297,
      "learning_rate": 1.4435434216711223e-05,
      "loss": 0.4915,
      "step": 23095
    },
    {
      "epoch": 0.7094891407857955,
      "grad_norm": 0.36177024245262146,
      "learning_rate": 1.4435001072824883e-05,
      "loss": 0.6207,
      "step": 23096
    },
    {
      "epoch": 0.7095198599207446,
      "grad_norm": 0.3792213797569275,
      "learning_rate": 1.443456791858029e-05,
      "loss": 0.5247,
      "step": 23097
    },
    {
      "epoch": 0.7095505790556937,
      "grad_norm": 0.3884359896183014,
      "learning_rate": 1.4434134753978452e-05,
      "loss": 0.4529,
      "step": 23098
    },
    {
      "epoch": 0.709581298190643,
      "grad_norm": 0.35379791259765625,
      "learning_rate": 1.4433701579020384e-05,
      "loss": 0.5183,
      "step": 23099
    },
    {
      "epoch": 0.7096120173255921,
      "grad_norm": 0.3638116717338562,
      "learning_rate": 1.4433268393707096e-05,
      "loss": 0.5418,
      "step": 23100
    },
    {
      "epoch": 0.7096427364605413,
      "grad_norm": 0.3687261641025543,
      "learning_rate": 1.44328351980396e-05,
      "loss": 0.5195,
      "step": 23101
    },
    {
      "epoch": 0.7096734555954904,
      "grad_norm": 0.37641438841819763,
      "learning_rate": 1.4432401992018908e-05,
      "loss": 0.5005,
      "step": 23102
    },
    {
      "epoch": 0.7097041747304396,
      "grad_norm": 0.3433673083782196,
      "learning_rate": 1.443196877564603e-05,
      "loss": 0.5577,
      "step": 23103
    },
    {
      "epoch": 0.7097348938653888,
      "grad_norm": 0.4470759928226471,
      "learning_rate": 1.4431535548921981e-05,
      "loss": 0.5269,
      "step": 23104
    },
    {
      "epoch": 0.7097656130003379,
      "grad_norm": 0.3392722010612488,
      "learning_rate": 1.4431102311847772e-05,
      "loss": 0.5687,
      "step": 23105
    },
    {
      "epoch": 0.709796332135287,
      "grad_norm": 0.42907336354255676,
      "learning_rate": 1.4430669064424412e-05,
      "loss": 0.5816,
      "step": 23106
    },
    {
      "epoch": 0.7098270512702363,
      "grad_norm": 0.3783896863460541,
      "learning_rate": 1.4430235806652915e-05,
      "loss": 0.6268,
      "step": 23107
    },
    {
      "epoch": 0.7098577704051854,
      "grad_norm": 0.38889607787132263,
      "learning_rate": 1.4429802538534294e-05,
      "loss": 0.4631,
      "step": 23108
    },
    {
      "epoch": 0.7098884895401345,
      "grad_norm": 0.36080121994018555,
      "learning_rate": 1.4429369260069559e-05,
      "loss": 0.5442,
      "step": 23109
    },
    {
      "epoch": 0.7099192086750837,
      "grad_norm": 0.31648266315460205,
      "learning_rate": 1.4428935971259723e-05,
      "loss": 0.5558,
      "step": 23110
    },
    {
      "epoch": 0.7099499278100329,
      "grad_norm": 0.3757586181163788,
      "learning_rate": 1.44285026721058e-05,
      "loss": 0.512,
      "step": 23111
    },
    {
      "epoch": 0.709980646944982,
      "grad_norm": 0.3717178404331207,
      "learning_rate": 1.4428069362608796e-05,
      "loss": 0.5651,
      "step": 23112
    },
    {
      "epoch": 0.7100113660799312,
      "grad_norm": 0.3475629687309265,
      "learning_rate": 1.4427636042769728e-05,
      "loss": 0.5819,
      "step": 23113
    },
    {
      "epoch": 0.7100420852148803,
      "grad_norm": 0.3877166211605072,
      "learning_rate": 1.4427202712589608e-05,
      "loss": 0.5226,
      "step": 23114
    },
    {
      "epoch": 0.7100728043498296,
      "grad_norm": 0.3571532368659973,
      "learning_rate": 1.4426769372069446e-05,
      "loss": 0.6254,
      "step": 23115
    },
    {
      "epoch": 0.7101035234847787,
      "grad_norm": 0.3352164626121521,
      "learning_rate": 1.4426336021210257e-05,
      "loss": 0.5367,
      "step": 23116
    },
    {
      "epoch": 0.7101342426197278,
      "grad_norm": 0.389855295419693,
      "learning_rate": 1.4425902660013047e-05,
      "loss": 0.5336,
      "step": 23117
    },
    {
      "epoch": 0.710164961754677,
      "grad_norm": 0.48637062311172485,
      "learning_rate": 1.4425469288478837e-05,
      "loss": 0.6014,
      "step": 23118
    },
    {
      "epoch": 0.7101956808896261,
      "grad_norm": 0.3846763074398041,
      "learning_rate": 1.442503590660863e-05,
      "loss": 0.5201,
      "step": 23119
    },
    {
      "epoch": 0.7102264000245753,
      "grad_norm": 0.3414325714111328,
      "learning_rate": 1.4424602514403446e-05,
      "loss": 0.5722,
      "step": 23120
    },
    {
      "epoch": 0.7102571191595245,
      "grad_norm": 0.4340962767601013,
      "learning_rate": 1.4424169111864292e-05,
      "loss": 0.6557,
      "step": 23121
    },
    {
      "epoch": 0.7102878382944736,
      "grad_norm": 0.35195252299308777,
      "learning_rate": 1.4423735698992182e-05,
      "loss": 0.5233,
      "step": 23122
    },
    {
      "epoch": 0.7103185574294227,
      "grad_norm": 0.3571989834308624,
      "learning_rate": 1.4423302275788129e-05,
      "loss": 0.6249,
      "step": 23123
    },
    {
      "epoch": 0.710349276564372,
      "grad_norm": 0.37197771668434143,
      "learning_rate": 1.4422868842253142e-05,
      "loss": 0.5459,
      "step": 23124
    },
    {
      "epoch": 0.7103799956993211,
      "grad_norm": 0.37214046716690063,
      "learning_rate": 1.4422435398388238e-05,
      "loss": 0.6276,
      "step": 23125
    },
    {
      "epoch": 0.7104107148342703,
      "grad_norm": 0.3478812277317047,
      "learning_rate": 1.4422001944194428e-05,
      "loss": 0.5993,
      "step": 23126
    },
    {
      "epoch": 0.7104414339692194,
      "grad_norm": 0.3654778301715851,
      "learning_rate": 1.4421568479672724e-05,
      "loss": 0.5434,
      "step": 23127
    },
    {
      "epoch": 0.7104721531041686,
      "grad_norm": 0.3626367449760437,
      "learning_rate": 1.4421135004824136e-05,
      "loss": 0.6272,
      "step": 23128
    },
    {
      "epoch": 0.7105028722391178,
      "grad_norm": 0.34407490491867065,
      "learning_rate": 1.442070151964968e-05,
      "loss": 0.5054,
      "step": 23129
    },
    {
      "epoch": 0.7105335913740669,
      "grad_norm": 0.3517288565635681,
      "learning_rate": 1.4420268024150365e-05,
      "loss": 0.5591,
      "step": 23130
    },
    {
      "epoch": 0.710564310509016,
      "grad_norm": 0.3527558445930481,
      "learning_rate": 1.441983451832721e-05,
      "loss": 0.6294,
      "step": 23131
    },
    {
      "epoch": 0.7105950296439653,
      "grad_norm": 0.34687817096710205,
      "learning_rate": 1.4419401002181217e-05,
      "loss": 0.5132,
      "step": 23132
    },
    {
      "epoch": 0.7106257487789144,
      "grad_norm": 0.3705577254295349,
      "learning_rate": 1.4418967475713409e-05,
      "loss": 0.5784,
      "step": 23133
    },
    {
      "epoch": 0.7106564679138635,
      "grad_norm": 0.3985271751880646,
      "learning_rate": 1.4418533938924793e-05,
      "loss": 0.6006,
      "step": 23134
    },
    {
      "epoch": 0.7106871870488127,
      "grad_norm": 0.3586808145046234,
      "learning_rate": 1.4418100391816379e-05,
      "loss": 0.5196,
      "step": 23135
    },
    {
      "epoch": 0.7107179061837618,
      "grad_norm": 0.355976402759552,
      "learning_rate": 1.4417666834389186e-05,
      "loss": 0.5504,
      "step": 23136
    },
    {
      "epoch": 0.7107486253187111,
      "grad_norm": 0.36334526538848877,
      "learning_rate": 1.4417233266644222e-05,
      "loss": 0.6067,
      "step": 23137
    },
    {
      "epoch": 0.7107793444536602,
      "grad_norm": 0.4030219316482544,
      "learning_rate": 1.4416799688582503e-05,
      "loss": 0.5995,
      "step": 23138
    },
    {
      "epoch": 0.7108100635886093,
      "grad_norm": 0.3105413615703583,
      "learning_rate": 1.4416366100205036e-05,
      "loss": 0.5032,
      "step": 23139
    },
    {
      "epoch": 0.7108407827235586,
      "grad_norm": 0.43707555532455444,
      "learning_rate": 1.4415932501512844e-05,
      "loss": 0.6419,
      "step": 23140
    },
    {
      "epoch": 0.7108715018585077,
      "grad_norm": 0.34092557430267334,
      "learning_rate": 1.4415498892506926e-05,
      "loss": 0.5514,
      "step": 23141
    },
    {
      "epoch": 0.7109022209934568,
      "grad_norm": 0.42173606157302856,
      "learning_rate": 1.4415065273188305e-05,
      "loss": 0.5854,
      "step": 23142
    },
    {
      "epoch": 0.710932940128406,
      "grad_norm": 0.366253525018692,
      "learning_rate": 1.4414631643557992e-05,
      "loss": 0.5963,
      "step": 23143
    },
    {
      "epoch": 0.7109636592633551,
      "grad_norm": 0.3504307270050049,
      "learning_rate": 1.4414198003616996e-05,
      "loss": 0.5117,
      "step": 23144
    },
    {
      "epoch": 0.7109943783983043,
      "grad_norm": 0.6091676950454712,
      "learning_rate": 1.4413764353366336e-05,
      "loss": 0.5936,
      "step": 23145
    },
    {
      "epoch": 0.7110250975332535,
      "grad_norm": 0.45024269819259644,
      "learning_rate": 1.441333069280702e-05,
      "loss": 0.6019,
      "step": 23146
    },
    {
      "epoch": 0.7110558166682026,
      "grad_norm": 0.4137520492076874,
      "learning_rate": 1.441289702194006e-05,
      "loss": 0.5727,
      "step": 23147
    },
    {
      "epoch": 0.7110865358031517,
      "grad_norm": 0.36061373353004456,
      "learning_rate": 1.4412463340766471e-05,
      "loss": 0.5656,
      "step": 23148
    },
    {
      "epoch": 0.711117254938101,
      "grad_norm": 0.4389161765575409,
      "learning_rate": 1.441202964928727e-05,
      "loss": 0.5492,
      "step": 23149
    },
    {
      "epoch": 0.7111479740730501,
      "grad_norm": 0.37058350443840027,
      "learning_rate": 1.4411595947503458e-05,
      "loss": 0.5525,
      "step": 23150
    },
    {
      "epoch": 0.7111786932079993,
      "grad_norm": 0.41106116771698,
      "learning_rate": 1.4411162235416061e-05,
      "loss": 0.5747,
      "step": 23151
    },
    {
      "epoch": 0.7112094123429484,
      "grad_norm": 0.4149491786956787,
      "learning_rate": 1.4410728513026086e-05,
      "loss": 0.5949,
      "step": 23152
    },
    {
      "epoch": 0.7112401314778976,
      "grad_norm": 0.3750985264778137,
      "learning_rate": 1.4410294780334546e-05,
      "loss": 0.5843,
      "step": 23153
    },
    {
      "epoch": 0.7112708506128468,
      "grad_norm": 0.35462892055511475,
      "learning_rate": 1.4409861037342454e-05,
      "loss": 0.6018,
      "step": 23154
    },
    {
      "epoch": 0.7113015697477959,
      "grad_norm": 0.3271157443523407,
      "learning_rate": 1.4409427284050824e-05,
      "loss": 0.574,
      "step": 23155
    },
    {
      "epoch": 0.711332288882745,
      "grad_norm": 0.40661928057670593,
      "learning_rate": 1.440899352046067e-05,
      "loss": 0.6022,
      "step": 23156
    },
    {
      "epoch": 0.7113630080176943,
      "grad_norm": 0.38703617453575134,
      "learning_rate": 1.4408559746572999e-05,
      "loss": 0.6287,
      "step": 23157
    },
    {
      "epoch": 0.7113937271526434,
      "grad_norm": 0.5234213471412659,
      "learning_rate": 1.4408125962388835e-05,
      "loss": 0.5602,
      "step": 23158
    },
    {
      "epoch": 0.7114244462875925,
      "grad_norm": 0.3974968194961548,
      "learning_rate": 1.440769216790918e-05,
      "loss": 0.5392,
      "step": 23159
    },
    {
      "epoch": 0.7114551654225417,
      "grad_norm": 0.4091323912143707,
      "learning_rate": 1.4407258363135053e-05,
      "loss": 0.5359,
      "step": 23160
    },
    {
      "epoch": 0.7114858845574908,
      "grad_norm": 0.3596690595149994,
      "learning_rate": 1.4406824548067469e-05,
      "loss": 0.5659,
      "step": 23161
    },
    {
      "epoch": 0.7115166036924401,
      "grad_norm": 0.36298155784606934,
      "learning_rate": 1.4406390722707436e-05,
      "loss": 0.5164,
      "step": 23162
    },
    {
      "epoch": 0.7115473228273892,
      "grad_norm": 0.34600916504859924,
      "learning_rate": 1.4405956887055973e-05,
      "loss": 0.5324,
      "step": 23163
    },
    {
      "epoch": 0.7115780419623383,
      "grad_norm": 0.39074718952178955,
      "learning_rate": 1.4405523041114084e-05,
      "loss": 0.5494,
      "step": 23164
    },
    {
      "epoch": 0.7116087610972875,
      "grad_norm": 0.38014692068099976,
      "learning_rate": 1.4405089184882793e-05,
      "loss": 0.5607,
      "step": 23165
    },
    {
      "epoch": 0.7116394802322367,
      "grad_norm": 0.37148168683052063,
      "learning_rate": 1.4404655318363108e-05,
      "loss": 0.585,
      "step": 23166
    },
    {
      "epoch": 0.7116701993671858,
      "grad_norm": 0.36409929394721985,
      "learning_rate": 1.4404221441556042e-05,
      "loss": 0.4892,
      "step": 23167
    },
    {
      "epoch": 0.711700918502135,
      "grad_norm": 0.35483771562576294,
      "learning_rate": 1.4403787554462607e-05,
      "loss": 0.5718,
      "step": 23168
    },
    {
      "epoch": 0.7117316376370841,
      "grad_norm": 0.330191969871521,
      "learning_rate": 1.4403353657083823e-05,
      "loss": 0.436,
      "step": 23169
    },
    {
      "epoch": 0.7117623567720333,
      "grad_norm": 0.3583383858203888,
      "learning_rate": 1.4402919749420699e-05,
      "loss": 0.5047,
      "step": 23170
    },
    {
      "epoch": 0.7117930759069825,
      "grad_norm": 0.5058189630508423,
      "learning_rate": 1.4402485831474245e-05,
      "loss": 0.58,
      "step": 23171
    },
    {
      "epoch": 0.7118237950419316,
      "grad_norm": 0.43713584542274475,
      "learning_rate": 1.440205190324548e-05,
      "loss": 0.5538,
      "step": 23172
    },
    {
      "epoch": 0.7118545141768807,
      "grad_norm": 0.33514082431793213,
      "learning_rate": 1.4401617964735415e-05,
      "loss": 0.5523,
      "step": 23173
    },
    {
      "epoch": 0.71188523331183,
      "grad_norm": 0.34641215205192566,
      "learning_rate": 1.4401184015945065e-05,
      "loss": 0.5597,
      "step": 23174
    },
    {
      "epoch": 0.7119159524467791,
      "grad_norm": 0.4287494421005249,
      "learning_rate": 1.440075005687544e-05,
      "loss": 0.5919,
      "step": 23175
    },
    {
      "epoch": 0.7119466715817283,
      "grad_norm": 0.5401845574378967,
      "learning_rate": 1.4400316087527557e-05,
      "loss": 0.506,
      "step": 23176
    },
    {
      "epoch": 0.7119773907166774,
      "grad_norm": 0.44411858916282654,
      "learning_rate": 1.4399882107902428e-05,
      "loss": 0.5616,
      "step": 23177
    },
    {
      "epoch": 0.7120081098516265,
      "grad_norm": 0.4344513416290283,
      "learning_rate": 1.4399448118001066e-05,
      "loss": 0.5393,
      "step": 23178
    },
    {
      "epoch": 0.7120388289865758,
      "grad_norm": 0.32687899470329285,
      "learning_rate": 1.4399014117824486e-05,
      "loss": 0.4815,
      "step": 23179
    },
    {
      "epoch": 0.7120695481215249,
      "grad_norm": 0.3641681969165802,
      "learning_rate": 1.4398580107373703e-05,
      "loss": 0.5535,
      "step": 23180
    },
    {
      "epoch": 0.712100267256474,
      "grad_norm": 0.3446493148803711,
      "learning_rate": 1.4398146086649728e-05,
      "loss": 0.5697,
      "step": 23181
    },
    {
      "epoch": 0.7121309863914232,
      "grad_norm": 0.4210122525691986,
      "learning_rate": 1.4397712055653577e-05,
      "loss": 0.4598,
      "step": 23182
    },
    {
      "epoch": 0.7121617055263724,
      "grad_norm": 0.3595261871814728,
      "learning_rate": 1.4397278014386262e-05,
      "loss": 0.5743,
      "step": 23183
    },
    {
      "epoch": 0.7121924246613215,
      "grad_norm": 0.34554776549339294,
      "learning_rate": 1.4396843962848794e-05,
      "loss": 0.5786,
      "step": 23184
    },
    {
      "epoch": 0.7122231437962707,
      "grad_norm": 0.42187047004699707,
      "learning_rate": 1.4396409901042195e-05,
      "loss": 0.5312,
      "step": 23185
    },
    {
      "epoch": 0.7122538629312198,
      "grad_norm": 0.3821777105331421,
      "learning_rate": 1.439597582896747e-05,
      "loss": 0.6443,
      "step": 23186
    },
    {
      "epoch": 0.7122845820661691,
      "grad_norm": 0.33297234773635864,
      "learning_rate": 1.4395541746625636e-05,
      "loss": 0.4766,
      "step": 23187
    },
    {
      "epoch": 0.7123153012011182,
      "grad_norm": 0.32210713624954224,
      "learning_rate": 1.4395107654017711e-05,
      "loss": 0.5172,
      "step": 23188
    },
    {
      "epoch": 0.7123460203360673,
      "grad_norm": 0.3457854390144348,
      "learning_rate": 1.43946735511447e-05,
      "loss": 0.5581,
      "step": 23189
    },
    {
      "epoch": 0.7123767394710165,
      "grad_norm": 0.336777001619339,
      "learning_rate": 1.4394239438007627e-05,
      "loss": 0.4611,
      "step": 23190
    },
    {
      "epoch": 0.7124074586059657,
      "grad_norm": 0.4799322187900543,
      "learning_rate": 1.4393805314607496e-05,
      "loss": 0.4805,
      "step": 23191
    },
    {
      "epoch": 0.7124381777409148,
      "grad_norm": 0.34266161918640137,
      "learning_rate": 1.439337118094533e-05,
      "loss": 0.5733,
      "step": 23192
    },
    {
      "epoch": 0.712468896875864,
      "grad_norm": 0.3782579004764557,
      "learning_rate": 1.4392937037022137e-05,
      "loss": 0.6275,
      "step": 23193
    },
    {
      "epoch": 0.7124996160108131,
      "grad_norm": 0.35909515619277954,
      "learning_rate": 1.4392502882838934e-05,
      "loss": 0.5783,
      "step": 23194
    },
    {
      "epoch": 0.7125303351457623,
      "grad_norm": 0.4945495128631592,
      "learning_rate": 1.4392068718396732e-05,
      "loss": 0.5301,
      "step": 23195
    },
    {
      "epoch": 0.7125610542807115,
      "grad_norm": 0.3391670882701874,
      "learning_rate": 1.4391634543696548e-05,
      "loss": 0.4759,
      "step": 23196
    },
    {
      "epoch": 0.7125917734156606,
      "grad_norm": 0.3458058536052704,
      "learning_rate": 1.4391200358739394e-05,
      "loss": 0.5754,
      "step": 23197
    },
    {
      "epoch": 0.7126224925506097,
      "grad_norm": 0.3640713095664978,
      "learning_rate": 1.4390766163526283e-05,
      "loss": 0.5461,
      "step": 23198
    },
    {
      "epoch": 0.712653211685559,
      "grad_norm": 0.4494645297527313,
      "learning_rate": 1.4390331958058235e-05,
      "loss": 0.4752,
      "step": 23199
    },
    {
      "epoch": 0.7126839308205081,
      "grad_norm": 0.3539104759693146,
      "learning_rate": 1.4389897742336256e-05,
      "loss": 0.6296,
      "step": 23200
    },
    {
      "epoch": 0.7127146499554573,
      "grad_norm": 0.35763445496559143,
      "learning_rate": 1.4389463516361368e-05,
      "loss": 0.5965,
      "step": 23201
    },
    {
      "epoch": 0.7127453690904064,
      "grad_norm": 0.42334264516830444,
      "learning_rate": 1.4389029280134578e-05,
      "loss": 0.5439,
      "step": 23202
    },
    {
      "epoch": 0.7127760882253555,
      "grad_norm": 0.38551226258277893,
      "learning_rate": 1.438859503365691e-05,
      "loss": 0.6234,
      "step": 23203
    },
    {
      "epoch": 0.7128068073603048,
      "grad_norm": 0.3605939447879791,
      "learning_rate": 1.4388160776929368e-05,
      "loss": 0.5752,
      "step": 23204
    },
    {
      "epoch": 0.7128375264952539,
      "grad_norm": 0.32525408267974854,
      "learning_rate": 1.4387726509952966e-05,
      "loss": 0.555,
      "step": 23205
    },
    {
      "epoch": 0.712868245630203,
      "grad_norm": 0.3363845944404602,
      "learning_rate": 1.4387292232728726e-05,
      "loss": 0.4951,
      "step": 23206
    },
    {
      "epoch": 0.7128989647651522,
      "grad_norm": 0.3857913911342621,
      "learning_rate": 1.438685794525766e-05,
      "loss": 0.5427,
      "step": 23207
    },
    {
      "epoch": 0.7129296839001014,
      "grad_norm": 0.4063234031200409,
      "learning_rate": 1.4386423647540779e-05,
      "loss": 0.6571,
      "step": 23208
    },
    {
      "epoch": 0.7129604030350505,
      "grad_norm": 0.3856711685657501,
      "learning_rate": 1.4385989339579099e-05,
      "loss": 0.591,
      "step": 23209
    },
    {
      "epoch": 0.7129911221699997,
      "grad_norm": 0.37258753180503845,
      "learning_rate": 1.4385555021373633e-05,
      "loss": 0.5816,
      "step": 23210
    },
    {
      "epoch": 0.7130218413049488,
      "grad_norm": 0.3642735779285431,
      "learning_rate": 1.4385120692925401e-05,
      "loss": 0.615,
      "step": 23211
    },
    {
      "epoch": 0.7130525604398981,
      "grad_norm": 0.3527680039405823,
      "learning_rate": 1.438468635423541e-05,
      "loss": 0.6164,
      "step": 23212
    },
    {
      "epoch": 0.7130832795748472,
      "grad_norm": 0.42647191882133484,
      "learning_rate": 1.438425200530468e-05,
      "loss": 0.6269,
      "step": 23213
    },
    {
      "epoch": 0.7131139987097963,
      "grad_norm": 0.37884822487831116,
      "learning_rate": 1.4383817646134221e-05,
      "loss": 0.499,
      "step": 23214
    },
    {
      "epoch": 0.7131447178447455,
      "grad_norm": 0.3612182140350342,
      "learning_rate": 1.4383383276725051e-05,
      "loss": 0.5414,
      "step": 23215
    },
    {
      "epoch": 0.7131754369796947,
      "grad_norm": 0.3987963795661926,
      "learning_rate": 1.4382948897078182e-05,
      "loss": 0.4966,
      "step": 23216
    },
    {
      "epoch": 0.7132061561146438,
      "grad_norm": 0.35355040431022644,
      "learning_rate": 1.4382514507194633e-05,
      "loss": 0.5231,
      "step": 23217
    },
    {
      "epoch": 0.713236875249593,
      "grad_norm": 0.35451841354370117,
      "learning_rate": 1.4382080107075411e-05,
      "loss": 0.5475,
      "step": 23218
    },
    {
      "epoch": 0.7132675943845421,
      "grad_norm": 0.4079259932041168,
      "learning_rate": 1.438164569672154e-05,
      "loss": 0.6281,
      "step": 23219
    },
    {
      "epoch": 0.7132983135194912,
      "grad_norm": 0.3593311607837677,
      "learning_rate": 1.4381211276134024e-05,
      "loss": 0.5751,
      "step": 23220
    },
    {
      "epoch": 0.7133290326544405,
      "grad_norm": 0.3853421211242676,
      "learning_rate": 1.4380776845313888e-05,
      "loss": 0.6224,
      "step": 23221
    },
    {
      "epoch": 0.7133597517893896,
      "grad_norm": 0.3302721083164215,
      "learning_rate": 1.438034240426214e-05,
      "loss": 0.6251,
      "step": 23222
    },
    {
      "epoch": 0.7133904709243387,
      "grad_norm": 0.3675985634326935,
      "learning_rate": 1.4379907952979795e-05,
      "loss": 0.6025,
      "step": 23223
    },
    {
      "epoch": 0.713421190059288,
      "grad_norm": 0.39555293321609497,
      "learning_rate": 1.437947349146787e-05,
      "loss": 0.5786,
      "step": 23224
    },
    {
      "epoch": 0.7134519091942371,
      "grad_norm": 0.3521851599216461,
      "learning_rate": 1.437903901972738e-05,
      "loss": 0.5954,
      "step": 23225
    },
    {
      "epoch": 0.7134826283291863,
      "grad_norm": 0.37242019176483154,
      "learning_rate": 1.4378604537759337e-05,
      "loss": 0.5482,
      "step": 23226
    },
    {
      "epoch": 0.7135133474641354,
      "grad_norm": 0.36565521359443665,
      "learning_rate": 1.4378170045564757e-05,
      "loss": 0.5812,
      "step": 23227
    },
    {
      "epoch": 0.7135440665990845,
      "grad_norm": 0.38653984665870667,
      "learning_rate": 1.4377735543144655e-05,
      "loss": 0.5488,
      "step": 23228
    },
    {
      "epoch": 0.7135747857340338,
      "grad_norm": 0.3806653916835785,
      "learning_rate": 1.4377301030500049e-05,
      "loss": 0.5551,
      "step": 23229
    },
    {
      "epoch": 0.7136055048689829,
      "grad_norm": 0.3746584355831146,
      "learning_rate": 1.4376866507631948e-05,
      "loss": 0.5095,
      "step": 23230
    },
    {
      "epoch": 0.713636224003932,
      "grad_norm": 0.39651650190353394,
      "learning_rate": 1.4376431974541367e-05,
      "loss": 0.5855,
      "step": 23231
    },
    {
      "epoch": 0.7136669431388812,
      "grad_norm": 0.3361566662788391,
      "learning_rate": 1.4375997431229326e-05,
      "loss": 0.4693,
      "step": 23232
    },
    {
      "epoch": 0.7136976622738304,
      "grad_norm": 0.39500734210014343,
      "learning_rate": 1.437556287769684e-05,
      "loss": 0.5515,
      "step": 23233
    },
    {
      "epoch": 0.7137283814087795,
      "grad_norm": 0.35733091831207275,
      "learning_rate": 1.4375128313944917e-05,
      "loss": 0.62,
      "step": 23234
    },
    {
      "epoch": 0.7137591005437287,
      "grad_norm": 0.40594691038131714,
      "learning_rate": 1.4374693739974578e-05,
      "loss": 0.6148,
      "step": 23235
    },
    {
      "epoch": 0.7137898196786778,
      "grad_norm": 0.40191906690597534,
      "learning_rate": 1.4374259155786838e-05,
      "loss": 0.5802,
      "step": 23236
    },
    {
      "epoch": 0.7138205388136271,
      "grad_norm": 0.37886014580726624,
      "learning_rate": 1.437382456138271e-05,
      "loss": 0.5868,
      "step": 23237
    },
    {
      "epoch": 0.7138512579485762,
      "grad_norm": 0.37020668387413025,
      "learning_rate": 1.4373389956763208e-05,
      "loss": 0.6479,
      "step": 23238
    },
    {
      "epoch": 0.7138819770835253,
      "grad_norm": 0.4108998477458954,
      "learning_rate": 1.4372955341929347e-05,
      "loss": 0.5781,
      "step": 23239
    },
    {
      "epoch": 0.7139126962184745,
      "grad_norm": 0.3749347925186157,
      "learning_rate": 1.4372520716882145e-05,
      "loss": 0.6201,
      "step": 23240
    },
    {
      "epoch": 0.7139434153534236,
      "grad_norm": 0.3828153908252716,
      "learning_rate": 1.4372086081622616e-05,
      "loss": 0.579,
      "step": 23241
    },
    {
      "epoch": 0.7139741344883728,
      "grad_norm": 0.3745262920856476,
      "learning_rate": 1.4371651436151775e-05,
      "loss": 0.505,
      "step": 23242
    },
    {
      "epoch": 0.714004853623322,
      "grad_norm": 0.36548444628715515,
      "learning_rate": 1.4371216780470634e-05,
      "loss": 0.5541,
      "step": 23243
    },
    {
      "epoch": 0.7140355727582711,
      "grad_norm": 0.34726086258888245,
      "learning_rate": 1.4370782114580216e-05,
      "loss": 0.5419,
      "step": 23244
    },
    {
      "epoch": 0.7140662918932202,
      "grad_norm": 0.3648160696029663,
      "learning_rate": 1.4370347438481525e-05,
      "loss": 0.506,
      "step": 23245
    },
    {
      "epoch": 0.7140970110281695,
      "grad_norm": 0.3389286398887634,
      "learning_rate": 1.4369912752175585e-05,
      "loss": 0.4732,
      "step": 23246
    },
    {
      "epoch": 0.7141277301631186,
      "grad_norm": 0.44821658730506897,
      "learning_rate": 1.4369478055663409e-05,
      "loss": 0.63,
      "step": 23247
    },
    {
      "epoch": 0.7141584492980678,
      "grad_norm": 0.37231093645095825,
      "learning_rate": 1.4369043348946012e-05,
      "loss": 0.6053,
      "step": 23248
    },
    {
      "epoch": 0.7141891684330169,
      "grad_norm": 0.3906601667404175,
      "learning_rate": 1.436860863202441e-05,
      "loss": 0.5956,
      "step": 23249
    },
    {
      "epoch": 0.7142198875679661,
      "grad_norm": 0.3578781187534332,
      "learning_rate": 1.4368173904899614e-05,
      "loss": 0.501,
      "step": 23250
    },
    {
      "epoch": 0.7142506067029153,
      "grad_norm": 0.35175591707229614,
      "learning_rate": 1.4367739167572646e-05,
      "loss": 0.5421,
      "step": 23251
    },
    {
      "epoch": 0.7142813258378644,
      "grad_norm": 0.4064997434616089,
      "learning_rate": 1.4367304420044514e-05,
      "loss": 0.5789,
      "step": 23252
    },
    {
      "epoch": 0.7143120449728135,
      "grad_norm": 0.37112247943878174,
      "learning_rate": 1.436686966231624e-05,
      "loss": 0.6515,
      "step": 23253
    },
    {
      "epoch": 0.7143427641077628,
      "grad_norm": 0.3833886682987213,
      "learning_rate": 1.4366434894388838e-05,
      "loss": 0.6044,
      "step": 23254
    },
    {
      "epoch": 0.7143734832427119,
      "grad_norm": 0.359438955783844,
      "learning_rate": 1.4366000116263323e-05,
      "loss": 0.5239,
      "step": 23255
    },
    {
      "epoch": 0.714404202377661,
      "grad_norm": 0.3801514506340027,
      "learning_rate": 1.4365565327940709e-05,
      "loss": 0.6288,
      "step": 23256
    },
    {
      "epoch": 0.7144349215126102,
      "grad_norm": 0.36502525210380554,
      "learning_rate": 1.436513052942201e-05,
      "loss": 0.559,
      "step": 23257
    },
    {
      "epoch": 0.7144656406475594,
      "grad_norm": 0.410566121339798,
      "learning_rate": 1.4364695720708249e-05,
      "loss": 0.6161,
      "step": 23258
    },
    {
      "epoch": 0.7144963597825085,
      "grad_norm": 0.36486223340034485,
      "learning_rate": 1.436426090180043e-05,
      "loss": 0.576,
      "step": 23259
    },
    {
      "epoch": 0.7145270789174577,
      "grad_norm": 0.4041081666946411,
      "learning_rate": 1.436382607269958e-05,
      "loss": 0.5171,
      "step": 23260
    },
    {
      "epoch": 0.7145577980524068,
      "grad_norm": 0.4316808879375458,
      "learning_rate": 1.4363391233406706e-05,
      "loss": 0.5615,
      "step": 23261
    },
    {
      "epoch": 0.714588517187356,
      "grad_norm": 0.4820363223552704,
      "learning_rate": 1.436295638392283e-05,
      "loss": 0.4624,
      "step": 23262
    },
    {
      "epoch": 0.7146192363223052,
      "grad_norm": 0.3624843657016754,
      "learning_rate": 1.436252152424896e-05,
      "loss": 0.6026,
      "step": 23263
    },
    {
      "epoch": 0.7146499554572543,
      "grad_norm": 0.426296591758728,
      "learning_rate": 1.4362086654386123e-05,
      "loss": 0.5209,
      "step": 23264
    },
    {
      "epoch": 0.7146806745922035,
      "grad_norm": 0.36864766478538513,
      "learning_rate": 1.4361651774335324e-05,
      "loss": 0.6411,
      "step": 23265
    },
    {
      "epoch": 0.7147113937271526,
      "grad_norm": 0.3212739825248718,
      "learning_rate": 1.4361216884097582e-05,
      "loss": 0.4897,
      "step": 23266
    },
    {
      "epoch": 0.7147421128621018,
      "grad_norm": 0.3411737382411957,
      "learning_rate": 1.4360781983673915e-05,
      "loss": 0.5444,
      "step": 23267
    },
    {
      "epoch": 0.714772831997051,
      "grad_norm": 0.37816518545150757,
      "learning_rate": 1.4360347073065335e-05,
      "loss": 0.5405,
      "step": 23268
    },
    {
      "epoch": 0.7148035511320001,
      "grad_norm": 0.405592679977417,
      "learning_rate": 1.4359912152272864e-05,
      "loss": 0.5881,
      "step": 23269
    },
    {
      "epoch": 0.7148342702669492,
      "grad_norm": 0.3976184129714966,
      "learning_rate": 1.4359477221297506e-05,
      "loss": 0.5742,
      "step": 23270
    },
    {
      "epoch": 0.7148649894018985,
      "grad_norm": 0.36280977725982666,
      "learning_rate": 1.4359042280140292e-05,
      "loss": 0.6012,
      "step": 23271
    },
    {
      "epoch": 0.7148957085368476,
      "grad_norm": 0.3753979802131653,
      "learning_rate": 1.4358607328802228e-05,
      "loss": 0.5738,
      "step": 23272
    },
    {
      "epoch": 0.7149264276717968,
      "grad_norm": 0.38848915696144104,
      "learning_rate": 1.435817236728433e-05,
      "loss": 0.5328,
      "step": 23273
    },
    {
      "epoch": 0.7149571468067459,
      "grad_norm": 0.38083934783935547,
      "learning_rate": 1.4357737395587621e-05,
      "loss": 0.5627,
      "step": 23274
    },
    {
      "epoch": 0.714987865941695,
      "grad_norm": 0.36678746342658997,
      "learning_rate": 1.4357302413713108e-05,
      "loss": 0.5414,
      "step": 23275
    },
    {
      "epoch": 0.7150185850766443,
      "grad_norm": 0.4170690178871155,
      "learning_rate": 1.4356867421661811e-05,
      "loss": 0.5087,
      "step": 23276
    },
    {
      "epoch": 0.7150493042115934,
      "grad_norm": 0.36380818486213684,
      "learning_rate": 1.4356432419434747e-05,
      "loss": 0.5841,
      "step": 23277
    },
    {
      "epoch": 0.7150800233465425,
      "grad_norm": 0.3793545663356781,
      "learning_rate": 1.435599740703293e-05,
      "loss": 0.5511,
      "step": 23278
    },
    {
      "epoch": 0.7151107424814918,
      "grad_norm": 0.3677300810813904,
      "learning_rate": 1.4355562384457378e-05,
      "loss": 0.6988,
      "step": 23279
    },
    {
      "epoch": 0.7151414616164409,
      "grad_norm": 0.34163081645965576,
      "learning_rate": 1.4355127351709106e-05,
      "loss": 0.5273,
      "step": 23280
    },
    {
      "epoch": 0.71517218075139,
      "grad_norm": 0.3674616515636444,
      "learning_rate": 1.4354692308789129e-05,
      "loss": 0.5459,
      "step": 23281
    },
    {
      "epoch": 0.7152028998863392,
      "grad_norm": 0.3884761333465576,
      "learning_rate": 1.4354257255698465e-05,
      "loss": 0.5058,
      "step": 23282
    },
    {
      "epoch": 0.7152336190212883,
      "grad_norm": 0.36278995871543884,
      "learning_rate": 1.4353822192438127e-05,
      "loss": 0.5749,
      "step": 23283
    },
    {
      "epoch": 0.7152643381562375,
      "grad_norm": 0.4294101893901825,
      "learning_rate": 1.4353387119009137e-05,
      "loss": 0.5724,
      "step": 23284
    },
    {
      "epoch": 0.7152950572911867,
      "grad_norm": 0.485844224691391,
      "learning_rate": 1.4352952035412504e-05,
      "loss": 0.7418,
      "step": 23285
    },
    {
      "epoch": 0.7153257764261358,
      "grad_norm": 0.3414039611816406,
      "learning_rate": 1.4352516941649249e-05,
      "loss": 0.5897,
      "step": 23286
    },
    {
      "epoch": 0.715356495561085,
      "grad_norm": 0.3572513163089752,
      "learning_rate": 1.4352081837720387e-05,
      "loss": 0.5226,
      "step": 23287
    },
    {
      "epoch": 0.7153872146960342,
      "grad_norm": 0.4040201008319855,
      "learning_rate": 1.4351646723626929e-05,
      "loss": 0.592,
      "step": 23288
    },
    {
      "epoch": 0.7154179338309833,
      "grad_norm": 0.34446364641189575,
      "learning_rate": 1.4351211599369901e-05,
      "loss": 0.516,
      "step": 23289
    },
    {
      "epoch": 0.7154486529659325,
      "grad_norm": 0.3523973822593689,
      "learning_rate": 1.4350776464950316e-05,
      "loss": 0.528,
      "step": 23290
    },
    {
      "epoch": 0.7154793721008816,
      "grad_norm": 0.3502325117588043,
      "learning_rate": 1.4350341320369183e-05,
      "loss": 0.6264,
      "step": 23291
    },
    {
      "epoch": 0.7155100912358308,
      "grad_norm": 0.3523746430873871,
      "learning_rate": 1.434990616562753e-05,
      "loss": 0.4959,
      "step": 23292
    },
    {
      "epoch": 0.71554081037078,
      "grad_norm": 0.40855416655540466,
      "learning_rate": 1.4349471000726362e-05,
      "loss": 0.507,
      "step": 23293
    },
    {
      "epoch": 0.7155715295057291,
      "grad_norm": 0.3590714633464813,
      "learning_rate": 1.4349035825666704e-05,
      "loss": 0.556,
      "step": 23294
    },
    {
      "epoch": 0.7156022486406782,
      "grad_norm": 0.3938080668449402,
      "learning_rate": 1.4348600640449569e-05,
      "loss": 0.5377,
      "step": 23295
    },
    {
      "epoch": 0.7156329677756275,
      "grad_norm": 0.4099295139312744,
      "learning_rate": 1.4348165445075975e-05,
      "loss": 0.5557,
      "step": 23296
    },
    {
      "epoch": 0.7156636869105766,
      "grad_norm": 0.484404981136322,
      "learning_rate": 1.4347730239546933e-05,
      "loss": 0.6096,
      "step": 23297
    },
    {
      "epoch": 0.7156944060455258,
      "grad_norm": 0.34550541639328003,
      "learning_rate": 1.4347295023863466e-05,
      "loss": 0.4908,
      "step": 23298
    },
    {
      "epoch": 0.7157251251804749,
      "grad_norm": 0.3521379828453064,
      "learning_rate": 1.4346859798026587e-05,
      "loss": 0.5452,
      "step": 23299
    },
    {
      "epoch": 0.715755844315424,
      "grad_norm": 0.32496801018714905,
      "learning_rate": 1.4346424562037314e-05,
      "loss": 0.5762,
      "step": 23300
    },
    {
      "epoch": 0.7157865634503733,
      "grad_norm": 0.3432060182094574,
      "learning_rate": 1.4345989315896663e-05,
      "loss": 0.5723,
      "step": 23301
    },
    {
      "epoch": 0.7158172825853224,
      "grad_norm": 0.36461469531059265,
      "learning_rate": 1.4345554059605649e-05,
      "loss": 0.5322,
      "step": 23302
    },
    {
      "epoch": 0.7158480017202715,
      "grad_norm": 0.3311673104763031,
      "learning_rate": 1.434511879316529e-05,
      "loss": 0.5613,
      "step": 23303
    },
    {
      "epoch": 0.7158787208552208,
      "grad_norm": 0.4263823926448822,
      "learning_rate": 1.4344683516576602e-05,
      "loss": 0.5887,
      "step": 23304
    },
    {
      "epoch": 0.7159094399901699,
      "grad_norm": 0.35805633664131165,
      "learning_rate": 1.4344248229840607e-05,
      "loss": 0.5551,
      "step": 23305
    },
    {
      "epoch": 0.715940159125119,
      "grad_norm": 0.36383625864982605,
      "learning_rate": 1.434381293295831e-05,
      "loss": 0.5287,
      "step": 23306
    },
    {
      "epoch": 0.7159708782600682,
      "grad_norm": 0.37530261278152466,
      "learning_rate": 1.4343377625930739e-05,
      "loss": 0.5837,
      "step": 23307
    },
    {
      "epoch": 0.7160015973950173,
      "grad_norm": 0.3517078459262848,
      "learning_rate": 1.4342942308758908e-05,
      "loss": 0.6055,
      "step": 23308
    },
    {
      "epoch": 0.7160323165299665,
      "grad_norm": 0.42102184891700745,
      "learning_rate": 1.4342506981443827e-05,
      "loss": 0.5974,
      "step": 23309
    },
    {
      "epoch": 0.7160630356649157,
      "grad_norm": 0.43585890531539917,
      "learning_rate": 1.4342071643986519e-05,
      "loss": 0.6014,
      "step": 23310
    },
    {
      "epoch": 0.7160937547998648,
      "grad_norm": 0.40566739439964294,
      "learning_rate": 1.4341636296388002e-05,
      "loss": 0.5566,
      "step": 23311
    },
    {
      "epoch": 0.716124473934814,
      "grad_norm": 0.35119661688804626,
      "learning_rate": 1.4341200938649289e-05,
      "loss": 0.6099,
      "step": 23312
    },
    {
      "epoch": 0.7161551930697632,
      "grad_norm": 0.30401116609573364,
      "learning_rate": 1.4340765570771396e-05,
      "loss": 0.4999,
      "step": 23313
    },
    {
      "epoch": 0.7161859122047123,
      "grad_norm": 0.3688519597053528,
      "learning_rate": 1.4340330192755345e-05,
      "loss": 0.5247,
      "step": 23314
    },
    {
      "epoch": 0.7162166313396615,
      "grad_norm": 0.4636021852493286,
      "learning_rate": 1.4339894804602146e-05,
      "loss": 0.5469,
      "step": 23315
    },
    {
      "epoch": 0.7162473504746106,
      "grad_norm": 0.3334212303161621,
      "learning_rate": 1.4339459406312823e-05,
      "loss": 0.5627,
      "step": 23316
    },
    {
      "epoch": 0.7162780696095598,
      "grad_norm": 0.3991237282752991,
      "learning_rate": 1.4339023997888388e-05,
      "loss": 0.5742,
      "step": 23317
    },
    {
      "epoch": 0.716308788744509,
      "grad_norm": 0.36510488390922546,
      "learning_rate": 1.4338588579329859e-05,
      "loss": 0.6266,
      "step": 23318
    },
    {
      "epoch": 0.7163395078794581,
      "grad_norm": 0.39876389503479004,
      "learning_rate": 1.4338153150638254e-05,
      "loss": 0.5302,
      "step": 23319
    },
    {
      "epoch": 0.7163702270144072,
      "grad_norm": 0.37326377630233765,
      "learning_rate": 1.433771771181459e-05,
      "loss": 0.5936,
      "step": 23320
    },
    {
      "epoch": 0.7164009461493565,
      "grad_norm": 0.3308236300945282,
      "learning_rate": 1.4337282262859883e-05,
      "loss": 0.4885,
      "step": 23321
    },
    {
      "epoch": 0.7164316652843056,
      "grad_norm": 0.3381790220737457,
      "learning_rate": 1.4336846803775148e-05,
      "loss": 0.5686,
      "step": 23322
    },
    {
      "epoch": 0.7164623844192548,
      "grad_norm": 0.4075927436351776,
      "learning_rate": 1.4336411334561408e-05,
      "loss": 0.6076,
      "step": 23323
    },
    {
      "epoch": 0.7164931035542039,
      "grad_norm": 0.34470346570014954,
      "learning_rate": 1.4335975855219673e-05,
      "loss": 0.565,
      "step": 23324
    },
    {
      "epoch": 0.716523822689153,
      "grad_norm": 0.40160301327705383,
      "learning_rate": 1.4335540365750966e-05,
      "loss": 0.6228,
      "step": 23325
    },
    {
      "epoch": 0.7165545418241023,
      "grad_norm": 0.38266289234161377,
      "learning_rate": 1.4335104866156302e-05,
      "loss": 0.4936,
      "step": 23326
    },
    {
      "epoch": 0.7165852609590514,
      "grad_norm": 0.33567723631858826,
      "learning_rate": 1.4334669356436698e-05,
      "loss": 0.5414,
      "step": 23327
    },
    {
      "epoch": 0.7166159800940005,
      "grad_norm": 0.409091979265213,
      "learning_rate": 1.433423383659317e-05,
      "loss": 0.6088,
      "step": 23328
    },
    {
      "epoch": 0.7166466992289497,
      "grad_norm": 0.346138060092926,
      "learning_rate": 1.4333798306626734e-05,
      "loss": 0.5689,
      "step": 23329
    },
    {
      "epoch": 0.7166774183638989,
      "grad_norm": 0.33970165252685547,
      "learning_rate": 1.4333362766538412e-05,
      "loss": 0.5053,
      "step": 23330
    },
    {
      "epoch": 0.716708137498848,
      "grad_norm": 0.3871152102947235,
      "learning_rate": 1.4332927216329218e-05,
      "loss": 0.5891,
      "step": 23331
    },
    {
      "epoch": 0.7167388566337972,
      "grad_norm": 0.33691972494125366,
      "learning_rate": 1.4332491656000171e-05,
      "loss": 0.5108,
      "step": 23332
    },
    {
      "epoch": 0.7167695757687463,
      "grad_norm": 0.47202879190444946,
      "learning_rate": 1.4332056085552287e-05,
      "loss": 0.5482,
      "step": 23333
    },
    {
      "epoch": 0.7168002949036956,
      "grad_norm": 0.3604145050048828,
      "learning_rate": 1.433162050498658e-05,
      "loss": 0.6573,
      "step": 23334
    },
    {
      "epoch": 0.7168310140386447,
      "grad_norm": 0.3350997567176819,
      "learning_rate": 1.4331184914304074e-05,
      "loss": 0.5688,
      "step": 23335
    },
    {
      "epoch": 0.7168617331735938,
      "grad_norm": 0.33414512872695923,
      "learning_rate": 1.4330749313505783e-05,
      "loss": 0.6111,
      "step": 23336
    },
    {
      "epoch": 0.716892452308543,
      "grad_norm": 0.3736283779144287,
      "learning_rate": 1.4330313702592726e-05,
      "loss": 0.5654,
      "step": 23337
    },
    {
      "epoch": 0.7169231714434922,
      "grad_norm": 0.35170868039131165,
      "learning_rate": 1.4329878081565915e-05,
      "loss": 0.5259,
      "step": 23338
    },
    {
      "epoch": 0.7169538905784413,
      "grad_norm": 0.35884276032447815,
      "learning_rate": 1.4329442450426374e-05,
      "loss": 0.5616,
      "step": 23339
    },
    {
      "epoch": 0.7169846097133905,
      "grad_norm": 0.38542717695236206,
      "learning_rate": 1.4329006809175117e-05,
      "loss": 0.5469,
      "step": 23340
    },
    {
      "epoch": 0.7170153288483396,
      "grad_norm": 0.3689219057559967,
      "learning_rate": 1.4328571157813164e-05,
      "loss": 0.5323,
      "step": 23341
    },
    {
      "epoch": 0.7170460479832887,
      "grad_norm": 0.4429589807987213,
      "learning_rate": 1.4328135496341529e-05,
      "loss": 0.5336,
      "step": 23342
    },
    {
      "epoch": 0.717076767118238,
      "grad_norm": 0.33750975131988525,
      "learning_rate": 1.432769982476123e-05,
      "loss": 0.4908,
      "step": 23343
    },
    {
      "epoch": 0.7171074862531871,
      "grad_norm": 0.34846019744873047,
      "learning_rate": 1.4327264143073288e-05,
      "loss": 0.5081,
      "step": 23344
    },
    {
      "epoch": 0.7171382053881362,
      "grad_norm": 0.4282776117324829,
      "learning_rate": 1.4326828451278715e-05,
      "loss": 0.6628,
      "step": 23345
    },
    {
      "epoch": 0.7171689245230854,
      "grad_norm": 0.4773401916027069,
      "learning_rate": 1.4326392749378538e-05,
      "loss": 0.5444,
      "step": 23346
    },
    {
      "epoch": 0.7171996436580346,
      "grad_norm": 0.37992265820503235,
      "learning_rate": 1.4325957037373764e-05,
      "loss": 0.5113,
      "step": 23347
    },
    {
      "epoch": 0.7172303627929838,
      "grad_norm": 0.3755682706832886,
      "learning_rate": 1.4325521315265417e-05,
      "loss": 0.5111,
      "step": 23348
    },
    {
      "epoch": 0.7172610819279329,
      "grad_norm": 0.34996992349624634,
      "learning_rate": 1.432508558305451e-05,
      "loss": 0.5154,
      "step": 23349
    },
    {
      "epoch": 0.717291801062882,
      "grad_norm": 0.3797302544116974,
      "learning_rate": 1.4324649840742066e-05,
      "loss": 0.5343,
      "step": 23350
    },
    {
      "epoch": 0.7173225201978313,
      "grad_norm": 0.35790523886680603,
      "learning_rate": 1.43242140883291e-05,
      "loss": 0.5546,
      "step": 23351
    },
    {
      "epoch": 0.7173532393327804,
      "grad_norm": 0.38124406337738037,
      "learning_rate": 1.432377832581663e-05,
      "loss": 0.5581,
      "step": 23352
    },
    {
      "epoch": 0.7173839584677295,
      "grad_norm": 0.3550511598587036,
      "learning_rate": 1.4323342553205677e-05,
      "loss": 0.5392,
      "step": 23353
    },
    {
      "epoch": 0.7174146776026787,
      "grad_norm": 0.36780500411987305,
      "learning_rate": 1.4322906770497252e-05,
      "loss": 0.5042,
      "step": 23354
    },
    {
      "epoch": 0.7174453967376279,
      "grad_norm": 0.3599548637866974,
      "learning_rate": 1.4322470977692375e-05,
      "loss": 0.6016,
      "step": 23355
    },
    {
      "epoch": 0.717476115872577,
      "grad_norm": 0.9069557189941406,
      "learning_rate": 1.4322035174792067e-05,
      "loss": 0.5127,
      "step": 23356
    },
    {
      "epoch": 0.7175068350075262,
      "grad_norm": 0.3885195553302765,
      "learning_rate": 1.4321599361797344e-05,
      "loss": 0.4883,
      "step": 23357
    },
    {
      "epoch": 0.7175375541424753,
      "grad_norm": 0.42352351546287537,
      "learning_rate": 1.4321163538709224e-05,
      "loss": 0.605,
      "step": 23358
    },
    {
      "epoch": 0.7175682732774246,
      "grad_norm": 0.3540290594100952,
      "learning_rate": 1.4320727705528725e-05,
      "loss": 0.6522,
      "step": 23359
    },
    {
      "epoch": 0.7175989924123737,
      "grad_norm": 0.332116037607193,
      "learning_rate": 1.4320291862256863e-05,
      "loss": 0.6044,
      "step": 23360
    },
    {
      "epoch": 0.7176297115473228,
      "grad_norm": 0.35039860010147095,
      "learning_rate": 1.4319856008894659e-05,
      "loss": 0.6117,
      "step": 23361
    },
    {
      "epoch": 0.717660430682272,
      "grad_norm": 0.353455513715744,
      "learning_rate": 1.431942014544313e-05,
      "loss": 0.533,
      "step": 23362
    },
    {
      "epoch": 0.7176911498172212,
      "grad_norm": 0.39966461062431335,
      "learning_rate": 1.4318984271903293e-05,
      "loss": 0.617,
      "step": 23363
    },
    {
      "epoch": 0.7177218689521703,
      "grad_norm": 0.3545120060443878,
      "learning_rate": 1.4318548388276167e-05,
      "loss": 0.5887,
      "step": 23364
    },
    {
      "epoch": 0.7177525880871195,
      "grad_norm": 0.37002456188201904,
      "learning_rate": 1.4318112494562769e-05,
      "loss": 0.5387,
      "step": 23365
    },
    {
      "epoch": 0.7177833072220686,
      "grad_norm": 0.38272687792778015,
      "learning_rate": 1.4317676590764118e-05,
      "loss": 0.558,
      "step": 23366
    },
    {
      "epoch": 0.7178140263570177,
      "grad_norm": 0.3638666272163391,
      "learning_rate": 1.431724067688123e-05,
      "loss": 0.564,
      "step": 23367
    },
    {
      "epoch": 0.717844745491967,
      "grad_norm": 0.35474076867103577,
      "learning_rate": 1.4316804752915128e-05,
      "loss": 0.5706,
      "step": 23368
    },
    {
      "epoch": 0.7178754646269161,
      "grad_norm": 0.33820199966430664,
      "learning_rate": 1.4316368818866826e-05,
      "loss": 0.5847,
      "step": 23369
    },
    {
      "epoch": 0.7179061837618652,
      "grad_norm": 0.38841402530670166,
      "learning_rate": 1.4315932874737342e-05,
      "loss": 0.5951,
      "step": 23370
    },
    {
      "epoch": 0.7179369028968144,
      "grad_norm": 0.37294360995292664,
      "learning_rate": 1.4315496920527698e-05,
      "loss": 0.58,
      "step": 23371
    },
    {
      "epoch": 0.7179676220317636,
      "grad_norm": 0.34825658798217773,
      "learning_rate": 1.4315060956238906e-05,
      "loss": 0.5927,
      "step": 23372
    },
    {
      "epoch": 0.7179983411667128,
      "grad_norm": 0.38324832916259766,
      "learning_rate": 1.4314624981871992e-05,
      "loss": 0.5841,
      "step": 23373
    },
    {
      "epoch": 0.7180290603016619,
      "grad_norm": 0.3947225511074066,
      "learning_rate": 1.4314188997427967e-05,
      "loss": 0.5404,
      "step": 23374
    },
    {
      "epoch": 0.718059779436611,
      "grad_norm": 0.3624431788921356,
      "learning_rate": 1.4313753002907854e-05,
      "loss": 0.565,
      "step": 23375
    },
    {
      "epoch": 0.7180904985715603,
      "grad_norm": 0.3630715310573578,
      "learning_rate": 1.4313316998312665e-05,
      "loss": 0.4658,
      "step": 23376
    },
    {
      "epoch": 0.7181212177065094,
      "grad_norm": 0.34741833806037903,
      "learning_rate": 1.4312880983643429e-05,
      "loss": 0.4836,
      "step": 23377
    },
    {
      "epoch": 0.7181519368414585,
      "grad_norm": 0.4227137267589569,
      "learning_rate": 1.4312444958901153e-05,
      "loss": 0.641,
      "step": 23378
    },
    {
      "epoch": 0.7181826559764077,
      "grad_norm": 0.3884705603122711,
      "learning_rate": 1.4312008924086862e-05,
      "loss": 0.572,
      "step": 23379
    },
    {
      "epoch": 0.7182133751113569,
      "grad_norm": 0.39625272154808044,
      "learning_rate": 1.4311572879201577e-05,
      "loss": 0.5974,
      "step": 23380
    },
    {
      "epoch": 0.718244094246306,
      "grad_norm": 0.398294597864151,
      "learning_rate": 1.4311136824246309e-05,
      "loss": 0.5638,
      "step": 23381
    },
    {
      "epoch": 0.7182748133812552,
      "grad_norm": 0.3662996292114258,
      "learning_rate": 1.431070075922208e-05,
      "loss": 0.6213,
      "step": 23382
    },
    {
      "epoch": 0.7183055325162043,
      "grad_norm": 0.3543523848056793,
      "learning_rate": 1.4310264684129908e-05,
      "loss": 0.4681,
      "step": 23383
    },
    {
      "epoch": 0.7183362516511536,
      "grad_norm": 0.34324678778648376,
      "learning_rate": 1.4309828598970814e-05,
      "loss": 0.5637,
      "step": 23384
    },
    {
      "epoch": 0.7183669707861027,
      "grad_norm": 0.34019735455513,
      "learning_rate": 1.4309392503745812e-05,
      "loss": 0.5376,
      "step": 23385
    },
    {
      "epoch": 0.7183976899210518,
      "grad_norm": 0.3611259460449219,
      "learning_rate": 1.4308956398455924e-05,
      "loss": 0.5509,
      "step": 23386
    },
    {
      "epoch": 0.718428409056001,
      "grad_norm": 0.36567965149879456,
      "learning_rate": 1.4308520283102167e-05,
      "loss": 0.5546,
      "step": 23387
    },
    {
      "epoch": 0.7184591281909501,
      "grad_norm": 0.39032405614852905,
      "learning_rate": 1.430808415768556e-05,
      "loss": 0.5141,
      "step": 23388
    },
    {
      "epoch": 0.7184898473258993,
      "grad_norm": 0.36387690901756287,
      "learning_rate": 1.4307648022207123e-05,
      "loss": 0.5576,
      "step": 23389
    },
    {
      "epoch": 0.7185205664608485,
      "grad_norm": 0.3832300007343292,
      "learning_rate": 1.430721187666787e-05,
      "loss": 0.6273,
      "step": 23390
    },
    {
      "epoch": 0.7185512855957976,
      "grad_norm": 0.7635495066642761,
      "learning_rate": 1.4306775721068826e-05,
      "loss": 0.5395,
      "step": 23391
    },
    {
      "epoch": 0.7185820047307467,
      "grad_norm": 0.37648671865463257,
      "learning_rate": 1.4306339555411003e-05,
      "loss": 0.4993,
      "step": 23392
    },
    {
      "epoch": 0.718612723865696,
      "grad_norm": 0.37910258769989014,
      "learning_rate": 1.4305903379695427e-05,
      "loss": 0.5715,
      "step": 23393
    },
    {
      "epoch": 0.7186434430006451,
      "grad_norm": 0.3670291602611542,
      "learning_rate": 1.4305467193923113e-05,
      "loss": 0.5825,
      "step": 23394
    },
    {
      "epoch": 0.7186741621355942,
      "grad_norm": 0.4225667715072632,
      "learning_rate": 1.4305030998095078e-05,
      "loss": 0.5188,
      "step": 23395
    },
    {
      "epoch": 0.7187048812705434,
      "grad_norm": 0.3438062369823456,
      "learning_rate": 1.4304594792212344e-05,
      "loss": 0.5301,
      "step": 23396
    },
    {
      "epoch": 0.7187356004054926,
      "grad_norm": 0.40781277418136597,
      "learning_rate": 1.4304158576275924e-05,
      "loss": 0.5693,
      "step": 23397
    },
    {
      "epoch": 0.7187663195404418,
      "grad_norm": 0.3350687325000763,
      "learning_rate": 1.4303722350286843e-05,
      "loss": 0.5378,
      "step": 23398
    },
    {
      "epoch": 0.7187970386753909,
      "grad_norm": 0.35388505458831787,
      "learning_rate": 1.4303286114246117e-05,
      "loss": 0.5841,
      "step": 23399
    },
    {
      "epoch": 0.71882775781034,
      "grad_norm": 0.3882730007171631,
      "learning_rate": 1.4302849868154771e-05,
      "loss": 0.5466,
      "step": 23400
    },
    {
      "epoch": 0.7188584769452893,
      "grad_norm": 0.37193191051483154,
      "learning_rate": 1.4302413612013815e-05,
      "loss": 0.5358,
      "step": 23401
    },
    {
      "epoch": 0.7188891960802384,
      "grad_norm": 0.35610097646713257,
      "learning_rate": 1.4301977345824272e-05,
      "loss": 0.5378,
      "step": 23402
    },
    {
      "epoch": 0.7189199152151875,
      "grad_norm": 0.3542301058769226,
      "learning_rate": 1.4301541069587157e-05,
      "loss": 0.4777,
      "step": 23403
    },
    {
      "epoch": 0.7189506343501367,
      "grad_norm": 0.39965328574180603,
      "learning_rate": 1.4301104783303496e-05,
      "loss": 0.5612,
      "step": 23404
    },
    {
      "epoch": 0.7189813534850859,
      "grad_norm": 0.355535089969635,
      "learning_rate": 1.4300668486974308e-05,
      "loss": 0.4996,
      "step": 23405
    },
    {
      "epoch": 0.719012072620035,
      "grad_norm": 0.37397462129592896,
      "learning_rate": 1.4300232180600602e-05,
      "loss": 0.5765,
      "step": 23406
    },
    {
      "epoch": 0.7190427917549842,
      "grad_norm": 0.36390209197998047,
      "learning_rate": 1.4299795864183406e-05,
      "loss": 0.567,
      "step": 23407
    },
    {
      "epoch": 0.7190735108899333,
      "grad_norm": 0.37729743123054504,
      "learning_rate": 1.4299359537723735e-05,
      "loss": 0.587,
      "step": 23408
    },
    {
      "epoch": 0.7191042300248826,
      "grad_norm": 0.40184929966926575,
      "learning_rate": 1.4298923201222611e-05,
      "loss": 0.6126,
      "step": 23409
    },
    {
      "epoch": 0.7191349491598317,
      "grad_norm": 0.40769609808921814,
      "learning_rate": 1.4298486854681052e-05,
      "loss": 0.4589,
      "step": 23410
    },
    {
      "epoch": 0.7191656682947808,
      "grad_norm": 0.5933443307876587,
      "learning_rate": 1.4298050498100077e-05,
      "loss": 0.5148,
      "step": 23411
    },
    {
      "epoch": 0.71919638742973,
      "grad_norm": 0.3954637944698334,
      "learning_rate": 1.4297614131480701e-05,
      "loss": 0.5271,
      "step": 23412
    },
    {
      "epoch": 0.7192271065646791,
      "grad_norm": 0.4042503237724304,
      "learning_rate": 1.4297177754823953e-05,
      "loss": 0.5499,
      "step": 23413
    },
    {
      "epoch": 0.7192578256996283,
      "grad_norm": 0.5043869018554688,
      "learning_rate": 1.4296741368130843e-05,
      "loss": 0.4963,
      "step": 23414
    },
    {
      "epoch": 0.7192885448345775,
      "grad_norm": 0.3813895285129547,
      "learning_rate": 1.4296304971402393e-05,
      "loss": 0.6043,
      "step": 23415
    },
    {
      "epoch": 0.7193192639695266,
      "grad_norm": 0.37226787209510803,
      "learning_rate": 1.4295868564639624e-05,
      "loss": 0.5243,
      "step": 23416
    },
    {
      "epoch": 0.7193499831044757,
      "grad_norm": 0.3344322741031647,
      "learning_rate": 1.4295432147843551e-05,
      "loss": 0.5806,
      "step": 23417
    },
    {
      "epoch": 0.719380702239425,
      "grad_norm": 0.4774976372718811,
      "learning_rate": 1.42949957210152e-05,
      "loss": 0.5425,
      "step": 23418
    },
    {
      "epoch": 0.7194114213743741,
      "grad_norm": 0.4311380088329315,
      "learning_rate": 1.4294559284155584e-05,
      "loss": 0.4993,
      "step": 23419
    },
    {
      "epoch": 0.7194421405093232,
      "grad_norm": 0.4222111999988556,
      "learning_rate": 1.4294122837265727e-05,
      "loss": 0.5399,
      "step": 23420
    },
    {
      "epoch": 0.7194728596442724,
      "grad_norm": 0.3721184730529785,
      "learning_rate": 1.4293686380346645e-05,
      "loss": 0.5528,
      "step": 23421
    },
    {
      "epoch": 0.7195035787792216,
      "grad_norm": 0.4661678075790405,
      "learning_rate": 1.4293249913399359e-05,
      "loss": 0.5689,
      "step": 23422
    },
    {
      "epoch": 0.7195342979141708,
      "grad_norm": 0.41172197461128235,
      "learning_rate": 1.4292813436424888e-05,
      "loss": 0.5738,
      "step": 23423
    },
    {
      "epoch": 0.7195650170491199,
      "grad_norm": 0.40150320529937744,
      "learning_rate": 1.4292376949424252e-05,
      "loss": 0.5771,
      "step": 23424
    },
    {
      "epoch": 0.719595736184069,
      "grad_norm": 0.396605908870697,
      "learning_rate": 1.429194045239847e-05,
      "loss": 0.5546,
      "step": 23425
    },
    {
      "epoch": 0.7196264553190183,
      "grad_norm": 0.3357087969779968,
      "learning_rate": 1.429150394534856e-05,
      "loss": 0.5701,
      "step": 23426
    },
    {
      "epoch": 0.7196571744539674,
      "grad_norm": 0.3965671956539154,
      "learning_rate": 1.4291067428275543e-05,
      "loss": 0.5357,
      "step": 23427
    },
    {
      "epoch": 0.7196878935889165,
      "grad_norm": 0.4435134828090668,
      "learning_rate": 1.4290630901180439e-05,
      "loss": 0.5683,
      "step": 23428
    },
    {
      "epoch": 0.7197186127238657,
      "grad_norm": 0.3520336151123047,
      "learning_rate": 1.4290194364064266e-05,
      "loss": 0.5516,
      "step": 23429
    },
    {
      "epoch": 0.7197493318588148,
      "grad_norm": 0.4225528836250305,
      "learning_rate": 1.4289757816928043e-05,
      "loss": 0.5117,
      "step": 23430
    },
    {
      "epoch": 0.719780050993764,
      "grad_norm": 0.3795910179615021,
      "learning_rate": 1.4289321259772795e-05,
      "loss": 0.573,
      "step": 23431
    },
    {
      "epoch": 0.7198107701287132,
      "grad_norm": 0.4273488521575928,
      "learning_rate": 1.4288884692599535e-05,
      "loss": 0.6004,
      "step": 23432
    },
    {
      "epoch": 0.7198414892636623,
      "grad_norm": 0.36052200198173523,
      "learning_rate": 1.4288448115409286e-05,
      "loss": 0.5627,
      "step": 23433
    },
    {
      "epoch": 0.7198722083986115,
      "grad_norm": 0.43812426924705505,
      "learning_rate": 1.4288011528203066e-05,
      "loss": 0.558,
      "step": 23434
    },
    {
      "epoch": 0.7199029275335607,
      "grad_norm": 0.4579241871833801,
      "learning_rate": 1.4287574930981896e-05,
      "loss": 0.6813,
      "step": 23435
    },
    {
      "epoch": 0.7199336466685098,
      "grad_norm": 0.31883493065834045,
      "learning_rate": 1.4287138323746797e-05,
      "loss": 0.5291,
      "step": 23436
    },
    {
      "epoch": 0.719964365803459,
      "grad_norm": 0.3641261160373688,
      "learning_rate": 1.4286701706498783e-05,
      "loss": 0.4937,
      "step": 23437
    },
    {
      "epoch": 0.7199950849384081,
      "grad_norm": 0.37596240639686584,
      "learning_rate": 1.4286265079238882e-05,
      "loss": 0.5416,
      "step": 23438
    },
    {
      "epoch": 0.7200258040733573,
      "grad_norm": 0.37289512157440186,
      "learning_rate": 1.4285828441968105e-05,
      "loss": 0.5633,
      "step": 23439
    },
    {
      "epoch": 0.7200565232083065,
      "grad_norm": 0.3479554057121277,
      "learning_rate": 1.4285391794687483e-05,
      "loss": 0.4653,
      "step": 23440
    },
    {
      "epoch": 0.7200872423432556,
      "grad_norm": 0.3610537350177765,
      "learning_rate": 1.4284955137398024e-05,
      "loss": 0.5408,
      "step": 23441
    },
    {
      "epoch": 0.7201179614782047,
      "grad_norm": 0.3511520326137543,
      "learning_rate": 1.4284518470100754e-05,
      "loss": 0.5596,
      "step": 23442
    },
    {
      "epoch": 0.720148680613154,
      "grad_norm": 0.3815266489982605,
      "learning_rate": 1.4284081792796693e-05,
      "loss": 0.5558,
      "step": 23443
    },
    {
      "epoch": 0.7201793997481031,
      "grad_norm": 0.36893096566200256,
      "learning_rate": 1.4283645105486859e-05,
      "loss": 0.5613,
      "step": 23444
    },
    {
      "epoch": 0.7202101188830523,
      "grad_norm": 0.3474266529083252,
      "learning_rate": 1.4283208408172273e-05,
      "loss": 0.527,
      "step": 23445
    },
    {
      "epoch": 0.7202408380180014,
      "grad_norm": 0.371135413646698,
      "learning_rate": 1.4282771700853955e-05,
      "loss": 0.6193,
      "step": 23446
    },
    {
      "epoch": 0.7202715571529505,
      "grad_norm": 0.32462865114212036,
      "learning_rate": 1.4282334983532927e-05,
      "loss": 0.4584,
      "step": 23447
    },
    {
      "epoch": 0.7203022762878998,
      "grad_norm": 0.37046581506729126,
      "learning_rate": 1.42818982562102e-05,
      "loss": 0.5058,
      "step": 23448
    },
    {
      "epoch": 0.7203329954228489,
      "grad_norm": 0.3731372356414795,
      "learning_rate": 1.4281461518886805e-05,
      "loss": 0.4411,
      "step": 23449
    },
    {
      "epoch": 0.720363714557798,
      "grad_norm": 0.359437495470047,
      "learning_rate": 1.4281024771563757e-05,
      "loss": 0.5051,
      "step": 23450
    },
    {
      "epoch": 0.7203944336927472,
      "grad_norm": 0.5205446481704712,
      "learning_rate": 1.4280588014242075e-05,
      "loss": 0.5746,
      "step": 23451
    },
    {
      "epoch": 0.7204251528276964,
      "grad_norm": 0.34987807273864746,
      "learning_rate": 1.4280151246922783e-05,
      "loss": 0.5467,
      "step": 23452
    },
    {
      "epoch": 0.7204558719626455,
      "grad_norm": 0.38661012053489685,
      "learning_rate": 1.4279714469606897e-05,
      "loss": 0.5524,
      "step": 23453
    },
    {
      "epoch": 0.7204865910975947,
      "grad_norm": 0.3387630581855774,
      "learning_rate": 1.427927768229544e-05,
      "loss": 0.5239,
      "step": 23454
    },
    {
      "epoch": 0.7205173102325438,
      "grad_norm": 0.3855663537979126,
      "learning_rate": 1.4278840884989431e-05,
      "loss": 0.5273,
      "step": 23455
    },
    {
      "epoch": 0.720548029367493,
      "grad_norm": 0.5183831453323364,
      "learning_rate": 1.4278404077689892e-05,
      "loss": 0.4896,
      "step": 23456
    },
    {
      "epoch": 0.7205787485024422,
      "grad_norm": 0.36710596084594727,
      "learning_rate": 1.4277967260397838e-05,
      "loss": 0.5133,
      "step": 23457
    },
    {
      "epoch": 0.7206094676373913,
      "grad_norm": 0.312406063079834,
      "learning_rate": 1.4277530433114298e-05,
      "loss": 0.4594,
      "step": 23458
    },
    {
      "epoch": 0.7206401867723405,
      "grad_norm": 0.450519859790802,
      "learning_rate": 1.4277093595840284e-05,
      "loss": 0.5608,
      "step": 23459
    },
    {
      "epoch": 0.7206709059072897,
      "grad_norm": 0.3597572445869446,
      "learning_rate": 1.4276656748576815e-05,
      "loss": 0.577,
      "step": 23460
    },
    {
      "epoch": 0.7207016250422388,
      "grad_norm": 0.49385905265808105,
      "learning_rate": 1.4276219891324923e-05,
      "loss": 0.6354,
      "step": 23461
    },
    {
      "epoch": 0.720732344177188,
      "grad_norm": 0.3317689001560211,
      "learning_rate": 1.4275783024085614e-05,
      "loss": 0.6569,
      "step": 23462
    },
    {
      "epoch": 0.7207630633121371,
      "grad_norm": 0.3661884367465973,
      "learning_rate": 1.427534614685992e-05,
      "loss": 0.5805,
      "step": 23463
    },
    {
      "epoch": 0.7207937824470863,
      "grad_norm": 0.3370664119720459,
      "learning_rate": 1.4274909259648855e-05,
      "loss": 0.5653,
      "step": 23464
    },
    {
      "epoch": 0.7208245015820355,
      "grad_norm": 0.33649757504463196,
      "learning_rate": 1.4274472362453442e-05,
      "loss": 0.6166,
      "step": 23465
    },
    {
      "epoch": 0.7208552207169846,
      "grad_norm": 0.39650124311447144,
      "learning_rate": 1.4274035455274695e-05,
      "loss": 0.5767,
      "step": 23466
    },
    {
      "epoch": 0.7208859398519337,
      "grad_norm": 0.3307555913925171,
      "learning_rate": 1.4273598538113646e-05,
      "loss": 0.4849,
      "step": 23467
    },
    {
      "epoch": 0.720916658986883,
      "grad_norm": 0.33985888957977295,
      "learning_rate": 1.4273161610971307e-05,
      "loss": 0.5805,
      "step": 23468
    },
    {
      "epoch": 0.7209473781218321,
      "grad_norm": 0.3778727948665619,
      "learning_rate": 1.42727246738487e-05,
      "loss": 0.4693,
      "step": 23469
    },
    {
      "epoch": 0.7209780972567813,
      "grad_norm": 0.5259585976600647,
      "learning_rate": 1.4272287726746845e-05,
      "loss": 0.6184,
      "step": 23470
    },
    {
      "epoch": 0.7210088163917304,
      "grad_norm": 0.3810993432998657,
      "learning_rate": 1.4271850769666763e-05,
      "loss": 0.5616,
      "step": 23471
    },
    {
      "epoch": 0.7210395355266795,
      "grad_norm": 0.3548995554447174,
      "learning_rate": 1.427141380260948e-05,
      "loss": 0.5633,
      "step": 23472
    },
    {
      "epoch": 0.7210702546616288,
      "grad_norm": 0.32920271158218384,
      "learning_rate": 1.4270976825576006e-05,
      "loss": 0.5484,
      "step": 23473
    },
    {
      "epoch": 0.7211009737965779,
      "grad_norm": 0.33987072110176086,
      "learning_rate": 1.4270539838567371e-05,
      "loss": 0.5073,
      "step": 23474
    },
    {
      "epoch": 0.721131692931527,
      "grad_norm": 0.37485525012016296,
      "learning_rate": 1.4270102841584594e-05,
      "loss": 0.5564,
      "step": 23475
    },
    {
      "epoch": 0.7211624120664762,
      "grad_norm": 0.32292401790618896,
      "learning_rate": 1.426966583462869e-05,
      "loss": 0.5713,
      "step": 23476
    },
    {
      "epoch": 0.7211931312014254,
      "grad_norm": 0.42183274030685425,
      "learning_rate": 1.4269228817700685e-05,
      "loss": 0.5866,
      "step": 23477
    },
    {
      "epoch": 0.7212238503363745,
      "grad_norm": 0.35733240842819214,
      "learning_rate": 1.4268791790801598e-05,
      "loss": 0.6096,
      "step": 23478
    },
    {
      "epoch": 0.7212545694713237,
      "grad_norm": 0.3717252314090729,
      "learning_rate": 1.4268354753932447e-05,
      "loss": 0.5921,
      "step": 23479
    },
    {
      "epoch": 0.7212852886062728,
      "grad_norm": 0.3736947178840637,
      "learning_rate": 1.4267917707094257e-05,
      "loss": 0.4554,
      "step": 23480
    },
    {
      "epoch": 0.721316007741222,
      "grad_norm": 0.3663298189640045,
      "learning_rate": 1.4267480650288048e-05,
      "loss": 0.5867,
      "step": 23481
    },
    {
      "epoch": 0.7213467268761712,
      "grad_norm": 0.45398327708244324,
      "learning_rate": 1.4267043583514836e-05,
      "loss": 0.5095,
      "step": 23482
    },
    {
      "epoch": 0.7213774460111203,
      "grad_norm": 0.36694446206092834,
      "learning_rate": 1.4266606506775653e-05,
      "loss": 0.5956,
      "step": 23483
    },
    {
      "epoch": 0.7214081651460695,
      "grad_norm": 0.4851472079753876,
      "learning_rate": 1.4266169420071507e-05,
      "loss": 0.5639,
      "step": 23484
    },
    {
      "epoch": 0.7214388842810187,
      "grad_norm": 0.39363670349121094,
      "learning_rate": 1.4265732323403426e-05,
      "loss": 0.5258,
      "step": 23485
    },
    {
      "epoch": 0.7214696034159678,
      "grad_norm": 0.3572028875350952,
      "learning_rate": 1.426529521677243e-05,
      "loss": 0.5246,
      "step": 23486
    },
    {
      "epoch": 0.721500322550917,
      "grad_norm": 0.3445357084274292,
      "learning_rate": 1.4264858100179537e-05,
      "loss": 0.5678,
      "step": 23487
    },
    {
      "epoch": 0.7215310416858661,
      "grad_norm": 0.4097510874271393,
      "learning_rate": 1.4264420973625772e-05,
      "loss": 0.5672,
      "step": 23488
    },
    {
      "epoch": 0.7215617608208152,
      "grad_norm": 0.3336658477783203,
      "learning_rate": 1.426398383711215e-05,
      "loss": 0.5434,
      "step": 23489
    },
    {
      "epoch": 0.7215924799557645,
      "grad_norm": 0.40842708945274353,
      "learning_rate": 1.42635466906397e-05,
      "loss": 0.5809,
      "step": 23490
    },
    {
      "epoch": 0.7216231990907136,
      "grad_norm": 0.3394746780395508,
      "learning_rate": 1.4263109534209436e-05,
      "loss": 0.5382,
      "step": 23491
    },
    {
      "epoch": 0.7216539182256627,
      "grad_norm": 0.34217455983161926,
      "learning_rate": 1.4262672367822385e-05,
      "loss": 0.5194,
      "step": 23492
    },
    {
      "epoch": 0.721684637360612,
      "grad_norm": 0.37281423807144165,
      "learning_rate": 1.4262235191479566e-05,
      "loss": 0.4995,
      "step": 23493
    },
    {
      "epoch": 0.7217153564955611,
      "grad_norm": 0.38173940777778625,
      "learning_rate": 1.4261798005181998e-05,
      "loss": 0.5987,
      "step": 23494
    },
    {
      "epoch": 0.7217460756305103,
      "grad_norm": 0.3785091042518616,
      "learning_rate": 1.4261360808930703e-05,
      "loss": 0.5775,
      "step": 23495
    },
    {
      "epoch": 0.7217767947654594,
      "grad_norm": 0.39345741271972656,
      "learning_rate": 1.42609236027267e-05,
      "loss": 0.6366,
      "step": 23496
    },
    {
      "epoch": 0.7218075139004085,
      "grad_norm": 0.34291011095046997,
      "learning_rate": 1.4260486386571012e-05,
      "loss": 0.6027,
      "step": 23497
    },
    {
      "epoch": 0.7218382330353578,
      "grad_norm": 0.411468505859375,
      "learning_rate": 1.4260049160464662e-05,
      "loss": 0.6068,
      "step": 23498
    },
    {
      "epoch": 0.7218689521703069,
      "grad_norm": 0.3584659695625305,
      "learning_rate": 1.4259611924408672e-05,
      "loss": 0.58,
      "step": 23499
    },
    {
      "epoch": 0.721899671305256,
      "grad_norm": 0.3552321493625641,
      "learning_rate": 1.4259174678404057e-05,
      "loss": 0.5471,
      "step": 23500
    },
    {
      "epoch": 0.7219303904402052,
      "grad_norm": 0.34494662284851074,
      "learning_rate": 1.4258737422451845e-05,
      "loss": 0.5457,
      "step": 23501
    },
    {
      "epoch": 0.7219611095751544,
      "grad_norm": 0.3720614016056061,
      "learning_rate": 1.4258300156553051e-05,
      "loss": 0.5179,
      "step": 23502
    },
    {
      "epoch": 0.7219918287101035,
      "grad_norm": 0.34958207607269287,
      "learning_rate": 1.4257862880708704e-05,
      "loss": 0.5272,
      "step": 23503
    },
    {
      "epoch": 0.7220225478450527,
      "grad_norm": 0.4568202495574951,
      "learning_rate": 1.4257425594919818e-05,
      "loss": 0.5586,
      "step": 23504
    },
    {
      "epoch": 0.7220532669800018,
      "grad_norm": 0.3843866288661957,
      "learning_rate": 1.4256988299187417e-05,
      "loss": 0.5801,
      "step": 23505
    },
    {
      "epoch": 0.722083986114951,
      "grad_norm": 0.36378565430641174,
      "learning_rate": 1.4256550993512527e-05,
      "loss": 0.607,
      "step": 23506
    },
    {
      "epoch": 0.7221147052499002,
      "grad_norm": 0.36671867966651917,
      "learning_rate": 1.4256113677896158e-05,
      "loss": 0.6193,
      "step": 23507
    },
    {
      "epoch": 0.7221454243848493,
      "grad_norm": 0.4297789931297302,
      "learning_rate": 1.425567635233934e-05,
      "loss": 0.5734,
      "step": 23508
    },
    {
      "epoch": 0.7221761435197985,
      "grad_norm": 0.728316605091095,
      "learning_rate": 1.4255239016843095e-05,
      "loss": 0.5575,
      "step": 23509
    },
    {
      "epoch": 0.7222068626547476,
      "grad_norm": 0.3559725284576416,
      "learning_rate": 1.4254801671408442e-05,
      "loss": 0.5936,
      "step": 23510
    },
    {
      "epoch": 0.7222375817896968,
      "grad_norm": 0.4130822718143463,
      "learning_rate": 1.4254364316036402e-05,
      "loss": 0.5243,
      "step": 23511
    },
    {
      "epoch": 0.722268300924646,
      "grad_norm": 0.3829379081726074,
      "learning_rate": 1.4253926950727997e-05,
      "loss": 0.4824,
      "step": 23512
    },
    {
      "epoch": 0.7222990200595951,
      "grad_norm": 0.3305726945400238,
      "learning_rate": 1.4253489575484247e-05,
      "loss": 0.5554,
      "step": 23513
    },
    {
      "epoch": 0.7223297391945442,
      "grad_norm": 0.3740295469760895,
      "learning_rate": 1.4253052190306177e-05,
      "loss": 0.5811,
      "step": 23514
    },
    {
      "epoch": 0.7223604583294935,
      "grad_norm": 0.3594711720943451,
      "learning_rate": 1.4252614795194805e-05,
      "loss": 0.603,
      "step": 23515
    },
    {
      "epoch": 0.7223911774644426,
      "grad_norm": 0.35480058193206787,
      "learning_rate": 1.4252177390151156e-05,
      "loss": 0.4766,
      "step": 23516
    },
    {
      "epoch": 0.7224218965993917,
      "grad_norm": 0.3549823462963104,
      "learning_rate": 1.4251739975176248e-05,
      "loss": 0.5985,
      "step": 23517
    },
    {
      "epoch": 0.7224526157343409,
      "grad_norm": 0.35526639223098755,
      "learning_rate": 1.4251302550271104e-05,
      "loss": 0.6272,
      "step": 23518
    },
    {
      "epoch": 0.7224833348692901,
      "grad_norm": 0.34360334277153015,
      "learning_rate": 1.4250865115436749e-05,
      "loss": 0.5596,
      "step": 23519
    },
    {
      "epoch": 0.7225140540042393,
      "grad_norm": 0.37993302941322327,
      "learning_rate": 1.4250427670674198e-05,
      "loss": 0.503,
      "step": 23520
    },
    {
      "epoch": 0.7225447731391884,
      "grad_norm": 0.3571467101573944,
      "learning_rate": 1.4249990215984482e-05,
      "loss": 0.578,
      "step": 23521
    },
    {
      "epoch": 0.7225754922741375,
      "grad_norm": 0.3444359600543976,
      "learning_rate": 1.4249552751368611e-05,
      "loss": 0.5547,
      "step": 23522
    },
    {
      "epoch": 0.7226062114090868,
      "grad_norm": 0.34911638498306274,
      "learning_rate": 1.4249115276827614e-05,
      "loss": 0.5207,
      "step": 23523
    },
    {
      "epoch": 0.7226369305440359,
      "grad_norm": 0.3860121965408325,
      "learning_rate": 1.4248677792362515e-05,
      "loss": 0.5549,
      "step": 23524
    },
    {
      "epoch": 0.722667649678985,
      "grad_norm": 0.3352706730365753,
      "learning_rate": 1.4248240297974327e-05,
      "loss": 0.5056,
      "step": 23525
    },
    {
      "epoch": 0.7226983688139342,
      "grad_norm": 0.3512820899486542,
      "learning_rate": 1.4247802793664081e-05,
      "loss": 0.5402,
      "step": 23526
    },
    {
      "epoch": 0.7227290879488834,
      "grad_norm": 0.43235495686531067,
      "learning_rate": 1.4247365279432794e-05,
      "loss": 0.5529,
      "step": 23527
    },
    {
      "epoch": 0.7227598070838325,
      "grad_norm": 0.37741196155548096,
      "learning_rate": 1.4246927755281488e-05,
      "loss": 0.5438,
      "step": 23528
    },
    {
      "epoch": 0.7227905262187817,
      "grad_norm": 0.3736162483692169,
      "learning_rate": 1.4246490221211186e-05,
      "loss": 0.5415,
      "step": 23529
    },
    {
      "epoch": 0.7228212453537308,
      "grad_norm": 0.4622918963432312,
      "learning_rate": 1.4246052677222909e-05,
      "loss": 0.4973,
      "step": 23530
    },
    {
      "epoch": 0.7228519644886799,
      "grad_norm": 0.3693772554397583,
      "learning_rate": 1.424561512331768e-05,
      "loss": 0.5761,
      "step": 23531
    },
    {
      "epoch": 0.7228826836236292,
      "grad_norm": 0.3438240587711334,
      "learning_rate": 1.4245177559496521e-05,
      "loss": 0.5499,
      "step": 23532
    },
    {
      "epoch": 0.7229134027585783,
      "grad_norm": 0.3542213439941406,
      "learning_rate": 1.4244739985760453e-05,
      "loss": 0.4583,
      "step": 23533
    },
    {
      "epoch": 0.7229441218935275,
      "grad_norm": 0.3750077486038208,
      "learning_rate": 1.4244302402110496e-05,
      "loss": 0.5647,
      "step": 23534
    },
    {
      "epoch": 0.7229748410284766,
      "grad_norm": 0.41831180453300476,
      "learning_rate": 1.4243864808547677e-05,
      "loss": 0.6675,
      "step": 23535
    },
    {
      "epoch": 0.7230055601634258,
      "grad_norm": 0.5244983434677124,
      "learning_rate": 1.4243427205073014e-05,
      "loss": 0.6826,
      "step": 23536
    },
    {
      "epoch": 0.723036279298375,
      "grad_norm": 0.4066429138183594,
      "learning_rate": 1.4242989591687532e-05,
      "loss": 0.5748,
      "step": 23537
    },
    {
      "epoch": 0.7230669984333241,
      "grad_norm": 0.616328775882721,
      "learning_rate": 1.4242551968392253e-05,
      "loss": 0.547,
      "step": 23538
    },
    {
      "epoch": 0.7230977175682732,
      "grad_norm": 0.3794616162776947,
      "learning_rate": 1.4242114335188193e-05,
      "loss": 0.4982,
      "step": 23539
    },
    {
      "epoch": 0.7231284367032225,
      "grad_norm": 0.34607994556427,
      "learning_rate": 1.4241676692076383e-05,
      "loss": 0.5203,
      "step": 23540
    },
    {
      "epoch": 0.7231591558381716,
      "grad_norm": 0.36104822158813477,
      "learning_rate": 1.4241239039057836e-05,
      "loss": 0.5054,
      "step": 23541
    },
    {
      "epoch": 0.7231898749731207,
      "grad_norm": 0.3541184961795807,
      "learning_rate": 1.4240801376133585e-05,
      "loss": 0.6594,
      "step": 23542
    },
    {
      "epoch": 0.7232205941080699,
      "grad_norm": 0.3412359952926636,
      "learning_rate": 1.4240363703304638e-05,
      "loss": 0.6325,
      "step": 23543
    },
    {
      "epoch": 0.7232513132430191,
      "grad_norm": 0.3251633942127228,
      "learning_rate": 1.4239926020572032e-05,
      "loss": 0.5314,
      "step": 23544
    },
    {
      "epoch": 0.7232820323779683,
      "grad_norm": 0.3489767611026764,
      "learning_rate": 1.4239488327936783e-05,
      "loss": 0.4876,
      "step": 23545
    },
    {
      "epoch": 0.7233127515129174,
      "grad_norm": 0.3867242932319641,
      "learning_rate": 1.4239050625399911e-05,
      "loss": 0.5427,
      "step": 23546
    },
    {
      "epoch": 0.7233434706478665,
      "grad_norm": 0.35458317399024963,
      "learning_rate": 1.423861291296244e-05,
      "loss": 0.5871,
      "step": 23547
    },
    {
      "epoch": 0.7233741897828158,
      "grad_norm": 0.34922313690185547,
      "learning_rate": 1.4238175190625392e-05,
      "loss": 0.5489,
      "step": 23548
    },
    {
      "epoch": 0.7234049089177649,
      "grad_norm": 0.3462423086166382,
      "learning_rate": 1.4237737458389791e-05,
      "loss": 0.5782,
      "step": 23549
    },
    {
      "epoch": 0.723435628052714,
      "grad_norm": 0.434574156999588,
      "learning_rate": 1.4237299716256656e-05,
      "loss": 0.518,
      "step": 23550
    },
    {
      "epoch": 0.7234663471876632,
      "grad_norm": 0.43729275465011597,
      "learning_rate": 1.4236861964227016e-05,
      "loss": 0.5057,
      "step": 23551
    },
    {
      "epoch": 0.7234970663226123,
      "grad_norm": 0.37877216935157776,
      "learning_rate": 1.4236424202301883e-05,
      "loss": 0.5618,
      "step": 23552
    },
    {
      "epoch": 0.7235277854575615,
      "grad_norm": 0.37984994053840637,
      "learning_rate": 1.4235986430482292e-05,
      "loss": 0.5368,
      "step": 23553
    },
    {
      "epoch": 0.7235585045925107,
      "grad_norm": 0.3621096611022949,
      "learning_rate": 1.4235548648769256e-05,
      "loss": 0.5725,
      "step": 23554
    },
    {
      "epoch": 0.7235892237274598,
      "grad_norm": 0.3596028685569763,
      "learning_rate": 1.42351108571638e-05,
      "loss": 0.6169,
      "step": 23555
    },
    {
      "epoch": 0.723619942862409,
      "grad_norm": 0.3701498210430145,
      "learning_rate": 1.4234673055666948e-05,
      "loss": 0.552,
      "step": 23556
    },
    {
      "epoch": 0.7236506619973582,
      "grad_norm": 0.3714126646518707,
      "learning_rate": 1.4234235244279717e-05,
      "loss": 0.5682,
      "step": 23557
    },
    {
      "epoch": 0.7236813811323073,
      "grad_norm": 0.40173104405403137,
      "learning_rate": 1.4233797423003139e-05,
      "loss": 0.7051,
      "step": 23558
    },
    {
      "epoch": 0.7237121002672565,
      "grad_norm": 0.3745660185813904,
      "learning_rate": 1.4233359591838227e-05,
      "loss": 0.5995,
      "step": 23559
    },
    {
      "epoch": 0.7237428194022056,
      "grad_norm": 0.38664981722831726,
      "learning_rate": 1.4232921750786013e-05,
      "loss": 0.5587,
      "step": 23560
    },
    {
      "epoch": 0.7237735385371548,
      "grad_norm": 0.4140790104866028,
      "learning_rate": 1.4232483899847511e-05,
      "loss": 0.5288,
      "step": 23561
    },
    {
      "epoch": 0.723804257672104,
      "grad_norm": 0.3839832544326782,
      "learning_rate": 1.4232046039023746e-05,
      "loss": 0.5741,
      "step": 23562
    },
    {
      "epoch": 0.7238349768070531,
      "grad_norm": 0.4153613746166229,
      "learning_rate": 1.4231608168315746e-05,
      "loss": 0.5012,
      "step": 23563
    },
    {
      "epoch": 0.7238656959420022,
      "grad_norm": 0.38559553027153015,
      "learning_rate": 1.4231170287724527e-05,
      "loss": 0.5815,
      "step": 23564
    },
    {
      "epoch": 0.7238964150769515,
      "grad_norm": 0.41478753089904785,
      "learning_rate": 1.4230732397251115e-05,
      "loss": 0.6385,
      "step": 23565
    },
    {
      "epoch": 0.7239271342119006,
      "grad_norm": 0.347736656665802,
      "learning_rate": 1.4230294496896532e-05,
      "loss": 0.507,
      "step": 23566
    },
    {
      "epoch": 0.7239578533468497,
      "grad_norm": 0.33042705059051514,
      "learning_rate": 1.4229856586661801e-05,
      "loss": 0.5066,
      "step": 23567
    },
    {
      "epoch": 0.7239885724817989,
      "grad_norm": 0.3666737377643585,
      "learning_rate": 1.4229418666547945e-05,
      "loss": 0.6081,
      "step": 23568
    },
    {
      "epoch": 0.724019291616748,
      "grad_norm": 0.3478720784187317,
      "learning_rate": 1.4228980736555986e-05,
      "loss": 0.5656,
      "step": 23569
    },
    {
      "epoch": 0.7240500107516973,
      "grad_norm": 0.36524301767349243,
      "learning_rate": 1.4228542796686946e-05,
      "loss": 0.533,
      "step": 23570
    },
    {
      "epoch": 0.7240807298866464,
      "grad_norm": 0.3652389645576477,
      "learning_rate": 1.422810484694185e-05,
      "loss": 0.6263,
      "step": 23571
    },
    {
      "epoch": 0.7241114490215955,
      "grad_norm": 0.32612359523773193,
      "learning_rate": 1.422766688732172e-05,
      "loss": 0.4685,
      "step": 23572
    },
    {
      "epoch": 0.7241421681565448,
      "grad_norm": 0.4568779170513153,
      "learning_rate": 1.4227228917827578e-05,
      "loss": 0.5696,
      "step": 23573
    },
    {
      "epoch": 0.7241728872914939,
      "grad_norm": 0.3929382860660553,
      "learning_rate": 1.4226790938460449e-05,
      "loss": 0.6065,
      "step": 23574
    },
    {
      "epoch": 0.724203606426443,
      "grad_norm": 0.34109339118003845,
      "learning_rate": 1.4226352949221354e-05,
      "loss": 0.5296,
      "step": 23575
    },
    {
      "epoch": 0.7242343255613922,
      "grad_norm": 0.35941293835639954,
      "learning_rate": 1.4225914950111318e-05,
      "loss": 0.5471,
      "step": 23576
    },
    {
      "epoch": 0.7242650446963413,
      "grad_norm": 0.36524489521980286,
      "learning_rate": 1.4225476941131358e-05,
      "loss": 0.5515,
      "step": 23577
    },
    {
      "epoch": 0.7242957638312905,
      "grad_norm": 0.32702356576919556,
      "learning_rate": 1.4225038922282506e-05,
      "loss": 0.5481,
      "step": 23578
    },
    {
      "epoch": 0.7243264829662397,
      "grad_norm": 0.37777161598205566,
      "learning_rate": 1.4224600893565777e-05,
      "loss": 0.6303,
      "step": 23579
    },
    {
      "epoch": 0.7243572021011888,
      "grad_norm": 0.365879625082016,
      "learning_rate": 1.4224162854982197e-05,
      "loss": 0.5312,
      "step": 23580
    },
    {
      "epoch": 0.724387921236138,
      "grad_norm": 0.34263065457344055,
      "learning_rate": 1.4223724806532793e-05,
      "loss": 0.5218,
      "step": 23581
    },
    {
      "epoch": 0.7244186403710872,
      "grad_norm": 0.3555160164833069,
      "learning_rate": 1.4223286748218583e-05,
      "loss": 0.5147,
      "step": 23582
    },
    {
      "epoch": 0.7244493595060363,
      "grad_norm": 0.34509575366973877,
      "learning_rate": 1.4222848680040593e-05,
      "loss": 0.6227,
      "step": 23583
    },
    {
      "epoch": 0.7244800786409855,
      "grad_norm": 0.3607139587402344,
      "learning_rate": 1.4222410601999843e-05,
      "loss": 0.5479,
      "step": 23584
    },
    {
      "epoch": 0.7245107977759346,
      "grad_norm": 0.43900054693222046,
      "learning_rate": 1.4221972514097363e-05,
      "loss": 0.6165,
      "step": 23585
    },
    {
      "epoch": 0.7245415169108838,
      "grad_norm": 0.34456953406333923,
      "learning_rate": 1.4221534416334167e-05,
      "loss": 0.5993,
      "step": 23586
    },
    {
      "epoch": 0.724572236045833,
      "grad_norm": 0.3278615474700928,
      "learning_rate": 1.4221096308711284e-05,
      "loss": 0.5482,
      "step": 23587
    },
    {
      "epoch": 0.7246029551807821,
      "grad_norm": 0.3542517423629761,
      "learning_rate": 1.4220658191229735e-05,
      "loss": 0.5655,
      "step": 23588
    },
    {
      "epoch": 0.7246336743157312,
      "grad_norm": 0.6193568110466003,
      "learning_rate": 1.4220220063890544e-05,
      "loss": 0.5425,
      "step": 23589
    },
    {
      "epoch": 0.7246643934506805,
      "grad_norm": 0.3758081793785095,
      "learning_rate": 1.4219781926694736e-05,
      "loss": 0.5533,
      "step": 23590
    },
    {
      "epoch": 0.7246951125856296,
      "grad_norm": 0.36420997977256775,
      "learning_rate": 1.4219343779643328e-05,
      "loss": 0.5604,
      "step": 23591
    },
    {
      "epoch": 0.7247258317205787,
      "grad_norm": 0.3886128067970276,
      "learning_rate": 1.4218905622737353e-05,
      "loss": 0.6149,
      "step": 23592
    },
    {
      "epoch": 0.7247565508555279,
      "grad_norm": 0.4585995674133301,
      "learning_rate": 1.4218467455977826e-05,
      "loss": 0.557,
      "step": 23593
    },
    {
      "epoch": 0.724787269990477,
      "grad_norm": 0.35859495401382446,
      "learning_rate": 1.4218029279365777e-05,
      "loss": 0.5058,
      "step": 23594
    },
    {
      "epoch": 0.7248179891254263,
      "grad_norm": 0.3854186236858368,
      "learning_rate": 1.4217591092902223e-05,
      "loss": 0.5406,
      "step": 23595
    },
    {
      "epoch": 0.7248487082603754,
      "grad_norm": 1.0835661888122559,
      "learning_rate": 1.4217152896588193e-05,
      "loss": 0.5466,
      "step": 23596
    },
    {
      "epoch": 0.7248794273953245,
      "grad_norm": 0.3648626208305359,
      "learning_rate": 1.4216714690424704e-05,
      "loss": 0.5928,
      "step": 23597
    },
    {
      "epoch": 0.7249101465302737,
      "grad_norm": 0.38134458661079407,
      "learning_rate": 1.4216276474412785e-05,
      "loss": 0.5591,
      "step": 23598
    },
    {
      "epoch": 0.7249408656652229,
      "grad_norm": 0.48309874534606934,
      "learning_rate": 1.4215838248553459e-05,
      "loss": 0.5667,
      "step": 23599
    },
    {
      "epoch": 0.724971584800172,
      "grad_norm": 0.3313147723674774,
      "learning_rate": 1.421540001284775e-05,
      "loss": 0.5457,
      "step": 23600
    },
    {
      "epoch": 0.7250023039351212,
      "grad_norm": 0.3960816264152527,
      "learning_rate": 1.4214961767296678e-05,
      "loss": 0.5322,
      "step": 23601
    },
    {
      "epoch": 0.7250330230700703,
      "grad_norm": 0.38588660955429077,
      "learning_rate": 1.4214523511901265e-05,
      "loss": 0.5452,
      "step": 23602
    },
    {
      "epoch": 0.7250637422050195,
      "grad_norm": 0.3263353109359741,
      "learning_rate": 1.4214085246662544e-05,
      "loss": 0.5888,
      "step": 23603
    },
    {
      "epoch": 0.7250944613399687,
      "grad_norm": 0.36650851368904114,
      "learning_rate": 1.4213646971581527e-05,
      "loss": 0.5392,
      "step": 23604
    },
    {
      "epoch": 0.7251251804749178,
      "grad_norm": 0.4747573137283325,
      "learning_rate": 1.4213208686659248e-05,
      "loss": 0.5754,
      "step": 23605
    },
    {
      "epoch": 0.725155899609867,
      "grad_norm": 0.3595588207244873,
      "learning_rate": 1.4212770391896724e-05,
      "loss": 0.5737,
      "step": 23606
    },
    {
      "epoch": 0.7251866187448162,
      "grad_norm": 0.35866689682006836,
      "learning_rate": 1.421233208729498e-05,
      "loss": 0.5038,
      "step": 23607
    },
    {
      "epoch": 0.7252173378797653,
      "grad_norm": 0.430494099855423,
      "learning_rate": 1.4211893772855043e-05,
      "loss": 0.619,
      "step": 23608
    },
    {
      "epoch": 0.7252480570147145,
      "grad_norm": 0.3667164146900177,
      "learning_rate": 1.4211455448577928e-05,
      "loss": 0.491,
      "step": 23609
    },
    {
      "epoch": 0.7252787761496636,
      "grad_norm": 0.3604293465614319,
      "learning_rate": 1.4211017114464671e-05,
      "loss": 0.5741,
      "step": 23610
    },
    {
      "epoch": 0.7253094952846127,
      "grad_norm": 0.3586040139198303,
      "learning_rate": 1.4210578770516286e-05,
      "loss": 0.4825,
      "step": 23611
    },
    {
      "epoch": 0.725340214419562,
      "grad_norm": 0.43813616037368774,
      "learning_rate": 1.4210140416733802e-05,
      "loss": 0.5524,
      "step": 23612
    },
    {
      "epoch": 0.7253709335545111,
      "grad_norm": 0.39980700612068176,
      "learning_rate": 1.4209702053118237e-05,
      "loss": 0.6294,
      "step": 23613
    },
    {
      "epoch": 0.7254016526894602,
      "grad_norm": 0.352367639541626,
      "learning_rate": 1.4209263679670624e-05,
      "loss": 0.5896,
      "step": 23614
    },
    {
      "epoch": 0.7254323718244094,
      "grad_norm": 0.3426440954208374,
      "learning_rate": 1.4208825296391979e-05,
      "loss": 0.6318,
      "step": 23615
    },
    {
      "epoch": 0.7254630909593586,
      "grad_norm": 0.3985994756221771,
      "learning_rate": 1.4208386903283327e-05,
      "loss": 0.5942,
      "step": 23616
    },
    {
      "epoch": 0.7254938100943077,
      "grad_norm": 0.417350172996521,
      "learning_rate": 1.4207948500345695e-05,
      "loss": 0.4961,
      "step": 23617
    },
    {
      "epoch": 0.7255245292292569,
      "grad_norm": 0.4160880148410797,
      "learning_rate": 1.4207510087580108e-05,
      "loss": 0.4906,
      "step": 23618
    },
    {
      "epoch": 0.725555248364206,
      "grad_norm": 0.3859294354915619,
      "learning_rate": 1.4207071664987587e-05,
      "loss": 0.5419,
      "step": 23619
    },
    {
      "epoch": 0.7255859674991553,
      "grad_norm": 0.37368664145469666,
      "learning_rate": 1.4206633232569151e-05,
      "loss": 0.5098,
      "step": 23620
    },
    {
      "epoch": 0.7256166866341044,
      "grad_norm": 0.808610200881958,
      "learning_rate": 1.4206194790325833e-05,
      "loss": 0.5449,
      "step": 23621
    },
    {
      "epoch": 0.7256474057690535,
      "grad_norm": 0.37795358896255493,
      "learning_rate": 1.4205756338258654e-05,
      "loss": 0.4909,
      "step": 23622
    },
    {
      "epoch": 0.7256781249040027,
      "grad_norm": 0.30645954608917236,
      "learning_rate": 1.4205317876368638e-05,
      "loss": 0.5003,
      "step": 23623
    },
    {
      "epoch": 0.7257088440389519,
      "grad_norm": 0.3907066881656647,
      "learning_rate": 1.4204879404656807e-05,
      "loss": 0.5422,
      "step": 23624
    },
    {
      "epoch": 0.725739563173901,
      "grad_norm": 0.38744497299194336,
      "learning_rate": 1.4204440923124185e-05,
      "loss": 0.566,
      "step": 23625
    },
    {
      "epoch": 0.7257702823088502,
      "grad_norm": 0.38452228903770447,
      "learning_rate": 1.4204002431771801e-05,
      "loss": 0.5625,
      "step": 23626
    },
    {
      "epoch": 0.7258010014437993,
      "grad_norm": 0.37231042981147766,
      "learning_rate": 1.4203563930600672e-05,
      "loss": 0.5877,
      "step": 23627
    },
    {
      "epoch": 0.7258317205787485,
      "grad_norm": 0.3269977569580078,
      "learning_rate": 1.420312541961183e-05,
      "loss": 0.6083,
      "step": 23628
    },
    {
      "epoch": 0.7258624397136977,
      "grad_norm": 0.397399365901947,
      "learning_rate": 1.420268689880629e-05,
      "loss": 0.5514,
      "step": 23629
    },
    {
      "epoch": 0.7258931588486468,
      "grad_norm": 0.35324257612228394,
      "learning_rate": 1.4202248368185085e-05,
      "loss": 0.5605,
      "step": 23630
    },
    {
      "epoch": 0.725923877983596,
      "grad_norm": 0.35701411962509155,
      "learning_rate": 1.4201809827749234e-05,
      "loss": 0.5274,
      "step": 23631
    },
    {
      "epoch": 0.7259545971185452,
      "grad_norm": 0.3501030504703522,
      "learning_rate": 1.4201371277499766e-05,
      "loss": 0.6404,
      "step": 23632
    },
    {
      "epoch": 0.7259853162534943,
      "grad_norm": 0.3604285717010498,
      "learning_rate": 1.4200932717437696e-05,
      "loss": 0.5357,
      "step": 23633
    },
    {
      "epoch": 0.7260160353884435,
      "grad_norm": 0.3467474579811096,
      "learning_rate": 1.4200494147564059e-05,
      "loss": 0.5708,
      "step": 23634
    },
    {
      "epoch": 0.7260467545233926,
      "grad_norm": 0.5039874911308289,
      "learning_rate": 1.4200055567879872e-05,
      "loss": 0.5587,
      "step": 23635
    },
    {
      "epoch": 0.7260774736583417,
      "grad_norm": 0.32333534955978394,
      "learning_rate": 1.4199616978386162e-05,
      "loss": 0.4742,
      "step": 23636
    },
    {
      "epoch": 0.726108192793291,
      "grad_norm": 0.3479653298854828,
      "learning_rate": 1.4199178379083954e-05,
      "loss": 0.6476,
      "step": 23637
    },
    {
      "epoch": 0.7261389119282401,
      "grad_norm": 0.445355087518692,
      "learning_rate": 1.419873976997427e-05,
      "loss": 0.5719,
      "step": 23638
    },
    {
      "epoch": 0.7261696310631892,
      "grad_norm": 0.37784457206726074,
      "learning_rate": 1.4198301151058138e-05,
      "loss": 0.4871,
      "step": 23639
    },
    {
      "epoch": 0.7262003501981384,
      "grad_norm": 0.34361544251441956,
      "learning_rate": 1.4197862522336578e-05,
      "loss": 0.507,
      "step": 23640
    },
    {
      "epoch": 0.7262310693330876,
      "grad_norm": 0.33159273862838745,
      "learning_rate": 1.4197423883810622e-05,
      "loss": 0.5632,
      "step": 23641
    },
    {
      "epoch": 0.7262617884680368,
      "grad_norm": 0.3924744725227356,
      "learning_rate": 1.4196985235481287e-05,
      "loss": 0.5602,
      "step": 23642
    },
    {
      "epoch": 0.7262925076029859,
      "grad_norm": 0.3940472900867462,
      "learning_rate": 1.41965465773496e-05,
      "loss": 0.4785,
      "step": 23643
    },
    {
      "epoch": 0.726323226737935,
      "grad_norm": 0.3590486943721771,
      "learning_rate": 1.4196107909416584e-05,
      "loss": 0.5561,
      "step": 23644
    },
    {
      "epoch": 0.7263539458728843,
      "grad_norm": 0.384631872177124,
      "learning_rate": 1.4195669231683264e-05,
      "loss": 0.6053,
      "step": 23645
    },
    {
      "epoch": 0.7263846650078334,
      "grad_norm": 0.6582173705101013,
      "learning_rate": 1.4195230544150668e-05,
      "loss": 0.5167,
      "step": 23646
    },
    {
      "epoch": 0.7264153841427825,
      "grad_norm": 0.49320319294929504,
      "learning_rate": 1.4194791846819817e-05,
      "loss": 0.5639,
      "step": 23647
    },
    {
      "epoch": 0.7264461032777317,
      "grad_norm": 0.36309540271759033,
      "learning_rate": 1.4194353139691737e-05,
      "loss": 0.6017,
      "step": 23648
    },
    {
      "epoch": 0.7264768224126809,
      "grad_norm": 0.3810455799102783,
      "learning_rate": 1.4193914422767452e-05,
      "loss": 0.5704,
      "step": 23649
    },
    {
      "epoch": 0.72650754154763,
      "grad_norm": 0.37978923320770264,
      "learning_rate": 1.4193475696047987e-05,
      "loss": 0.6431,
      "step": 23650
    },
    {
      "epoch": 0.7265382606825792,
      "grad_norm": 0.4737134277820587,
      "learning_rate": 1.4193036959534365e-05,
      "loss": 0.6235,
      "step": 23651
    },
    {
      "epoch": 0.7265689798175283,
      "grad_norm": 0.36666056513786316,
      "learning_rate": 1.4192598213227615e-05,
      "loss": 0.5328,
      "step": 23652
    },
    {
      "epoch": 0.7265996989524774,
      "grad_norm": 0.3435770571231842,
      "learning_rate": 1.4192159457128758e-05,
      "loss": 0.5205,
      "step": 23653
    },
    {
      "epoch": 0.7266304180874267,
      "grad_norm": 0.35588446259498596,
      "learning_rate": 1.4191720691238819e-05,
      "loss": 0.5005,
      "step": 23654
    },
    {
      "epoch": 0.7266611372223758,
      "grad_norm": 0.4103385806083679,
      "learning_rate": 1.4191281915558826e-05,
      "loss": 0.5791,
      "step": 23655
    },
    {
      "epoch": 0.726691856357325,
      "grad_norm": 0.33726218342781067,
      "learning_rate": 1.4190843130089797e-05,
      "loss": 0.6239,
      "step": 23656
    },
    {
      "epoch": 0.7267225754922741,
      "grad_norm": 0.33079278469085693,
      "learning_rate": 1.4190404334832766e-05,
      "loss": 0.5108,
      "step": 23657
    },
    {
      "epoch": 0.7267532946272233,
      "grad_norm": 0.3695538341999054,
      "learning_rate": 1.418996552978875e-05,
      "loss": 0.4978,
      "step": 23658
    },
    {
      "epoch": 0.7267840137621725,
      "grad_norm": 0.3764713406562805,
      "learning_rate": 1.4189526714958779e-05,
      "loss": 0.5155,
      "step": 23659
    },
    {
      "epoch": 0.7268147328971216,
      "grad_norm": 0.39029690623283386,
      "learning_rate": 1.4189087890343875e-05,
      "loss": 0.5318,
      "step": 23660
    },
    {
      "epoch": 0.7268454520320707,
      "grad_norm": 0.35460689663887024,
      "learning_rate": 1.4188649055945063e-05,
      "loss": 0.5321,
      "step": 23661
    },
    {
      "epoch": 0.72687617116702,
      "grad_norm": 0.36746084690093994,
      "learning_rate": 1.4188210211763371e-05,
      "loss": 0.5647,
      "step": 23662
    },
    {
      "epoch": 0.7269068903019691,
      "grad_norm": 0.3940039575099945,
      "learning_rate": 1.4187771357799818e-05,
      "loss": 0.5764,
      "step": 23663
    },
    {
      "epoch": 0.7269376094369182,
      "grad_norm": 0.3698848485946655,
      "learning_rate": 1.4187332494055434e-05,
      "loss": 0.5009,
      "step": 23664
    },
    {
      "epoch": 0.7269683285718674,
      "grad_norm": 0.3521776795387268,
      "learning_rate": 1.4186893620531242e-05,
      "loss": 0.559,
      "step": 23665
    },
    {
      "epoch": 0.7269990477068166,
      "grad_norm": 0.32246285676956177,
      "learning_rate": 1.418645473722827e-05,
      "loss": 0.5357,
      "step": 23666
    },
    {
      "epoch": 0.7270297668417658,
      "grad_norm": 0.36324405670166016,
      "learning_rate": 1.4186015844147538e-05,
      "loss": 0.5306,
      "step": 23667
    },
    {
      "epoch": 0.7270604859767149,
      "grad_norm": 0.3495122194290161,
      "learning_rate": 1.4185576941290073e-05,
      "loss": 0.5361,
      "step": 23668
    },
    {
      "epoch": 0.727091205111664,
      "grad_norm": 0.3654204308986664,
      "learning_rate": 1.4185138028656901e-05,
      "loss": 0.5168,
      "step": 23669
    },
    {
      "epoch": 0.7271219242466133,
      "grad_norm": 0.41240623593330383,
      "learning_rate": 1.4184699106249049e-05,
      "loss": 0.5746,
      "step": 23670
    },
    {
      "epoch": 0.7271526433815624,
      "grad_norm": 0.35371023416519165,
      "learning_rate": 1.4184260174067539e-05,
      "loss": 0.5814,
      "step": 23671
    },
    {
      "epoch": 0.7271833625165115,
      "grad_norm": 0.46820759773254395,
      "learning_rate": 1.4183821232113398e-05,
      "loss": 0.5673,
      "step": 23672
    },
    {
      "epoch": 0.7272140816514607,
      "grad_norm": 0.6816707849502563,
      "learning_rate": 1.4183382280387648e-05,
      "loss": 0.5718,
      "step": 23673
    },
    {
      "epoch": 0.7272448007864099,
      "grad_norm": 0.34966328740119934,
      "learning_rate": 1.4182943318891318e-05,
      "loss": 0.521,
      "step": 23674
    },
    {
      "epoch": 0.727275519921359,
      "grad_norm": 0.38064253330230713,
      "learning_rate": 1.4182504347625431e-05,
      "loss": 0.5502,
      "step": 23675
    },
    {
      "epoch": 0.7273062390563082,
      "grad_norm": 0.3547210097312927,
      "learning_rate": 1.4182065366591013e-05,
      "loss": 0.5587,
      "step": 23676
    },
    {
      "epoch": 0.7273369581912573,
      "grad_norm": 0.35320207476615906,
      "learning_rate": 1.418162637578909e-05,
      "loss": 0.4789,
      "step": 23677
    },
    {
      "epoch": 0.7273676773262064,
      "grad_norm": 0.4392543435096741,
      "learning_rate": 1.4181187375220688e-05,
      "loss": 0.5687,
      "step": 23678
    },
    {
      "epoch": 0.7273983964611557,
      "grad_norm": 0.35102733969688416,
      "learning_rate": 1.418074836488683e-05,
      "loss": 0.6056,
      "step": 23679
    },
    {
      "epoch": 0.7274291155961048,
      "grad_norm": 0.31673920154571533,
      "learning_rate": 1.418030934478854e-05,
      "loss": 0.4979,
      "step": 23680
    },
    {
      "epoch": 0.727459834731054,
      "grad_norm": 0.33973270654678345,
      "learning_rate": 1.4179870314926847e-05,
      "loss": 0.5974,
      "step": 23681
    },
    {
      "epoch": 0.7274905538660031,
      "grad_norm": 0.36820733547210693,
      "learning_rate": 1.4179431275302777e-05,
      "loss": 0.5429,
      "step": 23682
    },
    {
      "epoch": 0.7275212730009523,
      "grad_norm": 0.3375203311443329,
      "learning_rate": 1.417899222591735e-05,
      "loss": 0.4856,
      "step": 23683
    },
    {
      "epoch": 0.7275519921359015,
      "grad_norm": 0.4372187852859497,
      "learning_rate": 1.4178553166771599e-05,
      "loss": 0.6219,
      "step": 23684
    },
    {
      "epoch": 0.7275827112708506,
      "grad_norm": 0.36342763900756836,
      "learning_rate": 1.417811409786654e-05,
      "loss": 0.5706,
      "step": 23685
    },
    {
      "epoch": 0.7276134304057997,
      "grad_norm": 0.41063809394836426,
      "learning_rate": 1.4177675019203207e-05,
      "loss": 0.5834,
      "step": 23686
    },
    {
      "epoch": 0.727644149540749,
      "grad_norm": 0.35983720421791077,
      "learning_rate": 1.417723593078262e-05,
      "loss": 0.5377,
      "step": 23687
    },
    {
      "epoch": 0.7276748686756981,
      "grad_norm": 0.7070322632789612,
      "learning_rate": 1.417679683260581e-05,
      "loss": 0.6076,
      "step": 23688
    },
    {
      "epoch": 0.7277055878106472,
      "grad_norm": 0.3942178189754486,
      "learning_rate": 1.4176357724673798e-05,
      "loss": 0.5189,
      "step": 23689
    },
    {
      "epoch": 0.7277363069455964,
      "grad_norm": 0.406179815530777,
      "learning_rate": 1.4175918606987607e-05,
      "loss": 0.5003,
      "step": 23690
    },
    {
      "epoch": 0.7277670260805456,
      "grad_norm": 0.3940722644329071,
      "learning_rate": 1.4175479479548272e-05,
      "loss": 0.5898,
      "step": 23691
    },
    {
      "epoch": 0.7277977452154948,
      "grad_norm": 0.43896061182022095,
      "learning_rate": 1.4175040342356809e-05,
      "loss": 0.5015,
      "step": 23692
    },
    {
      "epoch": 0.7278284643504439,
      "grad_norm": 0.32563382387161255,
      "learning_rate": 1.417460119541425e-05,
      "loss": 0.5137,
      "step": 23693
    },
    {
      "epoch": 0.727859183485393,
      "grad_norm": 0.4146062135696411,
      "learning_rate": 1.4174162038721616e-05,
      "loss": 0.5592,
      "step": 23694
    },
    {
      "epoch": 0.7278899026203423,
      "grad_norm": 0.37616169452667236,
      "learning_rate": 1.4173722872279938e-05,
      "loss": 0.5174,
      "step": 23695
    },
    {
      "epoch": 0.7279206217552914,
      "grad_norm": 0.38926035165786743,
      "learning_rate": 1.4173283696090238e-05,
      "loss": 0.5809,
      "step": 23696
    },
    {
      "epoch": 0.7279513408902405,
      "grad_norm": 0.4060308635234833,
      "learning_rate": 1.4172844510153542e-05,
      "loss": 0.581,
      "step": 23697
    },
    {
      "epoch": 0.7279820600251897,
      "grad_norm": 0.3433569073677063,
      "learning_rate": 1.4172405314470879e-05,
      "loss": 0.6551,
      "step": 23698
    },
    {
      "epoch": 0.7280127791601388,
      "grad_norm": 0.38237112760543823,
      "learning_rate": 1.4171966109043267e-05,
      "loss": 0.5956,
      "step": 23699
    },
    {
      "epoch": 0.728043498295088,
      "grad_norm": 0.35107576847076416,
      "learning_rate": 1.417152689387174e-05,
      "loss": 0.5651,
      "step": 23700
    },
    {
      "epoch": 0.7280742174300372,
      "grad_norm": 0.39413052797317505,
      "learning_rate": 1.417108766895732e-05,
      "loss": 0.6055,
      "step": 23701
    },
    {
      "epoch": 0.7281049365649863,
      "grad_norm": 0.4344220757484436,
      "learning_rate": 1.4170648434301033e-05,
      "loss": 0.5153,
      "step": 23702
    },
    {
      "epoch": 0.7281356556999354,
      "grad_norm": 0.3744897246360779,
      "learning_rate": 1.4170209189903906e-05,
      "loss": 0.5292,
      "step": 23703
    },
    {
      "epoch": 0.7281663748348847,
      "grad_norm": 0.5169966220855713,
      "learning_rate": 1.4169769935766963e-05,
      "loss": 0.5295,
      "step": 23704
    },
    {
      "epoch": 0.7281970939698338,
      "grad_norm": 0.3597906529903412,
      "learning_rate": 1.416933067189123e-05,
      "loss": 0.577,
      "step": 23705
    },
    {
      "epoch": 0.728227813104783,
      "grad_norm": 0.376465380191803,
      "learning_rate": 1.4168891398277737e-05,
      "loss": 0.5306,
      "step": 23706
    },
    {
      "epoch": 0.7282585322397321,
      "grad_norm": 0.3684774935245514,
      "learning_rate": 1.416845211492751e-05,
      "loss": 0.5796,
      "step": 23707
    },
    {
      "epoch": 0.7282892513746813,
      "grad_norm": 0.32659581303596497,
      "learning_rate": 1.4168012821841564e-05,
      "loss": 0.4845,
      "step": 23708
    },
    {
      "epoch": 0.7283199705096305,
      "grad_norm": 0.3570389151573181,
      "learning_rate": 1.4167573519020937e-05,
      "loss": 0.5604,
      "step": 23709
    },
    {
      "epoch": 0.7283506896445796,
      "grad_norm": 0.386349081993103,
      "learning_rate": 1.4167134206466649e-05,
      "loss": 0.4984,
      "step": 23710
    },
    {
      "epoch": 0.7283814087795287,
      "grad_norm": 0.3805271089076996,
      "learning_rate": 1.4166694884179731e-05,
      "loss": 0.5491,
      "step": 23711
    },
    {
      "epoch": 0.728412127914478,
      "grad_norm": 0.3947352468967438,
      "learning_rate": 1.4166255552161206e-05,
      "loss": 0.5344,
      "step": 23712
    },
    {
      "epoch": 0.7284428470494271,
      "grad_norm": 0.3343518078327179,
      "learning_rate": 1.4165816210412098e-05,
      "loss": 0.5227,
      "step": 23713
    },
    {
      "epoch": 0.7284735661843762,
      "grad_norm": 0.3659738302230835,
      "learning_rate": 1.4165376858933438e-05,
      "loss": 0.6126,
      "step": 23714
    },
    {
      "epoch": 0.7285042853193254,
      "grad_norm": 0.33404213190078735,
      "learning_rate": 1.4164937497726245e-05,
      "loss": 0.5147,
      "step": 23715
    },
    {
      "epoch": 0.7285350044542745,
      "grad_norm": 0.3803084194660187,
      "learning_rate": 1.4164498126791555e-05,
      "loss": 0.6356,
      "step": 23716
    },
    {
      "epoch": 0.7285657235892238,
      "grad_norm": 0.3894367814064026,
      "learning_rate": 1.4164058746130385e-05,
      "loss": 0.5556,
      "step": 23717
    },
    {
      "epoch": 0.7285964427241729,
      "grad_norm": 0.37393128871917725,
      "learning_rate": 1.4163619355743768e-05,
      "loss": 0.56,
      "step": 23718
    },
    {
      "epoch": 0.728627161859122,
      "grad_norm": 0.3443280756473541,
      "learning_rate": 1.4163179955632721e-05,
      "loss": 0.5109,
      "step": 23719
    },
    {
      "epoch": 0.7286578809940712,
      "grad_norm": 0.3509398102760315,
      "learning_rate": 1.4162740545798284e-05,
      "loss": 0.6025,
      "step": 23720
    },
    {
      "epoch": 0.7286886001290204,
      "grad_norm": 0.38881832361221313,
      "learning_rate": 1.4162301126241471e-05,
      "loss": 0.5501,
      "step": 23721
    },
    {
      "epoch": 0.7287193192639695,
      "grad_norm": 0.37509265542030334,
      "learning_rate": 1.4161861696963318e-05,
      "loss": 0.5371,
      "step": 23722
    },
    {
      "epoch": 0.7287500383989187,
      "grad_norm": 0.5452874898910522,
      "learning_rate": 1.4161422257964843e-05,
      "loss": 0.5234,
      "step": 23723
    },
    {
      "epoch": 0.7287807575338678,
      "grad_norm": 0.4019443988800049,
      "learning_rate": 1.4160982809247075e-05,
      "loss": 0.5706,
      "step": 23724
    },
    {
      "epoch": 0.728811476668817,
      "grad_norm": 0.3421544134616852,
      "learning_rate": 1.4160543350811042e-05,
      "loss": 0.54,
      "step": 23725
    },
    {
      "epoch": 0.7288421958037662,
      "grad_norm": 0.36849454045295715,
      "learning_rate": 1.4160103882657766e-05,
      "loss": 0.5909,
      "step": 23726
    },
    {
      "epoch": 0.7288729149387153,
      "grad_norm": 0.38589173555374146,
      "learning_rate": 1.415966440478828e-05,
      "loss": 0.5259,
      "step": 23727
    },
    {
      "epoch": 0.7289036340736644,
      "grad_norm": 0.41061854362487793,
      "learning_rate": 1.4159224917203607e-05,
      "loss": 0.5833,
      "step": 23728
    },
    {
      "epoch": 0.7289343532086137,
      "grad_norm": 0.36486682295799255,
      "learning_rate": 1.4158785419904774e-05,
      "loss": 0.5775,
      "step": 23729
    },
    {
      "epoch": 0.7289650723435628,
      "grad_norm": 0.39157333970069885,
      "learning_rate": 1.4158345912892808e-05,
      "loss": 0.6332,
      "step": 23730
    },
    {
      "epoch": 0.728995791478512,
      "grad_norm": 0.36302247643470764,
      "learning_rate": 1.4157906396168733e-05,
      "loss": 0.4568,
      "step": 23731
    },
    {
      "epoch": 0.7290265106134611,
      "grad_norm": 0.3445998430252075,
      "learning_rate": 1.4157466869733581e-05,
      "loss": 0.5348,
      "step": 23732
    },
    {
      "epoch": 0.7290572297484103,
      "grad_norm": 0.4787598252296448,
      "learning_rate": 1.4157027333588369e-05,
      "loss": 0.5893,
      "step": 23733
    },
    {
      "epoch": 0.7290879488833595,
      "grad_norm": 0.38292160630226135,
      "learning_rate": 1.4156587787734134e-05,
      "loss": 0.5237,
      "step": 23734
    },
    {
      "epoch": 0.7291186680183086,
      "grad_norm": 0.36222484707832336,
      "learning_rate": 1.4156148232171893e-05,
      "loss": 0.6583,
      "step": 23735
    },
    {
      "epoch": 0.7291493871532577,
      "grad_norm": 0.3638589680194855,
      "learning_rate": 1.4155708666902683e-05,
      "loss": 0.5407,
      "step": 23736
    },
    {
      "epoch": 0.729180106288207,
      "grad_norm": 0.34387287497520447,
      "learning_rate": 1.4155269091927522e-05,
      "loss": 0.5783,
      "step": 23737
    },
    {
      "epoch": 0.7292108254231561,
      "grad_norm": 0.36789408326148987,
      "learning_rate": 1.4154829507247444e-05,
      "loss": 0.6014,
      "step": 23738
    },
    {
      "epoch": 0.7292415445581052,
      "grad_norm": 0.37597379088401794,
      "learning_rate": 1.4154389912863465e-05,
      "loss": 0.5534,
      "step": 23739
    },
    {
      "epoch": 0.7292722636930544,
      "grad_norm": 0.35946986079216003,
      "learning_rate": 1.4153950308776623e-05,
      "loss": 0.632,
      "step": 23740
    },
    {
      "epoch": 0.7293029828280035,
      "grad_norm": 0.44843506813049316,
      "learning_rate": 1.415351069498794e-05,
      "loss": 0.5819,
      "step": 23741
    },
    {
      "epoch": 0.7293337019629528,
      "grad_norm": 0.38117727637290955,
      "learning_rate": 1.4153071071498438e-05,
      "loss": 0.5955,
      "step": 23742
    },
    {
      "epoch": 0.7293644210979019,
      "grad_norm": 0.35568153858184814,
      "learning_rate": 1.4152631438309152e-05,
      "loss": 0.5855,
      "step": 23743
    },
    {
      "epoch": 0.729395140232851,
      "grad_norm": 2.803114891052246,
      "learning_rate": 1.4152191795421104e-05,
      "loss": 0.6971,
      "step": 23744
    },
    {
      "epoch": 0.7294258593678002,
      "grad_norm": 0.3489205539226532,
      "learning_rate": 1.4151752142835324e-05,
      "loss": 0.6009,
      "step": 23745
    },
    {
      "epoch": 0.7294565785027494,
      "grad_norm": 0.39385589957237244,
      "learning_rate": 1.4151312480552834e-05,
      "loss": 0.5883,
      "step": 23746
    },
    {
      "epoch": 0.7294872976376985,
      "grad_norm": 0.35110464692115784,
      "learning_rate": 1.4150872808574667e-05,
      "loss": 0.5261,
      "step": 23747
    },
    {
      "epoch": 0.7295180167726477,
      "grad_norm": 0.4131391942501068,
      "learning_rate": 1.4150433126901845e-05,
      "loss": 0.5845,
      "step": 23748
    },
    {
      "epoch": 0.7295487359075968,
      "grad_norm": 0.35200539231300354,
      "learning_rate": 1.4149993435535396e-05,
      "loss": 0.5523,
      "step": 23749
    },
    {
      "epoch": 0.729579455042546,
      "grad_norm": 0.3685833513736725,
      "learning_rate": 1.4149553734476349e-05,
      "loss": 0.502,
      "step": 23750
    },
    {
      "epoch": 0.7296101741774952,
      "grad_norm": 0.34631842374801636,
      "learning_rate": 1.4149114023725728e-05,
      "loss": 0.581,
      "step": 23751
    },
    {
      "epoch": 0.7296408933124443,
      "grad_norm": 0.35019397735595703,
      "learning_rate": 1.4148674303284564e-05,
      "loss": 0.5088,
      "step": 23752
    },
    {
      "epoch": 0.7296716124473935,
      "grad_norm": 0.36026641726493835,
      "learning_rate": 1.4148234573153879e-05,
      "loss": 0.6171,
      "step": 23753
    },
    {
      "epoch": 0.7297023315823427,
      "grad_norm": 0.4330006539821625,
      "learning_rate": 1.4147794833334702e-05,
      "loss": 0.5155,
      "step": 23754
    },
    {
      "epoch": 0.7297330507172918,
      "grad_norm": 0.3418286144733429,
      "learning_rate": 1.414735508382806e-05,
      "loss": 0.5793,
      "step": 23755
    },
    {
      "epoch": 0.729763769852241,
      "grad_norm": 0.6904200315475464,
      "learning_rate": 1.4146915324634985e-05,
      "loss": 0.562,
      "step": 23756
    },
    {
      "epoch": 0.7297944889871901,
      "grad_norm": 0.36489981412887573,
      "learning_rate": 1.4146475555756497e-05,
      "loss": 0.5959,
      "step": 23757
    },
    {
      "epoch": 0.7298252081221392,
      "grad_norm": 0.4145813584327698,
      "learning_rate": 1.4146035777193624e-05,
      "loss": 0.6023,
      "step": 23758
    },
    {
      "epoch": 0.7298559272570885,
      "grad_norm": 0.3624298870563507,
      "learning_rate": 1.4145595988947399e-05,
      "loss": 0.5944,
      "step": 23759
    },
    {
      "epoch": 0.7298866463920376,
      "grad_norm": 0.5102236270904541,
      "learning_rate": 1.4145156191018841e-05,
      "loss": 0.5354,
      "step": 23760
    },
    {
      "epoch": 0.7299173655269867,
      "grad_norm": 0.388832688331604,
      "learning_rate": 1.4144716383408983e-05,
      "loss": 0.5566,
      "step": 23761
    },
    {
      "epoch": 0.729948084661936,
      "grad_norm": 0.3607177436351776,
      "learning_rate": 1.4144276566118847e-05,
      "loss": 0.561,
      "step": 23762
    },
    {
      "epoch": 0.7299788037968851,
      "grad_norm": 0.37044408917427063,
      "learning_rate": 1.4143836739149468e-05,
      "loss": 0.5612,
      "step": 23763
    },
    {
      "epoch": 0.7300095229318342,
      "grad_norm": 0.3716779053211212,
      "learning_rate": 1.4143396902501869e-05,
      "loss": 0.5654,
      "step": 23764
    },
    {
      "epoch": 0.7300402420667834,
      "grad_norm": 0.3244674503803253,
      "learning_rate": 1.4142957056177074e-05,
      "loss": 0.6282,
      "step": 23765
    },
    {
      "epoch": 0.7300709612017325,
      "grad_norm": 0.34889617562294006,
      "learning_rate": 1.4142517200176115e-05,
      "loss": 0.4345,
      "step": 23766
    },
    {
      "epoch": 0.7301016803366818,
      "grad_norm": 0.3510979115962982,
      "learning_rate": 1.414207733450002e-05,
      "loss": 0.5173,
      "step": 23767
    },
    {
      "epoch": 0.7301323994716309,
      "grad_norm": 0.38287153840065,
      "learning_rate": 1.4141637459149811e-05,
      "loss": 0.5539,
      "step": 23768
    },
    {
      "epoch": 0.73016311860658,
      "grad_norm": 0.406887412071228,
      "learning_rate": 1.4141197574126519e-05,
      "loss": 0.5519,
      "step": 23769
    },
    {
      "epoch": 0.7301938377415292,
      "grad_norm": 0.3683392405509949,
      "learning_rate": 1.4140757679431172e-05,
      "loss": 0.5023,
      "step": 23770
    },
    {
      "epoch": 0.7302245568764784,
      "grad_norm": 0.38493525981903076,
      "learning_rate": 1.4140317775064794e-05,
      "loss": 0.6653,
      "step": 23771
    },
    {
      "epoch": 0.7302552760114275,
      "grad_norm": 0.47716188430786133,
      "learning_rate": 1.4139877861028417e-05,
      "loss": 0.5262,
      "step": 23772
    },
    {
      "epoch": 0.7302859951463767,
      "grad_norm": 0.3358722925186157,
      "learning_rate": 1.4139437937323066e-05,
      "loss": 0.5286,
      "step": 23773
    },
    {
      "epoch": 0.7303167142813258,
      "grad_norm": 0.3670349717140198,
      "learning_rate": 1.4138998003949768e-05,
      "loss": 0.5919,
      "step": 23774
    },
    {
      "epoch": 0.730347433416275,
      "grad_norm": 0.3686022162437439,
      "learning_rate": 1.4138558060909554e-05,
      "loss": 0.5198,
      "step": 23775
    },
    {
      "epoch": 0.7303781525512242,
      "grad_norm": 0.37169981002807617,
      "learning_rate": 1.4138118108203443e-05,
      "loss": 0.633,
      "step": 23776
    },
    {
      "epoch": 0.7304088716861733,
      "grad_norm": 0.35692423582077026,
      "learning_rate": 1.4137678145832472e-05,
      "loss": 0.6198,
      "step": 23777
    },
    {
      "epoch": 0.7304395908211225,
      "grad_norm": 0.38708075881004333,
      "learning_rate": 1.4137238173797662e-05,
      "loss": 0.469,
      "step": 23778
    },
    {
      "epoch": 0.7304703099560717,
      "grad_norm": 0.366332471370697,
      "learning_rate": 1.4136798192100048e-05,
      "loss": 0.5832,
      "step": 23779
    },
    {
      "epoch": 0.7305010290910208,
      "grad_norm": 0.38620463013648987,
      "learning_rate": 1.4136358200740648e-05,
      "loss": 0.5234,
      "step": 23780
    },
    {
      "epoch": 0.73053174822597,
      "grad_norm": 0.39283668994903564,
      "learning_rate": 1.4135918199720495e-05,
      "loss": 0.5622,
      "step": 23781
    },
    {
      "epoch": 0.7305624673609191,
      "grad_norm": 0.41996192932128906,
      "learning_rate": 1.4135478189040619e-05,
      "loss": 0.5483,
      "step": 23782
    },
    {
      "epoch": 0.7305931864958682,
      "grad_norm": 0.48027142882347107,
      "learning_rate": 1.4135038168702043e-05,
      "loss": 0.5421,
      "step": 23783
    },
    {
      "epoch": 0.7306239056308175,
      "grad_norm": 0.30207884311676025,
      "learning_rate": 1.4134598138705797e-05,
      "loss": 0.4644,
      "step": 23784
    },
    {
      "epoch": 0.7306546247657666,
      "grad_norm": 0.355209082365036,
      "learning_rate": 1.4134158099052908e-05,
      "loss": 0.4625,
      "step": 23785
    },
    {
      "epoch": 0.7306853439007157,
      "grad_norm": 0.37796348333358765,
      "learning_rate": 1.4133718049744404e-05,
      "loss": 0.5679,
      "step": 23786
    },
    {
      "epoch": 0.7307160630356649,
      "grad_norm": 0.37691113352775574,
      "learning_rate": 1.4133277990781314e-05,
      "loss": 0.641,
      "step": 23787
    },
    {
      "epoch": 0.7307467821706141,
      "grad_norm": 0.364925354719162,
      "learning_rate": 1.4132837922164664e-05,
      "loss": 0.5836,
      "step": 23788
    },
    {
      "epoch": 0.7307775013055632,
      "grad_norm": 0.35037028789520264,
      "learning_rate": 1.413239784389548e-05,
      "loss": 0.5516,
      "step": 23789
    },
    {
      "epoch": 0.7308082204405124,
      "grad_norm": 0.35052090883255005,
      "learning_rate": 1.4131957755974797e-05,
      "loss": 0.6165,
      "step": 23790
    },
    {
      "epoch": 0.7308389395754615,
      "grad_norm": 0.3854401409626007,
      "learning_rate": 1.4131517658403633e-05,
      "loss": 0.5946,
      "step": 23791
    },
    {
      "epoch": 0.7308696587104108,
      "grad_norm": 0.35541802644729614,
      "learning_rate": 1.4131077551183026e-05,
      "loss": 0.5778,
      "step": 23792
    },
    {
      "epoch": 0.7309003778453599,
      "grad_norm": 0.32179227471351624,
      "learning_rate": 1.4130637434313997e-05,
      "loss": 0.5899,
      "step": 23793
    },
    {
      "epoch": 0.730931096980309,
      "grad_norm": 0.36376190185546875,
      "learning_rate": 1.4130197307797572e-05,
      "loss": 0.5315,
      "step": 23794
    },
    {
      "epoch": 0.7309618161152582,
      "grad_norm": 0.38832175731658936,
      "learning_rate": 1.4129757171634788e-05,
      "loss": 0.6767,
      "step": 23795
    },
    {
      "epoch": 0.7309925352502074,
      "grad_norm": 0.3294855058193207,
      "learning_rate": 1.4129317025826665e-05,
      "loss": 0.4725,
      "step": 23796
    },
    {
      "epoch": 0.7310232543851565,
      "grad_norm": 0.3974390923976898,
      "learning_rate": 1.4128876870374235e-05,
      "loss": 0.5249,
      "step": 23797
    },
    {
      "epoch": 0.7310539735201057,
      "grad_norm": 0.33673760294914246,
      "learning_rate": 1.4128436705278523e-05,
      "loss": 0.5093,
      "step": 23798
    },
    {
      "epoch": 0.7310846926550548,
      "grad_norm": 0.3875851333141327,
      "learning_rate": 1.412799653054056e-05,
      "loss": 0.5226,
      "step": 23799
    },
    {
      "epoch": 0.7311154117900039,
      "grad_norm": 0.3860240876674652,
      "learning_rate": 1.4127556346161372e-05,
      "loss": 0.5315,
      "step": 23800
    },
    {
      "epoch": 0.7311461309249532,
      "grad_norm": 0.3507285714149475,
      "learning_rate": 1.4127116152141987e-05,
      "loss": 0.5334,
      "step": 23801
    },
    {
      "epoch": 0.7311768500599023,
      "grad_norm": 0.32238373160362244,
      "learning_rate": 1.4126675948483437e-05,
      "loss": 0.4495,
      "step": 23802
    },
    {
      "epoch": 0.7312075691948515,
      "grad_norm": 1.1306601762771606,
      "learning_rate": 1.4126235735186744e-05,
      "loss": 0.6395,
      "step": 23803
    },
    {
      "epoch": 0.7312382883298006,
      "grad_norm": 0.37212640047073364,
      "learning_rate": 1.4125795512252942e-05,
      "loss": 0.4793,
      "step": 23804
    },
    {
      "epoch": 0.7312690074647498,
      "grad_norm": 0.35936444997787476,
      "learning_rate": 1.4125355279683053e-05,
      "loss": 0.4765,
      "step": 23805
    },
    {
      "epoch": 0.731299726599699,
      "grad_norm": 0.37972119450569153,
      "learning_rate": 1.4124915037478113e-05,
      "loss": 0.5499,
      "step": 23806
    },
    {
      "epoch": 0.7313304457346481,
      "grad_norm": 0.37695568799972534,
      "learning_rate": 1.4124474785639141e-05,
      "loss": 0.5386,
      "step": 23807
    },
    {
      "epoch": 0.7313611648695972,
      "grad_norm": 0.36910682916641235,
      "learning_rate": 1.4124034524167176e-05,
      "loss": 0.5308,
      "step": 23808
    },
    {
      "epoch": 0.7313918840045465,
      "grad_norm": 0.4456002414226532,
      "learning_rate": 1.4123594253063236e-05,
      "loss": 0.6161,
      "step": 23809
    },
    {
      "epoch": 0.7314226031394956,
      "grad_norm": 0.4325506091117859,
      "learning_rate": 1.4123153972328357e-05,
      "loss": 0.5403,
      "step": 23810
    },
    {
      "epoch": 0.7314533222744447,
      "grad_norm": 0.3282666504383087,
      "learning_rate": 1.412271368196356e-05,
      "loss": 0.5588,
      "step": 23811
    },
    {
      "epoch": 0.7314840414093939,
      "grad_norm": 0.34438541531562805,
      "learning_rate": 1.412227338196988e-05,
      "loss": 0.5014,
      "step": 23812
    },
    {
      "epoch": 0.7315147605443431,
      "grad_norm": 0.42259544134140015,
      "learning_rate": 1.4121833072348341e-05,
      "loss": 0.5308,
      "step": 23813
    },
    {
      "epoch": 0.7315454796792922,
      "grad_norm": 0.3705318868160248,
      "learning_rate": 1.4121392753099975e-05,
      "loss": 0.4601,
      "step": 23814
    },
    {
      "epoch": 0.7315761988142414,
      "grad_norm": 0.4051368534564972,
      "learning_rate": 1.4120952424225807e-05,
      "loss": 0.5993,
      "step": 23815
    },
    {
      "epoch": 0.7316069179491905,
      "grad_norm": 0.3893367648124695,
      "learning_rate": 1.4120512085726866e-05,
      "loss": 0.571,
      "step": 23816
    },
    {
      "epoch": 0.7316376370841398,
      "grad_norm": 0.6370880007743835,
      "learning_rate": 1.412007173760418e-05,
      "loss": 0.5077,
      "step": 23817
    },
    {
      "epoch": 0.7316683562190889,
      "grad_norm": 0.3745144307613373,
      "learning_rate": 1.411963137985878e-05,
      "loss": 0.5648,
      "step": 23818
    },
    {
      "epoch": 0.731699075354038,
      "grad_norm": 0.44569480419158936,
      "learning_rate": 1.4119191012491694e-05,
      "loss": 0.6108,
      "step": 23819
    },
    {
      "epoch": 0.7317297944889872,
      "grad_norm": 0.3420185148715973,
      "learning_rate": 1.411875063550395e-05,
      "loss": 0.579,
      "step": 23820
    },
    {
      "epoch": 0.7317605136239363,
      "grad_norm": 0.3672969341278076,
      "learning_rate": 1.4118310248896577e-05,
      "loss": 0.6462,
      "step": 23821
    },
    {
      "epoch": 0.7317912327588855,
      "grad_norm": 0.3594294786453247,
      "learning_rate": 1.4117869852670603e-05,
      "loss": 0.4922,
      "step": 23822
    },
    {
      "epoch": 0.7318219518938347,
      "grad_norm": 0.3354698717594147,
      "learning_rate": 1.4117429446827053e-05,
      "loss": 0.4826,
      "step": 23823
    },
    {
      "epoch": 0.7318526710287838,
      "grad_norm": 0.38058674335479736,
      "learning_rate": 1.411698903136696e-05,
      "loss": 0.6047,
      "step": 23824
    },
    {
      "epoch": 0.7318833901637329,
      "grad_norm": 0.3777005076408386,
      "learning_rate": 1.4116548606291355e-05,
      "loss": 0.5904,
      "step": 23825
    },
    {
      "epoch": 0.7319141092986822,
      "grad_norm": 0.36339858174324036,
      "learning_rate": 1.4116108171601259e-05,
      "loss": 0.5605,
      "step": 23826
    },
    {
      "epoch": 0.7319448284336313,
      "grad_norm": 0.3897477686405182,
      "learning_rate": 1.4115667727297709e-05,
      "loss": 0.4936,
      "step": 23827
    },
    {
      "epoch": 0.7319755475685805,
      "grad_norm": 0.38832777738571167,
      "learning_rate": 1.4115227273381726e-05,
      "loss": 0.5864,
      "step": 23828
    },
    {
      "epoch": 0.7320062667035296,
      "grad_norm": 1.050102949142456,
      "learning_rate": 1.4114786809854346e-05,
      "loss": 0.5752,
      "step": 23829
    },
    {
      "epoch": 0.7320369858384788,
      "grad_norm": 0.36115455627441406,
      "learning_rate": 1.4114346336716588e-05,
      "loss": 0.5987,
      "step": 23830
    },
    {
      "epoch": 0.732067704973428,
      "grad_norm": 0.4233711361885071,
      "learning_rate": 1.4113905853969492e-05,
      "loss": 0.4848,
      "step": 23831
    },
    {
      "epoch": 0.7320984241083771,
      "grad_norm": 0.530774712562561,
      "learning_rate": 1.411346536161408e-05,
      "loss": 0.5446,
      "step": 23832
    },
    {
      "epoch": 0.7321291432433262,
      "grad_norm": 0.4054495692253113,
      "learning_rate": 1.4113024859651383e-05,
      "loss": 0.5227,
      "step": 23833
    },
    {
      "epoch": 0.7321598623782755,
      "grad_norm": 0.3408663272857666,
      "learning_rate": 1.4112584348082427e-05,
      "loss": 0.4912,
      "step": 23834
    },
    {
      "epoch": 0.7321905815132246,
      "grad_norm": 0.40786978602409363,
      "learning_rate": 1.4112143826908245e-05,
      "loss": 0.5043,
      "step": 23835
    },
    {
      "epoch": 0.7322213006481737,
      "grad_norm": 0.3754103481769562,
      "learning_rate": 1.4111703296129865e-05,
      "loss": 0.6351,
      "step": 23836
    },
    {
      "epoch": 0.7322520197831229,
      "grad_norm": 0.3712635934352875,
      "learning_rate": 1.4111262755748313e-05,
      "loss": 0.5846,
      "step": 23837
    },
    {
      "epoch": 0.732282738918072,
      "grad_norm": 0.38400259613990784,
      "learning_rate": 1.411082220576462e-05,
      "loss": 0.501,
      "step": 23838
    },
    {
      "epoch": 0.7323134580530213,
      "grad_norm": 0.39701202511787415,
      "learning_rate": 1.4110381646179812e-05,
      "loss": 0.5717,
      "step": 23839
    },
    {
      "epoch": 0.7323441771879704,
      "grad_norm": 0.4084271192550659,
      "learning_rate": 1.4109941076994926e-05,
      "loss": 0.5388,
      "step": 23840
    },
    {
      "epoch": 0.7323748963229195,
      "grad_norm": 0.4035400152206421,
      "learning_rate": 1.4109500498210982e-05,
      "loss": 0.5991,
      "step": 23841
    },
    {
      "epoch": 0.7324056154578688,
      "grad_norm": 0.31270331144332886,
      "learning_rate": 1.4109059909829013e-05,
      "loss": 0.4851,
      "step": 23842
    },
    {
      "epoch": 0.7324363345928179,
      "grad_norm": 0.4322281777858734,
      "learning_rate": 1.4108619311850048e-05,
      "loss": 0.5145,
      "step": 23843
    },
    {
      "epoch": 0.732467053727767,
      "grad_norm": 0.3824089765548706,
      "learning_rate": 1.4108178704275117e-05,
      "loss": 0.5024,
      "step": 23844
    },
    {
      "epoch": 0.7324977728627162,
      "grad_norm": 0.34385570883750916,
      "learning_rate": 1.4107738087105247e-05,
      "loss": 0.5376,
      "step": 23845
    },
    {
      "epoch": 0.7325284919976653,
      "grad_norm": 0.36713412404060364,
      "learning_rate": 1.4107297460341465e-05,
      "loss": 0.5681,
      "step": 23846
    },
    {
      "epoch": 0.7325592111326145,
      "grad_norm": 0.35734403133392334,
      "learning_rate": 1.4106856823984806e-05,
      "loss": 0.5191,
      "step": 23847
    },
    {
      "epoch": 0.7325899302675637,
      "grad_norm": 0.35544246435165405,
      "learning_rate": 1.4106416178036295e-05,
      "loss": 0.5044,
      "step": 23848
    },
    {
      "epoch": 0.7326206494025128,
      "grad_norm": 0.3531512916088104,
      "learning_rate": 1.4105975522496964e-05,
      "loss": 0.6401,
      "step": 23849
    },
    {
      "epoch": 0.7326513685374619,
      "grad_norm": 0.4275946617126465,
      "learning_rate": 1.4105534857367837e-05,
      "loss": 0.5802,
      "step": 23850
    },
    {
      "epoch": 0.7326820876724112,
      "grad_norm": 0.3868359327316284,
      "learning_rate": 1.410509418264995e-05,
      "loss": 0.605,
      "step": 23851
    },
    {
      "epoch": 0.7327128068073603,
      "grad_norm": 0.4179460108280182,
      "learning_rate": 1.4104653498344325e-05,
      "loss": 0.487,
      "step": 23852
    },
    {
      "epoch": 0.7327435259423095,
      "grad_norm": 0.398408442735672,
      "learning_rate": 1.4104212804452e-05,
      "loss": 0.5813,
      "step": 23853
    },
    {
      "epoch": 0.7327742450772586,
      "grad_norm": 0.3546433448791504,
      "learning_rate": 1.4103772100973995e-05,
      "loss": 0.5445,
      "step": 23854
    },
    {
      "epoch": 0.7328049642122078,
      "grad_norm": 0.5970355272293091,
      "learning_rate": 1.4103331387911343e-05,
      "loss": 0.4531,
      "step": 23855
    },
    {
      "epoch": 0.732835683347157,
      "grad_norm": 0.3688204288482666,
      "learning_rate": 1.4102890665265079e-05,
      "loss": 0.594,
      "step": 23856
    },
    {
      "epoch": 0.7328664024821061,
      "grad_norm": 0.3299977481365204,
      "learning_rate": 1.4102449933036224e-05,
      "loss": 0.5054,
      "step": 23857
    },
    {
      "epoch": 0.7328971216170552,
      "grad_norm": 0.35637158155441284,
      "learning_rate": 1.4102009191225812e-05,
      "loss": 0.5579,
      "step": 23858
    },
    {
      "epoch": 0.7329278407520045,
      "grad_norm": 1.057495355606079,
      "learning_rate": 1.410156843983487e-05,
      "loss": 0.5133,
      "step": 23859
    },
    {
      "epoch": 0.7329585598869536,
      "grad_norm": 0.33738529682159424,
      "learning_rate": 1.4101127678864429e-05,
      "loss": 0.5926,
      "step": 23860
    },
    {
      "epoch": 0.7329892790219027,
      "grad_norm": 0.3989870250225067,
      "learning_rate": 1.4100686908315517e-05,
      "loss": 0.5976,
      "step": 23861
    },
    {
      "epoch": 0.7330199981568519,
      "grad_norm": 0.46590688824653625,
      "learning_rate": 1.4100246128189165e-05,
      "loss": 0.6201,
      "step": 23862
    },
    {
      "epoch": 0.733050717291801,
      "grad_norm": 0.37158089876174927,
      "learning_rate": 1.4099805338486402e-05,
      "loss": 0.6296,
      "step": 23863
    },
    {
      "epoch": 0.7330814364267503,
      "grad_norm": 0.3727044463157654,
      "learning_rate": 1.4099364539208258e-05,
      "loss": 0.5229,
      "step": 23864
    },
    {
      "epoch": 0.7331121555616994,
      "grad_norm": 1.0757319927215576,
      "learning_rate": 1.4098923730355762e-05,
      "loss": 0.6049,
      "step": 23865
    },
    {
      "epoch": 0.7331428746966485,
      "grad_norm": 0.3643920421600342,
      "learning_rate": 1.409848291192994e-05,
      "loss": 0.6029,
      "step": 23866
    },
    {
      "epoch": 0.7331735938315977,
      "grad_norm": 0.4575008749961853,
      "learning_rate": 1.4098042083931832e-05,
      "loss": 0.6498,
      "step": 23867
    },
    {
      "epoch": 0.7332043129665469,
      "grad_norm": 0.31003108620643616,
      "learning_rate": 1.4097601246362453e-05,
      "loss": 0.6027,
      "step": 23868
    },
    {
      "epoch": 0.733235032101496,
      "grad_norm": 0.38965171575546265,
      "learning_rate": 1.4097160399222842e-05,
      "loss": 0.6407,
      "step": 23869
    },
    {
      "epoch": 0.7332657512364452,
      "grad_norm": 0.3760623335838318,
      "learning_rate": 1.4096719542514029e-05,
      "loss": 0.6064,
      "step": 23870
    },
    {
      "epoch": 0.7332964703713943,
      "grad_norm": 0.39543598890304565,
      "learning_rate": 1.4096278676237042e-05,
      "loss": 0.5293,
      "step": 23871
    },
    {
      "epoch": 0.7333271895063435,
      "grad_norm": 0.35998085141181946,
      "learning_rate": 1.4095837800392907e-05,
      "loss": 0.6313,
      "step": 23872
    },
    {
      "epoch": 0.7333579086412927,
      "grad_norm": 0.41826364398002625,
      "learning_rate": 1.4095396914982655e-05,
      "loss": 0.5654,
      "step": 23873
    },
    {
      "epoch": 0.7333886277762418,
      "grad_norm": 0.3970765173435211,
      "learning_rate": 1.4094956020007322e-05,
      "loss": 0.615,
      "step": 23874
    },
    {
      "epoch": 0.7334193469111909,
      "grad_norm": 0.40530863404273987,
      "learning_rate": 1.4094515115467931e-05,
      "loss": 0.6496,
      "step": 23875
    },
    {
      "epoch": 0.7334500660461402,
      "grad_norm": 0.35092347860336304,
      "learning_rate": 1.4094074201365515e-05,
      "loss": 0.5972,
      "step": 23876
    },
    {
      "epoch": 0.7334807851810893,
      "grad_norm": 0.3528945744037628,
      "learning_rate": 1.4093633277701102e-05,
      "loss": 0.4479,
      "step": 23877
    },
    {
      "epoch": 0.7335115043160385,
      "grad_norm": 0.349943608045578,
      "learning_rate": 1.4093192344475724e-05,
      "loss": 0.484,
      "step": 23878
    },
    {
      "epoch": 0.7335422234509876,
      "grad_norm": 0.38208290934562683,
      "learning_rate": 1.4092751401690409e-05,
      "loss": 0.5285,
      "step": 23879
    },
    {
      "epoch": 0.7335729425859367,
      "grad_norm": 0.3732461929321289,
      "learning_rate": 1.4092310449346186e-05,
      "loss": 0.519,
      "step": 23880
    },
    {
      "epoch": 0.733603661720886,
      "grad_norm": 0.4067455232143402,
      "learning_rate": 1.4091869487444088e-05,
      "loss": 0.5913,
      "step": 23881
    },
    {
      "epoch": 0.7336343808558351,
      "grad_norm": 0.3742539882659912,
      "learning_rate": 1.409142851598514e-05,
      "loss": 0.5907,
      "step": 23882
    },
    {
      "epoch": 0.7336650999907842,
      "grad_norm": 0.3537377715110779,
      "learning_rate": 1.4090987534970377e-05,
      "loss": 0.4751,
      "step": 23883
    },
    {
      "epoch": 0.7336958191257335,
      "grad_norm": 0.37998679280281067,
      "learning_rate": 1.4090546544400827e-05,
      "loss": 0.6438,
      "step": 23884
    },
    {
      "epoch": 0.7337265382606826,
      "grad_norm": 0.4697338044643402,
      "learning_rate": 1.4090105544277522e-05,
      "loss": 0.6412,
      "step": 23885
    },
    {
      "epoch": 0.7337572573956317,
      "grad_norm": 0.3450888693332672,
      "learning_rate": 1.4089664534601483e-05,
      "loss": 0.5243,
      "step": 23886
    },
    {
      "epoch": 0.7337879765305809,
      "grad_norm": 0.34048396348953247,
      "learning_rate": 1.4089223515373753e-05,
      "loss": 0.5299,
      "step": 23887
    },
    {
      "epoch": 0.73381869566553,
      "grad_norm": 0.3681848347187042,
      "learning_rate": 1.4088782486595353e-05,
      "loss": 0.6237,
      "step": 23888
    },
    {
      "epoch": 0.7338494148004793,
      "grad_norm": 0.3530117869377136,
      "learning_rate": 1.408834144826732e-05,
      "loss": 0.5713,
      "step": 23889
    },
    {
      "epoch": 0.7338801339354284,
      "grad_norm": 0.33086907863616943,
      "learning_rate": 1.4087900400390674e-05,
      "loss": 0.5516,
      "step": 23890
    },
    {
      "epoch": 0.7339108530703775,
      "grad_norm": 0.3624996542930603,
      "learning_rate": 1.4087459342966454e-05,
      "loss": 0.5364,
      "step": 23891
    },
    {
      "epoch": 0.7339415722053267,
      "grad_norm": 0.46207231283187866,
      "learning_rate": 1.408701827599569e-05,
      "loss": 0.5629,
      "step": 23892
    },
    {
      "epoch": 0.7339722913402759,
      "grad_norm": 0.34908565878868103,
      "learning_rate": 1.4086577199479405e-05,
      "loss": 0.5607,
      "step": 23893
    },
    {
      "epoch": 0.734003010475225,
      "grad_norm": 0.344638854265213,
      "learning_rate": 1.4086136113418636e-05,
      "loss": 0.5451,
      "step": 23894
    },
    {
      "epoch": 0.7340337296101742,
      "grad_norm": 0.37586358189582825,
      "learning_rate": 1.408569501781441e-05,
      "loss": 0.5665,
      "step": 23895
    },
    {
      "epoch": 0.7340644487451233,
      "grad_norm": 0.3607143759727478,
      "learning_rate": 1.4085253912667759e-05,
      "loss": 0.5365,
      "step": 23896
    },
    {
      "epoch": 0.7340951678800725,
      "grad_norm": 0.34121307730674744,
      "learning_rate": 1.4084812797979713e-05,
      "loss": 0.5422,
      "step": 23897
    },
    {
      "epoch": 0.7341258870150217,
      "grad_norm": 0.37564563751220703,
      "learning_rate": 1.4084371673751298e-05,
      "loss": 0.5317,
      "step": 23898
    },
    {
      "epoch": 0.7341566061499708,
      "grad_norm": 0.36113718152046204,
      "learning_rate": 1.408393053998355e-05,
      "loss": 0.5679,
      "step": 23899
    },
    {
      "epoch": 0.7341873252849199,
      "grad_norm": 0.39385986328125,
      "learning_rate": 1.4083489396677496e-05,
      "loss": 0.5464,
      "step": 23900
    },
    {
      "epoch": 0.7342180444198692,
      "grad_norm": 0.41663163900375366,
      "learning_rate": 1.4083048243834167e-05,
      "loss": 0.5627,
      "step": 23901
    },
    {
      "epoch": 0.7342487635548183,
      "grad_norm": 0.38099610805511475,
      "learning_rate": 1.4082607081454595e-05,
      "loss": 0.5574,
      "step": 23902
    },
    {
      "epoch": 0.7342794826897675,
      "grad_norm": 0.35265451669692993,
      "learning_rate": 1.408216590953981e-05,
      "loss": 0.5171,
      "step": 23903
    },
    {
      "epoch": 0.7343102018247166,
      "grad_norm": 0.4928490221500397,
      "learning_rate": 1.4081724728090838e-05,
      "loss": 0.5027,
      "step": 23904
    },
    {
      "epoch": 0.7343409209596657,
      "grad_norm": 0.3724992573261261,
      "learning_rate": 1.4081283537108713e-05,
      "loss": 0.5024,
      "step": 23905
    },
    {
      "epoch": 0.734371640094615,
      "grad_norm": 0.3969669044017792,
      "learning_rate": 1.4080842336594468e-05,
      "loss": 0.5283,
      "step": 23906
    },
    {
      "epoch": 0.7344023592295641,
      "grad_norm": 0.3377130925655365,
      "learning_rate": 1.4080401126549132e-05,
      "loss": 0.5453,
      "step": 23907
    },
    {
      "epoch": 0.7344330783645132,
      "grad_norm": 0.35825300216674805,
      "learning_rate": 1.407995990697373e-05,
      "loss": 0.5629,
      "step": 23908
    },
    {
      "epoch": 0.7344637974994624,
      "grad_norm": 0.34303900599479675,
      "learning_rate": 1.4079518677869298e-05,
      "loss": 0.5566,
      "step": 23909
    },
    {
      "epoch": 0.7344945166344116,
      "grad_norm": 0.6520171165466309,
      "learning_rate": 1.4079077439236866e-05,
      "loss": 0.6145,
      "step": 23910
    },
    {
      "epoch": 0.7345252357693607,
      "grad_norm": 0.349319726228714,
      "learning_rate": 1.4078636191077464e-05,
      "loss": 0.5857,
      "step": 23911
    },
    {
      "epoch": 0.7345559549043099,
      "grad_norm": 0.36469724774360657,
      "learning_rate": 1.4078194933392122e-05,
      "loss": 0.5454,
      "step": 23912
    },
    {
      "epoch": 0.734586674039259,
      "grad_norm": 0.3676665127277374,
      "learning_rate": 1.4077753666181871e-05,
      "loss": 0.6046,
      "step": 23913
    },
    {
      "epoch": 0.7346173931742083,
      "grad_norm": 0.33843523263931274,
      "learning_rate": 1.4077312389447742e-05,
      "loss": 0.5275,
      "step": 23914
    },
    {
      "epoch": 0.7346481123091574,
      "grad_norm": 0.4022136330604553,
      "learning_rate": 1.4076871103190764e-05,
      "loss": 0.5517,
      "step": 23915
    },
    {
      "epoch": 0.7346788314441065,
      "grad_norm": 0.3610767722129822,
      "learning_rate": 1.4076429807411969e-05,
      "loss": 0.5871,
      "step": 23916
    },
    {
      "epoch": 0.7347095505790557,
      "grad_norm": 0.36382797360420227,
      "learning_rate": 1.407598850211239e-05,
      "loss": 0.534,
      "step": 23917
    },
    {
      "epoch": 0.7347402697140049,
      "grad_norm": 0.343461275100708,
      "learning_rate": 1.407554718729305e-05,
      "loss": 0.5621,
      "step": 23918
    },
    {
      "epoch": 0.734770988848954,
      "grad_norm": 0.34922873973846436,
      "learning_rate": 1.407510586295499e-05,
      "loss": 0.5966,
      "step": 23919
    },
    {
      "epoch": 0.7348017079839032,
      "grad_norm": 0.34182265400886536,
      "learning_rate": 1.4074664529099233e-05,
      "loss": 0.5078,
      "step": 23920
    },
    {
      "epoch": 0.7348324271188523,
      "grad_norm": 0.3548901379108429,
      "learning_rate": 1.4074223185726811e-05,
      "loss": 0.6044,
      "step": 23921
    },
    {
      "epoch": 0.7348631462538014,
      "grad_norm": 0.35314759612083435,
      "learning_rate": 1.4073781832838759e-05,
      "loss": 0.529,
      "step": 23922
    },
    {
      "epoch": 0.7348938653887507,
      "grad_norm": 0.35011303424835205,
      "learning_rate": 1.4073340470436106e-05,
      "loss": 0.5359,
      "step": 23923
    },
    {
      "epoch": 0.7349245845236998,
      "grad_norm": 0.36161237955093384,
      "learning_rate": 1.4072899098519879e-05,
      "loss": 0.5631,
      "step": 23924
    },
    {
      "epoch": 0.7349553036586489,
      "grad_norm": 0.3432294428348541,
      "learning_rate": 1.4072457717091112e-05,
      "loss": 0.5836,
      "step": 23925
    },
    {
      "epoch": 0.7349860227935981,
      "grad_norm": 0.38183504343032837,
      "learning_rate": 1.407201632615084e-05,
      "loss": 0.5457,
      "step": 23926
    },
    {
      "epoch": 0.7350167419285473,
      "grad_norm": 0.4374266564846039,
      "learning_rate": 1.4071574925700082e-05,
      "loss": 0.6513,
      "step": 23927
    },
    {
      "epoch": 0.7350474610634965,
      "grad_norm": 0.4254762828350067,
      "learning_rate": 1.4071133515739881e-05,
      "loss": 0.4994,
      "step": 23928
    },
    {
      "epoch": 0.7350781801984456,
      "grad_norm": 0.365461528301239,
      "learning_rate": 1.4070692096271261e-05,
      "loss": 0.6058,
      "step": 23929
    },
    {
      "epoch": 0.7351088993333947,
      "grad_norm": 0.3637332618236542,
      "learning_rate": 1.4070250667295258e-05,
      "loss": 0.4784,
      "step": 23930
    },
    {
      "epoch": 0.735139618468344,
      "grad_norm": 0.426251083612442,
      "learning_rate": 1.4069809228812901e-05,
      "loss": 0.5811,
      "step": 23931
    },
    {
      "epoch": 0.7351703376032931,
      "grad_norm": 0.3704899847507477,
      "learning_rate": 1.4069367780825216e-05,
      "loss": 0.4917,
      "step": 23932
    },
    {
      "epoch": 0.7352010567382422,
      "grad_norm": 0.3922511041164398,
      "learning_rate": 1.4068926323333243e-05,
      "loss": 0.514,
      "step": 23933
    },
    {
      "epoch": 0.7352317758731914,
      "grad_norm": 0.32643023133277893,
      "learning_rate": 1.4068484856338004e-05,
      "loss": 0.4517,
      "step": 23934
    },
    {
      "epoch": 0.7352624950081406,
      "grad_norm": 0.33544814586639404,
      "learning_rate": 1.4068043379840538e-05,
      "loss": 0.5871,
      "step": 23935
    },
    {
      "epoch": 0.7352932141430897,
      "grad_norm": 0.3680316209793091,
      "learning_rate": 1.4067601893841872e-05,
      "loss": 0.4923,
      "step": 23936
    },
    {
      "epoch": 0.7353239332780389,
      "grad_norm": 0.3586023449897766,
      "learning_rate": 1.4067160398343038e-05,
      "loss": 0.4944,
      "step": 23937
    },
    {
      "epoch": 0.735354652412988,
      "grad_norm": 0.366202175617218,
      "learning_rate": 1.4066718893345064e-05,
      "loss": 0.5954,
      "step": 23938
    },
    {
      "epoch": 0.7353853715479373,
      "grad_norm": 0.36065879464149475,
      "learning_rate": 1.4066277378848987e-05,
      "loss": 0.5607,
      "step": 23939
    },
    {
      "epoch": 0.7354160906828864,
      "grad_norm": 0.3939714729785919,
      "learning_rate": 1.4065835854855831e-05,
      "loss": 0.5717,
      "step": 23940
    },
    {
      "epoch": 0.7354468098178355,
      "grad_norm": 0.3498212397098541,
      "learning_rate": 1.4065394321366637e-05,
      "loss": 0.6001,
      "step": 23941
    },
    {
      "epoch": 0.7354775289527847,
      "grad_norm": 0.3661903142929077,
      "learning_rate": 1.4064952778382428e-05,
      "loss": 0.5333,
      "step": 23942
    },
    {
      "epoch": 0.7355082480877339,
      "grad_norm": 0.3715902268886566,
      "learning_rate": 1.4064511225904238e-05,
      "loss": 0.6142,
      "step": 23943
    },
    {
      "epoch": 0.735538967222683,
      "grad_norm": 0.3283309042453766,
      "learning_rate": 1.40640696639331e-05,
      "loss": 0.5596,
      "step": 23944
    },
    {
      "epoch": 0.7355696863576322,
      "grad_norm": 0.3458085358142853,
      "learning_rate": 1.4063628092470038e-05,
      "loss": 0.5763,
      "step": 23945
    },
    {
      "epoch": 0.7356004054925813,
      "grad_norm": 0.401968777179718,
      "learning_rate": 1.4063186511516093e-05,
      "loss": 0.5635,
      "step": 23946
    },
    {
      "epoch": 0.7356311246275304,
      "grad_norm": 0.3870897591114044,
      "learning_rate": 1.406274492107229e-05,
      "loss": 0.5997,
      "step": 23947
    },
    {
      "epoch": 0.7356618437624797,
      "grad_norm": 0.34694695472717285,
      "learning_rate": 1.4062303321139666e-05,
      "loss": 0.5776,
      "step": 23948
    },
    {
      "epoch": 0.7356925628974288,
      "grad_norm": 0.3902072310447693,
      "learning_rate": 1.4061861711719248e-05,
      "loss": 0.557,
      "step": 23949
    },
    {
      "epoch": 0.735723282032378,
      "grad_norm": 0.45290282368659973,
      "learning_rate": 1.4061420092812065e-05,
      "loss": 0.586,
      "step": 23950
    },
    {
      "epoch": 0.7357540011673271,
      "grad_norm": 0.349902868270874,
      "learning_rate": 1.4060978464419157e-05,
      "loss": 0.4904,
      "step": 23951
    },
    {
      "epoch": 0.7357847203022763,
      "grad_norm": 0.4062516689300537,
      "learning_rate": 1.4060536826541547e-05,
      "loss": 0.5088,
      "step": 23952
    },
    {
      "epoch": 0.7358154394372255,
      "grad_norm": 0.374416321516037,
      "learning_rate": 1.4060095179180268e-05,
      "loss": 0.5091,
      "step": 23953
    },
    {
      "epoch": 0.7358461585721746,
      "grad_norm": 0.36285632848739624,
      "learning_rate": 1.4059653522336353e-05,
      "loss": 0.537,
      "step": 23954
    },
    {
      "epoch": 0.7358768777071237,
      "grad_norm": 0.3294793963432312,
      "learning_rate": 1.4059211856010838e-05,
      "loss": 0.528,
      "step": 23955
    },
    {
      "epoch": 0.735907596842073,
      "grad_norm": 0.36854037642478943,
      "learning_rate": 1.4058770180204748e-05,
      "loss": 0.5984,
      "step": 23956
    },
    {
      "epoch": 0.7359383159770221,
      "grad_norm": 0.3725568652153015,
      "learning_rate": 1.4058328494919117e-05,
      "loss": 0.6137,
      "step": 23957
    },
    {
      "epoch": 0.7359690351119712,
      "grad_norm": 0.3573515713214874,
      "learning_rate": 1.4057886800154976e-05,
      "loss": 0.5776,
      "step": 23958
    },
    {
      "epoch": 0.7359997542469204,
      "grad_norm": 0.371776282787323,
      "learning_rate": 1.4057445095913357e-05,
      "loss": 0.5518,
      "step": 23959
    },
    {
      "epoch": 0.7360304733818696,
      "grad_norm": 0.34047186374664307,
      "learning_rate": 1.4057003382195294e-05,
      "loss": 0.6296,
      "step": 23960
    },
    {
      "epoch": 0.7360611925168187,
      "grad_norm": 0.37181127071380615,
      "learning_rate": 1.4056561659001813e-05,
      "loss": 0.5008,
      "step": 23961
    },
    {
      "epoch": 0.7360919116517679,
      "grad_norm": 0.3385287821292877,
      "learning_rate": 1.4056119926333952e-05,
      "loss": 0.5483,
      "step": 23962
    },
    {
      "epoch": 0.736122630786717,
      "grad_norm": 0.3728054463863373,
      "learning_rate": 1.4055678184192732e-05,
      "loss": 0.5809,
      "step": 23963
    },
    {
      "epoch": 0.7361533499216663,
      "grad_norm": 0.3628765046596527,
      "learning_rate": 1.40552364325792e-05,
      "loss": 0.5829,
      "step": 23964
    },
    {
      "epoch": 0.7361840690566154,
      "grad_norm": 0.38654211163520813,
      "learning_rate": 1.4054794671494376e-05,
      "loss": 0.5268,
      "step": 23965
    },
    {
      "epoch": 0.7362147881915645,
      "grad_norm": 0.41645652055740356,
      "learning_rate": 1.4054352900939299e-05,
      "loss": 0.5419,
      "step": 23966
    },
    {
      "epoch": 0.7362455073265137,
      "grad_norm": 0.35983800888061523,
      "learning_rate": 1.4053911120914996e-05,
      "loss": 0.5183,
      "step": 23967
    },
    {
      "epoch": 0.7362762264614628,
      "grad_norm": 0.39624685049057007,
      "learning_rate": 1.40534693314225e-05,
      "loss": 0.6474,
      "step": 23968
    },
    {
      "epoch": 0.736306945596412,
      "grad_norm": 0.3621513545513153,
      "learning_rate": 1.4053027532462847e-05,
      "loss": 0.55,
      "step": 23969
    },
    {
      "epoch": 0.7363376647313612,
      "grad_norm": 0.34866905212402344,
      "learning_rate": 1.405258572403706e-05,
      "loss": 0.5725,
      "step": 23970
    },
    {
      "epoch": 0.7363683838663103,
      "grad_norm": 0.35034066438674927,
      "learning_rate": 1.405214390614618e-05,
      "loss": 0.5722,
      "step": 23971
    },
    {
      "epoch": 0.7363991030012594,
      "grad_norm": 0.4435269832611084,
      "learning_rate": 1.4051702078791232e-05,
      "loss": 0.5311,
      "step": 23972
    },
    {
      "epoch": 0.7364298221362087,
      "grad_norm": 1.0760148763656616,
      "learning_rate": 1.4051260241973253e-05,
      "loss": 0.6257,
      "step": 23973
    },
    {
      "epoch": 0.7364605412711578,
      "grad_norm": 0.37539005279541016,
      "learning_rate": 1.4050818395693271e-05,
      "loss": 0.5828,
      "step": 23974
    },
    {
      "epoch": 0.736491260406107,
      "grad_norm": 0.3581584095954895,
      "learning_rate": 1.4050376539952322e-05,
      "loss": 0.5046,
      "step": 23975
    },
    {
      "epoch": 0.7365219795410561,
      "grad_norm": 0.37505874037742615,
      "learning_rate": 1.4049934674751434e-05,
      "loss": 0.6339,
      "step": 23976
    },
    {
      "epoch": 0.7365526986760053,
      "grad_norm": 0.34565988183021545,
      "learning_rate": 1.404949280009164e-05,
      "loss": 0.5184,
      "step": 23977
    },
    {
      "epoch": 0.7365834178109545,
      "grad_norm": 0.3221534788608551,
      "learning_rate": 1.4049050915973974e-05,
      "loss": 0.4942,
      "step": 23978
    },
    {
      "epoch": 0.7366141369459036,
      "grad_norm": 0.38721615076065063,
      "learning_rate": 1.4048609022399467e-05,
      "loss": 0.6111,
      "step": 23979
    },
    {
      "epoch": 0.7366448560808527,
      "grad_norm": 0.3706909120082855,
      "learning_rate": 1.4048167119369152e-05,
      "loss": 0.5197,
      "step": 23980
    },
    {
      "epoch": 0.736675575215802,
      "grad_norm": 0.3615691363811493,
      "learning_rate": 1.4047725206884053e-05,
      "loss": 0.6521,
      "step": 23981
    },
    {
      "epoch": 0.7367062943507511,
      "grad_norm": 0.37460437417030334,
      "learning_rate": 1.4047283284945216e-05,
      "loss": 0.5817,
      "step": 23982
    },
    {
      "epoch": 0.7367370134857002,
      "grad_norm": 0.3444964289665222,
      "learning_rate": 1.4046841353553664e-05,
      "loss": 0.5133,
      "step": 23983
    },
    {
      "epoch": 0.7367677326206494,
      "grad_norm": 0.35620808601379395,
      "learning_rate": 1.4046399412710434e-05,
      "loss": 0.5859,
      "step": 23984
    },
    {
      "epoch": 0.7367984517555985,
      "grad_norm": 0.3288174867630005,
      "learning_rate": 1.4045957462416553e-05,
      "loss": 0.4673,
      "step": 23985
    },
    {
      "epoch": 0.7368291708905477,
      "grad_norm": 0.38143235445022583,
      "learning_rate": 1.4045515502673057e-05,
      "loss": 0.5743,
      "step": 23986
    },
    {
      "epoch": 0.7368598900254969,
      "grad_norm": 0.3475135266780853,
      "learning_rate": 1.4045073533480978e-05,
      "loss": 0.489,
      "step": 23987
    },
    {
      "epoch": 0.736890609160446,
      "grad_norm": 0.3271581530570984,
      "learning_rate": 1.4044631554841344e-05,
      "loss": 0.5285,
      "step": 23988
    },
    {
      "epoch": 0.7369213282953953,
      "grad_norm": 0.47731634974479675,
      "learning_rate": 1.4044189566755193e-05,
      "loss": 0.5748,
      "step": 23989
    },
    {
      "epoch": 0.7369520474303444,
      "grad_norm": 0.35412389039993286,
      "learning_rate": 1.4043747569223553e-05,
      "loss": 0.5991,
      "step": 23990
    },
    {
      "epoch": 0.7369827665652935,
      "grad_norm": 0.3622449040412903,
      "learning_rate": 1.404330556224746e-05,
      "loss": 0.5917,
      "step": 23991
    },
    {
      "epoch": 0.7370134857002427,
      "grad_norm": 0.34551748633384705,
      "learning_rate": 1.4042863545827943e-05,
      "loss": 0.5689,
      "step": 23992
    },
    {
      "epoch": 0.7370442048351918,
      "grad_norm": 0.3848418593406677,
      "learning_rate": 1.4042421519966039e-05,
      "loss": 0.5802,
      "step": 23993
    },
    {
      "epoch": 0.737074923970141,
      "grad_norm": 0.36744365096092224,
      "learning_rate": 1.404197948466277e-05,
      "loss": 0.5424,
      "step": 23994
    },
    {
      "epoch": 0.7371056431050902,
      "grad_norm": 0.36542680859565735,
      "learning_rate": 1.4041537439919184e-05,
      "loss": 0.6048,
      "step": 23995
    },
    {
      "epoch": 0.7371363622400393,
      "grad_norm": 0.38360899686813354,
      "learning_rate": 1.40410953857363e-05,
      "loss": 0.5903,
      "step": 23996
    },
    {
      "epoch": 0.7371670813749884,
      "grad_norm": 0.4056641459465027,
      "learning_rate": 1.4040653322115158e-05,
      "loss": 0.591,
      "step": 23997
    },
    {
      "epoch": 0.7371978005099377,
      "grad_norm": 0.3301253914833069,
      "learning_rate": 1.4040211249056787e-05,
      "loss": 0.5179,
      "step": 23998
    },
    {
      "epoch": 0.7372285196448868,
      "grad_norm": 0.32430121302604675,
      "learning_rate": 1.403976916656222e-05,
      "loss": 0.4936,
      "step": 23999
    },
    {
      "epoch": 0.737259238779836,
      "grad_norm": 0.35328444838523865,
      "learning_rate": 1.403932707463249e-05,
      "loss": 0.5415,
      "step": 24000
    },
    {
      "epoch": 0.7372899579147851,
      "grad_norm": 0.35685500502586365,
      "learning_rate": 1.4038884973268629e-05,
      "loss": 0.5547,
      "step": 24001
    },
    {
      "epoch": 0.7373206770497343,
      "grad_norm": 0.3723700940608978,
      "learning_rate": 1.403844286247167e-05,
      "loss": 0.6508,
      "step": 24002
    },
    {
      "epoch": 0.7373513961846835,
      "grad_norm": 0.37581154704093933,
      "learning_rate": 1.4038000742242647e-05,
      "loss": 0.5528,
      "step": 24003
    },
    {
      "epoch": 0.7373821153196326,
      "grad_norm": 0.45270076394081116,
      "learning_rate": 1.4037558612582592e-05,
      "loss": 0.4869,
      "step": 24004
    },
    {
      "epoch": 0.7374128344545817,
      "grad_norm": 0.34453266859054565,
      "learning_rate": 1.4037116473492536e-05,
      "loss": 0.6106,
      "step": 24005
    },
    {
      "epoch": 0.737443553589531,
      "grad_norm": 0.37359076738357544,
      "learning_rate": 1.4036674324973512e-05,
      "loss": 0.5018,
      "step": 24006
    },
    {
      "epoch": 0.7374742727244801,
      "grad_norm": 0.3359360992908478,
      "learning_rate": 1.4036232167026553e-05,
      "loss": 0.5359,
      "step": 24007
    },
    {
      "epoch": 0.7375049918594292,
      "grad_norm": 0.34190985560417175,
      "learning_rate": 1.403578999965269e-05,
      "loss": 0.5881,
      "step": 24008
    },
    {
      "epoch": 0.7375357109943784,
      "grad_norm": 0.362771213054657,
      "learning_rate": 1.4035347822852963e-05,
      "loss": 0.4929,
      "step": 24009
    },
    {
      "epoch": 0.7375664301293275,
      "grad_norm": 0.360774964094162,
      "learning_rate": 1.4034905636628395e-05,
      "loss": 0.5571,
      "step": 24010
    },
    {
      "epoch": 0.7375971492642767,
      "grad_norm": 0.3520717918872833,
      "learning_rate": 1.4034463440980024e-05,
      "loss": 0.4846,
      "step": 24011
    },
    {
      "epoch": 0.7376278683992259,
      "grad_norm": 0.4446204900741577,
      "learning_rate": 1.4034021235908885e-05,
      "loss": 0.5188,
      "step": 24012
    },
    {
      "epoch": 0.737658587534175,
      "grad_norm": 0.4092522859573364,
      "learning_rate": 1.4033579021416003e-05,
      "loss": 0.5168,
      "step": 24013
    },
    {
      "epoch": 0.7376893066691242,
      "grad_norm": 0.3499012589454651,
      "learning_rate": 1.4033136797502418e-05,
      "loss": 0.5616,
      "step": 24014
    },
    {
      "epoch": 0.7377200258040734,
      "grad_norm": 0.4429846405982971,
      "learning_rate": 1.4032694564169158e-05,
      "loss": 0.5637,
      "step": 24015
    },
    {
      "epoch": 0.7377507449390225,
      "grad_norm": 0.39011919498443604,
      "learning_rate": 1.4032252321417263e-05,
      "loss": 0.5589,
      "step": 24016
    },
    {
      "epoch": 0.7377814640739717,
      "grad_norm": 0.4570232033729553,
      "learning_rate": 1.4031810069247755e-05,
      "loss": 0.5826,
      "step": 24017
    },
    {
      "epoch": 0.7378121832089208,
      "grad_norm": 0.3443679213523865,
      "learning_rate": 1.4031367807661676e-05,
      "loss": 0.5308,
      "step": 24018
    },
    {
      "epoch": 0.73784290234387,
      "grad_norm": 0.3689989447593689,
      "learning_rate": 1.4030925536660056e-05,
      "loss": 0.5158,
      "step": 24019
    },
    {
      "epoch": 0.7378736214788192,
      "grad_norm": 0.4074837863445282,
      "learning_rate": 1.4030483256243927e-05,
      "loss": 0.599,
      "step": 24020
    },
    {
      "epoch": 0.7379043406137683,
      "grad_norm": 0.4306962788105011,
      "learning_rate": 1.4030040966414324e-05,
      "loss": 0.5188,
      "step": 24021
    },
    {
      "epoch": 0.7379350597487174,
      "grad_norm": 0.34936586022377014,
      "learning_rate": 1.4029598667172279e-05,
      "loss": 0.4699,
      "step": 24022
    },
    {
      "epoch": 0.7379657788836667,
      "grad_norm": 0.3359787166118622,
      "learning_rate": 1.4029156358518825e-05,
      "loss": 0.4988,
      "step": 24023
    },
    {
      "epoch": 0.7379964980186158,
      "grad_norm": 1.208280086517334,
      "learning_rate": 1.4028714040454993e-05,
      "loss": 0.5794,
      "step": 24024
    },
    {
      "epoch": 0.738027217153565,
      "grad_norm": 0.3483094573020935,
      "learning_rate": 1.4028271712981823e-05,
      "loss": 0.4516,
      "step": 24025
    },
    {
      "epoch": 0.7380579362885141,
      "grad_norm": 0.3598763942718506,
      "learning_rate": 1.4027829376100337e-05,
      "loss": 0.6699,
      "step": 24026
    },
    {
      "epoch": 0.7380886554234632,
      "grad_norm": 0.3392447531223297,
      "learning_rate": 1.4027387029811577e-05,
      "loss": 0.5702,
      "step": 24027
    },
    {
      "epoch": 0.7381193745584125,
      "grad_norm": 0.3769208788871765,
      "learning_rate": 1.4026944674116572e-05,
      "loss": 0.598,
      "step": 24028
    },
    {
      "epoch": 0.7381500936933616,
      "grad_norm": 0.45454928278923035,
      "learning_rate": 1.4026502309016358e-05,
      "loss": 0.5883,
      "step": 24029
    },
    {
      "epoch": 0.7381808128283107,
      "grad_norm": 0.3662364184856415,
      "learning_rate": 1.4026059934511968e-05,
      "loss": 0.5438,
      "step": 24030
    },
    {
      "epoch": 0.73821153196326,
      "grad_norm": 0.42357373237609863,
      "learning_rate": 1.4025617550604431e-05,
      "loss": 0.5645,
      "step": 24031
    },
    {
      "epoch": 0.7382422510982091,
      "grad_norm": 0.3918980360031128,
      "learning_rate": 1.4025175157294783e-05,
      "loss": 0.5833,
      "step": 24032
    },
    {
      "epoch": 0.7382729702331582,
      "grad_norm": 0.36832988262176514,
      "learning_rate": 1.402473275458406e-05,
      "loss": 0.5309,
      "step": 24033
    },
    {
      "epoch": 0.7383036893681074,
      "grad_norm": 0.41875535249710083,
      "learning_rate": 1.4024290342473293e-05,
      "loss": 0.5509,
      "step": 24034
    },
    {
      "epoch": 0.7383344085030565,
      "grad_norm": 0.35417771339416504,
      "learning_rate": 1.4023847920963509e-05,
      "loss": 0.5626,
      "step": 24035
    },
    {
      "epoch": 0.7383651276380057,
      "grad_norm": 0.3810676336288452,
      "learning_rate": 1.402340549005575e-05,
      "loss": 0.6445,
      "step": 24036
    },
    {
      "epoch": 0.7383958467729549,
      "grad_norm": 0.3971172869205475,
      "learning_rate": 1.4022963049751051e-05,
      "loss": 0.6079,
      "step": 24037
    },
    {
      "epoch": 0.738426565907904,
      "grad_norm": 0.35918736457824707,
      "learning_rate": 1.4022520600050435e-05,
      "loss": 0.5339,
      "step": 24038
    },
    {
      "epoch": 0.7384572850428532,
      "grad_norm": 0.3702136278152466,
      "learning_rate": 1.4022078140954945e-05,
      "loss": 0.6225,
      "step": 24039
    },
    {
      "epoch": 0.7384880041778024,
      "grad_norm": 0.3666830062866211,
      "learning_rate": 1.4021635672465608e-05,
      "loss": 0.5318,
      "step": 24040
    },
    {
      "epoch": 0.7385187233127515,
      "grad_norm": 0.4105644226074219,
      "learning_rate": 1.402119319458346e-05,
      "loss": 0.5735,
      "step": 24041
    },
    {
      "epoch": 0.7385494424477007,
      "grad_norm": 0.3340572714805603,
      "learning_rate": 1.4020750707309536e-05,
      "loss": 0.5327,
      "step": 24042
    },
    {
      "epoch": 0.7385801615826498,
      "grad_norm": 0.3777811527252197,
      "learning_rate": 1.4020308210644868e-05,
      "loss": 0.6017,
      "step": 24043
    },
    {
      "epoch": 0.738610880717599,
      "grad_norm": 0.43184736371040344,
      "learning_rate": 1.4019865704590488e-05,
      "loss": 0.5725,
      "step": 24044
    },
    {
      "epoch": 0.7386415998525482,
      "grad_norm": 0.4380151033401489,
      "learning_rate": 1.4019423189147432e-05,
      "loss": 0.5524,
      "step": 24045
    },
    {
      "epoch": 0.7386723189874973,
      "grad_norm": 0.3569099009037018,
      "learning_rate": 1.4018980664316732e-05,
      "loss": 0.529,
      "step": 24046
    },
    {
      "epoch": 0.7387030381224464,
      "grad_norm": 0.36972251534461975,
      "learning_rate": 1.4018538130099421e-05,
      "loss": 0.6117,
      "step": 24047
    },
    {
      "epoch": 0.7387337572573957,
      "grad_norm": 0.349970281124115,
      "learning_rate": 1.4018095586496538e-05,
      "loss": 0.5758,
      "step": 24048
    },
    {
      "epoch": 0.7387644763923448,
      "grad_norm": 0.37260302901268005,
      "learning_rate": 1.4017653033509107e-05,
      "loss": 0.5355,
      "step": 24049
    },
    {
      "epoch": 0.738795195527294,
      "grad_norm": 0.37481576204299927,
      "learning_rate": 1.401721047113817e-05,
      "loss": 0.5195,
      "step": 24050
    },
    {
      "epoch": 0.7388259146622431,
      "grad_norm": 0.33485570549964905,
      "learning_rate": 1.4016767899384753e-05,
      "loss": 0.4633,
      "step": 24051
    },
    {
      "epoch": 0.7388566337971922,
      "grad_norm": 0.368348628282547,
      "learning_rate": 1.4016325318249899e-05,
      "loss": 0.4829,
      "step": 24052
    },
    {
      "epoch": 0.7388873529321415,
      "grad_norm": 0.3314364552497864,
      "learning_rate": 1.4015882727734633e-05,
      "loss": 0.5465,
      "step": 24053
    },
    {
      "epoch": 0.7389180720670906,
      "grad_norm": 0.33065229654312134,
      "learning_rate": 1.4015440127839995e-05,
      "loss": 0.5199,
      "step": 24054
    },
    {
      "epoch": 0.7389487912020397,
      "grad_norm": 0.3633914589881897,
      "learning_rate": 1.4014997518567015e-05,
      "loss": 0.651,
      "step": 24055
    },
    {
      "epoch": 0.7389795103369889,
      "grad_norm": 0.37289178371429443,
      "learning_rate": 1.4014554899916728e-05,
      "loss": 0.5667,
      "step": 24056
    },
    {
      "epoch": 0.7390102294719381,
      "grad_norm": 0.36510995030403137,
      "learning_rate": 1.401411227189017e-05,
      "loss": 0.5635,
      "step": 24057
    },
    {
      "epoch": 0.7390409486068872,
      "grad_norm": 0.4184882640838623,
      "learning_rate": 1.4013669634488367e-05,
      "loss": 0.5594,
      "step": 24058
    },
    {
      "epoch": 0.7390716677418364,
      "grad_norm": 0.3926422595977783,
      "learning_rate": 1.4013226987712363e-05,
      "loss": 0.5119,
      "step": 24059
    },
    {
      "epoch": 0.7391023868767855,
      "grad_norm": 0.3785075545310974,
      "learning_rate": 1.4012784331563185e-05,
      "loss": 0.5328,
      "step": 24060
    },
    {
      "epoch": 0.7391331060117348,
      "grad_norm": 0.3395192325115204,
      "learning_rate": 1.4012341666041871e-05,
      "loss": 0.5307,
      "step": 24061
    },
    {
      "epoch": 0.7391638251466839,
      "grad_norm": 0.44648870825767517,
      "learning_rate": 1.401189899114945e-05,
      "loss": 0.6016,
      "step": 24062
    },
    {
      "epoch": 0.739194544281633,
      "grad_norm": 0.37489473819732666,
      "learning_rate": 1.4011456306886961e-05,
      "loss": 0.6054,
      "step": 24063
    },
    {
      "epoch": 0.7392252634165822,
      "grad_norm": 0.33771848678588867,
      "learning_rate": 1.4011013613255436e-05,
      "loss": 0.5683,
      "step": 24064
    },
    {
      "epoch": 0.7392559825515314,
      "grad_norm": 0.3283257484436035,
      "learning_rate": 1.4010570910255905e-05,
      "loss": 0.542,
      "step": 24065
    },
    {
      "epoch": 0.7392867016864805,
      "grad_norm": 0.334966242313385,
      "learning_rate": 1.401012819788941e-05,
      "loss": 0.6069,
      "step": 24066
    },
    {
      "epoch": 0.7393174208214297,
      "grad_norm": 0.35373446345329285,
      "learning_rate": 1.4009685476156977e-05,
      "loss": 0.5764,
      "step": 24067
    },
    {
      "epoch": 0.7393481399563788,
      "grad_norm": 0.5883303284645081,
      "learning_rate": 1.4009242745059646e-05,
      "loss": 0.6232,
      "step": 24068
    },
    {
      "epoch": 0.739378859091328,
      "grad_norm": 0.349556565284729,
      "learning_rate": 1.4008800004598446e-05,
      "loss": 0.5882,
      "step": 24069
    },
    {
      "epoch": 0.7394095782262772,
      "grad_norm": 0.33294105529785156,
      "learning_rate": 1.4008357254774416e-05,
      "loss": 0.4963,
      "step": 24070
    },
    {
      "epoch": 0.7394402973612263,
      "grad_norm": 0.3759443461894989,
      "learning_rate": 1.4007914495588586e-05,
      "loss": 0.5511,
      "step": 24071
    },
    {
      "epoch": 0.7394710164961754,
      "grad_norm": 0.36933282017707825,
      "learning_rate": 1.4007471727041994e-05,
      "loss": 0.5878,
      "step": 24072
    },
    {
      "epoch": 0.7395017356311246,
      "grad_norm": 0.48361724615097046,
      "learning_rate": 1.400702894913567e-05,
      "loss": 0.6043,
      "step": 24073
    },
    {
      "epoch": 0.7395324547660738,
      "grad_norm": 0.38287582993507385,
      "learning_rate": 1.400658616187065e-05,
      "loss": 0.6802,
      "step": 24074
    },
    {
      "epoch": 0.739563173901023,
      "grad_norm": 0.3953946530818939,
      "learning_rate": 1.400614336524797e-05,
      "loss": 0.5728,
      "step": 24075
    },
    {
      "epoch": 0.7395938930359721,
      "grad_norm": 0.3434072434902191,
      "learning_rate": 1.400570055926866e-05,
      "loss": 0.4521,
      "step": 24076
    },
    {
      "epoch": 0.7396246121709212,
      "grad_norm": 0.3852611482143402,
      "learning_rate": 1.4005257743933757e-05,
      "loss": 0.5015,
      "step": 24077
    },
    {
      "epoch": 0.7396553313058705,
      "grad_norm": 0.33754751086235046,
      "learning_rate": 1.4004814919244297e-05,
      "loss": 0.5,
      "step": 24078
    },
    {
      "epoch": 0.7396860504408196,
      "grad_norm": 0.384284108877182,
      "learning_rate": 1.400437208520131e-05,
      "loss": 0.5611,
      "step": 24079
    },
    {
      "epoch": 0.7397167695757687,
      "grad_norm": 0.34580808877944946,
      "learning_rate": 1.4003929241805834e-05,
      "loss": 0.5991,
      "step": 24080
    },
    {
      "epoch": 0.7397474887107179,
      "grad_norm": 0.3477906286716461,
      "learning_rate": 1.40034863890589e-05,
      "loss": 0.4796,
      "step": 24081
    },
    {
      "epoch": 0.7397782078456671,
      "grad_norm": 0.38307985663414,
      "learning_rate": 1.4003043526961547e-05,
      "loss": 0.4827,
      "step": 24082
    },
    {
      "epoch": 0.7398089269806162,
      "grad_norm": 0.3861304819583893,
      "learning_rate": 1.4002600655514802e-05,
      "loss": 0.6125,
      "step": 24083
    },
    {
      "epoch": 0.7398396461155654,
      "grad_norm": 0.38379088044166565,
      "learning_rate": 1.4002157774719707e-05,
      "loss": 0.5724,
      "step": 24084
    },
    {
      "epoch": 0.7398703652505145,
      "grad_norm": 0.3431858420372009,
      "learning_rate": 1.4001714884577288e-05,
      "loss": 0.4991,
      "step": 24085
    },
    {
      "epoch": 0.7399010843854638,
      "grad_norm": 0.7129083871841431,
      "learning_rate": 1.4001271985088589e-05,
      "loss": 0.6142,
      "step": 24086
    },
    {
      "epoch": 0.7399318035204129,
      "grad_norm": 0.40613263845443726,
      "learning_rate": 1.4000829076254638e-05,
      "loss": 0.6413,
      "step": 24087
    },
    {
      "epoch": 0.739962522655362,
      "grad_norm": 0.4554364085197449,
      "learning_rate": 1.4000386158076472e-05,
      "loss": 0.6276,
      "step": 24088
    },
    {
      "epoch": 0.7399932417903112,
      "grad_norm": 0.3417763411998749,
      "learning_rate": 1.3999943230555127e-05,
      "loss": 0.5591,
      "step": 24089
    },
    {
      "epoch": 0.7400239609252603,
      "grad_norm": 0.378839373588562,
      "learning_rate": 1.3999500293691633e-05,
      "loss": 0.5175,
      "step": 24090
    },
    {
      "epoch": 0.7400546800602095,
      "grad_norm": 0.3299786448478699,
      "learning_rate": 1.3999057347487024e-05,
      "loss": 0.5187,
      "step": 24091
    },
    {
      "epoch": 0.7400853991951587,
      "grad_norm": 0.35547545552253723,
      "learning_rate": 1.399861439194234e-05,
      "loss": 0.5167,
      "step": 24092
    },
    {
      "epoch": 0.7401161183301078,
      "grad_norm": 0.3292669355869293,
      "learning_rate": 1.3998171427058613e-05,
      "loss": 0.5668,
      "step": 24093
    },
    {
      "epoch": 0.7401468374650569,
      "grad_norm": 0.37461093068122864,
      "learning_rate": 1.3997728452836876e-05,
      "loss": 0.4791,
      "step": 24094
    },
    {
      "epoch": 0.7401775566000062,
      "grad_norm": 0.39083757996559143,
      "learning_rate": 1.3997285469278169e-05,
      "loss": 0.5454,
      "step": 24095
    },
    {
      "epoch": 0.7402082757349553,
      "grad_norm": 0.3868541419506073,
      "learning_rate": 1.399684247638352e-05,
      "loss": 0.544,
      "step": 24096
    },
    {
      "epoch": 0.7402389948699044,
      "grad_norm": 0.33153676986694336,
      "learning_rate": 1.3996399474153966e-05,
      "loss": 0.5815,
      "step": 24097
    },
    {
      "epoch": 0.7402697140048536,
      "grad_norm": 0.3644466698169708,
      "learning_rate": 1.3995956462590538e-05,
      "loss": 0.6358,
      "step": 24098
    },
    {
      "epoch": 0.7403004331398028,
      "grad_norm": 0.3573976755142212,
      "learning_rate": 1.3995513441694279e-05,
      "loss": 0.502,
      "step": 24099
    },
    {
      "epoch": 0.740331152274752,
      "grad_norm": 0.36074206233024597,
      "learning_rate": 1.3995070411466221e-05,
      "loss": 0.5414,
      "step": 24100
    },
    {
      "epoch": 0.7403618714097011,
      "grad_norm": 0.3397543132305145,
      "learning_rate": 1.3994627371907395e-05,
      "loss": 0.5651,
      "step": 24101
    },
    {
      "epoch": 0.7403925905446502,
      "grad_norm": 0.33978626132011414,
      "learning_rate": 1.3994184323018839e-05,
      "loss": 0.5611,
      "step": 24102
    },
    {
      "epoch": 0.7404233096795995,
      "grad_norm": 0.35022249817848206,
      "learning_rate": 1.3993741264801583e-05,
      "loss": 0.5617,
      "step": 24103
    },
    {
      "epoch": 0.7404540288145486,
      "grad_norm": 0.44543251395225525,
      "learning_rate": 1.3993298197256668e-05,
      "loss": 0.6228,
      "step": 24104
    },
    {
      "epoch": 0.7404847479494977,
      "grad_norm": 0.335196852684021,
      "learning_rate": 1.3992855120385125e-05,
      "loss": 0.5024,
      "step": 24105
    },
    {
      "epoch": 0.7405154670844469,
      "grad_norm": 0.3999618589878082,
      "learning_rate": 1.3992412034187992e-05,
      "loss": 0.6588,
      "step": 24106
    },
    {
      "epoch": 0.740546186219396,
      "grad_norm": 0.4161812961101532,
      "learning_rate": 1.39919689386663e-05,
      "loss": 0.5347,
      "step": 24107
    },
    {
      "epoch": 0.7405769053543452,
      "grad_norm": 0.36717838048934937,
      "learning_rate": 1.399152583382109e-05,
      "loss": 0.6098,
      "step": 24108
    },
    {
      "epoch": 0.7406076244892944,
      "grad_norm": 0.36016014218330383,
      "learning_rate": 1.3991082719653386e-05,
      "loss": 0.5633,
      "step": 24109
    },
    {
      "epoch": 0.7406383436242435,
      "grad_norm": 0.3586862087249756,
      "learning_rate": 1.3990639596164232e-05,
      "loss": 0.5873,
      "step": 24110
    },
    {
      "epoch": 0.7406690627591928,
      "grad_norm": 0.3714008927345276,
      "learning_rate": 1.3990196463354662e-05,
      "loss": 0.5933,
      "step": 24111
    },
    {
      "epoch": 0.7406997818941419,
      "grad_norm": 0.5032541751861572,
      "learning_rate": 1.3989753321225708e-05,
      "loss": 0.5932,
      "step": 24112
    },
    {
      "epoch": 0.740730501029091,
      "grad_norm": 0.33220216631889343,
      "learning_rate": 1.3989310169778407e-05,
      "loss": 0.5306,
      "step": 24113
    },
    {
      "epoch": 0.7407612201640402,
      "grad_norm": 0.6696385145187378,
      "learning_rate": 1.3988867009013793e-05,
      "loss": 0.6023,
      "step": 24114
    },
    {
      "epoch": 0.7407919392989893,
      "grad_norm": 0.34617888927459717,
      "learning_rate": 1.3988423838932903e-05,
      "loss": 0.6015,
      "step": 24115
    },
    {
      "epoch": 0.7408226584339385,
      "grad_norm": 0.40457382798194885,
      "learning_rate": 1.398798065953677e-05,
      "loss": 0.6164,
      "step": 24116
    },
    {
      "epoch": 0.7408533775688877,
      "grad_norm": 0.3597176671028137,
      "learning_rate": 1.3987537470826429e-05,
      "loss": 0.4988,
      "step": 24117
    },
    {
      "epoch": 0.7408840967038368,
      "grad_norm": 0.3635714054107666,
      "learning_rate": 1.3987094272802918e-05,
      "loss": 0.5936,
      "step": 24118
    },
    {
      "epoch": 0.7409148158387859,
      "grad_norm": 0.3780451714992523,
      "learning_rate": 1.3986651065467267e-05,
      "loss": 0.5899,
      "step": 24119
    },
    {
      "epoch": 0.7409455349737352,
      "grad_norm": 0.34673336148262024,
      "learning_rate": 1.3986207848820516e-05,
      "loss": 0.5033,
      "step": 24120
    },
    {
      "epoch": 0.7409762541086843,
      "grad_norm": 0.364650696516037,
      "learning_rate": 1.3985764622863696e-05,
      "loss": 0.569,
      "step": 24121
    },
    {
      "epoch": 0.7410069732436334,
      "grad_norm": 0.38662976026535034,
      "learning_rate": 1.3985321387597846e-05,
      "loss": 0.54,
      "step": 24122
    },
    {
      "epoch": 0.7410376923785826,
      "grad_norm": 0.3676775097846985,
      "learning_rate": 1.3984878143023999e-05,
      "loss": 0.5261,
      "step": 24123
    },
    {
      "epoch": 0.7410684115135318,
      "grad_norm": 0.33855563402175903,
      "learning_rate": 1.3984434889143193e-05,
      "loss": 0.5239,
      "step": 24124
    },
    {
      "epoch": 0.741099130648481,
      "grad_norm": 0.43141382932662964,
      "learning_rate": 1.3983991625956456e-05,
      "loss": 0.493,
      "step": 24125
    },
    {
      "epoch": 0.7411298497834301,
      "grad_norm": 0.36873507499694824,
      "learning_rate": 1.3983548353464833e-05,
      "loss": 0.5468,
      "step": 24126
    },
    {
      "epoch": 0.7411605689183792,
      "grad_norm": 0.3368791341781616,
      "learning_rate": 1.3983105071669352e-05,
      "loss": 0.5477,
      "step": 24127
    },
    {
      "epoch": 0.7411912880533285,
      "grad_norm": 0.3805893659591675,
      "learning_rate": 1.398266178057105e-05,
      "loss": 0.59,
      "step": 24128
    },
    {
      "epoch": 0.7412220071882776,
      "grad_norm": 0.3429812490940094,
      "learning_rate": 1.3982218480170966e-05,
      "loss": 0.5602,
      "step": 24129
    },
    {
      "epoch": 0.7412527263232267,
      "grad_norm": 0.37428224086761475,
      "learning_rate": 1.3981775170470131e-05,
      "loss": 0.5554,
      "step": 24130
    },
    {
      "epoch": 0.7412834454581759,
      "grad_norm": 0.3665332496166229,
      "learning_rate": 1.3981331851469583e-05,
      "loss": 0.6112,
      "step": 24131
    },
    {
      "epoch": 0.741314164593125,
      "grad_norm": 0.3315355181694031,
      "learning_rate": 1.3980888523170355e-05,
      "loss": 0.4565,
      "step": 24132
    },
    {
      "epoch": 0.7413448837280742,
      "grad_norm": 0.34935128688812256,
      "learning_rate": 1.3980445185573488e-05,
      "loss": 0.5004,
      "step": 24133
    },
    {
      "epoch": 0.7413756028630234,
      "grad_norm": 0.45483022928237915,
      "learning_rate": 1.398000183868001e-05,
      "loss": 0.5943,
      "step": 24134
    },
    {
      "epoch": 0.7414063219979725,
      "grad_norm": 0.43498826026916504,
      "learning_rate": 1.397955848249096e-05,
      "loss": 0.5712,
      "step": 24135
    },
    {
      "epoch": 0.7414370411329217,
      "grad_norm": 0.3472997844219208,
      "learning_rate": 1.3979115117007374e-05,
      "loss": 0.5205,
      "step": 24136
    },
    {
      "epoch": 0.7414677602678709,
      "grad_norm": 0.36821937561035156,
      "learning_rate": 1.3978671742230284e-05,
      "loss": 0.5408,
      "step": 24137
    },
    {
      "epoch": 0.74149847940282,
      "grad_norm": 0.3703446686267853,
      "learning_rate": 1.397822835816073e-05,
      "loss": 0.5392,
      "step": 24138
    },
    {
      "epoch": 0.7415291985377692,
      "grad_norm": 0.3232649862766266,
      "learning_rate": 1.3977784964799748e-05,
      "loss": 0.5277,
      "step": 24139
    },
    {
      "epoch": 0.7415599176727183,
      "grad_norm": 0.3419930934906006,
      "learning_rate": 1.397734156214837e-05,
      "loss": 0.5394,
      "step": 24140
    },
    {
      "epoch": 0.7415906368076675,
      "grad_norm": 0.3381323218345642,
      "learning_rate": 1.3976898150207632e-05,
      "loss": 0.5147,
      "step": 24141
    },
    {
      "epoch": 0.7416213559426167,
      "grad_norm": 0.8751561641693115,
      "learning_rate": 1.397645472897857e-05,
      "loss": 0.539,
      "step": 24142
    },
    {
      "epoch": 0.7416520750775658,
      "grad_norm": 0.38520804047584534,
      "learning_rate": 1.3976011298462221e-05,
      "loss": 0.5649,
      "step": 24143
    },
    {
      "epoch": 0.7416827942125149,
      "grad_norm": 0.37663424015045166,
      "learning_rate": 1.397556785865962e-05,
      "loss": 0.5401,
      "step": 24144
    },
    {
      "epoch": 0.7417135133474642,
      "grad_norm": 0.3466649353504181,
      "learning_rate": 1.3975124409571806e-05,
      "loss": 0.5567,
      "step": 24145
    },
    {
      "epoch": 0.7417442324824133,
      "grad_norm": 0.3477979302406311,
      "learning_rate": 1.3974680951199804e-05,
      "loss": 0.5731,
      "step": 24146
    },
    {
      "epoch": 0.7417749516173625,
      "grad_norm": 0.41759437322616577,
      "learning_rate": 1.3974237483544664e-05,
      "loss": 0.5803,
      "step": 24147
    },
    {
      "epoch": 0.7418056707523116,
      "grad_norm": 0.49904847145080566,
      "learning_rate": 1.3973794006607411e-05,
      "loss": 0.6013,
      "step": 24148
    },
    {
      "epoch": 0.7418363898872607,
      "grad_norm": 0.3744172155857086,
      "learning_rate": 1.3973350520389085e-05,
      "loss": 0.5419,
      "step": 24149
    },
    {
      "epoch": 0.74186710902221,
      "grad_norm": 0.352936714887619,
      "learning_rate": 1.3972907024890721e-05,
      "loss": 0.5541,
      "step": 24150
    },
    {
      "epoch": 0.7418978281571591,
      "grad_norm": 0.32561057806015015,
      "learning_rate": 1.3972463520113357e-05,
      "loss": 0.5031,
      "step": 24151
    },
    {
      "epoch": 0.7419285472921082,
      "grad_norm": 0.34309548139572144,
      "learning_rate": 1.3972020006058026e-05,
      "loss": 0.5613,
      "step": 24152
    },
    {
      "epoch": 0.7419592664270575,
      "grad_norm": 0.33721300959587097,
      "learning_rate": 1.3971576482725767e-05,
      "loss": 0.5338,
      "step": 24153
    },
    {
      "epoch": 0.7419899855620066,
      "grad_norm": 0.38324347138404846,
      "learning_rate": 1.3971132950117612e-05,
      "loss": 0.4771,
      "step": 24154
    },
    {
      "epoch": 0.7420207046969557,
      "grad_norm": 0.3637491464614868,
      "learning_rate": 1.3970689408234596e-05,
      "loss": 0.5308,
      "step": 24155
    },
    {
      "epoch": 0.7420514238319049,
      "grad_norm": 0.35825636982917786,
      "learning_rate": 1.3970245857077762e-05,
      "loss": 0.5437,
      "step": 24156
    },
    {
      "epoch": 0.742082142966854,
      "grad_norm": 0.3569939434528351,
      "learning_rate": 1.3969802296648138e-05,
      "loss": 0.5125,
      "step": 24157
    },
    {
      "epoch": 0.7421128621018032,
      "grad_norm": 0.39946073293685913,
      "learning_rate": 1.3969358726946766e-05,
      "loss": 0.4932,
      "step": 24158
    },
    {
      "epoch": 0.7421435812367524,
      "grad_norm": 0.37380123138427734,
      "learning_rate": 1.396891514797468e-05,
      "loss": 0.5723,
      "step": 24159
    },
    {
      "epoch": 0.7421743003717015,
      "grad_norm": 0.38735419511795044,
      "learning_rate": 1.3968471559732915e-05,
      "loss": 0.582,
      "step": 24160
    },
    {
      "epoch": 0.7422050195066507,
      "grad_norm": 0.4017593562602997,
      "learning_rate": 1.3968027962222504e-05,
      "loss": 0.555,
      "step": 24161
    },
    {
      "epoch": 0.7422357386415999,
      "grad_norm": 0.35706010460853577,
      "learning_rate": 1.396758435544449e-05,
      "loss": 0.4782,
      "step": 24162
    },
    {
      "epoch": 0.742266457776549,
      "grad_norm": 0.3563995659351349,
      "learning_rate": 1.3967140739399905e-05,
      "loss": 0.5514,
      "step": 24163
    },
    {
      "epoch": 0.7422971769114982,
      "grad_norm": 0.3625752329826355,
      "learning_rate": 1.3966697114089783e-05,
      "loss": 0.593,
      "step": 24164
    },
    {
      "epoch": 0.7423278960464473,
      "grad_norm": 0.37264594435691833,
      "learning_rate": 1.3966253479515169e-05,
      "loss": 0.5212,
      "step": 24165
    },
    {
      "epoch": 0.7423586151813965,
      "grad_norm": 0.45435431599617004,
      "learning_rate": 1.3965809835677087e-05,
      "loss": 0.5697,
      "step": 24166
    },
    {
      "epoch": 0.7423893343163457,
      "grad_norm": 0.36366111040115356,
      "learning_rate": 1.3965366182576583e-05,
      "loss": 0.5561,
      "step": 24167
    },
    {
      "epoch": 0.7424200534512948,
      "grad_norm": 0.3568592965602875,
      "learning_rate": 1.3964922520214688e-05,
      "loss": 0.6135,
      "step": 24168
    },
    {
      "epoch": 0.7424507725862439,
      "grad_norm": 0.3697623908519745,
      "learning_rate": 1.3964478848592438e-05,
      "loss": 0.4722,
      "step": 24169
    },
    {
      "epoch": 0.7424814917211932,
      "grad_norm": 0.37901216745376587,
      "learning_rate": 1.3964035167710875e-05,
      "loss": 0.5737,
      "step": 24170
    },
    {
      "epoch": 0.7425122108561423,
      "grad_norm": 0.431497722864151,
      "learning_rate": 1.3963591477571026e-05,
      "loss": 0.6095,
      "step": 24171
    },
    {
      "epoch": 0.7425429299910915,
      "grad_norm": 0.343195378780365,
      "learning_rate": 1.3963147778173936e-05,
      "loss": 0.5457,
      "step": 24172
    },
    {
      "epoch": 0.7425736491260406,
      "grad_norm": 0.36160191893577576,
      "learning_rate": 1.3962704069520634e-05,
      "loss": 0.58,
      "step": 24173
    },
    {
      "epoch": 0.7426043682609897,
      "grad_norm": 0.36049699783325195,
      "learning_rate": 1.3962260351612163e-05,
      "loss": 0.5628,
      "step": 24174
    },
    {
      "epoch": 0.742635087395939,
      "grad_norm": 0.3350850045681,
      "learning_rate": 1.3961816624449553e-05,
      "loss": 0.5289,
      "step": 24175
    },
    {
      "epoch": 0.7426658065308881,
      "grad_norm": 0.37808895111083984,
      "learning_rate": 1.3961372888033848e-05,
      "loss": 0.4449,
      "step": 24176
    },
    {
      "epoch": 0.7426965256658372,
      "grad_norm": 0.35625264048576355,
      "learning_rate": 1.3960929142366077e-05,
      "loss": 0.5552,
      "step": 24177
    },
    {
      "epoch": 0.7427272448007864,
      "grad_norm": 0.3743714392185211,
      "learning_rate": 1.396048538744728e-05,
      "loss": 0.5136,
      "step": 24178
    },
    {
      "epoch": 0.7427579639357356,
      "grad_norm": 0.3520742952823639,
      "learning_rate": 1.3960041623278495e-05,
      "loss": 0.5248,
      "step": 24179
    },
    {
      "epoch": 0.7427886830706847,
      "grad_norm": 0.3508898913860321,
      "learning_rate": 1.3959597849860753e-05,
      "loss": 0.5446,
      "step": 24180
    },
    {
      "epoch": 0.7428194022056339,
      "grad_norm": 0.3457241952419281,
      "learning_rate": 1.3959154067195096e-05,
      "loss": 0.6045,
      "step": 24181
    },
    {
      "epoch": 0.742850121340583,
      "grad_norm": 0.4005032777786255,
      "learning_rate": 1.3958710275282555e-05,
      "loss": 0.5824,
      "step": 24182
    },
    {
      "epoch": 0.7428808404755322,
      "grad_norm": 0.3411861062049866,
      "learning_rate": 1.3958266474124172e-05,
      "loss": 0.5473,
      "step": 24183
    },
    {
      "epoch": 0.7429115596104814,
      "grad_norm": 0.35423213243484497,
      "learning_rate": 1.395782266372098e-05,
      "loss": 0.5712,
      "step": 24184
    },
    {
      "epoch": 0.7429422787454305,
      "grad_norm": 0.37443649768829346,
      "learning_rate": 1.3957378844074018e-05,
      "loss": 0.593,
      "step": 24185
    },
    {
      "epoch": 0.7429729978803797,
      "grad_norm": 0.35715997219085693,
      "learning_rate": 1.3956935015184323e-05,
      "loss": 0.583,
      "step": 24186
    },
    {
      "epoch": 0.7430037170153289,
      "grad_norm": 0.3274696469306946,
      "learning_rate": 1.3956491177052927e-05,
      "loss": 0.5114,
      "step": 24187
    },
    {
      "epoch": 0.743034436150278,
      "grad_norm": 0.3526763319969177,
      "learning_rate": 1.3956047329680871e-05,
      "loss": 0.5456,
      "step": 24188
    },
    {
      "epoch": 0.7430651552852272,
      "grad_norm": 0.335777223110199,
      "learning_rate": 1.3955603473069187e-05,
      "loss": 0.5481,
      "step": 24189
    },
    {
      "epoch": 0.7430958744201763,
      "grad_norm": 0.4098687469959259,
      "learning_rate": 1.395515960721892e-05,
      "loss": 0.6215,
      "step": 24190
    },
    {
      "epoch": 0.7431265935551254,
      "grad_norm": 0.3662053644657135,
      "learning_rate": 1.3954715732131096e-05,
      "loss": 0.5338,
      "step": 24191
    },
    {
      "epoch": 0.7431573126900747,
      "grad_norm": 0.33739206194877625,
      "learning_rate": 1.3954271847806761e-05,
      "loss": 0.5522,
      "step": 24192
    },
    {
      "epoch": 0.7431880318250238,
      "grad_norm": 0.3790123760700226,
      "learning_rate": 1.3953827954246948e-05,
      "loss": 0.5653,
      "step": 24193
    },
    {
      "epoch": 0.7432187509599729,
      "grad_norm": 0.36215999722480774,
      "learning_rate": 1.3953384051452693e-05,
      "loss": 0.5382,
      "step": 24194
    },
    {
      "epoch": 0.7432494700949221,
      "grad_norm": 0.34811559319496155,
      "learning_rate": 1.3952940139425033e-05,
      "loss": 0.48,
      "step": 24195
    },
    {
      "epoch": 0.7432801892298713,
      "grad_norm": 0.35505208373069763,
      "learning_rate": 1.3952496218165006e-05,
      "loss": 0.5498,
      "step": 24196
    },
    {
      "epoch": 0.7433109083648205,
      "grad_norm": 0.36433714628219604,
      "learning_rate": 1.395205228767365e-05,
      "loss": 0.5031,
      "step": 24197
    },
    {
      "epoch": 0.7433416274997696,
      "grad_norm": 0.40672969818115234,
      "learning_rate": 1.3951608347951994e-05,
      "loss": 0.5347,
      "step": 24198
    },
    {
      "epoch": 0.7433723466347187,
      "grad_norm": 0.37118929624557495,
      "learning_rate": 1.3951164399001086e-05,
      "loss": 0.5213,
      "step": 24199
    },
    {
      "epoch": 0.743403065769668,
      "grad_norm": 0.3587082028388977,
      "learning_rate": 1.3950720440821953e-05,
      "loss": 0.5929,
      "step": 24200
    },
    {
      "epoch": 0.7434337849046171,
      "grad_norm": 0.40817737579345703,
      "learning_rate": 1.395027647341564e-05,
      "loss": 0.6345,
      "step": 24201
    },
    {
      "epoch": 0.7434645040395662,
      "grad_norm": 0.3997225761413574,
      "learning_rate": 1.3949832496783178e-05,
      "loss": 0.6826,
      "step": 24202
    },
    {
      "epoch": 0.7434952231745154,
      "grad_norm": 0.3848213255405426,
      "learning_rate": 1.394938851092561e-05,
      "loss": 0.6197,
      "step": 24203
    },
    {
      "epoch": 0.7435259423094646,
      "grad_norm": 0.3878210186958313,
      "learning_rate": 1.3948944515843968e-05,
      "loss": 0.5571,
      "step": 24204
    },
    {
      "epoch": 0.7435566614444137,
      "grad_norm": 0.3788864314556122,
      "learning_rate": 1.3948500511539287e-05,
      "loss": 0.5704,
      "step": 24205
    },
    {
      "epoch": 0.7435873805793629,
      "grad_norm": 0.3421024978160858,
      "learning_rate": 1.3948056498012612e-05,
      "loss": 0.4863,
      "step": 24206
    },
    {
      "epoch": 0.743618099714312,
      "grad_norm": 0.3601420819759369,
      "learning_rate": 1.394761247526497e-05,
      "loss": 0.5257,
      "step": 24207
    },
    {
      "epoch": 0.7436488188492612,
      "grad_norm": 0.38115647435188293,
      "learning_rate": 1.394716844329741e-05,
      "loss": 0.4525,
      "step": 24208
    },
    {
      "epoch": 0.7436795379842104,
      "grad_norm": 0.3315134346485138,
      "learning_rate": 1.3946724402110959e-05,
      "loss": 0.5085,
      "step": 24209
    },
    {
      "epoch": 0.7437102571191595,
      "grad_norm": 0.464437872171402,
      "learning_rate": 1.3946280351706658e-05,
      "loss": 0.5286,
      "step": 24210
    },
    {
      "epoch": 0.7437409762541087,
      "grad_norm": 0.3634023070335388,
      "learning_rate": 1.3945836292085542e-05,
      "loss": 0.5436,
      "step": 24211
    },
    {
      "epoch": 0.7437716953890579,
      "grad_norm": 0.3658812940120697,
      "learning_rate": 1.394539222324865e-05,
      "loss": 0.5387,
      "step": 24212
    },
    {
      "epoch": 0.743802414524007,
      "grad_norm": 0.381190687417984,
      "learning_rate": 1.394494814519702e-05,
      "loss": 0.5789,
      "step": 24213
    },
    {
      "epoch": 0.7438331336589562,
      "grad_norm": 0.3398866355419159,
      "learning_rate": 1.394450405793169e-05,
      "loss": 0.5593,
      "step": 24214
    },
    {
      "epoch": 0.7438638527939053,
      "grad_norm": 0.33352094888687134,
      "learning_rate": 1.3944059961453694e-05,
      "loss": 0.6154,
      "step": 24215
    },
    {
      "epoch": 0.7438945719288544,
      "grad_norm": 0.4397144615650177,
      "learning_rate": 1.3943615855764067e-05,
      "loss": 0.6067,
      "step": 24216
    },
    {
      "epoch": 0.7439252910638037,
      "grad_norm": 0.33332502841949463,
      "learning_rate": 1.3943171740863855e-05,
      "loss": 0.4809,
      "step": 24217
    },
    {
      "epoch": 0.7439560101987528,
      "grad_norm": 0.34704092144966125,
      "learning_rate": 1.3942727616754086e-05,
      "loss": 0.4933,
      "step": 24218
    },
    {
      "epoch": 0.7439867293337019,
      "grad_norm": 0.41253045201301575,
      "learning_rate": 1.3942283483435802e-05,
      "loss": 0.5945,
      "step": 24219
    },
    {
      "epoch": 0.7440174484686511,
      "grad_norm": 0.37822744250297546,
      "learning_rate": 1.3941839340910042e-05,
      "loss": 0.5283,
      "step": 24220
    },
    {
      "epoch": 0.7440481676036003,
      "grad_norm": 0.3508889079093933,
      "learning_rate": 1.3941395189177837e-05,
      "loss": 0.5787,
      "step": 24221
    },
    {
      "epoch": 0.7440788867385495,
      "grad_norm": 0.3932173550128937,
      "learning_rate": 1.3940951028240233e-05,
      "loss": 0.4605,
      "step": 24222
    },
    {
      "epoch": 0.7441096058734986,
      "grad_norm": 0.35058051347732544,
      "learning_rate": 1.3940506858098257e-05,
      "loss": 0.5043,
      "step": 24223
    },
    {
      "epoch": 0.7441403250084477,
      "grad_norm": 0.36043480038642883,
      "learning_rate": 1.3940062678752957e-05,
      "loss": 0.518,
      "step": 24224
    },
    {
      "epoch": 0.744171044143397,
      "grad_norm": 0.3765770196914673,
      "learning_rate": 1.3939618490205362e-05,
      "loss": 0.5418,
      "step": 24225
    },
    {
      "epoch": 0.7442017632783461,
      "grad_norm": 0.3744790256023407,
      "learning_rate": 1.3939174292456517e-05,
      "loss": 0.4772,
      "step": 24226
    },
    {
      "epoch": 0.7442324824132952,
      "grad_norm": 0.40797320008277893,
      "learning_rate": 1.3938730085507452e-05,
      "loss": 0.5584,
      "step": 24227
    },
    {
      "epoch": 0.7442632015482444,
      "grad_norm": 0.3712348937988281,
      "learning_rate": 1.393828586935921e-05,
      "loss": 0.5575,
      "step": 24228
    },
    {
      "epoch": 0.7442939206831936,
      "grad_norm": 0.4280013144016266,
      "learning_rate": 1.3937841644012822e-05,
      "loss": 0.5762,
      "step": 24229
    },
    {
      "epoch": 0.7443246398181427,
      "grad_norm": 0.3402077853679657,
      "learning_rate": 1.3937397409469335e-05,
      "loss": 0.5366,
      "step": 24230
    },
    {
      "epoch": 0.7443553589530919,
      "grad_norm": 0.36697009205818176,
      "learning_rate": 1.3936953165729779e-05,
      "loss": 0.6196,
      "step": 24231
    },
    {
      "epoch": 0.744386078088041,
      "grad_norm": 0.37117883563041687,
      "learning_rate": 1.3936508912795194e-05,
      "loss": 0.6196,
      "step": 24232
    },
    {
      "epoch": 0.7444167972229901,
      "grad_norm": 0.3615424931049347,
      "learning_rate": 1.3936064650666619e-05,
      "loss": 0.612,
      "step": 24233
    },
    {
      "epoch": 0.7444475163579394,
      "grad_norm": 0.3568446636199951,
      "learning_rate": 1.3935620379345087e-05,
      "loss": 0.5407,
      "step": 24234
    },
    {
      "epoch": 0.7444782354928885,
      "grad_norm": 0.4212568998336792,
      "learning_rate": 1.3935176098831643e-05,
      "loss": 0.5212,
      "step": 24235
    },
    {
      "epoch": 0.7445089546278377,
      "grad_norm": 0.37608468532562256,
      "learning_rate": 1.3934731809127315e-05,
      "loss": 0.5639,
      "step": 24236
    },
    {
      "epoch": 0.7445396737627868,
      "grad_norm": 0.32548534870147705,
      "learning_rate": 1.393428751023315e-05,
      "loss": 0.5272,
      "step": 24237
    },
    {
      "epoch": 0.744570392897736,
      "grad_norm": 0.35783159732818604,
      "learning_rate": 1.3933843202150179e-05,
      "loss": 0.4888,
      "step": 24238
    },
    {
      "epoch": 0.7446011120326852,
      "grad_norm": 0.34735554456710815,
      "learning_rate": 1.3933398884879444e-05,
      "loss": 0.5941,
      "step": 24239
    },
    {
      "epoch": 0.7446318311676343,
      "grad_norm": 0.37582260370254517,
      "learning_rate": 1.3932954558421982e-05,
      "loss": 0.5419,
      "step": 24240
    },
    {
      "epoch": 0.7446625503025834,
      "grad_norm": 0.3675706386566162,
      "learning_rate": 1.393251022277883e-05,
      "loss": 0.5425,
      "step": 24241
    },
    {
      "epoch": 0.7446932694375327,
      "grad_norm": 0.32339781522750854,
      "learning_rate": 1.3932065877951026e-05,
      "loss": 0.5887,
      "step": 24242
    },
    {
      "epoch": 0.7447239885724818,
      "grad_norm": 0.39473894238471985,
      "learning_rate": 1.3931621523939605e-05,
      "loss": 0.6433,
      "step": 24243
    },
    {
      "epoch": 0.7447547077074309,
      "grad_norm": 0.32943812012672424,
      "learning_rate": 1.393117716074561e-05,
      "loss": 0.5064,
      "step": 24244
    },
    {
      "epoch": 0.7447854268423801,
      "grad_norm": 0.35648566484451294,
      "learning_rate": 1.3930732788370074e-05,
      "loss": 0.5591,
      "step": 24245
    },
    {
      "epoch": 0.7448161459773293,
      "grad_norm": 0.3811604678630829,
      "learning_rate": 1.393028840681404e-05,
      "loss": 0.5827,
      "step": 24246
    },
    {
      "epoch": 0.7448468651122785,
      "grad_norm": 0.3401550352573395,
      "learning_rate": 1.3929844016078539e-05,
      "loss": 0.5883,
      "step": 24247
    },
    {
      "epoch": 0.7448775842472276,
      "grad_norm": 0.3234596848487854,
      "learning_rate": 1.3929399616164617e-05,
      "loss": 0.4891,
      "step": 24248
    },
    {
      "epoch": 0.7449083033821767,
      "grad_norm": 0.3502811789512634,
      "learning_rate": 1.3928955207073305e-05,
      "loss": 0.5406,
      "step": 24249
    },
    {
      "epoch": 0.744939022517126,
      "grad_norm": 0.3503537178039551,
      "learning_rate": 1.3928510788805646e-05,
      "loss": 0.5376,
      "step": 24250
    },
    {
      "epoch": 0.7449697416520751,
      "grad_norm": 0.38781267404556274,
      "learning_rate": 1.3928066361362673e-05,
      "loss": 0.557,
      "step": 24251
    },
    {
      "epoch": 0.7450004607870242,
      "grad_norm": 0.33628225326538086,
      "learning_rate": 1.3927621924745428e-05,
      "loss": 0.5234,
      "step": 24252
    },
    {
      "epoch": 0.7450311799219734,
      "grad_norm": 0.39167675375938416,
      "learning_rate": 1.3927177478954948e-05,
      "loss": 0.6172,
      "step": 24253
    },
    {
      "epoch": 0.7450618990569225,
      "grad_norm": 0.40443193912506104,
      "learning_rate": 1.392673302399227e-05,
      "loss": 0.618,
      "step": 24254
    },
    {
      "epoch": 0.7450926181918717,
      "grad_norm": 0.3616211712360382,
      "learning_rate": 1.392628855985843e-05,
      "loss": 0.5368,
      "step": 24255
    },
    {
      "epoch": 0.7451233373268209,
      "grad_norm": 0.3491271138191223,
      "learning_rate": 1.3925844086554473e-05,
      "loss": 0.5558,
      "step": 24256
    },
    {
      "epoch": 0.74515405646177,
      "grad_norm": 0.3251248002052307,
      "learning_rate": 1.392539960408143e-05,
      "loss": 0.476,
      "step": 24257
    },
    {
      "epoch": 0.7451847755967193,
      "grad_norm": 0.349777489900589,
      "learning_rate": 1.3924955112440346e-05,
      "loss": 0.5395,
      "step": 24258
    },
    {
      "epoch": 0.7452154947316684,
      "grad_norm": 0.3441862463951111,
      "learning_rate": 1.3924510611632252e-05,
      "loss": 0.5401,
      "step": 24259
    },
    {
      "epoch": 0.7452462138666175,
      "grad_norm": 0.3673233389854431,
      "learning_rate": 1.3924066101658192e-05,
      "loss": 0.5557,
      "step": 24260
    },
    {
      "epoch": 0.7452769330015667,
      "grad_norm": 0.36130037903785706,
      "learning_rate": 1.39236215825192e-05,
      "loss": 0.5552,
      "step": 24261
    },
    {
      "epoch": 0.7453076521365158,
      "grad_norm": 0.43323206901550293,
      "learning_rate": 1.3923177054216317e-05,
      "loss": 0.5466,
      "step": 24262
    },
    {
      "epoch": 0.745338371271465,
      "grad_norm": 0.37830227613449097,
      "learning_rate": 1.3922732516750577e-05,
      "loss": 0.5945,
      "step": 24263
    },
    {
      "epoch": 0.7453690904064142,
      "grad_norm": 0.37073755264282227,
      "learning_rate": 1.3922287970123023e-05,
      "loss": 0.5649,
      "step": 24264
    },
    {
      "epoch": 0.7453998095413633,
      "grad_norm": 0.4911746680736542,
      "learning_rate": 1.3921843414334691e-05,
      "loss": 0.5842,
      "step": 24265
    },
    {
      "epoch": 0.7454305286763124,
      "grad_norm": 0.33177611231803894,
      "learning_rate": 1.3921398849386623e-05,
      "loss": 0.5183,
      "step": 24266
    },
    {
      "epoch": 0.7454612478112617,
      "grad_norm": 0.357553094625473,
      "learning_rate": 1.3920954275279852e-05,
      "loss": 0.5382,
      "step": 24267
    },
    {
      "epoch": 0.7454919669462108,
      "grad_norm": 0.3585798442363739,
      "learning_rate": 1.3920509692015416e-05,
      "loss": 0.5473,
      "step": 24268
    },
    {
      "epoch": 0.7455226860811599,
      "grad_norm": 0.4668923318386078,
      "learning_rate": 1.392006509959436e-05,
      "loss": 0.5414,
      "step": 24269
    },
    {
      "epoch": 0.7455534052161091,
      "grad_norm": 0.3808416426181793,
      "learning_rate": 1.3919620498017713e-05,
      "loss": 0.5299,
      "step": 24270
    },
    {
      "epoch": 0.7455841243510583,
      "grad_norm": 0.5385532379150391,
      "learning_rate": 1.3919175887286525e-05,
      "loss": 0.5502,
      "step": 24271
    },
    {
      "epoch": 0.7456148434860075,
      "grad_norm": 0.3772508203983307,
      "learning_rate": 1.391873126740182e-05,
      "loss": 0.5179,
      "step": 24272
    },
    {
      "epoch": 0.7456455626209566,
      "grad_norm": 0.3820464313030243,
      "learning_rate": 1.3918286638364651e-05,
      "loss": 0.5321,
      "step": 24273
    },
    {
      "epoch": 0.7456762817559057,
      "grad_norm": 0.3347627818584442,
      "learning_rate": 1.3917842000176048e-05,
      "loss": 0.5624,
      "step": 24274
    },
    {
      "epoch": 0.745707000890855,
      "grad_norm": 0.3389339745044708,
      "learning_rate": 1.391739735283705e-05,
      "loss": 0.5808,
      "step": 24275
    },
    {
      "epoch": 0.7457377200258041,
      "grad_norm": 0.4047050476074219,
      "learning_rate": 1.3916952696348701e-05,
      "loss": 0.5554,
      "step": 24276
    },
    {
      "epoch": 0.7457684391607532,
      "grad_norm": 0.37262505292892456,
      "learning_rate": 1.391650803071203e-05,
      "loss": 0.5367,
      "step": 24277
    },
    {
      "epoch": 0.7457991582957024,
      "grad_norm": 0.37236863374710083,
      "learning_rate": 1.3916063355928084e-05,
      "loss": 0.631,
      "step": 24278
    },
    {
      "epoch": 0.7458298774306515,
      "grad_norm": 0.3316901922225952,
      "learning_rate": 1.3915618671997897e-05,
      "loss": 0.5593,
      "step": 24279
    },
    {
      "epoch": 0.7458605965656007,
      "grad_norm": 0.3525792360305786,
      "learning_rate": 1.391517397892251e-05,
      "loss": 0.5785,
      "step": 24280
    },
    {
      "epoch": 0.7458913157005499,
      "grad_norm": 0.3827996253967285,
      "learning_rate": 1.391472927670296e-05,
      "loss": 0.6164,
      "step": 24281
    },
    {
      "epoch": 0.745922034835499,
      "grad_norm": 0.40191739797592163,
      "learning_rate": 1.391428456534029e-05,
      "loss": 0.5249,
      "step": 24282
    },
    {
      "epoch": 0.7459527539704482,
      "grad_norm": 0.406488835811615,
      "learning_rate": 1.3913839844835533e-05,
      "loss": 0.5658,
      "step": 24283
    },
    {
      "epoch": 0.7459834731053974,
      "grad_norm": 0.37402811646461487,
      "learning_rate": 1.391339511518973e-05,
      "loss": 0.4913,
      "step": 24284
    },
    {
      "epoch": 0.7460141922403465,
      "grad_norm": 0.4367762804031372,
      "learning_rate": 1.3912950376403917e-05,
      "loss": 0.6588,
      "step": 24285
    },
    {
      "epoch": 0.7460449113752957,
      "grad_norm": 0.3823002576828003,
      "learning_rate": 1.3912505628479136e-05,
      "loss": 0.6149,
      "step": 24286
    },
    {
      "epoch": 0.7460756305102448,
      "grad_norm": 0.45210710167884827,
      "learning_rate": 1.3912060871416428e-05,
      "loss": 0.5594,
      "step": 24287
    },
    {
      "epoch": 0.746106349645194,
      "grad_norm": 0.3894357681274414,
      "learning_rate": 1.3911616105216825e-05,
      "loss": 0.5815,
      "step": 24288
    },
    {
      "epoch": 0.7461370687801432,
      "grad_norm": 0.38125842809677124,
      "learning_rate": 1.391117132988137e-05,
      "loss": 0.5951,
      "step": 24289
    },
    {
      "epoch": 0.7461677879150923,
      "grad_norm": 0.33436718583106995,
      "learning_rate": 1.3910726545411101e-05,
      "loss": 0.5686,
      "step": 24290
    },
    {
      "epoch": 0.7461985070500414,
      "grad_norm": 0.38050565123558044,
      "learning_rate": 1.391028175180706e-05,
      "loss": 0.5491,
      "step": 24291
    },
    {
      "epoch": 0.7462292261849907,
      "grad_norm": 0.33639514446258545,
      "learning_rate": 1.3909836949070279e-05,
      "loss": 0.519,
      "step": 24292
    },
    {
      "epoch": 0.7462599453199398,
      "grad_norm": 0.36144766211509705,
      "learning_rate": 1.3909392137201803e-05,
      "loss": 0.4874,
      "step": 24293
    },
    {
      "epoch": 0.7462906644548889,
      "grad_norm": 0.36026549339294434,
      "learning_rate": 1.3908947316202668e-05,
      "loss": 0.5368,
      "step": 24294
    },
    {
      "epoch": 0.7463213835898381,
      "grad_norm": 0.37216711044311523,
      "learning_rate": 1.3908502486073912e-05,
      "loss": 0.6844,
      "step": 24295
    },
    {
      "epoch": 0.7463521027247872,
      "grad_norm": 0.3357163369655609,
      "learning_rate": 1.3908057646816577e-05,
      "loss": 0.541,
      "step": 24296
    },
    {
      "epoch": 0.7463828218597365,
      "grad_norm": 0.4882644712924957,
      "learning_rate": 1.39076127984317e-05,
      "loss": 0.5612,
      "step": 24297
    },
    {
      "epoch": 0.7464135409946856,
      "grad_norm": 0.36877331137657166,
      "learning_rate": 1.3907167940920321e-05,
      "loss": 0.6252,
      "step": 24298
    },
    {
      "epoch": 0.7464442601296347,
      "grad_norm": 0.48167529702186584,
      "learning_rate": 1.390672307428348e-05,
      "loss": 0.6573,
      "step": 24299
    },
    {
      "epoch": 0.746474979264584,
      "grad_norm": 0.9233798980712891,
      "learning_rate": 1.3906278198522211e-05,
      "loss": 0.5583,
      "step": 24300
    },
    {
      "epoch": 0.7465056983995331,
      "grad_norm": 0.3836228549480438,
      "learning_rate": 1.390583331363756e-05,
      "loss": 0.5604,
      "step": 24301
    },
    {
      "epoch": 0.7465364175344822,
      "grad_norm": 0.35402312874794006,
      "learning_rate": 1.390538841963056e-05,
      "loss": 0.5477,
      "step": 24302
    },
    {
      "epoch": 0.7465671366694314,
      "grad_norm": 0.3448857367038727,
      "learning_rate": 1.3904943516502254e-05,
      "loss": 0.5579,
      "step": 24303
    },
    {
      "epoch": 0.7465978558043805,
      "grad_norm": 0.45526695251464844,
      "learning_rate": 1.3904498604253677e-05,
      "loss": 0.5211,
      "step": 24304
    },
    {
      "epoch": 0.7466285749393297,
      "grad_norm": 0.38319921493530273,
      "learning_rate": 1.3904053682885874e-05,
      "loss": 0.5395,
      "step": 24305
    },
    {
      "epoch": 0.7466592940742789,
      "grad_norm": 0.3827822804450989,
      "learning_rate": 1.3903608752399879e-05,
      "loss": 0.5105,
      "step": 24306
    },
    {
      "epoch": 0.746690013209228,
      "grad_norm": 0.35253193974494934,
      "learning_rate": 1.3903163812796736e-05,
      "loss": 0.5889,
      "step": 24307
    },
    {
      "epoch": 0.7467207323441772,
      "grad_norm": 0.4066231846809387,
      "learning_rate": 1.3902718864077479e-05,
      "loss": 0.5719,
      "step": 24308
    },
    {
      "epoch": 0.7467514514791264,
      "grad_norm": 0.47554945945739746,
      "learning_rate": 1.3902273906243149e-05,
      "loss": 0.6278,
      "step": 24309
    },
    {
      "epoch": 0.7467821706140755,
      "grad_norm": 0.3531419336795807,
      "learning_rate": 1.3901828939294786e-05,
      "loss": 0.4772,
      "step": 24310
    },
    {
      "epoch": 0.7468128897490247,
      "grad_norm": 0.34892112016677856,
      "learning_rate": 1.3901383963233429e-05,
      "loss": 0.5204,
      "step": 24311
    },
    {
      "epoch": 0.7468436088839738,
      "grad_norm": 0.3475990295410156,
      "learning_rate": 1.3900938978060116e-05,
      "loss": 0.4722,
      "step": 24312
    },
    {
      "epoch": 0.746874328018923,
      "grad_norm": 0.353998064994812,
      "learning_rate": 1.390049398377589e-05,
      "loss": 0.5836,
      "step": 24313
    },
    {
      "epoch": 0.7469050471538722,
      "grad_norm": 0.41844791173934937,
      "learning_rate": 1.3900048980381788e-05,
      "loss": 0.568,
      "step": 24314
    },
    {
      "epoch": 0.7469357662888213,
      "grad_norm": 0.3583321273326874,
      "learning_rate": 1.3899603967878848e-05,
      "loss": 0.6561,
      "step": 24315
    },
    {
      "epoch": 0.7469664854237704,
      "grad_norm": 0.6042196750640869,
      "learning_rate": 1.3899158946268113e-05,
      "loss": 0.526,
      "step": 24316
    },
    {
      "epoch": 0.7469972045587197,
      "grad_norm": 0.32835644483566284,
      "learning_rate": 1.3898713915550617e-05,
      "loss": 0.5674,
      "step": 24317
    },
    {
      "epoch": 0.7470279236936688,
      "grad_norm": 0.3638719320297241,
      "learning_rate": 1.3898268875727403e-05,
      "loss": 0.5959,
      "step": 24318
    },
    {
      "epoch": 0.7470586428286179,
      "grad_norm": 0.4006003737449646,
      "learning_rate": 1.3897823826799513e-05,
      "loss": 0.5194,
      "step": 24319
    },
    {
      "epoch": 0.7470893619635671,
      "grad_norm": 0.39564627408981323,
      "learning_rate": 1.3897378768767977e-05,
      "loss": 0.5683,
      "step": 24320
    },
    {
      "epoch": 0.7471200810985162,
      "grad_norm": 0.40016332268714905,
      "learning_rate": 1.3896933701633846e-05,
      "loss": 0.6083,
      "step": 24321
    },
    {
      "epoch": 0.7471508002334655,
      "grad_norm": 0.40976276993751526,
      "learning_rate": 1.389648862539815e-05,
      "loss": 0.5616,
      "step": 24322
    },
    {
      "epoch": 0.7471815193684146,
      "grad_norm": 0.5104149580001831,
      "learning_rate": 1.3896043540061937e-05,
      "loss": 0.4882,
      "step": 24323
    },
    {
      "epoch": 0.7472122385033637,
      "grad_norm": 0.39010149240493774,
      "learning_rate": 1.389559844562624e-05,
      "loss": 0.5934,
      "step": 24324
    },
    {
      "epoch": 0.7472429576383129,
      "grad_norm": 0.33001795411109924,
      "learning_rate": 1.38951533420921e-05,
      "loss": 0.5194,
      "step": 24325
    },
    {
      "epoch": 0.7472736767732621,
      "grad_norm": 0.3631680905818939,
      "learning_rate": 1.389470822946056e-05,
      "loss": 0.5336,
      "step": 24326
    },
    {
      "epoch": 0.7473043959082112,
      "grad_norm": 0.33931586146354675,
      "learning_rate": 1.3894263107732656e-05,
      "loss": 0.5071,
      "step": 24327
    },
    {
      "epoch": 0.7473351150431604,
      "grad_norm": 0.46645474433898926,
      "learning_rate": 1.3893817976909424e-05,
      "loss": 0.5395,
      "step": 24328
    },
    {
      "epoch": 0.7473658341781095,
      "grad_norm": 0.37330734729766846,
      "learning_rate": 1.3893372836991912e-05,
      "loss": 0.5235,
      "step": 24329
    },
    {
      "epoch": 0.7473965533130587,
      "grad_norm": 0.38862746953964233,
      "learning_rate": 1.3892927687981157e-05,
      "loss": 0.5463,
      "step": 24330
    },
    {
      "epoch": 0.7474272724480079,
      "grad_norm": 0.3302268087863922,
      "learning_rate": 1.3892482529878194e-05,
      "loss": 0.5733,
      "step": 24331
    },
    {
      "epoch": 0.747457991582957,
      "grad_norm": 0.36956873536109924,
      "learning_rate": 1.389203736268407e-05,
      "loss": 0.5537,
      "step": 24332
    },
    {
      "epoch": 0.7474887107179062,
      "grad_norm": 0.39870357513427734,
      "learning_rate": 1.3891592186399821e-05,
      "loss": 0.5189,
      "step": 24333
    },
    {
      "epoch": 0.7475194298528554,
      "grad_norm": 0.38837099075317383,
      "learning_rate": 1.3891147001026484e-05,
      "loss": 0.5318,
      "step": 24334
    },
    {
      "epoch": 0.7475501489878045,
      "grad_norm": 0.3461623191833496,
      "learning_rate": 1.3890701806565101e-05,
      "loss": 0.5458,
      "step": 24335
    },
    {
      "epoch": 0.7475808681227537,
      "grad_norm": 0.34969550371170044,
      "learning_rate": 1.3890256603016717e-05,
      "loss": 0.5539,
      "step": 24336
    },
    {
      "epoch": 0.7476115872577028,
      "grad_norm": 0.342507541179657,
      "learning_rate": 1.3889811390382365e-05,
      "loss": 0.4535,
      "step": 24337
    },
    {
      "epoch": 0.747642306392652,
      "grad_norm": 0.3902715742588043,
      "learning_rate": 1.3889366168663082e-05,
      "loss": 0.5198,
      "step": 24338
    },
    {
      "epoch": 0.7476730255276012,
      "grad_norm": 0.3636608421802521,
      "learning_rate": 1.3888920937859917e-05,
      "loss": 0.6116,
      "step": 24339
    },
    {
      "epoch": 0.7477037446625503,
      "grad_norm": 0.3768347501754761,
      "learning_rate": 1.3888475697973904e-05,
      "loss": 0.5204,
      "step": 24340
    },
    {
      "epoch": 0.7477344637974994,
      "grad_norm": 0.32288044691085815,
      "learning_rate": 1.3888030449006087e-05,
      "loss": 0.5015,
      "step": 24341
    },
    {
      "epoch": 0.7477651829324486,
      "grad_norm": 0.38497260212898254,
      "learning_rate": 1.38875851909575e-05,
      "loss": 0.5629,
      "step": 24342
    },
    {
      "epoch": 0.7477959020673978,
      "grad_norm": 0.38514018058776855,
      "learning_rate": 1.3887139923829189e-05,
      "loss": 0.5661,
      "step": 24343
    },
    {
      "epoch": 0.747826621202347,
      "grad_norm": 0.3485569953918457,
      "learning_rate": 1.388669464762219e-05,
      "loss": 0.5973,
      "step": 24344
    },
    {
      "epoch": 0.7478573403372961,
      "grad_norm": 0.46702176332473755,
      "learning_rate": 1.3886249362337545e-05,
      "loss": 0.5317,
      "step": 24345
    },
    {
      "epoch": 0.7478880594722452,
      "grad_norm": 0.3652004897594452,
      "learning_rate": 1.3885804067976292e-05,
      "loss": 0.5208,
      "step": 24346
    },
    {
      "epoch": 0.7479187786071945,
      "grad_norm": 0.3389112949371338,
      "learning_rate": 1.3885358764539471e-05,
      "loss": 0.45,
      "step": 24347
    },
    {
      "epoch": 0.7479494977421436,
      "grad_norm": 0.3560903072357178,
      "learning_rate": 1.3884913452028126e-05,
      "loss": 0.5556,
      "step": 24348
    },
    {
      "epoch": 0.7479802168770927,
      "grad_norm": 0.3473384976387024,
      "learning_rate": 1.3884468130443292e-05,
      "loss": 0.5761,
      "step": 24349
    },
    {
      "epoch": 0.7480109360120419,
      "grad_norm": 0.37553873658180237,
      "learning_rate": 1.3884022799786015e-05,
      "loss": 0.4544,
      "step": 24350
    },
    {
      "epoch": 0.7480416551469911,
      "grad_norm": 0.3603776693344116,
      "learning_rate": 1.3883577460057327e-05,
      "loss": 0.6008,
      "step": 24351
    },
    {
      "epoch": 0.7480723742819402,
      "grad_norm": 0.36258625984191895,
      "learning_rate": 1.3883132111258276e-05,
      "loss": 0.5771,
      "step": 24352
    },
    {
      "epoch": 0.7481030934168894,
      "grad_norm": 0.3458406627178192,
      "learning_rate": 1.3882686753389898e-05,
      "loss": 0.5584,
      "step": 24353
    },
    {
      "epoch": 0.7481338125518385,
      "grad_norm": 0.3684186041355133,
      "learning_rate": 1.3882241386453232e-05,
      "loss": 0.6252,
      "step": 24354
    },
    {
      "epoch": 0.7481645316867876,
      "grad_norm": 0.41318148374557495,
      "learning_rate": 1.3881796010449323e-05,
      "loss": 0.5749,
      "step": 24355
    },
    {
      "epoch": 0.7481952508217369,
      "grad_norm": 0.37578481435775757,
      "learning_rate": 1.3881350625379206e-05,
      "loss": 0.56,
      "step": 24356
    },
    {
      "epoch": 0.748225969956686,
      "grad_norm": 0.546559751033783,
      "learning_rate": 1.3880905231243925e-05,
      "loss": 0.5834,
      "step": 24357
    },
    {
      "epoch": 0.7482566890916352,
      "grad_norm": 0.38837581872940063,
      "learning_rate": 1.3880459828044517e-05,
      "loss": 0.5899,
      "step": 24358
    },
    {
      "epoch": 0.7482874082265843,
      "grad_norm": 0.36365386843681335,
      "learning_rate": 1.3880014415782025e-05,
      "loss": 0.5607,
      "step": 24359
    },
    {
      "epoch": 0.7483181273615335,
      "grad_norm": 0.38652753829956055,
      "learning_rate": 1.3879568994457491e-05,
      "loss": 0.5775,
      "step": 24360
    },
    {
      "epoch": 0.7483488464964827,
      "grad_norm": 0.3725283145904541,
      "learning_rate": 1.387912356407195e-05,
      "loss": 0.5322,
      "step": 24361
    },
    {
      "epoch": 0.7483795656314318,
      "grad_norm": 0.3718215227127075,
      "learning_rate": 1.3878678124626444e-05,
      "loss": 0.5383,
      "step": 24362
    },
    {
      "epoch": 0.7484102847663809,
      "grad_norm": 0.3383180499076843,
      "learning_rate": 1.3878232676122017e-05,
      "loss": 0.5336,
      "step": 24363
    },
    {
      "epoch": 0.7484410039013302,
      "grad_norm": 0.40451622009277344,
      "learning_rate": 1.3877787218559707e-05,
      "loss": 0.5902,
      "step": 24364
    },
    {
      "epoch": 0.7484717230362793,
      "grad_norm": 0.37394216656684875,
      "learning_rate": 1.387734175194055e-05,
      "loss": 0.5041,
      "step": 24365
    },
    {
      "epoch": 0.7485024421712284,
      "grad_norm": 0.3246656358242035,
      "learning_rate": 1.3876896276265593e-05,
      "loss": 0.5897,
      "step": 24366
    },
    {
      "epoch": 0.7485331613061776,
      "grad_norm": 0.34329280257225037,
      "learning_rate": 1.3876450791535874e-05,
      "loss": 0.544,
      "step": 24367
    },
    {
      "epoch": 0.7485638804411268,
      "grad_norm": 0.3985111117362976,
      "learning_rate": 1.3876005297752433e-05,
      "loss": 0.5377,
      "step": 24368
    },
    {
      "epoch": 0.748594599576076,
      "grad_norm": 0.36527955532073975,
      "learning_rate": 1.3875559794916312e-05,
      "loss": 0.5708,
      "step": 24369
    },
    {
      "epoch": 0.7486253187110251,
      "grad_norm": 0.3905005156993866,
      "learning_rate": 1.387511428302855e-05,
      "loss": 0.5287,
      "step": 24370
    },
    {
      "epoch": 0.7486560378459742,
      "grad_norm": 0.38877350091934204,
      "learning_rate": 1.3874668762090188e-05,
      "loss": 0.5733,
      "step": 24371
    },
    {
      "epoch": 0.7486867569809235,
      "grad_norm": 0.36978715658187866,
      "learning_rate": 1.3874223232102267e-05,
      "loss": 0.5758,
      "step": 24372
    },
    {
      "epoch": 0.7487174761158726,
      "grad_norm": 0.33545827865600586,
      "learning_rate": 1.3873777693065827e-05,
      "loss": 0.5403,
      "step": 24373
    },
    {
      "epoch": 0.7487481952508217,
      "grad_norm": 0.9636921286582947,
      "learning_rate": 1.3873332144981906e-05,
      "loss": 0.5805,
      "step": 24374
    },
    {
      "epoch": 0.7487789143857709,
      "grad_norm": 0.41313403844833374,
      "learning_rate": 1.387288658785155e-05,
      "loss": 0.5198,
      "step": 24375
    },
    {
      "epoch": 0.74880963352072,
      "grad_norm": 0.3611474633216858,
      "learning_rate": 1.3872441021675795e-05,
      "loss": 0.5021,
      "step": 24376
    },
    {
      "epoch": 0.7488403526556692,
      "grad_norm": 0.40582749247550964,
      "learning_rate": 1.3871995446455686e-05,
      "loss": 0.6318,
      "step": 24377
    },
    {
      "epoch": 0.7488710717906184,
      "grad_norm": 0.36131855845451355,
      "learning_rate": 1.387154986219226e-05,
      "loss": 0.5924,
      "step": 24378
    },
    {
      "epoch": 0.7489017909255675,
      "grad_norm": 0.3411530554294586,
      "learning_rate": 1.387110426888656e-05,
      "loss": 0.4545,
      "step": 24379
    },
    {
      "epoch": 0.7489325100605166,
      "grad_norm": 0.3383624851703644,
      "learning_rate": 1.3870658666539622e-05,
      "loss": 0.5916,
      "step": 24380
    },
    {
      "epoch": 0.7489632291954659,
      "grad_norm": 0.40634238719940186,
      "learning_rate": 1.3870213055152494e-05,
      "loss": 0.6255,
      "step": 24381
    },
    {
      "epoch": 0.748993948330415,
      "grad_norm": 0.4075835645198822,
      "learning_rate": 1.3869767434726213e-05,
      "loss": 0.5317,
      "step": 24382
    },
    {
      "epoch": 0.7490246674653642,
      "grad_norm": 0.3464733362197876,
      "learning_rate": 1.3869321805261814e-05,
      "loss": 0.5199,
      "step": 24383
    },
    {
      "epoch": 0.7490553866003133,
      "grad_norm": 0.37293216586112976,
      "learning_rate": 1.3868876166760351e-05,
      "loss": 0.536,
      "step": 24384
    },
    {
      "epoch": 0.7490861057352625,
      "grad_norm": 0.36385083198547363,
      "learning_rate": 1.3868430519222855e-05,
      "loss": 0.5444,
      "step": 24385
    },
    {
      "epoch": 0.7491168248702117,
      "grad_norm": 0.365121990442276,
      "learning_rate": 1.386798486265037e-05,
      "loss": 0.527,
      "step": 24386
    },
    {
      "epoch": 0.7491475440051608,
      "grad_norm": 0.41637900471687317,
      "learning_rate": 1.3867539197043935e-05,
      "loss": 0.5266,
      "step": 24387
    },
    {
      "epoch": 0.7491782631401099,
      "grad_norm": 0.3379952907562256,
      "learning_rate": 1.3867093522404593e-05,
      "loss": 0.5258,
      "step": 24388
    },
    {
      "epoch": 0.7492089822750592,
      "grad_norm": 0.42640504240989685,
      "learning_rate": 1.3866647838733385e-05,
      "loss": 0.5838,
      "step": 24389
    },
    {
      "epoch": 0.7492397014100083,
      "grad_norm": 0.35216599702835083,
      "learning_rate": 1.3866202146031348e-05,
      "loss": 0.537,
      "step": 24390
    },
    {
      "epoch": 0.7492704205449574,
      "grad_norm": 0.37318122386932373,
      "learning_rate": 1.386575644429953e-05,
      "loss": 0.5294,
      "step": 24391
    },
    {
      "epoch": 0.7493011396799066,
      "grad_norm": 0.35161611437797546,
      "learning_rate": 1.3865310733538964e-05,
      "loss": 0.572,
      "step": 24392
    },
    {
      "epoch": 0.7493318588148558,
      "grad_norm": 0.3731966018676758,
      "learning_rate": 1.3864865013750697e-05,
      "loss": 0.5878,
      "step": 24393
    },
    {
      "epoch": 0.749362577949805,
      "grad_norm": 0.3706686496734619,
      "learning_rate": 1.3864419284935765e-05,
      "loss": 0.56,
      "step": 24394
    },
    {
      "epoch": 0.7493932970847541,
      "grad_norm": 0.3443260192871094,
      "learning_rate": 1.3863973547095215e-05,
      "loss": 0.5087,
      "step": 24395
    },
    {
      "epoch": 0.7494240162197032,
      "grad_norm": 0.3402037024497986,
      "learning_rate": 1.3863527800230085e-05,
      "loss": 0.5129,
      "step": 24396
    },
    {
      "epoch": 0.7494547353546525,
      "grad_norm": 0.3844793140888214,
      "learning_rate": 1.3863082044341416e-05,
      "loss": 0.5278,
      "step": 24397
    },
    {
      "epoch": 0.7494854544896016,
      "grad_norm": 0.3740577697753906,
      "learning_rate": 1.3862636279430245e-05,
      "loss": 0.5471,
      "step": 24398
    },
    {
      "epoch": 0.7495161736245507,
      "grad_norm": 0.4002687633037567,
      "learning_rate": 1.3862190505497623e-05,
      "loss": 0.5716,
      "step": 24399
    },
    {
      "epoch": 0.7495468927594999,
      "grad_norm": 0.3604086935520172,
      "learning_rate": 1.3861744722544583e-05,
      "loss": 0.5864,
      "step": 24400
    },
    {
      "epoch": 0.749577611894449,
      "grad_norm": 0.4549020528793335,
      "learning_rate": 1.3861298930572165e-05,
      "loss": 0.5397,
      "step": 24401
    },
    {
      "epoch": 0.7496083310293982,
      "grad_norm": 0.40628865361213684,
      "learning_rate": 1.3860853129581417e-05,
      "loss": 0.5421,
      "step": 24402
    },
    {
      "epoch": 0.7496390501643474,
      "grad_norm": 0.34933483600616455,
      "learning_rate": 1.3860407319573377e-05,
      "loss": 0.4911,
      "step": 24403
    },
    {
      "epoch": 0.7496697692992965,
      "grad_norm": 0.39511898159980774,
      "learning_rate": 1.3859961500549087e-05,
      "loss": 0.6335,
      "step": 24404
    },
    {
      "epoch": 0.7497004884342456,
      "grad_norm": 0.39820635318756104,
      "learning_rate": 1.3859515672509587e-05,
      "loss": 0.6179,
      "step": 24405
    },
    {
      "epoch": 0.7497312075691949,
      "grad_norm": 0.3481858968734741,
      "learning_rate": 1.3859069835455915e-05,
      "loss": 0.5489,
      "step": 24406
    },
    {
      "epoch": 0.749761926704144,
      "grad_norm": 0.4438067674636841,
      "learning_rate": 1.3858623989389119e-05,
      "loss": 0.5729,
      "step": 24407
    },
    {
      "epoch": 0.7497926458390932,
      "grad_norm": 0.3442665934562683,
      "learning_rate": 1.3858178134310235e-05,
      "loss": 0.526,
      "step": 24408
    },
    {
      "epoch": 0.7498233649740423,
      "grad_norm": 0.3528478443622589,
      "learning_rate": 1.385773227022031e-05,
      "loss": 0.5409,
      "step": 24409
    },
    {
      "epoch": 0.7498540841089915,
      "grad_norm": 0.37678536772727966,
      "learning_rate": 1.385728639712038e-05,
      "loss": 0.5374,
      "step": 24410
    },
    {
      "epoch": 0.7498848032439407,
      "grad_norm": 0.3674841523170471,
      "learning_rate": 1.3856840515011489e-05,
      "loss": 0.5634,
      "step": 24411
    },
    {
      "epoch": 0.7499155223788898,
      "grad_norm": 0.4009157121181488,
      "learning_rate": 1.3856394623894676e-05,
      "loss": 0.5289,
      "step": 24412
    },
    {
      "epoch": 0.7499462415138389,
      "grad_norm": 0.3945879638195038,
      "learning_rate": 1.3855948723770987e-05,
      "loss": 0.6403,
      "step": 24413
    },
    {
      "epoch": 0.7499769606487882,
      "grad_norm": 0.36867228150367737,
      "learning_rate": 1.3855502814641457e-05,
      "loss": 0.6203,
      "step": 24414
    },
    {
      "epoch": 0.7500076797837373,
      "grad_norm": 0.37660765647888184,
      "learning_rate": 1.3855056896507132e-05,
      "loss": 0.5586,
      "step": 24415
    },
    {
      "epoch": 0.7500383989186864,
      "grad_norm": 0.3432517647743225,
      "learning_rate": 1.3854610969369055e-05,
      "loss": 0.5546,
      "step": 24416
    },
    {
      "epoch": 0.7500691180536356,
      "grad_norm": 0.3637527823448181,
      "learning_rate": 1.385416503322826e-05,
      "loss": 0.5536,
      "step": 24417
    },
    {
      "epoch": 0.7500998371885848,
      "grad_norm": 0.3998635411262512,
      "learning_rate": 1.3853719088085797e-05,
      "loss": 0.5822,
      "step": 24418
    },
    {
      "epoch": 0.750130556323534,
      "grad_norm": 0.37222814559936523,
      "learning_rate": 1.38532731339427e-05,
      "loss": 0.5312,
      "step": 24419
    },
    {
      "epoch": 0.7501612754584831,
      "grad_norm": 0.35037025809288025,
      "learning_rate": 1.3852827170800019e-05,
      "loss": 0.6126,
      "step": 24420
    },
    {
      "epoch": 0.7501919945934322,
      "grad_norm": 0.4001917541027069,
      "learning_rate": 1.3852381198658789e-05,
      "loss": 0.5514,
      "step": 24421
    },
    {
      "epoch": 0.7502227137283815,
      "grad_norm": 0.47321292757987976,
      "learning_rate": 1.3851935217520054e-05,
      "loss": 0.6186,
      "step": 24422
    },
    {
      "epoch": 0.7502534328633306,
      "grad_norm": 0.3437284827232361,
      "learning_rate": 1.3851489227384857e-05,
      "loss": 0.5936,
      "step": 24423
    },
    {
      "epoch": 0.7502841519982797,
      "grad_norm": 0.3314666450023651,
      "learning_rate": 1.3851043228254235e-05,
      "loss": 0.542,
      "step": 24424
    },
    {
      "epoch": 0.7503148711332289,
      "grad_norm": 0.33777546882629395,
      "learning_rate": 1.3850597220129234e-05,
      "loss": 0.494,
      "step": 24425
    },
    {
      "epoch": 0.750345590268178,
      "grad_norm": 0.3433629870414734,
      "learning_rate": 1.3850151203010893e-05,
      "loss": 0.526,
      "step": 24426
    },
    {
      "epoch": 0.7503763094031272,
      "grad_norm": 0.37354645133018494,
      "learning_rate": 1.3849705176900259e-05,
      "loss": 0.5112,
      "step": 24427
    },
    {
      "epoch": 0.7504070285380764,
      "grad_norm": 0.39258939027786255,
      "learning_rate": 1.3849259141798366e-05,
      "loss": 0.5191,
      "step": 24428
    },
    {
      "epoch": 0.7504377476730255,
      "grad_norm": 0.4133131206035614,
      "learning_rate": 1.3848813097706261e-05,
      "loss": 0.5875,
      "step": 24429
    },
    {
      "epoch": 0.7504684668079746,
      "grad_norm": 0.4157048463821411,
      "learning_rate": 1.3848367044624981e-05,
      "loss": 0.5749,
      "step": 24430
    },
    {
      "epoch": 0.7504991859429239,
      "grad_norm": 0.4071829617023468,
      "learning_rate": 1.3847920982555576e-05,
      "loss": 0.5361,
      "step": 24431
    },
    {
      "epoch": 0.750529905077873,
      "grad_norm": 0.3859230577945709,
      "learning_rate": 1.384747491149908e-05,
      "loss": 0.5289,
      "step": 24432
    },
    {
      "epoch": 0.7505606242128222,
      "grad_norm": 0.37909626960754395,
      "learning_rate": 1.3847028831456538e-05,
      "loss": 0.6059,
      "step": 24433
    },
    {
      "epoch": 0.7505913433477713,
      "grad_norm": 0.3416121304035187,
      "learning_rate": 1.384658274242899e-05,
      "loss": 0.466,
      "step": 24434
    },
    {
      "epoch": 0.7506220624827205,
      "grad_norm": 0.3269718885421753,
      "learning_rate": 1.3846136644417482e-05,
      "loss": 0.5806,
      "step": 24435
    },
    {
      "epoch": 0.7506527816176697,
      "grad_norm": 0.3470291495323181,
      "learning_rate": 1.3845690537423053e-05,
      "loss": 0.4903,
      "step": 24436
    },
    {
      "epoch": 0.7506835007526188,
      "grad_norm": 0.33253639936447144,
      "learning_rate": 1.3845244421446745e-05,
      "loss": 0.5293,
      "step": 24437
    },
    {
      "epoch": 0.7507142198875679,
      "grad_norm": 0.39228153228759766,
      "learning_rate": 1.3844798296489597e-05,
      "loss": 0.63,
      "step": 24438
    },
    {
      "epoch": 0.7507449390225172,
      "grad_norm": 0.35503003001213074,
      "learning_rate": 1.3844352162552654e-05,
      "loss": 0.5931,
      "step": 24439
    },
    {
      "epoch": 0.7507756581574663,
      "grad_norm": 0.33779534697532654,
      "learning_rate": 1.384390601963696e-05,
      "loss": 0.492,
      "step": 24440
    },
    {
      "epoch": 0.7508063772924154,
      "grad_norm": 0.33748894929885864,
      "learning_rate": 1.3843459867743558e-05,
      "loss": 0.5609,
      "step": 24441
    },
    {
      "epoch": 0.7508370964273646,
      "grad_norm": 0.385783314704895,
      "learning_rate": 1.3843013706873486e-05,
      "loss": 0.4792,
      "step": 24442
    },
    {
      "epoch": 0.7508678155623137,
      "grad_norm": 0.3793172538280487,
      "learning_rate": 1.3842567537027784e-05,
      "loss": 0.6186,
      "step": 24443
    },
    {
      "epoch": 0.750898534697263,
      "grad_norm": 0.3409092426300049,
      "learning_rate": 1.3842121358207499e-05,
      "loss": 0.5227,
      "step": 24444
    },
    {
      "epoch": 0.7509292538322121,
      "grad_norm": 0.3695496916770935,
      "learning_rate": 1.3841675170413673e-05,
      "loss": 0.6031,
      "step": 24445
    },
    {
      "epoch": 0.7509599729671612,
      "grad_norm": 0.37409430742263794,
      "learning_rate": 1.3841228973647343e-05,
      "loss": 0.5743,
      "step": 24446
    },
    {
      "epoch": 0.7509906921021104,
      "grad_norm": 0.3493788242340088,
      "learning_rate": 1.3840782767909555e-05,
      "loss": 0.5305,
      "step": 24447
    },
    {
      "epoch": 0.7510214112370596,
      "grad_norm": 0.3789497911930084,
      "learning_rate": 1.3840336553201352e-05,
      "loss": 0.5749,
      "step": 24448
    },
    {
      "epoch": 0.7510521303720087,
      "grad_norm": 0.373190701007843,
      "learning_rate": 1.3839890329523776e-05,
      "loss": 0.499,
      "step": 24449
    },
    {
      "epoch": 0.7510828495069579,
      "grad_norm": 0.3294575810432434,
      "learning_rate": 1.3839444096877864e-05,
      "loss": 0.4954,
      "step": 24450
    },
    {
      "epoch": 0.751113568641907,
      "grad_norm": 0.3312954306602478,
      "learning_rate": 1.3838997855264663e-05,
      "loss": 0.5499,
      "step": 24451
    },
    {
      "epoch": 0.7511442877768562,
      "grad_norm": 0.3626779317855835,
      "learning_rate": 1.3838551604685218e-05,
      "loss": 0.573,
      "step": 24452
    },
    {
      "epoch": 0.7511750069118054,
      "grad_norm": 0.3366241455078125,
      "learning_rate": 1.3838105345140565e-05,
      "loss": 0.5401,
      "step": 24453
    },
    {
      "epoch": 0.7512057260467545,
      "grad_norm": 0.3683604598045349,
      "learning_rate": 1.3837659076631751e-05,
      "loss": 0.573,
      "step": 24454
    },
    {
      "epoch": 0.7512364451817037,
      "grad_norm": 0.4167405068874359,
      "learning_rate": 1.3837212799159812e-05,
      "loss": 0.5266,
      "step": 24455
    },
    {
      "epoch": 0.7512671643166529,
      "grad_norm": 0.6818681359291077,
      "learning_rate": 1.3836766512725797e-05,
      "loss": 0.6535,
      "step": 24456
    },
    {
      "epoch": 0.751297883451602,
      "grad_norm": 0.43205317854881287,
      "learning_rate": 1.3836320217330746e-05,
      "loss": 0.5403,
      "step": 24457
    },
    {
      "epoch": 0.7513286025865512,
      "grad_norm": 0.3573950231075287,
      "learning_rate": 1.38358739129757e-05,
      "loss": 0.5571,
      "step": 24458
    },
    {
      "epoch": 0.7513593217215003,
      "grad_norm": 0.34494394063949585,
      "learning_rate": 1.3835427599661707e-05,
      "loss": 0.4658,
      "step": 24459
    },
    {
      "epoch": 0.7513900408564494,
      "grad_norm": 0.35267648100852966,
      "learning_rate": 1.3834981277389799e-05,
      "loss": 0.509,
      "step": 24460
    },
    {
      "epoch": 0.7514207599913987,
      "grad_norm": 0.33242514729499817,
      "learning_rate": 1.3834534946161028e-05,
      "loss": 0.5118,
      "step": 24461
    },
    {
      "epoch": 0.7514514791263478,
      "grad_norm": 0.3556055426597595,
      "learning_rate": 1.383408860597643e-05,
      "loss": 0.5656,
      "step": 24462
    },
    {
      "epoch": 0.7514821982612969,
      "grad_norm": 0.39833834767341614,
      "learning_rate": 1.3833642256837055e-05,
      "loss": 0.6123,
      "step": 24463
    },
    {
      "epoch": 0.7515129173962461,
      "grad_norm": 0.3810199201107025,
      "learning_rate": 1.3833195898743936e-05,
      "loss": 0.5987,
      "step": 24464
    },
    {
      "epoch": 0.7515436365311953,
      "grad_norm": 0.3774643838405609,
      "learning_rate": 1.3832749531698122e-05,
      "loss": 0.5641,
      "step": 24465
    },
    {
      "epoch": 0.7515743556661444,
      "grad_norm": 0.34536612033843994,
      "learning_rate": 1.3832303155700654e-05,
      "loss": 0.5235,
      "step": 24466
    },
    {
      "epoch": 0.7516050748010936,
      "grad_norm": 0.37235188484191895,
      "learning_rate": 1.3831856770752574e-05,
      "loss": 0.5406,
      "step": 24467
    },
    {
      "epoch": 0.7516357939360427,
      "grad_norm": 0.34628406167030334,
      "learning_rate": 1.3831410376854928e-05,
      "loss": 0.5772,
      "step": 24468
    },
    {
      "epoch": 0.751666513070992,
      "grad_norm": 0.35040482878685,
      "learning_rate": 1.3830963974008752e-05,
      "loss": 0.5354,
      "step": 24469
    },
    {
      "epoch": 0.7516972322059411,
      "grad_norm": 0.4151204228401184,
      "learning_rate": 1.3830517562215094e-05,
      "loss": 0.5631,
      "step": 24470
    },
    {
      "epoch": 0.7517279513408902,
      "grad_norm": 0.3208516240119934,
      "learning_rate": 1.3830071141474993e-05,
      "loss": 0.5509,
      "step": 24471
    },
    {
      "epoch": 0.7517586704758394,
      "grad_norm": 0.4101223945617676,
      "learning_rate": 1.3829624711789493e-05,
      "loss": 0.5433,
      "step": 24472
    },
    {
      "epoch": 0.7517893896107886,
      "grad_norm": 0.4279378354549408,
      "learning_rate": 1.3829178273159638e-05,
      "loss": 0.603,
      "step": 24473
    },
    {
      "epoch": 0.7518201087457377,
      "grad_norm": 0.3629553020000458,
      "learning_rate": 1.3828731825586468e-05,
      "loss": 0.6246,
      "step": 24474
    },
    {
      "epoch": 0.7518508278806869,
      "grad_norm": 0.34759655594825745,
      "learning_rate": 1.382828536907103e-05,
      "loss": 0.5519,
      "step": 24475
    },
    {
      "epoch": 0.751881547015636,
      "grad_norm": 0.34908056259155273,
      "learning_rate": 1.382783890361436e-05,
      "loss": 0.6737,
      "step": 24476
    },
    {
      "epoch": 0.7519122661505852,
      "grad_norm": 0.36967170238494873,
      "learning_rate": 1.3827392429217512e-05,
      "loss": 0.5436,
      "step": 24477
    },
    {
      "epoch": 0.7519429852855344,
      "grad_norm": 0.3748249411582947,
      "learning_rate": 1.3826945945881515e-05,
      "loss": 0.5705,
      "step": 24478
    },
    {
      "epoch": 0.7519737044204835,
      "grad_norm": 0.3832767903804779,
      "learning_rate": 1.3826499453607422e-05,
      "loss": 0.5568,
      "step": 24479
    },
    {
      "epoch": 0.7520044235554327,
      "grad_norm": 0.36699342727661133,
      "learning_rate": 1.3826052952396272e-05,
      "loss": 0.4963,
      "step": 24480
    },
    {
      "epoch": 0.7520351426903819,
      "grad_norm": 0.3853037655353546,
      "learning_rate": 1.3825606442249109e-05,
      "loss": 0.616,
      "step": 24481
    },
    {
      "epoch": 0.752065861825331,
      "grad_norm": 0.37182191014289856,
      "learning_rate": 1.3825159923166971e-05,
      "loss": 0.5073,
      "step": 24482
    },
    {
      "epoch": 0.7520965809602802,
      "grad_norm": 0.37940096855163574,
      "learning_rate": 1.3824713395150911e-05,
      "loss": 0.5432,
      "step": 24483
    },
    {
      "epoch": 0.7521273000952293,
      "grad_norm": 0.36670270562171936,
      "learning_rate": 1.382426685820196e-05,
      "loss": 0.5638,
      "step": 24484
    },
    {
      "epoch": 0.7521580192301784,
      "grad_norm": 0.3801240622997284,
      "learning_rate": 1.3823820312321171e-05,
      "loss": 0.5433,
      "step": 24485
    },
    {
      "epoch": 0.7521887383651277,
      "grad_norm": 0.36510324478149414,
      "learning_rate": 1.382337375750958e-05,
      "loss": 0.5526,
      "step": 24486
    },
    {
      "epoch": 0.7522194575000768,
      "grad_norm": 0.3597426116466522,
      "learning_rate": 1.3822927193768233e-05,
      "loss": 0.5513,
      "step": 24487
    },
    {
      "epoch": 0.7522501766350259,
      "grad_norm": 0.4063152074813843,
      "learning_rate": 1.3822480621098173e-05,
      "loss": 0.5463,
      "step": 24488
    },
    {
      "epoch": 0.7522808957699751,
      "grad_norm": 0.34734684228897095,
      "learning_rate": 1.382203403950044e-05,
      "loss": 0.6209,
      "step": 24489
    },
    {
      "epoch": 0.7523116149049243,
      "grad_norm": 0.3686735928058624,
      "learning_rate": 1.3821587448976084e-05,
      "loss": 0.4903,
      "step": 24490
    },
    {
      "epoch": 0.7523423340398734,
      "grad_norm": 0.37596747279167175,
      "learning_rate": 1.382114084952614e-05,
      "loss": 0.5626,
      "step": 24491
    },
    {
      "epoch": 0.7523730531748226,
      "grad_norm": 0.3711581230163574,
      "learning_rate": 1.3820694241151656e-05,
      "loss": 0.4962,
      "step": 24492
    },
    {
      "epoch": 0.7524037723097717,
      "grad_norm": 0.4185270369052887,
      "learning_rate": 1.3820247623853673e-05,
      "loss": 0.5966,
      "step": 24493
    },
    {
      "epoch": 0.752434491444721,
      "grad_norm": 0.369276225566864,
      "learning_rate": 1.3819800997633235e-05,
      "loss": 0.5251,
      "step": 24494
    },
    {
      "epoch": 0.7524652105796701,
      "grad_norm": 0.3428132236003876,
      "learning_rate": 1.3819354362491386e-05,
      "loss": 0.4765,
      "step": 24495
    },
    {
      "epoch": 0.7524959297146192,
      "grad_norm": 0.3991839587688446,
      "learning_rate": 1.3818907718429168e-05,
      "loss": 0.6353,
      "step": 24496
    },
    {
      "epoch": 0.7525266488495684,
      "grad_norm": 0.3577301800251007,
      "learning_rate": 1.3818461065447623e-05,
      "loss": 0.5528,
      "step": 24497
    },
    {
      "epoch": 0.7525573679845176,
      "grad_norm": 0.45897889137268066,
      "learning_rate": 1.3818014403547798e-05,
      "loss": 0.5312,
      "step": 24498
    },
    {
      "epoch": 0.7525880871194667,
      "grad_norm": 0.39265623688697815,
      "learning_rate": 1.3817567732730733e-05,
      "loss": 0.5316,
      "step": 24499
    },
    {
      "epoch": 0.7526188062544159,
      "grad_norm": 0.3536539077758789,
      "learning_rate": 1.381712105299747e-05,
      "loss": 0.5584,
      "step": 24500
    },
    {
      "epoch": 0.752649525389365,
      "grad_norm": 0.3660946190357208,
      "learning_rate": 1.3816674364349057e-05,
      "loss": 0.5149,
      "step": 24501
    },
    {
      "epoch": 0.7526802445243141,
      "grad_norm": 0.5963734984397888,
      "learning_rate": 1.3816227666786532e-05,
      "loss": 0.5684,
      "step": 24502
    },
    {
      "epoch": 0.7527109636592634,
      "grad_norm": 0.38786062598228455,
      "learning_rate": 1.3815780960310944e-05,
      "loss": 0.4734,
      "step": 24503
    },
    {
      "epoch": 0.7527416827942125,
      "grad_norm": 0.38837239146232605,
      "learning_rate": 1.381533424492333e-05,
      "loss": 0.5969,
      "step": 24504
    },
    {
      "epoch": 0.7527724019291617,
      "grad_norm": 0.40064579248428345,
      "learning_rate": 1.3814887520624735e-05,
      "loss": 0.5334,
      "step": 24505
    },
    {
      "epoch": 0.7528031210641108,
      "grad_norm": 0.3839111626148224,
      "learning_rate": 1.3814440787416208e-05,
      "loss": 0.5176,
      "step": 24506
    },
    {
      "epoch": 0.75283384019906,
      "grad_norm": 0.37009263038635254,
      "learning_rate": 1.3813994045298787e-05,
      "loss": 0.5247,
      "step": 24507
    },
    {
      "epoch": 0.7528645593340092,
      "grad_norm": 0.33917373418807983,
      "learning_rate": 1.3813547294273514e-05,
      "loss": 0.5768,
      "step": 24508
    },
    {
      "epoch": 0.7528952784689583,
      "grad_norm": 0.43069562315940857,
      "learning_rate": 1.3813100534341438e-05,
      "loss": 0.5575,
      "step": 24509
    },
    {
      "epoch": 0.7529259976039074,
      "grad_norm": 0.3448360860347748,
      "learning_rate": 1.3812653765503599e-05,
      "loss": 0.5152,
      "step": 24510
    },
    {
      "epoch": 0.7529567167388567,
      "grad_norm": 0.3584466874599457,
      "learning_rate": 1.3812206987761037e-05,
      "loss": 0.5398,
      "step": 24511
    },
    {
      "epoch": 0.7529874358738058,
      "grad_norm": 0.3485628366470337,
      "learning_rate": 1.3811760201114801e-05,
      "loss": 0.57,
      "step": 24512
    },
    {
      "epoch": 0.7530181550087549,
      "grad_norm": 0.3885654807090759,
      "learning_rate": 1.3811313405565936e-05,
      "loss": 0.5271,
      "step": 24513
    },
    {
      "epoch": 0.7530488741437041,
      "grad_norm": 0.3524733781814575,
      "learning_rate": 1.381086660111548e-05,
      "loss": 0.5264,
      "step": 24514
    },
    {
      "epoch": 0.7530795932786533,
      "grad_norm": 0.4210370182991028,
      "learning_rate": 1.381041978776448e-05,
      "loss": 0.5286,
      "step": 24515
    },
    {
      "epoch": 0.7531103124136024,
      "grad_norm": 0.39191532135009766,
      "learning_rate": 1.3809972965513976e-05,
      "loss": 0.5819,
      "step": 24516
    },
    {
      "epoch": 0.7531410315485516,
      "grad_norm": 0.3951699137687683,
      "learning_rate": 1.3809526134365016e-05,
      "loss": 0.5019,
      "step": 24517
    },
    {
      "epoch": 0.7531717506835007,
      "grad_norm": 0.42438504099845886,
      "learning_rate": 1.3809079294318642e-05,
      "loss": 0.4782,
      "step": 24518
    },
    {
      "epoch": 0.75320246981845,
      "grad_norm": 1.2248278856277466,
      "learning_rate": 1.3808632445375898e-05,
      "loss": 0.5372,
      "step": 24519
    },
    {
      "epoch": 0.7532331889533991,
      "grad_norm": 0.33487367630004883,
      "learning_rate": 1.3808185587537826e-05,
      "loss": 0.5579,
      "step": 24520
    },
    {
      "epoch": 0.7532639080883482,
      "grad_norm": 0.38232874870300293,
      "learning_rate": 1.380773872080547e-05,
      "loss": 0.6079,
      "step": 24521
    },
    {
      "epoch": 0.7532946272232974,
      "grad_norm": 0.5000663995742798,
      "learning_rate": 1.3807291845179876e-05,
      "loss": 0.5064,
      "step": 24522
    },
    {
      "epoch": 0.7533253463582466,
      "grad_norm": 0.33801260590553284,
      "learning_rate": 1.3806844960662082e-05,
      "loss": 0.5336,
      "step": 24523
    },
    {
      "epoch": 0.7533560654931957,
      "grad_norm": 0.4013778269290924,
      "learning_rate": 1.3806398067253139e-05,
      "loss": 0.5409,
      "step": 24524
    },
    {
      "epoch": 0.7533867846281449,
      "grad_norm": 0.3453293442726135,
      "learning_rate": 1.3805951164954089e-05,
      "loss": 0.6563,
      "step": 24525
    },
    {
      "epoch": 0.753417503763094,
      "grad_norm": 0.4392503798007965,
      "learning_rate": 1.3805504253765971e-05,
      "loss": 0.7089,
      "step": 24526
    },
    {
      "epoch": 0.7534482228980431,
      "grad_norm": 0.33924582600593567,
      "learning_rate": 1.3805057333689832e-05,
      "loss": 0.5807,
      "step": 24527
    },
    {
      "epoch": 0.7534789420329924,
      "grad_norm": 0.3394757807254791,
      "learning_rate": 1.3804610404726719e-05,
      "loss": 0.5976,
      "step": 24528
    },
    {
      "epoch": 0.7535096611679415,
      "grad_norm": 0.4053260087966919,
      "learning_rate": 1.3804163466877669e-05,
      "loss": 0.5679,
      "step": 24529
    },
    {
      "epoch": 0.7535403803028907,
      "grad_norm": 0.3554181456565857,
      "learning_rate": 1.380371652014373e-05,
      "loss": 0.5991,
      "step": 24530
    },
    {
      "epoch": 0.7535710994378398,
      "grad_norm": 0.3307189643383026,
      "learning_rate": 1.3803269564525947e-05,
      "loss": 0.4754,
      "step": 24531
    },
    {
      "epoch": 0.753601818572789,
      "grad_norm": 0.4120634198188782,
      "learning_rate": 1.3802822600025361e-05,
      "loss": 0.5392,
      "step": 24532
    },
    {
      "epoch": 0.7536325377077382,
      "grad_norm": 0.377346932888031,
      "learning_rate": 1.3802375626643021e-05,
      "loss": 0.6105,
      "step": 24533
    },
    {
      "epoch": 0.7536632568426873,
      "grad_norm": 0.368417352437973,
      "learning_rate": 1.3801928644379963e-05,
      "loss": 0.5645,
      "step": 24534
    },
    {
      "epoch": 0.7536939759776364,
      "grad_norm": 0.3645906150341034,
      "learning_rate": 1.3801481653237236e-05,
      "loss": 0.6171,
      "step": 24535
    },
    {
      "epoch": 0.7537246951125857,
      "grad_norm": 0.3928091824054718,
      "learning_rate": 1.3801034653215883e-05,
      "loss": 0.549,
      "step": 24536
    },
    {
      "epoch": 0.7537554142475348,
      "grad_norm": 0.38169705867767334,
      "learning_rate": 1.3800587644316949e-05,
      "loss": 0.6071,
      "step": 24537
    },
    {
      "epoch": 0.7537861333824839,
      "grad_norm": 0.3516536355018616,
      "learning_rate": 1.3800140626541479e-05,
      "loss": 0.5861,
      "step": 24538
    },
    {
      "epoch": 0.7538168525174331,
      "grad_norm": 0.3577292263507843,
      "learning_rate": 1.379969359989051e-05,
      "loss": 0.5693,
      "step": 24539
    },
    {
      "epoch": 0.7538475716523823,
      "grad_norm": 0.7510275840759277,
      "learning_rate": 1.3799246564365096e-05,
      "loss": 0.5293,
      "step": 24540
    },
    {
      "epoch": 0.7538782907873315,
      "grad_norm": 0.37442976236343384,
      "learning_rate": 1.3798799519966274e-05,
      "loss": 0.537,
      "step": 24541
    },
    {
      "epoch": 0.7539090099222806,
      "grad_norm": 0.3962199091911316,
      "learning_rate": 1.3798352466695093e-05,
      "loss": 0.4867,
      "step": 24542
    },
    {
      "epoch": 0.7539397290572297,
      "grad_norm": 0.3865078091621399,
      "learning_rate": 1.3797905404552591e-05,
      "loss": 0.5421,
      "step": 24543
    },
    {
      "epoch": 0.753970448192179,
      "grad_norm": 0.36846667528152466,
      "learning_rate": 1.3797458333539817e-05,
      "loss": 0.5088,
      "step": 24544
    },
    {
      "epoch": 0.7540011673271281,
      "grad_norm": 0.4232780337333679,
      "learning_rate": 1.3797011253657813e-05,
      "loss": 0.5075,
      "step": 24545
    },
    {
      "epoch": 0.7540318864620772,
      "grad_norm": 0.3436441123485565,
      "learning_rate": 1.3796564164907627e-05,
      "loss": 0.4556,
      "step": 24546
    },
    {
      "epoch": 0.7540626055970264,
      "grad_norm": 0.3638877272605896,
      "learning_rate": 1.3796117067290298e-05,
      "loss": 0.6205,
      "step": 24547
    },
    {
      "epoch": 0.7540933247319755,
      "grad_norm": 0.3091943562030792,
      "learning_rate": 1.379566996080687e-05,
      "loss": 0.4994,
      "step": 24548
    },
    {
      "epoch": 0.7541240438669247,
      "grad_norm": 0.37205827236175537,
      "learning_rate": 1.3795222845458394e-05,
      "loss": 0.548,
      "step": 24549
    },
    {
      "epoch": 0.7541547630018739,
      "grad_norm": 0.4075019657611847,
      "learning_rate": 1.3794775721245907e-05,
      "loss": 0.6115,
      "step": 24550
    },
    {
      "epoch": 0.754185482136823,
      "grad_norm": 0.3681865334510803,
      "learning_rate": 1.379432858817046e-05,
      "loss": 0.4895,
      "step": 24551
    },
    {
      "epoch": 0.7542162012717721,
      "grad_norm": 0.33194610476493835,
      "learning_rate": 1.379388144623309e-05,
      "loss": 0.5195,
      "step": 24552
    },
    {
      "epoch": 0.7542469204067214,
      "grad_norm": 0.35041293501853943,
      "learning_rate": 1.3793434295434847e-05,
      "loss": 0.5421,
      "step": 24553
    },
    {
      "epoch": 0.7542776395416705,
      "grad_norm": 0.38195714354515076,
      "learning_rate": 1.3792987135776772e-05,
      "loss": 0.5078,
      "step": 24554
    },
    {
      "epoch": 0.7543083586766197,
      "grad_norm": 0.36041247844696045,
      "learning_rate": 1.379253996725991e-05,
      "loss": 0.6083,
      "step": 24555
    },
    {
      "epoch": 0.7543390778115688,
      "grad_norm": 0.35830357670783997,
      "learning_rate": 1.3792092789885309e-05,
      "loss": 0.5436,
      "step": 24556
    },
    {
      "epoch": 0.754369796946518,
      "grad_norm": 0.32707107067108154,
      "learning_rate": 1.379164560365401e-05,
      "loss": 0.4813,
      "step": 24557
    },
    {
      "epoch": 0.7544005160814672,
      "grad_norm": 0.3882702887058258,
      "learning_rate": 1.3791198408567054e-05,
      "loss": 0.5926,
      "step": 24558
    },
    {
      "epoch": 0.7544312352164163,
      "grad_norm": 0.371085524559021,
      "learning_rate": 1.3790751204625492e-05,
      "loss": 0.552,
      "step": 24559
    },
    {
      "epoch": 0.7544619543513654,
      "grad_norm": 0.34712913632392883,
      "learning_rate": 1.3790303991830367e-05,
      "loss": 0.4992,
      "step": 24560
    },
    {
      "epoch": 0.7544926734863147,
      "grad_norm": 0.37336304783821106,
      "learning_rate": 1.3789856770182722e-05,
      "loss": 0.6019,
      "step": 24561
    },
    {
      "epoch": 0.7545233926212638,
      "grad_norm": 0.41874390840530396,
      "learning_rate": 1.37894095396836e-05,
      "loss": 0.5932,
      "step": 24562
    },
    {
      "epoch": 0.7545541117562129,
      "grad_norm": 0.3589402437210083,
      "learning_rate": 1.3788962300334048e-05,
      "loss": 0.5783,
      "step": 24563
    },
    {
      "epoch": 0.7545848308911621,
      "grad_norm": 0.3509446680545807,
      "learning_rate": 1.3788515052135111e-05,
      "loss": 0.5415,
      "step": 24564
    },
    {
      "epoch": 0.7546155500261112,
      "grad_norm": 0.35005611181259155,
      "learning_rate": 1.378806779508783e-05,
      "loss": 0.5655,
      "step": 24565
    },
    {
      "epoch": 0.7546462691610605,
      "grad_norm": 0.4016057550907135,
      "learning_rate": 1.3787620529193252e-05,
      "loss": 0.552,
      "step": 24566
    },
    {
      "epoch": 0.7546769882960096,
      "grad_norm": 0.3264881372451782,
      "learning_rate": 1.3787173254452426e-05,
      "loss": 0.5169,
      "step": 24567
    },
    {
      "epoch": 0.7547077074309587,
      "grad_norm": 0.4087226092815399,
      "learning_rate": 1.3786725970866387e-05,
      "loss": 0.6217,
      "step": 24568
    },
    {
      "epoch": 0.754738426565908,
      "grad_norm": 0.3359224796295166,
      "learning_rate": 1.3786278678436191e-05,
      "loss": 0.5357,
      "step": 24569
    },
    {
      "epoch": 0.7547691457008571,
      "grad_norm": 0.36813831329345703,
      "learning_rate": 1.3785831377162873e-05,
      "loss": 0.5224,
      "step": 24570
    },
    {
      "epoch": 0.7547998648358062,
      "grad_norm": 0.38564664125442505,
      "learning_rate": 1.3785384067047482e-05,
      "loss": 0.6343,
      "step": 24571
    },
    {
      "epoch": 0.7548305839707554,
      "grad_norm": 0.35081249475479126,
      "learning_rate": 1.3784936748091062e-05,
      "loss": 0.5367,
      "step": 24572
    },
    {
      "epoch": 0.7548613031057045,
      "grad_norm": 0.3622435927391052,
      "learning_rate": 1.3784489420294658e-05,
      "loss": 0.4684,
      "step": 24573
    },
    {
      "epoch": 0.7548920222406537,
      "grad_norm": 0.5146843194961548,
      "learning_rate": 1.3784042083659315e-05,
      "loss": 0.5152,
      "step": 24574
    },
    {
      "epoch": 0.7549227413756029,
      "grad_norm": 0.4173651933670044,
      "learning_rate": 1.3783594738186076e-05,
      "loss": 0.5601,
      "step": 24575
    },
    {
      "epoch": 0.754953460510552,
      "grad_norm": 0.39865541458129883,
      "learning_rate": 1.378314738387599e-05,
      "loss": 0.5553,
      "step": 24576
    },
    {
      "epoch": 0.7549841796455011,
      "grad_norm": 0.37845489382743835,
      "learning_rate": 1.3782700020730097e-05,
      "loss": 0.5413,
      "step": 24577
    },
    {
      "epoch": 0.7550148987804504,
      "grad_norm": 0.37389978766441345,
      "learning_rate": 1.3782252648749445e-05,
      "loss": 0.4463,
      "step": 24578
    },
    {
      "epoch": 0.7550456179153995,
      "grad_norm": 0.34584665298461914,
      "learning_rate": 1.3781805267935076e-05,
      "loss": 0.5713,
      "step": 24579
    },
    {
      "epoch": 0.7550763370503487,
      "grad_norm": 0.34691545367240906,
      "learning_rate": 1.378135787828804e-05,
      "loss": 0.5233,
      "step": 24580
    },
    {
      "epoch": 0.7551070561852978,
      "grad_norm": 0.43991658091545105,
      "learning_rate": 1.3780910479809375e-05,
      "loss": 0.5062,
      "step": 24581
    },
    {
      "epoch": 0.755137775320247,
      "grad_norm": 0.3282316327095032,
      "learning_rate": 1.3780463072500132e-05,
      "loss": 0.508,
      "step": 24582
    },
    {
      "epoch": 0.7551684944551962,
      "grad_norm": 0.3909160792827606,
      "learning_rate": 1.3780015656361351e-05,
      "loss": 0.6066,
      "step": 24583
    },
    {
      "epoch": 0.7551992135901453,
      "grad_norm": 0.3782077133655548,
      "learning_rate": 1.377956823139408e-05,
      "loss": 0.5299,
      "step": 24584
    },
    {
      "epoch": 0.7552299327250944,
      "grad_norm": 0.3630470931529999,
      "learning_rate": 1.3779120797599365e-05,
      "loss": 0.4693,
      "step": 24585
    },
    {
      "epoch": 0.7552606518600437,
      "grad_norm": 0.36964765191078186,
      "learning_rate": 1.3778673354978249e-05,
      "loss": 0.5311,
      "step": 24586
    },
    {
      "epoch": 0.7552913709949928,
      "grad_norm": 0.4086628556251526,
      "learning_rate": 1.3778225903531776e-05,
      "loss": 0.5382,
      "step": 24587
    },
    {
      "epoch": 0.7553220901299419,
      "grad_norm": 0.3861559331417084,
      "learning_rate": 1.3777778443260993e-05,
      "loss": 0.6142,
      "step": 24588
    },
    {
      "epoch": 0.7553528092648911,
      "grad_norm": 0.432924747467041,
      "learning_rate": 1.3777330974166948e-05,
      "loss": 0.6056,
      "step": 24589
    },
    {
      "epoch": 0.7553835283998402,
      "grad_norm": 0.35025712847709656,
      "learning_rate": 1.3776883496250682e-05,
      "loss": 0.4886,
      "step": 24590
    },
    {
      "epoch": 0.7554142475347895,
      "grad_norm": 0.3509158194065094,
      "learning_rate": 1.3776436009513236e-05,
      "loss": 0.4994,
      "step": 24591
    },
    {
      "epoch": 0.7554449666697386,
      "grad_norm": 0.36490491032600403,
      "learning_rate": 1.3775988513955664e-05,
      "loss": 0.5449,
      "step": 24592
    },
    {
      "epoch": 0.7554756858046877,
      "grad_norm": 0.4141114354133606,
      "learning_rate": 1.3775541009579005e-05,
      "loss": 0.4518,
      "step": 24593
    },
    {
      "epoch": 0.7555064049396369,
      "grad_norm": 0.35492292046546936,
      "learning_rate": 1.3775093496384308e-05,
      "loss": 0.4247,
      "step": 24594
    },
    {
      "epoch": 0.7555371240745861,
      "grad_norm": 0.42005231976509094,
      "learning_rate": 1.3774645974372616e-05,
      "loss": 0.5978,
      "step": 24595
    },
    {
      "epoch": 0.7555678432095352,
      "grad_norm": 0.39017075300216675,
      "learning_rate": 1.3774198443544975e-05,
      "loss": 0.5478,
      "step": 24596
    },
    {
      "epoch": 0.7555985623444844,
      "grad_norm": 0.41742679476737976,
      "learning_rate": 1.3773750903902428e-05,
      "loss": 0.5071,
      "step": 24597
    },
    {
      "epoch": 0.7556292814794335,
      "grad_norm": 0.40256229043006897,
      "learning_rate": 1.3773303355446027e-05,
      "loss": 0.5861,
      "step": 24598
    },
    {
      "epoch": 0.7556600006143827,
      "grad_norm": 0.3811611533164978,
      "learning_rate": 1.3772855798176807e-05,
      "loss": 0.6273,
      "step": 24599
    },
    {
      "epoch": 0.7556907197493319,
      "grad_norm": 0.372891902923584,
      "learning_rate": 1.3772408232095822e-05,
      "loss": 0.6017,
      "step": 24600
    },
    {
      "epoch": 0.755721438884281,
      "grad_norm": 0.3506641983985901,
      "learning_rate": 1.3771960657204112e-05,
      "loss": 0.5612,
      "step": 24601
    },
    {
      "epoch": 0.7557521580192301,
      "grad_norm": 0.34423959255218506,
      "learning_rate": 1.3771513073502725e-05,
      "loss": 0.5447,
      "step": 24602
    },
    {
      "epoch": 0.7557828771541794,
      "grad_norm": 0.3480944037437439,
      "learning_rate": 1.3771065480992704e-05,
      "loss": 0.5212,
      "step": 24603
    },
    {
      "epoch": 0.7558135962891285,
      "grad_norm": 0.42084208130836487,
      "learning_rate": 1.3770617879675098e-05,
      "loss": 0.5766,
      "step": 24604
    },
    {
      "epoch": 0.7558443154240777,
      "grad_norm": 0.4609842002391815,
      "learning_rate": 1.3770170269550953e-05,
      "loss": 0.5642,
      "step": 24605
    },
    {
      "epoch": 0.7558750345590268,
      "grad_norm": 0.36247891187667847,
      "learning_rate": 1.3769722650621309e-05,
      "loss": 0.5965,
      "step": 24606
    },
    {
      "epoch": 0.755905753693976,
      "grad_norm": 0.3919740915298462,
      "learning_rate": 1.3769275022887217e-05,
      "loss": 0.5593,
      "step": 24607
    },
    {
      "epoch": 0.7559364728289252,
      "grad_norm": 0.38612210750579834,
      "learning_rate": 1.376882738634972e-05,
      "loss": 0.6317,
      "step": 24608
    },
    {
      "epoch": 0.7559671919638743,
      "grad_norm": 0.3746379017829895,
      "learning_rate": 1.3768379741009861e-05,
      "loss": 0.5668,
      "step": 24609
    },
    {
      "epoch": 0.7559979110988234,
      "grad_norm": 0.3791041970252991,
      "learning_rate": 1.3767932086868689e-05,
      "loss": 0.5293,
      "step": 24610
    },
    {
      "epoch": 0.7560286302337726,
      "grad_norm": 0.3256434500217438,
      "learning_rate": 1.3767484423927248e-05,
      "loss": 0.4957,
      "step": 24611
    },
    {
      "epoch": 0.7560593493687218,
      "grad_norm": 0.41084566712379456,
      "learning_rate": 1.3767036752186584e-05,
      "loss": 0.5457,
      "step": 24612
    },
    {
      "epoch": 0.7560900685036709,
      "grad_norm": 0.41853004693984985,
      "learning_rate": 1.3766589071647745e-05,
      "loss": 0.5926,
      "step": 24613
    },
    {
      "epoch": 0.7561207876386201,
      "grad_norm": 0.370084673166275,
      "learning_rate": 1.376614138231177e-05,
      "loss": 0.5581,
      "step": 24614
    },
    {
      "epoch": 0.7561515067735692,
      "grad_norm": 0.5044322609901428,
      "learning_rate": 1.3765693684179711e-05,
      "loss": 0.5526,
      "step": 24615
    },
    {
      "epoch": 0.7561822259085185,
      "grad_norm": 0.4410322904586792,
      "learning_rate": 1.3765245977252613e-05,
      "loss": 0.5034,
      "step": 24616
    },
    {
      "epoch": 0.7562129450434676,
      "grad_norm": 0.343758225440979,
      "learning_rate": 1.3764798261531516e-05,
      "loss": 0.5869,
      "step": 24617
    },
    {
      "epoch": 0.7562436641784167,
      "grad_norm": 0.3803333044052124,
      "learning_rate": 1.3764350537017474e-05,
      "loss": 0.5332,
      "step": 24618
    },
    {
      "epoch": 0.7562743833133659,
      "grad_norm": 0.4048638939857483,
      "learning_rate": 1.3763902803711528e-05,
      "loss": 0.525,
      "step": 24619
    },
    {
      "epoch": 0.7563051024483151,
      "grad_norm": 0.33623582124710083,
      "learning_rate": 1.376345506161472e-05,
      "loss": 0.5731,
      "step": 24620
    },
    {
      "epoch": 0.7563358215832642,
      "grad_norm": 0.42063024640083313,
      "learning_rate": 1.3763007310728103e-05,
      "loss": 0.6427,
      "step": 24621
    },
    {
      "epoch": 0.7563665407182134,
      "grad_norm": 0.4743943214416504,
      "learning_rate": 1.3762559551052719e-05,
      "loss": 0.6396,
      "step": 24622
    },
    {
      "epoch": 0.7563972598531625,
      "grad_norm": 0.38188815116882324,
      "learning_rate": 1.3762111782589615e-05,
      "loss": 0.5735,
      "step": 24623
    },
    {
      "epoch": 0.7564279789881116,
      "grad_norm": 0.3637358248233795,
      "learning_rate": 1.3761664005339834e-05,
      "loss": 0.5664,
      "step": 24624
    },
    {
      "epoch": 0.7564586981230609,
      "grad_norm": 0.37863919138908386,
      "learning_rate": 1.3761216219304428e-05,
      "loss": 0.5357,
      "step": 24625
    },
    {
      "epoch": 0.75648941725801,
      "grad_norm": 0.3564393222332001,
      "learning_rate": 1.3760768424484437e-05,
      "loss": 0.5192,
      "step": 24626
    },
    {
      "epoch": 0.7565201363929591,
      "grad_norm": 0.33604729175567627,
      "learning_rate": 1.3760320620880908e-05,
      "loss": 0.4963,
      "step": 24627
    },
    {
      "epoch": 0.7565508555279084,
      "grad_norm": 0.35422414541244507,
      "learning_rate": 1.3759872808494888e-05,
      "loss": 0.6358,
      "step": 24628
    },
    {
      "epoch": 0.7565815746628575,
      "grad_norm": 0.4212462604045868,
      "learning_rate": 1.375942498732742e-05,
      "loss": 0.538,
      "step": 24629
    },
    {
      "epoch": 0.7566122937978067,
      "grad_norm": 0.34271398186683655,
      "learning_rate": 1.3758977157379555e-05,
      "loss": 0.5966,
      "step": 24630
    },
    {
      "epoch": 0.7566430129327558,
      "grad_norm": 0.3660988509654999,
      "learning_rate": 1.3758529318652336e-05,
      "loss": 0.5106,
      "step": 24631
    },
    {
      "epoch": 0.7566737320677049,
      "grad_norm": 0.37593725323677063,
      "learning_rate": 1.3758081471146811e-05,
      "loss": 0.5313,
      "step": 24632
    },
    {
      "epoch": 0.7567044512026542,
      "grad_norm": 0.3675180673599243,
      "learning_rate": 1.375763361486402e-05,
      "loss": 0.6493,
      "step": 24633
    },
    {
      "epoch": 0.7567351703376033,
      "grad_norm": 0.37050655484199524,
      "learning_rate": 1.3757185749805018e-05,
      "loss": 0.6017,
      "step": 24634
    },
    {
      "epoch": 0.7567658894725524,
      "grad_norm": 0.3495364785194397,
      "learning_rate": 1.3756737875970843e-05,
      "loss": 0.5189,
      "step": 24635
    },
    {
      "epoch": 0.7567966086075016,
      "grad_norm": 0.39740848541259766,
      "learning_rate": 1.3756289993362547e-05,
      "loss": 0.6151,
      "step": 24636
    },
    {
      "epoch": 0.7568273277424508,
      "grad_norm": 0.3728899359703064,
      "learning_rate": 1.3755842101981172e-05,
      "loss": 0.6079,
      "step": 24637
    },
    {
      "epoch": 0.7568580468773999,
      "grad_norm": 0.3700109124183655,
      "learning_rate": 1.3755394201827764e-05,
      "loss": 0.5851,
      "step": 24638
    },
    {
      "epoch": 0.7568887660123491,
      "grad_norm": 0.36370837688446045,
      "learning_rate": 1.375494629290337e-05,
      "loss": 0.5564,
      "step": 24639
    },
    {
      "epoch": 0.7569194851472982,
      "grad_norm": 0.35751664638519287,
      "learning_rate": 1.375449837520904e-05,
      "loss": 0.6008,
      "step": 24640
    },
    {
      "epoch": 0.7569502042822475,
      "grad_norm": 0.34068563580513,
      "learning_rate": 1.3754050448745815e-05,
      "loss": 0.5798,
      "step": 24641
    },
    {
      "epoch": 0.7569809234171966,
      "grad_norm": 0.3393838405609131,
      "learning_rate": 1.3753602513514746e-05,
      "loss": 0.5014,
      "step": 24642
    },
    {
      "epoch": 0.7570116425521457,
      "grad_norm": 0.34170013666152954,
      "learning_rate": 1.3753154569516871e-05,
      "loss": 0.5198,
      "step": 24643
    },
    {
      "epoch": 0.7570423616870949,
      "grad_norm": 0.4836895167827606,
      "learning_rate": 1.3752706616753243e-05,
      "loss": 0.5096,
      "step": 24644
    },
    {
      "epoch": 0.757073080822044,
      "grad_norm": 0.40865612030029297,
      "learning_rate": 1.3752258655224909e-05,
      "loss": 0.4615,
      "step": 24645
    },
    {
      "epoch": 0.7571037999569932,
      "grad_norm": 0.3650774359703064,
      "learning_rate": 1.3751810684932911e-05,
      "loss": 0.5343,
      "step": 24646
    },
    {
      "epoch": 0.7571345190919424,
      "grad_norm": 0.35175323486328125,
      "learning_rate": 1.3751362705878298e-05,
      "loss": 0.5165,
      "step": 24647
    },
    {
      "epoch": 0.7571652382268915,
      "grad_norm": 0.39050573110580444,
      "learning_rate": 1.3750914718062116e-05,
      "loss": 0.5653,
      "step": 24648
    },
    {
      "epoch": 0.7571959573618406,
      "grad_norm": 0.3575815260410309,
      "learning_rate": 1.3750466721485407e-05,
      "loss": 0.5093,
      "step": 24649
    },
    {
      "epoch": 0.7572266764967899,
      "grad_norm": 0.34421318769454956,
      "learning_rate": 1.3750018716149228e-05,
      "loss": 0.4284,
      "step": 24650
    },
    {
      "epoch": 0.757257395631739,
      "grad_norm": 0.3792278468608856,
      "learning_rate": 1.3749570702054611e-05,
      "loss": 0.6298,
      "step": 24651
    },
    {
      "epoch": 0.7572881147666882,
      "grad_norm": 0.37028202414512634,
      "learning_rate": 1.3749122679202614e-05,
      "loss": 0.5207,
      "step": 24652
    },
    {
      "epoch": 0.7573188339016373,
      "grad_norm": 0.38020607829093933,
      "learning_rate": 1.374867464759428e-05,
      "loss": 0.5495,
      "step": 24653
    },
    {
      "epoch": 0.7573495530365865,
      "grad_norm": 0.3975091576576233,
      "learning_rate": 1.374822660723065e-05,
      "loss": 0.608,
      "step": 24654
    },
    {
      "epoch": 0.7573802721715357,
      "grad_norm": 0.3693642318248749,
      "learning_rate": 1.374777855811278e-05,
      "loss": 0.555,
      "step": 24655
    },
    {
      "epoch": 0.7574109913064848,
      "grad_norm": 0.364785760641098,
      "learning_rate": 1.3747330500241707e-05,
      "loss": 0.5675,
      "step": 24656
    },
    {
      "epoch": 0.7574417104414339,
      "grad_norm": 0.3712325096130371,
      "learning_rate": 1.3746882433618483e-05,
      "loss": 0.5974,
      "step": 24657
    },
    {
      "epoch": 0.7574724295763832,
      "grad_norm": 0.40133458375930786,
      "learning_rate": 1.3746434358244151e-05,
      "loss": 0.5054,
      "step": 24658
    },
    {
      "epoch": 0.7575031487113323,
      "grad_norm": 0.37120792269706726,
      "learning_rate": 1.3745986274119767e-05,
      "loss": 0.5815,
      "step": 24659
    },
    {
      "epoch": 0.7575338678462814,
      "grad_norm": 0.4319974482059479,
      "learning_rate": 1.3745538181246367e-05,
      "loss": 0.6051,
      "step": 24660
    },
    {
      "epoch": 0.7575645869812306,
      "grad_norm": 0.3738507330417633,
      "learning_rate": 1.3745090079625e-05,
      "loss": 0.4718,
      "step": 24661
    },
    {
      "epoch": 0.7575953061161798,
      "grad_norm": 0.3453543186187744,
      "learning_rate": 1.3744641969256716e-05,
      "loss": 0.4777,
      "step": 24662
    },
    {
      "epoch": 0.7576260252511289,
      "grad_norm": 0.3540833592414856,
      "learning_rate": 1.3744193850142555e-05,
      "loss": 0.5492,
      "step": 24663
    },
    {
      "epoch": 0.7576567443860781,
      "grad_norm": 0.42123907804489136,
      "learning_rate": 1.374374572228357e-05,
      "loss": 0.561,
      "step": 24664
    },
    {
      "epoch": 0.7576874635210272,
      "grad_norm": 0.35331836342811584,
      "learning_rate": 1.3743297585680805e-05,
      "loss": 0.6215,
      "step": 24665
    },
    {
      "epoch": 0.7577181826559765,
      "grad_norm": 0.3585405945777893,
      "learning_rate": 1.3742849440335308e-05,
      "loss": 0.5207,
      "step": 24666
    },
    {
      "epoch": 0.7577489017909256,
      "grad_norm": 0.3646279573440552,
      "learning_rate": 1.3742401286248124e-05,
      "loss": 0.6292,
      "step": 24667
    },
    {
      "epoch": 0.7577796209258747,
      "grad_norm": 0.5906225442886353,
      "learning_rate": 1.3741953123420301e-05,
      "loss": 0.5105,
      "step": 24668
    },
    {
      "epoch": 0.7578103400608239,
      "grad_norm": 0.5079466104507446,
      "learning_rate": 1.3741504951852885e-05,
      "loss": 0.5545,
      "step": 24669
    },
    {
      "epoch": 0.757841059195773,
      "grad_norm": 0.3575819730758667,
      "learning_rate": 1.3741056771546924e-05,
      "loss": 0.5567,
      "step": 24670
    },
    {
      "epoch": 0.7578717783307222,
      "grad_norm": 0.32348138093948364,
      "learning_rate": 1.3740608582503462e-05,
      "loss": 0.5627,
      "step": 24671
    },
    {
      "epoch": 0.7579024974656714,
      "grad_norm": 0.32824409008026123,
      "learning_rate": 1.3740160384723549e-05,
      "loss": 0.5305,
      "step": 24672
    },
    {
      "epoch": 0.7579332166006205,
      "grad_norm": 0.3415224552154541,
      "learning_rate": 1.3739712178208228e-05,
      "loss": 0.5246,
      "step": 24673
    },
    {
      "epoch": 0.7579639357355696,
      "grad_norm": 0.34043633937835693,
      "learning_rate": 1.3739263962958548e-05,
      "loss": 0.5308,
      "step": 24674
    },
    {
      "epoch": 0.7579946548705189,
      "grad_norm": 0.34388554096221924,
      "learning_rate": 1.3738815738975557e-05,
      "loss": 0.5269,
      "step": 24675
    },
    {
      "epoch": 0.758025374005468,
      "grad_norm": 0.3561536967754364,
      "learning_rate": 1.37383675062603e-05,
      "loss": 0.5424,
      "step": 24676
    },
    {
      "epoch": 0.7580560931404172,
      "grad_norm": 0.35920000076293945,
      "learning_rate": 1.3737919264813826e-05,
      "loss": 0.4608,
      "step": 24677
    },
    {
      "epoch": 0.7580868122753663,
      "grad_norm": 4.399122714996338,
      "learning_rate": 1.373747101463718e-05,
      "loss": 0.5751,
      "step": 24678
    },
    {
      "epoch": 0.7581175314103155,
      "grad_norm": 0.3823566138744354,
      "learning_rate": 1.3737022755731409e-05,
      "loss": 0.4867,
      "step": 24679
    },
    {
      "epoch": 0.7581482505452647,
      "grad_norm": 0.37654030323028564,
      "learning_rate": 1.3736574488097561e-05,
      "loss": 0.5055,
      "step": 24680
    },
    {
      "epoch": 0.7581789696802138,
      "grad_norm": 0.746712327003479,
      "learning_rate": 1.3736126211736681e-05,
      "loss": 0.5592,
      "step": 24681
    },
    {
      "epoch": 0.7582096888151629,
      "grad_norm": 0.39567965269088745,
      "learning_rate": 1.373567792664982e-05,
      "loss": 0.5306,
      "step": 24682
    },
    {
      "epoch": 0.7582404079501122,
      "grad_norm": 0.32040926814079285,
      "learning_rate": 1.3735229632838018e-05,
      "loss": 0.5476,
      "step": 24683
    },
    {
      "epoch": 0.7582711270850613,
      "grad_norm": 0.3692101836204529,
      "learning_rate": 1.3734781330302331e-05,
      "loss": 0.5484,
      "step": 24684
    },
    {
      "epoch": 0.7583018462200104,
      "grad_norm": 0.35414811968803406,
      "learning_rate": 1.3734333019043798e-05,
      "loss": 0.5089,
      "step": 24685
    },
    {
      "epoch": 0.7583325653549596,
      "grad_norm": 0.37896838784217834,
      "learning_rate": 1.3733884699063471e-05,
      "loss": 0.6082,
      "step": 24686
    },
    {
      "epoch": 0.7583632844899088,
      "grad_norm": 0.3504708409309387,
      "learning_rate": 1.3733436370362395e-05,
      "loss": 0.5764,
      "step": 24687
    },
    {
      "epoch": 0.7583940036248579,
      "grad_norm": 0.3656189739704132,
      "learning_rate": 1.3732988032941619e-05,
      "loss": 0.5293,
      "step": 24688
    },
    {
      "epoch": 0.7584247227598071,
      "grad_norm": 0.3868030309677124,
      "learning_rate": 1.3732539686802189e-05,
      "loss": 0.5236,
      "step": 24689
    },
    {
      "epoch": 0.7584554418947562,
      "grad_norm": 0.4085100591182709,
      "learning_rate": 1.3732091331945148e-05,
      "loss": 0.6275,
      "step": 24690
    },
    {
      "epoch": 0.7584861610297055,
      "grad_norm": 0.39009878039360046,
      "learning_rate": 1.3731642968371551e-05,
      "loss": 0.49,
      "step": 24691
    },
    {
      "epoch": 0.7585168801646546,
      "grad_norm": 0.3782714009284973,
      "learning_rate": 1.3731194596082439e-05,
      "loss": 0.5745,
      "step": 24692
    },
    {
      "epoch": 0.7585475992996037,
      "grad_norm": 0.35443204641342163,
      "learning_rate": 1.3730746215078861e-05,
      "loss": 0.6018,
      "step": 24693
    },
    {
      "epoch": 0.7585783184345529,
      "grad_norm": 0.39768823981285095,
      "learning_rate": 1.3730297825361865e-05,
      "loss": 0.543,
      "step": 24694
    },
    {
      "epoch": 0.758609037569502,
      "grad_norm": 0.36183488368988037,
      "learning_rate": 1.3729849426932497e-05,
      "loss": 0.4596,
      "step": 24695
    },
    {
      "epoch": 0.7586397567044512,
      "grad_norm": 0.3509426414966583,
      "learning_rate": 1.372940101979181e-05,
      "loss": 0.5361,
      "step": 24696
    },
    {
      "epoch": 0.7586704758394004,
      "grad_norm": 0.37832698225975037,
      "learning_rate": 1.3728952603940841e-05,
      "loss": 0.5616,
      "step": 24697
    },
    {
      "epoch": 0.7587011949743495,
      "grad_norm": 0.34347474575042725,
      "learning_rate": 1.3728504179380646e-05,
      "loss": 0.565,
      "step": 24698
    },
    {
      "epoch": 0.7587319141092986,
      "grad_norm": 0.3384833037853241,
      "learning_rate": 1.3728055746112268e-05,
      "loss": 0.5555,
      "step": 24699
    },
    {
      "epoch": 0.7587626332442479,
      "grad_norm": 0.3410390019416809,
      "learning_rate": 1.3727607304136756e-05,
      "loss": 0.4831,
      "step": 24700
    },
    {
      "epoch": 0.758793352379197,
      "grad_norm": 0.35866865515708923,
      "learning_rate": 1.3727158853455156e-05,
      "loss": 0.4779,
      "step": 24701
    },
    {
      "epoch": 0.7588240715141462,
      "grad_norm": 0.36627915501594543,
      "learning_rate": 1.3726710394068517e-05,
      "loss": 0.6301,
      "step": 24702
    },
    {
      "epoch": 0.7588547906490953,
      "grad_norm": 0.4269801676273346,
      "learning_rate": 1.3726261925977884e-05,
      "loss": 0.6425,
      "step": 24703
    },
    {
      "epoch": 0.7588855097840445,
      "grad_norm": 0.3572266101837158,
      "learning_rate": 1.3725813449184308e-05,
      "loss": 0.5066,
      "step": 24704
    },
    {
      "epoch": 0.7589162289189937,
      "grad_norm": 0.3484805226325989,
      "learning_rate": 1.3725364963688836e-05,
      "loss": 0.4833,
      "step": 24705
    },
    {
      "epoch": 0.7589469480539428,
      "grad_norm": 0.3666360080242157,
      "learning_rate": 1.3724916469492509e-05,
      "loss": 0.551,
      "step": 24706
    },
    {
      "epoch": 0.7589776671888919,
      "grad_norm": 0.4152306616306305,
      "learning_rate": 1.3724467966596385e-05,
      "loss": 0.614,
      "step": 24707
    },
    {
      "epoch": 0.7590083863238412,
      "grad_norm": 0.37621551752090454,
      "learning_rate": 1.3724019455001501e-05,
      "loss": 0.5589,
      "step": 24708
    },
    {
      "epoch": 0.7590391054587903,
      "grad_norm": 0.3752250075340271,
      "learning_rate": 1.3723570934708912e-05,
      "loss": 0.451,
      "step": 24709
    },
    {
      "epoch": 0.7590698245937394,
      "grad_norm": 0.35436180233955383,
      "learning_rate": 1.3723122405719662e-05,
      "loss": 0.5781,
      "step": 24710
    },
    {
      "epoch": 0.7591005437286886,
      "grad_norm": 0.3437903821468353,
      "learning_rate": 1.37226738680348e-05,
      "loss": 0.501,
      "step": 24711
    },
    {
      "epoch": 0.7591312628636377,
      "grad_norm": 0.39030855894088745,
      "learning_rate": 1.3722225321655373e-05,
      "loss": 0.6084,
      "step": 24712
    },
    {
      "epoch": 0.7591619819985869,
      "grad_norm": 0.33232155442237854,
      "learning_rate": 1.372177676658243e-05,
      "loss": 0.5821,
      "step": 24713
    },
    {
      "epoch": 0.7591927011335361,
      "grad_norm": 0.3579506278038025,
      "learning_rate": 1.3721328202817016e-05,
      "loss": 0.5636,
      "step": 24714
    },
    {
      "epoch": 0.7592234202684852,
      "grad_norm": 0.36260464787483215,
      "learning_rate": 1.372087963036018e-05,
      "loss": 0.4621,
      "step": 24715
    },
    {
      "epoch": 0.7592541394034344,
      "grad_norm": 0.37215670943260193,
      "learning_rate": 1.3720431049212971e-05,
      "loss": 0.5276,
      "step": 24716
    },
    {
      "epoch": 0.7592848585383836,
      "grad_norm": 0.3720552921295166,
      "learning_rate": 1.3719982459376433e-05,
      "loss": 0.6117,
      "step": 24717
    },
    {
      "epoch": 0.7593155776733327,
      "grad_norm": 0.44346538186073303,
      "learning_rate": 1.3719533860851622e-05,
      "loss": 0.6193,
      "step": 24718
    },
    {
      "epoch": 0.7593462968082819,
      "grad_norm": 0.4135790765285492,
      "learning_rate": 1.3719085253639572e-05,
      "loss": 0.5602,
      "step": 24719
    },
    {
      "epoch": 0.759377015943231,
      "grad_norm": 0.3746446967124939,
      "learning_rate": 1.3718636637741344e-05,
      "loss": 0.4426,
      "step": 24720
    },
    {
      "epoch": 0.7594077350781802,
      "grad_norm": 0.37930503487586975,
      "learning_rate": 1.3718188013157978e-05,
      "loss": 0.4872,
      "step": 24721
    },
    {
      "epoch": 0.7594384542131294,
      "grad_norm": 0.3612819015979767,
      "learning_rate": 1.3717739379890527e-05,
      "loss": 0.5958,
      "step": 24722
    },
    {
      "epoch": 0.7594691733480785,
      "grad_norm": 0.39230942726135254,
      "learning_rate": 1.3717290737940036e-05,
      "loss": 0.5063,
      "step": 24723
    },
    {
      "epoch": 0.7594998924830276,
      "grad_norm": 0.3259080648422241,
      "learning_rate": 1.3716842087307549e-05,
      "loss": 0.4664,
      "step": 24724
    },
    {
      "epoch": 0.7595306116179769,
      "grad_norm": 0.37829339504241943,
      "learning_rate": 1.371639342799412e-05,
      "loss": 0.5894,
      "step": 24725
    },
    {
      "epoch": 0.759561330752926,
      "grad_norm": 0.3447209894657135,
      "learning_rate": 1.3715944760000794e-05,
      "loss": 0.6296,
      "step": 24726
    },
    {
      "epoch": 0.7595920498878752,
      "grad_norm": 0.3273679316043854,
      "learning_rate": 1.3715496083328621e-05,
      "loss": 0.5272,
      "step": 24727
    },
    {
      "epoch": 0.7596227690228243,
      "grad_norm": 0.4126949608325958,
      "learning_rate": 1.3715047397978647e-05,
      "loss": 0.6267,
      "step": 24728
    },
    {
      "epoch": 0.7596534881577734,
      "grad_norm": 0.4043728709220886,
      "learning_rate": 1.371459870395192e-05,
      "loss": 0.6271,
      "step": 24729
    },
    {
      "epoch": 0.7596842072927227,
      "grad_norm": 0.3891482949256897,
      "learning_rate": 1.3714150001249487e-05,
      "loss": 0.5395,
      "step": 24730
    },
    {
      "epoch": 0.7597149264276718,
      "grad_norm": 0.4043339788913727,
      "learning_rate": 1.3713701289872396e-05,
      "loss": 0.5621,
      "step": 24731
    },
    {
      "epoch": 0.7597456455626209,
      "grad_norm": 0.35335537791252136,
      "learning_rate": 1.37132525698217e-05,
      "loss": 0.534,
      "step": 24732
    },
    {
      "epoch": 0.7597763646975702,
      "grad_norm": 0.36199015378952026,
      "learning_rate": 1.3712803841098441e-05,
      "loss": 0.6048,
      "step": 24733
    },
    {
      "epoch": 0.7598070838325193,
      "grad_norm": 0.3994925916194916,
      "learning_rate": 1.3712355103703671e-05,
      "loss": 0.5172,
      "step": 24734
    },
    {
      "epoch": 0.7598378029674684,
      "grad_norm": 0.36801770329475403,
      "learning_rate": 1.3711906357638437e-05,
      "loss": 0.5255,
      "step": 24735
    },
    {
      "epoch": 0.7598685221024176,
      "grad_norm": 0.34837645292282104,
      "learning_rate": 1.3711457602903784e-05,
      "loss": 0.577,
      "step": 24736
    },
    {
      "epoch": 0.7598992412373667,
      "grad_norm": 0.40588074922561646,
      "learning_rate": 1.3711008839500764e-05,
      "loss": 0.5197,
      "step": 24737
    },
    {
      "epoch": 0.7599299603723159,
      "grad_norm": 0.35169658064842224,
      "learning_rate": 1.3710560067430422e-05,
      "loss": 0.627,
      "step": 24738
    },
    {
      "epoch": 0.7599606795072651,
      "grad_norm": 0.6078711152076721,
      "learning_rate": 1.3710111286693808e-05,
      "loss": 0.5969,
      "step": 24739
    },
    {
      "epoch": 0.7599913986422142,
      "grad_norm": 0.38796669244766235,
      "learning_rate": 1.3709662497291974e-05,
      "loss": 0.5197,
      "step": 24740
    },
    {
      "epoch": 0.7600221177771634,
      "grad_norm": 0.41113144159317017,
      "learning_rate": 1.3709213699225964e-05,
      "loss": 0.564,
      "step": 24741
    },
    {
      "epoch": 0.7600528369121126,
      "grad_norm": 0.3513335883617401,
      "learning_rate": 1.370876489249682e-05,
      "loss": 0.4951,
      "step": 24742
    },
    {
      "epoch": 0.7600835560470617,
      "grad_norm": 0.3519977033138275,
      "learning_rate": 1.3708316077105602e-05,
      "loss": 0.5334,
      "step": 24743
    },
    {
      "epoch": 0.7601142751820109,
      "grad_norm": 0.3926602303981781,
      "learning_rate": 1.3707867253053349e-05,
      "loss": 0.5671,
      "step": 24744
    },
    {
      "epoch": 0.76014499431696,
      "grad_norm": 0.360254168510437,
      "learning_rate": 1.3707418420341116e-05,
      "loss": 0.5284,
      "step": 24745
    },
    {
      "epoch": 0.7601757134519092,
      "grad_norm": 0.36145323514938354,
      "learning_rate": 1.3706969578969947e-05,
      "loss": 0.5962,
      "step": 24746
    },
    {
      "epoch": 0.7602064325868584,
      "grad_norm": 0.36920902132987976,
      "learning_rate": 1.3706520728940892e-05,
      "loss": 0.5315,
      "step": 24747
    },
    {
      "epoch": 0.7602371517218075,
      "grad_norm": 0.39002272486686707,
      "learning_rate": 1.3706071870255e-05,
      "loss": 0.5457,
      "step": 24748
    },
    {
      "epoch": 0.7602678708567566,
      "grad_norm": 0.3350180685520172,
      "learning_rate": 1.3705623002913315e-05,
      "loss": 0.5146,
      "step": 24749
    },
    {
      "epoch": 0.7602985899917059,
      "grad_norm": 0.3666127324104309,
      "learning_rate": 1.3705174126916894e-05,
      "loss": 0.5941,
      "step": 24750
    },
    {
      "epoch": 0.760329309126655,
      "grad_norm": 0.39968305826187134,
      "learning_rate": 1.3704725242266774e-05,
      "loss": 0.5704,
      "step": 24751
    },
    {
      "epoch": 0.7603600282616042,
      "grad_norm": 0.4519888162612915,
      "learning_rate": 1.3704276348964015e-05,
      "loss": 0.657,
      "step": 24752
    },
    {
      "epoch": 0.7603907473965533,
      "grad_norm": 0.41979265213012695,
      "learning_rate": 1.3703827447009657e-05,
      "loss": 0.4978,
      "step": 24753
    },
    {
      "epoch": 0.7604214665315024,
      "grad_norm": 0.3288288116455078,
      "learning_rate": 1.3703378536404752e-05,
      "loss": 0.5573,
      "step": 24754
    },
    {
      "epoch": 0.7604521856664517,
      "grad_norm": 0.3760867714881897,
      "learning_rate": 1.3702929617150347e-05,
      "loss": 0.5466,
      "step": 24755
    },
    {
      "epoch": 0.7604829048014008,
      "grad_norm": 0.3581031560897827,
      "learning_rate": 1.3702480689247492e-05,
      "loss": 0.5815,
      "step": 24756
    },
    {
      "epoch": 0.7605136239363499,
      "grad_norm": 0.3575216233730316,
      "learning_rate": 1.3702031752697233e-05,
      "loss": 0.5769,
      "step": 24757
    },
    {
      "epoch": 0.7605443430712991,
      "grad_norm": 0.38963866233825684,
      "learning_rate": 1.3701582807500624e-05,
      "loss": 0.5859,
      "step": 24758
    },
    {
      "epoch": 0.7605750622062483,
      "grad_norm": 0.374544233083725,
      "learning_rate": 1.3701133853658709e-05,
      "loss": 0.555,
      "step": 24759
    },
    {
      "epoch": 0.7606057813411974,
      "grad_norm": 0.3145492970943451,
      "learning_rate": 1.3700684891172532e-05,
      "loss": 0.5481,
      "step": 24760
    },
    {
      "epoch": 0.7606365004761466,
      "grad_norm": 0.3493175208568573,
      "learning_rate": 1.3700235920043154e-05,
      "loss": 0.5139,
      "step": 24761
    },
    {
      "epoch": 0.7606672196110957,
      "grad_norm": 0.36457204818725586,
      "learning_rate": 1.3699786940271614e-05,
      "loss": 0.6081,
      "step": 24762
    },
    {
      "epoch": 0.760697938746045,
      "grad_norm": 0.35624608397483826,
      "learning_rate": 1.3699337951858964e-05,
      "loss": 0.4972,
      "step": 24763
    },
    {
      "epoch": 0.7607286578809941,
      "grad_norm": 0.41096481680870056,
      "learning_rate": 1.3698888954806249e-05,
      "loss": 0.6115,
      "step": 24764
    },
    {
      "epoch": 0.7607593770159432,
      "grad_norm": 0.32993367314338684,
      "learning_rate": 1.3698439949114523e-05,
      "loss": 0.5418,
      "step": 24765
    },
    {
      "epoch": 0.7607900961508924,
      "grad_norm": 0.3507934510707855,
      "learning_rate": 1.369799093478483e-05,
      "loss": 0.5308,
      "step": 24766
    },
    {
      "epoch": 0.7608208152858416,
      "grad_norm": 0.38486191630363464,
      "learning_rate": 1.3697541911818223e-05,
      "loss": 0.5587,
      "step": 24767
    },
    {
      "epoch": 0.7608515344207907,
      "grad_norm": 0.3966338038444519,
      "learning_rate": 1.3697092880215747e-05,
      "loss": 0.526,
      "step": 24768
    },
    {
      "epoch": 0.7608822535557399,
      "grad_norm": 0.3396579325199127,
      "learning_rate": 1.3696643839978453e-05,
      "loss": 0.5575,
      "step": 24769
    },
    {
      "epoch": 0.760912972690689,
      "grad_norm": 0.333711713552475,
      "learning_rate": 1.3696194791107392e-05,
      "loss": 0.5646,
      "step": 24770
    },
    {
      "epoch": 0.7609436918256381,
      "grad_norm": 0.36222055554389954,
      "learning_rate": 1.3695745733603607e-05,
      "loss": 0.5307,
      "step": 24771
    },
    {
      "epoch": 0.7609744109605874,
      "grad_norm": 0.3493693172931671,
      "learning_rate": 1.3695296667468149e-05,
      "loss": 0.6633,
      "step": 24772
    },
    {
      "epoch": 0.7610051300955365,
      "grad_norm": 0.33814433217048645,
      "learning_rate": 1.3694847592702067e-05,
      "loss": 0.5782,
      "step": 24773
    },
    {
      "epoch": 0.7610358492304856,
      "grad_norm": 0.34516939520835876,
      "learning_rate": 1.3694398509306415e-05,
      "loss": 0.5199,
      "step": 24774
    },
    {
      "epoch": 0.7610665683654348,
      "grad_norm": 0.4049151539802551,
      "learning_rate": 1.3693949417282235e-05,
      "loss": 0.5365,
      "step": 24775
    },
    {
      "epoch": 0.761097287500384,
      "grad_norm": 0.3904387056827545,
      "learning_rate": 1.3693500316630577e-05,
      "loss": 0.5341,
      "step": 24776
    },
    {
      "epoch": 0.7611280066353332,
      "grad_norm": 0.4669255018234253,
      "learning_rate": 1.3693051207352492e-05,
      "loss": 0.6664,
      "step": 24777
    },
    {
      "epoch": 0.7611587257702823,
      "grad_norm": 0.36748820543289185,
      "learning_rate": 1.3692602089449028e-05,
      "loss": 0.531,
      "step": 24778
    },
    {
      "epoch": 0.7611894449052314,
      "grad_norm": 0.4135892987251282,
      "learning_rate": 1.3692152962921235e-05,
      "loss": 0.564,
      "step": 24779
    },
    {
      "epoch": 0.7612201640401807,
      "grad_norm": 0.37145698070526123,
      "learning_rate": 1.3691703827770157e-05,
      "loss": 0.5763,
      "step": 24780
    },
    {
      "epoch": 0.7612508831751298,
      "grad_norm": 0.3697250783443451,
      "learning_rate": 1.369125468399685e-05,
      "loss": 0.5885,
      "step": 24781
    },
    {
      "epoch": 0.7612816023100789,
      "grad_norm": 2.2890210151672363,
      "learning_rate": 1.3690805531602358e-05,
      "loss": 0.5688,
      "step": 24782
    },
    {
      "epoch": 0.7613123214450281,
      "grad_norm": 0.37775078415870667,
      "learning_rate": 1.3690356370587736e-05,
      "loss": 0.626,
      "step": 24783
    },
    {
      "epoch": 0.7613430405799773,
      "grad_norm": 0.3679448962211609,
      "learning_rate": 1.3689907200954025e-05,
      "loss": 0.5048,
      "step": 24784
    },
    {
      "epoch": 0.7613737597149264,
      "grad_norm": 0.4059910178184509,
      "learning_rate": 1.3689458022702277e-05,
      "loss": 0.5296,
      "step": 24785
    },
    {
      "epoch": 0.7614044788498756,
      "grad_norm": 0.3528602421283722,
      "learning_rate": 1.3689008835833546e-05,
      "loss": 0.548,
      "step": 24786
    },
    {
      "epoch": 0.7614351979848247,
      "grad_norm": 0.3877754509449005,
      "learning_rate": 1.3688559640348876e-05,
      "loss": 0.5175,
      "step": 24787
    },
    {
      "epoch": 0.761465917119774,
      "grad_norm": 0.35404568910598755,
      "learning_rate": 1.3688110436249316e-05,
      "loss": 0.5781,
      "step": 24788
    },
    {
      "epoch": 0.7614966362547231,
      "grad_norm": 0.35698819160461426,
      "learning_rate": 1.3687661223535918e-05,
      "loss": 0.5758,
      "step": 24789
    },
    {
      "epoch": 0.7615273553896722,
      "grad_norm": 0.36116865277290344,
      "learning_rate": 1.3687212002209729e-05,
      "loss": 0.5458,
      "step": 24790
    },
    {
      "epoch": 0.7615580745246214,
      "grad_norm": 0.3766316771507263,
      "learning_rate": 1.3686762772271799e-05,
      "loss": 0.5059,
      "step": 24791
    },
    {
      "epoch": 0.7615887936595706,
      "grad_norm": 0.3502940833568573,
      "learning_rate": 1.3686313533723177e-05,
      "loss": 0.5239,
      "step": 24792
    },
    {
      "epoch": 0.7616195127945197,
      "grad_norm": 0.3610153794288635,
      "learning_rate": 1.3685864286564914e-05,
      "loss": 0.5502,
      "step": 24793
    },
    {
      "epoch": 0.7616502319294689,
      "grad_norm": 0.41297203302383423,
      "learning_rate": 1.3685415030798054e-05,
      "loss": 0.5491,
      "step": 24794
    },
    {
      "epoch": 0.761680951064418,
      "grad_norm": 0.37176039814949036,
      "learning_rate": 1.3684965766423652e-05,
      "loss": 0.6189,
      "step": 24795
    },
    {
      "epoch": 0.7617116701993671,
      "grad_norm": 1.7753949165344238,
      "learning_rate": 1.3684516493442755e-05,
      "loss": 0.5959,
      "step": 24796
    },
    {
      "epoch": 0.7617423893343164,
      "grad_norm": 0.32361510396003723,
      "learning_rate": 1.3684067211856413e-05,
      "loss": 0.412,
      "step": 24797
    },
    {
      "epoch": 0.7617731084692655,
      "grad_norm": 0.48383447527885437,
      "learning_rate": 1.3683617921665673e-05,
      "loss": 0.7219,
      "step": 24798
    },
    {
      "epoch": 0.7618038276042146,
      "grad_norm": 0.6256800293922424,
      "learning_rate": 1.3683168622871587e-05,
      "loss": 0.6611,
      "step": 24799
    },
    {
      "epoch": 0.7618345467391638,
      "grad_norm": 0.3636181652545929,
      "learning_rate": 1.3682719315475201e-05,
      "loss": 0.5581,
      "step": 24800
    },
    {
      "epoch": 0.761865265874113,
      "grad_norm": 0.3410240709781647,
      "learning_rate": 1.3682269999477571e-05,
      "loss": 0.4824,
      "step": 24801
    },
    {
      "epoch": 0.7618959850090622,
      "grad_norm": 0.3477421998977661,
      "learning_rate": 1.368182067487974e-05,
      "loss": 0.5152,
      "step": 24802
    },
    {
      "epoch": 0.7619267041440113,
      "grad_norm": 0.34192943572998047,
      "learning_rate": 1.3681371341682759e-05,
      "loss": 0.489,
      "step": 24803
    },
    {
      "epoch": 0.7619574232789604,
      "grad_norm": 0.36760637164115906,
      "learning_rate": 1.368092199988768e-05,
      "loss": 0.5444,
      "step": 24804
    },
    {
      "epoch": 0.7619881424139097,
      "grad_norm": 0.35735073685646057,
      "learning_rate": 1.3680472649495549e-05,
      "loss": 0.5714,
      "step": 24805
    },
    {
      "epoch": 0.7620188615488588,
      "grad_norm": 0.4344329535961151,
      "learning_rate": 1.3680023290507421e-05,
      "loss": 0.512,
      "step": 24806
    },
    {
      "epoch": 0.7620495806838079,
      "grad_norm": 0.3560599982738495,
      "learning_rate": 1.3679573922924336e-05,
      "loss": 0.5711,
      "step": 24807
    },
    {
      "epoch": 0.7620802998187571,
      "grad_norm": 0.37296566367149353,
      "learning_rate": 1.3679124546747353e-05,
      "loss": 0.5767,
      "step": 24808
    },
    {
      "epoch": 0.7621110189537063,
      "grad_norm": 0.3992645740509033,
      "learning_rate": 1.3678675161977514e-05,
      "loss": 0.5629,
      "step": 24809
    },
    {
      "epoch": 0.7621417380886554,
      "grad_norm": 0.3465641736984253,
      "learning_rate": 1.3678225768615876e-05,
      "loss": 0.5548,
      "step": 24810
    },
    {
      "epoch": 0.7621724572236046,
      "grad_norm": 0.3217983543872833,
      "learning_rate": 1.3677776366663484e-05,
      "loss": 0.5239,
      "step": 24811
    },
    {
      "epoch": 0.7622031763585537,
      "grad_norm": 0.38258057832717896,
      "learning_rate": 1.3677326956121389e-05,
      "loss": 0.5918,
      "step": 24812
    },
    {
      "epoch": 0.762233895493503,
      "grad_norm": 0.341693252325058,
      "learning_rate": 1.3676877536990638e-05,
      "loss": 0.4783,
      "step": 24813
    },
    {
      "epoch": 0.7622646146284521,
      "grad_norm": 0.35746219754219055,
      "learning_rate": 1.3676428109272283e-05,
      "loss": 0.5763,
      "step": 24814
    },
    {
      "epoch": 0.7622953337634012,
      "grad_norm": 0.3892875909805298,
      "learning_rate": 1.3675978672967376e-05,
      "loss": 0.5594,
      "step": 24815
    },
    {
      "epoch": 0.7623260528983504,
      "grad_norm": 0.35998618602752686,
      "learning_rate": 1.3675529228076961e-05,
      "loss": 0.5283,
      "step": 24816
    },
    {
      "epoch": 0.7623567720332995,
      "grad_norm": 0.45389288663864136,
      "learning_rate": 1.367507977460209e-05,
      "loss": 0.5446,
      "step": 24817
    },
    {
      "epoch": 0.7623874911682487,
      "grad_norm": 0.4153731167316437,
      "learning_rate": 1.3674630312543817e-05,
      "loss": 0.5125,
      "step": 24818
    },
    {
      "epoch": 0.7624182103031979,
      "grad_norm": 0.37831416726112366,
      "learning_rate": 1.3674180841903186e-05,
      "loss": 0.6109,
      "step": 24819
    },
    {
      "epoch": 0.762448929438147,
      "grad_norm": 0.3374532163143158,
      "learning_rate": 1.367373136268125e-05,
      "loss": 0.5814,
      "step": 24820
    },
    {
      "epoch": 0.7624796485730961,
      "grad_norm": 0.35326147079467773,
      "learning_rate": 1.3673281874879057e-05,
      "loss": 0.5677,
      "step": 24821
    },
    {
      "epoch": 0.7625103677080454,
      "grad_norm": 0.3729391396045685,
      "learning_rate": 1.3672832378497658e-05,
      "loss": 0.6102,
      "step": 24822
    },
    {
      "epoch": 0.7625410868429945,
      "grad_norm": 0.36181408166885376,
      "learning_rate": 1.3672382873538101e-05,
      "loss": 0.438,
      "step": 24823
    },
    {
      "epoch": 0.7625718059779436,
      "grad_norm": 0.3394329249858856,
      "learning_rate": 1.3671933360001441e-05,
      "loss": 0.5502,
      "step": 24824
    },
    {
      "epoch": 0.7626025251128928,
      "grad_norm": 0.5988556742668152,
      "learning_rate": 1.3671483837888721e-05,
      "loss": 0.4903,
      "step": 24825
    },
    {
      "epoch": 0.762633244247842,
      "grad_norm": 0.4955488443374634,
      "learning_rate": 1.3671034307200996e-05,
      "loss": 0.6093,
      "step": 24826
    },
    {
      "epoch": 0.7626639633827912,
      "grad_norm": 0.3913930058479309,
      "learning_rate": 1.3670584767939317e-05,
      "loss": 0.519,
      "step": 24827
    },
    {
      "epoch": 0.7626946825177403,
      "grad_norm": 0.4424270689487457,
      "learning_rate": 1.3670135220104726e-05,
      "loss": 0.5157,
      "step": 24828
    },
    {
      "epoch": 0.7627254016526894,
      "grad_norm": 0.36992400884628296,
      "learning_rate": 1.366968566369828e-05,
      "loss": 0.5436,
      "step": 24829
    },
    {
      "epoch": 0.7627561207876387,
      "grad_norm": 0.3579747974872589,
      "learning_rate": 1.3669236098721024e-05,
      "loss": 0.5594,
      "step": 24830
    },
    {
      "epoch": 0.7627868399225878,
      "grad_norm": 0.34570643305778503,
      "learning_rate": 1.3668786525174014e-05,
      "loss": 0.4537,
      "step": 24831
    },
    {
      "epoch": 0.7628175590575369,
      "grad_norm": 0.37378138303756714,
      "learning_rate": 1.3668336943058294e-05,
      "loss": 0.6537,
      "step": 24832
    },
    {
      "epoch": 0.7628482781924861,
      "grad_norm": 0.3509792983531952,
      "learning_rate": 1.366788735237492e-05,
      "loss": 0.4995,
      "step": 24833
    },
    {
      "epoch": 0.7628789973274352,
      "grad_norm": 0.3767419457435608,
      "learning_rate": 1.3667437753124937e-05,
      "loss": 0.5964,
      "step": 24834
    },
    {
      "epoch": 0.7629097164623844,
      "grad_norm": 0.387366384267807,
      "learning_rate": 1.3666988145309397e-05,
      "loss": 0.5636,
      "step": 24835
    },
    {
      "epoch": 0.7629404355973336,
      "grad_norm": 0.385545551776886,
      "learning_rate": 1.3666538528929349e-05,
      "loss": 0.5805,
      "step": 24836
    },
    {
      "epoch": 0.7629711547322827,
      "grad_norm": 0.4078127145767212,
      "learning_rate": 1.3666088903985849e-05,
      "loss": 0.6336,
      "step": 24837
    },
    {
      "epoch": 0.763001873867232,
      "grad_norm": 0.3799315094947815,
      "learning_rate": 1.3665639270479938e-05,
      "loss": 0.5636,
      "step": 24838
    },
    {
      "epoch": 0.7630325930021811,
      "grad_norm": 0.3548796772956848,
      "learning_rate": 1.366518962841267e-05,
      "loss": 0.5724,
      "step": 24839
    },
    {
      "epoch": 0.7630633121371302,
      "grad_norm": 0.36335787177085876,
      "learning_rate": 1.3664739977785098e-05,
      "loss": 0.541,
      "step": 24840
    },
    {
      "epoch": 0.7630940312720794,
      "grad_norm": 0.3298206925392151,
      "learning_rate": 1.3664290318598268e-05,
      "loss": 0.4419,
      "step": 24841
    },
    {
      "epoch": 0.7631247504070285,
      "grad_norm": 0.3757633864879608,
      "learning_rate": 1.3663840650853233e-05,
      "loss": 0.5667,
      "step": 24842
    },
    {
      "epoch": 0.7631554695419777,
      "grad_norm": 0.3452656865119934,
      "learning_rate": 1.3663390974551042e-05,
      "loss": 0.6197,
      "step": 24843
    },
    {
      "epoch": 0.7631861886769269,
      "grad_norm": 0.39064252376556396,
      "learning_rate": 1.3662941289692749e-05,
      "loss": 0.5558,
      "step": 24844
    },
    {
      "epoch": 0.763216907811876,
      "grad_norm": 0.5123160481452942,
      "learning_rate": 1.3662491596279398e-05,
      "loss": 0.6113,
      "step": 24845
    },
    {
      "epoch": 0.7632476269468251,
      "grad_norm": 0.4105462431907654,
      "learning_rate": 1.3662041894312039e-05,
      "loss": 0.5907,
      "step": 24846
    },
    {
      "epoch": 0.7632783460817744,
      "grad_norm": 0.3727964460849762,
      "learning_rate": 1.366159218379173e-05,
      "loss": 0.637,
      "step": 24847
    },
    {
      "epoch": 0.7633090652167235,
      "grad_norm": 0.31496661901474,
      "learning_rate": 1.3661142464719514e-05,
      "loss": 0.4611,
      "step": 24848
    },
    {
      "epoch": 0.7633397843516727,
      "grad_norm": 0.35486555099487305,
      "learning_rate": 1.3660692737096445e-05,
      "loss": 0.4917,
      "step": 24849
    },
    {
      "epoch": 0.7633705034866218,
      "grad_norm": 0.4140135943889618,
      "learning_rate": 1.3660243000923572e-05,
      "loss": 0.5165,
      "step": 24850
    },
    {
      "epoch": 0.763401222621571,
      "grad_norm": 0.3506843149662018,
      "learning_rate": 1.3659793256201947e-05,
      "loss": 0.523,
      "step": 24851
    },
    {
      "epoch": 0.7634319417565202,
      "grad_norm": 0.38134410977363586,
      "learning_rate": 1.3659343502932618e-05,
      "loss": 0.5974,
      "step": 24852
    },
    {
      "epoch": 0.7634626608914693,
      "grad_norm": 0.35846415162086487,
      "learning_rate": 1.3658893741116637e-05,
      "loss": 0.5665,
      "step": 24853
    },
    {
      "epoch": 0.7634933800264184,
      "grad_norm": 0.33520522713661194,
      "learning_rate": 1.3658443970755056e-05,
      "loss": 0.4796,
      "step": 24854
    },
    {
      "epoch": 0.7635240991613677,
      "grad_norm": 0.39846882224082947,
      "learning_rate": 1.3657994191848923e-05,
      "loss": 0.6543,
      "step": 24855
    },
    {
      "epoch": 0.7635548182963168,
      "grad_norm": 0.34378230571746826,
      "learning_rate": 1.3657544404399287e-05,
      "loss": 0.538,
      "step": 24856
    },
    {
      "epoch": 0.7635855374312659,
      "grad_norm": 0.36865437030792236,
      "learning_rate": 1.3657094608407198e-05,
      "loss": 0.5997,
      "step": 24857
    },
    {
      "epoch": 0.7636162565662151,
      "grad_norm": 0.3704356849193573,
      "learning_rate": 1.3656644803873716e-05,
      "loss": 0.5987,
      "step": 24858
    },
    {
      "epoch": 0.7636469757011642,
      "grad_norm": 0.3306543529033661,
      "learning_rate": 1.3656194990799878e-05,
      "loss": 0.5635,
      "step": 24859
    },
    {
      "epoch": 0.7636776948361134,
      "grad_norm": 0.35839489102363586,
      "learning_rate": 1.3655745169186747e-05,
      "loss": 0.5379,
      "step": 24860
    },
    {
      "epoch": 0.7637084139710626,
      "grad_norm": 0.3894651532173157,
      "learning_rate": 1.3655295339035363e-05,
      "loss": 0.5694,
      "step": 24861
    },
    {
      "epoch": 0.7637391331060117,
      "grad_norm": 0.4283374845981598,
      "learning_rate": 1.3654845500346787e-05,
      "loss": 0.5562,
      "step": 24862
    },
    {
      "epoch": 0.763769852240961,
      "grad_norm": 0.420047402381897,
      "learning_rate": 1.3654395653122061e-05,
      "loss": 0.4956,
      "step": 24863
    },
    {
      "epoch": 0.7638005713759101,
      "grad_norm": 0.37703144550323486,
      "learning_rate": 1.3653945797362239e-05,
      "loss": 0.5692,
      "step": 24864
    },
    {
      "epoch": 0.7638312905108592,
      "grad_norm": 0.3990285396575928,
      "learning_rate": 1.3653495933068373e-05,
      "loss": 0.4592,
      "step": 24865
    },
    {
      "epoch": 0.7638620096458084,
      "grad_norm": 0.36058861017227173,
      "learning_rate": 1.3653046060241509e-05,
      "loss": 0.563,
      "step": 24866
    },
    {
      "epoch": 0.7638927287807575,
      "grad_norm": 0.3791651427745819,
      "learning_rate": 1.3652596178882702e-05,
      "loss": 0.4521,
      "step": 24867
    },
    {
      "epoch": 0.7639234479157067,
      "grad_norm": 0.5185900926589966,
      "learning_rate": 1.3652146288993e-05,
      "loss": 0.5165,
      "step": 24868
    },
    {
      "epoch": 0.7639541670506559,
      "grad_norm": 0.34065425395965576,
      "learning_rate": 1.3651696390573459e-05,
      "loss": 0.6062,
      "step": 24869
    },
    {
      "epoch": 0.763984886185605,
      "grad_norm": 0.45362338423728943,
      "learning_rate": 1.3651246483625123e-05,
      "loss": 0.5933,
      "step": 24870
    },
    {
      "epoch": 0.7640156053205541,
      "grad_norm": 0.34306851029396057,
      "learning_rate": 1.3650796568149047e-05,
      "loss": 0.5071,
      "step": 24871
    },
    {
      "epoch": 0.7640463244555034,
      "grad_norm": 0.39697372913360596,
      "learning_rate": 1.3650346644146279e-05,
      "loss": 0.5498,
      "step": 24872
    },
    {
      "epoch": 0.7640770435904525,
      "grad_norm": 0.3477513790130615,
      "learning_rate": 1.3649896711617873e-05,
      "loss": 0.6226,
      "step": 24873
    },
    {
      "epoch": 0.7641077627254017,
      "grad_norm": 0.3893751800060272,
      "learning_rate": 1.364944677056488e-05,
      "loss": 0.5881,
      "step": 24874
    },
    {
      "epoch": 0.7641384818603508,
      "grad_norm": 0.3712425231933594,
      "learning_rate": 1.3648996820988348e-05,
      "loss": 0.4697,
      "step": 24875
    },
    {
      "epoch": 0.7641692009953,
      "grad_norm": 0.34565141797065735,
      "learning_rate": 1.3648546862889327e-05,
      "loss": 0.5767,
      "step": 24876
    },
    {
      "epoch": 0.7641999201302492,
      "grad_norm": 0.3542563319206238,
      "learning_rate": 1.364809689626887e-05,
      "loss": 0.5463,
      "step": 24877
    },
    {
      "epoch": 0.7642306392651983,
      "grad_norm": 0.3915903866291046,
      "learning_rate": 1.364764692112803e-05,
      "loss": 0.5885,
      "step": 24878
    },
    {
      "epoch": 0.7642613584001474,
      "grad_norm": 0.3511504828929901,
      "learning_rate": 1.3647196937467858e-05,
      "loss": 0.5469,
      "step": 24879
    },
    {
      "epoch": 0.7642920775350966,
      "grad_norm": 0.42392992973327637,
      "learning_rate": 1.3646746945289398e-05,
      "loss": 0.4637,
      "step": 24880
    },
    {
      "epoch": 0.7643227966700458,
      "grad_norm": 0.33258017897605896,
      "learning_rate": 1.3646296944593708e-05,
      "loss": 0.5171,
      "step": 24881
    },
    {
      "epoch": 0.7643535158049949,
      "grad_norm": 0.34693050384521484,
      "learning_rate": 1.3645846935381836e-05,
      "loss": 0.5361,
      "step": 24882
    },
    {
      "epoch": 0.7643842349399441,
      "grad_norm": 0.36420267820358276,
      "learning_rate": 1.3645396917654836e-05,
      "loss": 0.5725,
      "step": 24883
    },
    {
      "epoch": 0.7644149540748932,
      "grad_norm": 0.37480929493904114,
      "learning_rate": 1.3644946891413755e-05,
      "loss": 0.5902,
      "step": 24884
    },
    {
      "epoch": 0.7644456732098424,
      "grad_norm": 0.3494318723678589,
      "learning_rate": 1.3644496856659648e-05,
      "loss": 0.5322,
      "step": 24885
    },
    {
      "epoch": 0.7644763923447916,
      "grad_norm": 0.536396324634552,
      "learning_rate": 1.3644046813393562e-05,
      "loss": 0.5114,
      "step": 24886
    },
    {
      "epoch": 0.7645071114797407,
      "grad_norm": 0.3565390408039093,
      "learning_rate": 1.364359676161655e-05,
      "loss": 0.5254,
      "step": 24887
    },
    {
      "epoch": 0.7645378306146899,
      "grad_norm": 0.3672274649143219,
      "learning_rate": 1.3643146701329664e-05,
      "loss": 0.6287,
      "step": 24888
    },
    {
      "epoch": 0.7645685497496391,
      "grad_norm": 0.34631332755088806,
      "learning_rate": 1.3642696632533955e-05,
      "loss": 0.5738,
      "step": 24889
    },
    {
      "epoch": 0.7645992688845882,
      "grad_norm": 0.39493557810783386,
      "learning_rate": 1.3642246555230477e-05,
      "loss": 0.6058,
      "step": 24890
    },
    {
      "epoch": 0.7646299880195374,
      "grad_norm": 0.37140390276908875,
      "learning_rate": 1.3641796469420272e-05,
      "loss": 0.5652,
      "step": 24891
    },
    {
      "epoch": 0.7646607071544865,
      "grad_norm": 0.4242677390575409,
      "learning_rate": 1.3641346375104399e-05,
      "loss": 0.6004,
      "step": 24892
    },
    {
      "epoch": 0.7646914262894356,
      "grad_norm": 0.35220348834991455,
      "learning_rate": 1.3640896272283905e-05,
      "loss": 0.571,
      "step": 24893
    },
    {
      "epoch": 0.7647221454243849,
      "grad_norm": 0.3675151765346527,
      "learning_rate": 1.3640446160959846e-05,
      "loss": 0.5334,
      "step": 24894
    },
    {
      "epoch": 0.764752864559334,
      "grad_norm": 0.39021554589271545,
      "learning_rate": 1.3639996041133267e-05,
      "loss": 0.5827,
      "step": 24895
    },
    {
      "epoch": 0.7647835836942831,
      "grad_norm": 0.3392220735549927,
      "learning_rate": 1.363954591280523e-05,
      "loss": 0.4851,
      "step": 24896
    },
    {
      "epoch": 0.7648143028292324,
      "grad_norm": 0.3838150203227997,
      "learning_rate": 1.3639095775976776e-05,
      "loss": 0.5299,
      "step": 24897
    },
    {
      "epoch": 0.7648450219641815,
      "grad_norm": 0.3797084093093872,
      "learning_rate": 1.3638645630648958e-05,
      "loss": 0.5719,
      "step": 24898
    },
    {
      "epoch": 0.7648757410991307,
      "grad_norm": 0.382255882024765,
      "learning_rate": 1.3638195476822831e-05,
      "loss": 0.5584,
      "step": 24899
    },
    {
      "epoch": 0.7649064602340798,
      "grad_norm": 0.3634386360645294,
      "learning_rate": 1.3637745314499445e-05,
      "loss": 0.6002,
      "step": 24900
    },
    {
      "epoch": 0.7649371793690289,
      "grad_norm": 0.36770886182785034,
      "learning_rate": 1.363729514367985e-05,
      "loss": 0.5702,
      "step": 24901
    },
    {
      "epoch": 0.7649678985039782,
      "grad_norm": 0.3594289720058441,
      "learning_rate": 1.3636844964365095e-05,
      "loss": 0.5788,
      "step": 24902
    },
    {
      "epoch": 0.7649986176389273,
      "grad_norm": 0.3725540339946747,
      "learning_rate": 1.3636394776556239e-05,
      "loss": 0.4814,
      "step": 24903
    },
    {
      "epoch": 0.7650293367738764,
      "grad_norm": 0.45093923807144165,
      "learning_rate": 1.3635944580254328e-05,
      "loss": 0.5841,
      "step": 24904
    },
    {
      "epoch": 0.7650600559088256,
      "grad_norm": 0.35699784755706787,
      "learning_rate": 1.3635494375460414e-05,
      "loss": 0.4861,
      "step": 24905
    },
    {
      "epoch": 0.7650907750437748,
      "grad_norm": 0.3692987561225891,
      "learning_rate": 1.3635044162175547e-05,
      "loss": 0.5406,
      "step": 24906
    },
    {
      "epoch": 0.7651214941787239,
      "grad_norm": 0.4092206656932831,
      "learning_rate": 1.3634593940400785e-05,
      "loss": 0.6119,
      "step": 24907
    },
    {
      "epoch": 0.7651522133136731,
      "grad_norm": 0.35651594400405884,
      "learning_rate": 1.3634143710137173e-05,
      "loss": 0.4718,
      "step": 24908
    },
    {
      "epoch": 0.7651829324486222,
      "grad_norm": 0.3802582323551178,
      "learning_rate": 1.3633693471385764e-05,
      "loss": 0.5691,
      "step": 24909
    },
    {
      "epoch": 0.7652136515835714,
      "grad_norm": 0.3687051832675934,
      "learning_rate": 1.3633243224147608e-05,
      "loss": 0.5911,
      "step": 24910
    },
    {
      "epoch": 0.7652443707185206,
      "grad_norm": 0.3307221531867981,
      "learning_rate": 1.363279296842376e-05,
      "loss": 0.5207,
      "step": 24911
    },
    {
      "epoch": 0.7652750898534697,
      "grad_norm": 0.3604053258895874,
      "learning_rate": 1.363234270421527e-05,
      "loss": 0.5842,
      "step": 24912
    },
    {
      "epoch": 0.7653058089884189,
      "grad_norm": 0.36072754859924316,
      "learning_rate": 1.363189243152319e-05,
      "loss": 0.5535,
      "step": 24913
    },
    {
      "epoch": 0.765336528123368,
      "grad_norm": 0.37767407298088074,
      "learning_rate": 1.3631442150348573e-05,
      "loss": 0.5667,
      "step": 24914
    },
    {
      "epoch": 0.7653672472583172,
      "grad_norm": 0.4119238257408142,
      "learning_rate": 1.363099186069247e-05,
      "loss": 0.6069,
      "step": 24915
    },
    {
      "epoch": 0.7653979663932664,
      "grad_norm": 0.32469120621681213,
      "learning_rate": 1.363054156255593e-05,
      "loss": 0.5063,
      "step": 24916
    },
    {
      "epoch": 0.7654286855282155,
      "grad_norm": 0.3818756937980652,
      "learning_rate": 1.363009125594001e-05,
      "loss": 0.6019,
      "step": 24917
    },
    {
      "epoch": 0.7654594046631646,
      "grad_norm": 0.31135043501853943,
      "learning_rate": 1.3629640940845755e-05,
      "loss": 0.5072,
      "step": 24918
    },
    {
      "epoch": 0.7654901237981139,
      "grad_norm": 0.39141392707824707,
      "learning_rate": 1.3629190617274221e-05,
      "loss": 0.5416,
      "step": 24919
    },
    {
      "epoch": 0.765520842933063,
      "grad_norm": 0.36572346091270447,
      "learning_rate": 1.3628740285226458e-05,
      "loss": 0.361,
      "step": 24920
    },
    {
      "epoch": 0.7655515620680121,
      "grad_norm": 0.348009318113327,
      "learning_rate": 1.3628289944703518e-05,
      "loss": 0.6037,
      "step": 24921
    },
    {
      "epoch": 0.7655822812029613,
      "grad_norm": 0.3482336401939392,
      "learning_rate": 1.3627839595706456e-05,
      "loss": 0.586,
      "step": 24922
    },
    {
      "epoch": 0.7656130003379105,
      "grad_norm": 0.41492336988449097,
      "learning_rate": 1.3627389238236322e-05,
      "loss": 0.5347,
      "step": 24923
    },
    {
      "epoch": 0.7656437194728597,
      "grad_norm": 0.3689221441745758,
      "learning_rate": 1.3626938872294162e-05,
      "loss": 0.5379,
      "step": 24924
    },
    {
      "epoch": 0.7656744386078088,
      "grad_norm": 0.36454999446868896,
      "learning_rate": 1.3626488497881036e-05,
      "loss": 0.6837,
      "step": 24925
    },
    {
      "epoch": 0.7657051577427579,
      "grad_norm": 0.4205811023712158,
      "learning_rate": 1.3626038114997994e-05,
      "loss": 0.6159,
      "step": 24926
    },
    {
      "epoch": 0.7657358768777072,
      "grad_norm": 0.3462379574775696,
      "learning_rate": 1.3625587723646085e-05,
      "loss": 0.5324,
      "step": 24927
    },
    {
      "epoch": 0.7657665960126563,
      "grad_norm": 0.41707101464271545,
      "learning_rate": 1.3625137323826365e-05,
      "loss": 0.5761,
      "step": 24928
    },
    {
      "epoch": 0.7657973151476054,
      "grad_norm": 0.3887665569782257,
      "learning_rate": 1.3624686915539881e-05,
      "loss": 0.5603,
      "step": 24929
    },
    {
      "epoch": 0.7658280342825546,
      "grad_norm": 0.3955906629562378,
      "learning_rate": 1.3624236498787688e-05,
      "loss": 0.554,
      "step": 24930
    },
    {
      "epoch": 0.7658587534175038,
      "grad_norm": 0.39125382900238037,
      "learning_rate": 1.3623786073570839e-05,
      "loss": 0.6618,
      "step": 24931
    },
    {
      "epoch": 0.7658894725524529,
      "grad_norm": 0.3610444664955139,
      "learning_rate": 1.3623335639890382e-05,
      "loss": 0.4791,
      "step": 24932
    },
    {
      "epoch": 0.7659201916874021,
      "grad_norm": 0.3974887430667877,
      "learning_rate": 1.3622885197747375e-05,
      "loss": 0.6531,
      "step": 24933
    },
    {
      "epoch": 0.7659509108223512,
      "grad_norm": 0.3536822199821472,
      "learning_rate": 1.3622434747142863e-05,
      "loss": 0.6179,
      "step": 24934
    },
    {
      "epoch": 0.7659816299573003,
      "grad_norm": 0.3788353502750397,
      "learning_rate": 1.3621984288077905e-05,
      "loss": 0.5601,
      "step": 24935
    },
    {
      "epoch": 0.7660123490922496,
      "grad_norm": 0.35983753204345703,
      "learning_rate": 1.3621533820553547e-05,
      "loss": 0.5597,
      "step": 24936
    },
    {
      "epoch": 0.7660430682271987,
      "grad_norm": 0.4721589982509613,
      "learning_rate": 1.3621083344570844e-05,
      "loss": 0.5364,
      "step": 24937
    },
    {
      "epoch": 0.7660737873621479,
      "grad_norm": 0.41371145844459534,
      "learning_rate": 1.3620632860130849e-05,
      "loss": 0.5409,
      "step": 24938
    },
    {
      "epoch": 0.766104506497097,
      "grad_norm": 0.4147651791572571,
      "learning_rate": 1.3620182367234613e-05,
      "loss": 0.5407,
      "step": 24939
    },
    {
      "epoch": 0.7661352256320462,
      "grad_norm": 0.5441293716430664,
      "learning_rate": 1.3619731865883189e-05,
      "loss": 0.5402,
      "step": 24940
    },
    {
      "epoch": 0.7661659447669954,
      "grad_norm": 0.3566250801086426,
      "learning_rate": 1.3619281356077628e-05,
      "loss": 0.5502,
      "step": 24941
    },
    {
      "epoch": 0.7661966639019445,
      "grad_norm": 0.38307908177375793,
      "learning_rate": 1.3618830837818983e-05,
      "loss": 0.512,
      "step": 24942
    },
    {
      "epoch": 0.7662273830368936,
      "grad_norm": 0.3521329164505005,
      "learning_rate": 1.3618380311108305e-05,
      "loss": 0.6146,
      "step": 24943
    },
    {
      "epoch": 0.7662581021718429,
      "grad_norm": 0.3550097346305847,
      "learning_rate": 1.3617929775946647e-05,
      "loss": 0.5118,
      "step": 24944
    },
    {
      "epoch": 0.766288821306792,
      "grad_norm": 0.3726860582828522,
      "learning_rate": 1.361747923233506e-05,
      "loss": 0.54,
      "step": 24945
    },
    {
      "epoch": 0.7663195404417411,
      "grad_norm": 0.404603511095047,
      "learning_rate": 1.3617028680274601e-05,
      "loss": 0.5014,
      "step": 24946
    },
    {
      "epoch": 0.7663502595766903,
      "grad_norm": 0.39679834246635437,
      "learning_rate": 1.3616578119766318e-05,
      "loss": 0.5567,
      "step": 24947
    },
    {
      "epoch": 0.7663809787116395,
      "grad_norm": 0.356781005859375,
      "learning_rate": 1.3616127550811262e-05,
      "loss": 0.5022,
      "step": 24948
    },
    {
      "epoch": 0.7664116978465887,
      "grad_norm": 0.36006176471710205,
      "learning_rate": 1.361567697341049e-05,
      "loss": 0.5413,
      "step": 24949
    },
    {
      "epoch": 0.7664424169815378,
      "grad_norm": 0.3754239082336426,
      "learning_rate": 1.3615226387565049e-05,
      "loss": 0.5836,
      "step": 24950
    },
    {
      "epoch": 0.7664731361164869,
      "grad_norm": 0.3386780321598053,
      "learning_rate": 1.3614775793275997e-05,
      "loss": 0.465,
      "step": 24951
    },
    {
      "epoch": 0.7665038552514362,
      "grad_norm": 0.36957573890686035,
      "learning_rate": 1.3614325190544383e-05,
      "loss": 0.4945,
      "step": 24952
    },
    {
      "epoch": 0.7665345743863853,
      "grad_norm": 0.35073724389076233,
      "learning_rate": 1.3613874579371258e-05,
      "loss": 0.5885,
      "step": 24953
    },
    {
      "epoch": 0.7665652935213344,
      "grad_norm": 0.3627093732357025,
      "learning_rate": 1.361342395975768e-05,
      "loss": 0.5718,
      "step": 24954
    },
    {
      "epoch": 0.7665960126562836,
      "grad_norm": 0.35836711525917053,
      "learning_rate": 1.3612973331704695e-05,
      "loss": 0.5182,
      "step": 24955
    },
    {
      "epoch": 0.7666267317912328,
      "grad_norm": 0.38514816761016846,
      "learning_rate": 1.361252269521336e-05,
      "loss": 0.5838,
      "step": 24956
    },
    {
      "epoch": 0.7666574509261819,
      "grad_norm": 0.3539328873157501,
      "learning_rate": 1.3612072050284726e-05,
      "loss": 0.5341,
      "step": 24957
    },
    {
      "epoch": 0.7666881700611311,
      "grad_norm": 0.3474467396736145,
      "learning_rate": 1.3611621396919845e-05,
      "loss": 0.5582,
      "step": 24958
    },
    {
      "epoch": 0.7667188891960802,
      "grad_norm": 0.3332984447479248,
      "learning_rate": 1.361117073511977e-05,
      "loss": 0.5812,
      "step": 24959
    },
    {
      "epoch": 0.7667496083310295,
      "grad_norm": 0.3503728210926056,
      "learning_rate": 1.3610720064885556e-05,
      "loss": 0.5687,
      "step": 24960
    },
    {
      "epoch": 0.7667803274659786,
      "grad_norm": 0.3708641231060028,
      "learning_rate": 1.361026938621825e-05,
      "loss": 0.5411,
      "step": 24961
    },
    {
      "epoch": 0.7668110466009277,
      "grad_norm": 0.4060436189174652,
      "learning_rate": 1.3609818699118908e-05,
      "loss": 0.6188,
      "step": 24962
    },
    {
      "epoch": 0.7668417657358769,
      "grad_norm": 0.36980435252189636,
      "learning_rate": 1.3609368003588583e-05,
      "loss": 0.5654,
      "step": 24963
    },
    {
      "epoch": 0.766872484870826,
      "grad_norm": 0.4734106659889221,
      "learning_rate": 1.3608917299628328e-05,
      "loss": 0.5094,
      "step": 24964
    },
    {
      "epoch": 0.7669032040057752,
      "grad_norm": 0.47517213225364685,
      "learning_rate": 1.3608466587239191e-05,
      "loss": 0.5358,
      "step": 24965
    },
    {
      "epoch": 0.7669339231407244,
      "grad_norm": 0.37680187821388245,
      "learning_rate": 1.3608015866422233e-05,
      "loss": 0.5151,
      "step": 24966
    },
    {
      "epoch": 0.7669646422756735,
      "grad_norm": 0.34504809975624084,
      "learning_rate": 1.3607565137178498e-05,
      "loss": 0.4921,
      "step": 24967
    },
    {
      "epoch": 0.7669953614106226,
      "grad_norm": 0.3435715436935425,
      "learning_rate": 1.3607114399509045e-05,
      "loss": 0.6485,
      "step": 24968
    },
    {
      "epoch": 0.7670260805455719,
      "grad_norm": 0.5246020555496216,
      "learning_rate": 1.3606663653414924e-05,
      "loss": 0.6898,
      "step": 24969
    },
    {
      "epoch": 0.767056799680521,
      "grad_norm": 0.3481222689151764,
      "learning_rate": 1.3606212898897186e-05,
      "loss": 0.605,
      "step": 24970
    },
    {
      "epoch": 0.7670875188154701,
      "grad_norm": 0.39010292291641235,
      "learning_rate": 1.3605762135956888e-05,
      "loss": 0.5744,
      "step": 24971
    },
    {
      "epoch": 0.7671182379504193,
      "grad_norm": 0.3232949674129486,
      "learning_rate": 1.3605311364595081e-05,
      "loss": 0.488,
      "step": 24972
    },
    {
      "epoch": 0.7671489570853685,
      "grad_norm": 0.3646180033683777,
      "learning_rate": 1.3604860584812817e-05,
      "loss": 0.5927,
      "step": 24973
    },
    {
      "epoch": 0.7671796762203177,
      "grad_norm": 0.34251669049263,
      "learning_rate": 1.3604409796611149e-05,
      "loss": 0.5533,
      "step": 24974
    },
    {
      "epoch": 0.7672103953552668,
      "grad_norm": 0.3801148533821106,
      "learning_rate": 1.3603958999991132e-05,
      "loss": 0.595,
      "step": 24975
    },
    {
      "epoch": 0.7672411144902159,
      "grad_norm": 0.3655979633331299,
      "learning_rate": 1.3603508194953814e-05,
      "loss": 0.6026,
      "step": 24976
    },
    {
      "epoch": 0.7672718336251652,
      "grad_norm": 0.5854457020759583,
      "learning_rate": 1.3603057381500256e-05,
      "loss": 0.5321,
      "step": 24977
    },
    {
      "epoch": 0.7673025527601143,
      "grad_norm": 0.36726412177085876,
      "learning_rate": 1.3602606559631501e-05,
      "loss": 0.5757,
      "step": 24978
    },
    {
      "epoch": 0.7673332718950634,
      "grad_norm": 0.37196359038352966,
      "learning_rate": 1.3602155729348607e-05,
      "loss": 0.5442,
      "step": 24979
    },
    {
      "epoch": 0.7673639910300126,
      "grad_norm": 0.3720220625400543,
      "learning_rate": 1.360170489065263e-05,
      "loss": 0.6243,
      "step": 24980
    },
    {
      "epoch": 0.7673947101649617,
      "grad_norm": 0.38065969944000244,
      "learning_rate": 1.3601254043544616e-05,
      "loss": 0.6159,
      "step": 24981
    },
    {
      "epoch": 0.7674254292999109,
      "grad_norm": 0.3727025091648102,
      "learning_rate": 1.3600803188025624e-05,
      "loss": 0.5636,
      "step": 24982
    },
    {
      "epoch": 0.7674561484348601,
      "grad_norm": 0.38669082522392273,
      "learning_rate": 1.3600352324096705e-05,
      "loss": 0.5129,
      "step": 24983
    },
    {
      "epoch": 0.7674868675698092,
      "grad_norm": 0.3852042853832245,
      "learning_rate": 1.359990145175891e-05,
      "loss": 0.5824,
      "step": 24984
    },
    {
      "epoch": 0.7675175867047584,
      "grad_norm": 0.37443387508392334,
      "learning_rate": 1.3599450571013293e-05,
      "loss": 0.5913,
      "step": 24985
    },
    {
      "epoch": 0.7675483058397076,
      "grad_norm": 0.3735333979129791,
      "learning_rate": 1.359899968186091e-05,
      "loss": 0.5921,
      "step": 24986
    },
    {
      "epoch": 0.7675790249746567,
      "grad_norm": 0.348197877407074,
      "learning_rate": 1.359854878430281e-05,
      "loss": 0.472,
      "step": 24987
    },
    {
      "epoch": 0.7676097441096059,
      "grad_norm": 0.36187252402305603,
      "learning_rate": 1.3598097878340049e-05,
      "loss": 0.5717,
      "step": 24988
    },
    {
      "epoch": 0.767640463244555,
      "grad_norm": 0.32942429184913635,
      "learning_rate": 1.3597646963973682e-05,
      "loss": 0.5842,
      "step": 24989
    },
    {
      "epoch": 0.7676711823795042,
      "grad_norm": 0.3603527545928955,
      "learning_rate": 1.3597196041204754e-05,
      "loss": 0.5273,
      "step": 24990
    },
    {
      "epoch": 0.7677019015144534,
      "grad_norm": 0.3738291561603546,
      "learning_rate": 1.3596745110034326e-05,
      "loss": 0.5776,
      "step": 24991
    },
    {
      "epoch": 0.7677326206494025,
      "grad_norm": 0.4039291739463806,
      "learning_rate": 1.3596294170463449e-05,
      "loss": 0.5451,
      "step": 24992
    },
    {
      "epoch": 0.7677633397843516,
      "grad_norm": 0.3611345887184143,
      "learning_rate": 1.3595843222493175e-05,
      "loss": 0.578,
      "step": 24993
    },
    {
      "epoch": 0.7677940589193009,
      "grad_norm": 0.35797181725502014,
      "learning_rate": 1.359539226612456e-05,
      "loss": 0.5121,
      "step": 24994
    },
    {
      "epoch": 0.76782477805425,
      "grad_norm": 0.36148926615715027,
      "learning_rate": 1.3594941301358652e-05,
      "loss": 0.5011,
      "step": 24995
    },
    {
      "epoch": 0.7678554971891991,
      "grad_norm": 0.4143373370170593,
      "learning_rate": 1.359449032819651e-05,
      "loss": 0.6353,
      "step": 24996
    },
    {
      "epoch": 0.7678862163241483,
      "grad_norm": 0.3831959068775177,
      "learning_rate": 1.3594039346639183e-05,
      "loss": 0.5515,
      "step": 24997
    },
    {
      "epoch": 0.7679169354590974,
      "grad_norm": 0.34459251165390015,
      "learning_rate": 1.3593588356687728e-05,
      "loss": 0.5905,
      "step": 24998
    },
    {
      "epoch": 0.7679476545940467,
      "grad_norm": 0.38996800780296326,
      "learning_rate": 1.3593137358343195e-05,
      "loss": 0.5182,
      "step": 24999
    },
    {
      "epoch": 0.7679783737289958,
      "grad_norm": 0.349935919046402,
      "learning_rate": 1.359268635160664e-05,
      "loss": 0.529,
      "step": 25000
    },
    {
      "epoch": 0.7680090928639449,
      "grad_norm": 0.5437840223312378,
      "learning_rate": 1.3592235336479114e-05,
      "loss": 0.5372,
      "step": 25001
    },
    {
      "epoch": 0.7680398119988942,
      "grad_norm": 0.3480723202228546,
      "learning_rate": 1.3591784312961673e-05,
      "loss": 0.6336,
      "step": 25002
    },
    {
      "epoch": 0.7680705311338433,
      "grad_norm": 0.4094555675983429,
      "learning_rate": 1.3591333281055366e-05,
      "loss": 0.575,
      "step": 25003
    },
    {
      "epoch": 0.7681012502687924,
      "grad_norm": 0.3662281632423401,
      "learning_rate": 1.359088224076125e-05,
      "loss": 0.5528,
      "step": 25004
    },
    {
      "epoch": 0.7681319694037416,
      "grad_norm": 0.32674098014831543,
      "learning_rate": 1.359043119208038e-05,
      "loss": 0.4938,
      "step": 25005
    },
    {
      "epoch": 0.7681626885386907,
      "grad_norm": 0.3768030107021332,
      "learning_rate": 1.3589980135013805e-05,
      "loss": 0.6062,
      "step": 25006
    },
    {
      "epoch": 0.7681934076736399,
      "grad_norm": 0.36800655722618103,
      "learning_rate": 1.3589529069562581e-05,
      "loss": 0.5024,
      "step": 25007
    },
    {
      "epoch": 0.7682241268085891,
      "grad_norm": 0.408626526594162,
      "learning_rate": 1.3589077995727762e-05,
      "loss": 0.6229,
      "step": 25008
    },
    {
      "epoch": 0.7682548459435382,
      "grad_norm": 0.8404573798179626,
      "learning_rate": 1.3588626913510404e-05,
      "loss": 0.4169,
      "step": 25009
    },
    {
      "epoch": 0.7682855650784874,
      "grad_norm": 0.3987136781215668,
      "learning_rate": 1.3588175822911551e-05,
      "loss": 0.5684,
      "step": 25010
    },
    {
      "epoch": 0.7683162842134366,
      "grad_norm": 0.3881964385509491,
      "learning_rate": 1.3587724723932264e-05,
      "loss": 0.5264,
      "step": 25011
    },
    {
      "epoch": 0.7683470033483857,
      "grad_norm": 0.3535960614681244,
      "learning_rate": 1.35872736165736e-05,
      "loss": 0.5642,
      "step": 25012
    },
    {
      "epoch": 0.7683777224833349,
      "grad_norm": 0.369853675365448,
      "learning_rate": 1.3586822500836603e-05,
      "loss": 0.5477,
      "step": 25013
    },
    {
      "epoch": 0.768408441618284,
      "grad_norm": 0.40143442153930664,
      "learning_rate": 1.3586371376722337e-05,
      "loss": 0.5625,
      "step": 25014
    },
    {
      "epoch": 0.7684391607532332,
      "grad_norm": 0.3828197717666626,
      "learning_rate": 1.3585920244231843e-05,
      "loss": 0.5269,
      "step": 25015
    },
    {
      "epoch": 0.7684698798881824,
      "grad_norm": 0.35121649503707886,
      "learning_rate": 1.3585469103366186e-05,
      "loss": 0.5423,
      "step": 25016
    },
    {
      "epoch": 0.7685005990231315,
      "grad_norm": 0.38839641213417053,
      "learning_rate": 1.3585017954126414e-05,
      "loss": 0.4885,
      "step": 25017
    },
    {
      "epoch": 0.7685313181580806,
      "grad_norm": 0.43228060007095337,
      "learning_rate": 1.3584566796513585e-05,
      "loss": 0.5616,
      "step": 25018
    },
    {
      "epoch": 0.7685620372930299,
      "grad_norm": 0.3588654100894928,
      "learning_rate": 1.3584115630528746e-05,
      "loss": 0.5539,
      "step": 25019
    },
    {
      "epoch": 0.768592756427979,
      "grad_norm": 0.3803045153617859,
      "learning_rate": 1.3583664456172958e-05,
      "loss": 0.6331,
      "step": 25020
    },
    {
      "epoch": 0.7686234755629281,
      "grad_norm": 0.3838726282119751,
      "learning_rate": 1.3583213273447268e-05,
      "loss": 0.5212,
      "step": 25021
    },
    {
      "epoch": 0.7686541946978773,
      "grad_norm": 0.4725419878959656,
      "learning_rate": 1.3582762082352737e-05,
      "loss": 0.5444,
      "step": 25022
    },
    {
      "epoch": 0.7686849138328264,
      "grad_norm": 0.3355001211166382,
      "learning_rate": 1.3582310882890413e-05,
      "loss": 0.4858,
      "step": 25023
    },
    {
      "epoch": 0.7687156329677757,
      "grad_norm": 0.41640859842300415,
      "learning_rate": 1.3581859675061351e-05,
      "loss": 0.4675,
      "step": 25024
    },
    {
      "epoch": 0.7687463521027248,
      "grad_norm": 0.422065794467926,
      "learning_rate": 1.3581408458866605e-05,
      "loss": 0.6257,
      "step": 25025
    },
    {
      "epoch": 0.7687770712376739,
      "grad_norm": 0.4078989326953888,
      "learning_rate": 1.3580957234307231e-05,
      "loss": 0.6903,
      "step": 25026
    },
    {
      "epoch": 0.7688077903726231,
      "grad_norm": 0.3419201672077179,
      "learning_rate": 1.3580506001384282e-05,
      "loss": 0.5876,
      "step": 25027
    },
    {
      "epoch": 0.7688385095075723,
      "grad_norm": 0.34321269392967224,
      "learning_rate": 1.3580054760098808e-05,
      "loss": 0.5553,
      "step": 25028
    },
    {
      "epoch": 0.7688692286425214,
      "grad_norm": 0.3356737792491913,
      "learning_rate": 1.357960351045187e-05,
      "loss": 0.5528,
      "step": 25029
    },
    {
      "epoch": 0.7688999477774706,
      "grad_norm": 0.3701646625995636,
      "learning_rate": 1.3579152252444518e-05,
      "loss": 0.5955,
      "step": 25030
    },
    {
      "epoch": 0.7689306669124197,
      "grad_norm": 0.3505585491657257,
      "learning_rate": 1.3578700986077804e-05,
      "loss": 0.5652,
      "step": 25031
    },
    {
      "epoch": 0.7689613860473689,
      "grad_norm": 0.4406530559062958,
      "learning_rate": 1.3578249711352784e-05,
      "loss": 0.4708,
      "step": 25032
    },
    {
      "epoch": 0.7689921051823181,
      "grad_norm": 0.3742580711841583,
      "learning_rate": 1.3577798428270512e-05,
      "loss": 0.5343,
      "step": 25033
    },
    {
      "epoch": 0.7690228243172672,
      "grad_norm": 0.3983992338180542,
      "learning_rate": 1.3577347136832042e-05,
      "loss": 0.5841,
      "step": 25034
    },
    {
      "epoch": 0.7690535434522164,
      "grad_norm": 0.34734708070755005,
      "learning_rate": 1.3576895837038426e-05,
      "loss": 0.5747,
      "step": 25035
    },
    {
      "epoch": 0.7690842625871656,
      "grad_norm": 0.594036877155304,
      "learning_rate": 1.3576444528890724e-05,
      "loss": 0.4733,
      "step": 25036
    },
    {
      "epoch": 0.7691149817221147,
      "grad_norm": 0.40043583512306213,
      "learning_rate": 1.3575993212389982e-05,
      "loss": 0.5978,
      "step": 25037
    },
    {
      "epoch": 0.7691457008570639,
      "grad_norm": 0.4173559248447418,
      "learning_rate": 1.3575541887537263e-05,
      "loss": 0.5418,
      "step": 25038
    },
    {
      "epoch": 0.769176419992013,
      "grad_norm": 0.37327417731285095,
      "learning_rate": 1.357509055433361e-05,
      "loss": 0.5809,
      "step": 25039
    },
    {
      "epoch": 0.7692071391269621,
      "grad_norm": 0.4071439504623413,
      "learning_rate": 1.3574639212780088e-05,
      "loss": 0.5188,
      "step": 25040
    },
    {
      "epoch": 0.7692378582619114,
      "grad_norm": 0.4102451503276825,
      "learning_rate": 1.3574187862877746e-05,
      "loss": 0.5193,
      "step": 25041
    },
    {
      "epoch": 0.7692685773968605,
      "grad_norm": 0.35419175028800964,
      "learning_rate": 1.3573736504627634e-05,
      "loss": 0.6053,
      "step": 25042
    },
    {
      "epoch": 0.7692992965318096,
      "grad_norm": 0.3791486918926239,
      "learning_rate": 1.3573285138030817e-05,
      "loss": 0.4754,
      "step": 25043
    },
    {
      "epoch": 0.7693300156667588,
      "grad_norm": 0.3579414486885071,
      "learning_rate": 1.3572833763088338e-05,
      "loss": 0.5068,
      "step": 25044
    },
    {
      "epoch": 0.769360734801708,
      "grad_norm": 0.37055540084838867,
      "learning_rate": 1.357238237980126e-05,
      "loss": 0.5995,
      "step": 25045
    },
    {
      "epoch": 0.7693914539366572,
      "grad_norm": 0.3754219114780426,
      "learning_rate": 1.3571930988170632e-05,
      "loss": 0.6239,
      "step": 25046
    },
    {
      "epoch": 0.7694221730716063,
      "grad_norm": 0.3256882131099701,
      "learning_rate": 1.3571479588197512e-05,
      "loss": 0.4934,
      "step": 25047
    },
    {
      "epoch": 0.7694528922065554,
      "grad_norm": 0.5269814133644104,
      "learning_rate": 1.357102817988295e-05,
      "loss": 0.4834,
      "step": 25048
    },
    {
      "epoch": 0.7694836113415047,
      "grad_norm": 0.3708003759384155,
      "learning_rate": 1.3570576763228e-05,
      "loss": 0.5517,
      "step": 25049
    },
    {
      "epoch": 0.7695143304764538,
      "grad_norm": 0.36905425786972046,
      "learning_rate": 1.3570125338233721e-05,
      "loss": 0.5501,
      "step": 25050
    },
    {
      "epoch": 0.7695450496114029,
      "grad_norm": 0.3507625460624695,
      "learning_rate": 1.3569673904901164e-05,
      "loss": 0.6024,
      "step": 25051
    },
    {
      "epoch": 0.7695757687463521,
      "grad_norm": 0.3424147963523865,
      "learning_rate": 1.3569222463231386e-05,
      "loss": 0.5295,
      "step": 25052
    },
    {
      "epoch": 0.7696064878813013,
      "grad_norm": 0.3464011251926422,
      "learning_rate": 1.3568771013225439e-05,
      "loss": 0.5378,
      "step": 25053
    },
    {
      "epoch": 0.7696372070162504,
      "grad_norm": 0.373953253030777,
      "learning_rate": 1.356831955488438e-05,
      "loss": 0.5842,
      "step": 25054
    },
    {
      "epoch": 0.7696679261511996,
      "grad_norm": 0.4674237370491028,
      "learning_rate": 1.3567868088209256e-05,
      "loss": 0.49,
      "step": 25055
    },
    {
      "epoch": 0.7696986452861487,
      "grad_norm": 0.3209557831287384,
      "learning_rate": 1.3567416613201132e-05,
      "loss": 0.5008,
      "step": 25056
    },
    {
      "epoch": 0.7697293644210979,
      "grad_norm": 0.455188512802124,
      "learning_rate": 1.3566965129861054e-05,
      "loss": 0.5455,
      "step": 25057
    },
    {
      "epoch": 0.7697600835560471,
      "grad_norm": 0.37587565183639526,
      "learning_rate": 1.356651363819008e-05,
      "loss": 0.5359,
      "step": 25058
    },
    {
      "epoch": 0.7697908026909962,
      "grad_norm": 0.4054117500782013,
      "learning_rate": 1.3566062138189266e-05,
      "loss": 0.5234,
      "step": 25059
    },
    {
      "epoch": 0.7698215218259454,
      "grad_norm": 0.35899609327316284,
      "learning_rate": 1.3565610629859664e-05,
      "loss": 0.6039,
      "step": 25060
    },
    {
      "epoch": 0.7698522409608946,
      "grad_norm": 0.36488184332847595,
      "learning_rate": 1.3565159113202331e-05,
      "loss": 0.586,
      "step": 25061
    },
    {
      "epoch": 0.7698829600958437,
      "grad_norm": 0.46729856729507446,
      "learning_rate": 1.3564707588218318e-05,
      "loss": 0.5373,
      "step": 25062
    },
    {
      "epoch": 0.7699136792307929,
      "grad_norm": 0.3484896123409271,
      "learning_rate": 1.3564256054908682e-05,
      "loss": 0.5485,
      "step": 25063
    },
    {
      "epoch": 0.769944398365742,
      "grad_norm": 0.364341139793396,
      "learning_rate": 1.356380451327448e-05,
      "loss": 0.5555,
      "step": 25064
    },
    {
      "epoch": 0.7699751175006911,
      "grad_norm": 0.35936087369918823,
      "learning_rate": 1.3563352963316757e-05,
      "loss": 0.4535,
      "step": 25065
    },
    {
      "epoch": 0.7700058366356404,
      "grad_norm": 0.3345872163772583,
      "learning_rate": 1.3562901405036581e-05,
      "loss": 0.5324,
      "step": 25066
    },
    {
      "epoch": 0.7700365557705895,
      "grad_norm": 0.334243506193161,
      "learning_rate": 1.3562449838434995e-05,
      "loss": 0.5422,
      "step": 25067
    },
    {
      "epoch": 0.7700672749055386,
      "grad_norm": 0.3703859746456146,
      "learning_rate": 1.3561998263513062e-05,
      "loss": 0.5794,
      "step": 25068
    },
    {
      "epoch": 0.7700979940404878,
      "grad_norm": 0.388470321893692,
      "learning_rate": 1.3561546680271831e-05,
      "loss": 0.5125,
      "step": 25069
    },
    {
      "epoch": 0.770128713175437,
      "grad_norm": 0.37088581919670105,
      "learning_rate": 1.3561095088712362e-05,
      "loss": 0.5267,
      "step": 25070
    },
    {
      "epoch": 0.7701594323103862,
      "grad_norm": 0.3982499837875366,
      "learning_rate": 1.3560643488835703e-05,
      "loss": 0.4806,
      "step": 25071
    },
    {
      "epoch": 0.7701901514453353,
      "grad_norm": 0.3556261360645294,
      "learning_rate": 1.3560191880642914e-05,
      "loss": 0.5942,
      "step": 25072
    },
    {
      "epoch": 0.7702208705802844,
      "grad_norm": 0.38089048862457275,
      "learning_rate": 1.3559740264135049e-05,
      "loss": 0.6151,
      "step": 25073
    },
    {
      "epoch": 0.7702515897152337,
      "grad_norm": 0.3883792757987976,
      "learning_rate": 1.3559288639313162e-05,
      "loss": 0.5362,
      "step": 25074
    },
    {
      "epoch": 0.7702823088501828,
      "grad_norm": 0.36609527468681335,
      "learning_rate": 1.3558837006178307e-05,
      "loss": 0.5533,
      "step": 25075
    },
    {
      "epoch": 0.7703130279851319,
      "grad_norm": 0.3827510178089142,
      "learning_rate": 1.3558385364731536e-05,
      "loss": 0.5107,
      "step": 25076
    },
    {
      "epoch": 0.7703437471200811,
      "grad_norm": 0.3830660283565521,
      "learning_rate": 1.3557933714973914e-05,
      "loss": 0.5885,
      "step": 25077
    },
    {
      "epoch": 0.7703744662550303,
      "grad_norm": 0.3626924753189087,
      "learning_rate": 1.3557482056906487e-05,
      "loss": 0.5572,
      "step": 25078
    },
    {
      "epoch": 0.7704051853899794,
      "grad_norm": 0.377551794052124,
      "learning_rate": 1.355703039053031e-05,
      "loss": 0.6172,
      "step": 25079
    },
    {
      "epoch": 0.7704359045249286,
      "grad_norm": 0.4394228160381317,
      "learning_rate": 1.3556578715846442e-05,
      "loss": 0.5889,
      "step": 25080
    },
    {
      "epoch": 0.7704666236598777,
      "grad_norm": 0.38759759068489075,
      "learning_rate": 1.3556127032855936e-05,
      "loss": 0.5705,
      "step": 25081
    },
    {
      "epoch": 0.7704973427948268,
      "grad_norm": 0.35815930366516113,
      "learning_rate": 1.3555675341559849e-05,
      "loss": 0.5252,
      "step": 25082
    },
    {
      "epoch": 0.7705280619297761,
      "grad_norm": 0.3438185751438141,
      "learning_rate": 1.355522364195923e-05,
      "loss": 0.5092,
      "step": 25083
    },
    {
      "epoch": 0.7705587810647252,
      "grad_norm": 0.42313769459724426,
      "learning_rate": 1.355477193405514e-05,
      "loss": 0.5257,
      "step": 25084
    },
    {
      "epoch": 0.7705895001996744,
      "grad_norm": 0.3913126587867737,
      "learning_rate": 1.355432021784863e-05,
      "loss": 0.5003,
      "step": 25085
    },
    {
      "epoch": 0.7706202193346235,
      "grad_norm": 0.3594985008239746,
      "learning_rate": 1.355386849334076e-05,
      "loss": 0.6641,
      "step": 25086
    },
    {
      "epoch": 0.7706509384695727,
      "grad_norm": 0.34534427523612976,
      "learning_rate": 1.355341676053258e-05,
      "loss": 0.3843,
      "step": 25087
    },
    {
      "epoch": 0.7706816576045219,
      "grad_norm": 0.3628765344619751,
      "learning_rate": 1.3552965019425149e-05,
      "loss": 0.5709,
      "step": 25088
    },
    {
      "epoch": 0.770712376739471,
      "grad_norm": 0.3634449243545532,
      "learning_rate": 1.3552513270019516e-05,
      "loss": 0.6352,
      "step": 25089
    },
    {
      "epoch": 0.7707430958744201,
      "grad_norm": 0.3578571379184723,
      "learning_rate": 1.3552061512316743e-05,
      "loss": 0.5961,
      "step": 25090
    },
    {
      "epoch": 0.7707738150093694,
      "grad_norm": 0.3263482451438904,
      "learning_rate": 1.3551609746317883e-05,
      "loss": 0.5034,
      "step": 25091
    },
    {
      "epoch": 0.7708045341443185,
      "grad_norm": 0.4853779673576355,
      "learning_rate": 1.355115797202399e-05,
      "loss": 0.6338,
      "step": 25092
    },
    {
      "epoch": 0.7708352532792676,
      "grad_norm": 0.3736148178577423,
      "learning_rate": 1.355070618943612e-05,
      "loss": 0.5122,
      "step": 25093
    },
    {
      "epoch": 0.7708659724142168,
      "grad_norm": 0.3628641963005066,
      "learning_rate": 1.3550254398555325e-05,
      "loss": 0.6082,
      "step": 25094
    },
    {
      "epoch": 0.770896691549166,
      "grad_norm": 0.38551342487335205,
      "learning_rate": 1.3549802599382664e-05,
      "loss": 0.6026,
      "step": 25095
    },
    {
      "epoch": 0.7709274106841152,
      "grad_norm": 0.3508957624435425,
      "learning_rate": 1.354935079191919e-05,
      "loss": 0.5711,
      "step": 25096
    },
    {
      "epoch": 0.7709581298190643,
      "grad_norm": 0.4063415229320526,
      "learning_rate": 1.3548898976165962e-05,
      "loss": 0.5377,
      "step": 25097
    },
    {
      "epoch": 0.7709888489540134,
      "grad_norm": 0.4346368610858917,
      "learning_rate": 1.3548447152124032e-05,
      "loss": 0.5806,
      "step": 25098
    },
    {
      "epoch": 0.7710195680889627,
      "grad_norm": 0.3506107032299042,
      "learning_rate": 1.3547995319794454e-05,
      "loss": 0.5792,
      "step": 25099
    },
    {
      "epoch": 0.7710502872239118,
      "grad_norm": 0.3506418466567993,
      "learning_rate": 1.3547543479178286e-05,
      "loss": 0.5508,
      "step": 25100
    },
    {
      "epoch": 0.7710810063588609,
      "grad_norm": 0.38244837522506714,
      "learning_rate": 1.3547091630276582e-05,
      "loss": 0.5672,
      "step": 25101
    },
    {
      "epoch": 0.7711117254938101,
      "grad_norm": 0.5369490385055542,
      "learning_rate": 1.3546639773090401e-05,
      "loss": 0.5284,
      "step": 25102
    },
    {
      "epoch": 0.7711424446287592,
      "grad_norm": 0.3638518750667572,
      "learning_rate": 1.354618790762079e-05,
      "loss": 0.4987,
      "step": 25103
    },
    {
      "epoch": 0.7711731637637084,
      "grad_norm": 0.3941265642642975,
      "learning_rate": 1.3545736033868816e-05,
      "loss": 0.5434,
      "step": 25104
    },
    {
      "epoch": 0.7712038828986576,
      "grad_norm": 0.3749350309371948,
      "learning_rate": 1.3545284151835523e-05,
      "loss": 0.5687,
      "step": 25105
    },
    {
      "epoch": 0.7712346020336067,
      "grad_norm": 0.5561928749084473,
      "learning_rate": 1.3544832261521972e-05,
      "loss": 0.5415,
      "step": 25106
    },
    {
      "epoch": 0.7712653211685558,
      "grad_norm": 0.33463022112846375,
      "learning_rate": 1.3544380362929217e-05,
      "loss": 0.5041,
      "step": 25107
    },
    {
      "epoch": 0.7712960403035051,
      "grad_norm": 0.3655843138694763,
      "learning_rate": 1.3543928456058318e-05,
      "loss": 0.5679,
      "step": 25108
    },
    {
      "epoch": 0.7713267594384542,
      "grad_norm": 0.3489049971103668,
      "learning_rate": 1.3543476540910323e-05,
      "loss": 0.5075,
      "step": 25109
    },
    {
      "epoch": 0.7713574785734034,
      "grad_norm": 0.3696572184562683,
      "learning_rate": 1.3543024617486291e-05,
      "loss": 0.5419,
      "step": 25110
    },
    {
      "epoch": 0.7713881977083525,
      "grad_norm": 0.33624032139778137,
      "learning_rate": 1.3542572685787281e-05,
      "loss": 0.5379,
      "step": 25111
    },
    {
      "epoch": 0.7714189168433017,
      "grad_norm": 0.32390686869621277,
      "learning_rate": 1.354212074581434e-05,
      "loss": 0.534,
      "step": 25112
    },
    {
      "epoch": 0.7714496359782509,
      "grad_norm": 0.3823825418949127,
      "learning_rate": 1.354166879756853e-05,
      "loss": 0.6085,
      "step": 25113
    },
    {
      "epoch": 0.7714803551132,
      "grad_norm": 0.3734080493450165,
      "learning_rate": 1.3541216841050906e-05,
      "loss": 0.556,
      "step": 25114
    },
    {
      "epoch": 0.7715110742481491,
      "grad_norm": 0.3479909896850586,
      "learning_rate": 1.3540764876262524e-05,
      "loss": 0.4938,
      "step": 25115
    },
    {
      "epoch": 0.7715417933830984,
      "grad_norm": 0.34333518147468567,
      "learning_rate": 1.3540312903204438e-05,
      "loss": 0.4661,
      "step": 25116
    },
    {
      "epoch": 0.7715725125180475,
      "grad_norm": 0.3543761372566223,
      "learning_rate": 1.3539860921877703e-05,
      "loss": 0.5604,
      "step": 25117
    },
    {
      "epoch": 0.7716032316529966,
      "grad_norm": 0.35131391882896423,
      "learning_rate": 1.3539408932283378e-05,
      "loss": 0.5088,
      "step": 25118
    },
    {
      "epoch": 0.7716339507879458,
      "grad_norm": 0.40542617440223694,
      "learning_rate": 1.3538956934422512e-05,
      "loss": 0.5251,
      "step": 25119
    },
    {
      "epoch": 0.771664669922895,
      "grad_norm": 0.3643665611743927,
      "learning_rate": 1.3538504928296169e-05,
      "loss": 0.5212,
      "step": 25120
    },
    {
      "epoch": 0.7716953890578442,
      "grad_norm": 0.3585774600505829,
      "learning_rate": 1.3538052913905398e-05,
      "loss": 0.6189,
      "step": 25121
    },
    {
      "epoch": 0.7717261081927933,
      "grad_norm": 0.30950918793678284,
      "learning_rate": 1.353760089125126e-05,
      "loss": 0.5015,
      "step": 25122
    },
    {
      "epoch": 0.7717568273277424,
      "grad_norm": 0.37892773747444153,
      "learning_rate": 1.3537148860334803e-05,
      "loss": 0.6053,
      "step": 25123
    },
    {
      "epoch": 0.7717875464626917,
      "grad_norm": 0.39721906185150146,
      "learning_rate": 1.3536696821157091e-05,
      "loss": 0.5765,
      "step": 25124
    },
    {
      "epoch": 0.7718182655976408,
      "grad_norm": 0.3827485740184784,
      "learning_rate": 1.3536244773719176e-05,
      "loss": 0.6277,
      "step": 25125
    },
    {
      "epoch": 0.7718489847325899,
      "grad_norm": 0.47324299812316895,
      "learning_rate": 1.3535792718022116e-05,
      "loss": 0.5368,
      "step": 25126
    },
    {
      "epoch": 0.7718797038675391,
      "grad_norm": 0.34427133202552795,
      "learning_rate": 1.3535340654066965e-05,
      "loss": 0.5347,
      "step": 25127
    },
    {
      "epoch": 0.7719104230024882,
      "grad_norm": 0.37673231959342957,
      "learning_rate": 1.3534888581854777e-05,
      "loss": 0.5814,
      "step": 25128
    },
    {
      "epoch": 0.7719411421374374,
      "grad_norm": 0.42019209265708923,
      "learning_rate": 1.3534436501386612e-05,
      "loss": 0.4875,
      "step": 25129
    },
    {
      "epoch": 0.7719718612723866,
      "grad_norm": 0.36115792393684387,
      "learning_rate": 1.3533984412663521e-05,
      "loss": 0.5817,
      "step": 25130
    },
    {
      "epoch": 0.7720025804073357,
      "grad_norm": 0.3674725592136383,
      "learning_rate": 1.3533532315686563e-05,
      "loss": 0.5623,
      "step": 25131
    },
    {
      "epoch": 0.7720332995422848,
      "grad_norm": 0.37219691276550293,
      "learning_rate": 1.3533080210456796e-05,
      "loss": 0.5794,
      "step": 25132
    },
    {
      "epoch": 0.7720640186772341,
      "grad_norm": 0.36996641755104065,
      "learning_rate": 1.353262809697527e-05,
      "loss": 0.6163,
      "step": 25133
    },
    {
      "epoch": 0.7720947378121832,
      "grad_norm": 0.42371422052383423,
      "learning_rate": 1.353217597524305e-05,
      "loss": 0.5416,
      "step": 25134
    },
    {
      "epoch": 0.7721254569471324,
      "grad_norm": 0.4252770245075226,
      "learning_rate": 1.353172384526118e-05,
      "loss": 0.4982,
      "step": 25135
    },
    {
      "epoch": 0.7721561760820815,
      "grad_norm": 0.3493882715702057,
      "learning_rate": 1.3531271707030726e-05,
      "loss": 0.4959,
      "step": 25136
    },
    {
      "epoch": 0.7721868952170307,
      "grad_norm": 0.3705718517303467,
      "learning_rate": 1.353081956055274e-05,
      "loss": 0.5663,
      "step": 25137
    },
    {
      "epoch": 0.7722176143519799,
      "grad_norm": 0.3655765652656555,
      "learning_rate": 1.3530367405828277e-05,
      "loss": 0.5779,
      "step": 25138
    },
    {
      "epoch": 0.772248333486929,
      "grad_norm": 0.3717970848083496,
      "learning_rate": 1.3529915242858395e-05,
      "loss": 0.506,
      "step": 25139
    },
    {
      "epoch": 0.7722790526218781,
      "grad_norm": 0.3697565197944641,
      "learning_rate": 1.3529463071644151e-05,
      "loss": 0.5324,
      "step": 25140
    },
    {
      "epoch": 0.7723097717568274,
      "grad_norm": 0.4754319190979004,
      "learning_rate": 1.3529010892186596e-05,
      "loss": 0.591,
      "step": 25141
    },
    {
      "epoch": 0.7723404908917765,
      "grad_norm": 0.35305097699165344,
      "learning_rate": 1.3528558704486794e-05,
      "loss": 0.561,
      "step": 25142
    },
    {
      "epoch": 0.7723712100267256,
      "grad_norm": 0.3333267271518707,
      "learning_rate": 1.3528106508545791e-05,
      "loss": 0.5396,
      "step": 25143
    },
    {
      "epoch": 0.7724019291616748,
      "grad_norm": 0.360700786113739,
      "learning_rate": 1.3527654304364654e-05,
      "loss": 0.6128,
      "step": 25144
    },
    {
      "epoch": 0.772432648296624,
      "grad_norm": 0.4018217623233795,
      "learning_rate": 1.3527202091944434e-05,
      "loss": 0.5343,
      "step": 25145
    },
    {
      "epoch": 0.7724633674315732,
      "grad_norm": 0.515845537185669,
      "learning_rate": 1.3526749871286185e-05,
      "loss": 0.6422,
      "step": 25146
    },
    {
      "epoch": 0.7724940865665223,
      "grad_norm": 0.37371689081192017,
      "learning_rate": 1.3526297642390964e-05,
      "loss": 0.5668,
      "step": 25147
    },
    {
      "epoch": 0.7725248057014714,
      "grad_norm": 0.41571044921875,
      "learning_rate": 1.352584540525983e-05,
      "loss": 0.5498,
      "step": 25148
    },
    {
      "epoch": 0.7725555248364206,
      "grad_norm": 0.39307358860969543,
      "learning_rate": 1.3525393159893839e-05,
      "loss": 0.57,
      "step": 25149
    },
    {
      "epoch": 0.7725862439713698,
      "grad_norm": 0.32149896025657654,
      "learning_rate": 1.3524940906294041e-05,
      "loss": 0.5905,
      "step": 25150
    },
    {
      "epoch": 0.7726169631063189,
      "grad_norm": 0.3698086738586426,
      "learning_rate": 1.3524488644461504e-05,
      "loss": 0.4559,
      "step": 25151
    },
    {
      "epoch": 0.7726476822412681,
      "grad_norm": 0.3495207130908966,
      "learning_rate": 1.3524036374397275e-05,
      "loss": 0.5564,
      "step": 25152
    },
    {
      "epoch": 0.7726784013762172,
      "grad_norm": 0.3402637541294098,
      "learning_rate": 1.3523584096102413e-05,
      "loss": 0.5643,
      "step": 25153
    },
    {
      "epoch": 0.7727091205111664,
      "grad_norm": 0.3745013475418091,
      "learning_rate": 1.3523131809577976e-05,
      "loss": 0.5529,
      "step": 25154
    },
    {
      "epoch": 0.7727398396461156,
      "grad_norm": 0.362822562456131,
      "learning_rate": 1.3522679514825017e-05,
      "loss": 0.5845,
      "step": 25155
    },
    {
      "epoch": 0.7727705587810647,
      "grad_norm": 0.35359346866607666,
      "learning_rate": 1.3522227211844595e-05,
      "loss": 0.4878,
      "step": 25156
    },
    {
      "epoch": 0.7728012779160139,
      "grad_norm": 0.37099695205688477,
      "learning_rate": 1.3521774900637761e-05,
      "loss": 0.4887,
      "step": 25157
    },
    {
      "epoch": 0.7728319970509631,
      "grad_norm": 0.36537429690361023,
      "learning_rate": 1.3521322581205581e-05,
      "loss": 0.587,
      "step": 25158
    },
    {
      "epoch": 0.7728627161859122,
      "grad_norm": 0.31292474269866943,
      "learning_rate": 1.3520870253549103e-05,
      "loss": 0.5283,
      "step": 25159
    },
    {
      "epoch": 0.7728934353208614,
      "grad_norm": 0.34704798460006714,
      "learning_rate": 1.3520417917669391e-05,
      "loss": 0.5599,
      "step": 25160
    },
    {
      "epoch": 0.7729241544558105,
      "grad_norm": 0.33407044410705566,
      "learning_rate": 1.3519965573567491e-05,
      "loss": 0.5661,
      "step": 25161
    },
    {
      "epoch": 0.7729548735907597,
      "grad_norm": 0.3482835590839386,
      "learning_rate": 1.351951322124447e-05,
      "loss": 0.527,
      "step": 25162
    },
    {
      "epoch": 0.7729855927257089,
      "grad_norm": 0.4636492133140564,
      "learning_rate": 1.3519060860701379e-05,
      "loss": 0.6227,
      "step": 25163
    },
    {
      "epoch": 0.773016311860658,
      "grad_norm": 0.4204336404800415,
      "learning_rate": 1.3518608491939275e-05,
      "loss": 0.5296,
      "step": 25164
    },
    {
      "epoch": 0.7730470309956071,
      "grad_norm": 0.42802518606185913,
      "learning_rate": 1.3518156114959215e-05,
      "loss": 0.6183,
      "step": 25165
    },
    {
      "epoch": 0.7730777501305564,
      "grad_norm": 0.34051018953323364,
      "learning_rate": 1.3517703729762255e-05,
      "loss": 0.4807,
      "step": 25166
    },
    {
      "epoch": 0.7731084692655055,
      "grad_norm": 0.3681139349937439,
      "learning_rate": 1.3517251336349454e-05,
      "loss": 0.5061,
      "step": 25167
    },
    {
      "epoch": 0.7731391884004546,
      "grad_norm": 0.31925177574157715,
      "learning_rate": 1.3516798934721866e-05,
      "loss": 0.5194,
      "step": 25168
    },
    {
      "epoch": 0.7731699075354038,
      "grad_norm": 0.340689092874527,
      "learning_rate": 1.3516346524880548e-05,
      "loss": 0.5146,
      "step": 25169
    },
    {
      "epoch": 0.7732006266703529,
      "grad_norm": 0.4468967020511627,
      "learning_rate": 1.3515894106826558e-05,
      "loss": 0.5951,
      "step": 25170
    },
    {
      "epoch": 0.7732313458053022,
      "grad_norm": 0.37360602617263794,
      "learning_rate": 1.351544168056095e-05,
      "loss": 0.6344,
      "step": 25171
    },
    {
      "epoch": 0.7732620649402513,
      "grad_norm": 0.360920250415802,
      "learning_rate": 1.3514989246084786e-05,
      "loss": 0.5862,
      "step": 25172
    },
    {
      "epoch": 0.7732927840752004,
      "grad_norm": 0.3904268443584442,
      "learning_rate": 1.3514536803399115e-05,
      "loss": 0.5005,
      "step": 25173
    },
    {
      "epoch": 0.7733235032101496,
      "grad_norm": 0.424314945936203,
      "learning_rate": 1.3514084352505002e-05,
      "loss": 0.5092,
      "step": 25174
    },
    {
      "epoch": 0.7733542223450988,
      "grad_norm": 0.349274218082428,
      "learning_rate": 1.3513631893403495e-05,
      "loss": 0.5403,
      "step": 25175
    },
    {
      "epoch": 0.7733849414800479,
      "grad_norm": 0.35791221261024475,
      "learning_rate": 1.3513179426095659e-05,
      "loss": 0.5171,
      "step": 25176
    },
    {
      "epoch": 0.7734156606149971,
      "grad_norm": 0.33968386054039,
      "learning_rate": 1.3512726950582543e-05,
      "loss": 0.5408,
      "step": 25177
    },
    {
      "epoch": 0.7734463797499462,
      "grad_norm": 0.36292874813079834,
      "learning_rate": 1.3512274466865214e-05,
      "loss": 0.5715,
      "step": 25178
    },
    {
      "epoch": 0.7734770988848954,
      "grad_norm": 0.3391778767108917,
      "learning_rate": 1.3511821974944722e-05,
      "loss": 0.458,
      "step": 25179
    },
    {
      "epoch": 0.7735078180198446,
      "grad_norm": 0.35848307609558105,
      "learning_rate": 1.351136947482212e-05,
      "loss": 0.5543,
      "step": 25180
    },
    {
      "epoch": 0.7735385371547937,
      "grad_norm": 0.3925538957118988,
      "learning_rate": 1.3510916966498471e-05,
      "loss": 0.5665,
      "step": 25181
    },
    {
      "epoch": 0.7735692562897429,
      "grad_norm": 0.3666202425956726,
      "learning_rate": 1.3510464449974832e-05,
      "loss": 0.5702,
      "step": 25182
    },
    {
      "epoch": 0.773599975424692,
      "grad_norm": 0.5064810514450073,
      "learning_rate": 1.3510011925252255e-05,
      "loss": 0.5822,
      "step": 25183
    },
    {
      "epoch": 0.7736306945596412,
      "grad_norm": 0.36120423674583435,
      "learning_rate": 1.3509559392331802e-05,
      "loss": 0.5246,
      "step": 25184
    },
    {
      "epoch": 0.7736614136945904,
      "grad_norm": 0.3710765838623047,
      "learning_rate": 1.350910685121453e-05,
      "loss": 0.528,
      "step": 25185
    },
    {
      "epoch": 0.7736921328295395,
      "grad_norm": 0.39113208651542664,
      "learning_rate": 1.350865430190149e-05,
      "loss": 0.5967,
      "step": 25186
    },
    {
      "epoch": 0.7737228519644886,
      "grad_norm": 0.39366084337234497,
      "learning_rate": 1.3508201744393743e-05,
      "loss": 0.531,
      "step": 25187
    },
    {
      "epoch": 0.7737535710994379,
      "grad_norm": 0.5768016576766968,
      "learning_rate": 1.3507749178692346e-05,
      "loss": 0.5561,
      "step": 25188
    },
    {
      "epoch": 0.773784290234387,
      "grad_norm": 0.33897095918655396,
      "learning_rate": 1.3507296604798356e-05,
      "loss": 0.4866,
      "step": 25189
    },
    {
      "epoch": 0.7738150093693361,
      "grad_norm": 0.439957857131958,
      "learning_rate": 1.3506844022712832e-05,
      "loss": 0.5446,
      "step": 25190
    },
    {
      "epoch": 0.7738457285042853,
      "grad_norm": 0.3660014271736145,
      "learning_rate": 1.3506391432436827e-05,
      "loss": 0.5418,
      "step": 25191
    },
    {
      "epoch": 0.7738764476392345,
      "grad_norm": 0.36046698689460754,
      "learning_rate": 1.3505938833971402e-05,
      "loss": 0.5936,
      "step": 25192
    },
    {
      "epoch": 0.7739071667741836,
      "grad_norm": 0.37256497144699097,
      "learning_rate": 1.350548622731761e-05,
      "loss": 0.5671,
      "step": 25193
    },
    {
      "epoch": 0.7739378859091328,
      "grad_norm": 0.37172457575798035,
      "learning_rate": 1.3505033612476513e-05,
      "loss": 0.5398,
      "step": 25194
    },
    {
      "epoch": 0.7739686050440819,
      "grad_norm": 0.4176674485206604,
      "learning_rate": 1.350458098944916e-05,
      "loss": 0.601,
      "step": 25195
    },
    {
      "epoch": 0.7739993241790312,
      "grad_norm": 0.3282027840614319,
      "learning_rate": 1.3504128358236617e-05,
      "loss": 0.5401,
      "step": 25196
    },
    {
      "epoch": 0.7740300433139803,
      "grad_norm": 0.35868483781814575,
      "learning_rate": 1.350367571883994e-05,
      "loss": 0.5697,
      "step": 25197
    },
    {
      "epoch": 0.7740607624489294,
      "grad_norm": 0.33146336674690247,
      "learning_rate": 1.3503223071260178e-05,
      "loss": 0.4998,
      "step": 25198
    },
    {
      "epoch": 0.7740914815838786,
      "grad_norm": 0.4379097819328308,
      "learning_rate": 1.3502770415498396e-05,
      "loss": 0.5447,
      "step": 25199
    },
    {
      "epoch": 0.7741222007188278,
      "grad_norm": 0.34099557995796204,
      "learning_rate": 1.3502317751555649e-05,
      "loss": 0.5353,
      "step": 25200
    },
    {
      "epoch": 0.7741529198537769,
      "grad_norm": 0.4512154161930084,
      "learning_rate": 1.3501865079432994e-05,
      "loss": 0.5791,
      "step": 25201
    },
    {
      "epoch": 0.7741836389887261,
      "grad_norm": 0.35762810707092285,
      "learning_rate": 1.3501412399131488e-05,
      "loss": 0.5141,
      "step": 25202
    },
    {
      "epoch": 0.7742143581236752,
      "grad_norm": 0.4140133261680603,
      "learning_rate": 1.3500959710652192e-05,
      "loss": 0.5952,
      "step": 25203
    },
    {
      "epoch": 0.7742450772586243,
      "grad_norm": 0.3543786406517029,
      "learning_rate": 1.3500507013996159e-05,
      "loss": 0.5366,
      "step": 25204
    },
    {
      "epoch": 0.7742757963935736,
      "grad_norm": 0.3493157625198364,
      "learning_rate": 1.3500054309164443e-05,
      "loss": 0.5672,
      "step": 25205
    },
    {
      "epoch": 0.7743065155285227,
      "grad_norm": 0.3714223802089691,
      "learning_rate": 1.3499601596158112e-05,
      "loss": 0.5149,
      "step": 25206
    },
    {
      "epoch": 0.7743372346634719,
      "grad_norm": 0.4733324646949768,
      "learning_rate": 1.3499148874978211e-05,
      "loss": 0.5661,
      "step": 25207
    },
    {
      "epoch": 0.774367953798421,
      "grad_norm": 0.38066887855529785,
      "learning_rate": 1.349869614562581e-05,
      "loss": 0.5969,
      "step": 25208
    },
    {
      "epoch": 0.7743986729333702,
      "grad_norm": 0.36567452549934387,
      "learning_rate": 1.3498243408101955e-05,
      "loss": 0.5041,
      "step": 25209
    },
    {
      "epoch": 0.7744293920683194,
      "grad_norm": 0.31159812211990356,
      "learning_rate": 1.349779066240771e-05,
      "loss": 0.5187,
      "step": 25210
    },
    {
      "epoch": 0.7744601112032685,
      "grad_norm": 0.3633589744567871,
      "learning_rate": 1.3497337908544127e-05,
      "loss": 0.5678,
      "step": 25211
    },
    {
      "epoch": 0.7744908303382176,
      "grad_norm": 0.4474671483039856,
      "learning_rate": 1.3496885146512273e-05,
      "loss": 0.5063,
      "step": 25212
    },
    {
      "epoch": 0.7745215494731669,
      "grad_norm": 0.37399858236312866,
      "learning_rate": 1.3496432376313195e-05,
      "loss": 0.5879,
      "step": 25213
    },
    {
      "epoch": 0.774552268608116,
      "grad_norm": 0.3540458381175995,
      "learning_rate": 1.3495979597947959e-05,
      "loss": 0.5402,
      "step": 25214
    },
    {
      "epoch": 0.7745829877430651,
      "grad_norm": 0.3617362380027771,
      "learning_rate": 1.3495526811417618e-05,
      "loss": 0.5363,
      "step": 25215
    },
    {
      "epoch": 0.7746137068780143,
      "grad_norm": 0.3555610179901123,
      "learning_rate": 1.3495074016723227e-05,
      "loss": 0.5039,
      "step": 25216
    },
    {
      "epoch": 0.7746444260129635,
      "grad_norm": 0.39198052883148193,
      "learning_rate": 1.3494621213865848e-05,
      "loss": 0.49,
      "step": 25217
    },
    {
      "epoch": 0.7746751451479126,
      "grad_norm": 0.3302285671234131,
      "learning_rate": 1.3494168402846536e-05,
      "loss": 0.4957,
      "step": 25218
    },
    {
      "epoch": 0.7747058642828618,
      "grad_norm": 0.37303435802459717,
      "learning_rate": 1.3493715583666354e-05,
      "loss": 0.5541,
      "step": 25219
    },
    {
      "epoch": 0.7747365834178109,
      "grad_norm": 0.40773919224739075,
      "learning_rate": 1.3493262756326348e-05,
      "loss": 0.5536,
      "step": 25220
    },
    {
      "epoch": 0.7747673025527602,
      "grad_norm": 0.34209415316581726,
      "learning_rate": 1.349280992082759e-05,
      "loss": 0.5144,
      "step": 25221
    },
    {
      "epoch": 0.7747980216877093,
      "grad_norm": 0.33332929015159607,
      "learning_rate": 1.3492357077171126e-05,
      "loss": 0.5483,
      "step": 25222
    },
    {
      "epoch": 0.7748287408226584,
      "grad_norm": 0.35871657729148865,
      "learning_rate": 1.3491904225358016e-05,
      "loss": 0.5767,
      "step": 25223
    },
    {
      "epoch": 0.7748594599576076,
      "grad_norm": 0.36609935760498047,
      "learning_rate": 1.3491451365389326e-05,
      "loss": 0.6108,
      "step": 25224
    },
    {
      "epoch": 0.7748901790925568,
      "grad_norm": 0.34706488251686096,
      "learning_rate": 1.3490998497266104e-05,
      "loss": 0.5314,
      "step": 25225
    },
    {
      "epoch": 0.7749208982275059,
      "grad_norm": 0.4993201792240143,
      "learning_rate": 1.3490545620989412e-05,
      "loss": 0.5685,
      "step": 25226
    },
    {
      "epoch": 0.7749516173624551,
      "grad_norm": 0.3881640136241913,
      "learning_rate": 1.3490092736560304e-05,
      "loss": 0.5411,
      "step": 25227
    },
    {
      "epoch": 0.7749823364974042,
      "grad_norm": 0.3876967132091522,
      "learning_rate": 1.3489639843979846e-05,
      "loss": 0.52,
      "step": 25228
    },
    {
      "epoch": 0.7750130556323533,
      "grad_norm": 0.402572900056839,
      "learning_rate": 1.3489186943249086e-05,
      "loss": 0.5259,
      "step": 25229
    },
    {
      "epoch": 0.7750437747673026,
      "grad_norm": 0.39318907260894775,
      "learning_rate": 1.348873403436909e-05,
      "loss": 0.5199,
      "step": 25230
    },
    {
      "epoch": 0.7750744939022517,
      "grad_norm": 0.354442298412323,
      "learning_rate": 1.3488281117340911e-05,
      "loss": 0.5766,
      "step": 25231
    },
    {
      "epoch": 0.7751052130372009,
      "grad_norm": 0.5182688236236572,
      "learning_rate": 1.3487828192165606e-05,
      "loss": 0.5915,
      "step": 25232
    },
    {
      "epoch": 0.77513593217215,
      "grad_norm": 0.32040834426879883,
      "learning_rate": 1.3487375258844238e-05,
      "loss": 0.5427,
      "step": 25233
    },
    {
      "epoch": 0.7751666513070992,
      "grad_norm": 0.38991475105285645,
      "learning_rate": 1.3486922317377858e-05,
      "loss": 0.6304,
      "step": 25234
    },
    {
      "epoch": 0.7751973704420484,
      "grad_norm": 0.35334259271621704,
      "learning_rate": 1.348646936776753e-05,
      "loss": 0.5827,
      "step": 25235
    },
    {
      "epoch": 0.7752280895769975,
      "grad_norm": 0.4270765781402588,
      "learning_rate": 1.3486016410014306e-05,
      "loss": 0.6221,
      "step": 25236
    },
    {
      "epoch": 0.7752588087119466,
      "grad_norm": 0.36150509119033813,
      "learning_rate": 1.348556344411925e-05,
      "loss": 0.5587,
      "step": 25237
    },
    {
      "epoch": 0.7752895278468959,
      "grad_norm": 0.36569827795028687,
      "learning_rate": 1.3485110470083416e-05,
      "loss": 0.5961,
      "step": 25238
    },
    {
      "epoch": 0.775320246981845,
      "grad_norm": 0.33766064047813416,
      "learning_rate": 1.3484657487907865e-05,
      "loss": 0.5735,
      "step": 25239
    },
    {
      "epoch": 0.7753509661167941,
      "grad_norm": 0.37152284383773804,
      "learning_rate": 1.348420449759365e-05,
      "loss": 0.6312,
      "step": 25240
    },
    {
      "epoch": 0.7753816852517433,
      "grad_norm": 0.3427976369857788,
      "learning_rate": 1.3483751499141832e-05,
      "loss": 0.5607,
      "step": 25241
    },
    {
      "epoch": 0.7754124043866925,
      "grad_norm": 0.5267860889434814,
      "learning_rate": 1.3483298492553472e-05,
      "loss": 0.5698,
      "step": 25242
    },
    {
      "epoch": 0.7754431235216416,
      "grad_norm": 0.38991230726242065,
      "learning_rate": 1.3482845477829623e-05,
      "loss": 0.5176,
      "step": 25243
    },
    {
      "epoch": 0.7754738426565908,
      "grad_norm": 0.3636607825756073,
      "learning_rate": 1.3482392454971345e-05,
      "loss": 0.5887,
      "step": 25244
    },
    {
      "epoch": 0.7755045617915399,
      "grad_norm": 0.3607715666294098,
      "learning_rate": 1.3481939423979698e-05,
      "loss": 0.5677,
      "step": 25245
    },
    {
      "epoch": 0.7755352809264892,
      "grad_norm": 0.3278428614139557,
      "learning_rate": 1.3481486384855738e-05,
      "loss": 0.4561,
      "step": 25246
    },
    {
      "epoch": 0.7755660000614383,
      "grad_norm": 0.3420860469341278,
      "learning_rate": 1.348103333760052e-05,
      "loss": 0.5597,
      "step": 25247
    },
    {
      "epoch": 0.7755967191963874,
      "grad_norm": 0.38649651408195496,
      "learning_rate": 1.348058028221511e-05,
      "loss": 0.575,
      "step": 25248
    },
    {
      "epoch": 0.7756274383313366,
      "grad_norm": 0.3594468832015991,
      "learning_rate": 1.348012721870056e-05,
      "loss": 0.5464,
      "step": 25249
    },
    {
      "epoch": 0.7756581574662857,
      "grad_norm": 0.35271602869033813,
      "learning_rate": 1.3479674147057931e-05,
      "loss": 0.5613,
      "step": 25250
    },
    {
      "epoch": 0.7756888766012349,
      "grad_norm": 0.3671829402446747,
      "learning_rate": 1.3479221067288277e-05,
      "loss": 0.5094,
      "step": 25251
    },
    {
      "epoch": 0.7757195957361841,
      "grad_norm": 0.4051421284675598,
      "learning_rate": 1.3478767979392662e-05,
      "loss": 0.5995,
      "step": 25252
    },
    {
      "epoch": 0.7757503148711332,
      "grad_norm": 0.33397966623306274,
      "learning_rate": 1.347831488337214e-05,
      "loss": 0.4742,
      "step": 25253
    },
    {
      "epoch": 0.7757810340060823,
      "grad_norm": 0.4159320592880249,
      "learning_rate": 1.347786177922777e-05,
      "loss": 0.5466,
      "step": 25254
    },
    {
      "epoch": 0.7758117531410316,
      "grad_norm": 0.4010430872440338,
      "learning_rate": 1.3477408666960615e-05,
      "loss": 0.5608,
      "step": 25255
    },
    {
      "epoch": 0.7758424722759807,
      "grad_norm": 0.33290719985961914,
      "learning_rate": 1.3476955546571725e-05,
      "loss": 0.5529,
      "step": 25256
    },
    {
      "epoch": 0.7758731914109299,
      "grad_norm": 0.357727974653244,
      "learning_rate": 1.3476502418062163e-05,
      "loss": 0.5522,
      "step": 25257
    },
    {
      "epoch": 0.775903910545879,
      "grad_norm": 0.4090959429740906,
      "learning_rate": 1.3476049281432989e-05,
      "loss": 0.6148,
      "step": 25258
    },
    {
      "epoch": 0.7759346296808282,
      "grad_norm": 0.3502054810523987,
      "learning_rate": 1.3475596136685254e-05,
      "loss": 0.6157,
      "step": 25259
    },
    {
      "epoch": 0.7759653488157774,
      "grad_norm": 0.33966565132141113,
      "learning_rate": 1.3475142983820026e-05,
      "loss": 0.6282,
      "step": 25260
    },
    {
      "epoch": 0.7759960679507265,
      "grad_norm": 0.5535008311271667,
      "learning_rate": 1.3474689822838359e-05,
      "loss": 0.5119,
      "step": 25261
    },
    {
      "epoch": 0.7760267870856756,
      "grad_norm": 0.3758619725704193,
      "learning_rate": 1.347423665374131e-05,
      "loss": 0.4925,
      "step": 25262
    },
    {
      "epoch": 0.7760575062206249,
      "grad_norm": 0.40378236770629883,
      "learning_rate": 1.3473783476529938e-05,
      "loss": 0.518,
      "step": 25263
    },
    {
      "epoch": 0.776088225355574,
      "grad_norm": 0.362070769071579,
      "learning_rate": 1.3473330291205305e-05,
      "loss": 0.546,
      "step": 25264
    },
    {
      "epoch": 0.7761189444905231,
      "grad_norm": 0.4217730462551117,
      "learning_rate": 1.3472877097768463e-05,
      "loss": 0.5476,
      "step": 25265
    },
    {
      "epoch": 0.7761496636254723,
      "grad_norm": 0.34437698125839233,
      "learning_rate": 1.3472423896220477e-05,
      "loss": 0.5564,
      "step": 25266
    },
    {
      "epoch": 0.7761803827604215,
      "grad_norm": 0.32641080021858215,
      "learning_rate": 1.3471970686562402e-05,
      "loss": 0.4162,
      "step": 25267
    },
    {
      "epoch": 0.7762111018953707,
      "grad_norm": 0.37982118129730225,
      "learning_rate": 1.3471517468795294e-05,
      "loss": 0.5248,
      "step": 25268
    },
    {
      "epoch": 0.7762418210303198,
      "grad_norm": 0.3894161880016327,
      "learning_rate": 1.3471064242920218e-05,
      "loss": 0.5507,
      "step": 25269
    },
    {
      "epoch": 0.7762725401652689,
      "grad_norm": 0.36163344979286194,
      "learning_rate": 1.3470611008938227e-05,
      "loss": 0.5499,
      "step": 25270
    },
    {
      "epoch": 0.7763032593002182,
      "grad_norm": 0.37006235122680664,
      "learning_rate": 1.347015776685038e-05,
      "loss": 0.5574,
      "step": 25271
    },
    {
      "epoch": 0.7763339784351673,
      "grad_norm": 0.4831543266773224,
      "learning_rate": 1.346970451665774e-05,
      "loss": 0.5848,
      "step": 25272
    },
    {
      "epoch": 0.7763646975701164,
      "grad_norm": 0.38679325580596924,
      "learning_rate": 1.3469251258361362e-05,
      "loss": 0.5414,
      "step": 25273
    },
    {
      "epoch": 0.7763954167050656,
      "grad_norm": 0.39228931069374084,
      "learning_rate": 1.3468797991962306e-05,
      "loss": 0.5582,
      "step": 25274
    },
    {
      "epoch": 0.7764261358400147,
      "grad_norm": 0.3644556999206543,
      "learning_rate": 1.346834471746163e-05,
      "loss": 0.5057,
      "step": 25275
    },
    {
      "epoch": 0.7764568549749639,
      "grad_norm": 0.33305203914642334,
      "learning_rate": 1.3467891434860392e-05,
      "loss": 0.5701,
      "step": 25276
    },
    {
      "epoch": 0.7764875741099131,
      "grad_norm": 0.39877599477767944,
      "learning_rate": 1.346743814415965e-05,
      "loss": 0.6347,
      "step": 25277
    },
    {
      "epoch": 0.7765182932448622,
      "grad_norm": 0.8412812352180481,
      "learning_rate": 1.3466984845360467e-05,
      "loss": 0.5292,
      "step": 25278
    },
    {
      "epoch": 0.7765490123798113,
      "grad_norm": 0.4234369695186615,
      "learning_rate": 1.3466531538463897e-05,
      "loss": 0.5933,
      "step": 25279
    },
    {
      "epoch": 0.7765797315147606,
      "grad_norm": 0.36390137672424316,
      "learning_rate": 1.3466078223471e-05,
      "loss": 0.4922,
      "step": 25280
    },
    {
      "epoch": 0.7766104506497097,
      "grad_norm": 0.34518471360206604,
      "learning_rate": 1.3465624900382834e-05,
      "loss": 0.5283,
      "step": 25281
    },
    {
      "epoch": 0.7766411697846589,
      "grad_norm": 0.34135758876800537,
      "learning_rate": 1.3465171569200464e-05,
      "loss": 0.5156,
      "step": 25282
    },
    {
      "epoch": 0.776671888919608,
      "grad_norm": 0.4083661139011383,
      "learning_rate": 1.346471822992494e-05,
      "loss": 0.5727,
      "step": 25283
    },
    {
      "epoch": 0.7767026080545572,
      "grad_norm": 0.3926020562648773,
      "learning_rate": 1.3464264882557325e-05,
      "loss": 0.6841,
      "step": 25284
    },
    {
      "epoch": 0.7767333271895064,
      "grad_norm": 0.38974612951278687,
      "learning_rate": 1.346381152709868e-05,
      "loss": 0.5533,
      "step": 25285
    },
    {
      "epoch": 0.7767640463244555,
      "grad_norm": 0.3562687933444977,
      "learning_rate": 1.3463358163550057e-05,
      "loss": 0.463,
      "step": 25286
    },
    {
      "epoch": 0.7767947654594046,
      "grad_norm": 0.35048019886016846,
      "learning_rate": 1.3462904791912523e-05,
      "loss": 0.5052,
      "step": 25287
    },
    {
      "epoch": 0.7768254845943539,
      "grad_norm": 0.3371111750602722,
      "learning_rate": 1.346245141218713e-05,
      "loss": 0.5763,
      "step": 25288
    },
    {
      "epoch": 0.776856203729303,
      "grad_norm": 0.3992452025413513,
      "learning_rate": 1.3461998024374942e-05,
      "loss": 0.5979,
      "step": 25289
    },
    {
      "epoch": 0.7768869228642521,
      "grad_norm": 0.3532593548297882,
      "learning_rate": 1.3461544628477015e-05,
      "loss": 0.5271,
      "step": 25290
    },
    {
      "epoch": 0.7769176419992013,
      "grad_norm": 0.40844422578811646,
      "learning_rate": 1.346109122449441e-05,
      "loss": 0.5994,
      "step": 25291
    },
    {
      "epoch": 0.7769483611341504,
      "grad_norm": 0.3614770472049713,
      "learning_rate": 1.3460637812428181e-05,
      "loss": 0.5314,
      "step": 25292
    },
    {
      "epoch": 0.7769790802690997,
      "grad_norm": 0.3540353775024414,
      "learning_rate": 1.3460184392279396e-05,
      "loss": 0.5258,
      "step": 25293
    },
    {
      "epoch": 0.7770097994040488,
      "grad_norm": 0.38987648487091064,
      "learning_rate": 1.3459730964049105e-05,
      "loss": 0.5714,
      "step": 25294
    },
    {
      "epoch": 0.7770405185389979,
      "grad_norm": 0.34863176941871643,
      "learning_rate": 1.345927752773837e-05,
      "loss": 0.5835,
      "step": 25295
    },
    {
      "epoch": 0.7770712376739471,
      "grad_norm": 0.3301045596599579,
      "learning_rate": 1.3458824083348253e-05,
      "loss": 0.5025,
      "step": 25296
    },
    {
      "epoch": 0.7771019568088963,
      "grad_norm": 0.6660440564155579,
      "learning_rate": 1.3458370630879808e-05,
      "loss": 0.5078,
      "step": 25297
    },
    {
      "epoch": 0.7771326759438454,
      "grad_norm": 0.3936895430088043,
      "learning_rate": 1.3457917170334103e-05,
      "loss": 0.5008,
      "step": 25298
    },
    {
      "epoch": 0.7771633950787946,
      "grad_norm": 0.41538479924201965,
      "learning_rate": 1.3457463701712183e-05,
      "loss": 0.4924,
      "step": 25299
    },
    {
      "epoch": 0.7771941142137437,
      "grad_norm": 0.3807576894760132,
      "learning_rate": 1.3457010225015121e-05,
      "loss": 0.4949,
      "step": 25300
    },
    {
      "epoch": 0.7772248333486929,
      "grad_norm": 0.41542530059814453,
      "learning_rate": 1.3456556740243972e-05,
      "loss": 0.5867,
      "step": 25301
    },
    {
      "epoch": 0.7772555524836421,
      "grad_norm": 0.3442547619342804,
      "learning_rate": 1.3456103247399787e-05,
      "loss": 0.4642,
      "step": 25302
    },
    {
      "epoch": 0.7772862716185912,
      "grad_norm": 0.32935598492622375,
      "learning_rate": 1.3455649746483634e-05,
      "loss": 0.5288,
      "step": 25303
    },
    {
      "epoch": 0.7773169907535403,
      "grad_norm": 0.3589381277561188,
      "learning_rate": 1.3455196237496568e-05,
      "loss": 0.5045,
      "step": 25304
    },
    {
      "epoch": 0.7773477098884896,
      "grad_norm": 0.44792893528938293,
      "learning_rate": 1.3454742720439655e-05,
      "loss": 0.5426,
      "step": 25305
    },
    {
      "epoch": 0.7773784290234387,
      "grad_norm": 0.3484170138835907,
      "learning_rate": 1.3454289195313943e-05,
      "loss": 0.5586,
      "step": 25306
    },
    {
      "epoch": 0.7774091481583879,
      "grad_norm": 0.6329813599586487,
      "learning_rate": 1.3453835662120502e-05,
      "loss": 0.5679,
      "step": 25307
    },
    {
      "epoch": 0.777439867293337,
      "grad_norm": 0.3425394296646118,
      "learning_rate": 1.3453382120860383e-05,
      "loss": 0.5536,
      "step": 25308
    },
    {
      "epoch": 0.7774705864282861,
      "grad_norm": 0.39550167322158813,
      "learning_rate": 1.345292857153465e-05,
      "loss": 0.5024,
      "step": 25309
    },
    {
      "epoch": 0.7775013055632354,
      "grad_norm": 0.3701869547367096,
      "learning_rate": 1.3452475014144365e-05,
      "loss": 0.5074,
      "step": 25310
    },
    {
      "epoch": 0.7775320246981845,
      "grad_norm": 0.3423631489276886,
      "learning_rate": 1.345202144869058e-05,
      "loss": 0.5745,
      "step": 25311
    },
    {
      "epoch": 0.7775627438331336,
      "grad_norm": 0.34731659293174744,
      "learning_rate": 1.3451567875174358e-05,
      "loss": 0.5815,
      "step": 25312
    },
    {
      "epoch": 0.7775934629680828,
      "grad_norm": 0.34888166189193726,
      "learning_rate": 1.3451114293596757e-05,
      "loss": 0.5359,
      "step": 25313
    },
    {
      "epoch": 0.777624182103032,
      "grad_norm": 0.3701856732368469,
      "learning_rate": 1.3450660703958837e-05,
      "loss": 0.5845,
      "step": 25314
    },
    {
      "epoch": 0.7776549012379811,
      "grad_norm": 0.35856732726097107,
      "learning_rate": 1.3450207106261658e-05,
      "loss": 0.51,
      "step": 25315
    },
    {
      "epoch": 0.7776856203729303,
      "grad_norm": 0.3475412130355835,
      "learning_rate": 1.3449753500506284e-05,
      "loss": 0.5518,
      "step": 25316
    },
    {
      "epoch": 0.7777163395078794,
      "grad_norm": 0.37135612964630127,
      "learning_rate": 1.3449299886693765e-05,
      "loss": 0.5372,
      "step": 25317
    },
    {
      "epoch": 0.7777470586428287,
      "grad_norm": 0.3626139163970947,
      "learning_rate": 1.3448846264825168e-05,
      "loss": 0.6045,
      "step": 25318
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.3501361906528473,
      "learning_rate": 1.344839263490155e-05,
      "loss": 0.4851,
      "step": 25319
    },
    {
      "epoch": 0.7778084969127269,
      "grad_norm": 0.33188533782958984,
      "learning_rate": 1.3447938996923968e-05,
      "loss": 0.5425,
      "step": 25320
    },
    {
      "epoch": 0.7778392160476761,
      "grad_norm": 0.361068993806839,
      "learning_rate": 1.3447485350893485e-05,
      "loss": 0.5761,
      "step": 25321
    },
    {
      "epoch": 0.7778699351826253,
      "grad_norm": 0.37324652075767517,
      "learning_rate": 1.344703169681116e-05,
      "loss": 0.5271,
      "step": 25322
    },
    {
      "epoch": 0.7779006543175744,
      "grad_norm": 0.33266377449035645,
      "learning_rate": 1.344657803467805e-05,
      "loss": 0.5228,
      "step": 25323
    },
    {
      "epoch": 0.7779313734525236,
      "grad_norm": 0.358826607465744,
      "learning_rate": 1.3446124364495217e-05,
      "loss": 0.6264,
      "step": 25324
    },
    {
      "epoch": 0.7779620925874727,
      "grad_norm": 0.3595719337463379,
      "learning_rate": 1.3445670686263719e-05,
      "loss": 0.5891,
      "step": 25325
    },
    {
      "epoch": 0.7779928117224219,
      "grad_norm": 0.3739510774612427,
      "learning_rate": 1.3445216999984616e-05,
      "loss": 0.6293,
      "step": 25326
    },
    {
      "epoch": 0.7780235308573711,
      "grad_norm": 0.31744933128356934,
      "learning_rate": 1.344476330565897e-05,
      "loss": 0.5296,
      "step": 25327
    },
    {
      "epoch": 0.7780542499923202,
      "grad_norm": 0.3563578724861145,
      "learning_rate": 1.3444309603287837e-05,
      "loss": 0.5909,
      "step": 25328
    },
    {
      "epoch": 0.7780849691272693,
      "grad_norm": 0.3548218309879303,
      "learning_rate": 1.344385589287228e-05,
      "loss": 0.5721,
      "step": 25329
    },
    {
      "epoch": 0.7781156882622186,
      "grad_norm": 0.3794254660606384,
      "learning_rate": 1.3443402174413358e-05,
      "loss": 0.5629,
      "step": 25330
    },
    {
      "epoch": 0.7781464073971677,
      "grad_norm": 0.4093839228153229,
      "learning_rate": 1.3442948447912128e-05,
      "loss": 0.5785,
      "step": 25331
    },
    {
      "epoch": 0.7781771265321169,
      "grad_norm": 0.4015212953090668,
      "learning_rate": 1.344249471336965e-05,
      "loss": 0.5161,
      "step": 25332
    },
    {
      "epoch": 0.778207845667066,
      "grad_norm": 0.3633307218551636,
      "learning_rate": 1.3442040970786985e-05,
      "loss": 0.6327,
      "step": 25333
    },
    {
      "epoch": 0.7782385648020151,
      "grad_norm": 0.37398844957351685,
      "learning_rate": 1.3441587220165196e-05,
      "loss": 0.5962,
      "step": 25334
    },
    {
      "epoch": 0.7782692839369644,
      "grad_norm": 0.4088019132614136,
      "learning_rate": 1.3441133461505338e-05,
      "loss": 0.5339,
      "step": 25335
    },
    {
      "epoch": 0.7783000030719135,
      "grad_norm": 0.47408124804496765,
      "learning_rate": 1.3440679694808471e-05,
      "loss": 0.6156,
      "step": 25336
    },
    {
      "epoch": 0.7783307222068626,
      "grad_norm": 0.3817709684371948,
      "learning_rate": 1.344022592007566e-05,
      "loss": 0.5322,
      "step": 25337
    },
    {
      "epoch": 0.7783614413418118,
      "grad_norm": 0.3480789065361023,
      "learning_rate": 1.3439772137307959e-05,
      "loss": 0.5046,
      "step": 25338
    },
    {
      "epoch": 0.778392160476761,
      "grad_norm": 0.5870785713195801,
      "learning_rate": 1.3439318346506431e-05,
      "loss": 0.5641,
      "step": 25339
    },
    {
      "epoch": 0.7784228796117101,
      "grad_norm": 0.4098789095878601,
      "learning_rate": 1.3438864547672133e-05,
      "loss": 0.6001,
      "step": 25340
    },
    {
      "epoch": 0.7784535987466593,
      "grad_norm": 0.342734694480896,
      "learning_rate": 1.343841074080613e-05,
      "loss": 0.4918,
      "step": 25341
    },
    {
      "epoch": 0.7784843178816084,
      "grad_norm": 0.3593689203262329,
      "learning_rate": 1.3437956925909474e-05,
      "loss": 0.5742,
      "step": 25342
    },
    {
      "epoch": 0.7785150370165577,
      "grad_norm": 0.3903767466545105,
      "learning_rate": 1.3437503102983231e-05,
      "loss": 0.5695,
      "step": 25343
    },
    {
      "epoch": 0.7785457561515068,
      "grad_norm": 0.33146557211875916,
      "learning_rate": 1.3437049272028459e-05,
      "loss": 0.4993,
      "step": 25344
    },
    {
      "epoch": 0.7785764752864559,
      "grad_norm": 0.38158559799194336,
      "learning_rate": 1.3436595433046222e-05,
      "loss": 0.5992,
      "step": 25345
    },
    {
      "epoch": 0.7786071944214051,
      "grad_norm": 0.35384446382522583,
      "learning_rate": 1.3436141586037572e-05,
      "loss": 0.6058,
      "step": 25346
    },
    {
      "epoch": 0.7786379135563543,
      "grad_norm": 0.3497174084186554,
      "learning_rate": 1.3435687731003577e-05,
      "loss": 0.5294,
      "step": 25347
    },
    {
      "epoch": 0.7786686326913034,
      "grad_norm": 0.37381163239479065,
      "learning_rate": 1.3435233867945293e-05,
      "loss": 0.5505,
      "step": 25348
    },
    {
      "epoch": 0.7786993518262526,
      "grad_norm": 0.38258105516433716,
      "learning_rate": 1.3434779996863778e-05,
      "loss": 0.6102,
      "step": 25349
    },
    {
      "epoch": 0.7787300709612017,
      "grad_norm": 0.3897209167480469,
      "learning_rate": 1.3434326117760094e-05,
      "loss": 0.5376,
      "step": 25350
    },
    {
      "epoch": 0.7787607900961508,
      "grad_norm": 0.38428884744644165,
      "learning_rate": 1.3433872230635301e-05,
      "loss": 0.5249,
      "step": 25351
    },
    {
      "epoch": 0.7787915092311001,
      "grad_norm": 0.35507258772850037,
      "learning_rate": 1.3433418335490462e-05,
      "loss": 0.5398,
      "step": 25352
    },
    {
      "epoch": 0.7788222283660492,
      "grad_norm": 0.3902254104614258,
      "learning_rate": 1.3432964432326636e-05,
      "loss": 0.5503,
      "step": 25353
    },
    {
      "epoch": 0.7788529475009984,
      "grad_norm": 0.35821232199668884,
      "learning_rate": 1.3432510521144879e-05,
      "loss": 0.4916,
      "step": 25354
    },
    {
      "epoch": 0.7788836666359475,
      "grad_norm": 0.33157098293304443,
      "learning_rate": 1.3432056601946255e-05,
      "loss": 0.5194,
      "step": 25355
    },
    {
      "epoch": 0.7789143857708967,
      "grad_norm": 0.37467464804649353,
      "learning_rate": 1.3431602674731823e-05,
      "loss": 0.6041,
      "step": 25356
    },
    {
      "epoch": 0.7789451049058459,
      "grad_norm": 0.34330224990844727,
      "learning_rate": 1.3431148739502644e-05,
      "loss": 0.6805,
      "step": 25357
    },
    {
      "epoch": 0.778975824040795,
      "grad_norm": 0.3360547423362732,
      "learning_rate": 1.3430694796259775e-05,
      "loss": 0.5523,
      "step": 25358
    },
    {
      "epoch": 0.7790065431757441,
      "grad_norm": 0.3709743618965149,
      "learning_rate": 1.3430240845004283e-05,
      "loss": 0.5489,
      "step": 25359
    },
    {
      "epoch": 0.7790372623106934,
      "grad_norm": 3.0571234226226807,
      "learning_rate": 1.342978688573722e-05,
      "loss": 0.6264,
      "step": 25360
    },
    {
      "epoch": 0.7790679814456425,
      "grad_norm": 0.34793245792388916,
      "learning_rate": 1.3429332918459652e-05,
      "loss": 0.5765,
      "step": 25361
    },
    {
      "epoch": 0.7790987005805916,
      "grad_norm": 0.33626753091812134,
      "learning_rate": 1.3428878943172636e-05,
      "loss": 0.4937,
      "step": 25362
    },
    {
      "epoch": 0.7791294197155408,
      "grad_norm": 0.4144015610218048,
      "learning_rate": 1.3428424959877235e-05,
      "loss": 0.5499,
      "step": 25363
    },
    {
      "epoch": 0.77916013885049,
      "grad_norm": 0.36853718757629395,
      "learning_rate": 1.342797096857451e-05,
      "loss": 0.478,
      "step": 25364
    },
    {
      "epoch": 0.7791908579854391,
      "grad_norm": 0.37357810139656067,
      "learning_rate": 1.3427516969265518e-05,
      "loss": 0.5454,
      "step": 25365
    },
    {
      "epoch": 0.7792215771203883,
      "grad_norm": 0.39185628294944763,
      "learning_rate": 1.342706296195132e-05,
      "loss": 0.5605,
      "step": 25366
    },
    {
      "epoch": 0.7792522962553374,
      "grad_norm": 0.3228795528411865,
      "learning_rate": 1.3426608946632975e-05,
      "loss": 0.5232,
      "step": 25367
    },
    {
      "epoch": 0.7792830153902867,
      "grad_norm": 0.3419444262981415,
      "learning_rate": 1.3426154923311547e-05,
      "loss": 0.5758,
      "step": 25368
    },
    {
      "epoch": 0.7793137345252358,
      "grad_norm": 0.3828301727771759,
      "learning_rate": 1.3425700891988095e-05,
      "loss": 0.5693,
      "step": 25369
    },
    {
      "epoch": 0.7793444536601849,
      "grad_norm": 0.3619670271873474,
      "learning_rate": 1.342524685266368e-05,
      "loss": 0.5018,
      "step": 25370
    },
    {
      "epoch": 0.7793751727951341,
      "grad_norm": 0.3937762677669525,
      "learning_rate": 1.3424792805339364e-05,
      "loss": 0.5588,
      "step": 25371
    },
    {
      "epoch": 0.7794058919300832,
      "grad_norm": 0.34634658694267273,
      "learning_rate": 1.3424338750016201e-05,
      "loss": 0.495,
      "step": 25372
    },
    {
      "epoch": 0.7794366110650324,
      "grad_norm": 0.33378610014915466,
      "learning_rate": 1.3423884686695258e-05,
      "loss": 0.4685,
      "step": 25373
    },
    {
      "epoch": 0.7794673301999816,
      "grad_norm": 0.3674440383911133,
      "learning_rate": 1.3423430615377593e-05,
      "loss": 0.6711,
      "step": 25374
    },
    {
      "epoch": 0.7794980493349307,
      "grad_norm": 0.37254300713539124,
      "learning_rate": 1.3422976536064267e-05,
      "loss": 0.5487,
      "step": 25375
    },
    {
      "epoch": 0.7795287684698798,
      "grad_norm": 0.44890666007995605,
      "learning_rate": 1.3422522448756339e-05,
      "loss": 0.5595,
      "step": 25376
    },
    {
      "epoch": 0.7795594876048291,
      "grad_norm": 0.3581266701221466,
      "learning_rate": 1.342206835345487e-05,
      "loss": 0.5095,
      "step": 25377
    },
    {
      "epoch": 0.7795902067397782,
      "grad_norm": 0.3864741325378418,
      "learning_rate": 1.3421614250160924e-05,
      "loss": 0.5161,
      "step": 25378
    },
    {
      "epoch": 0.7796209258747274,
      "grad_norm": 0.39340147376060486,
      "learning_rate": 1.342116013887556e-05,
      "loss": 0.5378,
      "step": 25379
    },
    {
      "epoch": 0.7796516450096765,
      "grad_norm": 0.34029507637023926,
      "learning_rate": 1.3420706019599834e-05,
      "loss": 0.6134,
      "step": 25380
    },
    {
      "epoch": 0.7796823641446257,
      "grad_norm": 0.5762830376625061,
      "learning_rate": 1.3420251892334812e-05,
      "loss": 0.6358,
      "step": 25381
    },
    {
      "epoch": 0.7797130832795749,
      "grad_norm": 0.4355362355709076,
      "learning_rate": 1.3419797757081555e-05,
      "loss": 0.5924,
      "step": 25382
    },
    {
      "epoch": 0.779743802414524,
      "grad_norm": 0.3613542914390564,
      "learning_rate": 1.3419343613841116e-05,
      "loss": 0.5315,
      "step": 25383
    },
    {
      "epoch": 0.7797745215494731,
      "grad_norm": 0.38934892416000366,
      "learning_rate": 1.3418889462614565e-05,
      "loss": 0.5269,
      "step": 25384
    },
    {
      "epoch": 0.7798052406844224,
      "grad_norm": 0.33399951457977295,
      "learning_rate": 1.3418435303402957e-05,
      "loss": 0.4478,
      "step": 25385
    },
    {
      "epoch": 0.7798359598193715,
      "grad_norm": 0.39937764406204224,
      "learning_rate": 1.3417981136207356e-05,
      "loss": 0.582,
      "step": 25386
    },
    {
      "epoch": 0.7798666789543206,
      "grad_norm": 0.3945847153663635,
      "learning_rate": 1.341752696102882e-05,
      "loss": 0.5138,
      "step": 25387
    },
    {
      "epoch": 0.7798973980892698,
      "grad_norm": 0.3713791072368622,
      "learning_rate": 1.3417072777868412e-05,
      "loss": 0.5303,
      "step": 25388
    },
    {
      "epoch": 0.779928117224219,
      "grad_norm": 0.38290295004844666,
      "learning_rate": 1.3416618586727192e-05,
      "loss": 0.5922,
      "step": 25389
    },
    {
      "epoch": 0.7799588363591681,
      "grad_norm": 0.3691234588623047,
      "learning_rate": 1.341616438760622e-05,
      "loss": 0.4907,
      "step": 25390
    },
    {
      "epoch": 0.7799895554941173,
      "grad_norm": 0.39937642216682434,
      "learning_rate": 1.341571018050656e-05,
      "loss": 0.5287,
      "step": 25391
    },
    {
      "epoch": 0.7800202746290664,
      "grad_norm": 0.391257107257843,
      "learning_rate": 1.3415255965429266e-05,
      "loss": 0.5953,
      "step": 25392
    },
    {
      "epoch": 0.7800509937640157,
      "grad_norm": 0.40183404088020325,
      "learning_rate": 1.3414801742375408e-05,
      "loss": 0.523,
      "step": 25393
    },
    {
      "epoch": 0.7800817128989648,
      "grad_norm": 0.3319677412509918,
      "learning_rate": 1.341434751134604e-05,
      "loss": 0.4851,
      "step": 25394
    },
    {
      "epoch": 0.7801124320339139,
      "grad_norm": 0.4038982689380646,
      "learning_rate": 1.3413893272342224e-05,
      "loss": 0.6328,
      "step": 25395
    },
    {
      "epoch": 0.7801431511688631,
      "grad_norm": 0.41185614466667175,
      "learning_rate": 1.3413439025365023e-05,
      "loss": 0.5466,
      "step": 25396
    },
    {
      "epoch": 0.7801738703038122,
      "grad_norm": 0.37210994958877563,
      "learning_rate": 1.3412984770415497e-05,
      "loss": 0.518,
      "step": 25397
    },
    {
      "epoch": 0.7802045894387614,
      "grad_norm": 1.0328165292739868,
      "learning_rate": 1.3412530507494703e-05,
      "loss": 0.5442,
      "step": 25398
    },
    {
      "epoch": 0.7802353085737106,
      "grad_norm": 0.3443508446216583,
      "learning_rate": 1.341207623660371e-05,
      "loss": 0.5892,
      "step": 25399
    },
    {
      "epoch": 0.7802660277086597,
      "grad_norm": 0.3988948464393616,
      "learning_rate": 1.3411621957743575e-05,
      "loss": 0.5849,
      "step": 25400
    },
    {
      "epoch": 0.7802967468436088,
      "grad_norm": 0.3709220886230469,
      "learning_rate": 1.3411167670915354e-05,
      "loss": 0.5511,
      "step": 25401
    },
    {
      "epoch": 0.7803274659785581,
      "grad_norm": 0.35383281111717224,
      "learning_rate": 1.3410713376120117e-05,
      "loss": 0.53,
      "step": 25402
    },
    {
      "epoch": 0.7803581851135072,
      "grad_norm": 0.36785727739334106,
      "learning_rate": 1.341025907335892e-05,
      "loss": 0.5733,
      "step": 25403
    },
    {
      "epoch": 0.7803889042484564,
      "grad_norm": 0.398689329624176,
      "learning_rate": 1.3409804762632823e-05,
      "loss": 0.5556,
      "step": 25404
    },
    {
      "epoch": 0.7804196233834055,
      "grad_norm": 0.3944772779941559,
      "learning_rate": 1.340935044394289e-05,
      "loss": 0.5523,
      "step": 25405
    },
    {
      "epoch": 0.7804503425183547,
      "grad_norm": 0.3519741892814636,
      "learning_rate": 1.340889611729018e-05,
      "loss": 0.5836,
      "step": 25406
    },
    {
      "epoch": 0.7804810616533039,
      "grad_norm": 0.5836843848228455,
      "learning_rate": 1.3408441782675756e-05,
      "loss": 0.5682,
      "step": 25407
    },
    {
      "epoch": 0.780511780788253,
      "grad_norm": 0.36111968755722046,
      "learning_rate": 1.3407987440100678e-05,
      "loss": 0.5138,
      "step": 25408
    },
    {
      "epoch": 0.7805424999232021,
      "grad_norm": 0.3941628336906433,
      "learning_rate": 1.3407533089566008e-05,
      "loss": 0.5831,
      "step": 25409
    },
    {
      "epoch": 0.7805732190581514,
      "grad_norm": 0.3433554470539093,
      "learning_rate": 1.3407078731072804e-05,
      "loss": 0.5351,
      "step": 25410
    },
    {
      "epoch": 0.7806039381931005,
      "grad_norm": 0.3623279929161072,
      "learning_rate": 1.340662436462213e-05,
      "loss": 0.4839,
      "step": 25411
    },
    {
      "epoch": 0.7806346573280496,
      "grad_norm": 0.3555039167404175,
      "learning_rate": 1.340616999021505e-05,
      "loss": 0.5366,
      "step": 25412
    },
    {
      "epoch": 0.7806653764629988,
      "grad_norm": 0.37102562189102173,
      "learning_rate": 1.340571560785262e-05,
      "loss": 0.6106,
      "step": 25413
    },
    {
      "epoch": 0.780696095597948,
      "grad_norm": 0.37807053327560425,
      "learning_rate": 1.3405261217535905e-05,
      "loss": 0.6196,
      "step": 25414
    },
    {
      "epoch": 0.7807268147328971,
      "grad_norm": 0.3432677686214447,
      "learning_rate": 1.3404806819265963e-05,
      "loss": 0.442,
      "step": 25415
    },
    {
      "epoch": 0.7807575338678463,
      "grad_norm": 0.40235623717308044,
      "learning_rate": 1.340435241304386e-05,
      "loss": 0.6275,
      "step": 25416
    },
    {
      "epoch": 0.7807882530027954,
      "grad_norm": 0.39316585659980774,
      "learning_rate": 1.340389799887065e-05,
      "loss": 0.585,
      "step": 25417
    },
    {
      "epoch": 0.7808189721377446,
      "grad_norm": 0.39260178804397583,
      "learning_rate": 1.34034435767474e-05,
      "loss": 0.5572,
      "step": 25418
    },
    {
      "epoch": 0.7808496912726938,
      "grad_norm": 0.4002392590045929,
      "learning_rate": 1.340298914667517e-05,
      "loss": 0.5039,
      "step": 25419
    },
    {
      "epoch": 0.7808804104076429,
      "grad_norm": 0.3448773920536041,
      "learning_rate": 1.3402534708655022e-05,
      "loss": 0.561,
      "step": 25420
    },
    {
      "epoch": 0.7809111295425921,
      "grad_norm": 0.3654865622520447,
      "learning_rate": 1.3402080262688016e-05,
      "loss": 0.4893,
      "step": 25421
    },
    {
      "epoch": 0.7809418486775412,
      "grad_norm": 0.3474367558956146,
      "learning_rate": 1.3401625808775212e-05,
      "loss": 0.5516,
      "step": 25422
    },
    {
      "epoch": 0.7809725678124904,
      "grad_norm": 0.4402119815349579,
      "learning_rate": 1.3401171346917674e-05,
      "loss": 0.476,
      "step": 25423
    },
    {
      "epoch": 0.7810032869474396,
      "grad_norm": 0.38286375999450684,
      "learning_rate": 1.3400716877116465e-05,
      "loss": 0.5569,
      "step": 25424
    },
    {
      "epoch": 0.7810340060823887,
      "grad_norm": 0.3321911096572876,
      "learning_rate": 1.3400262399372642e-05,
      "loss": 0.5495,
      "step": 25425
    },
    {
      "epoch": 0.7810647252173378,
      "grad_norm": 0.36268606781959534,
      "learning_rate": 1.3399807913687268e-05,
      "loss": 0.4847,
      "step": 25426
    },
    {
      "epoch": 0.7810954443522871,
      "grad_norm": 0.8800076842308044,
      "learning_rate": 1.339935342006141e-05,
      "loss": 0.4389,
      "step": 25427
    },
    {
      "epoch": 0.7811261634872362,
      "grad_norm": 0.3670199513435364,
      "learning_rate": 1.339889891849612e-05,
      "loss": 0.5766,
      "step": 25428
    },
    {
      "epoch": 0.7811568826221854,
      "grad_norm": 0.35813069343566895,
      "learning_rate": 1.3398444408992466e-05,
      "loss": 0.554,
      "step": 25429
    },
    {
      "epoch": 0.7811876017571345,
      "grad_norm": 0.3663506805896759,
      "learning_rate": 1.3397989891551506e-05,
      "loss": 0.555,
      "step": 25430
    },
    {
      "epoch": 0.7812183208920837,
      "grad_norm": 0.37882521748542786,
      "learning_rate": 1.3397535366174306e-05,
      "loss": 0.5579,
      "step": 25431
    },
    {
      "epoch": 0.7812490400270329,
      "grad_norm": 0.3580639362335205,
      "learning_rate": 1.3397080832861921e-05,
      "loss": 0.5868,
      "step": 25432
    },
    {
      "epoch": 0.781279759161982,
      "grad_norm": 0.3240402340888977,
      "learning_rate": 1.339662629161542e-05,
      "loss": 0.5613,
      "step": 25433
    },
    {
      "epoch": 0.7813104782969311,
      "grad_norm": 0.3988301157951355,
      "learning_rate": 1.3396171742435862e-05,
      "loss": 0.6174,
      "step": 25434
    },
    {
      "epoch": 0.7813411974318804,
      "grad_norm": 0.36444029211997986,
      "learning_rate": 1.3395717185324305e-05,
      "loss": 0.605,
      "step": 25435
    },
    {
      "epoch": 0.7813719165668295,
      "grad_norm": 0.38440564274787903,
      "learning_rate": 1.3395262620281815e-05,
      "loss": 0.6787,
      "step": 25436
    },
    {
      "epoch": 0.7814026357017786,
      "grad_norm": 0.3899966776371002,
      "learning_rate": 1.3394808047309451e-05,
      "loss": 0.5839,
      "step": 25437
    },
    {
      "epoch": 0.7814333548367278,
      "grad_norm": 0.4687120318412781,
      "learning_rate": 1.3394353466408277e-05,
      "loss": 0.5937,
      "step": 25438
    },
    {
      "epoch": 0.7814640739716769,
      "grad_norm": 0.35310161113739014,
      "learning_rate": 1.339389887757935e-05,
      "loss": 0.5446,
      "step": 25439
    },
    {
      "epoch": 0.7814947931066261,
      "grad_norm": 0.3946397006511688,
      "learning_rate": 1.3393444280823738e-05,
      "loss": 0.5814,
      "step": 25440
    },
    {
      "epoch": 0.7815255122415753,
      "grad_norm": 0.3907114267349243,
      "learning_rate": 1.3392989676142499e-05,
      "loss": 0.4759,
      "step": 25441
    },
    {
      "epoch": 0.7815562313765244,
      "grad_norm": 0.399709016084671,
      "learning_rate": 1.3392535063536695e-05,
      "loss": 0.5818,
      "step": 25442
    },
    {
      "epoch": 0.7815869505114736,
      "grad_norm": 0.38215410709381104,
      "learning_rate": 1.339208044300739e-05,
      "loss": 0.5633,
      "step": 25443
    },
    {
      "epoch": 0.7816176696464228,
      "grad_norm": 0.35187140107154846,
      "learning_rate": 1.3391625814555641e-05,
      "loss": 0.5452,
      "step": 25444
    },
    {
      "epoch": 0.7816483887813719,
      "grad_norm": 0.3553260266780853,
      "learning_rate": 1.3391171178182519e-05,
      "loss": 0.569,
      "step": 25445
    },
    {
      "epoch": 0.7816791079163211,
      "grad_norm": 0.37788867950439453,
      "learning_rate": 1.3390716533889074e-05,
      "loss": 0.5418,
      "step": 25446
    },
    {
      "epoch": 0.7817098270512702,
      "grad_norm": 0.3705982267856598,
      "learning_rate": 1.3390261881676379e-05,
      "loss": 0.5927,
      "step": 25447
    },
    {
      "epoch": 0.7817405461862194,
      "grad_norm": 0.488834023475647,
      "learning_rate": 1.3389807221545485e-05,
      "loss": 0.576,
      "step": 25448
    },
    {
      "epoch": 0.7817712653211686,
      "grad_norm": 0.36718320846557617,
      "learning_rate": 1.3389352553497465e-05,
      "loss": 0.6011,
      "step": 25449
    },
    {
      "epoch": 0.7818019844561177,
      "grad_norm": 0.3808114528656006,
      "learning_rate": 1.338889787753337e-05,
      "loss": 0.5389,
      "step": 25450
    },
    {
      "epoch": 0.7818327035910668,
      "grad_norm": 0.37641847133636475,
      "learning_rate": 1.3388443193654273e-05,
      "loss": 0.5609,
      "step": 25451
    },
    {
      "epoch": 0.781863422726016,
      "grad_norm": 0.40877464413642883,
      "learning_rate": 1.338798850186123e-05,
      "loss": 0.6189,
      "step": 25452
    },
    {
      "epoch": 0.7818941418609652,
      "grad_norm": 0.413413405418396,
      "learning_rate": 1.3387533802155297e-05,
      "loss": 0.5168,
      "step": 25453
    },
    {
      "epoch": 0.7819248609959144,
      "grad_norm": 0.34732913970947266,
      "learning_rate": 1.3387079094537547e-05,
      "loss": 0.5551,
      "step": 25454
    },
    {
      "epoch": 0.7819555801308635,
      "grad_norm": 0.34031808376312256,
      "learning_rate": 1.3386624379009035e-05,
      "loss": 0.4886,
      "step": 25455
    },
    {
      "epoch": 0.7819862992658126,
      "grad_norm": 0.4412764310836792,
      "learning_rate": 1.3386169655570829e-05,
      "loss": 0.5736,
      "step": 25456
    },
    {
      "epoch": 0.7820170184007619,
      "grad_norm": 0.3408191204071045,
      "learning_rate": 1.3385714924223983e-05,
      "loss": 0.5199,
      "step": 25457
    },
    {
      "epoch": 0.782047737535711,
      "grad_norm": 0.3460613787174225,
      "learning_rate": 1.3385260184969564e-05,
      "loss": 0.5542,
      "step": 25458
    },
    {
      "epoch": 0.7820784566706601,
      "grad_norm": 0.3856275677680969,
      "learning_rate": 1.3384805437808635e-05,
      "loss": 0.5806,
      "step": 25459
    },
    {
      "epoch": 0.7821091758056093,
      "grad_norm": 0.3641132116317749,
      "learning_rate": 1.3384350682742256e-05,
      "loss": 0.5459,
      "step": 25460
    },
    {
      "epoch": 0.7821398949405585,
      "grad_norm": 0.3307967483997345,
      "learning_rate": 1.338389591977149e-05,
      "loss": 0.583,
      "step": 25461
    },
    {
      "epoch": 0.7821706140755076,
      "grad_norm": 0.37387216091156006,
      "learning_rate": 1.3383441148897396e-05,
      "loss": 0.6185,
      "step": 25462
    },
    {
      "epoch": 0.7822013332104568,
      "grad_norm": 0.35643720626831055,
      "learning_rate": 1.3382986370121043e-05,
      "loss": 0.5202,
      "step": 25463
    },
    {
      "epoch": 0.7822320523454059,
      "grad_norm": 0.36681830883026123,
      "learning_rate": 1.3382531583443486e-05,
      "loss": 0.5486,
      "step": 25464
    },
    {
      "epoch": 0.7822627714803552,
      "grad_norm": 0.42116814851760864,
      "learning_rate": 1.3382076788865792e-05,
      "loss": 0.5417,
      "step": 25465
    },
    {
      "epoch": 0.7822934906153043,
      "grad_norm": 0.39442339539527893,
      "learning_rate": 1.338162198638902e-05,
      "loss": 0.4897,
      "step": 25466
    },
    {
      "epoch": 0.7823242097502534,
      "grad_norm": 0.41067278385162354,
      "learning_rate": 1.3381167176014235e-05,
      "loss": 0.6592,
      "step": 25467
    },
    {
      "epoch": 0.7823549288852026,
      "grad_norm": 0.3425329327583313,
      "learning_rate": 1.3380712357742498e-05,
      "loss": 0.5348,
      "step": 25468
    },
    {
      "epoch": 0.7823856480201518,
      "grad_norm": 0.45461419224739075,
      "learning_rate": 1.3380257531574871e-05,
      "loss": 0.6171,
      "step": 25469
    },
    {
      "epoch": 0.7824163671551009,
      "grad_norm": 0.40245959162712097,
      "learning_rate": 1.3379802697512417e-05,
      "loss": 0.5347,
      "step": 25470
    },
    {
      "epoch": 0.7824470862900501,
      "grad_norm": 0.36355966329574585,
      "learning_rate": 1.3379347855556195e-05,
      "loss": 0.6856,
      "step": 25471
    },
    {
      "epoch": 0.7824778054249992,
      "grad_norm": 0.3683556616306305,
      "learning_rate": 1.3378893005707275e-05,
      "loss": 0.6031,
      "step": 25472
    },
    {
      "epoch": 0.7825085245599483,
      "grad_norm": 0.9150704145431519,
      "learning_rate": 1.337843814796671e-05,
      "loss": 0.6635,
      "step": 25473
    },
    {
      "epoch": 0.7825392436948976,
      "grad_norm": 0.34667113423347473,
      "learning_rate": 1.3377983282335566e-05,
      "loss": 0.5691,
      "step": 25474
    },
    {
      "epoch": 0.7825699628298467,
      "grad_norm": 0.3663831353187561,
      "learning_rate": 1.3377528408814907e-05,
      "loss": 0.5481,
      "step": 25475
    },
    {
      "epoch": 0.7826006819647958,
      "grad_norm": 0.39653897285461426,
      "learning_rate": 1.3377073527405799e-05,
      "loss": 0.5314,
      "step": 25476
    },
    {
      "epoch": 0.782631401099745,
      "grad_norm": 0.3745523691177368,
      "learning_rate": 1.3376618638109295e-05,
      "loss": 0.5317,
      "step": 25477
    },
    {
      "epoch": 0.7826621202346942,
      "grad_norm": 0.37393254041671753,
      "learning_rate": 1.3376163740926464e-05,
      "loss": 0.5437,
      "step": 25478
    },
    {
      "epoch": 0.7826928393696434,
      "grad_norm": 0.36288779973983765,
      "learning_rate": 1.3375708835858367e-05,
      "loss": 0.5361,
      "step": 25479
    },
    {
      "epoch": 0.7827235585045925,
      "grad_norm": 0.3399887681007385,
      "learning_rate": 1.3375253922906066e-05,
      "loss": 0.5658,
      "step": 25480
    },
    {
      "epoch": 0.7827542776395416,
      "grad_norm": 0.40628135204315186,
      "learning_rate": 1.3374799002070625e-05,
      "loss": 0.5388,
      "step": 25481
    },
    {
      "epoch": 0.7827849967744909,
      "grad_norm": 0.3708997070789337,
      "learning_rate": 1.3374344073353103e-05,
      "loss": 0.4977,
      "step": 25482
    },
    {
      "epoch": 0.78281571590944,
      "grad_norm": 0.38399815559387207,
      "learning_rate": 1.3373889136754568e-05,
      "loss": 0.5027,
      "step": 25483
    },
    {
      "epoch": 0.7828464350443891,
      "grad_norm": 0.36928945779800415,
      "learning_rate": 1.3373434192276075e-05,
      "loss": 0.5671,
      "step": 25484
    },
    {
      "epoch": 0.7828771541793383,
      "grad_norm": 0.38718757033348083,
      "learning_rate": 1.3372979239918692e-05,
      "loss": 0.5085,
      "step": 25485
    },
    {
      "epoch": 0.7829078733142875,
      "grad_norm": 0.3805525302886963,
      "learning_rate": 1.3372524279683486e-05,
      "loss": 0.4707,
      "step": 25486
    },
    {
      "epoch": 0.7829385924492366,
      "grad_norm": 0.35944536328315735,
      "learning_rate": 1.3372069311571507e-05,
      "loss": 0.5301,
      "step": 25487
    },
    {
      "epoch": 0.7829693115841858,
      "grad_norm": 0.3874491751194,
      "learning_rate": 1.3371614335583828e-05,
      "loss": 0.5973,
      "step": 25488
    },
    {
      "epoch": 0.7830000307191349,
      "grad_norm": 0.38892674446105957,
      "learning_rate": 1.3371159351721505e-05,
      "loss": 0.6247,
      "step": 25489
    },
    {
      "epoch": 0.7830307498540842,
      "grad_norm": 0.38408342003822327,
      "learning_rate": 1.337070435998561e-05,
      "loss": 0.5587,
      "step": 25490
    },
    {
      "epoch": 0.7830614689890333,
      "grad_norm": 0.7183984518051147,
      "learning_rate": 1.3370249360377195e-05,
      "loss": 0.6235,
      "step": 25491
    },
    {
      "epoch": 0.7830921881239824,
      "grad_norm": 0.6154394745826721,
      "learning_rate": 1.3369794352897327e-05,
      "loss": 0.5902,
      "step": 25492
    },
    {
      "epoch": 0.7831229072589316,
      "grad_norm": 0.37668076157569885,
      "learning_rate": 1.3369339337547069e-05,
      "loss": 0.5712,
      "step": 25493
    },
    {
      "epoch": 0.7831536263938808,
      "grad_norm": 0.3805103898048401,
      "learning_rate": 1.3368884314327485e-05,
      "loss": 0.6355,
      "step": 25494
    },
    {
      "epoch": 0.7831843455288299,
      "grad_norm": 0.5883638858795166,
      "learning_rate": 1.3368429283239635e-05,
      "loss": 0.5083,
      "step": 25495
    },
    {
      "epoch": 0.7832150646637791,
      "grad_norm": 0.33270472288131714,
      "learning_rate": 1.3367974244284585e-05,
      "loss": 0.5334,
      "step": 25496
    },
    {
      "epoch": 0.7832457837987282,
      "grad_norm": 0.4229500889778137,
      "learning_rate": 1.3367519197463394e-05,
      "loss": 0.551,
      "step": 25497
    },
    {
      "epoch": 0.7832765029336773,
      "grad_norm": 0.36030712723731995,
      "learning_rate": 1.3367064142777127e-05,
      "loss": 0.5755,
      "step": 25498
    },
    {
      "epoch": 0.7833072220686266,
      "grad_norm": 0.39602363109588623,
      "learning_rate": 1.3366609080226849e-05,
      "loss": 0.6312,
      "step": 25499
    },
    {
      "epoch": 0.7833379412035757,
      "grad_norm": 0.3805014193058014,
      "learning_rate": 1.3366154009813617e-05,
      "loss": 0.518,
      "step": 25500
    },
    {
      "epoch": 0.7833686603385248,
      "grad_norm": 0.4507044851779938,
      "learning_rate": 1.33656989315385e-05,
      "loss": 0.6166,
      "step": 25501
    },
    {
      "epoch": 0.783399379473474,
      "grad_norm": 0.3746791481971741,
      "learning_rate": 1.3365243845402556e-05,
      "loss": 0.5281,
      "step": 25502
    },
    {
      "epoch": 0.7834300986084232,
      "grad_norm": 0.400005578994751,
      "learning_rate": 1.3364788751406854e-05,
      "loss": 0.5958,
      "step": 25503
    },
    {
      "epoch": 0.7834608177433724,
      "grad_norm": 0.5186564326286316,
      "learning_rate": 1.336433364955245e-05,
      "loss": 0.557,
      "step": 25504
    },
    {
      "epoch": 0.7834915368783215,
      "grad_norm": 0.34143975377082825,
      "learning_rate": 1.3363878539840409e-05,
      "loss": 0.5423,
      "step": 25505
    },
    {
      "epoch": 0.7835222560132706,
      "grad_norm": 0.4372069835662842,
      "learning_rate": 1.3363423422271795e-05,
      "loss": 0.5469,
      "step": 25506
    },
    {
      "epoch": 0.7835529751482199,
      "grad_norm": 0.3531036078929901,
      "learning_rate": 1.3362968296847672e-05,
      "loss": 0.5663,
      "step": 25507
    },
    {
      "epoch": 0.783583694283169,
      "grad_norm": 0.405367910861969,
      "learning_rate": 1.33625131635691e-05,
      "loss": 0.5053,
      "step": 25508
    },
    {
      "epoch": 0.7836144134181181,
      "grad_norm": 0.3817085027694702,
      "learning_rate": 1.3362058022437143e-05,
      "loss": 0.5888,
      "step": 25509
    },
    {
      "epoch": 0.7836451325530673,
      "grad_norm": 0.3639458417892456,
      "learning_rate": 1.3361602873452869e-05,
      "loss": 0.5509,
      "step": 25510
    },
    {
      "epoch": 0.7836758516880165,
      "grad_norm": 0.4658116400241852,
      "learning_rate": 1.3361147716617333e-05,
      "loss": 0.5312,
      "step": 25511
    },
    {
      "epoch": 0.7837065708229656,
      "grad_norm": 0.3359285295009613,
      "learning_rate": 1.3360692551931602e-05,
      "loss": 0.5825,
      "step": 25512
    },
    {
      "epoch": 0.7837372899579148,
      "grad_norm": 0.3234119415283203,
      "learning_rate": 1.3360237379396739e-05,
      "loss": 0.5878,
      "step": 25513
    },
    {
      "epoch": 0.7837680090928639,
      "grad_norm": 0.35607561469078064,
      "learning_rate": 1.3359782199013807e-05,
      "loss": 0.6053,
      "step": 25514
    },
    {
      "epoch": 0.7837987282278132,
      "grad_norm": 0.38064688444137573,
      "learning_rate": 1.3359327010783871e-05,
      "loss": 0.5842,
      "step": 25515
    },
    {
      "epoch": 0.7838294473627623,
      "grad_norm": 0.38499417901039124,
      "learning_rate": 1.335887181470799e-05,
      "loss": 0.5048,
      "step": 25516
    },
    {
      "epoch": 0.7838601664977114,
      "grad_norm": 0.46147620677948,
      "learning_rate": 1.335841661078723e-05,
      "loss": 0.6135,
      "step": 25517
    },
    {
      "epoch": 0.7838908856326606,
      "grad_norm": 0.3723396956920624,
      "learning_rate": 1.3357961399022652e-05,
      "loss": 0.571,
      "step": 25518
    },
    {
      "epoch": 0.7839216047676097,
      "grad_norm": 0.3888065814971924,
      "learning_rate": 1.3357506179415322e-05,
      "loss": 0.5377,
      "step": 25519
    },
    {
      "epoch": 0.7839523239025589,
      "grad_norm": 0.3613230884075165,
      "learning_rate": 1.3357050951966304e-05,
      "loss": 0.5107,
      "step": 25520
    },
    {
      "epoch": 0.7839830430375081,
      "grad_norm": 0.40241968631744385,
      "learning_rate": 1.3356595716676655e-05,
      "loss": 0.6104,
      "step": 25521
    },
    {
      "epoch": 0.7840137621724572,
      "grad_norm": 0.37505683302879333,
      "learning_rate": 1.3356140473547446e-05,
      "loss": 0.5634,
      "step": 25522
    },
    {
      "epoch": 0.7840444813074063,
      "grad_norm": 0.3414255976676941,
      "learning_rate": 1.3355685222579732e-05,
      "loss": 0.4435,
      "step": 25523
    },
    {
      "epoch": 0.7840752004423556,
      "grad_norm": 0.3712668716907501,
      "learning_rate": 1.3355229963774585e-05,
      "loss": 0.6068,
      "step": 25524
    },
    {
      "epoch": 0.7841059195773047,
      "grad_norm": 0.45417168736457825,
      "learning_rate": 1.3354774697133061e-05,
      "loss": 0.5091,
      "step": 25525
    },
    {
      "epoch": 0.7841366387122538,
      "grad_norm": 0.4303506016731262,
      "learning_rate": 1.3354319422656231e-05,
      "loss": 0.4593,
      "step": 25526
    },
    {
      "epoch": 0.784167357847203,
      "grad_norm": 0.38060033321380615,
      "learning_rate": 1.3353864140345149e-05,
      "loss": 0.554,
      "step": 25527
    },
    {
      "epoch": 0.7841980769821522,
      "grad_norm": 0.38089561462402344,
      "learning_rate": 1.3353408850200886e-05,
      "loss": 0.5286,
      "step": 25528
    },
    {
      "epoch": 0.7842287961171014,
      "grad_norm": 0.4334641695022583,
      "learning_rate": 1.3352953552224501e-05,
      "loss": 0.5695,
      "step": 25529
    },
    {
      "epoch": 0.7842595152520505,
      "grad_norm": 0.44873523712158203,
      "learning_rate": 1.3352498246417059e-05,
      "loss": 0.575,
      "step": 25530
    },
    {
      "epoch": 0.7842902343869996,
      "grad_norm": 0.3432571589946747,
      "learning_rate": 1.3352042932779626e-05,
      "loss": 0.4923,
      "step": 25531
    },
    {
      "epoch": 0.7843209535219489,
      "grad_norm": 0.35618212819099426,
      "learning_rate": 1.3351587611313257e-05,
      "loss": 0.5668,
      "step": 25532
    },
    {
      "epoch": 0.784351672656898,
      "grad_norm": 0.3585471212863922,
      "learning_rate": 1.3351132282019024e-05,
      "loss": 0.5695,
      "step": 25533
    },
    {
      "epoch": 0.7843823917918471,
      "grad_norm": 0.3715992569923401,
      "learning_rate": 1.3350676944897987e-05,
      "loss": 0.5914,
      "step": 25534
    },
    {
      "epoch": 0.7844131109267963,
      "grad_norm": 0.37443631887435913,
      "learning_rate": 1.335022159995121e-05,
      "loss": 0.5123,
      "step": 25535
    },
    {
      "epoch": 0.7844438300617455,
      "grad_norm": 0.3763824999332428,
      "learning_rate": 1.3349766247179756e-05,
      "loss": 0.5333,
      "step": 25536
    },
    {
      "epoch": 0.7844745491966946,
      "grad_norm": 0.4436018168926239,
      "learning_rate": 1.3349310886584692e-05,
      "loss": 0.5567,
      "step": 25537
    },
    {
      "epoch": 0.7845052683316438,
      "grad_norm": 0.5318166613578796,
      "learning_rate": 1.3348855518167076e-05,
      "loss": 0.5224,
      "step": 25538
    },
    {
      "epoch": 0.7845359874665929,
      "grad_norm": 0.34165671467781067,
      "learning_rate": 1.3348400141927972e-05,
      "loss": 0.4988,
      "step": 25539
    },
    {
      "epoch": 0.7845667066015422,
      "grad_norm": 0.3528457581996918,
      "learning_rate": 1.3347944757868452e-05,
      "loss": 0.5272,
      "step": 25540
    },
    {
      "epoch": 0.7845974257364913,
      "grad_norm": 0.3273635506629944,
      "learning_rate": 1.3347489365989567e-05,
      "loss": 0.5707,
      "step": 25541
    },
    {
      "epoch": 0.7846281448714404,
      "grad_norm": 0.38448965549468994,
      "learning_rate": 1.334703396629239e-05,
      "loss": 0.6032,
      "step": 25542
    },
    {
      "epoch": 0.7846588640063896,
      "grad_norm": 0.3486146330833435,
      "learning_rate": 1.3346578558777981e-05,
      "loss": 0.5538,
      "step": 25543
    },
    {
      "epoch": 0.7846895831413387,
      "grad_norm": 0.3923783302307129,
      "learning_rate": 1.3346123143447402e-05,
      "loss": 0.5272,
      "step": 25544
    },
    {
      "epoch": 0.7847203022762879,
      "grad_norm": 0.44027969241142273,
      "learning_rate": 1.334566772030172e-05,
      "loss": 0.5656,
      "step": 25545
    },
    {
      "epoch": 0.7847510214112371,
      "grad_norm": 0.3876269459724426,
      "learning_rate": 1.3345212289341998e-05,
      "loss": 0.56,
      "step": 25546
    },
    {
      "epoch": 0.7847817405461862,
      "grad_norm": 0.34452760219573975,
      "learning_rate": 1.3344756850569299e-05,
      "loss": 0.5405,
      "step": 25547
    },
    {
      "epoch": 0.7848124596811353,
      "grad_norm": 0.34904757142066956,
      "learning_rate": 1.3344301403984688e-05,
      "loss": 0.5814,
      "step": 25548
    },
    {
      "epoch": 0.7848431788160846,
      "grad_norm": 0.35193687677383423,
      "learning_rate": 1.3343845949589227e-05,
      "loss": 0.5327,
      "step": 25549
    },
    {
      "epoch": 0.7848738979510337,
      "grad_norm": 0.39284974336624146,
      "learning_rate": 1.3343390487383979e-05,
      "loss": 0.5728,
      "step": 25550
    },
    {
      "epoch": 0.7849046170859829,
      "grad_norm": 0.5599719285964966,
      "learning_rate": 1.3342935017370006e-05,
      "loss": 0.5192,
      "step": 25551
    },
    {
      "epoch": 0.784935336220932,
      "grad_norm": 0.3482486307621002,
      "learning_rate": 1.3342479539548379e-05,
      "loss": 0.5887,
      "step": 25552
    },
    {
      "epoch": 0.7849660553558812,
      "grad_norm": 0.34623146057128906,
      "learning_rate": 1.3342024053920155e-05,
      "loss": 0.4702,
      "step": 25553
    },
    {
      "epoch": 0.7849967744908304,
      "grad_norm": 0.3524731993675232,
      "learning_rate": 1.3341568560486402e-05,
      "loss": 0.5602,
      "step": 25554
    },
    {
      "epoch": 0.7850274936257795,
      "grad_norm": 0.40665990114212036,
      "learning_rate": 1.3341113059248183e-05,
      "loss": 0.5959,
      "step": 25555
    },
    {
      "epoch": 0.7850582127607286,
      "grad_norm": 0.3921956717967987,
      "learning_rate": 1.3340657550206561e-05,
      "loss": 0.5435,
      "step": 25556
    },
    {
      "epoch": 0.7850889318956779,
      "grad_norm": 0.38502198457717896,
      "learning_rate": 1.3340202033362599e-05,
      "loss": 0.597,
      "step": 25557
    },
    {
      "epoch": 0.785119651030627,
      "grad_norm": 0.38371628522872925,
      "learning_rate": 1.3339746508717364e-05,
      "loss": 0.5348,
      "step": 25558
    },
    {
      "epoch": 0.7851503701655761,
      "grad_norm": 0.33413758873939514,
      "learning_rate": 1.3339290976271915e-05,
      "loss": 0.5403,
      "step": 25559
    },
    {
      "epoch": 0.7851810893005253,
      "grad_norm": 0.4093566834926605,
      "learning_rate": 1.333883543602732e-05,
      "loss": 0.542,
      "step": 25560
    },
    {
      "epoch": 0.7852118084354744,
      "grad_norm": 0.3369514048099518,
      "learning_rate": 1.333837988798464e-05,
      "loss": 0.5459,
      "step": 25561
    },
    {
      "epoch": 0.7852425275704236,
      "grad_norm": 0.43897727131843567,
      "learning_rate": 1.3337924332144945e-05,
      "loss": 0.5079,
      "step": 25562
    },
    {
      "epoch": 0.7852732467053728,
      "grad_norm": 0.35562804341316223,
      "learning_rate": 1.333746876850929e-05,
      "loss": 0.462,
      "step": 25563
    },
    {
      "epoch": 0.7853039658403219,
      "grad_norm": 0.32126665115356445,
      "learning_rate": 1.3337013197078746e-05,
      "loss": 0.4749,
      "step": 25564
    },
    {
      "epoch": 0.7853346849752711,
      "grad_norm": 0.3852425217628479,
      "learning_rate": 1.3336557617854373e-05,
      "loss": 0.5025,
      "step": 25565
    },
    {
      "epoch": 0.7853654041102203,
      "grad_norm": 0.3827793002128601,
      "learning_rate": 1.3336102030837239e-05,
      "loss": 0.6432,
      "step": 25566
    },
    {
      "epoch": 0.7853961232451694,
      "grad_norm": 0.3752584755420685,
      "learning_rate": 1.3335646436028405e-05,
      "loss": 0.5119,
      "step": 25567
    },
    {
      "epoch": 0.7854268423801186,
      "grad_norm": 0.616121232509613,
      "learning_rate": 1.3335190833428934e-05,
      "loss": 0.532,
      "step": 25568
    },
    {
      "epoch": 0.7854575615150677,
      "grad_norm": 0.46701109409332275,
      "learning_rate": 1.3334735223039893e-05,
      "loss": 0.6175,
      "step": 25569
    },
    {
      "epoch": 0.7854882806500169,
      "grad_norm": 0.3490441143512726,
      "learning_rate": 1.3334279604862341e-05,
      "loss": 0.5154,
      "step": 25570
    },
    {
      "epoch": 0.7855189997849661,
      "grad_norm": 0.5582562685012817,
      "learning_rate": 1.3333823978897353e-05,
      "loss": 0.6458,
      "step": 25571
    },
    {
      "epoch": 0.7855497189199152,
      "grad_norm": 0.36094221472740173,
      "learning_rate": 1.3333368345145983e-05,
      "loss": 0.6117,
      "step": 25572
    },
    {
      "epoch": 0.7855804380548643,
      "grad_norm": 0.368044376373291,
      "learning_rate": 1.3332912703609297e-05,
      "loss": 0.5629,
      "step": 25573
    },
    {
      "epoch": 0.7856111571898136,
      "grad_norm": 0.4347415864467621,
      "learning_rate": 1.3332457054288367e-05,
      "loss": 0.5508,
      "step": 25574
    },
    {
      "epoch": 0.7856418763247627,
      "grad_norm": 0.5349265336990356,
      "learning_rate": 1.3332001397184242e-05,
      "loss": 0.5642,
      "step": 25575
    },
    {
      "epoch": 0.7856725954597119,
      "grad_norm": 0.3700239062309265,
      "learning_rate": 1.3331545732298002e-05,
      "loss": 0.5327,
      "step": 25576
    },
    {
      "epoch": 0.785703314594661,
      "grad_norm": 0.4159432649612427,
      "learning_rate": 1.33310900596307e-05,
      "loss": 0.5061,
      "step": 25577
    },
    {
      "epoch": 0.7857340337296101,
      "grad_norm": 0.3447383940219879,
      "learning_rate": 1.3330634379183407e-05,
      "loss": 0.5369,
      "step": 25578
    },
    {
      "epoch": 0.7857647528645594,
      "grad_norm": 0.424851655960083,
      "learning_rate": 1.3330178690957182e-05,
      "loss": 0.5402,
      "step": 25579
    },
    {
      "epoch": 0.7857954719995085,
      "grad_norm": 0.35713207721710205,
      "learning_rate": 1.3329722994953097e-05,
      "loss": 0.5325,
      "step": 25580
    },
    {
      "epoch": 0.7858261911344576,
      "grad_norm": 0.346017062664032,
      "learning_rate": 1.3329267291172205e-05,
      "loss": 0.5939,
      "step": 25581
    },
    {
      "epoch": 0.7858569102694068,
      "grad_norm": 0.3509264886379242,
      "learning_rate": 1.3328811579615581e-05,
      "loss": 0.5824,
      "step": 25582
    },
    {
      "epoch": 0.785887629404356,
      "grad_norm": 0.32563287019729614,
      "learning_rate": 1.3328355860284283e-05,
      "loss": 0.5326,
      "step": 25583
    },
    {
      "epoch": 0.7859183485393051,
      "grad_norm": 0.3614368140697479,
      "learning_rate": 1.3327900133179382e-05,
      "loss": 0.6141,
      "step": 25584
    },
    {
      "epoch": 0.7859490676742543,
      "grad_norm": 0.347596675157547,
      "learning_rate": 1.3327444398301933e-05,
      "loss": 0.5293,
      "step": 25585
    },
    {
      "epoch": 0.7859797868092034,
      "grad_norm": 0.33221226930618286,
      "learning_rate": 1.3326988655653005e-05,
      "loss": 0.5534,
      "step": 25586
    },
    {
      "epoch": 0.7860105059441526,
      "grad_norm": 0.32850930094718933,
      "learning_rate": 1.3326532905233665e-05,
      "loss": 0.4745,
      "step": 25587
    },
    {
      "epoch": 0.7860412250791018,
      "grad_norm": 0.37539973855018616,
      "learning_rate": 1.3326077147044974e-05,
      "loss": 0.5832,
      "step": 25588
    },
    {
      "epoch": 0.7860719442140509,
      "grad_norm": 0.36711615324020386,
      "learning_rate": 1.3325621381088e-05,
      "loss": 0.5192,
      "step": 25589
    },
    {
      "epoch": 0.7861026633490001,
      "grad_norm": 0.4215741753578186,
      "learning_rate": 1.3325165607363801e-05,
      "loss": 0.5945,
      "step": 25590
    },
    {
      "epoch": 0.7861333824839493,
      "grad_norm": 0.3396335542201996,
      "learning_rate": 1.3324709825873447e-05,
      "loss": 0.5985,
      "step": 25591
    },
    {
      "epoch": 0.7861641016188984,
      "grad_norm": 0.41550081968307495,
      "learning_rate": 1.3324254036618003e-05,
      "loss": 0.5855,
      "step": 25592
    },
    {
      "epoch": 0.7861948207538476,
      "grad_norm": 0.36707574129104614,
      "learning_rate": 1.3323798239598528e-05,
      "loss": 0.5548,
      "step": 25593
    },
    {
      "epoch": 0.7862255398887967,
      "grad_norm": 0.35108357667922974,
      "learning_rate": 1.3323342434816093e-05,
      "loss": 0.6027,
      "step": 25594
    },
    {
      "epoch": 0.7862562590237459,
      "grad_norm": 0.4170188903808594,
      "learning_rate": 1.3322886622271758e-05,
      "loss": 0.541,
      "step": 25595
    },
    {
      "epoch": 0.7862869781586951,
      "grad_norm": 0.5123753547668457,
      "learning_rate": 1.332243080196659e-05,
      "loss": 0.5869,
      "step": 25596
    },
    {
      "epoch": 0.7863176972936442,
      "grad_norm": 0.4324592649936676,
      "learning_rate": 1.3321974973901652e-05,
      "loss": 0.5148,
      "step": 25597
    },
    {
      "epoch": 0.7863484164285933,
      "grad_norm": 0.3376709222793579,
      "learning_rate": 1.3321519138078012e-05,
      "loss": 0.5309,
      "step": 25598
    },
    {
      "epoch": 0.7863791355635426,
      "grad_norm": 0.3790147304534912,
      "learning_rate": 1.3321063294496728e-05,
      "loss": 0.5958,
      "step": 25599
    },
    {
      "epoch": 0.7864098546984917,
      "grad_norm": 0.3540298640727997,
      "learning_rate": 1.3320607443158873e-05,
      "loss": 0.553,
      "step": 25600
    },
    {
      "epoch": 0.7864405738334409,
      "grad_norm": 0.3628934323787689,
      "learning_rate": 1.3320151584065507e-05,
      "loss": 0.6074,
      "step": 25601
    },
    {
      "epoch": 0.78647129296839,
      "grad_norm": 0.36749911308288574,
      "learning_rate": 1.3319695717217691e-05,
      "loss": 0.6347,
      "step": 25602
    },
    {
      "epoch": 0.7865020121033391,
      "grad_norm": 0.3608871400356293,
      "learning_rate": 1.3319239842616498e-05,
      "loss": 0.5884,
      "step": 25603
    },
    {
      "epoch": 0.7865327312382884,
      "grad_norm": 0.3629334270954132,
      "learning_rate": 1.3318783960262986e-05,
      "loss": 0.5447,
      "step": 25604
    },
    {
      "epoch": 0.7865634503732375,
      "grad_norm": 0.40241578221321106,
      "learning_rate": 1.3318328070158222e-05,
      "loss": 0.5937,
      "step": 25605
    },
    {
      "epoch": 0.7865941695081866,
      "grad_norm": 0.36860406398773193,
      "learning_rate": 1.331787217230327e-05,
      "loss": 0.4874,
      "step": 25606
    },
    {
      "epoch": 0.7866248886431358,
      "grad_norm": 0.3694966435432434,
      "learning_rate": 1.3317416266699199e-05,
      "loss": 0.6023,
      "step": 25607
    },
    {
      "epoch": 0.786655607778085,
      "grad_norm": 0.4055890738964081,
      "learning_rate": 1.331696035334707e-05,
      "loss": 0.5523,
      "step": 25608
    },
    {
      "epoch": 0.7866863269130341,
      "grad_norm": 0.36765769124031067,
      "learning_rate": 1.3316504432247948e-05,
      "loss": 0.5516,
      "step": 25609
    },
    {
      "epoch": 0.7867170460479833,
      "grad_norm": 0.3507416844367981,
      "learning_rate": 1.33160485034029e-05,
      "loss": 0.5798,
      "step": 25610
    },
    {
      "epoch": 0.7867477651829324,
      "grad_norm": 0.3906136751174927,
      "learning_rate": 1.3315592566812984e-05,
      "loss": 0.6149,
      "step": 25611
    },
    {
      "epoch": 0.7867784843178816,
      "grad_norm": 0.3383846580982208,
      "learning_rate": 1.3315136622479274e-05,
      "loss": 0.5051,
      "step": 25612
    },
    {
      "epoch": 0.7868092034528308,
      "grad_norm": 0.38725757598876953,
      "learning_rate": 1.331468067040283e-05,
      "loss": 0.5909,
      "step": 25613
    },
    {
      "epoch": 0.7868399225877799,
      "grad_norm": 0.412456750869751,
      "learning_rate": 1.331422471058472e-05,
      "loss": 0.61,
      "step": 25614
    },
    {
      "epoch": 0.7868706417227291,
      "grad_norm": 0.3624573051929474,
      "learning_rate": 1.3313768743026004e-05,
      "loss": 0.5139,
      "step": 25615
    },
    {
      "epoch": 0.7869013608576783,
      "grad_norm": 0.494440495967865,
      "learning_rate": 1.331331276772775e-05,
      "loss": 0.5903,
      "step": 25616
    },
    {
      "epoch": 0.7869320799926274,
      "grad_norm": 0.40452221035957336,
      "learning_rate": 1.3312856784691025e-05,
      "loss": 0.5814,
      "step": 25617
    },
    {
      "epoch": 0.7869627991275766,
      "grad_norm": 0.40734562277793884,
      "learning_rate": 1.3312400793916888e-05,
      "loss": 0.5173,
      "step": 25618
    },
    {
      "epoch": 0.7869935182625257,
      "grad_norm": 0.342227965593338,
      "learning_rate": 1.331194479540641e-05,
      "loss": 0.5355,
      "step": 25619
    },
    {
      "epoch": 0.7870242373974748,
      "grad_norm": 0.3684552311897278,
      "learning_rate": 1.3311488789160654e-05,
      "loss": 0.516,
      "step": 25620
    },
    {
      "epoch": 0.7870549565324241,
      "grad_norm": 0.34446555376052856,
      "learning_rate": 1.3311032775180683e-05,
      "loss": 0.6284,
      "step": 25621
    },
    {
      "epoch": 0.7870856756673732,
      "grad_norm": 0.36331692337989807,
      "learning_rate": 1.3310576753467564e-05,
      "loss": 0.6126,
      "step": 25622
    },
    {
      "epoch": 0.7871163948023223,
      "grad_norm": 0.4586779475212097,
      "learning_rate": 1.3310120724022363e-05,
      "loss": 0.5283,
      "step": 25623
    },
    {
      "epoch": 0.7871471139372715,
      "grad_norm": 0.3868986666202545,
      "learning_rate": 1.3309664686846139e-05,
      "loss": 0.5896,
      "step": 25624
    },
    {
      "epoch": 0.7871778330722207,
      "grad_norm": 0.3517029583454132,
      "learning_rate": 1.3309208641939968e-05,
      "loss": 0.5768,
      "step": 25625
    },
    {
      "epoch": 0.7872085522071699,
      "grad_norm": 0.34237027168273926,
      "learning_rate": 1.3308752589304907e-05,
      "loss": 0.5752,
      "step": 25626
    },
    {
      "epoch": 0.787239271342119,
      "grad_norm": 0.3666422367095947,
      "learning_rate": 1.3308296528942025e-05,
      "loss": 0.5357,
      "step": 25627
    },
    {
      "epoch": 0.7872699904770681,
      "grad_norm": 0.3896860182285309,
      "learning_rate": 1.3307840460852384e-05,
      "loss": 0.4713,
      "step": 25628
    },
    {
      "epoch": 0.7873007096120174,
      "grad_norm": 0.35154592990875244,
      "learning_rate": 1.3307384385037048e-05,
      "loss": 0.5133,
      "step": 25629
    },
    {
      "epoch": 0.7873314287469665,
      "grad_norm": 0.36977192759513855,
      "learning_rate": 1.3306928301497088e-05,
      "loss": 0.572,
      "step": 25630
    },
    {
      "epoch": 0.7873621478819156,
      "grad_norm": 0.35299184918403625,
      "learning_rate": 1.3306472210233564e-05,
      "loss": 0.6855,
      "step": 25631
    },
    {
      "epoch": 0.7873928670168648,
      "grad_norm": 0.3907211124897003,
      "learning_rate": 1.3306016111247547e-05,
      "loss": 0.6053,
      "step": 25632
    },
    {
      "epoch": 0.787423586151814,
      "grad_norm": 0.4332434833049774,
      "learning_rate": 1.3305560004540094e-05,
      "loss": 0.6298,
      "step": 25633
    },
    {
      "epoch": 0.7874543052867631,
      "grad_norm": 0.387882262468338,
      "learning_rate": 1.3305103890112276e-05,
      "loss": 0.5204,
      "step": 25634
    },
    {
      "epoch": 0.7874850244217123,
      "grad_norm": 0.3816657066345215,
      "learning_rate": 1.3304647767965157e-05,
      "loss": 0.5184,
      "step": 25635
    },
    {
      "epoch": 0.7875157435566614,
      "grad_norm": 0.41527900099754333,
      "learning_rate": 1.3304191638099803e-05,
      "loss": 0.6147,
      "step": 25636
    },
    {
      "epoch": 0.7875464626916105,
      "grad_norm": 0.42363908886909485,
      "learning_rate": 1.3303735500517281e-05,
      "loss": 0.5283,
      "step": 25637
    },
    {
      "epoch": 0.7875771818265598,
      "grad_norm": 0.4128238558769226,
      "learning_rate": 1.330327935521865e-05,
      "loss": 0.6157,
      "step": 25638
    },
    {
      "epoch": 0.7876079009615089,
      "grad_norm": 0.35600385069847107,
      "learning_rate": 1.3302823202204981e-05,
      "loss": 0.5162,
      "step": 25639
    },
    {
      "epoch": 0.7876386200964581,
      "grad_norm": 0.39153972268104553,
      "learning_rate": 1.3302367041477338e-05,
      "loss": 0.5236,
      "step": 25640
    },
    {
      "epoch": 0.7876693392314073,
      "grad_norm": 0.453346848487854,
      "learning_rate": 1.3301910873036787e-05,
      "loss": 0.6279,
      "step": 25641
    },
    {
      "epoch": 0.7877000583663564,
      "grad_norm": 0.39570149779319763,
      "learning_rate": 1.3301454696884391e-05,
      "loss": 0.5172,
      "step": 25642
    },
    {
      "epoch": 0.7877307775013056,
      "grad_norm": 0.37996286153793335,
      "learning_rate": 1.3300998513021217e-05,
      "loss": 0.5045,
      "step": 25643
    },
    {
      "epoch": 0.7877614966362547,
      "grad_norm": 0.3277568221092224,
      "learning_rate": 1.3300542321448332e-05,
      "loss": 0.5344,
      "step": 25644
    },
    {
      "epoch": 0.7877922157712038,
      "grad_norm": 0.3520147204399109,
      "learning_rate": 1.3300086122166798e-05,
      "loss": 0.5181,
      "step": 25645
    },
    {
      "epoch": 0.7878229349061531,
      "grad_norm": 0.439515620470047,
      "learning_rate": 1.3299629915177683e-05,
      "loss": 0.5806,
      "step": 25646
    },
    {
      "epoch": 0.7878536540411022,
      "grad_norm": 0.38588863611221313,
      "learning_rate": 1.329917370048205e-05,
      "loss": 0.5606,
      "step": 25647
    },
    {
      "epoch": 0.7878843731760513,
      "grad_norm": 0.3634164333343506,
      "learning_rate": 1.329871747808097e-05,
      "loss": 0.5357,
      "step": 25648
    },
    {
      "epoch": 0.7879150923110005,
      "grad_norm": 0.44586917757987976,
      "learning_rate": 1.3298261247975503e-05,
      "loss": 0.5408,
      "step": 25649
    },
    {
      "epoch": 0.7879458114459497,
      "grad_norm": 0.355695903301239,
      "learning_rate": 1.3297805010166718e-05,
      "loss": 0.544,
      "step": 25650
    },
    {
      "epoch": 0.7879765305808989,
      "grad_norm": 0.38222232460975647,
      "learning_rate": 1.3297348764655675e-05,
      "loss": 0.5517,
      "step": 25651
    },
    {
      "epoch": 0.788007249715848,
      "grad_norm": 0.38252341747283936,
      "learning_rate": 1.3296892511443448e-05,
      "loss": 0.5422,
      "step": 25652
    },
    {
      "epoch": 0.7880379688507971,
      "grad_norm": 0.32421037554740906,
      "learning_rate": 1.32964362505311e-05,
      "loss": 0.4887,
      "step": 25653
    },
    {
      "epoch": 0.7880686879857464,
      "grad_norm": 0.4235456585884094,
      "learning_rate": 1.3295979981919688e-05,
      "loss": 0.628,
      "step": 25654
    },
    {
      "epoch": 0.7880994071206955,
      "grad_norm": 0.3408637046813965,
      "learning_rate": 1.3295523705610291e-05,
      "loss": 0.553,
      "step": 25655
    },
    {
      "epoch": 0.7881301262556446,
      "grad_norm": 0.3882433772087097,
      "learning_rate": 1.3295067421603964e-05,
      "loss": 0.576,
      "step": 25656
    },
    {
      "epoch": 0.7881608453905938,
      "grad_norm": 0.38968291878700256,
      "learning_rate": 1.329461112990178e-05,
      "loss": 0.51,
      "step": 25657
    },
    {
      "epoch": 0.788191564525543,
      "grad_norm": 0.35534653067588806,
      "learning_rate": 1.32941548305048e-05,
      "loss": 0.4957,
      "step": 25658
    },
    {
      "epoch": 0.7882222836604921,
      "grad_norm": 0.3757345378398895,
      "learning_rate": 1.3293698523414093e-05,
      "loss": 0.5031,
      "step": 25659
    },
    {
      "epoch": 0.7882530027954413,
      "grad_norm": 0.341940313577652,
      "learning_rate": 1.3293242208630722e-05,
      "loss": 0.5049,
      "step": 25660
    },
    {
      "epoch": 0.7882837219303904,
      "grad_norm": 0.36503955721855164,
      "learning_rate": 1.329278588615575e-05,
      "loss": 0.5593,
      "step": 25661
    },
    {
      "epoch": 0.7883144410653397,
      "grad_norm": 0.3988998234272003,
      "learning_rate": 1.329232955599025e-05,
      "loss": 0.5971,
      "step": 25662
    },
    {
      "epoch": 0.7883451602002888,
      "grad_norm": 0.3681340217590332,
      "learning_rate": 1.3291873218135285e-05,
      "loss": 0.5609,
      "step": 25663
    },
    {
      "epoch": 0.7883758793352379,
      "grad_norm": 0.3537129759788513,
      "learning_rate": 1.329141687259192e-05,
      "loss": 0.4897,
      "step": 25664
    },
    {
      "epoch": 0.7884065984701871,
      "grad_norm": 0.4013456106185913,
      "learning_rate": 1.329096051936122e-05,
      "loss": 0.6066,
      "step": 25665
    },
    {
      "epoch": 0.7884373176051362,
      "grad_norm": 0.3670867085456848,
      "learning_rate": 1.3290504158444254e-05,
      "loss": 0.561,
      "step": 25666
    },
    {
      "epoch": 0.7884680367400854,
      "grad_norm": 0.40838295221328735,
      "learning_rate": 1.3290047789842082e-05,
      "loss": 0.6163,
      "step": 25667
    },
    {
      "epoch": 0.7884987558750346,
      "grad_norm": 0.35899460315704346,
      "learning_rate": 1.3289591413555777e-05,
      "loss": 0.4897,
      "step": 25668
    },
    {
      "epoch": 0.7885294750099837,
      "grad_norm": 0.40172243118286133,
      "learning_rate": 1.32891350295864e-05,
      "loss": 0.5566,
      "step": 25669
    },
    {
      "epoch": 0.7885601941449328,
      "grad_norm": 0.40334561467170715,
      "learning_rate": 1.328867863793502e-05,
      "loss": 0.4813,
      "step": 25670
    },
    {
      "epoch": 0.7885909132798821,
      "grad_norm": 0.38538166880607605,
      "learning_rate": 1.3288222238602701e-05,
      "loss": 0.5803,
      "step": 25671
    },
    {
      "epoch": 0.7886216324148312,
      "grad_norm": 0.3578324317932129,
      "learning_rate": 1.3287765831590506e-05,
      "loss": 0.6156,
      "step": 25672
    },
    {
      "epoch": 0.7886523515497803,
      "grad_norm": 0.3929175138473511,
      "learning_rate": 1.3287309416899508e-05,
      "loss": 0.6036,
      "step": 25673
    },
    {
      "epoch": 0.7886830706847295,
      "grad_norm": 0.3469280004501343,
      "learning_rate": 1.3286852994530767e-05,
      "loss": 0.6175,
      "step": 25674
    },
    {
      "epoch": 0.7887137898196787,
      "grad_norm": 0.4527817964553833,
      "learning_rate": 1.3286396564485353e-05,
      "loss": 0.6764,
      "step": 25675
    },
    {
      "epoch": 0.7887445089546279,
      "grad_norm": 0.362690269947052,
      "learning_rate": 1.3285940126764329e-05,
      "loss": 0.5472,
      "step": 25676
    },
    {
      "epoch": 0.788775228089577,
      "grad_norm": 0.3603293299674988,
      "learning_rate": 1.3285483681368765e-05,
      "loss": 0.5026,
      "step": 25677
    },
    {
      "epoch": 0.7888059472245261,
      "grad_norm": 0.40015462040901184,
      "learning_rate": 1.3285027228299721e-05,
      "loss": 0.4586,
      "step": 25678
    },
    {
      "epoch": 0.7888366663594754,
      "grad_norm": 0.34264475107192993,
      "learning_rate": 1.3284570767558268e-05,
      "loss": 0.5516,
      "step": 25679
    },
    {
      "epoch": 0.7888673854944245,
      "grad_norm": 0.42345890402793884,
      "learning_rate": 1.328411429914547e-05,
      "loss": 0.4954,
      "step": 25680
    },
    {
      "epoch": 0.7888981046293736,
      "grad_norm": 0.40134525299072266,
      "learning_rate": 1.3283657823062393e-05,
      "loss": 0.5502,
      "step": 25681
    },
    {
      "epoch": 0.7889288237643228,
      "grad_norm": 0.3862386643886566,
      "learning_rate": 1.3283201339310106e-05,
      "loss": 0.5858,
      "step": 25682
    },
    {
      "epoch": 0.788959542899272,
      "grad_norm": 0.3684404790401459,
      "learning_rate": 1.328274484788967e-05,
      "loss": 0.5139,
      "step": 25683
    },
    {
      "epoch": 0.7889902620342211,
      "grad_norm": 0.4124489724636078,
      "learning_rate": 1.3282288348802158e-05,
      "loss": 0.6384,
      "step": 25684
    },
    {
      "epoch": 0.7890209811691703,
      "grad_norm": 0.40197429060935974,
      "learning_rate": 1.328183184204863e-05,
      "loss": 0.6033,
      "step": 25685
    },
    {
      "epoch": 0.7890517003041194,
      "grad_norm": 0.354043573141098,
      "learning_rate": 1.3281375327630155e-05,
      "loss": 0.5751,
      "step": 25686
    },
    {
      "epoch": 0.7890824194390686,
      "grad_norm": 0.37822332978248596,
      "learning_rate": 1.3280918805547797e-05,
      "loss": 0.5161,
      "step": 25687
    },
    {
      "epoch": 0.7891131385740178,
      "grad_norm": 0.38954412937164307,
      "learning_rate": 1.3280462275802629e-05,
      "loss": 0.535,
      "step": 25688
    },
    {
      "epoch": 0.7891438577089669,
      "grad_norm": 0.3428371846675873,
      "learning_rate": 1.3280005738395707e-05,
      "loss": 0.6032,
      "step": 25689
    },
    {
      "epoch": 0.7891745768439161,
      "grad_norm": 0.5000455975532532,
      "learning_rate": 1.3279549193328106e-05,
      "loss": 0.5393,
      "step": 25690
    },
    {
      "epoch": 0.7892052959788652,
      "grad_norm": 0.35214370489120483,
      "learning_rate": 1.3279092640600885e-05,
      "loss": 0.5841,
      "step": 25691
    },
    {
      "epoch": 0.7892360151138144,
      "grad_norm": 0.4078379273414612,
      "learning_rate": 1.3278636080215117e-05,
      "loss": 0.5308,
      "step": 25692
    },
    {
      "epoch": 0.7892667342487636,
      "grad_norm": 0.39192599058151245,
      "learning_rate": 1.3278179512171865e-05,
      "loss": 0.5735,
      "step": 25693
    },
    {
      "epoch": 0.7892974533837127,
      "grad_norm": 0.5683619976043701,
      "learning_rate": 1.3277722936472195e-05,
      "loss": 0.5356,
      "step": 25694
    },
    {
      "epoch": 0.7893281725186618,
      "grad_norm": 0.39576098322868347,
      "learning_rate": 1.3277266353117174e-05,
      "loss": 0.597,
      "step": 25695
    },
    {
      "epoch": 0.7893588916536111,
      "grad_norm": 0.5175675749778748,
      "learning_rate": 1.327680976210787e-05,
      "loss": 0.5486,
      "step": 25696
    },
    {
      "epoch": 0.7893896107885602,
      "grad_norm": 0.41663670539855957,
      "learning_rate": 1.3276353163445346e-05,
      "loss": 0.6124,
      "step": 25697
    },
    {
      "epoch": 0.7894203299235093,
      "grad_norm": 0.3682381808757782,
      "learning_rate": 1.3275896557130671e-05,
      "loss": 0.5381,
      "step": 25698
    },
    {
      "epoch": 0.7894510490584585,
      "grad_norm": 0.3717355728149414,
      "learning_rate": 1.3275439943164914e-05,
      "loss": 0.5721,
      "step": 25699
    },
    {
      "epoch": 0.7894817681934077,
      "grad_norm": 0.39973074197769165,
      "learning_rate": 1.3274983321549136e-05,
      "loss": 0.5524,
      "step": 25700
    },
    {
      "epoch": 0.7895124873283569,
      "grad_norm": 0.37077632546424866,
      "learning_rate": 1.3274526692284404e-05,
      "loss": 0.558,
      "step": 25701
    },
    {
      "epoch": 0.789543206463306,
      "grad_norm": 0.32797327637672424,
      "learning_rate": 1.3274070055371789e-05,
      "loss": 0.5279,
      "step": 25702
    },
    {
      "epoch": 0.7895739255982551,
      "grad_norm": 0.36330369114875793,
      "learning_rate": 1.3273613410812352e-05,
      "loss": 0.57,
      "step": 25703
    },
    {
      "epoch": 0.7896046447332044,
      "grad_norm": 0.3982851505279541,
      "learning_rate": 1.3273156758607165e-05,
      "loss": 0.5124,
      "step": 25704
    },
    {
      "epoch": 0.7896353638681535,
      "grad_norm": 0.3433174192905426,
      "learning_rate": 1.3272700098757292e-05,
      "loss": 0.5569,
      "step": 25705
    },
    {
      "epoch": 0.7896660830031026,
      "grad_norm": 0.5805022120475769,
      "learning_rate": 1.3272243431263797e-05,
      "loss": 0.5159,
      "step": 25706
    },
    {
      "epoch": 0.7896968021380518,
      "grad_norm": 0.3628769814968109,
      "learning_rate": 1.3271786756127749e-05,
      "loss": 0.5532,
      "step": 25707
    },
    {
      "epoch": 0.7897275212730009,
      "grad_norm": 0.437651127576828,
      "learning_rate": 1.3271330073350216e-05,
      "loss": 0.5841,
      "step": 25708
    },
    {
      "epoch": 0.7897582404079501,
      "grad_norm": 0.3609328269958496,
      "learning_rate": 1.3270873382932262e-05,
      "loss": 0.5224,
      "step": 25709
    },
    {
      "epoch": 0.7897889595428993,
      "grad_norm": 0.39422059059143066,
      "learning_rate": 1.3270416684874954e-05,
      "loss": 0.5222,
      "step": 25710
    },
    {
      "epoch": 0.7898196786778484,
      "grad_norm": 0.35076776146888733,
      "learning_rate": 1.3269959979179362e-05,
      "loss": 0.5892,
      "step": 25711
    },
    {
      "epoch": 0.7898503978127976,
      "grad_norm": 0.37264102697372437,
      "learning_rate": 1.3269503265846548e-05,
      "loss": 0.5012,
      "step": 25712
    },
    {
      "epoch": 0.7898811169477468,
      "grad_norm": 0.33443158864974976,
      "learning_rate": 1.3269046544877581e-05,
      "loss": 0.4609,
      "step": 25713
    },
    {
      "epoch": 0.7899118360826959,
      "grad_norm": 0.35535380244255066,
      "learning_rate": 1.3268589816273529e-05,
      "loss": 0.5216,
      "step": 25714
    },
    {
      "epoch": 0.7899425552176451,
      "grad_norm": 0.32718202471733093,
      "learning_rate": 1.3268133080035455e-05,
      "loss": 0.4343,
      "step": 25715
    },
    {
      "epoch": 0.7899732743525942,
      "grad_norm": 0.4873031675815582,
      "learning_rate": 1.326767633616443e-05,
      "loss": 0.5398,
      "step": 25716
    },
    {
      "epoch": 0.7900039934875434,
      "grad_norm": 1.0549070835113525,
      "learning_rate": 1.3267219584661515e-05,
      "loss": 0.6101,
      "step": 25717
    },
    {
      "epoch": 0.7900347126224926,
      "grad_norm": 0.4245976507663727,
      "learning_rate": 1.3266762825527786e-05,
      "loss": 0.5209,
      "step": 25718
    },
    {
      "epoch": 0.7900654317574417,
      "grad_norm": 0.3408292531967163,
      "learning_rate": 1.32663060587643e-05,
      "loss": 0.5389,
      "step": 25719
    },
    {
      "epoch": 0.7900961508923908,
      "grad_norm": 0.3595948815345764,
      "learning_rate": 1.326584928437213e-05,
      "loss": 0.5231,
      "step": 25720
    },
    {
      "epoch": 0.7901268700273401,
      "grad_norm": 0.37688174843788147,
      "learning_rate": 1.326539250235234e-05,
      "loss": 0.4399,
      "step": 25721
    },
    {
      "epoch": 0.7901575891622892,
      "grad_norm": 0.45100268721580505,
      "learning_rate": 1.3264935712706e-05,
      "loss": 0.54,
      "step": 25722
    },
    {
      "epoch": 0.7901883082972383,
      "grad_norm": 0.39235901832580566,
      "learning_rate": 1.3264478915434174e-05,
      "loss": 0.5067,
      "step": 25723
    },
    {
      "epoch": 0.7902190274321875,
      "grad_norm": 0.3500441312789917,
      "learning_rate": 1.3264022110537926e-05,
      "loss": 0.5207,
      "step": 25724
    },
    {
      "epoch": 0.7902497465671366,
      "grad_norm": 0.3739815950393677,
      "learning_rate": 1.3263565298018331e-05,
      "loss": 0.5692,
      "step": 25725
    },
    {
      "epoch": 0.7902804657020859,
      "grad_norm": 0.33621975779533386,
      "learning_rate": 1.326310847787645e-05,
      "loss": 0.5457,
      "step": 25726
    },
    {
      "epoch": 0.790311184837035,
      "grad_norm": 0.3923107385635376,
      "learning_rate": 1.3262651650113349e-05,
      "loss": 0.5466,
      "step": 25727
    },
    {
      "epoch": 0.7903419039719841,
      "grad_norm": 0.3825068175792694,
      "learning_rate": 1.3262194814730099e-05,
      "loss": 0.5081,
      "step": 25728
    },
    {
      "epoch": 0.7903726231069333,
      "grad_norm": 0.4155884087085724,
      "learning_rate": 1.3261737971727766e-05,
      "loss": 0.5324,
      "step": 25729
    },
    {
      "epoch": 0.7904033422418825,
      "grad_norm": 0.38793569803237915,
      "learning_rate": 1.3261281121107415e-05,
      "loss": 0.6692,
      "step": 25730
    },
    {
      "epoch": 0.7904340613768316,
      "grad_norm": 0.551550030708313,
      "learning_rate": 1.3260824262870113e-05,
      "loss": 0.5863,
      "step": 25731
    },
    {
      "epoch": 0.7904647805117808,
      "grad_norm": 0.3852141499519348,
      "learning_rate": 1.3260367397016928e-05,
      "loss": 0.5807,
      "step": 25732
    },
    {
      "epoch": 0.7904954996467299,
      "grad_norm": 0.3602704703807831,
      "learning_rate": 1.3259910523548929e-05,
      "loss": 0.5963,
      "step": 25733
    },
    {
      "epoch": 0.7905262187816791,
      "grad_norm": 0.34892114996910095,
      "learning_rate": 1.3259453642467181e-05,
      "loss": 0.5612,
      "step": 25734
    },
    {
      "epoch": 0.7905569379166283,
      "grad_norm": 0.35050442814826965,
      "learning_rate": 1.325899675377275e-05,
      "loss": 0.6125,
      "step": 25735
    },
    {
      "epoch": 0.7905876570515774,
      "grad_norm": 0.4609145224094391,
      "learning_rate": 1.3258539857466708e-05,
      "loss": 0.5933,
      "step": 25736
    },
    {
      "epoch": 0.7906183761865266,
      "grad_norm": 0.4693754315376282,
      "learning_rate": 1.3258082953550115e-05,
      "loss": 0.5888,
      "step": 25737
    },
    {
      "epoch": 0.7906490953214758,
      "grad_norm": 0.3798951506614685,
      "learning_rate": 1.3257626042024043e-05,
      "loss": 0.5383,
      "step": 25738
    },
    {
      "epoch": 0.7906798144564249,
      "grad_norm": 0.3959641754627228,
      "learning_rate": 1.3257169122889559e-05,
      "loss": 0.5176,
      "step": 25739
    },
    {
      "epoch": 0.7907105335913741,
      "grad_norm": 0.4093362092971802,
      "learning_rate": 1.3256712196147727e-05,
      "loss": 0.5824,
      "step": 25740
    },
    {
      "epoch": 0.7907412527263232,
      "grad_norm": 0.41426965594291687,
      "learning_rate": 1.325625526179962e-05,
      "loss": 0.532,
      "step": 25741
    },
    {
      "epoch": 0.7907719718612723,
      "grad_norm": 0.3576471507549286,
      "learning_rate": 1.3255798319846296e-05,
      "loss": 0.5223,
      "step": 25742
    },
    {
      "epoch": 0.7908026909962216,
      "grad_norm": 0.34835365414619446,
      "learning_rate": 1.3255341370288832e-05,
      "loss": 0.4967,
      "step": 25743
    },
    {
      "epoch": 0.7908334101311707,
      "grad_norm": 0.36119282245635986,
      "learning_rate": 1.3254884413128289e-05,
      "loss": 0.4606,
      "step": 25744
    },
    {
      "epoch": 0.7908641292661198,
      "grad_norm": 0.3695414662361145,
      "learning_rate": 1.3254427448365737e-05,
      "loss": 0.4368,
      "step": 25745
    },
    {
      "epoch": 0.790894848401069,
      "grad_norm": 0.35363277792930603,
      "learning_rate": 1.325397047600224e-05,
      "loss": 0.4992,
      "step": 25746
    },
    {
      "epoch": 0.7909255675360182,
      "grad_norm": 0.3889347016811371,
      "learning_rate": 1.3253513496038872e-05,
      "loss": 0.5834,
      "step": 25747
    },
    {
      "epoch": 0.7909562866709673,
      "grad_norm": 0.35414406657218933,
      "learning_rate": 1.3253056508476692e-05,
      "loss": 0.5022,
      "step": 25748
    },
    {
      "epoch": 0.7909870058059165,
      "grad_norm": 0.392501562833786,
      "learning_rate": 1.3252599513316774e-05,
      "loss": 0.4581,
      "step": 25749
    },
    {
      "epoch": 0.7910177249408656,
      "grad_norm": 0.3868059515953064,
      "learning_rate": 1.325214251056018e-05,
      "loss": 0.5468,
      "step": 25750
    },
    {
      "epoch": 0.7910484440758149,
      "grad_norm": 0.3780817985534668,
      "learning_rate": 1.3251685500207983e-05,
      "loss": 0.4762,
      "step": 25751
    },
    {
      "epoch": 0.791079163210764,
      "grad_norm": 0.37030836939811707,
      "learning_rate": 1.3251228482261245e-05,
      "loss": 0.5527,
      "step": 25752
    },
    {
      "epoch": 0.7911098823457131,
      "grad_norm": 0.3759697377681732,
      "learning_rate": 1.3250771456721035e-05,
      "loss": 0.6467,
      "step": 25753
    },
    {
      "epoch": 0.7911406014806623,
      "grad_norm": 0.3712805509567261,
      "learning_rate": 1.3250314423588425e-05,
      "loss": 0.5707,
      "step": 25754
    },
    {
      "epoch": 0.7911713206156115,
      "grad_norm": 0.37761417031288147,
      "learning_rate": 1.3249857382864475e-05,
      "loss": 0.62,
      "step": 25755
    },
    {
      "epoch": 0.7912020397505606,
      "grad_norm": 0.36121633648872375,
      "learning_rate": 1.3249400334550257e-05,
      "loss": 0.4944,
      "step": 25756
    },
    {
      "epoch": 0.7912327588855098,
      "grad_norm": 0.364177405834198,
      "learning_rate": 1.324894327864684e-05,
      "loss": 0.5036,
      "step": 25757
    },
    {
      "epoch": 0.7912634780204589,
      "grad_norm": 0.4014582633972168,
      "learning_rate": 1.3248486215155286e-05,
      "loss": 0.4842,
      "step": 25758
    },
    {
      "epoch": 0.791294197155408,
      "grad_norm": 0.3554246127605438,
      "learning_rate": 1.3248029144076669e-05,
      "loss": 0.536,
      "step": 25759
    },
    {
      "epoch": 0.7913249162903573,
      "grad_norm": 0.3712151050567627,
      "learning_rate": 1.3247572065412048e-05,
      "loss": 0.6394,
      "step": 25760
    },
    {
      "epoch": 0.7913556354253064,
      "grad_norm": 0.3768034279346466,
      "learning_rate": 1.3247114979162502e-05,
      "loss": 0.5661,
      "step": 25761
    },
    {
      "epoch": 0.7913863545602556,
      "grad_norm": 0.3731251358985901,
      "learning_rate": 1.3246657885329088e-05,
      "loss": 0.5934,
      "step": 25762
    },
    {
      "epoch": 0.7914170736952048,
      "grad_norm": 0.36354610323905945,
      "learning_rate": 1.3246200783912879e-05,
      "loss": 0.6468,
      "step": 25763
    },
    {
      "epoch": 0.7914477928301539,
      "grad_norm": 0.35715755820274353,
      "learning_rate": 1.324574367491494e-05,
      "loss": 0.5824,
      "step": 25764
    },
    {
      "epoch": 0.7914785119651031,
      "grad_norm": 0.33757272362709045,
      "learning_rate": 1.3245286558336341e-05,
      "loss": 0.4847,
      "step": 25765
    },
    {
      "epoch": 0.7915092311000522,
      "grad_norm": 0.34051695466041565,
      "learning_rate": 1.3244829434178148e-05,
      "loss": 0.5242,
      "step": 25766
    },
    {
      "epoch": 0.7915399502350013,
      "grad_norm": 0.40342119336128235,
      "learning_rate": 1.324437230244143e-05,
      "loss": 0.5896,
      "step": 25767
    },
    {
      "epoch": 0.7915706693699506,
      "grad_norm": 0.35796675086021423,
      "learning_rate": 1.3243915163127254e-05,
      "loss": 0.5204,
      "step": 25768
    },
    {
      "epoch": 0.7916013885048997,
      "grad_norm": 0.32412853837013245,
      "learning_rate": 1.3243458016236688e-05,
      "loss": 0.566,
      "step": 25769
    },
    {
      "epoch": 0.7916321076398488,
      "grad_norm": 0.3665205240249634,
      "learning_rate": 1.3243000861770799e-05,
      "loss": 0.5088,
      "step": 25770
    },
    {
      "epoch": 0.791662826774798,
      "grad_norm": 0.3635343015193939,
      "learning_rate": 1.3242543699730652e-05,
      "loss": 0.5856,
      "step": 25771
    },
    {
      "epoch": 0.7916935459097472,
      "grad_norm": 0.5605050325393677,
      "learning_rate": 1.3242086530117322e-05,
      "loss": 0.5953,
      "step": 25772
    },
    {
      "epoch": 0.7917242650446964,
      "grad_norm": 0.3521329164505005,
      "learning_rate": 1.3241629352931868e-05,
      "loss": 0.5163,
      "step": 25773
    },
    {
      "epoch": 0.7917549841796455,
      "grad_norm": 0.3583928942680359,
      "learning_rate": 1.3241172168175367e-05,
      "loss": 0.5724,
      "step": 25774
    },
    {
      "epoch": 0.7917857033145946,
      "grad_norm": 0.389596551656723,
      "learning_rate": 1.3240714975848881e-05,
      "loss": 0.5748,
      "step": 25775
    },
    {
      "epoch": 0.7918164224495439,
      "grad_norm": 0.3750671148300171,
      "learning_rate": 1.3240257775953478e-05,
      "loss": 0.6031,
      "step": 25776
    },
    {
      "epoch": 0.791847141584493,
      "grad_norm": 0.3380883038043976,
      "learning_rate": 1.3239800568490226e-05,
      "loss": 0.5337,
      "step": 25777
    },
    {
      "epoch": 0.7918778607194421,
      "grad_norm": 0.4212368428707123,
      "learning_rate": 1.3239343353460194e-05,
      "loss": 0.5117,
      "step": 25778
    },
    {
      "epoch": 0.7919085798543913,
      "grad_norm": 0.37040096521377563,
      "learning_rate": 1.323888613086445e-05,
      "loss": 0.5522,
      "step": 25779
    },
    {
      "epoch": 0.7919392989893405,
      "grad_norm": 0.40121498703956604,
      "learning_rate": 1.3238428900704058e-05,
      "loss": 0.5291,
      "step": 25780
    },
    {
      "epoch": 0.7919700181242896,
      "grad_norm": 0.4006633162498474,
      "learning_rate": 1.3237971662980096e-05,
      "loss": 0.5585,
      "step": 25781
    },
    {
      "epoch": 0.7920007372592388,
      "grad_norm": 0.441283643245697,
      "learning_rate": 1.3237514417693618e-05,
      "loss": 0.4688,
      "step": 25782
    },
    {
      "epoch": 0.7920314563941879,
      "grad_norm": 0.3466672897338867,
      "learning_rate": 1.3237057164845703e-05,
      "loss": 0.5098,
      "step": 25783
    },
    {
      "epoch": 0.792062175529137,
      "grad_norm": 0.3659134805202484,
      "learning_rate": 1.3236599904437412e-05,
      "loss": 0.5358,
      "step": 25784
    },
    {
      "epoch": 0.7920928946640863,
      "grad_norm": 0.3746253252029419,
      "learning_rate": 1.323614263646982e-05,
      "loss": 0.6053,
      "step": 25785
    },
    {
      "epoch": 0.7921236137990354,
      "grad_norm": 0.40822792053222656,
      "learning_rate": 1.323568536094399e-05,
      "loss": 0.4377,
      "step": 25786
    },
    {
      "epoch": 0.7921543329339846,
      "grad_norm": 0.3702104389667511,
      "learning_rate": 1.3235228077860986e-05,
      "loss": 0.476,
      "step": 25787
    },
    {
      "epoch": 0.7921850520689337,
      "grad_norm": 0.44354337453842163,
      "learning_rate": 1.3234770787221884e-05,
      "loss": 0.5691,
      "step": 25788
    },
    {
      "epoch": 0.7922157712038829,
      "grad_norm": 0.36377689242362976,
      "learning_rate": 1.323431348902775e-05,
      "loss": 0.5475,
      "step": 25789
    },
    {
      "epoch": 0.7922464903388321,
      "grad_norm": 0.477884441614151,
      "learning_rate": 1.323385618327965e-05,
      "loss": 0.5385,
      "step": 25790
    },
    {
      "epoch": 0.7922772094737812,
      "grad_norm": 0.34985437989234924,
      "learning_rate": 1.3233398869978654e-05,
      "loss": 0.4797,
      "step": 25791
    },
    {
      "epoch": 0.7923079286087303,
      "grad_norm": 0.3667285442352295,
      "learning_rate": 1.3232941549125829e-05,
      "loss": 0.5403,
      "step": 25792
    },
    {
      "epoch": 0.7923386477436796,
      "grad_norm": 0.3726455271244049,
      "learning_rate": 1.3232484220722241e-05,
      "loss": 0.5188,
      "step": 25793
    },
    {
      "epoch": 0.7923693668786287,
      "grad_norm": 0.36684057116508484,
      "learning_rate": 1.3232026884768962e-05,
      "loss": 0.5665,
      "step": 25794
    },
    {
      "epoch": 0.7924000860135778,
      "grad_norm": 0.33736908435821533,
      "learning_rate": 1.323156954126706e-05,
      "loss": 0.5464,
      "step": 25795
    },
    {
      "epoch": 0.792430805148527,
      "grad_norm": 0.32632485032081604,
      "learning_rate": 1.3231112190217598e-05,
      "loss": 0.5839,
      "step": 25796
    },
    {
      "epoch": 0.7924615242834762,
      "grad_norm": 0.359298437833786,
      "learning_rate": 1.3230654831621651e-05,
      "loss": 0.4757,
      "step": 25797
    },
    {
      "epoch": 0.7924922434184254,
      "grad_norm": 0.4403110444545746,
      "learning_rate": 1.323019746548028e-05,
      "loss": 0.5741,
      "step": 25798
    },
    {
      "epoch": 0.7925229625533745,
      "grad_norm": 0.33675453066825867,
      "learning_rate": 1.3229740091794562e-05,
      "loss": 0.4781,
      "step": 25799
    },
    {
      "epoch": 0.7925536816883236,
      "grad_norm": 0.39627501368522644,
      "learning_rate": 1.3229282710565558e-05,
      "loss": 0.5577,
      "step": 25800
    },
    {
      "epoch": 0.7925844008232729,
      "grad_norm": 0.3867175877094269,
      "learning_rate": 1.322882532179434e-05,
      "loss": 0.6455,
      "step": 25801
    },
    {
      "epoch": 0.792615119958222,
      "grad_norm": 0.3626076877117157,
      "learning_rate": 1.3228367925481976e-05,
      "loss": 0.5679,
      "step": 25802
    },
    {
      "epoch": 0.7926458390931711,
      "grad_norm": 0.3795565962791443,
      "learning_rate": 1.322791052162953e-05,
      "loss": 0.5153,
      "step": 25803
    },
    {
      "epoch": 0.7926765582281203,
      "grad_norm": 0.3664473593235016,
      "learning_rate": 1.3227453110238075e-05,
      "loss": 0.635,
      "step": 25804
    },
    {
      "epoch": 0.7927072773630695,
      "grad_norm": 0.3738345801830292,
      "learning_rate": 1.322699569130868e-05,
      "loss": 0.5548,
      "step": 25805
    },
    {
      "epoch": 0.7927379964980186,
      "grad_norm": 0.3252347409725189,
      "learning_rate": 1.3226538264842405e-05,
      "loss": 0.4367,
      "step": 25806
    },
    {
      "epoch": 0.7927687156329678,
      "grad_norm": 0.3404231667518616,
      "learning_rate": 1.3226080830840329e-05,
      "loss": 0.5742,
      "step": 25807
    },
    {
      "epoch": 0.7927994347679169,
      "grad_norm": 0.40306469798088074,
      "learning_rate": 1.3225623389303517e-05,
      "loss": 0.4877,
      "step": 25808
    },
    {
      "epoch": 0.792830153902866,
      "grad_norm": 0.4006347954273224,
      "learning_rate": 1.3225165940233034e-05,
      "loss": 0.6347,
      "step": 25809
    },
    {
      "epoch": 0.7928608730378153,
      "grad_norm": 0.3108697533607483,
      "learning_rate": 1.322470848362995e-05,
      "loss": 0.5192,
      "step": 25810
    },
    {
      "epoch": 0.7928915921727644,
      "grad_norm": 0.3681524395942688,
      "learning_rate": 1.3224251019495338e-05,
      "loss": 0.6011,
      "step": 25811
    },
    {
      "epoch": 0.7929223113077136,
      "grad_norm": 0.4632471799850464,
      "learning_rate": 1.3223793547830259e-05,
      "loss": 0.5304,
      "step": 25812
    },
    {
      "epoch": 0.7929530304426627,
      "grad_norm": 0.38758862018585205,
      "learning_rate": 1.3223336068635786e-05,
      "loss": 0.5394,
      "step": 25813
    },
    {
      "epoch": 0.7929837495776119,
      "grad_norm": 0.3653997778892517,
      "learning_rate": 1.3222878581912988e-05,
      "loss": 0.5041,
      "step": 25814
    },
    {
      "epoch": 0.7930144687125611,
      "grad_norm": 0.36733362078666687,
      "learning_rate": 1.3222421087662931e-05,
      "loss": 0.5632,
      "step": 25815
    },
    {
      "epoch": 0.7930451878475102,
      "grad_norm": 0.34324222803115845,
      "learning_rate": 1.3221963585886681e-05,
      "loss": 0.5638,
      "step": 25816
    },
    {
      "epoch": 0.7930759069824593,
      "grad_norm": 0.40598562359809875,
      "learning_rate": 1.3221506076585316e-05,
      "loss": 0.5857,
      "step": 25817
    },
    {
      "epoch": 0.7931066261174086,
      "grad_norm": 0.3438378572463989,
      "learning_rate": 1.3221048559759894e-05,
      "loss": 0.5819,
      "step": 25818
    },
    {
      "epoch": 0.7931373452523577,
      "grad_norm": 0.32699480652809143,
      "learning_rate": 1.3220591035411492e-05,
      "loss": 0.5356,
      "step": 25819
    },
    {
      "epoch": 0.7931680643873068,
      "grad_norm": 0.39893078804016113,
      "learning_rate": 1.3220133503541171e-05,
      "loss": 0.5315,
      "step": 25820
    },
    {
      "epoch": 0.793198783522256,
      "grad_norm": 0.3583940267562866,
      "learning_rate": 1.3219675964150006e-05,
      "loss": 0.5902,
      "step": 25821
    },
    {
      "epoch": 0.7932295026572052,
      "grad_norm": 0.34539905190467834,
      "learning_rate": 1.3219218417239063e-05,
      "loss": 0.552,
      "step": 25822
    },
    {
      "epoch": 0.7932602217921544,
      "grad_norm": 0.3656444251537323,
      "learning_rate": 1.3218760862809407e-05,
      "loss": 0.5045,
      "step": 25823
    },
    {
      "epoch": 0.7932909409271035,
      "grad_norm": 0.3478304445743561,
      "learning_rate": 1.3218303300862115e-05,
      "loss": 0.5424,
      "step": 25824
    },
    {
      "epoch": 0.7933216600620526,
      "grad_norm": 0.41325902938842773,
      "learning_rate": 1.3217845731398244e-05,
      "loss": 0.6544,
      "step": 25825
    },
    {
      "epoch": 0.7933523791970019,
      "grad_norm": 0.35479438304901123,
      "learning_rate": 1.3217388154418877e-05,
      "loss": 0.5674,
      "step": 25826
    },
    {
      "epoch": 0.793383098331951,
      "grad_norm": 0.48120903968811035,
      "learning_rate": 1.3216930569925072e-05,
      "loss": 0.5562,
      "step": 25827
    },
    {
      "epoch": 0.7934138174669001,
      "grad_norm": 0.3582687973976135,
      "learning_rate": 1.3216472977917901e-05,
      "loss": 0.5696,
      "step": 25828
    },
    {
      "epoch": 0.7934445366018493,
      "grad_norm": 0.3155936300754547,
      "learning_rate": 1.3216015378398435e-05,
      "loss": 0.4876,
      "step": 25829
    },
    {
      "epoch": 0.7934752557367984,
      "grad_norm": 0.3492187559604645,
      "learning_rate": 1.3215557771367738e-05,
      "loss": 0.58,
      "step": 25830
    },
    {
      "epoch": 0.7935059748717476,
      "grad_norm": 0.36287569999694824,
      "learning_rate": 1.3215100156826881e-05,
      "loss": 0.4786,
      "step": 25831
    },
    {
      "epoch": 0.7935366940066968,
      "grad_norm": 0.3723464012145996,
      "learning_rate": 1.3214642534776933e-05,
      "loss": 0.5879,
      "step": 25832
    },
    {
      "epoch": 0.7935674131416459,
      "grad_norm": 0.36767345666885376,
      "learning_rate": 1.3214184905218965e-05,
      "loss": 0.5485,
      "step": 25833
    },
    {
      "epoch": 0.793598132276595,
      "grad_norm": 0.3693479895591736,
      "learning_rate": 1.3213727268154042e-05,
      "loss": 0.5334,
      "step": 25834
    },
    {
      "epoch": 0.7936288514115443,
      "grad_norm": 0.34294751286506653,
      "learning_rate": 1.3213269623583233e-05,
      "loss": 0.5726,
      "step": 25835
    },
    {
      "epoch": 0.7936595705464934,
      "grad_norm": 0.3199531137943268,
      "learning_rate": 1.321281197150761e-05,
      "loss": 0.5757,
      "step": 25836
    },
    {
      "epoch": 0.7936902896814426,
      "grad_norm": 0.3703114986419678,
      "learning_rate": 1.3212354311928245e-05,
      "loss": 0.5612,
      "step": 25837
    },
    {
      "epoch": 0.7937210088163917,
      "grad_norm": 0.36325645446777344,
      "learning_rate": 1.3211896644846197e-05,
      "loss": 0.5201,
      "step": 25838
    },
    {
      "epoch": 0.7937517279513409,
      "grad_norm": 0.3574269413948059,
      "learning_rate": 1.321143897026254e-05,
      "loss": 0.5289,
      "step": 25839
    },
    {
      "epoch": 0.7937824470862901,
      "grad_norm": 0.395268976688385,
      "learning_rate": 1.3210981288178345e-05,
      "loss": 0.5009,
      "step": 25840
    },
    {
      "epoch": 0.7938131662212392,
      "grad_norm": 0.3448356091976166,
      "learning_rate": 1.3210523598594675e-05,
      "loss": 0.4567,
      "step": 25841
    },
    {
      "epoch": 0.7938438853561883,
      "grad_norm": 0.4270251393318176,
      "learning_rate": 1.3210065901512607e-05,
      "loss": 0.6268,
      "step": 25842
    },
    {
      "epoch": 0.7938746044911376,
      "grad_norm": 0.3678332567214966,
      "learning_rate": 1.3209608196933202e-05,
      "loss": 0.5621,
      "step": 25843
    },
    {
      "epoch": 0.7939053236260867,
      "grad_norm": 0.39322003722190857,
      "learning_rate": 1.3209150484857536e-05,
      "loss": 0.5349,
      "step": 25844
    },
    {
      "epoch": 0.7939360427610358,
      "grad_norm": 0.3558408319950104,
      "learning_rate": 1.3208692765286674e-05,
      "loss": 0.6106,
      "step": 25845
    },
    {
      "epoch": 0.793966761895985,
      "grad_norm": 0.38039734959602356,
      "learning_rate": 1.3208235038221687e-05,
      "loss": 0.5281,
      "step": 25846
    },
    {
      "epoch": 0.7939974810309341,
      "grad_norm": 0.34674689173698425,
      "learning_rate": 1.3207777303663642e-05,
      "loss": 0.5728,
      "step": 25847
    },
    {
      "epoch": 0.7940282001658834,
      "grad_norm": 0.39170360565185547,
      "learning_rate": 1.3207319561613607e-05,
      "loss": 0.5011,
      "step": 25848
    },
    {
      "epoch": 0.7940589193008325,
      "grad_norm": 0.345059871673584,
      "learning_rate": 1.3206861812072657e-05,
      "loss": 0.6412,
      "step": 25849
    },
    {
      "epoch": 0.7940896384357816,
      "grad_norm": 0.3976093828678131,
      "learning_rate": 1.3206404055041855e-05,
      "loss": 0.6255,
      "step": 25850
    },
    {
      "epoch": 0.7941203575707309,
      "grad_norm": 0.3727046251296997,
      "learning_rate": 1.3205946290522276e-05,
      "loss": 0.5899,
      "step": 25851
    },
    {
      "epoch": 0.79415107670568,
      "grad_norm": 0.38945960998535156,
      "learning_rate": 1.320548851851498e-05,
      "loss": 0.4975,
      "step": 25852
    },
    {
      "epoch": 0.7941817958406291,
      "grad_norm": 0.39285561442375183,
      "learning_rate": 1.3205030739021046e-05,
      "loss": 0.519,
      "step": 25853
    },
    {
      "epoch": 0.7942125149755783,
      "grad_norm": 0.3303069472312927,
      "learning_rate": 1.3204572952041537e-05,
      "loss": 0.5136,
      "step": 25854
    },
    {
      "epoch": 0.7942432341105274,
      "grad_norm": 0.37648889422416687,
      "learning_rate": 1.3204115157577526e-05,
      "loss": 0.5636,
      "step": 25855
    },
    {
      "epoch": 0.7942739532454766,
      "grad_norm": 0.4016236960887909,
      "learning_rate": 1.3203657355630077e-05,
      "loss": 0.602,
      "step": 25856
    },
    {
      "epoch": 0.7943046723804258,
      "grad_norm": 0.40242651104927063,
      "learning_rate": 1.3203199546200265e-05,
      "loss": 0.5425,
      "step": 25857
    },
    {
      "epoch": 0.7943353915153749,
      "grad_norm": 0.3945392668247223,
      "learning_rate": 1.3202741729289157e-05,
      "loss": 0.519,
      "step": 25858
    },
    {
      "epoch": 0.7943661106503241,
      "grad_norm": 0.39229291677474976,
      "learning_rate": 1.320228390489782e-05,
      "loss": 0.5966,
      "step": 25859
    },
    {
      "epoch": 0.7943968297852733,
      "grad_norm": 0.34062322974205017,
      "learning_rate": 1.3201826073027326e-05,
      "loss": 0.4611,
      "step": 25860
    },
    {
      "epoch": 0.7944275489202224,
      "grad_norm": 0.3792220652103424,
      "learning_rate": 1.3201368233678743e-05,
      "loss": 0.4805,
      "step": 25861
    },
    {
      "epoch": 0.7944582680551716,
      "grad_norm": 0.34507840871810913,
      "learning_rate": 1.320091038685314e-05,
      "loss": 0.5377,
      "step": 25862
    },
    {
      "epoch": 0.7944889871901207,
      "grad_norm": 0.3438222110271454,
      "learning_rate": 1.3200452532551592e-05,
      "loss": 0.5447,
      "step": 25863
    },
    {
      "epoch": 0.7945197063250699,
      "grad_norm": 0.39573249220848083,
      "learning_rate": 1.3199994670775158e-05,
      "loss": 0.5694,
      "step": 25864
    },
    {
      "epoch": 0.7945504254600191,
      "grad_norm": 0.35836952924728394,
      "learning_rate": 1.3199536801524918e-05,
      "loss": 0.5106,
      "step": 25865
    },
    {
      "epoch": 0.7945811445949682,
      "grad_norm": 0.3538137376308441,
      "learning_rate": 1.319907892480193e-05,
      "loss": 0.5042,
      "step": 25866
    },
    {
      "epoch": 0.7946118637299173,
      "grad_norm": 0.41393041610717773,
      "learning_rate": 1.3198621040607276e-05,
      "loss": 0.6169,
      "step": 25867
    },
    {
      "epoch": 0.7946425828648666,
      "grad_norm": 0.8836017847061157,
      "learning_rate": 1.3198163148942017e-05,
      "loss": 0.5839,
      "step": 25868
    },
    {
      "epoch": 0.7946733019998157,
      "grad_norm": 0.35661768913269043,
      "learning_rate": 1.3197705249807224e-05,
      "loss": 0.5868,
      "step": 25869
    },
    {
      "epoch": 0.7947040211347648,
      "grad_norm": 0.35603585839271545,
      "learning_rate": 1.3197247343203967e-05,
      "loss": 0.47,
      "step": 25870
    },
    {
      "epoch": 0.794734740269714,
      "grad_norm": 0.3621756434440613,
      "learning_rate": 1.3196789429133317e-05,
      "loss": 0.5984,
      "step": 25871
    },
    {
      "epoch": 0.7947654594046631,
      "grad_norm": 0.3830057978630066,
      "learning_rate": 1.3196331507596341e-05,
      "loss": 0.6385,
      "step": 25872
    },
    {
      "epoch": 0.7947961785396124,
      "grad_norm": 0.3489990234375,
      "learning_rate": 1.319587357859411e-05,
      "loss": 0.5929,
      "step": 25873
    },
    {
      "epoch": 0.7948268976745615,
      "grad_norm": 0.3625670373439789,
      "learning_rate": 1.3195415642127693e-05,
      "loss": 0.6166,
      "step": 25874
    },
    {
      "epoch": 0.7948576168095106,
      "grad_norm": 0.8529596924781799,
      "learning_rate": 1.3194957698198158e-05,
      "loss": 0.5415,
      "step": 25875
    },
    {
      "epoch": 0.7948883359444598,
      "grad_norm": 0.39071017503738403,
      "learning_rate": 1.3194499746806577e-05,
      "loss": 0.4914,
      "step": 25876
    },
    {
      "epoch": 0.794919055079409,
      "grad_norm": 0.3501439392566681,
      "learning_rate": 1.319404178795402e-05,
      "loss": 0.5455,
      "step": 25877
    },
    {
      "epoch": 0.7949497742143581,
      "grad_norm": 0.36604151129722595,
      "learning_rate": 1.3193583821641556e-05,
      "loss": 0.5413,
      "step": 25878
    },
    {
      "epoch": 0.7949804933493073,
      "grad_norm": 0.44482243061065674,
      "learning_rate": 1.3193125847870252e-05,
      "loss": 0.5816,
      "step": 25879
    },
    {
      "epoch": 0.7950112124842564,
      "grad_norm": 0.334824800491333,
      "learning_rate": 1.3192667866641179e-05,
      "loss": 0.5343,
      "step": 25880
    },
    {
      "epoch": 0.7950419316192056,
      "grad_norm": 0.4012795388698578,
      "learning_rate": 1.3192209877955406e-05,
      "loss": 0.505,
      "step": 25881
    },
    {
      "epoch": 0.7950726507541548,
      "grad_norm": 0.37336716055870056,
      "learning_rate": 1.3191751881814008e-05,
      "loss": 0.5681,
      "step": 25882
    },
    {
      "epoch": 0.7951033698891039,
      "grad_norm": 0.39793428778648376,
      "learning_rate": 1.3191293878218049e-05,
      "loss": 0.5389,
      "step": 25883
    },
    {
      "epoch": 0.7951340890240531,
      "grad_norm": 0.4709588885307312,
      "learning_rate": 1.3190835867168599e-05,
      "loss": 0.4914,
      "step": 25884
    },
    {
      "epoch": 0.7951648081590023,
      "grad_norm": 0.3957739472389221,
      "learning_rate": 1.3190377848666728e-05,
      "loss": 0.6156,
      "step": 25885
    },
    {
      "epoch": 0.7951955272939514,
      "grad_norm": 0.648902177810669,
      "learning_rate": 1.318991982271351e-05,
      "loss": 0.54,
      "step": 25886
    },
    {
      "epoch": 0.7952262464289006,
      "grad_norm": 0.33387696743011475,
      "learning_rate": 1.3189461789310011e-05,
      "loss": 0.5741,
      "step": 25887
    },
    {
      "epoch": 0.7952569655638497,
      "grad_norm": 0.32171788811683655,
      "learning_rate": 1.31890037484573e-05,
      "loss": 0.5665,
      "step": 25888
    },
    {
      "epoch": 0.7952876846987988,
      "grad_norm": 0.3639090359210968,
      "learning_rate": 1.3188545700156447e-05,
      "loss": 0.4912,
      "step": 25889
    },
    {
      "epoch": 0.7953184038337481,
      "grad_norm": 0.36800283193588257,
      "learning_rate": 1.3188087644408527e-05,
      "loss": 0.4694,
      "step": 25890
    },
    {
      "epoch": 0.7953491229686972,
      "grad_norm": 0.35165005922317505,
      "learning_rate": 1.3187629581214601e-05,
      "loss": 0.53,
      "step": 25891
    },
    {
      "epoch": 0.7953798421036463,
      "grad_norm": 0.36563125252723694,
      "learning_rate": 1.3187171510575747e-05,
      "loss": 0.5528,
      "step": 25892
    },
    {
      "epoch": 0.7954105612385955,
      "grad_norm": 0.3461935520172119,
      "learning_rate": 1.3186713432493028e-05,
      "loss": 0.4923,
      "step": 25893
    },
    {
      "epoch": 0.7954412803735447,
      "grad_norm": 0.35816389322280884,
      "learning_rate": 1.318625534696752e-05,
      "loss": 0.5931,
      "step": 25894
    },
    {
      "epoch": 0.7954719995084938,
      "grad_norm": 0.5125569701194763,
      "learning_rate": 1.3185797254000288e-05,
      "loss": 0.5042,
      "step": 25895
    },
    {
      "epoch": 0.795502718643443,
      "grad_norm": 0.3476797044277191,
      "learning_rate": 1.3185339153592407e-05,
      "loss": 0.5541,
      "step": 25896
    },
    {
      "epoch": 0.7955334377783921,
      "grad_norm": 0.46420225501060486,
      "learning_rate": 1.3184881045744939e-05,
      "loss": 0.5535,
      "step": 25897
    },
    {
      "epoch": 0.7955641569133414,
      "grad_norm": 0.354490727186203,
      "learning_rate": 1.3184422930458963e-05,
      "loss": 0.5629,
      "step": 25898
    },
    {
      "epoch": 0.7955948760482905,
      "grad_norm": 0.3906576335430145,
      "learning_rate": 1.3183964807735542e-05,
      "loss": 0.6078,
      "step": 25899
    },
    {
      "epoch": 0.7956255951832396,
      "grad_norm": 0.40138643980026245,
      "learning_rate": 1.3183506677575752e-05,
      "loss": 0.4725,
      "step": 25900
    },
    {
      "epoch": 0.7956563143181888,
      "grad_norm": 0.3969191312789917,
      "learning_rate": 1.3183048539980658e-05,
      "loss": 0.5899,
      "step": 25901
    },
    {
      "epoch": 0.795687033453138,
      "grad_norm": 0.3644534945487976,
      "learning_rate": 1.3182590394951332e-05,
      "loss": 0.5621,
      "step": 25902
    },
    {
      "epoch": 0.7957177525880871,
      "grad_norm": 0.3749605119228363,
      "learning_rate": 1.3182132242488846e-05,
      "loss": 0.5198,
      "step": 25903
    },
    {
      "epoch": 0.7957484717230363,
      "grad_norm": 0.35019445419311523,
      "learning_rate": 1.3181674082594264e-05,
      "loss": 0.5607,
      "step": 25904
    },
    {
      "epoch": 0.7957791908579854,
      "grad_norm": 0.35686853528022766,
      "learning_rate": 1.3181215915268664e-05,
      "loss": 0.6409,
      "step": 25905
    },
    {
      "epoch": 0.7958099099929345,
      "grad_norm": 0.3461194634437561,
      "learning_rate": 1.3180757740513108e-05,
      "loss": 0.5445,
      "step": 25906
    },
    {
      "epoch": 0.7958406291278838,
      "grad_norm": 0.40002989768981934,
      "learning_rate": 1.3180299558328673e-05,
      "loss": 0.4958,
      "step": 25907
    },
    {
      "epoch": 0.7958713482628329,
      "grad_norm": 0.3387254476547241,
      "learning_rate": 1.3179841368716426e-05,
      "loss": 0.5379,
      "step": 25908
    },
    {
      "epoch": 0.7959020673977821,
      "grad_norm": 0.36108672618865967,
      "learning_rate": 1.3179383171677435e-05,
      "loss": 0.5326,
      "step": 25909
    },
    {
      "epoch": 0.7959327865327313,
      "grad_norm": 0.4868420958518982,
      "learning_rate": 1.3178924967212776e-05,
      "loss": 0.5795,
      "step": 25910
    },
    {
      "epoch": 0.7959635056676804,
      "grad_norm": 0.41119539737701416,
      "learning_rate": 1.3178466755323514e-05,
      "loss": 0.5419,
      "step": 25911
    },
    {
      "epoch": 0.7959942248026296,
      "grad_norm": 0.35152876377105713,
      "learning_rate": 1.3178008536010723e-05,
      "loss": 0.6099,
      "step": 25912
    },
    {
      "epoch": 0.7960249439375787,
      "grad_norm": 0.40046218037605286,
      "learning_rate": 1.3177550309275467e-05,
      "loss": 0.5164,
      "step": 25913
    },
    {
      "epoch": 0.7960556630725278,
      "grad_norm": 0.6004210710525513,
      "learning_rate": 1.3177092075118823e-05,
      "loss": 0.556,
      "step": 25914
    },
    {
      "epoch": 0.7960863822074771,
      "grad_norm": 0.31721651554107666,
      "learning_rate": 1.317663383354186e-05,
      "loss": 0.4676,
      "step": 25915
    },
    {
      "epoch": 0.7961171013424262,
      "grad_norm": 0.4093199074268341,
      "learning_rate": 1.317617558454564e-05,
      "loss": 0.5447,
      "step": 25916
    },
    {
      "epoch": 0.7961478204773753,
      "grad_norm": 0.37297341227531433,
      "learning_rate": 1.3175717328131248e-05,
      "loss": 0.5748,
      "step": 25917
    },
    {
      "epoch": 0.7961785396123245,
      "grad_norm": 0.4421272277832031,
      "learning_rate": 1.3175259064299742e-05,
      "loss": 0.6304,
      "step": 25918
    },
    {
      "epoch": 0.7962092587472737,
      "grad_norm": 0.3593054711818695,
      "learning_rate": 1.3174800793052198e-05,
      "loss": 0.5739,
      "step": 25919
    },
    {
      "epoch": 0.7962399778822228,
      "grad_norm": 0.35300108790397644,
      "learning_rate": 1.3174342514389684e-05,
      "loss": 0.514,
      "step": 25920
    },
    {
      "epoch": 0.796270697017172,
      "grad_norm": 0.3637191951274872,
      "learning_rate": 1.3173884228313274e-05,
      "loss": 0.5216,
      "step": 25921
    },
    {
      "epoch": 0.7963014161521211,
      "grad_norm": 0.373343825340271,
      "learning_rate": 1.3173425934824033e-05,
      "loss": 0.5721,
      "step": 25922
    },
    {
      "epoch": 0.7963321352870704,
      "grad_norm": 0.405061811208725,
      "learning_rate": 1.3172967633923038e-05,
      "loss": 0.5421,
      "step": 25923
    },
    {
      "epoch": 0.7963628544220195,
      "grad_norm": 0.35237690806388855,
      "learning_rate": 1.3172509325611351e-05,
      "loss": 0.5633,
      "step": 25924
    },
    {
      "epoch": 0.7963935735569686,
      "grad_norm": 0.3478228747844696,
      "learning_rate": 1.3172051009890048e-05,
      "loss": 0.5429,
      "step": 25925
    },
    {
      "epoch": 0.7964242926919178,
      "grad_norm": 0.34268006682395935,
      "learning_rate": 1.3171592686760201e-05,
      "loss": 0.5617,
      "step": 25926
    },
    {
      "epoch": 0.796455011826867,
      "grad_norm": 0.3770497441291809,
      "learning_rate": 1.3171134356222875e-05,
      "loss": 0.635,
      "step": 25927
    },
    {
      "epoch": 0.7964857309618161,
      "grad_norm": 0.3874342739582062,
      "learning_rate": 1.3170676018279146e-05,
      "loss": 0.5387,
      "step": 25928
    },
    {
      "epoch": 0.7965164500967653,
      "grad_norm": 0.3645528256893158,
      "learning_rate": 1.3170217672930076e-05,
      "loss": 0.486,
      "step": 25929
    },
    {
      "epoch": 0.7965471692317144,
      "grad_norm": 0.36777979135513306,
      "learning_rate": 1.3169759320176746e-05,
      "loss": 0.5982,
      "step": 25930
    },
    {
      "epoch": 0.7965778883666635,
      "grad_norm": 0.4138661324977875,
      "learning_rate": 1.3169300960020222e-05,
      "loss": 0.5446,
      "step": 25931
    },
    {
      "epoch": 0.7966086075016128,
      "grad_norm": 0.43886759877204895,
      "learning_rate": 1.3168842592461572e-05,
      "loss": 0.4749,
      "step": 25932
    },
    {
      "epoch": 0.7966393266365619,
      "grad_norm": 0.3796290159225464,
      "learning_rate": 1.3168384217501871e-05,
      "loss": 0.5898,
      "step": 25933
    },
    {
      "epoch": 0.7966700457715111,
      "grad_norm": 0.36930012702941895,
      "learning_rate": 1.3167925835142183e-05,
      "loss": 0.5209,
      "step": 25934
    },
    {
      "epoch": 0.7967007649064602,
      "grad_norm": 0.3713112771511078,
      "learning_rate": 1.3167467445383588e-05,
      "loss": 0.6039,
      "step": 25935
    },
    {
      "epoch": 0.7967314840414094,
      "grad_norm": 0.3340182602405548,
      "learning_rate": 1.3167009048227148e-05,
      "loss": 0.5045,
      "step": 25936
    },
    {
      "epoch": 0.7967622031763586,
      "grad_norm": 0.43085676431655884,
      "learning_rate": 1.316655064367394e-05,
      "loss": 0.4896,
      "step": 25937
    },
    {
      "epoch": 0.7967929223113077,
      "grad_norm": 0.35012221336364746,
      "learning_rate": 1.316609223172503e-05,
      "loss": 0.5828,
      "step": 25938
    },
    {
      "epoch": 0.7968236414462568,
      "grad_norm": 0.37341564893722534,
      "learning_rate": 1.3165633812381494e-05,
      "loss": 0.5654,
      "step": 25939
    },
    {
      "epoch": 0.7968543605812061,
      "grad_norm": 0.34541675448417664,
      "learning_rate": 1.3165175385644393e-05,
      "loss": 0.5491,
      "step": 25940
    },
    {
      "epoch": 0.7968850797161552,
      "grad_norm": 0.3932779133319855,
      "learning_rate": 1.3164716951514809e-05,
      "loss": 0.5298,
      "step": 25941
    },
    {
      "epoch": 0.7969157988511043,
      "grad_norm": 0.346660315990448,
      "learning_rate": 1.3164258509993806e-05,
      "loss": 0.5222,
      "step": 25942
    },
    {
      "epoch": 0.7969465179860535,
      "grad_norm": 0.419208288192749,
      "learning_rate": 1.3163800061082457e-05,
      "loss": 0.6187,
      "step": 25943
    },
    {
      "epoch": 0.7969772371210027,
      "grad_norm": 0.35131463408470154,
      "learning_rate": 1.3163341604781831e-05,
      "loss": 0.5315,
      "step": 25944
    },
    {
      "epoch": 0.7970079562559518,
      "grad_norm": 0.36767035722732544,
      "learning_rate": 1.3162883141093e-05,
      "loss": 0.5724,
      "step": 25945
    },
    {
      "epoch": 0.797038675390901,
      "grad_norm": 0.36650556325912476,
      "learning_rate": 1.3162424670017032e-05,
      "loss": 0.526,
      "step": 25946
    },
    {
      "epoch": 0.7970693945258501,
      "grad_norm": 0.34720495343208313,
      "learning_rate": 1.3161966191555004e-05,
      "loss": 0.4715,
      "step": 25947
    },
    {
      "epoch": 0.7971001136607994,
      "grad_norm": 0.4589812457561493,
      "learning_rate": 1.3161507705707984e-05,
      "loss": 0.5772,
      "step": 25948
    },
    {
      "epoch": 0.7971308327957485,
      "grad_norm": 0.3617023825645447,
      "learning_rate": 1.3161049212477038e-05,
      "loss": 0.594,
      "step": 25949
    },
    {
      "epoch": 0.7971615519306976,
      "grad_norm": 0.325928658246994,
      "learning_rate": 1.3160590711863241e-05,
      "loss": 0.4992,
      "step": 25950
    },
    {
      "epoch": 0.7971922710656468,
      "grad_norm": 0.39157634973526,
      "learning_rate": 1.3160132203867666e-05,
      "loss": 0.5727,
      "step": 25951
    },
    {
      "epoch": 0.797222990200596,
      "grad_norm": 0.3368477523326874,
      "learning_rate": 1.315967368849138e-05,
      "loss": 0.5172,
      "step": 25952
    },
    {
      "epoch": 0.7972537093355451,
      "grad_norm": 0.37543144822120667,
      "learning_rate": 1.3159215165735458e-05,
      "loss": 0.6124,
      "step": 25953
    },
    {
      "epoch": 0.7972844284704943,
      "grad_norm": 0.3722783029079437,
      "learning_rate": 1.3158756635600964e-05,
      "loss": 0.6216,
      "step": 25954
    },
    {
      "epoch": 0.7973151476054434,
      "grad_norm": 0.3719848096370697,
      "learning_rate": 1.3158298098088977e-05,
      "loss": 0.5072,
      "step": 25955
    },
    {
      "epoch": 0.7973458667403925,
      "grad_norm": 0.3670866787433624,
      "learning_rate": 1.3157839553200562e-05,
      "loss": 0.6064,
      "step": 25956
    },
    {
      "epoch": 0.7973765858753418,
      "grad_norm": 0.3615095913410187,
      "learning_rate": 1.3157381000936793e-05,
      "loss": 0.6143,
      "step": 25957
    },
    {
      "epoch": 0.7974073050102909,
      "grad_norm": 0.4489337205886841,
      "learning_rate": 1.315692244129874e-05,
      "loss": 0.5191,
      "step": 25958
    },
    {
      "epoch": 0.7974380241452401,
      "grad_norm": 0.3746497631072998,
      "learning_rate": 1.3156463874287475e-05,
      "loss": 0.6196,
      "step": 25959
    },
    {
      "epoch": 0.7974687432801892,
      "grad_norm": 0.36237776279449463,
      "learning_rate": 1.315600529990407e-05,
      "loss": 0.5764,
      "step": 25960
    },
    {
      "epoch": 0.7974994624151384,
      "grad_norm": 0.36777809262275696,
      "learning_rate": 1.315554671814959e-05,
      "loss": 0.565,
      "step": 25961
    },
    {
      "epoch": 0.7975301815500876,
      "grad_norm": 0.4179181158542633,
      "learning_rate": 1.3155088129025111e-05,
      "loss": 0.5269,
      "step": 25962
    },
    {
      "epoch": 0.7975609006850367,
      "grad_norm": 0.33473071455955505,
      "learning_rate": 1.3154629532531705e-05,
      "loss": 0.4891,
      "step": 25963
    },
    {
      "epoch": 0.7975916198199858,
      "grad_norm": 0.36183544993400574,
      "learning_rate": 1.3154170928670442e-05,
      "loss": 0.5305,
      "step": 25964
    },
    {
      "epoch": 0.7976223389549351,
      "grad_norm": 0.36269935965538025,
      "learning_rate": 1.3153712317442389e-05,
      "loss": 0.4534,
      "step": 25965
    },
    {
      "epoch": 0.7976530580898842,
      "grad_norm": 0.37418845295906067,
      "learning_rate": 1.3153253698848624e-05,
      "loss": 0.6281,
      "step": 25966
    },
    {
      "epoch": 0.7976837772248333,
      "grad_norm": 0.3524051904678345,
      "learning_rate": 1.3152795072890214e-05,
      "loss": 0.4773,
      "step": 25967
    },
    {
      "epoch": 0.7977144963597825,
      "grad_norm": 0.355947345495224,
      "learning_rate": 1.3152336439568232e-05,
      "loss": 0.5422,
      "step": 25968
    },
    {
      "epoch": 0.7977452154947317,
      "grad_norm": 0.3754839599132538,
      "learning_rate": 1.3151877798883745e-05,
      "loss": 0.6105,
      "step": 25969
    },
    {
      "epoch": 0.7977759346296809,
      "grad_norm": 0.351158082485199,
      "learning_rate": 1.315141915083783e-05,
      "loss": 0.5574,
      "step": 25970
    },
    {
      "epoch": 0.79780665376463,
      "grad_norm": 0.3891996443271637,
      "learning_rate": 1.3150960495431553e-05,
      "loss": 0.4584,
      "step": 25971
    },
    {
      "epoch": 0.7978373728995791,
      "grad_norm": 0.4051453769207001,
      "learning_rate": 1.3150501832665988e-05,
      "loss": 0.5332,
      "step": 25972
    },
    {
      "epoch": 0.7978680920345284,
      "grad_norm": 0.7068103551864624,
      "learning_rate": 1.3150043162542208e-05,
      "loss": 0.5822,
      "step": 25973
    },
    {
      "epoch": 0.7978988111694775,
      "grad_norm": 0.4201067388057709,
      "learning_rate": 1.3149584485061283e-05,
      "loss": 0.5172,
      "step": 25974
    },
    {
      "epoch": 0.7979295303044266,
      "grad_norm": 0.42194539308547974,
      "learning_rate": 1.3149125800224281e-05,
      "loss": 0.5604,
      "step": 25975
    },
    {
      "epoch": 0.7979602494393758,
      "grad_norm": 0.3290785253047943,
      "learning_rate": 1.3148667108032276e-05,
      "loss": 0.5293,
      "step": 25976
    },
    {
      "epoch": 0.7979909685743249,
      "grad_norm": 0.33781561255455017,
      "learning_rate": 1.314820840848634e-05,
      "loss": 0.4256,
      "step": 25977
    },
    {
      "epoch": 0.7980216877092741,
      "grad_norm": 0.4012170135974884,
      "learning_rate": 1.3147749701587545e-05,
      "loss": 0.5301,
      "step": 25978
    },
    {
      "epoch": 0.7980524068442233,
      "grad_norm": 0.3817545473575592,
      "learning_rate": 1.3147290987336956e-05,
      "loss": 0.5707,
      "step": 25979
    },
    {
      "epoch": 0.7980831259791724,
      "grad_norm": 0.3623744249343872,
      "learning_rate": 1.3146832265735654e-05,
      "loss": 0.525,
      "step": 25980
    },
    {
      "epoch": 0.7981138451141215,
      "grad_norm": 0.3681064546108246,
      "learning_rate": 1.3146373536784702e-05,
      "loss": 0.55,
      "step": 25981
    },
    {
      "epoch": 0.7981445642490708,
      "grad_norm": 0.3796258568763733,
      "learning_rate": 1.3145914800485175e-05,
      "loss": 0.5583,
      "step": 25982
    },
    {
      "epoch": 0.7981752833840199,
      "grad_norm": 0.4165703058242798,
      "learning_rate": 1.3145456056838146e-05,
      "loss": 0.5049,
      "step": 25983
    },
    {
      "epoch": 0.7982060025189691,
      "grad_norm": 0.30720359086990356,
      "learning_rate": 1.3144997305844687e-05,
      "loss": 0.5534,
      "step": 25984
    },
    {
      "epoch": 0.7982367216539182,
      "grad_norm": 0.3921777904033661,
      "learning_rate": 1.3144538547505863e-05,
      "loss": 0.5402,
      "step": 25985
    },
    {
      "epoch": 0.7982674407888674,
      "grad_norm": 0.38557904958724976,
      "learning_rate": 1.314407978182275e-05,
      "loss": 0.5538,
      "step": 25986
    },
    {
      "epoch": 0.7982981599238166,
      "grad_norm": 0.3743959367275238,
      "learning_rate": 1.3143621008796418e-05,
      "loss": 0.6154,
      "step": 25987
    },
    {
      "epoch": 0.7983288790587657,
      "grad_norm": 0.351915180683136,
      "learning_rate": 1.3143162228427944e-05,
      "loss": 0.5138,
      "step": 25988
    },
    {
      "epoch": 0.7983595981937148,
      "grad_norm": 0.3843056559562683,
      "learning_rate": 1.3142703440718392e-05,
      "loss": 0.4554,
      "step": 25989
    },
    {
      "epoch": 0.7983903173286641,
      "grad_norm": 0.3413323760032654,
      "learning_rate": 1.3142244645668836e-05,
      "loss": 0.5444,
      "step": 25990
    },
    {
      "epoch": 0.7984210364636132,
      "grad_norm": 0.3556300103664398,
      "learning_rate": 1.314178584328035e-05,
      "loss": 0.4655,
      "step": 25991
    },
    {
      "epoch": 0.7984517555985623,
      "grad_norm": 0.39269739389419556,
      "learning_rate": 1.3141327033554004e-05,
      "loss": 0.5096,
      "step": 25992
    },
    {
      "epoch": 0.7984824747335115,
      "grad_norm": 0.3481486141681671,
      "learning_rate": 1.3140868216490868e-05,
      "loss": 0.5791,
      "step": 25993
    },
    {
      "epoch": 0.7985131938684606,
      "grad_norm": 0.35920044779777527,
      "learning_rate": 1.3140409392092017e-05,
      "loss": 0.5273,
      "step": 25994
    },
    {
      "epoch": 0.7985439130034099,
      "grad_norm": 0.3546205461025238,
      "learning_rate": 1.3139950560358518e-05,
      "loss": 0.5304,
      "step": 25995
    },
    {
      "epoch": 0.798574632138359,
      "grad_norm": 0.34377312660217285,
      "learning_rate": 1.3139491721291449e-05,
      "loss": 0.5021,
      "step": 25996
    },
    {
      "epoch": 0.7986053512733081,
      "grad_norm": 0.3557325303554535,
      "learning_rate": 1.3139032874891873e-05,
      "loss": 0.5431,
      "step": 25997
    },
    {
      "epoch": 0.7986360704082573,
      "grad_norm": 0.9006661176681519,
      "learning_rate": 1.3138574021160869e-05,
      "loss": 0.5306,
      "step": 25998
    },
    {
      "epoch": 0.7986667895432065,
      "grad_norm": 0.3597590923309326,
      "learning_rate": 1.3138115160099505e-05,
      "loss": 0.5717,
      "step": 25999
    },
    {
      "epoch": 0.7986975086781556,
      "grad_norm": 0.34672948718070984,
      "learning_rate": 1.3137656291708856e-05,
      "loss": 0.5783,
      "step": 26000
    },
    {
      "epoch": 0.7987282278131048,
      "grad_norm": 0.3330441117286682,
      "learning_rate": 1.3137197415989988e-05,
      "loss": 0.5581,
      "step": 26001
    },
    {
      "epoch": 0.7987589469480539,
      "grad_norm": 0.36343884468078613,
      "learning_rate": 1.313673853294398e-05,
      "loss": 0.5037,
      "step": 26002
    },
    {
      "epoch": 0.7987896660830031,
      "grad_norm": 0.34563183784484863,
      "learning_rate": 1.3136279642571897e-05,
      "loss": 0.5492,
      "step": 26003
    },
    {
      "epoch": 0.7988203852179523,
      "grad_norm": 0.3613867461681366,
      "learning_rate": 1.3135820744874816e-05,
      "loss": 0.5662,
      "step": 26004
    },
    {
      "epoch": 0.7988511043529014,
      "grad_norm": 0.35942599177360535,
      "learning_rate": 1.3135361839853809e-05,
      "loss": 0.5943,
      "step": 26005
    },
    {
      "epoch": 0.7988818234878505,
      "grad_norm": 0.38746094703674316,
      "learning_rate": 1.313490292750994e-05,
      "loss": 0.5341,
      "step": 26006
    },
    {
      "epoch": 0.7989125426227998,
      "grad_norm": 0.41687777638435364,
      "learning_rate": 1.3134444007844289e-05,
      "loss": 0.5818,
      "step": 26007
    },
    {
      "epoch": 0.7989432617577489,
      "grad_norm": 0.3636980354785919,
      "learning_rate": 1.3133985080857923e-05,
      "loss": 0.5501,
      "step": 26008
    },
    {
      "epoch": 0.7989739808926981,
      "grad_norm": 0.35696107149124146,
      "learning_rate": 1.3133526146551918e-05,
      "loss": 0.604,
      "step": 26009
    },
    {
      "epoch": 0.7990047000276472,
      "grad_norm": 0.3698446452617645,
      "learning_rate": 1.3133067204927344e-05,
      "loss": 0.5697,
      "step": 26010
    },
    {
      "epoch": 0.7990354191625963,
      "grad_norm": 0.38343730568885803,
      "learning_rate": 1.3132608255985273e-05,
      "loss": 0.515,
      "step": 26011
    },
    {
      "epoch": 0.7990661382975456,
      "grad_norm": 0.3417481482028961,
      "learning_rate": 1.3132149299726777e-05,
      "loss": 0.5512,
      "step": 26012
    },
    {
      "epoch": 0.7990968574324947,
      "grad_norm": 0.40238040685653687,
      "learning_rate": 1.3131690336152927e-05,
      "loss": 0.6578,
      "step": 26013
    },
    {
      "epoch": 0.7991275765674438,
      "grad_norm": 0.37843987345695496,
      "learning_rate": 1.3131231365264797e-05,
      "loss": 0.4885,
      "step": 26014
    },
    {
      "epoch": 0.799158295702393,
      "grad_norm": 0.32668381929397583,
      "learning_rate": 1.3130772387063453e-05,
      "loss": 0.5503,
      "step": 26015
    },
    {
      "epoch": 0.7991890148373422,
      "grad_norm": 0.4286276400089264,
      "learning_rate": 1.3130313401549974e-05,
      "loss": 0.5791,
      "step": 26016
    },
    {
      "epoch": 0.7992197339722913,
      "grad_norm": 0.36461856961250305,
      "learning_rate": 1.3129854408725429e-05,
      "loss": 0.5349,
      "step": 26017
    },
    {
      "epoch": 0.7992504531072405,
      "grad_norm": 0.3559931516647339,
      "learning_rate": 1.3129395408590892e-05,
      "loss": 0.6079,
      "step": 26018
    },
    {
      "epoch": 0.7992811722421896,
      "grad_norm": 0.34531503915786743,
      "learning_rate": 1.3128936401147432e-05,
      "loss": 0.4731,
      "step": 26019
    },
    {
      "epoch": 0.7993118913771389,
      "grad_norm": 0.3795378506183624,
      "learning_rate": 1.3128477386396124e-05,
      "loss": 0.502,
      "step": 26020
    },
    {
      "epoch": 0.799342610512088,
      "grad_norm": 0.3717140853404999,
      "learning_rate": 1.3128018364338035e-05,
      "loss": 0.5116,
      "step": 26021
    },
    {
      "epoch": 0.7993733296470371,
      "grad_norm": 0.417337030172348,
      "learning_rate": 1.3127559334974245e-05,
      "loss": 0.551,
      "step": 26022
    },
    {
      "epoch": 0.7994040487819863,
      "grad_norm": 0.33806276321411133,
      "learning_rate": 1.3127100298305822e-05,
      "loss": 0.5385,
      "step": 26023
    },
    {
      "epoch": 0.7994347679169355,
      "grad_norm": 0.5566702485084534,
      "learning_rate": 1.3126641254333834e-05,
      "loss": 0.5249,
      "step": 26024
    },
    {
      "epoch": 0.7994654870518846,
      "grad_norm": 0.37143343687057495,
      "learning_rate": 1.3126182203059358e-05,
      "loss": 0.4764,
      "step": 26025
    },
    {
      "epoch": 0.7994962061868338,
      "grad_norm": 0.38810285925865173,
      "learning_rate": 1.3125723144483465e-05,
      "loss": 0.5605,
      "step": 26026
    },
    {
      "epoch": 0.7995269253217829,
      "grad_norm": 0.34514349699020386,
      "learning_rate": 1.312526407860723e-05,
      "loss": 0.5472,
      "step": 26027
    },
    {
      "epoch": 0.799557644456732,
      "grad_norm": 0.34701666235923767,
      "learning_rate": 1.3124805005431718e-05,
      "loss": 0.5455,
      "step": 26028
    },
    {
      "epoch": 0.7995883635916813,
      "grad_norm": 0.3594312369823456,
      "learning_rate": 1.312434592495801e-05,
      "loss": 0.5794,
      "step": 26029
    },
    {
      "epoch": 0.7996190827266304,
      "grad_norm": 0.46964624524116516,
      "learning_rate": 1.3123886837187173e-05,
      "loss": 0.494,
      "step": 26030
    },
    {
      "epoch": 0.7996498018615795,
      "grad_norm": 0.4257698059082031,
      "learning_rate": 1.312342774212028e-05,
      "loss": 0.5138,
      "step": 26031
    },
    {
      "epoch": 0.7996805209965288,
      "grad_norm": 0.3353979289531708,
      "learning_rate": 1.3122968639758402e-05,
      "loss": 0.5041,
      "step": 26032
    },
    {
      "epoch": 0.7997112401314779,
      "grad_norm": 0.3489910364151001,
      "learning_rate": 1.3122509530102614e-05,
      "loss": 0.529,
      "step": 26033
    },
    {
      "epoch": 0.7997419592664271,
      "grad_norm": 0.4353380799293518,
      "learning_rate": 1.3122050413153987e-05,
      "loss": 0.5471,
      "step": 26034
    },
    {
      "epoch": 0.7997726784013762,
      "grad_norm": 0.351635605096817,
      "learning_rate": 1.312159128891359e-05,
      "loss": 0.5006,
      "step": 26035
    },
    {
      "epoch": 0.7998033975363253,
      "grad_norm": 0.4392237663269043,
      "learning_rate": 1.3121132157382504e-05,
      "loss": 0.5391,
      "step": 26036
    },
    {
      "epoch": 0.7998341166712746,
      "grad_norm": 0.4381001889705658,
      "learning_rate": 1.3120673018561791e-05,
      "loss": 0.5026,
      "step": 26037
    },
    {
      "epoch": 0.7998648358062237,
      "grad_norm": 0.3264738619327545,
      "learning_rate": 1.3120213872452532e-05,
      "loss": 0.5123,
      "step": 26038
    },
    {
      "epoch": 0.7998955549411728,
      "grad_norm": 0.360623300075531,
      "learning_rate": 1.3119754719055793e-05,
      "loss": 0.5545,
      "step": 26039
    },
    {
      "epoch": 0.799926274076122,
      "grad_norm": 0.3634301722049713,
      "learning_rate": 1.311929555837265e-05,
      "loss": 0.4933,
      "step": 26040
    },
    {
      "epoch": 0.7999569932110712,
      "grad_norm": 0.3439560830593109,
      "learning_rate": 1.3118836390404174e-05,
      "loss": 0.5777,
      "step": 26041
    },
    {
      "epoch": 0.7999877123460203,
      "grad_norm": 0.38237085938453674,
      "learning_rate": 1.3118377215151439e-05,
      "loss": 0.6134,
      "step": 26042
    },
    {
      "epoch": 0.8000184314809695,
      "grad_norm": 0.3699914813041687,
      "learning_rate": 1.3117918032615515e-05,
      "loss": 0.4554,
      "step": 26043
    },
    {
      "epoch": 0.8000491506159186,
      "grad_norm": 0.3734308183193207,
      "learning_rate": 1.3117458842797472e-05,
      "loss": 0.5808,
      "step": 26044
    },
    {
      "epoch": 0.8000798697508679,
      "grad_norm": 0.38362058997154236,
      "learning_rate": 1.3116999645698392e-05,
      "loss": 0.5005,
      "step": 26045
    },
    {
      "epoch": 0.800110588885817,
      "grad_norm": 0.41260799765586853,
      "learning_rate": 1.3116540441319341e-05,
      "loss": 0.5286,
      "step": 26046
    },
    {
      "epoch": 0.8001413080207661,
      "grad_norm": 0.40700340270996094,
      "learning_rate": 1.3116081229661389e-05,
      "loss": 0.5099,
      "step": 26047
    },
    {
      "epoch": 0.8001720271557153,
      "grad_norm": 0.4948415756225586,
      "learning_rate": 1.3115622010725614e-05,
      "loss": 0.5313,
      "step": 26048
    },
    {
      "epoch": 0.8002027462906645,
      "grad_norm": 0.39953237771987915,
      "learning_rate": 1.3115162784513085e-05,
      "loss": 0.4943,
      "step": 26049
    },
    {
      "epoch": 0.8002334654256136,
      "grad_norm": 0.3643600046634674,
      "learning_rate": 1.3114703551024876e-05,
      "loss": 0.4957,
      "step": 26050
    },
    {
      "epoch": 0.8002641845605628,
      "grad_norm": 0.370609849691391,
      "learning_rate": 1.311424431026206e-05,
      "loss": 0.4733,
      "step": 26051
    },
    {
      "epoch": 0.8002949036955119,
      "grad_norm": 0.3524817228317261,
      "learning_rate": 1.311378506222571e-05,
      "loss": 0.6039,
      "step": 26052
    },
    {
      "epoch": 0.800325622830461,
      "grad_norm": 0.34567371010780334,
      "learning_rate": 1.3113325806916895e-05,
      "loss": 0.5226,
      "step": 26053
    },
    {
      "epoch": 0.8003563419654103,
      "grad_norm": 0.37508171796798706,
      "learning_rate": 1.311286654433669e-05,
      "loss": 0.5484,
      "step": 26054
    },
    {
      "epoch": 0.8003870611003594,
      "grad_norm": 0.441914826631546,
      "learning_rate": 1.3112407274486169e-05,
      "loss": 0.576,
      "step": 26055
    },
    {
      "epoch": 0.8004177802353086,
      "grad_norm": 0.3712744414806366,
      "learning_rate": 1.3111947997366405e-05,
      "loss": 0.607,
      "step": 26056
    },
    {
      "epoch": 0.8004484993702577,
      "grad_norm": 0.37870481610298157,
      "learning_rate": 1.3111488712978469e-05,
      "loss": 0.6215,
      "step": 26057
    },
    {
      "epoch": 0.8004792185052069,
      "grad_norm": 0.34891700744628906,
      "learning_rate": 1.311102942132343e-05,
      "loss": 0.5602,
      "step": 26058
    },
    {
      "epoch": 0.8005099376401561,
      "grad_norm": 0.3529869616031647,
      "learning_rate": 1.3110570122402369e-05,
      "loss": 0.5471,
      "step": 26059
    },
    {
      "epoch": 0.8005406567751052,
      "grad_norm": 0.35381096601486206,
      "learning_rate": 1.3110110816216351e-05,
      "loss": 0.5831,
      "step": 26060
    },
    {
      "epoch": 0.8005713759100543,
      "grad_norm": 0.5019901990890503,
      "learning_rate": 1.3109651502766454e-05,
      "loss": 0.5873,
      "step": 26061
    },
    {
      "epoch": 0.8006020950450036,
      "grad_norm": 0.3516576588153839,
      "learning_rate": 1.3109192182053745e-05,
      "loss": 0.5347,
      "step": 26062
    },
    {
      "epoch": 0.8006328141799527,
      "grad_norm": 0.3638651967048645,
      "learning_rate": 1.3108732854079304e-05,
      "loss": 0.5682,
      "step": 26063
    },
    {
      "epoch": 0.8006635333149018,
      "grad_norm": 0.38570958375930786,
      "learning_rate": 1.3108273518844202e-05,
      "loss": 0.5175,
      "step": 26064
    },
    {
      "epoch": 0.800694252449851,
      "grad_norm": 0.3804757297039032,
      "learning_rate": 1.3107814176349507e-05,
      "loss": 0.5777,
      "step": 26065
    },
    {
      "epoch": 0.8007249715848002,
      "grad_norm": 0.3805074691772461,
      "learning_rate": 1.3107354826596297e-05,
      "loss": 0.5204,
      "step": 26066
    },
    {
      "epoch": 0.8007556907197493,
      "grad_norm": 0.3425505459308624,
      "learning_rate": 1.3106895469585638e-05,
      "loss": 0.5762,
      "step": 26067
    },
    {
      "epoch": 0.8007864098546985,
      "grad_norm": 0.4042263329029083,
      "learning_rate": 1.3106436105318614e-05,
      "loss": 0.537,
      "step": 26068
    },
    {
      "epoch": 0.8008171289896476,
      "grad_norm": 0.41676095128059387,
      "learning_rate": 1.3105976733796286e-05,
      "loss": 0.6434,
      "step": 26069
    },
    {
      "epoch": 0.8008478481245969,
      "grad_norm": 0.3552660644054413,
      "learning_rate": 1.310551735501974e-05,
      "loss": 0.6455,
      "step": 26070
    },
    {
      "epoch": 0.800878567259546,
      "grad_norm": 0.40283024311065674,
      "learning_rate": 1.3105057968990033e-05,
      "loss": 0.4653,
      "step": 26071
    },
    {
      "epoch": 0.8009092863944951,
      "grad_norm": 0.3518514037132263,
      "learning_rate": 1.3104598575708251e-05,
      "loss": 0.5296,
      "step": 26072
    },
    {
      "epoch": 0.8009400055294443,
      "grad_norm": 0.3493010401725769,
      "learning_rate": 1.310413917517546e-05,
      "loss": 0.4753,
      "step": 26073
    },
    {
      "epoch": 0.8009707246643935,
      "grad_norm": 0.39399948716163635,
      "learning_rate": 1.3103679767392737e-05,
      "loss": 0.5953,
      "step": 26074
    },
    {
      "epoch": 0.8010014437993426,
      "grad_norm": 0.34893447160720825,
      "learning_rate": 1.3103220352361152e-05,
      "loss": 0.5921,
      "step": 26075
    },
    {
      "epoch": 0.8010321629342918,
      "grad_norm": 0.3695739805698395,
      "learning_rate": 1.310276093008178e-05,
      "loss": 0.5171,
      "step": 26076
    },
    {
      "epoch": 0.8010628820692409,
      "grad_norm": 0.37786665558815,
      "learning_rate": 1.3102301500555692e-05,
      "loss": 0.6175,
      "step": 26077
    },
    {
      "epoch": 0.80109360120419,
      "grad_norm": 0.44746172428131104,
      "learning_rate": 1.3101842063783963e-05,
      "loss": 0.5858,
      "step": 26078
    },
    {
      "epoch": 0.8011243203391393,
      "grad_norm": 0.36504459381103516,
      "learning_rate": 1.3101382619767667e-05,
      "loss": 0.5267,
      "step": 26079
    },
    {
      "epoch": 0.8011550394740884,
      "grad_norm": 0.43510743975639343,
      "learning_rate": 1.3100923168507869e-05,
      "loss": 0.6664,
      "step": 26080
    },
    {
      "epoch": 0.8011857586090376,
      "grad_norm": 0.5376330018043518,
      "learning_rate": 1.3100463710005652e-05,
      "loss": 0.55,
      "step": 26081
    },
    {
      "epoch": 0.8012164777439867,
      "grad_norm": 0.33635497093200684,
      "learning_rate": 1.310000424426209e-05,
      "loss": 0.534,
      "step": 26082
    },
    {
      "epoch": 0.8012471968789359,
      "grad_norm": 0.33453264832496643,
      "learning_rate": 1.3099544771278245e-05,
      "loss": 0.464,
      "step": 26083
    },
    {
      "epoch": 0.8012779160138851,
      "grad_norm": 0.3376138210296631,
      "learning_rate": 1.30990852910552e-05,
      "loss": 0.6122,
      "step": 26084
    },
    {
      "epoch": 0.8013086351488342,
      "grad_norm": 0.4851231873035431,
      "learning_rate": 1.3098625803594023e-05,
      "loss": 0.6001,
      "step": 26085
    },
    {
      "epoch": 0.8013393542837833,
      "grad_norm": 0.342579185962677,
      "learning_rate": 1.3098166308895792e-05,
      "loss": 0.4462,
      "step": 26086
    },
    {
      "epoch": 0.8013700734187326,
      "grad_norm": 0.3580623269081116,
      "learning_rate": 1.3097706806961575e-05,
      "loss": 0.5604,
      "step": 26087
    },
    {
      "epoch": 0.8014007925536817,
      "grad_norm": 0.3634633719921112,
      "learning_rate": 1.3097247297792448e-05,
      "loss": 0.585,
      "step": 26088
    },
    {
      "epoch": 0.8014315116886308,
      "grad_norm": 0.3509052097797394,
      "learning_rate": 1.3096787781389484e-05,
      "loss": 0.5446,
      "step": 26089
    },
    {
      "epoch": 0.80146223082358,
      "grad_norm": 0.4009198546409607,
      "learning_rate": 1.3096328257753756e-05,
      "loss": 0.5178,
      "step": 26090
    },
    {
      "epoch": 0.8014929499585292,
      "grad_norm": 0.36034858226776123,
      "learning_rate": 1.3095868726886333e-05,
      "loss": 0.5305,
      "step": 26091
    },
    {
      "epoch": 0.8015236690934783,
      "grad_norm": 0.34434840083122253,
      "learning_rate": 1.3095409188788299e-05,
      "loss": 0.5737,
      "step": 26092
    },
    {
      "epoch": 0.8015543882284275,
      "grad_norm": 0.35694393515586853,
      "learning_rate": 1.309494964346072e-05,
      "loss": 0.5447,
      "step": 26093
    },
    {
      "epoch": 0.8015851073633766,
      "grad_norm": 0.3767606019973755,
      "learning_rate": 1.3094490090904666e-05,
      "loss": 0.6028,
      "step": 26094
    },
    {
      "epoch": 0.8016158264983259,
      "grad_norm": 0.43184271454811096,
      "learning_rate": 1.3094030531121216e-05,
      "loss": 0.4991,
      "step": 26095
    },
    {
      "epoch": 0.801646545633275,
      "grad_norm": 0.37133118510246277,
      "learning_rate": 1.309357096411144e-05,
      "loss": 0.5939,
      "step": 26096
    },
    {
      "epoch": 0.8016772647682241,
      "grad_norm": 0.36673563718795776,
      "learning_rate": 1.3093111389876416e-05,
      "loss": 0.5366,
      "step": 26097
    },
    {
      "epoch": 0.8017079839031733,
      "grad_norm": 0.33350828289985657,
      "learning_rate": 1.309265180841721e-05,
      "loss": 0.545,
      "step": 26098
    },
    {
      "epoch": 0.8017387030381224,
      "grad_norm": 0.349079966545105,
      "learning_rate": 1.3092192219734903e-05,
      "loss": 0.5359,
      "step": 26099
    },
    {
      "epoch": 0.8017694221730716,
      "grad_norm": 0.4071907699108124,
      "learning_rate": 1.3091732623830566e-05,
      "loss": 0.5414,
      "step": 26100
    },
    {
      "epoch": 0.8018001413080208,
      "grad_norm": 0.3710370361804962,
      "learning_rate": 1.3091273020705269e-05,
      "loss": 0.5169,
      "step": 26101
    },
    {
      "epoch": 0.8018308604429699,
      "grad_norm": 0.39904922246932983,
      "learning_rate": 1.3090813410360088e-05,
      "loss": 0.6757,
      "step": 26102
    },
    {
      "epoch": 0.801861579577919,
      "grad_norm": 0.3046227693557739,
      "learning_rate": 1.3090353792796098e-05,
      "loss": 0.4833,
      "step": 26103
    },
    {
      "epoch": 0.8018922987128683,
      "grad_norm": 0.35173580050468445,
      "learning_rate": 1.308989416801437e-05,
      "loss": 0.588,
      "step": 26104
    },
    {
      "epoch": 0.8019230178478174,
      "grad_norm": 0.35749971866607666,
      "learning_rate": 1.308943453601598e-05,
      "loss": 0.5499,
      "step": 26105
    },
    {
      "epoch": 0.8019537369827666,
      "grad_norm": 0.35244616866111755,
      "learning_rate": 1.3088974896801998e-05,
      "loss": 0.5191,
      "step": 26106
    },
    {
      "epoch": 0.8019844561177157,
      "grad_norm": 0.41570258140563965,
      "learning_rate": 1.30885152503735e-05,
      "loss": 0.5274,
      "step": 26107
    },
    {
      "epoch": 0.8020151752526649,
      "grad_norm": 0.3391374349594116,
      "learning_rate": 1.308805559673156e-05,
      "loss": 0.5548,
      "step": 26108
    },
    {
      "epoch": 0.8020458943876141,
      "grad_norm": 0.3799046576023102,
      "learning_rate": 1.3087595935877247e-05,
      "loss": 0.5868,
      "step": 26109
    },
    {
      "epoch": 0.8020766135225632,
      "grad_norm": 0.4321231245994568,
      "learning_rate": 1.3087136267811642e-05,
      "loss": 0.5322,
      "step": 26110
    },
    {
      "epoch": 0.8021073326575123,
      "grad_norm": 0.3721866309642792,
      "learning_rate": 1.3086676592535814e-05,
      "loss": 0.5174,
      "step": 26111
    },
    {
      "epoch": 0.8021380517924616,
      "grad_norm": 0.6453045010566711,
      "learning_rate": 1.3086216910050835e-05,
      "loss": 0.6006,
      "step": 26112
    },
    {
      "epoch": 0.8021687709274107,
      "grad_norm": 0.33022141456604004,
      "learning_rate": 1.3085757220357785e-05,
      "loss": 0.4718,
      "step": 26113
    },
    {
      "epoch": 0.8021994900623598,
      "grad_norm": 0.36995232105255127,
      "learning_rate": 1.308529752345773e-05,
      "loss": 0.5654,
      "step": 26114
    },
    {
      "epoch": 0.802230209197309,
      "grad_norm": 0.3938498795032501,
      "learning_rate": 1.3084837819351748e-05,
      "loss": 0.5507,
      "step": 26115
    },
    {
      "epoch": 0.8022609283322581,
      "grad_norm": 0.35462838411331177,
      "learning_rate": 1.3084378108040909e-05,
      "loss": 0.4581,
      "step": 26116
    },
    {
      "epoch": 0.8022916474672073,
      "grad_norm": 0.4495857357978821,
      "learning_rate": 1.3083918389526291e-05,
      "loss": 0.5661,
      "step": 26117
    },
    {
      "epoch": 0.8023223666021565,
      "grad_norm": 0.41356581449508667,
      "learning_rate": 1.308345866380897e-05,
      "loss": 0.5226,
      "step": 26118
    },
    {
      "epoch": 0.8023530857371056,
      "grad_norm": 0.3567899465560913,
      "learning_rate": 1.3082998930890011e-05,
      "loss": 0.5365,
      "step": 26119
    },
    {
      "epoch": 0.8023838048720549,
      "grad_norm": 0.4289098083972931,
      "learning_rate": 1.3082539190770497e-05,
      "loss": 0.5753,
      "step": 26120
    },
    {
      "epoch": 0.802414524007004,
      "grad_norm": 0.35690388083457947,
      "learning_rate": 1.3082079443451495e-05,
      "loss": 0.5955,
      "step": 26121
    },
    {
      "epoch": 0.8024452431419531,
      "grad_norm": 0.3410249650478363,
      "learning_rate": 1.3081619688934082e-05,
      "loss": 0.5562,
      "step": 26122
    },
    {
      "epoch": 0.8024759622769023,
      "grad_norm": 0.47192901372909546,
      "learning_rate": 1.308115992721933e-05,
      "loss": 0.5877,
      "step": 26123
    },
    {
      "epoch": 0.8025066814118514,
      "grad_norm": 0.362843781709671,
      "learning_rate": 1.3080700158308315e-05,
      "loss": 0.5638,
      "step": 26124
    },
    {
      "epoch": 0.8025374005468006,
      "grad_norm": 0.3768976926803589,
      "learning_rate": 1.3080240382202108e-05,
      "loss": 0.5355,
      "step": 26125
    },
    {
      "epoch": 0.8025681196817498,
      "grad_norm": 0.3481595814228058,
      "learning_rate": 1.3079780598901788e-05,
      "loss": 0.4967,
      "step": 26126
    },
    {
      "epoch": 0.8025988388166989,
      "grad_norm": 0.3105914890766144,
      "learning_rate": 1.3079320808408423e-05,
      "loss": 0.5132,
      "step": 26127
    },
    {
      "epoch": 0.802629557951648,
      "grad_norm": 0.36178484559059143,
      "learning_rate": 1.3078861010723088e-05,
      "loss": 0.5824,
      "step": 26128
    },
    {
      "epoch": 0.8026602770865973,
      "grad_norm": 0.594438374042511,
      "learning_rate": 1.307840120584686e-05,
      "loss": 0.5404,
      "step": 26129
    },
    {
      "epoch": 0.8026909962215464,
      "grad_norm": 0.35874930024147034,
      "learning_rate": 1.307794139378081e-05,
      "loss": 0.5563,
      "step": 26130
    },
    {
      "epoch": 0.8027217153564956,
      "grad_norm": 0.36837640404701233,
      "learning_rate": 1.3077481574526013e-05,
      "loss": 0.5924,
      "step": 26131
    },
    {
      "epoch": 0.8027524344914447,
      "grad_norm": 0.38493528962135315,
      "learning_rate": 1.3077021748083542e-05,
      "loss": 0.6269,
      "step": 26132
    },
    {
      "epoch": 0.8027831536263939,
      "grad_norm": 0.3791649043560028,
      "learning_rate": 1.3076561914454474e-05,
      "loss": 0.6111,
      "step": 26133
    },
    {
      "epoch": 0.8028138727613431,
      "grad_norm": 0.3735343813896179,
      "learning_rate": 1.3076102073639878e-05,
      "loss": 0.5442,
      "step": 26134
    },
    {
      "epoch": 0.8028445918962922,
      "grad_norm": 0.3755734860897064,
      "learning_rate": 1.3075642225640833e-05,
      "loss": 0.6674,
      "step": 26135
    },
    {
      "epoch": 0.8028753110312413,
      "grad_norm": 0.377521276473999,
      "learning_rate": 1.307518237045841e-05,
      "loss": 0.457,
      "step": 26136
    },
    {
      "epoch": 0.8029060301661906,
      "grad_norm": 0.4080037772655487,
      "learning_rate": 1.3074722508093683e-05,
      "loss": 0.6039,
      "step": 26137
    },
    {
      "epoch": 0.8029367493011397,
      "grad_norm": 1.3671406507492065,
      "learning_rate": 1.3074262638547728e-05,
      "loss": 0.61,
      "step": 26138
    },
    {
      "epoch": 0.8029674684360888,
      "grad_norm": 0.3870183527469635,
      "learning_rate": 1.307380276182162e-05,
      "loss": 0.5089,
      "step": 26139
    },
    {
      "epoch": 0.802998187571038,
      "grad_norm": 0.45058515667915344,
      "learning_rate": 1.3073342877916426e-05,
      "loss": 0.5216,
      "step": 26140
    },
    {
      "epoch": 0.8030289067059871,
      "grad_norm": 0.42971301078796387,
      "learning_rate": 1.3072882986833229e-05,
      "loss": 0.5788,
      "step": 26141
    },
    {
      "epoch": 0.8030596258409363,
      "grad_norm": 0.37529247999191284,
      "learning_rate": 1.3072423088573099e-05,
      "loss": 0.5662,
      "step": 26142
    },
    {
      "epoch": 0.8030903449758855,
      "grad_norm": 0.3305055797100067,
      "learning_rate": 1.3071963183137109e-05,
      "loss": 0.4941,
      "step": 26143
    },
    {
      "epoch": 0.8031210641108346,
      "grad_norm": 0.3648013174533844,
      "learning_rate": 1.3071503270526333e-05,
      "loss": 0.5809,
      "step": 26144
    },
    {
      "epoch": 0.8031517832457838,
      "grad_norm": 0.4816353917121887,
      "learning_rate": 1.307104335074185e-05,
      "loss": 0.5126,
      "step": 26145
    },
    {
      "epoch": 0.803182502380733,
      "grad_norm": 0.4044342339038849,
      "learning_rate": 1.3070583423784729e-05,
      "loss": 0.5257,
      "step": 26146
    },
    {
      "epoch": 0.8032132215156821,
      "grad_norm": 0.38759416341781616,
      "learning_rate": 1.3070123489656045e-05,
      "loss": 0.5658,
      "step": 26147
    },
    {
      "epoch": 0.8032439406506313,
      "grad_norm": 0.4582498073577881,
      "learning_rate": 1.3069663548356875e-05,
      "loss": 0.5421,
      "step": 26148
    },
    {
      "epoch": 0.8032746597855804,
      "grad_norm": 0.36160436272621155,
      "learning_rate": 1.3069203599888291e-05,
      "loss": 0.5037,
      "step": 26149
    },
    {
      "epoch": 0.8033053789205296,
      "grad_norm": 0.3275303840637207,
      "learning_rate": 1.3068743644251364e-05,
      "loss": 0.495,
      "step": 26150
    },
    {
      "epoch": 0.8033360980554788,
      "grad_norm": 0.35767847299575806,
      "learning_rate": 1.3068283681447178e-05,
      "loss": 0.6357,
      "step": 26151
    },
    {
      "epoch": 0.8033668171904279,
      "grad_norm": 0.37351754307746887,
      "learning_rate": 1.3067823711476796e-05,
      "loss": 0.4879,
      "step": 26152
    },
    {
      "epoch": 0.803397536325377,
      "grad_norm": 0.3640378713607788,
      "learning_rate": 1.30673637343413e-05,
      "loss": 0.5204,
      "step": 26153
    },
    {
      "epoch": 0.8034282554603263,
      "grad_norm": 0.4045173227787018,
      "learning_rate": 1.3066903750041764e-05,
      "loss": 0.5193,
      "step": 26154
    },
    {
      "epoch": 0.8034589745952754,
      "grad_norm": 0.38443228602409363,
      "learning_rate": 1.3066443758579255e-05,
      "loss": 0.5428,
      "step": 26155
    },
    {
      "epoch": 0.8034896937302246,
      "grad_norm": 0.38330134749412537,
      "learning_rate": 1.3065983759954857e-05,
      "loss": 0.508,
      "step": 26156
    },
    {
      "epoch": 0.8035204128651737,
      "grad_norm": 0.335918128490448,
      "learning_rate": 1.3065523754169635e-05,
      "loss": 0.538,
      "step": 26157
    },
    {
      "epoch": 0.8035511320001228,
      "grad_norm": 0.36141470074653625,
      "learning_rate": 1.3065063741224673e-05,
      "loss": 0.5355,
      "step": 26158
    },
    {
      "epoch": 0.8035818511350721,
      "grad_norm": 0.40230101346969604,
      "learning_rate": 1.3064603721121039e-05,
      "loss": 0.519,
      "step": 26159
    },
    {
      "epoch": 0.8036125702700212,
      "grad_norm": 0.3505796492099762,
      "learning_rate": 1.3064143693859807e-05,
      "loss": 0.5701,
      "step": 26160
    },
    {
      "epoch": 0.8036432894049703,
      "grad_norm": 0.363002210855484,
      "learning_rate": 1.3063683659442055e-05,
      "loss": 0.4814,
      "step": 26161
    },
    {
      "epoch": 0.8036740085399195,
      "grad_norm": 0.41682595014572144,
      "learning_rate": 1.3063223617868856e-05,
      "loss": 0.5254,
      "step": 26162
    },
    {
      "epoch": 0.8037047276748687,
      "grad_norm": 0.34676799178123474,
      "learning_rate": 1.3062763569141285e-05,
      "loss": 0.5791,
      "step": 26163
    },
    {
      "epoch": 0.8037354468098178,
      "grad_norm": 0.36504411697387695,
      "learning_rate": 1.3062303513260414e-05,
      "loss": 0.5741,
      "step": 26164
    },
    {
      "epoch": 0.803766165944767,
      "grad_norm": 0.4885893762111664,
      "learning_rate": 1.3061843450227322e-05,
      "loss": 0.536,
      "step": 26165
    },
    {
      "epoch": 0.8037968850797161,
      "grad_norm": 0.33469223976135254,
      "learning_rate": 1.3061383380043077e-05,
      "loss": 0.4773,
      "step": 26166
    },
    {
      "epoch": 0.8038276042146654,
      "grad_norm": 0.34790417551994324,
      "learning_rate": 1.306092330270876e-05,
      "loss": 0.5168,
      "step": 26167
    },
    {
      "epoch": 0.8038583233496145,
      "grad_norm": 0.5030750036239624,
      "learning_rate": 1.3060463218225444e-05,
      "loss": 0.5441,
      "step": 26168
    },
    {
      "epoch": 0.8038890424845636,
      "grad_norm": 0.3610546290874481,
      "learning_rate": 1.30600031265942e-05,
      "loss": 0.5446,
      "step": 26169
    },
    {
      "epoch": 0.8039197616195128,
      "grad_norm": 0.36830395460128784,
      "learning_rate": 1.3059543027816105e-05,
      "loss": 0.4705,
      "step": 26170
    },
    {
      "epoch": 0.803950480754462,
      "grad_norm": 0.38100942969322205,
      "learning_rate": 1.3059082921892233e-05,
      "loss": 0.4993,
      "step": 26171
    },
    {
      "epoch": 0.8039811998894111,
      "grad_norm": 0.34796422719955444,
      "learning_rate": 1.3058622808823663e-05,
      "loss": 0.5547,
      "step": 26172
    },
    {
      "epoch": 0.8040119190243603,
      "grad_norm": 0.33574172854423523,
      "learning_rate": 1.305816268861146e-05,
      "loss": 0.5567,
      "step": 26173
    },
    {
      "epoch": 0.8040426381593094,
      "grad_norm": 0.3602200448513031,
      "learning_rate": 1.3057702561256708e-05,
      "loss": 0.4804,
      "step": 26174
    },
    {
      "epoch": 0.8040733572942586,
      "grad_norm": 0.4978688359260559,
      "learning_rate": 1.3057242426760479e-05,
      "loss": 0.6546,
      "step": 26175
    },
    {
      "epoch": 0.8041040764292078,
      "grad_norm": 0.36030077934265137,
      "learning_rate": 1.3056782285123846e-05,
      "loss": 0.4954,
      "step": 26176
    },
    {
      "epoch": 0.8041347955641569,
      "grad_norm": 0.3359937071800232,
      "learning_rate": 1.3056322136347884e-05,
      "loss": 0.492,
      "step": 26177
    },
    {
      "epoch": 0.804165514699106,
      "grad_norm": 0.38371211290359497,
      "learning_rate": 1.3055861980433669e-05,
      "loss": 0.5896,
      "step": 26178
    },
    {
      "epoch": 0.8041962338340553,
      "grad_norm": 0.40420010685920715,
      "learning_rate": 1.3055401817382274e-05,
      "loss": 0.5055,
      "step": 26179
    },
    {
      "epoch": 0.8042269529690044,
      "grad_norm": 0.35213908553123474,
      "learning_rate": 1.3054941647194775e-05,
      "loss": 0.5602,
      "step": 26180
    },
    {
      "epoch": 0.8042576721039536,
      "grad_norm": 0.3941834568977356,
      "learning_rate": 1.3054481469872247e-05,
      "loss": 0.492,
      "step": 26181
    },
    {
      "epoch": 0.8042883912389027,
      "grad_norm": 0.3993501365184784,
      "learning_rate": 1.3054021285415761e-05,
      "loss": 0.5977,
      "step": 26182
    },
    {
      "epoch": 0.8043191103738518,
      "grad_norm": 0.37732118368148804,
      "learning_rate": 1.3053561093826398e-05,
      "loss": 0.5892,
      "step": 26183
    },
    {
      "epoch": 0.8043498295088011,
      "grad_norm": 0.3478439748287201,
      "learning_rate": 1.305310089510523e-05,
      "loss": 0.5641,
      "step": 26184
    },
    {
      "epoch": 0.8043805486437502,
      "grad_norm": 0.3879576325416565,
      "learning_rate": 1.305264068925333e-05,
      "loss": 0.5004,
      "step": 26185
    },
    {
      "epoch": 0.8044112677786993,
      "grad_norm": 0.3448277711868286,
      "learning_rate": 1.3052180476271777e-05,
      "loss": 0.5618,
      "step": 26186
    },
    {
      "epoch": 0.8044419869136485,
      "grad_norm": 0.3645698130130768,
      "learning_rate": 1.3051720256161642e-05,
      "loss": 0.5525,
      "step": 26187
    },
    {
      "epoch": 0.8044727060485977,
      "grad_norm": 0.4729974567890167,
      "learning_rate": 1.3051260028924e-05,
      "loss": 0.5716,
      "step": 26188
    },
    {
      "epoch": 0.8045034251835468,
      "grad_norm": 0.36281731724739075,
      "learning_rate": 1.305079979455993e-05,
      "loss": 0.5964,
      "step": 26189
    },
    {
      "epoch": 0.804534144318496,
      "grad_norm": 0.36487072706222534,
      "learning_rate": 1.30503395530705e-05,
      "loss": 0.6258,
      "step": 26190
    },
    {
      "epoch": 0.8045648634534451,
      "grad_norm": 0.3819264769554138,
      "learning_rate": 1.304987930445679e-05,
      "loss": 0.5361,
      "step": 26191
    },
    {
      "epoch": 0.8045955825883944,
      "grad_norm": 0.41823437809944153,
      "learning_rate": 1.3049419048719876e-05,
      "loss": 0.5231,
      "step": 26192
    },
    {
      "epoch": 0.8046263017233435,
      "grad_norm": 0.47325199842453003,
      "learning_rate": 1.3048958785860828e-05,
      "loss": 0.5794,
      "step": 26193
    },
    {
      "epoch": 0.8046570208582926,
      "grad_norm": 0.5372823476791382,
      "learning_rate": 1.3048498515880726e-05,
      "loss": 0.4905,
      "step": 26194
    },
    {
      "epoch": 0.8046877399932418,
      "grad_norm": 0.39971253275871277,
      "learning_rate": 1.3048038238780643e-05,
      "loss": 0.5551,
      "step": 26195
    },
    {
      "epoch": 0.804718459128191,
      "grad_norm": 0.3594813942909241,
      "learning_rate": 1.3047577954561653e-05,
      "loss": 0.564,
      "step": 26196
    },
    {
      "epoch": 0.8047491782631401,
      "grad_norm": 0.36493849754333496,
      "learning_rate": 1.3047117663224833e-05,
      "loss": 0.5949,
      "step": 26197
    },
    {
      "epoch": 0.8047798973980893,
      "grad_norm": 0.3660360872745514,
      "learning_rate": 1.3046657364771256e-05,
      "loss": 0.595,
      "step": 26198
    },
    {
      "epoch": 0.8048106165330384,
      "grad_norm": 0.37878596782684326,
      "learning_rate": 1.3046197059201996e-05,
      "loss": 0.6114,
      "step": 26199
    },
    {
      "epoch": 0.8048413356679875,
      "grad_norm": 0.3497733175754547,
      "learning_rate": 1.3045736746518132e-05,
      "loss": 0.6151,
      "step": 26200
    },
    {
      "epoch": 0.8048720548029368,
      "grad_norm": 0.3922208845615387,
      "learning_rate": 1.304527642672074e-05,
      "loss": 0.5216,
      "step": 26201
    },
    {
      "epoch": 0.8049027739378859,
      "grad_norm": 0.3552209734916687,
      "learning_rate": 1.3044816099810886e-05,
      "loss": 0.5395,
      "step": 26202
    },
    {
      "epoch": 0.804933493072835,
      "grad_norm": 0.3840649425983429,
      "learning_rate": 1.3044355765789655e-05,
      "loss": 0.6501,
      "step": 26203
    },
    {
      "epoch": 0.8049642122077842,
      "grad_norm": 0.38087403774261475,
      "learning_rate": 1.304389542465812e-05,
      "loss": 0.6219,
      "step": 26204
    },
    {
      "epoch": 0.8049949313427334,
      "grad_norm": 0.3819849491119385,
      "learning_rate": 1.3043435076417353e-05,
      "loss": 0.5644,
      "step": 26205
    },
    {
      "epoch": 0.8050256504776826,
      "grad_norm": 0.39014339447021484,
      "learning_rate": 1.3042974721068429e-05,
      "loss": 0.5543,
      "step": 26206
    },
    {
      "epoch": 0.8050563696126317,
      "grad_norm": 0.3366779386997223,
      "learning_rate": 1.3042514358612426e-05,
      "loss": 0.5379,
      "step": 26207
    },
    {
      "epoch": 0.8050870887475808,
      "grad_norm": 0.34676599502563477,
      "learning_rate": 1.3042053989050418e-05,
      "loss": 0.5719,
      "step": 26208
    },
    {
      "epoch": 0.8051178078825301,
      "grad_norm": 0.4481033980846405,
      "learning_rate": 1.304159361238348e-05,
      "loss": 0.586,
      "step": 26209
    },
    {
      "epoch": 0.8051485270174792,
      "grad_norm": 0.43807855248451233,
      "learning_rate": 1.304113322861269e-05,
      "loss": 0.5269,
      "step": 26210
    },
    {
      "epoch": 0.8051792461524283,
      "grad_norm": 0.347015380859375,
      "learning_rate": 1.304067283773912e-05,
      "loss": 0.627,
      "step": 26211
    },
    {
      "epoch": 0.8052099652873775,
      "grad_norm": 0.3601894676685333,
      "learning_rate": 1.3040212439763847e-05,
      "loss": 0.5724,
      "step": 26212
    },
    {
      "epoch": 0.8052406844223267,
      "grad_norm": 0.3456360995769501,
      "learning_rate": 1.3039752034687943e-05,
      "loss": 0.5606,
      "step": 26213
    },
    {
      "epoch": 0.8052714035572758,
      "grad_norm": 0.3674483299255371,
      "learning_rate": 1.3039291622512488e-05,
      "loss": 0.5624,
      "step": 26214
    },
    {
      "epoch": 0.805302122692225,
      "grad_norm": 0.3995487689971924,
      "learning_rate": 1.3038831203238559e-05,
      "loss": 0.5758,
      "step": 26215
    },
    {
      "epoch": 0.8053328418271741,
      "grad_norm": 0.37542200088500977,
      "learning_rate": 1.303837077686722e-05,
      "loss": 0.6329,
      "step": 26216
    },
    {
      "epoch": 0.8053635609621234,
      "grad_norm": 0.39776766300201416,
      "learning_rate": 1.3037910343399557e-05,
      "loss": 0.5393,
      "step": 26217
    },
    {
      "epoch": 0.8053942800970725,
      "grad_norm": 0.4224998652935028,
      "learning_rate": 1.303744990283664e-05,
      "loss": 0.5237,
      "step": 26218
    },
    {
      "epoch": 0.8054249992320216,
      "grad_norm": 0.3587382435798645,
      "learning_rate": 1.3036989455179552e-05,
      "loss": 0.5405,
      "step": 26219
    },
    {
      "epoch": 0.8054557183669708,
      "grad_norm": 0.3469826579093933,
      "learning_rate": 1.3036529000429358e-05,
      "loss": 0.5155,
      "step": 26220
    },
    {
      "epoch": 0.80548643750192,
      "grad_norm": 0.3534233272075653,
      "learning_rate": 1.3036068538587143e-05,
      "loss": 0.5303,
      "step": 26221
    },
    {
      "epoch": 0.8055171566368691,
      "grad_norm": 0.36357125639915466,
      "learning_rate": 1.3035608069653974e-05,
      "loss": 0.5416,
      "step": 26222
    },
    {
      "epoch": 0.8055478757718183,
      "grad_norm": 0.3614296317100525,
      "learning_rate": 1.3035147593630932e-05,
      "loss": 0.5017,
      "step": 26223
    },
    {
      "epoch": 0.8055785949067674,
      "grad_norm": 0.351402223110199,
      "learning_rate": 1.3034687110519089e-05,
      "loss": 0.5689,
      "step": 26224
    },
    {
      "epoch": 0.8056093140417165,
      "grad_norm": 0.4191986620426178,
      "learning_rate": 1.3034226620319523e-05,
      "loss": 0.5439,
      "step": 26225
    },
    {
      "epoch": 0.8056400331766658,
      "grad_norm": 0.4044738709926605,
      "learning_rate": 1.3033766123033308e-05,
      "loss": 0.6235,
      "step": 26226
    },
    {
      "epoch": 0.8056707523116149,
      "grad_norm": 0.3714693784713745,
      "learning_rate": 1.3033305618661523e-05,
      "loss": 0.5336,
      "step": 26227
    },
    {
      "epoch": 0.805701471446564,
      "grad_norm": 0.346048504114151,
      "learning_rate": 1.3032845107205241e-05,
      "loss": 0.5203,
      "step": 26228
    },
    {
      "epoch": 0.8057321905815132,
      "grad_norm": 1.2490400075912476,
      "learning_rate": 1.3032384588665534e-05,
      "loss": 0.5734,
      "step": 26229
    },
    {
      "epoch": 0.8057629097164624,
      "grad_norm": 0.41657087206840515,
      "learning_rate": 1.3031924063043487e-05,
      "loss": 0.5711,
      "step": 26230
    },
    {
      "epoch": 0.8057936288514116,
      "grad_norm": 0.36753466725349426,
      "learning_rate": 1.3031463530340165e-05,
      "loss": 0.5534,
      "step": 26231
    },
    {
      "epoch": 0.8058243479863607,
      "grad_norm": 0.3476009666919708,
      "learning_rate": 1.3031002990556647e-05,
      "loss": 0.5323,
      "step": 26232
    },
    {
      "epoch": 0.8058550671213098,
      "grad_norm": 0.3581063747406006,
      "learning_rate": 1.3030542443694015e-05,
      "loss": 0.5128,
      "step": 26233
    },
    {
      "epoch": 0.8058857862562591,
      "grad_norm": 0.36520400643348694,
      "learning_rate": 1.3030081889753334e-05,
      "loss": 0.5186,
      "step": 26234
    },
    {
      "epoch": 0.8059165053912082,
      "grad_norm": 0.36810168623924255,
      "learning_rate": 1.3029621328735688e-05,
      "loss": 0.5307,
      "step": 26235
    },
    {
      "epoch": 0.8059472245261573,
      "grad_norm": 0.3962430953979492,
      "learning_rate": 1.3029160760642147e-05,
      "loss": 0.4835,
      "step": 26236
    },
    {
      "epoch": 0.8059779436611065,
      "grad_norm": 0.38799992203712463,
      "learning_rate": 1.3028700185473794e-05,
      "loss": 0.4842,
      "step": 26237
    },
    {
      "epoch": 0.8060086627960557,
      "grad_norm": 0.39240726828575134,
      "learning_rate": 1.3028239603231696e-05,
      "loss": 0.5753,
      "step": 26238
    },
    {
      "epoch": 0.8060393819310048,
      "grad_norm": 0.38567131757736206,
      "learning_rate": 1.3027779013916936e-05,
      "loss": 0.5616,
      "step": 26239
    },
    {
      "epoch": 0.806070101065954,
      "grad_norm": 0.3760822117328644,
      "learning_rate": 1.3027318417530586e-05,
      "loss": 0.5594,
      "step": 26240
    },
    {
      "epoch": 0.8061008202009031,
      "grad_norm": 0.3950330317020416,
      "learning_rate": 1.3026857814073721e-05,
      "loss": 0.6016,
      "step": 26241
    },
    {
      "epoch": 0.8061315393358524,
      "grad_norm": 0.354851633310318,
      "learning_rate": 1.3026397203547421e-05,
      "loss": 0.5425,
      "step": 26242
    },
    {
      "epoch": 0.8061622584708015,
      "grad_norm": 0.365953266620636,
      "learning_rate": 1.3025936585952756e-05,
      "loss": 0.5183,
      "step": 26243
    },
    {
      "epoch": 0.8061929776057506,
      "grad_norm": 0.3861527144908905,
      "learning_rate": 1.3025475961290806e-05,
      "loss": 0.5637,
      "step": 26244
    },
    {
      "epoch": 0.8062236967406998,
      "grad_norm": 0.3649355173110962,
      "learning_rate": 1.3025015329562645e-05,
      "loss": 0.5151,
      "step": 26245
    },
    {
      "epoch": 0.8062544158756489,
      "grad_norm": 0.3794938921928406,
      "learning_rate": 1.302455469076935e-05,
      "loss": 0.5429,
      "step": 26246
    },
    {
      "epoch": 0.8062851350105981,
      "grad_norm": 0.36975228786468506,
      "learning_rate": 1.3024094044911994e-05,
      "loss": 0.514,
      "step": 26247
    },
    {
      "epoch": 0.8063158541455473,
      "grad_norm": 0.3514556288719177,
      "learning_rate": 1.302363339199166e-05,
      "loss": 0.6141,
      "step": 26248
    },
    {
      "epoch": 0.8063465732804964,
      "grad_norm": 0.4300982654094696,
      "learning_rate": 1.3023172732009416e-05,
      "loss": 0.5451,
      "step": 26249
    },
    {
      "epoch": 0.8063772924154455,
      "grad_norm": 0.36475369334220886,
      "learning_rate": 1.302271206496634e-05,
      "loss": 0.5807,
      "step": 26250
    },
    {
      "epoch": 0.8064080115503948,
      "grad_norm": 0.34604331851005554,
      "learning_rate": 1.3022251390863511e-05,
      "loss": 0.5997,
      "step": 26251
    },
    {
      "epoch": 0.8064387306853439,
      "grad_norm": 0.4339134991168976,
      "learning_rate": 1.3021790709702002e-05,
      "loss": 0.5491,
      "step": 26252
    },
    {
      "epoch": 0.806469449820293,
      "grad_norm": 0.3714050352573395,
      "learning_rate": 1.3021330021482889e-05,
      "loss": 0.5728,
      "step": 26253
    },
    {
      "epoch": 0.8065001689552422,
      "grad_norm": 0.4229991137981415,
      "learning_rate": 1.3020869326207248e-05,
      "loss": 0.6213,
      "step": 26254
    },
    {
      "epoch": 0.8065308880901914,
      "grad_norm": 2.1319212913513184,
      "learning_rate": 1.302040862387616e-05,
      "loss": 0.5435,
      "step": 26255
    },
    {
      "epoch": 0.8065616072251406,
      "grad_norm": 0.3969366252422333,
      "learning_rate": 1.3019947914490691e-05,
      "loss": 0.5429,
      "step": 26256
    },
    {
      "epoch": 0.8065923263600897,
      "grad_norm": 0.3642822206020355,
      "learning_rate": 1.3019487198051928e-05,
      "loss": 0.5327,
      "step": 26257
    },
    {
      "epoch": 0.8066230454950388,
      "grad_norm": 0.3263793885707855,
      "learning_rate": 1.3019026474560939e-05,
      "loss": 0.5879,
      "step": 26258
    },
    {
      "epoch": 0.8066537646299881,
      "grad_norm": 0.4166395366191864,
      "learning_rate": 1.3018565744018803e-05,
      "loss": 0.637,
      "step": 26259
    },
    {
      "epoch": 0.8066844837649372,
      "grad_norm": 0.39320409297943115,
      "learning_rate": 1.3018105006426598e-05,
      "loss": 0.5853,
      "step": 26260
    },
    {
      "epoch": 0.8067152028998863,
      "grad_norm": 0.3255317509174347,
      "learning_rate": 1.3017644261785396e-05,
      "loss": 0.5394,
      "step": 26261
    },
    {
      "epoch": 0.8067459220348355,
      "grad_norm": 0.35818132758140564,
      "learning_rate": 1.3017183510096275e-05,
      "loss": 0.5608,
      "step": 26262
    },
    {
      "epoch": 0.8067766411697846,
      "grad_norm": 0.3707267642021179,
      "learning_rate": 1.3016722751360309e-05,
      "loss": 0.5753,
      "step": 26263
    },
    {
      "epoch": 0.8068073603047338,
      "grad_norm": 0.8200882077217102,
      "learning_rate": 1.301626198557858e-05,
      "loss": 0.5981,
      "step": 26264
    },
    {
      "epoch": 0.806838079439683,
      "grad_norm": 0.37741178274154663,
      "learning_rate": 1.3015801212752156e-05,
      "loss": 0.5609,
      "step": 26265
    },
    {
      "epoch": 0.8068687985746321,
      "grad_norm": 0.3725721538066864,
      "learning_rate": 1.3015340432882124e-05,
      "loss": 0.5925,
      "step": 26266
    },
    {
      "epoch": 0.8068995177095813,
      "grad_norm": 0.35568422079086304,
      "learning_rate": 1.301487964596955e-05,
      "loss": 0.5644,
      "step": 26267
    },
    {
      "epoch": 0.8069302368445305,
      "grad_norm": 0.380314439535141,
      "learning_rate": 1.3014418852015513e-05,
      "loss": 0.5009,
      "step": 26268
    },
    {
      "epoch": 0.8069609559794796,
      "grad_norm": 0.3544039726257324,
      "learning_rate": 1.3013958051021093e-05,
      "loss": 0.5912,
      "step": 26269
    },
    {
      "epoch": 0.8069916751144288,
      "grad_norm": 0.9892155528068542,
      "learning_rate": 1.3013497242987363e-05,
      "loss": 0.5895,
      "step": 26270
    },
    {
      "epoch": 0.8070223942493779,
      "grad_norm": 0.3749963939189911,
      "learning_rate": 1.30130364279154e-05,
      "loss": 0.5706,
      "step": 26271
    },
    {
      "epoch": 0.8070531133843271,
      "grad_norm": 0.4023978114128113,
      "learning_rate": 1.301257560580628e-05,
      "loss": 0.5451,
      "step": 26272
    },
    {
      "epoch": 0.8070838325192763,
      "grad_norm": 0.3741403818130493,
      "learning_rate": 1.3012114776661078e-05,
      "loss": 0.5553,
      "step": 26273
    },
    {
      "epoch": 0.8071145516542254,
      "grad_norm": 0.5140959024429321,
      "learning_rate": 1.301165394048087e-05,
      "loss": 0.5552,
      "step": 26274
    },
    {
      "epoch": 0.8071452707891745,
      "grad_norm": 0.3407035768032074,
      "learning_rate": 1.3011193097266737e-05,
      "loss": 0.4742,
      "step": 26275
    },
    {
      "epoch": 0.8071759899241238,
      "grad_norm": 0.39074766635894775,
      "learning_rate": 1.301073224701975e-05,
      "loss": 0.5629,
      "step": 26276
    },
    {
      "epoch": 0.8072067090590729,
      "grad_norm": 0.371873140335083,
      "learning_rate": 1.301027138974099e-05,
      "loss": 0.6285,
      "step": 26277
    },
    {
      "epoch": 0.8072374281940221,
      "grad_norm": 0.32973986864089966,
      "learning_rate": 1.300981052543153e-05,
      "loss": 0.4187,
      "step": 26278
    },
    {
      "epoch": 0.8072681473289712,
      "grad_norm": 0.38441959023475647,
      "learning_rate": 1.3009349654092447e-05,
      "loss": 0.6055,
      "step": 26279
    },
    {
      "epoch": 0.8072988664639204,
      "grad_norm": 0.38520804047584534,
      "learning_rate": 1.3008888775724817e-05,
      "loss": 0.5275,
      "step": 26280
    },
    {
      "epoch": 0.8073295855988696,
      "grad_norm": 0.4668167233467102,
      "learning_rate": 1.3008427890329715e-05,
      "loss": 0.6372,
      "step": 26281
    },
    {
      "epoch": 0.8073603047338187,
      "grad_norm": 0.4099523723125458,
      "learning_rate": 1.3007966997908223e-05,
      "loss": 0.5475,
      "step": 26282
    },
    {
      "epoch": 0.8073910238687678,
      "grad_norm": 0.36631104350090027,
      "learning_rate": 1.3007506098461416e-05,
      "loss": 0.5622,
      "step": 26283
    },
    {
      "epoch": 0.807421743003717,
      "grad_norm": 0.4290277063846588,
      "learning_rate": 1.3007045191990364e-05,
      "loss": 0.5694,
      "step": 26284
    },
    {
      "epoch": 0.8074524621386662,
      "grad_norm": 0.4658887982368469,
      "learning_rate": 1.300658427849615e-05,
      "loss": 0.5024,
      "step": 26285
    },
    {
      "epoch": 0.8074831812736153,
      "grad_norm": 0.34043169021606445,
      "learning_rate": 1.3006123357979848e-05,
      "loss": 0.5207,
      "step": 26286
    },
    {
      "epoch": 0.8075139004085645,
      "grad_norm": 0.3901040554046631,
      "learning_rate": 1.3005662430442536e-05,
      "loss": 0.4945,
      "step": 26287
    },
    {
      "epoch": 0.8075446195435136,
      "grad_norm": 0.36909550428390503,
      "learning_rate": 1.3005201495885286e-05,
      "loss": 0.4783,
      "step": 26288
    },
    {
      "epoch": 0.8075753386784628,
      "grad_norm": 0.3665211796760559,
      "learning_rate": 1.3004740554309183e-05,
      "loss": 0.5604,
      "step": 26289
    },
    {
      "epoch": 0.807606057813412,
      "grad_norm": 0.3449922800064087,
      "learning_rate": 1.3004279605715295e-05,
      "loss": 0.57,
      "step": 26290
    },
    {
      "epoch": 0.8076367769483611,
      "grad_norm": 0.3206842243671417,
      "learning_rate": 1.3003818650104706e-05,
      "loss": 0.5172,
      "step": 26291
    },
    {
      "epoch": 0.8076674960833103,
      "grad_norm": 0.3982529640197754,
      "learning_rate": 1.3003357687478483e-05,
      "loss": 0.6048,
      "step": 26292
    },
    {
      "epoch": 0.8076982152182595,
      "grad_norm": 0.33728912472724915,
      "learning_rate": 1.3002896717837712e-05,
      "loss": 0.5122,
      "step": 26293
    },
    {
      "epoch": 0.8077289343532086,
      "grad_norm": 0.35261106491088867,
      "learning_rate": 1.3002435741183468e-05,
      "loss": 0.5546,
      "step": 26294
    },
    {
      "epoch": 0.8077596534881578,
      "grad_norm": 0.3608912229537964,
      "learning_rate": 1.3001974757516822e-05,
      "loss": 0.5086,
      "step": 26295
    },
    {
      "epoch": 0.8077903726231069,
      "grad_norm": 0.3399486541748047,
      "learning_rate": 1.3001513766838856e-05,
      "loss": 0.4999,
      "step": 26296
    },
    {
      "epoch": 0.807821091758056,
      "grad_norm": 0.40286314487457275,
      "learning_rate": 1.3001052769150643e-05,
      "loss": 0.5487,
      "step": 26297
    },
    {
      "epoch": 0.8078518108930053,
      "grad_norm": 0.36024102568626404,
      "learning_rate": 1.3000591764453265e-05,
      "loss": 0.5752,
      "step": 26298
    },
    {
      "epoch": 0.8078825300279544,
      "grad_norm": 0.3642594516277313,
      "learning_rate": 1.3000130752747789e-05,
      "loss": 0.5376,
      "step": 26299
    },
    {
      "epoch": 0.8079132491629035,
      "grad_norm": 0.40295639634132385,
      "learning_rate": 1.2999669734035303e-05,
      "loss": 0.5943,
      "step": 26300
    },
    {
      "epoch": 0.8079439682978528,
      "grad_norm": 0.3413909375667572,
      "learning_rate": 1.299920870831688e-05,
      "loss": 0.6137,
      "step": 26301
    },
    {
      "epoch": 0.8079746874328019,
      "grad_norm": 0.3756406009197235,
      "learning_rate": 1.2998747675593592e-05,
      "loss": 0.5672,
      "step": 26302
    },
    {
      "epoch": 0.8080054065677511,
      "grad_norm": 0.36127954721450806,
      "learning_rate": 1.2998286635866524e-05,
      "loss": 0.5861,
      "step": 26303
    },
    {
      "epoch": 0.8080361257027002,
      "grad_norm": 0.32230839133262634,
      "learning_rate": 1.2997825589136744e-05,
      "loss": 0.4741,
      "step": 26304
    },
    {
      "epoch": 0.8080668448376493,
      "grad_norm": 0.39252856373786926,
      "learning_rate": 1.2997364535405335e-05,
      "loss": 0.5421,
      "step": 26305
    },
    {
      "epoch": 0.8080975639725986,
      "grad_norm": 0.38859912753105164,
      "learning_rate": 1.299690347467337e-05,
      "loss": 0.5028,
      "step": 26306
    },
    {
      "epoch": 0.8081282831075477,
      "grad_norm": 0.36077508330345154,
      "learning_rate": 1.299644240694193e-05,
      "loss": 0.5906,
      "step": 26307
    },
    {
      "epoch": 0.8081590022424968,
      "grad_norm": 0.5037927627563477,
      "learning_rate": 1.2995981332212089e-05,
      "loss": 0.5641,
      "step": 26308
    },
    {
      "epoch": 0.808189721377446,
      "grad_norm": 0.3409503698348999,
      "learning_rate": 1.2995520250484923e-05,
      "loss": 0.5466,
      "step": 26309
    },
    {
      "epoch": 0.8082204405123952,
      "grad_norm": 0.3528132140636444,
      "learning_rate": 1.299505916176151e-05,
      "loss": 0.538,
      "step": 26310
    },
    {
      "epoch": 0.8082511596473443,
      "grad_norm": 0.36082446575164795,
      "learning_rate": 1.2994598066042929e-05,
      "loss": 0.6009,
      "step": 26311
    },
    {
      "epoch": 0.8082818787822935,
      "grad_norm": 0.40234968066215515,
      "learning_rate": 1.2994136963330256e-05,
      "loss": 0.6248,
      "step": 26312
    },
    {
      "epoch": 0.8083125979172426,
      "grad_norm": 0.44480109214782715,
      "learning_rate": 1.2993675853624565e-05,
      "loss": 0.6477,
      "step": 26313
    },
    {
      "epoch": 0.8083433170521918,
      "grad_norm": 0.345110148191452,
      "learning_rate": 1.2993214736926936e-05,
      "loss": 0.4832,
      "step": 26314
    },
    {
      "epoch": 0.808374036187141,
      "grad_norm": 0.46998482942581177,
      "learning_rate": 1.2992753613238442e-05,
      "loss": 0.586,
      "step": 26315
    },
    {
      "epoch": 0.8084047553220901,
      "grad_norm": 0.39987924695014954,
      "learning_rate": 1.2992292482560166e-05,
      "loss": 0.6204,
      "step": 26316
    },
    {
      "epoch": 0.8084354744570393,
      "grad_norm": 0.38310760259628296,
      "learning_rate": 1.2991831344893178e-05,
      "loss": 0.571,
      "step": 26317
    },
    {
      "epoch": 0.8084661935919885,
      "grad_norm": 0.3928704857826233,
      "learning_rate": 1.2991370200238564e-05,
      "loss": 0.5458,
      "step": 26318
    },
    {
      "epoch": 0.8084969127269376,
      "grad_norm": 0.37309587001800537,
      "learning_rate": 1.2990909048597395e-05,
      "loss": 0.5808,
      "step": 26319
    },
    {
      "epoch": 0.8085276318618868,
      "grad_norm": 0.3715684711933136,
      "learning_rate": 1.2990447889970747e-05,
      "loss": 0.6439,
      "step": 26320
    },
    {
      "epoch": 0.8085583509968359,
      "grad_norm": 0.360910028219223,
      "learning_rate": 1.29899867243597e-05,
      "loss": 0.5646,
      "step": 26321
    },
    {
      "epoch": 0.808589070131785,
      "grad_norm": 0.3752129077911377,
      "learning_rate": 1.2989525551765329e-05,
      "loss": 0.5117,
      "step": 26322
    },
    {
      "epoch": 0.8086197892667343,
      "grad_norm": 0.3989008963108063,
      "learning_rate": 1.2989064372188715e-05,
      "loss": 0.5585,
      "step": 26323
    },
    {
      "epoch": 0.8086505084016834,
      "grad_norm": 0.3436627984046936,
      "learning_rate": 1.298860318563093e-05,
      "loss": 0.543,
      "step": 26324
    },
    {
      "epoch": 0.8086812275366325,
      "grad_norm": 0.36354485154151917,
      "learning_rate": 1.2988141992093056e-05,
      "loss": 0.5593,
      "step": 26325
    },
    {
      "epoch": 0.8087119466715817,
      "grad_norm": 0.5585031509399414,
      "learning_rate": 1.2987680791576165e-05,
      "loss": 0.5655,
      "step": 26326
    },
    {
      "epoch": 0.8087426658065309,
      "grad_norm": 0.4120101034641266,
      "learning_rate": 1.2987219584081339e-05,
      "loss": 0.6,
      "step": 26327
    },
    {
      "epoch": 0.8087733849414801,
      "grad_norm": 0.35381197929382324,
      "learning_rate": 1.2986758369609651e-05,
      "loss": 0.5473,
      "step": 26328
    },
    {
      "epoch": 0.8088041040764292,
      "grad_norm": 0.35954567790031433,
      "learning_rate": 1.2986297148162183e-05,
      "loss": 0.6057,
      "step": 26329
    },
    {
      "epoch": 0.8088348232113783,
      "grad_norm": 0.35674044489860535,
      "learning_rate": 1.2985835919740008e-05,
      "loss": 0.6093,
      "step": 26330
    },
    {
      "epoch": 0.8088655423463276,
      "grad_norm": 0.3696783483028412,
      "learning_rate": 1.2985374684344203e-05,
      "loss": 0.572,
      "step": 26331
    },
    {
      "epoch": 0.8088962614812767,
      "grad_norm": 0.32367846369743347,
      "learning_rate": 1.298491344197585e-05,
      "loss": 0.4889,
      "step": 26332
    },
    {
      "epoch": 0.8089269806162258,
      "grad_norm": 0.35038328170776367,
      "learning_rate": 1.2984452192636022e-05,
      "loss": 0.4857,
      "step": 26333
    },
    {
      "epoch": 0.808957699751175,
      "grad_norm": 0.37545809149742126,
      "learning_rate": 1.2983990936325796e-05,
      "loss": 0.5241,
      "step": 26334
    },
    {
      "epoch": 0.8089884188861242,
      "grad_norm": 0.35379937291145325,
      "learning_rate": 1.2983529673046252e-05,
      "loss": 0.5247,
      "step": 26335
    },
    {
      "epoch": 0.8090191380210733,
      "grad_norm": 0.38808172941207886,
      "learning_rate": 1.2983068402798465e-05,
      "loss": 0.5723,
      "step": 26336
    },
    {
      "epoch": 0.8090498571560225,
      "grad_norm": 0.420814573764801,
      "learning_rate": 1.2982607125583515e-05,
      "loss": 0.5781,
      "step": 26337
    },
    {
      "epoch": 0.8090805762909716,
      "grad_norm": 0.33358269929885864,
      "learning_rate": 1.2982145841402476e-05,
      "loss": 0.5932,
      "step": 26338
    },
    {
      "epoch": 0.8091112954259208,
      "grad_norm": 0.35613033175468445,
      "learning_rate": 1.2981684550256429e-05,
      "loss": 0.6279,
      "step": 26339
    },
    {
      "epoch": 0.80914201456087,
      "grad_norm": 0.6786279678344727,
      "learning_rate": 1.2981223252146446e-05,
      "loss": 0.5746,
      "step": 26340
    },
    {
      "epoch": 0.8091727336958191,
      "grad_norm": 0.3769492208957672,
      "learning_rate": 1.2980761947073613e-05,
      "loss": 0.5314,
      "step": 26341
    },
    {
      "epoch": 0.8092034528307683,
      "grad_norm": 0.36453139781951904,
      "learning_rate": 1.2980300635038998e-05,
      "loss": 0.5235,
      "step": 26342
    },
    {
      "epoch": 0.8092341719657175,
      "grad_norm": 0.3504563868045807,
      "learning_rate": 1.2979839316043685e-05,
      "loss": 0.5143,
      "step": 26343
    },
    {
      "epoch": 0.8092648911006666,
      "grad_norm": 0.4593275785446167,
      "learning_rate": 1.2979377990088748e-05,
      "loss": 0.5181,
      "step": 26344
    },
    {
      "epoch": 0.8092956102356158,
      "grad_norm": 0.343403697013855,
      "learning_rate": 1.2978916657175268e-05,
      "loss": 0.5199,
      "step": 26345
    },
    {
      "epoch": 0.8093263293705649,
      "grad_norm": 0.37772324681282043,
      "learning_rate": 1.2978455317304317e-05,
      "loss": 0.5475,
      "step": 26346
    },
    {
      "epoch": 0.809357048505514,
      "grad_norm": 0.3801419138908386,
      "learning_rate": 1.2977993970476979e-05,
      "loss": 0.5361,
      "step": 26347
    },
    {
      "epoch": 0.8093877676404633,
      "grad_norm": 0.3731255829334259,
      "learning_rate": 1.2977532616694326e-05,
      "loss": 0.5706,
      "step": 26348
    },
    {
      "epoch": 0.8094184867754124,
      "grad_norm": 0.49654605984687805,
      "learning_rate": 1.2977071255957436e-05,
      "loss": 0.4813,
      "step": 26349
    },
    {
      "epoch": 0.8094492059103615,
      "grad_norm": 0.34187424182891846,
      "learning_rate": 1.2976609888267394e-05,
      "loss": 0.579,
      "step": 26350
    },
    {
      "epoch": 0.8094799250453107,
      "grad_norm": 0.3656806945800781,
      "learning_rate": 1.2976148513625266e-05,
      "loss": 0.54,
      "step": 26351
    },
    {
      "epoch": 0.8095106441802599,
      "grad_norm": 0.37535804510116577,
      "learning_rate": 1.2975687132032138e-05,
      "loss": 0.5417,
      "step": 26352
    },
    {
      "epoch": 0.8095413633152091,
      "grad_norm": 0.3643534779548645,
      "learning_rate": 1.297522574348908e-05,
      "loss": 0.5631,
      "step": 26353
    },
    {
      "epoch": 0.8095720824501582,
      "grad_norm": 0.38546738028526306,
      "learning_rate": 1.2974764347997179e-05,
      "loss": 0.5468,
      "step": 26354
    },
    {
      "epoch": 0.8096028015851073,
      "grad_norm": 0.41131043434143066,
      "learning_rate": 1.2974302945557508e-05,
      "loss": 0.548,
      "step": 26355
    },
    {
      "epoch": 0.8096335207200566,
      "grad_norm": 0.3809976875782013,
      "learning_rate": 1.2973841536171144e-05,
      "loss": 0.5961,
      "step": 26356
    },
    {
      "epoch": 0.8096642398550057,
      "grad_norm": 0.36341017484664917,
      "learning_rate": 1.2973380119839165e-05,
      "loss": 0.566,
      "step": 26357
    },
    {
      "epoch": 0.8096949589899548,
      "grad_norm": 0.3617106080055237,
      "learning_rate": 1.297291869656265e-05,
      "loss": 0.5716,
      "step": 26358
    },
    {
      "epoch": 0.809725678124904,
      "grad_norm": 0.34949472546577454,
      "learning_rate": 1.2972457266342677e-05,
      "loss": 0.4913,
      "step": 26359
    },
    {
      "epoch": 0.8097563972598532,
      "grad_norm": 0.35772091150283813,
      "learning_rate": 1.297199582918032e-05,
      "loss": 0.5918,
      "step": 26360
    },
    {
      "epoch": 0.8097871163948023,
      "grad_norm": 0.40720921754837036,
      "learning_rate": 1.297153438507666e-05,
      "loss": 0.478,
      "step": 26361
    },
    {
      "epoch": 0.8098178355297515,
      "grad_norm": 0.3368711769580841,
      "learning_rate": 1.2971072934032774e-05,
      "loss": 0.4303,
      "step": 26362
    },
    {
      "epoch": 0.8098485546647006,
      "grad_norm": 0.35987818241119385,
      "learning_rate": 1.2970611476049739e-05,
      "loss": 0.549,
      "step": 26363
    },
    {
      "epoch": 0.8098792737996499,
      "grad_norm": 0.40766483545303345,
      "learning_rate": 1.2970150011128637e-05,
      "loss": 0.5048,
      "step": 26364
    },
    {
      "epoch": 0.809909992934599,
      "grad_norm": 0.3607076406478882,
      "learning_rate": 1.2969688539270537e-05,
      "loss": 0.5574,
      "step": 26365
    },
    {
      "epoch": 0.8099407120695481,
      "grad_norm": 0.3565358817577362,
      "learning_rate": 1.2969227060476526e-05,
      "loss": 0.4964,
      "step": 26366
    },
    {
      "epoch": 0.8099714312044973,
      "grad_norm": 0.3727165460586548,
      "learning_rate": 1.2968765574747675e-05,
      "loss": 0.5178,
      "step": 26367
    },
    {
      "epoch": 0.8100021503394464,
      "grad_norm": 0.39156100153923035,
      "learning_rate": 1.2968304082085065e-05,
      "loss": 0.5006,
      "step": 26368
    },
    {
      "epoch": 0.8100328694743956,
      "grad_norm": 0.3437104821205139,
      "learning_rate": 1.2967842582489775e-05,
      "loss": 0.5329,
      "step": 26369
    },
    {
      "epoch": 0.8100635886093448,
      "grad_norm": 0.3287113308906555,
      "learning_rate": 1.2967381075962882e-05,
      "loss": 0.5884,
      "step": 26370
    },
    {
      "epoch": 0.8100943077442939,
      "grad_norm": 0.3492245674133301,
      "learning_rate": 1.296691956250546e-05,
      "loss": 0.4598,
      "step": 26371
    },
    {
      "epoch": 0.810125026879243,
      "grad_norm": 0.33483439683914185,
      "learning_rate": 1.2966458042118593e-05,
      "loss": 0.5274,
      "step": 26372
    },
    {
      "epoch": 0.8101557460141923,
      "grad_norm": 0.3432069420814514,
      "learning_rate": 1.2965996514803354e-05,
      "loss": 0.5544,
      "step": 26373
    },
    {
      "epoch": 0.8101864651491414,
      "grad_norm": 0.3242409825325012,
      "learning_rate": 1.2965534980560823e-05,
      "loss": 0.4676,
      "step": 26374
    },
    {
      "epoch": 0.8102171842840905,
      "grad_norm": 0.37942391633987427,
      "learning_rate": 1.296507343939208e-05,
      "loss": 0.5614,
      "step": 26375
    },
    {
      "epoch": 0.8102479034190397,
      "grad_norm": 0.403598815202713,
      "learning_rate": 1.29646118912982e-05,
      "loss": 0.5785,
      "step": 26376
    },
    {
      "epoch": 0.8102786225539889,
      "grad_norm": 0.4394424557685852,
      "learning_rate": 1.2964150336280263e-05,
      "loss": 0.6241,
      "step": 26377
    },
    {
      "epoch": 0.8103093416889381,
      "grad_norm": 0.3628803491592407,
      "learning_rate": 1.2963688774339343e-05,
      "loss": 0.5805,
      "step": 26378
    },
    {
      "epoch": 0.8103400608238872,
      "grad_norm": 0.4794370234012604,
      "learning_rate": 1.2963227205476522e-05,
      "loss": 0.6002,
      "step": 26379
    },
    {
      "epoch": 0.8103707799588363,
      "grad_norm": 0.3566838800907135,
      "learning_rate": 1.296276562969288e-05,
      "loss": 0.5959,
      "step": 26380
    },
    {
      "epoch": 0.8104014990937856,
      "grad_norm": 0.3458081781864166,
      "learning_rate": 1.2962304046989489e-05,
      "loss": 0.4802,
      "step": 26381
    },
    {
      "epoch": 0.8104322182287347,
      "grad_norm": 0.4249017834663391,
      "learning_rate": 1.2961842457367432e-05,
      "loss": 0.5007,
      "step": 26382
    },
    {
      "epoch": 0.8104629373636838,
      "grad_norm": 0.3667864203453064,
      "learning_rate": 1.2961380860827783e-05,
      "loss": 0.4958,
      "step": 26383
    },
    {
      "epoch": 0.810493656498633,
      "grad_norm": 0.39660921692848206,
      "learning_rate": 1.2960919257371622e-05,
      "loss": 0.5127,
      "step": 26384
    },
    {
      "epoch": 0.8105243756335822,
      "grad_norm": 0.38112813234329224,
      "learning_rate": 1.2960457647000028e-05,
      "loss": 0.6122,
      "step": 26385
    },
    {
      "epoch": 0.8105550947685313,
      "grad_norm": 0.3655250370502472,
      "learning_rate": 1.2959996029714079e-05,
      "loss": 0.5702,
      "step": 26386
    },
    {
      "epoch": 0.8105858139034805,
      "grad_norm": 0.3464469015598297,
      "learning_rate": 1.2959534405514852e-05,
      "loss": 0.5618,
      "step": 26387
    },
    {
      "epoch": 0.8106165330384296,
      "grad_norm": 0.3917478919029236,
      "learning_rate": 1.2959072774403427e-05,
      "loss": 0.4267,
      "step": 26388
    },
    {
      "epoch": 0.8106472521733789,
      "grad_norm": 0.3730996251106262,
      "learning_rate": 1.2958611136380878e-05,
      "loss": 0.6136,
      "step": 26389
    },
    {
      "epoch": 0.810677971308328,
      "grad_norm": 0.36949342489242554,
      "learning_rate": 1.2958149491448287e-05,
      "loss": 0.6091,
      "step": 26390
    },
    {
      "epoch": 0.8107086904432771,
      "grad_norm": 0.37642398476600647,
      "learning_rate": 1.2957687839606732e-05,
      "loss": 0.6213,
      "step": 26391
    },
    {
      "epoch": 0.8107394095782263,
      "grad_norm": 0.37730175256729126,
      "learning_rate": 1.295722618085729e-05,
      "loss": 0.5827,
      "step": 26392
    },
    {
      "epoch": 0.8107701287131754,
      "grad_norm": 0.3733924925327301,
      "learning_rate": 1.2956764515201042e-05,
      "loss": 0.5765,
      "step": 26393
    },
    {
      "epoch": 0.8108008478481246,
      "grad_norm": 0.355344295501709,
      "learning_rate": 1.295630284263906e-05,
      "loss": 0.5821,
      "step": 26394
    },
    {
      "epoch": 0.8108315669830738,
      "grad_norm": 0.3903282582759857,
      "learning_rate": 1.295584116317243e-05,
      "loss": 0.5312,
      "step": 26395
    },
    {
      "epoch": 0.8108622861180229,
      "grad_norm": 0.3222629725933075,
      "learning_rate": 1.2955379476802224e-05,
      "loss": 0.5252,
      "step": 26396
    },
    {
      "epoch": 0.810893005252972,
      "grad_norm": 0.38473957777023315,
      "learning_rate": 1.2954917783529525e-05,
      "loss": 0.5738,
      "step": 26397
    },
    {
      "epoch": 0.8109237243879213,
      "grad_norm": 0.37645223736763,
      "learning_rate": 1.2954456083355407e-05,
      "loss": 0.5932,
      "step": 26398
    },
    {
      "epoch": 0.8109544435228704,
      "grad_norm": 0.42383983731269836,
      "learning_rate": 1.2953994376280951e-05,
      "loss": 0.6152,
      "step": 26399
    },
    {
      "epoch": 0.8109851626578195,
      "grad_norm": 0.3605952560901642,
      "learning_rate": 1.2953532662307238e-05,
      "loss": 0.5709,
      "step": 26400
    },
    {
      "epoch": 0.8110158817927687,
      "grad_norm": 0.4155566096305847,
      "learning_rate": 1.2953070941435338e-05,
      "loss": 0.6133,
      "step": 26401
    },
    {
      "epoch": 0.8110466009277179,
      "grad_norm": 0.41319355368614197,
      "learning_rate": 1.2952609213666338e-05,
      "loss": 0.5096,
      "step": 26402
    },
    {
      "epoch": 0.8110773200626671,
      "grad_norm": 0.6090933680534363,
      "learning_rate": 1.2952147479001312e-05,
      "loss": 0.4993,
      "step": 26403
    },
    {
      "epoch": 0.8111080391976162,
      "grad_norm": 0.3590015769004822,
      "learning_rate": 1.295168573744134e-05,
      "loss": 0.5549,
      "step": 26404
    },
    {
      "epoch": 0.8111387583325653,
      "grad_norm": 0.6072195768356323,
      "learning_rate": 1.2951223988987497e-05,
      "loss": 0.5314,
      "step": 26405
    },
    {
      "epoch": 0.8111694774675146,
      "grad_norm": 0.4618387520313263,
      "learning_rate": 1.2950762233640868e-05,
      "loss": 0.5276,
      "step": 26406
    },
    {
      "epoch": 0.8112001966024637,
      "grad_norm": 0.33752164244651794,
      "learning_rate": 1.2950300471402526e-05,
      "loss": 0.5752,
      "step": 26407
    },
    {
      "epoch": 0.8112309157374128,
      "grad_norm": 0.3628162443637848,
      "learning_rate": 1.2949838702273551e-05,
      "loss": 0.6347,
      "step": 26408
    },
    {
      "epoch": 0.811261634872362,
      "grad_norm": 0.3517531454563141,
      "learning_rate": 1.2949376926255022e-05,
      "loss": 0.5017,
      "step": 26409
    },
    {
      "epoch": 0.8112923540073111,
      "grad_norm": 0.3824778199195862,
      "learning_rate": 1.2948915143348016e-05,
      "loss": 0.557,
      "step": 26410
    },
    {
      "epoch": 0.8113230731422603,
      "grad_norm": 0.39080628752708435,
      "learning_rate": 1.2948453353553613e-05,
      "loss": 0.544,
      "step": 26411
    },
    {
      "epoch": 0.8113537922772095,
      "grad_norm": 0.3370012044906616,
      "learning_rate": 1.2947991556872893e-05,
      "loss": 0.4743,
      "step": 26412
    },
    {
      "epoch": 0.8113845114121586,
      "grad_norm": 0.3486691415309906,
      "learning_rate": 1.2947529753306933e-05,
      "loss": 0.5406,
      "step": 26413
    },
    {
      "epoch": 0.8114152305471078,
      "grad_norm": 0.3955516219139099,
      "learning_rate": 1.294706794285681e-05,
      "loss": 0.5893,
      "step": 26414
    },
    {
      "epoch": 0.811445949682057,
      "grad_norm": 0.38106635212898254,
      "learning_rate": 1.2946606125523604e-05,
      "loss": 0.6065,
      "step": 26415
    },
    {
      "epoch": 0.8114766688170061,
      "grad_norm": 0.39322054386138916,
      "learning_rate": 1.2946144301308396e-05,
      "loss": 0.545,
      "step": 26416
    },
    {
      "epoch": 0.8115073879519553,
      "grad_norm": 0.36962664127349854,
      "learning_rate": 1.294568247021226e-05,
      "loss": 0.5193,
      "step": 26417
    },
    {
      "epoch": 0.8115381070869044,
      "grad_norm": 0.36737972497940063,
      "learning_rate": 1.2945220632236279e-05,
      "loss": 0.4888,
      "step": 26418
    },
    {
      "epoch": 0.8115688262218536,
      "grad_norm": 0.3425534665584564,
      "learning_rate": 1.2944758787381526e-05,
      "loss": 0.6118,
      "step": 26419
    },
    {
      "epoch": 0.8115995453568028,
      "grad_norm": 0.31854334473609924,
      "learning_rate": 1.2944296935649085e-05,
      "loss": 0.552,
      "step": 26420
    },
    {
      "epoch": 0.8116302644917519,
      "grad_norm": 0.38726574182510376,
      "learning_rate": 1.2943835077040032e-05,
      "loss": 0.5528,
      "step": 26421
    },
    {
      "epoch": 0.811660983626701,
      "grad_norm": 0.3809078335762024,
      "learning_rate": 1.294337321155545e-05,
      "loss": 0.5427,
      "step": 26422
    },
    {
      "epoch": 0.8116917027616503,
      "grad_norm": 0.3932734727859497,
      "learning_rate": 1.2942911339196408e-05,
      "loss": 0.5409,
      "step": 26423
    },
    {
      "epoch": 0.8117224218965994,
      "grad_norm": 0.37386205792427063,
      "learning_rate": 1.2942449459963997e-05,
      "loss": 0.5135,
      "step": 26424
    },
    {
      "epoch": 0.8117531410315485,
      "grad_norm": 0.3925045430660248,
      "learning_rate": 1.2941987573859287e-05,
      "loss": 0.5477,
      "step": 26425
    },
    {
      "epoch": 0.8117838601664977,
      "grad_norm": 0.34404581785202026,
      "learning_rate": 1.294152568088336e-05,
      "loss": 0.5514,
      "step": 26426
    },
    {
      "epoch": 0.8118145793014468,
      "grad_norm": 0.35686731338500977,
      "learning_rate": 1.2941063781037296e-05,
      "loss": 0.5341,
      "step": 26427
    },
    {
      "epoch": 0.8118452984363961,
      "grad_norm": 0.3774053454399109,
      "learning_rate": 1.2940601874322167e-05,
      "loss": 0.4639,
      "step": 26428
    },
    {
      "epoch": 0.8118760175713452,
      "grad_norm": 0.3856010138988495,
      "learning_rate": 1.2940139960739062e-05,
      "loss": 0.6271,
      "step": 26429
    },
    {
      "epoch": 0.8119067367062943,
      "grad_norm": 0.40336117148399353,
      "learning_rate": 1.2939678040289052e-05,
      "loss": 0.6133,
      "step": 26430
    },
    {
      "epoch": 0.8119374558412435,
      "grad_norm": 0.4569160044193268,
      "learning_rate": 1.2939216112973221e-05,
      "loss": 0.5108,
      "step": 26431
    },
    {
      "epoch": 0.8119681749761927,
      "grad_norm": 0.3374609351158142,
      "learning_rate": 1.2938754178792643e-05,
      "loss": 0.4877,
      "step": 26432
    },
    {
      "epoch": 0.8119988941111418,
      "grad_norm": 0.3516600728034973,
      "learning_rate": 1.2938292237748402e-05,
      "loss": 0.5516,
      "step": 26433
    },
    {
      "epoch": 0.812029613246091,
      "grad_norm": 0.3998529016971588,
      "learning_rate": 1.2937830289841575e-05,
      "loss": 0.4923,
      "step": 26434
    },
    {
      "epoch": 0.8120603323810401,
      "grad_norm": 0.35559195280075073,
      "learning_rate": 1.2937368335073237e-05,
      "loss": 0.5183,
      "step": 26435
    },
    {
      "epoch": 0.8120910515159893,
      "grad_norm": 0.5950182676315308,
      "learning_rate": 1.2936906373444473e-05,
      "loss": 0.6565,
      "step": 26436
    },
    {
      "epoch": 0.8121217706509385,
      "grad_norm": 0.38230201601982117,
      "learning_rate": 1.2936444404956356e-05,
      "loss": 0.5523,
      "step": 26437
    },
    {
      "epoch": 0.8121524897858876,
      "grad_norm": 0.3262674808502197,
      "learning_rate": 1.293598242960997e-05,
      "loss": 0.5279,
      "step": 26438
    },
    {
      "epoch": 0.8121832089208368,
      "grad_norm": 0.39603301882743835,
      "learning_rate": 1.2935520447406389e-05,
      "loss": 0.5503,
      "step": 26439
    },
    {
      "epoch": 0.812213928055786,
      "grad_norm": 0.42001083493232727,
      "learning_rate": 1.2935058458346702e-05,
      "loss": 0.6036,
      "step": 26440
    },
    {
      "epoch": 0.8122446471907351,
      "grad_norm": 0.40994277596473694,
      "learning_rate": 1.2934596462431971e-05,
      "loss": 0.622,
      "step": 26441
    },
    {
      "epoch": 0.8122753663256843,
      "grad_norm": 0.36905398964881897,
      "learning_rate": 1.2934134459663295e-05,
      "loss": 0.5778,
      "step": 26442
    },
    {
      "epoch": 0.8123060854606334,
      "grad_norm": 0.34382495284080505,
      "learning_rate": 1.2933672450041735e-05,
      "loss": 0.5611,
      "step": 26443
    },
    {
      "epoch": 0.8123368045955826,
      "grad_norm": 0.3495948910713196,
      "learning_rate": 1.2933210433568384e-05,
      "loss": 0.5097,
      "step": 26444
    },
    {
      "epoch": 0.8123675237305318,
      "grad_norm": 0.3726136088371277,
      "learning_rate": 1.2932748410244311e-05,
      "loss": 0.5751,
      "step": 26445
    },
    {
      "epoch": 0.8123982428654809,
      "grad_norm": 0.37144482135772705,
      "learning_rate": 1.29322863800706e-05,
      "loss": 0.5462,
      "step": 26446
    },
    {
      "epoch": 0.81242896200043,
      "grad_norm": 0.3718896210193634,
      "learning_rate": 1.2931824343048331e-05,
      "loss": 0.6286,
      "step": 26447
    },
    {
      "epoch": 0.8124596811353793,
      "grad_norm": 0.38879191875457764,
      "learning_rate": 1.293136229917858e-05,
      "loss": 0.5112,
      "step": 26448
    },
    {
      "epoch": 0.8124904002703284,
      "grad_norm": 0.37452811002731323,
      "learning_rate": 1.293090024846243e-05,
      "loss": 0.5208,
      "step": 26449
    },
    {
      "epoch": 0.8125211194052775,
      "grad_norm": 0.3608669340610504,
      "learning_rate": 1.2930438190900953e-05,
      "loss": 0.5454,
      "step": 26450
    },
    {
      "epoch": 0.8125518385402267,
      "grad_norm": 0.38066473603248596,
      "learning_rate": 1.2929976126495239e-05,
      "loss": 0.6008,
      "step": 26451
    },
    {
      "epoch": 0.8125825576751758,
      "grad_norm": 0.3458561301231384,
      "learning_rate": 1.2929514055246359e-05,
      "loss": 0.5672,
      "step": 26452
    },
    {
      "epoch": 0.8126132768101251,
      "grad_norm": 0.3984225392341614,
      "learning_rate": 1.2929051977155394e-05,
      "loss": 0.5391,
      "step": 26453
    },
    {
      "epoch": 0.8126439959450742,
      "grad_norm": 0.3725435733795166,
      "learning_rate": 1.2928589892223422e-05,
      "loss": 0.5661,
      "step": 26454
    },
    {
      "epoch": 0.8126747150800233,
      "grad_norm": 0.36203479766845703,
      "learning_rate": 1.2928127800451524e-05,
      "loss": 0.5956,
      "step": 26455
    },
    {
      "epoch": 0.8127054342149725,
      "grad_norm": 0.4190383553504944,
      "learning_rate": 1.2927665701840781e-05,
      "loss": 0.5763,
      "step": 26456
    },
    {
      "epoch": 0.8127361533499217,
      "grad_norm": 0.37946683168411255,
      "learning_rate": 1.292720359639227e-05,
      "loss": 0.489,
      "step": 26457
    },
    {
      "epoch": 0.8127668724848708,
      "grad_norm": 0.3249615728855133,
      "learning_rate": 1.292674148410707e-05,
      "loss": 0.4806,
      "step": 26458
    },
    {
      "epoch": 0.81279759161982,
      "grad_norm": 0.38206392526626587,
      "learning_rate": 1.2926279364986261e-05,
      "loss": 0.5961,
      "step": 26459
    },
    {
      "epoch": 0.8128283107547691,
      "grad_norm": 0.3396950960159302,
      "learning_rate": 1.2925817239030923e-05,
      "loss": 0.5884,
      "step": 26460
    },
    {
      "epoch": 0.8128590298897183,
      "grad_norm": 0.43572553992271423,
      "learning_rate": 1.2925355106242132e-05,
      "loss": 0.4921,
      "step": 26461
    },
    {
      "epoch": 0.8128897490246675,
      "grad_norm": 0.3288643956184387,
      "learning_rate": 1.2924892966620972e-05,
      "loss": 0.5422,
      "step": 26462
    },
    {
      "epoch": 0.8129204681596166,
      "grad_norm": 0.3555660545825958,
      "learning_rate": 1.2924430820168516e-05,
      "loss": 0.4688,
      "step": 26463
    },
    {
      "epoch": 0.8129511872945658,
      "grad_norm": 0.35203567147254944,
      "learning_rate": 1.292396866688585e-05,
      "loss": 0.5118,
      "step": 26464
    },
    {
      "epoch": 0.812981906429515,
      "grad_norm": 0.3439578711986542,
      "learning_rate": 1.2923506506774055e-05,
      "loss": 0.525,
      "step": 26465
    },
    {
      "epoch": 0.8130126255644641,
      "grad_norm": 0.33699071407318115,
      "learning_rate": 1.2923044339834201e-05,
      "loss": 0.5196,
      "step": 26466
    },
    {
      "epoch": 0.8130433446994133,
      "grad_norm": 0.3710973560810089,
      "learning_rate": 1.2922582166067377e-05,
      "loss": 0.6124,
      "step": 26467
    },
    {
      "epoch": 0.8130740638343624,
      "grad_norm": 0.39785996079444885,
      "learning_rate": 1.2922119985474656e-05,
      "loss": 0.5164,
      "step": 26468
    },
    {
      "epoch": 0.8131047829693115,
      "grad_norm": 0.4112301468849182,
      "learning_rate": 1.292165779805712e-05,
      "loss": 0.5954,
      "step": 26469
    },
    {
      "epoch": 0.8131355021042608,
      "grad_norm": 0.35945817828178406,
      "learning_rate": 1.292119560381585e-05,
      "loss": 0.5036,
      "step": 26470
    },
    {
      "epoch": 0.8131662212392099,
      "grad_norm": 0.33008959889411926,
      "learning_rate": 1.2920733402751922e-05,
      "loss": 0.5604,
      "step": 26471
    },
    {
      "epoch": 0.813196940374159,
      "grad_norm": 0.505324125289917,
      "learning_rate": 1.2920271194866416e-05,
      "loss": 0.5596,
      "step": 26472
    },
    {
      "epoch": 0.8132276595091082,
      "grad_norm": 0.36151811480522156,
      "learning_rate": 1.2919808980160414e-05,
      "loss": 0.4865,
      "step": 26473
    },
    {
      "epoch": 0.8132583786440574,
      "grad_norm": 0.3582923710346222,
      "learning_rate": 1.2919346758634994e-05,
      "loss": 0.5736,
      "step": 26474
    },
    {
      "epoch": 0.8132890977790066,
      "grad_norm": 0.33583956956863403,
      "learning_rate": 1.2918884530291235e-05,
      "loss": 0.499,
      "step": 26475
    },
    {
      "epoch": 0.8133198169139557,
      "grad_norm": 0.3300650417804718,
      "learning_rate": 1.291842229513022e-05,
      "loss": 0.5082,
      "step": 26476
    },
    {
      "epoch": 0.8133505360489048,
      "grad_norm": 0.3728289008140564,
      "learning_rate": 1.2917960053153023e-05,
      "loss": 0.5404,
      "step": 26477
    },
    {
      "epoch": 0.8133812551838541,
      "grad_norm": 0.43847864866256714,
      "learning_rate": 1.2917497804360728e-05,
      "loss": 0.4874,
      "step": 26478
    },
    {
      "epoch": 0.8134119743188032,
      "grad_norm": 0.36215412616729736,
      "learning_rate": 1.2917035548754412e-05,
      "loss": 0.485,
      "step": 26479
    },
    {
      "epoch": 0.8134426934537523,
      "grad_norm": 0.3328584134578705,
      "learning_rate": 1.2916573286335157e-05,
      "loss": 0.5356,
      "step": 26480
    },
    {
      "epoch": 0.8134734125887015,
      "grad_norm": 0.34985485672950745,
      "learning_rate": 1.2916111017104043e-05,
      "loss": 0.5691,
      "step": 26481
    },
    {
      "epoch": 0.8135041317236507,
      "grad_norm": 0.3631986975669861,
      "learning_rate": 1.2915648741062141e-05,
      "loss": 0.6083,
      "step": 26482
    },
    {
      "epoch": 0.8135348508585998,
      "grad_norm": 0.3691447973251343,
      "learning_rate": 1.2915186458210545e-05,
      "loss": 0.5315,
      "step": 26483
    },
    {
      "epoch": 0.813565569993549,
      "grad_norm": 0.3760109543800354,
      "learning_rate": 1.2914724168550323e-05,
      "loss": 0.6082,
      "step": 26484
    },
    {
      "epoch": 0.8135962891284981,
      "grad_norm": 0.36880791187286377,
      "learning_rate": 1.291426187208256e-05,
      "loss": 0.5094,
      "step": 26485
    },
    {
      "epoch": 0.8136270082634472,
      "grad_norm": 0.37761619687080383,
      "learning_rate": 1.2913799568808339e-05,
      "loss": 0.4661,
      "step": 26486
    },
    {
      "epoch": 0.8136577273983965,
      "grad_norm": 0.45436012744903564,
      "learning_rate": 1.2913337258728731e-05,
      "loss": 0.4583,
      "step": 26487
    },
    {
      "epoch": 0.8136884465333456,
      "grad_norm": 0.39030030369758606,
      "learning_rate": 1.2912874941844825e-05,
      "loss": 0.5959,
      "step": 26488
    },
    {
      "epoch": 0.8137191656682948,
      "grad_norm": 0.3501146733760834,
      "learning_rate": 1.291241261815769e-05,
      "loss": 0.5018,
      "step": 26489
    },
    {
      "epoch": 0.813749884803244,
      "grad_norm": 0.39768216013908386,
      "learning_rate": 1.2911950287668416e-05,
      "loss": 0.5639,
      "step": 26490
    },
    {
      "epoch": 0.8137806039381931,
      "grad_norm": 0.42301541566848755,
      "learning_rate": 1.2911487950378076e-05,
      "loss": 0.6498,
      "step": 26491
    },
    {
      "epoch": 0.8138113230731423,
      "grad_norm": 0.49064961075782776,
      "learning_rate": 1.2911025606287756e-05,
      "loss": 0.5881,
      "step": 26492
    },
    {
      "epoch": 0.8138420422080914,
      "grad_norm": 0.3504241108894348,
      "learning_rate": 1.2910563255398531e-05,
      "loss": 0.5785,
      "step": 26493
    },
    {
      "epoch": 0.8138727613430405,
      "grad_norm": 0.3845399022102356,
      "learning_rate": 1.2910100897711481e-05,
      "loss": 0.4906,
      "step": 26494
    },
    {
      "epoch": 0.8139034804779898,
      "grad_norm": 0.366380900144577,
      "learning_rate": 1.290963853322769e-05,
      "loss": 0.5909,
      "step": 26495
    },
    {
      "epoch": 0.8139341996129389,
      "grad_norm": 0.3511548638343811,
      "learning_rate": 1.2909176161948232e-05,
      "loss": 0.6026,
      "step": 26496
    },
    {
      "epoch": 0.813964918747888,
      "grad_norm": 0.3456345200538635,
      "learning_rate": 1.2908713783874194e-05,
      "loss": 0.5059,
      "step": 26497
    },
    {
      "epoch": 0.8139956378828372,
      "grad_norm": 0.3841927945613861,
      "learning_rate": 1.2908251399006646e-05,
      "loss": 0.5836,
      "step": 26498
    },
    {
      "epoch": 0.8140263570177864,
      "grad_norm": 0.3587930202484131,
      "learning_rate": 1.2907789007346678e-05,
      "loss": 0.6113,
      "step": 26499
    },
    {
      "epoch": 0.8140570761527356,
      "grad_norm": 0.39908716082572937,
      "learning_rate": 1.290732660889536e-05,
      "loss": 0.6484,
      "step": 26500
    },
    {
      "epoch": 0.8140877952876847,
      "grad_norm": 0.3345057964324951,
      "learning_rate": 1.2906864203653783e-05,
      "loss": 0.5312,
      "step": 26501
    },
    {
      "epoch": 0.8141185144226338,
      "grad_norm": 0.36177539825439453,
      "learning_rate": 1.290640179162302e-05,
      "loss": 0.5538,
      "step": 26502
    },
    {
      "epoch": 0.8141492335575831,
      "grad_norm": 0.3504860997200012,
      "learning_rate": 1.2905939372804155e-05,
      "loss": 0.4696,
      "step": 26503
    },
    {
      "epoch": 0.8141799526925322,
      "grad_norm": 0.38284510374069214,
      "learning_rate": 1.2905476947198264e-05,
      "loss": 0.6032,
      "step": 26504
    },
    {
      "epoch": 0.8142106718274813,
      "grad_norm": 0.36135542392730713,
      "learning_rate": 1.2905014514806426e-05,
      "loss": 0.5325,
      "step": 26505
    },
    {
      "epoch": 0.8142413909624305,
      "grad_norm": 0.43138477206230164,
      "learning_rate": 1.2904552075629727e-05,
      "loss": 0.5441,
      "step": 26506
    },
    {
      "epoch": 0.8142721100973797,
      "grad_norm": 0.3645302355289459,
      "learning_rate": 1.2904089629669243e-05,
      "loss": 0.6413,
      "step": 26507
    },
    {
      "epoch": 0.8143028292323288,
      "grad_norm": 0.36785924434661865,
      "learning_rate": 1.2903627176926057e-05,
      "loss": 0.5964,
      "step": 26508
    },
    {
      "epoch": 0.814333548367278,
      "grad_norm": 0.3558421730995178,
      "learning_rate": 1.2903164717401245e-05,
      "loss": 0.5124,
      "step": 26509
    },
    {
      "epoch": 0.8143642675022271,
      "grad_norm": 0.3688459098339081,
      "learning_rate": 1.2902702251095888e-05,
      "loss": 0.563,
      "step": 26510
    },
    {
      "epoch": 0.8143949866371762,
      "grad_norm": 0.4209260642528534,
      "learning_rate": 1.2902239778011068e-05,
      "loss": 0.5608,
      "step": 26511
    },
    {
      "epoch": 0.8144257057721255,
      "grad_norm": 0.3600713312625885,
      "learning_rate": 1.2901777298147863e-05,
      "loss": 0.5274,
      "step": 26512
    },
    {
      "epoch": 0.8144564249070746,
      "grad_norm": 0.38266992568969727,
      "learning_rate": 1.2901314811507355e-05,
      "loss": 0.6188,
      "step": 26513
    },
    {
      "epoch": 0.8144871440420238,
      "grad_norm": 0.42566370964050293,
      "learning_rate": 1.2900852318090627e-05,
      "loss": 0.5332,
      "step": 26514
    },
    {
      "epoch": 0.814517863176973,
      "grad_norm": 0.33958351612091064,
      "learning_rate": 1.2900389817898754e-05,
      "loss": 0.5488,
      "step": 26515
    },
    {
      "epoch": 0.8145485823119221,
      "grad_norm": 0.4252163767814636,
      "learning_rate": 1.2899927310932815e-05,
      "loss": 0.574,
      "step": 26516
    },
    {
      "epoch": 0.8145793014468713,
      "grad_norm": 0.40581971406936646,
      "learning_rate": 1.2899464797193897e-05,
      "loss": 0.4814,
      "step": 26517
    },
    {
      "epoch": 0.8146100205818204,
      "grad_norm": 0.4008352756500244,
      "learning_rate": 1.2899002276683072e-05,
      "loss": 0.5334,
      "step": 26518
    },
    {
      "epoch": 0.8146407397167695,
      "grad_norm": 0.33051058650016785,
      "learning_rate": 1.2898539749401428e-05,
      "loss": 0.5349,
      "step": 26519
    },
    {
      "epoch": 0.8146714588517188,
      "grad_norm": 0.3394036591053009,
      "learning_rate": 1.2898077215350044e-05,
      "loss": 0.6085,
      "step": 26520
    },
    {
      "epoch": 0.8147021779866679,
      "grad_norm": 0.3550262749195099,
      "learning_rate": 1.2897614674529995e-05,
      "loss": 0.5865,
      "step": 26521
    },
    {
      "epoch": 0.814732897121617,
      "grad_norm": 0.3818245232105255,
      "learning_rate": 1.2897152126942367e-05,
      "loss": 0.5331,
      "step": 26522
    },
    {
      "epoch": 0.8147636162565662,
      "grad_norm": 0.3538561165332794,
      "learning_rate": 1.2896689572588234e-05,
      "loss": 0.5566,
      "step": 26523
    },
    {
      "epoch": 0.8147943353915154,
      "grad_norm": 0.37494024634361267,
      "learning_rate": 1.2896227011468683e-05,
      "loss": 0.6082,
      "step": 26524
    },
    {
      "epoch": 0.8148250545264646,
      "grad_norm": 0.3490696847438812,
      "learning_rate": 1.289576444358479e-05,
      "loss": 0.528,
      "step": 26525
    },
    {
      "epoch": 0.8148557736614137,
      "grad_norm": 0.39498940110206604,
      "learning_rate": 1.289530186893764e-05,
      "loss": 0.5165,
      "step": 26526
    },
    {
      "epoch": 0.8148864927963628,
      "grad_norm": 0.36816808581352234,
      "learning_rate": 1.2894839287528308e-05,
      "loss": 0.5535,
      "step": 26527
    },
    {
      "epoch": 0.8149172119313121,
      "grad_norm": 0.3549196422100067,
      "learning_rate": 1.2894376699357878e-05,
      "loss": 0.5556,
      "step": 26528
    },
    {
      "epoch": 0.8149479310662612,
      "grad_norm": 0.3507249355316162,
      "learning_rate": 1.2893914104427428e-05,
      "loss": 0.5948,
      "step": 26529
    },
    {
      "epoch": 0.8149786502012103,
      "grad_norm": 0.40923547744750977,
      "learning_rate": 1.289345150273804e-05,
      "loss": 0.5729,
      "step": 26530
    },
    {
      "epoch": 0.8150093693361595,
      "grad_norm": 0.41361674666404724,
      "learning_rate": 1.2892988894290795e-05,
      "loss": 0.6025,
      "step": 26531
    },
    {
      "epoch": 0.8150400884711086,
      "grad_norm": 0.364076167345047,
      "learning_rate": 1.2892526279086768e-05,
      "loss": 0.5275,
      "step": 26532
    },
    {
      "epoch": 0.8150708076060578,
      "grad_norm": 0.3750988841056824,
      "learning_rate": 1.2892063657127048e-05,
      "loss": 0.6123,
      "step": 26533
    },
    {
      "epoch": 0.815101526741007,
      "grad_norm": 0.40364697575569153,
      "learning_rate": 1.2891601028412709e-05,
      "loss": 0.5955,
      "step": 26534
    },
    {
      "epoch": 0.8151322458759561,
      "grad_norm": 0.3940364122390747,
      "learning_rate": 1.2891138392944835e-05,
      "loss": 0.5669,
      "step": 26535
    },
    {
      "epoch": 0.8151629650109052,
      "grad_norm": 0.4586775302886963,
      "learning_rate": 1.2890675750724503e-05,
      "loss": 0.5108,
      "step": 26536
    },
    {
      "epoch": 0.8151936841458545,
      "grad_norm": 0.3610551953315735,
      "learning_rate": 1.28902131017528e-05,
      "loss": 0.5835,
      "step": 26537
    },
    {
      "epoch": 0.8152244032808036,
      "grad_norm": 0.3765886127948761,
      "learning_rate": 1.2889750446030802e-05,
      "loss": 0.6289,
      "step": 26538
    },
    {
      "epoch": 0.8152551224157528,
      "grad_norm": 0.36427947878837585,
      "learning_rate": 1.2889287783559588e-05,
      "loss": 0.5642,
      "step": 26539
    },
    {
      "epoch": 0.8152858415507019,
      "grad_norm": 0.3973386287689209,
      "learning_rate": 1.288882511434024e-05,
      "loss": 0.6083,
      "step": 26540
    },
    {
      "epoch": 0.8153165606856511,
      "grad_norm": 0.36149242520332336,
      "learning_rate": 1.2888362438373841e-05,
      "loss": 0.626,
      "step": 26541
    },
    {
      "epoch": 0.8153472798206003,
      "grad_norm": 0.37453633546829224,
      "learning_rate": 1.288789975566147e-05,
      "loss": 0.5114,
      "step": 26542
    },
    {
      "epoch": 0.8153779989555494,
      "grad_norm": 0.4469817280769348,
      "learning_rate": 1.2887437066204204e-05,
      "loss": 0.6581,
      "step": 26543
    },
    {
      "epoch": 0.8154087180904985,
      "grad_norm": 0.3579249680042267,
      "learning_rate": 1.2886974370003132e-05,
      "loss": 0.5587,
      "step": 26544
    },
    {
      "epoch": 0.8154394372254478,
      "grad_norm": 0.3796764314174652,
      "learning_rate": 1.2886511667059325e-05,
      "loss": 0.5354,
      "step": 26545
    },
    {
      "epoch": 0.8154701563603969,
      "grad_norm": 0.43063852190971375,
      "learning_rate": 1.2886048957373874e-05,
      "loss": 0.5293,
      "step": 26546
    },
    {
      "epoch": 0.815500875495346,
      "grad_norm": 0.6034186482429504,
      "learning_rate": 1.288558624094785e-05,
      "loss": 0.5988,
      "step": 26547
    },
    {
      "epoch": 0.8155315946302952,
      "grad_norm": 0.3926079273223877,
      "learning_rate": 1.288512351778234e-05,
      "loss": 0.5524,
      "step": 26548
    },
    {
      "epoch": 0.8155623137652444,
      "grad_norm": 0.35242095589637756,
      "learning_rate": 1.2884660787878422e-05,
      "loss": 0.6642,
      "step": 26549
    },
    {
      "epoch": 0.8155930329001936,
      "grad_norm": 0.3455394506454468,
      "learning_rate": 1.2884198051237173e-05,
      "loss": 0.5254,
      "step": 26550
    },
    {
      "epoch": 0.8156237520351427,
      "grad_norm": 0.39459022879600525,
      "learning_rate": 1.2883735307859684e-05,
      "loss": 0.6228,
      "step": 26551
    },
    {
      "epoch": 0.8156544711700918,
      "grad_norm": 0.3630228340625763,
      "learning_rate": 1.2883272557747026e-05,
      "loss": 0.4882,
      "step": 26552
    },
    {
      "epoch": 0.815685190305041,
      "grad_norm": 0.3363417983055115,
      "learning_rate": 1.2882809800900286e-05,
      "loss": 0.5372,
      "step": 26553
    },
    {
      "epoch": 0.8157159094399902,
      "grad_norm": 0.3423668444156647,
      "learning_rate": 1.2882347037320542e-05,
      "loss": 0.5151,
      "step": 26554
    },
    {
      "epoch": 0.8157466285749393,
      "grad_norm": 0.38148602843284607,
      "learning_rate": 1.2881884267008874e-05,
      "loss": 0.5726,
      "step": 26555
    },
    {
      "epoch": 0.8157773477098885,
      "grad_norm": 0.3850660026073456,
      "learning_rate": 1.2881421489966363e-05,
      "loss": 0.5145,
      "step": 26556
    },
    {
      "epoch": 0.8158080668448376,
      "grad_norm": 0.34062284231185913,
      "learning_rate": 1.2880958706194093e-05,
      "loss": 0.5523,
      "step": 26557
    },
    {
      "epoch": 0.8158387859797868,
      "grad_norm": 0.3429887890815735,
      "learning_rate": 1.2880495915693143e-05,
      "loss": 0.626,
      "step": 26558
    },
    {
      "epoch": 0.815869505114736,
      "grad_norm": 0.4187089204788208,
      "learning_rate": 1.2880033118464592e-05,
      "loss": 0.5098,
      "step": 26559
    },
    {
      "epoch": 0.8159002242496851,
      "grad_norm": 0.37302738428115845,
      "learning_rate": 1.2879570314509524e-05,
      "loss": 0.5715,
      "step": 26560
    },
    {
      "epoch": 0.8159309433846343,
      "grad_norm": 0.49190664291381836,
      "learning_rate": 1.2879107503829016e-05,
      "loss": 0.5842,
      "step": 26561
    },
    {
      "epoch": 0.8159616625195835,
      "grad_norm": 0.3454671800136566,
      "learning_rate": 1.2878644686424155e-05,
      "loss": 0.57,
      "step": 26562
    },
    {
      "epoch": 0.8159923816545326,
      "grad_norm": 0.35619622468948364,
      "learning_rate": 1.2878181862296015e-05,
      "loss": 0.5482,
      "step": 26563
    },
    {
      "epoch": 0.8160231007894818,
      "grad_norm": 0.3326692283153534,
      "learning_rate": 1.2877719031445684e-05,
      "loss": 0.5441,
      "step": 26564
    },
    {
      "epoch": 0.8160538199244309,
      "grad_norm": 0.42644599080085754,
      "learning_rate": 1.2877256193874235e-05,
      "loss": 0.6054,
      "step": 26565
    },
    {
      "epoch": 0.81608453905938,
      "grad_norm": 0.36348623037338257,
      "learning_rate": 1.2876793349582757e-05,
      "loss": 0.5061,
      "step": 26566
    },
    {
      "epoch": 0.8161152581943293,
      "grad_norm": 0.3471420109272003,
      "learning_rate": 1.2876330498572325e-05,
      "loss": 0.5818,
      "step": 26567
    },
    {
      "epoch": 0.8161459773292784,
      "grad_norm": 0.3448346257209778,
      "learning_rate": 1.2875867640844023e-05,
      "loss": 0.537,
      "step": 26568
    },
    {
      "epoch": 0.8161766964642275,
      "grad_norm": 0.4122471809387207,
      "learning_rate": 1.287540477639893e-05,
      "loss": 0.55,
      "step": 26569
    },
    {
      "epoch": 0.8162074155991768,
      "grad_norm": 0.3715798556804657,
      "learning_rate": 1.2874941905238129e-05,
      "loss": 0.5283,
      "step": 26570
    },
    {
      "epoch": 0.8162381347341259,
      "grad_norm": 0.3450283706188202,
      "learning_rate": 1.28744790273627e-05,
      "loss": 0.6106,
      "step": 26571
    },
    {
      "epoch": 0.816268853869075,
      "grad_norm": 0.346669465303421,
      "learning_rate": 1.2874016142773725e-05,
      "loss": 0.5686,
      "step": 26572
    },
    {
      "epoch": 0.8162995730040242,
      "grad_norm": 0.38140857219696045,
      "learning_rate": 1.2873553251472284e-05,
      "loss": 0.5552,
      "step": 26573
    },
    {
      "epoch": 0.8163302921389733,
      "grad_norm": 0.4900709390640259,
      "learning_rate": 1.2873090353459459e-05,
      "loss": 0.5673,
      "step": 26574
    },
    {
      "epoch": 0.8163610112739226,
      "grad_norm": 0.36131322383880615,
      "learning_rate": 1.287262744873633e-05,
      "loss": 0.5903,
      "step": 26575
    },
    {
      "epoch": 0.8163917304088717,
      "grad_norm": 0.3640042543411255,
      "learning_rate": 1.2872164537303981e-05,
      "loss": 0.559,
      "step": 26576
    },
    {
      "epoch": 0.8164224495438208,
      "grad_norm": 0.36333274841308594,
      "learning_rate": 1.287170161916349e-05,
      "loss": 0.5635,
      "step": 26577
    },
    {
      "epoch": 0.81645316867877,
      "grad_norm": 0.38221627473831177,
      "learning_rate": 1.2871238694315941e-05,
      "loss": 0.5525,
      "step": 26578
    },
    {
      "epoch": 0.8164838878137192,
      "grad_norm": 0.35699403285980225,
      "learning_rate": 1.287077576276241e-05,
      "loss": 0.6229,
      "step": 26579
    },
    {
      "epoch": 0.8165146069486683,
      "grad_norm": 0.3956488370895386,
      "learning_rate": 1.2870312824503986e-05,
      "loss": 0.5577,
      "step": 26580
    },
    {
      "epoch": 0.8165453260836175,
      "grad_norm": 0.3523346781730652,
      "learning_rate": 1.2869849879541742e-05,
      "loss": 0.5678,
      "step": 26581
    },
    {
      "epoch": 0.8165760452185666,
      "grad_norm": 0.3940275311470032,
      "learning_rate": 1.2869386927876766e-05,
      "loss": 0.504,
      "step": 26582
    },
    {
      "epoch": 0.8166067643535158,
      "grad_norm": 0.4273434579372406,
      "learning_rate": 1.2868923969510136e-05,
      "loss": 0.4669,
      "step": 26583
    },
    {
      "epoch": 0.816637483488465,
      "grad_norm": 0.33706095814704895,
      "learning_rate": 1.2868461004442932e-05,
      "loss": 0.5672,
      "step": 26584
    },
    {
      "epoch": 0.8166682026234141,
      "grad_norm": 0.3759264349937439,
      "learning_rate": 1.2867998032676238e-05,
      "loss": 0.5709,
      "step": 26585
    },
    {
      "epoch": 0.8166989217583633,
      "grad_norm": 0.3641316890716553,
      "learning_rate": 1.2867535054211136e-05,
      "loss": 0.5247,
      "step": 26586
    },
    {
      "epoch": 0.8167296408933125,
      "grad_norm": 0.37306806445121765,
      "learning_rate": 1.2867072069048702e-05,
      "loss": 0.5101,
      "step": 26587
    },
    {
      "epoch": 0.8167603600282616,
      "grad_norm": 0.404131680727005,
      "learning_rate": 1.2866609077190022e-05,
      "loss": 0.6094,
      "step": 26588
    },
    {
      "epoch": 0.8167910791632108,
      "grad_norm": 0.39831849932670593,
      "learning_rate": 1.2866146078636179e-05,
      "loss": 0.4629,
      "step": 26589
    },
    {
      "epoch": 0.8168217982981599,
      "grad_norm": 0.3604658842086792,
      "learning_rate": 1.2865683073388249e-05,
      "loss": 0.5245,
      "step": 26590
    },
    {
      "epoch": 0.816852517433109,
      "grad_norm": 0.35793808102607727,
      "learning_rate": 1.2865220061447317e-05,
      "loss": 0.4985,
      "step": 26591
    },
    {
      "epoch": 0.8168832365680583,
      "grad_norm": 0.38337764143943787,
      "learning_rate": 1.2864757042814464e-05,
      "loss": 0.4935,
      "step": 26592
    },
    {
      "epoch": 0.8169139557030074,
      "grad_norm": 0.3628069758415222,
      "learning_rate": 1.2864294017490768e-05,
      "loss": 0.5581,
      "step": 26593
    },
    {
      "epoch": 0.8169446748379565,
      "grad_norm": 0.356502503156662,
      "learning_rate": 1.2863830985477317e-05,
      "loss": 0.5975,
      "step": 26594
    },
    {
      "epoch": 0.8169753939729058,
      "grad_norm": 0.37766793370246887,
      "learning_rate": 1.2863367946775184e-05,
      "loss": 0.5546,
      "step": 26595
    },
    {
      "epoch": 0.8170061131078549,
      "grad_norm": 0.38351938128471375,
      "learning_rate": 1.2862904901385462e-05,
      "loss": 0.6379,
      "step": 26596
    },
    {
      "epoch": 0.817036832242804,
      "grad_norm": 0.3637135624885559,
      "learning_rate": 1.2862441849309222e-05,
      "loss": 0.544,
      "step": 26597
    },
    {
      "epoch": 0.8170675513777532,
      "grad_norm": 0.35460320115089417,
      "learning_rate": 1.2861978790547549e-05,
      "loss": 0.6215,
      "step": 26598
    },
    {
      "epoch": 0.8170982705127023,
      "grad_norm": 0.3706585466861725,
      "learning_rate": 1.2861515725101523e-05,
      "loss": 0.5235,
      "step": 26599
    },
    {
      "epoch": 0.8171289896476516,
      "grad_norm": 0.3398427963256836,
      "learning_rate": 1.286105265297223e-05,
      "loss": 0.4705,
      "step": 26600
    },
    {
      "epoch": 0.8171597087826007,
      "grad_norm": 0.406465619802475,
      "learning_rate": 1.286058957416075e-05,
      "loss": 0.6001,
      "step": 26601
    },
    {
      "epoch": 0.8171904279175498,
      "grad_norm": 0.40822702646255493,
      "learning_rate": 1.286012648866816e-05,
      "loss": 0.5629,
      "step": 26602
    },
    {
      "epoch": 0.817221147052499,
      "grad_norm": 0.38090789318084717,
      "learning_rate": 1.2859663396495545e-05,
      "loss": 0.5019,
      "step": 26603
    },
    {
      "epoch": 0.8172518661874482,
      "grad_norm": 0.3451652228832245,
      "learning_rate": 1.2859200297643988e-05,
      "loss": 0.5171,
      "step": 26604
    },
    {
      "epoch": 0.8172825853223973,
      "grad_norm": 0.39935728907585144,
      "learning_rate": 1.2858737192114568e-05,
      "loss": 0.5459,
      "step": 26605
    },
    {
      "epoch": 0.8173133044573465,
      "grad_norm": 0.47929126024246216,
      "learning_rate": 1.2858274079908366e-05,
      "loss": 0.5064,
      "step": 26606
    },
    {
      "epoch": 0.8173440235922956,
      "grad_norm": 0.3528982996940613,
      "learning_rate": 1.2857810961026468e-05,
      "loss": 0.5763,
      "step": 26607
    },
    {
      "epoch": 0.8173747427272448,
      "grad_norm": 0.42673200368881226,
      "learning_rate": 1.2857347835469953e-05,
      "loss": 0.6216,
      "step": 26608
    },
    {
      "epoch": 0.817405461862194,
      "grad_norm": 0.36647799611091614,
      "learning_rate": 1.28568847032399e-05,
      "loss": 0.6114,
      "step": 26609
    },
    {
      "epoch": 0.8174361809971431,
      "grad_norm": 0.3945540189743042,
      "learning_rate": 1.2856421564337395e-05,
      "loss": 0.5686,
      "step": 26610
    },
    {
      "epoch": 0.8174669001320923,
      "grad_norm": 0.35531947016716003,
      "learning_rate": 1.2855958418763516e-05,
      "loss": 0.6125,
      "step": 26611
    },
    {
      "epoch": 0.8174976192670415,
      "grad_norm": 0.33505356311798096,
      "learning_rate": 1.2855495266519351e-05,
      "loss": 0.5816,
      "step": 26612
    },
    {
      "epoch": 0.8175283384019906,
      "grad_norm": 0.378243625164032,
      "learning_rate": 1.2855032107605974e-05,
      "loss": 0.548,
      "step": 26613
    },
    {
      "epoch": 0.8175590575369398,
      "grad_norm": 0.3609682023525238,
      "learning_rate": 1.2854568942024472e-05,
      "loss": 0.5256,
      "step": 26614
    },
    {
      "epoch": 0.8175897766718889,
      "grad_norm": 0.36049309372901917,
      "learning_rate": 1.2854105769775922e-05,
      "loss": 0.5476,
      "step": 26615
    },
    {
      "epoch": 0.817620495806838,
      "grad_norm": 0.3632739186286926,
      "learning_rate": 1.2853642590861412e-05,
      "loss": 0.6111,
      "step": 26616
    },
    {
      "epoch": 0.8176512149417873,
      "grad_norm": 0.35682809352874756,
      "learning_rate": 1.285317940528202e-05,
      "loss": 0.5605,
      "step": 26617
    },
    {
      "epoch": 0.8176819340767364,
      "grad_norm": 0.3773444592952728,
      "learning_rate": 1.2852716213038827e-05,
      "loss": 0.5063,
      "step": 26618
    },
    {
      "epoch": 0.8177126532116855,
      "grad_norm": 0.3831283152103424,
      "learning_rate": 1.2852253014132918e-05,
      "loss": 0.4977,
      "step": 26619
    },
    {
      "epoch": 0.8177433723466347,
      "grad_norm": 0.372177392244339,
      "learning_rate": 1.2851789808565369e-05,
      "loss": 0.6047,
      "step": 26620
    },
    {
      "epoch": 0.8177740914815839,
      "grad_norm": 0.4862440526485443,
      "learning_rate": 1.2851326596337268e-05,
      "loss": 0.5362,
      "step": 26621
    },
    {
      "epoch": 0.817804810616533,
      "grad_norm": 0.3269592523574829,
      "learning_rate": 1.2850863377449695e-05,
      "loss": 0.468,
      "step": 26622
    },
    {
      "epoch": 0.8178355297514822,
      "grad_norm": 0.3521438539028168,
      "learning_rate": 1.2850400151903733e-05,
      "loss": 0.4921,
      "step": 26623
    },
    {
      "epoch": 0.8178662488864313,
      "grad_norm": 0.3778867721557617,
      "learning_rate": 1.2849936919700458e-05,
      "loss": 0.5696,
      "step": 26624
    },
    {
      "epoch": 0.8178969680213806,
      "grad_norm": 0.43788042664527893,
      "learning_rate": 1.284947368084096e-05,
      "loss": 0.6042,
      "step": 26625
    },
    {
      "epoch": 0.8179276871563297,
      "grad_norm": 0.37505558133125305,
      "learning_rate": 1.2849010435326314e-05,
      "loss": 0.5824,
      "step": 26626
    },
    {
      "epoch": 0.8179584062912788,
      "grad_norm": 0.3833819329738617,
      "learning_rate": 1.284854718315761e-05,
      "loss": 0.5573,
      "step": 26627
    },
    {
      "epoch": 0.817989125426228,
      "grad_norm": 0.6364284753799438,
      "learning_rate": 1.2848083924335918e-05,
      "loss": 0.5017,
      "step": 26628
    },
    {
      "epoch": 0.8180198445611772,
      "grad_norm": 0.3856721520423889,
      "learning_rate": 1.2847620658862332e-05,
      "loss": 0.4806,
      "step": 26629
    },
    {
      "epoch": 0.8180505636961263,
      "grad_norm": 0.3414755165576935,
      "learning_rate": 1.2847157386737929e-05,
      "loss": 0.6052,
      "step": 26630
    },
    {
      "epoch": 0.8180812828310755,
      "grad_norm": 0.34879007935523987,
      "learning_rate": 1.2846694107963789e-05,
      "loss": 0.5214,
      "step": 26631
    },
    {
      "epoch": 0.8181120019660246,
      "grad_norm": 0.3319236636161804,
      "learning_rate": 1.2846230822541e-05,
      "loss": 0.5467,
      "step": 26632
    },
    {
      "epoch": 0.8181427211009737,
      "grad_norm": 0.4025714099407196,
      "learning_rate": 1.2845767530470634e-05,
      "loss": 0.59,
      "step": 26633
    },
    {
      "epoch": 0.818173440235923,
      "grad_norm": 0.4107726216316223,
      "learning_rate": 1.2845304231753786e-05,
      "loss": 0.6358,
      "step": 26634
    },
    {
      "epoch": 0.8182041593708721,
      "grad_norm": 0.3983345031738281,
      "learning_rate": 1.2844840926391526e-05,
      "loss": 0.5521,
      "step": 26635
    },
    {
      "epoch": 0.8182348785058213,
      "grad_norm": 0.3498138189315796,
      "learning_rate": 1.2844377614384944e-05,
      "loss": 0.5294,
      "step": 26636
    },
    {
      "epoch": 0.8182655976407704,
      "grad_norm": 0.3937561810016632,
      "learning_rate": 1.284391429573512e-05,
      "loss": 0.5336,
      "step": 26637
    },
    {
      "epoch": 0.8182963167757196,
      "grad_norm": 0.34828683733940125,
      "learning_rate": 1.2843450970443132e-05,
      "loss": 0.6055,
      "step": 26638
    },
    {
      "epoch": 0.8183270359106688,
      "grad_norm": 0.4137212336063385,
      "learning_rate": 1.2842987638510071e-05,
      "loss": 0.4964,
      "step": 26639
    },
    {
      "epoch": 0.8183577550456179,
      "grad_norm": 0.37540730834007263,
      "learning_rate": 1.284252429993701e-05,
      "loss": 0.5969,
      "step": 26640
    },
    {
      "epoch": 0.818388474180567,
      "grad_norm": 0.378143310546875,
      "learning_rate": 1.2842060954725035e-05,
      "loss": 0.5933,
      "step": 26641
    },
    {
      "epoch": 0.8184191933155163,
      "grad_norm": 0.3457762598991394,
      "learning_rate": 1.2841597602875229e-05,
      "loss": 0.4969,
      "step": 26642
    },
    {
      "epoch": 0.8184499124504654,
      "grad_norm": 0.39129266142845154,
      "learning_rate": 1.2841134244388673e-05,
      "loss": 0.4965,
      "step": 26643
    },
    {
      "epoch": 0.8184806315854145,
      "grad_norm": 0.3862467408180237,
      "learning_rate": 1.284067087926645e-05,
      "loss": 0.5003,
      "step": 26644
    },
    {
      "epoch": 0.8185113507203637,
      "grad_norm": 0.35875988006591797,
      "learning_rate": 1.2840207507509643e-05,
      "loss": 0.5127,
      "step": 26645
    },
    {
      "epoch": 0.8185420698553129,
      "grad_norm": 0.3680393397808075,
      "learning_rate": 1.283974412911933e-05,
      "loss": 0.4839,
      "step": 26646
    },
    {
      "epoch": 0.818572788990262,
      "grad_norm": 0.3366445302963257,
      "learning_rate": 1.2839280744096599e-05,
      "loss": 0.508,
      "step": 26647
    },
    {
      "epoch": 0.8186035081252112,
      "grad_norm": 0.35272228717803955,
      "learning_rate": 1.2838817352442528e-05,
      "loss": 0.5442,
      "step": 26648
    },
    {
      "epoch": 0.8186342272601603,
      "grad_norm": 0.3683136999607086,
      "learning_rate": 1.28383539541582e-05,
      "loss": 0.505,
      "step": 26649
    },
    {
      "epoch": 0.8186649463951096,
      "grad_norm": 0.33038634061813354,
      "learning_rate": 1.28378905492447e-05,
      "loss": 0.5165,
      "step": 26650
    },
    {
      "epoch": 0.8186956655300587,
      "grad_norm": 0.37008967995643616,
      "learning_rate": 1.2837427137703107e-05,
      "loss": 0.546,
      "step": 26651
    },
    {
      "epoch": 0.8187263846650078,
      "grad_norm": 0.3393779695034027,
      "learning_rate": 1.2836963719534507e-05,
      "loss": 0.5892,
      "step": 26652
    },
    {
      "epoch": 0.818757103799957,
      "grad_norm": 0.3466517925262451,
      "learning_rate": 1.283650029473998e-05,
      "loss": 0.5378,
      "step": 26653
    },
    {
      "epoch": 0.8187878229349062,
      "grad_norm": 0.35285013914108276,
      "learning_rate": 1.2836036863320604e-05,
      "loss": 0.5607,
      "step": 26654
    },
    {
      "epoch": 0.8188185420698553,
      "grad_norm": 0.36361852288246155,
      "learning_rate": 1.2835573425277473e-05,
      "loss": 0.5139,
      "step": 26655
    },
    {
      "epoch": 0.8188492612048045,
      "grad_norm": 0.3348584771156311,
      "learning_rate": 1.2835109980611656e-05,
      "loss": 0.5229,
      "step": 26656
    },
    {
      "epoch": 0.8188799803397536,
      "grad_norm": 0.3546358644962311,
      "learning_rate": 1.2834646529324245e-05,
      "loss": 0.4909,
      "step": 26657
    },
    {
      "epoch": 0.8189106994747027,
      "grad_norm": 0.35301464796066284,
      "learning_rate": 1.2834183071416316e-05,
      "loss": 0.585,
      "step": 26658
    },
    {
      "epoch": 0.818941418609652,
      "grad_norm": 0.38176482915878296,
      "learning_rate": 1.2833719606888957e-05,
      "loss": 0.509,
      "step": 26659
    },
    {
      "epoch": 0.8189721377446011,
      "grad_norm": 0.37141263484954834,
      "learning_rate": 1.2833256135743246e-05,
      "loss": 0.6004,
      "step": 26660
    },
    {
      "epoch": 0.8190028568795503,
      "grad_norm": 0.34485679864883423,
      "learning_rate": 1.283279265798027e-05,
      "loss": 0.537,
      "step": 26661
    },
    {
      "epoch": 0.8190335760144994,
      "grad_norm": 2.714688539505005,
      "learning_rate": 1.2832329173601105e-05,
      "loss": 0.4728,
      "step": 26662
    },
    {
      "epoch": 0.8190642951494486,
      "grad_norm": 0.38392239809036255,
      "learning_rate": 1.2831865682606843e-05,
      "loss": 0.5673,
      "step": 26663
    },
    {
      "epoch": 0.8190950142843978,
      "grad_norm": 0.38120341300964355,
      "learning_rate": 1.2831402184998556e-05,
      "loss": 0.4893,
      "step": 26664
    },
    {
      "epoch": 0.8191257334193469,
      "grad_norm": 0.37049153447151184,
      "learning_rate": 1.2830938680777334e-05,
      "loss": 0.4659,
      "step": 26665
    },
    {
      "epoch": 0.819156452554296,
      "grad_norm": 0.3839811682701111,
      "learning_rate": 1.2830475169944256e-05,
      "loss": 0.5283,
      "step": 26666
    },
    {
      "epoch": 0.8191871716892453,
      "grad_norm": 0.40734946727752686,
      "learning_rate": 1.2830011652500405e-05,
      "loss": 0.5939,
      "step": 26667
    },
    {
      "epoch": 0.8192178908241944,
      "grad_norm": 0.35801512002944946,
      "learning_rate": 1.2829548128446867e-05,
      "loss": 0.5537,
      "step": 26668
    },
    {
      "epoch": 0.8192486099591435,
      "grad_norm": 0.3291199803352356,
      "learning_rate": 1.2829084597784717e-05,
      "loss": 0.5551,
      "step": 26669
    },
    {
      "epoch": 0.8192793290940927,
      "grad_norm": 0.3493121266365051,
      "learning_rate": 1.2828621060515048e-05,
      "loss": 0.5811,
      "step": 26670
    },
    {
      "epoch": 0.8193100482290419,
      "grad_norm": 0.339057594537735,
      "learning_rate": 1.2828157516638935e-05,
      "loss": 0.5661,
      "step": 26671
    },
    {
      "epoch": 0.8193407673639911,
      "grad_norm": 0.3333013951778412,
      "learning_rate": 1.2827693966157462e-05,
      "loss": 0.4752,
      "step": 26672
    },
    {
      "epoch": 0.8193714864989402,
      "grad_norm": 0.3755849003791809,
      "learning_rate": 1.2827230409071711e-05,
      "loss": 0.5246,
      "step": 26673
    },
    {
      "epoch": 0.8194022056338893,
      "grad_norm": 0.35570818185806274,
      "learning_rate": 1.2826766845382767e-05,
      "loss": 0.5083,
      "step": 26674
    },
    {
      "epoch": 0.8194329247688386,
      "grad_norm": 0.34806710481643677,
      "learning_rate": 1.2826303275091711e-05,
      "loss": 0.5784,
      "step": 26675
    },
    {
      "epoch": 0.8194636439037877,
      "grad_norm": 0.3820943832397461,
      "learning_rate": 1.2825839698199628e-05,
      "loss": 0.5229,
      "step": 26676
    },
    {
      "epoch": 0.8194943630387368,
      "grad_norm": 0.4037698209285736,
      "learning_rate": 1.2825376114707597e-05,
      "loss": 0.4678,
      "step": 26677
    },
    {
      "epoch": 0.819525082173686,
      "grad_norm": 0.3750264048576355,
      "learning_rate": 1.2824912524616704e-05,
      "loss": 0.5624,
      "step": 26678
    },
    {
      "epoch": 0.8195558013086351,
      "grad_norm": 0.3362840712070465,
      "learning_rate": 1.2824448927928031e-05,
      "loss": 0.443,
      "step": 26679
    },
    {
      "epoch": 0.8195865204435843,
      "grad_norm": 0.329715758562088,
      "learning_rate": 1.2823985324642658e-05,
      "loss": 0.4974,
      "step": 26680
    },
    {
      "epoch": 0.8196172395785335,
      "grad_norm": 0.3688911199569702,
      "learning_rate": 1.2823521714761672e-05,
      "loss": 0.5821,
      "step": 26681
    },
    {
      "epoch": 0.8196479587134826,
      "grad_norm": 0.34257587790489197,
      "learning_rate": 1.2823058098286153e-05,
      "loss": 0.5317,
      "step": 26682
    },
    {
      "epoch": 0.8196786778484317,
      "grad_norm": 0.3699883818626404,
      "learning_rate": 1.2822594475217183e-05,
      "loss": 0.518,
      "step": 26683
    },
    {
      "epoch": 0.819709396983381,
      "grad_norm": 0.37947767972946167,
      "learning_rate": 1.282213084555585e-05,
      "loss": 0.5747,
      "step": 26684
    },
    {
      "epoch": 0.8197401161183301,
      "grad_norm": 0.3992612957954407,
      "learning_rate": 1.2821667209303233e-05,
      "loss": 0.579,
      "step": 26685
    },
    {
      "epoch": 0.8197708352532793,
      "grad_norm": 0.38369929790496826,
      "learning_rate": 1.2821203566460414e-05,
      "loss": 0.5787,
      "step": 26686
    },
    {
      "epoch": 0.8198015543882284,
      "grad_norm": 0.40040698647499084,
      "learning_rate": 1.2820739917028474e-05,
      "loss": 0.515,
      "step": 26687
    },
    {
      "epoch": 0.8198322735231776,
      "grad_norm": 0.3496083915233612,
      "learning_rate": 1.2820276261008504e-05,
      "loss": 0.5482,
      "step": 26688
    },
    {
      "epoch": 0.8198629926581268,
      "grad_norm": 0.3906041085720062,
      "learning_rate": 1.2819812598401579e-05,
      "loss": 0.5083,
      "step": 26689
    },
    {
      "epoch": 0.8198937117930759,
      "grad_norm": 0.5139492154121399,
      "learning_rate": 1.2819348929208786e-05,
      "loss": 0.6354,
      "step": 26690
    },
    {
      "epoch": 0.819924430928025,
      "grad_norm": 0.36296072602272034,
      "learning_rate": 1.2818885253431208e-05,
      "loss": 0.5452,
      "step": 26691
    },
    {
      "epoch": 0.8199551500629743,
      "grad_norm": 0.4085529148578644,
      "learning_rate": 1.2818421571069923e-05,
      "loss": 0.4984,
      "step": 26692
    },
    {
      "epoch": 0.8199858691979234,
      "grad_norm": 0.3664094805717468,
      "learning_rate": 1.2817957882126023e-05,
      "loss": 0.5381,
      "step": 26693
    },
    {
      "epoch": 0.8200165883328725,
      "grad_norm": 0.3694048821926117,
      "learning_rate": 1.2817494186600578e-05,
      "loss": 0.5276,
      "step": 26694
    },
    {
      "epoch": 0.8200473074678217,
      "grad_norm": 0.35093119740486145,
      "learning_rate": 1.2817030484494684e-05,
      "loss": 0.5999,
      "step": 26695
    },
    {
      "epoch": 0.8200780266027708,
      "grad_norm": 0.437137246131897,
      "learning_rate": 1.2816566775809415e-05,
      "loss": 0.6814,
      "step": 26696
    },
    {
      "epoch": 0.8201087457377201,
      "grad_norm": 0.34527620673179626,
      "learning_rate": 1.2816103060545862e-05,
      "loss": 0.5225,
      "step": 26697
    },
    {
      "epoch": 0.8201394648726692,
      "grad_norm": 0.41106754541397095,
      "learning_rate": 1.2815639338705099e-05,
      "loss": 0.6017,
      "step": 26698
    },
    {
      "epoch": 0.8201701840076183,
      "grad_norm": 0.37421828508377075,
      "learning_rate": 1.2815175610288218e-05,
      "loss": 0.5909,
      "step": 26699
    },
    {
      "epoch": 0.8202009031425676,
      "grad_norm": 0.35073021054267883,
      "learning_rate": 1.2814711875296297e-05,
      "loss": 0.565,
      "step": 26700
    },
    {
      "epoch": 0.8202316222775167,
      "grad_norm": 0.3860192596912384,
      "learning_rate": 1.2814248133730415e-05,
      "loss": 0.5472,
      "step": 26701
    },
    {
      "epoch": 0.8202623414124658,
      "grad_norm": 0.4029444754123688,
      "learning_rate": 1.2813784385591665e-05,
      "loss": 0.6072,
      "step": 26702
    },
    {
      "epoch": 0.820293060547415,
      "grad_norm": 0.4001292288303375,
      "learning_rate": 1.2813320630881121e-05,
      "loss": 0.4705,
      "step": 26703
    },
    {
      "epoch": 0.8203237796823641,
      "grad_norm": 0.3801327049732208,
      "learning_rate": 1.2812856869599874e-05,
      "loss": 0.5505,
      "step": 26704
    },
    {
      "epoch": 0.8203544988173133,
      "grad_norm": 0.33018672466278076,
      "learning_rate": 1.2812393101749003e-05,
      "loss": 0.4962,
      "step": 26705
    },
    {
      "epoch": 0.8203852179522625,
      "grad_norm": 0.37238186597824097,
      "learning_rate": 1.281192932732959e-05,
      "loss": 0.5396,
      "step": 26706
    },
    {
      "epoch": 0.8204159370872116,
      "grad_norm": 0.3814857006072998,
      "learning_rate": 1.281146554634272e-05,
      "loss": 0.5173,
      "step": 26707
    },
    {
      "epoch": 0.8204466562221607,
      "grad_norm": 0.3562465310096741,
      "learning_rate": 1.2811001758789476e-05,
      "loss": 0.6026,
      "step": 26708
    },
    {
      "epoch": 0.82047737535711,
      "grad_norm": 0.3753871023654938,
      "learning_rate": 1.2810537964670945e-05,
      "loss": 0.5792,
      "step": 26709
    },
    {
      "epoch": 0.8205080944920591,
      "grad_norm": 0.3687065839767456,
      "learning_rate": 1.28100741639882e-05,
      "loss": 0.5179,
      "step": 26710
    },
    {
      "epoch": 0.8205388136270083,
      "grad_norm": 0.36655738949775696,
      "learning_rate": 1.2809610356742335e-05,
      "loss": 0.5491,
      "step": 26711
    },
    {
      "epoch": 0.8205695327619574,
      "grad_norm": 0.3550429046154022,
      "learning_rate": 1.2809146542934423e-05,
      "loss": 0.5543,
      "step": 26712
    },
    {
      "epoch": 0.8206002518969066,
      "grad_norm": 0.3327757716178894,
      "learning_rate": 1.280868272256556e-05,
      "loss": 0.5317,
      "step": 26713
    },
    {
      "epoch": 0.8206309710318558,
      "grad_norm": 0.3832915425300598,
      "learning_rate": 1.2808218895636817e-05,
      "loss": 0.5817,
      "step": 26714
    },
    {
      "epoch": 0.8206616901668049,
      "grad_norm": 0.34611573815345764,
      "learning_rate": 1.2807755062149286e-05,
      "loss": 0.5941,
      "step": 26715
    },
    {
      "epoch": 0.820692409301754,
      "grad_norm": 0.3728242814540863,
      "learning_rate": 1.2807291222104045e-05,
      "loss": 0.6172,
      "step": 26716
    },
    {
      "epoch": 0.8207231284367033,
      "grad_norm": 0.46497318148612976,
      "learning_rate": 1.280682737550218e-05,
      "loss": 0.5529,
      "step": 26717
    },
    {
      "epoch": 0.8207538475716524,
      "grad_norm": 0.35321682691574097,
      "learning_rate": 1.2806363522344775e-05,
      "loss": 0.5499,
      "step": 26718
    },
    {
      "epoch": 0.8207845667066015,
      "grad_norm": 0.3575892746448517,
      "learning_rate": 1.2805899662632908e-05,
      "loss": 0.5575,
      "step": 26719
    },
    {
      "epoch": 0.8208152858415507,
      "grad_norm": 0.3471446931362152,
      "learning_rate": 1.2805435796367672e-05,
      "loss": 0.5099,
      "step": 26720
    },
    {
      "epoch": 0.8208460049764998,
      "grad_norm": 0.36770880222320557,
      "learning_rate": 1.2804971923550139e-05,
      "loss": 0.4932,
      "step": 26721
    },
    {
      "epoch": 0.8208767241114491,
      "grad_norm": 0.4726170599460602,
      "learning_rate": 1.2804508044181402e-05,
      "loss": 0.5631,
      "step": 26722
    },
    {
      "epoch": 0.8209074432463982,
      "grad_norm": 0.3833828866481781,
      "learning_rate": 1.2804044158262541e-05,
      "loss": 0.504,
      "step": 26723
    },
    {
      "epoch": 0.8209381623813473,
      "grad_norm": 0.4034837484359741,
      "learning_rate": 1.2803580265794637e-05,
      "loss": 0.5531,
      "step": 26724
    },
    {
      "epoch": 0.8209688815162965,
      "grad_norm": 0.3792079985141754,
      "learning_rate": 1.2803116366778778e-05,
      "loss": 0.541,
      "step": 26725
    },
    {
      "epoch": 0.8209996006512457,
      "grad_norm": 0.41782286763191223,
      "learning_rate": 1.280265246121604e-05,
      "loss": 0.476,
      "step": 26726
    },
    {
      "epoch": 0.8210303197861948,
      "grad_norm": 0.3573938310146332,
      "learning_rate": 1.2802188549107517e-05,
      "loss": 0.5147,
      "step": 26727
    },
    {
      "epoch": 0.821061038921144,
      "grad_norm": 0.38235488533973694,
      "learning_rate": 1.2801724630454282e-05,
      "loss": 0.5427,
      "step": 26728
    },
    {
      "epoch": 0.8210917580560931,
      "grad_norm": 0.3863923251628876,
      "learning_rate": 1.2801260705257428e-05,
      "loss": 0.6262,
      "step": 26729
    },
    {
      "epoch": 0.8211224771910423,
      "grad_norm": 0.37784674763679504,
      "learning_rate": 1.2800796773518031e-05,
      "loss": 0.5754,
      "step": 26730
    },
    {
      "epoch": 0.8211531963259915,
      "grad_norm": 0.3436751067638397,
      "learning_rate": 1.280033283523718e-05,
      "loss": 0.586,
      "step": 26731
    },
    {
      "epoch": 0.8211839154609406,
      "grad_norm": 0.40518346428871155,
      "learning_rate": 1.2799868890415952e-05,
      "loss": 0.5715,
      "step": 26732
    },
    {
      "epoch": 0.8212146345958897,
      "grad_norm": 0.3475019633769989,
      "learning_rate": 1.279940493905544e-05,
      "loss": 0.5247,
      "step": 26733
    },
    {
      "epoch": 0.821245353730839,
      "grad_norm": 0.34351521730422974,
      "learning_rate": 1.279894098115672e-05,
      "loss": 0.5635,
      "step": 26734
    },
    {
      "epoch": 0.8212760728657881,
      "grad_norm": 0.37029629945755005,
      "learning_rate": 1.2798477016720876e-05,
      "loss": 0.607,
      "step": 26735
    },
    {
      "epoch": 0.8213067920007373,
      "grad_norm": 0.3678818941116333,
      "learning_rate": 1.2798013045748996e-05,
      "loss": 0.5678,
      "step": 26736
    },
    {
      "epoch": 0.8213375111356864,
      "grad_norm": 0.34143924713134766,
      "learning_rate": 1.2797549068242156e-05,
      "loss": 0.5007,
      "step": 26737
    },
    {
      "epoch": 0.8213682302706355,
      "grad_norm": 0.5050284266471863,
      "learning_rate": 1.279708508420145e-05,
      "loss": 0.6013,
      "step": 26738
    },
    {
      "epoch": 0.8213989494055848,
      "grad_norm": 0.47670185565948486,
      "learning_rate": 1.2796621093627955e-05,
      "loss": 0.5924,
      "step": 26739
    },
    {
      "epoch": 0.8214296685405339,
      "grad_norm": 0.3413056433200836,
      "learning_rate": 1.2796157096522757e-05,
      "loss": 0.533,
      "step": 26740
    },
    {
      "epoch": 0.821460387675483,
      "grad_norm": 0.39173343777656555,
      "learning_rate": 1.2795693092886938e-05,
      "loss": 0.6103,
      "step": 26741
    },
    {
      "epoch": 0.8214911068104322,
      "grad_norm": 0.5585837364196777,
      "learning_rate": 1.2795229082721583e-05,
      "loss": 0.518,
      "step": 26742
    },
    {
      "epoch": 0.8215218259453814,
      "grad_norm": 0.3740701973438263,
      "learning_rate": 1.2794765066027776e-05,
      "loss": 0.5775,
      "step": 26743
    },
    {
      "epoch": 0.8215525450803305,
      "grad_norm": 0.36743295192718506,
      "learning_rate": 1.2794301042806599e-05,
      "loss": 0.4785,
      "step": 26744
    },
    {
      "epoch": 0.8215832642152797,
      "grad_norm": 0.40714138746261597,
      "learning_rate": 1.2793837013059136e-05,
      "loss": 0.7104,
      "step": 26745
    },
    {
      "epoch": 0.8216139833502288,
      "grad_norm": 0.3550049960613251,
      "learning_rate": 1.279337297678647e-05,
      "loss": 0.5227,
      "step": 26746
    },
    {
      "epoch": 0.8216447024851781,
      "grad_norm": 0.5305242538452148,
      "learning_rate": 1.2792908933989691e-05,
      "loss": 0.5546,
      "step": 26747
    },
    {
      "epoch": 0.8216754216201272,
      "grad_norm": 0.36983272433280945,
      "learning_rate": 1.2792444884669874e-05,
      "loss": 0.5626,
      "step": 26748
    },
    {
      "epoch": 0.8217061407550763,
      "grad_norm": 0.335239052772522,
      "learning_rate": 1.279198082882811e-05,
      "loss": 0.464,
      "step": 26749
    },
    {
      "epoch": 0.8217368598900255,
      "grad_norm": 0.371987521648407,
      "learning_rate": 1.2791516766465477e-05,
      "loss": 0.548,
      "step": 26750
    },
    {
      "epoch": 0.8217675790249747,
      "grad_norm": 0.406223863363266,
      "learning_rate": 1.2791052697583065e-05,
      "loss": 0.4932,
      "step": 26751
    },
    {
      "epoch": 0.8217982981599238,
      "grad_norm": 0.4156668186187744,
      "learning_rate": 1.2790588622181954e-05,
      "loss": 0.4178,
      "step": 26752
    },
    {
      "epoch": 0.821829017294873,
      "grad_norm": 0.3877778649330139,
      "learning_rate": 1.2790124540263227e-05,
      "loss": 0.5047,
      "step": 26753
    },
    {
      "epoch": 0.8218597364298221,
      "grad_norm": 0.38718461990356445,
      "learning_rate": 1.2789660451827968e-05,
      "loss": 0.582,
      "step": 26754
    },
    {
      "epoch": 0.8218904555647712,
      "grad_norm": 0.40484949946403503,
      "learning_rate": 1.278919635687726e-05,
      "loss": 0.5661,
      "step": 26755
    },
    {
      "epoch": 0.8219211746997205,
      "grad_norm": 0.4513966143131256,
      "learning_rate": 1.2788732255412195e-05,
      "loss": 0.5186,
      "step": 26756
    },
    {
      "epoch": 0.8219518938346696,
      "grad_norm": 0.3226415514945984,
      "learning_rate": 1.2788268147433848e-05,
      "loss": 0.5148,
      "step": 26757
    },
    {
      "epoch": 0.8219826129696188,
      "grad_norm": 0.3763408660888672,
      "learning_rate": 1.2787804032943308e-05,
      "loss": 0.5695,
      "step": 26758
    },
    {
      "epoch": 0.822013332104568,
      "grad_norm": 0.368598610162735,
      "learning_rate": 1.2787339911941653e-05,
      "loss": 0.5626,
      "step": 26759
    },
    {
      "epoch": 0.8220440512395171,
      "grad_norm": 0.3578270971775055,
      "learning_rate": 1.2786875784429975e-05,
      "loss": 0.5795,
      "step": 26760
    },
    {
      "epoch": 0.8220747703744663,
      "grad_norm": 0.3226490318775177,
      "learning_rate": 1.2786411650409353e-05,
      "loss": 0.5813,
      "step": 26761
    },
    {
      "epoch": 0.8221054895094154,
      "grad_norm": 0.37337321043014526,
      "learning_rate": 1.2785947509880869e-05,
      "loss": 0.557,
      "step": 26762
    },
    {
      "epoch": 0.8221362086443645,
      "grad_norm": 0.49872303009033203,
      "learning_rate": 1.2785483362845614e-05,
      "loss": 0.5425,
      "step": 26763
    },
    {
      "epoch": 0.8221669277793138,
      "grad_norm": 0.3626422882080078,
      "learning_rate": 1.2785019209304666e-05,
      "loss": 0.5195,
      "step": 26764
    },
    {
      "epoch": 0.8221976469142629,
      "grad_norm": 0.37069860100746155,
      "learning_rate": 1.2784555049259113e-05,
      "loss": 0.5335,
      "step": 26765
    },
    {
      "epoch": 0.822228366049212,
      "grad_norm": 0.3670347034931183,
      "learning_rate": 1.2784090882710034e-05,
      "loss": 0.5626,
      "step": 26766
    },
    {
      "epoch": 0.8222590851841612,
      "grad_norm": 0.3780268728733063,
      "learning_rate": 1.2783626709658522e-05,
      "loss": 0.4562,
      "step": 26767
    },
    {
      "epoch": 0.8222898043191104,
      "grad_norm": 0.37552404403686523,
      "learning_rate": 1.278316253010565e-05,
      "loss": 0.5114,
      "step": 26768
    },
    {
      "epoch": 0.8223205234540595,
      "grad_norm": 0.43956393003463745,
      "learning_rate": 1.2782698344052508e-05,
      "loss": 0.5657,
      "step": 26769
    },
    {
      "epoch": 0.8223512425890087,
      "grad_norm": 0.38764679431915283,
      "learning_rate": 1.2782234151500183e-05,
      "loss": 0.4983,
      "step": 26770
    },
    {
      "epoch": 0.8223819617239578,
      "grad_norm": 0.3429953455924988,
      "learning_rate": 1.2781769952449752e-05,
      "loss": 0.5026,
      "step": 26771
    },
    {
      "epoch": 0.8224126808589071,
      "grad_norm": 0.3669179081916809,
      "learning_rate": 1.2781305746902305e-05,
      "loss": 0.5748,
      "step": 26772
    },
    {
      "epoch": 0.8224433999938562,
      "grad_norm": 0.33010101318359375,
      "learning_rate": 1.2780841534858923e-05,
      "loss": 0.4762,
      "step": 26773
    },
    {
      "epoch": 0.8224741191288053,
      "grad_norm": 0.3292222023010254,
      "learning_rate": 1.2780377316320691e-05,
      "loss": 0.5554,
      "step": 26774
    },
    {
      "epoch": 0.8225048382637545,
      "grad_norm": 0.366773396730423,
      "learning_rate": 1.2779913091288698e-05,
      "loss": 0.5085,
      "step": 26775
    },
    {
      "epoch": 0.8225355573987037,
      "grad_norm": 0.32205116748809814,
      "learning_rate": 1.2779448859764018e-05,
      "loss": 0.4829,
      "step": 26776
    },
    {
      "epoch": 0.8225662765336528,
      "grad_norm": 0.37212973833084106,
      "learning_rate": 1.2778984621747745e-05,
      "loss": 0.4899,
      "step": 26777
    },
    {
      "epoch": 0.822596995668602,
      "grad_norm": 0.36014336347579956,
      "learning_rate": 1.2778520377240957e-05,
      "loss": 0.4827,
      "step": 26778
    },
    {
      "epoch": 0.8226277148035511,
      "grad_norm": 0.34410375356674194,
      "learning_rate": 1.2778056126244745e-05,
      "loss": 0.4871,
      "step": 26779
    },
    {
      "epoch": 0.8226584339385002,
      "grad_norm": 0.4373578429222107,
      "learning_rate": 1.2777591868760184e-05,
      "loss": 0.5882,
      "step": 26780
    },
    {
      "epoch": 0.8226891530734495,
      "grad_norm": 0.3046109676361084,
      "learning_rate": 1.2777127604788366e-05,
      "loss": 0.4645,
      "step": 26781
    },
    {
      "epoch": 0.8227198722083986,
      "grad_norm": 0.4053085446357727,
      "learning_rate": 1.2776663334330368e-05,
      "loss": 0.5191,
      "step": 26782
    },
    {
      "epoch": 0.8227505913433478,
      "grad_norm": 0.36246129870414734,
      "learning_rate": 1.2776199057387284e-05,
      "loss": 0.5998,
      "step": 26783
    },
    {
      "epoch": 0.822781310478297,
      "grad_norm": 0.33636635541915894,
      "learning_rate": 1.277573477396019e-05,
      "loss": 0.5795,
      "step": 26784
    },
    {
      "epoch": 0.8228120296132461,
      "grad_norm": 0.3409971296787262,
      "learning_rate": 1.2775270484050177e-05,
      "loss": 0.5192,
      "step": 26785
    },
    {
      "epoch": 0.8228427487481953,
      "grad_norm": 0.40819644927978516,
      "learning_rate": 1.2774806187658325e-05,
      "loss": 0.5866,
      "step": 26786
    },
    {
      "epoch": 0.8228734678831444,
      "grad_norm": 0.41970014572143555,
      "learning_rate": 1.2774341884785717e-05,
      "loss": 0.4936,
      "step": 26787
    },
    {
      "epoch": 0.8229041870180935,
      "grad_norm": 0.3668977618217468,
      "learning_rate": 1.2773877575433442e-05,
      "loss": 0.5205,
      "step": 26788
    },
    {
      "epoch": 0.8229349061530428,
      "grad_norm": 0.34369248151779175,
      "learning_rate": 1.277341325960258e-05,
      "loss": 0.5426,
      "step": 26789
    },
    {
      "epoch": 0.8229656252879919,
      "grad_norm": 0.3897152841091156,
      "learning_rate": 1.277294893729422e-05,
      "loss": 0.5675,
      "step": 26790
    },
    {
      "epoch": 0.822996344422941,
      "grad_norm": 0.3764110803604126,
      "learning_rate": 1.2772484608509443e-05,
      "loss": 0.6267,
      "step": 26791
    },
    {
      "epoch": 0.8230270635578902,
      "grad_norm": 0.4301290214061737,
      "learning_rate": 1.2772020273249333e-05,
      "loss": 0.6093,
      "step": 26792
    },
    {
      "epoch": 0.8230577826928394,
      "grad_norm": 0.6676391363143921,
      "learning_rate": 1.2771555931514978e-05,
      "loss": 0.5102,
      "step": 26793
    },
    {
      "epoch": 0.8230885018277885,
      "grad_norm": 0.3693092167377472,
      "learning_rate": 1.277109158330746e-05,
      "loss": 0.5582,
      "step": 26794
    },
    {
      "epoch": 0.8231192209627377,
      "grad_norm": 0.45971009135246277,
      "learning_rate": 1.2770627228627865e-05,
      "loss": 0.538,
      "step": 26795
    },
    {
      "epoch": 0.8231499400976868,
      "grad_norm": 0.37034544348716736,
      "learning_rate": 1.2770162867477276e-05,
      "loss": 0.6277,
      "step": 26796
    },
    {
      "epoch": 0.8231806592326361,
      "grad_norm": 0.3900626599788666,
      "learning_rate": 1.2769698499856777e-05,
      "loss": 0.5843,
      "step": 26797
    },
    {
      "epoch": 0.8232113783675852,
      "grad_norm": 0.3887786865234375,
      "learning_rate": 1.2769234125767453e-05,
      "loss": 0.5802,
      "step": 26798
    },
    {
      "epoch": 0.8232420975025343,
      "grad_norm": 0.37746381759643555,
      "learning_rate": 1.2768769745210394e-05,
      "loss": 0.5901,
      "step": 26799
    },
    {
      "epoch": 0.8232728166374835,
      "grad_norm": 0.35790348052978516,
      "learning_rate": 1.2768305358186677e-05,
      "loss": 0.6135,
      "step": 26800
    },
    {
      "epoch": 0.8233035357724326,
      "grad_norm": 0.38836193084716797,
      "learning_rate": 1.2767840964697388e-05,
      "loss": 0.5796,
      "step": 26801
    },
    {
      "epoch": 0.8233342549073818,
      "grad_norm": 0.46421217918395996,
      "learning_rate": 1.2767376564743614e-05,
      "loss": 0.5787,
      "step": 26802
    },
    {
      "epoch": 0.823364974042331,
      "grad_norm": 0.418083131313324,
      "learning_rate": 1.276691215832644e-05,
      "loss": 0.5466,
      "step": 26803
    },
    {
      "epoch": 0.8233956931772801,
      "grad_norm": 0.3977488875389099,
      "learning_rate": 1.276644774544695e-05,
      "loss": 0.5682,
      "step": 26804
    },
    {
      "epoch": 0.8234264123122292,
      "grad_norm": 0.3695371448993683,
      "learning_rate": 1.2765983326106226e-05,
      "loss": 0.51,
      "step": 26805
    },
    {
      "epoch": 0.8234571314471785,
      "grad_norm": 0.3585805594921112,
      "learning_rate": 1.2765518900305356e-05,
      "loss": 0.4962,
      "step": 26806
    },
    {
      "epoch": 0.8234878505821276,
      "grad_norm": 0.35752803087234497,
      "learning_rate": 1.2765054468045424e-05,
      "loss": 0.4904,
      "step": 26807
    },
    {
      "epoch": 0.8235185697170768,
      "grad_norm": 0.38967427611351013,
      "learning_rate": 1.2764590029327512e-05,
      "loss": 0.6543,
      "step": 26808
    },
    {
      "epoch": 0.8235492888520259,
      "grad_norm": 0.3433436155319214,
      "learning_rate": 1.2764125584152708e-05,
      "loss": 0.5978,
      "step": 26809
    },
    {
      "epoch": 0.8235800079869751,
      "grad_norm": 0.40899115800857544,
      "learning_rate": 1.2763661132522094e-05,
      "loss": 0.6373,
      "step": 26810
    },
    {
      "epoch": 0.8236107271219243,
      "grad_norm": 0.35696741938591003,
      "learning_rate": 1.276319667443676e-05,
      "loss": 0.5826,
      "step": 26811
    },
    {
      "epoch": 0.8236414462568734,
      "grad_norm": 0.41100433468818665,
      "learning_rate": 1.2762732209897783e-05,
      "loss": 0.5697,
      "step": 26812
    },
    {
      "epoch": 0.8236721653918225,
      "grad_norm": 0.44887465238571167,
      "learning_rate": 1.2762267738906257e-05,
      "loss": 0.6413,
      "step": 26813
    },
    {
      "epoch": 0.8237028845267718,
      "grad_norm": 0.3456462025642395,
      "learning_rate": 1.2761803261463257e-05,
      "loss": 0.5103,
      "step": 26814
    },
    {
      "epoch": 0.8237336036617209,
      "grad_norm": 0.35223740339279175,
      "learning_rate": 1.2761338777569877e-05,
      "loss": 0.5871,
      "step": 26815
    },
    {
      "epoch": 0.82376432279667,
      "grad_norm": 0.368351012468338,
      "learning_rate": 1.2760874287227194e-05,
      "loss": 0.5548,
      "step": 26816
    },
    {
      "epoch": 0.8237950419316192,
      "grad_norm": 0.34283551573753357,
      "learning_rate": 1.2760409790436298e-05,
      "loss": 0.5349,
      "step": 26817
    },
    {
      "epoch": 0.8238257610665684,
      "grad_norm": 0.35810235142707825,
      "learning_rate": 1.2759945287198272e-05,
      "loss": 0.5539,
      "step": 26818
    },
    {
      "epoch": 0.8238564802015175,
      "grad_norm": 0.3546234667301178,
      "learning_rate": 1.2759480777514201e-05,
      "loss": 0.5259,
      "step": 26819
    },
    {
      "epoch": 0.8238871993364667,
      "grad_norm": 0.39571818709373474,
      "learning_rate": 1.275901626138517e-05,
      "loss": 0.5375,
      "step": 26820
    },
    {
      "epoch": 0.8239179184714158,
      "grad_norm": 0.3384588658809662,
      "learning_rate": 1.2758551738812263e-05,
      "loss": 0.524,
      "step": 26821
    },
    {
      "epoch": 0.823948637606365,
      "grad_norm": 0.372892290353775,
      "learning_rate": 1.2758087209796568e-05,
      "loss": 0.6188,
      "step": 26822
    },
    {
      "epoch": 0.8239793567413142,
      "grad_norm": 0.3606509864330292,
      "learning_rate": 1.2757622674339163e-05,
      "loss": 0.587,
      "step": 26823
    },
    {
      "epoch": 0.8240100758762633,
      "grad_norm": 0.37478670477867126,
      "learning_rate": 1.2757158132441144e-05,
      "loss": 0.5401,
      "step": 26824
    },
    {
      "epoch": 0.8240407950112125,
      "grad_norm": 0.38098853826522827,
      "learning_rate": 1.2756693584103583e-05,
      "loss": 0.5314,
      "step": 26825
    },
    {
      "epoch": 0.8240715141461616,
      "grad_norm": 0.34779244661331177,
      "learning_rate": 1.2756229029327577e-05,
      "loss": 0.5331,
      "step": 26826
    },
    {
      "epoch": 0.8241022332811108,
      "grad_norm": 0.37429696321487427,
      "learning_rate": 1.2755764468114202e-05,
      "loss": 0.4587,
      "step": 26827
    },
    {
      "epoch": 0.82413295241606,
      "grad_norm": 0.35360005497932434,
      "learning_rate": 1.2755299900464546e-05,
      "loss": 0.571,
      "step": 26828
    },
    {
      "epoch": 0.8241636715510091,
      "grad_norm": 0.3332570195198059,
      "learning_rate": 1.2754835326379697e-05,
      "loss": 0.561,
      "step": 26829
    },
    {
      "epoch": 0.8241943906859582,
      "grad_norm": 0.397350937128067,
      "learning_rate": 1.2754370745860737e-05,
      "loss": 0.6306,
      "step": 26830
    },
    {
      "epoch": 0.8242251098209075,
      "grad_norm": 0.417923241853714,
      "learning_rate": 1.2753906158908753e-05,
      "loss": 0.5376,
      "step": 26831
    },
    {
      "epoch": 0.8242558289558566,
      "grad_norm": 0.333925724029541,
      "learning_rate": 1.2753441565524826e-05,
      "loss": 0.5374,
      "step": 26832
    },
    {
      "epoch": 0.8242865480908058,
      "grad_norm": 0.3473578095436096,
      "learning_rate": 1.2752976965710048e-05,
      "loss": 0.4906,
      "step": 26833
    },
    {
      "epoch": 0.8243172672257549,
      "grad_norm": 0.39683812856674194,
      "learning_rate": 1.2752512359465499e-05,
      "loss": 0.5508,
      "step": 26834
    },
    {
      "epoch": 0.824347986360704,
      "grad_norm": 0.3640992343425751,
      "learning_rate": 1.2752047746792264e-05,
      "loss": 0.5713,
      "step": 26835
    },
    {
      "epoch": 0.8243787054956533,
      "grad_norm": 0.3662235140800476,
      "learning_rate": 1.275158312769143e-05,
      "loss": 0.4979,
      "step": 26836
    },
    {
      "epoch": 0.8244094246306024,
      "grad_norm": 0.3674812614917755,
      "learning_rate": 1.2751118502164079e-05,
      "loss": 0.6574,
      "step": 26837
    },
    {
      "epoch": 0.8244401437655515,
      "grad_norm": 0.4277437925338745,
      "learning_rate": 1.2750653870211302e-05,
      "loss": 0.6209,
      "step": 26838
    },
    {
      "epoch": 0.8244708629005008,
      "grad_norm": 0.45715996623039246,
      "learning_rate": 1.2750189231834178e-05,
      "loss": 0.6132,
      "step": 26839
    },
    {
      "epoch": 0.8245015820354499,
      "grad_norm": 0.37541842460632324,
      "learning_rate": 1.2749724587033799e-05,
      "loss": 0.5107,
      "step": 26840
    },
    {
      "epoch": 0.824532301170399,
      "grad_norm": 0.39178046584129333,
      "learning_rate": 1.274925993581124e-05,
      "loss": 0.6016,
      "step": 26841
    },
    {
      "epoch": 0.8245630203053482,
      "grad_norm": 0.36148911714553833,
      "learning_rate": 1.2748795278167599e-05,
      "loss": 0.5274,
      "step": 26842
    },
    {
      "epoch": 0.8245937394402973,
      "grad_norm": 0.3702152967453003,
      "learning_rate": 1.2748330614103947e-05,
      "loss": 0.5202,
      "step": 26843
    },
    {
      "epoch": 0.8246244585752465,
      "grad_norm": 0.3676576316356659,
      "learning_rate": 1.2747865943621384e-05,
      "loss": 0.6019,
      "step": 26844
    },
    {
      "epoch": 0.8246551777101957,
      "grad_norm": 0.39211785793304443,
      "learning_rate": 1.2747401266720984e-05,
      "loss": 0.4218,
      "step": 26845
    },
    {
      "epoch": 0.8246858968451448,
      "grad_norm": 0.45239949226379395,
      "learning_rate": 1.274693658340384e-05,
      "loss": 0.5222,
      "step": 26846
    },
    {
      "epoch": 0.824716615980094,
      "grad_norm": 0.37645217776298523,
      "learning_rate": 1.274647189367103e-05,
      "loss": 0.5824,
      "step": 26847
    },
    {
      "epoch": 0.8247473351150432,
      "grad_norm": 0.363032728433609,
      "learning_rate": 1.2746007197523644e-05,
      "loss": 0.5464,
      "step": 26848
    },
    {
      "epoch": 0.8247780542499923,
      "grad_norm": 0.3432900309562683,
      "learning_rate": 1.2745542494962768e-05,
      "loss": 0.5581,
      "step": 26849
    },
    {
      "epoch": 0.8248087733849415,
      "grad_norm": 0.3754114508628845,
      "learning_rate": 1.2745077785989483e-05,
      "loss": 0.5808,
      "step": 26850
    },
    {
      "epoch": 0.8248394925198906,
      "grad_norm": 0.39439842104911804,
      "learning_rate": 1.274461307060488e-05,
      "loss": 0.5697,
      "step": 26851
    },
    {
      "epoch": 0.8248702116548398,
      "grad_norm": 0.37234196066856384,
      "learning_rate": 1.2744148348810041e-05,
      "loss": 0.5702,
      "step": 26852
    },
    {
      "epoch": 0.824900930789789,
      "grad_norm": 0.3806943893432617,
      "learning_rate": 1.2743683620606051e-05,
      "loss": 0.5859,
      "step": 26853
    },
    {
      "epoch": 0.8249316499247381,
      "grad_norm": 0.40372806787490845,
      "learning_rate": 1.2743218885993997e-05,
      "loss": 0.5703,
      "step": 26854
    },
    {
      "epoch": 0.8249623690596872,
      "grad_norm": 0.3689137399196625,
      "learning_rate": 1.2742754144974964e-05,
      "loss": 0.5235,
      "step": 26855
    },
    {
      "epoch": 0.8249930881946365,
      "grad_norm": 0.3790273666381836,
      "learning_rate": 1.2742289397550038e-05,
      "loss": 0.6097,
      "step": 26856
    },
    {
      "epoch": 0.8250238073295856,
      "grad_norm": 0.41985780000686646,
      "learning_rate": 1.2741824643720303e-05,
      "loss": 0.5953,
      "step": 26857
    },
    {
      "epoch": 0.8250545264645348,
      "grad_norm": 0.35004517436027527,
      "learning_rate": 1.2741359883486844e-05,
      "loss": 0.5216,
      "step": 26858
    },
    {
      "epoch": 0.8250852455994839,
      "grad_norm": 0.37208735942840576,
      "learning_rate": 1.2740895116850746e-05,
      "loss": 0.5778,
      "step": 26859
    },
    {
      "epoch": 0.825115964734433,
      "grad_norm": 0.37648236751556396,
      "learning_rate": 1.2740430343813099e-05,
      "loss": 0.5732,
      "step": 26860
    },
    {
      "epoch": 0.8251466838693823,
      "grad_norm": 0.40263068675994873,
      "learning_rate": 1.2739965564374982e-05,
      "loss": 0.5155,
      "step": 26861
    },
    {
      "epoch": 0.8251774030043314,
      "grad_norm": 0.3672737181186676,
      "learning_rate": 1.273950077853749e-05,
      "loss": 0.533,
      "step": 26862
    },
    {
      "epoch": 0.8252081221392805,
      "grad_norm": 0.46238163113594055,
      "learning_rate": 1.2739035986301698e-05,
      "loss": 0.4909,
      "step": 26863
    },
    {
      "epoch": 0.8252388412742298,
      "grad_norm": 0.34652939438819885,
      "learning_rate": 1.2738571187668699e-05,
      "loss": 0.5261,
      "step": 26864
    },
    {
      "epoch": 0.8252695604091789,
      "grad_norm": 0.4207092821598053,
      "learning_rate": 1.273810638263957e-05,
      "loss": 0.5476,
      "step": 26865
    },
    {
      "epoch": 0.825300279544128,
      "grad_norm": 0.37135830521583557,
      "learning_rate": 1.2737641571215406e-05,
      "loss": 0.5362,
      "step": 26866
    },
    {
      "epoch": 0.8253309986790772,
      "grad_norm": 0.3719664514064789,
      "learning_rate": 1.2737176753397292e-05,
      "loss": 0.6143,
      "step": 26867
    },
    {
      "epoch": 0.8253617178140263,
      "grad_norm": 0.3867357671260834,
      "learning_rate": 1.2736711929186305e-05,
      "loss": 0.5495,
      "step": 26868
    },
    {
      "epoch": 0.8253924369489756,
      "grad_norm": 0.3801984488964081,
      "learning_rate": 1.2736247098583541e-05,
      "loss": 0.5278,
      "step": 26869
    },
    {
      "epoch": 0.8254231560839247,
      "grad_norm": 0.34425270557403564,
      "learning_rate": 1.2735782261590078e-05,
      "loss": 0.5789,
      "step": 26870
    },
    {
      "epoch": 0.8254538752188738,
      "grad_norm": 0.4063805639743805,
      "learning_rate": 1.2735317418207005e-05,
      "loss": 0.5427,
      "step": 26871
    },
    {
      "epoch": 0.825484594353823,
      "grad_norm": 0.5455687642097473,
      "learning_rate": 1.2734852568435408e-05,
      "loss": 0.5392,
      "step": 26872
    },
    {
      "epoch": 0.8255153134887722,
      "grad_norm": 0.3391919732093811,
      "learning_rate": 1.273438771227637e-05,
      "loss": 0.5047,
      "step": 26873
    },
    {
      "epoch": 0.8255460326237213,
      "grad_norm": 0.38795292377471924,
      "learning_rate": 1.273392284973098e-05,
      "loss": 0.5467,
      "step": 26874
    },
    {
      "epoch": 0.8255767517586705,
      "grad_norm": 0.3745496869087219,
      "learning_rate": 1.273345798080032e-05,
      "loss": 0.5546,
      "step": 26875
    },
    {
      "epoch": 0.8256074708936196,
      "grad_norm": 0.39853647351264954,
      "learning_rate": 1.2732993105485483e-05,
      "loss": 0.5213,
      "step": 26876
    },
    {
      "epoch": 0.8256381900285688,
      "grad_norm": 0.3566369414329529,
      "learning_rate": 1.2732528223787543e-05,
      "loss": 0.5282,
      "step": 26877
    },
    {
      "epoch": 0.825668909163518,
      "grad_norm": 0.5854928493499756,
      "learning_rate": 1.2732063335707599e-05,
      "loss": 0.5305,
      "step": 26878
    },
    {
      "epoch": 0.8256996282984671,
      "grad_norm": 0.3376336991786957,
      "learning_rate": 1.2731598441246726e-05,
      "loss": 0.4939,
      "step": 26879
    },
    {
      "epoch": 0.8257303474334162,
      "grad_norm": 0.3565661311149597,
      "learning_rate": 1.2731133540406017e-05,
      "loss": 0.5843,
      "step": 26880
    },
    {
      "epoch": 0.8257610665683655,
      "grad_norm": 0.40404394268989563,
      "learning_rate": 1.2730668633186551e-05,
      "loss": 0.5342,
      "step": 26881
    },
    {
      "epoch": 0.8257917857033146,
      "grad_norm": 0.35204431414604187,
      "learning_rate": 1.2730203719589422e-05,
      "loss": 0.517,
      "step": 26882
    },
    {
      "epoch": 0.8258225048382638,
      "grad_norm": 0.3748473525047302,
      "learning_rate": 1.2729738799615708e-05,
      "loss": 0.6122,
      "step": 26883
    },
    {
      "epoch": 0.8258532239732129,
      "grad_norm": 0.35082295536994934,
      "learning_rate": 1.27292738732665e-05,
      "loss": 0.506,
      "step": 26884
    },
    {
      "epoch": 0.825883943108162,
      "grad_norm": 0.3450416028499603,
      "learning_rate": 1.2728808940542884e-05,
      "loss": 0.5679,
      "step": 26885
    },
    {
      "epoch": 0.8259146622431113,
      "grad_norm": 0.35869100689888,
      "learning_rate": 1.272834400144594e-05,
      "loss": 0.6147,
      "step": 26886
    },
    {
      "epoch": 0.8259453813780604,
      "grad_norm": 0.41359660029411316,
      "learning_rate": 1.2727879055976762e-05,
      "loss": 0.6054,
      "step": 26887
    },
    {
      "epoch": 0.8259761005130095,
      "grad_norm": 0.43846526741981506,
      "learning_rate": 1.2727414104136429e-05,
      "loss": 0.5724,
      "step": 26888
    },
    {
      "epoch": 0.8260068196479587,
      "grad_norm": 0.3286062777042389,
      "learning_rate": 1.272694914592603e-05,
      "loss": 0.5616,
      "step": 26889
    },
    {
      "epoch": 0.8260375387829079,
      "grad_norm": 0.33664020895957947,
      "learning_rate": 1.2726484181346654e-05,
      "loss": 0.5403,
      "step": 26890
    },
    {
      "epoch": 0.826068257917857,
      "grad_norm": 0.9134952425956726,
      "learning_rate": 1.2726019210399381e-05,
      "loss": 0.6388,
      "step": 26891
    },
    {
      "epoch": 0.8260989770528062,
      "grad_norm": 0.3833390474319458,
      "learning_rate": 1.2725554233085301e-05,
      "loss": 0.5658,
      "step": 26892
    },
    {
      "epoch": 0.8261296961877553,
      "grad_norm": 0.3463684618473053,
      "learning_rate": 1.2725089249405498e-05,
      "loss": 0.4925,
      "step": 26893
    },
    {
      "epoch": 0.8261604153227046,
      "grad_norm": 0.3991931080818176,
      "learning_rate": 1.272462425936106e-05,
      "loss": 0.5404,
      "step": 26894
    },
    {
      "epoch": 0.8261911344576537,
      "grad_norm": 0.397904634475708,
      "learning_rate": 1.2724159262953071e-05,
      "loss": 0.6205,
      "step": 26895
    },
    {
      "epoch": 0.8262218535926028,
      "grad_norm": 0.33627745509147644,
      "learning_rate": 1.2723694260182618e-05,
      "loss": 0.5245,
      "step": 26896
    },
    {
      "epoch": 0.826252572727552,
      "grad_norm": 0.375637948513031,
      "learning_rate": 1.2723229251050784e-05,
      "loss": 0.566,
      "step": 26897
    },
    {
      "epoch": 0.8262832918625012,
      "grad_norm": 0.38891738653182983,
      "learning_rate": 1.2722764235558663e-05,
      "loss": 0.6546,
      "step": 26898
    },
    {
      "epoch": 0.8263140109974503,
      "grad_norm": 0.4169718623161316,
      "learning_rate": 1.2722299213707332e-05,
      "loss": 0.5676,
      "step": 26899
    },
    {
      "epoch": 0.8263447301323995,
      "grad_norm": 0.369071364402771,
      "learning_rate": 1.2721834185497883e-05,
      "loss": 0.5779,
      "step": 26900
    },
    {
      "epoch": 0.8263754492673486,
      "grad_norm": 0.4235658347606659,
      "learning_rate": 1.2721369150931398e-05,
      "loss": 0.5904,
      "step": 26901
    },
    {
      "epoch": 0.8264061684022977,
      "grad_norm": 0.34950998425483704,
      "learning_rate": 1.2720904110008964e-05,
      "loss": 0.5123,
      "step": 26902
    },
    {
      "epoch": 0.826436887537247,
      "grad_norm": 0.39226070046424866,
      "learning_rate": 1.2720439062731673e-05,
      "loss": 0.61,
      "step": 26903
    },
    {
      "epoch": 0.8264676066721961,
      "grad_norm": 0.38144412636756897,
      "learning_rate": 1.2719974009100606e-05,
      "loss": 0.5597,
      "step": 26904
    },
    {
      "epoch": 0.8264983258071452,
      "grad_norm": 0.37281739711761475,
      "learning_rate": 1.2719508949116847e-05,
      "loss": 0.4755,
      "step": 26905
    },
    {
      "epoch": 0.8265290449420944,
      "grad_norm": 0.3847431242465973,
      "learning_rate": 1.2719043882781487e-05,
      "loss": 0.5274,
      "step": 26906
    },
    {
      "epoch": 0.8265597640770436,
      "grad_norm": 0.3974156081676483,
      "learning_rate": 1.2718578810095613e-05,
      "loss": 0.545,
      "step": 26907
    },
    {
      "epoch": 0.8265904832119928,
      "grad_norm": 0.3563803732395172,
      "learning_rate": 1.2718113731060305e-05,
      "loss": 0.562,
      "step": 26908
    },
    {
      "epoch": 0.8266212023469419,
      "grad_norm": 0.36866700649261475,
      "learning_rate": 1.271764864567665e-05,
      "loss": 0.5855,
      "step": 26909
    },
    {
      "epoch": 0.826651921481891,
      "grad_norm": 0.37142789363861084,
      "learning_rate": 1.271718355394574e-05,
      "loss": 0.4401,
      "step": 26910
    },
    {
      "epoch": 0.8266826406168403,
      "grad_norm": 0.4620428681373596,
      "learning_rate": 1.2716718455868655e-05,
      "loss": 0.6054,
      "step": 26911
    },
    {
      "epoch": 0.8267133597517894,
      "grad_norm": 0.41894206404685974,
      "learning_rate": 1.2716253351446488e-05,
      "loss": 0.5897,
      "step": 26912
    },
    {
      "epoch": 0.8267440788867385,
      "grad_norm": 0.3713472783565521,
      "learning_rate": 1.271578824068032e-05,
      "loss": 0.5835,
      "step": 26913
    },
    {
      "epoch": 0.8267747980216877,
      "grad_norm": 0.43513911962509155,
      "learning_rate": 1.271532312357124e-05,
      "loss": 0.5262,
      "step": 26914
    },
    {
      "epoch": 0.8268055171566369,
      "grad_norm": 0.41626888513565063,
      "learning_rate": 1.2714858000120332e-05,
      "loss": 0.5359,
      "step": 26915
    },
    {
      "epoch": 0.826836236291586,
      "grad_norm": 0.4104022681713104,
      "learning_rate": 1.2714392870328684e-05,
      "loss": 0.6153,
      "step": 26916
    },
    {
      "epoch": 0.8268669554265352,
      "grad_norm": 0.45463335514068604,
      "learning_rate": 1.2713927734197382e-05,
      "loss": 0.6179,
      "step": 26917
    },
    {
      "epoch": 0.8268976745614843,
      "grad_norm": 0.41913846135139465,
      "learning_rate": 1.2713462591727512e-05,
      "loss": 0.5849,
      "step": 26918
    },
    {
      "epoch": 0.8269283936964336,
      "grad_norm": 0.4297998547554016,
      "learning_rate": 1.271299744292016e-05,
      "loss": 0.4472,
      "step": 26919
    },
    {
      "epoch": 0.8269591128313827,
      "grad_norm": 0.34998464584350586,
      "learning_rate": 1.2712532287776411e-05,
      "loss": 0.4842,
      "step": 26920
    },
    {
      "epoch": 0.8269898319663318,
      "grad_norm": 0.35523539781570435,
      "learning_rate": 1.2712067126297359e-05,
      "loss": 0.5372,
      "step": 26921
    },
    {
      "epoch": 0.827020551101281,
      "grad_norm": 0.39635077118873596,
      "learning_rate": 1.2711601958484079e-05,
      "loss": 0.5092,
      "step": 26922
    },
    {
      "epoch": 0.8270512702362302,
      "grad_norm": 0.35925614833831787,
      "learning_rate": 1.2711136784337667e-05,
      "loss": 0.5561,
      "step": 26923
    },
    {
      "epoch": 0.8270819893711793,
      "grad_norm": 0.3712117373943329,
      "learning_rate": 1.2710671603859205e-05,
      "loss": 0.6216,
      "step": 26924
    },
    {
      "epoch": 0.8271127085061285,
      "grad_norm": 1.2848271131515503,
      "learning_rate": 1.2710206417049782e-05,
      "loss": 0.6035,
      "step": 26925
    },
    {
      "epoch": 0.8271434276410776,
      "grad_norm": 0.5938532948493958,
      "learning_rate": 1.270974122391048e-05,
      "loss": 0.5125,
      "step": 26926
    },
    {
      "epoch": 0.8271741467760267,
      "grad_norm": 0.370238721370697,
      "learning_rate": 1.2709276024442387e-05,
      "loss": 0.5035,
      "step": 26927
    },
    {
      "epoch": 0.827204865910976,
      "grad_norm": 0.3752968907356262,
      "learning_rate": 1.2708810818646593e-05,
      "loss": 0.5798,
      "step": 26928
    },
    {
      "epoch": 0.8272355850459251,
      "grad_norm": 0.3538978099822998,
      "learning_rate": 1.2708345606524183e-05,
      "loss": 0.5798,
      "step": 26929
    },
    {
      "epoch": 0.8272663041808742,
      "grad_norm": 0.378939151763916,
      "learning_rate": 1.2707880388076238e-05,
      "loss": 0.5222,
      "step": 26930
    },
    {
      "epoch": 0.8272970233158234,
      "grad_norm": 0.3629481792449951,
      "learning_rate": 1.2707415163303853e-05,
      "loss": 0.5349,
      "step": 26931
    },
    {
      "epoch": 0.8273277424507726,
      "grad_norm": 0.35041531920433044,
      "learning_rate": 1.2706949932208113e-05,
      "loss": 0.5024,
      "step": 26932
    },
    {
      "epoch": 0.8273584615857218,
      "grad_norm": 0.360953688621521,
      "learning_rate": 1.2706484694790097e-05,
      "loss": 0.5209,
      "step": 26933
    },
    {
      "epoch": 0.8273891807206709,
      "grad_norm": 0.3434022068977356,
      "learning_rate": 1.2706019451050901e-05,
      "loss": 0.6028,
      "step": 26934
    },
    {
      "epoch": 0.82741989985562,
      "grad_norm": 0.3644912838935852,
      "learning_rate": 1.2705554200991606e-05,
      "loss": 0.5456,
      "step": 26935
    },
    {
      "epoch": 0.8274506189905693,
      "grad_norm": 0.3548752963542938,
      "learning_rate": 1.27050889446133e-05,
      "loss": 0.5368,
      "step": 26936
    },
    {
      "epoch": 0.8274813381255184,
      "grad_norm": 0.3670947849750519,
      "learning_rate": 1.2704623681917073e-05,
      "loss": 0.5686,
      "step": 26937
    },
    {
      "epoch": 0.8275120572604675,
      "grad_norm": 0.3276214003562927,
      "learning_rate": 1.2704158412903999e-05,
      "loss": 0.5497,
      "step": 26938
    },
    {
      "epoch": 0.8275427763954167,
      "grad_norm": 0.3657810688018799,
      "learning_rate": 1.2703693137575184e-05,
      "loss": 0.5394,
      "step": 26939
    },
    {
      "epoch": 0.8275734955303659,
      "grad_norm": 0.3498515486717224,
      "learning_rate": 1.2703227855931702e-05,
      "loss": 0.5252,
      "step": 26940
    },
    {
      "epoch": 0.827604214665315,
      "grad_norm": 0.3620937764644623,
      "learning_rate": 1.2702762567974642e-05,
      "loss": 0.4921,
      "step": 26941
    },
    {
      "epoch": 0.8276349338002642,
      "grad_norm": 0.32411104440689087,
      "learning_rate": 1.2702297273705092e-05,
      "loss": 0.5242,
      "step": 26942
    },
    {
      "epoch": 0.8276656529352133,
      "grad_norm": 0.4263598620891571,
      "learning_rate": 1.2701831973124138e-05,
      "loss": 0.5979,
      "step": 26943
    },
    {
      "epoch": 0.8276963720701626,
      "grad_norm": 0.36490342020988464,
      "learning_rate": 1.2701366666232866e-05,
      "loss": 0.4859,
      "step": 26944
    },
    {
      "epoch": 0.8277270912051117,
      "grad_norm": 0.3328682482242584,
      "learning_rate": 1.2700901353032362e-05,
      "loss": 0.5341,
      "step": 26945
    },
    {
      "epoch": 0.8277578103400608,
      "grad_norm": 0.4048367738723755,
      "learning_rate": 1.2700436033523717e-05,
      "loss": 0.4723,
      "step": 26946
    },
    {
      "epoch": 0.82778852947501,
      "grad_norm": 0.352411687374115,
      "learning_rate": 1.2699970707708013e-05,
      "loss": 0.5374,
      "step": 26947
    },
    {
      "epoch": 0.8278192486099591,
      "grad_norm": 0.33094558119773865,
      "learning_rate": 1.2699505375586343e-05,
      "loss": 0.5543,
      "step": 26948
    },
    {
      "epoch": 0.8278499677449083,
      "grad_norm": 0.46349436044692993,
      "learning_rate": 1.2699040037159784e-05,
      "loss": 0.5712,
      "step": 26949
    },
    {
      "epoch": 0.8278806868798575,
      "grad_norm": 0.39765995740890503,
      "learning_rate": 1.2698574692429432e-05,
      "loss": 0.5794,
      "step": 26950
    },
    {
      "epoch": 0.8279114060148066,
      "grad_norm": 0.3699580729007721,
      "learning_rate": 1.269810934139637e-05,
      "loss": 0.6532,
      "step": 26951
    },
    {
      "epoch": 0.8279421251497557,
      "grad_norm": 0.3336356580257416,
      "learning_rate": 1.2697643984061685e-05,
      "loss": 0.5347,
      "step": 26952
    },
    {
      "epoch": 0.827972844284705,
      "grad_norm": 0.39645349979400635,
      "learning_rate": 1.2697178620426463e-05,
      "loss": 0.6186,
      "step": 26953
    },
    {
      "epoch": 0.8280035634196541,
      "grad_norm": 0.3887363076210022,
      "learning_rate": 1.2696713250491792e-05,
      "loss": 0.5183,
      "step": 26954
    },
    {
      "epoch": 0.8280342825546032,
      "grad_norm": 0.45315220952033997,
      "learning_rate": 1.269624787425876e-05,
      "loss": 0.5647,
      "step": 26955
    },
    {
      "epoch": 0.8280650016895524,
      "grad_norm": 0.3839477598667145,
      "learning_rate": 1.269578249172845e-05,
      "loss": 0.5502,
      "step": 26956
    },
    {
      "epoch": 0.8280957208245016,
      "grad_norm": 1.3484493494033813,
      "learning_rate": 1.2695317102901954e-05,
      "loss": 0.5636,
      "step": 26957
    },
    {
      "epoch": 0.8281264399594508,
      "grad_norm": 0.3261617422103882,
      "learning_rate": 1.2694851707780355e-05,
      "loss": 0.52,
      "step": 26958
    },
    {
      "epoch": 0.8281571590943999,
      "grad_norm": 0.36670929193496704,
      "learning_rate": 1.2694386306364746e-05,
      "loss": 0.5259,
      "step": 26959
    },
    {
      "epoch": 0.828187878229349,
      "grad_norm": 0.323982834815979,
      "learning_rate": 1.2693920898656207e-05,
      "loss": 0.4859,
      "step": 26960
    },
    {
      "epoch": 0.8282185973642983,
      "grad_norm": 0.37752285599708557,
      "learning_rate": 1.2693455484655828e-05,
      "loss": 0.6347,
      "step": 26961
    },
    {
      "epoch": 0.8282493164992474,
      "grad_norm": 0.3698410987854004,
      "learning_rate": 1.2692990064364695e-05,
      "loss": 0.4134,
      "step": 26962
    },
    {
      "epoch": 0.8282800356341965,
      "grad_norm": 0.37701651453971863,
      "learning_rate": 1.2692524637783895e-05,
      "loss": 0.6637,
      "step": 26963
    },
    {
      "epoch": 0.8283107547691457,
      "grad_norm": 0.39717188477516174,
      "learning_rate": 1.2692059204914517e-05,
      "loss": 0.575,
      "step": 26964
    },
    {
      "epoch": 0.8283414739040948,
      "grad_norm": 0.3470255136489868,
      "learning_rate": 1.2691593765757645e-05,
      "loss": 0.5581,
      "step": 26965
    },
    {
      "epoch": 0.828372193039044,
      "grad_norm": 0.35411548614501953,
      "learning_rate": 1.269112832031437e-05,
      "loss": 0.5888,
      "step": 26966
    },
    {
      "epoch": 0.8284029121739932,
      "grad_norm": 0.3876190185546875,
      "learning_rate": 1.2690662868585775e-05,
      "loss": 0.4909,
      "step": 26967
    },
    {
      "epoch": 0.8284336313089423,
      "grad_norm": 0.35871386528015137,
      "learning_rate": 1.269019741057295e-05,
      "loss": 0.5513,
      "step": 26968
    },
    {
      "epoch": 0.8284643504438916,
      "grad_norm": 0.4035522937774658,
      "learning_rate": 1.268973194627698e-05,
      "loss": 0.4657,
      "step": 26969
    },
    {
      "epoch": 0.8284950695788407,
      "grad_norm": 0.3887275159358978,
      "learning_rate": 1.2689266475698956e-05,
      "loss": 0.47,
      "step": 26970
    },
    {
      "epoch": 0.8285257887137898,
      "grad_norm": 0.35757237672805786,
      "learning_rate": 1.268880099883996e-05,
      "loss": 0.5761,
      "step": 26971
    },
    {
      "epoch": 0.828556507848739,
      "grad_norm": 0.5108929872512817,
      "learning_rate": 1.2688335515701083e-05,
      "loss": 0.6257,
      "step": 26972
    },
    {
      "epoch": 0.8285872269836881,
      "grad_norm": 0.3775435984134674,
      "learning_rate": 1.268787002628341e-05,
      "loss": 0.5875,
      "step": 26973
    },
    {
      "epoch": 0.8286179461186373,
      "grad_norm": 0.374016672372818,
      "learning_rate": 1.2687404530588024e-05,
      "loss": 0.548,
      "step": 26974
    },
    {
      "epoch": 0.8286486652535865,
      "grad_norm": 0.379194438457489,
      "learning_rate": 1.2686939028616023e-05,
      "loss": 0.5541,
      "step": 26975
    },
    {
      "epoch": 0.8286793843885356,
      "grad_norm": 0.40790504217147827,
      "learning_rate": 1.2686473520368485e-05,
      "loss": 0.4528,
      "step": 26976
    },
    {
      "epoch": 0.8287101035234847,
      "grad_norm": 0.6501482129096985,
      "learning_rate": 1.2686008005846505e-05,
      "loss": 0.5529,
      "step": 26977
    },
    {
      "epoch": 0.828740822658434,
      "grad_norm": 0.36176151037216187,
      "learning_rate": 1.2685542485051161e-05,
      "loss": 0.5864,
      "step": 26978
    },
    {
      "epoch": 0.8287715417933831,
      "grad_norm": 0.40803197026252747,
      "learning_rate": 1.2685076957983546e-05,
      "loss": 0.4891,
      "step": 26979
    },
    {
      "epoch": 0.8288022609283323,
      "grad_norm": 0.36752668023109436,
      "learning_rate": 1.2684611424644748e-05,
      "loss": 0.5561,
      "step": 26980
    },
    {
      "epoch": 0.8288329800632814,
      "grad_norm": 0.356103777885437,
      "learning_rate": 1.268414588503585e-05,
      "loss": 0.5374,
      "step": 26981
    },
    {
      "epoch": 0.8288636991982306,
      "grad_norm": 0.3583567142486572,
      "learning_rate": 1.2683680339157944e-05,
      "loss": 0.4895,
      "step": 26982
    },
    {
      "epoch": 0.8288944183331798,
      "grad_norm": 0.4376335144042969,
      "learning_rate": 1.2683214787012115e-05,
      "loss": 0.523,
      "step": 26983
    },
    {
      "epoch": 0.8289251374681289,
      "grad_norm": 0.368416428565979,
      "learning_rate": 1.268274922859945e-05,
      "loss": 0.5635,
      "step": 26984
    },
    {
      "epoch": 0.828955856603078,
      "grad_norm": 0.3480643033981323,
      "learning_rate": 1.2682283663921035e-05,
      "loss": 0.5654,
      "step": 26985
    },
    {
      "epoch": 0.8289865757380273,
      "grad_norm": 0.3765828311443329,
      "learning_rate": 1.2681818092977962e-05,
      "loss": 0.6123,
      "step": 26986
    },
    {
      "epoch": 0.8290172948729764,
      "grad_norm": 0.36674341559410095,
      "learning_rate": 1.2681352515771315e-05,
      "loss": 0.4789,
      "step": 26987
    },
    {
      "epoch": 0.8290480140079255,
      "grad_norm": 0.5024712681770325,
      "learning_rate": 1.2680886932302181e-05,
      "loss": 0.5623,
      "step": 26988
    },
    {
      "epoch": 0.8290787331428747,
      "grad_norm": 0.3492150902748108,
      "learning_rate": 1.268042134257165e-05,
      "loss": 0.5467,
      "step": 26989
    },
    {
      "epoch": 0.8291094522778238,
      "grad_norm": 0.4400257468223572,
      "learning_rate": 1.2679955746580805e-05,
      "loss": 0.5641,
      "step": 26990
    },
    {
      "epoch": 0.829140171412773,
      "grad_norm": 0.44692352414131165,
      "learning_rate": 1.267949014433074e-05,
      "loss": 0.5781,
      "step": 26991
    },
    {
      "epoch": 0.8291708905477222,
      "grad_norm": 0.4036007821559906,
      "learning_rate": 1.2679024535822535e-05,
      "loss": 0.5326,
      "step": 26992
    },
    {
      "epoch": 0.8292016096826713,
      "grad_norm": 0.3722107410430908,
      "learning_rate": 1.267855892105728e-05,
      "loss": 0.4937,
      "step": 26993
    },
    {
      "epoch": 0.8292323288176205,
      "grad_norm": 0.3507424294948578,
      "learning_rate": 1.2678093300036067e-05,
      "loss": 0.5224,
      "step": 26994
    },
    {
      "epoch": 0.8292630479525697,
      "grad_norm": 0.41942551732063293,
      "learning_rate": 1.2677627672759978e-05,
      "loss": 0.5678,
      "step": 26995
    },
    {
      "epoch": 0.8292937670875188,
      "grad_norm": 0.3413357436656952,
      "learning_rate": 1.2677162039230106e-05,
      "loss": 0.625,
      "step": 26996
    },
    {
      "epoch": 0.829324486222468,
      "grad_norm": 0.3853926956653595,
      "learning_rate": 1.267669639944753e-05,
      "loss": 0.5494,
      "step": 26997
    },
    {
      "epoch": 0.8293552053574171,
      "grad_norm": 0.3594391942024231,
      "learning_rate": 1.2676230753413348e-05,
      "loss": 0.5656,
      "step": 26998
    },
    {
      "epoch": 0.8293859244923663,
      "grad_norm": 0.35649624466896057,
      "learning_rate": 1.2675765101128637e-05,
      "loss": 0.53,
      "step": 26999
    },
    {
      "epoch": 0.8294166436273155,
      "grad_norm": 0.3734930157661438,
      "learning_rate": 1.2675299442594493e-05,
      "loss": 0.5625,
      "step": 27000
    },
    {
      "epoch": 0.8294473627622646,
      "grad_norm": 0.37703460454940796,
      "learning_rate": 1.2674833777811998e-05,
      "loss": 0.4822,
      "step": 27001
    },
    {
      "epoch": 0.8294780818972137,
      "grad_norm": 0.4156048595905304,
      "learning_rate": 1.2674368106782246e-05,
      "loss": 0.5677,
      "step": 27002
    },
    {
      "epoch": 0.829508801032163,
      "grad_norm": 0.3362496793270111,
      "learning_rate": 1.2673902429506317e-05,
      "loss": 0.4974,
      "step": 27003
    },
    {
      "epoch": 0.8295395201671121,
      "grad_norm": 0.3763400614261627,
      "learning_rate": 1.2673436745985303e-05,
      "loss": 0.6029,
      "step": 27004
    },
    {
      "epoch": 0.8295702393020613,
      "grad_norm": 0.3739820420742035,
      "learning_rate": 1.2672971056220292e-05,
      "loss": 0.5622,
      "step": 27005
    },
    {
      "epoch": 0.8296009584370104,
      "grad_norm": 0.3769420385360718,
      "learning_rate": 1.2672505360212368e-05,
      "loss": 0.5532,
      "step": 27006
    },
    {
      "epoch": 0.8296316775719595,
      "grad_norm": 0.3873150050640106,
      "learning_rate": 1.2672039657962625e-05,
      "loss": 0.5328,
      "step": 27007
    },
    {
      "epoch": 0.8296623967069088,
      "grad_norm": 0.35003164410591125,
      "learning_rate": 1.2671573949472143e-05,
      "loss": 0.4802,
      "step": 27008
    },
    {
      "epoch": 0.8296931158418579,
      "grad_norm": 0.3781835436820984,
      "learning_rate": 1.2671108234742015e-05,
      "loss": 0.5494,
      "step": 27009
    },
    {
      "epoch": 0.829723834976807,
      "grad_norm": 0.4039385914802551,
      "learning_rate": 1.2670642513773326e-05,
      "loss": 0.6248,
      "step": 27010
    },
    {
      "epoch": 0.8297545541117562,
      "grad_norm": 0.522290050983429,
      "learning_rate": 1.2670176786567164e-05,
      "loss": 0.5207,
      "step": 27011
    },
    {
      "epoch": 0.8297852732467054,
      "grad_norm": 0.3351229429244995,
      "learning_rate": 1.266971105312462e-05,
      "loss": 0.5169,
      "step": 27012
    },
    {
      "epoch": 0.8298159923816545,
      "grad_norm": 0.341731995344162,
      "learning_rate": 1.2669245313446779e-05,
      "loss": 0.6113,
      "step": 27013
    },
    {
      "epoch": 0.8298467115166037,
      "grad_norm": 0.34995561838150024,
      "learning_rate": 1.2668779567534728e-05,
      "loss": 0.5406,
      "step": 27014
    },
    {
      "epoch": 0.8298774306515528,
      "grad_norm": 0.3571462631225586,
      "learning_rate": 1.2668313815389557e-05,
      "loss": 0.5835,
      "step": 27015
    },
    {
      "epoch": 0.829908149786502,
      "grad_norm": 0.3654617667198181,
      "learning_rate": 1.2667848057012353e-05,
      "loss": 0.6096,
      "step": 27016
    },
    {
      "epoch": 0.8299388689214512,
      "grad_norm": 0.42585045099258423,
      "learning_rate": 1.2667382292404202e-05,
      "loss": 0.5044,
      "step": 27017
    },
    {
      "epoch": 0.8299695880564003,
      "grad_norm": 0.3374563455581665,
      "learning_rate": 1.2666916521566195e-05,
      "loss": 0.5633,
      "step": 27018
    },
    {
      "epoch": 0.8300003071913495,
      "grad_norm": 0.35860908031463623,
      "learning_rate": 1.2666450744499417e-05,
      "loss": 0.5728,
      "step": 27019
    },
    {
      "epoch": 0.8300310263262987,
      "grad_norm": 0.3166657090187073,
      "learning_rate": 1.2665984961204959e-05,
      "loss": 0.4763,
      "step": 27020
    },
    {
      "epoch": 0.8300617454612478,
      "grad_norm": 0.9564712643623352,
      "learning_rate": 1.2665519171683905e-05,
      "loss": 0.5387,
      "step": 27021
    },
    {
      "epoch": 0.830092464596197,
      "grad_norm": 0.3492712080478668,
      "learning_rate": 1.2665053375937344e-05,
      "loss": 0.4935,
      "step": 27022
    },
    {
      "epoch": 0.8301231837311461,
      "grad_norm": 0.453664094209671,
      "learning_rate": 1.2664587573966368e-05,
      "loss": 0.5151,
      "step": 27023
    },
    {
      "epoch": 0.8301539028660953,
      "grad_norm": 0.39165177941322327,
      "learning_rate": 1.266412176577206e-05,
      "loss": 0.6355,
      "step": 27024
    },
    {
      "epoch": 0.8301846220010445,
      "grad_norm": 0.33777567744255066,
      "learning_rate": 1.266365595135551e-05,
      "loss": 0.6092,
      "step": 27025
    },
    {
      "epoch": 0.8302153411359936,
      "grad_norm": 0.3641641438007355,
      "learning_rate": 1.2663190130717804e-05,
      "loss": 0.5363,
      "step": 27026
    },
    {
      "epoch": 0.8302460602709427,
      "grad_norm": 0.3698714077472687,
      "learning_rate": 1.2662724303860033e-05,
      "loss": 0.6133,
      "step": 27027
    },
    {
      "epoch": 0.830276779405892,
      "grad_norm": 0.3789611756801605,
      "learning_rate": 1.266225847078328e-05,
      "loss": 0.4482,
      "step": 27028
    },
    {
      "epoch": 0.8303074985408411,
      "grad_norm": 0.491183340549469,
      "learning_rate": 1.2661792631488639e-05,
      "loss": 0.5134,
      "step": 27029
    },
    {
      "epoch": 0.8303382176757903,
      "grad_norm": 0.5464342832565308,
      "learning_rate": 1.2661326785977198e-05,
      "loss": 0.5207,
      "step": 27030
    },
    {
      "epoch": 0.8303689368107394,
      "grad_norm": 0.3414505422115326,
      "learning_rate": 1.2660860934250036e-05,
      "loss": 0.5794,
      "step": 27031
    },
    {
      "epoch": 0.8303996559456885,
      "grad_norm": 0.33488985896110535,
      "learning_rate": 1.2660395076308254e-05,
      "loss": 0.4731,
      "step": 27032
    },
    {
      "epoch": 0.8304303750806378,
      "grad_norm": 0.394453227519989,
      "learning_rate": 1.2659929212152929e-05,
      "loss": 0.555,
      "step": 27033
    },
    {
      "epoch": 0.8304610942155869,
      "grad_norm": 0.3479311764240265,
      "learning_rate": 1.2659463341785157e-05,
      "loss": 0.5043,
      "step": 27034
    },
    {
      "epoch": 0.830491813350536,
      "grad_norm": 0.35404419898986816,
      "learning_rate": 1.265899746520602e-05,
      "loss": 0.5893,
      "step": 27035
    },
    {
      "epoch": 0.8305225324854852,
      "grad_norm": 0.4152596592903137,
      "learning_rate": 1.2658531582416611e-05,
      "loss": 0.601,
      "step": 27036
    },
    {
      "epoch": 0.8305532516204344,
      "grad_norm": 0.3402130603790283,
      "learning_rate": 1.2658065693418014e-05,
      "loss": 0.481,
      "step": 27037
    },
    {
      "epoch": 0.8305839707553835,
      "grad_norm": 0.3849560618400574,
      "learning_rate": 1.265759979821132e-05,
      "loss": 0.5607,
      "step": 27038
    },
    {
      "epoch": 0.8306146898903327,
      "grad_norm": 0.3951937258243561,
      "learning_rate": 1.2657133896797613e-05,
      "loss": 0.5913,
      "step": 27039
    },
    {
      "epoch": 0.8306454090252818,
      "grad_norm": 0.35849565267562866,
      "learning_rate": 1.2656667989177988e-05,
      "loss": 0.5908,
      "step": 27040
    },
    {
      "epoch": 0.830676128160231,
      "grad_norm": 0.3553217947483063,
      "learning_rate": 1.265620207535353e-05,
      "loss": 0.5306,
      "step": 27041
    },
    {
      "epoch": 0.8307068472951802,
      "grad_norm": 0.3615686297416687,
      "learning_rate": 1.2655736155325324e-05,
      "loss": 0.5761,
      "step": 27042
    },
    {
      "epoch": 0.8307375664301293,
      "grad_norm": 0.35458943247795105,
      "learning_rate": 1.2655270229094462e-05,
      "loss": 0.5907,
      "step": 27043
    },
    {
      "epoch": 0.8307682855650785,
      "grad_norm": 0.2981807291507721,
      "learning_rate": 1.2654804296662028e-05,
      "loss": 0.5105,
      "step": 27044
    },
    {
      "epoch": 0.8307990047000277,
      "grad_norm": 0.35650181770324707,
      "learning_rate": 1.265433835802912e-05,
      "loss": 0.5413,
      "step": 27045
    },
    {
      "epoch": 0.8308297238349768,
      "grad_norm": 0.3724871873855591,
      "learning_rate": 1.2653872413196813e-05,
      "loss": 0.5024,
      "step": 27046
    },
    {
      "epoch": 0.830860442969926,
      "grad_norm": 0.35411250591278076,
      "learning_rate": 1.2653406462166202e-05,
      "loss": 0.4997,
      "step": 27047
    },
    {
      "epoch": 0.8308911621048751,
      "grad_norm": 0.3299767076969147,
      "learning_rate": 1.2652940504938378e-05,
      "loss": 0.5003,
      "step": 27048
    },
    {
      "epoch": 0.8309218812398242,
      "grad_norm": 0.39350855350494385,
      "learning_rate": 1.2652474541514423e-05,
      "loss": 0.6175,
      "step": 27049
    },
    {
      "epoch": 0.8309526003747735,
      "grad_norm": 0.3589632213115692,
      "learning_rate": 1.2652008571895432e-05,
      "loss": 0.4628,
      "step": 27050
    },
    {
      "epoch": 0.8309833195097226,
      "grad_norm": 0.3867671489715576,
      "learning_rate": 1.2651542596082486e-05,
      "loss": 0.5726,
      "step": 27051
    },
    {
      "epoch": 0.8310140386446717,
      "grad_norm": 0.5267994999885559,
      "learning_rate": 1.265107661407668e-05,
      "loss": 0.6685,
      "step": 27052
    },
    {
      "epoch": 0.831044757779621,
      "grad_norm": 0.3496708571910858,
      "learning_rate": 1.2650610625879099e-05,
      "loss": 0.4579,
      "step": 27053
    },
    {
      "epoch": 0.8310754769145701,
      "grad_norm": 0.3627551794052124,
      "learning_rate": 1.2650144631490831e-05,
      "loss": 0.5418,
      "step": 27054
    },
    {
      "epoch": 0.8311061960495193,
      "grad_norm": 0.3928287923336029,
      "learning_rate": 1.2649678630912963e-05,
      "loss": 0.5457,
      "step": 27055
    },
    {
      "epoch": 0.8311369151844684,
      "grad_norm": 0.39567604660987854,
      "learning_rate": 1.264921262414659e-05,
      "loss": 0.5959,
      "step": 27056
    },
    {
      "epoch": 0.8311676343194175,
      "grad_norm": 0.40504854917526245,
      "learning_rate": 1.2648746611192795e-05,
      "loss": 0.5848,
      "step": 27057
    },
    {
      "epoch": 0.8311983534543668,
      "grad_norm": 0.5544378757476807,
      "learning_rate": 1.2648280592052665e-05,
      "loss": 0.62,
      "step": 27058
    },
    {
      "epoch": 0.8312290725893159,
      "grad_norm": 0.3729649484157562,
      "learning_rate": 1.2647814566727293e-05,
      "loss": 0.5392,
      "step": 27059
    },
    {
      "epoch": 0.831259791724265,
      "grad_norm": 0.35662877559661865,
      "learning_rate": 1.2647348535217762e-05,
      "loss": 0.5347,
      "step": 27060
    },
    {
      "epoch": 0.8312905108592142,
      "grad_norm": 0.3968266546726227,
      "learning_rate": 1.2646882497525166e-05,
      "loss": 0.5528,
      "step": 27061
    },
    {
      "epoch": 0.8313212299941634,
      "grad_norm": 0.3956371545791626,
      "learning_rate": 1.2646416453650589e-05,
      "loss": 0.5311,
      "step": 27062
    },
    {
      "epoch": 0.8313519491291125,
      "grad_norm": 0.356627881526947,
      "learning_rate": 1.2645950403595125e-05,
      "loss": 0.4238,
      "step": 27063
    },
    {
      "epoch": 0.8313826682640617,
      "grad_norm": 0.32638636231422424,
      "learning_rate": 1.2645484347359856e-05,
      "loss": 0.511,
      "step": 27064
    },
    {
      "epoch": 0.8314133873990108,
      "grad_norm": 0.3899553716182709,
      "learning_rate": 1.2645018284945876e-05,
      "loss": 0.5423,
      "step": 27065
    },
    {
      "epoch": 0.8314441065339601,
      "grad_norm": 0.356752872467041,
      "learning_rate": 1.264455221635427e-05,
      "loss": 0.6226,
      "step": 27066
    },
    {
      "epoch": 0.8314748256689092,
      "grad_norm": 0.4964306354522705,
      "learning_rate": 1.2644086141586124e-05,
      "loss": 0.4793,
      "step": 27067
    },
    {
      "epoch": 0.8315055448038583,
      "grad_norm": 0.3824189603328705,
      "learning_rate": 1.2643620060642535e-05,
      "loss": 0.5483,
      "step": 27068
    },
    {
      "epoch": 0.8315362639388075,
      "grad_norm": 0.4062287211418152,
      "learning_rate": 1.2643153973524585e-05,
      "loss": 0.4987,
      "step": 27069
    },
    {
      "epoch": 0.8315669830737566,
      "grad_norm": 0.40228381752967834,
      "learning_rate": 1.2642687880233364e-05,
      "loss": 0.5741,
      "step": 27070
    },
    {
      "epoch": 0.8315977022087058,
      "grad_norm": 0.35810816287994385,
      "learning_rate": 1.2642221780769961e-05,
      "loss": 0.5986,
      "step": 27071
    },
    {
      "epoch": 0.831628421343655,
      "grad_norm": 0.3371817469596863,
      "learning_rate": 1.2641755675135466e-05,
      "loss": 0.6288,
      "step": 27072
    },
    {
      "epoch": 0.8316591404786041,
      "grad_norm": 0.3353465795516968,
      "learning_rate": 1.2641289563330963e-05,
      "loss": 0.5166,
      "step": 27073
    },
    {
      "epoch": 0.8316898596135532,
      "grad_norm": 0.34841257333755493,
      "learning_rate": 1.2640823445357549e-05,
      "loss": 0.5337,
      "step": 27074
    },
    {
      "epoch": 0.8317205787485025,
      "grad_norm": 0.36266082525253296,
      "learning_rate": 1.2640357321216304e-05,
      "loss": 0.5478,
      "step": 27075
    },
    {
      "epoch": 0.8317512978834516,
      "grad_norm": 0.36563798785209656,
      "learning_rate": 1.263989119090832e-05,
      "loss": 0.4824,
      "step": 27076
    },
    {
      "epoch": 0.8317820170184007,
      "grad_norm": 0.33617064356803894,
      "learning_rate": 1.2639425054434686e-05,
      "loss": 0.4805,
      "step": 27077
    },
    {
      "epoch": 0.8318127361533499,
      "grad_norm": 0.41132470965385437,
      "learning_rate": 1.263895891179649e-05,
      "loss": 0.5066,
      "step": 27078
    },
    {
      "epoch": 0.8318434552882991,
      "grad_norm": 0.3725087642669678,
      "learning_rate": 1.2638492762994823e-05,
      "loss": 0.5931,
      "step": 27079
    },
    {
      "epoch": 0.8318741744232483,
      "grad_norm": 0.3834511339664459,
      "learning_rate": 1.263802660803077e-05,
      "loss": 0.584,
      "step": 27080
    },
    {
      "epoch": 0.8319048935581974,
      "grad_norm": 0.367012619972229,
      "learning_rate": 1.2637560446905421e-05,
      "loss": 0.647,
      "step": 27081
    },
    {
      "epoch": 0.8319356126931465,
      "grad_norm": 0.4073667526245117,
      "learning_rate": 1.2637094279619865e-05,
      "loss": 0.5097,
      "step": 27082
    },
    {
      "epoch": 0.8319663318280958,
      "grad_norm": 0.34496402740478516,
      "learning_rate": 1.2636628106175196e-05,
      "loss": 0.4909,
      "step": 27083
    },
    {
      "epoch": 0.8319970509630449,
      "grad_norm": 0.40438175201416016,
      "learning_rate": 1.2636161926572491e-05,
      "loss": 0.6482,
      "step": 27084
    },
    {
      "epoch": 0.832027770097994,
      "grad_norm": 0.39961132407188416,
      "learning_rate": 1.263569574081285e-05,
      "loss": 0.5,
      "step": 27085
    },
    {
      "epoch": 0.8320584892329432,
      "grad_norm": 0.37350043654441833,
      "learning_rate": 1.2635229548897358e-05,
      "loss": 0.6366,
      "step": 27086
    },
    {
      "epoch": 0.8320892083678924,
      "grad_norm": 0.3785265386104584,
      "learning_rate": 1.26347633508271e-05,
      "loss": 0.6599,
      "step": 27087
    },
    {
      "epoch": 0.8321199275028415,
      "grad_norm": 0.35079658031463623,
      "learning_rate": 1.2634297146603172e-05,
      "loss": 0.5993,
      "step": 27088
    },
    {
      "epoch": 0.8321506466377907,
      "grad_norm": 0.4071947932243347,
      "learning_rate": 1.2633830936226656e-05,
      "loss": 0.5722,
      "step": 27089
    },
    {
      "epoch": 0.8321813657727398,
      "grad_norm": 0.34931713342666626,
      "learning_rate": 1.2633364719698647e-05,
      "loss": 0.5477,
      "step": 27090
    },
    {
      "epoch": 0.832212084907689,
      "grad_norm": 0.377828449010849,
      "learning_rate": 1.2632898497020228e-05,
      "loss": 0.526,
      "step": 27091
    },
    {
      "epoch": 0.8322428040426382,
      "grad_norm": 0.3506288528442383,
      "learning_rate": 1.2632432268192493e-05,
      "loss": 0.5377,
      "step": 27092
    },
    {
      "epoch": 0.8322735231775873,
      "grad_norm": 0.40263330936431885,
      "learning_rate": 1.2631966033216526e-05,
      "loss": 0.5154,
      "step": 27093
    },
    {
      "epoch": 0.8323042423125365,
      "grad_norm": 0.33708661794662476,
      "learning_rate": 1.263149979209342e-05,
      "loss": 0.541,
      "step": 27094
    },
    {
      "epoch": 0.8323349614474856,
      "grad_norm": 0.36350345611572266,
      "learning_rate": 1.2631033544824265e-05,
      "loss": 0.5147,
      "step": 27095
    },
    {
      "epoch": 0.8323656805824348,
      "grad_norm": 0.3678392171859741,
      "learning_rate": 1.2630567291410143e-05,
      "loss": 0.5044,
      "step": 27096
    },
    {
      "epoch": 0.832396399717384,
      "grad_norm": 0.40007472038269043,
      "learning_rate": 1.2630101031852151e-05,
      "loss": 0.5781,
      "step": 27097
    },
    {
      "epoch": 0.8324271188523331,
      "grad_norm": 0.3887214660644531,
      "learning_rate": 1.262963476615137e-05,
      "loss": 0.5019,
      "step": 27098
    },
    {
      "epoch": 0.8324578379872822,
      "grad_norm": 0.39974507689476013,
      "learning_rate": 1.2629168494308897e-05,
      "loss": 0.5706,
      "step": 27099
    },
    {
      "epoch": 0.8324885571222315,
      "grad_norm": 0.3820039927959442,
      "learning_rate": 1.2628702216325815e-05,
      "loss": 0.5867,
      "step": 27100
    },
    {
      "epoch": 0.8325192762571806,
      "grad_norm": 0.3511575162410736,
      "learning_rate": 1.262823593220322e-05,
      "loss": 0.5766,
      "step": 27101
    },
    {
      "epoch": 0.8325499953921297,
      "grad_norm": 0.3556513488292694,
      "learning_rate": 1.262776964194219e-05,
      "loss": 0.5901,
      "step": 27102
    },
    {
      "epoch": 0.8325807145270789,
      "grad_norm": 0.5763691663742065,
      "learning_rate": 1.2627303345543821e-05,
      "loss": 0.5477,
      "step": 27103
    },
    {
      "epoch": 0.832611433662028,
      "grad_norm": 0.3491918444633484,
      "learning_rate": 1.2626837043009206e-05,
      "loss": 0.5221,
      "step": 27104
    },
    {
      "epoch": 0.8326421527969773,
      "grad_norm": 0.37159398198127747,
      "learning_rate": 1.2626370734339426e-05,
      "loss": 0.5179,
      "step": 27105
    },
    {
      "epoch": 0.8326728719319264,
      "grad_norm": 0.40930408239364624,
      "learning_rate": 1.2625904419535578e-05,
      "loss": 0.5474,
      "step": 27106
    },
    {
      "epoch": 0.8327035910668755,
      "grad_norm": 0.4810718595981598,
      "learning_rate": 1.2625438098598743e-05,
      "loss": 0.5035,
      "step": 27107
    },
    {
      "epoch": 0.8327343102018248,
      "grad_norm": 0.37804627418518066,
      "learning_rate": 1.2624971771530015e-05,
      "loss": 0.542,
      "step": 27108
    },
    {
      "epoch": 0.8327650293367739,
      "grad_norm": 0.3892856240272522,
      "learning_rate": 1.2624505438330483e-05,
      "loss": 0.5759,
      "step": 27109
    },
    {
      "epoch": 0.832795748471723,
      "grad_norm": 0.39277002215385437,
      "learning_rate": 1.2624039099001233e-05,
      "loss": 0.5953,
      "step": 27110
    },
    {
      "epoch": 0.8328264676066722,
      "grad_norm": 0.4093296527862549,
      "learning_rate": 1.262357275354336e-05,
      "loss": 0.5489,
      "step": 27111
    },
    {
      "epoch": 0.8328571867416213,
      "grad_norm": 0.34326648712158203,
      "learning_rate": 1.2623106401957944e-05,
      "loss": 0.6046,
      "step": 27112
    },
    {
      "epoch": 0.8328879058765705,
      "grad_norm": 0.38786593079566956,
      "learning_rate": 1.2622640044246087e-05,
      "loss": 0.5319,
      "step": 27113
    },
    {
      "epoch": 0.8329186250115197,
      "grad_norm": 0.3663075566291809,
      "learning_rate": 1.2622173680408866e-05,
      "loss": 0.4859,
      "step": 27114
    },
    {
      "epoch": 0.8329493441464688,
      "grad_norm": 0.35774466395378113,
      "learning_rate": 1.2621707310447378e-05,
      "loss": 0.62,
      "step": 27115
    },
    {
      "epoch": 0.832980063281418,
      "grad_norm": 0.3664122223854065,
      "learning_rate": 1.2621240934362706e-05,
      "loss": 0.5744,
      "step": 27116
    },
    {
      "epoch": 0.8330107824163672,
      "grad_norm": 4.290198802947998,
      "learning_rate": 1.2620774552155948e-05,
      "loss": 0.6331,
      "step": 27117
    },
    {
      "epoch": 0.8330415015513163,
      "grad_norm": 0.36765918135643005,
      "learning_rate": 1.2620308163828183e-05,
      "loss": 0.522,
      "step": 27118
    },
    {
      "epoch": 0.8330722206862655,
      "grad_norm": 0.4206209182739258,
      "learning_rate": 1.2619841769380507e-05,
      "loss": 0.4776,
      "step": 27119
    },
    {
      "epoch": 0.8331029398212146,
      "grad_norm": 0.3859998881816864,
      "learning_rate": 1.2619375368814007e-05,
      "loss": 0.5331,
      "step": 27120
    },
    {
      "epoch": 0.8331336589561638,
      "grad_norm": 0.41310861706733704,
      "learning_rate": 1.2618908962129772e-05,
      "loss": 0.5296,
      "step": 27121
    },
    {
      "epoch": 0.833164378091113,
      "grad_norm": 0.32796263694763184,
      "learning_rate": 1.2618442549328896e-05,
      "loss": 0.5386,
      "step": 27122
    },
    {
      "epoch": 0.8331950972260621,
      "grad_norm": 0.3701478838920593,
      "learning_rate": 1.2617976130412462e-05,
      "loss": 0.5554,
      "step": 27123
    },
    {
      "epoch": 0.8332258163610112,
      "grad_norm": 0.3700091540813446,
      "learning_rate": 1.2617509705381563e-05,
      "loss": 0.5021,
      "step": 27124
    },
    {
      "epoch": 0.8332565354959605,
      "grad_norm": 0.46360135078430176,
      "learning_rate": 1.2617043274237283e-05,
      "loss": 0.6205,
      "step": 27125
    },
    {
      "epoch": 0.8332872546309096,
      "grad_norm": 0.3756280541419983,
      "learning_rate": 1.2616576836980721e-05,
      "loss": 0.5202,
      "step": 27126
    },
    {
      "epoch": 0.8333179737658587,
      "grad_norm": 0.4168359339237213,
      "learning_rate": 1.2616110393612961e-05,
      "loss": 0.5967,
      "step": 27127
    },
    {
      "epoch": 0.8333486929008079,
      "grad_norm": 0.6348683834075928,
      "learning_rate": 1.261564394413509e-05,
      "loss": 0.5627,
      "step": 27128
    },
    {
      "epoch": 0.833379412035757,
      "grad_norm": 0.37496253848075867,
      "learning_rate": 1.26151774885482e-05,
      "loss": 0.5323,
      "step": 27129
    },
    {
      "epoch": 0.8334101311707063,
      "grad_norm": 0.3558742105960846,
      "learning_rate": 1.2614711026853382e-05,
      "loss": 0.5375,
      "step": 27130
    },
    {
      "epoch": 0.8334408503056554,
      "grad_norm": 0.3294356167316437,
      "learning_rate": 1.2614244559051722e-05,
      "loss": 0.6085,
      "step": 27131
    },
    {
      "epoch": 0.8334715694406045,
      "grad_norm": 0.36664435267448425,
      "learning_rate": 1.2613778085144312e-05,
      "loss": 0.6222,
      "step": 27132
    },
    {
      "epoch": 0.8335022885755538,
      "grad_norm": 0.345175176858902,
      "learning_rate": 1.2613311605132242e-05,
      "loss": 0.4373,
      "step": 27133
    },
    {
      "epoch": 0.8335330077105029,
      "grad_norm": 0.39413002133369446,
      "learning_rate": 1.2612845119016596e-05,
      "loss": 0.5378,
      "step": 27134
    },
    {
      "epoch": 0.833563726845452,
      "grad_norm": 0.34135720133781433,
      "learning_rate": 1.2612378626798473e-05,
      "loss": 0.552,
      "step": 27135
    },
    {
      "epoch": 0.8335944459804012,
      "grad_norm": 0.32896044850349426,
      "learning_rate": 1.2611912128478953e-05,
      "loss": 0.5106,
      "step": 27136
    },
    {
      "epoch": 0.8336251651153503,
      "grad_norm": 0.3446107506752014,
      "learning_rate": 1.2611445624059133e-05,
      "loss": 0.5259,
      "step": 27137
    },
    {
      "epoch": 0.8336558842502995,
      "grad_norm": 0.38430890440940857,
      "learning_rate": 1.26109791135401e-05,
      "loss": 0.4631,
      "step": 27138
    },
    {
      "epoch": 0.8336866033852487,
      "grad_norm": 0.3615051209926605,
      "learning_rate": 1.2610512596922937e-05,
      "loss": 0.5059,
      "step": 27139
    },
    {
      "epoch": 0.8337173225201978,
      "grad_norm": 0.35369184613227844,
      "learning_rate": 1.2610046074208747e-05,
      "loss": 0.5044,
      "step": 27140
    },
    {
      "epoch": 0.833748041655147,
      "grad_norm": 0.35535696148872375,
      "learning_rate": 1.2609579545398607e-05,
      "loss": 0.5387,
      "step": 27141
    },
    {
      "epoch": 0.8337787607900962,
      "grad_norm": 0.365693062543869,
      "learning_rate": 1.2609113010493615e-05,
      "loss": 0.4936,
      "step": 27142
    },
    {
      "epoch": 0.8338094799250453,
      "grad_norm": 0.36691272258758545,
      "learning_rate": 1.2608646469494854e-05,
      "loss": 0.5632,
      "step": 27143
    },
    {
      "epoch": 0.8338401990599945,
      "grad_norm": 0.38679590821266174,
      "learning_rate": 1.2608179922403418e-05,
      "loss": 0.6109,
      "step": 27144
    },
    {
      "epoch": 0.8338709181949436,
      "grad_norm": 0.3771839439868927,
      "learning_rate": 1.2607713369220398e-05,
      "loss": 0.6022,
      "step": 27145
    },
    {
      "epoch": 0.8339016373298928,
      "grad_norm": 0.36002257466316223,
      "learning_rate": 1.260724680994688e-05,
      "loss": 0.5277,
      "step": 27146
    },
    {
      "epoch": 0.833932356464842,
      "grad_norm": 0.3957432508468628,
      "learning_rate": 1.2606780244583953e-05,
      "loss": 0.5901,
      "step": 27147
    },
    {
      "epoch": 0.8339630755997911,
      "grad_norm": 0.38463887572288513,
      "learning_rate": 1.2606313673132711e-05,
      "loss": 0.5822,
      "step": 27148
    },
    {
      "epoch": 0.8339937947347402,
      "grad_norm": 0.37445613741874695,
      "learning_rate": 1.2605847095594244e-05,
      "loss": 0.5577,
      "step": 27149
    },
    {
      "epoch": 0.8340245138696895,
      "grad_norm": 0.35003194212913513,
      "learning_rate": 1.2605380511969634e-05,
      "loss": 0.5155,
      "step": 27150
    },
    {
      "epoch": 0.8340552330046386,
      "grad_norm": 0.3339172303676605,
      "learning_rate": 1.2604913922259979e-05,
      "loss": 0.4764,
      "step": 27151
    },
    {
      "epoch": 0.8340859521395877,
      "grad_norm": 0.35432130098342896,
      "learning_rate": 1.2604447326466362e-05,
      "loss": 0.5585,
      "step": 27152
    },
    {
      "epoch": 0.8341166712745369,
      "grad_norm": 0.3885953724384308,
      "learning_rate": 1.260398072458988e-05,
      "loss": 0.5477,
      "step": 27153
    },
    {
      "epoch": 0.834147390409486,
      "grad_norm": 0.35195234417915344,
      "learning_rate": 1.2603514116631616e-05,
      "loss": 0.4757,
      "step": 27154
    },
    {
      "epoch": 0.8341781095444353,
      "grad_norm": 0.9055678844451904,
      "learning_rate": 1.2603047502592667e-05,
      "loss": 0.5027,
      "step": 27155
    },
    {
      "epoch": 0.8342088286793844,
      "grad_norm": 0.3394427001476288,
      "learning_rate": 1.2602580882474116e-05,
      "loss": 0.5135,
      "step": 27156
    },
    {
      "epoch": 0.8342395478143335,
      "grad_norm": 0.34642505645751953,
      "learning_rate": 1.2602114256277054e-05,
      "loss": 0.587,
      "step": 27157
    },
    {
      "epoch": 0.8342702669492827,
      "grad_norm": 0.4406232237815857,
      "learning_rate": 1.2601647624002576e-05,
      "loss": 0.5509,
      "step": 27158
    },
    {
      "epoch": 0.8343009860842319,
      "grad_norm": 0.42881518602371216,
      "learning_rate": 1.2601180985651764e-05,
      "loss": 0.5236,
      "step": 27159
    },
    {
      "epoch": 0.834331705219181,
      "grad_norm": 0.35070428252220154,
      "learning_rate": 1.2600714341225718e-05,
      "loss": 0.4504,
      "step": 27160
    },
    {
      "epoch": 0.8343624243541302,
      "grad_norm": 0.36276328563690186,
      "learning_rate": 1.2600247690725518e-05,
      "loss": 0.5395,
      "step": 27161
    },
    {
      "epoch": 0.8343931434890793,
      "grad_norm": 0.3570937514305115,
      "learning_rate": 1.259978103415226e-05,
      "loss": 0.5883,
      "step": 27162
    },
    {
      "epoch": 0.8344238626240285,
      "grad_norm": 0.3457213342189789,
      "learning_rate": 1.2599314371507033e-05,
      "loss": 0.5012,
      "step": 27163
    },
    {
      "epoch": 0.8344545817589777,
      "grad_norm": 0.3574290871620178,
      "learning_rate": 1.2598847702790921e-05,
      "loss": 0.5632,
      "step": 27164
    },
    {
      "epoch": 0.8344853008939268,
      "grad_norm": 0.37608206272125244,
      "learning_rate": 1.2598381028005023e-05,
      "loss": 0.5045,
      "step": 27165
    },
    {
      "epoch": 0.834516020028876,
      "grad_norm": 0.41430267691612244,
      "learning_rate": 1.2597914347150421e-05,
      "loss": 0.5425,
      "step": 27166
    },
    {
      "epoch": 0.8345467391638252,
      "grad_norm": 0.39588865637779236,
      "learning_rate": 1.2597447660228212e-05,
      "loss": 0.6171,
      "step": 27167
    },
    {
      "epoch": 0.8345774582987743,
      "grad_norm": 0.3423202335834503,
      "learning_rate": 1.2596980967239479e-05,
      "loss": 0.5171,
      "step": 27168
    },
    {
      "epoch": 0.8346081774337235,
      "grad_norm": 0.3583185076713562,
      "learning_rate": 1.259651426818532e-05,
      "loss": 0.5068,
      "step": 27169
    },
    {
      "epoch": 0.8346388965686726,
      "grad_norm": 0.4065319895744324,
      "learning_rate": 1.2596047563066818e-05,
      "loss": 0.537,
      "step": 27170
    },
    {
      "epoch": 0.8346696157036217,
      "grad_norm": 0.3794134557247162,
      "learning_rate": 1.2595580851885066e-05,
      "loss": 0.5299,
      "step": 27171
    },
    {
      "epoch": 0.834700334838571,
      "grad_norm": 0.39265239238739014,
      "learning_rate": 1.2595114134641151e-05,
      "loss": 0.5511,
      "step": 27172
    },
    {
      "epoch": 0.8347310539735201,
      "grad_norm": 0.3983846604824066,
      "learning_rate": 1.259464741133617e-05,
      "loss": 0.5187,
      "step": 27173
    },
    {
      "epoch": 0.8347617731084692,
      "grad_norm": 0.37223607301712036,
      "learning_rate": 1.2594180681971209e-05,
      "loss": 0.5409,
      "step": 27174
    },
    {
      "epoch": 0.8347924922434184,
      "grad_norm": 0.34981220960617065,
      "learning_rate": 1.2593713946547352e-05,
      "loss": 0.5385,
      "step": 27175
    },
    {
      "epoch": 0.8348232113783676,
      "grad_norm": 0.3948376178741455,
      "learning_rate": 1.25932472050657e-05,
      "loss": 0.5359,
      "step": 27176
    },
    {
      "epoch": 0.8348539305133168,
      "grad_norm": 0.3573882281780243,
      "learning_rate": 1.2592780457527334e-05,
      "loss": 0.5739,
      "step": 27177
    },
    {
      "epoch": 0.8348846496482659,
      "grad_norm": 0.3786199688911438,
      "learning_rate": 1.2592313703933355e-05,
      "loss": 0.5752,
      "step": 27178
    },
    {
      "epoch": 0.834915368783215,
      "grad_norm": 0.41349610686302185,
      "learning_rate": 1.259184694428484e-05,
      "loss": 0.6043,
      "step": 27179
    },
    {
      "epoch": 0.8349460879181643,
      "grad_norm": 0.35898005962371826,
      "learning_rate": 1.2591380178582888e-05,
      "loss": 0.4856,
      "step": 27180
    },
    {
      "epoch": 0.8349768070531134,
      "grad_norm": 0.4040217101573944,
      "learning_rate": 1.2590913406828587e-05,
      "loss": 0.599,
      "step": 27181
    },
    {
      "epoch": 0.8350075261880625,
      "grad_norm": 0.36364856362342834,
      "learning_rate": 1.2590446629023026e-05,
      "loss": 0.6408,
      "step": 27182
    },
    {
      "epoch": 0.8350382453230117,
      "grad_norm": 0.3400316536426544,
      "learning_rate": 1.2589979845167297e-05,
      "loss": 0.5294,
      "step": 27183
    },
    {
      "epoch": 0.8350689644579609,
      "grad_norm": 0.387386292219162,
      "learning_rate": 1.2589513055262485e-05,
      "loss": 0.526,
      "step": 27184
    },
    {
      "epoch": 0.83509968359291,
      "grad_norm": 0.32111939787864685,
      "learning_rate": 1.2589046259309689e-05,
      "loss": 0.5507,
      "step": 27185
    },
    {
      "epoch": 0.8351304027278592,
      "grad_norm": 0.37117239832878113,
      "learning_rate": 1.2588579457309992e-05,
      "loss": 0.585,
      "step": 27186
    },
    {
      "epoch": 0.8351611218628083,
      "grad_norm": 0.40193602442741394,
      "learning_rate": 1.258811264926449e-05,
      "loss": 0.5938,
      "step": 27187
    },
    {
      "epoch": 0.8351918409977575,
      "grad_norm": 0.367811918258667,
      "learning_rate": 1.2587645835174267e-05,
      "loss": 0.587,
      "step": 27188
    },
    {
      "epoch": 0.8352225601327067,
      "grad_norm": 0.33812907338142395,
      "learning_rate": 1.258717901504042e-05,
      "loss": 0.4802,
      "step": 27189
    },
    {
      "epoch": 0.8352532792676558,
      "grad_norm": 0.3662867248058319,
      "learning_rate": 1.2586712188864034e-05,
      "loss": 0.517,
      "step": 27190
    },
    {
      "epoch": 0.835283998402605,
      "grad_norm": 0.3785248398780823,
      "learning_rate": 1.25862453566462e-05,
      "loss": 0.5511,
      "step": 27191
    },
    {
      "epoch": 0.8353147175375542,
      "grad_norm": 0.3953835666179657,
      "learning_rate": 1.2585778518388011e-05,
      "loss": 0.4806,
      "step": 27192
    },
    {
      "epoch": 0.8353454366725033,
      "grad_norm": 0.3635611832141876,
      "learning_rate": 1.2585311674090552e-05,
      "loss": 0.5604,
      "step": 27193
    },
    {
      "epoch": 0.8353761558074525,
      "grad_norm": 0.3480069935321808,
      "learning_rate": 1.258484482375492e-05,
      "loss": 0.5535,
      "step": 27194
    },
    {
      "epoch": 0.8354068749424016,
      "grad_norm": 0.37136948108673096,
      "learning_rate": 1.2584377967382202e-05,
      "loss": 0.5737,
      "step": 27195
    },
    {
      "epoch": 0.8354375940773507,
      "grad_norm": 0.38654592633247375,
      "learning_rate": 1.2583911104973488e-05,
      "loss": 0.5577,
      "step": 27196
    },
    {
      "epoch": 0.8354683132123,
      "grad_norm": 0.37401053309440613,
      "learning_rate": 1.2583444236529872e-05,
      "loss": 0.5535,
      "step": 27197
    },
    {
      "epoch": 0.8354990323472491,
      "grad_norm": 0.3488219678401947,
      "learning_rate": 1.2582977362052438e-05,
      "loss": 0.532,
      "step": 27198
    },
    {
      "epoch": 0.8355297514821982,
      "grad_norm": 0.32970908284187317,
      "learning_rate": 1.2582510481542282e-05,
      "loss": 0.5795,
      "step": 27199
    },
    {
      "epoch": 0.8355604706171474,
      "grad_norm": 0.35204964876174927,
      "learning_rate": 1.2582043595000491e-05,
      "loss": 0.5623,
      "step": 27200
    },
    {
      "epoch": 0.8355911897520966,
      "grad_norm": 0.3457474410533905,
      "learning_rate": 1.258157670242816e-05,
      "loss": 0.5489,
      "step": 27201
    },
    {
      "epoch": 0.8356219088870458,
      "grad_norm": 0.3735818564891815,
      "learning_rate": 1.2581109803826373e-05,
      "loss": 0.5485,
      "step": 27202
    },
    {
      "epoch": 0.8356526280219949,
      "grad_norm": 0.37982177734375,
      "learning_rate": 1.2580642899196226e-05,
      "loss": 0.5195,
      "step": 27203
    },
    {
      "epoch": 0.835683347156944,
      "grad_norm": 0.42487820982933044,
      "learning_rate": 1.2580175988538805e-05,
      "loss": 0.5141,
      "step": 27204
    },
    {
      "epoch": 0.8357140662918933,
      "grad_norm": 0.332711398601532,
      "learning_rate": 1.2579709071855205e-05,
      "loss": 0.4978,
      "step": 27205
    },
    {
      "epoch": 0.8357447854268424,
      "grad_norm": 0.3599708676338196,
      "learning_rate": 1.2579242149146511e-05,
      "loss": 0.5756,
      "step": 27206
    },
    {
      "epoch": 0.8357755045617915,
      "grad_norm": 0.5837527513504028,
      "learning_rate": 1.257877522041382e-05,
      "loss": 0.4422,
      "step": 27207
    },
    {
      "epoch": 0.8358062236967407,
      "grad_norm": 0.33339303731918335,
      "learning_rate": 1.257830828565822e-05,
      "loss": 0.4924,
      "step": 27208
    },
    {
      "epoch": 0.8358369428316899,
      "grad_norm": 0.3718223571777344,
      "learning_rate": 1.2577841344880798e-05,
      "loss": 0.4919,
      "step": 27209
    },
    {
      "epoch": 0.835867661966639,
      "grad_norm": 0.5367028117179871,
      "learning_rate": 1.257737439808265e-05,
      "loss": 0.4941,
      "step": 27210
    },
    {
      "epoch": 0.8358983811015882,
      "grad_norm": 0.3740280866622925,
      "learning_rate": 1.2576907445264862e-05,
      "loss": 0.5383,
      "step": 27211
    },
    {
      "epoch": 0.8359291002365373,
      "grad_norm": 0.3890063464641571,
      "learning_rate": 1.2576440486428524e-05,
      "loss": 0.6129,
      "step": 27212
    },
    {
      "epoch": 0.8359598193714864,
      "grad_norm": 0.3525165617465973,
      "learning_rate": 1.2575973521574734e-05,
      "loss": 0.5635,
      "step": 27213
    },
    {
      "epoch": 0.8359905385064357,
      "grad_norm": 0.3547230362892151,
      "learning_rate": 1.2575506550704578e-05,
      "loss": 0.5419,
      "step": 27214
    },
    {
      "epoch": 0.8360212576413848,
      "grad_norm": 0.3752461075782776,
      "learning_rate": 1.2575039573819145e-05,
      "loss": 0.6018,
      "step": 27215
    },
    {
      "epoch": 0.836051976776334,
      "grad_norm": 0.3400513231754303,
      "learning_rate": 1.2574572590919529e-05,
      "loss": 0.5319,
      "step": 27216
    },
    {
      "epoch": 0.8360826959112831,
      "grad_norm": 0.3762591481208801,
      "learning_rate": 1.2574105602006816e-05,
      "loss": 0.4963,
      "step": 27217
    },
    {
      "epoch": 0.8361134150462323,
      "grad_norm": 0.3747873306274414,
      "learning_rate": 1.2573638607082101e-05,
      "loss": 0.516,
      "step": 27218
    },
    {
      "epoch": 0.8361441341811815,
      "grad_norm": 0.3683248460292816,
      "learning_rate": 1.2573171606146475e-05,
      "loss": 0.5309,
      "step": 27219
    },
    {
      "epoch": 0.8361748533161306,
      "grad_norm": 0.3562697172164917,
      "learning_rate": 1.2572704599201024e-05,
      "loss": 0.532,
      "step": 27220
    },
    {
      "epoch": 0.8362055724510797,
      "grad_norm": 0.36692631244659424,
      "learning_rate": 1.2572237586246845e-05,
      "loss": 0.544,
      "step": 27221
    },
    {
      "epoch": 0.836236291586029,
      "grad_norm": 0.35064005851745605,
      "learning_rate": 1.2571770567285022e-05,
      "loss": 0.5773,
      "step": 27222
    },
    {
      "epoch": 0.8362670107209781,
      "grad_norm": 0.32848867774009705,
      "learning_rate": 1.2571303542316654e-05,
      "loss": 0.5242,
      "step": 27223
    },
    {
      "epoch": 0.8362977298559272,
      "grad_norm": 0.3873637914657593,
      "learning_rate": 1.2570836511342821e-05,
      "loss": 0.4989,
      "step": 27224
    },
    {
      "epoch": 0.8363284489908764,
      "grad_norm": 0.4216521382331848,
      "learning_rate": 1.2570369474364625e-05,
      "loss": 0.5718,
      "step": 27225
    },
    {
      "epoch": 0.8363591681258256,
      "grad_norm": 0.3381814658641815,
      "learning_rate": 1.256990243138315e-05,
      "loss": 0.5864,
      "step": 27226
    },
    {
      "epoch": 0.8363898872607748,
      "grad_norm": 0.4319554269313812,
      "learning_rate": 1.2569435382399486e-05,
      "loss": 0.5909,
      "step": 27227
    },
    {
      "epoch": 0.8364206063957239,
      "grad_norm": 0.3411705493927002,
      "learning_rate": 1.256896832741473e-05,
      "loss": 0.5046,
      "step": 27228
    },
    {
      "epoch": 0.836451325530673,
      "grad_norm": 0.35334405303001404,
      "learning_rate": 1.2568501266429964e-05,
      "loss": 0.5675,
      "step": 27229
    },
    {
      "epoch": 0.8364820446656223,
      "grad_norm": 0.36316514015197754,
      "learning_rate": 1.2568034199446286e-05,
      "loss": 0.5484,
      "step": 27230
    },
    {
      "epoch": 0.8365127638005714,
      "grad_norm": 0.39818838238716125,
      "learning_rate": 1.2567567126464788e-05,
      "loss": 0.5355,
      "step": 27231
    },
    {
      "epoch": 0.8365434829355205,
      "grad_norm": 0.37285131216049194,
      "learning_rate": 1.2567100047486553e-05,
      "loss": 0.6089,
      "step": 27232
    },
    {
      "epoch": 0.8365742020704697,
      "grad_norm": 0.38640958070755005,
      "learning_rate": 1.2566632962512681e-05,
      "loss": 0.4674,
      "step": 27233
    },
    {
      "epoch": 0.8366049212054188,
      "grad_norm": 0.3862704634666443,
      "learning_rate": 1.2566165871544254e-05,
      "loss": 0.609,
      "step": 27234
    },
    {
      "epoch": 0.836635640340368,
      "grad_norm": 0.37572693824768066,
      "learning_rate": 1.256569877458237e-05,
      "loss": 0.5039,
      "step": 27235
    },
    {
      "epoch": 0.8366663594753172,
      "grad_norm": 0.35194095969200134,
      "learning_rate": 1.2565231671628117e-05,
      "loss": 0.5512,
      "step": 27236
    },
    {
      "epoch": 0.8366970786102663,
      "grad_norm": 0.4492259919643402,
      "learning_rate": 1.2564764562682588e-05,
      "loss": 0.5446,
      "step": 27237
    },
    {
      "epoch": 0.8367277977452154,
      "grad_norm": 0.31157299876213074,
      "learning_rate": 1.2564297447746869e-05,
      "loss": 0.5181,
      "step": 27238
    },
    {
      "epoch": 0.8367585168801647,
      "grad_norm": 0.3606933355331421,
      "learning_rate": 1.2563830326822057e-05,
      "loss": 0.5806,
      "step": 27239
    },
    {
      "epoch": 0.8367892360151138,
      "grad_norm": 0.34865203499794006,
      "learning_rate": 1.2563363199909238e-05,
      "loss": 0.5989,
      "step": 27240
    },
    {
      "epoch": 0.836819955150063,
      "grad_norm": 0.3872257471084595,
      "learning_rate": 1.2562896067009507e-05,
      "loss": 0.6404,
      "step": 27241
    },
    {
      "epoch": 0.8368506742850121,
      "grad_norm": 0.34300297498703003,
      "learning_rate": 1.2562428928123953e-05,
      "loss": 0.5233,
      "step": 27242
    },
    {
      "epoch": 0.8368813934199613,
      "grad_norm": 0.3609107434749603,
      "learning_rate": 1.2561961783253666e-05,
      "loss": 0.5151,
      "step": 27243
    },
    {
      "epoch": 0.8369121125549105,
      "grad_norm": 0.3554883599281311,
      "learning_rate": 1.256149463239974e-05,
      "loss": 0.5541,
      "step": 27244
    },
    {
      "epoch": 0.8369428316898596,
      "grad_norm": 0.4559686481952667,
      "learning_rate": 1.2561027475563263e-05,
      "loss": 0.52,
      "step": 27245
    },
    {
      "epoch": 0.8369735508248087,
      "grad_norm": 0.3353393077850342,
      "learning_rate": 1.2560560312745329e-05,
      "loss": 0.6174,
      "step": 27246
    },
    {
      "epoch": 0.837004269959758,
      "grad_norm": 0.3315705358982086,
      "learning_rate": 1.2560093143947025e-05,
      "loss": 0.501,
      "step": 27247
    },
    {
      "epoch": 0.8370349890947071,
      "grad_norm": 0.35347384214401245,
      "learning_rate": 1.2559625969169444e-05,
      "loss": 0.5362,
      "step": 27248
    },
    {
      "epoch": 0.8370657082296562,
      "grad_norm": 0.39874184131622314,
      "learning_rate": 1.2559158788413682e-05,
      "loss": 0.6031,
      "step": 27249
    },
    {
      "epoch": 0.8370964273646054,
      "grad_norm": 0.34841418266296387,
      "learning_rate": 1.2558691601680824e-05,
      "loss": 0.494,
      "step": 27250
    },
    {
      "epoch": 0.8371271464995546,
      "grad_norm": 0.36195993423461914,
      "learning_rate": 1.2558224408971964e-05,
      "loss": 0.4887,
      "step": 27251
    },
    {
      "epoch": 0.8371578656345038,
      "grad_norm": 0.36107882857322693,
      "learning_rate": 1.2557757210288188e-05,
      "loss": 0.5306,
      "step": 27252
    },
    {
      "epoch": 0.8371885847694529,
      "grad_norm": 0.42881321907043457,
      "learning_rate": 1.2557290005630596e-05,
      "loss": 0.5621,
      "step": 27253
    },
    {
      "epoch": 0.837219303904402,
      "grad_norm": 0.39872342348098755,
      "learning_rate": 1.2556822795000272e-05,
      "loss": 0.5227,
      "step": 27254
    },
    {
      "epoch": 0.8372500230393513,
      "grad_norm": 0.411713570356369,
      "learning_rate": 1.2556355578398312e-05,
      "loss": 0.59,
      "step": 27255
    },
    {
      "epoch": 0.8372807421743004,
      "grad_norm": 0.37604600191116333,
      "learning_rate": 1.2555888355825803e-05,
      "loss": 0.5874,
      "step": 27256
    },
    {
      "epoch": 0.8373114613092495,
      "grad_norm": 0.41675612330436707,
      "learning_rate": 1.255542112728384e-05,
      "loss": 0.5329,
      "step": 27257
    },
    {
      "epoch": 0.8373421804441987,
      "grad_norm": 0.3506227731704712,
      "learning_rate": 1.2554953892773511e-05,
      "loss": 0.5755,
      "step": 27258
    },
    {
      "epoch": 0.8373728995791478,
      "grad_norm": 0.413656085729599,
      "learning_rate": 1.255448665229591e-05,
      "loss": 0.6234,
      "step": 27259
    },
    {
      "epoch": 0.837403618714097,
      "grad_norm": 0.36648890376091003,
      "learning_rate": 1.2554019405852129e-05,
      "loss": 0.5403,
      "step": 27260
    },
    {
      "epoch": 0.8374343378490462,
      "grad_norm": 0.3683713972568512,
      "learning_rate": 1.2553552153443254e-05,
      "loss": 0.5302,
      "step": 27261
    },
    {
      "epoch": 0.8374650569839953,
      "grad_norm": 0.35544779896736145,
      "learning_rate": 1.255308489507038e-05,
      "loss": 0.4855,
      "step": 27262
    },
    {
      "epoch": 0.8374957761189445,
      "grad_norm": 0.3506776988506317,
      "learning_rate": 1.2552617630734597e-05,
      "loss": 0.5792,
      "step": 27263
    },
    {
      "epoch": 0.8375264952538937,
      "grad_norm": 0.42464935779571533,
      "learning_rate": 1.2552150360437001e-05,
      "loss": 0.6403,
      "step": 27264
    },
    {
      "epoch": 0.8375572143888428,
      "grad_norm": 0.3401305079460144,
      "learning_rate": 1.2551683084178677e-05,
      "loss": 0.5161,
      "step": 27265
    },
    {
      "epoch": 0.837587933523792,
      "grad_norm": 0.37425580620765686,
      "learning_rate": 1.2551215801960717e-05,
      "loss": 0.5923,
      "step": 27266
    },
    {
      "epoch": 0.8376186526587411,
      "grad_norm": 0.3486095666885376,
      "learning_rate": 1.2550748513784217e-05,
      "loss": 0.6057,
      "step": 27267
    },
    {
      "epoch": 0.8376493717936903,
      "grad_norm": 0.39410898089408875,
      "learning_rate": 1.2550281219650265e-05,
      "loss": 0.5536,
      "step": 27268
    },
    {
      "epoch": 0.8376800909286395,
      "grad_norm": 0.38461628556251526,
      "learning_rate": 1.2549813919559952e-05,
      "loss": 0.5555,
      "step": 27269
    },
    {
      "epoch": 0.8377108100635886,
      "grad_norm": 0.37204709649086,
      "learning_rate": 1.2549346613514372e-05,
      "loss": 0.6098,
      "step": 27270
    },
    {
      "epoch": 0.8377415291985377,
      "grad_norm": 0.33690574765205383,
      "learning_rate": 1.2548879301514615e-05,
      "loss": 0.5359,
      "step": 27271
    },
    {
      "epoch": 0.837772248333487,
      "grad_norm": 0.34674566984176636,
      "learning_rate": 1.2548411983561772e-05,
      "loss": 0.517,
      "step": 27272
    },
    {
      "epoch": 0.8378029674684361,
      "grad_norm": 0.35266607999801636,
      "learning_rate": 1.2547944659656936e-05,
      "loss": 0.532,
      "step": 27273
    },
    {
      "epoch": 0.8378336866033852,
      "grad_norm": 0.36461493372917175,
      "learning_rate": 1.2547477329801194e-05,
      "loss": 0.525,
      "step": 27274
    },
    {
      "epoch": 0.8378644057383344,
      "grad_norm": 0.4328823387622833,
      "learning_rate": 1.2547009993995645e-05,
      "loss": 0.5665,
      "step": 27275
    },
    {
      "epoch": 0.8378951248732835,
      "grad_norm": 0.3448951840400696,
      "learning_rate": 1.2546542652241374e-05,
      "loss": 0.482,
      "step": 27276
    },
    {
      "epoch": 0.8379258440082328,
      "grad_norm": 0.43821653723716736,
      "learning_rate": 1.2546075304539476e-05,
      "loss": 0.5772,
      "step": 27277
    },
    {
      "epoch": 0.8379565631431819,
      "grad_norm": 0.3973292410373688,
      "learning_rate": 1.2545607950891041e-05,
      "loss": 0.5127,
      "step": 27278
    },
    {
      "epoch": 0.837987282278131,
      "grad_norm": 0.6576707363128662,
      "learning_rate": 1.2545140591297159e-05,
      "loss": 0.6096,
      "step": 27279
    },
    {
      "epoch": 0.8380180014130802,
      "grad_norm": 0.40060287714004517,
      "learning_rate": 1.2544673225758926e-05,
      "loss": 0.5575,
      "step": 27280
    },
    {
      "epoch": 0.8380487205480294,
      "grad_norm": 0.39765220880508423,
      "learning_rate": 1.2544205854277427e-05,
      "loss": 0.521,
      "step": 27281
    },
    {
      "epoch": 0.8380794396829785,
      "grad_norm": 0.3791797161102295,
      "learning_rate": 1.2543738476853761e-05,
      "loss": 0.5163,
      "step": 27282
    },
    {
      "epoch": 0.8381101588179277,
      "grad_norm": 0.4119715988636017,
      "learning_rate": 1.2543271093489015e-05,
      "loss": 0.5958,
      "step": 27283
    },
    {
      "epoch": 0.8381408779528768,
      "grad_norm": 0.34992966055870056,
      "learning_rate": 1.2542803704184282e-05,
      "loss": 0.5296,
      "step": 27284
    },
    {
      "epoch": 0.838171597087826,
      "grad_norm": 0.32244953513145447,
      "learning_rate": 1.2542336308940653e-05,
      "loss": 0.484,
      "step": 27285
    },
    {
      "epoch": 0.8382023162227752,
      "grad_norm": 0.3373901844024658,
      "learning_rate": 1.2541868907759218e-05,
      "loss": 0.4698,
      "step": 27286
    },
    {
      "epoch": 0.8382330353577243,
      "grad_norm": 0.37629565596580505,
      "learning_rate": 1.2541401500641074e-05,
      "loss": 0.5838,
      "step": 27287
    },
    {
      "epoch": 0.8382637544926735,
      "grad_norm": 0.33786267042160034,
      "learning_rate": 1.2540934087587308e-05,
      "loss": 0.5574,
      "step": 27288
    },
    {
      "epoch": 0.8382944736276227,
      "grad_norm": 0.3478632867336273,
      "learning_rate": 1.2540466668599014e-05,
      "loss": 0.5861,
      "step": 27289
    },
    {
      "epoch": 0.8383251927625718,
      "grad_norm": 0.38321202993392944,
      "learning_rate": 1.2539999243677282e-05,
      "loss": 0.5556,
      "step": 27290
    },
    {
      "epoch": 0.838355911897521,
      "grad_norm": 0.3476204574108124,
      "learning_rate": 1.2539531812823205e-05,
      "loss": 0.5372,
      "step": 27291
    },
    {
      "epoch": 0.8383866310324701,
      "grad_norm": 0.4056239128112793,
      "learning_rate": 1.2539064376037873e-05,
      "loss": 0.5995,
      "step": 27292
    },
    {
      "epoch": 0.8384173501674193,
      "grad_norm": 0.3640434443950653,
      "learning_rate": 1.253859693332238e-05,
      "loss": 0.5696,
      "step": 27293
    },
    {
      "epoch": 0.8384480693023685,
      "grad_norm": 0.3955352008342743,
      "learning_rate": 1.2538129484677816e-05,
      "loss": 0.5244,
      "step": 27294
    },
    {
      "epoch": 0.8384787884373176,
      "grad_norm": 0.36415204405784607,
      "learning_rate": 1.2537662030105273e-05,
      "loss": 0.478,
      "step": 27295
    },
    {
      "epoch": 0.8385095075722667,
      "grad_norm": 0.36376306414604187,
      "learning_rate": 1.2537194569605845e-05,
      "loss": 0.6201,
      "step": 27296
    },
    {
      "epoch": 0.838540226707216,
      "grad_norm": 0.3941848576068878,
      "learning_rate": 1.2536727103180617e-05,
      "loss": 0.6175,
      "step": 27297
    },
    {
      "epoch": 0.8385709458421651,
      "grad_norm": 0.5055290460586548,
      "learning_rate": 1.253625963083069e-05,
      "loss": 0.5875,
      "step": 27298
    },
    {
      "epoch": 0.8386016649771142,
      "grad_norm": 0.37365850806236267,
      "learning_rate": 1.2535792152557148e-05,
      "loss": 0.6422,
      "step": 27299
    },
    {
      "epoch": 0.8386323841120634,
      "grad_norm": 0.35252895951271057,
      "learning_rate": 1.253532466836109e-05,
      "loss": 0.5295,
      "step": 27300
    },
    {
      "epoch": 0.8386631032470125,
      "grad_norm": 0.34480997920036316,
      "learning_rate": 1.2534857178243603e-05,
      "loss": 0.5755,
      "step": 27301
    },
    {
      "epoch": 0.8386938223819618,
      "grad_norm": 0.3659254014492035,
      "learning_rate": 1.253438968220578e-05,
      "loss": 0.5531,
      "step": 27302
    },
    {
      "epoch": 0.8387245415169109,
      "grad_norm": 0.3705558776855469,
      "learning_rate": 1.2533922180248712e-05,
      "loss": 0.5273,
      "step": 27303
    },
    {
      "epoch": 0.83875526065186,
      "grad_norm": 0.34082502126693726,
      "learning_rate": 1.2533454672373494e-05,
      "loss": 0.6321,
      "step": 27304
    },
    {
      "epoch": 0.8387859797868092,
      "grad_norm": 0.35829079151153564,
      "learning_rate": 1.2532987158581213e-05,
      "loss": 0.5544,
      "step": 27305
    },
    {
      "epoch": 0.8388166989217584,
      "grad_norm": 0.4071875810623169,
      "learning_rate": 1.2532519638872965e-05,
      "loss": 0.5885,
      "step": 27306
    },
    {
      "epoch": 0.8388474180567075,
      "grad_norm": 0.35953786969184875,
      "learning_rate": 1.253205211324984e-05,
      "loss": 0.4634,
      "step": 27307
    },
    {
      "epoch": 0.8388781371916567,
      "grad_norm": 0.41640591621398926,
      "learning_rate": 1.253158458171293e-05,
      "loss": 0.5271,
      "step": 27308
    },
    {
      "epoch": 0.8389088563266058,
      "grad_norm": 0.35818150639533997,
      "learning_rate": 1.253111704426333e-05,
      "loss": 0.5257,
      "step": 27309
    },
    {
      "epoch": 0.838939575461555,
      "grad_norm": 0.3595513105392456,
      "learning_rate": 1.2530649500902126e-05,
      "loss": 0.6597,
      "step": 27310
    },
    {
      "epoch": 0.8389702945965042,
      "grad_norm": 0.3898240029811859,
      "learning_rate": 1.2530181951630415e-05,
      "loss": 0.5742,
      "step": 27311
    },
    {
      "epoch": 0.8390010137314533,
      "grad_norm": 0.3992443382740021,
      "learning_rate": 1.2529714396449288e-05,
      "loss": 0.6045,
      "step": 27312
    },
    {
      "epoch": 0.8390317328664025,
      "grad_norm": 0.37491995096206665,
      "learning_rate": 1.2529246835359837e-05,
      "loss": 0.6088,
      "step": 27313
    },
    {
      "epoch": 0.8390624520013517,
      "grad_norm": 0.37493255734443665,
      "learning_rate": 1.2528779268363152e-05,
      "loss": 0.5324,
      "step": 27314
    },
    {
      "epoch": 0.8390931711363008,
      "grad_norm": 0.3594975471496582,
      "learning_rate": 1.2528311695460325e-05,
      "loss": 0.5587,
      "step": 27315
    },
    {
      "epoch": 0.83912389027125,
      "grad_norm": 0.3621596395969391,
      "learning_rate": 1.2527844116652452e-05,
      "loss": 0.5697,
      "step": 27316
    },
    {
      "epoch": 0.8391546094061991,
      "grad_norm": 0.3881145417690277,
      "learning_rate": 1.2527376531940618e-05,
      "loss": 0.517,
      "step": 27317
    },
    {
      "epoch": 0.8391853285411482,
      "grad_norm": 0.3757256865501404,
      "learning_rate": 1.2526908941325926e-05,
      "loss": 0.5236,
      "step": 27318
    },
    {
      "epoch": 0.8392160476760975,
      "grad_norm": 0.3946109116077423,
      "learning_rate": 1.2526441344809457e-05,
      "loss": 0.6921,
      "step": 27319
    },
    {
      "epoch": 0.8392467668110466,
      "grad_norm": 0.35905736684799194,
      "learning_rate": 1.252597374239231e-05,
      "loss": 0.4885,
      "step": 27320
    },
    {
      "epoch": 0.8392774859459957,
      "grad_norm": 0.39490798115730286,
      "learning_rate": 1.2525506134075573e-05,
      "loss": 0.6803,
      "step": 27321
    },
    {
      "epoch": 0.839308205080945,
      "grad_norm": 0.39202913641929626,
      "learning_rate": 1.2525038519860342e-05,
      "loss": 0.5878,
      "step": 27322
    },
    {
      "epoch": 0.8393389242158941,
      "grad_norm": 0.3626631796360016,
      "learning_rate": 1.2524570899747706e-05,
      "loss": 0.5796,
      "step": 27323
    },
    {
      "epoch": 0.8393696433508432,
      "grad_norm": 0.35929930210113525,
      "learning_rate": 1.2524103273738759e-05,
      "loss": 0.572,
      "step": 27324
    },
    {
      "epoch": 0.8394003624857924,
      "grad_norm": 0.40476471185684204,
      "learning_rate": 1.2523635641834593e-05,
      "loss": 0.5265,
      "step": 27325
    },
    {
      "epoch": 0.8394310816207415,
      "grad_norm": 0.3491535484790802,
      "learning_rate": 1.2523168004036296e-05,
      "loss": 0.5673,
      "step": 27326
    },
    {
      "epoch": 0.8394618007556908,
      "grad_norm": 0.35581350326538086,
      "learning_rate": 1.2522700360344971e-05,
      "loss": 0.5335,
      "step": 27327
    },
    {
      "epoch": 0.8394925198906399,
      "grad_norm": 0.4850175380706787,
      "learning_rate": 1.2522232710761697e-05,
      "loss": 0.5953,
      "step": 27328
    },
    {
      "epoch": 0.839523239025589,
      "grad_norm": 0.3805260956287384,
      "learning_rate": 1.2521765055287575e-05,
      "loss": 0.5872,
      "step": 27329
    },
    {
      "epoch": 0.8395539581605382,
      "grad_norm": 0.3627995550632477,
      "learning_rate": 1.2521297393923697e-05,
      "loss": 0.5267,
      "step": 27330
    },
    {
      "epoch": 0.8395846772954874,
      "grad_norm": 0.35500285029411316,
      "learning_rate": 1.2520829726671146e-05,
      "loss": 0.4588,
      "step": 27331
    },
    {
      "epoch": 0.8396153964304365,
      "grad_norm": 0.40164029598236084,
      "learning_rate": 1.2520362053531028e-05,
      "loss": 0.5688,
      "step": 27332
    },
    {
      "epoch": 0.8396461155653857,
      "grad_norm": 0.36194875836372375,
      "learning_rate": 1.2519894374504424e-05,
      "loss": 0.5836,
      "step": 27333
    },
    {
      "epoch": 0.8396768347003348,
      "grad_norm": 0.35290655493736267,
      "learning_rate": 1.2519426689592433e-05,
      "loss": 0.4711,
      "step": 27334
    },
    {
      "epoch": 0.839707553835284,
      "grad_norm": 0.3932843804359436,
      "learning_rate": 1.2518958998796145e-05,
      "loss": 0.6345,
      "step": 27335
    },
    {
      "epoch": 0.8397382729702332,
      "grad_norm": 0.371915340423584,
      "learning_rate": 1.2518491302116651e-05,
      "loss": 0.6174,
      "step": 27336
    },
    {
      "epoch": 0.8397689921051823,
      "grad_norm": 0.36271932721138,
      "learning_rate": 1.2518023599555045e-05,
      "loss": 0.5443,
      "step": 27337
    },
    {
      "epoch": 0.8397997112401315,
      "grad_norm": 0.3493892550468445,
      "learning_rate": 1.251755589111242e-05,
      "loss": 0.4735,
      "step": 27338
    },
    {
      "epoch": 0.8398304303750806,
      "grad_norm": 0.34140512347221375,
      "learning_rate": 1.2517088176789867e-05,
      "loss": 0.4272,
      "step": 27339
    },
    {
      "epoch": 0.8398611495100298,
      "grad_norm": 0.41195449233055115,
      "learning_rate": 1.2516620456588475e-05,
      "loss": 0.4455,
      "step": 27340
    },
    {
      "epoch": 0.839891868644979,
      "grad_norm": 0.37157997488975525,
      "learning_rate": 1.2516152730509346e-05,
      "loss": 0.5284,
      "step": 27341
    },
    {
      "epoch": 0.8399225877799281,
      "grad_norm": 0.37312525510787964,
      "learning_rate": 1.2515684998553561e-05,
      "loss": 0.611,
      "step": 27342
    },
    {
      "epoch": 0.8399533069148772,
      "grad_norm": 0.3409443497657776,
      "learning_rate": 1.2515217260722223e-05,
      "loss": 0.5522,
      "step": 27343
    },
    {
      "epoch": 0.8399840260498265,
      "grad_norm": 0.3357234001159668,
      "learning_rate": 1.2514749517016419e-05,
      "loss": 0.6027,
      "step": 27344
    },
    {
      "epoch": 0.8400147451847756,
      "grad_norm": 0.3447968363761902,
      "learning_rate": 1.251428176743724e-05,
      "loss": 0.4346,
      "step": 27345
    },
    {
      "epoch": 0.8400454643197247,
      "grad_norm": 0.33905208110809326,
      "learning_rate": 1.251381401198578e-05,
      "loss": 0.5759,
      "step": 27346
    },
    {
      "epoch": 0.8400761834546739,
      "grad_norm": 0.3761582374572754,
      "learning_rate": 1.2513346250663134e-05,
      "loss": 0.5133,
      "step": 27347
    },
    {
      "epoch": 0.8401069025896231,
      "grad_norm": 0.3467869162559509,
      "learning_rate": 1.251287848347039e-05,
      "loss": 0.536,
      "step": 27348
    },
    {
      "epoch": 0.8401376217245722,
      "grad_norm": 0.3745793402194977,
      "learning_rate": 1.2512410710408642e-05,
      "loss": 0.533,
      "step": 27349
    },
    {
      "epoch": 0.8401683408595214,
      "grad_norm": 0.3932659327983856,
      "learning_rate": 1.2511942931478989e-05,
      "loss": 0.5799,
      "step": 27350
    },
    {
      "epoch": 0.8401990599944705,
      "grad_norm": 0.3524722158908844,
      "learning_rate": 1.2511475146682512e-05,
      "loss": 0.5155,
      "step": 27351
    },
    {
      "epoch": 0.8402297791294198,
      "grad_norm": 0.36737334728240967,
      "learning_rate": 1.2511007356020311e-05,
      "loss": 0.5256,
      "step": 27352
    },
    {
      "epoch": 0.8402604982643689,
      "grad_norm": 0.36616435647010803,
      "learning_rate": 1.2510539559493478e-05,
      "loss": 0.5644,
      "step": 27353
    },
    {
      "epoch": 0.840291217399318,
      "grad_norm": 0.3424672484397888,
      "learning_rate": 1.2510071757103103e-05,
      "loss": 0.6152,
      "step": 27354
    },
    {
      "epoch": 0.8403219365342672,
      "grad_norm": 0.5065821409225464,
      "learning_rate": 1.250960394885028e-05,
      "loss": 0.5329,
      "step": 27355
    },
    {
      "epoch": 0.8403526556692164,
      "grad_norm": 0.3999069035053253,
      "learning_rate": 1.2509136134736103e-05,
      "loss": 0.5879,
      "step": 27356
    },
    {
      "epoch": 0.8403833748041655,
      "grad_norm": 0.39688003063201904,
      "learning_rate": 1.2508668314761665e-05,
      "loss": 0.5411,
      "step": 27357
    },
    {
      "epoch": 0.8404140939391147,
      "grad_norm": 0.3372783064842224,
      "learning_rate": 1.250820048892805e-05,
      "loss": 0.4546,
      "step": 27358
    },
    {
      "epoch": 0.8404448130740638,
      "grad_norm": 0.3482044041156769,
      "learning_rate": 1.2507732657236364e-05,
      "loss": 0.5884,
      "step": 27359
    },
    {
      "epoch": 0.8404755322090129,
      "grad_norm": 0.400973379611969,
      "learning_rate": 1.2507264819687693e-05,
      "loss": 0.6469,
      "step": 27360
    },
    {
      "epoch": 0.8405062513439622,
      "grad_norm": 0.3507072329521179,
      "learning_rate": 1.2506796976283129e-05,
      "loss": 0.5573,
      "step": 27361
    },
    {
      "epoch": 0.8405369704789113,
      "grad_norm": 0.3534459173679352,
      "learning_rate": 1.2506329127023765e-05,
      "loss": 0.525,
      "step": 27362
    },
    {
      "epoch": 0.8405676896138605,
      "grad_norm": 0.48441699147224426,
      "learning_rate": 1.2505861271910695e-05,
      "loss": 0.636,
      "step": 27363
    },
    {
      "epoch": 0.8405984087488096,
      "grad_norm": 0.3570595979690552,
      "learning_rate": 1.250539341094501e-05,
      "loss": 0.5145,
      "step": 27364
    },
    {
      "epoch": 0.8406291278837588,
      "grad_norm": 0.3805569112300873,
      "learning_rate": 1.2504925544127804e-05,
      "loss": 0.5052,
      "step": 27365
    },
    {
      "epoch": 0.840659847018708,
      "grad_norm": 0.4003191292285919,
      "learning_rate": 1.250445767146017e-05,
      "loss": 0.5518,
      "step": 27366
    },
    {
      "epoch": 0.8406905661536571,
      "grad_norm": 0.38037845492362976,
      "learning_rate": 1.25039897929432e-05,
      "loss": 0.5273,
      "step": 27367
    },
    {
      "epoch": 0.8407212852886062,
      "grad_norm": 0.3821370601654053,
      "learning_rate": 1.2503521908577987e-05,
      "loss": 0.5639,
      "step": 27368
    },
    {
      "epoch": 0.8407520044235555,
      "grad_norm": 0.35012802481651306,
      "learning_rate": 1.2503054018365624e-05,
      "loss": 0.6222,
      "step": 27369
    },
    {
      "epoch": 0.8407827235585046,
      "grad_norm": 0.3252747058868408,
      "learning_rate": 1.2502586122307202e-05,
      "loss": 0.501,
      "step": 27370
    },
    {
      "epoch": 0.8408134426934537,
      "grad_norm": 0.3398558795452118,
      "learning_rate": 1.2502118220403817e-05,
      "loss": 0.5629,
      "step": 27371
    },
    {
      "epoch": 0.8408441618284029,
      "grad_norm": 0.3861139416694641,
      "learning_rate": 1.2501650312656558e-05,
      "loss": 0.6155,
      "step": 27372
    },
    {
      "epoch": 0.8408748809633521,
      "grad_norm": 0.3546919524669647,
      "learning_rate": 1.2501182399066521e-05,
      "loss": 0.5837,
      "step": 27373
    },
    {
      "epoch": 0.8409056000983013,
      "grad_norm": 0.34214919805526733,
      "learning_rate": 1.2500714479634799e-05,
      "loss": 0.5734,
      "step": 27374
    },
    {
      "epoch": 0.8409363192332504,
      "grad_norm": 0.3709850013256073,
      "learning_rate": 1.2500246554362485e-05,
      "loss": 0.5346,
      "step": 27375
    },
    {
      "epoch": 0.8409670383681995,
      "grad_norm": 0.4044996500015259,
      "learning_rate": 1.2499778623250664e-05,
      "loss": 0.5733,
      "step": 27376
    },
    {
      "epoch": 0.8409977575031488,
      "grad_norm": 0.4813549220561981,
      "learning_rate": 1.2499310686300443e-05,
      "loss": 0.5387,
      "step": 27377
    },
    {
      "epoch": 0.8410284766380979,
      "grad_norm": 0.3627794682979584,
      "learning_rate": 1.2498842743512902e-05,
      "loss": 0.4665,
      "step": 27378
    },
    {
      "epoch": 0.841059195773047,
      "grad_norm": 0.430976003408432,
      "learning_rate": 1.2498374794889143e-05,
      "loss": 0.5637,
      "step": 27379
    },
    {
      "epoch": 0.8410899149079962,
      "grad_norm": 0.5340626835823059,
      "learning_rate": 1.2497906840430253e-05,
      "loss": 0.5926,
      "step": 27380
    },
    {
      "epoch": 0.8411206340429453,
      "grad_norm": 0.39707258343696594,
      "learning_rate": 1.249743888013733e-05,
      "loss": 0.5544,
      "step": 27381
    },
    {
      "epoch": 0.8411513531778945,
      "grad_norm": 0.3835461735725403,
      "learning_rate": 1.2496970914011461e-05,
      "loss": 0.5724,
      "step": 27382
    },
    {
      "epoch": 0.8411820723128437,
      "grad_norm": 0.3666451573371887,
      "learning_rate": 1.2496502942053744e-05,
      "loss": 0.5926,
      "step": 27383
    },
    {
      "epoch": 0.8412127914477928,
      "grad_norm": 0.3810656666755676,
      "learning_rate": 1.2496034964265268e-05,
      "loss": 0.6066,
      "step": 27384
    },
    {
      "epoch": 0.8412435105827419,
      "grad_norm": 0.37072497606277466,
      "learning_rate": 1.249556698064713e-05,
      "loss": 0.5902,
      "step": 27385
    },
    {
      "epoch": 0.8412742297176912,
      "grad_norm": 0.6239602565765381,
      "learning_rate": 1.2495098991200421e-05,
      "loss": 0.5686,
      "step": 27386
    },
    {
      "epoch": 0.8413049488526403,
      "grad_norm": 0.33208611607551575,
      "learning_rate": 1.2494630995926231e-05,
      "loss": 0.5523,
      "step": 27387
    },
    {
      "epoch": 0.8413356679875895,
      "grad_norm": 0.35338446497917175,
      "learning_rate": 1.249416299482566e-05,
      "loss": 0.5659,
      "step": 27388
    },
    {
      "epoch": 0.8413663871225386,
      "grad_norm": 0.3607088029384613,
      "learning_rate": 1.2493694987899794e-05,
      "loss": 0.5779,
      "step": 27389
    },
    {
      "epoch": 0.8413971062574878,
      "grad_norm": 0.3727528154850006,
      "learning_rate": 1.2493226975149732e-05,
      "loss": 0.4683,
      "step": 27390
    },
    {
      "epoch": 0.841427825392437,
      "grad_norm": 0.3338002562522888,
      "learning_rate": 1.249275895657656e-05,
      "loss": 0.5685,
      "step": 27391
    },
    {
      "epoch": 0.8414585445273861,
      "grad_norm": 0.355518102645874,
      "learning_rate": 1.2492290932181381e-05,
      "loss": 0.5636,
      "step": 27392
    },
    {
      "epoch": 0.8414892636623352,
      "grad_norm": 0.37375548481941223,
      "learning_rate": 1.249182290196528e-05,
      "loss": 0.5666,
      "step": 27393
    },
    {
      "epoch": 0.8415199827972845,
      "grad_norm": 0.32521119713783264,
      "learning_rate": 1.2491354865929349e-05,
      "loss": 0.5823,
      "step": 27394
    },
    {
      "epoch": 0.8415507019322336,
      "grad_norm": 0.375021368265152,
      "learning_rate": 1.2490886824074688e-05,
      "loss": 0.5164,
      "step": 27395
    },
    {
      "epoch": 0.8415814210671827,
      "grad_norm": 0.38915857672691345,
      "learning_rate": 1.2490418776402386e-05,
      "loss": 0.5349,
      "step": 27396
    },
    {
      "epoch": 0.8416121402021319,
      "grad_norm": 0.33684274554252625,
      "learning_rate": 1.2489950722913539e-05,
      "loss": 0.4608,
      "step": 27397
    },
    {
      "epoch": 0.841642859337081,
      "grad_norm": 0.3802452087402344,
      "learning_rate": 1.248948266360924e-05,
      "loss": 0.5946,
      "step": 27398
    },
    {
      "epoch": 0.8416735784720303,
      "grad_norm": 0.4298010468482971,
      "learning_rate": 1.2489014598490577e-05,
      "loss": 0.5988,
      "step": 27399
    },
    {
      "epoch": 0.8417042976069794,
      "grad_norm": 0.36444807052612305,
      "learning_rate": 1.2488546527558647e-05,
      "loss": 0.4773,
      "step": 27400
    },
    {
      "epoch": 0.8417350167419285,
      "grad_norm": 0.33031296730041504,
      "learning_rate": 1.2488078450814541e-05,
      "loss": 0.5425,
      "step": 27401
    },
    {
      "epoch": 0.8417657358768778,
      "grad_norm": 0.36067917943000793,
      "learning_rate": 1.2487610368259357e-05,
      "loss": 0.4461,
      "step": 27402
    },
    {
      "epoch": 0.8417964550118269,
      "grad_norm": 0.44623494148254395,
      "learning_rate": 1.2487142279894181e-05,
      "loss": 0.5321,
      "step": 27403
    },
    {
      "epoch": 0.841827174146776,
      "grad_norm": 0.3596116304397583,
      "learning_rate": 1.2486674185720116e-05,
      "loss": 0.4865,
      "step": 27404
    },
    {
      "epoch": 0.8418578932817252,
      "grad_norm": 0.38318848609924316,
      "learning_rate": 1.2486206085738246e-05,
      "loss": 0.554,
      "step": 27405
    },
    {
      "epoch": 0.8418886124166743,
      "grad_norm": 0.33712226152420044,
      "learning_rate": 1.248573797994967e-05,
      "loss": 0.542,
      "step": 27406
    },
    {
      "epoch": 0.8419193315516235,
      "grad_norm": 0.36827778816223145,
      "learning_rate": 1.2485269868355478e-05,
      "loss": 0.6046,
      "step": 27407
    },
    {
      "epoch": 0.8419500506865727,
      "grad_norm": 0.32063066959381104,
      "learning_rate": 1.2484801750956767e-05,
      "loss": 0.477,
      "step": 27408
    },
    {
      "epoch": 0.8419807698215218,
      "grad_norm": 0.4022870361804962,
      "learning_rate": 1.2484333627754625e-05,
      "loss": 0.5679,
      "step": 27409
    },
    {
      "epoch": 0.8420114889564709,
      "grad_norm": 0.3763059079647064,
      "learning_rate": 1.2483865498750152e-05,
      "loss": 0.5568,
      "step": 27410
    },
    {
      "epoch": 0.8420422080914202,
      "grad_norm": 0.39209863543510437,
      "learning_rate": 1.2483397363944436e-05,
      "loss": 0.5311,
      "step": 27411
    },
    {
      "epoch": 0.8420729272263693,
      "grad_norm": 0.3428773880004883,
      "learning_rate": 1.2482929223338566e-05,
      "loss": 0.6133,
      "step": 27412
    },
    {
      "epoch": 0.8421036463613185,
      "grad_norm": 0.39146748185157776,
      "learning_rate": 1.2482461076933649e-05,
      "loss": 0.5413,
      "step": 27413
    },
    {
      "epoch": 0.8421343654962676,
      "grad_norm": 0.33835369348526,
      "learning_rate": 1.2481992924730768e-05,
      "loss": 0.5309,
      "step": 27414
    },
    {
      "epoch": 0.8421650846312168,
      "grad_norm": 0.3661634624004364,
      "learning_rate": 1.2481524766731022e-05,
      "loss": 0.5791,
      "step": 27415
    },
    {
      "epoch": 0.842195803766166,
      "grad_norm": 0.3841603696346283,
      "learning_rate": 1.24810566029355e-05,
      "loss": 0.5794,
      "step": 27416
    },
    {
      "epoch": 0.8422265229011151,
      "grad_norm": 0.3765762448310852,
      "learning_rate": 1.2480588433345296e-05,
      "loss": 0.5676,
      "step": 27417
    },
    {
      "epoch": 0.8422572420360642,
      "grad_norm": 0.4025719165802002,
      "learning_rate": 1.2480120257961503e-05,
      "loss": 0.5263,
      "step": 27418
    },
    {
      "epoch": 0.8422879611710135,
      "grad_norm": 0.3541122078895569,
      "learning_rate": 1.2479652076785218e-05,
      "loss": 0.5902,
      "step": 27419
    },
    {
      "epoch": 0.8423186803059626,
      "grad_norm": 0.34577128291130066,
      "learning_rate": 1.2479183889817534e-05,
      "loss": 0.5236,
      "step": 27420
    },
    {
      "epoch": 0.8423493994409117,
      "grad_norm": 0.3452979028224945,
      "learning_rate": 1.247871569705954e-05,
      "loss": 0.4874,
      "step": 27421
    },
    {
      "epoch": 0.8423801185758609,
      "grad_norm": 0.34384456276893616,
      "learning_rate": 1.2478247498512332e-05,
      "loss": 0.5005,
      "step": 27422
    },
    {
      "epoch": 0.84241083771081,
      "grad_norm": 0.35666245222091675,
      "learning_rate": 1.2477779294177006e-05,
      "loss": 0.5452,
      "step": 27423
    },
    {
      "epoch": 0.8424415568457593,
      "grad_norm": 0.962787926197052,
      "learning_rate": 1.2477311084054652e-05,
      "loss": 0.5507,
      "step": 27424
    },
    {
      "epoch": 0.8424722759807084,
      "grad_norm": 0.35569605231285095,
      "learning_rate": 1.2476842868146365e-05,
      "loss": 0.5778,
      "step": 27425
    },
    {
      "epoch": 0.8425029951156575,
      "grad_norm": 0.4006465971469879,
      "learning_rate": 1.2476374646453242e-05,
      "loss": 0.5493,
      "step": 27426
    },
    {
      "epoch": 0.8425337142506067,
      "grad_norm": 0.36328232288360596,
      "learning_rate": 1.2475906418976372e-05,
      "loss": 0.527,
      "step": 27427
    },
    {
      "epoch": 0.8425644333855559,
      "grad_norm": 0.37749743461608887,
      "learning_rate": 1.2475438185716846e-05,
      "loss": 0.5454,
      "step": 27428
    },
    {
      "epoch": 0.842595152520505,
      "grad_norm": 0.39355728030204773,
      "learning_rate": 1.2474969946675764e-05,
      "loss": 0.6359,
      "step": 27429
    },
    {
      "epoch": 0.8426258716554542,
      "grad_norm": 0.37623897194862366,
      "learning_rate": 1.2474501701854214e-05,
      "loss": 0.5565,
      "step": 27430
    },
    {
      "epoch": 0.8426565907904033,
      "grad_norm": 0.6305463314056396,
      "learning_rate": 1.2474033451253294e-05,
      "loss": 0.5848,
      "step": 27431
    },
    {
      "epoch": 0.8426873099253525,
      "grad_norm": 0.3767709732055664,
      "learning_rate": 1.2473565194874095e-05,
      "loss": 0.5534,
      "step": 27432
    },
    {
      "epoch": 0.8427180290603017,
      "grad_norm": 0.36122873425483704,
      "learning_rate": 1.2473096932717714e-05,
      "loss": 0.5762,
      "step": 27433
    },
    {
      "epoch": 0.8427487481952508,
      "grad_norm": 0.36045101284980774,
      "learning_rate": 1.2472628664785243e-05,
      "loss": 0.591,
      "step": 27434
    },
    {
      "epoch": 0.8427794673301999,
      "grad_norm": 0.35751375555992126,
      "learning_rate": 1.2472160391077773e-05,
      "loss": 0.4889,
      "step": 27435
    },
    {
      "epoch": 0.8428101864651492,
      "grad_norm": 0.3631209433078766,
      "learning_rate": 1.24716921115964e-05,
      "loss": 0.598,
      "step": 27436
    },
    {
      "epoch": 0.8428409056000983,
      "grad_norm": 0.40210917592048645,
      "learning_rate": 1.2471223826342217e-05,
      "loss": 0.5913,
      "step": 27437
    },
    {
      "epoch": 0.8428716247350475,
      "grad_norm": 0.36513596773147583,
      "learning_rate": 1.2470755535316321e-05,
      "loss": 0.4833,
      "step": 27438
    },
    {
      "epoch": 0.8429023438699966,
      "grad_norm": 0.35902804136276245,
      "learning_rate": 1.24702872385198e-05,
      "loss": 0.544,
      "step": 27439
    },
    {
      "epoch": 0.8429330630049457,
      "grad_norm": 0.3843648433685303,
      "learning_rate": 1.2469818935953753e-05,
      "loss": 0.5446,
      "step": 27440
    },
    {
      "epoch": 0.842963782139895,
      "grad_norm": 0.3491418957710266,
      "learning_rate": 1.2469350627619268e-05,
      "loss": 0.4775,
      "step": 27441
    },
    {
      "epoch": 0.8429945012748441,
      "grad_norm": 0.3477470874786377,
      "learning_rate": 1.2468882313517446e-05,
      "loss": 0.5165,
      "step": 27442
    },
    {
      "epoch": 0.8430252204097932,
      "grad_norm": 0.3816833794116974,
      "learning_rate": 1.2468413993649373e-05,
      "loss": 0.5472,
      "step": 27443
    },
    {
      "epoch": 0.8430559395447424,
      "grad_norm": 0.3773796558380127,
      "learning_rate": 1.246794566801615e-05,
      "loss": 0.512,
      "step": 27444
    },
    {
      "epoch": 0.8430866586796916,
      "grad_norm": 0.3752632141113281,
      "learning_rate": 1.2467477336618868e-05,
      "loss": 0.5166,
      "step": 27445
    },
    {
      "epoch": 0.8431173778146407,
      "grad_norm": 0.3504323661327362,
      "learning_rate": 1.2467008999458616e-05,
      "loss": 0.5573,
      "step": 27446
    },
    {
      "epoch": 0.8431480969495899,
      "grad_norm": 0.36194926500320435,
      "learning_rate": 1.2466540656536497e-05,
      "loss": 0.5513,
      "step": 27447
    },
    {
      "epoch": 0.843178816084539,
      "grad_norm": 0.3479464650154114,
      "learning_rate": 1.2466072307853595e-05,
      "loss": 0.5835,
      "step": 27448
    },
    {
      "epoch": 0.8432095352194883,
      "grad_norm": 0.40857839584350586,
      "learning_rate": 1.2465603953411012e-05,
      "loss": 0.5406,
      "step": 27449
    },
    {
      "epoch": 0.8432402543544374,
      "grad_norm": 0.406244695186615,
      "learning_rate": 1.2465135593209839e-05,
      "loss": 0.5562,
      "step": 27450
    },
    {
      "epoch": 0.8432709734893865,
      "grad_norm": 0.3406674861907959,
      "learning_rate": 1.2464667227251168e-05,
      "loss": 0.447,
      "step": 27451
    },
    {
      "epoch": 0.8433016926243357,
      "grad_norm": 0.3878394365310669,
      "learning_rate": 1.2464198855536099e-05,
      "loss": 0.4099,
      "step": 27452
    },
    {
      "epoch": 0.8433324117592849,
      "grad_norm": 0.5348444581031799,
      "learning_rate": 1.2463730478065717e-05,
      "loss": 0.5598,
      "step": 27453
    },
    {
      "epoch": 0.843363130894234,
      "grad_norm": 0.3873843848705292,
      "learning_rate": 1.2463262094841123e-05,
      "loss": 0.4979,
      "step": 27454
    },
    {
      "epoch": 0.8433938500291832,
      "grad_norm": 0.3943963050842285,
      "learning_rate": 1.2462793705863405e-05,
      "loss": 0.6055,
      "step": 27455
    },
    {
      "epoch": 0.8434245691641323,
      "grad_norm": 0.37207284569740295,
      "learning_rate": 1.2462325311133663e-05,
      "loss": 0.5498,
      "step": 27456
    },
    {
      "epoch": 0.8434552882990815,
      "grad_norm": 0.38212722539901733,
      "learning_rate": 1.2461856910652985e-05,
      "loss": 0.4573,
      "step": 27457
    },
    {
      "epoch": 0.8434860074340307,
      "grad_norm": 0.34409472346305847,
      "learning_rate": 1.2461388504422473e-05,
      "loss": 0.6071,
      "step": 27458
    },
    {
      "epoch": 0.8435167265689798,
      "grad_norm": 0.36049747467041016,
      "learning_rate": 1.2460920092443213e-05,
      "loss": 0.5962,
      "step": 27459
    },
    {
      "epoch": 0.8435474457039289,
      "grad_norm": 0.33845147490501404,
      "learning_rate": 1.2460451674716305e-05,
      "loss": 0.5955,
      "step": 27460
    },
    {
      "epoch": 0.8435781648388782,
      "grad_norm": 0.36615025997161865,
      "learning_rate": 1.2459983251242838e-05,
      "loss": 0.5233,
      "step": 27461
    },
    {
      "epoch": 0.8436088839738273,
      "grad_norm": 0.35513490438461304,
      "learning_rate": 1.2459514822023908e-05,
      "loss": 0.5157,
      "step": 27462
    },
    {
      "epoch": 0.8436396031087765,
      "grad_norm": 0.39335811138153076,
      "learning_rate": 1.2459046387060612e-05,
      "loss": 0.5459,
      "step": 27463
    },
    {
      "epoch": 0.8436703222437256,
      "grad_norm": 0.408810555934906,
      "learning_rate": 1.2458577946354038e-05,
      "loss": 0.5074,
      "step": 27464
    },
    {
      "epoch": 0.8437010413786747,
      "grad_norm": 0.3937597870826721,
      "learning_rate": 1.2458109499905286e-05,
      "loss": 0.5336,
      "step": 27465
    },
    {
      "epoch": 0.843731760513624,
      "grad_norm": 0.41812509298324585,
      "learning_rate": 1.2457641047715448e-05,
      "loss": 0.5243,
      "step": 27466
    },
    {
      "epoch": 0.8437624796485731,
      "grad_norm": 0.3814831078052521,
      "learning_rate": 1.2457172589785614e-05,
      "loss": 0.5572,
      "step": 27467
    },
    {
      "epoch": 0.8437931987835222,
      "grad_norm": 0.4409952759742737,
      "learning_rate": 1.2456704126116885e-05,
      "loss": 0.4851,
      "step": 27468
    },
    {
      "epoch": 0.8438239179184714,
      "grad_norm": 0.40220651030540466,
      "learning_rate": 1.2456235656710351e-05,
      "loss": 0.5336,
      "step": 27469
    },
    {
      "epoch": 0.8438546370534206,
      "grad_norm": 0.4967983067035675,
      "learning_rate": 1.245576718156711e-05,
      "loss": 0.5606,
      "step": 27470
    },
    {
      "epoch": 0.8438853561883697,
      "grad_norm": 0.3889867663383484,
      "learning_rate": 1.2455298700688248e-05,
      "loss": 0.6071,
      "step": 27471
    },
    {
      "epoch": 0.8439160753233189,
      "grad_norm": 0.4117208421230316,
      "learning_rate": 1.2454830214074867e-05,
      "loss": 0.6247,
      "step": 27472
    },
    {
      "epoch": 0.843946794458268,
      "grad_norm": 0.35783442854881287,
      "learning_rate": 1.2454361721728057e-05,
      "loss": 0.5623,
      "step": 27473
    },
    {
      "epoch": 0.8439775135932173,
      "grad_norm": 0.3555428385734558,
      "learning_rate": 1.2453893223648916e-05,
      "loss": 0.5628,
      "step": 27474
    },
    {
      "epoch": 0.8440082327281664,
      "grad_norm": 0.3803429901599884,
      "learning_rate": 1.2453424719838537e-05,
      "loss": 0.5293,
      "step": 27475
    },
    {
      "epoch": 0.8440389518631155,
      "grad_norm": 0.34978097677230835,
      "learning_rate": 1.245295621029801e-05,
      "loss": 0.5623,
      "step": 27476
    },
    {
      "epoch": 0.8440696709980647,
      "grad_norm": 0.3381558060646057,
      "learning_rate": 1.2452487695028434e-05,
      "loss": 0.5503,
      "step": 27477
    },
    {
      "epoch": 0.8441003901330139,
      "grad_norm": 0.35216203331947327,
      "learning_rate": 1.2452019174030902e-05,
      "loss": 0.5005,
      "step": 27478
    },
    {
      "epoch": 0.844131109267963,
      "grad_norm": 0.34353363513946533,
      "learning_rate": 1.245155064730651e-05,
      "loss": 0.4739,
      "step": 27479
    },
    {
      "epoch": 0.8441618284029122,
      "grad_norm": 0.4045220911502838,
      "learning_rate": 1.2451082114856345e-05,
      "loss": 0.5298,
      "step": 27480
    },
    {
      "epoch": 0.8441925475378613,
      "grad_norm": 0.3818540573120117,
      "learning_rate": 1.2450613576681513e-05,
      "loss": 0.5466,
      "step": 27481
    },
    {
      "epoch": 0.8442232666728104,
      "grad_norm": 0.37245962023735046,
      "learning_rate": 1.2450145032783097e-05,
      "loss": 0.5169,
      "step": 27482
    },
    {
      "epoch": 0.8442539858077597,
      "grad_norm": 0.36826032400131226,
      "learning_rate": 1.2449676483162196e-05,
      "loss": 0.5286,
      "step": 27483
    },
    {
      "epoch": 0.8442847049427088,
      "grad_norm": 0.3319023549556732,
      "learning_rate": 1.2449207927819906e-05,
      "loss": 0.5382,
      "step": 27484
    },
    {
      "epoch": 0.844315424077658,
      "grad_norm": 0.3656357526779175,
      "learning_rate": 1.244873936675732e-05,
      "loss": 0.4829,
      "step": 27485
    },
    {
      "epoch": 0.8443461432126071,
      "grad_norm": 0.3522183895111084,
      "learning_rate": 1.2448270799975532e-05,
      "loss": 0.5703,
      "step": 27486
    },
    {
      "epoch": 0.8443768623475563,
      "grad_norm": 0.3889095187187195,
      "learning_rate": 1.2447802227475636e-05,
      "loss": 0.5907,
      "step": 27487
    },
    {
      "epoch": 0.8444075814825055,
      "grad_norm": 0.417457640171051,
      "learning_rate": 1.2447333649258729e-05,
      "loss": 0.5654,
      "step": 27488
    },
    {
      "epoch": 0.8444383006174546,
      "grad_norm": 0.3740599453449249,
      "learning_rate": 1.24468650653259e-05,
      "loss": 0.6197,
      "step": 27489
    },
    {
      "epoch": 0.8444690197524037,
      "grad_norm": 0.3461305499076843,
      "learning_rate": 1.2446396475678249e-05,
      "loss": 0.5453,
      "step": 27490
    },
    {
      "epoch": 0.844499738887353,
      "grad_norm": 0.4766981899738312,
      "learning_rate": 1.2445927880316866e-05,
      "loss": 0.6333,
      "step": 27491
    },
    {
      "epoch": 0.8445304580223021,
      "grad_norm": 0.3580690026283264,
      "learning_rate": 1.244545927924285e-05,
      "loss": 0.4778,
      "step": 27492
    },
    {
      "epoch": 0.8445611771572512,
      "grad_norm": 0.3485373854637146,
      "learning_rate": 1.2444990672457293e-05,
      "loss": 0.5565,
      "step": 27493
    },
    {
      "epoch": 0.8445918962922004,
      "grad_norm": 0.3937159776687622,
      "learning_rate": 1.244452205996129e-05,
      "loss": 0.5676,
      "step": 27494
    },
    {
      "epoch": 0.8446226154271496,
      "grad_norm": 0.3483898341655731,
      "learning_rate": 1.2444053441755932e-05,
      "loss": 0.5715,
      "step": 27495
    },
    {
      "epoch": 0.8446533345620987,
      "grad_norm": 0.36250749230384827,
      "learning_rate": 1.244358481784232e-05,
      "loss": 0.5816,
      "step": 27496
    },
    {
      "epoch": 0.8446840536970479,
      "grad_norm": 0.46397534012794495,
      "learning_rate": 1.2443116188221544e-05,
      "loss": 0.5647,
      "step": 27497
    },
    {
      "epoch": 0.844714772831997,
      "grad_norm": 0.3613952398300171,
      "learning_rate": 1.2442647552894697e-05,
      "loss": 0.5563,
      "step": 27498
    },
    {
      "epoch": 0.8447454919669463,
      "grad_norm": 0.39790454506874084,
      "learning_rate": 1.2442178911862881e-05,
      "loss": 0.5708,
      "step": 27499
    },
    {
      "epoch": 0.8447762111018954,
      "grad_norm": 0.34501633048057556,
      "learning_rate": 1.244171026512718e-05,
      "loss": 0.6243,
      "step": 27500
    },
    {
      "epoch": 0.8448069302368445,
      "grad_norm": 0.36811622977256775,
      "learning_rate": 1.24412416126887e-05,
      "loss": 0.5027,
      "step": 27501
    },
    {
      "epoch": 0.8448376493717937,
      "grad_norm": 0.36631274223327637,
      "learning_rate": 1.2440772954548526e-05,
      "loss": 0.4092,
      "step": 27502
    },
    {
      "epoch": 0.8448683685067429,
      "grad_norm": 0.3737470805644989,
      "learning_rate": 1.2440304290707756e-05,
      "loss": 0.528,
      "step": 27503
    },
    {
      "epoch": 0.844899087641692,
      "grad_norm": 0.35294249653816223,
      "learning_rate": 1.2439835621167485e-05,
      "loss": 0.5674,
      "step": 27504
    },
    {
      "epoch": 0.8449298067766412,
      "grad_norm": 0.32488858699798584,
      "learning_rate": 1.2439366945928808e-05,
      "loss": 0.5054,
      "step": 27505
    },
    {
      "epoch": 0.8449605259115903,
      "grad_norm": 0.3372909128665924,
      "learning_rate": 1.2438898264992821e-05,
      "loss": 0.5236,
      "step": 27506
    },
    {
      "epoch": 0.8449912450465394,
      "grad_norm": 0.370376318693161,
      "learning_rate": 1.243842957836061e-05,
      "loss": 0.4734,
      "step": 27507
    },
    {
      "epoch": 0.8450219641814887,
      "grad_norm": 0.32630041241645813,
      "learning_rate": 1.2437960886033284e-05,
      "loss": 0.5533,
      "step": 27508
    },
    {
      "epoch": 0.8450526833164378,
      "grad_norm": 0.34646859765052795,
      "learning_rate": 1.2437492188011928e-05,
      "loss": 0.5514,
      "step": 27509
    },
    {
      "epoch": 0.845083402451387,
      "grad_norm": 0.3916209936141968,
      "learning_rate": 1.243702348429764e-05,
      "loss": 0.551,
      "step": 27510
    },
    {
      "epoch": 0.8451141215863361,
      "grad_norm": 0.3674609363079071,
      "learning_rate": 1.243655477489151e-05,
      "loss": 0.5221,
      "step": 27511
    },
    {
      "epoch": 0.8451448407212853,
      "grad_norm": 0.37774842977523804,
      "learning_rate": 1.2436086059794639e-05,
      "loss": 0.5602,
      "step": 27512
    },
    {
      "epoch": 0.8451755598562345,
      "grad_norm": 0.37175115942955017,
      "learning_rate": 1.2435617339008117e-05,
      "loss": 0.5174,
      "step": 27513
    },
    {
      "epoch": 0.8452062789911836,
      "grad_norm": 0.3656691610813141,
      "learning_rate": 1.2435148612533042e-05,
      "loss": 0.5709,
      "step": 27514
    },
    {
      "epoch": 0.8452369981261327,
      "grad_norm": 0.39803406596183777,
      "learning_rate": 1.2434679880370508e-05,
      "loss": 0.5414,
      "step": 27515
    },
    {
      "epoch": 0.845267717261082,
      "grad_norm": 0.3508002758026123,
      "learning_rate": 1.2434211142521607e-05,
      "loss": 0.532,
      "step": 27516
    },
    {
      "epoch": 0.8452984363960311,
      "grad_norm": 0.3391759693622589,
      "learning_rate": 1.2433742398987439e-05,
      "loss": 0.5063,
      "step": 27517
    },
    {
      "epoch": 0.8453291555309802,
      "grad_norm": 0.3664117753505707,
      "learning_rate": 1.243327364976909e-05,
      "loss": 0.5723,
      "step": 27518
    },
    {
      "epoch": 0.8453598746659294,
      "grad_norm": 0.3381238877773285,
      "learning_rate": 1.2432804894867667e-05,
      "loss": 0.5431,
      "step": 27519
    },
    {
      "epoch": 0.8453905938008786,
      "grad_norm": 0.38711369037628174,
      "learning_rate": 1.2432336134284253e-05,
      "loss": 0.4919,
      "step": 27520
    },
    {
      "epoch": 0.8454213129358277,
      "grad_norm": 0.4541545808315277,
      "learning_rate": 1.2431867368019952e-05,
      "loss": 0.5279,
      "step": 27521
    },
    {
      "epoch": 0.8454520320707769,
      "grad_norm": 0.37916433811187744,
      "learning_rate": 1.2431398596075852e-05,
      "loss": 0.5499,
      "step": 27522
    },
    {
      "epoch": 0.845482751205726,
      "grad_norm": 0.3459722399711609,
      "learning_rate": 1.243092981845305e-05,
      "loss": 0.5752,
      "step": 27523
    },
    {
      "epoch": 0.8455134703406753,
      "grad_norm": 0.3798540532588959,
      "learning_rate": 1.2430461035152646e-05,
      "loss": 0.5212,
      "step": 27524
    },
    {
      "epoch": 0.8455441894756244,
      "grad_norm": 0.38089612126350403,
      "learning_rate": 1.2429992246175726e-05,
      "loss": 0.5352,
      "step": 27525
    },
    {
      "epoch": 0.8455749086105735,
      "grad_norm": 0.3884556293487549,
      "learning_rate": 1.2429523451523392e-05,
      "loss": 0.5921,
      "step": 27526
    },
    {
      "epoch": 0.8456056277455227,
      "grad_norm": 0.3622110188007355,
      "learning_rate": 1.2429054651196734e-05,
      "loss": 0.4896,
      "step": 27527
    },
    {
      "epoch": 0.8456363468804718,
      "grad_norm": 0.356887549161911,
      "learning_rate": 1.2428585845196851e-05,
      "loss": 0.5377,
      "step": 27528
    },
    {
      "epoch": 0.845667066015421,
      "grad_norm": 0.3562752902507782,
      "learning_rate": 1.2428117033524838e-05,
      "loss": 0.5897,
      "step": 27529
    },
    {
      "epoch": 0.8456977851503702,
      "grad_norm": 0.34182778000831604,
      "learning_rate": 1.2427648216181787e-05,
      "loss": 0.5323,
      "step": 27530
    },
    {
      "epoch": 0.8457285042853193,
      "grad_norm": 0.35560935735702515,
      "learning_rate": 1.2427179393168794e-05,
      "loss": 0.5798,
      "step": 27531
    },
    {
      "epoch": 0.8457592234202684,
      "grad_norm": 0.3527083694934845,
      "learning_rate": 1.2426710564486952e-05,
      "loss": 0.5745,
      "step": 27532
    },
    {
      "epoch": 0.8457899425552177,
      "grad_norm": 0.38120928406715393,
      "learning_rate": 1.2426241730137361e-05,
      "loss": 0.5783,
      "step": 27533
    },
    {
      "epoch": 0.8458206616901668,
      "grad_norm": 0.4197694957256317,
      "learning_rate": 1.242577289012111e-05,
      "loss": 0.5684,
      "step": 27534
    },
    {
      "epoch": 0.845851380825116,
      "grad_norm": 0.37842699885368347,
      "learning_rate": 1.24253040444393e-05,
      "loss": 0.5808,
      "step": 27535
    },
    {
      "epoch": 0.8458820999600651,
      "grad_norm": 0.36563238501548767,
      "learning_rate": 1.242483519309302e-05,
      "loss": 0.5197,
      "step": 27536
    },
    {
      "epoch": 0.8459128190950143,
      "grad_norm": 0.34175485372543335,
      "learning_rate": 1.2424366336083369e-05,
      "loss": 0.468,
      "step": 27537
    },
    {
      "epoch": 0.8459435382299635,
      "grad_norm": 0.35126546025276184,
      "learning_rate": 1.2423897473411442e-05,
      "loss": 0.5393,
      "step": 27538
    },
    {
      "epoch": 0.8459742573649126,
      "grad_norm": 0.33626681566238403,
      "learning_rate": 1.2423428605078333e-05,
      "loss": 0.4872,
      "step": 27539
    },
    {
      "epoch": 0.8460049764998617,
      "grad_norm": 0.34489545226097107,
      "learning_rate": 1.2422959731085135e-05,
      "loss": 0.4927,
      "step": 27540
    },
    {
      "epoch": 0.846035695634811,
      "grad_norm": 0.32902905344963074,
      "learning_rate": 1.2422490851432947e-05,
      "loss": 0.5538,
      "step": 27541
    },
    {
      "epoch": 0.8460664147697601,
      "grad_norm": 0.39556071162223816,
      "learning_rate": 1.2422021966122864e-05,
      "loss": 0.6169,
      "step": 27542
    },
    {
      "epoch": 0.8460971339047092,
      "grad_norm": 0.36458417773246765,
      "learning_rate": 1.2421553075155976e-05,
      "loss": 0.5284,
      "step": 27543
    },
    {
      "epoch": 0.8461278530396584,
      "grad_norm": 0.3372204005718231,
      "learning_rate": 1.2421084178533385e-05,
      "loss": 0.5552,
      "step": 27544
    },
    {
      "epoch": 0.8461585721746075,
      "grad_norm": 0.4863251745700836,
      "learning_rate": 1.2420615276256181e-05,
      "loss": 0.6552,
      "step": 27545
    },
    {
      "epoch": 0.8461892913095567,
      "grad_norm": 0.35853105783462524,
      "learning_rate": 1.2420146368325463e-05,
      "loss": 0.5374,
      "step": 27546
    },
    {
      "epoch": 0.8462200104445059,
      "grad_norm": 0.3419025242328644,
      "learning_rate": 1.241967745474232e-05,
      "loss": 0.5207,
      "step": 27547
    },
    {
      "epoch": 0.846250729579455,
      "grad_norm": 0.38604798913002014,
      "learning_rate": 1.2419208535507856e-05,
      "loss": 0.4841,
      "step": 27548
    },
    {
      "epoch": 0.8462814487144042,
      "grad_norm": 0.9277123212814331,
      "learning_rate": 1.241873961062316e-05,
      "loss": 0.5742,
      "step": 27549
    },
    {
      "epoch": 0.8463121678493534,
      "grad_norm": 0.4297885298728943,
      "learning_rate": 1.2418270680089329e-05,
      "loss": 0.6459,
      "step": 27550
    },
    {
      "epoch": 0.8463428869843025,
      "grad_norm": 0.3648771345615387,
      "learning_rate": 1.2417801743907458e-05,
      "loss": 0.54,
      "step": 27551
    },
    {
      "epoch": 0.8463736061192517,
      "grad_norm": 0.34363052248954773,
      "learning_rate": 1.2417332802078642e-05,
      "loss": 0.5059,
      "step": 27552
    },
    {
      "epoch": 0.8464043252542008,
      "grad_norm": 0.3713448941707611,
      "learning_rate": 1.2416863854603975e-05,
      "loss": 0.5647,
      "step": 27553
    },
    {
      "epoch": 0.84643504438915,
      "grad_norm": 0.35090014338493347,
      "learning_rate": 1.2416394901484554e-05,
      "loss": 0.5637,
      "step": 27554
    },
    {
      "epoch": 0.8464657635240992,
      "grad_norm": 0.3549133539199829,
      "learning_rate": 1.2415925942721476e-05,
      "loss": 0.4734,
      "step": 27555
    },
    {
      "epoch": 0.8464964826590483,
      "grad_norm": 0.35566067695617676,
      "learning_rate": 1.2415456978315832e-05,
      "loss": 0.6177,
      "step": 27556
    },
    {
      "epoch": 0.8465272017939974,
      "grad_norm": 0.39036643505096436,
      "learning_rate": 1.241498800826872e-05,
      "loss": 0.5315,
      "step": 27557
    },
    {
      "epoch": 0.8465579209289467,
      "grad_norm": 0.3655991554260254,
      "learning_rate": 1.2414519032581234e-05,
      "loss": 0.6207,
      "step": 27558
    },
    {
      "epoch": 0.8465886400638958,
      "grad_norm": 0.3891712725162506,
      "learning_rate": 1.2414050051254472e-05,
      "loss": 0.6197,
      "step": 27559
    },
    {
      "epoch": 0.846619359198845,
      "grad_norm": 0.36192891001701355,
      "learning_rate": 1.2413581064289527e-05,
      "loss": 0.5645,
      "step": 27560
    },
    {
      "epoch": 0.8466500783337941,
      "grad_norm": 0.42353636026382446,
      "learning_rate": 1.2413112071687493e-05,
      "loss": 0.6113,
      "step": 27561
    },
    {
      "epoch": 0.8466807974687433,
      "grad_norm": 0.34134212136268616,
      "learning_rate": 1.241264307344947e-05,
      "loss": 0.596,
      "step": 27562
    },
    {
      "epoch": 0.8467115166036925,
      "grad_norm": 0.35790976881980896,
      "learning_rate": 1.2412174069576548e-05,
      "loss": 0.5215,
      "step": 27563
    },
    {
      "epoch": 0.8467422357386416,
      "grad_norm": 0.4133078455924988,
      "learning_rate": 1.2411705060069827e-05,
      "loss": 0.566,
      "step": 27564
    },
    {
      "epoch": 0.8467729548735907,
      "grad_norm": 0.34150758385658264,
      "learning_rate": 1.24112360449304e-05,
      "loss": 0.519,
      "step": 27565
    },
    {
      "epoch": 0.84680367400854,
      "grad_norm": 0.3692472577095032,
      "learning_rate": 1.2410767024159363e-05,
      "loss": 0.5399,
      "step": 27566
    },
    {
      "epoch": 0.8468343931434891,
      "grad_norm": 0.3617804944515228,
      "learning_rate": 1.2410297997757812e-05,
      "loss": 0.5082,
      "step": 27567
    },
    {
      "epoch": 0.8468651122784382,
      "grad_norm": 0.3893692195415497,
      "learning_rate": 1.240982896572684e-05,
      "loss": 0.546,
      "step": 27568
    },
    {
      "epoch": 0.8468958314133874,
      "grad_norm": 0.4071747958660126,
      "learning_rate": 1.2409359928067545e-05,
      "loss": 0.516,
      "step": 27569
    },
    {
      "epoch": 0.8469265505483365,
      "grad_norm": 0.4233867824077606,
      "learning_rate": 1.2408890884781021e-05,
      "loss": 0.6066,
      "step": 27570
    },
    {
      "epoch": 0.8469572696832858,
      "grad_norm": 0.37697258591651917,
      "learning_rate": 1.2408421835868366e-05,
      "loss": 0.479,
      "step": 27571
    },
    {
      "epoch": 0.8469879888182349,
      "grad_norm": 0.3660478889942169,
      "learning_rate": 1.2407952781330669e-05,
      "loss": 0.5091,
      "step": 27572
    },
    {
      "epoch": 0.847018707953184,
      "grad_norm": 0.4180964529514313,
      "learning_rate": 1.2407483721169036e-05,
      "loss": 0.6228,
      "step": 27573
    },
    {
      "epoch": 0.8470494270881332,
      "grad_norm": 0.36409011483192444,
      "learning_rate": 1.2407014655384553e-05,
      "loss": 0.5917,
      "step": 27574
    },
    {
      "epoch": 0.8470801462230824,
      "grad_norm": 0.3454005718231201,
      "learning_rate": 1.240654558397832e-05,
      "loss": 0.6072,
      "step": 27575
    },
    {
      "epoch": 0.8471108653580315,
      "grad_norm": 0.35828661918640137,
      "learning_rate": 1.2406076506951432e-05,
      "loss": 0.5921,
      "step": 27576
    },
    {
      "epoch": 0.8471415844929807,
      "grad_norm": 0.3394390940666199,
      "learning_rate": 1.2405607424304981e-05,
      "loss": 0.5259,
      "step": 27577
    },
    {
      "epoch": 0.8471723036279298,
      "grad_norm": 0.4342328906059265,
      "learning_rate": 1.2405138336040072e-05,
      "loss": 0.5931,
      "step": 27578
    },
    {
      "epoch": 0.847203022762879,
      "grad_norm": 0.4988875091075897,
      "learning_rate": 1.240466924215779e-05,
      "loss": 0.6536,
      "step": 27579
    },
    {
      "epoch": 0.8472337418978282,
      "grad_norm": 0.45602115988731384,
      "learning_rate": 1.2404200142659238e-05,
      "loss": 0.5935,
      "step": 27580
    },
    {
      "epoch": 0.8472644610327773,
      "grad_norm": 0.3758673071861267,
      "learning_rate": 1.2403731037545505e-05,
      "loss": 0.5508,
      "step": 27581
    },
    {
      "epoch": 0.8472951801677264,
      "grad_norm": 0.341767281293869,
      "learning_rate": 1.2403261926817693e-05,
      "loss": 0.504,
      "step": 27582
    },
    {
      "epoch": 0.8473258993026757,
      "grad_norm": 0.34443292021751404,
      "learning_rate": 1.2402792810476897e-05,
      "loss": 0.5203,
      "step": 27583
    },
    {
      "epoch": 0.8473566184376248,
      "grad_norm": 0.3747936189174652,
      "learning_rate": 1.2402323688524205e-05,
      "loss": 0.6031,
      "step": 27584
    },
    {
      "epoch": 0.847387337572574,
      "grad_norm": 0.36414021253585815,
      "learning_rate": 1.2401854560960722e-05,
      "loss": 0.509,
      "step": 27585
    },
    {
      "epoch": 0.8474180567075231,
      "grad_norm": 0.36967065930366516,
      "learning_rate": 1.2401385427787538e-05,
      "loss": 0.5198,
      "step": 27586
    },
    {
      "epoch": 0.8474487758424722,
      "grad_norm": 0.3400532007217407,
      "learning_rate": 1.2400916289005753e-05,
      "loss": 0.495,
      "step": 27587
    },
    {
      "epoch": 0.8474794949774215,
      "grad_norm": 0.3551408350467682,
      "learning_rate": 1.2400447144616457e-05,
      "loss": 0.6143,
      "step": 27588
    },
    {
      "epoch": 0.8475102141123706,
      "grad_norm": 0.3659326136112213,
      "learning_rate": 1.2399977994620753e-05,
      "loss": 0.5256,
      "step": 27589
    },
    {
      "epoch": 0.8475409332473197,
      "grad_norm": 0.3556739389896393,
      "learning_rate": 1.239950883901973e-05,
      "loss": 0.53,
      "step": 27590
    },
    {
      "epoch": 0.847571652382269,
      "grad_norm": 0.3547216057777405,
      "learning_rate": 1.2399039677814488e-05,
      "loss": 0.5626,
      "step": 27591
    },
    {
      "epoch": 0.8476023715172181,
      "grad_norm": 0.3815220892429352,
      "learning_rate": 1.239857051100612e-05,
      "loss": 0.5298,
      "step": 27592
    },
    {
      "epoch": 0.8476330906521672,
      "grad_norm": 0.33802327513694763,
      "learning_rate": 1.2398101338595725e-05,
      "loss": 0.5299,
      "step": 27593
    },
    {
      "epoch": 0.8476638097871164,
      "grad_norm": 0.3804583251476288,
      "learning_rate": 1.2397632160584396e-05,
      "loss": 0.5206,
      "step": 27594
    },
    {
      "epoch": 0.8476945289220655,
      "grad_norm": 0.3531932830810547,
      "learning_rate": 1.2397162976973226e-05,
      "loss": 0.4489,
      "step": 27595
    },
    {
      "epoch": 0.8477252480570148,
      "grad_norm": 0.3475799262523651,
      "learning_rate": 1.2396693787763318e-05,
      "loss": 0.5297,
      "step": 27596
    },
    {
      "epoch": 0.8477559671919639,
      "grad_norm": 0.434799462556839,
      "learning_rate": 1.2396224592955763e-05,
      "loss": 0.6215,
      "step": 27597
    },
    {
      "epoch": 0.847786686326913,
      "grad_norm": 0.37432989478111267,
      "learning_rate": 1.239575539255166e-05,
      "loss": 0.5969,
      "step": 27598
    },
    {
      "epoch": 0.8478174054618622,
      "grad_norm": 0.3698047995567322,
      "learning_rate": 1.23952861865521e-05,
      "loss": 0.6239,
      "step": 27599
    },
    {
      "epoch": 0.8478481245968114,
      "grad_norm": 0.4090425670146942,
      "learning_rate": 1.2394816974958186e-05,
      "loss": 0.6218,
      "step": 27600
    },
    {
      "epoch": 0.8478788437317605,
      "grad_norm": 0.3428356945514679,
      "learning_rate": 1.2394347757771009e-05,
      "loss": 0.6455,
      "step": 27601
    },
    {
      "epoch": 0.8479095628667097,
      "grad_norm": 0.4947218596935272,
      "learning_rate": 1.239387853499166e-05,
      "loss": 0.5012,
      "step": 27602
    },
    {
      "epoch": 0.8479402820016588,
      "grad_norm": 0.3196181654930115,
      "learning_rate": 1.2393409306621246e-05,
      "loss": 0.5038,
      "step": 27603
    },
    {
      "epoch": 0.847971001136608,
      "grad_norm": 0.37893858551979065,
      "learning_rate": 1.2392940072660857e-05,
      "loss": 0.565,
      "step": 27604
    },
    {
      "epoch": 0.8480017202715572,
      "grad_norm": 0.4031427204608917,
      "learning_rate": 1.239247083311159e-05,
      "loss": 0.5866,
      "step": 27605
    },
    {
      "epoch": 0.8480324394065063,
      "grad_norm": 0.3469350039958954,
      "learning_rate": 1.2392001587974536e-05,
      "loss": 0.4709,
      "step": 27606
    },
    {
      "epoch": 0.8480631585414554,
      "grad_norm": 0.40895912051200867,
      "learning_rate": 1.23915323372508e-05,
      "loss": 0.535,
      "step": 27607
    },
    {
      "epoch": 0.8480938776764047,
      "grad_norm": 0.3670434355735779,
      "learning_rate": 1.239106308094147e-05,
      "loss": 0.4464,
      "step": 27608
    },
    {
      "epoch": 0.8481245968113538,
      "grad_norm": 0.38032007217407227,
      "learning_rate": 1.2390593819047647e-05,
      "loss": 0.5194,
      "step": 27609
    },
    {
      "epoch": 0.848155315946303,
      "grad_norm": 0.3661014139652252,
      "learning_rate": 1.239012455157042e-05,
      "loss": 0.4715,
      "step": 27610
    },
    {
      "epoch": 0.8481860350812521,
      "grad_norm": 0.4126776158809662,
      "learning_rate": 1.2389655278510899e-05,
      "loss": 0.5417,
      "step": 27611
    },
    {
      "epoch": 0.8482167542162012,
      "grad_norm": 0.37472566962242126,
      "learning_rate": 1.2389185999870168e-05,
      "loss": 0.5441,
      "step": 27612
    },
    {
      "epoch": 0.8482474733511505,
      "grad_norm": 0.4004959762096405,
      "learning_rate": 1.238871671564932e-05,
      "loss": 0.5539,
      "step": 27613
    },
    {
      "epoch": 0.8482781924860996,
      "grad_norm": 0.3484770357608795,
      "learning_rate": 1.2388247425849465e-05,
      "loss": 0.5705,
      "step": 27614
    },
    {
      "epoch": 0.8483089116210487,
      "grad_norm": 0.33629119396209717,
      "learning_rate": 1.2387778130471687e-05,
      "loss": 0.5067,
      "step": 27615
    },
    {
      "epoch": 0.8483396307559979,
      "grad_norm": 0.3756142556667328,
      "learning_rate": 1.2387308829517088e-05,
      "loss": 0.5346,
      "step": 27616
    },
    {
      "epoch": 0.8483703498909471,
      "grad_norm": 0.3652289807796478,
      "learning_rate": 1.2386839522986763e-05,
      "loss": 0.5617,
      "step": 27617
    },
    {
      "epoch": 0.8484010690258962,
      "grad_norm": 0.37556180357933044,
      "learning_rate": 1.2386370210881809e-05,
      "loss": 0.5169,
      "step": 27618
    },
    {
      "epoch": 0.8484317881608454,
      "grad_norm": 0.42423388361930847,
      "learning_rate": 1.2385900893203317e-05,
      "loss": 0.6148,
      "step": 27619
    },
    {
      "epoch": 0.8484625072957945,
      "grad_norm": 0.3416650891304016,
      "learning_rate": 1.2385431569952388e-05,
      "loss": 0.5309,
      "step": 27620
    },
    {
      "epoch": 0.8484932264307438,
      "grad_norm": 0.36803749203681946,
      "learning_rate": 1.2384962241130121e-05,
      "loss": 0.546,
      "step": 27621
    },
    {
      "epoch": 0.8485239455656929,
      "grad_norm": 0.39428457617759705,
      "learning_rate": 1.2384492906737602e-05,
      "loss": 0.5962,
      "step": 27622
    },
    {
      "epoch": 0.848554664700642,
      "grad_norm": 0.5533764362335205,
      "learning_rate": 1.2384023566775939e-05,
      "loss": 0.5379,
      "step": 27623
    },
    {
      "epoch": 0.8485853838355912,
      "grad_norm": 0.38032206892967224,
      "learning_rate": 1.2383554221246217e-05,
      "loss": 0.5974,
      "step": 27624
    },
    {
      "epoch": 0.8486161029705404,
      "grad_norm": 0.36803096532821655,
      "learning_rate": 1.2383084870149542e-05,
      "loss": 0.618,
      "step": 27625
    },
    {
      "epoch": 0.8486468221054895,
      "grad_norm": 0.3871247470378876,
      "learning_rate": 1.2382615513487002e-05,
      "loss": 0.5456,
      "step": 27626
    },
    {
      "epoch": 0.8486775412404387,
      "grad_norm": 0.35111314058303833,
      "learning_rate": 1.23821461512597e-05,
      "loss": 0.4787,
      "step": 27627
    },
    {
      "epoch": 0.8487082603753878,
      "grad_norm": 0.32581064105033875,
      "learning_rate": 1.2381676783468728e-05,
      "loss": 0.473,
      "step": 27628
    },
    {
      "epoch": 0.8487389795103369,
      "grad_norm": 0.38832929730415344,
      "learning_rate": 1.2381207410115184e-05,
      "loss": 0.599,
      "step": 27629
    },
    {
      "epoch": 0.8487696986452862,
      "grad_norm": 0.34616926312446594,
      "learning_rate": 1.2380738031200166e-05,
      "loss": 0.4384,
      "step": 27630
    },
    {
      "epoch": 0.8488004177802353,
      "grad_norm": 0.45111897587776184,
      "learning_rate": 1.2380268646724763e-05,
      "loss": 0.5393,
      "step": 27631
    },
    {
      "epoch": 0.8488311369151844,
      "grad_norm": 0.34794455766677856,
      "learning_rate": 1.2379799256690079e-05,
      "loss": 0.5699,
      "step": 27632
    },
    {
      "epoch": 0.8488618560501336,
      "grad_norm": 0.3860713541507721,
      "learning_rate": 1.2379329861097207e-05,
      "loss": 0.612,
      "step": 27633
    },
    {
      "epoch": 0.8488925751850828,
      "grad_norm": 0.41103070974349976,
      "learning_rate": 1.2378860459947245e-05,
      "loss": 0.5743,
      "step": 27634
    },
    {
      "epoch": 0.848923294320032,
      "grad_norm": 0.35143613815307617,
      "learning_rate": 1.237839105324129e-05,
      "loss": 0.5397,
      "step": 27635
    },
    {
      "epoch": 0.8489540134549811,
      "grad_norm": 0.3847537636756897,
      "learning_rate": 1.2377921640980432e-05,
      "loss": 0.5129,
      "step": 27636
    },
    {
      "epoch": 0.8489847325899302,
      "grad_norm": 0.36957573890686035,
      "learning_rate": 1.2377452223165775e-05,
      "loss": 0.5632,
      "step": 27637
    },
    {
      "epoch": 0.8490154517248795,
      "grad_norm": 0.522733211517334,
      "learning_rate": 1.2376982799798412e-05,
      "loss": 0.5043,
      "step": 27638
    },
    {
      "epoch": 0.8490461708598286,
      "grad_norm": 0.3464639186859131,
      "learning_rate": 1.2376513370879442e-05,
      "loss": 0.5688,
      "step": 27639
    },
    {
      "epoch": 0.8490768899947777,
      "grad_norm": 0.38365262746810913,
      "learning_rate": 1.2376043936409954e-05,
      "loss": 0.5402,
      "step": 27640
    },
    {
      "epoch": 0.8491076091297269,
      "grad_norm": 0.35751473903656006,
      "learning_rate": 1.2375574496391054e-05,
      "loss": 0.596,
      "step": 27641
    },
    {
      "epoch": 0.8491383282646761,
      "grad_norm": 0.5369989275932312,
      "learning_rate": 1.237510505082383e-05,
      "loss": 0.648,
      "step": 27642
    },
    {
      "epoch": 0.8491690473996252,
      "grad_norm": 0.38200005888938904,
      "learning_rate": 1.2374635599709385e-05,
      "loss": 0.5663,
      "step": 27643
    },
    {
      "epoch": 0.8491997665345744,
      "grad_norm": 0.36229240894317627,
      "learning_rate": 1.2374166143048811e-05,
      "loss": 0.599,
      "step": 27644
    },
    {
      "epoch": 0.8492304856695235,
      "grad_norm": 0.34747445583343506,
      "learning_rate": 1.2373696680843208e-05,
      "loss": 0.5364,
      "step": 27645
    },
    {
      "epoch": 0.8492612048044728,
      "grad_norm": 0.36600613594055176,
      "learning_rate": 1.237322721309367e-05,
      "loss": 0.5333,
      "step": 27646
    },
    {
      "epoch": 0.8492919239394219,
      "grad_norm": 0.371778666973114,
      "learning_rate": 1.2372757739801294e-05,
      "loss": 0.603,
      "step": 27647
    },
    {
      "epoch": 0.849322643074371,
      "grad_norm": 0.3720551133155823,
      "learning_rate": 1.2372288260967176e-05,
      "loss": 0.5352,
      "step": 27648
    },
    {
      "epoch": 0.8493533622093202,
      "grad_norm": 0.34599435329437256,
      "learning_rate": 1.2371818776592412e-05,
      "loss": 0.6118,
      "step": 27649
    },
    {
      "epoch": 0.8493840813442693,
      "grad_norm": 0.3657319247722626,
      "learning_rate": 1.23713492866781e-05,
      "loss": 0.5604,
      "step": 27650
    },
    {
      "epoch": 0.8494148004792185,
      "grad_norm": 0.3356226682662964,
      "learning_rate": 1.2370879791225336e-05,
      "loss": 0.5055,
      "step": 27651
    },
    {
      "epoch": 0.8494455196141677,
      "grad_norm": 0.4043309688568115,
      "learning_rate": 1.237041029023522e-05,
      "loss": 0.5665,
      "step": 27652
    },
    {
      "epoch": 0.8494762387491168,
      "grad_norm": 0.3583422303199768,
      "learning_rate": 1.2369940783708843e-05,
      "loss": 0.5632,
      "step": 27653
    },
    {
      "epoch": 0.8495069578840659,
      "grad_norm": 0.3308202922344208,
      "learning_rate": 1.2369471271647301e-05,
      "loss": 0.5708,
      "step": 27654
    },
    {
      "epoch": 0.8495376770190152,
      "grad_norm": 0.3720800578594208,
      "learning_rate": 1.2369001754051699e-05,
      "loss": 0.5684,
      "step": 27655
    },
    {
      "epoch": 0.8495683961539643,
      "grad_norm": 0.36900806427001953,
      "learning_rate": 1.2368532230923124e-05,
      "loss": 0.5838,
      "step": 27656
    },
    {
      "epoch": 0.8495991152889134,
      "grad_norm": 0.3496271073818207,
      "learning_rate": 1.2368062702262679e-05,
      "loss": 0.4829,
      "step": 27657
    },
    {
      "epoch": 0.8496298344238626,
      "grad_norm": 0.3807847499847412,
      "learning_rate": 1.2367593168071456e-05,
      "loss": 0.5398,
      "step": 27658
    },
    {
      "epoch": 0.8496605535588118,
      "grad_norm": 0.39862456917762756,
      "learning_rate": 1.2367123628350555e-05,
      "loss": 0.6229,
      "step": 27659
    },
    {
      "epoch": 0.849691272693761,
      "grad_norm": 0.40468892455101013,
      "learning_rate": 1.2366654083101071e-05,
      "loss": 0.5431,
      "step": 27660
    },
    {
      "epoch": 0.8497219918287101,
      "grad_norm": 0.35003674030303955,
      "learning_rate": 1.2366184532324102e-05,
      "loss": 0.5963,
      "step": 27661
    },
    {
      "epoch": 0.8497527109636592,
      "grad_norm": 0.36983147263526917,
      "learning_rate": 1.2365714976020741e-05,
      "loss": 0.4921,
      "step": 27662
    },
    {
      "epoch": 0.8497834300986085,
      "grad_norm": 0.4098007380962372,
      "learning_rate": 1.236524541419209e-05,
      "loss": 0.4866,
      "step": 27663
    },
    {
      "epoch": 0.8498141492335576,
      "grad_norm": 0.42959994077682495,
      "learning_rate": 1.2364775846839243e-05,
      "loss": 0.4908,
      "step": 27664
    },
    {
      "epoch": 0.8498448683685067,
      "grad_norm": 0.3514260947704315,
      "learning_rate": 1.2364306273963296e-05,
      "loss": 0.527,
      "step": 27665
    },
    {
      "epoch": 0.8498755875034559,
      "grad_norm": 0.403155118227005,
      "learning_rate": 1.2363836695565347e-05,
      "loss": 0.5841,
      "step": 27666
    },
    {
      "epoch": 0.849906306638405,
      "grad_norm": 0.3411968946456909,
      "learning_rate": 1.2363367111646494e-05,
      "loss": 0.525,
      "step": 27667
    },
    {
      "epoch": 0.8499370257733542,
      "grad_norm": 0.3585547208786011,
      "learning_rate": 1.2362897522207828e-05,
      "loss": 0.4805,
      "step": 27668
    },
    {
      "epoch": 0.8499677449083034,
      "grad_norm": 0.35696566104888916,
      "learning_rate": 1.2362427927250451e-05,
      "loss": 0.5332,
      "step": 27669
    },
    {
      "epoch": 0.8499984640432525,
      "grad_norm": 0.35202375054359436,
      "learning_rate": 1.2361958326775461e-05,
      "loss": 0.536,
      "step": 27670
    },
    {
      "epoch": 0.8500291831782018,
      "grad_norm": 0.378108412027359,
      "learning_rate": 1.2361488720783953e-05,
      "loss": 0.5554,
      "step": 27671
    },
    {
      "epoch": 0.8500599023131509,
      "grad_norm": 0.3698126971721649,
      "learning_rate": 1.236101910927702e-05,
      "loss": 0.5573,
      "step": 27672
    },
    {
      "epoch": 0.8500906214481,
      "grad_norm": 0.3581342101097107,
      "learning_rate": 1.2360549492255764e-05,
      "loss": 0.5007,
      "step": 27673
    },
    {
      "epoch": 0.8501213405830492,
      "grad_norm": 0.34038016200065613,
      "learning_rate": 1.2360079869721278e-05,
      "loss": 0.5157,
      "step": 27674
    },
    {
      "epoch": 0.8501520597179983,
      "grad_norm": 0.34282708168029785,
      "learning_rate": 1.2359610241674663e-05,
      "loss": 0.4759,
      "step": 27675
    },
    {
      "epoch": 0.8501827788529475,
      "grad_norm": 0.3716139495372772,
      "learning_rate": 1.235914060811701e-05,
      "loss": 0.5942,
      "step": 27676
    },
    {
      "epoch": 0.8502134979878967,
      "grad_norm": 0.40348565578460693,
      "learning_rate": 1.2358670969049423e-05,
      "loss": 0.5888,
      "step": 27677
    },
    {
      "epoch": 0.8502442171228458,
      "grad_norm": 0.3560005724430084,
      "learning_rate": 1.2358201324472993e-05,
      "loss": 0.5953,
      "step": 27678
    },
    {
      "epoch": 0.8502749362577949,
      "grad_norm": 0.37286844849586487,
      "learning_rate": 1.235773167438882e-05,
      "loss": 0.4911,
      "step": 27679
    },
    {
      "epoch": 0.8503056553927442,
      "grad_norm": 0.38045474886894226,
      "learning_rate": 1.2357262018798e-05,
      "loss": 0.5369,
      "step": 27680
    },
    {
      "epoch": 0.8503363745276933,
      "grad_norm": 0.3868919610977173,
      "learning_rate": 1.235679235770163e-05,
      "loss": 0.5726,
      "step": 27681
    },
    {
      "epoch": 0.8503670936626425,
      "grad_norm": 0.3813724219799042,
      "learning_rate": 1.2356322691100808e-05,
      "loss": 0.6549,
      "step": 27682
    },
    {
      "epoch": 0.8503978127975916,
      "grad_norm": 0.40410080552101135,
      "learning_rate": 1.2355853018996626e-05,
      "loss": 0.4689,
      "step": 27683
    },
    {
      "epoch": 0.8504285319325408,
      "grad_norm": 0.3851407468318939,
      "learning_rate": 1.235538334139019e-05,
      "loss": 0.5534,
      "step": 27684
    },
    {
      "epoch": 0.85045925106749,
      "grad_norm": 0.373899906873703,
      "learning_rate": 1.2354913658282588e-05,
      "loss": 0.5304,
      "step": 27685
    },
    {
      "epoch": 0.8504899702024391,
      "grad_norm": 0.4116860032081604,
      "learning_rate": 1.2354443969674921e-05,
      "loss": 0.6504,
      "step": 27686
    },
    {
      "epoch": 0.8505206893373882,
      "grad_norm": 0.3494124114513397,
      "learning_rate": 1.2353974275568283e-05,
      "loss": 0.5252,
      "step": 27687
    },
    {
      "epoch": 0.8505514084723375,
      "grad_norm": 0.3701028823852539,
      "learning_rate": 1.235350457596378e-05,
      "loss": 0.607,
      "step": 27688
    },
    {
      "epoch": 0.8505821276072866,
      "grad_norm": 0.38732269406318665,
      "learning_rate": 1.23530348708625e-05,
      "loss": 0.5422,
      "step": 27689
    },
    {
      "epoch": 0.8506128467422357,
      "grad_norm": 0.3389124870300293,
      "learning_rate": 1.2352565160265542e-05,
      "loss": 0.6013,
      "step": 27690
    },
    {
      "epoch": 0.8506435658771849,
      "grad_norm": 0.34501469135284424,
      "learning_rate": 1.2352095444174004e-05,
      "loss": 0.5017,
      "step": 27691
    },
    {
      "epoch": 0.850674285012134,
      "grad_norm": 0.378718763589859,
      "learning_rate": 1.2351625722588983e-05,
      "loss": 0.5618,
      "step": 27692
    },
    {
      "epoch": 0.8507050041470832,
      "grad_norm": 0.38276028633117676,
      "learning_rate": 1.2351155995511577e-05,
      "loss": 0.5108,
      "step": 27693
    },
    {
      "epoch": 0.8507357232820324,
      "grad_norm": 0.3475668132305145,
      "learning_rate": 1.235068626294288e-05,
      "loss": 0.5566,
      "step": 27694
    },
    {
      "epoch": 0.8507664424169815,
      "grad_norm": 0.314266562461853,
      "learning_rate": 1.235021652488399e-05,
      "loss": 0.5815,
      "step": 27695
    },
    {
      "epoch": 0.8507971615519307,
      "grad_norm": 0.34614232182502747,
      "learning_rate": 1.2349746781336007e-05,
      "loss": 0.5314,
      "step": 27696
    },
    {
      "epoch": 0.8508278806868799,
      "grad_norm": 0.36781755089759827,
      "learning_rate": 1.2349277032300027e-05,
      "loss": 0.575,
      "step": 27697
    },
    {
      "epoch": 0.850858599821829,
      "grad_norm": 0.36114880442619324,
      "learning_rate": 1.2348807277777145e-05,
      "loss": 0.5868,
      "step": 27698
    },
    {
      "epoch": 0.8508893189567782,
      "grad_norm": 0.3418674170970917,
      "learning_rate": 1.2348337517768463e-05,
      "loss": 0.5001,
      "step": 27699
    },
    {
      "epoch": 0.8509200380917273,
      "grad_norm": 0.34694817662239075,
      "learning_rate": 1.234786775227507e-05,
      "loss": 0.4948,
      "step": 27700
    },
    {
      "epoch": 0.8509507572266765,
      "grad_norm": 0.3660411238670349,
      "learning_rate": 1.234739798129807e-05,
      "loss": 0.492,
      "step": 27701
    },
    {
      "epoch": 0.8509814763616257,
      "grad_norm": 0.35959649085998535,
      "learning_rate": 1.2346928204838559e-05,
      "loss": 0.6639,
      "step": 27702
    },
    {
      "epoch": 0.8510121954965748,
      "grad_norm": 0.5124613642692566,
      "learning_rate": 1.2346458422897631e-05,
      "loss": 0.5289,
      "step": 27703
    },
    {
      "epoch": 0.8510429146315239,
      "grad_norm": 0.39366415143013,
      "learning_rate": 1.2345988635476386e-05,
      "loss": 0.6025,
      "step": 27704
    },
    {
      "epoch": 0.8510736337664732,
      "grad_norm": 0.3338741958141327,
      "learning_rate": 1.2345518842575922e-05,
      "loss": 0.4333,
      "step": 27705
    },
    {
      "epoch": 0.8511043529014223,
      "grad_norm": 0.39096274971961975,
      "learning_rate": 1.2345049044197334e-05,
      "loss": 0.6094,
      "step": 27706
    },
    {
      "epoch": 0.8511350720363715,
      "grad_norm": 0.36250248551368713,
      "learning_rate": 1.2344579240341722e-05,
      "loss": 0.5184,
      "step": 27707
    },
    {
      "epoch": 0.8511657911713206,
      "grad_norm": 0.4240153133869171,
      "learning_rate": 1.2344109431010178e-05,
      "loss": 0.4464,
      "step": 27708
    },
    {
      "epoch": 0.8511965103062697,
      "grad_norm": 0.425925612449646,
      "learning_rate": 1.2343639616203806e-05,
      "loss": 0.545,
      "step": 27709
    },
    {
      "epoch": 0.851227229441219,
      "grad_norm": 1.0063949823379517,
      "learning_rate": 1.2343169795923697e-05,
      "loss": 0.5552,
      "step": 27710
    },
    {
      "epoch": 0.8512579485761681,
      "grad_norm": 0.34353914856910706,
      "learning_rate": 1.2342699970170955e-05,
      "loss": 0.5417,
      "step": 27711
    },
    {
      "epoch": 0.8512886677111172,
      "grad_norm": 0.34566131234169006,
      "learning_rate": 1.2342230138946672e-05,
      "loss": 0.5062,
      "step": 27712
    },
    {
      "epoch": 0.8513193868460665,
      "grad_norm": 0.4005297124385834,
      "learning_rate": 1.2341760302251947e-05,
      "loss": 0.6388,
      "step": 27713
    },
    {
      "epoch": 0.8513501059810156,
      "grad_norm": 0.357536643743515,
      "learning_rate": 1.2341290460087876e-05,
      "loss": 0.552,
      "step": 27714
    },
    {
      "epoch": 0.8513808251159647,
      "grad_norm": 0.43801993131637573,
      "learning_rate": 1.234082061245556e-05,
      "loss": 0.5338,
      "step": 27715
    },
    {
      "epoch": 0.8514115442509139,
      "grad_norm": 0.36187806725502014,
      "learning_rate": 1.2340350759356092e-05,
      "loss": 0.5242,
      "step": 27716
    },
    {
      "epoch": 0.851442263385863,
      "grad_norm": 0.3771367371082306,
      "learning_rate": 1.2339880900790571e-05,
      "loss": 0.5197,
      "step": 27717
    },
    {
      "epoch": 0.8514729825208122,
      "grad_norm": 0.3532012403011322,
      "learning_rate": 1.2339411036760096e-05,
      "loss": 0.5409,
      "step": 27718
    },
    {
      "epoch": 0.8515037016557614,
      "grad_norm": 0.34963709115982056,
      "learning_rate": 1.2338941167265761e-05,
      "loss": 0.584,
      "step": 27719
    },
    {
      "epoch": 0.8515344207907105,
      "grad_norm": 0.3729380965232849,
      "learning_rate": 1.2338471292308669e-05,
      "loss": 0.4935,
      "step": 27720
    },
    {
      "epoch": 0.8515651399256597,
      "grad_norm": 0.34471115469932556,
      "learning_rate": 1.233800141188991e-05,
      "loss": 0.5074,
      "step": 27721
    },
    {
      "epoch": 0.8515958590606089,
      "grad_norm": 0.360833078622818,
      "learning_rate": 1.233753152601059e-05,
      "loss": 0.5015,
      "step": 27722
    },
    {
      "epoch": 0.851626578195558,
      "grad_norm": 0.37381839752197266,
      "learning_rate": 1.2337061634671798e-05,
      "loss": 0.4978,
      "step": 27723
    },
    {
      "epoch": 0.8516572973305072,
      "grad_norm": 0.34398362040519714,
      "learning_rate": 1.2336591737874637e-05,
      "loss": 0.5329,
      "step": 27724
    },
    {
      "epoch": 0.8516880164654563,
      "grad_norm": 0.3794763684272766,
      "learning_rate": 1.2336121835620203e-05,
      "loss": 0.5148,
      "step": 27725
    },
    {
      "epoch": 0.8517187356004055,
      "grad_norm": 0.3366122543811798,
      "learning_rate": 1.2335651927909592e-05,
      "loss": 0.5405,
      "step": 27726
    },
    {
      "epoch": 0.8517494547353547,
      "grad_norm": 0.36852559447288513,
      "learning_rate": 1.2335182014743905e-05,
      "loss": 0.5925,
      "step": 27727
    },
    {
      "epoch": 0.8517801738703038,
      "grad_norm": 0.386248379945755,
      "learning_rate": 1.2334712096124235e-05,
      "loss": 0.5496,
      "step": 27728
    },
    {
      "epoch": 0.8518108930052529,
      "grad_norm": 0.373401403427124,
      "learning_rate": 1.2334242172051683e-05,
      "loss": 0.5177,
      "step": 27729
    },
    {
      "epoch": 0.8518416121402022,
      "grad_norm": 0.3655671775341034,
      "learning_rate": 1.2333772242527344e-05,
      "loss": 0.5748,
      "step": 27730
    },
    {
      "epoch": 0.8518723312751513,
      "grad_norm": 0.368206262588501,
      "learning_rate": 1.233330230755232e-05,
      "loss": 0.5012,
      "step": 27731
    },
    {
      "epoch": 0.8519030504101005,
      "grad_norm": 0.31548717617988586,
      "learning_rate": 1.2332832367127702e-05,
      "loss": 0.4881,
      "step": 27732
    },
    {
      "epoch": 0.8519337695450496,
      "grad_norm": 0.3904719948768616,
      "learning_rate": 1.2332362421254594e-05,
      "loss": 0.5306,
      "step": 27733
    },
    {
      "epoch": 0.8519644886799987,
      "grad_norm": 0.3459623157978058,
      "learning_rate": 1.233189246993409e-05,
      "loss": 0.5501,
      "step": 27734
    },
    {
      "epoch": 0.851995207814948,
      "grad_norm": 0.7190314531326294,
      "learning_rate": 1.2331422513167288e-05,
      "loss": 0.577,
      "step": 27735
    },
    {
      "epoch": 0.8520259269498971,
      "grad_norm": 0.3783929944038391,
      "learning_rate": 1.2330952550955286e-05,
      "loss": 0.5136,
      "step": 27736
    },
    {
      "epoch": 0.8520566460848462,
      "grad_norm": 0.3707468509674072,
      "learning_rate": 1.2330482583299179e-05,
      "loss": 0.5991,
      "step": 27737
    },
    {
      "epoch": 0.8520873652197954,
      "grad_norm": 0.42767050862312317,
      "learning_rate": 1.233001261020007e-05,
      "loss": 0.55,
      "step": 27738
    },
    {
      "epoch": 0.8521180843547446,
      "grad_norm": 0.36012694239616394,
      "learning_rate": 1.2329542631659053e-05,
      "loss": 0.5503,
      "step": 27739
    },
    {
      "epoch": 0.8521488034896937,
      "grad_norm": 0.3739129900932312,
      "learning_rate": 1.232907264767723e-05,
      "loss": 0.5916,
      "step": 27740
    },
    {
      "epoch": 0.8521795226246429,
      "grad_norm": 0.32727551460266113,
      "learning_rate": 1.2328602658255688e-05,
      "loss": 0.4608,
      "step": 27741
    },
    {
      "epoch": 0.852210241759592,
      "grad_norm": 0.37308982014656067,
      "learning_rate": 1.2328132663395536e-05,
      "loss": 0.6117,
      "step": 27742
    },
    {
      "epoch": 0.8522409608945412,
      "grad_norm": 0.38677358627319336,
      "learning_rate": 1.2327662663097867e-05,
      "loss": 0.4487,
      "step": 27743
    },
    {
      "epoch": 0.8522716800294904,
      "grad_norm": 0.3356735110282898,
      "learning_rate": 1.232719265736378e-05,
      "loss": 0.5458,
      "step": 27744
    },
    {
      "epoch": 0.8523023991644395,
      "grad_norm": 0.344997763633728,
      "learning_rate": 1.2326722646194371e-05,
      "loss": 0.5609,
      "step": 27745
    },
    {
      "epoch": 0.8523331182993887,
      "grad_norm": 0.40413641929626465,
      "learning_rate": 1.2326252629590738e-05,
      "loss": 0.545,
      "step": 27746
    },
    {
      "epoch": 0.8523638374343379,
      "grad_norm": 0.36955761909484863,
      "learning_rate": 1.2325782607553982e-05,
      "loss": 0.5402,
      "step": 27747
    },
    {
      "epoch": 0.852394556569287,
      "grad_norm": 0.37410488724708557,
      "learning_rate": 1.2325312580085198e-05,
      "loss": 0.6137,
      "step": 27748
    },
    {
      "epoch": 0.8524252757042362,
      "grad_norm": 0.33513057231903076,
      "learning_rate": 1.2324842547185482e-05,
      "loss": 0.5609,
      "step": 27749
    },
    {
      "epoch": 0.8524559948391853,
      "grad_norm": 0.3680737614631653,
      "learning_rate": 1.2324372508855934e-05,
      "loss": 0.541,
      "step": 27750
    },
    {
      "epoch": 0.8524867139741344,
      "grad_norm": 0.34349825978279114,
      "learning_rate": 1.2323902465097654e-05,
      "loss": 0.5677,
      "step": 27751
    },
    {
      "epoch": 0.8525174331090837,
      "grad_norm": 0.3588765859603882,
      "learning_rate": 1.2323432415911738e-05,
      "loss": 0.5802,
      "step": 27752
    },
    {
      "epoch": 0.8525481522440328,
      "grad_norm": 0.3366919457912445,
      "learning_rate": 1.232296236129928e-05,
      "loss": 0.5701,
      "step": 27753
    },
    {
      "epoch": 0.8525788713789819,
      "grad_norm": 0.40314435958862305,
      "learning_rate": 1.2322492301261383e-05,
      "loss": 0.6076,
      "step": 27754
    },
    {
      "epoch": 0.8526095905139311,
      "grad_norm": 0.372598797082901,
      "learning_rate": 1.2322022235799143e-05,
      "loss": 0.5555,
      "step": 27755
    },
    {
      "epoch": 0.8526403096488803,
      "grad_norm": 0.34022241830825806,
      "learning_rate": 1.232155216491366e-05,
      "loss": 0.5413,
      "step": 27756
    },
    {
      "epoch": 0.8526710287838295,
      "grad_norm": 0.32416266202926636,
      "learning_rate": 1.2321082088606025e-05,
      "loss": 0.5545,
      "step": 27757
    },
    {
      "epoch": 0.8527017479187786,
      "grad_norm": 0.4185382127761841,
      "learning_rate": 1.2320612006877343e-05,
      "loss": 0.6124,
      "step": 27758
    },
    {
      "epoch": 0.8527324670537277,
      "grad_norm": 0.36082401871681213,
      "learning_rate": 1.232014191972871e-05,
      "loss": 0.5648,
      "step": 27759
    },
    {
      "epoch": 0.852763186188677,
      "grad_norm": 0.3383876383304596,
      "learning_rate": 1.2319671827161221e-05,
      "loss": 0.5654,
      "step": 27760
    },
    {
      "epoch": 0.8527939053236261,
      "grad_norm": 0.4308532476425171,
      "learning_rate": 1.231920172917598e-05,
      "loss": 0.6767,
      "step": 27761
    },
    {
      "epoch": 0.8528246244585752,
      "grad_norm": 0.3607148230075836,
      "learning_rate": 1.2318731625774082e-05,
      "loss": 0.4601,
      "step": 27762
    },
    {
      "epoch": 0.8528553435935244,
      "grad_norm": 0.36847370862960815,
      "learning_rate": 1.2318261516956622e-05,
      "loss": 0.598,
      "step": 27763
    },
    {
      "epoch": 0.8528860627284736,
      "grad_norm": 0.36047089099884033,
      "learning_rate": 1.23177914027247e-05,
      "loss": 0.5176,
      "step": 27764
    },
    {
      "epoch": 0.8529167818634227,
      "grad_norm": 0.39380884170532227,
      "learning_rate": 1.2317321283079416e-05,
      "loss": 0.6192,
      "step": 27765
    },
    {
      "epoch": 0.8529475009983719,
      "grad_norm": 0.3488715589046478,
      "learning_rate": 1.2316851158021863e-05,
      "loss": 0.5345,
      "step": 27766
    },
    {
      "epoch": 0.852978220133321,
      "grad_norm": 0.3662119209766388,
      "learning_rate": 1.2316381027553146e-05,
      "loss": 0.5942,
      "step": 27767
    },
    {
      "epoch": 0.8530089392682703,
      "grad_norm": 0.38663047552108765,
      "learning_rate": 1.231591089167436e-05,
      "loss": 0.5565,
      "step": 27768
    },
    {
      "epoch": 0.8530396584032194,
      "grad_norm": 0.3316810429096222,
      "learning_rate": 1.2315440750386598e-05,
      "loss": 0.4756,
      "step": 27769
    },
    {
      "epoch": 0.8530703775381685,
      "grad_norm": 0.36014866828918457,
      "learning_rate": 1.2314970603690965e-05,
      "loss": 0.5781,
      "step": 27770
    },
    {
      "epoch": 0.8531010966731177,
      "grad_norm": 0.4250815212726593,
      "learning_rate": 1.2314500451588555e-05,
      "loss": 0.5308,
      "step": 27771
    },
    {
      "epoch": 0.8531318158080669,
      "grad_norm": 0.46146920323371887,
      "learning_rate": 1.231403029408047e-05,
      "loss": 0.4949,
      "step": 27772
    },
    {
      "epoch": 0.853162534943016,
      "grad_norm": 0.4032500386238098,
      "learning_rate": 1.2313560131167806e-05,
      "loss": 0.5139,
      "step": 27773
    },
    {
      "epoch": 0.8531932540779652,
      "grad_norm": 0.4079582989215851,
      "learning_rate": 1.2313089962851659e-05,
      "loss": 0.6213,
      "step": 27774
    },
    {
      "epoch": 0.8532239732129143,
      "grad_norm": 0.5043154954910278,
      "learning_rate": 1.2312619789133127e-05,
      "loss": 0.5095,
      "step": 27775
    },
    {
      "epoch": 0.8532546923478634,
      "grad_norm": 0.4260423481464386,
      "learning_rate": 1.2312149610013312e-05,
      "loss": 0.5136,
      "step": 27776
    },
    {
      "epoch": 0.8532854114828127,
      "grad_norm": 0.3751973807811737,
      "learning_rate": 1.231167942549331e-05,
      "loss": 0.5682,
      "step": 27777
    },
    {
      "epoch": 0.8533161306177618,
      "grad_norm": 0.40562862157821655,
      "learning_rate": 1.231120923557422e-05,
      "loss": 0.551,
      "step": 27778
    },
    {
      "epoch": 0.8533468497527109,
      "grad_norm": 0.39072665572166443,
      "learning_rate": 1.2310739040257139e-05,
      "loss": 0.5345,
      "step": 27779
    },
    {
      "epoch": 0.8533775688876601,
      "grad_norm": 0.3881576657295227,
      "learning_rate": 1.2310268839543164e-05,
      "loss": 0.4981,
      "step": 27780
    },
    {
      "epoch": 0.8534082880226093,
      "grad_norm": 0.3784579634666443,
      "learning_rate": 1.2309798633433396e-05,
      "loss": 0.5301,
      "step": 27781
    },
    {
      "epoch": 0.8534390071575585,
      "grad_norm": 0.6237891316413879,
      "learning_rate": 1.2309328421928931e-05,
      "loss": 0.5178,
      "step": 27782
    },
    {
      "epoch": 0.8534697262925076,
      "grad_norm": 0.4022156894207001,
      "learning_rate": 1.2308858205030871e-05,
      "loss": 0.6111,
      "step": 27783
    },
    {
      "epoch": 0.8535004454274567,
      "grad_norm": 0.39802563190460205,
      "learning_rate": 1.2308387982740309e-05,
      "loss": 0.5348,
      "step": 27784
    },
    {
      "epoch": 0.853531164562406,
      "grad_norm": 0.3966676890850067,
      "learning_rate": 1.2307917755058347e-05,
      "loss": 0.5242,
      "step": 27785
    },
    {
      "epoch": 0.8535618836973551,
      "grad_norm": 0.42816200852394104,
      "learning_rate": 1.2307447521986082e-05,
      "loss": 0.5178,
      "step": 27786
    },
    {
      "epoch": 0.8535926028323042,
      "grad_norm": 0.4654396176338196,
      "learning_rate": 1.2306977283524612e-05,
      "loss": 0.5665,
      "step": 27787
    },
    {
      "epoch": 0.8536233219672534,
      "grad_norm": 0.399015873670578,
      "learning_rate": 1.2306507039675036e-05,
      "loss": 0.5136,
      "step": 27788
    },
    {
      "epoch": 0.8536540411022026,
      "grad_norm": 0.37021368741989136,
      "learning_rate": 1.230603679043845e-05,
      "loss": 0.6099,
      "step": 27789
    },
    {
      "epoch": 0.8536847602371517,
      "grad_norm": 0.4140093922615051,
      "learning_rate": 1.2305566535815954e-05,
      "loss": 0.5048,
      "step": 27790
    },
    {
      "epoch": 0.8537154793721009,
      "grad_norm": 0.36630529165267944,
      "learning_rate": 1.2305096275808645e-05,
      "loss": 0.5378,
      "step": 27791
    },
    {
      "epoch": 0.85374619850705,
      "grad_norm": 0.3642320930957794,
      "learning_rate": 1.2304626010417626e-05,
      "loss": 0.5665,
      "step": 27792
    },
    {
      "epoch": 0.8537769176419993,
      "grad_norm": 0.3684598207473755,
      "learning_rate": 1.2304155739643991e-05,
      "loss": 0.485,
      "step": 27793
    },
    {
      "epoch": 0.8538076367769484,
      "grad_norm": 0.3651782274246216,
      "learning_rate": 1.2303685463488839e-05,
      "loss": 0.5298,
      "step": 27794
    },
    {
      "epoch": 0.8538383559118975,
      "grad_norm": 0.42666348814964294,
      "learning_rate": 1.2303215181953267e-05,
      "loss": 0.552,
      "step": 27795
    },
    {
      "epoch": 0.8538690750468467,
      "grad_norm": 0.39943987131118774,
      "learning_rate": 1.2302744895038377e-05,
      "loss": 0.6292,
      "step": 27796
    },
    {
      "epoch": 0.8538997941817958,
      "grad_norm": 0.442704975605011,
      "learning_rate": 1.2302274602745265e-05,
      "loss": 0.5349,
      "step": 27797
    },
    {
      "epoch": 0.853930513316745,
      "grad_norm": 0.37488821148872375,
      "learning_rate": 1.230180430507503e-05,
      "loss": 0.492,
      "step": 27798
    },
    {
      "epoch": 0.8539612324516942,
      "grad_norm": 0.3903057277202606,
      "learning_rate": 1.2301334002028771e-05,
      "loss": 0.5616,
      "step": 27799
    },
    {
      "epoch": 0.8539919515866433,
      "grad_norm": 0.3553638160228729,
      "learning_rate": 1.2300863693607586e-05,
      "loss": 0.5172,
      "step": 27800
    },
    {
      "epoch": 0.8540226707215924,
      "grad_norm": 0.33283498883247375,
      "learning_rate": 1.2300393379812571e-05,
      "loss": 0.5435,
      "step": 27801
    },
    {
      "epoch": 0.8540533898565417,
      "grad_norm": 0.4019143283367157,
      "learning_rate": 1.2299923060644827e-05,
      "loss": 0.6189,
      "step": 27802
    },
    {
      "epoch": 0.8540841089914908,
      "grad_norm": 0.37968674302101135,
      "learning_rate": 1.2299452736105455e-05,
      "loss": 0.5634,
      "step": 27803
    },
    {
      "epoch": 0.8541148281264399,
      "grad_norm": 0.388873815536499,
      "learning_rate": 1.229898240619555e-05,
      "loss": 0.493,
      "step": 27804
    },
    {
      "epoch": 0.8541455472613891,
      "grad_norm": 0.3610157072544098,
      "learning_rate": 1.229851207091621e-05,
      "loss": 0.6035,
      "step": 27805
    },
    {
      "epoch": 0.8541762663963383,
      "grad_norm": 0.345295786857605,
      "learning_rate": 1.2298041730268533e-05,
      "loss": 0.5426,
      "step": 27806
    },
    {
      "epoch": 0.8542069855312875,
      "grad_norm": 0.3503148555755615,
      "learning_rate": 1.229757138425362e-05,
      "loss": 0.5854,
      "step": 27807
    },
    {
      "epoch": 0.8542377046662366,
      "grad_norm": 0.36464110016822815,
      "learning_rate": 1.229710103287257e-05,
      "loss": 0.5208,
      "step": 27808
    },
    {
      "epoch": 0.8542684238011857,
      "grad_norm": 0.4120032787322998,
      "learning_rate": 1.2296630676126478e-05,
      "loss": 0.5718,
      "step": 27809
    },
    {
      "epoch": 0.854299142936135,
      "grad_norm": 0.3595506250858307,
      "learning_rate": 1.2296160314016445e-05,
      "loss": 0.5601,
      "step": 27810
    },
    {
      "epoch": 0.8543298620710841,
      "grad_norm": 0.36997929215431213,
      "learning_rate": 1.2295689946543567e-05,
      "loss": 0.4692,
      "step": 27811
    },
    {
      "epoch": 0.8543605812060332,
      "grad_norm": 0.39327314496040344,
      "learning_rate": 1.229521957370895e-05,
      "loss": 0.5105,
      "step": 27812
    },
    {
      "epoch": 0.8543913003409824,
      "grad_norm": 0.4274047315120697,
      "learning_rate": 1.2294749195513685e-05,
      "loss": 0.5957,
      "step": 27813
    },
    {
      "epoch": 0.8544220194759315,
      "grad_norm": 0.3482913076877594,
      "learning_rate": 1.2294278811958871e-05,
      "loss": 0.5767,
      "step": 27814
    },
    {
      "epoch": 0.8544527386108807,
      "grad_norm": 0.43638572096824646,
      "learning_rate": 1.2293808423045612e-05,
      "loss": 0.5512,
      "step": 27815
    },
    {
      "epoch": 0.8544834577458299,
      "grad_norm": 0.32190075516700745,
      "learning_rate": 1.2293338028774999e-05,
      "loss": 0.4885,
      "step": 27816
    },
    {
      "epoch": 0.854514176880779,
      "grad_norm": 0.35543328523635864,
      "learning_rate": 1.229286762914814e-05,
      "loss": 0.4968,
      "step": 27817
    },
    {
      "epoch": 0.8545448960157283,
      "grad_norm": 0.3791341185569763,
      "learning_rate": 1.2292397224166124e-05,
      "loss": 0.5649,
      "step": 27818
    },
    {
      "epoch": 0.8545756151506774,
      "grad_norm": 0.3394736349582672,
      "learning_rate": 1.2291926813830058e-05,
      "loss": 0.5504,
      "step": 27819
    },
    {
      "epoch": 0.8546063342856265,
      "grad_norm": 0.3511335849761963,
      "learning_rate": 1.2291456398141036e-05,
      "loss": 0.5212,
      "step": 27820
    },
    {
      "epoch": 0.8546370534205757,
      "grad_norm": 0.372125506401062,
      "learning_rate": 1.2290985977100156e-05,
      "loss": 0.579,
      "step": 27821
    },
    {
      "epoch": 0.8546677725555248,
      "grad_norm": 0.3706806004047394,
      "learning_rate": 1.229051555070852e-05,
      "loss": 0.5377,
      "step": 27822
    },
    {
      "epoch": 0.854698491690474,
      "grad_norm": 0.404598206281662,
      "learning_rate": 1.2290045118967221e-05,
      "loss": 0.5706,
      "step": 27823
    },
    {
      "epoch": 0.8547292108254232,
      "grad_norm": 0.3375270664691925,
      "learning_rate": 1.2289574681877368e-05,
      "loss": 0.4948,
      "step": 27824
    },
    {
      "epoch": 0.8547599299603723,
      "grad_norm": 0.39136001467704773,
      "learning_rate": 1.2289104239440048e-05,
      "loss": 0.5936,
      "step": 27825
    },
    {
      "epoch": 0.8547906490953214,
      "grad_norm": 0.3466721475124359,
      "learning_rate": 1.2288633791656367e-05,
      "loss": 0.5055,
      "step": 27826
    },
    {
      "epoch": 0.8548213682302707,
      "grad_norm": 0.35018718242645264,
      "learning_rate": 1.2288163338527421e-05,
      "loss": 0.5322,
      "step": 27827
    },
    {
      "epoch": 0.8548520873652198,
      "grad_norm": 0.3432736098766327,
      "learning_rate": 1.2287692880054314e-05,
      "loss": 0.6055,
      "step": 27828
    },
    {
      "epoch": 0.8548828065001689,
      "grad_norm": 0.3957948684692383,
      "learning_rate": 1.2287222416238136e-05,
      "loss": 0.5149,
      "step": 27829
    },
    {
      "epoch": 0.8549135256351181,
      "grad_norm": 0.3605062961578369,
      "learning_rate": 1.2286751947079991e-05,
      "loss": 0.5113,
      "step": 27830
    },
    {
      "epoch": 0.8549442447700673,
      "grad_norm": 0.3949517011642456,
      "learning_rate": 1.2286281472580978e-05,
      "loss": 0.5691,
      "step": 27831
    },
    {
      "epoch": 0.8549749639050165,
      "grad_norm": 0.33140885829925537,
      "learning_rate": 1.2285810992742193e-05,
      "loss": 0.5169,
      "step": 27832
    },
    {
      "epoch": 0.8550056830399656,
      "grad_norm": 0.3551516532897949,
      "learning_rate": 1.2285340507564741e-05,
      "loss": 0.5147,
      "step": 27833
    },
    {
      "epoch": 0.8550364021749147,
      "grad_norm": 0.3956296443939209,
      "learning_rate": 1.2284870017049712e-05,
      "loss": 0.5483,
      "step": 27834
    },
    {
      "epoch": 0.855067121309864,
      "grad_norm": 0.3451474606990814,
      "learning_rate": 1.2284399521198212e-05,
      "loss": 0.5479,
      "step": 27835
    },
    {
      "epoch": 0.8550978404448131,
      "grad_norm": 0.346734881401062,
      "learning_rate": 1.2283929020011337e-05,
      "loss": 0.578,
      "step": 27836
    },
    {
      "epoch": 0.8551285595797622,
      "grad_norm": 0.36936208605766296,
      "learning_rate": 1.2283458513490187e-05,
      "loss": 0.5796,
      "step": 27837
    },
    {
      "epoch": 0.8551592787147114,
      "grad_norm": 0.3712770640850067,
      "learning_rate": 1.228298800163586e-05,
      "loss": 0.4932,
      "step": 27838
    },
    {
      "epoch": 0.8551899978496605,
      "grad_norm": 0.36375266313552856,
      "learning_rate": 1.2282517484449455e-05,
      "loss": 0.6329,
      "step": 27839
    },
    {
      "epoch": 0.8552207169846097,
      "grad_norm": 0.34024080634117126,
      "learning_rate": 1.228204696193207e-05,
      "loss": 0.4901,
      "step": 27840
    },
    {
      "epoch": 0.8552514361195589,
      "grad_norm": 0.41130444407463074,
      "learning_rate": 1.2281576434084806e-05,
      "loss": 0.5344,
      "step": 27841
    },
    {
      "epoch": 0.855282155254508,
      "grad_norm": 0.3750464916229248,
      "learning_rate": 1.2281105900908761e-05,
      "loss": 0.5607,
      "step": 27842
    },
    {
      "epoch": 0.8553128743894572,
      "grad_norm": 0.3560344874858856,
      "learning_rate": 1.2280635362405032e-05,
      "loss": 0.5335,
      "step": 27843
    },
    {
      "epoch": 0.8553435935244064,
      "grad_norm": 0.3350215554237366,
      "learning_rate": 1.2280164818574722e-05,
      "loss": 0.5569,
      "step": 27844
    },
    {
      "epoch": 0.8553743126593555,
      "grad_norm": 0.3714674115180969,
      "learning_rate": 1.2279694269418924e-05,
      "loss": 0.5271,
      "step": 27845
    },
    {
      "epoch": 0.8554050317943047,
      "grad_norm": 0.44601598381996155,
      "learning_rate": 1.2279223714938746e-05,
      "loss": 0.5395,
      "step": 27846
    },
    {
      "epoch": 0.8554357509292538,
      "grad_norm": 0.3672606647014618,
      "learning_rate": 1.2278753155135278e-05,
      "loss": 0.5501,
      "step": 27847
    },
    {
      "epoch": 0.855466470064203,
      "grad_norm": 0.341852605342865,
      "learning_rate": 1.2278282590009627e-05,
      "loss": 0.6347,
      "step": 27848
    },
    {
      "epoch": 0.8554971891991522,
      "grad_norm": 0.35295847058296204,
      "learning_rate": 1.2277812019562884e-05,
      "loss": 0.5372,
      "step": 27849
    },
    {
      "epoch": 0.8555279083341013,
      "grad_norm": 0.37700098752975464,
      "learning_rate": 1.227734144379615e-05,
      "loss": 0.5241,
      "step": 27850
    },
    {
      "epoch": 0.8555586274690504,
      "grad_norm": 0.34076255559921265,
      "learning_rate": 1.2276870862710533e-05,
      "loss": 0.5105,
      "step": 27851
    },
    {
      "epoch": 0.8555893466039997,
      "grad_norm": 0.3701516091823578,
      "learning_rate": 1.227640027630712e-05,
      "loss": 0.5092,
      "step": 27852
    },
    {
      "epoch": 0.8556200657389488,
      "grad_norm": 0.3716222643852234,
      "learning_rate": 1.2275929684587019e-05,
      "loss": 0.5559,
      "step": 27853
    },
    {
      "epoch": 0.8556507848738979,
      "grad_norm": 0.32700347900390625,
      "learning_rate": 1.227545908755132e-05,
      "loss": 0.5209,
      "step": 27854
    },
    {
      "epoch": 0.8556815040088471,
      "grad_norm": 0.3878425061702728,
      "learning_rate": 1.2274988485201132e-05,
      "loss": 0.5729,
      "step": 27855
    },
    {
      "epoch": 0.8557122231437962,
      "grad_norm": 0.4009822905063629,
      "learning_rate": 1.2274517877537549e-05,
      "loss": 0.5058,
      "step": 27856
    },
    {
      "epoch": 0.8557429422787455,
      "grad_norm": 0.3958221971988678,
      "learning_rate": 1.2274047264561666e-05,
      "loss": 0.5365,
      "step": 27857
    },
    {
      "epoch": 0.8557736614136946,
      "grad_norm": 0.33384448289871216,
      "learning_rate": 1.2273576646274592e-05,
      "loss": 0.507,
      "step": 27858
    },
    {
      "epoch": 0.8558043805486437,
      "grad_norm": 0.5830596685409546,
      "learning_rate": 1.2273106022677417e-05,
      "loss": 0.5061,
      "step": 27859
    },
    {
      "epoch": 0.855835099683593,
      "grad_norm": 0.36213529109954834,
      "learning_rate": 1.2272635393771249e-05,
      "loss": 0.5408,
      "step": 27860
    },
    {
      "epoch": 0.8558658188185421,
      "grad_norm": 0.37394943833351135,
      "learning_rate": 1.2272164759557177e-05,
      "loss": 0.4831,
      "step": 27861
    },
    {
      "epoch": 0.8558965379534912,
      "grad_norm": 0.3218478262424469,
      "learning_rate": 1.227169412003631e-05,
      "loss": 0.4135,
      "step": 27862
    },
    {
      "epoch": 0.8559272570884404,
      "grad_norm": 0.34499725699424744,
      "learning_rate": 1.2271223475209739e-05,
      "loss": 0.6461,
      "step": 27863
    },
    {
      "epoch": 0.8559579762233895,
      "grad_norm": 0.3890269994735718,
      "learning_rate": 1.2270752825078571e-05,
      "loss": 0.5507,
      "step": 27864
    },
    {
      "epoch": 0.8559886953583387,
      "grad_norm": 0.4235478937625885,
      "learning_rate": 1.2270282169643897e-05,
      "loss": 0.5173,
      "step": 27865
    },
    {
      "epoch": 0.8560194144932879,
      "grad_norm": 0.37710338830947876,
      "learning_rate": 1.2269811508906823e-05,
      "loss": 0.5996,
      "step": 27866
    },
    {
      "epoch": 0.856050133628237,
      "grad_norm": 0.3799552321434021,
      "learning_rate": 1.2269340842868446e-05,
      "loss": 0.5656,
      "step": 27867
    },
    {
      "epoch": 0.8560808527631862,
      "grad_norm": 0.3807094693183899,
      "learning_rate": 1.2268870171529864e-05,
      "loss": 0.5656,
      "step": 27868
    },
    {
      "epoch": 0.8561115718981354,
      "grad_norm": 0.36839520931243896,
      "learning_rate": 1.2268399494892176e-05,
      "loss": 0.5281,
      "step": 27869
    },
    {
      "epoch": 0.8561422910330845,
      "grad_norm": 0.5964272618293762,
      "learning_rate": 1.2267928812956483e-05,
      "loss": 0.5519,
      "step": 27870
    },
    {
      "epoch": 0.8561730101680337,
      "grad_norm": 0.3601151406764984,
      "learning_rate": 1.2267458125723885e-05,
      "loss": 0.5134,
      "step": 27871
    },
    {
      "epoch": 0.8562037293029828,
      "grad_norm": 0.3634551167488098,
      "learning_rate": 1.2266987433195481e-05,
      "loss": 0.5755,
      "step": 27872
    },
    {
      "epoch": 0.856234448437932,
      "grad_norm": 0.3347277343273163,
      "learning_rate": 1.2266516735372367e-05,
      "loss": 0.4538,
      "step": 27873
    },
    {
      "epoch": 0.8562651675728812,
      "grad_norm": 0.348099946975708,
      "learning_rate": 1.2266046032255648e-05,
      "loss": 0.5283,
      "step": 27874
    },
    {
      "epoch": 0.8562958867078303,
      "grad_norm": 0.3729408085346222,
      "learning_rate": 1.2265575323846417e-05,
      "loss": 0.5531,
      "step": 27875
    },
    {
      "epoch": 0.8563266058427794,
      "grad_norm": 0.3797382116317749,
      "learning_rate": 1.2265104610145779e-05,
      "loss": 0.601,
      "step": 27876
    },
    {
      "epoch": 0.8563573249777287,
      "grad_norm": 0.3526412844657898,
      "learning_rate": 1.2264633891154829e-05,
      "loss": 0.5156,
      "step": 27877
    },
    {
      "epoch": 0.8563880441126778,
      "grad_norm": 0.3546144366264343,
      "learning_rate": 1.2264163166874671e-05,
      "loss": 0.5451,
      "step": 27878
    },
    {
      "epoch": 0.856418763247627,
      "grad_norm": 0.5102583765983582,
      "learning_rate": 1.2263692437306401e-05,
      "loss": 0.5301,
      "step": 27879
    },
    {
      "epoch": 0.8564494823825761,
      "grad_norm": 0.3690704107284546,
      "learning_rate": 1.2263221702451119e-05,
      "loss": 0.6893,
      "step": 27880
    },
    {
      "epoch": 0.8564802015175252,
      "grad_norm": 0.403723806142807,
      "learning_rate": 1.2262750962309924e-05,
      "loss": 0.5576,
      "step": 27881
    },
    {
      "epoch": 0.8565109206524745,
      "grad_norm": 0.3293156623840332,
      "learning_rate": 1.2262280216883916e-05,
      "loss": 0.5383,
      "step": 27882
    },
    {
      "epoch": 0.8565416397874236,
      "grad_norm": 0.34353455901145935,
      "learning_rate": 1.2261809466174194e-05,
      "loss": 0.6149,
      "step": 27883
    },
    {
      "epoch": 0.8565723589223727,
      "grad_norm": 0.47761696577072144,
      "learning_rate": 1.226133871018186e-05,
      "loss": 0.5723,
      "step": 27884
    },
    {
      "epoch": 0.8566030780573219,
      "grad_norm": 0.3396124541759491,
      "learning_rate": 1.226086794890801e-05,
      "loss": 0.5305,
      "step": 27885
    },
    {
      "epoch": 0.8566337971922711,
      "grad_norm": 0.3618820011615753,
      "learning_rate": 1.2260397182353744e-05,
      "loss": 0.5342,
      "step": 27886
    },
    {
      "epoch": 0.8566645163272202,
      "grad_norm": 0.38744086027145386,
      "learning_rate": 1.2259926410520165e-05,
      "loss": 0.5058,
      "step": 27887
    },
    {
      "epoch": 0.8566952354621694,
      "grad_norm": 0.39134925603866577,
      "learning_rate": 1.2259455633408369e-05,
      "loss": 0.6257,
      "step": 27888
    },
    {
      "epoch": 0.8567259545971185,
      "grad_norm": 0.32813358306884766,
      "learning_rate": 1.2258984851019456e-05,
      "loss": 0.5447,
      "step": 27889
    },
    {
      "epoch": 0.8567566737320677,
      "grad_norm": 0.3744778037071228,
      "learning_rate": 1.2258514063354527e-05,
      "loss": 0.6544,
      "step": 27890
    },
    {
      "epoch": 0.8567873928670169,
      "grad_norm": 0.35688358545303345,
      "learning_rate": 1.2258043270414678e-05,
      "loss": 0.5318,
      "step": 27891
    },
    {
      "epoch": 0.856818112001966,
      "grad_norm": 0.32990866899490356,
      "learning_rate": 1.2257572472201016e-05,
      "loss": 0.498,
      "step": 27892
    },
    {
      "epoch": 0.8568488311369152,
      "grad_norm": 0.3887975215911865,
      "learning_rate": 1.2257101668714632e-05,
      "loss": 0.5348,
      "step": 27893
    },
    {
      "epoch": 0.8568795502718644,
      "grad_norm": 0.38444772362709045,
      "learning_rate": 1.2256630859956633e-05,
      "loss": 0.5978,
      "step": 27894
    },
    {
      "epoch": 0.8569102694068135,
      "grad_norm": 0.3942812383174896,
      "learning_rate": 1.2256160045928112e-05,
      "loss": 0.5806,
      "step": 27895
    },
    {
      "epoch": 0.8569409885417627,
      "grad_norm": 0.34272146224975586,
      "learning_rate": 1.2255689226630172e-05,
      "loss": 0.4926,
      "step": 27896
    },
    {
      "epoch": 0.8569717076767118,
      "grad_norm": 0.3873318135738373,
      "learning_rate": 1.2255218402063912e-05,
      "loss": 0.5142,
      "step": 27897
    },
    {
      "epoch": 0.857002426811661,
      "grad_norm": 0.40973109006881714,
      "learning_rate": 1.2254747572230434e-05,
      "loss": 0.5845,
      "step": 27898
    },
    {
      "epoch": 0.8570331459466102,
      "grad_norm": 0.40104782581329346,
      "learning_rate": 1.2254276737130832e-05,
      "loss": 0.5243,
      "step": 27899
    },
    {
      "epoch": 0.8570638650815593,
      "grad_norm": 0.35483506321907043,
      "learning_rate": 1.2253805896766214e-05,
      "loss": 0.5798,
      "step": 27900
    },
    {
      "epoch": 0.8570945842165084,
      "grad_norm": 0.4269712567329407,
      "learning_rate": 1.2253335051137674e-05,
      "loss": 0.6137,
      "step": 27901
    },
    {
      "epoch": 0.8571253033514576,
      "grad_norm": 0.3881089687347412,
      "learning_rate": 1.2252864200246308e-05,
      "loss": 0.5414,
      "step": 27902
    },
    {
      "epoch": 0.8571560224864068,
      "grad_norm": 0.393797904253006,
      "learning_rate": 1.2252393344093225e-05,
      "loss": 0.5811,
      "step": 27903
    },
    {
      "epoch": 0.857186741621356,
      "grad_norm": 0.38085031509399414,
      "learning_rate": 1.225192248267952e-05,
      "loss": 0.5437,
      "step": 27904
    },
    {
      "epoch": 0.8572174607563051,
      "grad_norm": 0.4187985360622406,
      "learning_rate": 1.2251451616006289e-05,
      "loss": 0.4604,
      "step": 27905
    },
    {
      "epoch": 0.8572481798912542,
      "grad_norm": 0.412358820438385,
      "learning_rate": 1.2250980744074636e-05,
      "loss": 0.4973,
      "step": 27906
    },
    {
      "epoch": 0.8572788990262035,
      "grad_norm": 0.404795378446579,
      "learning_rate": 1.2250509866885662e-05,
      "loss": 0.4827,
      "step": 27907
    },
    {
      "epoch": 0.8573096181611526,
      "grad_norm": 0.34944605827331543,
      "learning_rate": 1.2250038984440467e-05,
      "loss": 0.5181,
      "step": 27908
    },
    {
      "epoch": 0.8573403372961017,
      "grad_norm": 0.33997491002082825,
      "learning_rate": 1.2249568096740146e-05,
      "loss": 0.5385,
      "step": 27909
    },
    {
      "epoch": 0.8573710564310509,
      "grad_norm": 0.33933472633361816,
      "learning_rate": 1.2249097203785803e-05,
      "loss": 0.5962,
      "step": 27910
    },
    {
      "epoch": 0.8574017755660001,
      "grad_norm": 0.32410404086112976,
      "learning_rate": 1.2248626305578534e-05,
      "loss": 0.5404,
      "step": 27911
    },
    {
      "epoch": 0.8574324947009492,
      "grad_norm": 0.32519298791885376,
      "learning_rate": 1.2248155402119443e-05,
      "loss": 0.4691,
      "step": 27912
    },
    {
      "epoch": 0.8574632138358984,
      "grad_norm": 0.3327036499977112,
      "learning_rate": 1.2247684493409629e-05,
      "loss": 0.494,
      "step": 27913
    },
    {
      "epoch": 0.8574939329708475,
      "grad_norm": 0.37759509682655334,
      "learning_rate": 1.224721357945019e-05,
      "loss": 0.5363,
      "step": 27914
    },
    {
      "epoch": 0.8575246521057966,
      "grad_norm": 0.41273561120033264,
      "learning_rate": 1.2246742660242225e-05,
      "loss": 0.4648,
      "step": 27915
    },
    {
      "epoch": 0.8575553712407459,
      "grad_norm": 0.3620213568210602,
      "learning_rate": 1.2246271735786839e-05,
      "loss": 0.5126,
      "step": 27916
    },
    {
      "epoch": 0.857586090375695,
      "grad_norm": 0.35247454047203064,
      "learning_rate": 1.2245800806085127e-05,
      "loss": 0.5585,
      "step": 27917
    },
    {
      "epoch": 0.8576168095106442,
      "grad_norm": 0.3273746073246002,
      "learning_rate": 1.2245329871138189e-05,
      "loss": 0.4977,
      "step": 27918
    },
    {
      "epoch": 0.8576475286455933,
      "grad_norm": 0.35373029112815857,
      "learning_rate": 1.224485893094713e-05,
      "loss": 0.6133,
      "step": 27919
    },
    {
      "epoch": 0.8576782477805425,
      "grad_norm": 0.41784608364105225,
      "learning_rate": 1.2244387985513043e-05,
      "loss": 0.5616,
      "step": 27920
    },
    {
      "epoch": 0.8577089669154917,
      "grad_norm": 0.3863956034183502,
      "learning_rate": 1.2243917034837032e-05,
      "loss": 0.5243,
      "step": 27921
    },
    {
      "epoch": 0.8577396860504408,
      "grad_norm": 0.34137463569641113,
      "learning_rate": 1.2243446078920194e-05,
      "loss": 0.5675,
      "step": 27922
    },
    {
      "epoch": 0.8577704051853899,
      "grad_norm": 0.3958633542060852,
      "learning_rate": 1.2242975117763632e-05,
      "loss": 0.6099,
      "step": 27923
    },
    {
      "epoch": 0.8578011243203392,
      "grad_norm": 0.3947158753871918,
      "learning_rate": 1.2242504151368446e-05,
      "loss": 0.6171,
      "step": 27924
    },
    {
      "epoch": 0.8578318434552883,
      "grad_norm": 0.39517998695373535,
      "learning_rate": 1.2242033179735735e-05,
      "loss": 0.5642,
      "step": 27925
    },
    {
      "epoch": 0.8578625625902374,
      "grad_norm": 0.3649339973926544,
      "learning_rate": 1.2241562202866599e-05,
      "loss": 0.5556,
      "step": 27926
    },
    {
      "epoch": 0.8578932817251866,
      "grad_norm": 0.451049268245697,
      "learning_rate": 1.2241091220762139e-05,
      "loss": 0.6157,
      "step": 27927
    },
    {
      "epoch": 0.8579240008601358,
      "grad_norm": 0.38279497623443604,
      "learning_rate": 1.2240620233423453e-05,
      "loss": 0.4818,
      "step": 27928
    },
    {
      "epoch": 0.857954719995085,
      "grad_norm": 0.38797488808631897,
      "learning_rate": 1.224014924085164e-05,
      "loss": 0.5686,
      "step": 27929
    },
    {
      "epoch": 0.8579854391300341,
      "grad_norm": 0.33632248640060425,
      "learning_rate": 1.2239678243047804e-05,
      "loss": 0.5562,
      "step": 27930
    },
    {
      "epoch": 0.8580161582649832,
      "grad_norm": 0.34845733642578125,
      "learning_rate": 1.223920724001304e-05,
      "loss": 0.6635,
      "step": 27931
    },
    {
      "epoch": 0.8580468773999325,
      "grad_norm": 0.3959728479385376,
      "learning_rate": 1.2238736231748455e-05,
      "loss": 0.5471,
      "step": 27932
    },
    {
      "epoch": 0.8580775965348816,
      "grad_norm": 0.413150817155838,
      "learning_rate": 1.2238265218255142e-05,
      "loss": 0.573,
      "step": 27933
    },
    {
      "epoch": 0.8581083156698307,
      "grad_norm": 0.35602498054504395,
      "learning_rate": 1.2237794199534208e-05,
      "loss": 0.5961,
      "step": 27934
    },
    {
      "epoch": 0.8581390348047799,
      "grad_norm": 0.39103561639785767,
      "learning_rate": 1.2237323175586749e-05,
      "loss": 0.4826,
      "step": 27935
    },
    {
      "epoch": 0.858169753939729,
      "grad_norm": 0.36219123005867004,
      "learning_rate": 1.2236852146413862e-05,
      "loss": 0.5934,
      "step": 27936
    },
    {
      "epoch": 0.8582004730746782,
      "grad_norm": 0.39069902896881104,
      "learning_rate": 1.2236381112016653e-05,
      "loss": 0.4924,
      "step": 27937
    },
    {
      "epoch": 0.8582311922096274,
      "grad_norm": 0.39814186096191406,
      "learning_rate": 1.223591007239622e-05,
      "loss": 0.5667,
      "step": 27938
    },
    {
      "epoch": 0.8582619113445765,
      "grad_norm": 0.3504239022731781,
      "learning_rate": 1.2235439027553661e-05,
      "loss": 0.5937,
      "step": 27939
    },
    {
      "epoch": 0.8582926304795256,
      "grad_norm": 0.7812365293502808,
      "learning_rate": 1.223496797749008e-05,
      "loss": 0.4471,
      "step": 27940
    },
    {
      "epoch": 0.8583233496144749,
      "grad_norm": 0.36257025599479675,
      "learning_rate": 1.2234496922206573e-05,
      "loss": 0.5999,
      "step": 27941
    },
    {
      "epoch": 0.858354068749424,
      "grad_norm": 0.372210294008255,
      "learning_rate": 1.2234025861704244e-05,
      "loss": 0.564,
      "step": 27942
    },
    {
      "epoch": 0.8583847878843732,
      "grad_norm": 0.442782461643219,
      "learning_rate": 1.2233554795984191e-05,
      "loss": 0.5115,
      "step": 27943
    },
    {
      "epoch": 0.8584155070193223,
      "grad_norm": 0.4189632833003998,
      "learning_rate": 1.2233083725047514e-05,
      "loss": 0.5374,
      "step": 27944
    },
    {
      "epoch": 0.8584462261542715,
      "grad_norm": 0.3877957761287689,
      "learning_rate": 1.2232612648895315e-05,
      "loss": 0.5462,
      "step": 27945
    },
    {
      "epoch": 0.8584769452892207,
      "grad_norm": 0.3999117612838745,
      "learning_rate": 1.2232141567528695e-05,
      "loss": 0.5661,
      "step": 27946
    },
    {
      "epoch": 0.8585076644241698,
      "grad_norm": 0.35847410559654236,
      "learning_rate": 1.223167048094875e-05,
      "loss": 0.53,
      "step": 27947
    },
    {
      "epoch": 0.8585383835591189,
      "grad_norm": 0.3902151584625244,
      "learning_rate": 1.2231199389156583e-05,
      "loss": 0.5019,
      "step": 27948
    },
    {
      "epoch": 0.8585691026940682,
      "grad_norm": 0.3498285710811615,
      "learning_rate": 1.2230728292153293e-05,
      "loss": 0.5351,
      "step": 27949
    },
    {
      "epoch": 0.8585998218290173,
      "grad_norm": 0.3648121654987335,
      "learning_rate": 1.2230257189939984e-05,
      "loss": 0.5943,
      "step": 27950
    },
    {
      "epoch": 0.8586305409639664,
      "grad_norm": 0.4056466519832611,
      "learning_rate": 1.2229786082517751e-05,
      "loss": 0.5972,
      "step": 27951
    },
    {
      "epoch": 0.8586612600989156,
      "grad_norm": 0.41696879267692566,
      "learning_rate": 1.22293149698877e-05,
      "loss": 0.5354,
      "step": 27952
    },
    {
      "epoch": 0.8586919792338648,
      "grad_norm": 0.3761141896247864,
      "learning_rate": 1.222884385205093e-05,
      "loss": 0.6291,
      "step": 27953
    },
    {
      "epoch": 0.858722698368814,
      "grad_norm": 0.3443341553211212,
      "learning_rate": 1.2228372729008533e-05,
      "loss": 0.5483,
      "step": 27954
    },
    {
      "epoch": 0.8587534175037631,
      "grad_norm": 0.4087982475757599,
      "learning_rate": 1.222790160076162e-05,
      "loss": 0.7017,
      "step": 27955
    },
    {
      "epoch": 0.8587841366387122,
      "grad_norm": 0.3447273075580597,
      "learning_rate": 1.2227430467311285e-05,
      "loss": 0.5573,
      "step": 27956
    },
    {
      "epoch": 0.8588148557736615,
      "grad_norm": 0.36068195104599,
      "learning_rate": 1.2226959328658632e-05,
      "loss": 0.5267,
      "step": 27957
    },
    {
      "epoch": 0.8588455749086106,
      "grad_norm": 0.3581807315349579,
      "learning_rate": 1.2226488184804758e-05,
      "loss": 0.5032,
      "step": 27958
    },
    {
      "epoch": 0.8588762940435597,
      "grad_norm": 0.3625902831554413,
      "learning_rate": 1.2226017035750768e-05,
      "loss": 0.6677,
      "step": 27959
    },
    {
      "epoch": 0.8589070131785089,
      "grad_norm": 0.37308594584465027,
      "learning_rate": 1.2225545881497757e-05,
      "loss": 0.496,
      "step": 27960
    },
    {
      "epoch": 0.858937732313458,
      "grad_norm": 0.36009013652801514,
      "learning_rate": 1.222507472204683e-05,
      "loss": 0.5815,
      "step": 27961
    },
    {
      "epoch": 0.8589684514484072,
      "grad_norm": 0.35388270020484924,
      "learning_rate": 1.2224603557399085e-05,
      "loss": 0.5845,
      "step": 27962
    },
    {
      "epoch": 0.8589991705833564,
      "grad_norm": 0.37619394063949585,
      "learning_rate": 1.2224132387555623e-05,
      "loss": 0.4899,
      "step": 27963
    },
    {
      "epoch": 0.8590298897183055,
      "grad_norm": 0.36960557103157043,
      "learning_rate": 1.2223661212517545e-05,
      "loss": 0.5469,
      "step": 27964
    },
    {
      "epoch": 0.8590606088532546,
      "grad_norm": 0.36737051606178284,
      "learning_rate": 1.2223190032285953e-05,
      "loss": 0.511,
      "step": 27965
    },
    {
      "epoch": 0.8590913279882039,
      "grad_norm": 0.3796035945415497,
      "learning_rate": 1.2222718846861943e-05,
      "loss": 0.59,
      "step": 27966
    },
    {
      "epoch": 0.859122047123153,
      "grad_norm": 0.4013253152370453,
      "learning_rate": 1.2222247656246618e-05,
      "loss": 0.58,
      "step": 27967
    },
    {
      "epoch": 0.8591527662581022,
      "grad_norm": 0.41957637667655945,
      "learning_rate": 1.2221776460441079e-05,
      "loss": 0.5213,
      "step": 27968
    },
    {
      "epoch": 0.8591834853930513,
      "grad_norm": 0.42187145352363586,
      "learning_rate": 1.2221305259446424e-05,
      "loss": 0.5311,
      "step": 27969
    },
    {
      "epoch": 0.8592142045280005,
      "grad_norm": 0.34909820556640625,
      "learning_rate": 1.2220834053263757e-05,
      "loss": 0.5519,
      "step": 27970
    },
    {
      "epoch": 0.8592449236629497,
      "grad_norm": 0.37643730640411377,
      "learning_rate": 1.2220362841894178e-05,
      "loss": 0.4934,
      "step": 27971
    },
    {
      "epoch": 0.8592756427978988,
      "grad_norm": 0.36117348074913025,
      "learning_rate": 1.2219891625338784e-05,
      "loss": 0.5568,
      "step": 27972
    },
    {
      "epoch": 0.8593063619328479,
      "grad_norm": 0.3675304651260376,
      "learning_rate": 1.221942040359868e-05,
      "loss": 0.5106,
      "step": 27973
    },
    {
      "epoch": 0.8593370810677972,
      "grad_norm": 0.397242933511734,
      "learning_rate": 1.2218949176674964e-05,
      "loss": 0.5616,
      "step": 27974
    },
    {
      "epoch": 0.8593678002027463,
      "grad_norm": 0.37104880809783936,
      "learning_rate": 1.2218477944568739e-05,
      "loss": 0.5527,
      "step": 27975
    },
    {
      "epoch": 0.8593985193376954,
      "grad_norm": 0.42052608728408813,
      "learning_rate": 1.22180067072811e-05,
      "loss": 0.4485,
      "step": 27976
    },
    {
      "epoch": 0.8594292384726446,
      "grad_norm": 0.31958386301994324,
      "learning_rate": 1.2217535464813155e-05,
      "loss": 0.4369,
      "step": 27977
    },
    {
      "epoch": 0.8594599576075937,
      "grad_norm": 0.34904977679252625,
      "learning_rate": 1.2217064217165999e-05,
      "loss": 0.5733,
      "step": 27978
    },
    {
      "epoch": 0.859490676742543,
      "grad_norm": 0.4194101095199585,
      "learning_rate": 1.2216592964340735e-05,
      "loss": 0.5457,
      "step": 27979
    },
    {
      "epoch": 0.8595213958774921,
      "grad_norm": 0.3757416903972626,
      "learning_rate": 1.2216121706338465e-05,
      "loss": 0.5978,
      "step": 27980
    },
    {
      "epoch": 0.8595521150124412,
      "grad_norm": 0.34763193130493164,
      "learning_rate": 1.2215650443160285e-05,
      "loss": 0.5432,
      "step": 27981
    },
    {
      "epoch": 0.8595828341473905,
      "grad_norm": 0.3776974081993103,
      "learning_rate": 1.22151791748073e-05,
      "loss": 0.5494,
      "step": 27982
    },
    {
      "epoch": 0.8596135532823396,
      "grad_norm": 0.40915268659591675,
      "learning_rate": 1.221470790128061e-05,
      "loss": 0.5588,
      "step": 27983
    },
    {
      "epoch": 0.8596442724172887,
      "grad_norm": 0.35812312364578247,
      "learning_rate": 1.2214236622581314e-05,
      "loss": 0.5745,
      "step": 27984
    },
    {
      "epoch": 0.8596749915522379,
      "grad_norm": 0.3787415027618408,
      "learning_rate": 1.2213765338710514e-05,
      "loss": 0.5167,
      "step": 27985
    },
    {
      "epoch": 0.859705710687187,
      "grad_norm": 0.3241567611694336,
      "learning_rate": 1.2213294049669311e-05,
      "loss": 0.4633,
      "step": 27986
    },
    {
      "epoch": 0.8597364298221362,
      "grad_norm": 0.3747265338897705,
      "learning_rate": 1.2212822755458804e-05,
      "loss": 0.5578,
      "step": 27987
    },
    {
      "epoch": 0.8597671489570854,
      "grad_norm": 0.3536657392978668,
      "learning_rate": 1.2212351456080097e-05,
      "loss": 0.5783,
      "step": 27988
    },
    {
      "epoch": 0.8597978680920345,
      "grad_norm": 0.42396798729896545,
      "learning_rate": 1.221188015153429e-05,
      "loss": 0.5142,
      "step": 27989
    },
    {
      "epoch": 0.8598285872269837,
      "grad_norm": 0.355142742395401,
      "learning_rate": 1.2211408841822478e-05,
      "loss": 0.5203,
      "step": 27990
    },
    {
      "epoch": 0.8598593063619329,
      "grad_norm": 0.3781788647174835,
      "learning_rate": 1.221093752694577e-05,
      "loss": 0.6159,
      "step": 27991
    },
    {
      "epoch": 0.859890025496882,
      "grad_norm": 0.3543121814727783,
      "learning_rate": 1.2210466206905261e-05,
      "loss": 0.5724,
      "step": 27992
    },
    {
      "epoch": 0.8599207446318312,
      "grad_norm": 0.3874433934688568,
      "learning_rate": 1.2209994881702053e-05,
      "loss": 0.5358,
      "step": 27993
    },
    {
      "epoch": 0.8599514637667803,
      "grad_norm": 0.3175719976425171,
      "learning_rate": 1.2209523551337247e-05,
      "loss": 0.4835,
      "step": 27994
    },
    {
      "epoch": 0.8599821829017295,
      "grad_norm": 0.3467021584510803,
      "learning_rate": 1.220905221581195e-05,
      "loss": 0.532,
      "step": 27995
    },
    {
      "epoch": 0.8600129020366787,
      "grad_norm": 0.38211074471473694,
      "learning_rate": 1.220858087512725e-05,
      "loss": 0.5779,
      "step": 27996
    },
    {
      "epoch": 0.8600436211716278,
      "grad_norm": 0.4006567895412445,
      "learning_rate": 1.2208109529284259e-05,
      "loss": 0.4905,
      "step": 27997
    },
    {
      "epoch": 0.8600743403065769,
      "grad_norm": 0.35316476225852966,
      "learning_rate": 1.2207638178284073e-05,
      "loss": 0.556,
      "step": 27998
    },
    {
      "epoch": 0.8601050594415262,
      "grad_norm": 0.3345332145690918,
      "learning_rate": 1.2207166822127794e-05,
      "loss": 0.4824,
      "step": 27999
    },
    {
      "epoch": 0.8601357785764753,
      "grad_norm": 0.34061044454574585,
      "learning_rate": 1.2206695460816524e-05,
      "loss": 0.5256,
      "step": 28000
    },
    {
      "epoch": 0.8601664977114244,
      "grad_norm": 0.3784792423248291,
      "learning_rate": 1.220622409435136e-05,
      "loss": 0.498,
      "step": 28001
    },
    {
      "epoch": 0.8601972168463736,
      "grad_norm": 0.35379546880722046,
      "learning_rate": 1.2205752722733408e-05,
      "loss": 0.5888,
      "step": 28002
    },
    {
      "epoch": 0.8602279359813227,
      "grad_norm": 0.7960163950920105,
      "learning_rate": 1.2205281345963765e-05,
      "loss": 0.5664,
      "step": 28003
    },
    {
      "epoch": 0.860258655116272,
      "grad_norm": 0.34865856170654297,
      "learning_rate": 1.2204809964043536e-05,
      "loss": 0.5238,
      "step": 28004
    },
    {
      "epoch": 0.8602893742512211,
      "grad_norm": 0.4017929136753082,
      "learning_rate": 1.2204338576973817e-05,
      "loss": 0.5594,
      "step": 28005
    },
    {
      "epoch": 0.8603200933861702,
      "grad_norm": 0.3641531467437744,
      "learning_rate": 1.220386718475571e-05,
      "loss": 0.5724,
      "step": 28006
    },
    {
      "epoch": 0.8603508125211194,
      "grad_norm": 0.41688087582588196,
      "learning_rate": 1.2203395787390322e-05,
      "loss": 0.5192,
      "step": 28007
    },
    {
      "epoch": 0.8603815316560686,
      "grad_norm": 0.3567323088645935,
      "learning_rate": 1.2202924384878744e-05,
      "loss": 0.4584,
      "step": 28008
    },
    {
      "epoch": 0.8604122507910177,
      "grad_norm": 0.34079280495643616,
      "learning_rate": 1.2202452977222085e-05,
      "loss": 0.493,
      "step": 28009
    },
    {
      "epoch": 0.8604429699259669,
      "grad_norm": 0.3836486339569092,
      "learning_rate": 1.2201981564421442e-05,
      "loss": 0.538,
      "step": 28010
    },
    {
      "epoch": 0.860473689060916,
      "grad_norm": 0.3707331120967865,
      "learning_rate": 1.220151014647792e-05,
      "loss": 0.5459,
      "step": 28011
    },
    {
      "epoch": 0.8605044081958652,
      "grad_norm": 0.3664844036102295,
      "learning_rate": 1.2201038723392613e-05,
      "loss": 0.5235,
      "step": 28012
    },
    {
      "epoch": 0.8605351273308144,
      "grad_norm": 0.44347500801086426,
      "learning_rate": 1.220056729516663e-05,
      "loss": 0.5397,
      "step": 28013
    },
    {
      "epoch": 0.8605658464657635,
      "grad_norm": 0.36191031336784363,
      "learning_rate": 1.2200095861801067e-05,
      "loss": 0.4753,
      "step": 28014
    },
    {
      "epoch": 0.8605965656007127,
      "grad_norm": 0.3497775197029114,
      "learning_rate": 1.2199624423297026e-05,
      "loss": 0.4831,
      "step": 28015
    },
    {
      "epoch": 0.8606272847356619,
      "grad_norm": 0.36825910210609436,
      "learning_rate": 1.2199152979655608e-05,
      "loss": 0.5432,
      "step": 28016
    },
    {
      "epoch": 0.860658003870611,
      "grad_norm": 0.3586590588092804,
      "learning_rate": 1.2198681530877915e-05,
      "loss": 0.5235,
      "step": 28017
    },
    {
      "epoch": 0.8606887230055602,
      "grad_norm": 0.3927917182445526,
      "learning_rate": 1.219821007696505e-05,
      "loss": 0.5544,
      "step": 28018
    },
    {
      "epoch": 0.8607194421405093,
      "grad_norm": 0.3653677999973297,
      "learning_rate": 1.2197738617918108e-05,
      "loss": 0.6235,
      "step": 28019
    },
    {
      "epoch": 0.8607501612754584,
      "grad_norm": 0.343046098947525,
      "learning_rate": 1.21972671537382e-05,
      "loss": 0.5807,
      "step": 28020
    },
    {
      "epoch": 0.8607808804104077,
      "grad_norm": 0.34243491291999817,
      "learning_rate": 1.2196795684426414e-05,
      "loss": 0.5099,
      "step": 28021
    },
    {
      "epoch": 0.8608115995453568,
      "grad_norm": 0.3594750463962555,
      "learning_rate": 1.2196324209983863e-05,
      "loss": 0.5507,
      "step": 28022
    },
    {
      "epoch": 0.8608423186803059,
      "grad_norm": 0.4017080068588257,
      "learning_rate": 1.2195852730411643e-05,
      "loss": 0.5866,
      "step": 28023
    },
    {
      "epoch": 0.8608730378152551,
      "grad_norm": 0.361447811126709,
      "learning_rate": 1.2195381245710853e-05,
      "loss": 0.5489,
      "step": 28024
    },
    {
      "epoch": 0.8609037569502043,
      "grad_norm": 0.36967912316322327,
      "learning_rate": 1.21949097558826e-05,
      "loss": 0.6163,
      "step": 28025
    },
    {
      "epoch": 0.8609344760851534,
      "grad_norm": 0.3634413480758667,
      "learning_rate": 1.219443826092798e-05,
      "loss": 0.5799,
      "step": 28026
    },
    {
      "epoch": 0.8609651952201026,
      "grad_norm": 0.3552924394607544,
      "learning_rate": 1.2193966760848098e-05,
      "loss": 0.5727,
      "step": 28027
    },
    {
      "epoch": 0.8609959143550517,
      "grad_norm": 0.38254085183143616,
      "learning_rate": 1.219349525564405e-05,
      "loss": 0.5925,
      "step": 28028
    },
    {
      "epoch": 0.861026633490001,
      "grad_norm": 0.4352259933948517,
      "learning_rate": 1.2193023745316943e-05,
      "loss": 0.5169,
      "step": 28029
    },
    {
      "epoch": 0.8610573526249501,
      "grad_norm": 0.3332619369029999,
      "learning_rate": 1.2192552229867875e-05,
      "loss": 0.5275,
      "step": 28030
    },
    {
      "epoch": 0.8610880717598992,
      "grad_norm": 0.36076605319976807,
      "learning_rate": 1.2192080709297948e-05,
      "loss": 0.5487,
      "step": 28031
    },
    {
      "epoch": 0.8611187908948484,
      "grad_norm": 0.3765714466571808,
      "learning_rate": 1.2191609183608264e-05,
      "loss": 0.5579,
      "step": 28032
    },
    {
      "epoch": 0.8611495100297976,
      "grad_norm": 0.3927370607852936,
      "learning_rate": 1.2191137652799923e-05,
      "loss": 0.6194,
      "step": 28033
    },
    {
      "epoch": 0.8611802291647467,
      "grad_norm": 0.3865217864513397,
      "learning_rate": 1.2190666116874028e-05,
      "loss": 0.5037,
      "step": 28034
    },
    {
      "epoch": 0.8612109482996959,
      "grad_norm": 0.3662228286266327,
      "learning_rate": 1.2190194575831677e-05,
      "loss": 0.5495,
      "step": 28035
    },
    {
      "epoch": 0.861241667434645,
      "grad_norm": 0.4278234839439392,
      "learning_rate": 1.2189723029673979e-05,
      "loss": 0.5964,
      "step": 28036
    },
    {
      "epoch": 0.8612723865695942,
      "grad_norm": 0.34770849347114563,
      "learning_rate": 1.2189251478402025e-05,
      "loss": 0.542,
      "step": 28037
    },
    {
      "epoch": 0.8613031057045434,
      "grad_norm": 0.4631699323654175,
      "learning_rate": 1.2188779922016925e-05,
      "loss": 0.5582,
      "step": 28038
    },
    {
      "epoch": 0.8613338248394925,
      "grad_norm": 0.3800567388534546,
      "learning_rate": 1.2188308360519772e-05,
      "loss": 0.5246,
      "step": 28039
    },
    {
      "epoch": 0.8613645439744417,
      "grad_norm": 0.4557029604911804,
      "learning_rate": 1.2187836793911676e-05,
      "loss": 0.5291,
      "step": 28040
    },
    {
      "epoch": 0.8613952631093909,
      "grad_norm": 0.3758394718170166,
      "learning_rate": 1.2187365222193732e-05,
      "loss": 0.5675,
      "step": 28041
    },
    {
      "epoch": 0.86142598224434,
      "grad_norm": 0.41473332047462463,
      "learning_rate": 1.2186893645367045e-05,
      "loss": 0.5355,
      "step": 28042
    },
    {
      "epoch": 0.8614567013792892,
      "grad_norm": 0.43191036581993103,
      "learning_rate": 1.2186422063432714e-05,
      "loss": 0.5478,
      "step": 28043
    },
    {
      "epoch": 0.8614874205142383,
      "grad_norm": 0.4053933620452881,
      "learning_rate": 1.2185950476391843e-05,
      "loss": 0.5849,
      "step": 28044
    },
    {
      "epoch": 0.8615181396491874,
      "grad_norm": 0.4632743000984192,
      "learning_rate": 1.2185478884245533e-05,
      "loss": 0.515,
      "step": 28045
    },
    {
      "epoch": 0.8615488587841367,
      "grad_norm": 0.3841489851474762,
      "learning_rate": 1.2185007286994881e-05,
      "loss": 0.5745,
      "step": 28046
    },
    {
      "epoch": 0.8615795779190858,
      "grad_norm": 0.3628014028072357,
      "learning_rate": 1.2184535684640994e-05,
      "loss": 0.5517,
      "step": 28047
    },
    {
      "epoch": 0.8616102970540349,
      "grad_norm": 0.376005083322525,
      "learning_rate": 1.218406407718497e-05,
      "loss": 0.549,
      "step": 28048
    },
    {
      "epoch": 0.8616410161889841,
      "grad_norm": 0.38568130135536194,
      "learning_rate": 1.2183592464627913e-05,
      "loss": 0.5398,
      "step": 28049
    },
    {
      "epoch": 0.8616717353239333,
      "grad_norm": 0.3827309310436249,
      "learning_rate": 1.2183120846970922e-05,
      "loss": 0.6082,
      "step": 28050
    },
    {
      "epoch": 0.8617024544588824,
      "grad_norm": 0.3787614405155182,
      "learning_rate": 1.21826492242151e-05,
      "loss": 0.4791,
      "step": 28051
    },
    {
      "epoch": 0.8617331735938316,
      "grad_norm": 0.4054242968559265,
      "learning_rate": 1.2182177596361551e-05,
      "loss": 0.4208,
      "step": 28052
    },
    {
      "epoch": 0.8617638927287807,
      "grad_norm": 0.34180521965026855,
      "learning_rate": 1.218170596341137e-05,
      "loss": 0.5298,
      "step": 28053
    },
    {
      "epoch": 0.86179461186373,
      "grad_norm": 0.44166794419288635,
      "learning_rate": 1.2181234325365664e-05,
      "loss": 0.546,
      "step": 28054
    },
    {
      "epoch": 0.8618253309986791,
      "grad_norm": 0.3754299283027649,
      "learning_rate": 1.2180762682225533e-05,
      "loss": 0.5318,
      "step": 28055
    },
    {
      "epoch": 0.8618560501336282,
      "grad_norm": 0.3665773272514343,
      "learning_rate": 1.218029103399208e-05,
      "loss": 0.5359,
      "step": 28056
    },
    {
      "epoch": 0.8618867692685774,
      "grad_norm": 0.3770677447319031,
      "learning_rate": 1.2179819380666405e-05,
      "loss": 0.5338,
      "step": 28057
    },
    {
      "epoch": 0.8619174884035266,
      "grad_norm": 0.3606318533420563,
      "learning_rate": 1.2179347722249608e-05,
      "loss": 0.5031,
      "step": 28058
    },
    {
      "epoch": 0.8619482075384757,
      "grad_norm": 0.46428433060646057,
      "learning_rate": 1.2178876058742793e-05,
      "loss": 0.5369,
      "step": 28059
    },
    {
      "epoch": 0.8619789266734249,
      "grad_norm": 0.3641799986362457,
      "learning_rate": 1.2178404390147058e-05,
      "loss": 0.5343,
      "step": 28060
    },
    {
      "epoch": 0.862009645808374,
      "grad_norm": 0.36584043502807617,
      "learning_rate": 1.2177932716463511e-05,
      "loss": 0.6252,
      "step": 28061
    },
    {
      "epoch": 0.8620403649433231,
      "grad_norm": 0.4056076407432556,
      "learning_rate": 1.2177461037693247e-05,
      "loss": 0.5435,
      "step": 28062
    },
    {
      "epoch": 0.8620710840782724,
      "grad_norm": 0.37391215562820435,
      "learning_rate": 1.2176989353837377e-05,
      "loss": 0.5668,
      "step": 28063
    },
    {
      "epoch": 0.8621018032132215,
      "grad_norm": 0.3537333607673645,
      "learning_rate": 1.217651766489699e-05,
      "loss": 0.5535,
      "step": 28064
    },
    {
      "epoch": 0.8621325223481707,
      "grad_norm": 0.4635092616081238,
      "learning_rate": 1.2176045970873196e-05,
      "loss": 0.5638,
      "step": 28065
    },
    {
      "epoch": 0.8621632414831198,
      "grad_norm": 0.38743308186531067,
      "learning_rate": 1.2175574271767092e-05,
      "loss": 0.5738,
      "step": 28066
    },
    {
      "epoch": 0.862193960618069,
      "grad_norm": 0.36777323484420776,
      "learning_rate": 1.2175102567579787e-05,
      "loss": 0.6163,
      "step": 28067
    },
    {
      "epoch": 0.8622246797530182,
      "grad_norm": 0.3574392795562744,
      "learning_rate": 1.2174630858312377e-05,
      "loss": 0.5281,
      "step": 28068
    },
    {
      "epoch": 0.8622553988879673,
      "grad_norm": 0.39983922243118286,
      "learning_rate": 1.217415914396596e-05,
      "loss": 0.5794,
      "step": 28069
    },
    {
      "epoch": 0.8622861180229164,
      "grad_norm": 0.3251422941684723,
      "learning_rate": 1.2173687424541647e-05,
      "loss": 0.521,
      "step": 28070
    },
    {
      "epoch": 0.8623168371578657,
      "grad_norm": 0.3484809398651123,
      "learning_rate": 1.2173215700040533e-05,
      "loss": 0.5765,
      "step": 28071
    },
    {
      "epoch": 0.8623475562928148,
      "grad_norm": 0.38626793026924133,
      "learning_rate": 1.2172743970463726e-05,
      "loss": 0.5176,
      "step": 28072
    },
    {
      "epoch": 0.8623782754277639,
      "grad_norm": 0.38249725103378296,
      "learning_rate": 1.2172272235812316e-05,
      "loss": 0.5444,
      "step": 28073
    },
    {
      "epoch": 0.8624089945627131,
      "grad_norm": 0.3514723479747772,
      "learning_rate": 1.217180049608742e-05,
      "loss": 0.6164,
      "step": 28074
    },
    {
      "epoch": 0.8624397136976623,
      "grad_norm": 0.4843306243419647,
      "learning_rate": 1.217132875129013e-05,
      "loss": 0.6117,
      "step": 28075
    },
    {
      "epoch": 0.8624704328326115,
      "grad_norm": 2.010173797607422,
      "learning_rate": 1.217085700142155e-05,
      "loss": 0.6137,
      "step": 28076
    },
    {
      "epoch": 0.8625011519675606,
      "grad_norm": 0.3792082965373993,
      "learning_rate": 1.2170385246482783e-05,
      "loss": 0.6292,
      "step": 28077
    },
    {
      "epoch": 0.8625318711025097,
      "grad_norm": 0.4027450382709503,
      "learning_rate": 1.2169913486474927e-05,
      "loss": 0.5262,
      "step": 28078
    },
    {
      "epoch": 0.862562590237459,
      "grad_norm": 0.38133400678634644,
      "learning_rate": 1.2169441721399089e-05,
      "loss": 0.5655,
      "step": 28079
    },
    {
      "epoch": 0.8625933093724081,
      "grad_norm": 0.5428820848464966,
      "learning_rate": 1.2168969951256364e-05,
      "loss": 0.5636,
      "step": 28080
    },
    {
      "epoch": 0.8626240285073572,
      "grad_norm": 0.35512107610702515,
      "learning_rate": 1.2168498176047863e-05,
      "loss": 0.5575,
      "step": 28081
    },
    {
      "epoch": 0.8626547476423064,
      "grad_norm": 0.40253180265426636,
      "learning_rate": 1.2168026395774681e-05,
      "loss": 0.5187,
      "step": 28082
    },
    {
      "epoch": 0.8626854667772555,
      "grad_norm": 0.33607593178749084,
      "learning_rate": 1.2167554610437923e-05,
      "loss": 0.5183,
      "step": 28083
    },
    {
      "epoch": 0.8627161859122047,
      "grad_norm": 0.49827149510383606,
      "learning_rate": 1.2167082820038686e-05,
      "loss": 0.6427,
      "step": 28084
    },
    {
      "epoch": 0.8627469050471539,
      "grad_norm": 0.4200965166091919,
      "learning_rate": 1.216661102457808e-05,
      "loss": 0.4714,
      "step": 28085
    },
    {
      "epoch": 0.862777624182103,
      "grad_norm": 0.37073957920074463,
      "learning_rate": 1.2166139224057205e-05,
      "loss": 0.5007,
      "step": 28086
    },
    {
      "epoch": 0.8628083433170521,
      "grad_norm": 0.41035038232803345,
      "learning_rate": 1.2165667418477157e-05,
      "loss": 0.5994,
      "step": 28087
    },
    {
      "epoch": 0.8628390624520014,
      "grad_norm": 0.3992158770561218,
      "learning_rate": 1.2165195607839037e-05,
      "loss": 0.5531,
      "step": 28088
    },
    {
      "epoch": 0.8628697815869505,
      "grad_norm": 0.4670623242855072,
      "learning_rate": 1.2164723792143957e-05,
      "loss": 0.5311,
      "step": 28089
    },
    {
      "epoch": 0.8629005007218997,
      "grad_norm": 0.35759907960891724,
      "learning_rate": 1.2164251971393012e-05,
      "loss": 0.5606,
      "step": 28090
    },
    {
      "epoch": 0.8629312198568488,
      "grad_norm": 0.38381102681159973,
      "learning_rate": 1.2163780145587305e-05,
      "loss": 0.5281,
      "step": 28091
    },
    {
      "epoch": 0.862961938991798,
      "grad_norm": 0.32145896553993225,
      "learning_rate": 1.2163308314727942e-05,
      "loss": 0.4815,
      "step": 28092
    },
    {
      "epoch": 0.8629926581267472,
      "grad_norm": 0.3913833796977997,
      "learning_rate": 1.2162836478816017e-05,
      "loss": 0.5616,
      "step": 28093
    },
    {
      "epoch": 0.8630233772616963,
      "grad_norm": 0.32410645484924316,
      "learning_rate": 1.2162364637852637e-05,
      "loss": 0.5184,
      "step": 28094
    },
    {
      "epoch": 0.8630540963966454,
      "grad_norm": 0.36208102107048035,
      "learning_rate": 1.2161892791838908e-05,
      "loss": 0.6006,
      "step": 28095
    },
    {
      "epoch": 0.8630848155315947,
      "grad_norm": 0.3400789201259613,
      "learning_rate": 1.2161420940775921e-05,
      "loss": 0.5446,
      "step": 28096
    },
    {
      "epoch": 0.8631155346665438,
      "grad_norm": 0.399844229221344,
      "learning_rate": 1.2160949084664788e-05,
      "loss": 0.4971,
      "step": 28097
    },
    {
      "epoch": 0.8631462538014929,
      "grad_norm": 0.41257476806640625,
      "learning_rate": 1.2160477223506606e-05,
      "loss": 0.558,
      "step": 28098
    },
    {
      "epoch": 0.8631769729364421,
      "grad_norm": 0.3950716257095337,
      "learning_rate": 1.2160005357302481e-05,
      "loss": 0.4394,
      "step": 28099
    },
    {
      "epoch": 0.8632076920713913,
      "grad_norm": 0.35571110248565674,
      "learning_rate": 1.2159533486053507e-05,
      "loss": 0.5398,
      "step": 28100
    },
    {
      "epoch": 0.8632384112063405,
      "grad_norm": 0.35678136348724365,
      "learning_rate": 1.2159061609760798e-05,
      "loss": 0.505,
      "step": 28101
    },
    {
      "epoch": 0.8632691303412896,
      "grad_norm": 0.43138155341148376,
      "learning_rate": 1.2158589728425445e-05,
      "loss": 0.5115,
      "step": 28102
    },
    {
      "epoch": 0.8632998494762387,
      "grad_norm": 0.34540635347366333,
      "learning_rate": 1.2158117842048558e-05,
      "loss": 0.4986,
      "step": 28103
    },
    {
      "epoch": 0.863330568611188,
      "grad_norm": 0.3270249366760254,
      "learning_rate": 1.2157645950631238e-05,
      "loss": 0.5263,
      "step": 28104
    },
    {
      "epoch": 0.8633612877461371,
      "grad_norm": 0.37044599652290344,
      "learning_rate": 1.215717405417458e-05,
      "loss": 0.4709,
      "step": 28105
    },
    {
      "epoch": 0.8633920068810862,
      "grad_norm": 0.4247455298900604,
      "learning_rate": 1.2156702152679693e-05,
      "loss": 0.5749,
      "step": 28106
    },
    {
      "epoch": 0.8634227260160354,
      "grad_norm": 0.39144396781921387,
      "learning_rate": 1.2156230246147677e-05,
      "loss": 0.588,
      "step": 28107
    },
    {
      "epoch": 0.8634534451509845,
      "grad_norm": 0.3646618127822876,
      "learning_rate": 1.2155758334579637e-05,
      "loss": 0.5727,
      "step": 28108
    },
    {
      "epoch": 0.8634841642859337,
      "grad_norm": 0.38119617104530334,
      "learning_rate": 1.2155286417976674e-05,
      "loss": 0.5767,
      "step": 28109
    },
    {
      "epoch": 0.8635148834208829,
      "grad_norm": 0.4091588854789734,
      "learning_rate": 1.2154814496339885e-05,
      "loss": 0.563,
      "step": 28110
    },
    {
      "epoch": 0.863545602555832,
      "grad_norm": 0.4038296639919281,
      "learning_rate": 1.2154342569670379e-05,
      "loss": 0.5656,
      "step": 28111
    },
    {
      "epoch": 0.8635763216907811,
      "grad_norm": 0.4639067053794861,
      "learning_rate": 1.2153870637969255e-05,
      "loss": 0.6155,
      "step": 28112
    },
    {
      "epoch": 0.8636070408257304,
      "grad_norm": 0.38309165835380554,
      "learning_rate": 1.2153398701237615e-05,
      "loss": 0.54,
      "step": 28113
    },
    {
      "epoch": 0.8636377599606795,
      "grad_norm": 0.3727457523345947,
      "learning_rate": 1.215292675947656e-05,
      "loss": 0.6255,
      "step": 28114
    },
    {
      "epoch": 0.8636684790956287,
      "grad_norm": 0.3973926603794098,
      "learning_rate": 1.2152454812687198e-05,
      "loss": 0.5877,
      "step": 28115
    },
    {
      "epoch": 0.8636991982305778,
      "grad_norm": 0.38559359312057495,
      "learning_rate": 1.2151982860870625e-05,
      "loss": 0.4995,
      "step": 28116
    },
    {
      "epoch": 0.863729917365527,
      "grad_norm": 0.34020867943763733,
      "learning_rate": 1.2151510904027947e-05,
      "loss": 0.5379,
      "step": 28117
    },
    {
      "epoch": 0.8637606365004762,
      "grad_norm": 0.34396201372146606,
      "learning_rate": 1.2151038942160265e-05,
      "loss": 0.5886,
      "step": 28118
    },
    {
      "epoch": 0.8637913556354253,
      "grad_norm": 0.39776915311813354,
      "learning_rate": 1.2150566975268681e-05,
      "loss": 0.5362,
      "step": 28119
    },
    {
      "epoch": 0.8638220747703744,
      "grad_norm": 0.3742005527019501,
      "learning_rate": 1.2150095003354298e-05,
      "loss": 0.5152,
      "step": 28120
    },
    {
      "epoch": 0.8638527939053237,
      "grad_norm": 0.3780343234539032,
      "learning_rate": 1.2149623026418218e-05,
      "loss": 0.5121,
      "step": 28121
    },
    {
      "epoch": 0.8638835130402728,
      "grad_norm": 0.3984128534793854,
      "learning_rate": 1.2149151044461545e-05,
      "loss": 0.6005,
      "step": 28122
    },
    {
      "epoch": 0.8639142321752219,
      "grad_norm": 0.36082884669303894,
      "learning_rate": 1.2148679057485375e-05,
      "loss": 0.5964,
      "step": 28123
    },
    {
      "epoch": 0.8639449513101711,
      "grad_norm": 0.3778296709060669,
      "learning_rate": 1.2148207065490816e-05,
      "loss": 0.5371,
      "step": 28124
    },
    {
      "epoch": 0.8639756704451202,
      "grad_norm": 0.4449632167816162,
      "learning_rate": 1.214773506847897e-05,
      "loss": 0.5696,
      "step": 28125
    },
    {
      "epoch": 0.8640063895800695,
      "grad_norm": 0.3624083697795868,
      "learning_rate": 1.2147263066450941e-05,
      "loss": 0.5225,
      "step": 28126
    },
    {
      "epoch": 0.8640371087150186,
      "grad_norm": 0.37673258781433105,
      "learning_rate": 1.2146791059407827e-05,
      "loss": 0.5558,
      "step": 28127
    },
    {
      "epoch": 0.8640678278499677,
      "grad_norm": 0.3459489047527313,
      "learning_rate": 1.2146319047350734e-05,
      "loss": 0.5358,
      "step": 28128
    },
    {
      "epoch": 0.864098546984917,
      "grad_norm": 0.3747577965259552,
      "learning_rate": 1.2145847030280762e-05,
      "loss": 0.5974,
      "step": 28129
    },
    {
      "epoch": 0.8641292661198661,
      "grad_norm": 0.43273988366127014,
      "learning_rate": 1.2145375008199014e-05,
      "loss": 0.504,
      "step": 28130
    },
    {
      "epoch": 0.8641599852548152,
      "grad_norm": 0.35696280002593994,
      "learning_rate": 1.2144902981106594e-05,
      "loss": 0.445,
      "step": 28131
    },
    {
      "epoch": 0.8641907043897644,
      "grad_norm": 0.344871461391449,
      "learning_rate": 1.2144430949004602e-05,
      "loss": 0.5989,
      "step": 28132
    },
    {
      "epoch": 0.8642214235247135,
      "grad_norm": 0.3495834767818451,
      "learning_rate": 1.2143958911894146e-05,
      "loss": 0.5119,
      "step": 28133
    },
    {
      "epoch": 0.8642521426596627,
      "grad_norm": 0.39951929450035095,
      "learning_rate": 1.2143486869776317e-05,
      "loss": 0.4998,
      "step": 28134
    },
    {
      "epoch": 0.8642828617946119,
      "grad_norm": 0.3212926685810089,
      "learning_rate": 1.214301482265223e-05,
      "loss": 0.5369,
      "step": 28135
    },
    {
      "epoch": 0.864313580929561,
      "grad_norm": 0.4089685082435608,
      "learning_rate": 1.2142542770522981e-05,
      "loss": 0.6067,
      "step": 28136
    },
    {
      "epoch": 0.8643443000645101,
      "grad_norm": 0.2873234450817108,
      "learning_rate": 1.2142070713389673e-05,
      "loss": 0.4419,
      "step": 28137
    },
    {
      "epoch": 0.8643750191994594,
      "grad_norm": 0.4441477060317993,
      "learning_rate": 1.2141598651253413e-05,
      "loss": 0.5425,
      "step": 28138
    },
    {
      "epoch": 0.8644057383344085,
      "grad_norm": 0.38240692019462585,
      "learning_rate": 1.2141126584115295e-05,
      "loss": 0.4906,
      "step": 28139
    },
    {
      "epoch": 0.8644364574693577,
      "grad_norm": 0.34498000144958496,
      "learning_rate": 1.2140654511976427e-05,
      "loss": 0.526,
      "step": 28140
    },
    {
      "epoch": 0.8644671766043068,
      "grad_norm": 0.340224951505661,
      "learning_rate": 1.2140182434837911e-05,
      "loss": 0.4583,
      "step": 28141
    },
    {
      "epoch": 0.864497895739256,
      "grad_norm": 0.38648393750190735,
      "learning_rate": 1.2139710352700849e-05,
      "loss": 0.5613,
      "step": 28142
    },
    {
      "epoch": 0.8645286148742052,
      "grad_norm": 0.3300640881061554,
      "learning_rate": 1.2139238265566345e-05,
      "loss": 0.5189,
      "step": 28143
    },
    {
      "epoch": 0.8645593340091543,
      "grad_norm": 0.3620241582393646,
      "learning_rate": 1.2138766173435502e-05,
      "loss": 0.5092,
      "step": 28144
    },
    {
      "epoch": 0.8645900531441034,
      "grad_norm": 0.32719746232032776,
      "learning_rate": 1.213829407630942e-05,
      "loss": 0.5714,
      "step": 28145
    },
    {
      "epoch": 0.8646207722790527,
      "grad_norm": 0.5992541313171387,
      "learning_rate": 1.2137821974189201e-05,
      "loss": 0.5263,
      "step": 28146
    },
    {
      "epoch": 0.8646514914140018,
      "grad_norm": 0.3603494167327881,
      "learning_rate": 1.2137349867075953e-05,
      "loss": 0.6178,
      "step": 28147
    },
    {
      "epoch": 0.8646822105489509,
      "grad_norm": 0.3603261411190033,
      "learning_rate": 1.2136877754970774e-05,
      "loss": 0.5451,
      "step": 28148
    },
    {
      "epoch": 0.8647129296839001,
      "grad_norm": 0.3820466995239258,
      "learning_rate": 1.2136405637874766e-05,
      "loss": 0.5131,
      "step": 28149
    },
    {
      "epoch": 0.8647436488188492,
      "grad_norm": 0.36099669337272644,
      "learning_rate": 1.2135933515789033e-05,
      "loss": 0.565,
      "step": 28150
    },
    {
      "epoch": 0.8647743679537985,
      "grad_norm": 0.38349997997283936,
      "learning_rate": 1.2135461388714683e-05,
      "loss": 0.54,
      "step": 28151
    },
    {
      "epoch": 0.8648050870887476,
      "grad_norm": 0.3675289750099182,
      "learning_rate": 1.2134989256652809e-05,
      "loss": 0.542,
      "step": 28152
    },
    {
      "epoch": 0.8648358062236967,
      "grad_norm": 0.35500192642211914,
      "learning_rate": 1.213451711960452e-05,
      "loss": 0.554,
      "step": 28153
    },
    {
      "epoch": 0.8648665253586459,
      "grad_norm": 0.36297667026519775,
      "learning_rate": 1.2134044977570917e-05,
      "loss": 0.6046,
      "step": 28154
    },
    {
      "epoch": 0.8648972444935951,
      "grad_norm": 0.38055089116096497,
      "learning_rate": 1.2133572830553105e-05,
      "loss": 0.5401,
      "step": 28155
    },
    {
      "epoch": 0.8649279636285442,
      "grad_norm": 0.39451348781585693,
      "learning_rate": 1.2133100678552183e-05,
      "loss": 0.546,
      "step": 28156
    },
    {
      "epoch": 0.8649586827634934,
      "grad_norm": 0.40430977940559387,
      "learning_rate": 1.2132628521569255e-05,
      "loss": 0.5747,
      "step": 28157
    },
    {
      "epoch": 0.8649894018984425,
      "grad_norm": 0.3661837875843048,
      "learning_rate": 1.2132156359605426e-05,
      "loss": 0.5562,
      "step": 28158
    },
    {
      "epoch": 0.8650201210333917,
      "grad_norm": 0.3513790965080261,
      "learning_rate": 1.2131684192661792e-05,
      "loss": 0.5735,
      "step": 28159
    },
    {
      "epoch": 0.8650508401683409,
      "grad_norm": 0.3407869040966034,
      "learning_rate": 1.2131212020739464e-05,
      "loss": 0.5741,
      "step": 28160
    },
    {
      "epoch": 0.86508155930329,
      "grad_norm": 0.3437838554382324,
      "learning_rate": 1.213073984383954e-05,
      "loss": 0.5559,
      "step": 28161
    },
    {
      "epoch": 0.8651122784382391,
      "grad_norm": 0.34281402826309204,
      "learning_rate": 1.2130267661963127e-05,
      "loss": 0.4584,
      "step": 28162
    },
    {
      "epoch": 0.8651429975731884,
      "grad_norm": 0.35963648557662964,
      "learning_rate": 1.2129795475111324e-05,
      "loss": 0.5323,
      "step": 28163
    },
    {
      "epoch": 0.8651737167081375,
      "grad_norm": 0.36112332344055176,
      "learning_rate": 1.2129323283285235e-05,
      "loss": 0.4547,
      "step": 28164
    },
    {
      "epoch": 0.8652044358430867,
      "grad_norm": 0.30556243658065796,
      "learning_rate": 1.2128851086485961e-05,
      "loss": 0.5128,
      "step": 28165
    },
    {
      "epoch": 0.8652351549780358,
      "grad_norm": 0.3551376163959503,
      "learning_rate": 1.212837888471461e-05,
      "loss": 0.5367,
      "step": 28166
    },
    {
      "epoch": 0.865265874112985,
      "grad_norm": 0.39591744542121887,
      "learning_rate": 1.2127906677972279e-05,
      "loss": 0.585,
      "step": 28167
    },
    {
      "epoch": 0.8652965932479342,
      "grad_norm": 0.4505634009838104,
      "learning_rate": 1.2127434466260073e-05,
      "loss": 0.6077,
      "step": 28168
    },
    {
      "epoch": 0.8653273123828833,
      "grad_norm": 0.38131365180015564,
      "learning_rate": 1.2126962249579097e-05,
      "loss": 0.6281,
      "step": 28169
    },
    {
      "epoch": 0.8653580315178324,
      "grad_norm": 0.4329361021518707,
      "learning_rate": 1.2126490027930451e-05,
      "loss": 0.5693,
      "step": 28170
    },
    {
      "epoch": 0.8653887506527816,
      "grad_norm": 0.4369283616542816,
      "learning_rate": 1.212601780131524e-05,
      "loss": 0.4657,
      "step": 28171
    },
    {
      "epoch": 0.8654194697877308,
      "grad_norm": 0.3591020703315735,
      "learning_rate": 1.2125545569734565e-05,
      "loss": 0.5578,
      "step": 28172
    },
    {
      "epoch": 0.8654501889226799,
      "grad_norm": 0.37670448422431946,
      "learning_rate": 1.212507333318953e-05,
      "loss": 0.5907,
      "step": 28173
    },
    {
      "epoch": 0.8654809080576291,
      "grad_norm": 0.351582795381546,
      "learning_rate": 1.2124601091681239e-05,
      "loss": 0.5656,
      "step": 28174
    },
    {
      "epoch": 0.8655116271925782,
      "grad_norm": 0.3309556841850281,
      "learning_rate": 1.2124128845210793e-05,
      "loss": 0.5382,
      "step": 28175
    },
    {
      "epoch": 0.8655423463275275,
      "grad_norm": 0.37537258863449097,
      "learning_rate": 1.2123656593779293e-05,
      "loss": 0.556,
      "step": 28176
    },
    {
      "epoch": 0.8655730654624766,
      "grad_norm": 0.37674087285995483,
      "learning_rate": 1.2123184337387848e-05,
      "loss": 0.7234,
      "step": 28177
    },
    {
      "epoch": 0.8656037845974257,
      "grad_norm": 0.38517293334007263,
      "learning_rate": 1.2122712076037558e-05,
      "loss": 0.5206,
      "step": 28178
    },
    {
      "epoch": 0.8656345037323749,
      "grad_norm": 0.3957965075969696,
      "learning_rate": 1.2122239809729524e-05,
      "loss": 0.5508,
      "step": 28179
    },
    {
      "epoch": 0.8656652228673241,
      "grad_norm": 0.401192843914032,
      "learning_rate": 1.2121767538464848e-05,
      "loss": 0.6003,
      "step": 28180
    },
    {
      "epoch": 0.8656959420022732,
      "grad_norm": 0.3732680082321167,
      "learning_rate": 1.2121295262244641e-05,
      "loss": 0.5671,
      "step": 28181
    },
    {
      "epoch": 0.8657266611372224,
      "grad_norm": 0.3510998785495758,
      "learning_rate": 1.2120822981069997e-05,
      "loss": 0.538,
      "step": 28182
    },
    {
      "epoch": 0.8657573802721715,
      "grad_norm": 0.36242640018463135,
      "learning_rate": 1.2120350694942027e-05,
      "loss": 0.5137,
      "step": 28183
    },
    {
      "epoch": 0.8657880994071206,
      "grad_norm": 0.36082300543785095,
      "learning_rate": 1.2119878403861827e-05,
      "loss": 0.4536,
      "step": 28184
    },
    {
      "epoch": 0.8658188185420699,
      "grad_norm": 0.3587583601474762,
      "learning_rate": 1.2119406107830502e-05,
      "loss": 0.5166,
      "step": 28185
    },
    {
      "epoch": 0.865849537677019,
      "grad_norm": 0.3663063943386078,
      "learning_rate": 1.2118933806849157e-05,
      "loss": 0.5451,
      "step": 28186
    },
    {
      "epoch": 0.8658802568119682,
      "grad_norm": 0.513342559337616,
      "learning_rate": 1.2118461500918896e-05,
      "loss": 0.6542,
      "step": 28187
    },
    {
      "epoch": 0.8659109759469173,
      "grad_norm": 0.40796080231666565,
      "learning_rate": 1.2117989190040818e-05,
      "loss": 0.5355,
      "step": 28188
    },
    {
      "epoch": 0.8659416950818665,
      "grad_norm": 0.46942299604415894,
      "learning_rate": 1.211751687421603e-05,
      "loss": 0.4732,
      "step": 28189
    },
    {
      "epoch": 0.8659724142168157,
      "grad_norm": 0.3810262382030487,
      "learning_rate": 1.2117044553445634e-05,
      "loss": 0.6102,
      "step": 28190
    },
    {
      "epoch": 0.8660031333517648,
      "grad_norm": 0.40272873640060425,
      "learning_rate": 1.2116572227730729e-05,
      "loss": 0.4945,
      "step": 28191
    },
    {
      "epoch": 0.8660338524867139,
      "grad_norm": 0.36627355217933655,
      "learning_rate": 1.2116099897072425e-05,
      "loss": 0.6349,
      "step": 28192
    },
    {
      "epoch": 0.8660645716216632,
      "grad_norm": 0.3637773394584656,
      "learning_rate": 1.2115627561471819e-05,
      "loss": 0.5344,
      "step": 28193
    },
    {
      "epoch": 0.8660952907566123,
      "grad_norm": 0.36690056324005127,
      "learning_rate": 1.2115155220930022e-05,
      "loss": 0.5946,
      "step": 28194
    },
    {
      "epoch": 0.8661260098915614,
      "grad_norm": 0.35724788904190063,
      "learning_rate": 1.2114682875448128e-05,
      "loss": 0.5952,
      "step": 28195
    },
    {
      "epoch": 0.8661567290265106,
      "grad_norm": 0.3874708414077759,
      "learning_rate": 1.2114210525027246e-05,
      "loss": 0.5253,
      "step": 28196
    },
    {
      "epoch": 0.8661874481614598,
      "grad_norm": 0.3616374433040619,
      "learning_rate": 1.2113738169668475e-05,
      "loss": 0.5728,
      "step": 28197
    },
    {
      "epoch": 0.8662181672964089,
      "grad_norm": 0.3944650888442993,
      "learning_rate": 1.2113265809372923e-05,
      "loss": 0.5142,
      "step": 28198
    },
    {
      "epoch": 0.8662488864313581,
      "grad_norm": 0.325636088848114,
      "learning_rate": 1.211279344414169e-05,
      "loss": 0.5362,
      "step": 28199
    },
    {
      "epoch": 0.8662796055663072,
      "grad_norm": 0.3875260353088379,
      "learning_rate": 1.2112321073975882e-05,
      "loss": 0.6357,
      "step": 28200
    },
    {
      "epoch": 0.8663103247012565,
      "grad_norm": 0.3384411931037903,
      "learning_rate": 1.2111848698876601e-05,
      "loss": 0.5341,
      "step": 28201
    },
    {
      "epoch": 0.8663410438362056,
      "grad_norm": 0.362048476934433,
      "learning_rate": 1.2111376318844948e-05,
      "loss": 0.4442,
      "step": 28202
    },
    {
      "epoch": 0.8663717629711547,
      "grad_norm": 0.34969377517700195,
      "learning_rate": 1.211090393388203e-05,
      "loss": 0.5058,
      "step": 28203
    },
    {
      "epoch": 0.8664024821061039,
      "grad_norm": 0.5487659573554993,
      "learning_rate": 1.2110431543988948e-05,
      "loss": 0.4626,
      "step": 28204
    },
    {
      "epoch": 0.866433201241053,
      "grad_norm": 0.4410102963447571,
      "learning_rate": 1.2109959149166805e-05,
      "loss": 0.4928,
      "step": 28205
    },
    {
      "epoch": 0.8664639203760022,
      "grad_norm": 0.37166082859039307,
      "learning_rate": 1.2109486749416703e-05,
      "loss": 0.5342,
      "step": 28206
    },
    {
      "epoch": 0.8664946395109514,
      "grad_norm": 0.3706166744232178,
      "learning_rate": 1.2109014344739752e-05,
      "loss": 0.5943,
      "step": 28207
    },
    {
      "epoch": 0.8665253586459005,
      "grad_norm": 0.3770751953125,
      "learning_rate": 1.210854193513705e-05,
      "loss": 0.5153,
      "step": 28208
    },
    {
      "epoch": 0.8665560777808496,
      "grad_norm": 0.39443373680114746,
      "learning_rate": 1.2108069520609697e-05,
      "loss": 0.4624,
      "step": 28209
    },
    {
      "epoch": 0.8665867969157989,
      "grad_norm": 0.3620499074459076,
      "learning_rate": 1.2107597101158806e-05,
      "loss": 0.6424,
      "step": 28210
    },
    {
      "epoch": 0.866617516050748,
      "grad_norm": 0.37124839425086975,
      "learning_rate": 1.210712467678547e-05,
      "loss": 0.5201,
      "step": 28211
    },
    {
      "epoch": 0.8666482351856972,
      "grad_norm": 0.4100263714790344,
      "learning_rate": 1.21066522474908e-05,
      "loss": 0.5309,
      "step": 28212
    },
    {
      "epoch": 0.8666789543206463,
      "grad_norm": 0.36346039175987244,
      "learning_rate": 1.2106179813275893e-05,
      "loss": 0.5231,
      "step": 28213
    },
    {
      "epoch": 0.8667096734555955,
      "grad_norm": 0.3434258699417114,
      "learning_rate": 1.210570737414186e-05,
      "loss": 0.5033,
      "step": 28214
    },
    {
      "epoch": 0.8667403925905447,
      "grad_norm": 0.3670867085456848,
      "learning_rate": 1.2105234930089798e-05,
      "loss": 0.6535,
      "step": 28215
    },
    {
      "epoch": 0.8667711117254938,
      "grad_norm": 0.3647504150867462,
      "learning_rate": 1.210476248112081e-05,
      "loss": 0.5047,
      "step": 28216
    },
    {
      "epoch": 0.8668018308604429,
      "grad_norm": 0.35337746143341064,
      "learning_rate": 1.210429002723601e-05,
      "loss": 0.5336,
      "step": 28217
    },
    {
      "epoch": 0.8668325499953922,
      "grad_norm": 0.38123470544815063,
      "learning_rate": 1.2103817568436486e-05,
      "loss": 0.5719,
      "step": 28218
    },
    {
      "epoch": 0.8668632691303413,
      "grad_norm": 0.3549462854862213,
      "learning_rate": 1.2103345104723353e-05,
      "loss": 0.524,
      "step": 28219
    },
    {
      "epoch": 0.8668939882652904,
      "grad_norm": 0.43360161781311035,
      "learning_rate": 1.210287263609771e-05,
      "loss": 0.5549,
      "step": 28220
    },
    {
      "epoch": 0.8669247074002396,
      "grad_norm": 0.3634427785873413,
      "learning_rate": 1.2102400162560664e-05,
      "loss": 0.4821,
      "step": 28221
    },
    {
      "epoch": 0.8669554265351888,
      "grad_norm": 0.34963181614875793,
      "learning_rate": 1.2101927684113311e-05,
      "loss": 0.5119,
      "step": 28222
    },
    {
      "epoch": 0.8669861456701379,
      "grad_norm": 0.4105188548564911,
      "learning_rate": 1.2101455200756762e-05,
      "loss": 0.5195,
      "step": 28223
    },
    {
      "epoch": 0.8670168648050871,
      "grad_norm": 0.36009135842323303,
      "learning_rate": 1.2100982712492115e-05,
      "loss": 0.5621,
      "step": 28224
    },
    {
      "epoch": 0.8670475839400362,
      "grad_norm": 0.585655152797699,
      "learning_rate": 1.2100510219320479e-05,
      "loss": 0.506,
      "step": 28225
    },
    {
      "epoch": 0.8670783030749855,
      "grad_norm": 0.40325987339019775,
      "learning_rate": 1.2100037721242955e-05,
      "loss": 0.5373,
      "step": 28226
    },
    {
      "epoch": 0.8671090222099346,
      "grad_norm": 0.41445568203926086,
      "learning_rate": 1.2099565218260642e-05,
      "loss": 0.6247,
      "step": 28227
    },
    {
      "epoch": 0.8671397413448837,
      "grad_norm": 0.3949780762195587,
      "learning_rate": 1.2099092710374653e-05,
      "loss": 0.6176,
      "step": 28228
    },
    {
      "epoch": 0.8671704604798329,
      "grad_norm": 0.3419690430164337,
      "learning_rate": 1.2098620197586082e-05,
      "loss": 0.4383,
      "step": 28229
    },
    {
      "epoch": 0.867201179614782,
      "grad_norm": 0.3402341604232788,
      "learning_rate": 1.2098147679896039e-05,
      "loss": 0.5766,
      "step": 28230
    },
    {
      "epoch": 0.8672318987497312,
      "grad_norm": 0.38239824771881104,
      "learning_rate": 1.2097675157305625e-05,
      "loss": 0.5906,
      "step": 28231
    },
    {
      "epoch": 0.8672626178846804,
      "grad_norm": 0.47236600518226624,
      "learning_rate": 1.2097202629815944e-05,
      "loss": 0.5411,
      "step": 28232
    },
    {
      "epoch": 0.8672933370196295,
      "grad_norm": 0.3779805302619934,
      "learning_rate": 1.2096730097428102e-05,
      "loss": 0.5749,
      "step": 28233
    },
    {
      "epoch": 0.8673240561545786,
      "grad_norm": 0.4310336410999298,
      "learning_rate": 1.2096257560143197e-05,
      "loss": 0.5907,
      "step": 28234
    },
    {
      "epoch": 0.8673547752895279,
      "grad_norm": 0.35946735739707947,
      "learning_rate": 1.2095785017962337e-05,
      "loss": 0.5659,
      "step": 28235
    },
    {
      "epoch": 0.867385494424477,
      "grad_norm": 0.35657989978790283,
      "learning_rate": 1.2095312470886627e-05,
      "loss": 0.6309,
      "step": 28236
    },
    {
      "epoch": 0.8674162135594262,
      "grad_norm": 0.41304346919059753,
      "learning_rate": 1.2094839918917167e-05,
      "loss": 0.5346,
      "step": 28237
    },
    {
      "epoch": 0.8674469326943753,
      "grad_norm": 0.38084983825683594,
      "learning_rate": 1.2094367362055062e-05,
      "loss": 0.6162,
      "step": 28238
    },
    {
      "epoch": 0.8674776518293245,
      "grad_norm": 0.3936210870742798,
      "learning_rate": 1.2093894800301416e-05,
      "loss": 0.5426,
      "step": 28239
    },
    {
      "epoch": 0.8675083709642737,
      "grad_norm": 0.3637482821941376,
      "learning_rate": 1.209342223365733e-05,
      "loss": 0.5667,
      "step": 28240
    },
    {
      "epoch": 0.8675390900992228,
      "grad_norm": 0.3544303774833679,
      "learning_rate": 1.2092949662123915e-05,
      "loss": 0.5215,
      "step": 28241
    },
    {
      "epoch": 0.8675698092341719,
      "grad_norm": 0.3575209379196167,
      "learning_rate": 1.2092477085702267e-05,
      "loss": 0.5964,
      "step": 28242
    },
    {
      "epoch": 0.8676005283691212,
      "grad_norm": 0.3794827461242676,
      "learning_rate": 1.2092004504393493e-05,
      "loss": 0.4866,
      "step": 28243
    },
    {
      "epoch": 0.8676312475040703,
      "grad_norm": 0.3641577661037445,
      "learning_rate": 1.2091531918198696e-05,
      "loss": 0.6006,
      "step": 28244
    },
    {
      "epoch": 0.8676619666390194,
      "grad_norm": 0.35853537917137146,
      "learning_rate": 1.2091059327118979e-05,
      "loss": 0.605,
      "step": 28245
    },
    {
      "epoch": 0.8676926857739686,
      "grad_norm": 0.37069225311279297,
      "learning_rate": 1.209058673115545e-05,
      "loss": 0.6016,
      "step": 28246
    },
    {
      "epoch": 0.8677234049089178,
      "grad_norm": 0.3637998700141907,
      "learning_rate": 1.2090114130309207e-05,
      "loss": 0.5399,
      "step": 28247
    },
    {
      "epoch": 0.8677541240438669,
      "grad_norm": 0.39712899923324585,
      "learning_rate": 1.2089641524581359e-05,
      "loss": 0.5731,
      "step": 28248
    },
    {
      "epoch": 0.8677848431788161,
      "grad_norm": 0.34125983715057373,
      "learning_rate": 1.2089168913973004e-05,
      "loss": 0.4865,
      "step": 28249
    },
    {
      "epoch": 0.8678155623137652,
      "grad_norm": 0.3918803036212921,
      "learning_rate": 1.2088696298485252e-05,
      "loss": 0.52,
      "step": 28250
    },
    {
      "epoch": 0.8678462814487145,
      "grad_norm": 0.3776468336582184,
      "learning_rate": 1.2088223678119202e-05,
      "loss": 0.5726,
      "step": 28251
    },
    {
      "epoch": 0.8678770005836636,
      "grad_norm": 0.42034825682640076,
      "learning_rate": 1.208775105287596e-05,
      "loss": 0.5934,
      "step": 28252
    },
    {
      "epoch": 0.8679077197186127,
      "grad_norm": 0.3591286838054657,
      "learning_rate": 1.208727842275663e-05,
      "loss": 0.5678,
      "step": 28253
    },
    {
      "epoch": 0.8679384388535619,
      "grad_norm": 0.35185706615448,
      "learning_rate": 1.2086805787762314e-05,
      "loss": 0.508,
      "step": 28254
    },
    {
      "epoch": 0.867969157988511,
      "grad_norm": 0.36784687638282776,
      "learning_rate": 1.2086333147894121e-05,
      "loss": 0.5318,
      "step": 28255
    },
    {
      "epoch": 0.8679998771234602,
      "grad_norm": 0.3960963189601898,
      "learning_rate": 1.2085860503153149e-05,
      "loss": 0.588,
      "step": 28256
    },
    {
      "epoch": 0.8680305962584094,
      "grad_norm": 0.3797062933444977,
      "learning_rate": 1.2085387853540504e-05,
      "loss": 0.5202,
      "step": 28257
    },
    {
      "epoch": 0.8680613153933585,
      "grad_norm": 0.3768194615840912,
      "learning_rate": 1.208491519905729e-05,
      "loss": 0.5477,
      "step": 28258
    },
    {
      "epoch": 0.8680920345283076,
      "grad_norm": 0.38469552993774414,
      "learning_rate": 1.2084442539704612e-05,
      "loss": 0.5771,
      "step": 28259
    },
    {
      "epoch": 0.8681227536632569,
      "grad_norm": 0.34327077865600586,
      "learning_rate": 1.2083969875483573e-05,
      "loss": 0.5329,
      "step": 28260
    },
    {
      "epoch": 0.868153472798206,
      "grad_norm": 0.39796653389930725,
      "learning_rate": 1.2083497206395274e-05,
      "loss": 0.5203,
      "step": 28261
    },
    {
      "epoch": 0.8681841919331552,
      "grad_norm": 0.382515549659729,
      "learning_rate": 1.2083024532440826e-05,
      "loss": 0.5415,
      "step": 28262
    },
    {
      "epoch": 0.8682149110681043,
      "grad_norm": 0.3330744802951813,
      "learning_rate": 1.2082551853621325e-05,
      "loss": 0.5788,
      "step": 28263
    },
    {
      "epoch": 0.8682456302030535,
      "grad_norm": 0.35241952538490295,
      "learning_rate": 1.208207916993788e-05,
      "loss": 0.5498,
      "step": 28264
    },
    {
      "epoch": 0.8682763493380027,
      "grad_norm": 0.33570146560668945,
      "learning_rate": 1.2081606481391595e-05,
      "loss": 0.5153,
      "step": 28265
    },
    {
      "epoch": 0.8683070684729518,
      "grad_norm": 0.3952699899673462,
      "learning_rate": 1.2081133787983572e-05,
      "loss": 0.5389,
      "step": 28266
    },
    {
      "epoch": 0.8683377876079009,
      "grad_norm": 0.34955304861068726,
      "learning_rate": 1.2080661089714914e-05,
      "loss": 0.543,
      "step": 28267
    },
    {
      "epoch": 0.8683685067428502,
      "grad_norm": 0.35482311248779297,
      "learning_rate": 1.2080188386586729e-05,
      "loss": 0.6308,
      "step": 28268
    },
    {
      "epoch": 0.8683992258777993,
      "grad_norm": 0.4179548919200897,
      "learning_rate": 1.2079715678600117e-05,
      "loss": 0.5908,
      "step": 28269
    },
    {
      "epoch": 0.8684299450127484,
      "grad_norm": 0.38749513030052185,
      "learning_rate": 1.2079242965756181e-05,
      "loss": 0.54,
      "step": 28270
    },
    {
      "epoch": 0.8684606641476976,
      "grad_norm": 0.3896263539791107,
      "learning_rate": 1.2078770248056033e-05,
      "loss": 0.5186,
      "step": 28271
    },
    {
      "epoch": 0.8684913832826467,
      "grad_norm": 0.46835511922836304,
      "learning_rate": 1.2078297525500771e-05,
      "loss": 0.5535,
      "step": 28272
    },
    {
      "epoch": 0.868522102417596,
      "grad_norm": 0.49034619331359863,
      "learning_rate": 1.20778247980915e-05,
      "loss": 0.615,
      "step": 28273
    },
    {
      "epoch": 0.8685528215525451,
      "grad_norm": 0.3779667615890503,
      "learning_rate": 1.2077352065829321e-05,
      "loss": 0.4924,
      "step": 28274
    },
    {
      "epoch": 0.8685835406874942,
      "grad_norm": 0.40355467796325684,
      "learning_rate": 1.2076879328715345e-05,
      "loss": 0.5616,
      "step": 28275
    },
    {
      "epoch": 0.8686142598224434,
      "grad_norm": 0.43120065331459045,
      "learning_rate": 1.2076406586750668e-05,
      "loss": 0.4883,
      "step": 28276
    },
    {
      "epoch": 0.8686449789573926,
      "grad_norm": 0.37144190073013306,
      "learning_rate": 1.2075933839936403e-05,
      "loss": 0.5316,
      "step": 28277
    },
    {
      "epoch": 0.8686756980923417,
      "grad_norm": 0.4047151207923889,
      "learning_rate": 1.2075461088273649e-05,
      "loss": 0.6156,
      "step": 28278
    },
    {
      "epoch": 0.8687064172272909,
      "grad_norm": 0.41164830327033997,
      "learning_rate": 1.207498833176351e-05,
      "loss": 0.5835,
      "step": 28279
    },
    {
      "epoch": 0.86873713636224,
      "grad_norm": 0.3746277987957001,
      "learning_rate": 1.207451557040709e-05,
      "loss": 0.5735,
      "step": 28280
    },
    {
      "epoch": 0.8687678554971892,
      "grad_norm": 0.3428497910499573,
      "learning_rate": 1.2074042804205493e-05,
      "loss": 0.5535,
      "step": 28281
    },
    {
      "epoch": 0.8687985746321384,
      "grad_norm": 0.38990241289138794,
      "learning_rate": 1.2073570033159826e-05,
      "loss": 0.546,
      "step": 28282
    },
    {
      "epoch": 0.8688292937670875,
      "grad_norm": 0.37238162755966187,
      "learning_rate": 1.2073097257271189e-05,
      "loss": 0.5352,
      "step": 28283
    },
    {
      "epoch": 0.8688600129020366,
      "grad_norm": 1.2515003681182861,
      "learning_rate": 1.2072624476540691e-05,
      "loss": 0.5469,
      "step": 28284
    },
    {
      "epoch": 0.8688907320369859,
      "grad_norm": 0.40762174129486084,
      "learning_rate": 1.2072151690969434e-05,
      "loss": 0.5332,
      "step": 28285
    },
    {
      "epoch": 0.868921451171935,
      "grad_norm": 0.37631866335868835,
      "learning_rate": 1.2071678900558521e-05,
      "loss": 0.5537,
      "step": 28286
    },
    {
      "epoch": 0.8689521703068842,
      "grad_norm": 0.33911219239234924,
      "learning_rate": 1.2071206105309057e-05,
      "loss": 0.5451,
      "step": 28287
    },
    {
      "epoch": 0.8689828894418333,
      "grad_norm": 0.6600348949432373,
      "learning_rate": 1.2070733305222144e-05,
      "loss": 0.5846,
      "step": 28288
    },
    {
      "epoch": 0.8690136085767824,
      "grad_norm": 0.3795805871486664,
      "learning_rate": 1.2070260500298893e-05,
      "loss": 0.6143,
      "step": 28289
    },
    {
      "epoch": 0.8690443277117317,
      "grad_norm": 0.40648725628852844,
      "learning_rate": 1.2069787690540402e-05,
      "loss": 0.557,
      "step": 28290
    },
    {
      "epoch": 0.8690750468466808,
      "grad_norm": 0.4348684847354889,
      "learning_rate": 1.206931487594778e-05,
      "loss": 0.505,
      "step": 28291
    },
    {
      "epoch": 0.8691057659816299,
      "grad_norm": 0.43361029028892517,
      "learning_rate": 1.2068842056522123e-05,
      "loss": 0.5501,
      "step": 28292
    },
    {
      "epoch": 0.8691364851165791,
      "grad_norm": 0.35881322622299194,
      "learning_rate": 1.2068369232264547e-05,
      "loss": 0.5264,
      "step": 28293
    },
    {
      "epoch": 0.8691672042515283,
      "grad_norm": 0.3718612492084503,
      "learning_rate": 1.2067896403176147e-05,
      "loss": 0.496,
      "step": 28294
    },
    {
      "epoch": 0.8691979233864774,
      "grad_norm": 0.3262152075767517,
      "learning_rate": 1.206742356925803e-05,
      "loss": 0.5447,
      "step": 28295
    },
    {
      "epoch": 0.8692286425214266,
      "grad_norm": 0.36109989881515503,
      "learning_rate": 1.2066950730511303e-05,
      "loss": 0.5342,
      "step": 28296
    },
    {
      "epoch": 0.8692593616563757,
      "grad_norm": 0.3652712404727936,
      "learning_rate": 1.2066477886937067e-05,
      "loss": 0.5749,
      "step": 28297
    },
    {
      "epoch": 0.869290080791325,
      "grad_norm": 0.3252395987510681,
      "learning_rate": 1.2066005038536428e-05,
      "loss": 0.4636,
      "step": 28298
    },
    {
      "epoch": 0.8693207999262741,
      "grad_norm": 0.35671788454055786,
      "learning_rate": 1.206553218531049e-05,
      "loss": 0.4892,
      "step": 28299
    },
    {
      "epoch": 0.8693515190612232,
      "grad_norm": 0.3569547235965729,
      "learning_rate": 1.2065059327260358e-05,
      "loss": 0.4943,
      "step": 28300
    },
    {
      "epoch": 0.8693822381961724,
      "grad_norm": 0.5488170981407166,
      "learning_rate": 1.2064586464387134e-05,
      "loss": 0.5814,
      "step": 28301
    },
    {
      "epoch": 0.8694129573311216,
      "grad_norm": 0.3410843312740326,
      "learning_rate": 1.2064113596691923e-05,
      "loss": 0.5201,
      "step": 28302
    },
    {
      "epoch": 0.8694436764660707,
      "grad_norm": 0.39925825595855713,
      "learning_rate": 1.2063640724175833e-05,
      "loss": 0.5637,
      "step": 28303
    },
    {
      "epoch": 0.8694743956010199,
      "grad_norm": 0.3406887650489807,
      "learning_rate": 1.2063167846839967e-05,
      "loss": 0.5505,
      "step": 28304
    },
    {
      "epoch": 0.869505114735969,
      "grad_norm": 0.3735995888710022,
      "learning_rate": 1.2062694964685426e-05,
      "loss": 0.5459,
      "step": 28305
    },
    {
      "epoch": 0.8695358338709182,
      "grad_norm": 0.3855251967906952,
      "learning_rate": 1.2062222077713318e-05,
      "loss": 0.6123,
      "step": 28306
    },
    {
      "epoch": 0.8695665530058674,
      "grad_norm": 0.3665768802165985,
      "learning_rate": 1.2061749185924744e-05,
      "loss": 0.4494,
      "step": 28307
    },
    {
      "epoch": 0.8695972721408165,
      "grad_norm": 0.37892502546310425,
      "learning_rate": 1.2061276289320812e-05,
      "loss": 0.5711,
      "step": 28308
    },
    {
      "epoch": 0.8696279912757656,
      "grad_norm": 0.3508387804031372,
      "learning_rate": 1.2060803387902626e-05,
      "loss": 0.5015,
      "step": 28309
    },
    {
      "epoch": 0.8696587104107149,
      "grad_norm": 0.3673098683357239,
      "learning_rate": 1.206033048167129e-05,
      "loss": 0.5804,
      "step": 28310
    },
    {
      "epoch": 0.869689429545664,
      "grad_norm": 0.3834904730319977,
      "learning_rate": 1.205985757062791e-05,
      "loss": 0.5469,
      "step": 28311
    },
    {
      "epoch": 0.8697201486806132,
      "grad_norm": 0.36852291226387024,
      "learning_rate": 1.2059384654773586e-05,
      "loss": 0.5327,
      "step": 28312
    },
    {
      "epoch": 0.8697508678155623,
      "grad_norm": 0.4282296895980835,
      "learning_rate": 1.2058911734109426e-05,
      "loss": 0.5142,
      "step": 28313
    },
    {
      "epoch": 0.8697815869505114,
      "grad_norm": 0.34131157398223877,
      "learning_rate": 1.2058438808636534e-05,
      "loss": 0.5079,
      "step": 28314
    },
    {
      "epoch": 0.8698123060854607,
      "grad_norm": 0.5953589677810669,
      "learning_rate": 1.2057965878356015e-05,
      "loss": 0.5468,
      "step": 28315
    },
    {
      "epoch": 0.8698430252204098,
      "grad_norm": 0.3637564480304718,
      "learning_rate": 1.205749294326897e-05,
      "loss": 0.618,
      "step": 28316
    },
    {
      "epoch": 0.8698737443553589,
      "grad_norm": 0.34850266575813293,
      "learning_rate": 1.205702000337651e-05,
      "loss": 0.5441,
      "step": 28317
    },
    {
      "epoch": 0.8699044634903081,
      "grad_norm": 0.3577592968940735,
      "learning_rate": 1.2056547058679735e-05,
      "loss": 0.6174,
      "step": 28318
    },
    {
      "epoch": 0.8699351826252573,
      "grad_norm": 0.3557618260383606,
      "learning_rate": 1.2056074109179752e-05,
      "loss": 0.6154,
      "step": 28319
    },
    {
      "epoch": 0.8699659017602064,
      "grad_norm": 0.3887292742729187,
      "learning_rate": 1.2055601154877663e-05,
      "loss": 0.6225,
      "step": 28320
    },
    {
      "epoch": 0.8699966208951556,
      "grad_norm": 0.37766939401626587,
      "learning_rate": 1.2055128195774572e-05,
      "loss": 0.5358,
      "step": 28321
    },
    {
      "epoch": 0.8700273400301047,
      "grad_norm": 0.35930126905441284,
      "learning_rate": 1.2054655231871588e-05,
      "loss": 0.4598,
      "step": 28322
    },
    {
      "epoch": 0.870058059165054,
      "grad_norm": 0.3371865153312683,
      "learning_rate": 1.2054182263169816e-05,
      "loss": 0.5605,
      "step": 28323
    },
    {
      "epoch": 0.8700887783000031,
      "grad_norm": 0.3411305546760559,
      "learning_rate": 1.2053709289670352e-05,
      "loss": 0.5706,
      "step": 28324
    },
    {
      "epoch": 0.8701194974349522,
      "grad_norm": 0.43060052394866943,
      "learning_rate": 1.2053236311374307e-05,
      "loss": 0.5278,
      "step": 28325
    },
    {
      "epoch": 0.8701502165699014,
      "grad_norm": 0.3841065764427185,
      "learning_rate": 1.2052763328282789e-05,
      "loss": 0.4938,
      "step": 28326
    },
    {
      "epoch": 0.8701809357048506,
      "grad_norm": 0.35268688201904297,
      "learning_rate": 1.2052290340396898e-05,
      "loss": 0.497,
      "step": 28327
    },
    {
      "epoch": 0.8702116548397997,
      "grad_norm": 0.3373374044895172,
      "learning_rate": 1.2051817347717738e-05,
      "loss": 0.5758,
      "step": 28328
    },
    {
      "epoch": 0.8702423739747489,
      "grad_norm": 0.32163485884666443,
      "learning_rate": 1.2051344350246417e-05,
      "loss": 0.4543,
      "step": 28329
    },
    {
      "epoch": 0.870273093109698,
      "grad_norm": 0.3770144581794739,
      "learning_rate": 1.2050871347984036e-05,
      "loss": 0.5007,
      "step": 28330
    },
    {
      "epoch": 0.8703038122446471,
      "grad_norm": 0.404241144657135,
      "learning_rate": 1.2050398340931703e-05,
      "loss": 0.5732,
      "step": 28331
    },
    {
      "epoch": 0.8703345313795964,
      "grad_norm": 0.34240633249282837,
      "learning_rate": 1.2049925329090521e-05,
      "loss": 0.6023,
      "step": 28332
    },
    {
      "epoch": 0.8703652505145455,
      "grad_norm": 0.32017794251441956,
      "learning_rate": 1.2049452312461595e-05,
      "loss": 0.52,
      "step": 28333
    },
    {
      "epoch": 0.8703959696494946,
      "grad_norm": 0.34968438744544983,
      "learning_rate": 1.2048979291046032e-05,
      "loss": 0.5789,
      "step": 28334
    },
    {
      "epoch": 0.8704266887844438,
      "grad_norm": 0.5014244914054871,
      "learning_rate": 1.2048506264844932e-05,
      "loss": 0.5229,
      "step": 28335
    },
    {
      "epoch": 0.870457407919393,
      "grad_norm": 0.3599821925163269,
      "learning_rate": 1.2048033233859404e-05,
      "loss": 0.5853,
      "step": 28336
    },
    {
      "epoch": 0.8704881270543422,
      "grad_norm": 0.35950425267219543,
      "learning_rate": 1.204756019809055e-05,
      "loss": 0.5337,
      "step": 28337
    },
    {
      "epoch": 0.8705188461892913,
      "grad_norm": 0.3515561521053314,
      "learning_rate": 1.2047087157539478e-05,
      "loss": 0.542,
      "step": 28338
    },
    {
      "epoch": 0.8705495653242404,
      "grad_norm": 0.3710479140281677,
      "learning_rate": 1.204661411220729e-05,
      "loss": 0.541,
      "step": 28339
    },
    {
      "epoch": 0.8705802844591897,
      "grad_norm": 0.38754239678382874,
      "learning_rate": 1.2046141062095093e-05,
      "loss": 0.5415,
      "step": 28340
    },
    {
      "epoch": 0.8706110035941388,
      "grad_norm": 0.3851338028907776,
      "learning_rate": 1.2045668007203993e-05,
      "loss": 0.5068,
      "step": 28341
    },
    {
      "epoch": 0.8706417227290879,
      "grad_norm": 0.37634167075157166,
      "learning_rate": 1.2045194947535088e-05,
      "loss": 0.4997,
      "step": 28342
    },
    {
      "epoch": 0.8706724418640371,
      "grad_norm": 1.1174964904785156,
      "learning_rate": 1.2044721883089487e-05,
      "loss": 0.5526,
      "step": 28343
    },
    {
      "epoch": 0.8707031609989863,
      "grad_norm": 0.3972259759902954,
      "learning_rate": 1.2044248813868296e-05,
      "loss": 0.5519,
      "step": 28344
    },
    {
      "epoch": 0.8707338801339354,
      "grad_norm": 0.37555593252182007,
      "learning_rate": 1.204377573987262e-05,
      "loss": 0.5572,
      "step": 28345
    },
    {
      "epoch": 0.8707645992688846,
      "grad_norm": 0.34312689304351807,
      "learning_rate": 1.2043302661103565e-05,
      "loss": 0.5655,
      "step": 28346
    },
    {
      "epoch": 0.8707953184038337,
      "grad_norm": 0.3722642660140991,
      "learning_rate": 1.204282957756223e-05,
      "loss": 0.4981,
      "step": 28347
    },
    {
      "epoch": 0.870826037538783,
      "grad_norm": 0.3831174671649933,
      "learning_rate": 1.2042356489249727e-05,
      "loss": 0.5383,
      "step": 28348
    },
    {
      "epoch": 0.8708567566737321,
      "grad_norm": 0.34630683064460754,
      "learning_rate": 1.2041883396167156e-05,
      "loss": 0.5848,
      "step": 28349
    },
    {
      "epoch": 0.8708874758086812,
      "grad_norm": 0.37555786967277527,
      "learning_rate": 1.2041410298315626e-05,
      "loss": 0.6067,
      "step": 28350
    },
    {
      "epoch": 0.8709181949436304,
      "grad_norm": 0.5176382064819336,
      "learning_rate": 1.2040937195696235e-05,
      "loss": 0.5641,
      "step": 28351
    },
    {
      "epoch": 0.8709489140785796,
      "grad_norm": 0.34975409507751465,
      "learning_rate": 1.2040464088310097e-05,
      "loss": 0.5102,
      "step": 28352
    },
    {
      "epoch": 0.8709796332135287,
      "grad_norm": 0.3589489459991455,
      "learning_rate": 1.2039990976158312e-05,
      "loss": 0.5214,
      "step": 28353
    },
    {
      "epoch": 0.8710103523484779,
      "grad_norm": 0.3910689949989319,
      "learning_rate": 1.2039517859241986e-05,
      "loss": 0.6606,
      "step": 28354
    },
    {
      "epoch": 0.871041071483427,
      "grad_norm": 0.3577881157398224,
      "learning_rate": 1.203904473756222e-05,
      "loss": 0.4905,
      "step": 28355
    },
    {
      "epoch": 0.8710717906183761,
      "grad_norm": 0.3914414048194885,
      "learning_rate": 1.2038571611120127e-05,
      "loss": 0.5442,
      "step": 28356
    },
    {
      "epoch": 0.8711025097533254,
      "grad_norm": 0.3504895269870758,
      "learning_rate": 1.2038098479916807e-05,
      "loss": 0.6555,
      "step": 28357
    },
    {
      "epoch": 0.8711332288882745,
      "grad_norm": 0.445613294839859,
      "learning_rate": 1.2037625343953363e-05,
      "loss": 0.5092,
      "step": 28358
    },
    {
      "epoch": 0.8711639480232236,
      "grad_norm": 0.37776419520378113,
      "learning_rate": 1.2037152203230905e-05,
      "loss": 0.6011,
      "step": 28359
    },
    {
      "epoch": 0.8711946671581728,
      "grad_norm": 0.4132393002510071,
      "learning_rate": 1.2036679057750534e-05,
      "loss": 0.5574,
      "step": 28360
    },
    {
      "epoch": 0.871225386293122,
      "grad_norm": 0.38311588764190674,
      "learning_rate": 1.2036205907513357e-05,
      "loss": 0.5174,
      "step": 28361
    },
    {
      "epoch": 0.8712561054280712,
      "grad_norm": 0.3761301040649414,
      "learning_rate": 1.2035732752520477e-05,
      "loss": 0.534,
      "step": 28362
    },
    {
      "epoch": 0.8712868245630203,
      "grad_norm": 0.3402872383594513,
      "learning_rate": 1.2035259592773005e-05,
      "loss": 0.5838,
      "step": 28363
    },
    {
      "epoch": 0.8713175436979694,
      "grad_norm": 0.36089766025543213,
      "learning_rate": 1.203478642827204e-05,
      "loss": 0.5951,
      "step": 28364
    },
    {
      "epoch": 0.8713482628329187,
      "grad_norm": 0.3616520166397095,
      "learning_rate": 1.203431325901869e-05,
      "loss": 0.5889,
      "step": 28365
    },
    {
      "epoch": 0.8713789819678678,
      "grad_norm": 0.40467703342437744,
      "learning_rate": 1.2033840085014062e-05,
      "loss": 0.5989,
      "step": 28366
    },
    {
      "epoch": 0.8714097011028169,
      "grad_norm": 0.37168195843696594,
      "learning_rate": 1.2033366906259252e-05,
      "loss": 0.5681,
      "step": 28367
    },
    {
      "epoch": 0.8714404202377661,
      "grad_norm": 0.3765406012535095,
      "learning_rate": 1.2032893722755376e-05,
      "loss": 0.5182,
      "step": 28368
    },
    {
      "epoch": 0.8714711393727153,
      "grad_norm": 0.4047154188156128,
      "learning_rate": 1.2032420534503533e-05,
      "loss": 0.5291,
      "step": 28369
    },
    {
      "epoch": 0.8715018585076644,
      "grad_norm": 0.3733317255973816,
      "learning_rate": 1.2031947341504832e-05,
      "loss": 0.474,
      "step": 28370
    },
    {
      "epoch": 0.8715325776426136,
      "grad_norm": 0.36944565176963806,
      "learning_rate": 1.2031474143760374e-05,
      "loss": 0.5445,
      "step": 28371
    },
    {
      "epoch": 0.8715632967775627,
      "grad_norm": 0.36369311809539795,
      "learning_rate": 1.2031000941271269e-05,
      "loss": 0.5393,
      "step": 28372
    },
    {
      "epoch": 0.871594015912512,
      "grad_norm": 0.43815261125564575,
      "learning_rate": 1.2030527734038615e-05,
      "loss": 0.5848,
      "step": 28373
    },
    {
      "epoch": 0.8716247350474611,
      "grad_norm": 0.3505791425704956,
      "learning_rate": 1.2030054522063525e-05,
      "loss": 0.4138,
      "step": 28374
    },
    {
      "epoch": 0.8716554541824102,
      "grad_norm": 0.3540589511394501,
      "learning_rate": 1.2029581305347102e-05,
      "loss": 0.5124,
      "step": 28375
    },
    {
      "epoch": 0.8716861733173594,
      "grad_norm": 0.5005012154579163,
      "learning_rate": 1.2029108083890448e-05,
      "loss": 0.4989,
      "step": 28376
    },
    {
      "epoch": 0.8717168924523085,
      "grad_norm": 0.3566738963127136,
      "learning_rate": 1.202863485769467e-05,
      "loss": 0.4498,
      "step": 28377
    },
    {
      "epoch": 0.8717476115872577,
      "grad_norm": 0.3552400767803192,
      "learning_rate": 1.2028161626760875e-05,
      "loss": 0.5022,
      "step": 28378
    },
    {
      "epoch": 0.8717783307222069,
      "grad_norm": 0.38504570722579956,
      "learning_rate": 1.2027688391090166e-05,
      "loss": 0.5223,
      "step": 28379
    },
    {
      "epoch": 0.871809049857156,
      "grad_norm": 0.34923699498176575,
      "learning_rate": 1.2027215150683646e-05,
      "loss": 0.5355,
      "step": 28380
    },
    {
      "epoch": 0.8718397689921051,
      "grad_norm": 0.3514001667499542,
      "learning_rate": 1.2026741905542427e-05,
      "loss": 0.5752,
      "step": 28381
    },
    {
      "epoch": 0.8718704881270544,
      "grad_norm": 0.5052415728569031,
      "learning_rate": 1.2026268655667613e-05,
      "loss": 0.5219,
      "step": 28382
    },
    {
      "epoch": 0.8719012072620035,
      "grad_norm": 0.36378154158592224,
      "learning_rate": 1.2025795401060303e-05,
      "loss": 0.5471,
      "step": 28383
    },
    {
      "epoch": 0.8719319263969527,
      "grad_norm": 0.4040933847427368,
      "learning_rate": 1.2025322141721607e-05,
      "loss": 0.5368,
      "step": 28384
    },
    {
      "epoch": 0.8719626455319018,
      "grad_norm": 0.38887929916381836,
      "learning_rate": 1.2024848877652631e-05,
      "loss": 0.5652,
      "step": 28385
    },
    {
      "epoch": 0.871993364666851,
      "grad_norm": 0.41604888439178467,
      "learning_rate": 1.202437560885448e-05,
      "loss": 0.5937,
      "step": 28386
    },
    {
      "epoch": 0.8720240838018002,
      "grad_norm": 0.38224557042121887,
      "learning_rate": 1.2023902335328254e-05,
      "loss": 0.525,
      "step": 28387
    },
    {
      "epoch": 0.8720548029367493,
      "grad_norm": 0.39212989807128906,
      "learning_rate": 1.2023429057075067e-05,
      "loss": 0.5639,
      "step": 28388
    },
    {
      "epoch": 0.8720855220716984,
      "grad_norm": 0.37059760093688965,
      "learning_rate": 1.202295577409602e-05,
      "loss": 0.6008,
      "step": 28389
    },
    {
      "epoch": 0.8721162412066477,
      "grad_norm": 0.3652953803539276,
      "learning_rate": 1.2022482486392217e-05,
      "loss": 0.5646,
      "step": 28390
    },
    {
      "epoch": 0.8721469603415968,
      "grad_norm": 0.34840190410614014,
      "learning_rate": 1.2022009193964764e-05,
      "loss": 0.5352,
      "step": 28391
    },
    {
      "epoch": 0.8721776794765459,
      "grad_norm": 0.43520575761795044,
      "learning_rate": 1.2021535896814768e-05,
      "loss": 0.5448,
      "step": 28392
    },
    {
      "epoch": 0.8722083986114951,
      "grad_norm": 0.37797415256500244,
      "learning_rate": 1.2021062594943335e-05,
      "loss": 0.546,
      "step": 28393
    },
    {
      "epoch": 0.8722391177464442,
      "grad_norm": 0.3550953269004822,
      "learning_rate": 1.202058928835157e-05,
      "loss": 0.5336,
      "step": 28394
    },
    {
      "epoch": 0.8722698368813934,
      "grad_norm": 0.3618764579296112,
      "learning_rate": 1.2020115977040576e-05,
      "loss": 0.5322,
      "step": 28395
    },
    {
      "epoch": 0.8723005560163426,
      "grad_norm": 0.37103471159935,
      "learning_rate": 1.2019642661011458e-05,
      "loss": 0.5581,
      "step": 28396
    },
    {
      "epoch": 0.8723312751512917,
      "grad_norm": 0.35329002141952515,
      "learning_rate": 1.2019169340265329e-05,
      "loss": 0.482,
      "step": 28397
    },
    {
      "epoch": 0.872361994286241,
      "grad_norm": 0.35215526819229126,
      "learning_rate": 1.2018696014803284e-05,
      "loss": 0.5222,
      "step": 28398
    },
    {
      "epoch": 0.8723927134211901,
      "grad_norm": 0.5158136487007141,
      "learning_rate": 1.2018222684626433e-05,
      "loss": 0.5852,
      "step": 28399
    },
    {
      "epoch": 0.8724234325561392,
      "grad_norm": 0.3559378683567047,
      "learning_rate": 1.2017749349735885e-05,
      "loss": 0.4943,
      "step": 28400
    },
    {
      "epoch": 0.8724541516910884,
      "grad_norm": 0.42552292346954346,
      "learning_rate": 1.2017276010132739e-05,
      "loss": 0.5666,
      "step": 28401
    },
    {
      "epoch": 0.8724848708260375,
      "grad_norm": 0.3351263403892517,
      "learning_rate": 1.2016802665818107e-05,
      "loss": 0.514,
      "step": 28402
    },
    {
      "epoch": 0.8725155899609867,
      "grad_norm": 0.3869855999946594,
      "learning_rate": 1.2016329316793092e-05,
      "loss": 0.5801,
      "step": 28403
    },
    {
      "epoch": 0.8725463090959359,
      "grad_norm": 0.44248974323272705,
      "learning_rate": 1.2015855963058799e-05,
      "loss": 0.5102,
      "step": 28404
    },
    {
      "epoch": 0.872577028230885,
      "grad_norm": 0.36946240067481995,
      "learning_rate": 1.201538260461633e-05,
      "loss": 0.5402,
      "step": 28405
    },
    {
      "epoch": 0.8726077473658341,
      "grad_norm": 0.3372649550437927,
      "learning_rate": 1.20149092414668e-05,
      "loss": 0.6167,
      "step": 28406
    },
    {
      "epoch": 0.8726384665007834,
      "grad_norm": 0.3475021421909332,
      "learning_rate": 1.2014435873611303e-05,
      "loss": 0.581,
      "step": 28407
    },
    {
      "epoch": 0.8726691856357325,
      "grad_norm": 0.3618728220462799,
      "learning_rate": 1.2013962501050956e-05,
      "loss": 0.601,
      "step": 28408
    },
    {
      "epoch": 0.8726999047706817,
      "grad_norm": 0.33615124225616455,
      "learning_rate": 1.2013489123786855e-05,
      "loss": 0.5719,
      "step": 28409
    },
    {
      "epoch": 0.8727306239056308,
      "grad_norm": 0.35050782561302185,
      "learning_rate": 1.201301574182011e-05,
      "loss": 0.5212,
      "step": 28410
    },
    {
      "epoch": 0.87276134304058,
      "grad_norm": 0.5041343569755554,
      "learning_rate": 1.2012542355151827e-05,
      "loss": 0.5489,
      "step": 28411
    },
    {
      "epoch": 0.8727920621755292,
      "grad_norm": 0.39476048946380615,
      "learning_rate": 1.201206896378311e-05,
      "loss": 0.5501,
      "step": 28412
    },
    {
      "epoch": 0.8728227813104783,
      "grad_norm": 0.40119466185569763,
      "learning_rate": 1.2011595567715066e-05,
      "loss": 0.588,
      "step": 28413
    },
    {
      "epoch": 0.8728535004454274,
      "grad_norm": 0.3947545289993286,
      "learning_rate": 1.2011122166948799e-05,
      "loss": 0.4643,
      "step": 28414
    },
    {
      "epoch": 0.8728842195803767,
      "grad_norm": 0.366443395614624,
      "learning_rate": 1.2010648761485418e-05,
      "loss": 0.5407,
      "step": 28415
    },
    {
      "epoch": 0.8729149387153258,
      "grad_norm": 0.35504522919654846,
      "learning_rate": 1.2010175351326023e-05,
      "loss": 0.4415,
      "step": 28416
    },
    {
      "epoch": 0.8729456578502749,
      "grad_norm": 0.3694327771663666,
      "learning_rate": 1.2009701936471724e-05,
      "loss": 0.5456,
      "step": 28417
    },
    {
      "epoch": 0.8729763769852241,
      "grad_norm": 0.3424679636955261,
      "learning_rate": 1.2009228516923628e-05,
      "loss": 0.5432,
      "step": 28418
    },
    {
      "epoch": 0.8730070961201732,
      "grad_norm": 0.362690269947052,
      "learning_rate": 1.2008755092682836e-05,
      "loss": 0.5338,
      "step": 28419
    },
    {
      "epoch": 0.8730378152551224,
      "grad_norm": 0.39937320351600647,
      "learning_rate": 1.2008281663750458e-05,
      "loss": 0.6598,
      "step": 28420
    },
    {
      "epoch": 0.8730685343900716,
      "grad_norm": 0.3452723026275635,
      "learning_rate": 1.2007808230127595e-05,
      "loss": 0.5612,
      "step": 28421
    },
    {
      "epoch": 0.8730992535250207,
      "grad_norm": 0.4428025782108307,
      "learning_rate": 1.200733479181536e-05,
      "loss": 0.4835,
      "step": 28422
    },
    {
      "epoch": 0.8731299726599699,
      "grad_norm": 0.3314797282218933,
      "learning_rate": 1.2006861348814851e-05,
      "loss": 0.4244,
      "step": 28423
    },
    {
      "epoch": 0.8731606917949191,
      "grad_norm": 0.3312529921531677,
      "learning_rate": 1.200638790112718e-05,
      "loss": 0.5258,
      "step": 28424
    },
    {
      "epoch": 0.8731914109298682,
      "grad_norm": 0.3261760473251343,
      "learning_rate": 1.2005914448753449e-05,
      "loss": 0.4752,
      "step": 28425
    },
    {
      "epoch": 0.8732221300648174,
      "grad_norm": 0.38583502173423767,
      "learning_rate": 1.2005440991694763e-05,
      "loss": 0.5055,
      "step": 28426
    },
    {
      "epoch": 0.8732528491997665,
      "grad_norm": 0.3740696907043457,
      "learning_rate": 1.2004967529952232e-05,
      "loss": 0.5636,
      "step": 28427
    },
    {
      "epoch": 0.8732835683347157,
      "grad_norm": 0.422904372215271,
      "learning_rate": 1.2004494063526956e-05,
      "loss": 0.6054,
      "step": 28428
    },
    {
      "epoch": 0.8733142874696649,
      "grad_norm": 0.33249735832214355,
      "learning_rate": 1.200402059242005e-05,
      "loss": 0.4509,
      "step": 28429
    },
    {
      "epoch": 0.873345006604614,
      "grad_norm": 0.41646090149879456,
      "learning_rate": 1.2003547116632608e-05,
      "loss": 0.5981,
      "step": 28430
    },
    {
      "epoch": 0.8733757257395631,
      "grad_norm": 0.4529435336589813,
      "learning_rate": 1.2003073636165745e-05,
      "loss": 0.5739,
      "step": 28431
    },
    {
      "epoch": 0.8734064448745124,
      "grad_norm": 0.3781065344810486,
      "learning_rate": 1.200260015102056e-05,
      "loss": 0.5844,
      "step": 28432
    },
    {
      "epoch": 0.8734371640094615,
      "grad_norm": 0.4346970021724701,
      "learning_rate": 1.2002126661198168e-05,
      "loss": 0.6099,
      "step": 28433
    },
    {
      "epoch": 0.8734678831444107,
      "grad_norm": 0.3558316230773926,
      "learning_rate": 1.2001653166699666e-05,
      "loss": 0.5097,
      "step": 28434
    },
    {
      "epoch": 0.8734986022793598,
      "grad_norm": 0.3581884205341339,
      "learning_rate": 1.200117966752616e-05,
      "loss": 0.5732,
      "step": 28435
    },
    {
      "epoch": 0.873529321414309,
      "grad_norm": 1.1512809991836548,
      "learning_rate": 1.2000706163678763e-05,
      "loss": 0.5112,
      "step": 28436
    },
    {
      "epoch": 0.8735600405492582,
      "grad_norm": 0.34583595395088196,
      "learning_rate": 1.2000232655158577e-05,
      "loss": 0.5539,
      "step": 28437
    },
    {
      "epoch": 0.8735907596842073,
      "grad_norm": 0.37214091420173645,
      "learning_rate": 1.199975914196671e-05,
      "loss": 0.4647,
      "step": 28438
    },
    {
      "epoch": 0.8736214788191564,
      "grad_norm": 0.37176012992858887,
      "learning_rate": 1.1999285624104263e-05,
      "loss": 0.5516,
      "step": 28439
    },
    {
      "epoch": 0.8736521979541056,
      "grad_norm": 0.34277960658073425,
      "learning_rate": 1.1998812101572344e-05,
      "loss": 0.5603,
      "step": 28440
    },
    {
      "epoch": 0.8736829170890548,
      "grad_norm": 0.38454344868659973,
      "learning_rate": 1.199833857437206e-05,
      "loss": 0.5059,
      "step": 28441
    },
    {
      "epoch": 0.8737136362240039,
      "grad_norm": 0.36601483821868896,
      "learning_rate": 1.199786504250452e-05,
      "loss": 0.5257,
      "step": 28442
    },
    {
      "epoch": 0.8737443553589531,
      "grad_norm": 0.3531837463378906,
      "learning_rate": 1.1997391505970821e-05,
      "loss": 0.514,
      "step": 28443
    },
    {
      "epoch": 0.8737750744939022,
      "grad_norm": 0.40768250823020935,
      "learning_rate": 1.199691796477208e-05,
      "loss": 0.6043,
      "step": 28444
    },
    {
      "epoch": 0.8738057936288514,
      "grad_norm": 0.4027094542980194,
      "learning_rate": 1.1996444418909397e-05,
      "loss": 0.5302,
      "step": 28445
    },
    {
      "epoch": 0.8738365127638006,
      "grad_norm": 0.37989288568496704,
      "learning_rate": 1.1995970868383878e-05,
      "loss": 0.5779,
      "step": 28446
    },
    {
      "epoch": 0.8738672318987497,
      "grad_norm": 0.3598441481590271,
      "learning_rate": 1.1995497313196628e-05,
      "loss": 0.5262,
      "step": 28447
    },
    {
      "epoch": 0.8738979510336989,
      "grad_norm": 0.34312736988067627,
      "learning_rate": 1.1995023753348756e-05,
      "loss": 0.5935,
      "step": 28448
    },
    {
      "epoch": 0.8739286701686481,
      "grad_norm": 0.35345765948295593,
      "learning_rate": 1.1994550188841366e-05,
      "loss": 0.4661,
      "step": 28449
    },
    {
      "epoch": 0.8739593893035972,
      "grad_norm": 0.3622262179851532,
      "learning_rate": 1.1994076619675564e-05,
      "loss": 0.6362,
      "step": 28450
    },
    {
      "epoch": 0.8739901084385464,
      "grad_norm": 0.3771741986274719,
      "learning_rate": 1.199360304585246e-05,
      "loss": 0.4532,
      "step": 28451
    },
    {
      "epoch": 0.8740208275734955,
      "grad_norm": 0.3380659222602844,
      "learning_rate": 1.1993129467373153e-05,
      "loss": 0.4989,
      "step": 28452
    },
    {
      "epoch": 0.8740515467084446,
      "grad_norm": 0.36526191234588623,
      "learning_rate": 1.1992655884238752e-05,
      "loss": 0.592,
      "step": 28453
    },
    {
      "epoch": 0.8740822658433939,
      "grad_norm": 0.3690098524093628,
      "learning_rate": 1.199218229645037e-05,
      "loss": 0.5066,
      "step": 28454
    },
    {
      "epoch": 0.874112984978343,
      "grad_norm": 0.3638240396976471,
      "learning_rate": 1.1991708704009102e-05,
      "loss": 0.5629,
      "step": 28455
    },
    {
      "epoch": 0.8741437041132921,
      "grad_norm": 0.35513952374458313,
      "learning_rate": 1.1991235106916062e-05,
      "loss": 0.5547,
      "step": 28456
    },
    {
      "epoch": 0.8741744232482414,
      "grad_norm": 0.4401882588863373,
      "learning_rate": 1.1990761505172351e-05,
      "loss": 0.656,
      "step": 28457
    },
    {
      "epoch": 0.8742051423831905,
      "grad_norm": 0.38038066029548645,
      "learning_rate": 1.1990287898779078e-05,
      "loss": 0.5544,
      "step": 28458
    },
    {
      "epoch": 0.8742358615181397,
      "grad_norm": 0.3848641514778137,
      "learning_rate": 1.198981428773735e-05,
      "loss": 0.5209,
      "step": 28459
    },
    {
      "epoch": 0.8742665806530888,
      "grad_norm": 0.3674757480621338,
      "learning_rate": 1.1989340672048271e-05,
      "loss": 0.498,
      "step": 28460
    },
    {
      "epoch": 0.8742972997880379,
      "grad_norm": 0.37454643845558167,
      "learning_rate": 1.1988867051712952e-05,
      "loss": 0.5377,
      "step": 28461
    },
    {
      "epoch": 0.8743280189229872,
      "grad_norm": 0.4118833839893341,
      "learning_rate": 1.1988393426732488e-05,
      "loss": 0.5715,
      "step": 28462
    },
    {
      "epoch": 0.8743587380579363,
      "grad_norm": 0.31500008702278137,
      "learning_rate": 1.1987919797107996e-05,
      "loss": 0.4664,
      "step": 28463
    },
    {
      "epoch": 0.8743894571928854,
      "grad_norm": 0.3179040253162384,
      "learning_rate": 1.1987446162840577e-05,
      "loss": 0.4353,
      "step": 28464
    },
    {
      "epoch": 0.8744201763278346,
      "grad_norm": 0.34795668721199036,
      "learning_rate": 1.1986972523931343e-05,
      "loss": 0.6149,
      "step": 28465
    },
    {
      "epoch": 0.8744508954627838,
      "grad_norm": 0.42334648966789246,
      "learning_rate": 1.1986498880381389e-05,
      "loss": 0.4578,
      "step": 28466
    },
    {
      "epoch": 0.8744816145977329,
      "grad_norm": 0.4124751389026642,
      "learning_rate": 1.1986025232191833e-05,
      "loss": 0.5754,
      "step": 28467
    },
    {
      "epoch": 0.8745123337326821,
      "grad_norm": 0.3709756135940552,
      "learning_rate": 1.1985551579363775e-05,
      "loss": 0.5432,
      "step": 28468
    },
    {
      "epoch": 0.8745430528676312,
      "grad_norm": 0.35963988304138184,
      "learning_rate": 1.1985077921898322e-05,
      "loss": 0.5947,
      "step": 28469
    },
    {
      "epoch": 0.8745737720025804,
      "grad_norm": 0.32027468085289,
      "learning_rate": 1.1984604259796582e-05,
      "loss": 0.4564,
      "step": 28470
    },
    {
      "epoch": 0.8746044911375296,
      "grad_norm": 0.35123881697654724,
      "learning_rate": 1.1984130593059657e-05,
      "loss": 0.4812,
      "step": 28471
    },
    {
      "epoch": 0.8746352102724787,
      "grad_norm": 0.35165804624557495,
      "learning_rate": 1.1983656921688662e-05,
      "loss": 0.5712,
      "step": 28472
    },
    {
      "epoch": 0.8746659294074279,
      "grad_norm": 0.33970072865486145,
      "learning_rate": 1.1983183245684692e-05,
      "loss": 0.5265,
      "step": 28473
    },
    {
      "epoch": 0.874696648542377,
      "grad_norm": 0.35628536343574524,
      "learning_rate": 1.1982709565048865e-05,
      "loss": 0.5585,
      "step": 28474
    },
    {
      "epoch": 0.8747273676773262,
      "grad_norm": 0.39367762207984924,
      "learning_rate": 1.1982235879782276e-05,
      "loss": 0.549,
      "step": 28475
    },
    {
      "epoch": 0.8747580868122754,
      "grad_norm": 0.3781222701072693,
      "learning_rate": 1.1981762189886039e-05,
      "loss": 0.554,
      "step": 28476
    },
    {
      "epoch": 0.8747888059472245,
      "grad_norm": 0.3650170862674713,
      "learning_rate": 1.1981288495361256e-05,
      "loss": 0.6579,
      "step": 28477
    },
    {
      "epoch": 0.8748195250821736,
      "grad_norm": 0.3629835247993469,
      "learning_rate": 1.198081479620904e-05,
      "loss": 0.5871,
      "step": 28478
    },
    {
      "epoch": 0.8748502442171229,
      "grad_norm": 0.31506964564323425,
      "learning_rate": 1.198034109243049e-05,
      "loss": 0.5439,
      "step": 28479
    },
    {
      "epoch": 0.874880963352072,
      "grad_norm": 0.39303264021873474,
      "learning_rate": 1.1979867384026713e-05,
      "loss": 0.4821,
      "step": 28480
    },
    {
      "epoch": 0.8749116824870211,
      "grad_norm": 0.3680780529975891,
      "learning_rate": 1.1979393670998823e-05,
      "loss": 0.5754,
      "step": 28481
    },
    {
      "epoch": 0.8749424016219703,
      "grad_norm": 0.40052494406700134,
      "learning_rate": 1.1978919953347913e-05,
      "loss": 0.4647,
      "step": 28482
    },
    {
      "epoch": 0.8749731207569195,
      "grad_norm": 0.3474857807159424,
      "learning_rate": 1.1978446231075106e-05,
      "loss": 0.5724,
      "step": 28483
    },
    {
      "epoch": 0.8750038398918687,
      "grad_norm": 0.37930673360824585,
      "learning_rate": 1.1977972504181493e-05,
      "loss": 0.6296,
      "step": 28484
    },
    {
      "epoch": 0.8750345590268178,
      "grad_norm": 0.3816988468170166,
      "learning_rate": 1.197749877266819e-05,
      "loss": 0.5506,
      "step": 28485
    },
    {
      "epoch": 0.8750652781617669,
      "grad_norm": 0.3843477666378021,
      "learning_rate": 1.1977025036536298e-05,
      "loss": 0.51,
      "step": 28486
    },
    {
      "epoch": 0.8750959972967162,
      "grad_norm": 0.3932378590106964,
      "learning_rate": 1.1976551295786928e-05,
      "loss": 0.4969,
      "step": 28487
    },
    {
      "epoch": 0.8751267164316653,
      "grad_norm": 0.6251181364059448,
      "learning_rate": 1.1976077550421183e-05,
      "loss": 0.5236,
      "step": 28488
    },
    {
      "epoch": 0.8751574355666144,
      "grad_norm": 0.39725425839424133,
      "learning_rate": 1.1975603800440171e-05,
      "loss": 0.545,
      "step": 28489
    },
    {
      "epoch": 0.8751881547015636,
      "grad_norm": 0.33884525299072266,
      "learning_rate": 1.1975130045845003e-05,
      "loss": 0.5348,
      "step": 28490
    },
    {
      "epoch": 0.8752188738365128,
      "grad_norm": 0.38952916860580444,
      "learning_rate": 1.1974656286636775e-05,
      "loss": 0.581,
      "step": 28491
    },
    {
      "epoch": 0.8752495929714619,
      "grad_norm": 0.3561926782131195,
      "learning_rate": 1.1974182522816601e-05,
      "loss": 0.5248,
      "step": 28492
    },
    {
      "epoch": 0.8752803121064111,
      "grad_norm": 0.38090750575065613,
      "learning_rate": 1.1973708754385587e-05,
      "loss": 0.5169,
      "step": 28493
    },
    {
      "epoch": 0.8753110312413602,
      "grad_norm": 0.4078444242477417,
      "learning_rate": 1.197323498134484e-05,
      "loss": 0.5043,
      "step": 28494
    },
    {
      "epoch": 0.8753417503763095,
      "grad_norm": 0.3465564250946045,
      "learning_rate": 1.197276120369546e-05,
      "loss": 0.5336,
      "step": 28495
    },
    {
      "epoch": 0.8753724695112586,
      "grad_norm": 0.35461142659187317,
      "learning_rate": 1.1972287421438563e-05,
      "loss": 0.5787,
      "step": 28496
    },
    {
      "epoch": 0.8754031886462077,
      "grad_norm": 0.3657251298427582,
      "learning_rate": 1.197181363457525e-05,
      "loss": 0.5132,
      "step": 28497
    },
    {
      "epoch": 0.8754339077811569,
      "grad_norm": 0.3772505819797516,
      "learning_rate": 1.1971339843106626e-05,
      "loss": 0.509,
      "step": 28498
    },
    {
      "epoch": 0.875464626916106,
      "grad_norm": 0.3799249529838562,
      "learning_rate": 1.1970866047033803e-05,
      "loss": 0.6318,
      "step": 28499
    },
    {
      "epoch": 0.8754953460510552,
      "grad_norm": 0.4004979133605957,
      "learning_rate": 1.197039224635788e-05,
      "loss": 0.6919,
      "step": 28500
    },
    {
      "epoch": 0.8755260651860044,
      "grad_norm": 0.3383437991142273,
      "learning_rate": 1.1969918441079976e-05,
      "loss": 0.5144,
      "step": 28501
    },
    {
      "epoch": 0.8755567843209535,
      "grad_norm": 0.3761340081691742,
      "learning_rate": 1.1969444631201183e-05,
      "loss": 0.5923,
      "step": 28502
    },
    {
      "epoch": 0.8755875034559026,
      "grad_norm": 0.35938945412635803,
      "learning_rate": 1.1968970816722618e-05,
      "loss": 0.567,
      "step": 28503
    },
    {
      "epoch": 0.8756182225908519,
      "grad_norm": 0.3502582907676697,
      "learning_rate": 1.1968496997645383e-05,
      "loss": 0.4865,
      "step": 28504
    },
    {
      "epoch": 0.875648941725801,
      "grad_norm": 0.3545056879520416,
      "learning_rate": 1.1968023173970587e-05,
      "loss": 0.5974,
      "step": 28505
    },
    {
      "epoch": 0.8756796608607501,
      "grad_norm": 0.3534618318080902,
      "learning_rate": 1.1967549345699332e-05,
      "loss": 0.5035,
      "step": 28506
    },
    {
      "epoch": 0.8757103799956993,
      "grad_norm": 0.38224393129348755,
      "learning_rate": 1.1967075512832731e-05,
      "loss": 0.5166,
      "step": 28507
    },
    {
      "epoch": 0.8757410991306485,
      "grad_norm": 0.4031940698623657,
      "learning_rate": 1.1966601675371887e-05,
      "loss": 0.5356,
      "step": 28508
    },
    {
      "epoch": 0.8757718182655977,
      "grad_norm": 0.4032827615737915,
      "learning_rate": 1.1966127833317906e-05,
      "loss": 0.6813,
      "step": 28509
    },
    {
      "epoch": 0.8758025374005468,
      "grad_norm": 0.38926735520362854,
      "learning_rate": 1.1965653986671901e-05,
      "loss": 0.5601,
      "step": 28510
    },
    {
      "epoch": 0.8758332565354959,
      "grad_norm": 0.3711499571800232,
      "learning_rate": 1.1965180135434968e-05,
      "loss": 0.5965,
      "step": 28511
    },
    {
      "epoch": 0.8758639756704452,
      "grad_norm": 0.3383844196796417,
      "learning_rate": 1.1964706279608224e-05,
      "loss": 0.494,
      "step": 28512
    },
    {
      "epoch": 0.8758946948053943,
      "grad_norm": 0.3685321807861328,
      "learning_rate": 1.1964232419192769e-05,
      "loss": 0.6024,
      "step": 28513
    },
    {
      "epoch": 0.8759254139403434,
      "grad_norm": 0.4037533402442932,
      "learning_rate": 1.1963758554189712e-05,
      "loss": 0.488,
      "step": 28514
    },
    {
      "epoch": 0.8759561330752926,
      "grad_norm": 0.4837189316749573,
      "learning_rate": 1.1963284684600162e-05,
      "loss": 0.5113,
      "step": 28515
    },
    {
      "epoch": 0.8759868522102418,
      "grad_norm": 0.36115920543670654,
      "learning_rate": 1.196281081042522e-05,
      "loss": 0.5508,
      "step": 28516
    },
    {
      "epoch": 0.8760175713451909,
      "grad_norm": 0.3209586441516876,
      "learning_rate": 1.1962336931666002e-05,
      "loss": 0.5337,
      "step": 28517
    },
    {
      "epoch": 0.8760482904801401,
      "grad_norm": 0.4126362204551697,
      "learning_rate": 1.1961863048323603e-05,
      "loss": 0.5662,
      "step": 28518
    },
    {
      "epoch": 0.8760790096150892,
      "grad_norm": 0.3545790910720825,
      "learning_rate": 1.1961389160399138e-05,
      "loss": 0.5298,
      "step": 28519
    },
    {
      "epoch": 0.8761097287500385,
      "grad_norm": 0.4286617636680603,
      "learning_rate": 1.1960915267893711e-05,
      "loss": 0.575,
      "step": 28520
    },
    {
      "epoch": 0.8761404478849876,
      "grad_norm": 0.3668558895587921,
      "learning_rate": 1.1960441370808431e-05,
      "loss": 0.5611,
      "step": 28521
    },
    {
      "epoch": 0.8761711670199367,
      "grad_norm": 0.3677925765514374,
      "learning_rate": 1.1959967469144402e-05,
      "loss": 0.561,
      "step": 28522
    },
    {
      "epoch": 0.8762018861548859,
      "grad_norm": 0.34738266468048096,
      "learning_rate": 1.1959493562902734e-05,
      "loss": 0.6089,
      "step": 28523
    },
    {
      "epoch": 0.876232605289835,
      "grad_norm": 0.32403188943862915,
      "learning_rate": 1.1959019652084527e-05,
      "loss": 0.4787,
      "step": 28524
    },
    {
      "epoch": 0.8762633244247842,
      "grad_norm": 0.3634187877178192,
      "learning_rate": 1.19585457366909e-05,
      "loss": 0.5615,
      "step": 28525
    },
    {
      "epoch": 0.8762940435597334,
      "grad_norm": 0.35820427536964417,
      "learning_rate": 1.1958071816722944e-05,
      "loss": 0.4748,
      "step": 28526
    },
    {
      "epoch": 0.8763247626946825,
      "grad_norm": 0.36405035853385925,
      "learning_rate": 1.1957597892181781e-05,
      "loss": 0.5684,
      "step": 28527
    },
    {
      "epoch": 0.8763554818296316,
      "grad_norm": 0.37877750396728516,
      "learning_rate": 1.1957123963068508e-05,
      "loss": 0.5658,
      "step": 28528
    },
    {
      "epoch": 0.8763862009645809,
      "grad_norm": 0.438912570476532,
      "learning_rate": 1.1956650029384239e-05,
      "loss": 0.615,
      "step": 28529
    },
    {
      "epoch": 0.87641692009953,
      "grad_norm": 0.37476322054862976,
      "learning_rate": 1.1956176091130074e-05,
      "loss": 0.5545,
      "step": 28530
    },
    {
      "epoch": 0.8764476392344791,
      "grad_norm": 0.401238352060318,
      "learning_rate": 1.1955702148307126e-05,
      "loss": 0.5535,
      "step": 28531
    },
    {
      "epoch": 0.8764783583694283,
      "grad_norm": 0.3393048644065857,
      "learning_rate": 1.1955228200916495e-05,
      "loss": 0.4938,
      "step": 28532
    },
    {
      "epoch": 0.8765090775043775,
      "grad_norm": 0.37326276302337646,
      "learning_rate": 1.1954754248959297e-05,
      "loss": 0.5221,
      "step": 28533
    },
    {
      "epoch": 0.8765397966393267,
      "grad_norm": 0.35535162687301636,
      "learning_rate": 1.1954280292436631e-05,
      "loss": 0.5764,
      "step": 28534
    },
    {
      "epoch": 0.8765705157742758,
      "grad_norm": 0.4396457076072693,
      "learning_rate": 1.1953806331349606e-05,
      "loss": 0.5983,
      "step": 28535
    },
    {
      "epoch": 0.8766012349092249,
      "grad_norm": 0.3452571630477905,
      "learning_rate": 1.195333236569933e-05,
      "loss": 0.511,
      "step": 28536
    },
    {
      "epoch": 0.8766319540441742,
      "grad_norm": 0.3852604329586029,
      "learning_rate": 1.1952858395486912e-05,
      "loss": 0.5789,
      "step": 28537
    },
    {
      "epoch": 0.8766626731791233,
      "grad_norm": 0.40779659152030945,
      "learning_rate": 1.1952384420713456e-05,
      "loss": 0.5492,
      "step": 28538
    },
    {
      "epoch": 0.8766933923140724,
      "grad_norm": 0.35132572054862976,
      "learning_rate": 1.195191044138007e-05,
      "loss": 0.5182,
      "step": 28539
    },
    {
      "epoch": 0.8767241114490216,
      "grad_norm": 0.4511793851852417,
      "learning_rate": 1.1951436457487859e-05,
      "loss": 0.5849,
      "step": 28540
    },
    {
      "epoch": 0.8767548305839707,
      "grad_norm": 0.36128172278404236,
      "learning_rate": 1.1950962469037934e-05,
      "loss": 0.5858,
      "step": 28541
    },
    {
      "epoch": 0.8767855497189199,
      "grad_norm": 0.3583977222442627,
      "learning_rate": 1.19504884760314e-05,
      "loss": 0.5635,
      "step": 28542
    },
    {
      "epoch": 0.8768162688538691,
      "grad_norm": 0.46043965220451355,
      "learning_rate": 1.1950014478469363e-05,
      "loss": 0.6164,
      "step": 28543
    },
    {
      "epoch": 0.8768469879888182,
      "grad_norm": 0.384075403213501,
      "learning_rate": 1.194954047635293e-05,
      "loss": 0.5177,
      "step": 28544
    },
    {
      "epoch": 0.8768777071237674,
      "grad_norm": 0.4157235622406006,
      "learning_rate": 1.1949066469683207e-05,
      "loss": 0.6756,
      "step": 28545
    },
    {
      "epoch": 0.8769084262587166,
      "grad_norm": 0.3424513339996338,
      "learning_rate": 1.194859245846131e-05,
      "loss": 0.5368,
      "step": 28546
    },
    {
      "epoch": 0.8769391453936657,
      "grad_norm": 0.3807108402252197,
      "learning_rate": 1.1948118442688335e-05,
      "loss": 0.5447,
      "step": 28547
    },
    {
      "epoch": 0.8769698645286149,
      "grad_norm": 0.3656023144721985,
      "learning_rate": 1.1947644422365394e-05,
      "loss": 0.5476,
      "step": 28548
    },
    {
      "epoch": 0.877000583663564,
      "grad_norm": 0.3773270547389984,
      "learning_rate": 1.1947170397493595e-05,
      "loss": 0.5879,
      "step": 28549
    },
    {
      "epoch": 0.8770313027985132,
      "grad_norm": 0.3797477185726166,
      "learning_rate": 1.194669636807404e-05,
      "loss": 0.5461,
      "step": 28550
    },
    {
      "epoch": 0.8770620219334624,
      "grad_norm": 0.4022761881351471,
      "learning_rate": 1.1946222334107843e-05,
      "loss": 0.5027,
      "step": 28551
    },
    {
      "epoch": 0.8770927410684115,
      "grad_norm": 0.38314321637153625,
      "learning_rate": 1.1945748295596104e-05,
      "loss": 0.5714,
      "step": 28552
    },
    {
      "epoch": 0.8771234602033606,
      "grad_norm": 0.3317645788192749,
      "learning_rate": 1.1945274252539939e-05,
      "loss": 0.5222,
      "step": 28553
    },
    {
      "epoch": 0.8771541793383099,
      "grad_norm": 0.37899336218833923,
      "learning_rate": 1.1944800204940446e-05,
      "loss": 0.5465,
      "step": 28554
    },
    {
      "epoch": 0.877184898473259,
      "grad_norm": 0.35870981216430664,
      "learning_rate": 1.1944326152798738e-05,
      "loss": 0.5966,
      "step": 28555
    },
    {
      "epoch": 0.8772156176082081,
      "grad_norm": 0.35689061880111694,
      "learning_rate": 1.194385209611592e-05,
      "loss": 0.5643,
      "step": 28556
    },
    {
      "epoch": 0.8772463367431573,
      "grad_norm": 0.381534218788147,
      "learning_rate": 1.19433780348931e-05,
      "loss": 0.5538,
      "step": 28557
    },
    {
      "epoch": 0.8772770558781064,
      "grad_norm": 0.4329849183559418,
      "learning_rate": 1.1942903969131383e-05,
      "loss": 0.5573,
      "step": 28558
    },
    {
      "epoch": 0.8773077750130557,
      "grad_norm": 0.3629775047302246,
      "learning_rate": 1.1942429898831882e-05,
      "loss": 0.5248,
      "step": 28559
    },
    {
      "epoch": 0.8773384941480048,
      "grad_norm": 0.3795928359031677,
      "learning_rate": 1.19419558239957e-05,
      "loss": 0.5388,
      "step": 28560
    },
    {
      "epoch": 0.8773692132829539,
      "grad_norm": 0.3473522663116455,
      "learning_rate": 1.194148174462394e-05,
      "loss": 0.5217,
      "step": 28561
    },
    {
      "epoch": 0.8773999324179032,
      "grad_norm": 0.3514872193336487,
      "learning_rate": 1.1941007660717716e-05,
      "loss": 0.5116,
      "step": 28562
    },
    {
      "epoch": 0.8774306515528523,
      "grad_norm": 0.37163352966308594,
      "learning_rate": 1.1940533572278133e-05,
      "loss": 0.5081,
      "step": 28563
    },
    {
      "epoch": 0.8774613706878014,
      "grad_norm": 0.3957999050617218,
      "learning_rate": 1.19400594793063e-05,
      "loss": 0.5194,
      "step": 28564
    },
    {
      "epoch": 0.8774920898227506,
      "grad_norm": 0.45667317509651184,
      "learning_rate": 1.193958538180332e-05,
      "loss": 0.5765,
      "step": 28565
    },
    {
      "epoch": 0.8775228089576997,
      "grad_norm": 0.31795796751976013,
      "learning_rate": 1.1939111279770306e-05,
      "loss": 0.498,
      "step": 28566
    },
    {
      "epoch": 0.8775535280926489,
      "grad_norm": 0.3534555733203888,
      "learning_rate": 1.193863717320836e-05,
      "loss": 0.5734,
      "step": 28567
    },
    {
      "epoch": 0.8775842472275981,
      "grad_norm": 0.35697636008262634,
      "learning_rate": 1.193816306211859e-05,
      "loss": 0.5093,
      "step": 28568
    },
    {
      "epoch": 0.8776149663625472,
      "grad_norm": 0.3742774724960327,
      "learning_rate": 1.1937688946502108e-05,
      "loss": 0.5307,
      "step": 28569
    },
    {
      "epoch": 0.8776456854974964,
      "grad_norm": 0.37554365396499634,
      "learning_rate": 1.1937214826360017e-05,
      "loss": 0.5607,
      "step": 28570
    },
    {
      "epoch": 0.8776764046324456,
      "grad_norm": 0.3330083191394806,
      "learning_rate": 1.1936740701693425e-05,
      "loss": 0.534,
      "step": 28571
    },
    {
      "epoch": 0.8777071237673947,
      "grad_norm": 0.4284761846065521,
      "learning_rate": 1.1936266572503441e-05,
      "loss": 0.4816,
      "step": 28572
    },
    {
      "epoch": 0.8777378429023439,
      "grad_norm": 0.3812798857688904,
      "learning_rate": 1.1935792438791171e-05,
      "loss": 0.599,
      "step": 28573
    },
    {
      "epoch": 0.877768562037293,
      "grad_norm": 0.3909289836883545,
      "learning_rate": 1.1935318300557722e-05,
      "loss": 0.5578,
      "step": 28574
    },
    {
      "epoch": 0.8777992811722422,
      "grad_norm": 0.38519397377967834,
      "learning_rate": 1.1934844157804202e-05,
      "loss": 0.608,
      "step": 28575
    },
    {
      "epoch": 0.8778300003071914,
      "grad_norm": 0.3625744879245758,
      "learning_rate": 1.1934370010531718e-05,
      "loss": 0.5256,
      "step": 28576
    },
    {
      "epoch": 0.8778607194421405,
      "grad_norm": 0.3755088448524475,
      "learning_rate": 1.1933895858741378e-05,
      "loss": 0.5265,
      "step": 28577
    },
    {
      "epoch": 0.8778914385770896,
      "grad_norm": 0.3729977011680603,
      "learning_rate": 1.1933421702434292e-05,
      "loss": 0.4795,
      "step": 28578
    },
    {
      "epoch": 0.8779221577120389,
      "grad_norm": 0.3635970652103424,
      "learning_rate": 1.193294754161156e-05,
      "loss": 0.522,
      "step": 28579
    },
    {
      "epoch": 0.877952876846988,
      "grad_norm": 0.44820940494537354,
      "learning_rate": 1.1932473376274294e-05,
      "loss": 0.5378,
      "step": 28580
    },
    {
      "epoch": 0.8779835959819372,
      "grad_norm": 0.36792418360710144,
      "learning_rate": 1.19319992064236e-05,
      "loss": 0.5052,
      "step": 28581
    },
    {
      "epoch": 0.8780143151168863,
      "grad_norm": 0.3944654166698456,
      "learning_rate": 1.1931525032060593e-05,
      "loss": 0.5779,
      "step": 28582
    },
    {
      "epoch": 0.8780450342518354,
      "grad_norm": 0.3996855616569519,
      "learning_rate": 1.1931050853186372e-05,
      "loss": 0.5606,
      "step": 28583
    },
    {
      "epoch": 0.8780757533867847,
      "grad_norm": 0.34706252813339233,
      "learning_rate": 1.1930576669802045e-05,
      "loss": 0.5052,
      "step": 28584
    },
    {
      "epoch": 0.8781064725217338,
      "grad_norm": 0.3386700749397278,
      "learning_rate": 1.1930102481908724e-05,
      "loss": 0.5663,
      "step": 28585
    },
    {
      "epoch": 0.8781371916566829,
      "grad_norm": 0.3904951214790344,
      "learning_rate": 1.1929628289507513e-05,
      "loss": 0.6165,
      "step": 28586
    },
    {
      "epoch": 0.8781679107916321,
      "grad_norm": 0.33483460545539856,
      "learning_rate": 1.1929154092599519e-05,
      "loss": 0.5028,
      "step": 28587
    },
    {
      "epoch": 0.8781986299265813,
      "grad_norm": 0.3866231441497803,
      "learning_rate": 1.1928679891185853e-05,
      "loss": 0.5031,
      "step": 28588
    },
    {
      "epoch": 0.8782293490615304,
      "grad_norm": 0.3592565059661865,
      "learning_rate": 1.1928205685267619e-05,
      "loss": 0.5163,
      "step": 28589
    },
    {
      "epoch": 0.8782600681964796,
      "grad_norm": 0.3535676896572113,
      "learning_rate": 1.1927731474845927e-05,
      "loss": 0.5618,
      "step": 28590
    },
    {
      "epoch": 0.8782907873314287,
      "grad_norm": 0.3651736378669739,
      "learning_rate": 1.1927257259921883e-05,
      "loss": 0.4933,
      "step": 28591
    },
    {
      "epoch": 0.8783215064663779,
      "grad_norm": 0.3568408489227295,
      "learning_rate": 1.1926783040496595e-05,
      "loss": 0.5976,
      "step": 28592
    },
    {
      "epoch": 0.8783522256013271,
      "grad_norm": 0.35250362753868103,
      "learning_rate": 1.192630881657117e-05,
      "loss": 0.526,
      "step": 28593
    },
    {
      "epoch": 0.8783829447362762,
      "grad_norm": 0.32746878266334534,
      "learning_rate": 1.1925834588146719e-05,
      "loss": 0.506,
      "step": 28594
    },
    {
      "epoch": 0.8784136638712254,
      "grad_norm": 0.37152794003486633,
      "learning_rate": 1.1925360355224342e-05,
      "loss": 0.5515,
      "step": 28595
    },
    {
      "epoch": 0.8784443830061746,
      "grad_norm": 0.370459645986557,
      "learning_rate": 1.1924886117805156e-05,
      "loss": 0.6041,
      "step": 28596
    },
    {
      "epoch": 0.8784751021411237,
      "grad_norm": 0.4606618285179138,
      "learning_rate": 1.1924411875890261e-05,
      "loss": 0.521,
      "step": 28597
    },
    {
      "epoch": 0.8785058212760729,
      "grad_norm": 0.37495335936546326,
      "learning_rate": 1.1923937629480769e-05,
      "loss": 0.5727,
      "step": 28598
    },
    {
      "epoch": 0.878536540411022,
      "grad_norm": 0.38151052594184875,
      "learning_rate": 1.1923463378577783e-05,
      "loss": 0.539,
      "step": 28599
    },
    {
      "epoch": 0.8785672595459711,
      "grad_norm": 0.35542571544647217,
      "learning_rate": 1.1922989123182418e-05,
      "loss": 0.5684,
      "step": 28600
    },
    {
      "epoch": 0.8785979786809204,
      "grad_norm": 0.42323094606399536,
      "learning_rate": 1.1922514863295778e-05,
      "loss": 0.5562,
      "step": 28601
    },
    {
      "epoch": 0.8786286978158695,
      "grad_norm": 0.32956644892692566,
      "learning_rate": 1.1922040598918967e-05,
      "loss": 0.4754,
      "step": 28602
    },
    {
      "epoch": 0.8786594169508186,
      "grad_norm": 0.38022640347480774,
      "learning_rate": 1.19215663300531e-05,
      "loss": 0.4774,
      "step": 28603
    },
    {
      "epoch": 0.8786901360857678,
      "grad_norm": 0.3761645555496216,
      "learning_rate": 1.1921092056699277e-05,
      "loss": 0.5376,
      "step": 28604
    },
    {
      "epoch": 0.878720855220717,
      "grad_norm": 0.34249207377433777,
      "learning_rate": 1.1920617778858612e-05,
      "loss": 0.47,
      "step": 28605
    },
    {
      "epoch": 0.8787515743556662,
      "grad_norm": 0.4622829854488373,
      "learning_rate": 1.1920143496532207e-05,
      "loss": 0.4745,
      "step": 28606
    },
    {
      "epoch": 0.8787822934906153,
      "grad_norm": 0.3649110496044159,
      "learning_rate": 1.1919669209721176e-05,
      "loss": 0.5858,
      "step": 28607
    },
    {
      "epoch": 0.8788130126255644,
      "grad_norm": 0.3742687404155731,
      "learning_rate": 1.191919491842662e-05,
      "loss": 0.5207,
      "step": 28608
    },
    {
      "epoch": 0.8788437317605137,
      "grad_norm": 0.3561270833015442,
      "learning_rate": 1.1918720622649653e-05,
      "loss": 0.6356,
      "step": 28609
    },
    {
      "epoch": 0.8788744508954628,
      "grad_norm": 0.3974371552467346,
      "learning_rate": 1.191824632239138e-05,
      "loss": 0.4933,
      "step": 28610
    },
    {
      "epoch": 0.8789051700304119,
      "grad_norm": 0.37987181544303894,
      "learning_rate": 1.1917772017652908e-05,
      "loss": 0.5556,
      "step": 28611
    },
    {
      "epoch": 0.8789358891653611,
      "grad_norm": 0.32581794261932373,
      "learning_rate": 1.1917297708435347e-05,
      "loss": 0.5206,
      "step": 28612
    },
    {
      "epoch": 0.8789666083003103,
      "grad_norm": 0.3868493437767029,
      "learning_rate": 1.19168233947398e-05,
      "loss": 0.5035,
      "step": 28613
    },
    {
      "epoch": 0.8789973274352594,
      "grad_norm": 0.4203509986400604,
      "learning_rate": 1.1916349076567381e-05,
      "loss": 0.4833,
      "step": 28614
    },
    {
      "epoch": 0.8790280465702086,
      "grad_norm": 0.5030935406684875,
      "learning_rate": 1.1915874753919194e-05,
      "loss": 0.5325,
      "step": 28615
    },
    {
      "epoch": 0.8790587657051577,
      "grad_norm": 0.36044424772262573,
      "learning_rate": 1.1915400426796349e-05,
      "loss": 0.5424,
      "step": 28616
    },
    {
      "epoch": 0.8790894848401068,
      "grad_norm": 0.3541775345802307,
      "learning_rate": 1.1914926095199945e-05,
      "loss": 0.5101,
      "step": 28617
    },
    {
      "epoch": 0.8791202039750561,
      "grad_norm": 0.34893181920051575,
      "learning_rate": 1.1914451759131107e-05,
      "loss": 0.5187,
      "step": 28618
    },
    {
      "epoch": 0.8791509231100052,
      "grad_norm": 0.3500135838985443,
      "learning_rate": 1.191397741859093e-05,
      "loss": 0.5539,
      "step": 28619
    },
    {
      "epoch": 0.8791816422449544,
      "grad_norm": 0.34665754437446594,
      "learning_rate": 1.1913503073580524e-05,
      "loss": 0.5584,
      "step": 28620
    },
    {
      "epoch": 0.8792123613799036,
      "grad_norm": 0.39776986837387085,
      "learning_rate": 1.1913028724100998e-05,
      "loss": 0.5757,
      "step": 28621
    },
    {
      "epoch": 0.8792430805148527,
      "grad_norm": 0.3833310008049011,
      "learning_rate": 1.191255437015346e-05,
      "loss": 0.5239,
      "step": 28622
    },
    {
      "epoch": 0.8792737996498019,
      "grad_norm": 0.3801657259464264,
      "learning_rate": 1.191208001173902e-05,
      "loss": 0.5395,
      "step": 28623
    },
    {
      "epoch": 0.879304518784751,
      "grad_norm": 0.4133453667163849,
      "learning_rate": 1.191160564885878e-05,
      "loss": 0.6014,
      "step": 28624
    },
    {
      "epoch": 0.8793352379197001,
      "grad_norm": 0.34215885400772095,
      "learning_rate": 1.1911131281513855e-05,
      "loss": 0.4963,
      "step": 28625
    },
    {
      "epoch": 0.8793659570546494,
      "grad_norm": 0.3751656115055084,
      "learning_rate": 1.1910656909705348e-05,
      "loss": 0.574,
      "step": 28626
    },
    {
      "epoch": 0.8793966761895985,
      "grad_norm": 0.4515533745288849,
      "learning_rate": 1.1910182533434366e-05,
      "loss": 0.5333,
      "step": 28627
    },
    {
      "epoch": 0.8794273953245476,
      "grad_norm": 0.3326597511768341,
      "learning_rate": 1.1909708152702021e-05,
      "loss": 0.4882,
      "step": 28628
    },
    {
      "epoch": 0.8794581144594968,
      "grad_norm": 0.38516512513160706,
      "learning_rate": 1.1909233767509421e-05,
      "loss": 0.5114,
      "step": 28629
    },
    {
      "epoch": 0.879488833594446,
      "grad_norm": 0.3187645673751831,
      "learning_rate": 1.190875937785767e-05,
      "loss": 0.4843,
      "step": 28630
    },
    {
      "epoch": 0.8795195527293952,
      "grad_norm": 0.4774008095264435,
      "learning_rate": 1.190828498374788e-05,
      "loss": 0.5731,
      "step": 28631
    },
    {
      "epoch": 0.8795502718643443,
      "grad_norm": 0.35603654384613037,
      "learning_rate": 1.1907810585181157e-05,
      "loss": 0.5551,
      "step": 28632
    },
    {
      "epoch": 0.8795809909992934,
      "grad_norm": 0.3325956165790558,
      "learning_rate": 1.1907336182158607e-05,
      "loss": 0.5545,
      "step": 28633
    },
    {
      "epoch": 0.8796117101342427,
      "grad_norm": 0.41112515330314636,
      "learning_rate": 1.1906861774681342e-05,
      "loss": 0.5704,
      "step": 28634
    },
    {
      "epoch": 0.8796424292691918,
      "grad_norm": 0.33738914132118225,
      "learning_rate": 1.1906387362750467e-05,
      "loss": 0.434,
      "step": 28635
    },
    {
      "epoch": 0.8796731484041409,
      "grad_norm": 0.37980222702026367,
      "learning_rate": 1.1905912946367088e-05,
      "loss": 0.5184,
      "step": 28636
    },
    {
      "epoch": 0.8797038675390901,
      "grad_norm": 0.36841580271720886,
      "learning_rate": 1.1905438525532322e-05,
      "loss": 0.5335,
      "step": 28637
    },
    {
      "epoch": 0.8797345866740393,
      "grad_norm": 0.34749457240104675,
      "learning_rate": 1.190496410024727e-05,
      "loss": 0.4204,
      "step": 28638
    },
    {
      "epoch": 0.8797653058089884,
      "grad_norm": 0.367552250623703,
      "learning_rate": 1.190448967051304e-05,
      "loss": 0.5153,
      "step": 28639
    },
    {
      "epoch": 0.8797960249439376,
      "grad_norm": 0.4074769616127014,
      "learning_rate": 1.1904015236330741e-05,
      "loss": 0.5809,
      "step": 28640
    },
    {
      "epoch": 0.8798267440788867,
      "grad_norm": 0.35253727436065674,
      "learning_rate": 1.1903540797701482e-05,
      "loss": 0.5552,
      "step": 28641
    },
    {
      "epoch": 0.8798574632138358,
      "grad_norm": 0.39211541414260864,
      "learning_rate": 1.190306635462637e-05,
      "loss": 0.5388,
      "step": 28642
    },
    {
      "epoch": 0.8798881823487851,
      "grad_norm": 0.34538722038269043,
      "learning_rate": 1.1902591907106515e-05,
      "loss": 0.5566,
      "step": 28643
    },
    {
      "epoch": 0.8799189014837342,
      "grad_norm": 0.39662429690361023,
      "learning_rate": 1.1902117455143023e-05,
      "loss": 0.5029,
      "step": 28644
    },
    {
      "epoch": 0.8799496206186834,
      "grad_norm": 0.3844943940639496,
      "learning_rate": 1.1901642998737003e-05,
      "loss": 0.5498,
      "step": 28645
    },
    {
      "epoch": 0.8799803397536325,
      "grad_norm": 0.3470093309879303,
      "learning_rate": 1.1901168537889565e-05,
      "loss": 0.5363,
      "step": 28646
    },
    {
      "epoch": 0.8800110588885817,
      "grad_norm": 0.5061672925949097,
      "learning_rate": 1.1900694072601813e-05,
      "loss": 0.6027,
      "step": 28647
    },
    {
      "epoch": 0.8800417780235309,
      "grad_norm": 0.39393261075019836,
      "learning_rate": 1.1900219602874859e-05,
      "loss": 0.5247,
      "step": 28648
    },
    {
      "epoch": 0.88007249715848,
      "grad_norm": 0.3467022180557251,
      "learning_rate": 1.1899745128709806e-05,
      "loss": 0.4802,
      "step": 28649
    },
    {
      "epoch": 0.8801032162934291,
      "grad_norm": 0.32742562890052795,
      "learning_rate": 1.1899270650107768e-05,
      "loss": 0.4966,
      "step": 28650
    },
    {
      "epoch": 0.8801339354283784,
      "grad_norm": 0.39101552963256836,
      "learning_rate": 1.1898796167069849e-05,
      "loss": 0.5488,
      "step": 28651
    },
    {
      "epoch": 0.8801646545633275,
      "grad_norm": 0.3973555266857147,
      "learning_rate": 1.189832167959716e-05,
      "loss": 0.6389,
      "step": 28652
    },
    {
      "epoch": 0.8801953736982766,
      "grad_norm": 0.36989277601242065,
      "learning_rate": 1.1897847187690807e-05,
      "loss": 0.5872,
      "step": 28653
    },
    {
      "epoch": 0.8802260928332258,
      "grad_norm": 0.3676644265651703,
      "learning_rate": 1.1897372691351899e-05,
      "loss": 0.5593,
      "step": 28654
    },
    {
      "epoch": 0.880256811968175,
      "grad_norm": 0.3642939329147339,
      "learning_rate": 1.1896898190581547e-05,
      "loss": 0.5475,
      "step": 28655
    },
    {
      "epoch": 0.8802875311031242,
      "grad_norm": 0.4619405269622803,
      "learning_rate": 1.1896423685380856e-05,
      "loss": 0.5512,
      "step": 28656
    },
    {
      "epoch": 0.8803182502380733,
      "grad_norm": 0.3612806499004364,
      "learning_rate": 1.1895949175750934e-05,
      "loss": 0.5785,
      "step": 28657
    },
    {
      "epoch": 0.8803489693730224,
      "grad_norm": 0.3421967625617981,
      "learning_rate": 1.1895474661692893e-05,
      "loss": 0.5073,
      "step": 28658
    },
    {
      "epoch": 0.8803796885079717,
      "grad_norm": 0.3827309310436249,
      "learning_rate": 1.1895000143207835e-05,
      "loss": 0.5513,
      "step": 28659
    },
    {
      "epoch": 0.8804104076429208,
      "grad_norm": 0.43373745679855347,
      "learning_rate": 1.1894525620296874e-05,
      "loss": 0.5464,
      "step": 28660
    },
    {
      "epoch": 0.8804411267778699,
      "grad_norm": 0.4101219177246094,
      "learning_rate": 1.1894051092961117e-05,
      "loss": 0.5772,
      "step": 28661
    },
    {
      "epoch": 0.8804718459128191,
      "grad_norm": 0.36512136459350586,
      "learning_rate": 1.1893576561201667e-05,
      "loss": 0.5333,
      "step": 28662
    },
    {
      "epoch": 0.8805025650477682,
      "grad_norm": 0.4511406719684601,
      "learning_rate": 1.189310202501964e-05,
      "loss": 0.5761,
      "step": 28663
    },
    {
      "epoch": 0.8805332841827174,
      "grad_norm": 0.36611056327819824,
      "learning_rate": 1.1892627484416144e-05,
      "loss": 0.5972,
      "step": 28664
    },
    {
      "epoch": 0.8805640033176666,
      "grad_norm": 0.36712414026260376,
      "learning_rate": 1.1892152939392278e-05,
      "loss": 0.488,
      "step": 28665
    },
    {
      "epoch": 0.8805947224526157,
      "grad_norm": 0.3500593602657318,
      "learning_rate": 1.1891678389949163e-05,
      "loss": 0.5469,
      "step": 28666
    },
    {
      "epoch": 0.8806254415875648,
      "grad_norm": 0.4563599228858948,
      "learning_rate": 1.1891203836087895e-05,
      "loss": 0.6111,
      "step": 28667
    },
    {
      "epoch": 0.8806561607225141,
      "grad_norm": 0.3901461958885193,
      "learning_rate": 1.1890729277809592e-05,
      "loss": 0.554,
      "step": 28668
    },
    {
      "epoch": 0.8806868798574632,
      "grad_norm": 0.3650174140930176,
      "learning_rate": 1.1890254715115356e-05,
      "loss": 0.4978,
      "step": 28669
    },
    {
      "epoch": 0.8807175989924124,
      "grad_norm": 0.464628666639328,
      "learning_rate": 1.1889780148006303e-05,
      "loss": 0.5626,
      "step": 28670
    },
    {
      "epoch": 0.8807483181273615,
      "grad_norm": 0.3557138442993164,
      "learning_rate": 1.188930557648353e-05,
      "loss": 0.5775,
      "step": 28671
    },
    {
      "epoch": 0.8807790372623107,
      "grad_norm": 0.38642969727516174,
      "learning_rate": 1.1888831000548156e-05,
      "loss": 0.4713,
      "step": 28672
    },
    {
      "epoch": 0.8808097563972599,
      "grad_norm": 0.3766513168811798,
      "learning_rate": 1.1888356420201284e-05,
      "loss": 0.48,
      "step": 28673
    },
    {
      "epoch": 0.880840475532209,
      "grad_norm": 0.3663230240345001,
      "learning_rate": 1.1887881835444024e-05,
      "loss": 0.4769,
      "step": 28674
    },
    {
      "epoch": 0.8808711946671581,
      "grad_norm": 0.35603582859039307,
      "learning_rate": 1.1887407246277486e-05,
      "loss": 0.5024,
      "step": 28675
    },
    {
      "epoch": 0.8809019138021074,
      "grad_norm": 0.34346920251846313,
      "learning_rate": 1.1886932652702771e-05,
      "loss": 0.579,
      "step": 28676
    },
    {
      "epoch": 0.8809326329370565,
      "grad_norm": 0.47976091504096985,
      "learning_rate": 1.1886458054720999e-05,
      "loss": 0.5248,
      "step": 28677
    },
    {
      "epoch": 0.8809633520720056,
      "grad_norm": 0.34490567445755005,
      "learning_rate": 1.188598345233327e-05,
      "loss": 0.4772,
      "step": 28678
    },
    {
      "epoch": 0.8809940712069548,
      "grad_norm": 0.3299933075904846,
      "learning_rate": 1.1885508845540696e-05,
      "loss": 0.5792,
      "step": 28679
    },
    {
      "epoch": 0.881024790341904,
      "grad_norm": 0.40825533866882324,
      "learning_rate": 1.1885034234344384e-05,
      "loss": 0.5357,
      "step": 28680
    },
    {
      "epoch": 0.8810555094768532,
      "grad_norm": 0.3503306210041046,
      "learning_rate": 1.1884559618745441e-05,
      "loss": 0.5623,
      "step": 28681
    },
    {
      "epoch": 0.8810862286118023,
      "grad_norm": 0.38100486993789673,
      "learning_rate": 1.1884084998744983e-05,
      "loss": 0.6028,
      "step": 28682
    },
    {
      "epoch": 0.8811169477467514,
      "grad_norm": 0.3583396077156067,
      "learning_rate": 1.1883610374344105e-05,
      "loss": 0.5284,
      "step": 28683
    },
    {
      "epoch": 0.8811476668817007,
      "grad_norm": 0.3678629994392395,
      "learning_rate": 1.188313574554393e-05,
      "loss": 0.541,
      "step": 28684
    },
    {
      "epoch": 0.8811783860166498,
      "grad_norm": 0.3996458351612091,
      "learning_rate": 1.1882661112345555e-05,
      "loss": 0.4984,
      "step": 28685
    },
    {
      "epoch": 0.8812091051515989,
      "grad_norm": 0.32259243726730347,
      "learning_rate": 1.1882186474750098e-05,
      "loss": 0.5577,
      "step": 28686
    },
    {
      "epoch": 0.8812398242865481,
      "grad_norm": 0.43160003423690796,
      "learning_rate": 1.188171183275866e-05,
      "loss": 0.5339,
      "step": 28687
    },
    {
      "epoch": 0.8812705434214972,
      "grad_norm": 0.37618017196655273,
      "learning_rate": 1.1881237186372355e-05,
      "loss": 0.5912,
      "step": 28688
    },
    {
      "epoch": 0.8813012625564464,
      "grad_norm": 0.3858717679977417,
      "learning_rate": 1.1880762535592284e-05,
      "loss": 0.527,
      "step": 28689
    },
    {
      "epoch": 0.8813319816913956,
      "grad_norm": 0.3916114866733551,
      "learning_rate": 1.1880287880419564e-05,
      "loss": 0.5318,
      "step": 28690
    },
    {
      "epoch": 0.8813627008263447,
      "grad_norm": 0.3604762554168701,
      "learning_rate": 1.1879813220855303e-05,
      "loss": 0.5694,
      "step": 28691
    },
    {
      "epoch": 0.881393419961294,
      "grad_norm": 0.3321112394332886,
      "learning_rate": 1.1879338556900604e-05,
      "loss": 0.5324,
      "step": 28692
    },
    {
      "epoch": 0.8814241390962431,
      "grad_norm": 0.36953675746917725,
      "learning_rate": 1.1878863888556577e-05,
      "loss": 0.5384,
      "step": 28693
    },
    {
      "epoch": 0.8814548582311922,
      "grad_norm": 0.367255836725235,
      "learning_rate": 1.1878389215824335e-05,
      "loss": 0.5613,
      "step": 28694
    },
    {
      "epoch": 0.8814855773661414,
      "grad_norm": 0.39371371269226074,
      "learning_rate": 1.1877914538704984e-05,
      "loss": 0.5013,
      "step": 28695
    },
    {
      "epoch": 0.8815162965010905,
      "grad_norm": 0.3365134596824646,
      "learning_rate": 1.187743985719963e-05,
      "loss": 0.5526,
      "step": 28696
    },
    {
      "epoch": 0.8815470156360397,
      "grad_norm": 0.3779672682285309,
      "learning_rate": 1.1876965171309387e-05,
      "loss": 0.4987,
      "step": 28697
    },
    {
      "epoch": 0.8815777347709889,
      "grad_norm": 0.3641018867492676,
      "learning_rate": 1.187649048103536e-05,
      "loss": 0.5794,
      "step": 28698
    },
    {
      "epoch": 0.881608453905938,
      "grad_norm": 0.3445289134979248,
      "learning_rate": 1.1876015786378657e-05,
      "loss": 0.5815,
      "step": 28699
    },
    {
      "epoch": 0.8816391730408871,
      "grad_norm": 0.3262920677661896,
      "learning_rate": 1.187554108734039e-05,
      "loss": 0.4479,
      "step": 28700
    },
    {
      "epoch": 0.8816698921758364,
      "grad_norm": 0.33516809344291687,
      "learning_rate": 1.1875066383921662e-05,
      "loss": 0.519,
      "step": 28701
    },
    {
      "epoch": 0.8817006113107855,
      "grad_norm": 0.38956326246261597,
      "learning_rate": 1.1874591676123593e-05,
      "loss": 0.5486,
      "step": 28702
    },
    {
      "epoch": 0.8817313304457346,
      "grad_norm": 0.3897840678691864,
      "learning_rate": 1.1874116963947278e-05,
      "loss": 0.5348,
      "step": 28703
    },
    {
      "epoch": 0.8817620495806838,
      "grad_norm": 0.401876837015152,
      "learning_rate": 1.1873642247393834e-05,
      "loss": 0.5682,
      "step": 28704
    },
    {
      "epoch": 0.881792768715633,
      "grad_norm": 0.33791154623031616,
      "learning_rate": 1.1873167526464365e-05,
      "loss": 0.5273,
      "step": 28705
    },
    {
      "epoch": 0.8818234878505822,
      "grad_norm": 0.3597770035266876,
      "learning_rate": 1.1872692801159986e-05,
      "loss": 0.5851,
      "step": 28706
    },
    {
      "epoch": 0.8818542069855313,
      "grad_norm": 0.3895593583583832,
      "learning_rate": 1.18722180714818e-05,
      "loss": 0.5382,
      "step": 28707
    },
    {
      "epoch": 0.8818849261204804,
      "grad_norm": 0.3710252344608307,
      "learning_rate": 1.1871743337430917e-05,
      "loss": 0.4693,
      "step": 28708
    },
    {
      "epoch": 0.8819156452554296,
      "grad_norm": 0.3702550530433655,
      "learning_rate": 1.187126859900845e-05,
      "loss": 0.5254,
      "step": 28709
    },
    {
      "epoch": 0.8819463643903788,
      "grad_norm": 0.38882213830947876,
      "learning_rate": 1.1870793856215502e-05,
      "loss": 0.6074,
      "step": 28710
    },
    {
      "epoch": 0.8819770835253279,
      "grad_norm": 0.3779081702232361,
      "learning_rate": 1.1870319109053185e-05,
      "loss": 0.5812,
      "step": 28711
    },
    {
      "epoch": 0.8820078026602771,
      "grad_norm": 0.3579406440258026,
      "learning_rate": 1.1869844357522607e-05,
      "loss": 0.5453,
      "step": 28712
    },
    {
      "epoch": 0.8820385217952262,
      "grad_norm": 0.36059561371803284,
      "learning_rate": 1.1869369601624875e-05,
      "loss": 0.5311,
      "step": 28713
    },
    {
      "epoch": 0.8820692409301754,
      "grad_norm": 0.3890632390975952,
      "learning_rate": 1.1868894841361102e-05,
      "loss": 0.6484,
      "step": 28714
    },
    {
      "epoch": 0.8820999600651246,
      "grad_norm": 0.39460521936416626,
      "learning_rate": 1.1868420076732396e-05,
      "loss": 0.5161,
      "step": 28715
    },
    {
      "epoch": 0.8821306792000737,
      "grad_norm": 0.8755515813827515,
      "learning_rate": 1.1867945307739865e-05,
      "loss": 0.5274,
      "step": 28716
    },
    {
      "epoch": 0.8821613983350229,
      "grad_norm": 0.4122254550457001,
      "learning_rate": 1.1867470534384613e-05,
      "loss": 0.5536,
      "step": 28717
    },
    {
      "epoch": 0.8821921174699721,
      "grad_norm": 0.4169957935810089,
      "learning_rate": 1.1866995756667757e-05,
      "loss": 0.5137,
      "step": 28718
    },
    {
      "epoch": 0.8822228366049212,
      "grad_norm": 0.3940141499042511,
      "learning_rate": 1.1866520974590399e-05,
      "loss": 0.5857,
      "step": 28719
    },
    {
      "epoch": 0.8822535557398704,
      "grad_norm": 0.3529159724712372,
      "learning_rate": 1.1866046188153653e-05,
      "loss": 0.6296,
      "step": 28720
    },
    {
      "epoch": 0.8822842748748195,
      "grad_norm": 0.3536147177219391,
      "learning_rate": 1.1865571397358623e-05,
      "loss": 0.5842,
      "step": 28721
    },
    {
      "epoch": 0.8823149940097686,
      "grad_norm": 0.3866824805736542,
      "learning_rate": 1.1865096602206426e-05,
      "loss": 0.5433,
      "step": 28722
    },
    {
      "epoch": 0.8823457131447179,
      "grad_norm": 0.40439629554748535,
      "learning_rate": 1.186462180269816e-05,
      "loss": 0.5538,
      "step": 28723
    },
    {
      "epoch": 0.882376432279667,
      "grad_norm": 0.33019500970840454,
      "learning_rate": 1.1864146998834944e-05,
      "loss": 0.5544,
      "step": 28724
    },
    {
      "epoch": 0.8824071514146161,
      "grad_norm": 0.4458649754524231,
      "learning_rate": 1.1863672190617878e-05,
      "loss": 0.5669,
      "step": 28725
    },
    {
      "epoch": 0.8824378705495654,
      "grad_norm": 0.3443959653377533,
      "learning_rate": 1.1863197378048077e-05,
      "loss": 0.5731,
      "step": 28726
    },
    {
      "epoch": 0.8824685896845145,
      "grad_norm": 0.36838939785957336,
      "learning_rate": 1.1862722561126652e-05,
      "loss": 0.504,
      "step": 28727
    },
    {
      "epoch": 0.8824993088194636,
      "grad_norm": 0.3484560549259186,
      "learning_rate": 1.1862247739854704e-05,
      "loss": 0.5707,
      "step": 28728
    },
    {
      "epoch": 0.8825300279544128,
      "grad_norm": 0.36207062005996704,
      "learning_rate": 1.1861772914233349e-05,
      "loss": 0.4897,
      "step": 28729
    },
    {
      "epoch": 0.8825607470893619,
      "grad_norm": 0.362156480550766,
      "learning_rate": 1.186129808426369e-05,
      "loss": 0.5217,
      "step": 28730
    },
    {
      "epoch": 0.8825914662243112,
      "grad_norm": 0.323417991399765,
      "learning_rate": 1.1860823249946842e-05,
      "loss": 0.5372,
      "step": 28731
    },
    {
      "epoch": 0.8826221853592603,
      "grad_norm": 0.36482182145118713,
      "learning_rate": 1.186034841128391e-05,
      "loss": 0.5452,
      "step": 28732
    },
    {
      "epoch": 0.8826529044942094,
      "grad_norm": 0.3593558371067047,
      "learning_rate": 1.1859873568276008e-05,
      "loss": 0.4984,
      "step": 28733
    },
    {
      "epoch": 0.8826836236291586,
      "grad_norm": 0.34719082713127136,
      "learning_rate": 1.185939872092424e-05,
      "loss": 0.5455,
      "step": 28734
    },
    {
      "epoch": 0.8827143427641078,
      "grad_norm": 0.39127615094184875,
      "learning_rate": 1.1858923869229712e-05,
      "loss": 0.61,
      "step": 28735
    },
    {
      "epoch": 0.8827450618990569,
      "grad_norm": 0.35191357135772705,
      "learning_rate": 1.1858449013193543e-05,
      "loss": 0.5888,
      "step": 28736
    },
    {
      "epoch": 0.8827757810340061,
      "grad_norm": 0.33052492141723633,
      "learning_rate": 1.1857974152816834e-05,
      "loss": 0.511,
      "step": 28737
    },
    {
      "epoch": 0.8828065001689552,
      "grad_norm": 0.40897446870803833,
      "learning_rate": 1.1857499288100698e-05,
      "loss": 0.5908,
      "step": 28738
    },
    {
      "epoch": 0.8828372193039044,
      "grad_norm": 0.32562682032585144,
      "learning_rate": 1.185702441904624e-05,
      "loss": 0.4617,
      "step": 28739
    },
    {
      "epoch": 0.8828679384388536,
      "grad_norm": 0.4204212725162506,
      "learning_rate": 1.1856549545654574e-05,
      "loss": 0.5623,
      "step": 28740
    },
    {
      "epoch": 0.8828986575738027,
      "grad_norm": 0.3367350101470947,
      "learning_rate": 1.1856074667926804e-05,
      "loss": 0.5117,
      "step": 28741
    },
    {
      "epoch": 0.8829293767087519,
      "grad_norm": 0.3556893765926361,
      "learning_rate": 1.1855599785864046e-05,
      "loss": 0.5141,
      "step": 28742
    },
    {
      "epoch": 0.882960095843701,
      "grad_norm": 0.33450549840927124,
      "learning_rate": 1.1855124899467402e-05,
      "loss": 0.5119,
      "step": 28743
    },
    {
      "epoch": 0.8829908149786502,
      "grad_norm": 0.373088002204895,
      "learning_rate": 1.1854650008737987e-05,
      "loss": 0.5444,
      "step": 28744
    },
    {
      "epoch": 0.8830215341135994,
      "grad_norm": 0.3712841868400574,
      "learning_rate": 1.1854175113676904e-05,
      "loss": 0.4562,
      "step": 28745
    },
    {
      "epoch": 0.8830522532485485,
      "grad_norm": 0.46100085973739624,
      "learning_rate": 1.1853700214285266e-05,
      "loss": 0.5369,
      "step": 28746
    },
    {
      "epoch": 0.8830829723834976,
      "grad_norm": 0.3749023973941803,
      "learning_rate": 1.1853225310564185e-05,
      "loss": 0.5591,
      "step": 28747
    },
    {
      "epoch": 0.8831136915184469,
      "grad_norm": 0.3326268196105957,
      "learning_rate": 1.1852750402514764e-05,
      "loss": 0.4532,
      "step": 28748
    },
    {
      "epoch": 0.883144410653396,
      "grad_norm": 0.45694220066070557,
      "learning_rate": 1.1852275490138117e-05,
      "loss": 0.4776,
      "step": 28749
    },
    {
      "epoch": 0.8831751297883451,
      "grad_norm": 0.7791348099708557,
      "learning_rate": 1.1851800573435348e-05,
      "loss": 0.6184,
      "step": 28750
    },
    {
      "epoch": 0.8832058489232943,
      "grad_norm": 0.38931572437286377,
      "learning_rate": 1.1851325652407573e-05,
      "loss": 0.6274,
      "step": 28751
    },
    {
      "epoch": 0.8832365680582435,
      "grad_norm": 0.3477408289909363,
      "learning_rate": 1.1850850727055897e-05,
      "loss": 0.5642,
      "step": 28752
    },
    {
      "epoch": 0.8832672871931926,
      "grad_norm": 0.40969350934028625,
      "learning_rate": 1.1850375797381429e-05,
      "loss": 0.5655,
      "step": 28753
    },
    {
      "epoch": 0.8832980063281418,
      "grad_norm": 0.4214032292366028,
      "learning_rate": 1.1849900863385279e-05,
      "loss": 0.5081,
      "step": 28754
    },
    {
      "epoch": 0.8833287254630909,
      "grad_norm": 0.3468281924724579,
      "learning_rate": 1.1849425925068557e-05,
      "loss": 0.6204,
      "step": 28755
    },
    {
      "epoch": 0.8833594445980402,
      "grad_norm": 0.38827022910118103,
      "learning_rate": 1.1848950982432373e-05,
      "loss": 0.5467,
      "step": 28756
    },
    {
      "epoch": 0.8833901637329893,
      "grad_norm": 0.36806589365005493,
      "learning_rate": 1.1848476035477829e-05,
      "loss": 0.5659,
      "step": 28757
    },
    {
      "epoch": 0.8834208828679384,
      "grad_norm": 0.39305374026298523,
      "learning_rate": 1.1848001084206046e-05,
      "loss": 0.5919,
      "step": 28758
    },
    {
      "epoch": 0.8834516020028876,
      "grad_norm": 0.3684200942516327,
      "learning_rate": 1.1847526128618125e-05,
      "loss": 0.4748,
      "step": 28759
    },
    {
      "epoch": 0.8834823211378368,
      "grad_norm": 0.3696395754814148,
      "learning_rate": 1.184705116871518e-05,
      "loss": 0.5955,
      "step": 28760
    },
    {
      "epoch": 0.8835130402727859,
      "grad_norm": 0.413555771112442,
      "learning_rate": 1.1846576204498314e-05,
      "loss": 0.471,
      "step": 28761
    },
    {
      "epoch": 0.8835437594077351,
      "grad_norm": 0.37124308943748474,
      "learning_rate": 1.1846101235968643e-05,
      "loss": 0.5942,
      "step": 28762
    },
    {
      "epoch": 0.8835744785426842,
      "grad_norm": 0.36381593346595764,
      "learning_rate": 1.1845626263127272e-05,
      "loss": 0.5295,
      "step": 28763
    },
    {
      "epoch": 0.8836051976776333,
      "grad_norm": 0.3212294578552246,
      "learning_rate": 1.1845151285975313e-05,
      "loss": 0.55,
      "step": 28764
    },
    {
      "epoch": 0.8836359168125826,
      "grad_norm": 0.35492080450057983,
      "learning_rate": 1.1844676304513875e-05,
      "loss": 0.544,
      "step": 28765
    },
    {
      "epoch": 0.8836666359475317,
      "grad_norm": 0.39948591589927673,
      "learning_rate": 1.1844201318744067e-05,
      "loss": 0.6257,
      "step": 28766
    },
    {
      "epoch": 0.8836973550824809,
      "grad_norm": 0.36700770258903503,
      "learning_rate": 1.1843726328666996e-05,
      "loss": 0.5929,
      "step": 28767
    },
    {
      "epoch": 0.88372807421743,
      "grad_norm": 0.3481409251689911,
      "learning_rate": 1.1843251334283777e-05,
      "loss": 0.5464,
      "step": 28768
    },
    {
      "epoch": 0.8837587933523792,
      "grad_norm": 0.39146941900253296,
      "learning_rate": 1.1842776335595511e-05,
      "loss": 0.5628,
      "step": 28769
    },
    {
      "epoch": 0.8837895124873284,
      "grad_norm": 0.3741774559020996,
      "learning_rate": 1.1842301332603317e-05,
      "loss": 0.5903,
      "step": 28770
    },
    {
      "epoch": 0.8838202316222775,
      "grad_norm": 0.3912888467311859,
      "learning_rate": 1.1841826325308294e-05,
      "loss": 0.5943,
      "step": 28771
    },
    {
      "epoch": 0.8838509507572266,
      "grad_norm": 0.3673592507839203,
      "learning_rate": 1.1841351313711562e-05,
      "loss": 0.551,
      "step": 28772
    },
    {
      "epoch": 0.8838816698921759,
      "grad_norm": 0.39287981390953064,
      "learning_rate": 1.1840876297814221e-05,
      "loss": 0.4959,
      "step": 28773
    },
    {
      "epoch": 0.883912389027125,
      "grad_norm": 0.401985228061676,
      "learning_rate": 1.184040127761739e-05,
      "loss": 0.529,
      "step": 28774
    },
    {
      "epoch": 0.8839431081620741,
      "grad_norm": 0.39204224944114685,
      "learning_rate": 1.1839926253122169e-05,
      "loss": 0.5354,
      "step": 28775
    },
    {
      "epoch": 0.8839738272970233,
      "grad_norm": 0.5625383257865906,
      "learning_rate": 1.1839451224329675e-05,
      "loss": 0.673,
      "step": 28776
    },
    {
      "epoch": 0.8840045464319725,
      "grad_norm": 0.4214898347854614,
      "learning_rate": 1.1838976191241009e-05,
      "loss": 0.5701,
      "step": 28777
    },
    {
      "epoch": 0.8840352655669217,
      "grad_norm": 0.3759685456752777,
      "learning_rate": 1.1838501153857292e-05,
      "loss": 0.5224,
      "step": 28778
    },
    {
      "epoch": 0.8840659847018708,
      "grad_norm": 0.3629912734031677,
      "learning_rate": 1.1838026112179626e-05,
      "loss": 0.5447,
      "step": 28779
    },
    {
      "epoch": 0.8840967038368199,
      "grad_norm": 0.38633570075035095,
      "learning_rate": 1.1837551066209119e-05,
      "loss": 0.5548,
      "step": 28780
    },
    {
      "epoch": 0.8841274229717692,
      "grad_norm": 0.36346718668937683,
      "learning_rate": 1.1837076015946883e-05,
      "loss": 0.596,
      "step": 28781
    },
    {
      "epoch": 0.8841581421067183,
      "grad_norm": 0.35284578800201416,
      "learning_rate": 1.1836600961394028e-05,
      "loss": 0.5783,
      "step": 28782
    },
    {
      "epoch": 0.8841888612416674,
      "grad_norm": 0.38617607951164246,
      "learning_rate": 1.1836125902551663e-05,
      "loss": 0.4886,
      "step": 28783
    },
    {
      "epoch": 0.8842195803766166,
      "grad_norm": 0.38138607144355774,
      "learning_rate": 1.1835650839420898e-05,
      "loss": 0.5182,
      "step": 28784
    },
    {
      "epoch": 0.8842502995115658,
      "grad_norm": 0.3860319256782532,
      "learning_rate": 1.1835175772002845e-05,
      "loss": 0.5026,
      "step": 28785
    },
    {
      "epoch": 0.8842810186465149,
      "grad_norm": 0.391011118888855,
      "learning_rate": 1.183470070029861e-05,
      "loss": 0.6034,
      "step": 28786
    },
    {
      "epoch": 0.8843117377814641,
      "grad_norm": 0.33110031485557556,
      "learning_rate": 1.18342256243093e-05,
      "loss": 0.5492,
      "step": 28787
    },
    {
      "epoch": 0.8843424569164132,
      "grad_norm": 0.3818282186985016,
      "learning_rate": 1.1833750544036031e-05,
      "loss": 0.6004,
      "step": 28788
    },
    {
      "epoch": 0.8843731760513623,
      "grad_norm": 0.3694525957107544,
      "learning_rate": 1.1833275459479908e-05,
      "loss": 0.5803,
      "step": 28789
    },
    {
      "epoch": 0.8844038951863116,
      "grad_norm": 0.37546443939208984,
      "learning_rate": 1.1832800370642044e-05,
      "loss": 0.6078,
      "step": 28790
    },
    {
      "epoch": 0.8844346143212607,
      "grad_norm": 0.3564591407775879,
      "learning_rate": 1.1832325277523544e-05,
      "loss": 0.5487,
      "step": 28791
    },
    {
      "epoch": 0.8844653334562099,
      "grad_norm": 0.3522203266620636,
      "learning_rate": 1.1831850180125523e-05,
      "loss": 0.5543,
      "step": 28792
    },
    {
      "epoch": 0.884496052591159,
      "grad_norm": 0.36349377036094666,
      "learning_rate": 1.1831375078449086e-05,
      "loss": 0.5465,
      "step": 28793
    },
    {
      "epoch": 0.8845267717261082,
      "grad_norm": 0.3836571276187897,
      "learning_rate": 1.1830899972495347e-05,
      "loss": 0.4777,
      "step": 28794
    },
    {
      "epoch": 0.8845574908610574,
      "grad_norm": 0.38532698154449463,
      "learning_rate": 1.183042486226541e-05,
      "loss": 0.5432,
      "step": 28795
    },
    {
      "epoch": 0.8845882099960065,
      "grad_norm": 0.3695721924304962,
      "learning_rate": 1.182994974776039e-05,
      "loss": 0.5144,
      "step": 28796
    },
    {
      "epoch": 0.8846189291309556,
      "grad_norm": 0.41050317883491516,
      "learning_rate": 1.1829474628981396e-05,
      "loss": 0.573,
      "step": 28797
    },
    {
      "epoch": 0.8846496482659049,
      "grad_norm": 0.3702645003795624,
      "learning_rate": 1.1828999505929532e-05,
      "loss": 0.5807,
      "step": 28798
    },
    {
      "epoch": 0.884680367400854,
      "grad_norm": 0.35607168078422546,
      "learning_rate": 1.1828524378605915e-05,
      "loss": 0.5477,
      "step": 28799
    },
    {
      "epoch": 0.8847110865358031,
      "grad_norm": 0.41972827911376953,
      "learning_rate": 1.1828049247011648e-05,
      "loss": 0.5455,
      "step": 28800
    },
    {
      "epoch": 0.8847418056707523,
      "grad_norm": 0.42780107259750366,
      "learning_rate": 1.182757411114785e-05,
      "loss": 0.5099,
      "step": 28801
    },
    {
      "epoch": 0.8847725248057015,
      "grad_norm": 0.3645953834056854,
      "learning_rate": 1.182709897101562e-05,
      "loss": 0.5381,
      "step": 28802
    },
    {
      "epoch": 0.8848032439406507,
      "grad_norm": 0.44355931878089905,
      "learning_rate": 1.1826623826616078e-05,
      "loss": 0.516,
      "step": 28803
    },
    {
      "epoch": 0.8848339630755998,
      "grad_norm": 0.33103883266448975,
      "learning_rate": 1.1826148677950324e-05,
      "loss": 0.5217,
      "step": 28804
    },
    {
      "epoch": 0.8848646822105489,
      "grad_norm": 0.3815517723560333,
      "learning_rate": 1.1825673525019475e-05,
      "loss": 0.6246,
      "step": 28805
    },
    {
      "epoch": 0.8848954013454982,
      "grad_norm": 0.34079280495643616,
      "learning_rate": 1.1825198367824634e-05,
      "loss": 0.4922,
      "step": 28806
    },
    {
      "epoch": 0.8849261204804473,
      "grad_norm": 0.436113178730011,
      "learning_rate": 1.182472320636692e-05,
      "loss": 0.5269,
      "step": 28807
    },
    {
      "epoch": 0.8849568396153964,
      "grad_norm": 0.42847123742103577,
      "learning_rate": 1.1824248040647435e-05,
      "loss": 0.526,
      "step": 28808
    },
    {
      "epoch": 0.8849875587503456,
      "grad_norm": 0.3636466860771179,
      "learning_rate": 1.182377287066729e-05,
      "loss": 0.6308,
      "step": 28809
    },
    {
      "epoch": 0.8850182778852947,
      "grad_norm": 0.7543382048606873,
      "learning_rate": 1.1823297696427598e-05,
      "loss": 0.5615,
      "step": 28810
    },
    {
      "epoch": 0.8850489970202439,
      "grad_norm": 0.4106084108352661,
      "learning_rate": 1.1822822517929464e-05,
      "loss": 0.6541,
      "step": 28811
    },
    {
      "epoch": 0.8850797161551931,
      "grad_norm": 0.38661712408065796,
      "learning_rate": 1.1822347335174004e-05,
      "loss": 0.5119,
      "step": 28812
    },
    {
      "epoch": 0.8851104352901422,
      "grad_norm": 0.35872945189476013,
      "learning_rate": 1.1821872148162323e-05,
      "loss": 0.5277,
      "step": 28813
    },
    {
      "epoch": 0.8851411544250913,
      "grad_norm": 0.4016355276107788,
      "learning_rate": 1.1821396956895534e-05,
      "loss": 0.596,
      "step": 28814
    },
    {
      "epoch": 0.8851718735600406,
      "grad_norm": 0.37546518445014954,
      "learning_rate": 1.1820921761374746e-05,
      "loss": 0.4886,
      "step": 28815
    },
    {
      "epoch": 0.8852025926949897,
      "grad_norm": 0.3714987635612488,
      "learning_rate": 1.1820446561601064e-05,
      "loss": 0.5466,
      "step": 28816
    },
    {
      "epoch": 0.8852333118299389,
      "grad_norm": 0.3532666265964508,
      "learning_rate": 1.1819971357575605e-05,
      "loss": 0.5692,
      "step": 28817
    },
    {
      "epoch": 0.885264030964888,
      "grad_norm": 0.3860808312892914,
      "learning_rate": 1.1819496149299472e-05,
      "loss": 0.5457,
      "step": 28818
    },
    {
      "epoch": 0.8852947500998372,
      "grad_norm": 0.750840961933136,
      "learning_rate": 1.1819020936773782e-05,
      "loss": 0.5153,
      "step": 28819
    },
    {
      "epoch": 0.8853254692347864,
      "grad_norm": 0.35707929730415344,
      "learning_rate": 1.1818545719999644e-05,
      "loss": 0.6053,
      "step": 28820
    },
    {
      "epoch": 0.8853561883697355,
      "grad_norm": 0.33397117257118225,
      "learning_rate": 1.181807049897816e-05,
      "loss": 0.5514,
      "step": 28821
    },
    {
      "epoch": 0.8853869075046846,
      "grad_norm": 0.3286038339138031,
      "learning_rate": 1.181759527371045e-05,
      "loss": 0.4947,
      "step": 28822
    },
    {
      "epoch": 0.8854176266396339,
      "grad_norm": 0.34672755002975464,
      "learning_rate": 1.1817120044197614e-05,
      "loss": 0.5543,
      "step": 28823
    },
    {
      "epoch": 0.885448345774583,
      "grad_norm": 0.40215668082237244,
      "learning_rate": 1.1816644810440772e-05,
      "loss": 0.5958,
      "step": 28824
    },
    {
      "epoch": 0.8854790649095321,
      "grad_norm": 0.37266805768013,
      "learning_rate": 1.1816169572441028e-05,
      "loss": 0.6229,
      "step": 28825
    },
    {
      "epoch": 0.8855097840444813,
      "grad_norm": 0.3461994528770447,
      "learning_rate": 1.1815694330199492e-05,
      "loss": 0.5167,
      "step": 28826
    },
    {
      "epoch": 0.8855405031794304,
      "grad_norm": 0.41044309735298157,
      "learning_rate": 1.1815219083717276e-05,
      "loss": 0.5545,
      "step": 28827
    },
    {
      "epoch": 0.8855712223143797,
      "grad_norm": 0.4606837332248688,
      "learning_rate": 1.1814743832995489e-05,
      "loss": 0.5116,
      "step": 28828
    },
    {
      "epoch": 0.8856019414493288,
      "grad_norm": 0.3953881859779358,
      "learning_rate": 1.181426857803524e-05,
      "loss": 0.5922,
      "step": 28829
    },
    {
      "epoch": 0.8856326605842779,
      "grad_norm": 0.37313157320022583,
      "learning_rate": 1.1813793318837641e-05,
      "loss": 0.5682,
      "step": 28830
    },
    {
      "epoch": 0.8856633797192272,
      "grad_norm": 0.4100241959095001,
      "learning_rate": 1.1813318055403802e-05,
      "loss": 0.5701,
      "step": 28831
    },
    {
      "epoch": 0.8856940988541763,
      "grad_norm": 0.3765318691730499,
      "learning_rate": 1.181284278773483e-05,
      "loss": 0.5837,
      "step": 28832
    },
    {
      "epoch": 0.8857248179891254,
      "grad_norm": 0.34791240096092224,
      "learning_rate": 1.181236751583184e-05,
      "loss": 0.5616,
      "step": 28833
    },
    {
      "epoch": 0.8857555371240746,
      "grad_norm": 0.3547991216182709,
      "learning_rate": 1.1811892239695934e-05,
      "loss": 0.5498,
      "step": 28834
    },
    {
      "epoch": 0.8857862562590237,
      "grad_norm": 0.3860110938549042,
      "learning_rate": 1.1811416959328232e-05,
      "loss": 0.5278,
      "step": 28835
    },
    {
      "epoch": 0.8858169753939729,
      "grad_norm": 0.3757220208644867,
      "learning_rate": 1.1810941674729835e-05,
      "loss": 0.5593,
      "step": 28836
    },
    {
      "epoch": 0.8858476945289221,
      "grad_norm": 0.3734588921070099,
      "learning_rate": 1.181046638590186e-05,
      "loss": 0.5274,
      "step": 28837
    },
    {
      "epoch": 0.8858784136638712,
      "grad_norm": 0.36524927616119385,
      "learning_rate": 1.1809991092845417e-05,
      "loss": 0.6405,
      "step": 28838
    },
    {
      "epoch": 0.8859091327988203,
      "grad_norm": 0.3494725227355957,
      "learning_rate": 1.1809515795561608e-05,
      "loss": 0.5825,
      "step": 28839
    },
    {
      "epoch": 0.8859398519337696,
      "grad_norm": 0.3887060880661011,
      "learning_rate": 1.1809040494051551e-05,
      "loss": 0.5155,
      "step": 28840
    },
    {
      "epoch": 0.8859705710687187,
      "grad_norm": 0.41668763756752014,
      "learning_rate": 1.1808565188316353e-05,
      "loss": 0.6821,
      "step": 28841
    },
    {
      "epoch": 0.8860012902036679,
      "grad_norm": 0.36746782064437866,
      "learning_rate": 1.1808089878357128e-05,
      "loss": 0.4987,
      "step": 28842
    },
    {
      "epoch": 0.886032009338617,
      "grad_norm": 0.35515421628952026,
      "learning_rate": 1.1807614564174977e-05,
      "loss": 0.5907,
      "step": 28843
    },
    {
      "epoch": 0.8860627284735662,
      "grad_norm": 0.45503389835357666,
      "learning_rate": 1.180713924577102e-05,
      "loss": 0.493,
      "step": 28844
    },
    {
      "epoch": 0.8860934476085154,
      "grad_norm": 0.43905001878738403,
      "learning_rate": 1.180666392314636e-05,
      "loss": 0.538,
      "step": 28845
    },
    {
      "epoch": 0.8861241667434645,
      "grad_norm": 0.36361634731292725,
      "learning_rate": 1.1806188596302116e-05,
      "loss": 0.5835,
      "step": 28846
    },
    {
      "epoch": 0.8861548858784136,
      "grad_norm": 0.39485684037208557,
      "learning_rate": 1.1805713265239384e-05,
      "loss": 0.6087,
      "step": 28847
    },
    {
      "epoch": 0.8861856050133629,
      "grad_norm": 0.3865734934806824,
      "learning_rate": 1.180523792995929e-05,
      "loss": 0.6201,
      "step": 28848
    },
    {
      "epoch": 0.886216324148312,
      "grad_norm": 0.3799424469470978,
      "learning_rate": 1.1804762590462934e-05,
      "loss": 0.5061,
      "step": 28849
    },
    {
      "epoch": 0.8862470432832611,
      "grad_norm": 0.34630098938941956,
      "learning_rate": 1.1804287246751429e-05,
      "loss": 0.5378,
      "step": 28850
    },
    {
      "epoch": 0.8862777624182103,
      "grad_norm": 0.38220685720443726,
      "learning_rate": 1.1803811898825885e-05,
      "loss": 0.5267,
      "step": 28851
    },
    {
      "epoch": 0.8863084815531594,
      "grad_norm": 0.38606616854667664,
      "learning_rate": 1.1803336546687412e-05,
      "loss": 0.5237,
      "step": 28852
    },
    {
      "epoch": 0.8863392006881087,
      "grad_norm": 0.3509537875652313,
      "learning_rate": 1.1802861190337121e-05,
      "loss": 0.5436,
      "step": 28853
    },
    {
      "epoch": 0.8863699198230578,
      "grad_norm": 0.3782220482826233,
      "learning_rate": 1.180238582977612e-05,
      "loss": 0.6328,
      "step": 28854
    },
    {
      "epoch": 0.8864006389580069,
      "grad_norm": 0.3503873646259308,
      "learning_rate": 1.1801910465005522e-05,
      "loss": 0.5109,
      "step": 28855
    },
    {
      "epoch": 0.8864313580929561,
      "grad_norm": 0.37204936146736145,
      "learning_rate": 1.1801435096026439e-05,
      "loss": 0.5252,
      "step": 28856
    },
    {
      "epoch": 0.8864620772279053,
      "grad_norm": 0.4351598024368286,
      "learning_rate": 1.1800959722839976e-05,
      "loss": 0.649,
      "step": 28857
    },
    {
      "epoch": 0.8864927963628544,
      "grad_norm": 0.346413254737854,
      "learning_rate": 1.1800484345447245e-05,
      "loss": 0.5295,
      "step": 28858
    },
    {
      "epoch": 0.8865235154978036,
      "grad_norm": 0.37163859605789185,
      "learning_rate": 1.1800008963849359e-05,
      "loss": 0.5704,
      "step": 28859
    },
    {
      "epoch": 0.8865542346327527,
      "grad_norm": 0.38946276903152466,
      "learning_rate": 1.1799533578047426e-05,
      "loss": 0.581,
      "step": 28860
    },
    {
      "epoch": 0.8865849537677019,
      "grad_norm": 0.38705602288246155,
      "learning_rate": 1.1799058188042556e-05,
      "loss": 0.6221,
      "step": 28861
    },
    {
      "epoch": 0.8866156729026511,
      "grad_norm": 0.35668689012527466,
      "learning_rate": 1.179858279383586e-05,
      "loss": 0.5479,
      "step": 28862
    },
    {
      "epoch": 0.8866463920376002,
      "grad_norm": 0.38796642422676086,
      "learning_rate": 1.1798107395428448e-05,
      "loss": 0.5316,
      "step": 28863
    },
    {
      "epoch": 0.8866771111725493,
      "grad_norm": 0.3858502507209778,
      "learning_rate": 1.1797631992821433e-05,
      "loss": 0.5441,
      "step": 28864
    },
    {
      "epoch": 0.8867078303074986,
      "grad_norm": 0.32650160789489746,
      "learning_rate": 1.1797156586015918e-05,
      "loss": 0.5813,
      "step": 28865
    },
    {
      "epoch": 0.8867385494424477,
      "grad_norm": 0.39082103967666626,
      "learning_rate": 1.1796681175013022e-05,
      "loss": 0.4115,
      "step": 28866
    },
    {
      "epoch": 0.8867692685773969,
      "grad_norm": 0.4091886579990387,
      "learning_rate": 1.1796205759813852e-05,
      "loss": 0.5397,
      "step": 28867
    },
    {
      "epoch": 0.886799987712346,
      "grad_norm": 0.35487100481987,
      "learning_rate": 1.1795730340419518e-05,
      "loss": 0.4984,
      "step": 28868
    },
    {
      "epoch": 0.8868307068472951,
      "grad_norm": 0.37216314673423767,
      "learning_rate": 1.179525491683113e-05,
      "loss": 0.5791,
      "step": 28869
    },
    {
      "epoch": 0.8868614259822444,
      "grad_norm": 0.37191838026046753,
      "learning_rate": 1.1794779489049797e-05,
      "loss": 0.5489,
      "step": 28870
    },
    {
      "epoch": 0.8868921451171935,
      "grad_norm": 0.4429958462715149,
      "learning_rate": 1.1794304057076633e-05,
      "loss": 0.6287,
      "step": 28871
    },
    {
      "epoch": 0.8869228642521426,
      "grad_norm": 0.40547290444374084,
      "learning_rate": 1.1793828620912744e-05,
      "loss": 0.5487,
      "step": 28872
    },
    {
      "epoch": 0.8869535833870918,
      "grad_norm": 0.35442492365837097,
      "learning_rate": 1.1793353180559245e-05,
      "loss": 0.5822,
      "step": 28873
    },
    {
      "epoch": 0.886984302522041,
      "grad_norm": 0.33529505133628845,
      "learning_rate": 1.1792877736017245e-05,
      "loss": 0.5254,
      "step": 28874
    },
    {
      "epoch": 0.8870150216569901,
      "grad_norm": 0.36264997720718384,
      "learning_rate": 1.1792402287287853e-05,
      "loss": 0.6282,
      "step": 28875
    },
    {
      "epoch": 0.8870457407919393,
      "grad_norm": 0.39809656143188477,
      "learning_rate": 1.179192683437218e-05,
      "loss": 0.5299,
      "step": 28876
    },
    {
      "epoch": 0.8870764599268884,
      "grad_norm": 0.4114306569099426,
      "learning_rate": 1.1791451377271334e-05,
      "loss": 0.607,
      "step": 28877
    },
    {
      "epoch": 0.8871071790618377,
      "grad_norm": 0.36931073665618896,
      "learning_rate": 1.1790975915986433e-05,
      "loss": 0.5135,
      "step": 28878
    },
    {
      "epoch": 0.8871378981967868,
      "grad_norm": 0.33933210372924805,
      "learning_rate": 1.1790500450518581e-05,
      "loss": 0.5566,
      "step": 28879
    },
    {
      "epoch": 0.8871686173317359,
      "grad_norm": 0.3626555800437927,
      "learning_rate": 1.179002498086889e-05,
      "loss": 0.5141,
      "step": 28880
    },
    {
      "epoch": 0.8871993364666851,
      "grad_norm": 0.3304084241390228,
      "learning_rate": 1.1789549507038471e-05,
      "loss": 0.5892,
      "step": 28881
    },
    {
      "epoch": 0.8872300556016343,
      "grad_norm": 0.38880956172943115,
      "learning_rate": 1.1789074029028433e-05,
      "loss": 0.5906,
      "step": 28882
    },
    {
      "epoch": 0.8872607747365834,
      "grad_norm": 0.3740380108356476,
      "learning_rate": 1.178859854683989e-05,
      "loss": 0.5353,
      "step": 28883
    },
    {
      "epoch": 0.8872914938715326,
      "grad_norm": 0.4566633105278015,
      "learning_rate": 1.1788123060473949e-05,
      "loss": 0.572,
      "step": 28884
    },
    {
      "epoch": 0.8873222130064817,
      "grad_norm": 0.7962703108787537,
      "learning_rate": 1.1787647569931722e-05,
      "loss": 0.5455,
      "step": 28885
    },
    {
      "epoch": 0.8873529321414309,
      "grad_norm": 0.3480527400970459,
      "learning_rate": 1.1787172075214316e-05,
      "loss": 0.5507,
      "step": 28886
    },
    {
      "epoch": 0.8873836512763801,
      "grad_norm": 0.35639697313308716,
      "learning_rate": 1.178669657632285e-05,
      "loss": 0.6104,
      "step": 28887
    },
    {
      "epoch": 0.8874143704113292,
      "grad_norm": 0.34075039625167847,
      "learning_rate": 1.1786221073258426e-05,
      "loss": 0.549,
      "step": 28888
    },
    {
      "epoch": 0.8874450895462784,
      "grad_norm": 0.3772374093532562,
      "learning_rate": 1.178574556602216e-05,
      "loss": 0.5467,
      "step": 28889
    },
    {
      "epoch": 0.8874758086812276,
      "grad_norm": 0.3319837749004364,
      "learning_rate": 1.1785270054615156e-05,
      "loss": 0.5323,
      "step": 28890
    },
    {
      "epoch": 0.8875065278161767,
      "grad_norm": 0.38996919989585876,
      "learning_rate": 1.1784794539038533e-05,
      "loss": 0.4993,
      "step": 28891
    },
    {
      "epoch": 0.8875372469511259,
      "grad_norm": 0.35976722836494446,
      "learning_rate": 1.1784319019293398e-05,
      "loss": 0.5901,
      "step": 28892
    },
    {
      "epoch": 0.887567966086075,
      "grad_norm": 0.32823413610458374,
      "learning_rate": 1.178384349538086e-05,
      "loss": 0.5242,
      "step": 28893
    },
    {
      "epoch": 0.8875986852210241,
      "grad_norm": 0.3826940953731537,
      "learning_rate": 1.178336796730203e-05,
      "loss": 0.5721,
      "step": 28894
    },
    {
      "epoch": 0.8876294043559734,
      "grad_norm": 0.3532222807407379,
      "learning_rate": 1.1782892435058023e-05,
      "loss": 0.4878,
      "step": 28895
    },
    {
      "epoch": 0.8876601234909225,
      "grad_norm": 0.3963314890861511,
      "learning_rate": 1.1782416898649944e-05,
      "loss": 0.5617,
      "step": 28896
    },
    {
      "epoch": 0.8876908426258716,
      "grad_norm": 0.4314756393432617,
      "learning_rate": 1.1781941358078903e-05,
      "loss": 0.4903,
      "step": 28897
    },
    {
      "epoch": 0.8877215617608208,
      "grad_norm": 0.3538123667240143,
      "learning_rate": 1.1781465813346018e-05,
      "loss": 0.541,
      "step": 28898
    },
    {
      "epoch": 0.88775228089577,
      "grad_norm": 0.3498910367488861,
      "learning_rate": 1.1780990264452394e-05,
      "loss": 0.5076,
      "step": 28899
    },
    {
      "epoch": 0.8877830000307191,
      "grad_norm": 0.4682481288909912,
      "learning_rate": 1.1780514711399142e-05,
      "loss": 0.5328,
      "step": 28900
    },
    {
      "epoch": 0.8878137191656683,
      "grad_norm": 0.36090508103370667,
      "learning_rate": 1.1780039154187377e-05,
      "loss": 0.4817,
      "step": 28901
    },
    {
      "epoch": 0.8878444383006174,
      "grad_norm": 0.371182918548584,
      "learning_rate": 1.1779563592818202e-05,
      "loss": 0.5826,
      "step": 28902
    },
    {
      "epoch": 0.8878751574355667,
      "grad_norm": 0.41682666540145874,
      "learning_rate": 1.1779088027292734e-05,
      "loss": 0.608,
      "step": 28903
    },
    {
      "epoch": 0.8879058765705158,
      "grad_norm": 0.34811192750930786,
      "learning_rate": 1.177861245761208e-05,
      "loss": 0.5869,
      "step": 28904
    },
    {
      "epoch": 0.8879365957054649,
      "grad_norm": 0.38269034028053284,
      "learning_rate": 1.1778136883777353e-05,
      "loss": 0.5098,
      "step": 28905
    },
    {
      "epoch": 0.8879673148404141,
      "grad_norm": 0.3593958914279938,
      "learning_rate": 1.1777661305789662e-05,
      "loss": 0.505,
      "step": 28906
    },
    {
      "epoch": 0.8879980339753633,
      "grad_norm": 0.3190249502658844,
      "learning_rate": 1.1777185723650122e-05,
      "loss": 0.4731,
      "step": 28907
    },
    {
      "epoch": 0.8880287531103124,
      "grad_norm": 0.36842408776283264,
      "learning_rate": 1.1776710137359837e-05,
      "loss": 0.579,
      "step": 28908
    },
    {
      "epoch": 0.8880594722452616,
      "grad_norm": 0.3684832751750946,
      "learning_rate": 1.1776234546919922e-05,
      "loss": 0.5314,
      "step": 28909
    },
    {
      "epoch": 0.8880901913802107,
      "grad_norm": 0.3728339374065399,
      "learning_rate": 1.177575895233149e-05,
      "loss": 0.5372,
      "step": 28910
    },
    {
      "epoch": 0.8881209105151598,
      "grad_norm": 0.34268802404403687,
      "learning_rate": 1.1775283353595648e-05,
      "loss": 0.5984,
      "step": 28911
    },
    {
      "epoch": 0.8881516296501091,
      "grad_norm": 0.3476943373680115,
      "learning_rate": 1.1774807750713506e-05,
      "loss": 0.5611,
      "step": 28912
    },
    {
      "epoch": 0.8881823487850582,
      "grad_norm": 0.3426256775856018,
      "learning_rate": 1.1774332143686177e-05,
      "loss": 0.5335,
      "step": 28913
    },
    {
      "epoch": 0.8882130679200074,
      "grad_norm": 0.3668546676635742,
      "learning_rate": 1.1773856532514773e-05,
      "loss": 0.5317,
      "step": 28914
    },
    {
      "epoch": 0.8882437870549565,
      "grad_norm": 0.4626966416835785,
      "learning_rate": 1.1773380917200401e-05,
      "loss": 0.4778,
      "step": 28915
    },
    {
      "epoch": 0.8882745061899057,
      "grad_norm": 0.34655100107192993,
      "learning_rate": 1.1772905297744177e-05,
      "loss": 0.5949,
      "step": 28916
    },
    {
      "epoch": 0.8883052253248549,
      "grad_norm": 0.3679962754249573,
      "learning_rate": 1.1772429674147206e-05,
      "loss": 0.5685,
      "step": 28917
    },
    {
      "epoch": 0.888335944459804,
      "grad_norm": 0.42858412861824036,
      "learning_rate": 1.1771954046410603e-05,
      "loss": 0.5292,
      "step": 28918
    },
    {
      "epoch": 0.8883666635947531,
      "grad_norm": 0.331386536359787,
      "learning_rate": 1.177147841453548e-05,
      "loss": 0.6001,
      "step": 28919
    },
    {
      "epoch": 0.8883973827297024,
      "grad_norm": 0.35045382380485535,
      "learning_rate": 1.1771002778522942e-05,
      "loss": 0.5904,
      "step": 28920
    },
    {
      "epoch": 0.8884281018646515,
      "grad_norm": 0.34320002794265747,
      "learning_rate": 1.1770527138374103e-05,
      "loss": 0.5411,
      "step": 28921
    },
    {
      "epoch": 0.8884588209996006,
      "grad_norm": 0.3626762926578522,
      "learning_rate": 1.1770051494090075e-05,
      "loss": 0.5777,
      "step": 28922
    },
    {
      "epoch": 0.8884895401345498,
      "grad_norm": 0.34664082527160645,
      "learning_rate": 1.176957584567197e-05,
      "loss": 0.4991,
      "step": 28923
    },
    {
      "epoch": 0.888520259269499,
      "grad_norm": 0.37304380536079407,
      "learning_rate": 1.1769100193120895e-05,
      "loss": 0.5894,
      "step": 28924
    },
    {
      "epoch": 0.8885509784044481,
      "grad_norm": 0.3290463387966156,
      "learning_rate": 1.1768624536437965e-05,
      "loss": 0.4283,
      "step": 28925
    },
    {
      "epoch": 0.8885816975393973,
      "grad_norm": 0.3669934570789337,
      "learning_rate": 1.1768148875624285e-05,
      "loss": 0.5605,
      "step": 28926
    },
    {
      "epoch": 0.8886124166743464,
      "grad_norm": 0.3832922875881195,
      "learning_rate": 1.176767321068097e-05,
      "loss": 0.5173,
      "step": 28927
    },
    {
      "epoch": 0.8886431358092957,
      "grad_norm": 0.3878687620162964,
      "learning_rate": 1.1767197541609134e-05,
      "loss": 0.5191,
      "step": 28928
    },
    {
      "epoch": 0.8886738549442448,
      "grad_norm": 0.36315709352493286,
      "learning_rate": 1.1766721868409883e-05,
      "loss": 0.5611,
      "step": 28929
    },
    {
      "epoch": 0.8887045740791939,
      "grad_norm": 0.78389573097229,
      "learning_rate": 1.1766246191084331e-05,
      "loss": 0.6934,
      "step": 28930
    },
    {
      "epoch": 0.8887352932141431,
      "grad_norm": 0.4277898073196411,
      "learning_rate": 1.1765770509633588e-05,
      "loss": 0.4793,
      "step": 28931
    },
    {
      "epoch": 0.8887660123490922,
      "grad_norm": 0.40674006938934326,
      "learning_rate": 1.1765294824058763e-05,
      "loss": 0.5501,
      "step": 28932
    },
    {
      "epoch": 0.8887967314840414,
      "grad_norm": 0.4271043539047241,
      "learning_rate": 1.176481913436097e-05,
      "loss": 0.5196,
      "step": 28933
    },
    {
      "epoch": 0.8888274506189906,
      "grad_norm": 0.41685980558395386,
      "learning_rate": 1.1764343440541317e-05,
      "loss": 0.4828,
      "step": 28934
    },
    {
      "epoch": 0.8888581697539397,
      "grad_norm": 0.3416048288345337,
      "learning_rate": 1.176386774260092e-05,
      "loss": 0.5675,
      "step": 28935
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3934910297393799,
      "learning_rate": 1.1763392040540882e-05,
      "loss": 0.5556,
      "step": 28936
    },
    {
      "epoch": 0.8889196080238381,
      "grad_norm": 0.36152660846710205,
      "learning_rate": 1.1762916334362322e-05,
      "loss": 0.5978,
      "step": 28937
    },
    {
      "epoch": 0.8889503271587872,
      "grad_norm": 0.37392738461494446,
      "learning_rate": 1.1762440624066347e-05,
      "loss": 0.6397,
      "step": 28938
    },
    {
      "epoch": 0.8889810462937364,
      "grad_norm": 0.3691830039024353,
      "learning_rate": 1.176196490965407e-05,
      "loss": 0.5085,
      "step": 28939
    },
    {
      "epoch": 0.8890117654286855,
      "grad_norm": 0.3801521062850952,
      "learning_rate": 1.1761489191126599e-05,
      "loss": 0.6063,
      "step": 28940
    },
    {
      "epoch": 0.8890424845636347,
      "grad_norm": 0.3843648433685303,
      "learning_rate": 1.1761013468485048e-05,
      "loss": 0.4818,
      "step": 28941
    },
    {
      "epoch": 0.8890732036985839,
      "grad_norm": 0.36389580368995667,
      "learning_rate": 1.1760537741730524e-05,
      "loss": 0.5738,
      "step": 28942
    },
    {
      "epoch": 0.889103922833533,
      "grad_norm": 0.3392965495586395,
      "learning_rate": 1.1760062010864147e-05,
      "loss": 0.435,
      "step": 28943
    },
    {
      "epoch": 0.8891346419684821,
      "grad_norm": 0.38295307755470276,
      "learning_rate": 1.1759586275887017e-05,
      "loss": 0.5153,
      "step": 28944
    },
    {
      "epoch": 0.8891653611034314,
      "grad_norm": 0.4161711633205414,
      "learning_rate": 1.175911053680025e-05,
      "loss": 0.5691,
      "step": 28945
    },
    {
      "epoch": 0.8891960802383805,
      "grad_norm": 0.3456330895423889,
      "learning_rate": 1.1758634793604961e-05,
      "loss": 0.5458,
      "step": 28946
    },
    {
      "epoch": 0.8892267993733296,
      "grad_norm": 0.5023092031478882,
      "learning_rate": 1.1758159046302255e-05,
      "loss": 0.556,
      "step": 28947
    },
    {
      "epoch": 0.8892575185082788,
      "grad_norm": 0.35854870080947876,
      "learning_rate": 1.175768329489325e-05,
      "loss": 0.472,
      "step": 28948
    },
    {
      "epoch": 0.889288237643228,
      "grad_norm": 0.42526817321777344,
      "learning_rate": 1.1757207539379048e-05,
      "loss": 0.5014,
      "step": 28949
    },
    {
      "epoch": 0.8893189567781771,
      "grad_norm": 0.3714195489883423,
      "learning_rate": 1.1756731779760768e-05,
      "loss": 0.4846,
      "step": 28950
    },
    {
      "epoch": 0.8893496759131263,
      "grad_norm": 0.37277156114578247,
      "learning_rate": 1.1756256016039518e-05,
      "loss": 0.596,
      "step": 28951
    },
    {
      "epoch": 0.8893803950480754,
      "grad_norm": 0.39023277163505554,
      "learning_rate": 1.1755780248216409e-05,
      "loss": 0.5248,
      "step": 28952
    },
    {
      "epoch": 0.8894111141830247,
      "grad_norm": 0.39622950553894043,
      "learning_rate": 1.1755304476292552e-05,
      "loss": 0.5645,
      "step": 28953
    },
    {
      "epoch": 0.8894418333179738,
      "grad_norm": 0.31875208020210266,
      "learning_rate": 1.175482870026906e-05,
      "loss": 0.4709,
      "step": 28954
    },
    {
      "epoch": 0.8894725524529229,
      "grad_norm": 0.37708935141563416,
      "learning_rate": 1.1754352920147043e-05,
      "loss": 0.5408,
      "step": 28955
    },
    {
      "epoch": 0.8895032715878721,
      "grad_norm": 0.3484902083873749,
      "learning_rate": 1.1753877135927609e-05,
      "loss": 0.518,
      "step": 28956
    },
    {
      "epoch": 0.8895339907228212,
      "grad_norm": 0.4592888355255127,
      "learning_rate": 1.1753401347611877e-05,
      "loss": 0.6268,
      "step": 28957
    },
    {
      "epoch": 0.8895647098577704,
      "grad_norm": 0.4016129672527313,
      "learning_rate": 1.1752925555200951e-05,
      "loss": 0.6008,
      "step": 28958
    },
    {
      "epoch": 0.8895954289927196,
      "grad_norm": 0.3927650451660156,
      "learning_rate": 1.1752449758695947e-05,
      "loss": 0.5746,
      "step": 28959
    },
    {
      "epoch": 0.8896261481276687,
      "grad_norm": 0.405592143535614,
      "learning_rate": 1.175197395809797e-05,
      "loss": 0.5565,
      "step": 28960
    },
    {
      "epoch": 0.8896568672626178,
      "grad_norm": 0.37797752022743225,
      "learning_rate": 1.175149815340814e-05,
      "loss": 0.5304,
      "step": 28961
    },
    {
      "epoch": 0.8896875863975671,
      "grad_norm": 0.38570138812065125,
      "learning_rate": 1.1751022344627562e-05,
      "loss": 0.5224,
      "step": 28962
    },
    {
      "epoch": 0.8897183055325162,
      "grad_norm": 0.3665459156036377,
      "learning_rate": 1.175054653175735e-05,
      "loss": 0.4758,
      "step": 28963
    },
    {
      "epoch": 0.8897490246674654,
      "grad_norm": 0.46825799345970154,
      "learning_rate": 1.1750070714798611e-05,
      "loss": 0.5531,
      "step": 28964
    },
    {
      "epoch": 0.8897797438024145,
      "grad_norm": 0.37258201837539673,
      "learning_rate": 1.1749594893752461e-05,
      "loss": 0.5288,
      "step": 28965
    },
    {
      "epoch": 0.8898104629373637,
      "grad_norm": 0.37475040555000305,
      "learning_rate": 1.1749119068620014e-05,
      "loss": 0.5926,
      "step": 28966
    },
    {
      "epoch": 0.8898411820723129,
      "grad_norm": 0.35719162225723267,
      "learning_rate": 1.1748643239402372e-05,
      "loss": 0.584,
      "step": 28967
    },
    {
      "epoch": 0.889871901207262,
      "grad_norm": 0.3528898358345032,
      "learning_rate": 1.1748167406100655e-05,
      "loss": 0.4964,
      "step": 28968
    },
    {
      "epoch": 0.8899026203422111,
      "grad_norm": 0.37365543842315674,
      "learning_rate": 1.1747691568715969e-05,
      "loss": 0.4995,
      "step": 28969
    },
    {
      "epoch": 0.8899333394771604,
      "grad_norm": 0.3509801924228668,
      "learning_rate": 1.1747215727249428e-05,
      "loss": 0.5912,
      "step": 28970
    },
    {
      "epoch": 0.8899640586121095,
      "grad_norm": 0.3592296242713928,
      "learning_rate": 1.1746739881702145e-05,
      "loss": 0.5199,
      "step": 28971
    },
    {
      "epoch": 0.8899947777470586,
      "grad_norm": 0.35401684045791626,
      "learning_rate": 1.1746264032075225e-05,
      "loss": 0.5039,
      "step": 28972
    },
    {
      "epoch": 0.8900254968820078,
      "grad_norm": 0.35983994603157043,
      "learning_rate": 1.1745788178369786e-05,
      "loss": 0.5271,
      "step": 28973
    },
    {
      "epoch": 0.890056216016957,
      "grad_norm": 0.39763957262039185,
      "learning_rate": 1.1745312320586934e-05,
      "loss": 0.4457,
      "step": 28974
    },
    {
      "epoch": 0.8900869351519061,
      "grad_norm": 0.36594071984291077,
      "learning_rate": 1.1744836458727786e-05,
      "loss": 0.5612,
      "step": 28975
    },
    {
      "epoch": 0.8901176542868553,
      "grad_norm": 0.3287925124168396,
      "learning_rate": 1.174436059279345e-05,
      "loss": 0.5391,
      "step": 28976
    },
    {
      "epoch": 0.8901483734218044,
      "grad_norm": 0.36755433678627014,
      "learning_rate": 1.1743884722785038e-05,
      "loss": 0.5778,
      "step": 28977
    },
    {
      "epoch": 0.8901790925567536,
      "grad_norm": 0.32556578516960144,
      "learning_rate": 1.1743408848703659e-05,
      "loss": 0.501,
      "step": 28978
    },
    {
      "epoch": 0.8902098116917028,
      "grad_norm": 0.34264522790908813,
      "learning_rate": 1.174293297055043e-05,
      "loss": 0.5752,
      "step": 28979
    },
    {
      "epoch": 0.8902405308266519,
      "grad_norm": 0.3422245979309082,
      "learning_rate": 1.1742457088326458e-05,
      "loss": 0.5296,
      "step": 28980
    },
    {
      "epoch": 0.8902712499616011,
      "grad_norm": 0.6367719769477844,
      "learning_rate": 1.1741981202032857e-05,
      "loss": 0.5368,
      "step": 28981
    },
    {
      "epoch": 0.8903019690965502,
      "grad_norm": 0.3849518299102783,
      "learning_rate": 1.1741505311670736e-05,
      "loss": 0.5386,
      "step": 28982
    },
    {
      "epoch": 0.8903326882314994,
      "grad_norm": 0.3385475277900696,
      "learning_rate": 1.1741029417241206e-05,
      "loss": 0.5451,
      "step": 28983
    },
    {
      "epoch": 0.8903634073664486,
      "grad_norm": 0.34317517280578613,
      "learning_rate": 1.1740553518745383e-05,
      "loss": 0.587,
      "step": 28984
    },
    {
      "epoch": 0.8903941265013977,
      "grad_norm": 0.3511945903301239,
      "learning_rate": 1.1740077616184373e-05,
      "loss": 0.5703,
      "step": 28985
    },
    {
      "epoch": 0.8904248456363468,
      "grad_norm": 0.3732929825782776,
      "learning_rate": 1.1739601709559295e-05,
      "loss": 0.5365,
      "step": 28986
    },
    {
      "epoch": 0.8904555647712961,
      "grad_norm": 0.34636974334716797,
      "learning_rate": 1.1739125798871254e-05,
      "loss": 0.5672,
      "step": 28987
    },
    {
      "epoch": 0.8904862839062452,
      "grad_norm": 0.39064469933509827,
      "learning_rate": 1.1738649884121361e-05,
      "loss": 0.4997,
      "step": 28988
    },
    {
      "epoch": 0.8905170030411944,
      "grad_norm": 0.383428692817688,
      "learning_rate": 1.173817396531073e-05,
      "loss": 0.5706,
      "step": 28989
    },
    {
      "epoch": 0.8905477221761435,
      "grad_norm": 0.4068516194820404,
      "learning_rate": 1.1737698042440473e-05,
      "loss": 0.5424,
      "step": 28990
    },
    {
      "epoch": 0.8905784413110927,
      "grad_norm": 0.36948490142822266,
      "learning_rate": 1.1737222115511701e-05,
      "loss": 0.5142,
      "step": 28991
    },
    {
      "epoch": 0.8906091604460419,
      "grad_norm": 0.3474804759025574,
      "learning_rate": 1.1736746184525524e-05,
      "loss": 0.553,
      "step": 28992
    },
    {
      "epoch": 0.890639879580991,
      "grad_norm": 0.35619673132896423,
      "learning_rate": 1.173627024948306e-05,
      "loss": 0.5035,
      "step": 28993
    },
    {
      "epoch": 0.8906705987159401,
      "grad_norm": 0.3490934371948242,
      "learning_rate": 1.1735794310385409e-05,
      "loss": 0.5549,
      "step": 28994
    },
    {
      "epoch": 0.8907013178508894,
      "grad_norm": 0.3745153248310089,
      "learning_rate": 1.1735318367233694e-05,
      "loss": 0.5934,
      "step": 28995
    },
    {
      "epoch": 0.8907320369858385,
      "grad_norm": 0.39144766330718994,
      "learning_rate": 1.1734842420029019e-05,
      "loss": 0.6145,
      "step": 28996
    },
    {
      "epoch": 0.8907627561207876,
      "grad_norm": 0.39825326204299927,
      "learning_rate": 1.17343664687725e-05,
      "loss": 0.7566,
      "step": 28997
    },
    {
      "epoch": 0.8907934752557368,
      "grad_norm": 0.436125785112381,
      "learning_rate": 1.1733890513465247e-05,
      "loss": 0.4768,
      "step": 28998
    },
    {
      "epoch": 0.8908241943906859,
      "grad_norm": 0.40765801072120667,
      "learning_rate": 1.1733414554108371e-05,
      "loss": 0.5374,
      "step": 28999
    },
    {
      "epoch": 0.8908549135256352,
      "grad_norm": 0.35587120056152344,
      "learning_rate": 1.1732938590702983e-05,
      "loss": 0.5906,
      "step": 29000
    },
    {
      "epoch": 0.8908856326605843,
      "grad_norm": 0.33609437942504883,
      "learning_rate": 1.1732462623250196e-05,
      "loss": 0.5657,
      "step": 29001
    },
    {
      "epoch": 0.8909163517955334,
      "grad_norm": 0.41958412528038025,
      "learning_rate": 1.1731986651751121e-05,
      "loss": 0.5594,
      "step": 29002
    },
    {
      "epoch": 0.8909470709304826,
      "grad_norm": 0.35127824544906616,
      "learning_rate": 1.1731510676206871e-05,
      "loss": 0.4953,
      "step": 29003
    },
    {
      "epoch": 0.8909777900654318,
      "grad_norm": 0.4268958270549774,
      "learning_rate": 1.1731034696618559e-05,
      "loss": 0.5935,
      "step": 29004
    },
    {
      "epoch": 0.8910085092003809,
      "grad_norm": 0.34146225452423096,
      "learning_rate": 1.1730558712987294e-05,
      "loss": 0.5874,
      "step": 29005
    },
    {
      "epoch": 0.8910392283353301,
      "grad_norm": 0.36192816495895386,
      "learning_rate": 1.1730082725314186e-05,
      "loss": 0.5498,
      "step": 29006
    },
    {
      "epoch": 0.8910699474702792,
      "grad_norm": 0.4366661608219147,
      "learning_rate": 1.1729606733600353e-05,
      "loss": 0.5563,
      "step": 29007
    },
    {
      "epoch": 0.8911006666052284,
      "grad_norm": 0.3393646776676178,
      "learning_rate": 1.1729130737846898e-05,
      "loss": 0.5949,
      "step": 29008
    },
    {
      "epoch": 0.8911313857401776,
      "grad_norm": 0.3784931004047394,
      "learning_rate": 1.1728654738054943e-05,
      "loss": 0.5919,
      "step": 29009
    },
    {
      "epoch": 0.8911621048751267,
      "grad_norm": 0.367180734872818,
      "learning_rate": 1.1728178734225588e-05,
      "loss": 0.5371,
      "step": 29010
    },
    {
      "epoch": 0.8911928240100758,
      "grad_norm": 0.4239346981048584,
      "learning_rate": 1.1727702726359955e-05,
      "loss": 0.5277,
      "step": 29011
    },
    {
      "epoch": 0.891223543145025,
      "grad_norm": 0.3788200616836548,
      "learning_rate": 1.172722671445915e-05,
      "loss": 0.566,
      "step": 29012
    },
    {
      "epoch": 0.8912542622799742,
      "grad_norm": 0.3487885296344757,
      "learning_rate": 1.1726750698524288e-05,
      "loss": 0.552,
      "step": 29013
    },
    {
      "epoch": 0.8912849814149234,
      "grad_norm": 0.37022462487220764,
      "learning_rate": 1.1726274678556475e-05,
      "loss": 0.5497,
      "step": 29014
    },
    {
      "epoch": 0.8913157005498725,
      "grad_norm": 0.3761101961135864,
      "learning_rate": 1.1725798654556831e-05,
      "loss": 0.5352,
      "step": 29015
    },
    {
      "epoch": 0.8913464196848216,
      "grad_norm": 0.3869961202144623,
      "learning_rate": 1.1725322626526462e-05,
      "loss": 0.5061,
      "step": 29016
    },
    {
      "epoch": 0.8913771388197709,
      "grad_norm": 0.335576593875885,
      "learning_rate": 1.1724846594466483e-05,
      "loss": 0.5282,
      "step": 29017
    },
    {
      "epoch": 0.89140785795472,
      "grad_norm": 0.40271615982055664,
      "learning_rate": 1.1724370558378002e-05,
      "loss": 0.4413,
      "step": 29018
    },
    {
      "epoch": 0.8914385770896691,
      "grad_norm": 0.3632548749446869,
      "learning_rate": 1.1723894518262133e-05,
      "loss": 0.5595,
      "step": 29019
    },
    {
      "epoch": 0.8914692962246183,
      "grad_norm": 0.37168291211128235,
      "learning_rate": 1.172341847411999e-05,
      "loss": 0.5607,
      "step": 29020
    },
    {
      "epoch": 0.8915000153595675,
      "grad_norm": 0.3443134129047394,
      "learning_rate": 1.1722942425952682e-05,
      "loss": 0.5228,
      "step": 29021
    },
    {
      "epoch": 0.8915307344945166,
      "grad_norm": 0.36192044615745544,
      "learning_rate": 1.1722466373761322e-05,
      "loss": 0.5612,
      "step": 29022
    },
    {
      "epoch": 0.8915614536294658,
      "grad_norm": 0.36753925681114197,
      "learning_rate": 1.1721990317547022e-05,
      "loss": 0.5561,
      "step": 29023
    },
    {
      "epoch": 0.8915921727644149,
      "grad_norm": 0.3704235553741455,
      "learning_rate": 1.172151425731089e-05,
      "loss": 0.5307,
      "step": 29024
    },
    {
      "epoch": 0.8916228918993642,
      "grad_norm": 0.39878177642822266,
      "learning_rate": 1.1721038193054046e-05,
      "loss": 0.5939,
      "step": 29025
    },
    {
      "epoch": 0.8916536110343133,
      "grad_norm": 0.4418213367462158,
      "learning_rate": 1.1720562124777594e-05,
      "loss": 0.5112,
      "step": 29026
    },
    {
      "epoch": 0.8916843301692624,
      "grad_norm": 0.4099626839160919,
      "learning_rate": 1.1720086052482651e-05,
      "loss": 0.5875,
      "step": 29027
    },
    {
      "epoch": 0.8917150493042116,
      "grad_norm": 0.3883257806301117,
      "learning_rate": 1.1719609976170325e-05,
      "loss": 0.511,
      "step": 29028
    },
    {
      "epoch": 0.8917457684391608,
      "grad_norm": 0.31214624643325806,
      "learning_rate": 1.171913389584173e-05,
      "loss": 0.5281,
      "step": 29029
    },
    {
      "epoch": 0.8917764875741099,
      "grad_norm": 0.35188019275665283,
      "learning_rate": 1.1718657811497978e-05,
      "loss": 0.5175,
      "step": 29030
    },
    {
      "epoch": 0.8918072067090591,
      "grad_norm": 0.3678131103515625,
      "learning_rate": 1.1718181723140183e-05,
      "loss": 0.4925,
      "step": 29031
    },
    {
      "epoch": 0.8918379258440082,
      "grad_norm": 0.3403291404247284,
      "learning_rate": 1.171770563076945e-05,
      "loss": 0.5744,
      "step": 29032
    },
    {
      "epoch": 0.8918686449789573,
      "grad_norm": 0.37363961338996887,
      "learning_rate": 1.1717229534386901e-05,
      "loss": 0.5406,
      "step": 29033
    },
    {
      "epoch": 0.8918993641139066,
      "grad_norm": 0.34401291608810425,
      "learning_rate": 1.171675343399364e-05,
      "loss": 0.5234,
      "step": 29034
    },
    {
      "epoch": 0.8919300832488557,
      "grad_norm": 0.34269994497299194,
      "learning_rate": 1.171627732959078e-05,
      "loss": 0.5094,
      "step": 29035
    },
    {
      "epoch": 0.8919608023838048,
      "grad_norm": 0.35016605257987976,
      "learning_rate": 1.1715801221179435e-05,
      "loss": 0.5363,
      "step": 29036
    },
    {
      "epoch": 0.891991521518754,
      "grad_norm": 0.38452988862991333,
      "learning_rate": 1.1715325108760714e-05,
      "loss": 0.5577,
      "step": 29037
    },
    {
      "epoch": 0.8920222406537032,
      "grad_norm": 0.3608287572860718,
      "learning_rate": 1.1714848992335737e-05,
      "loss": 0.5521,
      "step": 29038
    },
    {
      "epoch": 0.8920529597886524,
      "grad_norm": 0.39149388670921326,
      "learning_rate": 1.1714372871905607e-05,
      "loss": 0.4811,
      "step": 29039
    },
    {
      "epoch": 0.8920836789236015,
      "grad_norm": 0.3653331995010376,
      "learning_rate": 1.171389674747144e-05,
      "loss": 0.627,
      "step": 29040
    },
    {
      "epoch": 0.8921143980585506,
      "grad_norm": 0.3614308536052704,
      "learning_rate": 1.1713420619034348e-05,
      "loss": 0.5783,
      "step": 29041
    },
    {
      "epoch": 0.8921451171934999,
      "grad_norm": 0.40790632367134094,
      "learning_rate": 1.171294448659544e-05,
      "loss": 0.5905,
      "step": 29042
    },
    {
      "epoch": 0.892175836328449,
      "grad_norm": 0.506161093711853,
      "learning_rate": 1.1712468350155835e-05,
      "loss": 0.5411,
      "step": 29043
    },
    {
      "epoch": 0.8922065554633981,
      "grad_norm": 0.3868597745895386,
      "learning_rate": 1.1711992209716635e-05,
      "loss": 0.5956,
      "step": 29044
    },
    {
      "epoch": 0.8922372745983473,
      "grad_norm": 0.3605025112628937,
      "learning_rate": 1.1711516065278962e-05,
      "loss": 0.4919,
      "step": 29045
    },
    {
      "epoch": 0.8922679937332965,
      "grad_norm": 0.4490320682525635,
      "learning_rate": 1.1711039916843922e-05,
      "loss": 0.5362,
      "step": 29046
    },
    {
      "epoch": 0.8922987128682456,
      "grad_norm": 0.34128111600875854,
      "learning_rate": 1.1710563764412632e-05,
      "loss": 0.4967,
      "step": 29047
    },
    {
      "epoch": 0.8923294320031948,
      "grad_norm": 0.37127599120140076,
      "learning_rate": 1.1710087607986197e-05,
      "loss": 0.4854,
      "step": 29048
    },
    {
      "epoch": 0.8923601511381439,
      "grad_norm": 0.35695257782936096,
      "learning_rate": 1.1709611447565734e-05,
      "loss": 0.5915,
      "step": 29049
    },
    {
      "epoch": 0.8923908702730932,
      "grad_norm": 0.4584716856479645,
      "learning_rate": 1.1709135283152354e-05,
      "loss": 0.5645,
      "step": 29050
    },
    {
      "epoch": 0.8924215894080423,
      "grad_norm": 0.36193153262138367,
      "learning_rate": 1.170865911474717e-05,
      "loss": 0.5766,
      "step": 29051
    },
    {
      "epoch": 0.8924523085429914,
      "grad_norm": 0.3900162875652313,
      "learning_rate": 1.1708182942351294e-05,
      "loss": 0.4706,
      "step": 29052
    },
    {
      "epoch": 0.8924830276779406,
      "grad_norm": 0.3898542523384094,
      "learning_rate": 1.1707706765965834e-05,
      "loss": 0.6129,
      "step": 29053
    },
    {
      "epoch": 0.8925137468128898,
      "grad_norm": 0.36070582270622253,
      "learning_rate": 1.1707230585591909e-05,
      "loss": 0.5348,
      "step": 29054
    },
    {
      "epoch": 0.8925444659478389,
      "grad_norm": 0.3606311082839966,
      "learning_rate": 1.1706754401230622e-05,
      "loss": 0.6273,
      "step": 29055
    },
    {
      "epoch": 0.8925751850827881,
      "grad_norm": 0.33707061409950256,
      "learning_rate": 1.1706278212883098e-05,
      "loss": 0.5133,
      "step": 29056
    },
    {
      "epoch": 0.8926059042177372,
      "grad_norm": 0.3593640625476837,
      "learning_rate": 1.170580202055044e-05,
      "loss": 0.6042,
      "step": 29057
    },
    {
      "epoch": 0.8926366233526863,
      "grad_norm": 0.3751041293144226,
      "learning_rate": 1.1705325824233759e-05,
      "loss": 0.6293,
      "step": 29058
    },
    {
      "epoch": 0.8926673424876356,
      "grad_norm": 0.5558409094810486,
      "learning_rate": 1.1704849623934175e-05,
      "loss": 0.5485,
      "step": 29059
    },
    {
      "epoch": 0.8926980616225847,
      "grad_norm": 0.39583370089530945,
      "learning_rate": 1.1704373419652793e-05,
      "loss": 0.4343,
      "step": 29060
    },
    {
      "epoch": 0.8927287807575338,
      "grad_norm": 0.3611915409564972,
      "learning_rate": 1.170389721139073e-05,
      "loss": 0.5909,
      "step": 29061
    },
    {
      "epoch": 0.892759499892483,
      "grad_norm": 0.35294345021247864,
      "learning_rate": 1.1703420999149094e-05,
      "loss": 0.4747,
      "step": 29062
    },
    {
      "epoch": 0.8927902190274322,
      "grad_norm": 0.35425040125846863,
      "learning_rate": 1.1702944782929e-05,
      "loss": 0.5524,
      "step": 29063
    },
    {
      "epoch": 0.8928209381623814,
      "grad_norm": 0.36997100710868835,
      "learning_rate": 1.1702468562731557e-05,
      "loss": 0.5261,
      "step": 29064
    },
    {
      "epoch": 0.8928516572973305,
      "grad_norm": 0.38002336025238037,
      "learning_rate": 1.1701992338557884e-05,
      "loss": 0.5489,
      "step": 29065
    },
    {
      "epoch": 0.8928823764322796,
      "grad_norm": 0.40502017736434937,
      "learning_rate": 1.1701516110409086e-05,
      "loss": 0.5052,
      "step": 29066
    },
    {
      "epoch": 0.8929130955672289,
      "grad_norm": 0.37337663769721985,
      "learning_rate": 1.170103987828628e-05,
      "loss": 0.4856,
      "step": 29067
    },
    {
      "epoch": 0.892943814702178,
      "grad_norm": 0.33717480301856995,
      "learning_rate": 1.1700563642190578e-05,
      "loss": 0.5621,
      "step": 29068
    },
    {
      "epoch": 0.8929745338371271,
      "grad_norm": 0.38163459300994873,
      "learning_rate": 1.1700087402123089e-05,
      "loss": 0.5114,
      "step": 29069
    },
    {
      "epoch": 0.8930052529720763,
      "grad_norm": 0.3622649013996124,
      "learning_rate": 1.1699611158084928e-05,
      "loss": 0.5252,
      "step": 29070
    },
    {
      "epoch": 0.8930359721070255,
      "grad_norm": 0.3614450693130493,
      "learning_rate": 1.1699134910077204e-05,
      "loss": 0.5281,
      "step": 29071
    },
    {
      "epoch": 0.8930666912419746,
      "grad_norm": 0.4057738184928894,
      "learning_rate": 1.1698658658101034e-05,
      "loss": 0.544,
      "step": 29072
    },
    {
      "epoch": 0.8930974103769238,
      "grad_norm": 0.7699423432350159,
      "learning_rate": 1.1698182402157523e-05,
      "loss": 0.5872,
      "step": 29073
    },
    {
      "epoch": 0.8931281295118729,
      "grad_norm": 0.3690846860408783,
      "learning_rate": 1.1697706142247794e-05,
      "loss": 0.5888,
      "step": 29074
    },
    {
      "epoch": 0.8931588486468222,
      "grad_norm": 0.389926016330719,
      "learning_rate": 1.1697229878372953e-05,
      "loss": 0.6304,
      "step": 29075
    },
    {
      "epoch": 0.8931895677817713,
      "grad_norm": 0.44032153487205505,
      "learning_rate": 1.1696753610534112e-05,
      "loss": 0.5862,
      "step": 29076
    },
    {
      "epoch": 0.8932202869167204,
      "grad_norm": 0.39951300621032715,
      "learning_rate": 1.1696277338732386e-05,
      "loss": 0.532,
      "step": 29077
    },
    {
      "epoch": 0.8932510060516696,
      "grad_norm": 0.4318150281906128,
      "learning_rate": 1.1695801062968883e-05,
      "loss": 0.6641,
      "step": 29078
    },
    {
      "epoch": 0.8932817251866187,
      "grad_norm": 0.5193226933479309,
      "learning_rate": 1.169532478324472e-05,
      "loss": 0.6762,
      "step": 29079
    },
    {
      "epoch": 0.8933124443215679,
      "grad_norm": 0.3964790105819702,
      "learning_rate": 1.169484849956101e-05,
      "loss": 0.5693,
      "step": 29080
    },
    {
      "epoch": 0.8933431634565171,
      "grad_norm": 0.33887723088264465,
      "learning_rate": 1.169437221191886e-05,
      "loss": 0.5912,
      "step": 29081
    },
    {
      "epoch": 0.8933738825914662,
      "grad_norm": 0.3475557863712311,
      "learning_rate": 1.1693895920319384e-05,
      "loss": 0.5369,
      "step": 29082
    },
    {
      "epoch": 0.8934046017264153,
      "grad_norm": 0.35879871249198914,
      "learning_rate": 1.16934196247637e-05,
      "loss": 0.5343,
      "step": 29083
    },
    {
      "epoch": 0.8934353208613646,
      "grad_norm": 0.3953433930873871,
      "learning_rate": 1.1692943325252912e-05,
      "loss": 0.593,
      "step": 29084
    },
    {
      "epoch": 0.8934660399963137,
      "grad_norm": 0.38500505685806274,
      "learning_rate": 1.169246702178814e-05,
      "loss": 0.6101,
      "step": 29085
    },
    {
      "epoch": 0.8934967591312629,
      "grad_norm": 0.3428557217121124,
      "learning_rate": 1.1691990714370491e-05,
      "loss": 0.5203,
      "step": 29086
    },
    {
      "epoch": 0.893527478266212,
      "grad_norm": 0.3394281268119812,
      "learning_rate": 1.1691514403001081e-05,
      "loss": 0.5172,
      "step": 29087
    },
    {
      "epoch": 0.8935581974011612,
      "grad_norm": 0.3379194438457489,
      "learning_rate": 1.1691038087681021e-05,
      "loss": 0.5315,
      "step": 29088
    },
    {
      "epoch": 0.8935889165361104,
      "grad_norm": 0.36904579401016235,
      "learning_rate": 1.1690561768411421e-05,
      "loss": 0.4481,
      "step": 29089
    },
    {
      "epoch": 0.8936196356710595,
      "grad_norm": 0.3740984797477722,
      "learning_rate": 1.1690085445193398e-05,
      "loss": 0.4829,
      "step": 29090
    },
    {
      "epoch": 0.8936503548060086,
      "grad_norm": 0.4366152584552765,
      "learning_rate": 1.1689609118028058e-05,
      "loss": 0.5773,
      "step": 29091
    },
    {
      "epoch": 0.8936810739409579,
      "grad_norm": 0.38222813606262207,
      "learning_rate": 1.1689132786916524e-05,
      "loss": 0.6166,
      "step": 29092
    },
    {
      "epoch": 0.893711793075907,
      "grad_norm": 0.3493430018424988,
      "learning_rate": 1.16886564518599e-05,
      "loss": 0.4781,
      "step": 29093
    },
    {
      "epoch": 0.8937425122108561,
      "grad_norm": 0.35154253244400024,
      "learning_rate": 1.16881801128593e-05,
      "loss": 0.5466,
      "step": 29094
    },
    {
      "epoch": 0.8937732313458053,
      "grad_norm": 0.3608851730823517,
      "learning_rate": 1.1687703769915842e-05,
      "loss": 0.6008,
      "step": 29095
    },
    {
      "epoch": 0.8938039504807544,
      "grad_norm": 0.3733634352684021,
      "learning_rate": 1.1687227423030627e-05,
      "loss": 0.6094,
      "step": 29096
    },
    {
      "epoch": 0.8938346696157036,
      "grad_norm": 0.3546454906463623,
      "learning_rate": 1.168675107220478e-05,
      "loss": 0.4632,
      "step": 29097
    },
    {
      "epoch": 0.8938653887506528,
      "grad_norm": 0.35510751605033875,
      "learning_rate": 1.1686274717439406e-05,
      "loss": 0.5968,
      "step": 29098
    },
    {
      "epoch": 0.8938961078856019,
      "grad_norm": 0.37248674035072327,
      "learning_rate": 1.1685798358735618e-05,
      "loss": 0.6275,
      "step": 29099
    },
    {
      "epoch": 0.8939268270205512,
      "grad_norm": 0.41977736353874207,
      "learning_rate": 1.1685321996094533e-05,
      "loss": 0.6133,
      "step": 29100
    },
    {
      "epoch": 0.8939575461555003,
      "grad_norm": 0.3456113636493683,
      "learning_rate": 1.1684845629517262e-05,
      "loss": 0.5838,
      "step": 29101
    },
    {
      "epoch": 0.8939882652904494,
      "grad_norm": 0.37516549229621887,
      "learning_rate": 1.1684369259004911e-05,
      "loss": 0.5559,
      "step": 29102
    },
    {
      "epoch": 0.8940189844253986,
      "grad_norm": 0.3984665274620056,
      "learning_rate": 1.16838928845586e-05,
      "loss": 0.6283,
      "step": 29103
    },
    {
      "epoch": 0.8940497035603477,
      "grad_norm": 0.39230746030807495,
      "learning_rate": 1.1683416506179443e-05,
      "loss": 0.5239,
      "step": 29104
    },
    {
      "epoch": 0.8940804226952969,
      "grad_norm": 0.4490218758583069,
      "learning_rate": 1.1682940123868547e-05,
      "loss": 0.6255,
      "step": 29105
    },
    {
      "epoch": 0.8941111418302461,
      "grad_norm": 0.3584361970424652,
      "learning_rate": 1.1682463737627025e-05,
      "loss": 0.5016,
      "step": 29106
    },
    {
      "epoch": 0.8941418609651952,
      "grad_norm": 0.3265388011932373,
      "learning_rate": 1.1681987347455993e-05,
      "loss": 0.4841,
      "step": 29107
    },
    {
      "epoch": 0.8941725801001443,
      "grad_norm": 0.32914188504219055,
      "learning_rate": 1.1681510953356564e-05,
      "loss": 0.4848,
      "step": 29108
    },
    {
      "epoch": 0.8942032992350936,
      "grad_norm": 0.3997056484222412,
      "learning_rate": 1.1681034555329847e-05,
      "loss": 0.5563,
      "step": 29109
    },
    {
      "epoch": 0.8942340183700427,
      "grad_norm": 0.39220741391181946,
      "learning_rate": 1.1680558153376953e-05,
      "loss": 0.5184,
      "step": 29110
    },
    {
      "epoch": 0.8942647375049919,
      "grad_norm": 0.3491116166114807,
      "learning_rate": 1.1680081747499003e-05,
      "loss": 0.4583,
      "step": 29111
    },
    {
      "epoch": 0.894295456639941,
      "grad_norm": 0.39146098494529724,
      "learning_rate": 1.1679605337697102e-05,
      "loss": 0.5364,
      "step": 29112
    },
    {
      "epoch": 0.8943261757748902,
      "grad_norm": 0.3897015452384949,
      "learning_rate": 1.1679128923972366e-05,
      "loss": 0.5002,
      "step": 29113
    },
    {
      "epoch": 0.8943568949098394,
      "grad_norm": 0.38518622517585754,
      "learning_rate": 1.1678652506325907e-05,
      "loss": 0.5192,
      "step": 29114
    },
    {
      "epoch": 0.8943876140447885,
      "grad_norm": 0.344930499792099,
      "learning_rate": 1.1678176084758839e-05,
      "loss": 0.5515,
      "step": 29115
    },
    {
      "epoch": 0.8944183331797376,
      "grad_norm": 0.3362020254135132,
      "learning_rate": 1.1677699659272273e-05,
      "loss": 0.5512,
      "step": 29116
    },
    {
      "epoch": 0.8944490523146869,
      "grad_norm": 0.3783765435218811,
      "learning_rate": 1.1677223229867322e-05,
      "loss": 0.5902,
      "step": 29117
    },
    {
      "epoch": 0.894479771449636,
      "grad_norm": 0.3536039888858795,
      "learning_rate": 1.16767467965451e-05,
      "loss": 0.523,
      "step": 29118
    },
    {
      "epoch": 0.8945104905845851,
      "grad_norm": 0.3842537999153137,
      "learning_rate": 1.167627035930672e-05,
      "loss": 0.6587,
      "step": 29119
    },
    {
      "epoch": 0.8945412097195343,
      "grad_norm": 0.40035152435302734,
      "learning_rate": 1.1675793918153291e-05,
      "loss": 0.5252,
      "step": 29120
    },
    {
      "epoch": 0.8945719288544834,
      "grad_norm": 0.3601178824901581,
      "learning_rate": 1.1675317473085927e-05,
      "loss": 0.4637,
      "step": 29121
    },
    {
      "epoch": 0.8946026479894326,
      "grad_norm": 0.35206374526023865,
      "learning_rate": 1.1674841024105745e-05,
      "loss": 0.448,
      "step": 29122
    },
    {
      "epoch": 0.8946333671243818,
      "grad_norm": 0.3530576229095459,
      "learning_rate": 1.1674364571213852e-05,
      "loss": 0.5268,
      "step": 29123
    },
    {
      "epoch": 0.8946640862593309,
      "grad_norm": 0.35276296734809875,
      "learning_rate": 1.1673888114411367e-05,
      "loss": 0.49,
      "step": 29124
    },
    {
      "epoch": 0.8946948053942801,
      "grad_norm": 0.3794379234313965,
      "learning_rate": 1.1673411653699396e-05,
      "loss": 0.5235,
      "step": 29125
    },
    {
      "epoch": 0.8947255245292293,
      "grad_norm": 0.35325440764427185,
      "learning_rate": 1.1672935189079057e-05,
      "loss": 0.4334,
      "step": 29126
    },
    {
      "epoch": 0.8947562436641784,
      "grad_norm": 0.3410915732383728,
      "learning_rate": 1.167245872055146e-05,
      "loss": 0.5185,
      "step": 29127
    },
    {
      "epoch": 0.8947869627991276,
      "grad_norm": 0.36122846603393555,
      "learning_rate": 1.1671982248117719e-05,
      "loss": 0.5838,
      "step": 29128
    },
    {
      "epoch": 0.8948176819340767,
      "grad_norm": 0.3639472424983978,
      "learning_rate": 1.1671505771778947e-05,
      "loss": 0.5035,
      "step": 29129
    },
    {
      "epoch": 0.8948484010690259,
      "grad_norm": 0.3806101381778717,
      "learning_rate": 1.1671029291536258e-05,
      "loss": 0.563,
      "step": 29130
    },
    {
      "epoch": 0.8948791202039751,
      "grad_norm": 0.40977659821510315,
      "learning_rate": 1.1670552807390765e-05,
      "loss": 0.5157,
      "step": 29131
    },
    {
      "epoch": 0.8949098393389242,
      "grad_norm": 0.43634337186813354,
      "learning_rate": 1.1670076319343572e-05,
      "loss": 0.5601,
      "step": 29132
    },
    {
      "epoch": 0.8949405584738733,
      "grad_norm": 0.37837350368499756,
      "learning_rate": 1.1669599827395808e-05,
      "loss": 0.5589,
      "step": 29133
    },
    {
      "epoch": 0.8949712776088226,
      "grad_norm": 0.3434171974658966,
      "learning_rate": 1.1669123331548571e-05,
      "loss": 0.5143,
      "step": 29134
    },
    {
      "epoch": 0.8950019967437717,
      "grad_norm": 0.39081692695617676,
      "learning_rate": 1.1668646831802981e-05,
      "loss": 0.5637,
      "step": 29135
    },
    {
      "epoch": 0.8950327158787209,
      "grad_norm": 0.3740633428096771,
      "learning_rate": 1.1668170328160151e-05,
      "loss": 0.5858,
      "step": 29136
    },
    {
      "epoch": 0.89506343501367,
      "grad_norm": 0.3874022960662842,
      "learning_rate": 1.1667693820621194e-05,
      "loss": 0.4729,
      "step": 29137
    },
    {
      "epoch": 0.8950941541486191,
      "grad_norm": 0.3864888846874237,
      "learning_rate": 1.166721730918722e-05,
      "loss": 0.6178,
      "step": 29138
    },
    {
      "epoch": 0.8951248732835684,
      "grad_norm": 0.36377087235450745,
      "learning_rate": 1.1666740793859342e-05,
      "loss": 0.5159,
      "step": 29139
    },
    {
      "epoch": 0.8951555924185175,
      "grad_norm": 0.35021501779556274,
      "learning_rate": 1.1666264274638677e-05,
      "loss": 0.4614,
      "step": 29140
    },
    {
      "epoch": 0.8951863115534666,
      "grad_norm": 0.35061314702033997,
      "learning_rate": 1.1665787751526332e-05,
      "loss": 0.4863,
      "step": 29141
    },
    {
      "epoch": 0.8952170306884158,
      "grad_norm": 0.389512300491333,
      "learning_rate": 1.1665311224523425e-05,
      "loss": 0.4712,
      "step": 29142
    },
    {
      "epoch": 0.895247749823365,
      "grad_norm": 0.4310374855995178,
      "learning_rate": 1.166483469363107e-05,
      "loss": 0.5789,
      "step": 29143
    },
    {
      "epoch": 0.8952784689583141,
      "grad_norm": 0.3397652804851532,
      "learning_rate": 1.1664358158850375e-05,
      "loss": 0.5734,
      "step": 29144
    },
    {
      "epoch": 0.8953091880932633,
      "grad_norm": 0.39559900760650635,
      "learning_rate": 1.1663881620182454e-05,
      "loss": 0.5718,
      "step": 29145
    },
    {
      "epoch": 0.8953399072282124,
      "grad_norm": 0.3593844473361969,
      "learning_rate": 1.1663405077628421e-05,
      "loss": 0.5425,
      "step": 29146
    },
    {
      "epoch": 0.8953706263631616,
      "grad_norm": 0.3859720528125763,
      "learning_rate": 1.1662928531189392e-05,
      "loss": 0.6054,
      "step": 29147
    },
    {
      "epoch": 0.8954013454981108,
      "grad_norm": 0.3481912910938263,
      "learning_rate": 1.1662451980866475e-05,
      "loss": 0.5554,
      "step": 29148
    },
    {
      "epoch": 0.8954320646330599,
      "grad_norm": 0.4468294680118561,
      "learning_rate": 1.1661975426660788e-05,
      "loss": 0.5764,
      "step": 29149
    },
    {
      "epoch": 0.8954627837680091,
      "grad_norm": 0.38392722606658936,
      "learning_rate": 1.166149886857344e-05,
      "loss": 0.5776,
      "step": 29150
    },
    {
      "epoch": 0.8954935029029583,
      "grad_norm": 0.3704873323440552,
      "learning_rate": 1.1661022306605545e-05,
      "loss": 0.5148,
      "step": 29151
    },
    {
      "epoch": 0.8955242220379074,
      "grad_norm": 0.3437010943889618,
      "learning_rate": 1.1660545740758216e-05,
      "loss": 0.5317,
      "step": 29152
    },
    {
      "epoch": 0.8955549411728566,
      "grad_norm": 0.39671340584754944,
      "learning_rate": 1.1660069171032568e-05,
      "loss": 0.5024,
      "step": 29153
    },
    {
      "epoch": 0.8955856603078057,
      "grad_norm": 0.37411025166511536,
      "learning_rate": 1.165959259742971e-05,
      "loss": 0.5652,
      "step": 29154
    },
    {
      "epoch": 0.8956163794427549,
      "grad_norm": 0.37485265731811523,
      "learning_rate": 1.165911601995076e-05,
      "loss": 0.4663,
      "step": 29155
    },
    {
      "epoch": 0.8956470985777041,
      "grad_norm": 0.3611644208431244,
      "learning_rate": 1.1658639438596828e-05,
      "loss": 0.5177,
      "step": 29156
    },
    {
      "epoch": 0.8956778177126532,
      "grad_norm": 0.37300965189933777,
      "learning_rate": 1.1658162853369029e-05,
      "loss": 0.475,
      "step": 29157
    },
    {
      "epoch": 0.8957085368476023,
      "grad_norm": 0.35765308141708374,
      "learning_rate": 1.1657686264268473e-05,
      "loss": 0.4703,
      "step": 29158
    },
    {
      "epoch": 0.8957392559825516,
      "grad_norm": 0.40342289209365845,
      "learning_rate": 1.1657209671296274e-05,
      "loss": 0.511,
      "step": 29159
    },
    {
      "epoch": 0.8957699751175007,
      "grad_norm": 0.34205538034439087,
      "learning_rate": 1.1656733074453547e-05,
      "loss": 0.5676,
      "step": 29160
    },
    {
      "epoch": 0.8958006942524499,
      "grad_norm": 0.3680044412612915,
      "learning_rate": 1.1656256473741406e-05,
      "loss": 0.5527,
      "step": 29161
    },
    {
      "epoch": 0.895831413387399,
      "grad_norm": 0.4114828109741211,
      "learning_rate": 1.1655779869160962e-05,
      "loss": 0.5434,
      "step": 29162
    },
    {
      "epoch": 0.8958621325223481,
      "grad_norm": 0.3417610228061676,
      "learning_rate": 1.1655303260713326e-05,
      "loss": 0.5337,
      "step": 29163
    },
    {
      "epoch": 0.8958928516572974,
      "grad_norm": 0.3668915331363678,
      "learning_rate": 1.1654826648399613e-05,
      "loss": 0.4398,
      "step": 29164
    },
    {
      "epoch": 0.8959235707922465,
      "grad_norm": 0.3965575695037842,
      "learning_rate": 1.165435003222094e-05,
      "loss": 0.4681,
      "step": 29165
    },
    {
      "epoch": 0.8959542899271956,
      "grad_norm": 0.351157546043396,
      "learning_rate": 1.1653873412178416e-05,
      "loss": 0.6024,
      "step": 29166
    },
    {
      "epoch": 0.8959850090621448,
      "grad_norm": 0.44689276814460754,
      "learning_rate": 1.1653396788273155e-05,
      "loss": 0.6095,
      "step": 29167
    },
    {
      "epoch": 0.896015728197094,
      "grad_norm": 0.34697291254997253,
      "learning_rate": 1.1652920160506268e-05,
      "loss": 0.5594,
      "step": 29168
    },
    {
      "epoch": 0.8960464473320431,
      "grad_norm": 0.38427796959877014,
      "learning_rate": 1.1652443528878876e-05,
      "loss": 0.5079,
      "step": 29169
    },
    {
      "epoch": 0.8960771664669923,
      "grad_norm": 0.4112304747104645,
      "learning_rate": 1.1651966893392082e-05,
      "loss": 0.6218,
      "step": 29170
    },
    {
      "epoch": 0.8961078856019414,
      "grad_norm": 0.47631606459617615,
      "learning_rate": 1.1651490254047007e-05,
      "loss": 0.6294,
      "step": 29171
    },
    {
      "epoch": 0.8961386047368906,
      "grad_norm": 0.3414067327976227,
      "learning_rate": 1.1651013610844759e-05,
      "loss": 0.5528,
      "step": 29172
    },
    {
      "epoch": 0.8961693238718398,
      "grad_norm": 0.35288143157958984,
      "learning_rate": 1.1650536963786454e-05,
      "loss": 0.4993,
      "step": 29173
    },
    {
      "epoch": 0.8962000430067889,
      "grad_norm": 0.3751794397830963,
      "learning_rate": 1.1650060312873206e-05,
      "loss": 0.54,
      "step": 29174
    },
    {
      "epoch": 0.8962307621417381,
      "grad_norm": 0.3695565462112427,
      "learning_rate": 1.1649583658106126e-05,
      "loss": 0.4806,
      "step": 29175
    },
    {
      "epoch": 0.8962614812766873,
      "grad_norm": 0.346417635679245,
      "learning_rate": 1.1649106999486328e-05,
      "loss": 0.5572,
      "step": 29176
    },
    {
      "epoch": 0.8962922004116364,
      "grad_norm": 0.3941897451877594,
      "learning_rate": 1.1648630337014924e-05,
      "loss": 0.6011,
      "step": 29177
    },
    {
      "epoch": 0.8963229195465856,
      "grad_norm": 0.3722604811191559,
      "learning_rate": 1.164815367069303e-05,
      "loss": 0.5037,
      "step": 29178
    },
    {
      "epoch": 0.8963536386815347,
      "grad_norm": 0.331224650144577,
      "learning_rate": 1.1647677000521758e-05,
      "loss": 0.5603,
      "step": 29179
    },
    {
      "epoch": 0.8963843578164838,
      "grad_norm": 0.42777693271636963,
      "learning_rate": 1.1647200326502222e-05,
      "loss": 0.5699,
      "step": 29180
    },
    {
      "epoch": 0.8964150769514331,
      "grad_norm": 0.3496192395687103,
      "learning_rate": 1.1646723648635531e-05,
      "loss": 0.5088,
      "step": 29181
    },
    {
      "epoch": 0.8964457960863822,
      "grad_norm": 0.3685421347618103,
      "learning_rate": 1.1646246966922807e-05,
      "loss": 0.5148,
      "step": 29182
    },
    {
      "epoch": 0.8964765152213313,
      "grad_norm": 0.39778122305870056,
      "learning_rate": 1.1645770281365154e-05,
      "loss": 0.5638,
      "step": 29183
    },
    {
      "epoch": 0.8965072343562805,
      "grad_norm": 0.3787819445133209,
      "learning_rate": 1.164529359196369e-05,
      "loss": 0.5687,
      "step": 29184
    },
    {
      "epoch": 0.8965379534912297,
      "grad_norm": 0.4546995759010315,
      "learning_rate": 1.164481689871953e-05,
      "loss": 0.5118,
      "step": 29185
    },
    {
      "epoch": 0.8965686726261789,
      "grad_norm": 0.3548251688480377,
      "learning_rate": 1.1644340201633787e-05,
      "loss": 0.4901,
      "step": 29186
    },
    {
      "epoch": 0.896599391761128,
      "grad_norm": 0.41278010606765747,
      "learning_rate": 1.1643863500707568e-05,
      "loss": 0.54,
      "step": 29187
    },
    {
      "epoch": 0.8966301108960771,
      "grad_norm": 0.40834540128707886,
      "learning_rate": 1.1643386795941993e-05,
      "loss": 0.5447,
      "step": 29188
    },
    {
      "epoch": 0.8966608300310264,
      "grad_norm": 0.4543491303920746,
      "learning_rate": 1.1642910087338174e-05,
      "loss": 0.5362,
      "step": 29189
    },
    {
      "epoch": 0.8966915491659755,
      "grad_norm": 0.39631810784339905,
      "learning_rate": 1.1642433374897225e-05,
      "loss": 0.581,
      "step": 29190
    },
    {
      "epoch": 0.8967222683009246,
      "grad_norm": 0.4739347994327545,
      "learning_rate": 1.1641956658620257e-05,
      "loss": 0.5503,
      "step": 29191
    },
    {
      "epoch": 0.8967529874358738,
      "grad_norm": 0.3676416873931885,
      "learning_rate": 1.1641479938508385e-05,
      "loss": 0.5456,
      "step": 29192
    },
    {
      "epoch": 0.896783706570823,
      "grad_norm": 0.3718222677707672,
      "learning_rate": 1.1641003214562721e-05,
      "loss": 0.5033,
      "step": 29193
    },
    {
      "epoch": 0.8968144257057721,
      "grad_norm": 0.34875938296318054,
      "learning_rate": 1.164052648678438e-05,
      "loss": 0.5052,
      "step": 29194
    },
    {
      "epoch": 0.8968451448407213,
      "grad_norm": 0.3475865423679352,
      "learning_rate": 1.1640049755174472e-05,
      "loss": 0.5638,
      "step": 29195
    },
    {
      "epoch": 0.8968758639756704,
      "grad_norm": 0.42486128211021423,
      "learning_rate": 1.1639573019734117e-05,
      "loss": 0.5926,
      "step": 29196
    },
    {
      "epoch": 0.8969065831106197,
      "grad_norm": 0.3557370901107788,
      "learning_rate": 1.163909628046442e-05,
      "loss": 0.5908,
      "step": 29197
    },
    {
      "epoch": 0.8969373022455688,
      "grad_norm": 0.36703574657440186,
      "learning_rate": 1.1638619537366505e-05,
      "loss": 0.5586,
      "step": 29198
    },
    {
      "epoch": 0.8969680213805179,
      "grad_norm": 0.3919374644756317,
      "learning_rate": 1.1638142790441476e-05,
      "loss": 0.5825,
      "step": 29199
    },
    {
      "epoch": 0.8969987405154671,
      "grad_norm": 0.5415679216384888,
      "learning_rate": 1.1637666039690454e-05,
      "loss": 0.5821,
      "step": 29200
    },
    {
      "epoch": 0.8970294596504162,
      "grad_norm": 0.376060426235199,
      "learning_rate": 1.1637189285114544e-05,
      "loss": 0.5131,
      "step": 29201
    },
    {
      "epoch": 0.8970601787853654,
      "grad_norm": 0.3900511860847473,
      "learning_rate": 1.1636712526714864e-05,
      "loss": 0.5172,
      "step": 29202
    },
    {
      "epoch": 0.8970908979203146,
      "grad_norm": 0.4064315855503082,
      "learning_rate": 1.1636235764492532e-05,
      "loss": 0.5744,
      "step": 29203
    },
    {
      "epoch": 0.8971216170552637,
      "grad_norm": 0.38979625701904297,
      "learning_rate": 1.1635758998448652e-05,
      "loss": 0.5445,
      "step": 29204
    },
    {
      "epoch": 0.8971523361902128,
      "grad_norm": 0.3462862968444824,
      "learning_rate": 1.1635282228584346e-05,
      "loss": 0.5465,
      "step": 29205
    },
    {
      "epoch": 0.8971830553251621,
      "grad_norm": 0.42674165964126587,
      "learning_rate": 1.1634805454900721e-05,
      "loss": 0.5973,
      "step": 29206
    },
    {
      "epoch": 0.8972137744601112,
      "grad_norm": 0.3664769232273102,
      "learning_rate": 1.1634328677398899e-05,
      "loss": 0.4992,
      "step": 29207
    },
    {
      "epoch": 0.8972444935950603,
      "grad_norm": 0.3814771771430969,
      "learning_rate": 1.1633851896079987e-05,
      "loss": 0.5611,
      "step": 29208
    },
    {
      "epoch": 0.8972752127300095,
      "grad_norm": 0.33953872323036194,
      "learning_rate": 1.1633375110945095e-05,
      "loss": 0.5436,
      "step": 29209
    },
    {
      "epoch": 0.8973059318649587,
      "grad_norm": 0.38440465927124023,
      "learning_rate": 1.1632898321995344e-05,
      "loss": 0.5403,
      "step": 29210
    },
    {
      "epoch": 0.8973366509999079,
      "grad_norm": 0.4070439040660858,
      "learning_rate": 1.1632421529231845e-05,
      "loss": 0.5739,
      "step": 29211
    },
    {
      "epoch": 0.897367370134857,
      "grad_norm": 0.36272865533828735,
      "learning_rate": 1.1631944732655713e-05,
      "loss": 0.6034,
      "step": 29212
    },
    {
      "epoch": 0.8973980892698061,
      "grad_norm": 0.32232633233070374,
      "learning_rate": 1.1631467932268058e-05,
      "loss": 0.53,
      "step": 29213
    },
    {
      "epoch": 0.8974288084047554,
      "grad_norm": 0.3979099690914154,
      "learning_rate": 1.1630991128069999e-05,
      "loss": 0.5706,
      "step": 29214
    },
    {
      "epoch": 0.8974595275397045,
      "grad_norm": 0.3474920094013214,
      "learning_rate": 1.1630514320062642e-05,
      "loss": 0.4987,
      "step": 29215
    },
    {
      "epoch": 0.8974902466746536,
      "grad_norm": 0.4283681809902191,
      "learning_rate": 1.1630037508247107e-05,
      "loss": 0.5495,
      "step": 29216
    },
    {
      "epoch": 0.8975209658096028,
      "grad_norm": 0.372677743434906,
      "learning_rate": 1.1629560692624506e-05,
      "loss": 0.6037,
      "step": 29217
    },
    {
      "epoch": 0.897551684944552,
      "grad_norm": 0.3212263286113739,
      "learning_rate": 1.1629083873195952e-05,
      "loss": 0.5029,
      "step": 29218
    },
    {
      "epoch": 0.8975824040795011,
      "grad_norm": 0.37483924627304077,
      "learning_rate": 1.1628607049962557e-05,
      "loss": 0.5964,
      "step": 29219
    },
    {
      "epoch": 0.8976131232144503,
      "grad_norm": 0.37280532717704773,
      "learning_rate": 1.1628130222925438e-05,
      "loss": 0.6279,
      "step": 29220
    },
    {
      "epoch": 0.8976438423493994,
      "grad_norm": 0.3316991925239563,
      "learning_rate": 1.1627653392085707e-05,
      "loss": 0.5171,
      "step": 29221
    },
    {
      "epoch": 0.8976745614843487,
      "grad_norm": 0.36691421270370483,
      "learning_rate": 1.1627176557444477e-05,
      "loss": 0.5732,
      "step": 29222
    },
    {
      "epoch": 0.8977052806192978,
      "grad_norm": 0.39681878685951233,
      "learning_rate": 1.1626699719002866e-05,
      "loss": 0.599,
      "step": 29223
    },
    {
      "epoch": 0.8977359997542469,
      "grad_norm": 0.347149521112442,
      "learning_rate": 1.1626222876761982e-05,
      "loss": 0.5123,
      "step": 29224
    },
    {
      "epoch": 0.8977667188891961,
      "grad_norm": 0.375559538602829,
      "learning_rate": 1.1625746030722939e-05,
      "loss": 0.5742,
      "step": 29225
    },
    {
      "epoch": 0.8977974380241452,
      "grad_norm": 0.3767823278903961,
      "learning_rate": 1.1625269180886856e-05,
      "loss": 0.5279,
      "step": 29226
    },
    {
      "epoch": 0.8978281571590944,
      "grad_norm": 0.32713228464126587,
      "learning_rate": 1.1624792327254839e-05,
      "loss": 0.5294,
      "step": 29227
    },
    {
      "epoch": 0.8978588762940436,
      "grad_norm": 0.4051297903060913,
      "learning_rate": 1.162431546982801e-05,
      "loss": 0.5243,
      "step": 29228
    },
    {
      "epoch": 0.8978895954289927,
      "grad_norm": 0.39647752046585083,
      "learning_rate": 1.1623838608607477e-05,
      "loss": 0.573,
      "step": 29229
    },
    {
      "epoch": 0.8979203145639418,
      "grad_norm": 0.3469703197479248,
      "learning_rate": 1.1623361743594357e-05,
      "loss": 0.5694,
      "step": 29230
    },
    {
      "epoch": 0.8979510336988911,
      "grad_norm": 0.3807819187641144,
      "learning_rate": 1.162288487478976e-05,
      "loss": 0.52,
      "step": 29231
    },
    {
      "epoch": 0.8979817528338402,
      "grad_norm": 0.3375532925128937,
      "learning_rate": 1.1622408002194802e-05,
      "loss": 0.586,
      "step": 29232
    },
    {
      "epoch": 0.8980124719687893,
      "grad_norm": 0.3919714391231537,
      "learning_rate": 1.1621931125810598e-05,
      "loss": 0.5737,
      "step": 29233
    },
    {
      "epoch": 0.8980431911037385,
      "grad_norm": 0.35372433066368103,
      "learning_rate": 1.1621454245638262e-05,
      "loss": 0.6138,
      "step": 29234
    },
    {
      "epoch": 0.8980739102386877,
      "grad_norm": 0.3728470504283905,
      "learning_rate": 1.1620977361678904e-05,
      "loss": 0.5192,
      "step": 29235
    },
    {
      "epoch": 0.8981046293736369,
      "grad_norm": 0.33900967240333557,
      "learning_rate": 1.1620500473933643e-05,
      "loss": 0.5407,
      "step": 29236
    },
    {
      "epoch": 0.898135348508586,
      "grad_norm": 0.4055013358592987,
      "learning_rate": 1.1620023582403585e-05,
      "loss": 0.5673,
      "step": 29237
    },
    {
      "epoch": 0.8981660676435351,
      "grad_norm": 0.3752363920211792,
      "learning_rate": 1.161954668708985e-05,
      "loss": 0.6075,
      "step": 29238
    },
    {
      "epoch": 0.8981967867784844,
      "grad_norm": 0.3804185390472412,
      "learning_rate": 1.1619069787993555e-05,
      "loss": 0.6395,
      "step": 29239
    },
    {
      "epoch": 0.8982275059134335,
      "grad_norm": 0.3796903192996979,
      "learning_rate": 1.1618592885115805e-05,
      "loss": 0.5482,
      "step": 29240
    },
    {
      "epoch": 0.8982582250483826,
      "grad_norm": 0.4798710346221924,
      "learning_rate": 1.161811597845772e-05,
      "loss": 0.6141,
      "step": 29241
    },
    {
      "epoch": 0.8982889441833318,
      "grad_norm": 0.3611539900302887,
      "learning_rate": 1.1617639068020414e-05,
      "loss": 0.556,
      "step": 29242
    },
    {
      "epoch": 0.898319663318281,
      "grad_norm": 0.448697030544281,
      "learning_rate": 1.1617162153804997e-05,
      "loss": 0.6148,
      "step": 29243
    },
    {
      "epoch": 0.8983503824532301,
      "grad_norm": 0.4395407438278198,
      "learning_rate": 1.1616685235812586e-05,
      "loss": 0.5314,
      "step": 29244
    },
    {
      "epoch": 0.8983811015881793,
      "grad_norm": 0.31136104464530945,
      "learning_rate": 1.161620831404429e-05,
      "loss": 0.4122,
      "step": 29245
    },
    {
      "epoch": 0.8984118207231284,
      "grad_norm": 0.3255364000797272,
      "learning_rate": 1.1615731388501232e-05,
      "loss": 0.5423,
      "step": 29246
    },
    {
      "epoch": 0.8984425398580776,
      "grad_norm": 0.380889356136322,
      "learning_rate": 1.1615254459184517e-05,
      "loss": 0.5368,
      "step": 29247
    },
    {
      "epoch": 0.8984732589930268,
      "grad_norm": 0.38023850321769714,
      "learning_rate": 1.1614777526095265e-05,
      "loss": 0.595,
      "step": 29248
    },
    {
      "epoch": 0.8985039781279759,
      "grad_norm": 0.33138254284858704,
      "learning_rate": 1.1614300589234583e-05,
      "loss": 0.4988,
      "step": 29249
    },
    {
      "epoch": 0.8985346972629251,
      "grad_norm": 0.39108824729919434,
      "learning_rate": 1.1613823648603592e-05,
      "loss": 0.6049,
      "step": 29250
    },
    {
      "epoch": 0.8985654163978742,
      "grad_norm": 0.38546040654182434,
      "learning_rate": 1.1613346704203403e-05,
      "loss": 0.6082,
      "step": 29251
    },
    {
      "epoch": 0.8985961355328234,
      "grad_norm": 0.35764428973197937,
      "learning_rate": 1.1612869756035133e-05,
      "loss": 0.5169,
      "step": 29252
    },
    {
      "epoch": 0.8986268546677726,
      "grad_norm": 0.3549938499927521,
      "learning_rate": 1.161239280409989e-05,
      "loss": 0.5468,
      "step": 29253
    },
    {
      "epoch": 0.8986575738027217,
      "grad_norm": 0.3706185221672058,
      "learning_rate": 1.1611915848398789e-05,
      "loss": 0.4605,
      "step": 29254
    },
    {
      "epoch": 0.8986882929376708,
      "grad_norm": 0.35539355874061584,
      "learning_rate": 1.1611438888932949e-05,
      "loss": 0.5229,
      "step": 29255
    },
    {
      "epoch": 0.8987190120726201,
      "grad_norm": 0.3874891698360443,
      "learning_rate": 1.1610961925703476e-05,
      "loss": 0.6223,
      "step": 29256
    },
    {
      "epoch": 0.8987497312075692,
      "grad_norm": 0.34200021624565125,
      "learning_rate": 1.1610484958711495e-05,
      "loss": 0.5392,
      "step": 29257
    },
    {
      "epoch": 0.8987804503425183,
      "grad_norm": 0.381277471780777,
      "learning_rate": 1.1610007987958111e-05,
      "loss": 0.6429,
      "step": 29258
    },
    {
      "epoch": 0.8988111694774675,
      "grad_norm": 0.33084505796432495,
      "learning_rate": 1.1609531013444442e-05,
      "loss": 0.5137,
      "step": 29259
    },
    {
      "epoch": 0.8988418886124167,
      "grad_norm": 0.41172894835472107,
      "learning_rate": 1.1609054035171603e-05,
      "loss": 0.5603,
      "step": 29260
    },
    {
      "epoch": 0.8988726077473659,
      "grad_norm": 0.48996976017951965,
      "learning_rate": 1.1608577053140702e-05,
      "loss": 0.5469,
      "step": 29261
    },
    {
      "epoch": 0.898903326882315,
      "grad_norm": 0.35952329635620117,
      "learning_rate": 1.1608100067352858e-05,
      "loss": 0.5383,
      "step": 29262
    },
    {
      "epoch": 0.8989340460172641,
      "grad_norm": 0.3835344910621643,
      "learning_rate": 1.1607623077809185e-05,
      "loss": 0.5636,
      "step": 29263
    },
    {
      "epoch": 0.8989647651522134,
      "grad_norm": 0.37628307938575745,
      "learning_rate": 1.1607146084510797e-05,
      "loss": 0.5445,
      "step": 29264
    },
    {
      "epoch": 0.8989954842871625,
      "grad_norm": 0.34644749760627747,
      "learning_rate": 1.1606669087458803e-05,
      "loss": 0.5067,
      "step": 29265
    },
    {
      "epoch": 0.8990262034221116,
      "grad_norm": 0.45269137620925903,
      "learning_rate": 1.1606192086654327e-05,
      "loss": 0.5908,
      "step": 29266
    },
    {
      "epoch": 0.8990569225570608,
      "grad_norm": 0.37236082553863525,
      "learning_rate": 1.1605715082098473e-05,
      "loss": 0.5889,
      "step": 29267
    },
    {
      "epoch": 0.8990876416920099,
      "grad_norm": 0.3351103365421295,
      "learning_rate": 1.160523807379236e-05,
      "loss": 0.5541,
      "step": 29268
    },
    {
      "epoch": 0.8991183608269591,
      "grad_norm": 0.37064898014068604,
      "learning_rate": 1.16047610617371e-05,
      "loss": 0.5345,
      "step": 29269
    },
    {
      "epoch": 0.8991490799619083,
      "grad_norm": 0.40902402997016907,
      "learning_rate": 1.1604284045933812e-05,
      "loss": 0.5672,
      "step": 29270
    },
    {
      "epoch": 0.8991797990968574,
      "grad_norm": 0.3466871976852417,
      "learning_rate": 1.1603807026383604e-05,
      "loss": 0.4799,
      "step": 29271
    },
    {
      "epoch": 0.8992105182318066,
      "grad_norm": 0.3667127788066864,
      "learning_rate": 1.1603330003087594e-05,
      "loss": 0.5662,
      "step": 29272
    },
    {
      "epoch": 0.8992412373667558,
      "grad_norm": 0.4108659327030182,
      "learning_rate": 1.1602852976046894e-05,
      "loss": 0.6086,
      "step": 29273
    },
    {
      "epoch": 0.8992719565017049,
      "grad_norm": 0.36967742443084717,
      "learning_rate": 1.1602375945262615e-05,
      "loss": 0.5463,
      "step": 29274
    },
    {
      "epoch": 0.8993026756366541,
      "grad_norm": 0.3385744094848633,
      "learning_rate": 1.1601898910735882e-05,
      "loss": 0.4863,
      "step": 29275
    },
    {
      "epoch": 0.8993333947716032,
      "grad_norm": 0.4643601179122925,
      "learning_rate": 1.16014218724678e-05,
      "loss": 0.5176,
      "step": 29276
    },
    {
      "epoch": 0.8993641139065524,
      "grad_norm": 0.3586946427822113,
      "learning_rate": 1.1600944830459484e-05,
      "loss": 0.5527,
      "step": 29277
    },
    {
      "epoch": 0.8993948330415016,
      "grad_norm": 0.35994213819503784,
      "learning_rate": 1.160046778471205e-05,
      "loss": 0.5379,
      "step": 29278
    },
    {
      "epoch": 0.8994255521764507,
      "grad_norm": 0.38903114199638367,
      "learning_rate": 1.1599990735226613e-05,
      "loss": 0.5453,
      "step": 29279
    },
    {
      "epoch": 0.8994562713113998,
      "grad_norm": 0.38624700903892517,
      "learning_rate": 1.1599513682004283e-05,
      "loss": 0.5819,
      "step": 29280
    },
    {
      "epoch": 0.899486990446349,
      "grad_norm": 0.37496599555015564,
      "learning_rate": 1.1599036625046178e-05,
      "loss": 0.51,
      "step": 29281
    },
    {
      "epoch": 0.8995177095812982,
      "grad_norm": 0.4372881054878235,
      "learning_rate": 1.1598559564353415e-05,
      "loss": 0.525,
      "step": 29282
    },
    {
      "epoch": 0.8995484287162474,
      "grad_norm": 0.35726574063301086,
      "learning_rate": 1.1598082499927101e-05,
      "loss": 0.513,
      "step": 29283
    },
    {
      "epoch": 0.8995791478511965,
      "grad_norm": 0.43936729431152344,
      "learning_rate": 1.1597605431768356e-05,
      "loss": 0.5349,
      "step": 29284
    },
    {
      "epoch": 0.8996098669861456,
      "grad_norm": 0.3508240282535553,
      "learning_rate": 1.159712835987829e-05,
      "loss": 0.5661,
      "step": 29285
    },
    {
      "epoch": 0.8996405861210949,
      "grad_norm": 0.3656429052352905,
      "learning_rate": 1.1596651284258017e-05,
      "loss": 0.5056,
      "step": 29286
    },
    {
      "epoch": 0.899671305256044,
      "grad_norm": 0.382525771856308,
      "learning_rate": 1.1596174204908657e-05,
      "loss": 0.5746,
      "step": 29287
    },
    {
      "epoch": 0.8997020243909931,
      "grad_norm": 0.40686172246932983,
      "learning_rate": 1.159569712183132e-05,
      "loss": 0.5428,
      "step": 29288
    },
    {
      "epoch": 0.8997327435259423,
      "grad_norm": 0.36497044563293457,
      "learning_rate": 1.1595220035027121e-05,
      "loss": 0.57,
      "step": 29289
    },
    {
      "epoch": 0.8997634626608915,
      "grad_norm": 0.40388062596321106,
      "learning_rate": 1.1594742944497175e-05,
      "loss": 0.5697,
      "step": 29290
    },
    {
      "epoch": 0.8997941817958406,
      "grad_norm": 0.4128093421459198,
      "learning_rate": 1.1594265850242595e-05,
      "loss": 0.5618,
      "step": 29291
    },
    {
      "epoch": 0.8998249009307898,
      "grad_norm": 0.4392506778240204,
      "learning_rate": 1.159378875226449e-05,
      "loss": 0.5107,
      "step": 29292
    },
    {
      "epoch": 0.8998556200657389,
      "grad_norm": 0.32969772815704346,
      "learning_rate": 1.1593311650563987e-05,
      "loss": 0.5358,
      "step": 29293
    },
    {
      "epoch": 0.8998863392006881,
      "grad_norm": 0.38095366954803467,
      "learning_rate": 1.1592834545142194e-05,
      "loss": 0.5399,
      "step": 29294
    },
    {
      "epoch": 0.8999170583356373,
      "grad_norm": 0.3998109996318817,
      "learning_rate": 1.159235743600022e-05,
      "loss": 0.5273,
      "step": 29295
    },
    {
      "epoch": 0.8999477774705864,
      "grad_norm": 0.39055055379867554,
      "learning_rate": 1.1591880323139187e-05,
      "loss": 0.6052,
      "step": 29296
    },
    {
      "epoch": 0.8999784966055356,
      "grad_norm": 0.3822246491909027,
      "learning_rate": 1.1591403206560203e-05,
      "loss": 0.5294,
      "step": 29297
    },
    {
      "epoch": 0.9000092157404848,
      "grad_norm": 0.3779137432575226,
      "learning_rate": 1.1590926086264389e-05,
      "loss": 0.5471,
      "step": 29298
    },
    {
      "epoch": 0.9000399348754339,
      "grad_norm": 0.3434487581253052,
      "learning_rate": 1.1590448962252857e-05,
      "loss": 0.5955,
      "step": 29299
    },
    {
      "epoch": 0.9000706540103831,
      "grad_norm": 0.4829327166080475,
      "learning_rate": 1.1589971834526719e-05,
      "loss": 0.484,
      "step": 29300
    },
    {
      "epoch": 0.9001013731453322,
      "grad_norm": 0.36475369334220886,
      "learning_rate": 1.1589494703087087e-05,
      "loss": 0.531,
      "step": 29301
    },
    {
      "epoch": 0.9001320922802813,
      "grad_norm": 0.3607562184333801,
      "learning_rate": 1.1589017567935083e-05,
      "loss": 0.5158,
      "step": 29302
    },
    {
      "epoch": 0.9001628114152306,
      "grad_norm": 0.38439294695854187,
      "learning_rate": 1.1588540429071817e-05,
      "loss": 0.5305,
      "step": 29303
    },
    {
      "epoch": 0.9001935305501797,
      "grad_norm": 0.3898003399372101,
      "learning_rate": 1.1588063286498405e-05,
      "loss": 0.4943,
      "step": 29304
    },
    {
      "epoch": 0.9002242496851288,
      "grad_norm": 0.33420833945274353,
      "learning_rate": 1.1587586140215961e-05,
      "loss": 0.5181,
      "step": 29305
    },
    {
      "epoch": 0.900254968820078,
      "grad_norm": 0.3654800355434418,
      "learning_rate": 1.1587108990225595e-05,
      "loss": 0.5045,
      "step": 29306
    },
    {
      "epoch": 0.9002856879550272,
      "grad_norm": 0.3554096221923828,
      "learning_rate": 1.1586631836528427e-05,
      "loss": 0.5289,
      "step": 29307
    },
    {
      "epoch": 0.9003164070899764,
      "grad_norm": 0.350625604391098,
      "learning_rate": 1.1586154679125569e-05,
      "loss": 0.567,
      "step": 29308
    },
    {
      "epoch": 0.9003471262249255,
      "grad_norm": 0.3476911783218384,
      "learning_rate": 1.1585677518018137e-05,
      "loss": 0.5907,
      "step": 29309
    },
    {
      "epoch": 0.9003778453598746,
      "grad_norm": 0.3718331754207611,
      "learning_rate": 1.158520035320724e-05,
      "loss": 0.5615,
      "step": 29310
    },
    {
      "epoch": 0.9004085644948239,
      "grad_norm": 0.3689592182636261,
      "learning_rate": 1.1584723184694002e-05,
      "loss": 0.5505,
      "step": 29311
    },
    {
      "epoch": 0.900439283629773,
      "grad_norm": 0.352777361869812,
      "learning_rate": 1.1584246012479532e-05,
      "loss": 0.5831,
      "step": 29312
    },
    {
      "epoch": 0.9004700027647221,
      "grad_norm": 0.40394285321235657,
      "learning_rate": 1.1583768836564943e-05,
      "loss": 0.5759,
      "step": 29313
    },
    {
      "epoch": 0.9005007218996713,
      "grad_norm": 0.3612789511680603,
      "learning_rate": 1.1583291656951353e-05,
      "loss": 0.5473,
      "step": 29314
    },
    {
      "epoch": 0.9005314410346205,
      "grad_norm": 0.400181382894516,
      "learning_rate": 1.1582814473639874e-05,
      "loss": 0.5217,
      "step": 29315
    },
    {
      "epoch": 0.9005621601695696,
      "grad_norm": 0.4082617461681366,
      "learning_rate": 1.158233728663162e-05,
      "loss": 0.5818,
      "step": 29316
    },
    {
      "epoch": 0.9005928793045188,
      "grad_norm": 0.39978116750717163,
      "learning_rate": 1.1581860095927708e-05,
      "loss": 0.4939,
      "step": 29317
    },
    {
      "epoch": 0.9006235984394679,
      "grad_norm": 0.41021767258644104,
      "learning_rate": 1.1581382901529253e-05,
      "loss": 0.5646,
      "step": 29318
    },
    {
      "epoch": 0.900654317574417,
      "grad_norm": 0.35087695717811584,
      "learning_rate": 1.1580905703437364e-05,
      "loss": 0.5645,
      "step": 29319
    },
    {
      "epoch": 0.9006850367093663,
      "grad_norm": 0.3354513347148895,
      "learning_rate": 1.1580428501653162e-05,
      "loss": 0.6336,
      "step": 29320
    },
    {
      "epoch": 0.9007157558443154,
      "grad_norm": 0.37321850657463074,
      "learning_rate": 1.1579951296177755e-05,
      "loss": 0.4816,
      "step": 29321
    },
    {
      "epoch": 0.9007464749792646,
      "grad_norm": 0.4024014174938202,
      "learning_rate": 1.1579474087012268e-05,
      "loss": 0.5548,
      "step": 29322
    },
    {
      "epoch": 0.9007771941142138,
      "grad_norm": 0.3545786440372467,
      "learning_rate": 1.1578996874157806e-05,
      "loss": 0.4985,
      "step": 29323
    },
    {
      "epoch": 0.9008079132491629,
      "grad_norm": 0.37873250246047974,
      "learning_rate": 1.1578519657615484e-05,
      "loss": 0.5625,
      "step": 29324
    },
    {
      "epoch": 0.9008386323841121,
      "grad_norm": 0.38367074728012085,
      "learning_rate": 1.1578042437386423e-05,
      "loss": 0.6365,
      "step": 29325
    },
    {
      "epoch": 0.9008693515190612,
      "grad_norm": 0.4516834020614624,
      "learning_rate": 1.157756521347173e-05,
      "loss": 0.5662,
      "step": 29326
    },
    {
      "epoch": 0.9009000706540103,
      "grad_norm": 0.3553648293018341,
      "learning_rate": 1.1577087985872526e-05,
      "loss": 0.5973,
      "step": 29327
    },
    {
      "epoch": 0.9009307897889596,
      "grad_norm": 0.39309701323509216,
      "learning_rate": 1.157661075458992e-05,
      "loss": 0.5436,
      "step": 29328
    },
    {
      "epoch": 0.9009615089239087,
      "grad_norm": 0.3667060434818268,
      "learning_rate": 1.1576133519625031e-05,
      "loss": 0.5153,
      "step": 29329
    },
    {
      "epoch": 0.9009922280588578,
      "grad_norm": 0.39454346895217896,
      "learning_rate": 1.1575656280978973e-05,
      "loss": 0.5816,
      "step": 29330
    },
    {
      "epoch": 0.901022947193807,
      "grad_norm": 0.3639608323574066,
      "learning_rate": 1.1575179038652858e-05,
      "loss": 0.565,
      "step": 29331
    },
    {
      "epoch": 0.9010536663287562,
      "grad_norm": 0.3885846734046936,
      "learning_rate": 1.1574701792647805e-05,
      "loss": 0.5394,
      "step": 29332
    },
    {
      "epoch": 0.9010843854637054,
      "grad_norm": 0.35227170586586,
      "learning_rate": 1.1574224542964922e-05,
      "loss": 0.5845,
      "step": 29333
    },
    {
      "epoch": 0.9011151045986545,
      "grad_norm": 0.3654109537601471,
      "learning_rate": 1.1573747289605333e-05,
      "loss": 0.4724,
      "step": 29334
    },
    {
      "epoch": 0.9011458237336036,
      "grad_norm": 0.33935102820396423,
      "learning_rate": 1.1573270032570142e-05,
      "loss": 0.5255,
      "step": 29335
    },
    {
      "epoch": 0.9011765428685529,
      "grad_norm": 0.3269764482975006,
      "learning_rate": 1.1572792771860473e-05,
      "loss": 0.5017,
      "step": 29336
    },
    {
      "epoch": 0.901207262003502,
      "grad_norm": 0.39226067066192627,
      "learning_rate": 1.1572315507477434e-05,
      "loss": 0.619,
      "step": 29337
    },
    {
      "epoch": 0.9012379811384511,
      "grad_norm": 0.4187617301940918,
      "learning_rate": 1.1571838239422144e-05,
      "loss": 0.493,
      "step": 29338
    },
    {
      "epoch": 0.9012687002734003,
      "grad_norm": 0.3932759761810303,
      "learning_rate": 1.1571360967695716e-05,
      "loss": 0.5405,
      "step": 29339
    },
    {
      "epoch": 0.9012994194083495,
      "grad_norm": 0.3902454972267151,
      "learning_rate": 1.1570883692299264e-05,
      "loss": 0.5132,
      "step": 29340
    },
    {
      "epoch": 0.9013301385432986,
      "grad_norm": 0.4655286371707916,
      "learning_rate": 1.1570406413233904e-05,
      "loss": 0.5428,
      "step": 29341
    },
    {
      "epoch": 0.9013608576782478,
      "grad_norm": 0.3448968827724457,
      "learning_rate": 1.1569929130500748e-05,
      "loss": 0.5232,
      "step": 29342
    },
    {
      "epoch": 0.9013915768131969,
      "grad_norm": 0.41710254549980164,
      "learning_rate": 1.1569451844100917e-05,
      "loss": 0.6466,
      "step": 29343
    },
    {
      "epoch": 0.901422295948146,
      "grad_norm": 0.38822928071022034,
      "learning_rate": 1.1568974554035517e-05,
      "loss": 0.5213,
      "step": 29344
    },
    {
      "epoch": 0.9014530150830953,
      "grad_norm": 0.438874751329422,
      "learning_rate": 1.156849726030567e-05,
      "loss": 0.6552,
      "step": 29345
    },
    {
      "epoch": 0.9014837342180444,
      "grad_norm": 0.3584957420825958,
      "learning_rate": 1.1568019962912486e-05,
      "loss": 0.5814,
      "step": 29346
    },
    {
      "epoch": 0.9015144533529936,
      "grad_norm": 0.3470343351364136,
      "learning_rate": 1.1567542661857083e-05,
      "loss": 0.5395,
      "step": 29347
    },
    {
      "epoch": 0.9015451724879427,
      "grad_norm": 0.3551245331764221,
      "learning_rate": 1.1567065357140577e-05,
      "loss": 0.4768,
      "step": 29348
    },
    {
      "epoch": 0.9015758916228919,
      "grad_norm": 0.38639217615127563,
      "learning_rate": 1.1566588048764076e-05,
      "loss": 0.5956,
      "step": 29349
    },
    {
      "epoch": 0.9016066107578411,
      "grad_norm": 0.3693387806415558,
      "learning_rate": 1.1566110736728703e-05,
      "loss": 0.5252,
      "step": 29350
    },
    {
      "epoch": 0.9016373298927902,
      "grad_norm": 0.4033450782299042,
      "learning_rate": 1.1565633421035567e-05,
      "loss": 0.4851,
      "step": 29351
    },
    {
      "epoch": 0.9016680490277393,
      "grad_norm": 0.38036200404167175,
      "learning_rate": 1.1565156101685786e-05,
      "loss": 0.5792,
      "step": 29352
    },
    {
      "epoch": 0.9016987681626886,
      "grad_norm": 0.39378657937049866,
      "learning_rate": 1.1564678778680471e-05,
      "loss": 0.4818,
      "step": 29353
    },
    {
      "epoch": 0.9017294872976377,
      "grad_norm": 0.3506257236003876,
      "learning_rate": 1.1564201452020745e-05,
      "loss": 0.5307,
      "step": 29354
    },
    {
      "epoch": 0.9017602064325868,
      "grad_norm": 0.40408027172088623,
      "learning_rate": 1.1563724121707711e-05,
      "loss": 0.5547,
      "step": 29355
    },
    {
      "epoch": 0.901790925567536,
      "grad_norm": 0.394906222820282,
      "learning_rate": 1.1563246787742495e-05,
      "loss": 0.6589,
      "step": 29356
    },
    {
      "epoch": 0.9018216447024852,
      "grad_norm": 0.3898763060569763,
      "learning_rate": 1.1562769450126206e-05,
      "loss": 0.6148,
      "step": 29357
    },
    {
      "epoch": 0.9018523638374344,
      "grad_norm": 0.4264306128025055,
      "learning_rate": 1.1562292108859955e-05,
      "loss": 0.5496,
      "step": 29358
    },
    {
      "epoch": 0.9018830829723835,
      "grad_norm": 0.3806595206260681,
      "learning_rate": 1.1561814763944868e-05,
      "loss": 0.5679,
      "step": 29359
    },
    {
      "epoch": 0.9019138021073326,
      "grad_norm": 0.3467036783695221,
      "learning_rate": 1.156133741538205e-05,
      "loss": 0.5562,
      "step": 29360
    },
    {
      "epoch": 0.9019445212422819,
      "grad_norm": 0.3892757296562195,
      "learning_rate": 1.156086006317262e-05,
      "loss": 0.4643,
      "step": 29361
    },
    {
      "epoch": 0.901975240377231,
      "grad_norm": 0.3952309787273407,
      "learning_rate": 1.1560382707317693e-05,
      "loss": 0.5722,
      "step": 29362
    },
    {
      "epoch": 0.9020059595121801,
      "grad_norm": 0.37006300687789917,
      "learning_rate": 1.1559905347818384e-05,
      "loss": 0.4967,
      "step": 29363
    },
    {
      "epoch": 0.9020366786471293,
      "grad_norm": 0.3575572371482849,
      "learning_rate": 1.1559427984675803e-05,
      "loss": 0.5759,
      "step": 29364
    },
    {
      "epoch": 0.9020673977820785,
      "grad_norm": 0.41613826155662537,
      "learning_rate": 1.1558950617891074e-05,
      "loss": 0.5125,
      "step": 29365
    },
    {
      "epoch": 0.9020981169170276,
      "grad_norm": 0.3676168620586395,
      "learning_rate": 1.1558473247465304e-05,
      "loss": 0.5168,
      "step": 29366
    },
    {
      "epoch": 0.9021288360519768,
      "grad_norm": 0.3656062185764313,
      "learning_rate": 1.1557995873399612e-05,
      "loss": 0.5165,
      "step": 29367
    },
    {
      "epoch": 0.9021595551869259,
      "grad_norm": 0.3746381402015686,
      "learning_rate": 1.1557518495695112e-05,
      "loss": 0.5872,
      "step": 29368
    },
    {
      "epoch": 0.902190274321875,
      "grad_norm": 0.39362943172454834,
      "learning_rate": 1.1557041114352917e-05,
      "loss": 0.5509,
      "step": 29369
    },
    {
      "epoch": 0.9022209934568243,
      "grad_norm": 0.38215115666389465,
      "learning_rate": 1.1556563729374146e-05,
      "loss": 0.565,
      "step": 29370
    },
    {
      "epoch": 0.9022517125917734,
      "grad_norm": 0.379550963640213,
      "learning_rate": 1.155608634075991e-05,
      "loss": 0.5627,
      "step": 29371
    },
    {
      "epoch": 0.9022824317267226,
      "grad_norm": 0.358399897813797,
      "learning_rate": 1.1555608948511328e-05,
      "loss": 0.6198,
      "step": 29372
    },
    {
      "epoch": 0.9023131508616717,
      "grad_norm": 0.3549087941646576,
      "learning_rate": 1.1555131552629511e-05,
      "loss": 0.4856,
      "step": 29373
    },
    {
      "epoch": 0.9023438699966209,
      "grad_norm": 0.3918706178665161,
      "learning_rate": 1.1554654153115576e-05,
      "loss": 0.4817,
      "step": 29374
    },
    {
      "epoch": 0.9023745891315701,
      "grad_norm": 0.33043569326400757,
      "learning_rate": 1.1554176749970638e-05,
      "loss": 0.5108,
      "step": 29375
    },
    {
      "epoch": 0.9024053082665192,
      "grad_norm": 0.3278942108154297,
      "learning_rate": 1.155369934319581e-05,
      "loss": 0.4933,
      "step": 29376
    },
    {
      "epoch": 0.9024360274014683,
      "grad_norm": 0.3822532296180725,
      "learning_rate": 1.1553221932792211e-05,
      "loss": 0.6297,
      "step": 29377
    },
    {
      "epoch": 0.9024667465364176,
      "grad_norm": 0.37743616104125977,
      "learning_rate": 1.1552744518760952e-05,
      "loss": 0.5602,
      "step": 29378
    },
    {
      "epoch": 0.9024974656713667,
      "grad_norm": 0.3373430073261261,
      "learning_rate": 1.1552267101103151e-05,
      "loss": 0.5859,
      "step": 29379
    },
    {
      "epoch": 0.9025281848063158,
      "grad_norm": 0.37383541464805603,
      "learning_rate": 1.155178967981992e-05,
      "loss": 0.5499,
      "step": 29380
    },
    {
      "epoch": 0.902558903941265,
      "grad_norm": 0.37578848004341125,
      "learning_rate": 1.1551312254912377e-05,
      "loss": 0.6285,
      "step": 29381
    },
    {
      "epoch": 0.9025896230762142,
      "grad_norm": 0.4155479073524475,
      "learning_rate": 1.1550834826381636e-05,
      "loss": 0.5131,
      "step": 29382
    },
    {
      "epoch": 0.9026203422111634,
      "grad_norm": 0.35096386075019836,
      "learning_rate": 1.1550357394228811e-05,
      "loss": 0.5567,
      "step": 29383
    },
    {
      "epoch": 0.9026510613461125,
      "grad_norm": 0.39132460951805115,
      "learning_rate": 1.1549879958455019e-05,
      "loss": 0.4434,
      "step": 29384
    },
    {
      "epoch": 0.9026817804810616,
      "grad_norm": 0.3823644518852234,
      "learning_rate": 1.1549402519061372e-05,
      "loss": 0.4919,
      "step": 29385
    },
    {
      "epoch": 0.9027124996160109,
      "grad_norm": 0.3310815095901489,
      "learning_rate": 1.1548925076048992e-05,
      "loss": 0.5008,
      "step": 29386
    },
    {
      "epoch": 0.90274321875096,
      "grad_norm": 0.4212404787540436,
      "learning_rate": 1.1548447629418983e-05,
      "loss": 0.614,
      "step": 29387
    },
    {
      "epoch": 0.9027739378859091,
      "grad_norm": 0.42461031675338745,
      "learning_rate": 1.1547970179172473e-05,
      "loss": 0.541,
      "step": 29388
    },
    {
      "epoch": 0.9028046570208583,
      "grad_norm": 0.36618563532829285,
      "learning_rate": 1.1547492725310564e-05,
      "loss": 0.5486,
      "step": 29389
    },
    {
      "epoch": 0.9028353761558074,
      "grad_norm": 0.40258151292800903,
      "learning_rate": 1.1547015267834384e-05,
      "loss": 0.5282,
      "step": 29390
    },
    {
      "epoch": 0.9028660952907566,
      "grad_norm": 0.3550490140914917,
      "learning_rate": 1.1546537806745038e-05,
      "loss": 0.5591,
      "step": 29391
    },
    {
      "epoch": 0.9028968144257058,
      "grad_norm": 0.3382057249546051,
      "learning_rate": 1.1546060342043646e-05,
      "loss": 0.496,
      "step": 29392
    },
    {
      "epoch": 0.9029275335606549,
      "grad_norm": 0.3465280830860138,
      "learning_rate": 1.1545582873731323e-05,
      "loss": 0.5184,
      "step": 29393
    },
    {
      "epoch": 0.9029582526956041,
      "grad_norm": 0.4036102294921875,
      "learning_rate": 1.154510540180918e-05,
      "loss": 0.5114,
      "step": 29394
    },
    {
      "epoch": 0.9029889718305533,
      "grad_norm": 0.37061965465545654,
      "learning_rate": 1.1544627926278338e-05,
      "loss": 0.5574,
      "step": 29395
    },
    {
      "epoch": 0.9030196909655024,
      "grad_norm": 0.3728731870651245,
      "learning_rate": 1.1544150447139908e-05,
      "loss": 0.5979,
      "step": 29396
    },
    {
      "epoch": 0.9030504101004516,
      "grad_norm": 0.39472001791000366,
      "learning_rate": 1.154367296439501e-05,
      "loss": 0.5334,
      "step": 29397
    },
    {
      "epoch": 0.9030811292354007,
      "grad_norm": 0.39978158473968506,
      "learning_rate": 1.1543195478044753e-05,
      "loss": 0.493,
      "step": 29398
    },
    {
      "epoch": 0.9031118483703499,
      "grad_norm": 0.3879898488521576,
      "learning_rate": 1.1542717988090257e-05,
      "loss": 0.5546,
      "step": 29399
    },
    {
      "epoch": 0.9031425675052991,
      "grad_norm": 0.37038037180900574,
      "learning_rate": 1.1542240494532633e-05,
      "loss": 0.5781,
      "step": 29400
    },
    {
      "epoch": 0.9031732866402482,
      "grad_norm": 0.41499605774879456,
      "learning_rate": 1.1541762997373e-05,
      "loss": 0.4702,
      "step": 29401
    },
    {
      "epoch": 0.9032040057751973,
      "grad_norm": 0.3580656349658966,
      "learning_rate": 1.154128549661247e-05,
      "loss": 0.5115,
      "step": 29402
    },
    {
      "epoch": 0.9032347249101466,
      "grad_norm": 0.37814682722091675,
      "learning_rate": 1.1540807992252162e-05,
      "loss": 0.5288,
      "step": 29403
    },
    {
      "epoch": 0.9032654440450957,
      "grad_norm": 0.4046918749809265,
      "learning_rate": 1.1540330484293192e-05,
      "loss": 0.5384,
      "step": 29404
    },
    {
      "epoch": 0.9032961631800448,
      "grad_norm": 0.34232351183891296,
      "learning_rate": 1.1539852972736667e-05,
      "loss": 0.4688,
      "step": 29405
    },
    {
      "epoch": 0.903326882314994,
      "grad_norm": 0.36112868785858154,
      "learning_rate": 1.1539375457583712e-05,
      "loss": 0.5582,
      "step": 29406
    },
    {
      "epoch": 0.9033576014499431,
      "grad_norm": 0.3345273733139038,
      "learning_rate": 1.1538897938835436e-05,
      "loss": 0.5472,
      "step": 29407
    },
    {
      "epoch": 0.9033883205848924,
      "grad_norm": 0.3998262882232666,
      "learning_rate": 1.1538420416492959e-05,
      "loss": 0.6308,
      "step": 29408
    },
    {
      "epoch": 0.9034190397198415,
      "grad_norm": 0.4476866126060486,
      "learning_rate": 1.1537942890557391e-05,
      "loss": 0.5137,
      "step": 29409
    },
    {
      "epoch": 0.9034497588547906,
      "grad_norm": 0.40178605914115906,
      "learning_rate": 1.1537465361029852e-05,
      "loss": 0.648,
      "step": 29410
    },
    {
      "epoch": 0.9034804779897398,
      "grad_norm": 0.43135130405426025,
      "learning_rate": 1.1536987827911454e-05,
      "loss": 0.4734,
      "step": 29411
    },
    {
      "epoch": 0.903511197124689,
      "grad_norm": 0.3532111346721649,
      "learning_rate": 1.1536510291203313e-05,
      "loss": 0.5873,
      "step": 29412
    },
    {
      "epoch": 0.9035419162596381,
      "grad_norm": 0.3831571042537689,
      "learning_rate": 1.1536032750906548e-05,
      "loss": 0.6216,
      "step": 29413
    },
    {
      "epoch": 0.9035726353945873,
      "grad_norm": 0.3493700623512268,
      "learning_rate": 1.1535555207022266e-05,
      "loss": 0.5015,
      "step": 29414
    },
    {
      "epoch": 0.9036033545295364,
      "grad_norm": 0.3913020193576813,
      "learning_rate": 1.1535077659551592e-05,
      "loss": 0.5461,
      "step": 29415
    },
    {
      "epoch": 0.9036340736644856,
      "grad_norm": 0.3531235456466675,
      "learning_rate": 1.1534600108495635e-05,
      "loss": 0.5063,
      "step": 29416
    },
    {
      "epoch": 0.9036647927994348,
      "grad_norm": 0.3613587021827698,
      "learning_rate": 1.1534122553855514e-05,
      "loss": 0.5578,
      "step": 29417
    },
    {
      "epoch": 0.9036955119343839,
      "grad_norm": 0.4505279064178467,
      "learning_rate": 1.1533644995632338e-05,
      "loss": 0.5048,
      "step": 29418
    },
    {
      "epoch": 0.9037262310693331,
      "grad_norm": 0.3304678797721863,
      "learning_rate": 1.1533167433827233e-05,
      "loss": 0.5756,
      "step": 29419
    },
    {
      "epoch": 0.9037569502042823,
      "grad_norm": 0.37424954771995544,
      "learning_rate": 1.1532689868441304e-05,
      "loss": 0.5363,
      "step": 29420
    },
    {
      "epoch": 0.9037876693392314,
      "grad_norm": 0.3605819344520569,
      "learning_rate": 1.1532212299475672e-05,
      "loss": 0.546,
      "step": 29421
    },
    {
      "epoch": 0.9038183884741806,
      "grad_norm": 0.6737012267112732,
      "learning_rate": 1.1531734726931453e-05,
      "loss": 0.5458,
      "step": 29422
    },
    {
      "epoch": 0.9038491076091297,
      "grad_norm": 0.3869679272174835,
      "learning_rate": 1.1531257150809756e-05,
      "loss": 0.5859,
      "step": 29423
    },
    {
      "epoch": 0.9038798267440789,
      "grad_norm": 0.3604215085506439,
      "learning_rate": 1.1530779571111706e-05,
      "loss": 0.545,
      "step": 29424
    },
    {
      "epoch": 0.9039105458790281,
      "grad_norm": 0.363965779542923,
      "learning_rate": 1.153030198783841e-05,
      "loss": 0.6041,
      "step": 29425
    },
    {
      "epoch": 0.9039412650139772,
      "grad_norm": 0.38997790217399597,
      "learning_rate": 1.152982440099099e-05,
      "loss": 0.5582,
      "step": 29426
    },
    {
      "epoch": 0.9039719841489263,
      "grad_norm": 0.5612696409225464,
      "learning_rate": 1.1529346810570558e-05,
      "loss": 0.4717,
      "step": 29427
    },
    {
      "epoch": 0.9040027032838756,
      "grad_norm": 0.3752344250679016,
      "learning_rate": 1.1528869216578226e-05,
      "loss": 0.5106,
      "step": 29428
    },
    {
      "epoch": 0.9040334224188247,
      "grad_norm": 0.9133099317550659,
      "learning_rate": 1.1528391619015118e-05,
      "loss": 0.4717,
      "step": 29429
    },
    {
      "epoch": 0.9040641415537738,
      "grad_norm": 0.39173755049705505,
      "learning_rate": 1.152791401788234e-05,
      "loss": 0.5681,
      "step": 29430
    },
    {
      "epoch": 0.904094860688723,
      "grad_norm": 0.44839930534362793,
      "learning_rate": 1.1527436413181018e-05,
      "loss": 0.5804,
      "step": 29431
    },
    {
      "epoch": 0.9041255798236721,
      "grad_norm": 0.3425450026988983,
      "learning_rate": 1.1526958804912254e-05,
      "loss": 0.4021,
      "step": 29432
    },
    {
      "epoch": 0.9041562989586214,
      "grad_norm": 0.4432523250579834,
      "learning_rate": 1.1526481193077178e-05,
      "loss": 0.5542,
      "step": 29433
    },
    {
      "epoch": 0.9041870180935705,
      "grad_norm": 0.3860453963279724,
      "learning_rate": 1.1526003577676895e-05,
      "loss": 0.5358,
      "step": 29434
    },
    {
      "epoch": 0.9042177372285196,
      "grad_norm": 0.3541328012943268,
      "learning_rate": 1.1525525958712525e-05,
      "loss": 0.5711,
      "step": 29435
    },
    {
      "epoch": 0.9042484563634688,
      "grad_norm": 0.4939759373664856,
      "learning_rate": 1.152504833618518e-05,
      "loss": 0.5032,
      "step": 29436
    },
    {
      "epoch": 0.904279175498418,
      "grad_norm": 0.37140196561813354,
      "learning_rate": 1.1524570710095981e-05,
      "loss": 0.5434,
      "step": 29437
    },
    {
      "epoch": 0.9043098946333671,
      "grad_norm": 0.39834144711494446,
      "learning_rate": 1.1524093080446039e-05,
      "loss": 0.5636,
      "step": 29438
    },
    {
      "epoch": 0.9043406137683163,
      "grad_norm": 0.38704395294189453,
      "learning_rate": 1.1523615447236471e-05,
      "loss": 0.5612,
      "step": 29439
    },
    {
      "epoch": 0.9043713329032654,
      "grad_norm": 0.44223952293395996,
      "learning_rate": 1.1523137810468394e-05,
      "loss": 0.5445,
      "step": 29440
    },
    {
      "epoch": 0.9044020520382146,
      "grad_norm": 0.3757840394973755,
      "learning_rate": 1.1522660170142922e-05,
      "loss": 0.5421,
      "step": 29441
    },
    {
      "epoch": 0.9044327711731638,
      "grad_norm": 0.36519864201545715,
      "learning_rate": 1.1522182526261172e-05,
      "loss": 0.5757,
      "step": 29442
    },
    {
      "epoch": 0.9044634903081129,
      "grad_norm": 0.4136393070220947,
      "learning_rate": 1.1521704878824257e-05,
      "loss": 0.5631,
      "step": 29443
    },
    {
      "epoch": 0.9044942094430621,
      "grad_norm": 0.3771471679210663,
      "learning_rate": 1.1521227227833294e-05,
      "loss": 0.4907,
      "step": 29444
    },
    {
      "epoch": 0.9045249285780113,
      "grad_norm": 0.3471463620662689,
      "learning_rate": 1.15207495732894e-05,
      "loss": 0.5038,
      "step": 29445
    },
    {
      "epoch": 0.9045556477129604,
      "grad_norm": 0.34786853194236755,
      "learning_rate": 1.1520271915193686e-05,
      "loss": 0.5156,
      "step": 29446
    },
    {
      "epoch": 0.9045863668479096,
      "grad_norm": 0.3503272831439972,
      "learning_rate": 1.1519794253547274e-05,
      "loss": 0.562,
      "step": 29447
    },
    {
      "epoch": 0.9046170859828587,
      "grad_norm": 0.41893458366394043,
      "learning_rate": 1.1519316588351274e-05,
      "loss": 0.575,
      "step": 29448
    },
    {
      "epoch": 0.9046478051178078,
      "grad_norm": 0.3731043040752411,
      "learning_rate": 1.1518838919606808e-05,
      "loss": 0.5737,
      "step": 29449
    },
    {
      "epoch": 0.9046785242527571,
      "grad_norm": 0.37803924083709717,
      "learning_rate": 1.1518361247314982e-05,
      "loss": 0.6137,
      "step": 29450
    },
    {
      "epoch": 0.9047092433877062,
      "grad_norm": 0.3577786087989807,
      "learning_rate": 1.1517883571476923e-05,
      "loss": 0.5069,
      "step": 29451
    },
    {
      "epoch": 0.9047399625226553,
      "grad_norm": 0.3638598620891571,
      "learning_rate": 1.1517405892093736e-05,
      "loss": 0.5991,
      "step": 29452
    },
    {
      "epoch": 0.9047706816576045,
      "grad_norm": 0.3807497024536133,
      "learning_rate": 1.1516928209166544e-05,
      "loss": 0.544,
      "step": 29453
    },
    {
      "epoch": 0.9048014007925537,
      "grad_norm": 0.37895667552948,
      "learning_rate": 1.1516450522696458e-05,
      "loss": 0.4971,
      "step": 29454
    },
    {
      "epoch": 0.9048321199275028,
      "grad_norm": 0.3638170659542084,
      "learning_rate": 1.1515972832684598e-05,
      "loss": 0.5596,
      "step": 29455
    },
    {
      "epoch": 0.904862839062452,
      "grad_norm": 0.42452988028526306,
      "learning_rate": 1.1515495139132078e-05,
      "loss": 0.5141,
      "step": 29456
    },
    {
      "epoch": 0.9048935581974011,
      "grad_norm": 0.3569198250770569,
      "learning_rate": 1.151501744204001e-05,
      "loss": 0.4981,
      "step": 29457
    },
    {
      "epoch": 0.9049242773323504,
      "grad_norm": 0.3679662048816681,
      "learning_rate": 1.1514539741409516e-05,
      "loss": 0.4425,
      "step": 29458
    },
    {
      "epoch": 0.9049549964672995,
      "grad_norm": 0.41320639848709106,
      "learning_rate": 1.151406203724171e-05,
      "loss": 0.6383,
      "step": 29459
    },
    {
      "epoch": 0.9049857156022486,
      "grad_norm": 0.5240267515182495,
      "learning_rate": 1.1513584329537703e-05,
      "loss": 0.5207,
      "step": 29460
    },
    {
      "epoch": 0.9050164347371978,
      "grad_norm": 0.3486120402812958,
      "learning_rate": 1.1513106618298618e-05,
      "loss": 0.5762,
      "step": 29461
    },
    {
      "epoch": 0.905047153872147,
      "grad_norm": 0.41291341185569763,
      "learning_rate": 1.1512628903525563e-05,
      "loss": 0.5896,
      "step": 29462
    },
    {
      "epoch": 0.9050778730070961,
      "grad_norm": 0.35106563568115234,
      "learning_rate": 1.151215118521966e-05,
      "loss": 0.5985,
      "step": 29463
    },
    {
      "epoch": 0.9051085921420453,
      "grad_norm": 0.3914472162723541,
      "learning_rate": 1.1511673463382018e-05,
      "loss": 0.5216,
      "step": 29464
    },
    {
      "epoch": 0.9051393112769944,
      "grad_norm": 0.4021047353744507,
      "learning_rate": 1.1511195738013763e-05,
      "loss": 0.5353,
      "step": 29465
    },
    {
      "epoch": 0.9051700304119435,
      "grad_norm": 0.5029441714286804,
      "learning_rate": 1.1510718009116e-05,
      "loss": 0.4772,
      "step": 29466
    },
    {
      "epoch": 0.9052007495468928,
      "grad_norm": 0.35925212502479553,
      "learning_rate": 1.1510240276689853e-05,
      "loss": 0.5767,
      "step": 29467
    },
    {
      "epoch": 0.9052314686818419,
      "grad_norm": 0.41069847345352173,
      "learning_rate": 1.150976254073643e-05,
      "loss": 0.54,
      "step": 29468
    },
    {
      "epoch": 0.9052621878167911,
      "grad_norm": 0.33626899123191833,
      "learning_rate": 1.1509284801256857e-05,
      "loss": 0.6292,
      "step": 29469
    },
    {
      "epoch": 0.9052929069517403,
      "grad_norm": 0.3639281690120697,
      "learning_rate": 1.1508807058252241e-05,
      "loss": 0.5584,
      "step": 29470
    },
    {
      "epoch": 0.9053236260866894,
      "grad_norm": 0.3964698016643524,
      "learning_rate": 1.15083293117237e-05,
      "loss": 0.6177,
      "step": 29471
    },
    {
      "epoch": 0.9053543452216386,
      "grad_norm": 0.45813262462615967,
      "learning_rate": 1.1507851561672355e-05,
      "loss": 0.5604,
      "step": 29472
    },
    {
      "epoch": 0.9053850643565877,
      "grad_norm": 0.38048255443573,
      "learning_rate": 1.1507373808099312e-05,
      "loss": 0.5549,
      "step": 29473
    },
    {
      "epoch": 0.9054157834915368,
      "grad_norm": 0.5198050141334534,
      "learning_rate": 1.1506896051005694e-05,
      "loss": 0.5112,
      "step": 29474
    },
    {
      "epoch": 0.9054465026264861,
      "grad_norm": 0.3665630519390106,
      "learning_rate": 1.1506418290392611e-05,
      "loss": 0.5147,
      "step": 29475
    },
    {
      "epoch": 0.9054772217614352,
      "grad_norm": 0.3384034335613251,
      "learning_rate": 1.150594052626119e-05,
      "loss": 0.5248,
      "step": 29476
    },
    {
      "epoch": 0.9055079408963843,
      "grad_norm": 0.36701327562332153,
      "learning_rate": 1.1505462758612533e-05,
      "loss": 0.5285,
      "step": 29477
    },
    {
      "epoch": 0.9055386600313335,
      "grad_norm": 0.44184914231300354,
      "learning_rate": 1.150498498744777e-05,
      "loss": 0.5466,
      "step": 29478
    },
    {
      "epoch": 0.9055693791662827,
      "grad_norm": 0.3685563802719116,
      "learning_rate": 1.1504507212768006e-05,
      "loss": 0.5824,
      "step": 29479
    },
    {
      "epoch": 0.9056000983012319,
      "grad_norm": 0.37756574153900146,
      "learning_rate": 1.1504029434574358e-05,
      "loss": 0.6342,
      "step": 29480
    },
    {
      "epoch": 0.905630817436181,
      "grad_norm": 0.3540154695510864,
      "learning_rate": 1.1503551652867948e-05,
      "loss": 0.6215,
      "step": 29481
    },
    {
      "epoch": 0.9056615365711301,
      "grad_norm": 0.3383459746837616,
      "learning_rate": 1.1503073867649886e-05,
      "loss": 0.5218,
      "step": 29482
    },
    {
      "epoch": 0.9056922557060794,
      "grad_norm": 0.38150137662887573,
      "learning_rate": 1.1502596078921292e-05,
      "loss": 0.4969,
      "step": 29483
    },
    {
      "epoch": 0.9057229748410285,
      "grad_norm": 0.34056535363197327,
      "learning_rate": 1.1502118286683275e-05,
      "loss": 0.5385,
      "step": 29484
    },
    {
      "epoch": 0.9057536939759776,
      "grad_norm": 0.36817821860313416,
      "learning_rate": 1.150164049093696e-05,
      "loss": 0.5344,
      "step": 29485
    },
    {
      "epoch": 0.9057844131109268,
      "grad_norm": 0.36714646220207214,
      "learning_rate": 1.1501162691683456e-05,
      "loss": 0.5563,
      "step": 29486
    },
    {
      "epoch": 0.905815132245876,
      "grad_norm": 0.34227830171585083,
      "learning_rate": 1.1500684888923886e-05,
      "loss": 0.536,
      "step": 29487
    },
    {
      "epoch": 0.9058458513808251,
      "grad_norm": 0.383563756942749,
      "learning_rate": 1.1500207082659358e-05,
      "loss": 0.5802,
      "step": 29488
    },
    {
      "epoch": 0.9058765705157743,
      "grad_norm": 0.3417356312274933,
      "learning_rate": 1.1499729272890994e-05,
      "loss": 0.4278,
      "step": 29489
    },
    {
      "epoch": 0.9059072896507234,
      "grad_norm": 0.3877358138561249,
      "learning_rate": 1.1499251459619907e-05,
      "loss": 0.5389,
      "step": 29490
    },
    {
      "epoch": 0.9059380087856725,
      "grad_norm": 0.39652976393699646,
      "learning_rate": 1.1498773642847212e-05,
      "loss": 0.5731,
      "step": 29491
    },
    {
      "epoch": 0.9059687279206218,
      "grad_norm": 0.6378154754638672,
      "learning_rate": 1.1498295822574028e-05,
      "loss": 0.5213,
      "step": 29492
    },
    {
      "epoch": 0.9059994470555709,
      "grad_norm": 0.3806939721107483,
      "learning_rate": 1.1497817998801467e-05,
      "loss": 0.5884,
      "step": 29493
    },
    {
      "epoch": 0.9060301661905201,
      "grad_norm": 0.4073050320148468,
      "learning_rate": 1.1497340171530649e-05,
      "loss": 0.5494,
      "step": 29494
    },
    {
      "epoch": 0.9060608853254692,
      "grad_norm": 0.45103198289871216,
      "learning_rate": 1.1496862340762687e-05,
      "loss": 0.5744,
      "step": 29495
    },
    {
      "epoch": 0.9060916044604184,
      "grad_norm": 0.37117940187454224,
      "learning_rate": 1.1496384506498701e-05,
      "loss": 0.5546,
      "step": 29496
    },
    {
      "epoch": 0.9061223235953676,
      "grad_norm": 0.37641575932502747,
      "learning_rate": 1.1495906668739804e-05,
      "loss": 0.5062,
      "step": 29497
    },
    {
      "epoch": 0.9061530427303167,
      "grad_norm": 0.37278982996940613,
      "learning_rate": 1.1495428827487111e-05,
      "loss": 0.515,
      "step": 29498
    },
    {
      "epoch": 0.9061837618652658,
      "grad_norm": 0.8541435599327087,
      "learning_rate": 1.1494950982741741e-05,
      "loss": 0.5457,
      "step": 29499
    },
    {
      "epoch": 0.9062144810002151,
      "grad_norm": 0.39259347319602966,
      "learning_rate": 1.149447313450481e-05,
      "loss": 0.5847,
      "step": 29500
    },
    {
      "epoch": 0.9062452001351642,
      "grad_norm": 0.3490196764469147,
      "learning_rate": 1.149399528277743e-05,
      "loss": 0.5265,
      "step": 29501
    },
    {
      "epoch": 0.9062759192701133,
      "grad_norm": 0.3564862906932831,
      "learning_rate": 1.1493517427560721e-05,
      "loss": 0.5047,
      "step": 29502
    },
    {
      "epoch": 0.9063066384050625,
      "grad_norm": 0.3381771147251129,
      "learning_rate": 1.1493039568855797e-05,
      "loss": 0.5618,
      "step": 29503
    },
    {
      "epoch": 0.9063373575400117,
      "grad_norm": 0.4198782742023468,
      "learning_rate": 1.1492561706663774e-05,
      "loss": 0.5167,
      "step": 29504
    },
    {
      "epoch": 0.9063680766749609,
      "grad_norm": 0.37168067693710327,
      "learning_rate": 1.149208384098577e-05,
      "loss": 0.5311,
      "step": 29505
    },
    {
      "epoch": 0.90639879580991,
      "grad_norm": 0.381930410861969,
      "learning_rate": 1.1491605971822898e-05,
      "loss": 0.4738,
      "step": 29506
    },
    {
      "epoch": 0.9064295149448591,
      "grad_norm": 0.41776034235954285,
      "learning_rate": 1.1491128099176281e-05,
      "loss": 0.6012,
      "step": 29507
    },
    {
      "epoch": 0.9064602340798084,
      "grad_norm": 0.39596453309059143,
      "learning_rate": 1.149065022304703e-05,
      "loss": 0.5461,
      "step": 29508
    },
    {
      "epoch": 0.9064909532147575,
      "grad_norm": 0.3479979932308197,
      "learning_rate": 1.1490172343436257e-05,
      "loss": 0.3906,
      "step": 29509
    },
    {
      "epoch": 0.9065216723497066,
      "grad_norm": 0.3631843030452728,
      "learning_rate": 1.1489694460345085e-05,
      "loss": 0.6432,
      "step": 29510
    },
    {
      "epoch": 0.9065523914846558,
      "grad_norm": 0.3631741404533386,
      "learning_rate": 1.1489216573774622e-05,
      "loss": 0.5822,
      "step": 29511
    },
    {
      "epoch": 0.906583110619605,
      "grad_norm": 0.40315213799476624,
      "learning_rate": 1.1488738683725996e-05,
      "loss": 0.5535,
      "step": 29512
    },
    {
      "epoch": 0.9066138297545541,
      "grad_norm": 0.48762133717536926,
      "learning_rate": 1.1488260790200315e-05,
      "loss": 0.6171,
      "step": 29513
    },
    {
      "epoch": 0.9066445488895033,
      "grad_norm": 0.42865586280822754,
      "learning_rate": 1.1487782893198695e-05,
      "loss": 0.507,
      "step": 29514
    },
    {
      "epoch": 0.9066752680244524,
      "grad_norm": 0.35933801531791687,
      "learning_rate": 1.1487304992722259e-05,
      "loss": 0.5183,
      "step": 29515
    },
    {
      "epoch": 0.9067059871594015,
      "grad_norm": 0.443646639585495,
      "learning_rate": 1.1486827088772113e-05,
      "loss": 0.5339,
      "step": 29516
    },
    {
      "epoch": 0.9067367062943508,
      "grad_norm": 0.39196091890335083,
      "learning_rate": 1.1486349181349382e-05,
      "loss": 0.483,
      "step": 29517
    },
    {
      "epoch": 0.9067674254292999,
      "grad_norm": 1.86117422580719,
      "learning_rate": 1.1485871270455177e-05,
      "loss": 0.5631,
      "step": 29518
    },
    {
      "epoch": 0.9067981445642491,
      "grad_norm": 0.5529735088348389,
      "learning_rate": 1.1485393356090618e-05,
      "loss": 0.6066,
      "step": 29519
    },
    {
      "epoch": 0.9068288636991982,
      "grad_norm": 0.3888844847679138,
      "learning_rate": 1.1484915438256816e-05,
      "loss": 0.5468,
      "step": 29520
    },
    {
      "epoch": 0.9068595828341474,
      "grad_norm": 0.4145415127277374,
      "learning_rate": 1.1484437516954893e-05,
      "loss": 0.5517,
      "step": 29521
    },
    {
      "epoch": 0.9068903019690966,
      "grad_norm": 0.3572744131088257,
      "learning_rate": 1.148395959218596e-05,
      "loss": 0.521,
      "step": 29522
    },
    {
      "epoch": 0.9069210211040457,
      "grad_norm": 0.4214564859867096,
      "learning_rate": 1.1483481663951137e-05,
      "loss": 0.5702,
      "step": 29523
    },
    {
      "epoch": 0.9069517402389948,
      "grad_norm": 0.41523849964141846,
      "learning_rate": 1.1483003732251541e-05,
      "loss": 0.5074,
      "step": 29524
    },
    {
      "epoch": 0.9069824593739441,
      "grad_norm": 0.4014154374599457,
      "learning_rate": 1.1482525797088284e-05,
      "loss": 0.5913,
      "step": 29525
    },
    {
      "epoch": 0.9070131785088932,
      "grad_norm": 0.3834599256515503,
      "learning_rate": 1.1482047858462484e-05,
      "loss": 0.5363,
      "step": 29526
    },
    {
      "epoch": 0.9070438976438423,
      "grad_norm": 0.37780606746673584,
      "learning_rate": 1.148156991637526e-05,
      "loss": 0.5049,
      "step": 29527
    },
    {
      "epoch": 0.9070746167787915,
      "grad_norm": 0.4346534013748169,
      "learning_rate": 1.1481091970827725e-05,
      "loss": 0.5823,
      "step": 29528
    },
    {
      "epoch": 0.9071053359137407,
      "grad_norm": 0.36096107959747314,
      "learning_rate": 1.148061402182099e-05,
      "loss": 0.5793,
      "step": 29529
    },
    {
      "epoch": 0.9071360550486899,
      "grad_norm": 0.36910533905029297,
      "learning_rate": 1.1480136069356185e-05,
      "loss": 0.5961,
      "step": 29530
    },
    {
      "epoch": 0.907166774183639,
      "grad_norm": 0.3781280517578125,
      "learning_rate": 1.147965811343442e-05,
      "loss": 0.5514,
      "step": 29531
    },
    {
      "epoch": 0.9071974933185881,
      "grad_norm": 0.4799307882785797,
      "learning_rate": 1.1479180154056806e-05,
      "loss": 0.5142,
      "step": 29532
    },
    {
      "epoch": 0.9072282124535374,
      "grad_norm": 0.37554270029067993,
      "learning_rate": 1.1478702191224465e-05,
      "loss": 0.4771,
      "step": 29533
    },
    {
      "epoch": 0.9072589315884865,
      "grad_norm": 0.36259493231773376,
      "learning_rate": 1.147822422493851e-05,
      "loss": 0.5648,
      "step": 29534
    },
    {
      "epoch": 0.9072896507234356,
      "grad_norm": 0.3428749144077301,
      "learning_rate": 1.1477746255200062e-05,
      "loss": 0.4366,
      "step": 29535
    },
    {
      "epoch": 0.9073203698583848,
      "grad_norm": 0.36835846304893494,
      "learning_rate": 1.1477268282010231e-05,
      "loss": 0.569,
      "step": 29536
    },
    {
      "epoch": 0.9073510889933339,
      "grad_norm": 0.3937818109989166,
      "learning_rate": 1.147679030537014e-05,
      "loss": 0.4383,
      "step": 29537
    },
    {
      "epoch": 0.9073818081282831,
      "grad_norm": 0.37227651476860046,
      "learning_rate": 1.1476312325280901e-05,
      "loss": 0.6195,
      "step": 29538
    },
    {
      "epoch": 0.9074125272632323,
      "grad_norm": 0.3720909059047699,
      "learning_rate": 1.147583434174363e-05,
      "loss": 0.5492,
      "step": 29539
    },
    {
      "epoch": 0.9074432463981814,
      "grad_norm": 0.3508339822292328,
      "learning_rate": 1.1475356354759446e-05,
      "loss": 0.5459,
      "step": 29540
    },
    {
      "epoch": 0.9074739655331305,
      "grad_norm": 0.33086341619491577,
      "learning_rate": 1.1474878364329464e-05,
      "loss": 0.5566,
      "step": 29541
    },
    {
      "epoch": 0.9075046846680798,
      "grad_norm": 0.329486221075058,
      "learning_rate": 1.1474400370454804e-05,
      "loss": 0.5409,
      "step": 29542
    },
    {
      "epoch": 0.9075354038030289,
      "grad_norm": 0.36579620838165283,
      "learning_rate": 1.1473922373136574e-05,
      "loss": 0.561,
      "step": 29543
    },
    {
      "epoch": 0.9075661229379781,
      "grad_norm": 0.3904598355293274,
      "learning_rate": 1.1473444372375899e-05,
      "loss": 0.5873,
      "step": 29544
    },
    {
      "epoch": 0.9075968420729272,
      "grad_norm": 0.38605740666389465,
      "learning_rate": 1.1472966368173887e-05,
      "loss": 0.5831,
      "step": 29545
    },
    {
      "epoch": 0.9076275612078764,
      "grad_norm": 0.39480075240135193,
      "learning_rate": 1.1472488360531664e-05,
      "loss": 0.5488,
      "step": 29546
    },
    {
      "epoch": 0.9076582803428256,
      "grad_norm": 0.3931356370449066,
      "learning_rate": 1.147201034945034e-05,
      "loss": 0.4858,
      "step": 29547
    },
    {
      "epoch": 0.9076889994777747,
      "grad_norm": 0.3832562565803528,
      "learning_rate": 1.147153233493103e-05,
      "loss": 0.5233,
      "step": 29548
    },
    {
      "epoch": 0.9077197186127238,
      "grad_norm": 0.3783801794052124,
      "learning_rate": 1.1471054316974857e-05,
      "loss": 0.6053,
      "step": 29549
    },
    {
      "epoch": 0.9077504377476731,
      "grad_norm": 0.41295722126960754,
      "learning_rate": 1.1470576295582934e-05,
      "loss": 0.4785,
      "step": 29550
    },
    {
      "epoch": 0.9077811568826222,
      "grad_norm": 0.3531751036643982,
      "learning_rate": 1.1470098270756375e-05,
      "loss": 0.5391,
      "step": 29551
    },
    {
      "epoch": 0.9078118760175713,
      "grad_norm": 0.3744320273399353,
      "learning_rate": 1.14696202424963e-05,
      "loss": 0.6503,
      "step": 29552
    },
    {
      "epoch": 0.9078425951525205,
      "grad_norm": 0.35439440608024597,
      "learning_rate": 1.1469142210803825e-05,
      "loss": 0.5061,
      "step": 29553
    },
    {
      "epoch": 0.9078733142874696,
      "grad_norm": 0.47770047187805176,
      "learning_rate": 1.1468664175680067e-05,
      "loss": 0.5493,
      "step": 29554
    },
    {
      "epoch": 0.9079040334224189,
      "grad_norm": 0.38669562339782715,
      "learning_rate": 1.1468186137126138e-05,
      "loss": 0.5443,
      "step": 29555
    },
    {
      "epoch": 0.907934752557368,
      "grad_norm": 0.36570292711257935,
      "learning_rate": 1.146770809514316e-05,
      "loss": 0.5182,
      "step": 29556
    },
    {
      "epoch": 0.9079654716923171,
      "grad_norm": 0.34998103976249695,
      "learning_rate": 1.1467230049732248e-05,
      "loss": 0.5052,
      "step": 29557
    },
    {
      "epoch": 0.9079961908272663,
      "grad_norm": 0.3780595660209656,
      "learning_rate": 1.1466752000894515e-05,
      "loss": 0.5483,
      "step": 29558
    },
    {
      "epoch": 0.9080269099622155,
      "grad_norm": 0.3355556130409241,
      "learning_rate": 1.1466273948631082e-05,
      "loss": 0.489,
      "step": 29559
    },
    {
      "epoch": 0.9080576290971646,
      "grad_norm": 0.35726282000541687,
      "learning_rate": 1.1465795892943064e-05,
      "loss": 0.5221,
      "step": 29560
    },
    {
      "epoch": 0.9080883482321138,
      "grad_norm": 0.36109283566474915,
      "learning_rate": 1.1465317833831575e-05,
      "loss": 0.5124,
      "step": 29561
    },
    {
      "epoch": 0.9081190673670629,
      "grad_norm": 0.3594791293144226,
      "learning_rate": 1.1464839771297738e-05,
      "loss": 0.5449,
      "step": 29562
    },
    {
      "epoch": 0.9081497865020121,
      "grad_norm": 0.3460688591003418,
      "learning_rate": 1.1464361705342661e-05,
      "loss": 0.5779,
      "step": 29563
    },
    {
      "epoch": 0.9081805056369613,
      "grad_norm": 0.9237785339355469,
      "learning_rate": 1.1463883635967467e-05,
      "loss": 0.574,
      "step": 29564
    },
    {
      "epoch": 0.9082112247719104,
      "grad_norm": 0.47423872351646423,
      "learning_rate": 1.1463405563173272e-05,
      "loss": 0.4919,
      "step": 29565
    },
    {
      "epoch": 0.9082419439068595,
      "grad_norm": 0.38879773020744324,
      "learning_rate": 1.1462927486961187e-05,
      "loss": 0.5354,
      "step": 29566
    },
    {
      "epoch": 0.9082726630418088,
      "grad_norm": 0.38508936762809753,
      "learning_rate": 1.1462449407332337e-05,
      "loss": 0.6059,
      "step": 29567
    },
    {
      "epoch": 0.9083033821767579,
      "grad_norm": 0.3460991084575653,
      "learning_rate": 1.1461971324287831e-05,
      "loss": 0.4906,
      "step": 29568
    },
    {
      "epoch": 0.9083341013117071,
      "grad_norm": 0.42589500546455383,
      "learning_rate": 1.146149323782879e-05,
      "loss": 0.5616,
      "step": 29569
    },
    {
      "epoch": 0.9083648204466562,
      "grad_norm": 0.3404439091682434,
      "learning_rate": 1.1461015147956329e-05,
      "loss": 0.6024,
      "step": 29570
    },
    {
      "epoch": 0.9083955395816053,
      "grad_norm": 0.37429478764533997,
      "learning_rate": 1.1460537054671568e-05,
      "loss": 0.5659,
      "step": 29571
    },
    {
      "epoch": 0.9084262587165546,
      "grad_norm": 0.3752211928367615,
      "learning_rate": 1.1460058957975617e-05,
      "loss": 0.551,
      "step": 29572
    },
    {
      "epoch": 0.9084569778515037,
      "grad_norm": 0.3669992983341217,
      "learning_rate": 1.1459580857869599e-05,
      "loss": 0.4868,
      "step": 29573
    },
    {
      "epoch": 0.9084876969864528,
      "grad_norm": 0.3541378974914551,
      "learning_rate": 1.1459102754354624e-05,
      "loss": 0.542,
      "step": 29574
    },
    {
      "epoch": 0.908518416121402,
      "grad_norm": 0.3529665470123291,
      "learning_rate": 1.145862464743182e-05,
      "loss": 0.5313,
      "step": 29575
    },
    {
      "epoch": 0.9085491352563512,
      "grad_norm": 0.3300984501838684,
      "learning_rate": 1.145814653710229e-05,
      "loss": 0.4686,
      "step": 29576
    },
    {
      "epoch": 0.9085798543913003,
      "grad_norm": 0.35162582993507385,
      "learning_rate": 1.1457668423367158e-05,
      "loss": 0.533,
      "step": 29577
    },
    {
      "epoch": 0.9086105735262495,
      "grad_norm": 0.36670151352882385,
      "learning_rate": 1.1457190306227544e-05,
      "loss": 0.5328,
      "step": 29578
    },
    {
      "epoch": 0.9086412926611986,
      "grad_norm": 0.3923032581806183,
      "learning_rate": 1.1456712185684555e-05,
      "loss": 0.5744,
      "step": 29579
    },
    {
      "epoch": 0.9086720117961479,
      "grad_norm": 0.36146894097328186,
      "learning_rate": 1.1456234061739315e-05,
      "loss": 0.559,
      "step": 29580
    },
    {
      "epoch": 0.908702730931097,
      "grad_norm": 0.3578030467033386,
      "learning_rate": 1.1455755934392939e-05,
      "loss": 0.5277,
      "step": 29581
    },
    {
      "epoch": 0.9087334500660461,
      "grad_norm": 0.4160575270652771,
      "learning_rate": 1.1455277803646543e-05,
      "loss": 0.5024,
      "step": 29582
    },
    {
      "epoch": 0.9087641692009953,
      "grad_norm": 0.34450289607048035,
      "learning_rate": 1.1454799669501241e-05,
      "loss": 0.5811,
      "step": 29583
    },
    {
      "epoch": 0.9087948883359445,
      "grad_norm": 0.40066733956336975,
      "learning_rate": 1.1454321531958155e-05,
      "loss": 0.5567,
      "step": 29584
    },
    {
      "epoch": 0.9088256074708936,
      "grad_norm": 0.3794383704662323,
      "learning_rate": 1.1453843391018399e-05,
      "loss": 0.5647,
      "step": 29585
    },
    {
      "epoch": 0.9088563266058428,
      "grad_norm": 0.3834681510925293,
      "learning_rate": 1.1453365246683093e-05,
      "loss": 0.5756,
      "step": 29586
    },
    {
      "epoch": 0.9088870457407919,
      "grad_norm": 0.3843802809715271,
      "learning_rate": 1.145288709895335e-05,
      "loss": 0.4667,
      "step": 29587
    },
    {
      "epoch": 0.908917764875741,
      "grad_norm": 0.3940294086933136,
      "learning_rate": 1.1452408947830284e-05,
      "loss": 0.5043,
      "step": 29588
    },
    {
      "epoch": 0.9089484840106903,
      "grad_norm": 0.362973153591156,
      "learning_rate": 1.145193079331502e-05,
      "loss": 0.6528,
      "step": 29589
    },
    {
      "epoch": 0.9089792031456394,
      "grad_norm": 0.37068894505500793,
      "learning_rate": 1.1451452635408666e-05,
      "loss": 0.5864,
      "step": 29590
    },
    {
      "epoch": 0.9090099222805886,
      "grad_norm": 0.3772093653678894,
      "learning_rate": 1.1450974474112347e-05,
      "loss": 0.566,
      "step": 29591
    },
    {
      "epoch": 0.9090406414155378,
      "grad_norm": 0.3309723436832428,
      "learning_rate": 1.1450496309427176e-05,
      "loss": 0.4668,
      "step": 29592
    },
    {
      "epoch": 0.9090713605504869,
      "grad_norm": 0.34717467427253723,
      "learning_rate": 1.1450018141354267e-05,
      "loss": 0.5135,
      "step": 29593
    },
    {
      "epoch": 0.9091020796854361,
      "grad_norm": 0.3379620909690857,
      "learning_rate": 1.144953996989474e-05,
      "loss": 0.5358,
      "step": 29594
    },
    {
      "epoch": 0.9091327988203852,
      "grad_norm": 0.3599550426006317,
      "learning_rate": 1.1449061795049712e-05,
      "loss": 0.5284,
      "step": 29595
    },
    {
      "epoch": 0.9091635179553343,
      "grad_norm": 0.3576062321662903,
      "learning_rate": 1.14485836168203e-05,
      "loss": 0.5115,
      "step": 29596
    },
    {
      "epoch": 0.9091942370902836,
      "grad_norm": 0.38906949758529663,
      "learning_rate": 1.1448105435207615e-05,
      "loss": 0.5387,
      "step": 29597
    },
    {
      "epoch": 0.9092249562252327,
      "grad_norm": 0.3647676110267639,
      "learning_rate": 1.1447627250212783e-05,
      "loss": 0.5511,
      "step": 29598
    },
    {
      "epoch": 0.9092556753601818,
      "grad_norm": 0.4268209636211395,
      "learning_rate": 1.1447149061836915e-05,
      "loss": 0.5922,
      "step": 29599
    },
    {
      "epoch": 0.909286394495131,
      "grad_norm": 0.34292328357696533,
      "learning_rate": 1.1446670870081128e-05,
      "loss": 0.5923,
      "step": 29600
    },
    {
      "epoch": 0.9093171136300802,
      "grad_norm": 0.34966444969177246,
      "learning_rate": 1.1446192674946544e-05,
      "loss": 0.5001,
      "step": 29601
    },
    {
      "epoch": 0.9093478327650293,
      "grad_norm": 0.3914419114589691,
      "learning_rate": 1.144571447643427e-05,
      "loss": 0.5117,
      "step": 29602
    },
    {
      "epoch": 0.9093785518999785,
      "grad_norm": 0.3711423873901367,
      "learning_rate": 1.1445236274545435e-05,
      "loss": 0.4769,
      "step": 29603
    },
    {
      "epoch": 0.9094092710349276,
      "grad_norm": 0.37245336174964905,
      "learning_rate": 1.1444758069281145e-05,
      "loss": 0.5018,
      "step": 29604
    },
    {
      "epoch": 0.9094399901698769,
      "grad_norm": 0.3533836603164673,
      "learning_rate": 1.1444279860642526e-05,
      "loss": 0.5077,
      "step": 29605
    },
    {
      "epoch": 0.909470709304826,
      "grad_norm": 0.3817453384399414,
      "learning_rate": 1.1443801648630689e-05,
      "loss": 0.5909,
      "step": 29606
    },
    {
      "epoch": 0.9095014284397751,
      "grad_norm": 0.3963542580604553,
      "learning_rate": 1.1443323433246752e-05,
      "loss": 0.5982,
      "step": 29607
    },
    {
      "epoch": 0.9095321475747243,
      "grad_norm": 0.36137089133262634,
      "learning_rate": 1.144284521449183e-05,
      "loss": 0.5205,
      "step": 29608
    },
    {
      "epoch": 0.9095628667096735,
      "grad_norm": 0.34880515933036804,
      "learning_rate": 1.1442366992367046e-05,
      "loss": 0.5206,
      "step": 29609
    },
    {
      "epoch": 0.9095935858446226,
      "grad_norm": 0.39471152424812317,
      "learning_rate": 1.144188876687351e-05,
      "loss": 0.5713,
      "step": 29610
    },
    {
      "epoch": 0.9096243049795718,
      "grad_norm": 0.37558987736701965,
      "learning_rate": 1.1441410538012346e-05,
      "loss": 0.6332,
      "step": 29611
    },
    {
      "epoch": 0.9096550241145209,
      "grad_norm": 0.3571426570415497,
      "learning_rate": 1.1440932305784664e-05,
      "loss": 0.5003,
      "step": 29612
    },
    {
      "epoch": 0.90968574324947,
      "grad_norm": 0.3900526165962219,
      "learning_rate": 1.1440454070191585e-05,
      "loss": 0.5028,
      "step": 29613
    },
    {
      "epoch": 0.9097164623844193,
      "grad_norm": 0.4014030992984772,
      "learning_rate": 1.1439975831234225e-05,
      "loss": 0.5537,
      "step": 29614
    },
    {
      "epoch": 0.9097471815193684,
      "grad_norm": 0.37573039531707764,
      "learning_rate": 1.14394975889137e-05,
      "loss": 0.5554,
      "step": 29615
    },
    {
      "epoch": 0.9097779006543176,
      "grad_norm": 0.4053131639957428,
      "learning_rate": 1.1439019343231129e-05,
      "loss": 0.5562,
      "step": 29616
    },
    {
      "epoch": 0.9098086197892667,
      "grad_norm": 0.3360171318054199,
      "learning_rate": 1.1438541094187625e-05,
      "loss": 0.5374,
      "step": 29617
    },
    {
      "epoch": 0.9098393389242159,
      "grad_norm": 0.3634485602378845,
      "learning_rate": 1.1438062841784312e-05,
      "loss": 0.5466,
      "step": 29618
    },
    {
      "epoch": 0.9098700580591651,
      "grad_norm": 0.4060783088207245,
      "learning_rate": 1.14375845860223e-05,
      "loss": 0.546,
      "step": 29619
    },
    {
      "epoch": 0.9099007771941142,
      "grad_norm": 0.39347100257873535,
      "learning_rate": 1.1437106326902709e-05,
      "loss": 0.5946,
      "step": 29620
    },
    {
      "epoch": 0.9099314963290633,
      "grad_norm": 0.34627243876457214,
      "learning_rate": 1.1436628064426656e-05,
      "loss": 0.5123,
      "step": 29621
    },
    {
      "epoch": 0.9099622154640126,
      "grad_norm": 0.3908993601799011,
      "learning_rate": 1.1436149798595258e-05,
      "loss": 0.5737,
      "step": 29622
    },
    {
      "epoch": 0.9099929345989617,
      "grad_norm": 0.34931737184524536,
      "learning_rate": 1.1435671529409631e-05,
      "loss": 0.5821,
      "step": 29623
    },
    {
      "epoch": 0.9100236537339108,
      "grad_norm": 0.8863815665245056,
      "learning_rate": 1.1435193256870894e-05,
      "loss": 0.6715,
      "step": 29624
    },
    {
      "epoch": 0.91005437286886,
      "grad_norm": 0.34750527143478394,
      "learning_rate": 1.1434714980980163e-05,
      "loss": 0.52,
      "step": 29625
    },
    {
      "epoch": 0.9100850920038092,
      "grad_norm": 0.46106791496276855,
      "learning_rate": 1.1434236701738555e-05,
      "loss": 0.5807,
      "step": 29626
    },
    {
      "epoch": 0.9101158111387583,
      "grad_norm": 0.393120676279068,
      "learning_rate": 1.1433758419147187e-05,
      "loss": 0.5217,
      "step": 29627
    },
    {
      "epoch": 0.9101465302737075,
      "grad_norm": 0.3595203757286072,
      "learning_rate": 1.1433280133207174e-05,
      "loss": 0.5267,
      "step": 29628
    },
    {
      "epoch": 0.9101772494086566,
      "grad_norm": 0.36414211988449097,
      "learning_rate": 1.1432801843919638e-05,
      "loss": 0.5443,
      "step": 29629
    },
    {
      "epoch": 0.9102079685436059,
      "grad_norm": 0.3592149019241333,
      "learning_rate": 1.1432323551285693e-05,
      "loss": 0.5416,
      "step": 29630
    },
    {
      "epoch": 0.910238687678555,
      "grad_norm": 0.37364768981933594,
      "learning_rate": 1.1431845255306455e-05,
      "loss": 0.5917,
      "step": 29631
    },
    {
      "epoch": 0.9102694068135041,
      "grad_norm": 0.3437446355819702,
      "learning_rate": 1.1431366955983045e-05,
      "loss": 0.5953,
      "step": 29632
    },
    {
      "epoch": 0.9103001259484533,
      "grad_norm": 0.36530250310897827,
      "learning_rate": 1.1430888653316575e-05,
      "loss": 0.5479,
      "step": 29633
    },
    {
      "epoch": 0.9103308450834025,
      "grad_norm": 0.3453957140445709,
      "learning_rate": 1.1430410347308164e-05,
      "loss": 0.5271,
      "step": 29634
    },
    {
      "epoch": 0.9103615642183516,
      "grad_norm": 0.3812560439109802,
      "learning_rate": 1.142993203795893e-05,
      "loss": 0.5854,
      "step": 29635
    },
    {
      "epoch": 0.9103922833533008,
      "grad_norm": 0.42268821597099304,
      "learning_rate": 1.1429453725269992e-05,
      "loss": 0.4342,
      "step": 29636
    },
    {
      "epoch": 0.9104230024882499,
      "grad_norm": 0.3529781699180603,
      "learning_rate": 1.1428975409242463e-05,
      "loss": 0.5574,
      "step": 29637
    },
    {
      "epoch": 0.910453721623199,
      "grad_norm": 0.34806567430496216,
      "learning_rate": 1.1428497089877464e-05,
      "loss": 0.4603,
      "step": 29638
    },
    {
      "epoch": 0.9104844407581483,
      "grad_norm": 0.36020249128341675,
      "learning_rate": 1.1428018767176108e-05,
      "loss": 0.5276,
      "step": 29639
    },
    {
      "epoch": 0.9105151598930974,
      "grad_norm": 0.3896033763885498,
      "learning_rate": 1.1427540441139512e-05,
      "loss": 0.5345,
      "step": 29640
    },
    {
      "epoch": 0.9105458790280466,
      "grad_norm": 0.33764228224754333,
      "learning_rate": 1.1427062111768803e-05,
      "loss": 0.614,
      "step": 29641
    },
    {
      "epoch": 0.9105765981629957,
      "grad_norm": 0.35604336857795715,
      "learning_rate": 1.1426583779065086e-05,
      "loss": 0.5331,
      "step": 29642
    },
    {
      "epoch": 0.9106073172979449,
      "grad_norm": 0.327065646648407,
      "learning_rate": 1.1426105443029484e-05,
      "loss": 0.5168,
      "step": 29643
    },
    {
      "epoch": 0.9106380364328941,
      "grad_norm": 0.40635308623313904,
      "learning_rate": 1.142562710366311e-05,
      "loss": 0.5388,
      "step": 29644
    },
    {
      "epoch": 0.9106687555678432,
      "grad_norm": 0.38242319226264954,
      "learning_rate": 1.1425148760967091e-05,
      "loss": 0.4963,
      "step": 29645
    },
    {
      "epoch": 0.9106994747027923,
      "grad_norm": 0.3868727385997772,
      "learning_rate": 1.1424670414942534e-05,
      "loss": 0.6257,
      "step": 29646
    },
    {
      "epoch": 0.9107301938377416,
      "grad_norm": 0.34705081582069397,
      "learning_rate": 1.1424192065590558e-05,
      "loss": 0.5812,
      "step": 29647
    },
    {
      "epoch": 0.9107609129726907,
      "grad_norm": 0.3463880717754364,
      "learning_rate": 1.1423713712912286e-05,
      "loss": 0.5713,
      "step": 29648
    },
    {
      "epoch": 0.9107916321076398,
      "grad_norm": 0.3461008369922638,
      "learning_rate": 1.1423235356908827e-05,
      "loss": 0.5083,
      "step": 29649
    },
    {
      "epoch": 0.910822351242589,
      "grad_norm": 0.36267778277397156,
      "learning_rate": 1.1422756997581305e-05,
      "loss": 0.6224,
      "step": 29650
    },
    {
      "epoch": 0.9108530703775382,
      "grad_norm": 0.37913763523101807,
      "learning_rate": 1.1422278634930833e-05,
      "loss": 0.5013,
      "step": 29651
    },
    {
      "epoch": 0.9108837895124873,
      "grad_norm": 0.39018410444259644,
      "learning_rate": 1.1421800268958532e-05,
      "loss": 0.5807,
      "step": 29652
    },
    {
      "epoch": 0.9109145086474365,
      "grad_norm": 0.34863823652267456,
      "learning_rate": 1.1421321899665514e-05,
      "loss": 0.5863,
      "step": 29653
    },
    {
      "epoch": 0.9109452277823856,
      "grad_norm": 0.4285810887813568,
      "learning_rate": 1.1420843527052902e-05,
      "loss": 0.5614,
      "step": 29654
    },
    {
      "epoch": 0.9109759469173349,
      "grad_norm": 0.39849987626075745,
      "learning_rate": 1.142036515112181e-05,
      "loss": 0.6271,
      "step": 29655
    },
    {
      "epoch": 0.911006666052284,
      "grad_norm": 0.3470666706562042,
      "learning_rate": 1.1419886771873356e-05,
      "loss": 0.603,
      "step": 29656
    },
    {
      "epoch": 0.9110373851872331,
      "grad_norm": 0.34127500653266907,
      "learning_rate": 1.1419408389308656e-05,
      "loss": 0.5517,
      "step": 29657
    },
    {
      "epoch": 0.9110681043221823,
      "grad_norm": 0.5493097305297852,
      "learning_rate": 1.141893000342883e-05,
      "loss": 0.5826,
      "step": 29658
    },
    {
      "epoch": 0.9110988234571314,
      "grad_norm": 0.3744521141052246,
      "learning_rate": 1.1418451614234995e-05,
      "loss": 0.6696,
      "step": 29659
    },
    {
      "epoch": 0.9111295425920806,
      "grad_norm": 0.3674258291721344,
      "learning_rate": 1.1417973221728264e-05,
      "loss": 0.5317,
      "step": 29660
    },
    {
      "epoch": 0.9111602617270298,
      "grad_norm": 0.4055071771144867,
      "learning_rate": 1.141749482590976e-05,
      "loss": 0.5812,
      "step": 29661
    },
    {
      "epoch": 0.9111909808619789,
      "grad_norm": 0.37680482864379883,
      "learning_rate": 1.1417016426780598e-05,
      "loss": 0.5809,
      "step": 29662
    },
    {
      "epoch": 0.911221699996928,
      "grad_norm": 0.4018721580505371,
      "learning_rate": 1.1416538024341894e-05,
      "loss": 0.5437,
      "step": 29663
    },
    {
      "epoch": 0.9112524191318773,
      "grad_norm": 0.40797388553619385,
      "learning_rate": 1.141605961859477e-05,
      "loss": 0.6179,
      "step": 29664
    },
    {
      "epoch": 0.9112831382668264,
      "grad_norm": 0.349023699760437,
      "learning_rate": 1.1415581209540336e-05,
      "loss": 0.4502,
      "step": 29665
    },
    {
      "epoch": 0.9113138574017756,
      "grad_norm": 0.3904239535331726,
      "learning_rate": 1.1415102797179714e-05,
      "loss": 0.5599,
      "step": 29666
    },
    {
      "epoch": 0.9113445765367247,
      "grad_norm": 0.3267405033111572,
      "learning_rate": 1.141462438151402e-05,
      "loss": 0.4825,
      "step": 29667
    },
    {
      "epoch": 0.9113752956716739,
      "grad_norm": 0.38066205382347107,
      "learning_rate": 1.1414145962544375e-05,
      "loss": 0.5394,
      "step": 29668
    },
    {
      "epoch": 0.9114060148066231,
      "grad_norm": 0.3368546962738037,
      "learning_rate": 1.1413667540271888e-05,
      "loss": 0.5344,
      "step": 29669
    },
    {
      "epoch": 0.9114367339415722,
      "grad_norm": 0.43169236183166504,
      "learning_rate": 1.1413189114697686e-05,
      "loss": 0.5625,
      "step": 29670
    },
    {
      "epoch": 0.9114674530765213,
      "grad_norm": 0.3608761429786682,
      "learning_rate": 1.1412710685822881e-05,
      "loss": 0.5547,
      "step": 29671
    },
    {
      "epoch": 0.9114981722114706,
      "grad_norm": 0.38702887296676636,
      "learning_rate": 1.1412232253648592e-05,
      "loss": 0.5302,
      "step": 29672
    },
    {
      "epoch": 0.9115288913464197,
      "grad_norm": 0.3371926546096802,
      "learning_rate": 1.1411753818175935e-05,
      "loss": 0.5068,
      "step": 29673
    },
    {
      "epoch": 0.9115596104813688,
      "grad_norm": 0.3894369304180145,
      "learning_rate": 1.1411275379406029e-05,
      "loss": 0.5619,
      "step": 29674
    },
    {
      "epoch": 0.911590329616318,
      "grad_norm": 0.38616418838500977,
      "learning_rate": 1.141079693733999e-05,
      "loss": 0.5891,
      "step": 29675
    },
    {
      "epoch": 0.9116210487512671,
      "grad_norm": 0.363431841135025,
      "learning_rate": 1.1410318491978936e-05,
      "loss": 0.5973,
      "step": 29676
    },
    {
      "epoch": 0.9116517678862163,
      "grad_norm": 0.37978070974349976,
      "learning_rate": 1.1409840043323985e-05,
      "loss": 0.5617,
      "step": 29677
    },
    {
      "epoch": 0.9116824870211655,
      "grad_norm": 0.361229807138443,
      "learning_rate": 1.1409361591376253e-05,
      "loss": 0.6387,
      "step": 29678
    },
    {
      "epoch": 0.9117132061561146,
      "grad_norm": 0.3865732252597809,
      "learning_rate": 1.1408883136136862e-05,
      "loss": 0.5824,
      "step": 29679
    },
    {
      "epoch": 0.9117439252910639,
      "grad_norm": 0.34537753462791443,
      "learning_rate": 1.1408404677606923e-05,
      "loss": 0.4473,
      "step": 29680
    },
    {
      "epoch": 0.911774644426013,
      "grad_norm": 0.40693479776382446,
      "learning_rate": 1.140792621578756e-05,
      "loss": 0.554,
      "step": 29681
    },
    {
      "epoch": 0.9118053635609621,
      "grad_norm": 0.41441506147384644,
      "learning_rate": 1.1407447750679884e-05,
      "loss": 0.609,
      "step": 29682
    },
    {
      "epoch": 0.9118360826959113,
      "grad_norm": 0.7827738523483276,
      "learning_rate": 1.1406969282285013e-05,
      "loss": 0.5083,
      "step": 29683
    },
    {
      "epoch": 0.9118668018308604,
      "grad_norm": 0.40561243891716003,
      "learning_rate": 1.1406490810604074e-05,
      "loss": 0.546,
      "step": 29684
    },
    {
      "epoch": 0.9118975209658096,
      "grad_norm": 0.40101373195648193,
      "learning_rate": 1.1406012335638173e-05,
      "loss": 0.6023,
      "step": 29685
    },
    {
      "epoch": 0.9119282401007588,
      "grad_norm": 0.34067508578300476,
      "learning_rate": 1.1405533857388433e-05,
      "loss": 0.5198,
      "step": 29686
    },
    {
      "epoch": 0.9119589592357079,
      "grad_norm": 0.3718006908893585,
      "learning_rate": 1.1405055375855968e-05,
      "loss": 0.5048,
      "step": 29687
    },
    {
      "epoch": 0.911989678370657,
      "grad_norm": 0.3842949867248535,
      "learning_rate": 1.1404576891041901e-05,
      "loss": 0.5079,
      "step": 29688
    },
    {
      "epoch": 0.9120203975056063,
      "grad_norm": 0.3396540880203247,
      "learning_rate": 1.1404098402947345e-05,
      "loss": 0.5521,
      "step": 29689
    },
    {
      "epoch": 0.9120511166405554,
      "grad_norm": 0.34843090176582336,
      "learning_rate": 1.140361991157342e-05,
      "loss": 0.5489,
      "step": 29690
    },
    {
      "epoch": 0.9120818357755046,
      "grad_norm": 0.43462929129600525,
      "learning_rate": 1.1403141416921241e-05,
      "loss": 0.5438,
      "step": 29691
    },
    {
      "epoch": 0.9121125549104537,
      "grad_norm": 0.4300488233566284,
      "learning_rate": 1.1402662918991931e-05,
      "loss": 0.5462,
      "step": 29692
    },
    {
      "epoch": 0.9121432740454029,
      "grad_norm": 0.36503028869628906,
      "learning_rate": 1.1402184417786604e-05,
      "loss": 0.5223,
      "step": 29693
    },
    {
      "epoch": 0.9121739931803521,
      "grad_norm": 0.3724687397480011,
      "learning_rate": 1.1401705913306372e-05,
      "loss": 0.5063,
      "step": 29694
    },
    {
      "epoch": 0.9122047123153012,
      "grad_norm": 0.38562798500061035,
      "learning_rate": 1.1401227405552359e-05,
      "loss": 0.529,
      "step": 29695
    },
    {
      "epoch": 0.9122354314502503,
      "grad_norm": 0.3860780596733093,
      "learning_rate": 1.1400748894525684e-05,
      "loss": 0.5383,
      "step": 29696
    },
    {
      "epoch": 0.9122661505851996,
      "grad_norm": 0.41153228282928467,
      "learning_rate": 1.1400270380227464e-05,
      "loss": 0.5681,
      "step": 29697
    },
    {
      "epoch": 0.9122968697201487,
      "grad_norm": 0.40747809410095215,
      "learning_rate": 1.139979186265881e-05,
      "loss": 0.6081,
      "step": 29698
    },
    {
      "epoch": 0.9123275888550978,
      "grad_norm": 0.440523236989975,
      "learning_rate": 1.1399313341820847e-05,
      "loss": 0.5141,
      "step": 29699
    },
    {
      "epoch": 0.912358307990047,
      "grad_norm": 0.3612153232097626,
      "learning_rate": 1.139883481771469e-05,
      "loss": 0.469,
      "step": 29700
    },
    {
      "epoch": 0.9123890271249961,
      "grad_norm": 0.4362585246562958,
      "learning_rate": 1.1398356290341455e-05,
      "loss": 0.5677,
      "step": 29701
    },
    {
      "epoch": 0.9124197462599454,
      "grad_norm": 0.3617365062236786,
      "learning_rate": 1.1397877759702265e-05,
      "loss": 0.6003,
      "step": 29702
    },
    {
      "epoch": 0.9124504653948945,
      "grad_norm": 0.35112297534942627,
      "learning_rate": 1.1397399225798229e-05,
      "loss": 0.5518,
      "step": 29703
    },
    {
      "epoch": 0.9124811845298436,
      "grad_norm": 0.38153699040412903,
      "learning_rate": 1.1396920688630473e-05,
      "loss": 0.5563,
      "step": 29704
    },
    {
      "epoch": 0.9125119036647928,
      "grad_norm": 0.3876824676990509,
      "learning_rate": 1.1396442148200108e-05,
      "loss": 0.5673,
      "step": 29705
    },
    {
      "epoch": 0.912542622799742,
      "grad_norm": 0.44587504863739014,
      "learning_rate": 1.1395963604508257e-05,
      "loss": 0.5245,
      "step": 29706
    },
    {
      "epoch": 0.9125733419346911,
      "grad_norm": 0.363484650850296,
      "learning_rate": 1.1395485057556035e-05,
      "loss": 0.6121,
      "step": 29707
    },
    {
      "epoch": 0.9126040610696403,
      "grad_norm": 0.3916821777820587,
      "learning_rate": 1.1395006507344561e-05,
      "loss": 0.6365,
      "step": 29708
    },
    {
      "epoch": 0.9126347802045894,
      "grad_norm": 0.38654905557632446,
      "learning_rate": 1.1394527953874954e-05,
      "loss": 0.5975,
      "step": 29709
    },
    {
      "epoch": 0.9126654993395386,
      "grad_norm": 0.3578326404094696,
      "learning_rate": 1.1394049397148327e-05,
      "loss": 0.4958,
      "step": 29710
    },
    {
      "epoch": 0.9126962184744878,
      "grad_norm": 0.3601352572441101,
      "learning_rate": 1.13935708371658e-05,
      "loss": 0.5044,
      "step": 29711
    },
    {
      "epoch": 0.9127269376094369,
      "grad_norm": 0.41032400727272034,
      "learning_rate": 1.1393092273928487e-05,
      "loss": 0.5841,
      "step": 29712
    },
    {
      "epoch": 0.912757656744386,
      "grad_norm": 0.36684730648994446,
      "learning_rate": 1.1392613707437514e-05,
      "loss": 0.5487,
      "step": 29713
    },
    {
      "epoch": 0.9127883758793353,
      "grad_norm": 0.35705116391181946,
      "learning_rate": 1.1392135137693994e-05,
      "loss": 0.4695,
      "step": 29714
    },
    {
      "epoch": 0.9128190950142844,
      "grad_norm": 0.3365003168582916,
      "learning_rate": 1.1391656564699047e-05,
      "loss": 0.4691,
      "step": 29715
    },
    {
      "epoch": 0.9128498141492336,
      "grad_norm": 0.34280186891555786,
      "learning_rate": 1.1391177988453787e-05,
      "loss": 0.5212,
      "step": 29716
    },
    {
      "epoch": 0.9128805332841827,
      "grad_norm": 0.40295541286468506,
      "learning_rate": 1.1390699408959333e-05,
      "loss": 0.5189,
      "step": 29717
    },
    {
      "epoch": 0.9129112524191318,
      "grad_norm": 0.4262138903141022,
      "learning_rate": 1.1390220826216807e-05,
      "loss": 0.563,
      "step": 29718
    },
    {
      "epoch": 0.9129419715540811,
      "grad_norm": 0.3461266756057739,
      "learning_rate": 1.138974224022732e-05,
      "loss": 0.542,
      "step": 29719
    },
    {
      "epoch": 0.9129726906890302,
      "grad_norm": 0.3847388029098511,
      "learning_rate": 1.1389263650991993e-05,
      "loss": 0.4753,
      "step": 29720
    },
    {
      "epoch": 0.9130034098239793,
      "grad_norm": 0.3396283984184265,
      "learning_rate": 1.1388785058511944e-05,
      "loss": 0.5177,
      "step": 29721
    },
    {
      "epoch": 0.9130341289589285,
      "grad_norm": 0.35261014103889465,
      "learning_rate": 1.1388306462788293e-05,
      "loss": 0.5139,
      "step": 29722
    },
    {
      "epoch": 0.9130648480938777,
      "grad_norm": 0.41299960017204285,
      "learning_rate": 1.138782786382215e-05,
      "loss": 0.5614,
      "step": 29723
    },
    {
      "epoch": 0.9130955672288268,
      "grad_norm": 0.3549261689186096,
      "learning_rate": 1.1387349261614643e-05,
      "loss": 0.4937,
      "step": 29724
    },
    {
      "epoch": 0.913126286363776,
      "grad_norm": 0.3898283541202545,
      "learning_rate": 1.1386870656166882e-05,
      "loss": 0.5569,
      "step": 29725
    },
    {
      "epoch": 0.9131570054987251,
      "grad_norm": 0.35447824001312256,
      "learning_rate": 1.1386392047479988e-05,
      "loss": 0.6329,
      "step": 29726
    },
    {
      "epoch": 0.9131877246336744,
      "grad_norm": 0.3435254693031311,
      "learning_rate": 1.1385913435555081e-05,
      "loss": 0.479,
      "step": 29727
    },
    {
      "epoch": 0.9132184437686235,
      "grad_norm": 0.3747435212135315,
      "learning_rate": 1.1385434820393276e-05,
      "loss": 0.5465,
      "step": 29728
    },
    {
      "epoch": 0.9132491629035726,
      "grad_norm": 0.6024119257926941,
      "learning_rate": 1.1384956201995689e-05,
      "loss": 0.4773,
      "step": 29729
    },
    {
      "epoch": 0.9132798820385218,
      "grad_norm": 0.35046371817588806,
      "learning_rate": 1.1384477580363438e-05,
      "loss": 0.5297,
      "step": 29730
    },
    {
      "epoch": 0.913310601173471,
      "grad_norm": 0.41459399461746216,
      "learning_rate": 1.1383998955497647e-05,
      "loss": 0.6471,
      "step": 29731
    },
    {
      "epoch": 0.9133413203084201,
      "grad_norm": 0.40949124097824097,
      "learning_rate": 1.1383520327399427e-05,
      "loss": 0.5412,
      "step": 29732
    },
    {
      "epoch": 0.9133720394433693,
      "grad_norm": 0.39807960391044617,
      "learning_rate": 1.13830416960699e-05,
      "loss": 0.5364,
      "step": 29733
    },
    {
      "epoch": 0.9134027585783184,
      "grad_norm": 0.3354315757751465,
      "learning_rate": 1.1382563061510186e-05,
      "loss": 0.4828,
      "step": 29734
    },
    {
      "epoch": 0.9134334777132675,
      "grad_norm": 0.3752550780773163,
      "learning_rate": 1.1382084423721395e-05,
      "loss": 0.6056,
      "step": 29735
    },
    {
      "epoch": 0.9134641968482168,
      "grad_norm": 0.3611757457256317,
      "learning_rate": 1.138160578270465e-05,
      "loss": 0.5578,
      "step": 29736
    },
    {
      "epoch": 0.9134949159831659,
      "grad_norm": 0.4289241135120392,
      "learning_rate": 1.1381127138461068e-05,
      "loss": 0.5827,
      "step": 29737
    },
    {
      "epoch": 0.913525635118115,
      "grad_norm": 0.5071880221366882,
      "learning_rate": 1.138064849099177e-05,
      "loss": 0.662,
      "step": 29738
    },
    {
      "epoch": 0.9135563542530643,
      "grad_norm": 0.4324406683444977,
      "learning_rate": 1.1380169840297868e-05,
      "loss": 0.4758,
      "step": 29739
    },
    {
      "epoch": 0.9135870733880134,
      "grad_norm": 0.3971017301082611,
      "learning_rate": 1.1379691186380483e-05,
      "loss": 0.4509,
      "step": 29740
    },
    {
      "epoch": 0.9136177925229626,
      "grad_norm": 0.3495413362979889,
      "learning_rate": 1.1379212529240733e-05,
      "loss": 0.6046,
      "step": 29741
    },
    {
      "epoch": 0.9136485116579117,
      "grad_norm": 0.37461552023887634,
      "learning_rate": 1.1378733868879738e-05,
      "loss": 0.5626,
      "step": 29742
    },
    {
      "epoch": 0.9136792307928608,
      "grad_norm": 0.347076416015625,
      "learning_rate": 1.1378255205298612e-05,
      "loss": 0.5285,
      "step": 29743
    },
    {
      "epoch": 0.9137099499278101,
      "grad_norm": 0.3817490041255951,
      "learning_rate": 1.1377776538498475e-05,
      "loss": 0.5355,
      "step": 29744
    },
    {
      "epoch": 0.9137406690627592,
      "grad_norm": 0.33235490322113037,
      "learning_rate": 1.1377297868480445e-05,
      "loss": 0.5448,
      "step": 29745
    },
    {
      "epoch": 0.9137713881977083,
      "grad_norm": 0.3625320494174957,
      "learning_rate": 1.1376819195245639e-05,
      "loss": 0.5328,
      "step": 29746
    },
    {
      "epoch": 0.9138021073326575,
      "grad_norm": 0.33627426624298096,
      "learning_rate": 1.1376340518795177e-05,
      "loss": 0.5368,
      "step": 29747
    },
    {
      "epoch": 0.9138328264676067,
      "grad_norm": 0.38602083921432495,
      "learning_rate": 1.1375861839130171e-05,
      "loss": 0.5452,
      "step": 29748
    },
    {
      "epoch": 0.9138635456025558,
      "grad_norm": 0.3814568817615509,
      "learning_rate": 1.1375383156251749e-05,
      "loss": 0.4651,
      "step": 29749
    },
    {
      "epoch": 0.913894264737505,
      "grad_norm": 0.3519912362098694,
      "learning_rate": 1.1374904470161024e-05,
      "loss": 0.5694,
      "step": 29750
    },
    {
      "epoch": 0.9139249838724541,
      "grad_norm": 0.3724469840526581,
      "learning_rate": 1.1374425780859109e-05,
      "loss": 0.5166,
      "step": 29751
    },
    {
      "epoch": 0.9139557030074034,
      "grad_norm": 0.3797607123851776,
      "learning_rate": 1.137394708834713e-05,
      "loss": 0.5594,
      "step": 29752
    },
    {
      "epoch": 0.9139864221423525,
      "grad_norm": 0.4920189082622528,
      "learning_rate": 1.13734683926262e-05,
      "loss": 0.5357,
      "step": 29753
    },
    {
      "epoch": 0.9140171412773016,
      "grad_norm": 0.36709848046302795,
      "learning_rate": 1.137298969369744e-05,
      "loss": 0.5793,
      "step": 29754
    },
    {
      "epoch": 0.9140478604122508,
      "grad_norm": 0.4013237953186035,
      "learning_rate": 1.1372510991561965e-05,
      "loss": 0.5132,
      "step": 29755
    },
    {
      "epoch": 0.9140785795472,
      "grad_norm": 0.3612293303012848,
      "learning_rate": 1.1372032286220896e-05,
      "loss": 0.4913,
      "step": 29756
    },
    {
      "epoch": 0.9141092986821491,
      "grad_norm": 0.41800886392593384,
      "learning_rate": 1.1371553577675348e-05,
      "loss": 0.5497,
      "step": 29757
    },
    {
      "epoch": 0.9141400178170983,
      "grad_norm": 0.3713527023792267,
      "learning_rate": 1.1371074865926443e-05,
      "loss": 0.5045,
      "step": 29758
    },
    {
      "epoch": 0.9141707369520474,
      "grad_norm": 0.3809446096420288,
      "learning_rate": 1.1370596150975295e-05,
      "loss": 0.5291,
      "step": 29759
    },
    {
      "epoch": 0.9142014560869965,
      "grad_norm": 0.4202650487422943,
      "learning_rate": 1.1370117432823028e-05,
      "loss": 0.5153,
      "step": 29760
    },
    {
      "epoch": 0.9142321752219458,
      "grad_norm": 0.397167831659317,
      "learning_rate": 1.1369638711470751e-05,
      "loss": 0.5738,
      "step": 29761
    },
    {
      "epoch": 0.9142628943568949,
      "grad_norm": 0.41068416833877563,
      "learning_rate": 1.1369159986919589e-05,
      "loss": 0.4806,
      "step": 29762
    },
    {
      "epoch": 0.914293613491844,
      "grad_norm": 0.37226855754852295,
      "learning_rate": 1.136868125917066e-05,
      "loss": 0.5745,
      "step": 29763
    },
    {
      "epoch": 0.9143243326267932,
      "grad_norm": 0.36325976252555847,
      "learning_rate": 1.1368202528225078e-05,
      "loss": 0.5571,
      "step": 29764
    },
    {
      "epoch": 0.9143550517617424,
      "grad_norm": 0.3801557123661041,
      "learning_rate": 1.1367723794083965e-05,
      "loss": 0.567,
      "step": 29765
    },
    {
      "epoch": 0.9143857708966916,
      "grad_norm": 0.34358882904052734,
      "learning_rate": 1.1367245056748434e-05,
      "loss": 0.6037,
      "step": 29766
    },
    {
      "epoch": 0.9144164900316407,
      "grad_norm": 0.35549283027648926,
      "learning_rate": 1.1366766316219611e-05,
      "loss": 0.5617,
      "step": 29767
    },
    {
      "epoch": 0.9144472091665898,
      "grad_norm": 0.359526664018631,
      "learning_rate": 1.136628757249861e-05,
      "loss": 0.5918,
      "step": 29768
    },
    {
      "epoch": 0.9144779283015391,
      "grad_norm": 0.39478540420532227,
      "learning_rate": 1.1365808825586545e-05,
      "loss": 0.5748,
      "step": 29769
    },
    {
      "epoch": 0.9145086474364882,
      "grad_norm": 0.4241587221622467,
      "learning_rate": 1.1365330075484542e-05,
      "loss": 0.5573,
      "step": 29770
    },
    {
      "epoch": 0.9145393665714373,
      "grad_norm": 0.3986815810203552,
      "learning_rate": 1.1364851322193711e-05,
      "loss": 0.5961,
      "step": 29771
    },
    {
      "epoch": 0.9145700857063865,
      "grad_norm": 0.31327977776527405,
      "learning_rate": 1.1364372565715178e-05,
      "loss": 0.4852,
      "step": 29772
    },
    {
      "epoch": 0.9146008048413357,
      "grad_norm": 0.3652287721633911,
      "learning_rate": 1.1363893806050057e-05,
      "loss": 0.5274,
      "step": 29773
    },
    {
      "epoch": 0.9146315239762848,
      "grad_norm": 0.3577510118484497,
      "learning_rate": 1.1363415043199466e-05,
      "loss": 0.5278,
      "step": 29774
    },
    {
      "epoch": 0.914662243111234,
      "grad_norm": 0.3431572914123535,
      "learning_rate": 1.1362936277164525e-05,
      "loss": 0.5086,
      "step": 29775
    },
    {
      "epoch": 0.9146929622461831,
      "grad_norm": 0.34095799922943115,
      "learning_rate": 1.136245750794635e-05,
      "loss": 0.5629,
      "step": 29776
    },
    {
      "epoch": 0.9147236813811324,
      "grad_norm": 0.3747989535331726,
      "learning_rate": 1.136197873554606e-05,
      "loss": 0.609,
      "step": 29777
    },
    {
      "epoch": 0.9147544005160815,
      "grad_norm": 0.37615111470222473,
      "learning_rate": 1.1361499959964774e-05,
      "loss": 0.5991,
      "step": 29778
    },
    {
      "epoch": 0.9147851196510306,
      "grad_norm": 0.3722657859325409,
      "learning_rate": 1.1361021181203613e-05,
      "loss": 0.5718,
      "step": 29779
    },
    {
      "epoch": 0.9148158387859798,
      "grad_norm": 0.3626370429992676,
      "learning_rate": 1.1360542399263688e-05,
      "loss": 0.469,
      "step": 29780
    },
    {
      "epoch": 0.914846557920929,
      "grad_norm": 0.381083607673645,
      "learning_rate": 1.1360063614146121e-05,
      "loss": 0.5655,
      "step": 29781
    },
    {
      "epoch": 0.9148772770558781,
      "grad_norm": 0.4104706346988678,
      "learning_rate": 1.1359584825852033e-05,
      "loss": 0.6219,
      "step": 29782
    },
    {
      "epoch": 0.9149079961908273,
      "grad_norm": 0.3680785596370697,
      "learning_rate": 1.1359106034382539e-05,
      "loss": 0.5782,
      "step": 29783
    },
    {
      "epoch": 0.9149387153257764,
      "grad_norm": 0.3318933844566345,
      "learning_rate": 1.1358627239738756e-05,
      "loss": 0.4448,
      "step": 29784
    },
    {
      "epoch": 0.9149694344607255,
      "grad_norm": 0.39394259452819824,
      "learning_rate": 1.1358148441921804e-05,
      "loss": 0.529,
      "step": 29785
    },
    {
      "epoch": 0.9150001535956748,
      "grad_norm": 0.39842161536216736,
      "learning_rate": 1.1357669640932804e-05,
      "loss": 0.5421,
      "step": 29786
    },
    {
      "epoch": 0.9150308727306239,
      "grad_norm": 0.3512493073940277,
      "learning_rate": 1.1357190836772869e-05,
      "loss": 0.4209,
      "step": 29787
    },
    {
      "epoch": 0.9150615918655731,
      "grad_norm": 0.450266033411026,
      "learning_rate": 1.1356712029443125e-05,
      "loss": 0.5681,
      "step": 29788
    },
    {
      "epoch": 0.9150923110005222,
      "grad_norm": 0.36422500014305115,
      "learning_rate": 1.135623321894468e-05,
      "loss": 0.598,
      "step": 29789
    },
    {
      "epoch": 0.9151230301354714,
      "grad_norm": 0.3391086161136627,
      "learning_rate": 1.1355754405278661e-05,
      "loss": 0.558,
      "step": 29790
    },
    {
      "epoch": 0.9151537492704206,
      "grad_norm": 0.37135568261146545,
      "learning_rate": 1.135527558844618e-05,
      "loss": 0.6172,
      "step": 29791
    },
    {
      "epoch": 0.9151844684053697,
      "grad_norm": 0.38462555408477783,
      "learning_rate": 1.135479676844836e-05,
      "loss": 0.558,
      "step": 29792
    },
    {
      "epoch": 0.9152151875403188,
      "grad_norm": 0.3729138672351837,
      "learning_rate": 1.1354317945286317e-05,
      "loss": 0.5665,
      "step": 29793
    },
    {
      "epoch": 0.9152459066752681,
      "grad_norm": 0.3788667619228363,
      "learning_rate": 1.135383911896117e-05,
      "loss": 0.5742,
      "step": 29794
    },
    {
      "epoch": 0.9152766258102172,
      "grad_norm": 0.4169248640537262,
      "learning_rate": 1.1353360289474038e-05,
      "loss": 0.569,
      "step": 29795
    },
    {
      "epoch": 0.9153073449451663,
      "grad_norm": 0.3482382893562317,
      "learning_rate": 1.1352881456826037e-05,
      "loss": 0.5066,
      "step": 29796
    },
    {
      "epoch": 0.9153380640801155,
      "grad_norm": 0.35676130652427673,
      "learning_rate": 1.135240262101829e-05,
      "loss": 0.3806,
      "step": 29797
    },
    {
      "epoch": 0.9153687832150647,
      "grad_norm": 0.36297234892845154,
      "learning_rate": 1.1351923782051908e-05,
      "loss": 0.5234,
      "step": 29798
    },
    {
      "epoch": 0.9153995023500138,
      "grad_norm": 0.5203209519386292,
      "learning_rate": 1.1351444939928018e-05,
      "loss": 0.6043,
      "step": 29799
    },
    {
      "epoch": 0.915430221484963,
      "grad_norm": 0.37229931354522705,
      "learning_rate": 1.1350966094647728e-05,
      "loss": 0.5163,
      "step": 29800
    },
    {
      "epoch": 0.9154609406199121,
      "grad_norm": 0.3829618990421295,
      "learning_rate": 1.1350487246212168e-05,
      "loss": 0.5604,
      "step": 29801
    },
    {
      "epoch": 0.9154916597548614,
      "grad_norm": 0.37218207120895386,
      "learning_rate": 1.1350008394622447e-05,
      "loss": 0.5361,
      "step": 29802
    },
    {
      "epoch": 0.9155223788898105,
      "grad_norm": 0.39492088556289673,
      "learning_rate": 1.134952953987969e-05,
      "loss": 0.5269,
      "step": 29803
    },
    {
      "epoch": 0.9155530980247596,
      "grad_norm": 0.47764095664024353,
      "learning_rate": 1.1349050681985009e-05,
      "loss": 0.5962,
      "step": 29804
    },
    {
      "epoch": 0.9155838171597088,
      "grad_norm": 0.3557504117488861,
      "learning_rate": 1.1348571820939529e-05,
      "loss": 0.5295,
      "step": 29805
    },
    {
      "epoch": 0.9156145362946579,
      "grad_norm": 0.42461609840393066,
      "learning_rate": 1.1348092956744365e-05,
      "loss": 0.5234,
      "step": 29806
    },
    {
      "epoch": 0.9156452554296071,
      "grad_norm": 0.34580719470977783,
      "learning_rate": 1.1347614089400634e-05,
      "loss": 0.5256,
      "step": 29807
    },
    {
      "epoch": 0.9156759745645563,
      "grad_norm": 0.36660414934158325,
      "learning_rate": 1.1347135218909457e-05,
      "loss": 0.6005,
      "step": 29808
    },
    {
      "epoch": 0.9157066936995054,
      "grad_norm": 0.38876649737358093,
      "learning_rate": 1.1346656345271951e-05,
      "loss": 0.4847,
      "step": 29809
    },
    {
      "epoch": 0.9157374128344545,
      "grad_norm": 0.35271182656288147,
      "learning_rate": 1.134617746848924e-05,
      "loss": 0.6116,
      "step": 29810
    },
    {
      "epoch": 0.9157681319694038,
      "grad_norm": 0.5267618298530579,
      "learning_rate": 1.134569858856243e-05,
      "loss": 0.5432,
      "step": 29811
    },
    {
      "epoch": 0.9157988511043529,
      "grad_norm": 0.34377336502075195,
      "learning_rate": 1.1345219705492652e-05,
      "loss": 0.5142,
      "step": 29812
    },
    {
      "epoch": 0.9158295702393021,
      "grad_norm": 0.36077767610549927,
      "learning_rate": 1.1344740819281017e-05,
      "loss": 0.5498,
      "step": 29813
    },
    {
      "epoch": 0.9158602893742512,
      "grad_norm": 0.3289026916027069,
      "learning_rate": 1.1344261929928649e-05,
      "loss": 0.5473,
      "step": 29814
    },
    {
      "epoch": 0.9158910085092004,
      "grad_norm": 0.3697982728481293,
      "learning_rate": 1.1343783037436662e-05,
      "loss": 0.4948,
      "step": 29815
    },
    {
      "epoch": 0.9159217276441496,
      "grad_norm": 0.36773011088371277,
      "learning_rate": 1.1343304141806173e-05,
      "loss": 0.5251,
      "step": 29816
    },
    {
      "epoch": 0.9159524467790987,
      "grad_norm": 0.34727299213409424,
      "learning_rate": 1.1342825243038307e-05,
      "loss": 0.6086,
      "step": 29817
    },
    {
      "epoch": 0.9159831659140478,
      "grad_norm": 0.342718243598938,
      "learning_rate": 1.1342346341134177e-05,
      "loss": 0.4655,
      "step": 29818
    },
    {
      "epoch": 0.9160138850489971,
      "grad_norm": 0.35590770840644836,
      "learning_rate": 1.1341867436094901e-05,
      "loss": 0.5439,
      "step": 29819
    },
    {
      "epoch": 0.9160446041839462,
      "grad_norm": 0.35993117094039917,
      "learning_rate": 1.1341388527921604e-05,
      "loss": 0.5403,
      "step": 29820
    },
    {
      "epoch": 0.9160753233188953,
      "grad_norm": 0.35229575634002686,
      "learning_rate": 1.13409096166154e-05,
      "loss": 0.5057,
      "step": 29821
    },
    {
      "epoch": 0.9161060424538445,
      "grad_norm": 0.3748055696487427,
      "learning_rate": 1.1340430702177406e-05,
      "loss": 0.5405,
      "step": 29822
    },
    {
      "epoch": 0.9161367615887936,
      "grad_norm": 0.3849409222602844,
      "learning_rate": 1.1339951784608743e-05,
      "loss": 0.6079,
      "step": 29823
    },
    {
      "epoch": 0.9161674807237428,
      "grad_norm": 0.37229734659194946,
      "learning_rate": 1.133947286391053e-05,
      "loss": 0.5004,
      "step": 29824
    },
    {
      "epoch": 0.916198199858692,
      "grad_norm": 0.43534713983535767,
      "learning_rate": 1.1338993940083882e-05,
      "loss": 0.4981,
      "step": 29825
    },
    {
      "epoch": 0.9162289189936411,
      "grad_norm": 0.36371979117393494,
      "learning_rate": 1.1338515013129923e-05,
      "loss": 0.5062,
      "step": 29826
    },
    {
      "epoch": 0.9162596381285903,
      "grad_norm": 0.3950299918651581,
      "learning_rate": 1.1338036083049767e-05,
      "loss": 0.6111,
      "step": 29827
    },
    {
      "epoch": 0.9162903572635395,
      "grad_norm": 0.3730788230895996,
      "learning_rate": 1.1337557149844535e-05,
      "loss": 0.5467,
      "step": 29828
    },
    {
      "epoch": 0.9163210763984886,
      "grad_norm": 0.37635210156440735,
      "learning_rate": 1.1337078213515344e-05,
      "loss": 0.5029,
      "step": 29829
    },
    {
      "epoch": 0.9163517955334378,
      "grad_norm": 0.3747934401035309,
      "learning_rate": 1.1336599274063315e-05,
      "loss": 0.5481,
      "step": 29830
    },
    {
      "epoch": 0.9163825146683869,
      "grad_norm": 0.38963639736175537,
      "learning_rate": 1.1336120331489565e-05,
      "loss": 0.5203,
      "step": 29831
    },
    {
      "epoch": 0.9164132338033361,
      "grad_norm": 0.40385931730270386,
      "learning_rate": 1.1335641385795212e-05,
      "loss": 0.5778,
      "step": 29832
    },
    {
      "epoch": 0.9164439529382853,
      "grad_norm": 0.43252235651016235,
      "learning_rate": 1.1335162436981377e-05,
      "loss": 0.5736,
      "step": 29833
    },
    {
      "epoch": 0.9164746720732344,
      "grad_norm": 0.3492489159107208,
      "learning_rate": 1.1334683485049174e-05,
      "loss": 0.5581,
      "step": 29834
    },
    {
      "epoch": 0.9165053912081835,
      "grad_norm": 0.3785008490085602,
      "learning_rate": 1.1334204529999728e-05,
      "loss": 0.5517,
      "step": 29835
    },
    {
      "epoch": 0.9165361103431328,
      "grad_norm": 0.4204126298427582,
      "learning_rate": 1.1333725571834151e-05,
      "loss": 0.6252,
      "step": 29836
    },
    {
      "epoch": 0.9165668294780819,
      "grad_norm": 0.3687248229980469,
      "learning_rate": 1.1333246610553565e-05,
      "loss": 0.5265,
      "step": 29837
    },
    {
      "epoch": 0.9165975486130311,
      "grad_norm": 0.4019128382205963,
      "learning_rate": 1.1332767646159088e-05,
      "loss": 0.569,
      "step": 29838
    },
    {
      "epoch": 0.9166282677479802,
      "grad_norm": 0.40042823553085327,
      "learning_rate": 1.1332288678651842e-05,
      "loss": 0.561,
      "step": 29839
    },
    {
      "epoch": 0.9166589868829293,
      "grad_norm": 0.40015658736228943,
      "learning_rate": 1.133180970803294e-05,
      "loss": 0.5858,
      "step": 29840
    },
    {
      "epoch": 0.9166897060178786,
      "grad_norm": 0.3942359685897827,
      "learning_rate": 1.1331330734303502e-05,
      "loss": 0.5163,
      "step": 29841
    },
    {
      "epoch": 0.9167204251528277,
      "grad_norm": 0.38134104013442993,
      "learning_rate": 1.1330851757464654e-05,
      "loss": 0.6081,
      "step": 29842
    },
    {
      "epoch": 0.9167511442877768,
      "grad_norm": 0.5786691308021545,
      "learning_rate": 1.1330372777517501e-05,
      "loss": 0.5335,
      "step": 29843
    },
    {
      "epoch": 0.916781863422726,
      "grad_norm": 0.5383130311965942,
      "learning_rate": 1.1329893794463176e-05,
      "loss": 0.5219,
      "step": 29844
    },
    {
      "epoch": 0.9168125825576752,
      "grad_norm": 0.377191960811615,
      "learning_rate": 1.1329414808302788e-05,
      "loss": 0.5723,
      "step": 29845
    },
    {
      "epoch": 0.9168433016926243,
      "grad_norm": 0.3670126795768738,
      "learning_rate": 1.1328935819037461e-05,
      "loss": 0.5311,
      "step": 29846
    },
    {
      "epoch": 0.9168740208275735,
      "grad_norm": 0.361858606338501,
      "learning_rate": 1.132845682666831e-05,
      "loss": 0.631,
      "step": 29847
    },
    {
      "epoch": 0.9169047399625226,
      "grad_norm": 0.3342001736164093,
      "learning_rate": 1.1327977831196458e-05,
      "loss": 0.5699,
      "step": 29848
    },
    {
      "epoch": 0.9169354590974718,
      "grad_norm": 0.33372342586517334,
      "learning_rate": 1.1327498832623019e-05,
      "loss": 0.5333,
      "step": 29849
    },
    {
      "epoch": 0.916966178232421,
      "grad_norm": 0.36867091059684753,
      "learning_rate": 1.132701983094911e-05,
      "loss": 0.599,
      "step": 29850
    },
    {
      "epoch": 0.9169968973673701,
      "grad_norm": 0.39576247334480286,
      "learning_rate": 1.1326540826175859e-05,
      "loss": 0.5481,
      "step": 29851
    },
    {
      "epoch": 0.9170276165023193,
      "grad_norm": 0.4900851845741272,
      "learning_rate": 1.1326061818304376e-05,
      "loss": 0.5836,
      "step": 29852
    },
    {
      "epoch": 0.9170583356372685,
      "grad_norm": 0.37317702174186707,
      "learning_rate": 1.1325582807335787e-05,
      "loss": 0.551,
      "step": 29853
    },
    {
      "epoch": 0.9170890547722176,
      "grad_norm": 0.419871062040329,
      "learning_rate": 1.1325103793271201e-05,
      "loss": 0.5297,
      "step": 29854
    },
    {
      "epoch": 0.9171197739071668,
      "grad_norm": 0.3580839931964874,
      "learning_rate": 1.1324624776111748e-05,
      "loss": 0.6231,
      "step": 29855
    },
    {
      "epoch": 0.9171504930421159,
      "grad_norm": 0.3872574269771576,
      "learning_rate": 1.1324145755858536e-05,
      "loss": 0.5349,
      "step": 29856
    },
    {
      "epoch": 0.917181212177065,
      "grad_norm": 0.3449633717536926,
      "learning_rate": 1.1323666732512692e-05,
      "loss": 0.5028,
      "step": 29857
    },
    {
      "epoch": 0.9172119313120143,
      "grad_norm": 0.6797711849212646,
      "learning_rate": 1.1323187706075331e-05,
      "loss": 0.5172,
      "step": 29858
    },
    {
      "epoch": 0.9172426504469634,
      "grad_norm": 0.3633214831352234,
      "learning_rate": 1.1322708676547574e-05,
      "loss": 0.6291,
      "step": 29859
    },
    {
      "epoch": 0.9172733695819125,
      "grad_norm": 0.34720665216445923,
      "learning_rate": 1.1322229643930541e-05,
      "loss": 0.5191,
      "step": 29860
    },
    {
      "epoch": 0.9173040887168618,
      "grad_norm": 0.334983766078949,
      "learning_rate": 1.1321750608225342e-05,
      "loss": 0.5712,
      "step": 29861
    },
    {
      "epoch": 0.9173348078518109,
      "grad_norm": 0.3538673222064972,
      "learning_rate": 1.1321271569433108e-05,
      "loss": 0.5556,
      "step": 29862
    },
    {
      "epoch": 0.9173655269867601,
      "grad_norm": 0.39380282163619995,
      "learning_rate": 1.1320792527554947e-05,
      "loss": 0.6448,
      "step": 29863
    },
    {
      "epoch": 0.9173962461217092,
      "grad_norm": 0.357928991317749,
      "learning_rate": 1.1320313482591987e-05,
      "loss": 0.5159,
      "step": 29864
    },
    {
      "epoch": 0.9174269652566583,
      "grad_norm": 0.35758405923843384,
      "learning_rate": 1.131983443454534e-05,
      "loss": 0.4601,
      "step": 29865
    },
    {
      "epoch": 0.9174576843916076,
      "grad_norm": 0.3901301622390747,
      "learning_rate": 1.1319355383416129e-05,
      "loss": 0.5113,
      "step": 29866
    },
    {
      "epoch": 0.9174884035265567,
      "grad_norm": 0.3837173879146576,
      "learning_rate": 1.1318876329205473e-05,
      "loss": 0.4472,
      "step": 29867
    },
    {
      "epoch": 0.9175191226615058,
      "grad_norm": 0.3511482775211334,
      "learning_rate": 1.1318397271914485e-05,
      "loss": 0.5755,
      "step": 29868
    },
    {
      "epoch": 0.917549841796455,
      "grad_norm": 0.41961973905563354,
      "learning_rate": 1.1317918211544291e-05,
      "loss": 0.569,
      "step": 29869
    },
    {
      "epoch": 0.9175805609314042,
      "grad_norm": 0.4299531877040863,
      "learning_rate": 1.1317439148096006e-05,
      "loss": 0.4646,
      "step": 29870
    },
    {
      "epoch": 0.9176112800663533,
      "grad_norm": 0.3936574459075928,
      "learning_rate": 1.131696008157075e-05,
      "loss": 0.4695,
      "step": 29871
    },
    {
      "epoch": 0.9176419992013025,
      "grad_norm": 0.35572701692581177,
      "learning_rate": 1.131648101196964e-05,
      "loss": 0.5362,
      "step": 29872
    },
    {
      "epoch": 0.9176727183362516,
      "grad_norm": 0.366411954164505,
      "learning_rate": 1.13160019392938e-05,
      "loss": 0.5112,
      "step": 29873
    },
    {
      "epoch": 0.9177034374712008,
      "grad_norm": 0.36636224389076233,
      "learning_rate": 1.1315522863544344e-05,
      "loss": 0.5118,
      "step": 29874
    },
    {
      "epoch": 0.91773415660615,
      "grad_norm": 0.4019298851490021,
      "learning_rate": 1.1315043784722393e-05,
      "loss": 0.514,
      "step": 29875
    },
    {
      "epoch": 0.9177648757410991,
      "grad_norm": 0.4121556580066681,
      "learning_rate": 1.1314564702829062e-05,
      "loss": 0.5583,
      "step": 29876
    },
    {
      "epoch": 0.9177955948760483,
      "grad_norm": 0.44091570377349854,
      "learning_rate": 1.1314085617865476e-05,
      "loss": 0.5215,
      "step": 29877
    },
    {
      "epoch": 0.9178263140109975,
      "grad_norm": 0.34990063309669495,
      "learning_rate": 1.1313606529832752e-05,
      "loss": 0.5717,
      "step": 29878
    },
    {
      "epoch": 0.9178570331459466,
      "grad_norm": 0.41568228602409363,
      "learning_rate": 1.1313127438732008e-05,
      "loss": 0.5301,
      "step": 29879
    },
    {
      "epoch": 0.9178877522808958,
      "grad_norm": 0.38292476534843445,
      "learning_rate": 1.1312648344564364e-05,
      "loss": 0.5581,
      "step": 29880
    },
    {
      "epoch": 0.9179184714158449,
      "grad_norm": 0.3670329749584198,
      "learning_rate": 1.1312169247330936e-05,
      "loss": 0.5054,
      "step": 29881
    },
    {
      "epoch": 0.917949190550794,
      "grad_norm": 0.4003210663795471,
      "learning_rate": 1.1311690147032846e-05,
      "loss": 0.6062,
      "step": 29882
    },
    {
      "epoch": 0.9179799096857433,
      "grad_norm": 0.41060930490493774,
      "learning_rate": 1.1311211043671212e-05,
      "loss": 0.5489,
      "step": 29883
    },
    {
      "epoch": 0.9180106288206924,
      "grad_norm": 0.3740139305591583,
      "learning_rate": 1.1310731937247153e-05,
      "loss": 0.4545,
      "step": 29884
    },
    {
      "epoch": 0.9180413479556415,
      "grad_norm": 0.38347122073173523,
      "learning_rate": 1.131025282776179e-05,
      "loss": 0.5978,
      "step": 29885
    },
    {
      "epoch": 0.9180720670905907,
      "grad_norm": 0.37524494528770447,
      "learning_rate": 1.1309773715216238e-05,
      "loss": 0.4938,
      "step": 29886
    },
    {
      "epoch": 0.9181027862255399,
      "grad_norm": 0.38675257563591003,
      "learning_rate": 1.1309294599611617e-05,
      "loss": 0.5167,
      "step": 29887
    },
    {
      "epoch": 0.9181335053604891,
      "grad_norm": 0.38717299699783325,
      "learning_rate": 1.1308815480949047e-05,
      "loss": 0.4992,
      "step": 29888
    },
    {
      "epoch": 0.9181642244954382,
      "grad_norm": 0.36530157923698425,
      "learning_rate": 1.1308336359229651e-05,
      "loss": 0.539,
      "step": 29889
    },
    {
      "epoch": 0.9181949436303873,
      "grad_norm": 0.3768036365509033,
      "learning_rate": 1.1307857234454538e-05,
      "loss": 0.6253,
      "step": 29890
    },
    {
      "epoch": 0.9182256627653366,
      "grad_norm": 0.3879396319389343,
      "learning_rate": 1.1307378106624837e-05,
      "loss": 0.5262,
      "step": 29891
    },
    {
      "epoch": 0.9182563819002857,
      "grad_norm": 0.8011634945869446,
      "learning_rate": 1.1306898975741663e-05,
      "loss": 0.5728,
      "step": 29892
    },
    {
      "epoch": 0.9182871010352348,
      "grad_norm": 0.35654035210609436,
      "learning_rate": 1.1306419841806135e-05,
      "loss": 0.5434,
      "step": 29893
    },
    {
      "epoch": 0.918317820170184,
      "grad_norm": 0.3509308695793152,
      "learning_rate": 1.1305940704819372e-05,
      "loss": 0.5713,
      "step": 29894
    },
    {
      "epoch": 0.9183485393051332,
      "grad_norm": 0.3579682409763336,
      "learning_rate": 1.130546156478249e-05,
      "loss": 0.5348,
      "step": 29895
    },
    {
      "epoch": 0.9183792584400823,
      "grad_norm": 0.38309985399246216,
      "learning_rate": 1.1304982421696615e-05,
      "loss": 0.5246,
      "step": 29896
    },
    {
      "epoch": 0.9184099775750315,
      "grad_norm": 0.4499751627445221,
      "learning_rate": 1.1304503275562862e-05,
      "loss": 0.5918,
      "step": 29897
    },
    {
      "epoch": 0.9184406967099806,
      "grad_norm": 0.3576095402240753,
      "learning_rate": 1.1304024126382352e-05,
      "loss": 0.5175,
      "step": 29898
    },
    {
      "epoch": 0.9184714158449299,
      "grad_norm": 0.3618386387825012,
      "learning_rate": 1.1303544974156199e-05,
      "loss": 0.5625,
      "step": 29899
    },
    {
      "epoch": 0.918502134979879,
      "grad_norm": 0.3974545896053314,
      "learning_rate": 1.1303065818885529e-05,
      "loss": 0.5345,
      "step": 29900
    },
    {
      "epoch": 0.9185328541148281,
      "grad_norm": 0.36657220125198364,
      "learning_rate": 1.1302586660571457e-05,
      "loss": 0.5202,
      "step": 29901
    },
    {
      "epoch": 0.9185635732497773,
      "grad_norm": 0.3758341670036316,
      "learning_rate": 1.1302107499215102e-05,
      "loss": 0.6294,
      "step": 29902
    },
    {
      "epoch": 0.9185942923847265,
      "grad_norm": 0.36284491419792175,
      "learning_rate": 1.1301628334817584e-05,
      "loss": 0.53,
      "step": 29903
    },
    {
      "epoch": 0.9186250115196756,
      "grad_norm": 0.3757610023021698,
      "learning_rate": 1.1301149167380024e-05,
      "loss": 0.5434,
      "step": 29904
    },
    {
      "epoch": 0.9186557306546248,
      "grad_norm": 0.3532731831073761,
      "learning_rate": 1.1300669996903537e-05,
      "loss": 0.5733,
      "step": 29905
    },
    {
      "epoch": 0.9186864497895739,
      "grad_norm": 0.3599115312099457,
      "learning_rate": 1.1300190823389244e-05,
      "loss": 0.4619,
      "step": 29906
    },
    {
      "epoch": 0.918717168924523,
      "grad_norm": 0.3805372714996338,
      "learning_rate": 1.1299711646838267e-05,
      "loss": 0.542,
      "step": 29907
    },
    {
      "epoch": 0.9187478880594723,
      "grad_norm": 0.39002281427383423,
      "learning_rate": 1.129923246725172e-05,
      "loss": 0.6274,
      "step": 29908
    },
    {
      "epoch": 0.9187786071944214,
      "grad_norm": 0.4161083698272705,
      "learning_rate": 1.1298753284630725e-05,
      "loss": 0.5509,
      "step": 29909
    },
    {
      "epoch": 0.9188093263293705,
      "grad_norm": 0.3908417224884033,
      "learning_rate": 1.1298274098976403e-05,
      "loss": 0.5634,
      "step": 29910
    },
    {
      "epoch": 0.9188400454643197,
      "grad_norm": 0.4437156915664673,
      "learning_rate": 1.129779491028987e-05,
      "loss": 0.5964,
      "step": 29911
    },
    {
      "epoch": 0.9188707645992689,
      "grad_norm": 0.36368775367736816,
      "learning_rate": 1.1297315718572248e-05,
      "loss": 0.5146,
      "step": 29912
    },
    {
      "epoch": 0.9189014837342181,
      "grad_norm": 0.39373475313186646,
      "learning_rate": 1.129683652382465e-05,
      "loss": 0.6011,
      "step": 29913
    },
    {
      "epoch": 0.9189322028691672,
      "grad_norm": 0.3667777478694916,
      "learning_rate": 1.1296357326048204e-05,
      "loss": 0.5231,
      "step": 29914
    },
    {
      "epoch": 0.9189629220041163,
      "grad_norm": 0.35077378153800964,
      "learning_rate": 1.1295878125244024e-05,
      "loss": 0.5705,
      "step": 29915
    },
    {
      "epoch": 0.9189936411390656,
      "grad_norm": 2.929400682449341,
      "learning_rate": 1.129539892141323e-05,
      "loss": 0.5626,
      "step": 29916
    },
    {
      "epoch": 0.9190243602740147,
      "grad_norm": 0.34029829502105713,
      "learning_rate": 1.129491971455694e-05,
      "loss": 0.4481,
      "step": 29917
    },
    {
      "epoch": 0.9190550794089638,
      "grad_norm": 0.40010595321655273,
      "learning_rate": 1.1294440504676276e-05,
      "loss": 0.4876,
      "step": 29918
    },
    {
      "epoch": 0.919085798543913,
      "grad_norm": 0.4035710394382477,
      "learning_rate": 1.1293961291772358e-05,
      "loss": 0.581,
      "step": 29919
    },
    {
      "epoch": 0.9191165176788622,
      "grad_norm": 0.33969858288764954,
      "learning_rate": 1.1293482075846298e-05,
      "loss": 0.5623,
      "step": 29920
    },
    {
      "epoch": 0.9191472368138113,
      "grad_norm": 0.37759196758270264,
      "learning_rate": 1.1293002856899225e-05,
      "loss": 0.5499,
      "step": 29921
    },
    {
      "epoch": 0.9191779559487605,
      "grad_norm": 0.3605083227157593,
      "learning_rate": 1.129252363493225e-05,
      "loss": 0.5192,
      "step": 29922
    },
    {
      "epoch": 0.9192086750837096,
      "grad_norm": 0.36669406294822693,
      "learning_rate": 1.12920444099465e-05,
      "loss": 0.5409,
      "step": 29923
    },
    {
      "epoch": 0.9192393942186589,
      "grad_norm": 0.34949761629104614,
      "learning_rate": 1.1291565181943085e-05,
      "loss": 0.5268,
      "step": 29924
    },
    {
      "epoch": 0.919270113353608,
      "grad_norm": 0.562767744064331,
      "learning_rate": 1.1291085950923132e-05,
      "loss": 0.4612,
      "step": 29925
    },
    {
      "epoch": 0.9193008324885571,
      "grad_norm": 0.5294228196144104,
      "learning_rate": 1.1290606716887758e-05,
      "loss": 0.6393,
      "step": 29926
    },
    {
      "epoch": 0.9193315516235063,
      "grad_norm": 0.358151912689209,
      "learning_rate": 1.1290127479838082e-05,
      "loss": 0.4837,
      "step": 29927
    },
    {
      "epoch": 0.9193622707584554,
      "grad_norm": 0.3482421338558197,
      "learning_rate": 1.128964823977522e-05,
      "loss": 0.4862,
      "step": 29928
    },
    {
      "epoch": 0.9193929898934046,
      "grad_norm": 0.4176829159259796,
      "learning_rate": 1.1289168996700299e-05,
      "loss": 0.5038,
      "step": 29929
    },
    {
      "epoch": 0.9194237090283538,
      "grad_norm": 0.3559646010398865,
      "learning_rate": 1.1288689750614432e-05,
      "loss": 0.5705,
      "step": 29930
    },
    {
      "epoch": 0.9194544281633029,
      "grad_norm": 0.3752310872077942,
      "learning_rate": 1.1288210501518737e-05,
      "loss": 0.52,
      "step": 29931
    },
    {
      "epoch": 0.919485147298252,
      "grad_norm": 0.36884787678718567,
      "learning_rate": 1.128773124941434e-05,
      "loss": 0.5568,
      "step": 29932
    },
    {
      "epoch": 0.9195158664332013,
      "grad_norm": 0.39419183135032654,
      "learning_rate": 1.1287251994302353e-05,
      "loss": 0.6478,
      "step": 29933
    },
    {
      "epoch": 0.9195465855681504,
      "grad_norm": 0.36908623576164246,
      "learning_rate": 1.1286772736183904e-05,
      "loss": 0.522,
      "step": 29934
    },
    {
      "epoch": 0.9195773047030995,
      "grad_norm": 0.33384254574775696,
      "learning_rate": 1.1286293475060105e-05,
      "loss": 0.5165,
      "step": 29935
    },
    {
      "epoch": 0.9196080238380487,
      "grad_norm": 0.3534734845161438,
      "learning_rate": 1.1285814210932078e-05,
      "loss": 0.5061,
      "step": 29936
    },
    {
      "epoch": 0.9196387429729979,
      "grad_norm": 0.35465025901794434,
      "learning_rate": 1.1285334943800944e-05,
      "loss": 0.5404,
      "step": 29937
    },
    {
      "epoch": 0.9196694621079471,
      "grad_norm": 0.3753235936164856,
      "learning_rate": 1.1284855673667817e-05,
      "loss": 0.4548,
      "step": 29938
    },
    {
      "epoch": 0.9197001812428962,
      "grad_norm": 0.3529225289821625,
      "learning_rate": 1.1284376400533821e-05,
      "loss": 0.4775,
      "step": 29939
    },
    {
      "epoch": 0.9197309003778453,
      "grad_norm": 0.4067458212375641,
      "learning_rate": 1.1283897124400074e-05,
      "loss": 0.4759,
      "step": 29940
    },
    {
      "epoch": 0.9197616195127946,
      "grad_norm": 0.41151976585388184,
      "learning_rate": 1.1283417845267696e-05,
      "loss": 0.4888,
      "step": 29941
    },
    {
      "epoch": 0.9197923386477437,
      "grad_norm": 0.4397384822368622,
      "learning_rate": 1.1282938563137806e-05,
      "loss": 0.5253,
      "step": 29942
    },
    {
      "epoch": 0.9198230577826928,
      "grad_norm": 0.4017295837402344,
      "learning_rate": 1.1282459278011526e-05,
      "loss": 0.4328,
      "step": 29943
    },
    {
      "epoch": 0.919853776917642,
      "grad_norm": 0.392113596200943,
      "learning_rate": 1.1281979989889969e-05,
      "loss": 0.5004,
      "step": 29944
    },
    {
      "epoch": 0.9198844960525911,
      "grad_norm": 0.3677724003791809,
      "learning_rate": 1.1281500698774259e-05,
      "loss": 0.5933,
      "step": 29945
    },
    {
      "epoch": 0.9199152151875403,
      "grad_norm": 0.4128761887550354,
      "learning_rate": 1.1281021404665518e-05,
      "loss": 0.4541,
      "step": 29946
    },
    {
      "epoch": 0.9199459343224895,
      "grad_norm": 0.5061865448951721,
      "learning_rate": 1.1280542107564858e-05,
      "loss": 0.5368,
      "step": 29947
    },
    {
      "epoch": 0.9199766534574386,
      "grad_norm": 0.34909504652023315,
      "learning_rate": 1.1280062807473403e-05,
      "loss": 0.5537,
      "step": 29948
    },
    {
      "epoch": 0.9200073725923879,
      "grad_norm": 0.3381185233592987,
      "learning_rate": 1.127958350439227e-05,
      "loss": 0.5221,
      "step": 29949
    },
    {
      "epoch": 0.920038091727337,
      "grad_norm": 0.6326496601104736,
      "learning_rate": 1.1279104198322584e-05,
      "loss": 0.5419,
      "step": 29950
    },
    {
      "epoch": 0.9200688108622861,
      "grad_norm": 0.3726564347743988,
      "learning_rate": 1.1278624889265459e-05,
      "loss": 0.4852,
      "step": 29951
    },
    {
      "epoch": 0.9200995299972353,
      "grad_norm": 0.35474318265914917,
      "learning_rate": 1.1278145577222018e-05,
      "loss": 0.5644,
      "step": 29952
    },
    {
      "epoch": 0.9201302491321844,
      "grad_norm": 0.3307761549949646,
      "learning_rate": 1.1277666262193378e-05,
      "loss": 0.531,
      "step": 29953
    },
    {
      "epoch": 0.9201609682671336,
      "grad_norm": 0.41762402653694153,
      "learning_rate": 1.1277186944180658e-05,
      "loss": 0.5039,
      "step": 29954
    },
    {
      "epoch": 0.9201916874020828,
      "grad_norm": 0.46772515773773193,
      "learning_rate": 1.1276707623184981e-05,
      "loss": 0.5384,
      "step": 29955
    },
    {
      "epoch": 0.9202224065370319,
      "grad_norm": 0.3464648723602295,
      "learning_rate": 1.1276228299207464e-05,
      "loss": 0.5312,
      "step": 29956
    },
    {
      "epoch": 0.920253125671981,
      "grad_norm": 0.5225709676742554,
      "learning_rate": 1.1275748972249226e-05,
      "loss": 0.5766,
      "step": 29957
    },
    {
      "epoch": 0.9202838448069303,
      "grad_norm": 0.44617152214050293,
      "learning_rate": 1.1275269642311385e-05,
      "loss": 0.531,
      "step": 29958
    },
    {
      "epoch": 0.9203145639418794,
      "grad_norm": 0.4651534855365753,
      "learning_rate": 1.1274790309395066e-05,
      "loss": 0.491,
      "step": 29959
    },
    {
      "epoch": 0.9203452830768285,
      "grad_norm": 0.37205153703689575,
      "learning_rate": 1.127431097350138e-05,
      "loss": 0.4938,
      "step": 29960
    },
    {
      "epoch": 0.9203760022117777,
      "grad_norm": 0.4140256643295288,
      "learning_rate": 1.1273831634631459e-05,
      "loss": 0.4834,
      "step": 29961
    },
    {
      "epoch": 0.9204067213467269,
      "grad_norm": 0.3615560531616211,
      "learning_rate": 1.127335229278641e-05,
      "loss": 0.646,
      "step": 29962
    },
    {
      "epoch": 0.9204374404816761,
      "grad_norm": 0.4336291551589966,
      "learning_rate": 1.1272872947967359e-05,
      "loss": 0.5488,
      "step": 29963
    },
    {
      "epoch": 0.9204681596166252,
      "grad_norm": 0.4756731390953064,
      "learning_rate": 1.1272393600175427e-05,
      "loss": 0.4505,
      "step": 29964
    },
    {
      "epoch": 0.9204988787515743,
      "grad_norm": 0.4346102178096771,
      "learning_rate": 1.1271914249411729e-05,
      "loss": 0.5285,
      "step": 29965
    },
    {
      "epoch": 0.9205295978865236,
      "grad_norm": 0.38906222581863403,
      "learning_rate": 1.1271434895677387e-05,
      "loss": 0.5962,
      "step": 29966
    },
    {
      "epoch": 0.9205603170214727,
      "grad_norm": 0.3644165098667145,
      "learning_rate": 1.1270955538973513e-05,
      "loss": 0.4655,
      "step": 29967
    },
    {
      "epoch": 0.9205910361564218,
      "grad_norm": 0.36042895913124084,
      "learning_rate": 1.1270476179301241e-05,
      "loss": 0.4778,
      "step": 29968
    },
    {
      "epoch": 0.920621755291371,
      "grad_norm": 0.3721064627170563,
      "learning_rate": 1.1269996816661681e-05,
      "loss": 0.561,
      "step": 29969
    },
    {
      "epoch": 0.9206524744263201,
      "grad_norm": 0.34181132912635803,
      "learning_rate": 1.1269517451055959e-05,
      "loss": 0.5515,
      "step": 29970
    },
    {
      "epoch": 0.9206831935612693,
      "grad_norm": 0.3369958996772766,
      "learning_rate": 1.1269038082485187e-05,
      "loss": 0.5687,
      "step": 29971
    },
    {
      "epoch": 0.9207139126962185,
      "grad_norm": 0.3779838979244232,
      "learning_rate": 1.1268558710950487e-05,
      "loss": 0.4935,
      "step": 29972
    },
    {
      "epoch": 0.9207446318311676,
      "grad_norm": 0.3547717034816742,
      "learning_rate": 1.126807933645298e-05,
      "loss": 0.5707,
      "step": 29973
    },
    {
      "epoch": 0.9207753509661168,
      "grad_norm": 0.35227230191230774,
      "learning_rate": 1.1267599958993785e-05,
      "loss": 0.5369,
      "step": 29974
    },
    {
      "epoch": 0.920806070101066,
      "grad_norm": 0.4852278232574463,
      "learning_rate": 1.1267120578574022e-05,
      "loss": 0.4593,
      "step": 29975
    },
    {
      "epoch": 0.9208367892360151,
      "grad_norm": 0.3880731165409088,
      "learning_rate": 1.126664119519481e-05,
      "loss": 0.5216,
      "step": 29976
    },
    {
      "epoch": 0.9208675083709643,
      "grad_norm": 0.4194117486476898,
      "learning_rate": 1.1266161808857273e-05,
      "loss": 0.5379,
      "step": 29977
    },
    {
      "epoch": 0.9208982275059134,
      "grad_norm": 0.5134453177452087,
      "learning_rate": 1.126568241956252e-05,
      "loss": 0.5289,
      "step": 29978
    },
    {
      "epoch": 0.9209289466408626,
      "grad_norm": 0.36548614501953125,
      "learning_rate": 1.1265203027311681e-05,
      "loss": 0.497,
      "step": 29979
    },
    {
      "epoch": 0.9209596657758118,
      "grad_norm": 0.4193050265312195,
      "learning_rate": 1.1264723632105872e-05,
      "loss": 0.6173,
      "step": 29980
    },
    {
      "epoch": 0.9209903849107609,
      "grad_norm": 0.4160073399543762,
      "learning_rate": 1.1264244233946214e-05,
      "loss": 0.5221,
      "step": 29981
    },
    {
      "epoch": 0.92102110404571,
      "grad_norm": 0.3888459801673889,
      "learning_rate": 1.1263764832833823e-05,
      "loss": 0.6169,
      "step": 29982
    },
    {
      "epoch": 0.9210518231806593,
      "grad_norm": 0.3380714952945709,
      "learning_rate": 1.1263285428769821e-05,
      "loss": 0.4709,
      "step": 29983
    },
    {
      "epoch": 0.9210825423156084,
      "grad_norm": 0.39911699295043945,
      "learning_rate": 1.1262806021755331e-05,
      "loss": 0.522,
      "step": 29984
    },
    {
      "epoch": 0.9211132614505576,
      "grad_norm": 0.37550267577171326,
      "learning_rate": 1.1262326611791462e-05,
      "loss": 0.5146,
      "step": 29985
    },
    {
      "epoch": 0.9211439805855067,
      "grad_norm": 0.3666677176952362,
      "learning_rate": 1.1261847198879346e-05,
      "loss": 0.5873,
      "step": 29986
    },
    {
      "epoch": 0.9211746997204558,
      "grad_norm": 0.3925999104976654,
      "learning_rate": 1.12613677830201e-05,
      "loss": 0.547,
      "step": 29987
    },
    {
      "epoch": 0.9212054188554051,
      "grad_norm": 0.37403222918510437,
      "learning_rate": 1.1260888364214838e-05,
      "loss": 0.5192,
      "step": 29988
    },
    {
      "epoch": 0.9212361379903542,
      "grad_norm": 0.34289970993995667,
      "learning_rate": 1.1260408942464682e-05,
      "loss": 0.5011,
      "step": 29989
    },
    {
      "epoch": 0.9212668571253033,
      "grad_norm": 0.4002101719379425,
      "learning_rate": 1.1259929517770756e-05,
      "loss": 0.5646,
      "step": 29990
    },
    {
      "epoch": 0.9212975762602525,
      "grad_norm": 0.3749113380908966,
      "learning_rate": 1.1259450090134176e-05,
      "loss": 0.5658,
      "step": 29991
    },
    {
      "epoch": 0.9213282953952017,
      "grad_norm": 0.3723420202732086,
      "learning_rate": 1.1258970659556062e-05,
      "loss": 0.6112,
      "step": 29992
    },
    {
      "epoch": 0.9213590145301508,
      "grad_norm": 0.33891499042510986,
      "learning_rate": 1.1258491226037533e-05,
      "loss": 0.4365,
      "step": 29993
    },
    {
      "epoch": 0.9213897336651,
      "grad_norm": 0.39398443698883057,
      "learning_rate": 1.125801178957971e-05,
      "loss": 0.5243,
      "step": 29994
    },
    {
      "epoch": 0.9214204528000491,
      "grad_norm": 0.3891143500804901,
      "learning_rate": 1.1257532350183715e-05,
      "loss": 0.5473,
      "step": 29995
    },
    {
      "epoch": 0.9214511719349983,
      "grad_norm": 0.34050509333610535,
      "learning_rate": 1.1257052907850661e-05,
      "loss": 0.5313,
      "step": 29996
    },
    {
      "epoch": 0.9214818910699475,
      "grad_norm": 0.40583929419517517,
      "learning_rate": 1.1256573462581677e-05,
      "loss": 0.5461,
      "step": 29997
    },
    {
      "epoch": 0.9215126102048966,
      "grad_norm": 0.40817487239837646,
      "learning_rate": 1.1256094014377877e-05,
      "loss": 0.568,
      "step": 29998
    },
    {
      "epoch": 0.9215433293398458,
      "grad_norm": 0.3612138628959656,
      "learning_rate": 1.1255614563240378e-05,
      "loss": 0.5039,
      "step": 29999
    },
    {
      "epoch": 0.921574048474795,
      "grad_norm": 0.3561590313911438,
      "learning_rate": 1.1255135109170308e-05,
      "loss": 0.5691,
      "step": 30000
    },
    {
      "epoch": 0.9216047676097441,
      "grad_norm": 0.3488360345363617,
      "learning_rate": 1.125465565216878e-05,
      "loss": 0.4712,
      "step": 30001
    },
    {
      "epoch": 0.9216354867446933,
      "grad_norm": 0.4168758690357208,
      "learning_rate": 1.1254176192236917e-05,
      "loss": 0.551,
      "step": 30002
    },
    {
      "epoch": 0.9216662058796424,
      "grad_norm": 0.3940725326538086,
      "learning_rate": 1.1253696729375835e-05,
      "loss": 0.5932,
      "step": 30003
    },
    {
      "epoch": 0.9216969250145916,
      "grad_norm": 0.34979456663131714,
      "learning_rate": 1.1253217263586657e-05,
      "loss": 0.4473,
      "step": 30004
    },
    {
      "epoch": 0.9217276441495408,
      "grad_norm": 0.35536709427833557,
      "learning_rate": 1.1252737794870508e-05,
      "loss": 0.5934,
      "step": 30005
    },
    {
      "epoch": 0.9217583632844899,
      "grad_norm": 0.37758785486221313,
      "learning_rate": 1.1252258323228497e-05,
      "loss": 0.5712,
      "step": 30006
    },
    {
      "epoch": 0.921789082419439,
      "grad_norm": 0.4608696401119232,
      "learning_rate": 1.1251778848661752e-05,
      "loss": 0.5004,
      "step": 30007
    },
    {
      "epoch": 0.9218198015543883,
      "grad_norm": 0.3799079358577728,
      "learning_rate": 1.1251299371171388e-05,
      "loss": 0.558,
      "step": 30008
    },
    {
      "epoch": 0.9218505206893374,
      "grad_norm": 0.36049219965934753,
      "learning_rate": 1.1250819890758529e-05,
      "loss": 0.6065,
      "step": 30009
    },
    {
      "epoch": 0.9218812398242866,
      "grad_norm": 0.3438192307949066,
      "learning_rate": 1.1250340407424292e-05,
      "loss": 0.5415,
      "step": 30010
    },
    {
      "epoch": 0.9219119589592357,
      "grad_norm": 0.3826729655265808,
      "learning_rate": 1.1249860921169797e-05,
      "loss": 0.5006,
      "step": 30011
    },
    {
      "epoch": 0.9219426780941848,
      "grad_norm": 0.39334627985954285,
      "learning_rate": 1.1249381431996165e-05,
      "loss": 0.572,
      "step": 30012
    },
    {
      "epoch": 0.9219733972291341,
      "grad_norm": 0.4380052983760834,
      "learning_rate": 1.1248901939904517e-05,
      "loss": 0.5409,
      "step": 30013
    },
    {
      "epoch": 0.9220041163640832,
      "grad_norm": 0.3461383879184723,
      "learning_rate": 1.1248422444895967e-05,
      "loss": 0.5715,
      "step": 30014
    },
    {
      "epoch": 0.9220348354990323,
      "grad_norm": 0.37462317943573,
      "learning_rate": 1.1247942946971643e-05,
      "loss": 0.6101,
      "step": 30015
    },
    {
      "epoch": 0.9220655546339815,
      "grad_norm": 0.33808737993240356,
      "learning_rate": 1.1247463446132662e-05,
      "loss": 0.52,
      "step": 30016
    },
    {
      "epoch": 0.9220962737689307,
      "grad_norm": 0.3869457542896271,
      "learning_rate": 1.124698394238014e-05,
      "loss": 0.567,
      "step": 30017
    },
    {
      "epoch": 0.9221269929038798,
      "grad_norm": 0.3535647392272949,
      "learning_rate": 1.1246504435715204e-05,
      "loss": 0.6166,
      "step": 30018
    },
    {
      "epoch": 0.922157712038829,
      "grad_norm": 0.3918992578983307,
      "learning_rate": 1.1246024926138965e-05,
      "loss": 0.5636,
      "step": 30019
    },
    {
      "epoch": 0.9221884311737781,
      "grad_norm": 0.3863928020000458,
      "learning_rate": 1.124554541365255e-05,
      "loss": 0.503,
      "step": 30020
    },
    {
      "epoch": 0.9222191503087273,
      "grad_norm": 0.3549692928791046,
      "learning_rate": 1.1245065898257074e-05,
      "loss": 0.5501,
      "step": 30021
    },
    {
      "epoch": 0.9222498694436765,
      "grad_norm": 0.3330966830253601,
      "learning_rate": 1.1244586379953663e-05,
      "loss": 0.5186,
      "step": 30022
    },
    {
      "epoch": 0.9222805885786256,
      "grad_norm": 0.35222336649894714,
      "learning_rate": 1.1244106858743433e-05,
      "loss": 0.5897,
      "step": 30023
    },
    {
      "epoch": 0.9223113077135748,
      "grad_norm": 0.3579084575176239,
      "learning_rate": 1.1243627334627502e-05,
      "loss": 0.6038,
      "step": 30024
    },
    {
      "epoch": 0.922342026848524,
      "grad_norm": 0.3734002709388733,
      "learning_rate": 1.1243147807606998e-05,
      "loss": 0.5801,
      "step": 30025
    },
    {
      "epoch": 0.9223727459834731,
      "grad_norm": 0.3645961284637451,
      "learning_rate": 1.124266827768303e-05,
      "loss": 0.509,
      "step": 30026
    },
    {
      "epoch": 0.9224034651184223,
      "grad_norm": 0.4008324444293976,
      "learning_rate": 1.1242188744856726e-05,
      "loss": 0.5059,
      "step": 30027
    },
    {
      "epoch": 0.9224341842533714,
      "grad_norm": 0.3719411790370941,
      "learning_rate": 1.1241709209129203e-05,
      "loss": 0.5436,
      "step": 30028
    },
    {
      "epoch": 0.9224649033883205,
      "grad_norm": 0.44545838236808777,
      "learning_rate": 1.1241229670501582e-05,
      "loss": 0.6186,
      "step": 30029
    },
    {
      "epoch": 0.9224956225232698,
      "grad_norm": 0.381887823343277,
      "learning_rate": 1.124075012897498e-05,
      "loss": 0.569,
      "step": 30030
    },
    {
      "epoch": 0.9225263416582189,
      "grad_norm": 0.3798633813858032,
      "learning_rate": 1.1240270584550523e-05,
      "loss": 0.5563,
      "step": 30031
    },
    {
      "epoch": 0.922557060793168,
      "grad_norm": 0.3891291618347168,
      "learning_rate": 1.1239791037229325e-05,
      "loss": 0.5374,
      "step": 30032
    },
    {
      "epoch": 0.9225877799281172,
      "grad_norm": 0.34691083431243896,
      "learning_rate": 1.1239311487012509e-05,
      "loss": 0.547,
      "step": 30033
    },
    {
      "epoch": 0.9226184990630664,
      "grad_norm": 0.4190441370010376,
      "learning_rate": 1.1238831933901197e-05,
      "loss": 0.4987,
      "step": 30034
    },
    {
      "epoch": 0.9226492181980156,
      "grad_norm": 0.4357995092868805,
      "learning_rate": 1.1238352377896502e-05,
      "loss": 0.5934,
      "step": 30035
    },
    {
      "epoch": 0.9226799373329647,
      "grad_norm": 0.5160508155822754,
      "learning_rate": 1.1237872818999551e-05,
      "loss": 0.5693,
      "step": 30036
    },
    {
      "epoch": 0.9227106564679138,
      "grad_norm": 0.33477482199668884,
      "learning_rate": 1.1237393257211462e-05,
      "loss": 0.5258,
      "step": 30037
    },
    {
      "epoch": 0.9227413756028631,
      "grad_norm": 0.34983745217323303,
      "learning_rate": 1.1236913692533355e-05,
      "loss": 0.5481,
      "step": 30038
    },
    {
      "epoch": 0.9227720947378122,
      "grad_norm": 0.3413762152194977,
      "learning_rate": 1.1236434124966346e-05,
      "loss": 0.5023,
      "step": 30039
    },
    {
      "epoch": 0.9228028138727613,
      "grad_norm": 0.37891146540641785,
      "learning_rate": 1.1235954554511562e-05,
      "loss": 0.561,
      "step": 30040
    },
    {
      "epoch": 0.9228335330077105,
      "grad_norm": 0.47235676646232605,
      "learning_rate": 1.123547498117012e-05,
      "loss": 0.6007,
      "step": 30041
    },
    {
      "epoch": 0.9228642521426597,
      "grad_norm": 0.39065632224082947,
      "learning_rate": 1.1234995404943136e-05,
      "loss": 0.4931,
      "step": 30042
    },
    {
      "epoch": 0.9228949712776088,
      "grad_norm": 0.34963127970695496,
      "learning_rate": 1.123451582583174e-05,
      "loss": 0.5039,
      "step": 30043
    },
    {
      "epoch": 0.922925690412558,
      "grad_norm": 0.36501845717430115,
      "learning_rate": 1.1234036243837041e-05,
      "loss": 0.5658,
      "step": 30044
    },
    {
      "epoch": 0.9229564095475071,
      "grad_norm": 0.43439361453056335,
      "learning_rate": 1.1233556658960167e-05,
      "loss": 0.569,
      "step": 30045
    },
    {
      "epoch": 0.9229871286824562,
      "grad_norm": 0.36586782336235046,
      "learning_rate": 1.1233077071202235e-05,
      "loss": 0.5718,
      "step": 30046
    },
    {
      "epoch": 0.9230178478174055,
      "grad_norm": 0.47001656889915466,
      "learning_rate": 1.1232597480564365e-05,
      "loss": 0.5847,
      "step": 30047
    },
    {
      "epoch": 0.9230485669523546,
      "grad_norm": 0.347569078207016,
      "learning_rate": 1.1232117887047675e-05,
      "loss": 0.4886,
      "step": 30048
    },
    {
      "epoch": 0.9230792860873038,
      "grad_norm": 0.3632048964500427,
      "learning_rate": 1.1231638290653293e-05,
      "loss": 0.5485,
      "step": 30049
    },
    {
      "epoch": 0.923110005222253,
      "grad_norm": 0.3924248218536377,
      "learning_rate": 1.123115869138233e-05,
      "loss": 0.491,
      "step": 30050
    },
    {
      "epoch": 0.9231407243572021,
      "grad_norm": 0.3840333819389343,
      "learning_rate": 1.123067908923591e-05,
      "loss": 0.448,
      "step": 30051
    },
    {
      "epoch": 0.9231714434921513,
      "grad_norm": 0.3638237714767456,
      "learning_rate": 1.1230199484215155e-05,
      "loss": 0.5413,
      "step": 30052
    },
    {
      "epoch": 0.9232021626271004,
      "grad_norm": 0.3240947425365448,
      "learning_rate": 1.122971987632118e-05,
      "loss": 0.5109,
      "step": 30053
    },
    {
      "epoch": 0.9232328817620495,
      "grad_norm": 0.39878329634666443,
      "learning_rate": 1.1229240265555112e-05,
      "loss": 0.4908,
      "step": 30054
    },
    {
      "epoch": 0.9232636008969988,
      "grad_norm": 0.3747442662715912,
      "learning_rate": 1.1228760651918065e-05,
      "loss": 0.545,
      "step": 30055
    },
    {
      "epoch": 0.9232943200319479,
      "grad_norm": 0.47478190064430237,
      "learning_rate": 1.1228281035411163e-05,
      "loss": 0.573,
      "step": 30056
    },
    {
      "epoch": 0.923325039166897,
      "grad_norm": 0.3876458704471588,
      "learning_rate": 1.1227801416035525e-05,
      "loss": 0.6162,
      "step": 30057
    },
    {
      "epoch": 0.9233557583018462,
      "grad_norm": 0.38263174891471863,
      "learning_rate": 1.122732179379227e-05,
      "loss": 0.5911,
      "step": 30058
    },
    {
      "epoch": 0.9233864774367954,
      "grad_norm": 0.4247816801071167,
      "learning_rate": 1.1226842168682519e-05,
      "loss": 0.5247,
      "step": 30059
    },
    {
      "epoch": 0.9234171965717446,
      "grad_norm": 0.3633385896682739,
      "learning_rate": 1.1226362540707391e-05,
      "loss": 0.5185,
      "step": 30060
    },
    {
      "epoch": 0.9234479157066937,
      "grad_norm": 0.36043211817741394,
      "learning_rate": 1.122588290986801e-05,
      "loss": 0.5561,
      "step": 30061
    },
    {
      "epoch": 0.9234786348416428,
      "grad_norm": 0.35157543420791626,
      "learning_rate": 1.1225403276165495e-05,
      "loss": 0.6182,
      "step": 30062
    },
    {
      "epoch": 0.9235093539765921,
      "grad_norm": 0.39171096682548523,
      "learning_rate": 1.1224923639600961e-05,
      "loss": 0.4646,
      "step": 30063
    },
    {
      "epoch": 0.9235400731115412,
      "grad_norm": 0.3847489655017853,
      "learning_rate": 1.1224444000175537e-05,
      "loss": 0.5944,
      "step": 30064
    },
    {
      "epoch": 0.9235707922464903,
      "grad_norm": 0.3767077326774597,
      "learning_rate": 1.1223964357890336e-05,
      "loss": 0.6682,
      "step": 30065
    },
    {
      "epoch": 0.9236015113814395,
      "grad_norm": 0.3323873281478882,
      "learning_rate": 1.122348471274648e-05,
      "loss": 0.471,
      "step": 30066
    },
    {
      "epoch": 0.9236322305163887,
      "grad_norm": 0.3674118220806122,
      "learning_rate": 1.1223005064745092e-05,
      "loss": 0.5301,
      "step": 30067
    },
    {
      "epoch": 0.9236629496513378,
      "grad_norm": 0.3650074899196625,
      "learning_rate": 1.1222525413887291e-05,
      "loss": 0.5047,
      "step": 30068
    },
    {
      "epoch": 0.923693668786287,
      "grad_norm": 0.3513357639312744,
      "learning_rate": 1.1222045760174194e-05,
      "loss": 0.5474,
      "step": 30069
    },
    {
      "epoch": 0.9237243879212361,
      "grad_norm": 0.40105152130126953,
      "learning_rate": 1.1221566103606925e-05,
      "loss": 0.542,
      "step": 30070
    },
    {
      "epoch": 0.9237551070561852,
      "grad_norm": 0.4702177941799164,
      "learning_rate": 1.1221086444186602e-05,
      "loss": 0.5239,
      "step": 30071
    },
    {
      "epoch": 0.9237858261911345,
      "grad_norm": 0.3570261001586914,
      "learning_rate": 1.1220606781914347e-05,
      "loss": 0.5343,
      "step": 30072
    },
    {
      "epoch": 0.9238165453260836,
      "grad_norm": 0.6798921823501587,
      "learning_rate": 1.122012711679128e-05,
      "loss": 0.5008,
      "step": 30073
    },
    {
      "epoch": 0.9238472644610328,
      "grad_norm": 0.34671902656555176,
      "learning_rate": 1.121964744881852e-05,
      "loss": 0.5269,
      "step": 30074
    },
    {
      "epoch": 0.9238779835959819,
      "grad_norm": 0.3652777373790741,
      "learning_rate": 1.121916777799719e-05,
      "loss": 0.513,
      "step": 30075
    },
    {
      "epoch": 0.9239087027309311,
      "grad_norm": 0.36349523067474365,
      "learning_rate": 1.1218688104328408e-05,
      "loss": 0.5766,
      "step": 30076
    },
    {
      "epoch": 0.9239394218658803,
      "grad_norm": 0.3817389905452728,
      "learning_rate": 1.1218208427813293e-05,
      "loss": 0.5573,
      "step": 30077
    },
    {
      "epoch": 0.9239701410008294,
      "grad_norm": 0.3545553982257843,
      "learning_rate": 1.1217728748452967e-05,
      "loss": 0.5827,
      "step": 30078
    },
    {
      "epoch": 0.9240008601357785,
      "grad_norm": 0.3860584497451782,
      "learning_rate": 1.1217249066248551e-05,
      "loss": 0.522,
      "step": 30079
    },
    {
      "epoch": 0.9240315792707278,
      "grad_norm": 0.3380851745605469,
      "learning_rate": 1.1216769381201165e-05,
      "loss": 0.4915,
      "step": 30080
    },
    {
      "epoch": 0.9240622984056769,
      "grad_norm": 0.467037558555603,
      "learning_rate": 1.121628969331193e-05,
      "loss": 0.6002,
      "step": 30081
    },
    {
      "epoch": 0.924093017540626,
      "grad_norm": 0.3553353250026703,
      "learning_rate": 1.1215810002581966e-05,
      "loss": 0.6308,
      "step": 30082
    },
    {
      "epoch": 0.9241237366755752,
      "grad_norm": 0.43807563185691833,
      "learning_rate": 1.1215330309012393e-05,
      "loss": 0.6467,
      "step": 30083
    },
    {
      "epoch": 0.9241544558105244,
      "grad_norm": 0.362082302570343,
      "learning_rate": 1.121485061260433e-05,
      "loss": 0.5567,
      "step": 30084
    },
    {
      "epoch": 0.9241851749454736,
      "grad_norm": 0.3634592890739441,
      "learning_rate": 1.1214370913358898e-05,
      "loss": 0.4357,
      "step": 30085
    },
    {
      "epoch": 0.9242158940804227,
      "grad_norm": 0.3891961872577667,
      "learning_rate": 1.1213891211277219e-05,
      "loss": 0.614,
      "step": 30086
    },
    {
      "epoch": 0.9242466132153718,
      "grad_norm": 0.385306715965271,
      "learning_rate": 1.1213411506360413e-05,
      "loss": 0.5815,
      "step": 30087
    },
    {
      "epoch": 0.9242773323503211,
      "grad_norm": 0.35788872838020325,
      "learning_rate": 1.1212931798609599e-05,
      "loss": 0.5365,
      "step": 30088
    },
    {
      "epoch": 0.9243080514852702,
      "grad_norm": 0.4196898639202118,
      "learning_rate": 1.1212452088025895e-05,
      "loss": 0.4995,
      "step": 30089
    },
    {
      "epoch": 0.9243387706202193,
      "grad_norm": 0.3561948537826538,
      "learning_rate": 1.121197237461043e-05,
      "loss": 0.509,
      "step": 30090
    },
    {
      "epoch": 0.9243694897551685,
      "grad_norm": 0.6514362692832947,
      "learning_rate": 1.1211492658364314e-05,
      "loss": 0.5327,
      "step": 30091
    },
    {
      "epoch": 0.9244002088901176,
      "grad_norm": 0.3332548141479492,
      "learning_rate": 1.1211012939288675e-05,
      "loss": 0.5238,
      "step": 30092
    },
    {
      "epoch": 0.9244309280250668,
      "grad_norm": 0.35330429673194885,
      "learning_rate": 1.1210533217384629e-05,
      "loss": 0.4793,
      "step": 30093
    },
    {
      "epoch": 0.924461647160016,
      "grad_norm": 0.4256698489189148,
      "learning_rate": 1.1210053492653301e-05,
      "loss": 0.4688,
      "step": 30094
    },
    {
      "epoch": 0.9244923662949651,
      "grad_norm": 0.3737295866012573,
      "learning_rate": 1.1209573765095804e-05,
      "loss": 0.5143,
      "step": 30095
    },
    {
      "epoch": 0.9245230854299143,
      "grad_norm": 0.3410843312740326,
      "learning_rate": 1.1209094034713266e-05,
      "loss": 0.5006,
      "step": 30096
    },
    {
      "epoch": 0.9245538045648635,
      "grad_norm": 0.3523876965045929,
      "learning_rate": 1.1208614301506803e-05,
      "loss": 0.6028,
      "step": 30097
    },
    {
      "epoch": 0.9245845236998126,
      "grad_norm": 0.3579404652118683,
      "learning_rate": 1.1208134565477537e-05,
      "loss": 0.5306,
      "step": 30098
    },
    {
      "epoch": 0.9246152428347618,
      "grad_norm": 0.4276377260684967,
      "learning_rate": 1.1207654826626592e-05,
      "loss": 0.5569,
      "step": 30099
    },
    {
      "epoch": 0.9246459619697109,
      "grad_norm": 0.36201366782188416,
      "learning_rate": 1.120717508495508e-05,
      "loss": 0.542,
      "step": 30100
    },
    {
      "epoch": 0.9246766811046601,
      "grad_norm": 0.37701302766799927,
      "learning_rate": 1.1206695340464131e-05,
      "loss": 0.5332,
      "step": 30101
    },
    {
      "epoch": 0.9247074002396093,
      "grad_norm": 0.37165459990501404,
      "learning_rate": 1.1206215593154856e-05,
      "loss": 0.597,
      "step": 30102
    },
    {
      "epoch": 0.9247381193745584,
      "grad_norm": 0.35811248421669006,
      "learning_rate": 1.1205735843028385e-05,
      "loss": 0.6412,
      "step": 30103
    },
    {
      "epoch": 0.9247688385095075,
      "grad_norm": 0.34183159470558167,
      "learning_rate": 1.1205256090085832e-05,
      "loss": 0.6135,
      "step": 30104
    },
    {
      "epoch": 0.9247995576444568,
      "grad_norm": 0.3511563241481781,
      "learning_rate": 1.1204776334328315e-05,
      "loss": 0.5247,
      "step": 30105
    },
    {
      "epoch": 0.9248302767794059,
      "grad_norm": 0.3845004141330719,
      "learning_rate": 1.1204296575756966e-05,
      "loss": 0.5535,
      "step": 30106
    },
    {
      "epoch": 0.924860995914355,
      "grad_norm": 0.33403444290161133,
      "learning_rate": 1.1203816814372891e-05,
      "loss": 0.5062,
      "step": 30107
    },
    {
      "epoch": 0.9248917150493042,
      "grad_norm": 0.34827741980552673,
      "learning_rate": 1.1203337050177223e-05,
      "loss": 0.4774,
      "step": 30108
    },
    {
      "epoch": 0.9249224341842534,
      "grad_norm": 0.3576902449131012,
      "learning_rate": 1.1202857283171073e-05,
      "loss": 0.6077,
      "step": 30109
    },
    {
      "epoch": 0.9249531533192026,
      "grad_norm": 0.36620208621025085,
      "learning_rate": 1.1202377513355571e-05,
      "loss": 0.6001,
      "step": 30110
    },
    {
      "epoch": 0.9249838724541517,
      "grad_norm": 0.42570504546165466,
      "learning_rate": 1.1201897740731829e-05,
      "loss": 0.5418,
      "step": 30111
    },
    {
      "epoch": 0.9250145915891008,
      "grad_norm": 0.49701520800590515,
      "learning_rate": 1.1201417965300972e-05,
      "loss": 0.5107,
      "step": 30112
    },
    {
      "epoch": 0.92504531072405,
      "grad_norm": 0.42950209975242615,
      "learning_rate": 1.1200938187064116e-05,
      "loss": 0.5971,
      "step": 30113
    },
    {
      "epoch": 0.9250760298589992,
      "grad_norm": 0.391383558511734,
      "learning_rate": 1.1200458406022388e-05,
      "loss": 0.6149,
      "step": 30114
    },
    {
      "epoch": 0.9251067489939483,
      "grad_norm": 0.3904705047607422,
      "learning_rate": 1.1199978622176905e-05,
      "loss": 0.5551,
      "step": 30115
    },
    {
      "epoch": 0.9251374681288975,
      "grad_norm": 0.3922196328639984,
      "learning_rate": 1.1199498835528791e-05,
      "loss": 0.5689,
      "step": 30116
    },
    {
      "epoch": 0.9251681872638466,
      "grad_norm": 0.40581902861595154,
      "learning_rate": 1.119901904607916e-05,
      "loss": 0.5401,
      "step": 30117
    },
    {
      "epoch": 0.9251989063987958,
      "grad_norm": 0.3520056903362274,
      "learning_rate": 1.1198539253829136e-05,
      "loss": 0.5329,
      "step": 30118
    },
    {
      "epoch": 0.925229625533745,
      "grad_norm": 0.37194889783859253,
      "learning_rate": 1.1198059458779844e-05,
      "loss": 0.5482,
      "step": 30119
    },
    {
      "epoch": 0.9252603446686941,
      "grad_norm": 0.37963056564331055,
      "learning_rate": 1.1197579660932399e-05,
      "loss": 0.4966,
      "step": 30120
    },
    {
      "epoch": 0.9252910638036433,
      "grad_norm": 0.3649732172489166,
      "learning_rate": 1.119709986028792e-05,
      "loss": 0.513,
      "step": 30121
    },
    {
      "epoch": 0.9253217829385925,
      "grad_norm": 0.3953976035118103,
      "learning_rate": 1.1196620056847534e-05,
      "loss": 0.4547,
      "step": 30122
    },
    {
      "epoch": 0.9253525020735416,
      "grad_norm": 0.38349175453186035,
      "learning_rate": 1.1196140250612355e-05,
      "loss": 0.5884,
      "step": 30123
    },
    {
      "epoch": 0.9253832212084908,
      "grad_norm": 0.35273653268814087,
      "learning_rate": 1.1195660441583511e-05,
      "loss": 0.5528,
      "step": 30124
    },
    {
      "epoch": 0.9254139403434399,
      "grad_norm": 0.39514032006263733,
      "learning_rate": 1.1195180629762114e-05,
      "loss": 0.5961,
      "step": 30125
    },
    {
      "epoch": 0.925444659478389,
      "grad_norm": 0.41808539628982544,
      "learning_rate": 1.1194700815149294e-05,
      "loss": 0.5562,
      "step": 30126
    },
    {
      "epoch": 0.9254753786133383,
      "grad_norm": 0.3773539662361145,
      "learning_rate": 1.1194220997746163e-05,
      "loss": 0.4475,
      "step": 30127
    },
    {
      "epoch": 0.9255060977482874,
      "grad_norm": 0.3471530079841614,
      "learning_rate": 1.1193741177553847e-05,
      "loss": 0.5661,
      "step": 30128
    },
    {
      "epoch": 0.9255368168832365,
      "grad_norm": 0.3452467620372772,
      "learning_rate": 1.1193261354573464e-05,
      "loss": 0.5028,
      "step": 30129
    },
    {
      "epoch": 0.9255675360181858,
      "grad_norm": 0.36960768699645996,
      "learning_rate": 1.1192781528806139e-05,
      "loss": 0.5197,
      "step": 30130
    },
    {
      "epoch": 0.9255982551531349,
      "grad_norm": 0.3780989646911621,
      "learning_rate": 1.1192301700252987e-05,
      "loss": 0.6063,
      "step": 30131
    },
    {
      "epoch": 0.925628974288084,
      "grad_norm": 0.3182419538497925,
      "learning_rate": 1.1191821868915126e-05,
      "loss": 0.5079,
      "step": 30132
    },
    {
      "epoch": 0.9256596934230332,
      "grad_norm": 0.38533058762550354,
      "learning_rate": 1.119134203479369e-05,
      "loss": 0.539,
      "step": 30133
    },
    {
      "epoch": 0.9256904125579823,
      "grad_norm": 0.3389412760734558,
      "learning_rate": 1.1190862197889788e-05,
      "loss": 0.5061,
      "step": 30134
    },
    {
      "epoch": 0.9257211316929316,
      "grad_norm": 0.3827824294567108,
      "learning_rate": 1.1190382358204546e-05,
      "loss": 0.5061,
      "step": 30135
    },
    {
      "epoch": 0.9257518508278807,
      "grad_norm": 0.3931884467601776,
      "learning_rate": 1.118990251573908e-05,
      "loss": 0.5273,
      "step": 30136
    },
    {
      "epoch": 0.9257825699628298,
      "grad_norm": 0.4692617654800415,
      "learning_rate": 1.1189422670494517e-05,
      "loss": 0.4984,
      "step": 30137
    },
    {
      "epoch": 0.925813289097779,
      "grad_norm": 0.3824388384819031,
      "learning_rate": 1.118894282247197e-05,
      "loss": 0.4776,
      "step": 30138
    },
    {
      "epoch": 0.9258440082327282,
      "grad_norm": 0.3953078091144562,
      "learning_rate": 1.1188462971672567e-05,
      "loss": 0.5823,
      "step": 30139
    },
    {
      "epoch": 0.9258747273676773,
      "grad_norm": 0.8896430134773254,
      "learning_rate": 1.1187983118097425e-05,
      "loss": 0.4917,
      "step": 30140
    },
    {
      "epoch": 0.9259054465026265,
      "grad_norm": 0.3522399067878723,
      "learning_rate": 1.1187503261747666e-05,
      "loss": 0.5186,
      "step": 30141
    },
    {
      "epoch": 0.9259361656375756,
      "grad_norm": 0.3614135682582855,
      "learning_rate": 1.118702340262441e-05,
      "loss": 0.5321,
      "step": 30142
    },
    {
      "epoch": 0.9259668847725248,
      "grad_norm": 0.33916154503822327,
      "learning_rate": 1.1186543540728776e-05,
      "loss": 0.5302,
      "step": 30143
    },
    {
      "epoch": 0.925997603907474,
      "grad_norm": 0.3717201054096222,
      "learning_rate": 1.1186063676061891e-05,
      "loss": 0.461,
      "step": 30144
    },
    {
      "epoch": 0.9260283230424231,
      "grad_norm": 0.37520650029182434,
      "learning_rate": 1.1185583808624867e-05,
      "loss": 0.567,
      "step": 30145
    },
    {
      "epoch": 0.9260590421773723,
      "grad_norm": 0.39829209446907043,
      "learning_rate": 1.1185103938418833e-05,
      "loss": 0.5492,
      "step": 30146
    },
    {
      "epoch": 0.9260897613123215,
      "grad_norm": 0.3451083302497864,
      "learning_rate": 1.1184624065444901e-05,
      "loss": 0.4873,
      "step": 30147
    },
    {
      "epoch": 0.9261204804472706,
      "grad_norm": 0.3733082711696625,
      "learning_rate": 1.1184144189704203e-05,
      "loss": 0.5129,
      "step": 30148
    },
    {
      "epoch": 0.9261511995822198,
      "grad_norm": 0.6512208580970764,
      "learning_rate": 1.118366431119785e-05,
      "loss": 0.5181,
      "step": 30149
    },
    {
      "epoch": 0.9261819187171689,
      "grad_norm": 0.3566914498806,
      "learning_rate": 1.1183184429926962e-05,
      "loss": 0.477,
      "step": 30150
    },
    {
      "epoch": 0.926212637852118,
      "grad_norm": 0.4268516004085541,
      "learning_rate": 1.1182704545892671e-05,
      "loss": 0.5119,
      "step": 30151
    },
    {
      "epoch": 0.9262433569870673,
      "grad_norm": 0.4622008502483368,
      "learning_rate": 1.1182224659096087e-05,
      "loss": 0.6095,
      "step": 30152
    },
    {
      "epoch": 0.9262740761220164,
      "grad_norm": 0.3923918604850769,
      "learning_rate": 1.1181744769538339e-05,
      "loss": 0.5601,
      "step": 30153
    },
    {
      "epoch": 0.9263047952569655,
      "grad_norm": 0.36760303378105164,
      "learning_rate": 1.118126487722054e-05,
      "loss": 0.501,
      "step": 30154
    },
    {
      "epoch": 0.9263355143919147,
      "grad_norm": 0.39281052350997925,
      "learning_rate": 1.1180784982143816e-05,
      "loss": 0.588,
      "step": 30155
    },
    {
      "epoch": 0.9263662335268639,
      "grad_norm": 0.4472496211528778,
      "learning_rate": 1.1180305084309286e-05,
      "loss": 0.4992,
      "step": 30156
    },
    {
      "epoch": 0.926396952661813,
      "grad_norm": 0.3810509443283081,
      "learning_rate": 1.117982518371807e-05,
      "loss": 0.5128,
      "step": 30157
    },
    {
      "epoch": 0.9264276717967622,
      "grad_norm": 0.3797038495540619,
      "learning_rate": 1.1179345280371292e-05,
      "loss": 0.59,
      "step": 30158
    },
    {
      "epoch": 0.9264583909317113,
      "grad_norm": 0.3495463728904724,
      "learning_rate": 1.117886537427007e-05,
      "loss": 0.4298,
      "step": 30159
    },
    {
      "epoch": 0.9264891100666606,
      "grad_norm": 0.355399489402771,
      "learning_rate": 1.1178385465415524e-05,
      "loss": 0.49,
      "step": 30160
    },
    {
      "epoch": 0.9265198292016097,
      "grad_norm": 0.3675629496574402,
      "learning_rate": 1.1177905553808776e-05,
      "loss": 0.5293,
      "step": 30161
    },
    {
      "epoch": 0.9265505483365588,
      "grad_norm": 0.347541868686676,
      "learning_rate": 1.117742563945095e-05,
      "loss": 0.6078,
      "step": 30162
    },
    {
      "epoch": 0.926581267471508,
      "grad_norm": 0.4146934449672699,
      "learning_rate": 1.1176945722343163e-05,
      "loss": 0.5419,
      "step": 30163
    },
    {
      "epoch": 0.9266119866064572,
      "grad_norm": 0.4882093071937561,
      "learning_rate": 1.1176465802486536e-05,
      "loss": 0.5047,
      "step": 30164
    },
    {
      "epoch": 0.9266427057414063,
      "grad_norm": 0.3694634735584259,
      "learning_rate": 1.1175985879882191e-05,
      "loss": 0.5318,
      "step": 30165
    },
    {
      "epoch": 0.9266734248763555,
      "grad_norm": 0.361701101064682,
      "learning_rate": 1.1175505954531252e-05,
      "loss": 0.5664,
      "step": 30166
    },
    {
      "epoch": 0.9267041440113046,
      "grad_norm": 0.3858471214771271,
      "learning_rate": 1.1175026026434834e-05,
      "loss": 0.5287,
      "step": 30167
    },
    {
      "epoch": 0.9267348631462538,
      "grad_norm": 0.3563547730445862,
      "learning_rate": 1.1174546095594058e-05,
      "loss": 0.617,
      "step": 30168
    },
    {
      "epoch": 0.926765582281203,
      "grad_norm": 0.41002345085144043,
      "learning_rate": 1.1174066162010053e-05,
      "loss": 0.5417,
      "step": 30169
    },
    {
      "epoch": 0.9267963014161521,
      "grad_norm": 0.4150068461894989,
      "learning_rate": 1.117358622568393e-05,
      "loss": 0.5607,
      "step": 30170
    },
    {
      "epoch": 0.9268270205511013,
      "grad_norm": 0.35791248083114624,
      "learning_rate": 1.1173106286616818e-05,
      "loss": 0.5202,
      "step": 30171
    },
    {
      "epoch": 0.9268577396860505,
      "grad_norm": 0.33973070979118347,
      "learning_rate": 1.1172626344809833e-05,
      "loss": 0.5299,
      "step": 30172
    },
    {
      "epoch": 0.9268884588209996,
      "grad_norm": 0.38376370072364807,
      "learning_rate": 1.1172146400264096e-05,
      "loss": 0.4888,
      "step": 30173
    },
    {
      "epoch": 0.9269191779559488,
      "grad_norm": 0.4016306698322296,
      "learning_rate": 1.1171666452980732e-05,
      "loss": 0.6017,
      "step": 30174
    },
    {
      "epoch": 0.9269498970908979,
      "grad_norm": 0.37777766585350037,
      "learning_rate": 1.1171186502960855e-05,
      "loss": 0.4538,
      "step": 30175
    },
    {
      "epoch": 0.926980616225847,
      "grad_norm": 0.40095362067222595,
      "learning_rate": 1.1170706550205597e-05,
      "loss": 0.5504,
      "step": 30176
    },
    {
      "epoch": 0.9270113353607963,
      "grad_norm": 0.37049660086631775,
      "learning_rate": 1.1170226594716065e-05,
      "loss": 0.575,
      "step": 30177
    },
    {
      "epoch": 0.9270420544957454,
      "grad_norm": 0.359235942363739,
      "learning_rate": 1.1169746636493391e-05,
      "loss": 0.5766,
      "step": 30178
    },
    {
      "epoch": 0.9270727736306945,
      "grad_norm": 0.38208338618278503,
      "learning_rate": 1.116926667553869e-05,
      "loss": 0.5173,
      "step": 30179
    },
    {
      "epoch": 0.9271034927656437,
      "grad_norm": 0.420673668384552,
      "learning_rate": 1.1168786711853086e-05,
      "loss": 0.6042,
      "step": 30180
    },
    {
      "epoch": 0.9271342119005929,
      "grad_norm": 0.39908769726753235,
      "learning_rate": 1.1168306745437699e-05,
      "loss": 0.5883,
      "step": 30181
    },
    {
      "epoch": 0.927164931035542,
      "grad_norm": 0.5924801826477051,
      "learning_rate": 1.116782677629365e-05,
      "loss": 0.5061,
      "step": 30182
    },
    {
      "epoch": 0.9271956501704912,
      "grad_norm": 0.42617547512054443,
      "learning_rate": 1.1167346804422062e-05,
      "loss": 0.4808,
      "step": 30183
    },
    {
      "epoch": 0.9272263693054403,
      "grad_norm": 0.36484843492507935,
      "learning_rate": 1.116686682982405e-05,
      "loss": 0.5867,
      "step": 30184
    },
    {
      "epoch": 0.9272570884403896,
      "grad_norm": 0.35996875166893005,
      "learning_rate": 1.1166386852500742e-05,
      "loss": 0.5899,
      "step": 30185
    },
    {
      "epoch": 0.9272878075753387,
      "grad_norm": 2.797250270843506,
      "learning_rate": 1.1165906872453252e-05,
      "loss": 0.5431,
      "step": 30186
    },
    {
      "epoch": 0.9273185267102878,
      "grad_norm": 0.40430307388305664,
      "learning_rate": 1.1165426889682709e-05,
      "loss": 0.5845,
      "step": 30187
    },
    {
      "epoch": 0.927349245845237,
      "grad_norm": 0.4203284978866577,
      "learning_rate": 1.1164946904190229e-05,
      "loss": 0.5638,
      "step": 30188
    },
    {
      "epoch": 0.9273799649801862,
      "grad_norm": 0.41030803322792053,
      "learning_rate": 1.1164466915976935e-05,
      "loss": 0.5009,
      "step": 30189
    },
    {
      "epoch": 0.9274106841151353,
      "grad_norm": 0.3622567355632782,
      "learning_rate": 1.1163986925043948e-05,
      "loss": 0.4143,
      "step": 30190
    },
    {
      "epoch": 0.9274414032500845,
      "grad_norm": 0.35550570487976074,
      "learning_rate": 1.1163506931392384e-05,
      "loss": 0.5843,
      "step": 30191
    },
    {
      "epoch": 0.9274721223850336,
      "grad_norm": 0.32544004917144775,
      "learning_rate": 1.1163026935023373e-05,
      "loss": 0.4901,
      "step": 30192
    },
    {
      "epoch": 0.9275028415199827,
      "grad_norm": 0.3664722442626953,
      "learning_rate": 1.1162546935938028e-05,
      "loss": 0.6014,
      "step": 30193
    },
    {
      "epoch": 0.927533560654932,
      "grad_norm": 0.33454054594039917,
      "learning_rate": 1.1162066934137477e-05,
      "loss": 0.5652,
      "step": 30194
    },
    {
      "epoch": 0.9275642797898811,
      "grad_norm": 0.371844619512558,
      "learning_rate": 1.1161586929622834e-05,
      "loss": 0.525,
      "step": 30195
    },
    {
      "epoch": 0.9275949989248303,
      "grad_norm": 0.3830709457397461,
      "learning_rate": 1.1161106922395226e-05,
      "loss": 0.578,
      "step": 30196
    },
    {
      "epoch": 0.9276257180597794,
      "grad_norm": 0.36906898021698,
      "learning_rate": 1.116062691245577e-05,
      "loss": 0.56,
      "step": 30197
    },
    {
      "epoch": 0.9276564371947286,
      "grad_norm": 0.3508935272693634,
      "learning_rate": 1.1160146899805588e-05,
      "loss": 0.5921,
      "step": 30198
    },
    {
      "epoch": 0.9276871563296778,
      "grad_norm": 0.3938095271587372,
      "learning_rate": 1.1159666884445803e-05,
      "loss": 0.5132,
      "step": 30199
    },
    {
      "epoch": 0.9277178754646269,
      "grad_norm": 0.3800613284111023,
      "learning_rate": 1.1159186866377536e-05,
      "loss": 0.5565,
      "step": 30200
    },
    {
      "epoch": 0.927748594599576,
      "grad_norm": 0.3776589334011078,
      "learning_rate": 1.115870684560191e-05,
      "loss": 0.5867,
      "step": 30201
    },
    {
      "epoch": 0.9277793137345253,
      "grad_norm": 0.3376885950565338,
      "learning_rate": 1.1158226822120037e-05,
      "loss": 0.5782,
      "step": 30202
    },
    {
      "epoch": 0.9278100328694744,
      "grad_norm": 0.3892041742801666,
      "learning_rate": 1.115774679593305e-05,
      "loss": 0.605,
      "step": 30203
    },
    {
      "epoch": 0.9278407520044235,
      "grad_norm": 0.4134499430656433,
      "learning_rate": 1.1157266767042059e-05,
      "loss": 0.5076,
      "step": 30204
    },
    {
      "epoch": 0.9278714711393727,
      "grad_norm": 0.4356251657009125,
      "learning_rate": 1.1156786735448193e-05,
      "loss": 0.5477,
      "step": 30205
    },
    {
      "epoch": 0.9279021902743219,
      "grad_norm": 0.34721511602401733,
      "learning_rate": 1.1156306701152569e-05,
      "loss": 0.5775,
      "step": 30206
    },
    {
      "epoch": 0.9279329094092711,
      "grad_norm": 0.35710087418556213,
      "learning_rate": 1.1155826664156313e-05,
      "loss": 0.5952,
      "step": 30207
    },
    {
      "epoch": 0.9279636285442202,
      "grad_norm": 0.3986756205558777,
      "learning_rate": 1.1155346624460543e-05,
      "loss": 0.5319,
      "step": 30208
    },
    {
      "epoch": 0.9279943476791693,
      "grad_norm": 0.3309602439403534,
      "learning_rate": 1.115486658206638e-05,
      "loss": 0.4545,
      "step": 30209
    },
    {
      "epoch": 0.9280250668141186,
      "grad_norm": 0.5391010046005249,
      "learning_rate": 1.1154386536974944e-05,
      "loss": 0.534,
      "step": 30210
    },
    {
      "epoch": 0.9280557859490677,
      "grad_norm": 0.5507050156593323,
      "learning_rate": 1.1153906489187358e-05,
      "loss": 0.6325,
      "step": 30211
    },
    {
      "epoch": 0.9280865050840168,
      "grad_norm": 0.39598146080970764,
      "learning_rate": 1.1153426438704743e-05,
      "loss": 0.5678,
      "step": 30212
    },
    {
      "epoch": 0.928117224218966,
      "grad_norm": 0.38939976692199707,
      "learning_rate": 1.115294638552822e-05,
      "loss": 0.5814,
      "step": 30213
    },
    {
      "epoch": 0.9281479433539152,
      "grad_norm": 0.3737190365791321,
      "learning_rate": 1.1152466329658912e-05,
      "loss": 0.5561,
      "step": 30214
    },
    {
      "epoch": 0.9281786624888643,
      "grad_norm": 0.3885956406593323,
      "learning_rate": 1.1151986271097934e-05,
      "loss": 0.4476,
      "step": 30215
    },
    {
      "epoch": 0.9282093816238135,
      "grad_norm": 0.3685022294521332,
      "learning_rate": 1.1151506209846417e-05,
      "loss": 0.534,
      "step": 30216
    },
    {
      "epoch": 0.9282401007587626,
      "grad_norm": 0.6021429896354675,
      "learning_rate": 1.1151026145905472e-05,
      "loss": 0.4643,
      "step": 30217
    },
    {
      "epoch": 0.9282708198937117,
      "grad_norm": 0.3735480308532715,
      "learning_rate": 1.1150546079276228e-05,
      "loss": 0.4784,
      "step": 30218
    },
    {
      "epoch": 0.928301539028661,
      "grad_norm": 0.3666605055332184,
      "learning_rate": 1.1150066009959804e-05,
      "loss": 0.521,
      "step": 30219
    },
    {
      "epoch": 0.9283322581636101,
      "grad_norm": 0.3541179597377777,
      "learning_rate": 1.114958593795732e-05,
      "loss": 0.4946,
      "step": 30220
    },
    {
      "epoch": 0.9283629772985593,
      "grad_norm": 0.48388898372650146,
      "learning_rate": 1.1149105863269896e-05,
      "loss": 0.5943,
      "step": 30221
    },
    {
      "epoch": 0.9283936964335084,
      "grad_norm": 0.36419540643692017,
      "learning_rate": 1.1148625785898655e-05,
      "loss": 0.5239,
      "step": 30222
    },
    {
      "epoch": 0.9284244155684576,
      "grad_norm": 0.37652289867401123,
      "learning_rate": 1.1148145705844717e-05,
      "loss": 0.5461,
      "step": 30223
    },
    {
      "epoch": 0.9284551347034068,
      "grad_norm": 0.3907907009124756,
      "learning_rate": 1.114766562310921e-05,
      "loss": 0.6592,
      "step": 30224
    },
    {
      "epoch": 0.9284858538383559,
      "grad_norm": 0.3776606023311615,
      "learning_rate": 1.1147185537693243e-05,
      "loss": 0.5407,
      "step": 30225
    },
    {
      "epoch": 0.928516572973305,
      "grad_norm": 0.3791624903678894,
      "learning_rate": 1.114670544959795e-05,
      "loss": 0.497,
      "step": 30226
    },
    {
      "epoch": 0.9285472921082543,
      "grad_norm": 0.3809923827648163,
      "learning_rate": 1.1146225358824443e-05,
      "loss": 0.5287,
      "step": 30227
    },
    {
      "epoch": 0.9285780112432034,
      "grad_norm": 0.360485315322876,
      "learning_rate": 1.1145745265373849e-05,
      "loss": 0.5419,
      "step": 30228
    },
    {
      "epoch": 0.9286087303781525,
      "grad_norm": 0.3593321144580841,
      "learning_rate": 1.1145265169247284e-05,
      "loss": 0.5842,
      "step": 30229
    },
    {
      "epoch": 0.9286394495131017,
      "grad_norm": 0.44525986909866333,
      "learning_rate": 1.1144785070445875e-05,
      "loss": 0.5806,
      "step": 30230
    },
    {
      "epoch": 0.9286701686480509,
      "grad_norm": 0.3508704602718353,
      "learning_rate": 1.1144304968970737e-05,
      "loss": 0.5289,
      "step": 30231
    },
    {
      "epoch": 0.9287008877830001,
      "grad_norm": 0.34527403116226196,
      "learning_rate": 1.1143824864822998e-05,
      "loss": 0.4758,
      "step": 30232
    },
    {
      "epoch": 0.9287316069179492,
      "grad_norm": 0.4040375351905823,
      "learning_rate": 1.1143344758003773e-05,
      "loss": 0.5765,
      "step": 30233
    },
    {
      "epoch": 0.9287623260528983,
      "grad_norm": 0.42134901881217957,
      "learning_rate": 1.1142864648514189e-05,
      "loss": 0.5058,
      "step": 30234
    },
    {
      "epoch": 0.9287930451878476,
      "grad_norm": 0.3717963993549347,
      "learning_rate": 1.1142384536355367e-05,
      "loss": 0.5393,
      "step": 30235
    },
    {
      "epoch": 0.9288237643227967,
      "grad_norm": 0.3814767599105835,
      "learning_rate": 1.1141904421528423e-05,
      "loss": 0.5479,
      "step": 30236
    },
    {
      "epoch": 0.9288544834577458,
      "grad_norm": 0.6191640496253967,
      "learning_rate": 1.114142430403448e-05,
      "loss": 0.5124,
      "step": 30237
    },
    {
      "epoch": 0.928885202592695,
      "grad_norm": 0.31743502616882324,
      "learning_rate": 1.1140944183874662e-05,
      "loss": 0.5343,
      "step": 30238
    },
    {
      "epoch": 0.9289159217276441,
      "grad_norm": 0.43037182092666626,
      "learning_rate": 1.1140464061050092e-05,
      "loss": 0.5879,
      "step": 30239
    },
    {
      "epoch": 0.9289466408625933,
      "grad_norm": 0.3716990351676941,
      "learning_rate": 1.1139983935561885e-05,
      "loss": 0.5266,
      "step": 30240
    },
    {
      "epoch": 0.9289773599975425,
      "grad_norm": 0.33153966069221497,
      "learning_rate": 1.1139503807411167e-05,
      "loss": 0.5389,
      "step": 30241
    },
    {
      "epoch": 0.9290080791324916,
      "grad_norm": 0.359673410654068,
      "learning_rate": 1.1139023676599058e-05,
      "loss": 0.5387,
      "step": 30242
    },
    {
      "epoch": 0.9290387982674407,
      "grad_norm": 0.3780340850353241,
      "learning_rate": 1.1138543543126682e-05,
      "loss": 0.5567,
      "step": 30243
    },
    {
      "epoch": 0.92906951740239,
      "grad_norm": 0.3849318027496338,
      "learning_rate": 1.1138063406995157e-05,
      "loss": 0.5619,
      "step": 30244
    },
    {
      "epoch": 0.9291002365373391,
      "grad_norm": 0.36578169465065,
      "learning_rate": 1.1137583268205603e-05,
      "loss": 0.6635,
      "step": 30245
    },
    {
      "epoch": 0.9291309556722883,
      "grad_norm": 0.3579077124595642,
      "learning_rate": 1.1137103126759145e-05,
      "loss": 0.6202,
      "step": 30246
    },
    {
      "epoch": 0.9291616748072374,
      "grad_norm": 0.34753501415252686,
      "learning_rate": 1.1136622982656905e-05,
      "loss": 0.5133,
      "step": 30247
    },
    {
      "epoch": 0.9291923939421866,
      "grad_norm": 0.3555839955806732,
      "learning_rate": 1.1136142835900002e-05,
      "loss": 0.6061,
      "step": 30248
    },
    {
      "epoch": 0.9292231130771358,
      "grad_norm": 0.34870967268943787,
      "learning_rate": 1.1135662686489557e-05,
      "loss": 0.5979,
      "step": 30249
    },
    {
      "epoch": 0.9292538322120849,
      "grad_norm": 0.3530363440513611,
      "learning_rate": 1.1135182534426692e-05,
      "loss": 0.4879,
      "step": 30250
    },
    {
      "epoch": 0.929284551347034,
      "grad_norm": 0.35928890109062195,
      "learning_rate": 1.113470237971253e-05,
      "loss": 0.5983,
      "step": 30251
    },
    {
      "epoch": 0.9293152704819833,
      "grad_norm": 0.34430286288261414,
      "learning_rate": 1.1134222222348193e-05,
      "loss": 0.5099,
      "step": 30252
    },
    {
      "epoch": 0.9293459896169324,
      "grad_norm": 0.38013923168182373,
      "learning_rate": 1.1133742062334798e-05,
      "loss": 0.5879,
      "step": 30253
    },
    {
      "epoch": 0.9293767087518815,
      "grad_norm": 0.39649054408073425,
      "learning_rate": 1.113326189967347e-05,
      "loss": 0.6244,
      "step": 30254
    },
    {
      "epoch": 0.9294074278868307,
      "grad_norm": 0.42225560545921326,
      "learning_rate": 1.113278173436533e-05,
      "loss": 0.5627,
      "step": 30255
    },
    {
      "epoch": 0.9294381470217798,
      "grad_norm": 0.3511589765548706,
      "learning_rate": 1.1132301566411499e-05,
      "loss": 0.5287,
      "step": 30256
    },
    {
      "epoch": 0.9294688661567291,
      "grad_norm": 0.3910181224346161,
      "learning_rate": 1.11318213958131e-05,
      "loss": 0.5608,
      "step": 30257
    },
    {
      "epoch": 0.9294995852916782,
      "grad_norm": 0.3382779061794281,
      "learning_rate": 1.113134122257125e-05,
      "loss": 0.5389,
      "step": 30258
    },
    {
      "epoch": 0.9295303044266273,
      "grad_norm": 0.3790891468524933,
      "learning_rate": 1.1130861046687074e-05,
      "loss": 0.5686,
      "step": 30259
    },
    {
      "epoch": 0.9295610235615765,
      "grad_norm": 0.3785017728805542,
      "learning_rate": 1.1130380868161696e-05,
      "loss": 0.4903,
      "step": 30260
    },
    {
      "epoch": 0.9295917426965257,
      "grad_norm": 0.47548434138298035,
      "learning_rate": 1.1129900686996231e-05,
      "loss": 0.5732,
      "step": 30261
    },
    {
      "epoch": 0.9296224618314748,
      "grad_norm": 0.3643988370895386,
      "learning_rate": 1.1129420503191808e-05,
      "loss": 0.5589,
      "step": 30262
    },
    {
      "epoch": 0.929653180966424,
      "grad_norm": 0.39958712458610535,
      "learning_rate": 1.1128940316749542e-05,
      "loss": 0.594,
      "step": 30263
    },
    {
      "epoch": 0.9296839001013731,
      "grad_norm": 0.35895901918411255,
      "learning_rate": 1.1128460127670558e-05,
      "loss": 0.5568,
      "step": 30264
    },
    {
      "epoch": 0.9297146192363223,
      "grad_norm": 0.44642120599746704,
      "learning_rate": 1.1127979935955976e-05,
      "loss": 0.6024,
      "step": 30265
    },
    {
      "epoch": 0.9297453383712715,
      "grad_norm": 0.7317638397216797,
      "learning_rate": 1.1127499741606917e-05,
      "loss": 0.55,
      "step": 30266
    },
    {
      "epoch": 0.9297760575062206,
      "grad_norm": 0.3856443762779236,
      "learning_rate": 1.1127019544624505e-05,
      "loss": 0.474,
      "step": 30267
    },
    {
      "epoch": 0.9298067766411697,
      "grad_norm": 0.3441910147666931,
      "learning_rate": 1.1126539345009861e-05,
      "loss": 0.5254,
      "step": 30268
    },
    {
      "epoch": 0.929837495776119,
      "grad_norm": 0.3704175353050232,
      "learning_rate": 1.1126059142764103e-05,
      "loss": 0.5827,
      "step": 30269
    },
    {
      "epoch": 0.9298682149110681,
      "grad_norm": 0.3879517912864685,
      "learning_rate": 1.112557893788836e-05,
      "loss": 0.5499,
      "step": 30270
    },
    {
      "epoch": 0.9298989340460173,
      "grad_norm": 0.403178334236145,
      "learning_rate": 1.1125098730383745e-05,
      "loss": 0.5546,
      "step": 30271
    },
    {
      "epoch": 0.9299296531809664,
      "grad_norm": 0.4097563922405243,
      "learning_rate": 1.1124618520251383e-05,
      "loss": 0.5936,
      "step": 30272
    },
    {
      "epoch": 0.9299603723159156,
      "grad_norm": 0.3510383069515228,
      "learning_rate": 1.1124138307492397e-05,
      "loss": 0.5386,
      "step": 30273
    },
    {
      "epoch": 0.9299910914508648,
      "grad_norm": 0.3902590870857239,
      "learning_rate": 1.1123658092107908e-05,
      "loss": 0.6001,
      "step": 30274
    },
    {
      "epoch": 0.9300218105858139,
      "grad_norm": 0.3971397876739502,
      "learning_rate": 1.1123177874099036e-05,
      "loss": 0.4856,
      "step": 30275
    },
    {
      "epoch": 0.930052529720763,
      "grad_norm": 0.36651384830474854,
      "learning_rate": 1.1122697653466902e-05,
      "loss": 0.5393,
      "step": 30276
    },
    {
      "epoch": 0.9300832488557123,
      "grad_norm": 0.3709697425365448,
      "learning_rate": 1.1122217430212635e-05,
      "loss": 0.5203,
      "step": 30277
    },
    {
      "epoch": 0.9301139679906614,
      "grad_norm": 0.35187020897865295,
      "learning_rate": 1.1121737204337344e-05,
      "loss": 0.568,
      "step": 30278
    },
    {
      "epoch": 0.9301446871256105,
      "grad_norm": 0.35930103063583374,
      "learning_rate": 1.112125697584216e-05,
      "loss": 0.5387,
      "step": 30279
    },
    {
      "epoch": 0.9301754062605597,
      "grad_norm": 0.35704857110977173,
      "learning_rate": 1.1120776744728203e-05,
      "loss": 0.5125,
      "step": 30280
    },
    {
      "epoch": 0.9302061253955088,
      "grad_norm": 0.357063353061676,
      "learning_rate": 1.1120296510996593e-05,
      "loss": 0.5889,
      "step": 30281
    },
    {
      "epoch": 0.9302368445304581,
      "grad_norm": 0.37344467639923096,
      "learning_rate": 1.1119816274648455e-05,
      "loss": 0.4615,
      "step": 30282
    },
    {
      "epoch": 0.9302675636654072,
      "grad_norm": 0.37770646810531616,
      "learning_rate": 1.1119336035684902e-05,
      "loss": 0.5589,
      "step": 30283
    },
    {
      "epoch": 0.9302982828003563,
      "grad_norm": 0.3569287359714508,
      "learning_rate": 1.1118855794107066e-05,
      "loss": 0.5541,
      "step": 30284
    },
    {
      "epoch": 0.9303290019353055,
      "grad_norm": 0.3535950183868408,
      "learning_rate": 1.1118375549916063e-05,
      "loss": 0.5607,
      "step": 30285
    },
    {
      "epoch": 0.9303597210702547,
      "grad_norm": 0.3312683403491974,
      "learning_rate": 1.1117895303113016e-05,
      "loss": 0.4824,
      "step": 30286
    },
    {
      "epoch": 0.9303904402052038,
      "grad_norm": 0.40768083930015564,
      "learning_rate": 1.1117415053699047e-05,
      "loss": 0.5158,
      "step": 30287
    },
    {
      "epoch": 0.930421159340153,
      "grad_norm": 0.38447415828704834,
      "learning_rate": 1.1116934801675276e-05,
      "loss": 0.4889,
      "step": 30288
    },
    {
      "epoch": 0.9304518784751021,
      "grad_norm": 0.6174691319465637,
      "learning_rate": 1.1116454547042827e-05,
      "loss": 0.562,
      "step": 30289
    },
    {
      "epoch": 0.9304825976100513,
      "grad_norm": 0.3826034367084503,
      "learning_rate": 1.1115974289802818e-05,
      "loss": 0.5107,
      "step": 30290
    },
    {
      "epoch": 0.9305133167450005,
      "grad_norm": 0.3630359470844269,
      "learning_rate": 1.1115494029956375e-05,
      "loss": 0.5957,
      "step": 30291
    },
    {
      "epoch": 0.9305440358799496,
      "grad_norm": 0.3385410010814667,
      "learning_rate": 1.1115013767504617e-05,
      "loss": 0.5497,
      "step": 30292
    },
    {
      "epoch": 0.9305747550148988,
      "grad_norm": 0.35418665409088135,
      "learning_rate": 1.1114533502448667e-05,
      "loss": 0.5506,
      "step": 30293
    },
    {
      "epoch": 0.930605474149848,
      "grad_norm": 0.371004581451416,
      "learning_rate": 1.1114053234789646e-05,
      "loss": 0.5403,
      "step": 30294
    },
    {
      "epoch": 0.9306361932847971,
      "grad_norm": 0.3869469165802002,
      "learning_rate": 1.1113572964528679e-05,
      "loss": 0.5794,
      "step": 30295
    },
    {
      "epoch": 0.9306669124197463,
      "grad_norm": 0.37821313738822937,
      "learning_rate": 1.1113092691666878e-05,
      "loss": 0.5001,
      "step": 30296
    },
    {
      "epoch": 0.9306976315546954,
      "grad_norm": 0.539116382598877,
      "learning_rate": 1.1112612416205375e-05,
      "loss": 0.5189,
      "step": 30297
    },
    {
      "epoch": 0.9307283506896445,
      "grad_norm": 0.5251274108886719,
      "learning_rate": 1.111213213814529e-05,
      "loss": 0.4727,
      "step": 30298
    },
    {
      "epoch": 0.9307590698245938,
      "grad_norm": 0.832741379737854,
      "learning_rate": 1.1111651857487738e-05,
      "loss": 0.5494,
      "step": 30299
    },
    {
      "epoch": 0.9307897889595429,
      "grad_norm": 0.34394291043281555,
      "learning_rate": 1.1111171574233847e-05,
      "loss": 0.5243,
      "step": 30300
    },
    {
      "epoch": 0.930820508094492,
      "grad_norm": 0.39309871196746826,
      "learning_rate": 1.111069128838474e-05,
      "loss": 0.4977,
      "step": 30301
    },
    {
      "epoch": 0.9308512272294412,
      "grad_norm": 0.39742332696914673,
      "learning_rate": 1.1110210999941534e-05,
      "loss": 0.4866,
      "step": 30302
    },
    {
      "epoch": 0.9308819463643904,
      "grad_norm": 0.36647337675094604,
      "learning_rate": 1.110973070890535e-05,
      "loss": 0.5625,
      "step": 30303
    },
    {
      "epoch": 0.9309126654993395,
      "grad_norm": 0.4457987844944,
      "learning_rate": 1.1109250415277317e-05,
      "loss": 0.5083,
      "step": 30304
    },
    {
      "epoch": 0.9309433846342887,
      "grad_norm": 0.3755800724029541,
      "learning_rate": 1.1108770119058552e-05,
      "loss": 0.6149,
      "step": 30305
    },
    {
      "epoch": 0.9309741037692378,
      "grad_norm": 0.41726958751678467,
      "learning_rate": 1.1108289820250174e-05,
      "loss": 0.5807,
      "step": 30306
    },
    {
      "epoch": 0.9310048229041871,
      "grad_norm": 0.4208855926990509,
      "learning_rate": 1.110780951885331e-05,
      "loss": 0.5282,
      "step": 30307
    },
    {
      "epoch": 0.9310355420391362,
      "grad_norm": 0.3998314142227173,
      "learning_rate": 1.1107329214869078e-05,
      "loss": 0.67,
      "step": 30308
    },
    {
      "epoch": 0.9310662611740853,
      "grad_norm": 0.39345234632492065,
      "learning_rate": 1.1106848908298601e-05,
      "loss": 0.5297,
      "step": 30309
    },
    {
      "epoch": 0.9310969803090345,
      "grad_norm": 0.5335297584533691,
      "learning_rate": 1.1106368599143002e-05,
      "loss": 0.5184,
      "step": 30310
    },
    {
      "epoch": 0.9311276994439837,
      "grad_norm": 0.4061771333217621,
      "learning_rate": 1.1105888287403404e-05,
      "loss": 0.5525,
      "step": 30311
    },
    {
      "epoch": 0.9311584185789328,
      "grad_norm": 0.38005882501602173,
      "learning_rate": 1.1105407973080921e-05,
      "loss": 0.5803,
      "step": 30312
    },
    {
      "epoch": 0.931189137713882,
      "grad_norm": 0.5651965737342834,
      "learning_rate": 1.1104927656176687e-05,
      "loss": 0.5456,
      "step": 30313
    },
    {
      "epoch": 0.9312198568488311,
      "grad_norm": 0.3830072283744812,
      "learning_rate": 1.1104447336691812e-05,
      "loss": 0.5991,
      "step": 30314
    },
    {
      "epoch": 0.9312505759837802,
      "grad_norm": 0.3461000323295593,
      "learning_rate": 1.1103967014627424e-05,
      "loss": 0.4919,
      "step": 30315
    },
    {
      "epoch": 0.9312812951187295,
      "grad_norm": 0.3364415466785431,
      "learning_rate": 1.1103486689984646e-05,
      "loss": 0.5092,
      "step": 30316
    },
    {
      "epoch": 0.9313120142536786,
      "grad_norm": 0.3605083227157593,
      "learning_rate": 1.1103006362764597e-05,
      "loss": 0.5148,
      "step": 30317
    },
    {
      "epoch": 0.9313427333886278,
      "grad_norm": 0.3487533926963806,
      "learning_rate": 1.1102526032968401e-05,
      "loss": 0.5759,
      "step": 30318
    },
    {
      "epoch": 0.931373452523577,
      "grad_norm": 0.3756280839443207,
      "learning_rate": 1.1102045700597174e-05,
      "loss": 0.4824,
      "step": 30319
    },
    {
      "epoch": 0.9314041716585261,
      "grad_norm": 0.8592475652694702,
      "learning_rate": 1.1101565365652048e-05,
      "loss": 0.5309,
      "step": 30320
    },
    {
      "epoch": 0.9314348907934753,
      "grad_norm": 0.35884276032447815,
      "learning_rate": 1.1101085028134135e-05,
      "loss": 0.5203,
      "step": 30321
    },
    {
      "epoch": 0.9314656099284244,
      "grad_norm": 0.3769422471523285,
      "learning_rate": 1.1100604688044563e-05,
      "loss": 0.5983,
      "step": 30322
    },
    {
      "epoch": 0.9314963290633735,
      "grad_norm": 0.3817802965641022,
      "learning_rate": 1.1100124345384453e-05,
      "loss": 0.5807,
      "step": 30323
    },
    {
      "epoch": 0.9315270481983228,
      "grad_norm": 0.38562169671058655,
      "learning_rate": 1.1099644000154924e-05,
      "loss": 0.5542,
      "step": 30324
    },
    {
      "epoch": 0.9315577673332719,
      "grad_norm": 0.3510757088661194,
      "learning_rate": 1.1099163652357101e-05,
      "loss": 0.5876,
      "step": 30325
    },
    {
      "epoch": 0.931588486468221,
      "grad_norm": 0.39286163449287415,
      "learning_rate": 1.1098683301992102e-05,
      "loss": 0.6194,
      "step": 30326
    },
    {
      "epoch": 0.9316192056031702,
      "grad_norm": 0.3503819406032562,
      "learning_rate": 1.1098202949061054e-05,
      "loss": 0.5615,
      "step": 30327
    },
    {
      "epoch": 0.9316499247381194,
      "grad_norm": 0.3372073471546173,
      "learning_rate": 1.1097722593565072e-05,
      "loss": 0.515,
      "step": 30328
    },
    {
      "epoch": 0.9316806438730685,
      "grad_norm": 0.36622095108032227,
      "learning_rate": 1.1097242235505288e-05,
      "loss": 0.5506,
      "step": 30329
    },
    {
      "epoch": 0.9317113630080177,
      "grad_norm": 0.40187743306159973,
      "learning_rate": 1.1096761874882813e-05,
      "loss": 0.6105,
      "step": 30330
    },
    {
      "epoch": 0.9317420821429668,
      "grad_norm": 0.4083707928657532,
      "learning_rate": 1.1096281511698779e-05,
      "loss": 0.5528,
      "step": 30331
    },
    {
      "epoch": 0.9317728012779161,
      "grad_norm": 0.44303038716316223,
      "learning_rate": 1.10958011459543e-05,
      "loss": 0.5413,
      "step": 30332
    },
    {
      "epoch": 0.9318035204128652,
      "grad_norm": 0.35881274938583374,
      "learning_rate": 1.1095320777650498e-05,
      "loss": 0.5682,
      "step": 30333
    },
    {
      "epoch": 0.9318342395478143,
      "grad_norm": 0.5636556148529053,
      "learning_rate": 1.1094840406788503e-05,
      "loss": 0.6506,
      "step": 30334
    },
    {
      "epoch": 0.9318649586827635,
      "grad_norm": 0.38395124673843384,
      "learning_rate": 1.109436003336943e-05,
      "loss": 0.6242,
      "step": 30335
    },
    {
      "epoch": 0.9318956778177127,
      "grad_norm": 0.3429311215877533,
      "learning_rate": 1.1093879657394401e-05,
      "loss": 0.544,
      "step": 30336
    },
    {
      "epoch": 0.9319263969526618,
      "grad_norm": 0.34896957874298096,
      "learning_rate": 1.1093399278864542e-05,
      "loss": 0.6278,
      "step": 30337
    },
    {
      "epoch": 0.931957116087611,
      "grad_norm": 0.3332914710044861,
      "learning_rate": 1.1092918897780972e-05,
      "loss": 0.5157,
      "step": 30338
    },
    {
      "epoch": 0.9319878352225601,
      "grad_norm": 0.37697938084602356,
      "learning_rate": 1.1092438514144814e-05,
      "loss": 0.5447,
      "step": 30339
    },
    {
      "epoch": 0.9320185543575092,
      "grad_norm": 0.3488859236240387,
      "learning_rate": 1.109195812795719e-05,
      "loss": 0.5722,
      "step": 30340
    },
    {
      "epoch": 0.9320492734924585,
      "grad_norm": 0.3985539376735687,
      "learning_rate": 1.109147773921922e-05,
      "loss": 0.5252,
      "step": 30341
    },
    {
      "epoch": 0.9320799926274076,
      "grad_norm": 0.3363508880138397,
      "learning_rate": 1.1090997347932028e-05,
      "loss": 0.5824,
      "step": 30342
    },
    {
      "epoch": 0.9321107117623568,
      "grad_norm": 0.37577423453330994,
      "learning_rate": 1.1090516954096736e-05,
      "loss": 0.5989,
      "step": 30343
    },
    {
      "epoch": 0.932141430897306,
      "grad_norm": 0.47941818833351135,
      "learning_rate": 1.1090036557714466e-05,
      "loss": 0.4084,
      "step": 30344
    },
    {
      "epoch": 0.9321721500322551,
      "grad_norm": 0.43231022357940674,
      "learning_rate": 1.1089556158786339e-05,
      "loss": 0.5275,
      "step": 30345
    },
    {
      "epoch": 0.9322028691672043,
      "grad_norm": 0.3653135597705841,
      "learning_rate": 1.1089075757313474e-05,
      "loss": 0.5319,
      "step": 30346
    },
    {
      "epoch": 0.9322335883021534,
      "grad_norm": 0.3376675546169281,
      "learning_rate": 1.1088595353297002e-05,
      "loss": 0.5,
      "step": 30347
    },
    {
      "epoch": 0.9322643074371025,
      "grad_norm": 0.34869813919067383,
      "learning_rate": 1.1088114946738035e-05,
      "loss": 0.5214,
      "step": 30348
    },
    {
      "epoch": 0.9322950265720518,
      "grad_norm": 0.3511779308319092,
      "learning_rate": 1.1087634537637704e-05,
      "loss": 0.5232,
      "step": 30349
    },
    {
      "epoch": 0.9323257457070009,
      "grad_norm": 0.37601909041404724,
      "learning_rate": 1.1087154125997124e-05,
      "loss": 0.5251,
      "step": 30350
    },
    {
      "epoch": 0.93235646484195,
      "grad_norm": 0.39936646819114685,
      "learning_rate": 1.1086673711817417e-05,
      "loss": 0.5758,
      "step": 30351
    },
    {
      "epoch": 0.9323871839768992,
      "grad_norm": 0.3818790912628174,
      "learning_rate": 1.1086193295099712e-05,
      "loss": 0.57,
      "step": 30352
    },
    {
      "epoch": 0.9324179031118484,
      "grad_norm": 0.35319772362709045,
      "learning_rate": 1.1085712875845124e-05,
      "loss": 0.6077,
      "step": 30353
    },
    {
      "epoch": 0.9324486222467975,
      "grad_norm": 0.37438344955444336,
      "learning_rate": 1.1085232454054779e-05,
      "loss": 0.5357,
      "step": 30354
    },
    {
      "epoch": 0.9324793413817467,
      "grad_norm": 0.37220096588134766,
      "learning_rate": 1.1084752029729797e-05,
      "loss": 0.4531,
      "step": 30355
    },
    {
      "epoch": 0.9325100605166958,
      "grad_norm": 0.4069632291793823,
      "learning_rate": 1.1084271602871303e-05,
      "loss": 0.5223,
      "step": 30356
    },
    {
      "epoch": 0.9325407796516451,
      "grad_norm": 0.3822646737098694,
      "learning_rate": 1.1083791173480419e-05,
      "loss": 0.5588,
      "step": 30357
    },
    {
      "epoch": 0.9325714987865942,
      "grad_norm": 0.3690261244773865,
      "learning_rate": 1.108331074155826e-05,
      "loss": 0.5791,
      "step": 30358
    },
    {
      "epoch": 0.9326022179215433,
      "grad_norm": 0.37075576186180115,
      "learning_rate": 1.1082830307105954e-05,
      "loss": 0.5407,
      "step": 30359
    },
    {
      "epoch": 0.9326329370564925,
      "grad_norm": 0.3640204966068268,
      "learning_rate": 1.1082349870124622e-05,
      "loss": 0.5901,
      "step": 30360
    },
    {
      "epoch": 0.9326636561914416,
      "grad_norm": 0.35000869631767273,
      "learning_rate": 1.1081869430615389e-05,
      "loss": 0.4996,
      "step": 30361
    },
    {
      "epoch": 0.9326943753263908,
      "grad_norm": 0.34881195425987244,
      "learning_rate": 1.1081388988579372e-05,
      "loss": 0.5556,
      "step": 30362
    },
    {
      "epoch": 0.93272509446134,
      "grad_norm": 0.37116649746894836,
      "learning_rate": 1.1080908544017696e-05,
      "loss": 0.6141,
      "step": 30363
    },
    {
      "epoch": 0.9327558135962891,
      "grad_norm": 0.3539467751979828,
      "learning_rate": 1.1080428096931482e-05,
      "loss": 0.5615,
      "step": 30364
    },
    {
      "epoch": 0.9327865327312382,
      "grad_norm": 0.40236207842826843,
      "learning_rate": 1.1079947647321854e-05,
      "loss": 0.5997,
      "step": 30365
    },
    {
      "epoch": 0.9328172518661875,
      "grad_norm": 0.40072304010391235,
      "learning_rate": 1.1079467195189933e-05,
      "loss": 0.5476,
      "step": 30366
    },
    {
      "epoch": 0.9328479710011366,
      "grad_norm": 0.33370593190193176,
      "learning_rate": 1.1078986740536838e-05,
      "loss": 0.5105,
      "step": 30367
    },
    {
      "epoch": 0.9328786901360858,
      "grad_norm": 0.42500945925712585,
      "learning_rate": 1.1078506283363699e-05,
      "loss": 0.5092,
      "step": 30368
    },
    {
      "epoch": 0.9329094092710349,
      "grad_norm": 1.5651564598083496,
      "learning_rate": 1.1078025823671627e-05,
      "loss": 0.525,
      "step": 30369
    },
    {
      "epoch": 0.9329401284059841,
      "grad_norm": 0.3538157045841217,
      "learning_rate": 1.1077545361461754e-05,
      "loss": 0.5467,
      "step": 30370
    },
    {
      "epoch": 0.9329708475409333,
      "grad_norm": 0.3625772297382355,
      "learning_rate": 1.1077064896735198e-05,
      "loss": 0.5738,
      "step": 30371
    },
    {
      "epoch": 0.9330015666758824,
      "grad_norm": 0.3862822353839874,
      "learning_rate": 1.1076584429493085e-05,
      "loss": 0.5228,
      "step": 30372
    },
    {
      "epoch": 0.9330322858108315,
      "grad_norm": 0.33536428213119507,
      "learning_rate": 1.1076103959736528e-05,
      "loss": 0.5485,
      "step": 30373
    },
    {
      "epoch": 0.9330630049457808,
      "grad_norm": 0.36813119053840637,
      "learning_rate": 1.107562348746666e-05,
      "loss": 0.4551,
      "step": 30374
    },
    {
      "epoch": 0.9330937240807299,
      "grad_norm": 0.41439634561538696,
      "learning_rate": 1.1075143012684597e-05,
      "loss": 0.5269,
      "step": 30375
    },
    {
      "epoch": 0.933124443215679,
      "grad_norm": 0.3621596693992615,
      "learning_rate": 1.1074662535391462e-05,
      "loss": 0.467,
      "step": 30376
    },
    {
      "epoch": 0.9331551623506282,
      "grad_norm": 0.7658784985542297,
      "learning_rate": 1.107418205558838e-05,
      "loss": 0.5768,
      "step": 30377
    },
    {
      "epoch": 0.9331858814855774,
      "grad_norm": 0.38123631477355957,
      "learning_rate": 1.1073701573276466e-05,
      "loss": 0.5695,
      "step": 30378
    },
    {
      "epoch": 0.9332166006205265,
      "grad_norm": 0.4125577509403229,
      "learning_rate": 1.1073221088456848e-05,
      "loss": 0.6159,
      "step": 30379
    },
    {
      "epoch": 0.9332473197554757,
      "grad_norm": 0.40151122212409973,
      "learning_rate": 1.1072740601130649e-05,
      "loss": 0.5936,
      "step": 30380
    },
    {
      "epoch": 0.9332780388904248,
      "grad_norm": 0.33082494139671326,
      "learning_rate": 1.1072260111298989e-05,
      "loss": 0.5551,
      "step": 30381
    },
    {
      "epoch": 0.933308758025374,
      "grad_norm": 0.41849684715270996,
      "learning_rate": 1.107177961896299e-05,
      "loss": 0.4983,
      "step": 30382
    },
    {
      "epoch": 0.9333394771603232,
      "grad_norm": 0.38790836930274963,
      "learning_rate": 1.1071299124123777e-05,
      "loss": 0.5225,
      "step": 30383
    },
    {
      "epoch": 0.9333701962952723,
      "grad_norm": 0.3678896129131317,
      "learning_rate": 1.1070818626782467e-05,
      "loss": 0.5683,
      "step": 30384
    },
    {
      "epoch": 0.9334009154302215,
      "grad_norm": 0.34562885761260986,
      "learning_rate": 1.1070338126940188e-05,
      "loss": 0.5088,
      "step": 30385
    },
    {
      "epoch": 0.9334316345651706,
      "grad_norm": 0.3572862148284912,
      "learning_rate": 1.106985762459806e-05,
      "loss": 0.5565,
      "step": 30386
    },
    {
      "epoch": 0.9334623537001198,
      "grad_norm": 0.5405210256576538,
      "learning_rate": 1.1069377119757199e-05,
      "loss": 0.5807,
      "step": 30387
    },
    {
      "epoch": 0.933493072835069,
      "grad_norm": 0.3750610947608948,
      "learning_rate": 1.1068896612418738e-05,
      "loss": 0.6382,
      "step": 30388
    },
    {
      "epoch": 0.9335237919700181,
      "grad_norm": 0.3921282887458801,
      "learning_rate": 1.1068416102583792e-05,
      "loss": 0.4999,
      "step": 30389
    },
    {
      "epoch": 0.9335545111049672,
      "grad_norm": 0.4546433687210083,
      "learning_rate": 1.1067935590253488e-05,
      "loss": 0.5867,
      "step": 30390
    },
    {
      "epoch": 0.9335852302399165,
      "grad_norm": 0.3721960186958313,
      "learning_rate": 1.1067455075428944e-05,
      "loss": 0.5662,
      "step": 30391
    },
    {
      "epoch": 0.9336159493748656,
      "grad_norm": 0.36129632592201233,
      "learning_rate": 1.1066974558111286e-05,
      "loss": 0.5461,
      "step": 30392
    },
    {
      "epoch": 0.9336466685098148,
      "grad_norm": 0.3666982054710388,
      "learning_rate": 1.1066494038301634e-05,
      "loss": 0.5909,
      "step": 30393
    },
    {
      "epoch": 0.9336773876447639,
      "grad_norm": 0.37953704595565796,
      "learning_rate": 1.1066013516001109e-05,
      "loss": 0.5915,
      "step": 30394
    },
    {
      "epoch": 0.933708106779713,
      "grad_norm": 0.4282543361186981,
      "learning_rate": 1.1065532991210837e-05,
      "loss": 0.5552,
      "step": 30395
    },
    {
      "epoch": 0.9337388259146623,
      "grad_norm": 0.3558879494667053,
      "learning_rate": 1.1065052463931936e-05,
      "loss": 0.6569,
      "step": 30396
    },
    {
      "epoch": 0.9337695450496114,
      "grad_norm": 0.5090029835700989,
      "learning_rate": 1.1064571934165534e-05,
      "loss": 0.4801,
      "step": 30397
    },
    {
      "epoch": 0.9338002641845605,
      "grad_norm": 0.3559035360813141,
      "learning_rate": 1.1064091401912746e-05,
      "loss": 0.4851,
      "step": 30398
    },
    {
      "epoch": 0.9338309833195098,
      "grad_norm": 0.3810226321220398,
      "learning_rate": 1.10636108671747e-05,
      "loss": 0.5287,
      "step": 30399
    },
    {
      "epoch": 0.9338617024544589,
      "grad_norm": 0.3929925858974457,
      "learning_rate": 1.1063130329952516e-05,
      "loss": 0.492,
      "step": 30400
    },
    {
      "epoch": 0.933892421589408,
      "grad_norm": 0.37412703037261963,
      "learning_rate": 1.106264979024732e-05,
      "loss": 0.5285,
      "step": 30401
    },
    {
      "epoch": 0.9339231407243572,
      "grad_norm": 0.40237346291542053,
      "learning_rate": 1.1062169248060227e-05,
      "loss": 0.5307,
      "step": 30402
    },
    {
      "epoch": 0.9339538598593063,
      "grad_norm": 0.42197373509407043,
      "learning_rate": 1.1061688703392367e-05,
      "loss": 0.551,
      "step": 30403
    },
    {
      "epoch": 0.9339845789942556,
      "grad_norm": 0.4056549072265625,
      "learning_rate": 1.1061208156244856e-05,
      "loss": 0.5296,
      "step": 30404
    },
    {
      "epoch": 0.9340152981292047,
      "grad_norm": 0.4414810240268707,
      "learning_rate": 1.1060727606618818e-05,
      "loss": 0.4717,
      "step": 30405
    },
    {
      "epoch": 0.9340460172641538,
      "grad_norm": 0.3619079291820526,
      "learning_rate": 1.1060247054515379e-05,
      "loss": 0.5343,
      "step": 30406
    },
    {
      "epoch": 0.934076736399103,
      "grad_norm": 0.3521060049533844,
      "learning_rate": 1.1059766499935658e-05,
      "loss": 0.5257,
      "step": 30407
    },
    {
      "epoch": 0.9341074555340522,
      "grad_norm": 0.36023157835006714,
      "learning_rate": 1.105928594288078e-05,
      "loss": 0.4708,
      "step": 30408
    },
    {
      "epoch": 0.9341381746690013,
      "grad_norm": 0.5210719108581543,
      "learning_rate": 1.1058805383351867e-05,
      "loss": 0.5893,
      "step": 30409
    },
    {
      "epoch": 0.9341688938039505,
      "grad_norm": 0.38019904494285583,
      "learning_rate": 1.1058324821350035e-05,
      "loss": 0.5886,
      "step": 30410
    },
    {
      "epoch": 0.9341996129388996,
      "grad_norm": 0.3812773525714874,
      "learning_rate": 1.1057844256876416e-05,
      "loss": 0.5106,
      "step": 30411
    },
    {
      "epoch": 0.9342303320738488,
      "grad_norm": 0.3476789891719818,
      "learning_rate": 1.1057363689932126e-05,
      "loss": 0.5209,
      "step": 30412
    },
    {
      "epoch": 0.934261051208798,
      "grad_norm": 0.3741928040981293,
      "learning_rate": 1.105688312051829e-05,
      "loss": 0.5542,
      "step": 30413
    },
    {
      "epoch": 0.9342917703437471,
      "grad_norm": 0.34308159351348877,
      "learning_rate": 1.1056402548636027e-05,
      "loss": 0.5173,
      "step": 30414
    },
    {
      "epoch": 0.9343224894786962,
      "grad_norm": 0.38292208313941956,
      "learning_rate": 1.1055921974286465e-05,
      "loss": 0.5474,
      "step": 30415
    },
    {
      "epoch": 0.9343532086136455,
      "grad_norm": 0.4737255871295929,
      "learning_rate": 1.1055441397470724e-05,
      "loss": 0.5287,
      "step": 30416
    },
    {
      "epoch": 0.9343839277485946,
      "grad_norm": 0.38519009947776794,
      "learning_rate": 1.1054960818189924e-05,
      "loss": 0.6544,
      "step": 30417
    },
    {
      "epoch": 0.9344146468835438,
      "grad_norm": 0.36267155408859253,
      "learning_rate": 1.105448023644519e-05,
      "loss": 0.4885,
      "step": 30418
    },
    {
      "epoch": 0.9344453660184929,
      "grad_norm": 0.3529633581638336,
      "learning_rate": 1.1053999652237643e-05,
      "loss": 0.4649,
      "step": 30419
    },
    {
      "epoch": 0.934476085153442,
      "grad_norm": 0.42582646012306213,
      "learning_rate": 1.105351906556841e-05,
      "loss": 0.5379,
      "step": 30420
    },
    {
      "epoch": 0.9345068042883913,
      "grad_norm": 0.3851524591445923,
      "learning_rate": 1.1053038476438604e-05,
      "loss": 0.5039,
      "step": 30421
    },
    {
      "epoch": 0.9345375234233404,
      "grad_norm": 0.5443708896636963,
      "learning_rate": 1.1052557884849357e-05,
      "loss": 0.5273,
      "step": 30422
    },
    {
      "epoch": 0.9345682425582895,
      "grad_norm": 0.3715219795703888,
      "learning_rate": 1.1052077290801785e-05,
      "loss": 0.543,
      "step": 30423
    },
    {
      "epoch": 0.9345989616932388,
      "grad_norm": 0.38686370849609375,
      "learning_rate": 1.1051596694297013e-05,
      "loss": 0.4744,
      "step": 30424
    },
    {
      "epoch": 0.9346296808281879,
      "grad_norm": 0.37719622254371643,
      "learning_rate": 1.1051116095336166e-05,
      "loss": 0.6243,
      "step": 30425
    },
    {
      "epoch": 0.934660399963137,
      "grad_norm": 0.3858301043510437,
      "learning_rate": 1.1050635493920363e-05,
      "loss": 0.5325,
      "step": 30426
    },
    {
      "epoch": 0.9346911190980862,
      "grad_norm": 0.4668706953525543,
      "learning_rate": 1.1050154890050729e-05,
      "loss": 0.5497,
      "step": 30427
    },
    {
      "epoch": 0.9347218382330353,
      "grad_norm": 0.3703922927379608,
      "learning_rate": 1.1049674283728379e-05,
      "loss": 0.5355,
      "step": 30428
    },
    {
      "epoch": 0.9347525573679846,
      "grad_norm": 0.4908474385738373,
      "learning_rate": 1.1049193674954448e-05,
      "loss": 0.5374,
      "step": 30429
    },
    {
      "epoch": 0.9347832765029337,
      "grad_norm": 0.42486608028411865,
      "learning_rate": 1.1048713063730048e-05,
      "loss": 0.5526,
      "step": 30430
    },
    {
      "epoch": 0.9348139956378828,
      "grad_norm": 0.44306185841560364,
      "learning_rate": 1.1048232450056306e-05,
      "loss": 0.598,
      "step": 30431
    },
    {
      "epoch": 0.934844714772832,
      "grad_norm": 0.37743595242500305,
      "learning_rate": 1.1047751833934344e-05,
      "loss": 0.6303,
      "step": 30432
    },
    {
      "epoch": 0.9348754339077812,
      "grad_norm": 0.3774903118610382,
      "learning_rate": 1.1047271215365287e-05,
      "loss": 0.4842,
      "step": 30433
    },
    {
      "epoch": 0.9349061530427303,
      "grad_norm": 0.33440661430358887,
      "learning_rate": 1.1046790594350253e-05,
      "loss": 0.5463,
      "step": 30434
    },
    {
      "epoch": 0.9349368721776795,
      "grad_norm": 0.38640710711479187,
      "learning_rate": 1.1046309970890365e-05,
      "loss": 0.5513,
      "step": 30435
    },
    {
      "epoch": 0.9349675913126286,
      "grad_norm": 0.388054758310318,
      "learning_rate": 1.104582934498675e-05,
      "loss": 0.4894,
      "step": 30436
    },
    {
      "epoch": 0.9349983104475778,
      "grad_norm": 0.3746173083782196,
      "learning_rate": 1.1045348716640525e-05,
      "loss": 0.5463,
      "step": 30437
    },
    {
      "epoch": 0.935029029582527,
      "grad_norm": 0.3446078598499298,
      "learning_rate": 1.1044868085852817e-05,
      "loss": 0.5037,
      "step": 30438
    },
    {
      "epoch": 0.9350597487174761,
      "grad_norm": 0.3576319217681885,
      "learning_rate": 1.1044387452624746e-05,
      "loss": 0.5738,
      "step": 30439
    },
    {
      "epoch": 0.9350904678524252,
      "grad_norm": 0.34665703773498535,
      "learning_rate": 1.1043906816957436e-05,
      "loss": 0.5015,
      "step": 30440
    },
    {
      "epoch": 0.9351211869873745,
      "grad_norm": 0.399756520986557,
      "learning_rate": 1.1043426178852006e-05,
      "loss": 0.5621,
      "step": 30441
    },
    {
      "epoch": 0.9351519061223236,
      "grad_norm": 0.4014807641506195,
      "learning_rate": 1.1042945538309582e-05,
      "loss": 0.5959,
      "step": 30442
    },
    {
      "epoch": 0.9351826252572728,
      "grad_norm": 0.3342481851577759,
      "learning_rate": 1.1042464895331284e-05,
      "loss": 0.5775,
      "step": 30443
    },
    {
      "epoch": 0.9352133443922219,
      "grad_norm": 0.3667951226234436,
      "learning_rate": 1.104198424991824e-05,
      "loss": 0.5725,
      "step": 30444
    },
    {
      "epoch": 0.935244063527171,
      "grad_norm": 0.31376245617866516,
      "learning_rate": 1.104150360207157e-05,
      "loss": 0.5161,
      "step": 30445
    },
    {
      "epoch": 0.9352747826621203,
      "grad_norm": 0.36095085740089417,
      "learning_rate": 1.1041022951792393e-05,
      "loss": 0.485,
      "step": 30446
    },
    {
      "epoch": 0.9353055017970694,
      "grad_norm": 0.40169069170951843,
      "learning_rate": 1.1040542299081835e-05,
      "loss": 0.5982,
      "step": 30447
    },
    {
      "epoch": 0.9353362209320185,
      "grad_norm": 0.337018221616745,
      "learning_rate": 1.1040061643941016e-05,
      "loss": 0.4876,
      "step": 30448
    },
    {
      "epoch": 0.9353669400669677,
      "grad_norm": 0.3413563668727875,
      "learning_rate": 1.1039580986371064e-05,
      "loss": 0.4244,
      "step": 30449
    },
    {
      "epoch": 0.9353976592019169,
      "grad_norm": 0.37029215693473816,
      "learning_rate": 1.1039100326373095e-05,
      "loss": 0.5634,
      "step": 30450
    },
    {
      "epoch": 0.935428378336866,
      "grad_norm": 0.3702857494354248,
      "learning_rate": 1.1038619663948236e-05,
      "loss": 0.4873,
      "step": 30451
    },
    {
      "epoch": 0.9354590974718152,
      "grad_norm": 0.3662261366844177,
      "learning_rate": 1.1038138999097607e-05,
      "loss": 0.4875,
      "step": 30452
    },
    {
      "epoch": 0.9354898166067643,
      "grad_norm": 0.38516971468925476,
      "learning_rate": 1.1037658331822334e-05,
      "loss": 0.573,
      "step": 30453
    },
    {
      "epoch": 0.9355205357417136,
      "grad_norm": 0.3602786660194397,
      "learning_rate": 1.1037177662123534e-05,
      "loss": 0.4715,
      "step": 30454
    },
    {
      "epoch": 0.9355512548766627,
      "grad_norm": 0.45929694175720215,
      "learning_rate": 1.1036696990002339e-05,
      "loss": 0.5863,
      "step": 30455
    },
    {
      "epoch": 0.9355819740116118,
      "grad_norm": 0.3505461812019348,
      "learning_rate": 1.1036216315459862e-05,
      "loss": 0.474,
      "step": 30456
    },
    {
      "epoch": 0.935612693146561,
      "grad_norm": 0.392701655626297,
      "learning_rate": 1.103573563849723e-05,
      "loss": 0.5313,
      "step": 30457
    },
    {
      "epoch": 0.9356434122815102,
      "grad_norm": 0.8423426747322083,
      "learning_rate": 1.1035254959115564e-05,
      "loss": 0.5123,
      "step": 30458
    },
    {
      "epoch": 0.9356741314164593,
      "grad_norm": 0.3674393594264984,
      "learning_rate": 1.1034774277315987e-05,
      "loss": 0.4749,
      "step": 30459
    },
    {
      "epoch": 0.9357048505514085,
      "grad_norm": 0.3928945064544678,
      "learning_rate": 1.1034293593099623e-05,
      "loss": 0.4661,
      "step": 30460
    },
    {
      "epoch": 0.9357355696863576,
      "grad_norm": 0.3649788200855255,
      "learning_rate": 1.1033812906467596e-05,
      "loss": 0.4968,
      "step": 30461
    },
    {
      "epoch": 0.9357662888213067,
      "grad_norm": 0.39478060603141785,
      "learning_rate": 1.1033332217421024e-05,
      "loss": 0.5613,
      "step": 30462
    },
    {
      "epoch": 0.935797007956256,
      "grad_norm": 0.3862840533256531,
      "learning_rate": 1.1032851525961034e-05,
      "loss": 0.4998,
      "step": 30463
    },
    {
      "epoch": 0.9358277270912051,
      "grad_norm": 0.4269610047340393,
      "learning_rate": 1.1032370832088748e-05,
      "loss": 0.5287,
      "step": 30464
    },
    {
      "epoch": 0.9358584462261542,
      "grad_norm": 0.3816654086112976,
      "learning_rate": 1.1031890135805288e-05,
      "loss": 0.5941,
      "step": 30465
    },
    {
      "epoch": 0.9358891653611034,
      "grad_norm": 0.35906827449798584,
      "learning_rate": 1.1031409437111775e-05,
      "loss": 0.5733,
      "step": 30466
    },
    {
      "epoch": 0.9359198844960526,
      "grad_norm": 0.35455194115638733,
      "learning_rate": 1.1030928736009335e-05,
      "loss": 0.5297,
      "step": 30467
    },
    {
      "epoch": 0.9359506036310018,
      "grad_norm": 0.31200411915779114,
      "learning_rate": 1.1030448032499085e-05,
      "loss": 0.5509,
      "step": 30468
    },
    {
      "epoch": 0.9359813227659509,
      "grad_norm": 0.37960201501846313,
      "learning_rate": 1.1029967326582156e-05,
      "loss": 0.6164,
      "step": 30469
    },
    {
      "epoch": 0.9360120419009,
      "grad_norm": 0.5749216079711914,
      "learning_rate": 1.1029486618259663e-05,
      "loss": 0.543,
      "step": 30470
    },
    {
      "epoch": 0.9360427610358493,
      "grad_norm": 0.34579917788505554,
      "learning_rate": 1.1029005907532737e-05,
      "loss": 0.5735,
      "step": 30471
    },
    {
      "epoch": 0.9360734801707984,
      "grad_norm": 0.4105397164821625,
      "learning_rate": 1.1028525194402492e-05,
      "loss": 0.6368,
      "step": 30472
    },
    {
      "epoch": 0.9361041993057475,
      "grad_norm": 0.38152557611465454,
      "learning_rate": 1.1028044478870055e-05,
      "loss": 0.5342,
      "step": 30473
    },
    {
      "epoch": 0.9361349184406967,
      "grad_norm": 0.3708680272102356,
      "learning_rate": 1.102756376093655e-05,
      "loss": 0.5648,
      "step": 30474
    },
    {
      "epoch": 0.9361656375756459,
      "grad_norm": 0.3293423652648926,
      "learning_rate": 1.1027083040603095e-05,
      "loss": 0.5685,
      "step": 30475
    },
    {
      "epoch": 0.936196356710595,
      "grad_norm": 0.4050220549106598,
      "learning_rate": 1.1026602317870819e-05,
      "loss": 0.5413,
      "step": 30476
    },
    {
      "epoch": 0.9362270758455442,
      "grad_norm": 0.3598083555698395,
      "learning_rate": 1.102612159274084e-05,
      "loss": 0.5526,
      "step": 30477
    },
    {
      "epoch": 0.9362577949804933,
      "grad_norm": 0.36917465925216675,
      "learning_rate": 1.102564086521428e-05,
      "loss": 0.4909,
      "step": 30478
    },
    {
      "epoch": 0.9362885141154426,
      "grad_norm": 0.37562596797943115,
      "learning_rate": 1.1025160135292268e-05,
      "loss": 0.579,
      "step": 30479
    },
    {
      "epoch": 0.9363192332503917,
      "grad_norm": 0.40075400471687317,
      "learning_rate": 1.102467940297592e-05,
      "loss": 0.5671,
      "step": 30480
    },
    {
      "epoch": 0.9363499523853408,
      "grad_norm": 0.34429940581321716,
      "learning_rate": 1.1024198668266364e-05,
      "loss": 0.5523,
      "step": 30481
    },
    {
      "epoch": 0.93638067152029,
      "grad_norm": 0.3654640316963196,
      "learning_rate": 1.1023717931164719e-05,
      "loss": 0.5146,
      "step": 30482
    },
    {
      "epoch": 0.9364113906552392,
      "grad_norm": 0.34985607862472534,
      "learning_rate": 1.1023237191672112e-05,
      "loss": 0.5373,
      "step": 30483
    },
    {
      "epoch": 0.9364421097901883,
      "grad_norm": 0.3714081346988678,
      "learning_rate": 1.102275644978966e-05,
      "loss": 0.4518,
      "step": 30484
    },
    {
      "epoch": 0.9364728289251375,
      "grad_norm": 0.38884812593460083,
      "learning_rate": 1.102227570551849e-05,
      "loss": 0.4925,
      "step": 30485
    },
    {
      "epoch": 0.9365035480600866,
      "grad_norm": 0.3605530261993408,
      "learning_rate": 1.1021794958859721e-05,
      "loss": 0.4931,
      "step": 30486
    },
    {
      "epoch": 0.9365342671950357,
      "grad_norm": 0.39612045884132385,
      "learning_rate": 1.1021314209814485e-05,
      "loss": 0.6224,
      "step": 30487
    },
    {
      "epoch": 0.936564986329985,
      "grad_norm": 0.35809189081192017,
      "learning_rate": 1.1020833458383894e-05,
      "loss": 0.5784,
      "step": 30488
    },
    {
      "epoch": 0.9365957054649341,
      "grad_norm": 0.386057585477829,
      "learning_rate": 1.1020352704569076e-05,
      "loss": 0.5128,
      "step": 30489
    },
    {
      "epoch": 0.9366264245998833,
      "grad_norm": 0.6502811908721924,
      "learning_rate": 1.1019871948371153e-05,
      "loss": 0.5442,
      "step": 30490
    },
    {
      "epoch": 0.9366571437348324,
      "grad_norm": 0.36868345737457275,
      "learning_rate": 1.1019391189791246e-05,
      "loss": 0.6053,
      "step": 30491
    },
    {
      "epoch": 0.9366878628697816,
      "grad_norm": 0.3854413330554962,
      "learning_rate": 1.1018910428830483e-05,
      "loss": 0.4629,
      "step": 30492
    },
    {
      "epoch": 0.9367185820047308,
      "grad_norm": 0.3991881012916565,
      "learning_rate": 1.101842966548998e-05,
      "loss": 0.5386,
      "step": 30493
    },
    {
      "epoch": 0.9367493011396799,
      "grad_norm": 0.37113523483276367,
      "learning_rate": 1.1017948899770865e-05,
      "loss": 0.5331,
      "step": 30494
    },
    {
      "epoch": 0.936780020274629,
      "grad_norm": 0.37614697217941284,
      "learning_rate": 1.1017468131674258e-05,
      "loss": 0.5577,
      "step": 30495
    },
    {
      "epoch": 0.9368107394095783,
      "grad_norm": 0.34639772772789,
      "learning_rate": 1.1016987361201285e-05,
      "loss": 0.5683,
      "step": 30496
    },
    {
      "epoch": 0.9368414585445274,
      "grad_norm": 0.3526081144809723,
      "learning_rate": 1.1016506588353066e-05,
      "loss": 0.5333,
      "step": 30497
    },
    {
      "epoch": 0.9368721776794765,
      "grad_norm": 0.3944303095340729,
      "learning_rate": 1.1016025813130724e-05,
      "loss": 0.5867,
      "step": 30498
    },
    {
      "epoch": 0.9369028968144257,
      "grad_norm": 0.33467525243759155,
      "learning_rate": 1.1015545035535386e-05,
      "loss": 0.5438,
      "step": 30499
    },
    {
      "epoch": 0.9369336159493749,
      "grad_norm": 0.3856748640537262,
      "learning_rate": 1.1015064255568169e-05,
      "loss": 0.5435,
      "step": 30500
    },
    {
      "epoch": 0.936964335084324,
      "grad_norm": 0.5413875579833984,
      "learning_rate": 1.10145834732302e-05,
      "loss": 0.5802,
      "step": 30501
    },
    {
      "epoch": 0.9369950542192732,
      "grad_norm": 0.3418818712234497,
      "learning_rate": 1.1014102688522599e-05,
      "loss": 0.5173,
      "step": 30502
    },
    {
      "epoch": 0.9370257733542223,
      "grad_norm": 0.424415647983551,
      "learning_rate": 1.1013621901446491e-05,
      "loss": 0.4916,
      "step": 30503
    },
    {
      "epoch": 0.9370564924891716,
      "grad_norm": 0.31459856033325195,
      "learning_rate": 1.1013141112002999e-05,
      "loss": 0.4694,
      "step": 30504
    },
    {
      "epoch": 0.9370872116241207,
      "grad_norm": 0.3602941930294037,
      "learning_rate": 1.1012660320193244e-05,
      "loss": 0.5899,
      "step": 30505
    },
    {
      "epoch": 0.9371179307590698,
      "grad_norm": 0.352975994348526,
      "learning_rate": 1.101217952601835e-05,
      "loss": 0.5487,
      "step": 30506
    },
    {
      "epoch": 0.937148649894019,
      "grad_norm": 0.3918739855289459,
      "learning_rate": 1.1011698729479441e-05,
      "loss": 0.6075,
      "step": 30507
    },
    {
      "epoch": 0.9371793690289681,
      "grad_norm": 0.3351406455039978,
      "learning_rate": 1.101121793057764e-05,
      "loss": 0.5228,
      "step": 30508
    },
    {
      "epoch": 0.9372100881639173,
      "grad_norm": 0.371866375207901,
      "learning_rate": 1.1010737129314066e-05,
      "loss": 0.5792,
      "step": 30509
    },
    {
      "epoch": 0.9372408072988665,
      "grad_norm": 0.33267083764076233,
      "learning_rate": 1.1010256325689848e-05,
      "loss": 0.4676,
      "step": 30510
    },
    {
      "epoch": 0.9372715264338156,
      "grad_norm": 0.3816780745983124,
      "learning_rate": 1.1009775519706103e-05,
      "loss": 0.5918,
      "step": 30511
    },
    {
      "epoch": 0.9373022455687647,
      "grad_norm": 0.3800414800643921,
      "learning_rate": 1.1009294711363958e-05,
      "loss": 0.5515,
      "step": 30512
    },
    {
      "epoch": 0.937332964703714,
      "grad_norm": 0.3644031882286072,
      "learning_rate": 1.1008813900664535e-05,
      "loss": 0.5743,
      "step": 30513
    },
    {
      "epoch": 0.9373636838386631,
      "grad_norm": 0.3885006308555603,
      "learning_rate": 1.1008333087608956e-05,
      "loss": 0.5923,
      "step": 30514
    },
    {
      "epoch": 0.9373944029736123,
      "grad_norm": 0.3762899339199066,
      "learning_rate": 1.1007852272198343e-05,
      "loss": 0.6011,
      "step": 30515
    },
    {
      "epoch": 0.9374251221085614,
      "grad_norm": 0.3698633313179016,
      "learning_rate": 1.1007371454433821e-05,
      "loss": 0.5071,
      "step": 30516
    },
    {
      "epoch": 0.9374558412435106,
      "grad_norm": 0.38348883390426636,
      "learning_rate": 1.1006890634316517e-05,
      "loss": 0.5393,
      "step": 30517
    },
    {
      "epoch": 0.9374865603784598,
      "grad_norm": 0.38565918803215027,
      "learning_rate": 1.1006409811847544e-05,
      "loss": 0.4897,
      "step": 30518
    },
    {
      "epoch": 0.9375172795134089,
      "grad_norm": 0.40739551186561584,
      "learning_rate": 1.1005928987028036e-05,
      "loss": 0.5786,
      "step": 30519
    },
    {
      "epoch": 0.937547998648358,
      "grad_norm": 0.36479464173316956,
      "learning_rate": 1.1005448159859106e-05,
      "loss": 0.5541,
      "step": 30520
    },
    {
      "epoch": 0.9375787177833073,
      "grad_norm": 0.35180723667144775,
      "learning_rate": 1.1004967330341884e-05,
      "loss": 0.485,
      "step": 30521
    },
    {
      "epoch": 0.9376094369182564,
      "grad_norm": 0.4682829976081848,
      "learning_rate": 1.100448649847749e-05,
      "loss": 0.5227,
      "step": 30522
    },
    {
      "epoch": 0.9376401560532055,
      "grad_norm": 0.3561836779117584,
      "learning_rate": 1.1004005664267048e-05,
      "loss": 0.4781,
      "step": 30523
    },
    {
      "epoch": 0.9376708751881547,
      "grad_norm": 0.39238440990448,
      "learning_rate": 1.1003524827711683e-05,
      "loss": 0.5635,
      "step": 30524
    },
    {
      "epoch": 0.9377015943231038,
      "grad_norm": 0.3665147125720978,
      "learning_rate": 1.1003043988812512e-05,
      "loss": 0.4943,
      "step": 30525
    },
    {
      "epoch": 0.937732313458053,
      "grad_norm": 0.34298229217529297,
      "learning_rate": 1.1002563147570664e-05,
      "loss": 0.5721,
      "step": 30526
    },
    {
      "epoch": 0.9377630325930022,
      "grad_norm": 0.3582199513912201,
      "learning_rate": 1.1002082303987257e-05,
      "loss": 0.5608,
      "step": 30527
    },
    {
      "epoch": 0.9377937517279513,
      "grad_norm": 0.36220067739486694,
      "learning_rate": 1.100160145806342e-05,
      "loss": 0.4902,
      "step": 30528
    },
    {
      "epoch": 0.9378244708629005,
      "grad_norm": 0.3550640344619751,
      "learning_rate": 1.100112060980027e-05,
      "loss": 0.5657,
      "step": 30529
    },
    {
      "epoch": 0.9378551899978497,
      "grad_norm": 0.41666603088378906,
      "learning_rate": 1.1000639759198935e-05,
      "loss": 0.5847,
      "step": 30530
    },
    {
      "epoch": 0.9378859091327988,
      "grad_norm": 0.39002132415771484,
      "learning_rate": 1.1000158906260534e-05,
      "loss": 0.5678,
      "step": 30531
    },
    {
      "epoch": 0.937916628267748,
      "grad_norm": 0.36284101009368896,
      "learning_rate": 1.0999678050986193e-05,
      "loss": 0.4974,
      "step": 30532
    },
    {
      "epoch": 0.9379473474026971,
      "grad_norm": 0.4138340651988983,
      "learning_rate": 1.0999197193377034e-05,
      "loss": 0.5227,
      "step": 30533
    },
    {
      "epoch": 0.9379780665376463,
      "grad_norm": 0.3592665195465088,
      "learning_rate": 1.0998716333434178e-05,
      "loss": 0.5209,
      "step": 30534
    },
    {
      "epoch": 0.9380087856725955,
      "grad_norm": 0.35422003269195557,
      "learning_rate": 1.0998235471158753e-05,
      "loss": 0.5936,
      "step": 30535
    },
    {
      "epoch": 0.9380395048075446,
      "grad_norm": 0.42085981369018555,
      "learning_rate": 1.0997754606551878e-05,
      "loss": 0.5299,
      "step": 30536
    },
    {
      "epoch": 0.9380702239424937,
      "grad_norm": 0.39680832624435425,
      "learning_rate": 1.099727373961468e-05,
      "loss": 0.5807,
      "step": 30537
    },
    {
      "epoch": 0.938100943077443,
      "grad_norm": 0.36455219984054565,
      "learning_rate": 1.0996792870348275e-05,
      "loss": 0.5051,
      "step": 30538
    },
    {
      "epoch": 0.9381316622123921,
      "grad_norm": 0.38291677832603455,
      "learning_rate": 1.0996311998753797e-05,
      "loss": 0.5521,
      "step": 30539
    },
    {
      "epoch": 0.9381623813473413,
      "grad_norm": 0.6399614810943604,
      "learning_rate": 1.0995831124832359e-05,
      "loss": 0.4586,
      "step": 30540
    },
    {
      "epoch": 0.9381931004822904,
      "grad_norm": 0.4435330927371979,
      "learning_rate": 1.0995350248585088e-05,
      "loss": 0.5538,
      "step": 30541
    },
    {
      "epoch": 0.9382238196172396,
      "grad_norm": 0.4028201997280121,
      "learning_rate": 1.0994869370013108e-05,
      "loss": 0.4922,
      "step": 30542
    },
    {
      "epoch": 0.9382545387521888,
      "grad_norm": 0.3791435658931732,
      "learning_rate": 1.099438848911754e-05,
      "loss": 0.5813,
      "step": 30543
    },
    {
      "epoch": 0.9382852578871379,
      "grad_norm": 0.3636995553970337,
      "learning_rate": 1.099390760589951e-05,
      "loss": 0.5704,
      "step": 30544
    },
    {
      "epoch": 0.938315977022087,
      "grad_norm": 0.3340231776237488,
      "learning_rate": 1.0993426720360136e-05,
      "loss": 0.5009,
      "step": 30545
    },
    {
      "epoch": 0.9383466961570363,
      "grad_norm": 0.3629789650440216,
      "learning_rate": 1.0992945832500548e-05,
      "loss": 0.4889,
      "step": 30546
    },
    {
      "epoch": 0.9383774152919854,
      "grad_norm": 0.36056530475616455,
      "learning_rate": 1.0992464942321864e-05,
      "loss": 0.6249,
      "step": 30547
    },
    {
      "epoch": 0.9384081344269345,
      "grad_norm": 0.40736493468284607,
      "learning_rate": 1.099198404982521e-05,
      "loss": 0.5651,
      "step": 30548
    },
    {
      "epoch": 0.9384388535618837,
      "grad_norm": 0.4686693251132965,
      "learning_rate": 1.0991503155011705e-05,
      "loss": 0.5981,
      "step": 30549
    },
    {
      "epoch": 0.9384695726968328,
      "grad_norm": 0.4550022780895233,
      "learning_rate": 1.0991022257882478e-05,
      "loss": 0.4363,
      "step": 30550
    },
    {
      "epoch": 0.938500291831782,
      "grad_norm": 0.3507893979549408,
      "learning_rate": 1.0990541358438647e-05,
      "loss": 0.5053,
      "step": 30551
    },
    {
      "epoch": 0.9385310109667312,
      "grad_norm": 0.33585864305496216,
      "learning_rate": 1.0990060456681338e-05,
      "loss": 0.4345,
      "step": 30552
    },
    {
      "epoch": 0.9385617301016803,
      "grad_norm": 0.41759976744651794,
      "learning_rate": 1.0989579552611674e-05,
      "loss": 0.588,
      "step": 30553
    },
    {
      "epoch": 0.9385924492366295,
      "grad_norm": 1.5914274454116821,
      "learning_rate": 1.0989098646230777e-05,
      "loss": 0.505,
      "step": 30554
    },
    {
      "epoch": 0.9386231683715787,
      "grad_norm": 0.38381126523017883,
      "learning_rate": 1.0988617737539773e-05,
      "loss": 0.5402,
      "step": 30555
    },
    {
      "epoch": 0.9386538875065278,
      "grad_norm": 0.38524991273880005,
      "learning_rate": 1.0988136826539782e-05,
      "loss": 0.5307,
      "step": 30556
    },
    {
      "epoch": 0.938684606641477,
      "grad_norm": 0.3492327034473419,
      "learning_rate": 1.098765591323193e-05,
      "loss": 0.5706,
      "step": 30557
    },
    {
      "epoch": 0.9387153257764261,
      "grad_norm": 0.3999633491039276,
      "learning_rate": 1.0987174997617336e-05,
      "loss": 0.5013,
      "step": 30558
    },
    {
      "epoch": 0.9387460449113753,
      "grad_norm": 0.3781188130378723,
      "learning_rate": 1.0986694079697128e-05,
      "loss": 0.5611,
      "step": 30559
    },
    {
      "epoch": 0.9387767640463245,
      "grad_norm": 0.39904001355171204,
      "learning_rate": 1.0986213159472428e-05,
      "loss": 0.5358,
      "step": 30560
    },
    {
      "epoch": 0.9388074831812736,
      "grad_norm": 0.42379456758499146,
      "learning_rate": 1.0985732236944355e-05,
      "loss": 0.6249,
      "step": 30561
    },
    {
      "epoch": 0.9388382023162227,
      "grad_norm": 0.3560948371887207,
      "learning_rate": 1.098525131211404e-05,
      "loss": 0.537,
      "step": 30562
    },
    {
      "epoch": 0.938868921451172,
      "grad_norm": 0.33941134810447693,
      "learning_rate": 1.0984770384982597e-05,
      "loss": 0.5181,
      "step": 30563
    },
    {
      "epoch": 0.9388996405861211,
      "grad_norm": 0.37272125482559204,
      "learning_rate": 1.0984289455551159e-05,
      "loss": 0.5583,
      "step": 30564
    },
    {
      "epoch": 0.9389303597210703,
      "grad_norm": 0.3448246717453003,
      "learning_rate": 1.0983808523820838e-05,
      "loss": 0.4691,
      "step": 30565
    },
    {
      "epoch": 0.9389610788560194,
      "grad_norm": 0.38180193305015564,
      "learning_rate": 1.0983327589792769e-05,
      "loss": 0.62,
      "step": 30566
    },
    {
      "epoch": 0.9389917979909685,
      "grad_norm": 0.3451305627822876,
      "learning_rate": 1.0982846653468067e-05,
      "loss": 0.5637,
      "step": 30567
    },
    {
      "epoch": 0.9390225171259178,
      "grad_norm": 0.35697197914123535,
      "learning_rate": 1.0982365714847858e-05,
      "loss": 0.4963,
      "step": 30568
    },
    {
      "epoch": 0.9390532362608669,
      "grad_norm": 0.5609351992607117,
      "learning_rate": 1.0981884773933264e-05,
      "loss": 0.5659,
      "step": 30569
    },
    {
      "epoch": 0.939083955395816,
      "grad_norm": 0.3856447637081146,
      "learning_rate": 1.0981403830725413e-05,
      "loss": 0.559,
      "step": 30570
    },
    {
      "epoch": 0.9391146745307652,
      "grad_norm": 0.3715640604496002,
      "learning_rate": 1.0980922885225423e-05,
      "loss": 0.5167,
      "step": 30571
    },
    {
      "epoch": 0.9391453936657144,
      "grad_norm": 0.44372087717056274,
      "learning_rate": 1.0980441937434419e-05,
      "loss": 0.6017,
      "step": 30572
    },
    {
      "epoch": 0.9391761128006635,
      "grad_norm": 0.35631072521209717,
      "learning_rate": 1.0979960987353524e-05,
      "loss": 0.5969,
      "step": 30573
    },
    {
      "epoch": 0.9392068319356127,
      "grad_norm": 0.37863269448280334,
      "learning_rate": 1.097948003498386e-05,
      "loss": 0.5143,
      "step": 30574
    },
    {
      "epoch": 0.9392375510705618,
      "grad_norm": 0.36044996976852417,
      "learning_rate": 1.0978999080326555e-05,
      "loss": 0.4955,
      "step": 30575
    },
    {
      "epoch": 0.939268270205511,
      "grad_norm": 0.34307265281677246,
      "learning_rate": 1.0978518123382732e-05,
      "loss": 0.5303,
      "step": 30576
    },
    {
      "epoch": 0.9392989893404602,
      "grad_norm": 0.3604673147201538,
      "learning_rate": 1.0978037164153505e-05,
      "loss": 0.5333,
      "step": 30577
    },
    {
      "epoch": 0.9393297084754093,
      "grad_norm": 0.3738802373409271,
      "learning_rate": 1.097755620264001e-05,
      "loss": 0.469,
      "step": 30578
    },
    {
      "epoch": 0.9393604276103585,
      "grad_norm": 0.39931657910346985,
      "learning_rate": 1.097707523884336e-05,
      "loss": 0.5739,
      "step": 30579
    },
    {
      "epoch": 0.9393911467453077,
      "grad_norm": 0.38523465394973755,
      "learning_rate": 1.0976594272764685e-05,
      "loss": 0.5402,
      "step": 30580
    },
    {
      "epoch": 0.9394218658802568,
      "grad_norm": 0.4134034812450409,
      "learning_rate": 1.0976113304405103e-05,
      "loss": 0.5623,
      "step": 30581
    },
    {
      "epoch": 0.939452585015206,
      "grad_norm": 0.3752863109111786,
      "learning_rate": 1.0975632333765743e-05,
      "loss": 0.5936,
      "step": 30582
    },
    {
      "epoch": 0.9394833041501551,
      "grad_norm": 0.3676816523075104,
      "learning_rate": 1.0975151360847722e-05,
      "loss": 0.5012,
      "step": 30583
    },
    {
      "epoch": 0.9395140232851042,
      "grad_norm": 0.3982495069503784,
      "learning_rate": 1.0974670385652171e-05,
      "loss": 0.6132,
      "step": 30584
    },
    {
      "epoch": 0.9395447424200535,
      "grad_norm": 0.38514381647109985,
      "learning_rate": 1.0974189408180208e-05,
      "loss": 0.5052,
      "step": 30585
    },
    {
      "epoch": 0.9395754615550026,
      "grad_norm": 0.4124583601951599,
      "learning_rate": 1.0973708428432956e-05,
      "loss": 0.5222,
      "step": 30586
    },
    {
      "epoch": 0.9396061806899517,
      "grad_norm": 0.3395598232746124,
      "learning_rate": 1.0973227446411543e-05,
      "loss": 0.5423,
      "step": 30587
    },
    {
      "epoch": 0.939636899824901,
      "grad_norm": 0.4008364975452423,
      "learning_rate": 1.0972746462117083e-05,
      "loss": 0.5585,
      "step": 30588
    },
    {
      "epoch": 0.9396676189598501,
      "grad_norm": 0.36572718620300293,
      "learning_rate": 1.0972265475550711e-05,
      "loss": 0.5137,
      "step": 30589
    },
    {
      "epoch": 0.9396983380947993,
      "grad_norm": 0.3857976794242859,
      "learning_rate": 1.0971784486713544e-05,
      "loss": 0.5895,
      "step": 30590
    },
    {
      "epoch": 0.9397290572297484,
      "grad_norm": 0.3478478491306305,
      "learning_rate": 1.0971303495606707e-05,
      "loss": 0.5533,
      "step": 30591
    },
    {
      "epoch": 0.9397597763646975,
      "grad_norm": 0.383031964302063,
      "learning_rate": 1.0970822502231322e-05,
      "loss": 0.4685,
      "step": 30592
    },
    {
      "epoch": 0.9397904954996468,
      "grad_norm": 0.3461166322231293,
      "learning_rate": 1.0970341506588516e-05,
      "loss": 0.5378,
      "step": 30593
    },
    {
      "epoch": 0.9398212146345959,
      "grad_norm": 0.3745899498462677,
      "learning_rate": 1.0969860508679406e-05,
      "loss": 0.4918,
      "step": 30594
    },
    {
      "epoch": 0.939851933769545,
      "grad_norm": 0.3817872405052185,
      "learning_rate": 1.096937950850512e-05,
      "loss": 0.541,
      "step": 30595
    },
    {
      "epoch": 0.9398826529044942,
      "grad_norm": 0.3677142858505249,
      "learning_rate": 1.0968898506066782e-05,
      "loss": 0.5276,
      "step": 30596
    },
    {
      "epoch": 0.9399133720394434,
      "grad_norm": 0.4343697726726532,
      "learning_rate": 1.0968417501365511e-05,
      "loss": 0.5507,
      "step": 30597
    },
    {
      "epoch": 0.9399440911743925,
      "grad_norm": 0.352441668510437,
      "learning_rate": 1.0967936494402437e-05,
      "loss": 0.5552,
      "step": 30598
    },
    {
      "epoch": 0.9399748103093417,
      "grad_norm": 0.3439881205558777,
      "learning_rate": 1.0967455485178678e-05,
      "loss": 0.5449,
      "step": 30599
    },
    {
      "epoch": 0.9400055294442908,
      "grad_norm": 0.3587932586669922,
      "learning_rate": 1.096697447369536e-05,
      "loss": 0.5658,
      "step": 30600
    },
    {
      "epoch": 0.9400362485792401,
      "grad_norm": 0.37353864312171936,
      "learning_rate": 1.0966493459953602e-05,
      "loss": 0.5587,
      "step": 30601
    },
    {
      "epoch": 0.9400669677141892,
      "grad_norm": 0.3950367867946625,
      "learning_rate": 1.0966012443954534e-05,
      "loss": 0.5085,
      "step": 30602
    },
    {
      "epoch": 0.9400976868491383,
      "grad_norm": 0.36878931522369385,
      "learning_rate": 1.0965531425699276e-05,
      "loss": 0.5029,
      "step": 30603
    },
    {
      "epoch": 0.9401284059840875,
      "grad_norm": 0.5952804088592529,
      "learning_rate": 1.0965050405188953e-05,
      "loss": 0.4704,
      "step": 30604
    },
    {
      "epoch": 0.9401591251190367,
      "grad_norm": 0.377076119184494,
      "learning_rate": 1.0964569382424688e-05,
      "loss": 0.6289,
      "step": 30605
    },
    {
      "epoch": 0.9401898442539858,
      "grad_norm": 0.3976678252220154,
      "learning_rate": 1.0964088357407598e-05,
      "loss": 0.5118,
      "step": 30606
    },
    {
      "epoch": 0.940220563388935,
      "grad_norm": 0.41511476039886475,
      "learning_rate": 1.0963607330138816e-05,
      "loss": 0.4957,
      "step": 30607
    },
    {
      "epoch": 0.9402512825238841,
      "grad_norm": 0.3688296675682068,
      "learning_rate": 1.0963126300619462e-05,
      "loss": 0.5584,
      "step": 30608
    },
    {
      "epoch": 0.9402820016588332,
      "grad_norm": 0.3909655511379242,
      "learning_rate": 1.096264526885066e-05,
      "loss": 0.5197,
      "step": 30609
    },
    {
      "epoch": 0.9403127207937825,
      "grad_norm": 0.4365016222000122,
      "learning_rate": 1.0962164234833532e-05,
      "loss": 0.5768,
      "step": 30610
    },
    {
      "epoch": 0.9403434399287316,
      "grad_norm": 0.3880998194217682,
      "learning_rate": 1.0961683198569204e-05,
      "loss": 0.6037,
      "step": 30611
    },
    {
      "epoch": 0.9403741590636807,
      "grad_norm": 0.39228084683418274,
      "learning_rate": 1.0961202160058796e-05,
      "loss": 0.5221,
      "step": 30612
    },
    {
      "epoch": 0.94040487819863,
      "grad_norm": 0.33076387643814087,
      "learning_rate": 1.0960721119303433e-05,
      "loss": 0.5421,
      "step": 30613
    },
    {
      "epoch": 0.9404355973335791,
      "grad_norm": 0.40231987833976746,
      "learning_rate": 1.096024007630424e-05,
      "loss": 0.5614,
      "step": 30614
    },
    {
      "epoch": 0.9404663164685283,
      "grad_norm": 0.37394943833351135,
      "learning_rate": 1.0959759031062339e-05,
      "loss": 0.5859,
      "step": 30615
    },
    {
      "epoch": 0.9404970356034774,
      "grad_norm": 0.42474156618118286,
      "learning_rate": 1.0959277983578854e-05,
      "loss": 0.5792,
      "step": 30616
    },
    {
      "epoch": 0.9405277547384265,
      "grad_norm": 0.3770480155944824,
      "learning_rate": 1.0958796933854905e-05,
      "loss": 0.4568,
      "step": 30617
    },
    {
      "epoch": 0.9405584738733758,
      "grad_norm": 0.35851266980171204,
      "learning_rate": 1.0958315881891623e-05,
      "loss": 0.4985,
      "step": 30618
    },
    {
      "epoch": 0.9405891930083249,
      "grad_norm": 0.3842771053314209,
      "learning_rate": 1.0957834827690123e-05,
      "loss": 0.5149,
      "step": 30619
    },
    {
      "epoch": 0.940619912143274,
      "grad_norm": 0.3565131723880768,
      "learning_rate": 1.0957353771251538e-05,
      "loss": 0.5931,
      "step": 30620
    },
    {
      "epoch": 0.9406506312782232,
      "grad_norm": 0.37876391410827637,
      "learning_rate": 1.0956872712576982e-05,
      "loss": 0.5303,
      "step": 30621
    },
    {
      "epoch": 0.9406813504131724,
      "grad_norm": 0.3564164340496063,
      "learning_rate": 1.0956391651667586e-05,
      "loss": 0.5833,
      "step": 30622
    },
    {
      "epoch": 0.9407120695481215,
      "grad_norm": 0.34185802936553955,
      "learning_rate": 1.095591058852447e-05,
      "loss": 0.5126,
      "step": 30623
    },
    {
      "epoch": 0.9407427886830707,
      "grad_norm": 0.3650984764099121,
      "learning_rate": 1.0955429523148756e-05,
      "loss": 0.5597,
      "step": 30624
    },
    {
      "epoch": 0.9407735078180198,
      "grad_norm": 0.37044936418533325,
      "learning_rate": 1.095494845554157e-05,
      "loss": 0.5899,
      "step": 30625
    },
    {
      "epoch": 0.9408042269529691,
      "grad_norm": 0.33271145820617676,
      "learning_rate": 1.0954467385704035e-05,
      "loss": 0.5779,
      "step": 30626
    },
    {
      "epoch": 0.9408349460879182,
      "grad_norm": 0.3642820417881012,
      "learning_rate": 1.0953986313637277e-05,
      "loss": 0.5926,
      "step": 30627
    },
    {
      "epoch": 0.9408656652228673,
      "grad_norm": 0.36204296350479126,
      "learning_rate": 1.0953505239342417e-05,
      "loss": 0.5159,
      "step": 30628
    },
    {
      "epoch": 0.9408963843578165,
      "grad_norm": 0.38862529397010803,
      "learning_rate": 1.0953024162820579e-05,
      "loss": 0.5847,
      "step": 30629
    },
    {
      "epoch": 0.9409271034927656,
      "grad_norm": 0.35233786702156067,
      "learning_rate": 1.0952543084072887e-05,
      "loss": 0.5669,
      "step": 30630
    },
    {
      "epoch": 0.9409578226277148,
      "grad_norm": 0.3567686378955841,
      "learning_rate": 1.0952062003100462e-05,
      "loss": 0.5383,
      "step": 30631
    },
    {
      "epoch": 0.940988541762664,
      "grad_norm": 0.3495686650276184,
      "learning_rate": 1.095158091990443e-05,
      "loss": 0.4313,
      "step": 30632
    },
    {
      "epoch": 0.9410192608976131,
      "grad_norm": 0.3990044593811035,
      "learning_rate": 1.0951099834485914e-05,
      "loss": 0.524,
      "step": 30633
    },
    {
      "epoch": 0.9410499800325622,
      "grad_norm": 0.42440304160118103,
      "learning_rate": 1.095061874684604e-05,
      "loss": 0.6276,
      "step": 30634
    },
    {
      "epoch": 0.9410806991675115,
      "grad_norm": 0.3947928547859192,
      "learning_rate": 1.0950137656985927e-05,
      "loss": 0.4481,
      "step": 30635
    },
    {
      "epoch": 0.9411114183024606,
      "grad_norm": 0.3798501491546631,
      "learning_rate": 1.0949656564906704e-05,
      "loss": 0.4202,
      "step": 30636
    },
    {
      "epoch": 0.9411421374374097,
      "grad_norm": 0.3592594563961029,
      "learning_rate": 1.0949175470609488e-05,
      "loss": 0.6285,
      "step": 30637
    },
    {
      "epoch": 0.9411728565723589,
      "grad_norm": 0.4066087603569031,
      "learning_rate": 1.094869437409541e-05,
      "loss": 0.5373,
      "step": 30638
    },
    {
      "epoch": 0.9412035757073081,
      "grad_norm": 0.3720725476741791,
      "learning_rate": 1.0948213275365587e-05,
      "loss": 0.5372,
      "step": 30639
    },
    {
      "epoch": 0.9412342948422573,
      "grad_norm": 0.378385454416275,
      "learning_rate": 1.094773217442115e-05,
      "loss": 0.558,
      "step": 30640
    },
    {
      "epoch": 0.9412650139772064,
      "grad_norm": 0.3698541224002838,
      "learning_rate": 1.0947251071263215e-05,
      "loss": 0.5489,
      "step": 30641
    },
    {
      "epoch": 0.9412957331121555,
      "grad_norm": 0.33005666732788086,
      "learning_rate": 1.094676996589291e-05,
      "loss": 0.5048,
      "step": 30642
    },
    {
      "epoch": 0.9413264522471048,
      "grad_norm": 0.4004095792770386,
      "learning_rate": 1.0946288858311353e-05,
      "loss": 0.5098,
      "step": 30643
    },
    {
      "epoch": 0.9413571713820539,
      "grad_norm": 0.35159602761268616,
      "learning_rate": 1.0945807748519677e-05,
      "loss": 0.5487,
      "step": 30644
    },
    {
      "epoch": 0.941387890517003,
      "grad_norm": 0.3710736036300659,
      "learning_rate": 1.0945326636519e-05,
      "loss": 0.5557,
      "step": 30645
    },
    {
      "epoch": 0.9414186096519522,
      "grad_norm": 0.3679526150226593,
      "learning_rate": 1.094484552231045e-05,
      "loss": 0.5574,
      "step": 30646
    },
    {
      "epoch": 0.9414493287869014,
      "grad_norm": 0.36016786098480225,
      "learning_rate": 1.0944364405895142e-05,
      "loss": 0.6006,
      "step": 30647
    },
    {
      "epoch": 0.9414800479218505,
      "grad_norm": 0.35138291120529175,
      "learning_rate": 1.0943883287274208e-05,
      "loss": 0.5249,
      "step": 30648
    },
    {
      "epoch": 0.9415107670567997,
      "grad_norm": 0.330581396818161,
      "learning_rate": 1.0943402166448767e-05,
      "loss": 0.6269,
      "step": 30649
    },
    {
      "epoch": 0.9415414861917488,
      "grad_norm": 0.39819324016571045,
      "learning_rate": 1.0942921043419948e-05,
      "loss": 0.4877,
      "step": 30650
    },
    {
      "epoch": 0.941572205326698,
      "grad_norm": 0.3623211979866028,
      "learning_rate": 1.0942439918188865e-05,
      "loss": 0.5281,
      "step": 30651
    },
    {
      "epoch": 0.9416029244616472,
      "grad_norm": 0.4391518533229828,
      "learning_rate": 1.0941958790756652e-05,
      "loss": 0.5441,
      "step": 30652
    },
    {
      "epoch": 0.9416336435965963,
      "grad_norm": 0.3672217130661011,
      "learning_rate": 1.0941477661124429e-05,
      "loss": 0.5284,
      "step": 30653
    },
    {
      "epoch": 0.9416643627315455,
      "grad_norm": 0.3744504749774933,
      "learning_rate": 1.0940996529293318e-05,
      "loss": 0.5303,
      "step": 30654
    },
    {
      "epoch": 0.9416950818664946,
      "grad_norm": 0.37162771821022034,
      "learning_rate": 1.0940515395264441e-05,
      "loss": 0.5591,
      "step": 30655
    },
    {
      "epoch": 0.9417258010014438,
      "grad_norm": 0.32833045721054077,
      "learning_rate": 1.094003425903893e-05,
      "loss": 0.546,
      "step": 30656
    },
    {
      "epoch": 0.941756520136393,
      "grad_norm": 0.35805678367614746,
      "learning_rate": 1.09395531206179e-05,
      "loss": 0.5487,
      "step": 30657
    },
    {
      "epoch": 0.9417872392713421,
      "grad_norm": 0.3968590497970581,
      "learning_rate": 1.0939071980002479e-05,
      "loss": 0.6006,
      "step": 30658
    },
    {
      "epoch": 0.9418179584062912,
      "grad_norm": 0.3920024335384369,
      "learning_rate": 1.093859083719379e-05,
      "loss": 0.5981,
      "step": 30659
    },
    {
      "epoch": 0.9418486775412405,
      "grad_norm": 0.3350933790206909,
      "learning_rate": 1.0938109692192955e-05,
      "loss": 0.4547,
      "step": 30660
    },
    {
      "epoch": 0.9418793966761896,
      "grad_norm": 0.3847745656967163,
      "learning_rate": 1.09376285450011e-05,
      "loss": 0.5487,
      "step": 30661
    },
    {
      "epoch": 0.9419101158111387,
      "grad_norm": 0.41053205728530884,
      "learning_rate": 1.0937147395619345e-05,
      "loss": 0.5483,
      "step": 30662
    },
    {
      "epoch": 0.9419408349460879,
      "grad_norm": 0.38871651887893677,
      "learning_rate": 1.0936666244048824e-05,
      "loss": 0.6229,
      "step": 30663
    },
    {
      "epoch": 0.941971554081037,
      "grad_norm": 0.4028288424015045,
      "learning_rate": 1.093618509029065e-05,
      "loss": 0.6392,
      "step": 30664
    },
    {
      "epoch": 0.9420022732159863,
      "grad_norm": 0.4544677436351776,
      "learning_rate": 1.093570393434595e-05,
      "loss": 0.5262,
      "step": 30665
    },
    {
      "epoch": 0.9420329923509354,
      "grad_norm": 0.3976188600063324,
      "learning_rate": 1.0935222776215848e-05,
      "loss": 0.5819,
      "step": 30666
    },
    {
      "epoch": 0.9420637114858845,
      "grad_norm": 0.347687304019928,
      "learning_rate": 1.0934741615901467e-05,
      "loss": 0.4844,
      "step": 30667
    },
    {
      "epoch": 0.9420944306208338,
      "grad_norm": 0.36080387234687805,
      "learning_rate": 1.0934260453403933e-05,
      "loss": 0.5257,
      "step": 30668
    },
    {
      "epoch": 0.9421251497557829,
      "grad_norm": 0.36903485655784607,
      "learning_rate": 1.0933779288724366e-05,
      "loss": 0.5471,
      "step": 30669
    },
    {
      "epoch": 0.942155868890732,
      "grad_norm": 0.39570382237434387,
      "learning_rate": 1.0933298121863896e-05,
      "loss": 0.5324,
      "step": 30670
    },
    {
      "epoch": 0.9421865880256812,
      "grad_norm": 0.3322794437408447,
      "learning_rate": 1.0932816952823642e-05,
      "loss": 0.5214,
      "step": 30671
    },
    {
      "epoch": 0.9422173071606303,
      "grad_norm": 0.36827924847602844,
      "learning_rate": 1.0932335781604729e-05,
      "loss": 0.5477,
      "step": 30672
    },
    {
      "epoch": 0.9422480262955795,
      "grad_norm": 0.37766700983047485,
      "learning_rate": 1.093185460820828e-05,
      "loss": 0.5418,
      "step": 30673
    },
    {
      "epoch": 0.9422787454305287,
      "grad_norm": 0.34616997838020325,
      "learning_rate": 1.093137343263542e-05,
      "loss": 0.4954,
      "step": 30674
    },
    {
      "epoch": 0.9423094645654778,
      "grad_norm": 0.4389040172100067,
      "learning_rate": 1.0930892254887273e-05,
      "loss": 0.5746,
      "step": 30675
    },
    {
      "epoch": 0.942340183700427,
      "grad_norm": 0.41306641697883606,
      "learning_rate": 1.093041107496496e-05,
      "loss": 0.5234,
      "step": 30676
    },
    {
      "epoch": 0.9423709028353762,
      "grad_norm": 0.3939557671546936,
      "learning_rate": 1.0929929892869608e-05,
      "loss": 0.6104,
      "step": 30677
    },
    {
      "epoch": 0.9424016219703253,
      "grad_norm": 0.3664713203907013,
      "learning_rate": 1.092944870860234e-05,
      "loss": 0.6444,
      "step": 30678
    },
    {
      "epoch": 0.9424323411052745,
      "grad_norm": 0.4531330466270447,
      "learning_rate": 1.0928967522164275e-05,
      "loss": 0.5452,
      "step": 30679
    },
    {
      "epoch": 0.9424630602402236,
      "grad_norm": 0.3812418282032013,
      "learning_rate": 1.0928486333556547e-05,
      "loss": 0.535,
      "step": 30680
    },
    {
      "epoch": 0.9424937793751728,
      "grad_norm": 0.6591178178787231,
      "learning_rate": 1.0928005142780273e-05,
      "loss": 0.5737,
      "step": 30681
    },
    {
      "epoch": 0.942524498510122,
      "grad_norm": 0.3918472230434418,
      "learning_rate": 1.092752394983658e-05,
      "loss": 0.6348,
      "step": 30682
    },
    {
      "epoch": 0.9425552176450711,
      "grad_norm": 0.41105133295059204,
      "learning_rate": 1.0927042754726587e-05,
      "loss": 0.5409,
      "step": 30683
    },
    {
      "epoch": 0.9425859367800202,
      "grad_norm": 1.6519687175750732,
      "learning_rate": 1.0926561557451424e-05,
      "loss": 0.596,
      "step": 30684
    },
    {
      "epoch": 0.9426166559149695,
      "grad_norm": 0.35563623905181885,
      "learning_rate": 1.0926080358012208e-05,
      "loss": 0.5689,
      "step": 30685
    },
    {
      "epoch": 0.9426473750499186,
      "grad_norm": 0.33878716826438904,
      "learning_rate": 1.092559915641007e-05,
      "loss": 0.5104,
      "step": 30686
    },
    {
      "epoch": 0.9426780941848677,
      "grad_norm": 0.3320094347000122,
      "learning_rate": 1.0925117952646127e-05,
      "loss": 0.6018,
      "step": 30687
    },
    {
      "epoch": 0.9427088133198169,
      "grad_norm": 0.3782365918159485,
      "learning_rate": 1.092463674672151e-05,
      "loss": 0.5098,
      "step": 30688
    },
    {
      "epoch": 0.942739532454766,
      "grad_norm": 0.37028658390045166,
      "learning_rate": 1.0924155538637338e-05,
      "loss": 0.4378,
      "step": 30689
    },
    {
      "epoch": 0.9427702515897153,
      "grad_norm": 0.35953789949417114,
      "learning_rate": 1.0923674328394735e-05,
      "loss": 0.5965,
      "step": 30690
    },
    {
      "epoch": 0.9428009707246644,
      "grad_norm": 0.40814805030822754,
      "learning_rate": 1.0923193115994828e-05,
      "loss": 0.5056,
      "step": 30691
    },
    {
      "epoch": 0.9428316898596135,
      "grad_norm": 0.44681328535079956,
      "learning_rate": 1.0922711901438739e-05,
      "loss": 0.5016,
      "step": 30692
    },
    {
      "epoch": 0.9428624089945628,
      "grad_norm": 0.4427691698074341,
      "learning_rate": 1.0922230684727593e-05,
      "loss": 0.5967,
      "step": 30693
    },
    {
      "epoch": 0.9428931281295119,
      "grad_norm": 0.36629268527030945,
      "learning_rate": 1.0921749465862508e-05,
      "loss": 0.5653,
      "step": 30694
    },
    {
      "epoch": 0.942923847264461,
      "grad_norm": 0.3426606059074402,
      "learning_rate": 1.0921268244844618e-05,
      "loss": 0.5872,
      "step": 30695
    },
    {
      "epoch": 0.9429545663994102,
      "grad_norm": 0.396567702293396,
      "learning_rate": 1.0920787021675036e-05,
      "loss": 0.5502,
      "step": 30696
    },
    {
      "epoch": 0.9429852855343593,
      "grad_norm": 0.3817180097103119,
      "learning_rate": 1.0920305796354895e-05,
      "loss": 0.4769,
      "step": 30697
    },
    {
      "epoch": 0.9430160046693085,
      "grad_norm": 0.3242032825946808,
      "learning_rate": 1.0919824568885317e-05,
      "loss": 0.553,
      "step": 30698
    },
    {
      "epoch": 0.9430467238042577,
      "grad_norm": 0.3894921839237213,
      "learning_rate": 1.091934333926742e-05,
      "loss": 0.5186,
      "step": 30699
    },
    {
      "epoch": 0.9430774429392068,
      "grad_norm": 0.38750123977661133,
      "learning_rate": 1.091886210750234e-05,
      "loss": 0.4083,
      "step": 30700
    },
    {
      "epoch": 0.943108162074156,
      "grad_norm": 0.38312217593193054,
      "learning_rate": 1.0918380873591185e-05,
      "loss": 0.5465,
      "step": 30701
    },
    {
      "epoch": 0.9431388812091052,
      "grad_norm": 0.3582525849342346,
      "learning_rate": 1.0917899637535094e-05,
      "loss": 0.5589,
      "step": 30702
    },
    {
      "epoch": 0.9431696003440543,
      "grad_norm": 0.37599971890449524,
      "learning_rate": 1.091741839933518e-05,
      "loss": 0.4115,
      "step": 30703
    },
    {
      "epoch": 0.9432003194790035,
      "grad_norm": 0.4013470709323883,
      "learning_rate": 1.0916937158992573e-05,
      "loss": 0.6143,
      "step": 30704
    },
    {
      "epoch": 0.9432310386139526,
      "grad_norm": 0.4118158519268036,
      "learning_rate": 1.0916455916508395e-05,
      "loss": 0.5386,
      "step": 30705
    },
    {
      "epoch": 0.9432617577489018,
      "grad_norm": 0.38869982957839966,
      "learning_rate": 1.0915974671883772e-05,
      "loss": 0.6044,
      "step": 30706
    },
    {
      "epoch": 0.943292476883851,
      "grad_norm": 0.3812267780303955,
      "learning_rate": 1.091549342511982e-05,
      "loss": 0.5315,
      "step": 30707
    },
    {
      "epoch": 0.9433231960188001,
      "grad_norm": 0.47151172161102295,
      "learning_rate": 1.0915012176217677e-05,
      "loss": 0.675,
      "step": 30708
    },
    {
      "epoch": 0.9433539151537492,
      "grad_norm": 0.4259050786495209,
      "learning_rate": 1.0914530925178454e-05,
      "loss": 0.5835,
      "step": 30709
    },
    {
      "epoch": 0.9433846342886985,
      "grad_norm": 0.3968071937561035,
      "learning_rate": 1.0914049672003282e-05,
      "loss": 0.5265,
      "step": 30710
    },
    {
      "epoch": 0.9434153534236476,
      "grad_norm": 0.3967810273170471,
      "learning_rate": 1.0913568416693284e-05,
      "loss": 0.5175,
      "step": 30711
    },
    {
      "epoch": 0.9434460725585968,
      "grad_norm": 0.4038400650024414,
      "learning_rate": 1.091308715924958e-05,
      "loss": 0.5731,
      "step": 30712
    },
    {
      "epoch": 0.9434767916935459,
      "grad_norm": 0.3953440487384796,
      "learning_rate": 1.09126058996733e-05,
      "loss": 0.5828,
      "step": 30713
    },
    {
      "epoch": 0.943507510828495,
      "grad_norm": 0.3524687886238098,
      "learning_rate": 1.0912124637965564e-05,
      "loss": 0.578,
      "step": 30714
    },
    {
      "epoch": 0.9435382299634443,
      "grad_norm": 0.36862215399742126,
      "learning_rate": 1.0911643374127499e-05,
      "loss": 0.4966,
      "step": 30715
    },
    {
      "epoch": 0.9435689490983934,
      "grad_norm": 0.35657447576522827,
      "learning_rate": 1.0911162108160225e-05,
      "loss": 0.5427,
      "step": 30716
    },
    {
      "epoch": 0.9435996682333425,
      "grad_norm": 0.3504733145236969,
      "learning_rate": 1.0910680840064869e-05,
      "loss": 0.5363,
      "step": 30717
    },
    {
      "epoch": 0.9436303873682917,
      "grad_norm": 0.3724963665008545,
      "learning_rate": 1.0910199569842555e-05,
      "loss": 0.5762,
      "step": 30718
    },
    {
      "epoch": 0.9436611065032409,
      "grad_norm": 0.5166528224945068,
      "learning_rate": 1.0909718297494404e-05,
      "loss": 0.5107,
      "step": 30719
    },
    {
      "epoch": 0.94369182563819,
      "grad_norm": 0.9325889945030212,
      "learning_rate": 1.0909237023021546e-05,
      "loss": 0.5806,
      "step": 30720
    },
    {
      "epoch": 0.9437225447731392,
      "grad_norm": 0.3726601004600525,
      "learning_rate": 1.0908755746425098e-05,
      "loss": 0.5292,
      "step": 30721
    },
    {
      "epoch": 0.9437532639080883,
      "grad_norm": 0.34769582748413086,
      "learning_rate": 1.090827446770619e-05,
      "loss": 0.6006,
      "step": 30722
    },
    {
      "epoch": 0.9437839830430375,
      "grad_norm": 0.40030744671821594,
      "learning_rate": 1.0907793186865941e-05,
      "loss": 0.5485,
      "step": 30723
    },
    {
      "epoch": 0.9438147021779867,
      "grad_norm": 0.37545162439346313,
      "learning_rate": 1.090731190390548e-05,
      "loss": 0.555,
      "step": 30724
    },
    {
      "epoch": 0.9438454213129358,
      "grad_norm": 0.3553171455860138,
      "learning_rate": 1.0906830618825928e-05,
      "loss": 0.5979,
      "step": 30725
    },
    {
      "epoch": 0.943876140447885,
      "grad_norm": 0.3591116964817047,
      "learning_rate": 1.090634933162841e-05,
      "loss": 0.5006,
      "step": 30726
    },
    {
      "epoch": 0.9439068595828342,
      "grad_norm": 0.40418368577957153,
      "learning_rate": 1.0905868042314052e-05,
      "loss": 0.6645,
      "step": 30727
    },
    {
      "epoch": 0.9439375787177833,
      "grad_norm": 0.4203190505504608,
      "learning_rate": 1.090538675088397e-05,
      "loss": 0.6149,
      "step": 30728
    },
    {
      "epoch": 0.9439682978527325,
      "grad_norm": 0.3460955321788788,
      "learning_rate": 1.0904905457339299e-05,
      "loss": 0.578,
      "step": 30729
    },
    {
      "epoch": 0.9439990169876816,
      "grad_norm": 0.4423180818557739,
      "learning_rate": 1.0904424161681155e-05,
      "loss": 0.504,
      "step": 30730
    },
    {
      "epoch": 0.9440297361226307,
      "grad_norm": 0.39953377842903137,
      "learning_rate": 1.0903942863910669e-05,
      "loss": 0.5689,
      "step": 30731
    },
    {
      "epoch": 0.94406045525758,
      "grad_norm": 0.37462472915649414,
      "learning_rate": 1.0903461564028958e-05,
      "loss": 0.4585,
      "step": 30732
    },
    {
      "epoch": 0.9440911743925291,
      "grad_norm": 0.7479169964790344,
      "learning_rate": 1.0902980262037151e-05,
      "loss": 0.5272,
      "step": 30733
    },
    {
      "epoch": 0.9441218935274782,
      "grad_norm": 0.3691602349281311,
      "learning_rate": 1.090249895793637e-05,
      "loss": 0.5266,
      "step": 30734
    },
    {
      "epoch": 0.9441526126624274,
      "grad_norm": 0.3551304340362549,
      "learning_rate": 1.0902017651727736e-05,
      "loss": 0.5178,
      "step": 30735
    },
    {
      "epoch": 0.9441833317973766,
      "grad_norm": 0.437679260969162,
      "learning_rate": 1.0901536343412382e-05,
      "loss": 0.5783,
      "step": 30736
    },
    {
      "epoch": 0.9442140509323258,
      "grad_norm": 0.38654035329818726,
      "learning_rate": 1.0901055032991425e-05,
      "loss": 0.5313,
      "step": 30737
    },
    {
      "epoch": 0.9442447700672749,
      "grad_norm": 0.35758712887763977,
      "learning_rate": 1.0900573720465992e-05,
      "loss": 0.5831,
      "step": 30738
    },
    {
      "epoch": 0.944275489202224,
      "grad_norm": 0.3819088041782379,
      "learning_rate": 1.0900092405837206e-05,
      "loss": 0.669,
      "step": 30739
    },
    {
      "epoch": 0.9443062083371733,
      "grad_norm": 0.4337395131587982,
      "learning_rate": 1.089961108910619e-05,
      "loss": 0.4155,
      "step": 30740
    },
    {
      "epoch": 0.9443369274721224,
      "grad_norm": 0.3885762393474579,
      "learning_rate": 1.089912977027407e-05,
      "loss": 0.5867,
      "step": 30741
    },
    {
      "epoch": 0.9443676466070715,
      "grad_norm": 0.3640156090259552,
      "learning_rate": 1.089864844934197e-05,
      "loss": 0.5715,
      "step": 30742
    },
    {
      "epoch": 0.9443983657420207,
      "grad_norm": 0.3953651189804077,
      "learning_rate": 1.0898167126311015e-05,
      "loss": 0.5848,
      "step": 30743
    },
    {
      "epoch": 0.9444290848769699,
      "grad_norm": 0.3452005088329315,
      "learning_rate": 1.0897685801182327e-05,
      "loss": 0.4987,
      "step": 30744
    },
    {
      "epoch": 0.944459804011919,
      "grad_norm": 0.33986711502075195,
      "learning_rate": 1.0897204473957032e-05,
      "loss": 0.5113,
      "step": 30745
    },
    {
      "epoch": 0.9444905231468682,
      "grad_norm": 2.3873989582061768,
      "learning_rate": 1.0896723144636252e-05,
      "loss": 0.6544,
      "step": 30746
    },
    {
      "epoch": 0.9445212422818173,
      "grad_norm": 0.35634103417396545,
      "learning_rate": 1.0896241813221113e-05,
      "loss": 0.5061,
      "step": 30747
    },
    {
      "epoch": 0.9445519614167665,
      "grad_norm": 0.37158727645874023,
      "learning_rate": 1.0895760479712736e-05,
      "loss": 0.5508,
      "step": 30748
    },
    {
      "epoch": 0.9445826805517157,
      "grad_norm": 0.40026381611824036,
      "learning_rate": 1.0895279144112252e-05,
      "loss": 0.6468,
      "step": 30749
    },
    {
      "epoch": 0.9446133996866648,
      "grad_norm": 0.3809809386730194,
      "learning_rate": 1.0894797806420778e-05,
      "loss": 0.5191,
      "step": 30750
    },
    {
      "epoch": 0.944644118821614,
      "grad_norm": 0.36660927534103394,
      "learning_rate": 1.0894316466639443e-05,
      "loss": 0.5367,
      "step": 30751
    },
    {
      "epoch": 0.9446748379565632,
      "grad_norm": 0.35769328474998474,
      "learning_rate": 1.0893835124769367e-05,
      "loss": 0.5259,
      "step": 30752
    },
    {
      "epoch": 0.9447055570915123,
      "grad_norm": 0.35556861758232117,
      "learning_rate": 1.0893353780811677e-05,
      "loss": 0.5785,
      "step": 30753
    },
    {
      "epoch": 0.9447362762264615,
      "grad_norm": 0.474855899810791,
      "learning_rate": 1.0892872434767501e-05,
      "loss": 0.4606,
      "step": 30754
    },
    {
      "epoch": 0.9447669953614106,
      "grad_norm": 0.34195569157600403,
      "learning_rate": 1.0892391086637955e-05,
      "loss": 0.492,
      "step": 30755
    },
    {
      "epoch": 0.9447977144963597,
      "grad_norm": 0.36304664611816406,
      "learning_rate": 1.0891909736424169e-05,
      "loss": 0.5814,
      "step": 30756
    },
    {
      "epoch": 0.944828433631309,
      "grad_norm": 0.3815009295940399,
      "learning_rate": 1.0891428384127265e-05,
      "loss": 0.5233,
      "step": 30757
    },
    {
      "epoch": 0.9448591527662581,
      "grad_norm": 0.38864272832870483,
      "learning_rate": 1.089094702974837e-05,
      "loss": 0.546,
      "step": 30758
    },
    {
      "epoch": 0.9448898719012072,
      "grad_norm": 0.3925333023071289,
      "learning_rate": 1.0890465673288602e-05,
      "loss": 0.5727,
      "step": 30759
    },
    {
      "epoch": 0.9449205910361564,
      "grad_norm": 0.36815911531448364,
      "learning_rate": 1.0889984314749092e-05,
      "loss": 0.5659,
      "step": 30760
    },
    {
      "epoch": 0.9449513101711056,
      "grad_norm": 0.38197362422943115,
      "learning_rate": 1.0889502954130961e-05,
      "loss": 0.5537,
      "step": 30761
    },
    {
      "epoch": 0.9449820293060548,
      "grad_norm": 0.35442760586738586,
      "learning_rate": 1.0889021591435332e-05,
      "loss": 0.5588,
      "step": 30762
    },
    {
      "epoch": 0.9450127484410039,
      "grad_norm": 0.3832736909389496,
      "learning_rate": 1.0888540226663334e-05,
      "loss": 0.4952,
      "step": 30763
    },
    {
      "epoch": 0.945043467575953,
      "grad_norm": 0.4046028256416321,
      "learning_rate": 1.0888058859816086e-05,
      "loss": 0.5475,
      "step": 30764
    },
    {
      "epoch": 0.9450741867109023,
      "grad_norm": 0.3734009563922882,
      "learning_rate": 1.0887577490894717e-05,
      "loss": 0.5675,
      "step": 30765
    },
    {
      "epoch": 0.9451049058458514,
      "grad_norm": 0.4119701385498047,
      "learning_rate": 1.0887096119900345e-05,
      "loss": 0.523,
      "step": 30766
    },
    {
      "epoch": 0.9451356249808005,
      "grad_norm": 0.3440074026584625,
      "learning_rate": 1.0886614746834101e-05,
      "loss": 0.5819,
      "step": 30767
    },
    {
      "epoch": 0.9451663441157497,
      "grad_norm": 0.38046497106552124,
      "learning_rate": 1.0886133371697103e-05,
      "loss": 0.4392,
      "step": 30768
    },
    {
      "epoch": 0.9451970632506989,
      "grad_norm": 0.3558594286441803,
      "learning_rate": 1.0885651994490483e-05,
      "loss": 0.5645,
      "step": 30769
    },
    {
      "epoch": 0.945227782385648,
      "grad_norm": 0.3685606122016907,
      "learning_rate": 1.0885170615215358e-05,
      "loss": 0.507,
      "step": 30770
    },
    {
      "epoch": 0.9452585015205972,
      "grad_norm": 0.35258328914642334,
      "learning_rate": 1.0884689233872853e-05,
      "loss": 0.5212,
      "step": 30771
    },
    {
      "epoch": 0.9452892206555463,
      "grad_norm": 0.4346478581428528,
      "learning_rate": 1.0884207850464099e-05,
      "loss": 0.562,
      "step": 30772
    },
    {
      "epoch": 0.9453199397904954,
      "grad_norm": 0.4406599998474121,
      "learning_rate": 1.0883726464990214e-05,
      "loss": 0.5902,
      "step": 30773
    },
    {
      "epoch": 0.9453506589254447,
      "grad_norm": 0.3500063717365265,
      "learning_rate": 1.0883245077452324e-05,
      "loss": 0.5501,
      "step": 30774
    },
    {
      "epoch": 0.9453813780603938,
      "grad_norm": 0.4959089457988739,
      "learning_rate": 1.0882763687851554e-05,
      "loss": 0.6084,
      "step": 30775
    },
    {
      "epoch": 0.945412097195343,
      "grad_norm": 0.537386953830719,
      "learning_rate": 1.0882282296189029e-05,
      "loss": 0.5818,
      "step": 30776
    },
    {
      "epoch": 0.9454428163302921,
      "grad_norm": 0.49674904346466064,
      "learning_rate": 1.088180090246587e-05,
      "loss": 0.5293,
      "step": 30777
    },
    {
      "epoch": 0.9454735354652413,
      "grad_norm": 0.3675539493560791,
      "learning_rate": 1.0881319506683205e-05,
      "loss": 0.5649,
      "step": 30778
    },
    {
      "epoch": 0.9455042546001905,
      "grad_norm": 0.5166592001914978,
      "learning_rate": 1.0880838108842155e-05,
      "loss": 0.5106,
      "step": 30779
    },
    {
      "epoch": 0.9455349737351396,
      "grad_norm": 0.3945609927177429,
      "learning_rate": 1.0880356708943847e-05,
      "loss": 0.502,
      "step": 30780
    },
    {
      "epoch": 0.9455656928700887,
      "grad_norm": 0.3702213764190674,
      "learning_rate": 1.0879875306989405e-05,
      "loss": 0.5555,
      "step": 30781
    },
    {
      "epoch": 0.945596412005038,
      "grad_norm": 0.40363165736198425,
      "learning_rate": 1.0879393902979952e-05,
      "loss": 0.5664,
      "step": 30782
    },
    {
      "epoch": 0.9456271311399871,
      "grad_norm": 0.3684442937374115,
      "learning_rate": 1.0878912496916613e-05,
      "loss": 0.5317,
      "step": 30783
    },
    {
      "epoch": 0.9456578502749362,
      "grad_norm": 0.3604065179824829,
      "learning_rate": 1.0878431088800512e-05,
      "loss": 0.593,
      "step": 30784
    },
    {
      "epoch": 0.9456885694098854,
      "grad_norm": 0.6360969543457031,
      "learning_rate": 1.0877949678632777e-05,
      "loss": 0.529,
      "step": 30785
    },
    {
      "epoch": 0.9457192885448346,
      "grad_norm": 0.41391491889953613,
      "learning_rate": 1.0877468266414526e-05,
      "loss": 0.4774,
      "step": 30786
    },
    {
      "epoch": 0.9457500076797838,
      "grad_norm": 0.365797758102417,
      "learning_rate": 1.0876986852146886e-05,
      "loss": 0.5158,
      "step": 30787
    },
    {
      "epoch": 0.9457807268147329,
      "grad_norm": 0.3944757878780365,
      "learning_rate": 1.0876505435830985e-05,
      "loss": 0.6236,
      "step": 30788
    },
    {
      "epoch": 0.945811445949682,
      "grad_norm": 0.3921526372432709,
      "learning_rate": 1.0876024017467942e-05,
      "loss": 0.5708,
      "step": 30789
    },
    {
      "epoch": 0.9458421650846313,
      "grad_norm": 0.38548731803894043,
      "learning_rate": 1.0875542597058884e-05,
      "loss": 0.536,
      "step": 30790
    },
    {
      "epoch": 0.9458728842195804,
      "grad_norm": 0.38636600971221924,
      "learning_rate": 1.0875061174604934e-05,
      "loss": 0.5988,
      "step": 30791
    },
    {
      "epoch": 0.9459036033545295,
      "grad_norm": 0.42805007100105286,
      "learning_rate": 1.0874579750107221e-05,
      "loss": 0.5322,
      "step": 30792
    },
    {
      "epoch": 0.9459343224894787,
      "grad_norm": 0.3599318563938141,
      "learning_rate": 1.0874098323566861e-05,
      "loss": 0.5701,
      "step": 30793
    },
    {
      "epoch": 0.9459650416244278,
      "grad_norm": 0.3465520739555359,
      "learning_rate": 1.087361689498499e-05,
      "loss": 0.5698,
      "step": 30794
    },
    {
      "epoch": 0.945995760759377,
      "grad_norm": 0.3748539686203003,
      "learning_rate": 1.0873135464362718e-05,
      "loss": 0.5525,
      "step": 30795
    },
    {
      "epoch": 0.9460264798943262,
      "grad_norm": 0.34569424390792847,
      "learning_rate": 1.0872654031701185e-05,
      "loss": 0.5627,
      "step": 30796
    },
    {
      "epoch": 0.9460571990292753,
      "grad_norm": 0.3614463210105896,
      "learning_rate": 1.0872172597001505e-05,
      "loss": 0.5297,
      "step": 30797
    },
    {
      "epoch": 0.9460879181642246,
      "grad_norm": 0.38440608978271484,
      "learning_rate": 1.0871691160264802e-05,
      "loss": 0.5501,
      "step": 30798
    },
    {
      "epoch": 0.9461186372991737,
      "grad_norm": 0.39415857195854187,
      "learning_rate": 1.0871209721492207e-05,
      "loss": 0.5994,
      "step": 30799
    },
    {
      "epoch": 0.9461493564341228,
      "grad_norm": 0.3998890817165375,
      "learning_rate": 1.0870728280684837e-05,
      "loss": 0.5854,
      "step": 30800
    },
    {
      "epoch": 0.946180075569072,
      "grad_norm": 0.38441187143325806,
      "learning_rate": 1.0870246837843823e-05,
      "loss": 0.5379,
      "step": 30801
    },
    {
      "epoch": 0.9462107947040211,
      "grad_norm": 0.3825955390930176,
      "learning_rate": 1.0869765392970283e-05,
      "loss": 0.5308,
      "step": 30802
    },
    {
      "epoch": 0.9462415138389703,
      "grad_norm": 0.3708370625972748,
      "learning_rate": 1.086928394606535e-05,
      "loss": 0.5746,
      "step": 30803
    },
    {
      "epoch": 0.9462722329739195,
      "grad_norm": 0.39425474405288696,
      "learning_rate": 1.0868802497130142e-05,
      "loss": 0.5709,
      "step": 30804
    },
    {
      "epoch": 0.9463029521088686,
      "grad_norm": 0.430525004863739,
      "learning_rate": 1.0868321046165786e-05,
      "loss": 0.5649,
      "step": 30805
    },
    {
      "epoch": 0.9463336712438177,
      "grad_norm": 0.357363224029541,
      "learning_rate": 1.0867839593173403e-05,
      "loss": 0.5741,
      "step": 30806
    },
    {
      "epoch": 0.946364390378767,
      "grad_norm": 0.37563878297805786,
      "learning_rate": 1.086735813815412e-05,
      "loss": 0.568,
      "step": 30807
    },
    {
      "epoch": 0.9463951095137161,
      "grad_norm": 1.2520571947097778,
      "learning_rate": 1.0866876681109064e-05,
      "loss": 0.5641,
      "step": 30808
    },
    {
      "epoch": 0.9464258286486652,
      "grad_norm": 0.38165706396102905,
      "learning_rate": 1.0866395222039355e-05,
      "loss": 0.5742,
      "step": 30809
    },
    {
      "epoch": 0.9464565477836144,
      "grad_norm": 0.43859684467315674,
      "learning_rate": 1.086591376094612e-05,
      "loss": 0.5575,
      "step": 30810
    },
    {
      "epoch": 0.9464872669185636,
      "grad_norm": 0.39867863059043884,
      "learning_rate": 1.0865432297830483e-05,
      "loss": 0.5563,
      "step": 30811
    },
    {
      "epoch": 0.9465179860535128,
      "grad_norm": 0.4017806649208069,
      "learning_rate": 1.086495083269357e-05,
      "loss": 0.5604,
      "step": 30812
    },
    {
      "epoch": 0.9465487051884619,
      "grad_norm": 0.38888779282569885,
      "learning_rate": 1.0864469365536504e-05,
      "loss": 0.5783,
      "step": 30813
    },
    {
      "epoch": 0.946579424323411,
      "grad_norm": 0.3396161198616028,
      "learning_rate": 1.0863987896360406e-05,
      "loss": 0.534,
      "step": 30814
    },
    {
      "epoch": 0.9466101434583603,
      "grad_norm": 0.36972159147262573,
      "learning_rate": 1.0863506425166407e-05,
      "loss": 0.5674,
      "step": 30815
    },
    {
      "epoch": 0.9466408625933094,
      "grad_norm": 0.4062753915786743,
      "learning_rate": 1.0863024951955628e-05,
      "loss": 0.5699,
      "step": 30816
    },
    {
      "epoch": 0.9466715817282585,
      "grad_norm": 0.35333114862442017,
      "learning_rate": 1.0862543476729195e-05,
      "loss": 0.521,
      "step": 30817
    },
    {
      "epoch": 0.9467023008632077,
      "grad_norm": 0.39264345169067383,
      "learning_rate": 1.0862061999488228e-05,
      "loss": 0.4942,
      "step": 30818
    },
    {
      "epoch": 0.9467330199981568,
      "grad_norm": 0.3768382966518402,
      "learning_rate": 1.0861580520233858e-05,
      "loss": 0.5135,
      "step": 30819
    },
    {
      "epoch": 0.946763739133106,
      "grad_norm": 0.38220781087875366,
      "learning_rate": 1.0861099038967204e-05,
      "loss": 0.5434,
      "step": 30820
    },
    {
      "epoch": 0.9467944582680552,
      "grad_norm": 0.37298721075057983,
      "learning_rate": 1.0860617555689394e-05,
      "loss": 0.5633,
      "step": 30821
    },
    {
      "epoch": 0.9468251774030043,
      "grad_norm": 0.3746001124382019,
      "learning_rate": 1.0860136070401553e-05,
      "loss": 0.4882,
      "step": 30822
    },
    {
      "epoch": 0.9468558965379535,
      "grad_norm": 0.34808748960494995,
      "learning_rate": 1.0859654583104804e-05,
      "loss": 0.5367,
      "step": 30823
    },
    {
      "epoch": 0.9468866156729027,
      "grad_norm": 0.39319562911987305,
      "learning_rate": 1.0859173093800273e-05,
      "loss": 0.5484,
      "step": 30824
    },
    {
      "epoch": 0.9469173348078518,
      "grad_norm": 0.34816837310791016,
      "learning_rate": 1.0858691602489077e-05,
      "loss": 0.5578,
      "step": 30825
    },
    {
      "epoch": 0.946948053942801,
      "grad_norm": 0.35941609740257263,
      "learning_rate": 1.0858210109172352e-05,
      "loss": 0.5909,
      "step": 30826
    },
    {
      "epoch": 0.9469787730777501,
      "grad_norm": 0.38683420419692993,
      "learning_rate": 1.0857728613851215e-05,
      "loss": 0.468,
      "step": 30827
    },
    {
      "epoch": 0.9470094922126993,
      "grad_norm": 0.36542654037475586,
      "learning_rate": 1.0857247116526794e-05,
      "loss": 0.5695,
      "step": 30828
    },
    {
      "epoch": 0.9470402113476485,
      "grad_norm": 0.37170901894569397,
      "learning_rate": 1.0856765617200212e-05,
      "loss": 0.6178,
      "step": 30829
    },
    {
      "epoch": 0.9470709304825976,
      "grad_norm": 0.3401474356651306,
      "learning_rate": 1.0856284115872595e-05,
      "loss": 0.4959,
      "step": 30830
    },
    {
      "epoch": 0.9471016496175467,
      "grad_norm": 0.37856990098953247,
      "learning_rate": 1.0855802612545068e-05,
      "loss": 0.4816,
      "step": 30831
    },
    {
      "epoch": 0.947132368752496,
      "grad_norm": 0.38005298376083374,
      "learning_rate": 1.0855321107218752e-05,
      "loss": 0.4635,
      "step": 30832
    },
    {
      "epoch": 0.9471630878874451,
      "grad_norm": 0.3534003496170044,
      "learning_rate": 1.0854839599894776e-05,
      "loss": 0.5216,
      "step": 30833
    },
    {
      "epoch": 0.9471938070223942,
      "grad_norm": 0.38012373447418213,
      "learning_rate": 1.085435809057426e-05,
      "loss": 0.5819,
      "step": 30834
    },
    {
      "epoch": 0.9472245261573434,
      "grad_norm": 0.34466177225112915,
      "learning_rate": 1.0853876579258333e-05,
      "loss": 0.5866,
      "step": 30835
    },
    {
      "epoch": 0.9472552452922925,
      "grad_norm": 0.32831907272338867,
      "learning_rate": 1.0853395065948113e-05,
      "loss": 0.4584,
      "step": 30836
    },
    {
      "epoch": 0.9472859644272418,
      "grad_norm": 0.37011852860450745,
      "learning_rate": 1.0852913550644734e-05,
      "loss": 0.5666,
      "step": 30837
    },
    {
      "epoch": 0.9473166835621909,
      "grad_norm": 0.3392943739891052,
      "learning_rate": 1.0852432033349314e-05,
      "loss": 0.5249,
      "step": 30838
    },
    {
      "epoch": 0.94734740269714,
      "grad_norm": 0.38693496584892273,
      "learning_rate": 1.0851950514062981e-05,
      "loss": 0.5691,
      "step": 30839
    },
    {
      "epoch": 0.9473781218320892,
      "grad_norm": 0.4698086380958557,
      "learning_rate": 1.0851468992786858e-05,
      "loss": 0.5186,
      "step": 30840
    },
    {
      "epoch": 0.9474088409670384,
      "grad_norm": 0.4185049831867218,
      "learning_rate": 1.0850987469522068e-05,
      "loss": 0.6051,
      "step": 30841
    },
    {
      "epoch": 0.9474395601019875,
      "grad_norm": 0.4219761788845062,
      "learning_rate": 1.085050594426974e-05,
      "loss": 0.5556,
      "step": 30842
    },
    {
      "epoch": 0.9474702792369367,
      "grad_norm": 0.32831040024757385,
      "learning_rate": 1.0850024417030991e-05,
      "loss": 0.5813,
      "step": 30843
    },
    {
      "epoch": 0.9475009983718858,
      "grad_norm": 0.5203371644020081,
      "learning_rate": 1.0849542887806955e-05,
      "loss": 0.5656,
      "step": 30844
    },
    {
      "epoch": 0.947531717506835,
      "grad_norm": 0.3890923261642456,
      "learning_rate": 1.0849061356598749e-05,
      "loss": 0.5553,
      "step": 30845
    },
    {
      "epoch": 0.9475624366417842,
      "grad_norm": 0.3956112265586853,
      "learning_rate": 1.0848579823407503e-05,
      "loss": 0.5053,
      "step": 30846
    },
    {
      "epoch": 0.9475931557767333,
      "grad_norm": 0.3891233205795288,
      "learning_rate": 1.084809828823434e-05,
      "loss": 0.6278,
      "step": 30847
    },
    {
      "epoch": 0.9476238749116825,
      "grad_norm": 0.3502945005893707,
      "learning_rate": 1.0847616751080384e-05,
      "loss": 0.5304,
      "step": 30848
    },
    {
      "epoch": 0.9476545940466317,
      "grad_norm": 0.3877919614315033,
      "learning_rate": 1.084713521194676e-05,
      "loss": 0.6233,
      "step": 30849
    },
    {
      "epoch": 0.9476853131815808,
      "grad_norm": 0.3559962809085846,
      "learning_rate": 1.084665367083459e-05,
      "loss": 0.5837,
      "step": 30850
    },
    {
      "epoch": 0.94771603231653,
      "grad_norm": 0.37164273858070374,
      "learning_rate": 1.0846172127745004e-05,
      "loss": 0.4871,
      "step": 30851
    },
    {
      "epoch": 0.9477467514514791,
      "grad_norm": 0.4073159694671631,
      "learning_rate": 1.0845690582679122e-05,
      "loss": 0.5196,
      "step": 30852
    },
    {
      "epoch": 0.9477774705864283,
      "grad_norm": 0.3453143537044525,
      "learning_rate": 1.0845209035638073e-05,
      "loss": 0.5977,
      "step": 30853
    },
    {
      "epoch": 0.9478081897213775,
      "grad_norm": 0.42367732524871826,
      "learning_rate": 1.084472748662298e-05,
      "loss": 0.5732,
      "step": 30854
    },
    {
      "epoch": 0.9478389088563266,
      "grad_norm": 0.36757591366767883,
      "learning_rate": 1.0844245935634965e-05,
      "loss": 0.5139,
      "step": 30855
    },
    {
      "epoch": 0.9478696279912757,
      "grad_norm": 0.3743816316127777,
      "learning_rate": 1.0843764382675153e-05,
      "loss": 0.536,
      "step": 30856
    },
    {
      "epoch": 0.947900347126225,
      "grad_norm": 0.37106308341026306,
      "learning_rate": 1.0843282827744673e-05,
      "loss": 0.5705,
      "step": 30857
    },
    {
      "epoch": 0.9479310662611741,
      "grad_norm": 0.40849408507347107,
      "learning_rate": 1.0842801270844645e-05,
      "loss": 0.565,
      "step": 30858
    },
    {
      "epoch": 0.9479617853961232,
      "grad_norm": 0.3713688850402832,
      "learning_rate": 1.0842319711976197e-05,
      "loss": 0.5016,
      "step": 30859
    },
    {
      "epoch": 0.9479925045310724,
      "grad_norm": 0.36145952343940735,
      "learning_rate": 1.0841838151140453e-05,
      "loss": 0.5674,
      "step": 30860
    },
    {
      "epoch": 0.9480232236660215,
      "grad_norm": 0.3769175708293915,
      "learning_rate": 1.0841356588338537e-05,
      "loss": 0.5747,
      "step": 30861
    },
    {
      "epoch": 0.9480539428009708,
      "grad_norm": 0.3778441548347473,
      "learning_rate": 1.0840875023571571e-05,
      "loss": 0.5585,
      "step": 30862
    },
    {
      "epoch": 0.9480846619359199,
      "grad_norm": 0.35089170932769775,
      "learning_rate": 1.0840393456840686e-05,
      "loss": 0.4725,
      "step": 30863
    },
    {
      "epoch": 0.948115381070869,
      "grad_norm": 0.5021405816078186,
      "learning_rate": 1.0839911888147001e-05,
      "loss": 0.6247,
      "step": 30864
    },
    {
      "epoch": 0.9481461002058182,
      "grad_norm": 0.3611185550689697,
      "learning_rate": 1.0839430317491646e-05,
      "loss": 0.5467,
      "step": 30865
    },
    {
      "epoch": 0.9481768193407674,
      "grad_norm": 0.42122790217399597,
      "learning_rate": 1.0838948744875741e-05,
      "loss": 0.5368,
      "step": 30866
    },
    {
      "epoch": 0.9482075384757165,
      "grad_norm": 0.38480815291404724,
      "learning_rate": 1.0838467170300415e-05,
      "loss": 0.5316,
      "step": 30867
    },
    {
      "epoch": 0.9482382576106657,
      "grad_norm": 0.3519192636013031,
      "learning_rate": 1.0837985593766787e-05,
      "loss": 0.4874,
      "step": 30868
    },
    {
      "epoch": 0.9482689767456148,
      "grad_norm": 0.34229815006256104,
      "learning_rate": 1.0837504015275989e-05,
      "loss": 0.5842,
      "step": 30869
    },
    {
      "epoch": 0.948299695880564,
      "grad_norm": 0.3751688003540039,
      "learning_rate": 1.0837022434829136e-05,
      "loss": 0.468,
      "step": 30870
    },
    {
      "epoch": 0.9483304150155132,
      "grad_norm": 0.41560089588165283,
      "learning_rate": 1.0836540852427364e-05,
      "loss": 0.4928,
      "step": 30871
    },
    {
      "epoch": 0.9483611341504623,
      "grad_norm": 0.3451233208179474,
      "learning_rate": 1.0836059268071788e-05,
      "loss": 0.5064,
      "step": 30872
    },
    {
      "epoch": 0.9483918532854115,
      "grad_norm": 0.4089796543121338,
      "learning_rate": 1.0835577681763543e-05,
      "loss": 0.6016,
      "step": 30873
    },
    {
      "epoch": 0.9484225724203607,
      "grad_norm": 0.5191814303398132,
      "learning_rate": 1.0835096093503743e-05,
      "loss": 0.504,
      "step": 30874
    },
    {
      "epoch": 0.9484532915553098,
      "grad_norm": 0.38024112582206726,
      "learning_rate": 1.0834614503293519e-05,
      "loss": 0.486,
      "step": 30875
    },
    {
      "epoch": 0.948484010690259,
      "grad_norm": 0.38176390528678894,
      "learning_rate": 1.0834132911133994e-05,
      "loss": 0.5295,
      "step": 30876
    },
    {
      "epoch": 0.9485147298252081,
      "grad_norm": 0.355461984872818,
      "learning_rate": 1.0833651317026297e-05,
      "loss": 0.5174,
      "step": 30877
    },
    {
      "epoch": 0.9485454489601572,
      "grad_norm": 0.4096698462963104,
      "learning_rate": 1.0833169720971546e-05,
      "loss": 0.5736,
      "step": 30878
    },
    {
      "epoch": 0.9485761680951065,
      "grad_norm": 0.38363775610923767,
      "learning_rate": 1.0832688122970869e-05,
      "loss": 0.5046,
      "step": 30879
    },
    {
      "epoch": 0.9486068872300556,
      "grad_norm": 0.4012843370437622,
      "learning_rate": 1.083220652302539e-05,
      "loss": 0.4949,
      "step": 30880
    },
    {
      "epoch": 0.9486376063650047,
      "grad_norm": 0.41232892870903015,
      "learning_rate": 1.0831724921136235e-05,
      "loss": 0.6238,
      "step": 30881
    },
    {
      "epoch": 0.948668325499954,
      "grad_norm": 0.379808634519577,
      "learning_rate": 1.0831243317304529e-05,
      "loss": 0.5991,
      "step": 30882
    },
    {
      "epoch": 0.9486990446349031,
      "grad_norm": 0.37171101570129395,
      "learning_rate": 1.0830761711531397e-05,
      "loss": 0.5858,
      "step": 30883
    },
    {
      "epoch": 0.9487297637698522,
      "grad_norm": 0.47273218631744385,
      "learning_rate": 1.0830280103817961e-05,
      "loss": 0.584,
      "step": 30884
    },
    {
      "epoch": 0.9487604829048014,
      "grad_norm": 0.42394542694091797,
      "learning_rate": 1.0829798494165351e-05,
      "loss": 0.5406,
      "step": 30885
    },
    {
      "epoch": 0.9487912020397505,
      "grad_norm": 0.5417384505271912,
      "learning_rate": 1.0829316882574685e-05,
      "loss": 0.4411,
      "step": 30886
    },
    {
      "epoch": 0.9488219211746998,
      "grad_norm": 0.3566627502441406,
      "learning_rate": 1.0828835269047096e-05,
      "loss": 0.6008,
      "step": 30887
    },
    {
      "epoch": 0.9488526403096489,
      "grad_norm": 0.3553386926651001,
      "learning_rate": 1.0828353653583698e-05,
      "loss": 0.6158,
      "step": 30888
    },
    {
      "epoch": 0.948883359444598,
      "grad_norm": 0.3821137845516205,
      "learning_rate": 1.0827872036185627e-05,
      "loss": 0.5678,
      "step": 30889
    },
    {
      "epoch": 0.9489140785795472,
      "grad_norm": 0.46718865633010864,
      "learning_rate": 1.0827390416854e-05,
      "loss": 0.5011,
      "step": 30890
    },
    {
      "epoch": 0.9489447977144964,
      "grad_norm": 0.3752416968345642,
      "learning_rate": 1.082690879558995e-05,
      "loss": 0.5971,
      "step": 30891
    },
    {
      "epoch": 0.9489755168494455,
      "grad_norm": 0.381106436252594,
      "learning_rate": 1.0826427172394592e-05,
      "loss": 0.6055,
      "step": 30892
    },
    {
      "epoch": 0.9490062359843947,
      "grad_norm": 0.3784431219100952,
      "learning_rate": 1.0825945547269057e-05,
      "loss": 0.5045,
      "step": 30893
    },
    {
      "epoch": 0.9490369551193438,
      "grad_norm": 0.40219590067863464,
      "learning_rate": 1.082546392021447e-05,
      "loss": 0.502,
      "step": 30894
    },
    {
      "epoch": 0.949067674254293,
      "grad_norm": 0.37085556983947754,
      "learning_rate": 1.0824982291231951e-05,
      "loss": 0.6095,
      "step": 30895
    },
    {
      "epoch": 0.9490983933892422,
      "grad_norm": 0.38054779171943665,
      "learning_rate": 1.0824500660322633e-05,
      "loss": 0.5684,
      "step": 30896
    },
    {
      "epoch": 0.9491291125241913,
      "grad_norm": 0.40322959423065186,
      "learning_rate": 1.082401902748763e-05,
      "loss": 0.5979,
      "step": 30897
    },
    {
      "epoch": 0.9491598316591405,
      "grad_norm": 0.4010585844516754,
      "learning_rate": 1.0823537392728076e-05,
      "loss": 0.5882,
      "step": 30898
    },
    {
      "epoch": 0.9491905507940896,
      "grad_norm": 0.4444984197616577,
      "learning_rate": 1.0823055756045092e-05,
      "loss": 0.5629,
      "step": 30899
    },
    {
      "epoch": 0.9492212699290388,
      "grad_norm": 0.3968735933303833,
      "learning_rate": 1.0822574117439806e-05,
      "loss": 0.5655,
      "step": 30900
    },
    {
      "epoch": 0.949251989063988,
      "grad_norm": 0.39215174317359924,
      "learning_rate": 1.082209247691334e-05,
      "loss": 0.5762,
      "step": 30901
    },
    {
      "epoch": 0.9492827081989371,
      "grad_norm": 0.37365272641181946,
      "learning_rate": 1.0821610834466818e-05,
      "loss": 0.5672,
      "step": 30902
    },
    {
      "epoch": 0.9493134273338862,
      "grad_norm": 0.38274842500686646,
      "learning_rate": 1.082112919010137e-05,
      "loss": 0.5454,
      "step": 30903
    },
    {
      "epoch": 0.9493441464688355,
      "grad_norm": 0.38718533515930176,
      "learning_rate": 1.0820647543818115e-05,
      "loss": 0.5757,
      "step": 30904
    },
    {
      "epoch": 0.9493748656037846,
      "grad_norm": 0.38718634843826294,
      "learning_rate": 1.082016589561818e-05,
      "loss": 0.5017,
      "step": 30905
    },
    {
      "epoch": 0.9494055847387337,
      "grad_norm": 0.3836512565612793,
      "learning_rate": 1.0819684245502691e-05,
      "loss": 0.54,
      "step": 30906
    },
    {
      "epoch": 0.9494363038736829,
      "grad_norm": 0.36414843797683716,
      "learning_rate": 1.0819202593472772e-05,
      "loss": 0.63,
      "step": 30907
    },
    {
      "epoch": 0.9494670230086321,
      "grad_norm": 0.38565129041671753,
      "learning_rate": 1.0818720939529548e-05,
      "loss": 0.5487,
      "step": 30908
    },
    {
      "epoch": 0.9494977421435813,
      "grad_norm": 0.3537083864212036,
      "learning_rate": 1.0818239283674145e-05,
      "loss": 0.5167,
      "step": 30909
    },
    {
      "epoch": 0.9495284612785304,
      "grad_norm": 0.4190846383571625,
      "learning_rate": 1.0817757625907686e-05,
      "loss": 0.5863,
      "step": 30910
    },
    {
      "epoch": 0.9495591804134795,
      "grad_norm": 0.3769286572933197,
      "learning_rate": 1.0817275966231297e-05,
      "loss": 0.6037,
      "step": 30911
    },
    {
      "epoch": 0.9495898995484288,
      "grad_norm": 0.375468373298645,
      "learning_rate": 1.0816794304646104e-05,
      "loss": 0.6385,
      "step": 30912
    },
    {
      "epoch": 0.9496206186833779,
      "grad_norm": 0.4135298728942871,
      "learning_rate": 1.0816312641153229e-05,
      "loss": 0.517,
      "step": 30913
    },
    {
      "epoch": 0.949651337818327,
      "grad_norm": 0.37074559926986694,
      "learning_rate": 1.0815830975753801e-05,
      "loss": 0.5291,
      "step": 30914
    },
    {
      "epoch": 0.9496820569532762,
      "grad_norm": 0.3413192331790924,
      "learning_rate": 1.0815349308448939e-05,
      "loss": 0.5391,
      "step": 30915
    },
    {
      "epoch": 0.9497127760882254,
      "grad_norm": 0.38806870579719543,
      "learning_rate": 1.0814867639239775e-05,
      "loss": 0.5667,
      "step": 30916
    },
    {
      "epoch": 0.9497434952231745,
      "grad_norm": 0.5278379321098328,
      "learning_rate": 1.0814385968127427e-05,
      "loss": 0.5868,
      "step": 30917
    },
    {
      "epoch": 0.9497742143581237,
      "grad_norm": 0.34025296568870544,
      "learning_rate": 1.0813904295113029e-05,
      "loss": 0.4902,
      "step": 30918
    },
    {
      "epoch": 0.9498049334930728,
      "grad_norm": 0.36522406339645386,
      "learning_rate": 1.08134226201977e-05,
      "loss": 0.5744,
      "step": 30919
    },
    {
      "epoch": 0.9498356526280219,
      "grad_norm": 0.40396592020988464,
      "learning_rate": 1.0812940943382561e-05,
      "loss": 0.5802,
      "step": 30920
    },
    {
      "epoch": 0.9498663717629712,
      "grad_norm": 0.3551875650882721,
      "learning_rate": 1.0812459264668746e-05,
      "loss": 0.5456,
      "step": 30921
    },
    {
      "epoch": 0.9498970908979203,
      "grad_norm": 0.3771699368953705,
      "learning_rate": 1.0811977584057374e-05,
      "loss": 0.5916,
      "step": 30922
    },
    {
      "epoch": 0.9499278100328695,
      "grad_norm": 0.4529913663864136,
      "learning_rate": 1.0811495901549573e-05,
      "loss": 0.5713,
      "step": 30923
    },
    {
      "epoch": 0.9499585291678186,
      "grad_norm": 0.3813149034976959,
      "learning_rate": 1.0811014217146464e-05,
      "loss": 0.6139,
      "step": 30924
    },
    {
      "epoch": 0.9499892483027678,
      "grad_norm": 0.3374125361442566,
      "learning_rate": 1.0810532530849179e-05,
      "loss": 0.4998,
      "step": 30925
    },
    {
      "epoch": 0.950019967437717,
      "grad_norm": 0.3609704077243805,
      "learning_rate": 1.0810050842658835e-05,
      "loss": 0.4985,
      "step": 30926
    },
    {
      "epoch": 0.9500506865726661,
      "grad_norm": 0.40962982177734375,
      "learning_rate": 1.0809569152576562e-05,
      "loss": 0.5052,
      "step": 30927
    },
    {
      "epoch": 0.9500814057076152,
      "grad_norm": 0.4080347716808319,
      "learning_rate": 1.0809087460603482e-05,
      "loss": 0.5781,
      "step": 30928
    },
    {
      "epoch": 0.9501121248425645,
      "grad_norm": 0.45644158124923706,
      "learning_rate": 1.0808605766740724e-05,
      "loss": 0.5164,
      "step": 30929
    },
    {
      "epoch": 0.9501428439775136,
      "grad_norm": 0.37348800897598267,
      "learning_rate": 1.0808124070989413e-05,
      "loss": 0.6234,
      "step": 30930
    },
    {
      "epoch": 0.9501735631124627,
      "grad_norm": 0.3790205121040344,
      "learning_rate": 1.0807642373350666e-05,
      "loss": 0.5205,
      "step": 30931
    },
    {
      "epoch": 0.9502042822474119,
      "grad_norm": 0.35059595108032227,
      "learning_rate": 1.0807160673825617e-05,
      "loss": 0.602,
      "step": 30932
    },
    {
      "epoch": 0.950235001382361,
      "grad_norm": 0.39221686124801636,
      "learning_rate": 1.0806678972415385e-05,
      "loss": 0.5605,
      "step": 30933
    },
    {
      "epoch": 0.9502657205173103,
      "grad_norm": 0.3685643672943115,
      "learning_rate": 1.0806197269121102e-05,
      "loss": 0.549,
      "step": 30934
    },
    {
      "epoch": 0.9502964396522594,
      "grad_norm": 0.3706153333187103,
      "learning_rate": 1.0805715563943886e-05,
      "loss": 0.5472,
      "step": 30935
    },
    {
      "epoch": 0.9503271587872085,
      "grad_norm": 0.36282363533973694,
      "learning_rate": 1.0805233856884865e-05,
      "loss": 0.4787,
      "step": 30936
    },
    {
      "epoch": 0.9503578779221578,
      "grad_norm": 0.3842688202857971,
      "learning_rate": 1.0804752147945167e-05,
      "loss": 0.4754,
      "step": 30937
    },
    {
      "epoch": 0.9503885970571069,
      "grad_norm": 0.36942124366760254,
      "learning_rate": 1.0804270437125912e-05,
      "loss": 0.588,
      "step": 30938
    },
    {
      "epoch": 0.950419316192056,
      "grad_norm": 0.4372921586036682,
      "learning_rate": 1.0803788724428228e-05,
      "loss": 0.6241,
      "step": 30939
    },
    {
      "epoch": 0.9504500353270052,
      "grad_norm": 0.3549700975418091,
      "learning_rate": 1.0803307009853239e-05,
      "loss": 0.5405,
      "step": 30940
    },
    {
      "epoch": 0.9504807544619543,
      "grad_norm": 0.3994918465614319,
      "learning_rate": 1.080282529340207e-05,
      "loss": 0.5243,
      "step": 30941
    },
    {
      "epoch": 0.9505114735969035,
      "grad_norm": 0.47728633880615234,
      "learning_rate": 1.0802343575075846e-05,
      "loss": 0.5556,
      "step": 30942
    },
    {
      "epoch": 0.9505421927318527,
      "grad_norm": 0.34720802307128906,
      "learning_rate": 1.0801861854875695e-05,
      "loss": 0.4975,
      "step": 30943
    },
    {
      "epoch": 0.9505729118668018,
      "grad_norm": 0.37236812710762024,
      "learning_rate": 1.0801380132802736e-05,
      "loss": 0.5435,
      "step": 30944
    },
    {
      "epoch": 0.9506036310017509,
      "grad_norm": 0.40105491876602173,
      "learning_rate": 1.0800898408858102e-05,
      "loss": 0.6174,
      "step": 30945
    },
    {
      "epoch": 0.9506343501367002,
      "grad_norm": 0.42225512862205505,
      "learning_rate": 1.0800416683042911e-05,
      "loss": 0.5442,
      "step": 30946
    },
    {
      "epoch": 0.9506650692716493,
      "grad_norm": 0.39088818430900574,
      "learning_rate": 1.0799934955358291e-05,
      "loss": 0.5234,
      "step": 30947
    },
    {
      "epoch": 0.9506957884065985,
      "grad_norm": 0.3738718330860138,
      "learning_rate": 1.079945322580537e-05,
      "loss": 0.5049,
      "step": 30948
    },
    {
      "epoch": 0.9507265075415476,
      "grad_norm": 0.3710094094276428,
      "learning_rate": 1.0798971494385266e-05,
      "loss": 0.554,
      "step": 30949
    },
    {
      "epoch": 0.9507572266764968,
      "grad_norm": 0.355217844247818,
      "learning_rate": 1.0798489761099112e-05,
      "loss": 0.5337,
      "step": 30950
    },
    {
      "epoch": 0.950787945811446,
      "grad_norm": 0.38979461789131165,
      "learning_rate": 1.0798008025948025e-05,
      "loss": 0.6029,
      "step": 30951
    },
    {
      "epoch": 0.9508186649463951,
      "grad_norm": 0.3462592661380768,
      "learning_rate": 1.0797526288933137e-05,
      "loss": 0.5142,
      "step": 30952
    },
    {
      "epoch": 0.9508493840813442,
      "grad_norm": 0.3972148895263672,
      "learning_rate": 1.0797044550055571e-05,
      "loss": 0.5401,
      "step": 30953
    },
    {
      "epoch": 0.9508801032162935,
      "grad_norm": 0.37774044275283813,
      "learning_rate": 1.0796562809316451e-05,
      "loss": 0.5053,
      "step": 30954
    },
    {
      "epoch": 0.9509108223512426,
      "grad_norm": 0.3407493233680725,
      "learning_rate": 1.0796081066716904e-05,
      "loss": 0.5791,
      "step": 30955
    },
    {
      "epoch": 0.9509415414861917,
      "grad_norm": 0.4368727207183838,
      "learning_rate": 1.0795599322258053e-05,
      "loss": 0.582,
      "step": 30956
    },
    {
      "epoch": 0.9509722606211409,
      "grad_norm": 0.40769559144973755,
      "learning_rate": 1.0795117575941022e-05,
      "loss": 0.5361,
      "step": 30957
    },
    {
      "epoch": 0.95100297975609,
      "grad_norm": 0.34875115752220154,
      "learning_rate": 1.0794635827766941e-05,
      "loss": 0.5038,
      "step": 30958
    },
    {
      "epoch": 0.9510336988910393,
      "grad_norm": 0.37398770451545715,
      "learning_rate": 1.0794154077736937e-05,
      "loss": 0.5996,
      "step": 30959
    },
    {
      "epoch": 0.9510644180259884,
      "grad_norm": 0.35486823320388794,
      "learning_rate": 1.0793672325852123e-05,
      "loss": 0.4876,
      "step": 30960
    },
    {
      "epoch": 0.9510951371609375,
      "grad_norm": 0.38553789258003235,
      "learning_rate": 1.0793190572113637e-05,
      "loss": 0.5738,
      "step": 30961
    },
    {
      "epoch": 0.9511258562958868,
      "grad_norm": 1.3310694694519043,
      "learning_rate": 1.0792708816522595e-05,
      "loss": 0.5561,
      "step": 30962
    },
    {
      "epoch": 0.9511565754308359,
      "grad_norm": 0.40530306100845337,
      "learning_rate": 1.079222705908013e-05,
      "loss": 0.6066,
      "step": 30963
    },
    {
      "epoch": 0.951187294565785,
      "grad_norm": 0.35542547702789307,
      "learning_rate": 1.0791745299787362e-05,
      "loss": 0.5,
      "step": 30964
    },
    {
      "epoch": 0.9512180137007342,
      "grad_norm": 0.4095938503742218,
      "learning_rate": 1.0791263538645415e-05,
      "loss": 0.506,
      "step": 30965
    },
    {
      "epoch": 0.9512487328356833,
      "grad_norm": 0.41990503668785095,
      "learning_rate": 1.0790781775655422e-05,
      "loss": 0.6299,
      "step": 30966
    },
    {
      "epoch": 0.9512794519706325,
      "grad_norm": 0.3851116895675659,
      "learning_rate": 1.0790300010818497e-05,
      "loss": 0.5764,
      "step": 30967
    },
    {
      "epoch": 0.9513101711055817,
      "grad_norm": 0.5524551868438721,
      "learning_rate": 1.0789818244135777e-05,
      "loss": 0.5293,
      "step": 30968
    },
    {
      "epoch": 0.9513408902405308,
      "grad_norm": 0.5793049931526184,
      "learning_rate": 1.0789336475608377e-05,
      "loss": 0.548,
      "step": 30969
    },
    {
      "epoch": 0.9513716093754799,
      "grad_norm": 0.6024867296218872,
      "learning_rate": 1.0788854705237428e-05,
      "loss": 0.6463,
      "step": 30970
    },
    {
      "epoch": 0.9514023285104292,
      "grad_norm": 1.3629859685897827,
      "learning_rate": 1.0788372933024052e-05,
      "loss": 0.4293,
      "step": 30971
    },
    {
      "epoch": 0.9514330476453783,
      "grad_norm": 0.38339847326278687,
      "learning_rate": 1.0787891158969378e-05,
      "loss": 0.5568,
      "step": 30972
    },
    {
      "epoch": 0.9514637667803275,
      "grad_norm": 0.3673935532569885,
      "learning_rate": 1.0787409383074529e-05,
      "loss": 0.532,
      "step": 30973
    },
    {
      "epoch": 0.9514944859152766,
      "grad_norm": 0.3607647716999054,
      "learning_rate": 1.078692760534063e-05,
      "loss": 0.5708,
      "step": 30974
    },
    {
      "epoch": 0.9515252050502258,
      "grad_norm": 0.35404273867607117,
      "learning_rate": 1.0786445825768807e-05,
      "loss": 0.5188,
      "step": 30975
    },
    {
      "epoch": 0.951555924185175,
      "grad_norm": 0.3698168694972992,
      "learning_rate": 1.0785964044360182e-05,
      "loss": 0.5737,
      "step": 30976
    },
    {
      "epoch": 0.9515866433201241,
      "grad_norm": 0.3860945999622345,
      "learning_rate": 1.0785482261115888e-05,
      "loss": 0.5207,
      "step": 30977
    },
    {
      "epoch": 0.9516173624550732,
      "grad_norm": 0.4588707983493805,
      "learning_rate": 1.0785000476037042e-05,
      "loss": 0.5623,
      "step": 30978
    },
    {
      "epoch": 0.9516480815900225,
      "grad_norm": 0.4128292500972748,
      "learning_rate": 1.0784518689124775e-05,
      "loss": 0.6081,
      "step": 30979
    },
    {
      "epoch": 0.9516788007249716,
      "grad_norm": 0.48906612396240234,
      "learning_rate": 1.0784036900380206e-05,
      "loss": 0.6055,
      "step": 30980
    },
    {
      "epoch": 0.9517095198599207,
      "grad_norm": 0.3795595169067383,
      "learning_rate": 1.0783555109804469e-05,
      "loss": 0.5491,
      "step": 30981
    },
    {
      "epoch": 0.9517402389948699,
      "grad_norm": 0.41110214591026306,
      "learning_rate": 1.0783073317398683e-05,
      "loss": 0.5164,
      "step": 30982
    },
    {
      "epoch": 0.951770958129819,
      "grad_norm": 0.3734653890132904,
      "learning_rate": 1.078259152316397e-05,
      "loss": 0.5991,
      "step": 30983
    },
    {
      "epoch": 0.9518016772647683,
      "grad_norm": 0.3675665855407715,
      "learning_rate": 1.0782109727101467e-05,
      "loss": 0.5192,
      "step": 30984
    },
    {
      "epoch": 0.9518323963997174,
      "grad_norm": 0.3482363224029541,
      "learning_rate": 1.0781627929212286e-05,
      "loss": 0.5227,
      "step": 30985
    },
    {
      "epoch": 0.9518631155346665,
      "grad_norm": 0.5390978455543518,
      "learning_rate": 1.0781146129497561e-05,
      "loss": 0.5726,
      "step": 30986
    },
    {
      "epoch": 0.9518938346696157,
      "grad_norm": 0.5234819054603577,
      "learning_rate": 1.0780664327958413e-05,
      "loss": 0.5463,
      "step": 30987
    },
    {
      "epoch": 0.9519245538045649,
      "grad_norm": 0.41684797406196594,
      "learning_rate": 1.0780182524595973e-05,
      "loss": 0.5678,
      "step": 30988
    },
    {
      "epoch": 0.951955272939514,
      "grad_norm": 0.3566279113292694,
      "learning_rate": 1.0779700719411357e-05,
      "loss": 0.5812,
      "step": 30989
    },
    {
      "epoch": 0.9519859920744632,
      "grad_norm": 0.33322274684906006,
      "learning_rate": 1.0779218912405698e-05,
      "loss": 0.521,
      "step": 30990
    },
    {
      "epoch": 0.9520167112094123,
      "grad_norm": 0.3635595142841339,
      "learning_rate": 1.0778737103580119e-05,
      "loss": 0.5,
      "step": 30991
    },
    {
      "epoch": 0.9520474303443615,
      "grad_norm": 0.374435693025589,
      "learning_rate": 1.0778255292935745e-05,
      "loss": 0.5973,
      "step": 30992
    },
    {
      "epoch": 0.9520781494793107,
      "grad_norm": 0.4385298788547516,
      "learning_rate": 1.0777773480473701e-05,
      "loss": 0.5203,
      "step": 30993
    },
    {
      "epoch": 0.9521088686142598,
      "grad_norm": 0.3397486209869385,
      "learning_rate": 1.077729166619511e-05,
      "loss": 0.4835,
      "step": 30994
    },
    {
      "epoch": 0.952139587749209,
      "grad_norm": 0.31903403997421265,
      "learning_rate": 1.0776809850101107e-05,
      "loss": 0.4989,
      "step": 30995
    },
    {
      "epoch": 0.9521703068841582,
      "grad_norm": 0.4623032510280609,
      "learning_rate": 1.0776328032192804e-05,
      "loss": 0.5527,
      "step": 30996
    },
    {
      "epoch": 0.9522010260191073,
      "grad_norm": 0.3519303798675537,
      "learning_rate": 1.0775846212471337e-05,
      "loss": 0.5841,
      "step": 30997
    },
    {
      "epoch": 0.9522317451540565,
      "grad_norm": 0.3923332095146179,
      "learning_rate": 1.0775364390937826e-05,
      "loss": 0.5565,
      "step": 30998
    },
    {
      "epoch": 0.9522624642890056,
      "grad_norm": 0.3302658200263977,
      "learning_rate": 1.0774882567593395e-05,
      "loss": 0.5102,
      "step": 30999
    },
    {
      "epoch": 0.9522931834239547,
      "grad_norm": 0.5237910747528076,
      "learning_rate": 1.0774400742439176e-05,
      "loss": 0.5526,
      "step": 31000
    },
    {
      "epoch": 0.952323902558904,
      "grad_norm": 0.39163893461227417,
      "learning_rate": 1.0773918915476285e-05,
      "loss": 0.5363,
      "step": 31001
    },
    {
      "epoch": 0.9523546216938531,
      "grad_norm": 0.3617075979709625,
      "learning_rate": 1.0773437086705854e-05,
      "loss": 0.5873,
      "step": 31002
    },
    {
      "epoch": 0.9523853408288022,
      "grad_norm": 0.36217838525772095,
      "learning_rate": 1.0772955256129008e-05,
      "loss": 0.4849,
      "step": 31003
    },
    {
      "epoch": 0.9524160599637514,
      "grad_norm": 0.38370147347450256,
      "learning_rate": 1.077247342374687e-05,
      "loss": 0.5889,
      "step": 31004
    },
    {
      "epoch": 0.9524467790987006,
      "grad_norm": 0.40930983424186707,
      "learning_rate": 1.0771991589560564e-05,
      "loss": 0.5681,
      "step": 31005
    },
    {
      "epoch": 0.9524774982336497,
      "grad_norm": 0.3676809072494507,
      "learning_rate": 1.0771509753571223e-05,
      "loss": 0.5152,
      "step": 31006
    },
    {
      "epoch": 0.9525082173685989,
      "grad_norm": 0.3903096914291382,
      "learning_rate": 1.0771027915779962e-05,
      "loss": 0.5962,
      "step": 31007
    },
    {
      "epoch": 0.952538936503548,
      "grad_norm": 0.41065743565559387,
      "learning_rate": 1.0770546076187914e-05,
      "loss": 0.6267,
      "step": 31008
    },
    {
      "epoch": 0.9525696556384973,
      "grad_norm": 0.3601507544517517,
      "learning_rate": 1.07700642347962e-05,
      "loss": 0.4774,
      "step": 31009
    },
    {
      "epoch": 0.9526003747734464,
      "grad_norm": 0.36511093378067017,
      "learning_rate": 1.0769582391605949e-05,
      "loss": 0.5602,
      "step": 31010
    },
    {
      "epoch": 0.9526310939083955,
      "grad_norm": 0.36941829323768616,
      "learning_rate": 1.0769100546618286e-05,
      "loss": 0.5243,
      "step": 31011
    },
    {
      "epoch": 0.9526618130433447,
      "grad_norm": 0.44703564047813416,
      "learning_rate": 1.0768618699834332e-05,
      "loss": 0.5197,
      "step": 31012
    },
    {
      "epoch": 0.9526925321782939,
      "grad_norm": 0.34644606709480286,
      "learning_rate": 1.0768136851255218e-05,
      "loss": 0.5097,
      "step": 31013
    },
    {
      "epoch": 0.952723251313243,
      "grad_norm": 0.36371251940727234,
      "learning_rate": 1.0767655000882062e-05,
      "loss": 0.5846,
      "step": 31014
    },
    {
      "epoch": 0.9527539704481922,
      "grad_norm": 0.3661706745624542,
      "learning_rate": 1.0767173148715999e-05,
      "loss": 0.5753,
      "step": 31015
    },
    {
      "epoch": 0.9527846895831413,
      "grad_norm": 0.3599836826324463,
      "learning_rate": 1.0766691294758148e-05,
      "loss": 0.5966,
      "step": 31016
    },
    {
      "epoch": 0.9528154087180905,
      "grad_norm": 0.3794582784175873,
      "learning_rate": 1.0766209439009636e-05,
      "loss": 0.5155,
      "step": 31017
    },
    {
      "epoch": 0.9528461278530397,
      "grad_norm": 0.474394291639328,
      "learning_rate": 1.076572758147159e-05,
      "loss": 0.554,
      "step": 31018
    },
    {
      "epoch": 0.9528768469879888,
      "grad_norm": 0.4326396584510803,
      "learning_rate": 1.076524572214513e-05,
      "loss": 0.4917,
      "step": 31019
    },
    {
      "epoch": 0.952907566122938,
      "grad_norm": 0.36827903985977173,
      "learning_rate": 1.076476386103139e-05,
      "loss": 0.5768,
      "step": 31020
    },
    {
      "epoch": 0.9529382852578872,
      "grad_norm": 0.3426353931427002,
      "learning_rate": 1.0764281998131485e-05,
      "loss": 0.5188,
      "step": 31021
    },
    {
      "epoch": 0.9529690043928363,
      "grad_norm": 0.34185877442359924,
      "learning_rate": 1.0763800133446551e-05,
      "loss": 0.5245,
      "step": 31022
    },
    {
      "epoch": 0.9529997235277855,
      "grad_norm": 0.42596349120140076,
      "learning_rate": 1.0763318266977705e-05,
      "loss": 0.4824,
      "step": 31023
    },
    {
      "epoch": 0.9530304426627346,
      "grad_norm": 0.46154919266700745,
      "learning_rate": 1.0762836398726077e-05,
      "loss": 0.4264,
      "step": 31024
    },
    {
      "epoch": 0.9530611617976837,
      "grad_norm": 0.38565388321876526,
      "learning_rate": 1.0762354528692792e-05,
      "loss": 0.4503,
      "step": 31025
    },
    {
      "epoch": 0.953091880932633,
      "grad_norm": 0.34229665994644165,
      "learning_rate": 1.0761872656878971e-05,
      "loss": 0.5313,
      "step": 31026
    },
    {
      "epoch": 0.9531226000675821,
      "grad_norm": 0.3626265823841095,
      "learning_rate": 1.0761390783285748e-05,
      "loss": 0.5622,
      "step": 31027
    },
    {
      "epoch": 0.9531533192025312,
      "grad_norm": 0.43914955854415894,
      "learning_rate": 1.0760908907914242e-05,
      "loss": 0.6465,
      "step": 31028
    },
    {
      "epoch": 0.9531840383374804,
      "grad_norm": 0.3192178010940552,
      "learning_rate": 1.0760427030765582e-05,
      "loss": 0.5019,
      "step": 31029
    },
    {
      "epoch": 0.9532147574724296,
      "grad_norm": 0.36597269773483276,
      "learning_rate": 1.0759945151840888e-05,
      "loss": 0.4591,
      "step": 31030
    },
    {
      "epoch": 0.9532454766073787,
      "grad_norm": 0.45514678955078125,
      "learning_rate": 1.075946327114129e-05,
      "loss": 0.5218,
      "step": 31031
    },
    {
      "epoch": 0.9532761957423279,
      "grad_norm": 0.35683944821357727,
      "learning_rate": 1.0758981388667913e-05,
      "loss": 0.564,
      "step": 31032
    },
    {
      "epoch": 0.953306914877277,
      "grad_norm": 0.39912697672843933,
      "learning_rate": 1.0758499504421884e-05,
      "loss": 0.5235,
      "step": 31033
    },
    {
      "epoch": 0.9533376340122263,
      "grad_norm": 0.334819495677948,
      "learning_rate": 1.0758017618404326e-05,
      "loss": 0.5945,
      "step": 31034
    },
    {
      "epoch": 0.9533683531471754,
      "grad_norm": 0.40810495615005493,
      "learning_rate": 1.0757535730616362e-05,
      "loss": 0.5342,
      "step": 31035
    },
    {
      "epoch": 0.9533990722821245,
      "grad_norm": 0.38793641328811646,
      "learning_rate": 1.0757053841059123e-05,
      "loss": 0.5975,
      "step": 31036
    },
    {
      "epoch": 0.9534297914170737,
      "grad_norm": 0.4117545187473297,
      "learning_rate": 1.0756571949733729e-05,
      "loss": 0.5469,
      "step": 31037
    },
    {
      "epoch": 0.9534605105520229,
      "grad_norm": 0.3754781484603882,
      "learning_rate": 1.0756090056641311e-05,
      "loss": 0.6148,
      "step": 31038
    },
    {
      "epoch": 0.953491229686972,
      "grad_norm": 0.35030680894851685,
      "learning_rate": 1.075560816178299e-05,
      "loss": 0.4898,
      "step": 31039
    },
    {
      "epoch": 0.9535219488219212,
      "grad_norm": 0.47073888778686523,
      "learning_rate": 1.0755126265159896e-05,
      "loss": 0.5989,
      "step": 31040
    },
    {
      "epoch": 0.9535526679568703,
      "grad_norm": 0.37108463048934937,
      "learning_rate": 1.0754644366773151e-05,
      "loss": 0.5317,
      "step": 31041
    },
    {
      "epoch": 0.9535833870918194,
      "grad_norm": 0.5055146217346191,
      "learning_rate": 1.0754162466623882e-05,
      "loss": 0.5458,
      "step": 31042
    },
    {
      "epoch": 0.9536141062267687,
      "grad_norm": 0.3737885057926178,
      "learning_rate": 1.0753680564713209e-05,
      "loss": 0.53,
      "step": 31043
    },
    {
      "epoch": 0.9536448253617178,
      "grad_norm": 0.35530543327331543,
      "learning_rate": 1.0753198661042266e-05,
      "loss": 0.5207,
      "step": 31044
    },
    {
      "epoch": 0.953675544496667,
      "grad_norm": 0.3642294406890869,
      "learning_rate": 1.0752716755612176e-05,
      "loss": 0.5585,
      "step": 31045
    },
    {
      "epoch": 0.9537062636316161,
      "grad_norm": 0.3617432713508606,
      "learning_rate": 1.0752234848424061e-05,
      "loss": 0.5052,
      "step": 31046
    },
    {
      "epoch": 0.9537369827665653,
      "grad_norm": 0.3821350038051605,
      "learning_rate": 1.075175293947905e-05,
      "loss": 0.5941,
      "step": 31047
    },
    {
      "epoch": 0.9537677019015145,
      "grad_norm": 0.3533734083175659,
      "learning_rate": 1.0751271028778267e-05,
      "loss": 0.5998,
      "step": 31048
    },
    {
      "epoch": 0.9537984210364636,
      "grad_norm": 0.36095690727233887,
      "learning_rate": 1.075078911632284e-05,
      "loss": 0.5433,
      "step": 31049
    },
    {
      "epoch": 0.9538291401714127,
      "grad_norm": 0.4086596667766571,
      "learning_rate": 1.0750307202113893e-05,
      "loss": 0.5026,
      "step": 31050
    },
    {
      "epoch": 0.953859859306362,
      "grad_norm": 0.38475295901298523,
      "learning_rate": 1.074982528615255e-05,
      "loss": 0.5033,
      "step": 31051
    },
    {
      "epoch": 0.9538905784413111,
      "grad_norm": 0.37277552485466003,
      "learning_rate": 1.0749343368439937e-05,
      "loss": 0.5188,
      "step": 31052
    },
    {
      "epoch": 0.9539212975762602,
      "grad_norm": 0.42490410804748535,
      "learning_rate": 1.074886144897718e-05,
      "loss": 0.6137,
      "step": 31053
    },
    {
      "epoch": 0.9539520167112094,
      "grad_norm": 0.35291436314582825,
      "learning_rate": 1.0748379527765404e-05,
      "loss": 0.5365,
      "step": 31054
    },
    {
      "epoch": 0.9539827358461586,
      "grad_norm": 0.3947669565677643,
      "learning_rate": 1.0747897604805737e-05,
      "loss": 0.5262,
      "step": 31055
    },
    {
      "epoch": 0.9540134549811077,
      "grad_norm": 0.35671401023864746,
      "learning_rate": 1.0747415680099302e-05,
      "loss": 0.5634,
      "step": 31056
    },
    {
      "epoch": 0.9540441741160569,
      "grad_norm": 0.3493051826953888,
      "learning_rate": 1.0746933753647227e-05,
      "loss": 0.537,
      "step": 31057
    },
    {
      "epoch": 0.954074893251006,
      "grad_norm": 0.34591493010520935,
      "learning_rate": 1.0746451825450635e-05,
      "loss": 0.5009,
      "step": 31058
    },
    {
      "epoch": 0.9541056123859553,
      "grad_norm": 0.36736592650413513,
      "learning_rate": 1.0745969895510652e-05,
      "loss": 0.5417,
      "step": 31059
    },
    {
      "epoch": 0.9541363315209044,
      "grad_norm": 0.40323376655578613,
      "learning_rate": 1.0745487963828408e-05,
      "loss": 0.5871,
      "step": 31060
    },
    {
      "epoch": 0.9541670506558535,
      "grad_norm": 0.3677736520767212,
      "learning_rate": 1.0745006030405021e-05,
      "loss": 0.5425,
      "step": 31061
    },
    {
      "epoch": 0.9541977697908027,
      "grad_norm": 0.37404665350914,
      "learning_rate": 1.0744524095241617e-05,
      "loss": 0.6127,
      "step": 31062
    },
    {
      "epoch": 0.9542284889257518,
      "grad_norm": 0.3697444498538971,
      "learning_rate": 1.0744042158339332e-05,
      "loss": 0.5496,
      "step": 31063
    },
    {
      "epoch": 0.954259208060701,
      "grad_norm": 0.3573072552680969,
      "learning_rate": 1.0743560219699278e-05,
      "loss": 0.5034,
      "step": 31064
    },
    {
      "epoch": 0.9542899271956502,
      "grad_norm": 0.38660964369773865,
      "learning_rate": 1.0743078279322594e-05,
      "loss": 0.5313,
      "step": 31065
    },
    {
      "epoch": 0.9543206463305993,
      "grad_norm": 0.3655413091182709,
      "learning_rate": 1.0742596337210393e-05,
      "loss": 0.6189,
      "step": 31066
    },
    {
      "epoch": 0.9543513654655484,
      "grad_norm": 0.39382922649383545,
      "learning_rate": 1.0742114393363812e-05,
      "loss": 0.5727,
      "step": 31067
    },
    {
      "epoch": 0.9543820846004977,
      "grad_norm": 0.42909032106399536,
      "learning_rate": 1.0741632447783967e-05,
      "loss": 0.5323,
      "step": 31068
    },
    {
      "epoch": 0.9544128037354468,
      "grad_norm": 0.38690218329429626,
      "learning_rate": 1.0741150500471988e-05,
      "loss": 0.518,
      "step": 31069
    },
    {
      "epoch": 0.954443522870396,
      "grad_norm": 0.35824382305145264,
      "learning_rate": 1.0740668551429004e-05,
      "loss": 0.5567,
      "step": 31070
    },
    {
      "epoch": 0.9544742420053451,
      "grad_norm": 0.3571988344192505,
      "learning_rate": 1.0740186600656131e-05,
      "loss": 0.6099,
      "step": 31071
    },
    {
      "epoch": 0.9545049611402943,
      "grad_norm": 0.36972352862358093,
      "learning_rate": 1.0739704648154503e-05,
      "loss": 0.5454,
      "step": 31072
    },
    {
      "epoch": 0.9545356802752435,
      "grad_norm": 0.3783293664455414,
      "learning_rate": 1.0739222693925244e-05,
      "loss": 0.4876,
      "step": 31073
    },
    {
      "epoch": 0.9545663994101926,
      "grad_norm": 0.3639947474002838,
      "learning_rate": 1.0738740737969477e-05,
      "loss": 0.5029,
      "step": 31074
    },
    {
      "epoch": 0.9545971185451417,
      "grad_norm": 0.3684832453727722,
      "learning_rate": 1.073825878028833e-05,
      "loss": 0.5868,
      "step": 31075
    },
    {
      "epoch": 0.954627837680091,
      "grad_norm": 0.3908505439758301,
      "learning_rate": 1.073777682088293e-05,
      "loss": 0.5761,
      "step": 31076
    },
    {
      "epoch": 0.9546585568150401,
      "grad_norm": 0.39796268939971924,
      "learning_rate": 1.07372948597544e-05,
      "loss": 0.5164,
      "step": 31077
    },
    {
      "epoch": 0.9546892759499892,
      "grad_norm": 0.4063141345977783,
      "learning_rate": 1.0736812896903865e-05,
      "loss": 0.5804,
      "step": 31078
    },
    {
      "epoch": 0.9547199950849384,
      "grad_norm": 0.3271752595901489,
      "learning_rate": 1.0736330932332454e-05,
      "loss": 0.5427,
      "step": 31079
    },
    {
      "epoch": 0.9547507142198876,
      "grad_norm": 0.3891965448856354,
      "learning_rate": 1.073584896604129e-05,
      "loss": 0.5576,
      "step": 31080
    },
    {
      "epoch": 0.9547814333548367,
      "grad_norm": 0.3719733953475952,
      "learning_rate": 1.0735366998031496e-05,
      "loss": 0.5433,
      "step": 31081
    },
    {
      "epoch": 0.9548121524897859,
      "grad_norm": 0.418241024017334,
      "learning_rate": 1.0734885028304202e-05,
      "loss": 0.5817,
      "step": 31082
    },
    {
      "epoch": 0.954842871624735,
      "grad_norm": 0.367776483297348,
      "learning_rate": 1.0734403056860536e-05,
      "loss": 0.5449,
      "step": 31083
    },
    {
      "epoch": 0.9548735907596843,
      "grad_norm": 0.7414613366127014,
      "learning_rate": 1.0733921083701617e-05,
      "loss": 0.6168,
      "step": 31084
    },
    {
      "epoch": 0.9549043098946334,
      "grad_norm": 0.37466633319854736,
      "learning_rate": 1.0733439108828578e-05,
      "loss": 0.5515,
      "step": 31085
    },
    {
      "epoch": 0.9549350290295825,
      "grad_norm": 0.3651575744152069,
      "learning_rate": 1.0732957132242539e-05,
      "loss": 0.5434,
      "step": 31086
    },
    {
      "epoch": 0.9549657481645317,
      "grad_norm": 0.4150734841823578,
      "learning_rate": 1.0732475153944626e-05,
      "loss": 0.5756,
      "step": 31087
    },
    {
      "epoch": 0.9549964672994808,
      "grad_norm": 0.4145182967185974,
      "learning_rate": 1.0731993173935968e-05,
      "loss": 0.5323,
      "step": 31088
    },
    {
      "epoch": 0.95502718643443,
      "grad_norm": 0.3986591696739197,
      "learning_rate": 1.0731511192217687e-05,
      "loss": 0.6459,
      "step": 31089
    },
    {
      "epoch": 0.9550579055693792,
      "grad_norm": 0.5021080374717712,
      "learning_rate": 1.0731029208790913e-05,
      "loss": 0.5727,
      "step": 31090
    },
    {
      "epoch": 0.9550886247043283,
      "grad_norm": 0.3459963798522949,
      "learning_rate": 1.0730547223656766e-05,
      "loss": 0.4805,
      "step": 31091
    },
    {
      "epoch": 0.9551193438392774,
      "grad_norm": 0.3794079124927521,
      "learning_rate": 1.0730065236816378e-05,
      "loss": 0.5623,
      "step": 31092
    },
    {
      "epoch": 0.9551500629742267,
      "grad_norm": 0.42028912901878357,
      "learning_rate": 1.072958324827087e-05,
      "loss": 0.5187,
      "step": 31093
    },
    {
      "epoch": 0.9551807821091758,
      "grad_norm": 0.36280569434165955,
      "learning_rate": 1.072910125802137e-05,
      "loss": 0.5551,
      "step": 31094
    },
    {
      "epoch": 0.955211501244125,
      "grad_norm": 0.4109530746936798,
      "learning_rate": 1.0728619266069003e-05,
      "loss": 0.4859,
      "step": 31095
    },
    {
      "epoch": 0.9552422203790741,
      "grad_norm": 0.3339897394180298,
      "learning_rate": 1.0728137272414896e-05,
      "loss": 0.4998,
      "step": 31096
    },
    {
      "epoch": 0.9552729395140233,
      "grad_norm": 0.367399126291275,
      "learning_rate": 1.0727655277060172e-05,
      "loss": 0.5763,
      "step": 31097
    },
    {
      "epoch": 0.9553036586489725,
      "grad_norm": 0.3619154691696167,
      "learning_rate": 1.0727173280005957e-05,
      "loss": 0.5249,
      "step": 31098
    },
    {
      "epoch": 0.9553343777839216,
      "grad_norm": 0.3608294725418091,
      "learning_rate": 1.0726691281253379e-05,
      "loss": 0.5534,
      "step": 31099
    },
    {
      "epoch": 0.9553650969188707,
      "grad_norm": 0.38171514868736267,
      "learning_rate": 1.072620928080356e-05,
      "loss": 0.5525,
      "step": 31100
    },
    {
      "epoch": 0.95539581605382,
      "grad_norm": 0.36142656207084656,
      "learning_rate": 1.0725727278657634e-05,
      "loss": 0.5284,
      "step": 31101
    },
    {
      "epoch": 0.9554265351887691,
      "grad_norm": 0.4538683295249939,
      "learning_rate": 1.0725245274816721e-05,
      "loss": 0.5329,
      "step": 31102
    },
    {
      "epoch": 0.9554572543237182,
      "grad_norm": 0.40785178542137146,
      "learning_rate": 1.0724763269281943e-05,
      "loss": 0.4813,
      "step": 31103
    },
    {
      "epoch": 0.9554879734586674,
      "grad_norm": 0.3817589282989502,
      "learning_rate": 1.0724281262054435e-05,
      "loss": 0.5488,
      "step": 31104
    },
    {
      "epoch": 0.9555186925936165,
      "grad_norm": 0.40095341205596924,
      "learning_rate": 1.0723799253135311e-05,
      "loss": 0.5557,
      "step": 31105
    },
    {
      "epoch": 0.9555494117285658,
      "grad_norm": 0.384059876203537,
      "learning_rate": 1.0723317242525708e-05,
      "loss": 0.4778,
      "step": 31106
    },
    {
      "epoch": 0.9555801308635149,
      "grad_norm": 0.35819414258003235,
      "learning_rate": 1.0722835230226744e-05,
      "loss": 0.5715,
      "step": 31107
    },
    {
      "epoch": 0.955610849998464,
      "grad_norm": 0.36972275376319885,
      "learning_rate": 1.0722353216239552e-05,
      "loss": 0.5393,
      "step": 31108
    },
    {
      "epoch": 0.9556415691334132,
      "grad_norm": 0.3692964017391205,
      "learning_rate": 1.0721871200565247e-05,
      "loss": 0.5224,
      "step": 31109
    },
    {
      "epoch": 0.9556722882683624,
      "grad_norm": 0.3484252095222473,
      "learning_rate": 1.0721389183204968e-05,
      "loss": 0.3976,
      "step": 31110
    },
    {
      "epoch": 0.9557030074033115,
      "grad_norm": 0.4097770154476166,
      "learning_rate": 1.072090716415983e-05,
      "loss": 0.5451,
      "step": 31111
    },
    {
      "epoch": 0.9557337265382607,
      "grad_norm": 0.35587674379348755,
      "learning_rate": 1.0720425143430969e-05,
      "loss": 0.5148,
      "step": 31112
    },
    {
      "epoch": 0.9557644456732098,
      "grad_norm": 0.39030206203460693,
      "learning_rate": 1.07199431210195e-05,
      "loss": 0.5867,
      "step": 31113
    },
    {
      "epoch": 0.955795164808159,
      "grad_norm": 0.33973848819732666,
      "learning_rate": 1.0719461096926554e-05,
      "loss": 0.6168,
      "step": 31114
    },
    {
      "epoch": 0.9558258839431082,
      "grad_norm": 0.38966819643974304,
      "learning_rate": 1.0718979071153256e-05,
      "loss": 0.6515,
      "step": 31115
    },
    {
      "epoch": 0.9558566030780573,
      "grad_norm": 0.4711534380912781,
      "learning_rate": 1.0718497043700731e-05,
      "loss": 0.5674,
      "step": 31116
    },
    {
      "epoch": 0.9558873222130064,
      "grad_norm": 0.3775947093963623,
      "learning_rate": 1.0718015014570108e-05,
      "loss": 0.5551,
      "step": 31117
    },
    {
      "epoch": 0.9559180413479557,
      "grad_norm": 0.3504534959793091,
      "learning_rate": 1.071753298376251e-05,
      "loss": 0.544,
      "step": 31118
    },
    {
      "epoch": 0.9559487604829048,
      "grad_norm": 0.39083459973335266,
      "learning_rate": 1.0717050951279062e-05,
      "loss": 0.5057,
      "step": 31119
    },
    {
      "epoch": 0.955979479617854,
      "grad_norm": 0.4404184818267822,
      "learning_rate": 1.0716568917120896e-05,
      "loss": 0.5252,
      "step": 31120
    },
    {
      "epoch": 0.9560101987528031,
      "grad_norm": 0.36017128825187683,
      "learning_rate": 1.0716086881289129e-05,
      "loss": 0.5563,
      "step": 31121
    },
    {
      "epoch": 0.9560409178877523,
      "grad_norm": 0.408235639333725,
      "learning_rate": 1.0715604843784893e-05,
      "loss": 0.5153,
      "step": 31122
    },
    {
      "epoch": 0.9560716370227015,
      "grad_norm": 0.3616859018802643,
      "learning_rate": 1.0715122804609311e-05,
      "loss": 0.5031,
      "step": 31123
    },
    {
      "epoch": 0.9561023561576506,
      "grad_norm": 0.35563409328460693,
      "learning_rate": 1.071464076376351e-05,
      "loss": 0.5001,
      "step": 31124
    },
    {
      "epoch": 0.9561330752925997,
      "grad_norm": 0.3692292869091034,
      "learning_rate": 1.0714158721248616e-05,
      "loss": 0.515,
      "step": 31125
    },
    {
      "epoch": 0.956163794427549,
      "grad_norm": 0.40356799960136414,
      "learning_rate": 1.0713676677065754e-05,
      "loss": 0.5562,
      "step": 31126
    },
    {
      "epoch": 0.9561945135624981,
      "grad_norm": 0.3936729431152344,
      "learning_rate": 1.071319463121605e-05,
      "loss": 0.5605,
      "step": 31127
    },
    {
      "epoch": 0.9562252326974472,
      "grad_norm": 0.37917360663414,
      "learning_rate": 1.0712712583700632e-05,
      "loss": 0.5354,
      "step": 31128
    },
    {
      "epoch": 0.9562559518323964,
      "grad_norm": 0.36767256259918213,
      "learning_rate": 1.0712230534520622e-05,
      "loss": 0.4948,
      "step": 31129
    },
    {
      "epoch": 0.9562866709673455,
      "grad_norm": 0.4002554416656494,
      "learning_rate": 1.0711748483677149e-05,
      "loss": 0.5618,
      "step": 31130
    },
    {
      "epoch": 0.9563173901022948,
      "grad_norm": 0.3604064881801605,
      "learning_rate": 1.0711266431171338e-05,
      "loss": 0.5199,
      "step": 31131
    },
    {
      "epoch": 0.9563481092372439,
      "grad_norm": 0.3642093241214752,
      "learning_rate": 1.0710784377004313e-05,
      "loss": 0.6542,
      "step": 31132
    },
    {
      "epoch": 0.956378828372193,
      "grad_norm": 0.39119064807891846,
      "learning_rate": 1.0710302321177204e-05,
      "loss": 0.5906,
      "step": 31133
    },
    {
      "epoch": 0.9564095475071422,
      "grad_norm": 0.3996908962726593,
      "learning_rate": 1.0709820263691131e-05,
      "loss": 0.5383,
      "step": 31134
    },
    {
      "epoch": 0.9564402666420914,
      "grad_norm": 0.36287838220596313,
      "learning_rate": 1.0709338204547223e-05,
      "loss": 0.4934,
      "step": 31135
    },
    {
      "epoch": 0.9564709857770405,
      "grad_norm": 0.3638654947280884,
      "learning_rate": 1.0708856143746607e-05,
      "loss": 0.568,
      "step": 31136
    },
    {
      "epoch": 0.9565017049119897,
      "grad_norm": 0.3651708960533142,
      "learning_rate": 1.0708374081290409e-05,
      "loss": 0.5024,
      "step": 31137
    },
    {
      "epoch": 0.9565324240469388,
      "grad_norm": 0.39108192920684814,
      "learning_rate": 1.0707892017179755e-05,
      "loss": 0.5342,
      "step": 31138
    },
    {
      "epoch": 0.956563143181888,
      "grad_norm": 0.3625302016735077,
      "learning_rate": 1.0707409951415768e-05,
      "loss": 0.5392,
      "step": 31139
    },
    {
      "epoch": 0.9565938623168372,
      "grad_norm": 0.5079867243766785,
      "learning_rate": 1.0706927883999579e-05,
      "loss": 0.446,
      "step": 31140
    },
    {
      "epoch": 0.9566245814517863,
      "grad_norm": 0.368571400642395,
      "learning_rate": 1.0706445814932306e-05,
      "loss": 0.4762,
      "step": 31141
    },
    {
      "epoch": 0.9566553005867354,
      "grad_norm": 0.35284143686294556,
      "learning_rate": 1.0705963744215081e-05,
      "loss": 0.5413,
      "step": 31142
    },
    {
      "epoch": 0.9566860197216847,
      "grad_norm": 0.38096883893013,
      "learning_rate": 1.0705481671849028e-05,
      "loss": 0.6281,
      "step": 31143
    },
    {
      "epoch": 0.9567167388566338,
      "grad_norm": 0.3574945032596588,
      "learning_rate": 1.0704999597835275e-05,
      "loss": 0.5185,
      "step": 31144
    },
    {
      "epoch": 0.956747457991583,
      "grad_norm": 0.39579108357429504,
      "learning_rate": 1.0704517522174945e-05,
      "loss": 0.5769,
      "step": 31145
    },
    {
      "epoch": 0.9567781771265321,
      "grad_norm": 0.46602070331573486,
      "learning_rate": 1.0704035444869165e-05,
      "loss": 0.587,
      "step": 31146
    },
    {
      "epoch": 0.9568088962614812,
      "grad_norm": 0.4970080554485321,
      "learning_rate": 1.070355336591906e-05,
      "loss": 0.6237,
      "step": 31147
    },
    {
      "epoch": 0.9568396153964305,
      "grad_norm": 0.4302845299243927,
      "learning_rate": 1.0703071285325759e-05,
      "loss": 0.5996,
      "step": 31148
    },
    {
      "epoch": 0.9568703345313796,
      "grad_norm": 0.4191899299621582,
      "learning_rate": 1.0702589203090386e-05,
      "loss": 0.5593,
      "step": 31149
    },
    {
      "epoch": 0.9569010536663287,
      "grad_norm": 0.4484550654888153,
      "learning_rate": 1.0702107119214064e-05,
      "loss": 0.6234,
      "step": 31150
    },
    {
      "epoch": 0.956931772801278,
      "grad_norm": 0.3731340169906616,
      "learning_rate": 1.0701625033697924e-05,
      "loss": 0.4936,
      "step": 31151
    },
    {
      "epoch": 0.9569624919362271,
      "grad_norm": 0.4104960262775421,
      "learning_rate": 1.0701142946543091e-05,
      "loss": 0.5503,
      "step": 31152
    },
    {
      "epoch": 0.9569932110711762,
      "grad_norm": 0.3299347460269928,
      "learning_rate": 1.0700660857750689e-05,
      "loss": 0.5679,
      "step": 31153
    },
    {
      "epoch": 0.9570239302061254,
      "grad_norm": 0.42125409841537476,
      "learning_rate": 1.0700178767321839e-05,
      "loss": 0.5684,
      "step": 31154
    },
    {
      "epoch": 0.9570546493410745,
      "grad_norm": 0.396264910697937,
      "learning_rate": 1.0699696675257679e-05,
      "loss": 0.5263,
      "step": 31155
    },
    {
      "epoch": 0.9570853684760238,
      "grad_norm": 0.3439236581325531,
      "learning_rate": 1.0699214581559327e-05,
      "loss": 0.5236,
      "step": 31156
    },
    {
      "epoch": 0.9571160876109729,
      "grad_norm": 0.3468596935272217,
      "learning_rate": 1.069873248622791e-05,
      "loss": 0.567,
      "step": 31157
    },
    {
      "epoch": 0.957146806745922,
      "grad_norm": 0.3387076258659363,
      "learning_rate": 1.0698250389264556e-05,
      "loss": 0.5726,
      "step": 31158
    },
    {
      "epoch": 0.9571775258808712,
      "grad_norm": 0.3570272624492645,
      "learning_rate": 1.0697768290670388e-05,
      "loss": 0.4543,
      "step": 31159
    },
    {
      "epoch": 0.9572082450158204,
      "grad_norm": 0.4091201722621918,
      "learning_rate": 1.0697286190446534e-05,
      "loss": 0.6373,
      "step": 31160
    },
    {
      "epoch": 0.9572389641507695,
      "grad_norm": 0.34831514954566956,
      "learning_rate": 1.0696804088594117e-05,
      "loss": 0.5589,
      "step": 31161
    },
    {
      "epoch": 0.9572696832857187,
      "grad_norm": 0.34645330905914307,
      "learning_rate": 1.0696321985114268e-05,
      "loss": 0.5493,
      "step": 31162
    },
    {
      "epoch": 0.9573004024206678,
      "grad_norm": 0.3438960015773773,
      "learning_rate": 1.069583988000811e-05,
      "loss": 0.5094,
      "step": 31163
    },
    {
      "epoch": 0.957331121555617,
      "grad_norm": 0.3519696593284607,
      "learning_rate": 1.069535777327677e-05,
      "loss": 0.5094,
      "step": 31164
    },
    {
      "epoch": 0.9573618406905662,
      "grad_norm": 0.3144344091415405,
      "learning_rate": 1.0694875664921372e-05,
      "loss": 0.4798,
      "step": 31165
    },
    {
      "epoch": 0.9573925598255153,
      "grad_norm": 0.363679975271225,
      "learning_rate": 1.0694393554943046e-05,
      "loss": 0.5466,
      "step": 31166
    },
    {
      "epoch": 0.9574232789604644,
      "grad_norm": 0.38615596294403076,
      "learning_rate": 1.0693911443342912e-05,
      "loss": 0.5188,
      "step": 31167
    },
    {
      "epoch": 0.9574539980954136,
      "grad_norm": 0.3939090967178345,
      "learning_rate": 1.06934293301221e-05,
      "loss": 0.5999,
      "step": 31168
    },
    {
      "epoch": 0.9574847172303628,
      "grad_norm": 0.3297935128211975,
      "learning_rate": 1.0692947215281737e-05,
      "loss": 0.4745,
      "step": 31169
    },
    {
      "epoch": 0.957515436365312,
      "grad_norm": 0.3635217547416687,
      "learning_rate": 1.0692465098822947e-05,
      "loss": 0.6292,
      "step": 31170
    },
    {
      "epoch": 0.9575461555002611,
      "grad_norm": 0.7239215970039368,
      "learning_rate": 1.0691982980746855e-05,
      "loss": 0.5553,
      "step": 31171
    },
    {
      "epoch": 0.9575768746352102,
      "grad_norm": 0.3399271070957184,
      "learning_rate": 1.069150086105459e-05,
      "loss": 0.4836,
      "step": 31172
    },
    {
      "epoch": 0.9576075937701595,
      "grad_norm": 0.3971153497695923,
      "learning_rate": 1.0691018739747274e-05,
      "loss": 0.5727,
      "step": 31173
    },
    {
      "epoch": 0.9576383129051086,
      "grad_norm": 0.3430200219154358,
      "learning_rate": 1.0690536616826037e-05,
      "loss": 0.4668,
      "step": 31174
    },
    {
      "epoch": 0.9576690320400577,
      "grad_norm": 0.3712984025478363,
      "learning_rate": 1.0690054492292004e-05,
      "loss": 0.5567,
      "step": 31175
    },
    {
      "epoch": 0.9576997511750069,
      "grad_norm": 0.5242653489112854,
      "learning_rate": 1.0689572366146302e-05,
      "loss": 0.5183,
      "step": 31176
    },
    {
      "epoch": 0.9577304703099561,
      "grad_norm": 0.3577764332294464,
      "learning_rate": 1.0689090238390052e-05,
      "loss": 0.4832,
      "step": 31177
    },
    {
      "epoch": 0.9577611894449052,
      "grad_norm": 0.5000536441802979,
      "learning_rate": 1.0688608109024385e-05,
      "loss": 0.4822,
      "step": 31178
    },
    {
      "epoch": 0.9577919085798544,
      "grad_norm": 0.3390420377254486,
      "learning_rate": 1.0688125978050425e-05,
      "loss": 0.5216,
      "step": 31179
    },
    {
      "epoch": 0.9578226277148035,
      "grad_norm": 0.4083571135997772,
      "learning_rate": 1.0687643845469302e-05,
      "loss": 0.5534,
      "step": 31180
    },
    {
      "epoch": 0.9578533468497528,
      "grad_norm": 0.3600711226463318,
      "learning_rate": 1.0687161711282134e-05,
      "loss": 0.5378,
      "step": 31181
    },
    {
      "epoch": 0.9578840659847019,
      "grad_norm": 0.42300164699554443,
      "learning_rate": 1.0686679575490057e-05,
      "loss": 0.4767,
      "step": 31182
    },
    {
      "epoch": 0.957914785119651,
      "grad_norm": 0.43008291721343994,
      "learning_rate": 1.068619743809419e-05,
      "loss": 0.5286,
      "step": 31183
    },
    {
      "epoch": 0.9579455042546002,
      "grad_norm": 0.3900984525680542,
      "learning_rate": 1.0685715299095661e-05,
      "loss": 0.5527,
      "step": 31184
    },
    {
      "epoch": 0.9579762233895494,
      "grad_norm": 0.47899574041366577,
      "learning_rate": 1.0685233158495596e-05,
      "loss": 0.5348,
      "step": 31185
    },
    {
      "epoch": 0.9580069425244985,
      "grad_norm": 0.4063452184200287,
      "learning_rate": 1.0684751016295119e-05,
      "loss": 0.5992,
      "step": 31186
    },
    {
      "epoch": 0.9580376616594477,
      "grad_norm": 0.34418004751205444,
      "learning_rate": 1.068426887249536e-05,
      "loss": 0.5578,
      "step": 31187
    },
    {
      "epoch": 0.9580683807943968,
      "grad_norm": 0.37643858790397644,
      "learning_rate": 1.0683786727097443e-05,
      "loss": 0.5171,
      "step": 31188
    },
    {
      "epoch": 0.9580990999293459,
      "grad_norm": 0.3899693787097931,
      "learning_rate": 1.0683304580102493e-05,
      "loss": 0.5823,
      "step": 31189
    },
    {
      "epoch": 0.9581298190642952,
      "grad_norm": 0.36122435331344604,
      "learning_rate": 1.0682822431511639e-05,
      "loss": 0.6121,
      "step": 31190
    },
    {
      "epoch": 0.9581605381992443,
      "grad_norm": 0.44431084394454956,
      "learning_rate": 1.0682340281326002e-05,
      "loss": 0.5048,
      "step": 31191
    },
    {
      "epoch": 0.9581912573341934,
      "grad_norm": 0.3539047837257385,
      "learning_rate": 1.0681858129546718e-05,
      "loss": 0.5662,
      "step": 31192
    },
    {
      "epoch": 0.9582219764691426,
      "grad_norm": 0.37932583689689636,
      "learning_rate": 1.0681375976174901e-05,
      "loss": 0.5185,
      "step": 31193
    },
    {
      "epoch": 0.9582526956040918,
      "grad_norm": 0.41849416494369507,
      "learning_rate": 1.0680893821211687e-05,
      "loss": 0.552,
      "step": 31194
    },
    {
      "epoch": 0.958283414739041,
      "grad_norm": 0.35941359400749207,
      "learning_rate": 1.0680411664658194e-05,
      "loss": 0.5362,
      "step": 31195
    },
    {
      "epoch": 0.9583141338739901,
      "grad_norm": 0.31945210695266724,
      "learning_rate": 1.0679929506515557e-05,
      "loss": 0.5791,
      "step": 31196
    },
    {
      "epoch": 0.9583448530089392,
      "grad_norm": 0.40678009390830994,
      "learning_rate": 1.0679447346784892e-05,
      "loss": 0.5712,
      "step": 31197
    },
    {
      "epoch": 0.9583755721438885,
      "grad_norm": 0.3873791992664337,
      "learning_rate": 1.0678965185467333e-05,
      "loss": 0.5926,
      "step": 31198
    },
    {
      "epoch": 0.9584062912788376,
      "grad_norm": 0.3951398730278015,
      "learning_rate": 1.0678483022564004e-05,
      "loss": 0.5294,
      "step": 31199
    },
    {
      "epoch": 0.9584370104137867,
      "grad_norm": 0.3724425733089447,
      "learning_rate": 1.067800085807603e-05,
      "loss": 0.5407,
      "step": 31200
    },
    {
      "epoch": 0.9584677295487359,
      "grad_norm": 0.4112881124019623,
      "learning_rate": 1.0677518692004539e-05,
      "loss": 0.5424,
      "step": 31201
    },
    {
      "epoch": 0.9584984486836851,
      "grad_norm": 0.40565699338912964,
      "learning_rate": 1.0677036524350652e-05,
      "loss": 0.5419,
      "step": 31202
    },
    {
      "epoch": 0.9585291678186342,
      "grad_norm": 0.42522022128105164,
      "learning_rate": 1.0676554355115503e-05,
      "loss": 0.545,
      "step": 31203
    },
    {
      "epoch": 0.9585598869535834,
      "grad_norm": 0.3484309911727905,
      "learning_rate": 1.067607218430021e-05,
      "loss": 0.5767,
      "step": 31204
    },
    {
      "epoch": 0.9585906060885325,
      "grad_norm": 0.354068398475647,
      "learning_rate": 1.0675590011905908e-05,
      "loss": 0.5406,
      "step": 31205
    },
    {
      "epoch": 0.9586213252234818,
      "grad_norm": 0.4337655007839203,
      "learning_rate": 1.0675107837933714e-05,
      "loss": 0.602,
      "step": 31206
    },
    {
      "epoch": 0.9586520443584309,
      "grad_norm": 0.3696839213371277,
      "learning_rate": 1.0674625662384762e-05,
      "loss": 0.4514,
      "step": 31207
    },
    {
      "epoch": 0.95868276349338,
      "grad_norm": 0.37757787108421326,
      "learning_rate": 1.0674143485260169e-05,
      "loss": 0.5718,
      "step": 31208
    },
    {
      "epoch": 0.9587134826283292,
      "grad_norm": 0.3516896963119507,
      "learning_rate": 1.0673661306561069e-05,
      "loss": 0.4962,
      "step": 31209
    },
    {
      "epoch": 0.9587442017632783,
      "grad_norm": 0.39465653896331787,
      "learning_rate": 1.0673179126288588e-05,
      "loss": 0.5584,
      "step": 31210
    },
    {
      "epoch": 0.9587749208982275,
      "grad_norm": 0.3471616804599762,
      "learning_rate": 1.067269694444385e-05,
      "loss": 0.5448,
      "step": 31211
    },
    {
      "epoch": 0.9588056400331767,
      "grad_norm": 0.3962997794151306,
      "learning_rate": 1.067221476102798e-05,
      "loss": 0.554,
      "step": 31212
    },
    {
      "epoch": 0.9588363591681258,
      "grad_norm": 0.38729000091552734,
      "learning_rate": 1.0671732576042107e-05,
      "loss": 0.5405,
      "step": 31213
    },
    {
      "epoch": 0.9588670783030749,
      "grad_norm": 0.33640921115875244,
      "learning_rate": 1.0671250389487356e-05,
      "loss": 0.5183,
      "step": 31214
    },
    {
      "epoch": 0.9588977974380242,
      "grad_norm": 0.4182981848716736,
      "learning_rate": 1.0670768201364852e-05,
      "loss": 0.5879,
      "step": 31215
    },
    {
      "epoch": 0.9589285165729733,
      "grad_norm": 0.39197954535484314,
      "learning_rate": 1.0670286011675721e-05,
      "loss": 0.5439,
      "step": 31216
    },
    {
      "epoch": 0.9589592357079225,
      "grad_norm": 0.3769283890724182,
      "learning_rate": 1.0669803820421092e-05,
      "loss": 0.5693,
      "step": 31217
    },
    {
      "epoch": 0.9589899548428716,
      "grad_norm": 0.3680107891559601,
      "learning_rate": 1.066932162760209e-05,
      "loss": 0.5372,
      "step": 31218
    },
    {
      "epoch": 0.9590206739778208,
      "grad_norm": 0.3899257779121399,
      "learning_rate": 1.066883943321984e-05,
      "loss": 0.579,
      "step": 31219
    },
    {
      "epoch": 0.95905139311277,
      "grad_norm": 0.4734916388988495,
      "learning_rate": 1.0668357237275467e-05,
      "loss": 0.5599,
      "step": 31220
    },
    {
      "epoch": 0.9590821122477191,
      "grad_norm": 0.36482611298561096,
      "learning_rate": 1.06678750397701e-05,
      "loss": 0.4969,
      "step": 31221
    },
    {
      "epoch": 0.9591128313826682,
      "grad_norm": 0.437812864780426,
      "learning_rate": 1.0667392840704863e-05,
      "loss": 0.6634,
      "step": 31222
    },
    {
      "epoch": 0.9591435505176175,
      "grad_norm": 0.3597114384174347,
      "learning_rate": 1.0666910640080886e-05,
      "loss": 0.5275,
      "step": 31223
    },
    {
      "epoch": 0.9591742696525666,
      "grad_norm": 0.3695373833179474,
      "learning_rate": 1.066642843789929e-05,
      "loss": 0.5357,
      "step": 31224
    },
    {
      "epoch": 0.9592049887875157,
      "grad_norm": 0.35906362533569336,
      "learning_rate": 1.0665946234161204e-05,
      "loss": 0.5686,
      "step": 31225
    },
    {
      "epoch": 0.9592357079224649,
      "grad_norm": 0.3392479419708252,
      "learning_rate": 1.0665464028867757e-05,
      "loss": 0.558,
      "step": 31226
    },
    {
      "epoch": 0.959266427057414,
      "grad_norm": 0.4014118015766144,
      "learning_rate": 1.0664981822020066e-05,
      "loss": 0.577,
      "step": 31227
    },
    {
      "epoch": 0.9592971461923632,
      "grad_norm": 0.34549570083618164,
      "learning_rate": 1.066449961361927e-05,
      "loss": 0.521,
      "step": 31228
    },
    {
      "epoch": 0.9593278653273124,
      "grad_norm": 0.3726067543029785,
      "learning_rate": 1.0664017403666485e-05,
      "loss": 0.4754,
      "step": 31229
    },
    {
      "epoch": 0.9593585844622615,
      "grad_norm": 0.3768826127052307,
      "learning_rate": 1.0663535192162844e-05,
      "loss": 0.5152,
      "step": 31230
    },
    {
      "epoch": 0.9593893035972108,
      "grad_norm": 0.3453803062438965,
      "learning_rate": 1.0663052979109467e-05,
      "loss": 0.5252,
      "step": 31231
    },
    {
      "epoch": 0.9594200227321599,
      "grad_norm": 0.37634333968162537,
      "learning_rate": 1.0662570764507488e-05,
      "loss": 0.5155,
      "step": 31232
    },
    {
      "epoch": 0.959450741867109,
      "grad_norm": 0.4971604347229004,
      "learning_rate": 1.0662088548358023e-05,
      "loss": 0.4861,
      "step": 31233
    },
    {
      "epoch": 0.9594814610020582,
      "grad_norm": 0.3878370523452759,
      "learning_rate": 1.0661606330662209e-05,
      "loss": 0.5822,
      "step": 31234
    },
    {
      "epoch": 0.9595121801370073,
      "grad_norm": 0.3863724172115326,
      "learning_rate": 1.0661124111421166e-05,
      "loss": 0.5312,
      "step": 31235
    },
    {
      "epoch": 0.9595428992719565,
      "grad_norm": 0.44514790177345276,
      "learning_rate": 1.066064189063602e-05,
      "loss": 0.5069,
      "step": 31236
    },
    {
      "epoch": 0.9595736184069057,
      "grad_norm": 0.3894006311893463,
      "learning_rate": 1.0660159668307899e-05,
      "loss": 0.5764,
      "step": 31237
    },
    {
      "epoch": 0.9596043375418548,
      "grad_norm": 0.3814907670021057,
      "learning_rate": 1.0659677444437928e-05,
      "loss": 0.5826,
      "step": 31238
    },
    {
      "epoch": 0.9596350566768039,
      "grad_norm": 0.3832489848136902,
      "learning_rate": 1.0659195219027236e-05,
      "loss": 0.5611,
      "step": 31239
    },
    {
      "epoch": 0.9596657758117532,
      "grad_norm": 0.3605572283267975,
      "learning_rate": 1.0658712992076948e-05,
      "loss": 0.5976,
      "step": 31240
    },
    {
      "epoch": 0.9596964949467023,
      "grad_norm": 0.37168827652931213,
      "learning_rate": 1.0658230763588189e-05,
      "loss": 0.4739,
      "step": 31241
    },
    {
      "epoch": 0.9597272140816515,
      "grad_norm": 0.604569137096405,
      "learning_rate": 1.0657748533562084e-05,
      "loss": 0.5661,
      "step": 31242
    },
    {
      "epoch": 0.9597579332166006,
      "grad_norm": 0.3844488263130188,
      "learning_rate": 1.0657266301999764e-05,
      "loss": 0.5334,
      "step": 31243
    },
    {
      "epoch": 0.9597886523515498,
      "grad_norm": 0.3375336527824402,
      "learning_rate": 1.0656784068902353e-05,
      "loss": 0.5727,
      "step": 31244
    },
    {
      "epoch": 0.959819371486499,
      "grad_norm": 0.38923221826553345,
      "learning_rate": 1.0656301834270974e-05,
      "loss": 0.5222,
      "step": 31245
    },
    {
      "epoch": 0.9598500906214481,
      "grad_norm": 0.36969664692878723,
      "learning_rate": 1.0655819598106758e-05,
      "loss": 0.5764,
      "step": 31246
    },
    {
      "epoch": 0.9598808097563972,
      "grad_norm": 0.3323362171649933,
      "learning_rate": 1.0655337360410829e-05,
      "loss": 0.5002,
      "step": 31247
    },
    {
      "epoch": 0.9599115288913465,
      "grad_norm": 0.3293166756629944,
      "learning_rate": 1.0654855121184315e-05,
      "loss": 0.4929,
      "step": 31248
    },
    {
      "epoch": 0.9599422480262956,
      "grad_norm": 0.41125425696372986,
      "learning_rate": 1.065437288042834e-05,
      "loss": 0.5561,
      "step": 31249
    },
    {
      "epoch": 0.9599729671612447,
      "grad_norm": 0.361122727394104,
      "learning_rate": 1.0653890638144034e-05,
      "loss": 0.4779,
      "step": 31250
    },
    {
      "epoch": 0.9600036862961939,
      "grad_norm": 0.3337033987045288,
      "learning_rate": 1.0653408394332518e-05,
      "loss": 0.5806,
      "step": 31251
    },
    {
      "epoch": 0.960034405431143,
      "grad_norm": 0.3735812306404114,
      "learning_rate": 1.0652926148994922e-05,
      "loss": 0.5807,
      "step": 31252
    },
    {
      "epoch": 0.9600651245660922,
      "grad_norm": 0.38690319657325745,
      "learning_rate": 1.0652443902132372e-05,
      "loss": 0.543,
      "step": 31253
    },
    {
      "epoch": 0.9600958437010414,
      "grad_norm": 0.3715425133705139,
      "learning_rate": 1.0651961653745992e-05,
      "loss": 0.4945,
      "step": 31254
    },
    {
      "epoch": 0.9601265628359905,
      "grad_norm": 0.44294771552085876,
      "learning_rate": 1.0651479403836912e-05,
      "loss": 0.5583,
      "step": 31255
    },
    {
      "epoch": 0.9601572819709397,
      "grad_norm": 0.3510442078113556,
      "learning_rate": 1.0650997152406256e-05,
      "loss": 0.4916,
      "step": 31256
    },
    {
      "epoch": 0.9601880011058889,
      "grad_norm": 0.3968023359775543,
      "learning_rate": 1.065051489945515e-05,
      "loss": 0.5689,
      "step": 31257
    },
    {
      "epoch": 0.960218720240838,
      "grad_norm": 0.40577244758605957,
      "learning_rate": 1.065003264498472e-05,
      "loss": 0.5204,
      "step": 31258
    },
    {
      "epoch": 0.9602494393757872,
      "grad_norm": 0.3590373992919922,
      "learning_rate": 1.0649550388996095e-05,
      "loss": 0.5715,
      "step": 31259
    },
    {
      "epoch": 0.9602801585107363,
      "grad_norm": 0.3640611469745636,
      "learning_rate": 1.0649068131490398e-05,
      "loss": 0.541,
      "step": 31260
    },
    {
      "epoch": 0.9603108776456855,
      "grad_norm": 0.3978162407875061,
      "learning_rate": 1.064858587246876e-05,
      "loss": 0.6015,
      "step": 31261
    },
    {
      "epoch": 0.9603415967806347,
      "grad_norm": 0.3801581859588623,
      "learning_rate": 1.06481036119323e-05,
      "loss": 0.5605,
      "step": 31262
    },
    {
      "epoch": 0.9603723159155838,
      "grad_norm": 0.35424119234085083,
      "learning_rate": 1.0647621349882152e-05,
      "loss": 0.5722,
      "step": 31263
    },
    {
      "epoch": 0.9604030350505329,
      "grad_norm": 0.36806753277778625,
      "learning_rate": 1.0647139086319437e-05,
      "loss": 0.5549,
      "step": 31264
    },
    {
      "epoch": 0.9604337541854822,
      "grad_norm": 0.397953599691391,
      "learning_rate": 1.0646656821245286e-05,
      "loss": 0.4979,
      "step": 31265
    },
    {
      "epoch": 0.9604644733204313,
      "grad_norm": 0.356113076210022,
      "learning_rate": 1.0646174554660822e-05,
      "loss": 0.4912,
      "step": 31266
    },
    {
      "epoch": 0.9604951924553805,
      "grad_norm": 0.4235452115535736,
      "learning_rate": 1.064569228656717e-05,
      "loss": 0.5302,
      "step": 31267
    },
    {
      "epoch": 0.9605259115903296,
      "grad_norm": 0.4105539321899414,
      "learning_rate": 1.0645210016965462e-05,
      "loss": 0.5718,
      "step": 31268
    },
    {
      "epoch": 0.9605566307252787,
      "grad_norm": 0.379419207572937,
      "learning_rate": 1.0644727745856817e-05,
      "loss": 0.4715,
      "step": 31269
    },
    {
      "epoch": 0.960587349860228,
      "grad_norm": 0.4355173408985138,
      "learning_rate": 1.064424547324237e-05,
      "loss": 0.5729,
      "step": 31270
    },
    {
      "epoch": 0.9606180689951771,
      "grad_norm": 0.427031546831131,
      "learning_rate": 1.0643763199123241e-05,
      "loss": 0.5492,
      "step": 31271
    },
    {
      "epoch": 0.9606487881301262,
      "grad_norm": 0.3636293411254883,
      "learning_rate": 1.0643280923500556e-05,
      "loss": 0.5752,
      "step": 31272
    },
    {
      "epoch": 0.9606795072650754,
      "grad_norm": 0.340276837348938,
      "learning_rate": 1.0642798646375447e-05,
      "loss": 0.5157,
      "step": 31273
    },
    {
      "epoch": 0.9607102264000246,
      "grad_norm": 0.37847182154655457,
      "learning_rate": 1.0642316367749032e-05,
      "loss": 0.4237,
      "step": 31274
    },
    {
      "epoch": 0.9607409455349737,
      "grad_norm": 0.36110520362854004,
      "learning_rate": 1.0641834087622446e-05,
      "loss": 0.5207,
      "step": 31275
    },
    {
      "epoch": 0.9607716646699229,
      "grad_norm": 0.42602360248565674,
      "learning_rate": 1.0641351805996812e-05,
      "loss": 0.5539,
      "step": 31276
    },
    {
      "epoch": 0.960802383804872,
      "grad_norm": 0.38110750913619995,
      "learning_rate": 1.0640869522873256e-05,
      "loss": 0.4703,
      "step": 31277
    },
    {
      "epoch": 0.9608331029398212,
      "grad_norm": 0.40462446212768555,
      "learning_rate": 1.06403872382529e-05,
      "loss": 0.5547,
      "step": 31278
    },
    {
      "epoch": 0.9608638220747704,
      "grad_norm": 0.38750994205474854,
      "learning_rate": 1.0639904952136882e-05,
      "loss": 0.5025,
      "step": 31279
    },
    {
      "epoch": 0.9608945412097195,
      "grad_norm": 0.36655667424201965,
      "learning_rate": 1.0639422664526316e-05,
      "loss": 0.4848,
      "step": 31280
    },
    {
      "epoch": 0.9609252603446687,
      "grad_norm": 0.4096637964248657,
      "learning_rate": 1.0638940375422333e-05,
      "loss": 0.4956,
      "step": 31281
    },
    {
      "epoch": 0.9609559794796179,
      "grad_norm": 0.3832806348800659,
      "learning_rate": 1.0638458084826064e-05,
      "loss": 0.523,
      "step": 31282
    },
    {
      "epoch": 0.960986698614567,
      "grad_norm": 0.4190296232700348,
      "learning_rate": 1.0637975792738629e-05,
      "loss": 0.5493,
      "step": 31283
    },
    {
      "epoch": 0.9610174177495162,
      "grad_norm": 0.33006811141967773,
      "learning_rate": 1.0637493499161158e-05,
      "loss": 0.5031,
      "step": 31284
    },
    {
      "epoch": 0.9610481368844653,
      "grad_norm": 0.4006226658821106,
      "learning_rate": 1.0637011204094776e-05,
      "loss": 0.5676,
      "step": 31285
    },
    {
      "epoch": 0.9610788560194145,
      "grad_norm": 0.43273675441741943,
      "learning_rate": 1.063652890754061e-05,
      "loss": 0.5159,
      "step": 31286
    },
    {
      "epoch": 0.9611095751543637,
      "grad_norm": 0.3524719476699829,
      "learning_rate": 1.0636046609499788e-05,
      "loss": 0.5288,
      "step": 31287
    },
    {
      "epoch": 0.9611402942893128,
      "grad_norm": 0.35332077741622925,
      "learning_rate": 1.0635564309973432e-05,
      "loss": 0.541,
      "step": 31288
    },
    {
      "epoch": 0.9611710134242619,
      "grad_norm": 0.3744797706604004,
      "learning_rate": 1.0635082008962674e-05,
      "loss": 0.5384,
      "step": 31289
    },
    {
      "epoch": 0.9612017325592112,
      "grad_norm": 0.3802827298641205,
      "learning_rate": 1.0634599706468633e-05,
      "loss": 0.5815,
      "step": 31290
    },
    {
      "epoch": 0.9612324516941603,
      "grad_norm": 0.37270259857177734,
      "learning_rate": 1.0634117402492445e-05,
      "loss": 0.5422,
      "step": 31291
    },
    {
      "epoch": 0.9612631708291095,
      "grad_norm": 0.48703011870384216,
      "learning_rate": 1.0633635097035229e-05,
      "loss": 0.4929,
      "step": 31292
    },
    {
      "epoch": 0.9612938899640586,
      "grad_norm": 0.3363785743713379,
      "learning_rate": 1.0633152790098115e-05,
      "loss": 0.5421,
      "step": 31293
    },
    {
      "epoch": 0.9613246090990077,
      "grad_norm": 0.38242611289024353,
      "learning_rate": 1.0632670481682226e-05,
      "loss": 0.6323,
      "step": 31294
    },
    {
      "epoch": 0.961355328233957,
      "grad_norm": 0.4389020502567291,
      "learning_rate": 1.0632188171788695e-05,
      "loss": 0.5672,
      "step": 31295
    },
    {
      "epoch": 0.9613860473689061,
      "grad_norm": 0.36584120988845825,
      "learning_rate": 1.0631705860418642e-05,
      "loss": 0.5281,
      "step": 31296
    },
    {
      "epoch": 0.9614167665038552,
      "grad_norm": 1.0208768844604492,
      "learning_rate": 1.0631223547573196e-05,
      "loss": 0.4507,
      "step": 31297
    },
    {
      "epoch": 0.9614474856388044,
      "grad_norm": 0.3511597812175751,
      "learning_rate": 1.0630741233253485e-05,
      "loss": 0.5347,
      "step": 31298
    },
    {
      "epoch": 0.9614782047737536,
      "grad_norm": 0.3445207178592682,
      "learning_rate": 1.0630258917460629e-05,
      "loss": 0.4642,
      "step": 31299
    },
    {
      "epoch": 0.9615089239087027,
      "grad_norm": 0.40512973070144653,
      "learning_rate": 1.0629776600195763e-05,
      "loss": 0.5474,
      "step": 31300
    },
    {
      "epoch": 0.9615396430436519,
      "grad_norm": 0.37555253505706787,
      "learning_rate": 1.0629294281460007e-05,
      "loss": 0.5846,
      "step": 31301
    },
    {
      "epoch": 0.961570362178601,
      "grad_norm": 0.38207152485847473,
      "learning_rate": 1.0628811961254496e-05,
      "loss": 0.4329,
      "step": 31302
    },
    {
      "epoch": 0.9616010813135503,
      "grad_norm": 0.35642457008361816,
      "learning_rate": 1.0628329639580344e-05,
      "loss": 0.5626,
      "step": 31303
    },
    {
      "epoch": 0.9616318004484994,
      "grad_norm": 0.42203488945961,
      "learning_rate": 1.0627847316438689e-05,
      "loss": 0.5854,
      "step": 31304
    },
    {
      "epoch": 0.9616625195834485,
      "grad_norm": 0.479033887386322,
      "learning_rate": 1.0627364991830654e-05,
      "loss": 0.5924,
      "step": 31305
    },
    {
      "epoch": 0.9616932387183977,
      "grad_norm": 0.36524534225463867,
      "learning_rate": 1.0626882665757358e-05,
      "loss": 0.6084,
      "step": 31306
    },
    {
      "epoch": 0.9617239578533469,
      "grad_norm": 0.5206381678581238,
      "learning_rate": 1.0626400338219938e-05,
      "loss": 0.5155,
      "step": 31307
    },
    {
      "epoch": 0.961754676988296,
      "grad_norm": 0.4083087742328644,
      "learning_rate": 1.0625918009219515e-05,
      "loss": 0.5257,
      "step": 31308
    },
    {
      "epoch": 0.9617853961232452,
      "grad_norm": 0.351176917552948,
      "learning_rate": 1.0625435678757219e-05,
      "loss": 0.5465,
      "step": 31309
    },
    {
      "epoch": 0.9618161152581943,
      "grad_norm": 0.3691273629665375,
      "learning_rate": 1.062495334683417e-05,
      "loss": 0.5552,
      "step": 31310
    },
    {
      "epoch": 0.9618468343931434,
      "grad_norm": 0.34286707639694214,
      "learning_rate": 1.0624471013451504e-05,
      "loss": 0.5297,
      "step": 31311
    },
    {
      "epoch": 0.9618775535280927,
      "grad_norm": 0.3986319899559021,
      "learning_rate": 1.0623988678610338e-05,
      "loss": 0.5498,
      "step": 31312
    },
    {
      "epoch": 0.9619082726630418,
      "grad_norm": 0.3914359509944916,
      "learning_rate": 1.0623506342311805e-05,
      "loss": 0.5119,
      "step": 31313
    },
    {
      "epoch": 0.9619389917979909,
      "grad_norm": 0.43056178092956543,
      "learning_rate": 1.0623024004557028e-05,
      "loss": 0.5066,
      "step": 31314
    },
    {
      "epoch": 0.9619697109329401,
      "grad_norm": 0.37845563888549805,
      "learning_rate": 1.0622541665347137e-05,
      "loss": 0.4759,
      "step": 31315
    },
    {
      "epoch": 0.9620004300678893,
      "grad_norm": 0.4149250090122223,
      "learning_rate": 1.0622059324683255e-05,
      "loss": 0.5882,
      "step": 31316
    },
    {
      "epoch": 0.9620311492028385,
      "grad_norm": 0.39439117908477783,
      "learning_rate": 1.062157698256651e-05,
      "loss": 0.5176,
      "step": 31317
    },
    {
      "epoch": 0.9620618683377876,
      "grad_norm": 0.3358139395713806,
      "learning_rate": 1.0621094638998028e-05,
      "loss": 0.5882,
      "step": 31318
    },
    {
      "epoch": 0.9620925874727367,
      "grad_norm": 0.3814910650253296,
      "learning_rate": 1.0620612293978936e-05,
      "loss": 0.5481,
      "step": 31319
    },
    {
      "epoch": 0.962123306607686,
      "grad_norm": 0.37419167160987854,
      "learning_rate": 1.0620129947510363e-05,
      "loss": 0.5879,
      "step": 31320
    },
    {
      "epoch": 0.9621540257426351,
      "grad_norm": 0.36219146847724915,
      "learning_rate": 1.061964759959343e-05,
      "loss": 0.541,
      "step": 31321
    },
    {
      "epoch": 0.9621847448775842,
      "grad_norm": 0.39330047369003296,
      "learning_rate": 1.0619165250229271e-05,
      "loss": 0.6335,
      "step": 31322
    },
    {
      "epoch": 0.9622154640125334,
      "grad_norm": 0.3540416359901428,
      "learning_rate": 1.0618682899419006e-05,
      "loss": 0.4923,
      "step": 31323
    },
    {
      "epoch": 0.9622461831474826,
      "grad_norm": 0.36720576882362366,
      "learning_rate": 1.0618200547163764e-05,
      "loss": 0.4838,
      "step": 31324
    },
    {
      "epoch": 0.9622769022824317,
      "grad_norm": 0.4478447437286377,
      "learning_rate": 1.061771819346467e-05,
      "loss": 0.5416,
      "step": 31325
    },
    {
      "epoch": 0.9623076214173809,
      "grad_norm": 0.35928502678871155,
      "learning_rate": 1.0617235838322853e-05,
      "loss": 0.6008,
      "step": 31326
    },
    {
      "epoch": 0.96233834055233,
      "grad_norm": 0.4029443860054016,
      "learning_rate": 1.061675348173944e-05,
      "loss": 0.4528,
      "step": 31327
    },
    {
      "epoch": 0.9623690596872793,
      "grad_norm": 0.40657132863998413,
      "learning_rate": 1.0616271123715553e-05,
      "loss": 0.5925,
      "step": 31328
    },
    {
      "epoch": 0.9623997788222284,
      "grad_norm": 0.5462896823883057,
      "learning_rate": 1.0615788764252326e-05,
      "loss": 0.5456,
      "step": 31329
    },
    {
      "epoch": 0.9624304979571775,
      "grad_norm": 0.3442525565624237,
      "learning_rate": 1.0615306403350879e-05,
      "loss": 0.4739,
      "step": 31330
    },
    {
      "epoch": 0.9624612170921267,
      "grad_norm": 0.38281258940696716,
      "learning_rate": 1.0614824041012342e-05,
      "loss": 0.4758,
      "step": 31331
    },
    {
      "epoch": 0.9624919362270759,
      "grad_norm": 0.3696674406528473,
      "learning_rate": 1.0614341677237835e-05,
      "loss": 0.5161,
      "step": 31332
    },
    {
      "epoch": 0.962522655362025,
      "grad_norm": 0.3680787980556488,
      "learning_rate": 1.0613859312028498e-05,
      "loss": 0.5682,
      "step": 31333
    },
    {
      "epoch": 0.9625533744969742,
      "grad_norm": 0.3768875300884247,
      "learning_rate": 1.0613376945385448e-05,
      "loss": 0.6073,
      "step": 31334
    },
    {
      "epoch": 0.9625840936319233,
      "grad_norm": 0.3823074996471405,
      "learning_rate": 1.061289457730981e-05,
      "loss": 0.4594,
      "step": 31335
    },
    {
      "epoch": 0.9626148127668724,
      "grad_norm": 0.3811758756637573,
      "learning_rate": 1.0612412207802713e-05,
      "loss": 0.6691,
      "step": 31336
    },
    {
      "epoch": 0.9626455319018217,
      "grad_norm": 0.3744005858898163,
      "learning_rate": 1.0611929836865288e-05,
      "loss": 0.5609,
      "step": 31337
    },
    {
      "epoch": 0.9626762510367708,
      "grad_norm": 0.37993812561035156,
      "learning_rate": 1.0611447464498657e-05,
      "loss": 0.5641,
      "step": 31338
    },
    {
      "epoch": 0.9627069701717199,
      "grad_norm": 0.38699930906295776,
      "learning_rate": 1.0610965090703949e-05,
      "loss": 0.5539,
      "step": 31339
    },
    {
      "epoch": 0.9627376893066691,
      "grad_norm": 0.40495556592941284,
      "learning_rate": 1.0610482715482287e-05,
      "loss": 0.5994,
      "step": 31340
    },
    {
      "epoch": 0.9627684084416183,
      "grad_norm": 0.36308714747428894,
      "learning_rate": 1.0610000338834802e-05,
      "loss": 0.5627,
      "step": 31341
    },
    {
      "epoch": 0.9627991275765675,
      "grad_norm": 0.6773108243942261,
      "learning_rate": 1.0609517960762617e-05,
      "loss": 0.469,
      "step": 31342
    },
    {
      "epoch": 0.9628298467115166,
      "grad_norm": 0.3962970972061157,
      "learning_rate": 1.0609035581266862e-05,
      "loss": 0.5807,
      "step": 31343
    },
    {
      "epoch": 0.9628605658464657,
      "grad_norm": 0.3716757297515869,
      "learning_rate": 1.060855320034866e-05,
      "loss": 0.4727,
      "step": 31344
    },
    {
      "epoch": 0.962891284981415,
      "grad_norm": 0.3341767489910126,
      "learning_rate": 1.0608070818009142e-05,
      "loss": 0.564,
      "step": 31345
    },
    {
      "epoch": 0.9629220041163641,
      "grad_norm": 0.4499187767505646,
      "learning_rate": 1.060758843424943e-05,
      "loss": 0.581,
      "step": 31346
    },
    {
      "epoch": 0.9629527232513132,
      "grad_norm": 0.3993331491947174,
      "learning_rate": 1.0607106049070655e-05,
      "loss": 0.5849,
      "step": 31347
    },
    {
      "epoch": 0.9629834423862624,
      "grad_norm": 0.3474039137363434,
      "learning_rate": 1.0606623662473939e-05,
      "loss": 0.4829,
      "step": 31348
    },
    {
      "epoch": 0.9630141615212116,
      "grad_norm": 0.3436499834060669,
      "learning_rate": 1.060614127446041e-05,
      "loss": 0.5594,
      "step": 31349
    },
    {
      "epoch": 0.9630448806561607,
      "grad_norm": 0.36353278160095215,
      "learning_rate": 1.06056588850312e-05,
      "loss": 0.5294,
      "step": 31350
    },
    {
      "epoch": 0.9630755997911099,
      "grad_norm": 0.3413015902042389,
      "learning_rate": 1.0605176494187428e-05,
      "loss": 0.5597,
      "step": 31351
    },
    {
      "epoch": 0.963106318926059,
      "grad_norm": 0.3846340775489807,
      "learning_rate": 1.0604694101930226e-05,
      "loss": 0.4732,
      "step": 31352
    },
    {
      "epoch": 0.9631370380610083,
      "grad_norm": 0.3929237723350525,
      "learning_rate": 1.0604211708260716e-05,
      "loss": 0.5292,
      "step": 31353
    },
    {
      "epoch": 0.9631677571959574,
      "grad_norm": 0.38955169916152954,
      "learning_rate": 1.060372931318003e-05,
      "loss": 0.5863,
      "step": 31354
    },
    {
      "epoch": 0.9631984763309065,
      "grad_norm": 0.4047471284866333,
      "learning_rate": 1.0603246916689289e-05,
      "loss": 0.5612,
      "step": 31355
    },
    {
      "epoch": 0.9632291954658557,
      "grad_norm": 0.3864074647426605,
      "learning_rate": 1.0602764518789626e-05,
      "loss": 0.5245,
      "step": 31356
    },
    {
      "epoch": 0.9632599146008048,
      "grad_norm": 0.3699687421321869,
      "learning_rate": 1.0602282119482163e-05,
      "loss": 0.6139,
      "step": 31357
    },
    {
      "epoch": 0.963290633735754,
      "grad_norm": 0.3962550163269043,
      "learning_rate": 1.0601799718768028e-05,
      "loss": 0.5732,
      "step": 31358
    },
    {
      "epoch": 0.9633213528707032,
      "grad_norm": 0.35786476731300354,
      "learning_rate": 1.0601317316648349e-05,
      "loss": 0.4934,
      "step": 31359
    },
    {
      "epoch": 0.9633520720056523,
      "grad_norm": 0.36887112259864807,
      "learning_rate": 1.060083491312425e-05,
      "loss": 0.5312,
      "step": 31360
    },
    {
      "epoch": 0.9633827911406014,
      "grad_norm": 0.4184873402118683,
      "learning_rate": 1.0600352508196861e-05,
      "loss": 0.6065,
      "step": 31361
    },
    {
      "epoch": 0.9634135102755507,
      "grad_norm": 0.6548122763633728,
      "learning_rate": 1.0599870101867302e-05,
      "loss": 0.5824,
      "step": 31362
    },
    {
      "epoch": 0.9634442294104998,
      "grad_norm": 0.4044815003871918,
      "learning_rate": 1.0599387694136709e-05,
      "loss": 0.5433,
      "step": 31363
    },
    {
      "epoch": 0.9634749485454489,
      "grad_norm": 0.4959205687046051,
      "learning_rate": 1.0598905285006202e-05,
      "loss": 0.4638,
      "step": 31364
    },
    {
      "epoch": 0.9635056676803981,
      "grad_norm": 0.3668917119503021,
      "learning_rate": 1.0598422874476913e-05,
      "loss": 0.5723,
      "step": 31365
    },
    {
      "epoch": 0.9635363868153473,
      "grad_norm": 0.390249103307724,
      "learning_rate": 1.0597940462549961e-05,
      "loss": 0.6071,
      "step": 31366
    },
    {
      "epoch": 0.9635671059502965,
      "grad_norm": 0.3708314895629883,
      "learning_rate": 1.0597458049226482e-05,
      "loss": 0.5236,
      "step": 31367
    },
    {
      "epoch": 0.9635978250852456,
      "grad_norm": 0.7216207385063171,
      "learning_rate": 1.0596975634507595e-05,
      "loss": 0.4787,
      "step": 31368
    },
    {
      "epoch": 0.9636285442201947,
      "grad_norm": 0.34182995557785034,
      "learning_rate": 1.059649321839443e-05,
      "loss": 0.5463,
      "step": 31369
    },
    {
      "epoch": 0.963659263355144,
      "grad_norm": 0.38303259015083313,
      "learning_rate": 1.0596010800888114e-05,
      "loss": 0.5786,
      "step": 31370
    },
    {
      "epoch": 0.9636899824900931,
      "grad_norm": 0.37822821736335754,
      "learning_rate": 1.0595528381989772e-05,
      "loss": 0.5962,
      "step": 31371
    },
    {
      "epoch": 0.9637207016250422,
      "grad_norm": 0.376499205827713,
      "learning_rate": 1.0595045961700535e-05,
      "loss": 0.5387,
      "step": 31372
    },
    {
      "epoch": 0.9637514207599914,
      "grad_norm": 0.3780275881290436,
      "learning_rate": 1.0594563540021521e-05,
      "loss": 0.5153,
      "step": 31373
    },
    {
      "epoch": 0.9637821398949405,
      "grad_norm": 0.3739379048347473,
      "learning_rate": 1.0594081116953866e-05,
      "loss": 0.5739,
      "step": 31374
    },
    {
      "epoch": 0.9638128590298897,
      "grad_norm": 0.4480989873409271,
      "learning_rate": 1.0593598692498694e-05,
      "loss": 0.5491,
      "step": 31375
    },
    {
      "epoch": 0.9638435781648389,
      "grad_norm": 0.4056874215602875,
      "learning_rate": 1.0593116266657128e-05,
      "loss": 0.619,
      "step": 31376
    },
    {
      "epoch": 0.963874297299788,
      "grad_norm": 0.39930009841918945,
      "learning_rate": 1.0592633839430303e-05,
      "loss": 0.5845,
      "step": 31377
    },
    {
      "epoch": 0.9639050164347372,
      "grad_norm": 0.37627869844436646,
      "learning_rate": 1.0592151410819334e-05,
      "loss": 0.5617,
      "step": 31378
    },
    {
      "epoch": 0.9639357355696864,
      "grad_norm": 0.40860515832901,
      "learning_rate": 1.0591668980825355e-05,
      "loss": 0.627,
      "step": 31379
    },
    {
      "epoch": 0.9639664547046355,
      "grad_norm": 0.40317055583000183,
      "learning_rate": 1.0591186549449495e-05,
      "loss": 0.5345,
      "step": 31380
    },
    {
      "epoch": 0.9639971738395847,
      "grad_norm": 0.41351887583732605,
      "learning_rate": 1.0590704116692876e-05,
      "loss": 0.5546,
      "step": 31381
    },
    {
      "epoch": 0.9640278929745338,
      "grad_norm": 0.4152762293815613,
      "learning_rate": 1.0590221682556625e-05,
      "loss": 0.5748,
      "step": 31382
    },
    {
      "epoch": 0.964058612109483,
      "grad_norm": 0.3787285387516022,
      "learning_rate": 1.0589739247041873e-05,
      "loss": 0.5002,
      "step": 31383
    },
    {
      "epoch": 0.9640893312444322,
      "grad_norm": 0.35376080870628357,
      "learning_rate": 1.058925681014974e-05,
      "loss": 0.5045,
      "step": 31384
    },
    {
      "epoch": 0.9641200503793813,
      "grad_norm": 0.3771818280220032,
      "learning_rate": 1.0588774371881359e-05,
      "loss": 0.5747,
      "step": 31385
    },
    {
      "epoch": 0.9641507695143304,
      "grad_norm": 0.3313387334346771,
      "learning_rate": 1.0588291932237855e-05,
      "loss": 0.5125,
      "step": 31386
    },
    {
      "epoch": 0.9641814886492797,
      "grad_norm": 0.3711093068122864,
      "learning_rate": 1.0587809491220351e-05,
      "loss": 0.5922,
      "step": 31387
    },
    {
      "epoch": 0.9642122077842288,
      "grad_norm": 0.37837427854537964,
      "learning_rate": 1.058732704882998e-05,
      "loss": 0.6412,
      "step": 31388
    },
    {
      "epoch": 0.9642429269191779,
      "grad_norm": 0.5178149342536926,
      "learning_rate": 1.0586844605067863e-05,
      "loss": 0.5595,
      "step": 31389
    },
    {
      "epoch": 0.9642736460541271,
      "grad_norm": 0.3593289852142334,
      "learning_rate": 1.0586362159935133e-05,
      "loss": 0.5724,
      "step": 31390
    },
    {
      "epoch": 0.9643043651890763,
      "grad_norm": 0.4578056037425995,
      "learning_rate": 1.058587971343291e-05,
      "loss": 0.6273,
      "step": 31391
    },
    {
      "epoch": 0.9643350843240255,
      "grad_norm": 0.3900642395019531,
      "learning_rate": 1.0585397265562322e-05,
      "loss": 0.492,
      "step": 31392
    },
    {
      "epoch": 0.9643658034589746,
      "grad_norm": 0.38649871945381165,
      "learning_rate": 1.0584914816324502e-05,
      "loss": 0.607,
      "step": 31393
    },
    {
      "epoch": 0.9643965225939237,
      "grad_norm": 0.45116767287254333,
      "learning_rate": 1.0584432365720572e-05,
      "loss": 0.5167,
      "step": 31394
    },
    {
      "epoch": 0.964427241728873,
      "grad_norm": 0.41964033246040344,
      "learning_rate": 1.0583949913751658e-05,
      "loss": 0.4943,
      "step": 31395
    },
    {
      "epoch": 0.9644579608638221,
      "grad_norm": 0.42506253719329834,
      "learning_rate": 1.058346746041889e-05,
      "loss": 0.5367,
      "step": 31396
    },
    {
      "epoch": 0.9644886799987712,
      "grad_norm": 0.3502868115901947,
      "learning_rate": 1.0582985005723392e-05,
      "loss": 0.5239,
      "step": 31397
    },
    {
      "epoch": 0.9645193991337204,
      "grad_norm": 0.4167330861091614,
      "learning_rate": 1.0582502549666291e-05,
      "loss": 0.5693,
      "step": 31398
    },
    {
      "epoch": 0.9645501182686695,
      "grad_norm": 0.3796357214450836,
      "learning_rate": 1.0582020092248718e-05,
      "loss": 0.5148,
      "step": 31399
    },
    {
      "epoch": 0.9645808374036187,
      "grad_norm": 0.3608141839504242,
      "learning_rate": 1.0581537633471792e-05,
      "loss": 0.5905,
      "step": 31400
    },
    {
      "epoch": 0.9646115565385679,
      "grad_norm": 0.39116305112838745,
      "learning_rate": 1.0581055173336647e-05,
      "loss": 0.5835,
      "step": 31401
    },
    {
      "epoch": 0.964642275673517,
      "grad_norm": 0.33313265442848206,
      "learning_rate": 1.0580572711844409e-05,
      "loss": 0.5026,
      "step": 31402
    },
    {
      "epoch": 0.9646729948084662,
      "grad_norm": 0.37582555413246155,
      "learning_rate": 1.0580090248996197e-05,
      "loss": 0.5058,
      "step": 31403
    },
    {
      "epoch": 0.9647037139434154,
      "grad_norm": 0.3657222390174866,
      "learning_rate": 1.057960778479315e-05,
      "loss": 0.5176,
      "step": 31404
    },
    {
      "epoch": 0.9647344330783645,
      "grad_norm": 0.40661758184432983,
      "learning_rate": 1.0579125319236382e-05,
      "loss": 0.5807,
      "step": 31405
    },
    {
      "epoch": 0.9647651522133137,
      "grad_norm": 0.5013903379440308,
      "learning_rate": 1.057864285232703e-05,
      "loss": 0.5451,
      "step": 31406
    },
    {
      "epoch": 0.9647958713482628,
      "grad_norm": 0.39998942613601685,
      "learning_rate": 1.0578160384066216e-05,
      "loss": 0.5281,
      "step": 31407
    },
    {
      "epoch": 0.964826590483212,
      "grad_norm": 0.33370065689086914,
      "learning_rate": 1.0577677914455072e-05,
      "loss": 0.4954,
      "step": 31408
    },
    {
      "epoch": 0.9648573096181612,
      "grad_norm": 0.40260404348373413,
      "learning_rate": 1.0577195443494717e-05,
      "loss": 0.5138,
      "step": 31409
    },
    {
      "epoch": 0.9648880287531103,
      "grad_norm": 0.3968352973461151,
      "learning_rate": 1.057671297118628e-05,
      "loss": 0.5617,
      "step": 31410
    },
    {
      "epoch": 0.9649187478880594,
      "grad_norm": 0.35828548669815063,
      "learning_rate": 1.0576230497530893e-05,
      "loss": 0.5406,
      "step": 31411
    },
    {
      "epoch": 0.9649494670230087,
      "grad_norm": 0.4532454013824463,
      "learning_rate": 1.0575748022529678e-05,
      "loss": 0.4945,
      "step": 31412
    },
    {
      "epoch": 0.9649801861579578,
      "grad_norm": 0.3827739357948303,
      "learning_rate": 1.0575265546183764e-05,
      "loss": 0.5546,
      "step": 31413
    },
    {
      "epoch": 0.965010905292907,
      "grad_norm": 0.4335762560367584,
      "learning_rate": 1.0574783068494277e-05,
      "loss": 0.5359,
      "step": 31414
    },
    {
      "epoch": 0.9650416244278561,
      "grad_norm": 0.3695290684700012,
      "learning_rate": 1.0574300589462345e-05,
      "loss": 0.5459,
      "step": 31415
    },
    {
      "epoch": 0.9650723435628052,
      "grad_norm": 0.38871148228645325,
      "learning_rate": 1.0573818109089092e-05,
      "loss": 0.569,
      "step": 31416
    },
    {
      "epoch": 0.9651030626977545,
      "grad_norm": 0.5736449360847473,
      "learning_rate": 1.0573335627375649e-05,
      "loss": 0.552,
      "step": 31417
    },
    {
      "epoch": 0.9651337818327036,
      "grad_norm": 0.34838420152664185,
      "learning_rate": 1.0572853144323137e-05,
      "loss": 0.5387,
      "step": 31418
    },
    {
      "epoch": 0.9651645009676527,
      "grad_norm": 0.36492660641670227,
      "learning_rate": 1.0572370659932688e-05,
      "loss": 0.5433,
      "step": 31419
    },
    {
      "epoch": 0.965195220102602,
      "grad_norm": 0.34290167689323425,
      "learning_rate": 1.0571888174205431e-05,
      "loss": 0.5134,
      "step": 31420
    },
    {
      "epoch": 0.9652259392375511,
      "grad_norm": 0.3379954993724823,
      "learning_rate": 1.0571405687142487e-05,
      "loss": 0.5096,
      "step": 31421
    },
    {
      "epoch": 0.9652566583725002,
      "grad_norm": 0.39643022418022156,
      "learning_rate": 1.0570923198744985e-05,
      "loss": 0.5587,
      "step": 31422
    },
    {
      "epoch": 0.9652873775074494,
      "grad_norm": 0.4122602641582489,
      "learning_rate": 1.0570440709014049e-05,
      "loss": 0.5093,
      "step": 31423
    },
    {
      "epoch": 0.9653180966423985,
      "grad_norm": 0.35781171917915344,
      "learning_rate": 1.0569958217950814e-05,
      "loss": 0.532,
      "step": 31424
    },
    {
      "epoch": 0.9653488157773477,
      "grad_norm": 0.38870760798454285,
      "learning_rate": 1.0569475725556397e-05,
      "loss": 0.517,
      "step": 31425
    },
    {
      "epoch": 0.9653795349122969,
      "grad_norm": 0.3740333020687103,
      "learning_rate": 1.0568993231831933e-05,
      "loss": 0.5553,
      "step": 31426
    },
    {
      "epoch": 0.965410254047246,
      "grad_norm": 0.4045684337615967,
      "learning_rate": 1.0568510736778544e-05,
      "loss": 0.5737,
      "step": 31427
    },
    {
      "epoch": 0.9654409731821952,
      "grad_norm": 0.3622325360774994,
      "learning_rate": 1.0568028240397357e-05,
      "loss": 0.5221,
      "step": 31428
    },
    {
      "epoch": 0.9654716923171444,
      "grad_norm": 0.6681498885154724,
      "learning_rate": 1.0567545742689503e-05,
      "loss": 0.5764,
      "step": 31429
    },
    {
      "epoch": 0.9655024114520935,
      "grad_norm": 0.38864004611968994,
      "learning_rate": 1.0567063243656103e-05,
      "loss": 0.5021,
      "step": 31430
    },
    {
      "epoch": 0.9655331305870427,
      "grad_norm": 0.37636426091194153,
      "learning_rate": 1.0566580743298291e-05,
      "loss": 0.5505,
      "step": 31431
    },
    {
      "epoch": 0.9655638497219918,
      "grad_norm": 0.40853533148765564,
      "learning_rate": 1.0566098241617188e-05,
      "loss": 0.5153,
      "step": 31432
    },
    {
      "epoch": 0.965594568856941,
      "grad_norm": 0.38884061574935913,
      "learning_rate": 1.0565615738613923e-05,
      "loss": 0.5556,
      "step": 31433
    },
    {
      "epoch": 0.9656252879918902,
      "grad_norm": 0.36034825444221497,
      "learning_rate": 1.0565133234289623e-05,
      "loss": 0.479,
      "step": 31434
    },
    {
      "epoch": 0.9656560071268393,
      "grad_norm": 0.40104350447654724,
      "learning_rate": 1.0564650728645418e-05,
      "loss": 0.5388,
      "step": 31435
    },
    {
      "epoch": 0.9656867262617884,
      "grad_norm": 0.3575049042701721,
      "learning_rate": 1.0564168221682428e-05,
      "loss": 0.5834,
      "step": 31436
    },
    {
      "epoch": 0.9657174453967377,
      "grad_norm": 0.3453225791454315,
      "learning_rate": 1.0563685713401786e-05,
      "loss": 0.5605,
      "step": 31437
    },
    {
      "epoch": 0.9657481645316868,
      "grad_norm": 0.3570595383644104,
      "learning_rate": 1.0563203203804617e-05,
      "loss": 0.5202,
      "step": 31438
    },
    {
      "epoch": 0.965778883666636,
      "grad_norm": 0.3556460738182068,
      "learning_rate": 1.0562720692892046e-05,
      "loss": 0.5858,
      "step": 31439
    },
    {
      "epoch": 0.9658096028015851,
      "grad_norm": 0.35979539155960083,
      "learning_rate": 1.0562238180665202e-05,
      "loss": 0.5457,
      "step": 31440
    },
    {
      "epoch": 0.9658403219365342,
      "grad_norm": 0.3801931142807007,
      "learning_rate": 1.056175566712521e-05,
      "loss": 0.5727,
      "step": 31441
    },
    {
      "epoch": 0.9658710410714835,
      "grad_norm": 0.3284153938293457,
      "learning_rate": 1.0561273152273201e-05,
      "loss": 0.4318,
      "step": 31442
    },
    {
      "epoch": 0.9659017602064326,
      "grad_norm": 0.41104915738105774,
      "learning_rate": 1.0560790636110296e-05,
      "loss": 0.5771,
      "step": 31443
    },
    {
      "epoch": 0.9659324793413817,
      "grad_norm": 0.4236783981323242,
      "learning_rate": 1.0560308118637628e-05,
      "loss": 0.5985,
      "step": 31444
    },
    {
      "epoch": 0.9659631984763309,
      "grad_norm": 0.3547949194908142,
      "learning_rate": 1.055982559985632e-05,
      "loss": 0.5269,
      "step": 31445
    },
    {
      "epoch": 0.9659939176112801,
      "grad_norm": 0.3523111641407013,
      "learning_rate": 1.0559343079767498e-05,
      "loss": 0.4984,
      "step": 31446
    },
    {
      "epoch": 0.9660246367462292,
      "grad_norm": 0.39730459451675415,
      "learning_rate": 1.0558860558372296e-05,
      "loss": 0.5085,
      "step": 31447
    },
    {
      "epoch": 0.9660553558811784,
      "grad_norm": 1.2049907445907593,
      "learning_rate": 1.0558378035671834e-05,
      "loss": 0.4765,
      "step": 31448
    },
    {
      "epoch": 0.9660860750161275,
      "grad_norm": 0.35346519947052,
      "learning_rate": 1.0557895511667242e-05,
      "loss": 0.4796,
      "step": 31449
    },
    {
      "epoch": 0.9661167941510767,
      "grad_norm": 0.3422947824001312,
      "learning_rate": 1.0557412986359644e-05,
      "loss": 0.5284,
      "step": 31450
    },
    {
      "epoch": 0.9661475132860259,
      "grad_norm": 0.4590795934200287,
      "learning_rate": 1.0556930459750172e-05,
      "loss": 0.5526,
      "step": 31451
    },
    {
      "epoch": 0.966178232420975,
      "grad_norm": 0.42062535881996155,
      "learning_rate": 1.0556447931839946e-05,
      "loss": 0.5892,
      "step": 31452
    },
    {
      "epoch": 0.9662089515559242,
      "grad_norm": 0.3570277690887451,
      "learning_rate": 1.0555965402630101e-05,
      "loss": 0.6167,
      "step": 31453
    },
    {
      "epoch": 0.9662396706908734,
      "grad_norm": 0.35375475883483887,
      "learning_rate": 1.0555482872121758e-05,
      "loss": 0.5617,
      "step": 31454
    },
    {
      "epoch": 0.9662703898258225,
      "grad_norm": 0.36927419900894165,
      "learning_rate": 1.0555000340316045e-05,
      "loss": 0.5659,
      "step": 31455
    },
    {
      "epoch": 0.9663011089607717,
      "grad_norm": 0.3982950747013092,
      "learning_rate": 1.0554517807214093e-05,
      "loss": 0.5786,
      "step": 31456
    },
    {
      "epoch": 0.9663318280957208,
      "grad_norm": 0.37177377939224243,
      "learning_rate": 1.0554035272817025e-05,
      "loss": 0.5924,
      "step": 31457
    },
    {
      "epoch": 0.9663625472306699,
      "grad_norm": 0.411020427942276,
      "learning_rate": 1.0553552737125967e-05,
      "loss": 0.5831,
      "step": 31458
    },
    {
      "epoch": 0.9663932663656192,
      "grad_norm": 0.3554731607437134,
      "learning_rate": 1.0553070200142048e-05,
      "loss": 0.5156,
      "step": 31459
    },
    {
      "epoch": 0.9664239855005683,
      "grad_norm": 0.39531394839286804,
      "learning_rate": 1.0552587661866397e-05,
      "loss": 0.5625,
      "step": 31460
    },
    {
      "epoch": 0.9664547046355174,
      "grad_norm": 0.40776386857032776,
      "learning_rate": 1.0552105122300138e-05,
      "loss": 0.5411,
      "step": 31461
    },
    {
      "epoch": 0.9664854237704666,
      "grad_norm": 0.3652268350124359,
      "learning_rate": 1.0551622581444399e-05,
      "loss": 0.5387,
      "step": 31462
    },
    {
      "epoch": 0.9665161429054158,
      "grad_norm": 0.359662801027298,
      "learning_rate": 1.0551140039300305e-05,
      "loss": 0.5873,
      "step": 31463
    },
    {
      "epoch": 0.966546862040365,
      "grad_norm": 0.3693923354148865,
      "learning_rate": 1.0550657495868986e-05,
      "loss": 0.5874,
      "step": 31464
    },
    {
      "epoch": 0.9665775811753141,
      "grad_norm": 0.36592432856559753,
      "learning_rate": 1.055017495115157e-05,
      "loss": 0.5161,
      "step": 31465
    },
    {
      "epoch": 0.9666083003102632,
      "grad_norm": 0.4071306586265564,
      "learning_rate": 1.0549692405149179e-05,
      "loss": 0.5595,
      "step": 31466
    },
    {
      "epoch": 0.9666390194452125,
      "grad_norm": 0.3637971878051758,
      "learning_rate": 1.0549209857862945e-05,
      "loss": 0.534,
      "step": 31467
    },
    {
      "epoch": 0.9666697385801616,
      "grad_norm": 0.6144012808799744,
      "learning_rate": 1.0548727309293994e-05,
      "loss": 0.5782,
      "step": 31468
    },
    {
      "epoch": 0.9667004577151107,
      "grad_norm": 0.5172902345657349,
      "learning_rate": 1.0548244759443451e-05,
      "loss": 0.5159,
      "step": 31469
    },
    {
      "epoch": 0.9667311768500599,
      "grad_norm": 0.4003470838069916,
      "learning_rate": 1.0547762208312443e-05,
      "loss": 0.597,
      "step": 31470
    },
    {
      "epoch": 0.9667618959850091,
      "grad_norm": 0.3976392447948456,
      "learning_rate": 1.0547279655902098e-05,
      "loss": 0.6008,
      "step": 31471
    },
    {
      "epoch": 0.9667926151199582,
      "grad_norm": 0.6284521818161011,
      "learning_rate": 1.0546797102213547e-05,
      "loss": 0.5403,
      "step": 31472
    },
    {
      "epoch": 0.9668233342549074,
      "grad_norm": 0.3489667773246765,
      "learning_rate": 1.0546314547247908e-05,
      "loss": 0.5404,
      "step": 31473
    },
    {
      "epoch": 0.9668540533898565,
      "grad_norm": 0.4498499631881714,
      "learning_rate": 1.0545831991006317e-05,
      "loss": 0.4928,
      "step": 31474
    },
    {
      "epoch": 0.9668847725248056,
      "grad_norm": 0.3613872230052948,
      "learning_rate": 1.0545349433489893e-05,
      "loss": 0.547,
      "step": 31475
    },
    {
      "epoch": 0.9669154916597549,
      "grad_norm": 0.5393545627593994,
      "learning_rate": 1.0544866874699772e-05,
      "loss": 0.5299,
      "step": 31476
    },
    {
      "epoch": 0.966946210794704,
      "grad_norm": 0.36444997787475586,
      "learning_rate": 1.0544384314637073e-05,
      "loss": 0.5236,
      "step": 31477
    },
    {
      "epoch": 0.9669769299296532,
      "grad_norm": 0.3298209309577942,
      "learning_rate": 1.054390175330293e-05,
      "loss": 0.4995,
      "step": 31478
    },
    {
      "epoch": 0.9670076490646023,
      "grad_norm": 0.3340143859386444,
      "learning_rate": 1.0543419190698463e-05,
      "loss": 0.5124,
      "step": 31479
    },
    {
      "epoch": 0.9670383681995515,
      "grad_norm": 0.37353119254112244,
      "learning_rate": 1.0542936626824805e-05,
      "loss": 0.5819,
      "step": 31480
    },
    {
      "epoch": 0.9670690873345007,
      "grad_norm": 0.38200345635414124,
      "learning_rate": 1.0542454061683076e-05,
      "loss": 0.591,
      "step": 31481
    },
    {
      "epoch": 0.9670998064694498,
      "grad_norm": 0.37436559796333313,
      "learning_rate": 1.054197149527441e-05,
      "loss": 0.5418,
      "step": 31482
    },
    {
      "epoch": 0.9671305256043989,
      "grad_norm": 0.3718794584274292,
      "learning_rate": 1.0541488927599934e-05,
      "loss": 0.5481,
      "step": 31483
    },
    {
      "epoch": 0.9671612447393482,
      "grad_norm": 0.3828454613685608,
      "learning_rate": 1.054100635866077e-05,
      "loss": 0.5219,
      "step": 31484
    },
    {
      "epoch": 0.9671919638742973,
      "grad_norm": 0.4051169455051422,
      "learning_rate": 1.054052378845805e-05,
      "loss": 0.5,
      "step": 31485
    },
    {
      "epoch": 0.9672226830092464,
      "grad_norm": 0.3911679685115814,
      "learning_rate": 1.0540041216992898e-05,
      "loss": 0.5962,
      "step": 31486
    },
    {
      "epoch": 0.9672534021441956,
      "grad_norm": 0.36748436093330383,
      "learning_rate": 1.0539558644266443e-05,
      "loss": 0.5676,
      "step": 31487
    },
    {
      "epoch": 0.9672841212791448,
      "grad_norm": 0.340848445892334,
      "learning_rate": 1.053907607027981e-05,
      "loss": 0.4915,
      "step": 31488
    },
    {
      "epoch": 0.967314840414094,
      "grad_norm": 0.3733859360218048,
      "learning_rate": 1.0538593495034129e-05,
      "loss": 0.531,
      "step": 31489
    },
    {
      "epoch": 0.9673455595490431,
      "grad_norm": 0.38750743865966797,
      "learning_rate": 1.0538110918530525e-05,
      "loss": 0.5465,
      "step": 31490
    },
    {
      "epoch": 0.9673762786839922,
      "grad_norm": 0.3798360526561737,
      "learning_rate": 1.0537628340770124e-05,
      "loss": 0.5106,
      "step": 31491
    },
    {
      "epoch": 0.9674069978189415,
      "grad_norm": 0.3573945164680481,
      "learning_rate": 1.0537145761754056e-05,
      "loss": 0.4858,
      "step": 31492
    },
    {
      "epoch": 0.9674377169538906,
      "grad_norm": 0.39133062958717346,
      "learning_rate": 1.0536663181483442e-05,
      "loss": 0.5527,
      "step": 31493
    },
    {
      "epoch": 0.9674684360888397,
      "grad_norm": 0.37457939982414246,
      "learning_rate": 1.0536180599959418e-05,
      "loss": 0.5302,
      "step": 31494
    },
    {
      "epoch": 0.9674991552237889,
      "grad_norm": 0.442684531211853,
      "learning_rate": 1.0535698017183104e-05,
      "loss": 0.4507,
      "step": 31495
    },
    {
      "epoch": 0.967529874358738,
      "grad_norm": 0.3378961682319641,
      "learning_rate": 1.0535215433155634e-05,
      "loss": 0.5964,
      "step": 31496
    },
    {
      "epoch": 0.9675605934936872,
      "grad_norm": 0.3808746635913849,
      "learning_rate": 1.0534732847878127e-05,
      "loss": 0.5634,
      "step": 31497
    },
    {
      "epoch": 0.9675913126286364,
      "grad_norm": 0.38587966561317444,
      "learning_rate": 1.0534250261351718e-05,
      "loss": 0.4861,
      "step": 31498
    },
    {
      "epoch": 0.9676220317635855,
      "grad_norm": 0.3573414385318756,
      "learning_rate": 1.0533767673577525e-05,
      "loss": 0.5078,
      "step": 31499
    },
    {
      "epoch": 0.9676527508985348,
      "grad_norm": 0.3637157678604126,
      "learning_rate": 1.0533285084556682e-05,
      "loss": 0.5345,
      "step": 31500
    },
    {
      "epoch": 0.9676834700334839,
      "grad_norm": 0.4425986707210541,
      "learning_rate": 1.0532802494290317e-05,
      "loss": 0.551,
      "step": 31501
    },
    {
      "epoch": 0.967714189168433,
      "grad_norm": 0.32927370071411133,
      "learning_rate": 1.0532319902779553e-05,
      "loss": 0.5594,
      "step": 31502
    },
    {
      "epoch": 0.9677449083033822,
      "grad_norm": 0.39324477314949036,
      "learning_rate": 1.0531837310025518e-05,
      "loss": 0.577,
      "step": 31503
    },
    {
      "epoch": 0.9677756274383313,
      "grad_norm": 0.396894633769989,
      "learning_rate": 1.053135471602934e-05,
      "loss": 0.5924,
      "step": 31504
    },
    {
      "epoch": 0.9678063465732805,
      "grad_norm": 0.36470773816108704,
      "learning_rate": 1.0530872120792148e-05,
      "loss": 0.4895,
      "step": 31505
    },
    {
      "epoch": 0.9678370657082297,
      "grad_norm": 0.34801948070526123,
      "learning_rate": 1.0530389524315066e-05,
      "loss": 0.4695,
      "step": 31506
    },
    {
      "epoch": 0.9678677848431788,
      "grad_norm": 0.3997515141963959,
      "learning_rate": 1.0529906926599223e-05,
      "loss": 0.6078,
      "step": 31507
    },
    {
      "epoch": 0.9678985039781279,
      "grad_norm": 0.3805995285511017,
      "learning_rate": 1.0529424327645743e-05,
      "loss": 0.5846,
      "step": 31508
    },
    {
      "epoch": 0.9679292231130772,
      "grad_norm": 0.336215615272522,
      "learning_rate": 1.0528941727455757e-05,
      "loss": 0.5871,
      "step": 31509
    },
    {
      "epoch": 0.9679599422480263,
      "grad_norm": 0.38454991579055786,
      "learning_rate": 1.052845912603039e-05,
      "loss": 0.5551,
      "step": 31510
    },
    {
      "epoch": 0.9679906613829754,
      "grad_norm": 0.3563859462738037,
      "learning_rate": 1.0527976523370771e-05,
      "loss": 0.553,
      "step": 31511
    },
    {
      "epoch": 0.9680213805179246,
      "grad_norm": 0.3329734802246094,
      "learning_rate": 1.0527493919478027e-05,
      "loss": 0.5011,
      "step": 31512
    },
    {
      "epoch": 0.9680520996528738,
      "grad_norm": 0.43396300077438354,
      "learning_rate": 1.052701131435328e-05,
      "loss": 0.4838,
      "step": 31513
    },
    {
      "epoch": 0.968082818787823,
      "grad_norm": 0.3934822976589203,
      "learning_rate": 1.0526528707997666e-05,
      "loss": 0.5026,
      "step": 31514
    },
    {
      "epoch": 0.9681135379227721,
      "grad_norm": 0.3989558815956116,
      "learning_rate": 1.0526046100412301e-05,
      "loss": 0.5567,
      "step": 31515
    },
    {
      "epoch": 0.9681442570577212,
      "grad_norm": 0.3961544930934906,
      "learning_rate": 1.0525563491598326e-05,
      "loss": 0.5225,
      "step": 31516
    },
    {
      "epoch": 0.9681749761926705,
      "grad_norm": 0.351864218711853,
      "learning_rate": 1.0525080881556855e-05,
      "loss": 0.427,
      "step": 31517
    },
    {
      "epoch": 0.9682056953276196,
      "grad_norm": 0.3699679374694824,
      "learning_rate": 1.0524598270289024e-05,
      "loss": 0.4486,
      "step": 31518
    },
    {
      "epoch": 0.9682364144625687,
      "grad_norm": 0.48269155621528625,
      "learning_rate": 1.0524115657795957e-05,
      "loss": 0.5139,
      "step": 31519
    },
    {
      "epoch": 0.9682671335975179,
      "grad_norm": 0.3711334466934204,
      "learning_rate": 1.0523633044078779e-05,
      "loss": 0.6341,
      "step": 31520
    },
    {
      "epoch": 0.968297852732467,
      "grad_norm": 0.39163607358932495,
      "learning_rate": 1.0523150429138622e-05,
      "loss": 0.5484,
      "step": 31521
    },
    {
      "epoch": 0.9683285718674162,
      "grad_norm": 0.3598252534866333,
      "learning_rate": 1.0522667812976608e-05,
      "loss": 0.5413,
      "step": 31522
    },
    {
      "epoch": 0.9683592910023654,
      "grad_norm": 0.3469293713569641,
      "learning_rate": 1.052218519559387e-05,
      "loss": 0.5342,
      "step": 31523
    },
    {
      "epoch": 0.9683900101373145,
      "grad_norm": 0.39953160285949707,
      "learning_rate": 1.0521702576991532e-05,
      "loss": 0.5208,
      "step": 31524
    },
    {
      "epoch": 0.9684207292722637,
      "grad_norm": 0.4100295603275299,
      "learning_rate": 1.0521219957170719e-05,
      "loss": 0.5818,
      "step": 31525
    },
    {
      "epoch": 0.9684514484072129,
      "grad_norm": 0.3594414293766022,
      "learning_rate": 1.052073733613256e-05,
      "loss": 0.5599,
      "step": 31526
    },
    {
      "epoch": 0.968482167542162,
      "grad_norm": 0.3953518867492676,
      "learning_rate": 1.0520254713878185e-05,
      "loss": 0.5052,
      "step": 31527
    },
    {
      "epoch": 0.9685128866771112,
      "grad_norm": 0.3680560886859894,
      "learning_rate": 1.0519772090408718e-05,
      "loss": 0.5418,
      "step": 31528
    },
    {
      "epoch": 0.9685436058120603,
      "grad_norm": 0.33910897374153137,
      "learning_rate": 1.0519289465725283e-05,
      "loss": 0.6193,
      "step": 31529
    },
    {
      "epoch": 0.9685743249470095,
      "grad_norm": 0.37358948588371277,
      "learning_rate": 1.0518806839829018e-05,
      "loss": 0.5152,
      "step": 31530
    },
    {
      "epoch": 0.9686050440819587,
      "grad_norm": 0.3909909725189209,
      "learning_rate": 1.0518324212721038e-05,
      "loss": 0.5387,
      "step": 31531
    },
    {
      "epoch": 0.9686357632169078,
      "grad_norm": 0.32781150937080383,
      "learning_rate": 1.0517841584402479e-05,
      "loss": 0.4774,
      "step": 31532
    },
    {
      "epoch": 0.9686664823518569,
      "grad_norm": 0.3959876596927643,
      "learning_rate": 1.0517358954874464e-05,
      "loss": 0.6351,
      "step": 31533
    },
    {
      "epoch": 0.9686972014868062,
      "grad_norm": 0.452894002199173,
      "learning_rate": 1.0516876324138122e-05,
      "loss": 0.5214,
      "step": 31534
    },
    {
      "epoch": 0.9687279206217553,
      "grad_norm": 0.353475958108902,
      "learning_rate": 1.0516393692194578e-05,
      "loss": 0.5339,
      "step": 31535
    },
    {
      "epoch": 0.9687586397567044,
      "grad_norm": 0.4886999726295471,
      "learning_rate": 1.0515911059044958e-05,
      "loss": 0.5897,
      "step": 31536
    },
    {
      "epoch": 0.9687893588916536,
      "grad_norm": 0.39769744873046875,
      "learning_rate": 1.0515428424690393e-05,
      "loss": 0.5243,
      "step": 31537
    },
    {
      "epoch": 0.9688200780266027,
      "grad_norm": 0.3857365548610687,
      "learning_rate": 1.0514945789132009e-05,
      "loss": 0.5935,
      "step": 31538
    },
    {
      "epoch": 0.968850797161552,
      "grad_norm": 0.3668992817401886,
      "learning_rate": 1.0514463152370935e-05,
      "loss": 0.5897,
      "step": 31539
    },
    {
      "epoch": 0.9688815162965011,
      "grad_norm": 0.3751409947872162,
      "learning_rate": 1.0513980514408294e-05,
      "loss": 0.5162,
      "step": 31540
    },
    {
      "epoch": 0.9689122354314502,
      "grad_norm": 0.3752150237560272,
      "learning_rate": 1.0513497875245218e-05,
      "loss": 0.5124,
      "step": 31541
    },
    {
      "epoch": 0.9689429545663995,
      "grad_norm": 0.3490377366542816,
      "learning_rate": 1.0513015234882833e-05,
      "loss": 0.4411,
      "step": 31542
    },
    {
      "epoch": 0.9689736737013486,
      "grad_norm": 0.3692469000816345,
      "learning_rate": 1.0512532593322262e-05,
      "loss": 0.57,
      "step": 31543
    },
    {
      "epoch": 0.9690043928362977,
      "grad_norm": 0.4128754436969757,
      "learning_rate": 1.0512049950564639e-05,
      "loss": 0.6015,
      "step": 31544
    },
    {
      "epoch": 0.9690351119712469,
      "grad_norm": 0.3690427243709564,
      "learning_rate": 1.0511567306611081e-05,
      "loss": 0.4721,
      "step": 31545
    },
    {
      "epoch": 0.969065831106196,
      "grad_norm": 0.4351033568382263,
      "learning_rate": 1.0511084661462728e-05,
      "loss": 0.5308,
      "step": 31546
    },
    {
      "epoch": 0.9690965502411452,
      "grad_norm": 0.3727462589740753,
      "learning_rate": 1.0510602015120696e-05,
      "loss": 0.5526,
      "step": 31547
    },
    {
      "epoch": 0.9691272693760944,
      "grad_norm": 0.37958335876464844,
      "learning_rate": 1.0510119367586122e-05,
      "loss": 0.5951,
      "step": 31548
    },
    {
      "epoch": 0.9691579885110435,
      "grad_norm": 0.3608228862285614,
      "learning_rate": 1.0509636718860125e-05,
      "loss": 0.5698,
      "step": 31549
    },
    {
      "epoch": 0.9691887076459927,
      "grad_norm": 0.375479519367218,
      "learning_rate": 1.0509154068943839e-05,
      "loss": 0.625,
      "step": 31550
    },
    {
      "epoch": 0.9692194267809419,
      "grad_norm": 0.34613195061683655,
      "learning_rate": 1.0508671417838385e-05,
      "loss": 0.4573,
      "step": 31551
    },
    {
      "epoch": 0.969250145915891,
      "grad_norm": 0.36412933468818665,
      "learning_rate": 1.0508188765544897e-05,
      "loss": 0.6029,
      "step": 31552
    },
    {
      "epoch": 0.9692808650508402,
      "grad_norm": 0.36040350794792175,
      "learning_rate": 1.0507706112064498e-05,
      "loss": 0.555,
      "step": 31553
    },
    {
      "epoch": 0.9693115841857893,
      "grad_norm": 0.4057673215866089,
      "learning_rate": 1.0507223457398313e-05,
      "loss": 0.5588,
      "step": 31554
    },
    {
      "epoch": 0.9693423033207385,
      "grad_norm": 0.3463574945926666,
      "learning_rate": 1.0506740801547473e-05,
      "loss": 0.5484,
      "step": 31555
    },
    {
      "epoch": 0.9693730224556877,
      "grad_norm": 0.3506704568862915,
      "learning_rate": 1.0506258144513104e-05,
      "loss": 0.4744,
      "step": 31556
    },
    {
      "epoch": 0.9694037415906368,
      "grad_norm": 0.34461966156959534,
      "learning_rate": 1.0505775486296337e-05,
      "loss": 0.4877,
      "step": 31557
    },
    {
      "epoch": 0.9694344607255859,
      "grad_norm": 0.39006686210632324,
      "learning_rate": 1.0505292826898292e-05,
      "loss": 0.5907,
      "step": 31558
    },
    {
      "epoch": 0.9694651798605352,
      "grad_norm": 0.4030389189720154,
      "learning_rate": 1.0504810166320104e-05,
      "loss": 0.5157,
      "step": 31559
    },
    {
      "epoch": 0.9694958989954843,
      "grad_norm": 0.3452884554862976,
      "learning_rate": 1.0504327504562894e-05,
      "loss": 0.5202,
      "step": 31560
    },
    {
      "epoch": 0.9695266181304334,
      "grad_norm": 0.36559900641441345,
      "learning_rate": 1.0503844841627792e-05,
      "loss": 0.5124,
      "step": 31561
    },
    {
      "epoch": 0.9695573372653826,
      "grad_norm": 0.3887709975242615,
      "learning_rate": 1.0503362177515928e-05,
      "loss": 0.555,
      "step": 31562
    },
    {
      "epoch": 0.9695880564003317,
      "grad_norm": 0.3724515736103058,
      "learning_rate": 1.0502879512228423e-05,
      "loss": 0.5277,
      "step": 31563
    },
    {
      "epoch": 0.969618775535281,
      "grad_norm": 0.4354902505874634,
      "learning_rate": 1.0502396845766411e-05,
      "loss": 0.5301,
      "step": 31564
    },
    {
      "epoch": 0.9696494946702301,
      "grad_norm": 0.3187417984008789,
      "learning_rate": 1.0501914178131014e-05,
      "loss": 0.4623,
      "step": 31565
    },
    {
      "epoch": 0.9696802138051792,
      "grad_norm": 0.34548917412757874,
      "learning_rate": 1.0501431509323361e-05,
      "loss": 0.6017,
      "step": 31566
    },
    {
      "epoch": 0.9697109329401284,
      "grad_norm": 0.37835949659347534,
      "learning_rate": 1.0500948839344581e-05,
      "loss": 0.6232,
      "step": 31567
    },
    {
      "epoch": 0.9697416520750776,
      "grad_norm": 0.47944435477256775,
      "learning_rate": 1.0500466168195799e-05,
      "loss": 0.5418,
      "step": 31568
    },
    {
      "epoch": 0.9697723712100267,
      "grad_norm": 0.3762350082397461,
      "learning_rate": 1.0499983495878144e-05,
      "loss": 0.4577,
      "step": 31569
    },
    {
      "epoch": 0.9698030903449759,
      "grad_norm": 0.35220322012901306,
      "learning_rate": 1.0499500822392744e-05,
      "loss": 0.5186,
      "step": 31570
    },
    {
      "epoch": 0.969833809479925,
      "grad_norm": 0.3742513060569763,
      "learning_rate": 1.0499018147740723e-05,
      "loss": 0.5553,
      "step": 31571
    },
    {
      "epoch": 0.9698645286148742,
      "grad_norm": 0.3501766622066498,
      "learning_rate": 1.049853547192321e-05,
      "loss": 0.5275,
      "step": 31572
    },
    {
      "epoch": 0.9698952477498234,
      "grad_norm": 0.4040467143058777,
      "learning_rate": 1.0498052794941331e-05,
      "loss": 0.5583,
      "step": 31573
    },
    {
      "epoch": 0.9699259668847725,
      "grad_norm": 0.3993037939071655,
      "learning_rate": 1.0497570116796217e-05,
      "loss": 0.5009,
      "step": 31574
    },
    {
      "epoch": 0.9699566860197217,
      "grad_norm": 0.374704509973526,
      "learning_rate": 1.0497087437488993e-05,
      "loss": 0.5261,
      "step": 31575
    },
    {
      "epoch": 0.9699874051546709,
      "grad_norm": 0.38204294443130493,
      "learning_rate": 1.049660475702079e-05,
      "loss": 0.5902,
      "step": 31576
    },
    {
      "epoch": 0.97001812428962,
      "grad_norm": 0.38777968287467957,
      "learning_rate": 1.0496122075392727e-05,
      "loss": 0.5505,
      "step": 31577
    },
    {
      "epoch": 0.9700488434245692,
      "grad_norm": 0.3447237014770508,
      "learning_rate": 1.0495639392605939e-05,
      "loss": 0.5833,
      "step": 31578
    },
    {
      "epoch": 0.9700795625595183,
      "grad_norm": 0.3643571138381958,
      "learning_rate": 1.0495156708661549e-05,
      "loss": 0.5747,
      "step": 31579
    },
    {
      "epoch": 0.9701102816944674,
      "grad_norm": 0.48193737864494324,
      "learning_rate": 1.0494674023560688e-05,
      "loss": 0.6558,
      "step": 31580
    },
    {
      "epoch": 0.9701410008294167,
      "grad_norm": 0.382099986076355,
      "learning_rate": 1.0494191337304478e-05,
      "loss": 0.5856,
      "step": 31581
    },
    {
      "epoch": 0.9701717199643658,
      "grad_norm": 0.3432740569114685,
      "learning_rate": 1.0493708649894053e-05,
      "loss": 0.5247,
      "step": 31582
    },
    {
      "epoch": 0.9702024390993149,
      "grad_norm": 0.3925546705722809,
      "learning_rate": 1.0493225961330533e-05,
      "loss": 0.5365,
      "step": 31583
    },
    {
      "epoch": 0.9702331582342641,
      "grad_norm": 0.41769132018089294,
      "learning_rate": 1.0492743271615053e-05,
      "loss": 0.5429,
      "step": 31584
    },
    {
      "epoch": 0.9702638773692133,
      "grad_norm": 0.4180874824523926,
      "learning_rate": 1.0492260580748735e-05,
      "loss": 0.5159,
      "step": 31585
    },
    {
      "epoch": 0.9702945965041624,
      "grad_norm": 0.35358813405036926,
      "learning_rate": 1.0491777888732708e-05,
      "loss": 0.5016,
      "step": 31586
    },
    {
      "epoch": 0.9703253156391116,
      "grad_norm": 0.6353484988212585,
      "learning_rate": 1.0491295195568104e-05,
      "loss": 0.6104,
      "step": 31587
    },
    {
      "epoch": 0.9703560347740607,
      "grad_norm": 0.3773576319217682,
      "learning_rate": 1.0490812501256039e-05,
      "loss": 0.5059,
      "step": 31588
    },
    {
      "epoch": 0.97038675390901,
      "grad_norm": 0.32948657870292664,
      "learning_rate": 1.049032980579765e-05,
      "loss": 0.4449,
      "step": 31589
    },
    {
      "epoch": 0.9704174730439591,
      "grad_norm": 0.3576734662055969,
      "learning_rate": 1.048984710919406e-05,
      "loss": 0.4935,
      "step": 31590
    },
    {
      "epoch": 0.9704481921789082,
      "grad_norm": 0.4327628016471863,
      "learning_rate": 1.0489364411446401e-05,
      "loss": 0.5403,
      "step": 31591
    },
    {
      "epoch": 0.9704789113138574,
      "grad_norm": 0.385507196187973,
      "learning_rate": 1.0488881712555791e-05,
      "loss": 0.5763,
      "step": 31592
    },
    {
      "epoch": 0.9705096304488066,
      "grad_norm": 0.3564428985118866,
      "learning_rate": 1.0488399012523369e-05,
      "loss": 0.5152,
      "step": 31593
    },
    {
      "epoch": 0.9705403495837557,
      "grad_norm": 0.3512336015701294,
      "learning_rate": 1.0487916311350257e-05,
      "loss": 0.5417,
      "step": 31594
    },
    {
      "epoch": 0.9705710687187049,
      "grad_norm": 0.3721691370010376,
      "learning_rate": 1.0487433609037581e-05,
      "loss": 0.573,
      "step": 31595
    },
    {
      "epoch": 0.970601787853654,
      "grad_norm": 0.4147168695926666,
      "learning_rate": 1.0486950905586471e-05,
      "loss": 0.5263,
      "step": 31596
    },
    {
      "epoch": 0.9706325069886031,
      "grad_norm": 0.4040277898311615,
      "learning_rate": 1.0486468200998051e-05,
      "loss": 0.524,
      "step": 31597
    },
    {
      "epoch": 0.9706632261235524,
      "grad_norm": 0.40527936816215515,
      "learning_rate": 1.0485985495273452e-05,
      "loss": 0.5279,
      "step": 31598
    },
    {
      "epoch": 0.9706939452585015,
      "grad_norm": 0.36210545897483826,
      "learning_rate": 1.0485502788413799e-05,
      "loss": 0.5743,
      "step": 31599
    },
    {
      "epoch": 0.9707246643934507,
      "grad_norm": 0.36723068356513977,
      "learning_rate": 1.0485020080420224e-05,
      "loss": 0.5649,
      "step": 31600
    },
    {
      "epoch": 0.9707553835283999,
      "grad_norm": 0.42020702362060547,
      "learning_rate": 1.0484537371293845e-05,
      "loss": 0.4629,
      "step": 31601
    },
    {
      "epoch": 0.970786102663349,
      "grad_norm": 0.41366374492645264,
      "learning_rate": 1.0484054661035799e-05,
      "loss": 0.6018,
      "step": 31602
    },
    {
      "epoch": 0.9708168217982982,
      "grad_norm": 0.38865697383880615,
      "learning_rate": 1.0483571949647207e-05,
      "loss": 0.5556,
      "step": 31603
    },
    {
      "epoch": 0.9708475409332473,
      "grad_norm": 0.3723064064979553,
      "learning_rate": 1.0483089237129202e-05,
      "loss": 0.5055,
      "step": 31604
    },
    {
      "epoch": 0.9708782600681964,
      "grad_norm": 0.3696882426738739,
      "learning_rate": 1.0482606523482907e-05,
      "loss": 0.5215,
      "step": 31605
    },
    {
      "epoch": 0.9709089792031457,
      "grad_norm": 0.7731230854988098,
      "learning_rate": 1.048212380870945e-05,
      "loss": 0.5397,
      "step": 31606
    },
    {
      "epoch": 0.9709396983380948,
      "grad_norm": 0.3783917725086212,
      "learning_rate": 1.0481641092809963e-05,
      "loss": 0.6254,
      "step": 31607
    },
    {
      "epoch": 0.9709704174730439,
      "grad_norm": 0.4347817003726959,
      "learning_rate": 1.0481158375785563e-05,
      "loss": 0.5114,
      "step": 31608
    },
    {
      "epoch": 0.9710011366079931,
      "grad_norm": 0.45428428053855896,
      "learning_rate": 1.048067565763739e-05,
      "loss": 0.6319,
      "step": 31609
    },
    {
      "epoch": 0.9710318557429423,
      "grad_norm": 0.3613196015357971,
      "learning_rate": 1.0480192938366558e-05,
      "loss": 0.5101,
      "step": 31610
    },
    {
      "epoch": 0.9710625748778915,
      "grad_norm": 0.34813493490219116,
      "learning_rate": 1.0479710217974208e-05,
      "loss": 0.4984,
      "step": 31611
    },
    {
      "epoch": 0.9710932940128406,
      "grad_norm": 0.3677864670753479,
      "learning_rate": 1.0479227496461459e-05,
      "loss": 0.5052,
      "step": 31612
    },
    {
      "epoch": 0.9711240131477897,
      "grad_norm": 0.39821264147758484,
      "learning_rate": 1.0478744773829442e-05,
      "loss": 0.5297,
      "step": 31613
    },
    {
      "epoch": 0.971154732282739,
      "grad_norm": 0.3579888343811035,
      "learning_rate": 1.0478262050079283e-05,
      "loss": 0.5161,
      "step": 31614
    },
    {
      "epoch": 0.9711854514176881,
      "grad_norm": 0.3287578225135803,
      "learning_rate": 1.0477779325212109e-05,
      "loss": 0.5549,
      "step": 31615
    },
    {
      "epoch": 0.9712161705526372,
      "grad_norm": 0.34841588139533997,
      "learning_rate": 1.047729659922905e-05,
      "loss": 0.5574,
      "step": 31616
    },
    {
      "epoch": 0.9712468896875864,
      "grad_norm": 0.33949705958366394,
      "learning_rate": 1.0476813872131228e-05,
      "loss": 0.5941,
      "step": 31617
    },
    {
      "epoch": 0.9712776088225356,
      "grad_norm": 0.34355372190475464,
      "learning_rate": 1.0476331143919776e-05,
      "loss": 0.5199,
      "step": 31618
    },
    {
      "epoch": 0.9713083279574847,
      "grad_norm": 0.3672342300415039,
      "learning_rate": 1.0475848414595818e-05,
      "loss": 0.474,
      "step": 31619
    },
    {
      "epoch": 0.9713390470924339,
      "grad_norm": 0.3922313153743744,
      "learning_rate": 1.0475365684160486e-05,
      "loss": 0.4933,
      "step": 31620
    },
    {
      "epoch": 0.971369766227383,
      "grad_norm": 0.3746148645877838,
      "learning_rate": 1.04748829526149e-05,
      "loss": 0.5395,
      "step": 31621
    },
    {
      "epoch": 0.9714004853623321,
      "grad_norm": 0.5751687288284302,
      "learning_rate": 1.0474400219960195e-05,
      "loss": 0.4846,
      "step": 31622
    },
    {
      "epoch": 0.9714312044972814,
      "grad_norm": 0.39324694871902466,
      "learning_rate": 1.0473917486197496e-05,
      "loss": 0.6266,
      "step": 31623
    },
    {
      "epoch": 0.9714619236322305,
      "grad_norm": 0.34184303879737854,
      "learning_rate": 1.0473434751327924e-05,
      "loss": 0.3962,
      "step": 31624
    },
    {
      "epoch": 0.9714926427671797,
      "grad_norm": 0.38958415389060974,
      "learning_rate": 1.0472952015352618e-05,
      "loss": 0.5343,
      "step": 31625
    },
    {
      "epoch": 0.9715233619021288,
      "grad_norm": 0.3596343398094177,
      "learning_rate": 1.0472469278272697e-05,
      "loss": 0.5559,
      "step": 31626
    },
    {
      "epoch": 0.971554081037078,
      "grad_norm": 0.4262900650501251,
      "learning_rate": 1.0471986540089292e-05,
      "loss": 0.5328,
      "step": 31627
    },
    {
      "epoch": 0.9715848001720272,
      "grad_norm": 0.3851257860660553,
      "learning_rate": 1.0471503800803527e-05,
      "loss": 0.583,
      "step": 31628
    },
    {
      "epoch": 0.9716155193069763,
      "grad_norm": 0.3810208737850189,
      "learning_rate": 1.047102106041653e-05,
      "loss": 0.5048,
      "step": 31629
    },
    {
      "epoch": 0.9716462384419254,
      "grad_norm": 0.35892030596733093,
      "learning_rate": 1.0470538318929438e-05,
      "loss": 0.5009,
      "step": 31630
    },
    {
      "epoch": 0.9716769575768747,
      "grad_norm": 0.3408537805080414,
      "learning_rate": 1.0470055576343366e-05,
      "loss": 0.517,
      "step": 31631
    },
    {
      "epoch": 0.9717076767118238,
      "grad_norm": 0.3496520519256592,
      "learning_rate": 1.0469572832659448e-05,
      "loss": 0.4703,
      "step": 31632
    },
    {
      "epoch": 0.9717383958467729,
      "grad_norm": 0.36936572194099426,
      "learning_rate": 1.0469090087878806e-05,
      "loss": 0.5443,
      "step": 31633
    },
    {
      "epoch": 0.9717691149817221,
      "grad_norm": 0.37108927965164185,
      "learning_rate": 1.0468607342002577e-05,
      "loss": 0.5556,
      "step": 31634
    },
    {
      "epoch": 0.9717998341166713,
      "grad_norm": 0.39539986848831177,
      "learning_rate": 1.0468124595031878e-05,
      "loss": 0.5166,
      "step": 31635
    },
    {
      "epoch": 0.9718305532516205,
      "grad_norm": 0.3903703987598419,
      "learning_rate": 1.0467641846967844e-05,
      "loss": 0.5101,
      "step": 31636
    },
    {
      "epoch": 0.9718612723865696,
      "grad_norm": 0.4007001519203186,
      "learning_rate": 1.0467159097811599e-05,
      "loss": 0.575,
      "step": 31637
    },
    {
      "epoch": 0.9718919915215187,
      "grad_norm": 0.48600417375564575,
      "learning_rate": 1.0466676347564273e-05,
      "loss": 0.5884,
      "step": 31638
    },
    {
      "epoch": 0.971922710656468,
      "grad_norm": 0.3581136465072632,
      "learning_rate": 1.0466193596226992e-05,
      "loss": 0.51,
      "step": 31639
    },
    {
      "epoch": 0.9719534297914171,
      "grad_norm": 0.3584838807582855,
      "learning_rate": 1.046571084380088e-05,
      "loss": 0.5212,
      "step": 31640
    },
    {
      "epoch": 0.9719841489263662,
      "grad_norm": 0.39481422305107117,
      "learning_rate": 1.0465228090287072e-05,
      "loss": 0.5961,
      "step": 31641
    },
    {
      "epoch": 0.9720148680613154,
      "grad_norm": 0.3776954114437103,
      "learning_rate": 1.0464745335686685e-05,
      "loss": 0.5838,
      "step": 31642
    },
    {
      "epoch": 0.9720455871962645,
      "grad_norm": 0.3926045894622803,
      "learning_rate": 1.0464262580000859e-05,
      "loss": 0.5238,
      "step": 31643
    },
    {
      "epoch": 0.9720763063312137,
      "grad_norm": 0.36088451743125916,
      "learning_rate": 1.0463779823230714e-05,
      "loss": 0.5852,
      "step": 31644
    },
    {
      "epoch": 0.9721070254661629,
      "grad_norm": 0.34080055356025696,
      "learning_rate": 1.0463297065377378e-05,
      "loss": 0.5782,
      "step": 31645
    },
    {
      "epoch": 0.972137744601112,
      "grad_norm": 0.3612198829650879,
      "learning_rate": 1.0462814306441978e-05,
      "loss": 0.6262,
      "step": 31646
    },
    {
      "epoch": 0.9721684637360611,
      "grad_norm": 0.41339752078056335,
      "learning_rate": 1.0462331546425641e-05,
      "loss": 0.5588,
      "step": 31647
    },
    {
      "epoch": 0.9721991828710104,
      "grad_norm": 0.4051739573478699,
      "learning_rate": 1.0461848785329502e-05,
      "loss": 0.5651,
      "step": 31648
    },
    {
      "epoch": 0.9722299020059595,
      "grad_norm": 0.37674662470817566,
      "learning_rate": 1.0461366023154677e-05,
      "loss": 0.4878,
      "step": 31649
    },
    {
      "epoch": 0.9722606211409087,
      "grad_norm": 0.378358393907547,
      "learning_rate": 1.0460883259902306e-05,
      "loss": 0.4558,
      "step": 31650
    },
    {
      "epoch": 0.9722913402758578,
      "grad_norm": 0.3620191216468811,
      "learning_rate": 1.0460400495573504e-05,
      "loss": 0.4766,
      "step": 31651
    },
    {
      "epoch": 0.972322059410807,
      "grad_norm": 0.4066103398799896,
      "learning_rate": 1.0459917730169408e-05,
      "loss": 0.5549,
      "step": 31652
    },
    {
      "epoch": 0.9723527785457562,
      "grad_norm": 0.39105284214019775,
      "learning_rate": 1.0459434963691143e-05,
      "loss": 0.6346,
      "step": 31653
    },
    {
      "epoch": 0.9723834976807053,
      "grad_norm": 0.4198315143585205,
      "learning_rate": 1.0458952196139833e-05,
      "loss": 0.604,
      "step": 31654
    },
    {
      "epoch": 0.9724142168156544,
      "grad_norm": 0.38698410987854004,
      "learning_rate": 1.0458469427516609e-05,
      "loss": 0.4075,
      "step": 31655
    },
    {
      "epoch": 0.9724449359506037,
      "grad_norm": 0.3670664131641388,
      "learning_rate": 1.04579866578226e-05,
      "loss": 0.473,
      "step": 31656
    },
    {
      "epoch": 0.9724756550855528,
      "grad_norm": 0.664344310760498,
      "learning_rate": 1.0457503887058928e-05,
      "loss": 0.4964,
      "step": 31657
    },
    {
      "epoch": 0.9725063742205019,
      "grad_norm": 0.33645278215408325,
      "learning_rate": 1.0457021115226722e-05,
      "loss": 0.5785,
      "step": 31658
    },
    {
      "epoch": 0.9725370933554511,
      "grad_norm": 0.35189223289489746,
      "learning_rate": 1.0456538342327117e-05,
      "loss": 0.4989,
      "step": 31659
    },
    {
      "epoch": 0.9725678124904003,
      "grad_norm": 0.3407069444656372,
      "learning_rate": 1.045605556836123e-05,
      "loss": 0.4471,
      "step": 31660
    },
    {
      "epoch": 0.9725985316253495,
      "grad_norm": 0.3706635534763336,
      "learning_rate": 1.0455572793330195e-05,
      "loss": 0.5072,
      "step": 31661
    },
    {
      "epoch": 0.9726292507602986,
      "grad_norm": 0.34976404905319214,
      "learning_rate": 1.0455090017235137e-05,
      "loss": 0.5305,
      "step": 31662
    },
    {
      "epoch": 0.9726599698952477,
      "grad_norm": 0.3936966061592102,
      "learning_rate": 1.0454607240077187e-05,
      "loss": 0.5266,
      "step": 31663
    },
    {
      "epoch": 0.972690689030197,
      "grad_norm": 0.3550461530685425,
      "learning_rate": 1.0454124461857467e-05,
      "loss": 0.5152,
      "step": 31664
    },
    {
      "epoch": 0.9727214081651461,
      "grad_norm": 0.36760470271110535,
      "learning_rate": 1.0453641682577108e-05,
      "loss": 0.5461,
      "step": 31665
    },
    {
      "epoch": 0.9727521273000952,
      "grad_norm": 0.37979018688201904,
      "learning_rate": 1.0453158902237237e-05,
      "loss": 0.5931,
      "step": 31666
    },
    {
      "epoch": 0.9727828464350444,
      "grad_norm": 0.3222266137599945,
      "learning_rate": 1.0452676120838982e-05,
      "loss": 0.581,
      "step": 31667
    },
    {
      "epoch": 0.9728135655699935,
      "grad_norm": 0.36130547523498535,
      "learning_rate": 1.0452193338383471e-05,
      "loss": 0.577,
      "step": 31668
    },
    {
      "epoch": 0.9728442847049427,
      "grad_norm": 0.4214039444923401,
      "learning_rate": 1.0451710554871832e-05,
      "loss": 0.5517,
      "step": 31669
    },
    {
      "epoch": 0.9728750038398919,
      "grad_norm": 0.36164847016334534,
      "learning_rate": 1.045122777030519e-05,
      "loss": 0.578,
      "step": 31670
    },
    {
      "epoch": 0.972905722974841,
      "grad_norm": 0.4615993797779083,
      "learning_rate": 1.0450744984684675e-05,
      "loss": 0.5701,
      "step": 31671
    },
    {
      "epoch": 0.9729364421097901,
      "grad_norm": 0.37631139159202576,
      "learning_rate": 1.0450262198011414e-05,
      "loss": 0.5881,
      "step": 31672
    },
    {
      "epoch": 0.9729671612447394,
      "grad_norm": 0.34962451457977295,
      "learning_rate": 1.0449779410286531e-05,
      "loss": 0.4971,
      "step": 31673
    },
    {
      "epoch": 0.9729978803796885,
      "grad_norm": 0.3916904926300049,
      "learning_rate": 1.044929662151116e-05,
      "loss": 0.505,
      "step": 31674
    },
    {
      "epoch": 0.9730285995146377,
      "grad_norm": 0.34764787554740906,
      "learning_rate": 1.0448813831686426e-05,
      "loss": 0.4994,
      "step": 31675
    },
    {
      "epoch": 0.9730593186495868,
      "grad_norm": 0.37518173456192017,
      "learning_rate": 1.0448331040813454e-05,
      "loss": 0.5452,
      "step": 31676
    },
    {
      "epoch": 0.973090037784536,
      "grad_norm": 0.3292928636074066,
      "learning_rate": 1.0447848248893376e-05,
      "loss": 0.5279,
      "step": 31677
    },
    {
      "epoch": 0.9731207569194852,
      "grad_norm": 0.3505244255065918,
      "learning_rate": 1.0447365455927312e-05,
      "loss": 0.4692,
      "step": 31678
    },
    {
      "epoch": 0.9731514760544343,
      "grad_norm": 0.3917117118835449,
      "learning_rate": 1.04468826619164e-05,
      "loss": 0.5611,
      "step": 31679
    },
    {
      "epoch": 0.9731821951893834,
      "grad_norm": 0.3418664038181305,
      "learning_rate": 1.0446399866861758e-05,
      "loss": 0.5036,
      "step": 31680
    },
    {
      "epoch": 0.9732129143243327,
      "grad_norm": 0.3909062445163727,
      "learning_rate": 1.0445917070764521e-05,
      "loss": 0.4917,
      "step": 31681
    },
    {
      "epoch": 0.9732436334592818,
      "grad_norm": 0.39646798372268677,
      "learning_rate": 1.0445434273625813e-05,
      "loss": 0.5429,
      "step": 31682
    },
    {
      "epoch": 0.9732743525942309,
      "grad_norm": 0.39745762944221497,
      "learning_rate": 1.044495147544676e-05,
      "loss": 0.6324,
      "step": 31683
    },
    {
      "epoch": 0.9733050717291801,
      "grad_norm": 0.36094731092453003,
      "learning_rate": 1.0444468676228495e-05,
      "loss": 0.5216,
      "step": 31684
    },
    {
      "epoch": 0.9733357908641292,
      "grad_norm": 0.37656477093696594,
      "learning_rate": 1.0443985875972137e-05,
      "loss": 0.5422,
      "step": 31685
    },
    {
      "epoch": 0.9733665099990785,
      "grad_norm": 0.42133378982543945,
      "learning_rate": 1.0443503074678825e-05,
      "loss": 0.5523,
      "step": 31686
    },
    {
      "epoch": 0.9733972291340276,
      "grad_norm": 0.39036816358566284,
      "learning_rate": 1.0443020272349678e-05,
      "loss": 0.5555,
      "step": 31687
    },
    {
      "epoch": 0.9734279482689767,
      "grad_norm": 0.3580911159515381,
      "learning_rate": 1.0442537468985827e-05,
      "loss": 0.535,
      "step": 31688
    },
    {
      "epoch": 0.973458667403926,
      "grad_norm": 0.40291744470596313,
      "learning_rate": 1.0442054664588397e-05,
      "loss": 0.5134,
      "step": 31689
    },
    {
      "epoch": 0.9734893865388751,
      "grad_norm": 0.3464770019054413,
      "learning_rate": 1.0441571859158521e-05,
      "loss": 0.5608,
      "step": 31690
    },
    {
      "epoch": 0.9735201056738242,
      "grad_norm": 0.3484649956226349,
      "learning_rate": 1.044108905269732e-05,
      "loss": 0.5251,
      "step": 31691
    },
    {
      "epoch": 0.9735508248087734,
      "grad_norm": 0.394458532333374,
      "learning_rate": 1.0440606245205926e-05,
      "loss": 0.5567,
      "step": 31692
    },
    {
      "epoch": 0.9735815439437225,
      "grad_norm": 0.40247583389282227,
      "learning_rate": 1.0440123436685467e-05,
      "loss": 0.5668,
      "step": 31693
    },
    {
      "epoch": 0.9736122630786717,
      "grad_norm": 0.39186885952949524,
      "learning_rate": 1.0439640627137067e-05,
      "loss": 0.5068,
      "step": 31694
    },
    {
      "epoch": 0.9736429822136209,
      "grad_norm": 0.3667524755001068,
      "learning_rate": 1.0439157816561856e-05,
      "loss": 0.6079,
      "step": 31695
    },
    {
      "epoch": 0.97367370134857,
      "grad_norm": 2.2328598499298096,
      "learning_rate": 1.0438675004960959e-05,
      "loss": 0.5182,
      "step": 31696
    },
    {
      "epoch": 0.9737044204835192,
      "grad_norm": 0.4311334788799286,
      "learning_rate": 1.043819219233551e-05,
      "loss": 0.5637,
      "step": 31697
    },
    {
      "epoch": 0.9737351396184684,
      "grad_norm": 0.3893047273159027,
      "learning_rate": 1.043770937868663e-05,
      "loss": 0.5601,
      "step": 31698
    },
    {
      "epoch": 0.9737658587534175,
      "grad_norm": 0.4187517464160919,
      "learning_rate": 1.0437226564015448e-05,
      "loss": 0.6214,
      "step": 31699
    },
    {
      "epoch": 0.9737965778883667,
      "grad_norm": 0.5849623680114746,
      "learning_rate": 1.0436743748323094e-05,
      "loss": 0.5997,
      "step": 31700
    },
    {
      "epoch": 0.9738272970233158,
      "grad_norm": 0.36580339074134827,
      "learning_rate": 1.0436260931610694e-05,
      "loss": 0.5466,
      "step": 31701
    },
    {
      "epoch": 0.973858016158265,
      "grad_norm": 0.3744162917137146,
      "learning_rate": 1.0435778113879378e-05,
      "loss": 0.5806,
      "step": 31702
    },
    {
      "epoch": 0.9738887352932142,
      "grad_norm": 0.3684847950935364,
      "learning_rate": 1.043529529513027e-05,
      "loss": 0.5683,
      "step": 31703
    },
    {
      "epoch": 0.9739194544281633,
      "grad_norm": 0.3652074933052063,
      "learning_rate": 1.04348124753645e-05,
      "loss": 0.5142,
      "step": 31704
    },
    {
      "epoch": 0.9739501735631124,
      "grad_norm": 0.3457178473472595,
      "learning_rate": 1.0434329654583194e-05,
      "loss": 0.5297,
      "step": 31705
    },
    {
      "epoch": 0.9739808926980617,
      "grad_norm": 0.3881971538066864,
      "learning_rate": 1.0433846832787484e-05,
      "loss": 0.5788,
      "step": 31706
    },
    {
      "epoch": 0.9740116118330108,
      "grad_norm": 0.6442381143569946,
      "learning_rate": 1.0433364009978491e-05,
      "loss": 0.5637,
      "step": 31707
    },
    {
      "epoch": 0.9740423309679599,
      "grad_norm": 0.3546704053878784,
      "learning_rate": 1.0432881186157348e-05,
      "loss": 0.5168,
      "step": 31708
    },
    {
      "epoch": 0.9740730501029091,
      "grad_norm": 0.3925181031227112,
      "learning_rate": 1.0432398361325182e-05,
      "loss": 0.5327,
      "step": 31709
    },
    {
      "epoch": 0.9741037692378582,
      "grad_norm": 0.38471102714538574,
      "learning_rate": 1.0431915535483116e-05,
      "loss": 0.5677,
      "step": 31710
    },
    {
      "epoch": 0.9741344883728075,
      "grad_norm": 0.389973908662796,
      "learning_rate": 1.0431432708632286e-05,
      "loss": 0.51,
      "step": 31711
    },
    {
      "epoch": 0.9741652075077566,
      "grad_norm": 0.35187774896621704,
      "learning_rate": 1.0430949880773808e-05,
      "loss": 0.5094,
      "step": 31712
    },
    {
      "epoch": 0.9741959266427057,
      "grad_norm": 0.36420732736587524,
      "learning_rate": 1.0430467051908821e-05,
      "loss": 0.5367,
      "step": 31713
    },
    {
      "epoch": 0.9742266457776549,
      "grad_norm": 0.3667846918106079,
      "learning_rate": 1.0429984222038447e-05,
      "loss": 0.4926,
      "step": 31714
    },
    {
      "epoch": 0.9742573649126041,
      "grad_norm": 0.3470425307750702,
      "learning_rate": 1.0429501391163817e-05,
      "loss": 0.5527,
      "step": 31715
    },
    {
      "epoch": 0.9742880840475532,
      "grad_norm": 0.3793902099132538,
      "learning_rate": 1.0429018559286052e-05,
      "loss": 0.5463,
      "step": 31716
    },
    {
      "epoch": 0.9743188031825024,
      "grad_norm": 0.4066644310951233,
      "learning_rate": 1.0428535726406288e-05,
      "loss": 0.5913,
      "step": 31717
    },
    {
      "epoch": 0.9743495223174515,
      "grad_norm": 0.386191725730896,
      "learning_rate": 1.0428052892525647e-05,
      "loss": 0.5781,
      "step": 31718
    },
    {
      "epoch": 0.9743802414524007,
      "grad_norm": 0.3767086863517761,
      "learning_rate": 1.0427570057645257e-05,
      "loss": 0.5873,
      "step": 31719
    },
    {
      "epoch": 0.9744109605873499,
      "grad_norm": 0.4875081777572632,
      "learning_rate": 1.042708722176625e-05,
      "loss": 0.61,
      "step": 31720
    },
    {
      "epoch": 0.974441679722299,
      "grad_norm": 0.3366873562335968,
      "learning_rate": 1.042660438488975e-05,
      "loss": 0.4985,
      "step": 31721
    },
    {
      "epoch": 0.9744723988572482,
      "grad_norm": 0.3486553728580475,
      "learning_rate": 1.0426121547016887e-05,
      "loss": 0.5688,
      "step": 31722
    },
    {
      "epoch": 0.9745031179921974,
      "grad_norm": 0.37633031606674194,
      "learning_rate": 1.0425638708148786e-05,
      "loss": 0.5882,
      "step": 31723
    },
    {
      "epoch": 0.9745338371271465,
      "grad_norm": 0.3910212218761444,
      "learning_rate": 1.0425155868286578e-05,
      "loss": 0.5548,
      "step": 31724
    },
    {
      "epoch": 0.9745645562620957,
      "grad_norm": 0.3756842613220215,
      "learning_rate": 1.0424673027431384e-05,
      "loss": 0.5761,
      "step": 31725
    },
    {
      "epoch": 0.9745952753970448,
      "grad_norm": 0.3567489683628082,
      "learning_rate": 1.0424190185584341e-05,
      "loss": 0.5363,
      "step": 31726
    },
    {
      "epoch": 0.9746259945319939,
      "grad_norm": 0.40549495816230774,
      "learning_rate": 1.0423707342746574e-05,
      "loss": 0.6353,
      "step": 31727
    },
    {
      "epoch": 0.9746567136669432,
      "grad_norm": 0.39330926537513733,
      "learning_rate": 1.0423224498919204e-05,
      "loss": 0.6192,
      "step": 31728
    },
    {
      "epoch": 0.9746874328018923,
      "grad_norm": 0.7695876955986023,
      "learning_rate": 1.0422741654103365e-05,
      "loss": 0.5153,
      "step": 31729
    },
    {
      "epoch": 0.9747181519368414,
      "grad_norm": 0.3837186098098755,
      "learning_rate": 1.0422258808300186e-05,
      "loss": 0.537,
      "step": 31730
    },
    {
      "epoch": 0.9747488710717906,
      "grad_norm": 0.35759156942367554,
      "learning_rate": 1.0421775961510789e-05,
      "loss": 0.3948,
      "step": 31731
    },
    {
      "epoch": 0.9747795902067398,
      "grad_norm": 0.36448514461517334,
      "learning_rate": 1.0421293113736303e-05,
      "loss": 0.4855,
      "step": 31732
    },
    {
      "epoch": 0.9748103093416889,
      "grad_norm": 0.42020484805107117,
      "learning_rate": 1.0420810264977863e-05,
      "loss": 0.5701,
      "step": 31733
    },
    {
      "epoch": 0.9748410284766381,
      "grad_norm": 0.4496251046657562,
      "learning_rate": 1.0420327415236586e-05,
      "loss": 0.5213,
      "step": 31734
    },
    {
      "epoch": 0.9748717476115872,
      "grad_norm": 0.45878395438194275,
      "learning_rate": 1.041984456451361e-05,
      "loss": 0.5214,
      "step": 31735
    },
    {
      "epoch": 0.9749024667465365,
      "grad_norm": 0.373402863740921,
      "learning_rate": 1.0419361712810054e-05,
      "loss": 0.5099,
      "step": 31736
    },
    {
      "epoch": 0.9749331858814856,
      "grad_norm": 0.4473849833011627,
      "learning_rate": 1.0418878860127051e-05,
      "loss": 0.5218,
      "step": 31737
    },
    {
      "epoch": 0.9749639050164347,
      "grad_norm": 0.40925267338752747,
      "learning_rate": 1.0418396006465725e-05,
      "loss": 0.5567,
      "step": 31738
    },
    {
      "epoch": 0.9749946241513839,
      "grad_norm": 0.3737342953681946,
      "learning_rate": 1.0417913151827208e-05,
      "loss": 0.5364,
      "step": 31739
    },
    {
      "epoch": 0.9750253432863331,
      "grad_norm": 0.3575590252876282,
      "learning_rate": 1.0417430296212626e-05,
      "loss": 0.4604,
      "step": 31740
    },
    {
      "epoch": 0.9750560624212822,
      "grad_norm": 0.3412824869155884,
      "learning_rate": 1.0416947439623104e-05,
      "loss": 0.5577,
      "step": 31741
    },
    {
      "epoch": 0.9750867815562314,
      "grad_norm": 0.3810481131076813,
      "learning_rate": 1.0416464582059775e-05,
      "loss": 0.5402,
      "step": 31742
    },
    {
      "epoch": 0.9751175006911805,
      "grad_norm": 0.40847325325012207,
      "learning_rate": 1.0415981723523761e-05,
      "loss": 0.5092,
      "step": 31743
    },
    {
      "epoch": 0.9751482198261296,
      "grad_norm": 0.35818222165107727,
      "learning_rate": 1.0415498864016195e-05,
      "loss": 0.5439,
      "step": 31744
    },
    {
      "epoch": 0.9751789389610789,
      "grad_norm": 0.48065656423568726,
      "learning_rate": 1.0415016003538204e-05,
      "loss": 0.4885,
      "step": 31745
    },
    {
      "epoch": 0.975209658096028,
      "grad_norm": 0.3533862829208374,
      "learning_rate": 1.041453314209091e-05,
      "loss": 0.5185,
      "step": 31746
    },
    {
      "epoch": 0.9752403772309772,
      "grad_norm": 0.38209784030914307,
      "learning_rate": 1.0414050279675447e-05,
      "loss": 0.5107,
      "step": 31747
    },
    {
      "epoch": 0.9752710963659263,
      "grad_norm": 0.42415711283683777,
      "learning_rate": 1.041356741629294e-05,
      "loss": 0.5655,
      "step": 31748
    },
    {
      "epoch": 0.9753018155008755,
      "grad_norm": 0.3698064982891083,
      "learning_rate": 1.0413084551944519e-05,
      "loss": 0.5449,
      "step": 31749
    },
    {
      "epoch": 0.9753325346358247,
      "grad_norm": 0.43311718106269836,
      "learning_rate": 1.0412601686631308e-05,
      "loss": 0.5008,
      "step": 31750
    },
    {
      "epoch": 0.9753632537707738,
      "grad_norm": 0.39226260781288147,
      "learning_rate": 1.0412118820354439e-05,
      "loss": 0.5675,
      "step": 31751
    },
    {
      "epoch": 0.9753939729057229,
      "grad_norm": 0.5346664786338806,
      "learning_rate": 1.0411635953115036e-05,
      "loss": 0.6131,
      "step": 31752
    },
    {
      "epoch": 0.9754246920406722,
      "grad_norm": 0.4796568751335144,
      "learning_rate": 1.0411153084914229e-05,
      "loss": 0.462,
      "step": 31753
    },
    {
      "epoch": 0.9754554111756213,
      "grad_norm": 0.35523420572280884,
      "learning_rate": 1.0410670215753145e-05,
      "loss": 0.5367,
      "step": 31754
    },
    {
      "epoch": 0.9754861303105704,
      "grad_norm": 0.37570008635520935,
      "learning_rate": 1.0410187345632914e-05,
      "loss": 0.5205,
      "step": 31755
    },
    {
      "epoch": 0.9755168494455196,
      "grad_norm": 0.36763226985931396,
      "learning_rate": 1.0409704474554658e-05,
      "loss": 0.5508,
      "step": 31756
    },
    {
      "epoch": 0.9755475685804688,
      "grad_norm": 0.3975234031677246,
      "learning_rate": 1.040922160251951e-05,
      "loss": 0.5523,
      "step": 31757
    },
    {
      "epoch": 0.9755782877154179,
      "grad_norm": 0.3496290147304535,
      "learning_rate": 1.0408738729528598e-05,
      "loss": 0.4697,
      "step": 31758
    },
    {
      "epoch": 0.9756090068503671,
      "grad_norm": 0.3768047094345093,
      "learning_rate": 1.0408255855583047e-05,
      "loss": 0.5602,
      "step": 31759
    },
    {
      "epoch": 0.9756397259853162,
      "grad_norm": 0.3603276312351227,
      "learning_rate": 1.0407772980683986e-05,
      "loss": 0.5286,
      "step": 31760
    },
    {
      "epoch": 0.9756704451202655,
      "grad_norm": 0.37816518545150757,
      "learning_rate": 1.0407290104832544e-05,
      "loss": 0.5104,
      "step": 31761
    },
    {
      "epoch": 0.9757011642552146,
      "grad_norm": 0.41026052832603455,
      "learning_rate": 1.0406807228029846e-05,
      "loss": 0.4927,
      "step": 31762
    },
    {
      "epoch": 0.9757318833901637,
      "grad_norm": 0.38986316323280334,
      "learning_rate": 1.0406324350277022e-05,
      "loss": 0.6257,
      "step": 31763
    },
    {
      "epoch": 0.9757626025251129,
      "grad_norm": 0.3849495053291321,
      "learning_rate": 1.0405841471575197e-05,
      "loss": 0.575,
      "step": 31764
    },
    {
      "epoch": 0.975793321660062,
      "grad_norm": 0.40273213386535645,
      "learning_rate": 1.0405358591925504e-05,
      "loss": 0.5342,
      "step": 31765
    },
    {
      "epoch": 0.9758240407950112,
      "grad_norm": 0.37506210803985596,
      "learning_rate": 1.0404875711329066e-05,
      "loss": 0.6326,
      "step": 31766
    },
    {
      "epoch": 0.9758547599299604,
      "grad_norm": 0.3436989486217499,
      "learning_rate": 1.0404392829787016e-05,
      "loss": 0.5642,
      "step": 31767
    },
    {
      "epoch": 0.9758854790649095,
      "grad_norm": 0.3619338572025299,
      "learning_rate": 1.0403909947300472e-05,
      "loss": 0.5895,
      "step": 31768
    },
    {
      "epoch": 0.9759161981998586,
      "grad_norm": 0.33303943276405334,
      "learning_rate": 1.0403427063870572e-05,
      "loss": 0.5089,
      "step": 31769
    },
    {
      "epoch": 0.9759469173348079,
      "grad_norm": 0.36806824803352356,
      "learning_rate": 1.040294417949844e-05,
      "loss": 0.513,
      "step": 31770
    },
    {
      "epoch": 0.975977636469757,
      "grad_norm": 0.39438775181770325,
      "learning_rate": 1.0402461294185204e-05,
      "loss": 0.5132,
      "step": 31771
    },
    {
      "epoch": 0.9760083556047062,
      "grad_norm": 0.45494526624679565,
      "learning_rate": 1.0401978407931992e-05,
      "loss": 0.5594,
      "step": 31772
    },
    {
      "epoch": 0.9760390747396553,
      "grad_norm": 0.3860984146595001,
      "learning_rate": 1.0401495520739928e-05,
      "loss": 0.5502,
      "step": 31773
    },
    {
      "epoch": 0.9760697938746045,
      "grad_norm": 0.3698650598526001,
      "learning_rate": 1.0401012632610143e-05,
      "loss": 0.5233,
      "step": 31774
    },
    {
      "epoch": 0.9761005130095537,
      "grad_norm": 0.35371729731559753,
      "learning_rate": 1.0400529743543765e-05,
      "loss": 0.5801,
      "step": 31775
    },
    {
      "epoch": 0.9761312321445028,
      "grad_norm": 0.34774452447891235,
      "learning_rate": 1.0400046853541927e-05,
      "loss": 0.4963,
      "step": 31776
    },
    {
      "epoch": 0.9761619512794519,
      "grad_norm": 0.40209072828292847,
      "learning_rate": 1.0399563962605748e-05,
      "loss": 0.5427,
      "step": 31777
    },
    {
      "epoch": 0.9761926704144012,
      "grad_norm": 0.49042102694511414,
      "learning_rate": 1.0399081070736362e-05,
      "loss": 0.5437,
      "step": 31778
    },
    {
      "epoch": 0.9762233895493503,
      "grad_norm": 0.3823484778404236,
      "learning_rate": 1.0398598177934892e-05,
      "loss": 0.524,
      "step": 31779
    },
    {
      "epoch": 0.9762541086842994,
      "grad_norm": 0.49533891677856445,
      "learning_rate": 1.0398115284202465e-05,
      "loss": 0.582,
      "step": 31780
    },
    {
      "epoch": 0.9762848278192486,
      "grad_norm": 0.3466375172138214,
      "learning_rate": 1.0397632389540218e-05,
      "loss": 0.5622,
      "step": 31781
    },
    {
      "epoch": 0.9763155469541978,
      "grad_norm": 0.3666720390319824,
      "learning_rate": 1.039714949394927e-05,
      "loss": 0.5269,
      "step": 31782
    },
    {
      "epoch": 0.9763462660891469,
      "grad_norm": 0.38320642709732056,
      "learning_rate": 1.039666659743075e-05,
      "loss": 0.5887,
      "step": 31783
    },
    {
      "epoch": 0.9763769852240961,
      "grad_norm": 0.45933330059051514,
      "learning_rate": 1.039618369998579e-05,
      "loss": 0.5229,
      "step": 31784
    },
    {
      "epoch": 0.9764077043590452,
      "grad_norm": 0.3685220181941986,
      "learning_rate": 1.0395700801615516e-05,
      "loss": 0.5767,
      "step": 31785
    },
    {
      "epoch": 0.9764384234939945,
      "grad_norm": 0.400175541639328,
      "learning_rate": 1.0395217902321053e-05,
      "loss": 0.5102,
      "step": 31786
    },
    {
      "epoch": 0.9764691426289436,
      "grad_norm": 0.39334940910339355,
      "learning_rate": 1.0394735002103533e-05,
      "loss": 0.5452,
      "step": 31787
    },
    {
      "epoch": 0.9764998617638927,
      "grad_norm": 0.49555397033691406,
      "learning_rate": 1.0394252100964078e-05,
      "loss": 0.6094,
      "step": 31788
    },
    {
      "epoch": 0.9765305808988419,
      "grad_norm": 0.344706654548645,
      "learning_rate": 1.0393769198903823e-05,
      "loss": 0.4994,
      "step": 31789
    },
    {
      "epoch": 0.976561300033791,
      "grad_norm": 0.37986457347869873,
      "learning_rate": 1.0393286295923892e-05,
      "loss": 0.6368,
      "step": 31790
    },
    {
      "epoch": 0.9765920191687402,
      "grad_norm": 0.38612863421440125,
      "learning_rate": 1.0392803392025413e-05,
      "loss": 0.4875,
      "step": 31791
    },
    {
      "epoch": 0.9766227383036894,
      "grad_norm": 0.35136961936950684,
      "learning_rate": 1.0392320487209513e-05,
      "loss": 0.5404,
      "step": 31792
    },
    {
      "epoch": 0.9766534574386385,
      "grad_norm": 0.34633854031562805,
      "learning_rate": 1.0391837581477323e-05,
      "loss": 0.598,
      "step": 31793
    },
    {
      "epoch": 0.9766841765735876,
      "grad_norm": 0.39858752489089966,
      "learning_rate": 1.0391354674829968e-05,
      "loss": 0.5489,
      "step": 31794
    },
    {
      "epoch": 0.9767148957085369,
      "grad_norm": 0.4272110164165497,
      "learning_rate": 1.0390871767268576e-05,
      "loss": 0.564,
      "step": 31795
    },
    {
      "epoch": 0.976745614843486,
      "grad_norm": 0.44686657190322876,
      "learning_rate": 1.0390388858794278e-05,
      "loss": 0.571,
      "step": 31796
    },
    {
      "epoch": 0.9767763339784352,
      "grad_norm": 0.36476486921310425,
      "learning_rate": 1.03899059494082e-05,
      "loss": 0.5838,
      "step": 31797
    },
    {
      "epoch": 0.9768070531133843,
      "grad_norm": 0.3562127351760864,
      "learning_rate": 1.0389423039111466e-05,
      "loss": 0.5581,
      "step": 31798
    },
    {
      "epoch": 0.9768377722483335,
      "grad_norm": 0.39606910943984985,
      "learning_rate": 1.0388940127905212e-05,
      "loss": 0.5395,
      "step": 31799
    },
    {
      "epoch": 0.9768684913832827,
      "grad_norm": 0.37542226910591125,
      "learning_rate": 1.0388457215790555e-05,
      "loss": 0.5523,
      "step": 31800
    },
    {
      "epoch": 0.9768992105182318,
      "grad_norm": 0.5666344165802002,
      "learning_rate": 1.0387974302768635e-05,
      "loss": 0.5352,
      "step": 31801
    },
    {
      "epoch": 0.9769299296531809,
      "grad_norm": 0.3550601303577423,
      "learning_rate": 1.038749138884057e-05,
      "loss": 0.4912,
      "step": 31802
    },
    {
      "epoch": 0.9769606487881302,
      "grad_norm": 0.39865022897720337,
      "learning_rate": 1.0387008474007494e-05,
      "loss": 0.5264,
      "step": 31803
    },
    {
      "epoch": 0.9769913679230793,
      "grad_norm": 0.3354753851890564,
      "learning_rate": 1.038652555827053e-05,
      "loss": 0.4761,
      "step": 31804
    },
    {
      "epoch": 0.9770220870580284,
      "grad_norm": 0.3739648163318634,
      "learning_rate": 1.0386042641630812e-05,
      "loss": 0.568,
      "step": 31805
    },
    {
      "epoch": 0.9770528061929776,
      "grad_norm": 0.49911996722221375,
      "learning_rate": 1.0385559724089463e-05,
      "loss": 0.5441,
      "step": 31806
    },
    {
      "epoch": 0.9770835253279267,
      "grad_norm": 0.4647774398326874,
      "learning_rate": 1.0385076805647611e-05,
      "loss": 0.4541,
      "step": 31807
    },
    {
      "epoch": 0.977114244462876,
      "grad_norm": 0.39837074279785156,
      "learning_rate": 1.0384593886306388e-05,
      "loss": 0.5621,
      "step": 31808
    },
    {
      "epoch": 0.9771449635978251,
      "grad_norm": 0.3670060634613037,
      "learning_rate": 1.0384110966066916e-05,
      "loss": 0.4954,
      "step": 31809
    },
    {
      "epoch": 0.9771756827327742,
      "grad_norm": 0.4054301679134369,
      "learning_rate": 1.0383628044930329e-05,
      "loss": 0.5312,
      "step": 31810
    },
    {
      "epoch": 0.9772064018677235,
      "grad_norm": 0.3611025810241699,
      "learning_rate": 1.0383145122897747e-05,
      "loss": 0.5586,
      "step": 31811
    },
    {
      "epoch": 0.9772371210026726,
      "grad_norm": 0.3635924160480499,
      "learning_rate": 1.0382662199970309e-05,
      "loss": 0.4587,
      "step": 31812
    },
    {
      "epoch": 0.9772678401376217,
      "grad_norm": 0.4039316773414612,
      "learning_rate": 1.0382179276149134e-05,
      "loss": 0.5011,
      "step": 31813
    },
    {
      "epoch": 0.9772985592725709,
      "grad_norm": 0.3753242790699005,
      "learning_rate": 1.038169635143535e-05,
      "loss": 0.5692,
      "step": 31814
    },
    {
      "epoch": 0.97732927840752,
      "grad_norm": 0.34865444898605347,
      "learning_rate": 1.0381213425830092e-05,
      "loss": 0.5438,
      "step": 31815
    },
    {
      "epoch": 0.9773599975424692,
      "grad_norm": 0.36565086245536804,
      "learning_rate": 1.0380730499334482e-05,
      "loss": 0.5365,
      "step": 31816
    },
    {
      "epoch": 0.9773907166774184,
      "grad_norm": 0.3835081458091736,
      "learning_rate": 1.038024757194965e-05,
      "loss": 0.5625,
      "step": 31817
    },
    {
      "epoch": 0.9774214358123675,
      "grad_norm": 0.4596021771430969,
      "learning_rate": 1.037976464367672e-05,
      "loss": 0.5298,
      "step": 31818
    },
    {
      "epoch": 0.9774521549473166,
      "grad_norm": 0.3540317714214325,
      "learning_rate": 1.0379281714516825e-05,
      "loss": 0.5216,
      "step": 31819
    },
    {
      "epoch": 0.9774828740822659,
      "grad_norm": 0.3067481815814972,
      "learning_rate": 1.0378798784471091e-05,
      "loss": 0.5326,
      "step": 31820
    },
    {
      "epoch": 0.977513593217215,
      "grad_norm": 0.38077476620674133,
      "learning_rate": 1.0378315853540648e-05,
      "loss": 0.5737,
      "step": 31821
    },
    {
      "epoch": 0.9775443123521642,
      "grad_norm": 0.3966257870197296,
      "learning_rate": 1.0377832921726618e-05,
      "loss": 0.6019,
      "step": 31822
    },
    {
      "epoch": 0.9775750314871133,
      "grad_norm": 0.5639654994010925,
      "learning_rate": 1.0377349989030137e-05,
      "loss": 0.5193,
      "step": 31823
    },
    {
      "epoch": 0.9776057506220625,
      "grad_norm": 0.33979514241218567,
      "learning_rate": 1.0376867055452327e-05,
      "loss": 0.5075,
      "step": 31824
    },
    {
      "epoch": 0.9776364697570117,
      "grad_norm": 0.8125075697898865,
      "learning_rate": 1.0376384120994315e-05,
      "loss": 0.5751,
      "step": 31825
    },
    {
      "epoch": 0.9776671888919608,
      "grad_norm": 0.4882851839065552,
      "learning_rate": 1.0375901185657236e-05,
      "loss": 0.6143,
      "step": 31826
    },
    {
      "epoch": 0.9776979080269099,
      "grad_norm": 0.3492678105831146,
      "learning_rate": 1.037541824944221e-05,
      "loss": 0.522,
      "step": 31827
    },
    {
      "epoch": 0.9777286271618592,
      "grad_norm": 0.5231125950813293,
      "learning_rate": 1.0374935312350372e-05,
      "loss": 0.5082,
      "step": 31828
    },
    {
      "epoch": 0.9777593462968083,
      "grad_norm": 0.4409152865409851,
      "learning_rate": 1.037445237438284e-05,
      "loss": 0.6011,
      "step": 31829
    },
    {
      "epoch": 0.9777900654317574,
      "grad_norm": 0.36328673362731934,
      "learning_rate": 1.0373969435540755e-05,
      "loss": 0.5614,
      "step": 31830
    },
    {
      "epoch": 0.9778207845667066,
      "grad_norm": 0.41297417879104614,
      "learning_rate": 1.0373486495825235e-05,
      "loss": 0.5598,
      "step": 31831
    },
    {
      "epoch": 0.9778515037016557,
      "grad_norm": 0.3741563558578491,
      "learning_rate": 1.0373003555237414e-05,
      "loss": 0.5036,
      "step": 31832
    },
    {
      "epoch": 0.977882222836605,
      "grad_norm": 0.34850892424583435,
      "learning_rate": 1.0372520613778414e-05,
      "loss": 0.5655,
      "step": 31833
    },
    {
      "epoch": 0.9779129419715541,
      "grad_norm": 0.6769770383834839,
      "learning_rate": 1.0372037671449366e-05,
      "loss": 0.6138,
      "step": 31834
    },
    {
      "epoch": 0.9779436611065032,
      "grad_norm": 0.44338032603263855,
      "learning_rate": 1.0371554728251401e-05,
      "loss": 0.4858,
      "step": 31835
    },
    {
      "epoch": 0.9779743802414524,
      "grad_norm": 0.3721037805080414,
      "learning_rate": 1.0371071784185642e-05,
      "loss": 0.5192,
      "step": 31836
    },
    {
      "epoch": 0.9780050993764016,
      "grad_norm": 0.4055984616279602,
      "learning_rate": 1.037058883925322e-05,
      "loss": 0.5113,
      "step": 31837
    },
    {
      "epoch": 0.9780358185113507,
      "grad_norm": 0.33181315660476685,
      "learning_rate": 1.037010589345526e-05,
      "loss": 0.4828,
      "step": 31838
    },
    {
      "epoch": 0.9780665376462999,
      "grad_norm": 0.3731290400028229,
      "learning_rate": 1.0369622946792895e-05,
      "loss": 0.4927,
      "step": 31839
    },
    {
      "epoch": 0.978097256781249,
      "grad_norm": 0.3782953917980194,
      "learning_rate": 1.0369139999267245e-05,
      "loss": 0.5773,
      "step": 31840
    },
    {
      "epoch": 0.9781279759161982,
      "grad_norm": 0.37980955839157104,
      "learning_rate": 1.0368657050879447e-05,
      "loss": 0.6255,
      "step": 31841
    },
    {
      "epoch": 0.9781586950511474,
      "grad_norm": 0.3949737846851349,
      "learning_rate": 1.0368174101630625e-05,
      "loss": 0.6028,
      "step": 31842
    },
    {
      "epoch": 0.9781894141860965,
      "grad_norm": 0.4198267459869385,
      "learning_rate": 1.0367691151521903e-05,
      "loss": 0.5527,
      "step": 31843
    },
    {
      "epoch": 0.9782201333210456,
      "grad_norm": 0.36444488167762756,
      "learning_rate": 1.0367208200554417e-05,
      "loss": 0.5722,
      "step": 31844
    },
    {
      "epoch": 0.9782508524559949,
      "grad_norm": 0.522026538848877,
      "learning_rate": 1.0366725248729287e-05,
      "loss": 0.5233,
      "step": 31845
    },
    {
      "epoch": 0.978281571590944,
      "grad_norm": 0.3235233426094055,
      "learning_rate": 1.0366242296047647e-05,
      "loss": 0.5257,
      "step": 31846
    },
    {
      "epoch": 0.9783122907258932,
      "grad_norm": 0.4039902985095978,
      "learning_rate": 1.0365759342510618e-05,
      "loss": 0.5523,
      "step": 31847
    },
    {
      "epoch": 0.9783430098608423,
      "grad_norm": 0.36408674716949463,
      "learning_rate": 1.0365276388119336e-05,
      "loss": 0.6072,
      "step": 31848
    },
    {
      "epoch": 0.9783737289957914,
      "grad_norm": 0.36652442812919617,
      "learning_rate": 1.0364793432874926e-05,
      "loss": 0.5448,
      "step": 31849
    },
    {
      "epoch": 0.9784044481307407,
      "grad_norm": 0.35579001903533936,
      "learning_rate": 1.0364310476778514e-05,
      "loss": 0.5637,
      "step": 31850
    },
    {
      "epoch": 0.9784351672656898,
      "grad_norm": 0.46509498357772827,
      "learning_rate": 1.0363827519831233e-05,
      "loss": 0.585,
      "step": 31851
    },
    {
      "epoch": 0.9784658864006389,
      "grad_norm": 0.4034658968448639,
      "learning_rate": 1.0363344562034204e-05,
      "loss": 0.5424,
      "step": 31852
    },
    {
      "epoch": 0.9784966055355881,
      "grad_norm": 0.3502601385116577,
      "learning_rate": 1.0362861603388559e-05,
      "loss": 0.6203,
      "step": 31853
    },
    {
      "epoch": 0.9785273246705373,
      "grad_norm": 0.40994277596473694,
      "learning_rate": 1.0362378643895426e-05,
      "loss": 0.5638,
      "step": 31854
    },
    {
      "epoch": 0.9785580438054864,
      "grad_norm": 0.3465573191642761,
      "learning_rate": 1.0361895683555932e-05,
      "loss": 0.5124,
      "step": 31855
    },
    {
      "epoch": 0.9785887629404356,
      "grad_norm": 0.35198840498924255,
      "learning_rate": 1.0361412722371202e-05,
      "loss": 0.4921,
      "step": 31856
    },
    {
      "epoch": 0.9786194820753847,
      "grad_norm": 0.3710830807685852,
      "learning_rate": 1.0360929760342373e-05,
      "loss": 0.595,
      "step": 31857
    },
    {
      "epoch": 0.978650201210334,
      "grad_norm": 0.38003620505332947,
      "learning_rate": 1.0360446797470565e-05,
      "loss": 0.5588,
      "step": 31858
    },
    {
      "epoch": 0.9786809203452831,
      "grad_norm": 0.352708101272583,
      "learning_rate": 1.0359963833756908e-05,
      "loss": 0.5666,
      "step": 31859
    },
    {
      "epoch": 0.9787116394802322,
      "grad_norm": 0.44546350836753845,
      "learning_rate": 1.0359480869202532e-05,
      "loss": 0.6706,
      "step": 31860
    },
    {
      "epoch": 0.9787423586151814,
      "grad_norm": 0.3723531663417816,
      "learning_rate": 1.0358997903808562e-05,
      "loss": 0.6182,
      "step": 31861
    },
    {
      "epoch": 0.9787730777501306,
      "grad_norm": 0.8350784778594971,
      "learning_rate": 1.0358514937576127e-05,
      "loss": 0.6341,
      "step": 31862
    },
    {
      "epoch": 0.9788037968850797,
      "grad_norm": 0.5879863500595093,
      "learning_rate": 1.0358031970506354e-05,
      "loss": 0.5348,
      "step": 31863
    },
    {
      "epoch": 0.9788345160200289,
      "grad_norm": 0.3423125445842743,
      "learning_rate": 1.0357549002600375e-05,
      "loss": 0.6145,
      "step": 31864
    },
    {
      "epoch": 0.978865235154978,
      "grad_norm": 0.3890472650527954,
      "learning_rate": 1.0357066033859313e-05,
      "loss": 0.5264,
      "step": 31865
    },
    {
      "epoch": 0.9788959542899272,
      "grad_norm": 0.36578455567359924,
      "learning_rate": 1.0356583064284299e-05,
      "loss": 0.5261,
      "step": 31866
    },
    {
      "epoch": 0.9789266734248764,
      "grad_norm": 0.46511027216911316,
      "learning_rate": 1.035610009387646e-05,
      "loss": 0.5467,
      "step": 31867
    },
    {
      "epoch": 0.9789573925598255,
      "grad_norm": 0.36492007970809937,
      "learning_rate": 1.0355617122636924e-05,
      "loss": 0.5813,
      "step": 31868
    },
    {
      "epoch": 0.9789881116947746,
      "grad_norm": 0.37562286853790283,
      "learning_rate": 1.0355134150566823e-05,
      "loss": 0.61,
      "step": 31869
    },
    {
      "epoch": 0.9790188308297239,
      "grad_norm": 0.40181756019592285,
      "learning_rate": 1.0354651177667277e-05,
      "loss": 0.4971,
      "step": 31870
    },
    {
      "epoch": 0.979049549964673,
      "grad_norm": 0.4207066595554352,
      "learning_rate": 1.035416820393942e-05,
      "loss": 0.5728,
      "step": 31871
    },
    {
      "epoch": 0.9790802690996222,
      "grad_norm": 0.34430626034736633,
      "learning_rate": 1.035368522938438e-05,
      "loss": 0.4963,
      "step": 31872
    },
    {
      "epoch": 0.9791109882345713,
      "grad_norm": 0.3439619541168213,
      "learning_rate": 1.0353202254003283e-05,
      "loss": 0.5687,
      "step": 31873
    },
    {
      "epoch": 0.9791417073695204,
      "grad_norm": 0.3822717070579529,
      "learning_rate": 1.0352719277797256e-05,
      "loss": 0.4935,
      "step": 31874
    },
    {
      "epoch": 0.9791724265044697,
      "grad_norm": 0.386073499917984,
      "learning_rate": 1.035223630076743e-05,
      "loss": 0.5209,
      "step": 31875
    },
    {
      "epoch": 0.9792031456394188,
      "grad_norm": 0.3851942718029022,
      "learning_rate": 1.0351753322914932e-05,
      "loss": 0.5298,
      "step": 31876
    },
    {
      "epoch": 0.9792338647743679,
      "grad_norm": 0.3423268496990204,
      "learning_rate": 1.0351270344240886e-05,
      "loss": 0.518,
      "step": 31877
    },
    {
      "epoch": 0.9792645839093171,
      "grad_norm": 0.45519986748695374,
      "learning_rate": 1.0350787364746428e-05,
      "loss": 0.5242,
      "step": 31878
    },
    {
      "epoch": 0.9792953030442663,
      "grad_norm": 0.34202367067337036,
      "learning_rate": 1.0350304384432678e-05,
      "loss": 0.5443,
      "step": 31879
    },
    {
      "epoch": 0.9793260221792154,
      "grad_norm": 0.32598042488098145,
      "learning_rate": 1.034982140330077e-05,
      "loss": 0.5695,
      "step": 31880
    },
    {
      "epoch": 0.9793567413141646,
      "grad_norm": 0.3484920561313629,
      "learning_rate": 1.0349338421351827e-05,
      "loss": 0.5117,
      "step": 31881
    },
    {
      "epoch": 0.9793874604491137,
      "grad_norm": 0.3661588728427887,
      "learning_rate": 1.0348855438586984e-05,
      "loss": 0.5164,
      "step": 31882
    },
    {
      "epoch": 0.979418179584063,
      "grad_norm": 0.46072494983673096,
      "learning_rate": 1.034837245500736e-05,
      "loss": 0.51,
      "step": 31883
    },
    {
      "epoch": 0.9794488987190121,
      "grad_norm": 0.3719431161880493,
      "learning_rate": 1.034788947061409e-05,
      "loss": 0.6088,
      "step": 31884
    },
    {
      "epoch": 0.9794796178539612,
      "grad_norm": 0.357313871383667,
      "learning_rate": 1.03474064854083e-05,
      "loss": 0.5345,
      "step": 31885
    },
    {
      "epoch": 0.9795103369889104,
      "grad_norm": 0.35182565450668335,
      "learning_rate": 1.0346923499391117e-05,
      "loss": 0.4839,
      "step": 31886
    },
    {
      "epoch": 0.9795410561238596,
      "grad_norm": 0.36317554116249084,
      "learning_rate": 1.0346440512563671e-05,
      "loss": 0.5109,
      "step": 31887
    },
    {
      "epoch": 0.9795717752588087,
      "grad_norm": 0.3221729099750519,
      "learning_rate": 1.0345957524927088e-05,
      "loss": 0.4168,
      "step": 31888
    },
    {
      "epoch": 0.9796024943937579,
      "grad_norm": 0.40131086111068726,
      "learning_rate": 1.0345474536482498e-05,
      "loss": 0.5459,
      "step": 31889
    },
    {
      "epoch": 0.979633213528707,
      "grad_norm": 0.3480820655822754,
      "learning_rate": 1.0344991547231027e-05,
      "loss": 0.5431,
      "step": 31890
    },
    {
      "epoch": 0.9796639326636561,
      "grad_norm": 0.36039528250694275,
      "learning_rate": 1.0344508557173806e-05,
      "loss": 0.511,
      "step": 31891
    },
    {
      "epoch": 0.9796946517986054,
      "grad_norm": 0.6765239834785461,
      "learning_rate": 1.0344025566311959e-05,
      "loss": 0.5545,
      "step": 31892
    },
    {
      "epoch": 0.9797253709335545,
      "grad_norm": 0.38327866792678833,
      "learning_rate": 1.034354257464662e-05,
      "loss": 0.6169,
      "step": 31893
    },
    {
      "epoch": 0.9797560900685036,
      "grad_norm": 0.3840734660625458,
      "learning_rate": 1.0343059582178911e-05,
      "loss": 0.521,
      "step": 31894
    },
    {
      "epoch": 0.9797868092034528,
      "grad_norm": 0.4977242946624756,
      "learning_rate": 1.0342576588909962e-05,
      "loss": 0.5478,
      "step": 31895
    },
    {
      "epoch": 0.979817528338402,
      "grad_norm": 0.33487609028816223,
      "learning_rate": 1.0342093594840903e-05,
      "loss": 0.5518,
      "step": 31896
    },
    {
      "epoch": 0.9798482474733512,
      "grad_norm": 0.33996671438217163,
      "learning_rate": 1.0341610599972857e-05,
      "loss": 0.4968,
      "step": 31897
    },
    {
      "epoch": 0.9798789666083003,
      "grad_norm": 0.4277598261833191,
      "learning_rate": 1.034112760430696e-05,
      "loss": 0.5142,
      "step": 31898
    },
    {
      "epoch": 0.9799096857432494,
      "grad_norm": 0.3711586594581604,
      "learning_rate": 1.0340644607844332e-05,
      "loss": 0.517,
      "step": 31899
    },
    {
      "epoch": 0.9799404048781987,
      "grad_norm": 0.3923964500427246,
      "learning_rate": 1.0340161610586105e-05,
      "loss": 0.5706,
      "step": 31900
    },
    {
      "epoch": 0.9799711240131478,
      "grad_norm": 0.3833853602409363,
      "learning_rate": 1.0339678612533407e-05,
      "loss": 0.4999,
      "step": 31901
    },
    {
      "epoch": 0.9800018431480969,
      "grad_norm": 0.34039515256881714,
      "learning_rate": 1.0339195613687367e-05,
      "loss": 0.5408,
      "step": 31902
    },
    {
      "epoch": 0.9800325622830461,
      "grad_norm": 0.39804625511169434,
      "learning_rate": 1.0338712614049113e-05,
      "loss": 0.5483,
      "step": 31903
    },
    {
      "epoch": 0.9800632814179953,
      "grad_norm": 0.39987415075302124,
      "learning_rate": 1.033822961361977e-05,
      "loss": 0.5393,
      "step": 31904
    },
    {
      "epoch": 0.9800940005529444,
      "grad_norm": 0.4445105195045471,
      "learning_rate": 1.033774661240047e-05,
      "loss": 0.5516,
      "step": 31905
    },
    {
      "epoch": 0.9801247196878936,
      "grad_norm": 0.41202959418296814,
      "learning_rate": 1.0337263610392336e-05,
      "loss": 0.5278,
      "step": 31906
    },
    {
      "epoch": 0.9801554388228427,
      "grad_norm": 0.36656907200813293,
      "learning_rate": 1.0336780607596504e-05,
      "loss": 0.5884,
      "step": 31907
    },
    {
      "epoch": 0.980186157957792,
      "grad_norm": 0.4329138994216919,
      "learning_rate": 1.0336297604014092e-05,
      "loss": 0.5252,
      "step": 31908
    },
    {
      "epoch": 0.9802168770927411,
      "grad_norm": 0.40376463532447815,
      "learning_rate": 1.0335814599646238e-05,
      "loss": 0.5173,
      "step": 31909
    },
    {
      "epoch": 0.9802475962276902,
      "grad_norm": 0.35905522108078003,
      "learning_rate": 1.0335331594494062e-05,
      "loss": 0.5701,
      "step": 31910
    },
    {
      "epoch": 0.9802783153626394,
      "grad_norm": 0.4065244495868683,
      "learning_rate": 1.03348485885587e-05,
      "loss": 0.4622,
      "step": 31911
    },
    {
      "epoch": 0.9803090344975885,
      "grad_norm": 0.4157405495643616,
      "learning_rate": 1.0334365581841273e-05,
      "loss": 0.5253,
      "step": 31912
    },
    {
      "epoch": 0.9803397536325377,
      "grad_norm": 0.40570205450057983,
      "learning_rate": 1.0333882574342911e-05,
      "loss": 0.5911,
      "step": 31913
    },
    {
      "epoch": 0.9803704727674869,
      "grad_norm": 0.3712575137615204,
      "learning_rate": 1.0333399566064745e-05,
      "loss": 0.5294,
      "step": 31914
    },
    {
      "epoch": 0.980401191902436,
      "grad_norm": 0.33144423365592957,
      "learning_rate": 1.03329165570079e-05,
      "loss": 0.4885,
      "step": 31915
    },
    {
      "epoch": 0.9804319110373851,
      "grad_norm": 0.4524989426136017,
      "learning_rate": 1.0332433547173506e-05,
      "loss": 0.6204,
      "step": 31916
    },
    {
      "epoch": 0.9804626301723344,
      "grad_norm": 0.3597210645675659,
      "learning_rate": 1.0331950536562687e-05,
      "loss": 0.551,
      "step": 31917
    },
    {
      "epoch": 0.9804933493072835,
      "grad_norm": 0.3585183918476105,
      "learning_rate": 1.0331467525176577e-05,
      "loss": 0.571,
      "step": 31918
    },
    {
      "epoch": 0.9805240684422327,
      "grad_norm": 0.38666290044784546,
      "learning_rate": 1.03309845130163e-05,
      "loss": 0.5251,
      "step": 31919
    },
    {
      "epoch": 0.9805547875771818,
      "grad_norm": 0.42903590202331543,
      "learning_rate": 1.0330501500082985e-05,
      "loss": 0.5301,
      "step": 31920
    },
    {
      "epoch": 0.980585506712131,
      "grad_norm": 0.36231669783592224,
      "learning_rate": 1.0330018486377764e-05,
      "loss": 0.5129,
      "step": 31921
    },
    {
      "epoch": 0.9806162258470802,
      "grad_norm": 0.3449871242046356,
      "learning_rate": 1.032953547190176e-05,
      "loss": 0.5528,
      "step": 31922
    },
    {
      "epoch": 0.9806469449820293,
      "grad_norm": 0.36352860927581787,
      "learning_rate": 1.0329052456656103e-05,
      "loss": 0.5964,
      "step": 31923
    },
    {
      "epoch": 0.9806776641169784,
      "grad_norm": 0.38250285387039185,
      "learning_rate": 1.032856944064192e-05,
      "loss": 0.5339,
      "step": 31924
    },
    {
      "epoch": 0.9807083832519277,
      "grad_norm": 0.36722198128700256,
      "learning_rate": 1.0328086423860342e-05,
      "loss": 0.5549,
      "step": 31925
    },
    {
      "epoch": 0.9807391023868768,
      "grad_norm": 0.37398913502693176,
      "learning_rate": 1.0327603406312495e-05,
      "loss": 0.5687,
      "step": 31926
    },
    {
      "epoch": 0.9807698215218259,
      "grad_norm": 0.38242676854133606,
      "learning_rate": 1.0327120387999507e-05,
      "loss": 0.5073,
      "step": 31927
    },
    {
      "epoch": 0.9808005406567751,
      "grad_norm": 0.38359880447387695,
      "learning_rate": 1.0326637368922508e-05,
      "loss": 0.5715,
      "step": 31928
    },
    {
      "epoch": 0.9808312597917243,
      "grad_norm": 0.330453097820282,
      "learning_rate": 1.032615434908262e-05,
      "loss": 0.5726,
      "step": 31929
    },
    {
      "epoch": 0.9808619789266734,
      "grad_norm": 0.3590219020843506,
      "learning_rate": 1.032567132848098e-05,
      "loss": 0.5561,
      "step": 31930
    },
    {
      "epoch": 0.9808926980616226,
      "grad_norm": 0.3764004707336426,
      "learning_rate": 1.032518830711871e-05,
      "loss": 0.5522,
      "step": 31931
    },
    {
      "epoch": 0.9809234171965717,
      "grad_norm": 0.38894134759902954,
      "learning_rate": 1.032470528499694e-05,
      "loss": 0.5778,
      "step": 31932
    },
    {
      "epoch": 0.980954136331521,
      "grad_norm": 0.34807613492012024,
      "learning_rate": 1.0324222262116799e-05,
      "loss": 0.5198,
      "step": 31933
    },
    {
      "epoch": 0.9809848554664701,
      "grad_norm": 0.4533226191997528,
      "learning_rate": 1.0323739238479415e-05,
      "loss": 0.5848,
      "step": 31934
    },
    {
      "epoch": 0.9810155746014192,
      "grad_norm": 0.4015680253505707,
      "learning_rate": 1.0323256214085913e-05,
      "loss": 0.5672,
      "step": 31935
    },
    {
      "epoch": 0.9810462937363684,
      "grad_norm": 0.38349786400794983,
      "learning_rate": 1.0322773188937424e-05,
      "loss": 0.5042,
      "step": 31936
    },
    {
      "epoch": 0.9810770128713175,
      "grad_norm": 0.37603333592414856,
      "learning_rate": 1.0322290163035076e-05,
      "loss": 0.5681,
      "step": 31937
    },
    {
      "epoch": 0.9811077320062667,
      "grad_norm": 0.36798420548439026,
      "learning_rate": 1.0321807136379998e-05,
      "loss": 0.5561,
      "step": 31938
    },
    {
      "epoch": 0.9811384511412159,
      "grad_norm": 0.3314763009548187,
      "learning_rate": 1.0321324108973316e-05,
      "loss": 0.4878,
      "step": 31939
    },
    {
      "epoch": 0.981169170276165,
      "grad_norm": 0.3723415732383728,
      "learning_rate": 1.0320841080816157e-05,
      "loss": 0.6027,
      "step": 31940
    },
    {
      "epoch": 0.9811998894111141,
      "grad_norm": 0.4027707576751709,
      "learning_rate": 1.0320358051909656e-05,
      "loss": 0.5659,
      "step": 31941
    },
    {
      "epoch": 0.9812306085460634,
      "grad_norm": 0.3897800147533417,
      "learning_rate": 1.0319875022254933e-05,
      "loss": 0.5208,
      "step": 31942
    },
    {
      "epoch": 0.9812613276810125,
      "grad_norm": 0.33328354358673096,
      "learning_rate": 1.031939199185312e-05,
      "loss": 0.4932,
      "step": 31943
    },
    {
      "epoch": 0.9812920468159617,
      "grad_norm": 0.41365134716033936,
      "learning_rate": 1.0318908960705345e-05,
      "loss": 0.5816,
      "step": 31944
    },
    {
      "epoch": 0.9813227659509108,
      "grad_norm": 0.4682101607322693,
      "learning_rate": 1.0318425928812736e-05,
      "loss": 0.5954,
      "step": 31945
    },
    {
      "epoch": 0.98135348508586,
      "grad_norm": 0.37160632014274597,
      "learning_rate": 1.0317942896176423e-05,
      "loss": 0.496,
      "step": 31946
    },
    {
      "epoch": 0.9813842042208092,
      "grad_norm": 0.39224159717559814,
      "learning_rate": 1.031745986279753e-05,
      "loss": 0.5958,
      "step": 31947
    },
    {
      "epoch": 0.9814149233557583,
      "grad_norm": 0.37091127038002014,
      "learning_rate": 1.0316976828677188e-05,
      "loss": 0.5494,
      "step": 31948
    },
    {
      "epoch": 0.9814456424907074,
      "grad_norm": 0.40283840894699097,
      "learning_rate": 1.0316493793816523e-05,
      "loss": 0.579,
      "step": 31949
    },
    {
      "epoch": 0.9814763616256567,
      "grad_norm": 0.3956664204597473,
      "learning_rate": 1.0316010758216665e-05,
      "loss": 0.515,
      "step": 31950
    },
    {
      "epoch": 0.9815070807606058,
      "grad_norm": 0.9270488023757935,
      "learning_rate": 1.0315527721878742e-05,
      "loss": 0.5547,
      "step": 31951
    },
    {
      "epoch": 0.9815377998955549,
      "grad_norm": 0.4250369369983673,
      "learning_rate": 1.0315044684803885e-05,
      "loss": 0.5423,
      "step": 31952
    },
    {
      "epoch": 0.9815685190305041,
      "grad_norm": 0.3757081627845764,
      "learning_rate": 1.0314561646993216e-05,
      "loss": 0.5271,
      "step": 31953
    },
    {
      "epoch": 0.9815992381654532,
      "grad_norm": 0.47296592593193054,
      "learning_rate": 1.0314078608447866e-05,
      "loss": 0.6027,
      "step": 31954
    },
    {
      "epoch": 0.9816299573004024,
      "grad_norm": 0.4045969843864441,
      "learning_rate": 1.0313595569168965e-05,
      "loss": 0.5139,
      "step": 31955
    },
    {
      "epoch": 0.9816606764353516,
      "grad_norm": 0.37614503502845764,
      "learning_rate": 1.031311252915764e-05,
      "loss": 0.5062,
      "step": 31956
    },
    {
      "epoch": 0.9816913955703007,
      "grad_norm": 0.35088101029396057,
      "learning_rate": 1.0312629488415016e-05,
      "loss": 0.5615,
      "step": 31957
    },
    {
      "epoch": 0.98172211470525,
      "grad_norm": 0.3802255392074585,
      "learning_rate": 1.0312146446942223e-05,
      "loss": 0.5742,
      "step": 31958
    },
    {
      "epoch": 0.9817528338401991,
      "grad_norm": 0.4125663936138153,
      "learning_rate": 1.0311663404740395e-05,
      "loss": 0.5945,
      "step": 31959
    },
    {
      "epoch": 0.9817835529751482,
      "grad_norm": 0.38442471623420715,
      "learning_rate": 1.0311180361810653e-05,
      "loss": 0.6155,
      "step": 31960
    },
    {
      "epoch": 0.9818142721100974,
      "grad_norm": 0.352629691362381,
      "learning_rate": 1.0310697318154128e-05,
      "loss": 0.5541,
      "step": 31961
    },
    {
      "epoch": 0.9818449912450465,
      "grad_norm": 0.343912273645401,
      "learning_rate": 1.0310214273771948e-05,
      "loss": 0.5977,
      "step": 31962
    },
    {
      "epoch": 0.9818757103799957,
      "grad_norm": 0.45226970314979553,
      "learning_rate": 1.030973122866524e-05,
      "loss": 0.5907,
      "step": 31963
    },
    {
      "epoch": 0.9819064295149449,
      "grad_norm": 0.5472174286842346,
      "learning_rate": 1.0309248182835134e-05,
      "loss": 0.5453,
      "step": 31964
    },
    {
      "epoch": 0.981937148649894,
      "grad_norm": 0.3651614487171173,
      "learning_rate": 1.0308765136282757e-05,
      "loss": 0.5668,
      "step": 31965
    },
    {
      "epoch": 0.9819678677848431,
      "grad_norm": 0.34154245257377625,
      "learning_rate": 1.0308282089009238e-05,
      "loss": 0.5468,
      "step": 31966
    },
    {
      "epoch": 0.9819985869197924,
      "grad_norm": 0.38121286034584045,
      "learning_rate": 1.0307799041015702e-05,
      "loss": 0.4131,
      "step": 31967
    },
    {
      "epoch": 0.9820293060547415,
      "grad_norm": 0.4149737060070038,
      "learning_rate": 1.0307315992303284e-05,
      "loss": 0.5296,
      "step": 31968
    },
    {
      "epoch": 0.9820600251896907,
      "grad_norm": 0.4033730924129486,
      "learning_rate": 1.0306832942873104e-05,
      "loss": 0.5404,
      "step": 31969
    },
    {
      "epoch": 0.9820907443246398,
      "grad_norm": 0.363191157579422,
      "learning_rate": 1.0306349892726298e-05,
      "loss": 0.548,
      "step": 31970
    },
    {
      "epoch": 0.982121463459589,
      "grad_norm": 0.3378194272518158,
      "learning_rate": 1.0305866841863987e-05,
      "loss": 0.5347,
      "step": 31971
    },
    {
      "epoch": 0.9821521825945382,
      "grad_norm": 0.3886933922767639,
      "learning_rate": 1.0305383790287305e-05,
      "loss": 0.5143,
      "step": 31972
    },
    {
      "epoch": 0.9821829017294873,
      "grad_norm": 0.4048117399215698,
      "learning_rate": 1.0304900737997376e-05,
      "loss": 0.5565,
      "step": 31973
    },
    {
      "epoch": 0.9822136208644364,
      "grad_norm": 0.4006229341030121,
      "learning_rate": 1.0304417684995332e-05,
      "loss": 0.5531,
      "step": 31974
    },
    {
      "epoch": 0.9822443399993857,
      "grad_norm": 0.34659543633461,
      "learning_rate": 1.0303934631282298e-05,
      "loss": 0.5303,
      "step": 31975
    },
    {
      "epoch": 0.9822750591343348,
      "grad_norm": 0.39900660514831543,
      "learning_rate": 1.0303451576859402e-05,
      "loss": 0.5675,
      "step": 31976
    },
    {
      "epoch": 0.9823057782692839,
      "grad_norm": 0.5357086658477783,
      "learning_rate": 1.0302968521727776e-05,
      "loss": 0.6058,
      "step": 31977
    },
    {
      "epoch": 0.9823364974042331,
      "grad_norm": 0.4201912581920624,
      "learning_rate": 1.0302485465888544e-05,
      "loss": 0.535,
      "step": 31978
    },
    {
      "epoch": 0.9823672165391822,
      "grad_norm": 0.354784220457077,
      "learning_rate": 1.0302002409342839e-05,
      "loss": 0.5712,
      "step": 31979
    },
    {
      "epoch": 0.9823979356741314,
      "grad_norm": 0.34726110100746155,
      "learning_rate": 1.0301519352091782e-05,
      "loss": 0.5362,
      "step": 31980
    },
    {
      "epoch": 0.9824286548090806,
      "grad_norm": 0.34460628032684326,
      "learning_rate": 1.0301036294136511e-05,
      "loss": 0.5846,
      "step": 31981
    },
    {
      "epoch": 0.9824593739440297,
      "grad_norm": 0.3608395755290985,
      "learning_rate": 1.0300553235478145e-05,
      "loss": 0.5144,
      "step": 31982
    },
    {
      "epoch": 0.9824900930789789,
      "grad_norm": 0.43645769357681274,
      "learning_rate": 1.0300070176117816e-05,
      "loss": 0.5517,
      "step": 31983
    },
    {
      "epoch": 0.9825208122139281,
      "grad_norm": 0.34970420598983765,
      "learning_rate": 1.0299587116056653e-05,
      "loss": 0.6426,
      "step": 31984
    },
    {
      "epoch": 0.9825515313488772,
      "grad_norm": 0.40104398131370544,
      "learning_rate": 1.0299104055295783e-05,
      "loss": 0.5173,
      "step": 31985
    },
    {
      "epoch": 0.9825822504838264,
      "grad_norm": 0.35905003547668457,
      "learning_rate": 1.0298620993836337e-05,
      "loss": 0.509,
      "step": 31986
    },
    {
      "epoch": 0.9826129696187755,
      "grad_norm": 0.3893132209777832,
      "learning_rate": 1.0298137931679437e-05,
      "loss": 0.4938,
      "step": 31987
    },
    {
      "epoch": 0.9826436887537247,
      "grad_norm": 0.36325135827064514,
      "learning_rate": 1.0297654868826216e-05,
      "loss": 0.6176,
      "step": 31988
    },
    {
      "epoch": 0.9826744078886739,
      "grad_norm": 0.46086740493774414,
      "learning_rate": 1.0297171805277802e-05,
      "loss": 0.5288,
      "step": 31989
    },
    {
      "epoch": 0.982705127023623,
      "grad_norm": 0.33921533823013306,
      "learning_rate": 1.0296688741035324e-05,
      "loss": 0.5041,
      "step": 31990
    },
    {
      "epoch": 0.9827358461585721,
      "grad_norm": 0.3616562783718109,
      "learning_rate": 1.0296205676099905e-05,
      "loss": 0.5495,
      "step": 31991
    },
    {
      "epoch": 0.9827665652935214,
      "grad_norm": 0.550632119178772,
      "learning_rate": 1.029572261047268e-05,
      "loss": 0.5749,
      "step": 31992
    },
    {
      "epoch": 0.9827972844284705,
      "grad_norm": 0.39157038927078247,
      "learning_rate": 1.0295239544154771e-05,
      "loss": 0.5247,
      "step": 31993
    },
    {
      "epoch": 0.9828280035634197,
      "grad_norm": 0.44686976075172424,
      "learning_rate": 1.0294756477147311e-05,
      "loss": 0.4907,
      "step": 31994
    },
    {
      "epoch": 0.9828587226983688,
      "grad_norm": 0.3693929612636566,
      "learning_rate": 1.0294273409451429e-05,
      "loss": 0.5835,
      "step": 31995
    },
    {
      "epoch": 0.982889441833318,
      "grad_norm": 0.43999773263931274,
      "learning_rate": 1.0293790341068249e-05,
      "loss": 0.5923,
      "step": 31996
    },
    {
      "epoch": 0.9829201609682672,
      "grad_norm": 0.3644382357597351,
      "learning_rate": 1.0293307271998903e-05,
      "loss": 0.5456,
      "step": 31997
    },
    {
      "epoch": 0.9829508801032163,
      "grad_norm": 0.40638068318367004,
      "learning_rate": 1.0292824202244515e-05,
      "loss": 0.5717,
      "step": 31998
    },
    {
      "epoch": 0.9829815992381654,
      "grad_norm": 0.38299068808555603,
      "learning_rate": 1.0292341131806216e-05,
      "loss": 0.4311,
      "step": 31999
    },
    {
      "epoch": 0.9830123183731146,
      "grad_norm": 0.38791799545288086,
      "learning_rate": 1.0291858060685136e-05,
      "loss": 0.5266,
      "step": 32000
    },
    {
      "epoch": 0.9830430375080638,
      "grad_norm": 0.3584929406642914,
      "learning_rate": 1.0291374988882397e-05,
      "loss": 0.5156,
      "step": 32001
    },
    {
      "epoch": 0.9830737566430129,
      "grad_norm": 0.45656511187553406,
      "learning_rate": 1.0290891916399135e-05,
      "loss": 0.5948,
      "step": 32002
    },
    {
      "epoch": 0.9831044757779621,
      "grad_norm": 0.42374640703201294,
      "learning_rate": 1.0290408843236472e-05,
      "loss": 0.5296,
      "step": 32003
    },
    {
      "epoch": 0.9831351949129112,
      "grad_norm": 0.38516440987586975,
      "learning_rate": 1.0289925769395542e-05,
      "loss": 0.5701,
      "step": 32004
    },
    {
      "epoch": 0.9831659140478605,
      "grad_norm": 0.3793541193008423,
      "learning_rate": 1.0289442694877468e-05,
      "loss": 0.5298,
      "step": 32005
    },
    {
      "epoch": 0.9831966331828096,
      "grad_norm": 0.3695896863937378,
      "learning_rate": 1.028895961968338e-05,
      "loss": 0.4745,
      "step": 32006
    },
    {
      "epoch": 0.9832273523177587,
      "grad_norm": 0.3785282075405121,
      "learning_rate": 1.0288476543814408e-05,
      "loss": 0.5769,
      "step": 32007
    },
    {
      "epoch": 0.9832580714527079,
      "grad_norm": 0.36559629440307617,
      "learning_rate": 1.0287993467271678e-05,
      "loss": 0.4692,
      "step": 32008
    },
    {
      "epoch": 0.9832887905876571,
      "grad_norm": 0.3574185073375702,
      "learning_rate": 1.0287510390056321e-05,
      "loss": 0.5358,
      "step": 32009
    },
    {
      "epoch": 0.9833195097226062,
      "grad_norm": 0.4629267454147339,
      "learning_rate": 1.028702731216946e-05,
      "loss": 0.5713,
      "step": 32010
    },
    {
      "epoch": 0.9833502288575554,
      "grad_norm": 0.3944993019104004,
      "learning_rate": 1.0286544233612228e-05,
      "loss": 0.5693,
      "step": 32011
    },
    {
      "epoch": 0.9833809479925045,
      "grad_norm": 0.36778542399406433,
      "learning_rate": 1.028606115438575e-05,
      "loss": 0.5552,
      "step": 32012
    },
    {
      "epoch": 0.9834116671274536,
      "grad_norm": 0.47068390250205994,
      "learning_rate": 1.028557807449116e-05,
      "loss": 0.5262,
      "step": 32013
    },
    {
      "epoch": 0.9834423862624029,
      "grad_norm": 0.33381718397140503,
      "learning_rate": 1.0285094993929581e-05,
      "loss": 0.5308,
      "step": 32014
    },
    {
      "epoch": 0.983473105397352,
      "grad_norm": 0.6523380279541016,
      "learning_rate": 1.0284611912702143e-05,
      "loss": 0.4679,
      "step": 32015
    },
    {
      "epoch": 0.9835038245323011,
      "grad_norm": 0.37125617265701294,
      "learning_rate": 1.0284128830809975e-05,
      "loss": 0.586,
      "step": 32016
    },
    {
      "epoch": 0.9835345436672503,
      "grad_norm": 0.36677655577659607,
      "learning_rate": 1.02836457482542e-05,
      "loss": 0.5381,
      "step": 32017
    },
    {
      "epoch": 0.9835652628021995,
      "grad_norm": 0.3591811954975128,
      "learning_rate": 1.0283162665035954e-05,
      "loss": 0.467,
      "step": 32018
    },
    {
      "epoch": 0.9835959819371487,
      "grad_norm": 0.36789196729660034,
      "learning_rate": 1.0282679581156362e-05,
      "loss": 0.5358,
      "step": 32019
    },
    {
      "epoch": 0.9836267010720978,
      "grad_norm": 0.38514620065689087,
      "learning_rate": 1.0282196496616552e-05,
      "loss": 0.5976,
      "step": 32020
    },
    {
      "epoch": 0.9836574202070469,
      "grad_norm": 0.47825419902801514,
      "learning_rate": 1.028171341141765e-05,
      "loss": 0.5488,
      "step": 32021
    },
    {
      "epoch": 0.9836881393419962,
      "grad_norm": 0.3956505060195923,
      "learning_rate": 1.0281230325560792e-05,
      "loss": 0.5719,
      "step": 32022
    },
    {
      "epoch": 0.9837188584769453,
      "grad_norm": 0.41109201312065125,
      "learning_rate": 1.0280747239047095e-05,
      "loss": 0.5332,
      "step": 32023
    },
    {
      "epoch": 0.9837495776118944,
      "grad_norm": 0.40462726354599,
      "learning_rate": 1.0280264151877697e-05,
      "loss": 0.6142,
      "step": 32024
    },
    {
      "epoch": 0.9837802967468436,
      "grad_norm": 0.3465260863304138,
      "learning_rate": 1.027978106405372e-05,
      "loss": 0.5713,
      "step": 32025
    },
    {
      "epoch": 0.9838110158817928,
      "grad_norm": 0.3638586699962616,
      "learning_rate": 1.0279297975576297e-05,
      "loss": 0.5734,
      "step": 32026
    },
    {
      "epoch": 0.9838417350167419,
      "grad_norm": 0.7211752533912659,
      "learning_rate": 1.0278814886446553e-05,
      "loss": 0.5301,
      "step": 32027
    },
    {
      "epoch": 0.9838724541516911,
      "grad_norm": 0.3732266128063202,
      "learning_rate": 1.0278331796665616e-05,
      "loss": 0.48,
      "step": 32028
    },
    {
      "epoch": 0.9839031732866402,
      "grad_norm": 0.38954854011535645,
      "learning_rate": 1.027784870623462e-05,
      "loss": 0.5304,
      "step": 32029
    },
    {
      "epoch": 0.9839338924215895,
      "grad_norm": 0.48381757736206055,
      "learning_rate": 1.0277365615154681e-05,
      "loss": 0.5213,
      "step": 32030
    },
    {
      "epoch": 0.9839646115565386,
      "grad_norm": 2.149381399154663,
      "learning_rate": 1.0276882523426943e-05,
      "loss": 0.5974,
      "step": 32031
    },
    {
      "epoch": 0.9839953306914877,
      "grad_norm": 0.3987710475921631,
      "learning_rate": 1.0276399431052522e-05,
      "loss": 0.5119,
      "step": 32032
    },
    {
      "epoch": 0.9840260498264369,
      "grad_norm": 0.3687173128128052,
      "learning_rate": 1.0275916338032551e-05,
      "loss": 0.5226,
      "step": 32033
    },
    {
      "epoch": 0.984056768961386,
      "grad_norm": 0.4041935205459595,
      "learning_rate": 1.0275433244368162e-05,
      "loss": 0.4392,
      "step": 32034
    },
    {
      "epoch": 0.9840874880963352,
      "grad_norm": 0.40408897399902344,
      "learning_rate": 1.0274950150060476e-05,
      "loss": 0.5134,
      "step": 32035
    },
    {
      "epoch": 0.9841182072312844,
      "grad_norm": 0.3398621380329132,
      "learning_rate": 1.0274467055110628e-05,
      "loss": 0.5163,
      "step": 32036
    },
    {
      "epoch": 0.9841489263662335,
      "grad_norm": 0.3419729471206665,
      "learning_rate": 1.027398395951974e-05,
      "loss": 0.5034,
      "step": 32037
    },
    {
      "epoch": 0.9841796455011826,
      "grad_norm": 0.38036489486694336,
      "learning_rate": 1.0273500863288945e-05,
      "loss": 0.508,
      "step": 32038
    },
    {
      "epoch": 0.9842103646361319,
      "grad_norm": 0.41096487641334534,
      "learning_rate": 1.0273017766419366e-05,
      "loss": 0.6252,
      "step": 32039
    },
    {
      "epoch": 0.984241083771081,
      "grad_norm": 0.4117507040500641,
      "learning_rate": 1.027253466891214e-05,
      "loss": 0.5264,
      "step": 32040
    },
    {
      "epoch": 0.9842718029060301,
      "grad_norm": 0.34086135029792786,
      "learning_rate": 1.0272051570768387e-05,
      "loss": 0.4791,
      "step": 32041
    },
    {
      "epoch": 0.9843025220409793,
      "grad_norm": 0.37898099422454834,
      "learning_rate": 1.0271568471989241e-05,
      "loss": 0.5345,
      "step": 32042
    },
    {
      "epoch": 0.9843332411759285,
      "grad_norm": 0.3344566524028778,
      "learning_rate": 1.0271085372575824e-05,
      "loss": 0.505,
      "step": 32043
    },
    {
      "epoch": 0.9843639603108777,
      "grad_norm": 0.40458762645721436,
      "learning_rate": 1.0270602272529273e-05,
      "loss": 0.5428,
      "step": 32044
    },
    {
      "epoch": 0.9843946794458268,
      "grad_norm": 0.3471236526966095,
      "learning_rate": 1.027011917185071e-05,
      "loss": 0.5576,
      "step": 32045
    },
    {
      "epoch": 0.9844253985807759,
      "grad_norm": 0.4376184046268463,
      "learning_rate": 1.0269636070541262e-05,
      "loss": 0.5374,
      "step": 32046
    },
    {
      "epoch": 0.9844561177157252,
      "grad_norm": 0.36838850378990173,
      "learning_rate": 1.0269152968602064e-05,
      "loss": 0.5153,
      "step": 32047
    },
    {
      "epoch": 0.9844868368506743,
      "grad_norm": 0.42821189761161804,
      "learning_rate": 1.0268669866034235e-05,
      "loss": 0.5166,
      "step": 32048
    },
    {
      "epoch": 0.9845175559856234,
      "grad_norm": 0.3771461546421051,
      "learning_rate": 1.0268186762838912e-05,
      "loss": 0.5256,
      "step": 32049
    },
    {
      "epoch": 0.9845482751205726,
      "grad_norm": 0.3456963002681732,
      "learning_rate": 1.0267703659017223e-05,
      "loss": 0.6023,
      "step": 32050
    },
    {
      "epoch": 0.9845789942555218,
      "grad_norm": 0.35603198409080505,
      "learning_rate": 1.0267220554570289e-05,
      "loss": 0.5789,
      "step": 32051
    },
    {
      "epoch": 0.9846097133904709,
      "grad_norm": 0.36765363812446594,
      "learning_rate": 1.0266737449499244e-05,
      "loss": 0.4934,
      "step": 32052
    },
    {
      "epoch": 0.9846404325254201,
      "grad_norm": 0.402659147977829,
      "learning_rate": 1.0266254343805216e-05,
      "loss": 0.554,
      "step": 32053
    },
    {
      "epoch": 0.9846711516603692,
      "grad_norm": 0.3323395252227783,
      "learning_rate": 1.0265771237489332e-05,
      "loss": 0.4955,
      "step": 32054
    },
    {
      "epoch": 0.9847018707953185,
      "grad_norm": 0.37765857577323914,
      "learning_rate": 1.026528813055272e-05,
      "loss": 0.5098,
      "step": 32055
    },
    {
      "epoch": 0.9847325899302676,
      "grad_norm": 0.3569028377532959,
      "learning_rate": 1.0264805022996512e-05,
      "loss": 0.5778,
      "step": 32056
    },
    {
      "epoch": 0.9847633090652167,
      "grad_norm": 0.3930826783180237,
      "learning_rate": 1.026432191482183e-05,
      "loss": 0.5697,
      "step": 32057
    },
    {
      "epoch": 0.9847940282001659,
      "grad_norm": 0.3491280972957611,
      "learning_rate": 1.0263838806029807e-05,
      "loss": 0.5269,
      "step": 32058
    },
    {
      "epoch": 0.984824747335115,
      "grad_norm": 0.3929907977581024,
      "learning_rate": 1.0263355696621569e-05,
      "loss": 0.5257,
      "step": 32059
    },
    {
      "epoch": 0.9848554664700642,
      "grad_norm": 0.3435913920402527,
      "learning_rate": 1.0262872586598247e-05,
      "loss": 0.5945,
      "step": 32060
    },
    {
      "epoch": 0.9848861856050134,
      "grad_norm": 0.3846510052680969,
      "learning_rate": 1.0262389475960968e-05,
      "loss": 0.5349,
      "step": 32061
    },
    {
      "epoch": 0.9849169047399625,
      "grad_norm": 0.3685392439365387,
      "learning_rate": 1.0261906364710856e-05,
      "loss": 0.5729,
      "step": 32062
    },
    {
      "epoch": 0.9849476238749116,
      "grad_norm": 0.4071357250213623,
      "learning_rate": 1.0261423252849048e-05,
      "loss": 0.4965,
      "step": 32063
    },
    {
      "epoch": 0.9849783430098609,
      "grad_norm": 0.354800820350647,
      "learning_rate": 1.0260940140376664e-05,
      "loss": 0.534,
      "step": 32064
    },
    {
      "epoch": 0.98500906214481,
      "grad_norm": 0.42088061571121216,
      "learning_rate": 1.026045702729484e-05,
      "loss": 0.5887,
      "step": 32065
    },
    {
      "epoch": 0.9850397812797591,
      "grad_norm": 0.445123553276062,
      "learning_rate": 1.0259973913604695e-05,
      "loss": 0.5011,
      "step": 32066
    },
    {
      "epoch": 0.9850705004147083,
      "grad_norm": 0.3781382143497467,
      "learning_rate": 1.0259490799307367e-05,
      "loss": 0.5315,
      "step": 32067
    },
    {
      "epoch": 0.9851012195496575,
      "grad_norm": 0.3964947760105133,
      "learning_rate": 1.025900768440398e-05,
      "loss": 0.5299,
      "step": 32068
    },
    {
      "epoch": 0.9851319386846067,
      "grad_norm": 0.4811297655105591,
      "learning_rate": 1.0258524568895663e-05,
      "loss": 0.4333,
      "step": 32069
    },
    {
      "epoch": 0.9851626578195558,
      "grad_norm": 0.356442928314209,
      "learning_rate": 1.0258041452783542e-05,
      "loss": 0.4687,
      "step": 32070
    },
    {
      "epoch": 0.9851933769545049,
      "grad_norm": 0.3659574091434479,
      "learning_rate": 1.0257558336068746e-05,
      "loss": 0.5268,
      "step": 32071
    },
    {
      "epoch": 0.9852240960894542,
      "grad_norm": 0.38766664266586304,
      "learning_rate": 1.025707521875241e-05,
      "loss": 0.5855,
      "step": 32072
    },
    {
      "epoch": 0.9852548152244033,
      "grad_norm": 0.4032134711742401,
      "learning_rate": 1.0256592100835651e-05,
      "loss": 0.61,
      "step": 32073
    },
    {
      "epoch": 0.9852855343593524,
      "grad_norm": 0.3879472017288208,
      "learning_rate": 1.0256108982319608e-05,
      "loss": 0.5349,
      "step": 32074
    },
    {
      "epoch": 0.9853162534943016,
      "grad_norm": 0.3500577211380005,
      "learning_rate": 1.02556258632054e-05,
      "loss": 0.5013,
      "step": 32075
    },
    {
      "epoch": 0.9853469726292508,
      "grad_norm": 0.38323652744293213,
      "learning_rate": 1.0255142743494165e-05,
      "loss": 0.5072,
      "step": 32076
    },
    {
      "epoch": 0.9853776917641999,
      "grad_norm": 0.5666323900222778,
      "learning_rate": 1.025465962318702e-05,
      "loss": 0.6288,
      "step": 32077
    },
    {
      "epoch": 0.9854084108991491,
      "grad_norm": 0.36634477972984314,
      "learning_rate": 1.0254176502285105e-05,
      "loss": 0.5124,
      "step": 32078
    },
    {
      "epoch": 0.9854391300340982,
      "grad_norm": 0.4030751883983612,
      "learning_rate": 1.0253693380789542e-05,
      "loss": 0.553,
      "step": 32079
    },
    {
      "epoch": 0.9854698491690475,
      "grad_norm": 0.3452749252319336,
      "learning_rate": 1.0253210258701458e-05,
      "loss": 0.4975,
      "step": 32080
    },
    {
      "epoch": 0.9855005683039966,
      "grad_norm": 0.3653426468372345,
      "learning_rate": 1.0252727136021987e-05,
      "loss": 0.5382,
      "step": 32081
    },
    {
      "epoch": 0.9855312874389457,
      "grad_norm": 0.39312317967414856,
      "learning_rate": 1.025224401275225e-05,
      "loss": 0.5267,
      "step": 32082
    },
    {
      "epoch": 0.9855620065738949,
      "grad_norm": 0.36229953169822693,
      "learning_rate": 1.0251760888893383e-05,
      "loss": 0.5266,
      "step": 32083
    },
    {
      "epoch": 0.985592725708844,
      "grad_norm": 0.3720245361328125,
      "learning_rate": 1.0251277764446505e-05,
      "loss": 0.4537,
      "step": 32084
    },
    {
      "epoch": 0.9856234448437932,
      "grad_norm": 0.3742936849594116,
      "learning_rate": 1.0250794639412758e-05,
      "loss": 0.6031,
      "step": 32085
    },
    {
      "epoch": 0.9856541639787424,
      "grad_norm": 0.38030070066452026,
      "learning_rate": 1.0250311513793261e-05,
      "loss": 0.5803,
      "step": 32086
    },
    {
      "epoch": 0.9856848831136915,
      "grad_norm": 0.3794907331466675,
      "learning_rate": 1.024982838758914e-05,
      "loss": 0.521,
      "step": 32087
    },
    {
      "epoch": 0.9857156022486406,
      "grad_norm": 0.3630807101726532,
      "learning_rate": 1.0249345260801531e-05,
      "loss": 0.5828,
      "step": 32088
    },
    {
      "epoch": 0.9857463213835899,
      "grad_norm": 0.3708418011665344,
      "learning_rate": 1.0248862133431556e-05,
      "loss": 0.5222,
      "step": 32089
    },
    {
      "epoch": 0.985777040518539,
      "grad_norm": 0.38749948143959045,
      "learning_rate": 1.0248379005480348e-05,
      "loss": 0.4762,
      "step": 32090
    },
    {
      "epoch": 0.9858077596534881,
      "grad_norm": 0.437784880399704,
      "learning_rate": 1.0247895876949031e-05,
      "loss": 0.5476,
      "step": 32091
    },
    {
      "epoch": 0.9858384787884373,
      "grad_norm": 0.38579294085502625,
      "learning_rate": 1.024741274783874e-05,
      "loss": 0.5571,
      "step": 32092
    },
    {
      "epoch": 0.9858691979233865,
      "grad_norm": 0.3489190936088562,
      "learning_rate": 1.0246929618150599e-05,
      "loss": 0.4966,
      "step": 32093
    },
    {
      "epoch": 0.9858999170583357,
      "grad_norm": 0.3747866749763489,
      "learning_rate": 1.0246446487885734e-05,
      "loss": 0.5451,
      "step": 32094
    },
    {
      "epoch": 0.9859306361932848,
      "grad_norm": 0.4080027639865875,
      "learning_rate": 1.0245963357045277e-05,
      "loss": 0.5191,
      "step": 32095
    },
    {
      "epoch": 0.9859613553282339,
      "grad_norm": 0.39926716685295105,
      "learning_rate": 1.0245480225630355e-05,
      "loss": 0.5506,
      "step": 32096
    },
    {
      "epoch": 0.9859920744631832,
      "grad_norm": 0.3828631043434143,
      "learning_rate": 1.0244997093642099e-05,
      "loss": 0.4851,
      "step": 32097
    },
    {
      "epoch": 0.9860227935981323,
      "grad_norm": 0.38472846150398254,
      "learning_rate": 1.0244513961081633e-05,
      "loss": 0.5152,
      "step": 32098
    },
    {
      "epoch": 0.9860535127330814,
      "grad_norm": 0.364616334438324,
      "learning_rate": 1.0244030827950087e-05,
      "loss": 0.5801,
      "step": 32099
    },
    {
      "epoch": 0.9860842318680306,
      "grad_norm": 0.3428393006324768,
      "learning_rate": 1.024354769424859e-05,
      "loss": 0.4763,
      "step": 32100
    },
    {
      "epoch": 0.9861149510029797,
      "grad_norm": 0.44365885853767395,
      "learning_rate": 1.0243064559978272e-05,
      "loss": 0.5152,
      "step": 32101
    },
    {
      "epoch": 0.9861456701379289,
      "grad_norm": 0.38405945897102356,
      "learning_rate": 1.0242581425140258e-05,
      "loss": 0.5582,
      "step": 32102
    },
    {
      "epoch": 0.9861763892728781,
      "grad_norm": 0.3438846468925476,
      "learning_rate": 1.0242098289735678e-05,
      "loss": 0.4995,
      "step": 32103
    },
    {
      "epoch": 0.9862071084078272,
      "grad_norm": 0.3666609525680542,
      "learning_rate": 1.0241615153765663e-05,
      "loss": 0.5315,
      "step": 32104
    },
    {
      "epoch": 0.9862378275427764,
      "grad_norm": 0.4006696939468384,
      "learning_rate": 1.0241132017231337e-05,
      "loss": 0.608,
      "step": 32105
    },
    {
      "epoch": 0.9862685466777256,
      "grad_norm": 0.3731255829334259,
      "learning_rate": 1.0240648880133832e-05,
      "loss": 0.5064,
      "step": 32106
    },
    {
      "epoch": 0.9862992658126747,
      "grad_norm": 0.35332319140434265,
      "learning_rate": 1.024016574247427e-05,
      "loss": 0.5341,
      "step": 32107
    },
    {
      "epoch": 0.9863299849476239,
      "grad_norm": 0.3457493185997009,
      "learning_rate": 1.0239682604253791e-05,
      "loss": 0.4618,
      "step": 32108
    },
    {
      "epoch": 0.986360704082573,
      "grad_norm": 0.38677269220352173,
      "learning_rate": 1.0239199465473511e-05,
      "loss": 0.5465,
      "step": 32109
    },
    {
      "epoch": 0.9863914232175222,
      "grad_norm": 0.3368350863456726,
      "learning_rate": 1.0238716326134567e-05,
      "loss": 0.5525,
      "step": 32110
    },
    {
      "epoch": 0.9864221423524714,
      "grad_norm": 0.38273996114730835,
      "learning_rate": 1.0238233186238083e-05,
      "loss": 0.6568,
      "step": 32111
    },
    {
      "epoch": 0.9864528614874205,
      "grad_norm": 0.3683892786502838,
      "learning_rate": 1.023775004578519e-05,
      "loss": 0.5958,
      "step": 32112
    },
    {
      "epoch": 0.9864835806223696,
      "grad_norm": 0.33915042877197266,
      "learning_rate": 1.0237266904777016e-05,
      "loss": 0.5079,
      "step": 32113
    },
    {
      "epoch": 0.9865142997573189,
      "grad_norm": 0.3398439884185791,
      "learning_rate": 1.0236783763214685e-05,
      "loss": 0.4602,
      "step": 32114
    },
    {
      "epoch": 0.986545018892268,
      "grad_norm": 0.3854321837425232,
      "learning_rate": 1.0236300621099333e-05,
      "loss": 0.4961,
      "step": 32115
    },
    {
      "epoch": 0.9865757380272172,
      "grad_norm": 0.38647252321243286,
      "learning_rate": 1.0235817478432082e-05,
      "loss": 0.5158,
      "step": 32116
    },
    {
      "epoch": 0.9866064571621663,
      "grad_norm": 0.38820168375968933,
      "learning_rate": 1.0235334335214064e-05,
      "loss": 0.5551,
      "step": 32117
    },
    {
      "epoch": 0.9866371762971154,
      "grad_norm": 0.37868139147758484,
      "learning_rate": 1.0234851191446404e-05,
      "loss": 0.5112,
      "step": 32118
    },
    {
      "epoch": 0.9866678954320647,
      "grad_norm": 0.3591846823692322,
      "learning_rate": 1.0234368047130233e-05,
      "loss": 0.5837,
      "step": 32119
    },
    {
      "epoch": 0.9866986145670138,
      "grad_norm": 0.34265029430389404,
      "learning_rate": 1.0233884902266682e-05,
      "loss": 0.4133,
      "step": 32120
    },
    {
      "epoch": 0.9867293337019629,
      "grad_norm": 0.3706163167953491,
      "learning_rate": 1.0233401756856873e-05,
      "loss": 0.5111,
      "step": 32121
    },
    {
      "epoch": 0.9867600528369121,
      "grad_norm": 0.39550280570983887,
      "learning_rate": 1.0232918610901941e-05,
      "loss": 0.5908,
      "step": 32122
    },
    {
      "epoch": 0.9867907719718613,
      "grad_norm": 0.3786122798919678,
      "learning_rate": 1.0232435464403008e-05,
      "loss": 0.565,
      "step": 32123
    },
    {
      "epoch": 0.9868214911068104,
      "grad_norm": 0.3481711447238922,
      "learning_rate": 1.0231952317361209e-05,
      "loss": 0.5473,
      "step": 32124
    },
    {
      "epoch": 0.9868522102417596,
      "grad_norm": 0.3632776141166687,
      "learning_rate": 1.0231469169777667e-05,
      "loss": 0.4319,
      "step": 32125
    },
    {
      "epoch": 0.9868829293767087,
      "grad_norm": 0.4220213294029236,
      "learning_rate": 1.0230986021653512e-05,
      "loss": 0.542,
      "step": 32126
    },
    {
      "epoch": 0.9869136485116579,
      "grad_norm": 0.3723360002040863,
      "learning_rate": 1.0230502872989874e-05,
      "loss": 0.618,
      "step": 32127
    },
    {
      "epoch": 0.9869443676466071,
      "grad_norm": 0.3628038465976715,
      "learning_rate": 1.0230019723787882e-05,
      "loss": 0.5021,
      "step": 32128
    },
    {
      "epoch": 0.9869750867815562,
      "grad_norm": 0.41431644558906555,
      "learning_rate": 1.0229536574048661e-05,
      "loss": 0.5136,
      "step": 32129
    },
    {
      "epoch": 0.9870058059165054,
      "grad_norm": 0.35162433981895447,
      "learning_rate": 1.0229053423773343e-05,
      "loss": 0.5911,
      "step": 32130
    },
    {
      "epoch": 0.9870365250514546,
      "grad_norm": 0.38678860664367676,
      "learning_rate": 1.0228570272963054e-05,
      "loss": 0.5687,
      "step": 32131
    },
    {
      "epoch": 0.9870672441864037,
      "grad_norm": 0.35793063044548035,
      "learning_rate": 1.022808712161892e-05,
      "loss": 0.4981,
      "step": 32132
    },
    {
      "epoch": 0.9870979633213529,
      "grad_norm": 0.40275445580482483,
      "learning_rate": 1.022760396974208e-05,
      "loss": 0.5517,
      "step": 32133
    },
    {
      "epoch": 0.987128682456302,
      "grad_norm": 0.3625172972679138,
      "learning_rate": 1.0227120817333648e-05,
      "loss": 0.4709,
      "step": 32134
    },
    {
      "epoch": 0.9871594015912512,
      "grad_norm": 0.3763721287250519,
      "learning_rate": 1.0226637664394762e-05,
      "loss": 0.5407,
      "step": 32135
    },
    {
      "epoch": 0.9871901207262004,
      "grad_norm": 0.38016101717948914,
      "learning_rate": 1.0226154510926546e-05,
      "loss": 0.5463,
      "step": 32136
    },
    {
      "epoch": 0.9872208398611495,
      "grad_norm": 0.38186562061309814,
      "learning_rate": 1.0225671356930136e-05,
      "loss": 0.5242,
      "step": 32137
    },
    {
      "epoch": 0.9872515589960986,
      "grad_norm": 0.3767383396625519,
      "learning_rate": 1.0225188202406648e-05,
      "loss": 0.5733,
      "step": 32138
    },
    {
      "epoch": 0.9872822781310479,
      "grad_norm": 0.3732231557369232,
      "learning_rate": 1.022470504735722e-05,
      "loss": 0.5574,
      "step": 32139
    },
    {
      "epoch": 0.987312997265997,
      "grad_norm": 0.3482104539871216,
      "learning_rate": 1.0224221891782979e-05,
      "loss": 0.5832,
      "step": 32140
    },
    {
      "epoch": 0.9873437164009462,
      "grad_norm": 0.4270542562007904,
      "learning_rate": 1.022373873568505e-05,
      "loss": 0.5141,
      "step": 32141
    },
    {
      "epoch": 0.9873744355358953,
      "grad_norm": 0.40638014674186707,
      "learning_rate": 1.0223255579064567e-05,
      "loss": 0.5385,
      "step": 32142
    },
    {
      "epoch": 0.9874051546708444,
      "grad_norm": 0.36546358466148376,
      "learning_rate": 1.0222772421922649e-05,
      "loss": 0.5154,
      "step": 32143
    },
    {
      "epoch": 0.9874358738057937,
      "grad_norm": 0.34225887060165405,
      "learning_rate": 1.0222289264260436e-05,
      "loss": 0.4871,
      "step": 32144
    },
    {
      "epoch": 0.9874665929407428,
      "grad_norm": 0.3784179389476776,
      "learning_rate": 1.022180610607905e-05,
      "loss": 0.4584,
      "step": 32145
    },
    {
      "epoch": 0.9874973120756919,
      "grad_norm": 0.3725365698337555,
      "learning_rate": 1.0221322947379618e-05,
      "loss": 0.5486,
      "step": 32146
    },
    {
      "epoch": 0.9875280312106411,
      "grad_norm": 0.32223111391067505,
      "learning_rate": 1.022083978816327e-05,
      "loss": 0.5042,
      "step": 32147
    },
    {
      "epoch": 0.9875587503455903,
      "grad_norm": 0.35299181938171387,
      "learning_rate": 1.0220356628431139e-05,
      "loss": 0.5189,
      "step": 32148
    },
    {
      "epoch": 0.9875894694805394,
      "grad_norm": 0.4264563322067261,
      "learning_rate": 1.021987346818435e-05,
      "loss": 0.5719,
      "step": 32149
    },
    {
      "epoch": 0.9876201886154886,
      "grad_norm": 0.41617056727409363,
      "learning_rate": 1.0219390307424027e-05,
      "loss": 0.5824,
      "step": 32150
    },
    {
      "epoch": 0.9876509077504377,
      "grad_norm": 0.37520840764045715,
      "learning_rate": 1.0218907146151307e-05,
      "loss": 0.5427,
      "step": 32151
    },
    {
      "epoch": 0.9876816268853869,
      "grad_norm": 0.35431089997291565,
      "learning_rate": 1.021842398436731e-05,
      "loss": 0.549,
      "step": 32152
    },
    {
      "epoch": 0.9877123460203361,
      "grad_norm": 0.48377498984336853,
      "learning_rate": 1.0217940822073172e-05,
      "loss": 0.5604,
      "step": 32153
    },
    {
      "epoch": 0.9877430651552852,
      "grad_norm": 0.3397085666656494,
      "learning_rate": 1.0217457659270014e-05,
      "loss": 0.4898,
      "step": 32154
    },
    {
      "epoch": 0.9877737842902344,
      "grad_norm": 0.3797539174556732,
      "learning_rate": 1.0216974495958973e-05,
      "loss": 0.5547,
      "step": 32155
    },
    {
      "epoch": 0.9878045034251836,
      "grad_norm": 0.38696128129959106,
      "learning_rate": 1.021649133214117e-05,
      "loss": 0.5423,
      "step": 32156
    },
    {
      "epoch": 0.9878352225601327,
      "grad_norm": 0.5899645090103149,
      "learning_rate": 1.0216008167817736e-05,
      "loss": 0.5291,
      "step": 32157
    },
    {
      "epoch": 0.9878659416950819,
      "grad_norm": 0.35277801752090454,
      "learning_rate": 1.0215525002989802e-05,
      "loss": 0.5592,
      "step": 32158
    },
    {
      "epoch": 0.987896660830031,
      "grad_norm": 0.37696176767349243,
      "learning_rate": 1.021504183765849e-05,
      "loss": 0.592,
      "step": 32159
    },
    {
      "epoch": 0.9879273799649801,
      "grad_norm": 0.35649850964546204,
      "learning_rate": 1.0214558671824938e-05,
      "loss": 0.5608,
      "step": 32160
    },
    {
      "epoch": 0.9879580990999294,
      "grad_norm": 0.40814509987831116,
      "learning_rate": 1.0214075505490267e-05,
      "loss": 0.463,
      "step": 32161
    },
    {
      "epoch": 0.9879888182348785,
      "grad_norm": 0.3736914098262787,
      "learning_rate": 1.0213592338655608e-05,
      "loss": 0.4952,
      "step": 32162
    },
    {
      "epoch": 0.9880195373698276,
      "grad_norm": 0.4202638268470764,
      "learning_rate": 1.0213109171322089e-05,
      "loss": 0.5297,
      "step": 32163
    },
    {
      "epoch": 0.9880502565047768,
      "grad_norm": 0.47559407353401184,
      "learning_rate": 1.021262600349084e-05,
      "loss": 0.5069,
      "step": 32164
    },
    {
      "epoch": 0.988080975639726,
      "grad_norm": 0.3845932185649872,
      "learning_rate": 1.0212142835162988e-05,
      "loss": 0.5424,
      "step": 32165
    },
    {
      "epoch": 0.9881116947746752,
      "grad_norm": 0.36255648732185364,
      "learning_rate": 1.021165966633966e-05,
      "loss": 0.5026,
      "step": 32166
    },
    {
      "epoch": 0.9881424139096243,
      "grad_norm": 0.33209875226020813,
      "learning_rate": 1.0211176497021987e-05,
      "loss": 0.5528,
      "step": 32167
    },
    {
      "epoch": 0.9881731330445734,
      "grad_norm": 0.35274022817611694,
      "learning_rate": 1.0210693327211094e-05,
      "loss": 0.5373,
      "step": 32168
    },
    {
      "epoch": 0.9882038521795227,
      "grad_norm": 0.41809704899787903,
      "learning_rate": 1.0210210156908115e-05,
      "loss": 0.5559,
      "step": 32169
    },
    {
      "epoch": 0.9882345713144718,
      "grad_norm": 0.363588809967041,
      "learning_rate": 1.0209726986114174e-05,
      "loss": 0.4873,
      "step": 32170
    },
    {
      "epoch": 0.9882652904494209,
      "grad_norm": 0.40022894740104675,
      "learning_rate": 1.0209243814830403e-05,
      "loss": 0.5703,
      "step": 32171
    },
    {
      "epoch": 0.9882960095843701,
      "grad_norm": 0.42741236090660095,
      "learning_rate": 1.0208760643057925e-05,
      "loss": 0.5815,
      "step": 32172
    },
    {
      "epoch": 0.9883267287193193,
      "grad_norm": 0.3297968804836273,
      "learning_rate": 1.0208277470797875e-05,
      "loss": 0.4382,
      "step": 32173
    },
    {
      "epoch": 0.9883574478542684,
      "grad_norm": 0.3636147677898407,
      "learning_rate": 1.0207794298051376e-05,
      "loss": 0.5098,
      "step": 32174
    },
    {
      "epoch": 0.9883881669892176,
      "grad_norm": 0.3582250773906708,
      "learning_rate": 1.0207311124819561e-05,
      "loss": 0.5082,
      "step": 32175
    },
    {
      "epoch": 0.9884188861241667,
      "grad_norm": 0.44586923718452454,
      "learning_rate": 1.0206827951103555e-05,
      "loss": 0.4821,
      "step": 32176
    },
    {
      "epoch": 0.9884496052591158,
      "grad_norm": 0.505623996257782,
      "learning_rate": 1.0206344776904489e-05,
      "loss": 0.5454,
      "step": 32177
    },
    {
      "epoch": 0.9884803243940651,
      "grad_norm": 0.37903133034706116,
      "learning_rate": 1.020586160222349e-05,
      "loss": 0.5132,
      "step": 32178
    },
    {
      "epoch": 0.9885110435290142,
      "grad_norm": 0.355342835187912,
      "learning_rate": 1.0205378427061685e-05,
      "loss": 0.5319,
      "step": 32179
    },
    {
      "epoch": 0.9885417626639634,
      "grad_norm": 0.38622143864631653,
      "learning_rate": 1.0204895251420208e-05,
      "loss": 0.5703,
      "step": 32180
    },
    {
      "epoch": 0.9885724817989126,
      "grad_norm": 0.3711675703525543,
      "learning_rate": 1.020441207530018e-05,
      "loss": 0.5019,
      "step": 32181
    },
    {
      "epoch": 0.9886032009338617,
      "grad_norm": 0.3763747215270996,
      "learning_rate": 1.0203928898702737e-05,
      "loss": 0.5945,
      "step": 32182
    },
    {
      "epoch": 0.9886339200688109,
      "grad_norm": 0.38206368684768677,
      "learning_rate": 1.0203445721629004e-05,
      "loss": 0.5102,
      "step": 32183
    },
    {
      "epoch": 0.98866463920376,
      "grad_norm": 0.3954969346523285,
      "learning_rate": 1.0202962544080106e-05,
      "loss": 0.5277,
      "step": 32184
    },
    {
      "epoch": 0.9886953583387091,
      "grad_norm": 0.3902527987957001,
      "learning_rate": 1.0202479366057176e-05,
      "loss": 0.543,
      "step": 32185
    },
    {
      "epoch": 0.9887260774736584,
      "grad_norm": 0.35028916597366333,
      "learning_rate": 1.020199618756134e-05,
      "loss": 0.5554,
      "step": 32186
    },
    {
      "epoch": 0.9887567966086075,
      "grad_norm": 0.37626126408576965,
      "learning_rate": 1.0201513008593731e-05,
      "loss": 0.6022,
      "step": 32187
    },
    {
      "epoch": 0.9887875157435566,
      "grad_norm": 0.3694612383842468,
      "learning_rate": 1.020102982915547e-05,
      "loss": 0.567,
      "step": 32188
    },
    {
      "epoch": 0.9888182348785058,
      "grad_norm": 0.35958945751190186,
      "learning_rate": 1.0200546649247695e-05,
      "loss": 0.5304,
      "step": 32189
    },
    {
      "epoch": 0.988848954013455,
      "grad_norm": 0.3824270963668823,
      "learning_rate": 1.0200063468871527e-05,
      "loss": 0.5463,
      "step": 32190
    },
    {
      "epoch": 0.9888796731484042,
      "grad_norm": 0.3467811048030853,
      "learning_rate": 1.0199580288028097e-05,
      "loss": 0.5632,
      "step": 32191
    },
    {
      "epoch": 0.9889103922833533,
      "grad_norm": 0.40626856684684753,
      "learning_rate": 1.0199097106718532e-05,
      "loss": 0.5807,
      "step": 32192
    },
    {
      "epoch": 0.9889411114183024,
      "grad_norm": 0.3858722746372223,
      "learning_rate": 1.0198613924943962e-05,
      "loss": 0.5767,
      "step": 32193
    },
    {
      "epoch": 0.9889718305532517,
      "grad_norm": 0.4119257628917694,
      "learning_rate": 1.0198130742705517e-05,
      "loss": 0.6101,
      "step": 32194
    },
    {
      "epoch": 0.9890025496882008,
      "grad_norm": 0.3952065110206604,
      "learning_rate": 1.0197647560004321e-05,
      "loss": 0.519,
      "step": 32195
    },
    {
      "epoch": 0.9890332688231499,
      "grad_norm": 0.3862069249153137,
      "learning_rate": 1.0197164376841507e-05,
      "loss": 0.4968,
      "step": 32196
    },
    {
      "epoch": 0.9890639879580991,
      "grad_norm": 0.41822198033332825,
      "learning_rate": 1.0196681193218202e-05,
      "loss": 0.5054,
      "step": 32197
    },
    {
      "epoch": 0.9890947070930483,
      "grad_norm": 0.3915591239929199,
      "learning_rate": 1.0196198009135534e-05,
      "loss": 0.5174,
      "step": 32198
    },
    {
      "epoch": 0.9891254262279974,
      "grad_norm": 0.5144933462142944,
      "learning_rate": 1.019571482459463e-05,
      "loss": 0.6168,
      "step": 32199
    },
    {
      "epoch": 0.9891561453629466,
      "grad_norm": 0.3800897002220154,
      "learning_rate": 1.0195231639596625e-05,
      "loss": 0.531,
      "step": 32200
    },
    {
      "epoch": 0.9891868644978957,
      "grad_norm": 0.3817237615585327,
      "learning_rate": 1.019474845414264e-05,
      "loss": 0.5422,
      "step": 32201
    },
    {
      "epoch": 0.989217583632845,
      "grad_norm": 0.41069623827934265,
      "learning_rate": 1.0194265268233807e-05,
      "loss": 0.5677,
      "step": 32202
    },
    {
      "epoch": 0.9892483027677941,
      "grad_norm": 0.4282089173793793,
      "learning_rate": 1.0193782081871255e-05,
      "loss": 0.5582,
      "step": 32203
    },
    {
      "epoch": 0.9892790219027432,
      "grad_norm": 0.3866927921772003,
      "learning_rate": 1.0193298895056108e-05,
      "loss": 0.5707,
      "step": 32204
    },
    {
      "epoch": 0.9893097410376924,
      "grad_norm": 0.40817177295684814,
      "learning_rate": 1.01928157077895e-05,
      "loss": 0.5744,
      "step": 32205
    },
    {
      "epoch": 0.9893404601726415,
      "grad_norm": 0.4030611217021942,
      "learning_rate": 1.0192332520072556e-05,
      "loss": 0.5965,
      "step": 32206
    },
    {
      "epoch": 0.9893711793075907,
      "grad_norm": 0.41297513246536255,
      "learning_rate": 1.019184933190641e-05,
      "loss": 0.4977,
      "step": 32207
    },
    {
      "epoch": 0.9894018984425399,
      "grad_norm": 0.39029833674430847,
      "learning_rate": 1.0191366143292183e-05,
      "loss": 0.5556,
      "step": 32208
    },
    {
      "epoch": 0.989432617577489,
      "grad_norm": 0.3773021101951599,
      "learning_rate": 1.0190882954231008e-05,
      "loss": 0.5428,
      "step": 32209
    },
    {
      "epoch": 0.9894633367124381,
      "grad_norm": 0.39592665433883667,
      "learning_rate": 1.019039976472401e-05,
      "loss": 0.5394,
      "step": 32210
    },
    {
      "epoch": 0.9894940558473874,
      "grad_norm": 0.3763681650161743,
      "learning_rate": 1.0189916574772325e-05,
      "loss": 0.583,
      "step": 32211
    },
    {
      "epoch": 0.9895247749823365,
      "grad_norm": 0.4100067615509033,
      "learning_rate": 1.0189433384377071e-05,
      "loss": 0.5448,
      "step": 32212
    },
    {
      "epoch": 0.9895554941172856,
      "grad_norm": 0.355919748544693,
      "learning_rate": 1.0188950193539387e-05,
      "loss": 0.557,
      "step": 32213
    },
    {
      "epoch": 0.9895862132522348,
      "grad_norm": 0.37298139929771423,
      "learning_rate": 1.0188467002260394e-05,
      "loss": 0.5742,
      "step": 32214
    },
    {
      "epoch": 0.989616932387184,
      "grad_norm": 0.3398204445838928,
      "learning_rate": 1.0187983810541223e-05,
      "loss": 0.5347,
      "step": 32215
    },
    {
      "epoch": 0.9896476515221332,
      "grad_norm": 0.355074018239975,
      "learning_rate": 1.0187500618383004e-05,
      "loss": 0.511,
      "step": 32216
    },
    {
      "epoch": 0.9896783706570823,
      "grad_norm": 0.4251198172569275,
      "learning_rate": 1.0187017425786863e-05,
      "loss": 0.6844,
      "step": 32217
    },
    {
      "epoch": 0.9897090897920314,
      "grad_norm": 0.5558260679244995,
      "learning_rate": 1.0186534232753933e-05,
      "loss": 0.5837,
      "step": 32218
    },
    {
      "epoch": 0.9897398089269807,
      "grad_norm": 0.39636632800102234,
      "learning_rate": 1.0186051039285335e-05,
      "loss": 0.4636,
      "step": 32219
    },
    {
      "epoch": 0.9897705280619298,
      "grad_norm": 0.4399622678756714,
      "learning_rate": 1.0185567845382205e-05,
      "loss": 0.499,
      "step": 32220
    },
    {
      "epoch": 0.9898012471968789,
      "grad_norm": 0.45344293117523193,
      "learning_rate": 1.0185084651045667e-05,
      "loss": 0.6005,
      "step": 32221
    },
    {
      "epoch": 0.9898319663318281,
      "grad_norm": 0.36356452107429504,
      "learning_rate": 1.018460145627685e-05,
      "loss": 0.4415,
      "step": 32222
    },
    {
      "epoch": 0.9898626854667772,
      "grad_norm": 0.6256075501441956,
      "learning_rate": 1.0184118261076885e-05,
      "loss": 0.4918,
      "step": 32223
    },
    {
      "epoch": 0.9898934046017264,
      "grad_norm": 0.376596063375473,
      "learning_rate": 1.0183635065446898e-05,
      "loss": 0.5648,
      "step": 32224
    },
    {
      "epoch": 0.9899241237366756,
      "grad_norm": 0.5305349826812744,
      "learning_rate": 1.0183151869388019e-05,
      "loss": 0.5808,
      "step": 32225
    },
    {
      "epoch": 0.9899548428716247,
      "grad_norm": 0.39791011810302734,
      "learning_rate": 1.0182668672901375e-05,
      "loss": 0.4937,
      "step": 32226
    },
    {
      "epoch": 0.989985562006574,
      "grad_norm": 0.3604849576950073,
      "learning_rate": 1.0182185475988096e-05,
      "loss": 0.5107,
      "step": 32227
    },
    {
      "epoch": 0.9900162811415231,
      "grad_norm": 0.38815629482269287,
      "learning_rate": 1.018170227864931e-05,
      "loss": 0.5885,
      "step": 32228
    },
    {
      "epoch": 0.9900470002764722,
      "grad_norm": 0.3641103506088257,
      "learning_rate": 1.0181219080886146e-05,
      "loss": 0.5414,
      "step": 32229
    },
    {
      "epoch": 0.9900777194114214,
      "grad_norm": 0.5917376279830933,
      "learning_rate": 1.018073588269973e-05,
      "loss": 0.5704,
      "step": 32230
    },
    {
      "epoch": 0.9901084385463705,
      "grad_norm": 0.37418481707572937,
      "learning_rate": 1.0180252684091195e-05,
      "loss": 0.553,
      "step": 32231
    },
    {
      "epoch": 0.9901391576813197,
      "grad_norm": 0.42543885111808777,
      "learning_rate": 1.0179769485061668e-05,
      "loss": 0.5737,
      "step": 32232
    },
    {
      "epoch": 0.9901698768162689,
      "grad_norm": 0.4238223433494568,
      "learning_rate": 1.0179286285612275e-05,
      "loss": 0.5125,
      "step": 32233
    },
    {
      "epoch": 0.990200595951218,
      "grad_norm": 0.32704800367355347,
      "learning_rate": 1.0178803085744149e-05,
      "loss": 0.4435,
      "step": 32234
    },
    {
      "epoch": 0.9902313150861671,
      "grad_norm": 0.38485920429229736,
      "learning_rate": 1.0178319885458415e-05,
      "loss": 0.5392,
      "step": 32235
    },
    {
      "epoch": 0.9902620342211164,
      "grad_norm": 1.1051019430160522,
      "learning_rate": 1.01778366847562e-05,
      "loss": 0.5761,
      "step": 32236
    },
    {
      "epoch": 0.9902927533560655,
      "grad_norm": 0.36702483892440796,
      "learning_rate": 1.0177353483638637e-05,
      "loss": 0.58,
      "step": 32237
    },
    {
      "epoch": 0.9903234724910146,
      "grad_norm": 0.3971094489097595,
      "learning_rate": 1.0176870282106853e-05,
      "loss": 0.5056,
      "step": 32238
    },
    {
      "epoch": 0.9903541916259638,
      "grad_norm": 0.4128482937812805,
      "learning_rate": 1.0176387080161976e-05,
      "loss": 0.566,
      "step": 32239
    },
    {
      "epoch": 0.990384910760913,
      "grad_norm": 0.34403273463249207,
      "learning_rate": 1.0175903877805131e-05,
      "loss": 0.5203,
      "step": 32240
    },
    {
      "epoch": 0.9904156298958622,
      "grad_norm": 0.39846155047416687,
      "learning_rate": 1.0175420675037455e-05,
      "loss": 0.5189,
      "step": 32241
    },
    {
      "epoch": 0.9904463490308113,
      "grad_norm": 0.4115917384624481,
      "learning_rate": 1.0174937471860069e-05,
      "loss": 0.5265,
      "step": 32242
    },
    {
      "epoch": 0.9904770681657604,
      "grad_norm": 0.3716435134410858,
      "learning_rate": 1.0174454268274106e-05,
      "loss": 0.5351,
      "step": 32243
    },
    {
      "epoch": 0.9905077873007097,
      "grad_norm": 0.4204607605934143,
      "learning_rate": 1.017397106428069e-05,
      "loss": 0.6175,
      "step": 32244
    },
    {
      "epoch": 0.9905385064356588,
      "grad_norm": 0.3876058757305145,
      "learning_rate": 1.0173487859880958e-05,
      "loss": 0.5088,
      "step": 32245
    },
    {
      "epoch": 0.9905692255706079,
      "grad_norm": 0.3603725731372833,
      "learning_rate": 1.0173004655076028e-05,
      "loss": 0.5465,
      "step": 32246
    },
    {
      "epoch": 0.9905999447055571,
      "grad_norm": 0.36036229133605957,
      "learning_rate": 1.0172521449867034e-05,
      "loss": 0.5298,
      "step": 32247
    },
    {
      "epoch": 0.9906306638405062,
      "grad_norm": 0.3506869673728943,
      "learning_rate": 1.0172038244255107e-05,
      "loss": 0.5526,
      "step": 32248
    },
    {
      "epoch": 0.9906613829754554,
      "grad_norm": 0.33401280641555786,
      "learning_rate": 1.0171555038241367e-05,
      "loss": 0.4899,
      "step": 32249
    },
    {
      "epoch": 0.9906921021104046,
      "grad_norm": 0.39873453974723816,
      "learning_rate": 1.0171071831826953e-05,
      "loss": 0.549,
      "step": 32250
    },
    {
      "epoch": 0.9907228212453537,
      "grad_norm": 0.38574615120887756,
      "learning_rate": 1.0170588625012987e-05,
      "loss": 0.5526,
      "step": 32251
    },
    {
      "epoch": 0.9907535403803029,
      "grad_norm": 0.38286495208740234,
      "learning_rate": 1.0170105417800602e-05,
      "loss": 0.5904,
      "step": 32252
    },
    {
      "epoch": 0.9907842595152521,
      "grad_norm": 0.37456026673316956,
      "learning_rate": 1.0169622210190923e-05,
      "loss": 0.6155,
      "step": 32253
    },
    {
      "epoch": 0.9908149786502012,
      "grad_norm": 0.34495094418525696,
      "learning_rate": 1.0169139002185078e-05,
      "loss": 0.5106,
      "step": 32254
    },
    {
      "epoch": 0.9908456977851504,
      "grad_norm": 0.37490004301071167,
      "learning_rate": 1.0168655793784199e-05,
      "loss": 0.5542,
      "step": 32255
    },
    {
      "epoch": 0.9908764169200995,
      "grad_norm": 0.4356817901134491,
      "learning_rate": 1.0168172584989409e-05,
      "loss": 0.5613,
      "step": 32256
    },
    {
      "epoch": 0.9909071360550487,
      "grad_norm": 0.3393363356590271,
      "learning_rate": 1.0167689375801843e-05,
      "loss": 0.5426,
      "step": 32257
    },
    {
      "epoch": 0.9909378551899979,
      "grad_norm": 0.368733674287796,
      "learning_rate": 1.0167206166222624e-05,
      "loss": 0.4837,
      "step": 32258
    },
    {
      "epoch": 0.990968574324947,
      "grad_norm": 0.41447463631629944,
      "learning_rate": 1.0166722956252888e-05,
      "loss": 0.5273,
      "step": 32259
    },
    {
      "epoch": 0.9909992934598961,
      "grad_norm": 0.38014334440231323,
      "learning_rate": 1.0166239745893755e-05,
      "loss": 0.5252,
      "step": 32260
    },
    {
      "epoch": 0.9910300125948454,
      "grad_norm": 0.907802939414978,
      "learning_rate": 1.0165756535146361e-05,
      "loss": 0.4684,
      "step": 32261
    },
    {
      "epoch": 0.9910607317297945,
      "grad_norm": 0.3526974320411682,
      "learning_rate": 1.0165273324011829e-05,
      "loss": 0.5587,
      "step": 32262
    },
    {
      "epoch": 0.9910914508647436,
      "grad_norm": 0.3383224606513977,
      "learning_rate": 1.016479011249129e-05,
      "loss": 0.5372,
      "step": 32263
    },
    {
      "epoch": 0.9911221699996928,
      "grad_norm": 0.3339794874191284,
      "learning_rate": 1.0164306900585872e-05,
      "loss": 0.4884,
      "step": 32264
    },
    {
      "epoch": 0.991152889134642,
      "grad_norm": 0.3723840117454529,
      "learning_rate": 1.0163823688296702e-05,
      "loss": 0.5525,
      "step": 32265
    },
    {
      "epoch": 0.9911836082695912,
      "grad_norm": 0.3723396062850952,
      "learning_rate": 1.0163340475624911e-05,
      "loss": 0.5722,
      "step": 32266
    },
    {
      "epoch": 0.9912143274045403,
      "grad_norm": 0.3991277813911438,
      "learning_rate": 1.0162857262571626e-05,
      "loss": 0.6023,
      "step": 32267
    },
    {
      "epoch": 0.9912450465394894,
      "grad_norm": 0.4546571671962738,
      "learning_rate": 1.016237404913798e-05,
      "loss": 0.5726,
      "step": 32268
    },
    {
      "epoch": 0.9912757656744386,
      "grad_norm": 0.4115605652332306,
      "learning_rate": 1.0161890835325095e-05,
      "loss": 0.5303,
      "step": 32269
    },
    {
      "epoch": 0.9913064848093878,
      "grad_norm": 0.3842051029205322,
      "learning_rate": 1.0161407621134105e-05,
      "loss": 0.4946,
      "step": 32270
    },
    {
      "epoch": 0.9913372039443369,
      "grad_norm": 0.3567367494106293,
      "learning_rate": 1.0160924406566135e-05,
      "loss": 0.5794,
      "step": 32271
    },
    {
      "epoch": 0.9913679230792861,
      "grad_norm": 0.41901737451553345,
      "learning_rate": 1.0160441191622314e-05,
      "loss": 0.5448,
      "step": 32272
    },
    {
      "epoch": 0.9913986422142352,
      "grad_norm": 0.37941789627075195,
      "learning_rate": 1.0159957976303773e-05,
      "loss": 0.5053,
      "step": 32273
    },
    {
      "epoch": 0.9914293613491844,
      "grad_norm": 0.37065595388412476,
      "learning_rate": 1.0159474760611638e-05,
      "loss": 0.5489,
      "step": 32274
    },
    {
      "epoch": 0.9914600804841336,
      "grad_norm": 0.3861217796802521,
      "learning_rate": 1.015899154454704e-05,
      "loss": 0.6546,
      "step": 32275
    },
    {
      "epoch": 0.9914907996190827,
      "grad_norm": 0.37479111552238464,
      "learning_rate": 1.0158508328111104e-05,
      "loss": 0.5228,
      "step": 32276
    },
    {
      "epoch": 0.9915215187540319,
      "grad_norm": 0.41581717133522034,
      "learning_rate": 1.0158025111304962e-05,
      "loss": 0.5759,
      "step": 32277
    },
    {
      "epoch": 0.9915522378889811,
      "grad_norm": 0.3540689945220947,
      "learning_rate": 1.015754189412974e-05,
      "loss": 0.4879,
      "step": 32278
    },
    {
      "epoch": 0.9915829570239302,
      "grad_norm": 0.3910854756832123,
      "learning_rate": 1.015705867658657e-05,
      "loss": 0.5574,
      "step": 32279
    },
    {
      "epoch": 0.9916136761588794,
      "grad_norm": 0.3529926538467407,
      "learning_rate": 1.0156575458676576e-05,
      "loss": 0.509,
      "step": 32280
    },
    {
      "epoch": 0.9916443952938285,
      "grad_norm": 0.4353283941745758,
      "learning_rate": 1.0156092240400892e-05,
      "loss": 0.6398,
      "step": 32281
    },
    {
      "epoch": 0.9916751144287776,
      "grad_norm": 0.4393685460090637,
      "learning_rate": 1.0155609021760643e-05,
      "loss": 0.4854,
      "step": 32282
    },
    {
      "epoch": 0.9917058335637269,
      "grad_norm": 0.3620607256889343,
      "learning_rate": 1.0155125802756958e-05,
      "loss": 0.5846,
      "step": 32283
    },
    {
      "epoch": 0.991736552698676,
      "grad_norm": 0.39055222272872925,
      "learning_rate": 1.0154642583390965e-05,
      "loss": 0.566,
      "step": 32284
    },
    {
      "epoch": 0.9917672718336251,
      "grad_norm": 0.37977153062820435,
      "learning_rate": 1.0154159363663792e-05,
      "loss": 0.5372,
      "step": 32285
    },
    {
      "epoch": 0.9917979909685744,
      "grad_norm": 0.37354978919029236,
      "learning_rate": 1.0153676143576572e-05,
      "loss": 0.5762,
      "step": 32286
    },
    {
      "epoch": 0.9918287101035235,
      "grad_norm": 0.4053434133529663,
      "learning_rate": 1.0153192923130429e-05,
      "loss": 0.5669,
      "step": 32287
    },
    {
      "epoch": 0.9918594292384726,
      "grad_norm": 0.37165477871894836,
      "learning_rate": 1.0152709702326492e-05,
      "loss": 0.5108,
      "step": 32288
    },
    {
      "epoch": 0.9918901483734218,
      "grad_norm": 0.4061339795589447,
      "learning_rate": 1.0152226481165894e-05,
      "loss": 0.5535,
      "step": 32289
    },
    {
      "epoch": 0.9919208675083709,
      "grad_norm": 0.39246997237205505,
      "learning_rate": 1.0151743259649758e-05,
      "loss": 0.6204,
      "step": 32290
    },
    {
      "epoch": 0.9919515866433202,
      "grad_norm": 0.35129788517951965,
      "learning_rate": 1.0151260037779217e-05,
      "loss": 0.4708,
      "step": 32291
    },
    {
      "epoch": 0.9919823057782693,
      "grad_norm": 0.46255698800086975,
      "learning_rate": 1.0150776815555396e-05,
      "loss": 0.5871,
      "step": 32292
    },
    {
      "epoch": 0.9920130249132184,
      "grad_norm": 0.4030190408229828,
      "learning_rate": 1.0150293592979426e-05,
      "loss": 0.5389,
      "step": 32293
    },
    {
      "epoch": 0.9920437440481676,
      "grad_norm": 0.36360347270965576,
      "learning_rate": 1.0149810370052433e-05,
      "loss": 0.5235,
      "step": 32294
    },
    {
      "epoch": 0.9920744631831168,
      "grad_norm": 0.37075838446617126,
      "learning_rate": 1.0149327146775551e-05,
      "loss": 0.5611,
      "step": 32295
    },
    {
      "epoch": 0.9921051823180659,
      "grad_norm": 0.3758288323879242,
      "learning_rate": 1.0148843923149902e-05,
      "loss": 0.586,
      "step": 32296
    },
    {
      "epoch": 0.9921359014530151,
      "grad_norm": 0.3786045014858246,
      "learning_rate": 1.014836069917662e-05,
      "loss": 0.525,
      "step": 32297
    },
    {
      "epoch": 0.9921666205879642,
      "grad_norm": 0.38423487544059753,
      "learning_rate": 1.0147877474856832e-05,
      "loss": 0.5309,
      "step": 32298
    },
    {
      "epoch": 0.9921973397229134,
      "grad_norm": 0.4114548861980438,
      "learning_rate": 1.014739425019166e-05,
      "loss": 0.5445,
      "step": 32299
    },
    {
      "epoch": 0.9922280588578626,
      "grad_norm": 0.3660309910774231,
      "learning_rate": 1.0146911025182245e-05,
      "loss": 0.4923,
      "step": 32300
    },
    {
      "epoch": 0.9922587779928117,
      "grad_norm": 0.3678315281867981,
      "learning_rate": 1.0146427799829704e-05,
      "loss": 0.5438,
      "step": 32301
    },
    {
      "epoch": 0.9922894971277609,
      "grad_norm": 0.38054749369621277,
      "learning_rate": 1.0145944574135174e-05,
      "loss": 0.5454,
      "step": 32302
    },
    {
      "epoch": 0.99232021626271,
      "grad_norm": 0.39484742283821106,
      "learning_rate": 1.0145461348099777e-05,
      "loss": 0.5712,
      "step": 32303
    },
    {
      "epoch": 0.9923509353976592,
      "grad_norm": 0.35421767830848694,
      "learning_rate": 1.0144978121724647e-05,
      "loss": 0.5068,
      "step": 32304
    },
    {
      "epoch": 0.9923816545326084,
      "grad_norm": 0.3927289843559265,
      "learning_rate": 1.0144494895010912e-05,
      "loss": 0.5661,
      "step": 32305
    },
    {
      "epoch": 0.9924123736675575,
      "grad_norm": 0.44859829545021057,
      "learning_rate": 1.0144011667959698e-05,
      "loss": 0.5438,
      "step": 32306
    },
    {
      "epoch": 0.9924430928025066,
      "grad_norm": 0.3510657846927643,
      "learning_rate": 1.0143528440572133e-05,
      "loss": 0.4257,
      "step": 32307
    },
    {
      "epoch": 0.9924738119374559,
      "grad_norm": 0.35505038499832153,
      "learning_rate": 1.0143045212849348e-05,
      "loss": 0.5048,
      "step": 32308
    },
    {
      "epoch": 0.992504531072405,
      "grad_norm": 0.41280388832092285,
      "learning_rate": 1.0142561984792472e-05,
      "loss": 0.5666,
      "step": 32309
    },
    {
      "epoch": 0.9925352502073541,
      "grad_norm": 0.35539841651916504,
      "learning_rate": 1.0142078756402631e-05,
      "loss": 0.5674,
      "step": 32310
    },
    {
      "epoch": 0.9925659693423033,
      "grad_norm": 0.48130345344543457,
      "learning_rate": 1.0141595527680956e-05,
      "loss": 0.6614,
      "step": 32311
    },
    {
      "epoch": 0.9925966884772525,
      "grad_norm": 0.3733084201812744,
      "learning_rate": 1.0141112298628575e-05,
      "loss": 0.6236,
      "step": 32312
    },
    {
      "epoch": 0.9926274076122017,
      "grad_norm": 0.4213038682937622,
      "learning_rate": 1.0140629069246617e-05,
      "loss": 0.4828,
      "step": 32313
    },
    {
      "epoch": 0.9926581267471508,
      "grad_norm": 0.3847908675670624,
      "learning_rate": 1.0140145839536209e-05,
      "loss": 0.5769,
      "step": 32314
    },
    {
      "epoch": 0.9926888458820999,
      "grad_norm": 0.37023380398750305,
      "learning_rate": 1.013966260949848e-05,
      "loss": 0.5766,
      "step": 32315
    },
    {
      "epoch": 0.9927195650170492,
      "grad_norm": 0.4144892394542694,
      "learning_rate": 1.0139179379134563e-05,
      "loss": 0.563,
      "step": 32316
    },
    {
      "epoch": 0.9927502841519983,
      "grad_norm": 0.4024188220500946,
      "learning_rate": 1.0138696148445577e-05,
      "loss": 0.5083,
      "step": 32317
    },
    {
      "epoch": 0.9927810032869474,
      "grad_norm": 0.3184928596019745,
      "learning_rate": 1.0138212917432661e-05,
      "loss": 0.4635,
      "step": 32318
    },
    {
      "epoch": 0.9928117224218966,
      "grad_norm": 0.46869754791259766,
      "learning_rate": 1.0137729686096935e-05,
      "loss": 0.5997,
      "step": 32319
    },
    {
      "epoch": 0.9928424415568458,
      "grad_norm": 0.36067628860473633,
      "learning_rate": 1.0137246454439535e-05,
      "loss": 0.5386,
      "step": 32320
    },
    {
      "epoch": 0.9928731606917949,
      "grad_norm": 0.3709237575531006,
      "learning_rate": 1.0136763222461585e-05,
      "loss": 0.5001,
      "step": 32321
    },
    {
      "epoch": 0.9929038798267441,
      "grad_norm": 0.399245947599411,
      "learning_rate": 1.0136279990164215e-05,
      "loss": 0.5741,
      "step": 32322
    },
    {
      "epoch": 0.9929345989616932,
      "grad_norm": 0.39587199687957764,
      "learning_rate": 1.0135796757548554e-05,
      "loss": 0.4988,
      "step": 32323
    },
    {
      "epoch": 0.9929653180966423,
      "grad_norm": 0.3928129971027374,
      "learning_rate": 1.0135313524615729e-05,
      "loss": 0.5575,
      "step": 32324
    },
    {
      "epoch": 0.9929960372315916,
      "grad_norm": 0.3955269157886505,
      "learning_rate": 1.0134830291366873e-05,
      "loss": 0.5366,
      "step": 32325
    },
    {
      "epoch": 0.9930267563665407,
      "grad_norm": 0.36662885546684265,
      "learning_rate": 1.013434705780311e-05,
      "loss": 0.4428,
      "step": 32326
    },
    {
      "epoch": 0.9930574755014899,
      "grad_norm": 0.35725805163383484,
      "learning_rate": 1.013386382392557e-05,
      "loss": 0.4562,
      "step": 32327
    },
    {
      "epoch": 0.993088194636439,
      "grad_norm": 1.1828842163085938,
      "learning_rate": 1.0133380589735377e-05,
      "loss": 0.5641,
      "step": 32328
    },
    {
      "epoch": 0.9931189137713882,
      "grad_norm": 0.39458832144737244,
      "learning_rate": 1.013289735523367e-05,
      "loss": 0.5201,
      "step": 32329
    },
    {
      "epoch": 0.9931496329063374,
      "grad_norm": 0.39535757899284363,
      "learning_rate": 1.013241412042157e-05,
      "loss": 0.5075,
      "step": 32330
    },
    {
      "epoch": 0.9931803520412865,
      "grad_norm": 0.4177777171134949,
      "learning_rate": 1.013193088530021e-05,
      "loss": 0.5956,
      "step": 32331
    },
    {
      "epoch": 0.9932110711762356,
      "grad_norm": 0.3796970546245575,
      "learning_rate": 1.0131447649870712e-05,
      "loss": 0.6255,
      "step": 32332
    },
    {
      "epoch": 0.9932417903111849,
      "grad_norm": 0.35397031903266907,
      "learning_rate": 1.0130964414134211e-05,
      "loss": 0.5111,
      "step": 32333
    },
    {
      "epoch": 0.993272509446134,
      "grad_norm": 0.4327811896800995,
      "learning_rate": 1.0130481178091835e-05,
      "loss": 0.5119,
      "step": 32334
    },
    {
      "epoch": 0.9933032285810831,
      "grad_norm": 0.3871498107910156,
      "learning_rate": 1.0129997941744708e-05,
      "loss": 0.5825,
      "step": 32335
    },
    {
      "epoch": 0.9933339477160323,
      "grad_norm": 0.37914830446243286,
      "learning_rate": 1.0129514705093966e-05,
      "loss": 0.5263,
      "step": 32336
    },
    {
      "epoch": 0.9933646668509815,
      "grad_norm": 0.3796376883983612,
      "learning_rate": 1.0129031468140728e-05,
      "loss": 0.5359,
      "step": 32337
    },
    {
      "epoch": 0.9933953859859307,
      "grad_norm": 0.4221058189868927,
      "learning_rate": 1.0128548230886132e-05,
      "loss": 0.4277,
      "step": 32338
    },
    {
      "epoch": 0.9934261051208798,
      "grad_norm": 0.40415066480636597,
      "learning_rate": 1.0128064993331301e-05,
      "loss": 0.5451,
      "step": 32339
    },
    {
      "epoch": 0.9934568242558289,
      "grad_norm": 0.3732110261917114,
      "learning_rate": 1.0127581755477365e-05,
      "loss": 0.5467,
      "step": 32340
    },
    {
      "epoch": 0.9934875433907782,
      "grad_norm": 0.3436453640460968,
      "learning_rate": 1.0127098517325453e-05,
      "loss": 0.5944,
      "step": 32341
    },
    {
      "epoch": 0.9935182625257273,
      "grad_norm": 0.3754141926765442,
      "learning_rate": 1.0126615278876692e-05,
      "loss": 0.5628,
      "step": 32342
    },
    {
      "epoch": 0.9935489816606764,
      "grad_norm": 0.4354453682899475,
      "learning_rate": 1.0126132040132216e-05,
      "loss": 0.5705,
      "step": 32343
    },
    {
      "epoch": 0.9935797007956256,
      "grad_norm": 0.4480322301387787,
      "learning_rate": 1.0125648801093146e-05,
      "loss": 0.5747,
      "step": 32344
    },
    {
      "epoch": 0.9936104199305748,
      "grad_norm": 0.35247376561164856,
      "learning_rate": 1.012516556176062e-05,
      "loss": 0.4727,
      "step": 32345
    },
    {
      "epoch": 0.9936411390655239,
      "grad_norm": 0.37638911604881287,
      "learning_rate": 1.0124682322135755e-05,
      "loss": 0.6037,
      "step": 32346
    },
    {
      "epoch": 0.9936718582004731,
      "grad_norm": 0.3952213227748871,
      "learning_rate": 1.012419908221969e-05,
      "loss": 0.5161,
      "step": 32347
    },
    {
      "epoch": 0.9937025773354222,
      "grad_norm": 0.372242271900177,
      "learning_rate": 1.0123715842013546e-05,
      "loss": 0.5272,
      "step": 32348
    },
    {
      "epoch": 0.9937332964703713,
      "grad_norm": 0.363162100315094,
      "learning_rate": 1.0123232601518458e-05,
      "loss": 0.5105,
      "step": 32349
    },
    {
      "epoch": 0.9937640156053206,
      "grad_norm": 0.383843332529068,
      "learning_rate": 1.0122749360735552e-05,
      "loss": 0.5642,
      "step": 32350
    },
    {
      "epoch": 0.9937947347402697,
      "grad_norm": 0.4598860442638397,
      "learning_rate": 1.0122266119665953e-05,
      "loss": 0.5829,
      "step": 32351
    },
    {
      "epoch": 0.9938254538752189,
      "grad_norm": 0.38057762384414673,
      "learning_rate": 1.0121782878310795e-05,
      "loss": 0.4573,
      "step": 32352
    },
    {
      "epoch": 0.993856173010168,
      "grad_norm": 0.3661222457885742,
      "learning_rate": 1.0121299636671203e-05,
      "loss": 0.5417,
      "step": 32353
    },
    {
      "epoch": 0.9938868921451172,
      "grad_norm": 0.4155339300632477,
      "learning_rate": 1.012081639474831e-05,
      "loss": 0.5316,
      "step": 32354
    },
    {
      "epoch": 0.9939176112800664,
      "grad_norm": 0.3414105772972107,
      "learning_rate": 1.0120333152543238e-05,
      "loss": 0.4968,
      "step": 32355
    },
    {
      "epoch": 0.9939483304150155,
      "grad_norm": 0.3667045831680298,
      "learning_rate": 1.0119849910057123e-05,
      "loss": 0.5871,
      "step": 32356
    },
    {
      "epoch": 0.9939790495499646,
      "grad_norm": 0.3671264052391052,
      "learning_rate": 1.011936666729109e-05,
      "loss": 0.6167,
      "step": 32357
    },
    {
      "epoch": 0.9940097686849139,
      "grad_norm": 0.3853718638420105,
      "learning_rate": 1.0118883424246264e-05,
      "loss": 0.5515,
      "step": 32358
    },
    {
      "epoch": 0.994040487819863,
      "grad_norm": 0.3725956380367279,
      "learning_rate": 1.0118400180923779e-05,
      "loss": 0.4856,
      "step": 32359
    },
    {
      "epoch": 0.9940712069548121,
      "grad_norm": 0.38769960403442383,
      "learning_rate": 1.0117916937324763e-05,
      "loss": 0.6163,
      "step": 32360
    },
    {
      "epoch": 0.9941019260897613,
      "grad_norm": 0.37752413749694824,
      "learning_rate": 1.0117433693450345e-05,
      "loss": 0.5497,
      "step": 32361
    },
    {
      "epoch": 0.9941326452247105,
      "grad_norm": 0.37024715542793274,
      "learning_rate": 1.011695044930165e-05,
      "loss": 0.5575,
      "step": 32362
    },
    {
      "epoch": 0.9941633643596597,
      "grad_norm": 0.41636183857917786,
      "learning_rate": 1.0116467204879811e-05,
      "loss": 0.5525,
      "step": 32363
    },
    {
      "epoch": 0.9941940834946088,
      "grad_norm": 0.4153290092945099,
      "learning_rate": 1.0115983960185954e-05,
      "loss": 0.5772,
      "step": 32364
    },
    {
      "epoch": 0.9942248026295579,
      "grad_norm": 0.3899405300617218,
      "learning_rate": 1.0115500715221209e-05,
      "loss": 0.5991,
      "step": 32365
    },
    {
      "epoch": 0.9942555217645072,
      "grad_norm": 0.3532464802265167,
      "learning_rate": 1.0115017469986704e-05,
      "loss": 0.427,
      "step": 32366
    },
    {
      "epoch": 0.9942862408994563,
      "grad_norm": 0.3651235103607178,
      "learning_rate": 1.0114534224483568e-05,
      "loss": 0.4891,
      "step": 32367
    },
    {
      "epoch": 0.9943169600344054,
      "grad_norm": 0.3908202052116394,
      "learning_rate": 1.0114050978712928e-05,
      "loss": 0.5129,
      "step": 32368
    },
    {
      "epoch": 0.9943476791693546,
      "grad_norm": 0.36422044038772583,
      "learning_rate": 1.0113567732675916e-05,
      "loss": 0.57,
      "step": 32369
    },
    {
      "epoch": 0.9943783983043037,
      "grad_norm": 0.3861384093761444,
      "learning_rate": 1.0113084486373656e-05,
      "loss": 0.549,
      "step": 32370
    },
    {
      "epoch": 0.9944091174392529,
      "grad_norm": 0.4990008473396301,
      "learning_rate": 1.011260123980728e-05,
      "loss": 0.6204,
      "step": 32371
    },
    {
      "epoch": 0.9944398365742021,
      "grad_norm": 0.3760487735271454,
      "learning_rate": 1.0112117992977918e-05,
      "loss": 0.5089,
      "step": 32372
    },
    {
      "epoch": 0.9944705557091512,
      "grad_norm": 0.4104313254356384,
      "learning_rate": 1.0111634745886694e-05,
      "loss": 0.5575,
      "step": 32373
    },
    {
      "epoch": 0.9945012748441003,
      "grad_norm": 0.3898140788078308,
      "learning_rate": 1.011115149853474e-05,
      "loss": 0.5268,
      "step": 32374
    },
    {
      "epoch": 0.9945319939790496,
      "grad_norm": 0.3710586428642273,
      "learning_rate": 1.0110668250923184e-05,
      "loss": 0.6008,
      "step": 32375
    },
    {
      "epoch": 0.9945627131139987,
      "grad_norm": 0.34998446702957153,
      "learning_rate": 1.0110185003053153e-05,
      "loss": 0.4335,
      "step": 32376
    },
    {
      "epoch": 0.9945934322489479,
      "grad_norm": 0.3920132517814636,
      "learning_rate": 1.010970175492578e-05,
      "loss": 0.4971,
      "step": 32377
    },
    {
      "epoch": 0.994624151383897,
      "grad_norm": 0.39042842388153076,
      "learning_rate": 1.0109218506542188e-05,
      "loss": 0.6256,
      "step": 32378
    },
    {
      "epoch": 0.9946548705188462,
      "grad_norm": 0.36674395203590393,
      "learning_rate": 1.0108735257903512e-05,
      "loss": 0.5135,
      "step": 32379
    },
    {
      "epoch": 0.9946855896537954,
      "grad_norm": 0.3584077060222626,
      "learning_rate": 1.0108252009010875e-05,
      "loss": 0.5743,
      "step": 32380
    },
    {
      "epoch": 0.9947163087887445,
      "grad_norm": 0.3683011531829834,
      "learning_rate": 1.010776875986541e-05,
      "loss": 0.4456,
      "step": 32381
    },
    {
      "epoch": 0.9947470279236936,
      "grad_norm": 0.46519792079925537,
      "learning_rate": 1.0107285510468239e-05,
      "loss": 0.5445,
      "step": 32382
    },
    {
      "epoch": 0.9947777470586429,
      "grad_norm": 0.35834458470344543,
      "learning_rate": 1.0106802260820501e-05,
      "loss": 0.6097,
      "step": 32383
    },
    {
      "epoch": 0.994808466193592,
      "grad_norm": 0.38513660430908203,
      "learning_rate": 1.0106319010923314e-05,
      "loss": 0.5077,
      "step": 32384
    },
    {
      "epoch": 0.9948391853285411,
      "grad_norm": 0.37072116136550903,
      "learning_rate": 1.0105835760777813e-05,
      "loss": 0.5453,
      "step": 32385
    },
    {
      "epoch": 0.9948699044634903,
      "grad_norm": 0.35603463649749756,
      "learning_rate": 1.0105352510385129e-05,
      "loss": 0.4514,
      "step": 32386
    },
    {
      "epoch": 0.9949006235984394,
      "grad_norm": 0.41186046600341797,
      "learning_rate": 1.0104869259746381e-05,
      "loss": 0.6218,
      "step": 32387
    },
    {
      "epoch": 0.9949313427333887,
      "grad_norm": 0.34837719798088074,
      "learning_rate": 1.0104386008862708e-05,
      "loss": 0.5582,
      "step": 32388
    },
    {
      "epoch": 0.9949620618683378,
      "grad_norm": 0.38500940799713135,
      "learning_rate": 1.0103902757735231e-05,
      "loss": 0.5241,
      "step": 32389
    },
    {
      "epoch": 0.9949927810032869,
      "grad_norm": 0.37405043840408325,
      "learning_rate": 1.0103419506365084e-05,
      "loss": 0.5014,
      "step": 32390
    },
    {
      "epoch": 0.9950235001382361,
      "grad_norm": 0.38273391127586365,
      "learning_rate": 1.0102936254753393e-05,
      "loss": 0.5276,
      "step": 32391
    },
    {
      "epoch": 0.9950542192731853,
      "grad_norm": 0.384322851896286,
      "learning_rate": 1.0102453002901286e-05,
      "loss": 0.5035,
      "step": 32392
    },
    {
      "epoch": 0.9950849384081344,
      "grad_norm": 0.42898645997047424,
      "learning_rate": 1.0101969750809892e-05,
      "loss": 0.4743,
      "step": 32393
    },
    {
      "epoch": 0.9951156575430836,
      "grad_norm": 0.3572531044483185,
      "learning_rate": 1.0101486498480344e-05,
      "loss": 0.6189,
      "step": 32394
    },
    {
      "epoch": 0.9951463766780327,
      "grad_norm": 0.40767839550971985,
      "learning_rate": 1.0101003245913765e-05,
      "loss": 0.6101,
      "step": 32395
    },
    {
      "epoch": 0.9951770958129819,
      "grad_norm": 0.3994283974170685,
      "learning_rate": 1.0100519993111283e-05,
      "loss": 0.5126,
      "step": 32396
    },
    {
      "epoch": 0.9952078149479311,
      "grad_norm": 0.3825433552265167,
      "learning_rate": 1.0100036740074035e-05,
      "loss": 0.507,
      "step": 32397
    },
    {
      "epoch": 0.9952385340828802,
      "grad_norm": 0.3844190239906311,
      "learning_rate": 1.0099553486803142e-05,
      "loss": 0.5274,
      "step": 32398
    },
    {
      "epoch": 0.9952692532178293,
      "grad_norm": 0.3535843789577484,
      "learning_rate": 1.0099070233299734e-05,
      "loss": 0.5386,
      "step": 32399
    },
    {
      "epoch": 0.9952999723527786,
      "grad_norm": 0.3935088813304901,
      "learning_rate": 1.0098586979564942e-05,
      "loss": 0.5934,
      "step": 32400
    },
    {
      "epoch": 0.9953306914877277,
      "grad_norm": 0.4787008464336395,
      "learning_rate": 1.0098103725599896e-05,
      "loss": 0.5969,
      "step": 32401
    },
    {
      "epoch": 0.9953614106226769,
      "grad_norm": 0.3460431694984436,
      "learning_rate": 1.0097620471405719e-05,
      "loss": 0.5492,
      "step": 32402
    },
    {
      "epoch": 0.995392129757626,
      "grad_norm": 0.36139318346977234,
      "learning_rate": 1.0097137216983539e-05,
      "loss": 0.6154,
      "step": 32403
    },
    {
      "epoch": 0.9954228488925752,
      "grad_norm": 0.3430153429508209,
      "learning_rate": 1.0096653962334493e-05,
      "loss": 0.5639,
      "step": 32404
    },
    {
      "epoch": 0.9954535680275244,
      "grad_norm": 0.3873125910758972,
      "learning_rate": 1.0096170707459703e-05,
      "loss": 0.6568,
      "step": 32405
    },
    {
      "epoch": 0.9954842871624735,
      "grad_norm": 0.3961176872253418,
      "learning_rate": 1.00956874523603e-05,
      "loss": 0.5472,
      "step": 32406
    },
    {
      "epoch": 0.9955150062974226,
      "grad_norm": 0.36364656686782837,
      "learning_rate": 1.0095204197037411e-05,
      "loss": 0.5641,
      "step": 32407
    },
    {
      "epoch": 0.9955457254323719,
      "grad_norm": 0.3990556299686432,
      "learning_rate": 1.0094720941492169e-05,
      "loss": 0.5113,
      "step": 32408
    },
    {
      "epoch": 0.995576444567321,
      "grad_norm": 0.38404542207717896,
      "learning_rate": 1.0094237685725696e-05,
      "loss": 0.4317,
      "step": 32409
    },
    {
      "epoch": 0.9956071637022701,
      "grad_norm": 0.3396654725074768,
      "learning_rate": 1.0093754429739127e-05,
      "loss": 0.4906,
      "step": 32410
    },
    {
      "epoch": 0.9956378828372193,
      "grad_norm": 0.38201209902763367,
      "learning_rate": 1.0093271173533586e-05,
      "loss": 0.5592,
      "step": 32411
    },
    {
      "epoch": 0.9956686019721684,
      "grad_norm": 0.3706047832965851,
      "learning_rate": 1.0092787917110204e-05,
      "loss": 0.5022,
      "step": 32412
    },
    {
      "epoch": 0.9956993211071177,
      "grad_norm": 0.4036979377269745,
      "learning_rate": 1.0092304660470111e-05,
      "loss": 0.5294,
      "step": 32413
    },
    {
      "epoch": 0.9957300402420668,
      "grad_norm": 0.3706468641757965,
      "learning_rate": 1.0091821403614433e-05,
      "loss": 0.5269,
      "step": 32414
    },
    {
      "epoch": 0.9957607593770159,
      "grad_norm": 0.37191516160964966,
      "learning_rate": 1.0091338146544301e-05,
      "loss": 0.502,
      "step": 32415
    },
    {
      "epoch": 0.9957914785119651,
      "grad_norm": 0.35566309094429016,
      "learning_rate": 1.0090854889260839e-05,
      "loss": 0.5549,
      "step": 32416
    },
    {
      "epoch": 0.9958221976469143,
      "grad_norm": 0.4321800470352173,
      "learning_rate": 1.0090371631765182e-05,
      "loss": 0.5408,
      "step": 32417
    },
    {
      "epoch": 0.9958529167818634,
      "grad_norm": 0.4263523817062378,
      "learning_rate": 1.0089888374058454e-05,
      "loss": 0.5526,
      "step": 32418
    },
    {
      "epoch": 0.9958836359168126,
      "grad_norm": 0.38331693410873413,
      "learning_rate": 1.0089405116141789e-05,
      "loss": 0.578,
      "step": 32419
    },
    {
      "epoch": 0.9959143550517617,
      "grad_norm": 0.4290127456188202,
      "learning_rate": 1.008892185801631e-05,
      "loss": 0.5626,
      "step": 32420
    },
    {
      "epoch": 0.9959450741867109,
      "grad_norm": 0.42065030336380005,
      "learning_rate": 1.0088438599683145e-05,
      "loss": 0.5539,
      "step": 32421
    },
    {
      "epoch": 0.9959757933216601,
      "grad_norm": 0.36321550607681274,
      "learning_rate": 1.008795534114343e-05,
      "loss": 0.4765,
      "step": 32422
    },
    {
      "epoch": 0.9960065124566092,
      "grad_norm": 0.3538135588169098,
      "learning_rate": 1.0087472082398284e-05,
      "loss": 0.5186,
      "step": 32423
    },
    {
      "epoch": 0.9960372315915584,
      "grad_norm": 0.34270551800727844,
      "learning_rate": 1.0086988823448847e-05,
      "loss": 0.4627,
      "step": 32424
    },
    {
      "epoch": 0.9960679507265076,
      "grad_norm": 0.3883684575557709,
      "learning_rate": 1.0086505564296236e-05,
      "loss": 0.5272,
      "step": 32425
    },
    {
      "epoch": 0.9960986698614567,
      "grad_norm": 0.34237489104270935,
      "learning_rate": 1.0086022304941586e-05,
      "loss": 0.5948,
      "step": 32426
    },
    {
      "epoch": 0.9961293889964059,
      "grad_norm": 0.3729807138442993,
      "learning_rate": 1.0085539045386028e-05,
      "loss": 0.586,
      "step": 32427
    },
    {
      "epoch": 0.996160108131355,
      "grad_norm": 0.35016974806785583,
      "learning_rate": 1.0085055785630687e-05,
      "loss": 0.4917,
      "step": 32428
    },
    {
      "epoch": 0.9961908272663041,
      "grad_norm": 0.3664548397064209,
      "learning_rate": 1.008457252567669e-05,
      "loss": 0.4638,
      "step": 32429
    },
    {
      "epoch": 0.9962215464012534,
      "grad_norm": 0.38606134057044983,
      "learning_rate": 1.008408926552517e-05,
      "loss": 0.516,
      "step": 32430
    },
    {
      "epoch": 0.9962522655362025,
      "grad_norm": 0.37199342250823975,
      "learning_rate": 1.0083606005177251e-05,
      "loss": 0.6031,
      "step": 32431
    },
    {
      "epoch": 0.9962829846711516,
      "grad_norm": 0.3366070091724396,
      "learning_rate": 1.0083122744634066e-05,
      "loss": 0.5244,
      "step": 32432
    },
    {
      "epoch": 0.9963137038061008,
      "grad_norm": 0.3925579786300659,
      "learning_rate": 1.0082639483896744e-05,
      "loss": 0.5405,
      "step": 32433
    },
    {
      "epoch": 0.99634442294105,
      "grad_norm": 0.4124689996242523,
      "learning_rate": 1.0082156222966408e-05,
      "loss": 0.5353,
      "step": 32434
    },
    {
      "epoch": 0.9963751420759991,
      "grad_norm": 0.48427584767341614,
      "learning_rate": 1.0081672961844193e-05,
      "loss": 0.4203,
      "step": 32435
    },
    {
      "epoch": 0.9964058612109483,
      "grad_norm": 0.3740990161895752,
      "learning_rate": 1.0081189700531224e-05,
      "loss": 0.5258,
      "step": 32436
    },
    {
      "epoch": 0.9964365803458974,
      "grad_norm": 0.4176744222640991,
      "learning_rate": 1.0080706439028631e-05,
      "loss": 0.5669,
      "step": 32437
    },
    {
      "epoch": 0.9964672994808467,
      "grad_norm": 0.4217855632305145,
      "learning_rate": 1.0080223177337545e-05,
      "loss": 0.4893,
      "step": 32438
    },
    {
      "epoch": 0.9964980186157958,
      "grad_norm": 0.37449654936790466,
      "learning_rate": 1.0079739915459089e-05,
      "loss": 0.5198,
      "step": 32439
    },
    {
      "epoch": 0.9965287377507449,
      "grad_norm": 0.4392707347869873,
      "learning_rate": 1.0079256653394395e-05,
      "loss": 0.5209,
      "step": 32440
    },
    {
      "epoch": 0.9965594568856941,
      "grad_norm": 0.37100523710250854,
      "learning_rate": 1.0078773391144592e-05,
      "loss": 0.5082,
      "step": 32441
    },
    {
      "epoch": 0.9965901760206433,
      "grad_norm": 0.3307364881038666,
      "learning_rate": 1.0078290128710811e-05,
      "loss": 0.5023,
      "step": 32442
    },
    {
      "epoch": 0.9966208951555924,
      "grad_norm": 0.3909124732017517,
      "learning_rate": 1.0077806866094174e-05,
      "loss": 0.6025,
      "step": 32443
    },
    {
      "epoch": 0.9966516142905416,
      "grad_norm": 0.38406646251678467,
      "learning_rate": 1.0077323603295814e-05,
      "loss": 0.4663,
      "step": 32444
    },
    {
      "epoch": 0.9966823334254907,
      "grad_norm": 0.3528292179107666,
      "learning_rate": 1.007684034031686e-05,
      "loss": 0.5366,
      "step": 32445
    },
    {
      "epoch": 0.9967130525604398,
      "grad_norm": 0.39282089471817017,
      "learning_rate": 1.0076357077158443e-05,
      "loss": 0.4606,
      "step": 32446
    },
    {
      "epoch": 0.9967437716953891,
      "grad_norm": 0.3376142084598541,
      "learning_rate": 1.0075873813821684e-05,
      "loss": 0.5782,
      "step": 32447
    },
    {
      "epoch": 0.9967744908303382,
      "grad_norm": 0.37088051438331604,
      "learning_rate": 1.007539055030772e-05,
      "loss": 0.5582,
      "step": 32448
    },
    {
      "epoch": 0.9968052099652874,
      "grad_norm": 0.33095285296440125,
      "learning_rate": 1.0074907286617672e-05,
      "loss": 0.5358,
      "step": 32449
    },
    {
      "epoch": 0.9968359291002366,
      "grad_norm": 0.5791329741477966,
      "learning_rate": 1.0074424022752676e-05,
      "loss": 0.5896,
      "step": 32450
    },
    {
      "epoch": 0.9968666482351857,
      "grad_norm": 0.40861427783966064,
      "learning_rate": 1.0073940758713858e-05,
      "loss": 0.5954,
      "step": 32451
    },
    {
      "epoch": 0.9968973673701349,
      "grad_norm": 0.4007718563079834,
      "learning_rate": 1.0073457494502343e-05,
      "loss": 0.4915,
      "step": 32452
    },
    {
      "epoch": 0.996928086505084,
      "grad_norm": 0.41804710030555725,
      "learning_rate": 1.0072974230119265e-05,
      "loss": 0.5242,
      "step": 32453
    },
    {
      "epoch": 0.9969588056400331,
      "grad_norm": 0.37709417939186096,
      "learning_rate": 1.0072490965565753e-05,
      "loss": 0.5491,
      "step": 32454
    },
    {
      "epoch": 0.9969895247749824,
      "grad_norm": 0.3823970556259155,
      "learning_rate": 1.007200770084293e-05,
      "loss": 0.6397,
      "step": 32455
    },
    {
      "epoch": 0.9970202439099315,
      "grad_norm": 0.3760110139846802,
      "learning_rate": 1.007152443595193e-05,
      "loss": 0.5314,
      "step": 32456
    },
    {
      "epoch": 0.9970509630448806,
      "grad_norm": 0.32774215936660767,
      "learning_rate": 1.0071041170893879e-05,
      "loss": 0.5118,
      "step": 32457
    },
    {
      "epoch": 0.9970816821798298,
      "grad_norm": 0.4071796238422394,
      "learning_rate": 1.0070557905669906e-05,
      "loss": 0.5618,
      "step": 32458
    },
    {
      "epoch": 0.997112401314779,
      "grad_norm": 0.3634624481201172,
      "learning_rate": 1.0070074640281139e-05,
      "loss": 0.5401,
      "step": 32459
    },
    {
      "epoch": 0.9971431204497281,
      "grad_norm": 0.4256261885166168,
      "learning_rate": 1.0069591374728709e-05,
      "loss": 0.5948,
      "step": 32460
    },
    {
      "epoch": 0.9971738395846773,
      "grad_norm": 0.37881237268447876,
      "learning_rate": 1.0069108109013743e-05,
      "loss": 0.577,
      "step": 32461
    },
    {
      "epoch": 0.9972045587196264,
      "grad_norm": 0.36442121863365173,
      "learning_rate": 1.0068624843137371e-05,
      "loss": 0.5902,
      "step": 32462
    },
    {
      "epoch": 0.9972352778545757,
      "grad_norm": 0.33963873982429504,
      "learning_rate": 1.0068141577100718e-05,
      "loss": 0.5212,
      "step": 32463
    },
    {
      "epoch": 0.9972659969895248,
      "grad_norm": 0.3513931334018707,
      "learning_rate": 1.0067658310904919e-05,
      "loss": 0.5108,
      "step": 32464
    },
    {
      "epoch": 0.9972967161244739,
      "grad_norm": 0.5843539237976074,
      "learning_rate": 1.0067175044551098e-05,
      "loss": 0.6494,
      "step": 32465
    },
    {
      "epoch": 0.9973274352594231,
      "grad_norm": 0.38987401127815247,
      "learning_rate": 1.0066691778040388e-05,
      "loss": 0.6207,
      "step": 32466
    },
    {
      "epoch": 0.9973581543943723,
      "grad_norm": 0.3788263499736786,
      "learning_rate": 1.0066208511373911e-05,
      "loss": 0.5477,
      "step": 32467
    },
    {
      "epoch": 0.9973888735293214,
      "grad_norm": 0.3795483112335205,
      "learning_rate": 1.0065725244552797e-05,
      "loss": 0.5782,
      "step": 32468
    },
    {
      "epoch": 0.9974195926642706,
      "grad_norm": 0.40256696939468384,
      "learning_rate": 1.0065241977578182e-05,
      "loss": 0.5403,
      "step": 32469
    },
    {
      "epoch": 0.9974503117992197,
      "grad_norm": 0.36141452193260193,
      "learning_rate": 1.0064758710451187e-05,
      "loss": 0.5009,
      "step": 32470
    },
    {
      "epoch": 0.9974810309341688,
      "grad_norm": 0.35513198375701904,
      "learning_rate": 1.0064275443172947e-05,
      "loss": 0.5453,
      "step": 32471
    },
    {
      "epoch": 0.9975117500691181,
      "grad_norm": 0.38908877968788147,
      "learning_rate": 1.0063792175744585e-05,
      "loss": 0.5191,
      "step": 32472
    },
    {
      "epoch": 0.9975424692040672,
      "grad_norm": 0.4156550467014313,
      "learning_rate": 1.0063308908167231e-05,
      "loss": 0.4942,
      "step": 32473
    },
    {
      "epoch": 0.9975731883390164,
      "grad_norm": 0.37242233753204346,
      "learning_rate": 1.0062825640442018e-05,
      "loss": 0.5728,
      "step": 32474
    },
    {
      "epoch": 0.9976039074739655,
      "grad_norm": 0.3724967837333679,
      "learning_rate": 1.0062342372570066e-05,
      "loss": 0.5313,
      "step": 32475
    },
    {
      "epoch": 0.9976346266089147,
      "grad_norm": 0.40584075450897217,
      "learning_rate": 1.0061859104552515e-05,
      "loss": 0.5279,
      "step": 32476
    },
    {
      "epoch": 0.9976653457438639,
      "grad_norm": 0.3794108033180237,
      "learning_rate": 1.0061375836390481e-05,
      "loss": 0.579,
      "step": 32477
    },
    {
      "epoch": 0.997696064878813,
      "grad_norm": 0.32863909006118774,
      "learning_rate": 1.0060892568085106e-05,
      "loss": 0.5105,
      "step": 32478
    },
    {
      "epoch": 0.9977267840137621,
      "grad_norm": 0.37564361095428467,
      "learning_rate": 1.0060409299637508e-05,
      "loss": 0.6054,
      "step": 32479
    },
    {
      "epoch": 0.9977575031487114,
      "grad_norm": 0.3905028998851776,
      "learning_rate": 1.005992603104882e-05,
      "loss": 0.5072,
      "step": 32480
    },
    {
      "epoch": 0.9977882222836605,
      "grad_norm": 0.4089955687522888,
      "learning_rate": 1.0059442762320173e-05,
      "loss": 0.5514,
      "step": 32481
    },
    {
      "epoch": 0.9978189414186096,
      "grad_norm": 0.3737332224845886,
      "learning_rate": 1.0058959493452692e-05,
      "loss": 0.538,
      "step": 32482
    },
    {
      "epoch": 0.9978496605535588,
      "grad_norm": 0.3682406544685364,
      "learning_rate": 1.0058476224447508e-05,
      "loss": 0.4806,
      "step": 32483
    },
    {
      "epoch": 0.997880379688508,
      "grad_norm": 0.364387184381485,
      "learning_rate": 1.0057992955305746e-05,
      "loss": 0.4947,
      "step": 32484
    },
    {
      "epoch": 0.9979110988234571,
      "grad_norm": 0.3368184268474579,
      "learning_rate": 1.0057509686028541e-05,
      "loss": 0.5281,
      "step": 32485
    },
    {
      "epoch": 0.9979418179584063,
      "grad_norm": 0.39162567257881165,
      "learning_rate": 1.0057026416617012e-05,
      "loss": 0.6104,
      "step": 32486
    },
    {
      "epoch": 0.9979725370933554,
      "grad_norm": 0.36300233006477356,
      "learning_rate": 1.00565431470723e-05,
      "loss": 0.5777,
      "step": 32487
    },
    {
      "epoch": 0.9980032562283047,
      "grad_norm": 0.4013594388961792,
      "learning_rate": 1.0056059877395524e-05,
      "loss": 0.5289,
      "step": 32488
    },
    {
      "epoch": 0.9980339753632538,
      "grad_norm": 0.4861108064651489,
      "learning_rate": 1.0055576607587817e-05,
      "loss": 0.5988,
      "step": 32489
    },
    {
      "epoch": 0.9980646944982029,
      "grad_norm": 0.3732290267944336,
      "learning_rate": 1.005509333765031e-05,
      "loss": 0.4892,
      "step": 32490
    },
    {
      "epoch": 0.9980954136331521,
      "grad_norm": 0.33701613545417786,
      "learning_rate": 1.0054610067584125e-05,
      "loss": 0.5301,
      "step": 32491
    },
    {
      "epoch": 0.9981261327681012,
      "grad_norm": 0.33877891302108765,
      "learning_rate": 1.0054126797390398e-05,
      "loss": 0.5011,
      "step": 32492
    },
    {
      "epoch": 0.9981568519030504,
      "grad_norm": 0.3493198752403259,
      "learning_rate": 1.0053643527070248e-05,
      "loss": 0.535,
      "step": 32493
    },
    {
      "epoch": 0.9981875710379996,
      "grad_norm": 0.36749008297920227,
      "learning_rate": 1.0053160256624816e-05,
      "loss": 0.4789,
      "step": 32494
    },
    {
      "epoch": 0.9982182901729487,
      "grad_norm": 0.5626538395881653,
      "learning_rate": 1.005267698605522e-05,
      "loss": 0.6395,
      "step": 32495
    },
    {
      "epoch": 0.9982490093078978,
      "grad_norm": 0.6970357298851013,
      "learning_rate": 1.0052193715362596e-05,
      "loss": 0.5199,
      "step": 32496
    },
    {
      "epoch": 0.9982797284428471,
      "grad_norm": 0.3317001163959503,
      "learning_rate": 1.0051710444548071e-05,
      "loss": 0.5811,
      "step": 32497
    },
    {
      "epoch": 0.9983104475777962,
      "grad_norm": 0.37586510181427,
      "learning_rate": 1.0051227173612772e-05,
      "loss": 0.5791,
      "step": 32498
    },
    {
      "epoch": 0.9983411667127454,
      "grad_norm": 0.34398800134658813,
      "learning_rate": 1.0050743902557825e-05,
      "loss": 0.587,
      "step": 32499
    },
    {
      "epoch": 0.9983718858476945,
      "grad_norm": 0.40245866775512695,
      "learning_rate": 1.0050260631384366e-05,
      "loss": 0.5155,
      "step": 32500
    },
    {
      "epoch": 0.9984026049826437,
      "grad_norm": 0.3699391186237335,
      "learning_rate": 1.0049777360093518e-05,
      "loss": 0.579,
      "step": 32501
    },
    {
      "epoch": 0.9984333241175929,
      "grad_norm": 0.3696046471595764,
      "learning_rate": 1.0049294088686412e-05,
      "loss": 0.5373,
      "step": 32502
    },
    {
      "epoch": 0.998464043252542,
      "grad_norm": 0.3512346148490906,
      "learning_rate": 1.0048810817164177e-05,
      "loss": 0.5826,
      "step": 32503
    },
    {
      "epoch": 0.9984947623874911,
      "grad_norm": 0.3891742527484894,
      "learning_rate": 1.0048327545527936e-05,
      "loss": 0.4912,
      "step": 32504
    },
    {
      "epoch": 0.9985254815224404,
      "grad_norm": 0.3984135091304779,
      "learning_rate": 1.0047844273778827e-05,
      "loss": 0.5756,
      "step": 32505
    },
    {
      "epoch": 0.9985562006573895,
      "grad_norm": 0.4011856019496918,
      "learning_rate": 1.0047361001917972e-05,
      "loss": 0.5849,
      "step": 32506
    },
    {
      "epoch": 0.9985869197923386,
      "grad_norm": 0.37193843722343445,
      "learning_rate": 1.0046877729946505e-05,
      "loss": 0.6057,
      "step": 32507
    },
    {
      "epoch": 0.9986176389272878,
      "grad_norm": 0.3526730537414551,
      "learning_rate": 1.0046394457865551e-05,
      "loss": 0.5215,
      "step": 32508
    },
    {
      "epoch": 0.998648358062237,
      "grad_norm": 0.37684184312820435,
      "learning_rate": 1.0045911185676239e-05,
      "loss": 0.5589,
      "step": 32509
    },
    {
      "epoch": 0.9986790771971862,
      "grad_norm": 0.3467346727848053,
      "learning_rate": 1.0045427913379699e-05,
      "loss": 0.5411,
      "step": 32510
    },
    {
      "epoch": 0.9987097963321353,
      "grad_norm": 0.34298765659332275,
      "learning_rate": 1.0044944640977056e-05,
      "loss": 0.4773,
      "step": 32511
    },
    {
      "epoch": 0.9987405154670844,
      "grad_norm": 0.3588203489780426,
      "learning_rate": 1.0044461368469447e-05,
      "loss": 0.5195,
      "step": 32512
    },
    {
      "epoch": 0.9987712346020337,
      "grad_norm": 0.43060019612312317,
      "learning_rate": 1.004397809585799e-05,
      "loss": 0.5538,
      "step": 32513
    },
    {
      "epoch": 0.9988019537369828,
      "grad_norm": 0.3878839910030365,
      "learning_rate": 1.0043494823143823e-05,
      "loss": 0.5343,
      "step": 32514
    },
    {
      "epoch": 0.9988326728719319,
      "grad_norm": 1.0451518297195435,
      "learning_rate": 1.0043011550328069e-05,
      "loss": 0.5226,
      "step": 32515
    },
    {
      "epoch": 0.9988633920068811,
      "grad_norm": 0.3813377022743225,
      "learning_rate": 1.0042528277411858e-05,
      "loss": 0.5208,
      "step": 32516
    },
    {
      "epoch": 0.9988941111418302,
      "grad_norm": 0.4254327416419983,
      "learning_rate": 1.0042045004396319e-05,
      "loss": 0.4916,
      "step": 32517
    },
    {
      "epoch": 0.9989248302767794,
      "grad_norm": 0.4600476920604706,
      "learning_rate": 1.0041561731282584e-05,
      "loss": 0.5148,
      "step": 32518
    },
    {
      "epoch": 0.9989555494117286,
      "grad_norm": 0.3873882591724396,
      "learning_rate": 1.0041078458071778e-05,
      "loss": 0.5337,
      "step": 32519
    },
    {
      "epoch": 0.9989862685466777,
      "grad_norm": 0.38077062368392944,
      "learning_rate": 1.0040595184765028e-05,
      "loss": 0.55,
      "step": 32520
    },
    {
      "epoch": 0.9990169876816268,
      "grad_norm": 0.35137856006622314,
      "learning_rate": 1.0040111911363466e-05,
      "loss": 0.5776,
      "step": 32521
    },
    {
      "epoch": 0.9990477068165761,
      "grad_norm": 0.4217524230480194,
      "learning_rate": 1.0039628637868218e-05,
      "loss": 0.5634,
      "step": 32522
    },
    {
      "epoch": 0.9990784259515252,
      "grad_norm": 0.3787831664085388,
      "learning_rate": 1.0039145364280415e-05,
      "loss": 0.5581,
      "step": 32523
    },
    {
      "epoch": 0.9991091450864744,
      "grad_norm": 0.39409372210502625,
      "learning_rate": 1.003866209060119e-05,
      "loss": 0.4703,
      "step": 32524
    },
    {
      "epoch": 0.9991398642214235,
      "grad_norm": 0.32204505801200867,
      "learning_rate": 1.003817881683166e-05,
      "loss": 0.5143,
      "step": 32525
    },
    {
      "epoch": 0.9991705833563727,
      "grad_norm": 0.48686981201171875,
      "learning_rate": 1.0037695542972968e-05,
      "loss": 0.5339,
      "step": 32526
    },
    {
      "epoch": 0.9992013024913219,
      "grad_norm": 0.3817749321460724,
      "learning_rate": 1.0037212269026231e-05,
      "loss": 0.4925,
      "step": 32527
    },
    {
      "epoch": 0.999232021626271,
      "grad_norm": 0.3339221179485321,
      "learning_rate": 1.0036728994992584e-05,
      "loss": 0.4852,
      "step": 32528
    },
    {
      "epoch": 0.9992627407612201,
      "grad_norm": 0.35329970717430115,
      "learning_rate": 1.003624572087315e-05,
      "loss": 0.5057,
      "step": 32529
    },
    {
      "epoch": 0.9992934598961694,
      "grad_norm": 0.44805610179901123,
      "learning_rate": 1.0035762446669066e-05,
      "loss": 0.5288,
      "step": 32530
    },
    {
      "epoch": 0.9993241790311185,
      "grad_norm": 0.34205448627471924,
      "learning_rate": 1.0035279172381453e-05,
      "loss": 0.5517,
      "step": 32531
    },
    {
      "epoch": 0.9993548981660676,
      "grad_norm": 0.38832250237464905,
      "learning_rate": 1.0034795898011446e-05,
      "loss": 0.5968,
      "step": 32532
    },
    {
      "epoch": 0.9993856173010168,
      "grad_norm": 0.43230727314949036,
      "learning_rate": 1.003431262356017e-05,
      "loss": 0.5221,
      "step": 32533
    },
    {
      "epoch": 0.999416336435966,
      "grad_norm": 0.3910462260246277,
      "learning_rate": 1.0033829349028753e-05,
      "loss": 0.5865,
      "step": 32534
    },
    {
      "epoch": 0.9994470555709152,
      "grad_norm": 0.3965539336204529,
      "learning_rate": 1.003334607441833e-05,
      "loss": 0.5521,
      "step": 32535
    },
    {
      "epoch": 0.9994777747058643,
      "grad_norm": 0.3760276734828949,
      "learning_rate": 1.0032862799730019e-05,
      "loss": 0.5463,
      "step": 32536
    },
    {
      "epoch": 0.9995084938408134,
      "grad_norm": 0.3505136966705322,
      "learning_rate": 1.0032379524964957e-05,
      "loss": 0.4645,
      "step": 32537
    },
    {
      "epoch": 0.9995392129757626,
      "grad_norm": 0.5779119729995728,
      "learning_rate": 1.003189625012427e-05,
      "loss": 0.4729,
      "step": 32538
    },
    {
      "epoch": 0.9995699321107118,
      "grad_norm": 0.34309831261634827,
      "learning_rate": 1.0031412975209088e-05,
      "loss": 0.4785,
      "step": 32539
    },
    {
      "epoch": 0.9996006512456609,
      "grad_norm": 0.3851175308227539,
      "learning_rate": 1.0030929700220535e-05,
      "loss": 0.5392,
      "step": 32540
    },
    {
      "epoch": 0.9996313703806101,
      "grad_norm": 0.4300593137741089,
      "learning_rate": 1.0030446425159749e-05,
      "loss": 0.5697,
      "step": 32541
    },
    {
      "epoch": 0.9996620895155592,
      "grad_norm": 0.4027702510356903,
      "learning_rate": 1.002996315002785e-05,
      "loss": 0.6206,
      "step": 32542
    },
    {
      "epoch": 0.9996928086505084,
      "grad_norm": 0.38156986236572266,
      "learning_rate": 1.0029479874825969e-05,
      "loss": 0.4936,
      "step": 32543
    },
    {
      "epoch": 0.9997235277854576,
      "grad_norm": 0.37758946418762207,
      "learning_rate": 1.0028996599555239e-05,
      "loss": 0.5532,
      "step": 32544
    },
    {
      "epoch": 0.9997542469204067,
      "grad_norm": 0.37421488761901855,
      "learning_rate": 1.0028513324216781e-05,
      "loss": 0.5692,
      "step": 32545
    },
    {
      "epoch": 0.9997849660553558,
      "grad_norm": 0.36170199513435364,
      "learning_rate": 1.0028030048811734e-05,
      "loss": 0.5119,
      "step": 32546
    },
    {
      "epoch": 0.9998156851903051,
      "grad_norm": 0.4984782934188843,
      "learning_rate": 1.0027546773341217e-05,
      "loss": 0.5847,
      "step": 32547
    },
    {
      "epoch": 0.9998464043252542,
      "grad_norm": 0.4142237901687622,
      "learning_rate": 1.0027063497806364e-05,
      "loss": 0.5426,
      "step": 32548
    },
    {
      "epoch": 0.9998771234602034,
      "grad_norm": 0.3551313579082489,
      "learning_rate": 1.00265802222083e-05,
      "loss": 0.4415,
      "step": 32549
    },
    {
      "epoch": 0.9999078425951525,
      "grad_norm": 0.3464774489402771,
      "learning_rate": 1.0026096946548158e-05,
      "loss": 0.535,
      "step": 32550
    },
    {
      "epoch": 0.9999385617301016,
      "grad_norm": 0.37426653504371643,
      "learning_rate": 1.0025613670827063e-05,
      "loss": 0.468,
      "step": 32551
    },
    {
      "epoch": 0.9999692808650509,
      "grad_norm": 0.5279443860054016,
      "learning_rate": 1.002513039504615e-05,
      "loss": 0.4935,
      "step": 32552
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.40786212682724,
      "learning_rate": 1.002464711920654e-05,
      "loss": 0.6122,
      "step": 32553
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.22940881550312042,
      "eval_runtime": 174.2855,
      "eval_samples_per_second": 137.699,
      "eval_steps_per_second": 17.213,
      "step": 32553
    },
    {
      "epoch": 1.0000307191349491,
      "grad_norm": 0.5148109793663025,
      "learning_rate": 1.0024163843309365e-05,
      "loss": 0.6148,
      "step": 32554
    },
    {
      "epoch": 1.0000614382698982,
      "grad_norm": 0.3701762855052948,
      "learning_rate": 1.0023680567355754e-05,
      "loss": 0.4805,
      "step": 32555
    },
    {
      "epoch": 1.0000921574048476,
      "grad_norm": 0.4089810252189636,
      "learning_rate": 1.0023197291346836e-05,
      "loss": 0.5977,
      "step": 32556
    },
    {
      "epoch": 1.0001228765397967,
      "grad_norm": 0.4032365679740906,
      "learning_rate": 1.0022714015283739e-05,
      "loss": 0.4662,
      "step": 32557
    },
    {
      "epoch": 1.0001535956747458,
      "grad_norm": 0.3260350823402405,
      "learning_rate": 1.0022230739167588e-05,
      "loss": 0.4783,
      "step": 32558
    },
    {
      "epoch": 1.000184314809695,
      "grad_norm": 0.36135271191596985,
      "learning_rate": 1.0021747462999518e-05,
      "loss": 0.5306,
      "step": 32559
    },
    {
      "epoch": 1.000215033944644,
      "grad_norm": 0.3487664759159088,
      "learning_rate": 1.0021264186780656e-05,
      "loss": 0.5489,
      "step": 32560
    },
    {
      "epoch": 1.0002457530795932,
      "grad_norm": 0.3715169429779053,
      "learning_rate": 1.0020780910512132e-05,
      "loss": 0.5546,
      "step": 32561
    },
    {
      "epoch": 1.0002764722145425,
      "grad_norm": 0.3706234097480774,
      "learning_rate": 1.002029763419507e-05,
      "loss": 0.557,
      "step": 32562
    },
    {
      "epoch": 1.0003071913494916,
      "grad_norm": 0.3385290503501892,
      "learning_rate": 1.0019814357830602e-05,
      "loss": 0.5168,
      "step": 32563
    },
    {
      "epoch": 1.0003379104844408,
      "grad_norm": 0.35753607749938965,
      "learning_rate": 1.0019331081419857e-05,
      "loss": 0.4761,
      "step": 32564
    },
    {
      "epoch": 1.0003686296193899,
      "grad_norm": 0.3621217906475067,
      "learning_rate": 1.001884780496396e-05,
      "loss": 0.5576,
      "step": 32565
    },
    {
      "epoch": 1.000399348754339,
      "grad_norm": 0.36256900429725647,
      "learning_rate": 1.0018364528464046e-05,
      "loss": 0.5773,
      "step": 32566
    },
    {
      "epoch": 1.0004300678892883,
      "grad_norm": 0.3934039771556854,
      "learning_rate": 1.001788125192124e-05,
      "loss": 0.5656,
      "step": 32567
    },
    {
      "epoch": 1.0004607870242375,
      "grad_norm": 0.3764078915119171,
      "learning_rate": 1.0017397975336672e-05,
      "loss": 0.6189,
      "step": 32568
    },
    {
      "epoch": 1.0004915061591866,
      "grad_norm": 0.35704895853996277,
      "learning_rate": 1.0016914698711467e-05,
      "loss": 0.4696,
      "step": 32569
    },
    {
      "epoch": 1.0005222252941357,
      "grad_norm": 0.3745637834072113,
      "learning_rate": 1.0016431422046757e-05,
      "loss": 0.5452,
      "step": 32570
    },
    {
      "epoch": 1.0005529444290848,
      "grad_norm": 0.35847288370132446,
      "learning_rate": 1.0015948145343672e-05,
      "loss": 0.5138,
      "step": 32571
    },
    {
      "epoch": 1.000583663564034,
      "grad_norm": 0.3928171694278717,
      "learning_rate": 1.0015464868603337e-05,
      "loss": 0.5544,
      "step": 32572
    },
    {
      "epoch": 1.0006143826989833,
      "grad_norm": 0.41239023208618164,
      "learning_rate": 1.0014981591826885e-05,
      "loss": 0.5352,
      "step": 32573
    },
    {
      "epoch": 1.0006451018339324,
      "grad_norm": 0.3690122067928314,
      "learning_rate": 1.001449831501544e-05,
      "loss": 0.5688,
      "step": 32574
    },
    {
      "epoch": 1.0006758209688815,
      "grad_norm": 0.4152006208896637,
      "learning_rate": 1.0014015038170136e-05,
      "loss": 0.5756,
      "step": 32575
    },
    {
      "epoch": 1.0007065401038306,
      "grad_norm": 0.330631285905838,
      "learning_rate": 1.0013531761292094e-05,
      "loss": 0.4466,
      "step": 32576
    },
    {
      "epoch": 1.0007372592387798,
      "grad_norm": 0.41816413402557373,
      "learning_rate": 1.001304848438245e-05,
      "loss": 0.5746,
      "step": 32577
    },
    {
      "epoch": 1.000767978373729,
      "grad_norm": 0.361263245344162,
      "learning_rate": 1.0012565207442333e-05,
      "loss": 0.5938,
      "step": 32578
    },
    {
      "epoch": 1.0007986975086782,
      "grad_norm": 0.3888419568538666,
      "learning_rate": 1.0012081930472865e-05,
      "loss": 0.5602,
      "step": 32579
    },
    {
      "epoch": 1.0008294166436273,
      "grad_norm": 0.40891608595848083,
      "learning_rate": 1.0011598653475182e-05,
      "loss": 0.5119,
      "step": 32580
    },
    {
      "epoch": 1.0008601357785765,
      "grad_norm": 0.3927362263202667,
      "learning_rate": 1.001111537645041e-05,
      "loss": 0.5463,
      "step": 32581
    },
    {
      "epoch": 1.0008908549135256,
      "grad_norm": 0.41910743713378906,
      "learning_rate": 1.0010632099399675e-05,
      "loss": 0.6199,
      "step": 32582
    },
    {
      "epoch": 1.0009215740484747,
      "grad_norm": 0.3433389365673065,
      "learning_rate": 1.0010148822324109e-05,
      "loss": 0.4638,
      "step": 32583
    },
    {
      "epoch": 1.000952293183424,
      "grad_norm": 0.39295998215675354,
      "learning_rate": 1.000966554522484e-05,
      "loss": 0.5546,
      "step": 32584
    },
    {
      "epoch": 1.0009830123183732,
      "grad_norm": 0.4060482978820801,
      "learning_rate": 1.0009182268102995e-05,
      "loss": 0.5389,
      "step": 32585
    },
    {
      "epoch": 1.0010137314533223,
      "grad_norm": 0.3988680839538574,
      "learning_rate": 1.0008698990959707e-05,
      "loss": 0.4847,
      "step": 32586
    },
    {
      "epoch": 1.0010444505882714,
      "grad_norm": 0.41743916273117065,
      "learning_rate": 1.00082157137961e-05,
      "loss": 0.4749,
      "step": 32587
    },
    {
      "epoch": 1.0010751697232205,
      "grad_norm": 0.3374823033809662,
      "learning_rate": 1.0007732436613304e-05,
      "loss": 0.5279,
      "step": 32588
    },
    {
      "epoch": 1.0011058888581696,
      "grad_norm": 0.3357716500759125,
      "learning_rate": 1.0007249159412448e-05,
      "loss": 0.5497,
      "step": 32589
    },
    {
      "epoch": 1.001136607993119,
      "grad_norm": 0.4363842010498047,
      "learning_rate": 1.0006765882194662e-05,
      "loss": 0.6702,
      "step": 32590
    },
    {
      "epoch": 1.001167327128068,
      "grad_norm": 0.37368839979171753,
      "learning_rate": 1.0006282604961075e-05,
      "loss": 0.5582,
      "step": 32591
    },
    {
      "epoch": 1.0011980462630172,
      "grad_norm": 0.38280197978019714,
      "learning_rate": 1.0005799327712813e-05,
      "loss": 0.5415,
      "step": 32592
    },
    {
      "epoch": 1.0012287653979663,
      "grad_norm": 0.38399213552474976,
      "learning_rate": 1.0005316050451008e-05,
      "loss": 0.4919,
      "step": 32593
    },
    {
      "epoch": 1.0012594845329155,
      "grad_norm": 0.3495531976222992,
      "learning_rate": 1.0004832773176784e-05,
      "loss": 0.5556,
      "step": 32594
    },
    {
      "epoch": 1.0012902036678648,
      "grad_norm": 0.38443154096603394,
      "learning_rate": 1.0004349495891274e-05,
      "loss": 0.5429,
      "step": 32595
    },
    {
      "epoch": 1.001320922802814,
      "grad_norm": 0.41285815834999084,
      "learning_rate": 1.0003866218595607e-05,
      "loss": 0.4512,
      "step": 32596
    },
    {
      "epoch": 1.001351641937763,
      "grad_norm": 0.38344132900238037,
      "learning_rate": 1.000338294129091e-05,
      "loss": 0.5428,
      "step": 32597
    },
    {
      "epoch": 1.0013823610727122,
      "grad_norm": 0.37139424681663513,
      "learning_rate": 1.000289966397831e-05,
      "loss": 0.4782,
      "step": 32598
    },
    {
      "epoch": 1.0014130802076613,
      "grad_norm": 0.34520694613456726,
      "learning_rate": 1.0002416386658938e-05,
      "loss": 0.5829,
      "step": 32599
    },
    {
      "epoch": 1.0014437993426104,
      "grad_norm": 0.3706777095794678,
      "learning_rate": 1.0001933109333924e-05,
      "loss": 0.4483,
      "step": 32600
    },
    {
      "epoch": 1.0014745184775597,
      "grad_norm": 0.35612040758132935,
      "learning_rate": 1.0001449832004394e-05,
      "loss": 0.464,
      "step": 32601
    },
    {
      "epoch": 1.0015052376125089,
      "grad_norm": 0.3605324923992157,
      "learning_rate": 1.0000966554671477e-05,
      "loss": 0.5376,
      "step": 32602
    },
    {
      "epoch": 1.001535956747458,
      "grad_norm": 0.5246695280075073,
      "learning_rate": 1.0000483277336304e-05,
      "loss": 0.4532,
      "step": 32603
    },
    {
      "epoch": 1.001566675882407,
      "grad_norm": 0.5594083666801453,
      "learning_rate": 1e-05,
      "loss": 0.4707,
      "step": 32604
    },
    {
      "epoch": 1.0015973950173562,
      "grad_norm": 0.41293835639953613,
      "learning_rate": 9.999516722663698e-06,
      "loss": 0.5646,
      "step": 32605
    },
    {
      "epoch": 1.0016281141523056,
      "grad_norm": 0.3904820680618286,
      "learning_rate": 9.999033445328525e-06,
      "loss": 0.5898,
      "step": 32606
    },
    {
      "epoch": 1.0016588332872547,
      "grad_norm": 0.3599005937576294,
      "learning_rate": 9.998550167995608e-06,
      "loss": 0.5287,
      "step": 32607
    },
    {
      "epoch": 1.0016895524222038,
      "grad_norm": 0.37648192048072815,
      "learning_rate": 9.99806689066608e-06,
      "loss": 0.5212,
      "step": 32608
    },
    {
      "epoch": 1.001720271557153,
      "grad_norm": 0.42770710587501526,
      "learning_rate": 9.997583613341062e-06,
      "loss": 0.5233,
      "step": 32609
    },
    {
      "epoch": 1.001750990692102,
      "grad_norm": 3.2199180126190186,
      "learning_rate": 9.997100336021693e-06,
      "loss": 0.4699,
      "step": 32610
    },
    {
      "epoch": 1.0017817098270512,
      "grad_norm": 0.4153708219528198,
      "learning_rate": 9.996617058709092e-06,
      "loss": 0.5349,
      "step": 32611
    },
    {
      "epoch": 1.0018124289620005,
      "grad_norm": 0.3781038224697113,
      "learning_rate": 9.996133781404395e-06,
      "loss": 0.5599,
      "step": 32612
    },
    {
      "epoch": 1.0018431480969496,
      "grad_norm": 0.35523122549057007,
      "learning_rate": 9.995650504108728e-06,
      "loss": 0.5378,
      "step": 32613
    },
    {
      "epoch": 1.0018738672318988,
      "grad_norm": 0.3912612795829773,
      "learning_rate": 9.995167226823218e-06,
      "loss": 0.5052,
      "step": 32614
    },
    {
      "epoch": 1.0019045863668479,
      "grad_norm": 0.4381604492664337,
      "learning_rate": 9.994683949548994e-06,
      "loss": 0.5588,
      "step": 32615
    },
    {
      "epoch": 1.001935305501797,
      "grad_norm": 0.3401263654232025,
      "learning_rate": 9.994200672287192e-06,
      "loss": 0.5313,
      "step": 32616
    },
    {
      "epoch": 1.0019660246367463,
      "grad_norm": 0.37532559037208557,
      "learning_rate": 9.993717395038926e-06,
      "loss": 0.4813,
      "step": 32617
    },
    {
      "epoch": 1.0019967437716955,
      "grad_norm": 0.3639843463897705,
      "learning_rate": 9.993234117805343e-06,
      "loss": 0.5003,
      "step": 32618
    },
    {
      "epoch": 1.0020274629066446,
      "grad_norm": 0.3743228018283844,
      "learning_rate": 9.992750840587554e-06,
      "loss": 0.519,
      "step": 32619
    },
    {
      "epoch": 1.0020581820415937,
      "grad_norm": 0.3905612826347351,
      "learning_rate": 9.992267563386701e-06,
      "loss": 0.5514,
      "step": 32620
    },
    {
      "epoch": 1.0020889011765428,
      "grad_norm": 0.41446682810783386,
      "learning_rate": 9.991784286203903e-06,
      "loss": 0.5073,
      "step": 32621
    },
    {
      "epoch": 1.002119620311492,
      "grad_norm": 0.37935784459114075,
      "learning_rate": 9.9913010090403e-06,
      "loss": 0.5619,
      "step": 32622
    },
    {
      "epoch": 1.0021503394464413,
      "grad_norm": 0.39344465732574463,
      "learning_rate": 9.990817731897008e-06,
      "loss": 0.5374,
      "step": 32623
    },
    {
      "epoch": 1.0021810585813904,
      "grad_norm": 0.3721904158592224,
      "learning_rate": 9.990334454775162e-06,
      "loss": 0.5143,
      "step": 32624
    },
    {
      "epoch": 1.0022117777163395,
      "grad_norm": 0.36972200870513916,
      "learning_rate": 9.989851177675894e-06,
      "loss": 0.4953,
      "step": 32625
    },
    {
      "epoch": 1.0022424968512886,
      "grad_norm": 0.38884437084198,
      "learning_rate": 9.989367900600325e-06,
      "loss": 0.6185,
      "step": 32626
    },
    {
      "epoch": 1.0022732159862378,
      "grad_norm": 0.35807597637176514,
      "learning_rate": 9.988884623549594e-06,
      "loss": 0.5544,
      "step": 32627
    },
    {
      "epoch": 1.002303935121187,
      "grad_norm": 0.4498979449272156,
      "learning_rate": 9.98840134652482e-06,
      "loss": 0.4935,
      "step": 32628
    },
    {
      "epoch": 1.0023346542561362,
      "grad_norm": 0.352333664894104,
      "learning_rate": 9.987918069527136e-06,
      "loss": 0.5625,
      "step": 32629
    },
    {
      "epoch": 1.0023653733910853,
      "grad_norm": 0.38953718543052673,
      "learning_rate": 9.98743479255767e-06,
      "loss": 0.5118,
      "step": 32630
    },
    {
      "epoch": 1.0023960925260345,
      "grad_norm": 0.3871571123600006,
      "learning_rate": 9.986951515617553e-06,
      "loss": 0.5643,
      "step": 32631
    },
    {
      "epoch": 1.0024268116609836,
      "grad_norm": 0.36538586020469666,
      "learning_rate": 9.986468238707909e-06,
      "loss": 0.4528,
      "step": 32632
    },
    {
      "epoch": 1.0024575307959327,
      "grad_norm": 0.3780196011066437,
      "learning_rate": 9.98598496182987e-06,
      "loss": 0.5316,
      "step": 32633
    },
    {
      "epoch": 1.002488249930882,
      "grad_norm": 0.4052516222000122,
      "learning_rate": 9.985501684984562e-06,
      "loss": 0.5277,
      "step": 32634
    },
    {
      "epoch": 1.0025189690658312,
      "grad_norm": 0.37301531434059143,
      "learning_rate": 9.98501840817312e-06,
      "loss": 0.5133,
      "step": 32635
    },
    {
      "epoch": 1.0025496882007803,
      "grad_norm": 0.5256147384643555,
      "learning_rate": 9.984535131396665e-06,
      "loss": 0.5172,
      "step": 32636
    },
    {
      "epoch": 1.0025804073357294,
      "grad_norm": 0.3471887707710266,
      "learning_rate": 9.984051854656333e-06,
      "loss": 0.5405,
      "step": 32637
    },
    {
      "epoch": 1.0026111264706785,
      "grad_norm": 0.558083713054657,
      "learning_rate": 9.983568577953246e-06,
      "loss": 0.5035,
      "step": 32638
    },
    {
      "epoch": 1.0026418456056276,
      "grad_norm": 0.3873283267021179,
      "learning_rate": 9.983085301288537e-06,
      "loss": 0.4699,
      "step": 32639
    },
    {
      "epoch": 1.002672564740577,
      "grad_norm": 0.5691986083984375,
      "learning_rate": 9.982602024663333e-06,
      "loss": 0.4599,
      "step": 32640
    },
    {
      "epoch": 1.002703283875526,
      "grad_norm": 0.4107312560081482,
      "learning_rate": 9.982118748078762e-06,
      "loss": 0.5212,
      "step": 32641
    },
    {
      "epoch": 1.0027340030104752,
      "grad_norm": 0.5922107696533203,
      "learning_rate": 9.981635471535956e-06,
      "loss": 0.4192,
      "step": 32642
    },
    {
      "epoch": 1.0027647221454243,
      "grad_norm": 0.38555508852005005,
      "learning_rate": 9.98115219503604e-06,
      "loss": 0.4861,
      "step": 32643
    },
    {
      "epoch": 1.0027954412803735,
      "grad_norm": 0.4061982333660126,
      "learning_rate": 9.980668918580147e-06,
      "loss": 0.5137,
      "step": 32644
    },
    {
      "epoch": 1.0028261604153228,
      "grad_norm": 0.36057689785957336,
      "learning_rate": 9.9801856421694e-06,
      "loss": 0.4749,
      "step": 32645
    },
    {
      "epoch": 1.002856879550272,
      "grad_norm": 0.3870537281036377,
      "learning_rate": 9.979702365804933e-06,
      "loss": 0.531,
      "step": 32646
    },
    {
      "epoch": 1.002887598685221,
      "grad_norm": 0.35866308212280273,
      "learning_rate": 9.97921908948787e-06,
      "loss": 0.4781,
      "step": 32647
    },
    {
      "epoch": 1.0029183178201702,
      "grad_norm": 0.40583130717277527,
      "learning_rate": 9.978735813219345e-06,
      "loss": 0.4752,
      "step": 32648
    },
    {
      "epoch": 1.0029490369551193,
      "grad_norm": 0.3771948218345642,
      "learning_rate": 9.978252537000482e-06,
      "loss": 0.614,
      "step": 32649
    },
    {
      "epoch": 1.0029797560900684,
      "grad_norm": 0.42282572388648987,
      "learning_rate": 9.977769260832417e-06,
      "loss": 0.4553,
      "step": 32650
    },
    {
      "epoch": 1.0030104752250177,
      "grad_norm": 0.41622114181518555,
      "learning_rate": 9.977285984716265e-06,
      "loss": 0.6261,
      "step": 32651
    },
    {
      "epoch": 1.0030411943599669,
      "grad_norm": 0.3673150837421417,
      "learning_rate": 9.97680270865317e-06,
      "loss": 0.5435,
      "step": 32652
    },
    {
      "epoch": 1.003071913494916,
      "grad_norm": 0.4090784192085266,
      "learning_rate": 9.976319432644248e-06,
      "loss": 0.5227,
      "step": 32653
    },
    {
      "epoch": 1.003102632629865,
      "grad_norm": 0.3456175625324249,
      "learning_rate": 9.97583615669064e-06,
      "loss": 0.4213,
      "step": 32654
    },
    {
      "epoch": 1.0031333517648142,
      "grad_norm": 0.36420685052871704,
      "learning_rate": 9.975352880793461e-06,
      "loss": 0.5241,
      "step": 32655
    },
    {
      "epoch": 1.0031640708997636,
      "grad_norm": 2.7728912830352783,
      "learning_rate": 9.974869604953855e-06,
      "loss": 0.4058,
      "step": 32656
    },
    {
      "epoch": 1.0031947900347127,
      "grad_norm": 0.3372522294521332,
      "learning_rate": 9.974386329172938e-06,
      "loss": 0.4855,
      "step": 32657
    },
    {
      "epoch": 1.0032255091696618,
      "grad_norm": 0.3779716193675995,
      "learning_rate": 9.973903053451846e-06,
      "loss": 0.54,
      "step": 32658
    },
    {
      "epoch": 1.003256228304611,
      "grad_norm": 0.54923015832901,
      "learning_rate": 9.973419777791702e-06,
      "loss": 0.6058,
      "step": 32659
    },
    {
      "epoch": 1.00328694743956,
      "grad_norm": 0.39127105474472046,
      "learning_rate": 9.972936502193638e-06,
      "loss": 0.5023,
      "step": 32660
    },
    {
      "epoch": 1.0033176665745092,
      "grad_norm": 0.4067184627056122,
      "learning_rate": 9.972453226658788e-06,
      "loss": 0.4876,
      "step": 32661
    },
    {
      "epoch": 1.0033483857094585,
      "grad_norm": 0.6073370575904846,
      "learning_rate": 9.971969951188268e-06,
      "loss": 0.5029,
      "step": 32662
    },
    {
      "epoch": 1.0033791048444076,
      "grad_norm": 0.47983261942863464,
      "learning_rate": 9.97148667578322e-06,
      "loss": 0.5392,
      "step": 32663
    },
    {
      "epoch": 1.0034098239793567,
      "grad_norm": 0.3729410171508789,
      "learning_rate": 9.971003400444765e-06,
      "loss": 0.4659,
      "step": 32664
    },
    {
      "epoch": 1.0034405431143059,
      "grad_norm": 0.3865799903869629,
      "learning_rate": 9.970520125174033e-06,
      "loss": 0.5319,
      "step": 32665
    },
    {
      "epoch": 1.003471262249255,
      "grad_norm": 0.38604846596717834,
      "learning_rate": 9.970036849972153e-06,
      "loss": 0.5191,
      "step": 32666
    },
    {
      "epoch": 1.0035019813842043,
      "grad_norm": 0.38352274894714355,
      "learning_rate": 9.969553574840256e-06,
      "loss": 0.5297,
      "step": 32667
    },
    {
      "epoch": 1.0035327005191534,
      "grad_norm": 0.3613898456096649,
      "learning_rate": 9.969070299779467e-06,
      "loss": 0.4697,
      "step": 32668
    },
    {
      "epoch": 1.0035634196541026,
      "grad_norm": 0.32989269495010376,
      "learning_rate": 9.968587024790917e-06,
      "loss": 0.4732,
      "step": 32669
    },
    {
      "epoch": 1.0035941387890517,
      "grad_norm": 0.39899858832359314,
      "learning_rate": 9.968103749875734e-06,
      "loss": 0.4577,
      "step": 32670
    },
    {
      "epoch": 1.0036248579240008,
      "grad_norm": 0.392948180437088,
      "learning_rate": 9.967620475035048e-06,
      "loss": 0.4549,
      "step": 32671
    },
    {
      "epoch": 1.00365557705895,
      "grad_norm": 0.610389232635498,
      "learning_rate": 9.967137200269984e-06,
      "loss": 0.4983,
      "step": 32672
    },
    {
      "epoch": 1.0036862961938993,
      "grad_norm": 0.40537503361701965,
      "learning_rate": 9.966653925581676e-06,
      "loss": 0.5024,
      "step": 32673
    },
    {
      "epoch": 1.0037170153288484,
      "grad_norm": 0.4250895082950592,
      "learning_rate": 9.966170650971248e-06,
      "loss": 0.4976,
      "step": 32674
    },
    {
      "epoch": 1.0037477344637975,
      "grad_norm": 0.41828182339668274,
      "learning_rate": 9.965687376439834e-06,
      "loss": 0.5436,
      "step": 32675
    },
    {
      "epoch": 1.0037784535987466,
      "grad_norm": 0.4322506785392761,
      "learning_rate": 9.965204101988555e-06,
      "loss": 0.5948,
      "step": 32676
    },
    {
      "epoch": 1.0038091727336957,
      "grad_norm": 0.3681655526161194,
      "learning_rate": 9.964720827618547e-06,
      "loss": 0.4429,
      "step": 32677
    },
    {
      "epoch": 1.003839891868645,
      "grad_norm": 0.3768291175365448,
      "learning_rate": 9.964237553330937e-06,
      "loss": 0.5544,
      "step": 32678
    },
    {
      "epoch": 1.0038706110035942,
      "grad_norm": 0.45700666308403015,
      "learning_rate": 9.96375427912685e-06,
      "loss": 0.5236,
      "step": 32679
    },
    {
      "epoch": 1.0039013301385433,
      "grad_norm": 0.38427111506462097,
      "learning_rate": 9.96327100500742e-06,
      "loss": 0.4862,
      "step": 32680
    },
    {
      "epoch": 1.0039320492734924,
      "grad_norm": 0.3875623941421509,
      "learning_rate": 9.96278773097377e-06,
      "loss": 0.5407,
      "step": 32681
    },
    {
      "epoch": 1.0039627684084416,
      "grad_norm": 0.3668755888938904,
      "learning_rate": 9.962304457027035e-06,
      "loss": 0.4836,
      "step": 32682
    },
    {
      "epoch": 1.0039934875433907,
      "grad_norm": 0.3930204212665558,
      "learning_rate": 9.961821183168338e-06,
      "loss": 0.5071,
      "step": 32683
    },
    {
      "epoch": 1.00402420667834,
      "grad_norm": 0.3498730957508087,
      "learning_rate": 9.961337909398814e-06,
      "loss": 0.5145,
      "step": 32684
    },
    {
      "epoch": 1.0040549258132891,
      "grad_norm": 0.3984212577342987,
      "learning_rate": 9.960854635719585e-06,
      "loss": 0.5258,
      "step": 32685
    },
    {
      "epoch": 1.0040856449482383,
      "grad_norm": 0.4741820991039276,
      "learning_rate": 9.960371362131785e-06,
      "loss": 0.5287,
      "step": 32686
    },
    {
      "epoch": 1.0041163640831874,
      "grad_norm": 0.38268911838531494,
      "learning_rate": 9.959888088636536e-06,
      "loss": 0.485,
      "step": 32687
    },
    {
      "epoch": 1.0041470832181365,
      "grad_norm": 0.3886541724205017,
      "learning_rate": 9.959404815234977e-06,
      "loss": 0.4949,
      "step": 32688
    },
    {
      "epoch": 1.0041778023530858,
      "grad_norm": 0.3953627049922943,
      "learning_rate": 9.958921541928227e-06,
      "loss": 0.5058,
      "step": 32689
    },
    {
      "epoch": 1.004208521488035,
      "grad_norm": 0.38980183005332947,
      "learning_rate": 9.958438268717421e-06,
      "loss": 0.5645,
      "step": 32690
    },
    {
      "epoch": 1.004239240622984,
      "grad_norm": 0.4632399380207062,
      "learning_rate": 9.957954995603683e-06,
      "loss": 0.5575,
      "step": 32691
    },
    {
      "epoch": 1.0042699597579332,
      "grad_norm": 0.37755364179611206,
      "learning_rate": 9.957471722588145e-06,
      "loss": 0.5348,
      "step": 32692
    },
    {
      "epoch": 1.0043006788928823,
      "grad_norm": 0.3884478211402893,
      "learning_rate": 9.956988449671935e-06,
      "loss": 0.5268,
      "step": 32693
    },
    {
      "epoch": 1.0043313980278314,
      "grad_norm": 0.36840692162513733,
      "learning_rate": 9.956505176856182e-06,
      "loss": 0.4838,
      "step": 32694
    },
    {
      "epoch": 1.0043621171627808,
      "grad_norm": 0.4006490409374237,
      "learning_rate": 9.956021904142013e-06,
      "loss": 0.5242,
      "step": 32695
    },
    {
      "epoch": 1.00439283629773,
      "grad_norm": 0.3858742117881775,
      "learning_rate": 9.955538631530554e-06,
      "loss": 0.5287,
      "step": 32696
    },
    {
      "epoch": 1.004423555432679,
      "grad_norm": 0.4044870436191559,
      "learning_rate": 9.955055359022945e-06,
      "loss": 0.5122,
      "step": 32697
    },
    {
      "epoch": 1.0044542745676281,
      "grad_norm": 0.39190706610679626,
      "learning_rate": 9.954572086620303e-06,
      "loss": 0.5236,
      "step": 32698
    },
    {
      "epoch": 1.0044849937025773,
      "grad_norm": 0.3950536251068115,
      "learning_rate": 9.954088814323763e-06,
      "loss": 0.4597,
      "step": 32699
    },
    {
      "epoch": 1.0045157128375264,
      "grad_norm": 0.35394957661628723,
      "learning_rate": 9.953605542134452e-06,
      "loss": 0.5005,
      "step": 32700
    },
    {
      "epoch": 1.0045464319724757,
      "grad_norm": 0.4085291922092438,
      "learning_rate": 9.953122270053499e-06,
      "loss": 0.5301,
      "step": 32701
    },
    {
      "epoch": 1.0045771511074248,
      "grad_norm": 0.3757326304912567,
      "learning_rate": 9.952638998082028e-06,
      "loss": 0.5608,
      "step": 32702
    },
    {
      "epoch": 1.004607870242374,
      "grad_norm": 0.40034738183021545,
      "learning_rate": 9.952155726221175e-06,
      "loss": 0.5731,
      "step": 32703
    },
    {
      "epoch": 1.004638589377323,
      "grad_norm": 0.40862688422203064,
      "learning_rate": 9.951672454472065e-06,
      "loss": 0.4351,
      "step": 32704
    },
    {
      "epoch": 1.0046693085122722,
      "grad_norm": 0.4040968716144562,
      "learning_rate": 9.951189182835828e-06,
      "loss": 0.5662,
      "step": 32705
    },
    {
      "epoch": 1.0047000276472215,
      "grad_norm": 0.40996813774108887,
      "learning_rate": 9.950705911313591e-06,
      "loss": 0.5436,
      "step": 32706
    },
    {
      "epoch": 1.0047307467821707,
      "grad_norm": 0.36960434913635254,
      "learning_rate": 9.950222639906487e-06,
      "loss": 0.4261,
      "step": 32707
    },
    {
      "epoch": 1.0047614659171198,
      "grad_norm": 0.3644545078277588,
      "learning_rate": 9.949739368615637e-06,
      "loss": 0.4437,
      "step": 32708
    },
    {
      "epoch": 1.004792185052069,
      "grad_norm": 0.38703203201293945,
      "learning_rate": 9.949256097442178e-06,
      "loss": 0.5343,
      "step": 32709
    },
    {
      "epoch": 1.004822904187018,
      "grad_norm": 0.37498363852500916,
      "learning_rate": 9.948772826387231e-06,
      "loss": 0.4868,
      "step": 32710
    },
    {
      "epoch": 1.0048536233219671,
      "grad_norm": 0.3847171664237976,
      "learning_rate": 9.948289555451934e-06,
      "loss": 0.5161,
      "step": 32711
    },
    {
      "epoch": 1.0048843424569165,
      "grad_norm": 0.4522654712200165,
      "learning_rate": 9.947806284637405e-06,
      "loss": 0.5189,
      "step": 32712
    },
    {
      "epoch": 1.0049150615918656,
      "grad_norm": 0.391937255859375,
      "learning_rate": 9.947323013944785e-06,
      "loss": 0.5022,
      "step": 32713
    },
    {
      "epoch": 1.0049457807268147,
      "grad_norm": 0.42140769958496094,
      "learning_rate": 9.946839743375186e-06,
      "loss": 0.4473,
      "step": 32714
    },
    {
      "epoch": 1.0049764998617639,
      "grad_norm": 0.3896947205066681,
      "learning_rate": 9.946356472929751e-06,
      "loss": 0.5914,
      "step": 32715
    },
    {
      "epoch": 1.005007218996713,
      "grad_norm": 0.3819447159767151,
      "learning_rate": 9.945873202609605e-06,
      "loss": 0.5422,
      "step": 32716
    },
    {
      "epoch": 1.0050379381316623,
      "grad_norm": 0.3791516125202179,
      "learning_rate": 9.945389932415875e-06,
      "loss": 0.5764,
      "step": 32717
    },
    {
      "epoch": 1.0050686572666114,
      "grad_norm": 0.34468206763267517,
      "learning_rate": 9.944906662349693e-06,
      "loss": 0.5191,
      "step": 32718
    },
    {
      "epoch": 1.0050993764015606,
      "grad_norm": 0.424236923456192,
      "learning_rate": 9.944423392412183e-06,
      "loss": 0.4996,
      "step": 32719
    },
    {
      "epoch": 1.0051300955365097,
      "grad_norm": 0.3880615830421448,
      "learning_rate": 9.94394012260448e-06,
      "loss": 0.5796,
      "step": 32720
    },
    {
      "epoch": 1.0051608146714588,
      "grad_norm": 0.42282751202583313,
      "learning_rate": 9.9434568529277e-06,
      "loss": 0.4467,
      "step": 32721
    },
    {
      "epoch": 1.005191533806408,
      "grad_norm": 0.3878312110900879,
      "learning_rate": 9.942973583382991e-06,
      "loss": 0.4842,
      "step": 32722
    },
    {
      "epoch": 1.0052222529413573,
      "grad_norm": 0.36390772461891174,
      "learning_rate": 9.942490313971462e-06,
      "loss": 0.5845,
      "step": 32723
    },
    {
      "epoch": 1.0052529720763064,
      "grad_norm": 0.3881320655345917,
      "learning_rate": 9.942007044694259e-06,
      "loss": 0.5002,
      "step": 32724
    },
    {
      "epoch": 1.0052836912112555,
      "grad_norm": 0.4386211633682251,
      "learning_rate": 9.941523775552495e-06,
      "loss": 0.5353,
      "step": 32725
    },
    {
      "epoch": 1.0053144103462046,
      "grad_norm": 0.34361332654953003,
      "learning_rate": 9.941040506547313e-06,
      "loss": 0.5534,
      "step": 32726
    },
    {
      "epoch": 1.0053451294811537,
      "grad_norm": 0.46456989645957947,
      "learning_rate": 9.94055723767983e-06,
      "loss": 0.4887,
      "step": 32727
    },
    {
      "epoch": 1.005375848616103,
      "grad_norm": 0.42000269889831543,
      "learning_rate": 9.940073968951184e-06,
      "loss": 0.5675,
      "step": 32728
    },
    {
      "epoch": 1.0054065677510522,
      "grad_norm": 0.38026875257492065,
      "learning_rate": 9.939590700362496e-06,
      "loss": 0.4846,
      "step": 32729
    },
    {
      "epoch": 1.0054372868860013,
      "grad_norm": 0.4041139483451843,
      "learning_rate": 9.939107431914899e-06,
      "loss": 0.5475,
      "step": 32730
    },
    {
      "epoch": 1.0054680060209504,
      "grad_norm": 0.40596431493759155,
      "learning_rate": 9.93862416360952e-06,
      "loss": 0.4801,
      "step": 32731
    },
    {
      "epoch": 1.0054987251558996,
      "grad_norm": 0.37796714901924133,
      "learning_rate": 9.938140895447489e-06,
      "loss": 0.4253,
      "step": 32732
    },
    {
      "epoch": 1.0055294442908487,
      "grad_norm": 0.3504583537578583,
      "learning_rate": 9.937657627429936e-06,
      "loss": 0.4692,
      "step": 32733
    },
    {
      "epoch": 1.005560163425798,
      "grad_norm": 0.4023998975753784,
      "learning_rate": 9.937174359557986e-06,
      "loss": 0.4878,
      "step": 32734
    },
    {
      "epoch": 1.0055908825607471,
      "grad_norm": 0.4767884612083435,
      "learning_rate": 9.936691091832772e-06,
      "loss": 0.5495,
      "step": 32735
    },
    {
      "epoch": 1.0056216016956963,
      "grad_norm": 0.3867833614349365,
      "learning_rate": 9.936207824255417e-06,
      "loss": 0.488,
      "step": 32736
    },
    {
      "epoch": 1.0056523208306454,
      "grad_norm": 0.41855478286743164,
      "learning_rate": 9.935724556827057e-06,
      "loss": 0.4987,
      "step": 32737
    },
    {
      "epoch": 1.0056830399655945,
      "grad_norm": 1.1361759901046753,
      "learning_rate": 9.935241289548812e-06,
      "loss": 0.4126,
      "step": 32738
    },
    {
      "epoch": 1.0057137591005438,
      "grad_norm": 0.3457736372947693,
      "learning_rate": 9.93475802242182e-06,
      "loss": 0.5341,
      "step": 32739
    },
    {
      "epoch": 1.005744478235493,
      "grad_norm": 0.3732454776763916,
      "learning_rate": 9.934274755447203e-06,
      "loss": 0.5335,
      "step": 32740
    },
    {
      "epoch": 1.005775197370442,
      "grad_norm": 0.40368178486824036,
      "learning_rate": 9.933791488626094e-06,
      "loss": 0.5079,
      "step": 32741
    },
    {
      "epoch": 1.0058059165053912,
      "grad_norm": 0.3589126169681549,
      "learning_rate": 9.933308221959616e-06,
      "loss": 0.4857,
      "step": 32742
    },
    {
      "epoch": 1.0058366356403403,
      "grad_norm": 0.34269025921821594,
      "learning_rate": 9.932824955448904e-06,
      "loss": 0.4448,
      "step": 32743
    },
    {
      "epoch": 1.0058673547752894,
      "grad_norm": 0.4177064895629883,
      "learning_rate": 9.932341689095083e-06,
      "loss": 0.608,
      "step": 32744
    },
    {
      "epoch": 1.0058980739102388,
      "grad_norm": 0.3678257167339325,
      "learning_rate": 9.931858422899284e-06,
      "loss": 0.4568,
      "step": 32745
    },
    {
      "epoch": 1.005928793045188,
      "grad_norm": 0.3486933410167694,
      "learning_rate": 9.931375156862632e-06,
      "loss": 0.5876,
      "step": 32746
    },
    {
      "epoch": 1.005959512180137,
      "grad_norm": 0.3849911391735077,
      "learning_rate": 9.93089189098626e-06,
      "loss": 0.4806,
      "step": 32747
    },
    {
      "epoch": 1.0059902313150861,
      "grad_norm": 0.34340953826904297,
      "learning_rate": 9.930408625271295e-06,
      "loss": 0.5395,
      "step": 32748
    },
    {
      "epoch": 1.0060209504500353,
      "grad_norm": 0.3905690908432007,
      "learning_rate": 9.929925359718866e-06,
      "loss": 0.609,
      "step": 32749
    },
    {
      "epoch": 1.0060516695849846,
      "grad_norm": 0.3507601022720337,
      "learning_rate": 9.929442094330097e-06,
      "loss": 0.5606,
      "step": 32750
    },
    {
      "epoch": 1.0060823887199337,
      "grad_norm": 0.3990689218044281,
      "learning_rate": 9.928958829106123e-06,
      "loss": 0.5649,
      "step": 32751
    },
    {
      "epoch": 1.0061131078548828,
      "grad_norm": 0.34876322746276855,
      "learning_rate": 9.928475564048072e-06,
      "loss": 0.4587,
      "step": 32752
    },
    {
      "epoch": 1.006143826989832,
      "grad_norm": 0.4050522744655609,
      "learning_rate": 9.92799229915707e-06,
      "loss": 0.4893,
      "step": 32753
    },
    {
      "epoch": 1.006174546124781,
      "grad_norm": 0.3833911716938019,
      "learning_rate": 9.92750903443425e-06,
      "loss": 0.4174,
      "step": 32754
    },
    {
      "epoch": 1.0062052652597302,
      "grad_norm": 0.3814592659473419,
      "learning_rate": 9.927025769880734e-06,
      "loss": 0.5901,
      "step": 32755
    },
    {
      "epoch": 1.0062359843946795,
      "grad_norm": 0.38361892104148865,
      "learning_rate": 9.926542505497659e-06,
      "loss": 0.4854,
      "step": 32756
    },
    {
      "epoch": 1.0062667035296287,
      "grad_norm": 0.37025028467178345,
      "learning_rate": 9.926059241286143e-06,
      "loss": 0.4437,
      "step": 32757
    },
    {
      "epoch": 1.0062974226645778,
      "grad_norm": 0.3608899712562561,
      "learning_rate": 9.925575977247328e-06,
      "loss": 0.4914,
      "step": 32758
    },
    {
      "epoch": 1.006328141799527,
      "grad_norm": 0.37347444891929626,
      "learning_rate": 9.925092713382328e-06,
      "loss": 0.4577,
      "step": 32759
    },
    {
      "epoch": 1.006358860934476,
      "grad_norm": 0.3394983112812042,
      "learning_rate": 9.924609449692285e-06,
      "loss": 0.4454,
      "step": 32760
    },
    {
      "epoch": 1.0063895800694251,
      "grad_norm": 0.35877135396003723,
      "learning_rate": 9.92412618617832e-06,
      "loss": 0.4871,
      "step": 32761
    },
    {
      "epoch": 1.0064202992043745,
      "grad_norm": 0.46552586555480957,
      "learning_rate": 9.923642922841563e-06,
      "loss": 0.4741,
      "step": 32762
    },
    {
      "epoch": 1.0064510183393236,
      "grad_norm": 0.3636157512664795,
      "learning_rate": 9.923159659683142e-06,
      "loss": 0.4845,
      "step": 32763
    },
    {
      "epoch": 1.0064817374742727,
      "grad_norm": 0.411462664604187,
      "learning_rate": 9.92267639670419e-06,
      "loss": 0.5652,
      "step": 32764
    },
    {
      "epoch": 1.0065124566092218,
      "grad_norm": 0.4795480966567993,
      "learning_rate": 9.92219313390583e-06,
      "loss": 0.5211,
      "step": 32765
    },
    {
      "epoch": 1.006543175744171,
      "grad_norm": 0.3872503340244293,
      "learning_rate": 9.921709871289196e-06,
      "loss": 0.5103,
      "step": 32766
    },
    {
      "epoch": 1.0065738948791203,
      "grad_norm": 0.3933071494102478,
      "learning_rate": 9.921226608855411e-06,
      "loss": 0.6593,
      "step": 32767
    },
    {
      "epoch": 1.0066046140140694,
      "grad_norm": 0.40475398302078247,
      "learning_rate": 9.920743346605608e-06,
      "loss": 0.474,
      "step": 32768
    },
    {
      "epoch": 1.0066353331490185,
      "grad_norm": 0.3813355565071106,
      "learning_rate": 9.920260084540915e-06,
      "loss": 0.4994,
      "step": 32769
    },
    {
      "epoch": 1.0066660522839677,
      "grad_norm": 0.36581265926361084,
      "learning_rate": 9.919776822662458e-06,
      "loss": 0.448,
      "step": 32770
    },
    {
      "epoch": 1.0066967714189168,
      "grad_norm": 0.399530827999115,
      "learning_rate": 9.919293560971372e-06,
      "loss": 0.5236,
      "step": 32771
    },
    {
      "epoch": 1.006727490553866,
      "grad_norm": 0.395354688167572,
      "learning_rate": 9.918810299468778e-06,
      "loss": 0.4862,
      "step": 32772
    },
    {
      "epoch": 1.0067582096888152,
      "grad_norm": 0.3425847589969635,
      "learning_rate": 9.918327038155809e-06,
      "loss": 0.5493,
      "step": 32773
    },
    {
      "epoch": 1.0067889288237644,
      "grad_norm": 0.37312352657318115,
      "learning_rate": 9.917843777033592e-06,
      "loss": 0.59,
      "step": 32774
    },
    {
      "epoch": 1.0068196479587135,
      "grad_norm": 0.3538384735584259,
      "learning_rate": 9.91736051610326e-06,
      "loss": 0.508,
      "step": 32775
    },
    {
      "epoch": 1.0068503670936626,
      "grad_norm": 0.39995306730270386,
      "learning_rate": 9.916877255365936e-06,
      "loss": 0.5468,
      "step": 32776
    },
    {
      "epoch": 1.0068810862286117,
      "grad_norm": 0.41640815138816833,
      "learning_rate": 9.91639399482275e-06,
      "loss": 0.5229,
      "step": 32777
    },
    {
      "epoch": 1.006911805363561,
      "grad_norm": 0.39894425868988037,
      "learning_rate": 9.915910734474834e-06,
      "loss": 0.4538,
      "step": 32778
    },
    {
      "epoch": 1.0069425244985102,
      "grad_norm": 0.37993377447128296,
      "learning_rate": 9.915427474323314e-06,
      "loss": 0.5377,
      "step": 32779
    },
    {
      "epoch": 1.0069732436334593,
      "grad_norm": 0.38996800780296326,
      "learning_rate": 9.914944214369317e-06,
      "loss": 0.5581,
      "step": 32780
    },
    {
      "epoch": 1.0070039627684084,
      "grad_norm": 0.3348594903945923,
      "learning_rate": 9.914460954613975e-06,
      "loss": 0.4596,
      "step": 32781
    },
    {
      "epoch": 1.0070346819033575,
      "grad_norm": 0.34515586495399475,
      "learning_rate": 9.913977695058415e-06,
      "loss": 0.4653,
      "step": 32782
    },
    {
      "epoch": 1.0070654010383067,
      "grad_norm": 0.3744787871837616,
      "learning_rate": 9.91349443570377e-06,
      "loss": 0.5205,
      "step": 32783
    },
    {
      "epoch": 1.007096120173256,
      "grad_norm": 0.4083184003829956,
      "learning_rate": 9.913011176551156e-06,
      "loss": 0.5327,
      "step": 32784
    },
    {
      "epoch": 1.0071268393082051,
      "grad_norm": 0.3502887785434723,
      "learning_rate": 9.912527917601721e-06,
      "loss": 0.4923,
      "step": 32785
    },
    {
      "epoch": 1.0071575584431542,
      "grad_norm": 0.4163268208503723,
      "learning_rate": 9.912044658856575e-06,
      "loss": 0.5106,
      "step": 32786
    },
    {
      "epoch": 1.0071882775781034,
      "grad_norm": 0.36322689056396484,
      "learning_rate": 9.911561400316856e-06,
      "loss": 0.5037,
      "step": 32787
    },
    {
      "epoch": 1.0072189967130525,
      "grad_norm": 0.40282946825027466,
      "learning_rate": 9.911078141983695e-06,
      "loss": 0.5366,
      "step": 32788
    },
    {
      "epoch": 1.0072497158480018,
      "grad_norm": 0.35856887698173523,
      "learning_rate": 9.910594883858213e-06,
      "loss": 0.4675,
      "step": 32789
    },
    {
      "epoch": 1.007280434982951,
      "grad_norm": 0.43073001503944397,
      "learning_rate": 9.91011162594155e-06,
      "loss": 0.5133,
      "step": 32790
    },
    {
      "epoch": 1.0073111541179,
      "grad_norm": 0.41018423438072205,
      "learning_rate": 9.909628368234818e-06,
      "loss": 0.4997,
      "step": 32791
    },
    {
      "epoch": 1.0073418732528492,
      "grad_norm": 0.3739328980445862,
      "learning_rate": 9.909145110739164e-06,
      "loss": 0.4959,
      "step": 32792
    },
    {
      "epoch": 1.0073725923877983,
      "grad_norm": 0.34942662715911865,
      "learning_rate": 9.9086618534557e-06,
      "loss": 0.4878,
      "step": 32793
    },
    {
      "epoch": 1.0074033115227474,
      "grad_norm": 0.3852868378162384,
      "learning_rate": 9.908178596385572e-06,
      "loss": 0.4985,
      "step": 32794
    },
    {
      "epoch": 1.0074340306576968,
      "grad_norm": 0.38682425022125244,
      "learning_rate": 9.907695339529889e-06,
      "loss": 0.5545,
      "step": 32795
    },
    {
      "epoch": 1.0074647497926459,
      "grad_norm": 0.3806912302970886,
      "learning_rate": 9.907212082889799e-06,
      "loss": 0.5551,
      "step": 32796
    },
    {
      "epoch": 1.007495468927595,
      "grad_norm": 0.38440611958503723,
      "learning_rate": 9.906728826466416e-06,
      "loss": 0.4754,
      "step": 32797
    },
    {
      "epoch": 1.0075261880625441,
      "grad_norm": 0.4788365066051483,
      "learning_rate": 9.906245570260878e-06,
      "loss": 0.5729,
      "step": 32798
    },
    {
      "epoch": 1.0075569071974932,
      "grad_norm": 0.39585018157958984,
      "learning_rate": 9.905762314274306e-06,
      "loss": 0.5546,
      "step": 32799
    },
    {
      "epoch": 1.0075876263324426,
      "grad_norm": 0.41963672637939453,
      "learning_rate": 9.905279058507836e-06,
      "loss": 0.5443,
      "step": 32800
    },
    {
      "epoch": 1.0076183454673917,
      "grad_norm": 0.5367075204849243,
      "learning_rate": 9.90479580296259e-06,
      "loss": 0.4881,
      "step": 32801
    },
    {
      "epoch": 1.0076490646023408,
      "grad_norm": 0.4867176115512848,
      "learning_rate": 9.904312547639705e-06,
      "loss": 0.4886,
      "step": 32802
    },
    {
      "epoch": 1.00767978373729,
      "grad_norm": 0.40529176592826843,
      "learning_rate": 9.9038292925403e-06,
      "loss": 0.513,
      "step": 32803
    },
    {
      "epoch": 1.007710502872239,
      "grad_norm": 0.36009806394577026,
      "learning_rate": 9.903346037665512e-06,
      "loss": 0.476,
      "step": 32804
    },
    {
      "epoch": 1.0077412220071882,
      "grad_norm": 0.4058191180229187,
      "learning_rate": 9.902862783016463e-06,
      "loss": 0.569,
      "step": 32805
    },
    {
      "epoch": 1.0077719411421375,
      "grad_norm": 0.6346049904823303,
      "learning_rate": 9.902379528594285e-06,
      "loss": 0.5056,
      "step": 32806
    },
    {
      "epoch": 1.0078026602770866,
      "grad_norm": 0.38908976316452026,
      "learning_rate": 9.90189627440011e-06,
      "loss": 0.4499,
      "step": 32807
    },
    {
      "epoch": 1.0078333794120358,
      "grad_norm": 0.39955779910087585,
      "learning_rate": 9.901413020435058e-06,
      "loss": 0.5119,
      "step": 32808
    },
    {
      "epoch": 1.0078640985469849,
      "grad_norm": 0.3928951323032379,
      "learning_rate": 9.900929766700268e-06,
      "loss": 0.5154,
      "step": 32809
    },
    {
      "epoch": 1.007894817681934,
      "grad_norm": 0.36997511982917786,
      "learning_rate": 9.900446513196858e-06,
      "loss": 0.4131,
      "step": 32810
    },
    {
      "epoch": 1.0079255368168831,
      "grad_norm": 0.3491601049900055,
      "learning_rate": 9.899963259925967e-06,
      "loss": 0.5131,
      "step": 32811
    },
    {
      "epoch": 1.0079562559518325,
      "grad_norm": 0.6993468403816223,
      "learning_rate": 9.899480006888715e-06,
      "loss": 0.5652,
      "step": 32812
    },
    {
      "epoch": 1.0079869750867816,
      "grad_norm": 0.3704208433628082,
      "learning_rate": 9.898996754086237e-06,
      "loss": 0.4847,
      "step": 32813
    },
    {
      "epoch": 1.0080176942217307,
      "grad_norm": 0.3711683452129364,
      "learning_rate": 9.898513501519659e-06,
      "loss": 0.5897,
      "step": 32814
    },
    {
      "epoch": 1.0080484133566798,
      "grad_norm": 0.3540146052837372,
      "learning_rate": 9.89803024919011e-06,
      "loss": 0.4687,
      "step": 32815
    },
    {
      "epoch": 1.008079132491629,
      "grad_norm": 0.3735237419605255,
      "learning_rate": 9.897546997098716e-06,
      "loss": 0.5892,
      "step": 32816
    },
    {
      "epoch": 1.0081098516265783,
      "grad_norm": 0.36127179861068726,
      "learning_rate": 9.897063745246612e-06,
      "loss": 0.5275,
      "step": 32817
    },
    {
      "epoch": 1.0081405707615274,
      "grad_norm": 0.3890076279640198,
      "learning_rate": 9.896580493634918e-06,
      "loss": 0.5368,
      "step": 32818
    },
    {
      "epoch": 1.0081712898964765,
      "grad_norm": 0.370189905166626,
      "learning_rate": 9.896097242264774e-06,
      "loss": 0.5597,
      "step": 32819
    },
    {
      "epoch": 1.0082020090314256,
      "grad_norm": 0.3958148956298828,
      "learning_rate": 9.895613991137295e-06,
      "loss": 0.5435,
      "step": 32820
    },
    {
      "epoch": 1.0082327281663748,
      "grad_norm": 0.3820945620536804,
      "learning_rate": 9.895130740253624e-06,
      "loss": 0.5056,
      "step": 32821
    },
    {
      "epoch": 1.008263447301324,
      "grad_norm": 0.5288700461387634,
      "learning_rate": 9.894647489614875e-06,
      "loss": 0.6078,
      "step": 32822
    },
    {
      "epoch": 1.0082941664362732,
      "grad_norm": 0.45065417885780334,
      "learning_rate": 9.894164239222187e-06,
      "loss": 0.5625,
      "step": 32823
    },
    {
      "epoch": 1.0083248855712224,
      "grad_norm": 0.47693440318107605,
      "learning_rate": 9.89368098907669e-06,
      "loss": 0.4379,
      "step": 32824
    },
    {
      "epoch": 1.0083556047061715,
      "grad_norm": 0.39214518666267395,
      "learning_rate": 9.8931977391795e-06,
      "loss": 0.5385,
      "step": 32825
    },
    {
      "epoch": 1.0083863238411206,
      "grad_norm": 0.4065020680427551,
      "learning_rate": 9.892714489531763e-06,
      "loss": 0.4832,
      "step": 32826
    },
    {
      "epoch": 1.0084170429760697,
      "grad_norm": 0.4829716086387634,
      "learning_rate": 9.892231240134592e-06,
      "loss": 0.5544,
      "step": 32827
    },
    {
      "epoch": 1.008447762111019,
      "grad_norm": 0.40117236971855164,
      "learning_rate": 9.891747990989128e-06,
      "loss": 0.4909,
      "step": 32828
    },
    {
      "epoch": 1.0084784812459682,
      "grad_norm": 0.35912221670150757,
      "learning_rate": 9.89126474209649e-06,
      "loss": 0.532,
      "step": 32829
    },
    {
      "epoch": 1.0085092003809173,
      "grad_norm": 0.3762132525444031,
      "learning_rate": 9.890781493457814e-06,
      "loss": 0.5014,
      "step": 32830
    },
    {
      "epoch": 1.0085399195158664,
      "grad_norm": 0.40955668687820435,
      "learning_rate": 9.890298245074223e-06,
      "loss": 0.4128,
      "step": 32831
    },
    {
      "epoch": 1.0085706386508155,
      "grad_norm": 0.7371493577957153,
      "learning_rate": 9.88981499694685e-06,
      "loss": 0.4918,
      "step": 32832
    },
    {
      "epoch": 1.0086013577857647,
      "grad_norm": 0.49353688955307007,
      "learning_rate": 9.88933174907682e-06,
      "loss": 0.5085,
      "step": 32833
    },
    {
      "epoch": 1.008632076920714,
      "grad_norm": 0.3859722912311554,
      "learning_rate": 9.888848501465264e-06,
      "loss": 0.5264,
      "step": 32834
    },
    {
      "epoch": 1.0086627960556631,
      "grad_norm": 0.3914693593978882,
      "learning_rate": 9.88836525411331e-06,
      "loss": 0.5135,
      "step": 32835
    },
    {
      "epoch": 1.0086935151906122,
      "grad_norm": 0.36429303884506226,
      "learning_rate": 9.887882007022088e-06,
      "loss": 0.5393,
      "step": 32836
    },
    {
      "epoch": 1.0087242343255614,
      "grad_norm": 0.4380199909210205,
      "learning_rate": 9.887398760192723e-06,
      "loss": 0.4876,
      "step": 32837
    },
    {
      "epoch": 1.0087549534605105,
      "grad_norm": 0.38015589118003845,
      "learning_rate": 9.886915513626349e-06,
      "loss": 0.4364,
      "step": 32838
    },
    {
      "epoch": 1.0087856725954598,
      "grad_norm": 0.4340798258781433,
      "learning_rate": 9.88643226732409e-06,
      "loss": 0.4652,
      "step": 32839
    },
    {
      "epoch": 1.008816391730409,
      "grad_norm": 0.39500531554222107,
      "learning_rate": 9.885949021287075e-06,
      "loss": 0.4579,
      "step": 32840
    },
    {
      "epoch": 1.008847110865358,
      "grad_norm": 0.33055680990219116,
      "learning_rate": 9.885465775516436e-06,
      "loss": 0.4476,
      "step": 32841
    },
    {
      "epoch": 1.0088778300003072,
      "grad_norm": 0.38374757766723633,
      "learning_rate": 9.884982530013298e-06,
      "loss": 0.5725,
      "step": 32842
    },
    {
      "epoch": 1.0089085491352563,
      "grad_norm": 0.41787755489349365,
      "learning_rate": 9.884499284778793e-06,
      "loss": 0.4989,
      "step": 32843
    },
    {
      "epoch": 1.0089392682702054,
      "grad_norm": 0.41062062978744507,
      "learning_rate": 9.884016039814046e-06,
      "loss": 0.461,
      "step": 32844
    },
    {
      "epoch": 1.0089699874051548,
      "grad_norm": 0.3727319538593292,
      "learning_rate": 9.88353279512019e-06,
      "loss": 0.467,
      "step": 32845
    },
    {
      "epoch": 1.0090007065401039,
      "grad_norm": 0.421633780002594,
      "learning_rate": 9.883049550698351e-06,
      "loss": 0.5616,
      "step": 32846
    },
    {
      "epoch": 1.009031425675053,
      "grad_norm": 0.3753231465816498,
      "learning_rate": 9.882566306549656e-06,
      "loss": 0.4867,
      "step": 32847
    },
    {
      "epoch": 1.0090621448100021,
      "grad_norm": 0.38756805658340454,
      "learning_rate": 9.882083062675237e-06,
      "loss": 0.4768,
      "step": 32848
    },
    {
      "epoch": 1.0090928639449512,
      "grad_norm": 0.36857959628105164,
      "learning_rate": 9.881599819076223e-06,
      "loss": 0.4958,
      "step": 32849
    },
    {
      "epoch": 1.0091235830799006,
      "grad_norm": 0.3566691279411316,
      "learning_rate": 9.881116575753737e-06,
      "loss": 0.4817,
      "step": 32850
    },
    {
      "epoch": 1.0091543022148497,
      "grad_norm": 0.3557654917240143,
      "learning_rate": 9.880633332708916e-06,
      "loss": 0.5086,
      "step": 32851
    },
    {
      "epoch": 1.0091850213497988,
      "grad_norm": 0.36676186323165894,
      "learning_rate": 9.88015008994288e-06,
      "loss": 0.5505,
      "step": 32852
    },
    {
      "epoch": 1.009215740484748,
      "grad_norm": 0.47424134612083435,
      "learning_rate": 9.879666847456767e-06,
      "loss": 0.4688,
      "step": 32853
    },
    {
      "epoch": 1.009246459619697,
      "grad_norm": 0.3941843509674072,
      "learning_rate": 9.879183605251694e-06,
      "loss": 0.5263,
      "step": 32854
    },
    {
      "epoch": 1.0092771787546462,
      "grad_norm": 0.394702672958374,
      "learning_rate": 9.878700363328802e-06,
      "loss": 0.5047,
      "step": 32855
    },
    {
      "epoch": 1.0093078978895955,
      "grad_norm": 0.3790525197982788,
      "learning_rate": 9.878217121689208e-06,
      "loss": 0.4573,
      "step": 32856
    },
    {
      "epoch": 1.0093386170245446,
      "grad_norm": 0.4025374948978424,
      "learning_rate": 9.877733880334053e-06,
      "loss": 0.4641,
      "step": 32857
    },
    {
      "epoch": 1.0093693361594938,
      "grad_norm": 0.3475354313850403,
      "learning_rate": 9.877250639264452e-06,
      "loss": 0.5174,
      "step": 32858
    },
    {
      "epoch": 1.0094000552944429,
      "grad_norm": 0.38087335228919983,
      "learning_rate": 9.876767398481547e-06,
      "loss": 0.5285,
      "step": 32859
    },
    {
      "epoch": 1.009430774429392,
      "grad_norm": 0.38217270374298096,
      "learning_rate": 9.876284157986456e-06,
      "loss": 0.4982,
      "step": 32860
    },
    {
      "epoch": 1.0094614935643413,
      "grad_norm": 0.3896544277667999,
      "learning_rate": 9.875800917780312e-06,
      "loss": 0.5059,
      "step": 32861
    },
    {
      "epoch": 1.0094922126992905,
      "grad_norm": 0.39057865738868713,
      "learning_rate": 9.875317677864249e-06,
      "loss": 0.5194,
      "step": 32862
    },
    {
      "epoch": 1.0095229318342396,
      "grad_norm": 0.35399171710014343,
      "learning_rate": 9.87483443823938e-06,
      "loss": 0.5076,
      "step": 32863
    },
    {
      "epoch": 1.0095536509691887,
      "grad_norm": 0.3630847632884979,
      "learning_rate": 9.874351198906856e-06,
      "loss": 0.4204,
      "step": 32864
    },
    {
      "epoch": 1.0095843701041378,
      "grad_norm": 0.3579263389110565,
      "learning_rate": 9.873867959867787e-06,
      "loss": 0.5044,
      "step": 32865
    },
    {
      "epoch": 1.009615089239087,
      "grad_norm": 0.36521172523498535,
      "learning_rate": 9.87338472112331e-06,
      "loss": 0.5007,
      "step": 32866
    },
    {
      "epoch": 1.0096458083740363,
      "grad_norm": 0.7718433737754822,
      "learning_rate": 9.87290148267455e-06,
      "loss": 0.5217,
      "step": 32867
    },
    {
      "epoch": 1.0096765275089854,
      "grad_norm": 0.3482256531715393,
      "learning_rate": 9.87241824452264e-06,
      "loss": 0.4602,
      "step": 32868
    },
    {
      "epoch": 1.0097072466439345,
      "grad_norm": 0.4102220833301544,
      "learning_rate": 9.871935006668702e-06,
      "loss": 0.5004,
      "step": 32869
    },
    {
      "epoch": 1.0097379657788836,
      "grad_norm": 0.3777606785297394,
      "learning_rate": 9.871451769113873e-06,
      "loss": 0.5614,
      "step": 32870
    },
    {
      "epoch": 1.0097686849138328,
      "grad_norm": 0.4061432480812073,
      "learning_rate": 9.870968531859274e-06,
      "loss": 0.4688,
      "step": 32871
    },
    {
      "epoch": 1.0097994040487819,
      "grad_norm": 0.3810344934463501,
      "learning_rate": 9.870485294906039e-06,
      "loss": 0.4783,
      "step": 32872
    },
    {
      "epoch": 1.0098301231837312,
      "grad_norm": 0.36641639471054077,
      "learning_rate": 9.870002058255293e-06,
      "loss": 0.4935,
      "step": 32873
    },
    {
      "epoch": 1.0098608423186803,
      "grad_norm": 0.39395207166671753,
      "learning_rate": 9.86951882190817e-06,
      "loss": 0.5511,
      "step": 32874
    },
    {
      "epoch": 1.0098915614536295,
      "grad_norm": 0.4649188816547394,
      "learning_rate": 9.86903558586579e-06,
      "loss": 0.5389,
      "step": 32875
    },
    {
      "epoch": 1.0099222805885786,
      "grad_norm": 0.3871077597141266,
      "learning_rate": 9.868552350129291e-06,
      "loss": 0.5035,
      "step": 32876
    },
    {
      "epoch": 1.0099529997235277,
      "grad_norm": 0.35584327578544617,
      "learning_rate": 9.868069114699794e-06,
      "loss": 0.4741,
      "step": 32877
    },
    {
      "epoch": 1.009983718858477,
      "grad_norm": 0.4330346882343292,
      "learning_rate": 9.86758587957843e-06,
      "loss": 0.4634,
      "step": 32878
    },
    {
      "epoch": 1.0100144379934262,
      "grad_norm": 0.42824921011924744,
      "learning_rate": 9.867102644766333e-06,
      "loss": 0.5088,
      "step": 32879
    },
    {
      "epoch": 1.0100451571283753,
      "grad_norm": 0.3893076479434967,
      "learning_rate": 9.866619410264623e-06,
      "loss": 0.5512,
      "step": 32880
    },
    {
      "epoch": 1.0100758762633244,
      "grad_norm": 1.11764395236969,
      "learning_rate": 9.866136176074435e-06,
      "loss": 0.4942,
      "step": 32881
    },
    {
      "epoch": 1.0101065953982735,
      "grad_norm": 0.40109044313430786,
      "learning_rate": 9.865652942196892e-06,
      "loss": 0.4899,
      "step": 32882
    },
    {
      "epoch": 1.0101373145332226,
      "grad_norm": 0.3689500689506531,
      "learning_rate": 9.86516970863313e-06,
      "loss": 0.4946,
      "step": 32883
    },
    {
      "epoch": 1.010168033668172,
      "grad_norm": 0.37535160779953003,
      "learning_rate": 9.86468647538427e-06,
      "loss": 0.4727,
      "step": 32884
    },
    {
      "epoch": 1.010198752803121,
      "grad_norm": 0.37754130363464355,
      "learning_rate": 9.864203242451447e-06,
      "loss": 0.4565,
      "step": 32885
    },
    {
      "epoch": 1.0102294719380702,
      "grad_norm": 0.40139663219451904,
      "learning_rate": 9.863720009835785e-06,
      "loss": 0.5369,
      "step": 32886
    },
    {
      "epoch": 1.0102601910730193,
      "grad_norm": 0.3496739864349365,
      "learning_rate": 9.86323677753842e-06,
      "loss": 0.4916,
      "step": 32887
    },
    {
      "epoch": 1.0102909102079685,
      "grad_norm": 0.3899213969707489,
      "learning_rate": 9.862753545560467e-06,
      "loss": 0.5142,
      "step": 32888
    },
    {
      "epoch": 1.0103216293429178,
      "grad_norm": 0.3624113202095032,
      "learning_rate": 9.86227031390307e-06,
      "loss": 0.4857,
      "step": 32889
    },
    {
      "epoch": 1.010352348477867,
      "grad_norm": 0.4010041058063507,
      "learning_rate": 9.861787082567342e-06,
      "loss": 0.5501,
      "step": 32890
    },
    {
      "epoch": 1.010383067612816,
      "grad_norm": 0.5425707101821899,
      "learning_rate": 9.861303851554428e-06,
      "loss": 0.5252,
      "step": 32891
    },
    {
      "epoch": 1.0104137867477652,
      "grad_norm": 0.3899436593055725,
      "learning_rate": 9.860820620865442e-06,
      "loss": 0.5531,
      "step": 32892
    },
    {
      "epoch": 1.0104445058827143,
      "grad_norm": 0.3750813901424408,
      "learning_rate": 9.860337390501524e-06,
      "loss": 0.4514,
      "step": 32893
    },
    {
      "epoch": 1.0104752250176634,
      "grad_norm": 0.40571659803390503,
      "learning_rate": 9.859854160463795e-06,
      "loss": 0.5138,
      "step": 32894
    },
    {
      "epoch": 1.0105059441526127,
      "grad_norm": 0.37185370922088623,
      "learning_rate": 9.859370930753388e-06,
      "loss": 0.5316,
      "step": 32895
    },
    {
      "epoch": 1.0105366632875619,
      "grad_norm": 0.6760997176170349,
      "learning_rate": 9.858887701371428e-06,
      "loss": 0.5249,
      "step": 32896
    },
    {
      "epoch": 1.010567382422511,
      "grad_norm": 0.4189296066761017,
      "learning_rate": 9.858404472319044e-06,
      "loss": 0.5099,
      "step": 32897
    },
    {
      "epoch": 1.01059810155746,
      "grad_norm": 0.34702610969543457,
      "learning_rate": 9.857921243597372e-06,
      "loss": 0.4833,
      "step": 32898
    },
    {
      "epoch": 1.0106288206924092,
      "grad_norm": 0.5389624834060669,
      "learning_rate": 9.857438015207528e-06,
      "loss": 0.5721,
      "step": 32899
    },
    {
      "epoch": 1.0106595398273586,
      "grad_norm": 0.40181806683540344,
      "learning_rate": 9.856954787150655e-06,
      "loss": 0.5379,
      "step": 32900
    },
    {
      "epoch": 1.0106902589623077,
      "grad_norm": 0.4404603838920593,
      "learning_rate": 9.85647155942787e-06,
      "loss": 0.5482,
      "step": 32901
    },
    {
      "epoch": 1.0107209780972568,
      "grad_norm": 0.3793824017047882,
      "learning_rate": 9.855988332040308e-06,
      "loss": 0.6016,
      "step": 32902
    },
    {
      "epoch": 1.010751697232206,
      "grad_norm": 0.3860757350921631,
      "learning_rate": 9.855505104989091e-06,
      "loss": 0.5387,
      "step": 32903
    },
    {
      "epoch": 1.010782416367155,
      "grad_norm": 0.3575514554977417,
      "learning_rate": 9.855021878275356e-06,
      "loss": 0.4396,
      "step": 32904
    },
    {
      "epoch": 1.0108131355021042,
      "grad_norm": 0.37821099162101746,
      "learning_rate": 9.854538651900225e-06,
      "loss": 0.4851,
      "step": 32905
    },
    {
      "epoch": 1.0108438546370535,
      "grad_norm": 0.3919218182563782,
      "learning_rate": 9.854055425864831e-06,
      "loss": 0.4722,
      "step": 32906
    },
    {
      "epoch": 1.0108745737720026,
      "grad_norm": 0.3716832399368286,
      "learning_rate": 9.853572200170298e-06,
      "loss": 0.5073,
      "step": 32907
    },
    {
      "epoch": 1.0109052929069517,
      "grad_norm": 0.4356287717819214,
      "learning_rate": 9.85308897481776e-06,
      "loss": 0.542,
      "step": 32908
    },
    {
      "epoch": 1.0109360120419009,
      "grad_norm": 0.40322527289390564,
      "learning_rate": 9.852605749808342e-06,
      "loss": 0.5636,
      "step": 32909
    },
    {
      "epoch": 1.01096673117685,
      "grad_norm": 0.3667672872543335,
      "learning_rate": 9.852122525143175e-06,
      "loss": 0.553,
      "step": 32910
    },
    {
      "epoch": 1.0109974503117993,
      "grad_norm": 0.36807188391685486,
      "learning_rate": 9.851639300823384e-06,
      "loss": 0.4761,
      "step": 32911
    },
    {
      "epoch": 1.0110281694467484,
      "grad_norm": 0.4482726454734802,
      "learning_rate": 9.851156076850101e-06,
      "loss": 0.5335,
      "step": 32912
    },
    {
      "epoch": 1.0110588885816976,
      "grad_norm": 0.3635595440864563,
      "learning_rate": 9.850672853224452e-06,
      "loss": 0.5178,
      "step": 32913
    },
    {
      "epoch": 1.0110896077166467,
      "grad_norm": 0.34914931654930115,
      "learning_rate": 9.850189629947569e-06,
      "loss": 0.4389,
      "step": 32914
    },
    {
      "epoch": 1.0111203268515958,
      "grad_norm": 0.3572879731655121,
      "learning_rate": 9.849706407020576e-06,
      "loss": 0.4984,
      "step": 32915
    },
    {
      "epoch": 1.011151045986545,
      "grad_norm": 0.3567501902580261,
      "learning_rate": 9.849223184444606e-06,
      "loss": 0.5011,
      "step": 32916
    },
    {
      "epoch": 1.0111817651214943,
      "grad_norm": 0.38151314854621887,
      "learning_rate": 9.848739962220786e-06,
      "loss": 0.5535,
      "step": 32917
    },
    {
      "epoch": 1.0112124842564434,
      "grad_norm": 0.40681034326553345,
      "learning_rate": 9.848256740350243e-06,
      "loss": 0.5237,
      "step": 32918
    },
    {
      "epoch": 1.0112432033913925,
      "grad_norm": 0.39356425404548645,
      "learning_rate": 9.847773518834108e-06,
      "loss": 0.5665,
      "step": 32919
    },
    {
      "epoch": 1.0112739225263416,
      "grad_norm": 0.36809590458869934,
      "learning_rate": 9.847290297673508e-06,
      "loss": 0.5055,
      "step": 32920
    },
    {
      "epoch": 1.0113046416612907,
      "grad_norm": 0.3620111346244812,
      "learning_rate": 9.846807076869573e-06,
      "loss": 0.4367,
      "step": 32921
    },
    {
      "epoch": 1.0113353607962399,
      "grad_norm": 0.35414984822273254,
      "learning_rate": 9.84632385642343e-06,
      "loss": 0.4495,
      "step": 32922
    },
    {
      "epoch": 1.0113660799311892,
      "grad_norm": 0.3629875183105469,
      "learning_rate": 9.845840636336213e-06,
      "loss": 0.4811,
      "step": 32923
    },
    {
      "epoch": 1.0113967990661383,
      "grad_norm": 0.3845130503177643,
      "learning_rate": 9.845357416609036e-06,
      "loss": 0.5221,
      "step": 32924
    },
    {
      "epoch": 1.0114275182010874,
      "grad_norm": 0.3842809200286865,
      "learning_rate": 9.844874197243048e-06,
      "loss": 0.477,
      "step": 32925
    },
    {
      "epoch": 1.0114582373360366,
      "grad_norm": 0.4098057150840759,
      "learning_rate": 9.844390978239358e-06,
      "loss": 0.4989,
      "step": 32926
    },
    {
      "epoch": 1.0114889564709857,
      "grad_norm": 0.41833701729774475,
      "learning_rate": 9.843907759599113e-06,
      "loss": 0.5233,
      "step": 32927
    },
    {
      "epoch": 1.011519675605935,
      "grad_norm": 0.3455463945865631,
      "learning_rate": 9.843424541323426e-06,
      "loss": 0.5189,
      "step": 32928
    },
    {
      "epoch": 1.0115503947408842,
      "grad_norm": 0.4624841511249542,
      "learning_rate": 9.842941323413435e-06,
      "loss": 0.4824,
      "step": 32929
    },
    {
      "epoch": 1.0115811138758333,
      "grad_norm": 0.4494243264198303,
      "learning_rate": 9.842458105870261e-06,
      "loss": 0.5007,
      "step": 32930
    },
    {
      "epoch": 1.0116118330107824,
      "grad_norm": 0.37080323696136475,
      "learning_rate": 9.841974888695043e-06,
      "loss": 0.4999,
      "step": 32931
    },
    {
      "epoch": 1.0116425521457315,
      "grad_norm": 0.40637651085853577,
      "learning_rate": 9.841491671888898e-06,
      "loss": 0.4471,
      "step": 32932
    },
    {
      "epoch": 1.0116732712806806,
      "grad_norm": 0.41511276364326477,
      "learning_rate": 9.841008455452961e-06,
      "loss": 0.4829,
      "step": 32933
    },
    {
      "epoch": 1.01170399041563,
      "grad_norm": 0.370098352432251,
      "learning_rate": 9.840525239388364e-06,
      "loss": 0.5607,
      "step": 32934
    },
    {
      "epoch": 1.011734709550579,
      "grad_norm": 0.407024621963501,
      "learning_rate": 9.840042023696228e-06,
      "loss": 0.4784,
      "step": 32935
    },
    {
      "epoch": 1.0117654286855282,
      "grad_norm": 0.3493209481239319,
      "learning_rate": 9.839558808377689e-06,
      "loss": 0.4783,
      "step": 32936
    },
    {
      "epoch": 1.0117961478204773,
      "grad_norm": 0.3590095043182373,
      "learning_rate": 9.839075593433867e-06,
      "loss": 0.4961,
      "step": 32937
    },
    {
      "epoch": 1.0118268669554265,
      "grad_norm": 0.45229724049568176,
      "learning_rate": 9.838592378865898e-06,
      "loss": 0.5004,
      "step": 32938
    },
    {
      "epoch": 1.0118575860903758,
      "grad_norm": 0.3685888648033142,
      "learning_rate": 9.838109164674905e-06,
      "loss": 0.514,
      "step": 32939
    },
    {
      "epoch": 1.011888305225325,
      "grad_norm": 0.3836098611354828,
      "learning_rate": 9.837625950862023e-06,
      "loss": 0.4955,
      "step": 32940
    },
    {
      "epoch": 1.011919024360274,
      "grad_norm": 0.43548789620399475,
      "learning_rate": 9.837142737428374e-06,
      "loss": 0.5236,
      "step": 32941
    },
    {
      "epoch": 1.0119497434952232,
      "grad_norm": 0.42528805136680603,
      "learning_rate": 9.836659524375092e-06,
      "loss": 0.5603,
      "step": 32942
    },
    {
      "epoch": 1.0119804626301723,
      "grad_norm": 0.36393991112709045,
      "learning_rate": 9.8361763117033e-06,
      "loss": 0.4858,
      "step": 32943
    },
    {
      "epoch": 1.0120111817651214,
      "grad_norm": 0.6257643103599548,
      "learning_rate": 9.835693099414133e-06,
      "loss": 0.5129,
      "step": 32944
    },
    {
      "epoch": 1.0120419009000707,
      "grad_norm": 0.37687215209007263,
      "learning_rate": 9.835209887508715e-06,
      "loss": 0.5146,
      "step": 32945
    },
    {
      "epoch": 1.0120726200350199,
      "grad_norm": 0.3706906735897064,
      "learning_rate": 9.834726675988176e-06,
      "loss": 0.5563,
      "step": 32946
    },
    {
      "epoch": 1.012103339169969,
      "grad_norm": 0.3946026563644409,
      "learning_rate": 9.834243464853642e-06,
      "loss": 0.4993,
      "step": 32947
    },
    {
      "epoch": 1.012134058304918,
      "grad_norm": 0.3557297885417938,
      "learning_rate": 9.833760254106247e-06,
      "loss": 0.5152,
      "step": 32948
    },
    {
      "epoch": 1.0121647774398672,
      "grad_norm": 0.3617187440395355,
      "learning_rate": 9.833277043747115e-06,
      "loss": 0.5054,
      "step": 32949
    },
    {
      "epoch": 1.0121954965748166,
      "grad_norm": 0.402484267950058,
      "learning_rate": 9.832793833777379e-06,
      "loss": 0.5458,
      "step": 32950
    },
    {
      "epoch": 1.0122262157097657,
      "grad_norm": 0.39019519090652466,
      "learning_rate": 9.832310624198159e-06,
      "loss": 0.5447,
      "step": 32951
    },
    {
      "epoch": 1.0122569348447148,
      "grad_norm": 0.4090404808521271,
      "learning_rate": 9.831827415010591e-06,
      "loss": 0.5263,
      "step": 32952
    },
    {
      "epoch": 1.012287653979664,
      "grad_norm": 0.3893854022026062,
      "learning_rate": 9.831344206215804e-06,
      "loss": 0.5287,
      "step": 32953
    },
    {
      "epoch": 1.012318373114613,
      "grad_norm": 0.37014055252075195,
      "learning_rate": 9.830860997814922e-06,
      "loss": 0.4607,
      "step": 32954
    },
    {
      "epoch": 1.0123490922495622,
      "grad_norm": 0.3762637674808502,
      "learning_rate": 9.83037778980908e-06,
      "loss": 0.4989,
      "step": 32955
    },
    {
      "epoch": 1.0123798113845115,
      "grad_norm": 0.42397215962409973,
      "learning_rate": 9.829894582199398e-06,
      "loss": 0.4773,
      "step": 32956
    },
    {
      "epoch": 1.0124105305194606,
      "grad_norm": 0.32370641827583313,
      "learning_rate": 9.829411374987016e-06,
      "loss": 0.4675,
      "step": 32957
    },
    {
      "epoch": 1.0124412496544097,
      "grad_norm": 0.3835422098636627,
      "learning_rate": 9.828928168173047e-06,
      "loss": 0.5648,
      "step": 32958
    },
    {
      "epoch": 1.0124719687893589,
      "grad_norm": 0.3957692086696625,
      "learning_rate": 9.828444961758635e-06,
      "loss": 0.5476,
      "step": 32959
    },
    {
      "epoch": 1.012502687924308,
      "grad_norm": 0.35222887992858887,
      "learning_rate": 9.827961755744896e-06,
      "loss": 0.5142,
      "step": 32960
    },
    {
      "epoch": 1.0125334070592573,
      "grad_norm": 0.4590506851673126,
      "learning_rate": 9.82747855013297e-06,
      "loss": 0.5349,
      "step": 32961
    },
    {
      "epoch": 1.0125641261942064,
      "grad_norm": 0.3678765892982483,
      "learning_rate": 9.826995344923973e-06,
      "loss": 0.5594,
      "step": 32962
    },
    {
      "epoch": 1.0125948453291556,
      "grad_norm": 0.44144588708877563,
      "learning_rate": 9.826512140119049e-06,
      "loss": 0.5377,
      "step": 32963
    },
    {
      "epoch": 1.0126255644641047,
      "grad_norm": 0.4044701159000397,
      "learning_rate": 9.826028935719311e-06,
      "loss": 0.4558,
      "step": 32964
    },
    {
      "epoch": 1.0126562835990538,
      "grad_norm": 0.4599136710166931,
      "learning_rate": 9.825545731725899e-06,
      "loss": 0.5126,
      "step": 32965
    },
    {
      "epoch": 1.012687002734003,
      "grad_norm": 0.3848772943019867,
      "learning_rate": 9.825062528139933e-06,
      "loss": 0.5017,
      "step": 32966
    },
    {
      "epoch": 1.0127177218689523,
      "grad_norm": 0.36079302430152893,
      "learning_rate": 9.82457932496255e-06,
      "loss": 0.4625,
      "step": 32967
    },
    {
      "epoch": 1.0127484410039014,
      "grad_norm": 0.3475266993045807,
      "learning_rate": 9.82409612219487e-06,
      "loss": 0.4775,
      "step": 32968
    },
    {
      "epoch": 1.0127791601388505,
      "grad_norm": 0.4079134166240692,
      "learning_rate": 9.823612919838028e-06,
      "loss": 0.4536,
      "step": 32969
    },
    {
      "epoch": 1.0128098792737996,
      "grad_norm": 0.40552833676338196,
      "learning_rate": 9.82312971789315e-06,
      "loss": 0.5364,
      "step": 32970
    },
    {
      "epoch": 1.0128405984087487,
      "grad_norm": 0.39265674352645874,
      "learning_rate": 9.822646516361365e-06,
      "loss": 0.5666,
      "step": 32971
    },
    {
      "epoch": 1.012871317543698,
      "grad_norm": 0.3756729066371918,
      "learning_rate": 9.822163315243802e-06,
      "loss": 0.5405,
      "step": 32972
    },
    {
      "epoch": 1.0129020366786472,
      "grad_norm": 0.3838230073451996,
      "learning_rate": 9.821680114541589e-06,
      "loss": 0.4238,
      "step": 32973
    },
    {
      "epoch": 1.0129327558135963,
      "grad_norm": 0.35656002163887024,
      "learning_rate": 9.821196914255854e-06,
      "loss": 0.4803,
      "step": 32974
    },
    {
      "epoch": 1.0129634749485454,
      "grad_norm": 0.3701077103614807,
      "learning_rate": 9.820713714387724e-06,
      "loss": 0.5248,
      "step": 32975
    },
    {
      "epoch": 1.0129941940834946,
      "grad_norm": 0.3990524411201477,
      "learning_rate": 9.820230514938335e-06,
      "loss": 0.4754,
      "step": 32976
    },
    {
      "epoch": 1.0130249132184437,
      "grad_norm": 0.3807086646556854,
      "learning_rate": 9.819747315908805e-06,
      "loss": 0.483,
      "step": 32977
    },
    {
      "epoch": 1.013055632353393,
      "grad_norm": 0.3753092288970947,
      "learning_rate": 9.819264117300271e-06,
      "loss": 0.4223,
      "step": 32978
    },
    {
      "epoch": 1.0130863514883421,
      "grad_norm": 0.6612868905067444,
      "learning_rate": 9.818780919113855e-06,
      "loss": 0.568,
      "step": 32979
    },
    {
      "epoch": 1.0131170706232913,
      "grad_norm": 0.39104941487312317,
      "learning_rate": 9.818297721350694e-06,
      "loss": 0.5835,
      "step": 32980
    },
    {
      "epoch": 1.0131477897582404,
      "grad_norm": 0.397728830575943,
      "learning_rate": 9.817814524011906e-06,
      "loss": 0.5233,
      "step": 32981
    },
    {
      "epoch": 1.0131785088931895,
      "grad_norm": 0.7249870300292969,
      "learning_rate": 9.81733132709863e-06,
      "loss": 0.5837,
      "step": 32982
    },
    {
      "epoch": 1.0132092280281386,
      "grad_norm": 0.38113534450531006,
      "learning_rate": 9.816848130611984e-06,
      "loss": 0.5134,
      "step": 32983
    },
    {
      "epoch": 1.013239947163088,
      "grad_norm": 0.3446594774723053,
      "learning_rate": 9.816364934553107e-06,
      "loss": 0.5333,
      "step": 32984
    },
    {
      "epoch": 1.013270666298037,
      "grad_norm": 0.3857303261756897,
      "learning_rate": 9.815881738923117e-06,
      "loss": 0.5243,
      "step": 32985
    },
    {
      "epoch": 1.0133013854329862,
      "grad_norm": 0.3935571610927582,
      "learning_rate": 9.815398543723156e-06,
      "loss": 0.5097,
      "step": 32986
    },
    {
      "epoch": 1.0133321045679353,
      "grad_norm": 0.35491082072257996,
      "learning_rate": 9.814915348954336e-06,
      "loss": 0.4744,
      "step": 32987
    },
    {
      "epoch": 1.0133628237028844,
      "grad_norm": 0.3844335973262787,
      "learning_rate": 9.814432154617797e-06,
      "loss": 0.4951,
      "step": 32988
    },
    {
      "epoch": 1.0133935428378338,
      "grad_norm": 0.38466379046440125,
      "learning_rate": 9.813948960714666e-06,
      "loss": 0.4743,
      "step": 32989
    },
    {
      "epoch": 1.013424261972783,
      "grad_norm": 0.3810184895992279,
      "learning_rate": 9.813465767246068e-06,
      "loss": 0.5372,
      "step": 32990
    },
    {
      "epoch": 1.013454981107732,
      "grad_norm": 0.4312475025653839,
      "learning_rate": 9.812982574213138e-06,
      "loss": 0.4645,
      "step": 32991
    },
    {
      "epoch": 1.0134857002426811,
      "grad_norm": 0.3521716892719269,
      "learning_rate": 9.812499381616995e-06,
      "loss": 0.546,
      "step": 32992
    },
    {
      "epoch": 1.0135164193776303,
      "grad_norm": 0.4005984663963318,
      "learning_rate": 9.812016189458779e-06,
      "loss": 0.5388,
      "step": 32993
    },
    {
      "epoch": 1.0135471385125794,
      "grad_norm": 0.35354092717170715,
      "learning_rate": 9.811532997739607e-06,
      "loss": 0.3726,
      "step": 32994
    },
    {
      "epoch": 1.0135778576475287,
      "grad_norm": 0.39084306359291077,
      "learning_rate": 9.811049806460617e-06,
      "loss": 0.5211,
      "step": 32995
    },
    {
      "epoch": 1.0136085767824778,
      "grad_norm": 0.36751800775527954,
      "learning_rate": 9.810566615622929e-06,
      "loss": 0.4575,
      "step": 32996
    },
    {
      "epoch": 1.013639295917427,
      "grad_norm": 0.3348958492279053,
      "learning_rate": 9.81008342522768e-06,
      "loss": 0.4235,
      "step": 32997
    },
    {
      "epoch": 1.013670015052376,
      "grad_norm": 0.3804345428943634,
      "learning_rate": 9.809600235275991e-06,
      "loss": 0.4366,
      "step": 32998
    },
    {
      "epoch": 1.0137007341873252,
      "grad_norm": 0.39742544293403625,
      "learning_rate": 9.809117045768997e-06,
      "loss": 0.4783,
      "step": 32999
    },
    {
      "epoch": 1.0137314533222745,
      "grad_norm": 0.4125640094280243,
      "learning_rate": 9.808633856707822e-06,
      "loss": 0.5734,
      "step": 33000
    },
    {
      "epoch": 1.0137621724572237,
      "grad_norm": 0.387514591217041,
      "learning_rate": 9.808150668093595e-06,
      "loss": 0.5038,
      "step": 33001
    },
    {
      "epoch": 1.0137928915921728,
      "grad_norm": 0.3900303840637207,
      "learning_rate": 9.807667479927446e-06,
      "loss": 0.4054,
      "step": 33002
    },
    {
      "epoch": 1.013823610727122,
      "grad_norm": 0.43255919218063354,
      "learning_rate": 9.807184292210505e-06,
      "loss": 0.5345,
      "step": 33003
    },
    {
      "epoch": 1.013854329862071,
      "grad_norm": 0.4132224917411804,
      "learning_rate": 9.806701104943894e-06,
      "loss": 0.5182,
      "step": 33004
    },
    {
      "epoch": 1.0138850489970201,
      "grad_norm": 0.41763749718666077,
      "learning_rate": 9.80621791812875e-06,
      "loss": 0.4353,
      "step": 33005
    },
    {
      "epoch": 1.0139157681319695,
      "grad_norm": 0.36809244751930237,
      "learning_rate": 9.805734731766196e-06,
      "loss": 0.5226,
      "step": 33006
    },
    {
      "epoch": 1.0139464872669186,
      "grad_norm": 0.42358237504959106,
      "learning_rate": 9.805251545857362e-06,
      "loss": 0.4998,
      "step": 33007
    },
    {
      "epoch": 1.0139772064018677,
      "grad_norm": 0.39848145842552185,
      "learning_rate": 9.804768360403378e-06,
      "loss": 0.506,
      "step": 33008
    },
    {
      "epoch": 1.0140079255368168,
      "grad_norm": 0.3610289990901947,
      "learning_rate": 9.80428517540537e-06,
      "loss": 0.5106,
      "step": 33009
    },
    {
      "epoch": 1.014038644671766,
      "grad_norm": 0.37315604090690613,
      "learning_rate": 9.803801990864468e-06,
      "loss": 0.5456,
      "step": 33010
    },
    {
      "epoch": 1.0140693638067153,
      "grad_norm": 0.3925965428352356,
      "learning_rate": 9.8033188067818e-06,
      "loss": 0.4561,
      "step": 33011
    },
    {
      "epoch": 1.0141000829416644,
      "grad_norm": 0.44607776403427124,
      "learning_rate": 9.802835623158495e-06,
      "loss": 0.4938,
      "step": 33012
    },
    {
      "epoch": 1.0141308020766135,
      "grad_norm": 0.35893404483795166,
      "learning_rate": 9.80235243999568e-06,
      "loss": 0.5029,
      "step": 33013
    },
    {
      "epoch": 1.0141615212115627,
      "grad_norm": 0.4319865107536316,
      "learning_rate": 9.801869257294488e-06,
      "loss": 0.5066,
      "step": 33014
    },
    {
      "epoch": 1.0141922403465118,
      "grad_norm": 0.3735962510108948,
      "learning_rate": 9.801386075056039e-06,
      "loss": 0.4952,
      "step": 33015
    },
    {
      "epoch": 1.014222959481461,
      "grad_norm": 0.41981661319732666,
      "learning_rate": 9.800902893281471e-06,
      "loss": 0.516,
      "step": 33016
    },
    {
      "epoch": 1.0142536786164102,
      "grad_norm": 0.4060456454753876,
      "learning_rate": 9.800419711971906e-06,
      "loss": 0.4541,
      "step": 33017
    },
    {
      "epoch": 1.0142843977513594,
      "grad_norm": 0.41317999362945557,
      "learning_rate": 9.799936531128477e-06,
      "loss": 0.5101,
      "step": 33018
    },
    {
      "epoch": 1.0143151168863085,
      "grad_norm": 0.35241127014160156,
      "learning_rate": 9.799453350752308e-06,
      "loss": 0.4986,
      "step": 33019
    },
    {
      "epoch": 1.0143458360212576,
      "grad_norm": 0.3873284161090851,
      "learning_rate": 9.798970170844533e-06,
      "loss": 0.4678,
      "step": 33020
    },
    {
      "epoch": 1.0143765551562067,
      "grad_norm": 0.3770156800746918,
      "learning_rate": 9.79848699140627e-06,
      "loss": 0.4368,
      "step": 33021
    },
    {
      "epoch": 1.014407274291156,
      "grad_norm": 0.36964789032936096,
      "learning_rate": 9.798003812438663e-06,
      "loss": 0.5026,
      "step": 33022
    },
    {
      "epoch": 1.0144379934261052,
      "grad_norm": 0.4268989562988281,
      "learning_rate": 9.797520633942826e-06,
      "loss": 0.5458,
      "step": 33023
    },
    {
      "epoch": 1.0144687125610543,
      "grad_norm": 0.41715359687805176,
      "learning_rate": 9.797037455919896e-06,
      "loss": 0.4892,
      "step": 33024
    },
    {
      "epoch": 1.0144994316960034,
      "grad_norm": 0.3586050868034363,
      "learning_rate": 9.796554278371e-06,
      "loss": 0.5488,
      "step": 33025
    },
    {
      "epoch": 1.0145301508309525,
      "grad_norm": 0.4057035744190216,
      "learning_rate": 9.796071101297263e-06,
      "loss": 0.5086,
      "step": 33026
    },
    {
      "epoch": 1.0145608699659017,
      "grad_norm": 0.36539870500564575,
      "learning_rate": 9.795587924699822e-06,
      "loss": 0.4778,
      "step": 33027
    },
    {
      "epoch": 1.014591589100851,
      "grad_norm": 0.380877286195755,
      "learning_rate": 9.795104748579792e-06,
      "loss": 0.5757,
      "step": 33028
    },
    {
      "epoch": 1.0146223082358001,
      "grad_norm": 0.3583027720451355,
      "learning_rate": 9.794621572938317e-06,
      "loss": 0.4924,
      "step": 33029
    },
    {
      "epoch": 1.0146530273707492,
      "grad_norm": 0.40838074684143066,
      "learning_rate": 9.79413839777651e-06,
      "loss": 0.4652,
      "step": 33030
    },
    {
      "epoch": 1.0146837465056984,
      "grad_norm": 0.35244742035865784,
      "learning_rate": 9.793655223095515e-06,
      "loss": 0.5043,
      "step": 33031
    },
    {
      "epoch": 1.0147144656406475,
      "grad_norm": 0.40042805671691895,
      "learning_rate": 9.793172048896445e-06,
      "loss": 0.5547,
      "step": 33032
    },
    {
      "epoch": 1.0147451847755966,
      "grad_norm": 0.3889009952545166,
      "learning_rate": 9.792688875180442e-06,
      "loss": 0.4368,
      "step": 33033
    },
    {
      "epoch": 1.014775903910546,
      "grad_norm": 0.48324429988861084,
      "learning_rate": 9.792205701948626e-06,
      "loss": 0.4339,
      "step": 33034
    },
    {
      "epoch": 1.014806623045495,
      "grad_norm": 0.347834974527359,
      "learning_rate": 9.79172252920213e-06,
      "loss": 0.4686,
      "step": 33035
    },
    {
      "epoch": 1.0148373421804442,
      "grad_norm": 0.40504190325737,
      "learning_rate": 9.791239356942076e-06,
      "loss": 0.5412,
      "step": 33036
    },
    {
      "epoch": 1.0148680613153933,
      "grad_norm": 0.37600162625312805,
      "learning_rate": 9.790756185169602e-06,
      "loss": 0.5429,
      "step": 33037
    },
    {
      "epoch": 1.0148987804503424,
      "grad_norm": 0.4045856297016144,
      "learning_rate": 9.790273013885829e-06,
      "loss": 0.5485,
      "step": 33038
    },
    {
      "epoch": 1.0149294995852918,
      "grad_norm": 0.4209355413913727,
      "learning_rate": 9.78978984309189e-06,
      "loss": 0.4467,
      "step": 33039
    },
    {
      "epoch": 1.014960218720241,
      "grad_norm": 0.4122985005378723,
      "learning_rate": 9.789306672788908e-06,
      "loss": 0.5242,
      "step": 33040
    },
    {
      "epoch": 1.01499093785519,
      "grad_norm": 0.360931932926178,
      "learning_rate": 9.788823502978018e-06,
      "loss": 0.5229,
      "step": 33041
    },
    {
      "epoch": 1.0150216569901391,
      "grad_norm": 0.3967532813549042,
      "learning_rate": 9.788340333660344e-06,
      "loss": 0.5563,
      "step": 33042
    },
    {
      "epoch": 1.0150523761250883,
      "grad_norm": 0.36832141876220703,
      "learning_rate": 9.787857164837015e-06,
      "loss": 0.5837,
      "step": 33043
    },
    {
      "epoch": 1.0150830952600374,
      "grad_norm": 0.3998969495296478,
      "learning_rate": 9.787373996509165e-06,
      "loss": 0.481,
      "step": 33044
    },
    {
      "epoch": 1.0151138143949867,
      "grad_norm": 0.41278091073036194,
      "learning_rate": 9.786890828677911e-06,
      "loss": 0.4377,
      "step": 33045
    },
    {
      "epoch": 1.0151445335299358,
      "grad_norm": 0.37016546726226807,
      "learning_rate": 9.786407661344395e-06,
      "loss": 0.5101,
      "step": 33046
    },
    {
      "epoch": 1.015175252664885,
      "grad_norm": 0.3657781779766083,
      "learning_rate": 9.785924494509735e-06,
      "loss": 0.5273,
      "step": 33047
    },
    {
      "epoch": 1.015205971799834,
      "grad_norm": 0.3716632127761841,
      "learning_rate": 9.785441328175065e-06,
      "loss": 0.485,
      "step": 33048
    },
    {
      "epoch": 1.0152366909347832,
      "grad_norm": 0.36276963353157043,
      "learning_rate": 9.784958162341508e-06,
      "loss": 0.4696,
      "step": 33049
    },
    {
      "epoch": 1.0152674100697325,
      "grad_norm": 0.3682088851928711,
      "learning_rate": 9.784474997010202e-06,
      "loss": 0.546,
      "step": 33050
    },
    {
      "epoch": 1.0152981292046817,
      "grad_norm": 0.3876621127128601,
      "learning_rate": 9.783991832182266e-06,
      "loss": 0.535,
      "step": 33051
    },
    {
      "epoch": 1.0153288483396308,
      "grad_norm": 0.4055650532245636,
      "learning_rate": 9.783508667858834e-06,
      "loss": 0.5303,
      "step": 33052
    },
    {
      "epoch": 1.01535956747458,
      "grad_norm": 0.6799834370613098,
      "learning_rate": 9.78302550404103e-06,
      "loss": 0.4863,
      "step": 33053
    },
    {
      "epoch": 1.015390286609529,
      "grad_norm": 0.3680397570133209,
      "learning_rate": 9.782542340729987e-06,
      "loss": 0.5428,
      "step": 33054
    },
    {
      "epoch": 1.0154210057444781,
      "grad_norm": 0.3775704801082611,
      "learning_rate": 9.782059177926831e-06,
      "loss": 0.5149,
      "step": 33055
    },
    {
      "epoch": 1.0154517248794275,
      "grad_norm": 0.39232492446899414,
      "learning_rate": 9.781576015632695e-06,
      "loss": 0.5521,
      "step": 33056
    },
    {
      "epoch": 1.0154824440143766,
      "grad_norm": 0.44320976734161377,
      "learning_rate": 9.781092853848698e-06,
      "loss": 0.5085,
      "step": 33057
    },
    {
      "epoch": 1.0155131631493257,
      "grad_norm": 0.4190423786640167,
      "learning_rate": 9.780609692575978e-06,
      "loss": 0.4812,
      "step": 33058
    },
    {
      "epoch": 1.0155438822842748,
      "grad_norm": 0.38137778639793396,
      "learning_rate": 9.780126531815654e-06,
      "loss": 0.5486,
      "step": 33059
    },
    {
      "epoch": 1.015574601419224,
      "grad_norm": 0.5967245697975159,
      "learning_rate": 9.779643371568866e-06,
      "loss": 0.5403,
      "step": 33060
    },
    {
      "epoch": 1.0156053205541733,
      "grad_norm": 0.3639461100101471,
      "learning_rate": 9.779160211836733e-06,
      "loss": 0.494,
      "step": 33061
    },
    {
      "epoch": 1.0156360396891224,
      "grad_norm": 0.3508661687374115,
      "learning_rate": 9.778677052620382e-06,
      "loss": 0.4839,
      "step": 33062
    },
    {
      "epoch": 1.0156667588240715,
      "grad_norm": 0.3878996968269348,
      "learning_rate": 9.778193893920956e-06,
      "loss": 0.487,
      "step": 33063
    },
    {
      "epoch": 1.0156974779590207,
      "grad_norm": 0.42717742919921875,
      "learning_rate": 9.777710735739566e-06,
      "loss": 0.5284,
      "step": 33064
    },
    {
      "epoch": 1.0157281970939698,
      "grad_norm": 0.3811529278755188,
      "learning_rate": 9.777227578077353e-06,
      "loss": 0.4903,
      "step": 33065
    },
    {
      "epoch": 1.015758916228919,
      "grad_norm": 0.38499510288238525,
      "learning_rate": 9.776744420935435e-06,
      "loss": 0.5547,
      "step": 33066
    },
    {
      "epoch": 1.0157896353638682,
      "grad_norm": 0.39997372031211853,
      "learning_rate": 9.776261264314954e-06,
      "loss": 0.4907,
      "step": 33067
    },
    {
      "epoch": 1.0158203544988174,
      "grad_norm": 0.36270979046821594,
      "learning_rate": 9.775778108217025e-06,
      "loss": 0.4352,
      "step": 33068
    },
    {
      "epoch": 1.0158510736337665,
      "grad_norm": 0.3417689800262451,
      "learning_rate": 9.775294952642783e-06,
      "loss": 0.4879,
      "step": 33069
    },
    {
      "epoch": 1.0158817927687156,
      "grad_norm": 0.36277875304222107,
      "learning_rate": 9.774811797593354e-06,
      "loss": 0.4793,
      "step": 33070
    },
    {
      "epoch": 1.0159125119036647,
      "grad_norm": 0.39034631848335266,
      "learning_rate": 9.77432864306987e-06,
      "loss": 0.5608,
      "step": 33071
    },
    {
      "epoch": 1.015943231038614,
      "grad_norm": 0.40191909670829773,
      "learning_rate": 9.773845489073455e-06,
      "loss": 0.5201,
      "step": 33072
    },
    {
      "epoch": 1.0159739501735632,
      "grad_norm": 0.39520224928855896,
      "learning_rate": 9.773362335605243e-06,
      "loss": 0.3711,
      "step": 33073
    },
    {
      "epoch": 1.0160046693085123,
      "grad_norm": 0.42025619745254517,
      "learning_rate": 9.772879182666355e-06,
      "loss": 0.4818,
      "step": 33074
    },
    {
      "epoch": 1.0160353884434614,
      "grad_norm": 0.3872661292552948,
      "learning_rate": 9.772396030257927e-06,
      "loss": 0.441,
      "step": 33075
    },
    {
      "epoch": 1.0160661075784105,
      "grad_norm": 0.39738813042640686,
      "learning_rate": 9.771912878381081e-06,
      "loss": 0.5824,
      "step": 33076
    },
    {
      "epoch": 1.0160968267133597,
      "grad_norm": 0.37199294567108154,
      "learning_rate": 9.771429727036951e-06,
      "loss": 0.4292,
      "step": 33077
    },
    {
      "epoch": 1.016127545848309,
      "grad_norm": 0.3656083047389984,
      "learning_rate": 9.77094657622666e-06,
      "loss": 0.4743,
      "step": 33078
    },
    {
      "epoch": 1.0161582649832581,
      "grad_norm": 0.37207090854644775,
      "learning_rate": 9.77046342595134e-06,
      "loss": 0.4895,
      "step": 33079
    },
    {
      "epoch": 1.0161889841182072,
      "grad_norm": 0.37715423107147217,
      "learning_rate": 9.769980276212121e-06,
      "loss": 0.5031,
      "step": 33080
    },
    {
      "epoch": 1.0162197032531564,
      "grad_norm": 0.3616122007369995,
      "learning_rate": 9.769497127010126e-06,
      "loss": 0.5117,
      "step": 33081
    },
    {
      "epoch": 1.0162504223881055,
      "grad_norm": 0.4117738902568817,
      "learning_rate": 9.76901397834649e-06,
      "loss": 0.4399,
      "step": 33082
    },
    {
      "epoch": 1.0162811415230548,
      "grad_norm": 0.3769628703594208,
      "learning_rate": 9.768530830222335e-06,
      "loss": 0.5042,
      "step": 33083
    },
    {
      "epoch": 1.016311860658004,
      "grad_norm": 0.3704775273799896,
      "learning_rate": 9.768047682638794e-06,
      "loss": 0.5579,
      "step": 33084
    },
    {
      "epoch": 1.016342579792953,
      "grad_norm": 0.39726483821868896,
      "learning_rate": 9.767564535596992e-06,
      "loss": 0.4556,
      "step": 33085
    },
    {
      "epoch": 1.0163732989279022,
      "grad_norm": 0.3833392858505249,
      "learning_rate": 9.767081389098064e-06,
      "loss": 0.4867,
      "step": 33086
    },
    {
      "epoch": 1.0164040180628513,
      "grad_norm": 0.35452258586883545,
      "learning_rate": 9.766598243143129e-06,
      "loss": 0.4392,
      "step": 33087
    },
    {
      "epoch": 1.0164347371978004,
      "grad_norm": 0.4234860837459564,
      "learning_rate": 9.766115097733322e-06,
      "loss": 0.5765,
      "step": 33088
    },
    {
      "epoch": 1.0164654563327498,
      "grad_norm": 0.40326809883117676,
      "learning_rate": 9.765631952869768e-06,
      "loss": 0.5049,
      "step": 33089
    },
    {
      "epoch": 1.0164961754676989,
      "grad_norm": 0.4129529893398285,
      "learning_rate": 9.765148808553601e-06,
      "loss": 0.5492,
      "step": 33090
    },
    {
      "epoch": 1.016526894602648,
      "grad_norm": 0.4472584128379822,
      "learning_rate": 9.764665664785939e-06,
      "loss": 0.4811,
      "step": 33091
    },
    {
      "epoch": 1.0165576137375971,
      "grad_norm": 0.37212106585502625,
      "learning_rate": 9.764182521567925e-06,
      "loss": 0.5687,
      "step": 33092
    },
    {
      "epoch": 1.0165883328725462,
      "grad_norm": 0.39000338315963745,
      "learning_rate": 9.76369937890067e-06,
      "loss": 0.4301,
      "step": 33093
    },
    {
      "epoch": 1.0166190520074954,
      "grad_norm": 0.39298224449157715,
      "learning_rate": 9.763216236785318e-06,
      "loss": 0.4948,
      "step": 33094
    },
    {
      "epoch": 1.0166497711424447,
      "grad_norm": 0.38740938901901245,
      "learning_rate": 9.762733095222987e-06,
      "loss": 0.465,
      "step": 33095
    },
    {
      "epoch": 1.0166804902773938,
      "grad_norm": 0.4959239065647125,
      "learning_rate": 9.762249954214814e-06,
      "loss": 0.4773,
      "step": 33096
    },
    {
      "epoch": 1.016711209412343,
      "grad_norm": 0.3610796332359314,
      "learning_rate": 9.761766813761919e-06,
      "loss": 0.5031,
      "step": 33097
    },
    {
      "epoch": 1.016741928547292,
      "grad_norm": 0.378986656665802,
      "learning_rate": 9.761283673865433e-06,
      "loss": 0.512,
      "step": 33098
    },
    {
      "epoch": 1.0167726476822412,
      "grad_norm": 0.3919293284416199,
      "learning_rate": 9.76080053452649e-06,
      "loss": 0.5299,
      "step": 33099
    },
    {
      "epoch": 1.0168033668171905,
      "grad_norm": 0.35053595900535583,
      "learning_rate": 9.76031739574621e-06,
      "loss": 0.5456,
      "step": 33100
    },
    {
      "epoch": 1.0168340859521396,
      "grad_norm": 0.41464442014694214,
      "learning_rate": 9.759834257525732e-06,
      "loss": 0.5827,
      "step": 33101
    },
    {
      "epoch": 1.0168648050870888,
      "grad_norm": 0.38973093032836914,
      "learning_rate": 9.759351119866171e-06,
      "loss": 0.4353,
      "step": 33102
    },
    {
      "epoch": 1.0168955242220379,
      "grad_norm": 0.3852671980857849,
      "learning_rate": 9.758867982768668e-06,
      "loss": 0.5696,
      "step": 33103
    },
    {
      "epoch": 1.016926243356987,
      "grad_norm": 0.39399343729019165,
      "learning_rate": 9.75838484623434e-06,
      "loss": 0.4967,
      "step": 33104
    },
    {
      "epoch": 1.0169569624919361,
      "grad_norm": 0.41809314489364624,
      "learning_rate": 9.757901710264324e-06,
      "loss": 0.5135,
      "step": 33105
    },
    {
      "epoch": 1.0169876816268855,
      "grad_norm": 0.40397992730140686,
      "learning_rate": 9.757418574859745e-06,
      "loss": 0.4676,
      "step": 33106
    },
    {
      "epoch": 1.0170184007618346,
      "grad_norm": 0.36448928713798523,
      "learning_rate": 9.756935440021733e-06,
      "loss": 0.509,
      "step": 33107
    },
    {
      "epoch": 1.0170491198967837,
      "grad_norm": 0.38876402378082275,
      "learning_rate": 9.756452305751412e-06,
      "loss": 0.4996,
      "step": 33108
    },
    {
      "epoch": 1.0170798390317328,
      "grad_norm": 0.4071533679962158,
      "learning_rate": 9.755969172049918e-06,
      "loss": 0.5314,
      "step": 33109
    },
    {
      "epoch": 1.017110558166682,
      "grad_norm": 0.3654632866382599,
      "learning_rate": 9.755486038918372e-06,
      "loss": 0.5585,
      "step": 33110
    },
    {
      "epoch": 1.0171412773016313,
      "grad_norm": 0.39759278297424316,
      "learning_rate": 9.755002906357906e-06,
      "loss": 0.4807,
      "step": 33111
    },
    {
      "epoch": 1.0171719964365804,
      "grad_norm": 0.3750724196434021,
      "learning_rate": 9.754519774369648e-06,
      "loss": 0.4787,
      "step": 33112
    },
    {
      "epoch": 1.0172027155715295,
      "grad_norm": 0.38060250878334045,
      "learning_rate": 9.754036642954726e-06,
      "loss": 0.5024,
      "step": 33113
    },
    {
      "epoch": 1.0172334347064786,
      "grad_norm": 0.4397392272949219,
      "learning_rate": 9.753553512114269e-06,
      "loss": 0.5197,
      "step": 33114
    },
    {
      "epoch": 1.0172641538414278,
      "grad_norm": 0.36562207341194153,
      "learning_rate": 9.753070381849403e-06,
      "loss": 0.5634,
      "step": 33115
    },
    {
      "epoch": 1.0172948729763769,
      "grad_norm": 0.3588309586048126,
      "learning_rate": 9.752587252161263e-06,
      "loss": 0.4931,
      "step": 33116
    },
    {
      "epoch": 1.0173255921113262,
      "grad_norm": 0.4210517704486847,
      "learning_rate": 9.752104123050967e-06,
      "loss": 0.5135,
      "step": 33117
    },
    {
      "epoch": 1.0173563112462753,
      "grad_norm": 0.35786110162734985,
      "learning_rate": 9.751620994519654e-06,
      "loss": 0.5198,
      "step": 33118
    },
    {
      "epoch": 1.0173870303812245,
      "grad_norm": 0.4015229344367981,
      "learning_rate": 9.751137866568444e-06,
      "loss": 0.6186,
      "step": 33119
    },
    {
      "epoch": 1.0174177495161736,
      "grad_norm": 0.37353968620300293,
      "learning_rate": 9.750654739198472e-06,
      "loss": 0.5283,
      "step": 33120
    },
    {
      "epoch": 1.0174484686511227,
      "grad_norm": 0.3862921893596649,
      "learning_rate": 9.75017161241086e-06,
      "loss": 0.4718,
      "step": 33121
    },
    {
      "epoch": 1.017479187786072,
      "grad_norm": 0.3695107698440552,
      "learning_rate": 9.749688486206744e-06,
      "loss": 0.5425,
      "step": 33122
    },
    {
      "epoch": 1.0175099069210212,
      "grad_norm": 0.43399566411972046,
      "learning_rate": 9.749205360587243e-06,
      "loss": 0.5102,
      "step": 33123
    },
    {
      "epoch": 1.0175406260559703,
      "grad_norm": 0.4007861614227295,
      "learning_rate": 9.748722235553497e-06,
      "loss": 0.4745,
      "step": 33124
    },
    {
      "epoch": 1.0175713451909194,
      "grad_norm": 0.36703190207481384,
      "learning_rate": 9.74823911110662e-06,
      "loss": 0.4439,
      "step": 33125
    },
    {
      "epoch": 1.0176020643258685,
      "grad_norm": 0.40388694405555725,
      "learning_rate": 9.747755987247754e-06,
      "loss": 0.4577,
      "step": 33126
    },
    {
      "epoch": 1.0176327834608176,
      "grad_norm": 0.3812686502933502,
      "learning_rate": 9.747272863978017e-06,
      "loss": 0.5476,
      "step": 33127
    },
    {
      "epoch": 1.017663502595767,
      "grad_norm": 0.4020976126194,
      "learning_rate": 9.746789741298547e-06,
      "loss": 0.4915,
      "step": 33128
    },
    {
      "epoch": 1.017694221730716,
      "grad_norm": 0.38089656829833984,
      "learning_rate": 9.746306619210461e-06,
      "loss": 0.5424,
      "step": 33129
    },
    {
      "epoch": 1.0177249408656652,
      "grad_norm": 0.3699548542499542,
      "learning_rate": 9.7458234977149e-06,
      "loss": 0.5158,
      "step": 33130
    },
    {
      "epoch": 1.0177556600006143,
      "grad_norm": 0.3704119622707367,
      "learning_rate": 9.745340376812984e-06,
      "loss": 0.5034,
      "step": 33131
    },
    {
      "epoch": 1.0177863791355635,
      "grad_norm": 0.40338030457496643,
      "learning_rate": 9.744857256505842e-06,
      "loss": 0.5086,
      "step": 33132
    },
    {
      "epoch": 1.0178170982705128,
      "grad_norm": 0.44230470061302185,
      "learning_rate": 9.744374136794603e-06,
      "loss": 0.4901,
      "step": 33133
    },
    {
      "epoch": 1.017847817405462,
      "grad_norm": 0.42558300495147705,
      "learning_rate": 9.743891017680394e-06,
      "loss": 0.5731,
      "step": 33134
    },
    {
      "epoch": 1.017878536540411,
      "grad_norm": 0.38263317942619324,
      "learning_rate": 9.74340789916435e-06,
      "loss": 0.5272,
      "step": 33135
    },
    {
      "epoch": 1.0179092556753602,
      "grad_norm": 0.45414358377456665,
      "learning_rate": 9.742924781247591e-06,
      "loss": 0.5077,
      "step": 33136
    },
    {
      "epoch": 1.0179399748103093,
      "grad_norm": 0.40701818466186523,
      "learning_rate": 9.742441663931255e-06,
      "loss": 0.514,
      "step": 33137
    },
    {
      "epoch": 1.0179706939452584,
      "grad_norm": 0.3678682744503021,
      "learning_rate": 9.74195854721646e-06,
      "loss": 0.5492,
      "step": 33138
    },
    {
      "epoch": 1.0180014130802078,
      "grad_norm": 0.4123195707798004,
      "learning_rate": 9.74147543110434e-06,
      "loss": 0.5138,
      "step": 33139
    },
    {
      "epoch": 1.0180321322151569,
      "grad_norm": 0.3569906949996948,
      "learning_rate": 9.740992315596021e-06,
      "loss": 0.4543,
      "step": 33140
    },
    {
      "epoch": 1.018062851350106,
      "grad_norm": 0.3796038031578064,
      "learning_rate": 9.740509200692635e-06,
      "loss": 0.4897,
      "step": 33141
    },
    {
      "epoch": 1.018093570485055,
      "grad_norm": 0.375171959400177,
      "learning_rate": 9.740026086395305e-06,
      "loss": 0.4749,
      "step": 33142
    },
    {
      "epoch": 1.0181242896200042,
      "grad_norm": 0.338820219039917,
      "learning_rate": 9.739542972705164e-06,
      "loss": 0.5231,
      "step": 33143
    },
    {
      "epoch": 1.0181550087549534,
      "grad_norm": 0.3689025938510895,
      "learning_rate": 9.739059859623337e-06,
      "loss": 0.5215,
      "step": 33144
    },
    {
      "epoch": 1.0181857278899027,
      "grad_norm": 0.3972766697406769,
      "learning_rate": 9.738576747150956e-06,
      "loss": 0.563,
      "step": 33145
    },
    {
      "epoch": 1.0182164470248518,
      "grad_norm": 0.35430091619491577,
      "learning_rate": 9.738093635289146e-06,
      "loss": 0.4605,
      "step": 33146
    },
    {
      "epoch": 1.018247166159801,
      "grad_norm": 0.38247203826904297,
      "learning_rate": 9.737610524039037e-06,
      "loss": 0.5136,
      "step": 33147
    },
    {
      "epoch": 1.01827788529475,
      "grad_norm": 0.39354220032691956,
      "learning_rate": 9.737127413401758e-06,
      "loss": 0.5505,
      "step": 33148
    },
    {
      "epoch": 1.0183086044296992,
      "grad_norm": 0.46015945076942444,
      "learning_rate": 9.736644303378434e-06,
      "loss": 0.4963,
      "step": 33149
    },
    {
      "epoch": 1.0183393235646485,
      "grad_norm": 0.45025819540023804,
      "learning_rate": 9.736161193970196e-06,
      "loss": 0.4581,
      "step": 33150
    },
    {
      "epoch": 1.0183700426995976,
      "grad_norm": 0.4903341233730316,
      "learning_rate": 9.735678085178174e-06,
      "loss": 0.4297,
      "step": 33151
    },
    {
      "epoch": 1.0184007618345468,
      "grad_norm": 0.3664488196372986,
      "learning_rate": 9.735194977003492e-06,
      "loss": 0.5123,
      "step": 33152
    },
    {
      "epoch": 1.0184314809694959,
      "grad_norm": 0.38326385617256165,
      "learning_rate": 9.73471186944728e-06,
      "loss": 0.5172,
      "step": 33153
    },
    {
      "epoch": 1.018462200104445,
      "grad_norm": 0.43731334805488586,
      "learning_rate": 9.734228762510671e-06,
      "loss": 0.4981,
      "step": 33154
    },
    {
      "epoch": 1.0184929192393941,
      "grad_norm": 0.3703259527683258,
      "learning_rate": 9.733745656194785e-06,
      "loss": 0.5537,
      "step": 33155
    },
    {
      "epoch": 1.0185236383743435,
      "grad_norm": 0.37471362948417664,
      "learning_rate": 9.733262550500758e-06,
      "loss": 0.5442,
      "step": 33156
    },
    {
      "epoch": 1.0185543575092926,
      "grad_norm": 0.3735966384410858,
      "learning_rate": 9.732779445429713e-06,
      "loss": 0.4762,
      "step": 33157
    },
    {
      "epoch": 1.0185850766442417,
      "grad_norm": 0.36284002661705017,
      "learning_rate": 9.732296340982782e-06,
      "loss": 0.5655,
      "step": 33158
    },
    {
      "epoch": 1.0186157957791908,
      "grad_norm": 0.4013334810733795,
      "learning_rate": 9.731813237161088e-06,
      "loss": 0.5253,
      "step": 33159
    },
    {
      "epoch": 1.01864651491414,
      "grad_norm": 0.36079147458076477,
      "learning_rate": 9.731330133965769e-06,
      "loss": 0.5757,
      "step": 33160
    },
    {
      "epoch": 1.0186772340490893,
      "grad_norm": 0.4462360739707947,
      "learning_rate": 9.73084703139794e-06,
      "loss": 0.5075,
      "step": 33161
    },
    {
      "epoch": 1.0187079531840384,
      "grad_norm": 0.37059444189071655,
      "learning_rate": 9.730363929458743e-06,
      "loss": 0.4759,
      "step": 33162
    },
    {
      "epoch": 1.0187386723189875,
      "grad_norm": 0.37781983613967896,
      "learning_rate": 9.729880828149293e-06,
      "loss": 0.4724,
      "step": 33163
    },
    {
      "epoch": 1.0187693914539366,
      "grad_norm": 0.3866967260837555,
      "learning_rate": 9.729397727470734e-06,
      "loss": 0.5389,
      "step": 33164
    },
    {
      "epoch": 1.0188001105888858,
      "grad_norm": 0.388962060213089,
      "learning_rate": 9.728914627424178e-06,
      "loss": 0.5963,
      "step": 33165
    },
    {
      "epoch": 1.0188308297238349,
      "grad_norm": 0.4573509991168976,
      "learning_rate": 9.728431528010764e-06,
      "loss": 0.5086,
      "step": 33166
    },
    {
      "epoch": 1.0188615488587842,
      "grad_norm": 0.3442240059375763,
      "learning_rate": 9.727948429231617e-06,
      "loss": 0.5459,
      "step": 33167
    },
    {
      "epoch": 1.0188922679937333,
      "grad_norm": 0.4047497808933258,
      "learning_rate": 9.727465331087865e-06,
      "loss": 0.4945,
      "step": 33168
    },
    {
      "epoch": 1.0189229871286825,
      "grad_norm": 0.357736200094223,
      "learning_rate": 9.726982233580636e-06,
      "loss": 0.4578,
      "step": 33169
    },
    {
      "epoch": 1.0189537062636316,
      "grad_norm": 0.4203770160675049,
      "learning_rate": 9.726499136711056e-06,
      "loss": 0.4368,
      "step": 33170
    },
    {
      "epoch": 1.0189844253985807,
      "grad_norm": 0.4104636609554291,
      "learning_rate": 9.726016040480262e-06,
      "loss": 0.5884,
      "step": 33171
    },
    {
      "epoch": 1.01901514453353,
      "grad_norm": 0.36894458532333374,
      "learning_rate": 9.725532944889376e-06,
      "loss": 0.5442,
      "step": 33172
    },
    {
      "epoch": 1.0190458636684792,
      "grad_norm": 0.3507578670978546,
      "learning_rate": 9.725049849939525e-06,
      "loss": 0.5328,
      "step": 33173
    },
    {
      "epoch": 1.0190765828034283,
      "grad_norm": 0.5066321492195129,
      "learning_rate": 9.72456675563184e-06,
      "loss": 0.5527,
      "step": 33174
    },
    {
      "epoch": 1.0191073019383774,
      "grad_norm": 0.4051806926727295,
      "learning_rate": 9.72408366196745e-06,
      "loss": 0.5232,
      "step": 33175
    },
    {
      "epoch": 1.0191380210733265,
      "grad_norm": 0.6562433242797852,
      "learning_rate": 9.723600568947478e-06,
      "loss": 0.583,
      "step": 33176
    },
    {
      "epoch": 1.0191687402082756,
      "grad_norm": 0.4142877459526062,
      "learning_rate": 9.72311747657306e-06,
      "loss": 0.5196,
      "step": 33177
    },
    {
      "epoch": 1.019199459343225,
      "grad_norm": 0.3887529671192169,
      "learning_rate": 9.722634384845319e-06,
      "loss": 0.5525,
      "step": 33178
    },
    {
      "epoch": 1.019230178478174,
      "grad_norm": 0.410595566034317,
      "learning_rate": 9.722151293765386e-06,
      "loss": 0.5221,
      "step": 33179
    },
    {
      "epoch": 1.0192608976131232,
      "grad_norm": 0.43365123867988586,
      "learning_rate": 9.721668203334385e-06,
      "loss": 0.5424,
      "step": 33180
    },
    {
      "epoch": 1.0192916167480723,
      "grad_norm": 0.39106130599975586,
      "learning_rate": 9.72118511355345e-06,
      "loss": 0.4954,
      "step": 33181
    },
    {
      "epoch": 1.0193223358830215,
      "grad_norm": 0.4402911365032196,
      "learning_rate": 9.720702024423706e-06,
      "loss": 0.4531,
      "step": 33182
    },
    {
      "epoch": 1.0193530550179708,
      "grad_norm": 0.3834497630596161,
      "learning_rate": 9.720218935946283e-06,
      "loss": 0.5028,
      "step": 33183
    },
    {
      "epoch": 1.01938377415292,
      "grad_norm": 0.3758843243122101,
      "learning_rate": 9.719735848122306e-06,
      "loss": 0.5529,
      "step": 33184
    },
    {
      "epoch": 1.019414493287869,
      "grad_norm": 0.3702302873134613,
      "learning_rate": 9.719252760952908e-06,
      "loss": 0.5064,
      "step": 33185
    },
    {
      "epoch": 1.0194452124228182,
      "grad_norm": 0.4045269191265106,
      "learning_rate": 9.718769674439213e-06,
      "loss": 0.4801,
      "step": 33186
    },
    {
      "epoch": 1.0194759315577673,
      "grad_norm": 0.37980222702026367,
      "learning_rate": 9.718286588582354e-06,
      "loss": 0.5212,
      "step": 33187
    },
    {
      "epoch": 1.0195066506927164,
      "grad_norm": 0.4845421016216278,
      "learning_rate": 9.717803503383451e-06,
      "loss": 0.4666,
      "step": 33188
    },
    {
      "epoch": 1.0195373698276657,
      "grad_norm": 0.40964475274086,
      "learning_rate": 9.71732041884364e-06,
      "loss": 0.4993,
      "step": 33189
    },
    {
      "epoch": 1.0195680889626149,
      "grad_norm": 0.38456496596336365,
      "learning_rate": 9.716837334964047e-06,
      "loss": 0.4682,
      "step": 33190
    },
    {
      "epoch": 1.019598808097564,
      "grad_norm": 0.38956353068351746,
      "learning_rate": 9.7163542517458e-06,
      "loss": 0.4875,
      "step": 33191
    },
    {
      "epoch": 1.019629527232513,
      "grad_norm": 0.39908576011657715,
      "learning_rate": 9.715871169190029e-06,
      "loss": 0.4782,
      "step": 33192
    },
    {
      "epoch": 1.0196602463674622,
      "grad_norm": 0.36509451270103455,
      "learning_rate": 9.715388087297857e-06,
      "loss": 0.5453,
      "step": 33193
    },
    {
      "epoch": 1.0196909655024116,
      "grad_norm": 0.39809978008270264,
      "learning_rate": 9.714905006070424e-06,
      "loss": 0.5168,
      "step": 33194
    },
    {
      "epoch": 1.0197216846373607,
      "grad_norm": 0.4180024564266205,
      "learning_rate": 9.714421925508841e-06,
      "loss": 0.5351,
      "step": 33195
    },
    {
      "epoch": 1.0197524037723098,
      "grad_norm": 0.4532981812953949,
      "learning_rate": 9.713938845614253e-06,
      "loss": 0.5286,
      "step": 33196
    },
    {
      "epoch": 1.019783122907259,
      "grad_norm": 0.45709455013275146,
      "learning_rate": 9.713455766387773e-06,
      "loss": 0.5354,
      "step": 33197
    },
    {
      "epoch": 1.019813842042208,
      "grad_norm": 0.4208514988422394,
      "learning_rate": 9.712972687830545e-06,
      "loss": 0.5798,
      "step": 33198
    },
    {
      "epoch": 1.0198445611771572,
      "grad_norm": 0.3799675405025482,
      "learning_rate": 9.712489609943682e-06,
      "loss": 0.4996,
      "step": 33199
    },
    {
      "epoch": 1.0198752803121065,
      "grad_norm": 0.3536839485168457,
      "learning_rate": 9.712006532728327e-06,
      "loss": 0.4438,
      "step": 33200
    },
    {
      "epoch": 1.0199059994470556,
      "grad_norm": 0.47797107696533203,
      "learning_rate": 9.711523456185597e-06,
      "loss": 0.4289,
      "step": 33201
    },
    {
      "epoch": 1.0199367185820047,
      "grad_norm": 0.3938635587692261,
      "learning_rate": 9.711040380316625e-06,
      "loss": 0.4978,
      "step": 33202
    },
    {
      "epoch": 1.0199674377169539,
      "grad_norm": 0.3715091049671173,
      "learning_rate": 9.710557305122537e-06,
      "loss": 0.5144,
      "step": 33203
    },
    {
      "epoch": 1.019998156851903,
      "grad_norm": 0.3782646059989929,
      "learning_rate": 9.710074230604463e-06,
      "loss": 0.5432,
      "step": 33204
    },
    {
      "epoch": 1.020028875986852,
      "grad_norm": 0.3945621848106384,
      "learning_rate": 9.70959115676353e-06,
      "loss": 0.4826,
      "step": 33205
    },
    {
      "epoch": 1.0200595951218014,
      "grad_norm": 0.3778330683708191,
      "learning_rate": 9.70910808360087e-06,
      "loss": 0.5378,
      "step": 33206
    },
    {
      "epoch": 1.0200903142567506,
      "grad_norm": 0.379609614610672,
      "learning_rate": 9.708625011117606e-06,
      "loss": 0.484,
      "step": 33207
    },
    {
      "epoch": 1.0201210333916997,
      "grad_norm": 0.39071422815322876,
      "learning_rate": 9.708141939314868e-06,
      "loss": 0.5185,
      "step": 33208
    },
    {
      "epoch": 1.0201517525266488,
      "grad_norm": 0.4131443500518799,
      "learning_rate": 9.707658868193787e-06,
      "loss": 0.5168,
      "step": 33209
    },
    {
      "epoch": 1.020182471661598,
      "grad_norm": 0.43338295817375183,
      "learning_rate": 9.707175797755487e-06,
      "loss": 0.4564,
      "step": 33210
    },
    {
      "epoch": 1.0202131907965473,
      "grad_norm": 0.354907363653183,
      "learning_rate": 9.7066927280011e-06,
      "loss": 0.4985,
      "step": 33211
    },
    {
      "epoch": 1.0202439099314964,
      "grad_norm": 0.4398908019065857,
      "learning_rate": 9.706209658931753e-06,
      "loss": 0.5114,
      "step": 33212
    },
    {
      "epoch": 1.0202746290664455,
      "grad_norm": 0.6690111756324768,
      "learning_rate": 9.705726590548574e-06,
      "loss": 0.4991,
      "step": 33213
    },
    {
      "epoch": 1.0203053482013946,
      "grad_norm": 0.37301644682884216,
      "learning_rate": 9.705243522852689e-06,
      "loss": 0.4773,
      "step": 33214
    },
    {
      "epoch": 1.0203360673363437,
      "grad_norm": 0.374409019947052,
      "learning_rate": 9.70476045584523e-06,
      "loss": 0.4905,
      "step": 33215
    },
    {
      "epoch": 1.0203667864712929,
      "grad_norm": 0.3831743597984314,
      "learning_rate": 9.704277389527322e-06,
      "loss": 0.5819,
      "step": 33216
    },
    {
      "epoch": 1.0203975056062422,
      "grad_norm": 0.4208642244338989,
      "learning_rate": 9.703794323900097e-06,
      "loss": 0.5234,
      "step": 33217
    },
    {
      "epoch": 1.0204282247411913,
      "grad_norm": 0.3689329922199249,
      "learning_rate": 9.70331125896468e-06,
      "loss": 0.4912,
      "step": 33218
    },
    {
      "epoch": 1.0204589438761404,
      "grad_norm": 0.39359477162361145,
      "learning_rate": 9.702828194722202e-06,
      "loss": 0.505,
      "step": 33219
    },
    {
      "epoch": 1.0204896630110896,
      "grad_norm": 0.3951911926269531,
      "learning_rate": 9.702345131173786e-06,
      "loss": 0.4833,
      "step": 33220
    },
    {
      "epoch": 1.0205203821460387,
      "grad_norm": 0.3713982403278351,
      "learning_rate": 9.701862068320567e-06,
      "loss": 0.5506,
      "step": 33221
    },
    {
      "epoch": 1.020551101280988,
      "grad_norm": 0.3830614686012268,
      "learning_rate": 9.701379006163667e-06,
      "loss": 0.4848,
      "step": 33222
    },
    {
      "epoch": 1.0205818204159371,
      "grad_norm": 0.3845013380050659,
      "learning_rate": 9.700895944704222e-06,
      "loss": 0.4986,
      "step": 33223
    },
    {
      "epoch": 1.0206125395508863,
      "grad_norm": 0.381062388420105,
      "learning_rate": 9.700412883943349e-06,
      "loss": 0.4629,
      "step": 33224
    },
    {
      "epoch": 1.0206432586858354,
      "grad_norm": 0.35843104124069214,
      "learning_rate": 9.699929823882184e-06,
      "loss": 0.4347,
      "step": 33225
    },
    {
      "epoch": 1.0206739778207845,
      "grad_norm": 0.41433343291282654,
      "learning_rate": 9.699446764521857e-06,
      "loss": 0.5247,
      "step": 33226
    },
    {
      "epoch": 1.0207046969557336,
      "grad_norm": 0.4039890170097351,
      "learning_rate": 9.69896370586349e-06,
      "loss": 0.5061,
      "step": 33227
    },
    {
      "epoch": 1.020735416090683,
      "grad_norm": 0.9852221012115479,
      "learning_rate": 9.698480647908221e-06,
      "loss": 0.5224,
      "step": 33228
    },
    {
      "epoch": 1.020766135225632,
      "grad_norm": 0.39940083026885986,
      "learning_rate": 9.697997590657163e-06,
      "loss": 0.4831,
      "step": 33229
    },
    {
      "epoch": 1.0207968543605812,
      "grad_norm": 0.3907320201396942,
      "learning_rate": 9.697514534111458e-06,
      "loss": 0.5159,
      "step": 33230
    },
    {
      "epoch": 1.0208275734955303,
      "grad_norm": 0.47826409339904785,
      "learning_rate": 9.697031478272224e-06,
      "loss": 0.5209,
      "step": 33231
    },
    {
      "epoch": 1.0208582926304794,
      "grad_norm": 0.40351518988609314,
      "learning_rate": 9.696548423140602e-06,
      "loss": 0.5368,
      "step": 33232
    },
    {
      "epoch": 1.0208890117654288,
      "grad_norm": 0.4133273661136627,
      "learning_rate": 9.696065368717704e-06,
      "loss": 0.482,
      "step": 33233
    },
    {
      "epoch": 1.020919730900378,
      "grad_norm": 0.40519949793815613,
      "learning_rate": 9.695582315004673e-06,
      "loss": 0.5209,
      "step": 33234
    },
    {
      "epoch": 1.020950450035327,
      "grad_norm": 0.3853886127471924,
      "learning_rate": 9.695099262002626e-06,
      "loss": 0.5065,
      "step": 33235
    },
    {
      "epoch": 1.0209811691702761,
      "grad_norm": 0.45348069071769714,
      "learning_rate": 9.694616209712699e-06,
      "loss": 0.4599,
      "step": 33236
    },
    {
      "epoch": 1.0210118883052253,
      "grad_norm": 0.3985898494720459,
      "learning_rate": 9.694133158136016e-06,
      "loss": 0.4661,
      "step": 33237
    },
    {
      "epoch": 1.0210426074401744,
      "grad_norm": 0.379268616437912,
      "learning_rate": 9.693650107273707e-06,
      "loss": 0.5534,
      "step": 33238
    },
    {
      "epoch": 1.0210733265751237,
      "grad_norm": 0.40730270743370056,
      "learning_rate": 9.693167057126899e-06,
      "loss": 0.519,
      "step": 33239
    },
    {
      "epoch": 1.0211040457100728,
      "grad_norm": 0.3581237494945526,
      "learning_rate": 9.692684007696722e-06,
      "loss": 0.4951,
      "step": 33240
    },
    {
      "epoch": 1.021134764845022,
      "grad_norm": 0.41013312339782715,
      "learning_rate": 9.692200958984301e-06,
      "loss": 0.5066,
      "step": 33241
    },
    {
      "epoch": 1.021165483979971,
      "grad_norm": 0.41018691658973694,
      "learning_rate": 9.691717910990766e-06,
      "loss": 0.5183,
      "step": 33242
    },
    {
      "epoch": 1.0211962031149202,
      "grad_norm": 0.4043945372104645,
      "learning_rate": 9.691234863717246e-06,
      "loss": 0.5538,
      "step": 33243
    },
    {
      "epoch": 1.0212269222498696,
      "grad_norm": 0.3784068524837494,
      "learning_rate": 9.690751817164868e-06,
      "loss": 0.4784,
      "step": 33244
    },
    {
      "epoch": 1.0212576413848187,
      "grad_norm": 0.484662264585495,
      "learning_rate": 9.690268771334762e-06,
      "loss": 0.5963,
      "step": 33245
    },
    {
      "epoch": 1.0212883605197678,
      "grad_norm": 0.4051731824874878,
      "learning_rate": 9.689785726228054e-06,
      "loss": 0.5515,
      "step": 33246
    },
    {
      "epoch": 1.021319079654717,
      "grad_norm": 0.4027006924152374,
      "learning_rate": 9.689302681845874e-06,
      "loss": 0.514,
      "step": 33247
    },
    {
      "epoch": 1.021349798789666,
      "grad_norm": 0.36161184310913086,
      "learning_rate": 9.688819638189349e-06,
      "loss": 0.5304,
      "step": 33248
    },
    {
      "epoch": 1.0213805179246151,
      "grad_norm": 0.37236642837524414,
      "learning_rate": 9.688336595259607e-06,
      "loss": 0.52,
      "step": 33249
    },
    {
      "epoch": 1.0214112370595645,
      "grad_norm": 0.36945840716362,
      "learning_rate": 9.687853553057777e-06,
      "loss": 0.4969,
      "step": 33250
    },
    {
      "epoch": 1.0214419561945136,
      "grad_norm": 0.38000550866127014,
      "learning_rate": 9.687370511584987e-06,
      "loss": 0.5201,
      "step": 33251
    },
    {
      "epoch": 1.0214726753294627,
      "grad_norm": 0.41684889793395996,
      "learning_rate": 9.686887470842362e-06,
      "loss": 0.5344,
      "step": 33252
    },
    {
      "epoch": 1.0215033944644119,
      "grad_norm": 0.3837417960166931,
      "learning_rate": 9.686404430831039e-06,
      "loss": 0.474,
      "step": 33253
    },
    {
      "epoch": 1.021534113599361,
      "grad_norm": 0.4456336498260498,
      "learning_rate": 9.685921391552136e-06,
      "loss": 0.5483,
      "step": 33254
    },
    {
      "epoch": 1.02156483273431,
      "grad_norm": 0.4290299117565155,
      "learning_rate": 9.685438353006787e-06,
      "loss": 0.5025,
      "step": 33255
    },
    {
      "epoch": 1.0215955518692594,
      "grad_norm": 0.4205642640590668,
      "learning_rate": 9.684955315196118e-06,
      "loss": 0.5277,
      "step": 33256
    },
    {
      "epoch": 1.0216262710042086,
      "grad_norm": 0.39163491129875183,
      "learning_rate": 9.684472278121263e-06,
      "loss": 0.5585,
      "step": 33257
    },
    {
      "epoch": 1.0216569901391577,
      "grad_norm": 0.3377537429332733,
      "learning_rate": 9.683989241783336e-06,
      "loss": 0.4984,
      "step": 33258
    },
    {
      "epoch": 1.0216877092741068,
      "grad_norm": 0.4134657382965088,
      "learning_rate": 9.683506206183482e-06,
      "loss": 0.5047,
      "step": 33259
    },
    {
      "epoch": 1.021718428409056,
      "grad_norm": 0.40050554275512695,
      "learning_rate": 9.683023171322815e-06,
      "loss": 0.4189,
      "step": 33260
    },
    {
      "epoch": 1.0217491475440053,
      "grad_norm": 0.39267003536224365,
      "learning_rate": 9.68254013720247e-06,
      "loss": 0.5054,
      "step": 33261
    },
    {
      "epoch": 1.0217798666789544,
      "grad_norm": 0.3563804030418396,
      "learning_rate": 9.682057103823579e-06,
      "loss": 0.4968,
      "step": 33262
    },
    {
      "epoch": 1.0218105858139035,
      "grad_norm": 0.3952100872993469,
      "learning_rate": 9.681574071187262e-06,
      "loss": 0.5699,
      "step": 33263
    },
    {
      "epoch": 1.0218413049488526,
      "grad_norm": 0.3960922956466675,
      "learning_rate": 9.681091039294658e-06,
      "loss": 0.5437,
      "step": 33264
    },
    {
      "epoch": 1.0218720240838017,
      "grad_norm": 0.419157475233078,
      "learning_rate": 9.680608008146878e-06,
      "loss": 0.4296,
      "step": 33265
    },
    {
      "epoch": 1.0219027432187509,
      "grad_norm": 0.3741406202316284,
      "learning_rate": 9.68012497774507e-06,
      "loss": 0.5394,
      "step": 33266
    },
    {
      "epoch": 1.0219334623537002,
      "grad_norm": 0.4289803206920624,
      "learning_rate": 9.679641948090344e-06,
      "loss": 0.5426,
      "step": 33267
    },
    {
      "epoch": 1.0219641814886493,
      "grad_norm": 0.3545558750629425,
      "learning_rate": 9.679158919183844e-06,
      "loss": 0.53,
      "step": 33268
    },
    {
      "epoch": 1.0219949006235984,
      "grad_norm": 0.6115617156028748,
      "learning_rate": 9.678675891026686e-06,
      "loss": 0.5281,
      "step": 33269
    },
    {
      "epoch": 1.0220256197585476,
      "grad_norm": 0.3650645613670349,
      "learning_rate": 9.678192863620007e-06,
      "loss": 0.4548,
      "step": 33270
    },
    {
      "epoch": 1.0220563388934967,
      "grad_norm": 0.4277181625366211,
      "learning_rate": 9.677709836964926e-06,
      "loss": 0.5085,
      "step": 33271
    },
    {
      "epoch": 1.022087058028446,
      "grad_norm": 0.3671046793460846,
      "learning_rate": 9.67722681106258e-06,
      "loss": 0.4369,
      "step": 33272
    },
    {
      "epoch": 1.0221177771633951,
      "grad_norm": 0.3978177011013031,
      "learning_rate": 9.67674378591409e-06,
      "loss": 0.5094,
      "step": 33273
    },
    {
      "epoch": 1.0221484962983443,
      "grad_norm": 0.3835834860801697,
      "learning_rate": 9.67626076152059e-06,
      "loss": 0.5422,
      "step": 33274
    },
    {
      "epoch": 1.0221792154332934,
      "grad_norm": 0.38421347737312317,
      "learning_rate": 9.675777737883204e-06,
      "loss": 0.5213,
      "step": 33275
    },
    {
      "epoch": 1.0222099345682425,
      "grad_norm": 0.4259081482887268,
      "learning_rate": 9.675294715003064e-06,
      "loss": 0.5221,
      "step": 33276
    },
    {
      "epoch": 1.0222406537031916,
      "grad_norm": 0.36766526103019714,
      "learning_rate": 9.674811692881293e-06,
      "loss": 0.4542,
      "step": 33277
    },
    {
      "epoch": 1.022271372838141,
      "grad_norm": 0.37603598833084106,
      "learning_rate": 9.674328671519025e-06,
      "loss": 0.4998,
      "step": 33278
    },
    {
      "epoch": 1.02230209197309,
      "grad_norm": 0.3752067983150482,
      "learning_rate": 9.673845650917381e-06,
      "loss": 0.487,
      "step": 33279
    },
    {
      "epoch": 1.0223328111080392,
      "grad_norm": 0.40434613823890686,
      "learning_rate": 9.673362631077495e-06,
      "loss": 0.5323,
      "step": 33280
    },
    {
      "epoch": 1.0223635302429883,
      "grad_norm": 0.3741978704929352,
      "learning_rate": 9.672879612000496e-06,
      "loss": 0.4764,
      "step": 33281
    },
    {
      "epoch": 1.0223942493779374,
      "grad_norm": 0.3575175404548645,
      "learning_rate": 9.672396593687507e-06,
      "loss": 0.539,
      "step": 33282
    },
    {
      "epoch": 1.0224249685128868,
      "grad_norm": 0.4551032781600952,
      "learning_rate": 9.67191357613966e-06,
      "loss": 0.5336,
      "step": 33283
    },
    {
      "epoch": 1.022455687647836,
      "grad_norm": 0.43149933218955994,
      "learning_rate": 9.67143055935808e-06,
      "loss": 0.5823,
      "step": 33284
    },
    {
      "epoch": 1.022486406782785,
      "grad_norm": 0.446709007024765,
      "learning_rate": 9.6709475433439e-06,
      "loss": 0.52,
      "step": 33285
    },
    {
      "epoch": 1.0225171259177341,
      "grad_norm": 0.399300754070282,
      "learning_rate": 9.67046452809824e-06,
      "loss": 0.5608,
      "step": 33286
    },
    {
      "epoch": 1.0225478450526833,
      "grad_norm": 0.3961450457572937,
      "learning_rate": 9.669981513622238e-06,
      "loss": 0.4317,
      "step": 33287
    },
    {
      "epoch": 1.0225785641876324,
      "grad_norm": 0.372596800327301,
      "learning_rate": 9.669498499917013e-06,
      "loss": 0.4276,
      "step": 33288
    },
    {
      "epoch": 1.0226092833225817,
      "grad_norm": 0.34845104813575745,
      "learning_rate": 9.669015486983701e-06,
      "loss": 0.501,
      "step": 33289
    },
    {
      "epoch": 1.0226400024575308,
      "grad_norm": 0.3647650480270386,
      "learning_rate": 9.668532474823424e-06,
      "loss": 0.5521,
      "step": 33290
    },
    {
      "epoch": 1.02267072159248,
      "grad_norm": 0.4217427968978882,
      "learning_rate": 9.668049463437316e-06,
      "loss": 0.4845,
      "step": 33291
    },
    {
      "epoch": 1.022701440727429,
      "grad_norm": 0.37509071826934814,
      "learning_rate": 9.667566452826498e-06,
      "loss": 0.5275,
      "step": 33292
    },
    {
      "epoch": 1.0227321598623782,
      "grad_norm": 0.3910379409790039,
      "learning_rate": 9.667083442992105e-06,
      "loss": 0.5099,
      "step": 33293
    },
    {
      "epoch": 1.0227628789973275,
      "grad_norm": 0.3577229082584381,
      "learning_rate": 9.666600433935258e-06,
      "loss": 0.4793,
      "step": 33294
    },
    {
      "epoch": 1.0227935981322767,
      "grad_norm": 0.38416239619255066,
      "learning_rate": 9.666117425657094e-06,
      "loss": 0.4611,
      "step": 33295
    },
    {
      "epoch": 1.0228243172672258,
      "grad_norm": 0.42689281702041626,
      "learning_rate": 9.665634418158728e-06,
      "loss": 0.5487,
      "step": 33296
    },
    {
      "epoch": 1.022855036402175,
      "grad_norm": 0.3660314381122589,
      "learning_rate": 9.665151411441305e-06,
      "loss": 0.4584,
      "step": 33297
    },
    {
      "epoch": 1.022885755537124,
      "grad_norm": 0.4360458552837372,
      "learning_rate": 9.664668405505941e-06,
      "loss": 0.5513,
      "step": 33298
    },
    {
      "epoch": 1.0229164746720731,
      "grad_norm": 0.39943546056747437,
      "learning_rate": 9.664185400353763e-06,
      "loss": 0.4976,
      "step": 33299
    },
    {
      "epoch": 1.0229471938070225,
      "grad_norm": 0.34358590841293335,
      "learning_rate": 9.66370239598591e-06,
      "loss": 0.4802,
      "step": 33300
    },
    {
      "epoch": 1.0229779129419716,
      "grad_norm": 0.3868047893047333,
      "learning_rate": 9.663219392403498e-06,
      "loss": 0.4674,
      "step": 33301
    },
    {
      "epoch": 1.0230086320769207,
      "grad_norm": 0.43209564685821533,
      "learning_rate": 9.662736389607666e-06,
      "loss": 0.4381,
      "step": 33302
    },
    {
      "epoch": 1.0230393512118698,
      "grad_norm": 0.42430379986763,
      "learning_rate": 9.662253387599531e-06,
      "loss": 0.4744,
      "step": 33303
    },
    {
      "epoch": 1.023070070346819,
      "grad_norm": 0.37384936213493347,
      "learning_rate": 9.661770386380234e-06,
      "loss": 0.4829,
      "step": 33304
    },
    {
      "epoch": 1.0231007894817683,
      "grad_norm": 0.4016823470592499,
      "learning_rate": 9.66128738595089e-06,
      "loss": 0.5021,
      "step": 33305
    },
    {
      "epoch": 1.0231315086167174,
      "grad_norm": 0.39456942677497864,
      "learning_rate": 9.660804386312635e-06,
      "loss": 0.5223,
      "step": 33306
    },
    {
      "epoch": 1.0231622277516665,
      "grad_norm": 0.3724276125431061,
      "learning_rate": 9.660321387466594e-06,
      "loss": 0.5326,
      "step": 33307
    },
    {
      "epoch": 1.0231929468866157,
      "grad_norm": 0.46052512526512146,
      "learning_rate": 9.659838389413898e-06,
      "loss": 0.5375,
      "step": 33308
    },
    {
      "epoch": 1.0232236660215648,
      "grad_norm": 0.5276495814323425,
      "learning_rate": 9.659355392155671e-06,
      "loss": 0.6121,
      "step": 33309
    },
    {
      "epoch": 1.023254385156514,
      "grad_norm": 0.4044646918773651,
      "learning_rate": 9.658872395693046e-06,
      "loss": 0.4366,
      "step": 33310
    },
    {
      "epoch": 1.0232851042914632,
      "grad_norm": 0.45840150117874146,
      "learning_rate": 9.658389400027144e-06,
      "loss": 0.509,
      "step": 33311
    },
    {
      "epoch": 1.0233158234264124,
      "grad_norm": 0.4579474627971649,
      "learning_rate": 9.657906405159104e-06,
      "loss": 0.5119,
      "step": 33312
    },
    {
      "epoch": 1.0233465425613615,
      "grad_norm": 0.4162417948246002,
      "learning_rate": 9.65742341109004e-06,
      "loss": 0.5327,
      "step": 33313
    },
    {
      "epoch": 1.0233772616963106,
      "grad_norm": 0.4206759035587311,
      "learning_rate": 9.656940417821094e-06,
      "loss": 0.5204,
      "step": 33314
    },
    {
      "epoch": 1.0234079808312597,
      "grad_norm": 0.38974234461784363,
      "learning_rate": 9.656457425353382e-06,
      "loss": 0.521,
      "step": 33315
    },
    {
      "epoch": 1.0234386999662088,
      "grad_norm": 0.38173896074295044,
      "learning_rate": 9.655974433688041e-06,
      "loss": 0.4977,
      "step": 33316
    },
    {
      "epoch": 1.0234694191011582,
      "grad_norm": 0.37650132179260254,
      "learning_rate": 9.655491442826195e-06,
      "loss": 0.4402,
      "step": 33317
    },
    {
      "epoch": 1.0235001382361073,
      "grad_norm": 0.4435749650001526,
      "learning_rate": 9.655008452768972e-06,
      "loss": 0.571,
      "step": 33318
    },
    {
      "epoch": 1.0235308573710564,
      "grad_norm": 0.3764971196651459,
      "learning_rate": 9.654525463517503e-06,
      "loss": 0.5761,
      "step": 33319
    },
    {
      "epoch": 1.0235615765060055,
      "grad_norm": 0.38790836930274963,
      "learning_rate": 9.654042475072912e-06,
      "loss": 0.5908,
      "step": 33320
    },
    {
      "epoch": 1.0235922956409547,
      "grad_norm": 0.38933268189430237,
      "learning_rate": 9.65355948743633e-06,
      "loss": 0.5185,
      "step": 33321
    },
    {
      "epoch": 1.023623014775904,
      "grad_norm": 0.3666721284389496,
      "learning_rate": 9.653076500608883e-06,
      "loss": 0.4665,
      "step": 33322
    },
    {
      "epoch": 1.0236537339108531,
      "grad_norm": 0.3797910213470459,
      "learning_rate": 9.652593514591703e-06,
      "loss": 0.4134,
      "step": 33323
    },
    {
      "epoch": 1.0236844530458022,
      "grad_norm": 0.4058994948863983,
      "learning_rate": 9.652110529385911e-06,
      "loss": 0.5708,
      "step": 33324
    },
    {
      "epoch": 1.0237151721807514,
      "grad_norm": 0.39636486768722534,
      "learning_rate": 9.651627544992643e-06,
      "loss": 0.4602,
      "step": 33325
    },
    {
      "epoch": 1.0237458913157005,
      "grad_norm": 0.35492491722106934,
      "learning_rate": 9.65114456141302e-06,
      "loss": 0.4356,
      "step": 33326
    },
    {
      "epoch": 1.0237766104506496,
      "grad_norm": 0.3549976050853729,
      "learning_rate": 9.650661578648177e-06,
      "loss": 0.5754,
      "step": 33327
    },
    {
      "epoch": 1.023807329585599,
      "grad_norm": 0.410519003868103,
      "learning_rate": 9.650178596699232e-06,
      "loss": 0.4671,
      "step": 33328
    },
    {
      "epoch": 1.023838048720548,
      "grad_norm": 0.4330325424671173,
      "learning_rate": 9.649695615567327e-06,
      "loss": 0.528,
      "step": 33329
    },
    {
      "epoch": 1.0238687678554972,
      "grad_norm": 0.3400406837463379,
      "learning_rate": 9.649212635253575e-06,
      "loss": 0.4987,
      "step": 33330
    },
    {
      "epoch": 1.0238994869904463,
      "grad_norm": 0.36738160252571106,
      "learning_rate": 9.648729655759119e-06,
      "loss": 0.498,
      "step": 33331
    },
    {
      "epoch": 1.0239302061253954,
      "grad_norm": 0.369961678981781,
      "learning_rate": 9.648246677085071e-06,
      "loss": 0.5213,
      "step": 33332
    },
    {
      "epoch": 1.0239609252603448,
      "grad_norm": 0.40385690331459045,
      "learning_rate": 9.647763699232576e-06,
      "loss": 0.4981,
      "step": 33333
    },
    {
      "epoch": 1.0239916443952939,
      "grad_norm": 0.3953475058078766,
      "learning_rate": 9.647280722202748e-06,
      "loss": 0.5095,
      "step": 33334
    },
    {
      "epoch": 1.024022363530243,
      "grad_norm": 0.41146236658096313,
      "learning_rate": 9.646797745996718e-06,
      "loss": 0.5069,
      "step": 33335
    },
    {
      "epoch": 1.0240530826651921,
      "grad_norm": 0.3627711236476898,
      "learning_rate": 9.646314770615623e-06,
      "loss": 0.5123,
      "step": 33336
    },
    {
      "epoch": 1.0240838018001412,
      "grad_norm": 0.4627808630466461,
      "learning_rate": 9.645831796060578e-06,
      "loss": 0.5952,
      "step": 33337
    },
    {
      "epoch": 1.0241145209350904,
      "grad_norm": 0.5064405202865601,
      "learning_rate": 9.645348822332725e-06,
      "loss": 0.4974,
      "step": 33338
    },
    {
      "epoch": 1.0241452400700397,
      "grad_norm": 0.3647824227809906,
      "learning_rate": 9.64486584943318e-06,
      "loss": 0.4746,
      "step": 33339
    },
    {
      "epoch": 1.0241759592049888,
      "grad_norm": 0.3845549523830414,
      "learning_rate": 9.644382877363077e-06,
      "loss": 0.5437,
      "step": 33340
    },
    {
      "epoch": 1.024206678339938,
      "grad_norm": 0.3609982132911682,
      "learning_rate": 9.643899906123541e-06,
      "loss": 0.4747,
      "step": 33341
    },
    {
      "epoch": 1.024237397474887,
      "grad_norm": 0.4390055537223816,
      "learning_rate": 9.643416935715705e-06,
      "loss": 0.5334,
      "step": 33342
    },
    {
      "epoch": 1.0242681166098362,
      "grad_norm": 1.5710242986679077,
      "learning_rate": 9.64293396614069e-06,
      "loss": 0.4875,
      "step": 33343
    },
    {
      "epoch": 1.0242988357447855,
      "grad_norm": 0.35380515456199646,
      "learning_rate": 9.64245099739963e-06,
      "loss": 0.4724,
      "step": 33344
    },
    {
      "epoch": 1.0243295548797346,
      "grad_norm": 0.3902585506439209,
      "learning_rate": 9.64196802949365e-06,
      "loss": 0.4756,
      "step": 33345
    },
    {
      "epoch": 1.0243602740146838,
      "grad_norm": 0.44064202904701233,
      "learning_rate": 9.641485062423878e-06,
      "loss": 0.5118,
      "step": 33346
    },
    {
      "epoch": 1.024390993149633,
      "grad_norm": 0.4034018814563751,
      "learning_rate": 9.641002096191444e-06,
      "loss": 0.5554,
      "step": 33347
    },
    {
      "epoch": 1.024421712284582,
      "grad_norm": 0.3730049431324005,
      "learning_rate": 9.640519130797473e-06,
      "loss": 0.4669,
      "step": 33348
    },
    {
      "epoch": 1.0244524314195311,
      "grad_norm": 0.3868698179721832,
      "learning_rate": 9.640036166243095e-06,
      "loss": 0.4973,
      "step": 33349
    },
    {
      "epoch": 1.0244831505544805,
      "grad_norm": 0.3795906901359558,
      "learning_rate": 9.63955320252944e-06,
      "loss": 0.5206,
      "step": 33350
    },
    {
      "epoch": 1.0245138696894296,
      "grad_norm": 0.39630576968193054,
      "learning_rate": 9.63907023965763e-06,
      "loss": 0.4733,
      "step": 33351
    },
    {
      "epoch": 1.0245445888243787,
      "grad_norm": 0.33996281027793884,
      "learning_rate": 9.6385872776288e-06,
      "loss": 0.4491,
      "step": 33352
    },
    {
      "epoch": 1.0245753079593278,
      "grad_norm": 0.3913906216621399,
      "learning_rate": 9.638104316444072e-06,
      "loss": 0.4727,
      "step": 33353
    },
    {
      "epoch": 1.024606027094277,
      "grad_norm": 0.42174866795539856,
      "learning_rate": 9.637621356104575e-06,
      "loss": 0.4503,
      "step": 33354
    },
    {
      "epoch": 1.0246367462292263,
      "grad_norm": 0.39899247884750366,
      "learning_rate": 9.637138396611445e-06,
      "loss": 0.4827,
      "step": 33355
    },
    {
      "epoch": 1.0246674653641754,
      "grad_norm": 0.40237492322921753,
      "learning_rate": 9.636655437965798e-06,
      "loss": 0.4352,
      "step": 33356
    },
    {
      "epoch": 1.0246981844991245,
      "grad_norm": 0.3622012436389923,
      "learning_rate": 9.63617248016877e-06,
      "loss": 0.5283,
      "step": 33357
    },
    {
      "epoch": 1.0247289036340737,
      "grad_norm": 0.37063929438591003,
      "learning_rate": 9.635689523221486e-06,
      "loss": 0.4998,
      "step": 33358
    },
    {
      "epoch": 1.0247596227690228,
      "grad_norm": 0.4077414274215698,
      "learning_rate": 9.635206567125076e-06,
      "loss": 0.5457,
      "step": 33359
    },
    {
      "epoch": 1.024790341903972,
      "grad_norm": 0.3823511600494385,
      "learning_rate": 9.634723611880664e-06,
      "loss": 0.4964,
      "step": 33360
    },
    {
      "epoch": 1.0248210610389212,
      "grad_norm": 0.3663158118724823,
      "learning_rate": 9.634240657489384e-06,
      "loss": 0.4672,
      "step": 33361
    },
    {
      "epoch": 1.0248517801738704,
      "grad_norm": 0.37407028675079346,
      "learning_rate": 9.633757703952355e-06,
      "loss": 0.4928,
      "step": 33362
    },
    {
      "epoch": 1.0248824993088195,
      "grad_norm": 0.34007856249809265,
      "learning_rate": 9.633274751270718e-06,
      "loss": 0.4804,
      "step": 33363
    },
    {
      "epoch": 1.0249132184437686,
      "grad_norm": 0.41682538390159607,
      "learning_rate": 9.632791799445585e-06,
      "loss": 0.5022,
      "step": 33364
    },
    {
      "epoch": 1.0249439375787177,
      "grad_norm": 0.3768748342990875,
      "learning_rate": 9.6323088484781e-06,
      "loss": 0.4872,
      "step": 33365
    },
    {
      "epoch": 1.0249746567136668,
      "grad_norm": 0.3727400004863739,
      "learning_rate": 9.631825898369378e-06,
      "loss": 0.4926,
      "step": 33366
    },
    {
      "epoch": 1.0250053758486162,
      "grad_norm": 0.3944089114665985,
      "learning_rate": 9.631342949120557e-06,
      "loss": 0.5873,
      "step": 33367
    },
    {
      "epoch": 1.0250360949835653,
      "grad_norm": 0.3991028368473053,
      "learning_rate": 9.630860000732756e-06,
      "loss": 0.4639,
      "step": 33368
    },
    {
      "epoch": 1.0250668141185144,
      "grad_norm": 0.45962199568748474,
      "learning_rate": 9.63037705320711e-06,
      "loss": 0.5334,
      "step": 33369
    },
    {
      "epoch": 1.0250975332534635,
      "grad_norm": 0.4010620415210724,
      "learning_rate": 9.629894106544743e-06,
      "loss": 0.4243,
      "step": 33370
    },
    {
      "epoch": 1.0251282523884127,
      "grad_norm": 0.3548051118850708,
      "learning_rate": 9.62941116074678e-06,
      "loss": 0.4339,
      "step": 33371
    },
    {
      "epoch": 1.025158971523362,
      "grad_norm": 0.3901346027851105,
      "learning_rate": 9.628928215814361e-06,
      "loss": 0.4851,
      "step": 33372
    },
    {
      "epoch": 1.0251896906583111,
      "grad_norm": 0.3630383312702179,
      "learning_rate": 9.628445271748599e-06,
      "loss": 0.4752,
      "step": 33373
    },
    {
      "epoch": 1.0252204097932602,
      "grad_norm": 0.43651697039604187,
      "learning_rate": 9.627962328550635e-06,
      "loss": 0.5139,
      "step": 33374
    },
    {
      "epoch": 1.0252511289282094,
      "grad_norm": 0.37020695209503174,
      "learning_rate": 9.627479386221587e-06,
      "loss": 0.4563,
      "step": 33375
    },
    {
      "epoch": 1.0252818480631585,
      "grad_norm": 0.36566415429115295,
      "learning_rate": 9.626996444762591e-06,
      "loss": 0.4874,
      "step": 33376
    },
    {
      "epoch": 1.0253125671981076,
      "grad_norm": 0.4315047562122345,
      "learning_rate": 9.626513504174767e-06,
      "loss": 0.5236,
      "step": 33377
    },
    {
      "epoch": 1.025343286333057,
      "grad_norm": 0.39066699147224426,
      "learning_rate": 9.626030564459249e-06,
      "loss": 0.4945,
      "step": 33378
    },
    {
      "epoch": 1.025374005468006,
      "grad_norm": 0.38546574115753174,
      "learning_rate": 9.625547625617159e-06,
      "loss": 0.4731,
      "step": 33379
    },
    {
      "epoch": 1.0254047246029552,
      "grad_norm": 0.4637537896633148,
      "learning_rate": 9.625064687649633e-06,
      "loss": 0.4225,
      "step": 33380
    },
    {
      "epoch": 1.0254354437379043,
      "grad_norm": 0.35922685265541077,
      "learning_rate": 9.624581750557793e-06,
      "loss": 0.4665,
      "step": 33381
    },
    {
      "epoch": 1.0254661628728534,
      "grad_norm": 0.40064096450805664,
      "learning_rate": 9.624098814342769e-06,
      "loss": 0.5064,
      "step": 33382
    },
    {
      "epoch": 1.0254968820078028,
      "grad_norm": 0.35966822504997253,
      "learning_rate": 9.623615879005686e-06,
      "loss": 0.5232,
      "step": 33383
    },
    {
      "epoch": 1.0255276011427519,
      "grad_norm": 0.34459811449050903,
      "learning_rate": 9.623132944547678e-06,
      "loss": 0.4144,
      "step": 33384
    },
    {
      "epoch": 1.025558320277701,
      "grad_norm": 0.3595855236053467,
      "learning_rate": 9.622650010969868e-06,
      "loss": 0.4913,
      "step": 33385
    },
    {
      "epoch": 1.0255890394126501,
      "grad_norm": 0.38971710205078125,
      "learning_rate": 9.622167078273385e-06,
      "loss": 0.5693,
      "step": 33386
    },
    {
      "epoch": 1.0256197585475992,
      "grad_norm": 0.38556185364723206,
      "learning_rate": 9.621684146459357e-06,
      "loss": 0.567,
      "step": 33387
    },
    {
      "epoch": 1.0256504776825484,
      "grad_norm": 0.40497756004333496,
      "learning_rate": 9.621201215528912e-06,
      "loss": 0.4781,
      "step": 33388
    },
    {
      "epoch": 1.0256811968174977,
      "grad_norm": 0.38642045855522156,
      "learning_rate": 9.620718285483177e-06,
      "loss": 0.4765,
      "step": 33389
    },
    {
      "epoch": 1.0257119159524468,
      "grad_norm": 0.3676644265651703,
      "learning_rate": 9.62023535632328e-06,
      "loss": 0.4484,
      "step": 33390
    },
    {
      "epoch": 1.025742635087396,
      "grad_norm": 0.3903476297855377,
      "learning_rate": 9.619752428050354e-06,
      "loss": 0.4803,
      "step": 33391
    },
    {
      "epoch": 1.025773354222345,
      "grad_norm": 0.4050379991531372,
      "learning_rate": 9.61926950066552e-06,
      "loss": 0.5311,
      "step": 33392
    },
    {
      "epoch": 1.0258040733572942,
      "grad_norm": 0.3815571069717407,
      "learning_rate": 9.61878657416991e-06,
      "loss": 0.4675,
      "step": 33393
    },
    {
      "epoch": 1.0258347924922435,
      "grad_norm": 0.40175577998161316,
      "learning_rate": 9.61830364856465e-06,
      "loss": 0.4875,
      "step": 33394
    },
    {
      "epoch": 1.0258655116271926,
      "grad_norm": 0.33746397495269775,
      "learning_rate": 9.61782072385087e-06,
      "loss": 0.4718,
      "step": 33395
    },
    {
      "epoch": 1.0258962307621418,
      "grad_norm": 0.34640923142433167,
      "learning_rate": 9.617337800029693e-06,
      "loss": 0.4228,
      "step": 33396
    },
    {
      "epoch": 1.0259269498970909,
      "grad_norm": 0.37381038069725037,
      "learning_rate": 9.616854877102255e-06,
      "loss": 0.4861,
      "step": 33397
    },
    {
      "epoch": 1.02595766903204,
      "grad_norm": 0.4050646424293518,
      "learning_rate": 9.616371955069673e-06,
      "loss": 0.5316,
      "step": 33398
    },
    {
      "epoch": 1.0259883881669891,
      "grad_norm": 0.38922879099845886,
      "learning_rate": 9.615889033933087e-06,
      "loss": 0.5175,
      "step": 33399
    },
    {
      "epoch": 1.0260191073019385,
      "grad_norm": 0.348446249961853,
      "learning_rate": 9.615406113693615e-06,
      "loss": 0.5056,
      "step": 33400
    },
    {
      "epoch": 1.0260498264368876,
      "grad_norm": 0.4153062701225281,
      "learning_rate": 9.614923194352394e-06,
      "loss": 0.5623,
      "step": 33401
    },
    {
      "epoch": 1.0260805455718367,
      "grad_norm": 0.3604893684387207,
      "learning_rate": 9.614440275910542e-06,
      "loss": 0.4686,
      "step": 33402
    },
    {
      "epoch": 1.0261112647067858,
      "grad_norm": 0.36731207370758057,
      "learning_rate": 9.613957358369193e-06,
      "loss": 0.5049,
      "step": 33403
    },
    {
      "epoch": 1.026141983841735,
      "grad_norm": 0.39077863097190857,
      "learning_rate": 9.613474441729472e-06,
      "loss": 0.4882,
      "step": 33404
    },
    {
      "epoch": 1.0261727029766843,
      "grad_norm": 0.3976578712463379,
      "learning_rate": 9.612991525992511e-06,
      "loss": 0.4931,
      "step": 33405
    },
    {
      "epoch": 1.0262034221116334,
      "grad_norm": 0.39343124628067017,
      "learning_rate": 9.612508611159433e-06,
      "loss": 0.5062,
      "step": 33406
    },
    {
      "epoch": 1.0262341412465825,
      "grad_norm": 0.4709831476211548,
      "learning_rate": 9.612025697231366e-06,
      "loss": 0.4963,
      "step": 33407
    },
    {
      "epoch": 1.0262648603815316,
      "grad_norm": 0.3886103928089142,
      "learning_rate": 9.611542784209446e-06,
      "loss": 0.4798,
      "step": 33408
    },
    {
      "epoch": 1.0262955795164808,
      "grad_norm": 0.3459004759788513,
      "learning_rate": 9.611059872094792e-06,
      "loss": 0.5201,
      "step": 33409
    },
    {
      "epoch": 1.0263262986514299,
      "grad_norm": 0.4103408455848694,
      "learning_rate": 9.610576960888536e-06,
      "loss": 0.5641,
      "step": 33410
    },
    {
      "epoch": 1.0263570177863792,
      "grad_norm": 0.40661802887916565,
      "learning_rate": 9.610094050591802e-06,
      "loss": 0.55,
      "step": 33411
    },
    {
      "epoch": 1.0263877369213283,
      "grad_norm": 0.37397804856300354,
      "learning_rate": 9.609611141205724e-06,
      "loss": 0.4796,
      "step": 33412
    },
    {
      "epoch": 1.0264184560562775,
      "grad_norm": 0.39877915382385254,
      "learning_rate": 9.609128232731424e-06,
      "loss": 0.5399,
      "step": 33413
    },
    {
      "epoch": 1.0264491751912266,
      "grad_norm": 0.34956756234169006,
      "learning_rate": 9.608645325170036e-06,
      "loss": 0.4694,
      "step": 33414
    },
    {
      "epoch": 1.0264798943261757,
      "grad_norm": 0.35252881050109863,
      "learning_rate": 9.608162418522679e-06,
      "loss": 0.519,
      "step": 33415
    },
    {
      "epoch": 1.026510613461125,
      "grad_norm": 0.42202290892601013,
      "learning_rate": 9.607679512790489e-06,
      "loss": 0.5437,
      "step": 33416
    },
    {
      "epoch": 1.0265413325960742,
      "grad_norm": 0.383163183927536,
      "learning_rate": 9.607196607974589e-06,
      "loss": 0.5211,
      "step": 33417
    },
    {
      "epoch": 1.0265720517310233,
      "grad_norm": 0.3785974085330963,
      "learning_rate": 9.606713704076111e-06,
      "loss": 0.508,
      "step": 33418
    },
    {
      "epoch": 1.0266027708659724,
      "grad_norm": 0.33065980672836304,
      "learning_rate": 9.606230801096179e-06,
      "loss": 0.4511,
      "step": 33419
    },
    {
      "epoch": 1.0266334900009215,
      "grad_norm": 0.3337951600551605,
      "learning_rate": 9.605747899035924e-06,
      "loss": 0.4869,
      "step": 33420
    },
    {
      "epoch": 1.0266642091358706,
      "grad_norm": 0.33869171142578125,
      "learning_rate": 9.60526499789647e-06,
      "loss": 0.5155,
      "step": 33421
    },
    {
      "epoch": 1.02669492827082,
      "grad_norm": 0.4371293783187866,
      "learning_rate": 9.60478209767895e-06,
      "loss": 0.4758,
      "step": 33422
    },
    {
      "epoch": 1.026725647405769,
      "grad_norm": 0.3801507353782654,
      "learning_rate": 9.604299198384487e-06,
      "loss": 0.4427,
      "step": 33423
    },
    {
      "epoch": 1.0267563665407182,
      "grad_norm": 0.4954855144023895,
      "learning_rate": 9.603816300014215e-06,
      "loss": 0.4588,
      "step": 33424
    },
    {
      "epoch": 1.0267870856756673,
      "grad_norm": 0.3884853422641754,
      "learning_rate": 9.603333402569251e-06,
      "loss": 0.4975,
      "step": 33425
    },
    {
      "epoch": 1.0268178048106165,
      "grad_norm": 0.3698611557483673,
      "learning_rate": 9.602850506050731e-06,
      "loss": 0.5124,
      "step": 33426
    },
    {
      "epoch": 1.0268485239455658,
      "grad_norm": 0.35102173686027527,
      "learning_rate": 9.602367610459784e-06,
      "loss": 0.4858,
      "step": 33427
    },
    {
      "epoch": 1.026879243080515,
      "grad_norm": 0.3905712962150574,
      "learning_rate": 9.601884715797533e-06,
      "loss": 0.5385,
      "step": 33428
    },
    {
      "epoch": 1.026909962215464,
      "grad_norm": 0.4207044243812561,
      "learning_rate": 9.601401822065112e-06,
      "loss": 0.4638,
      "step": 33429
    },
    {
      "epoch": 1.0269406813504132,
      "grad_norm": 0.3774755597114563,
      "learning_rate": 9.60091892926364e-06,
      "loss": 0.5297,
      "step": 33430
    },
    {
      "epoch": 1.0269714004853623,
      "grad_norm": 0.4218906760215759,
      "learning_rate": 9.600436037394255e-06,
      "loss": 0.4963,
      "step": 33431
    },
    {
      "epoch": 1.0270021196203114,
      "grad_norm": 0.39828306436538696,
      "learning_rate": 9.599953146458074e-06,
      "loss": 0.5096,
      "step": 33432
    },
    {
      "epoch": 1.0270328387552607,
      "grad_norm": 0.41262781620025635,
      "learning_rate": 9.599470256456236e-06,
      "loss": 0.5252,
      "step": 33433
    },
    {
      "epoch": 1.0270635578902099,
      "grad_norm": 0.35560932755470276,
      "learning_rate": 9.598987367389857e-06,
      "loss": 0.5339,
      "step": 33434
    },
    {
      "epoch": 1.027094277025159,
      "grad_norm": 0.4506785571575165,
      "learning_rate": 9.598504479260077e-06,
      "loss": 0.5157,
      "step": 33435
    },
    {
      "epoch": 1.027124996160108,
      "grad_norm": 0.3503867983818054,
      "learning_rate": 9.598021592068011e-06,
      "loss": 0.5099,
      "step": 33436
    },
    {
      "epoch": 1.0271557152950572,
      "grad_norm": 0.3641520142555237,
      "learning_rate": 9.597538705814801e-06,
      "loss": 0.4692,
      "step": 33437
    },
    {
      "epoch": 1.0271864344300063,
      "grad_norm": 0.4004623591899872,
      "learning_rate": 9.597055820501565e-06,
      "loss": 0.479,
      "step": 33438
    },
    {
      "epoch": 1.0272171535649557,
      "grad_norm": 0.3992210924625397,
      "learning_rate": 9.596572936129432e-06,
      "loss": 0.5195,
      "step": 33439
    },
    {
      "epoch": 1.0272478726999048,
      "grad_norm": 0.4833066463470459,
      "learning_rate": 9.596090052699531e-06,
      "loss": 0.5249,
      "step": 33440
    },
    {
      "epoch": 1.027278591834854,
      "grad_norm": 0.3790881633758545,
      "learning_rate": 9.595607170212991e-06,
      "loss": 0.5253,
      "step": 33441
    },
    {
      "epoch": 1.027309310969803,
      "grad_norm": 0.36027637124061584,
      "learning_rate": 9.595124288670935e-06,
      "loss": 0.5027,
      "step": 33442
    },
    {
      "epoch": 1.0273400301047522,
      "grad_norm": 0.39357444643974304,
      "learning_rate": 9.5946414080745e-06,
      "loss": 0.5043,
      "step": 33443
    },
    {
      "epoch": 1.0273707492397015,
      "grad_norm": 0.3549610376358032,
      "learning_rate": 9.594158528424805e-06,
      "loss": 0.5246,
      "step": 33444
    },
    {
      "epoch": 1.0274014683746506,
      "grad_norm": 0.3940858244895935,
      "learning_rate": 9.59367564972298e-06,
      "loss": 0.6247,
      "step": 33445
    },
    {
      "epoch": 1.0274321875095997,
      "grad_norm": 0.4185873866081238,
      "learning_rate": 9.593192771970156e-06,
      "loss": 0.5802,
      "step": 33446
    },
    {
      "epoch": 1.0274629066445489,
      "grad_norm": 1.4035580158233643,
      "learning_rate": 9.592709895167458e-06,
      "loss": 0.4875,
      "step": 33447
    },
    {
      "epoch": 1.027493625779498,
      "grad_norm": 0.38717421889305115,
      "learning_rate": 9.592227019316015e-06,
      "loss": 0.5287,
      "step": 33448
    },
    {
      "epoch": 1.027524344914447,
      "grad_norm": 0.3608623147010803,
      "learning_rate": 9.591744144416955e-06,
      "loss": 0.5018,
      "step": 33449
    },
    {
      "epoch": 1.0275550640493964,
      "grad_norm": 0.47437775135040283,
      "learning_rate": 9.591261270471405e-06,
      "loss": 0.4661,
      "step": 33450
    },
    {
      "epoch": 1.0275857831843456,
      "grad_norm": 0.38373079895973206,
      "learning_rate": 9.590778397480491e-06,
      "loss": 0.5141,
      "step": 33451
    },
    {
      "epoch": 1.0276165023192947,
      "grad_norm": 0.3822019696235657,
      "learning_rate": 9.590295525445344e-06,
      "loss": 0.5463,
      "step": 33452
    },
    {
      "epoch": 1.0276472214542438,
      "grad_norm": 0.40883585810661316,
      "learning_rate": 9.58981265436709e-06,
      "loss": 0.5381,
      "step": 33453
    },
    {
      "epoch": 1.027677940589193,
      "grad_norm": 0.3622909486293793,
      "learning_rate": 9.589329784246858e-06,
      "loss": 0.5068,
      "step": 33454
    },
    {
      "epoch": 1.0277086597241423,
      "grad_norm": 0.3919828236103058,
      "learning_rate": 9.588846915085773e-06,
      "loss": 0.4664,
      "step": 33455
    },
    {
      "epoch": 1.0277393788590914,
      "grad_norm": 0.34027907252311707,
      "learning_rate": 9.588364046884969e-06,
      "loss": 0.4931,
      "step": 33456
    },
    {
      "epoch": 1.0277700979940405,
      "grad_norm": 0.37350964546203613,
      "learning_rate": 9.587881179645564e-06,
      "loss": 0.4893,
      "step": 33457
    },
    {
      "epoch": 1.0278008171289896,
      "grad_norm": 0.41077175736427307,
      "learning_rate": 9.587398313368696e-06,
      "loss": 0.5681,
      "step": 33458
    },
    {
      "epoch": 1.0278315362639387,
      "grad_norm": 0.3694780170917511,
      "learning_rate": 9.586915448055483e-06,
      "loss": 0.5074,
      "step": 33459
    },
    {
      "epoch": 1.0278622553988879,
      "grad_norm": 0.3868616223335266,
      "learning_rate": 9.586432583707065e-06,
      "loss": 0.4697,
      "step": 33460
    },
    {
      "epoch": 1.0278929745338372,
      "grad_norm": 0.3767593502998352,
      "learning_rate": 9.585949720324555e-06,
      "loss": 0.5462,
      "step": 33461
    },
    {
      "epoch": 1.0279236936687863,
      "grad_norm": 0.37958410382270813,
      "learning_rate": 9.585466857909091e-06,
      "loss": 0.5067,
      "step": 33462
    },
    {
      "epoch": 1.0279544128037355,
      "grad_norm": 0.402168333530426,
      "learning_rate": 9.5849839964618e-06,
      "loss": 0.5633,
      "step": 33463
    },
    {
      "epoch": 1.0279851319386846,
      "grad_norm": 0.39355286955833435,
      "learning_rate": 9.584501135983805e-06,
      "loss": 0.5042,
      "step": 33464
    },
    {
      "epoch": 1.0280158510736337,
      "grad_norm": 0.3743191063404083,
      "learning_rate": 9.58401827647624e-06,
      "loss": 0.5434,
      "step": 33465
    },
    {
      "epoch": 1.028046570208583,
      "grad_norm": 0.3866492807865143,
      "learning_rate": 9.583535417940227e-06,
      "loss": 0.5156,
      "step": 33466
    },
    {
      "epoch": 1.0280772893435322,
      "grad_norm": 0.3896915018558502,
      "learning_rate": 9.583052560376898e-06,
      "loss": 0.4823,
      "step": 33467
    },
    {
      "epoch": 1.0281080084784813,
      "grad_norm": 0.4137442708015442,
      "learning_rate": 9.582569703787376e-06,
      "loss": 0.5232,
      "step": 33468
    },
    {
      "epoch": 1.0281387276134304,
      "grad_norm": 0.4218652546405792,
      "learning_rate": 9.582086848172795e-06,
      "loss": 0.5323,
      "step": 33469
    },
    {
      "epoch": 1.0281694467483795,
      "grad_norm": 0.40496760606765747,
      "learning_rate": 9.581603993534275e-06,
      "loss": 0.5315,
      "step": 33470
    },
    {
      "epoch": 1.0282001658833286,
      "grad_norm": 0.4343350827693939,
      "learning_rate": 9.581121139872954e-06,
      "loss": 0.5374,
      "step": 33471
    },
    {
      "epoch": 1.028230885018278,
      "grad_norm": 0.36735525727272034,
      "learning_rate": 9.58063828718995e-06,
      "loss": 0.5345,
      "step": 33472
    },
    {
      "epoch": 1.028261604153227,
      "grad_norm": 0.40730613470077515,
      "learning_rate": 9.580155435486396e-06,
      "loss": 0.5906,
      "step": 33473
    },
    {
      "epoch": 1.0282923232881762,
      "grad_norm": 0.39939332008361816,
      "learning_rate": 9.579672584763416e-06,
      "loss": 0.5071,
      "step": 33474
    },
    {
      "epoch": 1.0283230424231253,
      "grad_norm": 0.4542454481124878,
      "learning_rate": 9.579189735022142e-06,
      "loss": 0.4633,
      "step": 33475
    },
    {
      "epoch": 1.0283537615580745,
      "grad_norm": 0.3705582022666931,
      "learning_rate": 9.578706886263698e-06,
      "loss": 0.4649,
      "step": 33476
    },
    {
      "epoch": 1.0283844806930236,
      "grad_norm": 0.37279123067855835,
      "learning_rate": 9.578224038489216e-06,
      "loss": 0.5467,
      "step": 33477
    },
    {
      "epoch": 1.028415199827973,
      "grad_norm": 0.42707791924476624,
      "learning_rate": 9.57774119169982e-06,
      "loss": 0.4141,
      "step": 33478
    },
    {
      "epoch": 1.028445918962922,
      "grad_norm": 0.4161951243877411,
      "learning_rate": 9.577258345896638e-06,
      "loss": 0.4807,
      "step": 33479
    },
    {
      "epoch": 1.0284766380978712,
      "grad_norm": 0.36071833968162537,
      "learning_rate": 9.5767755010808e-06,
      "loss": 0.4728,
      "step": 33480
    },
    {
      "epoch": 1.0285073572328203,
      "grad_norm": 0.40113353729248047,
      "learning_rate": 9.57629265725343e-06,
      "loss": 0.3843,
      "step": 33481
    },
    {
      "epoch": 1.0285380763677694,
      "grad_norm": 0.35483548045158386,
      "learning_rate": 9.57580981441566e-06,
      "loss": 0.4646,
      "step": 33482
    },
    {
      "epoch": 1.0285687955027187,
      "grad_norm": 0.3807874619960785,
      "learning_rate": 9.575326972568615e-06,
      "loss": 0.5109,
      "step": 33483
    },
    {
      "epoch": 1.0285995146376679,
      "grad_norm": 0.3464207649230957,
      "learning_rate": 9.574844131713426e-06,
      "loss": 0.4978,
      "step": 33484
    },
    {
      "epoch": 1.028630233772617,
      "grad_norm": 0.3900219798088074,
      "learning_rate": 9.574361291851215e-06,
      "loss": 0.5353,
      "step": 33485
    },
    {
      "epoch": 1.028660952907566,
      "grad_norm": 0.3677520155906677,
      "learning_rate": 9.573878452983115e-06,
      "loss": 0.5334,
      "step": 33486
    },
    {
      "epoch": 1.0286916720425152,
      "grad_norm": 0.36593613028526306,
      "learning_rate": 9.573395615110251e-06,
      "loss": 0.5075,
      "step": 33487
    },
    {
      "epoch": 1.0287223911774643,
      "grad_norm": 0.379268616437912,
      "learning_rate": 9.572912778233752e-06,
      "loss": 0.5828,
      "step": 33488
    },
    {
      "epoch": 1.0287531103124137,
      "grad_norm": 0.3778064250946045,
      "learning_rate": 9.572429942354743e-06,
      "loss": 0.5148,
      "step": 33489
    },
    {
      "epoch": 1.0287838294473628,
      "grad_norm": 0.40476658940315247,
      "learning_rate": 9.571947107474357e-06,
      "loss": 0.5688,
      "step": 33490
    },
    {
      "epoch": 1.028814548582312,
      "grad_norm": 0.3789983093738556,
      "learning_rate": 9.571464273593715e-06,
      "loss": 0.4497,
      "step": 33491
    },
    {
      "epoch": 1.028845267717261,
      "grad_norm": 0.39515483379364014,
      "learning_rate": 9.57098144071395e-06,
      "loss": 0.5498,
      "step": 33492
    },
    {
      "epoch": 1.0288759868522102,
      "grad_norm": 0.394696444272995,
      "learning_rate": 9.570498608836187e-06,
      "loss": 0.4862,
      "step": 33493
    },
    {
      "epoch": 1.0289067059871595,
      "grad_norm": 0.3775997459888458,
      "learning_rate": 9.570015777961558e-06,
      "loss": 0.4953,
      "step": 33494
    },
    {
      "epoch": 1.0289374251221086,
      "grad_norm": 0.3739544749259949,
      "learning_rate": 9.56953294809118e-06,
      "loss": 0.4618,
      "step": 33495
    },
    {
      "epoch": 1.0289681442570577,
      "grad_norm": 0.362629234790802,
      "learning_rate": 9.569050119226197e-06,
      "loss": 0.4837,
      "step": 33496
    },
    {
      "epoch": 1.0289988633920069,
      "grad_norm": 0.4340142011642456,
      "learning_rate": 9.56856729136772e-06,
      "loss": 0.5058,
      "step": 33497
    },
    {
      "epoch": 1.029029582526956,
      "grad_norm": 0.352293461561203,
      "learning_rate": 9.568084464516889e-06,
      "loss": 0.5385,
      "step": 33498
    },
    {
      "epoch": 1.029060301661905,
      "grad_norm": 0.3519737124443054,
      "learning_rate": 9.56760163867482e-06,
      "loss": 0.4637,
      "step": 33499
    },
    {
      "epoch": 1.0290910207968544,
      "grad_norm": 0.36025264859199524,
      "learning_rate": 9.567118813842652e-06,
      "loss": 0.533,
      "step": 33500
    },
    {
      "epoch": 1.0291217399318036,
      "grad_norm": 0.368082731962204,
      "learning_rate": 9.566635990021512e-06,
      "loss": 0.4783,
      "step": 33501
    },
    {
      "epoch": 1.0291524590667527,
      "grad_norm": 0.4276025593280792,
      "learning_rate": 9.566153167212518e-06,
      "loss": 0.4397,
      "step": 33502
    },
    {
      "epoch": 1.0291831782017018,
      "grad_norm": 0.40509486198425293,
      "learning_rate": 9.565670345416809e-06,
      "loss": 0.4354,
      "step": 33503
    },
    {
      "epoch": 1.029213897336651,
      "grad_norm": 0.4167095124721527,
      "learning_rate": 9.5651875246355e-06,
      "loss": 0.5282,
      "step": 33504
    },
    {
      "epoch": 1.0292446164716003,
      "grad_norm": 0.4035779535770416,
      "learning_rate": 9.564704704869734e-06,
      "loss": 0.5612,
      "step": 33505
    },
    {
      "epoch": 1.0292753356065494,
      "grad_norm": 0.426177442073822,
      "learning_rate": 9.564221886120624e-06,
      "loss": 0.5527,
      "step": 33506
    },
    {
      "epoch": 1.0293060547414985,
      "grad_norm": 0.418182909488678,
      "learning_rate": 9.56373906838931e-06,
      "loss": 0.4847,
      "step": 33507
    },
    {
      "epoch": 1.0293367738764476,
      "grad_norm": 0.36636126041412354,
      "learning_rate": 9.563256251676909e-06,
      "loss": 0.501,
      "step": 33508
    },
    {
      "epoch": 1.0293674930113967,
      "grad_norm": 0.37104591727256775,
      "learning_rate": 9.562773435984555e-06,
      "loss": 0.4325,
      "step": 33509
    },
    {
      "epoch": 1.0293982121463459,
      "grad_norm": 0.3609201908111572,
      "learning_rate": 9.562290621313376e-06,
      "loss": 0.5012,
      "step": 33510
    },
    {
      "epoch": 1.0294289312812952,
      "grad_norm": 0.41157400608062744,
      "learning_rate": 9.561807807664495e-06,
      "loss": 0.5169,
      "step": 33511
    },
    {
      "epoch": 1.0294596504162443,
      "grad_norm": 0.39345046877861023,
      "learning_rate": 9.561324995039044e-06,
      "loss": 0.5535,
      "step": 33512
    },
    {
      "epoch": 1.0294903695511934,
      "grad_norm": 0.3716055154800415,
      "learning_rate": 9.56084218343815e-06,
      "loss": 0.5225,
      "step": 33513
    },
    {
      "epoch": 1.0295210886861426,
      "grad_norm": 0.3742269277572632,
      "learning_rate": 9.560359372862938e-06,
      "loss": 0.5124,
      "step": 33514
    },
    {
      "epoch": 1.0295518078210917,
      "grad_norm": 0.38512876629829407,
      "learning_rate": 9.55987656331454e-06,
      "loss": 0.5461,
      "step": 33515
    },
    {
      "epoch": 1.029582526956041,
      "grad_norm": 0.39002808928489685,
      "learning_rate": 9.559393754794076e-06,
      "loss": 0.4375,
      "step": 33516
    },
    {
      "epoch": 1.0296132460909901,
      "grad_norm": 0.39546558260917664,
      "learning_rate": 9.558910947302681e-06,
      "loss": 0.5073,
      "step": 33517
    },
    {
      "epoch": 1.0296439652259393,
      "grad_norm": 0.41365742683410645,
      "learning_rate": 9.558428140841482e-06,
      "loss": 0.5132,
      "step": 33518
    },
    {
      "epoch": 1.0296746843608884,
      "grad_norm": 0.37298810482025146,
      "learning_rate": 9.557945335411603e-06,
      "loss": 0.4925,
      "step": 33519
    },
    {
      "epoch": 1.0297054034958375,
      "grad_norm": 0.42182475328445435,
      "learning_rate": 9.557462531014176e-06,
      "loss": 0.464,
      "step": 33520
    },
    {
      "epoch": 1.0297361226307866,
      "grad_norm": 0.4291943311691284,
      "learning_rate": 9.556979727650322e-06,
      "loss": 0.5236,
      "step": 33521
    },
    {
      "epoch": 1.029766841765736,
      "grad_norm": 0.4025992453098297,
      "learning_rate": 9.556496925321177e-06,
      "loss": 0.535,
      "step": 33522
    },
    {
      "epoch": 1.029797560900685,
      "grad_norm": 0.3632483184337616,
      "learning_rate": 9.556014124027861e-06,
      "loss": 0.4815,
      "step": 33523
    },
    {
      "epoch": 1.0298282800356342,
      "grad_norm": 0.39630556106567383,
      "learning_rate": 9.555531323771509e-06,
      "loss": 0.5095,
      "step": 33524
    },
    {
      "epoch": 1.0298589991705833,
      "grad_norm": 0.4109874367713928,
      "learning_rate": 9.55504852455324e-06,
      "loss": 0.5499,
      "step": 33525
    },
    {
      "epoch": 1.0298897183055324,
      "grad_norm": 0.38532793521881104,
      "learning_rate": 9.55456572637419e-06,
      "loss": 0.5188,
      "step": 33526
    },
    {
      "epoch": 1.0299204374404818,
      "grad_norm": 0.38398173451423645,
      "learning_rate": 9.554082929235482e-06,
      "loss": 0.508,
      "step": 33527
    },
    {
      "epoch": 1.029951156575431,
      "grad_norm": 0.4220253825187683,
      "learning_rate": 9.553600133138244e-06,
      "loss": 0.5359,
      "step": 33528
    },
    {
      "epoch": 1.02998187571038,
      "grad_norm": 0.41752585768699646,
      "learning_rate": 9.553117338083604e-06,
      "loss": 0.4741,
      "step": 33529
    },
    {
      "epoch": 1.0300125948453291,
      "grad_norm": 0.3432421088218689,
      "learning_rate": 9.552634544072693e-06,
      "loss": 0.4899,
      "step": 33530
    },
    {
      "epoch": 1.0300433139802783,
      "grad_norm": 0.35562631487846375,
      "learning_rate": 9.55215175110663e-06,
      "loss": 0.4607,
      "step": 33531
    },
    {
      "epoch": 1.0300740331152274,
      "grad_norm": 0.3840622305870056,
      "learning_rate": 9.551668959186552e-06,
      "loss": 0.5186,
      "step": 33532
    },
    {
      "epoch": 1.0301047522501767,
      "grad_norm": 0.4024999439716339,
      "learning_rate": 9.551186168313576e-06,
      "loss": 0.4905,
      "step": 33533
    },
    {
      "epoch": 1.0301354713851258,
      "grad_norm": 0.37179821729660034,
      "learning_rate": 9.550703378488844e-06,
      "loss": 0.5272,
      "step": 33534
    },
    {
      "epoch": 1.030166190520075,
      "grad_norm": 0.3507470190525055,
      "learning_rate": 9.55022058971347e-06,
      "loss": 0.5243,
      "step": 33535
    },
    {
      "epoch": 1.030196909655024,
      "grad_norm": 0.372224360704422,
      "learning_rate": 9.549737801988586e-06,
      "loss": 0.5376,
      "step": 33536
    },
    {
      "epoch": 1.0302276287899732,
      "grad_norm": 0.3879859447479248,
      "learning_rate": 9.549255015315329e-06,
      "loss": 0.4203,
      "step": 33537
    },
    {
      "epoch": 1.0302583479249225,
      "grad_norm": 0.3689415752887726,
      "learning_rate": 9.54877222969481e-06,
      "loss": 0.5191,
      "step": 33538
    },
    {
      "epoch": 1.0302890670598717,
      "grad_norm": 0.3723948001861572,
      "learning_rate": 9.548289445128172e-06,
      "loss": 0.4236,
      "step": 33539
    },
    {
      "epoch": 1.0303197861948208,
      "grad_norm": 0.3667793273925781,
      "learning_rate": 9.547806661616527e-06,
      "loss": 0.5031,
      "step": 33540
    },
    {
      "epoch": 1.03035050532977,
      "grad_norm": 0.45974335074424744,
      "learning_rate": 9.547323879161021e-06,
      "loss": 0.5693,
      "step": 33541
    },
    {
      "epoch": 1.030381224464719,
      "grad_norm": 0.384109765291214,
      "learning_rate": 9.546841097762764e-06,
      "loss": 0.4462,
      "step": 33542
    },
    {
      "epoch": 1.0304119435996681,
      "grad_norm": 0.3973436951637268,
      "learning_rate": 9.546358317422896e-06,
      "loss": 0.454,
      "step": 33543
    },
    {
      "epoch": 1.0304426627346175,
      "grad_norm": 0.3604933023452759,
      "learning_rate": 9.545875538142537e-06,
      "loss": 0.5003,
      "step": 33544
    },
    {
      "epoch": 1.0304733818695666,
      "grad_norm": 0.4261434078216553,
      "learning_rate": 9.545392759922818e-06,
      "loss": 0.4763,
      "step": 33545
    },
    {
      "epoch": 1.0305041010045157,
      "grad_norm": 0.3739794194698334,
      "learning_rate": 9.544909982764866e-06,
      "loss": 0.5172,
      "step": 33546
    },
    {
      "epoch": 1.0305348201394648,
      "grad_norm": 0.40154024958610535,
      "learning_rate": 9.54442720666981e-06,
      "loss": 0.5128,
      "step": 33547
    },
    {
      "epoch": 1.030565539274414,
      "grad_norm": 0.34991002082824707,
      "learning_rate": 9.543944431638775e-06,
      "loss": 0.5714,
      "step": 33548
    },
    {
      "epoch": 1.030596258409363,
      "grad_norm": 0.3957844078540802,
      "learning_rate": 9.54346165767289e-06,
      "loss": 0.502,
      "step": 33549
    },
    {
      "epoch": 1.0306269775443124,
      "grad_norm": 0.3932842016220093,
      "learning_rate": 9.542978884773281e-06,
      "loss": 0.4772,
      "step": 33550
    },
    {
      "epoch": 1.0306576966792615,
      "grad_norm": 0.4636971056461334,
      "learning_rate": 9.542496112941077e-06,
      "loss": 0.5367,
      "step": 33551
    },
    {
      "epoch": 1.0306884158142107,
      "grad_norm": 0.3701063394546509,
      "learning_rate": 9.542013342177406e-06,
      "loss": 0.4063,
      "step": 33552
    },
    {
      "epoch": 1.0307191349491598,
      "grad_norm": 0.3747507631778717,
      "learning_rate": 9.541530572483393e-06,
      "loss": 0.4945,
      "step": 33553
    },
    {
      "epoch": 1.030749854084109,
      "grad_norm": 0.3769509792327881,
      "learning_rate": 9.54104780386017e-06,
      "loss": 0.5054,
      "step": 33554
    },
    {
      "epoch": 1.0307805732190582,
      "grad_norm": 0.40588274598121643,
      "learning_rate": 9.540565036308859e-06,
      "loss": 0.4931,
      "step": 33555
    },
    {
      "epoch": 1.0308112923540074,
      "grad_norm": 0.41767993569374084,
      "learning_rate": 9.540082269830593e-06,
      "loss": 0.5224,
      "step": 33556
    },
    {
      "epoch": 1.0308420114889565,
      "grad_norm": 0.3774369955062866,
      "learning_rate": 9.539599504426495e-06,
      "loss": 0.4945,
      "step": 33557
    },
    {
      "epoch": 1.0308727306239056,
      "grad_norm": 0.40185144543647766,
      "learning_rate": 9.539116740097698e-06,
      "loss": 0.5065,
      "step": 33558
    },
    {
      "epoch": 1.0309034497588547,
      "grad_norm": 0.3487735986709595,
      "learning_rate": 9.538633976845321e-06,
      "loss": 0.5048,
      "step": 33559
    },
    {
      "epoch": 1.0309341688938038,
      "grad_norm": 0.37471309304237366,
      "learning_rate": 9.538151214670501e-06,
      "loss": 0.529,
      "step": 33560
    },
    {
      "epoch": 1.0309648880287532,
      "grad_norm": 0.3931155204772949,
      "learning_rate": 9.537668453574359e-06,
      "loss": 0.5378,
      "step": 33561
    },
    {
      "epoch": 1.0309956071637023,
      "grad_norm": 0.3650891184806824,
      "learning_rate": 9.537185693558026e-06,
      "loss": 0.4833,
      "step": 33562
    },
    {
      "epoch": 1.0310263262986514,
      "grad_norm": 0.3540371060371399,
      "learning_rate": 9.536702934622625e-06,
      "loss": 0.4353,
      "step": 33563
    },
    {
      "epoch": 1.0310570454336005,
      "grad_norm": 0.3689501881599426,
      "learning_rate": 9.536220176769293e-06,
      "loss": 0.472,
      "step": 33564
    },
    {
      "epoch": 1.0310877645685497,
      "grad_norm": 0.36490413546562195,
      "learning_rate": 9.535737419999144e-06,
      "loss": 0.4603,
      "step": 33565
    },
    {
      "epoch": 1.031118483703499,
      "grad_norm": 0.38253557682037354,
      "learning_rate": 9.535254664313318e-06,
      "loss": 0.4957,
      "step": 33566
    },
    {
      "epoch": 1.0311492028384481,
      "grad_norm": 0.4233580231666565,
      "learning_rate": 9.534771909712933e-06,
      "loss": 0.4824,
      "step": 33567
    },
    {
      "epoch": 1.0311799219733973,
      "grad_norm": 0.33958005905151367,
      "learning_rate": 9.534289156199124e-06,
      "loss": 0.4619,
      "step": 33568
    },
    {
      "epoch": 1.0312106411083464,
      "grad_norm": 0.39988207817077637,
      "learning_rate": 9.533806403773011e-06,
      "loss": 0.4442,
      "step": 33569
    },
    {
      "epoch": 1.0312413602432955,
      "grad_norm": 0.4090278446674347,
      "learning_rate": 9.533323652435732e-06,
      "loss": 0.4252,
      "step": 33570
    },
    {
      "epoch": 1.0312720793782446,
      "grad_norm": 0.3521837294101715,
      "learning_rate": 9.532840902188405e-06,
      "loss": 0.3964,
      "step": 33571
    },
    {
      "epoch": 1.031302798513194,
      "grad_norm": 0.3706211745738983,
      "learning_rate": 9.532358153032156e-06,
      "loss": 0.552,
      "step": 33572
    },
    {
      "epoch": 1.031333517648143,
      "grad_norm": 0.37451082468032837,
      "learning_rate": 9.531875404968125e-06,
      "loss": 0.4813,
      "step": 33573
    },
    {
      "epoch": 1.0313642367830922,
      "grad_norm": 0.41058987379074097,
      "learning_rate": 9.531392657997424e-06,
      "loss": 0.4839,
      "step": 33574
    },
    {
      "epoch": 1.0313949559180413,
      "grad_norm": 0.434723436832428,
      "learning_rate": 9.530909912121195e-06,
      "loss": 0.5929,
      "step": 33575
    },
    {
      "epoch": 1.0314256750529904,
      "grad_norm": 0.3972930312156677,
      "learning_rate": 9.530427167340556e-06,
      "loss": 0.4908,
      "step": 33576
    },
    {
      "epoch": 1.0314563941879398,
      "grad_norm": 0.4024519622325897,
      "learning_rate": 9.52994442365664e-06,
      "loss": 0.5619,
      "step": 33577
    },
    {
      "epoch": 1.031487113322889,
      "grad_norm": 0.3755244016647339,
      "learning_rate": 9.529461681070566e-06,
      "loss": 0.5141,
      "step": 33578
    },
    {
      "epoch": 1.031517832457838,
      "grad_norm": 0.38822728395462036,
      "learning_rate": 9.528978939583472e-06,
      "loss": 0.5391,
      "step": 33579
    },
    {
      "epoch": 1.0315485515927871,
      "grad_norm": 0.3588193356990814,
      "learning_rate": 9.528496199196477e-06,
      "loss": 0.507,
      "step": 33580
    },
    {
      "epoch": 1.0315792707277363,
      "grad_norm": 0.39136308431625366,
      "learning_rate": 9.528013459910714e-06,
      "loss": 0.5407,
      "step": 33581
    },
    {
      "epoch": 1.0316099898626854,
      "grad_norm": 0.37042757868766785,
      "learning_rate": 9.527530721727308e-06,
      "loss": 0.4681,
      "step": 33582
    },
    {
      "epoch": 1.0316407089976347,
      "grad_norm": 0.3892516791820526,
      "learning_rate": 9.527047984647387e-06,
      "loss": 0.5208,
      "step": 33583
    },
    {
      "epoch": 1.0316714281325838,
      "grad_norm": 0.36038801074028015,
      "learning_rate": 9.526565248672077e-06,
      "loss": 0.5059,
      "step": 33584
    },
    {
      "epoch": 1.031702147267533,
      "grad_norm": 0.3660852015018463,
      "learning_rate": 9.526082513802511e-06,
      "loss": 0.5157,
      "step": 33585
    },
    {
      "epoch": 1.031732866402482,
      "grad_norm": 0.389304518699646,
      "learning_rate": 9.525599780039808e-06,
      "loss": 0.4992,
      "step": 33586
    },
    {
      "epoch": 1.0317635855374312,
      "grad_norm": 0.43988925218582153,
      "learning_rate": 9.525117047385103e-06,
      "loss": 0.5739,
      "step": 33587
    },
    {
      "epoch": 1.0317943046723803,
      "grad_norm": 0.3631833493709564,
      "learning_rate": 9.524634315839518e-06,
      "loss": 0.4853,
      "step": 33588
    },
    {
      "epoch": 1.0318250238073297,
      "grad_norm": 0.3586077094078064,
      "learning_rate": 9.524151585404184e-06,
      "loss": 0.4982,
      "step": 33589
    },
    {
      "epoch": 1.0318557429422788,
      "grad_norm": 0.37555164098739624,
      "learning_rate": 9.523668856080226e-06,
      "loss": 0.4029,
      "step": 33590
    },
    {
      "epoch": 1.031886462077228,
      "grad_norm": 0.34928908944129944,
      "learning_rate": 9.523186127868774e-06,
      "loss": 0.4409,
      "step": 33591
    },
    {
      "epoch": 1.031917181212177,
      "grad_norm": 0.35972005128860474,
      "learning_rate": 9.522703400770953e-06,
      "loss": 0.4845,
      "step": 33592
    },
    {
      "epoch": 1.0319479003471261,
      "grad_norm": 0.38145920634269714,
      "learning_rate": 9.522220674787893e-06,
      "loss": 0.4417,
      "step": 33593
    },
    {
      "epoch": 1.0319786194820755,
      "grad_norm": 0.49528881907463074,
      "learning_rate": 9.52173794992072e-06,
      "loss": 0.461,
      "step": 33594
    },
    {
      "epoch": 1.0320093386170246,
      "grad_norm": 0.35487818717956543,
      "learning_rate": 9.52125522617056e-06,
      "loss": 0.4469,
      "step": 33595
    },
    {
      "epoch": 1.0320400577519737,
      "grad_norm": 0.39142635464668274,
      "learning_rate": 9.520772503538543e-06,
      "loss": 0.5158,
      "step": 33596
    },
    {
      "epoch": 1.0320707768869228,
      "grad_norm": 0.39507976174354553,
      "learning_rate": 9.520289782025794e-06,
      "loss": 0.485,
      "step": 33597
    },
    {
      "epoch": 1.032101496021872,
      "grad_norm": 0.39810848236083984,
      "learning_rate": 9.519807061633445e-06,
      "loss": 0.4623,
      "step": 33598
    },
    {
      "epoch": 1.032132215156821,
      "grad_norm": 0.38312071561813354,
      "learning_rate": 9.519324342362614e-06,
      "loss": 0.5723,
      "step": 33599
    },
    {
      "epoch": 1.0321629342917704,
      "grad_norm": 0.3805636167526245,
      "learning_rate": 9.518841624214442e-06,
      "loss": 0.4842,
      "step": 33600
    },
    {
      "epoch": 1.0321936534267195,
      "grad_norm": 0.42498674988746643,
      "learning_rate": 9.518358907190042e-06,
      "loss": 0.4742,
      "step": 33601
    },
    {
      "epoch": 1.0322243725616687,
      "grad_norm": 0.3884199261665344,
      "learning_rate": 9.517876191290555e-06,
      "loss": 0.5267,
      "step": 33602
    },
    {
      "epoch": 1.0322550916966178,
      "grad_norm": 0.3822295069694519,
      "learning_rate": 9.517393476517094e-06,
      "loss": 0.5242,
      "step": 33603
    },
    {
      "epoch": 1.032285810831567,
      "grad_norm": 0.36948463320732117,
      "learning_rate": 9.516910762870804e-06,
      "loss": 0.5314,
      "step": 33604
    },
    {
      "epoch": 1.0323165299665162,
      "grad_norm": 0.3657485842704773,
      "learning_rate": 9.516428050352794e-06,
      "loss": 0.4814,
      "step": 33605
    },
    {
      "epoch": 1.0323472491014654,
      "grad_norm": 0.43641865253448486,
      "learning_rate": 9.515945338964206e-06,
      "loss": 0.4883,
      "step": 33606
    },
    {
      "epoch": 1.0323779682364145,
      "grad_norm": 0.37145689129829407,
      "learning_rate": 9.515462628706158e-06,
      "loss": 0.4797,
      "step": 33607
    },
    {
      "epoch": 1.0324086873713636,
      "grad_norm": 0.35073956847190857,
      "learning_rate": 9.514979919579778e-06,
      "loss": 0.5526,
      "step": 33608
    },
    {
      "epoch": 1.0324394065063127,
      "grad_norm": 0.3779061734676361,
      "learning_rate": 9.514497211586203e-06,
      "loss": 0.449,
      "step": 33609
    },
    {
      "epoch": 1.0324701256412618,
      "grad_norm": 0.38187965750694275,
      "learning_rate": 9.514014504726548e-06,
      "loss": 0.4532,
      "step": 33610
    },
    {
      "epoch": 1.0325008447762112,
      "grad_norm": 0.43501508235931396,
      "learning_rate": 9.513531799001952e-06,
      "loss": 0.5353,
      "step": 33611
    },
    {
      "epoch": 1.0325315639111603,
      "grad_norm": 0.4695570170879364,
      "learning_rate": 9.513049094413532e-06,
      "loss": 0.4773,
      "step": 33612
    },
    {
      "epoch": 1.0325622830461094,
      "grad_norm": 0.37330108880996704,
      "learning_rate": 9.512566390962422e-06,
      "loss": 0.4633,
      "step": 33613
    },
    {
      "epoch": 1.0325930021810585,
      "grad_norm": 0.5147490501403809,
      "learning_rate": 9.512083688649745e-06,
      "loss": 0.5369,
      "step": 33614
    },
    {
      "epoch": 1.0326237213160077,
      "grad_norm": 0.3848625123500824,
      "learning_rate": 9.511600987476633e-06,
      "loss": 0.4845,
      "step": 33615
    },
    {
      "epoch": 1.032654440450957,
      "grad_norm": 0.4075007736682892,
      "learning_rate": 9.511118287444209e-06,
      "loss": 0.5268,
      "step": 33616
    },
    {
      "epoch": 1.0326851595859061,
      "grad_norm": 0.39298105239868164,
      "learning_rate": 9.510635588553604e-06,
      "loss": 0.5497,
      "step": 33617
    },
    {
      "epoch": 1.0327158787208552,
      "grad_norm": 0.3626101315021515,
      "learning_rate": 9.510152890805943e-06,
      "loss": 0.465,
      "step": 33618
    },
    {
      "epoch": 1.0327465978558044,
      "grad_norm": 0.3814185559749603,
      "learning_rate": 9.509670194202355e-06,
      "loss": 0.4848,
      "step": 33619
    },
    {
      "epoch": 1.0327773169907535,
      "grad_norm": 0.3901973366737366,
      "learning_rate": 9.509187498743965e-06,
      "loss": 0.4682,
      "step": 33620
    },
    {
      "epoch": 1.0328080361257026,
      "grad_norm": 0.39612266421318054,
      "learning_rate": 9.508704804431903e-06,
      "loss": 0.4633,
      "step": 33621
    },
    {
      "epoch": 1.032838755260652,
      "grad_norm": 0.3560422658920288,
      "learning_rate": 9.508222111267293e-06,
      "loss": 0.5224,
      "step": 33622
    },
    {
      "epoch": 1.032869474395601,
      "grad_norm": 0.39473700523376465,
      "learning_rate": 9.507739419251269e-06,
      "loss": 0.4762,
      "step": 33623
    },
    {
      "epoch": 1.0329001935305502,
      "grad_norm": 0.3940582275390625,
      "learning_rate": 9.507256728384949e-06,
      "loss": 0.4882,
      "step": 33624
    },
    {
      "epoch": 1.0329309126654993,
      "grad_norm": 0.4091220498085022,
      "learning_rate": 9.506774038669469e-06,
      "loss": 0.5668,
      "step": 33625
    },
    {
      "epoch": 1.0329616318004484,
      "grad_norm": 0.3482207655906677,
      "learning_rate": 9.50629135010595e-06,
      "loss": 0.5163,
      "step": 33626
    },
    {
      "epoch": 1.0329923509353978,
      "grad_norm": 0.49404439330101013,
      "learning_rate": 9.505808662695523e-06,
      "loss": 0.5395,
      "step": 33627
    },
    {
      "epoch": 1.0330230700703469,
      "grad_norm": 0.42605775594711304,
      "learning_rate": 9.505325976439316e-06,
      "loss": 0.5107,
      "step": 33628
    },
    {
      "epoch": 1.033053789205296,
      "grad_norm": 0.3800888657569885,
      "learning_rate": 9.504843291338453e-06,
      "loss": 0.5324,
      "step": 33629
    },
    {
      "epoch": 1.0330845083402451,
      "grad_norm": 0.45665428042411804,
      "learning_rate": 9.504360607394064e-06,
      "loss": 0.4872,
      "step": 33630
    },
    {
      "epoch": 1.0331152274751942,
      "grad_norm": 0.3409416377544403,
      "learning_rate": 9.503877924607275e-06,
      "loss": 0.5213,
      "step": 33631
    },
    {
      "epoch": 1.0331459466101434,
      "grad_norm": 0.3481321632862091,
      "learning_rate": 9.503395242979215e-06,
      "loss": 0.51,
      "step": 33632
    },
    {
      "epoch": 1.0331766657450927,
      "grad_norm": 0.3481525778770447,
      "learning_rate": 9.502912562511007e-06,
      "loss": 0.5039,
      "step": 33633
    },
    {
      "epoch": 1.0332073848800418,
      "grad_norm": 0.4184187352657318,
      "learning_rate": 9.502429883203787e-06,
      "loss": 0.4784,
      "step": 33634
    },
    {
      "epoch": 1.033238104014991,
      "grad_norm": 0.36090710759162903,
      "learning_rate": 9.501947205058669e-06,
      "loss": 0.4711,
      "step": 33635
    },
    {
      "epoch": 1.03326882314994,
      "grad_norm": 0.38545456528663635,
      "learning_rate": 9.501464528076796e-06,
      "loss": 0.4999,
      "step": 33636
    },
    {
      "epoch": 1.0332995422848892,
      "grad_norm": 0.4042567312717438,
      "learning_rate": 9.50098185225928e-06,
      "loss": 0.5366,
      "step": 33637
    },
    {
      "epoch": 1.0333302614198385,
      "grad_norm": 0.3664296865463257,
      "learning_rate": 9.500499177607261e-06,
      "loss": 0.506,
      "step": 33638
    },
    {
      "epoch": 1.0333609805547876,
      "grad_norm": 0.4382072687149048,
      "learning_rate": 9.50001650412186e-06,
      "loss": 0.5092,
      "step": 33639
    },
    {
      "epoch": 1.0333916996897368,
      "grad_norm": 0.3697429299354553,
      "learning_rate": 9.499533831804206e-06,
      "loss": 0.4854,
      "step": 33640
    },
    {
      "epoch": 1.0334224188246859,
      "grad_norm": 0.3809567987918854,
      "learning_rate": 9.499051160655422e-06,
      "loss": 0.4771,
      "step": 33641
    },
    {
      "epoch": 1.033453137959635,
      "grad_norm": 0.38338327407836914,
      "learning_rate": 9.498568490676644e-06,
      "loss": 0.5384,
      "step": 33642
    },
    {
      "epoch": 1.0334838570945841,
      "grad_norm": 0.4135737121105194,
      "learning_rate": 9.49808582186899e-06,
      "loss": 0.4901,
      "step": 33643
    },
    {
      "epoch": 1.0335145762295335,
      "grad_norm": 0.37619829177856445,
      "learning_rate": 9.497603154233595e-06,
      "loss": 0.4463,
      "step": 33644
    },
    {
      "epoch": 1.0335452953644826,
      "grad_norm": 0.3699212968349457,
      "learning_rate": 9.497120487771579e-06,
      "loss": 0.5332,
      "step": 33645
    },
    {
      "epoch": 1.0335760144994317,
      "grad_norm": 0.3750663995742798,
      "learning_rate": 9.496637822484075e-06,
      "loss": 0.4668,
      "step": 33646
    },
    {
      "epoch": 1.0336067336343808,
      "grad_norm": 0.3786858022212982,
      "learning_rate": 9.49615515837221e-06,
      "loss": 0.472,
      "step": 33647
    },
    {
      "epoch": 1.03363745276933,
      "grad_norm": 0.4231634736061096,
      "learning_rate": 9.495672495437107e-06,
      "loss": 0.4528,
      "step": 33648
    },
    {
      "epoch": 1.0336681719042793,
      "grad_norm": 0.3779270648956299,
      "learning_rate": 9.4951898336799e-06,
      "loss": 0.5519,
      "step": 33649
    },
    {
      "epoch": 1.0336988910392284,
      "grad_norm": 0.377387672662735,
      "learning_rate": 9.494707173101708e-06,
      "loss": 0.5319,
      "step": 33650
    },
    {
      "epoch": 1.0337296101741775,
      "grad_norm": 0.4064617455005646,
      "learning_rate": 9.494224513703667e-06,
      "loss": 0.5699,
      "step": 33651
    },
    {
      "epoch": 1.0337603293091266,
      "grad_norm": 0.36624449491500854,
      "learning_rate": 9.493741855486896e-06,
      "loss": 0.5139,
      "step": 33652
    },
    {
      "epoch": 1.0337910484440758,
      "grad_norm": 0.38198322057724,
      "learning_rate": 9.49325919845253e-06,
      "loss": 0.4748,
      "step": 33653
    },
    {
      "epoch": 1.0338217675790249,
      "grad_norm": 0.3525660037994385,
      "learning_rate": 9.492776542601689e-06,
      "loss": 0.439,
      "step": 33654
    },
    {
      "epoch": 1.0338524867139742,
      "grad_norm": 0.35200145840644836,
      "learning_rate": 9.492293887935507e-06,
      "loss": 0.5306,
      "step": 33655
    },
    {
      "epoch": 1.0338832058489233,
      "grad_norm": 0.44533494114875793,
      "learning_rate": 9.491811234455106e-06,
      "loss": 0.5377,
      "step": 33656
    },
    {
      "epoch": 1.0339139249838725,
      "grad_norm": 0.4040505886077881,
      "learning_rate": 9.491328582161618e-06,
      "loss": 0.4963,
      "step": 33657
    },
    {
      "epoch": 1.0339446441188216,
      "grad_norm": 0.3680058717727661,
      "learning_rate": 9.490845931056163e-06,
      "loss": 0.5407,
      "step": 33658
    },
    {
      "epoch": 1.0339753632537707,
      "grad_norm": 0.44524818658828735,
      "learning_rate": 9.490363281139876e-06,
      "loss": 0.5822,
      "step": 33659
    },
    {
      "epoch": 1.0340060823887198,
      "grad_norm": 0.3555769622325897,
      "learning_rate": 9.489880632413881e-06,
      "loss": 0.5101,
      "step": 33660
    },
    {
      "epoch": 1.0340368015236692,
      "grad_norm": 0.408109575510025,
      "learning_rate": 9.489397984879309e-06,
      "loss": 0.54,
      "step": 33661
    },
    {
      "epoch": 1.0340675206586183,
      "grad_norm": 0.3806965947151184,
      "learning_rate": 9.488915338537276e-06,
      "loss": 0.4381,
      "step": 33662
    },
    {
      "epoch": 1.0340982397935674,
      "grad_norm": 0.40791377425193787,
      "learning_rate": 9.488432693388919e-06,
      "loss": 0.5272,
      "step": 33663
    },
    {
      "epoch": 1.0341289589285165,
      "grad_norm": 0.44940850138664246,
      "learning_rate": 9.487950049435366e-06,
      "loss": 0.4679,
      "step": 33664
    },
    {
      "epoch": 1.0341596780634656,
      "grad_norm": 0.39804092049598694,
      "learning_rate": 9.48746740667774e-06,
      "loss": 0.5137,
      "step": 33665
    },
    {
      "epoch": 1.034190397198415,
      "grad_norm": 0.5261709094047546,
      "learning_rate": 9.48698476511717e-06,
      "loss": 0.4327,
      "step": 33666
    },
    {
      "epoch": 1.034221116333364,
      "grad_norm": 0.41537609696388245,
      "learning_rate": 9.486502124754782e-06,
      "loss": 0.5217,
      "step": 33667
    },
    {
      "epoch": 1.0342518354683132,
      "grad_norm": 0.370795875787735,
      "learning_rate": 9.486019485591709e-06,
      "loss": 0.5412,
      "step": 33668
    },
    {
      "epoch": 1.0342825546032623,
      "grad_norm": 0.43003353476524353,
      "learning_rate": 9.485536847629065e-06,
      "loss": 0.4855,
      "step": 33669
    },
    {
      "epoch": 1.0343132737382115,
      "grad_norm": 0.37400534749031067,
      "learning_rate": 9.485054210867993e-06,
      "loss": 0.5032,
      "step": 33670
    },
    {
      "epoch": 1.0343439928731606,
      "grad_norm": 0.372877299785614,
      "learning_rate": 9.484571575309607e-06,
      "loss": 0.5342,
      "step": 33671
    },
    {
      "epoch": 1.03437471200811,
      "grad_norm": 0.408217191696167,
      "learning_rate": 9.484088940955047e-06,
      "loss": 0.5158,
      "step": 33672
    },
    {
      "epoch": 1.034405431143059,
      "grad_norm": 0.5012348294258118,
      "learning_rate": 9.483606307805425e-06,
      "loss": 0.4544,
      "step": 33673
    },
    {
      "epoch": 1.0344361502780082,
      "grad_norm": 0.5342575907707214,
      "learning_rate": 9.483123675861883e-06,
      "loss": 0.4696,
      "step": 33674
    },
    {
      "epoch": 1.0344668694129573,
      "grad_norm": 0.37131088972091675,
      "learning_rate": 9.48264104512554e-06,
      "loss": 0.4533,
      "step": 33675
    },
    {
      "epoch": 1.0344975885479064,
      "grad_norm": 0.41034838557243347,
      "learning_rate": 9.482158415597526e-06,
      "loss": 0.5011,
      "step": 33676
    },
    {
      "epoch": 1.0345283076828558,
      "grad_norm": 0.3687947690486908,
      "learning_rate": 9.481675787278963e-06,
      "loss": 0.497,
      "step": 33677
    },
    {
      "epoch": 1.0345590268178049,
      "grad_norm": 0.4024796783924103,
      "learning_rate": 9.481193160170987e-06,
      "loss": 0.4961,
      "step": 33678
    },
    {
      "epoch": 1.034589745952754,
      "grad_norm": 0.3648204505443573,
      "learning_rate": 9.480710534274718e-06,
      "loss": 0.4874,
      "step": 33679
    },
    {
      "epoch": 1.0346204650877031,
      "grad_norm": 0.3936530649662018,
      "learning_rate": 9.480227909591287e-06,
      "loss": 0.476,
      "step": 33680
    },
    {
      "epoch": 1.0346511842226522,
      "grad_norm": 0.3603692352771759,
      "learning_rate": 9.479745286121819e-06,
      "loss": 0.3972,
      "step": 33681
    },
    {
      "epoch": 1.0346819033576014,
      "grad_norm": 0.4145245850086212,
      "learning_rate": 9.479262663867441e-06,
      "loss": 0.4637,
      "step": 33682
    },
    {
      "epoch": 1.0347126224925507,
      "grad_norm": 0.40731483697891235,
      "learning_rate": 9.478780042829284e-06,
      "loss": 0.5549,
      "step": 33683
    },
    {
      "epoch": 1.0347433416274998,
      "grad_norm": 0.40700316429138184,
      "learning_rate": 9.478297423008471e-06,
      "loss": 0.4712,
      "step": 33684
    },
    {
      "epoch": 1.034774060762449,
      "grad_norm": 0.3532617390155792,
      "learning_rate": 9.477814804406132e-06,
      "loss": 0.5377,
      "step": 33685
    },
    {
      "epoch": 1.034804779897398,
      "grad_norm": 0.3816488981246948,
      "learning_rate": 9.477332187023393e-06,
      "loss": 0.4593,
      "step": 33686
    },
    {
      "epoch": 1.0348354990323472,
      "grad_norm": 0.416494756937027,
      "learning_rate": 9.476849570861381e-06,
      "loss": 0.488,
      "step": 33687
    },
    {
      "epoch": 1.0348662181672965,
      "grad_norm": 0.4066781997680664,
      "learning_rate": 9.476366955921223e-06,
      "loss": 0.5598,
      "step": 33688
    },
    {
      "epoch": 1.0348969373022456,
      "grad_norm": 0.38852617144584656,
      "learning_rate": 9.475884342204046e-06,
      "loss": 0.4881,
      "step": 33689
    },
    {
      "epoch": 1.0349276564371948,
      "grad_norm": 0.37145090103149414,
      "learning_rate": 9.475401729710978e-06,
      "loss": 0.4402,
      "step": 33690
    },
    {
      "epoch": 1.0349583755721439,
      "grad_norm": 0.48576951026916504,
      "learning_rate": 9.474919118443148e-06,
      "loss": 0.503,
      "step": 33691
    },
    {
      "epoch": 1.034989094707093,
      "grad_norm": 0.3850913345813751,
      "learning_rate": 9.474436508401678e-06,
      "loss": 0.5073,
      "step": 33692
    },
    {
      "epoch": 1.0350198138420421,
      "grad_norm": 0.411418080329895,
      "learning_rate": 9.4739538995877e-06,
      "loss": 0.4557,
      "step": 33693
    },
    {
      "epoch": 1.0350505329769915,
      "grad_norm": 0.41617536544799805,
      "learning_rate": 9.473471292002339e-06,
      "loss": 0.4662,
      "step": 33694
    },
    {
      "epoch": 1.0350812521119406,
      "grad_norm": 0.37286391854286194,
      "learning_rate": 9.472988685646724e-06,
      "loss": 0.5271,
      "step": 33695
    },
    {
      "epoch": 1.0351119712468897,
      "grad_norm": 0.35164332389831543,
      "learning_rate": 9.472506080521977e-06,
      "loss": 0.4716,
      "step": 33696
    },
    {
      "epoch": 1.0351426903818388,
      "grad_norm": 0.3709319829940796,
      "learning_rate": 9.472023476629236e-06,
      "loss": 0.5167,
      "step": 33697
    },
    {
      "epoch": 1.035173409516788,
      "grad_norm": 0.3697132468223572,
      "learning_rate": 9.471540873969612e-06,
      "loss": 0.4251,
      "step": 33698
    },
    {
      "epoch": 1.035204128651737,
      "grad_norm": 0.36667218804359436,
      "learning_rate": 9.471058272544243e-06,
      "loss": 0.5753,
      "step": 33699
    },
    {
      "epoch": 1.0352348477866864,
      "grad_norm": 0.39590734243392944,
      "learning_rate": 9.470575672354259e-06,
      "loss": 0.5571,
      "step": 33700
    },
    {
      "epoch": 1.0352655669216355,
      "grad_norm": 0.36856046319007874,
      "learning_rate": 9.470093073400779e-06,
      "loss": 0.5501,
      "step": 33701
    },
    {
      "epoch": 1.0352962860565846,
      "grad_norm": 0.3825017213821411,
      "learning_rate": 9.469610475684939e-06,
      "loss": 0.5011,
      "step": 33702
    },
    {
      "epoch": 1.0353270051915338,
      "grad_norm": 0.4044850468635559,
      "learning_rate": 9.469127879207852e-06,
      "loss": 0.499,
      "step": 33703
    },
    {
      "epoch": 1.0353577243264829,
      "grad_norm": 0.7553992867469788,
      "learning_rate": 9.468645283970663e-06,
      "loss": 0.5073,
      "step": 33704
    },
    {
      "epoch": 1.0353884434614322,
      "grad_norm": 0.3915863037109375,
      "learning_rate": 9.468162689974482e-06,
      "loss": 0.5014,
      "step": 33705
    },
    {
      "epoch": 1.0354191625963813,
      "grad_norm": 0.37790459394454956,
      "learning_rate": 9.46768009722045e-06,
      "loss": 0.5372,
      "step": 33706
    },
    {
      "epoch": 1.0354498817313305,
      "grad_norm": 0.39839670062065125,
      "learning_rate": 9.467197505709683e-06,
      "loss": 0.4376,
      "step": 33707
    },
    {
      "epoch": 1.0354806008662796,
      "grad_norm": 0.4222439229488373,
      "learning_rate": 9.46671491544332e-06,
      "loss": 0.4809,
      "step": 33708
    },
    {
      "epoch": 1.0355113200012287,
      "grad_norm": 0.8665531873703003,
      "learning_rate": 9.466232326422478e-06,
      "loss": 0.4856,
      "step": 33709
    },
    {
      "epoch": 1.0355420391361778,
      "grad_norm": 0.3676523268222809,
      "learning_rate": 9.465749738648289e-06,
      "loss": 0.509,
      "step": 33710
    },
    {
      "epoch": 1.0355727582711272,
      "grad_norm": 0.35791441798210144,
      "learning_rate": 9.465267152121875e-06,
      "loss": 0.4814,
      "step": 33711
    },
    {
      "epoch": 1.0356034774060763,
      "grad_norm": 0.3549646735191345,
      "learning_rate": 9.464784566844371e-06,
      "loss": 0.5733,
      "step": 33712
    },
    {
      "epoch": 1.0356341965410254,
      "grad_norm": 0.4247387647628784,
      "learning_rate": 9.464301982816899e-06,
      "loss": 0.5441,
      "step": 33713
    },
    {
      "epoch": 1.0356649156759745,
      "grad_norm": 0.39582157135009766,
      "learning_rate": 9.463819400040587e-06,
      "loss": 0.444,
      "step": 33714
    },
    {
      "epoch": 1.0356956348109236,
      "grad_norm": 0.384598970413208,
      "learning_rate": 9.463336818516561e-06,
      "loss": 0.5078,
      "step": 33715
    },
    {
      "epoch": 1.035726353945873,
      "grad_norm": 0.39880314469337463,
      "learning_rate": 9.462854238245951e-06,
      "loss": 0.5558,
      "step": 33716
    },
    {
      "epoch": 1.035757073080822,
      "grad_norm": 0.38086724281311035,
      "learning_rate": 9.46237165922988e-06,
      "loss": 0.5281,
      "step": 33717
    },
    {
      "epoch": 1.0357877922157712,
      "grad_norm": 0.4025239944458008,
      "learning_rate": 9.461889081469479e-06,
      "loss": 0.4617,
      "step": 33718
    },
    {
      "epoch": 1.0358185113507203,
      "grad_norm": 0.41131874918937683,
      "learning_rate": 9.461406504965875e-06,
      "loss": 0.5204,
      "step": 33719
    },
    {
      "epoch": 1.0358492304856695,
      "grad_norm": 0.4249606430530548,
      "learning_rate": 9.46092392972019e-06,
      "loss": 0.3928,
      "step": 33720
    },
    {
      "epoch": 1.0358799496206186,
      "grad_norm": 0.3608604669570923,
      "learning_rate": 9.460441355733559e-06,
      "loss": 0.4726,
      "step": 33721
    },
    {
      "epoch": 1.035910668755568,
      "grad_norm": 0.42147380113601685,
      "learning_rate": 9.459958783007103e-06,
      "loss": 0.5451,
      "step": 33722
    },
    {
      "epoch": 1.035941387890517,
      "grad_norm": 0.36037734150886536,
      "learning_rate": 9.459476211541951e-06,
      "loss": 0.5031,
      "step": 33723
    },
    {
      "epoch": 1.0359721070254662,
      "grad_norm": 0.3865375816822052,
      "learning_rate": 9.45899364133923e-06,
      "loss": 0.4477,
      "step": 33724
    },
    {
      "epoch": 1.0360028261604153,
      "grad_norm": 0.4427050054073334,
      "learning_rate": 9.458511072400068e-06,
      "loss": 0.5248,
      "step": 33725
    },
    {
      "epoch": 1.0360335452953644,
      "grad_norm": 0.4027595818042755,
      "learning_rate": 9.458028504725591e-06,
      "loss": 0.6151,
      "step": 33726
    },
    {
      "epoch": 1.0360642644303137,
      "grad_norm": 0.38283294439315796,
      "learning_rate": 9.457545938316926e-06,
      "loss": 0.5254,
      "step": 33727
    },
    {
      "epoch": 1.0360949835652629,
      "grad_norm": 0.34380221366882324,
      "learning_rate": 9.4570633731752e-06,
      "loss": 0.4887,
      "step": 33728
    },
    {
      "epoch": 1.036125702700212,
      "grad_norm": 0.3966551125049591,
      "learning_rate": 9.456580809301542e-06,
      "loss": 0.4599,
      "step": 33729
    },
    {
      "epoch": 1.036156421835161,
      "grad_norm": 0.4437136948108673,
      "learning_rate": 9.456098246697074e-06,
      "loss": 0.5556,
      "step": 33730
    },
    {
      "epoch": 1.0361871409701102,
      "grad_norm": 0.39807382225990295,
      "learning_rate": 9.455615685362932e-06,
      "loss": 0.49,
      "step": 33731
    },
    {
      "epoch": 1.0362178601050593,
      "grad_norm": 0.4055267572402954,
      "learning_rate": 9.455133125300231e-06,
      "loss": 0.5102,
      "step": 33732
    },
    {
      "epoch": 1.0362485792400087,
      "grad_norm": 0.4821641445159912,
      "learning_rate": 9.45465056651011e-06,
      "loss": 0.551,
      "step": 33733
    },
    {
      "epoch": 1.0362792983749578,
      "grad_norm": 0.3857080638408661,
      "learning_rate": 9.454168008993687e-06,
      "loss": 0.5196,
      "step": 33734
    },
    {
      "epoch": 1.036310017509907,
      "grad_norm": 0.3280375003814697,
      "learning_rate": 9.453685452752097e-06,
      "loss": 0.4202,
      "step": 33735
    },
    {
      "epoch": 1.036340736644856,
      "grad_norm": 0.36752453446388245,
      "learning_rate": 9.453202897786457e-06,
      "loss": 0.5097,
      "step": 33736
    },
    {
      "epoch": 1.0363714557798052,
      "grad_norm": 0.40888798236846924,
      "learning_rate": 9.452720344097902e-06,
      "loss": 0.4715,
      "step": 33737
    },
    {
      "epoch": 1.0364021749147545,
      "grad_norm": 0.38939452171325684,
      "learning_rate": 9.45223779168756e-06,
      "loss": 0.5041,
      "step": 33738
    },
    {
      "epoch": 1.0364328940497036,
      "grad_norm": 0.37522274255752563,
      "learning_rate": 9.45175524055655e-06,
      "loss": 0.5316,
      "step": 33739
    },
    {
      "epoch": 1.0364636131846527,
      "grad_norm": 0.3929535150527954,
      "learning_rate": 9.45127269070601e-06,
      "loss": 0.5227,
      "step": 33740
    },
    {
      "epoch": 1.0364943323196019,
      "grad_norm": 0.33887264132499695,
      "learning_rate": 9.450790142137054e-06,
      "loss": 0.5267,
      "step": 33741
    },
    {
      "epoch": 1.036525051454551,
      "grad_norm": 0.4202176332473755,
      "learning_rate": 9.450307594850824e-06,
      "loss": 0.5593,
      "step": 33742
    },
    {
      "epoch": 1.0365557705895,
      "grad_norm": 0.3413526713848114,
      "learning_rate": 9.449825048848433e-06,
      "loss": 0.4525,
      "step": 33743
    },
    {
      "epoch": 1.0365864897244494,
      "grad_norm": 0.3438032567501068,
      "learning_rate": 9.449342504131016e-06,
      "loss": 0.5715,
      "step": 33744
    },
    {
      "epoch": 1.0366172088593986,
      "grad_norm": 0.38898295164108276,
      "learning_rate": 9.448859960699697e-06,
      "loss": 0.4628,
      "step": 33745
    },
    {
      "epoch": 1.0366479279943477,
      "grad_norm": 0.42098361253738403,
      "learning_rate": 9.448377418555606e-06,
      "loss": 0.5606,
      "step": 33746
    },
    {
      "epoch": 1.0366786471292968,
      "grad_norm": 0.3673853278160095,
      "learning_rate": 9.447894877699867e-06,
      "loss": 0.5117,
      "step": 33747
    },
    {
      "epoch": 1.036709366264246,
      "grad_norm": 0.4359983801841736,
      "learning_rate": 9.447412338133608e-06,
      "loss": 0.5197,
      "step": 33748
    },
    {
      "epoch": 1.0367400853991953,
      "grad_norm": 0.3711196482181549,
      "learning_rate": 9.446929799857954e-06,
      "loss": 0.4955,
      "step": 33749
    },
    {
      "epoch": 1.0367708045341444,
      "grad_norm": 0.41533851623535156,
      "learning_rate": 9.446447262874036e-06,
      "loss": 0.4457,
      "step": 33750
    },
    {
      "epoch": 1.0368015236690935,
      "grad_norm": 0.37187743186950684,
      "learning_rate": 9.44596472718298e-06,
      "loss": 0.526,
      "step": 33751
    },
    {
      "epoch": 1.0368322428040426,
      "grad_norm": 0.3775397539138794,
      "learning_rate": 9.44548219278591e-06,
      "loss": 0.5249,
      "step": 33752
    },
    {
      "epoch": 1.0368629619389917,
      "grad_norm": 0.4393284022808075,
      "learning_rate": 9.444999659683956e-06,
      "loss": 0.5212,
      "step": 33753
    },
    {
      "epoch": 1.0368936810739409,
      "grad_norm": 0.3860146701335907,
      "learning_rate": 9.444517127878244e-06,
      "loss": 0.5083,
      "step": 33754
    },
    {
      "epoch": 1.0369244002088902,
      "grad_norm": 0.3938135802745819,
      "learning_rate": 9.444034597369902e-06,
      "loss": 0.5279,
      "step": 33755
    },
    {
      "epoch": 1.0369551193438393,
      "grad_norm": 0.35082441568374634,
      "learning_rate": 9.443552068160053e-06,
      "loss": 0.4503,
      "step": 33756
    },
    {
      "epoch": 1.0369858384787884,
      "grad_norm": 0.4190543293952942,
      "learning_rate": 9.443069540249831e-06,
      "loss": 0.5149,
      "step": 33757
    },
    {
      "epoch": 1.0370165576137376,
      "grad_norm": 0.4050571024417877,
      "learning_rate": 9.442587013640357e-06,
      "loss": 0.4796,
      "step": 33758
    },
    {
      "epoch": 1.0370472767486867,
      "grad_norm": 0.384962260723114,
      "learning_rate": 9.442104488332761e-06,
      "loss": 0.49,
      "step": 33759
    },
    {
      "epoch": 1.037077995883636,
      "grad_norm": 0.36867278814315796,
      "learning_rate": 9.441621964328168e-06,
      "loss": 0.5236,
      "step": 33760
    },
    {
      "epoch": 1.0371087150185851,
      "grad_norm": 0.3817111551761627,
      "learning_rate": 9.441139441627705e-06,
      "loss": 0.489,
      "step": 33761
    },
    {
      "epoch": 1.0371394341535343,
      "grad_norm": 0.3951494097709656,
      "learning_rate": 9.4406569202325e-06,
      "loss": 0.5592,
      "step": 33762
    },
    {
      "epoch": 1.0371701532884834,
      "grad_norm": 0.3865242004394531,
      "learning_rate": 9.440174400143682e-06,
      "loss": 0.4623,
      "step": 33763
    },
    {
      "epoch": 1.0372008724234325,
      "grad_norm": 0.3891184329986572,
      "learning_rate": 9.439691881362374e-06,
      "loss": 0.5061,
      "step": 33764
    },
    {
      "epoch": 1.0372315915583816,
      "grad_norm": 0.45926278829574585,
      "learning_rate": 9.439209363889709e-06,
      "loss": 0.5231,
      "step": 33765
    },
    {
      "epoch": 1.037262310693331,
      "grad_norm": 0.3831252455711365,
      "learning_rate": 9.438726847726802e-06,
      "loss": 0.4975,
      "step": 33766
    },
    {
      "epoch": 1.03729302982828,
      "grad_norm": 0.3840726912021637,
      "learning_rate": 9.438244332874794e-06,
      "loss": 0.4886,
      "step": 33767
    },
    {
      "epoch": 1.0373237489632292,
      "grad_norm": 0.4211612343788147,
      "learning_rate": 9.4377618193348e-06,
      "loss": 0.4336,
      "step": 33768
    },
    {
      "epoch": 1.0373544680981783,
      "grad_norm": 0.371273398399353,
      "learning_rate": 9.437279307107961e-06,
      "loss": 0.4944,
      "step": 33769
    },
    {
      "epoch": 1.0373851872331274,
      "grad_norm": 0.36957719922065735,
      "learning_rate": 9.436796796195387e-06,
      "loss": 0.5271,
      "step": 33770
    },
    {
      "epoch": 1.0374159063680766,
      "grad_norm": 0.3766572177410126,
      "learning_rate": 9.436314286598219e-06,
      "loss": 0.4905,
      "step": 33771
    },
    {
      "epoch": 1.037446625503026,
      "grad_norm": 0.374370813369751,
      "learning_rate": 9.435831778317574e-06,
      "loss": 0.474,
      "step": 33772
    },
    {
      "epoch": 1.037477344637975,
      "grad_norm": 0.38875070214271545,
      "learning_rate": 9.435349271354584e-06,
      "loss": 0.5487,
      "step": 33773
    },
    {
      "epoch": 1.0375080637729241,
      "grad_norm": 0.36809226870536804,
      "learning_rate": 9.434866765710378e-06,
      "loss": 0.465,
      "step": 33774
    },
    {
      "epoch": 1.0375387829078733,
      "grad_norm": 0.3961772620677948,
      "learning_rate": 9.434384261386075e-06,
      "loss": 0.4854,
      "step": 33775
    },
    {
      "epoch": 1.0375695020428224,
      "grad_norm": 0.3869054913520813,
      "learning_rate": 9.433901758382815e-06,
      "loss": 0.5444,
      "step": 33776
    },
    {
      "epoch": 1.0376002211777717,
      "grad_norm": 0.3929774761199951,
      "learning_rate": 9.433419256701709e-06,
      "loss": 0.513,
      "step": 33777
    },
    {
      "epoch": 1.0376309403127209,
      "grad_norm": 0.3766538202762604,
      "learning_rate": 9.4329367563439e-06,
      "loss": 0.4089,
      "step": 33778
    },
    {
      "epoch": 1.03766165944767,
      "grad_norm": 0.48099493980407715,
      "learning_rate": 9.4324542573105e-06,
      "loss": 0.5065,
      "step": 33779
    },
    {
      "epoch": 1.037692378582619,
      "grad_norm": 0.36160045862197876,
      "learning_rate": 9.431971759602646e-06,
      "loss": 0.4804,
      "step": 33780
    },
    {
      "epoch": 1.0377230977175682,
      "grad_norm": 0.373038649559021,
      "learning_rate": 9.431489263221461e-06,
      "loss": 0.5385,
      "step": 33781
    },
    {
      "epoch": 1.0377538168525173,
      "grad_norm": 0.3455847501754761,
      "learning_rate": 9.431006768168072e-06,
      "loss": 0.4794,
      "step": 33782
    },
    {
      "epoch": 1.0377845359874667,
      "grad_norm": 0.33582910895347595,
      "learning_rate": 9.430524274443606e-06,
      "loss": 0.4831,
      "step": 33783
    },
    {
      "epoch": 1.0378152551224158,
      "grad_norm": 0.5981481075286865,
      "learning_rate": 9.430041782049193e-06,
      "loss": 0.5388,
      "step": 33784
    },
    {
      "epoch": 1.037845974257365,
      "grad_norm": 0.3707377314567566,
      "learning_rate": 9.429559290985953e-06,
      "loss": 0.5484,
      "step": 33785
    },
    {
      "epoch": 1.037876693392314,
      "grad_norm": 0.4031006395816803,
      "learning_rate": 9.429076801255021e-06,
      "loss": 0.4544,
      "step": 33786
    },
    {
      "epoch": 1.0379074125272632,
      "grad_norm": 0.3860076367855072,
      "learning_rate": 9.428594312857518e-06,
      "loss": 0.5428,
      "step": 33787
    },
    {
      "epoch": 1.0379381316622125,
      "grad_norm": 0.41352686285972595,
      "learning_rate": 9.428111825794574e-06,
      "loss": 0.5176,
      "step": 33788
    },
    {
      "epoch": 1.0379688507971616,
      "grad_norm": 0.4082614481449127,
      "learning_rate": 9.427629340067313e-06,
      "loss": 0.5278,
      "step": 33789
    },
    {
      "epoch": 1.0379995699321107,
      "grad_norm": 0.4219139516353607,
      "learning_rate": 9.427146855676865e-06,
      "loss": 0.5225,
      "step": 33790
    },
    {
      "epoch": 1.0380302890670599,
      "grad_norm": 0.37652918696403503,
      "learning_rate": 9.426664372624355e-06,
      "loss": 0.4717,
      "step": 33791
    },
    {
      "epoch": 1.038061008202009,
      "grad_norm": 0.39649125933647156,
      "learning_rate": 9.42618189091091e-06,
      "loss": 0.4826,
      "step": 33792
    },
    {
      "epoch": 1.038091727336958,
      "grad_norm": 0.42278069257736206,
      "learning_rate": 9.425699410537658e-06,
      "loss": 0.3934,
      "step": 33793
    },
    {
      "epoch": 1.0381224464719074,
      "grad_norm": 0.43329957127571106,
      "learning_rate": 9.425216931505723e-06,
      "loss": 0.5703,
      "step": 33794
    },
    {
      "epoch": 1.0381531656068566,
      "grad_norm": 0.3991699516773224,
      "learning_rate": 9.424734453816237e-06,
      "loss": 0.4674,
      "step": 33795
    },
    {
      "epoch": 1.0381838847418057,
      "grad_norm": 0.3912006616592407,
      "learning_rate": 9.424251977470322e-06,
      "loss": 0.4902,
      "step": 33796
    },
    {
      "epoch": 1.0382146038767548,
      "grad_norm": 0.35498881340026855,
      "learning_rate": 9.423769502469109e-06,
      "loss": 0.4254,
      "step": 33797
    },
    {
      "epoch": 1.038245323011704,
      "grad_norm": 0.45073068141937256,
      "learning_rate": 9.42328702881372e-06,
      "loss": 0.495,
      "step": 33798
    },
    {
      "epoch": 1.0382760421466533,
      "grad_norm": 0.4104717969894409,
      "learning_rate": 9.422804556505288e-06,
      "loss": 0.5189,
      "step": 33799
    },
    {
      "epoch": 1.0383067612816024,
      "grad_norm": 0.46193504333496094,
      "learning_rate": 9.422322085544932e-06,
      "loss": 0.4924,
      "step": 33800
    },
    {
      "epoch": 1.0383374804165515,
      "grad_norm": 0.3780488073825836,
      "learning_rate": 9.421839615933787e-06,
      "loss": 0.5016,
      "step": 33801
    },
    {
      "epoch": 1.0383681995515006,
      "grad_norm": 0.3686734437942505,
      "learning_rate": 9.421357147672971e-06,
      "loss": 0.4862,
      "step": 33802
    },
    {
      "epoch": 1.0383989186864497,
      "grad_norm": 0.37339478731155396,
      "learning_rate": 9.420874680763623e-06,
      "loss": 0.5373,
      "step": 33803
    },
    {
      "epoch": 1.0384296378213989,
      "grad_norm": 0.35889995098114014,
      "learning_rate": 9.420392215206855e-06,
      "loss": 0.4875,
      "step": 33804
    },
    {
      "epoch": 1.0384603569563482,
      "grad_norm": 0.37178847193717957,
      "learning_rate": 9.419909751003808e-06,
      "loss": 0.5362,
      "step": 33805
    },
    {
      "epoch": 1.0384910760912973,
      "grad_norm": 0.3835752308368683,
      "learning_rate": 9.419427288155596e-06,
      "loss": 0.4591,
      "step": 33806
    },
    {
      "epoch": 1.0385217952262464,
      "grad_norm": 0.37446051836013794,
      "learning_rate": 9.418944826663358e-06,
      "loss": 0.4719,
      "step": 33807
    },
    {
      "epoch": 1.0385525143611956,
      "grad_norm": 0.518743634223938,
      "learning_rate": 9.418462366528211e-06,
      "loss": 0.5441,
      "step": 33808
    },
    {
      "epoch": 1.0385832334961447,
      "grad_norm": 0.41384661197662354,
      "learning_rate": 9.417979907751284e-06,
      "loss": 0.4868,
      "step": 33809
    },
    {
      "epoch": 1.0386139526310938,
      "grad_norm": 0.39369693398475647,
      "learning_rate": 9.41749745033371e-06,
      "loss": 0.5738,
      "step": 33810
    },
    {
      "epoch": 1.0386446717660431,
      "grad_norm": 0.40111789107322693,
      "learning_rate": 9.417014994276608e-06,
      "loss": 0.6276,
      "step": 33811
    },
    {
      "epoch": 1.0386753909009923,
      "grad_norm": 0.3728591203689575,
      "learning_rate": 9.416532539581114e-06,
      "loss": 0.5597,
      "step": 33812
    },
    {
      "epoch": 1.0387061100359414,
      "grad_norm": 0.43673962354660034,
      "learning_rate": 9.416050086248343e-06,
      "loss": 0.4758,
      "step": 33813
    },
    {
      "epoch": 1.0387368291708905,
      "grad_norm": 0.3707500100135803,
      "learning_rate": 9.415567634279431e-06,
      "loss": 0.4978,
      "step": 33814
    },
    {
      "epoch": 1.0387675483058396,
      "grad_norm": 0.9526381492614746,
      "learning_rate": 9.4150851836755e-06,
      "loss": 0.5573,
      "step": 33815
    },
    {
      "epoch": 1.038798267440789,
      "grad_norm": 0.41794353723526,
      "learning_rate": 9.41460273443768e-06,
      "loss": 0.4917,
      "step": 33816
    },
    {
      "epoch": 1.038828986575738,
      "grad_norm": 0.4083116054534912,
      "learning_rate": 9.414120286567094e-06,
      "loss": 0.5625,
      "step": 33817
    },
    {
      "epoch": 1.0388597057106872,
      "grad_norm": 0.3585303723812103,
      "learning_rate": 9.413637840064873e-06,
      "loss": 0.5411,
      "step": 33818
    },
    {
      "epoch": 1.0388904248456363,
      "grad_norm": 0.353134423494339,
      "learning_rate": 9.413155394932139e-06,
      "loss": 0.4831,
      "step": 33819
    },
    {
      "epoch": 1.0389211439805854,
      "grad_norm": 0.3923119902610779,
      "learning_rate": 9.412672951170024e-06,
      "loss": 0.475,
      "step": 33820
    },
    {
      "epoch": 1.0389518631155346,
      "grad_norm": 0.36057692766189575,
      "learning_rate": 9.412190508779652e-06,
      "loss": 0.4651,
      "step": 33821
    },
    {
      "epoch": 1.038982582250484,
      "grad_norm": 0.39349693059921265,
      "learning_rate": 9.411708067762152e-06,
      "loss": 0.4936,
      "step": 33822
    },
    {
      "epoch": 1.039013301385433,
      "grad_norm": 0.5095657110214233,
      "learning_rate": 9.411225628118645e-06,
      "loss": 0.5194,
      "step": 33823
    },
    {
      "epoch": 1.0390440205203821,
      "grad_norm": 0.34030646085739136,
      "learning_rate": 9.410743189850264e-06,
      "loss": 0.418,
      "step": 33824
    },
    {
      "epoch": 1.0390747396553313,
      "grad_norm": 0.419024795293808,
      "learning_rate": 9.410260752958132e-06,
      "loss": 0.4796,
      "step": 33825
    },
    {
      "epoch": 1.0391054587902804,
      "grad_norm": 0.32751670479774475,
      "learning_rate": 9.409778317443379e-06,
      "loss": 0.4224,
      "step": 33826
    },
    {
      "epoch": 1.0391361779252297,
      "grad_norm": 0.39762330055236816,
      "learning_rate": 9.409295883307128e-06,
      "loss": 0.5437,
      "step": 33827
    },
    {
      "epoch": 1.0391668970601788,
      "grad_norm": 0.5234258770942688,
      "learning_rate": 9.408813450550507e-06,
      "loss": 0.4289,
      "step": 33828
    },
    {
      "epoch": 1.039197616195128,
      "grad_norm": 0.38787323236465454,
      "learning_rate": 9.408331019174647e-06,
      "loss": 0.531,
      "step": 33829
    },
    {
      "epoch": 1.039228335330077,
      "grad_norm": 0.3598477244377136,
      "learning_rate": 9.407848589180668e-06,
      "loss": 0.483,
      "step": 33830
    },
    {
      "epoch": 1.0392590544650262,
      "grad_norm": 0.3682362735271454,
      "learning_rate": 9.407366160569702e-06,
      "loss": 0.4829,
      "step": 33831
    },
    {
      "epoch": 1.0392897735999753,
      "grad_norm": 0.3700944185256958,
      "learning_rate": 9.406883733342872e-06,
      "loss": 0.5176,
      "step": 33832
    },
    {
      "epoch": 1.0393204927349247,
      "grad_norm": 0.37620213627815247,
      "learning_rate": 9.406401307501308e-06,
      "loss": 0.5232,
      "step": 33833
    },
    {
      "epoch": 1.0393512118698738,
      "grad_norm": 0.3979595899581909,
      "learning_rate": 9.405918883046135e-06,
      "loss": 0.5663,
      "step": 33834
    },
    {
      "epoch": 1.039381931004823,
      "grad_norm": 0.36733654141426086,
      "learning_rate": 9.405436459978482e-06,
      "loss": 0.4733,
      "step": 33835
    },
    {
      "epoch": 1.039412650139772,
      "grad_norm": 0.39925676584243774,
      "learning_rate": 9.404954038299469e-06,
      "loss": 0.5796,
      "step": 33836
    },
    {
      "epoch": 1.0394433692747211,
      "grad_norm": 0.3995209336280823,
      "learning_rate": 9.404471618010233e-06,
      "loss": 0.5863,
      "step": 33837
    },
    {
      "epoch": 1.0394740884096705,
      "grad_norm": 0.42794713377952576,
      "learning_rate": 9.403989199111888e-06,
      "loss": 0.5245,
      "step": 33838
    },
    {
      "epoch": 1.0395048075446196,
      "grad_norm": 0.5534713268280029,
      "learning_rate": 9.403506781605575e-06,
      "loss": 0.6298,
      "step": 33839
    },
    {
      "epoch": 1.0395355266795687,
      "grad_norm": 0.43000295758247375,
      "learning_rate": 9.403024365492406e-06,
      "loss": 0.4907,
      "step": 33840
    },
    {
      "epoch": 1.0395662458145178,
      "grad_norm": 0.3733818233013153,
      "learning_rate": 9.402541950773523e-06,
      "loss": 0.4942,
      "step": 33841
    },
    {
      "epoch": 1.039596964949467,
      "grad_norm": 0.40258291363716125,
      "learning_rate": 9.40205953745004e-06,
      "loss": 0.5118,
      "step": 33842
    },
    {
      "epoch": 1.039627684084416,
      "grad_norm": 0.7758044004440308,
      "learning_rate": 9.401577125523092e-06,
      "loss": 0.4428,
      "step": 33843
    },
    {
      "epoch": 1.0396584032193654,
      "grad_norm": 0.3806062936782837,
      "learning_rate": 9.4010947149938e-06,
      "loss": 0.5337,
      "step": 33844
    },
    {
      "epoch": 1.0396891223543145,
      "grad_norm": 0.37536656856536865,
      "learning_rate": 9.400612305863291e-06,
      "loss": 0.5072,
      "step": 33845
    },
    {
      "epoch": 1.0397198414892637,
      "grad_norm": 0.4356875419616699,
      "learning_rate": 9.400129898132701e-06,
      "loss": 0.5063,
      "step": 33846
    },
    {
      "epoch": 1.0397505606242128,
      "grad_norm": 0.4338480830192566,
      "learning_rate": 9.39964749180314e-06,
      "loss": 0.4788,
      "step": 33847
    },
    {
      "epoch": 1.039781279759162,
      "grad_norm": 0.4010075628757477,
      "learning_rate": 9.399165086875754e-06,
      "loss": 0.4968,
      "step": 33848
    },
    {
      "epoch": 1.0398119988941112,
      "grad_norm": 0.44060149788856506,
      "learning_rate": 9.398682683351654e-06,
      "loss": 0.4381,
      "step": 33849
    },
    {
      "epoch": 1.0398427180290604,
      "grad_norm": 0.39950016140937805,
      "learning_rate": 9.398200281231975e-06,
      "loss": 0.4635,
      "step": 33850
    },
    {
      "epoch": 1.0398734371640095,
      "grad_norm": 0.39230993390083313,
      "learning_rate": 9.39771788051784e-06,
      "loss": 0.5043,
      "step": 33851
    },
    {
      "epoch": 1.0399041562989586,
      "grad_norm": 0.43306928873062134,
      "learning_rate": 9.397235481210377e-06,
      "loss": 0.5064,
      "step": 33852
    },
    {
      "epoch": 1.0399348754339077,
      "grad_norm": 0.35705089569091797,
      "learning_rate": 9.396753083310713e-06,
      "loss": 0.4464,
      "step": 33853
    },
    {
      "epoch": 1.0399655945688568,
      "grad_norm": 0.42507463693618774,
      "learning_rate": 9.396270686819974e-06,
      "loss": 0.5049,
      "step": 33854
    },
    {
      "epoch": 1.0399963137038062,
      "grad_norm": 0.38845598697662354,
      "learning_rate": 9.395788291739287e-06,
      "loss": 0.5012,
      "step": 33855
    },
    {
      "epoch": 1.0400270328387553,
      "grad_norm": 0.9788706302642822,
      "learning_rate": 9.395305898069779e-06,
      "loss": 0.5197,
      "step": 33856
    },
    {
      "epoch": 1.0400577519737044,
      "grad_norm": 0.3597688674926758,
      "learning_rate": 9.394823505812575e-06,
      "loss": 0.5079,
      "step": 33857
    },
    {
      "epoch": 1.0400884711086535,
      "grad_norm": 0.40301719307899475,
      "learning_rate": 9.394341114968805e-06,
      "loss": 0.5436,
      "step": 33858
    },
    {
      "epoch": 1.0401191902436027,
      "grad_norm": 0.3918842673301697,
      "learning_rate": 9.393858725539591e-06,
      "loss": 0.5419,
      "step": 33859
    },
    {
      "epoch": 1.040149909378552,
      "grad_norm": 0.365330308675766,
      "learning_rate": 9.393376337526065e-06,
      "loss": 0.524,
      "step": 33860
    },
    {
      "epoch": 1.0401806285135011,
      "grad_norm": 0.3826327323913574,
      "learning_rate": 9.39289395092935e-06,
      "loss": 0.4618,
      "step": 33861
    },
    {
      "epoch": 1.0402113476484502,
      "grad_norm": 0.5597448945045471,
      "learning_rate": 9.392411565750573e-06,
      "loss": 0.408,
      "step": 33862
    },
    {
      "epoch": 1.0402420667833994,
      "grad_norm": 0.4863584637641907,
      "learning_rate": 9.391929181990861e-06,
      "loss": 0.5528,
      "step": 33863
    },
    {
      "epoch": 1.0402727859183485,
      "grad_norm": 0.5098206996917725,
      "learning_rate": 9.39144679965134e-06,
      "loss": 0.5515,
      "step": 33864
    },
    {
      "epoch": 1.0403035050532976,
      "grad_norm": 0.3945404291152954,
      "learning_rate": 9.39096441873314e-06,
      "loss": 0.4812,
      "step": 33865
    },
    {
      "epoch": 1.040334224188247,
      "grad_norm": 0.49432435631752014,
      "learning_rate": 9.390482039237383e-06,
      "loss": 0.4279,
      "step": 33866
    },
    {
      "epoch": 1.040364943323196,
      "grad_norm": 0.557635486125946,
      "learning_rate": 9.3899996611652e-06,
      "loss": 0.507,
      "step": 33867
    },
    {
      "epoch": 1.0403956624581452,
      "grad_norm": 0.42762675881385803,
      "learning_rate": 9.389517284517713e-06,
      "loss": 0.472,
      "step": 33868
    },
    {
      "epoch": 1.0404263815930943,
      "grad_norm": 0.6030056476593018,
      "learning_rate": 9.389034909296053e-06,
      "loss": 0.5083,
      "step": 33869
    },
    {
      "epoch": 1.0404571007280434,
      "grad_norm": 0.43824467062950134,
      "learning_rate": 9.388552535501343e-06,
      "loss": 0.5073,
      "step": 33870
    },
    {
      "epoch": 1.0404878198629928,
      "grad_norm": 0.40402936935424805,
      "learning_rate": 9.388070163134716e-06,
      "loss": 0.5044,
      "step": 33871
    },
    {
      "epoch": 1.0405185389979419,
      "grad_norm": 0.3461920917034149,
      "learning_rate": 9.387587792197287e-06,
      "loss": 0.521,
      "step": 33872
    },
    {
      "epoch": 1.040549258132891,
      "grad_norm": 0.41666826605796814,
      "learning_rate": 9.387105422690195e-06,
      "loss": 0.5484,
      "step": 33873
    },
    {
      "epoch": 1.0405799772678401,
      "grad_norm": 0.36135125160217285,
      "learning_rate": 9.386623054614555e-06,
      "loss": 0.5189,
      "step": 33874
    },
    {
      "epoch": 1.0406106964027892,
      "grad_norm": 0.4081341326236725,
      "learning_rate": 9.386140687971508e-06,
      "loss": 0.5168,
      "step": 33875
    },
    {
      "epoch": 1.0406414155377384,
      "grad_norm": 0.43410253524780273,
      "learning_rate": 9.385658322762166e-06,
      "loss": 0.4516,
      "step": 33876
    },
    {
      "epoch": 1.0406721346726877,
      "grad_norm": 0.40912026166915894,
      "learning_rate": 9.385175958987665e-06,
      "loss": 0.48,
      "step": 33877
    },
    {
      "epoch": 1.0407028538076368,
      "grad_norm": 0.3561113476753235,
      "learning_rate": 9.384693596649125e-06,
      "loss": 0.4528,
      "step": 33878
    },
    {
      "epoch": 1.040733572942586,
      "grad_norm": 0.372723251581192,
      "learning_rate": 9.38421123574768e-06,
      "loss": 0.5242,
      "step": 33879
    },
    {
      "epoch": 1.040764292077535,
      "grad_norm": 0.4106674790382385,
      "learning_rate": 9.383728876284449e-06,
      "loss": 0.4567,
      "step": 33880
    },
    {
      "epoch": 1.0407950112124842,
      "grad_norm": 0.37160825729370117,
      "learning_rate": 9.383246518260564e-06,
      "loss": 0.4795,
      "step": 33881
    },
    {
      "epoch": 1.0408257303474333,
      "grad_norm": 0.39917269349098206,
      "learning_rate": 9.382764161677149e-06,
      "loss": 0.548,
      "step": 33882
    },
    {
      "epoch": 1.0408564494823827,
      "grad_norm": 0.36386266350746155,
      "learning_rate": 9.382281806535331e-06,
      "loss": 0.5278,
      "step": 33883
    },
    {
      "epoch": 1.0408871686173318,
      "grad_norm": 0.4064784049987793,
      "learning_rate": 9.38179945283624e-06,
      "loss": 0.5675,
      "step": 33884
    },
    {
      "epoch": 1.040917887752281,
      "grad_norm": 0.3742906153202057,
      "learning_rate": 9.381317100580996e-06,
      "loss": 0.4771,
      "step": 33885
    },
    {
      "epoch": 1.04094860688723,
      "grad_norm": 0.388448566198349,
      "learning_rate": 9.380834749770734e-06,
      "loss": 0.4874,
      "step": 33886
    },
    {
      "epoch": 1.0409793260221791,
      "grad_norm": 0.502800464630127,
      "learning_rate": 9.38035240040657e-06,
      "loss": 0.5626,
      "step": 33887
    },
    {
      "epoch": 1.0410100451571285,
      "grad_norm": 0.4490084946155548,
      "learning_rate": 9.37987005248964e-06,
      "loss": 0.5991,
      "step": 33888
    },
    {
      "epoch": 1.0410407642920776,
      "grad_norm": 0.4405173361301422,
      "learning_rate": 9.379387706021065e-06,
      "loss": 0.5133,
      "step": 33889
    },
    {
      "epoch": 1.0410714834270267,
      "grad_norm": 0.4163747727870941,
      "learning_rate": 9.378905361001974e-06,
      "loss": 0.5283,
      "step": 33890
    },
    {
      "epoch": 1.0411022025619758,
      "grad_norm": 0.3772214353084564,
      "learning_rate": 9.378423017433493e-06,
      "loss": 0.4014,
      "step": 33891
    },
    {
      "epoch": 1.041132921696925,
      "grad_norm": 0.39828068017959595,
      "learning_rate": 9.37794067531675e-06,
      "loss": 0.513,
      "step": 33892
    },
    {
      "epoch": 1.041163640831874,
      "grad_norm": 0.39384377002716064,
      "learning_rate": 9.377458334652866e-06,
      "loss": 0.5412,
      "step": 33893
    },
    {
      "epoch": 1.0411943599668234,
      "grad_norm": 0.41701069474220276,
      "learning_rate": 9.376975995442976e-06,
      "loss": 0.4882,
      "step": 33894
    },
    {
      "epoch": 1.0412250791017725,
      "grad_norm": 0.37594661116600037,
      "learning_rate": 9.376493657688197e-06,
      "loss": 0.4639,
      "step": 33895
    },
    {
      "epoch": 1.0412557982367217,
      "grad_norm": 0.4074537456035614,
      "learning_rate": 9.376011321389665e-06,
      "loss": 0.4971,
      "step": 33896
    },
    {
      "epoch": 1.0412865173716708,
      "grad_norm": 0.35641980171203613,
      "learning_rate": 9.3755289865485e-06,
      "loss": 0.5848,
      "step": 33897
    },
    {
      "epoch": 1.04131723650662,
      "grad_norm": 0.3653149902820587,
      "learning_rate": 9.375046653165835e-06,
      "loss": 0.4829,
      "step": 33898
    },
    {
      "epoch": 1.0413479556415692,
      "grad_norm": 0.39032885432243347,
      "learning_rate": 9.374564321242785e-06,
      "loss": 0.5144,
      "step": 33899
    },
    {
      "epoch": 1.0413786747765184,
      "grad_norm": 0.37186405062675476,
      "learning_rate": 9.374081990780486e-06,
      "loss": 0.4651,
      "step": 33900
    },
    {
      "epoch": 1.0414093939114675,
      "grad_norm": 0.3589050769805908,
      "learning_rate": 9.373599661780064e-06,
      "loss": 0.4973,
      "step": 33901
    },
    {
      "epoch": 1.0414401130464166,
      "grad_norm": 0.37161508202552795,
      "learning_rate": 9.373117334242642e-06,
      "loss": 0.4622,
      "step": 33902
    },
    {
      "epoch": 1.0414708321813657,
      "grad_norm": 0.36272600293159485,
      "learning_rate": 9.372635008169351e-06,
      "loss": 0.507,
      "step": 33903
    },
    {
      "epoch": 1.0415015513163148,
      "grad_norm": 0.39590010046958923,
      "learning_rate": 9.372152683561311e-06,
      "loss": 0.5074,
      "step": 33904
    },
    {
      "epoch": 1.0415322704512642,
      "grad_norm": 0.420081228017807,
      "learning_rate": 9.371670360419658e-06,
      "loss": 0.5939,
      "step": 33905
    },
    {
      "epoch": 1.0415629895862133,
      "grad_norm": 0.393181711435318,
      "learning_rate": 9.371188038745506e-06,
      "loss": 0.4679,
      "step": 33906
    },
    {
      "epoch": 1.0415937087211624,
      "grad_norm": 0.3715534210205078,
      "learning_rate": 9.370705718539996e-06,
      "loss": 0.513,
      "step": 33907
    },
    {
      "epoch": 1.0416244278561115,
      "grad_norm": 0.39615944027900696,
      "learning_rate": 9.370223399804239e-06,
      "loss": 0.4867,
      "step": 33908
    },
    {
      "epoch": 1.0416551469910607,
      "grad_norm": 0.3470612168312073,
      "learning_rate": 9.369741082539374e-06,
      "loss": 0.4314,
      "step": 33909
    },
    {
      "epoch": 1.04168586612601,
      "grad_norm": 0.3669474422931671,
      "learning_rate": 9.369258766746518e-06,
      "loss": 0.5097,
      "step": 33910
    },
    {
      "epoch": 1.0417165852609591,
      "grad_norm": 0.37576407194137573,
      "learning_rate": 9.36877645242681e-06,
      "loss": 0.5291,
      "step": 33911
    },
    {
      "epoch": 1.0417473043959082,
      "grad_norm": 0.3884713053703308,
      "learning_rate": 9.368294139581362e-06,
      "loss": 0.5108,
      "step": 33912
    },
    {
      "epoch": 1.0417780235308574,
      "grad_norm": 0.36889877915382385,
      "learning_rate": 9.367811828211311e-06,
      "loss": 0.494,
      "step": 33913
    },
    {
      "epoch": 1.0418087426658065,
      "grad_norm": 0.36724627017974854,
      "learning_rate": 9.367329518317775e-06,
      "loss": 0.4039,
      "step": 33914
    },
    {
      "epoch": 1.0418394618007556,
      "grad_norm": 0.41770726442337036,
      "learning_rate": 9.36684720990189e-06,
      "loss": 0.5493,
      "step": 33915
    },
    {
      "epoch": 1.041870180935705,
      "grad_norm": 0.43041613698005676,
      "learning_rate": 9.366364902964775e-06,
      "loss": 0.5213,
      "step": 33916
    },
    {
      "epoch": 1.041900900070654,
      "grad_norm": 0.38779252767562866,
      "learning_rate": 9.36588259750756e-06,
      "loss": 0.5156,
      "step": 33917
    },
    {
      "epoch": 1.0419316192056032,
      "grad_norm": 0.3704081177711487,
      "learning_rate": 9.365400293531369e-06,
      "loss": 0.5838,
      "step": 33918
    },
    {
      "epoch": 1.0419623383405523,
      "grad_norm": 0.41516759991645813,
      "learning_rate": 9.36491799103733e-06,
      "loss": 0.5234,
      "step": 33919
    },
    {
      "epoch": 1.0419930574755014,
      "grad_norm": 0.380435973405838,
      "learning_rate": 9.364435690026572e-06,
      "loss": 0.4611,
      "step": 33920
    },
    {
      "epoch": 1.0420237766104505,
      "grad_norm": 0.37077704071998596,
      "learning_rate": 9.363953390500214e-06,
      "loss": 0.4786,
      "step": 33921
    },
    {
      "epoch": 1.0420544957453999,
      "grad_norm": 0.3887590169906616,
      "learning_rate": 9.363471092459393e-06,
      "loss": 0.4423,
      "step": 33922
    },
    {
      "epoch": 1.042085214880349,
      "grad_norm": 0.4139353036880493,
      "learning_rate": 9.362988795905226e-06,
      "loss": 0.4915,
      "step": 33923
    },
    {
      "epoch": 1.0421159340152981,
      "grad_norm": 0.3420692980289459,
      "learning_rate": 9.362506500838846e-06,
      "loss": 0.4714,
      "step": 33924
    },
    {
      "epoch": 1.0421466531502472,
      "grad_norm": 0.3938315510749817,
      "learning_rate": 9.362024207261373e-06,
      "loss": 0.4957,
      "step": 33925
    },
    {
      "epoch": 1.0421773722851964,
      "grad_norm": 0.38182950019836426,
      "learning_rate": 9.36154191517394e-06,
      "loss": 0.4067,
      "step": 33926
    },
    {
      "epoch": 1.0422080914201457,
      "grad_norm": 0.3741079568862915,
      "learning_rate": 9.361059624577667e-06,
      "loss": 0.5293,
      "step": 33927
    },
    {
      "epoch": 1.0422388105550948,
      "grad_norm": 0.3641929626464844,
      "learning_rate": 9.360577335473689e-06,
      "loss": 0.5039,
      "step": 33928
    },
    {
      "epoch": 1.042269529690044,
      "grad_norm": 0.3960769474506378,
      "learning_rate": 9.360095047863123e-06,
      "loss": 0.5571,
      "step": 33929
    },
    {
      "epoch": 1.042300248824993,
      "grad_norm": 0.40191587805747986,
      "learning_rate": 9.359612761747101e-06,
      "loss": 0.4921,
      "step": 33930
    },
    {
      "epoch": 1.0423309679599422,
      "grad_norm": 0.3685997426509857,
      "learning_rate": 9.359130477126748e-06,
      "loss": 0.5109,
      "step": 33931
    },
    {
      "epoch": 1.0423616870948913,
      "grad_norm": 0.36158376932144165,
      "learning_rate": 9.358648194003191e-06,
      "loss": 0.5305,
      "step": 33932
    },
    {
      "epoch": 1.0423924062298406,
      "grad_norm": 0.39875486493110657,
      "learning_rate": 9.358165912377555e-06,
      "loss": 0.4621,
      "step": 33933
    },
    {
      "epoch": 1.0424231253647898,
      "grad_norm": 0.4095331132411957,
      "learning_rate": 9.357683632250971e-06,
      "loss": 0.5158,
      "step": 33934
    },
    {
      "epoch": 1.0424538444997389,
      "grad_norm": 0.410759836435318,
      "learning_rate": 9.357201353624556e-06,
      "loss": 0.4681,
      "step": 33935
    },
    {
      "epoch": 1.042484563634688,
      "grad_norm": 0.37170082330703735,
      "learning_rate": 9.356719076499449e-06,
      "loss": 0.4665,
      "step": 33936
    },
    {
      "epoch": 1.0425152827696371,
      "grad_norm": 0.39975133538246155,
      "learning_rate": 9.35623680087676e-06,
      "loss": 0.5314,
      "step": 33937
    },
    {
      "epoch": 1.0425460019045865,
      "grad_norm": 0.3491276502609253,
      "learning_rate": 9.355754526757632e-06,
      "loss": 0.447,
      "step": 33938
    },
    {
      "epoch": 1.0425767210395356,
      "grad_norm": 0.5431485772132874,
      "learning_rate": 9.355272254143185e-06,
      "loss": 0.5052,
      "step": 33939
    },
    {
      "epoch": 1.0426074401744847,
      "grad_norm": 0.3832908272743225,
      "learning_rate": 9.354789983034538e-06,
      "loss": 0.4284,
      "step": 33940
    },
    {
      "epoch": 1.0426381593094338,
      "grad_norm": 0.3678613603115082,
      "learning_rate": 9.354307713432833e-06,
      "loss": 0.4879,
      "step": 33941
    },
    {
      "epoch": 1.042668878444383,
      "grad_norm": 0.3574201464653015,
      "learning_rate": 9.35382544533918e-06,
      "loss": 0.4376,
      "step": 33942
    },
    {
      "epoch": 1.042699597579332,
      "grad_norm": 0.3963245749473572,
      "learning_rate": 9.353343178754718e-06,
      "loss": 0.5084,
      "step": 33943
    },
    {
      "epoch": 1.0427303167142814,
      "grad_norm": 0.38343778252601624,
      "learning_rate": 9.352860913680563e-06,
      "loss": 0.444,
      "step": 33944
    },
    {
      "epoch": 1.0427610358492305,
      "grad_norm": 0.3562784790992737,
      "learning_rate": 9.352378650117852e-06,
      "loss": 0.5497,
      "step": 33945
    },
    {
      "epoch": 1.0427917549841796,
      "grad_norm": 0.3774773180484772,
      "learning_rate": 9.351896388067703e-06,
      "loss": 0.424,
      "step": 33946
    },
    {
      "epoch": 1.0428224741191288,
      "grad_norm": 0.44285452365875244,
      "learning_rate": 9.351414127531247e-06,
      "loss": 0.5396,
      "step": 33947
    },
    {
      "epoch": 1.0428531932540779,
      "grad_norm": 0.37869489192962646,
      "learning_rate": 9.350931868509605e-06,
      "loss": 0.4505,
      "step": 33948
    },
    {
      "epoch": 1.0428839123890272,
      "grad_norm": 0.44777238368988037,
      "learning_rate": 9.35044961100391e-06,
      "loss": 0.5377,
      "step": 33949
    },
    {
      "epoch": 1.0429146315239763,
      "grad_norm": 0.37764522433280945,
      "learning_rate": 9.349967355015284e-06,
      "loss": 0.4856,
      "step": 33950
    },
    {
      "epoch": 1.0429453506589255,
      "grad_norm": 0.380257785320282,
      "learning_rate": 9.349485100544855e-06,
      "loss": 0.4668,
      "step": 33951
    },
    {
      "epoch": 1.0429760697938746,
      "grad_norm": 0.3553163707256317,
      "learning_rate": 9.34900284759375e-06,
      "loss": 0.5617,
      "step": 33952
    },
    {
      "epoch": 1.0430067889288237,
      "grad_norm": 0.4032905399799347,
      "learning_rate": 9.348520596163093e-06,
      "loss": 0.4614,
      "step": 33953
    },
    {
      "epoch": 1.0430375080637728,
      "grad_norm": 0.39943140745162964,
      "learning_rate": 9.348038346254011e-06,
      "loss": 0.4937,
      "step": 33954
    },
    {
      "epoch": 1.0430682271987222,
      "grad_norm": 0.5645134449005127,
      "learning_rate": 9.34755609786763e-06,
      "loss": 0.4593,
      "step": 33955
    },
    {
      "epoch": 1.0430989463336713,
      "grad_norm": 0.5940502285957336,
      "learning_rate": 9.347073851005081e-06,
      "loss": 0.4853,
      "step": 33956
    },
    {
      "epoch": 1.0431296654686204,
      "grad_norm": 0.3790186047554016,
      "learning_rate": 9.346591605667484e-06,
      "loss": 0.4198,
      "step": 33957
    },
    {
      "epoch": 1.0431603846035695,
      "grad_norm": 0.38953280448913574,
      "learning_rate": 9.34610936185597e-06,
      "loss": 0.4658,
      "step": 33958
    },
    {
      "epoch": 1.0431911037385186,
      "grad_norm": 0.4000532031059265,
      "learning_rate": 9.34562711957166e-06,
      "loss": 0.5045,
      "step": 33959
    },
    {
      "epoch": 1.043221822873468,
      "grad_norm": 0.35854536294937134,
      "learning_rate": 9.345144878815687e-06,
      "loss": 0.5217,
      "step": 33960
    },
    {
      "epoch": 1.043252542008417,
      "grad_norm": 0.4007240831851959,
      "learning_rate": 9.344662639589171e-06,
      "loss": 0.5084,
      "step": 33961
    },
    {
      "epoch": 1.0432832611433662,
      "grad_norm": 0.3939480185508728,
      "learning_rate": 9.344180401893243e-06,
      "loss": 0.5377,
      "step": 33962
    },
    {
      "epoch": 1.0433139802783153,
      "grad_norm": 0.3700767159461975,
      "learning_rate": 9.343698165729028e-06,
      "loss": 0.5002,
      "step": 33963
    },
    {
      "epoch": 1.0433446994132645,
      "grad_norm": 0.39202404022216797,
      "learning_rate": 9.343215931097652e-06,
      "loss": 0.5273,
      "step": 33964
    },
    {
      "epoch": 1.0433754185482136,
      "grad_norm": 0.38780951499938965,
      "learning_rate": 9.342733698000238e-06,
      "loss": 0.6416,
      "step": 33965
    },
    {
      "epoch": 1.043406137683163,
      "grad_norm": 0.38013601303100586,
      "learning_rate": 9.342251466437918e-06,
      "loss": 0.5183,
      "step": 33966
    },
    {
      "epoch": 1.043436856818112,
      "grad_norm": 0.41101372241973877,
      "learning_rate": 9.341769236411815e-06,
      "loss": 0.4868,
      "step": 33967
    },
    {
      "epoch": 1.0434675759530612,
      "grad_norm": 0.42030853033065796,
      "learning_rate": 9.341287007923057e-06,
      "loss": 0.5264,
      "step": 33968
    },
    {
      "epoch": 1.0434982950880103,
      "grad_norm": 0.36148977279663086,
      "learning_rate": 9.340804780972766e-06,
      "loss": 0.4959,
      "step": 33969
    },
    {
      "epoch": 1.0435290142229594,
      "grad_norm": 0.35880914330482483,
      "learning_rate": 9.340322555562077e-06,
      "loss": 0.4353,
      "step": 33970
    },
    {
      "epoch": 1.0435597333579087,
      "grad_norm": 0.6104787588119507,
      "learning_rate": 9.339840331692104e-06,
      "loss": 0.5345,
      "step": 33971
    },
    {
      "epoch": 1.0435904524928579,
      "grad_norm": 0.9914140105247498,
      "learning_rate": 9.339358109363986e-06,
      "loss": 0.4769,
      "step": 33972
    },
    {
      "epoch": 1.043621171627807,
      "grad_norm": 0.37343630194664,
      "learning_rate": 9.338875888578837e-06,
      "loss": 0.4327,
      "step": 33973
    },
    {
      "epoch": 1.043651890762756,
      "grad_norm": 0.3548815846443176,
      "learning_rate": 9.338393669337793e-06,
      "loss": 0.4612,
      "step": 33974
    },
    {
      "epoch": 1.0436826098977052,
      "grad_norm": 0.3995237946510315,
      "learning_rate": 9.337911451641978e-06,
      "loss": 0.4338,
      "step": 33975
    },
    {
      "epoch": 1.0437133290326543,
      "grad_norm": 0.3477083444595337,
      "learning_rate": 9.337429235492514e-06,
      "loss": 0.5695,
      "step": 33976
    },
    {
      "epoch": 1.0437440481676037,
      "grad_norm": 0.41030070185661316,
      "learning_rate": 9.336947020890535e-06,
      "loss": 0.5345,
      "step": 33977
    },
    {
      "epoch": 1.0437747673025528,
      "grad_norm": 0.5923715233802795,
      "learning_rate": 9.336464807837156e-06,
      "loss": 0.4601,
      "step": 33978
    },
    {
      "epoch": 1.043805486437502,
      "grad_norm": 0.3674415051937103,
      "learning_rate": 9.335982596333517e-06,
      "loss": 0.4905,
      "step": 33979
    },
    {
      "epoch": 1.043836205572451,
      "grad_norm": 0.38052529096603394,
      "learning_rate": 9.335500386380732e-06,
      "loss": 0.5287,
      "step": 33980
    },
    {
      "epoch": 1.0438669247074002,
      "grad_norm": 0.3917510509490967,
      "learning_rate": 9.335018177979936e-06,
      "loss": 0.5316,
      "step": 33981
    },
    {
      "epoch": 1.0438976438423495,
      "grad_norm": 0.38163089752197266,
      "learning_rate": 9.334535971132248e-06,
      "loss": 0.4833,
      "step": 33982
    },
    {
      "epoch": 1.0439283629772986,
      "grad_norm": 0.40732160210609436,
      "learning_rate": 9.334053765838799e-06,
      "loss": 0.5874,
      "step": 33983
    },
    {
      "epoch": 1.0439590821122477,
      "grad_norm": 0.41669002175331116,
      "learning_rate": 9.333571562100714e-06,
      "loss": 0.5461,
      "step": 33984
    },
    {
      "epoch": 1.0439898012471969,
      "grad_norm": 0.39708250761032104,
      "learning_rate": 9.33308935991912e-06,
      "loss": 0.5334,
      "step": 33985
    },
    {
      "epoch": 1.044020520382146,
      "grad_norm": 0.42299652099609375,
      "learning_rate": 9.33260715929514e-06,
      "loss": 0.4578,
      "step": 33986
    },
    {
      "epoch": 1.044051239517095,
      "grad_norm": 0.4004869759082794,
      "learning_rate": 9.332124960229906e-06,
      "loss": 0.5356,
      "step": 33987
    },
    {
      "epoch": 1.0440819586520445,
      "grad_norm": 0.43984225392341614,
      "learning_rate": 9.331642762724538e-06,
      "loss": 0.4067,
      "step": 33988
    },
    {
      "epoch": 1.0441126777869936,
      "grad_norm": 0.3886035978794098,
      "learning_rate": 9.331160566780166e-06,
      "loss": 0.5574,
      "step": 33989
    },
    {
      "epoch": 1.0441433969219427,
      "grad_norm": 0.3958039879798889,
      "learning_rate": 9.330678372397915e-06,
      "loss": 0.4541,
      "step": 33990
    },
    {
      "epoch": 1.0441741160568918,
      "grad_norm": 0.403437077999115,
      "learning_rate": 9.33019617957891e-06,
      "loss": 0.5035,
      "step": 33991
    },
    {
      "epoch": 1.044204835191841,
      "grad_norm": 0.3807113766670227,
      "learning_rate": 9.32971398832428e-06,
      "loss": 0.4656,
      "step": 33992
    },
    {
      "epoch": 1.0442355543267903,
      "grad_norm": 0.36654847860336304,
      "learning_rate": 9.32923179863515e-06,
      "loss": 0.5466,
      "step": 33993
    },
    {
      "epoch": 1.0442662734617394,
      "grad_norm": 0.39141809940338135,
      "learning_rate": 9.328749610512646e-06,
      "loss": 0.4811,
      "step": 33994
    },
    {
      "epoch": 1.0442969925966885,
      "grad_norm": 0.3905625343322754,
      "learning_rate": 9.328267423957893e-06,
      "loss": 0.5479,
      "step": 33995
    },
    {
      "epoch": 1.0443277117316376,
      "grad_norm": 0.42715081572532654,
      "learning_rate": 9.327785238972021e-06,
      "loss": 0.4941,
      "step": 33996
    },
    {
      "epoch": 1.0443584308665868,
      "grad_norm": 0.3666486442089081,
      "learning_rate": 9.32730305555615e-06,
      "loss": 0.4757,
      "step": 33997
    },
    {
      "epoch": 1.0443891500015359,
      "grad_norm": 0.398044615983963,
      "learning_rate": 9.326820873711414e-06,
      "loss": 0.5064,
      "step": 33998
    },
    {
      "epoch": 1.0444198691364852,
      "grad_norm": 0.4253307282924652,
      "learning_rate": 9.326338693438931e-06,
      "loss": 0.4364,
      "step": 33999
    },
    {
      "epoch": 1.0444505882714343,
      "grad_norm": 0.3844166696071625,
      "learning_rate": 9.325856514739833e-06,
      "loss": 0.4619,
      "step": 34000
    },
    {
      "epoch": 1.0444813074063835,
      "grad_norm": 0.40666836500167847,
      "learning_rate": 9.325374337615243e-06,
      "loss": 0.4879,
      "step": 34001
    },
    {
      "epoch": 1.0445120265413326,
      "grad_norm": 0.3718469440937042,
      "learning_rate": 9.324892162066293e-06,
      "loss": 0.5393,
      "step": 34002
    },
    {
      "epoch": 1.0445427456762817,
      "grad_norm": 0.3847617506980896,
      "learning_rate": 9.324409988094097e-06,
      "loss": 0.4672,
      "step": 34003
    },
    {
      "epoch": 1.0445734648112308,
      "grad_norm": 0.4009818136692047,
      "learning_rate": 9.323927815699795e-06,
      "loss": 0.4672,
      "step": 34004
    },
    {
      "epoch": 1.0446041839461802,
      "grad_norm": 0.3727009892463684,
      "learning_rate": 9.3234456448845e-06,
      "loss": 0.5625,
      "step": 34005
    },
    {
      "epoch": 1.0446349030811293,
      "grad_norm": 0.3902702331542969,
      "learning_rate": 9.322963475649353e-06,
      "loss": 0.5256,
      "step": 34006
    },
    {
      "epoch": 1.0446656222160784,
      "grad_norm": 0.3631177842617035,
      "learning_rate": 9.322481307995465e-06,
      "loss": 0.5507,
      "step": 34007
    },
    {
      "epoch": 1.0446963413510275,
      "grad_norm": 0.4081112742424011,
      "learning_rate": 9.321999141923976e-06,
      "loss": 0.4741,
      "step": 34008
    },
    {
      "epoch": 1.0447270604859766,
      "grad_norm": 0.4254947304725647,
      "learning_rate": 9.321516977436e-06,
      "loss": 0.5209,
      "step": 34009
    },
    {
      "epoch": 1.044757779620926,
      "grad_norm": 0.3876986503601074,
      "learning_rate": 9.321034814532666e-06,
      "loss": 0.5133,
      "step": 34010
    },
    {
      "epoch": 1.044788498755875,
      "grad_norm": 0.3556341826915741,
      "learning_rate": 9.320552653215111e-06,
      "loss": 0.5192,
      "step": 34011
    },
    {
      "epoch": 1.0448192178908242,
      "grad_norm": 0.3730611801147461,
      "learning_rate": 9.320070493484445e-06,
      "loss": 0.528,
      "step": 34012
    },
    {
      "epoch": 1.0448499370257733,
      "grad_norm": 0.3766675889492035,
      "learning_rate": 9.319588335341808e-06,
      "loss": 0.4945,
      "step": 34013
    },
    {
      "epoch": 1.0448806561607225,
      "grad_norm": 0.35788169503211975,
      "learning_rate": 9.319106178788313e-06,
      "loss": 0.4536,
      "step": 34014
    },
    {
      "epoch": 1.0449113752956716,
      "grad_norm": 0.3502439558506012,
      "learning_rate": 9.318624023825102e-06,
      "loss": 0.5033,
      "step": 34015
    },
    {
      "epoch": 1.044942094430621,
      "grad_norm": 0.3850110173225403,
      "learning_rate": 9.318141870453285e-06,
      "loss": 0.4646,
      "step": 34016
    },
    {
      "epoch": 1.04497281356557,
      "grad_norm": 0.393436074256897,
      "learning_rate": 9.317659718674e-06,
      "loss": 0.4678,
      "step": 34017
    },
    {
      "epoch": 1.0450035327005192,
      "grad_norm": 0.3744446337223053,
      "learning_rate": 9.317177568488365e-06,
      "loss": 0.4945,
      "step": 34018
    },
    {
      "epoch": 1.0450342518354683,
      "grad_norm": 0.36852461099624634,
      "learning_rate": 9.316695419897512e-06,
      "loss": 0.4688,
      "step": 34019
    },
    {
      "epoch": 1.0450649709704174,
      "grad_norm": 0.4194071888923645,
      "learning_rate": 9.316213272902562e-06,
      "loss": 0.4908,
      "step": 34020
    },
    {
      "epoch": 1.0450956901053667,
      "grad_norm": 0.3655696213245392,
      "learning_rate": 9.315731127504645e-06,
      "loss": 0.4527,
      "step": 34021
    },
    {
      "epoch": 1.0451264092403159,
      "grad_norm": 0.3832097351551056,
      "learning_rate": 9.315248983704884e-06,
      "loss": 0.4289,
      "step": 34022
    },
    {
      "epoch": 1.045157128375265,
      "grad_norm": 0.36229416728019714,
      "learning_rate": 9.31476684150441e-06,
      "loss": 0.4592,
      "step": 34023
    },
    {
      "epoch": 1.045187847510214,
      "grad_norm": 0.3467705547809601,
      "learning_rate": 9.314284700904344e-06,
      "loss": 0.3809,
      "step": 34024
    },
    {
      "epoch": 1.0452185666451632,
      "grad_norm": 0.43004608154296875,
      "learning_rate": 9.313802561905815e-06,
      "loss": 0.4753,
      "step": 34025
    },
    {
      "epoch": 1.0452492857801123,
      "grad_norm": 0.3866691589355469,
      "learning_rate": 9.313320424509946e-06,
      "loss": 0.4472,
      "step": 34026
    },
    {
      "epoch": 1.0452800049150617,
      "grad_norm": 0.6846810579299927,
      "learning_rate": 9.312838288717867e-06,
      "loss": 0.5136,
      "step": 34027
    },
    {
      "epoch": 1.0453107240500108,
      "grad_norm": 0.3379989564418793,
      "learning_rate": 9.3123561545307e-06,
      "loss": 0.4508,
      "step": 34028
    },
    {
      "epoch": 1.04534144318496,
      "grad_norm": 0.3548176884651184,
      "learning_rate": 9.311874021949573e-06,
      "loss": 0.4638,
      "step": 34029
    },
    {
      "epoch": 1.045372162319909,
      "grad_norm": 0.37569695711135864,
      "learning_rate": 9.311391890975616e-06,
      "loss": 0.4835,
      "step": 34030
    },
    {
      "epoch": 1.0454028814548582,
      "grad_norm": 0.405422568321228,
      "learning_rate": 9.310909761609948e-06,
      "loss": 0.4694,
      "step": 34031
    },
    {
      "epoch": 1.0454336005898073,
      "grad_norm": 0.439142644405365,
      "learning_rate": 9.310427633853701e-06,
      "loss": 0.4334,
      "step": 34032
    },
    {
      "epoch": 1.0454643197247566,
      "grad_norm": 0.39518076181411743,
      "learning_rate": 9.309945507707996e-06,
      "loss": 0.5353,
      "step": 34033
    },
    {
      "epoch": 1.0454950388597057,
      "grad_norm": 0.4307543933391571,
      "learning_rate": 9.309463383173965e-06,
      "loss": 0.5175,
      "step": 34034
    },
    {
      "epoch": 1.0455257579946549,
      "grad_norm": 0.3993328809738159,
      "learning_rate": 9.308981260252726e-06,
      "loss": 0.5041,
      "step": 34035
    },
    {
      "epoch": 1.045556477129604,
      "grad_norm": 0.4100136160850525,
      "learning_rate": 9.308499138945414e-06,
      "loss": 0.5315,
      "step": 34036
    },
    {
      "epoch": 1.045587196264553,
      "grad_norm": 0.4084118604660034,
      "learning_rate": 9.308017019253146e-06,
      "loss": 0.5057,
      "step": 34037
    },
    {
      "epoch": 1.0456179153995024,
      "grad_norm": 0.3640713393688202,
      "learning_rate": 9.307534901177058e-06,
      "loss": 0.5286,
      "step": 34038
    },
    {
      "epoch": 1.0456486345344516,
      "grad_norm": 0.4038369059562683,
      "learning_rate": 9.307052784718265e-06,
      "loss": 0.5216,
      "step": 34039
    },
    {
      "epoch": 1.0456793536694007,
      "grad_norm": 0.38600707054138184,
      "learning_rate": 9.306570669877905e-06,
      "loss": 0.4648,
      "step": 34040
    },
    {
      "epoch": 1.0457100728043498,
      "grad_norm": 0.3848806619644165,
      "learning_rate": 9.30608855665709e-06,
      "loss": 0.5885,
      "step": 34041
    },
    {
      "epoch": 1.045740791939299,
      "grad_norm": 0.39482381939888,
      "learning_rate": 9.305606445056961e-06,
      "loss": 0.5617,
      "step": 34042
    },
    {
      "epoch": 1.045771511074248,
      "grad_norm": 0.4034236967563629,
      "learning_rate": 9.305124335078632e-06,
      "loss": 0.4766,
      "step": 34043
    },
    {
      "epoch": 1.0458022302091974,
      "grad_norm": 0.34380677342414856,
      "learning_rate": 9.304642226723234e-06,
      "loss": 0.5081,
      "step": 34044
    },
    {
      "epoch": 1.0458329493441465,
      "grad_norm": 0.34602800011634827,
      "learning_rate": 9.304160119991892e-06,
      "loss": 0.4491,
      "step": 34045
    },
    {
      "epoch": 1.0458636684790956,
      "grad_norm": 0.4156486690044403,
      "learning_rate": 9.30367801488573e-06,
      "loss": 0.4922,
      "step": 34046
    },
    {
      "epoch": 1.0458943876140447,
      "grad_norm": 0.3505558669567108,
      "learning_rate": 9.303195911405885e-06,
      "loss": 0.4491,
      "step": 34047
    },
    {
      "epoch": 1.0459251067489939,
      "grad_norm": 0.37247687578201294,
      "learning_rate": 9.302713809553468e-06,
      "loss": 0.477,
      "step": 34048
    },
    {
      "epoch": 1.0459558258839432,
      "grad_norm": 0.383526474237442,
      "learning_rate": 9.302231709329617e-06,
      "loss": 0.5354,
      "step": 34049
    },
    {
      "epoch": 1.0459865450188923,
      "grad_norm": 0.3661307394504547,
      "learning_rate": 9.301749610735446e-06,
      "loss": 0.5349,
      "step": 34050
    },
    {
      "epoch": 1.0460172641538414,
      "grad_norm": 0.34972134232521057,
      "learning_rate": 9.301267513772093e-06,
      "loss": 0.4702,
      "step": 34051
    },
    {
      "epoch": 1.0460479832887906,
      "grad_norm": 0.37622421979904175,
      "learning_rate": 9.300785418440676e-06,
      "loss": 0.4577,
      "step": 34052
    },
    {
      "epoch": 1.0460787024237397,
      "grad_norm": 0.3803962171077728,
      "learning_rate": 9.300303324742325e-06,
      "loss": 0.5373,
      "step": 34053
    },
    {
      "epoch": 1.0461094215586888,
      "grad_norm": 0.4011455476284027,
      "learning_rate": 9.299821232678161e-06,
      "loss": 0.4338,
      "step": 34054
    },
    {
      "epoch": 1.0461401406936381,
      "grad_norm": 0.40772321820259094,
      "learning_rate": 9.299339142249318e-06,
      "loss": 0.5405,
      "step": 34055
    },
    {
      "epoch": 1.0461708598285873,
      "grad_norm": 0.3868836462497711,
      "learning_rate": 9.298857053456914e-06,
      "loss": 0.4554,
      "step": 34056
    },
    {
      "epoch": 1.0462015789635364,
      "grad_norm": 0.4020368158817291,
      "learning_rate": 9.298374966302079e-06,
      "loss": 0.5097,
      "step": 34057
    },
    {
      "epoch": 1.0462322980984855,
      "grad_norm": 0.36463919281959534,
      "learning_rate": 9.297892880785937e-06,
      "loss": 0.4643,
      "step": 34058
    },
    {
      "epoch": 1.0462630172334346,
      "grad_norm": 0.3716832995414734,
      "learning_rate": 9.29741079690962e-06,
      "loss": 0.4859,
      "step": 34059
    },
    {
      "epoch": 1.046293736368384,
      "grad_norm": 0.39296847581863403,
      "learning_rate": 9.296928714674243e-06,
      "loss": 0.4755,
      "step": 34060
    },
    {
      "epoch": 1.046324455503333,
      "grad_norm": 0.4288809895515442,
      "learning_rate": 9.296446634080943e-06,
      "loss": 0.4717,
      "step": 34061
    },
    {
      "epoch": 1.0463551746382822,
      "grad_norm": 0.37530532479286194,
      "learning_rate": 9.295964555130839e-06,
      "loss": 0.5133,
      "step": 34062
    },
    {
      "epoch": 1.0463858937732313,
      "grad_norm": 0.3807789385318756,
      "learning_rate": 9.29548247782506e-06,
      "loss": 0.5052,
      "step": 34063
    },
    {
      "epoch": 1.0464166129081804,
      "grad_norm": 0.37415578961372375,
      "learning_rate": 9.29500040216473e-06,
      "loss": 0.4984,
      "step": 34064
    },
    {
      "epoch": 1.0464473320431296,
      "grad_norm": 0.5241823792457581,
      "learning_rate": 9.294518328150974e-06,
      "loss": 0.4352,
      "step": 34065
    },
    {
      "epoch": 1.046478051178079,
      "grad_norm": 0.37750598788261414,
      "learning_rate": 9.294036255784922e-06,
      "loss": 0.5995,
      "step": 34066
    },
    {
      "epoch": 1.046508770313028,
      "grad_norm": 0.387616902589798,
      "learning_rate": 9.293554185067696e-06,
      "loss": 0.4693,
      "step": 34067
    },
    {
      "epoch": 1.0465394894479771,
      "grad_norm": 0.38260024785995483,
      "learning_rate": 9.293072116000426e-06,
      "loss": 0.5196,
      "step": 34068
    },
    {
      "epoch": 1.0465702085829263,
      "grad_norm": 0.37317508459091187,
      "learning_rate": 9.292590048584232e-06,
      "loss": 0.6124,
      "step": 34069
    },
    {
      "epoch": 1.0466009277178754,
      "grad_norm": 0.409204363822937,
      "learning_rate": 9.292107982820246e-06,
      "loss": 0.4919,
      "step": 34070
    },
    {
      "epoch": 1.0466316468528247,
      "grad_norm": 0.3977223038673401,
      "learning_rate": 9.29162591870959e-06,
      "loss": 0.5458,
      "step": 34071
    },
    {
      "epoch": 1.0466623659877738,
      "grad_norm": 0.366750568151474,
      "learning_rate": 9.291143856253395e-06,
      "loss": 0.5125,
      "step": 34072
    },
    {
      "epoch": 1.046693085122723,
      "grad_norm": 0.3898029923439026,
      "learning_rate": 9.290661795452777e-06,
      "loss": 0.4578,
      "step": 34073
    },
    {
      "epoch": 1.046723804257672,
      "grad_norm": 0.38925743103027344,
      "learning_rate": 9.290179736308874e-06,
      "loss": 0.537,
      "step": 34074
    },
    {
      "epoch": 1.0467545233926212,
      "grad_norm": 0.4159979224205017,
      "learning_rate": 9.2896976788228e-06,
      "loss": 0.5674,
      "step": 34075
    },
    {
      "epoch": 1.0467852425275703,
      "grad_norm": 0.3674437999725342,
      "learning_rate": 9.289215622995692e-06,
      "loss": 0.4739,
      "step": 34076
    },
    {
      "epoch": 1.0468159616625197,
      "grad_norm": 0.3936508297920227,
      "learning_rate": 9.288733568828664e-06,
      "loss": 0.5598,
      "step": 34077
    },
    {
      "epoch": 1.0468466807974688,
      "grad_norm": 0.3619556427001953,
      "learning_rate": 9.288251516322856e-06,
      "loss": 0.5318,
      "step": 34078
    },
    {
      "epoch": 1.046877399932418,
      "grad_norm": 0.3689148426055908,
      "learning_rate": 9.287769465479382e-06,
      "loss": 0.5173,
      "step": 34079
    },
    {
      "epoch": 1.046908119067367,
      "grad_norm": 0.37254002690315247,
      "learning_rate": 9.287287416299373e-06,
      "loss": 0.4622,
      "step": 34080
    },
    {
      "epoch": 1.0469388382023161,
      "grad_norm": 0.36290043592453003,
      "learning_rate": 9.286805368783953e-06,
      "loss": 0.4791,
      "step": 34081
    },
    {
      "epoch": 1.0469695573372655,
      "grad_norm": 0.3515339493751526,
      "learning_rate": 9.28632332293425e-06,
      "loss": 0.4545,
      "step": 34082
    },
    {
      "epoch": 1.0470002764722146,
      "grad_norm": 0.37717947363853455,
      "learning_rate": 9.285841278751388e-06,
      "loss": 0.4911,
      "step": 34083
    },
    {
      "epoch": 1.0470309956071637,
      "grad_norm": 0.3780222237110138,
      "learning_rate": 9.285359236236492e-06,
      "loss": 0.4474,
      "step": 34084
    },
    {
      "epoch": 1.0470617147421128,
      "grad_norm": 0.3700314462184906,
      "learning_rate": 9.284877195390692e-06,
      "loss": 0.4958,
      "step": 34085
    },
    {
      "epoch": 1.047092433877062,
      "grad_norm": 0.3871597647666931,
      "learning_rate": 9.28439515621511e-06,
      "loss": 0.5573,
      "step": 34086
    },
    {
      "epoch": 1.047123153012011,
      "grad_norm": 0.36264488101005554,
      "learning_rate": 9.283913118710875e-06,
      "loss": 0.4543,
      "step": 34087
    },
    {
      "epoch": 1.0471538721469604,
      "grad_norm": 0.36682364344596863,
      "learning_rate": 9.283431082879109e-06,
      "loss": 0.4435,
      "step": 34088
    },
    {
      "epoch": 1.0471845912819095,
      "grad_norm": 0.36299651861190796,
      "learning_rate": 9.28294904872094e-06,
      "loss": 0.4713,
      "step": 34089
    },
    {
      "epoch": 1.0472153104168587,
      "grad_norm": 0.34367915987968445,
      "learning_rate": 9.282467016237492e-06,
      "loss": 0.5278,
      "step": 34090
    },
    {
      "epoch": 1.0472460295518078,
      "grad_norm": 0.38405847549438477,
      "learning_rate": 9.281984985429896e-06,
      "loss": 0.4842,
      "step": 34091
    },
    {
      "epoch": 1.047276748686757,
      "grad_norm": 0.428442120552063,
      "learning_rate": 9.281502956299272e-06,
      "loss": 0.4559,
      "step": 34092
    },
    {
      "epoch": 1.0473074678217063,
      "grad_norm": 0.3981625735759735,
      "learning_rate": 9.28102092884675e-06,
      "loss": 0.5202,
      "step": 34093
    },
    {
      "epoch": 1.0473381869566554,
      "grad_norm": 0.38623905181884766,
      "learning_rate": 9.280538903073451e-06,
      "loss": 0.4938,
      "step": 34094
    },
    {
      "epoch": 1.0473689060916045,
      "grad_norm": 0.3539016544818878,
      "learning_rate": 9.280056878980505e-06,
      "loss": 0.4833,
      "step": 34095
    },
    {
      "epoch": 1.0473996252265536,
      "grad_norm": 0.3687068819999695,
      "learning_rate": 9.279574856569036e-06,
      "loss": 0.5107,
      "step": 34096
    },
    {
      "epoch": 1.0474303443615027,
      "grad_norm": 0.36910006403923035,
      "learning_rate": 9.279092835840171e-06,
      "loss": 0.4877,
      "step": 34097
    },
    {
      "epoch": 1.0474610634964518,
      "grad_norm": 0.40477025508880615,
      "learning_rate": 9.278610816795033e-06,
      "loss": 0.4684,
      "step": 34098
    },
    {
      "epoch": 1.0474917826314012,
      "grad_norm": 0.4239041209220886,
      "learning_rate": 9.278128799434754e-06,
      "loss": 0.6031,
      "step": 34099
    },
    {
      "epoch": 1.0475225017663503,
      "grad_norm": 0.3633604347705841,
      "learning_rate": 9.277646783760452e-06,
      "loss": 0.5256,
      "step": 34100
    },
    {
      "epoch": 1.0475532209012994,
      "grad_norm": 0.37996238470077515,
      "learning_rate": 9.277164769773256e-06,
      "loss": 0.4735,
      "step": 34101
    },
    {
      "epoch": 1.0475839400362486,
      "grad_norm": 0.5071167945861816,
      "learning_rate": 9.276682757474295e-06,
      "loss": 0.4592,
      "step": 34102
    },
    {
      "epoch": 1.0476146591711977,
      "grad_norm": 0.3850935697555542,
      "learning_rate": 9.276200746864689e-06,
      "loss": 0.5252,
      "step": 34103
    },
    {
      "epoch": 1.047645378306147,
      "grad_norm": 0.37112459540367126,
      "learning_rate": 9.275718737945569e-06,
      "loss": 0.4784,
      "step": 34104
    },
    {
      "epoch": 1.0476760974410961,
      "grad_norm": 0.40081408619880676,
      "learning_rate": 9.275236730718057e-06,
      "loss": 0.4469,
      "step": 34105
    },
    {
      "epoch": 1.0477068165760453,
      "grad_norm": 0.40340524911880493,
      "learning_rate": 9.274754725183282e-06,
      "loss": 0.5079,
      "step": 34106
    },
    {
      "epoch": 1.0477375357109944,
      "grad_norm": 0.4419589936733246,
      "learning_rate": 9.274272721342366e-06,
      "loss": 0.4966,
      "step": 34107
    },
    {
      "epoch": 1.0477682548459435,
      "grad_norm": 0.3629013001918793,
      "learning_rate": 9.273790719196441e-06,
      "loss": 0.5274,
      "step": 34108
    },
    {
      "epoch": 1.0477989739808926,
      "grad_norm": 0.4406476616859436,
      "learning_rate": 9.273308718746623e-06,
      "loss": 0.6131,
      "step": 34109
    },
    {
      "epoch": 1.047829693115842,
      "grad_norm": 0.395897775888443,
      "learning_rate": 9.272826719994048e-06,
      "loss": 0.5215,
      "step": 34110
    },
    {
      "epoch": 1.047860412250791,
      "grad_norm": 0.3688553273677826,
      "learning_rate": 9.272344722939832e-06,
      "loss": 0.5119,
      "step": 34111
    },
    {
      "epoch": 1.0478911313857402,
      "grad_norm": 0.3691202700138092,
      "learning_rate": 9.271862727585111e-06,
      "loss": 0.4877,
      "step": 34112
    },
    {
      "epoch": 1.0479218505206893,
      "grad_norm": 0.3867063522338867,
      "learning_rate": 9.271380733931e-06,
      "loss": 0.4684,
      "step": 34113
    },
    {
      "epoch": 1.0479525696556384,
      "grad_norm": 0.36998507380485535,
      "learning_rate": 9.270898741978635e-06,
      "loss": 0.5245,
      "step": 34114
    },
    {
      "epoch": 1.0479832887905876,
      "grad_norm": 0.38200101256370544,
      "learning_rate": 9.270416751729132e-06,
      "loss": 0.4164,
      "step": 34115
    },
    {
      "epoch": 1.048014007925537,
      "grad_norm": 0.36688265204429626,
      "learning_rate": 9.269934763183627e-06,
      "loss": 0.5202,
      "step": 34116
    },
    {
      "epoch": 1.048044727060486,
      "grad_norm": 0.3889903724193573,
      "learning_rate": 9.269452776343237e-06,
      "loss": 0.464,
      "step": 34117
    },
    {
      "epoch": 1.0480754461954351,
      "grad_norm": 0.35048729181289673,
      "learning_rate": 9.268970791209092e-06,
      "loss": 0.4877,
      "step": 34118
    },
    {
      "epoch": 1.0481061653303843,
      "grad_norm": 0.4211285412311554,
      "learning_rate": 9.268488807782315e-06,
      "loss": 0.5666,
      "step": 34119
    },
    {
      "epoch": 1.0481368844653334,
      "grad_norm": 0.38872024416923523,
      "learning_rate": 9.268006826064035e-06,
      "loss": 0.4449,
      "step": 34120
    },
    {
      "epoch": 1.0481676036002827,
      "grad_norm": 0.8709166049957275,
      "learning_rate": 9.267524846055376e-06,
      "loss": 0.4742,
      "step": 34121
    },
    {
      "epoch": 1.0481983227352318,
      "grad_norm": 0.38304299116134644,
      "learning_rate": 9.267042867757463e-06,
      "loss": 0.5339,
      "step": 34122
    },
    {
      "epoch": 1.048229041870181,
      "grad_norm": 0.3925394117832184,
      "learning_rate": 9.266560891171425e-06,
      "loss": 0.5115,
      "step": 34123
    },
    {
      "epoch": 1.04825976100513,
      "grad_norm": 0.37228021025657654,
      "learning_rate": 9.266078916298383e-06,
      "loss": 0.5003,
      "step": 34124
    },
    {
      "epoch": 1.0482904801400792,
      "grad_norm": 0.5737432837486267,
      "learning_rate": 9.265596943139466e-06,
      "loss": 0.5235,
      "step": 34125
    },
    {
      "epoch": 1.0483211992750283,
      "grad_norm": 0.3951815068721771,
      "learning_rate": 9.265114971695798e-06,
      "loss": 0.515,
      "step": 34126
    },
    {
      "epoch": 1.0483519184099777,
      "grad_norm": 0.37502074241638184,
      "learning_rate": 9.264633001968506e-06,
      "loss": 0.5194,
      "step": 34127
    },
    {
      "epoch": 1.0483826375449268,
      "grad_norm": 0.42300423979759216,
      "learning_rate": 9.264151033958714e-06,
      "loss": 0.5415,
      "step": 34128
    },
    {
      "epoch": 1.048413356679876,
      "grad_norm": 0.49479055404663086,
      "learning_rate": 9.26366906766755e-06,
      "loss": 0.5009,
      "step": 34129
    },
    {
      "epoch": 1.048444075814825,
      "grad_norm": 0.3551281988620758,
      "learning_rate": 9.263187103096137e-06,
      "loss": 0.4333,
      "step": 34130
    },
    {
      "epoch": 1.0484747949497741,
      "grad_norm": 0.36728808283805847,
      "learning_rate": 9.262705140245604e-06,
      "loss": 0.4857,
      "step": 34131
    },
    {
      "epoch": 1.0485055140847235,
      "grad_norm": 0.3722226917743683,
      "learning_rate": 9.262223179117072e-06,
      "loss": 0.564,
      "step": 34132
    },
    {
      "epoch": 1.0485362332196726,
      "grad_norm": 0.3928483724594116,
      "learning_rate": 9.261741219711671e-06,
      "loss": 0.4282,
      "step": 34133
    },
    {
      "epoch": 1.0485669523546217,
      "grad_norm": 0.5546562075614929,
      "learning_rate": 9.261259262030525e-06,
      "loss": 0.4257,
      "step": 34134
    },
    {
      "epoch": 1.0485976714895708,
      "grad_norm": 0.40380629897117615,
      "learning_rate": 9.260777306074762e-06,
      "loss": 0.5463,
      "step": 34135
    },
    {
      "epoch": 1.04862839062452,
      "grad_norm": 0.48743903636932373,
      "learning_rate": 9.260295351845499e-06,
      "loss": 0.4554,
      "step": 34136
    },
    {
      "epoch": 1.048659109759469,
      "grad_norm": 0.3649856150150299,
      "learning_rate": 9.25981339934387e-06,
      "loss": 0.4626,
      "step": 34137
    },
    {
      "epoch": 1.0486898288944184,
      "grad_norm": 0.4043062925338745,
      "learning_rate": 9.259331448571001e-06,
      "loss": 0.5029,
      "step": 34138
    },
    {
      "epoch": 1.0487205480293675,
      "grad_norm": 0.41245517134666443,
      "learning_rate": 9.258849499528012e-06,
      "loss": 0.504,
      "step": 34139
    },
    {
      "epoch": 1.0487512671643167,
      "grad_norm": 0.4409780502319336,
      "learning_rate": 9.258367552216036e-06,
      "loss": 0.5257,
      "step": 34140
    },
    {
      "epoch": 1.0487819862992658,
      "grad_norm": 0.4073697030544281,
      "learning_rate": 9.25788560663619e-06,
      "loss": 0.4888,
      "step": 34141
    },
    {
      "epoch": 1.048812705434215,
      "grad_norm": 0.44027212262153625,
      "learning_rate": 9.257403662789609e-06,
      "loss": 0.5079,
      "step": 34142
    },
    {
      "epoch": 1.048843424569164,
      "grad_norm": 0.42438697814941406,
      "learning_rate": 9.256921720677407e-06,
      "loss": 0.4502,
      "step": 34143
    },
    {
      "epoch": 1.0488741437041134,
      "grad_norm": 0.41122186183929443,
      "learning_rate": 9.256439780300724e-06,
      "loss": 0.4981,
      "step": 34144
    },
    {
      "epoch": 1.0489048628390625,
      "grad_norm": 0.38716942071914673,
      "learning_rate": 9.25595784166067e-06,
      "loss": 0.4823,
      "step": 34145
    },
    {
      "epoch": 1.0489355819740116,
      "grad_norm": 0.4013090133666992,
      "learning_rate": 9.255475904758385e-06,
      "loss": 0.4949,
      "step": 34146
    },
    {
      "epoch": 1.0489663011089607,
      "grad_norm": 0.39842355251312256,
      "learning_rate": 9.254993969594982e-06,
      "loss": 0.4885,
      "step": 34147
    },
    {
      "epoch": 1.0489970202439098,
      "grad_norm": 0.39371857047080994,
      "learning_rate": 9.254512036171599e-06,
      "loss": 0.5611,
      "step": 34148
    },
    {
      "epoch": 1.0490277393788592,
      "grad_norm": 0.3648524284362793,
      "learning_rate": 9.254030104489351e-06,
      "loss": 0.4439,
      "step": 34149
    },
    {
      "epoch": 1.0490584585138083,
      "grad_norm": 0.3525049388408661,
      "learning_rate": 9.253548174549369e-06,
      "loss": 0.4493,
      "step": 34150
    },
    {
      "epoch": 1.0490891776487574,
      "grad_norm": 0.3628554046154022,
      "learning_rate": 9.253066246352777e-06,
      "loss": 0.4317,
      "step": 34151
    },
    {
      "epoch": 1.0491198967837065,
      "grad_norm": 0.3692683279514313,
      "learning_rate": 9.252584319900701e-06,
      "loss": 0.5087,
      "step": 34152
    },
    {
      "epoch": 1.0491506159186557,
      "grad_norm": 0.3693801164627075,
      "learning_rate": 9.252102395194266e-06,
      "loss": 0.4476,
      "step": 34153
    },
    {
      "epoch": 1.0491813350536048,
      "grad_norm": 0.3514919877052307,
      "learning_rate": 9.2516204722346e-06,
      "loss": 0.4913,
      "step": 34154
    },
    {
      "epoch": 1.0492120541885541,
      "grad_norm": 0.4096478819847107,
      "learning_rate": 9.251138551022824e-06,
      "loss": 0.51,
      "step": 34155
    },
    {
      "epoch": 1.0492427733235032,
      "grad_norm": 0.45801982283592224,
      "learning_rate": 9.250656631560067e-06,
      "loss": 0.4615,
      "step": 34156
    },
    {
      "epoch": 1.0492734924584524,
      "grad_norm": 0.3799290060997009,
      "learning_rate": 9.250174713847454e-06,
      "loss": 0.4434,
      "step": 34157
    },
    {
      "epoch": 1.0493042115934015,
      "grad_norm": 0.3569878935813904,
      "learning_rate": 9.249692797886109e-06,
      "loss": 0.5247,
      "step": 34158
    },
    {
      "epoch": 1.0493349307283506,
      "grad_norm": 0.3945162296295166,
      "learning_rate": 9.249210883677161e-06,
      "loss": 0.472,
      "step": 34159
    },
    {
      "epoch": 1.0493656498633,
      "grad_norm": 0.4297954738140106,
      "learning_rate": 9.248728971221733e-06,
      "loss": 0.5527,
      "step": 34160
    },
    {
      "epoch": 1.049396368998249,
      "grad_norm": 0.37760257720947266,
      "learning_rate": 9.248247060520952e-06,
      "loss": 0.5299,
      "step": 34161
    },
    {
      "epoch": 1.0494270881331982,
      "grad_norm": 0.38496196269989014,
      "learning_rate": 9.24776515157594e-06,
      "loss": 0.4669,
      "step": 34162
    },
    {
      "epoch": 1.0494578072681473,
      "grad_norm": 0.39719000458717346,
      "learning_rate": 9.247283244387829e-06,
      "loss": 0.5892,
      "step": 34163
    },
    {
      "epoch": 1.0494885264030964,
      "grad_norm": 0.3724523186683655,
      "learning_rate": 9.246801338957736e-06,
      "loss": 0.5239,
      "step": 34164
    },
    {
      "epoch": 1.0495192455380455,
      "grad_norm": 0.3539277911186218,
      "learning_rate": 9.246319435286793e-06,
      "loss": 0.5041,
      "step": 34165
    },
    {
      "epoch": 1.0495499646729949,
      "grad_norm": 0.3814619481563568,
      "learning_rate": 9.245837533376123e-06,
      "loss": 0.4907,
      "step": 34166
    },
    {
      "epoch": 1.049580683807944,
      "grad_norm": 0.354462206363678,
      "learning_rate": 9.245355633226854e-06,
      "loss": 0.5135,
      "step": 34167
    },
    {
      "epoch": 1.0496114029428931,
      "grad_norm": 0.3563615381717682,
      "learning_rate": 9.244873734840106e-06,
      "loss": 0.536,
      "step": 34168
    },
    {
      "epoch": 1.0496421220778422,
      "grad_norm": 0.40032389760017395,
      "learning_rate": 9.244391838217013e-06,
      "loss": 0.4946,
      "step": 34169
    },
    {
      "epoch": 1.0496728412127914,
      "grad_norm": 0.3732759356498718,
      "learning_rate": 9.24390994335869e-06,
      "loss": 0.5555,
      "step": 34170
    },
    {
      "epoch": 1.0497035603477407,
      "grad_norm": 0.38321685791015625,
      "learning_rate": 9.243428050266276e-06,
      "loss": 0.4634,
      "step": 34171
    },
    {
      "epoch": 1.0497342794826898,
      "grad_norm": 0.3539113998413086,
      "learning_rate": 9.242946158940879e-06,
      "loss": 0.4978,
      "step": 34172
    },
    {
      "epoch": 1.049764998617639,
      "grad_norm": 0.3800903856754303,
      "learning_rate": 9.242464269383643e-06,
      "loss": 0.5854,
      "step": 34173
    },
    {
      "epoch": 1.049795717752588,
      "grad_norm": 0.3553610146045685,
      "learning_rate": 9.241982381595678e-06,
      "loss": 0.4459,
      "step": 34174
    },
    {
      "epoch": 1.0498264368875372,
      "grad_norm": 0.41903236508369446,
      "learning_rate": 9.241500495578118e-06,
      "loss": 0.5216,
      "step": 34175
    },
    {
      "epoch": 1.0498571560224863,
      "grad_norm": 0.35074442625045776,
      "learning_rate": 9.24101861133209e-06,
      "loss": 0.4903,
      "step": 34176
    },
    {
      "epoch": 1.0498878751574356,
      "grad_norm": 0.3671639859676361,
      "learning_rate": 9.24053672885871e-06,
      "loss": 0.3945,
      "step": 34177
    },
    {
      "epoch": 1.0499185942923848,
      "grad_norm": 0.3550037145614624,
      "learning_rate": 9.240054848159116e-06,
      "loss": 0.5046,
      "step": 34178
    },
    {
      "epoch": 1.0499493134273339,
      "grad_norm": 0.44227156043052673,
      "learning_rate": 9.23957296923442e-06,
      "loss": 0.5262,
      "step": 34179
    },
    {
      "epoch": 1.049980032562283,
      "grad_norm": 0.36250996589660645,
      "learning_rate": 9.239091092085761e-06,
      "loss": 0.5012,
      "step": 34180
    },
    {
      "epoch": 1.0500107516972321,
      "grad_norm": 0.3991483449935913,
      "learning_rate": 9.238609216714252e-06,
      "loss": 0.4651,
      "step": 34181
    },
    {
      "epoch": 1.0500414708321815,
      "grad_norm": 0.42697760462760925,
      "learning_rate": 9.23812734312103e-06,
      "loss": 0.4482,
      "step": 34182
    },
    {
      "epoch": 1.0500721899671306,
      "grad_norm": 0.3950907588005066,
      "learning_rate": 9.237645471307212e-06,
      "loss": 0.4992,
      "step": 34183
    },
    {
      "epoch": 1.0501029091020797,
      "grad_norm": 0.3693212568759918,
      "learning_rate": 9.237163601273928e-06,
      "loss": 0.484,
      "step": 34184
    },
    {
      "epoch": 1.0501336282370288,
      "grad_norm": 0.38962382078170776,
      "learning_rate": 9.236681733022298e-06,
      "loss": 0.4812,
      "step": 34185
    },
    {
      "epoch": 1.050164347371978,
      "grad_norm": 0.4256131649017334,
      "learning_rate": 9.236199866553455e-06,
      "loss": 0.5174,
      "step": 34186
    },
    {
      "epoch": 1.050195066506927,
      "grad_norm": 0.373146653175354,
      "learning_rate": 9.235718001868517e-06,
      "loss": 0.4884,
      "step": 34187
    },
    {
      "epoch": 1.0502257856418764,
      "grad_norm": 0.35473552346229553,
      "learning_rate": 9.235236138968616e-06,
      "loss": 0.4702,
      "step": 34188
    },
    {
      "epoch": 1.0502565047768255,
      "grad_norm": 0.3975101709365845,
      "learning_rate": 9.234754277854872e-06,
      "loss": 0.5056,
      "step": 34189
    },
    {
      "epoch": 1.0502872239117746,
      "grad_norm": 0.3897227942943573,
      "learning_rate": 9.234272418528414e-06,
      "loss": 0.5023,
      "step": 34190
    },
    {
      "epoch": 1.0503179430467238,
      "grad_norm": 0.3881513178348541,
      "learning_rate": 9.233790560990367e-06,
      "loss": 0.5175,
      "step": 34191
    },
    {
      "epoch": 1.0503486621816729,
      "grad_norm": 3.1960601806640625,
      "learning_rate": 9.233308705241853e-06,
      "loss": 0.4808,
      "step": 34192
    },
    {
      "epoch": 1.0503793813166222,
      "grad_norm": 0.38810834288597107,
      "learning_rate": 9.232826851284004e-06,
      "loss": 0.4748,
      "step": 34193
    },
    {
      "epoch": 1.0504101004515713,
      "grad_norm": 0.4396970868110657,
      "learning_rate": 9.232344999117937e-06,
      "loss": 0.5493,
      "step": 34194
    },
    {
      "epoch": 1.0504408195865205,
      "grad_norm": 0.4178351163864136,
      "learning_rate": 9.231863148744787e-06,
      "loss": 0.553,
      "step": 34195
    },
    {
      "epoch": 1.0504715387214696,
      "grad_norm": 0.36997678875923157,
      "learning_rate": 9.23138130016567e-06,
      "loss": 0.4966,
      "step": 34196
    },
    {
      "epoch": 1.0505022578564187,
      "grad_norm": 0.37571603059768677,
      "learning_rate": 9.230899453381718e-06,
      "loss": 0.4731,
      "step": 34197
    },
    {
      "epoch": 1.0505329769913678,
      "grad_norm": 0.35308271646499634,
      "learning_rate": 9.230417608394053e-06,
      "loss": 0.4859,
      "step": 34198
    },
    {
      "epoch": 1.0505636961263172,
      "grad_norm": 0.37699493765830994,
      "learning_rate": 9.229935765203802e-06,
      "loss": 0.4733,
      "step": 34199
    },
    {
      "epoch": 1.0505944152612663,
      "grad_norm": 0.4071975350379944,
      "learning_rate": 9.229453923812088e-06,
      "loss": 0.5413,
      "step": 34200
    },
    {
      "epoch": 1.0506251343962154,
      "grad_norm": 0.36681419610977173,
      "learning_rate": 9.22897208422004e-06,
      "loss": 0.5233,
      "step": 34201
    },
    {
      "epoch": 1.0506558535311645,
      "grad_norm": 0.4319721758365631,
      "learning_rate": 9.22849024642878e-06,
      "loss": 0.4933,
      "step": 34202
    },
    {
      "epoch": 1.0506865726661136,
      "grad_norm": 0.3795817494392395,
      "learning_rate": 9.22800841043944e-06,
      "loss": 0.5507,
      "step": 34203
    },
    {
      "epoch": 1.050717291801063,
      "grad_norm": 0.3990222215652466,
      "learning_rate": 9.227526576253133e-06,
      "loss": 0.5269,
      "step": 34204
    },
    {
      "epoch": 1.0507480109360121,
      "grad_norm": 0.3737598955631256,
      "learning_rate": 9.227044743870999e-06,
      "loss": 0.4518,
      "step": 34205
    },
    {
      "epoch": 1.0507787300709612,
      "grad_norm": 0.39616698026657104,
      "learning_rate": 9.226562913294148e-06,
      "loss": 0.561,
      "step": 34206
    },
    {
      "epoch": 1.0508094492059104,
      "grad_norm": 0.3995480537414551,
      "learning_rate": 9.226081084523721e-06,
      "loss": 0.4398,
      "step": 34207
    },
    {
      "epoch": 1.0508401683408595,
      "grad_norm": 0.349324494600296,
      "learning_rate": 9.22559925756083e-06,
      "loss": 0.5463,
      "step": 34208
    },
    {
      "epoch": 1.0508708874758086,
      "grad_norm": 0.38668590784072876,
      "learning_rate": 9.22511743240661e-06,
      "loss": 0.4323,
      "step": 34209
    },
    {
      "epoch": 1.050901606610758,
      "grad_norm": 0.3835613429546356,
      "learning_rate": 9.224635609062177e-06,
      "loss": 0.4846,
      "step": 34210
    },
    {
      "epoch": 1.050932325745707,
      "grad_norm": 0.4439292550086975,
      "learning_rate": 9.224153787528663e-06,
      "loss": 0.4946,
      "step": 34211
    },
    {
      "epoch": 1.0509630448806562,
      "grad_norm": 0.3774280846118927,
      "learning_rate": 9.223671967807198e-06,
      "loss": 0.5523,
      "step": 34212
    },
    {
      "epoch": 1.0509937640156053,
      "grad_norm": 0.4535204768180847,
      "learning_rate": 9.223190149898895e-06,
      "loss": 0.5783,
      "step": 34213
    },
    {
      "epoch": 1.0510244831505544,
      "grad_norm": 0.35664311051368713,
      "learning_rate": 9.22270833380489e-06,
      "loss": 0.4696,
      "step": 34214
    },
    {
      "epoch": 1.0510552022855038,
      "grad_norm": 0.41878610849380493,
      "learning_rate": 9.2222265195263e-06,
      "loss": 0.5318,
      "step": 34215
    },
    {
      "epoch": 1.0510859214204529,
      "grad_norm": 0.36299702525138855,
      "learning_rate": 9.22174470706426e-06,
      "loss": 0.4435,
      "step": 34216
    },
    {
      "epoch": 1.051116640555402,
      "grad_norm": 0.3683048486709595,
      "learning_rate": 9.221262896419883e-06,
      "loss": 0.5285,
      "step": 34217
    },
    {
      "epoch": 1.0511473596903511,
      "grad_norm": 0.5754954814910889,
      "learning_rate": 9.220781087594306e-06,
      "loss": 0.5212,
      "step": 34218
    },
    {
      "epoch": 1.0511780788253002,
      "grad_norm": 0.4423569142818451,
      "learning_rate": 9.220299280588647e-06,
      "loss": 0.4981,
      "step": 34219
    },
    {
      "epoch": 1.0512087979602494,
      "grad_norm": 0.37083470821380615,
      "learning_rate": 9.219817475404034e-06,
      "loss": 0.4905,
      "step": 34220
    },
    {
      "epoch": 1.0512395170951987,
      "grad_norm": 0.3811243176460266,
      "learning_rate": 9.219335672041589e-06,
      "loss": 0.4587,
      "step": 34221
    },
    {
      "epoch": 1.0512702362301478,
      "grad_norm": 0.37629175186157227,
      "learning_rate": 9.218853870502445e-06,
      "loss": 0.4624,
      "step": 34222
    },
    {
      "epoch": 1.051300955365097,
      "grad_norm": 0.3734048902988434,
      "learning_rate": 9.218372070787717e-06,
      "loss": 0.4574,
      "step": 34223
    },
    {
      "epoch": 1.051331674500046,
      "grad_norm": 0.40043023228645325,
      "learning_rate": 9.21789027289854e-06,
      "loss": 0.4609,
      "step": 34224
    },
    {
      "epoch": 1.0513623936349952,
      "grad_norm": 0.41158708930015564,
      "learning_rate": 9.217408476836032e-06,
      "loss": 0.4991,
      "step": 34225
    },
    {
      "epoch": 1.0513931127699443,
      "grad_norm": 0.35435783863067627,
      "learning_rate": 9.216926682601324e-06,
      "loss": 0.4823,
      "step": 34226
    },
    {
      "epoch": 1.0514238319048936,
      "grad_norm": 0.38062724471092224,
      "learning_rate": 9.216444890195535e-06,
      "loss": 0.5321,
      "step": 34227
    },
    {
      "epoch": 1.0514545510398428,
      "grad_norm": 0.38878190517425537,
      "learning_rate": 9.215963099619797e-06,
      "loss": 0.5077,
      "step": 34228
    },
    {
      "epoch": 1.0514852701747919,
      "grad_norm": 0.36729055643081665,
      "learning_rate": 9.215481310875228e-06,
      "loss": 0.4051,
      "step": 34229
    },
    {
      "epoch": 1.051515989309741,
      "grad_norm": 0.45556750893592834,
      "learning_rate": 9.21499952396296e-06,
      "loss": 0.4928,
      "step": 34230
    },
    {
      "epoch": 1.0515467084446901,
      "grad_norm": 0.43541473150253296,
      "learning_rate": 9.214517738884115e-06,
      "loss": 0.4917,
      "step": 34231
    },
    {
      "epoch": 1.0515774275796395,
      "grad_norm": 0.36196279525756836,
      "learning_rate": 9.214035955639818e-06,
      "loss": 0.4553,
      "step": 34232
    },
    {
      "epoch": 1.0516081467145886,
      "grad_norm": 0.40136784315109253,
      "learning_rate": 9.213554174231196e-06,
      "loss": 0.4052,
      "step": 34233
    },
    {
      "epoch": 1.0516388658495377,
      "grad_norm": 0.4328831434249878,
      "learning_rate": 9.213072394659372e-06,
      "loss": 0.4746,
      "step": 34234
    },
    {
      "epoch": 1.0516695849844868,
      "grad_norm": 0.38695910573005676,
      "learning_rate": 9.212590616925474e-06,
      "loss": 0.5147,
      "step": 34235
    },
    {
      "epoch": 1.051700304119436,
      "grad_norm": 0.5002702474594116,
      "learning_rate": 9.212108841030624e-06,
      "loss": 0.4376,
      "step": 34236
    },
    {
      "epoch": 1.051731023254385,
      "grad_norm": 0.38976550102233887,
      "learning_rate": 9.21162706697595e-06,
      "loss": 0.4902,
      "step": 34237
    },
    {
      "epoch": 1.0517617423893344,
      "grad_norm": 0.42787274718284607,
      "learning_rate": 9.211145294762575e-06,
      "loss": 0.4895,
      "step": 34238
    },
    {
      "epoch": 1.0517924615242835,
      "grad_norm": 0.3916904926300049,
      "learning_rate": 9.210663524391628e-06,
      "loss": 0.5056,
      "step": 34239
    },
    {
      "epoch": 1.0518231806592326,
      "grad_norm": 0.40863320231437683,
      "learning_rate": 9.210181755864226e-06,
      "loss": 0.5051,
      "step": 34240
    },
    {
      "epoch": 1.0518538997941818,
      "grad_norm": 0.39327186346054077,
      "learning_rate": 9.209699989181508e-06,
      "loss": 0.5096,
      "step": 34241
    },
    {
      "epoch": 1.0518846189291309,
      "grad_norm": 0.36317890882492065,
      "learning_rate": 9.209218224344581e-06,
      "loss": 0.5118,
      "step": 34242
    },
    {
      "epoch": 1.0519153380640802,
      "grad_norm": 0.3886670172214508,
      "learning_rate": 9.20873646135459e-06,
      "loss": 0.5028,
      "step": 34243
    },
    {
      "epoch": 1.0519460571990293,
      "grad_norm": 0.3975578844547272,
      "learning_rate": 9.20825470021264e-06,
      "loss": 0.5182,
      "step": 34244
    },
    {
      "epoch": 1.0519767763339785,
      "grad_norm": 0.3683357238769531,
      "learning_rate": 9.207772940919875e-06,
      "loss": 0.4202,
      "step": 34245
    },
    {
      "epoch": 1.0520074954689276,
      "grad_norm": 0.37896376848220825,
      "learning_rate": 9.207291183477409e-06,
      "loss": 0.4996,
      "step": 34246
    },
    {
      "epoch": 1.0520382146038767,
      "grad_norm": 0.3700784742832184,
      "learning_rate": 9.206809427886365e-06,
      "loss": 0.5197,
      "step": 34247
    },
    {
      "epoch": 1.0520689337388258,
      "grad_norm": 0.3561612665653229,
      "learning_rate": 9.20632767414788e-06,
      "loss": 0.5187,
      "step": 34248
    },
    {
      "epoch": 1.0520996528737752,
      "grad_norm": 0.38744571805000305,
      "learning_rate": 9.205845922263065e-06,
      "loss": 0.5815,
      "step": 34249
    },
    {
      "epoch": 1.0521303720087243,
      "grad_norm": 0.4197918474674225,
      "learning_rate": 9.20536417223306e-06,
      "loss": 0.5762,
      "step": 34250
    },
    {
      "epoch": 1.0521610911436734,
      "grad_norm": 0.38175728917121887,
      "learning_rate": 9.204882424058976e-06,
      "loss": 0.4771,
      "step": 34251
    },
    {
      "epoch": 1.0521918102786225,
      "grad_norm": 0.36492428183555603,
      "learning_rate": 9.204400677741952e-06,
      "loss": 0.4859,
      "step": 34252
    },
    {
      "epoch": 1.0522225294135716,
      "grad_norm": 0.33379697799682617,
      "learning_rate": 9.2039189332831e-06,
      "loss": 0.4232,
      "step": 34253
    },
    {
      "epoch": 1.052253248548521,
      "grad_norm": 0.3925151228904724,
      "learning_rate": 9.203437190683552e-06,
      "loss": 0.5084,
      "step": 34254
    },
    {
      "epoch": 1.05228396768347,
      "grad_norm": 0.38659802079200745,
      "learning_rate": 9.202955449944432e-06,
      "loss": 0.4984,
      "step": 34255
    },
    {
      "epoch": 1.0523146868184192,
      "grad_norm": 0.3818240463733673,
      "learning_rate": 9.202473711066868e-06,
      "loss": 0.5549,
      "step": 34256
    },
    {
      "epoch": 1.0523454059533683,
      "grad_norm": 0.3436886966228485,
      "learning_rate": 9.201991974051978e-06,
      "loss": 0.498,
      "step": 34257
    },
    {
      "epoch": 1.0523761250883175,
      "grad_norm": 0.3529503047466278,
      "learning_rate": 9.201510238900893e-06,
      "loss": 0.4529,
      "step": 34258
    },
    {
      "epoch": 1.0524068442232666,
      "grad_norm": 0.5010283589363098,
      "learning_rate": 9.201028505614738e-06,
      "loss": 0.4209,
      "step": 34259
    },
    {
      "epoch": 1.052437563358216,
      "grad_norm": 0.4160858988761902,
      "learning_rate": 9.200546774194635e-06,
      "loss": 0.4874,
      "step": 34260
    },
    {
      "epoch": 1.052468282493165,
      "grad_norm": 0.3762315511703491,
      "learning_rate": 9.20006504464171e-06,
      "loss": 0.5275,
      "step": 34261
    },
    {
      "epoch": 1.0524990016281142,
      "grad_norm": 0.37458109855651855,
      "learning_rate": 9.199583316957092e-06,
      "loss": 0.4575,
      "step": 34262
    },
    {
      "epoch": 1.0525297207630633,
      "grad_norm": 0.3553732931613922,
      "learning_rate": 9.199101591141901e-06,
      "loss": 0.5157,
      "step": 34263
    },
    {
      "epoch": 1.0525604398980124,
      "grad_norm": 0.36737340688705444,
      "learning_rate": 9.198619867197265e-06,
      "loss": 0.4434,
      "step": 34264
    },
    {
      "epoch": 1.0525911590329615,
      "grad_norm": 0.4266413450241089,
      "learning_rate": 9.198138145124308e-06,
      "loss": 0.4816,
      "step": 34265
    },
    {
      "epoch": 1.0526218781679109,
      "grad_norm": 0.39251819252967834,
      "learning_rate": 9.197656424924154e-06,
      "loss": 0.5675,
      "step": 34266
    },
    {
      "epoch": 1.05265259730286,
      "grad_norm": 0.3952415883541107,
      "learning_rate": 9.197174706597932e-06,
      "loss": 0.4558,
      "step": 34267
    },
    {
      "epoch": 1.052683316437809,
      "grad_norm": 0.3518349230289459,
      "learning_rate": 9.196692990146763e-06,
      "loss": 0.4709,
      "step": 34268
    },
    {
      "epoch": 1.0527140355727582,
      "grad_norm": 0.38090747594833374,
      "learning_rate": 9.196211275571775e-06,
      "loss": 0.5034,
      "step": 34269
    },
    {
      "epoch": 1.0527447547077073,
      "grad_norm": 0.4210585951805115,
      "learning_rate": 9.19572956287409e-06,
      "loss": 0.5911,
      "step": 34270
    },
    {
      "epoch": 1.0527754738426567,
      "grad_norm": 0.3822696805000305,
      "learning_rate": 9.195247852054836e-06,
      "loss": 0.506,
      "step": 34271
    },
    {
      "epoch": 1.0528061929776058,
      "grad_norm": 0.3575421869754791,
      "learning_rate": 9.194766143115135e-06,
      "loss": 0.4662,
      "step": 34272
    },
    {
      "epoch": 1.052836912112555,
      "grad_norm": 0.3877210021018982,
      "learning_rate": 9.194284436056116e-06,
      "loss": 0.4824,
      "step": 34273
    },
    {
      "epoch": 1.052867631247504,
      "grad_norm": 0.3862335681915283,
      "learning_rate": 9.1938027308789e-06,
      "loss": 0.5114,
      "step": 34274
    },
    {
      "epoch": 1.0528983503824532,
      "grad_norm": 0.4022451937198639,
      "learning_rate": 9.193321027584619e-06,
      "loss": 0.4728,
      "step": 34275
    },
    {
      "epoch": 1.0529290695174023,
      "grad_norm": 0.4524765908718109,
      "learning_rate": 9.192839326174385e-06,
      "loss": 0.4502,
      "step": 34276
    },
    {
      "epoch": 1.0529597886523516,
      "grad_norm": 0.5090203881263733,
      "learning_rate": 9.19235762664934e-06,
      "loss": 0.4755,
      "step": 34277
    },
    {
      "epoch": 1.0529905077873007,
      "grad_norm": 0.3698157072067261,
      "learning_rate": 9.191875929010592e-06,
      "loss": 0.4543,
      "step": 34278
    },
    {
      "epoch": 1.0530212269222499,
      "grad_norm": 0.3675597012042999,
      "learning_rate": 9.19139423325928e-06,
      "loss": 0.5038,
      "step": 34279
    },
    {
      "epoch": 1.053051946057199,
      "grad_norm": 0.40243372321128845,
      "learning_rate": 9.190912539396522e-06,
      "loss": 0.4915,
      "step": 34280
    },
    {
      "epoch": 1.053082665192148,
      "grad_norm": 0.3879340887069702,
      "learning_rate": 9.190430847423444e-06,
      "loss": 0.5218,
      "step": 34281
    },
    {
      "epoch": 1.0531133843270974,
      "grad_norm": 0.3422752320766449,
      "learning_rate": 9.18994915734117e-06,
      "loss": 0.4283,
      "step": 34282
    },
    {
      "epoch": 1.0531441034620466,
      "grad_norm": 0.40226221084594727,
      "learning_rate": 9.189467469150823e-06,
      "loss": 0.5231,
      "step": 34283
    },
    {
      "epoch": 1.0531748225969957,
      "grad_norm": 0.3854070007801056,
      "learning_rate": 9.188985782853537e-06,
      "loss": 0.4705,
      "step": 34284
    },
    {
      "epoch": 1.0532055417319448,
      "grad_norm": 0.3773510158061981,
      "learning_rate": 9.188504098450427e-06,
      "loss": 0.4865,
      "step": 34285
    },
    {
      "epoch": 1.053236260866894,
      "grad_norm": 0.39380356669425964,
      "learning_rate": 9.18802241594263e-06,
      "loss": 0.4919,
      "step": 34286
    },
    {
      "epoch": 1.053266980001843,
      "grad_norm": 0.3723137378692627,
      "learning_rate": 9.187540735331256e-06,
      "loss": 0.4263,
      "step": 34287
    },
    {
      "epoch": 1.0532976991367924,
      "grad_norm": 0.3320336639881134,
      "learning_rate": 9.18705905661744e-06,
      "loss": 0.4293,
      "step": 34288
    },
    {
      "epoch": 1.0533284182717415,
      "grad_norm": 0.38411611318588257,
      "learning_rate": 9.186577379802304e-06,
      "loss": 0.4774,
      "step": 34289
    },
    {
      "epoch": 1.0533591374066906,
      "grad_norm": 0.41071540117263794,
      "learning_rate": 9.186095704886974e-06,
      "loss": 0.5209,
      "step": 34290
    },
    {
      "epoch": 1.0533898565416397,
      "grad_norm": 0.3790282905101776,
      "learning_rate": 9.185614031872573e-06,
      "loss": 0.4469,
      "step": 34291
    },
    {
      "epoch": 1.0534205756765889,
      "grad_norm": 0.3905302584171295,
      "learning_rate": 9.185132360760228e-06,
      "loss": 0.5364,
      "step": 34292
    },
    {
      "epoch": 1.0534512948115382,
      "grad_norm": 0.4109134078025818,
      "learning_rate": 9.184650691551063e-06,
      "loss": 0.5719,
      "step": 34293
    },
    {
      "epoch": 1.0534820139464873,
      "grad_norm": 0.3865853548049927,
      "learning_rate": 9.184169024246204e-06,
      "loss": 0.4914,
      "step": 34294
    },
    {
      "epoch": 1.0535127330814364,
      "grad_norm": 0.4136357307434082,
      "learning_rate": 9.183687358846773e-06,
      "loss": 0.5315,
      "step": 34295
    },
    {
      "epoch": 1.0535434522163856,
      "grad_norm": 0.3634019196033478,
      "learning_rate": 9.183205695353901e-06,
      "loss": 0.455,
      "step": 34296
    },
    {
      "epoch": 1.0535741713513347,
      "grad_norm": 0.4039430320262909,
      "learning_rate": 9.182724033768707e-06,
      "loss": 0.4846,
      "step": 34297
    },
    {
      "epoch": 1.0536048904862838,
      "grad_norm": 0.3602287173271179,
      "learning_rate": 9.182242374092318e-06,
      "loss": 0.5743,
      "step": 34298
    },
    {
      "epoch": 1.0536356096212331,
      "grad_norm": 0.3715030550956726,
      "learning_rate": 9.181760716325858e-06,
      "loss": 0.5184,
      "step": 34299
    },
    {
      "epoch": 1.0536663287561823,
      "grad_norm": 0.41795778274536133,
      "learning_rate": 9.181279060470457e-06,
      "loss": 0.5698,
      "step": 34300
    },
    {
      "epoch": 1.0536970478911314,
      "grad_norm": 0.4342537820339203,
      "learning_rate": 9.180797406527231e-06,
      "loss": 0.5089,
      "step": 34301
    },
    {
      "epoch": 1.0537277670260805,
      "grad_norm": 0.40652599930763245,
      "learning_rate": 9.18031575449731e-06,
      "loss": 0.4598,
      "step": 34302
    },
    {
      "epoch": 1.0537584861610296,
      "grad_norm": 0.3984373211860657,
      "learning_rate": 9.179834104381823e-06,
      "loss": 0.6031,
      "step": 34303
    },
    {
      "epoch": 1.053789205295979,
      "grad_norm": 0.3969450891017914,
      "learning_rate": 9.179352456181887e-06,
      "loss": 0.635,
      "step": 34304
    },
    {
      "epoch": 1.053819924430928,
      "grad_norm": 0.35652217268943787,
      "learning_rate": 9.178870809898634e-06,
      "loss": 0.5019,
      "step": 34305
    },
    {
      "epoch": 1.0538506435658772,
      "grad_norm": 0.4179324507713318,
      "learning_rate": 9.17838916553318e-06,
      "loss": 0.5669,
      "step": 34306
    },
    {
      "epoch": 1.0538813627008263,
      "grad_norm": 0.39507511258125305,
      "learning_rate": 9.177907523086662e-06,
      "loss": 0.5027,
      "step": 34307
    },
    {
      "epoch": 1.0539120818357754,
      "grad_norm": 0.40117794275283813,
      "learning_rate": 9.177425882560195e-06,
      "loss": 0.5168,
      "step": 34308
    },
    {
      "epoch": 1.0539428009707246,
      "grad_norm": 0.4119916260242462,
      "learning_rate": 9.17694424395491e-06,
      "loss": 0.4695,
      "step": 34309
    },
    {
      "epoch": 1.053973520105674,
      "grad_norm": 0.38940638303756714,
      "learning_rate": 9.176462607271924e-06,
      "loss": 0.5457,
      "step": 34310
    },
    {
      "epoch": 1.054004239240623,
      "grad_norm": 0.375468909740448,
      "learning_rate": 9.175980972512374e-06,
      "loss": 0.4867,
      "step": 34311
    },
    {
      "epoch": 1.0540349583755722,
      "grad_norm": 0.38709673285484314,
      "learning_rate": 9.175499339677372e-06,
      "loss": 0.4565,
      "step": 34312
    },
    {
      "epoch": 1.0540656775105213,
      "grad_norm": 0.3810303807258606,
      "learning_rate": 9.175017708768054e-06,
      "loss": 0.5362,
      "step": 34313
    },
    {
      "epoch": 1.0540963966454704,
      "grad_norm": 0.34877580404281616,
      "learning_rate": 9.174536079785533e-06,
      "loss": 0.4518,
      "step": 34314
    },
    {
      "epoch": 1.0541271157804197,
      "grad_norm": 0.4212757647037506,
      "learning_rate": 9.174054452730948e-06,
      "loss": 0.4781,
      "step": 34315
    },
    {
      "epoch": 1.0541578349153689,
      "grad_norm": 0.3960435688495636,
      "learning_rate": 9.173572827605411e-06,
      "loss": 0.4629,
      "step": 34316
    },
    {
      "epoch": 1.054188554050318,
      "grad_norm": 0.4780082702636719,
      "learning_rate": 9.173091204410056e-06,
      "loss": 0.4408,
      "step": 34317
    },
    {
      "epoch": 1.054219273185267,
      "grad_norm": 0.36413219571113586,
      "learning_rate": 9.172609583146001e-06,
      "loss": 0.4701,
      "step": 34318
    },
    {
      "epoch": 1.0542499923202162,
      "grad_norm": 0.39385178685188293,
      "learning_rate": 9.172127963814378e-06,
      "loss": 0.5268,
      "step": 34319
    },
    {
      "epoch": 1.0542807114551653,
      "grad_norm": 0.4164915680885315,
      "learning_rate": 9.171646346416304e-06,
      "loss": 0.4867,
      "step": 34320
    },
    {
      "epoch": 1.0543114305901147,
      "grad_norm": 0.39596661925315857,
      "learning_rate": 9.171164730952909e-06,
      "loss": 0.4448,
      "step": 34321
    },
    {
      "epoch": 1.0543421497250638,
      "grad_norm": 0.4550074636936188,
      "learning_rate": 9.170683117425318e-06,
      "loss": 0.415,
      "step": 34322
    },
    {
      "epoch": 1.054372868860013,
      "grad_norm": 0.4282073676586151,
      "learning_rate": 9.170201505834652e-06,
      "loss": 0.5426,
      "step": 34323
    },
    {
      "epoch": 1.054403587994962,
      "grad_norm": 0.4138653874397278,
      "learning_rate": 9.16971989618204e-06,
      "loss": 0.4536,
      "step": 34324
    },
    {
      "epoch": 1.0544343071299112,
      "grad_norm": 0.3766722083091736,
      "learning_rate": 9.169238288468604e-06,
      "loss": 0.5009,
      "step": 34325
    },
    {
      "epoch": 1.0544650262648605,
      "grad_norm": 0.4089229702949524,
      "learning_rate": 9.168756682695473e-06,
      "loss": 0.5186,
      "step": 34326
    },
    {
      "epoch": 1.0544957453998096,
      "grad_norm": 0.38775068521499634,
      "learning_rate": 9.168275078863766e-06,
      "loss": 0.4636,
      "step": 34327
    },
    {
      "epoch": 1.0545264645347587,
      "grad_norm": 0.42007800936698914,
      "learning_rate": 9.167793476974613e-06,
      "loss": 0.4853,
      "step": 34328
    },
    {
      "epoch": 1.0545571836697079,
      "grad_norm": 0.35936591029167175,
      "learning_rate": 9.167311877029135e-06,
      "loss": 0.4763,
      "step": 34329
    },
    {
      "epoch": 1.054587902804657,
      "grad_norm": 0.43340662121772766,
      "learning_rate": 9.166830279028457e-06,
      "loss": 0.5341,
      "step": 34330
    },
    {
      "epoch": 1.054618621939606,
      "grad_norm": 0.38771852850914,
      "learning_rate": 9.166348682973708e-06,
      "loss": 0.5286,
      "step": 34331
    },
    {
      "epoch": 1.0546493410745554,
      "grad_norm": 0.37302058935165405,
      "learning_rate": 9.165867088866009e-06,
      "loss": 0.4154,
      "step": 34332
    },
    {
      "epoch": 1.0546800602095046,
      "grad_norm": 0.3591589331626892,
      "learning_rate": 9.165385496706483e-06,
      "loss": 0.5037,
      "step": 34333
    },
    {
      "epoch": 1.0547107793444537,
      "grad_norm": 0.3630141615867615,
      "learning_rate": 9.16490390649626e-06,
      "loss": 0.4981,
      "step": 34334
    },
    {
      "epoch": 1.0547414984794028,
      "grad_norm": 0.3871229588985443,
      "learning_rate": 9.164422318236462e-06,
      "loss": 0.5442,
      "step": 34335
    },
    {
      "epoch": 1.054772217614352,
      "grad_norm": 0.38740843534469604,
      "learning_rate": 9.163940731928214e-06,
      "loss": 0.4814,
      "step": 34336
    },
    {
      "epoch": 1.054802936749301,
      "grad_norm": 0.5155394077301025,
      "learning_rate": 9.16345914757264e-06,
      "loss": 0.443,
      "step": 34337
    },
    {
      "epoch": 1.0548336558842504,
      "grad_norm": 0.39112311601638794,
      "learning_rate": 9.162977565170864e-06,
      "loss": 0.5035,
      "step": 34338
    },
    {
      "epoch": 1.0548643750191995,
      "grad_norm": 0.34671953320503235,
      "learning_rate": 9.162495984724016e-06,
      "loss": 0.4931,
      "step": 34339
    },
    {
      "epoch": 1.0548950941541486,
      "grad_norm": 0.4042615294456482,
      "learning_rate": 9.162014406233213e-06,
      "loss": 0.4727,
      "step": 34340
    },
    {
      "epoch": 1.0549258132890977,
      "grad_norm": 0.38720667362213135,
      "learning_rate": 9.161532829699588e-06,
      "loss": 0.5236,
      "step": 34341
    },
    {
      "epoch": 1.0549565324240469,
      "grad_norm": 0.388751745223999,
      "learning_rate": 9.161051255124259e-06,
      "loss": 0.5684,
      "step": 34342
    },
    {
      "epoch": 1.0549872515589962,
      "grad_norm": 0.40317079424858093,
      "learning_rate": 9.160569682508356e-06,
      "loss": 0.463,
      "step": 34343
    },
    {
      "epoch": 1.0550179706939453,
      "grad_norm": 0.36985471844673157,
      "learning_rate": 9.160088111852999e-06,
      "loss": 0.4851,
      "step": 34344
    },
    {
      "epoch": 1.0550486898288944,
      "grad_norm": 0.42421072721481323,
      "learning_rate": 9.159606543159318e-06,
      "loss": 0.4701,
      "step": 34345
    },
    {
      "epoch": 1.0550794089638436,
      "grad_norm": 0.39931920170783997,
      "learning_rate": 9.15912497642843e-06,
      "loss": 0.4664,
      "step": 34346
    },
    {
      "epoch": 1.0551101280987927,
      "grad_norm": 0.3774932622909546,
      "learning_rate": 9.158643411661468e-06,
      "loss": 0.5025,
      "step": 34347
    },
    {
      "epoch": 1.0551408472337418,
      "grad_norm": 0.4675509035587311,
      "learning_rate": 9.15816184885955e-06,
      "loss": 0.5261,
      "step": 34348
    },
    {
      "epoch": 1.0551715663686911,
      "grad_norm": 0.3911201059818268,
      "learning_rate": 9.157680288023807e-06,
      "loss": 0.4512,
      "step": 34349
    },
    {
      "epoch": 1.0552022855036403,
      "grad_norm": 0.4003838002681732,
      "learning_rate": 9.157198729155359e-06,
      "loss": 0.5029,
      "step": 34350
    },
    {
      "epoch": 1.0552330046385894,
      "grad_norm": 0.41735342144966125,
      "learning_rate": 9.156717172255332e-06,
      "loss": 0.4955,
      "step": 34351
    },
    {
      "epoch": 1.0552637237735385,
      "grad_norm": 0.5218634009361267,
      "learning_rate": 9.15623561732485e-06,
      "loss": 0.3559,
      "step": 34352
    },
    {
      "epoch": 1.0552944429084876,
      "grad_norm": 0.3961445093154907,
      "learning_rate": 9.155754064365041e-06,
      "loss": 0.5707,
      "step": 34353
    },
    {
      "epoch": 1.055325162043437,
      "grad_norm": 0.37856757640838623,
      "learning_rate": 9.155272513377025e-06,
      "loss": 0.4844,
      "step": 34354
    },
    {
      "epoch": 1.055355881178386,
      "grad_norm": 0.40494948625564575,
      "learning_rate": 9.15479096436193e-06,
      "loss": 0.495,
      "step": 34355
    },
    {
      "epoch": 1.0553866003133352,
      "grad_norm": 0.4054337441921234,
      "learning_rate": 9.15430941732088e-06,
      "loss": 0.4617,
      "step": 34356
    },
    {
      "epoch": 1.0554173194482843,
      "grad_norm": 0.41571035981178284,
      "learning_rate": 9.153827872254997e-06,
      "loss": 0.4589,
      "step": 34357
    },
    {
      "epoch": 1.0554480385832334,
      "grad_norm": 0.4022594094276428,
      "learning_rate": 9.153346329165411e-06,
      "loss": 0.5247,
      "step": 34358
    },
    {
      "epoch": 1.0554787577181826,
      "grad_norm": 0.5653477907180786,
      "learning_rate": 9.152864788053243e-06,
      "loss": 0.5134,
      "step": 34359
    },
    {
      "epoch": 1.055509476853132,
      "grad_norm": 0.38104870915412903,
      "learning_rate": 9.15238324891962e-06,
      "loss": 0.5031,
      "step": 34360
    },
    {
      "epoch": 1.055540195988081,
      "grad_norm": 0.40859314799308777,
      "learning_rate": 9.151901711765662e-06,
      "loss": 0.4157,
      "step": 34361
    },
    {
      "epoch": 1.0555709151230301,
      "grad_norm": 0.4080294668674469,
      "learning_rate": 9.1514201765925e-06,
      "loss": 0.4749,
      "step": 34362
    },
    {
      "epoch": 1.0556016342579793,
      "grad_norm": 0.39151790738105774,
      "learning_rate": 9.150938643401251e-06,
      "loss": 0.5478,
      "step": 34363
    },
    {
      "epoch": 1.0556323533929284,
      "grad_norm": 0.390944242477417,
      "learning_rate": 9.150457112193048e-06,
      "loss": 0.5423,
      "step": 34364
    },
    {
      "epoch": 1.0556630725278777,
      "grad_norm": 0.3781951367855072,
      "learning_rate": 9.14997558296901e-06,
      "loss": 0.527,
      "step": 34365
    },
    {
      "epoch": 1.0556937916628268,
      "grad_norm": 0.3607373833656311,
      "learning_rate": 9.149494055730266e-06,
      "loss": 0.557,
      "step": 34366
    },
    {
      "epoch": 1.055724510797776,
      "grad_norm": 0.4081726670265198,
      "learning_rate": 9.149012530477934e-06,
      "loss": 0.522,
      "step": 34367
    },
    {
      "epoch": 1.055755229932725,
      "grad_norm": 0.33268505334854126,
      "learning_rate": 9.148531007213147e-06,
      "loss": 0.4269,
      "step": 34368
    },
    {
      "epoch": 1.0557859490676742,
      "grad_norm": 0.3838963508605957,
      "learning_rate": 9.14804948593702e-06,
      "loss": 0.6108,
      "step": 34369
    },
    {
      "epoch": 1.0558166682026233,
      "grad_norm": 0.36091822385787964,
      "learning_rate": 9.147567966650688e-06,
      "loss": 0.4698,
      "step": 34370
    },
    {
      "epoch": 1.0558473873375727,
      "grad_norm": 0.38430899381637573,
      "learning_rate": 9.147086449355269e-06,
      "loss": 0.4804,
      "step": 34371
    },
    {
      "epoch": 1.0558781064725218,
      "grad_norm": 0.3932786285877228,
      "learning_rate": 9.14660493405189e-06,
      "loss": 0.4862,
      "step": 34372
    },
    {
      "epoch": 1.055908825607471,
      "grad_norm": 0.38893038034439087,
      "learning_rate": 9.14612342074167e-06,
      "loss": 0.592,
      "step": 34373
    },
    {
      "epoch": 1.05593954474242,
      "grad_norm": 0.3926084637641907,
      "learning_rate": 9.145641909425745e-06,
      "loss": 0.5258,
      "step": 34374
    },
    {
      "epoch": 1.0559702638773691,
      "grad_norm": 0.3738088011741638,
      "learning_rate": 9.145160400105227e-06,
      "loss": 0.5007,
      "step": 34375
    },
    {
      "epoch": 1.0560009830123183,
      "grad_norm": 0.48087072372436523,
      "learning_rate": 9.14467889278125e-06,
      "loss": 0.4564,
      "step": 34376
    },
    {
      "epoch": 1.0560317021472676,
      "grad_norm": 0.3844855725765228,
      "learning_rate": 9.144197387454933e-06,
      "loss": 0.4859,
      "step": 34377
    },
    {
      "epoch": 1.0560624212822167,
      "grad_norm": 0.36323848366737366,
      "learning_rate": 9.143715884127405e-06,
      "loss": 0.5228,
      "step": 34378
    },
    {
      "epoch": 1.0560931404171658,
      "grad_norm": 0.38111791014671326,
      "learning_rate": 9.14323438279979e-06,
      "loss": 0.4713,
      "step": 34379
    },
    {
      "epoch": 1.056123859552115,
      "grad_norm": 0.380008339881897,
      "learning_rate": 9.142752883473206e-06,
      "loss": 0.5256,
      "step": 34380
    },
    {
      "epoch": 1.056154578687064,
      "grad_norm": 0.38590365648269653,
      "learning_rate": 9.14227138614879e-06,
      "loss": 0.5323,
      "step": 34381
    },
    {
      "epoch": 1.0561852978220134,
      "grad_norm": 0.38510552048683167,
      "learning_rate": 9.141789890827648e-06,
      "loss": 0.484,
      "step": 34382
    },
    {
      "epoch": 1.0562160169569625,
      "grad_norm": 0.421936571598053,
      "learning_rate": 9.141308397510926e-06,
      "loss": 0.5506,
      "step": 34383
    },
    {
      "epoch": 1.0562467360919117,
      "grad_norm": 0.4106430411338806,
      "learning_rate": 9.140826906199732e-06,
      "loss": 0.4916,
      "step": 34384
    },
    {
      "epoch": 1.0562774552268608,
      "grad_norm": 0.41832369565963745,
      "learning_rate": 9.140345416895201e-06,
      "loss": 0.524,
      "step": 34385
    },
    {
      "epoch": 1.05630817436181,
      "grad_norm": 0.35870444774627686,
      "learning_rate": 9.13986392959845e-06,
      "loss": 0.4843,
      "step": 34386
    },
    {
      "epoch": 1.056338893496759,
      "grad_norm": 0.3993151783943176,
      "learning_rate": 9.139382444310609e-06,
      "loss": 0.4679,
      "step": 34387
    },
    {
      "epoch": 1.0563696126317084,
      "grad_norm": 0.36996620893478394,
      "learning_rate": 9.138900961032799e-06,
      "loss": 0.5224,
      "step": 34388
    },
    {
      "epoch": 1.0564003317666575,
      "grad_norm": 0.40079185366630554,
      "learning_rate": 9.138419479766147e-06,
      "loss": 0.5714,
      "step": 34389
    },
    {
      "epoch": 1.0564310509016066,
      "grad_norm": 0.3808416426181793,
      "learning_rate": 9.137938000511774e-06,
      "loss": 0.4946,
      "step": 34390
    },
    {
      "epoch": 1.0564617700365557,
      "grad_norm": 0.36484068632125854,
      "learning_rate": 9.137456523270812e-06,
      "loss": 0.4666,
      "step": 34391
    },
    {
      "epoch": 1.0564924891715048,
      "grad_norm": 0.351441890001297,
      "learning_rate": 9.136975048044375e-06,
      "loss": 0.5226,
      "step": 34392
    },
    {
      "epoch": 1.0565232083064542,
      "grad_norm": 0.4225353002548218,
      "learning_rate": 9.136493574833594e-06,
      "loss": 0.5332,
      "step": 34393
    },
    {
      "epoch": 1.0565539274414033,
      "grad_norm": 0.3544893264770508,
      "learning_rate": 9.136012103639595e-06,
      "loss": 0.454,
      "step": 34394
    },
    {
      "epoch": 1.0565846465763524,
      "grad_norm": 0.4164715111255646,
      "learning_rate": 9.135530634463498e-06,
      "loss": 0.4206,
      "step": 34395
    },
    {
      "epoch": 1.0566153657113015,
      "grad_norm": 0.46998730301856995,
      "learning_rate": 9.135049167306433e-06,
      "loss": 0.5751,
      "step": 34396
    },
    {
      "epoch": 1.0566460848462507,
      "grad_norm": 0.41605010628700256,
      "learning_rate": 9.134567702169517e-06,
      "loss": 0.532,
      "step": 34397
    },
    {
      "epoch": 1.0566768039811998,
      "grad_norm": 0.37074077129364014,
      "learning_rate": 9.134086239053882e-06,
      "loss": 0.509,
      "step": 34398
    },
    {
      "epoch": 1.0567075231161491,
      "grad_norm": 0.3743104636669159,
      "learning_rate": 9.133604777960645e-06,
      "loss": 0.534,
      "step": 34399
    },
    {
      "epoch": 1.0567382422510982,
      "grad_norm": 0.40369197726249695,
      "learning_rate": 9.133123318890939e-06,
      "loss": 0.477,
      "step": 34400
    },
    {
      "epoch": 1.0567689613860474,
      "grad_norm": 0.4070036709308624,
      "learning_rate": 9.132641861845882e-06,
      "loss": 0.5441,
      "step": 34401
    },
    {
      "epoch": 1.0567996805209965,
      "grad_norm": 0.4596494436264038,
      "learning_rate": 9.1321604068266e-06,
      "loss": 0.549,
      "step": 34402
    },
    {
      "epoch": 1.0568303996559456,
      "grad_norm": 0.37273091077804565,
      "learning_rate": 9.131678953834218e-06,
      "loss": 0.4969,
      "step": 34403
    },
    {
      "epoch": 1.056861118790895,
      "grad_norm": 0.45004168152809143,
      "learning_rate": 9.131197502869863e-06,
      "loss": 0.4923,
      "step": 34404
    },
    {
      "epoch": 1.056891837925844,
      "grad_norm": 0.37999945878982544,
      "learning_rate": 9.130716053934651e-06,
      "loss": 0.4428,
      "step": 34405
    },
    {
      "epoch": 1.0569225570607932,
      "grad_norm": 0.38023850321769714,
      "learning_rate": 9.130234607029718e-06,
      "loss": 0.5145,
      "step": 34406
    },
    {
      "epoch": 1.0569532761957423,
      "grad_norm": 0.4027741849422455,
      "learning_rate": 9.12975316215618e-06,
      "loss": 0.5152,
      "step": 34407
    },
    {
      "epoch": 1.0569839953306914,
      "grad_norm": 0.38423675298690796,
      "learning_rate": 9.12927171931517e-06,
      "loss": 0.4833,
      "step": 34408
    },
    {
      "epoch": 1.0570147144656405,
      "grad_norm": 0.3821945786476135,
      "learning_rate": 9.128790278507798e-06,
      "loss": 0.494,
      "step": 34409
    },
    {
      "epoch": 1.05704543360059,
      "grad_norm": 0.442412406206131,
      "learning_rate": 9.128308839735203e-06,
      "loss": 0.5711,
      "step": 34410
    },
    {
      "epoch": 1.057076152735539,
      "grad_norm": 0.3625510334968567,
      "learning_rate": 9.1278274029985e-06,
      "loss": 0.525,
      "step": 34411
    },
    {
      "epoch": 1.0571068718704881,
      "grad_norm": 0.3604722023010254,
      "learning_rate": 9.127345968298817e-06,
      "loss": 0.518,
      "step": 34412
    },
    {
      "epoch": 1.0571375910054372,
      "grad_norm": 0.360512375831604,
      "learning_rate": 9.126864535637283e-06,
      "loss": 0.4657,
      "step": 34413
    },
    {
      "epoch": 1.0571683101403864,
      "grad_norm": 0.42828261852264404,
      "learning_rate": 9.126383105015012e-06,
      "loss": 0.4939,
      "step": 34414
    },
    {
      "epoch": 1.0571990292753357,
      "grad_norm": 0.40815621614456177,
      "learning_rate": 9.12590167643314e-06,
      "loss": 0.5119,
      "step": 34415
    },
    {
      "epoch": 1.0572297484102848,
      "grad_norm": 0.41214996576309204,
      "learning_rate": 9.12542024989278e-06,
      "loss": 0.4493,
      "step": 34416
    },
    {
      "epoch": 1.057260467545234,
      "grad_norm": 0.38925546407699585,
      "learning_rate": 9.124938825395069e-06,
      "loss": 0.5927,
      "step": 34417
    },
    {
      "epoch": 1.057291186680183,
      "grad_norm": 0.40601590275764465,
      "learning_rate": 9.124457402941118e-06,
      "loss": 0.5157,
      "step": 34418
    },
    {
      "epoch": 1.0573219058151322,
      "grad_norm": 0.3615138530731201,
      "learning_rate": 9.123975982532063e-06,
      "loss": 0.4553,
      "step": 34419
    },
    {
      "epoch": 1.0573526249500813,
      "grad_norm": 0.44608405232429504,
      "learning_rate": 9.123494564169019e-06,
      "loss": 0.5312,
      "step": 34420
    },
    {
      "epoch": 1.0573833440850307,
      "grad_norm": 0.36703306436538696,
      "learning_rate": 9.123013147853117e-06,
      "loss": 0.5179,
      "step": 34421
    },
    {
      "epoch": 1.0574140632199798,
      "grad_norm": 0.4133560061454773,
      "learning_rate": 9.122531733585479e-06,
      "loss": 0.4688,
      "step": 34422
    },
    {
      "epoch": 1.057444782354929,
      "grad_norm": 0.3916955590248108,
      "learning_rate": 9.122050321367228e-06,
      "loss": 0.5174,
      "step": 34423
    },
    {
      "epoch": 1.057475501489878,
      "grad_norm": 0.40233004093170166,
      "learning_rate": 9.12156891119949e-06,
      "loss": 0.4805,
      "step": 34424
    },
    {
      "epoch": 1.0575062206248271,
      "grad_norm": 0.6008226871490479,
      "learning_rate": 9.121087503083392e-06,
      "loss": 0.522,
      "step": 34425
    },
    {
      "epoch": 1.0575369397597765,
      "grad_norm": 0.4263792037963867,
      "learning_rate": 9.12060609702005e-06,
      "loss": 0.5402,
      "step": 34426
    },
    {
      "epoch": 1.0575676588947256,
      "grad_norm": 0.3621577322483063,
      "learning_rate": 9.120124693010599e-06,
      "loss": 0.5005,
      "step": 34427
    },
    {
      "epoch": 1.0575983780296747,
      "grad_norm": 0.4695116877555847,
      "learning_rate": 9.119643291056154e-06,
      "loss": 0.4121,
      "step": 34428
    },
    {
      "epoch": 1.0576290971646238,
      "grad_norm": 0.4003829061985016,
      "learning_rate": 9.119161891157847e-06,
      "loss": 0.5826,
      "step": 34429
    },
    {
      "epoch": 1.057659816299573,
      "grad_norm": 0.4134208559989929,
      "learning_rate": 9.118680493316798e-06,
      "loss": 0.5014,
      "step": 34430
    },
    {
      "epoch": 1.057690535434522,
      "grad_norm": 0.39586585760116577,
      "learning_rate": 9.118199097534132e-06,
      "loss": 0.486,
      "step": 34431
    },
    {
      "epoch": 1.0577212545694714,
      "grad_norm": 0.36527445912361145,
      "learning_rate": 9.117717703810974e-06,
      "loss": 0.4741,
      "step": 34432
    },
    {
      "epoch": 1.0577519737044205,
      "grad_norm": 0.5564559102058411,
      "learning_rate": 9.117236312148446e-06,
      "loss": 0.4702,
      "step": 34433
    },
    {
      "epoch": 1.0577826928393697,
      "grad_norm": 0.39271289110183716,
      "learning_rate": 9.116754922547677e-06,
      "loss": 0.4947,
      "step": 34434
    },
    {
      "epoch": 1.0578134119743188,
      "grad_norm": 0.37284132838249207,
      "learning_rate": 9.116273535009788e-06,
      "loss": 0.5151,
      "step": 34435
    },
    {
      "epoch": 1.057844131109268,
      "grad_norm": 0.36988207697868347,
      "learning_rate": 9.115792149535904e-06,
      "loss": 0.4693,
      "step": 34436
    },
    {
      "epoch": 1.0578748502442172,
      "grad_norm": 0.4014728367328644,
      "learning_rate": 9.115310766127147e-06,
      "loss": 0.5199,
      "step": 34437
    },
    {
      "epoch": 1.0579055693791664,
      "grad_norm": 0.4823722541332245,
      "learning_rate": 9.114829384784646e-06,
      "loss": 0.4569,
      "step": 34438
    },
    {
      "epoch": 1.0579362885141155,
      "grad_norm": 0.37908047437667847,
      "learning_rate": 9.11434800550952e-06,
      "loss": 0.4758,
      "step": 34439
    },
    {
      "epoch": 1.0579670076490646,
      "grad_norm": 0.3609057664871216,
      "learning_rate": 9.1138666283029e-06,
      "loss": 0.485,
      "step": 34440
    },
    {
      "epoch": 1.0579977267840137,
      "grad_norm": 0.42015722393989563,
      "learning_rate": 9.113385253165902e-06,
      "loss": 0.5849,
      "step": 34441
    },
    {
      "epoch": 1.0580284459189628,
      "grad_norm": 0.35959941148757935,
      "learning_rate": 9.11290388009966e-06,
      "loss": 0.5216,
      "step": 34442
    },
    {
      "epoch": 1.0580591650539122,
      "grad_norm": 0.36744412779808044,
      "learning_rate": 9.112422509105288e-06,
      "loss": 0.4749,
      "step": 34443
    },
    {
      "epoch": 1.0580898841888613,
      "grad_norm": 0.432125985622406,
      "learning_rate": 9.11194114018392e-06,
      "loss": 0.5038,
      "step": 34444
    },
    {
      "epoch": 1.0581206033238104,
      "grad_norm": 0.4034057855606079,
      "learning_rate": 9.11145977333667e-06,
      "loss": 0.4615,
      "step": 34445
    },
    {
      "epoch": 1.0581513224587595,
      "grad_norm": 0.4054633378982544,
      "learning_rate": 9.110978408564673e-06,
      "loss": 0.5131,
      "step": 34446
    },
    {
      "epoch": 1.0581820415937087,
      "grad_norm": 0.4242044985294342,
      "learning_rate": 9.110497045869042e-06,
      "loss": 0.5091,
      "step": 34447
    },
    {
      "epoch": 1.0582127607286578,
      "grad_norm": 0.41068410873413086,
      "learning_rate": 9.11001568525091e-06,
      "loss": 0.4448,
      "step": 34448
    },
    {
      "epoch": 1.0582434798636071,
      "grad_norm": 0.5319815278053284,
      "learning_rate": 9.109534326711402e-06,
      "loss": 0.532,
      "step": 34449
    },
    {
      "epoch": 1.0582741989985562,
      "grad_norm": 0.3641766309738159,
      "learning_rate": 9.109052970251632e-06,
      "loss": 0.5352,
      "step": 34450
    },
    {
      "epoch": 1.0583049181335054,
      "grad_norm": 0.373077929019928,
      "learning_rate": 9.108571615872738e-06,
      "loss": 0.4414,
      "step": 34451
    },
    {
      "epoch": 1.0583356372684545,
      "grad_norm": 0.5003872513771057,
      "learning_rate": 9.10809026357583e-06,
      "loss": 0.5284,
      "step": 34452
    },
    {
      "epoch": 1.0583663564034036,
      "grad_norm": 0.40953728556632996,
      "learning_rate": 9.107608913362048e-06,
      "loss": 0.5852,
      "step": 34453
    },
    {
      "epoch": 1.058397075538353,
      "grad_norm": 0.40094974637031555,
      "learning_rate": 9.107127565232502e-06,
      "loss": 0.4442,
      "step": 34454
    },
    {
      "epoch": 1.058427794673302,
      "grad_norm": 0.38827070593833923,
      "learning_rate": 9.106646219188324e-06,
      "loss": 0.504,
      "step": 34455
    },
    {
      "epoch": 1.0584585138082512,
      "grad_norm": 0.39764514565467834,
      "learning_rate": 9.106164875230636e-06,
      "loss": 0.5305,
      "step": 34456
    },
    {
      "epoch": 1.0584892329432003,
      "grad_norm": 0.4205226004123688,
      "learning_rate": 9.105683533360562e-06,
      "loss": 0.5514,
      "step": 34457
    },
    {
      "epoch": 1.0585199520781494,
      "grad_norm": 0.4410560131072998,
      "learning_rate": 9.105202193579225e-06,
      "loss": 0.5774,
      "step": 34458
    },
    {
      "epoch": 1.0585506712130985,
      "grad_norm": 0.36240333318710327,
      "learning_rate": 9.104720855887753e-06,
      "loss": 0.473,
      "step": 34459
    },
    {
      "epoch": 1.0585813903480479,
      "grad_norm": 0.3981799781322479,
      "learning_rate": 9.104239520287266e-06,
      "loss": 0.4917,
      "step": 34460
    },
    {
      "epoch": 1.058612109482997,
      "grad_norm": 0.4256010055541992,
      "learning_rate": 9.103758186778892e-06,
      "loss": 0.4821,
      "step": 34461
    },
    {
      "epoch": 1.0586428286179461,
      "grad_norm": 0.39974245429039,
      "learning_rate": 9.103276855363753e-06,
      "loss": 0.5603,
      "step": 34462
    },
    {
      "epoch": 1.0586735477528952,
      "grad_norm": 0.43227994441986084,
      "learning_rate": 9.102795526042973e-06,
      "loss": 0.4256,
      "step": 34463
    },
    {
      "epoch": 1.0587042668878444,
      "grad_norm": 0.4622112810611725,
      "learning_rate": 9.102314198817675e-06,
      "loss": 0.4233,
      "step": 34464
    },
    {
      "epoch": 1.0587349860227937,
      "grad_norm": 0.3828054666519165,
      "learning_rate": 9.101832873688988e-06,
      "loss": 0.4704,
      "step": 34465
    },
    {
      "epoch": 1.0587657051577428,
      "grad_norm": 0.4089263677597046,
      "learning_rate": 9.101351550658032e-06,
      "loss": 0.5394,
      "step": 34466
    },
    {
      "epoch": 1.058796424292692,
      "grad_norm": 0.3748475909233093,
      "learning_rate": 9.100870229725929e-06,
      "loss": 0.5278,
      "step": 34467
    },
    {
      "epoch": 1.058827143427641,
      "grad_norm": 0.3698730170726776,
      "learning_rate": 9.100388910893811e-06,
      "loss": 0.54,
      "step": 34468
    },
    {
      "epoch": 1.0588578625625902,
      "grad_norm": 0.37749847769737244,
      "learning_rate": 9.099907594162796e-06,
      "loss": 0.5272,
      "step": 34469
    },
    {
      "epoch": 1.0588885816975393,
      "grad_norm": 0.3722824156284332,
      "learning_rate": 9.099426279534011e-06,
      "loss": 0.4825,
      "step": 34470
    },
    {
      "epoch": 1.0589193008324886,
      "grad_norm": 0.3401872217655182,
      "learning_rate": 9.098944967008575e-06,
      "loss": 0.4574,
      "step": 34471
    },
    {
      "epoch": 1.0589500199674378,
      "grad_norm": 0.3815496861934662,
      "learning_rate": 9.09846365658762e-06,
      "loss": 0.4217,
      "step": 34472
    },
    {
      "epoch": 1.0589807391023869,
      "grad_norm": 0.397842675447464,
      "learning_rate": 9.097982348272263e-06,
      "loss": 0.6168,
      "step": 34473
    },
    {
      "epoch": 1.059011458237336,
      "grad_norm": 0.36848142743110657,
      "learning_rate": 9.097501042063634e-06,
      "loss": 0.4728,
      "step": 34474
    },
    {
      "epoch": 1.0590421773722851,
      "grad_norm": 0.4173181354999542,
      "learning_rate": 9.09701973796285e-06,
      "loss": 0.5366,
      "step": 34475
    },
    {
      "epoch": 1.0590728965072345,
      "grad_norm": 0.37819090485572815,
      "learning_rate": 9.096538435971047e-06,
      "loss": 0.492,
      "step": 34476
    },
    {
      "epoch": 1.0591036156421836,
      "grad_norm": 0.454654723405838,
      "learning_rate": 9.096057136089333e-06,
      "loss": 0.5658,
      "step": 34477
    },
    {
      "epoch": 1.0591343347771327,
      "grad_norm": 0.38147297501564026,
      "learning_rate": 9.095575838318848e-06,
      "loss": 0.464,
      "step": 34478
    },
    {
      "epoch": 1.0591650539120818,
      "grad_norm": 0.36367109417915344,
      "learning_rate": 9.095094542660703e-06,
      "loss": 0.5026,
      "step": 34479
    },
    {
      "epoch": 1.059195773047031,
      "grad_norm": 0.42839744687080383,
      "learning_rate": 9.094613249116034e-06,
      "loss": 0.5444,
      "step": 34480
    },
    {
      "epoch": 1.05922649218198,
      "grad_norm": 0.38696345686912537,
      "learning_rate": 9.094131957685952e-06,
      "loss": 0.4825,
      "step": 34481
    },
    {
      "epoch": 1.0592572113169294,
      "grad_norm": 0.45260554552078247,
      "learning_rate": 9.093650668371595e-06,
      "loss": 0.5965,
      "step": 34482
    },
    {
      "epoch": 1.0592879304518785,
      "grad_norm": 0.35213708877563477,
      "learning_rate": 9.093169381174076e-06,
      "loss": 0.3877,
      "step": 34483
    },
    {
      "epoch": 1.0593186495868276,
      "grad_norm": 0.4321938753128052,
      "learning_rate": 9.09268809609452e-06,
      "loss": 0.5297,
      "step": 34484
    },
    {
      "epoch": 1.0593493687217768,
      "grad_norm": 0.40306800603866577,
      "learning_rate": 9.09220681313406e-06,
      "loss": 0.5676,
      "step": 34485
    },
    {
      "epoch": 1.0593800878567259,
      "grad_norm": 0.3928591310977936,
      "learning_rate": 9.09172553229381e-06,
      "loss": 0.5013,
      "step": 34486
    },
    {
      "epoch": 1.059410806991675,
      "grad_norm": 0.5598305463790894,
      "learning_rate": 9.091244253574904e-06,
      "loss": 0.5427,
      "step": 34487
    },
    {
      "epoch": 1.0594415261266243,
      "grad_norm": 0.36135658621788025,
      "learning_rate": 9.090762976978456e-06,
      "loss": 0.5023,
      "step": 34488
    },
    {
      "epoch": 1.0594722452615735,
      "grad_norm": 0.36941173672676086,
      "learning_rate": 9.090281702505599e-06,
      "loss": 0.4979,
      "step": 34489
    },
    {
      "epoch": 1.0595029643965226,
      "grad_norm": 0.39940395951271057,
      "learning_rate": 9.089800430157448e-06,
      "loss": 0.4804,
      "step": 34490
    },
    {
      "epoch": 1.0595336835314717,
      "grad_norm": 0.32691627740859985,
      "learning_rate": 9.089319159935135e-06,
      "loss": 0.501,
      "step": 34491
    },
    {
      "epoch": 1.0595644026664208,
      "grad_norm": 0.35628047585487366,
      "learning_rate": 9.088837891839779e-06,
      "loss": 0.4823,
      "step": 34492
    },
    {
      "epoch": 1.0595951218013702,
      "grad_norm": 0.3567172884941101,
      "learning_rate": 9.088356625872505e-06,
      "loss": 0.4808,
      "step": 34493
    },
    {
      "epoch": 1.0596258409363193,
      "grad_norm": 0.37666016817092896,
      "learning_rate": 9.087875362034438e-06,
      "loss": 0.4555,
      "step": 34494
    },
    {
      "epoch": 1.0596565600712684,
      "grad_norm": 0.3642556369304657,
      "learning_rate": 9.087394100326705e-06,
      "loss": 0.4735,
      "step": 34495
    },
    {
      "epoch": 1.0596872792062175,
      "grad_norm": 0.3592042028903961,
      "learning_rate": 9.086912840750421e-06,
      "loss": 0.4742,
      "step": 34496
    },
    {
      "epoch": 1.0597179983411666,
      "grad_norm": 0.40355968475341797,
      "learning_rate": 9.086431583306721e-06,
      "loss": 0.3911,
      "step": 34497
    },
    {
      "epoch": 1.0597487174761158,
      "grad_norm": 0.47777101397514343,
      "learning_rate": 9.085950327996721e-06,
      "loss": 0.4895,
      "step": 34498
    },
    {
      "epoch": 1.059779436611065,
      "grad_norm": 0.37529540061950684,
      "learning_rate": 9.085469074821549e-06,
      "loss": 0.4852,
      "step": 34499
    },
    {
      "epoch": 1.0598101557460142,
      "grad_norm": 0.38559070229530334,
      "learning_rate": 9.084987823782328e-06,
      "loss": 0.4655,
      "step": 34500
    },
    {
      "epoch": 1.0598408748809633,
      "grad_norm": 0.37546372413635254,
      "learning_rate": 9.084506574880183e-06,
      "loss": 0.5724,
      "step": 34501
    },
    {
      "epoch": 1.0598715940159125,
      "grad_norm": 0.40366262197494507,
      "learning_rate": 9.084025328116233e-06,
      "loss": 0.5323,
      "step": 34502
    },
    {
      "epoch": 1.0599023131508616,
      "grad_norm": 0.37742647528648376,
      "learning_rate": 9.083544083491606e-06,
      "loss": 0.4788,
      "step": 34503
    },
    {
      "epoch": 1.059933032285811,
      "grad_norm": 0.40263673663139343,
      "learning_rate": 9.08306284100743e-06,
      "loss": 0.5376,
      "step": 34504
    },
    {
      "epoch": 1.05996375142076,
      "grad_norm": 0.37786659598350525,
      "learning_rate": 9.082581600664822e-06,
      "loss": 0.4648,
      "step": 34505
    },
    {
      "epoch": 1.0599944705557092,
      "grad_norm": 0.37020477652549744,
      "learning_rate": 9.08210036246491e-06,
      "loss": 0.429,
      "step": 34506
    },
    {
      "epoch": 1.0600251896906583,
      "grad_norm": 0.4206860363483429,
      "learning_rate": 9.081619126408815e-06,
      "loss": 0.4844,
      "step": 34507
    },
    {
      "epoch": 1.0600559088256074,
      "grad_norm": 0.36370760202407837,
      "learning_rate": 9.081137892497664e-06,
      "loss": 0.5549,
      "step": 34508
    },
    {
      "epoch": 1.0600866279605565,
      "grad_norm": 0.4149535596370697,
      "learning_rate": 9.08065666073258e-06,
      "loss": 0.5351,
      "step": 34509
    },
    {
      "epoch": 1.0601173470955059,
      "grad_norm": 0.4224608838558197,
      "learning_rate": 9.080175431114686e-06,
      "loss": 0.4574,
      "step": 34510
    },
    {
      "epoch": 1.060148066230455,
      "grad_norm": 0.40291377902030945,
      "learning_rate": 9.079694203645105e-06,
      "loss": 0.5793,
      "step": 34511
    },
    {
      "epoch": 1.060178785365404,
      "grad_norm": 0.40436476469039917,
      "learning_rate": 9.079212978324967e-06,
      "loss": 0.416,
      "step": 34512
    },
    {
      "epoch": 1.0602095045003532,
      "grad_norm": 0.34740352630615234,
      "learning_rate": 9.078731755155385e-06,
      "loss": 0.5499,
      "step": 34513
    },
    {
      "epoch": 1.0602402236353023,
      "grad_norm": 0.43307146430015564,
      "learning_rate": 9.078250534137497e-06,
      "loss": 0.4405,
      "step": 34514
    },
    {
      "epoch": 1.0602709427702517,
      "grad_norm": 0.398091584444046,
      "learning_rate": 9.07776931527241e-06,
      "loss": 0.6444,
      "step": 34515
    },
    {
      "epoch": 1.0603016619052008,
      "grad_norm": 0.4143748879432678,
      "learning_rate": 9.077288098561266e-06,
      "loss": 0.495,
      "step": 34516
    },
    {
      "epoch": 1.06033238104015,
      "grad_norm": 0.4058375060558319,
      "learning_rate": 9.076806884005175e-06,
      "loss": 0.4735,
      "step": 34517
    },
    {
      "epoch": 1.060363100175099,
      "grad_norm": 0.39339831471443176,
      "learning_rate": 9.076325671605268e-06,
      "loss": 0.4736,
      "step": 34518
    },
    {
      "epoch": 1.0603938193100482,
      "grad_norm": 0.49192240834236145,
      "learning_rate": 9.075844461362665e-06,
      "loss": 0.5274,
      "step": 34519
    },
    {
      "epoch": 1.0604245384449973,
      "grad_norm": 0.45379602909088135,
      "learning_rate": 9.075363253278494e-06,
      "loss": 0.5365,
      "step": 34520
    },
    {
      "epoch": 1.0604552575799466,
      "grad_norm": 0.36913979053497314,
      "learning_rate": 9.074882047353874e-06,
      "loss": 0.4841,
      "step": 34521
    },
    {
      "epoch": 1.0604859767148958,
      "grad_norm": 0.4066097140312195,
      "learning_rate": 9.074400843589932e-06,
      "loss": 0.4978,
      "step": 34522
    },
    {
      "epoch": 1.0605166958498449,
      "grad_norm": 0.37574878334999084,
      "learning_rate": 9.073919641987795e-06,
      "loss": 0.5269,
      "step": 34523
    },
    {
      "epoch": 1.060547414984794,
      "grad_norm": 0.38502535223960876,
      "learning_rate": 9.07343844254858e-06,
      "loss": 0.5958,
      "step": 34524
    },
    {
      "epoch": 1.060578134119743,
      "grad_norm": 0.3779594600200653,
      "learning_rate": 9.072957245273416e-06,
      "loss": 0.5132,
      "step": 34525
    },
    {
      "epoch": 1.0606088532546925,
      "grad_norm": 0.36274009943008423,
      "learning_rate": 9.072476050163423e-06,
      "loss": 0.4962,
      "step": 34526
    },
    {
      "epoch": 1.0606395723896416,
      "grad_norm": 0.41675135493278503,
      "learning_rate": 9.071994857219729e-06,
      "loss": 0.5266,
      "step": 34527
    },
    {
      "epoch": 1.0606702915245907,
      "grad_norm": 0.3754853308200836,
      "learning_rate": 9.071513666443454e-06,
      "loss": 0.5136,
      "step": 34528
    },
    {
      "epoch": 1.0607010106595398,
      "grad_norm": 0.3661934435367584,
      "learning_rate": 9.071032477835727e-06,
      "loss": 0.5469,
      "step": 34529
    },
    {
      "epoch": 1.060731729794489,
      "grad_norm": 0.39989253878593445,
      "learning_rate": 9.070551291397664e-06,
      "loss": 0.4793,
      "step": 34530
    },
    {
      "epoch": 1.060762448929438,
      "grad_norm": 0.39428403973579407,
      "learning_rate": 9.070070107130397e-06,
      "loss": 0.4558,
      "step": 34531
    },
    {
      "epoch": 1.0607931680643874,
      "grad_norm": 0.3759656548500061,
      "learning_rate": 9.069588925035045e-06,
      "loss": 0.4351,
      "step": 34532
    },
    {
      "epoch": 1.0608238871993365,
      "grad_norm": 0.37912383675575256,
      "learning_rate": 9.069107745112732e-06,
      "loss": 0.567,
      "step": 34533
    },
    {
      "epoch": 1.0608546063342856,
      "grad_norm": 0.40586966276168823,
      "learning_rate": 9.068626567364584e-06,
      "loss": 0.5705,
      "step": 34534
    },
    {
      "epoch": 1.0608853254692348,
      "grad_norm": 0.3789331614971161,
      "learning_rate": 9.068145391791724e-06,
      "loss": 0.5406,
      "step": 34535
    },
    {
      "epoch": 1.0609160446041839,
      "grad_norm": 0.33692753314971924,
      "learning_rate": 9.067664218395275e-06,
      "loss": 0.4866,
      "step": 34536
    },
    {
      "epoch": 1.0609467637391332,
      "grad_norm": 0.3681670129299164,
      "learning_rate": 9.067183047176363e-06,
      "loss": 0.5422,
      "step": 34537
    },
    {
      "epoch": 1.0609774828740823,
      "grad_norm": 0.3957594037055969,
      "learning_rate": 9.066701878136106e-06,
      "loss": 0.5431,
      "step": 34538
    },
    {
      "epoch": 1.0610082020090315,
      "grad_norm": 0.46067243814468384,
      "learning_rate": 9.066220711275632e-06,
      "loss": 0.4597,
      "step": 34539
    },
    {
      "epoch": 1.0610389211439806,
      "grad_norm": 0.37541306018829346,
      "learning_rate": 9.06573954659607e-06,
      "loss": 0.5105,
      "step": 34540
    },
    {
      "epoch": 1.0610696402789297,
      "grad_norm": 0.37239426374435425,
      "learning_rate": 9.065258384098535e-06,
      "loss": 0.4998,
      "step": 34541
    },
    {
      "epoch": 1.0611003594138788,
      "grad_norm": 0.4176139235496521,
      "learning_rate": 9.064777223784155e-06,
      "loss": 0.4576,
      "step": 34542
    },
    {
      "epoch": 1.0611310785488282,
      "grad_norm": 0.38793471455574036,
      "learning_rate": 9.064296065654052e-06,
      "loss": 0.5541,
      "step": 34543
    },
    {
      "epoch": 1.0611617976837773,
      "grad_norm": 0.3768535554409027,
      "learning_rate": 9.063814909709355e-06,
      "loss": 0.4533,
      "step": 34544
    },
    {
      "epoch": 1.0611925168187264,
      "grad_norm": 0.4087384045124054,
      "learning_rate": 9.063333755951178e-06,
      "loss": 0.5828,
      "step": 34545
    },
    {
      "epoch": 1.0612232359536755,
      "grad_norm": 0.4077761769294739,
      "learning_rate": 9.062852604380657e-06,
      "loss": 0.4968,
      "step": 34546
    },
    {
      "epoch": 1.0612539550886246,
      "grad_norm": 0.3914402425289154,
      "learning_rate": 9.062371454998902e-06,
      "loss": 0.4917,
      "step": 34547
    },
    {
      "epoch": 1.061284674223574,
      "grad_norm": 0.3807124197483063,
      "learning_rate": 9.06189030780705e-06,
      "loss": 0.4446,
      "step": 34548
    },
    {
      "epoch": 1.061315393358523,
      "grad_norm": 0.4224700927734375,
      "learning_rate": 9.061409162806213e-06,
      "loss": 0.4762,
      "step": 34549
    },
    {
      "epoch": 1.0613461124934722,
      "grad_norm": 0.37347742915153503,
      "learning_rate": 9.060928019997526e-06,
      "loss": 0.5246,
      "step": 34550
    },
    {
      "epoch": 1.0613768316284213,
      "grad_norm": 0.40591713786125183,
      "learning_rate": 9.060446879382103e-06,
      "loss": 0.4572,
      "step": 34551
    },
    {
      "epoch": 1.0614075507633705,
      "grad_norm": 0.5260277390480042,
      "learning_rate": 9.059965740961075e-06,
      "loss": 0.5203,
      "step": 34552
    },
    {
      "epoch": 1.0614382698983196,
      "grad_norm": 0.38621804118156433,
      "learning_rate": 9.05948460473556e-06,
      "loss": 0.4718,
      "step": 34553
    },
    {
      "epoch": 1.061468989033269,
      "grad_norm": 0.39460811018943787,
      "learning_rate": 9.059003470706687e-06,
      "loss": 0.4697,
      "step": 34554
    },
    {
      "epoch": 1.061499708168218,
      "grad_norm": 0.3939265310764313,
      "learning_rate": 9.058522338875575e-06,
      "loss": 0.5085,
      "step": 34555
    },
    {
      "epoch": 1.0615304273031672,
      "grad_norm": 0.40186432003974915,
      "learning_rate": 9.058041209243351e-06,
      "loss": 0.5624,
      "step": 34556
    },
    {
      "epoch": 1.0615611464381163,
      "grad_norm": 0.3797282576560974,
      "learning_rate": 9.057560081811136e-06,
      "loss": 0.4728,
      "step": 34557
    },
    {
      "epoch": 1.0615918655730654,
      "grad_norm": 0.3602895438671112,
      "learning_rate": 9.057078956580055e-06,
      "loss": 0.5031,
      "step": 34558
    },
    {
      "epoch": 1.0616225847080145,
      "grad_norm": 0.38091808557510376,
      "learning_rate": 9.056597833551235e-06,
      "loss": 0.4655,
      "step": 34559
    },
    {
      "epoch": 1.0616533038429639,
      "grad_norm": 0.405291885137558,
      "learning_rate": 9.056116712725794e-06,
      "loss": 0.5643,
      "step": 34560
    },
    {
      "epoch": 1.061684022977913,
      "grad_norm": 0.3976026177406311,
      "learning_rate": 9.05563559410486e-06,
      "loss": 0.4751,
      "step": 34561
    },
    {
      "epoch": 1.061714742112862,
      "grad_norm": 0.37756648659706116,
      "learning_rate": 9.055154477689553e-06,
      "loss": 0.4935,
      "step": 34562
    },
    {
      "epoch": 1.0617454612478112,
      "grad_norm": 0.40226075053215027,
      "learning_rate": 9.054673363481002e-06,
      "loss": 0.5032,
      "step": 34563
    },
    {
      "epoch": 1.0617761803827603,
      "grad_norm": 0.3833020329475403,
      "learning_rate": 9.054192251480323e-06,
      "loss": 0.4518,
      "step": 34564
    },
    {
      "epoch": 1.0618068995177097,
      "grad_norm": 0.45434775948524475,
      "learning_rate": 9.053711141688649e-06,
      "loss": 0.4636,
      "step": 34565
    },
    {
      "epoch": 1.0618376186526588,
      "grad_norm": 0.43114009499549866,
      "learning_rate": 9.053230034107095e-06,
      "loss": 0.5313,
      "step": 34566
    },
    {
      "epoch": 1.061868337787608,
      "grad_norm": 0.3808661699295044,
      "learning_rate": 9.05274892873679e-06,
      "loss": 0.5373,
      "step": 34567
    },
    {
      "epoch": 1.061899056922557,
      "grad_norm": 0.3916378915309906,
      "learning_rate": 9.052267825578854e-06,
      "loss": 0.5067,
      "step": 34568
    },
    {
      "epoch": 1.0619297760575062,
      "grad_norm": 0.3459908366203308,
      "learning_rate": 9.051786724634417e-06,
      "loss": 0.5178,
      "step": 34569
    },
    {
      "epoch": 1.0619604951924553,
      "grad_norm": 0.36837658286094666,
      "learning_rate": 9.051305625904593e-06,
      "loss": 0.4897,
      "step": 34570
    },
    {
      "epoch": 1.0619912143274046,
      "grad_norm": 0.3767724931240082,
      "learning_rate": 9.050824529390515e-06,
      "loss": 0.5253,
      "step": 34571
    },
    {
      "epoch": 1.0620219334623537,
      "grad_norm": 0.417377769947052,
      "learning_rate": 9.0503434350933e-06,
      "loss": 0.5021,
      "step": 34572
    },
    {
      "epoch": 1.0620526525973029,
      "grad_norm": 0.3475373387336731,
      "learning_rate": 9.049862343014077e-06,
      "loss": 0.5224,
      "step": 34573
    },
    {
      "epoch": 1.062083371732252,
      "grad_norm": 0.3761378824710846,
      "learning_rate": 9.049381253153963e-06,
      "loss": 0.5222,
      "step": 34574
    },
    {
      "epoch": 1.062114090867201,
      "grad_norm": 0.3798580467700958,
      "learning_rate": 9.048900165514088e-06,
      "loss": 0.5336,
      "step": 34575
    },
    {
      "epoch": 1.0621448100021504,
      "grad_norm": 0.3751274049282074,
      "learning_rate": 9.048419080095573e-06,
      "loss": 0.5381,
      "step": 34576
    },
    {
      "epoch": 1.0621755291370996,
      "grad_norm": 0.4190656244754791,
      "learning_rate": 9.04793799689954e-06,
      "loss": 0.4797,
      "step": 34577
    },
    {
      "epoch": 1.0622062482720487,
      "grad_norm": 0.3992367386817932,
      "learning_rate": 9.047456915927118e-06,
      "loss": 0.5309,
      "step": 34578
    },
    {
      "epoch": 1.0622369674069978,
      "grad_norm": 0.430542528629303,
      "learning_rate": 9.046975837179423e-06,
      "loss": 0.5002,
      "step": 34579
    },
    {
      "epoch": 1.062267686541947,
      "grad_norm": 0.4018670320510864,
      "learning_rate": 9.046494760657587e-06,
      "loss": 0.4677,
      "step": 34580
    },
    {
      "epoch": 1.062298405676896,
      "grad_norm": 0.3843851685523987,
      "learning_rate": 9.046013686362723e-06,
      "loss": 0.485,
      "step": 34581
    },
    {
      "epoch": 1.0623291248118454,
      "grad_norm": 0.41809403896331787,
      "learning_rate": 9.045532614295967e-06,
      "loss": 0.5057,
      "step": 34582
    },
    {
      "epoch": 1.0623598439467945,
      "grad_norm": 0.3776850998401642,
      "learning_rate": 9.04505154445843e-06,
      "loss": 0.4712,
      "step": 34583
    },
    {
      "epoch": 1.0623905630817436,
      "grad_norm": 0.36730536818504333,
      "learning_rate": 9.04457047685125e-06,
      "loss": 0.5258,
      "step": 34584
    },
    {
      "epoch": 1.0624212822166927,
      "grad_norm": 0.3720499873161316,
      "learning_rate": 9.044089411475531e-06,
      "loss": 0.5142,
      "step": 34585
    },
    {
      "epoch": 1.0624520013516419,
      "grad_norm": 0.42076122760772705,
      "learning_rate": 9.04360834833242e-06,
      "loss": 0.4513,
      "step": 34586
    },
    {
      "epoch": 1.0624827204865912,
      "grad_norm": 0.38450887799263,
      "learning_rate": 9.04312728742302e-06,
      "loss": 0.4846,
      "step": 34587
    },
    {
      "epoch": 1.0625134396215403,
      "grad_norm": 0.36374974250793457,
      "learning_rate": 9.042646228748467e-06,
      "loss": 0.4763,
      "step": 34588
    },
    {
      "epoch": 1.0625441587564894,
      "grad_norm": 0.36890485882759094,
      "learning_rate": 9.042165172309878e-06,
      "loss": 0.4534,
      "step": 34589
    },
    {
      "epoch": 1.0625748778914386,
      "grad_norm": 0.3705882132053375,
      "learning_rate": 9.041684118108383e-06,
      "loss": 0.5125,
      "step": 34590
    },
    {
      "epoch": 1.0626055970263877,
      "grad_norm": 0.43808847665786743,
      "learning_rate": 9.041203066145098e-06,
      "loss": 0.5512,
      "step": 34591
    },
    {
      "epoch": 1.0626363161613368,
      "grad_norm": 0.45696526765823364,
      "learning_rate": 9.040722016421151e-06,
      "loss": 0.4349,
      "step": 34592
    },
    {
      "epoch": 1.0626670352962861,
      "grad_norm": 0.37722453474998474,
      "learning_rate": 9.040240968937664e-06,
      "loss": 0.5188,
      "step": 34593
    },
    {
      "epoch": 1.0626977544312353,
      "grad_norm": 0.3627104163169861,
      "learning_rate": 9.039759923695762e-06,
      "loss": 0.5058,
      "step": 34594
    },
    {
      "epoch": 1.0627284735661844,
      "grad_norm": 0.3835314214229584,
      "learning_rate": 9.039278880696569e-06,
      "loss": 0.5278,
      "step": 34595
    },
    {
      "epoch": 1.0627591927011335,
      "grad_norm": 0.3924214541912079,
      "learning_rate": 9.038797839941205e-06,
      "loss": 0.586,
      "step": 34596
    },
    {
      "epoch": 1.0627899118360826,
      "grad_norm": 0.38980790972709656,
      "learning_rate": 9.038316801430799e-06,
      "loss": 0.5013,
      "step": 34597
    },
    {
      "epoch": 1.0628206309710317,
      "grad_norm": 0.4191659688949585,
      "learning_rate": 9.037835765166468e-06,
      "loss": 0.492,
      "step": 34598
    },
    {
      "epoch": 1.062851350105981,
      "grad_norm": 0.37312623858451843,
      "learning_rate": 9.037354731149342e-06,
      "loss": 0.4332,
      "step": 34599
    },
    {
      "epoch": 1.0628820692409302,
      "grad_norm": 0.3890596628189087,
      "learning_rate": 9.036873699380538e-06,
      "loss": 0.5822,
      "step": 34600
    },
    {
      "epoch": 1.0629127883758793,
      "grad_norm": 0.5049858093261719,
      "learning_rate": 9.036392669861185e-06,
      "loss": 0.4085,
      "step": 34601
    },
    {
      "epoch": 1.0629435075108284,
      "grad_norm": 0.391718327999115,
      "learning_rate": 9.035911642592404e-06,
      "loss": 0.5473,
      "step": 34602
    },
    {
      "epoch": 1.0629742266457776,
      "grad_norm": 0.48960667848587036,
      "learning_rate": 9.035430617575319e-06,
      "loss": 0.6083,
      "step": 34603
    },
    {
      "epoch": 1.063004945780727,
      "grad_norm": 0.37425315380096436,
      "learning_rate": 9.03494959481105e-06,
      "loss": 0.5189,
      "step": 34604
    },
    {
      "epoch": 1.063035664915676,
      "grad_norm": 0.3801305294036865,
      "learning_rate": 9.034468574300727e-06,
      "loss": 0.4834,
      "step": 34605
    },
    {
      "epoch": 1.0630663840506251,
      "grad_norm": 0.403105229139328,
      "learning_rate": 9.033987556045467e-06,
      "loss": 0.4927,
      "step": 34606
    },
    {
      "epoch": 1.0630971031855743,
      "grad_norm": 0.36981409788131714,
      "learning_rate": 9.0335065400464e-06,
      "loss": 0.4768,
      "step": 34607
    },
    {
      "epoch": 1.0631278223205234,
      "grad_norm": 0.401840478181839,
      "learning_rate": 9.033025526304643e-06,
      "loss": 0.5265,
      "step": 34608
    },
    {
      "epoch": 1.0631585414554725,
      "grad_norm": 0.5217737555503845,
      "learning_rate": 9.032544514821329e-06,
      "loss": 0.5282,
      "step": 34609
    },
    {
      "epoch": 1.0631892605904218,
      "grad_norm": 0.3961772620677948,
      "learning_rate": 9.032063505597566e-06,
      "loss": 0.4612,
      "step": 34610
    },
    {
      "epoch": 1.063219979725371,
      "grad_norm": 0.4034962058067322,
      "learning_rate": 9.031582498634492e-06,
      "loss": 0.4836,
      "step": 34611
    },
    {
      "epoch": 1.06325069886032,
      "grad_norm": 0.3812278211116791,
      "learning_rate": 9.031101493933221e-06,
      "loss": 0.4949,
      "step": 34612
    },
    {
      "epoch": 1.0632814179952692,
      "grad_norm": 0.3821195065975189,
      "learning_rate": 9.03062049149488e-06,
      "loss": 0.5165,
      "step": 34613
    },
    {
      "epoch": 1.0633121371302183,
      "grad_norm": 0.42474111914634705,
      "learning_rate": 9.030139491320596e-06,
      "loss": 0.5505,
      "step": 34614
    },
    {
      "epoch": 1.0633428562651677,
      "grad_norm": 0.37710413336753845,
      "learning_rate": 9.029658493411485e-06,
      "loss": 0.5322,
      "step": 34615
    },
    {
      "epoch": 1.0633735754001168,
      "grad_norm": 0.39008355140686035,
      "learning_rate": 9.029177497768681e-06,
      "loss": 0.4456,
      "step": 34616
    },
    {
      "epoch": 1.063404294535066,
      "grad_norm": 0.36033201217651367,
      "learning_rate": 9.028696504393293e-06,
      "loss": 0.4467,
      "step": 34617
    },
    {
      "epoch": 1.063435013670015,
      "grad_norm": 0.37109336256980896,
      "learning_rate": 9.028215513286459e-06,
      "loss": 0.4641,
      "step": 34618
    },
    {
      "epoch": 1.0634657328049641,
      "grad_norm": 0.42481353878974915,
      "learning_rate": 9.027734524449289e-06,
      "loss": 0.5165,
      "step": 34619
    },
    {
      "epoch": 1.0634964519399133,
      "grad_norm": 0.39010581374168396,
      "learning_rate": 9.02725353788292e-06,
      "loss": 0.4824,
      "step": 34620
    },
    {
      "epoch": 1.0635271710748626,
      "grad_norm": 0.37299883365631104,
      "learning_rate": 9.02677255358846e-06,
      "loss": 0.475,
      "step": 34621
    },
    {
      "epoch": 1.0635578902098117,
      "grad_norm": 0.35804134607315063,
      "learning_rate": 9.026291571567049e-06,
      "loss": 0.4215,
      "step": 34622
    },
    {
      "epoch": 1.0635886093447608,
      "grad_norm": 0.34062305092811584,
      "learning_rate": 9.025810591819797e-06,
      "loss": 0.5054,
      "step": 34623
    },
    {
      "epoch": 1.06361932847971,
      "grad_norm": 0.3642065227031708,
      "learning_rate": 9.025329614347834e-06,
      "loss": 0.4358,
      "step": 34624
    },
    {
      "epoch": 1.063650047614659,
      "grad_norm": 0.378141313791275,
      "learning_rate": 9.02484863915228e-06,
      "loss": 0.4942,
      "step": 34625
    },
    {
      "epoch": 1.0636807667496084,
      "grad_norm": 0.40842732787132263,
      "learning_rate": 9.024367666234262e-06,
      "loss": 0.4346,
      "step": 34626
    },
    {
      "epoch": 1.0637114858845576,
      "grad_norm": 0.41873612999916077,
      "learning_rate": 9.0238866955949e-06,
      "loss": 0.4757,
      "step": 34627
    },
    {
      "epoch": 1.0637422050195067,
      "grad_norm": 0.3720126450061798,
      "learning_rate": 9.023405727235322e-06,
      "loss": 0.4293,
      "step": 34628
    },
    {
      "epoch": 1.0637729241544558,
      "grad_norm": 0.4152867794036865,
      "learning_rate": 9.022924761156644e-06,
      "loss": 0.4965,
      "step": 34629
    },
    {
      "epoch": 1.063803643289405,
      "grad_norm": 0.6221581697463989,
      "learning_rate": 9.022443797359994e-06,
      "loss": 0.4523,
      "step": 34630
    },
    {
      "epoch": 1.063834362424354,
      "grad_norm": 0.3548772633075714,
      "learning_rate": 9.021962835846497e-06,
      "loss": 0.528,
      "step": 34631
    },
    {
      "epoch": 1.0638650815593034,
      "grad_norm": 0.3983420729637146,
      "learning_rate": 9.021481876617272e-06,
      "loss": 0.457,
      "step": 34632
    },
    {
      "epoch": 1.0638958006942525,
      "grad_norm": 0.3851315975189209,
      "learning_rate": 9.021000919673446e-06,
      "loss": 0.562,
      "step": 34633
    },
    {
      "epoch": 1.0639265198292016,
      "grad_norm": 0.3977729380130768,
      "learning_rate": 9.020519965016139e-06,
      "loss": 0.4555,
      "step": 34634
    },
    {
      "epoch": 1.0639572389641507,
      "grad_norm": 0.9711658358573914,
      "learning_rate": 9.020039012646478e-06,
      "loss": 0.4543,
      "step": 34635
    },
    {
      "epoch": 1.0639879580990999,
      "grad_norm": 0.3689742386341095,
      "learning_rate": 9.019558062565583e-06,
      "loss": 0.5206,
      "step": 34636
    },
    {
      "epoch": 1.0640186772340492,
      "grad_norm": 0.4078413248062134,
      "learning_rate": 9.01907711477458e-06,
      "loss": 0.5107,
      "step": 34637
    },
    {
      "epoch": 1.0640493963689983,
      "grad_norm": 0.38407185673713684,
      "learning_rate": 9.018596169274589e-06,
      "loss": 0.5277,
      "step": 34638
    },
    {
      "epoch": 1.0640801155039474,
      "grad_norm": 0.4059376120567322,
      "learning_rate": 9.018115226066738e-06,
      "loss": 0.447,
      "step": 34639
    },
    {
      "epoch": 1.0641108346388966,
      "grad_norm": 0.4050901532173157,
      "learning_rate": 9.017634285152145e-06,
      "loss": 0.4847,
      "step": 34640
    },
    {
      "epoch": 1.0641415537738457,
      "grad_norm": 0.4569106698036194,
      "learning_rate": 9.017153346531936e-06,
      "loss": 0.5137,
      "step": 34641
    },
    {
      "epoch": 1.0641722729087948,
      "grad_norm": 0.3707694411277771,
      "learning_rate": 9.016672410207234e-06,
      "loss": 0.4665,
      "step": 34642
    },
    {
      "epoch": 1.0642029920437441,
      "grad_norm": 0.44086766242980957,
      "learning_rate": 9.016191476179165e-06,
      "loss": 0.4541,
      "step": 34643
    },
    {
      "epoch": 1.0642337111786933,
      "grad_norm": 0.37628471851348877,
      "learning_rate": 9.015710544448846e-06,
      "loss": 0.4527,
      "step": 34644
    },
    {
      "epoch": 1.0642644303136424,
      "grad_norm": 0.3976086378097534,
      "learning_rate": 9.015229615017408e-06,
      "loss": 0.4819,
      "step": 34645
    },
    {
      "epoch": 1.0642951494485915,
      "grad_norm": 0.3745806813240051,
      "learning_rate": 9.014748687885963e-06,
      "loss": 0.4493,
      "step": 34646
    },
    {
      "epoch": 1.0643258685835406,
      "grad_norm": 0.3925791084766388,
      "learning_rate": 9.014267763055649e-06,
      "loss": 0.4996,
      "step": 34647
    },
    {
      "epoch": 1.06435658771849,
      "grad_norm": 0.410871297121048,
      "learning_rate": 9.013786840527573e-06,
      "loss": 0.4904,
      "step": 34648
    },
    {
      "epoch": 1.064387306853439,
      "grad_norm": 0.3464493453502655,
      "learning_rate": 9.013305920302872e-06,
      "loss": 0.5206,
      "step": 34649
    },
    {
      "epoch": 1.0644180259883882,
      "grad_norm": 0.37375953793525696,
      "learning_rate": 9.012825002382668e-06,
      "loss": 0.5413,
      "step": 34650
    },
    {
      "epoch": 1.0644487451233373,
      "grad_norm": 0.35319244861602783,
      "learning_rate": 9.012344086768072e-06,
      "loss": 0.495,
      "step": 34651
    },
    {
      "epoch": 1.0644794642582864,
      "grad_norm": 0.400920033454895,
      "learning_rate": 9.011863173460221e-06,
      "loss": 0.5031,
      "step": 34652
    },
    {
      "epoch": 1.0645101833932356,
      "grad_norm": 0.33926790952682495,
      "learning_rate": 9.011382262460227e-06,
      "loss": 0.4408,
      "step": 34653
    },
    {
      "epoch": 1.064540902528185,
      "grad_norm": 0.38851961493492126,
      "learning_rate": 9.010901353769226e-06,
      "loss": 0.5195,
      "step": 34654
    },
    {
      "epoch": 1.064571621663134,
      "grad_norm": 0.4092808961868286,
      "learning_rate": 9.010420447388326e-06,
      "loss": 0.4921,
      "step": 34655
    },
    {
      "epoch": 1.0646023407980831,
      "grad_norm": 0.4659632444381714,
      "learning_rate": 9.009939543318667e-06,
      "loss": 0.439,
      "step": 34656
    },
    {
      "epoch": 1.0646330599330323,
      "grad_norm": 0.3636682331562042,
      "learning_rate": 9.009458641561358e-06,
      "loss": 0.4912,
      "step": 34657
    },
    {
      "epoch": 1.0646637790679814,
      "grad_norm": 0.3820069432258606,
      "learning_rate": 9.008977742117529e-06,
      "loss": 0.5261,
      "step": 34658
    },
    {
      "epoch": 1.0646944982029307,
      "grad_norm": 0.3683375418186188,
      "learning_rate": 9.008496844988299e-06,
      "loss": 0.4834,
      "step": 34659
    },
    {
      "epoch": 1.0647252173378798,
      "grad_norm": 0.3855583071708679,
      "learning_rate": 9.008015950174796e-06,
      "loss": 0.5296,
      "step": 34660
    },
    {
      "epoch": 1.064755936472829,
      "grad_norm": 0.38965874910354614,
      "learning_rate": 9.00753505767814e-06,
      "loss": 0.4479,
      "step": 34661
    },
    {
      "epoch": 1.064786655607778,
      "grad_norm": 0.4009667932987213,
      "learning_rate": 9.007054167499457e-06,
      "loss": 0.5289,
      "step": 34662
    },
    {
      "epoch": 1.0648173747427272,
      "grad_norm": 0.377365380525589,
      "learning_rate": 9.006573279639868e-06,
      "loss": 0.5676,
      "step": 34663
    },
    {
      "epoch": 1.0648480938776763,
      "grad_norm": 0.37669387459754944,
      "learning_rate": 9.006092394100496e-06,
      "loss": 0.5331,
      "step": 34664
    },
    {
      "epoch": 1.0648788130126257,
      "grad_norm": 0.39922067523002625,
      "learning_rate": 9.005611510882465e-06,
      "loss": 0.4279,
      "step": 34665
    },
    {
      "epoch": 1.0649095321475748,
      "grad_norm": 0.3870439827442169,
      "learning_rate": 9.005130629986897e-06,
      "loss": 0.579,
      "step": 34666
    },
    {
      "epoch": 1.064940251282524,
      "grad_norm": 0.40718740224838257,
      "learning_rate": 9.004649751414914e-06,
      "loss": 0.5126,
      "step": 34667
    },
    {
      "epoch": 1.064970970417473,
      "grad_norm": 0.3961641788482666,
      "learning_rate": 9.004168875167643e-06,
      "loss": 0.4955,
      "step": 34668
    },
    {
      "epoch": 1.0650016895524221,
      "grad_norm": 0.377218097448349,
      "learning_rate": 9.003688001246206e-06,
      "loss": 0.5487,
      "step": 34669
    },
    {
      "epoch": 1.0650324086873715,
      "grad_norm": 0.3714149594306946,
      "learning_rate": 9.003207129651723e-06,
      "loss": 0.4551,
      "step": 34670
    },
    {
      "epoch": 1.0650631278223206,
      "grad_norm": 0.3811953365802765,
      "learning_rate": 9.002726260385323e-06,
      "loss": 0.4431,
      "step": 34671
    },
    {
      "epoch": 1.0650938469572697,
      "grad_norm": 0.4321991801261902,
      "learning_rate": 9.002245393448122e-06,
      "loss": 0.5229,
      "step": 34672
    },
    {
      "epoch": 1.0651245660922188,
      "grad_norm": 0.35218167304992676,
      "learning_rate": 9.001764528841249e-06,
      "loss": 0.4823,
      "step": 34673
    },
    {
      "epoch": 1.065155285227168,
      "grad_norm": 0.3942931890487671,
      "learning_rate": 9.001283666565822e-06,
      "loss": 0.5816,
      "step": 34674
    },
    {
      "epoch": 1.065186004362117,
      "grad_norm": 0.369104266166687,
      "learning_rate": 9.00080280662297e-06,
      "loss": 0.5243,
      "step": 34675
    },
    {
      "epoch": 1.0652167234970664,
      "grad_norm": 0.3729519844055176,
      "learning_rate": 9.00032194901381e-06,
      "loss": 0.503,
      "step": 34676
    },
    {
      "epoch": 1.0652474426320155,
      "grad_norm": 0.5487062931060791,
      "learning_rate": 8.99984109373947e-06,
      "loss": 0.5005,
      "step": 34677
    },
    {
      "epoch": 1.0652781617669647,
      "grad_norm": 0.38768044114112854,
      "learning_rate": 8.999360240801068e-06,
      "loss": 0.5033,
      "step": 34678
    },
    {
      "epoch": 1.0653088809019138,
      "grad_norm": 0.42267924547195435,
      "learning_rate": 8.998879390199736e-06,
      "loss": 0.4975,
      "step": 34679
    },
    {
      "epoch": 1.065339600036863,
      "grad_norm": 0.37793582677841187,
      "learning_rate": 8.998398541936584e-06,
      "loss": 0.5111,
      "step": 34680
    },
    {
      "epoch": 1.065370319171812,
      "grad_norm": 0.36027413606643677,
      "learning_rate": 8.997917696012748e-06,
      "loss": 0.5336,
      "step": 34681
    },
    {
      "epoch": 1.0654010383067614,
      "grad_norm": 0.3790108561515808,
      "learning_rate": 8.99743685242934e-06,
      "loss": 0.5045,
      "step": 34682
    },
    {
      "epoch": 1.0654317574417105,
      "grad_norm": 0.46368661522865295,
      "learning_rate": 8.996956011187494e-06,
      "loss": 0.5735,
      "step": 34683
    },
    {
      "epoch": 1.0654624765766596,
      "grad_norm": 0.4602244198322296,
      "learning_rate": 8.99647517228832e-06,
      "loss": 0.4871,
      "step": 34684
    },
    {
      "epoch": 1.0654931957116087,
      "grad_norm": 0.36994504928588867,
      "learning_rate": 8.995994335732952e-06,
      "loss": 0.5165,
      "step": 34685
    },
    {
      "epoch": 1.0655239148465578,
      "grad_norm": 0.36446937918663025,
      "learning_rate": 8.995513501522512e-06,
      "loss": 0.5144,
      "step": 34686
    },
    {
      "epoch": 1.0655546339815072,
      "grad_norm": 0.38671374320983887,
      "learning_rate": 8.995032669658116e-06,
      "loss": 0.4374,
      "step": 34687
    },
    {
      "epoch": 1.0655853531164563,
      "grad_norm": 0.3920287787914276,
      "learning_rate": 8.994551840140897e-06,
      "loss": 0.4545,
      "step": 34688
    },
    {
      "epoch": 1.0656160722514054,
      "grad_norm": 0.38964590430259705,
      "learning_rate": 8.994071012971966e-06,
      "loss": 0.4722,
      "step": 34689
    },
    {
      "epoch": 1.0656467913863545,
      "grad_norm": 0.33485522866249084,
      "learning_rate": 8.993590188152458e-06,
      "loss": 0.4385,
      "step": 34690
    },
    {
      "epoch": 1.0656775105213037,
      "grad_norm": 0.3580092191696167,
      "learning_rate": 8.993109365683486e-06,
      "loss": 0.4621,
      "step": 34691
    },
    {
      "epoch": 1.0657082296562528,
      "grad_norm": 0.3826780915260315,
      "learning_rate": 8.99262854556618e-06,
      "loss": 0.5167,
      "step": 34692
    },
    {
      "epoch": 1.0657389487912021,
      "grad_norm": 0.38349902629852295,
      "learning_rate": 8.992147727801659e-06,
      "loss": 0.3991,
      "step": 34693
    },
    {
      "epoch": 1.0657696679261512,
      "grad_norm": 0.3410252630710602,
      "learning_rate": 8.991666912391049e-06,
      "loss": 0.4853,
      "step": 34694
    },
    {
      "epoch": 1.0658003870611004,
      "grad_norm": 0.36350569128990173,
      "learning_rate": 8.99118609933547e-06,
      "loss": 0.4163,
      "step": 34695
    },
    {
      "epoch": 1.0658311061960495,
      "grad_norm": 0.36598408222198486,
      "learning_rate": 8.990705288636047e-06,
      "loss": 0.5204,
      "step": 34696
    },
    {
      "epoch": 1.0658618253309986,
      "grad_norm": 0.8475886583328247,
      "learning_rate": 8.990224480293902e-06,
      "loss": 0.4154,
      "step": 34697
    },
    {
      "epoch": 1.0658925444659477,
      "grad_norm": 0.40319114923477173,
      "learning_rate": 8.989743674310157e-06,
      "loss": 0.4794,
      "step": 34698
    },
    {
      "epoch": 1.065923263600897,
      "grad_norm": 0.36921635270118713,
      "learning_rate": 8.989262870685936e-06,
      "loss": 0.4709,
      "step": 34699
    },
    {
      "epoch": 1.0659539827358462,
      "grad_norm": 0.35108858346939087,
      "learning_rate": 8.988782069422365e-06,
      "loss": 0.4575,
      "step": 34700
    },
    {
      "epoch": 1.0659847018707953,
      "grad_norm": 0.4354109764099121,
      "learning_rate": 8.988301270520562e-06,
      "loss": 0.526,
      "step": 34701
    },
    {
      "epoch": 1.0660154210057444,
      "grad_norm": 0.38815581798553467,
      "learning_rate": 8.987820473981653e-06,
      "loss": 0.542,
      "step": 34702
    },
    {
      "epoch": 1.0660461401406935,
      "grad_norm": 0.3798476755619049,
      "learning_rate": 8.987339679806759e-06,
      "loss": 0.495,
      "step": 34703
    },
    {
      "epoch": 1.0660768592756429,
      "grad_norm": 0.4298725128173828,
      "learning_rate": 8.986858887997003e-06,
      "loss": 0.4537,
      "step": 34704
    },
    {
      "epoch": 1.066107578410592,
      "grad_norm": 0.3722853362560272,
      "learning_rate": 8.98637809855351e-06,
      "loss": 0.4863,
      "step": 34705
    },
    {
      "epoch": 1.0661382975455411,
      "grad_norm": 0.35963982343673706,
      "learning_rate": 8.985897311477403e-06,
      "loss": 0.4827,
      "step": 34706
    },
    {
      "epoch": 1.0661690166804902,
      "grad_norm": 0.38110145926475525,
      "learning_rate": 8.985416526769804e-06,
      "loss": 0.522,
      "step": 34707
    },
    {
      "epoch": 1.0661997358154394,
      "grad_norm": 0.39160096645355225,
      "learning_rate": 8.984935744431831e-06,
      "loss": 0.4673,
      "step": 34708
    },
    {
      "epoch": 1.0662304549503885,
      "grad_norm": 0.4325980246067047,
      "learning_rate": 8.984454964464617e-06,
      "loss": 0.5343,
      "step": 34709
    },
    {
      "epoch": 1.0662611740853378,
      "grad_norm": 0.40636202692985535,
      "learning_rate": 8.983974186869276e-06,
      "loss": 0.5062,
      "step": 34710
    },
    {
      "epoch": 1.066291893220287,
      "grad_norm": 0.3859656751155853,
      "learning_rate": 8.983493411646937e-06,
      "loss": 0.4764,
      "step": 34711
    },
    {
      "epoch": 1.066322612355236,
      "grad_norm": 0.3434425890445709,
      "learning_rate": 8.983012638798716e-06,
      "loss": 0.4855,
      "step": 34712
    },
    {
      "epoch": 1.0663533314901852,
      "grad_norm": 0.4015387296676636,
      "learning_rate": 8.982531868325745e-06,
      "loss": 0.5044,
      "step": 34713
    },
    {
      "epoch": 1.0663840506251343,
      "grad_norm": 0.35335299372673035,
      "learning_rate": 8.982051100229137e-06,
      "loss": 0.4312,
      "step": 34714
    },
    {
      "epoch": 1.0664147697600836,
      "grad_norm": 0.34697815775871277,
      "learning_rate": 8.981570334510026e-06,
      "loss": 0.5474,
      "step": 34715
    },
    {
      "epoch": 1.0664454888950328,
      "grad_norm": 0.3902365565299988,
      "learning_rate": 8.981089571169522e-06,
      "loss": 0.532,
      "step": 34716
    },
    {
      "epoch": 1.0664762080299819,
      "grad_norm": 0.39930102229118347,
      "learning_rate": 8.98060881020876e-06,
      "loss": 0.5342,
      "step": 34717
    },
    {
      "epoch": 1.066506927164931,
      "grad_norm": 0.4108559489250183,
      "learning_rate": 8.98012805162885e-06,
      "loss": 0.4765,
      "step": 34718
    },
    {
      "epoch": 1.0665376462998801,
      "grad_norm": 0.3990646004676819,
      "learning_rate": 8.97964729543093e-06,
      "loss": 0.4977,
      "step": 34719
    },
    {
      "epoch": 1.0665683654348292,
      "grad_norm": 0.41214174032211304,
      "learning_rate": 8.979166541616111e-06,
      "loss": 0.5436,
      "step": 34720
    },
    {
      "epoch": 1.0665990845697786,
      "grad_norm": 0.3939685821533203,
      "learning_rate": 8.978685790185517e-06,
      "loss": 0.4773,
      "step": 34721
    },
    {
      "epoch": 1.0666298037047277,
      "grad_norm": 0.5397027730941772,
      "learning_rate": 8.97820504114028e-06,
      "loss": 0.462,
      "step": 34722
    },
    {
      "epoch": 1.0666605228396768,
      "grad_norm": 0.3853359818458557,
      "learning_rate": 8.97772429448151e-06,
      "loss": 0.4567,
      "step": 34723
    },
    {
      "epoch": 1.066691241974626,
      "grad_norm": 1.3720701932907104,
      "learning_rate": 8.977243550210345e-06,
      "loss": 0.4623,
      "step": 34724
    },
    {
      "epoch": 1.066721961109575,
      "grad_norm": 0.40843719244003296,
      "learning_rate": 8.97676280832789e-06,
      "loss": 0.5039,
      "step": 34725
    },
    {
      "epoch": 1.0667526802445244,
      "grad_norm": 0.3680703043937683,
      "learning_rate": 8.976282068835284e-06,
      "loss": 0.488,
      "step": 34726
    },
    {
      "epoch": 1.0667833993794735,
      "grad_norm": 0.3743877112865448,
      "learning_rate": 8.975801331733638e-06,
      "loss": 0.4964,
      "step": 34727
    },
    {
      "epoch": 1.0668141185144226,
      "grad_norm": 0.36016979813575745,
      "learning_rate": 8.975320597024081e-06,
      "loss": 0.5303,
      "step": 34728
    },
    {
      "epoch": 1.0668448376493718,
      "grad_norm": 0.40916699171066284,
      "learning_rate": 8.974839864707736e-06,
      "loss": 0.5432,
      "step": 34729
    },
    {
      "epoch": 1.0668755567843209,
      "grad_norm": 0.412430077791214,
      "learning_rate": 8.974359134785723e-06,
      "loss": 0.4837,
      "step": 34730
    },
    {
      "epoch": 1.06690627591927,
      "grad_norm": 0.42448747158050537,
      "learning_rate": 8.973878407259164e-06,
      "loss": 0.4798,
      "step": 34731
    },
    {
      "epoch": 1.0669369950542194,
      "grad_norm": 0.3804609775543213,
      "learning_rate": 8.973397682129186e-06,
      "loss": 0.6011,
      "step": 34732
    },
    {
      "epoch": 1.0669677141891685,
      "grad_norm": 0.37199780344963074,
      "learning_rate": 8.972916959396908e-06,
      "loss": 0.5183,
      "step": 34733
    },
    {
      "epoch": 1.0669984333241176,
      "grad_norm": 0.4586452543735504,
      "learning_rate": 8.972436239063456e-06,
      "loss": 0.4288,
      "step": 34734
    },
    {
      "epoch": 1.0670291524590667,
      "grad_norm": 0.3531269431114197,
      "learning_rate": 8.971955521129948e-06,
      "loss": 0.4637,
      "step": 34735
    },
    {
      "epoch": 1.0670598715940158,
      "grad_norm": 0.3575794994831085,
      "learning_rate": 8.971474805597513e-06,
      "loss": 0.4897,
      "step": 34736
    },
    {
      "epoch": 1.0670905907289652,
      "grad_norm": 0.4303586184978485,
      "learning_rate": 8.970994092467266e-06,
      "loss": 0.608,
      "step": 34737
    },
    {
      "epoch": 1.0671213098639143,
      "grad_norm": 0.3927271068096161,
      "learning_rate": 8.970513381740338e-06,
      "loss": 0.4347,
      "step": 34738
    },
    {
      "epoch": 1.0671520289988634,
      "grad_norm": 0.37774866819381714,
      "learning_rate": 8.970032673417847e-06,
      "loss": 0.5282,
      "step": 34739
    },
    {
      "epoch": 1.0671827481338125,
      "grad_norm": 0.3968800902366638,
      "learning_rate": 8.969551967500915e-06,
      "loss": 0.5268,
      "step": 34740
    },
    {
      "epoch": 1.0672134672687617,
      "grad_norm": 0.4385422468185425,
      "learning_rate": 8.969071263990668e-06,
      "loss": 0.4697,
      "step": 34741
    },
    {
      "epoch": 1.0672441864037108,
      "grad_norm": 0.37370941042900085,
      "learning_rate": 8.968590562888227e-06,
      "loss": 0.469,
      "step": 34742
    },
    {
      "epoch": 1.0672749055386601,
      "grad_norm": 0.43821072578430176,
      "learning_rate": 8.968109864194715e-06,
      "loss": 0.4835,
      "step": 34743
    },
    {
      "epoch": 1.0673056246736092,
      "grad_norm": 0.38133031129837036,
      "learning_rate": 8.967629167911252e-06,
      "loss": 0.5203,
      "step": 34744
    },
    {
      "epoch": 1.0673363438085584,
      "grad_norm": 0.37629973888397217,
      "learning_rate": 8.967148474038967e-06,
      "loss": 0.4796,
      "step": 34745
    },
    {
      "epoch": 1.0673670629435075,
      "grad_norm": 0.4145251512527466,
      "learning_rate": 8.966667782578976e-06,
      "loss": 0.5026,
      "step": 34746
    },
    {
      "epoch": 1.0673977820784566,
      "grad_norm": 0.4312696158885956,
      "learning_rate": 8.966187093532407e-06,
      "loss": 0.5611,
      "step": 34747
    },
    {
      "epoch": 1.067428501213406,
      "grad_norm": 0.40975791215896606,
      "learning_rate": 8.965706406900377e-06,
      "loss": 0.5574,
      "step": 34748
    },
    {
      "epoch": 1.067459220348355,
      "grad_norm": 0.36516374349594116,
      "learning_rate": 8.965225722684018e-06,
      "loss": 0.4614,
      "step": 34749
    },
    {
      "epoch": 1.0674899394833042,
      "grad_norm": 0.35657328367233276,
      "learning_rate": 8.964745040884438e-06,
      "loss": 0.4498,
      "step": 34750
    },
    {
      "epoch": 1.0675206586182533,
      "grad_norm": 0.3687759041786194,
      "learning_rate": 8.964264361502777e-06,
      "loss": 0.4823,
      "step": 34751
    },
    {
      "epoch": 1.0675513777532024,
      "grad_norm": 0.4030207097530365,
      "learning_rate": 8.963783684540141e-06,
      "loss": 0.4308,
      "step": 34752
    },
    {
      "epoch": 1.0675820968881515,
      "grad_norm": 0.396424263715744,
      "learning_rate": 8.963303009997666e-06,
      "loss": 0.4907,
      "step": 34753
    },
    {
      "epoch": 1.0676128160231009,
      "grad_norm": 0.3699718415737152,
      "learning_rate": 8.962822337876467e-06,
      "loss": 0.4682,
      "step": 34754
    },
    {
      "epoch": 1.06764353515805,
      "grad_norm": 0.35223984718322754,
      "learning_rate": 8.96234166817767e-06,
      "loss": 0.5053,
      "step": 34755
    },
    {
      "epoch": 1.0676742542929991,
      "grad_norm": 0.3854721188545227,
      "learning_rate": 8.961861000902395e-06,
      "loss": 0.4835,
      "step": 34756
    },
    {
      "epoch": 1.0677049734279482,
      "grad_norm": 0.37235796451568604,
      "learning_rate": 8.961380336051767e-06,
      "loss": 0.5029,
      "step": 34757
    },
    {
      "epoch": 1.0677356925628974,
      "grad_norm": 0.3565496504306793,
      "learning_rate": 8.960899673626909e-06,
      "loss": 0.5002,
      "step": 34758
    },
    {
      "epoch": 1.0677664116978467,
      "grad_norm": 0.3835023045539856,
      "learning_rate": 8.960419013628936e-06,
      "loss": 0.4461,
      "step": 34759
    },
    {
      "epoch": 1.0677971308327958,
      "grad_norm": 0.34158065915107727,
      "learning_rate": 8.959938356058986e-06,
      "loss": 0.4522,
      "step": 34760
    },
    {
      "epoch": 1.067827849967745,
      "grad_norm": 0.3916434645652771,
      "learning_rate": 8.959457700918168e-06,
      "loss": 0.4204,
      "step": 34761
    },
    {
      "epoch": 1.067858569102694,
      "grad_norm": 0.38265031576156616,
      "learning_rate": 8.958977048207612e-06,
      "loss": 0.5077,
      "step": 34762
    },
    {
      "epoch": 1.0678892882376432,
      "grad_norm": 0.42064473032951355,
      "learning_rate": 8.958496397928433e-06,
      "loss": 0.5939,
      "step": 34763
    },
    {
      "epoch": 1.0679200073725923,
      "grad_norm": 0.4249926507472992,
      "learning_rate": 8.958015750081762e-06,
      "loss": 0.4599,
      "step": 34764
    },
    {
      "epoch": 1.0679507265075416,
      "grad_norm": 0.42494305968284607,
      "learning_rate": 8.957535104668716e-06,
      "loss": 0.4812,
      "step": 34765
    },
    {
      "epoch": 1.0679814456424908,
      "grad_norm": 0.3486521542072296,
      "learning_rate": 8.957054461690423e-06,
      "loss": 0.4958,
      "step": 34766
    },
    {
      "epoch": 1.0680121647774399,
      "grad_norm": 0.39574846625328064,
      "learning_rate": 8.956573821147998e-06,
      "loss": 0.4567,
      "step": 34767
    },
    {
      "epoch": 1.068042883912389,
      "grad_norm": 0.39366382360458374,
      "learning_rate": 8.95609318304257e-06,
      "loss": 0.5235,
      "step": 34768
    },
    {
      "epoch": 1.0680736030473381,
      "grad_norm": 0.3534010946750641,
      "learning_rate": 8.955612547375258e-06,
      "loss": 0.5223,
      "step": 34769
    },
    {
      "epoch": 1.0681043221822875,
      "grad_norm": 0.3818601965904236,
      "learning_rate": 8.955131914147188e-06,
      "loss": 0.4741,
      "step": 34770
    },
    {
      "epoch": 1.0681350413172366,
      "grad_norm": 0.42256659269332886,
      "learning_rate": 8.954651283359479e-06,
      "loss": 0.6147,
      "step": 34771
    },
    {
      "epoch": 1.0681657604521857,
      "grad_norm": 0.39101383090019226,
      "learning_rate": 8.954170655013254e-06,
      "loss": 0.5482,
      "step": 34772
    },
    {
      "epoch": 1.0681964795871348,
      "grad_norm": 0.4208555519580841,
      "learning_rate": 8.953690029109637e-06,
      "loss": 0.5793,
      "step": 34773
    },
    {
      "epoch": 1.068227198722084,
      "grad_norm": 0.37199729681015015,
      "learning_rate": 8.95320940564975e-06,
      "loss": 0.4033,
      "step": 34774
    },
    {
      "epoch": 1.068257917857033,
      "grad_norm": 0.3886241018772125,
      "learning_rate": 8.952728784634715e-06,
      "loss": 0.5375,
      "step": 34775
    },
    {
      "epoch": 1.0682886369919824,
      "grad_norm": 0.46572020649909973,
      "learning_rate": 8.952248166065656e-06,
      "loss": 0.5144,
      "step": 34776
    },
    {
      "epoch": 1.0683193561269315,
      "grad_norm": 0.3888372480869293,
      "learning_rate": 8.951767549943696e-06,
      "loss": 0.4991,
      "step": 34777
    },
    {
      "epoch": 1.0683500752618806,
      "grad_norm": 0.36119571328163147,
      "learning_rate": 8.951286936269952e-06,
      "loss": 0.5314,
      "step": 34778
    },
    {
      "epoch": 1.0683807943968298,
      "grad_norm": 0.4306562542915344,
      "learning_rate": 8.950806325045555e-06,
      "loss": 0.5262,
      "step": 34779
    },
    {
      "epoch": 1.0684115135317789,
      "grad_norm": 0.40095746517181396,
      "learning_rate": 8.95032571627162e-06,
      "loss": 0.4642,
      "step": 34780
    },
    {
      "epoch": 1.0684422326667282,
      "grad_norm": 0.4095107913017273,
      "learning_rate": 8.949845109949276e-06,
      "loss": 0.5045,
      "step": 34781
    },
    {
      "epoch": 1.0684729518016773,
      "grad_norm": 0.37577152252197266,
      "learning_rate": 8.949364506079639e-06,
      "loss": 0.5015,
      "step": 34782
    },
    {
      "epoch": 1.0685036709366265,
      "grad_norm": 0.3995058238506317,
      "learning_rate": 8.94888390466384e-06,
      "loss": 0.5074,
      "step": 34783
    },
    {
      "epoch": 1.0685343900715756,
      "grad_norm": 0.3870552182197571,
      "learning_rate": 8.948403305702987e-06,
      "loss": 0.4354,
      "step": 34784
    },
    {
      "epoch": 1.0685651092065247,
      "grad_norm": 0.43483543395996094,
      "learning_rate": 8.94792270919822e-06,
      "loss": 0.4909,
      "step": 34785
    },
    {
      "epoch": 1.0685958283414738,
      "grad_norm": 0.4062402546405792,
      "learning_rate": 8.947442115150644e-06,
      "loss": 0.5198,
      "step": 34786
    },
    {
      "epoch": 1.0686265474764232,
      "grad_norm": 0.40696534514427185,
      "learning_rate": 8.946961523561401e-06,
      "loss": 0.5024,
      "step": 34787
    },
    {
      "epoch": 1.0686572666113723,
      "grad_norm": 0.40357276797294617,
      "learning_rate": 8.946480934431594e-06,
      "loss": 0.5858,
      "step": 34788
    },
    {
      "epoch": 1.0686879857463214,
      "grad_norm": 0.4253063201904297,
      "learning_rate": 8.94600034776236e-06,
      "loss": 0.4702,
      "step": 34789
    },
    {
      "epoch": 1.0687187048812705,
      "grad_norm": 0.34346309304237366,
      "learning_rate": 8.945519763554812e-06,
      "loss": 0.5611,
      "step": 34790
    },
    {
      "epoch": 1.0687494240162196,
      "grad_norm": 0.4584558606147766,
      "learning_rate": 8.94503918181008e-06,
      "loss": 0.4829,
      "step": 34791
    },
    {
      "epoch": 1.0687801431511688,
      "grad_norm": 0.408781498670578,
      "learning_rate": 8.94455860252928e-06,
      "loss": 0.4945,
      "step": 34792
    },
    {
      "epoch": 1.068810862286118,
      "grad_norm": 0.36488044261932373,
      "learning_rate": 8.944078025713538e-06,
      "loss": 0.4918,
      "step": 34793
    },
    {
      "epoch": 1.0688415814210672,
      "grad_norm": 0.38450080156326294,
      "learning_rate": 8.943597451363975e-06,
      "loss": 0.4866,
      "step": 34794
    },
    {
      "epoch": 1.0688723005560163,
      "grad_norm": 0.39181289076805115,
      "learning_rate": 8.943116879481712e-06,
      "loss": 0.4422,
      "step": 34795
    },
    {
      "epoch": 1.0689030196909655,
      "grad_norm": 0.3629930317401886,
      "learning_rate": 8.942636310067877e-06,
      "loss": 0.4322,
      "step": 34796
    },
    {
      "epoch": 1.0689337388259146,
      "grad_norm": 0.3913276791572571,
      "learning_rate": 8.942155743123586e-06,
      "loss": 0.5325,
      "step": 34797
    },
    {
      "epoch": 1.068964457960864,
      "grad_norm": 0.3911421000957489,
      "learning_rate": 8.941675178649966e-06,
      "loss": 0.495,
      "step": 34798
    },
    {
      "epoch": 1.068995177095813,
      "grad_norm": 0.38613075017929077,
      "learning_rate": 8.941194616648136e-06,
      "loss": 0.5156,
      "step": 34799
    },
    {
      "epoch": 1.0690258962307622,
      "grad_norm": 0.4015994668006897,
      "learning_rate": 8.940714057119224e-06,
      "loss": 0.47,
      "step": 34800
    },
    {
      "epoch": 1.0690566153657113,
      "grad_norm": 0.37102046608924866,
      "learning_rate": 8.940233500064342e-06,
      "loss": 0.5503,
      "step": 34801
    },
    {
      "epoch": 1.0690873345006604,
      "grad_norm": 0.44810357689857483,
      "learning_rate": 8.939752945484623e-06,
      "loss": 0.5031,
      "step": 34802
    },
    {
      "epoch": 1.0691180536356095,
      "grad_norm": 0.3878161609172821,
      "learning_rate": 8.939272393381184e-06,
      "loss": 0.5337,
      "step": 34803
    },
    {
      "epoch": 1.0691487727705589,
      "grad_norm": 0.34939947724342346,
      "learning_rate": 8.938791843755149e-06,
      "loss": 0.5248,
      "step": 34804
    },
    {
      "epoch": 1.069179491905508,
      "grad_norm": 0.3975195288658142,
      "learning_rate": 8.938311296607639e-06,
      "loss": 0.5166,
      "step": 34805
    },
    {
      "epoch": 1.069210211040457,
      "grad_norm": 0.41083812713623047,
      "learning_rate": 8.937830751939777e-06,
      "loss": 0.4966,
      "step": 34806
    },
    {
      "epoch": 1.0692409301754062,
      "grad_norm": 0.4021827280521393,
      "learning_rate": 8.937350209752685e-06,
      "loss": 0.4986,
      "step": 34807
    },
    {
      "epoch": 1.0692716493103553,
      "grad_norm": 0.3859582245349884,
      "learning_rate": 8.936869670047487e-06,
      "loss": 0.4762,
      "step": 34808
    },
    {
      "epoch": 1.0693023684453045,
      "grad_norm": 0.4026171565055847,
      "learning_rate": 8.936389132825301e-06,
      "loss": 0.5538,
      "step": 34809
    },
    {
      "epoch": 1.0693330875802538,
      "grad_norm": 0.44860970973968506,
      "learning_rate": 8.935908598087257e-06,
      "loss": 0.5052,
      "step": 34810
    },
    {
      "epoch": 1.069363806715203,
      "grad_norm": 0.37941303849220276,
      "learning_rate": 8.93542806583447e-06,
      "loss": 0.4353,
      "step": 34811
    },
    {
      "epoch": 1.069394525850152,
      "grad_norm": 0.3856983184814453,
      "learning_rate": 8.934947536068069e-06,
      "loss": 0.5005,
      "step": 34812
    },
    {
      "epoch": 1.0694252449851012,
      "grad_norm": 0.39545777440071106,
      "learning_rate": 8.934467008789167e-06,
      "loss": 0.4475,
      "step": 34813
    },
    {
      "epoch": 1.0694559641200503,
      "grad_norm": 0.40961334109306335,
      "learning_rate": 8.933986483998893e-06,
      "loss": 0.6031,
      "step": 34814
    },
    {
      "epoch": 1.0694866832549996,
      "grad_norm": 0.35576415061950684,
      "learning_rate": 8.93350596169837e-06,
      "loss": 0.4583,
      "step": 34815
    },
    {
      "epoch": 1.0695174023899487,
      "grad_norm": 0.37115946412086487,
      "learning_rate": 8.933025441888716e-06,
      "loss": 0.508,
      "step": 34816
    },
    {
      "epoch": 1.0695481215248979,
      "grad_norm": 0.4460626542568207,
      "learning_rate": 8.93254492457106e-06,
      "loss": 0.5618,
      "step": 34817
    },
    {
      "epoch": 1.069578840659847,
      "grad_norm": 0.40103253722190857,
      "learning_rate": 8.932064409746513e-06,
      "loss": 0.4971,
      "step": 34818
    },
    {
      "epoch": 1.069609559794796,
      "grad_norm": 0.35054075717926025,
      "learning_rate": 8.931583897416211e-06,
      "loss": 0.4438,
      "step": 34819
    },
    {
      "epoch": 1.0696402789297452,
      "grad_norm": 0.4099445641040802,
      "learning_rate": 8.931103387581263e-06,
      "loss": 0.4302,
      "step": 34820
    },
    {
      "epoch": 1.0696709980646946,
      "grad_norm": 0.4121115207672119,
      "learning_rate": 8.930622880242804e-06,
      "loss": 0.5523,
      "step": 34821
    },
    {
      "epoch": 1.0697017171996437,
      "grad_norm": 0.3952104449272156,
      "learning_rate": 8.930142375401944e-06,
      "loss": 0.4674,
      "step": 34822
    },
    {
      "epoch": 1.0697324363345928,
      "grad_norm": 0.4424109160900116,
      "learning_rate": 8.929661873059817e-06,
      "loss": 0.505,
      "step": 34823
    },
    {
      "epoch": 1.069763155469542,
      "grad_norm": 0.40764135122299194,
      "learning_rate": 8.929181373217535e-06,
      "loss": 0.4841,
      "step": 34824
    },
    {
      "epoch": 1.069793874604491,
      "grad_norm": 0.4127988815307617,
      "learning_rate": 8.928700875876228e-06,
      "loss": 0.4693,
      "step": 34825
    },
    {
      "epoch": 1.0698245937394404,
      "grad_norm": 0.4067346453666687,
      "learning_rate": 8.928220381037012e-06,
      "loss": 0.4928,
      "step": 34826
    },
    {
      "epoch": 1.0698553128743895,
      "grad_norm": 0.3879227042198181,
      "learning_rate": 8.927739888701015e-06,
      "loss": 0.4922,
      "step": 34827
    },
    {
      "epoch": 1.0698860320093386,
      "grad_norm": 0.40862342715263367,
      "learning_rate": 8.927259398869353e-06,
      "loss": 0.5365,
      "step": 34828
    },
    {
      "epoch": 1.0699167511442877,
      "grad_norm": 0.3777029514312744,
      "learning_rate": 8.926778911543155e-06,
      "loss": 0.4643,
      "step": 34829
    },
    {
      "epoch": 1.0699474702792369,
      "grad_norm": 0.45547959208488464,
      "learning_rate": 8.926298426723538e-06,
      "loss": 0.5118,
      "step": 34830
    },
    {
      "epoch": 1.069978189414186,
      "grad_norm": 0.3851049840450287,
      "learning_rate": 8.925817944411624e-06,
      "loss": 0.4763,
      "step": 34831
    },
    {
      "epoch": 1.0700089085491353,
      "grad_norm": 0.5651910901069641,
      "learning_rate": 8.925337464608541e-06,
      "loss": 0.5022,
      "step": 34832
    },
    {
      "epoch": 1.0700396276840844,
      "grad_norm": 0.3839171230792999,
      "learning_rate": 8.924856987315404e-06,
      "loss": 0.4765,
      "step": 34833
    },
    {
      "epoch": 1.0700703468190336,
      "grad_norm": 0.3969389796257019,
      "learning_rate": 8.924376512533343e-06,
      "loss": 0.4547,
      "step": 34834
    },
    {
      "epoch": 1.0701010659539827,
      "grad_norm": 0.44279244542121887,
      "learning_rate": 8.92389604026347e-06,
      "loss": 0.4937,
      "step": 34835
    },
    {
      "epoch": 1.0701317850889318,
      "grad_norm": 0.4199814200401306,
      "learning_rate": 8.923415570506918e-06,
      "loss": 0.5315,
      "step": 34836
    },
    {
      "epoch": 1.0701625042238812,
      "grad_norm": 0.3952881693840027,
      "learning_rate": 8.922935103264802e-06,
      "loss": 0.559,
      "step": 34837
    },
    {
      "epoch": 1.0701932233588303,
      "grad_norm": 0.4009440839290619,
      "learning_rate": 8.922454638538248e-06,
      "loss": 0.5287,
      "step": 34838
    },
    {
      "epoch": 1.0702239424937794,
      "grad_norm": 0.39531445503234863,
      "learning_rate": 8.921974176328372e-06,
      "loss": 0.4313,
      "step": 34839
    },
    {
      "epoch": 1.0702546616287285,
      "grad_norm": 0.35497722029685974,
      "learning_rate": 8.921493716636306e-06,
      "loss": 0.5029,
      "step": 34840
    },
    {
      "epoch": 1.0702853807636776,
      "grad_norm": 0.3475484549999237,
      "learning_rate": 8.921013259463163e-06,
      "loss": 0.5137,
      "step": 34841
    },
    {
      "epoch": 1.0703160998986267,
      "grad_norm": 0.34481653571128845,
      "learning_rate": 8.920532804810072e-06,
      "loss": 0.4941,
      "step": 34842
    },
    {
      "epoch": 1.070346819033576,
      "grad_norm": 0.382455974817276,
      "learning_rate": 8.920052352678148e-06,
      "loss": 0.538,
      "step": 34843
    },
    {
      "epoch": 1.0703775381685252,
      "grad_norm": 0.39087310433387756,
      "learning_rate": 8.919571903068521e-06,
      "loss": 0.4522,
      "step": 34844
    },
    {
      "epoch": 1.0704082573034743,
      "grad_norm": 0.3630492091178894,
      "learning_rate": 8.919091455982307e-06,
      "loss": 0.491,
      "step": 34845
    },
    {
      "epoch": 1.0704389764384235,
      "grad_norm": 0.34441936016082764,
      "learning_rate": 8.918611011420633e-06,
      "loss": 0.4424,
      "step": 34846
    },
    {
      "epoch": 1.0704696955733726,
      "grad_norm": 1.0570759773254395,
      "learning_rate": 8.918130569384614e-06,
      "loss": 0.4683,
      "step": 34847
    },
    {
      "epoch": 1.070500414708322,
      "grad_norm": 0.38327425718307495,
      "learning_rate": 8.917650129875383e-06,
      "loss": 0.5339,
      "step": 34848
    },
    {
      "epoch": 1.070531133843271,
      "grad_norm": 0.38021907210350037,
      "learning_rate": 8.917169692894049e-06,
      "loss": 0.5538,
      "step": 34849
    },
    {
      "epoch": 1.0705618529782202,
      "grad_norm": 0.389951229095459,
      "learning_rate": 8.916689258441742e-06,
      "loss": 0.5303,
      "step": 34850
    },
    {
      "epoch": 1.0705925721131693,
      "grad_norm": 0.37902504205703735,
      "learning_rate": 8.916208826519586e-06,
      "loss": 0.5159,
      "step": 34851
    },
    {
      "epoch": 1.0706232912481184,
      "grad_norm": 0.35590657591819763,
      "learning_rate": 8.915728397128697e-06,
      "loss": 0.3953,
      "step": 34852
    },
    {
      "epoch": 1.0706540103830675,
      "grad_norm": 0.39474812150001526,
      "learning_rate": 8.915247970270204e-06,
      "loss": 0.5568,
      "step": 34853
    },
    {
      "epoch": 1.0706847295180169,
      "grad_norm": 0.36987045407295227,
      "learning_rate": 8.91476754594522e-06,
      "loss": 0.5163,
      "step": 34854
    },
    {
      "epoch": 1.070715448652966,
      "grad_norm": 0.413244366645813,
      "learning_rate": 8.914287124154879e-06,
      "loss": 0.4487,
      "step": 34855
    },
    {
      "epoch": 1.070746167787915,
      "grad_norm": 0.3791740834712982,
      "learning_rate": 8.91380670490029e-06,
      "loss": 0.4869,
      "step": 34856
    },
    {
      "epoch": 1.0707768869228642,
      "grad_norm": 0.41722455620765686,
      "learning_rate": 8.913326288182585e-06,
      "loss": 0.5448,
      "step": 34857
    },
    {
      "epoch": 1.0708076060578133,
      "grad_norm": 0.3858228623867035,
      "learning_rate": 8.91284587400288e-06,
      "loss": 0.5312,
      "step": 34858
    },
    {
      "epoch": 1.0708383251927627,
      "grad_norm": 0.4499853253364563,
      "learning_rate": 8.912365462362301e-06,
      "loss": 0.5465,
      "step": 34859
    },
    {
      "epoch": 1.0708690443277118,
      "grad_norm": 0.3780333399772644,
      "learning_rate": 8.911885053261968e-06,
      "loss": 0.4546,
      "step": 34860
    },
    {
      "epoch": 1.070899763462661,
      "grad_norm": 0.3972732126712799,
      "learning_rate": 8.911404646703004e-06,
      "loss": 0.5328,
      "step": 34861
    },
    {
      "epoch": 1.07093048259761,
      "grad_norm": 0.3776867687702179,
      "learning_rate": 8.910924242686527e-06,
      "loss": 0.5082,
      "step": 34862
    },
    {
      "epoch": 1.0709612017325592,
      "grad_norm": 0.38812580704689026,
      "learning_rate": 8.910443841213668e-06,
      "loss": 0.4738,
      "step": 34863
    },
    {
      "epoch": 1.0709919208675083,
      "grad_norm": 0.3970615565776825,
      "learning_rate": 8.909963442285538e-06,
      "loss": 0.4863,
      "step": 34864
    },
    {
      "epoch": 1.0710226400024576,
      "grad_norm": 0.35815784335136414,
      "learning_rate": 8.909483045903269e-06,
      "loss": 0.4365,
      "step": 34865
    },
    {
      "epoch": 1.0710533591374067,
      "grad_norm": 0.39760926365852356,
      "learning_rate": 8.909002652067975e-06,
      "loss": 0.4906,
      "step": 34866
    },
    {
      "epoch": 1.0710840782723559,
      "grad_norm": 0.4000842869281769,
      "learning_rate": 8.908522260780782e-06,
      "loss": 0.399,
      "step": 34867
    },
    {
      "epoch": 1.071114797407305,
      "grad_norm": 0.3870265781879425,
      "learning_rate": 8.908041872042814e-06,
      "loss": 0.442,
      "step": 34868
    },
    {
      "epoch": 1.071145516542254,
      "grad_norm": 0.39575493335723877,
      "learning_rate": 8.907561485855187e-06,
      "loss": 0.4446,
      "step": 34869
    },
    {
      "epoch": 1.0711762356772034,
      "grad_norm": 0.41615423560142517,
      "learning_rate": 8.907081102219031e-06,
      "loss": 0.5236,
      "step": 34870
    },
    {
      "epoch": 1.0712069548121526,
      "grad_norm": 0.3775666356086731,
      "learning_rate": 8.90660072113546e-06,
      "loss": 0.5076,
      "step": 34871
    },
    {
      "epoch": 1.0712376739471017,
      "grad_norm": 0.3730021119117737,
      "learning_rate": 8.9061203426056e-06,
      "loss": 0.4604,
      "step": 34872
    },
    {
      "epoch": 1.0712683930820508,
      "grad_norm": 0.3524581491947174,
      "learning_rate": 8.905639966630572e-06,
      "loss": 0.4103,
      "step": 34873
    },
    {
      "epoch": 1.071299112217,
      "grad_norm": 0.4441150426864624,
      "learning_rate": 8.9051595932115e-06,
      "loss": 0.492,
      "step": 34874
    },
    {
      "epoch": 1.071329831351949,
      "grad_norm": 0.3594617247581482,
      "learning_rate": 8.904679222349502e-06,
      "loss": 0.426,
      "step": 34875
    },
    {
      "epoch": 1.0713605504868984,
      "grad_norm": 0.40377095341682434,
      "learning_rate": 8.904198854045704e-06,
      "loss": 0.5198,
      "step": 34876
    },
    {
      "epoch": 1.0713912696218475,
      "grad_norm": 0.4187350571155548,
      "learning_rate": 8.903718488301225e-06,
      "loss": 0.5201,
      "step": 34877
    },
    {
      "epoch": 1.0714219887567966,
      "grad_norm": 0.39425817131996155,
      "learning_rate": 8.903238125117189e-06,
      "loss": 0.4714,
      "step": 34878
    },
    {
      "epoch": 1.0714527078917457,
      "grad_norm": 0.42136895656585693,
      "learning_rate": 8.902757764494716e-06,
      "loss": 0.4857,
      "step": 34879
    },
    {
      "epoch": 1.0714834270266949,
      "grad_norm": 0.44334954023361206,
      "learning_rate": 8.90227740643493e-06,
      "loss": 0.509,
      "step": 34880
    },
    {
      "epoch": 1.0715141461616442,
      "grad_norm": 0.3792163133621216,
      "learning_rate": 8.901797050938949e-06,
      "loss": 0.4331,
      "step": 34881
    },
    {
      "epoch": 1.0715448652965933,
      "grad_norm": 0.3962704539299011,
      "learning_rate": 8.901316698007903e-06,
      "loss": 0.5032,
      "step": 34882
    },
    {
      "epoch": 1.0715755844315424,
      "grad_norm": 0.45717501640319824,
      "learning_rate": 8.900836347642902e-06,
      "loss": 0.4816,
      "step": 34883
    },
    {
      "epoch": 1.0716063035664916,
      "grad_norm": 0.3818124830722809,
      "learning_rate": 8.900355999845081e-06,
      "loss": 0.5651,
      "step": 34884
    },
    {
      "epoch": 1.0716370227014407,
      "grad_norm": 0.3438481390476227,
      "learning_rate": 8.89987565461555e-06,
      "loss": 0.4224,
      "step": 34885
    },
    {
      "epoch": 1.0716677418363898,
      "grad_norm": 0.3931686580181122,
      "learning_rate": 8.899395311955437e-06,
      "loss": 0.5131,
      "step": 34886
    },
    {
      "epoch": 1.0716984609713391,
      "grad_norm": 0.3889324367046356,
      "learning_rate": 8.898914971865867e-06,
      "loss": 0.4895,
      "step": 34887
    },
    {
      "epoch": 1.0717291801062883,
      "grad_norm": 0.37645792961120605,
      "learning_rate": 8.898434634347954e-06,
      "loss": 0.5101,
      "step": 34888
    },
    {
      "epoch": 1.0717598992412374,
      "grad_norm": 0.44039398431777954,
      "learning_rate": 8.897954299402827e-06,
      "loss": 0.4417,
      "step": 34889
    },
    {
      "epoch": 1.0717906183761865,
      "grad_norm": 0.42308640480041504,
      "learning_rate": 8.8974739670316e-06,
      "loss": 0.5295,
      "step": 34890
    },
    {
      "epoch": 1.0718213375111356,
      "grad_norm": 0.3795901834964752,
      "learning_rate": 8.896993637235406e-06,
      "loss": 0.533,
      "step": 34891
    },
    {
      "epoch": 1.071852056646085,
      "grad_norm": 0.3670957386493683,
      "learning_rate": 8.896513310015354e-06,
      "loss": 0.4247,
      "step": 34892
    },
    {
      "epoch": 1.071882775781034,
      "grad_norm": 0.4506451189517975,
      "learning_rate": 8.896032985372577e-06,
      "loss": 0.5157,
      "step": 34893
    },
    {
      "epoch": 1.0719134949159832,
      "grad_norm": 0.3680041432380676,
      "learning_rate": 8.89555266330819e-06,
      "loss": 0.474,
      "step": 34894
    },
    {
      "epoch": 1.0719442140509323,
      "grad_norm": 0.42875587940216064,
      "learning_rate": 8.895072343823318e-06,
      "loss": 0.5011,
      "step": 34895
    },
    {
      "epoch": 1.0719749331858814,
      "grad_norm": 0.4937994182109833,
      "learning_rate": 8.89459202691908e-06,
      "loss": 0.4049,
      "step": 34896
    },
    {
      "epoch": 1.0720056523208306,
      "grad_norm": 0.4201846718788147,
      "learning_rate": 8.894111712596603e-06,
      "loss": 0.4995,
      "step": 34897
    },
    {
      "epoch": 1.07203637145578,
      "grad_norm": 0.4829796552658081,
      "learning_rate": 8.893631400857e-06,
      "loss": 0.4639,
      "step": 34898
    },
    {
      "epoch": 1.072067090590729,
      "grad_norm": 0.4206603467464447,
      "learning_rate": 8.893151091701404e-06,
      "loss": 0.4799,
      "step": 34899
    },
    {
      "epoch": 1.0720978097256781,
      "grad_norm": 0.3788292109966278,
      "learning_rate": 8.892670785130926e-06,
      "loss": 0.5387,
      "step": 34900
    },
    {
      "epoch": 1.0721285288606273,
      "grad_norm": 0.4722787141799927,
      "learning_rate": 8.892190481146695e-06,
      "loss": 0.4575,
      "step": 34901
    },
    {
      "epoch": 1.0721592479955764,
      "grad_norm": 0.476521372795105,
      "learning_rate": 8.891710179749828e-06,
      "loss": 0.4543,
      "step": 34902
    },
    {
      "epoch": 1.0721899671305255,
      "grad_norm": 0.39474397897720337,
      "learning_rate": 8.891229880941453e-06,
      "loss": 0.4907,
      "step": 34903
    },
    {
      "epoch": 1.0722206862654748,
      "grad_norm": 0.39876824617385864,
      "learning_rate": 8.890749584722685e-06,
      "loss": 0.5187,
      "step": 34904
    },
    {
      "epoch": 1.072251405400424,
      "grad_norm": 0.387472540140152,
      "learning_rate": 8.89026929109465e-06,
      "loss": 0.4702,
      "step": 34905
    },
    {
      "epoch": 1.072282124535373,
      "grad_norm": 0.3762294054031372,
      "learning_rate": 8.889789000058468e-06,
      "loss": 0.4247,
      "step": 34906
    },
    {
      "epoch": 1.0723128436703222,
      "grad_norm": 0.4132658839225769,
      "learning_rate": 8.889308711615262e-06,
      "loss": 0.5378,
      "step": 34907
    },
    {
      "epoch": 1.0723435628052713,
      "grad_norm": 0.37608030438423157,
      "learning_rate": 8.888828425766154e-06,
      "loss": 0.4992,
      "step": 34908
    },
    {
      "epoch": 1.0723742819402207,
      "grad_norm": 0.3581237494945526,
      "learning_rate": 8.888348142512262e-06,
      "loss": 0.4408,
      "step": 34909
    },
    {
      "epoch": 1.0724050010751698,
      "grad_norm": 0.4001695215702057,
      "learning_rate": 8.887867861854714e-06,
      "loss": 0.5318,
      "step": 34910
    },
    {
      "epoch": 1.072435720210119,
      "grad_norm": 0.40744078159332275,
      "learning_rate": 8.887387583794626e-06,
      "loss": 0.5307,
      "step": 34911
    },
    {
      "epoch": 1.072466439345068,
      "grad_norm": 0.46713101863861084,
      "learning_rate": 8.886907308333124e-06,
      "loss": 0.4769,
      "step": 34912
    },
    {
      "epoch": 1.0724971584800171,
      "grad_norm": 0.36973801255226135,
      "learning_rate": 8.886427035471325e-06,
      "loss": 0.4228,
      "step": 34913
    },
    {
      "epoch": 1.0725278776149663,
      "grad_norm": 0.3923894464969635,
      "learning_rate": 8.885946765210356e-06,
      "loss": 0.4975,
      "step": 34914
    },
    {
      "epoch": 1.0725585967499156,
      "grad_norm": 0.3964729607105255,
      "learning_rate": 8.885466497551334e-06,
      "loss": 0.4773,
      "step": 34915
    },
    {
      "epoch": 1.0725893158848647,
      "grad_norm": 0.38284432888031006,
      "learning_rate": 8.884986232495388e-06,
      "loss": 0.4745,
      "step": 34916
    },
    {
      "epoch": 1.0726200350198138,
      "grad_norm": 0.36519455909729004,
      "learning_rate": 8.884505970043627e-06,
      "loss": 0.4254,
      "step": 34917
    },
    {
      "epoch": 1.072650754154763,
      "grad_norm": 0.4344754219055176,
      "learning_rate": 8.884025710197185e-06,
      "loss": 0.4718,
      "step": 34918
    },
    {
      "epoch": 1.072681473289712,
      "grad_norm": 0.378472238779068,
      "learning_rate": 8.883545452957176e-06,
      "loss": 0.5321,
      "step": 34919
    },
    {
      "epoch": 1.0727121924246612,
      "grad_norm": 0.3842238187789917,
      "learning_rate": 8.88306519832473e-06,
      "loss": 0.4933,
      "step": 34920
    },
    {
      "epoch": 1.0727429115596105,
      "grad_norm": 0.41095593571662903,
      "learning_rate": 8.882584946300955e-06,
      "loss": 0.4994,
      "step": 34921
    },
    {
      "epoch": 1.0727736306945597,
      "grad_norm": 0.4011625349521637,
      "learning_rate": 8.882104696886984e-06,
      "loss": 0.541,
      "step": 34922
    },
    {
      "epoch": 1.0728043498295088,
      "grad_norm": 0.3644658923149109,
      "learning_rate": 8.88162445008394e-06,
      "loss": 0.4945,
      "step": 34923
    },
    {
      "epoch": 1.072835068964458,
      "grad_norm": 0.43927034735679626,
      "learning_rate": 8.881144205892934e-06,
      "loss": 0.5151,
      "step": 34924
    },
    {
      "epoch": 1.072865788099407,
      "grad_norm": 0.38328811526298523,
      "learning_rate": 8.880663964315101e-06,
      "loss": 0.6144,
      "step": 34925
    },
    {
      "epoch": 1.0728965072343564,
      "grad_norm": 0.41144365072250366,
      "learning_rate": 8.880183725351547e-06,
      "loss": 0.5559,
      "step": 34926
    },
    {
      "epoch": 1.0729272263693055,
      "grad_norm": 0.40204736590385437,
      "learning_rate": 8.87970348900341e-06,
      "loss": 0.5111,
      "step": 34927
    },
    {
      "epoch": 1.0729579455042546,
      "grad_norm": 0.393232524394989,
      "learning_rate": 8.879223255271799e-06,
      "loss": 0.4486,
      "step": 34928
    },
    {
      "epoch": 1.0729886646392037,
      "grad_norm": 0.39769071340560913,
      "learning_rate": 8.878743024157842e-06,
      "loss": 0.4394,
      "step": 34929
    },
    {
      "epoch": 1.0730193837741528,
      "grad_norm": 0.3798184394836426,
      "learning_rate": 8.878262795662658e-06,
      "loss": 0.4691,
      "step": 34930
    },
    {
      "epoch": 1.073050102909102,
      "grad_norm": 0.4171995520591736,
      "learning_rate": 8.87778256978737e-06,
      "loss": 0.5086,
      "step": 34931
    },
    {
      "epoch": 1.0730808220440513,
      "grad_norm": 0.42790094017982483,
      "learning_rate": 8.8773023465331e-06,
      "loss": 0.5068,
      "step": 34932
    },
    {
      "epoch": 1.0731115411790004,
      "grad_norm": 0.37691324949264526,
      "learning_rate": 8.876822125900968e-06,
      "loss": 0.4297,
      "step": 34933
    },
    {
      "epoch": 1.0731422603139495,
      "grad_norm": 0.371364027261734,
      "learning_rate": 8.876341907892096e-06,
      "loss": 0.5557,
      "step": 34934
    },
    {
      "epoch": 1.0731729794488987,
      "grad_norm": 0.5110998153686523,
      "learning_rate": 8.875861692507606e-06,
      "loss": 0.5062,
      "step": 34935
    },
    {
      "epoch": 1.0732036985838478,
      "grad_norm": 0.3534952998161316,
      "learning_rate": 8.875381479748619e-06,
      "loss": 0.4731,
      "step": 34936
    },
    {
      "epoch": 1.0732344177187971,
      "grad_norm": 0.3776421546936035,
      "learning_rate": 8.87490126961626e-06,
      "loss": 0.5842,
      "step": 34937
    },
    {
      "epoch": 1.0732651368537462,
      "grad_norm": 0.36666154861450195,
      "learning_rate": 8.874421062111644e-06,
      "loss": 0.4109,
      "step": 34938
    },
    {
      "epoch": 1.0732958559886954,
      "grad_norm": 0.385595440864563,
      "learning_rate": 8.873940857235899e-06,
      "loss": 0.5513,
      "step": 34939
    },
    {
      "epoch": 1.0733265751236445,
      "grad_norm": 0.4536202549934387,
      "learning_rate": 8.873460654990142e-06,
      "loss": 0.5142,
      "step": 34940
    },
    {
      "epoch": 1.0733572942585936,
      "grad_norm": 0.3771567642688751,
      "learning_rate": 8.872980455375495e-06,
      "loss": 0.5438,
      "step": 34941
    },
    {
      "epoch": 1.0733880133935427,
      "grad_norm": 0.38962045311927795,
      "learning_rate": 8.872500258393084e-06,
      "loss": 0.4956,
      "step": 34942
    },
    {
      "epoch": 1.073418732528492,
      "grad_norm": 0.39154595136642456,
      "learning_rate": 8.872020064044026e-06,
      "loss": 0.5063,
      "step": 34943
    },
    {
      "epoch": 1.0734494516634412,
      "grad_norm": 0.40490537881851196,
      "learning_rate": 8.871539872329444e-06,
      "loss": 0.5671,
      "step": 34944
    },
    {
      "epoch": 1.0734801707983903,
      "grad_norm": 0.3635438084602356,
      "learning_rate": 8.871059683250458e-06,
      "loss": 0.5391,
      "step": 34945
    },
    {
      "epoch": 1.0735108899333394,
      "grad_norm": 0.4104335606098175,
      "learning_rate": 8.870579496808195e-06,
      "loss": 0.4926,
      "step": 34946
    },
    {
      "epoch": 1.0735416090682885,
      "grad_norm": 0.3698731064796448,
      "learning_rate": 8.870099313003769e-06,
      "loss": 0.5021,
      "step": 34947
    },
    {
      "epoch": 1.073572328203238,
      "grad_norm": 0.38626986742019653,
      "learning_rate": 8.869619131838306e-06,
      "loss": 0.4489,
      "step": 34948
    },
    {
      "epoch": 1.073603047338187,
      "grad_norm": 0.3732716143131256,
      "learning_rate": 8.869138953312926e-06,
      "loss": 0.521,
      "step": 34949
    },
    {
      "epoch": 1.0736337664731361,
      "grad_norm": 0.3639442026615143,
      "learning_rate": 8.868658777428754e-06,
      "loss": 0.4591,
      "step": 34950
    },
    {
      "epoch": 1.0736644856080853,
      "grad_norm": 0.36017927527427673,
      "learning_rate": 8.868178604186903e-06,
      "loss": 0.4426,
      "step": 34951
    },
    {
      "epoch": 1.0736952047430344,
      "grad_norm": 0.3736017346382141,
      "learning_rate": 8.867698433588506e-06,
      "loss": 0.4635,
      "step": 34952
    },
    {
      "epoch": 1.0737259238779835,
      "grad_norm": 0.39511874318122864,
      "learning_rate": 8.867218265634672e-06,
      "loss": 0.4964,
      "step": 34953
    },
    {
      "epoch": 1.0737566430129328,
      "grad_norm": 0.3597133755683899,
      "learning_rate": 8.866738100326534e-06,
      "loss": 0.5368,
      "step": 34954
    },
    {
      "epoch": 1.073787362147882,
      "grad_norm": 0.4201827049255371,
      "learning_rate": 8.866257937665204e-06,
      "loss": 0.5053,
      "step": 34955
    },
    {
      "epoch": 1.073818081282831,
      "grad_norm": 0.3784991204738617,
      "learning_rate": 8.865777777651812e-06,
      "loss": 0.4989,
      "step": 34956
    },
    {
      "epoch": 1.0738488004177802,
      "grad_norm": 0.37981706857681274,
      "learning_rate": 8.865297620287474e-06,
      "loss": 0.5185,
      "step": 34957
    },
    {
      "epoch": 1.0738795195527293,
      "grad_norm": 0.3856654167175293,
      "learning_rate": 8.864817465573313e-06,
      "loss": 0.4356,
      "step": 34958
    },
    {
      "epoch": 1.0739102386876787,
      "grad_norm": 0.41482123732566833,
      "learning_rate": 8.864337313510447e-06,
      "loss": 0.5774,
      "step": 34959
    },
    {
      "epoch": 1.0739409578226278,
      "grad_norm": 0.607205867767334,
      "learning_rate": 8.8638571641e-06,
      "loss": 0.4657,
      "step": 34960
    },
    {
      "epoch": 1.073971676957577,
      "grad_norm": 0.3717655837535858,
      "learning_rate": 8.863377017343099e-06,
      "loss": 0.4874,
      "step": 34961
    },
    {
      "epoch": 1.074002396092526,
      "grad_norm": 0.35141897201538086,
      "learning_rate": 8.862896873240855e-06,
      "loss": 0.55,
      "step": 34962
    },
    {
      "epoch": 1.0740331152274751,
      "grad_norm": 0.37077587842941284,
      "learning_rate": 8.862416731794402e-06,
      "loss": 0.5186,
      "step": 34963
    },
    {
      "epoch": 1.0740638343624243,
      "grad_norm": 0.3906930983066559,
      "learning_rate": 8.861936593004847e-06,
      "loss": 0.4985,
      "step": 34964
    },
    {
      "epoch": 1.0740945534973736,
      "grad_norm": 0.3913589417934418,
      "learning_rate": 8.861456456873323e-06,
      "loss": 0.5522,
      "step": 34965
    },
    {
      "epoch": 1.0741252726323227,
      "grad_norm": 0.6226313710212708,
      "learning_rate": 8.860976323400943e-06,
      "loss": 0.4217,
      "step": 34966
    },
    {
      "epoch": 1.0741559917672718,
      "grad_norm": 0.373991459608078,
      "learning_rate": 8.860496192588836e-06,
      "loss": 0.5274,
      "step": 34967
    },
    {
      "epoch": 1.074186710902221,
      "grad_norm": 0.39648622274398804,
      "learning_rate": 8.860016064438116e-06,
      "loss": 0.4899,
      "step": 34968
    },
    {
      "epoch": 1.07421743003717,
      "grad_norm": 0.3673712909221649,
      "learning_rate": 8.859535938949913e-06,
      "loss": 0.3991,
      "step": 34969
    },
    {
      "epoch": 1.0742481491721194,
      "grad_norm": 0.41545939445495605,
      "learning_rate": 8.85905581612534e-06,
      "loss": 0.5021,
      "step": 34970
    },
    {
      "epoch": 1.0742788683070685,
      "grad_norm": 0.5480833053588867,
      "learning_rate": 8.858575695965524e-06,
      "loss": 0.426,
      "step": 34971
    },
    {
      "epoch": 1.0743095874420177,
      "grad_norm": 0.38076281547546387,
      "learning_rate": 8.858095578471582e-06,
      "loss": 0.5292,
      "step": 34972
    },
    {
      "epoch": 1.0743403065769668,
      "grad_norm": 0.4522625803947449,
      "learning_rate": 8.857615463644638e-06,
      "loss": 0.4936,
      "step": 34973
    },
    {
      "epoch": 1.074371025711916,
      "grad_norm": 0.39337101578712463,
      "learning_rate": 8.857135351485813e-06,
      "loss": 0.5316,
      "step": 34974
    },
    {
      "epoch": 1.074401744846865,
      "grad_norm": 0.40364083647727966,
      "learning_rate": 8.856655241996228e-06,
      "loss": 0.4929,
      "step": 34975
    },
    {
      "epoch": 1.0744324639818144,
      "grad_norm": 0.39904266595840454,
      "learning_rate": 8.856175135177005e-06,
      "loss": 0.4886,
      "step": 34976
    },
    {
      "epoch": 1.0744631831167635,
      "grad_norm": 0.41195863485336304,
      "learning_rate": 8.855695031029265e-06,
      "loss": 0.5528,
      "step": 34977
    },
    {
      "epoch": 1.0744939022517126,
      "grad_norm": 0.3656248450279236,
      "learning_rate": 8.855214929554129e-06,
      "loss": 0.4697,
      "step": 34978
    },
    {
      "epoch": 1.0745246213866617,
      "grad_norm": 0.3919376730918884,
      "learning_rate": 8.854734830752718e-06,
      "loss": 0.5094,
      "step": 34979
    },
    {
      "epoch": 1.0745553405216108,
      "grad_norm": 0.45043954253196716,
      "learning_rate": 8.854254734626156e-06,
      "loss": 0.3843,
      "step": 34980
    },
    {
      "epoch": 1.0745860596565602,
      "grad_norm": 0.4255034327507019,
      "learning_rate": 8.853774641175559e-06,
      "loss": 0.4798,
      "step": 34981
    },
    {
      "epoch": 1.0746167787915093,
      "grad_norm": 0.39987194538116455,
      "learning_rate": 8.853294550402052e-06,
      "loss": 0.5283,
      "step": 34982
    },
    {
      "epoch": 1.0746474979264584,
      "grad_norm": 0.36492884159088135,
      "learning_rate": 8.852814462306757e-06,
      "loss": 0.5267,
      "step": 34983
    },
    {
      "epoch": 1.0746782170614075,
      "grad_norm": 0.40838146209716797,
      "learning_rate": 8.852334376890794e-06,
      "loss": 0.5138,
      "step": 34984
    },
    {
      "epoch": 1.0747089361963567,
      "grad_norm": 0.7080197930335999,
      "learning_rate": 8.851854294155283e-06,
      "loss": 0.499,
      "step": 34985
    },
    {
      "epoch": 1.0747396553313058,
      "grad_norm": 0.3711550533771515,
      "learning_rate": 8.85137421410135e-06,
      "loss": 0.4394,
      "step": 34986
    },
    {
      "epoch": 1.0747703744662551,
      "grad_norm": 0.37385815382003784,
      "learning_rate": 8.850894136730105e-06,
      "loss": 0.5028,
      "step": 34987
    },
    {
      "epoch": 1.0748010936012042,
      "grad_norm": 0.39751237630844116,
      "learning_rate": 8.850414062042687e-06,
      "loss": 0.489,
      "step": 34988
    },
    {
      "epoch": 1.0748318127361534,
      "grad_norm": 0.35396867990493774,
      "learning_rate": 8.849933990040198e-06,
      "loss": 0.5281,
      "step": 34989
    },
    {
      "epoch": 1.0748625318711025,
      "grad_norm": 0.40294477343559265,
      "learning_rate": 8.849453920723776e-06,
      "loss": 0.454,
      "step": 34990
    },
    {
      "epoch": 1.0748932510060516,
      "grad_norm": 0.43844202160835266,
      "learning_rate": 8.84897385409453e-06,
      "loss": 0.5251,
      "step": 34991
    },
    {
      "epoch": 1.074923970141001,
      "grad_norm": 0.3786305785179138,
      "learning_rate": 8.848493790153588e-06,
      "loss": 0.4703,
      "step": 34992
    },
    {
      "epoch": 1.07495468927595,
      "grad_norm": 0.4163285493850708,
      "learning_rate": 8.848013728902068e-06,
      "loss": 0.5106,
      "step": 34993
    },
    {
      "epoch": 1.0749854084108992,
      "grad_norm": 0.436197429895401,
      "learning_rate": 8.847533670341093e-06,
      "loss": 0.462,
      "step": 34994
    },
    {
      "epoch": 1.0750161275458483,
      "grad_norm": 0.40550318360328674,
      "learning_rate": 8.847053614471783e-06,
      "loss": 0.4534,
      "step": 34995
    },
    {
      "epoch": 1.0750468466807974,
      "grad_norm": 0.374892920255661,
      "learning_rate": 8.846573561295258e-06,
      "loss": 0.4766,
      "step": 34996
    },
    {
      "epoch": 1.0750775658157465,
      "grad_norm": 0.37629130482673645,
      "learning_rate": 8.846093510812645e-06,
      "loss": 0.4693,
      "step": 34997
    },
    {
      "epoch": 1.0751082849506959,
      "grad_norm": 0.3556252717971802,
      "learning_rate": 8.84561346302506e-06,
      "loss": 0.4387,
      "step": 34998
    },
    {
      "epoch": 1.075139004085645,
      "grad_norm": 0.4184148907661438,
      "learning_rate": 8.845133417933625e-06,
      "loss": 0.4918,
      "step": 34999
    },
    {
      "epoch": 1.0751697232205941,
      "grad_norm": 0.39447978138923645,
      "learning_rate": 8.84465337553946e-06,
      "loss": 0.455,
      "step": 35000
    },
    {
      "epoch": 1.0752004423555432,
      "grad_norm": 0.5658600330352783,
      "learning_rate": 8.84417333584369e-06,
      "loss": 0.4801,
      "step": 35001
    },
    {
      "epoch": 1.0752311614904924,
      "grad_norm": 0.40192195773124695,
      "learning_rate": 8.843693298847432e-06,
      "loss": 0.4004,
      "step": 35002
    },
    {
      "epoch": 1.0752618806254417,
      "grad_norm": 0.40772294998168945,
      "learning_rate": 8.84321326455181e-06,
      "loss": 0.4829,
      "step": 35003
    },
    {
      "epoch": 1.0752925997603908,
      "grad_norm": 0.5280488729476929,
      "learning_rate": 8.842733232957945e-06,
      "loss": 0.5381,
      "step": 35004
    },
    {
      "epoch": 1.07532331889534,
      "grad_norm": 0.3944304883480072,
      "learning_rate": 8.842253204066956e-06,
      "loss": 0.4691,
      "step": 35005
    },
    {
      "epoch": 1.075354038030289,
      "grad_norm": 0.3866713345050812,
      "learning_rate": 8.841773177879965e-06,
      "loss": 0.4401,
      "step": 35006
    },
    {
      "epoch": 1.0753847571652382,
      "grad_norm": 0.4590199291706085,
      "learning_rate": 8.841293154398096e-06,
      "loss": 0.5483,
      "step": 35007
    },
    {
      "epoch": 1.0754154763001873,
      "grad_norm": 0.39793121814727783,
      "learning_rate": 8.840813133622465e-06,
      "loss": 0.5157,
      "step": 35008
    },
    {
      "epoch": 1.0754461954351366,
      "grad_norm": 0.34790530800819397,
      "learning_rate": 8.840333115554199e-06,
      "loss": 0.4352,
      "step": 35009
    },
    {
      "epoch": 1.0754769145700858,
      "grad_norm": 0.3938809037208557,
      "learning_rate": 8.839853100194414e-06,
      "loss": 0.5285,
      "step": 35010
    },
    {
      "epoch": 1.0755076337050349,
      "grad_norm": 0.4359607994556427,
      "learning_rate": 8.839373087544235e-06,
      "loss": 0.5223,
      "step": 35011
    },
    {
      "epoch": 1.075538352839984,
      "grad_norm": 0.3678448796272278,
      "learning_rate": 8.838893077604778e-06,
      "loss": 0.5163,
      "step": 35012
    },
    {
      "epoch": 1.0755690719749331,
      "grad_norm": 0.3734376132488251,
      "learning_rate": 8.838413070377168e-06,
      "loss": 0.5053,
      "step": 35013
    },
    {
      "epoch": 1.0755997911098822,
      "grad_norm": 0.39347726106643677,
      "learning_rate": 8.837933065862527e-06,
      "loss": 0.4803,
      "step": 35014
    },
    {
      "epoch": 1.0756305102448316,
      "grad_norm": 0.38157179951667786,
      "learning_rate": 8.837453064061972e-06,
      "loss": 0.4851,
      "step": 35015
    },
    {
      "epoch": 1.0756612293797807,
      "grad_norm": 0.44186681509017944,
      "learning_rate": 8.83697306497663e-06,
      "loss": 0.4862,
      "step": 35016
    },
    {
      "epoch": 1.0756919485147298,
      "grad_norm": 0.36326947808265686,
      "learning_rate": 8.836493068607616e-06,
      "loss": 0.4596,
      "step": 35017
    },
    {
      "epoch": 1.075722667649679,
      "grad_norm": 0.3809824585914612,
      "learning_rate": 8.836013074956055e-06,
      "loss": 0.5289,
      "step": 35018
    },
    {
      "epoch": 1.075753386784628,
      "grad_norm": 0.39502596855163574,
      "learning_rate": 8.835533084023065e-06,
      "loss": 0.5351,
      "step": 35019
    },
    {
      "epoch": 1.0757841059195774,
      "grad_norm": 0.7130744457244873,
      "learning_rate": 8.835053095809775e-06,
      "loss": 0.5,
      "step": 35020
    },
    {
      "epoch": 1.0758148250545265,
      "grad_norm": 0.367485910654068,
      "learning_rate": 8.834573110317291e-06,
      "loss": 0.4573,
      "step": 35021
    },
    {
      "epoch": 1.0758455441894756,
      "grad_norm": 0.3678930699825287,
      "learning_rate": 8.834093127546751e-06,
      "loss": 0.4541,
      "step": 35022
    },
    {
      "epoch": 1.0758762633244248,
      "grad_norm": 0.39162275195121765,
      "learning_rate": 8.83361314749926e-06,
      "loss": 0.5257,
      "step": 35023
    },
    {
      "epoch": 1.0759069824593739,
      "grad_norm": 0.43141499161720276,
      "learning_rate": 8.833133170175955e-06,
      "loss": 0.4959,
      "step": 35024
    },
    {
      "epoch": 1.075937701594323,
      "grad_norm": 0.39308732748031616,
      "learning_rate": 8.832653195577941e-06,
      "loss": 0.4275,
      "step": 35025
    },
    {
      "epoch": 1.0759684207292723,
      "grad_norm": 0.4340321719646454,
      "learning_rate": 8.832173223706356e-06,
      "loss": 0.5265,
      "step": 35026
    },
    {
      "epoch": 1.0759991398642215,
      "grad_norm": 0.4390796720981598,
      "learning_rate": 8.831693254562304e-06,
      "loss": 0.3921,
      "step": 35027
    },
    {
      "epoch": 1.0760298589991706,
      "grad_norm": 0.37811169028282166,
      "learning_rate": 8.831213288146919e-06,
      "loss": 0.4886,
      "step": 35028
    },
    {
      "epoch": 1.0760605781341197,
      "grad_norm": 0.3981475234031677,
      "learning_rate": 8.830733324461314e-06,
      "loss": 0.5231,
      "step": 35029
    },
    {
      "epoch": 1.0760912972690688,
      "grad_norm": 0.39993050694465637,
      "learning_rate": 8.830253363506614e-06,
      "loss": 0.5028,
      "step": 35030
    },
    {
      "epoch": 1.0761220164040182,
      "grad_norm": 0.43887919187545776,
      "learning_rate": 8.829773405283938e-06,
      "loss": 0.5444,
      "step": 35031
    },
    {
      "epoch": 1.0761527355389673,
      "grad_norm": 0.3890642523765564,
      "learning_rate": 8.829293449794407e-06,
      "loss": 0.433,
      "step": 35032
    },
    {
      "epoch": 1.0761834546739164,
      "grad_norm": 0.47758224606513977,
      "learning_rate": 8.828813497039147e-06,
      "loss": 0.4696,
      "step": 35033
    },
    {
      "epoch": 1.0762141738088655,
      "grad_norm": 0.38580039143562317,
      "learning_rate": 8.82833354701927e-06,
      "loss": 0.4454,
      "step": 35034
    },
    {
      "epoch": 1.0762448929438146,
      "grad_norm": 0.43302181363105774,
      "learning_rate": 8.827853599735905e-06,
      "loss": 0.5555,
      "step": 35035
    },
    {
      "epoch": 1.0762756120787638,
      "grad_norm": 0.39902782440185547,
      "learning_rate": 8.827373655190168e-06,
      "loss": 0.5266,
      "step": 35036
    },
    {
      "epoch": 1.076306331213713,
      "grad_norm": 0.38679060339927673,
      "learning_rate": 8.826893713383184e-06,
      "loss": 0.5445,
      "step": 35037
    },
    {
      "epoch": 1.0763370503486622,
      "grad_norm": 0.40541884303092957,
      "learning_rate": 8.826413774316071e-06,
      "loss": 0.5369,
      "step": 35038
    },
    {
      "epoch": 1.0763677694836113,
      "grad_norm": 0.3603004813194275,
      "learning_rate": 8.82593383798995e-06,
      "loss": 0.5406,
      "step": 35039
    },
    {
      "epoch": 1.0763984886185605,
      "grad_norm": 0.4126432240009308,
      "learning_rate": 8.825453904405941e-06,
      "loss": 0.4843,
      "step": 35040
    },
    {
      "epoch": 1.0764292077535096,
      "grad_norm": 0.40021929144859314,
      "learning_rate": 8.82497397356517e-06,
      "loss": 0.5001,
      "step": 35041
    },
    {
      "epoch": 1.0764599268884587,
      "grad_norm": 0.364172101020813,
      "learning_rate": 8.824494045468753e-06,
      "loss": 0.5127,
      "step": 35042
    },
    {
      "epoch": 1.076490646023408,
      "grad_norm": 0.39230918884277344,
      "learning_rate": 8.824014120117812e-06,
      "loss": 0.5426,
      "step": 35043
    },
    {
      "epoch": 1.0765213651583572,
      "grad_norm": 0.43843874335289,
      "learning_rate": 8.823534197513466e-06,
      "loss": 0.6063,
      "step": 35044
    },
    {
      "epoch": 1.0765520842933063,
      "grad_norm": 0.37640494108200073,
      "learning_rate": 8.82305427765684e-06,
      "loss": 0.4703,
      "step": 35045
    },
    {
      "epoch": 1.0765828034282554,
      "grad_norm": 0.40118783712387085,
      "learning_rate": 8.822574360549054e-06,
      "loss": 0.5117,
      "step": 35046
    },
    {
      "epoch": 1.0766135225632045,
      "grad_norm": 0.42662540078163147,
      "learning_rate": 8.822094446191225e-06,
      "loss": 0.452,
      "step": 35047
    },
    {
      "epoch": 1.0766442416981539,
      "grad_norm": 0.3437207043170929,
      "learning_rate": 8.821614534584479e-06,
      "loss": 0.4983,
      "step": 35048
    },
    {
      "epoch": 1.076674960833103,
      "grad_norm": 0.37805497646331787,
      "learning_rate": 8.821134625729937e-06,
      "loss": 0.5501,
      "step": 35049
    },
    {
      "epoch": 1.076705679968052,
      "grad_norm": 0.38357266783714294,
      "learning_rate": 8.82065471962871e-06,
      "loss": 0.4359,
      "step": 35050
    },
    {
      "epoch": 1.0767363991030012,
      "grad_norm": 0.412523090839386,
      "learning_rate": 8.82017481628193e-06,
      "loss": 0.4728,
      "step": 35051
    },
    {
      "epoch": 1.0767671182379503,
      "grad_norm": 0.3984787166118622,
      "learning_rate": 8.819694915690717e-06,
      "loss": 0.5302,
      "step": 35052
    },
    {
      "epoch": 1.0767978373728995,
      "grad_norm": 0.3847818374633789,
      "learning_rate": 8.819215017856184e-06,
      "loss": 0.4904,
      "step": 35053
    },
    {
      "epoch": 1.0768285565078488,
      "grad_norm": 0.3906286060810089,
      "learning_rate": 8.818735122779462e-06,
      "loss": 0.4151,
      "step": 35054
    },
    {
      "epoch": 1.076859275642798,
      "grad_norm": 0.4197559356689453,
      "learning_rate": 8.818255230461661e-06,
      "loss": 0.463,
      "step": 35055
    },
    {
      "epoch": 1.076889994777747,
      "grad_norm": 0.38297170400619507,
      "learning_rate": 8.817775340903914e-06,
      "loss": 0.5137,
      "step": 35056
    },
    {
      "epoch": 1.0769207139126962,
      "grad_norm": 0.4120982885360718,
      "learning_rate": 8.817295454107328e-06,
      "loss": 0.4458,
      "step": 35057
    },
    {
      "epoch": 1.0769514330476453,
      "grad_norm": 0.3709647059440613,
      "learning_rate": 8.81681557007304e-06,
      "loss": 0.4557,
      "step": 35058
    },
    {
      "epoch": 1.0769821521825946,
      "grad_norm": 0.3642008900642395,
      "learning_rate": 8.816335688802153e-06,
      "loss": 0.5043,
      "step": 35059
    },
    {
      "epoch": 1.0770128713175438,
      "grad_norm": 0.35225850343704224,
      "learning_rate": 8.815855810295804e-06,
      "loss": 0.4783,
      "step": 35060
    },
    {
      "epoch": 1.0770435904524929,
      "grad_norm": 0.3572183847427368,
      "learning_rate": 8.8153759345551e-06,
      "loss": 0.4824,
      "step": 35061
    },
    {
      "epoch": 1.077074309587442,
      "grad_norm": 0.33765658736228943,
      "learning_rate": 8.814896061581172e-06,
      "loss": 0.3847,
      "step": 35062
    },
    {
      "epoch": 1.0771050287223911,
      "grad_norm": 0.3661775290966034,
      "learning_rate": 8.814416191375136e-06,
      "loss": 0.4338,
      "step": 35063
    },
    {
      "epoch": 1.0771357478573402,
      "grad_norm": 0.4401364326477051,
      "learning_rate": 8.813936323938115e-06,
      "loss": 0.5304,
      "step": 35064
    },
    {
      "epoch": 1.0771664669922896,
      "grad_norm": 0.3644336462020874,
      "learning_rate": 8.813456459271226e-06,
      "loss": 0.4914,
      "step": 35065
    },
    {
      "epoch": 1.0771971861272387,
      "grad_norm": 0.6121870875358582,
      "learning_rate": 8.812976597375595e-06,
      "loss": 0.5643,
      "step": 35066
    },
    {
      "epoch": 1.0772279052621878,
      "grad_norm": 0.3701501488685608,
      "learning_rate": 8.812496738252338e-06,
      "loss": 0.5071,
      "step": 35067
    },
    {
      "epoch": 1.077258624397137,
      "grad_norm": 0.43852686882019043,
      "learning_rate": 8.812016881902577e-06,
      "loss": 0.5098,
      "step": 35068
    },
    {
      "epoch": 1.077289343532086,
      "grad_norm": 0.38711950182914734,
      "learning_rate": 8.811537028327436e-06,
      "loss": 0.4951,
      "step": 35069
    },
    {
      "epoch": 1.0773200626670354,
      "grad_norm": 0.35426226258277893,
      "learning_rate": 8.811057177528031e-06,
      "loss": 0.5983,
      "step": 35070
    },
    {
      "epoch": 1.0773507818019845,
      "grad_norm": 0.40308958292007446,
      "learning_rate": 8.810577329505488e-06,
      "loss": 0.5088,
      "step": 35071
    },
    {
      "epoch": 1.0773815009369336,
      "grad_norm": 0.3849542737007141,
      "learning_rate": 8.81009748426092e-06,
      "loss": 0.525,
      "step": 35072
    },
    {
      "epoch": 1.0774122200718828,
      "grad_norm": 0.41032204031944275,
      "learning_rate": 8.809617641795457e-06,
      "loss": 0.4789,
      "step": 35073
    },
    {
      "epoch": 1.0774429392068319,
      "grad_norm": 0.3933815360069275,
      "learning_rate": 8.809137802110214e-06,
      "loss": 0.5384,
      "step": 35074
    },
    {
      "epoch": 1.077473658341781,
      "grad_norm": 0.38149914145469666,
      "learning_rate": 8.808657965206313e-06,
      "loss": 0.5064,
      "step": 35075
    },
    {
      "epoch": 1.0775043774767303,
      "grad_norm": 0.4334541857242584,
      "learning_rate": 8.808178131084872e-06,
      "loss": 0.5107,
      "step": 35076
    },
    {
      "epoch": 1.0775350966116795,
      "grad_norm": 0.35143518447875977,
      "learning_rate": 8.807698299747018e-06,
      "loss": 0.4396,
      "step": 35077
    },
    {
      "epoch": 1.0775658157466286,
      "grad_norm": 0.382094144821167,
      "learning_rate": 8.807218471193865e-06,
      "loss": 0.4509,
      "step": 35078
    },
    {
      "epoch": 1.0775965348815777,
      "grad_norm": 0.39010655879974365,
      "learning_rate": 8.80673864542654e-06,
      "loss": 0.4812,
      "step": 35079
    },
    {
      "epoch": 1.0776272540165268,
      "grad_norm": 0.3849423825740814,
      "learning_rate": 8.806258822446155e-06,
      "loss": 0.5402,
      "step": 35080
    },
    {
      "epoch": 1.0776579731514762,
      "grad_norm": 0.4017280638217926,
      "learning_rate": 8.80577900225384e-06,
      "loss": 0.5755,
      "step": 35081
    },
    {
      "epoch": 1.0776886922864253,
      "grad_norm": 0.3713527321815491,
      "learning_rate": 8.80529918485071e-06,
      "loss": 0.5265,
      "step": 35082
    },
    {
      "epoch": 1.0777194114213744,
      "grad_norm": 0.44096580147743225,
      "learning_rate": 8.80481937023789e-06,
      "loss": 0.5358,
      "step": 35083
    },
    {
      "epoch": 1.0777501305563235,
      "grad_norm": 0.41275185346603394,
      "learning_rate": 8.804339558416492e-06,
      "loss": 0.5249,
      "step": 35084
    },
    {
      "epoch": 1.0777808496912726,
      "grad_norm": 0.3466639220714569,
      "learning_rate": 8.80385974938765e-06,
      "loss": 0.5041,
      "step": 35085
    },
    {
      "epoch": 1.0778115688262218,
      "grad_norm": 0.3778485655784607,
      "learning_rate": 8.80337994315247e-06,
      "loss": 0.4775,
      "step": 35086
    },
    {
      "epoch": 1.077842287961171,
      "grad_norm": 0.3707592189311981,
      "learning_rate": 8.802900139712081e-06,
      "loss": 0.5112,
      "step": 35087
    },
    {
      "epoch": 1.0778730070961202,
      "grad_norm": 0.35095375776290894,
      "learning_rate": 8.802420339067604e-06,
      "loss": 0.4533,
      "step": 35088
    },
    {
      "epoch": 1.0779037262310693,
      "grad_norm": 0.3784503936767578,
      "learning_rate": 8.801940541220157e-06,
      "loss": 0.3995,
      "step": 35089
    },
    {
      "epoch": 1.0779344453660185,
      "grad_norm": 0.3803808391094208,
      "learning_rate": 8.801460746170865e-06,
      "loss": 0.4988,
      "step": 35090
    },
    {
      "epoch": 1.0779651645009676,
      "grad_norm": 0.4034731686115265,
      "learning_rate": 8.80098095392084e-06,
      "loss": 0.5707,
      "step": 35091
    },
    {
      "epoch": 1.077995883635917,
      "grad_norm": 0.39221611618995667,
      "learning_rate": 8.800501164471214e-06,
      "loss": 0.5593,
      "step": 35092
    },
    {
      "epoch": 1.078026602770866,
      "grad_norm": 0.3894493579864502,
      "learning_rate": 8.800021377823093e-06,
      "loss": 0.4639,
      "step": 35093
    },
    {
      "epoch": 1.0780573219058152,
      "grad_norm": 1.071890115737915,
      "learning_rate": 8.799541593977614e-06,
      "loss": 0.4718,
      "step": 35094
    },
    {
      "epoch": 1.0780880410407643,
      "grad_norm": 0.4009661078453064,
      "learning_rate": 8.799061812935885e-06,
      "loss": 0.4998,
      "step": 35095
    },
    {
      "epoch": 1.0781187601757134,
      "grad_norm": 0.41442564129829407,
      "learning_rate": 8.798582034699033e-06,
      "loss": 0.4956,
      "step": 35096
    },
    {
      "epoch": 1.0781494793106625,
      "grad_norm": 0.4035271108150482,
      "learning_rate": 8.798102259268174e-06,
      "loss": 0.5195,
      "step": 35097
    },
    {
      "epoch": 1.0781801984456119,
      "grad_norm": 0.4095297157764435,
      "learning_rate": 8.797622486644435e-06,
      "loss": 0.4816,
      "step": 35098
    },
    {
      "epoch": 1.078210917580561,
      "grad_norm": 0.3652089238166809,
      "learning_rate": 8.797142716828929e-06,
      "loss": 0.4686,
      "step": 35099
    },
    {
      "epoch": 1.07824163671551,
      "grad_norm": 0.4112456142902374,
      "learning_rate": 8.796662949822782e-06,
      "loss": 0.5832,
      "step": 35100
    },
    {
      "epoch": 1.0782723558504592,
      "grad_norm": 0.4409281611442566,
      "learning_rate": 8.79618318562711e-06,
      "loss": 0.5036,
      "step": 35101
    },
    {
      "epoch": 1.0783030749854083,
      "grad_norm": 0.4767536520957947,
      "learning_rate": 8.795703424243041e-06,
      "loss": 0.5735,
      "step": 35102
    },
    {
      "epoch": 1.0783337941203577,
      "grad_norm": 0.3632979691028595,
      "learning_rate": 8.795223665671687e-06,
      "loss": 0.3891,
      "step": 35103
    },
    {
      "epoch": 1.0783645132553068,
      "grad_norm": 0.38313525915145874,
      "learning_rate": 8.794743909914174e-06,
      "loss": 0.4462,
      "step": 35104
    },
    {
      "epoch": 1.078395232390256,
      "grad_norm": 0.3979284465312958,
      "learning_rate": 8.794264156971619e-06,
      "loss": 0.5065,
      "step": 35105
    },
    {
      "epoch": 1.078425951525205,
      "grad_norm": 0.37177616357803345,
      "learning_rate": 8.793784406845144e-06,
      "loss": 0.4961,
      "step": 35106
    },
    {
      "epoch": 1.0784566706601542,
      "grad_norm": 0.35284423828125,
      "learning_rate": 8.793304659535872e-06,
      "loss": 0.4309,
      "step": 35107
    },
    {
      "epoch": 1.0784873897951033,
      "grad_norm": 0.39724501967430115,
      "learning_rate": 8.79282491504492e-06,
      "loss": 0.4358,
      "step": 35108
    },
    {
      "epoch": 1.0785181089300526,
      "grad_norm": 0.5390146970748901,
      "learning_rate": 8.792345173373411e-06,
      "loss": 0.5045,
      "step": 35109
    },
    {
      "epoch": 1.0785488280650017,
      "grad_norm": 0.36521705985069275,
      "learning_rate": 8.791865434522461e-06,
      "loss": 0.5242,
      "step": 35110
    },
    {
      "epoch": 1.0785795471999509,
      "grad_norm": 0.38568243384361267,
      "learning_rate": 8.791385698493198e-06,
      "loss": 0.4471,
      "step": 35111
    },
    {
      "epoch": 1.0786102663349,
      "grad_norm": 0.4190440773963928,
      "learning_rate": 8.790905965286735e-06,
      "loss": 0.5139,
      "step": 35112
    },
    {
      "epoch": 1.078640985469849,
      "grad_norm": 0.41498205065727234,
      "learning_rate": 8.790426234904197e-06,
      "loss": 0.5291,
      "step": 35113
    },
    {
      "epoch": 1.0786717046047984,
      "grad_norm": 0.3465074896812439,
      "learning_rate": 8.789946507346702e-06,
      "loss": 0.4974,
      "step": 35114
    },
    {
      "epoch": 1.0787024237397476,
      "grad_norm": 0.3905070424079895,
      "learning_rate": 8.789466782615373e-06,
      "loss": 0.55,
      "step": 35115
    },
    {
      "epoch": 1.0787331428746967,
      "grad_norm": 0.37453025579452515,
      "learning_rate": 8.788987060711328e-06,
      "loss": 0.4549,
      "step": 35116
    },
    {
      "epoch": 1.0787638620096458,
      "grad_norm": 0.3578416109085083,
      "learning_rate": 8.78850734163569e-06,
      "loss": 0.497,
      "step": 35117
    },
    {
      "epoch": 1.078794581144595,
      "grad_norm": 0.4423622190952301,
      "learning_rate": 8.788027625389575e-06,
      "loss": 0.5178,
      "step": 35118
    },
    {
      "epoch": 1.078825300279544,
      "grad_norm": 0.37981438636779785,
      "learning_rate": 8.78754791197411e-06,
      "loss": 0.4926,
      "step": 35119
    },
    {
      "epoch": 1.0788560194144934,
      "grad_norm": 0.3811779022216797,
      "learning_rate": 8.787068201390405e-06,
      "loss": 0.5464,
      "step": 35120
    },
    {
      "epoch": 1.0788867385494425,
      "grad_norm": 0.37884461879730225,
      "learning_rate": 8.786588493639594e-06,
      "loss": 0.4691,
      "step": 35121
    },
    {
      "epoch": 1.0789174576843916,
      "grad_norm": 0.39722540974617004,
      "learning_rate": 8.786108788722783e-06,
      "loss": 0.4945,
      "step": 35122
    },
    {
      "epoch": 1.0789481768193407,
      "grad_norm": 0.5324167609214783,
      "learning_rate": 8.785629086641103e-06,
      "loss": 0.4777,
      "step": 35123
    },
    {
      "epoch": 1.0789788959542899,
      "grad_norm": 0.3469242453575134,
      "learning_rate": 8.785149387395676e-06,
      "loss": 0.444,
      "step": 35124
    },
    {
      "epoch": 1.0790096150892392,
      "grad_norm": 0.41563284397125244,
      "learning_rate": 8.784669690987609e-06,
      "loss": 0.5549,
      "step": 35125
    },
    {
      "epoch": 1.0790403342241883,
      "grad_norm": 0.38894182443618774,
      "learning_rate": 8.784189997418038e-06,
      "loss": 0.4901,
      "step": 35126
    },
    {
      "epoch": 1.0790710533591374,
      "grad_norm": 0.3909252882003784,
      "learning_rate": 8.78371030668807e-06,
      "loss": 0.481,
      "step": 35127
    },
    {
      "epoch": 1.0791017724940866,
      "grad_norm": 0.3960227370262146,
      "learning_rate": 8.783230618798837e-06,
      "loss": 0.5395,
      "step": 35128
    },
    {
      "epoch": 1.0791324916290357,
      "grad_norm": 0.4029490649700165,
      "learning_rate": 8.782750933751448e-06,
      "loss": 0.4752,
      "step": 35129
    },
    {
      "epoch": 1.0791632107639848,
      "grad_norm": 0.41259458661079407,
      "learning_rate": 8.782271251547037e-06,
      "loss": 0.5939,
      "step": 35130
    },
    {
      "epoch": 1.0791939298989341,
      "grad_norm": 0.5093470811843872,
      "learning_rate": 8.78179157218671e-06,
      "loss": 0.4633,
      "step": 35131
    },
    {
      "epoch": 1.0792246490338833,
      "grad_norm": 0.39240437746047974,
      "learning_rate": 8.781311895671599e-06,
      "loss": 0.5308,
      "step": 35132
    },
    {
      "epoch": 1.0792553681688324,
      "grad_norm": 0.35336029529571533,
      "learning_rate": 8.780832222002814e-06,
      "loss": 0.5856,
      "step": 35133
    },
    {
      "epoch": 1.0792860873037815,
      "grad_norm": 0.47997304797172546,
      "learning_rate": 8.780352551181483e-06,
      "loss": 0.4898,
      "step": 35134
    },
    {
      "epoch": 1.0793168064387306,
      "grad_norm": 0.3997180163860321,
      "learning_rate": 8.779872883208724e-06,
      "loss": 0.5606,
      "step": 35135
    },
    {
      "epoch": 1.0793475255736797,
      "grad_norm": 0.42056339979171753,
      "learning_rate": 8.779393218085656e-06,
      "loss": 0.5633,
      "step": 35136
    },
    {
      "epoch": 1.079378244708629,
      "grad_norm": 0.35850077867507935,
      "learning_rate": 8.778913555813402e-06,
      "loss": 0.4863,
      "step": 35137
    },
    {
      "epoch": 1.0794089638435782,
      "grad_norm": 0.3741324841976166,
      "learning_rate": 8.77843389639308e-06,
      "loss": 0.5085,
      "step": 35138
    },
    {
      "epoch": 1.0794396829785273,
      "grad_norm": 0.36699026823043823,
      "learning_rate": 8.77795423982581e-06,
      "loss": 0.4721,
      "step": 35139
    },
    {
      "epoch": 1.0794704021134764,
      "grad_norm": 0.4155936539173126,
      "learning_rate": 8.777474586112714e-06,
      "loss": 0.5534,
      "step": 35140
    },
    {
      "epoch": 1.0795011212484256,
      "grad_norm": 0.3640156686306,
      "learning_rate": 8.776994935254911e-06,
      "loss": 0.548,
      "step": 35141
    },
    {
      "epoch": 1.079531840383375,
      "grad_norm": 0.3764994144439697,
      "learning_rate": 8.77651528725352e-06,
      "loss": 0.4781,
      "step": 35142
    },
    {
      "epoch": 1.079562559518324,
      "grad_norm": 0.378051221370697,
      "learning_rate": 8.776035642109668e-06,
      "loss": 0.4693,
      "step": 35143
    },
    {
      "epoch": 1.0795932786532731,
      "grad_norm": 0.46784138679504395,
      "learning_rate": 8.775555999824465e-06,
      "loss": 0.4617,
      "step": 35144
    },
    {
      "epoch": 1.0796239977882223,
      "grad_norm": 0.4835301637649536,
      "learning_rate": 8.77507636039904e-06,
      "loss": 0.4751,
      "step": 35145
    },
    {
      "epoch": 1.0796547169231714,
      "grad_norm": 0.39207208156585693,
      "learning_rate": 8.774596723834507e-06,
      "loss": 0.5106,
      "step": 35146
    },
    {
      "epoch": 1.0796854360581205,
      "grad_norm": 0.38909071683883667,
      "learning_rate": 8.774117090131991e-06,
      "loss": 0.4281,
      "step": 35147
    },
    {
      "epoch": 1.0797161551930698,
      "grad_norm": 0.4034678041934967,
      "learning_rate": 8.77363745929261e-06,
      "loss": 0.5619,
      "step": 35148
    },
    {
      "epoch": 1.079746874328019,
      "grad_norm": 0.4082513749599457,
      "learning_rate": 8.773157831317484e-06,
      "loss": 0.4457,
      "step": 35149
    },
    {
      "epoch": 1.079777593462968,
      "grad_norm": 0.41492360830307007,
      "learning_rate": 8.772678206207733e-06,
      "loss": 0.4951,
      "step": 35150
    },
    {
      "epoch": 1.0798083125979172,
      "grad_norm": 0.3682437539100647,
      "learning_rate": 8.77219858396448e-06,
      "loss": 0.4083,
      "step": 35151
    },
    {
      "epoch": 1.0798390317328663,
      "grad_norm": 0.37875428795814514,
      "learning_rate": 8.77171896458884e-06,
      "loss": 0.5192,
      "step": 35152
    },
    {
      "epoch": 1.0798697508678154,
      "grad_norm": 0.3977926969528198,
      "learning_rate": 8.77123934808194e-06,
      "loss": 0.5091,
      "step": 35153
    },
    {
      "epoch": 1.0799004700027648,
      "grad_norm": 0.438355416059494,
      "learning_rate": 8.77075973444489e-06,
      "loss": 0.5643,
      "step": 35154
    },
    {
      "epoch": 1.079931189137714,
      "grad_norm": 0.4379035234451294,
      "learning_rate": 8.770280123678823e-06,
      "loss": 0.5351,
      "step": 35155
    },
    {
      "epoch": 1.079961908272663,
      "grad_norm": 0.43899258971214294,
      "learning_rate": 8.769800515784847e-06,
      "loss": 0.489,
      "step": 35156
    },
    {
      "epoch": 1.0799926274076121,
      "grad_norm": 0.3820227384567261,
      "learning_rate": 8.769320910764095e-06,
      "loss": 0.4434,
      "step": 35157
    },
    {
      "epoch": 1.0800233465425613,
      "grad_norm": 0.4401674270629883,
      "learning_rate": 8.768841308617673e-06,
      "loss": 0.4943,
      "step": 35158
    },
    {
      "epoch": 1.0800540656775106,
      "grad_norm": 0.37529489398002625,
      "learning_rate": 8.768361709346709e-06,
      "loss": 0.5164,
      "step": 35159
    },
    {
      "epoch": 1.0800847848124597,
      "grad_norm": 0.3639287054538727,
      "learning_rate": 8.767882112952327e-06,
      "loss": 0.5156,
      "step": 35160
    },
    {
      "epoch": 1.0801155039474089,
      "grad_norm": 0.4773150086402893,
      "learning_rate": 8.767402519435635e-06,
      "loss": 0.544,
      "step": 35161
    },
    {
      "epoch": 1.080146223082358,
      "grad_norm": 0.39487865567207336,
      "learning_rate": 8.76692292879777e-06,
      "loss": 0.499,
      "step": 35162
    },
    {
      "epoch": 1.080176942217307,
      "grad_norm": 0.44280675053596497,
      "learning_rate": 8.766443341039833e-06,
      "loss": 0.5641,
      "step": 35163
    },
    {
      "epoch": 1.0802076613522562,
      "grad_norm": 0.36441922187805176,
      "learning_rate": 8.765963756162962e-06,
      "loss": 0.5003,
      "step": 35164
    },
    {
      "epoch": 1.0802383804872056,
      "grad_norm": 0.6899383664131165,
      "learning_rate": 8.765484174168264e-06,
      "loss": 0.5131,
      "step": 35165
    },
    {
      "epoch": 1.0802690996221547,
      "grad_norm": 0.4892163872718811,
      "learning_rate": 8.765004595056867e-06,
      "loss": 0.5255,
      "step": 35166
    },
    {
      "epoch": 1.0802998187571038,
      "grad_norm": 0.380890429019928,
      "learning_rate": 8.764525018829884e-06,
      "loss": 0.4733,
      "step": 35167
    },
    {
      "epoch": 1.080330537892053,
      "grad_norm": 0.380201131105423,
      "learning_rate": 8.764045445488441e-06,
      "loss": 0.5354,
      "step": 35168
    },
    {
      "epoch": 1.080361257027002,
      "grad_norm": 0.40221890807151794,
      "learning_rate": 8.763565875033655e-06,
      "loss": 0.5773,
      "step": 35169
    },
    {
      "epoch": 1.0803919761619514,
      "grad_norm": 0.3680659532546997,
      "learning_rate": 8.76308630746665e-06,
      "loss": 0.4636,
      "step": 35170
    },
    {
      "epoch": 1.0804226952969005,
      "grad_norm": 0.3856039345264435,
      "learning_rate": 8.762606742788543e-06,
      "loss": 0.4226,
      "step": 35171
    },
    {
      "epoch": 1.0804534144318496,
      "grad_norm": 0.39358845353126526,
      "learning_rate": 8.762127181000452e-06,
      "loss": 0.4835,
      "step": 35172
    },
    {
      "epoch": 1.0804841335667987,
      "grad_norm": 0.3748472332954407,
      "learning_rate": 8.7616476221035e-06,
      "loss": 0.4659,
      "step": 35173
    },
    {
      "epoch": 1.0805148527017479,
      "grad_norm": 0.3967859148979187,
      "learning_rate": 8.761168066098808e-06,
      "loss": 0.4866,
      "step": 35174
    },
    {
      "epoch": 1.080545571836697,
      "grad_norm": 0.41985753178596497,
      "learning_rate": 8.760688512987493e-06,
      "loss": 0.4399,
      "step": 35175
    },
    {
      "epoch": 1.0805762909716463,
      "grad_norm": 0.4086407721042633,
      "learning_rate": 8.760208962770677e-06,
      "loss": 0.4024,
      "step": 35176
    },
    {
      "epoch": 1.0806070101065954,
      "grad_norm": 0.4289815425872803,
      "learning_rate": 8.759729415449479e-06,
      "loss": 0.5112,
      "step": 35177
    },
    {
      "epoch": 1.0806377292415446,
      "grad_norm": 0.49205029010772705,
      "learning_rate": 8.75924987102502e-06,
      "loss": 0.4964,
      "step": 35178
    },
    {
      "epoch": 1.0806684483764937,
      "grad_norm": 0.3744967579841614,
      "learning_rate": 8.75877032949842e-06,
      "loss": 0.5618,
      "step": 35179
    },
    {
      "epoch": 1.0806991675114428,
      "grad_norm": 0.4792676568031311,
      "learning_rate": 8.758290790870798e-06,
      "loss": 0.491,
      "step": 35180
    },
    {
      "epoch": 1.0807298866463921,
      "grad_norm": 0.3554190695285797,
      "learning_rate": 8.757811255143276e-06,
      "loss": 0.4995,
      "step": 35181
    },
    {
      "epoch": 1.0807606057813413,
      "grad_norm": 0.37034013867378235,
      "learning_rate": 8.757331722316971e-06,
      "loss": 0.4471,
      "step": 35182
    },
    {
      "epoch": 1.0807913249162904,
      "grad_norm": 0.3710719645023346,
      "learning_rate": 8.756852192393007e-06,
      "loss": 0.5314,
      "step": 35183
    },
    {
      "epoch": 1.0808220440512395,
      "grad_norm": 0.4289921820163727,
      "learning_rate": 8.756372665372496e-06,
      "loss": 0.5664,
      "step": 35184
    },
    {
      "epoch": 1.0808527631861886,
      "grad_norm": 0.38207823038101196,
      "learning_rate": 8.755893141256569e-06,
      "loss": 0.5107,
      "step": 35185
    },
    {
      "epoch": 1.0808834823211377,
      "grad_norm": 0.39468124508857727,
      "learning_rate": 8.755413620046339e-06,
      "loss": 0.484,
      "step": 35186
    },
    {
      "epoch": 1.080914201456087,
      "grad_norm": 0.39934241771698,
      "learning_rate": 8.754934101742929e-06,
      "loss": 0.5186,
      "step": 35187
    },
    {
      "epoch": 1.0809449205910362,
      "grad_norm": 0.35525819659233093,
      "learning_rate": 8.754454586347451e-06,
      "loss": 0.4509,
      "step": 35188
    },
    {
      "epoch": 1.0809756397259853,
      "grad_norm": 0.3756202757358551,
      "learning_rate": 8.75397507386104e-06,
      "loss": 0.5043,
      "step": 35189
    },
    {
      "epoch": 1.0810063588609344,
      "grad_norm": 0.4293060302734375,
      "learning_rate": 8.7534955642848e-06,
      "loss": 0.4529,
      "step": 35190
    },
    {
      "epoch": 1.0810370779958836,
      "grad_norm": 0.34535500407218933,
      "learning_rate": 8.753016057619865e-06,
      "loss": 0.3857,
      "step": 35191
    },
    {
      "epoch": 1.081067797130833,
      "grad_norm": 0.42667055130004883,
      "learning_rate": 8.752536553867341e-06,
      "loss": 0.5406,
      "step": 35192
    },
    {
      "epoch": 1.081098516265782,
      "grad_norm": 0.40059706568717957,
      "learning_rate": 8.75205705302836e-06,
      "loss": 0.4895,
      "step": 35193
    },
    {
      "epoch": 1.0811292354007311,
      "grad_norm": 0.38756006956100464,
      "learning_rate": 8.751577555104034e-06,
      "loss": 0.4607,
      "step": 35194
    },
    {
      "epoch": 1.0811599545356803,
      "grad_norm": 0.4144650101661682,
      "learning_rate": 8.751098060095488e-06,
      "loss": 0.4685,
      "step": 35195
    },
    {
      "epoch": 1.0811906736706294,
      "grad_norm": 0.3928653299808502,
      "learning_rate": 8.750618568003838e-06,
      "loss": 0.4052,
      "step": 35196
    },
    {
      "epoch": 1.0812213928055785,
      "grad_norm": 0.3889720141887665,
      "learning_rate": 8.750139078830202e-06,
      "loss": 0.4573,
      "step": 35197
    },
    {
      "epoch": 1.0812521119405278,
      "grad_norm": 0.38654181361198425,
      "learning_rate": 8.749659592575712e-06,
      "loss": 0.4697,
      "step": 35198
    },
    {
      "epoch": 1.081282831075477,
      "grad_norm": 0.3976511061191559,
      "learning_rate": 8.749180109241471e-06,
      "loss": 0.4563,
      "step": 35199
    },
    {
      "epoch": 1.081313550210426,
      "grad_norm": 0.4126007854938507,
      "learning_rate": 8.748700628828615e-06,
      "loss": 0.5251,
      "step": 35200
    },
    {
      "epoch": 1.0813442693453752,
      "grad_norm": 0.4141683578491211,
      "learning_rate": 8.748221151338251e-06,
      "loss": 0.4357,
      "step": 35201
    },
    {
      "epoch": 1.0813749884803243,
      "grad_norm": 0.3653150796890259,
      "learning_rate": 8.747741676771507e-06,
      "loss": 0.5138,
      "step": 35202
    },
    {
      "epoch": 1.0814057076152737,
      "grad_norm": 0.37913671135902405,
      "learning_rate": 8.747262205129497e-06,
      "loss": 0.4445,
      "step": 35203
    },
    {
      "epoch": 1.0814364267502228,
      "grad_norm": 0.38683605194091797,
      "learning_rate": 8.746782736413344e-06,
      "loss": 0.517,
      "step": 35204
    },
    {
      "epoch": 1.081467145885172,
      "grad_norm": 0.3600003123283386,
      "learning_rate": 8.746303270624168e-06,
      "loss": 0.4486,
      "step": 35205
    },
    {
      "epoch": 1.081497865020121,
      "grad_norm": 0.38238266110420227,
      "learning_rate": 8.745823807763088e-06,
      "loss": 0.5169,
      "step": 35206
    },
    {
      "epoch": 1.0815285841550701,
      "grad_norm": 0.3865676820278168,
      "learning_rate": 8.745344347831223e-06,
      "loss": 0.4851,
      "step": 35207
    },
    {
      "epoch": 1.0815593032900193,
      "grad_norm": 0.362864226102829,
      "learning_rate": 8.744864890829697e-06,
      "loss": 0.4703,
      "step": 35208
    },
    {
      "epoch": 1.0815900224249686,
      "grad_norm": 0.40464693307876587,
      "learning_rate": 8.744385436759623e-06,
      "loss": 0.5464,
      "step": 35209
    },
    {
      "epoch": 1.0816207415599177,
      "grad_norm": 0.35782384872436523,
      "learning_rate": 8.743905985622128e-06,
      "loss": 0.4057,
      "step": 35210
    },
    {
      "epoch": 1.0816514606948668,
      "grad_norm": 0.38151949644088745,
      "learning_rate": 8.743426537418327e-06,
      "loss": 0.5318,
      "step": 35211
    },
    {
      "epoch": 1.081682179829816,
      "grad_norm": 0.3699563145637512,
      "learning_rate": 8.74294709214934e-06,
      "loss": 0.3993,
      "step": 35212
    },
    {
      "epoch": 1.081712898964765,
      "grad_norm": 0.44542622566223145,
      "learning_rate": 8.742467649816289e-06,
      "loss": 0.5414,
      "step": 35213
    },
    {
      "epoch": 1.0817436180997144,
      "grad_norm": 0.4459279775619507,
      "learning_rate": 8.741988210420292e-06,
      "loss": 0.4071,
      "step": 35214
    },
    {
      "epoch": 1.0817743372346635,
      "grad_norm": 0.3832571506500244,
      "learning_rate": 8.74150877396247e-06,
      "loss": 0.4454,
      "step": 35215
    },
    {
      "epoch": 1.0818050563696127,
      "grad_norm": 0.37562769651412964,
      "learning_rate": 8.74102934044394e-06,
      "loss": 0.5173,
      "step": 35216
    },
    {
      "epoch": 1.0818357755045618,
      "grad_norm": 0.4264739751815796,
      "learning_rate": 8.740549909865827e-06,
      "loss": 0.576,
      "step": 35217
    },
    {
      "epoch": 1.081866494639511,
      "grad_norm": 0.3894939124584198,
      "learning_rate": 8.740070482229246e-06,
      "loss": 0.5078,
      "step": 35218
    },
    {
      "epoch": 1.08189721377446,
      "grad_norm": 0.36341822147369385,
      "learning_rate": 8.73959105753532e-06,
      "loss": 0.4686,
      "step": 35219
    },
    {
      "epoch": 1.0819279329094094,
      "grad_norm": 0.4171496033668518,
      "learning_rate": 8.739111635785164e-06,
      "loss": 0.4325,
      "step": 35220
    },
    {
      "epoch": 1.0819586520443585,
      "grad_norm": 0.34990352392196655,
      "learning_rate": 8.738632216979904e-06,
      "loss": 0.4734,
      "step": 35221
    },
    {
      "epoch": 1.0819893711793076,
      "grad_norm": 0.37396156787872314,
      "learning_rate": 8.738152801120654e-06,
      "loss": 0.4428,
      "step": 35222
    },
    {
      "epoch": 1.0820200903142567,
      "grad_norm": 0.4075150489807129,
      "learning_rate": 8.737673388208541e-06,
      "loss": 0.4132,
      "step": 35223
    },
    {
      "epoch": 1.0820508094492058,
      "grad_norm": 0.458482563495636,
      "learning_rate": 8.737193978244674e-06,
      "loss": 0.4911,
      "step": 35224
    },
    {
      "epoch": 1.0820815285841552,
      "grad_norm": 0.3642597794532776,
      "learning_rate": 8.736714571230184e-06,
      "loss": 0.4978,
      "step": 35225
    },
    {
      "epoch": 1.0821122477191043,
      "grad_norm": 0.3777979016304016,
      "learning_rate": 8.736235167166179e-06,
      "loss": 0.4883,
      "step": 35226
    },
    {
      "epoch": 1.0821429668540534,
      "grad_norm": 0.37913191318511963,
      "learning_rate": 8.735755766053791e-06,
      "loss": 0.4923,
      "step": 35227
    },
    {
      "epoch": 1.0821736859890025,
      "grad_norm": 0.4094216525554657,
      "learning_rate": 8.735276367894131e-06,
      "loss": 0.5051,
      "step": 35228
    },
    {
      "epoch": 1.0822044051239517,
      "grad_norm": 0.38593265414237976,
      "learning_rate": 8.734796972688324e-06,
      "loss": 0.4291,
      "step": 35229
    },
    {
      "epoch": 1.0822351242589008,
      "grad_norm": 0.3777523338794708,
      "learning_rate": 8.734317580437483e-06,
      "loss": 0.5265,
      "step": 35230
    },
    {
      "epoch": 1.0822658433938501,
      "grad_norm": 0.4138195514678955,
      "learning_rate": 8.733838191142734e-06,
      "loss": 0.4601,
      "step": 35231
    },
    {
      "epoch": 1.0822965625287992,
      "grad_norm": 0.40414273738861084,
      "learning_rate": 8.733358804805192e-06,
      "loss": 0.526,
      "step": 35232
    },
    {
      "epoch": 1.0823272816637484,
      "grad_norm": 0.3968426585197449,
      "learning_rate": 8.732879421425978e-06,
      "loss": 0.4671,
      "step": 35233
    },
    {
      "epoch": 1.0823580007986975,
      "grad_norm": 0.4668234586715698,
      "learning_rate": 8.732400041006218e-06,
      "loss": 0.4552,
      "step": 35234
    },
    {
      "epoch": 1.0823887199336466,
      "grad_norm": 0.3984522521495819,
      "learning_rate": 8.731920663547022e-06,
      "loss": 0.4858,
      "step": 35235
    },
    {
      "epoch": 1.082419439068596,
      "grad_norm": 0.3928183913230896,
      "learning_rate": 8.731441289049517e-06,
      "loss": 0.6309,
      "step": 35236
    },
    {
      "epoch": 1.082450158203545,
      "grad_norm": 0.3986503481864929,
      "learning_rate": 8.730961917514816e-06,
      "loss": 0.4737,
      "step": 35237
    },
    {
      "epoch": 1.0824808773384942,
      "grad_norm": 0.5347297191619873,
      "learning_rate": 8.730482548944046e-06,
      "loss": 0.4691,
      "step": 35238
    },
    {
      "epoch": 1.0825115964734433,
      "grad_norm": 0.3865586817264557,
      "learning_rate": 8.730003183338319e-06,
      "loss": 0.4497,
      "step": 35239
    },
    {
      "epoch": 1.0825423156083924,
      "grad_norm": 0.5685057044029236,
      "learning_rate": 8.72952382069876e-06,
      "loss": 0.4827,
      "step": 35240
    },
    {
      "epoch": 1.0825730347433415,
      "grad_norm": 0.40331387519836426,
      "learning_rate": 8.729044461026485e-06,
      "loss": 0.5308,
      "step": 35241
    },
    {
      "epoch": 1.0826037538782909,
      "grad_norm": 0.3992629647254944,
      "learning_rate": 8.72856510432262e-06,
      "loss": 0.5435,
      "step": 35242
    },
    {
      "epoch": 1.08263447301324,
      "grad_norm": 0.3947942554950714,
      "learning_rate": 8.728085750588276e-06,
      "loss": 0.4921,
      "step": 35243
    },
    {
      "epoch": 1.0826651921481891,
      "grad_norm": 0.37451666593551636,
      "learning_rate": 8.727606399824578e-06,
      "loss": 0.4736,
      "step": 35244
    },
    {
      "epoch": 1.0826959112831382,
      "grad_norm": 0.377805233001709,
      "learning_rate": 8.727127052032643e-06,
      "loss": 0.5037,
      "step": 35245
    },
    {
      "epoch": 1.0827266304180874,
      "grad_norm": 0.3797258138656616,
      "learning_rate": 8.726647707213594e-06,
      "loss": 0.47,
      "step": 35246
    },
    {
      "epoch": 1.0827573495530365,
      "grad_norm": 0.41819775104522705,
      "learning_rate": 8.726168365368545e-06,
      "loss": 0.523,
      "step": 35247
    },
    {
      "epoch": 1.0827880686879858,
      "grad_norm": 0.41229936480522156,
      "learning_rate": 8.725689026498621e-06,
      "loss": 0.4604,
      "step": 35248
    },
    {
      "epoch": 1.082818787822935,
      "grad_norm": 0.39348381757736206,
      "learning_rate": 8.725209690604938e-06,
      "loss": 0.5257,
      "step": 35249
    },
    {
      "epoch": 1.082849506957884,
      "grad_norm": 0.4185068905353546,
      "learning_rate": 8.72473035768862e-06,
      "loss": 0.4967,
      "step": 35250
    },
    {
      "epoch": 1.0828802260928332,
      "grad_norm": 0.398149698972702,
      "learning_rate": 8.724251027750778e-06,
      "loss": 0.5599,
      "step": 35251
    },
    {
      "epoch": 1.0829109452277823,
      "grad_norm": 0.41737106442451477,
      "learning_rate": 8.723771700792538e-06,
      "loss": 0.5547,
      "step": 35252
    },
    {
      "epoch": 1.0829416643627316,
      "grad_norm": 0.3697816729545593,
      "learning_rate": 8.72329237681502e-06,
      "loss": 0.4696,
      "step": 35253
    },
    {
      "epoch": 1.0829723834976808,
      "grad_norm": 0.41704675555229187,
      "learning_rate": 8.722813055819342e-06,
      "loss": 0.5624,
      "step": 35254
    },
    {
      "epoch": 1.0830031026326299,
      "grad_norm": 0.36653101444244385,
      "learning_rate": 8.722333737806624e-06,
      "loss": 0.4777,
      "step": 35255
    },
    {
      "epoch": 1.083033821767579,
      "grad_norm": 0.3764247000217438,
      "learning_rate": 8.721854422777982e-06,
      "loss": 0.4189,
      "step": 35256
    },
    {
      "epoch": 1.0830645409025281,
      "grad_norm": 0.41285184025764465,
      "learning_rate": 8.721375110734544e-06,
      "loss": 0.5169,
      "step": 35257
    },
    {
      "epoch": 1.0830952600374772,
      "grad_norm": 0.4056461751461029,
      "learning_rate": 8.720895801677416e-06,
      "loss": 0.4697,
      "step": 35258
    },
    {
      "epoch": 1.0831259791724266,
      "grad_norm": 0.3958335816860199,
      "learning_rate": 8.720416495607733e-06,
      "loss": 0.5382,
      "step": 35259
    },
    {
      "epoch": 1.0831566983073757,
      "grad_norm": 0.42857110500335693,
      "learning_rate": 8.719937192526598e-06,
      "loss": 0.4895,
      "step": 35260
    },
    {
      "epoch": 1.0831874174423248,
      "grad_norm": 0.3805692791938782,
      "learning_rate": 8.719457892435147e-06,
      "loss": 0.5234,
      "step": 35261
    },
    {
      "epoch": 1.083218136577274,
      "grad_norm": 0.3884364068508148,
      "learning_rate": 8.718978595334487e-06,
      "loss": 0.4081,
      "step": 35262
    },
    {
      "epoch": 1.083248855712223,
      "grad_norm": 0.4191773235797882,
      "learning_rate": 8.718499301225745e-06,
      "loss": 0.5142,
      "step": 35263
    },
    {
      "epoch": 1.0832795748471722,
      "grad_norm": 0.4616118371486664,
      "learning_rate": 8.718020010110034e-06,
      "loss": 0.4458,
      "step": 35264
    },
    {
      "epoch": 1.0833102939821215,
      "grad_norm": 0.3904980421066284,
      "learning_rate": 8.71754072198848e-06,
      "loss": 0.5166,
      "step": 35265
    },
    {
      "epoch": 1.0833410131170707,
      "grad_norm": 0.4008583724498749,
      "learning_rate": 8.717061436862196e-06,
      "loss": 0.5216,
      "step": 35266
    },
    {
      "epoch": 1.0833717322520198,
      "grad_norm": 0.40516042709350586,
      "learning_rate": 8.716582154732307e-06,
      "loss": 0.4531,
      "step": 35267
    },
    {
      "epoch": 1.083402451386969,
      "grad_norm": 0.3892996907234192,
      "learning_rate": 8.71610287559993e-06,
      "loss": 0.422,
      "step": 35268
    },
    {
      "epoch": 1.083433170521918,
      "grad_norm": 0.4098338782787323,
      "learning_rate": 8.71562359946618e-06,
      "loss": 0.5957,
      "step": 35269
    },
    {
      "epoch": 1.0834638896568674,
      "grad_norm": 0.4193084239959717,
      "learning_rate": 8.715144326332187e-06,
      "loss": 0.4811,
      "step": 35270
    },
    {
      "epoch": 1.0834946087918165,
      "grad_norm": 0.4011010527610779,
      "learning_rate": 8.71466505619906e-06,
      "loss": 0.534,
      "step": 35271
    },
    {
      "epoch": 1.0835253279267656,
      "grad_norm": 0.3740549087524414,
      "learning_rate": 8.714185789067926e-06,
      "loss": 0.527,
      "step": 35272
    },
    {
      "epoch": 1.0835560470617147,
      "grad_norm": 0.3792119324207306,
      "learning_rate": 8.713706524939896e-06,
      "loss": 0.5268,
      "step": 35273
    },
    {
      "epoch": 1.0835867661966638,
      "grad_norm": 0.3749108910560608,
      "learning_rate": 8.7132272638161e-06,
      "loss": 0.4712,
      "step": 35274
    },
    {
      "epoch": 1.083617485331613,
      "grad_norm": 0.3918917179107666,
      "learning_rate": 8.712748005697647e-06,
      "loss": 0.49,
      "step": 35275
    },
    {
      "epoch": 1.0836482044665623,
      "grad_norm": 0.38092511892318726,
      "learning_rate": 8.712268750585665e-06,
      "loss": 0.4597,
      "step": 35276
    },
    {
      "epoch": 1.0836789236015114,
      "grad_norm": 0.37847900390625,
      "learning_rate": 8.711789498481265e-06,
      "loss": 0.4788,
      "step": 35277
    },
    {
      "epoch": 1.0837096427364605,
      "grad_norm": 0.39658862352371216,
      "learning_rate": 8.711310249385575e-06,
      "loss": 0.4829,
      "step": 35278
    },
    {
      "epoch": 1.0837403618714097,
      "grad_norm": 0.40196841955184937,
      "learning_rate": 8.710831003299704e-06,
      "loss": 0.4702,
      "step": 35279
    },
    {
      "epoch": 1.0837710810063588,
      "grad_norm": 0.37070462107658386,
      "learning_rate": 8.710351760224782e-06,
      "loss": 0.4896,
      "step": 35280
    },
    {
      "epoch": 1.0838018001413081,
      "grad_norm": 0.3600454330444336,
      "learning_rate": 8.709872520161921e-06,
      "loss": 0.4328,
      "step": 35281
    },
    {
      "epoch": 1.0838325192762572,
      "grad_norm": 0.37760332226753235,
      "learning_rate": 8.709393283112246e-06,
      "loss": 0.5209,
      "step": 35282
    },
    {
      "epoch": 1.0838632384112064,
      "grad_norm": 0.4195184111595154,
      "learning_rate": 8.70891404907687e-06,
      "loss": 0.4859,
      "step": 35283
    },
    {
      "epoch": 1.0838939575461555,
      "grad_norm": 0.360542356967926,
      "learning_rate": 8.708434818056918e-06,
      "loss": 0.5558,
      "step": 35284
    },
    {
      "epoch": 1.0839246766811046,
      "grad_norm": 0.3877836763858795,
      "learning_rate": 8.707955590053504e-06,
      "loss": 0.5014,
      "step": 35285
    },
    {
      "epoch": 1.0839553958160537,
      "grad_norm": 0.40779009461402893,
      "learning_rate": 8.707476365067755e-06,
      "loss": 0.5115,
      "step": 35286
    },
    {
      "epoch": 1.083986114951003,
      "grad_norm": 0.3844108581542969,
      "learning_rate": 8.706997143100777e-06,
      "loss": 0.5558,
      "step": 35287
    },
    {
      "epoch": 1.0840168340859522,
      "grad_norm": 0.39907610416412354,
      "learning_rate": 8.706517924153702e-06,
      "loss": 0.5438,
      "step": 35288
    },
    {
      "epoch": 1.0840475532209013,
      "grad_norm": 0.3933716118335724,
      "learning_rate": 8.706038708227646e-06,
      "loss": 0.5158,
      "step": 35289
    },
    {
      "epoch": 1.0840782723558504,
      "grad_norm": 0.3871007263660431,
      "learning_rate": 8.705559495323724e-06,
      "loss": 0.4406,
      "step": 35290
    },
    {
      "epoch": 1.0841089914907995,
      "grad_norm": 0.356162965297699,
      "learning_rate": 8.705080285443062e-06,
      "loss": 0.5026,
      "step": 35291
    },
    {
      "epoch": 1.0841397106257489,
      "grad_norm": 0.45427629351615906,
      "learning_rate": 8.70460107858677e-06,
      "loss": 0.533,
      "step": 35292
    },
    {
      "epoch": 1.084170429760698,
      "grad_norm": 0.4313524663448334,
      "learning_rate": 8.70412187475598e-06,
      "loss": 0.5258,
      "step": 35293
    },
    {
      "epoch": 1.0842011488956471,
      "grad_norm": 0.5000015497207642,
      "learning_rate": 8.703642673951796e-06,
      "loss": 0.553,
      "step": 35294
    },
    {
      "epoch": 1.0842318680305962,
      "grad_norm": 0.3967672288417816,
      "learning_rate": 8.703163476175352e-06,
      "loss": 0.4794,
      "step": 35295
    },
    {
      "epoch": 1.0842625871655454,
      "grad_norm": 0.37970760464668274,
      "learning_rate": 8.702684281427754e-06,
      "loss": 0.4866,
      "step": 35296
    },
    {
      "epoch": 1.0842933063004945,
      "grad_norm": 0.4729689657688141,
      "learning_rate": 8.702205089710133e-06,
      "loss": 0.4965,
      "step": 35297
    },
    {
      "epoch": 1.0843240254354438,
      "grad_norm": 0.39094075560569763,
      "learning_rate": 8.7017259010236e-06,
      "loss": 0.4791,
      "step": 35298
    },
    {
      "epoch": 1.084354744570393,
      "grad_norm": 0.3967553973197937,
      "learning_rate": 8.701246715369278e-06,
      "loss": 0.5216,
      "step": 35299
    },
    {
      "epoch": 1.084385463705342,
      "grad_norm": 0.4042695164680481,
      "learning_rate": 8.700767532748283e-06,
      "loss": 0.5228,
      "step": 35300
    },
    {
      "epoch": 1.0844161828402912,
      "grad_norm": 0.5418195724487305,
      "learning_rate": 8.700288353161738e-06,
      "loss": 0.4232,
      "step": 35301
    },
    {
      "epoch": 1.0844469019752403,
      "grad_norm": 0.3716225028038025,
      "learning_rate": 8.699809176610758e-06,
      "loss": 0.4846,
      "step": 35302
    },
    {
      "epoch": 1.0844776211101896,
      "grad_norm": 0.41922926902770996,
      "learning_rate": 8.699330003096468e-06,
      "loss": 0.5015,
      "step": 35303
    },
    {
      "epoch": 1.0845083402451388,
      "grad_norm": 0.48808553814888,
      "learning_rate": 8.698850832619981e-06,
      "loss": 0.5172,
      "step": 35304
    },
    {
      "epoch": 1.0845390593800879,
      "grad_norm": 0.3927291929721832,
      "learning_rate": 8.698371665182417e-06,
      "loss": 0.5065,
      "step": 35305
    },
    {
      "epoch": 1.084569778515037,
      "grad_norm": 0.37029820680618286,
      "learning_rate": 8.697892500784901e-06,
      "loss": 0.4787,
      "step": 35306
    },
    {
      "epoch": 1.0846004976499861,
      "grad_norm": 0.4063304364681244,
      "learning_rate": 8.697413339428545e-06,
      "loss": 0.5125,
      "step": 35307
    },
    {
      "epoch": 1.0846312167849352,
      "grad_norm": 0.510894775390625,
      "learning_rate": 8.696934181114473e-06,
      "loss": 0.4558,
      "step": 35308
    },
    {
      "epoch": 1.0846619359198846,
      "grad_norm": 0.3989025354385376,
      "learning_rate": 8.696455025843803e-06,
      "loss": 0.5161,
      "step": 35309
    },
    {
      "epoch": 1.0846926550548337,
      "grad_norm": 0.3944162130355835,
      "learning_rate": 8.695975873617652e-06,
      "loss": 0.5126,
      "step": 35310
    },
    {
      "epoch": 1.0847233741897828,
      "grad_norm": 0.3889642059803009,
      "learning_rate": 8.69549672443714e-06,
      "loss": 0.4905,
      "step": 35311
    },
    {
      "epoch": 1.084754093324732,
      "grad_norm": 0.4287087917327881,
      "learning_rate": 8.695017578303387e-06,
      "loss": 0.4387,
      "step": 35312
    },
    {
      "epoch": 1.084784812459681,
      "grad_norm": 0.43590080738067627,
      "learning_rate": 8.69453843521751e-06,
      "loss": 0.507,
      "step": 35313
    },
    {
      "epoch": 1.0848155315946304,
      "grad_norm": 0.37936079502105713,
      "learning_rate": 8.694059295180633e-06,
      "loss": 0.4567,
      "step": 35314
    },
    {
      "epoch": 1.0848462507295795,
      "grad_norm": 0.4334239065647125,
      "learning_rate": 8.693580158193868e-06,
      "loss": 0.4799,
      "step": 35315
    },
    {
      "epoch": 1.0848769698645286,
      "grad_norm": 0.3416709303855896,
      "learning_rate": 8.69310102425834e-06,
      "loss": 0.4323,
      "step": 35316
    },
    {
      "epoch": 1.0849076889994778,
      "grad_norm": 0.36026257276535034,
      "learning_rate": 8.692621893375165e-06,
      "loss": 0.4472,
      "step": 35317
    },
    {
      "epoch": 1.0849384081344269,
      "grad_norm": 0.4456712305545807,
      "learning_rate": 8.692142765545463e-06,
      "loss": 0.4991,
      "step": 35318
    },
    {
      "epoch": 1.084969127269376,
      "grad_norm": 0.35516417026519775,
      "learning_rate": 8.691663640770354e-06,
      "loss": 0.4831,
      "step": 35319
    },
    {
      "epoch": 1.0849998464043253,
      "grad_norm": 0.43871116638183594,
      "learning_rate": 8.691184519050959e-06,
      "loss": 0.5353,
      "step": 35320
    },
    {
      "epoch": 1.0850305655392745,
      "grad_norm": 0.38542062044143677,
      "learning_rate": 8.690705400388386e-06,
      "loss": 0.524,
      "step": 35321
    },
    {
      "epoch": 1.0850612846742236,
      "grad_norm": 0.3998182713985443,
      "learning_rate": 8.69022628478377e-06,
      "loss": 0.559,
      "step": 35322
    },
    {
      "epoch": 1.0850920038091727,
      "grad_norm": 0.39488062262535095,
      "learning_rate": 8.689747172238215e-06,
      "loss": 0.5174,
      "step": 35323
    },
    {
      "epoch": 1.0851227229441218,
      "grad_norm": 0.3888096511363983,
      "learning_rate": 8.689268062752848e-06,
      "loss": 0.5002,
      "step": 35324
    },
    {
      "epoch": 1.0851534420790712,
      "grad_norm": 0.35592344403266907,
      "learning_rate": 8.68878895632879e-06,
      "loss": 0.4965,
      "step": 35325
    },
    {
      "epoch": 1.0851841612140203,
      "grad_norm": 0.39080727100372314,
      "learning_rate": 8.688309852967156e-06,
      "loss": 0.5416,
      "step": 35326
    },
    {
      "epoch": 1.0852148803489694,
      "grad_norm": 0.3718597888946533,
      "learning_rate": 8.68783075266907e-06,
      "loss": 0.459,
      "step": 35327
    },
    {
      "epoch": 1.0852455994839185,
      "grad_norm": 0.4198606610298157,
      "learning_rate": 8.687351655435638e-06,
      "loss": 0.4051,
      "step": 35328
    },
    {
      "epoch": 1.0852763186188676,
      "grad_norm": 0.418011337518692,
      "learning_rate": 8.686872561267997e-06,
      "loss": 0.5206,
      "step": 35329
    },
    {
      "epoch": 1.0853070377538168,
      "grad_norm": 0.37593796849250793,
      "learning_rate": 8.686393470167248e-06,
      "loss": 0.5258,
      "step": 35330
    },
    {
      "epoch": 1.085337756888766,
      "grad_norm": 0.36944714188575745,
      "learning_rate": 8.685914382134527e-06,
      "loss": 0.5124,
      "step": 35331
    },
    {
      "epoch": 1.0853684760237152,
      "grad_norm": 0.3722938895225525,
      "learning_rate": 8.68543529717094e-06,
      "loss": 0.5169,
      "step": 35332
    },
    {
      "epoch": 1.0853991951586643,
      "grad_norm": 0.3773650825023651,
      "learning_rate": 8.684956215277612e-06,
      "loss": 0.5445,
      "step": 35333
    },
    {
      "epoch": 1.0854299142936135,
      "grad_norm": 0.3686072826385498,
      "learning_rate": 8.68447713645566e-06,
      "loss": 0.4818,
      "step": 35334
    },
    {
      "epoch": 1.0854606334285626,
      "grad_norm": 0.4111711084842682,
      "learning_rate": 8.683998060706204e-06,
      "loss": 0.4671,
      "step": 35335
    },
    {
      "epoch": 1.085491352563512,
      "grad_norm": 0.6018297076225281,
      "learning_rate": 8.683518988030362e-06,
      "loss": 0.4921,
      "step": 35336
    },
    {
      "epoch": 1.085522071698461,
      "grad_norm": 0.35726964473724365,
      "learning_rate": 8.683039918429254e-06,
      "loss": 0.4626,
      "step": 35337
    },
    {
      "epoch": 1.0855527908334102,
      "grad_norm": 0.39521780610084534,
      "learning_rate": 8.682560851903998e-06,
      "loss": 0.4544,
      "step": 35338
    },
    {
      "epoch": 1.0855835099683593,
      "grad_norm": 0.3754856288433075,
      "learning_rate": 8.682081788455714e-06,
      "loss": 0.4889,
      "step": 35339
    },
    {
      "epoch": 1.0856142291033084,
      "grad_norm": 0.37861740589141846,
      "learning_rate": 8.681602728085519e-06,
      "loss": 0.4801,
      "step": 35340
    },
    {
      "epoch": 1.0856449482382575,
      "grad_norm": 0.42463967204093933,
      "learning_rate": 8.681123670794534e-06,
      "loss": 0.5023,
      "step": 35341
    },
    {
      "epoch": 1.0856756673732069,
      "grad_norm": 0.3608461916446686,
      "learning_rate": 8.680644616583875e-06,
      "loss": 0.5375,
      "step": 35342
    },
    {
      "epoch": 1.085706386508156,
      "grad_norm": 0.39130303263664246,
      "learning_rate": 8.680165565454662e-06,
      "loss": 0.4518,
      "step": 35343
    },
    {
      "epoch": 1.085737105643105,
      "grad_norm": 0.43093934655189514,
      "learning_rate": 8.679686517408017e-06,
      "loss": 0.4767,
      "step": 35344
    },
    {
      "epoch": 1.0857678247780542,
      "grad_norm": 0.3978172838687897,
      "learning_rate": 8.679207472445053e-06,
      "loss": 0.519,
      "step": 35345
    },
    {
      "epoch": 1.0857985439130033,
      "grad_norm": 0.40143173933029175,
      "learning_rate": 8.678728430566897e-06,
      "loss": 0.5075,
      "step": 35346
    },
    {
      "epoch": 1.0858292630479527,
      "grad_norm": 0.37752464413642883,
      "learning_rate": 8.678249391774658e-06,
      "loss": 0.4727,
      "step": 35347
    },
    {
      "epoch": 1.0858599821829018,
      "grad_norm": 0.3785378634929657,
      "learning_rate": 8.677770356069464e-06,
      "loss": 0.5181,
      "step": 35348
    },
    {
      "epoch": 1.085890701317851,
      "grad_norm": 0.4074515700340271,
      "learning_rate": 8.677291323452427e-06,
      "loss": 0.4431,
      "step": 35349
    },
    {
      "epoch": 1.0859214204528,
      "grad_norm": 0.3568401634693146,
      "learning_rate": 8.67681229392467e-06,
      "loss": 0.4449,
      "step": 35350
    },
    {
      "epoch": 1.0859521395877492,
      "grad_norm": 0.40878722071647644,
      "learning_rate": 8.67633326748731e-06,
      "loss": 0.482,
      "step": 35351
    },
    {
      "epoch": 1.0859828587226983,
      "grad_norm": 0.35988849401474,
      "learning_rate": 8.675854244141465e-06,
      "loss": 0.4534,
      "step": 35352
    },
    {
      "epoch": 1.0860135778576476,
      "grad_norm": 0.3771413564682007,
      "learning_rate": 8.675375223888257e-06,
      "loss": 0.528,
      "step": 35353
    },
    {
      "epoch": 1.0860442969925967,
      "grad_norm": 0.4274681508541107,
      "learning_rate": 8.674896206728804e-06,
      "loss": 0.531,
      "step": 35354
    },
    {
      "epoch": 1.0860750161275459,
      "grad_norm": 0.3972030282020569,
      "learning_rate": 8.674417192664218e-06,
      "loss": 0.5347,
      "step": 35355
    },
    {
      "epoch": 1.086105735262495,
      "grad_norm": 0.3704386353492737,
      "learning_rate": 8.673938181695629e-06,
      "loss": 0.4656,
      "step": 35356
    },
    {
      "epoch": 1.086136454397444,
      "grad_norm": 0.3922633230686188,
      "learning_rate": 8.673459173824143e-06,
      "loss": 0.4955,
      "step": 35357
    },
    {
      "epoch": 1.0861671735323932,
      "grad_norm": 1.3463996648788452,
      "learning_rate": 8.672980169050893e-06,
      "loss": 0.4692,
      "step": 35358
    },
    {
      "epoch": 1.0861978926673426,
      "grad_norm": 0.36618727445602417,
      "learning_rate": 8.672501167376985e-06,
      "loss": 0.4972,
      "step": 35359
    },
    {
      "epoch": 1.0862286118022917,
      "grad_norm": 0.3708639442920685,
      "learning_rate": 8.672022168803544e-06,
      "loss": 0.5188,
      "step": 35360
    },
    {
      "epoch": 1.0862593309372408,
      "grad_norm": 0.44300052523612976,
      "learning_rate": 8.671543173331694e-06,
      "loss": 0.5402,
      "step": 35361
    },
    {
      "epoch": 1.08629005007219,
      "grad_norm": 0.3954002559185028,
      "learning_rate": 8.67106418096254e-06,
      "loss": 0.4592,
      "step": 35362
    },
    {
      "epoch": 1.086320769207139,
      "grad_norm": 0.4262317717075348,
      "learning_rate": 8.670585191697214e-06,
      "loss": 0.5475,
      "step": 35363
    },
    {
      "epoch": 1.0863514883420884,
      "grad_norm": 0.4028949439525604,
      "learning_rate": 8.670106205536824e-06,
      "loss": 0.5292,
      "step": 35364
    },
    {
      "epoch": 1.0863822074770375,
      "grad_norm": 0.40613406896591187,
      "learning_rate": 8.6696272224825e-06,
      "loss": 0.5465,
      "step": 35365
    },
    {
      "epoch": 1.0864129266119866,
      "grad_norm": 0.4355505704879761,
      "learning_rate": 8.669148242535348e-06,
      "loss": 0.5014,
      "step": 35366
    },
    {
      "epoch": 1.0864436457469357,
      "grad_norm": 0.3755452036857605,
      "learning_rate": 8.6686692656965e-06,
      "loss": 0.4767,
      "step": 35367
    },
    {
      "epoch": 1.0864743648818849,
      "grad_norm": 0.356317400932312,
      "learning_rate": 8.668190291967062e-06,
      "loss": 0.5071,
      "step": 35368
    },
    {
      "epoch": 1.086505084016834,
      "grad_norm": 0.5739595890045166,
      "learning_rate": 8.667711321348163e-06,
      "loss": 0.4953,
      "step": 35369
    },
    {
      "epoch": 1.0865358031517833,
      "grad_norm": 0.4523470103740692,
      "learning_rate": 8.667232353840914e-06,
      "loss": 0.4994,
      "step": 35370
    },
    {
      "epoch": 1.0865665222867325,
      "grad_norm": 0.38741183280944824,
      "learning_rate": 8.666753389446438e-06,
      "loss": 0.4253,
      "step": 35371
    },
    {
      "epoch": 1.0865972414216816,
      "grad_norm": 0.416674941778183,
      "learning_rate": 8.666274428165854e-06,
      "loss": 0.4933,
      "step": 35372
    },
    {
      "epoch": 1.0866279605566307,
      "grad_norm": 0.37404635548591614,
      "learning_rate": 8.665795470000277e-06,
      "loss": 0.5351,
      "step": 35373
    },
    {
      "epoch": 1.0866586796915798,
      "grad_norm": 0.3572320342063904,
      "learning_rate": 8.665316514950828e-06,
      "loss": 0.503,
      "step": 35374
    },
    {
      "epoch": 1.086689398826529,
      "grad_norm": 0.37852513790130615,
      "learning_rate": 8.664837563018628e-06,
      "loss": 0.5559,
      "step": 35375
    },
    {
      "epoch": 1.0867201179614783,
      "grad_norm": 0.417131632566452,
      "learning_rate": 8.66435861420479e-06,
      "loss": 0.5048,
      "step": 35376
    },
    {
      "epoch": 1.0867508370964274,
      "grad_norm": 0.3980288505554199,
      "learning_rate": 8.663879668510438e-06,
      "loss": 0.4572,
      "step": 35377
    },
    {
      "epoch": 1.0867815562313765,
      "grad_norm": 0.4168146848678589,
      "learning_rate": 8.663400725936686e-06,
      "loss": 0.5481,
      "step": 35378
    },
    {
      "epoch": 1.0868122753663256,
      "grad_norm": 0.3986838161945343,
      "learning_rate": 8.662921786484656e-06,
      "loss": 0.5146,
      "step": 35379
    },
    {
      "epoch": 1.0868429945012748,
      "grad_norm": 0.3986409604549408,
      "learning_rate": 8.662442850155467e-06,
      "loss": 0.5143,
      "step": 35380
    },
    {
      "epoch": 1.086873713636224,
      "grad_norm": 0.4172945022583008,
      "learning_rate": 8.661963916950233e-06,
      "loss": 0.5141,
      "step": 35381
    },
    {
      "epoch": 1.0869044327711732,
      "grad_norm": 0.3951832354068756,
      "learning_rate": 8.661484986870079e-06,
      "loss": 0.4708,
      "step": 35382
    },
    {
      "epoch": 1.0869351519061223,
      "grad_norm": 0.4147246778011322,
      "learning_rate": 8.661006059916118e-06,
      "loss": 0.5117,
      "step": 35383
    },
    {
      "epoch": 1.0869658710410715,
      "grad_norm": 0.35885897278785706,
      "learning_rate": 8.660527136089473e-06,
      "loss": 0.5525,
      "step": 35384
    },
    {
      "epoch": 1.0869965901760206,
      "grad_norm": 0.5505685806274414,
      "learning_rate": 8.660048215391259e-06,
      "loss": 0.4853,
      "step": 35385
    },
    {
      "epoch": 1.0870273093109697,
      "grad_norm": 0.3850502371788025,
      "learning_rate": 8.659569297822598e-06,
      "loss": 0.4781,
      "step": 35386
    },
    {
      "epoch": 1.087058028445919,
      "grad_norm": 0.37222447991371155,
      "learning_rate": 8.659090383384602e-06,
      "loss": 0.4437,
      "step": 35387
    },
    {
      "epoch": 1.0870887475808682,
      "grad_norm": 0.5330944061279297,
      "learning_rate": 8.6586114720784e-06,
      "loss": 0.4227,
      "step": 35388
    },
    {
      "epoch": 1.0871194667158173,
      "grad_norm": 0.39358094334602356,
      "learning_rate": 8.6581325639051e-06,
      "loss": 0.5522,
      "step": 35389
    },
    {
      "epoch": 1.0871501858507664,
      "grad_norm": 0.4139229357242584,
      "learning_rate": 8.65765365886583e-06,
      "loss": 0.5949,
      "step": 35390
    },
    {
      "epoch": 1.0871809049857155,
      "grad_norm": 0.3920552432537079,
      "learning_rate": 8.657174756961696e-06,
      "loss": 0.5178,
      "step": 35391
    },
    {
      "epoch": 1.0872116241206649,
      "grad_norm": 0.44464728236198425,
      "learning_rate": 8.656695858193832e-06,
      "loss": 0.5598,
      "step": 35392
    },
    {
      "epoch": 1.087242343255614,
      "grad_norm": 0.38101309537887573,
      "learning_rate": 8.656216962563343e-06,
      "loss": 0.437,
      "step": 35393
    },
    {
      "epoch": 1.087273062390563,
      "grad_norm": 0.3782411813735962,
      "learning_rate": 8.655738070071358e-06,
      "loss": 0.4446,
      "step": 35394
    },
    {
      "epoch": 1.0873037815255122,
      "grad_norm": 0.3655429184436798,
      "learning_rate": 8.655259180718985e-06,
      "loss": 0.4637,
      "step": 35395
    },
    {
      "epoch": 1.0873345006604613,
      "grad_norm": 0.3878093659877777,
      "learning_rate": 8.654780294507353e-06,
      "loss": 0.5013,
      "step": 35396
    },
    {
      "epoch": 1.0873652197954105,
      "grad_norm": 0.36093345284461975,
      "learning_rate": 8.654301411437573e-06,
      "loss": 0.4788,
      "step": 35397
    },
    {
      "epoch": 1.0873959389303598,
      "grad_norm": 0.3730415105819702,
      "learning_rate": 8.653822531510762e-06,
      "loss": 0.51,
      "step": 35398
    },
    {
      "epoch": 1.087426658065309,
      "grad_norm": 0.3936198949813843,
      "learning_rate": 8.65334365472805e-06,
      "loss": 0.462,
      "step": 35399
    },
    {
      "epoch": 1.087457377200258,
      "grad_norm": 0.36190903186798096,
      "learning_rate": 8.652864781090543e-06,
      "loss": 0.4543,
      "step": 35400
    },
    {
      "epoch": 1.0874880963352072,
      "grad_norm": 0.3887304961681366,
      "learning_rate": 8.65238591059937e-06,
      "loss": 0.511,
      "step": 35401
    },
    {
      "epoch": 1.0875188154701563,
      "grad_norm": 0.5923585891723633,
      "learning_rate": 8.651907043255638e-06,
      "loss": 0.5305,
      "step": 35402
    },
    {
      "epoch": 1.0875495346051056,
      "grad_norm": 0.33744165301322937,
      "learning_rate": 8.651428179060474e-06,
      "loss": 0.4535,
      "step": 35403
    },
    {
      "epoch": 1.0875802537400547,
      "grad_norm": 0.3914245069026947,
      "learning_rate": 8.650949318014992e-06,
      "loss": 0.5301,
      "step": 35404
    },
    {
      "epoch": 1.0876109728750039,
      "grad_norm": 0.41694751381874084,
      "learning_rate": 8.650470460120316e-06,
      "loss": 0.5155,
      "step": 35405
    },
    {
      "epoch": 1.087641692009953,
      "grad_norm": 0.3990491032600403,
      "learning_rate": 8.649991605377555e-06,
      "loss": 0.4992,
      "step": 35406
    },
    {
      "epoch": 1.087672411144902,
      "grad_norm": 0.37827643752098083,
      "learning_rate": 8.649512753787837e-06,
      "loss": 0.5431,
      "step": 35407
    },
    {
      "epoch": 1.0877031302798512,
      "grad_norm": 0.4393119215965271,
      "learning_rate": 8.649033905352274e-06,
      "loss": 0.4964,
      "step": 35408
    },
    {
      "epoch": 1.0877338494148006,
      "grad_norm": 0.3970404267311096,
      "learning_rate": 8.648555060071987e-06,
      "loss": 0.3961,
      "step": 35409
    },
    {
      "epoch": 1.0877645685497497,
      "grad_norm": 0.40265074372291565,
      "learning_rate": 8.648076217948095e-06,
      "loss": 0.5354,
      "step": 35410
    },
    {
      "epoch": 1.0877952876846988,
      "grad_norm": 0.416925847530365,
      "learning_rate": 8.647597378981716e-06,
      "loss": 0.5023,
      "step": 35411
    },
    {
      "epoch": 1.087826006819648,
      "grad_norm": 0.4344797134399414,
      "learning_rate": 8.647118543173965e-06,
      "loss": 0.4995,
      "step": 35412
    },
    {
      "epoch": 1.087856725954597,
      "grad_norm": 0.4016920030117035,
      "learning_rate": 8.646639710525966e-06,
      "loss": 0.4603,
      "step": 35413
    },
    {
      "epoch": 1.0878874450895464,
      "grad_norm": 0.36601272225379944,
      "learning_rate": 8.646160881038832e-06,
      "loss": 0.4561,
      "step": 35414
    },
    {
      "epoch": 1.0879181642244955,
      "grad_norm": 0.3751540184020996,
      "learning_rate": 8.645682054713685e-06,
      "loss": 0.5293,
      "step": 35415
    },
    {
      "epoch": 1.0879488833594446,
      "grad_norm": 1.6967517137527466,
      "learning_rate": 8.645203231551641e-06,
      "loss": 0.5162,
      "step": 35416
    },
    {
      "epoch": 1.0879796024943937,
      "grad_norm": 0.3940534293651581,
      "learning_rate": 8.644724411553822e-06,
      "loss": 0.4494,
      "step": 35417
    },
    {
      "epoch": 1.0880103216293429,
      "grad_norm": 0.5785499811172485,
      "learning_rate": 8.644245594721344e-06,
      "loss": 0.4808,
      "step": 35418
    },
    {
      "epoch": 1.088041040764292,
      "grad_norm": 0.4066708981990814,
      "learning_rate": 8.643766781055322e-06,
      "loss": 0.3943,
      "step": 35419
    },
    {
      "epoch": 1.0880717598992413,
      "grad_norm": 0.41721266508102417,
      "learning_rate": 8.64328797055688e-06,
      "loss": 0.442,
      "step": 35420
    },
    {
      "epoch": 1.0881024790341904,
      "grad_norm": 0.4060917794704437,
      "learning_rate": 8.642809163227131e-06,
      "loss": 0.5208,
      "step": 35421
    },
    {
      "epoch": 1.0881331981691396,
      "grad_norm": 0.4035612940788269,
      "learning_rate": 8.6423303590672e-06,
      "loss": 0.3925,
      "step": 35422
    },
    {
      "epoch": 1.0881639173040887,
      "grad_norm": 0.4359792470932007,
      "learning_rate": 8.641851558078196e-06,
      "loss": 0.5593,
      "step": 35423
    },
    {
      "epoch": 1.0881946364390378,
      "grad_norm": 0.36522021889686584,
      "learning_rate": 8.641372760261249e-06,
      "loss": 0.5493,
      "step": 35424
    },
    {
      "epoch": 1.0882253555739871,
      "grad_norm": 0.35036176443099976,
      "learning_rate": 8.640893965617465e-06,
      "loss": 0.525,
      "step": 35425
    },
    {
      "epoch": 1.0882560747089363,
      "grad_norm": 0.39373084902763367,
      "learning_rate": 8.640415174147974e-06,
      "loss": 0.543,
      "step": 35426
    },
    {
      "epoch": 1.0882867938438854,
      "grad_norm": 0.37167036533355713,
      "learning_rate": 8.63993638585388e-06,
      "loss": 0.5085,
      "step": 35427
    },
    {
      "epoch": 1.0883175129788345,
      "grad_norm": 0.38977086544036865,
      "learning_rate": 8.639457600736319e-06,
      "loss": 0.4663,
      "step": 35428
    },
    {
      "epoch": 1.0883482321137836,
      "grad_norm": 0.44919583201408386,
      "learning_rate": 8.63897881879639e-06,
      "loss": 0.534,
      "step": 35429
    },
    {
      "epoch": 1.0883789512487327,
      "grad_norm": 0.4035685062408447,
      "learning_rate": 8.638500040035231e-06,
      "loss": 0.5188,
      "step": 35430
    },
    {
      "epoch": 1.088409670383682,
      "grad_norm": 0.3886275887489319,
      "learning_rate": 8.638021264453944e-06,
      "loss": 0.5013,
      "step": 35431
    },
    {
      "epoch": 1.0884403895186312,
      "grad_norm": 0.3939111828804016,
      "learning_rate": 8.637542492053655e-06,
      "loss": 0.5437,
      "step": 35432
    },
    {
      "epoch": 1.0884711086535803,
      "grad_norm": 0.4057706892490387,
      "learning_rate": 8.637063722835479e-06,
      "loss": 0.5454,
      "step": 35433
    },
    {
      "epoch": 1.0885018277885294,
      "grad_norm": 0.4128466546535492,
      "learning_rate": 8.636584956800534e-06,
      "loss": 0.5004,
      "step": 35434
    },
    {
      "epoch": 1.0885325469234786,
      "grad_norm": 0.4183901250362396,
      "learning_rate": 8.636106193949947e-06,
      "loss": 0.5795,
      "step": 35435
    },
    {
      "epoch": 1.088563266058428,
      "grad_norm": 0.3638751804828644,
      "learning_rate": 8.635627434284822e-06,
      "loss": 0.4609,
      "step": 35436
    },
    {
      "epoch": 1.088593985193377,
      "grad_norm": 0.39705929160118103,
      "learning_rate": 8.63514867780629e-06,
      "loss": 0.464,
      "step": 35437
    },
    {
      "epoch": 1.0886247043283261,
      "grad_norm": 0.38784950971603394,
      "learning_rate": 8.634669924515461e-06,
      "loss": 0.5692,
      "step": 35438
    },
    {
      "epoch": 1.0886554234632753,
      "grad_norm": 0.36209118366241455,
      "learning_rate": 8.634191174413457e-06,
      "loss": 0.4914,
      "step": 35439
    },
    {
      "epoch": 1.0886861425982244,
      "grad_norm": 0.3878856301307678,
      "learning_rate": 8.633712427501396e-06,
      "loss": 0.5002,
      "step": 35440
    },
    {
      "epoch": 1.0887168617331735,
      "grad_norm": 0.48852109909057617,
      "learning_rate": 8.633233683780394e-06,
      "loss": 0.4838,
      "step": 35441
    },
    {
      "epoch": 1.0887475808681228,
      "grad_norm": 0.38530656695365906,
      "learning_rate": 8.632754943251567e-06,
      "loss": 0.5555,
      "step": 35442
    },
    {
      "epoch": 1.088778300003072,
      "grad_norm": 0.3867889642715454,
      "learning_rate": 8.632276205916038e-06,
      "loss": 0.4846,
      "step": 35443
    },
    {
      "epoch": 1.088809019138021,
      "grad_norm": 0.42422905564308167,
      "learning_rate": 8.631797471774925e-06,
      "loss": 0.5374,
      "step": 35444
    },
    {
      "epoch": 1.0888397382729702,
      "grad_norm": 0.465370774269104,
      "learning_rate": 8.631318740829345e-06,
      "loss": 0.4524,
      "step": 35445
    },
    {
      "epoch": 1.0888704574079193,
      "grad_norm": 0.4063605070114136,
      "learning_rate": 8.630840013080413e-06,
      "loss": 0.4509,
      "step": 35446
    },
    {
      "epoch": 1.0889011765428687,
      "grad_norm": 0.6935099959373474,
      "learning_rate": 8.630361288529252e-06,
      "loss": 0.4616,
      "step": 35447
    },
    {
      "epoch": 1.0889318956778178,
      "grad_norm": 0.3710043132305145,
      "learning_rate": 8.629882567176978e-06,
      "loss": 0.5253,
      "step": 35448
    },
    {
      "epoch": 1.088962614812767,
      "grad_norm": 0.4282998740673065,
      "learning_rate": 8.629403849024709e-06,
      "loss": 0.4904,
      "step": 35449
    },
    {
      "epoch": 1.088993333947716,
      "grad_norm": 0.40183988213539124,
      "learning_rate": 8.628925134073558e-06,
      "loss": 0.5537,
      "step": 35450
    },
    {
      "epoch": 1.0890240530826651,
      "grad_norm": 0.4399738609790802,
      "learning_rate": 8.628446422324652e-06,
      "loss": 0.5044,
      "step": 35451
    },
    {
      "epoch": 1.0890547722176143,
      "grad_norm": 0.35853901505470276,
      "learning_rate": 8.627967713779105e-06,
      "loss": 0.4981,
      "step": 35452
    },
    {
      "epoch": 1.0890854913525636,
      "grad_norm": 0.3882202208042145,
      "learning_rate": 8.627489008438037e-06,
      "loss": 0.5574,
      "step": 35453
    },
    {
      "epoch": 1.0891162104875127,
      "grad_norm": 0.37613722681999207,
      "learning_rate": 8.627010306302563e-06,
      "loss": 0.5135,
      "step": 35454
    },
    {
      "epoch": 1.0891469296224618,
      "grad_norm": 0.3800446391105652,
      "learning_rate": 8.626531607373802e-06,
      "loss": 0.4738,
      "step": 35455
    },
    {
      "epoch": 1.089177648757411,
      "grad_norm": 0.3577973246574402,
      "learning_rate": 8.626052911652873e-06,
      "loss": 0.5239,
      "step": 35456
    },
    {
      "epoch": 1.08920836789236,
      "grad_norm": 0.371834933757782,
      "learning_rate": 8.625574219140891e-06,
      "loss": 0.4781,
      "step": 35457
    },
    {
      "epoch": 1.0892390870273094,
      "grad_norm": 0.37534183263778687,
      "learning_rate": 8.625095529838981e-06,
      "loss": 0.5746,
      "step": 35458
    },
    {
      "epoch": 1.0892698061622585,
      "grad_norm": 0.43388885259628296,
      "learning_rate": 8.624616843748251e-06,
      "loss": 0.4834,
      "step": 35459
    },
    {
      "epoch": 1.0893005252972077,
      "grad_norm": 0.35691365599632263,
      "learning_rate": 8.62413816086983e-06,
      "loss": 0.486,
      "step": 35460
    },
    {
      "epoch": 1.0893312444321568,
      "grad_norm": 0.4007910490036011,
      "learning_rate": 8.623659481204824e-06,
      "loss": 0.5364,
      "step": 35461
    },
    {
      "epoch": 1.089361963567106,
      "grad_norm": 0.3712594211101532,
      "learning_rate": 8.623180804754366e-06,
      "loss": 0.4411,
      "step": 35462
    },
    {
      "epoch": 1.089392682702055,
      "grad_norm": 0.36288291215896606,
      "learning_rate": 8.622702131519556e-06,
      "loss": 0.5103,
      "step": 35463
    },
    {
      "epoch": 1.0894234018370044,
      "grad_norm": 0.48999688029289246,
      "learning_rate": 8.622223461501529e-06,
      "loss": 0.467,
      "step": 35464
    },
    {
      "epoch": 1.0894541209719535,
      "grad_norm": 0.39972689747810364,
      "learning_rate": 8.621744794701391e-06,
      "loss": 0.5069,
      "step": 35465
    },
    {
      "epoch": 1.0894848401069026,
      "grad_norm": 0.4967796504497528,
      "learning_rate": 8.621266131120267e-06,
      "loss": 0.4148,
      "step": 35466
    },
    {
      "epoch": 1.0895155592418517,
      "grad_norm": 0.37292400002479553,
      "learning_rate": 8.620787470759269e-06,
      "loss": 0.505,
      "step": 35467
    },
    {
      "epoch": 1.0895462783768008,
      "grad_norm": 0.398238867521286,
      "learning_rate": 8.62030881361952e-06,
      "loss": 0.4716,
      "step": 35468
    },
    {
      "epoch": 1.08957699751175,
      "grad_norm": 0.38192951679229736,
      "learning_rate": 8.619830159702135e-06,
      "loss": 0.4465,
      "step": 35469
    },
    {
      "epoch": 1.0896077166466993,
      "grad_norm": 1.2207623720169067,
      "learning_rate": 8.61935150900823e-06,
      "loss": 0.4476,
      "step": 35470
    },
    {
      "epoch": 1.0896384357816484,
      "grad_norm": 0.37657788395881653,
      "learning_rate": 8.618872861538933e-06,
      "loss": 0.5388,
      "step": 35471
    },
    {
      "epoch": 1.0896691549165975,
      "grad_norm": 0.4118942618370056,
      "learning_rate": 8.618394217295351e-06,
      "loss": 0.4896,
      "step": 35472
    },
    {
      "epoch": 1.0896998740515467,
      "grad_norm": 0.3479716181755066,
      "learning_rate": 8.617915576278608e-06,
      "loss": 0.4708,
      "step": 35473
    },
    {
      "epoch": 1.0897305931864958,
      "grad_norm": 0.45458143949508667,
      "learning_rate": 8.617436938489817e-06,
      "loss": 0.4516,
      "step": 35474
    },
    {
      "epoch": 1.0897613123214451,
      "grad_norm": 0.3743239939212799,
      "learning_rate": 8.616958303930101e-06,
      "loss": 0.5196,
      "step": 35475
    },
    {
      "epoch": 1.0897920314563943,
      "grad_norm": 0.40087732672691345,
      "learning_rate": 8.616479672600575e-06,
      "loss": 0.5476,
      "step": 35476
    },
    {
      "epoch": 1.0898227505913434,
      "grad_norm": 0.40314000844955444,
      "learning_rate": 8.616001044502355e-06,
      "loss": 0.5078,
      "step": 35477
    },
    {
      "epoch": 1.0898534697262925,
      "grad_norm": 0.39267706871032715,
      "learning_rate": 8.615522419636562e-06,
      "loss": 0.5193,
      "step": 35478
    },
    {
      "epoch": 1.0898841888612416,
      "grad_norm": 0.36839404702186584,
      "learning_rate": 8.615043798004316e-06,
      "loss": 0.4449,
      "step": 35479
    },
    {
      "epoch": 1.0899149079961907,
      "grad_norm": 0.380971223115921,
      "learning_rate": 8.61456517960673e-06,
      "loss": 0.445,
      "step": 35480
    },
    {
      "epoch": 1.08994562713114,
      "grad_norm": 0.40797802805900574,
      "learning_rate": 8.614086564444924e-06,
      "loss": 0.5258,
      "step": 35481
    },
    {
      "epoch": 1.0899763462660892,
      "grad_norm": 0.3735940456390381,
      "learning_rate": 8.613607952520014e-06,
      "loss": 0.5033,
      "step": 35482
    },
    {
      "epoch": 1.0900070654010383,
      "grad_norm": 0.4367336928844452,
      "learning_rate": 8.613129343833121e-06,
      "loss": 0.5362,
      "step": 35483
    },
    {
      "epoch": 1.0900377845359874,
      "grad_norm": 0.3750437796115875,
      "learning_rate": 8.61265073838536e-06,
      "loss": 0.484,
      "step": 35484
    },
    {
      "epoch": 1.0900685036709366,
      "grad_norm": 0.3609010875225067,
      "learning_rate": 8.612172136177852e-06,
      "loss": 0.464,
      "step": 35485
    },
    {
      "epoch": 1.0900992228058857,
      "grad_norm": 0.370535671710968,
      "learning_rate": 8.611693537211712e-06,
      "loss": 0.4812,
      "step": 35486
    },
    {
      "epoch": 1.090129941940835,
      "grad_norm": 0.3971123695373535,
      "learning_rate": 8.611214941488063e-06,
      "loss": 0.4715,
      "step": 35487
    },
    {
      "epoch": 1.0901606610757841,
      "grad_norm": 0.3603927195072174,
      "learning_rate": 8.610736349008009e-06,
      "loss": 0.4736,
      "step": 35488
    },
    {
      "epoch": 1.0901913802107333,
      "grad_norm": 0.4706789255142212,
      "learning_rate": 8.610257759772682e-06,
      "loss": 0.4205,
      "step": 35489
    },
    {
      "epoch": 1.0902220993456824,
      "grad_norm": 0.3410016596317291,
      "learning_rate": 8.609779173783196e-06,
      "loss": 0.4351,
      "step": 35490
    },
    {
      "epoch": 1.0902528184806315,
      "grad_norm": 0.3944557011127472,
      "learning_rate": 8.609300591040667e-06,
      "loss": 0.5222,
      "step": 35491
    },
    {
      "epoch": 1.0902835376155808,
      "grad_norm": 0.3796711564064026,
      "learning_rate": 8.608822011546214e-06,
      "loss": 0.4829,
      "step": 35492
    },
    {
      "epoch": 1.09031425675053,
      "grad_norm": 0.382020503282547,
      "learning_rate": 8.608343435300955e-06,
      "loss": 0.4128,
      "step": 35493
    },
    {
      "epoch": 1.090344975885479,
      "grad_norm": 0.3773631751537323,
      "learning_rate": 8.607864862306008e-06,
      "loss": 0.4719,
      "step": 35494
    },
    {
      "epoch": 1.0903756950204282,
      "grad_norm": 0.4600472152233124,
      "learning_rate": 8.607386292562485e-06,
      "loss": 0.5223,
      "step": 35495
    },
    {
      "epoch": 1.0904064141553773,
      "grad_norm": 0.41251426935195923,
      "learning_rate": 8.606907726071516e-06,
      "loss": 0.5139,
      "step": 35496
    },
    {
      "epoch": 1.0904371332903264,
      "grad_norm": 0.4388940632343292,
      "learning_rate": 8.606429162834204e-06,
      "loss": 0.5007,
      "step": 35497
    },
    {
      "epoch": 1.0904678524252758,
      "grad_norm": 0.4306029677391052,
      "learning_rate": 8.60595060285168e-06,
      "loss": 0.5217,
      "step": 35498
    },
    {
      "epoch": 1.090498571560225,
      "grad_norm": 0.3505968749523163,
      "learning_rate": 8.60547204612505e-06,
      "loss": 0.4751,
      "step": 35499
    },
    {
      "epoch": 1.090529290695174,
      "grad_norm": 0.35298681259155273,
      "learning_rate": 8.604993492655442e-06,
      "loss": 0.4414,
      "step": 35500
    },
    {
      "epoch": 1.0905600098301231,
      "grad_norm": 0.3929768204689026,
      "learning_rate": 8.604514942443967e-06,
      "loss": 0.4656,
      "step": 35501
    },
    {
      "epoch": 1.0905907289650723,
      "grad_norm": 0.40706855058670044,
      "learning_rate": 8.604036395491746e-06,
      "loss": 0.4232,
      "step": 35502
    },
    {
      "epoch": 1.0906214481000216,
      "grad_norm": 0.38174211978912354,
      "learning_rate": 8.603557851799894e-06,
      "loss": 0.4913,
      "step": 35503
    },
    {
      "epoch": 1.0906521672349707,
      "grad_norm": 0.3908109962940216,
      "learning_rate": 8.603079311369532e-06,
      "loss": 0.5067,
      "step": 35504
    },
    {
      "epoch": 1.0906828863699198,
      "grad_norm": 0.3661676347255707,
      "learning_rate": 8.602600774201774e-06,
      "loss": 0.5183,
      "step": 35505
    },
    {
      "epoch": 1.090713605504869,
      "grad_norm": 0.3663683235645294,
      "learning_rate": 8.602122240297738e-06,
      "loss": 0.4223,
      "step": 35506
    },
    {
      "epoch": 1.090744324639818,
      "grad_norm": 0.38849949836730957,
      "learning_rate": 8.601643709658547e-06,
      "loss": 0.5245,
      "step": 35507
    },
    {
      "epoch": 1.0907750437747672,
      "grad_norm": 0.37465307116508484,
      "learning_rate": 8.601165182285313e-06,
      "loss": 0.5242,
      "step": 35508
    },
    {
      "epoch": 1.0908057629097165,
      "grad_norm": 0.4004514217376709,
      "learning_rate": 8.600686658179156e-06,
      "loss": 0.5108,
      "step": 35509
    },
    {
      "epoch": 1.0908364820446657,
      "grad_norm": 0.39154475927352905,
      "learning_rate": 8.600208137341191e-06,
      "loss": 0.5512,
      "step": 35510
    },
    {
      "epoch": 1.0908672011796148,
      "grad_norm": 0.4132827818393707,
      "learning_rate": 8.599729619772541e-06,
      "loss": 0.499,
      "step": 35511
    },
    {
      "epoch": 1.090897920314564,
      "grad_norm": 0.4191522002220154,
      "learning_rate": 8.599251105474316e-06,
      "loss": 0.541,
      "step": 35512
    },
    {
      "epoch": 1.090928639449513,
      "grad_norm": 0.4058913290500641,
      "learning_rate": 8.598772594447643e-06,
      "loss": 0.4799,
      "step": 35513
    },
    {
      "epoch": 1.0909593585844624,
      "grad_norm": 0.3450806140899658,
      "learning_rate": 8.59829408669363e-06,
      "loss": 0.4851,
      "step": 35514
    },
    {
      "epoch": 1.0909900777194115,
      "grad_norm": 0.39674580097198486,
      "learning_rate": 8.597815582213402e-06,
      "loss": 0.4954,
      "step": 35515
    },
    {
      "epoch": 1.0910207968543606,
      "grad_norm": 0.5011155605316162,
      "learning_rate": 8.597337081008072e-06,
      "loss": 0.3755,
      "step": 35516
    },
    {
      "epoch": 1.0910515159893097,
      "grad_norm": 0.3921327590942383,
      "learning_rate": 8.59685858307876e-06,
      "loss": 0.472,
      "step": 35517
    },
    {
      "epoch": 1.0910822351242588,
      "grad_norm": 0.3776731491088867,
      "learning_rate": 8.596380088426582e-06,
      "loss": 0.5251,
      "step": 35518
    },
    {
      "epoch": 1.091112954259208,
      "grad_norm": 0.40679019689559937,
      "learning_rate": 8.595901597052657e-06,
      "loss": 0.51,
      "step": 35519
    },
    {
      "epoch": 1.0911436733941573,
      "grad_norm": 0.3858471214771271,
      "learning_rate": 8.5954231089581e-06,
      "loss": 0.4159,
      "step": 35520
    },
    {
      "epoch": 1.0911743925291064,
      "grad_norm": 0.3742695152759552,
      "learning_rate": 8.594944624144035e-06,
      "loss": 0.5198,
      "step": 35521
    },
    {
      "epoch": 1.0912051116640555,
      "grad_norm": 0.39718636870384216,
      "learning_rate": 8.59446614261157e-06,
      "loss": 0.5073,
      "step": 35522
    },
    {
      "epoch": 1.0912358307990047,
      "grad_norm": 0.4356961250305176,
      "learning_rate": 8.593987664361834e-06,
      "loss": 0.4573,
      "step": 35523
    },
    {
      "epoch": 1.0912665499339538,
      "grad_norm": 0.3666445016860962,
      "learning_rate": 8.59350918939593e-06,
      "loss": 0.5354,
      "step": 35524
    },
    {
      "epoch": 1.0912972690689031,
      "grad_norm": 0.4091757833957672,
      "learning_rate": 8.593030717714985e-06,
      "loss": 0.5224,
      "step": 35525
    },
    {
      "epoch": 1.0913279882038522,
      "grad_norm": 0.37146562337875366,
      "learning_rate": 8.592552249320118e-06,
      "loss": 0.5111,
      "step": 35526
    },
    {
      "epoch": 1.0913587073388014,
      "grad_norm": 0.4194639027118683,
      "learning_rate": 8.592073784212442e-06,
      "loss": 0.3746,
      "step": 35527
    },
    {
      "epoch": 1.0913894264737505,
      "grad_norm": 0.38028353452682495,
      "learning_rate": 8.59159532239308e-06,
      "loss": 0.4304,
      "step": 35528
    },
    {
      "epoch": 1.0914201456086996,
      "grad_norm": 0.42518654465675354,
      "learning_rate": 8.591116863863138e-06,
      "loss": 0.6131,
      "step": 35529
    },
    {
      "epoch": 1.0914508647436487,
      "grad_norm": 0.3891012370586395,
      "learning_rate": 8.59063840862375e-06,
      "loss": 0.4575,
      "step": 35530
    },
    {
      "epoch": 1.091481583878598,
      "grad_norm": 0.3978027105331421,
      "learning_rate": 8.590159956676015e-06,
      "loss": 0.4583,
      "step": 35531
    },
    {
      "epoch": 1.0915123030135472,
      "grad_norm": 0.3882611393928528,
      "learning_rate": 8.589681508021068e-06,
      "loss": 0.4961,
      "step": 35532
    },
    {
      "epoch": 1.0915430221484963,
      "grad_norm": 0.40116629004478455,
      "learning_rate": 8.589203062660012e-06,
      "loss": 0.5275,
      "step": 35533
    },
    {
      "epoch": 1.0915737412834454,
      "grad_norm": 0.37958431243896484,
      "learning_rate": 8.588724620593976e-06,
      "loss": 0.4904,
      "step": 35534
    },
    {
      "epoch": 1.0916044604183945,
      "grad_norm": 0.41167938709259033,
      "learning_rate": 8.58824618182407e-06,
      "loss": 0.4603,
      "step": 35535
    },
    {
      "epoch": 1.0916351795533439,
      "grad_norm": 0.4134971499443054,
      "learning_rate": 8.587767746351413e-06,
      "loss": 0.5111,
      "step": 35536
    },
    {
      "epoch": 1.091665898688293,
      "grad_norm": 0.38993188738822937,
      "learning_rate": 8.587289314177122e-06,
      "loss": 0.4055,
      "step": 35537
    },
    {
      "epoch": 1.0916966178232421,
      "grad_norm": 0.37817543745040894,
      "learning_rate": 8.586810885302319e-06,
      "loss": 0.4211,
      "step": 35538
    },
    {
      "epoch": 1.0917273369581912,
      "grad_norm": 0.5010704398155212,
      "learning_rate": 8.586332459728113e-06,
      "loss": 0.4626,
      "step": 35539
    },
    {
      "epoch": 1.0917580560931404,
      "grad_norm": 0.41440147161483765,
      "learning_rate": 8.58585403745563e-06,
      "loss": 0.5018,
      "step": 35540
    },
    {
      "epoch": 1.0917887752280895,
      "grad_norm": 0.3852914571762085,
      "learning_rate": 8.585375618485983e-06,
      "loss": 0.4329,
      "step": 35541
    },
    {
      "epoch": 1.0918194943630388,
      "grad_norm": 0.37389615178108215,
      "learning_rate": 8.58489720282029e-06,
      "loss": 0.5016,
      "step": 35542
    },
    {
      "epoch": 1.091850213497988,
      "grad_norm": 0.35531824827194214,
      "learning_rate": 8.584418790459667e-06,
      "loss": 0.453,
      "step": 35543
    },
    {
      "epoch": 1.091880932632937,
      "grad_norm": 0.47659021615982056,
      "learning_rate": 8.583940381405233e-06,
      "loss": 0.4369,
      "step": 35544
    },
    {
      "epoch": 1.0919116517678862,
      "grad_norm": 0.38617557287216187,
      "learning_rate": 8.583461975658107e-06,
      "loss": 0.5232,
      "step": 35545
    },
    {
      "epoch": 1.0919423709028353,
      "grad_norm": 0.37889227271080017,
      "learning_rate": 8.582983573219404e-06,
      "loss": 0.5903,
      "step": 35546
    },
    {
      "epoch": 1.0919730900377846,
      "grad_norm": 0.4129190146923065,
      "learning_rate": 8.582505174090241e-06,
      "loss": 0.5865,
      "step": 35547
    },
    {
      "epoch": 1.0920038091727338,
      "grad_norm": 0.435520738363266,
      "learning_rate": 8.582026778271735e-06,
      "loss": 0.4383,
      "step": 35548
    },
    {
      "epoch": 1.0920345283076829,
      "grad_norm": 0.5146291255950928,
      "learning_rate": 8.581548385765008e-06,
      "loss": 0.445,
      "step": 35549
    },
    {
      "epoch": 1.092065247442632,
      "grad_norm": 0.39225906133651733,
      "learning_rate": 8.581069996571171e-06,
      "loss": 0.4653,
      "step": 35550
    },
    {
      "epoch": 1.0920959665775811,
      "grad_norm": 0.37312623858451843,
      "learning_rate": 8.580591610691345e-06,
      "loss": 0.5119,
      "step": 35551
    },
    {
      "epoch": 1.0921266857125302,
      "grad_norm": 0.4289185106754303,
      "learning_rate": 8.580113228126645e-06,
      "loss": 0.5231,
      "step": 35552
    },
    {
      "epoch": 1.0921574048474796,
      "grad_norm": 0.4083510935306549,
      "learning_rate": 8.579634848878193e-06,
      "loss": 0.5426,
      "step": 35553
    },
    {
      "epoch": 1.0921881239824287,
      "grad_norm": 0.3546481430530548,
      "learning_rate": 8.5791564729471e-06,
      "loss": 0.4186,
      "step": 35554
    },
    {
      "epoch": 1.0922188431173778,
      "grad_norm": 0.4490339457988739,
      "learning_rate": 8.578678100334488e-06,
      "loss": 0.4239,
      "step": 35555
    },
    {
      "epoch": 1.092249562252327,
      "grad_norm": 0.38403424620628357,
      "learning_rate": 8.578199731041471e-06,
      "loss": 0.4524,
      "step": 35556
    },
    {
      "epoch": 1.092280281387276,
      "grad_norm": 0.49100348353385925,
      "learning_rate": 8.57772136506917e-06,
      "loss": 0.539,
      "step": 35557
    },
    {
      "epoch": 1.0923110005222254,
      "grad_norm": 0.3884807229042053,
      "learning_rate": 8.577243002418698e-06,
      "loss": 0.4556,
      "step": 35558
    },
    {
      "epoch": 1.0923417196571745,
      "grad_norm": 0.4477863907814026,
      "learning_rate": 8.576764643091178e-06,
      "loss": 0.5827,
      "step": 35559
    },
    {
      "epoch": 1.0923724387921236,
      "grad_norm": 0.4003540277481079,
      "learning_rate": 8.576286287087717e-06,
      "loss": 0.5027,
      "step": 35560
    },
    {
      "epoch": 1.0924031579270728,
      "grad_norm": 0.40656590461730957,
      "learning_rate": 8.575807934409442e-06,
      "loss": 0.4648,
      "step": 35561
    },
    {
      "epoch": 1.0924338770620219,
      "grad_norm": 0.39635351300239563,
      "learning_rate": 8.57532958505747e-06,
      "loss": 0.4987,
      "step": 35562
    },
    {
      "epoch": 1.092464596196971,
      "grad_norm": 0.40105465054512024,
      "learning_rate": 8.57485123903291e-06,
      "loss": 0.5071,
      "step": 35563
    },
    {
      "epoch": 1.0924953153319203,
      "grad_norm": 0.39580556750297546,
      "learning_rate": 8.57437289633689e-06,
      "loss": 0.4906,
      "step": 35564
    },
    {
      "epoch": 1.0925260344668695,
      "grad_norm": 0.42838817834854126,
      "learning_rate": 8.573894556970517e-06,
      "loss": 0.4503,
      "step": 35565
    },
    {
      "epoch": 1.0925567536018186,
      "grad_norm": 0.39594295620918274,
      "learning_rate": 8.573416220934918e-06,
      "loss": 0.4745,
      "step": 35566
    },
    {
      "epoch": 1.0925874727367677,
      "grad_norm": 0.3588157594203949,
      "learning_rate": 8.572937888231198e-06,
      "loss": 0.4847,
      "step": 35567
    },
    {
      "epoch": 1.0926181918717168,
      "grad_norm": 0.38502180576324463,
      "learning_rate": 8.57245955886049e-06,
      "loss": 0.4297,
      "step": 35568
    },
    {
      "epoch": 1.0926489110066662,
      "grad_norm": 0.3755019009113312,
      "learning_rate": 8.571981232823895e-06,
      "loss": 0.5043,
      "step": 35569
    },
    {
      "epoch": 1.0926796301416153,
      "grad_norm": 0.4023919105529785,
      "learning_rate": 8.571502910122541e-06,
      "loss": 0.4216,
      "step": 35570
    },
    {
      "epoch": 1.0927103492765644,
      "grad_norm": 0.4072716534137726,
      "learning_rate": 8.571024590757539e-06,
      "loss": 0.4768,
      "step": 35571
    },
    {
      "epoch": 1.0927410684115135,
      "grad_norm": 0.36714786291122437,
      "learning_rate": 8.570546274730013e-06,
      "loss": 0.4604,
      "step": 35572
    },
    {
      "epoch": 1.0927717875464626,
      "grad_norm": 0.3926941156387329,
      "learning_rate": 8.570067962041073e-06,
      "loss": 0.4303,
      "step": 35573
    },
    {
      "epoch": 1.0928025066814118,
      "grad_norm": 0.44231852889060974,
      "learning_rate": 8.56958965269184e-06,
      "loss": 0.4659,
      "step": 35574
    },
    {
      "epoch": 1.092833225816361,
      "grad_norm": 0.3649634122848511,
      "learning_rate": 8.56911134668343e-06,
      "loss": 0.4803,
      "step": 35575
    },
    {
      "epoch": 1.0928639449513102,
      "grad_norm": 0.4592183530330658,
      "learning_rate": 8.568633044016961e-06,
      "loss": 0.4462,
      "step": 35576
    },
    {
      "epoch": 1.0928946640862593,
      "grad_norm": 0.4296092092990875,
      "learning_rate": 8.568154744693547e-06,
      "loss": 0.4907,
      "step": 35577
    },
    {
      "epoch": 1.0929253832212085,
      "grad_norm": 0.3747735023498535,
      "learning_rate": 8.56767644871431e-06,
      "loss": 0.5092,
      "step": 35578
    },
    {
      "epoch": 1.0929561023561576,
      "grad_norm": 0.4454331696033478,
      "learning_rate": 8.567198156080364e-06,
      "loss": 0.4813,
      "step": 35579
    },
    {
      "epoch": 1.0929868214911067,
      "grad_norm": 0.39522862434387207,
      "learning_rate": 8.566719866792826e-06,
      "loss": 0.5249,
      "step": 35580
    },
    {
      "epoch": 1.093017540626056,
      "grad_norm": 0.37475520372390747,
      "learning_rate": 8.566241580852816e-06,
      "loss": 0.4738,
      "step": 35581
    },
    {
      "epoch": 1.0930482597610052,
      "grad_norm": 0.3783215582370758,
      "learning_rate": 8.565763298261447e-06,
      "loss": 0.4639,
      "step": 35582
    },
    {
      "epoch": 1.0930789788959543,
      "grad_norm": 0.5967388153076172,
      "learning_rate": 8.56528501901984e-06,
      "loss": 0.5193,
      "step": 35583
    },
    {
      "epoch": 1.0931096980309034,
      "grad_norm": 0.4199596047401428,
      "learning_rate": 8.564806743129107e-06,
      "loss": 0.5286,
      "step": 35584
    },
    {
      "epoch": 1.0931404171658525,
      "grad_norm": 0.3999186158180237,
      "learning_rate": 8.56432847059037e-06,
      "loss": 0.4632,
      "step": 35585
    },
    {
      "epoch": 1.0931711363008019,
      "grad_norm": 0.432572603225708,
      "learning_rate": 8.563850201404744e-06,
      "loss": 0.5021,
      "step": 35586
    },
    {
      "epoch": 1.093201855435751,
      "grad_norm": 0.38288623094558716,
      "learning_rate": 8.563371935573348e-06,
      "loss": 0.5385,
      "step": 35587
    },
    {
      "epoch": 1.0932325745707,
      "grad_norm": 0.384622722864151,
      "learning_rate": 8.562893673097293e-06,
      "loss": 0.467,
      "step": 35588
    },
    {
      "epoch": 1.0932632937056492,
      "grad_norm": 0.42304933071136475,
      "learning_rate": 8.562415413977704e-06,
      "loss": 0.4349,
      "step": 35589
    },
    {
      "epoch": 1.0932940128405984,
      "grad_norm": 0.40635836124420166,
      "learning_rate": 8.561937158215691e-06,
      "loss": 0.4675,
      "step": 35590
    },
    {
      "epoch": 1.0933247319755475,
      "grad_norm": 0.37878626585006714,
      "learning_rate": 8.56145890581238e-06,
      "loss": 0.5744,
      "step": 35591
    },
    {
      "epoch": 1.0933554511104968,
      "grad_norm": 0.38630741834640503,
      "learning_rate": 8.560980656768875e-06,
      "loss": 0.5493,
      "step": 35592
    },
    {
      "epoch": 1.093386170245446,
      "grad_norm": 0.4294546842575073,
      "learning_rate": 8.560502411086307e-06,
      "loss": 0.5079,
      "step": 35593
    },
    {
      "epoch": 1.093416889380395,
      "grad_norm": 0.6479926705360413,
      "learning_rate": 8.560024168765779e-06,
      "loss": 0.5796,
      "step": 35594
    },
    {
      "epoch": 1.0934476085153442,
      "grad_norm": 0.6920290589332581,
      "learning_rate": 8.559545929808422e-06,
      "loss": 0.5112,
      "step": 35595
    },
    {
      "epoch": 1.0934783276502933,
      "grad_norm": 0.4099348187446594,
      "learning_rate": 8.559067694215338e-06,
      "loss": 0.5095,
      "step": 35596
    },
    {
      "epoch": 1.0935090467852424,
      "grad_norm": 0.40620043873786926,
      "learning_rate": 8.558589461987656e-06,
      "loss": 0.4348,
      "step": 35597
    },
    {
      "epoch": 1.0935397659201918,
      "grad_norm": 0.431299090385437,
      "learning_rate": 8.558111233126493e-06,
      "loss": 0.5074,
      "step": 35598
    },
    {
      "epoch": 1.0935704850551409,
      "grad_norm": 0.4164414703845978,
      "learning_rate": 8.557633007632956e-06,
      "loss": 0.5358,
      "step": 35599
    },
    {
      "epoch": 1.09360120419009,
      "grad_norm": 0.44190049171447754,
      "learning_rate": 8.557154785508173e-06,
      "loss": 0.4763,
      "step": 35600
    },
    {
      "epoch": 1.0936319233250391,
      "grad_norm": 0.40259402990341187,
      "learning_rate": 8.55667656675325e-06,
      "loss": 0.5194,
      "step": 35601
    },
    {
      "epoch": 1.0936626424599882,
      "grad_norm": 0.38179895281791687,
      "learning_rate": 8.556198351369317e-06,
      "loss": 0.4492,
      "step": 35602
    },
    {
      "epoch": 1.0936933615949376,
      "grad_norm": 0.3802211284637451,
      "learning_rate": 8.555720139357475e-06,
      "loss": 0.4855,
      "step": 35603
    },
    {
      "epoch": 1.0937240807298867,
      "grad_norm": 0.3801369071006775,
      "learning_rate": 8.555241930718857e-06,
      "loss": 0.5232,
      "step": 35604
    },
    {
      "epoch": 1.0937547998648358,
      "grad_norm": 0.4401725232601166,
      "learning_rate": 8.554763725454568e-06,
      "loss": 0.5348,
      "step": 35605
    },
    {
      "epoch": 1.093785518999785,
      "grad_norm": 0.35288435220718384,
      "learning_rate": 8.554285523565731e-06,
      "loss": 0.4985,
      "step": 35606
    },
    {
      "epoch": 1.093816238134734,
      "grad_norm": 0.4042361378669739,
      "learning_rate": 8.553807325053461e-06,
      "loss": 0.4835,
      "step": 35607
    },
    {
      "epoch": 1.0938469572696832,
      "grad_norm": 0.38879668712615967,
      "learning_rate": 8.553329129918875e-06,
      "loss": 0.5033,
      "step": 35608
    },
    {
      "epoch": 1.0938776764046325,
      "grad_norm": 0.39783337712287903,
      "learning_rate": 8.552850938163088e-06,
      "loss": 0.4593,
      "step": 35609
    },
    {
      "epoch": 1.0939083955395816,
      "grad_norm": 0.40862175822257996,
      "learning_rate": 8.55237274978722e-06,
      "loss": 0.5284,
      "step": 35610
    },
    {
      "epoch": 1.0939391146745308,
      "grad_norm": 0.37958279252052307,
      "learning_rate": 8.551894564792386e-06,
      "loss": 0.5229,
      "step": 35611
    },
    {
      "epoch": 1.0939698338094799,
      "grad_norm": 0.45118480920791626,
      "learning_rate": 8.551416383179707e-06,
      "loss": 0.5435,
      "step": 35612
    },
    {
      "epoch": 1.094000552944429,
      "grad_norm": 0.47146040201187134,
      "learning_rate": 8.550938204950293e-06,
      "loss": 0.4687,
      "step": 35613
    },
    {
      "epoch": 1.0940312720793783,
      "grad_norm": 0.4217805564403534,
      "learning_rate": 8.550460030105265e-06,
      "loss": 0.5994,
      "step": 35614
    },
    {
      "epoch": 1.0940619912143275,
      "grad_norm": 0.4178244173526764,
      "learning_rate": 8.549981858645736e-06,
      "loss": 0.3848,
      "step": 35615
    },
    {
      "epoch": 1.0940927103492766,
      "grad_norm": 0.5315815806388855,
      "learning_rate": 8.549503690572826e-06,
      "loss": 0.5143,
      "step": 35616
    },
    {
      "epoch": 1.0941234294842257,
      "grad_norm": 0.4191828668117523,
      "learning_rate": 8.549025525887655e-06,
      "loss": 0.4608,
      "step": 35617
    },
    {
      "epoch": 1.0941541486191748,
      "grad_norm": 0.422191858291626,
      "learning_rate": 8.548547364591334e-06,
      "loss": 0.4861,
      "step": 35618
    },
    {
      "epoch": 1.094184867754124,
      "grad_norm": 0.43577611446380615,
      "learning_rate": 8.548069206684983e-06,
      "loss": 0.4949,
      "step": 35619
    },
    {
      "epoch": 1.0942155868890733,
      "grad_norm": 0.4465779960155487,
      "learning_rate": 8.547591052169718e-06,
      "loss": 0.5424,
      "step": 35620
    },
    {
      "epoch": 1.0942463060240224,
      "grad_norm": 0.3807156980037689,
      "learning_rate": 8.547112901046655e-06,
      "loss": 0.5235,
      "step": 35621
    },
    {
      "epoch": 1.0942770251589715,
      "grad_norm": 0.3882593512535095,
      "learning_rate": 8.546634753316909e-06,
      "loss": 0.4637,
      "step": 35622
    },
    {
      "epoch": 1.0943077442939206,
      "grad_norm": 0.4174474775791168,
      "learning_rate": 8.546156608981603e-06,
      "loss": 0.5143,
      "step": 35623
    },
    {
      "epoch": 1.0943384634288698,
      "grad_norm": 0.40084755420684814,
      "learning_rate": 8.545678468041846e-06,
      "loss": 0.4895,
      "step": 35624
    },
    {
      "epoch": 1.094369182563819,
      "grad_norm": 0.40631869435310364,
      "learning_rate": 8.545200330498762e-06,
      "loss": 0.4671,
      "step": 35625
    },
    {
      "epoch": 1.0943999016987682,
      "grad_norm": 0.4634721875190735,
      "learning_rate": 8.54472219635346e-06,
      "loss": 0.5466,
      "step": 35626
    },
    {
      "epoch": 1.0944306208337173,
      "grad_norm": 0.3643905222415924,
      "learning_rate": 8.544244065607068e-06,
      "loss": 0.4899,
      "step": 35627
    },
    {
      "epoch": 1.0944613399686665,
      "grad_norm": 0.3990155756473541,
      "learning_rate": 8.543765938260688e-06,
      "loss": 0.5417,
      "step": 35628
    },
    {
      "epoch": 1.0944920591036156,
      "grad_norm": 0.39834052324295044,
      "learning_rate": 8.54328781431545e-06,
      "loss": 0.5003,
      "step": 35629
    },
    {
      "epoch": 1.0945227782385647,
      "grad_norm": 0.40808597207069397,
      "learning_rate": 8.542809693772461e-06,
      "loss": 0.4489,
      "step": 35630
    },
    {
      "epoch": 1.094553497373514,
      "grad_norm": 0.4335676431655884,
      "learning_rate": 8.542331576632845e-06,
      "loss": 0.4584,
      "step": 35631
    },
    {
      "epoch": 1.0945842165084632,
      "grad_norm": 0.3772093653678894,
      "learning_rate": 8.541853462897714e-06,
      "loss": 0.4825,
      "step": 35632
    },
    {
      "epoch": 1.0946149356434123,
      "grad_norm": 0.376865953207016,
      "learning_rate": 8.541375352568187e-06,
      "loss": 0.4579,
      "step": 35633
    },
    {
      "epoch": 1.0946456547783614,
      "grad_norm": 0.4202686846256256,
      "learning_rate": 8.540897245645377e-06,
      "loss": 0.5132,
      "step": 35634
    },
    {
      "epoch": 1.0946763739133105,
      "grad_norm": 0.39648211002349854,
      "learning_rate": 8.540419142130401e-06,
      "loss": 0.4296,
      "step": 35635
    },
    {
      "epoch": 1.0947070930482599,
      "grad_norm": 0.45031675696372986,
      "learning_rate": 8.539941042024386e-06,
      "loss": 0.5292,
      "step": 35636
    },
    {
      "epoch": 1.094737812183209,
      "grad_norm": 0.4088585376739502,
      "learning_rate": 8.539462945328434e-06,
      "loss": 0.4743,
      "step": 35637
    },
    {
      "epoch": 1.094768531318158,
      "grad_norm": 0.48423004150390625,
      "learning_rate": 8.538984852043674e-06,
      "loss": 0.4204,
      "step": 35638
    },
    {
      "epoch": 1.0947992504531072,
      "grad_norm": 0.42983460426330566,
      "learning_rate": 8.538506762171213e-06,
      "loss": 0.4873,
      "step": 35639
    },
    {
      "epoch": 1.0948299695880563,
      "grad_norm": 0.40060779452323914,
      "learning_rate": 8.538028675712172e-06,
      "loss": 0.4924,
      "step": 35640
    },
    {
      "epoch": 1.0948606887230055,
      "grad_norm": 0.4186538755893707,
      "learning_rate": 8.537550592667667e-06,
      "loss": 0.5392,
      "step": 35641
    },
    {
      "epoch": 1.0948914078579548,
      "grad_norm": 0.39455896615982056,
      "learning_rate": 8.537072513038815e-06,
      "loss": 0.5609,
      "step": 35642
    },
    {
      "epoch": 1.094922126992904,
      "grad_norm": 0.40092772245407104,
      "learning_rate": 8.536594436826733e-06,
      "loss": 0.4242,
      "step": 35643
    },
    {
      "epoch": 1.094952846127853,
      "grad_norm": 0.4287976324558258,
      "learning_rate": 8.536116364032538e-06,
      "loss": 0.5732,
      "step": 35644
    },
    {
      "epoch": 1.0949835652628022,
      "grad_norm": 0.3454320728778839,
      "learning_rate": 8.535638294657342e-06,
      "loss": 0.4675,
      "step": 35645
    },
    {
      "epoch": 1.0950142843977513,
      "grad_norm": 0.4005044996738434,
      "learning_rate": 8.535160228702268e-06,
      "loss": 0.4483,
      "step": 35646
    },
    {
      "epoch": 1.0950450035327006,
      "grad_norm": 0.3633843660354614,
      "learning_rate": 8.534682166168427e-06,
      "loss": 0.4864,
      "step": 35647
    },
    {
      "epoch": 1.0950757226676497,
      "grad_norm": 0.38016510009765625,
      "learning_rate": 8.534204107056941e-06,
      "loss": 0.5333,
      "step": 35648
    },
    {
      "epoch": 1.0951064418025989,
      "grad_norm": 0.38868534564971924,
      "learning_rate": 8.533726051368922e-06,
      "loss": 0.456,
      "step": 35649
    },
    {
      "epoch": 1.095137160937548,
      "grad_norm": 0.3582300841808319,
      "learning_rate": 8.533247999105489e-06,
      "loss": 0.497,
      "step": 35650
    },
    {
      "epoch": 1.095167880072497,
      "grad_norm": 0.43278148770332336,
      "learning_rate": 8.532769950267757e-06,
      "loss": 0.5276,
      "step": 35651
    },
    {
      "epoch": 1.0951985992074462,
      "grad_norm": 0.3976197838783264,
      "learning_rate": 8.532291904856842e-06,
      "loss": 0.4652,
      "step": 35652
    },
    {
      "epoch": 1.0952293183423956,
      "grad_norm": 0.3736256957054138,
      "learning_rate": 8.531813862873863e-06,
      "loss": 0.5117,
      "step": 35653
    },
    {
      "epoch": 1.0952600374773447,
      "grad_norm": 0.3849649727344513,
      "learning_rate": 8.531335824319935e-06,
      "loss": 0.4868,
      "step": 35654
    },
    {
      "epoch": 1.0952907566122938,
      "grad_norm": 0.3854615092277527,
      "learning_rate": 8.530857789196176e-06,
      "loss": 0.5598,
      "step": 35655
    },
    {
      "epoch": 1.095321475747243,
      "grad_norm": 0.4040275514125824,
      "learning_rate": 8.5303797575037e-06,
      "loss": 0.4797,
      "step": 35656
    },
    {
      "epoch": 1.095352194882192,
      "grad_norm": 0.4030679166316986,
      "learning_rate": 8.529901729243626e-06,
      "loss": 0.4713,
      "step": 35657
    },
    {
      "epoch": 1.0953829140171414,
      "grad_norm": 0.39053842425346375,
      "learning_rate": 8.529423704417068e-06,
      "loss": 0.4381,
      "step": 35658
    },
    {
      "epoch": 1.0954136331520905,
      "grad_norm": 0.4244135022163391,
      "learning_rate": 8.528945683025145e-06,
      "loss": 0.5607,
      "step": 35659
    },
    {
      "epoch": 1.0954443522870396,
      "grad_norm": 0.3834063410758972,
      "learning_rate": 8.52846766506897e-06,
      "loss": 0.5263,
      "step": 35660
    },
    {
      "epoch": 1.0954750714219887,
      "grad_norm": 0.4292452037334442,
      "learning_rate": 8.527989650549666e-06,
      "loss": 0.4365,
      "step": 35661
    },
    {
      "epoch": 1.0955057905569379,
      "grad_norm": 0.4181267023086548,
      "learning_rate": 8.52751163946834e-06,
      "loss": 0.4515,
      "step": 35662
    },
    {
      "epoch": 1.095536509691887,
      "grad_norm": 0.3894737958908081,
      "learning_rate": 8.527033631826118e-06,
      "loss": 0.4783,
      "step": 35663
    },
    {
      "epoch": 1.0955672288268363,
      "grad_norm": 0.41994354128837585,
      "learning_rate": 8.526555627624105e-06,
      "loss": 0.5525,
      "step": 35664
    },
    {
      "epoch": 1.0955979479617854,
      "grad_norm": 0.40765902400016785,
      "learning_rate": 8.526077626863431e-06,
      "loss": 0.4919,
      "step": 35665
    },
    {
      "epoch": 1.0956286670967346,
      "grad_norm": 0.4158641993999481,
      "learning_rate": 8.525599629545199e-06,
      "loss": 0.4441,
      "step": 35666
    },
    {
      "epoch": 1.0956593862316837,
      "grad_norm": 0.37438955903053284,
      "learning_rate": 8.525121635670539e-06,
      "loss": 0.4366,
      "step": 35667
    },
    {
      "epoch": 1.0956901053666328,
      "grad_norm": 0.4094998240470886,
      "learning_rate": 8.524643645240557e-06,
      "loss": 0.5002,
      "step": 35668
    },
    {
      "epoch": 1.0957208245015821,
      "grad_norm": 0.4326545298099518,
      "learning_rate": 8.524165658256374e-06,
      "loss": 0.5398,
      "step": 35669
    },
    {
      "epoch": 1.0957515436365313,
      "grad_norm": 0.38409966230392456,
      "learning_rate": 8.523687674719104e-06,
      "loss": 0.4005,
      "step": 35670
    },
    {
      "epoch": 1.0957822627714804,
      "grad_norm": 0.4426717460155487,
      "learning_rate": 8.523209694629861e-06,
      "loss": 0.5156,
      "step": 35671
    },
    {
      "epoch": 1.0958129819064295,
      "grad_norm": 0.954280436038971,
      "learning_rate": 8.522731717989772e-06,
      "loss": 0.5654,
      "step": 35672
    },
    {
      "epoch": 1.0958437010413786,
      "grad_norm": 0.3587718605995178,
      "learning_rate": 8.522253744799941e-06,
      "loss": 0.4938,
      "step": 35673
    },
    {
      "epoch": 1.0958744201763277,
      "grad_norm": 0.4139050543308258,
      "learning_rate": 8.521775775061493e-06,
      "loss": 0.5262,
      "step": 35674
    },
    {
      "epoch": 1.095905139311277,
      "grad_norm": 0.40043801069259644,
      "learning_rate": 8.521297808775538e-06,
      "loss": 0.5583,
      "step": 35675
    },
    {
      "epoch": 1.0959358584462262,
      "grad_norm": 0.3797990679740906,
      "learning_rate": 8.520819845943197e-06,
      "loss": 0.4678,
      "step": 35676
    },
    {
      "epoch": 1.0959665775811753,
      "grad_norm": 0.45250415802001953,
      "learning_rate": 8.520341886565583e-06,
      "loss": 0.4489,
      "step": 35677
    },
    {
      "epoch": 1.0959972967161244,
      "grad_norm": 0.44824549555778503,
      "learning_rate": 8.519863930643817e-06,
      "loss": 0.5459,
      "step": 35678
    },
    {
      "epoch": 1.0960280158510736,
      "grad_norm": 0.46007633209228516,
      "learning_rate": 8.519385978179008e-06,
      "loss": 0.5189,
      "step": 35679
    },
    {
      "epoch": 1.096058734986023,
      "grad_norm": 0.33535653352737427,
      "learning_rate": 8.518908029172282e-06,
      "loss": 0.4015,
      "step": 35680
    },
    {
      "epoch": 1.096089454120972,
      "grad_norm": 0.4161185026168823,
      "learning_rate": 8.518430083624744e-06,
      "loss": 0.5243,
      "step": 35681
    },
    {
      "epoch": 1.0961201732559211,
      "grad_norm": 0.3974143862724304,
      "learning_rate": 8.51795214153752e-06,
      "loss": 0.4675,
      "step": 35682
    },
    {
      "epoch": 1.0961508923908703,
      "grad_norm": 0.3662581443786621,
      "learning_rate": 8.51747420291172e-06,
      "loss": 0.4823,
      "step": 35683
    },
    {
      "epoch": 1.0961816115258194,
      "grad_norm": 0.4315793514251709,
      "learning_rate": 8.516996267748464e-06,
      "loss": 0.485,
      "step": 35684
    },
    {
      "epoch": 1.0962123306607685,
      "grad_norm": 0.39653632044792175,
      "learning_rate": 8.516518336048865e-06,
      "loss": 0.4795,
      "step": 35685
    },
    {
      "epoch": 1.0962430497957178,
      "grad_norm": 0.3575965464115143,
      "learning_rate": 8.516040407814044e-06,
      "loss": 0.463,
      "step": 35686
    },
    {
      "epoch": 1.096273768930667,
      "grad_norm": 0.3833383321762085,
      "learning_rate": 8.51556248304511e-06,
      "loss": 0.4936,
      "step": 35687
    },
    {
      "epoch": 1.096304488065616,
      "grad_norm": 0.43823644518852234,
      "learning_rate": 8.515084561743188e-06,
      "loss": 0.5775,
      "step": 35688
    },
    {
      "epoch": 1.0963352072005652,
      "grad_norm": 0.364677369594574,
      "learning_rate": 8.514606643909386e-06,
      "loss": 0.4594,
      "step": 35689
    },
    {
      "epoch": 1.0963659263355143,
      "grad_norm": 0.38722333312034607,
      "learning_rate": 8.514128729544824e-06,
      "loss": 0.4862,
      "step": 35690
    },
    {
      "epoch": 1.0963966454704634,
      "grad_norm": 0.41379547119140625,
      "learning_rate": 8.51365081865062e-06,
      "loss": 0.5532,
      "step": 35691
    },
    {
      "epoch": 1.0964273646054128,
      "grad_norm": 0.4812766909599304,
      "learning_rate": 8.513172911227887e-06,
      "loss": 0.5298,
      "step": 35692
    },
    {
      "epoch": 1.096458083740362,
      "grad_norm": 0.357683002948761,
      "learning_rate": 8.512695007277745e-06,
      "loss": 0.4892,
      "step": 35693
    },
    {
      "epoch": 1.096488802875311,
      "grad_norm": 0.4196988642215729,
      "learning_rate": 8.512217106801305e-06,
      "loss": 0.4624,
      "step": 35694
    },
    {
      "epoch": 1.0965195220102602,
      "grad_norm": 0.3809865117073059,
      "learning_rate": 8.511739209799687e-06,
      "loss": 0.4799,
      "step": 35695
    },
    {
      "epoch": 1.0965502411452093,
      "grad_norm": 0.4082748293876648,
      "learning_rate": 8.511261316274006e-06,
      "loss": 0.5341,
      "step": 35696
    },
    {
      "epoch": 1.0965809602801586,
      "grad_norm": 0.4080330431461334,
      "learning_rate": 8.510783426225382e-06,
      "loss": 0.4408,
      "step": 35697
    },
    {
      "epoch": 1.0966116794151077,
      "grad_norm": 0.3810392916202545,
      "learning_rate": 8.510305539654919e-06,
      "loss": 0.5142,
      "step": 35698
    },
    {
      "epoch": 1.0966423985500569,
      "grad_norm": 0.4002768099308014,
      "learning_rate": 8.50982765656375e-06,
      "loss": 0.4546,
      "step": 35699
    },
    {
      "epoch": 1.096673117685006,
      "grad_norm": 0.4180963337421417,
      "learning_rate": 8.509349776952976e-06,
      "loss": 0.5227,
      "step": 35700
    },
    {
      "epoch": 1.096703836819955,
      "grad_norm": 0.375600129365921,
      "learning_rate": 8.508871900823724e-06,
      "loss": 0.5565,
      "step": 35701
    },
    {
      "epoch": 1.0967345559549042,
      "grad_norm": 0.4374639093875885,
      "learning_rate": 8.508394028177103e-06,
      "loss": 0.5332,
      "step": 35702
    },
    {
      "epoch": 1.0967652750898536,
      "grad_norm": 0.3746410608291626,
      "learning_rate": 8.507916159014233e-06,
      "loss": 0.4674,
      "step": 35703
    },
    {
      "epoch": 1.0967959942248027,
      "grad_norm": 0.4035598635673523,
      "learning_rate": 8.507438293336229e-06,
      "loss": 0.494,
      "step": 35704
    },
    {
      "epoch": 1.0968267133597518,
      "grad_norm": 0.37907275557518005,
      "learning_rate": 8.506960431144208e-06,
      "loss": 0.4777,
      "step": 35705
    },
    {
      "epoch": 1.096857432494701,
      "grad_norm": 0.34928804636001587,
      "learning_rate": 8.506482572439284e-06,
      "loss": 0.4588,
      "step": 35706
    },
    {
      "epoch": 1.09688815162965,
      "grad_norm": 0.3889208436012268,
      "learning_rate": 8.50600471722257e-06,
      "loss": 0.483,
      "step": 35707
    },
    {
      "epoch": 1.0969188707645992,
      "grad_norm": 0.38519003987312317,
      "learning_rate": 8.505526865495195e-06,
      "loss": 0.5989,
      "step": 35708
    },
    {
      "epoch": 1.0969495898995485,
      "grad_norm": 0.47084325551986694,
      "learning_rate": 8.50504901725826e-06,
      "loss": 0.505,
      "step": 35709
    },
    {
      "epoch": 1.0969803090344976,
      "grad_norm": 0.4050866365432739,
      "learning_rate": 8.50457117251289e-06,
      "loss": 0.6119,
      "step": 35710
    },
    {
      "epoch": 1.0970110281694467,
      "grad_norm": 0.36819666624069214,
      "learning_rate": 8.504093331260198e-06,
      "loss": 0.506,
      "step": 35711
    },
    {
      "epoch": 1.0970417473043959,
      "grad_norm": 0.39739423990249634,
      "learning_rate": 8.5036154935013e-06,
      "loss": 0.4458,
      "step": 35712
    },
    {
      "epoch": 1.097072466439345,
      "grad_norm": 0.3734246790409088,
      "learning_rate": 8.503137659237314e-06,
      "loss": 0.4697,
      "step": 35713
    },
    {
      "epoch": 1.0971031855742943,
      "grad_norm": 0.39889174699783325,
      "learning_rate": 8.502659828469355e-06,
      "loss": 0.5258,
      "step": 35714
    },
    {
      "epoch": 1.0971339047092434,
      "grad_norm": 0.4301435351371765,
      "learning_rate": 8.502182001198535e-06,
      "loss": 0.4817,
      "step": 35715
    },
    {
      "epoch": 1.0971646238441926,
      "grad_norm": 0.34629693627357483,
      "learning_rate": 8.501704177425978e-06,
      "loss": 0.5789,
      "step": 35716
    },
    {
      "epoch": 1.0971953429791417,
      "grad_norm": 0.4111872911453247,
      "learning_rate": 8.501226357152793e-06,
      "loss": 0.5074,
      "step": 35717
    },
    {
      "epoch": 1.0972260621140908,
      "grad_norm": 0.3882156312465668,
      "learning_rate": 8.500748540380098e-06,
      "loss": 0.4791,
      "step": 35718
    },
    {
      "epoch": 1.09725678124904,
      "grad_norm": 0.43573686480522156,
      "learning_rate": 8.50027072710901e-06,
      "loss": 0.5427,
      "step": 35719
    },
    {
      "epoch": 1.0972875003839893,
      "grad_norm": 0.3900320827960968,
      "learning_rate": 8.499792917340645e-06,
      "loss": 0.4512,
      "step": 35720
    },
    {
      "epoch": 1.0973182195189384,
      "grad_norm": 0.406880646944046,
      "learning_rate": 8.499315111076117e-06,
      "loss": 0.5027,
      "step": 35721
    },
    {
      "epoch": 1.0973489386538875,
      "grad_norm": 0.4207877814769745,
      "learning_rate": 8.498837308316546e-06,
      "loss": 0.4566,
      "step": 35722
    },
    {
      "epoch": 1.0973796577888366,
      "grad_norm": 0.39001762866973877,
      "learning_rate": 8.498359509063041e-06,
      "loss": 0.499,
      "step": 35723
    },
    {
      "epoch": 1.0974103769237857,
      "grad_norm": 0.3848218321800232,
      "learning_rate": 8.49788171331673e-06,
      "loss": 0.4957,
      "step": 35724
    },
    {
      "epoch": 1.097441096058735,
      "grad_norm": 0.44804811477661133,
      "learning_rate": 8.497403921078713e-06,
      "loss": 0.5156,
      "step": 35725
    },
    {
      "epoch": 1.0974718151936842,
      "grad_norm": 0.41129574179649353,
      "learning_rate": 8.496926132350115e-06,
      "loss": 0.4966,
      "step": 35726
    },
    {
      "epoch": 1.0975025343286333,
      "grad_norm": 0.3905911147594452,
      "learning_rate": 8.496448347132056e-06,
      "loss": 0.4555,
      "step": 35727
    },
    {
      "epoch": 1.0975332534635824,
      "grad_norm": 0.4187312126159668,
      "learning_rate": 8.495970565425642e-06,
      "loss": 0.5296,
      "step": 35728
    },
    {
      "epoch": 1.0975639725985316,
      "grad_norm": 0.37389299273490906,
      "learning_rate": 8.495492787231998e-06,
      "loss": 0.4873,
      "step": 35729
    },
    {
      "epoch": 1.0975946917334807,
      "grad_norm": 0.38715237379074097,
      "learning_rate": 8.495015012552232e-06,
      "loss": 0.4668,
      "step": 35730
    },
    {
      "epoch": 1.09762541086843,
      "grad_norm": 0.4745267629623413,
      "learning_rate": 8.494537241387469e-06,
      "loss": 0.5153,
      "step": 35731
    },
    {
      "epoch": 1.0976561300033791,
      "grad_norm": 0.41252508759498596,
      "learning_rate": 8.494059473738812e-06,
      "loss": 0.5352,
      "step": 35732
    },
    {
      "epoch": 1.0976868491383283,
      "grad_norm": 0.34848350286483765,
      "learning_rate": 8.49358170960739e-06,
      "loss": 0.4496,
      "step": 35733
    },
    {
      "epoch": 1.0977175682732774,
      "grad_norm": 0.385651558637619,
      "learning_rate": 8.493103948994308e-06,
      "loss": 0.4545,
      "step": 35734
    },
    {
      "epoch": 1.0977482874082265,
      "grad_norm": 0.37545081973075867,
      "learning_rate": 8.492626191900693e-06,
      "loss": 0.408,
      "step": 35735
    },
    {
      "epoch": 1.0977790065431758,
      "grad_norm": 0.4086902439594269,
      "learning_rate": 8.492148438327649e-06,
      "loss": 0.4694,
      "step": 35736
    },
    {
      "epoch": 1.097809725678125,
      "grad_norm": 0.408730685710907,
      "learning_rate": 8.491670688276303e-06,
      "loss": 0.4694,
      "step": 35737
    },
    {
      "epoch": 1.097840444813074,
      "grad_norm": 0.36522266268730164,
      "learning_rate": 8.491192941747762e-06,
      "loss": 0.4948,
      "step": 35738
    },
    {
      "epoch": 1.0978711639480232,
      "grad_norm": 0.36055561900138855,
      "learning_rate": 8.490715198743148e-06,
      "loss": 0.528,
      "step": 35739
    },
    {
      "epoch": 1.0979018830829723,
      "grad_norm": 0.38231387734413147,
      "learning_rate": 8.490237459263571e-06,
      "loss": 0.4808,
      "step": 35740
    },
    {
      "epoch": 1.0979326022179214,
      "grad_norm": 0.37161147594451904,
      "learning_rate": 8.489759723310152e-06,
      "loss": 0.4661,
      "step": 35741
    },
    {
      "epoch": 1.0979633213528708,
      "grad_norm": 0.37934425473213196,
      "learning_rate": 8.489281990884002e-06,
      "loss": 0.5318,
      "step": 35742
    },
    {
      "epoch": 1.09799404048782,
      "grad_norm": 0.42317846417427063,
      "learning_rate": 8.48880426198624e-06,
      "loss": 0.4956,
      "step": 35743
    },
    {
      "epoch": 1.098024759622769,
      "grad_norm": 0.4032776653766632,
      "learning_rate": 8.488326536617984e-06,
      "loss": 0.4976,
      "step": 35744
    },
    {
      "epoch": 1.0980554787577181,
      "grad_norm": 0.39189305901527405,
      "learning_rate": 8.487848814780343e-06,
      "loss": 0.45,
      "step": 35745
    },
    {
      "epoch": 1.0980861978926673,
      "grad_norm": 0.39147722721099854,
      "learning_rate": 8.48737109647444e-06,
      "loss": 0.4835,
      "step": 35746
    },
    {
      "epoch": 1.0981169170276166,
      "grad_norm": 0.47096920013427734,
      "learning_rate": 8.486893381701385e-06,
      "loss": 0.4992,
      "step": 35747
    },
    {
      "epoch": 1.0981476361625657,
      "grad_norm": 0.4019244611263275,
      "learning_rate": 8.486415670462299e-06,
      "loss": 0.5011,
      "step": 35748
    },
    {
      "epoch": 1.0981783552975148,
      "grad_norm": 0.3979804217815399,
      "learning_rate": 8.485937962758292e-06,
      "loss": 0.5314,
      "step": 35749
    },
    {
      "epoch": 1.098209074432464,
      "grad_norm": 0.3613835573196411,
      "learning_rate": 8.485460258590486e-06,
      "loss": 0.4382,
      "step": 35750
    },
    {
      "epoch": 1.098239793567413,
      "grad_norm": 0.41163715720176697,
      "learning_rate": 8.48498255795999e-06,
      "loss": 0.4904,
      "step": 35751
    },
    {
      "epoch": 1.0982705127023622,
      "grad_norm": 0.36651211977005005,
      "learning_rate": 8.484504860867925e-06,
      "loss": 0.5082,
      "step": 35752
    },
    {
      "epoch": 1.0983012318373115,
      "grad_norm": 0.40548110008239746,
      "learning_rate": 8.484027167315403e-06,
      "loss": 0.464,
      "step": 35753
    },
    {
      "epoch": 1.0983319509722607,
      "grad_norm": 0.41311705112457275,
      "learning_rate": 8.483549477303544e-06,
      "loss": 0.5331,
      "step": 35754
    },
    {
      "epoch": 1.0983626701072098,
      "grad_norm": 0.39739638566970825,
      "learning_rate": 8.483071790833459e-06,
      "loss": 0.4893,
      "step": 35755
    },
    {
      "epoch": 1.098393389242159,
      "grad_norm": 0.3851813077926636,
      "learning_rate": 8.482594107906267e-06,
      "loss": 0.5419,
      "step": 35756
    },
    {
      "epoch": 1.098424108377108,
      "grad_norm": 0.41160595417022705,
      "learning_rate": 8.482116428523082e-06,
      "loss": 0.5603,
      "step": 35757
    },
    {
      "epoch": 1.0984548275120574,
      "grad_norm": 0.37808868288993835,
      "learning_rate": 8.481638752685021e-06,
      "loss": 0.4629,
      "step": 35758
    },
    {
      "epoch": 1.0984855466470065,
      "grad_norm": 0.4846690595149994,
      "learning_rate": 8.481161080393196e-06,
      "loss": 0.4137,
      "step": 35759
    },
    {
      "epoch": 1.0985162657819556,
      "grad_norm": 0.4406474828720093,
      "learning_rate": 8.48068341164873e-06,
      "loss": 0.488,
      "step": 35760
    },
    {
      "epoch": 1.0985469849169047,
      "grad_norm": 0.41852885484695435,
      "learning_rate": 8.480205746452727e-06,
      "loss": 0.4447,
      "step": 35761
    },
    {
      "epoch": 1.0985777040518538,
      "grad_norm": 0.3987368941307068,
      "learning_rate": 8.479728084806314e-06,
      "loss": 0.4965,
      "step": 35762
    },
    {
      "epoch": 1.098608423186803,
      "grad_norm": 0.4480000436306,
      "learning_rate": 8.479250426710603e-06,
      "loss": 0.4872,
      "step": 35763
    },
    {
      "epoch": 1.0986391423217523,
      "grad_norm": 0.39402398467063904,
      "learning_rate": 8.478772772166706e-06,
      "loss": 0.5188,
      "step": 35764
    },
    {
      "epoch": 1.0986698614567014,
      "grad_norm": 0.425040602684021,
      "learning_rate": 8.478295121175747e-06,
      "loss": 0.4401,
      "step": 35765
    },
    {
      "epoch": 1.0987005805916505,
      "grad_norm": 0.3994177281856537,
      "learning_rate": 8.47781747373883e-06,
      "loss": 0.5904,
      "step": 35766
    },
    {
      "epoch": 1.0987312997265997,
      "grad_norm": 0.3837502598762512,
      "learning_rate": 8.47733982985708e-06,
      "loss": 0.4106,
      "step": 35767
    },
    {
      "epoch": 1.0987620188615488,
      "grad_norm": 0.4063056707382202,
      "learning_rate": 8.476862189531606e-06,
      "loss": 0.4822,
      "step": 35768
    },
    {
      "epoch": 1.0987927379964981,
      "grad_norm": 0.4014219343662262,
      "learning_rate": 8.476384552763532e-06,
      "loss": 0.5598,
      "step": 35769
    },
    {
      "epoch": 1.0988234571314472,
      "grad_norm": 0.3782016932964325,
      "learning_rate": 8.475906919553963e-06,
      "loss": 0.4297,
      "step": 35770
    },
    {
      "epoch": 1.0988541762663964,
      "grad_norm": 0.39086228609085083,
      "learning_rate": 8.475429289904024e-06,
      "loss": 0.5547,
      "step": 35771
    },
    {
      "epoch": 1.0988848954013455,
      "grad_norm": 0.3842780590057373,
      "learning_rate": 8.474951663814824e-06,
      "loss": 0.4536,
      "step": 35772
    },
    {
      "epoch": 1.0989156145362946,
      "grad_norm": 0.37178120017051697,
      "learning_rate": 8.474474041287481e-06,
      "loss": 0.5293,
      "step": 35773
    },
    {
      "epoch": 1.0989463336712437,
      "grad_norm": 0.45206472277641296,
      "learning_rate": 8.47399642232311e-06,
      "loss": 0.4856,
      "step": 35774
    },
    {
      "epoch": 1.098977052806193,
      "grad_norm": 0.4055219888687134,
      "learning_rate": 8.473518806922827e-06,
      "loss": 0.4821,
      "step": 35775
    },
    {
      "epoch": 1.0990077719411422,
      "grad_norm": 0.3594236671924591,
      "learning_rate": 8.473041195087748e-06,
      "loss": 0.4749,
      "step": 35776
    },
    {
      "epoch": 1.0990384910760913,
      "grad_norm": 0.3537386953830719,
      "learning_rate": 8.47256358681899e-06,
      "loss": 0.4925,
      "step": 35777
    },
    {
      "epoch": 1.0990692102110404,
      "grad_norm": 0.37605682015419006,
      "learning_rate": 8.472085982117662e-06,
      "loss": 0.4289,
      "step": 35778
    },
    {
      "epoch": 1.0990999293459895,
      "grad_norm": 0.3812645673751831,
      "learning_rate": 8.471608380984887e-06,
      "loss": 0.4022,
      "step": 35779
    },
    {
      "epoch": 1.0991306484809389,
      "grad_norm": 0.4020863473415375,
      "learning_rate": 8.471130783421775e-06,
      "loss": 0.5043,
      "step": 35780
    },
    {
      "epoch": 1.099161367615888,
      "grad_norm": 0.3977010250091553,
      "learning_rate": 8.470653189429445e-06,
      "loss": 0.4961,
      "step": 35781
    },
    {
      "epoch": 1.0991920867508371,
      "grad_norm": 0.4013741612434387,
      "learning_rate": 8.470175599009012e-06,
      "loss": 0.5413,
      "step": 35782
    },
    {
      "epoch": 1.0992228058857862,
      "grad_norm": 0.3890700936317444,
      "learning_rate": 8.46969801216159e-06,
      "loss": 0.437,
      "step": 35783
    },
    {
      "epoch": 1.0992535250207354,
      "grad_norm": 0.39592093229293823,
      "learning_rate": 8.469220428888295e-06,
      "loss": 0.4843,
      "step": 35784
    },
    {
      "epoch": 1.0992842441556845,
      "grad_norm": 0.3594931364059448,
      "learning_rate": 8.468742849190244e-06,
      "loss": 0.519,
      "step": 35785
    },
    {
      "epoch": 1.0993149632906338,
      "grad_norm": 0.40429553389549255,
      "learning_rate": 8.46826527306855e-06,
      "loss": 0.4944,
      "step": 35786
    },
    {
      "epoch": 1.099345682425583,
      "grad_norm": 0.4161960482597351,
      "learning_rate": 8.46778770052433e-06,
      "loss": 0.4817,
      "step": 35787
    },
    {
      "epoch": 1.099376401560532,
      "grad_norm": 0.37570279836654663,
      "learning_rate": 8.4673101315587e-06,
      "loss": 0.4507,
      "step": 35788
    },
    {
      "epoch": 1.0994071206954812,
      "grad_norm": 0.37734538316726685,
      "learning_rate": 8.46683256617277e-06,
      "loss": 0.5627,
      "step": 35789
    },
    {
      "epoch": 1.0994378398304303,
      "grad_norm": 0.43550002574920654,
      "learning_rate": 8.466355004367664e-06,
      "loss": 0.5393,
      "step": 35790
    },
    {
      "epoch": 1.0994685589653796,
      "grad_norm": 0.389669269323349,
      "learning_rate": 8.46587744614449e-06,
      "loss": 0.4864,
      "step": 35791
    },
    {
      "epoch": 1.0994992781003288,
      "grad_norm": 0.41397035121917725,
      "learning_rate": 8.465399891504368e-06,
      "loss": 0.4977,
      "step": 35792
    },
    {
      "epoch": 1.099529997235278,
      "grad_norm": 0.4144585132598877,
      "learning_rate": 8.464922340448411e-06,
      "loss": 0.4811,
      "step": 35793
    },
    {
      "epoch": 1.099560716370227,
      "grad_norm": 0.3765220642089844,
      "learning_rate": 8.464444792977739e-06,
      "loss": 0.5075,
      "step": 35794
    },
    {
      "epoch": 1.0995914355051761,
      "grad_norm": 0.4192506968975067,
      "learning_rate": 8.463967249093457e-06,
      "loss": 0.5087,
      "step": 35795
    },
    {
      "epoch": 1.0996221546401252,
      "grad_norm": 0.40792569518089294,
      "learning_rate": 8.463489708796692e-06,
      "loss": 0.3982,
      "step": 35796
    },
    {
      "epoch": 1.0996528737750746,
      "grad_norm": 0.3574604392051697,
      "learning_rate": 8.463012172088548e-06,
      "loss": 0.4828,
      "step": 35797
    },
    {
      "epoch": 1.0996835929100237,
      "grad_norm": 0.4196889102458954,
      "learning_rate": 8.46253463897015e-06,
      "loss": 0.5303,
      "step": 35798
    },
    {
      "epoch": 1.0997143120449728,
      "grad_norm": 0.394668847322464,
      "learning_rate": 8.46205710944261e-06,
      "loss": 0.4495,
      "step": 35799
    },
    {
      "epoch": 1.099745031179922,
      "grad_norm": 0.40691277384757996,
      "learning_rate": 8.461579583507043e-06,
      "loss": 0.4947,
      "step": 35800
    },
    {
      "epoch": 1.099775750314871,
      "grad_norm": 0.41175755858421326,
      "learning_rate": 8.461102061164567e-06,
      "loss": 0.5409,
      "step": 35801
    },
    {
      "epoch": 1.0998064694498202,
      "grad_norm": 0.39661720395088196,
      "learning_rate": 8.460624542416288e-06,
      "loss": 0.4841,
      "step": 35802
    },
    {
      "epoch": 1.0998371885847695,
      "grad_norm": 0.5456371903419495,
      "learning_rate": 8.460147027263335e-06,
      "loss": 0.4362,
      "step": 35803
    },
    {
      "epoch": 1.0998679077197187,
      "grad_norm": 0.37194687128067017,
      "learning_rate": 8.45966951570681e-06,
      "loss": 0.4955,
      "step": 35804
    },
    {
      "epoch": 1.0998986268546678,
      "grad_norm": 0.40889355540275574,
      "learning_rate": 8.459192007747841e-06,
      "loss": 0.4769,
      "step": 35805
    },
    {
      "epoch": 1.099929345989617,
      "grad_norm": 0.36659929156303406,
      "learning_rate": 8.458714503387531e-06,
      "loss": 0.4878,
      "step": 35806
    },
    {
      "epoch": 1.099960065124566,
      "grad_norm": 0.39644506573677063,
      "learning_rate": 8.458237002627004e-06,
      "loss": 0.5316,
      "step": 35807
    },
    {
      "epoch": 1.0999907842595154,
      "grad_norm": 0.45338174700737,
      "learning_rate": 8.45775950546737e-06,
      "loss": 0.5697,
      "step": 35808
    },
    {
      "epoch": 1.1000215033944645,
      "grad_norm": 0.40756890177726746,
      "learning_rate": 8.45728201190975e-06,
      "loss": 0.4667,
      "step": 35809
    },
    {
      "epoch": 1.1000522225294136,
      "grad_norm": 0.4077584743499756,
      "learning_rate": 8.45680452195525e-06,
      "loss": 0.4996,
      "step": 35810
    },
    {
      "epoch": 1.1000829416643627,
      "grad_norm": 0.36648401618003845,
      "learning_rate": 8.456327035604996e-06,
      "loss": 0.5244,
      "step": 35811
    },
    {
      "epoch": 1.1001136607993118,
      "grad_norm": 0.38988783955574036,
      "learning_rate": 8.455849552860094e-06,
      "loss": 0.486,
      "step": 35812
    },
    {
      "epoch": 1.100144379934261,
      "grad_norm": 0.49888932704925537,
      "learning_rate": 8.455372073721665e-06,
      "loss": 0.4503,
      "step": 35813
    },
    {
      "epoch": 1.1001750990692103,
      "grad_norm": 0.4107951819896698,
      "learning_rate": 8.454894598190823e-06,
      "loss": 0.4979,
      "step": 35814
    },
    {
      "epoch": 1.1002058182041594,
      "grad_norm": 0.3470335006713867,
      "learning_rate": 8.454417126268683e-06,
      "loss": 0.4749,
      "step": 35815
    },
    {
      "epoch": 1.1002365373391085,
      "grad_norm": 0.4445754587650299,
      "learning_rate": 8.453939657956358e-06,
      "loss": 0.5112,
      "step": 35816
    },
    {
      "epoch": 1.1002672564740577,
      "grad_norm": 0.4096040427684784,
      "learning_rate": 8.453462193254964e-06,
      "loss": 0.5641,
      "step": 35817
    },
    {
      "epoch": 1.1002979756090068,
      "grad_norm": 0.36712267994880676,
      "learning_rate": 8.45298473216562e-06,
      "loss": 0.4003,
      "step": 35818
    },
    {
      "epoch": 1.100328694743956,
      "grad_norm": 0.42740607261657715,
      "learning_rate": 8.452507274689437e-06,
      "loss": 0.5207,
      "step": 35819
    },
    {
      "epoch": 1.1003594138789052,
      "grad_norm": 0.362922340631485,
      "learning_rate": 8.452029820827532e-06,
      "loss": 0.5178,
      "step": 35820
    },
    {
      "epoch": 1.1003901330138544,
      "grad_norm": 0.3776401877403259,
      "learning_rate": 8.451552370581018e-06,
      "loss": 0.5041,
      "step": 35821
    },
    {
      "epoch": 1.1004208521488035,
      "grad_norm": 0.4077129662036896,
      "learning_rate": 8.451074923951013e-06,
      "loss": 0.4049,
      "step": 35822
    },
    {
      "epoch": 1.1004515712837526,
      "grad_norm": 0.3805355727672577,
      "learning_rate": 8.450597480938628e-06,
      "loss": 0.4557,
      "step": 35823
    },
    {
      "epoch": 1.1004822904187017,
      "grad_norm": 0.4205757975578308,
      "learning_rate": 8.450120041544984e-06,
      "loss": 0.5998,
      "step": 35824
    },
    {
      "epoch": 1.100513009553651,
      "grad_norm": 0.3657282888889313,
      "learning_rate": 8.44964260577119e-06,
      "loss": 0.5197,
      "step": 35825
    },
    {
      "epoch": 1.1005437286886002,
      "grad_norm": 0.37460291385650635,
      "learning_rate": 8.449165173618367e-06,
      "loss": 0.4312,
      "step": 35826
    },
    {
      "epoch": 1.1005744478235493,
      "grad_norm": 0.4689743220806122,
      "learning_rate": 8.448687745087625e-06,
      "loss": 0.5024,
      "step": 35827
    },
    {
      "epoch": 1.1006051669584984,
      "grad_norm": 0.3905900716781616,
      "learning_rate": 8.448210320180086e-06,
      "loss": 0.4703,
      "step": 35828
    },
    {
      "epoch": 1.1006358860934475,
      "grad_norm": 0.47716692090034485,
      "learning_rate": 8.447732898896852e-06,
      "loss": 0.5532,
      "step": 35829
    },
    {
      "epoch": 1.1006666052283967,
      "grad_norm": 0.37631964683532715,
      "learning_rate": 8.447255481239053e-06,
      "loss": 0.5028,
      "step": 35830
    },
    {
      "epoch": 1.100697324363346,
      "grad_norm": 0.4506363868713379,
      "learning_rate": 8.446778067207792e-06,
      "loss": 0.4995,
      "step": 35831
    },
    {
      "epoch": 1.1007280434982951,
      "grad_norm": 0.3899762034416199,
      "learning_rate": 8.446300656804195e-06,
      "loss": 0.5127,
      "step": 35832
    },
    {
      "epoch": 1.1007587626332442,
      "grad_norm": 0.4284973740577698,
      "learning_rate": 8.445823250029365e-06,
      "loss": 0.4147,
      "step": 35833
    },
    {
      "epoch": 1.1007894817681934,
      "grad_norm": 0.48396870493888855,
      "learning_rate": 8.44534584688443e-06,
      "loss": 0.4816,
      "step": 35834
    },
    {
      "epoch": 1.1008202009031425,
      "grad_norm": 0.3872016370296478,
      "learning_rate": 8.444868447370494e-06,
      "loss": 0.5353,
      "step": 35835
    },
    {
      "epoch": 1.1008509200380918,
      "grad_norm": 0.3810563385486603,
      "learning_rate": 8.444391051488673e-06,
      "loss": 0.4523,
      "step": 35836
    },
    {
      "epoch": 1.100881639173041,
      "grad_norm": 0.392206072807312,
      "learning_rate": 8.443913659240093e-06,
      "loss": 0.491,
      "step": 35837
    },
    {
      "epoch": 1.10091235830799,
      "grad_norm": 0.3658769726753235,
      "learning_rate": 8.443436270625854e-06,
      "loss": 0.5615,
      "step": 35838
    },
    {
      "epoch": 1.1009430774429392,
      "grad_norm": 0.41423264145851135,
      "learning_rate": 8.442958885647086e-06,
      "loss": 0.4929,
      "step": 35839
    },
    {
      "epoch": 1.1009737965778883,
      "grad_norm": 0.34648799896240234,
      "learning_rate": 8.44248150430489e-06,
      "loss": 0.4399,
      "step": 35840
    },
    {
      "epoch": 1.1010045157128374,
      "grad_norm": 0.37969470024108887,
      "learning_rate": 8.442004126600391e-06,
      "loss": 0.5089,
      "step": 35841
    },
    {
      "epoch": 1.1010352348477868,
      "grad_norm": 0.37750357389450073,
      "learning_rate": 8.441526752534699e-06,
      "loss": 0.5065,
      "step": 35842
    },
    {
      "epoch": 1.1010659539827359,
      "grad_norm": 0.38485223054885864,
      "learning_rate": 8.441049382108931e-06,
      "loss": 0.4624,
      "step": 35843
    },
    {
      "epoch": 1.101096673117685,
      "grad_norm": 0.4197693169116974,
      "learning_rate": 8.440572015324198e-06,
      "loss": 0.5137,
      "step": 35844
    },
    {
      "epoch": 1.1011273922526341,
      "grad_norm": 0.38198933005332947,
      "learning_rate": 8.440094652181621e-06,
      "loss": 0.5052,
      "step": 35845
    },
    {
      "epoch": 1.1011581113875832,
      "grad_norm": 0.4960520267486572,
      "learning_rate": 8.439617292682309e-06,
      "loss": 0.4664,
      "step": 35846
    },
    {
      "epoch": 1.1011888305225326,
      "grad_norm": 0.40821373462677,
      "learning_rate": 8.439139936827383e-06,
      "loss": 0.4106,
      "step": 35847
    },
    {
      "epoch": 1.1012195496574817,
      "grad_norm": 0.37252166867256165,
      "learning_rate": 8.438662584617953e-06,
      "loss": 0.4592,
      "step": 35848
    },
    {
      "epoch": 1.1012502687924308,
      "grad_norm": 0.4186623990535736,
      "learning_rate": 8.438185236055137e-06,
      "loss": 0.4789,
      "step": 35849
    },
    {
      "epoch": 1.10128098792738,
      "grad_norm": 0.528617262840271,
      "learning_rate": 8.437707891140046e-06,
      "loss": 0.5442,
      "step": 35850
    },
    {
      "epoch": 1.101311707062329,
      "grad_norm": 0.3416963517665863,
      "learning_rate": 8.4372305498738e-06,
      "loss": 0.4644,
      "step": 35851
    },
    {
      "epoch": 1.1013424261972782,
      "grad_norm": 0.41425246000289917,
      "learning_rate": 8.436753212257509e-06,
      "loss": 0.5165,
      "step": 35852
    },
    {
      "epoch": 1.1013731453322275,
      "grad_norm": 0.38171151280403137,
      "learning_rate": 8.436275878292289e-06,
      "loss": 0.4682,
      "step": 35853
    },
    {
      "epoch": 1.1014038644671766,
      "grad_norm": 0.4791110157966614,
      "learning_rate": 8.435798547979259e-06,
      "loss": 0.4803,
      "step": 35854
    },
    {
      "epoch": 1.1014345836021258,
      "grad_norm": 0.3578577935695648,
      "learning_rate": 8.435321221319527e-06,
      "loss": 0.4179,
      "step": 35855
    },
    {
      "epoch": 1.1014653027370749,
      "grad_norm": 0.39939233660697937,
      "learning_rate": 8.434843898314216e-06,
      "loss": 0.5287,
      "step": 35856
    },
    {
      "epoch": 1.101496021872024,
      "grad_norm": 0.4293335974216461,
      "learning_rate": 8.434366578964433e-06,
      "loss": 0.4597,
      "step": 35857
    },
    {
      "epoch": 1.1015267410069733,
      "grad_norm": 0.5911864042282104,
      "learning_rate": 8.4338892632713e-06,
      "loss": 0.5571,
      "step": 35858
    },
    {
      "epoch": 1.1015574601419225,
      "grad_norm": 0.3811950087547302,
      "learning_rate": 8.433411951235924e-06,
      "loss": 0.5128,
      "step": 35859
    },
    {
      "epoch": 1.1015881792768716,
      "grad_norm": 0.35368743538856506,
      "learning_rate": 8.432934642859428e-06,
      "loss": 0.4598,
      "step": 35860
    },
    {
      "epoch": 1.1016188984118207,
      "grad_norm": 0.38254514336586,
      "learning_rate": 8.432457338142918e-06,
      "loss": 0.5394,
      "step": 35861
    },
    {
      "epoch": 1.1016496175467698,
      "grad_norm": 0.41690877079963684,
      "learning_rate": 8.431980037087516e-06,
      "loss": 0.5374,
      "step": 35862
    },
    {
      "epoch": 1.101680336681719,
      "grad_norm": 0.39338845014572144,
      "learning_rate": 8.431502739694333e-06,
      "loss": 0.4531,
      "step": 35863
    },
    {
      "epoch": 1.1017110558166683,
      "grad_norm": 0.414870023727417,
      "learning_rate": 8.431025445964488e-06,
      "loss": 0.4406,
      "step": 35864
    },
    {
      "epoch": 1.1017417749516174,
      "grad_norm": 0.38011273741722107,
      "learning_rate": 8.430548155899087e-06,
      "loss": 0.5468,
      "step": 35865
    },
    {
      "epoch": 1.1017724940865665,
      "grad_norm": 0.42169052362442017,
      "learning_rate": 8.430070869499257e-06,
      "loss": 0.5291,
      "step": 35866
    },
    {
      "epoch": 1.1018032132215156,
      "grad_norm": 0.36819297075271606,
      "learning_rate": 8.429593586766098e-06,
      "loss": 0.469,
      "step": 35867
    },
    {
      "epoch": 1.1018339323564648,
      "grad_norm": 0.38599807024002075,
      "learning_rate": 8.429116307700741e-06,
      "loss": 0.5101,
      "step": 35868
    },
    {
      "epoch": 1.101864651491414,
      "grad_norm": 0.4134403169155121,
      "learning_rate": 8.42863903230429e-06,
      "loss": 0.4959,
      "step": 35869
    },
    {
      "epoch": 1.1018953706263632,
      "grad_norm": 0.47375214099884033,
      "learning_rate": 8.428161760577861e-06,
      "loss": 0.478,
      "step": 35870
    },
    {
      "epoch": 1.1019260897613123,
      "grad_norm": 0.4363442063331604,
      "learning_rate": 8.42768449252257e-06,
      "loss": 0.5541,
      "step": 35871
    },
    {
      "epoch": 1.1019568088962615,
      "grad_norm": 0.3871859312057495,
      "learning_rate": 8.427207228139527e-06,
      "loss": 0.4741,
      "step": 35872
    },
    {
      "epoch": 1.1019875280312106,
      "grad_norm": 0.38364988565444946,
      "learning_rate": 8.426729967429861e-06,
      "loss": 0.4805,
      "step": 35873
    },
    {
      "epoch": 1.1020182471661597,
      "grad_norm": 0.34949439764022827,
      "learning_rate": 8.426252710394669e-06,
      "loss": 0.4595,
      "step": 35874
    },
    {
      "epoch": 1.102048966301109,
      "grad_norm": 0.3588481843471527,
      "learning_rate": 8.42577545703508e-06,
      "loss": 0.4368,
      "step": 35875
    },
    {
      "epoch": 1.1020796854360582,
      "grad_norm": 0.4324817955493927,
      "learning_rate": 8.425298207352198e-06,
      "loss": 0.513,
      "step": 35876
    },
    {
      "epoch": 1.1021104045710073,
      "grad_norm": 0.3669717311859131,
      "learning_rate": 8.424820961347144e-06,
      "loss": 0.515,
      "step": 35877
    },
    {
      "epoch": 1.1021411237059564,
      "grad_norm": 0.48963165283203125,
      "learning_rate": 8.42434371902103e-06,
      "loss": 0.4395,
      "step": 35878
    },
    {
      "epoch": 1.1021718428409055,
      "grad_norm": 0.3956102728843689,
      "learning_rate": 8.42386648037497e-06,
      "loss": 0.5011,
      "step": 35879
    },
    {
      "epoch": 1.1022025619758549,
      "grad_norm": 0.3618389666080475,
      "learning_rate": 8.423389245410081e-06,
      "loss": 0.4465,
      "step": 35880
    },
    {
      "epoch": 1.102233281110804,
      "grad_norm": 0.37363067269325256,
      "learning_rate": 8.42291201412748e-06,
      "loss": 0.469,
      "step": 35881
    },
    {
      "epoch": 1.102264000245753,
      "grad_norm": 0.4276112914085388,
      "learning_rate": 8.422434786528273e-06,
      "loss": 0.4966,
      "step": 35882
    },
    {
      "epoch": 1.1022947193807022,
      "grad_norm": 0.4311162829399109,
      "learning_rate": 8.421957562613582e-06,
      "loss": 0.4437,
      "step": 35883
    },
    {
      "epoch": 1.1023254385156513,
      "grad_norm": 0.3780519366264343,
      "learning_rate": 8.421480342384518e-06,
      "loss": 0.443,
      "step": 35884
    },
    {
      "epoch": 1.1023561576506005,
      "grad_norm": 0.4670686721801758,
      "learning_rate": 8.4210031258422e-06,
      "loss": 0.4654,
      "step": 35885
    },
    {
      "epoch": 1.1023868767855498,
      "grad_norm": 0.42800742387771606,
      "learning_rate": 8.420525912987735e-06,
      "loss": 0.4541,
      "step": 35886
    },
    {
      "epoch": 1.102417595920499,
      "grad_norm": 0.387490838766098,
      "learning_rate": 8.420048703822246e-06,
      "loss": 0.5614,
      "step": 35887
    },
    {
      "epoch": 1.102448315055448,
      "grad_norm": 0.39735427498817444,
      "learning_rate": 8.419571498346841e-06,
      "loss": 0.5143,
      "step": 35888
    },
    {
      "epoch": 1.1024790341903972,
      "grad_norm": 0.3969859480857849,
      "learning_rate": 8.419094296562637e-06,
      "loss": 0.4868,
      "step": 35889
    },
    {
      "epoch": 1.1025097533253463,
      "grad_norm": 0.44671303033828735,
      "learning_rate": 8.418617098470752e-06,
      "loss": 0.5317,
      "step": 35890
    },
    {
      "epoch": 1.1025404724602956,
      "grad_norm": 0.36406493186950684,
      "learning_rate": 8.418139904072293e-06,
      "loss": 0.4793,
      "step": 35891
    },
    {
      "epoch": 1.1025711915952447,
      "grad_norm": 0.4173063635826111,
      "learning_rate": 8.417662713368382e-06,
      "loss": 0.508,
      "step": 35892
    },
    {
      "epoch": 1.1026019107301939,
      "grad_norm": 0.379691481590271,
      "learning_rate": 8.417185526360128e-06,
      "loss": 0.4867,
      "step": 35893
    },
    {
      "epoch": 1.102632629865143,
      "grad_norm": 0.3582425117492676,
      "learning_rate": 8.416708343048649e-06,
      "loss": 0.4594,
      "step": 35894
    },
    {
      "epoch": 1.102663349000092,
      "grad_norm": 0.36989712715148926,
      "learning_rate": 8.416231163435059e-06,
      "loss": 0.4965,
      "step": 35895
    },
    {
      "epoch": 1.1026940681350412,
      "grad_norm": 0.36630451679229736,
      "learning_rate": 8.415753987520471e-06,
      "loss": 0.5331,
      "step": 35896
    },
    {
      "epoch": 1.1027247872699906,
      "grad_norm": 0.3866090476512909,
      "learning_rate": 8.415276815305998e-06,
      "loss": 0.5229,
      "step": 35897
    },
    {
      "epoch": 1.1027555064049397,
      "grad_norm": 0.377180278301239,
      "learning_rate": 8.414799646792761e-06,
      "loss": 0.4157,
      "step": 35898
    },
    {
      "epoch": 1.1027862255398888,
      "grad_norm": 0.44201329350471497,
      "learning_rate": 8.414322481981866e-06,
      "loss": 0.5361,
      "step": 35899
    },
    {
      "epoch": 1.102816944674838,
      "grad_norm": 0.3935558497905731,
      "learning_rate": 8.413845320874436e-06,
      "loss": 0.5354,
      "step": 35900
    },
    {
      "epoch": 1.102847663809787,
      "grad_norm": 0.4046335220336914,
      "learning_rate": 8.413368163471576e-06,
      "loss": 0.4487,
      "step": 35901
    },
    {
      "epoch": 1.1028783829447364,
      "grad_norm": 0.38116422295570374,
      "learning_rate": 8.41289100977441e-06,
      "loss": 0.5174,
      "step": 35902
    },
    {
      "epoch": 1.1029091020796855,
      "grad_norm": 0.4145878255367279,
      "learning_rate": 8.412413859784044e-06,
      "loss": 0.4869,
      "step": 35903
    },
    {
      "epoch": 1.1029398212146346,
      "grad_norm": 0.40598663687705994,
      "learning_rate": 8.4119367135016e-06,
      "loss": 0.4383,
      "step": 35904
    },
    {
      "epoch": 1.1029705403495838,
      "grad_norm": 0.4324440062046051,
      "learning_rate": 8.411459570928186e-06,
      "loss": 0.6042,
      "step": 35905
    },
    {
      "epoch": 1.1030012594845329,
      "grad_norm": 0.4551964998245239,
      "learning_rate": 8.41098243206492e-06,
      "loss": 0.5665,
      "step": 35906
    },
    {
      "epoch": 1.103031978619482,
      "grad_norm": 0.3824213445186615,
      "learning_rate": 8.410505296912914e-06,
      "loss": 0.4872,
      "step": 35907
    },
    {
      "epoch": 1.1030626977544313,
      "grad_norm": 0.44284793734550476,
      "learning_rate": 8.410028165473283e-06,
      "loss": 0.5155,
      "step": 35908
    },
    {
      "epoch": 1.1030934168893805,
      "grad_norm": 0.37432122230529785,
      "learning_rate": 8.409551037747148e-06,
      "loss": 0.4737,
      "step": 35909
    },
    {
      "epoch": 1.1031241360243296,
      "grad_norm": 0.4633605182170868,
      "learning_rate": 8.409073913735613e-06,
      "loss": 0.5506,
      "step": 35910
    },
    {
      "epoch": 1.1031548551592787,
      "grad_norm": 0.4009982645511627,
      "learning_rate": 8.408596793439799e-06,
      "loss": 0.5414,
      "step": 35911
    },
    {
      "epoch": 1.1031855742942278,
      "grad_norm": 0.3875066339969635,
      "learning_rate": 8.408119676860817e-06,
      "loss": 0.4546,
      "step": 35912
    },
    {
      "epoch": 1.103216293429177,
      "grad_norm": 0.37433359026908875,
      "learning_rate": 8.407642563999782e-06,
      "loss": 0.4178,
      "step": 35913
    },
    {
      "epoch": 1.1032470125641263,
      "grad_norm": 0.3803587257862091,
      "learning_rate": 8.407165454857811e-06,
      "loss": 0.5467,
      "step": 35914
    },
    {
      "epoch": 1.1032777316990754,
      "grad_norm": 0.39607834815979004,
      "learning_rate": 8.406688349436016e-06,
      "loss": 0.5345,
      "step": 35915
    },
    {
      "epoch": 1.1033084508340245,
      "grad_norm": 0.39321231842041016,
      "learning_rate": 8.40621124773551e-06,
      "loss": 0.5165,
      "step": 35916
    },
    {
      "epoch": 1.1033391699689736,
      "grad_norm": 0.37795138359069824,
      "learning_rate": 8.40573414975741e-06,
      "loss": 0.4903,
      "step": 35917
    },
    {
      "epoch": 1.1033698891039228,
      "grad_norm": 0.3808745741844177,
      "learning_rate": 8.40525705550283e-06,
      "loss": 0.5252,
      "step": 35918
    },
    {
      "epoch": 1.103400608238872,
      "grad_norm": 0.39710837602615356,
      "learning_rate": 8.404779964972882e-06,
      "loss": 0.4788,
      "step": 35919
    },
    {
      "epoch": 1.1034313273738212,
      "grad_norm": 0.39601659774780273,
      "learning_rate": 8.404302878168681e-06,
      "loss": 0.4732,
      "step": 35920
    },
    {
      "epoch": 1.1034620465087703,
      "grad_norm": 0.3728521466255188,
      "learning_rate": 8.403825795091346e-06,
      "loss": 0.5028,
      "step": 35921
    },
    {
      "epoch": 1.1034927656437195,
      "grad_norm": 0.4289679527282715,
      "learning_rate": 8.403348715741984e-06,
      "loss": 0.5619,
      "step": 35922
    },
    {
      "epoch": 1.1035234847786686,
      "grad_norm": 0.4201843738555908,
      "learning_rate": 8.402871640121715e-06,
      "loss": 0.6085,
      "step": 35923
    },
    {
      "epoch": 1.1035542039136177,
      "grad_norm": 0.38841477036476135,
      "learning_rate": 8.402394568231647e-06,
      "loss": 0.629,
      "step": 35924
    },
    {
      "epoch": 1.103584923048567,
      "grad_norm": 0.42854398488998413,
      "learning_rate": 8.401917500072902e-06,
      "loss": 0.4972,
      "step": 35925
    },
    {
      "epoch": 1.1036156421835162,
      "grad_norm": 0.4466290771961212,
      "learning_rate": 8.401440435646589e-06,
      "loss": 0.4814,
      "step": 35926
    },
    {
      "epoch": 1.1036463613184653,
      "grad_norm": 0.3830578923225403,
      "learning_rate": 8.400963374953822e-06,
      "loss": 0.4618,
      "step": 35927
    },
    {
      "epoch": 1.1036770804534144,
      "grad_norm": 0.48606258630752563,
      "learning_rate": 8.400486317995718e-06,
      "loss": 0.4866,
      "step": 35928
    },
    {
      "epoch": 1.1037077995883635,
      "grad_norm": 0.384700208902359,
      "learning_rate": 8.400009264773389e-06,
      "loss": 0.5093,
      "step": 35929
    },
    {
      "epoch": 1.1037385187233126,
      "grad_norm": 0.37173888087272644,
      "learning_rate": 8.399532215287953e-06,
      "loss": 0.5203,
      "step": 35930
    },
    {
      "epoch": 1.103769237858262,
      "grad_norm": 0.36236926913261414,
      "learning_rate": 8.399055169540518e-06,
      "loss": 0.5235,
      "step": 35931
    },
    {
      "epoch": 1.103799956993211,
      "grad_norm": 0.4035740792751312,
      "learning_rate": 8.398578127532204e-06,
      "loss": 0.4827,
      "step": 35932
    },
    {
      "epoch": 1.1038306761281602,
      "grad_norm": 0.39096617698669434,
      "learning_rate": 8.39810108926412e-06,
      "loss": 0.5142,
      "step": 35933
    },
    {
      "epoch": 1.1038613952631093,
      "grad_norm": 0.3903493583202362,
      "learning_rate": 8.397624054737386e-06,
      "loss": 0.4853,
      "step": 35934
    },
    {
      "epoch": 1.1038921143980585,
      "grad_norm": 0.5692742466926575,
      "learning_rate": 8.397147023953109e-06,
      "loss": 0.5043,
      "step": 35935
    },
    {
      "epoch": 1.1039228335330078,
      "grad_norm": 0.40619683265686035,
      "learning_rate": 8.396669996912412e-06,
      "loss": 0.5711,
      "step": 35936
    },
    {
      "epoch": 1.103953552667957,
      "grad_norm": 0.4203169047832489,
      "learning_rate": 8.396192973616398e-06,
      "loss": 0.4815,
      "step": 35937
    },
    {
      "epoch": 1.103984271802906,
      "grad_norm": 0.37934646010398865,
      "learning_rate": 8.395715954066193e-06,
      "loss": 0.5104,
      "step": 35938
    },
    {
      "epoch": 1.1040149909378552,
      "grad_norm": 0.37340110540390015,
      "learning_rate": 8.395238938262901e-06,
      "loss": 0.5014,
      "step": 35939
    },
    {
      "epoch": 1.1040457100728043,
      "grad_norm": 0.40091997385025024,
      "learning_rate": 8.394761926207646e-06,
      "loss": 0.4888,
      "step": 35940
    },
    {
      "epoch": 1.1040764292077534,
      "grad_norm": 0.36724913120269775,
      "learning_rate": 8.394284917901532e-06,
      "loss": 0.4175,
      "step": 35941
    },
    {
      "epoch": 1.1041071483427027,
      "grad_norm": 0.4412040114402771,
      "learning_rate": 8.39380791334568e-06,
      "loss": 0.5795,
      "step": 35942
    },
    {
      "epoch": 1.1041378674776519,
      "grad_norm": 0.3826271593570709,
      "learning_rate": 8.393330912541198e-06,
      "loss": 0.4577,
      "step": 35943
    },
    {
      "epoch": 1.104168586612601,
      "grad_norm": 0.405787855386734,
      "learning_rate": 8.392853915489203e-06,
      "loss": 0.4866,
      "step": 35944
    },
    {
      "epoch": 1.10419930574755,
      "grad_norm": 0.45748695731163025,
      "learning_rate": 8.392376922190818e-06,
      "loss": 0.5458,
      "step": 35945
    },
    {
      "epoch": 1.1042300248824992,
      "grad_norm": 0.43384647369384766,
      "learning_rate": 8.391899932647144e-06,
      "loss": 0.5207,
      "step": 35946
    },
    {
      "epoch": 1.1042607440174486,
      "grad_norm": 0.35714808106422424,
      "learning_rate": 8.391422946859301e-06,
      "loss": 0.4884,
      "step": 35947
    },
    {
      "epoch": 1.1042914631523977,
      "grad_norm": 0.42426788806915283,
      "learning_rate": 8.3909459648284e-06,
      "loss": 0.5375,
      "step": 35948
    },
    {
      "epoch": 1.1043221822873468,
      "grad_norm": 0.41996708512306213,
      "learning_rate": 8.39046898655556e-06,
      "loss": 0.5883,
      "step": 35949
    },
    {
      "epoch": 1.104352901422296,
      "grad_norm": 0.4124501943588257,
      "learning_rate": 8.38999201204189e-06,
      "loss": 0.5302,
      "step": 35950
    },
    {
      "epoch": 1.104383620557245,
      "grad_norm": 0.37754112482070923,
      "learning_rate": 8.389515041288507e-06,
      "loss": 0.504,
      "step": 35951
    },
    {
      "epoch": 1.1044143396921942,
      "grad_norm": 0.3814478814601898,
      "learning_rate": 8.389038074296524e-06,
      "loss": 0.6065,
      "step": 35952
    },
    {
      "epoch": 1.1044450588271435,
      "grad_norm": 0.37920960783958435,
      "learning_rate": 8.388561111067056e-06,
      "loss": 0.5117,
      "step": 35953
    },
    {
      "epoch": 1.1044757779620926,
      "grad_norm": 0.3863190710544586,
      "learning_rate": 8.388084151601213e-06,
      "loss": 0.5057,
      "step": 35954
    },
    {
      "epoch": 1.1045064970970417,
      "grad_norm": 0.3910352885723114,
      "learning_rate": 8.387607195900116e-06,
      "loss": 0.5936,
      "step": 35955
    },
    {
      "epoch": 1.1045372162319909,
      "grad_norm": 0.4784342348575592,
      "learning_rate": 8.387130243964872e-06,
      "loss": 0.4401,
      "step": 35956
    },
    {
      "epoch": 1.10456793536694,
      "grad_norm": 0.37744179368019104,
      "learning_rate": 8.386653295796599e-06,
      "loss": 0.462,
      "step": 35957
    },
    {
      "epoch": 1.1045986545018893,
      "grad_norm": 0.3911671042442322,
      "learning_rate": 8.38617635139641e-06,
      "loss": 0.4985,
      "step": 35958
    },
    {
      "epoch": 1.1046293736368384,
      "grad_norm": 0.4157850444316864,
      "learning_rate": 8.38569941076542e-06,
      "loss": 0.4825,
      "step": 35959
    },
    {
      "epoch": 1.1046600927717876,
      "grad_norm": 0.39634665846824646,
      "learning_rate": 8.38522247390474e-06,
      "loss": 0.5257,
      "step": 35960
    },
    {
      "epoch": 1.1046908119067367,
      "grad_norm": 0.43078500032424927,
      "learning_rate": 8.38474554081549e-06,
      "loss": 0.5469,
      "step": 35961
    },
    {
      "epoch": 1.1047215310416858,
      "grad_norm": 0.37517473101615906,
      "learning_rate": 8.384268611498771e-06,
      "loss": 0.5003,
      "step": 35962
    },
    {
      "epoch": 1.104752250176635,
      "grad_norm": 0.3730398416519165,
      "learning_rate": 8.383791685955708e-06,
      "loss": 0.5268,
      "step": 35963
    },
    {
      "epoch": 1.1047829693115843,
      "grad_norm": 0.34759533405303955,
      "learning_rate": 8.383314764187418e-06,
      "loss": 0.5039,
      "step": 35964
    },
    {
      "epoch": 1.1048136884465334,
      "grad_norm": 0.38700270652770996,
      "learning_rate": 8.382837846195005e-06,
      "loss": 0.4867,
      "step": 35965
    },
    {
      "epoch": 1.1048444075814825,
      "grad_norm": 0.3820338845252991,
      "learning_rate": 8.382360931979588e-06,
      "loss": 0.4664,
      "step": 35966
    },
    {
      "epoch": 1.1048751267164316,
      "grad_norm": 0.3378138244152069,
      "learning_rate": 8.381884021542279e-06,
      "loss": 0.4668,
      "step": 35967
    },
    {
      "epoch": 1.1049058458513807,
      "grad_norm": 0.390704482793808,
      "learning_rate": 8.381407114884198e-06,
      "loss": 0.4732,
      "step": 35968
    },
    {
      "epoch": 1.10493656498633,
      "grad_norm": 0.39859315752983093,
      "learning_rate": 8.380930212006446e-06,
      "loss": 0.4606,
      "step": 35969
    },
    {
      "epoch": 1.1049672841212792,
      "grad_norm": 0.40205711126327515,
      "learning_rate": 8.380453312910151e-06,
      "loss": 0.4646,
      "step": 35970
    },
    {
      "epoch": 1.1049980032562283,
      "grad_norm": 0.45399606227874756,
      "learning_rate": 8.379976417596417e-06,
      "loss": 0.4529,
      "step": 35971
    },
    {
      "epoch": 1.1050287223911774,
      "grad_norm": 0.4020051658153534,
      "learning_rate": 8.379499526066364e-06,
      "loss": 0.4826,
      "step": 35972
    },
    {
      "epoch": 1.1050594415261266,
      "grad_norm": 0.4312158524990082,
      "learning_rate": 8.379022638321097e-06,
      "loss": 0.5892,
      "step": 35973
    },
    {
      "epoch": 1.1050901606610757,
      "grad_norm": 0.39058083295822144,
      "learning_rate": 8.378545754361743e-06,
      "loss": 0.5337,
      "step": 35974
    },
    {
      "epoch": 1.105120879796025,
      "grad_norm": 0.39482152462005615,
      "learning_rate": 8.378068874189404e-06,
      "loss": 0.4673,
      "step": 35975
    },
    {
      "epoch": 1.1051515989309741,
      "grad_norm": 0.34891828894615173,
      "learning_rate": 8.377591997805203e-06,
      "loss": 0.505,
      "step": 35976
    },
    {
      "epoch": 1.1051823180659233,
      "grad_norm": 0.3727254271507263,
      "learning_rate": 8.377115125210244e-06,
      "loss": 0.4955,
      "step": 35977
    },
    {
      "epoch": 1.1052130372008724,
      "grad_norm": 0.4456183910369873,
      "learning_rate": 8.37663825640565e-06,
      "loss": 0.4575,
      "step": 35978
    },
    {
      "epoch": 1.1052437563358215,
      "grad_norm": 0.48625707626342773,
      "learning_rate": 8.376161391392527e-06,
      "loss": 0.5623,
      "step": 35979
    },
    {
      "epoch": 1.1052744754707708,
      "grad_norm": 0.3761940002441406,
      "learning_rate": 8.375684530171994e-06,
      "loss": 0.4961,
      "step": 35980
    },
    {
      "epoch": 1.10530519460572,
      "grad_norm": 0.3994525671005249,
      "learning_rate": 8.375207672745164e-06,
      "loss": 0.5028,
      "step": 35981
    },
    {
      "epoch": 1.105335913740669,
      "grad_norm": 0.44104906916618347,
      "learning_rate": 8.374730819113149e-06,
      "loss": 0.55,
      "step": 35982
    },
    {
      "epoch": 1.1053666328756182,
      "grad_norm": 0.3744979798793793,
      "learning_rate": 8.374253969277064e-06,
      "loss": 0.5165,
      "step": 35983
    },
    {
      "epoch": 1.1053973520105673,
      "grad_norm": 0.3857613801956177,
      "learning_rate": 8.373777123238022e-06,
      "loss": 0.506,
      "step": 35984
    },
    {
      "epoch": 1.1054280711455164,
      "grad_norm": 0.4247254729270935,
      "learning_rate": 8.37330028099714e-06,
      "loss": 0.5292,
      "step": 35985
    },
    {
      "epoch": 1.1054587902804658,
      "grad_norm": 0.4045582711696625,
      "learning_rate": 8.372823442555523e-06,
      "loss": 0.5163,
      "step": 35986
    },
    {
      "epoch": 1.105489509415415,
      "grad_norm": 0.3658778965473175,
      "learning_rate": 8.372346607914296e-06,
      "loss": 0.4374,
      "step": 35987
    },
    {
      "epoch": 1.105520228550364,
      "grad_norm": 0.3616500198841095,
      "learning_rate": 8.371869777074564e-06,
      "loss": 0.4904,
      "step": 35988
    },
    {
      "epoch": 1.1055509476853131,
      "grad_norm": 0.5530361533164978,
      "learning_rate": 8.371392950037447e-06,
      "loss": 0.4954,
      "step": 35989
    },
    {
      "epoch": 1.1055816668202623,
      "grad_norm": 0.39292407035827637,
      "learning_rate": 8.370916126804051e-06,
      "loss": 0.4543,
      "step": 35990
    },
    {
      "epoch": 1.1056123859552116,
      "grad_norm": 0.37033191323280334,
      "learning_rate": 8.370439307375497e-06,
      "loss": 0.4437,
      "step": 35991
    },
    {
      "epoch": 1.1056431050901607,
      "grad_norm": 0.4032454490661621,
      "learning_rate": 8.369962491752894e-06,
      "loss": 0.4661,
      "step": 35992
    },
    {
      "epoch": 1.1056738242251098,
      "grad_norm": 0.42623287439346313,
      "learning_rate": 8.369485679937361e-06,
      "loss": 0.4664,
      "step": 35993
    },
    {
      "epoch": 1.105704543360059,
      "grad_norm": 0.361191064119339,
      "learning_rate": 8.369008871930004e-06,
      "loss": 0.5142,
      "step": 35994
    },
    {
      "epoch": 1.105735262495008,
      "grad_norm": 0.39197301864624023,
      "learning_rate": 8.368532067731943e-06,
      "loss": 0.5162,
      "step": 35995
    },
    {
      "epoch": 1.1057659816299572,
      "grad_norm": 0.39131927490234375,
      "learning_rate": 8.368055267344288e-06,
      "loss": 0.4933,
      "step": 35996
    },
    {
      "epoch": 1.1057967007649065,
      "grad_norm": 0.42218586802482605,
      "learning_rate": 8.367578470768158e-06,
      "loss": 0.5602,
      "step": 35997
    },
    {
      "epoch": 1.1058274198998557,
      "grad_norm": 0.3945823311805725,
      "learning_rate": 8.367101678004657e-06,
      "loss": 0.4413,
      "step": 35998
    },
    {
      "epoch": 1.1058581390348048,
      "grad_norm": 0.41062772274017334,
      "learning_rate": 8.366624889054905e-06,
      "loss": 0.4985,
      "step": 35999
    },
    {
      "epoch": 1.105888858169754,
      "grad_norm": 0.4109916388988495,
      "learning_rate": 8.366148103920018e-06,
      "loss": 0.5403,
      "step": 36000
    },
    {
      "epoch": 1.105919577304703,
      "grad_norm": 0.41992124915122986,
      "learning_rate": 8.365671322601101e-06,
      "loss": 0.4821,
      "step": 36001
    },
    {
      "epoch": 1.1059502964396524,
      "grad_norm": 0.42250344157218933,
      "learning_rate": 8.36519454509928e-06,
      "loss": 0.4829,
      "step": 36002
    },
    {
      "epoch": 1.1059810155746015,
      "grad_norm": 0.38795584440231323,
      "learning_rate": 8.364717771415654e-06,
      "loss": 0.52,
      "step": 36003
    },
    {
      "epoch": 1.1060117347095506,
      "grad_norm": 0.3979661762714386,
      "learning_rate": 8.36424100155135e-06,
      "loss": 0.45,
      "step": 36004
    },
    {
      "epoch": 1.1060424538444997,
      "grad_norm": 0.36886486411094666,
      "learning_rate": 8.36376423550747e-06,
      "loss": 0.4247,
      "step": 36005
    },
    {
      "epoch": 1.1060731729794488,
      "grad_norm": 0.4245639145374298,
      "learning_rate": 8.363287473285139e-06,
      "loss": 0.552,
      "step": 36006
    },
    {
      "epoch": 1.106103892114398,
      "grad_norm": 0.39312711358070374,
      "learning_rate": 8.362810714885458e-06,
      "loss": 0.5192,
      "step": 36007
    },
    {
      "epoch": 1.1061346112493473,
      "grad_norm": 0.42761367559432983,
      "learning_rate": 8.362333960309551e-06,
      "loss": 0.4685,
      "step": 36008
    },
    {
      "epoch": 1.1061653303842964,
      "grad_norm": 0.38684895634651184,
      "learning_rate": 8.361857209558526e-06,
      "loss": 0.4512,
      "step": 36009
    },
    {
      "epoch": 1.1061960495192456,
      "grad_norm": 0.3965528905391693,
      "learning_rate": 8.3613804626335e-06,
      "loss": 0.5,
      "step": 36010
    },
    {
      "epoch": 1.1062267686541947,
      "grad_norm": 0.45653900504112244,
      "learning_rate": 8.360903719535581e-06,
      "loss": 0.4816,
      "step": 36011
    },
    {
      "epoch": 1.1062574877891438,
      "grad_norm": 0.41176676750183105,
      "learning_rate": 8.360426980265888e-06,
      "loss": 0.4123,
      "step": 36012
    },
    {
      "epoch": 1.1062882069240931,
      "grad_norm": 0.39973896741867065,
      "learning_rate": 8.35995024482553e-06,
      "loss": 0.5503,
      "step": 36013
    },
    {
      "epoch": 1.1063189260590423,
      "grad_norm": 0.43360474705696106,
      "learning_rate": 8.359473513215626e-06,
      "loss": 0.5327,
      "step": 36014
    },
    {
      "epoch": 1.1063496451939914,
      "grad_norm": 0.37811824679374695,
      "learning_rate": 8.358996785437284e-06,
      "loss": 0.4612,
      "step": 36015
    },
    {
      "epoch": 1.1063803643289405,
      "grad_norm": 0.3932754397392273,
      "learning_rate": 8.35852006149162e-06,
      "loss": 0.4625,
      "step": 36016
    },
    {
      "epoch": 1.1064110834638896,
      "grad_norm": 0.3634997606277466,
      "learning_rate": 8.358043341379748e-06,
      "loss": 0.5015,
      "step": 36017
    },
    {
      "epoch": 1.1064418025988387,
      "grad_norm": 0.3885595500469208,
      "learning_rate": 8.357566625102776e-06,
      "loss": 0.4414,
      "step": 36018
    },
    {
      "epoch": 1.106472521733788,
      "grad_norm": 0.4374626576900482,
      "learning_rate": 8.357089912661827e-06,
      "loss": 0.4908,
      "step": 36019
    },
    {
      "epoch": 1.1065032408687372,
      "grad_norm": 0.3991006910800934,
      "learning_rate": 8.356613204058007e-06,
      "loss": 0.4467,
      "step": 36020
    },
    {
      "epoch": 1.1065339600036863,
      "grad_norm": 0.38146254420280457,
      "learning_rate": 8.356136499292434e-06,
      "loss": 0.4528,
      "step": 36021
    },
    {
      "epoch": 1.1065646791386354,
      "grad_norm": 0.3758035898208618,
      "learning_rate": 8.355659798366215e-06,
      "loss": 0.5137,
      "step": 36022
    },
    {
      "epoch": 1.1065953982735846,
      "grad_norm": 0.40403279662132263,
      "learning_rate": 8.355183101280471e-06,
      "loss": 0.4766,
      "step": 36023
    },
    {
      "epoch": 1.106626117408534,
      "grad_norm": 0.3778131902217865,
      "learning_rate": 8.354706408036309e-06,
      "loss": 0.4654,
      "step": 36024
    },
    {
      "epoch": 1.106656836543483,
      "grad_norm": 0.37108275294303894,
      "learning_rate": 8.354229718634848e-06,
      "loss": 0.5171,
      "step": 36025
    },
    {
      "epoch": 1.1066875556784321,
      "grad_norm": 0.4121716022491455,
      "learning_rate": 8.353753033077197e-06,
      "loss": 0.4835,
      "step": 36026
    },
    {
      "epoch": 1.1067182748133813,
      "grad_norm": 0.4207612872123718,
      "learning_rate": 8.35327635136447e-06,
      "loss": 0.4991,
      "step": 36027
    },
    {
      "epoch": 1.1067489939483304,
      "grad_norm": 0.4134810268878937,
      "learning_rate": 8.352799673497782e-06,
      "loss": 0.4597,
      "step": 36028
    },
    {
      "epoch": 1.1067797130832795,
      "grad_norm": 0.4123743176460266,
      "learning_rate": 8.352322999478246e-06,
      "loss": 0.5986,
      "step": 36029
    },
    {
      "epoch": 1.1068104322182288,
      "grad_norm": 0.40018242597579956,
      "learning_rate": 8.351846329306973e-06,
      "loss": 0.4478,
      "step": 36030
    },
    {
      "epoch": 1.106841151353178,
      "grad_norm": 0.42322254180908203,
      "learning_rate": 8.351369662985081e-06,
      "loss": 0.4115,
      "step": 36031
    },
    {
      "epoch": 1.106871870488127,
      "grad_norm": 0.4519776999950409,
      "learning_rate": 8.350893000513675e-06,
      "loss": 0.4255,
      "step": 36032
    },
    {
      "epoch": 1.1069025896230762,
      "grad_norm": 0.4221128523349762,
      "learning_rate": 8.350416341893881e-06,
      "loss": 0.4569,
      "step": 36033
    },
    {
      "epoch": 1.1069333087580253,
      "grad_norm": 0.3769068419933319,
      "learning_rate": 8.349939687126797e-06,
      "loss": 0.5402,
      "step": 36034
    },
    {
      "epoch": 1.1069640278929744,
      "grad_norm": 0.37720635533332825,
      "learning_rate": 8.349463036213546e-06,
      "loss": 0.4546,
      "step": 36035
    },
    {
      "epoch": 1.1069947470279238,
      "grad_norm": 0.40599656105041504,
      "learning_rate": 8.348986389155243e-06,
      "loss": 0.4729,
      "step": 36036
    },
    {
      "epoch": 1.107025466162873,
      "grad_norm": 0.42829564213752747,
      "learning_rate": 8.348509745952993e-06,
      "loss": 0.5532,
      "step": 36037
    },
    {
      "epoch": 1.107056185297822,
      "grad_norm": 0.3665543496608734,
      "learning_rate": 8.348033106607921e-06,
      "loss": 0.579,
      "step": 36038
    },
    {
      "epoch": 1.1070869044327711,
      "grad_norm": 0.39286288619041443,
      "learning_rate": 8.347556471121125e-06,
      "loss": 0.4259,
      "step": 36039
    },
    {
      "epoch": 1.1071176235677203,
      "grad_norm": 0.4396795332431793,
      "learning_rate": 8.347079839493733e-06,
      "loss": 0.5109,
      "step": 36040
    },
    {
      "epoch": 1.1071483427026696,
      "grad_norm": 0.3669690489768982,
      "learning_rate": 8.346603211726846e-06,
      "loss": 0.4517,
      "step": 36041
    },
    {
      "epoch": 1.1071790618376187,
      "grad_norm": 0.3762078285217285,
      "learning_rate": 8.346126587821588e-06,
      "loss": 0.4989,
      "step": 36042
    },
    {
      "epoch": 1.1072097809725678,
      "grad_norm": 0.41516783833503723,
      "learning_rate": 8.345649967779062e-06,
      "loss": 0.4695,
      "step": 36043
    },
    {
      "epoch": 1.107240500107517,
      "grad_norm": 0.39295995235443115,
      "learning_rate": 8.34517335160039e-06,
      "loss": 0.441,
      "step": 36044
    },
    {
      "epoch": 1.107271219242466,
      "grad_norm": 0.4312859773635864,
      "learning_rate": 8.344696739286678e-06,
      "loss": 0.5098,
      "step": 36045
    },
    {
      "epoch": 1.1073019383774152,
      "grad_norm": 0.4022170901298523,
      "learning_rate": 8.344220130839043e-06,
      "loss": 0.5553,
      "step": 36046
    },
    {
      "epoch": 1.1073326575123645,
      "grad_norm": 0.3637503683567047,
      "learning_rate": 8.343743526258597e-06,
      "loss": 0.5019,
      "step": 36047
    },
    {
      "epoch": 1.1073633766473137,
      "grad_norm": 0.4276292622089386,
      "learning_rate": 8.343266925546456e-06,
      "loss": 0.5275,
      "step": 36048
    },
    {
      "epoch": 1.1073940957822628,
      "grad_norm": 0.4094916880130768,
      "learning_rate": 8.342790328703729e-06,
      "loss": 0.4897,
      "step": 36049
    },
    {
      "epoch": 1.107424814917212,
      "grad_norm": 0.3652860224246979,
      "learning_rate": 8.342313735731532e-06,
      "loss": 0.5527,
      "step": 36050
    },
    {
      "epoch": 1.107455534052161,
      "grad_norm": 0.42745107412338257,
      "learning_rate": 8.341837146630976e-06,
      "loss": 0.5652,
      "step": 36051
    },
    {
      "epoch": 1.1074862531871101,
      "grad_norm": 0.3948643207550049,
      "learning_rate": 8.341360561403175e-06,
      "loss": 0.514,
      "step": 36052
    },
    {
      "epoch": 1.1075169723220595,
      "grad_norm": 0.43636420369148254,
      "learning_rate": 8.340883980049243e-06,
      "loss": 0.4946,
      "step": 36053
    },
    {
      "epoch": 1.1075476914570086,
      "grad_norm": 0.380952924489975,
      "learning_rate": 8.34040740257029e-06,
      "loss": 0.5286,
      "step": 36054
    },
    {
      "epoch": 1.1075784105919577,
      "grad_norm": 0.36619648337364197,
      "learning_rate": 8.339930828967435e-06,
      "loss": 0.4886,
      "step": 36055
    },
    {
      "epoch": 1.1076091297269068,
      "grad_norm": 0.37952256202697754,
      "learning_rate": 8.339454259241785e-06,
      "loss": 0.4719,
      "step": 36056
    },
    {
      "epoch": 1.107639848861856,
      "grad_norm": 0.42208656668663025,
      "learning_rate": 8.338977693394459e-06,
      "loss": 0.4898,
      "step": 36057
    },
    {
      "epoch": 1.1076705679968053,
      "grad_norm": 0.4105800688266754,
      "learning_rate": 8.338501131426561e-06,
      "loss": 0.3942,
      "step": 36058
    },
    {
      "epoch": 1.1077012871317544,
      "grad_norm": 0.38611671328544617,
      "learning_rate": 8.338024573339215e-06,
      "loss": 0.5236,
      "step": 36059
    },
    {
      "epoch": 1.1077320062667035,
      "grad_norm": 0.3679158687591553,
      "learning_rate": 8.337548019133526e-06,
      "loss": 0.5197,
      "step": 36060
    },
    {
      "epoch": 1.1077627254016527,
      "grad_norm": 0.38648855686187744,
      "learning_rate": 8.337071468810611e-06,
      "loss": 0.4889,
      "step": 36061
    },
    {
      "epoch": 1.1077934445366018,
      "grad_norm": 0.44059085845947266,
      "learning_rate": 8.336594922371579e-06,
      "loss": 0.4795,
      "step": 36062
    },
    {
      "epoch": 1.107824163671551,
      "grad_norm": 0.37881630659103394,
      "learning_rate": 8.33611837981755e-06,
      "loss": 0.5582,
      "step": 36063
    },
    {
      "epoch": 1.1078548828065002,
      "grad_norm": 0.3807840049266815,
      "learning_rate": 8.335641841149628e-06,
      "loss": 0.5429,
      "step": 36064
    },
    {
      "epoch": 1.1078856019414494,
      "grad_norm": 0.405499666929245,
      "learning_rate": 8.335165306368936e-06,
      "loss": 0.4949,
      "step": 36065
    },
    {
      "epoch": 1.1079163210763985,
      "grad_norm": 0.3946492373943329,
      "learning_rate": 8.334688775476577e-06,
      "loss": 0.4839,
      "step": 36066
    },
    {
      "epoch": 1.1079470402113476,
      "grad_norm": 0.4237247109413147,
      "learning_rate": 8.334212248473673e-06,
      "loss": 0.4822,
      "step": 36067
    },
    {
      "epoch": 1.1079777593462967,
      "grad_norm": 0.4275304675102234,
      "learning_rate": 8.333735725361327e-06,
      "loss": 0.477,
      "step": 36068
    },
    {
      "epoch": 1.108008478481246,
      "grad_norm": 0.38245460391044617,
      "learning_rate": 8.333259206140663e-06,
      "loss": 0.4986,
      "step": 36069
    },
    {
      "epoch": 1.1080391976161952,
      "grad_norm": 0.39668262004852295,
      "learning_rate": 8.332782690812784e-06,
      "loss": 0.4583,
      "step": 36070
    },
    {
      "epoch": 1.1080699167511443,
      "grad_norm": 0.38994744420051575,
      "learning_rate": 8.332306179378813e-06,
      "loss": 0.5119,
      "step": 36071
    },
    {
      "epoch": 1.1081006358860934,
      "grad_norm": 0.40309712290763855,
      "learning_rate": 8.331829671839852e-06,
      "loss": 0.5604,
      "step": 36072
    },
    {
      "epoch": 1.1081313550210425,
      "grad_norm": 0.3699771463871002,
      "learning_rate": 8.331353168197019e-06,
      "loss": 0.504,
      "step": 36073
    },
    {
      "epoch": 1.1081620741559917,
      "grad_norm": 0.387967586517334,
      "learning_rate": 8.330876668451434e-06,
      "loss": 0.4633,
      "step": 36074
    },
    {
      "epoch": 1.108192793290941,
      "grad_norm": 0.4050954282283783,
      "learning_rate": 8.330400172604194e-06,
      "loss": 0.5128,
      "step": 36075
    },
    {
      "epoch": 1.1082235124258901,
      "grad_norm": 0.4015730619430542,
      "learning_rate": 8.32992368065643e-06,
      "loss": 0.4261,
      "step": 36076
    },
    {
      "epoch": 1.1082542315608392,
      "grad_norm": 0.3518688976764679,
      "learning_rate": 8.329447192609236e-06,
      "loss": 0.4323,
      "step": 36077
    },
    {
      "epoch": 1.1082849506957884,
      "grad_norm": 0.3957396149635315,
      "learning_rate": 8.328970708463745e-06,
      "loss": 0.4871,
      "step": 36078
    },
    {
      "epoch": 1.1083156698307375,
      "grad_norm": 0.41756609082221985,
      "learning_rate": 8.328494228221054e-06,
      "loss": 0.6128,
      "step": 36079
    },
    {
      "epoch": 1.1083463889656868,
      "grad_norm": 0.4050573408603668,
      "learning_rate": 8.328017751882282e-06,
      "loss": 0.5205,
      "step": 36080
    },
    {
      "epoch": 1.108377108100636,
      "grad_norm": 0.4316193461418152,
      "learning_rate": 8.327541279448541e-06,
      "loss": 0.4161,
      "step": 36081
    },
    {
      "epoch": 1.108407827235585,
      "grad_norm": 0.4184597432613373,
      "learning_rate": 8.327064810920946e-06,
      "loss": 0.5312,
      "step": 36082
    },
    {
      "epoch": 1.1084385463705342,
      "grad_norm": 0.38824647665023804,
      "learning_rate": 8.326588346300606e-06,
      "loss": 0.4407,
      "step": 36083
    },
    {
      "epoch": 1.1084692655054833,
      "grad_norm": 0.4096281826496124,
      "learning_rate": 8.326111885588638e-06,
      "loss": 0.5443,
      "step": 36084
    },
    {
      "epoch": 1.1084999846404324,
      "grad_norm": 0.4032398462295532,
      "learning_rate": 8.32563542878615e-06,
      "loss": 0.4578,
      "step": 36085
    },
    {
      "epoch": 1.1085307037753818,
      "grad_norm": 0.42259809374809265,
      "learning_rate": 8.32515897589426e-06,
      "loss": 0.4508,
      "step": 36086
    },
    {
      "epoch": 1.1085614229103309,
      "grad_norm": 0.41574063897132874,
      "learning_rate": 8.324682526914074e-06,
      "loss": 0.5606,
      "step": 36087
    },
    {
      "epoch": 1.10859214204528,
      "grad_norm": 0.44908973574638367,
      "learning_rate": 8.324206081846714e-06,
      "loss": 0.4489,
      "step": 36088
    },
    {
      "epoch": 1.1086228611802291,
      "grad_norm": 0.3948613703250885,
      "learning_rate": 8.323729640693284e-06,
      "loss": 0.5265,
      "step": 36089
    },
    {
      "epoch": 1.1086535803151782,
      "grad_norm": 0.4630931615829468,
      "learning_rate": 8.323253203454902e-06,
      "loss": 0.4509,
      "step": 36090
    },
    {
      "epoch": 1.1086842994501276,
      "grad_norm": 0.3865891695022583,
      "learning_rate": 8.32277677013268e-06,
      "loss": 0.4792,
      "step": 36091
    },
    {
      "epoch": 1.1087150185850767,
      "grad_norm": 0.39497140049934387,
      "learning_rate": 8.322300340727727e-06,
      "loss": 0.4008,
      "step": 36092
    },
    {
      "epoch": 1.1087457377200258,
      "grad_norm": 0.44395217299461365,
      "learning_rate": 8.321823915241163e-06,
      "loss": 0.4661,
      "step": 36093
    },
    {
      "epoch": 1.108776456854975,
      "grad_norm": 0.43377920985221863,
      "learning_rate": 8.321347493674093e-06,
      "loss": 0.4511,
      "step": 36094
    },
    {
      "epoch": 1.108807175989924,
      "grad_norm": 0.38940221071243286,
      "learning_rate": 8.320871076027635e-06,
      "loss": 0.5539,
      "step": 36095
    },
    {
      "epoch": 1.1088378951248732,
      "grad_norm": 0.4075993597507477,
      "learning_rate": 8.3203946623029e-06,
      "loss": 0.4888,
      "step": 36096
    },
    {
      "epoch": 1.1088686142598225,
      "grad_norm": 0.4136408269405365,
      "learning_rate": 8.319918252501e-06,
      "loss": 0.5398,
      "step": 36097
    },
    {
      "epoch": 1.1088993333947716,
      "grad_norm": 0.405692458152771,
      "learning_rate": 8.319441846623047e-06,
      "loss": 0.4803,
      "step": 36098
    },
    {
      "epoch": 1.1089300525297208,
      "grad_norm": 0.393646240234375,
      "learning_rate": 8.318965444670158e-06,
      "loss": 0.504,
      "step": 36099
    },
    {
      "epoch": 1.1089607716646699,
      "grad_norm": 0.42132315039634705,
      "learning_rate": 8.318489046643438e-06,
      "loss": 0.5625,
      "step": 36100
    },
    {
      "epoch": 1.108991490799619,
      "grad_norm": 0.3890664279460907,
      "learning_rate": 8.318012652544012e-06,
      "loss": 0.4923,
      "step": 36101
    },
    {
      "epoch": 1.1090222099345683,
      "grad_norm": 0.4295024573802948,
      "learning_rate": 8.317536262372977e-06,
      "loss": 0.5361,
      "step": 36102
    },
    {
      "epoch": 1.1090529290695175,
      "grad_norm": 0.3635393977165222,
      "learning_rate": 8.31705987613146e-06,
      "loss": 0.4622,
      "step": 36103
    },
    {
      "epoch": 1.1090836482044666,
      "grad_norm": 0.4488576352596283,
      "learning_rate": 8.316583493820558e-06,
      "loss": 0.4703,
      "step": 36104
    },
    {
      "epoch": 1.1091143673394157,
      "grad_norm": 0.3948436975479126,
      "learning_rate": 8.316107115441403e-06,
      "loss": 0.4638,
      "step": 36105
    },
    {
      "epoch": 1.1091450864743648,
      "grad_norm": 0.3923354744911194,
      "learning_rate": 8.315630740995092e-06,
      "loss": 0.4884,
      "step": 36106
    },
    {
      "epoch": 1.109175805609314,
      "grad_norm": 0.39768263697624207,
      "learning_rate": 8.315154370482745e-06,
      "loss": 0.5121,
      "step": 36107
    },
    {
      "epoch": 1.1092065247442633,
      "grad_norm": 0.36457371711730957,
      "learning_rate": 8.31467800390547e-06,
      "loss": 0.4374,
      "step": 36108
    },
    {
      "epoch": 1.1092372438792124,
      "grad_norm": 0.41037625074386597,
      "learning_rate": 8.31420164126438e-06,
      "loss": 0.556,
      "step": 36109
    },
    {
      "epoch": 1.1092679630141615,
      "grad_norm": 0.4013737142086029,
      "learning_rate": 8.3137252825606e-06,
      "loss": 0.4866,
      "step": 36110
    },
    {
      "epoch": 1.1092986821491106,
      "grad_norm": 0.3926120102405548,
      "learning_rate": 8.313248927795221e-06,
      "loss": 0.5303,
      "step": 36111
    },
    {
      "epoch": 1.1093294012840598,
      "grad_norm": 0.5801867842674255,
      "learning_rate": 8.312772576969375e-06,
      "loss": 0.4245,
      "step": 36112
    },
    {
      "epoch": 1.109360120419009,
      "grad_norm": 0.36844515800476074,
      "learning_rate": 8.312296230084163e-06,
      "loss": 0.5309,
      "step": 36113
    },
    {
      "epoch": 1.1093908395539582,
      "grad_norm": 0.4004768133163452,
      "learning_rate": 8.311819887140702e-06,
      "loss": 0.4615,
      "step": 36114
    },
    {
      "epoch": 1.1094215586889073,
      "grad_norm": 0.4014149308204651,
      "learning_rate": 8.311343548140101e-06,
      "loss": 0.4331,
      "step": 36115
    },
    {
      "epoch": 1.1094522778238565,
      "grad_norm": 0.4333304166793823,
      "learning_rate": 8.31086721308348e-06,
      "loss": 0.46,
      "step": 36116
    },
    {
      "epoch": 1.1094829969588056,
      "grad_norm": 0.417203813791275,
      "learning_rate": 8.310390881971942e-06,
      "loss": 0.4731,
      "step": 36117
    },
    {
      "epoch": 1.1095137160937547,
      "grad_norm": 0.4090697169303894,
      "learning_rate": 8.309914554806606e-06,
      "loss": 0.4629,
      "step": 36118
    },
    {
      "epoch": 1.109544435228704,
      "grad_norm": 0.386857807636261,
      "learning_rate": 8.309438231588582e-06,
      "loss": 0.4964,
      "step": 36119
    },
    {
      "epoch": 1.1095751543636532,
      "grad_norm": 0.3709237277507782,
      "learning_rate": 8.308961912318985e-06,
      "loss": 0.4726,
      "step": 36120
    },
    {
      "epoch": 1.1096058734986023,
      "grad_norm": 0.3640683889389038,
      "learning_rate": 8.308485596998922e-06,
      "loss": 0.4321,
      "step": 36121
    },
    {
      "epoch": 1.1096365926335514,
      "grad_norm": 0.37957704067230225,
      "learning_rate": 8.308009285629512e-06,
      "loss": 0.523,
      "step": 36122
    },
    {
      "epoch": 1.1096673117685005,
      "grad_norm": 0.3990994989871979,
      "learning_rate": 8.307532978211863e-06,
      "loss": 0.4752,
      "step": 36123
    },
    {
      "epoch": 1.1096980309034499,
      "grad_norm": 0.4026382565498352,
      "learning_rate": 8.30705667474709e-06,
      "loss": 0.4762,
      "step": 36124
    },
    {
      "epoch": 1.109728750038399,
      "grad_norm": 0.7368397116661072,
      "learning_rate": 8.306580375236303e-06,
      "loss": 0.48,
      "step": 36125
    },
    {
      "epoch": 1.1097594691733481,
      "grad_norm": 0.40987107157707214,
      "learning_rate": 8.306104079680617e-06,
      "loss": 0.4833,
      "step": 36126
    },
    {
      "epoch": 1.1097901883082972,
      "grad_norm": 0.38688069581985474,
      "learning_rate": 8.305627788081143e-06,
      "loss": 0.4647,
      "step": 36127
    },
    {
      "epoch": 1.1098209074432464,
      "grad_norm": 0.3814372420310974,
      "learning_rate": 8.305151500438992e-06,
      "loss": 0.533,
      "step": 36128
    },
    {
      "epoch": 1.1098516265781955,
      "grad_norm": 0.45784515142440796,
      "learning_rate": 8.30467521675528e-06,
      "loss": 0.5711,
      "step": 36129
    },
    {
      "epoch": 1.1098823457131448,
      "grad_norm": 0.8897783160209656,
      "learning_rate": 8.304198937031116e-06,
      "loss": 0.5275,
      "step": 36130
    },
    {
      "epoch": 1.109913064848094,
      "grad_norm": 0.3921704590320587,
      "learning_rate": 8.303722661267617e-06,
      "loss": 0.4815,
      "step": 36131
    },
    {
      "epoch": 1.109943783983043,
      "grad_norm": 0.3676682114601135,
      "learning_rate": 8.30324638946589e-06,
      "loss": 0.51,
      "step": 36132
    },
    {
      "epoch": 1.1099745031179922,
      "grad_norm": 0.4877904951572418,
      "learning_rate": 8.302770121627049e-06,
      "loss": 0.5162,
      "step": 36133
    },
    {
      "epoch": 1.1100052222529413,
      "grad_norm": 0.38627293705940247,
      "learning_rate": 8.302293857752206e-06,
      "loss": 0.5525,
      "step": 36134
    },
    {
      "epoch": 1.1100359413878906,
      "grad_norm": 0.3734480142593384,
      "learning_rate": 8.301817597842479e-06,
      "loss": 0.5081,
      "step": 36135
    },
    {
      "epoch": 1.1100666605228398,
      "grad_norm": 0.3726801872253418,
      "learning_rate": 8.30134134189897e-06,
      "loss": 0.5009,
      "step": 36136
    },
    {
      "epoch": 1.1100973796577889,
      "grad_norm": 0.3954404890537262,
      "learning_rate": 8.300865089922801e-06,
      "loss": 0.4408,
      "step": 36137
    },
    {
      "epoch": 1.110128098792738,
      "grad_norm": 0.3919336795806885,
      "learning_rate": 8.300388841915076e-06,
      "loss": 0.4559,
      "step": 36138
    },
    {
      "epoch": 1.1101588179276871,
      "grad_norm": 0.36988720297813416,
      "learning_rate": 8.299912597876916e-06,
      "loss": 0.4707,
      "step": 36139
    },
    {
      "epoch": 1.1101895370626362,
      "grad_norm": 0.3948971927165985,
      "learning_rate": 8.299436357809425e-06,
      "loss": 0.4935,
      "step": 36140
    },
    {
      "epoch": 1.1102202561975856,
      "grad_norm": 0.34754711389541626,
      "learning_rate": 8.298960121713724e-06,
      "loss": 0.4621,
      "step": 36141
    },
    {
      "epoch": 1.1102509753325347,
      "grad_norm": 0.37686291337013245,
      "learning_rate": 8.298483889590915e-06,
      "loss": 0.4361,
      "step": 36142
    },
    {
      "epoch": 1.1102816944674838,
      "grad_norm": 0.39759570360183716,
      "learning_rate": 8.29800766144212e-06,
      "loss": 0.522,
      "step": 36143
    },
    {
      "epoch": 1.110312413602433,
      "grad_norm": 0.409165620803833,
      "learning_rate": 8.297531437268444e-06,
      "loss": 0.4862,
      "step": 36144
    },
    {
      "epoch": 1.110343132737382,
      "grad_norm": 0.38960355520248413,
      "learning_rate": 8.297055217071001e-06,
      "loss": 0.4489,
      "step": 36145
    },
    {
      "epoch": 1.1103738518723312,
      "grad_norm": 0.5837599635124207,
      "learning_rate": 8.29657900085091e-06,
      "loss": 0.4387,
      "step": 36146
    },
    {
      "epoch": 1.1104045710072805,
      "grad_norm": 0.37548843026161194,
      "learning_rate": 8.296102788609272e-06,
      "loss": 0.467,
      "step": 36147
    },
    {
      "epoch": 1.1104352901422296,
      "grad_norm": 0.3921680152416229,
      "learning_rate": 8.29562658034721e-06,
      "loss": 0.5467,
      "step": 36148
    },
    {
      "epoch": 1.1104660092771788,
      "grad_norm": 0.41982004046440125,
      "learning_rate": 8.295150376065828e-06,
      "loss": 0.5305,
      "step": 36149
    },
    {
      "epoch": 1.1104967284121279,
      "grad_norm": 0.3895998001098633,
      "learning_rate": 8.294674175766243e-06,
      "loss": 0.524,
      "step": 36150
    },
    {
      "epoch": 1.110527447547077,
      "grad_norm": 0.5059168934822083,
      "learning_rate": 8.294197979449563e-06,
      "loss": 0.4757,
      "step": 36151
    },
    {
      "epoch": 1.1105581666820263,
      "grad_norm": 0.48312342166900635,
      "learning_rate": 8.293721787116905e-06,
      "loss": 0.4677,
      "step": 36152
    },
    {
      "epoch": 1.1105888858169755,
      "grad_norm": 0.43093761801719666,
      "learning_rate": 8.293245598769378e-06,
      "loss": 0.4599,
      "step": 36153
    },
    {
      "epoch": 1.1106196049519246,
      "grad_norm": 0.4339294135570526,
      "learning_rate": 8.292769414408096e-06,
      "loss": 0.4494,
      "step": 36154
    },
    {
      "epoch": 1.1106503240868737,
      "grad_norm": 0.44179555773735046,
      "learning_rate": 8.29229323403417e-06,
      "loss": 0.4716,
      "step": 36155
    },
    {
      "epoch": 1.1106810432218228,
      "grad_norm": 0.4133910834789276,
      "learning_rate": 8.291817057648712e-06,
      "loss": 0.4547,
      "step": 36156
    },
    {
      "epoch": 1.110711762356772,
      "grad_norm": 0.4073392450809479,
      "learning_rate": 8.291340885252833e-06,
      "loss": 0.4371,
      "step": 36157
    },
    {
      "epoch": 1.1107424814917213,
      "grad_norm": 0.37706151604652405,
      "learning_rate": 8.29086471684765e-06,
      "loss": 0.5062,
      "step": 36158
    },
    {
      "epoch": 1.1107732006266704,
      "grad_norm": 0.3892967700958252,
      "learning_rate": 8.290388552434268e-06,
      "loss": 0.4251,
      "step": 36159
    },
    {
      "epoch": 1.1108039197616195,
      "grad_norm": 0.503807783126831,
      "learning_rate": 8.289912392013807e-06,
      "loss": 0.4678,
      "step": 36160
    },
    {
      "epoch": 1.1108346388965686,
      "grad_norm": 0.3841076195240021,
      "learning_rate": 8.289436235587372e-06,
      "loss": 0.4582,
      "step": 36161
    },
    {
      "epoch": 1.1108653580315178,
      "grad_norm": 0.424348384141922,
      "learning_rate": 8.288960083156081e-06,
      "loss": 0.4562,
      "step": 36162
    },
    {
      "epoch": 1.1108960771664669,
      "grad_norm": 0.3554740846157074,
      "learning_rate": 8.28848393472104e-06,
      "loss": 0.5315,
      "step": 36163
    },
    {
      "epoch": 1.1109267963014162,
      "grad_norm": 0.3855690062046051,
      "learning_rate": 8.288007790283363e-06,
      "loss": 0.431,
      "step": 36164
    },
    {
      "epoch": 1.1109575154363653,
      "grad_norm": 0.4016292095184326,
      "learning_rate": 8.287531649844168e-06,
      "loss": 0.51,
      "step": 36165
    },
    {
      "epoch": 1.1109882345713145,
      "grad_norm": 0.37973421812057495,
      "learning_rate": 8.28705551340456e-06,
      "loss": 0.4728,
      "step": 36166
    },
    {
      "epoch": 1.1110189537062636,
      "grad_norm": 0.3610166609287262,
      "learning_rate": 8.286579380965655e-06,
      "loss": 0.5191,
      "step": 36167
    },
    {
      "epoch": 1.1110496728412127,
      "grad_norm": 0.37661194801330566,
      "learning_rate": 8.286103252528562e-06,
      "loss": 0.4195,
      "step": 36168
    },
    {
      "epoch": 1.111080391976162,
      "grad_norm": 0.3789941966533661,
      "learning_rate": 8.285627128094399e-06,
      "loss": 0.3812,
      "step": 36169
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.4062367081642151,
      "learning_rate": 8.285151007664265e-06,
      "loss": 0.5324,
      "step": 36170
    },
    {
      "epoch": 1.1111418302460603,
      "grad_norm": 0.41630083322525024,
      "learning_rate": 8.284674891239288e-06,
      "loss": 0.4812,
      "step": 36171
    },
    {
      "epoch": 1.1111725493810094,
      "grad_norm": 0.3920579254627228,
      "learning_rate": 8.284198778820566e-06,
      "loss": 0.4442,
      "step": 36172
    },
    {
      "epoch": 1.1112032685159585,
      "grad_norm": 0.43769562244415283,
      "learning_rate": 8.283722670409226e-06,
      "loss": 0.4591,
      "step": 36173
    },
    {
      "epoch": 1.1112339876509076,
      "grad_norm": 0.4471302628517151,
      "learning_rate": 8.283246566006363e-06,
      "loss": 0.4472,
      "step": 36174
    },
    {
      "epoch": 1.111264706785857,
      "grad_norm": 0.4183529019355774,
      "learning_rate": 8.282770465613104e-06,
      "loss": 0.5143,
      "step": 36175
    },
    {
      "epoch": 1.111295425920806,
      "grad_norm": 0.36298421025276184,
      "learning_rate": 8.282294369230553e-06,
      "loss": 0.5232,
      "step": 36176
    },
    {
      "epoch": 1.1113261450557552,
      "grad_norm": 0.4052520990371704,
      "learning_rate": 8.281818276859824e-06,
      "loss": 0.418,
      "step": 36177
    },
    {
      "epoch": 1.1113568641907043,
      "grad_norm": 0.408052533864975,
      "learning_rate": 8.281342188502024e-06,
      "loss": 0.5465,
      "step": 36178
    },
    {
      "epoch": 1.1113875833256535,
      "grad_norm": 0.36920517683029175,
      "learning_rate": 8.280866104158274e-06,
      "loss": 0.3937,
      "step": 36179
    },
    {
      "epoch": 1.1114183024606028,
      "grad_norm": 0.3629435896873474,
      "learning_rate": 8.280390023829678e-06,
      "loss": 0.4537,
      "step": 36180
    },
    {
      "epoch": 1.111449021595552,
      "grad_norm": 0.4255351424217224,
      "learning_rate": 8.279913947517349e-06,
      "loss": 0.506,
      "step": 36181
    },
    {
      "epoch": 1.111479740730501,
      "grad_norm": 0.40023720264434814,
      "learning_rate": 8.279437875222409e-06,
      "loss": 0.5002,
      "step": 36182
    },
    {
      "epoch": 1.1115104598654502,
      "grad_norm": 0.4713941216468811,
      "learning_rate": 8.278961806945956e-06,
      "loss": 0.4859,
      "step": 36183
    },
    {
      "epoch": 1.1115411790003993,
      "grad_norm": 0.378598690032959,
      "learning_rate": 8.278485742689111e-06,
      "loss": 0.5196,
      "step": 36184
    },
    {
      "epoch": 1.1115718981353484,
      "grad_norm": 0.396716445684433,
      "learning_rate": 8.278009682452981e-06,
      "loss": 0.4695,
      "step": 36185
    },
    {
      "epoch": 1.1116026172702977,
      "grad_norm": 0.3742186725139618,
      "learning_rate": 8.27753362623868e-06,
      "loss": 0.5071,
      "step": 36186
    },
    {
      "epoch": 1.1116333364052469,
      "grad_norm": 0.36318114399909973,
      "learning_rate": 8.27705757404732e-06,
      "loss": 0.4376,
      "step": 36187
    },
    {
      "epoch": 1.111664055540196,
      "grad_norm": 0.5106165409088135,
      "learning_rate": 8.276581525880013e-06,
      "loss": 0.5551,
      "step": 36188
    },
    {
      "epoch": 1.111694774675145,
      "grad_norm": 0.45416098833084106,
      "learning_rate": 8.276105481737868e-06,
      "loss": 0.5089,
      "step": 36189
    },
    {
      "epoch": 1.1117254938100942,
      "grad_norm": 0.3599211573600769,
      "learning_rate": 8.275629441622001e-06,
      "loss": 0.4676,
      "step": 36190
    },
    {
      "epoch": 1.1117562129450436,
      "grad_norm": 0.4474811553955078,
      "learning_rate": 8.27515340553352e-06,
      "loss": 0.4754,
      "step": 36191
    },
    {
      "epoch": 1.1117869320799927,
      "grad_norm": 0.38730886578559875,
      "learning_rate": 8.274677373473541e-06,
      "loss": 0.4919,
      "step": 36192
    },
    {
      "epoch": 1.1118176512149418,
      "grad_norm": 0.36183756589889526,
      "learning_rate": 8.27420134544317e-06,
      "loss": 0.465,
      "step": 36193
    },
    {
      "epoch": 1.111848370349891,
      "grad_norm": 0.40340378880500793,
      "learning_rate": 8.273725321443528e-06,
      "loss": 0.5205,
      "step": 36194
    },
    {
      "epoch": 1.11187908948484,
      "grad_norm": 0.44285860657691956,
      "learning_rate": 8.273249301475717e-06,
      "loss": 0.4891,
      "step": 36195
    },
    {
      "epoch": 1.1119098086197892,
      "grad_norm": 0.6486440896987915,
      "learning_rate": 8.272773285540854e-06,
      "loss": 0.5662,
      "step": 36196
    },
    {
      "epoch": 1.1119405277547385,
      "grad_norm": 0.36208242177963257,
      "learning_rate": 8.272297273640047e-06,
      "loss": 0.4764,
      "step": 36197
    },
    {
      "epoch": 1.1119712468896876,
      "grad_norm": 0.5193272233009338,
      "learning_rate": 8.271821265774416e-06,
      "loss": 0.5043,
      "step": 36198
    },
    {
      "epoch": 1.1120019660246367,
      "grad_norm": 0.4087527096271515,
      "learning_rate": 8.27134526194506e-06,
      "loss": 0.3916,
      "step": 36199
    },
    {
      "epoch": 1.1120326851595859,
      "grad_norm": 0.5210282802581787,
      "learning_rate": 8.2708692621531e-06,
      "loss": 0.5266,
      "step": 36200
    },
    {
      "epoch": 1.112063404294535,
      "grad_norm": 0.3797316551208496,
      "learning_rate": 8.27039326639965e-06,
      "loss": 0.4625,
      "step": 36201
    },
    {
      "epoch": 1.1120941234294843,
      "grad_norm": 0.39479631185531616,
      "learning_rate": 8.269917274685812e-06,
      "loss": 0.4753,
      "step": 36202
    },
    {
      "epoch": 1.1121248425644334,
      "grad_norm": 0.34109169244766235,
      "learning_rate": 8.269441287012708e-06,
      "loss": 0.4503,
      "step": 36203
    },
    {
      "epoch": 1.1121555616993826,
      "grad_norm": 0.7340635061264038,
      "learning_rate": 8.26896530338144e-06,
      "loss": 0.5179,
      "step": 36204
    },
    {
      "epoch": 1.1121862808343317,
      "grad_norm": 0.36235368251800537,
      "learning_rate": 8.26848932379313e-06,
      "loss": 0.4838,
      "step": 36205
    },
    {
      "epoch": 1.1122169999692808,
      "grad_norm": 0.3684758245944977,
      "learning_rate": 8.268013348248879e-06,
      "loss": 0.5075,
      "step": 36206
    },
    {
      "epoch": 1.11224771910423,
      "grad_norm": 0.4173068106174469,
      "learning_rate": 8.267537376749807e-06,
      "loss": 0.4217,
      "step": 36207
    },
    {
      "epoch": 1.1122784382391793,
      "grad_norm": 0.3727661073207855,
      "learning_rate": 8.267061409297017e-06,
      "loss": 0.43,
      "step": 36208
    },
    {
      "epoch": 1.1123091573741284,
      "grad_norm": 0.4260835647583008,
      "learning_rate": 8.266585445891635e-06,
      "loss": 0.4359,
      "step": 36209
    },
    {
      "epoch": 1.1123398765090775,
      "grad_norm": 0.4221624732017517,
      "learning_rate": 8.266109486534756e-06,
      "loss": 0.5389,
      "step": 36210
    },
    {
      "epoch": 1.1123705956440266,
      "grad_norm": 0.4033565819263458,
      "learning_rate": 8.265633531227505e-06,
      "loss": 0.5187,
      "step": 36211
    },
    {
      "epoch": 1.1124013147789757,
      "grad_norm": 0.400908499956131,
      "learning_rate": 8.265157579970983e-06,
      "loss": 0.5,
      "step": 36212
    },
    {
      "epoch": 1.112432033913925,
      "grad_norm": 0.4168139100074768,
      "learning_rate": 8.26468163276631e-06,
      "loss": 0.4993,
      "step": 36213
    },
    {
      "epoch": 1.1124627530488742,
      "grad_norm": 0.40451687574386597,
      "learning_rate": 8.264205689614593e-06,
      "loss": 0.5604,
      "step": 36214
    },
    {
      "epoch": 1.1124934721838233,
      "grad_norm": 0.4041461646556854,
      "learning_rate": 8.263729750516947e-06,
      "loss": 0.5484,
      "step": 36215
    },
    {
      "epoch": 1.1125241913187724,
      "grad_norm": 0.41857948899269104,
      "learning_rate": 8.263253815474477e-06,
      "loss": 0.4805,
      "step": 36216
    },
    {
      "epoch": 1.1125549104537216,
      "grad_norm": 0.3629535436630249,
      "learning_rate": 8.262777884488304e-06,
      "loss": 0.3993,
      "step": 36217
    },
    {
      "epoch": 1.1125856295886707,
      "grad_norm": 0.3860471248626709,
      "learning_rate": 8.26230195755953e-06,
      "loss": 0.6137,
      "step": 36218
    },
    {
      "epoch": 1.11261634872362,
      "grad_norm": 0.4700695872306824,
      "learning_rate": 8.261826034689273e-06,
      "loss": 0.4613,
      "step": 36219
    },
    {
      "epoch": 1.1126470678585691,
      "grad_norm": 0.37571385502815247,
      "learning_rate": 8.261350115878642e-06,
      "loss": 0.4395,
      "step": 36220
    },
    {
      "epoch": 1.1126777869935183,
      "grad_norm": 0.4107080399990082,
      "learning_rate": 8.26087420112875e-06,
      "loss": 0.4918,
      "step": 36221
    },
    {
      "epoch": 1.1127085061284674,
      "grad_norm": 0.40169045329093933,
      "learning_rate": 8.260398290440709e-06,
      "loss": 0.4513,
      "step": 36222
    },
    {
      "epoch": 1.1127392252634165,
      "grad_norm": 0.4108979105949402,
      "learning_rate": 8.259922383815627e-06,
      "loss": 0.4648,
      "step": 36223
    },
    {
      "epoch": 1.1127699443983659,
      "grad_norm": 0.37343329191207886,
      "learning_rate": 8.259446481254619e-06,
      "loss": 0.4992,
      "step": 36224
    },
    {
      "epoch": 1.112800663533315,
      "grad_norm": 0.38687071204185486,
      "learning_rate": 8.258970582758794e-06,
      "loss": 0.4958,
      "step": 36225
    },
    {
      "epoch": 1.112831382668264,
      "grad_norm": 0.40260016918182373,
      "learning_rate": 8.258494688329269e-06,
      "loss": 0.5264,
      "step": 36226
    },
    {
      "epoch": 1.1128621018032132,
      "grad_norm": 0.39233675599098206,
      "learning_rate": 8.258018797967146e-06,
      "loss": 0.596,
      "step": 36227
    },
    {
      "epoch": 1.1128928209381623,
      "grad_norm": 0.3713424801826477,
      "learning_rate": 8.257542911673545e-06,
      "loss": 0.4403,
      "step": 36228
    },
    {
      "epoch": 1.1129235400731115,
      "grad_norm": 0.36053481698036194,
      "learning_rate": 8.257067029449573e-06,
      "loss": 0.438,
      "step": 36229
    },
    {
      "epoch": 1.1129542592080608,
      "grad_norm": 0.4212050437927246,
      "learning_rate": 8.256591151296343e-06,
      "loss": 0.4449,
      "step": 36230
    },
    {
      "epoch": 1.11298497834301,
      "grad_norm": 0.39204320311546326,
      "learning_rate": 8.256115277214964e-06,
      "loss": 0.4653,
      "step": 36231
    },
    {
      "epoch": 1.113015697477959,
      "grad_norm": 0.373286634683609,
      "learning_rate": 8.255639407206554e-06,
      "loss": 0.4807,
      "step": 36232
    },
    {
      "epoch": 1.1130464166129082,
      "grad_norm": 0.4010905921459198,
      "learning_rate": 8.255163541272216e-06,
      "loss": 0.5099,
      "step": 36233
    },
    {
      "epoch": 1.1130771357478573,
      "grad_norm": 0.37473565340042114,
      "learning_rate": 8.25468767941307e-06,
      "loss": 0.5475,
      "step": 36234
    },
    {
      "epoch": 1.1131078548828066,
      "grad_norm": 0.33289775252342224,
      "learning_rate": 8.254211821630217e-06,
      "loss": 0.4292,
      "step": 36235
    },
    {
      "epoch": 1.1131385740177557,
      "grad_norm": 0.3839799165725708,
      "learning_rate": 8.253735967924777e-06,
      "loss": 0.5105,
      "step": 36236
    },
    {
      "epoch": 1.1131692931527049,
      "grad_norm": 0.39142873883247375,
      "learning_rate": 8.253260118297858e-06,
      "loss": 0.4657,
      "step": 36237
    },
    {
      "epoch": 1.113200012287654,
      "grad_norm": 0.36752915382385254,
      "learning_rate": 8.252784272750572e-06,
      "loss": 0.489,
      "step": 36238
    },
    {
      "epoch": 1.113230731422603,
      "grad_norm": 0.40566542744636536,
      "learning_rate": 8.252308431284036e-06,
      "loss": 0.5251,
      "step": 36239
    },
    {
      "epoch": 1.1132614505575522,
      "grad_norm": 0.41827908158302307,
      "learning_rate": 8.251832593899345e-06,
      "loss": 0.5123,
      "step": 36240
    },
    {
      "epoch": 1.1132921696925016,
      "grad_norm": 0.4440522789955139,
      "learning_rate": 8.251356760597631e-06,
      "loss": 0.5152,
      "step": 36241
    },
    {
      "epoch": 1.1133228888274507,
      "grad_norm": 0.37830349802970886,
      "learning_rate": 8.250880931379988e-06,
      "loss": 0.4819,
      "step": 36242
    },
    {
      "epoch": 1.1133536079623998,
      "grad_norm": 0.39951860904693604,
      "learning_rate": 8.25040510624754e-06,
      "loss": 0.5512,
      "step": 36243
    },
    {
      "epoch": 1.113384327097349,
      "grad_norm": 0.4367513358592987,
      "learning_rate": 8.249929285201389e-06,
      "loss": 0.4797,
      "step": 36244
    },
    {
      "epoch": 1.113415046232298,
      "grad_norm": 0.3970949649810791,
      "learning_rate": 8.249453468242655e-06,
      "loss": 0.4917,
      "step": 36245
    },
    {
      "epoch": 1.1134457653672474,
      "grad_norm": 0.39730122685432434,
      "learning_rate": 8.248977655372441e-06,
      "loss": 0.5407,
      "step": 36246
    },
    {
      "epoch": 1.1134764845021965,
      "grad_norm": 0.42537304759025574,
      "learning_rate": 8.248501846591863e-06,
      "loss": 0.5425,
      "step": 36247
    },
    {
      "epoch": 1.1135072036371456,
      "grad_norm": 0.36908918619155884,
      "learning_rate": 8.248026041902031e-06,
      "loss": 0.4521,
      "step": 36248
    },
    {
      "epoch": 1.1135379227720947,
      "grad_norm": 0.38522419333457947,
      "learning_rate": 8.24755024130406e-06,
      "loss": 0.5193,
      "step": 36249
    },
    {
      "epoch": 1.1135686419070439,
      "grad_norm": 0.4117032587528229,
      "learning_rate": 8.247074444799052e-06,
      "loss": 0.4884,
      "step": 36250
    },
    {
      "epoch": 1.113599361041993,
      "grad_norm": 0.37758341431617737,
      "learning_rate": 8.246598652388128e-06,
      "loss": 0.4807,
      "step": 36251
    },
    {
      "epoch": 1.1136300801769423,
      "grad_norm": 0.39457422494888306,
      "learning_rate": 8.246122864072393e-06,
      "loss": 0.4562,
      "step": 36252
    },
    {
      "epoch": 1.1136607993118914,
      "grad_norm": 0.403958797454834,
      "learning_rate": 8.245647079852962e-06,
      "loss": 0.4719,
      "step": 36253
    },
    {
      "epoch": 1.1136915184468406,
      "grad_norm": 0.3755776882171631,
      "learning_rate": 8.245171299730942e-06,
      "loss": 0.4261,
      "step": 36254
    },
    {
      "epoch": 1.1137222375817897,
      "grad_norm": 0.3947184383869171,
      "learning_rate": 8.24469552370745e-06,
      "loss": 0.5389,
      "step": 36255
    },
    {
      "epoch": 1.1137529567167388,
      "grad_norm": 0.4093603789806366,
      "learning_rate": 8.244219751783594e-06,
      "loss": 0.5051,
      "step": 36256
    },
    {
      "epoch": 1.113783675851688,
      "grad_norm": 0.41349849104881287,
      "learning_rate": 8.243743983960483e-06,
      "loss": 0.4855,
      "step": 36257
    },
    {
      "epoch": 1.1138143949866373,
      "grad_norm": 0.37731900811195374,
      "learning_rate": 8.243268220239234e-06,
      "loss": 0.4618,
      "step": 36258
    },
    {
      "epoch": 1.1138451141215864,
      "grad_norm": 0.38024619221687317,
      "learning_rate": 8.242792460620952e-06,
      "loss": 0.4458,
      "step": 36259
    },
    {
      "epoch": 1.1138758332565355,
      "grad_norm": 0.37488046288490295,
      "learning_rate": 8.242316705106754e-06,
      "loss": 0.512,
      "step": 36260
    },
    {
      "epoch": 1.1139065523914846,
      "grad_norm": 0.39431264996528625,
      "learning_rate": 8.241840953697745e-06,
      "loss": 0.5003,
      "step": 36261
    },
    {
      "epoch": 1.1139372715264337,
      "grad_norm": 0.34883224964141846,
      "learning_rate": 8.24136520639504e-06,
      "loss": 0.3983,
      "step": 36262
    },
    {
      "epoch": 1.113967990661383,
      "grad_norm": 0.37200725078582764,
      "learning_rate": 8.240889463199751e-06,
      "loss": 0.5093,
      "step": 36263
    },
    {
      "epoch": 1.1139987097963322,
      "grad_norm": 0.5895480513572693,
      "learning_rate": 8.240413724112987e-06,
      "loss": 0.5112,
      "step": 36264
    },
    {
      "epoch": 1.1140294289312813,
      "grad_norm": 0.3826207220554352,
      "learning_rate": 8.239937989135858e-06,
      "loss": 0.4983,
      "step": 36265
    },
    {
      "epoch": 1.1140601480662304,
      "grad_norm": 0.7265223264694214,
      "learning_rate": 8.239462258269479e-06,
      "loss": 0.4418,
      "step": 36266
    },
    {
      "epoch": 1.1140908672011796,
      "grad_norm": 0.4123903512954712,
      "learning_rate": 8.238986531514955e-06,
      "loss": 0.4618,
      "step": 36267
    },
    {
      "epoch": 1.1141215863361287,
      "grad_norm": 0.3779185116291046,
      "learning_rate": 8.238510808873408e-06,
      "loss": 0.4918,
      "step": 36268
    },
    {
      "epoch": 1.114152305471078,
      "grad_norm": 0.40102043747901917,
      "learning_rate": 8.238035090345934e-06,
      "loss": 0.5178,
      "step": 36269
    },
    {
      "epoch": 1.1141830246060271,
      "grad_norm": 0.3677186369895935,
      "learning_rate": 8.23755937593366e-06,
      "loss": 0.4714,
      "step": 36270
    },
    {
      "epoch": 1.1142137437409763,
      "grad_norm": 0.39481425285339355,
      "learning_rate": 8.23708366563768e-06,
      "loss": 0.5252,
      "step": 36271
    },
    {
      "epoch": 1.1142444628759254,
      "grad_norm": 0.5187501907348633,
      "learning_rate": 8.236607959459121e-06,
      "loss": 0.5755,
      "step": 36272
    },
    {
      "epoch": 1.1142751820108745,
      "grad_norm": 0.370677649974823,
      "learning_rate": 8.236132257399082e-06,
      "loss": 0.4724,
      "step": 36273
    },
    {
      "epoch": 1.1143059011458236,
      "grad_norm": 0.3991447687149048,
      "learning_rate": 8.235656559458683e-06,
      "loss": 0.4719,
      "step": 36274
    },
    {
      "epoch": 1.114336620280773,
      "grad_norm": 0.4393148124217987,
      "learning_rate": 8.235180865639035e-06,
      "loss": 0.5358,
      "step": 36275
    },
    {
      "epoch": 1.114367339415722,
      "grad_norm": 0.41340991854667664,
      "learning_rate": 8.234705175941238e-06,
      "loss": 0.4661,
      "step": 36276
    },
    {
      "epoch": 1.1143980585506712,
      "grad_norm": 0.37219706177711487,
      "learning_rate": 8.234229490366417e-06,
      "loss": 0.4987,
      "step": 36277
    },
    {
      "epoch": 1.1144287776856203,
      "grad_norm": 0.4289917051792145,
      "learning_rate": 8.233753808915669e-06,
      "loss": 0.5571,
      "step": 36278
    },
    {
      "epoch": 1.1144594968205694,
      "grad_norm": 0.4211406409740448,
      "learning_rate": 8.233278131590119e-06,
      "loss": 0.466,
      "step": 36279
    },
    {
      "epoch": 1.1144902159555188,
      "grad_norm": 0.40173977613449097,
      "learning_rate": 8.232802458390867e-06,
      "loss": 0.5584,
      "step": 36280
    },
    {
      "epoch": 1.114520935090468,
      "grad_norm": 0.4087776839733124,
      "learning_rate": 8.232326789319031e-06,
      "loss": 0.459,
      "step": 36281
    },
    {
      "epoch": 1.114551654225417,
      "grad_norm": 0.3717847764492035,
      "learning_rate": 8.231851124375718e-06,
      "loss": 0.4924,
      "step": 36282
    },
    {
      "epoch": 1.1145823733603661,
      "grad_norm": 0.38384976983070374,
      "learning_rate": 8.231375463562042e-06,
      "loss": 0.5234,
      "step": 36283
    },
    {
      "epoch": 1.1146130924953153,
      "grad_norm": 0.4294115900993347,
      "learning_rate": 8.23089980687911e-06,
      "loss": 0.5797,
      "step": 36284
    },
    {
      "epoch": 1.1146438116302644,
      "grad_norm": 0.37713623046875,
      "learning_rate": 8.230424154328035e-06,
      "loss": 0.4724,
      "step": 36285
    },
    {
      "epoch": 1.1146745307652137,
      "grad_norm": 0.34920310974121094,
      "learning_rate": 8.229948505909927e-06,
      "loss": 0.459,
      "step": 36286
    },
    {
      "epoch": 1.1147052499001628,
      "grad_norm": 0.4324868321418762,
      "learning_rate": 8.229472861625902e-06,
      "loss": 0.471,
      "step": 36287
    },
    {
      "epoch": 1.114735969035112,
      "grad_norm": 0.4018310606479645,
      "learning_rate": 8.228997221477061e-06,
      "loss": 0.5053,
      "step": 36288
    },
    {
      "epoch": 1.114766688170061,
      "grad_norm": 0.41297057271003723,
      "learning_rate": 8.228521585464526e-06,
      "loss": 0.4712,
      "step": 36289
    },
    {
      "epoch": 1.1147974073050102,
      "grad_norm": 0.41928407549858093,
      "learning_rate": 8.228045953589399e-06,
      "loss": 0.4872,
      "step": 36290
    },
    {
      "epoch": 1.1148281264399595,
      "grad_norm": 0.388435423374176,
      "learning_rate": 8.227570325852796e-06,
      "loss": 0.4472,
      "step": 36291
    },
    {
      "epoch": 1.1148588455749087,
      "grad_norm": 0.5067564845085144,
      "learning_rate": 8.227094702255826e-06,
      "loss": 0.4735,
      "step": 36292
    },
    {
      "epoch": 1.1148895647098578,
      "grad_norm": 0.35907304286956787,
      "learning_rate": 8.226619082799599e-06,
      "loss": 0.5224,
      "step": 36293
    },
    {
      "epoch": 1.114920283844807,
      "grad_norm": 0.36514779925346375,
      "learning_rate": 8.226143467485229e-06,
      "loss": 0.4961,
      "step": 36294
    },
    {
      "epoch": 1.114951002979756,
      "grad_norm": 0.37926939129829407,
      "learning_rate": 8.225667856313824e-06,
      "loss": 0.4987,
      "step": 36295
    },
    {
      "epoch": 1.1149817221147051,
      "grad_norm": 0.4479624927043915,
      "learning_rate": 8.225192249286496e-06,
      "loss": 0.4331,
      "step": 36296
    },
    {
      "epoch": 1.1150124412496545,
      "grad_norm": 0.4061727523803711,
      "learning_rate": 8.224716646404354e-06,
      "loss": 0.4871,
      "step": 36297
    },
    {
      "epoch": 1.1150431603846036,
      "grad_norm": 0.39144980907440186,
      "learning_rate": 8.224241047668513e-06,
      "loss": 0.5284,
      "step": 36298
    },
    {
      "epoch": 1.1150738795195527,
      "grad_norm": 1.3952668905258179,
      "learning_rate": 8.223765453080077e-06,
      "loss": 0.5425,
      "step": 36299
    },
    {
      "epoch": 1.1151045986545018,
      "grad_norm": 0.4196789860725403,
      "learning_rate": 8.223289862640164e-06,
      "loss": 0.3677,
      "step": 36300
    },
    {
      "epoch": 1.115135317789451,
      "grad_norm": 0.40552064776420593,
      "learning_rate": 8.222814276349881e-06,
      "loss": 0.5528,
      "step": 36301
    },
    {
      "epoch": 1.1151660369244003,
      "grad_norm": 0.35654279589653015,
      "learning_rate": 8.222338694210343e-06,
      "loss": 0.5435,
      "step": 36302
    },
    {
      "epoch": 1.1151967560593494,
      "grad_norm": 0.38027888536453247,
      "learning_rate": 8.22186311622265e-06,
      "loss": 0.5369,
      "step": 36303
    },
    {
      "epoch": 1.1152274751942985,
      "grad_norm": 0.39203721284866333,
      "learning_rate": 8.221387542387926e-06,
      "loss": 0.5118,
      "step": 36304
    },
    {
      "epoch": 1.1152581943292477,
      "grad_norm": 0.37420740723609924,
      "learning_rate": 8.22091197270727e-06,
      "loss": 0.5333,
      "step": 36305
    },
    {
      "epoch": 1.1152889134641968,
      "grad_norm": 0.368510901927948,
      "learning_rate": 8.220436407181804e-06,
      "loss": 0.4264,
      "step": 36306
    },
    {
      "epoch": 1.115319632599146,
      "grad_norm": 0.41174474358558655,
      "learning_rate": 8.219960845812627e-06,
      "loss": 0.4677,
      "step": 36307
    },
    {
      "epoch": 1.1153503517340952,
      "grad_norm": 0.3978034555912018,
      "learning_rate": 8.219485288600863e-06,
      "loss": 0.5152,
      "step": 36308
    },
    {
      "epoch": 1.1153810708690444,
      "grad_norm": 0.45019760727882385,
      "learning_rate": 8.21900973554761e-06,
      "loss": 0.5795,
      "step": 36309
    },
    {
      "epoch": 1.1154117900039935,
      "grad_norm": 0.35792914032936096,
      "learning_rate": 8.218534186653982e-06,
      "loss": 0.5066,
      "step": 36310
    },
    {
      "epoch": 1.1154425091389426,
      "grad_norm": 0.44984811544418335,
      "learning_rate": 8.218058641921099e-06,
      "loss": 0.5655,
      "step": 36311
    },
    {
      "epoch": 1.1154732282738917,
      "grad_norm": 0.391938716173172,
      "learning_rate": 8.217583101350058e-06,
      "loss": 0.5803,
      "step": 36312
    },
    {
      "epoch": 1.115503947408841,
      "grad_norm": 0.37619516253471375,
      "learning_rate": 8.217107564941982e-06,
      "loss": 0.4693,
      "step": 36313
    },
    {
      "epoch": 1.1155346665437902,
      "grad_norm": 0.4307810664176941,
      "learning_rate": 8.216632032697968e-06,
      "loss": 0.4633,
      "step": 36314
    },
    {
      "epoch": 1.1155653856787393,
      "grad_norm": 0.3868425786495209,
      "learning_rate": 8.216156504619144e-06,
      "loss": 0.5008,
      "step": 36315
    },
    {
      "epoch": 1.1155961048136884,
      "grad_norm": 0.40860679745674133,
      "learning_rate": 8.215680980706605e-06,
      "loss": 0.4837,
      "step": 36316
    },
    {
      "epoch": 1.1156268239486375,
      "grad_norm": 0.36696410179138184,
      "learning_rate": 8.21520546096147e-06,
      "loss": 0.4879,
      "step": 36317
    },
    {
      "epoch": 1.1156575430835867,
      "grad_norm": 0.3696122467517853,
      "learning_rate": 8.214729945384845e-06,
      "loss": 0.4587,
      "step": 36318
    },
    {
      "epoch": 1.115688262218536,
      "grad_norm": 0.3986589014530182,
      "learning_rate": 8.214254433977845e-06,
      "loss": 0.5234,
      "step": 36319
    },
    {
      "epoch": 1.1157189813534851,
      "grad_norm": 0.38298299908638,
      "learning_rate": 8.213778926741577e-06,
      "loss": 0.4661,
      "step": 36320
    },
    {
      "epoch": 1.1157497004884342,
      "grad_norm": 0.4078904092311859,
      "learning_rate": 8.213303423677155e-06,
      "loss": 0.4797,
      "step": 36321
    },
    {
      "epoch": 1.1157804196233834,
      "grad_norm": 0.4987632632255554,
      "learning_rate": 8.212827924785685e-06,
      "loss": 0.3735,
      "step": 36322
    },
    {
      "epoch": 1.1158111387583325,
      "grad_norm": 0.4109664857387543,
      "learning_rate": 8.212352430068284e-06,
      "loss": 0.4585,
      "step": 36323
    },
    {
      "epoch": 1.1158418578932818,
      "grad_norm": 0.3699803650379181,
      "learning_rate": 8.211876939526054e-06,
      "loss": 0.3896,
      "step": 36324
    },
    {
      "epoch": 1.115872577028231,
      "grad_norm": 0.3908594250679016,
      "learning_rate": 8.211401453160115e-06,
      "loss": 0.4227,
      "step": 36325
    },
    {
      "epoch": 1.11590329616318,
      "grad_norm": 0.3646855652332306,
      "learning_rate": 8.210925970971568e-06,
      "loss": 0.5086,
      "step": 36326
    },
    {
      "epoch": 1.1159340152981292,
      "grad_norm": 0.4060916006565094,
      "learning_rate": 8.21045049296153e-06,
      "loss": 0.4319,
      "step": 36327
    },
    {
      "epoch": 1.1159647344330783,
      "grad_norm": 0.4690030515193939,
      "learning_rate": 8.209975019131113e-06,
      "loss": 0.4798,
      "step": 36328
    },
    {
      "epoch": 1.1159954535680274,
      "grad_norm": 0.38235989212989807,
      "learning_rate": 8.20949954948142e-06,
      "loss": 0.5228,
      "step": 36329
    },
    {
      "epoch": 1.1160261727029768,
      "grad_norm": 0.38587701320648193,
      "learning_rate": 8.209024084013569e-06,
      "loss": 0.496,
      "step": 36330
    },
    {
      "epoch": 1.116056891837926,
      "grad_norm": 0.4077600836753845,
      "learning_rate": 8.208548622728664e-06,
      "loss": 0.4958,
      "step": 36331
    },
    {
      "epoch": 1.116087610972875,
      "grad_norm": 0.4066891074180603,
      "learning_rate": 8.208073165627823e-06,
      "loss": 0.4985,
      "step": 36332
    },
    {
      "epoch": 1.1161183301078241,
      "grad_norm": 0.3846379220485687,
      "learning_rate": 8.207597712712149e-06,
      "loss": 0.4719,
      "step": 36333
    },
    {
      "epoch": 1.1161490492427733,
      "grad_norm": 0.3660666346549988,
      "learning_rate": 8.207122263982758e-06,
      "loss": 0.4879,
      "step": 36334
    },
    {
      "epoch": 1.1161797683777226,
      "grad_norm": 0.39436566829681396,
      "learning_rate": 8.206646819440757e-06,
      "loss": 0.4927,
      "step": 36335
    },
    {
      "epoch": 1.1162104875126717,
      "grad_norm": 0.41530412435531616,
      "learning_rate": 8.206171379087258e-06,
      "loss": 0.4943,
      "step": 36336
    },
    {
      "epoch": 1.1162412066476208,
      "grad_norm": 0.3663370907306671,
      "learning_rate": 8.20569594292337e-06,
      "loss": 0.4995,
      "step": 36337
    },
    {
      "epoch": 1.11627192578257,
      "grad_norm": 0.4005286991596222,
      "learning_rate": 8.20522051095021e-06,
      "loss": 0.4645,
      "step": 36338
    },
    {
      "epoch": 1.116302644917519,
      "grad_norm": 0.4134683907032013,
      "learning_rate": 8.204745083168874e-06,
      "loss": 0.5152,
      "step": 36339
    },
    {
      "epoch": 1.1163333640524682,
      "grad_norm": 0.41479629278182983,
      "learning_rate": 8.204269659580487e-06,
      "loss": 0.4364,
      "step": 36340
    },
    {
      "epoch": 1.1163640831874175,
      "grad_norm": 0.4405485987663269,
      "learning_rate": 8.20379424018615e-06,
      "loss": 0.4171,
      "step": 36341
    },
    {
      "epoch": 1.1163948023223667,
      "grad_norm": 0.42628565430641174,
      "learning_rate": 8.203318824986983e-06,
      "loss": 0.4874,
      "step": 36342
    },
    {
      "epoch": 1.1164255214573158,
      "grad_norm": 0.3852342367172241,
      "learning_rate": 8.202843413984083e-06,
      "loss": 0.4391,
      "step": 36343
    },
    {
      "epoch": 1.116456240592265,
      "grad_norm": 0.4032575190067291,
      "learning_rate": 8.202368007178572e-06,
      "loss": 0.5157,
      "step": 36344
    },
    {
      "epoch": 1.116486959727214,
      "grad_norm": 0.38712623715400696,
      "learning_rate": 8.201892604571555e-06,
      "loss": 0.4483,
      "step": 36345
    },
    {
      "epoch": 1.1165176788621634,
      "grad_norm": 0.38775259256362915,
      "learning_rate": 8.20141720616414e-06,
      "loss": 0.5024,
      "step": 36346
    },
    {
      "epoch": 1.1165483979971125,
      "grad_norm": 0.41327154636383057,
      "learning_rate": 8.200941811957449e-06,
      "loss": 0.525,
      "step": 36347
    },
    {
      "epoch": 1.1165791171320616,
      "grad_norm": 0.3904426097869873,
      "learning_rate": 8.200466421952576e-06,
      "loss": 0.5243,
      "step": 36348
    },
    {
      "epoch": 1.1166098362670107,
      "grad_norm": 0.3684883415699005,
      "learning_rate": 8.199991036150646e-06,
      "loss": 0.4722,
      "step": 36349
    },
    {
      "epoch": 1.1166405554019598,
      "grad_norm": 0.45764222741127014,
      "learning_rate": 8.199515654552756e-06,
      "loss": 0.5077,
      "step": 36350
    },
    {
      "epoch": 1.116671274536909,
      "grad_norm": 0.40582045912742615,
      "learning_rate": 8.19904027716003e-06,
      "loss": 0.5872,
      "step": 36351
    },
    {
      "epoch": 1.1167019936718583,
      "grad_norm": 0.3727607727050781,
      "learning_rate": 8.198564903973564e-06,
      "loss": 0.465,
      "step": 36352
    },
    {
      "epoch": 1.1167327128068074,
      "grad_norm": 0.3927478790283203,
      "learning_rate": 8.19808953499448e-06,
      "loss": 0.3982,
      "step": 36353
    },
    {
      "epoch": 1.1167634319417565,
      "grad_norm": 0.3735318183898926,
      "learning_rate": 8.197614170223882e-06,
      "loss": 0.5098,
      "step": 36354
    },
    {
      "epoch": 1.1167941510767057,
      "grad_norm": 0.4022999703884125,
      "learning_rate": 8.197138809662884e-06,
      "loss": 0.4717,
      "step": 36355
    },
    {
      "epoch": 1.1168248702116548,
      "grad_norm": 0.3973110318183899,
      "learning_rate": 8.196663453312592e-06,
      "loss": 0.451,
      "step": 36356
    },
    {
      "epoch": 1.1168555893466041,
      "grad_norm": 0.3716775178909302,
      "learning_rate": 8.19618810117412e-06,
      "loss": 0.4845,
      "step": 36357
    },
    {
      "epoch": 1.1168863084815532,
      "grad_norm": 0.4041096270084381,
      "learning_rate": 8.195712753248575e-06,
      "loss": 0.4341,
      "step": 36358
    },
    {
      "epoch": 1.1169170276165024,
      "grad_norm": 0.3653416335582733,
      "learning_rate": 8.195237409537071e-06,
      "loss": 0.485,
      "step": 36359
    },
    {
      "epoch": 1.1169477467514515,
      "grad_norm": 0.4083595275878906,
      "learning_rate": 8.194762070040713e-06,
      "loss": 0.569,
      "step": 36360
    },
    {
      "epoch": 1.1169784658864006,
      "grad_norm": 0.4402519464492798,
      "learning_rate": 8.194286734760618e-06,
      "loss": 0.5292,
      "step": 36361
    },
    {
      "epoch": 1.1170091850213497,
      "grad_norm": 0.3537764549255371,
      "learning_rate": 8.19381140369789e-06,
      "loss": 0.439,
      "step": 36362
    },
    {
      "epoch": 1.117039904156299,
      "grad_norm": 0.4648404121398926,
      "learning_rate": 8.193336076853642e-06,
      "loss": 0.5063,
      "step": 36363
    },
    {
      "epoch": 1.1170706232912482,
      "grad_norm": 0.41727641224861145,
      "learning_rate": 8.192860754228983e-06,
      "loss": 0.4919,
      "step": 36364
    },
    {
      "epoch": 1.1171013424261973,
      "grad_norm": 0.39407190680503845,
      "learning_rate": 8.192385435825023e-06,
      "loss": 0.512,
      "step": 36365
    },
    {
      "epoch": 1.1171320615611464,
      "grad_norm": 0.4559796154499054,
      "learning_rate": 8.191910121642877e-06,
      "loss": 0.4812,
      "step": 36366
    },
    {
      "epoch": 1.1171627806960955,
      "grad_norm": 0.3875409960746765,
      "learning_rate": 8.191434811683647e-06,
      "loss": 0.5196,
      "step": 36367
    },
    {
      "epoch": 1.1171934998310447,
      "grad_norm": 0.3667628765106201,
      "learning_rate": 8.19095950594845e-06,
      "loss": 0.4949,
      "step": 36368
    },
    {
      "epoch": 1.117224218965994,
      "grad_norm": 0.4749634861946106,
      "learning_rate": 8.190484204438392e-06,
      "loss": 0.5154,
      "step": 36369
    },
    {
      "epoch": 1.1172549381009431,
      "grad_norm": 0.3919699490070343,
      "learning_rate": 8.190008907154587e-06,
      "loss": 0.4661,
      "step": 36370
    },
    {
      "epoch": 1.1172856572358922,
      "grad_norm": 0.4246128797531128,
      "learning_rate": 8.18953361409814e-06,
      "loss": 0.4566,
      "step": 36371
    },
    {
      "epoch": 1.1173163763708414,
      "grad_norm": 0.36109983921051025,
      "learning_rate": 8.189058325270168e-06,
      "loss": 0.4618,
      "step": 36372
    },
    {
      "epoch": 1.1173470955057905,
      "grad_norm": 0.4143454134464264,
      "learning_rate": 8.188583040671771e-06,
      "loss": 0.4982,
      "step": 36373
    },
    {
      "epoch": 1.1173778146407398,
      "grad_norm": 0.3703164756298065,
      "learning_rate": 8.18810776030407e-06,
      "loss": 0.4023,
      "step": 36374
    },
    {
      "epoch": 1.117408533775689,
      "grad_norm": 0.37730303406715393,
      "learning_rate": 8.187632484168163e-06,
      "loss": 0.5053,
      "step": 36375
    },
    {
      "epoch": 1.117439252910638,
      "grad_norm": 0.4049557149410248,
      "learning_rate": 8.187157212265175e-06,
      "loss": 0.5152,
      "step": 36376
    },
    {
      "epoch": 1.1174699720455872,
      "grad_norm": 0.3714270293712616,
      "learning_rate": 8.1866819445962e-06,
      "loss": 0.4897,
      "step": 36377
    },
    {
      "epoch": 1.1175006911805363,
      "grad_norm": 0.45423656702041626,
      "learning_rate": 8.186206681162362e-06,
      "loss": 0.4692,
      "step": 36378
    },
    {
      "epoch": 1.1175314103154854,
      "grad_norm": 0.4162859618663788,
      "learning_rate": 8.185731421964764e-06,
      "loss": 0.5245,
      "step": 36379
    },
    {
      "epoch": 1.1175621294504348,
      "grad_norm": 0.40817174315452576,
      "learning_rate": 8.185256167004517e-06,
      "loss": 0.5594,
      "step": 36380
    },
    {
      "epoch": 1.1175928485853839,
      "grad_norm": 0.3711165487766266,
      "learning_rate": 8.18478091628273e-06,
      "loss": 0.4585,
      "step": 36381
    },
    {
      "epoch": 1.117623567720333,
      "grad_norm": 0.3670102655887604,
      "learning_rate": 8.184305669800508e-06,
      "loss": 0.4106,
      "step": 36382
    },
    {
      "epoch": 1.1176542868552821,
      "grad_norm": 0.37013110518455505,
      "learning_rate": 8.183830427558977e-06,
      "loss": 0.4842,
      "step": 36383
    },
    {
      "epoch": 1.1176850059902312,
      "grad_norm": 0.3728129267692566,
      "learning_rate": 8.183355189559232e-06,
      "loss": 0.4649,
      "step": 36384
    },
    {
      "epoch": 1.1177157251251804,
      "grad_norm": 0.4222761392593384,
      "learning_rate": 8.182879955802388e-06,
      "loss": 0.5329,
      "step": 36385
    },
    {
      "epoch": 1.1177464442601297,
      "grad_norm": 0.43476471304893494,
      "learning_rate": 8.182404726289555e-06,
      "loss": 0.5046,
      "step": 36386
    },
    {
      "epoch": 1.1177771633950788,
      "grad_norm": 0.4003230631351471,
      "learning_rate": 8.181929501021843e-06,
      "loss": 0.5396,
      "step": 36387
    },
    {
      "epoch": 1.117807882530028,
      "grad_norm": 0.44162309169769287,
      "learning_rate": 8.18145428000036e-06,
      "loss": 0.4798,
      "step": 36388
    },
    {
      "epoch": 1.117838601664977,
      "grad_norm": 0.44520556926727295,
      "learning_rate": 8.180979063226221e-06,
      "loss": 0.493,
      "step": 36389
    },
    {
      "epoch": 1.1178693207999262,
      "grad_norm": 0.3750988245010376,
      "learning_rate": 8.18050385070053e-06,
      "loss": 0.4592,
      "step": 36390
    },
    {
      "epoch": 1.1179000399348755,
      "grad_norm": 0.7820866703987122,
      "learning_rate": 8.1800286424244e-06,
      "loss": 0.4391,
      "step": 36391
    },
    {
      "epoch": 1.1179307590698246,
      "grad_norm": 0.3934723734855652,
      "learning_rate": 8.179553438398938e-06,
      "loss": 0.533,
      "step": 36392
    },
    {
      "epoch": 1.1179614782047738,
      "grad_norm": 0.40571165084838867,
      "learning_rate": 8.17907823862526e-06,
      "loss": 0.4431,
      "step": 36393
    },
    {
      "epoch": 1.1179921973397229,
      "grad_norm": 0.4146728217601776,
      "learning_rate": 8.178603043104468e-06,
      "loss": 0.4221,
      "step": 36394
    },
    {
      "epoch": 1.118022916474672,
      "grad_norm": 0.3652135729789734,
      "learning_rate": 8.17812785183768e-06,
      "loss": 0.5179,
      "step": 36395
    },
    {
      "epoch": 1.1180536356096211,
      "grad_norm": 0.411324143409729,
      "learning_rate": 8.177652664825998e-06,
      "loss": 0.4877,
      "step": 36396
    },
    {
      "epoch": 1.1180843547445705,
      "grad_norm": 0.37532666325569153,
      "learning_rate": 8.177177482070537e-06,
      "loss": 0.5034,
      "step": 36397
    },
    {
      "epoch": 1.1181150738795196,
      "grad_norm": 0.36257797479629517,
      "learning_rate": 8.176702303572405e-06,
      "loss": 0.4739,
      "step": 36398
    },
    {
      "epoch": 1.1181457930144687,
      "grad_norm": 0.38641318678855896,
      "learning_rate": 8.176227129332714e-06,
      "loss": 0.5415,
      "step": 36399
    },
    {
      "epoch": 1.1181765121494178,
      "grad_norm": 0.3828403055667877,
      "learning_rate": 8.175751959352569e-06,
      "loss": 0.4372,
      "step": 36400
    },
    {
      "epoch": 1.118207231284367,
      "grad_norm": 0.43896645307540894,
      "learning_rate": 8.175276793633082e-06,
      "loss": 0.3964,
      "step": 36401
    },
    {
      "epoch": 1.1182379504193163,
      "grad_norm": 0.4133467972278595,
      "learning_rate": 8.174801632175367e-06,
      "loss": 0.518,
      "step": 36402
    },
    {
      "epoch": 1.1182686695542654,
      "grad_norm": 0.39341211318969727,
      "learning_rate": 8.174326474980527e-06,
      "loss": 0.4903,
      "step": 36403
    },
    {
      "epoch": 1.1182993886892145,
      "grad_norm": 0.3907738924026489,
      "learning_rate": 8.173851322049678e-06,
      "loss": 0.4391,
      "step": 36404
    },
    {
      "epoch": 1.1183301078241636,
      "grad_norm": 0.390657514333725,
      "learning_rate": 8.173376173383924e-06,
      "loss": 0.5133,
      "step": 36405
    },
    {
      "epoch": 1.1183608269591128,
      "grad_norm": 0.3853166997432709,
      "learning_rate": 8.172901028984382e-06,
      "loss": 0.6022,
      "step": 36406
    },
    {
      "epoch": 1.1183915460940619,
      "grad_norm": 0.3373440206050873,
      "learning_rate": 8.172425888852151e-06,
      "loss": 0.4513,
      "step": 36407
    },
    {
      "epoch": 1.1184222652290112,
      "grad_norm": 0.41529905796051025,
      "learning_rate": 8.171950752988354e-06,
      "loss": 0.4636,
      "step": 36408
    },
    {
      "epoch": 1.1184529843639603,
      "grad_norm": 0.38883450627326965,
      "learning_rate": 8.171475621394086e-06,
      "loss": 0.4946,
      "step": 36409
    },
    {
      "epoch": 1.1184837034989095,
      "grad_norm": 0.4204646050930023,
      "learning_rate": 8.171000494070473e-06,
      "loss": 0.4914,
      "step": 36410
    },
    {
      "epoch": 1.1185144226338586,
      "grad_norm": 0.3850260078907013,
      "learning_rate": 8.170525371018607e-06,
      "loss": 0.531,
      "step": 36411
    },
    {
      "epoch": 1.1185451417688077,
      "grad_norm": 0.39744237065315247,
      "learning_rate": 8.170050252239615e-06,
      "loss": 0.4882,
      "step": 36412
    },
    {
      "epoch": 1.118575860903757,
      "grad_norm": 0.38211163878440857,
      "learning_rate": 8.169575137734593e-06,
      "loss": 0.4964,
      "step": 36413
    },
    {
      "epoch": 1.1186065800387062,
      "grad_norm": 0.4170502722263336,
      "learning_rate": 8.169100027504658e-06,
      "loss": 0.5618,
      "step": 36414
    },
    {
      "epoch": 1.1186372991736553,
      "grad_norm": 0.3876363933086395,
      "learning_rate": 8.168624921550917e-06,
      "loss": 0.5113,
      "step": 36415
    },
    {
      "epoch": 1.1186680183086044,
      "grad_norm": 0.4067496955394745,
      "learning_rate": 8.168149819874482e-06,
      "loss": 0.5511,
      "step": 36416
    },
    {
      "epoch": 1.1186987374435535,
      "grad_norm": 0.3933696150779724,
      "learning_rate": 8.167674722476458e-06,
      "loss": 0.5847,
      "step": 36417
    },
    {
      "epoch": 1.1187294565785026,
      "grad_norm": 0.38870248198509216,
      "learning_rate": 8.167199629357961e-06,
      "loss": 0.4593,
      "step": 36418
    },
    {
      "epoch": 1.118760175713452,
      "grad_norm": 0.40084603428840637,
      "learning_rate": 8.166724540520094e-06,
      "loss": 0.5088,
      "step": 36419
    },
    {
      "epoch": 1.118790894848401,
      "grad_norm": 0.3965952396392822,
      "learning_rate": 8.166249455963972e-06,
      "loss": 0.546,
      "step": 36420
    },
    {
      "epoch": 1.1188216139833502,
      "grad_norm": 0.41876351833343506,
      "learning_rate": 8.165774375690703e-06,
      "loss": 0.5236,
      "step": 36421
    },
    {
      "epoch": 1.1188523331182993,
      "grad_norm": 0.4059271812438965,
      "learning_rate": 8.165299299701394e-06,
      "loss": 0.5337,
      "step": 36422
    },
    {
      "epoch": 1.1188830522532485,
      "grad_norm": 0.4133809506893158,
      "learning_rate": 8.164824227997159e-06,
      "loss": 0.4647,
      "step": 36423
    },
    {
      "epoch": 1.1189137713881978,
      "grad_norm": 0.3706158697605133,
      "learning_rate": 8.164349160579103e-06,
      "loss": 0.4202,
      "step": 36424
    },
    {
      "epoch": 1.118944490523147,
      "grad_norm": 0.3889884352684021,
      "learning_rate": 8.163874097448339e-06,
      "loss": 0.5481,
      "step": 36425
    },
    {
      "epoch": 1.118975209658096,
      "grad_norm": 0.3601617217063904,
      "learning_rate": 8.163399038605974e-06,
      "loss": 0.446,
      "step": 36426
    },
    {
      "epoch": 1.1190059287930452,
      "grad_norm": 0.4105015993118286,
      "learning_rate": 8.16292398405312e-06,
      "loss": 0.434,
      "step": 36427
    },
    {
      "epoch": 1.1190366479279943,
      "grad_norm": 0.3955754041671753,
      "learning_rate": 8.162448933790886e-06,
      "loss": 0.5357,
      "step": 36428
    },
    {
      "epoch": 1.1190673670629434,
      "grad_norm": 0.38188591599464417,
      "learning_rate": 8.16197388782038e-06,
      "loss": 0.5199,
      "step": 36429
    },
    {
      "epoch": 1.1190980861978927,
      "grad_norm": 0.41357094049453735,
      "learning_rate": 8.161498846142711e-06,
      "loss": 0.5265,
      "step": 36430
    },
    {
      "epoch": 1.1191288053328419,
      "grad_norm": 0.42219844460487366,
      "learning_rate": 8.161023808758993e-06,
      "loss": 0.4409,
      "step": 36431
    },
    {
      "epoch": 1.119159524467791,
      "grad_norm": 0.35661056637763977,
      "learning_rate": 8.160548775670329e-06,
      "loss": 0.5143,
      "step": 36432
    },
    {
      "epoch": 1.11919024360274,
      "grad_norm": 0.3819882273674011,
      "learning_rate": 8.160073746877835e-06,
      "loss": 0.4611,
      "step": 36433
    },
    {
      "epoch": 1.1192209627376892,
      "grad_norm": 0.38955849409103394,
      "learning_rate": 8.159598722382613e-06,
      "loss": 0.4373,
      "step": 36434
    },
    {
      "epoch": 1.1192516818726386,
      "grad_norm": 0.42687302827835083,
      "learning_rate": 8.159123702185782e-06,
      "loss": 0.5438,
      "step": 36435
    },
    {
      "epoch": 1.1192824010075877,
      "grad_norm": 0.3706524670124054,
      "learning_rate": 8.15864868628844e-06,
      "loss": 0.4525,
      "step": 36436
    },
    {
      "epoch": 1.1193131201425368,
      "grad_norm": 0.3871396481990814,
      "learning_rate": 8.158173674691706e-06,
      "loss": 0.5633,
      "step": 36437
    },
    {
      "epoch": 1.119343839277486,
      "grad_norm": 0.4130469262599945,
      "learning_rate": 8.157698667396688e-06,
      "loss": 0.5163,
      "step": 36438
    },
    {
      "epoch": 1.119374558412435,
      "grad_norm": 0.36960598826408386,
      "learning_rate": 8.15722366440449e-06,
      "loss": 0.4878,
      "step": 36439
    },
    {
      "epoch": 1.1194052775473842,
      "grad_norm": 0.4264954924583435,
      "learning_rate": 8.156748665716227e-06,
      "loss": 0.4636,
      "step": 36440
    },
    {
      "epoch": 1.1194359966823335,
      "grad_norm": 0.4116571545600891,
      "learning_rate": 8.156273671333004e-06,
      "loss": 0.5535,
      "step": 36441
    },
    {
      "epoch": 1.1194667158172826,
      "grad_norm": 0.3818819224834442,
      "learning_rate": 8.155798681255938e-06,
      "loss": 0.5699,
      "step": 36442
    },
    {
      "epoch": 1.1194974349522318,
      "grad_norm": 0.37822064757347107,
      "learning_rate": 8.155323695486126e-06,
      "loss": 0.4176,
      "step": 36443
    },
    {
      "epoch": 1.1195281540871809,
      "grad_norm": 0.398100346326828,
      "learning_rate": 8.15484871402469e-06,
      "loss": 0.5131,
      "step": 36444
    },
    {
      "epoch": 1.11955887322213,
      "grad_norm": 0.4266163110733032,
      "learning_rate": 8.154373736872727e-06,
      "loss": 0.426,
      "step": 36445
    },
    {
      "epoch": 1.1195895923570793,
      "grad_norm": 0.49329790472984314,
      "learning_rate": 8.153898764031362e-06,
      "loss": 0.504,
      "step": 36446
    },
    {
      "epoch": 1.1196203114920285,
      "grad_norm": 0.3913196623325348,
      "learning_rate": 8.153423795501689e-06,
      "loss": 0.5302,
      "step": 36447
    },
    {
      "epoch": 1.1196510306269776,
      "grad_norm": 0.4805942177772522,
      "learning_rate": 8.152948831284825e-06,
      "loss": 0.5258,
      "step": 36448
    },
    {
      "epoch": 1.1196817497619267,
      "grad_norm": 0.4108848571777344,
      "learning_rate": 8.152473871381878e-06,
      "loss": 0.4766,
      "step": 36449
    },
    {
      "epoch": 1.1197124688968758,
      "grad_norm": 0.38747864961624146,
      "learning_rate": 8.151998915793957e-06,
      "loss": 0.4605,
      "step": 36450
    },
    {
      "epoch": 1.119743188031825,
      "grad_norm": 0.39753231406211853,
      "learning_rate": 8.151523964522173e-06,
      "loss": 0.4559,
      "step": 36451
    },
    {
      "epoch": 1.1197739071667743,
      "grad_norm": 0.38160762190818787,
      "learning_rate": 8.151049017567634e-06,
      "loss": 0.5448,
      "step": 36452
    },
    {
      "epoch": 1.1198046263017234,
      "grad_norm": 0.36182481050491333,
      "learning_rate": 8.150574074931447e-06,
      "loss": 0.5284,
      "step": 36453
    },
    {
      "epoch": 1.1198353454366725,
      "grad_norm": 0.4389762580394745,
      "learning_rate": 8.150099136614726e-06,
      "loss": 0.4703,
      "step": 36454
    },
    {
      "epoch": 1.1198660645716216,
      "grad_norm": 0.586388111114502,
      "learning_rate": 8.149624202618575e-06,
      "loss": 0.4548,
      "step": 36455
    },
    {
      "epoch": 1.1198967837065708,
      "grad_norm": 0.3898521661758423,
      "learning_rate": 8.149149272944106e-06,
      "loss": 0.518,
      "step": 36456
    },
    {
      "epoch": 1.11992750284152,
      "grad_norm": 0.4172675609588623,
      "learning_rate": 8.148674347592429e-06,
      "loss": 0.5478,
      "step": 36457
    },
    {
      "epoch": 1.1199582219764692,
      "grad_norm": 0.40319550037384033,
      "learning_rate": 8.148199426564652e-06,
      "loss": 0.4441,
      "step": 36458
    },
    {
      "epoch": 1.1199889411114183,
      "grad_norm": 0.3826221227645874,
      "learning_rate": 8.147724509861886e-06,
      "loss": 0.4928,
      "step": 36459
    },
    {
      "epoch": 1.1200196602463675,
      "grad_norm": 0.3743147850036621,
      "learning_rate": 8.147249597485238e-06,
      "loss": 0.473,
      "step": 36460
    },
    {
      "epoch": 1.1200503793813166,
      "grad_norm": 0.3781511187553406,
      "learning_rate": 8.146774689435818e-06,
      "loss": 0.469,
      "step": 36461
    },
    {
      "epoch": 1.1200810985162657,
      "grad_norm": 0.6438694596290588,
      "learning_rate": 8.146299785714734e-06,
      "loss": 0.5073,
      "step": 36462
    },
    {
      "epoch": 1.120111817651215,
      "grad_norm": 0.38433927297592163,
      "learning_rate": 8.145824886323099e-06,
      "loss": 0.5779,
      "step": 36463
    },
    {
      "epoch": 1.1201425367861642,
      "grad_norm": 0.3854932487010956,
      "learning_rate": 8.145349991262016e-06,
      "loss": 0.5414,
      "step": 36464
    },
    {
      "epoch": 1.1201732559211133,
      "grad_norm": 0.39084386825561523,
      "learning_rate": 8.144875100532601e-06,
      "loss": 0.403,
      "step": 36465
    },
    {
      "epoch": 1.1202039750560624,
      "grad_norm": 0.397830605506897,
      "learning_rate": 8.144400214135956e-06,
      "loss": 0.4823,
      "step": 36466
    },
    {
      "epoch": 1.1202346941910115,
      "grad_norm": 0.4116213023662567,
      "learning_rate": 8.143925332073199e-06,
      "loss": 0.5426,
      "step": 36467
    },
    {
      "epoch": 1.1202654133259609,
      "grad_norm": 0.3843042552471161,
      "learning_rate": 8.14345045434543e-06,
      "loss": 0.5521,
      "step": 36468
    },
    {
      "epoch": 1.12029613246091,
      "grad_norm": 0.3848385810852051,
      "learning_rate": 8.142975580953764e-06,
      "loss": 0.4716,
      "step": 36469
    },
    {
      "epoch": 1.120326851595859,
      "grad_norm": 0.38584503531455994,
      "learning_rate": 8.142500711899307e-06,
      "loss": 0.524,
      "step": 36470
    },
    {
      "epoch": 1.1203575707308082,
      "grad_norm": 0.3833138644695282,
      "learning_rate": 8.142025847183171e-06,
      "loss": 0.4833,
      "step": 36471
    },
    {
      "epoch": 1.1203882898657573,
      "grad_norm": 0.44277825951576233,
      "learning_rate": 8.141550986806458e-06,
      "loss": 0.5612,
      "step": 36472
    },
    {
      "epoch": 1.1204190090007065,
      "grad_norm": 0.39741283655166626,
      "learning_rate": 8.141076130770286e-06,
      "loss": 0.536,
      "step": 36473
    },
    {
      "epoch": 1.1204497281356558,
      "grad_norm": 0.41740450263023376,
      "learning_rate": 8.140601279075764e-06,
      "loss": 0.4924,
      "step": 36474
    },
    {
      "epoch": 1.120480447270605,
      "grad_norm": 0.40180703997612,
      "learning_rate": 8.140126431723994e-06,
      "loss": 0.5347,
      "step": 36475
    },
    {
      "epoch": 1.120511166405554,
      "grad_norm": 0.39028599858283997,
      "learning_rate": 8.139651588716091e-06,
      "loss": 0.5043,
      "step": 36476
    },
    {
      "epoch": 1.1205418855405032,
      "grad_norm": 0.4298003017902374,
      "learning_rate": 8.139176750053158e-06,
      "loss": 0.4315,
      "step": 36477
    },
    {
      "epoch": 1.1205726046754523,
      "grad_norm": 0.4136304259300232,
      "learning_rate": 8.138701915736313e-06,
      "loss": 0.4998,
      "step": 36478
    },
    {
      "epoch": 1.1206033238104014,
      "grad_norm": 0.381378710269928,
      "learning_rate": 8.138227085766653e-06,
      "loss": 0.4898,
      "step": 36479
    },
    {
      "epoch": 1.1206340429453507,
      "grad_norm": 0.388313353061676,
      "learning_rate": 8.1377522601453e-06,
      "loss": 0.552,
      "step": 36480
    },
    {
      "epoch": 1.1206647620802999,
      "grad_norm": 0.43555977940559387,
      "learning_rate": 8.13727743887335e-06,
      "loss": 0.4528,
      "step": 36481
    },
    {
      "epoch": 1.120695481215249,
      "grad_norm": 0.3658747971057892,
      "learning_rate": 8.136802621951924e-06,
      "loss": 0.4575,
      "step": 36482
    },
    {
      "epoch": 1.120726200350198,
      "grad_norm": 0.44120317697525024,
      "learning_rate": 8.136327809382124e-06,
      "loss": 0.4552,
      "step": 36483
    },
    {
      "epoch": 1.1207569194851472,
      "grad_norm": 0.3978351950645447,
      "learning_rate": 8.135853001165061e-06,
      "loss": 0.4234,
      "step": 36484
    },
    {
      "epoch": 1.1207876386200966,
      "grad_norm": 0.3633003234863281,
      "learning_rate": 8.135378197301842e-06,
      "loss": 0.5799,
      "step": 36485
    },
    {
      "epoch": 1.1208183577550457,
      "grad_norm": 0.4820171296596527,
      "learning_rate": 8.13490339779358e-06,
      "loss": 0.4667,
      "step": 36486
    },
    {
      "epoch": 1.1208490768899948,
      "grad_norm": 0.3958112597465515,
      "learning_rate": 8.134428602641378e-06,
      "loss": 0.4789,
      "step": 36487
    },
    {
      "epoch": 1.120879796024944,
      "grad_norm": 0.384402871131897,
      "learning_rate": 8.133953811846352e-06,
      "loss": 0.6011,
      "step": 36488
    },
    {
      "epoch": 1.120910515159893,
      "grad_norm": 0.4347565472126007,
      "learning_rate": 8.133479025409605e-06,
      "loss": 0.4741,
      "step": 36489
    },
    {
      "epoch": 1.1209412342948422,
      "grad_norm": 0.4201759397983551,
      "learning_rate": 8.133004243332248e-06,
      "loss": 0.5506,
      "step": 36490
    },
    {
      "epoch": 1.1209719534297915,
      "grad_norm": 0.4135158061981201,
      "learning_rate": 8.132529465615388e-06,
      "loss": 0.4468,
      "step": 36491
    },
    {
      "epoch": 1.1210026725647406,
      "grad_norm": 0.4390754699707031,
      "learning_rate": 8.132054692260138e-06,
      "loss": 0.4408,
      "step": 36492
    },
    {
      "epoch": 1.1210333916996897,
      "grad_norm": 0.46917787194252014,
      "learning_rate": 8.131579923267606e-06,
      "loss": 0.4304,
      "step": 36493
    },
    {
      "epoch": 1.1210641108346389,
      "grad_norm": 0.3488259017467499,
      "learning_rate": 8.131105158638898e-06,
      "loss": 0.4545,
      "step": 36494
    },
    {
      "epoch": 1.121094829969588,
      "grad_norm": 0.4308486580848694,
      "learning_rate": 8.130630398375126e-06,
      "loss": 0.4352,
      "step": 36495
    },
    {
      "epoch": 1.121125549104537,
      "grad_norm": 0.40323346853256226,
      "learning_rate": 8.130155642477395e-06,
      "loss": 0.4198,
      "step": 36496
    },
    {
      "epoch": 1.1211562682394864,
      "grad_norm": 0.40151917934417725,
      "learning_rate": 8.129680890946818e-06,
      "loss": 0.4958,
      "step": 36497
    },
    {
      "epoch": 1.1211869873744356,
      "grad_norm": 0.4679749310016632,
      "learning_rate": 8.1292061437845e-06,
      "loss": 0.5087,
      "step": 36498
    },
    {
      "epoch": 1.1212177065093847,
      "grad_norm": 0.3911607563495636,
      "learning_rate": 8.128731400991554e-06,
      "loss": 0.4902,
      "step": 36499
    },
    {
      "epoch": 1.1212484256443338,
      "grad_norm": 0.714244544506073,
      "learning_rate": 8.128256662569084e-06,
      "loss": 0.4911,
      "step": 36500
    },
    {
      "epoch": 1.121279144779283,
      "grad_norm": 0.4025557041168213,
      "learning_rate": 8.127781928518203e-06,
      "loss": 0.4999,
      "step": 36501
    },
    {
      "epoch": 1.1213098639142323,
      "grad_norm": 0.40950626134872437,
      "learning_rate": 8.127307198840017e-06,
      "loss": 0.5586,
      "step": 36502
    },
    {
      "epoch": 1.1213405830491814,
      "grad_norm": 0.3894093334674835,
      "learning_rate": 8.126832473535637e-06,
      "loss": 0.3638,
      "step": 36503
    },
    {
      "epoch": 1.1213713021841305,
      "grad_norm": 0.38852015137672424,
      "learning_rate": 8.12635775260617e-06,
      "loss": 0.5706,
      "step": 36504
    },
    {
      "epoch": 1.1214020213190796,
      "grad_norm": 0.428307443857193,
      "learning_rate": 8.125883036052729e-06,
      "loss": 0.4763,
      "step": 36505
    },
    {
      "epoch": 1.1214327404540287,
      "grad_norm": 0.5039339661598206,
      "learning_rate": 8.125408323876412e-06,
      "loss": 0.4171,
      "step": 36506
    },
    {
      "epoch": 1.1214634595889779,
      "grad_norm": 0.38562729954719543,
      "learning_rate": 8.124933616078341e-06,
      "loss": 0.4441,
      "step": 36507
    },
    {
      "epoch": 1.1214941787239272,
      "grad_norm": 0.4460655152797699,
      "learning_rate": 8.124458912659612e-06,
      "loss": 0.4832,
      "step": 36508
    },
    {
      "epoch": 1.1215248978588763,
      "grad_norm": 0.4659549295902252,
      "learning_rate": 8.123984213621347e-06,
      "loss": 0.5035,
      "step": 36509
    },
    {
      "epoch": 1.1215556169938254,
      "grad_norm": 0.38649535179138184,
      "learning_rate": 8.123509518964641e-06,
      "loss": 0.5472,
      "step": 36510
    },
    {
      "epoch": 1.1215863361287746,
      "grad_norm": 0.3937267065048218,
      "learning_rate": 8.123034828690613e-06,
      "loss": 0.4543,
      "step": 36511
    },
    {
      "epoch": 1.1216170552637237,
      "grad_norm": 0.4232015311717987,
      "learning_rate": 8.122560142800371e-06,
      "loss": 0.5089,
      "step": 36512
    },
    {
      "epoch": 1.121647774398673,
      "grad_norm": 0.392724871635437,
      "learning_rate": 8.122085461295018e-06,
      "loss": 0.531,
      "step": 36513
    },
    {
      "epoch": 1.1216784935336221,
      "grad_norm": 0.42972487211227417,
      "learning_rate": 8.121610784175668e-06,
      "loss": 0.5062,
      "step": 36514
    },
    {
      "epoch": 1.1217092126685713,
      "grad_norm": 0.6345405578613281,
      "learning_rate": 8.121136111443421e-06,
      "loss": 0.5353,
      "step": 36515
    },
    {
      "epoch": 1.1217399318035204,
      "grad_norm": 0.40633726119995117,
      "learning_rate": 8.1206614430994e-06,
      "loss": 0.5026,
      "step": 36516
    },
    {
      "epoch": 1.1217706509384695,
      "grad_norm": 0.39332470297813416,
      "learning_rate": 8.1201867791447e-06,
      "loss": 0.5426,
      "step": 36517
    },
    {
      "epoch": 1.1218013700734186,
      "grad_norm": 0.3931262195110321,
      "learning_rate": 8.119712119580438e-06,
      "loss": 0.4917,
      "step": 36518
    },
    {
      "epoch": 1.121832089208368,
      "grad_norm": 0.3897412121295929,
      "learning_rate": 8.119237464407717e-06,
      "loss": 0.4536,
      "step": 36519
    },
    {
      "epoch": 1.121862808343317,
      "grad_norm": 0.4209316670894623,
      "learning_rate": 8.118762813627652e-06,
      "loss": 0.6293,
      "step": 36520
    },
    {
      "epoch": 1.1218935274782662,
      "grad_norm": 0.377167284488678,
      "learning_rate": 8.118288167241343e-06,
      "loss": 0.4485,
      "step": 36521
    },
    {
      "epoch": 1.1219242466132153,
      "grad_norm": 0.36898088455200195,
      "learning_rate": 8.117813525249907e-06,
      "loss": 0.5292,
      "step": 36522
    },
    {
      "epoch": 1.1219549657481644,
      "grad_norm": 0.3778228163719177,
      "learning_rate": 8.117338887654447e-06,
      "loss": 0.5058,
      "step": 36523
    },
    {
      "epoch": 1.1219856848831138,
      "grad_norm": 0.42500999569892883,
      "learning_rate": 8.116864254456075e-06,
      "loss": 0.4585,
      "step": 36524
    },
    {
      "epoch": 1.122016404018063,
      "grad_norm": 0.3783986270427704,
      "learning_rate": 8.116389625655896e-06,
      "loss": 0.5832,
      "step": 36525
    },
    {
      "epoch": 1.122047123153012,
      "grad_norm": 0.3975417912006378,
      "learning_rate": 8.115915001255024e-06,
      "loss": 0.6028,
      "step": 36526
    },
    {
      "epoch": 1.1220778422879611,
      "grad_norm": 0.39301106333732605,
      "learning_rate": 8.11544038125456e-06,
      "loss": 0.4847,
      "step": 36527
    },
    {
      "epoch": 1.1221085614229103,
      "grad_norm": 0.43588191270828247,
      "learning_rate": 8.114965765655618e-06,
      "loss": 0.4623,
      "step": 36528
    },
    {
      "epoch": 1.1221392805578594,
      "grad_norm": 0.4244876801967621,
      "learning_rate": 8.114491154459306e-06,
      "loss": 0.4972,
      "step": 36529
    },
    {
      "epoch": 1.1221699996928087,
      "grad_norm": 0.42379459738731384,
      "learning_rate": 8.11401654766673e-06,
      "loss": 0.4448,
      "step": 36530
    },
    {
      "epoch": 1.1222007188277578,
      "grad_norm": 0.3708704710006714,
      "learning_rate": 8.113541945279003e-06,
      "loss": 0.503,
      "step": 36531
    },
    {
      "epoch": 1.122231437962707,
      "grad_norm": 0.3902510702610016,
      "learning_rate": 8.113067347297227e-06,
      "loss": 0.5152,
      "step": 36532
    },
    {
      "epoch": 1.122262157097656,
      "grad_norm": 0.44317227602005005,
      "learning_rate": 8.112592753722518e-06,
      "loss": 0.4598,
      "step": 36533
    },
    {
      "epoch": 1.1222928762326052,
      "grad_norm": 0.39968201518058777,
      "learning_rate": 8.112118164555978e-06,
      "loss": 0.4949,
      "step": 36534
    },
    {
      "epoch": 1.1223235953675545,
      "grad_norm": 0.4224444627761841,
      "learning_rate": 8.111643579798718e-06,
      "loss": 0.4773,
      "step": 36535
    },
    {
      "epoch": 1.1223543145025037,
      "grad_norm": 0.4672848582267761,
      "learning_rate": 8.111168999451846e-06,
      "loss": 0.5064,
      "step": 36536
    },
    {
      "epoch": 1.1223850336374528,
      "grad_norm": 0.37999218702316284,
      "learning_rate": 8.110694423516472e-06,
      "loss": 0.4722,
      "step": 36537
    },
    {
      "epoch": 1.122415752772402,
      "grad_norm": 0.3914923667907715,
      "learning_rate": 8.110219851993702e-06,
      "loss": 0.5019,
      "step": 36538
    },
    {
      "epoch": 1.122446471907351,
      "grad_norm": 0.399872750043869,
      "learning_rate": 8.109745284884649e-06,
      "loss": 0.5118,
      "step": 36539
    },
    {
      "epoch": 1.1224771910423001,
      "grad_norm": 0.3673505485057831,
      "learning_rate": 8.109270722190411e-06,
      "loss": 0.491,
      "step": 36540
    },
    {
      "epoch": 1.1225079101772495,
      "grad_norm": 0.440313458442688,
      "learning_rate": 8.10879616391211e-06,
      "loss": 0.4509,
      "step": 36541
    },
    {
      "epoch": 1.1225386293121986,
      "grad_norm": 0.4328891336917877,
      "learning_rate": 8.108321610050842e-06,
      "loss": 0.4807,
      "step": 36542
    },
    {
      "epoch": 1.1225693484471477,
      "grad_norm": 0.3907163441181183,
      "learning_rate": 8.107847060607727e-06,
      "loss": 0.4991,
      "step": 36543
    },
    {
      "epoch": 1.1226000675820968,
      "grad_norm": 0.36619508266448975,
      "learning_rate": 8.10737251558386e-06,
      "loss": 0.492,
      "step": 36544
    },
    {
      "epoch": 1.122630786717046,
      "grad_norm": 0.3610757887363434,
      "learning_rate": 8.106897974980363e-06,
      "loss": 0.4541,
      "step": 36545
    },
    {
      "epoch": 1.1226615058519953,
      "grad_norm": 0.4155515730381012,
      "learning_rate": 8.106423438798336e-06,
      "loss": 0.4802,
      "step": 36546
    },
    {
      "epoch": 1.1226922249869444,
      "grad_norm": 0.35065069794654846,
      "learning_rate": 8.105948907038885e-06,
      "loss": 0.4656,
      "step": 36547
    },
    {
      "epoch": 1.1227229441218936,
      "grad_norm": 0.4062114655971527,
      "learning_rate": 8.10547437970313e-06,
      "loss": 0.5032,
      "step": 36548
    },
    {
      "epoch": 1.1227536632568427,
      "grad_norm": 0.36947184801101685,
      "learning_rate": 8.104999856792164e-06,
      "loss": 0.4275,
      "step": 36549
    },
    {
      "epoch": 1.1227843823917918,
      "grad_norm": 0.3974300026893616,
      "learning_rate": 8.104525338307112e-06,
      "loss": 0.503,
      "step": 36550
    },
    {
      "epoch": 1.122815101526741,
      "grad_norm": 0.3837025761604309,
      "learning_rate": 8.104050824249066e-06,
      "loss": 0.4745,
      "step": 36551
    },
    {
      "epoch": 1.1228458206616903,
      "grad_norm": 0.348881334066391,
      "learning_rate": 8.103576314619149e-06,
      "loss": 0.5168,
      "step": 36552
    },
    {
      "epoch": 1.1228765397966394,
      "grad_norm": 0.39210784435272217,
      "learning_rate": 8.103101809418455e-06,
      "loss": 0.4931,
      "step": 36553
    },
    {
      "epoch": 1.1229072589315885,
      "grad_norm": 0.37047648429870605,
      "learning_rate": 8.102627308648103e-06,
      "loss": 0.45,
      "step": 36554
    },
    {
      "epoch": 1.1229379780665376,
      "grad_norm": 0.3863775134086609,
      "learning_rate": 8.102152812309196e-06,
      "loss": 0.4445,
      "step": 36555
    },
    {
      "epoch": 1.1229686972014867,
      "grad_norm": 0.3792617917060852,
      "learning_rate": 8.101678320402845e-06,
      "loss": 0.4135,
      "step": 36556
    },
    {
      "epoch": 1.122999416336436,
      "grad_norm": 0.3786957859992981,
      "learning_rate": 8.101203832930155e-06,
      "loss": 0.5091,
      "step": 36557
    },
    {
      "epoch": 1.1230301354713852,
      "grad_norm": 0.4282900094985962,
      "learning_rate": 8.100729349892237e-06,
      "loss": 0.5294,
      "step": 36558
    },
    {
      "epoch": 1.1230608546063343,
      "grad_norm": 0.3598741888999939,
      "learning_rate": 8.100254871290199e-06,
      "loss": 0.4773,
      "step": 36559
    },
    {
      "epoch": 1.1230915737412834,
      "grad_norm": 0.39360934495925903,
      "learning_rate": 8.099780397125148e-06,
      "loss": 0.4058,
      "step": 36560
    },
    {
      "epoch": 1.1231222928762326,
      "grad_norm": 0.5079706907272339,
      "learning_rate": 8.09930592739819e-06,
      "loss": 0.4208,
      "step": 36561
    },
    {
      "epoch": 1.1231530120111817,
      "grad_norm": 0.45307672023773193,
      "learning_rate": 8.09883146211044e-06,
      "loss": 0.5274,
      "step": 36562
    },
    {
      "epoch": 1.123183731146131,
      "grad_norm": 0.3834635317325592,
      "learning_rate": 8.098357001262998e-06,
      "loss": 0.4835,
      "step": 36563
    },
    {
      "epoch": 1.1232144502810801,
      "grad_norm": 0.37009966373443604,
      "learning_rate": 8.097882544856979e-06,
      "loss": 0.4983,
      "step": 36564
    },
    {
      "epoch": 1.1232451694160293,
      "grad_norm": 0.3965339958667755,
      "learning_rate": 8.097408092893487e-06,
      "loss": 0.4698,
      "step": 36565
    },
    {
      "epoch": 1.1232758885509784,
      "grad_norm": 0.4239524006843567,
      "learning_rate": 8.09693364537363e-06,
      "loss": 0.4527,
      "step": 36566
    },
    {
      "epoch": 1.1233066076859275,
      "grad_norm": 0.4749658703804016,
      "learning_rate": 8.09645920229852e-06,
      "loss": 0.4175,
      "step": 36567
    },
    {
      "epoch": 1.1233373268208768,
      "grad_norm": 0.38761094212532043,
      "learning_rate": 8.09598476366926e-06,
      "loss": 0.4763,
      "step": 36568
    },
    {
      "epoch": 1.123368045955826,
      "grad_norm": 0.42758095264434814,
      "learning_rate": 8.095510329486963e-06,
      "loss": 0.4725,
      "step": 36569
    },
    {
      "epoch": 1.123398765090775,
      "grad_norm": 0.38419121503829956,
      "learning_rate": 8.095035899752732e-06,
      "loss": 0.4502,
      "step": 36570
    },
    {
      "epoch": 1.1234294842257242,
      "grad_norm": 0.40605655312538147,
      "learning_rate": 8.094561474467681e-06,
      "loss": 0.4119,
      "step": 36571
    },
    {
      "epoch": 1.1234602033606733,
      "grad_norm": 0.4287356734275818,
      "learning_rate": 8.09408705363291e-06,
      "loss": 0.5291,
      "step": 36572
    },
    {
      "epoch": 1.1234909224956224,
      "grad_norm": 0.3965205252170563,
      "learning_rate": 8.093612637249537e-06,
      "loss": 0.4759,
      "step": 36573
    },
    {
      "epoch": 1.1235216416305718,
      "grad_norm": 0.3704223930835724,
      "learning_rate": 8.093138225318661e-06,
      "loss": 0.4694,
      "step": 36574
    },
    {
      "epoch": 1.123552360765521,
      "grad_norm": 0.4278491735458374,
      "learning_rate": 8.092663817841398e-06,
      "loss": 0.536,
      "step": 36575
    },
    {
      "epoch": 1.12358307990047,
      "grad_norm": 0.40391311049461365,
      "learning_rate": 8.092189414818846e-06,
      "loss": 0.3993,
      "step": 36576
    },
    {
      "epoch": 1.1236137990354191,
      "grad_norm": 0.4199172258377075,
      "learning_rate": 8.091715016252126e-06,
      "loss": 0.5657,
      "step": 36577
    },
    {
      "epoch": 1.1236445181703683,
      "grad_norm": 0.3981613218784332,
      "learning_rate": 8.091240622142331e-06,
      "loss": 0.4683,
      "step": 36578
    },
    {
      "epoch": 1.1236752373053176,
      "grad_norm": 0.383688360452652,
      "learning_rate": 8.090766232490584e-06,
      "loss": 0.5085,
      "step": 36579
    },
    {
      "epoch": 1.1237059564402667,
      "grad_norm": 0.4029853045940399,
      "learning_rate": 8.090291847297982e-06,
      "loss": 0.4481,
      "step": 36580
    },
    {
      "epoch": 1.1237366755752158,
      "grad_norm": 0.3565370738506317,
      "learning_rate": 8.089817466565639e-06,
      "loss": 0.4556,
      "step": 36581
    },
    {
      "epoch": 1.123767394710165,
      "grad_norm": 0.3444245755672455,
      "learning_rate": 8.089343090294657e-06,
      "loss": 0.4596,
      "step": 36582
    },
    {
      "epoch": 1.123798113845114,
      "grad_norm": 0.36422640085220337,
      "learning_rate": 8.088868718486145e-06,
      "loss": 0.528,
      "step": 36583
    },
    {
      "epoch": 1.1238288329800632,
      "grad_norm": 0.40835142135620117,
      "learning_rate": 8.088394351141222e-06,
      "loss": 0.5119,
      "step": 36584
    },
    {
      "epoch": 1.1238595521150125,
      "grad_norm": 0.39016193151474,
      "learning_rate": 8.087919988260981e-06,
      "loss": 0.4946,
      "step": 36585
    },
    {
      "epoch": 1.1238902712499617,
      "grad_norm": 0.3969264328479767,
      "learning_rate": 8.087445629846542e-06,
      "loss": 0.4863,
      "step": 36586
    },
    {
      "epoch": 1.1239209903849108,
      "grad_norm": 0.41438326239585876,
      "learning_rate": 8.086971275899003e-06,
      "loss": 0.5052,
      "step": 36587
    },
    {
      "epoch": 1.12395170951986,
      "grad_norm": 0.39551132917404175,
      "learning_rate": 8.08649692641948e-06,
      "loss": 0.4869,
      "step": 36588
    },
    {
      "epoch": 1.123982428654809,
      "grad_norm": 0.34735673666000366,
      "learning_rate": 8.086022581409074e-06,
      "loss": 0.4858,
      "step": 36589
    },
    {
      "epoch": 1.1240131477897581,
      "grad_norm": 0.43654659390449524,
      "learning_rate": 8.085548240868896e-06,
      "loss": 0.5147,
      "step": 36590
    },
    {
      "epoch": 1.1240438669247075,
      "grad_norm": 0.43735232949256897,
      "learning_rate": 8.085073904800053e-06,
      "loss": 0.6155,
      "step": 36591
    },
    {
      "epoch": 1.1240745860596566,
      "grad_norm": 0.42166876792907715,
      "learning_rate": 8.084599573203658e-06,
      "loss": 0.5011,
      "step": 36592
    },
    {
      "epoch": 1.1241053051946057,
      "grad_norm": 0.42203736305236816,
      "learning_rate": 8.08412524608081e-06,
      "loss": 0.4285,
      "step": 36593
    },
    {
      "epoch": 1.1241360243295548,
      "grad_norm": 0.3695298731327057,
      "learning_rate": 8.083650923432624e-06,
      "loss": 0.433,
      "step": 36594
    },
    {
      "epoch": 1.124166743464504,
      "grad_norm": 0.3715103566646576,
      "learning_rate": 8.083176605260203e-06,
      "loss": 0.489,
      "step": 36595
    },
    {
      "epoch": 1.1241974625994533,
      "grad_norm": 0.3924229145050049,
      "learning_rate": 8.082702291564658e-06,
      "loss": 0.5289,
      "step": 36596
    },
    {
      "epoch": 1.1242281817344024,
      "grad_norm": 0.3581947684288025,
      "learning_rate": 8.082227982347095e-06,
      "loss": 0.4985,
      "step": 36597
    },
    {
      "epoch": 1.1242589008693515,
      "grad_norm": 0.47993403673171997,
      "learning_rate": 8.081753677608624e-06,
      "loss": 0.4779,
      "step": 36598
    },
    {
      "epoch": 1.1242896200043007,
      "grad_norm": 0.4450210630893707,
      "learning_rate": 8.081279377350348e-06,
      "loss": 0.4845,
      "step": 36599
    },
    {
      "epoch": 1.1243203391392498,
      "grad_norm": 0.4239077568054199,
      "learning_rate": 8.080805081573382e-06,
      "loss": 0.4622,
      "step": 36600
    },
    {
      "epoch": 1.124351058274199,
      "grad_norm": 0.3782675266265869,
      "learning_rate": 8.080330790278828e-06,
      "loss": 0.4951,
      "step": 36601
    },
    {
      "epoch": 1.1243817774091482,
      "grad_norm": 0.39032143354415894,
      "learning_rate": 8.079856503467793e-06,
      "loss": 0.5222,
      "step": 36602
    },
    {
      "epoch": 1.1244124965440974,
      "grad_norm": 0.40134328603744507,
      "learning_rate": 8.079382221141392e-06,
      "loss": 0.4405,
      "step": 36603
    },
    {
      "epoch": 1.1244432156790465,
      "grad_norm": 0.37214693427085876,
      "learning_rate": 8.078907943300724e-06,
      "loss": 0.489,
      "step": 36604
    },
    {
      "epoch": 1.1244739348139956,
      "grad_norm": 0.3652556240558624,
      "learning_rate": 8.078433669946904e-06,
      "loss": 0.5254,
      "step": 36605
    },
    {
      "epoch": 1.1245046539489447,
      "grad_norm": 0.3556540012359619,
      "learning_rate": 8.077959401081033e-06,
      "loss": 0.5299,
      "step": 36606
    },
    {
      "epoch": 1.1245353730838938,
      "grad_norm": 0.369933158159256,
      "learning_rate": 8.077485136704225e-06,
      "loss": 0.4785,
      "step": 36607
    },
    {
      "epoch": 1.1245660922188432,
      "grad_norm": 0.3793730139732361,
      "learning_rate": 8.077010876817583e-06,
      "loss": 0.5041,
      "step": 36608
    },
    {
      "epoch": 1.1245968113537923,
      "grad_norm": 0.40478256344795227,
      "learning_rate": 8.07653662142222e-06,
      "loss": 0.5309,
      "step": 36609
    },
    {
      "epoch": 1.1246275304887414,
      "grad_norm": 0.37304550409317017,
      "learning_rate": 8.076062370519233e-06,
      "loss": 0.4328,
      "step": 36610
    },
    {
      "epoch": 1.1246582496236905,
      "grad_norm": 0.39981862902641296,
      "learning_rate": 8.075588124109744e-06,
      "loss": 0.4886,
      "step": 36611
    },
    {
      "epoch": 1.1246889687586397,
      "grad_norm": 0.4175029993057251,
      "learning_rate": 8.075113882194847e-06,
      "loss": 0.5194,
      "step": 36612
    },
    {
      "epoch": 1.124719687893589,
      "grad_norm": 0.39023762941360474,
      "learning_rate": 8.074639644775663e-06,
      "loss": 0.5087,
      "step": 36613
    },
    {
      "epoch": 1.1247504070285381,
      "grad_norm": 0.4645942151546478,
      "learning_rate": 8.074165411853285e-06,
      "loss": 0.454,
      "step": 36614
    },
    {
      "epoch": 1.1247811261634872,
      "grad_norm": 0.3961411714553833,
      "learning_rate": 8.073691183428834e-06,
      "loss": 0.4946,
      "step": 36615
    },
    {
      "epoch": 1.1248118452984364,
      "grad_norm": 0.38794460892677307,
      "learning_rate": 8.07321695950341e-06,
      "loss": 0.5009,
      "step": 36616
    },
    {
      "epoch": 1.1248425644333855,
      "grad_norm": 0.4006175994873047,
      "learning_rate": 8.072742740078122e-06,
      "loss": 0.4109,
      "step": 36617
    },
    {
      "epoch": 1.1248732835683346,
      "grad_norm": 0.39254844188690186,
      "learning_rate": 8.072268525154076e-06,
      "loss": 0.4577,
      "step": 36618
    },
    {
      "epoch": 1.124904002703284,
      "grad_norm": 0.3907023072242737,
      "learning_rate": 8.071794314732381e-06,
      "loss": 0.5243,
      "step": 36619
    },
    {
      "epoch": 1.124934721838233,
      "grad_norm": 0.36693865060806274,
      "learning_rate": 8.07132010881415e-06,
      "loss": 0.4452,
      "step": 36620
    },
    {
      "epoch": 1.1249654409731822,
      "grad_norm": 0.3648204803466797,
      "learning_rate": 8.070845907400483e-06,
      "loss": 0.4176,
      "step": 36621
    },
    {
      "epoch": 1.1249961601081313,
      "grad_norm": 0.43844014406204224,
      "learning_rate": 8.07037171049249e-06,
      "loss": 0.5834,
      "step": 36622
    },
    {
      "epoch": 1.1250268792430804,
      "grad_norm": 0.3980101943016052,
      "learning_rate": 8.069897518091277e-06,
      "loss": 0.5193,
      "step": 36623
    },
    {
      "epoch": 1.1250575983780298,
      "grad_norm": 0.4011548161506653,
      "learning_rate": 8.069423330197957e-06,
      "loss": 0.5513,
      "step": 36624
    },
    {
      "epoch": 1.1250883175129789,
      "grad_norm": 0.39845913648605347,
      "learning_rate": 8.06894914681363e-06,
      "loss": 0.463,
      "step": 36625
    },
    {
      "epoch": 1.125119036647928,
      "grad_norm": 0.43545496463775635,
      "learning_rate": 8.068474967939409e-06,
      "loss": 0.5056,
      "step": 36626
    },
    {
      "epoch": 1.1251497557828771,
      "grad_norm": 0.46252086758613586,
      "learning_rate": 8.068000793576398e-06,
      "loss": 0.4759,
      "step": 36627
    },
    {
      "epoch": 1.1251804749178262,
      "grad_norm": 0.36247581243515015,
      "learning_rate": 8.067526623725709e-06,
      "loss": 0.4425,
      "step": 36628
    },
    {
      "epoch": 1.1252111940527754,
      "grad_norm": 0.4004240334033966,
      "learning_rate": 8.067052458388444e-06,
      "loss": 0.4907,
      "step": 36629
    },
    {
      "epoch": 1.1252419131877247,
      "grad_norm": 0.3839876353740692,
      "learning_rate": 8.066578297565715e-06,
      "loss": 0.5177,
      "step": 36630
    },
    {
      "epoch": 1.1252726323226738,
      "grad_norm": 0.3847575783729553,
      "learning_rate": 8.066104141258626e-06,
      "loss": 0.5342,
      "step": 36631
    },
    {
      "epoch": 1.125303351457623,
      "grad_norm": 0.43727317452430725,
      "learning_rate": 8.065629989468285e-06,
      "loss": 0.5535,
      "step": 36632
    },
    {
      "epoch": 1.125334070592572,
      "grad_norm": 0.39220482110977173,
      "learning_rate": 8.0651558421958e-06,
      "loss": 0.49,
      "step": 36633
    },
    {
      "epoch": 1.1253647897275212,
      "grad_norm": 0.39749863743782043,
      "learning_rate": 8.064681699442281e-06,
      "loss": 0.4792,
      "step": 36634
    },
    {
      "epoch": 1.1253955088624705,
      "grad_norm": 0.3972979485988617,
      "learning_rate": 8.064207561208832e-06,
      "loss": 0.4798,
      "step": 36635
    },
    {
      "epoch": 1.1254262279974196,
      "grad_norm": 0.38046354055404663,
      "learning_rate": 8.063733427496564e-06,
      "loss": 0.4618,
      "step": 36636
    },
    {
      "epoch": 1.1254569471323688,
      "grad_norm": 0.40882474184036255,
      "learning_rate": 8.063259298306577e-06,
      "loss": 0.4962,
      "step": 36637
    },
    {
      "epoch": 1.1254876662673179,
      "grad_norm": 0.42512136697769165,
      "learning_rate": 8.062785173639985e-06,
      "loss": 0.5331,
      "step": 36638
    },
    {
      "epoch": 1.125518385402267,
      "grad_norm": 0.553038477897644,
      "learning_rate": 8.062311053497894e-06,
      "loss": 0.4782,
      "step": 36639
    },
    {
      "epoch": 1.1255491045372161,
      "grad_norm": 0.40637943148612976,
      "learning_rate": 8.06183693788141e-06,
      "loss": 0.4254,
      "step": 36640
    },
    {
      "epoch": 1.1255798236721655,
      "grad_norm": 0.45585623383522034,
      "learning_rate": 8.061362826791643e-06,
      "loss": 0.4908,
      "step": 36641
    },
    {
      "epoch": 1.1256105428071146,
      "grad_norm": 0.4469433128833771,
      "learning_rate": 8.060888720229696e-06,
      "loss": 0.5099,
      "step": 36642
    },
    {
      "epoch": 1.1256412619420637,
      "grad_norm": 0.36893999576568604,
      "learning_rate": 8.060414618196683e-06,
      "loss": 0.4497,
      "step": 36643
    },
    {
      "epoch": 1.1256719810770128,
      "grad_norm": 0.40372562408447266,
      "learning_rate": 8.059940520693702e-06,
      "loss": 0.4348,
      "step": 36644
    },
    {
      "epoch": 1.125702700211962,
      "grad_norm": 0.3848975896835327,
      "learning_rate": 8.05946642772187e-06,
      "loss": 0.4912,
      "step": 36645
    },
    {
      "epoch": 1.1257334193469113,
      "grad_norm": 0.460190087556839,
      "learning_rate": 8.058992339282286e-06,
      "loss": 0.5155,
      "step": 36646
    },
    {
      "epoch": 1.1257641384818604,
      "grad_norm": 0.4266948103904724,
      "learning_rate": 8.058518255376065e-06,
      "loss": 0.5567,
      "step": 36647
    },
    {
      "epoch": 1.1257948576168095,
      "grad_norm": 0.3726992905139923,
      "learning_rate": 8.058044176004304e-06,
      "loss": 0.46,
      "step": 36648
    },
    {
      "epoch": 1.1258255767517586,
      "grad_norm": 0.4305844008922577,
      "learning_rate": 8.057570101168125e-06,
      "loss": 0.4919,
      "step": 36649
    },
    {
      "epoch": 1.1258562958867078,
      "grad_norm": 0.4445251226425171,
      "learning_rate": 8.057096030868618e-06,
      "loss": 0.4883,
      "step": 36650
    },
    {
      "epoch": 1.125887015021657,
      "grad_norm": 0.5943894386291504,
      "learning_rate": 8.056621965106905e-06,
      "loss": 0.4413,
      "step": 36651
    },
    {
      "epoch": 1.1259177341566062,
      "grad_norm": 0.365334689617157,
      "learning_rate": 8.056147903884084e-06,
      "loss": 0.4395,
      "step": 36652
    },
    {
      "epoch": 1.1259484532915554,
      "grad_norm": 0.3572026789188385,
      "learning_rate": 8.055673847201266e-06,
      "loss": 0.4453,
      "step": 36653
    },
    {
      "epoch": 1.1259791724265045,
      "grad_norm": 0.39663565158843994,
      "learning_rate": 8.055199795059557e-06,
      "loss": 0.3764,
      "step": 36654
    },
    {
      "epoch": 1.1260098915614536,
      "grad_norm": 0.36256322264671326,
      "learning_rate": 8.054725747460066e-06,
      "loss": 0.5181,
      "step": 36655
    },
    {
      "epoch": 1.1260406106964027,
      "grad_norm": 0.46189433336257935,
      "learning_rate": 8.054251704403898e-06,
      "loss": 0.4739,
      "step": 36656
    },
    {
      "epoch": 1.126071329831352,
      "grad_norm": 0.3629840612411499,
      "learning_rate": 8.05377766589216e-06,
      "loss": 0.4879,
      "step": 36657
    },
    {
      "epoch": 1.1261020489663012,
      "grad_norm": 0.3624345362186432,
      "learning_rate": 8.053303631925963e-06,
      "loss": 0.5867,
      "step": 36658
    },
    {
      "epoch": 1.1261327681012503,
      "grad_norm": 0.44021281599998474,
      "learning_rate": 8.052829602506409e-06,
      "loss": 0.4794,
      "step": 36659
    },
    {
      "epoch": 1.1261634872361994,
      "grad_norm": 0.4608388841152191,
      "learning_rate": 8.05235557763461e-06,
      "loss": 0.5273,
      "step": 36660
    },
    {
      "epoch": 1.1261942063711485,
      "grad_norm": 0.43773606419563293,
      "learning_rate": 8.051881557311666e-06,
      "loss": 0.4478,
      "step": 36661
    },
    {
      "epoch": 1.1262249255060977,
      "grad_norm": 0.3971039950847626,
      "learning_rate": 8.051407541538693e-06,
      "loss": 0.4654,
      "step": 36662
    },
    {
      "epoch": 1.126255644641047,
      "grad_norm": 0.4713329076766968,
      "learning_rate": 8.050933530316791e-06,
      "loss": 0.4796,
      "step": 36663
    },
    {
      "epoch": 1.1262863637759961,
      "grad_norm": 0.36543217301368713,
      "learning_rate": 8.050459523647072e-06,
      "loss": 0.5128,
      "step": 36664
    },
    {
      "epoch": 1.1263170829109452,
      "grad_norm": 0.36404314637184143,
      "learning_rate": 8.04998552153064e-06,
      "loss": 0.4981,
      "step": 36665
    },
    {
      "epoch": 1.1263478020458944,
      "grad_norm": 0.3825770914554596,
      "learning_rate": 8.049511523968604e-06,
      "loss": 0.5292,
      "step": 36666
    },
    {
      "epoch": 1.1263785211808435,
      "grad_norm": 0.6073914766311646,
      "learning_rate": 8.049037530962068e-06,
      "loss": 0.5459,
      "step": 36667
    },
    {
      "epoch": 1.1264092403157928,
      "grad_norm": 0.39281558990478516,
      "learning_rate": 8.048563542512143e-06,
      "loss": 0.4864,
      "step": 36668
    },
    {
      "epoch": 1.126439959450742,
      "grad_norm": 0.33712276816368103,
      "learning_rate": 8.048089558619933e-06,
      "loss": 0.4131,
      "step": 36669
    },
    {
      "epoch": 1.126470678585691,
      "grad_norm": 0.4036058783531189,
      "learning_rate": 8.047615579286548e-06,
      "loss": 0.4885,
      "step": 36670
    },
    {
      "epoch": 1.1265013977206402,
      "grad_norm": 0.370785653591156,
      "learning_rate": 8.04714160451309e-06,
      "loss": 0.4311,
      "step": 36671
    },
    {
      "epoch": 1.1265321168555893,
      "grad_norm": 0.49975821375846863,
      "learning_rate": 8.046667634300673e-06,
      "loss": 0.4992,
      "step": 36672
    },
    {
      "epoch": 1.1265628359905384,
      "grad_norm": 0.410865843296051,
      "learning_rate": 8.046193668650396e-06,
      "loss": 0.5133,
      "step": 36673
    },
    {
      "epoch": 1.1265935551254878,
      "grad_norm": 0.4978240728378296,
      "learning_rate": 8.04571970756337e-06,
      "loss": 0.5018,
      "step": 36674
    },
    {
      "epoch": 1.1266242742604369,
      "grad_norm": 0.4277656376361847,
      "learning_rate": 8.045245751040706e-06,
      "loss": 0.4755,
      "step": 36675
    },
    {
      "epoch": 1.126654993395386,
      "grad_norm": 0.39504173398017883,
      "learning_rate": 8.044771799083503e-06,
      "loss": 0.5703,
      "step": 36676
    },
    {
      "epoch": 1.1266857125303351,
      "grad_norm": 0.39013195037841797,
      "learning_rate": 8.044297851692877e-06,
      "loss": 0.4405,
      "step": 36677
    },
    {
      "epoch": 1.1267164316652842,
      "grad_norm": 0.38391879200935364,
      "learning_rate": 8.043823908869926e-06,
      "loss": 0.5192,
      "step": 36678
    },
    {
      "epoch": 1.1267471508002336,
      "grad_norm": 0.4099702537059784,
      "learning_rate": 8.043349970615766e-06,
      "loss": 0.4512,
      "step": 36679
    },
    {
      "epoch": 1.1267778699351827,
      "grad_norm": 0.4476545751094818,
      "learning_rate": 8.04287603693149e-06,
      "loss": 0.3602,
      "step": 36680
    },
    {
      "epoch": 1.1268085890701318,
      "grad_norm": 0.40920737385749817,
      "learning_rate": 8.042402107818224e-06,
      "loss": 0.4245,
      "step": 36681
    },
    {
      "epoch": 1.126839308205081,
      "grad_norm": 0.4195100963115692,
      "learning_rate": 8.041928183277054e-06,
      "loss": 0.5189,
      "step": 36682
    },
    {
      "epoch": 1.12687002734003,
      "grad_norm": 0.3868078887462616,
      "learning_rate": 8.041454263309108e-06,
      "loss": 0.4757,
      "step": 36683
    },
    {
      "epoch": 1.1269007464749792,
      "grad_norm": 0.3769599199295044,
      "learning_rate": 8.040980347915475e-06,
      "loss": 0.5132,
      "step": 36684
    },
    {
      "epoch": 1.1269314656099285,
      "grad_norm": 0.4284503757953644,
      "learning_rate": 8.040506437097273e-06,
      "loss": 0.4961,
      "step": 36685
    },
    {
      "epoch": 1.1269621847448776,
      "grad_norm": 0.4008386433124542,
      "learning_rate": 8.0400325308556e-06,
      "loss": 0.5575,
      "step": 36686
    },
    {
      "epoch": 1.1269929038798268,
      "grad_norm": 0.37471622228622437,
      "learning_rate": 8.039558629191574e-06,
      "loss": 0.4791,
      "step": 36687
    },
    {
      "epoch": 1.1270236230147759,
      "grad_norm": 0.357245534658432,
      "learning_rate": 8.039084732106292e-06,
      "loss": 0.4712,
      "step": 36688
    },
    {
      "epoch": 1.127054342149725,
      "grad_norm": 0.42823150753974915,
      "learning_rate": 8.038610839600867e-06,
      "loss": 0.5417,
      "step": 36689
    },
    {
      "epoch": 1.1270850612846743,
      "grad_norm": 0.38187122344970703,
      "learning_rate": 8.0381369516764e-06,
      "loss": 0.4879,
      "step": 36690
    },
    {
      "epoch": 1.1271157804196235,
      "grad_norm": 0.4279220998287201,
      "learning_rate": 8.037663068334005e-06,
      "loss": 0.5013,
      "step": 36691
    },
    {
      "epoch": 1.1271464995545726,
      "grad_norm": 0.4070560038089752,
      "learning_rate": 8.03718918957478e-06,
      "loss": 0.4804,
      "step": 36692
    },
    {
      "epoch": 1.1271772186895217,
      "grad_norm": 0.36095792055130005,
      "learning_rate": 8.03671531539984e-06,
      "loss": 0.5778,
      "step": 36693
    },
    {
      "epoch": 1.1272079378244708,
      "grad_norm": 0.4095231890678406,
      "learning_rate": 8.03624144581029e-06,
      "loss": 0.4736,
      "step": 36694
    },
    {
      "epoch": 1.12723865695942,
      "grad_norm": 0.35555747151374817,
      "learning_rate": 8.035767580807232e-06,
      "loss": 0.4358,
      "step": 36695
    },
    {
      "epoch": 1.127269376094369,
      "grad_norm": 0.3948540985584259,
      "learning_rate": 8.035293720391779e-06,
      "loss": 0.5015,
      "step": 36696
    },
    {
      "epoch": 1.1273000952293184,
      "grad_norm": 0.41842812299728394,
      "learning_rate": 8.034819864565032e-06,
      "loss": 0.3606,
      "step": 36697
    },
    {
      "epoch": 1.1273308143642675,
      "grad_norm": 0.4128626883029938,
      "learning_rate": 8.034346013328102e-06,
      "loss": 0.4731,
      "step": 36698
    },
    {
      "epoch": 1.1273615334992166,
      "grad_norm": 0.41537943482398987,
      "learning_rate": 8.033872166682092e-06,
      "loss": 0.4686,
      "step": 36699
    },
    {
      "epoch": 1.1273922526341658,
      "grad_norm": 0.46664389967918396,
      "learning_rate": 8.033398324628116e-06,
      "loss": 0.3907,
      "step": 36700
    },
    {
      "epoch": 1.127422971769115,
      "grad_norm": 0.3816084861755371,
      "learning_rate": 8.03292448716727e-06,
      "loss": 0.5178,
      "step": 36701
    },
    {
      "epoch": 1.1274536909040642,
      "grad_norm": 0.3772332966327667,
      "learning_rate": 8.03245065430067e-06,
      "loss": 0.5806,
      "step": 36702
    },
    {
      "epoch": 1.1274844100390133,
      "grad_norm": 0.3499276041984558,
      "learning_rate": 8.031976826029417e-06,
      "loss": 0.4714,
      "step": 36703
    },
    {
      "epoch": 1.1275151291739625,
      "grad_norm": 0.4036250114440918,
      "learning_rate": 8.03150300235462e-06,
      "loss": 0.4977,
      "step": 36704
    },
    {
      "epoch": 1.1275458483089116,
      "grad_norm": 0.6565640568733215,
      "learning_rate": 8.031029183277385e-06,
      "loss": 0.4713,
      "step": 36705
    },
    {
      "epoch": 1.1275765674438607,
      "grad_norm": 0.3908877372741699,
      "learning_rate": 8.030555368798822e-06,
      "loss": 0.4872,
      "step": 36706
    },
    {
      "epoch": 1.1276072865788098,
      "grad_norm": 0.36912935972213745,
      "learning_rate": 8.03008155892003e-06,
      "loss": 0.5486,
      "step": 36707
    },
    {
      "epoch": 1.1276380057137592,
      "grad_norm": 0.4114687740802765,
      "learning_rate": 8.029607753642123e-06,
      "loss": 0.4838,
      "step": 36708
    },
    {
      "epoch": 1.1276687248487083,
      "grad_norm": 0.5087268948554993,
      "learning_rate": 8.0291339529662e-06,
      "loss": 0.4041,
      "step": 36709
    },
    {
      "epoch": 1.1276994439836574,
      "grad_norm": 0.37317484617233276,
      "learning_rate": 8.028660156893379e-06,
      "loss": 0.5172,
      "step": 36710
    },
    {
      "epoch": 1.1277301631186065,
      "grad_norm": 0.4113369286060333,
      "learning_rate": 8.028186365424754e-06,
      "loss": 0.4726,
      "step": 36711
    },
    {
      "epoch": 1.1277608822535559,
      "grad_norm": 0.3713957667350769,
      "learning_rate": 8.027712578561439e-06,
      "loss": 0.5275,
      "step": 36712
    },
    {
      "epoch": 1.127791601388505,
      "grad_norm": 0.3877732753753662,
      "learning_rate": 8.027238796304543e-06,
      "loss": 0.5076,
      "step": 36713
    },
    {
      "epoch": 1.127822320523454,
      "grad_norm": 0.39314401149749756,
      "learning_rate": 8.026765018655162e-06,
      "loss": 0.4673,
      "step": 36714
    },
    {
      "epoch": 1.1278530396584032,
      "grad_norm": 0.3838682472705841,
      "learning_rate": 8.026291245614417e-06,
      "loss": 0.5528,
      "step": 36715
    },
    {
      "epoch": 1.1278837587933523,
      "grad_norm": 0.40979331731796265,
      "learning_rate": 8.025817477183399e-06,
      "loss": 0.4778,
      "step": 36716
    },
    {
      "epoch": 1.1279144779283015,
      "grad_norm": 0.43459075689315796,
      "learning_rate": 8.025343713363229e-06,
      "loss": 0.4657,
      "step": 36717
    },
    {
      "epoch": 1.1279451970632506,
      "grad_norm": 0.3651573061943054,
      "learning_rate": 8.024869954154999e-06,
      "loss": 0.4693,
      "step": 36718
    },
    {
      "epoch": 1.1279759161982,
      "grad_norm": 0.40565773844718933,
      "learning_rate": 8.02439619955983e-06,
      "loss": 0.4573,
      "step": 36719
    },
    {
      "epoch": 1.128006635333149,
      "grad_norm": 0.39617210626602173,
      "learning_rate": 8.023922449578818e-06,
      "loss": 0.4285,
      "step": 36720
    },
    {
      "epoch": 1.1280373544680982,
      "grad_norm": 0.386956125497818,
      "learning_rate": 8.023448704213075e-06,
      "loss": 0.5355,
      "step": 36721
    },
    {
      "epoch": 1.1280680736030473,
      "grad_norm": 0.4250669479370117,
      "learning_rate": 8.022974963463704e-06,
      "loss": 0.5022,
      "step": 36722
    },
    {
      "epoch": 1.1280987927379964,
      "grad_norm": 0.38238948583602905,
      "learning_rate": 8.022501227331814e-06,
      "loss": 0.446,
      "step": 36723
    },
    {
      "epoch": 1.1281295118729457,
      "grad_norm": 0.4337948262691498,
      "learning_rate": 8.022027495818509e-06,
      "loss": 0.4632,
      "step": 36724
    },
    {
      "epoch": 1.1281602310078949,
      "grad_norm": 0.4447489380836487,
      "learning_rate": 8.0215537689249e-06,
      "loss": 0.5221,
      "step": 36725
    },
    {
      "epoch": 1.128190950142844,
      "grad_norm": 0.3829479515552521,
      "learning_rate": 8.021080046652088e-06,
      "loss": 0.421,
      "step": 36726
    },
    {
      "epoch": 1.128221669277793,
      "grad_norm": 0.3736962378025055,
      "learning_rate": 8.020606329001184e-06,
      "loss": 0.4786,
      "step": 36727
    },
    {
      "epoch": 1.1282523884127422,
      "grad_norm": 0.38536280393600464,
      "learning_rate": 8.020132615973288e-06,
      "loss": 0.4439,
      "step": 36728
    },
    {
      "epoch": 1.1282831075476913,
      "grad_norm": 0.3862038254737854,
      "learning_rate": 8.019658907569512e-06,
      "loss": 0.5007,
      "step": 36729
    },
    {
      "epoch": 1.1283138266826407,
      "grad_norm": 0.4443136155605316,
      "learning_rate": 8.019185203790964e-06,
      "loss": 0.4956,
      "step": 36730
    },
    {
      "epoch": 1.1283445458175898,
      "grad_norm": 0.3854890763759613,
      "learning_rate": 8.018711504638744e-06,
      "loss": 0.5299,
      "step": 36731
    },
    {
      "epoch": 1.128375264952539,
      "grad_norm": 0.49456796050071716,
      "learning_rate": 8.018237810113964e-06,
      "loss": 0.4803,
      "step": 36732
    },
    {
      "epoch": 1.128405984087488,
      "grad_norm": 0.43951916694641113,
      "learning_rate": 8.017764120217726e-06,
      "loss": 0.4704,
      "step": 36733
    },
    {
      "epoch": 1.1284367032224372,
      "grad_norm": 0.37846922874450684,
      "learning_rate": 8.01729043495114e-06,
      "loss": 0.4455,
      "step": 36734
    },
    {
      "epoch": 1.1284674223573865,
      "grad_norm": 0.4050174951553345,
      "learning_rate": 8.01681675431531e-06,
      "loss": 0.4835,
      "step": 36735
    },
    {
      "epoch": 1.1284981414923356,
      "grad_norm": 0.38241931796073914,
      "learning_rate": 8.016343078311341e-06,
      "loss": 0.4621,
      "step": 36736
    },
    {
      "epoch": 1.1285288606272847,
      "grad_norm": 0.40956366062164307,
      "learning_rate": 8.015869406940343e-06,
      "loss": 0.5131,
      "step": 36737
    },
    {
      "epoch": 1.1285595797622339,
      "grad_norm": 0.39224639534950256,
      "learning_rate": 8.015395740203421e-06,
      "loss": 0.5171,
      "step": 36738
    },
    {
      "epoch": 1.128590298897183,
      "grad_norm": 0.4457416832447052,
      "learning_rate": 8.01492207810168e-06,
      "loss": 0.4766,
      "step": 36739
    },
    {
      "epoch": 1.128621018032132,
      "grad_norm": 0.417169451713562,
      "learning_rate": 8.014448420636228e-06,
      "loss": 0.4936,
      "step": 36740
    },
    {
      "epoch": 1.1286517371670814,
      "grad_norm": 0.3961960971355438,
      "learning_rate": 8.013974767808169e-06,
      "loss": 0.5399,
      "step": 36741
    },
    {
      "epoch": 1.1286824563020306,
      "grad_norm": 0.36174559593200684,
      "learning_rate": 8.013501119618614e-06,
      "loss": 0.4995,
      "step": 36742
    },
    {
      "epoch": 1.1287131754369797,
      "grad_norm": 0.40553754568099976,
      "learning_rate": 8.013027476068663e-06,
      "loss": 0.4375,
      "step": 36743
    },
    {
      "epoch": 1.1287438945719288,
      "grad_norm": 0.4075098931789398,
      "learning_rate": 8.012553837159426e-06,
      "loss": 0.5263,
      "step": 36744
    },
    {
      "epoch": 1.128774613706878,
      "grad_norm": 0.39572834968566895,
      "learning_rate": 8.012080202892007e-06,
      "loss": 0.5498,
      "step": 36745
    },
    {
      "epoch": 1.1288053328418273,
      "grad_norm": 0.42640507221221924,
      "learning_rate": 8.011606573267516e-06,
      "loss": 0.4617,
      "step": 36746
    },
    {
      "epoch": 1.1288360519767764,
      "grad_norm": 0.3995102345943451,
      "learning_rate": 8.011132948287052e-06,
      "loss": 0.4339,
      "step": 36747
    },
    {
      "epoch": 1.1288667711117255,
      "grad_norm": 0.4491756856441498,
      "learning_rate": 8.010659327951729e-06,
      "loss": 0.5117,
      "step": 36748
    },
    {
      "epoch": 1.1288974902466746,
      "grad_norm": 0.3926803767681122,
      "learning_rate": 8.010185712262652e-06,
      "loss": 0.5165,
      "step": 36749
    },
    {
      "epoch": 1.1289282093816237,
      "grad_norm": 0.4291432797908783,
      "learning_rate": 8.009712101220922e-06,
      "loss": 0.4755,
      "step": 36750
    },
    {
      "epoch": 1.1289589285165729,
      "grad_norm": 0.40038564801216125,
      "learning_rate": 8.009238494827652e-06,
      "loss": 0.4468,
      "step": 36751
    },
    {
      "epoch": 1.1289896476515222,
      "grad_norm": 0.36875882744789124,
      "learning_rate": 8.008764893083938e-06,
      "loss": 0.448,
      "step": 36752
    },
    {
      "epoch": 1.1290203667864713,
      "grad_norm": 0.4552854597568512,
      "learning_rate": 8.008291295990903e-06,
      "loss": 0.4818,
      "step": 36753
    },
    {
      "epoch": 1.1290510859214204,
      "grad_norm": 0.34291914105415344,
      "learning_rate": 8.007817703549635e-06,
      "loss": 0.4422,
      "step": 36754
    },
    {
      "epoch": 1.1290818050563696,
      "grad_norm": 0.3834388554096222,
      "learning_rate": 8.00734411576125e-06,
      "loss": 0.4973,
      "step": 36755
    },
    {
      "epoch": 1.1291125241913187,
      "grad_norm": 0.3758564889431,
      "learning_rate": 8.00687053262685e-06,
      "loss": 0.5448,
      "step": 36756
    },
    {
      "epoch": 1.129143243326268,
      "grad_norm": 0.43172910809516907,
      "learning_rate": 8.006396954147545e-06,
      "loss": 0.4224,
      "step": 36757
    },
    {
      "epoch": 1.1291739624612172,
      "grad_norm": 0.41409701108932495,
      "learning_rate": 8.005923380324438e-06,
      "loss": 0.5125,
      "step": 36758
    },
    {
      "epoch": 1.1292046815961663,
      "grad_norm": 0.41517823934555054,
      "learning_rate": 8.005449811158639e-06,
      "loss": 0.5521,
      "step": 36759
    },
    {
      "epoch": 1.1292354007311154,
      "grad_norm": 0.41427624225616455,
      "learning_rate": 8.004976246651249e-06,
      "loss": 0.4527,
      "step": 36760
    },
    {
      "epoch": 1.1292661198660645,
      "grad_norm": 0.38175299763679504,
      "learning_rate": 8.004502686803377e-06,
      "loss": 0.5016,
      "step": 36761
    },
    {
      "epoch": 1.1292968390010136,
      "grad_norm": 0.39971423149108887,
      "learning_rate": 8.004029131616127e-06,
      "loss": 0.5386,
      "step": 36762
    },
    {
      "epoch": 1.129327558135963,
      "grad_norm": 0.3994947075843811,
      "learning_rate": 8.003555581090607e-06,
      "loss": 0.4851,
      "step": 36763
    },
    {
      "epoch": 1.129358277270912,
      "grad_norm": 0.39443403482437134,
      "learning_rate": 8.003082035227923e-06,
      "loss": 0.461,
      "step": 36764
    },
    {
      "epoch": 1.1293889964058612,
      "grad_norm": 0.427367627620697,
      "learning_rate": 8.002608494029179e-06,
      "loss": 0.558,
      "step": 36765
    },
    {
      "epoch": 1.1294197155408103,
      "grad_norm": 0.40932753682136536,
      "learning_rate": 8.002134957495485e-06,
      "loss": 0.5387,
      "step": 36766
    },
    {
      "epoch": 1.1294504346757595,
      "grad_norm": 0.42100533843040466,
      "learning_rate": 8.00166142562794e-06,
      "loss": 0.4674,
      "step": 36767
    },
    {
      "epoch": 1.1294811538107088,
      "grad_norm": 0.49521005153656006,
      "learning_rate": 8.001187898427657e-06,
      "loss": 0.4725,
      "step": 36768
    },
    {
      "epoch": 1.129511872945658,
      "grad_norm": 0.4086134135723114,
      "learning_rate": 8.000714375895739e-06,
      "loss": 0.506,
      "step": 36769
    },
    {
      "epoch": 1.129542592080607,
      "grad_norm": 0.4280128479003906,
      "learning_rate": 8.000240858033294e-06,
      "loss": 0.4751,
      "step": 36770
    },
    {
      "epoch": 1.1295733112155562,
      "grad_norm": 0.3856049180030823,
      "learning_rate": 7.999767344841423e-06,
      "loss": 0.5101,
      "step": 36771
    },
    {
      "epoch": 1.1296040303505053,
      "grad_norm": 0.3828904926776886,
      "learning_rate": 7.999293836321239e-06,
      "loss": 0.4558,
      "step": 36772
    },
    {
      "epoch": 1.1296347494854544,
      "grad_norm": 0.3975425362586975,
      "learning_rate": 7.99882033247384e-06,
      "loss": 0.5283,
      "step": 36773
    },
    {
      "epoch": 1.1296654686204037,
      "grad_norm": 0.3919820487499237,
      "learning_rate": 7.99834683330034e-06,
      "loss": 0.4874,
      "step": 36774
    },
    {
      "epoch": 1.1296961877553529,
      "grad_norm": 0.356414258480072,
      "learning_rate": 7.997873338801837e-06,
      "loss": 0.4273,
      "step": 36775
    },
    {
      "epoch": 1.129726906890302,
      "grad_norm": 0.3962569832801819,
      "learning_rate": 7.997399848979444e-06,
      "loss": 0.5065,
      "step": 36776
    },
    {
      "epoch": 1.129757626025251,
      "grad_norm": 0.39407607913017273,
      "learning_rate": 7.996926363834258e-06,
      "loss": 0.4473,
      "step": 36777
    },
    {
      "epoch": 1.1297883451602002,
      "grad_norm": 0.38521236181259155,
      "learning_rate": 7.996452883367397e-06,
      "loss": 0.501,
      "step": 36778
    },
    {
      "epoch": 1.1298190642951496,
      "grad_norm": 0.42244359850883484,
      "learning_rate": 7.995979407579954e-06,
      "loss": 0.5477,
      "step": 36779
    },
    {
      "epoch": 1.1298497834300987,
      "grad_norm": 0.37116342782974243,
      "learning_rate": 7.995505936473047e-06,
      "loss": 0.4612,
      "step": 36780
    },
    {
      "epoch": 1.1298805025650478,
      "grad_norm": 0.4012557864189148,
      "learning_rate": 7.99503247004777e-06,
      "loss": 0.484,
      "step": 36781
    },
    {
      "epoch": 1.129911221699997,
      "grad_norm": 0.4268002212047577,
      "learning_rate": 7.994559008305242e-06,
      "loss": 0.5676,
      "step": 36782
    },
    {
      "epoch": 1.129941940834946,
      "grad_norm": 0.5152812004089355,
      "learning_rate": 7.994085551246556e-06,
      "loss": 0.4277,
      "step": 36783
    },
    {
      "epoch": 1.1299726599698952,
      "grad_norm": 0.44921383261680603,
      "learning_rate": 7.993612098872821e-06,
      "loss": 0.5258,
      "step": 36784
    },
    {
      "epoch": 1.1300033791048445,
      "grad_norm": 0.3772616386413574,
      "learning_rate": 7.99313865118515e-06,
      "loss": 0.4632,
      "step": 36785
    },
    {
      "epoch": 1.1300340982397936,
      "grad_norm": 0.44760286808013916,
      "learning_rate": 7.99266520818464e-06,
      "loss": 0.4497,
      "step": 36786
    },
    {
      "epoch": 1.1300648173747427,
      "grad_norm": 0.5270360112190247,
      "learning_rate": 7.992191769872406e-06,
      "loss": 0.4497,
      "step": 36787
    },
    {
      "epoch": 1.1300955365096919,
      "grad_norm": 0.4044038653373718,
      "learning_rate": 7.991718336249542e-06,
      "loss": 0.4624,
      "step": 36788
    },
    {
      "epoch": 1.130126255644641,
      "grad_norm": 0.3805335462093353,
      "learning_rate": 7.991244907317167e-06,
      "loss": 0.4843,
      "step": 36789
    },
    {
      "epoch": 1.1301569747795903,
      "grad_norm": 0.376316100358963,
      "learning_rate": 7.990771483076375e-06,
      "loss": 0.4622,
      "step": 36790
    },
    {
      "epoch": 1.1301876939145394,
      "grad_norm": 0.3954533040523529,
      "learning_rate": 7.990298063528279e-06,
      "loss": 0.5229,
      "step": 36791
    },
    {
      "epoch": 1.1302184130494886,
      "grad_norm": 0.3844377100467682,
      "learning_rate": 7.989824648673979e-06,
      "loss": 0.4979,
      "step": 36792
    },
    {
      "epoch": 1.1302491321844377,
      "grad_norm": 0.39873093366622925,
      "learning_rate": 7.989351238514587e-06,
      "loss": 0.4458,
      "step": 36793
    },
    {
      "epoch": 1.1302798513193868,
      "grad_norm": 0.4018557369709015,
      "learning_rate": 7.988877833051204e-06,
      "loss": 0.5057,
      "step": 36794
    },
    {
      "epoch": 1.130310570454336,
      "grad_norm": 0.40277037024497986,
      "learning_rate": 7.988404432284939e-06,
      "loss": 0.514,
      "step": 36795
    },
    {
      "epoch": 1.1303412895892853,
      "grad_norm": 0.40315350890159607,
      "learning_rate": 7.987931036216894e-06,
      "loss": 0.5046,
      "step": 36796
    },
    {
      "epoch": 1.1303720087242344,
      "grad_norm": 0.406656414270401,
      "learning_rate": 7.987457644848178e-06,
      "loss": 0.4993,
      "step": 36797
    },
    {
      "epoch": 1.1304027278591835,
      "grad_norm": 0.3406294286251068,
      "learning_rate": 7.986984258179892e-06,
      "loss": 0.438,
      "step": 36798
    },
    {
      "epoch": 1.1304334469941326,
      "grad_norm": 0.37780946493148804,
      "learning_rate": 7.986510876213149e-06,
      "loss": 0.4378,
      "step": 36799
    },
    {
      "epoch": 1.1304641661290817,
      "grad_norm": 0.4371301829814911,
      "learning_rate": 7.98603749894905e-06,
      "loss": 0.5554,
      "step": 36800
    },
    {
      "epoch": 1.130494885264031,
      "grad_norm": 0.36214131116867065,
      "learning_rate": 7.9855641263887e-06,
      "loss": 0.5022,
      "step": 36801
    },
    {
      "epoch": 1.1305256043989802,
      "grad_norm": 0.36728712916374207,
      "learning_rate": 7.985090758533204e-06,
      "loss": 0.5362,
      "step": 36802
    },
    {
      "epoch": 1.1305563235339293,
      "grad_norm": 0.39253002405166626,
      "learning_rate": 7.98461739538367e-06,
      "loss": 0.4596,
      "step": 36803
    },
    {
      "epoch": 1.1305870426688784,
      "grad_norm": 1.6940819025039673,
      "learning_rate": 7.984144036941203e-06,
      "loss": 0.4408,
      "step": 36804
    },
    {
      "epoch": 1.1306177618038276,
      "grad_norm": 0.418771892786026,
      "learning_rate": 7.983670683206908e-06,
      "loss": 0.5409,
      "step": 36805
    },
    {
      "epoch": 1.1306484809387767,
      "grad_norm": 0.4433974027633667,
      "learning_rate": 7.983197334181894e-06,
      "loss": 0.5361,
      "step": 36806
    },
    {
      "epoch": 1.130679200073726,
      "grad_norm": 0.37971231341362,
      "learning_rate": 7.98272398986726e-06,
      "loss": 0.459,
      "step": 36807
    },
    {
      "epoch": 1.1307099192086751,
      "grad_norm": 0.4124172627925873,
      "learning_rate": 7.982250650264119e-06,
      "loss": 0.6065,
      "step": 36808
    },
    {
      "epoch": 1.1307406383436243,
      "grad_norm": 0.38858142495155334,
      "learning_rate": 7.981777315373567e-06,
      "loss": 0.4885,
      "step": 36809
    },
    {
      "epoch": 1.1307713574785734,
      "grad_norm": 0.35992592573165894,
      "learning_rate": 7.98130398519672e-06,
      "loss": 0.4566,
      "step": 36810
    },
    {
      "epoch": 1.1308020766135225,
      "grad_norm": 0.3913944363594055,
      "learning_rate": 7.980830659734676e-06,
      "loss": 0.4873,
      "step": 36811
    },
    {
      "epoch": 1.1308327957484718,
      "grad_norm": 0.40942636132240295,
      "learning_rate": 7.980357338988547e-06,
      "loss": 0.4439,
      "step": 36812
    },
    {
      "epoch": 1.130863514883421,
      "grad_norm": 0.3815653622150421,
      "learning_rate": 7.979884022959427e-06,
      "loss": 0.4641,
      "step": 36813
    },
    {
      "epoch": 1.13089423401837,
      "grad_norm": 0.4085237383842468,
      "learning_rate": 7.979410711648437e-06,
      "loss": 0.4775,
      "step": 36814
    },
    {
      "epoch": 1.1309249531533192,
      "grad_norm": 0.4068952202796936,
      "learning_rate": 7.978937405056667e-06,
      "loss": 0.5239,
      "step": 36815
    },
    {
      "epoch": 1.1309556722882683,
      "grad_norm": 0.4022630453109741,
      "learning_rate": 7.978464103185235e-06,
      "loss": 0.4573,
      "step": 36816
    },
    {
      "epoch": 1.1309863914232174,
      "grad_norm": 0.4094844162464142,
      "learning_rate": 7.977990806035238e-06,
      "loss": 0.5045,
      "step": 36817
    },
    {
      "epoch": 1.1310171105581666,
      "grad_norm": 0.4067402780056,
      "learning_rate": 7.977517513607788e-06,
      "loss": 0.4919,
      "step": 36818
    },
    {
      "epoch": 1.131047829693116,
      "grad_norm": 0.3757820427417755,
      "learning_rate": 7.977044225903986e-06,
      "loss": 0.4999,
      "step": 36819
    },
    {
      "epoch": 1.131078548828065,
      "grad_norm": 0.41559839248657227,
      "learning_rate": 7.976570942924933e-06,
      "loss": 0.4583,
      "step": 36820
    },
    {
      "epoch": 1.1311092679630141,
      "grad_norm": 0.35666534304618835,
      "learning_rate": 7.976097664671748e-06,
      "loss": 0.4028,
      "step": 36821
    },
    {
      "epoch": 1.1311399870979633,
      "grad_norm": 0.3849678933620453,
      "learning_rate": 7.975624391145522e-06,
      "loss": 0.5302,
      "step": 36822
    },
    {
      "epoch": 1.1311707062329126,
      "grad_norm": 0.39565011858940125,
      "learning_rate": 7.975151122347372e-06,
      "loss": 0.4103,
      "step": 36823
    },
    {
      "epoch": 1.1312014253678617,
      "grad_norm": 0.3958309292793274,
      "learning_rate": 7.974677858278394e-06,
      "loss": 0.4954,
      "step": 36824
    },
    {
      "epoch": 1.1312321445028108,
      "grad_norm": 0.4583006203174591,
      "learning_rate": 7.9742045989397e-06,
      "loss": 0.5714,
      "step": 36825
    },
    {
      "epoch": 1.13126286363776,
      "grad_norm": 0.4036029875278473,
      "learning_rate": 7.97373134433239e-06,
      "loss": 0.5533,
      "step": 36826
    },
    {
      "epoch": 1.131293582772709,
      "grad_norm": 0.4105491638183594,
      "learning_rate": 7.973258094457576e-06,
      "loss": 0.447,
      "step": 36827
    },
    {
      "epoch": 1.1313243019076582,
      "grad_norm": 0.4317551553249359,
      "learning_rate": 7.972784849316355e-06,
      "loss": 0.5301,
      "step": 36828
    },
    {
      "epoch": 1.1313550210426073,
      "grad_norm": 0.38182076811790466,
      "learning_rate": 7.97231160890984e-06,
      "loss": 0.4725,
      "step": 36829
    },
    {
      "epoch": 1.1313857401775567,
      "grad_norm": 0.42808860540390015,
      "learning_rate": 7.97183837323913e-06,
      "loss": 0.4608,
      "step": 36830
    },
    {
      "epoch": 1.1314164593125058,
      "grad_norm": 0.40086600184440613,
      "learning_rate": 7.971365142305334e-06,
      "loss": 0.5127,
      "step": 36831
    },
    {
      "epoch": 1.131447178447455,
      "grad_norm": 0.39867103099823,
      "learning_rate": 7.970891916109555e-06,
      "loss": 0.4693,
      "step": 36832
    },
    {
      "epoch": 1.131477897582404,
      "grad_norm": 0.3763619065284729,
      "learning_rate": 7.970418694652903e-06,
      "loss": 0.5676,
      "step": 36833
    },
    {
      "epoch": 1.1315086167173531,
      "grad_norm": 0.4113011956214905,
      "learning_rate": 7.969945477936476e-06,
      "loss": 0.5634,
      "step": 36834
    },
    {
      "epoch": 1.1315393358523025,
      "grad_norm": 0.4251602590084076,
      "learning_rate": 7.969472265961387e-06,
      "loss": 0.4953,
      "step": 36835
    },
    {
      "epoch": 1.1315700549872516,
      "grad_norm": 0.4330484867095947,
      "learning_rate": 7.968999058728735e-06,
      "loss": 0.5626,
      "step": 36836
    },
    {
      "epoch": 1.1316007741222007,
      "grad_norm": 0.4409750998020172,
      "learning_rate": 7.968525856239628e-06,
      "loss": 0.483,
      "step": 36837
    },
    {
      "epoch": 1.1316314932571498,
      "grad_norm": 0.38421526551246643,
      "learning_rate": 7.968052658495171e-06,
      "loss": 0.5131,
      "step": 36838
    },
    {
      "epoch": 1.131662212392099,
      "grad_norm": 0.4478890001773834,
      "learning_rate": 7.967579465496467e-06,
      "loss": 0.4677,
      "step": 36839
    },
    {
      "epoch": 1.131692931527048,
      "grad_norm": 0.3990154564380646,
      "learning_rate": 7.967106277244626e-06,
      "loss": 0.5026,
      "step": 36840
    },
    {
      "epoch": 1.1317236506619974,
      "grad_norm": 0.43597638607025146,
      "learning_rate": 7.966633093740748e-06,
      "loss": 0.515,
      "step": 36841
    },
    {
      "epoch": 1.1317543697969465,
      "grad_norm": 0.365166574716568,
      "learning_rate": 7.966159914985943e-06,
      "loss": 0.438,
      "step": 36842
    },
    {
      "epoch": 1.1317850889318957,
      "grad_norm": 0.4056132137775421,
      "learning_rate": 7.965686740981311e-06,
      "loss": 0.5211,
      "step": 36843
    },
    {
      "epoch": 1.1318158080668448,
      "grad_norm": 0.3840271234512329,
      "learning_rate": 7.965213571727961e-06,
      "loss": 0.5269,
      "step": 36844
    },
    {
      "epoch": 1.131846527201794,
      "grad_norm": 0.40665844082832336,
      "learning_rate": 7.964740407226996e-06,
      "loss": 0.5855,
      "step": 36845
    },
    {
      "epoch": 1.1318772463367432,
      "grad_norm": 0.37718114256858826,
      "learning_rate": 7.964267247479526e-06,
      "loss": 0.4378,
      "step": 36846
    },
    {
      "epoch": 1.1319079654716924,
      "grad_norm": 0.398354172706604,
      "learning_rate": 7.963794092486645e-06,
      "loss": 0.4878,
      "step": 36847
    },
    {
      "epoch": 1.1319386846066415,
      "grad_norm": 0.4252913296222687,
      "learning_rate": 7.963320942249471e-06,
      "loss": 0.5117,
      "step": 36848
    },
    {
      "epoch": 1.1319694037415906,
      "grad_norm": 0.402157723903656,
      "learning_rate": 7.962847796769099e-06,
      "loss": 0.5237,
      "step": 36849
    },
    {
      "epoch": 1.1320001228765397,
      "grad_norm": 0.3576604127883911,
      "learning_rate": 7.962374656046642e-06,
      "loss": 0.4218,
      "step": 36850
    },
    {
      "epoch": 1.1320308420114888,
      "grad_norm": 0.4094579219818115,
      "learning_rate": 7.961901520083197e-06,
      "loss": 0.4488,
      "step": 36851
    },
    {
      "epoch": 1.1320615611464382,
      "grad_norm": 0.38591718673706055,
      "learning_rate": 7.96142838887988e-06,
      "loss": 0.5088,
      "step": 36852
    },
    {
      "epoch": 1.1320922802813873,
      "grad_norm": 0.3518843650817871,
      "learning_rate": 7.960955262437782e-06,
      "loss": 0.4761,
      "step": 36853
    },
    {
      "epoch": 1.1321229994163364,
      "grad_norm": 0.8438888192176819,
      "learning_rate": 7.96048214075802e-06,
      "loss": 0.4349,
      "step": 36854
    },
    {
      "epoch": 1.1321537185512855,
      "grad_norm": 0.3891736567020416,
      "learning_rate": 7.960009023841692e-06,
      "loss": 0.4141,
      "step": 36855
    },
    {
      "epoch": 1.1321844376862347,
      "grad_norm": 0.3834741413593292,
      "learning_rate": 7.959535911689908e-06,
      "loss": 0.4976,
      "step": 36856
    },
    {
      "epoch": 1.132215156821184,
      "grad_norm": 0.4425015151500702,
      "learning_rate": 7.959062804303766e-06,
      "loss": 0.5462,
      "step": 36857
    },
    {
      "epoch": 1.1322458759561331,
      "grad_norm": 0.41176748275756836,
      "learning_rate": 7.958589701684379e-06,
      "loss": 0.5095,
      "step": 36858
    },
    {
      "epoch": 1.1322765950910822,
      "grad_norm": 0.3760293126106262,
      "learning_rate": 7.958116603832847e-06,
      "loss": 0.4363,
      "step": 36859
    },
    {
      "epoch": 1.1323073142260314,
      "grad_norm": 0.38057976961135864,
      "learning_rate": 7.957643510750275e-06,
      "loss": 0.4187,
      "step": 36860
    },
    {
      "epoch": 1.1323380333609805,
      "grad_norm": 0.36309948563575745,
      "learning_rate": 7.957170422437772e-06,
      "loss": 0.4564,
      "step": 36861
    },
    {
      "epoch": 1.1323687524959296,
      "grad_norm": 0.4295801818370819,
      "learning_rate": 7.956697338896439e-06,
      "loss": 0.5136,
      "step": 36862
    },
    {
      "epoch": 1.132399471630879,
      "grad_norm": 0.42558950185775757,
      "learning_rate": 7.956224260127382e-06,
      "loss": 0.4644,
      "step": 36863
    },
    {
      "epoch": 1.132430190765828,
      "grad_norm": 0.42809826135635376,
      "learning_rate": 7.955751186131704e-06,
      "loss": 0.4597,
      "step": 36864
    },
    {
      "epoch": 1.1324609099007772,
      "grad_norm": 0.43067288398742676,
      "learning_rate": 7.955278116910516e-06,
      "loss": 0.4539,
      "step": 36865
    },
    {
      "epoch": 1.1324916290357263,
      "grad_norm": 0.4252425730228424,
      "learning_rate": 7.954805052464915e-06,
      "loss": 0.4635,
      "step": 36866
    },
    {
      "epoch": 1.1325223481706754,
      "grad_norm": 0.39858517050743103,
      "learning_rate": 7.954331992796012e-06,
      "loss": 0.4471,
      "step": 36867
    },
    {
      "epoch": 1.1325530673056248,
      "grad_norm": 0.42000800371170044,
      "learning_rate": 7.953858937904909e-06,
      "loss": 0.5223,
      "step": 36868
    },
    {
      "epoch": 1.132583786440574,
      "grad_norm": 0.3672613799571991,
      "learning_rate": 7.953385887792711e-06,
      "loss": 0.4417,
      "step": 36869
    },
    {
      "epoch": 1.132614505575523,
      "grad_norm": 0.4089730679988861,
      "learning_rate": 7.952912842460524e-06,
      "loss": 0.5098,
      "step": 36870
    },
    {
      "epoch": 1.1326452247104721,
      "grad_norm": 0.3985975980758667,
      "learning_rate": 7.952439801909451e-06,
      "loss": 0.4871,
      "step": 36871
    },
    {
      "epoch": 1.1326759438454213,
      "grad_norm": 0.4434913098812103,
      "learning_rate": 7.951966766140598e-06,
      "loss": 0.5375,
      "step": 36872
    },
    {
      "epoch": 1.1327066629803704,
      "grad_norm": 0.3752886950969696,
      "learning_rate": 7.95149373515507e-06,
      "loss": 0.4553,
      "step": 36873
    },
    {
      "epoch": 1.1327373821153197,
      "grad_norm": 0.38121476769447327,
      "learning_rate": 7.95102070895397e-06,
      "loss": 0.4461,
      "step": 36874
    },
    {
      "epoch": 1.1327681012502688,
      "grad_norm": 0.40753793716430664,
      "learning_rate": 7.950547687538405e-06,
      "loss": 0.539,
      "step": 36875
    },
    {
      "epoch": 1.132798820385218,
      "grad_norm": 0.387342631816864,
      "learning_rate": 7.95007467090948e-06,
      "loss": 0.515,
      "step": 36876
    },
    {
      "epoch": 1.132829539520167,
      "grad_norm": 0.40891799330711365,
      "learning_rate": 7.949601659068298e-06,
      "loss": 0.4892,
      "step": 36877
    },
    {
      "epoch": 1.1328602586551162,
      "grad_norm": 0.3884458839893341,
      "learning_rate": 7.949128652015966e-06,
      "loss": 0.5324,
      "step": 36878
    },
    {
      "epoch": 1.1328909777900655,
      "grad_norm": 0.40184372663497925,
      "learning_rate": 7.948655649753584e-06,
      "loss": 0.517,
      "step": 36879
    },
    {
      "epoch": 1.1329216969250147,
      "grad_norm": 0.35113900899887085,
      "learning_rate": 7.948182652282265e-06,
      "loss": 0.4817,
      "step": 36880
    },
    {
      "epoch": 1.1329524160599638,
      "grad_norm": 0.3808857500553131,
      "learning_rate": 7.947709659603104e-06,
      "loss": 0.5069,
      "step": 36881
    },
    {
      "epoch": 1.132983135194913,
      "grad_norm": 0.39262792468070984,
      "learning_rate": 7.947236671717216e-06,
      "loss": 0.4142,
      "step": 36882
    },
    {
      "epoch": 1.133013854329862,
      "grad_norm": 0.39800792932510376,
      "learning_rate": 7.94676368862569e-06,
      "loss": 0.4573,
      "step": 36883
    },
    {
      "epoch": 1.1330445734648111,
      "grad_norm": 0.39058175683021545,
      "learning_rate": 7.946290710329653e-06,
      "loss": 0.4312,
      "step": 36884
    },
    {
      "epoch": 1.1330752925997605,
      "grad_norm": 0.3729003965854645,
      "learning_rate": 7.945817736830187e-06,
      "loss": 0.421,
      "step": 36885
    },
    {
      "epoch": 1.1331060117347096,
      "grad_norm": 0.4619048535823822,
      "learning_rate": 7.945344768128415e-06,
      "loss": 0.514,
      "step": 36886
    },
    {
      "epoch": 1.1331367308696587,
      "grad_norm": 0.38407236337661743,
      "learning_rate": 7.94487180422543e-06,
      "loss": 0.5288,
      "step": 36887
    },
    {
      "epoch": 1.1331674500046078,
      "grad_norm": 0.37470459938049316,
      "learning_rate": 7.944398845122342e-06,
      "loss": 0.4973,
      "step": 36888
    },
    {
      "epoch": 1.133198169139557,
      "grad_norm": 0.3425183594226837,
      "learning_rate": 7.943925890820251e-06,
      "loss": 0.5283,
      "step": 36889
    },
    {
      "epoch": 1.1332288882745063,
      "grad_norm": 0.3839905261993408,
      "learning_rate": 7.943452941320269e-06,
      "loss": 0.4545,
      "step": 36890
    },
    {
      "epoch": 1.1332596074094554,
      "grad_norm": 0.4159511625766754,
      "learning_rate": 7.942979996623492e-06,
      "loss": 0.5139,
      "step": 36891
    },
    {
      "epoch": 1.1332903265444045,
      "grad_norm": 0.3830459713935852,
      "learning_rate": 7.942507056731033e-06,
      "loss": 0.4816,
      "step": 36892
    },
    {
      "epoch": 1.1333210456793537,
      "grad_norm": 0.3768047094345093,
      "learning_rate": 7.942034121643988e-06,
      "loss": 0.4862,
      "step": 36893
    },
    {
      "epoch": 1.1333517648143028,
      "grad_norm": 0.40615880489349365,
      "learning_rate": 7.941561191363468e-06,
      "loss": 0.4456,
      "step": 36894
    },
    {
      "epoch": 1.133382483949252,
      "grad_norm": 0.3883635997772217,
      "learning_rate": 7.941088265890577e-06,
      "loss": 0.4223,
      "step": 36895
    },
    {
      "epoch": 1.1334132030842012,
      "grad_norm": 0.38832545280456543,
      "learning_rate": 7.940615345226415e-06,
      "loss": 0.5262,
      "step": 36896
    },
    {
      "epoch": 1.1334439222191504,
      "grad_norm": 0.3672095239162445,
      "learning_rate": 7.940142429372094e-06,
      "loss": 0.5087,
      "step": 36897
    },
    {
      "epoch": 1.1334746413540995,
      "grad_norm": 0.3815074861049652,
      "learning_rate": 7.939669518328712e-06,
      "loss": 0.5092,
      "step": 36898
    },
    {
      "epoch": 1.1335053604890486,
      "grad_norm": 0.39066317677497864,
      "learning_rate": 7.939196612097376e-06,
      "loss": 0.4376,
      "step": 36899
    },
    {
      "epoch": 1.1335360796239977,
      "grad_norm": 0.36543744802474976,
      "learning_rate": 7.938723710679188e-06,
      "loss": 0.4354,
      "step": 36900
    },
    {
      "epoch": 1.133566798758947,
      "grad_norm": 0.3881165087223053,
      "learning_rate": 7.938250814075258e-06,
      "loss": 0.5058,
      "step": 36901
    },
    {
      "epoch": 1.1335975178938962,
      "grad_norm": 0.3862670958042145,
      "learning_rate": 7.937777922286684e-06,
      "loss": 0.5191,
      "step": 36902
    },
    {
      "epoch": 1.1336282370288453,
      "grad_norm": 0.5075985789299011,
      "learning_rate": 7.937305035314577e-06,
      "loss": 0.4819,
      "step": 36903
    },
    {
      "epoch": 1.1336589561637944,
      "grad_norm": 0.3715755343437195,
      "learning_rate": 7.936832153160038e-06,
      "loss": 0.405,
      "step": 36904
    },
    {
      "epoch": 1.1336896752987435,
      "grad_norm": 0.3958597481250763,
      "learning_rate": 7.936359275824169e-06,
      "loss": 0.4208,
      "step": 36905
    },
    {
      "epoch": 1.1337203944336927,
      "grad_norm": 0.39656567573547363,
      "learning_rate": 7.935886403308078e-06,
      "loss": 0.5197,
      "step": 36906
    },
    {
      "epoch": 1.133751113568642,
      "grad_norm": 0.37596723437309265,
      "learning_rate": 7.93541353561287e-06,
      "loss": 0.4834,
      "step": 36907
    },
    {
      "epoch": 1.1337818327035911,
      "grad_norm": 0.38505107164382935,
      "learning_rate": 7.934940672739645e-06,
      "loss": 0.5541,
      "step": 36908
    },
    {
      "epoch": 1.1338125518385402,
      "grad_norm": 0.4013684093952179,
      "learning_rate": 7.934467814689516e-06,
      "loss": 0.5054,
      "step": 36909
    },
    {
      "epoch": 1.1338432709734894,
      "grad_norm": 0.39788341522216797,
      "learning_rate": 7.933994961463574e-06,
      "loss": 0.5906,
      "step": 36910
    },
    {
      "epoch": 1.1338739901084385,
      "grad_norm": 0.4191548526287079,
      "learning_rate": 7.933522113062933e-06,
      "loss": 0.5015,
      "step": 36911
    },
    {
      "epoch": 1.1339047092433878,
      "grad_norm": 0.39153826236724854,
      "learning_rate": 7.933049269488698e-06,
      "loss": 0.496,
      "step": 36912
    },
    {
      "epoch": 1.133935428378337,
      "grad_norm": 0.38036149740219116,
      "learning_rate": 7.93257643074197e-06,
      "loss": 0.4547,
      "step": 36913
    },
    {
      "epoch": 1.133966147513286,
      "grad_norm": 0.42335057258605957,
      "learning_rate": 7.932103596823854e-06,
      "loss": 0.5155,
      "step": 36914
    },
    {
      "epoch": 1.1339968666482352,
      "grad_norm": 0.38347285985946655,
      "learning_rate": 7.931630767735455e-06,
      "loss": 0.4535,
      "step": 36915
    },
    {
      "epoch": 1.1340275857831843,
      "grad_norm": 0.3658248484134674,
      "learning_rate": 7.931157943477879e-06,
      "loss": 0.5084,
      "step": 36916
    },
    {
      "epoch": 1.1340583049181334,
      "grad_norm": 0.4027783274650574,
      "learning_rate": 7.930685124052221e-06,
      "loss": 0.4979,
      "step": 36917
    },
    {
      "epoch": 1.1340890240530828,
      "grad_norm": 0.3952813446521759,
      "learning_rate": 7.930212309459601e-06,
      "loss": 0.4958,
      "step": 36918
    },
    {
      "epoch": 1.1341197431880319,
      "grad_norm": 0.3660188615322113,
      "learning_rate": 7.929739499701109e-06,
      "loss": 0.5024,
      "step": 36919
    },
    {
      "epoch": 1.134150462322981,
      "grad_norm": 0.3754180669784546,
      "learning_rate": 7.92926669477786e-06,
      "loss": 0.5006,
      "step": 36920
    },
    {
      "epoch": 1.1341811814579301,
      "grad_norm": 0.4606361389160156,
      "learning_rate": 7.928793894690946e-06,
      "loss": 0.5024,
      "step": 36921
    },
    {
      "epoch": 1.1342119005928792,
      "grad_norm": 0.43674686551094055,
      "learning_rate": 7.928321099441484e-06,
      "loss": 0.4875,
      "step": 36922
    },
    {
      "epoch": 1.1342426197278286,
      "grad_norm": 0.4648934006690979,
      "learning_rate": 7.92784830903057e-06,
      "loss": 0.4968,
      "step": 36923
    },
    {
      "epoch": 1.1342733388627777,
      "grad_norm": 0.3946649134159088,
      "learning_rate": 7.927375523459314e-06,
      "loss": 0.4812,
      "step": 36924
    },
    {
      "epoch": 1.1343040579977268,
      "grad_norm": 0.42677196860313416,
      "learning_rate": 7.926902742728813e-06,
      "loss": 0.4909,
      "step": 36925
    },
    {
      "epoch": 1.134334777132676,
      "grad_norm": 0.3845316469669342,
      "learning_rate": 7.92642996684018e-06,
      "loss": 0.4587,
      "step": 36926
    },
    {
      "epoch": 1.134365496267625,
      "grad_norm": 0.4051971435546875,
      "learning_rate": 7.92595719579451e-06,
      "loss": 0.5293,
      "step": 36927
    },
    {
      "epoch": 1.1343962154025742,
      "grad_norm": 0.3852175176143646,
      "learning_rate": 7.925484429592915e-06,
      "loss": 0.4453,
      "step": 36928
    },
    {
      "epoch": 1.1344269345375233,
      "grad_norm": 0.3681160807609558,
      "learning_rate": 7.925011668236496e-06,
      "loss": 0.5317,
      "step": 36929
    },
    {
      "epoch": 1.1344576536724726,
      "grad_norm": 0.4493587017059326,
      "learning_rate": 7.924538911726353e-06,
      "loss": 0.556,
      "step": 36930
    },
    {
      "epoch": 1.1344883728074218,
      "grad_norm": 0.41909870505332947,
      "learning_rate": 7.924066160063599e-06,
      "loss": 0.544,
      "step": 36931
    },
    {
      "epoch": 1.1345190919423709,
      "grad_norm": 0.4052278697490692,
      "learning_rate": 7.92359341324933e-06,
      "loss": 0.5475,
      "step": 36932
    },
    {
      "epoch": 1.13454981107732,
      "grad_norm": 0.371452271938324,
      "learning_rate": 7.923120671284658e-06,
      "loss": 0.5236,
      "step": 36933
    },
    {
      "epoch": 1.1345805302122693,
      "grad_norm": 0.3951089382171631,
      "learning_rate": 7.92264793417068e-06,
      "loss": 0.4657,
      "step": 36934
    },
    {
      "epoch": 1.1346112493472185,
      "grad_norm": 0.3896147310733795,
      "learning_rate": 7.922175201908504e-06,
      "loss": 0.4919,
      "step": 36935
    },
    {
      "epoch": 1.1346419684821676,
      "grad_norm": 0.5801007151603699,
      "learning_rate": 7.92170247449923e-06,
      "loss": 0.4212,
      "step": 36936
    },
    {
      "epoch": 1.1346726876171167,
      "grad_norm": 0.3799929618835449,
      "learning_rate": 7.921229751943969e-06,
      "loss": 0.5498,
      "step": 36937
    },
    {
      "epoch": 1.1347034067520658,
      "grad_norm": 0.44418591260910034,
      "learning_rate": 7.920757034243817e-06,
      "loss": 0.5135,
      "step": 36938
    },
    {
      "epoch": 1.134734125887015,
      "grad_norm": 0.45363810658454895,
      "learning_rate": 7.920284321399886e-06,
      "loss": 0.4701,
      "step": 36939
    },
    {
      "epoch": 1.134764845021964,
      "grad_norm": 0.39003312587738037,
      "learning_rate": 7.919811613413275e-06,
      "loss": 0.5277,
      "step": 36940
    },
    {
      "epoch": 1.1347955641569134,
      "grad_norm": 0.41855016350746155,
      "learning_rate": 7.91933891028509e-06,
      "loss": 0.5166,
      "step": 36941
    },
    {
      "epoch": 1.1348262832918625,
      "grad_norm": 0.38797205686569214,
      "learning_rate": 7.918866212016431e-06,
      "loss": 0.5254,
      "step": 36942
    },
    {
      "epoch": 1.1348570024268116,
      "grad_norm": 0.3900837302207947,
      "learning_rate": 7.918393518608412e-06,
      "loss": 0.4914,
      "step": 36943
    },
    {
      "epoch": 1.1348877215617608,
      "grad_norm": 0.5067312717437744,
      "learning_rate": 7.917920830062123e-06,
      "loss": 0.4274,
      "step": 36944
    },
    {
      "epoch": 1.1349184406967099,
      "grad_norm": 0.43108880519866943,
      "learning_rate": 7.91744814637868e-06,
      "loss": 0.5291,
      "step": 36945
    },
    {
      "epoch": 1.1349491598316592,
      "grad_norm": 0.4238395392894745,
      "learning_rate": 7.916975467559177e-06,
      "loss": 0.426,
      "step": 36946
    },
    {
      "epoch": 1.1349798789666083,
      "grad_norm": 0.370324045419693,
      "learning_rate": 7.91650279360473e-06,
      "loss": 0.4375,
      "step": 36947
    },
    {
      "epoch": 1.1350105981015575,
      "grad_norm": 0.3643943667411804,
      "learning_rate": 7.916030124516429e-06,
      "loss": 0.4842,
      "step": 36948
    },
    {
      "epoch": 1.1350413172365066,
      "grad_norm": 0.6093102693557739,
      "learning_rate": 7.91555746029539e-06,
      "loss": 0.4689,
      "step": 36949
    },
    {
      "epoch": 1.1350720363714557,
      "grad_norm": 0.3656734824180603,
      "learning_rate": 7.915084800942714e-06,
      "loss": 0.4219,
      "step": 36950
    },
    {
      "epoch": 1.1351027555064048,
      "grad_norm": 0.5793356895446777,
      "learning_rate": 7.914612146459496e-06,
      "loss": 0.5714,
      "step": 36951
    },
    {
      "epoch": 1.1351334746413542,
      "grad_norm": 0.38591983914375305,
      "learning_rate": 7.914139496846856e-06,
      "loss": 0.4427,
      "step": 36952
    },
    {
      "epoch": 1.1351641937763033,
      "grad_norm": 0.499652624130249,
      "learning_rate": 7.91366685210588e-06,
      "loss": 0.5308,
      "step": 36953
    },
    {
      "epoch": 1.1351949129112524,
      "grad_norm": 0.3666210174560547,
      "learning_rate": 7.913194212237689e-06,
      "loss": 0.4193,
      "step": 36954
    },
    {
      "epoch": 1.1352256320462015,
      "grad_norm": 0.40249961614608765,
      "learning_rate": 7.912721577243369e-06,
      "loss": 0.4389,
      "step": 36955
    },
    {
      "epoch": 1.1352563511811506,
      "grad_norm": 0.36745259165763855,
      "learning_rate": 7.912248947124044e-06,
      "loss": 0.4538,
      "step": 36956
    },
    {
      "epoch": 1.1352870703161,
      "grad_norm": 0.3798019289970398,
      "learning_rate": 7.911776321880801e-06,
      "loss": 0.5047,
      "step": 36957
    },
    {
      "epoch": 1.135317789451049,
      "grad_norm": 0.3794703781604767,
      "learning_rate": 7.911303701514754e-06,
      "loss": 0.4767,
      "step": 36958
    },
    {
      "epoch": 1.1353485085859982,
      "grad_norm": 0.4209107756614685,
      "learning_rate": 7.910831086027e-06,
      "loss": 0.5732,
      "step": 36959
    },
    {
      "epoch": 1.1353792277209473,
      "grad_norm": 0.36698710918426514,
      "learning_rate": 7.910358475418648e-06,
      "loss": 0.4596,
      "step": 36960
    },
    {
      "epoch": 1.1354099468558965,
      "grad_norm": 0.41389358043670654,
      "learning_rate": 7.909885869690795e-06,
      "loss": 0.4612,
      "step": 36961
    },
    {
      "epoch": 1.1354406659908456,
      "grad_norm": 1.0584450960159302,
      "learning_rate": 7.909413268844554e-06,
      "loss": 0.4927,
      "step": 36962
    },
    {
      "epoch": 1.135471385125795,
      "grad_norm": 0.38413235545158386,
      "learning_rate": 7.908940672881023e-06,
      "loss": 0.5155,
      "step": 36963
    },
    {
      "epoch": 1.135502104260744,
      "grad_norm": 0.399074524641037,
      "learning_rate": 7.908468081801309e-06,
      "loss": 0.5303,
      "step": 36964
    },
    {
      "epoch": 1.1355328233956932,
      "grad_norm": 0.38787907361984253,
      "learning_rate": 7.90799549560651e-06,
      "loss": 0.4486,
      "step": 36965
    },
    {
      "epoch": 1.1355635425306423,
      "grad_norm": 0.3822980523109436,
      "learning_rate": 7.907522914297735e-06,
      "loss": 0.4276,
      "step": 36966
    },
    {
      "epoch": 1.1355942616655914,
      "grad_norm": 0.3970640003681183,
      "learning_rate": 7.907050337876089e-06,
      "loss": 0.5011,
      "step": 36967
    },
    {
      "epoch": 1.1356249808005408,
      "grad_norm": 0.386884480714798,
      "learning_rate": 7.90657776634267e-06,
      "loss": 0.4641,
      "step": 36968
    },
    {
      "epoch": 1.1356556999354899,
      "grad_norm": 0.37514644861221313,
      "learning_rate": 7.906105199698587e-06,
      "loss": 0.4955,
      "step": 36969
    },
    {
      "epoch": 1.135686419070439,
      "grad_norm": 0.36582255363464355,
      "learning_rate": 7.90563263794494e-06,
      "loss": 0.5672,
      "step": 36970
    },
    {
      "epoch": 1.135717138205388,
      "grad_norm": 0.4332919418811798,
      "learning_rate": 7.905160081082836e-06,
      "loss": 0.4725,
      "step": 36971
    },
    {
      "epoch": 1.1357478573403372,
      "grad_norm": 0.3766014873981476,
      "learning_rate": 7.904687529113374e-06,
      "loss": 0.4645,
      "step": 36972
    },
    {
      "epoch": 1.1357785764752863,
      "grad_norm": 0.4044293463230133,
      "learning_rate": 7.904214982037664e-06,
      "loss": 0.5356,
      "step": 36973
    },
    {
      "epoch": 1.1358092956102357,
      "grad_norm": 0.40196478366851807,
      "learning_rate": 7.903742439856805e-06,
      "loss": 0.4499,
      "step": 36974
    },
    {
      "epoch": 1.1358400147451848,
      "grad_norm": 0.3545234501361847,
      "learning_rate": 7.903269902571901e-06,
      "loss": 0.5328,
      "step": 36975
    },
    {
      "epoch": 1.135870733880134,
      "grad_norm": 0.39860132336616516,
      "learning_rate": 7.902797370184057e-06,
      "loss": 0.4415,
      "step": 36976
    },
    {
      "epoch": 1.135901453015083,
      "grad_norm": 0.4361482560634613,
      "learning_rate": 7.902324842694378e-06,
      "loss": 0.5513,
      "step": 36977
    },
    {
      "epoch": 1.1359321721500322,
      "grad_norm": 0.42306315898895264,
      "learning_rate": 7.901852320103963e-06,
      "loss": 0.4634,
      "step": 36978
    },
    {
      "epoch": 1.1359628912849815,
      "grad_norm": 0.3948831260204315,
      "learning_rate": 7.901379802413923e-06,
      "loss": 0.4898,
      "step": 36979
    },
    {
      "epoch": 1.1359936104199306,
      "grad_norm": 0.37308016419410706,
      "learning_rate": 7.90090728962535e-06,
      "loss": 0.5123,
      "step": 36980
    },
    {
      "epoch": 1.1360243295548798,
      "grad_norm": 0.38572147488594055,
      "learning_rate": 7.900434781739361e-06,
      "loss": 0.5027,
      "step": 36981
    },
    {
      "epoch": 1.1360550486898289,
      "grad_norm": 0.396320641040802,
      "learning_rate": 7.899962278757049e-06,
      "loss": 0.4699,
      "step": 36982
    },
    {
      "epoch": 1.136085767824778,
      "grad_norm": 0.3874286413192749,
      "learning_rate": 7.899489780679526e-06,
      "loss": 0.5606,
      "step": 36983
    },
    {
      "epoch": 1.1361164869597271,
      "grad_norm": 0.40283700823783875,
      "learning_rate": 7.899017287507887e-06,
      "loss": 0.4192,
      "step": 36984
    },
    {
      "epoch": 1.1361472060946765,
      "grad_norm": 0.4210040271282196,
      "learning_rate": 7.898544799243238e-06,
      "loss": 0.502,
      "step": 36985
    },
    {
      "epoch": 1.1361779252296256,
      "grad_norm": 0.4283956289291382,
      "learning_rate": 7.898072315886692e-06,
      "loss": 0.3661,
      "step": 36986
    },
    {
      "epoch": 1.1362086443645747,
      "grad_norm": 0.4045950174331665,
      "learning_rate": 7.897599837439338e-06,
      "loss": 0.4407,
      "step": 36987
    },
    {
      "epoch": 1.1362393634995238,
      "grad_norm": 0.3882567584514618,
      "learning_rate": 7.897127363902291e-06,
      "loss": 0.4444,
      "step": 36988
    },
    {
      "epoch": 1.136270082634473,
      "grad_norm": 0.4631681442260742,
      "learning_rate": 7.896654895276645e-06,
      "loss": 0.4991,
      "step": 36989
    },
    {
      "epoch": 1.1363008017694223,
      "grad_norm": 0.38217484951019287,
      "learning_rate": 7.896182431563517e-06,
      "loss": 0.4874,
      "step": 36990
    },
    {
      "epoch": 1.1363315209043714,
      "grad_norm": 0.43579360842704773,
      "learning_rate": 7.895709972763995e-06,
      "loss": 0.5484,
      "step": 36991
    },
    {
      "epoch": 1.1363622400393205,
      "grad_norm": 0.37142908573150635,
      "learning_rate": 7.895237518879192e-06,
      "loss": 0.4803,
      "step": 36992
    },
    {
      "epoch": 1.1363929591742696,
      "grad_norm": 0.4235420525074005,
      "learning_rate": 7.894765069910205e-06,
      "loss": 0.454,
      "step": 36993
    },
    {
      "epoch": 1.1364236783092188,
      "grad_norm": 0.4123857319355011,
      "learning_rate": 7.894292625858145e-06,
      "loss": 0.3866,
      "step": 36994
    },
    {
      "epoch": 1.1364543974441679,
      "grad_norm": 0.42872297763824463,
      "learning_rate": 7.893820186724109e-06,
      "loss": 0.5449,
      "step": 36995
    },
    {
      "epoch": 1.1364851165791172,
      "grad_norm": 0.3915287256240845,
      "learning_rate": 7.893347752509206e-06,
      "loss": 0.4999,
      "step": 36996
    },
    {
      "epoch": 1.1365158357140663,
      "grad_norm": 0.4025292694568634,
      "learning_rate": 7.892875323214534e-06,
      "loss": 0.4705,
      "step": 36997
    },
    {
      "epoch": 1.1365465548490155,
      "grad_norm": 0.5701542496681213,
      "learning_rate": 7.8924028988412e-06,
      "loss": 0.5115,
      "step": 36998
    },
    {
      "epoch": 1.1365772739839646,
      "grad_norm": 0.3757260739803314,
      "learning_rate": 7.891930479390306e-06,
      "loss": 0.49,
      "step": 36999
    },
    {
      "epoch": 1.1366079931189137,
      "grad_norm": 0.3873749077320099,
      "learning_rate": 7.891458064862956e-06,
      "loss": 0.493,
      "step": 37000
    },
    {
      "epoch": 1.136638712253863,
      "grad_norm": 0.39408570528030396,
      "learning_rate": 7.89098565526025e-06,
      "loss": 0.5007,
      "step": 37001
    },
    {
      "epoch": 1.1366694313888122,
      "grad_norm": 0.4150158166885376,
      "learning_rate": 7.890513250583299e-06,
      "loss": 0.5112,
      "step": 37002
    },
    {
      "epoch": 1.1367001505237613,
      "grad_norm": 0.5363106727600098,
      "learning_rate": 7.890040850833198e-06,
      "loss": 0.4104,
      "step": 37003
    },
    {
      "epoch": 1.1367308696587104,
      "grad_norm": 0.42842480540275574,
      "learning_rate": 7.889568456011054e-06,
      "loss": 0.4016,
      "step": 37004
    },
    {
      "epoch": 1.1367615887936595,
      "grad_norm": 0.4387744069099426,
      "learning_rate": 7.889096066117973e-06,
      "loss": 0.4462,
      "step": 37005
    },
    {
      "epoch": 1.1367923079286086,
      "grad_norm": 0.35564228892326355,
      "learning_rate": 7.888623681155054e-06,
      "loss": 0.4509,
      "step": 37006
    },
    {
      "epoch": 1.136823027063558,
      "grad_norm": 0.41333281993865967,
      "learning_rate": 7.888151301123402e-06,
      "loss": 0.5313,
      "step": 37007
    },
    {
      "epoch": 1.136853746198507,
      "grad_norm": 0.42675086855888367,
      "learning_rate": 7.88767892602412e-06,
      "loss": 0.4657,
      "step": 37008
    },
    {
      "epoch": 1.1368844653334562,
      "grad_norm": 0.40372878313064575,
      "learning_rate": 7.887206555858312e-06,
      "loss": 0.4853,
      "step": 37009
    },
    {
      "epoch": 1.1369151844684053,
      "grad_norm": 0.39204832911491394,
      "learning_rate": 7.886734190627079e-06,
      "loss": 0.4983,
      "step": 37010
    },
    {
      "epoch": 1.1369459036033545,
      "grad_norm": 0.3803746998310089,
      "learning_rate": 7.886261830331527e-06,
      "loss": 0.4422,
      "step": 37011
    },
    {
      "epoch": 1.1369766227383038,
      "grad_norm": 0.3923000991344452,
      "learning_rate": 7.885789474972758e-06,
      "loss": 0.4458,
      "step": 37012
    },
    {
      "epoch": 1.137007341873253,
      "grad_norm": 0.3829500675201416,
      "learning_rate": 7.885317124551879e-06,
      "loss": 0.4595,
      "step": 37013
    },
    {
      "epoch": 1.137038061008202,
      "grad_norm": 0.40597182512283325,
      "learning_rate": 7.884844779069983e-06,
      "loss": 0.5322,
      "step": 37014
    },
    {
      "epoch": 1.1370687801431512,
      "grad_norm": 0.43054014444351196,
      "learning_rate": 7.884372438528185e-06,
      "loss": 0.4928,
      "step": 37015
    },
    {
      "epoch": 1.1370994992781003,
      "grad_norm": 0.47374847531318665,
      "learning_rate": 7.883900102927577e-06,
      "loss": 0.4449,
      "step": 37016
    },
    {
      "epoch": 1.1371302184130494,
      "grad_norm": 0.4161330461502075,
      "learning_rate": 7.883427772269276e-06,
      "loss": 0.4786,
      "step": 37017
    },
    {
      "epoch": 1.1371609375479987,
      "grad_norm": 0.39974334836006165,
      "learning_rate": 7.88295544655437e-06,
      "loss": 0.4877,
      "step": 37018
    },
    {
      "epoch": 1.1371916566829479,
      "grad_norm": 0.3956177830696106,
      "learning_rate": 7.882483125783976e-06,
      "loss": 0.5752,
      "step": 37019
    },
    {
      "epoch": 1.137222375817897,
      "grad_norm": 0.34950703382492065,
      "learning_rate": 7.882010809959185e-06,
      "loss": 0.3437,
      "step": 37020
    },
    {
      "epoch": 1.137253094952846,
      "grad_norm": 0.38146498799324036,
      "learning_rate": 7.881538499081106e-06,
      "loss": 0.4369,
      "step": 37021
    },
    {
      "epoch": 1.1372838140877952,
      "grad_norm": 0.4059842824935913,
      "learning_rate": 7.881066193150846e-06,
      "loss": 0.518,
      "step": 37022
    },
    {
      "epoch": 1.1373145332227446,
      "grad_norm": 0.45612961053848267,
      "learning_rate": 7.880593892169496e-06,
      "loss": 0.4966,
      "step": 37023
    },
    {
      "epoch": 1.1373452523576937,
      "grad_norm": 0.388187438249588,
      "learning_rate": 7.880121596138177e-06,
      "loss": 0.4741,
      "step": 37024
    },
    {
      "epoch": 1.1373759714926428,
      "grad_norm": 0.42293432354927063,
      "learning_rate": 7.879649305057975e-06,
      "loss": 0.5271,
      "step": 37025
    },
    {
      "epoch": 1.137406690627592,
      "grad_norm": 0.42162007093429565,
      "learning_rate": 7.879177018930005e-06,
      "loss": 0.4953,
      "step": 37026
    },
    {
      "epoch": 1.137437409762541,
      "grad_norm": 0.40777644515037537,
      "learning_rate": 7.878704737755362e-06,
      "loss": 0.5233,
      "step": 37027
    },
    {
      "epoch": 1.1374681288974902,
      "grad_norm": 0.4038427770137787,
      "learning_rate": 7.878232461535154e-06,
      "loss": 0.4986,
      "step": 37028
    },
    {
      "epoch": 1.1374988480324395,
      "grad_norm": 0.4016590714454651,
      "learning_rate": 7.87776019027048e-06,
      "loss": 0.478,
      "step": 37029
    },
    {
      "epoch": 1.1375295671673886,
      "grad_norm": 0.3784770965576172,
      "learning_rate": 7.877287923962447e-06,
      "loss": 0.5258,
      "step": 37030
    },
    {
      "epoch": 1.1375602863023377,
      "grad_norm": 0.4141036570072174,
      "learning_rate": 7.876815662612155e-06,
      "loss": 0.537,
      "step": 37031
    },
    {
      "epoch": 1.1375910054372869,
      "grad_norm": 0.43121543526649475,
      "learning_rate": 7.87634340622071e-06,
      "loss": 0.4946,
      "step": 37032
    },
    {
      "epoch": 1.137621724572236,
      "grad_norm": 0.42312851548194885,
      "learning_rate": 7.875871154789212e-06,
      "loss": 0.4418,
      "step": 37033
    },
    {
      "epoch": 1.1376524437071853,
      "grad_norm": 0.3706146478652954,
      "learning_rate": 7.875398908318766e-06,
      "loss": 0.5183,
      "step": 37034
    },
    {
      "epoch": 1.1376831628421344,
      "grad_norm": 0.4067630469799042,
      "learning_rate": 7.874926666810473e-06,
      "loss": 0.5526,
      "step": 37035
    },
    {
      "epoch": 1.1377138819770836,
      "grad_norm": 0.3680829107761383,
      "learning_rate": 7.874454430265439e-06,
      "loss": 0.4762,
      "step": 37036
    },
    {
      "epoch": 1.1377446011120327,
      "grad_norm": 0.3749326467514038,
      "learning_rate": 7.873982198684763e-06,
      "loss": 0.4857,
      "step": 37037
    },
    {
      "epoch": 1.1377753202469818,
      "grad_norm": 0.4846896827220917,
      "learning_rate": 7.873509972069554e-06,
      "loss": 0.4768,
      "step": 37038
    },
    {
      "epoch": 1.137806039381931,
      "grad_norm": 0.4040449559688568,
      "learning_rate": 7.873037750420907e-06,
      "loss": 0.4618,
      "step": 37039
    },
    {
      "epoch": 1.13783675851688,
      "grad_norm": 0.40955930948257446,
      "learning_rate": 7.872565533739928e-06,
      "loss": 0.5514,
      "step": 37040
    },
    {
      "epoch": 1.1378674776518294,
      "grad_norm": 0.4303429424762726,
      "learning_rate": 7.872093322027725e-06,
      "loss": 0.4761,
      "step": 37041
    },
    {
      "epoch": 1.1378981967867785,
      "grad_norm": 0.3882708251476288,
      "learning_rate": 7.871621115285392e-06,
      "loss": 0.4729,
      "step": 37042
    },
    {
      "epoch": 1.1379289159217276,
      "grad_norm": 0.38201242685317993,
      "learning_rate": 7.87114891351404e-06,
      "loss": 0.4841,
      "step": 37043
    },
    {
      "epoch": 1.1379596350566767,
      "grad_norm": 0.3591639995574951,
      "learning_rate": 7.870676716714767e-06,
      "loss": 0.4918,
      "step": 37044
    },
    {
      "epoch": 1.137990354191626,
      "grad_norm": 0.4063514769077301,
      "learning_rate": 7.870204524888678e-06,
      "loss": 0.5762,
      "step": 37045
    },
    {
      "epoch": 1.1380210733265752,
      "grad_norm": 0.3692830502986908,
      "learning_rate": 7.869732338036874e-06,
      "loss": 0.4471,
      "step": 37046
    },
    {
      "epoch": 1.1380517924615243,
      "grad_norm": 0.39800864458084106,
      "learning_rate": 7.869260156160461e-06,
      "loss": 0.4851,
      "step": 37047
    },
    {
      "epoch": 1.1380825115964734,
      "grad_norm": 0.36636069416999817,
      "learning_rate": 7.868787979260538e-06,
      "loss": 0.4755,
      "step": 37048
    },
    {
      "epoch": 1.1381132307314226,
      "grad_norm": 0.3808705508708954,
      "learning_rate": 7.868315807338213e-06,
      "loss": 0.5078,
      "step": 37049
    },
    {
      "epoch": 1.1381439498663717,
      "grad_norm": 0.37298792600631714,
      "learning_rate": 7.86784364039458e-06,
      "loss": 0.5228,
      "step": 37050
    },
    {
      "epoch": 1.1381746690013208,
      "grad_norm": 0.38089704513549805,
      "learning_rate": 7.86737147843075e-06,
      "loss": 0.4756,
      "step": 37051
    },
    {
      "epoch": 1.1382053881362701,
      "grad_norm": 0.40182074904441833,
      "learning_rate": 7.86689932144782e-06,
      "loss": 0.5711,
      "step": 37052
    },
    {
      "epoch": 1.1382361072712193,
      "grad_norm": 0.38614368438720703,
      "learning_rate": 7.8664271694469e-06,
      "loss": 0.5157,
      "step": 37053
    },
    {
      "epoch": 1.1382668264061684,
      "grad_norm": 0.4015420973300934,
      "learning_rate": 7.865955022429086e-06,
      "loss": 0.5347,
      "step": 37054
    },
    {
      "epoch": 1.1382975455411175,
      "grad_norm": 0.48097673058509827,
      "learning_rate": 7.865482880395485e-06,
      "loss": 0.4946,
      "step": 37055
    },
    {
      "epoch": 1.1383282646760666,
      "grad_norm": 0.3834722936153412,
      "learning_rate": 7.865010743347194e-06,
      "loss": 0.5353,
      "step": 37056
    },
    {
      "epoch": 1.138358983811016,
      "grad_norm": 0.41609933972358704,
      "learning_rate": 7.864538611285319e-06,
      "loss": 0.4626,
      "step": 37057
    },
    {
      "epoch": 1.138389702945965,
      "grad_norm": 0.3995834290981293,
      "learning_rate": 7.864066484210969e-06,
      "loss": 0.5579,
      "step": 37058
    },
    {
      "epoch": 1.1384204220809142,
      "grad_norm": 0.3956362009048462,
      "learning_rate": 7.863594362125234e-06,
      "loss": 0.4961,
      "step": 37059
    },
    {
      "epoch": 1.1384511412158633,
      "grad_norm": 0.4016041159629822,
      "learning_rate": 7.863122245029231e-06,
      "loss": 0.4811,
      "step": 37060
    },
    {
      "epoch": 1.1384818603508124,
      "grad_norm": 0.37302184104919434,
      "learning_rate": 7.86265013292405e-06,
      "loss": 0.4939,
      "step": 37061
    },
    {
      "epoch": 1.1385125794857616,
      "grad_norm": 0.41663211584091187,
      "learning_rate": 7.8621780258108e-06,
      "loss": 0.5232,
      "step": 37062
    },
    {
      "epoch": 1.138543298620711,
      "grad_norm": 0.3882730007171631,
      "learning_rate": 7.861705923690584e-06,
      "loss": 0.459,
      "step": 37063
    },
    {
      "epoch": 1.13857401775566,
      "grad_norm": 0.404579758644104,
      "learning_rate": 7.861233826564502e-06,
      "loss": 0.4316,
      "step": 37064
    },
    {
      "epoch": 1.1386047368906091,
      "grad_norm": 0.435691773891449,
      "learning_rate": 7.860761734433657e-06,
      "loss": 0.4753,
      "step": 37065
    },
    {
      "epoch": 1.1386354560255583,
      "grad_norm": 0.4201490581035614,
      "learning_rate": 7.860289647299154e-06,
      "loss": 0.4944,
      "step": 37066
    },
    {
      "epoch": 1.1386661751605074,
      "grad_norm": 0.399119108915329,
      "learning_rate": 7.859817565162092e-06,
      "loss": 0.5311,
      "step": 37067
    },
    {
      "epoch": 1.1386968942954567,
      "grad_norm": 0.3881491720676422,
      "learning_rate": 7.859345488023578e-06,
      "loss": 0.5736,
      "step": 37068
    },
    {
      "epoch": 1.1387276134304058,
      "grad_norm": 0.38555800914764404,
      "learning_rate": 7.85887341588471e-06,
      "loss": 0.4635,
      "step": 37069
    },
    {
      "epoch": 1.138758332565355,
      "grad_norm": 0.4355103373527527,
      "learning_rate": 7.858401348746594e-06,
      "loss": 0.546,
      "step": 37070
    },
    {
      "epoch": 1.138789051700304,
      "grad_norm": 0.38740450143814087,
      "learning_rate": 7.857929286610329e-06,
      "loss": 0.5069,
      "step": 37071
    },
    {
      "epoch": 1.1388197708352532,
      "grad_norm": 0.3942693769931793,
      "learning_rate": 7.857457229477024e-06,
      "loss": 0.4752,
      "step": 37072
    },
    {
      "epoch": 1.1388504899702023,
      "grad_norm": 0.5144684910774231,
      "learning_rate": 7.856985177347772e-06,
      "loss": 0.4118,
      "step": 37073
    },
    {
      "epoch": 1.1388812091051517,
      "grad_norm": 0.34426528215408325,
      "learning_rate": 7.856513130223685e-06,
      "loss": 0.4287,
      "step": 37074
    },
    {
      "epoch": 1.1389119282401008,
      "grad_norm": 0.41874486207962036,
      "learning_rate": 7.85604108810586e-06,
      "loss": 0.5326,
      "step": 37075
    },
    {
      "epoch": 1.13894264737505,
      "grad_norm": 0.38064053654670715,
      "learning_rate": 7.855569050995397e-06,
      "loss": 0.542,
      "step": 37076
    },
    {
      "epoch": 1.138973366509999,
      "grad_norm": 0.47560712695121765,
      "learning_rate": 7.855097018893408e-06,
      "loss": 0.4912,
      "step": 37077
    },
    {
      "epoch": 1.1390040856449481,
      "grad_norm": 0.34127077460289,
      "learning_rate": 7.854624991800986e-06,
      "loss": 0.4339,
      "step": 37078
    },
    {
      "epoch": 1.1390348047798975,
      "grad_norm": 0.5746409893035889,
      "learning_rate": 7.85415296971924e-06,
      "loss": 0.5192,
      "step": 37079
    },
    {
      "epoch": 1.1390655239148466,
      "grad_norm": 0.4195559024810791,
      "learning_rate": 7.853680952649268e-06,
      "loss": 0.4576,
      "step": 37080
    },
    {
      "epoch": 1.1390962430497957,
      "grad_norm": 0.37681034207344055,
      "learning_rate": 7.853208940592175e-06,
      "loss": 0.5086,
      "step": 37081
    },
    {
      "epoch": 1.1391269621847449,
      "grad_norm": 0.38769078254699707,
      "learning_rate": 7.85273693354906e-06,
      "loss": 0.4649,
      "step": 37082
    },
    {
      "epoch": 1.139157681319694,
      "grad_norm": 0.44037365913391113,
      "learning_rate": 7.852264931521034e-06,
      "loss": 0.412,
      "step": 37083
    },
    {
      "epoch": 1.139188400454643,
      "grad_norm": 0.3862050771713257,
      "learning_rate": 7.851792934509185e-06,
      "loss": 0.4142,
      "step": 37084
    },
    {
      "epoch": 1.1392191195895924,
      "grad_norm": 0.3985099792480469,
      "learning_rate": 7.851320942514631e-06,
      "loss": 0.4692,
      "step": 37085
    },
    {
      "epoch": 1.1392498387245416,
      "grad_norm": 0.40153801441192627,
      "learning_rate": 7.85084895553846e-06,
      "loss": 0.493,
      "step": 37086
    },
    {
      "epoch": 1.1392805578594907,
      "grad_norm": 0.4311068058013916,
      "learning_rate": 7.850376973581788e-06,
      "loss": 0.5151,
      "step": 37087
    },
    {
      "epoch": 1.1393112769944398,
      "grad_norm": 0.5370480418205261,
      "learning_rate": 7.849904996645705e-06,
      "loss": 0.4791,
      "step": 37088
    },
    {
      "epoch": 1.139341996129389,
      "grad_norm": 0.5707345604896545,
      "learning_rate": 7.849433024731324e-06,
      "loss": 0.4905,
      "step": 37089
    },
    {
      "epoch": 1.1393727152643383,
      "grad_norm": 0.38960978388786316,
      "learning_rate": 7.848961057839739e-06,
      "loss": 0.4953,
      "step": 37090
    },
    {
      "epoch": 1.1394034343992874,
      "grad_norm": 0.43535515666007996,
      "learning_rate": 7.848489095972058e-06,
      "loss": 0.457,
      "step": 37091
    },
    {
      "epoch": 1.1394341535342365,
      "grad_norm": 0.45290708541870117,
      "learning_rate": 7.848017139129378e-06,
      "loss": 0.3824,
      "step": 37092
    },
    {
      "epoch": 1.1394648726691856,
      "grad_norm": 0.38377419114112854,
      "learning_rate": 7.847545187312805e-06,
      "loss": 0.5028,
      "step": 37093
    },
    {
      "epoch": 1.1394955918041347,
      "grad_norm": 0.42803582549095154,
      "learning_rate": 7.847073240523441e-06,
      "loss": 0.4638,
      "step": 37094
    },
    {
      "epoch": 1.1395263109390839,
      "grad_norm": 0.3979891240596771,
      "learning_rate": 7.846601298762388e-06,
      "loss": 0.4866,
      "step": 37095
    },
    {
      "epoch": 1.1395570300740332,
      "grad_norm": 0.37043556571006775,
      "learning_rate": 7.84612936203075e-06,
      "loss": 0.4812,
      "step": 37096
    },
    {
      "epoch": 1.1395877492089823,
      "grad_norm": 0.39043697714805603,
      "learning_rate": 7.845657430329625e-06,
      "loss": 0.4729,
      "step": 37097
    },
    {
      "epoch": 1.1396184683439314,
      "grad_norm": 0.3699720501899719,
      "learning_rate": 7.845185503660117e-06,
      "loss": 0.5034,
      "step": 37098
    },
    {
      "epoch": 1.1396491874788806,
      "grad_norm": 0.3981350362300873,
      "learning_rate": 7.84471358202333e-06,
      "loss": 0.563,
      "step": 37099
    },
    {
      "epoch": 1.1396799066138297,
      "grad_norm": 0.374110609292984,
      "learning_rate": 7.844241665420366e-06,
      "loss": 0.4923,
      "step": 37100
    },
    {
      "epoch": 1.139710625748779,
      "grad_norm": 0.3730166256427765,
      "learning_rate": 7.843769753852324e-06,
      "loss": 0.5039,
      "step": 37101
    },
    {
      "epoch": 1.1397413448837281,
      "grad_norm": 0.4314277172088623,
      "learning_rate": 7.84329784732031e-06,
      "loss": 0.5297,
      "step": 37102
    },
    {
      "epoch": 1.1397720640186773,
      "grad_norm": 0.3963576555252075,
      "learning_rate": 7.842825945825423e-06,
      "loss": 0.492,
      "step": 37103
    },
    {
      "epoch": 1.1398027831536264,
      "grad_norm": 0.388623982667923,
      "learning_rate": 7.842354049368767e-06,
      "loss": 0.4362,
      "step": 37104
    },
    {
      "epoch": 1.1398335022885755,
      "grad_norm": 0.3760610818862915,
      "learning_rate": 7.841882157951444e-06,
      "loss": 0.5078,
      "step": 37105
    },
    {
      "epoch": 1.1398642214235246,
      "grad_norm": 0.42016351222991943,
      "learning_rate": 7.841410271574557e-06,
      "loss": 0.5379,
      "step": 37106
    },
    {
      "epoch": 1.139894940558474,
      "grad_norm": 0.4216240346431732,
      "learning_rate": 7.840938390239206e-06,
      "loss": 0.5092,
      "step": 37107
    },
    {
      "epoch": 1.139925659693423,
      "grad_norm": 0.38701632618904114,
      "learning_rate": 7.840466513946495e-06,
      "loss": 0.486,
      "step": 37108
    },
    {
      "epoch": 1.1399563788283722,
      "grad_norm": 0.3566158413887024,
      "learning_rate": 7.839994642697524e-06,
      "loss": 0.3859,
      "step": 37109
    },
    {
      "epoch": 1.1399870979633213,
      "grad_norm": 0.4251480996608734,
      "learning_rate": 7.839522776493397e-06,
      "loss": 0.4609,
      "step": 37110
    },
    {
      "epoch": 1.1400178170982704,
      "grad_norm": 0.38081687688827515,
      "learning_rate": 7.839050915335215e-06,
      "loss": 0.4974,
      "step": 37111
    },
    {
      "epoch": 1.1400485362332198,
      "grad_norm": 0.39046844840049744,
      "learning_rate": 7.83857905922408e-06,
      "loss": 0.4748,
      "step": 37112
    },
    {
      "epoch": 1.140079255368169,
      "grad_norm": 0.3970136046409607,
      "learning_rate": 7.838107208161096e-06,
      "loss": 0.5018,
      "step": 37113
    },
    {
      "epoch": 1.140109974503118,
      "grad_norm": 0.3601641356945038,
      "learning_rate": 7.837635362147363e-06,
      "loss": 0.5121,
      "step": 37114
    },
    {
      "epoch": 1.1401406936380671,
      "grad_norm": 0.41070160269737244,
      "learning_rate": 7.837163521183984e-06,
      "loss": 0.4736,
      "step": 37115
    },
    {
      "epoch": 1.1401714127730163,
      "grad_norm": 0.35976505279541016,
      "learning_rate": 7.83669168527206e-06,
      "loss": 0.4772,
      "step": 37116
    },
    {
      "epoch": 1.1402021319079654,
      "grad_norm": 0.39797767996788025,
      "learning_rate": 7.836219854412696e-06,
      "loss": 0.5254,
      "step": 37117
    },
    {
      "epoch": 1.1402328510429147,
      "grad_norm": 0.4183429479598999,
      "learning_rate": 7.835748028606988e-06,
      "loss": 0.4868,
      "step": 37118
    },
    {
      "epoch": 1.1402635701778638,
      "grad_norm": 0.4168464243412018,
      "learning_rate": 7.835276207856046e-06,
      "loss": 0.495,
      "step": 37119
    },
    {
      "epoch": 1.140294289312813,
      "grad_norm": 0.3783096969127655,
      "learning_rate": 7.834804392160961e-06,
      "loss": 0.4527,
      "step": 37120
    },
    {
      "epoch": 1.140325008447762,
      "grad_norm": 0.3713330030441284,
      "learning_rate": 7.83433258152285e-06,
      "loss": 0.4636,
      "step": 37121
    },
    {
      "epoch": 1.1403557275827112,
      "grad_norm": 0.38201993703842163,
      "learning_rate": 7.833860775942799e-06,
      "loss": 0.543,
      "step": 37122
    },
    {
      "epoch": 1.1403864467176605,
      "grad_norm": 0.35051992535591125,
      "learning_rate": 7.833388975421923e-06,
      "loss": 0.4819,
      "step": 37123
    },
    {
      "epoch": 1.1404171658526097,
      "grad_norm": 0.36456969380378723,
      "learning_rate": 7.832917179961315e-06,
      "loss": 0.4857,
      "step": 37124
    },
    {
      "epoch": 1.1404478849875588,
      "grad_norm": 0.3765043020248413,
      "learning_rate": 7.832445389562082e-06,
      "loss": 0.4699,
      "step": 37125
    },
    {
      "epoch": 1.140478604122508,
      "grad_norm": 0.4254309833049774,
      "learning_rate": 7.831973604225322e-06,
      "loss": 0.4875,
      "step": 37126
    },
    {
      "epoch": 1.140509323257457,
      "grad_norm": 0.42341938614845276,
      "learning_rate": 7.831501823952142e-06,
      "loss": 0.5341,
      "step": 37127
    },
    {
      "epoch": 1.1405400423924061,
      "grad_norm": 0.36464786529541016,
      "learning_rate": 7.831030048743638e-06,
      "loss": 0.5299,
      "step": 37128
    },
    {
      "epoch": 1.1405707615273555,
      "grad_norm": 0.3714972138404846,
      "learning_rate": 7.830558278600918e-06,
      "loss": 0.5683,
      "step": 37129
    },
    {
      "epoch": 1.1406014806623046,
      "grad_norm": 0.3478257954120636,
      "learning_rate": 7.830086513525078e-06,
      "loss": 0.4149,
      "step": 37130
    },
    {
      "epoch": 1.1406321997972537,
      "grad_norm": 0.3863089680671692,
      "learning_rate": 7.82961475351722e-06,
      "loss": 0.3732,
      "step": 37131
    },
    {
      "epoch": 1.1406629189322028,
      "grad_norm": 0.44210025668144226,
      "learning_rate": 7.829142998578454e-06,
      "loss": 0.508,
      "step": 37132
    },
    {
      "epoch": 1.140693638067152,
      "grad_norm": 0.39820563793182373,
      "learning_rate": 7.828671248709872e-06,
      "loss": 0.5176,
      "step": 37133
    },
    {
      "epoch": 1.1407243572021013,
      "grad_norm": 0.40132835507392883,
      "learning_rate": 7.828199503912582e-06,
      "loss": 0.5057,
      "step": 37134
    },
    {
      "epoch": 1.1407550763370504,
      "grad_norm": 0.41126301884651184,
      "learning_rate": 7.827727764187682e-06,
      "loss": 0.4987,
      "step": 37135
    },
    {
      "epoch": 1.1407857954719995,
      "grad_norm": 0.4054825007915497,
      "learning_rate": 7.82725602953628e-06,
      "loss": 0.5533,
      "step": 37136
    },
    {
      "epoch": 1.1408165146069487,
      "grad_norm": 0.4261172413825989,
      "learning_rate": 7.826784299959468e-06,
      "loss": 0.467,
      "step": 37137
    },
    {
      "epoch": 1.1408472337418978,
      "grad_norm": 0.40154463052749634,
      "learning_rate": 7.826312575458356e-06,
      "loss": 0.4444,
      "step": 37138
    },
    {
      "epoch": 1.140877952876847,
      "grad_norm": 0.40598928928375244,
      "learning_rate": 7.825840856034041e-06,
      "loss": 0.594,
      "step": 37139
    },
    {
      "epoch": 1.1409086720117962,
      "grad_norm": 0.38290977478027344,
      "learning_rate": 7.82536914168763e-06,
      "loss": 0.4712,
      "step": 37140
    },
    {
      "epoch": 1.1409393911467454,
      "grad_norm": 0.38710078597068787,
      "learning_rate": 7.824897432420217e-06,
      "loss": 0.5329,
      "step": 37141
    },
    {
      "epoch": 1.1409701102816945,
      "grad_norm": 0.4364968538284302,
      "learning_rate": 7.82442572823291e-06,
      "loss": 0.5174,
      "step": 37142
    },
    {
      "epoch": 1.1410008294166436,
      "grad_norm": 0.43606317043304443,
      "learning_rate": 7.823954029126808e-06,
      "loss": 0.4441,
      "step": 37143
    },
    {
      "epoch": 1.1410315485515927,
      "grad_norm": 0.38487717509269714,
      "learning_rate": 7.823482335103015e-06,
      "loss": 0.4526,
      "step": 37144
    },
    {
      "epoch": 1.141062267686542,
      "grad_norm": 0.4575599133968353,
      "learning_rate": 7.823010646162628e-06,
      "loss": 0.4391,
      "step": 37145
    },
    {
      "epoch": 1.1410929868214912,
      "grad_norm": 0.3915445804595947,
      "learning_rate": 7.822538962306756e-06,
      "loss": 0.5279,
      "step": 37146
    },
    {
      "epoch": 1.1411237059564403,
      "grad_norm": 0.3854977786540985,
      "learning_rate": 7.82206728353649e-06,
      "loss": 0.4681,
      "step": 37147
    },
    {
      "epoch": 1.1411544250913894,
      "grad_norm": 0.5184025764465332,
      "learning_rate": 7.821595609852946e-06,
      "loss": 0.5537,
      "step": 37148
    },
    {
      "epoch": 1.1411851442263385,
      "grad_norm": 0.4266902506351471,
      "learning_rate": 7.821123941257209e-06,
      "loss": 0.5358,
      "step": 37149
    },
    {
      "epoch": 1.1412158633612877,
      "grad_norm": 0.38285279273986816,
      "learning_rate": 7.820652277750394e-06,
      "loss": 0.557,
      "step": 37150
    },
    {
      "epoch": 1.1412465824962368,
      "grad_norm": 0.43444105982780457,
      "learning_rate": 7.820180619333597e-06,
      "loss": 0.4593,
      "step": 37151
    },
    {
      "epoch": 1.1412773016311861,
      "grad_norm": 0.4125456213951111,
      "learning_rate": 7.81970896600792e-06,
      "loss": 0.5187,
      "step": 37152
    },
    {
      "epoch": 1.1413080207661352,
      "grad_norm": 0.4097421169281006,
      "learning_rate": 7.819237317774469e-06,
      "loss": 0.3915,
      "step": 37153
    },
    {
      "epoch": 1.1413387399010844,
      "grad_norm": 0.35915663838386536,
      "learning_rate": 7.818765674634334e-06,
      "loss": 0.5269,
      "step": 37154
    },
    {
      "epoch": 1.1413694590360335,
      "grad_norm": 0.37554794549942017,
      "learning_rate": 7.818294036588631e-06,
      "loss": 0.5154,
      "step": 37155
    },
    {
      "epoch": 1.1414001781709828,
      "grad_norm": 0.3640054762363434,
      "learning_rate": 7.81782240363845e-06,
      "loss": 0.4679,
      "step": 37156
    },
    {
      "epoch": 1.141430897305932,
      "grad_norm": 0.40999284386634827,
      "learning_rate": 7.817350775784902e-06,
      "loss": 0.5207,
      "step": 37157
    },
    {
      "epoch": 1.141461616440881,
      "grad_norm": 0.37298446893692017,
      "learning_rate": 7.81687915302908e-06,
      "loss": 0.4486,
      "step": 37158
    },
    {
      "epoch": 1.1414923355758302,
      "grad_norm": 0.39098310470581055,
      "learning_rate": 7.816407535372092e-06,
      "loss": 0.4869,
      "step": 37159
    },
    {
      "epoch": 1.1415230547107793,
      "grad_norm": 0.40122854709625244,
      "learning_rate": 7.815935922815032e-06,
      "loss": 0.4821,
      "step": 37160
    },
    {
      "epoch": 1.1415537738457284,
      "grad_norm": 0.3526706397533417,
      "learning_rate": 7.815464315359011e-06,
      "loss": 0.5015,
      "step": 37161
    },
    {
      "epoch": 1.1415844929806775,
      "grad_norm": 0.40282246470451355,
      "learning_rate": 7.814992713005124e-06,
      "loss": 0.4289,
      "step": 37162
    },
    {
      "epoch": 1.1416152121156269,
      "grad_norm": 0.4041963517665863,
      "learning_rate": 7.814521115754473e-06,
      "loss": 0.4848,
      "step": 37163
    },
    {
      "epoch": 1.141645931250576,
      "grad_norm": 0.5504847764968872,
      "learning_rate": 7.81404952360816e-06,
      "loss": 0.5347,
      "step": 37164
    },
    {
      "epoch": 1.1416766503855251,
      "grad_norm": 0.4489118456840515,
      "learning_rate": 7.813577936567289e-06,
      "loss": 0.4799,
      "step": 37165
    },
    {
      "epoch": 1.1417073695204742,
      "grad_norm": 0.46614477038383484,
      "learning_rate": 7.813106354632957e-06,
      "loss": 0.4827,
      "step": 37166
    },
    {
      "epoch": 1.1417380886554234,
      "grad_norm": 0.4098764657974243,
      "learning_rate": 7.81263477780627e-06,
      "loss": 0.5203,
      "step": 37167
    },
    {
      "epoch": 1.1417688077903727,
      "grad_norm": 0.39597055315971375,
      "learning_rate": 7.812163206088329e-06,
      "loss": 0.5485,
      "step": 37168
    },
    {
      "epoch": 1.1417995269253218,
      "grad_norm": 0.41299399733543396,
      "learning_rate": 7.81169163948023e-06,
      "loss": 0.3778,
      "step": 37169
    },
    {
      "epoch": 1.141830246060271,
      "grad_norm": 0.37823933362960815,
      "learning_rate": 7.81122007798308e-06,
      "loss": 0.4904,
      "step": 37170
    },
    {
      "epoch": 1.14186096519522,
      "grad_norm": 0.3668566346168518,
      "learning_rate": 7.810748521597975e-06,
      "loss": 0.5218,
      "step": 37171
    },
    {
      "epoch": 1.1418916843301692,
      "grad_norm": 0.40934890508651733,
      "learning_rate": 7.810276970326024e-06,
      "loss": 0.4876,
      "step": 37172
    },
    {
      "epoch": 1.1419224034651183,
      "grad_norm": 0.3535430431365967,
      "learning_rate": 7.809805424168321e-06,
      "loss": 0.4381,
      "step": 37173
    },
    {
      "epoch": 1.1419531226000676,
      "grad_norm": 0.3764670491218567,
      "learning_rate": 7.809333883125973e-06,
      "loss": 0.4405,
      "step": 37174
    },
    {
      "epoch": 1.1419838417350168,
      "grad_norm": 0.40342676639556885,
      "learning_rate": 7.808862347200077e-06,
      "loss": 0.5333,
      "step": 37175
    },
    {
      "epoch": 1.142014560869966,
      "grad_norm": 0.42883050441741943,
      "learning_rate": 7.80839081639174e-06,
      "loss": 0.5072,
      "step": 37176
    },
    {
      "epoch": 1.142045280004915,
      "grad_norm": 0.44548869132995605,
      "learning_rate": 7.807919290702054e-06,
      "loss": 0.5207,
      "step": 37177
    },
    {
      "epoch": 1.1420759991398641,
      "grad_norm": 0.45278534293174744,
      "learning_rate": 7.807447770132128e-06,
      "loss": 0.5011,
      "step": 37178
    },
    {
      "epoch": 1.1421067182748135,
      "grad_norm": 0.37754955887794495,
      "learning_rate": 7.806976254683059e-06,
      "loss": 0.4074,
      "step": 37179
    },
    {
      "epoch": 1.1421374374097626,
      "grad_norm": 0.3563055396080017,
      "learning_rate": 7.806504744355955e-06,
      "loss": 0.4173,
      "step": 37180
    },
    {
      "epoch": 1.1421681565447117,
      "grad_norm": 0.4230959415435791,
      "learning_rate": 7.806033239151905e-06,
      "loss": 0.5924,
      "step": 37181
    },
    {
      "epoch": 1.1421988756796608,
      "grad_norm": 0.3878747820854187,
      "learning_rate": 7.805561739072025e-06,
      "loss": 0.4939,
      "step": 37182
    },
    {
      "epoch": 1.14222959481461,
      "grad_norm": 0.3711695075035095,
      "learning_rate": 7.805090244117403e-06,
      "loss": 0.5879,
      "step": 37183
    },
    {
      "epoch": 1.142260313949559,
      "grad_norm": 0.3866095244884491,
      "learning_rate": 7.804618754289152e-06,
      "loss": 0.4408,
      "step": 37184
    },
    {
      "epoch": 1.1422910330845084,
      "grad_norm": 0.3789484202861786,
      "learning_rate": 7.80414726958836e-06,
      "loss": 0.4971,
      "step": 37185
    },
    {
      "epoch": 1.1423217522194575,
      "grad_norm": 0.3768121004104614,
      "learning_rate": 7.803675790016137e-06,
      "loss": 0.548,
      "step": 37186
    },
    {
      "epoch": 1.1423524713544067,
      "grad_norm": 0.39340826869010925,
      "learning_rate": 7.803204315573588e-06,
      "loss": 0.4565,
      "step": 37187
    },
    {
      "epoch": 1.1423831904893558,
      "grad_norm": 0.39720436930656433,
      "learning_rate": 7.802732846261802e-06,
      "loss": 0.4446,
      "step": 37188
    },
    {
      "epoch": 1.142413909624305,
      "grad_norm": 0.38970261812210083,
      "learning_rate": 7.802261382081893e-06,
      "loss": 0.5131,
      "step": 37189
    },
    {
      "epoch": 1.1424446287592542,
      "grad_norm": 0.3470967710018158,
      "learning_rate": 7.80178992303495e-06,
      "loss": 0.5331,
      "step": 37190
    },
    {
      "epoch": 1.1424753478942034,
      "grad_norm": 0.4148749113082886,
      "learning_rate": 7.801318469122088e-06,
      "loss": 0.4939,
      "step": 37191
    },
    {
      "epoch": 1.1425060670291525,
      "grad_norm": 0.4516198933124542,
      "learning_rate": 7.800847020344392e-06,
      "loss": 0.5394,
      "step": 37192
    },
    {
      "epoch": 1.1425367861641016,
      "grad_norm": 0.5394443273544312,
      "learning_rate": 7.800375576702979e-06,
      "loss": 0.4576,
      "step": 37193
    },
    {
      "epoch": 1.1425675052990507,
      "grad_norm": 0.3976479172706604,
      "learning_rate": 7.799904138198937e-06,
      "loss": 0.4774,
      "step": 37194
    },
    {
      "epoch": 1.1425982244339998,
      "grad_norm": 0.4750392436981201,
      "learning_rate": 7.799432704833374e-06,
      "loss": 0.5231,
      "step": 37195
    },
    {
      "epoch": 1.1426289435689492,
      "grad_norm": 0.3568459451198578,
      "learning_rate": 7.798961276607389e-06,
      "loss": 0.4794,
      "step": 37196
    },
    {
      "epoch": 1.1426596627038983,
      "grad_norm": 0.39476022124290466,
      "learning_rate": 7.798489853522085e-06,
      "loss": 0.5137,
      "step": 37197
    },
    {
      "epoch": 1.1426903818388474,
      "grad_norm": 0.443489670753479,
      "learning_rate": 7.79801843557856e-06,
      "loss": 0.3784,
      "step": 37198
    },
    {
      "epoch": 1.1427211009737965,
      "grad_norm": 0.41740915179252625,
      "learning_rate": 7.79754702277792e-06,
      "loss": 0.501,
      "step": 37199
    },
    {
      "epoch": 1.1427518201087457,
      "grad_norm": 0.38630273938179016,
      "learning_rate": 7.797075615121259e-06,
      "loss": 0.4958,
      "step": 37200
    },
    {
      "epoch": 1.142782539243695,
      "grad_norm": 0.37735238671302795,
      "learning_rate": 7.796604212609685e-06,
      "loss": 0.5031,
      "step": 37201
    },
    {
      "epoch": 1.1428132583786441,
      "grad_norm": 0.3919088542461395,
      "learning_rate": 7.796132815244291e-06,
      "loss": 0.4638,
      "step": 37202
    },
    {
      "epoch": 1.1428439775135932,
      "grad_norm": 0.4284490644931793,
      "learning_rate": 7.795661423026184e-06,
      "loss": 0.4741,
      "step": 37203
    },
    {
      "epoch": 1.1428746966485424,
      "grad_norm": 0.36698344349861145,
      "learning_rate": 7.795190035956468e-06,
      "loss": 0.4122,
      "step": 37204
    },
    {
      "epoch": 1.1429054157834915,
      "grad_norm": 0.41251957416534424,
      "learning_rate": 7.794718654036235e-06,
      "loss": 0.4818,
      "step": 37205
    },
    {
      "epoch": 1.1429361349184406,
      "grad_norm": 0.4009343683719635,
      "learning_rate": 7.794247277266595e-06,
      "loss": 0.5374,
      "step": 37206
    },
    {
      "epoch": 1.14296685405339,
      "grad_norm": 0.3837367296218872,
      "learning_rate": 7.79377590564864e-06,
      "loss": 0.4589,
      "step": 37207
    },
    {
      "epoch": 1.142997573188339,
      "grad_norm": 0.38941365480422974,
      "learning_rate": 7.79330453918348e-06,
      "loss": 0.4438,
      "step": 37208
    },
    {
      "epoch": 1.1430282923232882,
      "grad_norm": 0.3990972936153412,
      "learning_rate": 7.792833177872207e-06,
      "loss": 0.4934,
      "step": 37209
    },
    {
      "epoch": 1.1430590114582373,
      "grad_norm": 0.3557084798812866,
      "learning_rate": 7.792361821715929e-06,
      "loss": 0.4424,
      "step": 37210
    },
    {
      "epoch": 1.1430897305931864,
      "grad_norm": 0.38319042325019836,
      "learning_rate": 7.791890470715743e-06,
      "loss": 0.5255,
      "step": 37211
    },
    {
      "epoch": 1.1431204497281358,
      "grad_norm": 0.4074711501598358,
      "learning_rate": 7.791419124872751e-06,
      "loss": 0.4408,
      "step": 37212
    },
    {
      "epoch": 1.1431511688630849,
      "grad_norm": 0.38255438208580017,
      "learning_rate": 7.790947784188055e-06,
      "loss": 0.5085,
      "step": 37213
    },
    {
      "epoch": 1.143181887998034,
      "grad_norm": 0.5002043843269348,
      "learning_rate": 7.790476448662754e-06,
      "loss": 0.6148,
      "step": 37214
    },
    {
      "epoch": 1.1432126071329831,
      "grad_norm": 0.39238089323043823,
      "learning_rate": 7.79000511829795e-06,
      "loss": 0.4691,
      "step": 37215
    },
    {
      "epoch": 1.1432433262679322,
      "grad_norm": 0.40434154868125916,
      "learning_rate": 7.789533793094746e-06,
      "loss": 0.5043,
      "step": 37216
    },
    {
      "epoch": 1.1432740454028814,
      "grad_norm": 0.35963383316993713,
      "learning_rate": 7.789062473054232e-06,
      "loss": 0.3934,
      "step": 37217
    },
    {
      "epoch": 1.1433047645378307,
      "grad_norm": 0.4363662004470825,
      "learning_rate": 7.788591158177527e-06,
      "loss": 0.4912,
      "step": 37218
    },
    {
      "epoch": 1.1433354836727798,
      "grad_norm": 0.39894500374794006,
      "learning_rate": 7.788119848465713e-06,
      "loss": 0.4956,
      "step": 37219
    },
    {
      "epoch": 1.143366202807729,
      "grad_norm": 0.4511984884738922,
      "learning_rate": 7.787648543919906e-06,
      "loss": 0.4753,
      "step": 37220
    },
    {
      "epoch": 1.143396921942678,
      "grad_norm": 0.37488484382629395,
      "learning_rate": 7.787177244541198e-06,
      "loss": 0.4483,
      "step": 37221
    },
    {
      "epoch": 1.1434276410776272,
      "grad_norm": 0.40855082869529724,
      "learning_rate": 7.786705950330689e-06,
      "loss": 0.4884,
      "step": 37222
    },
    {
      "epoch": 1.1434583602125765,
      "grad_norm": 0.4012760818004608,
      "learning_rate": 7.786234661289489e-06,
      "loss": 0.4894,
      "step": 37223
    },
    {
      "epoch": 1.1434890793475256,
      "grad_norm": 0.44407597184181213,
      "learning_rate": 7.785763377418686e-06,
      "loss": 0.475,
      "step": 37224
    },
    {
      "epoch": 1.1435197984824748,
      "grad_norm": 0.40465936064720154,
      "learning_rate": 7.785292098719394e-06,
      "loss": 0.4672,
      "step": 37225
    },
    {
      "epoch": 1.1435505176174239,
      "grad_norm": 0.3939778804779053,
      "learning_rate": 7.784820825192701e-06,
      "loss": 0.5312,
      "step": 37226
    },
    {
      "epoch": 1.143581236752373,
      "grad_norm": 0.4650048613548279,
      "learning_rate": 7.784349556839719e-06,
      "loss": 0.548,
      "step": 37227
    },
    {
      "epoch": 1.1436119558873221,
      "grad_norm": 0.399558961391449,
      "learning_rate": 7.783878293661539e-06,
      "loss": 0.4215,
      "step": 37228
    },
    {
      "epoch": 1.1436426750222715,
      "grad_norm": 0.37747129797935486,
      "learning_rate": 7.783407035659269e-06,
      "loss": 0.4498,
      "step": 37229
    },
    {
      "epoch": 1.1436733941572206,
      "grad_norm": 0.4406804144382477,
      "learning_rate": 7.782935782834003e-06,
      "loss": 0.4778,
      "step": 37230
    },
    {
      "epoch": 1.1437041132921697,
      "grad_norm": 0.37218111753463745,
      "learning_rate": 7.782464535186848e-06,
      "loss": 0.4544,
      "step": 37231
    },
    {
      "epoch": 1.1437348324271188,
      "grad_norm": 0.3995908200740814,
      "learning_rate": 7.781993292718903e-06,
      "loss": 0.5367,
      "step": 37232
    },
    {
      "epoch": 1.143765551562068,
      "grad_norm": 0.40746399760246277,
      "learning_rate": 7.781522055431266e-06,
      "loss": 0.5214,
      "step": 37233
    },
    {
      "epoch": 1.1437962706970173,
      "grad_norm": 0.39681002497673035,
      "learning_rate": 7.781050823325038e-06,
      "loss": 0.4421,
      "step": 37234
    },
    {
      "epoch": 1.1438269898319664,
      "grad_norm": 0.3721450865268707,
      "learning_rate": 7.780579596401323e-06,
      "loss": 0.4551,
      "step": 37235
    },
    {
      "epoch": 1.1438577089669155,
      "grad_norm": 0.4144189953804016,
      "learning_rate": 7.780108374661218e-06,
      "loss": 0.5194,
      "step": 37236
    },
    {
      "epoch": 1.1438884281018646,
      "grad_norm": 0.48055022954940796,
      "learning_rate": 7.779637158105825e-06,
      "loss": 0.4456,
      "step": 37237
    },
    {
      "epoch": 1.1439191472368138,
      "grad_norm": 0.4009672999382019,
      "learning_rate": 7.779165946736244e-06,
      "loss": 0.3831,
      "step": 37238
    },
    {
      "epoch": 1.1439498663717629,
      "grad_norm": 0.39080044627189636,
      "learning_rate": 7.77869474055358e-06,
      "loss": 0.4801,
      "step": 37239
    },
    {
      "epoch": 1.1439805855067122,
      "grad_norm": 0.38208088278770447,
      "learning_rate": 7.778223539558924e-06,
      "loss": 0.5243,
      "step": 37240
    },
    {
      "epoch": 1.1440113046416613,
      "grad_norm": 0.37841787934303284,
      "learning_rate": 7.777752343753384e-06,
      "loss": 0.5036,
      "step": 37241
    },
    {
      "epoch": 1.1440420237766105,
      "grad_norm": 0.3687121868133545,
      "learning_rate": 7.77728115313806e-06,
      "loss": 0.5129,
      "step": 37242
    },
    {
      "epoch": 1.1440727429115596,
      "grad_norm": 0.44407710433006287,
      "learning_rate": 7.776809967714049e-06,
      "loss": 0.5006,
      "step": 37243
    },
    {
      "epoch": 1.1441034620465087,
      "grad_norm": 0.3798134922981262,
      "learning_rate": 7.776338787482456e-06,
      "loss": 0.4721,
      "step": 37244
    },
    {
      "epoch": 1.144134181181458,
      "grad_norm": 0.43068256974220276,
      "learning_rate": 7.775867612444377e-06,
      "loss": 0.5231,
      "step": 37245
    },
    {
      "epoch": 1.1441649003164072,
      "grad_norm": 0.3724113404750824,
      "learning_rate": 7.775396442600916e-06,
      "loss": 0.3981,
      "step": 37246
    },
    {
      "epoch": 1.1441956194513563,
      "grad_norm": 0.49549195170402527,
      "learning_rate": 7.774925277953171e-06,
      "loss": 0.4444,
      "step": 37247
    },
    {
      "epoch": 1.1442263385863054,
      "grad_norm": 0.4323045313358307,
      "learning_rate": 7.774454118502244e-06,
      "loss": 0.5489,
      "step": 37248
    },
    {
      "epoch": 1.1442570577212545,
      "grad_norm": 0.4287247955799103,
      "learning_rate": 7.773982964249234e-06,
      "loss": 0.4905,
      "step": 37249
    },
    {
      "epoch": 1.1442877768562036,
      "grad_norm": 0.4289187788963318,
      "learning_rate": 7.773511815195247e-06,
      "loss": 0.4964,
      "step": 37250
    },
    {
      "epoch": 1.144318495991153,
      "grad_norm": 0.3822726607322693,
      "learning_rate": 7.773040671341371e-06,
      "loss": 0.4928,
      "step": 37251
    },
    {
      "epoch": 1.144349215126102,
      "grad_norm": 0.39737823605537415,
      "learning_rate": 7.77256953268872e-06,
      "loss": 0.5352,
      "step": 37252
    },
    {
      "epoch": 1.1443799342610512,
      "grad_norm": 0.41447797417640686,
      "learning_rate": 7.772098399238384e-06,
      "loss": 0.4877,
      "step": 37253
    },
    {
      "epoch": 1.1444106533960003,
      "grad_norm": 0.4448695778846741,
      "learning_rate": 7.771627270991472e-06,
      "loss": 0.5487,
      "step": 37254
    },
    {
      "epoch": 1.1444413725309495,
      "grad_norm": 0.4009229838848114,
      "learning_rate": 7.771156147949076e-06,
      "loss": 0.4331,
      "step": 37255
    },
    {
      "epoch": 1.1444720916658988,
      "grad_norm": 0.4304632246494293,
      "learning_rate": 7.770685030112305e-06,
      "loss": 0.472,
      "step": 37256
    },
    {
      "epoch": 1.144502810800848,
      "grad_norm": 0.38177260756492615,
      "learning_rate": 7.77021391748225e-06,
      "loss": 0.4806,
      "step": 37257
    },
    {
      "epoch": 1.144533529935797,
      "grad_norm": 0.40129339694976807,
      "learning_rate": 7.769742810060016e-06,
      "loss": 0.5277,
      "step": 37258
    },
    {
      "epoch": 1.1445642490707462,
      "grad_norm": 0.4039367735385895,
      "learning_rate": 7.769271707846709e-06,
      "loss": 0.5346,
      "step": 37259
    },
    {
      "epoch": 1.1445949682056953,
      "grad_norm": 0.3927523195743561,
      "learning_rate": 7.768800610843416e-06,
      "loss": 0.4851,
      "step": 37260
    },
    {
      "epoch": 1.1446256873406444,
      "grad_norm": 0.3793134093284607,
      "learning_rate": 7.768329519051254e-06,
      "loss": 0.4336,
      "step": 37261
    },
    {
      "epoch": 1.1446564064755935,
      "grad_norm": 0.4231044352054596,
      "learning_rate": 7.767858432471308e-06,
      "loss": 0.468,
      "step": 37262
    },
    {
      "epoch": 1.1446871256105429,
      "grad_norm": 0.35724538564682007,
      "learning_rate": 7.767387351104686e-06,
      "loss": 0.4154,
      "step": 37263
    },
    {
      "epoch": 1.144717844745492,
      "grad_norm": 0.3891391456127167,
      "learning_rate": 7.766916274952487e-06,
      "loss": 0.5005,
      "step": 37264
    },
    {
      "epoch": 1.144748563880441,
      "grad_norm": 0.3928762376308441,
      "learning_rate": 7.766445204015812e-06,
      "loss": 0.4688,
      "step": 37265
    },
    {
      "epoch": 1.1447792830153902,
      "grad_norm": 0.3572370409965515,
      "learning_rate": 7.76597413829576e-06,
      "loss": 0.5602,
      "step": 37266
    },
    {
      "epoch": 1.1448100021503396,
      "grad_norm": 0.37525618076324463,
      "learning_rate": 7.76550307779343e-06,
      "loss": 0.5194,
      "step": 37267
    },
    {
      "epoch": 1.1448407212852887,
      "grad_norm": 0.40490683913230896,
      "learning_rate": 7.765032022509925e-06,
      "loss": 0.504,
      "step": 37268
    },
    {
      "epoch": 1.1448714404202378,
      "grad_norm": 0.42460644245147705,
      "learning_rate": 7.764560972446342e-06,
      "loss": 0.5191,
      "step": 37269
    },
    {
      "epoch": 1.144902159555187,
      "grad_norm": 0.44000446796417236,
      "learning_rate": 7.764089927603784e-06,
      "loss": 0.5388,
      "step": 37270
    },
    {
      "epoch": 1.144932878690136,
      "grad_norm": 0.3975358009338379,
      "learning_rate": 7.76361888798335e-06,
      "loss": 0.5104,
      "step": 37271
    },
    {
      "epoch": 1.1449635978250852,
      "grad_norm": 0.39690136909484863,
      "learning_rate": 7.76314785358614e-06,
      "loss": 0.4682,
      "step": 37272
    },
    {
      "epoch": 1.1449943169600343,
      "grad_norm": 0.41019001603126526,
      "learning_rate": 7.762676824413256e-06,
      "loss": 0.448,
      "step": 37273
    },
    {
      "epoch": 1.1450250360949836,
      "grad_norm": 0.36227545142173767,
      "learning_rate": 7.762205800465793e-06,
      "loss": 0.4147,
      "step": 37274
    },
    {
      "epoch": 1.1450557552299327,
      "grad_norm": 0.45474618673324585,
      "learning_rate": 7.76173478174486e-06,
      "loss": 0.4118,
      "step": 37275
    },
    {
      "epoch": 1.1450864743648819,
      "grad_norm": 0.38649067282676697,
      "learning_rate": 7.761263768251548e-06,
      "loss": 0.4953,
      "step": 37276
    },
    {
      "epoch": 1.145117193499831,
      "grad_norm": 0.37866872549057007,
      "learning_rate": 7.76079275998696e-06,
      "loss": 0.4409,
      "step": 37277
    },
    {
      "epoch": 1.1451479126347803,
      "grad_norm": 0.3900689482688904,
      "learning_rate": 7.7603217569522e-06,
      "loss": 0.4232,
      "step": 37278
    },
    {
      "epoch": 1.1451786317697294,
      "grad_norm": 0.3789790868759155,
      "learning_rate": 7.759850759148361e-06,
      "loss": 0.3971,
      "step": 37279
    },
    {
      "epoch": 1.1452093509046786,
      "grad_norm": 0.4174889028072357,
      "learning_rate": 7.759379766576552e-06,
      "loss": 0.5375,
      "step": 37280
    },
    {
      "epoch": 1.1452400700396277,
      "grad_norm": 0.36196258664131165,
      "learning_rate": 7.758908779237863e-06,
      "loss": 0.4325,
      "step": 37281
    },
    {
      "epoch": 1.1452707891745768,
      "grad_norm": 0.3948162794113159,
      "learning_rate": 7.758437797133404e-06,
      "loss": 0.5603,
      "step": 37282
    },
    {
      "epoch": 1.145301508309526,
      "grad_norm": 0.39200082421302795,
      "learning_rate": 7.757966820264266e-06,
      "loss": 0.4412,
      "step": 37283
    },
    {
      "epoch": 1.145332227444475,
      "grad_norm": 0.39344850182533264,
      "learning_rate": 7.757495848631555e-06,
      "loss": 0.4967,
      "step": 37284
    },
    {
      "epoch": 1.1453629465794244,
      "grad_norm": 0.4472986161708832,
      "learning_rate": 7.757024882236368e-06,
      "loss": 0.4333,
      "step": 37285
    },
    {
      "epoch": 1.1453936657143735,
      "grad_norm": 0.40845853090286255,
      "learning_rate": 7.75655392107981e-06,
      "loss": 0.386,
      "step": 37286
    },
    {
      "epoch": 1.1454243848493226,
      "grad_norm": 0.4133579730987549,
      "learning_rate": 7.756082965162972e-06,
      "loss": 0.5359,
      "step": 37287
    },
    {
      "epoch": 1.1454551039842717,
      "grad_norm": 0.5904930830001831,
      "learning_rate": 7.755612014486962e-06,
      "loss": 0.4176,
      "step": 37288
    },
    {
      "epoch": 1.1454858231192209,
      "grad_norm": 0.38059353828430176,
      "learning_rate": 7.755141069052872e-06,
      "loss": 0.431,
      "step": 37289
    },
    {
      "epoch": 1.1455165422541702,
      "grad_norm": 0.35354363918304443,
      "learning_rate": 7.754670128861814e-06,
      "loss": 0.4742,
      "step": 37290
    },
    {
      "epoch": 1.1455472613891193,
      "grad_norm": 0.4480586647987366,
      "learning_rate": 7.754199193914876e-06,
      "loss": 0.4946,
      "step": 37291
    },
    {
      "epoch": 1.1455779805240685,
      "grad_norm": 0.41818276047706604,
      "learning_rate": 7.753728264213164e-06,
      "loss": 0.5228,
      "step": 37292
    },
    {
      "epoch": 1.1456086996590176,
      "grad_norm": 0.4650334417819977,
      "learning_rate": 7.753257339757776e-06,
      "loss": 0.4815,
      "step": 37293
    },
    {
      "epoch": 1.1456394187939667,
      "grad_norm": 0.43085652589797974,
      "learning_rate": 7.752786420549813e-06,
      "loss": 0.5506,
      "step": 37294
    },
    {
      "epoch": 1.1456701379289158,
      "grad_norm": 0.422717809677124,
      "learning_rate": 7.752315506590375e-06,
      "loss": 0.4833,
      "step": 37295
    },
    {
      "epoch": 1.1457008570638652,
      "grad_norm": 0.5465220808982849,
      "learning_rate": 7.751844597880555e-06,
      "loss": 0.5545,
      "step": 37296
    },
    {
      "epoch": 1.1457315761988143,
      "grad_norm": 0.37932199239730835,
      "learning_rate": 7.751373694421469e-06,
      "loss": 0.4211,
      "step": 37297
    },
    {
      "epoch": 1.1457622953337634,
      "grad_norm": 0.37443482875823975,
      "learning_rate": 7.7509027962142e-06,
      "loss": 0.5039,
      "step": 37298
    },
    {
      "epoch": 1.1457930144687125,
      "grad_norm": 0.4112727642059326,
      "learning_rate": 7.750431903259858e-06,
      "loss": 0.5036,
      "step": 37299
    },
    {
      "epoch": 1.1458237336036616,
      "grad_norm": 0.395747572183609,
      "learning_rate": 7.749961015559536e-06,
      "loss": 0.4977,
      "step": 37300
    },
    {
      "epoch": 1.145854452738611,
      "grad_norm": 0.37890923023223877,
      "learning_rate": 7.74949013311434e-06,
      "loss": 0.468,
      "step": 37301
    },
    {
      "epoch": 1.14588517187356,
      "grad_norm": 0.39167550206184387,
      "learning_rate": 7.749019255925366e-06,
      "loss": 0.5169,
      "step": 37302
    },
    {
      "epoch": 1.1459158910085092,
      "grad_norm": 0.37333187460899353,
      "learning_rate": 7.748548383993715e-06,
      "loss": 0.4571,
      "step": 37303
    },
    {
      "epoch": 1.1459466101434583,
      "grad_norm": 0.4376128315925598,
      "learning_rate": 7.748077517320485e-06,
      "loss": 0.4756,
      "step": 37304
    },
    {
      "epoch": 1.1459773292784075,
      "grad_norm": 0.4511782228946686,
      "learning_rate": 7.747606655906778e-06,
      "loss": 0.4671,
      "step": 37305
    },
    {
      "epoch": 1.1460080484133566,
      "grad_norm": 0.384975790977478,
      "learning_rate": 7.747135799753694e-06,
      "loss": 0.4443,
      "step": 37306
    },
    {
      "epoch": 1.146038767548306,
      "grad_norm": 0.38153672218322754,
      "learning_rate": 7.746664948862331e-06,
      "loss": 0.5047,
      "step": 37307
    },
    {
      "epoch": 1.146069486683255,
      "grad_norm": 0.42546162009239197,
      "learning_rate": 7.746194103233788e-06,
      "loss": 0.4844,
      "step": 37308
    },
    {
      "epoch": 1.1461002058182042,
      "grad_norm": 0.38210374116897583,
      "learning_rate": 7.74572326286917e-06,
      "loss": 0.4962,
      "step": 37309
    },
    {
      "epoch": 1.1461309249531533,
      "grad_norm": 0.3994908332824707,
      "learning_rate": 7.745252427769569e-06,
      "loss": 0.4526,
      "step": 37310
    },
    {
      "epoch": 1.1461616440881024,
      "grad_norm": 0.37531161308288574,
      "learning_rate": 7.74478159793609e-06,
      "loss": 0.4932,
      "step": 37311
    },
    {
      "epoch": 1.1461923632230517,
      "grad_norm": 0.4286355674266815,
      "learning_rate": 7.74431077336983e-06,
      "loss": 0.4421,
      "step": 37312
    },
    {
      "epoch": 1.1462230823580009,
      "grad_norm": 0.37738534808158875,
      "learning_rate": 7.74383995407189e-06,
      "loss": 0.483,
      "step": 37313
    },
    {
      "epoch": 1.14625380149295,
      "grad_norm": 0.41661757230758667,
      "learning_rate": 7.74336914004337e-06,
      "loss": 0.5785,
      "step": 37314
    },
    {
      "epoch": 1.146284520627899,
      "grad_norm": 0.38487231731414795,
      "learning_rate": 7.742898331285368e-06,
      "loss": 0.4523,
      "step": 37315
    },
    {
      "epoch": 1.1463152397628482,
      "grad_norm": 0.38506191968917847,
      "learning_rate": 7.742427527798985e-06,
      "loss": 0.4537,
      "step": 37316
    },
    {
      "epoch": 1.1463459588977973,
      "grad_norm": 0.3969109356403351,
      "learning_rate": 7.74195672958532e-06,
      "loss": 0.5068,
      "step": 37317
    },
    {
      "epoch": 1.1463766780327467,
      "grad_norm": 0.46063554286956787,
      "learning_rate": 7.741485936645475e-06,
      "loss": 0.4399,
      "step": 37318
    },
    {
      "epoch": 1.1464073971676958,
      "grad_norm": 0.44748789072036743,
      "learning_rate": 7.741015148980544e-06,
      "loss": 0.4797,
      "step": 37319
    },
    {
      "epoch": 1.146438116302645,
      "grad_norm": 0.39435169100761414,
      "learning_rate": 7.740544366591636e-06,
      "loss": 0.4845,
      "step": 37320
    },
    {
      "epoch": 1.146468835437594,
      "grad_norm": 0.395049512386322,
      "learning_rate": 7.740073589479837e-06,
      "loss": 0.4401,
      "step": 37321
    },
    {
      "epoch": 1.1464995545725432,
      "grad_norm": 0.40355777740478516,
      "learning_rate": 7.739602817646259e-06,
      "loss": 0.4634,
      "step": 37322
    },
    {
      "epoch": 1.1465302737074925,
      "grad_norm": 0.3406039774417877,
      "learning_rate": 7.739132051091992e-06,
      "loss": 0.4976,
      "step": 37323
    },
    {
      "epoch": 1.1465609928424416,
      "grad_norm": 0.3898021876811981,
      "learning_rate": 7.738661289818146e-06,
      "loss": 0.4818,
      "step": 37324
    },
    {
      "epoch": 1.1465917119773907,
      "grad_norm": 0.43144845962524414,
      "learning_rate": 7.738190533825807e-06,
      "loss": 0.4913,
      "step": 37325
    },
    {
      "epoch": 1.1466224311123399,
      "grad_norm": 0.36965838074684143,
      "learning_rate": 7.73771978311609e-06,
      "loss": 0.457,
      "step": 37326
    },
    {
      "epoch": 1.146653150247289,
      "grad_norm": 0.4044095575809479,
      "learning_rate": 7.73724903769008e-06,
      "loss": 0.4731,
      "step": 37327
    },
    {
      "epoch": 1.146683869382238,
      "grad_norm": 0.36131513118743896,
      "learning_rate": 7.736778297548886e-06,
      "loss": 0.5224,
      "step": 37328
    },
    {
      "epoch": 1.1467145885171874,
      "grad_norm": 0.3781527280807495,
      "learning_rate": 7.736307562693604e-06,
      "loss": 0.4974,
      "step": 37329
    },
    {
      "epoch": 1.1467453076521366,
      "grad_norm": 0.3565804064273834,
      "learning_rate": 7.735836833125334e-06,
      "loss": 0.5077,
      "step": 37330
    },
    {
      "epoch": 1.1467760267870857,
      "grad_norm": 0.38439029455184937,
      "learning_rate": 7.735366108845173e-06,
      "loss": 0.454,
      "step": 37331
    },
    {
      "epoch": 1.1468067459220348,
      "grad_norm": 0.3974727392196655,
      "learning_rate": 7.734895389854223e-06,
      "loss": 0.4974,
      "step": 37332
    },
    {
      "epoch": 1.146837465056984,
      "grad_norm": 0.3660006523132324,
      "learning_rate": 7.734424676153585e-06,
      "loss": 0.4931,
      "step": 37333
    },
    {
      "epoch": 1.1468681841919333,
      "grad_norm": 0.37357208132743835,
      "learning_rate": 7.733953967744353e-06,
      "loss": 0.512,
      "step": 37334
    },
    {
      "epoch": 1.1468989033268824,
      "grad_norm": 0.4169104993343353,
      "learning_rate": 7.733483264627634e-06,
      "loss": 0.5313,
      "step": 37335
    },
    {
      "epoch": 1.1469296224618315,
      "grad_norm": 0.4169697165489197,
      "learning_rate": 7.73301256680452e-06,
      "loss": 0.4962,
      "step": 37336
    },
    {
      "epoch": 1.1469603415967806,
      "grad_norm": 0.4664887487888336,
      "learning_rate": 7.732541874276117e-06,
      "loss": 0.5913,
      "step": 37337
    },
    {
      "epoch": 1.1469910607317297,
      "grad_norm": 0.4226469099521637,
      "learning_rate": 7.732071187043517e-06,
      "loss": 0.5007,
      "step": 37338
    },
    {
      "epoch": 1.1470217798666789,
      "grad_norm": 0.4749804437160492,
      "learning_rate": 7.731600505107828e-06,
      "loss": 0.4863,
      "step": 37339
    },
    {
      "epoch": 1.1470524990016282,
      "grad_norm": 0.3645458221435547,
      "learning_rate": 7.731129828470138e-06,
      "loss": 0.5526,
      "step": 37340
    },
    {
      "epoch": 1.1470832181365773,
      "grad_norm": 0.4444531202316284,
      "learning_rate": 7.730659157131559e-06,
      "loss": 0.4744,
      "step": 37341
    },
    {
      "epoch": 1.1471139372715264,
      "grad_norm": 0.4307401180267334,
      "learning_rate": 7.730188491093179e-06,
      "loss": 0.4744,
      "step": 37342
    },
    {
      "epoch": 1.1471446564064756,
      "grad_norm": 0.41284260153770447,
      "learning_rate": 7.729717830356105e-06,
      "loss": 0.4672,
      "step": 37343
    },
    {
      "epoch": 1.1471753755414247,
      "grad_norm": 0.38918426632881165,
      "learning_rate": 7.729247174921432e-06,
      "loss": 0.5103,
      "step": 37344
    },
    {
      "epoch": 1.147206094676374,
      "grad_norm": 0.46389374136924744,
      "learning_rate": 7.728776524790264e-06,
      "loss": 0.5016,
      "step": 37345
    },
    {
      "epoch": 1.1472368138113231,
      "grad_norm": 0.38143789768218994,
      "learning_rate": 7.728305879963693e-06,
      "loss": 0.5143,
      "step": 37346
    },
    {
      "epoch": 1.1472675329462723,
      "grad_norm": 0.3883214592933655,
      "learning_rate": 7.727835240442824e-06,
      "loss": 0.587,
      "step": 37347
    },
    {
      "epoch": 1.1472982520812214,
      "grad_norm": 0.38835054636001587,
      "learning_rate": 7.727364606228754e-06,
      "loss": 0.5283,
      "step": 37348
    },
    {
      "epoch": 1.1473289712161705,
      "grad_norm": 0.37644413113594055,
      "learning_rate": 7.726893977322582e-06,
      "loss": 0.4841,
      "step": 37349
    },
    {
      "epoch": 1.1473596903511196,
      "grad_norm": 0.3986707627773285,
      "learning_rate": 7.726423353725411e-06,
      "loss": 0.5162,
      "step": 37350
    },
    {
      "epoch": 1.147390409486069,
      "grad_norm": 0.4391576051712036,
      "learning_rate": 7.725952735438334e-06,
      "loss": 0.5223,
      "step": 37351
    },
    {
      "epoch": 1.147421128621018,
      "grad_norm": 0.3770429790019989,
      "learning_rate": 7.725482122462455e-06,
      "loss": 0.4809,
      "step": 37352
    },
    {
      "epoch": 1.1474518477559672,
      "grad_norm": 0.3755047917366028,
      "learning_rate": 7.72501151479887e-06,
      "loss": 0.4835,
      "step": 37353
    },
    {
      "epoch": 1.1474825668909163,
      "grad_norm": 0.3831252157688141,
      "learning_rate": 7.724540912448683e-06,
      "loss": 0.4841,
      "step": 37354
    },
    {
      "epoch": 1.1475132860258654,
      "grad_norm": 0.6012532114982605,
      "learning_rate": 7.724070315412983e-06,
      "loss": 0.4499,
      "step": 37355
    },
    {
      "epoch": 1.1475440051608148,
      "grad_norm": 0.39023810625076294,
      "learning_rate": 7.723599723692884e-06,
      "loss": 0.4416,
      "step": 37356
    },
    {
      "epoch": 1.147574724295764,
      "grad_norm": 0.3731776773929596,
      "learning_rate": 7.723129137289468e-06,
      "loss": 0.4741,
      "step": 37357
    },
    {
      "epoch": 1.147605443430713,
      "grad_norm": 0.4774072766304016,
      "learning_rate": 7.722658556203851e-06,
      "loss": 0.486,
      "step": 37358
    },
    {
      "epoch": 1.1476361625656621,
      "grad_norm": 0.4298626184463501,
      "learning_rate": 7.722187980437118e-06,
      "loss": 0.4683,
      "step": 37359
    },
    {
      "epoch": 1.1476668817006113,
      "grad_norm": 0.41686782240867615,
      "learning_rate": 7.72171740999038e-06,
      "loss": 0.4921,
      "step": 37360
    },
    {
      "epoch": 1.1476976008355604,
      "grad_norm": 0.7801361083984375,
      "learning_rate": 7.721246844864723e-06,
      "loss": 0.4368,
      "step": 37361
    },
    {
      "epoch": 1.1477283199705097,
      "grad_norm": 0.4268505275249481,
      "learning_rate": 7.72077628506126e-06,
      "loss": 0.4442,
      "step": 37362
    },
    {
      "epoch": 1.1477590391054588,
      "grad_norm": 0.37310051918029785,
      "learning_rate": 7.720305730581077e-06,
      "loss": 0.5071,
      "step": 37363
    },
    {
      "epoch": 1.147789758240408,
      "grad_norm": 0.5101449489593506,
      "learning_rate": 7.719835181425283e-06,
      "loss": 0.5406,
      "step": 37364
    },
    {
      "epoch": 1.147820477375357,
      "grad_norm": 0.41801080107688904,
      "learning_rate": 7.719364637594972e-06,
      "loss": 0.5428,
      "step": 37365
    },
    {
      "epoch": 1.1478511965103062,
      "grad_norm": 0.4043174386024475,
      "learning_rate": 7.718894099091244e-06,
      "loss": 0.3877,
      "step": 37366
    },
    {
      "epoch": 1.1478819156452555,
      "grad_norm": 0.4040890336036682,
      "learning_rate": 7.718423565915199e-06,
      "loss": 0.5119,
      "step": 37367
    },
    {
      "epoch": 1.1479126347802047,
      "grad_norm": 0.38576754927635193,
      "learning_rate": 7.717953038067932e-06,
      "loss": 0.4477,
      "step": 37368
    },
    {
      "epoch": 1.1479433539151538,
      "grad_norm": 0.397416889667511,
      "learning_rate": 7.71748251555055e-06,
      "loss": 0.4835,
      "step": 37369
    },
    {
      "epoch": 1.147974073050103,
      "grad_norm": 0.43181416392326355,
      "learning_rate": 7.717011998364143e-06,
      "loss": 0.5118,
      "step": 37370
    },
    {
      "epoch": 1.148004792185052,
      "grad_norm": 0.3894619643688202,
      "learning_rate": 7.716541486509816e-06,
      "loss": 0.4611,
      "step": 37371
    },
    {
      "epoch": 1.1480355113200011,
      "grad_norm": 0.38632482290267944,
      "learning_rate": 7.716070979988663e-06,
      "loss": 0.4921,
      "step": 37372
    },
    {
      "epoch": 1.1480662304549503,
      "grad_norm": 0.3991576135158539,
      "learning_rate": 7.71560047880179e-06,
      "loss": 0.4308,
      "step": 37373
    },
    {
      "epoch": 1.1480969495898996,
      "grad_norm": 0.43041500449180603,
      "learning_rate": 7.71512998295029e-06,
      "loss": 0.5272,
      "step": 37374
    },
    {
      "epoch": 1.1481276687248487,
      "grad_norm": 0.439833402633667,
      "learning_rate": 7.714659492435264e-06,
      "loss": 0.5265,
      "step": 37375
    },
    {
      "epoch": 1.1481583878597978,
      "grad_norm": 0.4269711673259735,
      "learning_rate": 7.714189007257807e-06,
      "loss": 0.5328,
      "step": 37376
    },
    {
      "epoch": 1.148189106994747,
      "grad_norm": 0.3997444212436676,
      "learning_rate": 7.713718527419025e-06,
      "loss": 0.477,
      "step": 37377
    },
    {
      "epoch": 1.1482198261296963,
      "grad_norm": 0.3955383896827698,
      "learning_rate": 7.71324805292001e-06,
      "loss": 0.5114,
      "step": 37378
    },
    {
      "epoch": 1.1482505452646454,
      "grad_norm": 0.3875702917575836,
      "learning_rate": 7.712777583761869e-06,
      "loss": 0.462,
      "step": 37379
    },
    {
      "epoch": 1.1482812643995945,
      "grad_norm": 0.42235079407691956,
      "learning_rate": 7.71230711994569e-06,
      "loss": 0.4913,
      "step": 37380
    },
    {
      "epoch": 1.1483119835345437,
      "grad_norm": 0.3973158895969391,
      "learning_rate": 7.71183666147258e-06,
      "loss": 0.5309,
      "step": 37381
    },
    {
      "epoch": 1.1483427026694928,
      "grad_norm": 0.4911181628704071,
      "learning_rate": 7.711366208343634e-06,
      "loss": 0.4606,
      "step": 37382
    },
    {
      "epoch": 1.148373421804442,
      "grad_norm": 0.39122819900512695,
      "learning_rate": 7.710895760559957e-06,
      "loss": 0.4391,
      "step": 37383
    },
    {
      "epoch": 1.148404140939391,
      "grad_norm": 0.3706519603729248,
      "learning_rate": 7.710425318122636e-06,
      "loss": 0.461,
      "step": 37384
    },
    {
      "epoch": 1.1484348600743404,
      "grad_norm": 0.362745076417923,
      "learning_rate": 7.709954881032784e-06,
      "loss": 0.4822,
      "step": 37385
    },
    {
      "epoch": 1.1484655792092895,
      "grad_norm": 0.380093514919281,
      "learning_rate": 7.709484449291484e-06,
      "loss": 0.4294,
      "step": 37386
    },
    {
      "epoch": 1.1484962983442386,
      "grad_norm": 0.41855600476264954,
      "learning_rate": 7.709014022899846e-06,
      "loss": 0.4384,
      "step": 37387
    },
    {
      "epoch": 1.1485270174791877,
      "grad_norm": 0.41947147250175476,
      "learning_rate": 7.708543601858966e-06,
      "loss": 0.5332,
      "step": 37388
    },
    {
      "epoch": 1.148557736614137,
      "grad_norm": 0.381664901971817,
      "learning_rate": 7.708073186169943e-06,
      "loss": 0.4914,
      "step": 37389
    },
    {
      "epoch": 1.1485884557490862,
      "grad_norm": 0.4095613360404968,
      "learning_rate": 7.707602775833878e-06,
      "loss": 0.5163,
      "step": 37390
    },
    {
      "epoch": 1.1486191748840353,
      "grad_norm": 0.40561527013778687,
      "learning_rate": 7.707132370851862e-06,
      "loss": 0.4989,
      "step": 37391
    },
    {
      "epoch": 1.1486498940189844,
      "grad_norm": 0.3821457624435425,
      "learning_rate": 7.706661971225003e-06,
      "loss": 0.579,
      "step": 37392
    },
    {
      "epoch": 1.1486806131539335,
      "grad_norm": 0.4289294183254242,
      "learning_rate": 7.70619157695439e-06,
      "loss": 0.4433,
      "step": 37393
    },
    {
      "epoch": 1.1487113322888827,
      "grad_norm": 0.44101354479789734,
      "learning_rate": 7.705721188041132e-06,
      "loss": 0.4745,
      "step": 37394
    },
    {
      "epoch": 1.1487420514238318,
      "grad_norm": 0.4229295551776886,
      "learning_rate": 7.70525080448632e-06,
      "loss": 0.5436,
      "step": 37395
    },
    {
      "epoch": 1.1487727705587811,
      "grad_norm": 0.3971399664878845,
      "learning_rate": 7.704780426291053e-06,
      "loss": 0.4856,
      "step": 37396
    },
    {
      "epoch": 1.1488034896937303,
      "grad_norm": 0.3891458511352539,
      "learning_rate": 7.704310053456435e-06,
      "loss": 0.4555,
      "step": 37397
    },
    {
      "epoch": 1.1488342088286794,
      "grad_norm": 0.35391801595687866,
      "learning_rate": 7.70383968598356e-06,
      "loss": 0.4829,
      "step": 37398
    },
    {
      "epoch": 1.1488649279636285,
      "grad_norm": 0.41530269384384155,
      "learning_rate": 7.703369323873527e-06,
      "loss": 0.3526,
      "step": 37399
    },
    {
      "epoch": 1.1488956470985776,
      "grad_norm": 0.3850344121456146,
      "learning_rate": 7.702898967127435e-06,
      "loss": 0.5582,
      "step": 37400
    },
    {
      "epoch": 1.148926366233527,
      "grad_norm": 0.5121968388557434,
      "learning_rate": 7.702428615746384e-06,
      "loss": 0.5184,
      "step": 37401
    },
    {
      "epoch": 1.148957085368476,
      "grad_norm": 0.4349689781665802,
      "learning_rate": 7.701958269731472e-06,
      "loss": 0.5839,
      "step": 37402
    },
    {
      "epoch": 1.1489878045034252,
      "grad_norm": 0.3960781991481781,
      "learning_rate": 7.701487929083796e-06,
      "loss": 0.4957,
      "step": 37403
    },
    {
      "epoch": 1.1490185236383743,
      "grad_norm": 0.414905846118927,
      "learning_rate": 7.701017593804453e-06,
      "loss": 0.4802,
      "step": 37404
    },
    {
      "epoch": 1.1490492427733234,
      "grad_norm": 0.3837336301803589,
      "learning_rate": 7.700547263894548e-06,
      "loss": 0.4706,
      "step": 37405
    },
    {
      "epoch": 1.1490799619082726,
      "grad_norm": 0.37327098846435547,
      "learning_rate": 7.700076939355172e-06,
      "loss": 0.4476,
      "step": 37406
    },
    {
      "epoch": 1.149110681043222,
      "grad_norm": 0.3938305079936981,
      "learning_rate": 7.69960662018743e-06,
      "loss": 0.4295,
      "step": 37407
    },
    {
      "epoch": 1.149141400178171,
      "grad_norm": 0.3947393000125885,
      "learning_rate": 7.699136306392416e-06,
      "loss": 0.4712,
      "step": 37408
    },
    {
      "epoch": 1.1491721193131201,
      "grad_norm": 0.41984763741493225,
      "learning_rate": 7.69866599797123e-06,
      "loss": 0.556,
      "step": 37409
    },
    {
      "epoch": 1.1492028384480693,
      "grad_norm": 0.39220085740089417,
      "learning_rate": 7.698195694924971e-06,
      "loss": 0.4404,
      "step": 37410
    },
    {
      "epoch": 1.1492335575830184,
      "grad_norm": 0.3696572780609131,
      "learning_rate": 7.697725397254736e-06,
      "loss": 0.4392,
      "step": 37411
    },
    {
      "epoch": 1.1492642767179677,
      "grad_norm": 0.45732206106185913,
      "learning_rate": 7.697255104961624e-06,
      "loss": 0.5067,
      "step": 37412
    },
    {
      "epoch": 1.1492949958529168,
      "grad_norm": 0.4175836741924286,
      "learning_rate": 7.696784818046735e-06,
      "loss": 0.5086,
      "step": 37413
    },
    {
      "epoch": 1.149325714987866,
      "grad_norm": 0.38025930523872375,
      "learning_rate": 7.696314536511163e-06,
      "loss": 0.4769,
      "step": 37414
    },
    {
      "epoch": 1.149356434122815,
      "grad_norm": 0.4298633933067322,
      "learning_rate": 7.695844260356012e-06,
      "loss": 0.4267,
      "step": 37415
    },
    {
      "epoch": 1.1493871532577642,
      "grad_norm": 0.3896193504333496,
      "learning_rate": 7.695373989582375e-06,
      "loss": 0.514,
      "step": 37416
    },
    {
      "epoch": 1.1494178723927133,
      "grad_norm": 0.3924100995063782,
      "learning_rate": 7.694903724191358e-06,
      "loss": 0.4826,
      "step": 37417
    },
    {
      "epoch": 1.1494485915276627,
      "grad_norm": 0.35900479555130005,
      "learning_rate": 7.694433464184047e-06,
      "loss": 0.5018,
      "step": 37418
    },
    {
      "epoch": 1.1494793106626118,
      "grad_norm": 0.3583028316497803,
      "learning_rate": 7.693963209561555e-06,
      "loss": 0.4487,
      "step": 37419
    },
    {
      "epoch": 1.149510029797561,
      "grad_norm": 0.39913955330848694,
      "learning_rate": 7.693492960324968e-06,
      "loss": 0.5212,
      "step": 37420
    },
    {
      "epoch": 1.14954074893251,
      "grad_norm": 0.38643762469291687,
      "learning_rate": 7.693022716475393e-06,
      "loss": 0.479,
      "step": 37421
    },
    {
      "epoch": 1.1495714680674591,
      "grad_norm": 0.3812168836593628,
      "learning_rate": 7.69255247801392e-06,
      "loss": 0.5252,
      "step": 37422
    },
    {
      "epoch": 1.1496021872024085,
      "grad_norm": 0.44133010506629944,
      "learning_rate": 7.692082244941653e-06,
      "loss": 0.4774,
      "step": 37423
    },
    {
      "epoch": 1.1496329063373576,
      "grad_norm": 0.40694907307624817,
      "learning_rate": 7.691612017259693e-06,
      "loss": 0.5025,
      "step": 37424
    },
    {
      "epoch": 1.1496636254723067,
      "grad_norm": 0.811884880065918,
      "learning_rate": 7.691141794969129e-06,
      "loss": 0.4907,
      "step": 37425
    },
    {
      "epoch": 1.1496943446072558,
      "grad_norm": 0.36351528763771057,
      "learning_rate": 7.69067157807107e-06,
      "loss": 0.519,
      "step": 37426
    },
    {
      "epoch": 1.149725063742205,
      "grad_norm": 0.3931821882724762,
      "learning_rate": 7.690201366566604e-06,
      "loss": 0.5031,
      "step": 37427
    },
    {
      "epoch": 1.149755782877154,
      "grad_norm": 0.3652336299419403,
      "learning_rate": 7.68973116045684e-06,
      "loss": 0.4717,
      "step": 37428
    },
    {
      "epoch": 1.1497865020121034,
      "grad_norm": 0.4086206555366516,
      "learning_rate": 7.689260959742861e-06,
      "loss": 0.474,
      "step": 37429
    },
    {
      "epoch": 1.1498172211470525,
      "grad_norm": 0.41653814911842346,
      "learning_rate": 7.688790764425784e-06,
      "loss": 0.5422,
      "step": 37430
    },
    {
      "epoch": 1.1498479402820017,
      "grad_norm": 0.4127499759197235,
      "learning_rate": 7.688320574506692e-06,
      "loss": 0.4296,
      "step": 37431
    },
    {
      "epoch": 1.1498786594169508,
      "grad_norm": 0.3728230893611908,
      "learning_rate": 7.687850389986691e-06,
      "loss": 0.5044,
      "step": 37432
    },
    {
      "epoch": 1.1499093785519,
      "grad_norm": 0.41722071170806885,
      "learning_rate": 7.687380210866874e-06,
      "loss": 0.535,
      "step": 37433
    },
    {
      "epoch": 1.1499400976868492,
      "grad_norm": 0.38185176253318787,
      "learning_rate": 7.686910037148346e-06,
      "loss": 0.5057,
      "step": 37434
    },
    {
      "epoch": 1.1499708168217984,
      "grad_norm": 0.3621453642845154,
      "learning_rate": 7.686439868832199e-06,
      "loss": 0.5217,
      "step": 37435
    },
    {
      "epoch": 1.1500015359567475,
      "grad_norm": 0.40285277366638184,
      "learning_rate": 7.685969705919534e-06,
      "loss": 0.4083,
      "step": 37436
    },
    {
      "epoch": 1.1500322550916966,
      "grad_norm": 0.38500675559043884,
      "learning_rate": 7.685499548411446e-06,
      "loss": 0.5239,
      "step": 37437
    },
    {
      "epoch": 1.1500629742266457,
      "grad_norm": 0.39928489923477173,
      "learning_rate": 7.685029396309038e-06,
      "loss": 0.5137,
      "step": 37438
    },
    {
      "epoch": 1.1500936933615948,
      "grad_norm": 0.38487792015075684,
      "learning_rate": 7.684559249613405e-06,
      "loss": 0.377,
      "step": 37439
    },
    {
      "epoch": 1.1501244124965442,
      "grad_norm": 0.3908240795135498,
      "learning_rate": 7.684089108325646e-06,
      "loss": 0.5627,
      "step": 37440
    },
    {
      "epoch": 1.1501551316314933,
      "grad_norm": 0.38672930002212524,
      "learning_rate": 7.683618972446858e-06,
      "loss": 0.4749,
      "step": 37441
    },
    {
      "epoch": 1.1501858507664424,
      "grad_norm": 0.4054378271102905,
      "learning_rate": 7.683148841978138e-06,
      "loss": 0.4408,
      "step": 37442
    },
    {
      "epoch": 1.1502165699013915,
      "grad_norm": 0.41948947310447693,
      "learning_rate": 7.682678716920587e-06,
      "loss": 0.5285,
      "step": 37443
    },
    {
      "epoch": 1.1502472890363407,
      "grad_norm": 0.4226943552494049,
      "learning_rate": 7.6822085972753e-06,
      "loss": 0.4981,
      "step": 37444
    },
    {
      "epoch": 1.15027800817129,
      "grad_norm": 0.3665429651737213,
      "learning_rate": 7.681738483043381e-06,
      "loss": 0.5353,
      "step": 37445
    },
    {
      "epoch": 1.1503087273062391,
      "grad_norm": 0.3936362564563751,
      "learning_rate": 7.68126837422592e-06,
      "loss": 0.5208,
      "step": 37446
    },
    {
      "epoch": 1.1503394464411882,
      "grad_norm": 0.3904409110546112,
      "learning_rate": 7.680798270824022e-06,
      "loss": 0.5159,
      "step": 37447
    },
    {
      "epoch": 1.1503701655761374,
      "grad_norm": 0.4197114408016205,
      "learning_rate": 7.680328172838779e-06,
      "loss": 0.4965,
      "step": 37448
    },
    {
      "epoch": 1.1504008847110865,
      "grad_norm": 0.368789941072464,
      "learning_rate": 7.679858080271292e-06,
      "loss": 0.4799,
      "step": 37449
    },
    {
      "epoch": 1.1504316038460356,
      "grad_norm": 0.3674834966659546,
      "learning_rate": 7.679387993122658e-06,
      "loss": 0.4874,
      "step": 37450
    },
    {
      "epoch": 1.150462322980985,
      "grad_norm": 0.4836265444755554,
      "learning_rate": 7.678917911393977e-06,
      "loss": 0.5353,
      "step": 37451
    },
    {
      "epoch": 1.150493042115934,
      "grad_norm": 0.373092383146286,
      "learning_rate": 7.678447835086345e-06,
      "loss": 0.4804,
      "step": 37452
    },
    {
      "epoch": 1.1505237612508832,
      "grad_norm": 0.38784265518188477,
      "learning_rate": 7.67797776420086e-06,
      "loss": 0.5641,
      "step": 37453
    },
    {
      "epoch": 1.1505544803858323,
      "grad_norm": 0.436545193195343,
      "learning_rate": 7.677507698738618e-06,
      "loss": 0.5169,
      "step": 37454
    },
    {
      "epoch": 1.1505851995207814,
      "grad_norm": 0.41028618812561035,
      "learning_rate": 7.677037638700724e-06,
      "loss": 0.4225,
      "step": 37455
    },
    {
      "epoch": 1.1506159186557308,
      "grad_norm": 0.3780076801776886,
      "learning_rate": 7.676567584088266e-06,
      "loss": 0.5009,
      "step": 37456
    },
    {
      "epoch": 1.1506466377906799,
      "grad_norm": 0.37894949316978455,
      "learning_rate": 7.67609753490235e-06,
      "loss": 0.5007,
      "step": 37457
    },
    {
      "epoch": 1.150677356925629,
      "grad_norm": 0.38108986616134644,
      "learning_rate": 7.675627491144067e-06,
      "loss": 0.4209,
      "step": 37458
    },
    {
      "epoch": 1.1507080760605781,
      "grad_norm": 0.42997798323631287,
      "learning_rate": 7.675157452814516e-06,
      "loss": 0.5002,
      "step": 37459
    },
    {
      "epoch": 1.1507387951955272,
      "grad_norm": 0.37935829162597656,
      "learning_rate": 7.674687419914806e-06,
      "loss": 0.4287,
      "step": 37460
    },
    {
      "epoch": 1.1507695143304764,
      "grad_norm": 0.48577815294265747,
      "learning_rate": 7.674217392446018e-06,
      "loss": 0.4452,
      "step": 37461
    },
    {
      "epoch": 1.1508002334654257,
      "grad_norm": 0.3727874159812927,
      "learning_rate": 7.673747370409264e-06,
      "loss": 0.4613,
      "step": 37462
    },
    {
      "epoch": 1.1508309526003748,
      "grad_norm": 0.42001253366470337,
      "learning_rate": 7.673277353805628e-06,
      "loss": 0.5102,
      "step": 37463
    },
    {
      "epoch": 1.150861671735324,
      "grad_norm": 0.3599275052547455,
      "learning_rate": 7.672807342636224e-06,
      "loss": 0.5127,
      "step": 37464
    },
    {
      "epoch": 1.150892390870273,
      "grad_norm": 0.45338866114616394,
      "learning_rate": 7.672337336902134e-06,
      "loss": 0.4699,
      "step": 37465
    },
    {
      "epoch": 1.1509231100052222,
      "grad_norm": 0.38438981771469116,
      "learning_rate": 7.671867336604468e-06,
      "loss": 0.5384,
      "step": 37466
    },
    {
      "epoch": 1.1509538291401715,
      "grad_norm": 0.4089297950267792,
      "learning_rate": 7.671397341744314e-06,
      "loss": 0.4616,
      "step": 37467
    },
    {
      "epoch": 1.1509845482751206,
      "grad_norm": 0.3814452588558197,
      "learning_rate": 7.670927352322777e-06,
      "loss": 0.5546,
      "step": 37468
    },
    {
      "epoch": 1.1510152674100698,
      "grad_norm": 0.41200801730155945,
      "learning_rate": 7.670457368340949e-06,
      "loss": 0.4325,
      "step": 37469
    },
    {
      "epoch": 1.1510459865450189,
      "grad_norm": 0.39102789759635925,
      "learning_rate": 7.669987389799933e-06,
      "loss": 0.5363,
      "step": 37470
    },
    {
      "epoch": 1.151076705679968,
      "grad_norm": 0.40223076939582825,
      "learning_rate": 7.669517416700823e-06,
      "loss": 0.5221,
      "step": 37471
    },
    {
      "epoch": 1.1511074248149171,
      "grad_norm": 0.40734753012657166,
      "learning_rate": 7.66904744904472e-06,
      "loss": 0.525,
      "step": 37472
    },
    {
      "epoch": 1.1511381439498665,
      "grad_norm": 0.39850708842277527,
      "learning_rate": 7.668577486832715e-06,
      "loss": 0.5136,
      "step": 37473
    },
    {
      "epoch": 1.1511688630848156,
      "grad_norm": 0.38497528433799744,
      "learning_rate": 7.668107530065915e-06,
      "loss": 0.4562,
      "step": 37474
    },
    {
      "epoch": 1.1511995822197647,
      "grad_norm": 0.3778719902038574,
      "learning_rate": 7.667637578745407e-06,
      "loss": 0.4949,
      "step": 37475
    },
    {
      "epoch": 1.1512303013547138,
      "grad_norm": 0.3888987600803375,
      "learning_rate": 7.667167632872301e-06,
      "loss": 0.5099,
      "step": 37476
    },
    {
      "epoch": 1.151261020489663,
      "grad_norm": 0.6698362231254578,
      "learning_rate": 7.666697692447683e-06,
      "loss": 0.4158,
      "step": 37477
    },
    {
      "epoch": 1.1512917396246123,
      "grad_norm": 0.35105374455451965,
      "learning_rate": 7.666227757472656e-06,
      "loss": 0.4848,
      "step": 37478
    },
    {
      "epoch": 1.1513224587595614,
      "grad_norm": 0.3951427638530731,
      "learning_rate": 7.665757827948319e-06,
      "loss": 0.4415,
      "step": 37479
    },
    {
      "epoch": 1.1513531778945105,
      "grad_norm": 0.40007272362709045,
      "learning_rate": 7.665287903875767e-06,
      "loss": 0.4953,
      "step": 37480
    },
    {
      "epoch": 1.1513838970294596,
      "grad_norm": 0.38591429591178894,
      "learning_rate": 7.664817985256098e-06,
      "loss": 0.5175,
      "step": 37481
    },
    {
      "epoch": 1.1514146161644088,
      "grad_norm": 0.4113841652870178,
      "learning_rate": 7.664348072090408e-06,
      "loss": 0.4348,
      "step": 37482
    },
    {
      "epoch": 1.1514453352993579,
      "grad_norm": 0.3761806786060333,
      "learning_rate": 7.6638781643798e-06,
      "loss": 0.5407,
      "step": 37483
    },
    {
      "epoch": 1.151476054434307,
      "grad_norm": 0.43973487615585327,
      "learning_rate": 7.663408262125364e-06,
      "loss": 0.5643,
      "step": 37484
    },
    {
      "epoch": 1.1515067735692563,
      "grad_norm": 0.36686763167381287,
      "learning_rate": 7.662938365328203e-06,
      "loss": 0.4905,
      "step": 37485
    },
    {
      "epoch": 1.1515374927042055,
      "grad_norm": 0.43282967805862427,
      "learning_rate": 7.662468473989413e-06,
      "loss": 0.5558,
      "step": 37486
    },
    {
      "epoch": 1.1515682118391546,
      "grad_norm": 0.398908406496048,
      "learning_rate": 7.661998588110093e-06,
      "loss": 0.4742,
      "step": 37487
    },
    {
      "epoch": 1.1515989309741037,
      "grad_norm": 0.3823612928390503,
      "learning_rate": 7.661528707691334e-06,
      "loss": 0.5302,
      "step": 37488
    },
    {
      "epoch": 1.151629650109053,
      "grad_norm": 0.4081062078475952,
      "learning_rate": 7.661058832734242e-06,
      "loss": 0.493,
      "step": 37489
    },
    {
      "epoch": 1.1516603692440022,
      "grad_norm": 0.468857079744339,
      "learning_rate": 7.660588963239906e-06,
      "loss": 0.6599,
      "step": 37490
    },
    {
      "epoch": 1.1516910883789513,
      "grad_norm": 0.3768787086009979,
      "learning_rate": 7.660119099209434e-06,
      "loss": 0.5321,
      "step": 37491
    },
    {
      "epoch": 1.1517218075139004,
      "grad_norm": 0.3573528528213501,
      "learning_rate": 7.659649240643911e-06,
      "loss": 0.4929,
      "step": 37492
    },
    {
      "epoch": 1.1517525266488495,
      "grad_norm": 0.3557971715927124,
      "learning_rate": 7.659179387544447e-06,
      "loss": 0.5148,
      "step": 37493
    },
    {
      "epoch": 1.1517832457837986,
      "grad_norm": 0.40988388657569885,
      "learning_rate": 7.658709539912127e-06,
      "loss": 0.5442,
      "step": 37494
    },
    {
      "epoch": 1.1518139649187478,
      "grad_norm": 0.40365535020828247,
      "learning_rate": 7.658239697748055e-06,
      "loss": 0.5068,
      "step": 37495
    },
    {
      "epoch": 1.151844684053697,
      "grad_norm": 0.4038914740085602,
      "learning_rate": 7.657769861053333e-06,
      "loss": 0.4598,
      "step": 37496
    },
    {
      "epoch": 1.1518754031886462,
      "grad_norm": 0.3635377585887909,
      "learning_rate": 7.657300029829045e-06,
      "loss": 0.4629,
      "step": 37497
    },
    {
      "epoch": 1.1519061223235953,
      "grad_norm": 0.3899625837802887,
      "learning_rate": 7.656830204076305e-06,
      "loss": 0.4928,
      "step": 37498
    },
    {
      "epoch": 1.1519368414585445,
      "grad_norm": 0.43184971809387207,
      "learning_rate": 7.656360383796196e-06,
      "loss": 0.4316,
      "step": 37499
    },
    {
      "epoch": 1.1519675605934938,
      "grad_norm": 0.3914450705051422,
      "learning_rate": 7.655890568989824e-06,
      "loss": 0.4173,
      "step": 37500
    },
    {
      "epoch": 1.151998279728443,
      "grad_norm": 0.4507097899913788,
      "learning_rate": 7.655420759658281e-06,
      "loss": 0.4951,
      "step": 37501
    },
    {
      "epoch": 1.152028998863392,
      "grad_norm": 0.42968031764030457,
      "learning_rate": 7.654950955802668e-06,
      "loss": 0.5996,
      "step": 37502
    },
    {
      "epoch": 1.1520597179983412,
      "grad_norm": 0.41182827949523926,
      "learning_rate": 7.65448115742408e-06,
      "loss": 0.49,
      "step": 37503
    },
    {
      "epoch": 1.1520904371332903,
      "grad_norm": 0.4069254994392395,
      "learning_rate": 7.654011364523615e-06,
      "loss": 0.5098,
      "step": 37504
    },
    {
      "epoch": 1.1521211562682394,
      "grad_norm": 0.40859872102737427,
      "learning_rate": 7.65354157710237e-06,
      "loss": 0.5483,
      "step": 37505
    },
    {
      "epoch": 1.1521518754031885,
      "grad_norm": 0.3970411419868469,
      "learning_rate": 7.653071795161446e-06,
      "loss": 0.4769,
      "step": 37506
    },
    {
      "epoch": 1.1521825945381379,
      "grad_norm": 0.3965008854866028,
      "learning_rate": 7.652602018701933e-06,
      "loss": 0.5111,
      "step": 37507
    },
    {
      "epoch": 1.152213313673087,
      "grad_norm": 0.39037829637527466,
      "learning_rate": 7.652132247724933e-06,
      "loss": 0.5076,
      "step": 37508
    },
    {
      "epoch": 1.1522440328080361,
      "grad_norm": 0.4416552484035492,
      "learning_rate": 7.651662482231542e-06,
      "loss": 0.5047,
      "step": 37509
    },
    {
      "epoch": 1.1522747519429852,
      "grad_norm": 0.3724193871021271,
      "learning_rate": 7.651192722222858e-06,
      "loss": 0.4971,
      "step": 37510
    },
    {
      "epoch": 1.1523054710779344,
      "grad_norm": 0.3700956404209137,
      "learning_rate": 7.650722967699975e-06,
      "loss": 0.4948,
      "step": 37511
    },
    {
      "epoch": 1.1523361902128837,
      "grad_norm": 0.40188443660736084,
      "learning_rate": 7.650253218663995e-06,
      "loss": 0.4387,
      "step": 37512
    },
    {
      "epoch": 1.1523669093478328,
      "grad_norm": 0.4181254506111145,
      "learning_rate": 7.64978347511601e-06,
      "loss": 0.47,
      "step": 37513
    },
    {
      "epoch": 1.152397628482782,
      "grad_norm": 0.477460116147995,
      "learning_rate": 7.649313737057122e-06,
      "loss": 0.4923,
      "step": 37514
    },
    {
      "epoch": 1.152428347617731,
      "grad_norm": 0.41819095611572266,
      "learning_rate": 7.648844004488427e-06,
      "loss": 0.4987,
      "step": 37515
    },
    {
      "epoch": 1.1524590667526802,
      "grad_norm": 0.40280240774154663,
      "learning_rate": 7.648374277411019e-06,
      "loss": 0.5924,
      "step": 37516
    },
    {
      "epoch": 1.1524897858876293,
      "grad_norm": 0.3960496783256531,
      "learning_rate": 7.647904555826e-06,
      "loss": 0.5172,
      "step": 37517
    },
    {
      "epoch": 1.1525205050225786,
      "grad_norm": 0.39000776410102844,
      "learning_rate": 7.64743483973446e-06,
      "loss": 0.4816,
      "step": 37518
    },
    {
      "epoch": 1.1525512241575278,
      "grad_norm": 0.4059249460697174,
      "learning_rate": 7.646965129137504e-06,
      "loss": 0.5422,
      "step": 37519
    },
    {
      "epoch": 1.1525819432924769,
      "grad_norm": 0.41485604643821716,
      "learning_rate": 7.646495424036222e-06,
      "loss": 0.5153,
      "step": 37520
    },
    {
      "epoch": 1.152612662427426,
      "grad_norm": 0.5056260824203491,
      "learning_rate": 7.646025724431719e-06,
      "loss": 0.5105,
      "step": 37521
    },
    {
      "epoch": 1.1526433815623751,
      "grad_norm": 0.4141644537448883,
      "learning_rate": 7.64555603032508e-06,
      "loss": 0.4862,
      "step": 37522
    },
    {
      "epoch": 1.1526741006973245,
      "grad_norm": 0.4099492132663727,
      "learning_rate": 7.645086341717418e-06,
      "loss": 0.477,
      "step": 37523
    },
    {
      "epoch": 1.1527048198322736,
      "grad_norm": 0.4003128409385681,
      "learning_rate": 7.644616658609814e-06,
      "loss": 0.4412,
      "step": 37524
    },
    {
      "epoch": 1.1527355389672227,
      "grad_norm": 0.35531705617904663,
      "learning_rate": 7.644146981003377e-06,
      "loss": 0.4782,
      "step": 37525
    },
    {
      "epoch": 1.1527662581021718,
      "grad_norm": 0.3653171956539154,
      "learning_rate": 7.643677308899195e-06,
      "loss": 0.4293,
      "step": 37526
    },
    {
      "epoch": 1.152796977237121,
      "grad_norm": 0.38601890206336975,
      "learning_rate": 7.643207642298374e-06,
      "loss": 0.4811,
      "step": 37527
    },
    {
      "epoch": 1.15282769637207,
      "grad_norm": 0.4185290038585663,
      "learning_rate": 7.642737981202002e-06,
      "loss": 0.5656,
      "step": 37528
    },
    {
      "epoch": 1.1528584155070194,
      "grad_norm": 0.4350544512271881,
      "learning_rate": 7.642268325611183e-06,
      "loss": 0.4802,
      "step": 37529
    },
    {
      "epoch": 1.1528891346419685,
      "grad_norm": 0.38550281524658203,
      "learning_rate": 7.64179867552701e-06,
      "loss": 0.4784,
      "step": 37530
    },
    {
      "epoch": 1.1529198537769176,
      "grad_norm": 0.38051384687423706,
      "learning_rate": 7.641329030950582e-06,
      "loss": 0.4599,
      "step": 37531
    },
    {
      "epoch": 1.1529505729118668,
      "grad_norm": 0.41361933946609497,
      "learning_rate": 7.640859391882993e-06,
      "loss": 0.49,
      "step": 37532
    },
    {
      "epoch": 1.1529812920468159,
      "grad_norm": 0.3856230676174164,
      "learning_rate": 7.640389758325339e-06,
      "loss": 0.4548,
      "step": 37533
    },
    {
      "epoch": 1.1530120111817652,
      "grad_norm": 0.46244996786117554,
      "learning_rate": 7.639920130278725e-06,
      "loss": 0.4904,
      "step": 37534
    },
    {
      "epoch": 1.1530427303167143,
      "grad_norm": 0.3960731029510498,
      "learning_rate": 7.63945050774424e-06,
      "loss": 0.4913,
      "step": 37535
    },
    {
      "epoch": 1.1530734494516635,
      "grad_norm": 0.40126705169677734,
      "learning_rate": 7.638980890722984e-06,
      "loss": 0.5391,
      "step": 37536
    },
    {
      "epoch": 1.1531041685866126,
      "grad_norm": 0.3859115540981293,
      "learning_rate": 7.63851127921605e-06,
      "loss": 0.4323,
      "step": 37537
    },
    {
      "epoch": 1.1531348877215617,
      "grad_norm": 0.37553703784942627,
      "learning_rate": 7.638041673224542e-06,
      "loss": 0.5364,
      "step": 37538
    },
    {
      "epoch": 1.1531656068565108,
      "grad_norm": 0.4229523837566376,
      "learning_rate": 7.63757207274955e-06,
      "loss": 0.501,
      "step": 37539
    },
    {
      "epoch": 1.1531963259914602,
      "grad_norm": 0.4137103855609894,
      "learning_rate": 7.637102477792174e-06,
      "loss": 0.4288,
      "step": 37540
    },
    {
      "epoch": 1.1532270451264093,
      "grad_norm": 0.4085409343242645,
      "learning_rate": 7.63663288835351e-06,
      "loss": 0.4479,
      "step": 37541
    },
    {
      "epoch": 1.1532577642613584,
      "grad_norm": 0.4471985101699829,
      "learning_rate": 7.636163304434656e-06,
      "loss": 0.5231,
      "step": 37542
    },
    {
      "epoch": 1.1532884833963075,
      "grad_norm": 0.3650609254837036,
      "learning_rate": 7.635693726036706e-06,
      "loss": 0.4413,
      "step": 37543
    },
    {
      "epoch": 1.1533192025312566,
      "grad_norm": 0.3335863947868347,
      "learning_rate": 7.63522415316076e-06,
      "loss": 0.4392,
      "step": 37544
    },
    {
      "epoch": 1.153349921666206,
      "grad_norm": 0.6091307401657104,
      "learning_rate": 7.634754585807913e-06,
      "loss": 0.4919,
      "step": 37545
    },
    {
      "epoch": 1.153380640801155,
      "grad_norm": 0.41489529609680176,
      "learning_rate": 7.634285023979262e-06,
      "loss": 0.5139,
      "step": 37546
    },
    {
      "epoch": 1.1534113599361042,
      "grad_norm": 0.4316425025463104,
      "learning_rate": 7.633815467675902e-06,
      "loss": 0.4923,
      "step": 37547
    },
    {
      "epoch": 1.1534420790710533,
      "grad_norm": 0.39404618740081787,
      "learning_rate": 7.633345916898934e-06,
      "loss": 0.5441,
      "step": 37548
    },
    {
      "epoch": 1.1534727982060025,
      "grad_norm": 0.36872434616088867,
      "learning_rate": 7.632876371649447e-06,
      "loss": 0.4799,
      "step": 37549
    },
    {
      "epoch": 1.1535035173409516,
      "grad_norm": 0.3582327365875244,
      "learning_rate": 7.632406831928545e-06,
      "loss": 0.444,
      "step": 37550
    },
    {
      "epoch": 1.153534236475901,
      "grad_norm": 0.40352556109428406,
      "learning_rate": 7.631937297737324e-06,
      "loss": 0.5129,
      "step": 37551
    },
    {
      "epoch": 1.15356495561085,
      "grad_norm": 0.44039249420166016,
      "learning_rate": 7.631467769076878e-06,
      "loss": 0.5328,
      "step": 37552
    },
    {
      "epoch": 1.1535956747457992,
      "grad_norm": 0.41487306356430054,
      "learning_rate": 7.630998245948303e-06,
      "loss": 0.5048,
      "step": 37553
    },
    {
      "epoch": 1.1536263938807483,
      "grad_norm": 0.36930134892463684,
      "learning_rate": 7.630528728352697e-06,
      "loss": 0.5552,
      "step": 37554
    },
    {
      "epoch": 1.1536571130156974,
      "grad_norm": 0.365587055683136,
      "learning_rate": 7.630059216291159e-06,
      "loss": 0.4615,
      "step": 37555
    },
    {
      "epoch": 1.1536878321506467,
      "grad_norm": 0.39274516701698303,
      "learning_rate": 7.62958970976478e-06,
      "loss": 0.5119,
      "step": 37556
    },
    {
      "epoch": 1.1537185512855959,
      "grad_norm": 0.40481802821159363,
      "learning_rate": 7.629120208774667e-06,
      "loss": 0.5231,
      "step": 37557
    },
    {
      "epoch": 1.153749270420545,
      "grad_norm": 0.3848203122615814,
      "learning_rate": 7.6286507133219e-06,
      "loss": 0.5013,
      "step": 37558
    },
    {
      "epoch": 1.153779989555494,
      "grad_norm": 0.432172030210495,
      "learning_rate": 7.6281812234075925e-06,
      "loss": 0.4999,
      "step": 37559
    },
    {
      "epoch": 1.1538107086904432,
      "grad_norm": 0.4156314432621002,
      "learning_rate": 7.627711739032826e-06,
      "loss": 0.5339,
      "step": 37560
    },
    {
      "epoch": 1.1538414278253923,
      "grad_norm": 0.39222463965415955,
      "learning_rate": 7.627242260198711e-06,
      "loss": 0.578,
      "step": 37561
    },
    {
      "epoch": 1.1538721469603417,
      "grad_norm": 0.4356880187988281,
      "learning_rate": 7.626772786906333e-06,
      "loss": 0.4144,
      "step": 37562
    },
    {
      "epoch": 1.1539028660952908,
      "grad_norm": 0.3960820436477661,
      "learning_rate": 7.626303319156797e-06,
      "loss": 0.4766,
      "step": 37563
    },
    {
      "epoch": 1.15393358523024,
      "grad_norm": 0.3673454821109772,
      "learning_rate": 7.6258338569511925e-06,
      "loss": 0.4587,
      "step": 37564
    },
    {
      "epoch": 1.153964304365189,
      "grad_norm": 0.3970431983470917,
      "learning_rate": 7.62536440029062e-06,
      "loss": 0.5369,
      "step": 37565
    },
    {
      "epoch": 1.1539950235001382,
      "grad_norm": 0.38079994916915894,
      "learning_rate": 7.6248949491761725e-06,
      "loss": 0.5564,
      "step": 37566
    },
    {
      "epoch": 1.1540257426350875,
      "grad_norm": 0.4308040738105774,
      "learning_rate": 7.624425503608952e-06,
      "loss": 0.5358,
      "step": 37567
    },
    {
      "epoch": 1.1540564617700366,
      "grad_norm": 0.3847323954105377,
      "learning_rate": 7.623956063590048e-06,
      "loss": 0.4976,
      "step": 37568
    },
    {
      "epoch": 1.1540871809049857,
      "grad_norm": 0.3910925090312958,
      "learning_rate": 7.623486629120562e-06,
      "loss": 0.4863,
      "step": 37569
    },
    {
      "epoch": 1.1541179000399349,
      "grad_norm": 0.40888914465904236,
      "learning_rate": 7.62301720020159e-06,
      "loss": 0.5557,
      "step": 37570
    },
    {
      "epoch": 1.154148619174884,
      "grad_norm": 0.384016215801239,
      "learning_rate": 7.622547776834226e-06,
      "loss": 0.4245,
      "step": 37571
    },
    {
      "epoch": 1.154179338309833,
      "grad_norm": 0.3953287601470947,
      "learning_rate": 7.622078359019569e-06,
      "loss": 0.4251,
      "step": 37572
    },
    {
      "epoch": 1.1542100574447824,
      "grad_norm": 0.3551488518714905,
      "learning_rate": 7.621608946758713e-06,
      "loss": 0.4143,
      "step": 37573
    },
    {
      "epoch": 1.1542407765797316,
      "grad_norm": 0.3952527642250061,
      "learning_rate": 7.621139540052758e-06,
      "loss": 0.448,
      "step": 37574
    },
    {
      "epoch": 1.1542714957146807,
      "grad_norm": 0.3797330856323242,
      "learning_rate": 7.620670138902794e-06,
      "loss": 0.4956,
      "step": 37575
    },
    {
      "epoch": 1.1543022148496298,
      "grad_norm": 0.44392654299736023,
      "learning_rate": 7.620200743309924e-06,
      "loss": 0.5307,
      "step": 37576
    },
    {
      "epoch": 1.154332933984579,
      "grad_norm": 0.3954799771308899,
      "learning_rate": 7.619731353275238e-06,
      "loss": 0.4384,
      "step": 37577
    },
    {
      "epoch": 1.1543636531195283,
      "grad_norm": 0.39613863825798035,
      "learning_rate": 7.619261968799839e-06,
      "loss": 0.5162,
      "step": 37578
    },
    {
      "epoch": 1.1543943722544774,
      "grad_norm": 0.3928292393684387,
      "learning_rate": 7.618792589884818e-06,
      "loss": 0.5321,
      "step": 37579
    },
    {
      "epoch": 1.1544250913894265,
      "grad_norm": 0.41135406494140625,
      "learning_rate": 7.618323216531275e-06,
      "loss": 0.4926,
      "step": 37580
    },
    {
      "epoch": 1.1544558105243756,
      "grad_norm": 0.42283257842063904,
      "learning_rate": 7.617853848740302e-06,
      "loss": 0.5176,
      "step": 37581
    },
    {
      "epoch": 1.1544865296593247,
      "grad_norm": 0.5493407845497131,
      "learning_rate": 7.617384486513001e-06,
      "loss": 0.5141,
      "step": 37582
    },
    {
      "epoch": 1.1545172487942739,
      "grad_norm": 0.421242892742157,
      "learning_rate": 7.616915129850462e-06,
      "loss": 0.5169,
      "step": 37583
    },
    {
      "epoch": 1.1545479679292232,
      "grad_norm": 0.40160274505615234,
      "learning_rate": 7.616445778753786e-06,
      "loss": 0.4744,
      "step": 37584
    },
    {
      "epoch": 1.1545786870641723,
      "grad_norm": 0.4038997292518616,
      "learning_rate": 7.615976433224065e-06,
      "loss": 0.4882,
      "step": 37585
    },
    {
      "epoch": 1.1546094061991214,
      "grad_norm": 0.4144016206264496,
      "learning_rate": 7.615507093262402e-06,
      "loss": 0.4994,
      "step": 37586
    },
    {
      "epoch": 1.1546401253340706,
      "grad_norm": 0.4233560264110565,
      "learning_rate": 7.615037758869883e-06,
      "loss": 0.3789,
      "step": 37587
    },
    {
      "epoch": 1.1546708444690197,
      "grad_norm": 0.3624393343925476,
      "learning_rate": 7.614568430047612e-06,
      "loss": 0.472,
      "step": 37588
    },
    {
      "epoch": 1.154701563603969,
      "grad_norm": 0.37757518887519836,
      "learning_rate": 7.614099106796684e-06,
      "loss": 0.5167,
      "step": 37589
    },
    {
      "epoch": 1.1547322827389181,
      "grad_norm": 0.3971867561340332,
      "learning_rate": 7.613629789118193e-06,
      "loss": 0.4651,
      "step": 37590
    },
    {
      "epoch": 1.1547630018738673,
      "grad_norm": 0.3863036632537842,
      "learning_rate": 7.613160477013241e-06,
      "loss": 0.4881,
      "step": 37591
    },
    {
      "epoch": 1.1547937210088164,
      "grad_norm": 0.37554964423179626,
      "learning_rate": 7.612691170482912e-06,
      "loss": 0.4866,
      "step": 37592
    },
    {
      "epoch": 1.1548244401437655,
      "grad_norm": 0.4146634042263031,
      "learning_rate": 7.612221869528316e-06,
      "loss": 0.5719,
      "step": 37593
    },
    {
      "epoch": 1.1548551592787146,
      "grad_norm": 0.39378583431243896,
      "learning_rate": 7.611752574150537e-06,
      "loss": 0.4579,
      "step": 37594
    },
    {
      "epoch": 1.1548858784136637,
      "grad_norm": 0.38859644532203674,
      "learning_rate": 7.611283284350682e-06,
      "loss": 0.5124,
      "step": 37595
    },
    {
      "epoch": 1.154916597548613,
      "grad_norm": 0.38065168261528015,
      "learning_rate": 7.610814000129836e-06,
      "loss": 0.5129,
      "step": 37596
    },
    {
      "epoch": 1.1549473166835622,
      "grad_norm": 0.41273558139801025,
      "learning_rate": 7.610344721489107e-06,
      "loss": 0.6029,
      "step": 37597
    },
    {
      "epoch": 1.1549780358185113,
      "grad_norm": 0.35630691051483154,
      "learning_rate": 7.60987544842958e-06,
      "loss": 0.4597,
      "step": 37598
    },
    {
      "epoch": 1.1550087549534604,
      "grad_norm": 0.3729763925075531,
      "learning_rate": 7.609406180952359e-06,
      "loss": 0.5418,
      "step": 37599
    },
    {
      "epoch": 1.1550394740884098,
      "grad_norm": 0.3456522226333618,
      "learning_rate": 7.608936919058534e-06,
      "loss": 0.4195,
      "step": 37600
    },
    {
      "epoch": 1.155070193223359,
      "grad_norm": 0.4302183985710144,
      "learning_rate": 7.608467662749206e-06,
      "loss": 0.4887,
      "step": 37601
    },
    {
      "epoch": 1.155100912358308,
      "grad_norm": 0.38325420022010803,
      "learning_rate": 7.6079984120254665e-06,
      "loss": 0.472,
      "step": 37602
    },
    {
      "epoch": 1.1551316314932571,
      "grad_norm": 0.38372641801834106,
      "learning_rate": 7.607529166888417e-06,
      "loss": 0.5059,
      "step": 37603
    },
    {
      "epoch": 1.1551623506282063,
      "grad_norm": 0.3471723198890686,
      "learning_rate": 7.6070599273391465e-06,
      "loss": 0.4661,
      "step": 37604
    },
    {
      "epoch": 1.1551930697631554,
      "grad_norm": 0.3991563320159912,
      "learning_rate": 7.606590693378755e-06,
      "loss": 0.4671,
      "step": 37605
    },
    {
      "epoch": 1.1552237888981045,
      "grad_norm": 0.39275607466697693,
      "learning_rate": 7.60612146500834e-06,
      "loss": 0.485,
      "step": 37606
    },
    {
      "epoch": 1.1552545080330539,
      "grad_norm": 0.4339527189731598,
      "learning_rate": 7.6056522422289946e-06,
      "loss": 0.4655,
      "step": 37607
    },
    {
      "epoch": 1.155285227168003,
      "grad_norm": 0.3681863248348236,
      "learning_rate": 7.605183025041818e-06,
      "loss": 0.4921,
      "step": 37608
    },
    {
      "epoch": 1.155315946302952,
      "grad_norm": 0.45928406715393066,
      "learning_rate": 7.6047138134479e-06,
      "loss": 0.5222,
      "step": 37609
    },
    {
      "epoch": 1.1553466654379012,
      "grad_norm": 0.3896220922470093,
      "learning_rate": 7.6042446074483435e-06,
      "loss": 0.4856,
      "step": 37610
    },
    {
      "epoch": 1.1553773845728506,
      "grad_norm": 0.4426616132259369,
      "learning_rate": 7.603775407044238e-06,
      "loss": 0.5411,
      "step": 37611
    },
    {
      "epoch": 1.1554081037077997,
      "grad_norm": 0.4061145484447479,
      "learning_rate": 7.603306212236685e-06,
      "loss": 0.4967,
      "step": 37612
    },
    {
      "epoch": 1.1554388228427488,
      "grad_norm": 0.39489123225212097,
      "learning_rate": 7.602837023026776e-06,
      "loss": 0.4862,
      "step": 37613
    },
    {
      "epoch": 1.155469541977698,
      "grad_norm": 0.40312108397483826,
      "learning_rate": 7.60236783941561e-06,
      "loss": 0.4899,
      "step": 37614
    },
    {
      "epoch": 1.155500261112647,
      "grad_norm": 0.3669200837612152,
      "learning_rate": 7.601898661404279e-06,
      "loss": 0.4743,
      "step": 37615
    },
    {
      "epoch": 1.1555309802475962,
      "grad_norm": 0.4504404067993164,
      "learning_rate": 7.601429488993883e-06,
      "loss": 0.5139,
      "step": 37616
    },
    {
      "epoch": 1.1555616993825453,
      "grad_norm": 0.44273024797439575,
      "learning_rate": 7.600960322185516e-06,
      "loss": 0.4632,
      "step": 37617
    },
    {
      "epoch": 1.1555924185174946,
      "grad_norm": 0.39768657088279724,
      "learning_rate": 7.600491160980273e-06,
      "loss": 0.4598,
      "step": 37618
    },
    {
      "epoch": 1.1556231376524437,
      "grad_norm": 0.38680005073547363,
      "learning_rate": 7.600022005379251e-06,
      "loss": 0.5155,
      "step": 37619
    },
    {
      "epoch": 1.1556538567873929,
      "grad_norm": 0.41124609112739563,
      "learning_rate": 7.599552855383547e-06,
      "loss": 0.4829,
      "step": 37620
    },
    {
      "epoch": 1.155684575922342,
      "grad_norm": 0.3921184837818146,
      "learning_rate": 7.599083710994251e-06,
      "loss": 0.4908,
      "step": 37621
    },
    {
      "epoch": 1.155715295057291,
      "grad_norm": 0.3895082473754883,
      "learning_rate": 7.5986145722124675e-06,
      "loss": 0.5533,
      "step": 37622
    },
    {
      "epoch": 1.1557460141922404,
      "grad_norm": 0.389616459608078,
      "learning_rate": 7.598145439039281e-06,
      "loss": 0.5101,
      "step": 37623
    },
    {
      "epoch": 1.1557767333271896,
      "grad_norm": 0.4062431752681732,
      "learning_rate": 7.597676311475796e-06,
      "loss": 0.4707,
      "step": 37624
    },
    {
      "epoch": 1.1558074524621387,
      "grad_norm": 0.4437093734741211,
      "learning_rate": 7.5972071895231085e-06,
      "loss": 0.5008,
      "step": 37625
    },
    {
      "epoch": 1.1558381715970878,
      "grad_norm": 0.37570351362228394,
      "learning_rate": 7.5967380731823086e-06,
      "loss": 0.4943,
      "step": 37626
    },
    {
      "epoch": 1.155868890732037,
      "grad_norm": 0.4145309627056122,
      "learning_rate": 7.596268962454499e-06,
      "loss": 0.4778,
      "step": 37627
    },
    {
      "epoch": 1.155899609866986,
      "grad_norm": 0.38806360960006714,
      "learning_rate": 7.595799857340764e-06,
      "loss": 0.5384,
      "step": 37628
    },
    {
      "epoch": 1.1559303290019354,
      "grad_norm": 0.41031283140182495,
      "learning_rate": 7.595330757842213e-06,
      "loss": 0.4539,
      "step": 37629
    },
    {
      "epoch": 1.1559610481368845,
      "grad_norm": 0.40506914258003235,
      "learning_rate": 7.594861663959929e-06,
      "loss": 0.5331,
      "step": 37630
    },
    {
      "epoch": 1.1559917672718336,
      "grad_norm": 0.4177742302417755,
      "learning_rate": 7.594392575695021e-06,
      "loss": 0.5271,
      "step": 37631
    },
    {
      "epoch": 1.1560224864067827,
      "grad_norm": 0.375117689371109,
      "learning_rate": 7.593923493048572e-06,
      "loss": 0.4765,
      "step": 37632
    },
    {
      "epoch": 1.1560532055417319,
      "grad_norm": 0.4552232027053833,
      "learning_rate": 7.593454416021684e-06,
      "loss": 0.5314,
      "step": 37633
    },
    {
      "epoch": 1.1560839246766812,
      "grad_norm": 0.36169177293777466,
      "learning_rate": 7.59298534461545e-06,
      "loss": 0.5043,
      "step": 37634
    },
    {
      "epoch": 1.1561146438116303,
      "grad_norm": 0.4211994707584381,
      "learning_rate": 7.5925162788309695e-06,
      "loss": 0.5118,
      "step": 37635
    },
    {
      "epoch": 1.1561453629465794,
      "grad_norm": 0.3930290639400482,
      "learning_rate": 7.592047218669332e-06,
      "loss": 0.5341,
      "step": 37636
    },
    {
      "epoch": 1.1561760820815286,
      "grad_norm": 0.37670350074768066,
      "learning_rate": 7.5915781641316385e-06,
      "loss": 0.5084,
      "step": 37637
    },
    {
      "epoch": 1.1562068012164777,
      "grad_norm": 0.426120787858963,
      "learning_rate": 7.591109115218982e-06,
      "loss": 0.4696,
      "step": 37638
    },
    {
      "epoch": 1.1562375203514268,
      "grad_norm": 0.45022425055503845,
      "learning_rate": 7.590640071932459e-06,
      "loss": 0.5231,
      "step": 37639
    },
    {
      "epoch": 1.1562682394863761,
      "grad_norm": 0.41049686074256897,
      "learning_rate": 7.5901710342731626e-06,
      "loss": 0.5576,
      "step": 37640
    },
    {
      "epoch": 1.1562989586213253,
      "grad_norm": 0.38624072074890137,
      "learning_rate": 7.589702002242191e-06,
      "loss": 0.4527,
      "step": 37641
    },
    {
      "epoch": 1.1563296777562744,
      "grad_norm": 0.4398072361946106,
      "learning_rate": 7.5892329758406395e-06,
      "loss": 0.5486,
      "step": 37642
    },
    {
      "epoch": 1.1563603968912235,
      "grad_norm": 0.4039018452167511,
      "learning_rate": 7.5887639550696014e-06,
      "loss": 0.491,
      "step": 37643
    },
    {
      "epoch": 1.1563911160261726,
      "grad_norm": 0.3753493130207062,
      "learning_rate": 7.588294939930175e-06,
      "loss": 0.4474,
      "step": 37644
    },
    {
      "epoch": 1.156421835161122,
      "grad_norm": 0.36921367049217224,
      "learning_rate": 7.587825930423452e-06,
      "loss": 0.4334,
      "step": 37645
    },
    {
      "epoch": 1.156452554296071,
      "grad_norm": 0.4302331209182739,
      "learning_rate": 7.5873569265505335e-06,
      "loss": 0.5229,
      "step": 37646
    },
    {
      "epoch": 1.1564832734310202,
      "grad_norm": 0.3735713064670563,
      "learning_rate": 7.586887928312507e-06,
      "loss": 0.4347,
      "step": 37647
    },
    {
      "epoch": 1.1565139925659693,
      "grad_norm": 0.4625169038772583,
      "learning_rate": 7.5864189357104765e-06,
      "loss": 0.5495,
      "step": 37648
    },
    {
      "epoch": 1.1565447117009184,
      "grad_norm": 0.37724971771240234,
      "learning_rate": 7.5859499487455304e-06,
      "loss": 0.4982,
      "step": 37649
    },
    {
      "epoch": 1.1565754308358676,
      "grad_norm": 0.3799176514148712,
      "learning_rate": 7.585480967418768e-06,
      "loss": 0.5213,
      "step": 37650
    },
    {
      "epoch": 1.156606149970817,
      "grad_norm": 0.38072118163108826,
      "learning_rate": 7.585011991731283e-06,
      "loss": 0.3935,
      "step": 37651
    },
    {
      "epoch": 1.156636869105766,
      "grad_norm": 0.4952715039253235,
      "learning_rate": 7.584543021684172e-06,
      "loss": 0.4478,
      "step": 37652
    },
    {
      "epoch": 1.1566675882407151,
      "grad_norm": 0.41639798879623413,
      "learning_rate": 7.5840740572785275e-06,
      "loss": 0.5109,
      "step": 37653
    },
    {
      "epoch": 1.1566983073756643,
      "grad_norm": 0.40463194251060486,
      "learning_rate": 7.583605098515451e-06,
      "loss": 0.4613,
      "step": 37654
    },
    {
      "epoch": 1.1567290265106134,
      "grad_norm": 0.3523409962654114,
      "learning_rate": 7.583136145396027e-06,
      "loss": 0.4987,
      "step": 37655
    },
    {
      "epoch": 1.1567597456455627,
      "grad_norm": 0.3710983991622925,
      "learning_rate": 7.582667197921365e-06,
      "loss": 0.437,
      "step": 37656
    },
    {
      "epoch": 1.1567904647805118,
      "grad_norm": 0.4149652421474457,
      "learning_rate": 7.582198256092545e-06,
      "loss": 0.4862,
      "step": 37657
    },
    {
      "epoch": 1.156821183915461,
      "grad_norm": 0.37121066451072693,
      "learning_rate": 7.5817293199106755e-06,
      "loss": 0.4674,
      "step": 37658
    },
    {
      "epoch": 1.15685190305041,
      "grad_norm": 0.3635012209415436,
      "learning_rate": 7.581260389376841e-06,
      "loss": 0.4619,
      "step": 37659
    },
    {
      "epoch": 1.1568826221853592,
      "grad_norm": 0.4269960820674896,
      "learning_rate": 7.580791464492143e-06,
      "loss": 0.4589,
      "step": 37660
    },
    {
      "epoch": 1.1569133413203083,
      "grad_norm": 0.37677696347236633,
      "learning_rate": 7.580322545257681e-06,
      "loss": 0.4336,
      "step": 37661
    },
    {
      "epoch": 1.1569440604552577,
      "grad_norm": 0.36093297600746155,
      "learning_rate": 7.579853631674537e-06,
      "loss": 0.4923,
      "step": 37662
    },
    {
      "epoch": 1.1569747795902068,
      "grad_norm": 0.4029397666454315,
      "learning_rate": 7.5793847237438215e-06,
      "loss": 0.4908,
      "step": 37663
    },
    {
      "epoch": 1.157005498725156,
      "grad_norm": 0.42819321155548096,
      "learning_rate": 7.5789158214666144e-06,
      "loss": 0.4956,
      "step": 37664
    },
    {
      "epoch": 1.157036217860105,
      "grad_norm": 0.4192494750022888,
      "learning_rate": 7.5784469248440265e-06,
      "loss": 0.5069,
      "step": 37665
    },
    {
      "epoch": 1.1570669369950541,
      "grad_norm": 0.38323044776916504,
      "learning_rate": 7.577978033877137e-06,
      "loss": 0.5432,
      "step": 37666
    },
    {
      "epoch": 1.1570976561300035,
      "grad_norm": 0.37719932198524475,
      "learning_rate": 7.577509148567056e-06,
      "loss": 0.492,
      "step": 37667
    },
    {
      "epoch": 1.1571283752649526,
      "grad_norm": 0.3736550509929657,
      "learning_rate": 7.577040268914867e-06,
      "loss": 0.5046,
      "step": 37668
    },
    {
      "epoch": 1.1571590943999017,
      "grad_norm": 0.4132552742958069,
      "learning_rate": 7.5765713949216724e-06,
      "loss": 0.5263,
      "step": 37669
    },
    {
      "epoch": 1.1571898135348508,
      "grad_norm": 0.5634324550628662,
      "learning_rate": 7.576102526588561e-06,
      "loss": 0.5474,
      "step": 37670
    },
    {
      "epoch": 1.1572205326698,
      "grad_norm": 0.3925916254520416,
      "learning_rate": 7.575633663916635e-06,
      "loss": 0.3801,
      "step": 37671
    },
    {
      "epoch": 1.157251251804749,
      "grad_norm": 0.4081023037433624,
      "learning_rate": 7.575164806906984e-06,
      "loss": 0.4855,
      "step": 37672
    },
    {
      "epoch": 1.1572819709396984,
      "grad_norm": 0.4038010239601135,
      "learning_rate": 7.574695955560706e-06,
      "loss": 0.5076,
      "step": 37673
    },
    {
      "epoch": 1.1573126900746475,
      "grad_norm": 0.36065956950187683,
      "learning_rate": 7.5742271098788935e-06,
      "loss": 0.4399,
      "step": 37674
    },
    {
      "epoch": 1.1573434092095967,
      "grad_norm": 0.3726087212562561,
      "learning_rate": 7.573758269862644e-06,
      "loss": 0.4981,
      "step": 37675
    },
    {
      "epoch": 1.1573741283445458,
      "grad_norm": 0.5084359049797058,
      "learning_rate": 7.57328943551305e-06,
      "loss": 0.4238,
      "step": 37676
    },
    {
      "epoch": 1.157404847479495,
      "grad_norm": 0.4195747673511505,
      "learning_rate": 7.5728206068312105e-06,
      "loss": 0.5244,
      "step": 37677
    },
    {
      "epoch": 1.1574355666144442,
      "grad_norm": 0.36640456318855286,
      "learning_rate": 7.572351783818216e-06,
      "loss": 0.4889,
      "step": 37678
    },
    {
      "epoch": 1.1574662857493934,
      "grad_norm": 0.4592973291873932,
      "learning_rate": 7.571882966475164e-06,
      "loss": 0.4821,
      "step": 37679
    },
    {
      "epoch": 1.1574970048843425,
      "grad_norm": 0.38591834902763367,
      "learning_rate": 7.571414154803149e-06,
      "loss": 0.4701,
      "step": 37680
    },
    {
      "epoch": 1.1575277240192916,
      "grad_norm": 0.46890199184417725,
      "learning_rate": 7.5709453488032655e-06,
      "loss": 0.499,
      "step": 37681
    },
    {
      "epoch": 1.1575584431542407,
      "grad_norm": 0.42654162645339966,
      "learning_rate": 7.570476548476611e-06,
      "loss": 0.418,
      "step": 37682
    },
    {
      "epoch": 1.1575891622891898,
      "grad_norm": 0.41741424798965454,
      "learning_rate": 7.570007753824274e-06,
      "loss": 0.5702,
      "step": 37683
    },
    {
      "epoch": 1.1576198814241392,
      "grad_norm": 0.3826674818992615,
      "learning_rate": 7.569538964847359e-06,
      "loss": 0.5347,
      "step": 37684
    },
    {
      "epoch": 1.1576506005590883,
      "grad_norm": 0.37284570932388306,
      "learning_rate": 7.569070181546951e-06,
      "loss": 0.4657,
      "step": 37685
    },
    {
      "epoch": 1.1576813196940374,
      "grad_norm": 0.4256347119808197,
      "learning_rate": 7.568601403924152e-06,
      "loss": 0.4504,
      "step": 37686
    },
    {
      "epoch": 1.1577120388289865,
      "grad_norm": 0.42670008540153503,
      "learning_rate": 7.568132631980052e-06,
      "loss": 0.5096,
      "step": 37687
    },
    {
      "epoch": 1.1577427579639357,
      "grad_norm": 0.3692847788333893,
      "learning_rate": 7.56766386571575e-06,
      "loss": 0.5195,
      "step": 37688
    },
    {
      "epoch": 1.157773477098885,
      "grad_norm": 0.39297133684158325,
      "learning_rate": 7.567195105132337e-06,
      "loss": 0.5202,
      "step": 37689
    },
    {
      "epoch": 1.1578041962338341,
      "grad_norm": 0.4874275028705597,
      "learning_rate": 7.566726350230914e-06,
      "loss": 0.5034,
      "step": 37690
    },
    {
      "epoch": 1.1578349153687832,
      "grad_norm": 0.3858906030654907,
      "learning_rate": 7.5662576010125654e-06,
      "loss": 0.4895,
      "step": 37691
    },
    {
      "epoch": 1.1578656345037324,
      "grad_norm": 0.4053008556365967,
      "learning_rate": 7.565788857478398e-06,
      "loss": 0.5618,
      "step": 37692
    },
    {
      "epoch": 1.1578963536386815,
      "grad_norm": 0.41155436635017395,
      "learning_rate": 7.565320119629495e-06,
      "loss": 0.4926,
      "step": 37693
    },
    {
      "epoch": 1.1579270727736306,
      "grad_norm": 0.3799072206020355,
      "learning_rate": 7.564851387466963e-06,
      "loss": 0.5377,
      "step": 37694
    },
    {
      "epoch": 1.15795779190858,
      "grad_norm": 0.39241188764572144,
      "learning_rate": 7.564382660991887e-06,
      "loss": 0.4865,
      "step": 37695
    },
    {
      "epoch": 1.157988511043529,
      "grad_norm": 0.3920230567455292,
      "learning_rate": 7.563913940205362e-06,
      "loss": 0.4678,
      "step": 37696
    },
    {
      "epoch": 1.1580192301784782,
      "grad_norm": 0.3735315501689911,
      "learning_rate": 7.563445225108493e-06,
      "loss": 0.4953,
      "step": 37697
    },
    {
      "epoch": 1.1580499493134273,
      "grad_norm": 0.43058088421821594,
      "learning_rate": 7.562976515702361e-06,
      "loss": 0.4965,
      "step": 37698
    },
    {
      "epoch": 1.1580806684483764,
      "grad_norm": 0.4183669090270996,
      "learning_rate": 7.5625078119880754e-06,
      "loss": 0.5305,
      "step": 37699
    },
    {
      "epoch": 1.1581113875833258,
      "grad_norm": 0.3648013472557068,
      "learning_rate": 7.562039113966716e-06,
      "loss": 0.4784,
      "step": 37700
    },
    {
      "epoch": 1.1581421067182749,
      "grad_norm": 1.2031513452529907,
      "learning_rate": 7.56157042163939e-06,
      "loss": 0.5442,
      "step": 37701
    },
    {
      "epoch": 1.158172825853224,
      "grad_norm": 0.3542778789997101,
      "learning_rate": 7.561101735007183e-06,
      "loss": 0.4824,
      "step": 37702
    },
    {
      "epoch": 1.1582035449881731,
      "grad_norm": 0.4123345911502838,
      "learning_rate": 7.560633054071196e-06,
      "loss": 0.4814,
      "step": 37703
    },
    {
      "epoch": 1.1582342641231222,
      "grad_norm": 0.39553102850914,
      "learning_rate": 7.5601643788325176e-06,
      "loss": 0.5296,
      "step": 37704
    },
    {
      "epoch": 1.1582649832580714,
      "grad_norm": 0.39312341809272766,
      "learning_rate": 7.559695709292249e-06,
      "loss": 0.4576,
      "step": 37705
    },
    {
      "epoch": 1.1582957023930207,
      "grad_norm": 0.42198577523231506,
      "learning_rate": 7.559227045451478e-06,
      "loss": 0.4374,
      "step": 37706
    },
    {
      "epoch": 1.1583264215279698,
      "grad_norm": 0.38463184237480164,
      "learning_rate": 7.558758387311306e-06,
      "loss": 0.4487,
      "step": 37707
    },
    {
      "epoch": 1.158357140662919,
      "grad_norm": 0.3825833797454834,
      "learning_rate": 7.558289734872821e-06,
      "loss": 0.4705,
      "step": 37708
    },
    {
      "epoch": 1.158387859797868,
      "grad_norm": 0.38987916707992554,
      "learning_rate": 7.557821088137124e-06,
      "loss": 0.4455,
      "step": 37709
    },
    {
      "epoch": 1.1584185789328172,
      "grad_norm": 0.4025222957134247,
      "learning_rate": 7.557352447105304e-06,
      "loss": 0.4961,
      "step": 37710
    },
    {
      "epoch": 1.1584492980677665,
      "grad_norm": 0.3605562746524811,
      "learning_rate": 7.556883811778461e-06,
      "loss": 0.5396,
      "step": 37711
    },
    {
      "epoch": 1.1584800172027157,
      "grad_norm": 0.3952379822731018,
      "learning_rate": 7.556415182157682e-06,
      "loss": 0.4657,
      "step": 37712
    },
    {
      "epoch": 1.1585107363376648,
      "grad_norm": 0.564749538898468,
      "learning_rate": 7.5559465582440705e-06,
      "loss": 0.5185,
      "step": 37713
    },
    {
      "epoch": 1.158541455472614,
      "grad_norm": 0.4122146964073181,
      "learning_rate": 7.5554779400387136e-06,
      "loss": 0.4775,
      "step": 37714
    },
    {
      "epoch": 1.158572174607563,
      "grad_norm": 0.35026776790618896,
      "learning_rate": 7.5550093275427086e-06,
      "loss": 0.4603,
      "step": 37715
    },
    {
      "epoch": 1.1586028937425121,
      "grad_norm": 0.38452643156051636,
      "learning_rate": 7.554540720757151e-06,
      "loss": 0.4172,
      "step": 37716
    },
    {
      "epoch": 1.1586336128774612,
      "grad_norm": 0.4009579122066498,
      "learning_rate": 7.554072119683133e-06,
      "loss": 0.4575,
      "step": 37717
    },
    {
      "epoch": 1.1586643320124106,
      "grad_norm": 0.4570568799972534,
      "learning_rate": 7.553603524321753e-06,
      "loss": 0.4292,
      "step": 37718
    },
    {
      "epoch": 1.1586950511473597,
      "grad_norm": 0.401983380317688,
      "learning_rate": 7.5531349346741015e-06,
      "loss": 0.4982,
      "step": 37719
    },
    {
      "epoch": 1.1587257702823088,
      "grad_norm": 0.4177778363227844,
      "learning_rate": 7.552666350741276e-06,
      "loss": 0.58,
      "step": 37720
    },
    {
      "epoch": 1.158756489417258,
      "grad_norm": 0.39648720622062683,
      "learning_rate": 7.552197772524365e-06,
      "loss": 0.4706,
      "step": 37721
    },
    {
      "epoch": 1.1587872085522073,
      "grad_norm": 0.42205849289894104,
      "learning_rate": 7.551729200024471e-06,
      "loss": 0.5704,
      "step": 37722
    },
    {
      "epoch": 1.1588179276871564,
      "grad_norm": 0.5735269784927368,
      "learning_rate": 7.5512606332426816e-06,
      "loss": 0.424,
      "step": 37723
    },
    {
      "epoch": 1.1588486468221055,
      "grad_norm": 0.38437896966934204,
      "learning_rate": 7.5507920721800985e-06,
      "loss": 0.5354,
      "step": 37724
    },
    {
      "epoch": 1.1588793659570547,
      "grad_norm": 0.42901211977005005,
      "learning_rate": 7.550323516837805e-06,
      "loss": 0.4788,
      "step": 37725
    },
    {
      "epoch": 1.1589100850920038,
      "grad_norm": 0.43300527334213257,
      "learning_rate": 7.54985496721691e-06,
      "loss": 0.5929,
      "step": 37726
    },
    {
      "epoch": 1.158940804226953,
      "grad_norm": 0.4021817743778229,
      "learning_rate": 7.549386423318491e-06,
      "loss": 0.4316,
      "step": 37727
    },
    {
      "epoch": 1.158971523361902,
      "grad_norm": 0.3919947147369385,
      "learning_rate": 7.548917885143659e-06,
      "loss": 0.4546,
      "step": 37728
    },
    {
      "epoch": 1.1590022424968514,
      "grad_norm": 0.36586377024650574,
      "learning_rate": 7.5484493526934946e-06,
      "loss": 0.4883,
      "step": 37729
    },
    {
      "epoch": 1.1590329616318005,
      "grad_norm": 0.38100582361221313,
      "learning_rate": 7.547980825969102e-06,
      "loss": 0.4396,
      "step": 37730
    },
    {
      "epoch": 1.1590636807667496,
      "grad_norm": 0.3825877606868744,
      "learning_rate": 7.5475123049715696e-06,
      "loss": 0.5308,
      "step": 37731
    },
    {
      "epoch": 1.1590943999016987,
      "grad_norm": 0.3870520293712616,
      "learning_rate": 7.547043789701994e-06,
      "loss": 0.4464,
      "step": 37732
    },
    {
      "epoch": 1.1591251190366478,
      "grad_norm": 0.4213481843471527,
      "learning_rate": 7.546575280161468e-06,
      "loss": 0.5495,
      "step": 37733
    },
    {
      "epoch": 1.1591558381715972,
      "grad_norm": 0.45758700370788574,
      "learning_rate": 7.546106776351083e-06,
      "loss": 0.4823,
      "step": 37734
    },
    {
      "epoch": 1.1591865573065463,
      "grad_norm": 0.3704661726951599,
      "learning_rate": 7.545638278271945e-06,
      "loss": 0.4035,
      "step": 37735
    },
    {
      "epoch": 1.1592172764414954,
      "grad_norm": 0.41441231966018677,
      "learning_rate": 7.545169785925136e-06,
      "loss": 0.4073,
      "step": 37736
    },
    {
      "epoch": 1.1592479955764445,
      "grad_norm": 0.40015071630477905,
      "learning_rate": 7.544701299311756e-06,
      "loss": 0.5318,
      "step": 37737
    },
    {
      "epoch": 1.1592787147113937,
      "grad_norm": 0.39758121967315674,
      "learning_rate": 7.544232818432895e-06,
      "loss": 0.5281,
      "step": 37738
    },
    {
      "epoch": 1.1593094338463428,
      "grad_norm": 0.4040605425834656,
      "learning_rate": 7.543764343289653e-06,
      "loss": 0.598,
      "step": 37739
    },
    {
      "epoch": 1.1593401529812921,
      "grad_norm": 0.40324845910072327,
      "learning_rate": 7.543295873883117e-06,
      "loss": 0.4185,
      "step": 37740
    },
    {
      "epoch": 1.1593708721162412,
      "grad_norm": 0.3986642062664032,
      "learning_rate": 7.542827410214388e-06,
      "loss": 0.4723,
      "step": 37741
    },
    {
      "epoch": 1.1594015912511904,
      "grad_norm": 0.435038298368454,
      "learning_rate": 7.542358952284557e-06,
      "loss": 0.4497,
      "step": 37742
    },
    {
      "epoch": 1.1594323103861395,
      "grad_norm": 0.4593387246131897,
      "learning_rate": 7.541890500094718e-06,
      "loss": 0.5475,
      "step": 37743
    },
    {
      "epoch": 1.1594630295210886,
      "grad_norm": 0.3454752564430237,
      "learning_rate": 7.541422053645964e-06,
      "loss": 0.4559,
      "step": 37744
    },
    {
      "epoch": 1.159493748656038,
      "grad_norm": 0.43370771408081055,
      "learning_rate": 7.540953612939393e-06,
      "loss": 0.4334,
      "step": 37745
    },
    {
      "epoch": 1.159524467790987,
      "grad_norm": 0.4353458881378174,
      "learning_rate": 7.540485177976094e-06,
      "loss": 0.5178,
      "step": 37746
    },
    {
      "epoch": 1.1595551869259362,
      "grad_norm": 0.3803175985813141,
      "learning_rate": 7.540016748757166e-06,
      "loss": 0.5438,
      "step": 37747
    },
    {
      "epoch": 1.1595859060608853,
      "grad_norm": 0.4280395805835724,
      "learning_rate": 7.539548325283699e-06,
      "loss": 0.4978,
      "step": 37748
    },
    {
      "epoch": 1.1596166251958344,
      "grad_norm": 0.42957204580307007,
      "learning_rate": 7.53907990755679e-06,
      "loss": 0.5104,
      "step": 37749
    },
    {
      "epoch": 1.1596473443307835,
      "grad_norm": 0.41868504881858826,
      "learning_rate": 7.53861149557753e-06,
      "loss": 0.4866,
      "step": 37750
    },
    {
      "epoch": 1.1596780634657329,
      "grad_norm": 0.41457945108413696,
      "learning_rate": 7.538143089347014e-06,
      "loss": 0.5579,
      "step": 37751
    },
    {
      "epoch": 1.159708782600682,
      "grad_norm": 0.3659287989139557,
      "learning_rate": 7.53767468886634e-06,
      "loss": 0.5036,
      "step": 37752
    },
    {
      "epoch": 1.1597395017356311,
      "grad_norm": 0.41242241859436035,
      "learning_rate": 7.5372062941365965e-06,
      "loss": 0.5458,
      "step": 37753
    },
    {
      "epoch": 1.1597702208705802,
      "grad_norm": 0.37030622363090515,
      "learning_rate": 7.536737905158882e-06,
      "loss": 0.5523,
      "step": 37754
    },
    {
      "epoch": 1.1598009400055294,
      "grad_norm": 0.40763169527053833,
      "learning_rate": 7.536269521934285e-06,
      "loss": 0.4898,
      "step": 37755
    },
    {
      "epoch": 1.1598316591404787,
      "grad_norm": 0.3800148665904999,
      "learning_rate": 7.535801144463905e-06,
      "loss": 0.4522,
      "step": 37756
    },
    {
      "epoch": 1.1598623782754278,
      "grad_norm": 0.36372360587120056,
      "learning_rate": 7.535332772748831e-06,
      "loss": 0.4494,
      "step": 37757
    },
    {
      "epoch": 1.159893097410377,
      "grad_norm": 0.41906648874282837,
      "learning_rate": 7.534864406790165e-06,
      "loss": 0.5021,
      "step": 37758
    },
    {
      "epoch": 1.159923816545326,
      "grad_norm": 0.35352402925491333,
      "learning_rate": 7.534396046588989e-06,
      "loss": 0.4721,
      "step": 37759
    },
    {
      "epoch": 1.1599545356802752,
      "grad_norm": 0.4126661717891693,
      "learning_rate": 7.533927692146409e-06,
      "loss": 0.5308,
      "step": 37760
    },
    {
      "epoch": 1.1599852548152243,
      "grad_norm": 0.40684953331947327,
      "learning_rate": 7.533459343463506e-06,
      "loss": 0.5,
      "step": 37761
    },
    {
      "epoch": 1.1600159739501736,
      "grad_norm": 0.3755864202976227,
      "learning_rate": 7.532991000541387e-06,
      "loss": 0.4746,
      "step": 37762
    },
    {
      "epoch": 1.1600466930851228,
      "grad_norm": 0.3780556321144104,
      "learning_rate": 7.532522663381135e-06,
      "loss": 0.4683,
      "step": 37763
    },
    {
      "epoch": 1.1600774122200719,
      "grad_norm": 0.48607662320137024,
      "learning_rate": 7.532054331983856e-06,
      "loss": 0.5057,
      "step": 37764
    },
    {
      "epoch": 1.160108131355021,
      "grad_norm": 0.42031431198120117,
      "learning_rate": 7.53158600635063e-06,
      "loss": 0.4844,
      "step": 37765
    },
    {
      "epoch": 1.1601388504899701,
      "grad_norm": 0.37826862931251526,
      "learning_rate": 7.5311176864825595e-06,
      "loss": 0.5255,
      "step": 37766
    },
    {
      "epoch": 1.1601695696249195,
      "grad_norm": 0.4322376549243927,
      "learning_rate": 7.530649372380735e-06,
      "loss": 0.5442,
      "step": 37767
    },
    {
      "epoch": 1.1602002887598686,
      "grad_norm": 0.4139716625213623,
      "learning_rate": 7.5301810640462525e-06,
      "loss": 0.4558,
      "step": 37768
    },
    {
      "epoch": 1.1602310078948177,
      "grad_norm": 0.3936997652053833,
      "learning_rate": 7.529712761480203e-06,
      "loss": 0.473,
      "step": 37769
    },
    {
      "epoch": 1.1602617270297668,
      "grad_norm": 0.41604751348495483,
      "learning_rate": 7.52924446468368e-06,
      "loss": 0.4914,
      "step": 37770
    },
    {
      "epoch": 1.160292446164716,
      "grad_norm": 0.40317463874816895,
      "learning_rate": 7.528776173657786e-06,
      "loss": 0.5502,
      "step": 37771
    },
    {
      "epoch": 1.160323165299665,
      "grad_norm": 0.3956168293952942,
      "learning_rate": 7.528307888403602e-06,
      "loss": 0.478,
      "step": 37772
    },
    {
      "epoch": 1.1603538844346144,
      "grad_norm": 0.3752398192882538,
      "learning_rate": 7.527839608922231e-06,
      "loss": 0.4514,
      "step": 37773
    },
    {
      "epoch": 1.1603846035695635,
      "grad_norm": 0.35188737511634827,
      "learning_rate": 7.52737133521476e-06,
      "loss": 0.4524,
      "step": 37774
    },
    {
      "epoch": 1.1604153227045126,
      "grad_norm": 0.3810655474662781,
      "learning_rate": 7.526903067282288e-06,
      "loss": 0.5037,
      "step": 37775
    },
    {
      "epoch": 1.1604460418394618,
      "grad_norm": 0.39951783418655396,
      "learning_rate": 7.526434805125906e-06,
      "loss": 0.4568,
      "step": 37776
    },
    {
      "epoch": 1.1604767609744109,
      "grad_norm": 0.37867146730422974,
      "learning_rate": 7.525966548746709e-06,
      "loss": 0.4632,
      "step": 37777
    },
    {
      "epoch": 1.1605074801093602,
      "grad_norm": 0.4098640978336334,
      "learning_rate": 7.525498298145788e-06,
      "loss": 0.4682,
      "step": 37778
    },
    {
      "epoch": 1.1605381992443093,
      "grad_norm": 0.36286216974258423,
      "learning_rate": 7.525030053324241e-06,
      "loss": 0.4579,
      "step": 37779
    },
    {
      "epoch": 1.1605689183792585,
      "grad_norm": 0.5522835850715637,
      "learning_rate": 7.524561814283158e-06,
      "loss": 0.4864,
      "step": 37780
    },
    {
      "epoch": 1.1605996375142076,
      "grad_norm": 0.4033557176589966,
      "learning_rate": 7.524093581023635e-06,
      "loss": 0.4338,
      "step": 37781
    },
    {
      "epoch": 1.1606303566491567,
      "grad_norm": 0.37071433663368225,
      "learning_rate": 7.523625353546762e-06,
      "loss": 0.4462,
      "step": 37782
    },
    {
      "epoch": 1.1606610757841058,
      "grad_norm": 0.401541143655777,
      "learning_rate": 7.523157131853637e-06,
      "loss": 0.5421,
      "step": 37783
    },
    {
      "epoch": 1.1606917949190552,
      "grad_norm": 0.42920124530792236,
      "learning_rate": 7.522688915945349e-06,
      "loss": 0.5246,
      "step": 37784
    },
    {
      "epoch": 1.1607225140540043,
      "grad_norm": 0.3808244466781616,
      "learning_rate": 7.5222207058229965e-06,
      "loss": 0.5566,
      "step": 37785
    },
    {
      "epoch": 1.1607532331889534,
      "grad_norm": 0.38671648502349854,
      "learning_rate": 7.521752501487669e-06,
      "loss": 0.5158,
      "step": 37786
    },
    {
      "epoch": 1.1607839523239025,
      "grad_norm": 0.40143340826034546,
      "learning_rate": 7.521284302940461e-06,
      "loss": 0.4472,
      "step": 37787
    },
    {
      "epoch": 1.1608146714588516,
      "grad_norm": 0.37270742654800415,
      "learning_rate": 7.52081611018247e-06,
      "loss": 0.5021,
      "step": 37788
    },
    {
      "epoch": 1.160845390593801,
      "grad_norm": 0.3946525454521179,
      "learning_rate": 7.520347923214782e-06,
      "loss": 0.4964,
      "step": 37789
    },
    {
      "epoch": 1.16087610972875,
      "grad_norm": 0.38762685656547546,
      "learning_rate": 7.519879742038499e-06,
      "loss": 0.4446,
      "step": 37790
    },
    {
      "epoch": 1.1609068288636992,
      "grad_norm": 0.43595409393310547,
      "learning_rate": 7.519411566654707e-06,
      "loss": 0.4243,
      "step": 37791
    },
    {
      "epoch": 1.1609375479986483,
      "grad_norm": 0.41277799010276794,
      "learning_rate": 7.518943397064503e-06,
      "loss": 0.5247,
      "step": 37792
    },
    {
      "epoch": 1.1609682671335975,
      "grad_norm": 0.40174201130867004,
      "learning_rate": 7.51847523326898e-06,
      "loss": 0.4541,
      "step": 37793
    },
    {
      "epoch": 1.1609989862685466,
      "grad_norm": 0.367910772562027,
      "learning_rate": 7.518007075269235e-06,
      "loss": 0.4911,
      "step": 37794
    },
    {
      "epoch": 1.161029705403496,
      "grad_norm": 0.3706749677658081,
      "learning_rate": 7.517538923066351e-06,
      "loss": 0.4326,
      "step": 37795
    },
    {
      "epoch": 1.161060424538445,
      "grad_norm": 0.4100418984889984,
      "learning_rate": 7.517070776661435e-06,
      "loss": 0.4607,
      "step": 37796
    },
    {
      "epoch": 1.1610911436733942,
      "grad_norm": 0.3573119640350342,
      "learning_rate": 7.516602636055566e-06,
      "loss": 0.4154,
      "step": 37797
    },
    {
      "epoch": 1.1611218628083433,
      "grad_norm": 0.42447900772094727,
      "learning_rate": 7.516134501249853e-06,
      "loss": 0.5207,
      "step": 37798
    },
    {
      "epoch": 1.1611525819432924,
      "grad_norm": 0.39317944645881653,
      "learning_rate": 7.515666372245377e-06,
      "loss": 0.4276,
      "step": 37799
    },
    {
      "epoch": 1.1611833010782417,
      "grad_norm": 0.4109950661659241,
      "learning_rate": 7.515198249043237e-06,
      "loss": 0.5062,
      "step": 37800
    },
    {
      "epoch": 1.1612140202131909,
      "grad_norm": 0.3981681764125824,
      "learning_rate": 7.514730131644523e-06,
      "loss": 0.5309,
      "step": 37801
    },
    {
      "epoch": 1.16124473934814,
      "grad_norm": 0.3535238802433014,
      "learning_rate": 7.514262020050333e-06,
      "loss": 0.4508,
      "step": 37802
    },
    {
      "epoch": 1.161275458483089,
      "grad_norm": 0.3662507236003876,
      "learning_rate": 7.513793914261756e-06,
      "loss": 0.449,
      "step": 37803
    },
    {
      "epoch": 1.1613061776180382,
      "grad_norm": 0.43304938077926636,
      "learning_rate": 7.513325814279888e-06,
      "loss": 0.5078,
      "step": 37804
    },
    {
      "epoch": 1.1613368967529873,
      "grad_norm": 0.36510366201400757,
      "learning_rate": 7.5128577201058194e-06,
      "loss": 0.5086,
      "step": 37805
    },
    {
      "epoch": 1.1613676158879367,
      "grad_norm": 0.4112796187400818,
      "learning_rate": 7.512389631740645e-06,
      "loss": 0.5375,
      "step": 37806
    },
    {
      "epoch": 1.1613983350228858,
      "grad_norm": 0.39694449305534363,
      "learning_rate": 7.511921549185461e-06,
      "loss": 0.4816,
      "step": 37807
    },
    {
      "epoch": 1.161429054157835,
      "grad_norm": 0.40168941020965576,
      "learning_rate": 7.5114534724413565e-06,
      "loss": 0.4951,
      "step": 37808
    },
    {
      "epoch": 1.161459773292784,
      "grad_norm": 0.4054115414619446,
      "learning_rate": 7.510985401509427e-06,
      "loss": 0.4448,
      "step": 37809
    },
    {
      "epoch": 1.1614904924277332,
      "grad_norm": 0.4846842586994171,
      "learning_rate": 7.510517336390763e-06,
      "loss": 0.5525,
      "step": 37810
    },
    {
      "epoch": 1.1615212115626825,
      "grad_norm": 0.39458709955215454,
      "learning_rate": 7.5100492770864634e-06,
      "loss": 0.4404,
      "step": 37811
    },
    {
      "epoch": 1.1615519306976316,
      "grad_norm": 0.41206061840057373,
      "learning_rate": 7.5095812235976125e-06,
      "loss": 0.424,
      "step": 37812
    },
    {
      "epoch": 1.1615826498325807,
      "grad_norm": 0.3862597346305847,
      "learning_rate": 7.509113175925313e-06,
      "loss": 0.467,
      "step": 37813
    },
    {
      "epoch": 1.1616133689675299,
      "grad_norm": 0.3747875690460205,
      "learning_rate": 7.508645134070651e-06,
      "loss": 0.4132,
      "step": 37814
    },
    {
      "epoch": 1.161644088102479,
      "grad_norm": 0.39163681864738464,
      "learning_rate": 7.508177098034724e-06,
      "loss": 0.489,
      "step": 37815
    },
    {
      "epoch": 1.161674807237428,
      "grad_norm": 0.3835715651512146,
      "learning_rate": 7.507709067818623e-06,
      "loss": 0.5093,
      "step": 37816
    },
    {
      "epoch": 1.1617055263723775,
      "grad_norm": 0.4003736674785614,
      "learning_rate": 7.507241043423441e-06,
      "loss": 0.4591,
      "step": 37817
    },
    {
      "epoch": 1.1617362455073266,
      "grad_norm": 0.41080451011657715,
      "learning_rate": 7.506773024850271e-06,
      "loss": 0.4875,
      "step": 37818
    },
    {
      "epoch": 1.1617669646422757,
      "grad_norm": 0.42660829424858093,
      "learning_rate": 7.506305012100209e-06,
      "loss": 0.4521,
      "step": 37819
    },
    {
      "epoch": 1.1617976837772248,
      "grad_norm": 0.3821091055870056,
      "learning_rate": 7.505837005174344e-06,
      "loss": 0.4648,
      "step": 37820
    },
    {
      "epoch": 1.161828402912174,
      "grad_norm": 0.40413013100624084,
      "learning_rate": 7.5053690040737715e-06,
      "loss": 0.5366,
      "step": 37821
    },
    {
      "epoch": 1.1618591220471233,
      "grad_norm": 0.40065300464630127,
      "learning_rate": 7.504901008799582e-06,
      "loss": 0.4403,
      "step": 37822
    },
    {
      "epoch": 1.1618898411820724,
      "grad_norm": 0.38516902923583984,
      "learning_rate": 7.504433019352876e-06,
      "loss": 0.4538,
      "step": 37823
    },
    {
      "epoch": 1.1619205603170215,
      "grad_norm": 0.40149474143981934,
      "learning_rate": 7.503965035734734e-06,
      "loss": 0.5117,
      "step": 37824
    },
    {
      "epoch": 1.1619512794519706,
      "grad_norm": 0.3823796212673187,
      "learning_rate": 7.503497057946257e-06,
      "loss": 0.5287,
      "step": 37825
    },
    {
      "epoch": 1.1619819985869198,
      "grad_norm": 0.4130176901817322,
      "learning_rate": 7.50302908598854e-06,
      "loss": 0.4618,
      "step": 37826
    },
    {
      "epoch": 1.1620127177218689,
      "grad_norm": 0.4055701196193695,
      "learning_rate": 7.502561119862671e-06,
      "loss": 0.4976,
      "step": 37827
    },
    {
      "epoch": 1.162043436856818,
      "grad_norm": 0.39046725630760193,
      "learning_rate": 7.50209315956975e-06,
      "loss": 0.5495,
      "step": 37828
    },
    {
      "epoch": 1.1620741559917673,
      "grad_norm": 0.4148443341255188,
      "learning_rate": 7.501625205110857e-06,
      "loss": 0.513,
      "step": 37829
    },
    {
      "epoch": 1.1621048751267165,
      "grad_norm": 0.36608389019966125,
      "learning_rate": 7.5011572564871e-06,
      "loss": 0.4654,
      "step": 37830
    },
    {
      "epoch": 1.1621355942616656,
      "grad_norm": 0.412278950214386,
      "learning_rate": 7.500689313699558e-06,
      "loss": 0.5307,
      "step": 37831
    },
    {
      "epoch": 1.1621663133966147,
      "grad_norm": 0.38766416907310486,
      "learning_rate": 7.500221376749337e-06,
      "loss": 0.4609,
      "step": 37832
    },
    {
      "epoch": 1.162197032531564,
      "grad_norm": 0.42503106594085693,
      "learning_rate": 7.499753445637518e-06,
      "loss": 0.4353,
      "step": 37833
    },
    {
      "epoch": 1.1622277516665132,
      "grad_norm": 0.4583165943622589,
      "learning_rate": 7.4992855203652045e-06,
      "loss": 0.5158,
      "step": 37834
    },
    {
      "epoch": 1.1622584708014623,
      "grad_norm": 0.4292896091938019,
      "learning_rate": 7.4988176009334815e-06,
      "loss": 0.5087,
      "step": 37835
    },
    {
      "epoch": 1.1622891899364114,
      "grad_norm": 0.4611436724662781,
      "learning_rate": 7.498349687343446e-06,
      "loss": 0.4478,
      "step": 37836
    },
    {
      "epoch": 1.1623199090713605,
      "grad_norm": 0.39585044980049133,
      "learning_rate": 7.4978817795961874e-06,
      "loss": 0.4265,
      "step": 37837
    },
    {
      "epoch": 1.1623506282063096,
      "grad_norm": 0.3905349671840668,
      "learning_rate": 7.497413877692803e-06,
      "loss": 0.4957,
      "step": 37838
    },
    {
      "epoch": 1.1623813473412588,
      "grad_norm": 0.3851450979709625,
      "learning_rate": 7.49694598163438e-06,
      "loss": 0.5342,
      "step": 37839
    },
    {
      "epoch": 1.162412066476208,
      "grad_norm": 0.38684096932411194,
      "learning_rate": 7.4964780914220185e-06,
      "loss": 0.4931,
      "step": 37840
    },
    {
      "epoch": 1.1624427856111572,
      "grad_norm": 0.41104787588119507,
      "learning_rate": 7.496010207056803e-06,
      "loss": 0.5345,
      "step": 37841
    },
    {
      "epoch": 1.1624735047461063,
      "grad_norm": 0.4327830672264099,
      "learning_rate": 7.4955423285398335e-06,
      "loss": 0.4907,
      "step": 37842
    },
    {
      "epoch": 1.1625042238810555,
      "grad_norm": 0.40555042028427124,
      "learning_rate": 7.4950744558722e-06,
      "loss": 0.4906,
      "step": 37843
    },
    {
      "epoch": 1.1625349430160046,
      "grad_norm": 0.3939354419708252,
      "learning_rate": 7.494606589054992e-06,
      "loss": 0.4507,
      "step": 37844
    },
    {
      "epoch": 1.162565662150954,
      "grad_norm": 0.42569419741630554,
      "learning_rate": 7.4941387280893084e-06,
      "loss": 0.5384,
      "step": 37845
    },
    {
      "epoch": 1.162596381285903,
      "grad_norm": 0.41693535447120667,
      "learning_rate": 7.493670872976238e-06,
      "loss": 0.4347,
      "step": 37846
    },
    {
      "epoch": 1.1626271004208522,
      "grad_norm": 0.40051308274269104,
      "learning_rate": 7.4932030237168755e-06,
      "loss": 0.4194,
      "step": 37847
    },
    {
      "epoch": 1.1626578195558013,
      "grad_norm": 0.513370931148529,
      "learning_rate": 7.492735180312309e-06,
      "loss": 0.469,
      "step": 37848
    },
    {
      "epoch": 1.1626885386907504,
      "grad_norm": 0.4155104458332062,
      "learning_rate": 7.492267342763637e-06,
      "loss": 0.4803,
      "step": 37849
    },
    {
      "epoch": 1.1627192578256995,
      "grad_norm": 0.37034279108047485,
      "learning_rate": 7.491799511071949e-06,
      "loss": 0.4691,
      "step": 37850
    },
    {
      "epoch": 1.1627499769606489,
      "grad_norm": 0.4898759722709656,
      "learning_rate": 7.49133168523834e-06,
      "loss": 0.4929,
      "step": 37851
    },
    {
      "epoch": 1.162780696095598,
      "grad_norm": 0.4065060317516327,
      "learning_rate": 7.4908638652638984e-06,
      "loss": 0.4913,
      "step": 37852
    },
    {
      "epoch": 1.162811415230547,
      "grad_norm": 0.38637250661849976,
      "learning_rate": 7.490396051149722e-06,
      "loss": 0.4997,
      "step": 37853
    },
    {
      "epoch": 1.1628421343654962,
      "grad_norm": 0.38586103916168213,
      "learning_rate": 7.489928242896899e-06,
      "loss": 0.4817,
      "step": 37854
    },
    {
      "epoch": 1.1628728535004453,
      "grad_norm": 0.4231812059879303,
      "learning_rate": 7.489460440506526e-06,
      "loss": 0.4219,
      "step": 37855
    },
    {
      "epoch": 1.1629035726353947,
      "grad_norm": 0.4261297881603241,
      "learning_rate": 7.488992643979691e-06,
      "loss": 0.3968,
      "step": 37856
    },
    {
      "epoch": 1.1629342917703438,
      "grad_norm": 0.4094599187374115,
      "learning_rate": 7.488524853317494e-06,
      "loss": 0.5448,
      "step": 37857
    },
    {
      "epoch": 1.162965010905293,
      "grad_norm": 0.42660433053970337,
      "learning_rate": 7.488057068521015e-06,
      "loss": 0.4927,
      "step": 37858
    },
    {
      "epoch": 1.162995730040242,
      "grad_norm": 0.38384324312210083,
      "learning_rate": 7.487589289591362e-06,
      "loss": 0.4462,
      "step": 37859
    },
    {
      "epoch": 1.1630264491751912,
      "grad_norm": 0.4432663917541504,
      "learning_rate": 7.487121516529612e-06,
      "loss": 0.4412,
      "step": 37860
    },
    {
      "epoch": 1.1630571683101403,
      "grad_norm": 0.4262882471084595,
      "learning_rate": 7.486653749336867e-06,
      "loss": 0.4401,
      "step": 37861
    },
    {
      "epoch": 1.1630878874450896,
      "grad_norm": 0.4156726896762848,
      "learning_rate": 7.486185988014221e-06,
      "loss": 0.3883,
      "step": 37862
    },
    {
      "epoch": 1.1631186065800387,
      "grad_norm": 0.37558701634407043,
      "learning_rate": 7.4857182325627605e-06,
      "loss": 0.5517,
      "step": 37863
    },
    {
      "epoch": 1.1631493257149879,
      "grad_norm": 0.45516079664230347,
      "learning_rate": 7.4852504829835855e-06,
      "loss": 0.5163,
      "step": 37864
    },
    {
      "epoch": 1.163180044849937,
      "grad_norm": 0.40617263317108154,
      "learning_rate": 7.484782739277777e-06,
      "loss": 0.5054,
      "step": 37865
    },
    {
      "epoch": 1.163210763984886,
      "grad_norm": 0.39002496004104614,
      "learning_rate": 7.484315001446441e-06,
      "loss": 0.4793,
      "step": 37866
    },
    {
      "epoch": 1.1632414831198354,
      "grad_norm": 0.3934631645679474,
      "learning_rate": 7.483847269490655e-06,
      "loss": 0.4368,
      "step": 37867
    },
    {
      "epoch": 1.1632722022547846,
      "grad_norm": 0.38522306084632874,
      "learning_rate": 7.483379543411526e-06,
      "loss": 0.4178,
      "step": 37868
    },
    {
      "epoch": 1.1633029213897337,
      "grad_norm": 0.42578381299972534,
      "learning_rate": 7.482911823210137e-06,
      "loss": 0.5012,
      "step": 37869
    },
    {
      "epoch": 1.1633336405246828,
      "grad_norm": 0.44854483008384705,
      "learning_rate": 7.4824441088875855e-06,
      "loss": 0.4564,
      "step": 37870
    },
    {
      "epoch": 1.163364359659632,
      "grad_norm": 0.3860468864440918,
      "learning_rate": 7.481976400444958e-06,
      "loss": 0.4792,
      "step": 37871
    },
    {
      "epoch": 1.163395078794581,
      "grad_norm": 0.3913397192955017,
      "learning_rate": 7.481508697883353e-06,
      "loss": 0.5281,
      "step": 37872
    },
    {
      "epoch": 1.1634257979295304,
      "grad_norm": 0.3900808095932007,
      "learning_rate": 7.481041001203859e-06,
      "loss": 0.4243,
      "step": 37873
    },
    {
      "epoch": 1.1634565170644795,
      "grad_norm": 0.38394880294799805,
      "learning_rate": 7.480573310407571e-06,
      "loss": 0.4615,
      "step": 37874
    },
    {
      "epoch": 1.1634872361994286,
      "grad_norm": 0.3964335322380066,
      "learning_rate": 7.480105625495579e-06,
      "loss": 0.4811,
      "step": 37875
    },
    {
      "epoch": 1.1635179553343777,
      "grad_norm": 0.4023151695728302,
      "learning_rate": 7.479637946468977e-06,
      "loss": 0.5064,
      "step": 37876
    },
    {
      "epoch": 1.1635486744693269,
      "grad_norm": 0.4052397608757019,
      "learning_rate": 7.479170273328855e-06,
      "loss": 0.4907,
      "step": 37877
    },
    {
      "epoch": 1.1635793936042762,
      "grad_norm": 0.39389094710350037,
      "learning_rate": 7.478702606076309e-06,
      "loss": 0.49,
      "step": 37878
    },
    {
      "epoch": 1.1636101127392253,
      "grad_norm": 0.39796632528305054,
      "learning_rate": 7.478234944712427e-06,
      "loss": 0.5197,
      "step": 37879
    },
    {
      "epoch": 1.1636408318741744,
      "grad_norm": 0.44944167137145996,
      "learning_rate": 7.4777672892383034e-06,
      "loss": 0.5,
      "step": 37880
    },
    {
      "epoch": 1.1636715510091236,
      "grad_norm": 0.5075975060462952,
      "learning_rate": 7.477299639655033e-06,
      "loss": 0.5005,
      "step": 37881
    },
    {
      "epoch": 1.1637022701440727,
      "grad_norm": 0.381767213344574,
      "learning_rate": 7.476831995963703e-06,
      "loss": 0.4353,
      "step": 37882
    },
    {
      "epoch": 1.1637329892790218,
      "grad_norm": 0.38382506370544434,
      "learning_rate": 7.47636435816541e-06,
      "loss": 0.4668,
      "step": 37883
    },
    {
      "epoch": 1.1637637084139711,
      "grad_norm": 0.4013426899909973,
      "learning_rate": 7.475896726261243e-06,
      "loss": 0.5446,
      "step": 37884
    },
    {
      "epoch": 1.1637944275489203,
      "grad_norm": 0.40170156955718994,
      "learning_rate": 7.475429100252296e-06,
      "loss": 0.4986,
      "step": 37885
    },
    {
      "epoch": 1.1638251466838694,
      "grad_norm": 0.39158958196640015,
      "learning_rate": 7.47496148013966e-06,
      "loss": 0.4581,
      "step": 37886
    },
    {
      "epoch": 1.1638558658188185,
      "grad_norm": 0.4276169240474701,
      "learning_rate": 7.474493865924429e-06,
      "loss": 0.4595,
      "step": 37887
    },
    {
      "epoch": 1.1638865849537676,
      "grad_norm": 0.34008902311325073,
      "learning_rate": 7.474026257607692e-06,
      "loss": 0.3713,
      "step": 37888
    },
    {
      "epoch": 1.163917304088717,
      "grad_norm": 0.3994864821434021,
      "learning_rate": 7.4735586551905455e-06,
      "loss": 0.4576,
      "step": 37889
    },
    {
      "epoch": 1.163948023223666,
      "grad_norm": 0.38164952397346497,
      "learning_rate": 7.473091058674078e-06,
      "loss": 0.5276,
      "step": 37890
    },
    {
      "epoch": 1.1639787423586152,
      "grad_norm": 0.3748580515384674,
      "learning_rate": 7.472623468059386e-06,
      "loss": 0.4528,
      "step": 37891
    },
    {
      "epoch": 1.1640094614935643,
      "grad_norm": 0.42779088020324707,
      "learning_rate": 7.4721558833475516e-06,
      "loss": 0.4763,
      "step": 37892
    },
    {
      "epoch": 1.1640401806285134,
      "grad_norm": 0.43333226442337036,
      "learning_rate": 7.47168830453968e-06,
      "loss": 0.4991,
      "step": 37893
    },
    {
      "epoch": 1.1640708997634626,
      "grad_norm": 0.42639535665512085,
      "learning_rate": 7.471220731636852e-06,
      "loss": 0.4915,
      "step": 37894
    },
    {
      "epoch": 1.164101618898412,
      "grad_norm": 0.3958908021450043,
      "learning_rate": 7.47075316464017e-06,
      "loss": 0.5201,
      "step": 37895
    },
    {
      "epoch": 1.164132338033361,
      "grad_norm": 0.402727335691452,
      "learning_rate": 7.470285603550714e-06,
      "loss": 0.4704,
      "step": 37896
    },
    {
      "epoch": 1.1641630571683101,
      "grad_norm": 0.42322656512260437,
      "learning_rate": 7.469818048369586e-06,
      "loss": 0.5005,
      "step": 37897
    },
    {
      "epoch": 1.1641937763032593,
      "grad_norm": 0.393583208322525,
      "learning_rate": 7.469350499097877e-06,
      "loss": 0.4846,
      "step": 37898
    },
    {
      "epoch": 1.1642244954382084,
      "grad_norm": 0.39755818247795105,
      "learning_rate": 7.468882955736671e-06,
      "loss": 0.4396,
      "step": 37899
    },
    {
      "epoch": 1.1642552145731577,
      "grad_norm": 0.3944491446018219,
      "learning_rate": 7.468415418287074e-06,
      "loss": 0.5103,
      "step": 37900
    },
    {
      "epoch": 1.1642859337081068,
      "grad_norm": 0.3683246374130249,
      "learning_rate": 7.46794788675016e-06,
      "loss": 0.4195,
      "step": 37901
    },
    {
      "epoch": 1.164316652843056,
      "grad_norm": 0.38192468881607056,
      "learning_rate": 7.46748036112704e-06,
      "loss": 0.5102,
      "step": 37902
    },
    {
      "epoch": 1.164347371978005,
      "grad_norm": 0.5427341461181641,
      "learning_rate": 7.4670128414187885e-06,
      "loss": 0.5628,
      "step": 37903
    },
    {
      "epoch": 1.1643780911129542,
      "grad_norm": 0.38658347725868225,
      "learning_rate": 7.466545327626511e-06,
      "loss": 0.5435,
      "step": 37904
    },
    {
      "epoch": 1.1644088102479033,
      "grad_norm": 0.44703957438468933,
      "learning_rate": 7.46607781975129e-06,
      "loss": 0.4936,
      "step": 37905
    },
    {
      "epoch": 1.1644395293828527,
      "grad_norm": 0.3770676851272583,
      "learning_rate": 7.465610317794224e-06,
      "loss": 0.4438,
      "step": 37906
    },
    {
      "epoch": 1.1644702485178018,
      "grad_norm": 0.4258630573749542,
      "learning_rate": 7.465142821756399e-06,
      "loss": 0.5371,
      "step": 37907
    },
    {
      "epoch": 1.164500967652751,
      "grad_norm": 0.43131816387176514,
      "learning_rate": 7.464675331638913e-06,
      "loss": 0.5221,
      "step": 37908
    },
    {
      "epoch": 1.1645316867877,
      "grad_norm": 0.40245702862739563,
      "learning_rate": 7.464207847442852e-06,
      "loss": 0.4458,
      "step": 37909
    },
    {
      "epoch": 1.1645624059226491,
      "grad_norm": 0.39057838916778564,
      "learning_rate": 7.463740369169315e-06,
      "loss": 0.4364,
      "step": 37910
    },
    {
      "epoch": 1.1645931250575985,
      "grad_norm": 0.6191688776016235,
      "learning_rate": 7.463272896819384e-06,
      "loss": 0.4503,
      "step": 37911
    },
    {
      "epoch": 1.1646238441925476,
      "grad_norm": 0.434500128030777,
      "learning_rate": 7.462805430394162e-06,
      "loss": 0.4465,
      "step": 37912
    },
    {
      "epoch": 1.1646545633274967,
      "grad_norm": 0.3686712086200714,
      "learning_rate": 7.462337969894731e-06,
      "loss": 0.5126,
      "step": 37913
    },
    {
      "epoch": 1.1646852824624458,
      "grad_norm": 0.4145752191543579,
      "learning_rate": 7.46187051532219e-06,
      "loss": 0.5318,
      "step": 37914
    },
    {
      "epoch": 1.164716001597395,
      "grad_norm": 0.3878639340400696,
      "learning_rate": 7.461403066677624e-06,
      "loss": 0.4857,
      "step": 37915
    },
    {
      "epoch": 1.164746720732344,
      "grad_norm": 0.4288082420825958,
      "learning_rate": 7.460935623962129e-06,
      "loss": 0.5342,
      "step": 37916
    },
    {
      "epoch": 1.1647774398672934,
      "grad_norm": 0.3999573290348053,
      "learning_rate": 7.4604681871767985e-06,
      "loss": 0.4715,
      "step": 37917
    },
    {
      "epoch": 1.1648081590022425,
      "grad_norm": 0.4560602307319641,
      "learning_rate": 7.460000756322719e-06,
      "loss": 0.5347,
      "step": 37918
    },
    {
      "epoch": 1.1648388781371917,
      "grad_norm": 0.426729291677475,
      "learning_rate": 7.459533331400987e-06,
      "loss": 0.4647,
      "step": 37919
    },
    {
      "epoch": 1.1648695972721408,
      "grad_norm": 0.40183836221694946,
      "learning_rate": 7.4590659124126925e-06,
      "loss": 0.4646,
      "step": 37920
    },
    {
      "epoch": 1.16490031640709,
      "grad_norm": 0.38271528482437134,
      "learning_rate": 7.4585984993589275e-06,
      "loss": 0.4791,
      "step": 37921
    },
    {
      "epoch": 1.1649310355420393,
      "grad_norm": 0.40598055720329285,
      "learning_rate": 7.458131092240781e-06,
      "loss": 0.5139,
      "step": 37922
    },
    {
      "epoch": 1.1649617546769884,
      "grad_norm": 0.3703325688838959,
      "learning_rate": 7.457663691059349e-06,
      "loss": 0.4787,
      "step": 37923
    },
    {
      "epoch": 1.1649924738119375,
      "grad_norm": 0.4934580624103546,
      "learning_rate": 7.457196295815721e-06,
      "loss": 0.4771,
      "step": 37924
    },
    {
      "epoch": 1.1650231929468866,
      "grad_norm": 0.42547547817230225,
      "learning_rate": 7.4567289065109884e-06,
      "loss": 0.5068,
      "step": 37925
    },
    {
      "epoch": 1.1650539120818357,
      "grad_norm": 0.372315913438797,
      "learning_rate": 7.456261523146242e-06,
      "loss": 0.4581,
      "step": 37926
    },
    {
      "epoch": 1.1650846312167848,
      "grad_norm": 0.3956329822540283,
      "learning_rate": 7.455794145722577e-06,
      "loss": 0.5383,
      "step": 37927
    },
    {
      "epoch": 1.1651153503517342,
      "grad_norm": 0.3860184848308563,
      "learning_rate": 7.455326774241079e-06,
      "loss": 0.3624,
      "step": 37928
    },
    {
      "epoch": 1.1651460694866833,
      "grad_norm": 0.4000478684902191,
      "learning_rate": 7.454859408702847e-06,
      "loss": 0.492,
      "step": 37929
    },
    {
      "epoch": 1.1651767886216324,
      "grad_norm": 0.41881850361824036,
      "learning_rate": 7.454392049108963e-06,
      "loss": 0.5296,
      "step": 37930
    },
    {
      "epoch": 1.1652075077565816,
      "grad_norm": 0.44121912121772766,
      "learning_rate": 7.45392469546053e-06,
      "loss": 0.5192,
      "step": 37931
    },
    {
      "epoch": 1.1652382268915307,
      "grad_norm": 0.38271331787109375,
      "learning_rate": 7.45345734775863e-06,
      "loss": 0.4219,
      "step": 37932
    },
    {
      "epoch": 1.16526894602648,
      "grad_norm": 0.4855521023273468,
      "learning_rate": 7.452990006004357e-06,
      "loss": 0.5004,
      "step": 37933
    },
    {
      "epoch": 1.1652996651614291,
      "grad_norm": 0.4205767512321472,
      "learning_rate": 7.4525226701988085e-06,
      "loss": 0.526,
      "step": 37934
    },
    {
      "epoch": 1.1653303842963783,
      "grad_norm": 0.4130600392818451,
      "learning_rate": 7.452055340343065e-06,
      "loss": 0.4981,
      "step": 37935
    },
    {
      "epoch": 1.1653611034313274,
      "grad_norm": 0.4234842360019684,
      "learning_rate": 7.451588016438232e-06,
      "loss": 0.5708,
      "step": 37936
    },
    {
      "epoch": 1.1653918225662765,
      "grad_norm": 0.4085381031036377,
      "learning_rate": 7.4511206984853855e-06,
      "loss": 0.5404,
      "step": 37937
    },
    {
      "epoch": 1.1654225417012256,
      "grad_norm": 0.3843952715396881,
      "learning_rate": 7.450653386485631e-06,
      "loss": 0.4645,
      "step": 37938
    },
    {
      "epoch": 1.1654532608361747,
      "grad_norm": 0.3972106873989105,
      "learning_rate": 7.4501860804400495e-06,
      "loss": 0.5071,
      "step": 37939
    },
    {
      "epoch": 1.165483979971124,
      "grad_norm": 0.34561973810195923,
      "learning_rate": 7.44971878034974e-06,
      "loss": 0.4115,
      "step": 37940
    },
    {
      "epoch": 1.1655146991060732,
      "grad_norm": 0.39068931341171265,
      "learning_rate": 7.449251486215786e-06,
      "loss": 0.4824,
      "step": 37941
    },
    {
      "epoch": 1.1655454182410223,
      "grad_norm": 0.44486182928085327,
      "learning_rate": 7.448784198039287e-06,
      "loss": 0.5221,
      "step": 37942
    },
    {
      "epoch": 1.1655761373759714,
      "grad_norm": 0.3928796947002411,
      "learning_rate": 7.448316915821327e-06,
      "loss": 0.5356,
      "step": 37943
    },
    {
      "epoch": 1.1656068565109208,
      "grad_norm": 0.38068443536758423,
      "learning_rate": 7.447849639563005e-06,
      "loss": 0.5181,
      "step": 37944
    },
    {
      "epoch": 1.16563757564587,
      "grad_norm": 0.4058447480201721,
      "learning_rate": 7.447382369265406e-06,
      "loss": 0.5299,
      "step": 37945
    },
    {
      "epoch": 1.165668294780819,
      "grad_norm": 0.3923320770263672,
      "learning_rate": 7.446915104929624e-06,
      "loss": 0.458,
      "step": 37946
    },
    {
      "epoch": 1.1656990139157681,
      "grad_norm": 0.4184018075466156,
      "learning_rate": 7.44644784655675e-06,
      "loss": 0.505,
      "step": 37947
    },
    {
      "epoch": 1.1657297330507173,
      "grad_norm": 0.3955913484096527,
      "learning_rate": 7.445980594147877e-06,
      "loss": 0.4434,
      "step": 37948
    },
    {
      "epoch": 1.1657604521856664,
      "grad_norm": 0.40824684500694275,
      "learning_rate": 7.445513347704092e-06,
      "loss": 0.5021,
      "step": 37949
    },
    {
      "epoch": 1.1657911713206155,
      "grad_norm": 0.5813740491867065,
      "learning_rate": 7.445046107226491e-06,
      "loss": 0.4318,
      "step": 37950
    },
    {
      "epoch": 1.1658218904555648,
      "grad_norm": 0.4216131567955017,
      "learning_rate": 7.4445788727161616e-06,
      "loss": 0.4649,
      "step": 37951
    },
    {
      "epoch": 1.165852609590514,
      "grad_norm": 0.41204771399497986,
      "learning_rate": 7.4441116441741965e-06,
      "loss": 0.4761,
      "step": 37952
    },
    {
      "epoch": 1.165883328725463,
      "grad_norm": 0.42836132645606995,
      "learning_rate": 7.44364442160169e-06,
      "loss": 0.4882,
      "step": 37953
    },
    {
      "epoch": 1.1659140478604122,
      "grad_norm": 0.41225284337997437,
      "learning_rate": 7.443177204999728e-06,
      "loss": 0.4402,
      "step": 37954
    },
    {
      "epoch": 1.1659447669953613,
      "grad_norm": 0.3816756308078766,
      "learning_rate": 7.442709994369406e-06,
      "loss": 0.4641,
      "step": 37955
    },
    {
      "epoch": 1.1659754861303107,
      "grad_norm": 0.3851957619190216,
      "learning_rate": 7.442242789711811e-06,
      "loss": 0.5204,
      "step": 37956
    },
    {
      "epoch": 1.1660062052652598,
      "grad_norm": 1.014066457748413,
      "learning_rate": 7.44177559102804e-06,
      "loss": 0.5775,
      "step": 37957
    },
    {
      "epoch": 1.166036924400209,
      "grad_norm": 0.3827759623527527,
      "learning_rate": 7.441308398319178e-06,
      "loss": 0.4722,
      "step": 37958
    },
    {
      "epoch": 1.166067643535158,
      "grad_norm": 0.3959725797176361,
      "learning_rate": 7.44084121158632e-06,
      "loss": 0.425,
      "step": 37959
    },
    {
      "epoch": 1.1660983626701071,
      "grad_norm": 0.40094810724258423,
      "learning_rate": 7.440374030830555e-06,
      "loss": 0.5084,
      "step": 37960
    },
    {
      "epoch": 1.1661290818050563,
      "grad_norm": 0.49788129329681396,
      "learning_rate": 7.439906856052979e-06,
      "loss": 0.4377,
      "step": 37961
    },
    {
      "epoch": 1.1661598009400056,
      "grad_norm": 0.39837270975112915,
      "learning_rate": 7.439439687254675e-06,
      "loss": 0.5055,
      "step": 37962
    },
    {
      "epoch": 1.1661905200749547,
      "grad_norm": 0.4033597707748413,
      "learning_rate": 7.438972524436743e-06,
      "loss": 0.4545,
      "step": 37963
    },
    {
      "epoch": 1.1662212392099038,
      "grad_norm": 0.41470417380332947,
      "learning_rate": 7.438505367600263e-06,
      "loss": 0.4961,
      "step": 37964
    },
    {
      "epoch": 1.166251958344853,
      "grad_norm": 0.4169902205467224,
      "learning_rate": 7.43803821674634e-06,
      "loss": 0.4846,
      "step": 37965
    },
    {
      "epoch": 1.166282677479802,
      "grad_norm": 0.47581005096435547,
      "learning_rate": 7.437571071876048e-06,
      "loss": 0.4897,
      "step": 37966
    },
    {
      "epoch": 1.1663133966147514,
      "grad_norm": 0.3759779930114746,
      "learning_rate": 7.437103932990498e-06,
      "loss": 0.4851,
      "step": 37967
    },
    {
      "epoch": 1.1663441157497005,
      "grad_norm": 0.4204815924167633,
      "learning_rate": 7.436636800090765e-06,
      "loss": 0.434,
      "step": 37968
    },
    {
      "epoch": 1.1663748348846497,
      "grad_norm": 0.3653603792190552,
      "learning_rate": 7.4361696731779485e-06,
      "loss": 0.4251,
      "step": 37969
    },
    {
      "epoch": 1.1664055540195988,
      "grad_norm": 0.37207111716270447,
      "learning_rate": 7.435702552253135e-06,
      "loss": 0.4784,
      "step": 37970
    },
    {
      "epoch": 1.166436273154548,
      "grad_norm": 0.3325193524360657,
      "learning_rate": 7.435235437317413e-06,
      "loss": 0.4562,
      "step": 37971
    },
    {
      "epoch": 1.166466992289497,
      "grad_norm": 0.5652695298194885,
      "learning_rate": 7.434768328371886e-06,
      "loss": 0.4667,
      "step": 37972
    },
    {
      "epoch": 1.1664977114244464,
      "grad_norm": 0.5208496451377869,
      "learning_rate": 7.434301225417632e-06,
      "loss": 0.5274,
      "step": 37973
    },
    {
      "epoch": 1.1665284305593955,
      "grad_norm": 0.382438600063324,
      "learning_rate": 7.433834128455748e-06,
      "loss": 0.4863,
      "step": 37974
    },
    {
      "epoch": 1.1665591496943446,
      "grad_norm": 0.3735049068927765,
      "learning_rate": 7.433367037487322e-06,
      "loss": 0.4447,
      "step": 37975
    },
    {
      "epoch": 1.1665898688292937,
      "grad_norm": 0.3854500949382782,
      "learning_rate": 7.43289995251345e-06,
      "loss": 0.5104,
      "step": 37976
    },
    {
      "epoch": 1.1666205879642428,
      "grad_norm": 0.41392621397972107,
      "learning_rate": 7.432432873535216e-06,
      "loss": 0.5116,
      "step": 37977
    },
    {
      "epoch": 1.1666513070991922,
      "grad_norm": 0.4089454412460327,
      "learning_rate": 7.431965800553715e-06,
      "loss": 0.413,
      "step": 37978
    },
    {
      "epoch": 1.1666820262341413,
      "grad_norm": 1.5849480628967285,
      "learning_rate": 7.431498733570037e-06,
      "loss": 0.5288,
      "step": 37979
    },
    {
      "epoch": 1.1667127453690904,
      "grad_norm": 0.4418480694293976,
      "learning_rate": 7.431031672585276e-06,
      "loss": 0.4407,
      "step": 37980
    },
    {
      "epoch": 1.1667434645040395,
      "grad_norm": 0.42446961998939514,
      "learning_rate": 7.430564617600518e-06,
      "loss": 0.5683,
      "step": 37981
    },
    {
      "epoch": 1.1667741836389887,
      "grad_norm": 0.39458519220352173,
      "learning_rate": 7.430097568616855e-06,
      "loss": 0.5274,
      "step": 37982
    },
    {
      "epoch": 1.1668049027739378,
      "grad_norm": 0.3725006878376007,
      "learning_rate": 7.4296305256353785e-06,
      "loss": 0.4161,
      "step": 37983
    },
    {
      "epoch": 1.1668356219088871,
      "grad_norm": 0.3923514783382416,
      "learning_rate": 7.42916348865718e-06,
      "loss": 0.5276,
      "step": 37984
    },
    {
      "epoch": 1.1668663410438362,
      "grad_norm": 0.8903595209121704,
      "learning_rate": 7.4286964576833505e-06,
      "loss": 0.5187,
      "step": 37985
    },
    {
      "epoch": 1.1668970601787854,
      "grad_norm": 0.40763983130455017,
      "learning_rate": 7.428229432714979e-06,
      "loss": 0.5408,
      "step": 37986
    },
    {
      "epoch": 1.1669277793137345,
      "grad_norm": 0.3946273922920227,
      "learning_rate": 7.427762413753158e-06,
      "loss": 0.395,
      "step": 37987
    },
    {
      "epoch": 1.1669584984486836,
      "grad_norm": 0.39489033818244934,
      "learning_rate": 7.427295400798976e-06,
      "loss": 0.5123,
      "step": 37988
    },
    {
      "epoch": 1.166989217583633,
      "grad_norm": 0.38699641823768616,
      "learning_rate": 7.426828393853527e-06,
      "loss": 0.4503,
      "step": 37989
    },
    {
      "epoch": 1.167019936718582,
      "grad_norm": 0.38857004046440125,
      "learning_rate": 7.426361392917899e-06,
      "loss": 0.4501,
      "step": 37990
    },
    {
      "epoch": 1.1670506558535312,
      "grad_norm": 0.43319857120513916,
      "learning_rate": 7.425894397993185e-06,
      "loss": 0.441,
      "step": 37991
    },
    {
      "epoch": 1.1670813749884803,
      "grad_norm": 0.3766670823097229,
      "learning_rate": 7.425427409080472e-06,
      "loss": 0.5142,
      "step": 37992
    },
    {
      "epoch": 1.1671120941234294,
      "grad_norm": 0.3930441737174988,
      "learning_rate": 7.424960426180856e-06,
      "loss": 0.5097,
      "step": 37993
    },
    {
      "epoch": 1.1671428132583785,
      "grad_norm": 0.41796648502349854,
      "learning_rate": 7.424493449295422e-06,
      "loss": 0.4408,
      "step": 37994
    },
    {
      "epoch": 1.1671735323933279,
      "grad_norm": 0.4024369418621063,
      "learning_rate": 7.424026478425268e-06,
      "loss": 0.4771,
      "step": 37995
    },
    {
      "epoch": 1.167204251528277,
      "grad_norm": 0.4088670611381531,
      "learning_rate": 7.423559513571474e-06,
      "loss": 0.4405,
      "step": 37996
    },
    {
      "epoch": 1.1672349706632261,
      "grad_norm": 0.5046653151512146,
      "learning_rate": 7.423092554735143e-06,
      "loss": 0.4314,
      "step": 37997
    },
    {
      "epoch": 1.1672656897981752,
      "grad_norm": 0.4311087727546692,
      "learning_rate": 7.422625601917353e-06,
      "loss": 0.4878,
      "step": 37998
    },
    {
      "epoch": 1.1672964089331244,
      "grad_norm": 0.4205828011035919,
      "learning_rate": 7.422158655119207e-06,
      "loss": 0.5162,
      "step": 37999
    },
    {
      "epoch": 1.1673271280680737,
      "grad_norm": 0.4128727316856384,
      "learning_rate": 7.4216917143417835e-06,
      "loss": 0.497,
      "step": 38000
    },
    {
      "epoch": 1.1673578472030228,
      "grad_norm": 0.3975770175457001,
      "learning_rate": 7.4212247795861845e-06,
      "loss": 0.4571,
      "step": 38001
    },
    {
      "epoch": 1.167388566337972,
      "grad_norm": 0.4959905743598938,
      "learning_rate": 7.420757850853492e-06,
      "loss": 0.4171,
      "step": 38002
    },
    {
      "epoch": 1.167419285472921,
      "grad_norm": 0.4159630239009857,
      "learning_rate": 7.420290928144801e-06,
      "loss": 0.5028,
      "step": 38003
    },
    {
      "epoch": 1.1674500046078702,
      "grad_norm": 0.4572177529335022,
      "learning_rate": 7.419824011461199e-06,
      "loss": 0.5099,
      "step": 38004
    },
    {
      "epoch": 1.1674807237428193,
      "grad_norm": 0.45718657970428467,
      "learning_rate": 7.419357100803779e-06,
      "loss": 0.5393,
      "step": 38005
    },
    {
      "epoch": 1.1675114428777686,
      "grad_norm": 0.40777158737182617,
      "learning_rate": 7.4188901961736306e-06,
      "loss": 0.4235,
      "step": 38006
    },
    {
      "epoch": 1.1675421620127178,
      "grad_norm": 0.40210118889808655,
      "learning_rate": 7.418423297571841e-06,
      "loss": 0.4938,
      "step": 38007
    },
    {
      "epoch": 1.1675728811476669,
      "grad_norm": 0.38360166549682617,
      "learning_rate": 7.417956404999511e-06,
      "loss": 0.5031,
      "step": 38008
    },
    {
      "epoch": 1.167603600282616,
      "grad_norm": 0.3511248528957367,
      "learning_rate": 7.41748951845772e-06,
      "loss": 0.4012,
      "step": 38009
    },
    {
      "epoch": 1.1676343194175651,
      "grad_norm": 0.365004301071167,
      "learning_rate": 7.417022637947564e-06,
      "loss": 0.4121,
      "step": 38010
    },
    {
      "epoch": 1.1676650385525145,
      "grad_norm": 0.3829047977924347,
      "learning_rate": 7.416555763470131e-06,
      "loss": 0.4914,
      "step": 38011
    },
    {
      "epoch": 1.1676957576874636,
      "grad_norm": 0.3920700252056122,
      "learning_rate": 7.416088895026514e-06,
      "loss": 0.4704,
      "step": 38012
    },
    {
      "epoch": 1.1677264768224127,
      "grad_norm": 0.3995278477668762,
      "learning_rate": 7.4156220326178e-06,
      "loss": 0.5226,
      "step": 38013
    },
    {
      "epoch": 1.1677571959573618,
      "grad_norm": 0.37839406728744507,
      "learning_rate": 7.415155176245084e-06,
      "loss": 0.4622,
      "step": 38014
    },
    {
      "epoch": 1.167787915092311,
      "grad_norm": 0.3890407383441925,
      "learning_rate": 7.414688325909449e-06,
      "loss": 0.5398,
      "step": 38015
    },
    {
      "epoch": 1.16781863422726,
      "grad_norm": 0.42320460081100464,
      "learning_rate": 7.4142214816119936e-06,
      "loss": 0.4928,
      "step": 38016
    },
    {
      "epoch": 1.1678493533622094,
      "grad_norm": 0.40662145614624023,
      "learning_rate": 7.413754643353803e-06,
      "loss": 0.4718,
      "step": 38017
    },
    {
      "epoch": 1.1678800724971585,
      "grad_norm": 0.38356560468673706,
      "learning_rate": 7.41328781113597e-06,
      "loss": 0.4444,
      "step": 38018
    },
    {
      "epoch": 1.1679107916321076,
      "grad_norm": 0.3798414170742035,
      "learning_rate": 7.412820984959584e-06,
      "loss": 0.4872,
      "step": 38019
    },
    {
      "epoch": 1.1679415107670568,
      "grad_norm": 0.45679375529289246,
      "learning_rate": 7.412354164825735e-06,
      "loss": 0.4717,
      "step": 38020
    },
    {
      "epoch": 1.1679722299020059,
      "grad_norm": 0.3753243386745453,
      "learning_rate": 7.411887350735512e-06,
      "loss": 0.5576,
      "step": 38021
    },
    {
      "epoch": 1.1680029490369552,
      "grad_norm": 0.4294443726539612,
      "learning_rate": 7.411420542690008e-06,
      "loss": 0.4607,
      "step": 38022
    },
    {
      "epoch": 1.1680336681719043,
      "grad_norm": 0.3606957495212555,
      "learning_rate": 7.410953740690312e-06,
      "loss": 0.4383,
      "step": 38023
    },
    {
      "epoch": 1.1680643873068535,
      "grad_norm": 0.3941667973995209,
      "learning_rate": 7.410486944737518e-06,
      "loss": 0.4635,
      "step": 38024
    },
    {
      "epoch": 1.1680951064418026,
      "grad_norm": 0.37224411964416504,
      "learning_rate": 7.4100201548327065e-06,
      "loss": 0.4737,
      "step": 38025
    },
    {
      "epoch": 1.1681258255767517,
      "grad_norm": 0.41124197840690613,
      "learning_rate": 7.409553370976975e-06,
      "loss": 0.4709,
      "step": 38026
    },
    {
      "epoch": 1.1681565447117008,
      "grad_norm": 0.40131014585494995,
      "learning_rate": 7.409086593171415e-06,
      "loss": 0.5526,
      "step": 38027
    },
    {
      "epoch": 1.1681872638466502,
      "grad_norm": 0.37963563203811646,
      "learning_rate": 7.408619821417113e-06,
      "loss": 0.5125,
      "step": 38028
    },
    {
      "epoch": 1.1682179829815993,
      "grad_norm": 0.3755725622177124,
      "learning_rate": 7.408153055715162e-06,
      "loss": 0.5187,
      "step": 38029
    },
    {
      "epoch": 1.1682487021165484,
      "grad_norm": 0.422406941652298,
      "learning_rate": 7.407686296066648e-06,
      "loss": 0.5431,
      "step": 38030
    },
    {
      "epoch": 1.1682794212514975,
      "grad_norm": 0.4015355706214905,
      "learning_rate": 7.407219542472668e-06,
      "loss": 0.5117,
      "step": 38031
    },
    {
      "epoch": 1.1683101403864466,
      "grad_norm": 0.3658779263496399,
      "learning_rate": 7.406752794934302e-06,
      "loss": 0.4992,
      "step": 38032
    },
    {
      "epoch": 1.168340859521396,
      "grad_norm": 0.3867194354534149,
      "learning_rate": 7.406286053452652e-06,
      "loss": 0.5333,
      "step": 38033
    },
    {
      "epoch": 1.1683715786563451,
      "grad_norm": 0.43932297825813293,
      "learning_rate": 7.405819318028795e-06,
      "loss": 0.5093,
      "step": 38034
    },
    {
      "epoch": 1.1684022977912942,
      "grad_norm": 0.37491899728775024,
      "learning_rate": 7.405352588663835e-06,
      "loss": 0.4936,
      "step": 38035
    },
    {
      "epoch": 1.1684330169262434,
      "grad_norm": 0.41162240505218506,
      "learning_rate": 7.4048858653588505e-06,
      "loss": 0.4911,
      "step": 38036
    },
    {
      "epoch": 1.1684637360611925,
      "grad_norm": 0.42963430285453796,
      "learning_rate": 7.40441914811494e-06,
      "loss": 0.5369,
      "step": 38037
    },
    {
      "epoch": 1.1684944551961416,
      "grad_norm": 0.39509838819503784,
      "learning_rate": 7.403952436933186e-06,
      "loss": 0.5039,
      "step": 38038
    },
    {
      "epoch": 1.168525174331091,
      "grad_norm": 0.3824523091316223,
      "learning_rate": 7.403485731814686e-06,
      "loss": 0.4629,
      "step": 38039
    },
    {
      "epoch": 1.16855589346604,
      "grad_norm": 0.3754926919937134,
      "learning_rate": 7.4030190327605235e-06,
      "loss": 0.507,
      "step": 38040
    },
    {
      "epoch": 1.1685866126009892,
      "grad_norm": 0.37077102065086365,
      "learning_rate": 7.402552339771794e-06,
      "loss": 0.4076,
      "step": 38041
    },
    {
      "epoch": 1.1686173317359383,
      "grad_norm": 1.3519995212554932,
      "learning_rate": 7.402085652849582e-06,
      "loss": 0.4666,
      "step": 38042
    },
    {
      "epoch": 1.1686480508708874,
      "grad_norm": 0.4309574365615845,
      "learning_rate": 7.401618971994981e-06,
      "loss": 0.5297,
      "step": 38043
    },
    {
      "epoch": 1.1686787700058368,
      "grad_norm": 0.3662623465061188,
      "learning_rate": 7.401152297209082e-06,
      "loss": 0.5227,
      "step": 38044
    },
    {
      "epoch": 1.1687094891407859,
      "grad_norm": 0.39326977729797363,
      "learning_rate": 7.400685628492972e-06,
      "loss": 0.5275,
      "step": 38045
    },
    {
      "epoch": 1.168740208275735,
      "grad_norm": 0.393823504447937,
      "learning_rate": 7.400218965847743e-06,
      "loss": 0.5063,
      "step": 38046
    },
    {
      "epoch": 1.1687709274106841,
      "grad_norm": 0.37892287969589233,
      "learning_rate": 7.399752309274484e-06,
      "loss": 0.4418,
      "step": 38047
    },
    {
      "epoch": 1.1688016465456332,
      "grad_norm": 0.3970004618167877,
      "learning_rate": 7.3992856587742846e-06,
      "loss": 0.4216,
      "step": 38048
    },
    {
      "epoch": 1.1688323656805824,
      "grad_norm": 0.41988706588745117,
      "learning_rate": 7.3988190143482355e-06,
      "loss": 0.523,
      "step": 38049
    },
    {
      "epoch": 1.1688630848155315,
      "grad_norm": 0.37031441926956177,
      "learning_rate": 7.398352375997426e-06,
      "loss": 0.4625,
      "step": 38050
    },
    {
      "epoch": 1.1688938039504808,
      "grad_norm": 0.42170101404190063,
      "learning_rate": 7.397885743722946e-06,
      "loss": 0.5273,
      "step": 38051
    },
    {
      "epoch": 1.16892452308543,
      "grad_norm": 0.3841194808483124,
      "learning_rate": 7.397419117525888e-06,
      "loss": 0.5212,
      "step": 38052
    },
    {
      "epoch": 1.168955242220379,
      "grad_norm": 0.4807000458240509,
      "learning_rate": 7.396952497407337e-06,
      "loss": 0.4639,
      "step": 38053
    },
    {
      "epoch": 1.1689859613553282,
      "grad_norm": 0.38565826416015625,
      "learning_rate": 7.3964858833683865e-06,
      "loss": 0.5042,
      "step": 38054
    },
    {
      "epoch": 1.1690166804902775,
      "grad_norm": 0.4050699770450592,
      "learning_rate": 7.396019275410122e-06,
      "loss": 0.4892,
      "step": 38055
    },
    {
      "epoch": 1.1690473996252266,
      "grad_norm": 0.3912915289402008,
      "learning_rate": 7.3955526735336415e-06,
      "loss": 0.4795,
      "step": 38056
    },
    {
      "epoch": 1.1690781187601758,
      "grad_norm": 0.4878472685813904,
      "learning_rate": 7.3950860777400255e-06,
      "loss": 0.4488,
      "step": 38057
    },
    {
      "epoch": 1.1691088378951249,
      "grad_norm": 0.37800291180610657,
      "learning_rate": 7.39461948803037e-06,
      "loss": 0.557,
      "step": 38058
    },
    {
      "epoch": 1.169139557030074,
      "grad_norm": 0.3826909065246582,
      "learning_rate": 7.394152904405761e-06,
      "loss": 0.489,
      "step": 38059
    },
    {
      "epoch": 1.1691702761650231,
      "grad_norm": 0.4011465609073639,
      "learning_rate": 7.393686326867293e-06,
      "loss": 0.4574,
      "step": 38060
    },
    {
      "epoch": 1.1692009952999722,
      "grad_norm": 0.3945993483066559,
      "learning_rate": 7.393219755416048e-06,
      "loss": 0.4736,
      "step": 38061
    },
    {
      "epoch": 1.1692317144349216,
      "grad_norm": 0.37882179021835327,
      "learning_rate": 7.392753190053121e-06,
      "loss": 0.4672,
      "step": 38062
    },
    {
      "epoch": 1.1692624335698707,
      "grad_norm": 0.41783827543258667,
      "learning_rate": 7.3922866307796035e-06,
      "loss": 0.5698,
      "step": 38063
    },
    {
      "epoch": 1.1692931527048198,
      "grad_norm": 0.4376923143863678,
      "learning_rate": 7.3918200775965805e-06,
      "loss": 0.355,
      "step": 38064
    },
    {
      "epoch": 1.169323871839769,
      "grad_norm": 0.3951417803764343,
      "learning_rate": 7.39135353050515e-06,
      "loss": 0.5556,
      "step": 38065
    },
    {
      "epoch": 1.169354590974718,
      "grad_norm": 0.4348035752773285,
      "learning_rate": 7.390886989506388e-06,
      "loss": 0.4325,
      "step": 38066
    },
    {
      "epoch": 1.1693853101096674,
      "grad_norm": 0.39991873502731323,
      "learning_rate": 7.390420454601397e-06,
      "loss": 0.4388,
      "step": 38067
    },
    {
      "epoch": 1.1694160292446165,
      "grad_norm": 0.3959287703037262,
      "learning_rate": 7.389953925791256e-06,
      "loss": 0.4504,
      "step": 38068
    },
    {
      "epoch": 1.1694467483795656,
      "grad_norm": 0.46024584770202637,
      "learning_rate": 7.389487403077065e-06,
      "loss": 0.4191,
      "step": 38069
    },
    {
      "epoch": 1.1694774675145148,
      "grad_norm": 0.3732599914073944,
      "learning_rate": 7.389020886459903e-06,
      "loss": 0.4697,
      "step": 38070
    },
    {
      "epoch": 1.1695081866494639,
      "grad_norm": 0.4244217574596405,
      "learning_rate": 7.388554375940871e-06,
      "loss": 0.4302,
      "step": 38071
    },
    {
      "epoch": 1.169538905784413,
      "grad_norm": 0.4415023624897003,
      "learning_rate": 7.388087871521048e-06,
      "loss": 0.4796,
      "step": 38072
    },
    {
      "epoch": 1.1695696249193623,
      "grad_norm": 0.3893210291862488,
      "learning_rate": 7.3876213732015326e-06,
      "loss": 0.4563,
      "step": 38073
    },
    {
      "epoch": 1.1696003440543115,
      "grad_norm": 0.4288569390773773,
      "learning_rate": 7.387154880983405e-06,
      "loss": 0.4203,
      "step": 38074
    },
    {
      "epoch": 1.1696310631892606,
      "grad_norm": 0.42348212003707886,
      "learning_rate": 7.386688394867762e-06,
      "loss": 0.479,
      "step": 38075
    },
    {
      "epoch": 1.1696617823242097,
      "grad_norm": 0.4715808928012848,
      "learning_rate": 7.3862219148556915e-06,
      "loss": 0.4216,
      "step": 38076
    },
    {
      "epoch": 1.1696925014591588,
      "grad_norm": 0.3834100067615509,
      "learning_rate": 7.385755440948281e-06,
      "loss": 0.407,
      "step": 38077
    },
    {
      "epoch": 1.1697232205941082,
      "grad_norm": 0.49666640162467957,
      "learning_rate": 7.385288973146621e-06,
      "loss": 0.5037,
      "step": 38078
    },
    {
      "epoch": 1.1697539397290573,
      "grad_norm": 0.42497774958610535,
      "learning_rate": 7.3848225114518015e-06,
      "loss": 0.437,
      "step": 38079
    },
    {
      "epoch": 1.1697846588640064,
      "grad_norm": 0.35906773805618286,
      "learning_rate": 7.384356055864913e-06,
      "loss": 0.4695,
      "step": 38080
    },
    {
      "epoch": 1.1698153779989555,
      "grad_norm": 0.3970288634300232,
      "learning_rate": 7.383889606387043e-06,
      "loss": 0.5011,
      "step": 38081
    },
    {
      "epoch": 1.1698460971339046,
      "grad_norm": 0.3987344205379486,
      "learning_rate": 7.383423163019281e-06,
      "loss": 0.5202,
      "step": 38082
    },
    {
      "epoch": 1.1698768162688538,
      "grad_norm": 0.3968541920185089,
      "learning_rate": 7.382956725762716e-06,
      "loss": 0.4963,
      "step": 38083
    },
    {
      "epoch": 1.169907535403803,
      "grad_norm": 0.418013334274292,
      "learning_rate": 7.3824902946184406e-06,
      "loss": 0.4994,
      "step": 38084
    },
    {
      "epoch": 1.1699382545387522,
      "grad_norm": 0.5441401600837708,
      "learning_rate": 7.38202386958754e-06,
      "loss": 0.5118,
      "step": 38085
    },
    {
      "epoch": 1.1699689736737013,
      "grad_norm": 0.4041048288345337,
      "learning_rate": 7.381557450671108e-06,
      "loss": 0.523,
      "step": 38086
    },
    {
      "epoch": 1.1699996928086505,
      "grad_norm": 0.3608129620552063,
      "learning_rate": 7.381091037870227e-06,
      "loss": 0.4606,
      "step": 38087
    },
    {
      "epoch": 1.1700304119435996,
      "grad_norm": 0.42134907841682434,
      "learning_rate": 7.380624631185995e-06,
      "loss": 0.5032,
      "step": 38088
    },
    {
      "epoch": 1.170061131078549,
      "grad_norm": 0.38339680433273315,
      "learning_rate": 7.380158230619495e-06,
      "loss": 0.4599,
      "step": 38089
    },
    {
      "epoch": 1.170091850213498,
      "grad_norm": 0.3830023407936096,
      "learning_rate": 7.379691836171821e-06,
      "loss": 0.4451,
      "step": 38090
    },
    {
      "epoch": 1.1701225693484472,
      "grad_norm": 0.3609790802001953,
      "learning_rate": 7.379225447844056e-06,
      "loss": 0.4398,
      "step": 38091
    },
    {
      "epoch": 1.1701532884833963,
      "grad_norm": 0.3865024149417877,
      "learning_rate": 7.378759065637295e-06,
      "loss": 0.4793,
      "step": 38092
    },
    {
      "epoch": 1.1701840076183454,
      "grad_norm": 0.399372935295105,
      "learning_rate": 7.378292689552624e-06,
      "loss": 0.4123,
      "step": 38093
    },
    {
      "epoch": 1.1702147267532945,
      "grad_norm": 0.4016575813293457,
      "learning_rate": 7.377826319591139e-06,
      "loss": 0.5149,
      "step": 38094
    },
    {
      "epoch": 1.1702454458882439,
      "grad_norm": 0.4197708070278168,
      "learning_rate": 7.377359955753916e-06,
      "loss": 0.497,
      "step": 38095
    },
    {
      "epoch": 1.170276165023193,
      "grad_norm": 0.4438900947570801,
      "learning_rate": 7.376893598042059e-06,
      "loss": 0.5497,
      "step": 38096
    },
    {
      "epoch": 1.170306884158142,
      "grad_norm": 0.38160768151283264,
      "learning_rate": 7.376427246456643e-06,
      "loss": 0.4766,
      "step": 38097
    },
    {
      "epoch": 1.1703376032930912,
      "grad_norm": 0.4105680286884308,
      "learning_rate": 7.3759609009987664e-06,
      "loss": 0.5022,
      "step": 38098
    },
    {
      "epoch": 1.1703683224280403,
      "grad_norm": 0.4277615249156952,
      "learning_rate": 7.3754945616695186e-06,
      "loss": 0.5172,
      "step": 38099
    },
    {
      "epoch": 1.1703990415629897,
      "grad_norm": 0.46654337644577026,
      "learning_rate": 7.375028228469985e-06,
      "loss": 0.4717,
      "step": 38100
    },
    {
      "epoch": 1.1704297606979388,
      "grad_norm": 0.3897742033004761,
      "learning_rate": 7.37456190140126e-06,
      "loss": 0.4685,
      "step": 38101
    },
    {
      "epoch": 1.170460479832888,
      "grad_norm": 0.5466895699501038,
      "learning_rate": 7.374095580464425e-06,
      "loss": 0.4558,
      "step": 38102
    },
    {
      "epoch": 1.170491198967837,
      "grad_norm": 0.38238397240638733,
      "learning_rate": 7.373629265660575e-06,
      "loss": 0.4665,
      "step": 38103
    },
    {
      "epoch": 1.1705219181027862,
      "grad_norm": 0.393161803483963,
      "learning_rate": 7.373162956990795e-06,
      "loss": 0.5457,
      "step": 38104
    },
    {
      "epoch": 1.1705526372377353,
      "grad_norm": 0.38216161727905273,
      "learning_rate": 7.37269665445618e-06,
      "loss": 0.4471,
      "step": 38105
    },
    {
      "epoch": 1.1705833563726846,
      "grad_norm": 0.4367828071117401,
      "learning_rate": 7.372230358057812e-06,
      "loss": 0.5823,
      "step": 38106
    },
    {
      "epoch": 1.1706140755076337,
      "grad_norm": 0.3793039321899414,
      "learning_rate": 7.3717640677967875e-06,
      "loss": 0.4671,
      "step": 38107
    },
    {
      "epoch": 1.1706447946425829,
      "grad_norm": 0.3742101788520813,
      "learning_rate": 7.3712977836741876e-06,
      "loss": 0.4714,
      "step": 38108
    },
    {
      "epoch": 1.170675513777532,
      "grad_norm": 0.3878604471683502,
      "learning_rate": 7.370831505691107e-06,
      "loss": 0.4624,
      "step": 38109
    },
    {
      "epoch": 1.170706232912481,
      "grad_norm": 0.40986260771751404,
      "learning_rate": 7.370365233848633e-06,
      "loss": 0.4556,
      "step": 38110
    },
    {
      "epoch": 1.1707369520474304,
      "grad_norm": 0.4114881157875061,
      "learning_rate": 7.369898968147855e-06,
      "loss": 0.5319,
      "step": 38111
    },
    {
      "epoch": 1.1707676711823796,
      "grad_norm": 0.42615196108818054,
      "learning_rate": 7.369432708589861e-06,
      "loss": 0.5548,
      "step": 38112
    },
    {
      "epoch": 1.1707983903173287,
      "grad_norm": 0.39773496985435486,
      "learning_rate": 7.368966455175741e-06,
      "loss": 0.5492,
      "step": 38113
    },
    {
      "epoch": 1.1708291094522778,
      "grad_norm": 0.42863699793815613,
      "learning_rate": 7.368500207906581e-06,
      "loss": 0.4639,
      "step": 38114
    },
    {
      "epoch": 1.170859828587227,
      "grad_norm": 0.38551098108291626,
      "learning_rate": 7.368033966783477e-06,
      "loss": 0.5347,
      "step": 38115
    },
    {
      "epoch": 1.170890547722176,
      "grad_norm": 0.45287254452705383,
      "learning_rate": 7.36756773180751e-06,
      "loss": 0.4952,
      "step": 38116
    },
    {
      "epoch": 1.1709212668571254,
      "grad_norm": 0.43193042278289795,
      "learning_rate": 7.367101502979772e-06,
      "loss": 0.5162,
      "step": 38117
    },
    {
      "epoch": 1.1709519859920745,
      "grad_norm": 0.3869371712207794,
      "learning_rate": 7.366635280301355e-06,
      "loss": 0.4509,
      "step": 38118
    },
    {
      "epoch": 1.1709827051270236,
      "grad_norm": 0.4170006513595581,
      "learning_rate": 7.3661690637733445e-06,
      "loss": 0.4672,
      "step": 38119
    },
    {
      "epoch": 1.1710134242619727,
      "grad_norm": 0.37638798356056213,
      "learning_rate": 7.36570285339683e-06,
      "loss": 0.4809,
      "step": 38120
    },
    {
      "epoch": 1.1710441433969219,
      "grad_norm": 0.3730100393295288,
      "learning_rate": 7.3652366491729e-06,
      "loss": 0.4503,
      "step": 38121
    },
    {
      "epoch": 1.1710748625318712,
      "grad_norm": 0.4426427185535431,
      "learning_rate": 7.364770451102645e-06,
      "loss": 0.4093,
      "step": 38122
    },
    {
      "epoch": 1.1711055816668203,
      "grad_norm": 0.3968707323074341,
      "learning_rate": 7.364304259187151e-06,
      "loss": 0.4806,
      "step": 38123
    },
    {
      "epoch": 1.1711363008017694,
      "grad_norm": 0.38160645961761475,
      "learning_rate": 7.3638380734275094e-06,
      "loss": 0.543,
      "step": 38124
    },
    {
      "epoch": 1.1711670199367186,
      "grad_norm": 0.38931459188461304,
      "learning_rate": 7.363371893824808e-06,
      "loss": 0.4643,
      "step": 38125
    },
    {
      "epoch": 1.1711977390716677,
      "grad_norm": 0.3967760503292084,
      "learning_rate": 7.3629057203801355e-06,
      "loss": 0.4899,
      "step": 38126
    },
    {
      "epoch": 1.1712284582066168,
      "grad_norm": 0.5781551599502563,
      "learning_rate": 7.36243955309458e-06,
      "loss": 0.4887,
      "step": 38127
    },
    {
      "epoch": 1.1712591773415661,
      "grad_norm": 0.4088192582130432,
      "learning_rate": 7.361973391969236e-06,
      "loss": 0.4762,
      "step": 38128
    },
    {
      "epoch": 1.1712898964765153,
      "grad_norm": 0.4234023988246918,
      "learning_rate": 7.361507237005181e-06,
      "loss": 0.4987,
      "step": 38129
    },
    {
      "epoch": 1.1713206156114644,
      "grad_norm": 0.39709657430648804,
      "learning_rate": 7.361041088203515e-06,
      "loss": 0.4708,
      "step": 38130
    },
    {
      "epoch": 1.1713513347464135,
      "grad_norm": 0.6518976092338562,
      "learning_rate": 7.360574945565316e-06,
      "loss": 0.4899,
      "step": 38131
    },
    {
      "epoch": 1.1713820538813626,
      "grad_norm": 0.4544081389904022,
      "learning_rate": 7.360108809091686e-06,
      "loss": 0.5732,
      "step": 38132
    },
    {
      "epoch": 1.171412773016312,
      "grad_norm": 0.4017379879951477,
      "learning_rate": 7.3596426787836984e-06,
      "loss": 0.484,
      "step": 38133
    },
    {
      "epoch": 1.171443492151261,
      "grad_norm": 0.39297398924827576,
      "learning_rate": 7.359176554642453e-06,
      "loss": 0.4558,
      "step": 38134
    },
    {
      "epoch": 1.1714742112862102,
      "grad_norm": 0.4148786962032318,
      "learning_rate": 7.358710436669039e-06,
      "loss": 0.4773,
      "step": 38135
    },
    {
      "epoch": 1.1715049304211593,
      "grad_norm": 0.39812755584716797,
      "learning_rate": 7.358244324864534e-06,
      "loss": 0.4812,
      "step": 38136
    },
    {
      "epoch": 1.1715356495561084,
      "grad_norm": 0.4072246551513672,
      "learning_rate": 7.357778219230041e-06,
      "loss": 0.4633,
      "step": 38137
    },
    {
      "epoch": 1.1715663686910576,
      "grad_norm": 0.398801326751709,
      "learning_rate": 7.357312119766636e-06,
      "loss": 0.5768,
      "step": 38138
    },
    {
      "epoch": 1.171597087826007,
      "grad_norm": 0.3913688361644745,
      "learning_rate": 7.35684602647542e-06,
      "loss": 0.4614,
      "step": 38139
    },
    {
      "epoch": 1.171627806960956,
      "grad_norm": 0.4080447852611542,
      "learning_rate": 7.3563799393574654e-06,
      "loss": 0.471,
      "step": 38140
    },
    {
      "epoch": 1.1716585260959052,
      "grad_norm": 0.37487301230430603,
      "learning_rate": 7.355913858413879e-06,
      "loss": 0.4876,
      "step": 38141
    },
    {
      "epoch": 1.1716892452308543,
      "grad_norm": 0.3777512013912201,
      "learning_rate": 7.355447783645735e-06,
      "loss": 0.4597,
      "step": 38142
    },
    {
      "epoch": 1.1717199643658034,
      "grad_norm": 0.37074506282806396,
      "learning_rate": 7.35498171505413e-06,
      "loss": 0.4802,
      "step": 38143
    },
    {
      "epoch": 1.1717506835007527,
      "grad_norm": 0.4578268826007843,
      "learning_rate": 7.354515652640147e-06,
      "loss": 0.4205,
      "step": 38144
    },
    {
      "epoch": 1.1717814026357019,
      "grad_norm": 0.42061343789100647,
      "learning_rate": 7.354049596404879e-06,
      "loss": 0.5094,
      "step": 38145
    },
    {
      "epoch": 1.171812121770651,
      "grad_norm": 0.35789552330970764,
      "learning_rate": 7.353583546349413e-06,
      "loss": 0.4547,
      "step": 38146
    },
    {
      "epoch": 1.1718428409056,
      "grad_norm": 0.3731529414653778,
      "learning_rate": 7.353117502474839e-06,
      "loss": 0.471,
      "step": 38147
    },
    {
      "epoch": 1.1718735600405492,
      "grad_norm": 0.41099104285240173,
      "learning_rate": 7.352651464782241e-06,
      "loss": 0.4213,
      "step": 38148
    },
    {
      "epoch": 1.1719042791754983,
      "grad_norm": 0.41468435525894165,
      "learning_rate": 7.352185433272714e-06,
      "loss": 0.474,
      "step": 38149
    },
    {
      "epoch": 1.1719349983104477,
      "grad_norm": 0.4174550771713257,
      "learning_rate": 7.3517194079473395e-06,
      "loss": 0.5038,
      "step": 38150
    },
    {
      "epoch": 1.1719657174453968,
      "grad_norm": 0.37447482347488403,
      "learning_rate": 7.3512533888072115e-06,
      "loss": 0.4974,
      "step": 38151
    },
    {
      "epoch": 1.171996436580346,
      "grad_norm": 0.38025936484336853,
      "learning_rate": 7.350787375853414e-06,
      "loss": 0.466,
      "step": 38152
    },
    {
      "epoch": 1.172027155715295,
      "grad_norm": 0.42324498295783997,
      "learning_rate": 7.3503213690870365e-06,
      "loss": 0.4636,
      "step": 38153
    },
    {
      "epoch": 1.1720578748502442,
      "grad_norm": 0.4746611416339874,
      "learning_rate": 7.349855368509173e-06,
      "loss": 0.4562,
      "step": 38154
    },
    {
      "epoch": 1.1720885939851935,
      "grad_norm": 0.41944119334220886,
      "learning_rate": 7.349389374120903e-06,
      "loss": 0.5197,
      "step": 38155
    },
    {
      "epoch": 1.1721193131201426,
      "grad_norm": 0.48709696531295776,
      "learning_rate": 7.348923385923323e-06,
      "loss": 0.5266,
      "step": 38156
    },
    {
      "epoch": 1.1721500322550917,
      "grad_norm": 0.418820321559906,
      "learning_rate": 7.348457403917515e-06,
      "loss": 0.5516,
      "step": 38157
    },
    {
      "epoch": 1.1721807513900409,
      "grad_norm": 0.3834165632724762,
      "learning_rate": 7.347991428104572e-06,
      "loss": 0.4878,
      "step": 38158
    },
    {
      "epoch": 1.17221147052499,
      "grad_norm": 0.43481215834617615,
      "learning_rate": 7.347525458485578e-06,
      "loss": 0.4936,
      "step": 38159
    },
    {
      "epoch": 1.172242189659939,
      "grad_norm": 0.41635823249816895,
      "learning_rate": 7.3470594950616255e-06,
      "loss": 0.5104,
      "step": 38160
    },
    {
      "epoch": 1.1722729087948882,
      "grad_norm": 0.39614877104759216,
      "learning_rate": 7.3465935378338e-06,
      "loss": 0.5093,
      "step": 38161
    },
    {
      "epoch": 1.1723036279298376,
      "grad_norm": 0.4084574282169342,
      "learning_rate": 7.346127586803191e-06,
      "loss": 0.5181,
      "step": 38162
    },
    {
      "epoch": 1.1723343470647867,
      "grad_norm": 0.41634035110473633,
      "learning_rate": 7.345661641970885e-06,
      "loss": 0.515,
      "step": 38163
    },
    {
      "epoch": 1.1723650661997358,
      "grad_norm": 0.3592391014099121,
      "learning_rate": 7.345195703337975e-06,
      "loss": 0.4817,
      "step": 38164
    },
    {
      "epoch": 1.172395785334685,
      "grad_norm": 0.51210618019104,
      "learning_rate": 7.344729770905541e-06,
      "loss": 0.4644,
      "step": 38165
    },
    {
      "epoch": 1.1724265044696343,
      "grad_norm": 0.3864993155002594,
      "learning_rate": 7.344263844674682e-06,
      "loss": 0.4907,
      "step": 38166
    },
    {
      "epoch": 1.1724572236045834,
      "grad_norm": 0.41360411047935486,
      "learning_rate": 7.343797924646472e-06,
      "loss": 0.4625,
      "step": 38167
    },
    {
      "epoch": 1.1724879427395325,
      "grad_norm": 0.4107552170753479,
      "learning_rate": 7.343332010822015e-06,
      "loss": 0.4301,
      "step": 38168
    },
    {
      "epoch": 1.1725186618744816,
      "grad_norm": 0.39047229290008545,
      "learning_rate": 7.342866103202388e-06,
      "loss": 0.4719,
      "step": 38169
    },
    {
      "epoch": 1.1725493810094307,
      "grad_norm": 0.3984309136867523,
      "learning_rate": 7.3424002017886855e-06,
      "loss": 0.3959,
      "step": 38170
    },
    {
      "epoch": 1.1725801001443799,
      "grad_norm": 0.41870710253715515,
      "learning_rate": 7.34193430658199e-06,
      "loss": 0.4764,
      "step": 38171
    },
    {
      "epoch": 1.172610819279329,
      "grad_norm": 0.4247964322566986,
      "learning_rate": 7.341468417583391e-06,
      "loss": 0.5252,
      "step": 38172
    },
    {
      "epoch": 1.1726415384142783,
      "grad_norm": 0.4028679132461548,
      "learning_rate": 7.341002534793983e-06,
      "loss": 0.4389,
      "step": 38173
    },
    {
      "epoch": 1.1726722575492274,
      "grad_norm": 0.4493064880371094,
      "learning_rate": 7.340536658214844e-06,
      "loss": 0.5227,
      "step": 38174
    },
    {
      "epoch": 1.1727029766841766,
      "grad_norm": 0.4015650451183319,
      "learning_rate": 7.340070787847073e-06,
      "loss": 0.5522,
      "step": 38175
    },
    {
      "epoch": 1.1727336958191257,
      "grad_norm": 0.4257204234600067,
      "learning_rate": 7.33960492369175e-06,
      "loss": 0.5078,
      "step": 38176
    },
    {
      "epoch": 1.1727644149540748,
      "grad_norm": 0.38493290543556213,
      "learning_rate": 7.339139065749965e-06,
      "loss": 0.4815,
      "step": 38177
    },
    {
      "epoch": 1.1727951340890241,
      "grad_norm": 0.43365615606307983,
      "learning_rate": 7.3386732140228065e-06,
      "loss": 0.4706,
      "step": 38178
    },
    {
      "epoch": 1.1728258532239733,
      "grad_norm": 0.39143437147140503,
      "learning_rate": 7.338207368511364e-06,
      "loss": 0.4218,
      "step": 38179
    },
    {
      "epoch": 1.1728565723589224,
      "grad_norm": 0.42459937930107117,
      "learning_rate": 7.337741529216722e-06,
      "loss": 0.522,
      "step": 38180
    },
    {
      "epoch": 1.1728872914938715,
      "grad_norm": 0.4127047657966614,
      "learning_rate": 7.337275696139973e-06,
      "loss": 0.4728,
      "step": 38181
    },
    {
      "epoch": 1.1729180106288206,
      "grad_norm": 0.43618130683898926,
      "learning_rate": 7.3368098692822e-06,
      "loss": 0.4842,
      "step": 38182
    },
    {
      "epoch": 1.1729487297637697,
      "grad_norm": 0.40122345089912415,
      "learning_rate": 7.336344048644496e-06,
      "loss": 0.4288,
      "step": 38183
    },
    {
      "epoch": 1.172979448898719,
      "grad_norm": 0.37698301672935486,
      "learning_rate": 7.335878234227944e-06,
      "loss": 0.4569,
      "step": 38184
    },
    {
      "epoch": 1.1730101680336682,
      "grad_norm": 0.3849223852157593,
      "learning_rate": 7.335412426033637e-06,
      "loss": 0.5176,
      "step": 38185
    },
    {
      "epoch": 1.1730408871686173,
      "grad_norm": 0.38318973779678345,
      "learning_rate": 7.334946624062658e-06,
      "loss": 0.5058,
      "step": 38186
    },
    {
      "epoch": 1.1730716063035664,
      "grad_norm": 0.3770143389701843,
      "learning_rate": 7.334480828316099e-06,
      "loss": 0.4736,
      "step": 38187
    },
    {
      "epoch": 1.1731023254385156,
      "grad_norm": 0.4472016990184784,
      "learning_rate": 7.334015038795045e-06,
      "loss": 0.5636,
      "step": 38188
    },
    {
      "epoch": 1.173133044573465,
      "grad_norm": 0.39791396260261536,
      "learning_rate": 7.333549255500585e-06,
      "loss": 0.4719,
      "step": 38189
    },
    {
      "epoch": 1.173163763708414,
      "grad_norm": 0.3848189115524292,
      "learning_rate": 7.333083478433808e-06,
      "loss": 0.5282,
      "step": 38190
    },
    {
      "epoch": 1.1731944828433631,
      "grad_norm": 0.37805283069610596,
      "learning_rate": 7.3326177075957994e-06,
      "loss": 0.4993,
      "step": 38191
    },
    {
      "epoch": 1.1732252019783123,
      "grad_norm": 0.36105433106422424,
      "learning_rate": 7.332151942987651e-06,
      "loss": 0.4645,
      "step": 38192
    },
    {
      "epoch": 1.1732559211132614,
      "grad_norm": 0.42980003356933594,
      "learning_rate": 7.331686184610445e-06,
      "loss": 0.512,
      "step": 38193
    },
    {
      "epoch": 1.1732866402482105,
      "grad_norm": 0.376947283744812,
      "learning_rate": 7.331220432465273e-06,
      "loss": 0.4894,
      "step": 38194
    },
    {
      "epoch": 1.1733173593831598,
      "grad_norm": 0.38559597730636597,
      "learning_rate": 7.330754686553223e-06,
      "loss": 0.4941,
      "step": 38195
    },
    {
      "epoch": 1.173348078518109,
      "grad_norm": 0.376690149307251,
      "learning_rate": 7.3302889468753826e-06,
      "loss": 0.5496,
      "step": 38196
    },
    {
      "epoch": 1.173378797653058,
      "grad_norm": 0.3833836317062378,
      "learning_rate": 7.329823213432836e-06,
      "loss": 0.4636,
      "step": 38197
    },
    {
      "epoch": 1.1734095167880072,
      "grad_norm": 0.41416117548942566,
      "learning_rate": 7.32935748622668e-06,
      "loss": 0.4679,
      "step": 38198
    },
    {
      "epoch": 1.1734402359229563,
      "grad_norm": 0.41347214579582214,
      "learning_rate": 7.328891765257988e-06,
      "loss": 0.4493,
      "step": 38199
    },
    {
      "epoch": 1.1734709550579057,
      "grad_norm": 0.4169005751609802,
      "learning_rate": 7.328426050527863e-06,
      "loss": 0.5702,
      "step": 38200
    },
    {
      "epoch": 1.1735016741928548,
      "grad_norm": 0.35882043838500977,
      "learning_rate": 7.327960342037379e-06,
      "loss": 0.4479,
      "step": 38201
    },
    {
      "epoch": 1.173532393327804,
      "grad_norm": 0.3621900677680969,
      "learning_rate": 7.327494639787636e-06,
      "loss": 0.3894,
      "step": 38202
    },
    {
      "epoch": 1.173563112462753,
      "grad_norm": 0.3833077549934387,
      "learning_rate": 7.327028943779711e-06,
      "loss": 0.4408,
      "step": 38203
    },
    {
      "epoch": 1.1735938315977021,
      "grad_norm": 0.37177905440330505,
      "learning_rate": 7.326563254014701e-06,
      "loss": 0.4299,
      "step": 38204
    },
    {
      "epoch": 1.1736245507326513,
      "grad_norm": 0.3699350953102112,
      "learning_rate": 7.326097570493687e-06,
      "loss": 0.556,
      "step": 38205
    },
    {
      "epoch": 1.1736552698676006,
      "grad_norm": 0.3985835909843445,
      "learning_rate": 7.32563189321776e-06,
      "loss": 0.4879,
      "step": 38206
    },
    {
      "epoch": 1.1736859890025497,
      "grad_norm": 0.39217573404312134,
      "learning_rate": 7.3251662221880035e-06,
      "loss": 0.4662,
      "step": 38207
    },
    {
      "epoch": 1.1737167081374988,
      "grad_norm": 0.4246979057788849,
      "learning_rate": 7.324700557405507e-06,
      "loss": 0.4592,
      "step": 38208
    },
    {
      "epoch": 1.173747427272448,
      "grad_norm": 0.3611113131046295,
      "learning_rate": 7.324234898871365e-06,
      "loss": 0.4315,
      "step": 38209
    },
    {
      "epoch": 1.173778146407397,
      "grad_norm": 0.3733488619327545,
      "learning_rate": 7.323769246586656e-06,
      "loss": 0.4538,
      "step": 38210
    },
    {
      "epoch": 1.1738088655423464,
      "grad_norm": 0.3852531909942627,
      "learning_rate": 7.3233036005524715e-06,
      "loss": 0.4403,
      "step": 38211
    },
    {
      "epoch": 1.1738395846772955,
      "grad_norm": 0.4210026264190674,
      "learning_rate": 7.322837960769897e-06,
      "loss": 0.4642,
      "step": 38212
    },
    {
      "epoch": 1.1738703038122447,
      "grad_norm": 0.4041183292865753,
      "learning_rate": 7.322372327240023e-06,
      "loss": 0.5009,
      "step": 38213
    },
    {
      "epoch": 1.1739010229471938,
      "grad_norm": 0.40272489190101624,
      "learning_rate": 7.3219066999639345e-06,
      "loss": 0.4819,
      "step": 38214
    },
    {
      "epoch": 1.173931742082143,
      "grad_norm": 0.38101649284362793,
      "learning_rate": 7.3214410789427215e-06,
      "loss": 0.4829,
      "step": 38215
    },
    {
      "epoch": 1.173962461217092,
      "grad_norm": 0.47884759306907654,
      "learning_rate": 7.3209754641774685e-06,
      "loss": 0.5322,
      "step": 38216
    },
    {
      "epoch": 1.1739931803520414,
      "grad_norm": 0.40776994824409485,
      "learning_rate": 7.320509855669266e-06,
      "loss": 0.5867,
      "step": 38217
    },
    {
      "epoch": 1.1740238994869905,
      "grad_norm": 0.3979995846748352,
      "learning_rate": 7.320044253419197e-06,
      "loss": 0.4827,
      "step": 38218
    },
    {
      "epoch": 1.1740546186219396,
      "grad_norm": 0.3765912353992462,
      "learning_rate": 7.319578657428355e-06,
      "loss": 0.4706,
      "step": 38219
    },
    {
      "epoch": 1.1740853377568887,
      "grad_norm": 0.3742276430130005,
      "learning_rate": 7.3191130676978205e-06,
      "loss": 0.4492,
      "step": 38220
    },
    {
      "epoch": 1.1741160568918378,
      "grad_norm": 0.3923814594745636,
      "learning_rate": 7.318647484228689e-06,
      "loss": 0.4588,
      "step": 38221
    },
    {
      "epoch": 1.1741467760267872,
      "grad_norm": 0.4002762734889984,
      "learning_rate": 7.318181907022039e-06,
      "loss": 0.5265,
      "step": 38222
    },
    {
      "epoch": 1.1741774951617363,
      "grad_norm": 0.44990241527557373,
      "learning_rate": 7.317716336078967e-06,
      "loss": 0.51,
      "step": 38223
    },
    {
      "epoch": 1.1742082142966854,
      "grad_norm": 0.4383370578289032,
      "learning_rate": 7.317250771400552e-06,
      "loss": 0.3957,
      "step": 38224
    },
    {
      "epoch": 1.1742389334316345,
      "grad_norm": 0.3716123104095459,
      "learning_rate": 7.316785212987887e-06,
      "loss": 0.4472,
      "step": 38225
    },
    {
      "epoch": 1.1742696525665837,
      "grad_norm": 0.39694881439208984,
      "learning_rate": 7.316319660842057e-06,
      "loss": 0.4576,
      "step": 38226
    },
    {
      "epoch": 1.1743003717015328,
      "grad_norm": 0.4358331263065338,
      "learning_rate": 7.31585411496415e-06,
      "loss": 0.478,
      "step": 38227
    },
    {
      "epoch": 1.1743310908364821,
      "grad_norm": 0.38895469903945923,
      "learning_rate": 7.315388575355256e-06,
      "loss": 0.4799,
      "step": 38228
    },
    {
      "epoch": 1.1743618099714312,
      "grad_norm": 0.45689159631729126,
      "learning_rate": 7.314923042016455e-06,
      "loss": 0.5033,
      "step": 38229
    },
    {
      "epoch": 1.1743925291063804,
      "grad_norm": 0.48757901787757874,
      "learning_rate": 7.31445751494884e-06,
      "loss": 0.4745,
      "step": 38230
    },
    {
      "epoch": 1.1744232482413295,
      "grad_norm": 0.41528066992759705,
      "learning_rate": 7.313991994153498e-06,
      "loss": 0.5123,
      "step": 38231
    },
    {
      "epoch": 1.1744539673762786,
      "grad_norm": 0.3711129128932953,
      "learning_rate": 7.3135264796315185e-06,
      "loss": 0.4896,
      "step": 38232
    },
    {
      "epoch": 1.174484686511228,
      "grad_norm": 0.4020887017250061,
      "learning_rate": 7.313060971383978e-06,
      "loss": 0.3873,
      "step": 38233
    },
    {
      "epoch": 1.174515405646177,
      "grad_norm": 0.3734980523586273,
      "learning_rate": 7.312595469411979e-06,
      "loss": 0.4905,
      "step": 38234
    },
    {
      "epoch": 1.1745461247811262,
      "grad_norm": 0.3941723108291626,
      "learning_rate": 7.312129973716594e-06,
      "loss": 0.4344,
      "step": 38235
    },
    {
      "epoch": 1.1745768439160753,
      "grad_norm": 0.44211864471435547,
      "learning_rate": 7.311664484298924e-06,
      "loss": 0.4561,
      "step": 38236
    },
    {
      "epoch": 1.1746075630510244,
      "grad_norm": 0.38867488503456116,
      "learning_rate": 7.311199001160042e-06,
      "loss": 0.4417,
      "step": 38237
    },
    {
      "epoch": 1.1746382821859735,
      "grad_norm": 0.4087494909763336,
      "learning_rate": 7.31073352430105e-06,
      "loss": 0.4984,
      "step": 38238
    },
    {
      "epoch": 1.174669001320923,
      "grad_norm": 0.3894682824611664,
      "learning_rate": 7.3102680537230216e-06,
      "loss": 0.5439,
      "step": 38239
    },
    {
      "epoch": 1.174699720455872,
      "grad_norm": 0.4956413209438324,
      "learning_rate": 7.309802589427054e-06,
      "loss": 0.4858,
      "step": 38240
    },
    {
      "epoch": 1.1747304395908211,
      "grad_norm": 0.41942718625068665,
      "learning_rate": 7.309337131414228e-06,
      "loss": 0.4825,
      "step": 38241
    },
    {
      "epoch": 1.1747611587257702,
      "grad_norm": 0.4355858862400055,
      "learning_rate": 7.308871679685634e-06,
      "loss": 0.484,
      "step": 38242
    },
    {
      "epoch": 1.1747918778607194,
      "grad_norm": 0.39418455958366394,
      "learning_rate": 7.308406234242358e-06,
      "loss": 0.5434,
      "step": 38243
    },
    {
      "epoch": 1.1748225969956687,
      "grad_norm": 0.4265308678150177,
      "learning_rate": 7.307940795085484e-06,
      "loss": 0.457,
      "step": 38244
    },
    {
      "epoch": 1.1748533161306178,
      "grad_norm": 0.3930363953113556,
      "learning_rate": 7.307475362216108e-06,
      "loss": 0.4428,
      "step": 38245
    },
    {
      "epoch": 1.174884035265567,
      "grad_norm": 0.4221149981021881,
      "learning_rate": 7.3070099356353076e-06,
      "loss": 0.5229,
      "step": 38246
    },
    {
      "epoch": 1.174914754400516,
      "grad_norm": 0.38190174102783203,
      "learning_rate": 7.306544515344176e-06,
      "loss": 0.5222,
      "step": 38247
    },
    {
      "epoch": 1.1749454735354652,
      "grad_norm": 0.4188251793384552,
      "learning_rate": 7.306079101343795e-06,
      "loss": 0.4954,
      "step": 38248
    },
    {
      "epoch": 1.1749761926704143,
      "grad_norm": 0.42147621512413025,
      "learning_rate": 7.305613693635257e-06,
      "loss": 0.4159,
      "step": 38249
    },
    {
      "epoch": 1.1750069118053637,
      "grad_norm": 0.405571311712265,
      "learning_rate": 7.305148292219644e-06,
      "loss": 0.4953,
      "step": 38250
    },
    {
      "epoch": 1.1750376309403128,
      "grad_norm": 0.3723185360431671,
      "learning_rate": 7.304682897098047e-06,
      "loss": 0.4685,
      "step": 38251
    },
    {
      "epoch": 1.175068350075262,
      "grad_norm": 0.41118526458740234,
      "learning_rate": 7.304217508271552e-06,
      "loss": 0.4102,
      "step": 38252
    },
    {
      "epoch": 1.175099069210211,
      "grad_norm": 0.3827782869338989,
      "learning_rate": 7.303752125741244e-06,
      "loss": 0.419,
      "step": 38253
    },
    {
      "epoch": 1.1751297883451601,
      "grad_norm": 0.40729784965515137,
      "learning_rate": 7.303286749508211e-06,
      "loss": 0.4779,
      "step": 38254
    },
    {
      "epoch": 1.1751605074801095,
      "grad_norm": 0.3861715793609619,
      "learning_rate": 7.302821379573542e-06,
      "loss": 0.5389,
      "step": 38255
    },
    {
      "epoch": 1.1751912266150586,
      "grad_norm": 0.39399099349975586,
      "learning_rate": 7.3023560159383185e-06,
      "loss": 0.5085,
      "step": 38256
    },
    {
      "epoch": 1.1752219457500077,
      "grad_norm": 0.5022055506706238,
      "learning_rate": 7.301890658603634e-06,
      "loss": 0.4135,
      "step": 38257
    },
    {
      "epoch": 1.1752526648849568,
      "grad_norm": 0.42326974868774414,
      "learning_rate": 7.301425307570571e-06,
      "loss": 0.4485,
      "step": 38258
    },
    {
      "epoch": 1.175283384019906,
      "grad_norm": 0.3808606266975403,
      "learning_rate": 7.30095996284022e-06,
      "loss": 0.4329,
      "step": 38259
    },
    {
      "epoch": 1.175314103154855,
      "grad_norm": 0.3700239956378937,
      "learning_rate": 7.300494624413661e-06,
      "loss": 0.5747,
      "step": 38260
    },
    {
      "epoch": 1.1753448222898044,
      "grad_norm": 0.4304943084716797,
      "learning_rate": 7.300029292291991e-06,
      "loss": 0.4814,
      "step": 38261
    },
    {
      "epoch": 1.1753755414247535,
      "grad_norm": 0.42495349049568176,
      "learning_rate": 7.299563966476285e-06,
      "loss": 0.5191,
      "step": 38262
    },
    {
      "epoch": 1.1754062605597027,
      "grad_norm": 0.3787766396999359,
      "learning_rate": 7.299098646967637e-06,
      "loss": 0.4912,
      "step": 38263
    },
    {
      "epoch": 1.1754369796946518,
      "grad_norm": 0.42635083198547363,
      "learning_rate": 7.298633333767137e-06,
      "loss": 0.5611,
      "step": 38264
    },
    {
      "epoch": 1.175467698829601,
      "grad_norm": 0.37815332412719727,
      "learning_rate": 7.298168026875864e-06,
      "loss": 0.4685,
      "step": 38265
    },
    {
      "epoch": 1.1754984179645502,
      "grad_norm": 0.40357059240341187,
      "learning_rate": 7.297702726294911e-06,
      "loss": 0.4491,
      "step": 38266
    },
    {
      "epoch": 1.1755291370994994,
      "grad_norm": 0.41482216119766235,
      "learning_rate": 7.297237432025359e-06,
      "loss": 0.4708,
      "step": 38267
    },
    {
      "epoch": 1.1755598562344485,
      "grad_norm": 0.3927702307701111,
      "learning_rate": 7.296772144068303e-06,
      "loss": 0.4496,
      "step": 38268
    },
    {
      "epoch": 1.1755905753693976,
      "grad_norm": 0.3811015486717224,
      "learning_rate": 7.296306862424817e-06,
      "loss": 0.4737,
      "step": 38269
    },
    {
      "epoch": 1.1756212945043467,
      "grad_norm": 0.38209763169288635,
      "learning_rate": 7.295841587096002e-06,
      "loss": 0.4184,
      "step": 38270
    },
    {
      "epoch": 1.1756520136392958,
      "grad_norm": 0.37905704975128174,
      "learning_rate": 7.295376318082932e-06,
      "loss": 0.5025,
      "step": 38271
    },
    {
      "epoch": 1.175682732774245,
      "grad_norm": 0.41965818405151367,
      "learning_rate": 7.294911055386704e-06,
      "loss": 0.4281,
      "step": 38272
    },
    {
      "epoch": 1.1757134519091943,
      "grad_norm": 0.36773261427879333,
      "learning_rate": 7.294445799008398e-06,
      "loss": 0.4595,
      "step": 38273
    },
    {
      "epoch": 1.1757441710441434,
      "grad_norm": 0.404353529214859,
      "learning_rate": 7.293980548949105e-06,
      "loss": 0.4676,
      "step": 38274
    },
    {
      "epoch": 1.1757748901790925,
      "grad_norm": 0.47203826904296875,
      "learning_rate": 7.293515305209906e-06,
      "loss": 0.4513,
      "step": 38275
    },
    {
      "epoch": 1.1758056093140417,
      "grad_norm": 0.40735775232315063,
      "learning_rate": 7.2930500677918936e-06,
      "loss": 0.5034,
      "step": 38276
    },
    {
      "epoch": 1.175836328448991,
      "grad_norm": 0.3945184648036957,
      "learning_rate": 7.292584836696148e-06,
      "loss": 0.5227,
      "step": 38277
    },
    {
      "epoch": 1.1758670475839401,
      "grad_norm": 0.4148262143135071,
      "learning_rate": 7.292119611923765e-06,
      "loss": 0.5221,
      "step": 38278
    },
    {
      "epoch": 1.1758977667188892,
      "grad_norm": 3.8379456996917725,
      "learning_rate": 7.2916543934758225e-06,
      "loss": 0.4924,
      "step": 38279
    },
    {
      "epoch": 1.1759284858538384,
      "grad_norm": 0.45148131251335144,
      "learning_rate": 7.291189181353409e-06,
      "loss": 0.5388,
      "step": 38280
    },
    {
      "epoch": 1.1759592049887875,
      "grad_norm": 0.43076813220977783,
      "learning_rate": 7.290723975557615e-06,
      "loss": 0.4071,
      "step": 38281
    },
    {
      "epoch": 1.1759899241237366,
      "grad_norm": 0.42190560698509216,
      "learning_rate": 7.290258776089523e-06,
      "loss": 0.4956,
      "step": 38282
    },
    {
      "epoch": 1.1760206432586857,
      "grad_norm": 0.40089306235313416,
      "learning_rate": 7.289793582950222e-06,
      "loss": 0.4243,
      "step": 38283
    },
    {
      "epoch": 1.176051362393635,
      "grad_norm": 0.41635242104530334,
      "learning_rate": 7.289328396140795e-06,
      "loss": 0.5404,
      "step": 38284
    },
    {
      "epoch": 1.1760820815285842,
      "grad_norm": 0.467489093542099,
      "learning_rate": 7.288863215662335e-06,
      "loss": 0.475,
      "step": 38285
    },
    {
      "epoch": 1.1761128006635333,
      "grad_norm": 0.39768946170806885,
      "learning_rate": 7.2883980415159205e-06,
      "loss": 0.533,
      "step": 38286
    },
    {
      "epoch": 1.1761435197984824,
      "grad_norm": 0.37636634707450867,
      "learning_rate": 7.287932873702645e-06,
      "loss": 0.4281,
      "step": 38287
    },
    {
      "epoch": 1.1761742389334318,
      "grad_norm": 0.38136759400367737,
      "learning_rate": 7.287467712223588e-06,
      "loss": 0.4443,
      "step": 38288
    },
    {
      "epoch": 1.1762049580683809,
      "grad_norm": 0.4207957088947296,
      "learning_rate": 7.287002557079843e-06,
      "loss": 0.5033,
      "step": 38289
    },
    {
      "epoch": 1.17623567720333,
      "grad_norm": 0.3666040897369385,
      "learning_rate": 7.28653740827249e-06,
      "loss": 0.4933,
      "step": 38290
    },
    {
      "epoch": 1.1762663963382791,
      "grad_norm": 0.4008415639400482,
      "learning_rate": 7.286072265802621e-06,
      "loss": 0.5281,
      "step": 38291
    },
    {
      "epoch": 1.1762971154732282,
      "grad_norm": 0.3999003767967224,
      "learning_rate": 7.285607129671319e-06,
      "loss": 0.4788,
      "step": 38292
    },
    {
      "epoch": 1.1763278346081774,
      "grad_norm": 0.48137226700782776,
      "learning_rate": 7.285141999879671e-06,
      "loss": 0.4677,
      "step": 38293
    },
    {
      "epoch": 1.1763585537431265,
      "grad_norm": 0.37322092056274414,
      "learning_rate": 7.2846768764287624e-06,
      "loss": 0.4956,
      "step": 38294
    },
    {
      "epoch": 1.1763892728780758,
      "grad_norm": 0.39380407333374023,
      "learning_rate": 7.284211759319685e-06,
      "loss": 0.491,
      "step": 38295
    },
    {
      "epoch": 1.176419992013025,
      "grad_norm": 0.36771759390830994,
      "learning_rate": 7.283746648553513e-06,
      "loss": 0.4776,
      "step": 38296
    },
    {
      "epoch": 1.176450711147974,
      "grad_norm": 0.41406068205833435,
      "learning_rate": 7.283281544131349e-06,
      "loss": 0.4563,
      "step": 38297
    },
    {
      "epoch": 1.1764814302829232,
      "grad_norm": 0.3606850504875183,
      "learning_rate": 7.282816446054263e-06,
      "loss": 0.4499,
      "step": 38298
    },
    {
      "epoch": 1.1765121494178723,
      "grad_norm": 0.3999437391757965,
      "learning_rate": 7.28235135432335e-06,
      "loss": 0.5085,
      "step": 38299
    },
    {
      "epoch": 1.1765428685528216,
      "grad_norm": 0.381365567445755,
      "learning_rate": 7.2818862689396995e-06,
      "loss": 0.4992,
      "step": 38300
    },
    {
      "epoch": 1.1765735876877708,
      "grad_norm": 0.4525010585784912,
      "learning_rate": 7.28142118990439e-06,
      "loss": 0.5204,
      "step": 38301
    },
    {
      "epoch": 1.1766043068227199,
      "grad_norm": 0.3958549499511719,
      "learning_rate": 7.280956117218516e-06,
      "loss": 0.4982,
      "step": 38302
    },
    {
      "epoch": 1.176635025957669,
      "grad_norm": 0.38206589221954346,
      "learning_rate": 7.280491050883152e-06,
      "loss": 0.4172,
      "step": 38303
    },
    {
      "epoch": 1.1766657450926181,
      "grad_norm": 0.3977448642253876,
      "learning_rate": 7.280025990899398e-06,
      "loss": 0.4801,
      "step": 38304
    },
    {
      "epoch": 1.1766964642275672,
      "grad_norm": 0.373574435710907,
      "learning_rate": 7.279560937268326e-06,
      "loss": 0.56,
      "step": 38305
    },
    {
      "epoch": 1.1767271833625166,
      "grad_norm": 0.34299135208129883,
      "learning_rate": 7.279095889991037e-06,
      "loss": 0.4927,
      "step": 38306
    },
    {
      "epoch": 1.1767579024974657,
      "grad_norm": 0.41193699836730957,
      "learning_rate": 7.278630849068602e-06,
      "loss": 0.499,
      "step": 38307
    },
    {
      "epoch": 1.1767886216324148,
      "grad_norm": 0.384733110666275,
      "learning_rate": 7.278165814502123e-06,
      "loss": 0.4798,
      "step": 38308
    },
    {
      "epoch": 1.176819340767364,
      "grad_norm": 0.4176709055900574,
      "learning_rate": 7.277700786292672e-06,
      "loss": 0.5144,
      "step": 38309
    },
    {
      "epoch": 1.176850059902313,
      "grad_norm": 0.393006831407547,
      "learning_rate": 7.277235764441342e-06,
      "loss": 0.4839,
      "step": 38310
    },
    {
      "epoch": 1.1768807790372624,
      "grad_norm": 0.3839729130268097,
      "learning_rate": 7.276770748949218e-06,
      "loss": 0.4651,
      "step": 38311
    },
    {
      "epoch": 1.1769114981722115,
      "grad_norm": 0.4898962676525116,
      "learning_rate": 7.276305739817387e-06,
      "loss": 0.4549,
      "step": 38312
    },
    {
      "epoch": 1.1769422173071606,
      "grad_norm": 0.420603483915329,
      "learning_rate": 7.275840737046933e-06,
      "loss": 0.4954,
      "step": 38313
    },
    {
      "epoch": 1.1769729364421098,
      "grad_norm": 0.4294295907020569,
      "learning_rate": 7.275375740638944e-06,
      "loss": 0.4946,
      "step": 38314
    },
    {
      "epoch": 1.1770036555770589,
      "grad_norm": 0.41101938486099243,
      "learning_rate": 7.2749107505945035e-06,
      "loss": 0.5073,
      "step": 38315
    },
    {
      "epoch": 1.177034374712008,
      "grad_norm": 0.48401474952697754,
      "learning_rate": 7.274445766914703e-06,
      "loss": 0.5081,
      "step": 38316
    },
    {
      "epoch": 1.1770650938469573,
      "grad_norm": 0.41878870129585266,
      "learning_rate": 7.273980789600621e-06,
      "loss": 0.5112,
      "step": 38317
    },
    {
      "epoch": 1.1770958129819065,
      "grad_norm": 0.39575937390327454,
      "learning_rate": 7.273515818653347e-06,
      "loss": 0.5368,
      "step": 38318
    },
    {
      "epoch": 1.1771265321168556,
      "grad_norm": 0.40731313824653625,
      "learning_rate": 7.273050854073971e-06,
      "loss": 0.4712,
      "step": 38319
    },
    {
      "epoch": 1.1771572512518047,
      "grad_norm": 0.4122251868247986,
      "learning_rate": 7.272585895863572e-06,
      "loss": 0.4949,
      "step": 38320
    },
    {
      "epoch": 1.1771879703867538,
      "grad_norm": 0.4134660065174103,
      "learning_rate": 7.272120944023242e-06,
      "loss": 0.5107,
      "step": 38321
    },
    {
      "epoch": 1.1772186895217032,
      "grad_norm": 0.4133107662200928,
      "learning_rate": 7.271655998554061e-06,
      "loss": 0.51,
      "step": 38322
    },
    {
      "epoch": 1.1772494086566523,
      "grad_norm": 0.41223081946372986,
      "learning_rate": 7.27119105945712e-06,
      "loss": 0.5106,
      "step": 38323
    },
    {
      "epoch": 1.1772801277916014,
      "grad_norm": 0.3715841472148895,
      "learning_rate": 7.270726126733501e-06,
      "loss": 0.4571,
      "step": 38324
    },
    {
      "epoch": 1.1773108469265505,
      "grad_norm": 0.41393807530403137,
      "learning_rate": 7.270261200384294e-06,
      "loss": 0.4723,
      "step": 38325
    },
    {
      "epoch": 1.1773415660614996,
      "grad_norm": 0.3803037106990814,
      "learning_rate": 7.269796280410582e-06,
      "loss": 0.5035,
      "step": 38326
    },
    {
      "epoch": 1.1773722851964488,
      "grad_norm": 0.38286978006362915,
      "learning_rate": 7.26933136681345e-06,
      "loss": 0.4686,
      "step": 38327
    },
    {
      "epoch": 1.177403004331398,
      "grad_norm": 0.41584017872810364,
      "learning_rate": 7.2688664595939865e-06,
      "loss": 0.5174,
      "step": 38328
    },
    {
      "epoch": 1.1774337234663472,
      "grad_norm": 0.37405312061309814,
      "learning_rate": 7.268401558753276e-06,
      "loss": 0.5473,
      "step": 38329
    },
    {
      "epoch": 1.1774644426012963,
      "grad_norm": 0.4150308072566986,
      "learning_rate": 7.267936664292403e-06,
      "loss": 0.3642,
      "step": 38330
    },
    {
      "epoch": 1.1774951617362455,
      "grad_norm": 0.38747984170913696,
      "learning_rate": 7.26747177621246e-06,
      "loss": 0.4428,
      "step": 38331
    },
    {
      "epoch": 1.1775258808711946,
      "grad_norm": 0.9976147413253784,
      "learning_rate": 7.267006894514521e-06,
      "loss": 0.433,
      "step": 38332
    },
    {
      "epoch": 1.177556600006144,
      "grad_norm": 0.41550546884536743,
      "learning_rate": 7.266542019199683e-06,
      "loss": 0.5362,
      "step": 38333
    },
    {
      "epoch": 1.177587319141093,
      "grad_norm": 0.3884138762950897,
      "learning_rate": 7.266077150269022e-06,
      "loss": 0.4837,
      "step": 38334
    },
    {
      "epoch": 1.1776180382760422,
      "grad_norm": 0.4349948465824127,
      "learning_rate": 7.265612287723631e-06,
      "loss": 0.5885,
      "step": 38335
    },
    {
      "epoch": 1.1776487574109913,
      "grad_norm": 0.39691364765167236,
      "learning_rate": 7.265147431564594e-06,
      "loss": 0.5444,
      "step": 38336
    },
    {
      "epoch": 1.1776794765459404,
      "grad_norm": 0.3889229893684387,
      "learning_rate": 7.264682581792997e-06,
      "loss": 0.4845,
      "step": 38337
    },
    {
      "epoch": 1.1777101956808895,
      "grad_norm": 0.42365506291389465,
      "learning_rate": 7.264217738409926e-06,
      "loss": 0.503,
      "step": 38338
    },
    {
      "epoch": 1.1777409148158389,
      "grad_norm": 0.4626255929470062,
      "learning_rate": 7.263752901416461e-06,
      "loss": 0.4334,
      "step": 38339
    },
    {
      "epoch": 1.177771633950788,
      "grad_norm": 0.4030575454235077,
      "learning_rate": 7.263288070813698e-06,
      "loss": 0.4593,
      "step": 38340
    },
    {
      "epoch": 1.177802353085737,
      "grad_norm": 0.4442136287689209,
      "learning_rate": 7.2628232466027105e-06,
      "loss": 0.4859,
      "step": 38341
    },
    {
      "epoch": 1.1778330722206862,
      "grad_norm": 0.4114741384983063,
      "learning_rate": 7.262358428784597e-06,
      "loss": 0.4877,
      "step": 38342
    },
    {
      "epoch": 1.1778637913556353,
      "grad_norm": 0.38682976365089417,
      "learning_rate": 7.261893617360432e-06,
      "loss": 0.4793,
      "step": 38343
    },
    {
      "epoch": 1.1778945104905847,
      "grad_norm": 0.3762219250202179,
      "learning_rate": 7.261428812331308e-06,
      "loss": 0.3861,
      "step": 38344
    },
    {
      "epoch": 1.1779252296255338,
      "grad_norm": 0.46199336647987366,
      "learning_rate": 7.260964013698306e-06,
      "loss": 0.4746,
      "step": 38345
    },
    {
      "epoch": 1.177955948760483,
      "grad_norm": 0.8093759417533875,
      "learning_rate": 7.260499221462516e-06,
      "loss": 0.4382,
      "step": 38346
    },
    {
      "epoch": 1.177986667895432,
      "grad_norm": 0.3443109393119812,
      "learning_rate": 7.2600344356250184e-06,
      "loss": 0.4471,
      "step": 38347
    },
    {
      "epoch": 1.1780173870303812,
      "grad_norm": 0.38341256976127625,
      "learning_rate": 7.259569656186905e-06,
      "loss": 0.4264,
      "step": 38348
    },
    {
      "epoch": 1.1780481061653303,
      "grad_norm": 0.4201861321926117,
      "learning_rate": 7.259104883149257e-06,
      "loss": 0.5093,
      "step": 38349
    },
    {
      "epoch": 1.1780788253002796,
      "grad_norm": 0.38390231132507324,
      "learning_rate": 7.258640116513162e-06,
      "loss": 0.4812,
      "step": 38350
    },
    {
      "epoch": 1.1781095444352288,
      "grad_norm": 0.5846291780471802,
      "learning_rate": 7.258175356279702e-06,
      "loss": 0.5267,
      "step": 38351
    },
    {
      "epoch": 1.1781402635701779,
      "grad_norm": 0.43302810192108154,
      "learning_rate": 7.257710602449967e-06,
      "loss": 0.46,
      "step": 38352
    },
    {
      "epoch": 1.178170982705127,
      "grad_norm": 0.40172311663627625,
      "learning_rate": 7.257245855025038e-06,
      "loss": 0.5081,
      "step": 38353
    },
    {
      "epoch": 1.178201701840076,
      "grad_norm": 0.36765167117118835,
      "learning_rate": 7.256781114006004e-06,
      "loss": 0.4982,
      "step": 38354
    },
    {
      "epoch": 1.1782324209750255,
      "grad_norm": 0.419430673122406,
      "learning_rate": 7.2563163793939505e-06,
      "loss": 0.4468,
      "step": 38355
    },
    {
      "epoch": 1.1782631401099746,
      "grad_norm": 0.4101925492286682,
      "learning_rate": 7.25585165118996e-06,
      "loss": 0.4483,
      "step": 38356
    },
    {
      "epoch": 1.1782938592449237,
      "grad_norm": 0.43414032459259033,
      "learning_rate": 7.255386929395121e-06,
      "loss": 0.5129,
      "step": 38357
    },
    {
      "epoch": 1.1783245783798728,
      "grad_norm": 0.38568875193595886,
      "learning_rate": 7.254922214010516e-06,
      "loss": 0.4806,
      "step": 38358
    },
    {
      "epoch": 1.178355297514822,
      "grad_norm": 0.36547034978866577,
      "learning_rate": 7.254457505037235e-06,
      "loss": 0.5078,
      "step": 38359
    },
    {
      "epoch": 1.178386016649771,
      "grad_norm": 0.3612224757671356,
      "learning_rate": 7.253992802476357e-06,
      "loss": 0.4728,
      "step": 38360
    },
    {
      "epoch": 1.1784167357847204,
      "grad_norm": 0.487199068069458,
      "learning_rate": 7.253528106328973e-06,
      "loss": 0.516,
      "step": 38361
    },
    {
      "epoch": 1.1784474549196695,
      "grad_norm": 0.4284682869911194,
      "learning_rate": 7.253063416596163e-06,
      "loss": 0.4747,
      "step": 38362
    },
    {
      "epoch": 1.1784781740546186,
      "grad_norm": 0.38629665970802307,
      "learning_rate": 7.252598733279018e-06,
      "loss": 0.5784,
      "step": 38363
    },
    {
      "epoch": 1.1785088931895678,
      "grad_norm": 0.5705215334892273,
      "learning_rate": 7.252134056378619e-06,
      "loss": 0.4727,
      "step": 38364
    },
    {
      "epoch": 1.1785396123245169,
      "grad_norm": 0.3921964764595032,
      "learning_rate": 7.2516693858960564e-06,
      "loss": 0.4512,
      "step": 38365
    },
    {
      "epoch": 1.1785703314594662,
      "grad_norm": 0.3668782711029053,
      "learning_rate": 7.251204721832405e-06,
      "loss": 0.4378,
      "step": 38366
    },
    {
      "epoch": 1.1786010505944153,
      "grad_norm": 0.4028550684452057,
      "learning_rate": 7.250740064188763e-06,
      "loss": 0.5045,
      "step": 38367
    },
    {
      "epoch": 1.1786317697293645,
      "grad_norm": 0.42946889996528625,
      "learning_rate": 7.250275412966205e-06,
      "loss": 0.491,
      "step": 38368
    },
    {
      "epoch": 1.1786624888643136,
      "grad_norm": 0.42383071780204773,
      "learning_rate": 7.249810768165826e-06,
      "loss": 0.4714,
      "step": 38369
    },
    {
      "epoch": 1.1786932079992627,
      "grad_norm": 0.40806078910827637,
      "learning_rate": 7.249346129788701e-06,
      "loss": 0.401,
      "step": 38370
    },
    {
      "epoch": 1.1787239271342118,
      "grad_norm": 0.3829353451728821,
      "learning_rate": 7.24888149783592e-06,
      "loss": 0.4461,
      "step": 38371
    },
    {
      "epoch": 1.1787546462691612,
      "grad_norm": 0.3994465172290802,
      "learning_rate": 7.248416872308574e-06,
      "loss": 0.4767,
      "step": 38372
    },
    {
      "epoch": 1.1787853654041103,
      "grad_norm": 0.41678133606910706,
      "learning_rate": 7.247952253207738e-06,
      "loss": 0.4704,
      "step": 38373
    },
    {
      "epoch": 1.1788160845390594,
      "grad_norm": 0.4233435094356537,
      "learning_rate": 7.2474876405345054e-06,
      "loss": 0.4799,
      "step": 38374
    },
    {
      "epoch": 1.1788468036740085,
      "grad_norm": 0.48827221989631653,
      "learning_rate": 7.247023034289952e-06,
      "loss": 0.4907,
      "step": 38375
    },
    {
      "epoch": 1.1788775228089576,
      "grad_norm": 0.4674427807331085,
      "learning_rate": 7.246558434475175e-06,
      "loss": 0.5386,
      "step": 38376
    },
    {
      "epoch": 1.178908241943907,
      "grad_norm": 0.39982637763023376,
      "learning_rate": 7.246093841091247e-06,
      "loss": 0.491,
      "step": 38377
    },
    {
      "epoch": 1.178938961078856,
      "grad_norm": 0.42528945207595825,
      "learning_rate": 7.245629254139265e-06,
      "loss": 0.5773,
      "step": 38378
    },
    {
      "epoch": 1.1789696802138052,
      "grad_norm": 0.40918275713920593,
      "learning_rate": 7.245164673620304e-06,
      "loss": 0.4849,
      "step": 38379
    },
    {
      "epoch": 1.1790003993487543,
      "grad_norm": 0.43168166279792786,
      "learning_rate": 7.244700099535455e-06,
      "loss": 0.5178,
      "step": 38380
    },
    {
      "epoch": 1.1790311184837035,
      "grad_norm": 0.3851706087589264,
      "learning_rate": 7.244235531885802e-06,
      "loss": 0.5086,
      "step": 38381
    },
    {
      "epoch": 1.1790618376186526,
      "grad_norm": 0.3704490661621094,
      "learning_rate": 7.243770970672428e-06,
      "loss": 0.5152,
      "step": 38382
    },
    {
      "epoch": 1.1790925567536017,
      "grad_norm": 0.4310045838356018,
      "learning_rate": 7.243306415896418e-06,
      "loss": 0.4813,
      "step": 38383
    },
    {
      "epoch": 1.179123275888551,
      "grad_norm": 0.3838377594947815,
      "learning_rate": 7.242841867558863e-06,
      "loss": 0.4998,
      "step": 38384
    },
    {
      "epoch": 1.1791539950235002,
      "grad_norm": 0.38816049695014954,
      "learning_rate": 7.242377325660839e-06,
      "loss": 0.5016,
      "step": 38385
    },
    {
      "epoch": 1.1791847141584493,
      "grad_norm": 0.36745983362197876,
      "learning_rate": 7.241912790203438e-06,
      "loss": 0.4244,
      "step": 38386
    },
    {
      "epoch": 1.1792154332933984,
      "grad_norm": 0.3903661072254181,
      "learning_rate": 7.24144826118774e-06,
      "loss": 0.484,
      "step": 38387
    },
    {
      "epoch": 1.1792461524283477,
      "grad_norm": 0.41683363914489746,
      "learning_rate": 7.240983738614834e-06,
      "loss": 0.5221,
      "step": 38388
    },
    {
      "epoch": 1.1792768715632969,
      "grad_norm": 0.39235588908195496,
      "learning_rate": 7.240519222485802e-06,
      "loss": 0.4378,
      "step": 38389
    },
    {
      "epoch": 1.179307590698246,
      "grad_norm": 0.37695133686065674,
      "learning_rate": 7.24005471280173e-06,
      "loss": 0.4935,
      "step": 38390
    },
    {
      "epoch": 1.179338309833195,
      "grad_norm": 0.42188912630081177,
      "learning_rate": 7.2395902095637035e-06,
      "loss": 0.5508,
      "step": 38391
    },
    {
      "epoch": 1.1793690289681442,
      "grad_norm": 0.3818901479244232,
      "learning_rate": 7.2391257127728066e-06,
      "loss": 0.4869,
      "step": 38392
    },
    {
      "epoch": 1.1793997481030933,
      "grad_norm": 0.3927029073238373,
      "learning_rate": 7.238661222430126e-06,
      "loss": 0.5429,
      "step": 38393
    },
    {
      "epoch": 1.1794304672380425,
      "grad_norm": 0.36124104261398315,
      "learning_rate": 7.238196738536742e-06,
      "loss": 0.4765,
      "step": 38394
    },
    {
      "epoch": 1.1794611863729918,
      "grad_norm": 0.43617111444473267,
      "learning_rate": 7.2377322610937464e-06,
      "loss": 0.4937,
      "step": 38395
    },
    {
      "epoch": 1.179491905507941,
      "grad_norm": 0.37944507598876953,
      "learning_rate": 7.237267790102216e-06,
      "loss": 0.4517,
      "step": 38396
    },
    {
      "epoch": 1.17952262464289,
      "grad_norm": 0.37764161825180054,
      "learning_rate": 7.236803325563242e-06,
      "loss": 0.4907,
      "step": 38397
    },
    {
      "epoch": 1.1795533437778392,
      "grad_norm": 0.40466633439064026,
      "learning_rate": 7.2363388674779054e-06,
      "loss": 0.5048,
      "step": 38398
    },
    {
      "epoch": 1.1795840629127885,
      "grad_norm": 0.37299081683158875,
      "learning_rate": 7.235874415847295e-06,
      "loss": 0.4427,
      "step": 38399
    },
    {
      "epoch": 1.1796147820477376,
      "grad_norm": 0.4006350040435791,
      "learning_rate": 7.235409970672489e-06,
      "loss": 0.4747,
      "step": 38400
    },
    {
      "epoch": 1.1796455011826867,
      "grad_norm": 0.39881330728530884,
      "learning_rate": 7.2349455319545825e-06,
      "loss": 0.5111,
      "step": 38401
    },
    {
      "epoch": 1.1796762203176359,
      "grad_norm": 0.3981975018978119,
      "learning_rate": 7.234481099694646e-06,
      "loss": 0.449,
      "step": 38402
    },
    {
      "epoch": 1.179706939452585,
      "grad_norm": 0.39759594202041626,
      "learning_rate": 7.234016673893778e-06,
      "loss": 0.4899,
      "step": 38403
    },
    {
      "epoch": 1.179737658587534,
      "grad_norm": 0.4257930517196655,
      "learning_rate": 7.233552254553053e-06,
      "loss": 0.4597,
      "step": 38404
    },
    {
      "epoch": 1.1797683777224832,
      "grad_norm": 0.40189120173454285,
      "learning_rate": 7.233087841673564e-06,
      "loss": 0.4958,
      "step": 38405
    },
    {
      "epoch": 1.1797990968574326,
      "grad_norm": 0.44881486892700195,
      "learning_rate": 7.232623435256389e-06,
      "loss": 0.5206,
      "step": 38406
    },
    {
      "epoch": 1.1798298159923817,
      "grad_norm": 0.3733363747596741,
      "learning_rate": 7.232159035302616e-06,
      "loss": 0.4599,
      "step": 38407
    },
    {
      "epoch": 1.1798605351273308,
      "grad_norm": 0.3706199526786804,
      "learning_rate": 7.231694641813327e-06,
      "loss": 0.4735,
      "step": 38408
    },
    {
      "epoch": 1.17989125426228,
      "grad_norm": 0.3787103593349457,
      "learning_rate": 7.231230254789608e-06,
      "loss": 0.4526,
      "step": 38409
    },
    {
      "epoch": 1.179921973397229,
      "grad_norm": 0.38939785957336426,
      "learning_rate": 7.230765874232548e-06,
      "loss": 0.4307,
      "step": 38410
    },
    {
      "epoch": 1.1799526925321784,
      "grad_norm": 0.38513484597206116,
      "learning_rate": 7.230301500143223e-06,
      "loss": 0.5161,
      "step": 38411
    },
    {
      "epoch": 1.1799834116671275,
      "grad_norm": 0.4131280779838562,
      "learning_rate": 7.229837132522728e-06,
      "loss": 0.3919,
      "step": 38412
    },
    {
      "epoch": 1.1800141308020766,
      "grad_norm": 0.4250034689903259,
      "learning_rate": 7.229372771372138e-06,
      "loss": 0.5241,
      "step": 38413
    },
    {
      "epoch": 1.1800448499370257,
      "grad_norm": 0.4554297626018524,
      "learning_rate": 7.228908416692544e-06,
      "loss": 0.5312,
      "step": 38414
    },
    {
      "epoch": 1.1800755690719749,
      "grad_norm": 0.40787768363952637,
      "learning_rate": 7.228444068485024e-06,
      "loss": 0.4731,
      "step": 38415
    },
    {
      "epoch": 1.180106288206924,
      "grad_norm": 0.40890803933143616,
      "learning_rate": 7.22797972675067e-06,
      "loss": 0.4866,
      "step": 38416
    },
    {
      "epoch": 1.1801370073418733,
      "grad_norm": 0.4347211718559265,
      "learning_rate": 7.22751539149056e-06,
      "loss": 0.3991,
      "step": 38417
    },
    {
      "epoch": 1.1801677264768224,
      "grad_norm": 0.38860487937927246,
      "learning_rate": 7.227051062705785e-06,
      "loss": 0.4995,
      "step": 38418
    },
    {
      "epoch": 1.1801984456117716,
      "grad_norm": 0.4046924412250519,
      "learning_rate": 7.226586740397422e-06,
      "loss": 0.5908,
      "step": 38419
    },
    {
      "epoch": 1.1802291647467207,
      "grad_norm": 0.4690229594707489,
      "learning_rate": 7.226122424566563e-06,
      "loss": 0.4946,
      "step": 38420
    },
    {
      "epoch": 1.1802598838816698,
      "grad_norm": 0.40972578525543213,
      "learning_rate": 7.225658115214286e-06,
      "loss": 0.4911,
      "step": 38421
    },
    {
      "epoch": 1.1802906030166191,
      "grad_norm": 0.40558674931526184,
      "learning_rate": 7.225193812341679e-06,
      "loss": 0.4985,
      "step": 38422
    },
    {
      "epoch": 1.1803213221515683,
      "grad_norm": 0.44305381178855896,
      "learning_rate": 7.224729515949826e-06,
      "loss": 0.4691,
      "step": 38423
    },
    {
      "epoch": 1.1803520412865174,
      "grad_norm": 0.4568690359592438,
      "learning_rate": 7.2242652260398125e-06,
      "loss": 0.4924,
      "step": 38424
    },
    {
      "epoch": 1.1803827604214665,
      "grad_norm": 0.4115668833255768,
      "learning_rate": 7.223800942612718e-06,
      "loss": 0.4639,
      "step": 38425
    },
    {
      "epoch": 1.1804134795564156,
      "grad_norm": 0.41449764370918274,
      "learning_rate": 7.2233366656696315e-06,
      "loss": 0.5001,
      "step": 38426
    },
    {
      "epoch": 1.1804441986913647,
      "grad_norm": 0.41124433279037476,
      "learning_rate": 7.222872395211638e-06,
      "loss": 0.4667,
      "step": 38427
    },
    {
      "epoch": 1.180474917826314,
      "grad_norm": 0.3578966557979584,
      "learning_rate": 7.2224081312398175e-06,
      "loss": 0.4451,
      "step": 38428
    },
    {
      "epoch": 1.1805056369612632,
      "grad_norm": 0.4690937101840973,
      "learning_rate": 7.221943873755259e-06,
      "loss": 0.508,
      "step": 38429
    },
    {
      "epoch": 1.1805363560962123,
      "grad_norm": 0.37960267066955566,
      "learning_rate": 7.2214796227590425e-06,
      "loss": 0.5157,
      "step": 38430
    },
    {
      "epoch": 1.1805670752311614,
      "grad_norm": 0.36440810561180115,
      "learning_rate": 7.221015378252256e-06,
      "loss": 0.4107,
      "step": 38431
    },
    {
      "epoch": 1.1805977943661106,
      "grad_norm": 0.41128596663475037,
      "learning_rate": 7.220551140235982e-06,
      "loss": 0.4387,
      "step": 38432
    },
    {
      "epoch": 1.18062851350106,
      "grad_norm": 0.38646388053894043,
      "learning_rate": 7.220086908711305e-06,
      "loss": 0.4932,
      "step": 38433
    },
    {
      "epoch": 1.180659232636009,
      "grad_norm": 0.40554559230804443,
      "learning_rate": 7.219622683679308e-06,
      "loss": 0.5569,
      "step": 38434
    },
    {
      "epoch": 1.1806899517709581,
      "grad_norm": 0.4069522023200989,
      "learning_rate": 7.219158465141081e-06,
      "loss": 0.4409,
      "step": 38435
    },
    {
      "epoch": 1.1807206709059073,
      "grad_norm": 0.3719732165336609,
      "learning_rate": 7.218694253097695e-06,
      "loss": 0.4655,
      "step": 38436
    },
    {
      "epoch": 1.1807513900408564,
      "grad_norm": 0.5018415451049805,
      "learning_rate": 7.218230047550252e-06,
      "loss": 0.5911,
      "step": 38437
    },
    {
      "epoch": 1.1807821091758055,
      "grad_norm": 0.43787986040115356,
      "learning_rate": 7.21776584849982e-06,
      "loss": 0.473,
      "step": 38438
    },
    {
      "epoch": 1.1808128283107548,
      "grad_norm": 0.4312039911746979,
      "learning_rate": 7.217301655947495e-06,
      "loss": 0.4991,
      "step": 38439
    },
    {
      "epoch": 1.180843547445704,
      "grad_norm": 0.8885818719863892,
      "learning_rate": 7.216837469894351e-06,
      "loss": 0.4811,
      "step": 38440
    },
    {
      "epoch": 1.180874266580653,
      "grad_norm": 0.44350573420524597,
      "learning_rate": 7.216373290341485e-06,
      "loss": 0.4876,
      "step": 38441
    },
    {
      "epoch": 1.1809049857156022,
      "grad_norm": 0.3832188546657562,
      "learning_rate": 7.215909117289968e-06,
      "loss": 0.4555,
      "step": 38442
    },
    {
      "epoch": 1.1809357048505513,
      "grad_norm": 0.3773619532585144,
      "learning_rate": 7.215444950740891e-06,
      "loss": 0.5468,
      "step": 38443
    },
    {
      "epoch": 1.1809664239855007,
      "grad_norm": 0.43254554271698,
      "learning_rate": 7.2149807906953365e-06,
      "loss": 0.5222,
      "step": 38444
    },
    {
      "epoch": 1.1809971431204498,
      "grad_norm": 0.4708801209926605,
      "learning_rate": 7.214516637154385e-06,
      "loss": 0.428,
      "step": 38445
    },
    {
      "epoch": 1.181027862255399,
      "grad_norm": 0.4073845148086548,
      "learning_rate": 7.214052490119132e-06,
      "loss": 0.431,
      "step": 38446
    },
    {
      "epoch": 1.181058581390348,
      "grad_norm": 0.40082958340644836,
      "learning_rate": 7.21358834959065e-06,
      "loss": 0.5484,
      "step": 38447
    },
    {
      "epoch": 1.1810893005252971,
      "grad_norm": 0.44798871874809265,
      "learning_rate": 7.2131242155700285e-06,
      "loss": 0.4654,
      "step": 38448
    },
    {
      "epoch": 1.1811200196602463,
      "grad_norm": 0.3910003900527954,
      "learning_rate": 7.2126600880583475e-06,
      "loss": 0.4514,
      "step": 38449
    },
    {
      "epoch": 1.1811507387951956,
      "grad_norm": 0.4451075494289398,
      "learning_rate": 7.212195967056697e-06,
      "loss": 0.5425,
      "step": 38450
    },
    {
      "epoch": 1.1811814579301447,
      "grad_norm": 0.3757244050502777,
      "learning_rate": 7.211731852566154e-06,
      "loss": 0.4162,
      "step": 38451
    },
    {
      "epoch": 1.1812121770650938,
      "grad_norm": 0.4206479489803314,
      "learning_rate": 7.2112677445878084e-06,
      "loss": 0.516,
      "step": 38452
    },
    {
      "epoch": 1.181242896200043,
      "grad_norm": 0.41747215390205383,
      "learning_rate": 7.210803643122739e-06,
      "loss": 0.4297,
      "step": 38453
    },
    {
      "epoch": 1.181273615334992,
      "grad_norm": 0.3892149031162262,
      "learning_rate": 7.210339548172036e-06,
      "loss": 0.4993,
      "step": 38454
    },
    {
      "epoch": 1.1813043344699414,
      "grad_norm": 0.3894139230251312,
      "learning_rate": 7.2098754597367774e-06,
      "loss": 0.5283,
      "step": 38455
    },
    {
      "epoch": 1.1813350536048906,
      "grad_norm": 0.521317720413208,
      "learning_rate": 7.209411377818052e-06,
      "loss": 0.5101,
      "step": 38456
    },
    {
      "epoch": 1.1813657727398397,
      "grad_norm": 0.42814359068870544,
      "learning_rate": 7.208947302416938e-06,
      "loss": 0.4964,
      "step": 38457
    },
    {
      "epoch": 1.1813964918747888,
      "grad_norm": 0.3932219445705414,
      "learning_rate": 7.2084832335345245e-06,
      "loss": 0.4309,
      "step": 38458
    },
    {
      "epoch": 1.181427211009738,
      "grad_norm": 0.49492335319519043,
      "learning_rate": 7.208019171171891e-06,
      "loss": 0.4568,
      "step": 38459
    },
    {
      "epoch": 1.181457930144687,
      "grad_norm": 0.41332805156707764,
      "learning_rate": 7.207555115330128e-06,
      "loss": 0.4875,
      "step": 38460
    },
    {
      "epoch": 1.1814886492796364,
      "grad_norm": 0.3484869599342346,
      "learning_rate": 7.207091066010312e-06,
      "loss": 0.381,
      "step": 38461
    },
    {
      "epoch": 1.1815193684145855,
      "grad_norm": 0.43730050325393677,
      "learning_rate": 7.20662702321353e-06,
      "loss": 0.4645,
      "step": 38462
    },
    {
      "epoch": 1.1815500875495346,
      "grad_norm": 0.37928932905197144,
      "learning_rate": 7.2061629869408655e-06,
      "loss": 0.5019,
      "step": 38463
    },
    {
      "epoch": 1.1815808066844837,
      "grad_norm": 0.4495307207107544,
      "learning_rate": 7.205698957193404e-06,
      "loss": 0.5214,
      "step": 38464
    },
    {
      "epoch": 1.1816115258194329,
      "grad_norm": 0.43081480264663696,
      "learning_rate": 7.2052349339722274e-06,
      "loss": 0.4799,
      "step": 38465
    },
    {
      "epoch": 1.1816422449543822,
      "grad_norm": 0.40015190839767456,
      "learning_rate": 7.2047709172784175e-06,
      "loss": 0.4642,
      "step": 38466
    },
    {
      "epoch": 1.1816729640893313,
      "grad_norm": 0.4004564583301544,
      "learning_rate": 7.204306907113063e-06,
      "loss": 0.5084,
      "step": 38467
    },
    {
      "epoch": 1.1817036832242804,
      "grad_norm": 0.39573392271995544,
      "learning_rate": 7.203842903477243e-06,
      "loss": 0.4593,
      "step": 38468
    },
    {
      "epoch": 1.1817344023592296,
      "grad_norm": 0.38697922229766846,
      "learning_rate": 7.203378906372047e-06,
      "loss": 0.5144,
      "step": 38469
    },
    {
      "epoch": 1.1817651214941787,
      "grad_norm": 0.3874494135379791,
      "learning_rate": 7.20291491579855e-06,
      "loss": 0.4738,
      "step": 38470
    },
    {
      "epoch": 1.1817958406291278,
      "grad_norm": 0.36479702591896057,
      "learning_rate": 7.202450931757846e-06,
      "loss": 0.4238,
      "step": 38471
    },
    {
      "epoch": 1.1818265597640771,
      "grad_norm": 0.45953884720802307,
      "learning_rate": 7.201986954251007e-06,
      "loss": 0.4862,
      "step": 38472
    },
    {
      "epoch": 1.1818572788990263,
      "grad_norm": 0.4083768427371979,
      "learning_rate": 7.201522983279129e-06,
      "loss": 0.4828,
      "step": 38473
    },
    {
      "epoch": 1.1818879980339754,
      "grad_norm": 0.3713088631629944,
      "learning_rate": 7.201059018843283e-06,
      "loss": 0.4264,
      "step": 38474
    },
    {
      "epoch": 1.1819187171689245,
      "grad_norm": 0.4367072582244873,
      "learning_rate": 7.200595060944567e-06,
      "loss": 0.5248,
      "step": 38475
    },
    {
      "epoch": 1.1819494363038736,
      "grad_norm": 0.40177077054977417,
      "learning_rate": 7.2001311095840495e-06,
      "loss": 0.5028,
      "step": 38476
    },
    {
      "epoch": 1.181980155438823,
      "grad_norm": 0.4602883756160736,
      "learning_rate": 7.199667164762825e-06,
      "loss": 0.519,
      "step": 38477
    },
    {
      "epoch": 1.182010874573772,
      "grad_norm": 0.37278103828430176,
      "learning_rate": 7.199203226481972e-06,
      "loss": 0.4257,
      "step": 38478
    },
    {
      "epoch": 1.1820415937087212,
      "grad_norm": 0.37958788871765137,
      "learning_rate": 7.198739294742576e-06,
      "loss": 0.5383,
      "step": 38479
    },
    {
      "epoch": 1.1820723128436703,
      "grad_norm": 0.44381850957870483,
      "learning_rate": 7.19827536954572e-06,
      "loss": 0.4834,
      "step": 38480
    },
    {
      "epoch": 1.1821030319786194,
      "grad_norm": 0.47905394434928894,
      "learning_rate": 7.1978114508924845e-06,
      "loss": 0.4827,
      "step": 38481
    },
    {
      "epoch": 1.1821337511135686,
      "grad_norm": 0.3739997148513794,
      "learning_rate": 7.197347538783962e-06,
      "loss": 0.431,
      "step": 38482
    },
    {
      "epoch": 1.182164470248518,
      "grad_norm": 0.39960792660713196,
      "learning_rate": 7.196883633221225e-06,
      "loss": 0.4839,
      "step": 38483
    },
    {
      "epoch": 1.182195189383467,
      "grad_norm": 0.3822951018810272,
      "learning_rate": 7.1964197342053666e-06,
      "loss": 0.4301,
      "step": 38484
    },
    {
      "epoch": 1.1822259085184161,
      "grad_norm": 0.36214378476142883,
      "learning_rate": 7.195955841737461e-06,
      "loss": 0.3869,
      "step": 38485
    },
    {
      "epoch": 1.1822566276533653,
      "grad_norm": 0.3907179832458496,
      "learning_rate": 7.195491955818601e-06,
      "loss": 0.5168,
      "step": 38486
    },
    {
      "epoch": 1.1822873467883144,
      "grad_norm": 0.40646716952323914,
      "learning_rate": 7.195028076449861e-06,
      "loss": 0.5292,
      "step": 38487
    },
    {
      "epoch": 1.1823180659232637,
      "grad_norm": 0.4027955234050751,
      "learning_rate": 7.1945642036323325e-06,
      "loss": 0.4251,
      "step": 38488
    },
    {
      "epoch": 1.1823487850582128,
      "grad_norm": 0.4380202293395996,
      "learning_rate": 7.194100337367092e-06,
      "loss": 0.4862,
      "step": 38489
    },
    {
      "epoch": 1.182379504193162,
      "grad_norm": 0.5959159135818481,
      "learning_rate": 7.193636477655229e-06,
      "loss": 0.4344,
      "step": 38490
    },
    {
      "epoch": 1.182410223328111,
      "grad_norm": 0.38433921337127686,
      "learning_rate": 7.193172624497821e-06,
      "loss": 0.4593,
      "step": 38491
    },
    {
      "epoch": 1.1824409424630602,
      "grad_norm": 0.3879375159740448,
      "learning_rate": 7.192708777895958e-06,
      "loss": 0.5489,
      "step": 38492
    },
    {
      "epoch": 1.1824716615980093,
      "grad_norm": 0.38860249519348145,
      "learning_rate": 7.192244937850716e-06,
      "loss": 0.4129,
      "step": 38493
    },
    {
      "epoch": 1.1825023807329584,
      "grad_norm": 0.40492376685142517,
      "learning_rate": 7.191781104363186e-06,
      "loss": 0.467,
      "step": 38494
    },
    {
      "epoch": 1.1825330998679078,
      "grad_norm": 0.38800978660583496,
      "learning_rate": 7.191317277434444e-06,
      "loss": 0.4745,
      "step": 38495
    },
    {
      "epoch": 1.182563819002857,
      "grad_norm": 0.4870554804801941,
      "learning_rate": 7.190853457065578e-06,
      "loss": 0.4484,
      "step": 38496
    },
    {
      "epoch": 1.182594538137806,
      "grad_norm": 0.4097041189670563,
      "learning_rate": 7.1903896432576696e-06,
      "loss": 0.4344,
      "step": 38497
    },
    {
      "epoch": 1.1826252572727551,
      "grad_norm": 0.39009523391723633,
      "learning_rate": 7.1899258360118065e-06,
      "loss": 0.4763,
      "step": 38498
    },
    {
      "epoch": 1.1826559764077045,
      "grad_norm": 0.3518867492675781,
      "learning_rate": 7.18946203532906e-06,
      "loss": 0.4724,
      "step": 38499
    },
    {
      "epoch": 1.1826866955426536,
      "grad_norm": 0.3719058334827423,
      "learning_rate": 7.188998241210524e-06,
      "loss": 0.4132,
      "step": 38500
    },
    {
      "epoch": 1.1827174146776027,
      "grad_norm": 0.3908645212650299,
      "learning_rate": 7.188534453657281e-06,
      "loss": 0.5909,
      "step": 38501
    },
    {
      "epoch": 1.1827481338125518,
      "grad_norm": 0.3964349031448364,
      "learning_rate": 7.188070672670411e-06,
      "loss": 0.4619,
      "step": 38502
    },
    {
      "epoch": 1.182778852947501,
      "grad_norm": 0.40507036447525024,
      "learning_rate": 7.1876068982509986e-06,
      "loss": 0.4458,
      "step": 38503
    },
    {
      "epoch": 1.18280957208245,
      "grad_norm": 0.37894192337989807,
      "learning_rate": 7.187143130400126e-06,
      "loss": 0.5143,
      "step": 38504
    },
    {
      "epoch": 1.1828402912173992,
      "grad_norm": 0.43798282742500305,
      "learning_rate": 7.18667936911888e-06,
      "loss": 0.541,
      "step": 38505
    },
    {
      "epoch": 1.1828710103523485,
      "grad_norm": 0.3911665380001068,
      "learning_rate": 7.186215614408336e-06,
      "loss": 0.4537,
      "step": 38506
    },
    {
      "epoch": 1.1829017294872977,
      "grad_norm": 0.41419345140457153,
      "learning_rate": 7.185751866269588e-06,
      "loss": 0.5386,
      "step": 38507
    },
    {
      "epoch": 1.1829324486222468,
      "grad_norm": 0.3970668911933899,
      "learning_rate": 7.185288124703707e-06,
      "loss": 0.4195,
      "step": 38508
    },
    {
      "epoch": 1.182963167757196,
      "grad_norm": 0.4578370451927185,
      "learning_rate": 7.184824389711786e-06,
      "loss": 0.5339,
      "step": 38509
    },
    {
      "epoch": 1.1829938868921452,
      "grad_norm": 0.5731179118156433,
      "learning_rate": 7.184360661294903e-06,
      "loss": 0.4319,
      "step": 38510
    },
    {
      "epoch": 1.1830246060270944,
      "grad_norm": 0.4273708462715149,
      "learning_rate": 7.183896939454143e-06,
      "loss": 0.4649,
      "step": 38511
    },
    {
      "epoch": 1.1830553251620435,
      "grad_norm": 0.4284989833831787,
      "learning_rate": 7.183433224190587e-06,
      "loss": 0.5636,
      "step": 38512
    },
    {
      "epoch": 1.1830860442969926,
      "grad_norm": 0.37073463201522827,
      "learning_rate": 7.1829695155053205e-06,
      "loss": 0.5002,
      "step": 38513
    },
    {
      "epoch": 1.1831167634319417,
      "grad_norm": 0.3945944309234619,
      "learning_rate": 7.182505813399424e-06,
      "loss": 0.4681,
      "step": 38514
    },
    {
      "epoch": 1.1831474825668908,
      "grad_norm": 0.4772319793701172,
      "learning_rate": 7.182042117873984e-06,
      "loss": 0.4611,
      "step": 38515
    },
    {
      "epoch": 1.18317820170184,
      "grad_norm": 0.43253272771835327,
      "learning_rate": 7.1815784289300795e-06,
      "loss": 0.5313,
      "step": 38516
    },
    {
      "epoch": 1.1832089208367893,
      "grad_norm": 0.39398908615112305,
      "learning_rate": 7.181114746568796e-06,
      "loss": 0.5175,
      "step": 38517
    },
    {
      "epoch": 1.1832396399717384,
      "grad_norm": 0.39710694551467896,
      "learning_rate": 7.1806510707912155e-06,
      "loss": 0.5403,
      "step": 38518
    },
    {
      "epoch": 1.1832703591066875,
      "grad_norm": 0.3965400457382202,
      "learning_rate": 7.180187401598422e-06,
      "loss": 0.5066,
      "step": 38519
    },
    {
      "epoch": 1.1833010782416367,
      "grad_norm": 0.3913455009460449,
      "learning_rate": 7.179723738991499e-06,
      "loss": 0.4368,
      "step": 38520
    },
    {
      "epoch": 1.1833317973765858,
      "grad_norm": 0.42630332708358765,
      "learning_rate": 7.1792600829715255e-06,
      "loss": 0.4952,
      "step": 38521
    },
    {
      "epoch": 1.1833625165115351,
      "grad_norm": 0.42581385374069214,
      "learning_rate": 7.1787964335395895e-06,
      "loss": 0.4806,
      "step": 38522
    },
    {
      "epoch": 1.1833932356464842,
      "grad_norm": 0.3903634250164032,
      "learning_rate": 7.178332790696769e-06,
      "loss": 0.445,
      "step": 38523
    },
    {
      "epoch": 1.1834239547814334,
      "grad_norm": 0.36999109387397766,
      "learning_rate": 7.177869154444153e-06,
      "loss": 0.4453,
      "step": 38524
    },
    {
      "epoch": 1.1834546739163825,
      "grad_norm": 0.3952052593231201,
      "learning_rate": 7.177405524782817e-06,
      "loss": 0.473,
      "step": 38525
    },
    {
      "epoch": 1.1834853930513316,
      "grad_norm": 0.4596386253833771,
      "learning_rate": 7.17694190171385e-06,
      "loss": 0.5706,
      "step": 38526
    },
    {
      "epoch": 1.1835161121862807,
      "grad_norm": 0.4262028634548187,
      "learning_rate": 7.176478285238331e-06,
      "loss": 0.4754,
      "step": 38527
    },
    {
      "epoch": 1.18354683132123,
      "grad_norm": 0.38949960470199585,
      "learning_rate": 7.176014675357344e-06,
      "loss": 0.5445,
      "step": 38528
    },
    {
      "epoch": 1.1835775504561792,
      "grad_norm": 0.42074111104011536,
      "learning_rate": 7.1755510720719715e-06,
      "loss": 0.4138,
      "step": 38529
    },
    {
      "epoch": 1.1836082695911283,
      "grad_norm": 0.3755321800708771,
      "learning_rate": 7.1750874753833e-06,
      "loss": 0.5505,
      "step": 38530
    },
    {
      "epoch": 1.1836389887260774,
      "grad_norm": 0.39550718665122986,
      "learning_rate": 7.174623885292404e-06,
      "loss": 0.535,
      "step": 38531
    },
    {
      "epoch": 1.1836697078610265,
      "grad_norm": 0.3864976167678833,
      "learning_rate": 7.174160301800378e-06,
      "loss": 0.4688,
      "step": 38532
    },
    {
      "epoch": 1.1837004269959759,
      "grad_norm": 0.38393715023994446,
      "learning_rate": 7.17369672490829e-06,
      "loss": 0.4996,
      "step": 38533
    },
    {
      "epoch": 1.183731146130925,
      "grad_norm": 0.38569387793540955,
      "learning_rate": 7.173233154617239e-06,
      "loss": 0.4979,
      "step": 38534
    },
    {
      "epoch": 1.1837618652658741,
      "grad_norm": 0.4176095426082611,
      "learning_rate": 7.1727695909282915e-06,
      "loss": 0.4576,
      "step": 38535
    },
    {
      "epoch": 1.1837925844008232,
      "grad_norm": 0.38151755928993225,
      "learning_rate": 7.1723060338425395e-06,
      "loss": 0.495,
      "step": 38536
    },
    {
      "epoch": 1.1838233035357724,
      "grad_norm": 0.44669029116630554,
      "learning_rate": 7.171842483361068e-06,
      "loss": 0.4562,
      "step": 38537
    },
    {
      "epoch": 1.1838540226707215,
      "grad_norm": 0.4300011992454529,
      "learning_rate": 7.171378939484953e-06,
      "loss": 0.5563,
      "step": 38538
    },
    {
      "epoch": 1.1838847418056708,
      "grad_norm": 0.40015289187431335,
      "learning_rate": 7.170915402215284e-06,
      "loss": 0.5112,
      "step": 38539
    },
    {
      "epoch": 1.18391546094062,
      "grad_norm": 0.4147768020629883,
      "learning_rate": 7.170451871553134e-06,
      "loss": 0.502,
      "step": 38540
    },
    {
      "epoch": 1.183946180075569,
      "grad_norm": 0.4131745994091034,
      "learning_rate": 7.169988347499597e-06,
      "loss": 0.4094,
      "step": 38541
    },
    {
      "epoch": 1.1839768992105182,
      "grad_norm": 0.4120432436466217,
      "learning_rate": 7.169524830055744e-06,
      "loss": 0.4775,
      "step": 38542
    },
    {
      "epoch": 1.1840076183454673,
      "grad_norm": 0.37272804975509644,
      "learning_rate": 7.16906131922267e-06,
      "loss": 0.463,
      "step": 38543
    },
    {
      "epoch": 1.1840383374804166,
      "grad_norm": 0.4535489082336426,
      "learning_rate": 7.168597815001444e-06,
      "loss": 0.4271,
      "step": 38544
    },
    {
      "epoch": 1.1840690566153658,
      "grad_norm": 0.41319018602371216,
      "learning_rate": 7.168134317393163e-06,
      "loss": 0.5004,
      "step": 38545
    },
    {
      "epoch": 1.1840997757503149,
      "grad_norm": 0.39640361070632935,
      "learning_rate": 7.167670826398896e-06,
      "loss": 0.4853,
      "step": 38546
    },
    {
      "epoch": 1.184130494885264,
      "grad_norm": 0.3897349238395691,
      "learning_rate": 7.167207342019735e-06,
      "loss": 0.4885,
      "step": 38547
    },
    {
      "epoch": 1.1841612140202131,
      "grad_norm": 0.38309839367866516,
      "learning_rate": 7.166743864256756e-06,
      "loss": 0.511,
      "step": 38548
    },
    {
      "epoch": 1.1841919331551622,
      "grad_norm": 0.44898754358291626,
      "learning_rate": 7.166280393111048e-06,
      "loss": 0.4594,
      "step": 38549
    },
    {
      "epoch": 1.1842226522901116,
      "grad_norm": 0.3741266429424286,
      "learning_rate": 7.165816928583687e-06,
      "loss": 0.4988,
      "step": 38550
    },
    {
      "epoch": 1.1842533714250607,
      "grad_norm": 0.4058641195297241,
      "learning_rate": 7.165353470675761e-06,
      "loss": 0.4421,
      "step": 38551
    },
    {
      "epoch": 1.1842840905600098,
      "grad_norm": 0.41018936038017273,
      "learning_rate": 7.164890019388348e-06,
      "loss": 0.5492,
      "step": 38552
    },
    {
      "epoch": 1.184314809694959,
      "grad_norm": 0.3614369332790375,
      "learning_rate": 7.164426574722534e-06,
      "loss": 0.4956,
      "step": 38553
    },
    {
      "epoch": 1.184345528829908,
      "grad_norm": 0.42037466168403625,
      "learning_rate": 7.163963136679397e-06,
      "loss": 0.5518,
      "step": 38554
    },
    {
      "epoch": 1.1843762479648574,
      "grad_norm": 0.4208832085132599,
      "learning_rate": 7.163499705260024e-06,
      "loss": 0.4928,
      "step": 38555
    },
    {
      "epoch": 1.1844069670998065,
      "grad_norm": 0.4463188350200653,
      "learning_rate": 7.1630362804654964e-06,
      "loss": 0.4868,
      "step": 38556
    },
    {
      "epoch": 1.1844376862347556,
      "grad_norm": 0.37557676434516907,
      "learning_rate": 7.162572862296893e-06,
      "loss": 0.4611,
      "step": 38557
    },
    {
      "epoch": 1.1844684053697048,
      "grad_norm": 0.4246636629104614,
      "learning_rate": 7.162109450755303e-06,
      "loss": 0.4758,
      "step": 38558
    },
    {
      "epoch": 1.1844991245046539,
      "grad_norm": 0.4249544143676758,
      "learning_rate": 7.161646045841801e-06,
      "loss": 0.4473,
      "step": 38559
    },
    {
      "epoch": 1.184529843639603,
      "grad_norm": 0.3913397490978241,
      "learning_rate": 7.161182647557475e-06,
      "loss": 0.4432,
      "step": 38560
    },
    {
      "epoch": 1.1845605627745524,
      "grad_norm": 0.46688005328178406,
      "learning_rate": 7.160719255903403e-06,
      "loss": 0.4869,
      "step": 38561
    },
    {
      "epoch": 1.1845912819095015,
      "grad_norm": 0.3825374245643616,
      "learning_rate": 7.160255870880672e-06,
      "loss": 0.4309,
      "step": 38562
    },
    {
      "epoch": 1.1846220010444506,
      "grad_norm": 0.4052302837371826,
      "learning_rate": 7.159792492490361e-06,
      "loss": 0.5254,
      "step": 38563
    },
    {
      "epoch": 1.1846527201793997,
      "grad_norm": 0.48583897948265076,
      "learning_rate": 7.159329120733553e-06,
      "loss": 0.5298,
      "step": 38564
    },
    {
      "epoch": 1.1846834393143488,
      "grad_norm": 0.41350695490837097,
      "learning_rate": 7.158865755611328e-06,
      "loss": 0.4499,
      "step": 38565
    },
    {
      "epoch": 1.1847141584492982,
      "grad_norm": 0.38938432931900024,
      "learning_rate": 7.158402397124774e-06,
      "loss": 0.5167,
      "step": 38566
    },
    {
      "epoch": 1.1847448775842473,
      "grad_norm": 0.4158456325531006,
      "learning_rate": 7.157939045274966e-06,
      "loss": 0.5622,
      "step": 38567
    },
    {
      "epoch": 1.1847755967191964,
      "grad_norm": 0.3673172891139984,
      "learning_rate": 7.1574757000629956e-06,
      "loss": 0.418,
      "step": 38568
    },
    {
      "epoch": 1.1848063158541455,
      "grad_norm": 0.4071676731109619,
      "learning_rate": 7.157012361489932e-06,
      "loss": 0.4246,
      "step": 38569
    },
    {
      "epoch": 1.1848370349890947,
      "grad_norm": 0.4102998375892639,
      "learning_rate": 7.1565490295568715e-06,
      "loss": 0.5309,
      "step": 38570
    },
    {
      "epoch": 1.1848677541240438,
      "grad_norm": 0.4469594657421112,
      "learning_rate": 7.156085704264883e-06,
      "loss": 0.5583,
      "step": 38571
    },
    {
      "epoch": 1.1848984732589931,
      "grad_norm": 0.410009503364563,
      "learning_rate": 7.155622385615057e-06,
      "loss": 0.561,
      "step": 38572
    },
    {
      "epoch": 1.1849291923939422,
      "grad_norm": 0.38459518551826477,
      "learning_rate": 7.155159073608478e-06,
      "loss": 0.4945,
      "step": 38573
    },
    {
      "epoch": 1.1849599115288914,
      "grad_norm": 0.4106585681438446,
      "learning_rate": 7.154695768246216e-06,
      "loss": 0.5813,
      "step": 38574
    },
    {
      "epoch": 1.1849906306638405,
      "grad_norm": 0.3860970735549927,
      "learning_rate": 7.154232469529368e-06,
      "loss": 0.4826,
      "step": 38575
    },
    {
      "epoch": 1.1850213497987896,
      "grad_norm": 0.41020894050598145,
      "learning_rate": 7.153769177459002e-06,
      "loss": 0.4914,
      "step": 38576
    },
    {
      "epoch": 1.185052068933739,
      "grad_norm": 0.37822768092155457,
      "learning_rate": 7.153305892036213e-06,
      "loss": 0.5204,
      "step": 38577
    },
    {
      "epoch": 1.185082788068688,
      "grad_norm": 0.3944324851036072,
      "learning_rate": 7.152842613262072e-06,
      "loss": 0.4916,
      "step": 38578
    },
    {
      "epoch": 1.1851135072036372,
      "grad_norm": 0.3728145360946655,
      "learning_rate": 7.1523793411376715e-06,
      "loss": 0.4487,
      "step": 38579
    },
    {
      "epoch": 1.1851442263385863,
      "grad_norm": 0.382907509803772,
      "learning_rate": 7.151916075664082e-06,
      "loss": 0.4721,
      "step": 38580
    },
    {
      "epoch": 1.1851749454735354,
      "grad_norm": 0.47845542430877686,
      "learning_rate": 7.151452816842397e-06,
      "loss": 0.501,
      "step": 38581
    },
    {
      "epoch": 1.1852056646084845,
      "grad_norm": 0.3863953649997711,
      "learning_rate": 7.150989564673688e-06,
      "loss": 0.4844,
      "step": 38582
    },
    {
      "epoch": 1.1852363837434339,
      "grad_norm": 0.4308140277862549,
      "learning_rate": 7.1505263191590455e-06,
      "loss": 0.4512,
      "step": 38583
    },
    {
      "epoch": 1.185267102878383,
      "grad_norm": 0.42385953664779663,
      "learning_rate": 7.150063080299545e-06,
      "loss": 0.4626,
      "step": 38584
    },
    {
      "epoch": 1.1852978220133321,
      "grad_norm": 0.4185844957828522,
      "learning_rate": 7.149599848096273e-06,
      "loss": 0.4647,
      "step": 38585
    },
    {
      "epoch": 1.1853285411482812,
      "grad_norm": 0.40292829275131226,
      "learning_rate": 7.149136622550308e-06,
      "loss": 0.5199,
      "step": 38586
    },
    {
      "epoch": 1.1853592602832304,
      "grad_norm": 0.3741781413555145,
      "learning_rate": 7.1486734036627355e-06,
      "loss": 0.4935,
      "step": 38587
    },
    {
      "epoch": 1.1853899794181797,
      "grad_norm": 0.41815900802612305,
      "learning_rate": 7.148210191434634e-06,
      "loss": 0.513,
      "step": 38588
    },
    {
      "epoch": 1.1854206985531288,
      "grad_norm": 0.40287619829177856,
      "learning_rate": 7.147746985867088e-06,
      "loss": 0.4478,
      "step": 38589
    },
    {
      "epoch": 1.185451417688078,
      "grad_norm": 0.4496530592441559,
      "learning_rate": 7.147283786961177e-06,
      "loss": 0.4389,
      "step": 38590
    },
    {
      "epoch": 1.185482136823027,
      "grad_norm": 0.3842164874076843,
      "learning_rate": 7.146820594717982e-06,
      "loss": 0.5365,
      "step": 38591
    },
    {
      "epoch": 1.1855128559579762,
      "grad_norm": 0.39876964688301086,
      "learning_rate": 7.14635740913859e-06,
      "loss": 0.4949,
      "step": 38592
    },
    {
      "epoch": 1.1855435750929253,
      "grad_norm": 0.36967018246650696,
      "learning_rate": 7.1458942302240776e-06,
      "loss": 0.464,
      "step": 38593
    },
    {
      "epoch": 1.1855742942278746,
      "grad_norm": 0.4134487211704254,
      "learning_rate": 7.14543105797553e-06,
      "loss": 0.5216,
      "step": 38594
    },
    {
      "epoch": 1.1856050133628238,
      "grad_norm": 0.45564350485801697,
      "learning_rate": 7.1449678923940255e-06,
      "loss": 0.4356,
      "step": 38595
    },
    {
      "epoch": 1.1856357324977729,
      "grad_norm": 0.38771283626556396,
      "learning_rate": 7.144504733480651e-06,
      "loss": 0.4847,
      "step": 38596
    },
    {
      "epoch": 1.185666451632722,
      "grad_norm": 0.4285474419593811,
      "learning_rate": 7.144041581236483e-06,
      "loss": 0.4654,
      "step": 38597
    },
    {
      "epoch": 1.1856971707676711,
      "grad_norm": 0.3760300278663635,
      "learning_rate": 7.143578435662606e-06,
      "loss": 0.5286,
      "step": 38598
    },
    {
      "epoch": 1.1857278899026205,
      "grad_norm": 0.42101728916168213,
      "learning_rate": 7.1431152967601e-06,
      "loss": 0.5297,
      "step": 38599
    },
    {
      "epoch": 1.1857586090375696,
      "grad_norm": 0.38727933168411255,
      "learning_rate": 7.14265216453005e-06,
      "loss": 0.4948,
      "step": 38600
    },
    {
      "epoch": 1.1857893281725187,
      "grad_norm": 0.4180184304714203,
      "learning_rate": 7.1421890389735325e-06,
      "loss": 0.436,
      "step": 38601
    },
    {
      "epoch": 1.1858200473074678,
      "grad_norm": 0.3894593119621277,
      "learning_rate": 7.141725920091638e-06,
      "loss": 0.5446,
      "step": 38602
    },
    {
      "epoch": 1.185850766442417,
      "grad_norm": 0.3772319555282593,
      "learning_rate": 7.141262807885434e-06,
      "loss": 0.4846,
      "step": 38603
    },
    {
      "epoch": 1.185881485577366,
      "grad_norm": 0.41671010851860046,
      "learning_rate": 7.140799702356018e-06,
      "loss": 0.5416,
      "step": 38604
    },
    {
      "epoch": 1.1859122047123152,
      "grad_norm": 0.4276532232761383,
      "learning_rate": 7.140336603504456e-06,
      "loss": 0.5127,
      "step": 38605
    },
    {
      "epoch": 1.1859429238472645,
      "grad_norm": 0.3904968500137329,
      "learning_rate": 7.139873511331845e-06,
      "loss": 0.468,
      "step": 38606
    },
    {
      "epoch": 1.1859736429822136,
      "grad_norm": 0.37429279088974,
      "learning_rate": 7.139410425839253e-06,
      "loss": 0.429,
      "step": 38607
    },
    {
      "epoch": 1.1860043621171628,
      "grad_norm": 0.4100487232208252,
      "learning_rate": 7.138947347027774e-06,
      "loss": 0.5028,
      "step": 38608
    },
    {
      "epoch": 1.1860350812521119,
      "grad_norm": 0.4206901490688324,
      "learning_rate": 7.13848427489848e-06,
      "loss": 0.5216,
      "step": 38609
    },
    {
      "epoch": 1.1860658003870612,
      "grad_norm": 0.4164251685142517,
      "learning_rate": 7.138021209452452e-06,
      "loss": 0.4848,
      "step": 38610
    },
    {
      "epoch": 1.1860965195220103,
      "grad_norm": 0.379415899515152,
      "learning_rate": 7.137558150690782e-06,
      "loss": 0.4272,
      "step": 38611
    },
    {
      "epoch": 1.1861272386569595,
      "grad_norm": 0.4660171866416931,
      "learning_rate": 7.137095098614539e-06,
      "loss": 0.5073,
      "step": 38612
    },
    {
      "epoch": 1.1861579577919086,
      "grad_norm": 0.42666926980018616,
      "learning_rate": 7.136632053224817e-06,
      "loss": 0.5098,
      "step": 38613
    },
    {
      "epoch": 1.1861886769268577,
      "grad_norm": 0.4188029170036316,
      "learning_rate": 7.136169014522684e-06,
      "loss": 0.4624,
      "step": 38614
    },
    {
      "epoch": 1.1862193960618068,
      "grad_norm": 0.43107980489730835,
      "learning_rate": 7.135705982509234e-06,
      "loss": 0.5441,
      "step": 38615
    },
    {
      "epoch": 1.186250115196756,
      "grad_norm": 0.386821448802948,
      "learning_rate": 7.13524295718554e-06,
      "loss": 0.5149,
      "step": 38616
    },
    {
      "epoch": 1.1862808343317053,
      "grad_norm": 0.43009328842163086,
      "learning_rate": 7.134779938552687e-06,
      "loss": 0.494,
      "step": 38617
    },
    {
      "epoch": 1.1863115534666544,
      "grad_norm": 0.40852001309394836,
      "learning_rate": 7.134316926611753e-06,
      "loss": 0.4494,
      "step": 38618
    },
    {
      "epoch": 1.1863422726016035,
      "grad_norm": 0.42439180612564087,
      "learning_rate": 7.133853921363825e-06,
      "loss": 0.3783,
      "step": 38619
    },
    {
      "epoch": 1.1863729917365526,
      "grad_norm": 0.44799095392227173,
      "learning_rate": 7.1333909228099796e-06,
      "loss": 0.4977,
      "step": 38620
    },
    {
      "epoch": 1.186403710871502,
      "grad_norm": 0.39914652705192566,
      "learning_rate": 7.132927930951301e-06,
      "loss": 0.4945,
      "step": 38621
    },
    {
      "epoch": 1.186434430006451,
      "grad_norm": 0.4144383668899536,
      "learning_rate": 7.132464945788868e-06,
      "loss": 0.469,
      "step": 38622
    },
    {
      "epoch": 1.1864651491414002,
      "grad_norm": 0.4381045401096344,
      "learning_rate": 7.132001967323765e-06,
      "loss": 0.4935,
      "step": 38623
    },
    {
      "epoch": 1.1864958682763493,
      "grad_norm": 0.4121220111846924,
      "learning_rate": 7.13153899555707e-06,
      "loss": 0.3911,
      "step": 38624
    },
    {
      "epoch": 1.1865265874112985,
      "grad_norm": 0.3764558732509613,
      "learning_rate": 7.131076030489869e-06,
      "loss": 0.454,
      "step": 38625
    },
    {
      "epoch": 1.1865573065462476,
      "grad_norm": 0.42625728249549866,
      "learning_rate": 7.130613072123237e-06,
      "loss": 0.4908,
      "step": 38626
    },
    {
      "epoch": 1.1865880256811967,
      "grad_norm": 0.4143946170806885,
      "learning_rate": 7.130150120458259e-06,
      "loss": 0.4856,
      "step": 38627
    },
    {
      "epoch": 1.186618744816146,
      "grad_norm": 0.3714250922203064,
      "learning_rate": 7.129687175496018e-06,
      "loss": 0.4304,
      "step": 38628
    },
    {
      "epoch": 1.1866494639510952,
      "grad_norm": 0.37324059009552,
      "learning_rate": 7.129224237237589e-06,
      "loss": 0.4637,
      "step": 38629
    },
    {
      "epoch": 1.1866801830860443,
      "grad_norm": 0.4207802712917328,
      "learning_rate": 7.128761305684062e-06,
      "loss": 0.526,
      "step": 38630
    },
    {
      "epoch": 1.1867109022209934,
      "grad_norm": 0.3979499638080597,
      "learning_rate": 7.12829838083651e-06,
      "loss": 0.5273,
      "step": 38631
    },
    {
      "epoch": 1.1867416213559425,
      "grad_norm": 0.40036824345588684,
      "learning_rate": 7.12783546269602e-06,
      "loss": 0.4402,
      "step": 38632
    },
    {
      "epoch": 1.1867723404908919,
      "grad_norm": 0.40009093284606934,
      "learning_rate": 7.127372551263669e-06,
      "loss": 0.5244,
      "step": 38633
    },
    {
      "epoch": 1.186803059625841,
      "grad_norm": 0.3999038338661194,
      "learning_rate": 7.126909646540543e-06,
      "loss": 0.5181,
      "step": 38634
    },
    {
      "epoch": 1.18683377876079,
      "grad_norm": 0.3842979967594147,
      "learning_rate": 7.1264467485277174e-06,
      "loss": 0.4733,
      "step": 38635
    },
    {
      "epoch": 1.1868644978957392,
      "grad_norm": 0.46290865540504456,
      "learning_rate": 7.1259838572262775e-06,
      "loss": 0.507,
      "step": 38636
    },
    {
      "epoch": 1.1868952170306883,
      "grad_norm": 0.4256381690502167,
      "learning_rate": 7.125520972637302e-06,
      "loss": 0.4853,
      "step": 38637
    },
    {
      "epoch": 1.1869259361656375,
      "grad_norm": 0.4101239740848541,
      "learning_rate": 7.125058094761876e-06,
      "loss": 0.4415,
      "step": 38638
    },
    {
      "epoch": 1.1869566553005868,
      "grad_norm": 0.4130633771419525,
      "learning_rate": 7.124595223601072e-06,
      "loss": 0.4345,
      "step": 38639
    },
    {
      "epoch": 1.186987374435536,
      "grad_norm": 0.43598851561546326,
      "learning_rate": 7.124132359155984e-06,
      "loss": 0.4884,
      "step": 38640
    },
    {
      "epoch": 1.187018093570485,
      "grad_norm": 0.43091288208961487,
      "learning_rate": 7.123669501427678e-06,
      "loss": 0.4122,
      "step": 38641
    },
    {
      "epoch": 1.1870488127054342,
      "grad_norm": 0.4082549512386322,
      "learning_rate": 7.123206650417249e-06,
      "loss": 0.4711,
      "step": 38642
    },
    {
      "epoch": 1.1870795318403833,
      "grad_norm": 0.44191378355026245,
      "learning_rate": 7.122743806125768e-06,
      "loss": 0.5277,
      "step": 38643
    },
    {
      "epoch": 1.1871102509753326,
      "grad_norm": 0.36894142627716064,
      "learning_rate": 7.122280968554323e-06,
      "loss": 0.4451,
      "step": 38644
    },
    {
      "epoch": 1.1871409701102817,
      "grad_norm": 0.3866889178752899,
      "learning_rate": 7.121818137703989e-06,
      "loss": 0.4713,
      "step": 38645
    },
    {
      "epoch": 1.1871716892452309,
      "grad_norm": 0.4512236714363098,
      "learning_rate": 7.121355313575846e-06,
      "loss": 0.5315,
      "step": 38646
    },
    {
      "epoch": 1.18720240838018,
      "grad_norm": 0.45128002762794495,
      "learning_rate": 7.120892496170986e-06,
      "loss": 0.5177,
      "step": 38647
    },
    {
      "epoch": 1.187233127515129,
      "grad_norm": 0.4080408811569214,
      "learning_rate": 7.1204296854904774e-06,
      "loss": 0.4845,
      "step": 38648
    },
    {
      "epoch": 1.1872638466500782,
      "grad_norm": 0.37620657682418823,
      "learning_rate": 7.119966881535412e-06,
      "loss": 0.4565,
      "step": 38649
    },
    {
      "epoch": 1.1872945657850276,
      "grad_norm": 0.39094212651252747,
      "learning_rate": 7.119504084306861e-06,
      "loss": 0.4591,
      "step": 38650
    },
    {
      "epoch": 1.1873252849199767,
      "grad_norm": 0.37028688192367554,
      "learning_rate": 7.119041293805911e-06,
      "loss": 0.5028,
      "step": 38651
    },
    {
      "epoch": 1.1873560040549258,
      "grad_norm": 0.3804953992366791,
      "learning_rate": 7.118578510033638e-06,
      "loss": 0.4798,
      "step": 38652
    },
    {
      "epoch": 1.187386723189875,
      "grad_norm": 0.4013119637966156,
      "learning_rate": 7.118115732991131e-06,
      "loss": 0.5043,
      "step": 38653
    },
    {
      "epoch": 1.187417442324824,
      "grad_norm": 0.39142248034477234,
      "learning_rate": 7.117652962679462e-06,
      "loss": 0.4117,
      "step": 38654
    },
    {
      "epoch": 1.1874481614597734,
      "grad_norm": 0.3935091495513916,
      "learning_rate": 7.117190199099719e-06,
      "loss": 0.4909,
      "step": 38655
    },
    {
      "epoch": 1.1874788805947225,
      "grad_norm": 0.48351335525512695,
      "learning_rate": 7.116727442252975e-06,
      "loss": 0.4956,
      "step": 38656
    },
    {
      "epoch": 1.1875095997296716,
      "grad_norm": 0.4145917296409607,
      "learning_rate": 7.11626469214032e-06,
      "loss": 0.4736,
      "step": 38657
    },
    {
      "epoch": 1.1875403188646207,
      "grad_norm": 0.41350245475769043,
      "learning_rate": 7.115801948762828e-06,
      "loss": 0.442,
      "step": 38658
    },
    {
      "epoch": 1.1875710379995699,
      "grad_norm": 0.40299224853515625,
      "learning_rate": 7.115339212121584e-06,
      "loss": 0.464,
      "step": 38659
    },
    {
      "epoch": 1.187601757134519,
      "grad_norm": 0.4112759828567505,
      "learning_rate": 7.114876482217664e-06,
      "loss": 0.5186,
      "step": 38660
    },
    {
      "epoch": 1.1876324762694683,
      "grad_norm": 0.4044054448604584,
      "learning_rate": 7.114413759052155e-06,
      "loss": 0.4573,
      "step": 38661
    },
    {
      "epoch": 1.1876631954044174,
      "grad_norm": 0.40077880024909973,
      "learning_rate": 7.11395104262613e-06,
      "loss": 0.4551,
      "step": 38662
    },
    {
      "epoch": 1.1876939145393666,
      "grad_norm": 0.44111916422843933,
      "learning_rate": 7.113488332940674e-06,
      "loss": 0.4944,
      "step": 38663
    },
    {
      "epoch": 1.1877246336743157,
      "grad_norm": 0.42383286356925964,
      "learning_rate": 7.1130256299968706e-06,
      "loss": 0.4947,
      "step": 38664
    },
    {
      "epoch": 1.1877553528092648,
      "grad_norm": 0.41594409942626953,
      "learning_rate": 7.1125629337957955e-06,
      "loss": 0.5224,
      "step": 38665
    },
    {
      "epoch": 1.1877860719442142,
      "grad_norm": 0.42258313298225403,
      "learning_rate": 7.112100244338533e-06,
      "loss": 0.4878,
      "step": 38666
    },
    {
      "epoch": 1.1878167910791633,
      "grad_norm": 0.40429654717445374,
      "learning_rate": 7.1116375616261615e-06,
      "loss": 0.5454,
      "step": 38667
    },
    {
      "epoch": 1.1878475102141124,
      "grad_norm": 0.3886113464832306,
      "learning_rate": 7.111174885659762e-06,
      "loss": 0.5024,
      "step": 38668
    },
    {
      "epoch": 1.1878782293490615,
      "grad_norm": 0.4149287939071655,
      "learning_rate": 7.110712216440414e-06,
      "loss": 0.4592,
      "step": 38669
    },
    {
      "epoch": 1.1879089484840106,
      "grad_norm": 0.44566288590431213,
      "learning_rate": 7.110249553969202e-06,
      "loss": 0.4838,
      "step": 38670
    },
    {
      "epoch": 1.1879396676189597,
      "grad_norm": 0.42156079411506653,
      "learning_rate": 7.109786898247202e-06,
      "loss": 0.4992,
      "step": 38671
    },
    {
      "epoch": 1.187970386753909,
      "grad_norm": 0.3719891607761383,
      "learning_rate": 7.1093242492755e-06,
      "loss": 0.4375,
      "step": 38672
    },
    {
      "epoch": 1.1880011058888582,
      "grad_norm": 0.4867657721042633,
      "learning_rate": 7.108861607055166e-06,
      "loss": 0.5347,
      "step": 38673
    },
    {
      "epoch": 1.1880318250238073,
      "grad_norm": 0.37892985343933105,
      "learning_rate": 7.1083989715872956e-06,
      "loss": 0.5303,
      "step": 38674
    },
    {
      "epoch": 1.1880625441587565,
      "grad_norm": 0.4842138886451721,
      "learning_rate": 7.107936342872954e-06,
      "loss": 0.4957,
      "step": 38675
    },
    {
      "epoch": 1.1880932632937056,
      "grad_norm": 0.4445033073425293,
      "learning_rate": 7.107473720913236e-06,
      "loss": 0.4923,
      "step": 38676
    },
    {
      "epoch": 1.188123982428655,
      "grad_norm": 0.43066778779029846,
      "learning_rate": 7.1070111057092095e-06,
      "loss": 0.4788,
      "step": 38677
    },
    {
      "epoch": 1.188154701563604,
      "grad_norm": 0.39891424775123596,
      "learning_rate": 7.106548497261967e-06,
      "loss": 0.5251,
      "step": 38678
    },
    {
      "epoch": 1.1881854206985532,
      "grad_norm": 0.3984197974205017,
      "learning_rate": 7.106085895572576e-06,
      "loss": 0.5384,
      "step": 38679
    },
    {
      "epoch": 1.1882161398335023,
      "grad_norm": 0.3714176118373871,
      "learning_rate": 7.1056233006421285e-06,
      "loss": 0.3842,
      "step": 38680
    },
    {
      "epoch": 1.1882468589684514,
      "grad_norm": 0.5290697813034058,
      "learning_rate": 7.105160712471695e-06,
      "loss": 0.3759,
      "step": 38681
    },
    {
      "epoch": 1.1882775781034005,
      "grad_norm": 0.4280994236469269,
      "learning_rate": 7.104698131062361e-06,
      "loss": 0.4873,
      "step": 38682
    },
    {
      "epoch": 1.1883082972383499,
      "grad_norm": 0.4113338887691498,
      "learning_rate": 7.104235556415211e-06,
      "loss": 0.4783,
      "step": 38683
    },
    {
      "epoch": 1.188339016373299,
      "grad_norm": 0.37811240553855896,
      "learning_rate": 7.103772988531319e-06,
      "loss": 0.5643,
      "step": 38684
    },
    {
      "epoch": 1.188369735508248,
      "grad_norm": 0.41880375146865845,
      "learning_rate": 7.103310427411768e-06,
      "loss": 0.5117,
      "step": 38685
    },
    {
      "epoch": 1.1884004546431972,
      "grad_norm": 0.42781496047973633,
      "learning_rate": 7.102847873057637e-06,
      "loss": 0.5694,
      "step": 38686
    },
    {
      "epoch": 1.1884311737781463,
      "grad_norm": 0.39716067910194397,
      "learning_rate": 7.102385325470008e-06,
      "loss": 0.5317,
      "step": 38687
    },
    {
      "epoch": 1.1884618929130957,
      "grad_norm": 0.39761069416999817,
      "learning_rate": 7.101922784649959e-06,
      "loss": 0.6145,
      "step": 38688
    },
    {
      "epoch": 1.1884926120480448,
      "grad_norm": 0.3549610376358032,
      "learning_rate": 7.101460250598573e-06,
      "loss": 0.4329,
      "step": 38689
    },
    {
      "epoch": 1.188523331182994,
      "grad_norm": 0.4443548619747162,
      "learning_rate": 7.100997723316928e-06,
      "loss": 0.5145,
      "step": 38690
    },
    {
      "epoch": 1.188554050317943,
      "grad_norm": 0.44587576389312744,
      "learning_rate": 7.100535202806107e-06,
      "loss": 0.4821,
      "step": 38691
    },
    {
      "epoch": 1.1885847694528922,
      "grad_norm": 0.4191153049468994,
      "learning_rate": 7.100072689067187e-06,
      "loss": 0.4761,
      "step": 38692
    },
    {
      "epoch": 1.1886154885878413,
      "grad_norm": 0.430946946144104,
      "learning_rate": 7.0996101821012506e-06,
      "loss": 0.4519,
      "step": 38693
    },
    {
      "epoch": 1.1886462077227906,
      "grad_norm": 0.4173978567123413,
      "learning_rate": 7.099147681909375e-06,
      "loss": 0.4411,
      "step": 38694
    },
    {
      "epoch": 1.1886769268577397,
      "grad_norm": 0.43101760745048523,
      "learning_rate": 7.098685188492647e-06,
      "loss": 0.616,
      "step": 38695
    },
    {
      "epoch": 1.1887076459926889,
      "grad_norm": 0.39081844687461853,
      "learning_rate": 7.098222701852137e-06,
      "loss": 0.496,
      "step": 38696
    },
    {
      "epoch": 1.188738365127638,
      "grad_norm": 0.37060797214508057,
      "learning_rate": 7.097760221988936e-06,
      "loss": 0.5122,
      "step": 38697
    },
    {
      "epoch": 1.188769084262587,
      "grad_norm": 0.411415159702301,
      "learning_rate": 7.097297748904115e-06,
      "loss": 0.4652,
      "step": 38698
    },
    {
      "epoch": 1.1887998033975364,
      "grad_norm": 0.4454004764556885,
      "learning_rate": 7.096835282598759e-06,
      "loss": 0.4328,
      "step": 38699
    },
    {
      "epoch": 1.1888305225324856,
      "grad_norm": 0.36663052439689636,
      "learning_rate": 7.096372823073946e-06,
      "loss": 0.4704,
      "step": 38700
    },
    {
      "epoch": 1.1888612416674347,
      "grad_norm": 0.3934459984302521,
      "learning_rate": 7.0959103703307564e-06,
      "loss": 0.549,
      "step": 38701
    },
    {
      "epoch": 1.1888919608023838,
      "grad_norm": 0.38847285509109497,
      "learning_rate": 7.095447924370273e-06,
      "loss": 0.4083,
      "step": 38702
    },
    {
      "epoch": 1.188922679937333,
      "grad_norm": 0.3829843997955322,
      "learning_rate": 7.094985485193573e-06,
      "loss": 0.4798,
      "step": 38703
    },
    {
      "epoch": 1.188953399072282,
      "grad_norm": 0.3572656214237213,
      "learning_rate": 7.0945230528017385e-06,
      "loss": 0.4735,
      "step": 38704
    },
    {
      "epoch": 1.1889841182072314,
      "grad_norm": 0.3950955867767334,
      "learning_rate": 7.094060627195847e-06,
      "loss": 0.4852,
      "step": 38705
    },
    {
      "epoch": 1.1890148373421805,
      "grad_norm": 0.387044757604599,
      "learning_rate": 7.093598208376983e-06,
      "loss": 0.4572,
      "step": 38706
    },
    {
      "epoch": 1.1890455564771296,
      "grad_norm": 0.41577327251434326,
      "learning_rate": 7.093135796346217e-06,
      "loss": 0.4586,
      "step": 38707
    },
    {
      "epoch": 1.1890762756120787,
      "grad_norm": 0.3914719223976135,
      "learning_rate": 7.092673391104642e-06,
      "loss": 0.4472,
      "step": 38708
    },
    {
      "epoch": 1.1891069947470279,
      "grad_norm": 0.3809575140476227,
      "learning_rate": 7.0922109926533255e-06,
      "loss": 0.4988,
      "step": 38709
    },
    {
      "epoch": 1.1891377138819772,
      "grad_norm": 0.4196317195892334,
      "learning_rate": 7.091748600993359e-06,
      "loss": 0.4751,
      "step": 38710
    },
    {
      "epoch": 1.1891684330169263,
      "grad_norm": 0.39316925406455994,
      "learning_rate": 7.09128621612581e-06,
      "loss": 0.514,
      "step": 38711
    },
    {
      "epoch": 1.1891991521518754,
      "grad_norm": 0.40355145931243896,
      "learning_rate": 7.0908238380517726e-06,
      "loss": 0.4862,
      "step": 38712
    },
    {
      "epoch": 1.1892298712868246,
      "grad_norm": 0.39918118715286255,
      "learning_rate": 7.090361466772314e-06,
      "loss": 0.5184,
      "step": 38713
    },
    {
      "epoch": 1.1892605904217737,
      "grad_norm": 0.3634707033634186,
      "learning_rate": 7.089899102288522e-06,
      "loss": 0.3736,
      "step": 38714
    },
    {
      "epoch": 1.1892913095567228,
      "grad_norm": 0.3860117793083191,
      "learning_rate": 7.089436744601472e-06,
      "loss": 0.534,
      "step": 38715
    },
    {
      "epoch": 1.1893220286916721,
      "grad_norm": 0.41231346130371094,
      "learning_rate": 7.088974393712249e-06,
      "loss": 0.5576,
      "step": 38716
    },
    {
      "epoch": 1.1893527478266213,
      "grad_norm": 0.4042482078075409,
      "learning_rate": 7.0885120496219254e-06,
      "loss": 0.5184,
      "step": 38717
    },
    {
      "epoch": 1.1893834669615704,
      "grad_norm": 0.4198247790336609,
      "learning_rate": 7.088049712331584e-06,
      "loss": 0.4737,
      "step": 38718
    },
    {
      "epoch": 1.1894141860965195,
      "grad_norm": 0.4118560552597046,
      "learning_rate": 7.087587381842313e-06,
      "loss": 0.4645,
      "step": 38719
    },
    {
      "epoch": 1.1894449052314686,
      "grad_norm": 0.40770795941352844,
      "learning_rate": 7.08712505815518e-06,
      "loss": 0.5028,
      "step": 38720
    },
    {
      "epoch": 1.189475624366418,
      "grad_norm": 0.4273983836174011,
      "learning_rate": 7.0866627412712705e-06,
      "loss": 0.5642,
      "step": 38721
    },
    {
      "epoch": 1.189506343501367,
      "grad_norm": 0.39915868639945984,
      "learning_rate": 7.086200431191664e-06,
      "loss": 0.4931,
      "step": 38722
    },
    {
      "epoch": 1.1895370626363162,
      "grad_norm": 0.4125980734825134,
      "learning_rate": 7.0857381279174406e-06,
      "loss": 0.5082,
      "step": 38723
    },
    {
      "epoch": 1.1895677817712653,
      "grad_norm": 0.3779720962047577,
      "learning_rate": 7.085275831449679e-06,
      "loss": 0.4699,
      "step": 38724
    },
    {
      "epoch": 1.1895985009062144,
      "grad_norm": 0.37488213181495667,
      "learning_rate": 7.0848135417894595e-06,
      "loss": 0.3979,
      "step": 38725
    },
    {
      "epoch": 1.1896292200411636,
      "grad_norm": 0.3798316419124603,
      "learning_rate": 7.08435125893786e-06,
      "loss": 0.4831,
      "step": 38726
    },
    {
      "epoch": 1.1896599391761127,
      "grad_norm": 0.517860472202301,
      "learning_rate": 7.083888982895964e-06,
      "loss": 0.4778,
      "step": 38727
    },
    {
      "epoch": 1.189690658311062,
      "grad_norm": 0.402315616607666,
      "learning_rate": 7.083426713664846e-06,
      "loss": 0.4869,
      "step": 38728
    },
    {
      "epoch": 1.1897213774460111,
      "grad_norm": 0.38075169920921326,
      "learning_rate": 7.082964451245591e-06,
      "loss": 0.4641,
      "step": 38729
    },
    {
      "epoch": 1.1897520965809603,
      "grad_norm": 0.41475242376327515,
      "learning_rate": 7.082502195639274e-06,
      "loss": 0.5142,
      "step": 38730
    },
    {
      "epoch": 1.1897828157159094,
      "grad_norm": 0.3988414704799652,
      "learning_rate": 7.08203994684698e-06,
      "loss": 0.4885,
      "step": 38731
    },
    {
      "epoch": 1.1898135348508587,
      "grad_norm": 0.3951878547668457,
      "learning_rate": 7.081577704869783e-06,
      "loss": 0.4592,
      "step": 38732
    },
    {
      "epoch": 1.1898442539858078,
      "grad_norm": 0.4682263135910034,
      "learning_rate": 7.081115469708768e-06,
      "loss": 0.4143,
      "step": 38733
    },
    {
      "epoch": 1.189874973120757,
      "grad_norm": 0.45842352509498596,
      "learning_rate": 7.080653241365008e-06,
      "loss": 0.4821,
      "step": 38734
    },
    {
      "epoch": 1.189905692255706,
      "grad_norm": 0.39797428250312805,
      "learning_rate": 7.080191019839591e-06,
      "loss": 0.448,
      "step": 38735
    },
    {
      "epoch": 1.1899364113906552,
      "grad_norm": 0.4289807379245758,
      "learning_rate": 7.079728805133586e-06,
      "loss": 0.4804,
      "step": 38736
    },
    {
      "epoch": 1.1899671305256043,
      "grad_norm": 0.3868156373500824,
      "learning_rate": 7.07926659724808e-06,
      "loss": 0.5681,
      "step": 38737
    },
    {
      "epoch": 1.1899978496605534,
      "grad_norm": 0.4132407009601593,
      "learning_rate": 7.078804396184154e-06,
      "loss": 0.568,
      "step": 38738
    },
    {
      "epoch": 1.1900285687955028,
      "grad_norm": 0.41864725947380066,
      "learning_rate": 7.07834220194288e-06,
      "loss": 0.501,
      "step": 38739
    },
    {
      "epoch": 1.190059287930452,
      "grad_norm": 0.41777122020721436,
      "learning_rate": 7.077880014525344e-06,
      "loss": 0.4267,
      "step": 38740
    },
    {
      "epoch": 1.190090007065401,
      "grad_norm": 0.4031756520271301,
      "learning_rate": 7.077417833932623e-06,
      "loss": 0.5206,
      "step": 38741
    },
    {
      "epoch": 1.1901207262003501,
      "grad_norm": 0.41801896691322327,
      "learning_rate": 7.076955660165801e-06,
      "loss": 0.4536,
      "step": 38742
    },
    {
      "epoch": 1.1901514453352993,
      "grad_norm": 0.3727012276649475,
      "learning_rate": 7.076493493225947e-06,
      "loss": 0.4716,
      "step": 38743
    },
    {
      "epoch": 1.1901821644702486,
      "grad_norm": 0.37973204255104065,
      "learning_rate": 7.076031333114151e-06,
      "loss": 0.4311,
      "step": 38744
    },
    {
      "epoch": 1.1902128836051977,
      "grad_norm": 0.41783779859542847,
      "learning_rate": 7.075569179831483e-06,
      "loss": 0.5225,
      "step": 38745
    },
    {
      "epoch": 1.1902436027401468,
      "grad_norm": 0.41659289598464966,
      "learning_rate": 7.0751070333790335e-06,
      "loss": 0.4542,
      "step": 38746
    },
    {
      "epoch": 1.190274321875096,
      "grad_norm": 0.4343563914299011,
      "learning_rate": 7.074644893757872e-06,
      "loss": 0.4322,
      "step": 38747
    },
    {
      "epoch": 1.190305041010045,
      "grad_norm": 0.4020683169364929,
      "learning_rate": 7.074182760969084e-06,
      "loss": 0.5102,
      "step": 38748
    },
    {
      "epoch": 1.1903357601449942,
      "grad_norm": 0.3815688490867615,
      "learning_rate": 7.073720635013743e-06,
      "loss": 0.4405,
      "step": 38749
    },
    {
      "epoch": 1.1903664792799435,
      "grad_norm": 0.3853127658367157,
      "learning_rate": 7.073258515892935e-06,
      "loss": 0.5323,
      "step": 38750
    },
    {
      "epoch": 1.1903971984148927,
      "grad_norm": 0.39890870451927185,
      "learning_rate": 7.0727964036077335e-06,
      "loss": 0.4474,
      "step": 38751
    },
    {
      "epoch": 1.1904279175498418,
      "grad_norm": 0.4447925388813019,
      "learning_rate": 7.0723342981592224e-06,
      "loss": 0.41,
      "step": 38752
    },
    {
      "epoch": 1.190458636684791,
      "grad_norm": 0.35552534461021423,
      "learning_rate": 7.071872199548477e-06,
      "loss": 0.4347,
      "step": 38753
    },
    {
      "epoch": 1.19048935581974,
      "grad_norm": 0.3727526366710663,
      "learning_rate": 7.071410107776582e-06,
      "loss": 0.44,
      "step": 38754
    },
    {
      "epoch": 1.1905200749546894,
      "grad_norm": 0.4460900127887726,
      "learning_rate": 7.070948022844611e-06,
      "loss": 0.4863,
      "step": 38755
    },
    {
      "epoch": 1.1905507940896385,
      "grad_norm": 0.4572903513908386,
      "learning_rate": 7.0704859447536435e-06,
      "loss": 0.4535,
      "step": 38756
    },
    {
      "epoch": 1.1905815132245876,
      "grad_norm": 0.42499154806137085,
      "learning_rate": 7.070023873504764e-06,
      "loss": 0.5008,
      "step": 38757
    },
    {
      "epoch": 1.1906122323595367,
      "grad_norm": 0.4229621887207031,
      "learning_rate": 7.069561809099046e-06,
      "loss": 0.5043,
      "step": 38758
    },
    {
      "epoch": 1.1906429514944858,
      "grad_norm": 0.43850523233413696,
      "learning_rate": 7.069099751537574e-06,
      "loss": 0.477,
      "step": 38759
    },
    {
      "epoch": 1.190673670629435,
      "grad_norm": 0.4328325092792511,
      "learning_rate": 7.0686377008214216e-06,
      "loss": 0.4916,
      "step": 38760
    },
    {
      "epoch": 1.1907043897643843,
      "grad_norm": 0.3903597593307495,
      "learning_rate": 7.068175656951672e-06,
      "loss": 0.476,
      "step": 38761
    },
    {
      "epoch": 1.1907351088993334,
      "grad_norm": 0.538716733455658,
      "learning_rate": 7.0677136199294015e-06,
      "loss": 0.4289,
      "step": 38762
    },
    {
      "epoch": 1.1907658280342825,
      "grad_norm": 0.43775463104248047,
      "learning_rate": 7.067251589755693e-06,
      "loss": 0.5058,
      "step": 38763
    },
    {
      "epoch": 1.1907965471692317,
      "grad_norm": 0.3768996298313141,
      "learning_rate": 7.06678956643162e-06,
      "loss": 0.4687,
      "step": 38764
    },
    {
      "epoch": 1.1908272663041808,
      "grad_norm": 0.397623747587204,
      "learning_rate": 7.066327549958267e-06,
      "loss": 0.5005,
      "step": 38765
    },
    {
      "epoch": 1.1908579854391301,
      "grad_norm": 0.37632209062576294,
      "learning_rate": 7.0658655403367095e-06,
      "loss": 0.4683,
      "step": 38766
    },
    {
      "epoch": 1.1908887045740792,
      "grad_norm": 0.395746111869812,
      "learning_rate": 7.065403537568029e-06,
      "loss": 0.4316,
      "step": 38767
    },
    {
      "epoch": 1.1909194237090284,
      "grad_norm": 0.385794073343277,
      "learning_rate": 7.064941541653303e-06,
      "loss": 0.5152,
      "step": 38768
    },
    {
      "epoch": 1.1909501428439775,
      "grad_norm": 0.39695584774017334,
      "learning_rate": 7.064479552593615e-06,
      "loss": 0.6028,
      "step": 38769
    },
    {
      "epoch": 1.1909808619789266,
      "grad_norm": 0.3748641014099121,
      "learning_rate": 7.064017570390034e-06,
      "loss": 0.5043,
      "step": 38770
    },
    {
      "epoch": 1.1910115811138757,
      "grad_norm": 0.41389259696006775,
      "learning_rate": 7.06355559504365e-06,
      "loss": 0.4814,
      "step": 38771
    },
    {
      "epoch": 1.191042300248825,
      "grad_norm": 0.45373785495758057,
      "learning_rate": 7.0630936265555305e-06,
      "loss": 0.5165,
      "step": 38772
    },
    {
      "epoch": 1.1910730193837742,
      "grad_norm": 0.39894115924835205,
      "learning_rate": 7.062631664926765e-06,
      "loss": 0.5436,
      "step": 38773
    },
    {
      "epoch": 1.1911037385187233,
      "grad_norm": 0.3661194443702698,
      "learning_rate": 7.0621697101584286e-06,
      "loss": 0.489,
      "step": 38774
    },
    {
      "epoch": 1.1911344576536724,
      "grad_norm": 0.39951029419898987,
      "learning_rate": 7.061707762251598e-06,
      "loss": 0.4262,
      "step": 38775
    },
    {
      "epoch": 1.1911651767886215,
      "grad_norm": 0.41759616136550903,
      "learning_rate": 7.061245821207359e-06,
      "loss": 0.513,
      "step": 38776
    },
    {
      "epoch": 1.191195895923571,
      "grad_norm": 0.3725961744785309,
      "learning_rate": 7.060783887026779e-06,
      "loss": 0.552,
      "step": 38777
    },
    {
      "epoch": 1.19122661505852,
      "grad_norm": 0.3882925510406494,
      "learning_rate": 7.060321959710951e-06,
      "loss": 0.4799,
      "step": 38778
    },
    {
      "epoch": 1.1912573341934691,
      "grad_norm": 0.43265363574028015,
      "learning_rate": 7.059860039260938e-06,
      "loss": 0.4727,
      "step": 38779
    },
    {
      "epoch": 1.1912880533284183,
      "grad_norm": 0.39535748958587646,
      "learning_rate": 7.059398125677835e-06,
      "loss": 0.4659,
      "step": 38780
    },
    {
      "epoch": 1.1913187724633674,
      "grad_norm": 0.3922533392906189,
      "learning_rate": 7.0589362189627065e-06,
      "loss": 0.4701,
      "step": 38781
    },
    {
      "epoch": 1.1913494915983165,
      "grad_norm": 0.3932303786277771,
      "learning_rate": 7.058474319116644e-06,
      "loss": 0.466,
      "step": 38782
    },
    {
      "epoch": 1.1913802107332658,
      "grad_norm": 0.49550315737724304,
      "learning_rate": 7.058012426140717e-06,
      "loss": 0.5063,
      "step": 38783
    },
    {
      "epoch": 1.191410929868215,
      "grad_norm": 0.4046695828437805,
      "learning_rate": 7.057550540036008e-06,
      "loss": 0.4313,
      "step": 38784
    },
    {
      "epoch": 1.191441649003164,
      "grad_norm": 0.397671103477478,
      "learning_rate": 7.0570886608035925e-06,
      "loss": 0.5103,
      "step": 38785
    },
    {
      "epoch": 1.1914723681381132,
      "grad_norm": 0.3746435344219208,
      "learning_rate": 7.0566267884445564e-06,
      "loss": 0.4946,
      "step": 38786
    },
    {
      "epoch": 1.1915030872730623,
      "grad_norm": 0.3927176296710968,
      "learning_rate": 7.05616492295997e-06,
      "loss": 0.5269,
      "step": 38787
    },
    {
      "epoch": 1.1915338064080117,
      "grad_norm": 0.7041789889335632,
      "learning_rate": 7.055703064350919e-06,
      "loss": 0.3894,
      "step": 38788
    },
    {
      "epoch": 1.1915645255429608,
      "grad_norm": 0.4018845856189728,
      "learning_rate": 7.055241212618478e-06,
      "loss": 0.5462,
      "step": 38789
    },
    {
      "epoch": 1.19159524467791,
      "grad_norm": 0.39978349208831787,
      "learning_rate": 7.054779367763726e-06,
      "loss": 0.4925,
      "step": 38790
    },
    {
      "epoch": 1.191625963812859,
      "grad_norm": 0.4573715925216675,
      "learning_rate": 7.054317529787743e-06,
      "loss": 0.4888,
      "step": 38791
    },
    {
      "epoch": 1.1916566829478081,
      "grad_norm": 0.43394750356674194,
      "learning_rate": 7.053855698691606e-06,
      "loss": 0.4627,
      "step": 38792
    },
    {
      "epoch": 1.1916874020827573,
      "grad_norm": 0.3892383873462677,
      "learning_rate": 7.053393874476397e-06,
      "loss": 0.4517,
      "step": 38793
    },
    {
      "epoch": 1.1917181212177066,
      "grad_norm": 0.3686729073524475,
      "learning_rate": 7.052932057143191e-06,
      "loss": 0.4522,
      "step": 38794
    },
    {
      "epoch": 1.1917488403526557,
      "grad_norm": 0.5336560010910034,
      "learning_rate": 7.052470246693069e-06,
      "loss": 0.4281,
      "step": 38795
    },
    {
      "epoch": 1.1917795594876048,
      "grad_norm": 0.38804513216018677,
      "learning_rate": 7.052008443127107e-06,
      "loss": 0.4519,
      "step": 38796
    },
    {
      "epoch": 1.191810278622554,
      "grad_norm": 0.36877933144569397,
      "learning_rate": 7.051546646446387e-06,
      "loss": 0.4721,
      "step": 38797
    },
    {
      "epoch": 1.191840997757503,
      "grad_norm": 0.41696298122406006,
      "learning_rate": 7.051084856651984e-06,
      "loss": 0.5201,
      "step": 38798
    },
    {
      "epoch": 1.1918717168924524,
      "grad_norm": 0.3826340138912201,
      "learning_rate": 7.050623073744981e-06,
      "loss": 0.5059,
      "step": 38799
    },
    {
      "epoch": 1.1919024360274015,
      "grad_norm": 0.4020996391773224,
      "learning_rate": 7.050161297726451e-06,
      "loss": 0.4662,
      "step": 38800
    },
    {
      "epoch": 1.1919331551623507,
      "grad_norm": 0.3947649598121643,
      "learning_rate": 7.049699528597478e-06,
      "loss": 0.5048,
      "step": 38801
    },
    {
      "epoch": 1.1919638742972998,
      "grad_norm": 0.41233333945274353,
      "learning_rate": 7.049237766359134e-06,
      "loss": 0.4846,
      "step": 38802
    },
    {
      "epoch": 1.191994593432249,
      "grad_norm": 0.427354097366333,
      "learning_rate": 7.048776011012504e-06,
      "loss": 0.5327,
      "step": 38803
    },
    {
      "epoch": 1.192025312567198,
      "grad_norm": 0.45511600375175476,
      "learning_rate": 7.048314262558663e-06,
      "loss": 0.5308,
      "step": 38804
    },
    {
      "epoch": 1.1920560317021474,
      "grad_norm": 0.4361916184425354,
      "learning_rate": 7.047852520998694e-06,
      "loss": 0.4872,
      "step": 38805
    },
    {
      "epoch": 1.1920867508370965,
      "grad_norm": 0.371437668800354,
      "learning_rate": 7.047390786333664e-06,
      "loss": 0.5422,
      "step": 38806
    },
    {
      "epoch": 1.1921174699720456,
      "grad_norm": 0.40557870268821716,
      "learning_rate": 7.0469290585646664e-06,
      "loss": 0.4395,
      "step": 38807
    },
    {
      "epoch": 1.1921481891069947,
      "grad_norm": 0.3691862225532532,
      "learning_rate": 7.046467337692766e-06,
      "loss": 0.4457,
      "step": 38808
    },
    {
      "epoch": 1.1921789082419438,
      "grad_norm": 0.4483613967895508,
      "learning_rate": 7.0460056237190485e-06,
      "loss": 0.5896,
      "step": 38809
    },
    {
      "epoch": 1.1922096273768932,
      "grad_norm": 0.40475329756736755,
      "learning_rate": 7.045543916644596e-06,
      "loss": 0.5471,
      "step": 38810
    },
    {
      "epoch": 1.1922403465118423,
      "grad_norm": 0.45310455560684204,
      "learning_rate": 7.0450822164704755e-06,
      "loss": 0.5204,
      "step": 38811
    },
    {
      "epoch": 1.1922710656467914,
      "grad_norm": 0.3674681484699249,
      "learning_rate": 7.044620523197778e-06,
      "loss": 0.5176,
      "step": 38812
    },
    {
      "epoch": 1.1923017847817405,
      "grad_norm": 0.39587119221687317,
      "learning_rate": 7.04415883682757e-06,
      "loss": 0.4506,
      "step": 38813
    },
    {
      "epoch": 1.1923325039166897,
      "grad_norm": 0.4031813442707062,
      "learning_rate": 7.0436971573609425e-06,
      "loss": 0.4846,
      "step": 38814
    },
    {
      "epoch": 1.1923632230516388,
      "grad_norm": 0.3966813385486603,
      "learning_rate": 7.043235484798959e-06,
      "loss": 0.4978,
      "step": 38815
    },
    {
      "epoch": 1.1923939421865881,
      "grad_norm": 0.412388414144516,
      "learning_rate": 7.042773819142712e-06,
      "loss": 0.4927,
      "step": 38816
    },
    {
      "epoch": 1.1924246613215372,
      "grad_norm": 0.39592474699020386,
      "learning_rate": 7.04231216039327e-06,
      "loss": 0.4792,
      "step": 38817
    },
    {
      "epoch": 1.1924553804564864,
      "grad_norm": 0.4238753020763397,
      "learning_rate": 7.041850508551716e-06,
      "loss": 0.536,
      "step": 38818
    },
    {
      "epoch": 1.1924860995914355,
      "grad_norm": 0.39183562994003296,
      "learning_rate": 7.041388863619125e-06,
      "loss": 0.5498,
      "step": 38819
    },
    {
      "epoch": 1.1925168187263846,
      "grad_norm": 0.3928813338279724,
      "learning_rate": 7.040927225596579e-06,
      "loss": 0.5012,
      "step": 38820
    },
    {
      "epoch": 1.192547537861334,
      "grad_norm": 0.40608638525009155,
      "learning_rate": 7.040465594485151e-06,
      "loss": 0.535,
      "step": 38821
    },
    {
      "epoch": 1.192578256996283,
      "grad_norm": 0.4117131531238556,
      "learning_rate": 7.040003970285925e-06,
      "loss": 0.4565,
      "step": 38822
    },
    {
      "epoch": 1.1926089761312322,
      "grad_norm": 0.46661439538002014,
      "learning_rate": 7.039542352999975e-06,
      "loss": 0.4964,
      "step": 38823
    },
    {
      "epoch": 1.1926396952661813,
      "grad_norm": 0.37720274925231934,
      "learning_rate": 7.0390807426283814e-06,
      "loss": 0.4442,
      "step": 38824
    },
    {
      "epoch": 1.1926704144011304,
      "grad_norm": 0.3566669821739197,
      "learning_rate": 7.03861913917222e-06,
      "loss": 0.4281,
      "step": 38825
    },
    {
      "epoch": 1.1927011335360795,
      "grad_norm": 0.37549424171447754,
      "learning_rate": 7.038157542632573e-06,
      "loss": 0.4999,
      "step": 38826
    },
    {
      "epoch": 1.1927318526710289,
      "grad_norm": 0.3775792419910431,
      "learning_rate": 7.037695953010513e-06,
      "loss": 0.4923,
      "step": 38827
    },
    {
      "epoch": 1.192762571805978,
      "grad_norm": 0.3832881450653076,
      "learning_rate": 7.037234370307122e-06,
      "loss": 0.5102,
      "step": 38828
    },
    {
      "epoch": 1.1927932909409271,
      "grad_norm": 0.4546467959880829,
      "learning_rate": 7.0367727945234785e-06,
      "loss": 0.5093,
      "step": 38829
    },
    {
      "epoch": 1.1928240100758762,
      "grad_norm": 0.43836459517478943,
      "learning_rate": 7.036311225660657e-06,
      "loss": 0.4445,
      "step": 38830
    },
    {
      "epoch": 1.1928547292108254,
      "grad_norm": 0.5447574257850647,
      "learning_rate": 7.035849663719741e-06,
      "loss": 0.485,
      "step": 38831
    },
    {
      "epoch": 1.1928854483457747,
      "grad_norm": 0.41106462478637695,
      "learning_rate": 7.035388108701801e-06,
      "loss": 0.4604,
      "step": 38832
    },
    {
      "epoch": 1.1929161674807238,
      "grad_norm": 0.5014963746070862,
      "learning_rate": 7.034926560607922e-06,
      "loss": 0.5232,
      "step": 38833
    },
    {
      "epoch": 1.192946886615673,
      "grad_norm": 0.46577581763267517,
      "learning_rate": 7.034465019439176e-06,
      "loss": 0.485,
      "step": 38834
    },
    {
      "epoch": 1.192977605750622,
      "grad_norm": 0.3804458975791931,
      "learning_rate": 7.034003485196648e-06,
      "loss": 0.4224,
      "step": 38835
    },
    {
      "epoch": 1.1930083248855712,
      "grad_norm": 0.44186142086982727,
      "learning_rate": 7.033541957881409e-06,
      "loss": 0.4679,
      "step": 38836
    },
    {
      "epoch": 1.1930390440205203,
      "grad_norm": 0.3866579234600067,
      "learning_rate": 7.033080437494542e-06,
      "loss": 0.4307,
      "step": 38837
    },
    {
      "epoch": 1.1930697631554694,
      "grad_norm": 0.3772995173931122,
      "learning_rate": 7.032618924037121e-06,
      "loss": 0.4698,
      "step": 38838
    },
    {
      "epoch": 1.1931004822904188,
      "grad_norm": 0.40554261207580566,
      "learning_rate": 7.03215741751023e-06,
      "loss": 0.5723,
      "step": 38839
    },
    {
      "epoch": 1.1931312014253679,
      "grad_norm": 0.35899049043655396,
      "learning_rate": 7.031695917914936e-06,
      "loss": 0.4308,
      "step": 38840
    },
    {
      "epoch": 1.193161920560317,
      "grad_norm": 0.4022141396999359,
      "learning_rate": 7.03123442525233e-06,
      "loss": 0.6003,
      "step": 38841
    },
    {
      "epoch": 1.1931926396952661,
      "grad_norm": 0.40105175971984863,
      "learning_rate": 7.030772939523477e-06,
      "loss": 0.4651,
      "step": 38842
    },
    {
      "epoch": 1.1932233588302155,
      "grad_norm": 0.4064866900444031,
      "learning_rate": 7.030311460729467e-06,
      "loss": 0.5176,
      "step": 38843
    },
    {
      "epoch": 1.1932540779651646,
      "grad_norm": 0.6361554861068726,
      "learning_rate": 7.029849988871367e-06,
      "loss": 0.4811,
      "step": 38844
    },
    {
      "epoch": 1.1932847971001137,
      "grad_norm": 0.40615376830101013,
      "learning_rate": 7.029388523950264e-06,
      "loss": 0.4261,
      "step": 38845
    },
    {
      "epoch": 1.1933155162350628,
      "grad_norm": 0.4329901337623596,
      "learning_rate": 7.0289270659672294e-06,
      "loss": 0.4277,
      "step": 38846
    },
    {
      "epoch": 1.193346235370012,
      "grad_norm": 0.416781485080719,
      "learning_rate": 7.028465614923341e-06,
      "loss": 0.4546,
      "step": 38847
    },
    {
      "epoch": 1.193376954504961,
      "grad_norm": 0.5243059992790222,
      "learning_rate": 7.028004170819683e-06,
      "loss": 0.3789,
      "step": 38848
    },
    {
      "epoch": 1.1934076736399102,
      "grad_norm": 0.39764487743377686,
      "learning_rate": 7.027542733657325e-06,
      "loss": 0.4663,
      "step": 38849
    },
    {
      "epoch": 1.1934383927748595,
      "grad_norm": 0.3855510652065277,
      "learning_rate": 7.027081303437353e-06,
      "loss": 0.452,
      "step": 38850
    },
    {
      "epoch": 1.1934691119098086,
      "grad_norm": 0.43932029604911804,
      "learning_rate": 7.026619880160836e-06,
      "loss": 0.506,
      "step": 38851
    },
    {
      "epoch": 1.1934998310447578,
      "grad_norm": 0.3662925958633423,
      "learning_rate": 7.0261584638288585e-06,
      "loss": 0.4462,
      "step": 38852
    },
    {
      "epoch": 1.1935305501797069,
      "grad_norm": 0.36238062381744385,
      "learning_rate": 7.025697054442494e-06,
      "loss": 0.4205,
      "step": 38853
    },
    {
      "epoch": 1.193561269314656,
      "grad_norm": 0.4256034195423126,
      "learning_rate": 7.025235652002824e-06,
      "loss": 0.5506,
      "step": 38854
    },
    {
      "epoch": 1.1935919884496053,
      "grad_norm": 0.41086429357528687,
      "learning_rate": 7.024774256510921e-06,
      "loss": 0.5153,
      "step": 38855
    },
    {
      "epoch": 1.1936227075845545,
      "grad_norm": 0.3876981735229492,
      "learning_rate": 7.024312867967868e-06,
      "loss": 0.4556,
      "step": 38856
    },
    {
      "epoch": 1.1936534267195036,
      "grad_norm": 0.42724505066871643,
      "learning_rate": 7.023851486374738e-06,
      "loss": 0.3828,
      "step": 38857
    },
    {
      "epoch": 1.1936841458544527,
      "grad_norm": 0.3859190344810486,
      "learning_rate": 7.023390111732613e-06,
      "loss": 0.4841,
      "step": 38858
    },
    {
      "epoch": 1.1937148649894018,
      "grad_norm": 0.4961966276168823,
      "learning_rate": 7.022928744042565e-06,
      "loss": 0.4763,
      "step": 38859
    },
    {
      "epoch": 1.193745584124351,
      "grad_norm": 0.3639869689941406,
      "learning_rate": 7.022467383305678e-06,
      "loss": 0.4389,
      "step": 38860
    },
    {
      "epoch": 1.1937763032593003,
      "grad_norm": 0.42456331849098206,
      "learning_rate": 7.022006029523024e-06,
      "loss": 0.4601,
      "step": 38861
    },
    {
      "epoch": 1.1938070223942494,
      "grad_norm": 0.4183158874511719,
      "learning_rate": 7.021544682695685e-06,
      "loss": 0.4906,
      "step": 38862
    },
    {
      "epoch": 1.1938377415291985,
      "grad_norm": 0.4196661710739136,
      "learning_rate": 7.021083342824735e-06,
      "loss": 0.5184,
      "step": 38863
    },
    {
      "epoch": 1.1938684606641476,
      "grad_norm": 0.3814021348953247,
      "learning_rate": 7.020622009911252e-06,
      "loss": 0.4712,
      "step": 38864
    },
    {
      "epoch": 1.1938991797990968,
      "grad_norm": 0.43710994720458984,
      "learning_rate": 7.020160683956316e-06,
      "loss": 0.4911,
      "step": 38865
    },
    {
      "epoch": 1.193929898934046,
      "grad_norm": 0.42707929015159607,
      "learning_rate": 7.019699364961003e-06,
      "loss": 0.4891,
      "step": 38866
    },
    {
      "epoch": 1.1939606180689952,
      "grad_norm": 0.49710050225257874,
      "learning_rate": 7.019238052926391e-06,
      "loss": 0.4325,
      "step": 38867
    },
    {
      "epoch": 1.1939913372039443,
      "grad_norm": 0.3933860957622528,
      "learning_rate": 7.018776747853553e-06,
      "loss": 0.534,
      "step": 38868
    },
    {
      "epoch": 1.1940220563388935,
      "grad_norm": 0.457865446805954,
      "learning_rate": 7.018315449743574e-06,
      "loss": 0.4845,
      "step": 38869
    },
    {
      "epoch": 1.1940527754738426,
      "grad_norm": 0.3617178499698639,
      "learning_rate": 7.017854158597526e-06,
      "loss": 0.4295,
      "step": 38870
    },
    {
      "epoch": 1.1940834946087917,
      "grad_norm": 0.42516589164733887,
      "learning_rate": 7.017392874416489e-06,
      "loss": 0.4727,
      "step": 38871
    },
    {
      "epoch": 1.194114213743741,
      "grad_norm": 0.4027937352657318,
      "learning_rate": 7.016931597201537e-06,
      "loss": 0.4787,
      "step": 38872
    },
    {
      "epoch": 1.1941449328786902,
      "grad_norm": 0.4491814076900482,
      "learning_rate": 7.016470326953751e-06,
      "loss": 0.5378,
      "step": 38873
    },
    {
      "epoch": 1.1941756520136393,
      "grad_norm": 0.4499909579753876,
      "learning_rate": 7.016009063674206e-06,
      "loss": 0.4512,
      "step": 38874
    },
    {
      "epoch": 1.1942063711485884,
      "grad_norm": 0.3963734805583954,
      "learning_rate": 7.015547807363985e-06,
      "loss": 0.4723,
      "step": 38875
    },
    {
      "epoch": 1.1942370902835375,
      "grad_norm": 0.4120335280895233,
      "learning_rate": 7.015086558024154e-06,
      "loss": 0.4668,
      "step": 38876
    },
    {
      "epoch": 1.1942678094184869,
      "grad_norm": 0.47551941871643066,
      "learning_rate": 7.014625315655801e-06,
      "loss": 0.4197,
      "step": 38877
    },
    {
      "epoch": 1.194298528553436,
      "grad_norm": 0.3684416115283966,
      "learning_rate": 7.014164080259995e-06,
      "loss": 0.419,
      "step": 38878
    },
    {
      "epoch": 1.194329247688385,
      "grad_norm": 0.4051266014575958,
      "learning_rate": 7.013702851837823e-06,
      "loss": 0.4783,
      "step": 38879
    },
    {
      "epoch": 1.1943599668233342,
      "grad_norm": 0.4016292989253998,
      "learning_rate": 7.013241630390351e-06,
      "loss": 0.4617,
      "step": 38880
    },
    {
      "epoch": 1.1943906859582833,
      "grad_norm": 0.4415235221385956,
      "learning_rate": 7.0127804159186655e-06,
      "loss": 0.4799,
      "step": 38881
    },
    {
      "epoch": 1.1944214050932325,
      "grad_norm": 0.4381870627403259,
      "learning_rate": 7.0123192084238375e-06,
      "loss": 0.4659,
      "step": 38882
    },
    {
      "epoch": 1.1944521242281818,
      "grad_norm": 0.42407339811325073,
      "learning_rate": 7.011858007906944e-06,
      "loss": 0.4002,
      "step": 38883
    },
    {
      "epoch": 1.194482843363131,
      "grad_norm": 0.4019722640514374,
      "learning_rate": 7.011396814369073e-06,
      "loss": 0.4925,
      "step": 38884
    },
    {
      "epoch": 1.19451356249808,
      "grad_norm": 0.3655983507633209,
      "learning_rate": 7.010935627811285e-06,
      "loss": 0.4449,
      "step": 38885
    },
    {
      "epoch": 1.1945442816330292,
      "grad_norm": 0.42424601316452026,
      "learning_rate": 7.0104744482346736e-06,
      "loss": 0.4249,
      "step": 38886
    },
    {
      "epoch": 1.1945750007679783,
      "grad_norm": 0.4224364757537842,
      "learning_rate": 7.010013275640302e-06,
      "loss": 0.5505,
      "step": 38887
    },
    {
      "epoch": 1.1946057199029276,
      "grad_norm": 0.4144071340560913,
      "learning_rate": 7.009552110029256e-06,
      "loss": 0.4641,
      "step": 38888
    },
    {
      "epoch": 1.1946364390378768,
      "grad_norm": 0.46360936760902405,
      "learning_rate": 7.0090909514026086e-06,
      "loss": 0.5565,
      "step": 38889
    },
    {
      "epoch": 1.1946671581728259,
      "grad_norm": 0.4394613206386566,
      "learning_rate": 7.00862979976144e-06,
      "loss": 0.5211,
      "step": 38890
    },
    {
      "epoch": 1.194697877307775,
      "grad_norm": 0.4089597761631012,
      "learning_rate": 7.0081686551068214e-06,
      "loss": 0.5193,
      "step": 38891
    },
    {
      "epoch": 1.1947285964427241,
      "grad_norm": 0.4123389422893524,
      "learning_rate": 7.007707517439838e-06,
      "loss": 0.4403,
      "step": 38892
    },
    {
      "epoch": 1.1947593155776732,
      "grad_norm": 0.42781680822372437,
      "learning_rate": 7.0072463867615605e-06,
      "loss": 0.4338,
      "step": 38893
    },
    {
      "epoch": 1.1947900347126226,
      "grad_norm": 0.4026534855365753,
      "learning_rate": 7.006785263073069e-06,
      "loss": 0.4362,
      "step": 38894
    },
    {
      "epoch": 1.1948207538475717,
      "grad_norm": 0.4102562963962555,
      "learning_rate": 7.006324146375438e-06,
      "loss": 0.4693,
      "step": 38895
    },
    {
      "epoch": 1.1948514729825208,
      "grad_norm": 0.39901840686798096,
      "learning_rate": 7.005863036669749e-06,
      "loss": 0.4702,
      "step": 38896
    },
    {
      "epoch": 1.19488219211747,
      "grad_norm": 0.4145796298980713,
      "learning_rate": 7.005401933957072e-06,
      "loss": 0.5213,
      "step": 38897
    },
    {
      "epoch": 1.194912911252419,
      "grad_norm": 0.41273823380470276,
      "learning_rate": 7.004940838238492e-06,
      "loss": 0.5644,
      "step": 38898
    },
    {
      "epoch": 1.1949436303873684,
      "grad_norm": 0.42990243434906006,
      "learning_rate": 7.004479749515079e-06,
      "loss": 0.4429,
      "step": 38899
    },
    {
      "epoch": 1.1949743495223175,
      "grad_norm": 0.4008100628852844,
      "learning_rate": 7.004018667787915e-06,
      "loss": 0.4817,
      "step": 38900
    },
    {
      "epoch": 1.1950050686572666,
      "grad_norm": 0.4312707483768463,
      "learning_rate": 7.0035575930580725e-06,
      "loss": 0.5101,
      "step": 38901
    },
    {
      "epoch": 1.1950357877922158,
      "grad_norm": 0.37871435284614563,
      "learning_rate": 7.003096525326629e-06,
      "loss": 0.4903,
      "step": 38902
    },
    {
      "epoch": 1.1950665069271649,
      "grad_norm": 0.3752419352531433,
      "learning_rate": 7.002635464594667e-06,
      "loss": 0.4462,
      "step": 38903
    },
    {
      "epoch": 1.195097226062114,
      "grad_norm": 0.41718411445617676,
      "learning_rate": 7.002174410863256e-06,
      "loss": 0.4024,
      "step": 38904
    },
    {
      "epoch": 1.1951279451970633,
      "grad_norm": 0.4022257924079895,
      "learning_rate": 7.00171336413348e-06,
      "loss": 0.4592,
      "step": 38905
    },
    {
      "epoch": 1.1951586643320125,
      "grad_norm": 0.4073588252067566,
      "learning_rate": 7.001252324406407e-06,
      "loss": 0.3593,
      "step": 38906
    },
    {
      "epoch": 1.1951893834669616,
      "grad_norm": 0.39749306440353394,
      "learning_rate": 7.0007912916831226e-06,
      "loss": 0.4701,
      "step": 38907
    },
    {
      "epoch": 1.1952201026019107,
      "grad_norm": 0.3453357517719269,
      "learning_rate": 7.0003302659646965e-06,
      "loss": 0.4747,
      "step": 38908
    },
    {
      "epoch": 1.1952508217368598,
      "grad_norm": 0.37037894129753113,
      "learning_rate": 6.999869247252213e-06,
      "loss": 0.5061,
      "step": 38909
    },
    {
      "epoch": 1.1952815408718092,
      "grad_norm": 0.45187482237815857,
      "learning_rate": 6.999408235546738e-06,
      "loss": 0.4198,
      "step": 38910
    },
    {
      "epoch": 1.1953122600067583,
      "grad_norm": 0.36781004071235657,
      "learning_rate": 6.998947230849362e-06,
      "loss": 0.5023,
      "step": 38911
    },
    {
      "epoch": 1.1953429791417074,
      "grad_norm": 0.37203460931777954,
      "learning_rate": 6.998486233161147e-06,
      "loss": 0.4461,
      "step": 38912
    },
    {
      "epoch": 1.1953736982766565,
      "grad_norm": 0.5212629437446594,
      "learning_rate": 6.998025242483184e-06,
      "loss": 0.4533,
      "step": 38913
    },
    {
      "epoch": 1.1954044174116056,
      "grad_norm": 0.37282267212867737,
      "learning_rate": 6.997564258816536e-06,
      "loss": 0.4693,
      "step": 38914
    },
    {
      "epoch": 1.1954351365465548,
      "grad_norm": 0.387431800365448,
      "learning_rate": 6.997103282162292e-06,
      "loss": 0.5109,
      "step": 38915
    },
    {
      "epoch": 1.195465855681504,
      "grad_norm": 0.4479350447654724,
      "learning_rate": 6.99664231252152e-06,
      "loss": 0.5156,
      "step": 38916
    },
    {
      "epoch": 1.1954965748164532,
      "grad_norm": 0.38102829456329346,
      "learning_rate": 6.996181349895301e-06,
      "loss": 0.4491,
      "step": 38917
    },
    {
      "epoch": 1.1955272939514023,
      "grad_norm": 0.4268677830696106,
      "learning_rate": 6.995720394284709e-06,
      "loss": 0.5193,
      "step": 38918
    },
    {
      "epoch": 1.1955580130863515,
      "grad_norm": 0.39478209614753723,
      "learning_rate": 6.995259445690819e-06,
      "loss": 0.4522,
      "step": 38919
    },
    {
      "epoch": 1.1955887322213006,
      "grad_norm": 0.45982545614242554,
      "learning_rate": 6.994798504114716e-06,
      "loss": 0.5343,
      "step": 38920
    },
    {
      "epoch": 1.19561945135625,
      "grad_norm": 0.412210077047348,
      "learning_rate": 6.9943375695574674e-06,
      "loss": 0.5886,
      "step": 38921
    },
    {
      "epoch": 1.195650170491199,
      "grad_norm": 0.38754868507385254,
      "learning_rate": 6.993876642020155e-06,
      "loss": 0.4401,
      "step": 38922
    },
    {
      "epoch": 1.1956808896261482,
      "grad_norm": 0.42139485478401184,
      "learning_rate": 6.993415721503852e-06,
      "loss": 0.4515,
      "step": 38923
    },
    {
      "epoch": 1.1957116087610973,
      "grad_norm": 0.3898217976093292,
      "learning_rate": 6.99295480800964e-06,
      "loss": 0.5146,
      "step": 38924
    },
    {
      "epoch": 1.1957423278960464,
      "grad_norm": 0.4113191068172455,
      "learning_rate": 6.992493901538589e-06,
      "loss": 0.4873,
      "step": 38925
    },
    {
      "epoch": 1.1957730470309955,
      "grad_norm": 0.40454158186912537,
      "learning_rate": 6.99203300209178e-06,
      "loss": 0.4872,
      "step": 38926
    },
    {
      "epoch": 1.1958037661659449,
      "grad_norm": 0.38743749260902405,
      "learning_rate": 6.991572109670286e-06,
      "loss": 0.4539,
      "step": 38927
    },
    {
      "epoch": 1.195834485300894,
      "grad_norm": 0.434688001871109,
      "learning_rate": 6.9911112242751865e-06,
      "loss": 0.5303,
      "step": 38928
    },
    {
      "epoch": 1.195865204435843,
      "grad_norm": 0.40342527627944946,
      "learning_rate": 6.990650345907557e-06,
      "loss": 0.4841,
      "step": 38929
    },
    {
      "epoch": 1.1958959235707922,
      "grad_norm": 0.39068490266799927,
      "learning_rate": 6.990189474568474e-06,
      "loss": 0.5243,
      "step": 38930
    },
    {
      "epoch": 1.1959266427057413,
      "grad_norm": 0.43545544147491455,
      "learning_rate": 6.989728610259014e-06,
      "loss": 0.4636,
      "step": 38931
    },
    {
      "epoch": 1.1959573618406907,
      "grad_norm": 0.3791142404079437,
      "learning_rate": 6.9892677529802535e-06,
      "loss": 0.5064,
      "step": 38932
    },
    {
      "epoch": 1.1959880809756398,
      "grad_norm": 0.4209554195404053,
      "learning_rate": 6.988806902733266e-06,
      "loss": 0.4787,
      "step": 38933
    },
    {
      "epoch": 1.196018800110589,
      "grad_norm": 0.41788384318351746,
      "learning_rate": 6.988346059519133e-06,
      "loss": 0.5718,
      "step": 38934
    },
    {
      "epoch": 1.196049519245538,
      "grad_norm": 0.42493119835853577,
      "learning_rate": 6.987885223338926e-06,
      "loss": 0.4704,
      "step": 38935
    },
    {
      "epoch": 1.1960802383804872,
      "grad_norm": 0.4139884412288666,
      "learning_rate": 6.9874243941937245e-06,
      "loss": 0.5575,
      "step": 38936
    },
    {
      "epoch": 1.1961109575154363,
      "grad_norm": 0.44564002752304077,
      "learning_rate": 6.986963572084603e-06,
      "loss": 0.4859,
      "step": 38937
    },
    {
      "epoch": 1.1961416766503856,
      "grad_norm": 0.4210149049758911,
      "learning_rate": 6.986502757012639e-06,
      "loss": 0.5237,
      "step": 38938
    },
    {
      "epoch": 1.1961723957853347,
      "grad_norm": 0.3728465735912323,
      "learning_rate": 6.986041948978909e-06,
      "loss": 0.515,
      "step": 38939
    },
    {
      "epoch": 1.1962031149202839,
      "grad_norm": 0.37108707427978516,
      "learning_rate": 6.985581147984486e-06,
      "loss": 0.3921,
      "step": 38940
    },
    {
      "epoch": 1.196233834055233,
      "grad_norm": 0.37417733669281006,
      "learning_rate": 6.985120354030453e-06,
      "loss": 0.4725,
      "step": 38941
    },
    {
      "epoch": 1.196264553190182,
      "grad_norm": 0.3844296634197235,
      "learning_rate": 6.984659567117877e-06,
      "loss": 0.4551,
      "step": 38942
    },
    {
      "epoch": 1.1962952723251314,
      "grad_norm": 0.4488532245159149,
      "learning_rate": 6.984198787247846e-06,
      "loss": 0.4324,
      "step": 38943
    },
    {
      "epoch": 1.1963259914600806,
      "grad_norm": 0.43305137753486633,
      "learning_rate": 6.9837380144214215e-06,
      "loss": 0.4892,
      "step": 38944
    },
    {
      "epoch": 1.1963567105950297,
      "grad_norm": 0.36973288655281067,
      "learning_rate": 6.983277248639695e-06,
      "loss": 0.4915,
      "step": 38945
    },
    {
      "epoch": 1.1963874297299788,
      "grad_norm": 0.3922840654850006,
      "learning_rate": 6.982816489903728e-06,
      "loss": 0.5303,
      "step": 38946
    },
    {
      "epoch": 1.196418148864928,
      "grad_norm": 0.3987000584602356,
      "learning_rate": 6.98235573821461e-06,
      "loss": 0.5082,
      "step": 38947
    },
    {
      "epoch": 1.196448867999877,
      "grad_norm": 0.36748212575912476,
      "learning_rate": 6.981894993573405e-06,
      "loss": 0.5058,
      "step": 38948
    },
    {
      "epoch": 1.1964795871348262,
      "grad_norm": 0.387521892786026,
      "learning_rate": 6.981434255981201e-06,
      "loss": 0.4533,
      "step": 38949
    },
    {
      "epoch": 1.1965103062697755,
      "grad_norm": 0.40732306241989136,
      "learning_rate": 6.980973525439064e-06,
      "loss": 0.4836,
      "step": 38950
    },
    {
      "epoch": 1.1965410254047246,
      "grad_norm": 0.3903404176235199,
      "learning_rate": 6.980512801948076e-06,
      "loss": 0.4841,
      "step": 38951
    },
    {
      "epoch": 1.1965717445396737,
      "grad_norm": 0.38582658767700195,
      "learning_rate": 6.98005208550931e-06,
      "loss": 0.496,
      "step": 38952
    },
    {
      "epoch": 1.1966024636746229,
      "grad_norm": 0.4037163257598877,
      "learning_rate": 6.979591376123844e-06,
      "loss": 0.5028,
      "step": 38953
    },
    {
      "epoch": 1.1966331828095722,
      "grad_norm": 0.4870733916759491,
      "learning_rate": 6.979130673792753e-06,
      "loss": 0.4861,
      "step": 38954
    },
    {
      "epoch": 1.1966639019445213,
      "grad_norm": 0.44994062185287476,
      "learning_rate": 6.978669978517109e-06,
      "loss": 0.491,
      "step": 38955
    },
    {
      "epoch": 1.1966946210794704,
      "grad_norm": 0.3832978308200836,
      "learning_rate": 6.978209290298001e-06,
      "loss": 0.5382,
      "step": 38956
    },
    {
      "epoch": 1.1967253402144196,
      "grad_norm": 0.40180420875549316,
      "learning_rate": 6.977748609136491e-06,
      "loss": 0.3614,
      "step": 38957
    },
    {
      "epoch": 1.1967560593493687,
      "grad_norm": 0.44962263107299805,
      "learning_rate": 6.977287935033663e-06,
      "loss": 0.5333,
      "step": 38958
    },
    {
      "epoch": 1.1967867784843178,
      "grad_norm": 0.42820578813552856,
      "learning_rate": 6.976827267990587e-06,
      "loss": 0.4726,
      "step": 38959
    },
    {
      "epoch": 1.196817497619267,
      "grad_norm": 0.4005942940711975,
      "learning_rate": 6.976366608008345e-06,
      "loss": 0.4666,
      "step": 38960
    },
    {
      "epoch": 1.1968482167542163,
      "grad_norm": 0.39184731245040894,
      "learning_rate": 6.975905955088006e-06,
      "loss": 0.4745,
      "step": 38961
    },
    {
      "epoch": 1.1968789358891654,
      "grad_norm": 0.4277098476886749,
      "learning_rate": 6.975445309230653e-06,
      "loss": 0.4497,
      "step": 38962
    },
    {
      "epoch": 1.1969096550241145,
      "grad_norm": 0.40393227338790894,
      "learning_rate": 6.974984670437357e-06,
      "loss": 0.4998,
      "step": 38963
    },
    {
      "epoch": 1.1969403741590636,
      "grad_norm": 0.3853152394294739,
      "learning_rate": 6.974524038709199e-06,
      "loss": 0.5346,
      "step": 38964
    },
    {
      "epoch": 1.1969710932940127,
      "grad_norm": 0.4126640260219574,
      "learning_rate": 6.974063414047246e-06,
      "loss": 0.459,
      "step": 38965
    },
    {
      "epoch": 1.197001812428962,
      "grad_norm": 0.40818652510643005,
      "learning_rate": 6.973602796452583e-06,
      "loss": 0.5225,
      "step": 38966
    },
    {
      "epoch": 1.1970325315639112,
      "grad_norm": 0.45485931634902954,
      "learning_rate": 6.973142185926281e-06,
      "loss": 0.57,
      "step": 38967
    },
    {
      "epoch": 1.1970632506988603,
      "grad_norm": 0.3608264923095703,
      "learning_rate": 6.972681582469417e-06,
      "loss": 0.4661,
      "step": 38968
    },
    {
      "epoch": 1.1970939698338094,
      "grad_norm": 0.43717750906944275,
      "learning_rate": 6.972220986083066e-06,
      "loss": 0.5183,
      "step": 38969
    },
    {
      "epoch": 1.1971246889687586,
      "grad_norm": 0.39507338404655457,
      "learning_rate": 6.971760396768305e-06,
      "loss": 0.4581,
      "step": 38970
    },
    {
      "epoch": 1.1971554081037077,
      "grad_norm": 0.3913661241531372,
      "learning_rate": 6.971299814526209e-06,
      "loss": 0.5113,
      "step": 38971
    },
    {
      "epoch": 1.197186127238657,
      "grad_norm": 0.40888288617134094,
      "learning_rate": 6.970839239357856e-06,
      "loss": 0.4417,
      "step": 38972
    },
    {
      "epoch": 1.1972168463736061,
      "grad_norm": 0.4227715730667114,
      "learning_rate": 6.970378671264315e-06,
      "loss": 0.4771,
      "step": 38973
    },
    {
      "epoch": 1.1972475655085553,
      "grad_norm": 0.40379762649536133,
      "learning_rate": 6.969918110246668e-06,
      "loss": 0.6725,
      "step": 38974
    },
    {
      "epoch": 1.1972782846435044,
      "grad_norm": 0.44422680139541626,
      "learning_rate": 6.9694575563059895e-06,
      "loss": 0.4699,
      "step": 38975
    },
    {
      "epoch": 1.1973090037784535,
      "grad_norm": 0.4228273034095764,
      "learning_rate": 6.9689970094433525e-06,
      "loss": 0.5033,
      "step": 38976
    },
    {
      "epoch": 1.1973397229134028,
      "grad_norm": 0.3837312161922455,
      "learning_rate": 6.968536469659838e-06,
      "loss": 0.4765,
      "step": 38977
    },
    {
      "epoch": 1.197370442048352,
      "grad_norm": 0.38377639651298523,
      "learning_rate": 6.9680759369565155e-06,
      "loss": 0.4369,
      "step": 38978
    },
    {
      "epoch": 1.197401161183301,
      "grad_norm": 0.3919091522693634,
      "learning_rate": 6.967615411334467e-06,
      "loss": 0.5151,
      "step": 38979
    },
    {
      "epoch": 1.1974318803182502,
      "grad_norm": 0.40252548456192017,
      "learning_rate": 6.967154892794761e-06,
      "loss": 0.5069,
      "step": 38980
    },
    {
      "epoch": 1.1974625994531993,
      "grad_norm": 0.4257739186286926,
      "learning_rate": 6.966694381338479e-06,
      "loss": 0.5293,
      "step": 38981
    },
    {
      "epoch": 1.1974933185881484,
      "grad_norm": 0.3981654644012451,
      "learning_rate": 6.966233876966691e-06,
      "loss": 0.4267,
      "step": 38982
    },
    {
      "epoch": 1.1975240377230978,
      "grad_norm": 0.3734370470046997,
      "learning_rate": 6.96577337968048e-06,
      "loss": 0.422,
      "step": 38983
    },
    {
      "epoch": 1.197554756858047,
      "grad_norm": 0.41617846488952637,
      "learning_rate": 6.965312889480913e-06,
      "loss": 0.4701,
      "step": 38984
    },
    {
      "epoch": 1.197585475992996,
      "grad_norm": 0.45202142000198364,
      "learning_rate": 6.964852406369074e-06,
      "loss": 0.5209,
      "step": 38985
    },
    {
      "epoch": 1.1976161951279451,
      "grad_norm": 0.41322481632232666,
      "learning_rate": 6.96439193034603e-06,
      "loss": 0.4873,
      "step": 38986
    },
    {
      "epoch": 1.1976469142628943,
      "grad_norm": 0.3530791401863098,
      "learning_rate": 6.9639314614128625e-06,
      "loss": 0.5268,
      "step": 38987
    },
    {
      "epoch": 1.1976776333978436,
      "grad_norm": 0.37734800577163696,
      "learning_rate": 6.963470999570644e-06,
      "loss": 0.5177,
      "step": 38988
    },
    {
      "epoch": 1.1977083525327927,
      "grad_norm": 0.387704998254776,
      "learning_rate": 6.963010544820453e-06,
      "loss": 0.4928,
      "step": 38989
    },
    {
      "epoch": 1.1977390716677419,
      "grad_norm": 0.38603273034095764,
      "learning_rate": 6.962550097163361e-06,
      "loss": 0.4694,
      "step": 38990
    },
    {
      "epoch": 1.197769790802691,
      "grad_norm": 0.38785243034362793,
      "learning_rate": 6.962089656600447e-06,
      "loss": 0.4743,
      "step": 38991
    },
    {
      "epoch": 1.19780050993764,
      "grad_norm": 0.4096830189228058,
      "learning_rate": 6.961629223132783e-06,
      "loss": 0.5149,
      "step": 38992
    },
    {
      "epoch": 1.1978312290725892,
      "grad_norm": 0.40872299671173096,
      "learning_rate": 6.9611687967614465e-06,
      "loss": 0.5289,
      "step": 38993
    },
    {
      "epoch": 1.1978619482075386,
      "grad_norm": 0.3878936171531677,
      "learning_rate": 6.9607083774875135e-06,
      "loss": 0.4092,
      "step": 38994
    },
    {
      "epoch": 1.1978926673424877,
      "grad_norm": 0.3676561713218689,
      "learning_rate": 6.960247965312057e-06,
      "loss": 0.533,
      "step": 38995
    },
    {
      "epoch": 1.1979233864774368,
      "grad_norm": 0.41609370708465576,
      "learning_rate": 6.959787560236155e-06,
      "loss": 0.4773,
      "step": 38996
    },
    {
      "epoch": 1.197954105612386,
      "grad_norm": 0.394552081823349,
      "learning_rate": 6.959327162260881e-06,
      "loss": 0.4681,
      "step": 38997
    },
    {
      "epoch": 1.197984824747335,
      "grad_norm": 0.3787112236022949,
      "learning_rate": 6.958866771387311e-06,
      "loss": 0.4392,
      "step": 38998
    },
    {
      "epoch": 1.1980155438822844,
      "grad_norm": 0.3966192305088043,
      "learning_rate": 6.958406387616519e-06,
      "loss": 0.4032,
      "step": 38999
    },
    {
      "epoch": 1.1980462630172335,
      "grad_norm": 0.45777058601379395,
      "learning_rate": 6.957946010949583e-06,
      "loss": 0.493,
      "step": 39000
    },
    {
      "epoch": 1.1980769821521826,
      "grad_norm": 0.39561930298805237,
      "learning_rate": 6.957485641387576e-06,
      "loss": 0.4627,
      "step": 39001
    },
    {
      "epoch": 1.1981077012871317,
      "grad_norm": 0.4381209909915924,
      "learning_rate": 6.957025278931575e-06,
      "loss": 0.5008,
      "step": 39002
    },
    {
      "epoch": 1.1981384204220809,
      "grad_norm": 0.4866999089717865,
      "learning_rate": 6.9565649235826515e-06,
      "loss": 0.4989,
      "step": 39003
    },
    {
      "epoch": 1.19816913955703,
      "grad_norm": 0.3924867808818817,
      "learning_rate": 6.956104575341884e-06,
      "loss": 0.4719,
      "step": 39004
    },
    {
      "epoch": 1.1981998586919793,
      "grad_norm": 0.4314519762992859,
      "learning_rate": 6.9556442342103455e-06,
      "loss": 0.5125,
      "step": 39005
    },
    {
      "epoch": 1.1982305778269284,
      "grad_norm": 0.37947332859039307,
      "learning_rate": 6.9551839001891174e-06,
      "loss": 0.4201,
      "step": 39006
    },
    {
      "epoch": 1.1982612969618776,
      "grad_norm": 0.4161510467529297,
      "learning_rate": 6.9547235732792654e-06,
      "loss": 0.5411,
      "step": 39007
    },
    {
      "epoch": 1.1982920160968267,
      "grad_norm": 0.4202074408531189,
      "learning_rate": 6.954263253481872e-06,
      "loss": 0.506,
      "step": 39008
    },
    {
      "epoch": 1.1983227352317758,
      "grad_norm": 0.45497971773147583,
      "learning_rate": 6.9538029407980045e-06,
      "loss": 0.4773,
      "step": 39009
    },
    {
      "epoch": 1.1983534543667251,
      "grad_norm": 0.3785220682621002,
      "learning_rate": 6.953342635228746e-06,
      "loss": 0.4586,
      "step": 39010
    },
    {
      "epoch": 1.1983841735016743,
      "grad_norm": 0.37750133872032166,
      "learning_rate": 6.95288233677517e-06,
      "loss": 0.503,
      "step": 39011
    },
    {
      "epoch": 1.1984148926366234,
      "grad_norm": 0.3972863554954529,
      "learning_rate": 6.952422045438347e-06,
      "loss": 0.495,
      "step": 39012
    },
    {
      "epoch": 1.1984456117715725,
      "grad_norm": 0.37869641184806824,
      "learning_rate": 6.951961761219361e-06,
      "loss": 0.5125,
      "step": 39013
    },
    {
      "epoch": 1.1984763309065216,
      "grad_norm": 0.3859618306159973,
      "learning_rate": 6.951501484119274e-06,
      "loss": 0.4994,
      "step": 39014
    },
    {
      "epoch": 1.1985070500414707,
      "grad_norm": 0.5024675130844116,
      "learning_rate": 6.951041214139175e-06,
      "loss": 0.4297,
      "step": 39015
    },
    {
      "epoch": 1.19853776917642,
      "grad_norm": 0.4050949215888977,
      "learning_rate": 6.950580951280126e-06,
      "loss": 0.4957,
      "step": 39016
    },
    {
      "epoch": 1.1985684883113692,
      "grad_norm": 0.3888651430606842,
      "learning_rate": 6.950120695543214e-06,
      "loss": 0.4585,
      "step": 39017
    },
    {
      "epoch": 1.1985992074463183,
      "grad_norm": 0.49534106254577637,
      "learning_rate": 6.949660446929501e-06,
      "loss": 0.5123,
      "step": 39018
    },
    {
      "epoch": 1.1986299265812674,
      "grad_norm": 0.39137277007102966,
      "learning_rate": 6.949200205440076e-06,
      "loss": 0.5393,
      "step": 39019
    },
    {
      "epoch": 1.1986606457162166,
      "grad_norm": 0.4101957678794861,
      "learning_rate": 6.948739971076004e-06,
      "loss": 0.4639,
      "step": 39020
    },
    {
      "epoch": 1.198691364851166,
      "grad_norm": 0.43820828199386597,
      "learning_rate": 6.948279743838364e-06,
      "loss": 0.4223,
      "step": 39021
    },
    {
      "epoch": 1.198722083986115,
      "grad_norm": 0.38338539004325867,
      "learning_rate": 6.947819523728228e-06,
      "loss": 0.5341,
      "step": 39022
    },
    {
      "epoch": 1.1987528031210641,
      "grad_norm": 0.3788881003856659,
      "learning_rate": 6.947359310746673e-06,
      "loss": 0.4534,
      "step": 39023
    },
    {
      "epoch": 1.1987835222560133,
      "grad_norm": 0.3360898196697235,
      "learning_rate": 6.946899104894773e-06,
      "loss": 0.4248,
      "step": 39024
    },
    {
      "epoch": 1.1988142413909624,
      "grad_norm": 0.37808385491371155,
      "learning_rate": 6.946438906173606e-06,
      "loss": 0.4526,
      "step": 39025
    },
    {
      "epoch": 1.1988449605259115,
      "grad_norm": 0.3577388823032379,
      "learning_rate": 6.945978714584241e-06,
      "loss": 0.4837,
      "step": 39026
    },
    {
      "epoch": 1.1988756796608608,
      "grad_norm": 0.3840714693069458,
      "learning_rate": 6.94551853012776e-06,
      "loss": 0.4221,
      "step": 39027
    },
    {
      "epoch": 1.19890639879581,
      "grad_norm": 0.3783164322376251,
      "learning_rate": 6.94505835280523e-06,
      "loss": 0.3874,
      "step": 39028
    },
    {
      "epoch": 1.198937117930759,
      "grad_norm": 0.45710113644599915,
      "learning_rate": 6.9445981826177275e-06,
      "loss": 0.4694,
      "step": 39029
    },
    {
      "epoch": 1.1989678370657082,
      "grad_norm": 0.4012098014354706,
      "learning_rate": 6.944138019566336e-06,
      "loss": 0.4916,
      "step": 39030
    },
    {
      "epoch": 1.1989985562006573,
      "grad_norm": 0.43023210763931274,
      "learning_rate": 6.943677863652119e-06,
      "loss": 0.4462,
      "step": 39031
    },
    {
      "epoch": 1.1990292753356067,
      "grad_norm": 0.4058217704296112,
      "learning_rate": 6.943217714876157e-06,
      "loss": 0.4621,
      "step": 39032
    },
    {
      "epoch": 1.1990599944705558,
      "grad_norm": 0.36768683791160583,
      "learning_rate": 6.942757573239522e-06,
      "loss": 0.5165,
      "step": 39033
    },
    {
      "epoch": 1.199090713605505,
      "grad_norm": 0.36374348402023315,
      "learning_rate": 6.942297438743293e-06,
      "loss": 0.4331,
      "step": 39034
    },
    {
      "epoch": 1.199121432740454,
      "grad_norm": 0.40769824385643005,
      "learning_rate": 6.94183731138854e-06,
      "loss": 0.493,
      "step": 39035
    },
    {
      "epoch": 1.1991521518754031,
      "grad_norm": 0.39279815554618835,
      "learning_rate": 6.941377191176341e-06,
      "loss": 0.4737,
      "step": 39036
    },
    {
      "epoch": 1.1991828710103523,
      "grad_norm": 0.42285752296447754,
      "learning_rate": 6.940917078107767e-06,
      "loss": 0.4695,
      "step": 39037
    },
    {
      "epoch": 1.1992135901453016,
      "grad_norm": 0.38093629479408264,
      "learning_rate": 6.940456972183898e-06,
      "loss": 0.502,
      "step": 39038
    },
    {
      "epoch": 1.1992443092802507,
      "grad_norm": 0.3794403374195099,
      "learning_rate": 6.939996873405802e-06,
      "loss": 0.4473,
      "step": 39039
    },
    {
      "epoch": 1.1992750284151998,
      "grad_norm": 0.42644280195236206,
      "learning_rate": 6.93953678177456e-06,
      "loss": 0.4149,
      "step": 39040
    },
    {
      "epoch": 1.199305747550149,
      "grad_norm": 0.566203773021698,
      "learning_rate": 6.93907669729124e-06,
      "loss": 0.6138,
      "step": 39041
    },
    {
      "epoch": 1.199336466685098,
      "grad_norm": 0.39503830671310425,
      "learning_rate": 6.938616619956926e-06,
      "loss": 0.4691,
      "step": 39042
    },
    {
      "epoch": 1.1993671858200474,
      "grad_norm": 0.39543309807777405,
      "learning_rate": 6.93815654977268e-06,
      "loss": 0.5751,
      "step": 39043
    },
    {
      "epoch": 1.1993979049549965,
      "grad_norm": 0.447044312953949,
      "learning_rate": 6.937696486739589e-06,
      "loss": 0.4003,
      "step": 39044
    },
    {
      "epoch": 1.1994286240899457,
      "grad_norm": 0.38898855447769165,
      "learning_rate": 6.937236430858716e-06,
      "loss": 0.4728,
      "step": 39045
    },
    {
      "epoch": 1.1994593432248948,
      "grad_norm": 0.43426042795181274,
      "learning_rate": 6.936776382131147e-06,
      "loss": 0.4978,
      "step": 39046
    },
    {
      "epoch": 1.199490062359844,
      "grad_norm": 0.385623961687088,
      "learning_rate": 6.936316340557947e-06,
      "loss": 0.4638,
      "step": 39047
    },
    {
      "epoch": 1.199520781494793,
      "grad_norm": 0.40420714020729065,
      "learning_rate": 6.935856306140192e-06,
      "loss": 0.5418,
      "step": 39048
    },
    {
      "epoch": 1.1995515006297424,
      "grad_norm": 0.40917783975601196,
      "learning_rate": 6.935396278878965e-06,
      "loss": 0.4984,
      "step": 39049
    },
    {
      "epoch": 1.1995822197646915,
      "grad_norm": 0.40705451369285583,
      "learning_rate": 6.934936258775328e-06,
      "loss": 0.4924,
      "step": 39050
    },
    {
      "epoch": 1.1996129388996406,
      "grad_norm": 0.4418829679489136,
      "learning_rate": 6.934476245830366e-06,
      "loss": 0.4782,
      "step": 39051
    },
    {
      "epoch": 1.1996436580345897,
      "grad_norm": 0.416400671005249,
      "learning_rate": 6.934016240045145e-06,
      "loss": 0.5032,
      "step": 39052
    },
    {
      "epoch": 1.1996743771695388,
      "grad_norm": 0.35875633358955383,
      "learning_rate": 6.933556241420747e-06,
      "loss": 0.4558,
      "step": 39053
    },
    {
      "epoch": 1.1997050963044882,
      "grad_norm": 0.42698830366134644,
      "learning_rate": 6.93309624995824e-06,
      "loss": 0.5365,
      "step": 39054
    },
    {
      "epoch": 1.1997358154394373,
      "grad_norm": 0.4315250813961029,
      "learning_rate": 6.932636265658703e-06,
      "loss": 0.5506,
      "step": 39055
    },
    {
      "epoch": 1.1997665345743864,
      "grad_norm": 0.3588654100894928,
      "learning_rate": 6.9321762885232045e-06,
      "loss": 0.4726,
      "step": 39056
    },
    {
      "epoch": 1.1997972537093355,
      "grad_norm": 0.37706390023231506,
      "learning_rate": 6.931716318552827e-06,
      "loss": 0.5303,
      "step": 39057
    },
    {
      "epoch": 1.1998279728442847,
      "grad_norm": 0.36112484335899353,
      "learning_rate": 6.931256355748637e-06,
      "loss": 0.4335,
      "step": 39058
    },
    {
      "epoch": 1.1998586919792338,
      "grad_norm": 0.3681485056877136,
      "learning_rate": 6.930796400111715e-06,
      "loss": 0.4056,
      "step": 39059
    },
    {
      "epoch": 1.199889411114183,
      "grad_norm": 0.3934994339942932,
      "learning_rate": 6.930336451643129e-06,
      "loss": 0.4654,
      "step": 39060
    },
    {
      "epoch": 1.1999201302491322,
      "grad_norm": 0.3580789864063263,
      "learning_rate": 6.929876510343958e-06,
      "loss": 0.4282,
      "step": 39061
    },
    {
      "epoch": 1.1999508493840814,
      "grad_norm": 0.4453315734863281,
      "learning_rate": 6.929416576215275e-06,
      "loss": 0.5854,
      "step": 39062
    },
    {
      "epoch": 1.1999815685190305,
      "grad_norm": 0.34682610630989075,
      "learning_rate": 6.928956649258154e-06,
      "loss": 0.4678,
      "step": 39063
    },
    {
      "epoch": 1.2000122876539796,
      "grad_norm": 0.404751181602478,
      "learning_rate": 6.9284967294736686e-06,
      "loss": 0.4874,
      "step": 39064
    },
    {
      "epoch": 1.200043006788929,
      "grad_norm": 0.42830294370651245,
      "learning_rate": 6.928036816862893e-06,
      "loss": 0.5378,
      "step": 39065
    },
    {
      "epoch": 1.200073725923878,
      "grad_norm": 0.3854021430015564,
      "learning_rate": 6.927576911426906e-06,
      "loss": 0.5226,
      "step": 39066
    },
    {
      "epoch": 1.2001044450588272,
      "grad_norm": 0.38169556856155396,
      "learning_rate": 6.927117013166773e-06,
      "loss": 0.4519,
      "step": 39067
    },
    {
      "epoch": 1.2001351641937763,
      "grad_norm": 0.4252074360847473,
      "learning_rate": 6.926657122083575e-06,
      "loss": 0.5553,
      "step": 39068
    },
    {
      "epoch": 1.2001658833287254,
      "grad_norm": 0.38513901829719543,
      "learning_rate": 6.926197238178383e-06,
      "loss": 0.5301,
      "step": 39069
    },
    {
      "epoch": 1.2001966024636745,
      "grad_norm": 0.34861329197883606,
      "learning_rate": 6.925737361452274e-06,
      "loss": 0.4425,
      "step": 39070
    },
    {
      "epoch": 1.2002273215986237,
      "grad_norm": 0.4386860728263855,
      "learning_rate": 6.925277491906317e-06,
      "loss": 0.5513,
      "step": 39071
    },
    {
      "epoch": 1.200258040733573,
      "grad_norm": 0.38491904735565186,
      "learning_rate": 6.9248176295415925e-06,
      "loss": 0.4587,
      "step": 39072
    },
    {
      "epoch": 1.2002887598685221,
      "grad_norm": 0.40426820516586304,
      "learning_rate": 6.924357774359169e-06,
      "loss": 0.5105,
      "step": 39073
    },
    {
      "epoch": 1.2003194790034712,
      "grad_norm": 0.5843591690063477,
      "learning_rate": 6.923897926360124e-06,
      "loss": 0.5286,
      "step": 39074
    },
    {
      "epoch": 1.2003501981384204,
      "grad_norm": 0.41254922747612,
      "learning_rate": 6.923438085545529e-06,
      "loss": 0.4923,
      "step": 39075
    },
    {
      "epoch": 1.2003809172733695,
      "grad_norm": 0.3971681296825409,
      "learning_rate": 6.922978251916462e-06,
      "loss": 0.5138,
      "step": 39076
    },
    {
      "epoch": 1.2004116364083188,
      "grad_norm": 0.4050145447254181,
      "learning_rate": 6.92251842547399e-06,
      "loss": 0.5032,
      "step": 39077
    },
    {
      "epoch": 1.200442355543268,
      "grad_norm": 0.4425250291824341,
      "learning_rate": 6.922058606219195e-06,
      "loss": 0.5365,
      "step": 39078
    },
    {
      "epoch": 1.200473074678217,
      "grad_norm": 0.39535683393478394,
      "learning_rate": 6.921598794153142e-06,
      "loss": 0.5648,
      "step": 39079
    },
    {
      "epoch": 1.2005037938131662,
      "grad_norm": 0.3931134045124054,
      "learning_rate": 6.921138989276917e-06,
      "loss": 0.4705,
      "step": 39080
    },
    {
      "epoch": 1.2005345129481153,
      "grad_norm": 0.5533664226531982,
      "learning_rate": 6.92067919159158e-06,
      "loss": 0.4391,
      "step": 39081
    },
    {
      "epoch": 1.2005652320830644,
      "grad_norm": 0.4137369394302368,
      "learning_rate": 6.920219401098218e-06,
      "loss": 0.4999,
      "step": 39082
    },
    {
      "epoch": 1.2005959512180138,
      "grad_norm": 0.416766881942749,
      "learning_rate": 6.919759617797895e-06,
      "loss": 0.5125,
      "step": 39083
    },
    {
      "epoch": 1.2006266703529629,
      "grad_norm": 0.40527695417404175,
      "learning_rate": 6.919299841691684e-06,
      "loss": 0.4971,
      "step": 39084
    },
    {
      "epoch": 1.200657389487912,
      "grad_norm": 0.4142168164253235,
      "learning_rate": 6.918840072780672e-06,
      "loss": 0.5095,
      "step": 39085
    },
    {
      "epoch": 1.2006881086228611,
      "grad_norm": 0.4071113169193268,
      "learning_rate": 6.918380311065919e-06,
      "loss": 0.512,
      "step": 39086
    },
    {
      "epoch": 1.2007188277578102,
      "grad_norm": 0.4083026349544525,
      "learning_rate": 6.917920556548509e-06,
      "loss": 0.5326,
      "step": 39087
    },
    {
      "epoch": 1.2007495468927596,
      "grad_norm": 0.4559582471847534,
      "learning_rate": 6.917460809229506e-06,
      "loss": 0.4502,
      "step": 39088
    },
    {
      "epoch": 1.2007802660277087,
      "grad_norm": 1.1160314083099365,
      "learning_rate": 6.917001069109991e-06,
      "loss": 0.499,
      "step": 39089
    },
    {
      "epoch": 1.2008109851626578,
      "grad_norm": 0.3955957591533661,
      "learning_rate": 6.916541336191034e-06,
      "loss": 0.4571,
      "step": 39090
    },
    {
      "epoch": 1.200841704297607,
      "grad_norm": 0.41220787167549133,
      "learning_rate": 6.9160816104737105e-06,
      "loss": 0.5347,
      "step": 39091
    },
    {
      "epoch": 1.200872423432556,
      "grad_norm": 0.3954203426837921,
      "learning_rate": 6.915621891959092e-06,
      "loss": 0.43,
      "step": 39092
    },
    {
      "epoch": 1.2009031425675052,
      "grad_norm": 0.3750710189342499,
      "learning_rate": 6.915162180648258e-06,
      "loss": 0.479,
      "step": 39093
    },
    {
      "epoch": 1.2009338617024545,
      "grad_norm": 0.4125686585903168,
      "learning_rate": 6.914702476542274e-06,
      "loss": 0.5204,
      "step": 39094
    },
    {
      "epoch": 1.2009645808374037,
      "grad_norm": 0.3839930295944214,
      "learning_rate": 6.914242779642222e-06,
      "loss": 0.4545,
      "step": 39095
    },
    {
      "epoch": 1.2009952999723528,
      "grad_norm": 0.39940279722213745,
      "learning_rate": 6.913783089949168e-06,
      "loss": 0.535,
      "step": 39096
    },
    {
      "epoch": 1.201026019107302,
      "grad_norm": 0.4107985496520996,
      "learning_rate": 6.913323407464191e-06,
      "loss": 0.4261,
      "step": 39097
    },
    {
      "epoch": 1.201056738242251,
      "grad_norm": 0.40537169575691223,
      "learning_rate": 6.91286373218836e-06,
      "loss": 0.5095,
      "step": 39098
    },
    {
      "epoch": 1.2010874573772004,
      "grad_norm": 0.49959343671798706,
      "learning_rate": 6.912404064122755e-06,
      "loss": 0.5247,
      "step": 39099
    },
    {
      "epoch": 1.2011181765121495,
      "grad_norm": 0.4365657567977905,
      "learning_rate": 6.9119444032684435e-06,
      "loss": 0.5227,
      "step": 39100
    },
    {
      "epoch": 1.2011488956470986,
      "grad_norm": 0.4044029116630554,
      "learning_rate": 6.9114847496265014e-06,
      "loss": 0.4812,
      "step": 39101
    },
    {
      "epoch": 1.2011796147820477,
      "grad_norm": 0.4290449917316437,
      "learning_rate": 6.911025103198005e-06,
      "loss": 0.5155,
      "step": 39102
    },
    {
      "epoch": 1.2012103339169968,
      "grad_norm": 0.4128534495830536,
      "learning_rate": 6.910565463984023e-06,
      "loss": 0.503,
      "step": 39103
    },
    {
      "epoch": 1.201241053051946,
      "grad_norm": 0.39068764448165894,
      "learning_rate": 6.910105831985632e-06,
      "loss": 0.4968,
      "step": 39104
    },
    {
      "epoch": 1.2012717721868953,
      "grad_norm": 0.4082544147968292,
      "learning_rate": 6.909646207203903e-06,
      "loss": 0.4691,
      "step": 39105
    },
    {
      "epoch": 1.2013024913218444,
      "grad_norm": 0.4196286201477051,
      "learning_rate": 6.909186589639913e-06,
      "loss": 0.5149,
      "step": 39106
    },
    {
      "epoch": 1.2013332104567935,
      "grad_norm": 0.3934844136238098,
      "learning_rate": 6.908726979294733e-06,
      "loss": 0.4266,
      "step": 39107
    },
    {
      "epoch": 1.2013639295917427,
      "grad_norm": 0.47909659147262573,
      "learning_rate": 6.908267376169438e-06,
      "loss": 0.465,
      "step": 39108
    },
    {
      "epoch": 1.2013946487266918,
      "grad_norm": 0.3955286145210266,
      "learning_rate": 6.907807780265098e-06,
      "loss": 0.4107,
      "step": 39109
    },
    {
      "epoch": 1.2014253678616411,
      "grad_norm": 0.42281004786491394,
      "learning_rate": 6.907348191582793e-06,
      "loss": 0.4624,
      "step": 39110
    },
    {
      "epoch": 1.2014560869965902,
      "grad_norm": 0.4381698966026306,
      "learning_rate": 6.906888610123588e-06,
      "loss": 0.557,
      "step": 39111
    },
    {
      "epoch": 1.2014868061315394,
      "grad_norm": 0.38595283031463623,
      "learning_rate": 6.906429035888565e-06,
      "loss": 0.5296,
      "step": 39112
    },
    {
      "epoch": 1.2015175252664885,
      "grad_norm": 0.4066694974899292,
      "learning_rate": 6.905969468878787e-06,
      "loss": 0.5362,
      "step": 39113
    },
    {
      "epoch": 1.2015482444014376,
      "grad_norm": 0.35613110661506653,
      "learning_rate": 6.90550990909534e-06,
      "loss": 0.4907,
      "step": 39114
    },
    {
      "epoch": 1.2015789635363867,
      "grad_norm": 0.40089714527130127,
      "learning_rate": 6.905050356539285e-06,
      "loss": 0.4712,
      "step": 39115
    },
    {
      "epoch": 1.201609682671336,
      "grad_norm": 0.37192732095718384,
      "learning_rate": 6.904590811211706e-06,
      "loss": 0.477,
      "step": 39116
    },
    {
      "epoch": 1.2016404018062852,
      "grad_norm": 0.4572427570819855,
      "learning_rate": 6.9041312731136675e-06,
      "loss": 0.4349,
      "step": 39117
    },
    {
      "epoch": 1.2016711209412343,
      "grad_norm": 0.40948379039764404,
      "learning_rate": 6.903671742246249e-06,
      "loss": 0.4871,
      "step": 39118
    },
    {
      "epoch": 1.2017018400761834,
      "grad_norm": 0.3732907474040985,
      "learning_rate": 6.90321221861052e-06,
      "loss": 0.5252,
      "step": 39119
    },
    {
      "epoch": 1.2017325592111325,
      "grad_norm": 0.4100523591041565,
      "learning_rate": 6.902752702207551e-06,
      "loss": 0.4233,
      "step": 39120
    },
    {
      "epoch": 1.2017632783460819,
      "grad_norm": 0.39196324348449707,
      "learning_rate": 6.9022931930384275e-06,
      "loss": 0.5002,
      "step": 39121
    },
    {
      "epoch": 1.201793997481031,
      "grad_norm": 0.3843376636505127,
      "learning_rate": 6.901833691104208e-06,
      "loss": 0.4332,
      "step": 39122
    },
    {
      "epoch": 1.2018247166159801,
      "grad_norm": 0.38908708095550537,
      "learning_rate": 6.901374196405979e-06,
      "loss": 0.4468,
      "step": 39123
    },
    {
      "epoch": 1.2018554357509292,
      "grad_norm": 0.45206984877586365,
      "learning_rate": 6.900914708944802e-06,
      "loss": 0.4946,
      "step": 39124
    },
    {
      "epoch": 1.2018861548858784,
      "grad_norm": 0.5617502927780151,
      "learning_rate": 6.900455228721758e-06,
      "loss": 0.4163,
      "step": 39125
    },
    {
      "epoch": 1.2019168740208275,
      "grad_norm": 0.3769007623195648,
      "learning_rate": 6.899995755737914e-06,
      "loss": 0.4296,
      "step": 39126
    },
    {
      "epoch": 1.2019475931557768,
      "grad_norm": 0.37805697321891785,
      "learning_rate": 6.8995362899943485e-06,
      "loss": 0.3842,
      "step": 39127
    },
    {
      "epoch": 1.201978312290726,
      "grad_norm": 0.4640524983406067,
      "learning_rate": 6.899076831492132e-06,
      "loss": 0.5311,
      "step": 39128
    },
    {
      "epoch": 1.202009031425675,
      "grad_norm": 0.3864176273345947,
      "learning_rate": 6.89861738023234e-06,
      "loss": 0.4796,
      "step": 39129
    },
    {
      "epoch": 1.2020397505606242,
      "grad_norm": 0.3941654562950134,
      "learning_rate": 6.89815793621604e-06,
      "loss": 0.3936,
      "step": 39130
    },
    {
      "epoch": 1.2020704696955733,
      "grad_norm": 0.38102662563323975,
      "learning_rate": 6.897698499444312e-06,
      "loss": 0.4667,
      "step": 39131
    },
    {
      "epoch": 1.2021011888305226,
      "grad_norm": 0.3833714425563812,
      "learning_rate": 6.8972390699182235e-06,
      "loss": 0.483,
      "step": 39132
    },
    {
      "epoch": 1.2021319079654718,
      "grad_norm": 0.4428873658180237,
      "learning_rate": 6.896779647638852e-06,
      "loss": 0.371,
      "step": 39133
    },
    {
      "epoch": 1.2021626271004209,
      "grad_norm": 0.3771428167819977,
      "learning_rate": 6.896320232607265e-06,
      "loss": 0.4123,
      "step": 39134
    },
    {
      "epoch": 1.20219334623537,
      "grad_norm": 0.37260791659355164,
      "learning_rate": 6.895860824824543e-06,
      "loss": 0.4525,
      "step": 39135
    },
    {
      "epoch": 1.2022240653703191,
      "grad_norm": 0.4180949032306671,
      "learning_rate": 6.895401424291752e-06,
      "loss": 0.5864,
      "step": 39136
    },
    {
      "epoch": 1.2022547845052682,
      "grad_norm": 0.4054289758205414,
      "learning_rate": 6.89494203100997e-06,
      "loss": 0.3832,
      "step": 39137
    },
    {
      "epoch": 1.2022855036402176,
      "grad_norm": 0.4126811921596527,
      "learning_rate": 6.894482644980265e-06,
      "loss": 0.4807,
      "step": 39138
    },
    {
      "epoch": 1.2023162227751667,
      "grad_norm": 0.3647298216819763,
      "learning_rate": 6.894023266203713e-06,
      "loss": 0.4541,
      "step": 39139
    },
    {
      "epoch": 1.2023469419101158,
      "grad_norm": 0.37105831503868103,
      "learning_rate": 6.893563894681389e-06,
      "loss": 0.4386,
      "step": 39140
    },
    {
      "epoch": 1.202377661045065,
      "grad_norm": 0.4122081696987152,
      "learning_rate": 6.89310453041436e-06,
      "loss": 0.5299,
      "step": 39141
    },
    {
      "epoch": 1.202408380180014,
      "grad_norm": 0.3952111601829529,
      "learning_rate": 6.892645173403707e-06,
      "loss": 0.4703,
      "step": 39142
    },
    {
      "epoch": 1.2024390993149634,
      "grad_norm": 0.3996935486793518,
      "learning_rate": 6.892185823650495e-06,
      "loss": 0.5211,
      "step": 39143
    },
    {
      "epoch": 1.2024698184499125,
      "grad_norm": 0.421428382396698,
      "learning_rate": 6.891726481155802e-06,
      "loss": 0.5651,
      "step": 39144
    },
    {
      "epoch": 1.2025005375848616,
      "grad_norm": 0.3869277238845825,
      "learning_rate": 6.891267145920696e-06,
      "loss": 0.4687,
      "step": 39145
    },
    {
      "epoch": 1.2025312567198108,
      "grad_norm": 0.42413172125816345,
      "learning_rate": 6.890807817946257e-06,
      "loss": 0.4019,
      "step": 39146
    },
    {
      "epoch": 1.2025619758547599,
      "grad_norm": 0.39800912141799927,
      "learning_rate": 6.890348497233548e-06,
      "loss": 0.5022,
      "step": 39147
    },
    {
      "epoch": 1.202592694989709,
      "grad_norm": 0.4026009440422058,
      "learning_rate": 6.889889183783654e-06,
      "loss": 0.4968,
      "step": 39148
    },
    {
      "epoch": 1.2026234141246583,
      "grad_norm": 0.4137613773345947,
      "learning_rate": 6.889429877597633e-06,
      "loss": 0.4525,
      "step": 39149
    },
    {
      "epoch": 1.2026541332596075,
      "grad_norm": 0.41631656885147095,
      "learning_rate": 6.888970578676574e-06,
      "loss": 0.5484,
      "step": 39150
    },
    {
      "epoch": 1.2026848523945566,
      "grad_norm": 0.40110310912132263,
      "learning_rate": 6.8885112870215334e-06,
      "loss": 0.5316,
      "step": 39151
    },
    {
      "epoch": 1.2027155715295057,
      "grad_norm": 0.38737979531288147,
      "learning_rate": 6.8880520026336e-06,
      "loss": 0.4336,
      "step": 39152
    },
    {
      "epoch": 1.2027462906644548,
      "grad_norm": 0.3672296702861786,
      "learning_rate": 6.887592725513833e-06,
      "loss": 0.4411,
      "step": 39153
    },
    {
      "epoch": 1.2027770097994042,
      "grad_norm": 0.35511675477027893,
      "learning_rate": 6.887133455663313e-06,
      "loss": 0.4418,
      "step": 39154
    },
    {
      "epoch": 1.2028077289343533,
      "grad_norm": 0.3890793025493622,
      "learning_rate": 6.886674193083108e-06,
      "loss": 0.4674,
      "step": 39155
    },
    {
      "epoch": 1.2028384480693024,
      "grad_norm": 0.4302886128425598,
      "learning_rate": 6.886214937774291e-06,
      "loss": 0.5624,
      "step": 39156
    },
    {
      "epoch": 1.2028691672042515,
      "grad_norm": 0.4005853831768036,
      "learning_rate": 6.885755689737943e-06,
      "loss": 0.4417,
      "step": 39157
    },
    {
      "epoch": 1.2028998863392006,
      "grad_norm": 0.3803142309188843,
      "learning_rate": 6.885296448975125e-06,
      "loss": 0.4685,
      "step": 39158
    },
    {
      "epoch": 1.2029306054741498,
      "grad_norm": 0.41490575671195984,
      "learning_rate": 6.884837215486918e-06,
      "loss": 0.5084,
      "step": 39159
    },
    {
      "epoch": 1.202961324609099,
      "grad_norm": 0.4144349992275238,
      "learning_rate": 6.884377989274389e-06,
      "loss": 0.503,
      "step": 39160
    },
    {
      "epoch": 1.2029920437440482,
      "grad_norm": 0.38635116815567017,
      "learning_rate": 6.883918770338614e-06,
      "loss": 0.4388,
      "step": 39161
    },
    {
      "epoch": 1.2030227628789973,
      "grad_norm": 0.37994059920310974,
      "learning_rate": 6.883459558680663e-06,
      "loss": 0.4314,
      "step": 39162
    },
    {
      "epoch": 1.2030534820139465,
      "grad_norm": 0.3792239725589752,
      "learning_rate": 6.883000354301611e-06,
      "loss": 0.4693,
      "step": 39163
    },
    {
      "epoch": 1.2030842011488956,
      "grad_norm": 0.4498917758464813,
      "learning_rate": 6.882541157202528e-06,
      "loss": 0.4854,
      "step": 39164
    },
    {
      "epoch": 1.203114920283845,
      "grad_norm": 0.40356311202049255,
      "learning_rate": 6.88208196738449e-06,
      "loss": 0.4084,
      "step": 39165
    },
    {
      "epoch": 1.203145639418794,
      "grad_norm": 0.4083981513977051,
      "learning_rate": 6.881622784848565e-06,
      "loss": 0.52,
      "step": 39166
    },
    {
      "epoch": 1.2031763585537432,
      "grad_norm": 0.417634516954422,
      "learning_rate": 6.88116360959583e-06,
      "loss": 0.4571,
      "step": 39167
    },
    {
      "epoch": 1.2032070776886923,
      "grad_norm": 0.4678308963775635,
      "learning_rate": 6.880704441627353e-06,
      "loss": 0.5058,
      "step": 39168
    },
    {
      "epoch": 1.2032377968236414,
      "grad_norm": 0.42403602600097656,
      "learning_rate": 6.880245280944211e-06,
      "loss": 0.4823,
      "step": 39169
    },
    {
      "epoch": 1.2032685159585905,
      "grad_norm": 0.38215336203575134,
      "learning_rate": 6.879786127547472e-06,
      "loss": 0.4469,
      "step": 39170
    },
    {
      "epoch": 1.2032992350935396,
      "grad_norm": 0.41483408212661743,
      "learning_rate": 6.879326981438212e-06,
      "loss": 0.4911,
      "step": 39171
    },
    {
      "epoch": 1.203329954228489,
      "grad_norm": 0.4086763858795166,
      "learning_rate": 6.878867842617499e-06,
      "loss": 0.562,
      "step": 39172
    },
    {
      "epoch": 1.203360673363438,
      "grad_norm": 0.44166526198387146,
      "learning_rate": 6.878408711086412e-06,
      "loss": 0.4563,
      "step": 39173
    },
    {
      "epoch": 1.2033913924983872,
      "grad_norm": 0.46531566977500916,
      "learning_rate": 6.877949586846016e-06,
      "loss": 0.4979,
      "step": 39174
    },
    {
      "epoch": 1.2034221116333363,
      "grad_norm": 0.3974080979824066,
      "learning_rate": 6.877490469897388e-06,
      "loss": 0.4688,
      "step": 39175
    },
    {
      "epoch": 1.2034528307682857,
      "grad_norm": 0.385095477104187,
      "learning_rate": 6.8770313602416e-06,
      "loss": 0.4943,
      "step": 39176
    },
    {
      "epoch": 1.2034835499032348,
      "grad_norm": 0.38592803478240967,
      "learning_rate": 6.876572257879721e-06,
      "loss": 0.4786,
      "step": 39177
    },
    {
      "epoch": 1.203514269038184,
      "grad_norm": 0.40205055475234985,
      "learning_rate": 6.87611316281283e-06,
      "loss": 0.496,
      "step": 39178
    },
    {
      "epoch": 1.203544988173133,
      "grad_norm": 0.3743661642074585,
      "learning_rate": 6.875654075041991e-06,
      "loss": 0.4388,
      "step": 39179
    },
    {
      "epoch": 1.2035757073080822,
      "grad_norm": 0.4010912775993347,
      "learning_rate": 6.875194994568284e-06,
      "loss": 0.4577,
      "step": 39180
    },
    {
      "epoch": 1.2036064264430313,
      "grad_norm": 0.4226249158382416,
      "learning_rate": 6.8747359213927715e-06,
      "loss": 0.487,
      "step": 39181
    },
    {
      "epoch": 1.2036371455779804,
      "grad_norm": 0.44705238938331604,
      "learning_rate": 6.874276855516538e-06,
      "loss": 0.5305,
      "step": 39182
    },
    {
      "epoch": 1.2036678647129297,
      "grad_norm": 0.388686865568161,
      "learning_rate": 6.873817796940643e-06,
      "loss": 0.4476,
      "step": 39183
    },
    {
      "epoch": 1.2036985838478789,
      "grad_norm": 0.4251645803451538,
      "learning_rate": 6.87335874566617e-06,
      "loss": 0.4601,
      "step": 39184
    },
    {
      "epoch": 1.203729302982828,
      "grad_norm": 0.38311994075775146,
      "learning_rate": 6.87289970169418e-06,
      "loss": 0.427,
      "step": 39185
    },
    {
      "epoch": 1.203760022117777,
      "grad_norm": 0.42029672861099243,
      "learning_rate": 6.872440665025759e-06,
      "loss": 0.5321,
      "step": 39186
    },
    {
      "epoch": 1.2037907412527262,
      "grad_norm": 0.46629583835601807,
      "learning_rate": 6.871981635661966e-06,
      "loss": 0.4555,
      "step": 39187
    },
    {
      "epoch": 1.2038214603876756,
      "grad_norm": 0.3893955945968628,
      "learning_rate": 6.87152261360388e-06,
      "loss": 0.4704,
      "step": 39188
    },
    {
      "epoch": 1.2038521795226247,
      "grad_norm": 0.3965875208377838,
      "learning_rate": 6.87106359885257e-06,
      "loss": 0.4277,
      "step": 39189
    },
    {
      "epoch": 1.2038828986575738,
      "grad_norm": 0.3959168493747711,
      "learning_rate": 6.870604591409111e-06,
      "loss": 0.5222,
      "step": 39190
    },
    {
      "epoch": 1.203913617792523,
      "grad_norm": 0.4239955544471741,
      "learning_rate": 6.870145591274573e-06,
      "loss": 0.4415,
      "step": 39191
    },
    {
      "epoch": 1.203944336927472,
      "grad_norm": 0.36428847908973694,
      "learning_rate": 6.869686598450029e-06,
      "loss": 0.4824,
      "step": 39192
    },
    {
      "epoch": 1.2039750560624212,
      "grad_norm": 0.4057629406452179,
      "learning_rate": 6.86922761293655e-06,
      "loss": 0.474,
      "step": 39193
    },
    {
      "epoch": 1.2040057751973705,
      "grad_norm": 0.41780105233192444,
      "learning_rate": 6.868768634735208e-06,
      "loss": 0.4121,
      "step": 39194
    },
    {
      "epoch": 1.2040364943323196,
      "grad_norm": 0.37741973996162415,
      "learning_rate": 6.868309663847077e-06,
      "loss": 0.5412,
      "step": 39195
    },
    {
      "epoch": 1.2040672134672687,
      "grad_norm": 0.382916659116745,
      "learning_rate": 6.867850700273225e-06,
      "loss": 0.5097,
      "step": 39196
    },
    {
      "epoch": 1.2040979326022179,
      "grad_norm": 0.4172792136669159,
      "learning_rate": 6.8673917440147284e-06,
      "loss": 0.5362,
      "step": 39197
    },
    {
      "epoch": 1.204128651737167,
      "grad_norm": 0.40628769993782043,
      "learning_rate": 6.866932795072656e-06,
      "loss": 0.491,
      "step": 39198
    },
    {
      "epoch": 1.2041593708721163,
      "grad_norm": 0.4286840856075287,
      "learning_rate": 6.866473853448083e-06,
      "loss": 0.4334,
      "step": 39199
    },
    {
      "epoch": 1.2041900900070655,
      "grad_norm": 1.0203062295913696,
      "learning_rate": 6.8660149191420775e-06,
      "loss": 0.4423,
      "step": 39200
    },
    {
      "epoch": 1.2042208091420146,
      "grad_norm": 0.42869681119918823,
      "learning_rate": 6.865555992155715e-06,
      "loss": 0.4765,
      "step": 39201
    },
    {
      "epoch": 1.2042515282769637,
      "grad_norm": 0.4311734139919281,
      "learning_rate": 6.865097072490062e-06,
      "loss": 0.4152,
      "step": 39202
    },
    {
      "epoch": 1.2042822474119128,
      "grad_norm": 0.40237003564834595,
      "learning_rate": 6.864638160146198e-06,
      "loss": 0.5134,
      "step": 39203
    },
    {
      "epoch": 1.204312966546862,
      "grad_norm": 0.40219834446907043,
      "learning_rate": 6.864179255125185e-06,
      "loss": 0.4901,
      "step": 39204
    },
    {
      "epoch": 1.2043436856818113,
      "grad_norm": 0.4152776598930359,
      "learning_rate": 6.863720357428105e-06,
      "loss": 0.5578,
      "step": 39205
    },
    {
      "epoch": 1.2043744048167604,
      "grad_norm": 0.4042684733867645,
      "learning_rate": 6.863261467056024e-06,
      "loss": 0.5162,
      "step": 39206
    },
    {
      "epoch": 1.2044051239517095,
      "grad_norm": 0.3956233561038971,
      "learning_rate": 6.862802584010014e-06,
      "loss": 0.4995,
      "step": 39207
    },
    {
      "epoch": 1.2044358430866586,
      "grad_norm": 0.36027127504348755,
      "learning_rate": 6.862343708291148e-06,
      "loss": 0.4466,
      "step": 39208
    },
    {
      "epoch": 1.2044665622216078,
      "grad_norm": 0.38511112332344055,
      "learning_rate": 6.861884839900501e-06,
      "loss": 0.4373,
      "step": 39209
    },
    {
      "epoch": 1.204497281356557,
      "grad_norm": 0.43451589345932007,
      "learning_rate": 6.861425978839134e-06,
      "loss": 0.5411,
      "step": 39210
    },
    {
      "epoch": 1.2045280004915062,
      "grad_norm": 0.43903541564941406,
      "learning_rate": 6.860967125108129e-06,
      "loss": 0.5486,
      "step": 39211
    },
    {
      "epoch": 1.2045587196264553,
      "grad_norm": 0.3898526430130005,
      "learning_rate": 6.860508278708555e-06,
      "loss": 0.5267,
      "step": 39212
    },
    {
      "epoch": 1.2045894387614045,
      "grad_norm": 0.5503031015396118,
      "learning_rate": 6.860049439641483e-06,
      "loss": 0.4831,
      "step": 39213
    },
    {
      "epoch": 1.2046201578963536,
      "grad_norm": 0.40444502234458923,
      "learning_rate": 6.859590607907987e-06,
      "loss": 0.4504,
      "step": 39214
    },
    {
      "epoch": 1.2046508770313027,
      "grad_norm": 0.40994352102279663,
      "learning_rate": 6.859131783509132e-06,
      "loss": 0.5161,
      "step": 39215
    },
    {
      "epoch": 1.204681596166252,
      "grad_norm": 0.3854621648788452,
      "learning_rate": 6.858672966446001e-06,
      "loss": 0.4552,
      "step": 39216
    },
    {
      "epoch": 1.2047123153012012,
      "grad_norm": 0.4330212473869324,
      "learning_rate": 6.858214156719649e-06,
      "loss": 0.4939,
      "step": 39217
    },
    {
      "epoch": 1.2047430344361503,
      "grad_norm": 0.373473197221756,
      "learning_rate": 6.857755354331166e-06,
      "loss": 0.5126,
      "step": 39218
    },
    {
      "epoch": 1.2047737535710994,
      "grad_norm": 0.47948867082595825,
      "learning_rate": 6.857296559281609e-06,
      "loss": 0.4496,
      "step": 39219
    },
    {
      "epoch": 1.2048044727060485,
      "grad_norm": 0.4149765372276306,
      "learning_rate": 6.85683777157206e-06,
      "loss": 0.4768,
      "step": 39220
    },
    {
      "epoch": 1.2048351918409979,
      "grad_norm": 0.38735079765319824,
      "learning_rate": 6.8563789912035825e-06,
      "loss": 0.4911,
      "step": 39221
    },
    {
      "epoch": 1.204865910975947,
      "grad_norm": 0.440748929977417,
      "learning_rate": 6.8559202181772545e-06,
      "loss": 0.5223,
      "step": 39222
    },
    {
      "epoch": 1.204896630110896,
      "grad_norm": 0.4320032298564911,
      "learning_rate": 6.855461452494141e-06,
      "loss": 0.4419,
      "step": 39223
    },
    {
      "epoch": 1.2049273492458452,
      "grad_norm": 0.4019514322280884,
      "learning_rate": 6.855002694155319e-06,
      "loss": 0.4361,
      "step": 39224
    },
    {
      "epoch": 1.2049580683807943,
      "grad_norm": 0.39339518547058105,
      "learning_rate": 6.854543943161856e-06,
      "loss": 0.4748,
      "step": 39225
    },
    {
      "epoch": 1.2049887875157435,
      "grad_norm": 0.40376052260398865,
      "learning_rate": 6.854085199514829e-06,
      "loss": 0.4409,
      "step": 39226
    },
    {
      "epoch": 1.2050195066506928,
      "grad_norm": 0.3858802318572998,
      "learning_rate": 6.853626463215301e-06,
      "loss": 0.5389,
      "step": 39227
    },
    {
      "epoch": 1.205050225785642,
      "grad_norm": 0.4575912058353424,
      "learning_rate": 6.853167734264352e-06,
      "loss": 0.4689,
      "step": 39228
    },
    {
      "epoch": 1.205080944920591,
      "grad_norm": 0.3682827353477478,
      "learning_rate": 6.852709012663046e-06,
      "loss": 0.3943,
      "step": 39229
    },
    {
      "epoch": 1.2051116640555402,
      "grad_norm": 0.3806253671646118,
      "learning_rate": 6.85225029841246e-06,
      "loss": 0.4266,
      "step": 39230
    },
    {
      "epoch": 1.2051423831904893,
      "grad_norm": 0.4078397750854492,
      "learning_rate": 6.8517915915136635e-06,
      "loss": 0.4904,
      "step": 39231
    },
    {
      "epoch": 1.2051731023254386,
      "grad_norm": 0.3981799781322479,
      "learning_rate": 6.851332891967726e-06,
      "loss": 0.5498,
      "step": 39232
    },
    {
      "epoch": 1.2052038214603877,
      "grad_norm": 0.4473201632499695,
      "learning_rate": 6.850874199775722e-06,
      "loss": 0.491,
      "step": 39233
    },
    {
      "epoch": 1.2052345405953369,
      "grad_norm": 0.39915579557418823,
      "learning_rate": 6.85041551493872e-06,
      "loss": 0.4276,
      "step": 39234
    },
    {
      "epoch": 1.205265259730286,
      "grad_norm": 0.46128228306770325,
      "learning_rate": 6.849956837457794e-06,
      "loss": 0.5292,
      "step": 39235
    },
    {
      "epoch": 1.205295978865235,
      "grad_norm": 0.4273691475391388,
      "learning_rate": 6.849498167334012e-06,
      "loss": 0.5195,
      "step": 39236
    },
    {
      "epoch": 1.2053266980001842,
      "grad_norm": 0.43021222949028015,
      "learning_rate": 6.84903950456845e-06,
      "loss": 0.4476,
      "step": 39237
    },
    {
      "epoch": 1.2053574171351336,
      "grad_norm": 0.39484989643096924,
      "learning_rate": 6.848580849162173e-06,
      "loss": 0.5265,
      "step": 39238
    },
    {
      "epoch": 1.2053881362700827,
      "grad_norm": 0.40064066648483276,
      "learning_rate": 6.848122201116259e-06,
      "loss": 0.4616,
      "step": 39239
    },
    {
      "epoch": 1.2054188554050318,
      "grad_norm": 0.3823679983615875,
      "learning_rate": 6.847663560431772e-06,
      "loss": 0.505,
      "step": 39240
    },
    {
      "epoch": 1.205449574539981,
      "grad_norm": 0.3726970851421356,
      "learning_rate": 6.84720492710979e-06,
      "loss": 0.5452,
      "step": 39241
    },
    {
      "epoch": 1.20548029367493,
      "grad_norm": 0.5032830834388733,
      "learning_rate": 6.846746301151378e-06,
      "loss": 0.4429,
      "step": 39242
    },
    {
      "epoch": 1.2055110128098794,
      "grad_norm": 0.5555566549301147,
      "learning_rate": 6.846287682557615e-06,
      "loss": 0.4803,
      "step": 39243
    },
    {
      "epoch": 1.2055417319448285,
      "grad_norm": 0.4558089077472687,
      "learning_rate": 6.845829071329562e-06,
      "loss": 0.4834,
      "step": 39244
    },
    {
      "epoch": 1.2055724510797776,
      "grad_norm": 0.47548413276672363,
      "learning_rate": 6.845370467468299e-06,
      "loss": 0.4753,
      "step": 39245
    },
    {
      "epoch": 1.2056031702147267,
      "grad_norm": 0.3948487639427185,
      "learning_rate": 6.84491187097489e-06,
      "loss": 0.4825,
      "step": 39246
    },
    {
      "epoch": 1.2056338893496759,
      "grad_norm": 0.400409072637558,
      "learning_rate": 6.8444532818504114e-06,
      "loss": 0.4784,
      "step": 39247
    },
    {
      "epoch": 1.205664608484625,
      "grad_norm": 0.4292892813682556,
      "learning_rate": 6.843994700095935e-06,
      "loss": 0.4449,
      "step": 39248
    },
    {
      "epoch": 1.2056953276195743,
      "grad_norm": 0.38086560368537903,
      "learning_rate": 6.843536125712527e-06,
      "loss": 0.5007,
      "step": 39249
    },
    {
      "epoch": 1.2057260467545234,
      "grad_norm": 0.3987078070640564,
      "learning_rate": 6.8430775587012635e-06,
      "loss": 0.4817,
      "step": 39250
    },
    {
      "epoch": 1.2057567658894726,
      "grad_norm": 0.41046440601348877,
      "learning_rate": 6.842618999063208e-06,
      "loss": 0.4621,
      "step": 39251
    },
    {
      "epoch": 1.2057874850244217,
      "grad_norm": 0.41036853194236755,
      "learning_rate": 6.842160446799442e-06,
      "loss": 0.4481,
      "step": 39252
    },
    {
      "epoch": 1.2058182041593708,
      "grad_norm": 0.5227260589599609,
      "learning_rate": 6.841701901911024e-06,
      "loss": 0.4658,
      "step": 39253
    },
    {
      "epoch": 1.2058489232943201,
      "grad_norm": 0.40431565046310425,
      "learning_rate": 6.84124336439904e-06,
      "loss": 0.4717,
      "step": 39254
    },
    {
      "epoch": 1.2058796424292693,
      "grad_norm": 0.40230605006217957,
      "learning_rate": 6.840784834264544e-06,
      "loss": 0.4967,
      "step": 39255
    },
    {
      "epoch": 1.2059103615642184,
      "grad_norm": 0.3846505582332611,
      "learning_rate": 6.840326311508624e-06,
      "loss": 0.424,
      "step": 39256
    },
    {
      "epoch": 1.2059410806991675,
      "grad_norm": 0.40894240140914917,
      "learning_rate": 6.839867796132338e-06,
      "loss": 0.5242,
      "step": 39257
    },
    {
      "epoch": 1.2059717998341166,
      "grad_norm": 0.5158970355987549,
      "learning_rate": 6.839409288136763e-06,
      "loss": 0.4331,
      "step": 39258
    },
    {
      "epoch": 1.2060025189690657,
      "grad_norm": 0.41666701436042786,
      "learning_rate": 6.838950787522967e-06,
      "loss": 0.5393,
      "step": 39259
    },
    {
      "epoch": 1.206033238104015,
      "grad_norm": 0.39472496509552,
      "learning_rate": 6.838492294292023e-06,
      "loss": 0.3869,
      "step": 39260
    },
    {
      "epoch": 1.2060639572389642,
      "grad_norm": 0.40315625071525574,
      "learning_rate": 6.838033808444999e-06,
      "loss": 0.4773,
      "step": 39261
    },
    {
      "epoch": 1.2060946763739133,
      "grad_norm": 0.3968997895717621,
      "learning_rate": 6.837575329982971e-06,
      "loss": 0.4743,
      "step": 39262
    },
    {
      "epoch": 1.2061253955088624,
      "grad_norm": 0.37578532099723816,
      "learning_rate": 6.837116858907005e-06,
      "loss": 0.4111,
      "step": 39263
    },
    {
      "epoch": 1.2061561146438116,
      "grad_norm": 0.39784637093544006,
      "learning_rate": 6.836658395218175e-06,
      "loss": 0.466,
      "step": 39264
    },
    {
      "epoch": 1.206186833778761,
      "grad_norm": 0.40924355387687683,
      "learning_rate": 6.836199938917547e-06,
      "loss": 0.4264,
      "step": 39265
    },
    {
      "epoch": 1.20621755291371,
      "grad_norm": 0.39500126242637634,
      "learning_rate": 6.835741490006196e-06,
      "loss": 0.4172,
      "step": 39266
    },
    {
      "epoch": 1.2062482720486591,
      "grad_norm": 0.4236375689506531,
      "learning_rate": 6.835283048485193e-06,
      "loss": 0.5543,
      "step": 39267
    },
    {
      "epoch": 1.2062789911836083,
      "grad_norm": 0.40953919291496277,
      "learning_rate": 6.834824614355606e-06,
      "loss": 0.4975,
      "step": 39268
    },
    {
      "epoch": 1.2063097103185574,
      "grad_norm": 0.43752190470695496,
      "learning_rate": 6.834366187618511e-06,
      "loss": 0.4314,
      "step": 39269
    },
    {
      "epoch": 1.2063404294535065,
      "grad_norm": 0.41159865260124207,
      "learning_rate": 6.83390776827497e-06,
      "loss": 0.4523,
      "step": 39270
    },
    {
      "epoch": 1.2063711485884558,
      "grad_norm": 0.41786760091781616,
      "learning_rate": 6.8334493563260615e-06,
      "loss": 0.4929,
      "step": 39271
    },
    {
      "epoch": 1.206401867723405,
      "grad_norm": 0.41472327709198,
      "learning_rate": 6.832990951772852e-06,
      "loss": 0.5097,
      "step": 39272
    },
    {
      "epoch": 1.206432586858354,
      "grad_norm": 0.44675496220588684,
      "learning_rate": 6.832532554616414e-06,
      "loss": 0.4796,
      "step": 39273
    },
    {
      "epoch": 1.2064633059933032,
      "grad_norm": 0.34866347908973694,
      "learning_rate": 6.832074164857816e-06,
      "loss": 0.4937,
      "step": 39274
    },
    {
      "epoch": 1.2064940251282523,
      "grad_norm": 0.36322587728500366,
      "learning_rate": 6.831615782498133e-06,
      "loss": 0.4589,
      "step": 39275
    },
    {
      "epoch": 1.2065247442632017,
      "grad_norm": 0.4633106291294098,
      "learning_rate": 6.831157407538429e-06,
      "loss": 0.4691,
      "step": 39276
    },
    {
      "epoch": 1.2065554633981508,
      "grad_norm": 0.3973149061203003,
      "learning_rate": 6.830699039979783e-06,
      "loss": 0.4676,
      "step": 39277
    },
    {
      "epoch": 1.2065861825331,
      "grad_norm": 0.3898068368434906,
      "learning_rate": 6.830240679823254e-06,
      "loss": 0.549,
      "step": 39278
    },
    {
      "epoch": 1.206616901668049,
      "grad_norm": 0.3631635010242462,
      "learning_rate": 6.829782327069927e-06,
      "loss": 0.4937,
      "step": 39279
    },
    {
      "epoch": 1.2066476208029981,
      "grad_norm": 0.4167688488960266,
      "learning_rate": 6.829323981720858e-06,
      "loss": 0.528,
      "step": 39280
    },
    {
      "epoch": 1.2066783399379473,
      "grad_norm": 0.39188823103904724,
      "learning_rate": 6.82886564377713e-06,
      "loss": 0.4923,
      "step": 39281
    },
    {
      "epoch": 1.2067090590728964,
      "grad_norm": 0.3849238455295563,
      "learning_rate": 6.828407313239802e-06,
      "loss": 0.4646,
      "step": 39282
    },
    {
      "epoch": 1.2067397782078457,
      "grad_norm": 0.37447839975357056,
      "learning_rate": 6.827948990109956e-06,
      "loss": 0.4693,
      "step": 39283
    },
    {
      "epoch": 1.2067704973427948,
      "grad_norm": 0.40333786606788635,
      "learning_rate": 6.827490674388653e-06,
      "loss": 0.4374,
      "step": 39284
    },
    {
      "epoch": 1.206801216477744,
      "grad_norm": 0.38942113518714905,
      "learning_rate": 6.827032366076965e-06,
      "loss": 0.4548,
      "step": 39285
    },
    {
      "epoch": 1.206831935612693,
      "grad_norm": 0.3675590753555298,
      "learning_rate": 6.82657406517597e-06,
      "loss": 0.4913,
      "step": 39286
    },
    {
      "epoch": 1.2068626547476424,
      "grad_norm": 0.37955620884895325,
      "learning_rate": 6.826115771686726e-06,
      "loss": 0.4119,
      "step": 39287
    },
    {
      "epoch": 1.2068933738825915,
      "grad_norm": 0.3791685104370117,
      "learning_rate": 6.825657485610317e-06,
      "loss": 0.4162,
      "step": 39288
    },
    {
      "epoch": 1.2069240930175407,
      "grad_norm": 0.36559632420539856,
      "learning_rate": 6.825199206947802e-06,
      "loss": 0.5341,
      "step": 39289
    },
    {
      "epoch": 1.2069548121524898,
      "grad_norm": 0.49589255452156067,
      "learning_rate": 6.824740935700262e-06,
      "loss": 0.5252,
      "step": 39290
    },
    {
      "epoch": 1.206985531287439,
      "grad_norm": 0.4718340337276459,
      "learning_rate": 6.824282671868756e-06,
      "loss": 0.44,
      "step": 39291
    },
    {
      "epoch": 1.207016250422388,
      "grad_norm": 0.394410103559494,
      "learning_rate": 6.823824415454361e-06,
      "loss": 0.4204,
      "step": 39292
    },
    {
      "epoch": 1.2070469695573371,
      "grad_norm": 0.40190115571022034,
      "learning_rate": 6.823366166458145e-06,
      "loss": 0.4615,
      "step": 39293
    },
    {
      "epoch": 1.2070776886922865,
      "grad_norm": 0.4088479280471802,
      "learning_rate": 6.822907924881181e-06,
      "loss": 0.4825,
      "step": 39294
    },
    {
      "epoch": 1.2071084078272356,
      "grad_norm": 0.40159279108047485,
      "learning_rate": 6.822449690724536e-06,
      "loss": 0.538,
      "step": 39295
    },
    {
      "epoch": 1.2071391269621847,
      "grad_norm": 0.4130803346633911,
      "learning_rate": 6.821991463989284e-06,
      "loss": 0.4973,
      "step": 39296
    },
    {
      "epoch": 1.2071698460971338,
      "grad_norm": 0.4175156056880951,
      "learning_rate": 6.821533244676489e-06,
      "loss": 0.3406,
      "step": 39297
    },
    {
      "epoch": 1.2072005652320832,
      "grad_norm": 0.40841782093048096,
      "learning_rate": 6.821075032787228e-06,
      "loss": 0.4839,
      "step": 39298
    },
    {
      "epoch": 1.2072312843670323,
      "grad_norm": 0.38065528869628906,
      "learning_rate": 6.820616828322566e-06,
      "loss": 0.5142,
      "step": 39299
    },
    {
      "epoch": 1.2072620035019814,
      "grad_norm": 0.415458083152771,
      "learning_rate": 6.820158631283578e-06,
      "loss": 0.4806,
      "step": 39300
    },
    {
      "epoch": 1.2072927226369305,
      "grad_norm": 0.38350680470466614,
      "learning_rate": 6.81970044167133e-06,
      "loss": 0.5054,
      "step": 39301
    },
    {
      "epoch": 1.2073234417718797,
      "grad_norm": 0.40429583191871643,
      "learning_rate": 6.819242259486893e-06,
      "loss": 0.5533,
      "step": 39302
    },
    {
      "epoch": 1.2073541609068288,
      "grad_norm": 0.3929591774940491,
      "learning_rate": 6.81878408473134e-06,
      "loss": 0.5225,
      "step": 39303
    },
    {
      "epoch": 1.207384880041778,
      "grad_norm": 0.4010718762874603,
      "learning_rate": 6.818325917405737e-06,
      "loss": 0.4551,
      "step": 39304
    },
    {
      "epoch": 1.2074155991767272,
      "grad_norm": 0.3966512978076935,
      "learning_rate": 6.817867757511158e-06,
      "loss": 0.5322,
      "step": 39305
    },
    {
      "epoch": 1.2074463183116764,
      "grad_norm": 0.372688889503479,
      "learning_rate": 6.817409605048668e-06,
      "loss": 0.4314,
      "step": 39306
    },
    {
      "epoch": 1.2074770374466255,
      "grad_norm": 0.4047953486442566,
      "learning_rate": 6.816951460019344e-06,
      "loss": 0.511,
      "step": 39307
    },
    {
      "epoch": 1.2075077565815746,
      "grad_norm": 0.4163406193256378,
      "learning_rate": 6.816493322424249e-06,
      "loss": 0.4985,
      "step": 39308
    },
    {
      "epoch": 1.2075384757165237,
      "grad_norm": 0.42508459091186523,
      "learning_rate": 6.816035192264458e-06,
      "loss": 0.5552,
      "step": 39309
    },
    {
      "epoch": 1.207569194851473,
      "grad_norm": 0.39872628450393677,
      "learning_rate": 6.815577069541039e-06,
      "loss": 0.4257,
      "step": 39310
    },
    {
      "epoch": 1.2075999139864222,
      "grad_norm": 0.38710829615592957,
      "learning_rate": 6.815118954255062e-06,
      "loss": 0.4633,
      "step": 39311
    },
    {
      "epoch": 1.2076306331213713,
      "grad_norm": 0.36552944779396057,
      "learning_rate": 6.814660846407597e-06,
      "loss": 0.4983,
      "step": 39312
    },
    {
      "epoch": 1.2076613522563204,
      "grad_norm": 0.41956305503845215,
      "learning_rate": 6.814202745999717e-06,
      "loss": 0.5186,
      "step": 39313
    },
    {
      "epoch": 1.2076920713912696,
      "grad_norm": 0.4274355471134186,
      "learning_rate": 6.813744653032483e-06,
      "loss": 0.4615,
      "step": 39314
    },
    {
      "epoch": 1.2077227905262187,
      "grad_norm": 0.3976043164730072,
      "learning_rate": 6.813286567506976e-06,
      "loss": 0.5384,
      "step": 39315
    },
    {
      "epoch": 1.207753509661168,
      "grad_norm": 0.3841707110404968,
      "learning_rate": 6.8128284894242565e-06,
      "loss": 0.4854,
      "step": 39316
    },
    {
      "epoch": 1.2077842287961171,
      "grad_norm": 0.39429861307144165,
      "learning_rate": 6.812370418785403e-06,
      "loss": 0.5458,
      "step": 39317
    },
    {
      "epoch": 1.2078149479310663,
      "grad_norm": 0.38916003704071045,
      "learning_rate": 6.811912355591477e-06,
      "loss": 0.4439,
      "step": 39318
    },
    {
      "epoch": 1.2078456670660154,
      "grad_norm": 0.4084920287132263,
      "learning_rate": 6.811454299843556e-06,
      "loss": 0.4455,
      "step": 39319
    },
    {
      "epoch": 1.2078763862009645,
      "grad_norm": 0.41887471079826355,
      "learning_rate": 6.810996251542703e-06,
      "loss": 0.3703,
      "step": 39320
    },
    {
      "epoch": 1.2079071053359138,
      "grad_norm": 0.37889525294303894,
      "learning_rate": 6.810538210689989e-06,
      "loss": 0.507,
      "step": 39321
    },
    {
      "epoch": 1.207937824470863,
      "grad_norm": 0.4106638729572296,
      "learning_rate": 6.8100801772864934e-06,
      "loss": 0.3899,
      "step": 39322
    },
    {
      "epoch": 1.207968543605812,
      "grad_norm": 0.41390132904052734,
      "learning_rate": 6.809622151333271e-06,
      "loss": 0.4604,
      "step": 39323
    },
    {
      "epoch": 1.2079992627407612,
      "grad_norm": 0.3960007131099701,
      "learning_rate": 6.809164132831405e-06,
      "loss": 0.4675,
      "step": 39324
    },
    {
      "epoch": 1.2080299818757103,
      "grad_norm": 0.41699615120887756,
      "learning_rate": 6.808706121781954e-06,
      "loss": 0.5087,
      "step": 39325
    },
    {
      "epoch": 1.2080607010106594,
      "grad_norm": 0.3869266211986542,
      "learning_rate": 6.808248118185996e-06,
      "loss": 0.5005,
      "step": 39326
    },
    {
      "epoch": 1.2080914201456088,
      "grad_norm": 0.4063643217086792,
      "learning_rate": 6.807790122044595e-06,
      "loss": 0.555,
      "step": 39327
    },
    {
      "epoch": 1.208122139280558,
      "grad_norm": 0.4370146095752716,
      "learning_rate": 6.807332133358826e-06,
      "loss": 0.496,
      "step": 39328
    },
    {
      "epoch": 1.208152858415507,
      "grad_norm": 0.4218113422393799,
      "learning_rate": 6.806874152129752e-06,
      "loss": 0.4872,
      "step": 39329
    },
    {
      "epoch": 1.2081835775504561,
      "grad_norm": 0.42535126209259033,
      "learning_rate": 6.8064161783584506e-06,
      "loss": 0.5145,
      "step": 39330
    },
    {
      "epoch": 1.2082142966854053,
      "grad_norm": 0.4146946370601654,
      "learning_rate": 6.805958212045983e-06,
      "loss": 0.5216,
      "step": 39331
    },
    {
      "epoch": 1.2082450158203546,
      "grad_norm": 0.3532523810863495,
      "learning_rate": 6.805500253193427e-06,
      "loss": 0.4507,
      "step": 39332
    },
    {
      "epoch": 1.2082757349553037,
      "grad_norm": 0.42268264293670654,
      "learning_rate": 6.8050423018018455e-06,
      "loss": 0.5553,
      "step": 39333
    },
    {
      "epoch": 1.2083064540902528,
      "grad_norm": 0.4052131175994873,
      "learning_rate": 6.804584357872313e-06,
      "loss": 0.5064,
      "step": 39334
    },
    {
      "epoch": 1.208337173225202,
      "grad_norm": 0.41696393489837646,
      "learning_rate": 6.804126421405893e-06,
      "loss": 0.4889,
      "step": 39335
    },
    {
      "epoch": 1.208367892360151,
      "grad_norm": 0.4548267722129822,
      "learning_rate": 6.803668492403663e-06,
      "loss": 0.4481,
      "step": 39336
    },
    {
      "epoch": 1.2083986114951002,
      "grad_norm": 0.4240301251411438,
      "learning_rate": 6.803210570866685e-06,
      "loss": 0.4414,
      "step": 39337
    },
    {
      "epoch": 1.2084293306300495,
      "grad_norm": 0.4573636054992676,
      "learning_rate": 6.802752656796037e-06,
      "loss": 0.4227,
      "step": 39338
    },
    {
      "epoch": 1.2084600497649987,
      "grad_norm": 0.38994044065475464,
      "learning_rate": 6.802294750192779e-06,
      "loss": 0.5464,
      "step": 39339
    },
    {
      "epoch": 1.2084907688999478,
      "grad_norm": 0.38780197501182556,
      "learning_rate": 6.801836851057984e-06,
      "loss": 0.5301,
      "step": 39340
    },
    {
      "epoch": 1.208521488034897,
      "grad_norm": 0.41244032979011536,
      "learning_rate": 6.801378959392726e-06,
      "loss": 0.5178,
      "step": 39341
    },
    {
      "epoch": 1.208552207169846,
      "grad_norm": 0.5312095284461975,
      "learning_rate": 6.800921075198069e-06,
      "loss": 0.4654,
      "step": 39342
    },
    {
      "epoch": 1.2085829263047954,
      "grad_norm": 0.41506803035736084,
      "learning_rate": 6.800463198475086e-06,
      "loss": 0.4522,
      "step": 39343
    },
    {
      "epoch": 1.2086136454397445,
      "grad_norm": 0.41916608810424805,
      "learning_rate": 6.800005329224843e-06,
      "loss": 0.5385,
      "step": 39344
    },
    {
      "epoch": 1.2086443645746936,
      "grad_norm": 0.4468660056591034,
      "learning_rate": 6.799547467448412e-06,
      "loss": 0.5186,
      "step": 39345
    },
    {
      "epoch": 1.2086750837096427,
      "grad_norm": 0.34455978870391846,
      "learning_rate": 6.79908961314686e-06,
      "loss": 0.406,
      "step": 39346
    },
    {
      "epoch": 1.2087058028445918,
      "grad_norm": 0.39501678943634033,
      "learning_rate": 6.798631766321262e-06,
      "loss": 0.4135,
      "step": 39347
    },
    {
      "epoch": 1.208736521979541,
      "grad_norm": 0.3970968425273895,
      "learning_rate": 6.798173926972675e-06,
      "loss": 0.4688,
      "step": 39348
    },
    {
      "epoch": 1.2087672411144903,
      "grad_norm": 0.3934290111064911,
      "learning_rate": 6.797716095102185e-06,
      "loss": 0.4489,
      "step": 39349
    },
    {
      "epoch": 1.2087979602494394,
      "grad_norm": 0.42326274514198303,
      "learning_rate": 6.797258270710847e-06,
      "loss": 0.5372,
      "step": 39350
    },
    {
      "epoch": 1.2088286793843885,
      "grad_norm": 0.3856142461299896,
      "learning_rate": 6.79680045379974e-06,
      "loss": 0.5511,
      "step": 39351
    },
    {
      "epoch": 1.2088593985193377,
      "grad_norm": 0.396790474653244,
      "learning_rate": 6.7963426443699244e-06,
      "loss": 0.451,
      "step": 39352
    },
    {
      "epoch": 1.2088901176542868,
      "grad_norm": 0.4590971767902374,
      "learning_rate": 6.79588484242248e-06,
      "loss": 0.4915,
      "step": 39353
    },
    {
      "epoch": 1.2089208367892361,
      "grad_norm": 0.40919652581214905,
      "learning_rate": 6.795427047958466e-06,
      "loss": 0.5195,
      "step": 39354
    },
    {
      "epoch": 1.2089515559241852,
      "grad_norm": 0.3925895094871521,
      "learning_rate": 6.794969260978958e-06,
      "loss": 0.4779,
      "step": 39355
    },
    {
      "epoch": 1.2089822750591344,
      "grad_norm": 0.39757925271987915,
      "learning_rate": 6.7945114814850225e-06,
      "loss": 0.5255,
      "step": 39356
    },
    {
      "epoch": 1.2090129941940835,
      "grad_norm": 0.37150585651397705,
      "learning_rate": 6.794053709477726e-06,
      "loss": 0.4617,
      "step": 39357
    },
    {
      "epoch": 1.2090437133290326,
      "grad_norm": 0.49883535504341125,
      "learning_rate": 6.793595944958147e-06,
      "loss": 0.4222,
      "step": 39358
    },
    {
      "epoch": 1.2090744324639817,
      "grad_norm": 0.4301506578922272,
      "learning_rate": 6.793138187927342e-06,
      "loss": 0.5457,
      "step": 39359
    },
    {
      "epoch": 1.209105151598931,
      "grad_norm": 0.4219457805156708,
      "learning_rate": 6.792680438386394e-06,
      "loss": 0.4617,
      "step": 39360
    },
    {
      "epoch": 1.2091358707338802,
      "grad_norm": 0.38804757595062256,
      "learning_rate": 6.79222269633636e-06,
      "loss": 0.4434,
      "step": 39361
    },
    {
      "epoch": 1.2091665898688293,
      "grad_norm": 0.4319915473461151,
      "learning_rate": 6.791764961778317e-06,
      "loss": 0.5219,
      "step": 39362
    },
    {
      "epoch": 1.2091973090037784,
      "grad_norm": 0.38348737359046936,
      "learning_rate": 6.791307234713328e-06,
      "loss": 0.4637,
      "step": 39363
    },
    {
      "epoch": 1.2092280281387275,
      "grad_norm": 0.4384652376174927,
      "learning_rate": 6.790849515142468e-06,
      "loss": 0.4475,
      "step": 39364
    },
    {
      "epoch": 1.2092587472736769,
      "grad_norm": 0.3775121867656708,
      "learning_rate": 6.790391803066801e-06,
      "loss": 0.4954,
      "step": 39365
    },
    {
      "epoch": 1.209289466408626,
      "grad_norm": 0.46364113688468933,
      "learning_rate": 6.789934098487399e-06,
      "loss": 0.4595,
      "step": 39366
    },
    {
      "epoch": 1.2093201855435751,
      "grad_norm": 0.3801162838935852,
      "learning_rate": 6.789476401405328e-06,
      "loss": 0.5009,
      "step": 39367
    },
    {
      "epoch": 1.2093509046785242,
      "grad_norm": 0.39384058117866516,
      "learning_rate": 6.789018711821662e-06,
      "loss": 0.4354,
      "step": 39368
    },
    {
      "epoch": 1.2093816238134734,
      "grad_norm": 0.3781415820121765,
      "learning_rate": 6.788561029737464e-06,
      "loss": 0.4406,
      "step": 39369
    },
    {
      "epoch": 1.2094123429484225,
      "grad_norm": 0.4221196472644806,
      "learning_rate": 6.788103355153809e-06,
      "loss": 0.4107,
      "step": 39370
    },
    {
      "epoch": 1.2094430620833718,
      "grad_norm": 0.4177965819835663,
      "learning_rate": 6.78764568807176e-06,
      "loss": 0.4766,
      "step": 39371
    },
    {
      "epoch": 1.209473781218321,
      "grad_norm": 0.4103931486606598,
      "learning_rate": 6.787188028492392e-06,
      "loss": 0.4555,
      "step": 39372
    },
    {
      "epoch": 1.20950450035327,
      "grad_norm": 0.4048985540866852,
      "learning_rate": 6.786730376416768e-06,
      "loss": 0.4713,
      "step": 39373
    },
    {
      "epoch": 1.2095352194882192,
      "grad_norm": 0.3917410671710968,
      "learning_rate": 6.786272731845962e-06,
      "loss": 0.4997,
      "step": 39374
    },
    {
      "epoch": 1.2095659386231683,
      "grad_norm": 0.42860662937164307,
      "learning_rate": 6.785815094781038e-06,
      "loss": 0.4371,
      "step": 39375
    },
    {
      "epoch": 1.2095966577581176,
      "grad_norm": 0.41743341088294983,
      "learning_rate": 6.785357465223068e-06,
      "loss": 0.46,
      "step": 39376
    },
    {
      "epoch": 1.2096273768930668,
      "grad_norm": 0.41282105445861816,
      "learning_rate": 6.784899843173121e-06,
      "loss": 0.5444,
      "step": 39377
    },
    {
      "epoch": 1.2096580960280159,
      "grad_norm": 0.4111522138118744,
      "learning_rate": 6.7844422286322644e-06,
      "loss": 0.5507,
      "step": 39378
    },
    {
      "epoch": 1.209688815162965,
      "grad_norm": 0.45998573303222656,
      "learning_rate": 6.783984621601569e-06,
      "loss": 0.5134,
      "step": 39379
    },
    {
      "epoch": 1.2097195342979141,
      "grad_norm": 0.38719555735588074,
      "learning_rate": 6.783527022082099e-06,
      "loss": 0.5788,
      "step": 39380
    },
    {
      "epoch": 1.2097502534328632,
      "grad_norm": 0.393048495054245,
      "learning_rate": 6.78306943007493e-06,
      "loss": 0.4593,
      "step": 39381
    },
    {
      "epoch": 1.2097809725678126,
      "grad_norm": 0.35512298345565796,
      "learning_rate": 6.7826118455811245e-06,
      "loss": 0.4327,
      "step": 39382
    },
    {
      "epoch": 1.2098116917027617,
      "grad_norm": 0.37308043241500854,
      "learning_rate": 6.782154268601757e-06,
      "loss": 0.4518,
      "step": 39383
    },
    {
      "epoch": 1.2098424108377108,
      "grad_norm": 0.3931298553943634,
      "learning_rate": 6.7816966991378874e-06,
      "loss": 0.4919,
      "step": 39384
    },
    {
      "epoch": 1.20987312997266,
      "grad_norm": 0.39394888281822205,
      "learning_rate": 6.781239137190596e-06,
      "loss": 0.4789,
      "step": 39385
    },
    {
      "epoch": 1.209903849107609,
      "grad_norm": 0.3736456036567688,
      "learning_rate": 6.78078158276094e-06,
      "loss": 0.4895,
      "step": 39386
    },
    {
      "epoch": 1.2099345682425584,
      "grad_norm": 0.3865259885787964,
      "learning_rate": 6.7803240358499986e-06,
      "loss": 0.4716,
      "step": 39387
    },
    {
      "epoch": 1.2099652873775075,
      "grad_norm": 0.36823272705078125,
      "learning_rate": 6.7798664964588315e-06,
      "loss": 0.5533,
      "step": 39388
    },
    {
      "epoch": 1.2099960065124566,
      "grad_norm": 0.387874960899353,
      "learning_rate": 6.779408964588514e-06,
      "loss": 0.4614,
      "step": 39389
    },
    {
      "epoch": 1.2100267256474058,
      "grad_norm": 0.3798202872276306,
      "learning_rate": 6.778951440240109e-06,
      "loss": 0.4817,
      "step": 39390
    },
    {
      "epoch": 1.2100574447823549,
      "grad_norm": 0.4484778642654419,
      "learning_rate": 6.778493923414688e-06,
      "loss": 0.4604,
      "step": 39391
    },
    {
      "epoch": 1.210088163917304,
      "grad_norm": 0.42543020844459534,
      "learning_rate": 6.778036414113321e-06,
      "loss": 0.3996,
      "step": 39392
    },
    {
      "epoch": 1.2101188830522531,
      "grad_norm": 0.41378337144851685,
      "learning_rate": 6.777578912337071e-06,
      "loss": 0.5271,
      "step": 39393
    },
    {
      "epoch": 1.2101496021872025,
      "grad_norm": 0.3887094259262085,
      "learning_rate": 6.777121418087016e-06,
      "loss": 0.4906,
      "step": 39394
    },
    {
      "epoch": 1.2101803213221516,
      "grad_norm": 0.36421144008636475,
      "learning_rate": 6.776663931364216e-06,
      "loss": 0.4656,
      "step": 39395
    },
    {
      "epoch": 1.2102110404571007,
      "grad_norm": 0.4687268137931824,
      "learning_rate": 6.776206452169744e-06,
      "loss": 0.4837,
      "step": 39396
    },
    {
      "epoch": 1.2102417595920498,
      "grad_norm": 0.41933944821357727,
      "learning_rate": 6.775748980504665e-06,
      "loss": 0.3787,
      "step": 39397
    },
    {
      "epoch": 1.2102724787269992,
      "grad_norm": 0.42018643021583557,
      "learning_rate": 6.775291516370052e-06,
      "loss": 0.5357,
      "step": 39398
    },
    {
      "epoch": 1.2103031978619483,
      "grad_norm": 0.4204961657524109,
      "learning_rate": 6.774834059766968e-06,
      "loss": 0.4673,
      "step": 39399
    },
    {
      "epoch": 1.2103339169968974,
      "grad_norm": 0.3865715265274048,
      "learning_rate": 6.774376610696487e-06,
      "loss": 0.4882,
      "step": 39400
    },
    {
      "epoch": 1.2103646361318465,
      "grad_norm": 0.40245047211647034,
      "learning_rate": 6.7739191691596725e-06,
      "loss": 0.4738,
      "step": 39401
    },
    {
      "epoch": 1.2103953552667956,
      "grad_norm": 0.43074896931648254,
      "learning_rate": 6.773461735157596e-06,
      "loss": 0.4461,
      "step": 39402
    },
    {
      "epoch": 1.2104260744017448,
      "grad_norm": 0.42097610235214233,
      "learning_rate": 6.773004308691325e-06,
      "loss": 0.4475,
      "step": 39403
    },
    {
      "epoch": 1.2104567935366939,
      "grad_norm": 0.41287457942962646,
      "learning_rate": 6.772546889761928e-06,
      "loss": 0.5268,
      "step": 39404
    },
    {
      "epoch": 1.2104875126716432,
      "grad_norm": 0.49267423152923584,
      "learning_rate": 6.772089478370473e-06,
      "loss": 0.5554,
      "step": 39405
    },
    {
      "epoch": 1.2105182318065923,
      "grad_norm": 0.3775085210800171,
      "learning_rate": 6.771632074518029e-06,
      "loss": 0.4573,
      "step": 39406
    },
    {
      "epoch": 1.2105489509415415,
      "grad_norm": 0.4139881134033203,
      "learning_rate": 6.771174678205662e-06,
      "loss": 0.4336,
      "step": 39407
    },
    {
      "epoch": 1.2105796700764906,
      "grad_norm": 0.5130407810211182,
      "learning_rate": 6.770717289434444e-06,
      "loss": 0.5359,
      "step": 39408
    },
    {
      "epoch": 1.21061038921144,
      "grad_norm": 0.3748375475406647,
      "learning_rate": 6.77025990820544e-06,
      "loss": 0.4699,
      "step": 39409
    },
    {
      "epoch": 1.210641108346389,
      "grad_norm": 0.41155460476875305,
      "learning_rate": 6.769802534519721e-06,
      "loss": 0.5456,
      "step": 39410
    },
    {
      "epoch": 1.2106718274813382,
      "grad_norm": 0.3803104758262634,
      "learning_rate": 6.769345168378352e-06,
      "loss": 0.4515,
      "step": 39411
    },
    {
      "epoch": 1.2107025466162873,
      "grad_norm": 0.38341233134269714,
      "learning_rate": 6.768887809782403e-06,
      "loss": 0.4758,
      "step": 39412
    },
    {
      "epoch": 1.2107332657512364,
      "grad_norm": 0.35982877016067505,
      "learning_rate": 6.768430458732944e-06,
      "loss": 0.4602,
      "step": 39413
    },
    {
      "epoch": 1.2107639848861855,
      "grad_norm": 0.40577733516693115,
      "learning_rate": 6.767973115231039e-06,
      "loss": 0.546,
      "step": 39414
    },
    {
      "epoch": 1.2107947040211346,
      "grad_norm": 0.3867928683757782,
      "learning_rate": 6.7675157792777605e-06,
      "loss": 0.4465,
      "step": 39415
    },
    {
      "epoch": 1.210825423156084,
      "grad_norm": 0.5194929242134094,
      "learning_rate": 6.767058450874173e-06,
      "loss": 0.4754,
      "step": 39416
    },
    {
      "epoch": 1.210856142291033,
      "grad_norm": 0.379557341337204,
      "learning_rate": 6.7666011300213505e-06,
      "loss": 0.4144,
      "step": 39417
    },
    {
      "epoch": 1.2108868614259822,
      "grad_norm": 0.40209120512008667,
      "learning_rate": 6.76614381672035e-06,
      "loss": 0.5318,
      "step": 39418
    },
    {
      "epoch": 1.2109175805609314,
      "grad_norm": 0.47226494550704956,
      "learning_rate": 6.765686510972254e-06,
      "loss": 0.4776,
      "step": 39419
    },
    {
      "epoch": 1.2109482996958805,
      "grad_norm": 0.3739565312862396,
      "learning_rate": 6.765229212778115e-06,
      "loss": 0.431,
      "step": 39420
    },
    {
      "epoch": 1.2109790188308298,
      "grad_norm": 0.41738998889923096,
      "learning_rate": 6.764771922139017e-06,
      "loss": 0.4762,
      "step": 39421
    },
    {
      "epoch": 1.211009737965779,
      "grad_norm": 0.38213875889778137,
      "learning_rate": 6.7643146390560135e-06,
      "loss": 0.4515,
      "step": 39422
    },
    {
      "epoch": 1.211040457100728,
      "grad_norm": 0.39540374279022217,
      "learning_rate": 6.763857363530185e-06,
      "loss": 0.5335,
      "step": 39423
    },
    {
      "epoch": 1.2110711762356772,
      "grad_norm": 0.4238554537296295,
      "learning_rate": 6.763400095562589e-06,
      "loss": 0.5098,
      "step": 39424
    },
    {
      "epoch": 1.2111018953706263,
      "grad_norm": 0.38743096590042114,
      "learning_rate": 6.762942835154301e-06,
      "loss": 0.4828,
      "step": 39425
    },
    {
      "epoch": 1.2111326145055754,
      "grad_norm": 0.4270751178264618,
      "learning_rate": 6.762485582306384e-06,
      "loss": 0.4588,
      "step": 39426
    },
    {
      "epoch": 1.2111633336405248,
      "grad_norm": 0.3982330560684204,
      "learning_rate": 6.76202833701991e-06,
      "loss": 0.5342,
      "step": 39427
    },
    {
      "epoch": 1.2111940527754739,
      "grad_norm": 0.3717980682849884,
      "learning_rate": 6.761571099295942e-06,
      "loss": 0.4849,
      "step": 39428
    },
    {
      "epoch": 1.211224771910423,
      "grad_norm": 0.39780211448669434,
      "learning_rate": 6.761113869135554e-06,
      "loss": 0.4798,
      "step": 39429
    },
    {
      "epoch": 1.2112554910453721,
      "grad_norm": 0.469818115234375,
      "learning_rate": 6.760656646539809e-06,
      "loss": 0.4592,
      "step": 39430
    },
    {
      "epoch": 1.2112862101803212,
      "grad_norm": 0.4381217360496521,
      "learning_rate": 6.760199431509776e-06,
      "loss": 0.3797,
      "step": 39431
    },
    {
      "epoch": 1.2113169293152706,
      "grad_norm": 0.387375146150589,
      "learning_rate": 6.759742224046526e-06,
      "loss": 0.5229,
      "step": 39432
    },
    {
      "epoch": 1.2113476484502197,
      "grad_norm": 0.3784997761249542,
      "learning_rate": 6.759285024151121e-06,
      "loss": 0.5153,
      "step": 39433
    },
    {
      "epoch": 1.2113783675851688,
      "grad_norm": 0.41773518919944763,
      "learning_rate": 6.758827831824636e-06,
      "loss": 0.5193,
      "step": 39434
    },
    {
      "epoch": 1.211409086720118,
      "grad_norm": 0.41510388255119324,
      "learning_rate": 6.7583706470681306e-06,
      "loss": 0.5154,
      "step": 39435
    },
    {
      "epoch": 1.211439805855067,
      "grad_norm": 0.3589208424091339,
      "learning_rate": 6.757913469882682e-06,
      "loss": 0.4911,
      "step": 39436
    },
    {
      "epoch": 1.2114705249900162,
      "grad_norm": 0.37953031063079834,
      "learning_rate": 6.757456300269349e-06,
      "loss": 0.5118,
      "step": 39437
    },
    {
      "epoch": 1.2115012441249655,
      "grad_norm": 0.40071552991867065,
      "learning_rate": 6.756999138229205e-06,
      "loss": 0.5098,
      "step": 39438
    },
    {
      "epoch": 1.2115319632599146,
      "grad_norm": 0.4827546775341034,
      "learning_rate": 6.756541983763315e-06,
      "loss": 0.5283,
      "step": 39439
    },
    {
      "epoch": 1.2115626823948638,
      "grad_norm": 0.4874029755592346,
      "learning_rate": 6.75608483687275e-06,
      "loss": 0.5046,
      "step": 39440
    },
    {
      "epoch": 1.2115934015298129,
      "grad_norm": 0.38430577516555786,
      "learning_rate": 6.755627697558571e-06,
      "loss": 0.5023,
      "step": 39441
    },
    {
      "epoch": 1.211624120664762,
      "grad_norm": 0.4322763681411743,
      "learning_rate": 6.755170565821855e-06,
      "loss": 0.4784,
      "step": 39442
    },
    {
      "epoch": 1.2116548397997113,
      "grad_norm": 0.40555083751678467,
      "learning_rate": 6.75471344166366e-06,
      "loss": 0.4429,
      "step": 39443
    },
    {
      "epoch": 1.2116855589346605,
      "grad_norm": 0.3784549832344055,
      "learning_rate": 6.754256325085062e-06,
      "loss": 0.4682,
      "step": 39444
    },
    {
      "epoch": 1.2117162780696096,
      "grad_norm": 0.40951812267303467,
      "learning_rate": 6.753799216087124e-06,
      "loss": 0.4981,
      "step": 39445
    },
    {
      "epoch": 1.2117469972045587,
      "grad_norm": 0.44148439168930054,
      "learning_rate": 6.753342114670917e-06,
      "loss": 0.4778,
      "step": 39446
    },
    {
      "epoch": 1.2117777163395078,
      "grad_norm": 0.39066216349601746,
      "learning_rate": 6.752885020837501e-06,
      "loss": 0.4227,
      "step": 39447
    },
    {
      "epoch": 1.211808435474457,
      "grad_norm": 0.39199188351631165,
      "learning_rate": 6.752427934587951e-06,
      "loss": 0.4687,
      "step": 39448
    },
    {
      "epoch": 1.2118391546094063,
      "grad_norm": 0.45542386174201965,
      "learning_rate": 6.751970855923334e-06,
      "loss": 0.6052,
      "step": 39449
    },
    {
      "epoch": 1.2118698737443554,
      "grad_norm": 0.3950277268886566,
      "learning_rate": 6.751513784844714e-06,
      "loss": 0.4637,
      "step": 39450
    },
    {
      "epoch": 1.2119005928793045,
      "grad_norm": 0.6061893105506897,
      "learning_rate": 6.7510567213531616e-06,
      "loss": 0.4835,
      "step": 39451
    },
    {
      "epoch": 1.2119313120142536,
      "grad_norm": 0.4218772053718567,
      "learning_rate": 6.750599665449743e-06,
      "loss": 0.442,
      "step": 39452
    },
    {
      "epoch": 1.2119620311492028,
      "grad_norm": 0.37543338537216187,
      "learning_rate": 6.7501426171355285e-06,
      "loss": 0.5115,
      "step": 39453
    },
    {
      "epoch": 1.211992750284152,
      "grad_norm": 0.40089020133018494,
      "learning_rate": 6.749685576411578e-06,
      "loss": 0.4788,
      "step": 39454
    },
    {
      "epoch": 1.2120234694191012,
      "grad_norm": 0.3867103159427643,
      "learning_rate": 6.749228543278968e-06,
      "loss": 0.5102,
      "step": 39455
    },
    {
      "epoch": 1.2120541885540503,
      "grad_norm": 0.4053439199924469,
      "learning_rate": 6.748771517738757e-06,
      "loss": 0.3765,
      "step": 39456
    },
    {
      "epoch": 1.2120849076889995,
      "grad_norm": 0.4317619502544403,
      "learning_rate": 6.748314499792024e-06,
      "loss": 0.4977,
      "step": 39457
    },
    {
      "epoch": 1.2121156268239486,
      "grad_norm": 0.38546445965766907,
      "learning_rate": 6.747857489439823e-06,
      "loss": 0.4463,
      "step": 39458
    },
    {
      "epoch": 1.2121463459588977,
      "grad_norm": 0.37937673926353455,
      "learning_rate": 6.747400486683231e-06,
      "loss": 0.4375,
      "step": 39459
    },
    {
      "epoch": 1.212177065093847,
      "grad_norm": 0.43706122040748596,
      "learning_rate": 6.746943491523312e-06,
      "loss": 0.5196,
      "step": 39460
    },
    {
      "epoch": 1.2122077842287962,
      "grad_norm": 0.4393773376941681,
      "learning_rate": 6.746486503961134e-06,
      "loss": 0.4303,
      "step": 39461
    },
    {
      "epoch": 1.2122385033637453,
      "grad_norm": 0.4100397527217865,
      "learning_rate": 6.746029523997762e-06,
      "loss": 0.4668,
      "step": 39462
    },
    {
      "epoch": 1.2122692224986944,
      "grad_norm": 0.5901340246200562,
      "learning_rate": 6.745572551634267e-06,
      "loss": 0.5264,
      "step": 39463
    },
    {
      "epoch": 1.2122999416336435,
      "grad_norm": 0.37779197096824646,
      "learning_rate": 6.745115586871714e-06,
      "loss": 0.4905,
      "step": 39464
    },
    {
      "epoch": 1.2123306607685929,
      "grad_norm": 0.42460131645202637,
      "learning_rate": 6.744658629711173e-06,
      "loss": 0.3977,
      "step": 39465
    },
    {
      "epoch": 1.212361379903542,
      "grad_norm": 0.422417014837265,
      "learning_rate": 6.744201680153706e-06,
      "loss": 0.4957,
      "step": 39466
    },
    {
      "epoch": 1.212392099038491,
      "grad_norm": 0.39975276589393616,
      "learning_rate": 6.743744738200384e-06,
      "loss": 0.524,
      "step": 39467
    },
    {
      "epoch": 1.2124228181734402,
      "grad_norm": 0.49444177746772766,
      "learning_rate": 6.743287803852275e-06,
      "loss": 0.5097,
      "step": 39468
    },
    {
      "epoch": 1.2124535373083893,
      "grad_norm": 0.42001351714134216,
      "learning_rate": 6.742830877110442e-06,
      "loss": 0.5008,
      "step": 39469
    },
    {
      "epoch": 1.2124842564433385,
      "grad_norm": 0.38033631443977356,
      "learning_rate": 6.7423739579759585e-06,
      "loss": 0.4529,
      "step": 39470
    },
    {
      "epoch": 1.2125149755782878,
      "grad_norm": 0.4089433550834656,
      "learning_rate": 6.741917046449886e-06,
      "loss": 0.4751,
      "step": 39471
    },
    {
      "epoch": 1.212545694713237,
      "grad_norm": 0.3749157786369324,
      "learning_rate": 6.7414601425332955e-06,
      "loss": 0.5139,
      "step": 39472
    },
    {
      "epoch": 1.212576413848186,
      "grad_norm": 0.3647174835205078,
      "learning_rate": 6.74100324622725e-06,
      "loss": 0.4982,
      "step": 39473
    },
    {
      "epoch": 1.2126071329831352,
      "grad_norm": 0.4233056902885437,
      "learning_rate": 6.7405463575328214e-06,
      "loss": 0.4803,
      "step": 39474
    },
    {
      "epoch": 1.2126378521180843,
      "grad_norm": 0.36392855644226074,
      "learning_rate": 6.7400894764510726e-06,
      "loss": 0.5428,
      "step": 39475
    },
    {
      "epoch": 1.2126685712530336,
      "grad_norm": 0.42813339829444885,
      "learning_rate": 6.739632602983074e-06,
      "loss": 0.5084,
      "step": 39476
    },
    {
      "epoch": 1.2126992903879827,
      "grad_norm": 0.37970563769340515,
      "learning_rate": 6.739175737129889e-06,
      "loss": 0.4714,
      "step": 39477
    },
    {
      "epoch": 1.2127300095229319,
      "grad_norm": 0.3535830080509186,
      "learning_rate": 6.738718878892589e-06,
      "loss": 0.504,
      "step": 39478
    },
    {
      "epoch": 1.212760728657881,
      "grad_norm": 0.41109228134155273,
      "learning_rate": 6.7382620282722375e-06,
      "loss": 0.5028,
      "step": 39479
    },
    {
      "epoch": 1.21279144779283,
      "grad_norm": 0.3911581337451935,
      "learning_rate": 6.737805185269907e-06,
      "loss": 0.4318,
      "step": 39480
    },
    {
      "epoch": 1.2128221669277792,
      "grad_norm": 0.43181487917900085,
      "learning_rate": 6.7373483498866536e-06,
      "loss": 0.4841,
      "step": 39481
    },
    {
      "epoch": 1.2128528860627286,
      "grad_norm": 0.41498202085494995,
      "learning_rate": 6.736891522123556e-06,
      "loss": 0.5176,
      "step": 39482
    },
    {
      "epoch": 1.2128836051976777,
      "grad_norm": 0.4382219910621643,
      "learning_rate": 6.736434701981671e-06,
      "loss": 0.539,
      "step": 39483
    },
    {
      "epoch": 1.2129143243326268,
      "grad_norm": 0.3738967180252075,
      "learning_rate": 6.735977889462078e-06,
      "loss": 0.4504,
      "step": 39484
    },
    {
      "epoch": 1.212945043467576,
      "grad_norm": 0.40183937549591064,
      "learning_rate": 6.735521084565829e-06,
      "loss": 0.4281,
      "step": 39485
    },
    {
      "epoch": 1.212975762602525,
      "grad_norm": 0.41209346055984497,
      "learning_rate": 6.735064287294001e-06,
      "loss": 0.4226,
      "step": 39486
    },
    {
      "epoch": 1.2130064817374744,
      "grad_norm": 0.37974387407302856,
      "learning_rate": 6.734607497647663e-06,
      "loss": 0.4567,
      "step": 39487
    },
    {
      "epoch": 1.2130372008724235,
      "grad_norm": 0.4221791923046112,
      "learning_rate": 6.73415071562787e-06,
      "loss": 0.4892,
      "step": 39488
    },
    {
      "epoch": 1.2130679200073726,
      "grad_norm": 0.3795790374279022,
      "learning_rate": 6.7336939412357025e-06,
      "loss": 0.4606,
      "step": 39489
    },
    {
      "epoch": 1.2130986391423217,
      "grad_norm": 0.4759843647480011,
      "learning_rate": 6.7332371744722155e-06,
      "loss": 0.5502,
      "step": 39490
    },
    {
      "epoch": 1.2131293582772709,
      "grad_norm": 0.4043831527233124,
      "learning_rate": 6.732780415338487e-06,
      "loss": 0.4951,
      "step": 39491
    },
    {
      "epoch": 1.21316007741222,
      "grad_norm": 0.3718363046646118,
      "learning_rate": 6.732323663835572e-06,
      "loss": 0.4582,
      "step": 39492
    },
    {
      "epoch": 1.2131907965471693,
      "grad_norm": 0.40380987524986267,
      "learning_rate": 6.731866919964549e-06,
      "loss": 0.4228,
      "step": 39493
    },
    {
      "epoch": 1.2132215156821184,
      "grad_norm": 0.41780829429626465,
      "learning_rate": 6.7314101837264746e-06,
      "loss": 0.4542,
      "step": 39494
    },
    {
      "epoch": 1.2132522348170676,
      "grad_norm": 0.39646872878074646,
      "learning_rate": 6.730953455122422e-06,
      "loss": 0.4472,
      "step": 39495
    },
    {
      "epoch": 1.2132829539520167,
      "grad_norm": 0.46241435408592224,
      "learning_rate": 6.730496734153456e-06,
      "loss": 0.5114,
      "step": 39496
    },
    {
      "epoch": 1.2133136730869658,
      "grad_norm": 0.4139566719532013,
      "learning_rate": 6.730040020820643e-06,
      "loss": 0.4866,
      "step": 39497
    },
    {
      "epoch": 1.2133443922219151,
      "grad_norm": 0.3639732599258423,
      "learning_rate": 6.729583315125048e-06,
      "loss": 0.3569,
      "step": 39498
    },
    {
      "epoch": 1.2133751113568643,
      "grad_norm": 0.37355688214302063,
      "learning_rate": 6.729126617067743e-06,
      "loss": 0.4794,
      "step": 39499
    },
    {
      "epoch": 1.2134058304918134,
      "grad_norm": 0.4095483124256134,
      "learning_rate": 6.728669926649788e-06,
      "loss": 0.4946,
      "step": 39500
    },
    {
      "epoch": 1.2134365496267625,
      "grad_norm": 0.427935928106308,
      "learning_rate": 6.728213243872255e-06,
      "loss": 0.5853,
      "step": 39501
    },
    {
      "epoch": 1.2134672687617116,
      "grad_norm": 0.38871878385543823,
      "learning_rate": 6.727756568736208e-06,
      "loss": 0.5021,
      "step": 39502
    },
    {
      "epoch": 1.2134979878966607,
      "grad_norm": 0.377618670463562,
      "learning_rate": 6.727299901242712e-06,
      "loss": 0.4862,
      "step": 39503
    },
    {
      "epoch": 1.2135287070316099,
      "grad_norm": 0.4015846252441406,
      "learning_rate": 6.726843241392837e-06,
      "loss": 0.4672,
      "step": 39504
    },
    {
      "epoch": 1.2135594261665592,
      "grad_norm": 0.3776869773864746,
      "learning_rate": 6.726386589187649e-06,
      "loss": 0.4626,
      "step": 39505
    },
    {
      "epoch": 1.2135901453015083,
      "grad_norm": 0.3710155785083771,
      "learning_rate": 6.725929944628214e-06,
      "loss": 0.5265,
      "step": 39506
    },
    {
      "epoch": 1.2136208644364574,
      "grad_norm": 0.4174067974090576,
      "learning_rate": 6.725473307715597e-06,
      "loss": 0.4968,
      "step": 39507
    },
    {
      "epoch": 1.2136515835714066,
      "grad_norm": 0.623245894908905,
      "learning_rate": 6.725016678450868e-06,
      "loss": 0.5419,
      "step": 39508
    },
    {
      "epoch": 1.213682302706356,
      "grad_norm": 0.43619441986083984,
      "learning_rate": 6.724560056835088e-06,
      "loss": 0.4742,
      "step": 39509
    },
    {
      "epoch": 1.213713021841305,
      "grad_norm": 0.3369445204734802,
      "learning_rate": 6.7241034428693295e-06,
      "loss": 0.4443,
      "step": 39510
    },
    {
      "epoch": 1.2137437409762541,
      "grad_norm": 0.4040496051311493,
      "learning_rate": 6.723646836554654e-06,
      "loss": 0.5066,
      "step": 39511
    },
    {
      "epoch": 1.2137744601112033,
      "grad_norm": 0.39801064133644104,
      "learning_rate": 6.723190237892132e-06,
      "loss": 0.4624,
      "step": 39512
    },
    {
      "epoch": 1.2138051792461524,
      "grad_norm": 0.40258434414863586,
      "learning_rate": 6.722733646882826e-06,
      "loss": 0.4596,
      "step": 39513
    },
    {
      "epoch": 1.2138358983811015,
      "grad_norm": 0.42275750637054443,
      "learning_rate": 6.722277063527808e-06,
      "loss": 0.4961,
      "step": 39514
    },
    {
      "epoch": 1.2138666175160506,
      "grad_norm": 0.39540189504623413,
      "learning_rate": 6.7218204878281365e-06,
      "loss": 0.534,
      "step": 39515
    },
    {
      "epoch": 1.213897336651,
      "grad_norm": 0.4147152006626129,
      "learning_rate": 6.721363919784888e-06,
      "loss": 0.4725,
      "step": 39516
    },
    {
      "epoch": 1.213928055785949,
      "grad_norm": 0.36015719175338745,
      "learning_rate": 6.720907359399116e-06,
      "loss": 0.4821,
      "step": 39517
    },
    {
      "epoch": 1.2139587749208982,
      "grad_norm": 0.45409080386161804,
      "learning_rate": 6.720450806671901e-06,
      "loss": 0.4196,
      "step": 39518
    },
    {
      "epoch": 1.2139894940558473,
      "grad_norm": 0.4056028425693512,
      "learning_rate": 6.719994261604295e-06,
      "loss": 0.4368,
      "step": 39519
    },
    {
      "epoch": 1.2140202131907967,
      "grad_norm": 0.4081474542617798,
      "learning_rate": 6.719537724197378e-06,
      "loss": 0.4599,
      "step": 39520
    },
    {
      "epoch": 1.2140509323257458,
      "grad_norm": 0.3801190257072449,
      "learning_rate": 6.719081194452206e-06,
      "loss": 0.4484,
      "step": 39521
    },
    {
      "epoch": 1.214081651460695,
      "grad_norm": 0.42725905776023865,
      "learning_rate": 6.718624672369847e-06,
      "loss": 0.4648,
      "step": 39522
    },
    {
      "epoch": 1.214112370595644,
      "grad_norm": 0.426367849111557,
      "learning_rate": 6.718168157951375e-06,
      "loss": 0.4098,
      "step": 39523
    },
    {
      "epoch": 1.2141430897305932,
      "grad_norm": 0.6899026036262512,
      "learning_rate": 6.717711651197843e-06,
      "loss": 0.4909,
      "step": 39524
    },
    {
      "epoch": 1.2141738088655423,
      "grad_norm": 0.43248051404953003,
      "learning_rate": 6.717255152110333e-06,
      "loss": 0.5289,
      "step": 39525
    },
    {
      "epoch": 1.2142045280004914,
      "grad_norm": 0.39015740156173706,
      "learning_rate": 6.716798660689895e-06,
      "loss": 0.4347,
      "step": 39526
    },
    {
      "epoch": 1.2142352471354407,
      "grad_norm": 0.43029746413230896,
      "learning_rate": 6.7163421769376105e-06,
      "loss": 0.5769,
      "step": 39527
    },
    {
      "epoch": 1.2142659662703899,
      "grad_norm": 0.5151451826095581,
      "learning_rate": 6.715885700854533e-06,
      "loss": 0.49,
      "step": 39528
    },
    {
      "epoch": 1.214296685405339,
      "grad_norm": 0.39563754200935364,
      "learning_rate": 6.715429232441737e-06,
      "loss": 0.4832,
      "step": 39529
    },
    {
      "epoch": 1.214327404540288,
      "grad_norm": 0.38781601190567017,
      "learning_rate": 6.7149727717002825e-06,
      "loss": 0.4851,
      "step": 39530
    },
    {
      "epoch": 1.2143581236752372,
      "grad_norm": 0.4044078290462494,
      "learning_rate": 6.714516318631241e-06,
      "loss": 0.4364,
      "step": 39531
    },
    {
      "epoch": 1.2143888428101866,
      "grad_norm": 0.375384122133255,
      "learning_rate": 6.7140598732356745e-06,
      "loss": 0.4279,
      "step": 39532
    },
    {
      "epoch": 1.2144195619451357,
      "grad_norm": 0.4707833230495453,
      "learning_rate": 6.713603435514651e-06,
      "loss": 0.4656,
      "step": 39533
    },
    {
      "epoch": 1.2144502810800848,
      "grad_norm": 0.3976288139820099,
      "learning_rate": 6.713147005469236e-06,
      "loss": 0.4388,
      "step": 39534
    },
    {
      "epoch": 1.214481000215034,
      "grad_norm": 0.46283698081970215,
      "learning_rate": 6.712690583100497e-06,
      "loss": 0.4625,
      "step": 39535
    },
    {
      "epoch": 1.214511719349983,
      "grad_norm": 0.4323793947696686,
      "learning_rate": 6.712234168409496e-06,
      "loss": 0.4741,
      "step": 39536
    },
    {
      "epoch": 1.2145424384849322,
      "grad_norm": 0.3910820782184601,
      "learning_rate": 6.711777761397304e-06,
      "loss": 0.4568,
      "step": 39537
    },
    {
      "epoch": 1.2145731576198815,
      "grad_norm": 0.41834935545921326,
      "learning_rate": 6.711321362064984e-06,
      "loss": 0.4233,
      "step": 39538
    },
    {
      "epoch": 1.2146038767548306,
      "grad_norm": 0.44748201966285706,
      "learning_rate": 6.710864970413602e-06,
      "loss": 0.4925,
      "step": 39539
    },
    {
      "epoch": 1.2146345958897797,
      "grad_norm": 0.37726593017578125,
      "learning_rate": 6.710408586444226e-06,
      "loss": 0.3916,
      "step": 39540
    },
    {
      "epoch": 1.2146653150247289,
      "grad_norm": 0.40778499841690063,
      "learning_rate": 6.7099522101579185e-06,
      "loss": 0.485,
      "step": 39541
    },
    {
      "epoch": 1.214696034159678,
      "grad_norm": 0.40124043822288513,
      "learning_rate": 6.70949584155575e-06,
      "loss": 0.5215,
      "step": 39542
    },
    {
      "epoch": 1.2147267532946273,
      "grad_norm": 0.4032503664493561,
      "learning_rate": 6.709039480638781e-06,
      "loss": 0.5563,
      "step": 39543
    },
    {
      "epoch": 1.2147574724295764,
      "grad_norm": 0.3850254714488983,
      "learning_rate": 6.708583127408083e-06,
      "loss": 0.4245,
      "step": 39544
    },
    {
      "epoch": 1.2147881915645256,
      "grad_norm": 0.4006176292896271,
      "learning_rate": 6.708126781864716e-06,
      "loss": 0.4692,
      "step": 39545
    },
    {
      "epoch": 1.2148189106994747,
      "grad_norm": 0.3989940285682678,
      "learning_rate": 6.707670444009752e-06,
      "loss": 0.4863,
      "step": 39546
    },
    {
      "epoch": 1.2148496298344238,
      "grad_norm": 0.40359988808631897,
      "learning_rate": 6.70721411384425e-06,
      "loss": 0.4693,
      "step": 39547
    },
    {
      "epoch": 1.214880348969373,
      "grad_norm": 0.3903033137321472,
      "learning_rate": 6.706757791369282e-06,
      "loss": 0.4416,
      "step": 39548
    },
    {
      "epoch": 1.2149110681043223,
      "grad_norm": 0.42400357127189636,
      "learning_rate": 6.70630147658591e-06,
      "loss": 0.5381,
      "step": 39549
    },
    {
      "epoch": 1.2149417872392714,
      "grad_norm": 0.3887423276901245,
      "learning_rate": 6.705845169495205e-06,
      "loss": 0.4956,
      "step": 39550
    },
    {
      "epoch": 1.2149725063742205,
      "grad_norm": 0.37290725111961365,
      "learning_rate": 6.705388870098222e-06,
      "loss": 0.5019,
      "step": 39551
    },
    {
      "epoch": 1.2150032255091696,
      "grad_norm": 0.3924875855445862,
      "learning_rate": 6.70493257839604e-06,
      "loss": 0.4683,
      "step": 39552
    },
    {
      "epoch": 1.2150339446441187,
      "grad_norm": 0.3848816752433777,
      "learning_rate": 6.704476294389711e-06,
      "loss": 0.4819,
      "step": 39553
    },
    {
      "epoch": 1.215064663779068,
      "grad_norm": 0.3807603716850281,
      "learning_rate": 6.704020018080315e-06,
      "loss": 0.4064,
      "step": 39554
    },
    {
      "epoch": 1.2150953829140172,
      "grad_norm": 0.41309162974357605,
      "learning_rate": 6.703563749468904e-06,
      "loss": 0.4642,
      "step": 39555
    },
    {
      "epoch": 1.2151261020489663,
      "grad_norm": 0.40421760082244873,
      "learning_rate": 6.703107488556555e-06,
      "loss": 0.4531,
      "step": 39556
    },
    {
      "epoch": 1.2151568211839154,
      "grad_norm": 0.4289077818393707,
      "learning_rate": 6.702651235344326e-06,
      "loss": 0.4556,
      "step": 39557
    },
    {
      "epoch": 1.2151875403188646,
      "grad_norm": 0.406501442193985,
      "learning_rate": 6.7021949898332825e-06,
      "loss": 0.5297,
      "step": 39558
    },
    {
      "epoch": 1.2152182594538137,
      "grad_norm": 0.375557005405426,
      "learning_rate": 6.7017387520245e-06,
      "loss": 0.4719,
      "step": 39559
    },
    {
      "epoch": 1.215248978588763,
      "grad_norm": 0.40799480676651,
      "learning_rate": 6.70128252191903e-06,
      "loss": 0.5159,
      "step": 39560
    },
    {
      "epoch": 1.2152796977237121,
      "grad_norm": 0.40838155150413513,
      "learning_rate": 6.700826299517951e-06,
      "loss": 0.4541,
      "step": 39561
    },
    {
      "epoch": 1.2153104168586613,
      "grad_norm": 0.4006117582321167,
      "learning_rate": 6.70037008482232e-06,
      "loss": 0.5103,
      "step": 39562
    },
    {
      "epoch": 1.2153411359936104,
      "grad_norm": 0.4271118938922882,
      "learning_rate": 6.699913877833206e-06,
      "loss": 0.4412,
      "step": 39563
    },
    {
      "epoch": 1.2153718551285595,
      "grad_norm": 0.4086977243423462,
      "learning_rate": 6.699457678551672e-06,
      "loss": 0.4381,
      "step": 39564
    },
    {
      "epoch": 1.2154025742635088,
      "grad_norm": 0.39957359433174133,
      "learning_rate": 6.699001486978787e-06,
      "loss": 0.4754,
      "step": 39565
    },
    {
      "epoch": 1.215433293398458,
      "grad_norm": 0.40153005719184875,
      "learning_rate": 6.6985453031156115e-06,
      "loss": 0.4145,
      "step": 39566
    },
    {
      "epoch": 1.215464012533407,
      "grad_norm": 0.5141119956970215,
      "learning_rate": 6.698089126963216e-06,
      "loss": 0.4323,
      "step": 39567
    },
    {
      "epoch": 1.2154947316683562,
      "grad_norm": 0.4009549617767334,
      "learning_rate": 6.697632958522664e-06,
      "loss": 0.4913,
      "step": 39568
    },
    {
      "epoch": 1.2155254508033053,
      "grad_norm": 0.3957909345626831,
      "learning_rate": 6.697176797795022e-06,
      "loss": 0.474,
      "step": 39569
    },
    {
      "epoch": 1.2155561699382544,
      "grad_norm": 0.4250713586807251,
      "learning_rate": 6.696720644781351e-06,
      "loss": 0.5129,
      "step": 39570
    },
    {
      "epoch": 1.2155868890732038,
      "grad_norm": 0.4049071669578552,
      "learning_rate": 6.696264499482723e-06,
      "loss": 0.5001,
      "step": 39571
    },
    {
      "epoch": 1.215617608208153,
      "grad_norm": 0.4206014573574066,
      "learning_rate": 6.695808361900198e-06,
      "loss": 0.482,
      "step": 39572
    },
    {
      "epoch": 1.215648327343102,
      "grad_norm": 0.42093005776405334,
      "learning_rate": 6.695352232034845e-06,
      "loss": 0.4933,
      "step": 39573
    },
    {
      "epoch": 1.2156790464780511,
      "grad_norm": 0.4645894765853882,
      "learning_rate": 6.6948961098877255e-06,
      "loss": 0.4495,
      "step": 39574
    },
    {
      "epoch": 1.2157097656130003,
      "grad_norm": 0.3992704153060913,
      "learning_rate": 6.694439995459909e-06,
      "loss": 0.5467,
      "step": 39575
    },
    {
      "epoch": 1.2157404847479496,
      "grad_norm": 0.412657231092453,
      "learning_rate": 6.693983888752456e-06,
      "loss": 0.5152,
      "step": 39576
    },
    {
      "epoch": 1.2157712038828987,
      "grad_norm": 0.42589688301086426,
      "learning_rate": 6.693527789766436e-06,
      "loss": 0.4587,
      "step": 39577
    },
    {
      "epoch": 1.2158019230178478,
      "grad_norm": 0.41503167152404785,
      "learning_rate": 6.693071698502914e-06,
      "loss": 0.4887,
      "step": 39578
    },
    {
      "epoch": 1.215832642152797,
      "grad_norm": 0.3841959536075592,
      "learning_rate": 6.692615614962952e-06,
      "loss": 0.4724,
      "step": 39579
    },
    {
      "epoch": 1.215863361287746,
      "grad_norm": 0.3748842477798462,
      "learning_rate": 6.69215953914762e-06,
      "loss": 0.4689,
      "step": 39580
    },
    {
      "epoch": 1.2158940804226952,
      "grad_norm": 0.42740359902381897,
      "learning_rate": 6.691703471057978e-06,
      "loss": 0.4938,
      "step": 39581
    },
    {
      "epoch": 1.2159247995576445,
      "grad_norm": 0.36324769258499146,
      "learning_rate": 6.691247410695094e-06,
      "loss": 0.498,
      "step": 39582
    },
    {
      "epoch": 1.2159555186925937,
      "grad_norm": 0.42871326208114624,
      "learning_rate": 6.690791358060032e-06,
      "loss": 0.5036,
      "step": 39583
    },
    {
      "epoch": 1.2159862378275428,
      "grad_norm": 0.4331163167953491,
      "learning_rate": 6.6903353131538625e-06,
      "loss": 0.5217,
      "step": 39584
    },
    {
      "epoch": 1.216016956962492,
      "grad_norm": 0.43560701608657837,
      "learning_rate": 6.68987927597764e-06,
      "loss": 0.454,
      "step": 39585
    },
    {
      "epoch": 1.216047676097441,
      "grad_norm": 0.3726789951324463,
      "learning_rate": 6.68942324653244e-06,
      "loss": 0.3847,
      "step": 39586
    },
    {
      "epoch": 1.2160783952323904,
      "grad_norm": 0.399172306060791,
      "learning_rate": 6.688967224819318e-06,
      "loss": 0.495,
      "step": 39587
    },
    {
      "epoch": 1.2161091143673395,
      "grad_norm": 0.46975255012512207,
      "learning_rate": 6.688511210839352e-06,
      "loss": 0.4619,
      "step": 39588
    },
    {
      "epoch": 1.2161398335022886,
      "grad_norm": 0.4268970191478729,
      "learning_rate": 6.688055204593591e-06,
      "loss": 0.5634,
      "step": 39589
    },
    {
      "epoch": 1.2161705526372377,
      "grad_norm": 0.6892391443252563,
      "learning_rate": 6.687599206083115e-06,
      "loss": 0.4849,
      "step": 39590
    },
    {
      "epoch": 1.2162012717721868,
      "grad_norm": 0.39431414008140564,
      "learning_rate": 6.68714321530898e-06,
      "loss": 0.4841,
      "step": 39591
    },
    {
      "epoch": 1.216231990907136,
      "grad_norm": 0.396271675825119,
      "learning_rate": 6.6866872322722535e-06,
      "loss": 0.5139,
      "step": 39592
    },
    {
      "epoch": 1.2162627100420853,
      "grad_norm": 0.40527278184890747,
      "learning_rate": 6.6862312569739984e-06,
      "loss": 0.4596,
      "step": 39593
    },
    {
      "epoch": 1.2162934291770344,
      "grad_norm": 0.3891226351261139,
      "learning_rate": 6.685775289415281e-06,
      "loss": 0.4277,
      "step": 39594
    },
    {
      "epoch": 1.2163241483119835,
      "grad_norm": 0.40004509687423706,
      "learning_rate": 6.685319329597172e-06,
      "loss": 0.5256,
      "step": 39595
    },
    {
      "epoch": 1.2163548674469327,
      "grad_norm": 0.6970557570457458,
      "learning_rate": 6.684863377520725e-06,
      "loss": 0.4695,
      "step": 39596
    },
    {
      "epoch": 1.2163855865818818,
      "grad_norm": 0.3859918713569641,
      "learning_rate": 6.6844074331870165e-06,
      "loss": 0.4759,
      "step": 39597
    },
    {
      "epoch": 1.2164163057168311,
      "grad_norm": 0.4254773259162903,
      "learning_rate": 6.683951496597104e-06,
      "loss": 0.4632,
      "step": 39598
    },
    {
      "epoch": 1.2164470248517802,
      "grad_norm": 0.3818497955799103,
      "learning_rate": 6.683495567752055e-06,
      "loss": 0.4978,
      "step": 39599
    },
    {
      "epoch": 1.2164777439867294,
      "grad_norm": 0.3986061215400696,
      "learning_rate": 6.683039646652932e-06,
      "loss": 0.4947,
      "step": 39600
    },
    {
      "epoch": 1.2165084631216785,
      "grad_norm": 0.44222304224967957,
      "learning_rate": 6.682583733300804e-06,
      "loss": 0.4665,
      "step": 39601
    },
    {
      "epoch": 1.2165391822566276,
      "grad_norm": 0.458924263715744,
      "learning_rate": 6.6821278276967305e-06,
      "loss": 0.5415,
      "step": 39602
    },
    {
      "epoch": 1.2165699013915767,
      "grad_norm": 0.38464784622192383,
      "learning_rate": 6.681671929841782e-06,
      "loss": 0.4335,
      "step": 39603
    },
    {
      "epoch": 1.216600620526526,
      "grad_norm": 0.41180479526519775,
      "learning_rate": 6.681216039737018e-06,
      "loss": 0.478,
      "step": 39604
    },
    {
      "epoch": 1.2166313396614752,
      "grad_norm": 0.37557825446128845,
      "learning_rate": 6.6807601573835076e-06,
      "loss": 0.4746,
      "step": 39605
    },
    {
      "epoch": 1.2166620587964243,
      "grad_norm": 0.39651817083358765,
      "learning_rate": 6.6803042827823115e-06,
      "loss": 0.4804,
      "step": 39606
    },
    {
      "epoch": 1.2166927779313734,
      "grad_norm": 0.46818020939826965,
      "learning_rate": 6.679848415934499e-06,
      "loss": 0.4618,
      "step": 39607
    },
    {
      "epoch": 1.2167234970663225,
      "grad_norm": 0.46698153018951416,
      "learning_rate": 6.679392556841131e-06,
      "loss": 0.5066,
      "step": 39608
    },
    {
      "epoch": 1.2167542162012719,
      "grad_norm": 0.4011486768722534,
      "learning_rate": 6.678936705503274e-06,
      "loss": 0.5267,
      "step": 39609
    },
    {
      "epoch": 1.216784935336221,
      "grad_norm": 0.3767476975917816,
      "learning_rate": 6.678480861921992e-06,
      "loss": 0.4419,
      "step": 39610
    },
    {
      "epoch": 1.2168156544711701,
      "grad_norm": 0.40791523456573486,
      "learning_rate": 6.67802502609835e-06,
      "loss": 0.5024,
      "step": 39611
    },
    {
      "epoch": 1.2168463736061192,
      "grad_norm": 0.3951862156391144,
      "learning_rate": 6.677569198033413e-06,
      "loss": 0.453,
      "step": 39612
    },
    {
      "epoch": 1.2168770927410684,
      "grad_norm": 0.41021376848220825,
      "learning_rate": 6.677113377728244e-06,
      "loss": 0.4188,
      "step": 39613
    },
    {
      "epoch": 1.2169078118760175,
      "grad_norm": 0.393354594707489,
      "learning_rate": 6.6766575651839096e-06,
      "loss": 0.4475,
      "step": 39614
    },
    {
      "epoch": 1.2169385310109666,
      "grad_norm": 0.39224720001220703,
      "learning_rate": 6.676201760401473e-06,
      "loss": 0.4565,
      "step": 39615
    },
    {
      "epoch": 1.216969250145916,
      "grad_norm": 0.39576488733291626,
      "learning_rate": 6.675745963382001e-06,
      "loss": 0.4587,
      "step": 39616
    },
    {
      "epoch": 1.216999969280865,
      "grad_norm": 0.3828100860118866,
      "learning_rate": 6.675290174126554e-06,
      "loss": 0.4979,
      "step": 39617
    },
    {
      "epoch": 1.2170306884158142,
      "grad_norm": 0.39058971405029297,
      "learning_rate": 6.6748343926362e-06,
      "loss": 0.4782,
      "step": 39618
    },
    {
      "epoch": 1.2170614075507633,
      "grad_norm": 0.4326542019844055,
      "learning_rate": 6.674378618912003e-06,
      "loss": 0.5075,
      "step": 39619
    },
    {
      "epoch": 1.2170921266857126,
      "grad_norm": 0.444278359413147,
      "learning_rate": 6.6739228529550306e-06,
      "loss": 0.3923,
      "step": 39620
    },
    {
      "epoch": 1.2171228458206618,
      "grad_norm": 0.37417981028556824,
      "learning_rate": 6.673467094766336e-06,
      "loss": 0.5311,
      "step": 39621
    },
    {
      "epoch": 1.217153564955611,
      "grad_norm": 0.3993087410926819,
      "learning_rate": 6.673011344346998e-06,
      "loss": 0.5964,
      "step": 39622
    },
    {
      "epoch": 1.21718428409056,
      "grad_norm": 0.41431498527526855,
      "learning_rate": 6.672555601698068e-06,
      "loss": 0.5744,
      "step": 39623
    },
    {
      "epoch": 1.2172150032255091,
      "grad_norm": 0.46684300899505615,
      "learning_rate": 6.672099866820625e-06,
      "loss": 0.5002,
      "step": 39624
    },
    {
      "epoch": 1.2172457223604582,
      "grad_norm": 0.5607221722602844,
      "learning_rate": 6.671644139715718e-06,
      "loss": 0.4765,
      "step": 39625
    },
    {
      "epoch": 1.2172764414954074,
      "grad_norm": 0.44135063886642456,
      "learning_rate": 6.671188420384422e-06,
      "loss": 0.5043,
      "step": 39626
    },
    {
      "epoch": 1.2173071606303567,
      "grad_norm": 0.3805403411388397,
      "learning_rate": 6.670732708827796e-06,
      "loss": 0.4457,
      "step": 39627
    },
    {
      "epoch": 1.2173378797653058,
      "grad_norm": 0.3999718725681305,
      "learning_rate": 6.670277005046909e-06,
      "loss": 0.5107,
      "step": 39628
    },
    {
      "epoch": 1.217368598900255,
      "grad_norm": 0.43309029936790466,
      "learning_rate": 6.66982130904282e-06,
      "loss": 0.5706,
      "step": 39629
    },
    {
      "epoch": 1.217399318035204,
      "grad_norm": 0.36965468525886536,
      "learning_rate": 6.669365620816598e-06,
      "loss": 0.4421,
      "step": 39630
    },
    {
      "epoch": 1.2174300371701534,
      "grad_norm": 0.42227715253829956,
      "learning_rate": 6.668909940369304e-06,
      "loss": 0.4659,
      "step": 39631
    },
    {
      "epoch": 1.2174607563051025,
      "grad_norm": 0.3798072636127472,
      "learning_rate": 6.668454267702001e-06,
      "loss": 0.4504,
      "step": 39632
    },
    {
      "epoch": 1.2174914754400517,
      "grad_norm": 0.40598416328430176,
      "learning_rate": 6.66799860281576e-06,
      "loss": 0.4759,
      "step": 39633
    },
    {
      "epoch": 1.2175221945750008,
      "grad_norm": 0.37868645787239075,
      "learning_rate": 6.6675429457116385e-06,
      "loss": 0.4963,
      "step": 39634
    },
    {
      "epoch": 1.21755291370995,
      "grad_norm": 0.39861318469047546,
      "learning_rate": 6.667087296390704e-06,
      "loss": 0.4789,
      "step": 39635
    },
    {
      "epoch": 1.217583632844899,
      "grad_norm": 0.4141906797885895,
      "learning_rate": 6.666631654854019e-06,
      "loss": 0.5063,
      "step": 39636
    },
    {
      "epoch": 1.2176143519798481,
      "grad_norm": 0.42100369930267334,
      "learning_rate": 6.66617602110265e-06,
      "loss": 0.445,
      "step": 39637
    },
    {
      "epoch": 1.2176450711147975,
      "grad_norm": 0.4135073721408844,
      "learning_rate": 6.665720395137658e-06,
      "loss": 0.5147,
      "step": 39638
    },
    {
      "epoch": 1.2176757902497466,
      "grad_norm": 0.4347793459892273,
      "learning_rate": 6.665264776960111e-06,
      "loss": 0.5155,
      "step": 39639
    },
    {
      "epoch": 1.2177065093846957,
      "grad_norm": 0.45108872652053833,
      "learning_rate": 6.664809166571069e-06,
      "loss": 0.5501,
      "step": 39640
    },
    {
      "epoch": 1.2177372285196448,
      "grad_norm": 0.4140002429485321,
      "learning_rate": 6.6643535639716e-06,
      "loss": 0.5144,
      "step": 39641
    },
    {
      "epoch": 1.217767947654594,
      "grad_norm": 0.35961347818374634,
      "learning_rate": 6.6638979691627646e-06,
      "loss": 0.5341,
      "step": 39642
    },
    {
      "epoch": 1.2177986667895433,
      "grad_norm": 0.4239404499530792,
      "learning_rate": 6.663442382145631e-06,
      "loss": 0.5241,
      "step": 39643
    },
    {
      "epoch": 1.2178293859244924,
      "grad_norm": 0.4366198778152466,
      "learning_rate": 6.6629868029212565e-06,
      "loss": 0.5061,
      "step": 39644
    },
    {
      "epoch": 1.2178601050594415,
      "grad_norm": 0.43020525574684143,
      "learning_rate": 6.662531231490713e-06,
      "loss": 0.509,
      "step": 39645
    },
    {
      "epoch": 1.2178908241943907,
      "grad_norm": 0.42514529824256897,
      "learning_rate": 6.6620756678550595e-06,
      "loss": 0.4517,
      "step": 39646
    },
    {
      "epoch": 1.2179215433293398,
      "grad_norm": 0.3847354054450989,
      "learning_rate": 6.661620112015361e-06,
      "loss": 0.4985,
      "step": 39647
    },
    {
      "epoch": 1.217952262464289,
      "grad_norm": 0.4102526903152466,
      "learning_rate": 6.661164563972682e-06,
      "loss": 0.5327,
      "step": 39648
    },
    {
      "epoch": 1.2179829815992382,
      "grad_norm": 0.4042055010795593,
      "learning_rate": 6.660709023728086e-06,
      "loss": 0.4552,
      "step": 39649
    },
    {
      "epoch": 1.2180137007341874,
      "grad_norm": 0.39905571937561035,
      "learning_rate": 6.660253491282639e-06,
      "loss": 0.5828,
      "step": 39650
    },
    {
      "epoch": 1.2180444198691365,
      "grad_norm": 0.4056222140789032,
      "learning_rate": 6.659797966637401e-06,
      "loss": 0.4586,
      "step": 39651
    },
    {
      "epoch": 1.2180751390040856,
      "grad_norm": 0.42202523350715637,
      "learning_rate": 6.65934244979344e-06,
      "loss": 0.4839,
      "step": 39652
    },
    {
      "epoch": 1.2181058581390347,
      "grad_norm": 0.36551913619041443,
      "learning_rate": 6.658886940751817e-06,
      "loss": 0.4885,
      "step": 39653
    },
    {
      "epoch": 1.218136577273984,
      "grad_norm": 0.4016847610473633,
      "learning_rate": 6.658431439513601e-06,
      "loss": 0.4848,
      "step": 39654
    },
    {
      "epoch": 1.2181672964089332,
      "grad_norm": 0.3779422342777252,
      "learning_rate": 6.657975946079844e-06,
      "loss": 0.4508,
      "step": 39655
    },
    {
      "epoch": 1.2181980155438823,
      "grad_norm": 0.403660386800766,
      "learning_rate": 6.6575204604516256e-06,
      "loss": 0.4802,
      "step": 39656
    },
    {
      "epoch": 1.2182287346788314,
      "grad_norm": 0.40500566363334656,
      "learning_rate": 6.657064982629995e-06,
      "loss": 0.5093,
      "step": 39657
    },
    {
      "epoch": 1.2182594538137805,
      "grad_norm": 0.44146594405174255,
      "learning_rate": 6.656609512616028e-06,
      "loss": 0.4414,
      "step": 39658
    },
    {
      "epoch": 1.2182901729487297,
      "grad_norm": 0.39536628127098083,
      "learning_rate": 6.656154050410777e-06,
      "loss": 0.4966,
      "step": 39659
    },
    {
      "epoch": 1.218320892083679,
      "grad_norm": 0.42458710074424744,
      "learning_rate": 6.655698596015318e-06,
      "loss": 0.4462,
      "step": 39660
    },
    {
      "epoch": 1.2183516112186281,
      "grad_norm": 0.4093323051929474,
      "learning_rate": 6.6552431494307035e-06,
      "loss": 0.5262,
      "step": 39661
    },
    {
      "epoch": 1.2183823303535772,
      "grad_norm": 0.44811129570007324,
      "learning_rate": 6.6547877106580064e-06,
      "loss": 0.516,
      "step": 39662
    },
    {
      "epoch": 1.2184130494885264,
      "grad_norm": 0.3912271559238434,
      "learning_rate": 6.654332279698282e-06,
      "loss": 0.5129,
      "step": 39663
    },
    {
      "epoch": 1.2184437686234755,
      "grad_norm": 0.4247848391532898,
      "learning_rate": 6.653876856552602e-06,
      "loss": 0.5083,
      "step": 39664
    },
    {
      "epoch": 1.2184744877584248,
      "grad_norm": 0.426126629114151,
      "learning_rate": 6.653421441222023e-06,
      "loss": 0.4088,
      "step": 39665
    },
    {
      "epoch": 1.218505206893374,
      "grad_norm": 0.4558229148387909,
      "learning_rate": 6.652966033707615e-06,
      "loss": 0.5403,
      "step": 39666
    },
    {
      "epoch": 1.218535926028323,
      "grad_norm": 0.3880213499069214,
      "learning_rate": 6.652510634010436e-06,
      "loss": 0.5043,
      "step": 39667
    },
    {
      "epoch": 1.2185666451632722,
      "grad_norm": 0.4008655250072479,
      "learning_rate": 6.652055242131552e-06,
      "loss": 0.5092,
      "step": 39668
    },
    {
      "epoch": 1.2185973642982213,
      "grad_norm": 0.41232311725616455,
      "learning_rate": 6.651599858072028e-06,
      "loss": 0.4611,
      "step": 39669
    },
    {
      "epoch": 1.2186280834331704,
      "grad_norm": 0.40368255972862244,
      "learning_rate": 6.651144481832926e-06,
      "loss": 0.4691,
      "step": 39670
    },
    {
      "epoch": 1.2186588025681198,
      "grad_norm": 0.42182785272598267,
      "learning_rate": 6.650689113415312e-06,
      "loss": 0.5038,
      "step": 39671
    },
    {
      "epoch": 1.2186895217030689,
      "grad_norm": 0.3898964822292328,
      "learning_rate": 6.6502337528202454e-06,
      "loss": 0.5295,
      "step": 39672
    },
    {
      "epoch": 1.218720240838018,
      "grad_norm": 0.4149148464202881,
      "learning_rate": 6.649778400048792e-06,
      "loss": 0.483,
      "step": 39673
    },
    {
      "epoch": 1.2187509599729671,
      "grad_norm": 0.3682872951030731,
      "learning_rate": 6.649323055102015e-06,
      "loss": 0.4803,
      "step": 39674
    },
    {
      "epoch": 1.2187816791079162,
      "grad_norm": 0.4238584637641907,
      "learning_rate": 6.64886771798098e-06,
      "loss": 0.5079,
      "step": 39675
    },
    {
      "epoch": 1.2188123982428656,
      "grad_norm": 0.45524099469184875,
      "learning_rate": 6.648412388686745e-06,
      "loss": 0.4893,
      "step": 39676
    },
    {
      "epoch": 1.2188431173778147,
      "grad_norm": 0.3874931335449219,
      "learning_rate": 6.647957067220381e-06,
      "loss": 0.5084,
      "step": 39677
    },
    {
      "epoch": 1.2188738365127638,
      "grad_norm": 0.4158560037612915,
      "learning_rate": 6.6475017535829435e-06,
      "loss": 0.4343,
      "step": 39678
    },
    {
      "epoch": 1.218904555647713,
      "grad_norm": 0.3654296398162842,
      "learning_rate": 6.647046447775502e-06,
      "loss": 0.5322,
      "step": 39679
    },
    {
      "epoch": 1.218935274782662,
      "grad_norm": 0.4025120139122009,
      "learning_rate": 6.646591149799116e-06,
      "loss": 0.4892,
      "step": 39680
    },
    {
      "epoch": 1.2189659939176112,
      "grad_norm": 0.4166220426559448,
      "learning_rate": 6.646135859654854e-06,
      "loss": 0.5251,
      "step": 39681
    },
    {
      "epoch": 1.2189967130525605,
      "grad_norm": 0.3891931474208832,
      "learning_rate": 6.645680577343772e-06,
      "loss": 0.4184,
      "step": 39682
    },
    {
      "epoch": 1.2190274321875096,
      "grad_norm": 0.37431398034095764,
      "learning_rate": 6.6452253028669425e-06,
      "loss": 0.4546,
      "step": 39683
    },
    {
      "epoch": 1.2190581513224588,
      "grad_norm": 0.38512122631073,
      "learning_rate": 6.644770036225416e-06,
      "loss": 0.5341,
      "step": 39684
    },
    {
      "epoch": 1.2190888704574079,
      "grad_norm": 0.3955760598182678,
      "learning_rate": 6.644314777420266e-06,
      "loss": 0.5784,
      "step": 39685
    },
    {
      "epoch": 1.219119589592357,
      "grad_norm": 0.4278357923030853,
      "learning_rate": 6.643859526452556e-06,
      "loss": 0.5266,
      "step": 39686
    },
    {
      "epoch": 1.2191503087273063,
      "grad_norm": 0.38187089562416077,
      "learning_rate": 6.643404283323345e-06,
      "loss": 0.4427,
      "step": 39687
    },
    {
      "epoch": 1.2191810278622555,
      "grad_norm": 0.37243685126304626,
      "learning_rate": 6.642949048033699e-06,
      "loss": 0.5291,
      "step": 39688
    },
    {
      "epoch": 1.2192117469972046,
      "grad_norm": 0.3852686285972595,
      "learning_rate": 6.642493820584678e-06,
      "loss": 0.3958,
      "step": 39689
    },
    {
      "epoch": 1.2192424661321537,
      "grad_norm": 0.39374321699142456,
      "learning_rate": 6.642038600977351e-06,
      "loss": 0.4905,
      "step": 39690
    },
    {
      "epoch": 1.2192731852671028,
      "grad_norm": 0.4324414134025574,
      "learning_rate": 6.641583389212771e-06,
      "loss": 0.5183,
      "step": 39691
    },
    {
      "epoch": 1.219303904402052,
      "grad_norm": 0.42230796813964844,
      "learning_rate": 6.641128185292014e-06,
      "loss": 0.5059,
      "step": 39692
    },
    {
      "epoch": 1.2193346235370013,
      "grad_norm": 0.4086543917655945,
      "learning_rate": 6.640672989216131e-06,
      "loss": 0.5022,
      "step": 39693
    },
    {
      "epoch": 1.2193653426719504,
      "grad_norm": 0.40014344453811646,
      "learning_rate": 6.640217800986196e-06,
      "loss": 0.4684,
      "step": 39694
    },
    {
      "epoch": 1.2193960618068995,
      "grad_norm": 0.346453458070755,
      "learning_rate": 6.639762620603263e-06,
      "loss": 0.4262,
      "step": 39695
    },
    {
      "epoch": 1.2194267809418486,
      "grad_norm": 0.37807580828666687,
      "learning_rate": 6.639307448068401e-06,
      "loss": 0.4936,
      "step": 39696
    },
    {
      "epoch": 1.2194575000767978,
      "grad_norm": 0.38756346702575684,
      "learning_rate": 6.638852283382671e-06,
      "loss": 0.3646,
      "step": 39697
    },
    {
      "epoch": 1.219488219211747,
      "grad_norm": 0.4130900204181671,
      "learning_rate": 6.638397126547136e-06,
      "loss": 0.5005,
      "step": 39698
    },
    {
      "epoch": 1.2195189383466962,
      "grad_norm": 0.4607918858528137,
      "learning_rate": 6.637941977562858e-06,
      "loss": 0.4306,
      "step": 39699
    },
    {
      "epoch": 1.2195496574816453,
      "grad_norm": 0.39436402916908264,
      "learning_rate": 6.637486836430904e-06,
      "loss": 0.4734,
      "step": 39700
    },
    {
      "epoch": 1.2195803766165945,
      "grad_norm": 0.42604339122772217,
      "learning_rate": 6.637031703152333e-06,
      "loss": 0.5043,
      "step": 39701
    },
    {
      "epoch": 1.2196110957515436,
      "grad_norm": 0.38318321108818054,
      "learning_rate": 6.636576577728209e-06,
      "loss": 0.376,
      "step": 39702
    },
    {
      "epoch": 1.2196418148864927,
      "grad_norm": 0.43484705686569214,
      "learning_rate": 6.636121460159595e-06,
      "loss": 0.5194,
      "step": 39703
    },
    {
      "epoch": 1.219672534021442,
      "grad_norm": 0.3860880136489868,
      "learning_rate": 6.6356663504475535e-06,
      "loss": 0.4992,
      "step": 39704
    },
    {
      "epoch": 1.2197032531563912,
      "grad_norm": 1.0174050331115723,
      "learning_rate": 6.63521124859315e-06,
      "loss": 0.48,
      "step": 39705
    },
    {
      "epoch": 1.2197339722913403,
      "grad_norm": 0.40128350257873535,
      "learning_rate": 6.634756154597444e-06,
      "loss": 0.4761,
      "step": 39706
    },
    {
      "epoch": 1.2197646914262894,
      "grad_norm": 0.42877399921417236,
      "learning_rate": 6.634301068461502e-06,
      "loss": 0.523,
      "step": 39707
    },
    {
      "epoch": 1.2197954105612385,
      "grad_norm": 0.42104458808898926,
      "learning_rate": 6.633845990186383e-06,
      "loss": 0.4765,
      "step": 39708
    },
    {
      "epoch": 1.2198261296961879,
      "grad_norm": 0.42074480652809143,
      "learning_rate": 6.6333909197731535e-06,
      "loss": 0.5524,
      "step": 39709
    },
    {
      "epoch": 1.219856848831137,
      "grad_norm": 0.40396374464035034,
      "learning_rate": 6.6329358572228734e-06,
      "loss": 0.4608,
      "step": 39710
    },
    {
      "epoch": 1.219887567966086,
      "grad_norm": 0.4074905216693878,
      "learning_rate": 6.632480802536607e-06,
      "loss": 0.432,
      "step": 39711
    },
    {
      "epoch": 1.2199182871010352,
      "grad_norm": 0.44757571816444397,
      "learning_rate": 6.6320257557154164e-06,
      "loss": 0.4944,
      "step": 39712
    },
    {
      "epoch": 1.2199490062359843,
      "grad_norm": 0.4325200915336609,
      "learning_rate": 6.631570716760367e-06,
      "loss": 0.529,
      "step": 39713
    },
    {
      "epoch": 1.2199797253709335,
      "grad_norm": 0.4362145662307739,
      "learning_rate": 6.631115685672518e-06,
      "loss": 0.4781,
      "step": 39714
    },
    {
      "epoch": 1.2200104445058828,
      "grad_norm": 0.376628041267395,
      "learning_rate": 6.630660662452934e-06,
      "loss": 0.4848,
      "step": 39715
    },
    {
      "epoch": 1.220041163640832,
      "grad_norm": 0.38986778259277344,
      "learning_rate": 6.630205647102675e-06,
      "loss": 0.4602,
      "step": 39716
    },
    {
      "epoch": 1.220071882775781,
      "grad_norm": 0.38575899600982666,
      "learning_rate": 6.629750639622812e-06,
      "loss": 0.5051,
      "step": 39717
    },
    {
      "epoch": 1.2201026019107302,
      "grad_norm": 0.3813040852546692,
      "learning_rate": 6.629295640014395e-06,
      "loss": 0.5109,
      "step": 39718
    },
    {
      "epoch": 1.2201333210456793,
      "grad_norm": 0.38139480352401733,
      "learning_rate": 6.6288406482784985e-06,
      "loss": 0.4994,
      "step": 39719
    },
    {
      "epoch": 1.2201640401806286,
      "grad_norm": 0.44480204582214355,
      "learning_rate": 6.628385664416175e-06,
      "loss": 0.4467,
      "step": 39720
    },
    {
      "epoch": 1.2201947593155777,
      "grad_norm": 0.3754200339317322,
      "learning_rate": 6.627930688428498e-06,
      "loss": 0.4768,
      "step": 39721
    },
    {
      "epoch": 1.2202254784505269,
      "grad_norm": 0.3685949146747589,
      "learning_rate": 6.627475720316519e-06,
      "loss": 0.4227,
      "step": 39722
    },
    {
      "epoch": 1.220256197585476,
      "grad_norm": 0.42704248428344727,
      "learning_rate": 6.627020760081306e-06,
      "loss": 0.5174,
      "step": 39723
    },
    {
      "epoch": 1.220286916720425,
      "grad_norm": 0.9071894884109497,
      "learning_rate": 6.626565807723928e-06,
      "loss": 0.454,
      "step": 39724
    },
    {
      "epoch": 1.2203176358553742,
      "grad_norm": 0.4333970844745636,
      "learning_rate": 6.626110863245434e-06,
      "loss": 0.4537,
      "step": 39725
    },
    {
      "epoch": 1.2203483549903236,
      "grad_norm": 0.3967719078063965,
      "learning_rate": 6.625655926646899e-06,
      "loss": 0.5403,
      "step": 39726
    },
    {
      "epoch": 1.2203790741252727,
      "grad_norm": 0.4099419116973877,
      "learning_rate": 6.625200997929375e-06,
      "loss": 0.4856,
      "step": 39727
    },
    {
      "epoch": 1.2204097932602218,
      "grad_norm": 0.4345340132713318,
      "learning_rate": 6.624746077093936e-06,
      "loss": 0.4969,
      "step": 39728
    },
    {
      "epoch": 1.220440512395171,
      "grad_norm": 0.411577045917511,
      "learning_rate": 6.6242911641416315e-06,
      "loss": 0.4773,
      "step": 39729
    },
    {
      "epoch": 1.22047123153012,
      "grad_norm": 0.3859010636806488,
      "learning_rate": 6.62383625907354e-06,
      "loss": 0.4322,
      "step": 39730
    },
    {
      "epoch": 1.2205019506650694,
      "grad_norm": 0.4575861096382141,
      "learning_rate": 6.623381361890706e-06,
      "loss": 0.4753,
      "step": 39731
    },
    {
      "epoch": 1.2205326698000185,
      "grad_norm": 0.3731575310230255,
      "learning_rate": 6.6229264725942055e-06,
      "loss": 0.4151,
      "step": 39732
    },
    {
      "epoch": 1.2205633889349676,
      "grad_norm": 0.3945287764072418,
      "learning_rate": 6.622471591185093e-06,
      "loss": 0.4188,
      "step": 39733
    },
    {
      "epoch": 1.2205941080699168,
      "grad_norm": 0.3589381277561188,
      "learning_rate": 6.622016717664437e-06,
      "loss": 0.4057,
      "step": 39734
    },
    {
      "epoch": 1.2206248272048659,
      "grad_norm": 0.40760231018066406,
      "learning_rate": 6.621561852033294e-06,
      "loss": 0.4537,
      "step": 39735
    },
    {
      "epoch": 1.220655546339815,
      "grad_norm": 0.38548681139945984,
      "learning_rate": 6.621106994292731e-06,
      "loss": 0.4768,
      "step": 39736
    },
    {
      "epoch": 1.220686265474764,
      "grad_norm": 0.3792547881603241,
      "learning_rate": 6.620652144443806e-06,
      "loss": 0.483,
      "step": 39737
    },
    {
      "epoch": 1.2207169846097135,
      "grad_norm": 0.4073573052883148,
      "learning_rate": 6.620197302487587e-06,
      "loss": 0.5148,
      "step": 39738
    },
    {
      "epoch": 1.2207477037446626,
      "grad_norm": 0.40086105465888977,
      "learning_rate": 6.619742468425132e-06,
      "loss": 0.5199,
      "step": 39739
    },
    {
      "epoch": 1.2207784228796117,
      "grad_norm": 0.4016943871974945,
      "learning_rate": 6.619287642257503e-06,
      "loss": 0.5347,
      "step": 39740
    },
    {
      "epoch": 1.2208091420145608,
      "grad_norm": 0.4060845375061035,
      "learning_rate": 6.618832823985768e-06,
      "loss": 0.4936,
      "step": 39741
    },
    {
      "epoch": 1.2208398611495102,
      "grad_norm": 0.4186389148235321,
      "learning_rate": 6.618378013610981e-06,
      "loss": 0.4533,
      "step": 39742
    },
    {
      "epoch": 1.2208705802844593,
      "grad_norm": 0.3906612694263458,
      "learning_rate": 6.617923211134211e-06,
      "loss": 0.4702,
      "step": 39743
    },
    {
      "epoch": 1.2209012994194084,
      "grad_norm": 0.40367457270622253,
      "learning_rate": 6.617468416556515e-06,
      "loss": 0.5327,
      "step": 39744
    },
    {
      "epoch": 1.2209320185543575,
      "grad_norm": 0.39984285831451416,
      "learning_rate": 6.617013629878961e-06,
      "loss": 0.4825,
      "step": 39745
    },
    {
      "epoch": 1.2209627376893066,
      "grad_norm": 0.4418559968471527,
      "learning_rate": 6.616558851102605e-06,
      "loss": 0.4167,
      "step": 39746
    },
    {
      "epoch": 1.2209934568242558,
      "grad_norm": 0.40977945923805237,
      "learning_rate": 6.616104080228514e-06,
      "loss": 0.4659,
      "step": 39747
    },
    {
      "epoch": 1.2210241759592049,
      "grad_norm": 0.40200138092041016,
      "learning_rate": 6.615649317257746e-06,
      "loss": 0.493,
      "step": 39748
    },
    {
      "epoch": 1.2210548950941542,
      "grad_norm": 0.4020986557006836,
      "learning_rate": 6.615194562191369e-06,
      "loss": 0.4116,
      "step": 39749
    },
    {
      "epoch": 1.2210856142291033,
      "grad_norm": 0.35051628947257996,
      "learning_rate": 6.614739815030438e-06,
      "loss": 0.4038,
      "step": 39750
    },
    {
      "epoch": 1.2211163333640525,
      "grad_norm": 0.40966328978538513,
      "learning_rate": 6.61428507577602e-06,
      "loss": 0.4532,
      "step": 39751
    },
    {
      "epoch": 1.2211470524990016,
      "grad_norm": 0.40590399503707886,
      "learning_rate": 6.6138303444291756e-06,
      "loss": 0.5293,
      "step": 39752
    },
    {
      "epoch": 1.2211777716339507,
      "grad_norm": 0.4199085533618927,
      "learning_rate": 6.613375620990969e-06,
      "loss": 0.4814,
      "step": 39753
    },
    {
      "epoch": 1.2212084907689,
      "grad_norm": 0.3750116229057312,
      "learning_rate": 6.612920905462455e-06,
      "loss": 0.4749,
      "step": 39754
    },
    {
      "epoch": 1.2212392099038492,
      "grad_norm": 0.38299331068992615,
      "learning_rate": 6.612466197844707e-06,
      "loss": 0.4835,
      "step": 39755
    },
    {
      "epoch": 1.2212699290387983,
      "grad_norm": 0.4003848433494568,
      "learning_rate": 6.612011498138775e-06,
      "loss": 0.4865,
      "step": 39756
    },
    {
      "epoch": 1.2213006481737474,
      "grad_norm": 0.3946819603443146,
      "learning_rate": 6.611556806345732e-06,
      "loss": 0.5486,
      "step": 39757
    },
    {
      "epoch": 1.2213313673086965,
      "grad_norm": 0.386270135641098,
      "learning_rate": 6.611102122466631e-06,
      "loss": 0.518,
      "step": 39758
    },
    {
      "epoch": 1.2213620864436456,
      "grad_norm": 0.37448737025260925,
      "learning_rate": 6.610647446502536e-06,
      "loss": 0.486,
      "step": 39759
    },
    {
      "epoch": 1.221392805578595,
      "grad_norm": 0.4032372236251831,
      "learning_rate": 6.610192778454516e-06,
      "loss": 0.5261,
      "step": 39760
    },
    {
      "epoch": 1.221423524713544,
      "grad_norm": 0.3503241240978241,
      "learning_rate": 6.609738118323622e-06,
      "loss": 0.4847,
      "step": 39761
    },
    {
      "epoch": 1.2214542438484932,
      "grad_norm": 0.3816228210926056,
      "learning_rate": 6.609283466110927e-06,
      "loss": 0.4772,
      "step": 39762
    },
    {
      "epoch": 1.2214849629834423,
      "grad_norm": 0.3871634602546692,
      "learning_rate": 6.608828821817482e-06,
      "loss": 0.4507,
      "step": 39763
    },
    {
      "epoch": 1.2215156821183915,
      "grad_norm": 0.40754106640815735,
      "learning_rate": 6.608374185444359e-06,
      "loss": 0.5069,
      "step": 39764
    },
    {
      "epoch": 1.2215464012533408,
      "grad_norm": 0.3861454129219055,
      "learning_rate": 6.607919556992613e-06,
      "loss": 0.4337,
      "step": 39765
    },
    {
      "epoch": 1.22157712038829,
      "grad_norm": 0.42360150814056396,
      "learning_rate": 6.607464936463308e-06,
      "loss": 0.5074,
      "step": 39766
    },
    {
      "epoch": 1.221607839523239,
      "grad_norm": 0.43614816665649414,
      "learning_rate": 6.607010323857503e-06,
      "loss": 0.4747,
      "step": 39767
    },
    {
      "epoch": 1.2216385586581882,
      "grad_norm": 0.3919905722141266,
      "learning_rate": 6.606555719176266e-06,
      "loss": 0.4099,
      "step": 39768
    },
    {
      "epoch": 1.2216692777931373,
      "grad_norm": 0.3964143395423889,
      "learning_rate": 6.6061011224206524e-06,
      "loss": 0.4135,
      "step": 39769
    },
    {
      "epoch": 1.2216999969280864,
      "grad_norm": 0.4511663317680359,
      "learning_rate": 6.60564653359173e-06,
      "loss": 0.5572,
      "step": 39770
    },
    {
      "epoch": 1.2217307160630357,
      "grad_norm": 0.4065612256526947,
      "learning_rate": 6.605191952690552e-06,
      "loss": 0.4693,
      "step": 39771
    },
    {
      "epoch": 1.2217614351979849,
      "grad_norm": 0.4573655426502228,
      "learning_rate": 6.6047373797181906e-06,
      "loss": 0.4862,
      "step": 39772
    },
    {
      "epoch": 1.221792154332934,
      "grad_norm": 0.4500722587108612,
      "learning_rate": 6.604282814675698e-06,
      "loss": 0.4481,
      "step": 39773
    },
    {
      "epoch": 1.221822873467883,
      "grad_norm": 0.4374054968357086,
      "learning_rate": 6.603828257564143e-06,
      "loss": 0.512,
      "step": 39774
    },
    {
      "epoch": 1.2218535926028322,
      "grad_norm": 0.3619667589664459,
      "learning_rate": 6.603373708384582e-06,
      "loss": 0.4242,
      "step": 39775
    },
    {
      "epoch": 1.2218843117377816,
      "grad_norm": 0.38021326065063477,
      "learning_rate": 6.602919167138081e-06,
      "loss": 0.4705,
      "step": 39776
    },
    {
      "epoch": 1.2219150308727307,
      "grad_norm": 0.38089606165885925,
      "learning_rate": 6.6024646338256985e-06,
      "loss": 0.4194,
      "step": 39777
    },
    {
      "epoch": 1.2219457500076798,
      "grad_norm": 0.35696589946746826,
      "learning_rate": 6.602010108448496e-06,
      "loss": 0.3875,
      "step": 39778
    },
    {
      "epoch": 1.221976469142629,
      "grad_norm": 0.39468997716903687,
      "learning_rate": 6.601555591007538e-06,
      "loss": 0.4003,
      "step": 39779
    },
    {
      "epoch": 1.222007188277578,
      "grad_norm": 0.4825323820114136,
      "learning_rate": 6.601101081503882e-06,
      "loss": 0.5215,
      "step": 39780
    },
    {
      "epoch": 1.2220379074125272,
      "grad_norm": 0.3970352113246918,
      "learning_rate": 6.600646579938594e-06,
      "loss": 0.4812,
      "step": 39781
    },
    {
      "epoch": 1.2220686265474765,
      "grad_norm": 0.4300154745578766,
      "learning_rate": 6.600192086312732e-06,
      "loss": 0.4736,
      "step": 39782
    },
    {
      "epoch": 1.2220993456824256,
      "grad_norm": 0.4399353563785553,
      "learning_rate": 6.599737600627361e-06,
      "loss": 0.5449,
      "step": 39783
    },
    {
      "epoch": 1.2221300648173747,
      "grad_norm": 0.4207626283168793,
      "learning_rate": 6.5992831228835376e-06,
      "loss": 0.4864,
      "step": 39784
    },
    {
      "epoch": 1.2221607839523239,
      "grad_norm": 0.4443109333515167,
      "learning_rate": 6.598828653082329e-06,
      "loss": 0.4721,
      "step": 39785
    },
    {
      "epoch": 1.222191503087273,
      "grad_norm": 0.4115098714828491,
      "learning_rate": 6.59837419122479e-06,
      "loss": 0.4806,
      "step": 39786
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 0.4120217263698578,
      "learning_rate": 6.597919737311991e-06,
      "loss": 0.4744,
      "step": 39787
    },
    {
      "epoch": 1.2222529413571714,
      "grad_norm": 0.3527621328830719,
      "learning_rate": 6.5974652913449825e-06,
      "loss": 0.4062,
      "step": 39788
    },
    {
      "epoch": 1.2222836604921206,
      "grad_norm": 0.37851232290267944,
      "learning_rate": 6.5970108533248354e-06,
      "loss": 0.4633,
      "step": 39789
    },
    {
      "epoch": 1.2223143796270697,
      "grad_norm": 0.4043060541152954,
      "learning_rate": 6.596556423252603e-06,
      "loss": 0.4443,
      "step": 39790
    },
    {
      "epoch": 1.2223450987620188,
      "grad_norm": 0.39613765478134155,
      "learning_rate": 6.596102001129356e-06,
      "loss": 0.4623,
      "step": 39791
    },
    {
      "epoch": 1.222375817896968,
      "grad_norm": 0.41353127360343933,
      "learning_rate": 6.595647586956144e-06,
      "loss": 0.5612,
      "step": 39792
    },
    {
      "epoch": 1.2224065370319173,
      "grad_norm": 0.3784431219100952,
      "learning_rate": 6.595193180734041e-06,
      "loss": 0.5431,
      "step": 39793
    },
    {
      "epoch": 1.2224372561668664,
      "grad_norm": 0.3762095272541046,
      "learning_rate": 6.594738782464099e-06,
      "loss": 0.448,
      "step": 39794
    },
    {
      "epoch": 1.2224679753018155,
      "grad_norm": 0.4045242667198181,
      "learning_rate": 6.5942843921473785e-06,
      "loss": 0.5042,
      "step": 39795
    },
    {
      "epoch": 1.2224986944367646,
      "grad_norm": 0.6118902564048767,
      "learning_rate": 6.593830009784952e-06,
      "loss": 0.4449,
      "step": 39796
    },
    {
      "epoch": 1.2225294135717137,
      "grad_norm": 0.37365826964378357,
      "learning_rate": 6.593375635377867e-06,
      "loss": 0.4875,
      "step": 39797
    },
    {
      "epoch": 1.222560132706663,
      "grad_norm": 0.37670835852622986,
      "learning_rate": 6.592921268927199e-06,
      "loss": 0.4247,
      "step": 39798
    },
    {
      "epoch": 1.2225908518416122,
      "grad_norm": 0.36884769797325134,
      "learning_rate": 6.592466910433995e-06,
      "loss": 0.4786,
      "step": 39799
    },
    {
      "epoch": 1.2226215709765613,
      "grad_norm": 0.4109020233154297,
      "learning_rate": 6.5920125598993255e-06,
      "loss": 0.5421,
      "step": 39800
    },
    {
      "epoch": 1.2226522901115104,
      "grad_norm": 0.377258837223053,
      "learning_rate": 6.591558217324247e-06,
      "loss": 0.4496,
      "step": 39801
    },
    {
      "epoch": 1.2226830092464596,
      "grad_norm": 0.4056178331375122,
      "learning_rate": 6.5911038827098235e-06,
      "loss": 0.4678,
      "step": 39802
    },
    {
      "epoch": 1.2227137283814087,
      "grad_norm": 0.3832072615623474,
      "learning_rate": 6.5906495560571136e-06,
      "loss": 0.3966,
      "step": 39803
    },
    {
      "epoch": 1.222744447516358,
      "grad_norm": 0.4153055250644684,
      "learning_rate": 6.590195237367181e-06,
      "loss": 0.434,
      "step": 39804
    },
    {
      "epoch": 1.2227751666513071,
      "grad_norm": 0.4465251564979553,
      "learning_rate": 6.589740926641084e-06,
      "loss": 0.5062,
      "step": 39805
    },
    {
      "epoch": 1.2228058857862563,
      "grad_norm": 0.4276168942451477,
      "learning_rate": 6.589286623879887e-06,
      "loss": 0.5103,
      "step": 39806
    },
    {
      "epoch": 1.2228366049212054,
      "grad_norm": 0.45243778824806213,
      "learning_rate": 6.588832329084648e-06,
      "loss": 0.4667,
      "step": 39807
    },
    {
      "epoch": 1.2228673240561545,
      "grad_norm": 0.3952505588531494,
      "learning_rate": 6.588378042256432e-06,
      "loss": 0.4818,
      "step": 39808
    },
    {
      "epoch": 1.2228980431911038,
      "grad_norm": 0.41356509923934937,
      "learning_rate": 6.587923763396294e-06,
      "loss": 0.457,
      "step": 39809
    },
    {
      "epoch": 1.222928762326053,
      "grad_norm": 0.4755159616470337,
      "learning_rate": 6.5874694925053e-06,
      "loss": 0.493,
      "step": 39810
    },
    {
      "epoch": 1.222959481461002,
      "grad_norm": 0.40637123584747314,
      "learning_rate": 6.587015229584508e-06,
      "loss": 0.5489,
      "step": 39811
    },
    {
      "epoch": 1.2229902005959512,
      "grad_norm": 0.448773592710495,
      "learning_rate": 6.5865609746349815e-06,
      "loss": 0.4071,
      "step": 39812
    },
    {
      "epoch": 1.2230209197309003,
      "grad_norm": 0.38318946957588196,
      "learning_rate": 6.586106727657779e-06,
      "loss": 0.5055,
      "step": 39813
    },
    {
      "epoch": 1.2230516388658494,
      "grad_norm": 0.4224664270877838,
      "learning_rate": 6.585652488653962e-06,
      "loss": 0.5085,
      "step": 39814
    },
    {
      "epoch": 1.2230823580007988,
      "grad_norm": 0.3973473012447357,
      "learning_rate": 6.5851982576245945e-06,
      "loss": 0.4756,
      "step": 39815
    },
    {
      "epoch": 1.223113077135748,
      "grad_norm": 0.4184272289276123,
      "learning_rate": 6.5847440345707334e-06,
      "loss": 0.4771,
      "step": 39816
    },
    {
      "epoch": 1.223143796270697,
      "grad_norm": 0.4119325280189514,
      "learning_rate": 6.5842898194934435e-06,
      "loss": 0.4673,
      "step": 39817
    },
    {
      "epoch": 1.2231745154056461,
      "grad_norm": 0.41336098313331604,
      "learning_rate": 6.583835612393781e-06,
      "loss": 0.5294,
      "step": 39818
    },
    {
      "epoch": 1.2232052345405953,
      "grad_norm": 0.39928048849105835,
      "learning_rate": 6.583381413272809e-06,
      "loss": 0.5461,
      "step": 39819
    },
    {
      "epoch": 1.2232359536755446,
      "grad_norm": 0.41370490193367004,
      "learning_rate": 6.582927222131589e-06,
      "loss": 0.5008,
      "step": 39820
    },
    {
      "epoch": 1.2232666728104937,
      "grad_norm": 0.4190139174461365,
      "learning_rate": 6.582473038971184e-06,
      "loss": 0.5315,
      "step": 39821
    },
    {
      "epoch": 1.2232973919454428,
      "grad_norm": 0.4613603353500366,
      "learning_rate": 6.582018863792645e-06,
      "loss": 0.4851,
      "step": 39822
    },
    {
      "epoch": 1.223328111080392,
      "grad_norm": 0.4041823744773865,
      "learning_rate": 6.581564696597047e-06,
      "loss": 0.4375,
      "step": 39823
    },
    {
      "epoch": 1.223358830215341,
      "grad_norm": 0.4026612341403961,
      "learning_rate": 6.581110537385438e-06,
      "loss": 0.51,
      "step": 39824
    },
    {
      "epoch": 1.2233895493502902,
      "grad_norm": 0.3657567799091339,
      "learning_rate": 6.580656386158888e-06,
      "loss": 0.4976,
      "step": 39825
    },
    {
      "epoch": 1.2234202684852395,
      "grad_norm": 0.4121149778366089,
      "learning_rate": 6.58020224291845e-06,
      "loss": 0.5548,
      "step": 39826
    },
    {
      "epoch": 1.2234509876201887,
      "grad_norm": 0.44604557752609253,
      "learning_rate": 6.579748107665193e-06,
      "loss": 0.5123,
      "step": 39827
    },
    {
      "epoch": 1.2234817067551378,
      "grad_norm": 0.39462536573410034,
      "learning_rate": 6.57929398040017e-06,
      "loss": 0.4415,
      "step": 39828
    },
    {
      "epoch": 1.223512425890087,
      "grad_norm": 0.4735744893550873,
      "learning_rate": 6.578839861124446e-06,
      "loss": 0.5102,
      "step": 39829
    },
    {
      "epoch": 1.223543145025036,
      "grad_norm": 0.38071954250335693,
      "learning_rate": 6.578385749839078e-06,
      "loss": 0.4713,
      "step": 39830
    },
    {
      "epoch": 1.2235738641599854,
      "grad_norm": 0.42192453145980835,
      "learning_rate": 6.577931646545128e-06,
      "loss": 0.3943,
      "step": 39831
    },
    {
      "epoch": 1.2236045832949345,
      "grad_norm": 0.4335874617099762,
      "learning_rate": 6.577477551243664e-06,
      "loss": 0.4415,
      "step": 39832
    },
    {
      "epoch": 1.2236353024298836,
      "grad_norm": 0.435526579618454,
      "learning_rate": 6.577023463935733e-06,
      "loss": 0.4545,
      "step": 39833
    },
    {
      "epoch": 1.2236660215648327,
      "grad_norm": 0.3669143617153168,
      "learning_rate": 6.57656938462241e-06,
      "loss": 0.4821,
      "step": 39834
    },
    {
      "epoch": 1.2236967406997818,
      "grad_norm": 0.3890465199947357,
      "learning_rate": 6.5761153133047425e-06,
      "loss": 0.5005,
      "step": 39835
    },
    {
      "epoch": 1.223727459834731,
      "grad_norm": 0.3955336809158325,
      "learning_rate": 6.575661249983802e-06,
      "loss": 0.5154,
      "step": 39836
    },
    {
      "epoch": 1.2237581789696803,
      "grad_norm": 0.4473333954811096,
      "learning_rate": 6.575207194660639e-06,
      "loss": 0.4424,
      "step": 39837
    },
    {
      "epoch": 1.2237888981046294,
      "grad_norm": 0.3931669592857361,
      "learning_rate": 6.574753147336321e-06,
      "loss": 0.4206,
      "step": 39838
    },
    {
      "epoch": 1.2238196172395785,
      "grad_norm": 0.41005757451057434,
      "learning_rate": 6.5742991080119055e-06,
      "loss": 0.4754,
      "step": 39839
    },
    {
      "epoch": 1.2238503363745277,
      "grad_norm": 0.565636157989502,
      "learning_rate": 6.573845076688456e-06,
      "loss": 0.4688,
      "step": 39840
    },
    {
      "epoch": 1.2238810555094768,
      "grad_norm": 0.4026099741458893,
      "learning_rate": 6.573391053367026e-06,
      "loss": 0.4951,
      "step": 39841
    },
    {
      "epoch": 1.2239117746444261,
      "grad_norm": 0.3972811698913574,
      "learning_rate": 6.572937038048686e-06,
      "loss": 0.5448,
      "step": 39842
    },
    {
      "epoch": 1.2239424937793753,
      "grad_norm": 0.38780152797698975,
      "learning_rate": 6.572483030734487e-06,
      "loss": 0.4296,
      "step": 39843
    },
    {
      "epoch": 1.2239732129143244,
      "grad_norm": 0.38177675008773804,
      "learning_rate": 6.572029031425494e-06,
      "loss": 0.4726,
      "step": 39844
    },
    {
      "epoch": 1.2240039320492735,
      "grad_norm": 0.4063335955142975,
      "learning_rate": 6.571575040122766e-06,
      "loss": 0.5093,
      "step": 39845
    },
    {
      "epoch": 1.2240346511842226,
      "grad_norm": 0.49941274523735046,
      "learning_rate": 6.571121056827366e-06,
      "loss": 0.4599,
      "step": 39846
    },
    {
      "epoch": 1.2240653703191717,
      "grad_norm": 0.4078691601753235,
      "learning_rate": 6.570667081540349e-06,
      "loss": 0.5055,
      "step": 39847
    },
    {
      "epoch": 1.2240960894541209,
      "grad_norm": 0.4219099283218384,
      "learning_rate": 6.570213114262782e-06,
      "loss": 0.5079,
      "step": 39848
    },
    {
      "epoch": 1.2241268085890702,
      "grad_norm": 0.37797045707702637,
      "learning_rate": 6.56975915499572e-06,
      "loss": 0.5131,
      "step": 39849
    },
    {
      "epoch": 1.2241575277240193,
      "grad_norm": 0.5329598784446716,
      "learning_rate": 6.569305203740225e-06,
      "loss": 0.4933,
      "step": 39850
    },
    {
      "epoch": 1.2241882468589684,
      "grad_norm": 0.41489171981811523,
      "learning_rate": 6.568851260497359e-06,
      "loss": 0.4748,
      "step": 39851
    },
    {
      "epoch": 1.2242189659939176,
      "grad_norm": 0.4308578372001648,
      "learning_rate": 6.568397325268177e-06,
      "loss": 0.4134,
      "step": 39852
    },
    {
      "epoch": 1.224249685128867,
      "grad_norm": 0.40753382444381714,
      "learning_rate": 6.567943398053746e-06,
      "loss": 0.554,
      "step": 39853
    },
    {
      "epoch": 1.224280404263816,
      "grad_norm": 0.4670199751853943,
      "learning_rate": 6.5674894788551225e-06,
      "loss": 0.4902,
      "step": 39854
    },
    {
      "epoch": 1.2243111233987651,
      "grad_norm": 0.351092129945755,
      "learning_rate": 6.5670355676733666e-06,
      "loss": 0.3766,
      "step": 39855
    },
    {
      "epoch": 1.2243418425337143,
      "grad_norm": 0.36688873171806335,
      "learning_rate": 6.566581664509537e-06,
      "loss": 0.4302,
      "step": 39856
    },
    {
      "epoch": 1.2243725616686634,
      "grad_norm": 0.3682074546813965,
      "learning_rate": 6.566127769364701e-06,
      "loss": 0.3766,
      "step": 39857
    },
    {
      "epoch": 1.2244032808036125,
      "grad_norm": 0.39469724893569946,
      "learning_rate": 6.565673882239907e-06,
      "loss": 0.3814,
      "step": 39858
    },
    {
      "epoch": 1.2244339999385616,
      "grad_norm": 0.422329843044281,
      "learning_rate": 6.5652200031362275e-06,
      "loss": 0.4909,
      "step": 39859
    },
    {
      "epoch": 1.224464719073511,
      "grad_norm": 0.4126850366592407,
      "learning_rate": 6.56476613205471e-06,
      "loss": 0.4421,
      "step": 39860
    },
    {
      "epoch": 1.22449543820846,
      "grad_norm": 0.4412786364555359,
      "learning_rate": 6.5643122689964276e-06,
      "loss": 0.4991,
      "step": 39861
    },
    {
      "epoch": 1.2245261573434092,
      "grad_norm": 0.43112117052078247,
      "learning_rate": 6.563858413962429e-06,
      "loss": 0.4868,
      "step": 39862
    },
    {
      "epoch": 1.2245568764783583,
      "grad_norm": 0.3673616051673889,
      "learning_rate": 6.563404566953784e-06,
      "loss": 0.444,
      "step": 39863
    },
    {
      "epoch": 1.2245875956133074,
      "grad_norm": 0.3898695707321167,
      "learning_rate": 6.562950727971542e-06,
      "loss": 0.4469,
      "step": 39864
    },
    {
      "epoch": 1.2246183147482568,
      "grad_norm": 0.38722845911979675,
      "learning_rate": 6.5624968970167724e-06,
      "loss": 0.4884,
      "step": 39865
    },
    {
      "epoch": 1.224649033883206,
      "grad_norm": 0.49845945835113525,
      "learning_rate": 6.562043074090529e-06,
      "loss": 0.4905,
      "step": 39866
    },
    {
      "epoch": 1.224679753018155,
      "grad_norm": 0.44645431637763977,
      "learning_rate": 6.561589259193877e-06,
      "loss": 0.4923,
      "step": 39867
    },
    {
      "epoch": 1.2247104721531041,
      "grad_norm": 0.475924015045166,
      "learning_rate": 6.5611354523278695e-06,
      "loss": 0.4928,
      "step": 39868
    },
    {
      "epoch": 1.2247411912880533,
      "grad_norm": 0.39894282817840576,
      "learning_rate": 6.560681653493573e-06,
      "loss": 0.5293,
      "step": 39869
    },
    {
      "epoch": 1.2247719104230024,
      "grad_norm": 0.47710397839546204,
      "learning_rate": 6.560227862692044e-06,
      "loss": 0.4686,
      "step": 39870
    },
    {
      "epoch": 1.2248026295579517,
      "grad_norm": 0.41053083539009094,
      "learning_rate": 6.559774079924342e-06,
      "loss": 0.4675,
      "step": 39871
    },
    {
      "epoch": 1.2248333486929008,
      "grad_norm": 0.41558414697647095,
      "learning_rate": 6.55932030519153e-06,
      "loss": 0.4759,
      "step": 39872
    },
    {
      "epoch": 1.22486406782785,
      "grad_norm": 0.4522177278995514,
      "learning_rate": 6.558866538494663e-06,
      "loss": 0.4643,
      "step": 39873
    },
    {
      "epoch": 1.224894786962799,
      "grad_norm": 0.36804693937301636,
      "learning_rate": 6.5584127798348065e-06,
      "loss": 0.4179,
      "step": 39874
    },
    {
      "epoch": 1.2249255060977482,
      "grad_norm": 0.4073216915130615,
      "learning_rate": 6.557959029213016e-06,
      "loss": 0.5431,
      "step": 39875
    },
    {
      "epoch": 1.2249562252326975,
      "grad_norm": 0.6018360257148743,
      "learning_rate": 6.557505286630354e-06,
      "loss": 0.4944,
      "step": 39876
    },
    {
      "epoch": 1.2249869443676467,
      "grad_norm": 0.4042842388153076,
      "learning_rate": 6.557051552087876e-06,
      "loss": 0.4975,
      "step": 39877
    },
    {
      "epoch": 1.2250176635025958,
      "grad_norm": 0.4825116693973541,
      "learning_rate": 6.556597825586647e-06,
      "loss": 0.5034,
      "step": 39878
    },
    {
      "epoch": 1.225048382637545,
      "grad_norm": 0.34698787331581116,
      "learning_rate": 6.556144107127722e-06,
      "loss": 0.4919,
      "step": 39879
    },
    {
      "epoch": 1.225079101772494,
      "grad_norm": 0.3671503961086273,
      "learning_rate": 6.555690396712165e-06,
      "loss": 0.4947,
      "step": 39880
    },
    {
      "epoch": 1.2251098209074431,
      "grad_norm": 0.4596795439720154,
      "learning_rate": 6.555236694341031e-06,
      "loss": 0.3959,
      "step": 39881
    },
    {
      "epoch": 1.2251405400423925,
      "grad_norm": 0.3829607665538788,
      "learning_rate": 6.554783000015387e-06,
      "loss": 0.46,
      "step": 39882
    },
    {
      "epoch": 1.2251712591773416,
      "grad_norm": 0.45808732509613037,
      "learning_rate": 6.5543293137362825e-06,
      "loss": 0.488,
      "step": 39883
    },
    {
      "epoch": 1.2252019783122907,
      "grad_norm": 0.41208571195602417,
      "learning_rate": 6.553875635504789e-06,
      "loss": 0.4205,
      "step": 39884
    },
    {
      "epoch": 1.2252326974472398,
      "grad_norm": 0.4113544821739197,
      "learning_rate": 6.553421965321954e-06,
      "loss": 0.4083,
      "step": 39885
    },
    {
      "epoch": 1.225263416582189,
      "grad_norm": 0.41195380687713623,
      "learning_rate": 6.552968303188842e-06,
      "loss": 0.4278,
      "step": 39886
    },
    {
      "epoch": 1.2252941357171383,
      "grad_norm": 0.4358372986316681,
      "learning_rate": 6.552514649106517e-06,
      "loss": 0.5259,
      "step": 39887
    },
    {
      "epoch": 1.2253248548520874,
      "grad_norm": 0.39696645736694336,
      "learning_rate": 6.5520610030760335e-06,
      "loss": 0.4676,
      "step": 39888
    },
    {
      "epoch": 1.2253555739870365,
      "grad_norm": 0.42233189940452576,
      "learning_rate": 6.551607365098453e-06,
      "loss": 0.422,
      "step": 39889
    },
    {
      "epoch": 1.2253862931219857,
      "grad_norm": 0.42352038621902466,
      "learning_rate": 6.551153735174832e-06,
      "loss": 0.492,
      "step": 39890
    },
    {
      "epoch": 1.2254170122569348,
      "grad_norm": 0.40276581048965454,
      "learning_rate": 6.550700113306238e-06,
      "loss": 0.534,
      "step": 39891
    },
    {
      "epoch": 1.225447731391884,
      "grad_norm": 0.39476874470710754,
      "learning_rate": 6.5502464994937175e-06,
      "loss": 0.4409,
      "step": 39892
    },
    {
      "epoch": 1.2254784505268332,
      "grad_norm": 0.4017919600009918,
      "learning_rate": 6.5497928937383424e-06,
      "loss": 0.4429,
      "step": 39893
    },
    {
      "epoch": 1.2255091696617824,
      "grad_norm": 1.110775351524353,
      "learning_rate": 6.549339296041163e-06,
      "loss": 0.4021,
      "step": 39894
    },
    {
      "epoch": 1.2255398887967315,
      "grad_norm": 0.4234164357185364,
      "learning_rate": 6.5488857064032475e-06,
      "loss": 0.4504,
      "step": 39895
    },
    {
      "epoch": 1.2255706079316806,
      "grad_norm": 0.46221470832824707,
      "learning_rate": 6.5484321248256444e-06,
      "loss": 0.4823,
      "step": 39896
    },
    {
      "epoch": 1.2256013270666297,
      "grad_norm": 0.386434406042099,
      "learning_rate": 6.547978551309427e-06,
      "loss": 0.4987,
      "step": 39897
    },
    {
      "epoch": 1.225632046201579,
      "grad_norm": 0.3909851610660553,
      "learning_rate": 6.54752498585564e-06,
      "loss": 0.5568,
      "step": 39898
    },
    {
      "epoch": 1.2256627653365282,
      "grad_norm": 0.4623294174671173,
      "learning_rate": 6.547071428465353e-06,
      "loss": 0.5125,
      "step": 39899
    },
    {
      "epoch": 1.2256934844714773,
      "grad_norm": 0.464513897895813,
      "learning_rate": 6.5466178791396184e-06,
      "loss": 0.483,
      "step": 39900
    },
    {
      "epoch": 1.2257242036064264,
      "grad_norm": 0.38610073924064636,
      "learning_rate": 6.546164337879504e-06,
      "loss": 0.5245,
      "step": 39901
    },
    {
      "epoch": 1.2257549227413755,
      "grad_norm": 0.40793749690055847,
      "learning_rate": 6.545710804686058e-06,
      "loss": 0.5527,
      "step": 39902
    },
    {
      "epoch": 1.2257856418763247,
      "grad_norm": 0.4065055549144745,
      "learning_rate": 6.545257279560351e-06,
      "loss": 0.4753,
      "step": 39903
    },
    {
      "epoch": 1.225816361011274,
      "grad_norm": 0.46447208523750305,
      "learning_rate": 6.5448037625034335e-06,
      "loss": 0.4964,
      "step": 39904
    },
    {
      "epoch": 1.2258470801462231,
      "grad_norm": 0.4089255928993225,
      "learning_rate": 6.544350253516368e-06,
      "loss": 0.5288,
      "step": 39905
    },
    {
      "epoch": 1.2258777992811722,
      "grad_norm": 0.41324999928474426,
      "learning_rate": 6.543896752600216e-06,
      "loss": 0.5178,
      "step": 39906
    },
    {
      "epoch": 1.2259085184161214,
      "grad_norm": 0.37409940361976624,
      "learning_rate": 6.543443259756033e-06,
      "loss": 0.472,
      "step": 39907
    },
    {
      "epoch": 1.2259392375510705,
      "grad_norm": 0.38425931334495544,
      "learning_rate": 6.54298977498488e-06,
      "loss": 0.4571,
      "step": 39908
    },
    {
      "epoch": 1.2259699566860198,
      "grad_norm": 0.36512234807014465,
      "learning_rate": 6.542536298287816e-06,
      "loss": 0.438,
      "step": 39909
    },
    {
      "epoch": 1.226000675820969,
      "grad_norm": 0.39887213706970215,
      "learning_rate": 6.542082829665901e-06,
      "loss": 0.4905,
      "step": 39910
    },
    {
      "epoch": 1.226031394955918,
      "grad_norm": 0.4466301202774048,
      "learning_rate": 6.54162936912019e-06,
      "loss": 0.4536,
      "step": 39911
    },
    {
      "epoch": 1.2260621140908672,
      "grad_norm": 0.41433632373809814,
      "learning_rate": 6.54117591665175e-06,
      "loss": 0.522,
      "step": 39912
    },
    {
      "epoch": 1.2260928332258163,
      "grad_norm": 0.46739500761032104,
      "learning_rate": 6.540722472261632e-06,
      "loss": 0.4949,
      "step": 39913
    },
    {
      "epoch": 1.2261235523607654,
      "grad_norm": 0.35439664125442505,
      "learning_rate": 6.540269035950899e-06,
      "loss": 0.4076,
      "step": 39914
    },
    {
      "epoch": 1.2261542714957148,
      "grad_norm": 0.432822048664093,
      "learning_rate": 6.539815607720607e-06,
      "loss": 0.4005,
      "step": 39915
    },
    {
      "epoch": 1.2261849906306639,
      "grad_norm": 0.38857391476631165,
      "learning_rate": 6.539362187571821e-06,
      "loss": 0.4218,
      "step": 39916
    },
    {
      "epoch": 1.226215709765613,
      "grad_norm": 0.4254770874977112,
      "learning_rate": 6.538908775505593e-06,
      "loss": 0.6332,
      "step": 39917
    },
    {
      "epoch": 1.2262464289005621,
      "grad_norm": 0.4229549169540405,
      "learning_rate": 6.538455371522988e-06,
      "loss": 0.4312,
      "step": 39918
    },
    {
      "epoch": 1.2262771480355112,
      "grad_norm": 0.43666356801986694,
      "learning_rate": 6.53800197562506e-06,
      "loss": 0.5233,
      "step": 39919
    },
    {
      "epoch": 1.2263078671704606,
      "grad_norm": 0.4424327313899994,
      "learning_rate": 6.5375485878128745e-06,
      "loss": 0.4778,
      "step": 39920
    },
    {
      "epoch": 1.2263385863054097,
      "grad_norm": 0.4225887656211853,
      "learning_rate": 6.537095208087479e-06,
      "loss": 0.48,
      "step": 39921
    },
    {
      "epoch": 1.2263693054403588,
      "grad_norm": 0.39290085434913635,
      "learning_rate": 6.536641836449946e-06,
      "loss": 0.4214,
      "step": 39922
    },
    {
      "epoch": 1.226400024575308,
      "grad_norm": 0.41483497619628906,
      "learning_rate": 6.536188472901323e-06,
      "loss": 0.4887,
      "step": 39923
    },
    {
      "epoch": 1.226430743710257,
      "grad_norm": 0.4145083427429199,
      "learning_rate": 6.535735117442674e-06,
      "loss": 0.5108,
      "step": 39924
    },
    {
      "epoch": 1.2264614628452062,
      "grad_norm": 0.4337809085845947,
      "learning_rate": 6.535281770075064e-06,
      "loss": 0.509,
      "step": 39925
    },
    {
      "epoch": 1.2264921819801555,
      "grad_norm": 0.3776599168777466,
      "learning_rate": 6.534828430799538e-06,
      "loss": 0.4861,
      "step": 39926
    },
    {
      "epoch": 1.2265229011151046,
      "grad_norm": 0.42771267890930176,
      "learning_rate": 6.534375099617167e-06,
      "loss": 0.4988,
      "step": 39927
    },
    {
      "epoch": 1.2265536202500538,
      "grad_norm": 0.39674681425094604,
      "learning_rate": 6.533921776529e-06,
      "loss": 0.4948,
      "step": 39928
    },
    {
      "epoch": 1.2265843393850029,
      "grad_norm": 0.43147626519203186,
      "learning_rate": 6.5334684615361075e-06,
      "loss": 0.5268,
      "step": 39929
    },
    {
      "epoch": 1.226615058519952,
      "grad_norm": 0.41545453667640686,
      "learning_rate": 6.533015154639535e-06,
      "loss": 0.4113,
      "step": 39930
    },
    {
      "epoch": 1.2266457776549013,
      "grad_norm": 0.4836457669734955,
      "learning_rate": 6.532561855840353e-06,
      "loss": 0.463,
      "step": 39931
    },
    {
      "epoch": 1.2266764967898505,
      "grad_norm": 0.3997834622859955,
      "learning_rate": 6.532108565139612e-06,
      "loss": 0.4968,
      "step": 39932
    },
    {
      "epoch": 1.2267072159247996,
      "grad_norm": 0.3820384740829468,
      "learning_rate": 6.531655282538375e-06,
      "loss": 0.3649,
      "step": 39933
    },
    {
      "epoch": 1.2267379350597487,
      "grad_norm": 0.3818795382976532,
      "learning_rate": 6.531202008037698e-06,
      "loss": 0.5368,
      "step": 39934
    },
    {
      "epoch": 1.2267686541946978,
      "grad_norm": 0.39834529161453247,
      "learning_rate": 6.530748741638641e-06,
      "loss": 0.4978,
      "step": 39935
    },
    {
      "epoch": 1.226799373329647,
      "grad_norm": 0.38736048340797424,
      "learning_rate": 6.530295483342263e-06,
      "loss": 0.4601,
      "step": 39936
    },
    {
      "epoch": 1.2268300924645963,
      "grad_norm": 0.3826312720775604,
      "learning_rate": 6.529842233149623e-06,
      "loss": 0.4067,
      "step": 39937
    },
    {
      "epoch": 1.2268608115995454,
      "grad_norm": 0.39994943141937256,
      "learning_rate": 6.5293889910617784e-06,
      "loss": 0.536,
      "step": 39938
    },
    {
      "epoch": 1.2268915307344945,
      "grad_norm": 0.4099031686782837,
      "learning_rate": 6.528935757079788e-06,
      "loss": 0.496,
      "step": 39939
    },
    {
      "epoch": 1.2269222498694436,
      "grad_norm": 0.36719217896461487,
      "learning_rate": 6.52848253120471e-06,
      "loss": 0.4397,
      "step": 39940
    },
    {
      "epoch": 1.2269529690043928,
      "grad_norm": 0.436987966299057,
      "learning_rate": 6.5280293134376026e-06,
      "loss": 0.517,
      "step": 39941
    },
    {
      "epoch": 1.226983688139342,
      "grad_norm": 0.4577119052410126,
      "learning_rate": 6.527576103779527e-06,
      "loss": 0.509,
      "step": 39942
    },
    {
      "epoch": 1.2270144072742912,
      "grad_norm": 0.41721612215042114,
      "learning_rate": 6.527122902231538e-06,
      "loss": 0.539,
      "step": 39943
    },
    {
      "epoch": 1.2270451264092403,
      "grad_norm": 0.3801136314868927,
      "learning_rate": 6.526669708794699e-06,
      "loss": 0.4908,
      "step": 39944
    },
    {
      "epoch": 1.2270758455441895,
      "grad_norm": 0.45020341873168945,
      "learning_rate": 6.526216523470064e-06,
      "loss": 0.4855,
      "step": 39945
    },
    {
      "epoch": 1.2271065646791386,
      "grad_norm": 0.3732978403568268,
      "learning_rate": 6.525763346258693e-06,
      "loss": 0.4558,
      "step": 39946
    },
    {
      "epoch": 1.2271372838140877,
      "grad_norm": 0.4057992994785309,
      "learning_rate": 6.5253101771616435e-06,
      "loss": 0.4117,
      "step": 39947
    },
    {
      "epoch": 1.227168002949037,
      "grad_norm": 0.3904794156551361,
      "learning_rate": 6.524857016179977e-06,
      "loss": 0.4799,
      "step": 39948
    },
    {
      "epoch": 1.2271987220839862,
      "grad_norm": 0.43496403098106384,
      "learning_rate": 6.5244038633147455e-06,
      "loss": 0.4472,
      "step": 39949
    },
    {
      "epoch": 1.2272294412189353,
      "grad_norm": 0.4027702808380127,
      "learning_rate": 6.523950718567016e-06,
      "loss": 0.5285,
      "step": 39950
    },
    {
      "epoch": 1.2272601603538844,
      "grad_norm": 0.4164176881313324,
      "learning_rate": 6.523497581937839e-06,
      "loss": 0.4813,
      "step": 39951
    },
    {
      "epoch": 1.2272908794888335,
      "grad_norm": 0.41354456543922424,
      "learning_rate": 6.523044453428279e-06,
      "loss": 0.4451,
      "step": 39952
    },
    {
      "epoch": 1.2273215986237829,
      "grad_norm": 0.42592164874076843,
      "learning_rate": 6.522591333039389e-06,
      "loss": 0.4289,
      "step": 39953
    },
    {
      "epoch": 1.227352317758732,
      "grad_norm": 0.394052654504776,
      "learning_rate": 6.522138220772234e-06,
      "loss": 0.527,
      "step": 39954
    },
    {
      "epoch": 1.2273830368936811,
      "grad_norm": 0.4453944265842438,
      "learning_rate": 6.521685116627863e-06,
      "loss": 0.4835,
      "step": 39955
    },
    {
      "epoch": 1.2274137560286302,
      "grad_norm": 0.4017569422721863,
      "learning_rate": 6.521232020607345e-06,
      "loss": 0.5093,
      "step": 39956
    },
    {
      "epoch": 1.2274444751635794,
      "grad_norm": 0.39205342531204224,
      "learning_rate": 6.520778932711724e-06,
      "loss": 0.4613,
      "step": 39957
    },
    {
      "epoch": 1.2274751942985285,
      "grad_norm": 0.3773793876171112,
      "learning_rate": 6.520325852942075e-06,
      "loss": 0.4562,
      "step": 39958
    },
    {
      "epoch": 1.2275059134334776,
      "grad_norm": 0.3900647461414337,
      "learning_rate": 6.5198727812994425e-06,
      "loss": 0.4619,
      "step": 39959
    },
    {
      "epoch": 1.227536632568427,
      "grad_norm": 0.37689363956451416,
      "learning_rate": 6.519419717784891e-06,
      "loss": 0.4022,
      "step": 39960
    },
    {
      "epoch": 1.227567351703376,
      "grad_norm": 0.4143717885017395,
      "learning_rate": 6.518966662399482e-06,
      "loss": 0.4522,
      "step": 39961
    },
    {
      "epoch": 1.2275980708383252,
      "grad_norm": 0.4980081021785736,
      "learning_rate": 6.518513615144264e-06,
      "loss": 0.4984,
      "step": 39962
    },
    {
      "epoch": 1.2276287899732743,
      "grad_norm": 0.3734235167503357,
      "learning_rate": 6.518060576020306e-06,
      "loss": 0.4833,
      "step": 39963
    },
    {
      "epoch": 1.2276595091082236,
      "grad_norm": 0.3979637026786804,
      "learning_rate": 6.517607545028655e-06,
      "loss": 0.4995,
      "step": 39964
    },
    {
      "epoch": 1.2276902282431728,
      "grad_norm": 0.42132067680358887,
      "learning_rate": 6.5171545221703816e-06,
      "loss": 0.5645,
      "step": 39965
    },
    {
      "epoch": 1.2277209473781219,
      "grad_norm": 0.44939911365509033,
      "learning_rate": 6.51670150744653e-06,
      "loss": 0.4742,
      "step": 39966
    },
    {
      "epoch": 1.227751666513071,
      "grad_norm": 0.40394482016563416,
      "learning_rate": 6.516248500858171e-06,
      "loss": 0.433,
      "step": 39967
    },
    {
      "epoch": 1.2277823856480201,
      "grad_norm": 0.37837591767311096,
      "learning_rate": 6.515795502406353e-06,
      "loss": 0.4569,
      "step": 39968
    },
    {
      "epoch": 1.2278131047829692,
      "grad_norm": 0.43185847997665405,
      "learning_rate": 6.515342512092141e-06,
      "loss": 0.5052,
      "step": 39969
    },
    {
      "epoch": 1.2278438239179184,
      "grad_norm": 0.3456041216850281,
      "learning_rate": 6.5148895299165884e-06,
      "loss": 0.4568,
      "step": 39970
    },
    {
      "epoch": 1.2278745430528677,
      "grad_norm": 0.381202757358551,
      "learning_rate": 6.514436555880755e-06,
      "loss": 0.4833,
      "step": 39971
    },
    {
      "epoch": 1.2279052621878168,
      "grad_norm": 0.38804057240486145,
      "learning_rate": 6.513983589985698e-06,
      "loss": 0.5071,
      "step": 39972
    },
    {
      "epoch": 1.227935981322766,
      "grad_norm": 0.4206029176712036,
      "learning_rate": 6.513530632232476e-06,
      "loss": 0.4734,
      "step": 39973
    },
    {
      "epoch": 1.227966700457715,
      "grad_norm": 0.42636770009994507,
      "learning_rate": 6.513077682622145e-06,
      "loss": 0.4247,
      "step": 39974
    },
    {
      "epoch": 1.2279974195926642,
      "grad_norm": 0.40284544229507446,
      "learning_rate": 6.512624741155768e-06,
      "loss": 0.4863,
      "step": 39975
    },
    {
      "epoch": 1.2280281387276135,
      "grad_norm": 0.40461358428001404,
      "learning_rate": 6.512171807834395e-06,
      "loss": 0.5205,
      "step": 39976
    },
    {
      "epoch": 1.2280588578625626,
      "grad_norm": 0.4185521602630615,
      "learning_rate": 6.51171888265909e-06,
      "loss": 0.4321,
      "step": 39977
    },
    {
      "epoch": 1.2280895769975118,
      "grad_norm": 0.4391227960586548,
      "learning_rate": 6.511265965630913e-06,
      "loss": 0.548,
      "step": 39978
    },
    {
      "epoch": 1.2281202961324609,
      "grad_norm": 0.4733844995498657,
      "learning_rate": 6.510813056750913e-06,
      "loss": 0.4307,
      "step": 39979
    },
    {
      "epoch": 1.22815101526741,
      "grad_norm": 0.4326402544975281,
      "learning_rate": 6.510360156020157e-06,
      "loss": 0.4157,
      "step": 39980
    },
    {
      "epoch": 1.2281817344023591,
      "grad_norm": 0.42145267128944397,
      "learning_rate": 6.509907263439694e-06,
      "loss": 0.4903,
      "step": 39981
    },
    {
      "epoch": 1.2282124535373085,
      "grad_norm": 0.4069973826408386,
      "learning_rate": 6.509454379010591e-06,
      "loss": 0.4864,
      "step": 39982
    },
    {
      "epoch": 1.2282431726722576,
      "grad_norm": 0.3979707360267639,
      "learning_rate": 6.5090015027338986e-06,
      "loss": 0.4581,
      "step": 39983
    },
    {
      "epoch": 1.2282738918072067,
      "grad_norm": 0.3752160966396332,
      "learning_rate": 6.5085486346106765e-06,
      "loss": 0.437,
      "step": 39984
    },
    {
      "epoch": 1.2283046109421558,
      "grad_norm": 0.39709171652793884,
      "learning_rate": 6.508095774641983e-06,
      "loss": 0.5172,
      "step": 39985
    },
    {
      "epoch": 1.228335330077105,
      "grad_norm": 0.4210292100906372,
      "learning_rate": 6.507642922828878e-06,
      "loss": 0.4388,
      "step": 39986
    },
    {
      "epoch": 1.2283660492120543,
      "grad_norm": 0.4061720371246338,
      "learning_rate": 6.507190079172414e-06,
      "loss": 0.4954,
      "step": 39987
    },
    {
      "epoch": 1.2283967683470034,
      "grad_norm": 0.4055385887622833,
      "learning_rate": 6.506737243673653e-06,
      "loss": 0.4867,
      "step": 39988
    },
    {
      "epoch": 1.2284274874819525,
      "grad_norm": 0.4141383469104767,
      "learning_rate": 6.506284416333651e-06,
      "loss": 0.4492,
      "step": 39989
    },
    {
      "epoch": 1.2284582066169016,
      "grad_norm": 0.4178287982940674,
      "learning_rate": 6.5058315971534694e-06,
      "loss": 0.49,
      "step": 39990
    },
    {
      "epoch": 1.2284889257518508,
      "grad_norm": 0.40500178933143616,
      "learning_rate": 6.505378786134154e-06,
      "loss": 0.4561,
      "step": 39991
    },
    {
      "epoch": 1.2285196448867999,
      "grad_norm": 0.43326494097709656,
      "learning_rate": 6.5049259832767774e-06,
      "loss": 0.4964,
      "step": 39992
    },
    {
      "epoch": 1.2285503640217492,
      "grad_norm": 0.4132402241230011,
      "learning_rate": 6.504473188582385e-06,
      "loss": 0.5631,
      "step": 39993
    },
    {
      "epoch": 1.2285810831566983,
      "grad_norm": 0.3973047137260437,
      "learning_rate": 6.504020402052046e-06,
      "loss": 0.497,
      "step": 39994
    },
    {
      "epoch": 1.2286118022916475,
      "grad_norm": 0.3835005760192871,
      "learning_rate": 6.503567623686806e-06,
      "loss": 0.507,
      "step": 39995
    },
    {
      "epoch": 1.2286425214265966,
      "grad_norm": 0.38313987851142883,
      "learning_rate": 6.5031148534877275e-06,
      "loss": 0.4913,
      "step": 39996
    },
    {
      "epoch": 1.2286732405615457,
      "grad_norm": 0.48446524143218994,
      "learning_rate": 6.502662091455873e-06,
      "loss": 0.4487,
      "step": 39997
    },
    {
      "epoch": 1.228703959696495,
      "grad_norm": 0.3861658275127411,
      "learning_rate": 6.502209337592291e-06,
      "loss": 0.4814,
      "step": 39998
    },
    {
      "epoch": 1.2287346788314442,
      "grad_norm": 0.39198678731918335,
      "learning_rate": 6.501756591898049e-06,
      "loss": 0.5482,
      "step": 39999
    },
    {
      "epoch": 1.2287653979663933,
      "grad_norm": 0.43593868613243103,
      "learning_rate": 6.501303854374193e-06,
      "loss": 0.5427,
      "step": 40000
    },
    {
      "epoch": 1.2287961171013424,
      "grad_norm": 0.42579492926597595,
      "learning_rate": 6.5008511250217894e-06,
      "loss": 0.5456,
      "step": 40001
    },
    {
      "epoch": 1.2288268362362915,
      "grad_norm": 0.3949185609817505,
      "learning_rate": 6.500398403841892e-06,
      "loss": 0.438,
      "step": 40002
    },
    {
      "epoch": 1.2288575553712406,
      "grad_norm": 0.4462447464466095,
      "learning_rate": 6.499945690835559e-06,
      "loss": 0.4438,
      "step": 40003
    },
    {
      "epoch": 1.22888827450619,
      "grad_norm": 0.37166234850883484,
      "learning_rate": 6.4994929860038455e-06,
      "loss": 0.3531,
      "step": 40004
    },
    {
      "epoch": 1.228918993641139,
      "grad_norm": 0.3964901864528656,
      "learning_rate": 6.499040289347812e-06,
      "loss": 0.5128,
      "step": 40005
    },
    {
      "epoch": 1.2289497127760882,
      "grad_norm": 0.3755132555961609,
      "learning_rate": 6.4985876008685135e-06,
      "loss": 0.5503,
      "step": 40006
    },
    {
      "epoch": 1.2289804319110373,
      "grad_norm": 0.38495445251464844,
      "learning_rate": 6.49813492056701e-06,
      "loss": 0.49,
      "step": 40007
    },
    {
      "epoch": 1.2290111510459865,
      "grad_norm": 0.3948209285736084,
      "learning_rate": 6.497682248444355e-06,
      "loss": 0.3756,
      "step": 40008
    },
    {
      "epoch": 1.2290418701809358,
      "grad_norm": 0.4448241591453552,
      "learning_rate": 6.497229584501608e-06,
      "loss": 0.4865,
      "step": 40009
    },
    {
      "epoch": 1.229072589315885,
      "grad_norm": 0.4218771755695343,
      "learning_rate": 6.496776928739825e-06,
      "loss": 0.4749,
      "step": 40010
    },
    {
      "epoch": 1.229103308450834,
      "grad_norm": 0.4637538492679596,
      "learning_rate": 6.496324281160067e-06,
      "loss": 0.4598,
      "step": 40011
    },
    {
      "epoch": 1.2291340275857832,
      "grad_norm": 0.40155577659606934,
      "learning_rate": 6.495871641763385e-06,
      "loss": 0.4973,
      "step": 40012
    },
    {
      "epoch": 1.2291647467207323,
      "grad_norm": 0.4326263964176178,
      "learning_rate": 6.495419010550843e-06,
      "loss": 0.4477,
      "step": 40013
    },
    {
      "epoch": 1.2291954658556814,
      "grad_norm": 0.39098748564720154,
      "learning_rate": 6.4949663875234916e-06,
      "loss": 0.4254,
      "step": 40014
    },
    {
      "epoch": 1.2292261849906307,
      "grad_norm": 0.4029839336872101,
      "learning_rate": 6.4945137726823916e-06,
      "loss": 0.5276,
      "step": 40015
    },
    {
      "epoch": 1.2292569041255799,
      "grad_norm": 0.3876575827598572,
      "learning_rate": 6.4940611660286e-06,
      "loss": 0.5186,
      "step": 40016
    },
    {
      "epoch": 1.229287623260529,
      "grad_norm": 0.40170037746429443,
      "learning_rate": 6.493608567563173e-06,
      "loss": 0.4386,
      "step": 40017
    },
    {
      "epoch": 1.229318342395478,
      "grad_norm": 0.4416399300098419,
      "learning_rate": 6.49315597728717e-06,
      "loss": 0.544,
      "step": 40018
    },
    {
      "epoch": 1.2293490615304272,
      "grad_norm": 0.37934601306915283,
      "learning_rate": 6.492703395201644e-06,
      "loss": 0.4749,
      "step": 40019
    },
    {
      "epoch": 1.2293797806653766,
      "grad_norm": 0.4265148937702179,
      "learning_rate": 6.492250821307655e-06,
      "loss": 0.4705,
      "step": 40020
    },
    {
      "epoch": 1.2294104998003257,
      "grad_norm": 0.39105966687202454,
      "learning_rate": 6.491798255606258e-06,
      "loss": 0.508,
      "step": 40021
    },
    {
      "epoch": 1.2294412189352748,
      "grad_norm": 0.35748201608657837,
      "learning_rate": 6.4913456980985146e-06,
      "loss": 0.5234,
      "step": 40022
    },
    {
      "epoch": 1.229471938070224,
      "grad_norm": 0.37665855884552,
      "learning_rate": 6.490893148785474e-06,
      "loss": 0.3936,
      "step": 40023
    },
    {
      "epoch": 1.229502657205173,
      "grad_norm": 0.41368308663368225,
      "learning_rate": 6.4904406076682024e-06,
      "loss": 0.4739,
      "step": 40024
    },
    {
      "epoch": 1.2295333763401222,
      "grad_norm": 0.4051779806613922,
      "learning_rate": 6.4899880747477466e-06,
      "loss": 0.4458,
      "step": 40025
    },
    {
      "epoch": 1.2295640954750715,
      "grad_norm": 0.39507365226745605,
      "learning_rate": 6.4895355500251745e-06,
      "loss": 0.4629,
      "step": 40026
    },
    {
      "epoch": 1.2295948146100206,
      "grad_norm": 0.3926432430744171,
      "learning_rate": 6.489083033501531e-06,
      "loss": 0.5303,
      "step": 40027
    },
    {
      "epoch": 1.2296255337449697,
      "grad_norm": 0.418564110994339,
      "learning_rate": 6.488630525177886e-06,
      "loss": 0.478,
      "step": 40028
    },
    {
      "epoch": 1.2296562528799189,
      "grad_norm": 0.4620739221572876,
      "learning_rate": 6.488178025055283e-06,
      "loss": 0.4532,
      "step": 40029
    },
    {
      "epoch": 1.229686972014868,
      "grad_norm": 0.41107216477394104,
      "learning_rate": 6.48772553313479e-06,
      "loss": 0.4643,
      "step": 40030
    },
    {
      "epoch": 1.2297176911498173,
      "grad_norm": 0.39428430795669556,
      "learning_rate": 6.487273049417457e-06,
      "loss": 0.4409,
      "step": 40031
    },
    {
      "epoch": 1.2297484102847664,
      "grad_norm": 0.44845861196517944,
      "learning_rate": 6.486820573904341e-06,
      "loss": 0.4657,
      "step": 40032
    },
    {
      "epoch": 1.2297791294197156,
      "grad_norm": 0.41735637187957764,
      "learning_rate": 6.486368106596506e-06,
      "loss": 0.459,
      "step": 40033
    },
    {
      "epoch": 1.2298098485546647,
      "grad_norm": 0.4409942626953125,
      "learning_rate": 6.485915647494999e-06,
      "loss": 0.4818,
      "step": 40034
    },
    {
      "epoch": 1.2298405676896138,
      "grad_norm": 0.42617955803871155,
      "learning_rate": 6.485463196600888e-06,
      "loss": 0.4787,
      "step": 40035
    },
    {
      "epoch": 1.229871286824563,
      "grad_norm": 0.3979465067386627,
      "learning_rate": 6.4850107539152175e-06,
      "loss": 0.4499,
      "step": 40036
    },
    {
      "epoch": 1.2299020059595123,
      "grad_norm": 0.4009784460067749,
      "learning_rate": 6.484558319439052e-06,
      "loss": 0.4864,
      "step": 40037
    },
    {
      "epoch": 1.2299327250944614,
      "grad_norm": 0.6109302639961243,
      "learning_rate": 6.484105893173445e-06,
      "loss": 0.5412,
      "step": 40038
    },
    {
      "epoch": 1.2299634442294105,
      "grad_norm": 0.3937928378582001,
      "learning_rate": 6.4836534751194555e-06,
      "loss": 0.4614,
      "step": 40039
    },
    {
      "epoch": 1.2299941633643596,
      "grad_norm": 0.43081530928611755,
      "learning_rate": 6.483201065278138e-06,
      "loss": 0.5115,
      "step": 40040
    },
    {
      "epoch": 1.2300248824993087,
      "grad_norm": 0.4714968204498291,
      "learning_rate": 6.48274866365055e-06,
      "loss": 0.5575,
      "step": 40041
    },
    {
      "epoch": 1.230055601634258,
      "grad_norm": 0.41685986518859863,
      "learning_rate": 6.482296270237747e-06,
      "loss": 0.3983,
      "step": 40042
    },
    {
      "epoch": 1.2300863207692072,
      "grad_norm": 0.4259982109069824,
      "learning_rate": 6.481843885040789e-06,
      "loss": 0.5086,
      "step": 40043
    },
    {
      "epoch": 1.2301170399041563,
      "grad_norm": 0.3976724445819855,
      "learning_rate": 6.4813915080607285e-06,
      "loss": 0.4272,
      "step": 40044
    },
    {
      "epoch": 1.2301477590391054,
      "grad_norm": 0.3744586706161499,
      "learning_rate": 6.4809391392986256e-06,
      "loss": 0.3888,
      "step": 40045
    },
    {
      "epoch": 1.2301784781740546,
      "grad_norm": 0.42125627398490906,
      "learning_rate": 6.480486778755532e-06,
      "loss": 0.586,
      "step": 40046
    },
    {
      "epoch": 1.2302091973090037,
      "grad_norm": 0.3979530930519104,
      "learning_rate": 6.480034426432511e-06,
      "loss": 0.5369,
      "step": 40047
    },
    {
      "epoch": 1.230239916443953,
      "grad_norm": 0.39247578382492065,
      "learning_rate": 6.479582082330614e-06,
      "loss": 0.4863,
      "step": 40048
    },
    {
      "epoch": 1.2302706355789021,
      "grad_norm": 0.4031983017921448,
      "learning_rate": 6.4791297464509e-06,
      "loss": 0.5174,
      "step": 40049
    },
    {
      "epoch": 1.2303013547138513,
      "grad_norm": 0.4106149971485138,
      "learning_rate": 6.4786774187944216e-06,
      "loss": 0.48,
      "step": 40050
    },
    {
      "epoch": 1.2303320738488004,
      "grad_norm": 0.40836384892463684,
      "learning_rate": 6.4782250993622385e-06,
      "loss": 0.4728,
      "step": 40051
    },
    {
      "epoch": 1.2303627929837495,
      "grad_norm": 0.465354323387146,
      "learning_rate": 6.4777727881554085e-06,
      "loss": 0.5251,
      "step": 40052
    },
    {
      "epoch": 1.2303935121186989,
      "grad_norm": 0.4092022776603699,
      "learning_rate": 6.477320485174985e-06,
      "loss": 0.4859,
      "step": 40053
    },
    {
      "epoch": 1.230424231253648,
      "grad_norm": 0.39695340394973755,
      "learning_rate": 6.476868190422026e-06,
      "loss": 0.5004,
      "step": 40054
    },
    {
      "epoch": 1.230454950388597,
      "grad_norm": 0.4227778911590576,
      "learning_rate": 6.476415903897587e-06,
      "loss": 0.5773,
      "step": 40055
    },
    {
      "epoch": 1.2304856695235462,
      "grad_norm": 0.42016109824180603,
      "learning_rate": 6.475963625602726e-06,
      "loss": 0.5145,
      "step": 40056
    },
    {
      "epoch": 1.2305163886584953,
      "grad_norm": 0.40122291445732117,
      "learning_rate": 6.475511355538496e-06,
      "loss": 0.5,
      "step": 40057
    },
    {
      "epoch": 1.2305471077934445,
      "grad_norm": 0.3841736614704132,
      "learning_rate": 6.47505909370596e-06,
      "loss": 0.475,
      "step": 40058
    },
    {
      "epoch": 1.2305778269283938,
      "grad_norm": 0.3970603048801422,
      "learning_rate": 6.474606840106164e-06,
      "loss": 0.5402,
      "step": 40059
    },
    {
      "epoch": 1.230608546063343,
      "grad_norm": 0.3731878995895386,
      "learning_rate": 6.474154594740174e-06,
      "loss": 0.4992,
      "step": 40060
    },
    {
      "epoch": 1.230639265198292,
      "grad_norm": 0.36368510127067566,
      "learning_rate": 6.473702357609037e-06,
      "loss": 0.4426,
      "step": 40061
    },
    {
      "epoch": 1.2306699843332412,
      "grad_norm": 0.405612051486969,
      "learning_rate": 6.473250128713822e-06,
      "loss": 0.4928,
      "step": 40062
    },
    {
      "epoch": 1.2307007034681903,
      "grad_norm": 0.521338939666748,
      "learning_rate": 6.472797908055569e-06,
      "loss": 0.5166,
      "step": 40063
    },
    {
      "epoch": 1.2307314226031396,
      "grad_norm": 0.4163051247596741,
      "learning_rate": 6.47234569563535e-06,
      "loss": 0.513,
      "step": 40064
    },
    {
      "epoch": 1.2307621417380887,
      "grad_norm": 0.4230366051197052,
      "learning_rate": 6.471893491454211e-06,
      "loss": 0.4758,
      "step": 40065
    },
    {
      "epoch": 1.2307928608730379,
      "grad_norm": 0.38534015417099,
      "learning_rate": 6.471441295513212e-06,
      "loss": 0.4905,
      "step": 40066
    },
    {
      "epoch": 1.230823580007987,
      "grad_norm": 0.42503002285957336,
      "learning_rate": 6.470989107813406e-06,
      "loss": 0.532,
      "step": 40067
    },
    {
      "epoch": 1.230854299142936,
      "grad_norm": 0.42506542801856995,
      "learning_rate": 6.470536928355855e-06,
      "loss": 0.5196,
      "step": 40068
    },
    {
      "epoch": 1.2308850182778852,
      "grad_norm": 0.40254825353622437,
      "learning_rate": 6.4700847571416084e-06,
      "loss": 0.5742,
      "step": 40069
    },
    {
      "epoch": 1.2309157374128343,
      "grad_norm": 0.4231937527656555,
      "learning_rate": 6.469632594171723e-06,
      "loss": 0.5711,
      "step": 40070
    },
    {
      "epoch": 1.2309464565477837,
      "grad_norm": 0.3959684371948242,
      "learning_rate": 6.4691804394472644e-06,
      "loss": 0.4292,
      "step": 40071
    },
    {
      "epoch": 1.2309771756827328,
      "grad_norm": 0.3871344327926636,
      "learning_rate": 6.468728292969276e-06,
      "loss": 0.4816,
      "step": 40072
    },
    {
      "epoch": 1.231007894817682,
      "grad_norm": 0.3717745840549469,
      "learning_rate": 6.468276154738822e-06,
      "loss": 0.4467,
      "step": 40073
    },
    {
      "epoch": 1.231038613952631,
      "grad_norm": 0.4206722676753998,
      "learning_rate": 6.4678240247569544e-06,
      "loss": 0.4846,
      "step": 40074
    },
    {
      "epoch": 1.2310693330875804,
      "grad_norm": 0.4192754924297333,
      "learning_rate": 6.46737190302473e-06,
      "loss": 0.4823,
      "step": 40075
    },
    {
      "epoch": 1.2311000522225295,
      "grad_norm": 0.46330347657203674,
      "learning_rate": 6.466919789543207e-06,
      "loss": 0.5774,
      "step": 40076
    },
    {
      "epoch": 1.2311307713574786,
      "grad_norm": 0.5488266944885254,
      "learning_rate": 6.46646768431344e-06,
      "loss": 0.4051,
      "step": 40077
    },
    {
      "epoch": 1.2311614904924277,
      "grad_norm": 0.43059632182121277,
      "learning_rate": 6.466015587336481e-06,
      "loss": 0.4247,
      "step": 40078
    },
    {
      "epoch": 1.2311922096273769,
      "grad_norm": 0.38993269205093384,
      "learning_rate": 6.465563498613393e-06,
      "loss": 0.4853,
      "step": 40079
    },
    {
      "epoch": 1.231222928762326,
      "grad_norm": 0.37307971715927124,
      "learning_rate": 6.465111418145225e-06,
      "loss": 0.4621,
      "step": 40080
    },
    {
      "epoch": 1.231253647897275,
      "grad_norm": 0.34351545572280884,
      "learning_rate": 6.46465934593304e-06,
      "loss": 0.4428,
      "step": 40081
    },
    {
      "epoch": 1.2312843670322244,
      "grad_norm": 0.538987934589386,
      "learning_rate": 6.464207281977886e-06,
      "loss": 0.6058,
      "step": 40082
    },
    {
      "epoch": 1.2313150861671736,
      "grad_norm": 0.4193694293498993,
      "learning_rate": 6.463755226280827e-06,
      "loss": 0.432,
      "step": 40083
    },
    {
      "epoch": 1.2313458053021227,
      "grad_norm": 0.4196256697177887,
      "learning_rate": 6.463303178842911e-06,
      "loss": 0.4573,
      "step": 40084
    },
    {
      "epoch": 1.2313765244370718,
      "grad_norm": 0.49814483523368835,
      "learning_rate": 6.462851139665201e-06,
      "loss": 0.4796,
      "step": 40085
    },
    {
      "epoch": 1.231407243572021,
      "grad_norm": 0.42800572514533997,
      "learning_rate": 6.462399108748745e-06,
      "loss": 0.4438,
      "step": 40086
    },
    {
      "epoch": 1.2314379627069703,
      "grad_norm": 0.47295936942100525,
      "learning_rate": 6.461947086094604e-06,
      "loss": 0.5594,
      "step": 40087
    },
    {
      "epoch": 1.2314686818419194,
      "grad_norm": 0.4187174439430237,
      "learning_rate": 6.461495071703835e-06,
      "loss": 0.4805,
      "step": 40088
    },
    {
      "epoch": 1.2314994009768685,
      "grad_norm": 0.3889654874801636,
      "learning_rate": 6.461043065577488e-06,
      "loss": 0.4293,
      "step": 40089
    },
    {
      "epoch": 1.2315301201118176,
      "grad_norm": 0.4099891185760498,
      "learning_rate": 6.460591067716626e-06,
      "loss": 0.5231,
      "step": 40090
    },
    {
      "epoch": 1.2315608392467667,
      "grad_norm": 0.41557809710502625,
      "learning_rate": 6.460139078122299e-06,
      "loss": 0.4378,
      "step": 40091
    },
    {
      "epoch": 1.2315915583817159,
      "grad_norm": 0.40454980731010437,
      "learning_rate": 6.459687096795564e-06,
      "loss": 0.4282,
      "step": 40092
    },
    {
      "epoch": 1.2316222775166652,
      "grad_norm": 0.43143534660339355,
      "learning_rate": 6.459235123737477e-06,
      "loss": 0.5232,
      "step": 40093
    },
    {
      "epoch": 1.2316529966516143,
      "grad_norm": 0.49300047755241394,
      "learning_rate": 6.458783158949097e-06,
      "loss": 0.5467,
      "step": 40094
    },
    {
      "epoch": 1.2316837157865634,
      "grad_norm": 0.38769838213920593,
      "learning_rate": 6.458331202431469e-06,
      "loss": 0.4476,
      "step": 40095
    },
    {
      "epoch": 1.2317144349215126,
      "grad_norm": 0.4249107539653778,
      "learning_rate": 6.457879254185664e-06,
      "loss": 0.5078,
      "step": 40096
    },
    {
      "epoch": 1.2317451540564617,
      "grad_norm": 0.4070116877555847,
      "learning_rate": 6.457427314212723e-06,
      "loss": 0.5478,
      "step": 40097
    },
    {
      "epoch": 1.231775873191411,
      "grad_norm": 0.38521793484687805,
      "learning_rate": 6.456975382513713e-06,
      "loss": 0.4955,
      "step": 40098
    },
    {
      "epoch": 1.2318065923263601,
      "grad_norm": 0.43624332547187805,
      "learning_rate": 6.456523459089681e-06,
      "loss": 0.5071,
      "step": 40099
    },
    {
      "epoch": 1.2318373114613093,
      "grad_norm": 0.42262279987335205,
      "learning_rate": 6.456071543941688e-06,
      "loss": 0.4149,
      "step": 40100
    },
    {
      "epoch": 1.2318680305962584,
      "grad_norm": 0.41786104440689087,
      "learning_rate": 6.4556196370707845e-06,
      "loss": 0.4452,
      "step": 40101
    },
    {
      "epoch": 1.2318987497312075,
      "grad_norm": 0.4237605035305023,
      "learning_rate": 6.455167738478032e-06,
      "loss": 0.5404,
      "step": 40102
    },
    {
      "epoch": 1.2319294688661566,
      "grad_norm": 0.391647070646286,
      "learning_rate": 6.454715848164481e-06,
      "loss": 0.4892,
      "step": 40103
    },
    {
      "epoch": 1.231960188001106,
      "grad_norm": 0.4147752821445465,
      "learning_rate": 6.454263966131189e-06,
      "loss": 0.51,
      "step": 40104
    },
    {
      "epoch": 1.231990907136055,
      "grad_norm": 0.3992515504360199,
      "learning_rate": 6.45381209237921e-06,
      "loss": 0.469,
      "step": 40105
    },
    {
      "epoch": 1.2320216262710042,
      "grad_norm": 0.3964965045452118,
      "learning_rate": 6.453360226909602e-06,
      "loss": 0.5008,
      "step": 40106
    },
    {
      "epoch": 1.2320523454059533,
      "grad_norm": 0.4158400297164917,
      "learning_rate": 6.4529083697234185e-06,
      "loss": 0.4188,
      "step": 40107
    },
    {
      "epoch": 1.2320830645409024,
      "grad_norm": 0.3653981685638428,
      "learning_rate": 6.452456520821715e-06,
      "loss": 0.4951,
      "step": 40108
    },
    {
      "epoch": 1.2321137836758518,
      "grad_norm": 0.40497806668281555,
      "learning_rate": 6.452004680205548e-06,
      "loss": 0.5175,
      "step": 40109
    },
    {
      "epoch": 1.232144502810801,
      "grad_norm": 0.3777776062488556,
      "learning_rate": 6.45155284787597e-06,
      "loss": 0.5241,
      "step": 40110
    },
    {
      "epoch": 1.23217522194575,
      "grad_norm": 0.3950236737728119,
      "learning_rate": 6.451101023834041e-06,
      "loss": 0.4653,
      "step": 40111
    },
    {
      "epoch": 1.2322059410806991,
      "grad_norm": 0.39593783020973206,
      "learning_rate": 6.450649208080811e-06,
      "loss": 0.4411,
      "step": 40112
    },
    {
      "epoch": 1.2322366602156483,
      "grad_norm": 0.40838685631752014,
      "learning_rate": 6.450197400617339e-06,
      "loss": 0.469,
      "step": 40113
    },
    {
      "epoch": 1.2322673793505974,
      "grad_norm": 0.3957135081291199,
      "learning_rate": 6.449745601444678e-06,
      "loss": 0.4902,
      "step": 40114
    },
    {
      "epoch": 1.2322980984855467,
      "grad_norm": 0.3668607771396637,
      "learning_rate": 6.4492938105638855e-06,
      "loss": 0.4834,
      "step": 40115
    },
    {
      "epoch": 1.2323288176204958,
      "grad_norm": 0.4346656799316406,
      "learning_rate": 6.448842027976013e-06,
      "loss": 0.4355,
      "step": 40116
    },
    {
      "epoch": 1.232359536755445,
      "grad_norm": 0.400261253118515,
      "learning_rate": 6.44839025368212e-06,
      "loss": 0.4512,
      "step": 40117
    },
    {
      "epoch": 1.232390255890394,
      "grad_norm": 0.39236992597579956,
      "learning_rate": 6.447938487683258e-06,
      "loss": 0.4221,
      "step": 40118
    },
    {
      "epoch": 1.2324209750253432,
      "grad_norm": 0.39886751770973206,
      "learning_rate": 6.447486729980486e-06,
      "loss": 0.4756,
      "step": 40119
    },
    {
      "epoch": 1.2324516941602925,
      "grad_norm": 0.3679353892803192,
      "learning_rate": 6.447034980574855e-06,
      "loss": 0.4986,
      "step": 40120
    },
    {
      "epoch": 1.2324824132952417,
      "grad_norm": 0.47453048825263977,
      "learning_rate": 6.446583239467425e-06,
      "loss": 0.4857,
      "step": 40121
    },
    {
      "epoch": 1.2325131324301908,
      "grad_norm": 0.3870314955711365,
      "learning_rate": 6.446131506659241e-06,
      "loss": 0.4591,
      "step": 40122
    },
    {
      "epoch": 1.23254385156514,
      "grad_norm": 0.3984334468841553,
      "learning_rate": 6.4456797821513696e-06,
      "loss": 0.5521,
      "step": 40123
    },
    {
      "epoch": 1.232574570700089,
      "grad_norm": 0.396399587392807,
      "learning_rate": 6.445228065944862e-06,
      "loss": 0.4286,
      "step": 40124
    },
    {
      "epoch": 1.2326052898350381,
      "grad_norm": 0.4155430197715759,
      "learning_rate": 6.444776358040771e-06,
      "loss": 0.4331,
      "step": 40125
    },
    {
      "epoch": 1.2326360089699875,
      "grad_norm": 0.39218783378601074,
      "learning_rate": 6.4443246584401545e-06,
      "loss": 0.4453,
      "step": 40126
    },
    {
      "epoch": 1.2326667281049366,
      "grad_norm": 0.46782439947128296,
      "learning_rate": 6.443872967144064e-06,
      "loss": 0.452,
      "step": 40127
    },
    {
      "epoch": 1.2326974472398857,
      "grad_norm": 0.4122389853000641,
      "learning_rate": 6.443421284153562e-06,
      "loss": 0.5128,
      "step": 40128
    },
    {
      "epoch": 1.2327281663748348,
      "grad_norm": 0.4393291175365448,
      "learning_rate": 6.442969609469689e-06,
      "loss": 0.4547,
      "step": 40129
    },
    {
      "epoch": 1.232758885509784,
      "grad_norm": 0.42690733075141907,
      "learning_rate": 6.4425179430935185e-06,
      "loss": 0.4569,
      "step": 40130
    },
    {
      "epoch": 1.2327896046447333,
      "grad_norm": 0.4001777470111847,
      "learning_rate": 6.442066285026087e-06,
      "loss": 0.3905,
      "step": 40131
    },
    {
      "epoch": 1.2328203237796824,
      "grad_norm": 0.41081634163856506,
      "learning_rate": 6.441614635268465e-06,
      "loss": 0.5584,
      "step": 40132
    },
    {
      "epoch": 1.2328510429146315,
      "grad_norm": 0.3748078942298889,
      "learning_rate": 6.441162993821695e-06,
      "loss": 0.5542,
      "step": 40133
    },
    {
      "epoch": 1.2328817620495807,
      "grad_norm": 0.41270995140075684,
      "learning_rate": 6.4407113606868435e-06,
      "loss": 0.4577,
      "step": 40134
    },
    {
      "epoch": 1.2329124811845298,
      "grad_norm": 0.49356669187545776,
      "learning_rate": 6.4402597358649555e-06,
      "loss": 0.4657,
      "step": 40135
    },
    {
      "epoch": 1.232943200319479,
      "grad_norm": 0.507680356502533,
      "learning_rate": 6.43980811935709e-06,
      "loss": 0.4349,
      "step": 40136
    },
    {
      "epoch": 1.2329739194544282,
      "grad_norm": 0.4000544250011444,
      "learning_rate": 6.439356511164301e-06,
      "loss": 0.4825,
      "step": 40137
    },
    {
      "epoch": 1.2330046385893774,
      "grad_norm": 0.49138808250427246,
      "learning_rate": 6.438904911287645e-06,
      "loss": 0.5173,
      "step": 40138
    },
    {
      "epoch": 1.2330353577243265,
      "grad_norm": 0.3841347396373749,
      "learning_rate": 6.438453319728171e-06,
      "loss": 0.4686,
      "step": 40139
    },
    {
      "epoch": 1.2330660768592756,
      "grad_norm": 0.43106409907341003,
      "learning_rate": 6.438001736486943e-06,
      "loss": 0.5064,
      "step": 40140
    },
    {
      "epoch": 1.2330967959942247,
      "grad_norm": 0.39128348231315613,
      "learning_rate": 6.437550161565007e-06,
      "loss": 0.4492,
      "step": 40141
    },
    {
      "epoch": 1.233127515129174,
      "grad_norm": 0.40748685598373413,
      "learning_rate": 6.437098594963422e-06,
      "loss": 0.5324,
      "step": 40142
    },
    {
      "epoch": 1.2331582342641232,
      "grad_norm": 0.4430209994316101,
      "learning_rate": 6.436647036683244e-06,
      "loss": 0.4868,
      "step": 40143
    },
    {
      "epoch": 1.2331889533990723,
      "grad_norm": 0.4048938751220703,
      "learning_rate": 6.436195486725525e-06,
      "loss": 0.4445,
      "step": 40144
    },
    {
      "epoch": 1.2332196725340214,
      "grad_norm": 0.4491131603717804,
      "learning_rate": 6.435743945091321e-06,
      "loss": 0.4658,
      "step": 40145
    },
    {
      "epoch": 1.2332503916689705,
      "grad_norm": 0.4270564019680023,
      "learning_rate": 6.435292411781684e-06,
      "loss": 0.5628,
      "step": 40146
    },
    {
      "epoch": 1.2332811108039197,
      "grad_norm": 0.4045374095439911,
      "learning_rate": 6.434840886797673e-06,
      "loss": 0.491,
      "step": 40147
    },
    {
      "epoch": 1.233311829938869,
      "grad_norm": 0.4277134835720062,
      "learning_rate": 6.434389370140337e-06,
      "loss": 0.4808,
      "step": 40148
    },
    {
      "epoch": 1.2333425490738181,
      "grad_norm": 0.3905918300151825,
      "learning_rate": 6.433937861810736e-06,
      "loss": 0.429,
      "step": 40149
    },
    {
      "epoch": 1.2333732682087672,
      "grad_norm": 0.3847481310367584,
      "learning_rate": 6.4334863618099205e-06,
      "loss": 0.4717,
      "step": 40150
    },
    {
      "epoch": 1.2334039873437164,
      "grad_norm": 0.382651686668396,
      "learning_rate": 6.433034870138949e-06,
      "loss": 0.4731,
      "step": 40151
    },
    {
      "epoch": 1.2334347064786655,
      "grad_norm": 0.4424609839916229,
      "learning_rate": 6.432583386798872e-06,
      "loss": 0.4379,
      "step": 40152
    },
    {
      "epoch": 1.2334654256136148,
      "grad_norm": 0.3955657184123993,
      "learning_rate": 6.432131911790747e-06,
      "loss": 0.4371,
      "step": 40153
    },
    {
      "epoch": 1.233496144748564,
      "grad_norm": 0.39807242155075073,
      "learning_rate": 6.431680445115624e-06,
      "loss": 0.4607,
      "step": 40154
    },
    {
      "epoch": 1.233526863883513,
      "grad_norm": 0.6522780656814575,
      "learning_rate": 6.4312289867745645e-06,
      "loss": 0.4981,
      "step": 40155
    },
    {
      "epoch": 1.2335575830184622,
      "grad_norm": 0.39844632148742676,
      "learning_rate": 6.430777536768616e-06,
      "loss": 0.5175,
      "step": 40156
    },
    {
      "epoch": 1.2335883021534113,
      "grad_norm": 0.3895840048789978,
      "learning_rate": 6.43032609509884e-06,
      "loss": 0.5064,
      "step": 40157
    },
    {
      "epoch": 1.2336190212883604,
      "grad_norm": 0.4033401608467102,
      "learning_rate": 6.42987466176628e-06,
      "loss": 0.3768,
      "step": 40158
    },
    {
      "epoch": 1.2336497404233098,
      "grad_norm": 0.41791588068008423,
      "learning_rate": 6.429423236772004e-06,
      "loss": 0.5777,
      "step": 40159
    },
    {
      "epoch": 1.233680459558259,
      "grad_norm": 0.3987414240837097,
      "learning_rate": 6.428971820117054e-06,
      "loss": 0.4518,
      "step": 40160
    },
    {
      "epoch": 1.233711178693208,
      "grad_norm": 0.3774709403514862,
      "learning_rate": 6.42852041180249e-06,
      "loss": 0.461,
      "step": 40161
    },
    {
      "epoch": 1.2337418978281571,
      "grad_norm": 0.45881032943725586,
      "learning_rate": 6.428069011829371e-06,
      "loss": 0.4484,
      "step": 40162
    },
    {
      "epoch": 1.2337726169631063,
      "grad_norm": 0.48251107335090637,
      "learning_rate": 6.42761762019874e-06,
      "loss": 0.4082,
      "step": 40163
    },
    {
      "epoch": 1.2338033360980556,
      "grad_norm": 0.37243497371673584,
      "learning_rate": 6.427166236911664e-06,
      "loss": 0.5185,
      "step": 40164
    },
    {
      "epoch": 1.2338340552330047,
      "grad_norm": 0.40598922967910767,
      "learning_rate": 6.426714861969185e-06,
      "loss": 0.4296,
      "step": 40165
    },
    {
      "epoch": 1.2338647743679538,
      "grad_norm": 0.3968138098716736,
      "learning_rate": 6.4262634953723676e-06,
      "loss": 0.4609,
      "step": 40166
    },
    {
      "epoch": 1.233895493502903,
      "grad_norm": 0.37107160687446594,
      "learning_rate": 6.425812137122256e-06,
      "loss": 0.394,
      "step": 40167
    },
    {
      "epoch": 1.233926212637852,
      "grad_norm": 0.3939988613128662,
      "learning_rate": 6.4253607872199165e-06,
      "loss": 0.42,
      "step": 40168
    },
    {
      "epoch": 1.2339569317728012,
      "grad_norm": 0.3871891498565674,
      "learning_rate": 6.424909445666392e-06,
      "loss": 0.478,
      "step": 40169
    },
    {
      "epoch": 1.2339876509077505,
      "grad_norm": 0.4319402575492859,
      "learning_rate": 6.424458112462744e-06,
      "loss": 0.568,
      "step": 40170
    },
    {
      "epoch": 1.2340183700426997,
      "grad_norm": 0.3735378682613373,
      "learning_rate": 6.4240067876100196e-06,
      "loss": 0.4483,
      "step": 40171
    },
    {
      "epoch": 1.2340490891776488,
      "grad_norm": 0.45181721448898315,
      "learning_rate": 6.4235554711092805e-06,
      "loss": 0.4771,
      "step": 40172
    },
    {
      "epoch": 1.234079808312598,
      "grad_norm": 0.45630714297294617,
      "learning_rate": 6.4231041629615755e-06,
      "loss": 0.3988,
      "step": 40173
    },
    {
      "epoch": 1.234110527447547,
      "grad_norm": 0.3636225759983063,
      "learning_rate": 6.422652863167962e-06,
      "loss": 0.4959,
      "step": 40174
    },
    {
      "epoch": 1.2341412465824964,
      "grad_norm": 0.37872394919395447,
      "learning_rate": 6.422201571729492e-06,
      "loss": 0.5198,
      "step": 40175
    },
    {
      "epoch": 1.2341719657174455,
      "grad_norm": 0.483165979385376,
      "learning_rate": 6.421750288647221e-06,
      "loss": 0.5271,
      "step": 40176
    },
    {
      "epoch": 1.2342026848523946,
      "grad_norm": 0.393228143453598,
      "learning_rate": 6.4212990139222e-06,
      "loss": 0.4927,
      "step": 40177
    },
    {
      "epoch": 1.2342334039873437,
      "grad_norm": 0.3951447606086731,
      "learning_rate": 6.420847747555485e-06,
      "loss": 0.5036,
      "step": 40178
    },
    {
      "epoch": 1.2342641231222928,
      "grad_norm": 0.41335123777389526,
      "learning_rate": 6.420396489548133e-06,
      "loss": 0.5179,
      "step": 40179
    },
    {
      "epoch": 1.234294842257242,
      "grad_norm": 0.42754560708999634,
      "learning_rate": 6.419945239901191e-06,
      "loss": 0.4855,
      "step": 40180
    },
    {
      "epoch": 1.234325561392191,
      "grad_norm": 0.4024553596973419,
      "learning_rate": 6.41949399861572e-06,
      "loss": 0.5032,
      "step": 40181
    },
    {
      "epoch": 1.2343562805271404,
      "grad_norm": 0.4031878113746643,
      "learning_rate": 6.41904276569277e-06,
      "loss": 0.5276,
      "step": 40182
    },
    {
      "epoch": 1.2343869996620895,
      "grad_norm": 0.40207862854003906,
      "learning_rate": 6.418591541133396e-06,
      "loss": 0.5317,
      "step": 40183
    },
    {
      "epoch": 1.2344177187970387,
      "grad_norm": 0.396876722574234,
      "learning_rate": 6.418140324938651e-06,
      "loss": 0.4894,
      "step": 40184
    },
    {
      "epoch": 1.2344484379319878,
      "grad_norm": 0.41121706366539,
      "learning_rate": 6.4176891171095914e-06,
      "loss": 0.5261,
      "step": 40185
    },
    {
      "epoch": 1.2344791570669371,
      "grad_norm": 0.40206700563430786,
      "learning_rate": 6.417237917647266e-06,
      "loss": 0.5563,
      "step": 40186
    },
    {
      "epoch": 1.2345098762018862,
      "grad_norm": 0.3755887746810913,
      "learning_rate": 6.416786726552734e-06,
      "loss": 0.5228,
      "step": 40187
    },
    {
      "epoch": 1.2345405953368354,
      "grad_norm": 0.40220004320144653,
      "learning_rate": 6.416335543827044e-06,
      "loss": 0.4982,
      "step": 40188
    },
    {
      "epoch": 1.2345713144717845,
      "grad_norm": 0.41234567761421204,
      "learning_rate": 6.415884369471257e-06,
      "loss": 0.4492,
      "step": 40189
    },
    {
      "epoch": 1.2346020336067336,
      "grad_norm": 0.4073432981967926,
      "learning_rate": 6.415433203486419e-06,
      "loss": 0.4709,
      "step": 40190
    },
    {
      "epoch": 1.2346327527416827,
      "grad_norm": 0.3970004916191101,
      "learning_rate": 6.41498204587359e-06,
      "loss": 0.5344,
      "step": 40191
    },
    {
      "epoch": 1.2346634718766318,
      "grad_norm": 0.5236771702766418,
      "learning_rate": 6.414530896633816e-06,
      "loss": 0.4032,
      "step": 40192
    },
    {
      "epoch": 1.2346941910115812,
      "grad_norm": 0.3971310555934906,
      "learning_rate": 6.414079755768161e-06,
      "loss": 0.4685,
      "step": 40193
    },
    {
      "epoch": 1.2347249101465303,
      "grad_norm": 0.42173850536346436,
      "learning_rate": 6.413628623277668e-06,
      "loss": 0.4767,
      "step": 40194
    },
    {
      "epoch": 1.2347556292814794,
      "grad_norm": 0.4230518341064453,
      "learning_rate": 6.413177499163401e-06,
      "loss": 0.5293,
      "step": 40195
    },
    {
      "epoch": 1.2347863484164285,
      "grad_norm": 0.4160398244857788,
      "learning_rate": 6.412726383426403e-06,
      "loss": 0.5209,
      "step": 40196
    },
    {
      "epoch": 1.2348170675513777,
      "grad_norm": 0.38748103380203247,
      "learning_rate": 6.412275276067734e-06,
      "loss": 0.3848,
      "step": 40197
    },
    {
      "epoch": 1.234847786686327,
      "grad_norm": 0.42944663763046265,
      "learning_rate": 6.411824177088452e-06,
      "loss": 0.5472,
      "step": 40198
    },
    {
      "epoch": 1.2348785058212761,
      "grad_norm": 0.43708235025405884,
      "learning_rate": 6.411373086489599e-06,
      "loss": 0.4204,
      "step": 40199
    },
    {
      "epoch": 1.2349092249562252,
      "grad_norm": 0.408955454826355,
      "learning_rate": 6.4109220042722394e-06,
      "loss": 0.4472,
      "step": 40200
    },
    {
      "epoch": 1.2349399440911744,
      "grad_norm": 0.36810070276260376,
      "learning_rate": 6.410470930437418e-06,
      "loss": 0.4186,
      "step": 40201
    },
    {
      "epoch": 1.2349706632261235,
      "grad_norm": 0.3957865834236145,
      "learning_rate": 6.410019864986198e-06,
      "loss": 0.4326,
      "step": 40202
    },
    {
      "epoch": 1.2350013823610726,
      "grad_norm": 0.3991374373435974,
      "learning_rate": 6.4095688079196224e-06,
      "loss": 0.5374,
      "step": 40203
    },
    {
      "epoch": 1.235032101496022,
      "grad_norm": 0.40103113651275635,
      "learning_rate": 6.409117759238752e-06,
      "loss": 0.4836,
      "step": 40204
    },
    {
      "epoch": 1.235062820630971,
      "grad_norm": 0.3782845437526703,
      "learning_rate": 6.4086667189446365e-06,
      "loss": 0.4595,
      "step": 40205
    },
    {
      "epoch": 1.2350935397659202,
      "grad_norm": 0.38176336884498596,
      "learning_rate": 6.408215687038333e-06,
      "loss": 0.4912,
      "step": 40206
    },
    {
      "epoch": 1.2351242589008693,
      "grad_norm": 0.3854520618915558,
      "learning_rate": 6.407764663520889e-06,
      "loss": 0.3969,
      "step": 40207
    },
    {
      "epoch": 1.2351549780358184,
      "grad_norm": 0.39898228645324707,
      "learning_rate": 6.4073136483933655e-06,
      "loss": 0.5332,
      "step": 40208
    },
    {
      "epoch": 1.2351856971707678,
      "grad_norm": 0.4097481966018677,
      "learning_rate": 6.406862641656808e-06,
      "loss": 0.4479,
      "step": 40209
    },
    {
      "epoch": 1.2352164163057169,
      "grad_norm": 0.3959212899208069,
      "learning_rate": 6.406411643312276e-06,
      "loss": 0.3952,
      "step": 40210
    },
    {
      "epoch": 1.235247135440666,
      "grad_norm": 0.4180295169353485,
      "learning_rate": 6.405960653360819e-06,
      "loss": 0.4437,
      "step": 40211
    },
    {
      "epoch": 1.2352778545756151,
      "grad_norm": 0.39764586091041565,
      "learning_rate": 6.405509671803494e-06,
      "loss": 0.4845,
      "step": 40212
    },
    {
      "epoch": 1.2353085737105642,
      "grad_norm": 0.3869525194168091,
      "learning_rate": 6.405058698641351e-06,
      "loss": 0.5316,
      "step": 40213
    },
    {
      "epoch": 1.2353392928455134,
      "grad_norm": 0.40203040838241577,
      "learning_rate": 6.4046077338754454e-06,
      "loss": 0.4724,
      "step": 40214
    },
    {
      "epoch": 1.2353700119804627,
      "grad_norm": 0.3942371904850006,
      "learning_rate": 6.404156777506827e-06,
      "loss": 0.4257,
      "step": 40215
    },
    {
      "epoch": 1.2354007311154118,
      "grad_norm": 0.39585354924201965,
      "learning_rate": 6.403705829536553e-06,
      "loss": 0.4836,
      "step": 40216
    },
    {
      "epoch": 1.235431450250361,
      "grad_norm": 0.3981932997703552,
      "learning_rate": 6.4032548899656755e-06,
      "loss": 0.4473,
      "step": 40217
    },
    {
      "epoch": 1.23546216938531,
      "grad_norm": 0.4299621284008026,
      "learning_rate": 6.402803958795247e-06,
      "loss": 0.4873,
      "step": 40218
    },
    {
      "epoch": 1.2354928885202592,
      "grad_norm": 0.35438841581344604,
      "learning_rate": 6.4023530360263234e-06,
      "loss": 0.4293,
      "step": 40219
    },
    {
      "epoch": 1.2355236076552085,
      "grad_norm": 0.4495788514614105,
      "learning_rate": 6.4019021216599505e-06,
      "loss": 0.4753,
      "step": 40220
    },
    {
      "epoch": 1.2355543267901576,
      "grad_norm": 0.3829928934574127,
      "learning_rate": 6.401451215697192e-06,
      "loss": 0.5239,
      "step": 40221
    },
    {
      "epoch": 1.2355850459251068,
      "grad_norm": 0.4106098711490631,
      "learning_rate": 6.401000318139092e-06,
      "loss": 0.3492,
      "step": 40222
    },
    {
      "epoch": 1.2356157650600559,
      "grad_norm": 0.4136336147785187,
      "learning_rate": 6.400549428986709e-06,
      "loss": 0.5189,
      "step": 40223
    },
    {
      "epoch": 1.235646484195005,
      "grad_norm": 0.37628835439682007,
      "learning_rate": 6.400098548241093e-06,
      "loss": 0.4821,
      "step": 40224
    },
    {
      "epoch": 1.2356772033299541,
      "grad_norm": 0.3904038667678833,
      "learning_rate": 6.3996476759033e-06,
      "loss": 0.4597,
      "step": 40225
    },
    {
      "epoch": 1.2357079224649035,
      "grad_norm": 0.4039047062397003,
      "learning_rate": 6.399196811974378e-06,
      "loss": 0.4551,
      "step": 40226
    },
    {
      "epoch": 1.2357386415998526,
      "grad_norm": 0.38286662101745605,
      "learning_rate": 6.3987459564553874e-06,
      "loss": 0.4562,
      "step": 40227
    },
    {
      "epoch": 1.2357693607348017,
      "grad_norm": 0.44461631774902344,
      "learning_rate": 6.3982951093473735e-06,
      "loss": 0.4504,
      "step": 40228
    },
    {
      "epoch": 1.2358000798697508,
      "grad_norm": 0.3931523859500885,
      "learning_rate": 6.397844270651397e-06,
      "loss": 0.49,
      "step": 40229
    },
    {
      "epoch": 1.2358307990047,
      "grad_norm": 0.38456419110298157,
      "learning_rate": 6.3973934403685015e-06,
      "loss": 0.5143,
      "step": 40230
    },
    {
      "epoch": 1.2358615181396493,
      "grad_norm": 0.36478105187416077,
      "learning_rate": 6.396942618499751e-06,
      "loss": 0.4683,
      "step": 40231
    },
    {
      "epoch": 1.2358922372745984,
      "grad_norm": 0.41113102436065674,
      "learning_rate": 6.396491805046187e-06,
      "loss": 0.4177,
      "step": 40232
    },
    {
      "epoch": 1.2359229564095475,
      "grad_norm": 0.4127441644668579,
      "learning_rate": 6.396041000008869e-06,
      "loss": 0.468,
      "step": 40233
    },
    {
      "epoch": 1.2359536755444966,
      "grad_norm": 0.36758852005004883,
      "learning_rate": 6.395590203388853e-06,
      "loss": 0.5062,
      "step": 40234
    },
    {
      "epoch": 1.2359843946794458,
      "grad_norm": 0.4024151563644409,
      "learning_rate": 6.395139415187184e-06,
      "loss": 0.4152,
      "step": 40235
    },
    {
      "epoch": 1.2360151138143949,
      "grad_norm": 0.4183485805988312,
      "learning_rate": 6.394688635404922e-06,
      "loss": 0.4871,
      "step": 40236
    },
    {
      "epoch": 1.2360458329493442,
      "grad_norm": 0.4058716595172882,
      "learning_rate": 6.394237864043111e-06,
      "loss": 0.475,
      "step": 40237
    },
    {
      "epoch": 1.2360765520842933,
      "grad_norm": 0.41674497723579407,
      "learning_rate": 6.3937871011028165e-06,
      "loss": 0.4989,
      "step": 40238
    },
    {
      "epoch": 1.2361072712192425,
      "grad_norm": 1.0493888854980469,
      "learning_rate": 6.393336346585079e-06,
      "loss": 0.4032,
      "step": 40239
    },
    {
      "epoch": 1.2361379903541916,
      "grad_norm": 0.4795157313346863,
      "learning_rate": 6.392885600490959e-06,
      "loss": 0.5137,
      "step": 40240
    },
    {
      "epoch": 1.2361687094891407,
      "grad_norm": 0.41447126865386963,
      "learning_rate": 6.392434862821504e-06,
      "loss": 0.451,
      "step": 40241
    },
    {
      "epoch": 1.23619942862409,
      "grad_norm": 0.40595659613609314,
      "learning_rate": 6.391984133577772e-06,
      "loss": 0.5033,
      "step": 40242
    },
    {
      "epoch": 1.2362301477590392,
      "grad_norm": 0.41820451617240906,
      "learning_rate": 6.391533412760811e-06,
      "loss": 0.4826,
      "step": 40243
    },
    {
      "epoch": 1.2362608668939883,
      "grad_norm": 0.44519108533859253,
      "learning_rate": 6.391082700371678e-06,
      "loss": 0.4642,
      "step": 40244
    },
    {
      "epoch": 1.2362915860289374,
      "grad_norm": 0.3894633650779724,
      "learning_rate": 6.390631996411421e-06,
      "loss": 0.4893,
      "step": 40245
    },
    {
      "epoch": 1.2363223051638865,
      "grad_norm": 0.502159833908081,
      "learning_rate": 6.390181300881095e-06,
      "loss": 0.5643,
      "step": 40246
    },
    {
      "epoch": 1.2363530242988356,
      "grad_norm": 0.41404953598976135,
      "learning_rate": 6.389730613781754e-06,
      "loss": 0.4924,
      "step": 40247
    },
    {
      "epoch": 1.236383743433785,
      "grad_norm": 0.3890151083469391,
      "learning_rate": 6.38927993511445e-06,
      "loss": 0.4859,
      "step": 40248
    },
    {
      "epoch": 1.236414462568734,
      "grad_norm": 0.43138399720191956,
      "learning_rate": 6.3888292648802315e-06,
      "loss": 0.4195,
      "step": 40249
    },
    {
      "epoch": 1.2364451817036832,
      "grad_norm": 0.39552080631256104,
      "learning_rate": 6.388378603080159e-06,
      "loss": 0.5613,
      "step": 40250
    },
    {
      "epoch": 1.2364759008386323,
      "grad_norm": 0.47291335463523865,
      "learning_rate": 6.387927949715277e-06,
      "loss": 0.4214,
      "step": 40251
    },
    {
      "epoch": 1.2365066199735815,
      "grad_norm": 0.38707810640335083,
      "learning_rate": 6.387477304786641e-06,
      "loss": 0.5233,
      "step": 40252
    },
    {
      "epoch": 1.2365373391085308,
      "grad_norm": 0.390796959400177,
      "learning_rate": 6.387026668295308e-06,
      "loss": 0.4751,
      "step": 40253
    },
    {
      "epoch": 1.23656805824348,
      "grad_norm": 0.40651029348373413,
      "learning_rate": 6.386576040242323e-06,
      "loss": 0.4768,
      "step": 40254
    },
    {
      "epoch": 1.236598777378429,
      "grad_norm": 0.46211865544319153,
      "learning_rate": 6.386125420628744e-06,
      "loss": 0.5971,
      "step": 40255
    },
    {
      "epoch": 1.2366294965133782,
      "grad_norm": 0.4167782664299011,
      "learning_rate": 6.38567480945562e-06,
      "loss": 0.5006,
      "step": 40256
    },
    {
      "epoch": 1.2366602156483273,
      "grad_norm": 0.40347999334335327,
      "learning_rate": 6.385224206724007e-06,
      "loss": 0.4682,
      "step": 40257
    },
    {
      "epoch": 1.2366909347832764,
      "grad_norm": 0.41349050402641296,
      "learning_rate": 6.384773612434952e-06,
      "loss": 0.4627,
      "step": 40258
    },
    {
      "epoch": 1.2367216539182257,
      "grad_norm": 0.3958434462547302,
      "learning_rate": 6.384323026589514e-06,
      "loss": 0.5062,
      "step": 40259
    },
    {
      "epoch": 1.2367523730531749,
      "grad_norm": 0.3756488263607025,
      "learning_rate": 6.38387244918874e-06,
      "loss": 0.4986,
      "step": 40260
    },
    {
      "epoch": 1.236783092188124,
      "grad_norm": 0.3676875829696655,
      "learning_rate": 6.383421880233689e-06,
      "loss": 0.4436,
      "step": 40261
    },
    {
      "epoch": 1.236813811323073,
      "grad_norm": 0.4201688766479492,
      "learning_rate": 6.382971319725402e-06,
      "loss": 0.5615,
      "step": 40262
    },
    {
      "epoch": 1.2368445304580222,
      "grad_norm": 0.4479523301124573,
      "learning_rate": 6.382520767664944e-06,
      "loss": 0.4595,
      "step": 40263
    },
    {
      "epoch": 1.2368752495929716,
      "grad_norm": 0.39822831749916077,
      "learning_rate": 6.382070224053355e-06,
      "loss": 0.554,
      "step": 40264
    },
    {
      "epoch": 1.2369059687279207,
      "grad_norm": 0.40322431921958923,
      "learning_rate": 6.381619688891701e-06,
      "loss": 0.5178,
      "step": 40265
    },
    {
      "epoch": 1.2369366878628698,
      "grad_norm": 0.36512887477874756,
      "learning_rate": 6.38116916218102e-06,
      "loss": 0.439,
      "step": 40266
    },
    {
      "epoch": 1.236967406997819,
      "grad_norm": 0.42622244358062744,
      "learning_rate": 6.380718643922377e-06,
      "loss": 0.5083,
      "step": 40267
    },
    {
      "epoch": 1.236998126132768,
      "grad_norm": 0.4503008723258972,
      "learning_rate": 6.380268134116814e-06,
      "loss": 0.4756,
      "step": 40268
    },
    {
      "epoch": 1.2370288452677172,
      "grad_norm": 0.40036898851394653,
      "learning_rate": 6.379817632765386e-06,
      "loss": 0.4644,
      "step": 40269
    },
    {
      "epoch": 1.2370595644026665,
      "grad_norm": 0.37433066964149475,
      "learning_rate": 6.379367139869154e-06,
      "loss": 0.4747,
      "step": 40270
    },
    {
      "epoch": 1.2370902835376156,
      "grad_norm": 0.4347667098045349,
      "learning_rate": 6.378916655429155e-06,
      "loss": 0.536,
      "step": 40271
    },
    {
      "epoch": 1.2371210026725648,
      "grad_norm": 1.4931886196136475,
      "learning_rate": 6.378466179446456e-06,
      "loss": 0.5311,
      "step": 40272
    },
    {
      "epoch": 1.2371517218075139,
      "grad_norm": 0.39459970593452454,
      "learning_rate": 6.378015711922098e-06,
      "loss": 0.4755,
      "step": 40273
    },
    {
      "epoch": 1.237182440942463,
      "grad_norm": 0.41324248909950256,
      "learning_rate": 6.377565252857141e-06,
      "loss": 0.4429,
      "step": 40274
    },
    {
      "epoch": 1.2372131600774123,
      "grad_norm": 0.5753193497657776,
      "learning_rate": 6.377114802252629e-06,
      "loss": 0.4333,
      "step": 40275
    },
    {
      "epoch": 1.2372438792123615,
      "grad_norm": 0.41908615827560425,
      "learning_rate": 6.376664360109621e-06,
      "loss": 0.5145,
      "step": 40276
    },
    {
      "epoch": 1.2372745983473106,
      "grad_norm": 0.4049200415611267,
      "learning_rate": 6.3762139264291644e-06,
      "loss": 0.4762,
      "step": 40277
    },
    {
      "epoch": 1.2373053174822597,
      "grad_norm": 0.4033043682575226,
      "learning_rate": 6.375763501212315e-06,
      "loss": 0.4957,
      "step": 40278
    },
    {
      "epoch": 1.2373360366172088,
      "grad_norm": 0.41759809851646423,
      "learning_rate": 6.375313084460122e-06,
      "loss": 0.5065,
      "step": 40279
    },
    {
      "epoch": 1.237366755752158,
      "grad_norm": 0.3620065450668335,
      "learning_rate": 6.3748626761736395e-06,
      "loss": 0.5066,
      "step": 40280
    },
    {
      "epoch": 1.2373974748871073,
      "grad_norm": 0.4030841886997223,
      "learning_rate": 6.374412276353916e-06,
      "loss": 0.4216,
      "step": 40281
    },
    {
      "epoch": 1.2374281940220564,
      "grad_norm": 0.3797062039375305,
      "learning_rate": 6.373961885002009e-06,
      "loss": 0.4877,
      "step": 40282
    },
    {
      "epoch": 1.2374589131570055,
      "grad_norm": 0.4300960898399353,
      "learning_rate": 6.373511502118965e-06,
      "loss": 0.4922,
      "step": 40283
    },
    {
      "epoch": 1.2374896322919546,
      "grad_norm": 0.4009098708629608,
      "learning_rate": 6.37306112770584e-06,
      "loss": 0.5629,
      "step": 40284
    },
    {
      "epoch": 1.2375203514269038,
      "grad_norm": 0.46178290247917175,
      "learning_rate": 6.3726107617636825e-06,
      "loss": 0.5154,
      "step": 40285
    },
    {
      "epoch": 1.237551070561853,
      "grad_norm": 0.42490050196647644,
      "learning_rate": 6.372160404293548e-06,
      "loss": 0.482,
      "step": 40286
    },
    {
      "epoch": 1.2375817896968022,
      "grad_norm": 0.40314581990242004,
      "learning_rate": 6.371710055296483e-06,
      "loss": 0.5033,
      "step": 40287
    },
    {
      "epoch": 1.2376125088317513,
      "grad_norm": 0.4081561267375946,
      "learning_rate": 6.371259714773543e-06,
      "loss": 0.4747,
      "step": 40288
    },
    {
      "epoch": 1.2376432279667005,
      "grad_norm": 0.4037840962409973,
      "learning_rate": 6.370809382725782e-06,
      "loss": 0.4793,
      "step": 40289
    },
    {
      "epoch": 1.2376739471016496,
      "grad_norm": 1.0057095289230347,
      "learning_rate": 6.370359059154247e-06,
      "loss": 0.5116,
      "step": 40290
    },
    {
      "epoch": 1.2377046662365987,
      "grad_norm": 0.40323007106781006,
      "learning_rate": 6.369908744059994e-06,
      "loss": 0.4329,
      "step": 40291
    },
    {
      "epoch": 1.2377353853715478,
      "grad_norm": 0.3829009532928467,
      "learning_rate": 6.369458437444069e-06,
      "loss": 0.4839,
      "step": 40292
    },
    {
      "epoch": 1.2377661045064972,
      "grad_norm": 0.3822895884513855,
      "learning_rate": 6.369008139307532e-06,
      "loss": 0.5365,
      "step": 40293
    },
    {
      "epoch": 1.2377968236414463,
      "grad_norm": 0.4124521315097809,
      "learning_rate": 6.368557849651427e-06,
      "loss": 0.4746,
      "step": 40294
    },
    {
      "epoch": 1.2378275427763954,
      "grad_norm": 0.3758434057235718,
      "learning_rate": 6.368107568476812e-06,
      "loss": 0.4692,
      "step": 40295
    },
    {
      "epoch": 1.2378582619113445,
      "grad_norm": 0.44857776165008545,
      "learning_rate": 6.36765729578473e-06,
      "loss": 0.4494,
      "step": 40296
    },
    {
      "epoch": 1.2378889810462939,
      "grad_norm": 0.39286985993385315,
      "learning_rate": 6.367207031576244e-06,
      "loss": 0.4929,
      "step": 40297
    },
    {
      "epoch": 1.237919700181243,
      "grad_norm": 0.41946515440940857,
      "learning_rate": 6.366756775852394e-06,
      "loss": 0.4794,
      "step": 40298
    },
    {
      "epoch": 1.237950419316192,
      "grad_norm": 0.4094868302345276,
      "learning_rate": 6.366306528614243e-06,
      "loss": 0.5747,
      "step": 40299
    },
    {
      "epoch": 1.2379811384511412,
      "grad_norm": 0.37804973125457764,
      "learning_rate": 6.365856289862831e-06,
      "loss": 0.4815,
      "step": 40300
    },
    {
      "epoch": 1.2380118575860903,
      "grad_norm": 0.3993890881538391,
      "learning_rate": 6.365406059599222e-06,
      "loss": 0.4744,
      "step": 40301
    },
    {
      "epoch": 1.2380425767210395,
      "grad_norm": 0.42676886916160583,
      "learning_rate": 6.364955837824456e-06,
      "loss": 0.5108,
      "step": 40302
    },
    {
      "epoch": 1.2380732958559886,
      "grad_norm": 0.3572072684764862,
      "learning_rate": 6.364505624539592e-06,
      "loss": 0.4254,
      "step": 40303
    },
    {
      "epoch": 1.238104014990938,
      "grad_norm": 0.4153217673301697,
      "learning_rate": 6.364055419745676e-06,
      "loss": 0.4797,
      "step": 40304
    },
    {
      "epoch": 1.238134734125887,
      "grad_norm": 0.3897945284843445,
      "learning_rate": 6.363605223443765e-06,
      "loss": 0.446,
      "step": 40305
    },
    {
      "epoch": 1.2381654532608362,
      "grad_norm": 0.377939909696579,
      "learning_rate": 6.363155035634907e-06,
      "loss": 0.5621,
      "step": 40306
    },
    {
      "epoch": 1.2381961723957853,
      "grad_norm": 0.4302099049091339,
      "learning_rate": 6.362704856320152e-06,
      "loss": 0.4802,
      "step": 40307
    },
    {
      "epoch": 1.2382268915307346,
      "grad_norm": 0.3658977448940277,
      "learning_rate": 6.36225468550056e-06,
      "loss": 0.4387,
      "step": 40308
    },
    {
      "epoch": 1.2382576106656837,
      "grad_norm": 0.43876394629478455,
      "learning_rate": 6.361804523177171e-06,
      "loss": 0.4011,
      "step": 40309
    },
    {
      "epoch": 1.2382883298006329,
      "grad_norm": 0.40092653036117554,
      "learning_rate": 6.361354369351045e-06,
      "loss": 0.4823,
      "step": 40310
    },
    {
      "epoch": 1.238319048935582,
      "grad_norm": 0.4111995995044708,
      "learning_rate": 6.360904224023227e-06,
      "loss": 0.4504,
      "step": 40311
    },
    {
      "epoch": 1.238349768070531,
      "grad_norm": 0.38550934195518494,
      "learning_rate": 6.360454087194774e-06,
      "loss": 0.4738,
      "step": 40312
    },
    {
      "epoch": 1.2383804872054802,
      "grad_norm": 0.40683048963546753,
      "learning_rate": 6.360003958866732e-06,
      "loss": 0.4001,
      "step": 40313
    },
    {
      "epoch": 1.2384112063404293,
      "grad_norm": 0.45348507165908813,
      "learning_rate": 6.359553839040158e-06,
      "loss": 0.5528,
      "step": 40314
    },
    {
      "epoch": 1.2384419254753787,
      "grad_norm": 0.8077100515365601,
      "learning_rate": 6.359103727716097e-06,
      "loss": 0.4636,
      "step": 40315
    },
    {
      "epoch": 1.2384726446103278,
      "grad_norm": 0.4580698609352112,
      "learning_rate": 6.358653624895605e-06,
      "loss": 0.4968,
      "step": 40316
    },
    {
      "epoch": 1.238503363745277,
      "grad_norm": 0.3907395899295807,
      "learning_rate": 6.358203530579732e-06,
      "loss": 0.4589,
      "step": 40317
    },
    {
      "epoch": 1.238534082880226,
      "grad_norm": 0.38867315649986267,
      "learning_rate": 6.35775344476953e-06,
      "loss": 0.4428,
      "step": 40318
    },
    {
      "epoch": 1.2385648020151752,
      "grad_norm": 0.43775391578674316,
      "learning_rate": 6.357303367466048e-06,
      "loss": 0.4998,
      "step": 40319
    },
    {
      "epoch": 1.2385955211501245,
      "grad_norm": 0.3992392420768738,
      "learning_rate": 6.356853298670338e-06,
      "loss": 0.4495,
      "step": 40320
    },
    {
      "epoch": 1.2386262402850736,
      "grad_norm": 0.4079326391220093,
      "learning_rate": 6.356403238383452e-06,
      "loss": 0.4481,
      "step": 40321
    },
    {
      "epoch": 1.2386569594200227,
      "grad_norm": 0.4745919108390808,
      "learning_rate": 6.355953186606442e-06,
      "loss": 0.5094,
      "step": 40322
    },
    {
      "epoch": 1.2386876785549719,
      "grad_norm": 0.38984179496765137,
      "learning_rate": 6.355503143340356e-06,
      "loss": 0.4724,
      "step": 40323
    },
    {
      "epoch": 1.238718397689921,
      "grad_norm": 0.41749250888824463,
      "learning_rate": 6.355053108586245e-06,
      "loss": 0.4319,
      "step": 40324
    },
    {
      "epoch": 1.23874911682487,
      "grad_norm": 0.39390984177589417,
      "learning_rate": 6.354603082345165e-06,
      "loss": 0.5137,
      "step": 40325
    },
    {
      "epoch": 1.2387798359598194,
      "grad_norm": 0.3848346769809723,
      "learning_rate": 6.354153064618164e-06,
      "loss": 0.4348,
      "step": 40326
    },
    {
      "epoch": 1.2388105550947686,
      "grad_norm": 0.4580186903476715,
      "learning_rate": 6.3537030554062925e-06,
      "loss": 0.5762,
      "step": 40327
    },
    {
      "epoch": 1.2388412742297177,
      "grad_norm": 0.41328948736190796,
      "learning_rate": 6.353253054710602e-06,
      "loss": 0.4302,
      "step": 40328
    },
    {
      "epoch": 1.2388719933646668,
      "grad_norm": 0.4710099399089813,
      "learning_rate": 6.352803062532146e-06,
      "loss": 0.4787,
      "step": 40329
    },
    {
      "epoch": 1.238902712499616,
      "grad_norm": 0.3648155927658081,
      "learning_rate": 6.35235307887197e-06,
      "loss": 0.5235,
      "step": 40330
    },
    {
      "epoch": 1.2389334316345653,
      "grad_norm": 0.3930925726890564,
      "learning_rate": 6.351903103731132e-06,
      "loss": 0.4761,
      "step": 40331
    },
    {
      "epoch": 1.2389641507695144,
      "grad_norm": 0.3699168264865875,
      "learning_rate": 6.351453137110675e-06,
      "loss": 0.4638,
      "step": 40332
    },
    {
      "epoch": 1.2389948699044635,
      "grad_norm": 0.3475005030632019,
      "learning_rate": 6.351003179011657e-06,
      "loss": 0.4744,
      "step": 40333
    },
    {
      "epoch": 1.2390255890394126,
      "grad_norm": 0.38920459151268005,
      "learning_rate": 6.350553229435121e-06,
      "loss": 0.4265,
      "step": 40334
    },
    {
      "epoch": 1.2390563081743617,
      "grad_norm": 0.40485161542892456,
      "learning_rate": 6.35010328838213e-06,
      "loss": 0.4737,
      "step": 40335
    },
    {
      "epoch": 1.2390870273093109,
      "grad_norm": 0.42227527499198914,
      "learning_rate": 6.3496533558537235e-06,
      "loss": 0.4223,
      "step": 40336
    },
    {
      "epoch": 1.2391177464442602,
      "grad_norm": 0.3943679928779602,
      "learning_rate": 6.349203431850958e-06,
      "loss": 0.4853,
      "step": 40337
    },
    {
      "epoch": 1.2391484655792093,
      "grad_norm": 0.36383113265037537,
      "learning_rate": 6.34875351637488e-06,
      "loss": 0.3788,
      "step": 40338
    },
    {
      "epoch": 1.2391791847141584,
      "grad_norm": 0.41140902042388916,
      "learning_rate": 6.348303609426547e-06,
      "loss": 0.5256,
      "step": 40339
    },
    {
      "epoch": 1.2392099038491076,
      "grad_norm": 0.39173460006713867,
      "learning_rate": 6.347853711007002e-06,
      "loss": 0.4407,
      "step": 40340
    },
    {
      "epoch": 1.2392406229840567,
      "grad_norm": 0.48084190487861633,
      "learning_rate": 6.347403821117303e-06,
      "loss": 0.5504,
      "step": 40341
    },
    {
      "epoch": 1.239271342119006,
      "grad_norm": 0.4051497280597687,
      "learning_rate": 6.346953939758495e-06,
      "loss": 0.4681,
      "step": 40342
    },
    {
      "epoch": 1.2393020612539551,
      "grad_norm": 0.3980984389781952,
      "learning_rate": 6.3465040669316315e-06,
      "loss": 0.5266,
      "step": 40343
    },
    {
      "epoch": 1.2393327803889043,
      "grad_norm": 0.36344119906425476,
      "learning_rate": 6.346054202637765e-06,
      "loss": 0.4227,
      "step": 40344
    },
    {
      "epoch": 1.2393634995238534,
      "grad_norm": 0.41655591130256653,
      "learning_rate": 6.345604346877941e-06,
      "loss": 0.4873,
      "step": 40345
    },
    {
      "epoch": 1.2393942186588025,
      "grad_norm": 0.4079550802707672,
      "learning_rate": 6.345154499653217e-06,
      "loss": 0.4935,
      "step": 40346
    },
    {
      "epoch": 1.2394249377937516,
      "grad_norm": 0.41911736130714417,
      "learning_rate": 6.344704660964637e-06,
      "loss": 0.4693,
      "step": 40347
    },
    {
      "epoch": 1.239455656928701,
      "grad_norm": 0.4242783784866333,
      "learning_rate": 6.344254830813257e-06,
      "loss": 0.5697,
      "step": 40348
    },
    {
      "epoch": 1.23948637606365,
      "grad_norm": 0.40087103843688965,
      "learning_rate": 6.343805009200122e-06,
      "loss": 0.4302,
      "step": 40349
    },
    {
      "epoch": 1.2395170951985992,
      "grad_norm": 0.4162265956401825,
      "learning_rate": 6.343355196126288e-06,
      "loss": 0.5109,
      "step": 40350
    },
    {
      "epoch": 1.2395478143335483,
      "grad_norm": 0.4111569821834564,
      "learning_rate": 6.3429053915928016e-06,
      "loss": 0.4809,
      "step": 40351
    },
    {
      "epoch": 1.2395785334684974,
      "grad_norm": 0.4094749391078949,
      "learning_rate": 6.342455595600718e-06,
      "loss": 0.4795,
      "step": 40352
    },
    {
      "epoch": 1.2396092526034468,
      "grad_norm": 0.4219523072242737,
      "learning_rate": 6.342005808151081e-06,
      "loss": 0.5013,
      "step": 40353
    },
    {
      "epoch": 1.239639971738396,
      "grad_norm": 0.3948803246021271,
      "learning_rate": 6.341556029244948e-06,
      "loss": 0.4608,
      "step": 40354
    },
    {
      "epoch": 1.239670690873345,
      "grad_norm": 0.3990439176559448,
      "learning_rate": 6.341106258883365e-06,
      "loss": 0.5025,
      "step": 40355
    },
    {
      "epoch": 1.2397014100082941,
      "grad_norm": 0.3932631015777588,
      "learning_rate": 6.340656497067386e-06,
      "loss": 0.4982,
      "step": 40356
    },
    {
      "epoch": 1.2397321291432433,
      "grad_norm": 0.44882479310035706,
      "learning_rate": 6.340206743798056e-06,
      "loss": 0.5043,
      "step": 40357
    },
    {
      "epoch": 1.2397628482781924,
      "grad_norm": 0.44984281063079834,
      "learning_rate": 6.339756999076433e-06,
      "loss": 0.5638,
      "step": 40358
    },
    {
      "epoch": 1.2397935674131417,
      "grad_norm": 0.4529239535331726,
      "learning_rate": 6.339307262903558e-06,
      "loss": 0.4903,
      "step": 40359
    },
    {
      "epoch": 1.2398242865480908,
      "grad_norm": 0.382478266954422,
      "learning_rate": 6.338857535280492e-06,
      "loss": 0.4894,
      "step": 40360
    },
    {
      "epoch": 1.23985500568304,
      "grad_norm": 0.3776605427265167,
      "learning_rate": 6.338407816208274e-06,
      "loss": 0.5147,
      "step": 40361
    },
    {
      "epoch": 1.239885724817989,
      "grad_norm": 0.4620261788368225,
      "learning_rate": 6.337958105687961e-06,
      "loss": 0.5598,
      "step": 40362
    },
    {
      "epoch": 1.2399164439529382,
      "grad_norm": 0.40099671483039856,
      "learning_rate": 6.337508403720607e-06,
      "loss": 0.5119,
      "step": 40363
    },
    {
      "epoch": 1.2399471630878875,
      "grad_norm": 0.39178910851478577,
      "learning_rate": 6.337058710307254e-06,
      "loss": 0.4644,
      "step": 40364
    },
    {
      "epoch": 1.2399778822228367,
      "grad_norm": 0.42519187927246094,
      "learning_rate": 6.336609025448961e-06,
      "loss": 0.551,
      "step": 40365
    },
    {
      "epoch": 1.2400086013577858,
      "grad_norm": 0.3866787850856781,
      "learning_rate": 6.3361593491467665e-06,
      "loss": 0.4441,
      "step": 40366
    },
    {
      "epoch": 1.240039320492735,
      "grad_norm": 0.42046621441841125,
      "learning_rate": 6.335709681401735e-06,
      "loss": 0.4952,
      "step": 40367
    },
    {
      "epoch": 1.240070039627684,
      "grad_norm": 0.4505671560764313,
      "learning_rate": 6.335260022214903e-06,
      "loss": 0.4807,
      "step": 40368
    },
    {
      "epoch": 1.2401007587626331,
      "grad_norm": 0.3949449360370636,
      "learning_rate": 6.334810371587333e-06,
      "loss": 0.4888,
      "step": 40369
    },
    {
      "epoch": 1.2401314778975825,
      "grad_norm": 0.4226914346218109,
      "learning_rate": 6.334360729520064e-06,
      "loss": 0.4981,
      "step": 40370
    },
    {
      "epoch": 1.2401621970325316,
      "grad_norm": 0.4057844579219818,
      "learning_rate": 6.333911096014157e-06,
      "loss": 0.5353,
      "step": 40371
    },
    {
      "epoch": 1.2401929161674807,
      "grad_norm": 0.3976956307888031,
      "learning_rate": 6.333461471070652e-06,
      "loss": 0.4979,
      "step": 40372
    },
    {
      "epoch": 1.2402236353024298,
      "grad_norm": 0.37345772981643677,
      "learning_rate": 6.333011854690607e-06,
      "loss": 0.4616,
      "step": 40373
    },
    {
      "epoch": 1.240254354437379,
      "grad_norm": 0.49633359909057617,
      "learning_rate": 6.332562246875067e-06,
      "loss": 0.5191,
      "step": 40374
    },
    {
      "epoch": 1.2402850735723283,
      "grad_norm": 0.41425079107284546,
      "learning_rate": 6.332112647625085e-06,
      "loss": 0.4704,
      "step": 40375
    },
    {
      "epoch": 1.2403157927072774,
      "grad_norm": 0.3854123651981354,
      "learning_rate": 6.331663056941708e-06,
      "loss": 0.4938,
      "step": 40376
    },
    {
      "epoch": 1.2403465118422266,
      "grad_norm": 0.4133965075016022,
      "learning_rate": 6.331213474825991e-06,
      "loss": 0.5079,
      "step": 40377
    },
    {
      "epoch": 1.2403772309771757,
      "grad_norm": 0.39565327763557434,
      "learning_rate": 6.330763901278979e-06,
      "loss": 0.5252,
      "step": 40378
    },
    {
      "epoch": 1.2404079501121248,
      "grad_norm": 0.3761954605579376,
      "learning_rate": 6.330314336301724e-06,
      "loss": 0.4077,
      "step": 40379
    },
    {
      "epoch": 1.240438669247074,
      "grad_norm": 0.4445789158344269,
      "learning_rate": 6.329864779895279e-06,
      "loss": 0.525,
      "step": 40380
    },
    {
      "epoch": 1.2404693883820233,
      "grad_norm": 0.38390353322029114,
      "learning_rate": 6.3294152320606875e-06,
      "loss": 0.441,
      "step": 40381
    },
    {
      "epoch": 1.2405001075169724,
      "grad_norm": 0.4817599952220917,
      "learning_rate": 6.328965692799005e-06,
      "loss": 0.4546,
      "step": 40382
    },
    {
      "epoch": 1.2405308266519215,
      "grad_norm": 0.38708746433258057,
      "learning_rate": 6.3285161621112786e-06,
      "loss": 0.395,
      "step": 40383
    },
    {
      "epoch": 1.2405615457868706,
      "grad_norm": 0.40162596106529236,
      "learning_rate": 6.328066639998561e-06,
      "loss": 0.4493,
      "step": 40384
    },
    {
      "epoch": 1.2405922649218197,
      "grad_norm": 0.39886704087257385,
      "learning_rate": 6.327617126461898e-06,
      "loss": 0.5248,
      "step": 40385
    },
    {
      "epoch": 1.240622984056769,
      "grad_norm": 0.3910784125328064,
      "learning_rate": 6.327167621502343e-06,
      "loss": 0.4356,
      "step": 40386
    },
    {
      "epoch": 1.2406537031917182,
      "grad_norm": 0.40764525532722473,
      "learning_rate": 6.326718125120944e-06,
      "loss": 0.4949,
      "step": 40387
    },
    {
      "epoch": 1.2406844223266673,
      "grad_norm": 0.3933161795139313,
      "learning_rate": 6.326268637318753e-06,
      "loss": 0.4549,
      "step": 40388
    },
    {
      "epoch": 1.2407151414616164,
      "grad_norm": 0.41056230664253235,
      "learning_rate": 6.325819158096816e-06,
      "loss": 0.5184,
      "step": 40389
    },
    {
      "epoch": 1.2407458605965656,
      "grad_norm": 0.3960588276386261,
      "learning_rate": 6.325369687456187e-06,
      "loss": 0.4334,
      "step": 40390
    },
    {
      "epoch": 1.2407765797315147,
      "grad_norm": 0.4443325698375702,
      "learning_rate": 6.32492022539791e-06,
      "loss": 0.4932,
      "step": 40391
    },
    {
      "epoch": 1.240807298866464,
      "grad_norm": 0.394679456949234,
      "learning_rate": 6.3244707719230424e-06,
      "loss": 0.4811,
      "step": 40392
    },
    {
      "epoch": 1.2408380180014131,
      "grad_norm": 0.39706525206565857,
      "learning_rate": 6.324021327032628e-06,
      "loss": 0.4824,
      "step": 40393
    },
    {
      "epoch": 1.2408687371363623,
      "grad_norm": 0.9454624652862549,
      "learning_rate": 6.323571890727722e-06,
      "loss": 0.4746,
      "step": 40394
    },
    {
      "epoch": 1.2408994562713114,
      "grad_norm": 0.4048154950141907,
      "learning_rate": 6.3231224630093635e-06,
      "loss": 0.5049,
      "step": 40395
    },
    {
      "epoch": 1.2409301754062605,
      "grad_norm": 0.3965737521648407,
      "learning_rate": 6.322673043878617e-06,
      "loss": 0.4976,
      "step": 40396
    },
    {
      "epoch": 1.2409608945412098,
      "grad_norm": 0.40517234802246094,
      "learning_rate": 6.3222236333365184e-06,
      "loss": 0.4897,
      "step": 40397
    },
    {
      "epoch": 1.240991613676159,
      "grad_norm": 0.3877079486846924,
      "learning_rate": 6.321774231384125e-06,
      "loss": 0.4705,
      "step": 40398
    },
    {
      "epoch": 1.241022332811108,
      "grad_norm": 0.590505063533783,
      "learning_rate": 6.321324838022489e-06,
      "loss": 0.4628,
      "step": 40399
    },
    {
      "epoch": 1.2410530519460572,
      "grad_norm": 0.37111642956733704,
      "learning_rate": 6.3208754532526484e-06,
      "loss": 0.4314,
      "step": 40400
    },
    {
      "epoch": 1.2410837710810063,
      "grad_norm": 0.45470115542411804,
      "learning_rate": 6.320426077075667e-06,
      "loss": 0.4265,
      "step": 40401
    },
    {
      "epoch": 1.2411144902159554,
      "grad_norm": 0.6756667494773865,
      "learning_rate": 6.319976709492582e-06,
      "loss": 0.5126,
      "step": 40402
    },
    {
      "epoch": 1.2411452093509046,
      "grad_norm": 0.40799564123153687,
      "learning_rate": 6.319527350504453e-06,
      "loss": 0.4749,
      "step": 40403
    },
    {
      "epoch": 1.241175928485854,
      "grad_norm": 0.42942702770233154,
      "learning_rate": 6.31907800011232e-06,
      "loss": 0.4656,
      "step": 40404
    },
    {
      "epoch": 1.241206647620803,
      "grad_norm": 0.41568154096603394,
      "learning_rate": 6.318628658317244e-06,
      "loss": 0.4805,
      "step": 40405
    },
    {
      "epoch": 1.2412373667557521,
      "grad_norm": 0.46453529596328735,
      "learning_rate": 6.318179325120263e-06,
      "loss": 0.5099,
      "step": 40406
    },
    {
      "epoch": 1.2412680858907013,
      "grad_norm": 0.45687049627304077,
      "learning_rate": 6.317730000522433e-06,
      "loss": 0.5029,
      "step": 40407
    },
    {
      "epoch": 1.2412988050256506,
      "grad_norm": 0.4269804060459137,
      "learning_rate": 6.3172806845248e-06,
      "loss": 0.4875,
      "step": 40408
    },
    {
      "epoch": 1.2413295241605997,
      "grad_norm": 0.42517292499542236,
      "learning_rate": 6.316831377128419e-06,
      "loss": 0.4829,
      "step": 40409
    },
    {
      "epoch": 1.2413602432955488,
      "grad_norm": 0.4327138662338257,
      "learning_rate": 6.316382078334331e-06,
      "loss": 0.5216,
      "step": 40410
    },
    {
      "epoch": 1.241390962430498,
      "grad_norm": 0.4304196238517761,
      "learning_rate": 6.315932788143593e-06,
      "loss": 0.5215,
      "step": 40411
    },
    {
      "epoch": 1.241421681565447,
      "grad_norm": 0.41160377860069275,
      "learning_rate": 6.3154835065572494e-06,
      "loss": 0.5135,
      "step": 40412
    },
    {
      "epoch": 1.2414524007003962,
      "grad_norm": 0.38187506794929504,
      "learning_rate": 6.315034233576352e-06,
      "loss": 0.427,
      "step": 40413
    },
    {
      "epoch": 1.2414831198353453,
      "grad_norm": 0.3898296654224396,
      "learning_rate": 6.314584969201949e-06,
      "loss": 0.4396,
      "step": 40414
    },
    {
      "epoch": 1.2415138389702947,
      "grad_norm": 0.4076257050037384,
      "learning_rate": 6.31413571343509e-06,
      "loss": 0.4756,
      "step": 40415
    },
    {
      "epoch": 1.2415445581052438,
      "grad_norm": 0.4069412648677826,
      "learning_rate": 6.313686466276826e-06,
      "loss": 0.4559,
      "step": 40416
    },
    {
      "epoch": 1.241575277240193,
      "grad_norm": 0.3881126940250397,
      "learning_rate": 6.313237227728204e-06,
      "loss": 0.4893,
      "step": 40417
    },
    {
      "epoch": 1.241605996375142,
      "grad_norm": 0.41910889744758606,
      "learning_rate": 6.312787997790274e-06,
      "loss": 0.5129,
      "step": 40418
    },
    {
      "epoch": 1.2416367155100914,
      "grad_norm": 0.3928549587726593,
      "learning_rate": 6.312338776464084e-06,
      "loss": 0.447,
      "step": 40419
    },
    {
      "epoch": 1.2416674346450405,
      "grad_norm": 0.5527915358543396,
      "learning_rate": 6.311889563750686e-06,
      "loss": 0.3468,
      "step": 40420
    },
    {
      "epoch": 1.2416981537799896,
      "grad_norm": 0.39458632469177246,
      "learning_rate": 6.311440359651127e-06,
      "loss": 0.4814,
      "step": 40421
    },
    {
      "epoch": 1.2417288729149387,
      "grad_norm": 0.3789803683757782,
      "learning_rate": 6.310991164166457e-06,
      "loss": 0.5059,
      "step": 40422
    },
    {
      "epoch": 1.2417595920498878,
      "grad_norm": 0.43966078758239746,
      "learning_rate": 6.310541977297724e-06,
      "loss": 0.4525,
      "step": 40423
    },
    {
      "epoch": 1.241790311184837,
      "grad_norm": 0.4026927649974823,
      "learning_rate": 6.310092799045978e-06,
      "loss": 0.4672,
      "step": 40424
    },
    {
      "epoch": 1.241821030319786,
      "grad_norm": 0.3974359929561615,
      "learning_rate": 6.309643629412267e-06,
      "loss": 0.5112,
      "step": 40425
    },
    {
      "epoch": 1.2418517494547354,
      "grad_norm": 0.3943782150745392,
      "learning_rate": 6.309194468397643e-06,
      "loss": 0.4818,
      "step": 40426
    },
    {
      "epoch": 1.2418824685896845,
      "grad_norm": 0.41689959168434143,
      "learning_rate": 6.308745316003152e-06,
      "loss": 0.5266,
      "step": 40427
    },
    {
      "epoch": 1.2419131877246337,
      "grad_norm": 0.40539178252220154,
      "learning_rate": 6.308296172229848e-06,
      "loss": 0.4525,
      "step": 40428
    },
    {
      "epoch": 1.2419439068595828,
      "grad_norm": 0.41518157720565796,
      "learning_rate": 6.307847037078769e-06,
      "loss": 0.503,
      "step": 40429
    },
    {
      "epoch": 1.241974625994532,
      "grad_norm": 0.4061320126056671,
      "learning_rate": 6.307397910550977e-06,
      "loss": 0.5156,
      "step": 40430
    },
    {
      "epoch": 1.2420053451294812,
      "grad_norm": 0.3938910961151123,
      "learning_rate": 6.306948792647509e-06,
      "loss": 0.4759,
      "step": 40431
    },
    {
      "epoch": 1.2420360642644304,
      "grad_norm": 0.417732298374176,
      "learning_rate": 6.306499683369427e-06,
      "loss": 0.5258,
      "step": 40432
    },
    {
      "epoch": 1.2420667833993795,
      "grad_norm": 0.3975021541118622,
      "learning_rate": 6.3060505827177666e-06,
      "loss": 0.4633,
      "step": 40433
    },
    {
      "epoch": 1.2420975025343286,
      "grad_norm": 0.38773441314697266,
      "learning_rate": 6.305601490693586e-06,
      "loss": 0.4513,
      "step": 40434
    },
    {
      "epoch": 1.2421282216692777,
      "grad_norm": 0.43703293800354004,
      "learning_rate": 6.3051524072979346e-06,
      "loss": 0.4226,
      "step": 40435
    },
    {
      "epoch": 1.2421589408042268,
      "grad_norm": 0.39533862471580505,
      "learning_rate": 6.304703332531851e-06,
      "loss": 0.5044,
      "step": 40436
    },
    {
      "epoch": 1.2421896599391762,
      "grad_norm": 0.37448200583457947,
      "learning_rate": 6.304254266396397e-06,
      "loss": 0.4751,
      "step": 40437
    },
    {
      "epoch": 1.2422203790741253,
      "grad_norm": 0.4078150689601898,
      "learning_rate": 6.303805208892609e-06,
      "loss": 0.5058,
      "step": 40438
    },
    {
      "epoch": 1.2422510982090744,
      "grad_norm": 0.3616626262664795,
      "learning_rate": 6.30335616002155e-06,
      "loss": 0.4368,
      "step": 40439
    },
    {
      "epoch": 1.2422818173440235,
      "grad_norm": 0.3746935725212097,
      "learning_rate": 6.302907119784254e-06,
      "loss": 0.4367,
      "step": 40440
    },
    {
      "epoch": 1.2423125364789727,
      "grad_norm": 0.41305652260780334,
      "learning_rate": 6.30245808818178e-06,
      "loss": 0.4975,
      "step": 40441
    },
    {
      "epoch": 1.242343255613922,
      "grad_norm": 0.3918651342391968,
      "learning_rate": 6.302009065215171e-06,
      "loss": 0.5049,
      "step": 40442
    },
    {
      "epoch": 1.2423739747488711,
      "grad_norm": 0.4428272545337677,
      "learning_rate": 6.301560050885481e-06,
      "loss": 0.5341,
      "step": 40443
    },
    {
      "epoch": 1.2424046938838202,
      "grad_norm": 0.5075063109397888,
      "learning_rate": 6.301111045193753e-06,
      "loss": 0.4989,
      "step": 40444
    },
    {
      "epoch": 1.2424354130187694,
      "grad_norm": 0.4112776517868042,
      "learning_rate": 6.300662048141042e-06,
      "loss": 0.487,
      "step": 40445
    },
    {
      "epoch": 1.2424661321537185,
      "grad_norm": 0.39257100224494934,
      "learning_rate": 6.300213059728389e-06,
      "loss": 0.4143,
      "step": 40446
    },
    {
      "epoch": 1.2424968512886676,
      "grad_norm": 0.4186182916164398,
      "learning_rate": 6.299764079956851e-06,
      "loss": 0.4994,
      "step": 40447
    },
    {
      "epoch": 1.242527570423617,
      "grad_norm": 0.47229069471359253,
      "learning_rate": 6.299315108827468e-06,
      "loss": 0.5288,
      "step": 40448
    },
    {
      "epoch": 1.242558289558566,
      "grad_norm": 0.39613744616508484,
      "learning_rate": 6.298866146341296e-06,
      "loss": 0.4539,
      "step": 40449
    },
    {
      "epoch": 1.2425890086935152,
      "grad_norm": 0.40057164430618286,
      "learning_rate": 6.2984171924993795e-06,
      "loss": 0.4595,
      "step": 40450
    },
    {
      "epoch": 1.2426197278284643,
      "grad_norm": 0.4344346523284912,
      "learning_rate": 6.29796824730277e-06,
      "loss": 0.5441,
      "step": 40451
    },
    {
      "epoch": 1.2426504469634134,
      "grad_norm": 0.3932739496231079,
      "learning_rate": 6.297519310752511e-06,
      "loss": 0.4584,
      "step": 40452
    },
    {
      "epoch": 1.2426811660983628,
      "grad_norm": 0.549072802066803,
      "learning_rate": 6.297070382849655e-06,
      "loss": 0.437,
      "step": 40453
    },
    {
      "epoch": 1.2427118852333119,
      "grad_norm": 0.395950585603714,
      "learning_rate": 6.296621463595252e-06,
      "loss": 0.5206,
      "step": 40454
    },
    {
      "epoch": 1.242742604368261,
      "grad_norm": 0.4360170364379883,
      "learning_rate": 6.296172552990345e-06,
      "loss": 0.4769,
      "step": 40455
    },
    {
      "epoch": 1.2427733235032101,
      "grad_norm": 0.3808812201023102,
      "learning_rate": 6.295723651035989e-06,
      "loss": 0.4923,
      "step": 40456
    },
    {
      "epoch": 1.2428040426381592,
      "grad_norm": 0.3765101134777069,
      "learning_rate": 6.295274757733226e-06,
      "loss": 0.456,
      "step": 40457
    },
    {
      "epoch": 1.2428347617731084,
      "grad_norm": 0.39096546173095703,
      "learning_rate": 6.2948258730831105e-06,
      "loss": 0.45,
      "step": 40458
    },
    {
      "epoch": 1.2428654809080577,
      "grad_norm": 0.4202808439731598,
      "learning_rate": 6.294376997086685e-06,
      "loss": 0.4704,
      "step": 40459
    },
    {
      "epoch": 1.2428962000430068,
      "grad_norm": 0.3799503445625305,
      "learning_rate": 6.293928129745004e-06,
      "loss": 0.4639,
      "step": 40460
    },
    {
      "epoch": 1.242926919177956,
      "grad_norm": 0.39327272772789,
      "learning_rate": 6.29347927105911e-06,
      "loss": 0.4986,
      "step": 40461
    },
    {
      "epoch": 1.242957638312905,
      "grad_norm": 0.3991181552410126,
      "learning_rate": 6.293030421030055e-06,
      "loss": 0.5556,
      "step": 40462
    },
    {
      "epoch": 1.2429883574478542,
      "grad_norm": 0.4464489817619324,
      "learning_rate": 6.2925815796588865e-06,
      "loss": 0.4887,
      "step": 40463
    },
    {
      "epoch": 1.2430190765828035,
      "grad_norm": 0.42953938245773315,
      "learning_rate": 6.292132746946655e-06,
      "loss": 0.4749,
      "step": 40464
    },
    {
      "epoch": 1.2430497957177526,
      "grad_norm": 0.4540750980377197,
      "learning_rate": 6.2916839228944e-06,
      "loss": 0.49,
      "step": 40465
    },
    {
      "epoch": 1.2430805148527018,
      "grad_norm": 0.4175678789615631,
      "learning_rate": 6.291235107503184e-06,
      "loss": 0.5201,
      "step": 40466
    },
    {
      "epoch": 1.2431112339876509,
      "grad_norm": 0.44154706597328186,
      "learning_rate": 6.290786300774041e-06,
      "loss": 0.5106,
      "step": 40467
    },
    {
      "epoch": 1.2431419531226,
      "grad_norm": 0.4798579812049866,
      "learning_rate": 6.290337502708032e-06,
      "loss": 0.5324,
      "step": 40468
    },
    {
      "epoch": 1.2431726722575491,
      "grad_norm": 0.4002624750137329,
      "learning_rate": 6.289888713306194e-06,
      "loss": 0.4968,
      "step": 40469
    },
    {
      "epoch": 1.2432033913924985,
      "grad_norm": 0.4054640233516693,
      "learning_rate": 6.289439932569578e-06,
      "loss": 0.4226,
      "step": 40470
    },
    {
      "epoch": 1.2432341105274476,
      "grad_norm": 0.3705909848213196,
      "learning_rate": 6.288991160499241e-06,
      "loss": 0.4468,
      "step": 40471
    },
    {
      "epoch": 1.2432648296623967,
      "grad_norm": 0.38318756222724915,
      "learning_rate": 6.288542397096216e-06,
      "loss": 0.4374,
      "step": 40472
    },
    {
      "epoch": 1.2432955487973458,
      "grad_norm": 0.44933050870895386,
      "learning_rate": 6.288093642361568e-06,
      "loss": 0.6709,
      "step": 40473
    },
    {
      "epoch": 1.243326267932295,
      "grad_norm": 0.45448577404022217,
      "learning_rate": 6.2876448962963285e-06,
      "loss": 0.5069,
      "step": 40474
    },
    {
      "epoch": 1.2433569870672443,
      "grad_norm": 0.39460960030555725,
      "learning_rate": 6.287196158901561e-06,
      "loss": 0.5036,
      "step": 40475
    },
    {
      "epoch": 1.2433877062021934,
      "grad_norm": 0.4078461229801178,
      "learning_rate": 6.286747430178302e-06,
      "loss": 0.4986,
      "step": 40476
    },
    {
      "epoch": 1.2434184253371425,
      "grad_norm": 0.43791663646698,
      "learning_rate": 6.2862987101276056e-06,
      "loss": 0.4604,
      "step": 40477
    },
    {
      "epoch": 1.2434491444720916,
      "grad_norm": 0.40630337595939636,
      "learning_rate": 6.285849998750516e-06,
      "loss": 0.5007,
      "step": 40478
    },
    {
      "epoch": 1.2434798636070408,
      "grad_norm": 0.4000517427921295,
      "learning_rate": 6.285401296048085e-06,
      "loss": 0.5018,
      "step": 40479
    },
    {
      "epoch": 1.24351058274199,
      "grad_norm": 0.4626564383506775,
      "learning_rate": 6.284952602021357e-06,
      "loss": 0.4886,
      "step": 40480
    },
    {
      "epoch": 1.2435413018769392,
      "grad_norm": 0.3987131118774414,
      "learning_rate": 6.284503916671383e-06,
      "loss": 0.4578,
      "step": 40481
    },
    {
      "epoch": 1.2435720210118884,
      "grad_norm": 0.3902384340763092,
      "learning_rate": 6.284055239999208e-06,
      "loss": 0.5083,
      "step": 40482
    },
    {
      "epoch": 1.2436027401468375,
      "grad_norm": 0.4195041358470917,
      "learning_rate": 6.2836065720058835e-06,
      "loss": 0.5377,
      "step": 40483
    },
    {
      "epoch": 1.2436334592817866,
      "grad_norm": 0.4070850908756256,
      "learning_rate": 6.283157912692454e-06,
      "loss": 0.5531,
      "step": 40484
    },
    {
      "epoch": 1.2436641784167357,
      "grad_norm": 0.39121270179748535,
      "learning_rate": 6.28270926205997e-06,
      "loss": 0.4513,
      "step": 40485
    },
    {
      "epoch": 1.243694897551685,
      "grad_norm": 0.39539143443107605,
      "learning_rate": 6.282260620109476e-06,
      "loss": 0.5469,
      "step": 40486
    },
    {
      "epoch": 1.2437256166866342,
      "grad_norm": 0.42768508195877075,
      "learning_rate": 6.281811986842023e-06,
      "loss": 0.5346,
      "step": 40487
    },
    {
      "epoch": 1.2437563358215833,
      "grad_norm": 0.388704776763916,
      "learning_rate": 6.281363362258658e-06,
      "loss": 0.4398,
      "step": 40488
    },
    {
      "epoch": 1.2437870549565324,
      "grad_norm": 0.4328747093677521,
      "learning_rate": 6.280914746360427e-06,
      "loss": 0.4706,
      "step": 40489
    },
    {
      "epoch": 1.2438177740914815,
      "grad_norm": 0.4134398400783539,
      "learning_rate": 6.280466139148383e-06,
      "loss": 0.5528,
      "step": 40490
    },
    {
      "epoch": 1.2438484932264307,
      "grad_norm": 0.3822793662548065,
      "learning_rate": 6.280017540623567e-06,
      "loss": 0.492,
      "step": 40491
    },
    {
      "epoch": 1.24387921236138,
      "grad_norm": 0.36558303236961365,
      "learning_rate": 6.279568950787032e-06,
      "loss": 0.4675,
      "step": 40492
    },
    {
      "epoch": 1.2439099314963291,
      "grad_norm": 0.41326406598091125,
      "learning_rate": 6.279120369639822e-06,
      "loss": 0.5351,
      "step": 40493
    },
    {
      "epoch": 1.2439406506312782,
      "grad_norm": 0.40337690711021423,
      "learning_rate": 6.278671797182987e-06,
      "loss": 0.5131,
      "step": 40494
    },
    {
      "epoch": 1.2439713697662274,
      "grad_norm": 0.3952043354511261,
      "learning_rate": 6.278223233417573e-06,
      "loss": 0.5105,
      "step": 40495
    },
    {
      "epoch": 1.2440020889011765,
      "grad_norm": 0.40056711435317993,
      "learning_rate": 6.277774678344629e-06,
      "loss": 0.4766,
      "step": 40496
    },
    {
      "epoch": 1.2440328080361258,
      "grad_norm": 0.39657124876976013,
      "learning_rate": 6.2773261319652026e-06,
      "loss": 0.5157,
      "step": 40497
    },
    {
      "epoch": 1.244063527171075,
      "grad_norm": 0.40219956636428833,
      "learning_rate": 6.276877594280343e-06,
      "loss": 0.5684,
      "step": 40498
    },
    {
      "epoch": 1.244094246306024,
      "grad_norm": 0.45289427042007446,
      "learning_rate": 6.27642906529109e-06,
      "loss": 0.4394,
      "step": 40499
    },
    {
      "epoch": 1.2441249654409732,
      "grad_norm": 0.4670129716396332,
      "learning_rate": 6.275980544998503e-06,
      "loss": 0.4776,
      "step": 40500
    },
    {
      "epoch": 1.2441556845759223,
      "grad_norm": 0.3855265974998474,
      "learning_rate": 6.27553203340362e-06,
      "loss": 0.4636,
      "step": 40501
    },
    {
      "epoch": 1.2441864037108714,
      "grad_norm": 0.3850870728492737,
      "learning_rate": 6.275083530507495e-06,
      "loss": 0.4597,
      "step": 40502
    },
    {
      "epoch": 1.2442171228458208,
      "grad_norm": 0.4298243224620819,
      "learning_rate": 6.274635036311167e-06,
      "loss": 0.5103,
      "step": 40503
    },
    {
      "epoch": 1.2442478419807699,
      "grad_norm": 0.40451711416244507,
      "learning_rate": 6.274186550815697e-06,
      "loss": 0.4268,
      "step": 40504
    },
    {
      "epoch": 1.244278561115719,
      "grad_norm": 0.47958996891975403,
      "learning_rate": 6.273738074022119e-06,
      "loss": 0.477,
      "step": 40505
    },
    {
      "epoch": 1.2443092802506681,
      "grad_norm": 0.432657927274704,
      "learning_rate": 6.273289605931487e-06,
      "loss": 0.4727,
      "step": 40506
    },
    {
      "epoch": 1.2443399993856172,
      "grad_norm": 0.41646742820739746,
      "learning_rate": 6.272841146544848e-06,
      "loss": 0.5628,
      "step": 40507
    },
    {
      "epoch": 1.2443707185205666,
      "grad_norm": 0.42151254415512085,
      "learning_rate": 6.272392695863245e-06,
      "loss": 0.4425,
      "step": 40508
    },
    {
      "epoch": 1.2444014376555157,
      "grad_norm": 0.39710772037506104,
      "learning_rate": 6.271944253887735e-06,
      "loss": 0.4304,
      "step": 40509
    },
    {
      "epoch": 1.2444321567904648,
      "grad_norm": 0.3970654010772705,
      "learning_rate": 6.271495820619357e-06,
      "loss": 0.4883,
      "step": 40510
    },
    {
      "epoch": 1.244462875925414,
      "grad_norm": 0.38443371653556824,
      "learning_rate": 6.271047396059162e-06,
      "loss": 0.4365,
      "step": 40511
    },
    {
      "epoch": 1.244493595060363,
      "grad_norm": 0.4128120243549347,
      "learning_rate": 6.270598980208194e-06,
      "loss": 0.4387,
      "step": 40512
    },
    {
      "epoch": 1.2445243141953122,
      "grad_norm": 0.39633285999298096,
      "learning_rate": 6.270150573067504e-06,
      "loss": 0.513,
      "step": 40513
    },
    {
      "epoch": 1.2445550333302613,
      "grad_norm": 0.39442259073257446,
      "learning_rate": 6.269702174638137e-06,
      "loss": 0.4289,
      "step": 40514
    },
    {
      "epoch": 1.2445857524652106,
      "grad_norm": 0.39572402834892273,
      "learning_rate": 6.269253784921144e-06,
      "loss": 0.4464,
      "step": 40515
    },
    {
      "epoch": 1.2446164716001598,
      "grad_norm": 0.4208093583583832,
      "learning_rate": 6.268805403917565e-06,
      "loss": 0.4445,
      "step": 40516
    },
    {
      "epoch": 1.2446471907351089,
      "grad_norm": 0.4244927167892456,
      "learning_rate": 6.268357031628455e-06,
      "loss": 0.5044,
      "step": 40517
    },
    {
      "epoch": 1.244677909870058,
      "grad_norm": 0.42995381355285645,
      "learning_rate": 6.267908668054855e-06,
      "loss": 0.439,
      "step": 40518
    },
    {
      "epoch": 1.2447086290050073,
      "grad_norm": 0.4335392415523529,
      "learning_rate": 6.267460313197817e-06,
      "loss": 0.5315,
      "step": 40519
    },
    {
      "epoch": 1.2447393481399565,
      "grad_norm": 0.3576936721801758,
      "learning_rate": 6.267011967058385e-06,
      "loss": 0.3538,
      "step": 40520
    },
    {
      "epoch": 1.2447700672749056,
      "grad_norm": 0.3942754566669464,
      "learning_rate": 6.266563629637609e-06,
      "loss": 0.5024,
      "step": 40521
    },
    {
      "epoch": 1.2448007864098547,
      "grad_norm": 0.3936404287815094,
      "learning_rate": 6.266115300936531e-06,
      "loss": 0.4291,
      "step": 40522
    },
    {
      "epoch": 1.2448315055448038,
      "grad_norm": 0.40609267354011536,
      "learning_rate": 6.265666980956205e-06,
      "loss": 0.394,
      "step": 40523
    },
    {
      "epoch": 1.244862224679753,
      "grad_norm": 0.40222784876823425,
      "learning_rate": 6.265218669697673e-06,
      "loss": 0.4542,
      "step": 40524
    },
    {
      "epoch": 1.244892943814702,
      "grad_norm": 0.406762033700943,
      "learning_rate": 6.264770367161982e-06,
      "loss": 0.4618,
      "step": 40525
    },
    {
      "epoch": 1.2449236629496514,
      "grad_norm": 0.38946405053138733,
      "learning_rate": 6.264322073350184e-06,
      "loss": 0.4711,
      "step": 40526
    },
    {
      "epoch": 1.2449543820846005,
      "grad_norm": 0.4046754837036133,
      "learning_rate": 6.263873788263319e-06,
      "loss": 0.5228,
      "step": 40527
    },
    {
      "epoch": 1.2449851012195496,
      "grad_norm": 0.379461407661438,
      "learning_rate": 6.2634255119024415e-06,
      "loss": 0.4829,
      "step": 40528
    },
    {
      "epoch": 1.2450158203544988,
      "grad_norm": 0.4122847020626068,
      "learning_rate": 6.2629772442685925e-06,
      "loss": 0.4499,
      "step": 40529
    },
    {
      "epoch": 1.245046539489448,
      "grad_norm": 0.389812707901001,
      "learning_rate": 6.2625289853628225e-06,
      "loss": 0.4886,
      "step": 40530
    },
    {
      "epoch": 1.2450772586243972,
      "grad_norm": 0.42437711358070374,
      "learning_rate": 6.262080735186176e-06,
      "loss": 0.5436,
      "step": 40531
    },
    {
      "epoch": 1.2451079777593463,
      "grad_norm": 0.4491676688194275,
      "learning_rate": 6.261632493739703e-06,
      "loss": 0.4762,
      "step": 40532
    },
    {
      "epoch": 1.2451386968942955,
      "grad_norm": 0.40035906434059143,
      "learning_rate": 6.261184261024444e-06,
      "loss": 0.4536,
      "step": 40533
    },
    {
      "epoch": 1.2451694160292446,
      "grad_norm": 0.3948867619037628,
      "learning_rate": 6.260736037041456e-06,
      "loss": 0.4363,
      "step": 40534
    },
    {
      "epoch": 1.2452001351641937,
      "grad_norm": 0.3994697332382202,
      "learning_rate": 6.260287821791774e-06,
      "loss": 0.5224,
      "step": 40535
    },
    {
      "epoch": 1.2452308542991428,
      "grad_norm": 0.44021886587142944,
      "learning_rate": 6.259839615276457e-06,
      "loss": 0.4423,
      "step": 40536
    },
    {
      "epoch": 1.2452615734340922,
      "grad_norm": 0.40757307410240173,
      "learning_rate": 6.2593914174965394e-06,
      "loss": 0.4934,
      "step": 40537
    },
    {
      "epoch": 1.2452922925690413,
      "grad_norm": 0.37839147448539734,
      "learning_rate": 6.2589432284530805e-06,
      "loss": 0.5014,
      "step": 40538
    },
    {
      "epoch": 1.2453230117039904,
      "grad_norm": 0.42886683344841003,
      "learning_rate": 6.258495048147117e-06,
      "loss": 0.4355,
      "step": 40539
    },
    {
      "epoch": 1.2453537308389395,
      "grad_norm": 0.449799120426178,
      "learning_rate": 6.258046876579702e-06,
      "loss": 0.4849,
      "step": 40540
    },
    {
      "epoch": 1.2453844499738886,
      "grad_norm": 0.42599937319755554,
      "learning_rate": 6.257598713751878e-06,
      "loss": 0.4634,
      "step": 40541
    },
    {
      "epoch": 1.245415169108838,
      "grad_norm": 0.5728925466537476,
      "learning_rate": 6.2571505596646955e-06,
      "loss": 0.4629,
      "step": 40542
    },
    {
      "epoch": 1.245445888243787,
      "grad_norm": 0.42497873306274414,
      "learning_rate": 6.256702414319198e-06,
      "loss": 0.5188,
      "step": 40543
    },
    {
      "epoch": 1.2454766073787362,
      "grad_norm": 0.4041181802749634,
      "learning_rate": 6.2562542777164296e-06,
      "loss": 0.4816,
      "step": 40544
    },
    {
      "epoch": 1.2455073265136853,
      "grad_norm": 0.3844083547592163,
      "learning_rate": 6.2558061498574486e-06,
      "loss": 0.4472,
      "step": 40545
    },
    {
      "epoch": 1.2455380456486345,
      "grad_norm": 0.4250504672527313,
      "learning_rate": 6.255358030743288e-06,
      "loss": 0.487,
      "step": 40546
    },
    {
      "epoch": 1.2455687647835836,
      "grad_norm": 0.36773422360420227,
      "learning_rate": 6.254909920375003e-06,
      "loss": 0.4115,
      "step": 40547
    },
    {
      "epoch": 1.245599483918533,
      "grad_norm": 0.4047491252422333,
      "learning_rate": 6.254461818753637e-06,
      "loss": 0.4699,
      "step": 40548
    },
    {
      "epoch": 1.245630203053482,
      "grad_norm": 0.40179046988487244,
      "learning_rate": 6.254013725880237e-06,
      "loss": 0.4712,
      "step": 40549
    },
    {
      "epoch": 1.2456609221884312,
      "grad_norm": 0.3681620955467224,
      "learning_rate": 6.253565641755848e-06,
      "loss": 0.4209,
      "step": 40550
    },
    {
      "epoch": 1.2456916413233803,
      "grad_norm": 0.4045116901397705,
      "learning_rate": 6.2531175663815205e-06,
      "loss": 0.5233,
      "step": 40551
    },
    {
      "epoch": 1.2457223604583294,
      "grad_norm": 0.4217640459537506,
      "learning_rate": 6.252669499758296e-06,
      "loss": 0.4817,
      "step": 40552
    },
    {
      "epoch": 1.2457530795932787,
      "grad_norm": 0.3923298120498657,
      "learning_rate": 6.252221441887225e-06,
      "loss": 0.4307,
      "step": 40553
    },
    {
      "epoch": 1.2457837987282279,
      "grad_norm": 0.42915698885917664,
      "learning_rate": 6.2517733927693525e-06,
      "loss": 0.4875,
      "step": 40554
    },
    {
      "epoch": 1.245814517863177,
      "grad_norm": 0.4042534828186035,
      "learning_rate": 6.251325352405726e-06,
      "loss": 0.491,
      "step": 40555
    },
    {
      "epoch": 1.245845236998126,
      "grad_norm": 0.431619793176651,
      "learning_rate": 6.250877320797388e-06,
      "loss": 0.4845,
      "step": 40556
    },
    {
      "epoch": 1.2458759561330752,
      "grad_norm": 0.40031707286834717,
      "learning_rate": 6.2504292979453915e-06,
      "loss": 0.4483,
      "step": 40557
    },
    {
      "epoch": 1.2459066752680243,
      "grad_norm": 0.3934233486652374,
      "learning_rate": 6.249981283850777e-06,
      "loss": 0.5198,
      "step": 40558
    },
    {
      "epoch": 1.2459373944029737,
      "grad_norm": 0.46559059619903564,
      "learning_rate": 6.249533278514594e-06,
      "loss": 0.5023,
      "step": 40559
    },
    {
      "epoch": 1.2459681135379228,
      "grad_norm": 0.38440898060798645,
      "learning_rate": 6.249085281937888e-06,
      "loss": 0.4397,
      "step": 40560
    },
    {
      "epoch": 1.245998832672872,
      "grad_norm": 0.413097083568573,
      "learning_rate": 6.248637294121702e-06,
      "loss": 0.5062,
      "step": 40561
    },
    {
      "epoch": 1.246029551807821,
      "grad_norm": 0.4013464152812958,
      "learning_rate": 6.24818931506709e-06,
      "loss": 0.4774,
      "step": 40562
    },
    {
      "epoch": 1.2460602709427702,
      "grad_norm": 0.37280911207199097,
      "learning_rate": 6.2477413447750914e-06,
      "loss": 0.4728,
      "step": 40563
    },
    {
      "epoch": 1.2460909900777195,
      "grad_norm": 0.4246279001235962,
      "learning_rate": 6.247293383246757e-06,
      "loss": 0.4781,
      "step": 40564
    },
    {
      "epoch": 1.2461217092126686,
      "grad_norm": 0.38525375723838806,
      "learning_rate": 6.24684543048313e-06,
      "loss": 0.4936,
      "step": 40565
    },
    {
      "epoch": 1.2461524283476177,
      "grad_norm": 0.35131776332855225,
      "learning_rate": 6.246397486485258e-06,
      "loss": 0.4736,
      "step": 40566
    },
    {
      "epoch": 1.2461831474825669,
      "grad_norm": 0.4261925220489502,
      "learning_rate": 6.245949551254185e-06,
      "loss": 0.4825,
      "step": 40567
    },
    {
      "epoch": 1.246213866617516,
      "grad_norm": 0.5969681739807129,
      "learning_rate": 6.245501624790964e-06,
      "loss": 0.5038,
      "step": 40568
    },
    {
      "epoch": 1.246244585752465,
      "grad_norm": 0.4314793348312378,
      "learning_rate": 6.245053707096629e-06,
      "loss": 0.4983,
      "step": 40569
    },
    {
      "epoch": 1.2462753048874144,
      "grad_norm": 0.4022469222545624,
      "learning_rate": 6.244605798172241e-06,
      "loss": 0.4866,
      "step": 40570
    },
    {
      "epoch": 1.2463060240223636,
      "grad_norm": 0.40908491611480713,
      "learning_rate": 6.24415789801883e-06,
      "loss": 0.4599,
      "step": 40571
    },
    {
      "epoch": 1.2463367431573127,
      "grad_norm": 0.40133893489837646,
      "learning_rate": 6.243710006637458e-06,
      "loss": 0.4815,
      "step": 40572
    },
    {
      "epoch": 1.2463674622922618,
      "grad_norm": 0.4082179367542267,
      "learning_rate": 6.243262124029159e-06,
      "loss": 0.5112,
      "step": 40573
    },
    {
      "epoch": 1.246398181427211,
      "grad_norm": 0.4111689329147339,
      "learning_rate": 6.2428142501949866e-06,
      "loss": 0.4525,
      "step": 40574
    },
    {
      "epoch": 1.2464289005621603,
      "grad_norm": 0.43123650550842285,
      "learning_rate": 6.242366385135982e-06,
      "loss": 0.5123,
      "step": 40575
    },
    {
      "epoch": 1.2464596196971094,
      "grad_norm": 0.39391645789146423,
      "learning_rate": 6.241918528853195e-06,
      "loss": 0.5553,
      "step": 40576
    },
    {
      "epoch": 1.2464903388320585,
      "grad_norm": 0.37639737129211426,
      "learning_rate": 6.241470681347666e-06,
      "loss": 0.4502,
      "step": 40577
    },
    {
      "epoch": 1.2465210579670076,
      "grad_norm": 0.38298508524894714,
      "learning_rate": 6.241022842620448e-06,
      "loss": 0.4912,
      "step": 40578
    },
    {
      "epoch": 1.2465517771019567,
      "grad_norm": 0.4285868704319,
      "learning_rate": 6.240575012672583e-06,
      "loss": 0.5129,
      "step": 40579
    },
    {
      "epoch": 1.2465824962369059,
      "grad_norm": 0.5211032032966614,
      "learning_rate": 6.240127191505115e-06,
      "loss": 0.5384,
      "step": 40580
    },
    {
      "epoch": 1.2466132153718552,
      "grad_norm": 0.400290310382843,
      "learning_rate": 6.239679379119097e-06,
      "loss": 0.4795,
      "step": 40581
    },
    {
      "epoch": 1.2466439345068043,
      "grad_norm": 0.41297608613967896,
      "learning_rate": 6.239231575515566e-06,
      "loss": 0.4658,
      "step": 40582
    },
    {
      "epoch": 1.2466746536417534,
      "grad_norm": 0.4231368899345398,
      "learning_rate": 6.238783780695576e-06,
      "loss": 0.4749,
      "step": 40583
    },
    {
      "epoch": 1.2467053727767026,
      "grad_norm": 0.38228172063827515,
      "learning_rate": 6.238335994660167e-06,
      "loss": 0.4195,
      "step": 40584
    },
    {
      "epoch": 1.2467360919116517,
      "grad_norm": 0.427703320980072,
      "learning_rate": 6.237888217410388e-06,
      "loss": 0.4854,
      "step": 40585
    },
    {
      "epoch": 1.246766811046601,
      "grad_norm": 0.44863197207450867,
      "learning_rate": 6.237440448947283e-06,
      "loss": 0.4199,
      "step": 40586
    },
    {
      "epoch": 1.2467975301815502,
      "grad_norm": 0.46983253955841064,
      "learning_rate": 6.2369926892719e-06,
      "loss": 0.4908,
      "step": 40587
    },
    {
      "epoch": 1.2468282493164993,
      "grad_norm": 0.41210320591926575,
      "learning_rate": 6.236544938385282e-06,
      "loss": 0.4949,
      "step": 40588
    },
    {
      "epoch": 1.2468589684514484,
      "grad_norm": 0.4090520739555359,
      "learning_rate": 6.236097196288477e-06,
      "loss": 0.4516,
      "step": 40589
    },
    {
      "epoch": 1.2468896875863975,
      "grad_norm": 0.371224045753479,
      "learning_rate": 6.2356494629825295e-06,
      "loss": 0.5597,
      "step": 40590
    },
    {
      "epoch": 1.2469204067213466,
      "grad_norm": 0.8001412153244019,
      "learning_rate": 6.235201738468486e-06,
      "loss": 0.4577,
      "step": 40591
    },
    {
      "epoch": 1.246951125856296,
      "grad_norm": 0.5485019087791443,
      "learning_rate": 6.23475402274739e-06,
      "loss": 0.4875,
      "step": 40592
    },
    {
      "epoch": 1.246981844991245,
      "grad_norm": 0.46068936586380005,
      "learning_rate": 6.234306315820291e-06,
      "loss": 0.4353,
      "step": 40593
    },
    {
      "epoch": 1.2470125641261942,
      "grad_norm": 0.40584221482276917,
      "learning_rate": 6.233858617688231e-06,
      "loss": 0.4773,
      "step": 40594
    },
    {
      "epoch": 1.2470432832611433,
      "grad_norm": 0.4075098931789398,
      "learning_rate": 6.233410928352262e-06,
      "loss": 0.4748,
      "step": 40595
    },
    {
      "epoch": 1.2470740023960925,
      "grad_norm": 0.47427234053611755,
      "learning_rate": 6.232963247813417e-06,
      "loss": 0.5692,
      "step": 40596
    },
    {
      "epoch": 1.2471047215310418,
      "grad_norm": 0.382052481174469,
      "learning_rate": 6.232515576072757e-06,
      "loss": 0.4245,
      "step": 40597
    },
    {
      "epoch": 1.247135440665991,
      "grad_norm": 0.4066298305988312,
      "learning_rate": 6.232067913131313e-06,
      "loss": 0.4752,
      "step": 40598
    },
    {
      "epoch": 1.24716615980094,
      "grad_norm": 0.4325602352619171,
      "learning_rate": 6.231620258990141e-06,
      "loss": 0.4637,
      "step": 40599
    },
    {
      "epoch": 1.2471968789358892,
      "grad_norm": 0.393121600151062,
      "learning_rate": 6.231172613650283e-06,
      "loss": 0.4048,
      "step": 40600
    },
    {
      "epoch": 1.2472275980708383,
      "grad_norm": 0.4127865731716156,
      "learning_rate": 6.230724977112783e-06,
      "loss": 0.4317,
      "step": 40601
    },
    {
      "epoch": 1.2472583172057874,
      "grad_norm": 0.495545357465744,
      "learning_rate": 6.2302773493786925e-06,
      "loss": 0.4553,
      "step": 40602
    },
    {
      "epoch": 1.2472890363407367,
      "grad_norm": 0.3922842741012573,
      "learning_rate": 6.229829730449047e-06,
      "loss": 0.4535,
      "step": 40603
    },
    {
      "epoch": 1.2473197554756859,
      "grad_norm": 0.43365833163261414,
      "learning_rate": 6.229382120324903e-06,
      "loss": 0.4899,
      "step": 40604
    },
    {
      "epoch": 1.247350474610635,
      "grad_norm": 0.46947532892227173,
      "learning_rate": 6.228934519007295e-06,
      "loss": 0.4604,
      "step": 40605
    },
    {
      "epoch": 1.247381193745584,
      "grad_norm": 0.407787561416626,
      "learning_rate": 6.2284869264972795e-06,
      "loss": 0.5245,
      "step": 40606
    },
    {
      "epoch": 1.2474119128805332,
      "grad_norm": 0.39503660798072815,
      "learning_rate": 6.228039342795889e-06,
      "loss": 0.4498,
      "step": 40607
    },
    {
      "epoch": 1.2474426320154826,
      "grad_norm": 0.3909173309803009,
      "learning_rate": 6.2275917679041846e-06,
      "loss": 0.4736,
      "step": 40608
    },
    {
      "epoch": 1.2474733511504317,
      "grad_norm": 0.3873254060745239,
      "learning_rate": 6.227144201823196e-06,
      "loss": 0.4755,
      "step": 40609
    },
    {
      "epoch": 1.2475040702853808,
      "grad_norm": 0.5018250346183777,
      "learning_rate": 6.22669664455398e-06,
      "loss": 0.525,
      "step": 40610
    },
    {
      "epoch": 1.24753478942033,
      "grad_norm": 0.39702844619750977,
      "learning_rate": 6.226249096097574e-06,
      "loss": 0.4336,
      "step": 40611
    },
    {
      "epoch": 1.247565508555279,
      "grad_norm": 0.403771311044693,
      "learning_rate": 6.22580155645503e-06,
      "loss": 0.4701,
      "step": 40612
    },
    {
      "epoch": 1.2475962276902282,
      "grad_norm": 0.36606618762016296,
      "learning_rate": 6.225354025627387e-06,
      "loss": 0.4409,
      "step": 40613
    },
    {
      "epoch": 1.2476269468251775,
      "grad_norm": 0.47573888301849365,
      "learning_rate": 6.224906503615695e-06,
      "loss": 0.4815,
      "step": 40614
    },
    {
      "epoch": 1.2476576659601266,
      "grad_norm": 0.4110378324985504,
      "learning_rate": 6.224458990420997e-06,
      "loss": 0.4922,
      "step": 40615
    },
    {
      "epoch": 1.2476883850950757,
      "grad_norm": 0.4023560881614685,
      "learning_rate": 6.224011486044339e-06,
      "loss": 0.5672,
      "step": 40616
    },
    {
      "epoch": 1.2477191042300249,
      "grad_norm": 0.42738452553749084,
      "learning_rate": 6.223563990486766e-06,
      "loss": 0.4984,
      "step": 40617
    },
    {
      "epoch": 1.247749823364974,
      "grad_norm": 0.4113742709159851,
      "learning_rate": 6.223116503749323e-06,
      "loss": 0.4741,
      "step": 40618
    },
    {
      "epoch": 1.2477805424999233,
      "grad_norm": 0.43901070952415466,
      "learning_rate": 6.222669025833055e-06,
      "loss": 0.6124,
      "step": 40619
    },
    {
      "epoch": 1.2478112616348724,
      "grad_norm": 0.6315969824790955,
      "learning_rate": 6.222221556739007e-06,
      "loss": 0.4344,
      "step": 40620
    },
    {
      "epoch": 1.2478419807698216,
      "grad_norm": 0.40390852093696594,
      "learning_rate": 6.221774096468225e-06,
      "loss": 0.4732,
      "step": 40621
    },
    {
      "epoch": 1.2478726999047707,
      "grad_norm": 0.5902213454246521,
      "learning_rate": 6.221326645021753e-06,
      "loss": 0.4858,
      "step": 40622
    },
    {
      "epoch": 1.2479034190397198,
      "grad_norm": 0.4269365966320038,
      "learning_rate": 6.220879202400637e-06,
      "loss": 0.4974,
      "step": 40623
    },
    {
      "epoch": 1.247934138174669,
      "grad_norm": 0.4067597985267639,
      "learning_rate": 6.2204317686059214e-06,
      "loss": 0.5135,
      "step": 40624
    },
    {
      "epoch": 1.247964857309618,
      "grad_norm": 0.4337010085582733,
      "learning_rate": 6.219984343638652e-06,
      "loss": 0.4471,
      "step": 40625
    },
    {
      "epoch": 1.2479955764445674,
      "grad_norm": 0.3959830105304718,
      "learning_rate": 6.219536927499871e-06,
      "loss": 0.5135,
      "step": 40626
    },
    {
      "epoch": 1.2480262955795165,
      "grad_norm": 0.4088430106639862,
      "learning_rate": 6.219089520190628e-06,
      "loss": 0.4279,
      "step": 40627
    },
    {
      "epoch": 1.2480570147144656,
      "grad_norm": 0.4251636862754822,
      "learning_rate": 6.218642121711963e-06,
      "loss": 0.4633,
      "step": 40628
    },
    {
      "epoch": 1.2480877338494147,
      "grad_norm": 0.40681517124176025,
      "learning_rate": 6.218194732064926e-06,
      "loss": 0.5431,
      "step": 40629
    },
    {
      "epoch": 1.248118452984364,
      "grad_norm": 0.4384414255619049,
      "learning_rate": 6.217747351250558e-06,
      "loss": 0.4806,
      "step": 40630
    },
    {
      "epoch": 1.2481491721193132,
      "grad_norm": 0.43668895959854126,
      "learning_rate": 6.2172999792699085e-06,
      "loss": 0.4938,
      "step": 40631
    },
    {
      "epoch": 1.2481798912542623,
      "grad_norm": 0.41205668449401855,
      "learning_rate": 6.216852616124011e-06,
      "loss": 0.4208,
      "step": 40632
    },
    {
      "epoch": 1.2482106103892114,
      "grad_norm": 0.4212071895599365,
      "learning_rate": 6.216405261813927e-06,
      "loss": 0.4477,
      "step": 40633
    },
    {
      "epoch": 1.2482413295241606,
      "grad_norm": 0.3821747899055481,
      "learning_rate": 6.2159579163406865e-06,
      "loss": 0.5372,
      "step": 40634
    },
    {
      "epoch": 1.2482720486591097,
      "grad_norm": 0.4941580891609192,
      "learning_rate": 6.215510579705342e-06,
      "loss": 0.4605,
      "step": 40635
    },
    {
      "epoch": 1.2483027677940588,
      "grad_norm": 0.4114059805870056,
      "learning_rate": 6.2150632519089415e-06,
      "loss": 0.4508,
      "step": 40636
    },
    {
      "epoch": 1.2483334869290081,
      "grad_norm": 0.4265094995498657,
      "learning_rate": 6.214615932952519e-06,
      "loss": 0.4888,
      "step": 40637
    },
    {
      "epoch": 1.2483642060639573,
      "grad_norm": 0.39620018005371094,
      "learning_rate": 6.214168622837132e-06,
      "loss": 0.4073,
      "step": 40638
    },
    {
      "epoch": 1.2483949251989064,
      "grad_norm": 0.4144431948661804,
      "learning_rate": 6.213721321563811e-06,
      "loss": 0.4767,
      "step": 40639
    },
    {
      "epoch": 1.2484256443338555,
      "grad_norm": 0.40671297907829285,
      "learning_rate": 6.2132740291336135e-06,
      "loss": 0.5646,
      "step": 40640
    },
    {
      "epoch": 1.2484563634688048,
      "grad_norm": 0.42575764656066895,
      "learning_rate": 6.2128267455475754e-06,
      "loss": 0.4535,
      "step": 40641
    },
    {
      "epoch": 1.248487082603754,
      "grad_norm": 0.3794598877429962,
      "learning_rate": 6.21237947080675e-06,
      "loss": 0.4749,
      "step": 40642
    },
    {
      "epoch": 1.248517801738703,
      "grad_norm": 0.3927910327911377,
      "learning_rate": 6.2119322049121724e-06,
      "loss": 0.4743,
      "step": 40643
    },
    {
      "epoch": 1.2485485208736522,
      "grad_norm": 0.3905474543571472,
      "learning_rate": 6.211484947864894e-06,
      "loss": 0.456,
      "step": 40644
    },
    {
      "epoch": 1.2485792400086013,
      "grad_norm": 0.41055524349212646,
      "learning_rate": 6.211037699665956e-06,
      "loss": 0.4421,
      "step": 40645
    },
    {
      "epoch": 1.2486099591435504,
      "grad_norm": 0.40327349305152893,
      "learning_rate": 6.210590460316405e-06,
      "loss": 0.5443,
      "step": 40646
    },
    {
      "epoch": 1.2486406782784996,
      "grad_norm": 0.45706093311309814,
      "learning_rate": 6.210143229817283e-06,
      "loss": 0.4735,
      "step": 40647
    },
    {
      "epoch": 1.248671397413449,
      "grad_norm": 0.40557748079299927,
      "learning_rate": 6.209696008169637e-06,
      "loss": 0.4135,
      "step": 40648
    },
    {
      "epoch": 1.248702116548398,
      "grad_norm": 0.3903508484363556,
      "learning_rate": 6.2092487953745095e-06,
      "loss": 0.5115,
      "step": 40649
    },
    {
      "epoch": 1.2487328356833471,
      "grad_norm": 0.4169941842556,
      "learning_rate": 6.208801591432949e-06,
      "loss": 0.4191,
      "step": 40650
    },
    {
      "epoch": 1.2487635548182963,
      "grad_norm": 0.38996782898902893,
      "learning_rate": 6.208354396345995e-06,
      "loss": 0.5138,
      "step": 40651
    },
    {
      "epoch": 1.2487942739532454,
      "grad_norm": 0.3766908645629883,
      "learning_rate": 6.207907210114695e-06,
      "loss": 0.4961,
      "step": 40652
    },
    {
      "epoch": 1.2488249930881947,
      "grad_norm": 0.4036324918270111,
      "learning_rate": 6.207460032740091e-06,
      "loss": 0.4397,
      "step": 40653
    },
    {
      "epoch": 1.2488557122231438,
      "grad_norm": 0.43836426734924316,
      "learning_rate": 6.20701286422323e-06,
      "loss": 0.5482,
      "step": 40654
    },
    {
      "epoch": 1.248886431358093,
      "grad_norm": 0.4342961311340332,
      "learning_rate": 6.206565704565157e-06,
      "loss": 0.4649,
      "step": 40655
    },
    {
      "epoch": 1.248917150493042,
      "grad_norm": 0.4295036792755127,
      "learning_rate": 6.206118553766911e-06,
      "loss": 0.5046,
      "step": 40656
    },
    {
      "epoch": 1.2489478696279912,
      "grad_norm": 0.40351203083992004,
      "learning_rate": 6.205671411829544e-06,
      "loss": 0.5044,
      "step": 40657
    },
    {
      "epoch": 1.2489785887629403,
      "grad_norm": 0.43130794167518616,
      "learning_rate": 6.205224278754094e-06,
      "loss": 0.5025,
      "step": 40658
    },
    {
      "epoch": 1.2490093078978897,
      "grad_norm": 0.3872431516647339,
      "learning_rate": 6.204777154541608e-06,
      "loss": 0.469,
      "step": 40659
    },
    {
      "epoch": 1.2490400270328388,
      "grad_norm": 0.39136752486228943,
      "learning_rate": 6.20433003919313e-06,
      "loss": 0.4023,
      "step": 40660
    },
    {
      "epoch": 1.249070746167788,
      "grad_norm": 0.5304385423660278,
      "learning_rate": 6.203882932709706e-06,
      "loss": 0.5111,
      "step": 40661
    },
    {
      "epoch": 1.249101465302737,
      "grad_norm": 0.39831113815307617,
      "learning_rate": 6.203435835092376e-06,
      "loss": 0.5239,
      "step": 40662
    },
    {
      "epoch": 1.2491321844376861,
      "grad_norm": 0.3788197934627533,
      "learning_rate": 6.202988746342189e-06,
      "loss": 0.4088,
      "step": 40663
    },
    {
      "epoch": 1.2491629035726355,
      "grad_norm": 0.3570568263530731,
      "learning_rate": 6.202541666460184e-06,
      "loss": 0.4323,
      "step": 40664
    },
    {
      "epoch": 1.2491936227075846,
      "grad_norm": 0.3954818546772003,
      "learning_rate": 6.202094595447414e-06,
      "loss": 0.4748,
      "step": 40665
    },
    {
      "epoch": 1.2492243418425337,
      "grad_norm": 0.4285747706890106,
      "learning_rate": 6.201647533304911e-06,
      "loss": 0.4396,
      "step": 40666
    },
    {
      "epoch": 1.2492550609774828,
      "grad_norm": 0.4184619188308716,
      "learning_rate": 6.2012004800337315e-06,
      "loss": 0.4375,
      "step": 40667
    },
    {
      "epoch": 1.249285780112432,
      "grad_norm": 0.4098142683506012,
      "learning_rate": 6.200753435634906e-06,
      "loss": 0.4811,
      "step": 40668
    },
    {
      "epoch": 1.249316499247381,
      "grad_norm": 0.3993755578994751,
      "learning_rate": 6.2003064001094935e-06,
      "loss": 0.4126,
      "step": 40669
    },
    {
      "epoch": 1.2493472183823304,
      "grad_norm": 0.4003773629665375,
      "learning_rate": 6.199859373458525e-06,
      "loss": 0.4904,
      "step": 40670
    },
    {
      "epoch": 1.2493779375172795,
      "grad_norm": 0.38182923197746277,
      "learning_rate": 6.199412355683051e-06,
      "loss": 0.5259,
      "step": 40671
    },
    {
      "epoch": 1.2494086566522287,
      "grad_norm": 0.46559223532676697,
      "learning_rate": 6.19896534678412e-06,
      "loss": 0.4714,
      "step": 40672
    },
    {
      "epoch": 1.2494393757871778,
      "grad_norm": 0.42175203561782837,
      "learning_rate": 6.1985183467627645e-06,
      "loss": 0.4071,
      "step": 40673
    },
    {
      "epoch": 1.249470094922127,
      "grad_norm": 0.43388301134109497,
      "learning_rate": 6.198071355620041e-06,
      "loss": 0.4701,
      "step": 40674
    },
    {
      "epoch": 1.2495008140570762,
      "grad_norm": 0.3443583548069,
      "learning_rate": 6.197624373356981e-06,
      "loss": 0.4698,
      "step": 40675
    },
    {
      "epoch": 1.2495315331920254,
      "grad_norm": 0.3914492428302765,
      "learning_rate": 6.197177399974641e-06,
      "loss": 0.5343,
      "step": 40676
    },
    {
      "epoch": 1.2495622523269745,
      "grad_norm": 0.4448172152042389,
      "learning_rate": 6.196730435474055e-06,
      "loss": 0.5107,
      "step": 40677
    },
    {
      "epoch": 1.2495929714619236,
      "grad_norm": 0.45261695981025696,
      "learning_rate": 6.196283479856273e-06,
      "loss": 0.4699,
      "step": 40678
    },
    {
      "epoch": 1.2496236905968727,
      "grad_norm": 0.4092843234539032,
      "learning_rate": 6.195836533122335e-06,
      "loss": 0.4238,
      "step": 40679
    },
    {
      "epoch": 1.2496544097318218,
      "grad_norm": 0.3841501772403717,
      "learning_rate": 6.195389595273286e-06,
      "loss": 0.4439,
      "step": 40680
    },
    {
      "epoch": 1.2496851288667712,
      "grad_norm": 0.3858429491519928,
      "learning_rate": 6.194942666310171e-06,
      "loss": 0.4458,
      "step": 40681
    },
    {
      "epoch": 1.2497158480017203,
      "grad_norm": 0.4280146658420563,
      "learning_rate": 6.194495746234034e-06,
      "loss": 0.5333,
      "step": 40682
    },
    {
      "epoch": 1.2497465671366694,
      "grad_norm": 0.418792188167572,
      "learning_rate": 6.194048835045916e-06,
      "loss": 0.481,
      "step": 40683
    },
    {
      "epoch": 1.2497772862716185,
      "grad_norm": 0.4170922636985779,
      "learning_rate": 6.193601932746865e-06,
      "loss": 0.4316,
      "step": 40684
    },
    {
      "epoch": 1.2498080054065677,
      "grad_norm": 0.46844491362571716,
      "learning_rate": 6.193155039337919e-06,
      "loss": 0.4499,
      "step": 40685
    },
    {
      "epoch": 1.249838724541517,
      "grad_norm": 0.4307189881801605,
      "learning_rate": 6.192708154820129e-06,
      "loss": 0.4824,
      "step": 40686
    },
    {
      "epoch": 1.2498694436764661,
      "grad_norm": 0.4125913977622986,
      "learning_rate": 6.192261279194534e-06,
      "loss": 0.4577,
      "step": 40687
    },
    {
      "epoch": 1.2499001628114152,
      "grad_norm": 0.3712337613105774,
      "learning_rate": 6.191814412462178e-06,
      "loss": 0.4742,
      "step": 40688
    },
    {
      "epoch": 1.2499308819463644,
      "grad_norm": 0.8177515864372253,
      "learning_rate": 6.191367554624106e-06,
      "loss": 0.5288,
      "step": 40689
    },
    {
      "epoch": 1.2499616010813135,
      "grad_norm": 0.4119442105293274,
      "learning_rate": 6.190920705681358e-06,
      "loss": 0.4915,
      "step": 40690
    },
    {
      "epoch": 1.2499923202162626,
      "grad_norm": 0.42995011806488037,
      "learning_rate": 6.190473865634985e-06,
      "loss": 0.523,
      "step": 40691
    },
    {
      "epoch": 1.250023039351212,
      "grad_norm": 0.3925355076789856,
      "learning_rate": 6.190027034486024e-06,
      "loss": 0.5166,
      "step": 40692
    },
    {
      "epoch": 1.250053758486161,
      "grad_norm": 0.48838016390800476,
      "learning_rate": 6.189580212235523e-06,
      "loss": 0.4829,
      "step": 40693
    },
    {
      "epoch": 1.2500844776211102,
      "grad_norm": 0.3849024772644043,
      "learning_rate": 6.189133398884522e-06,
      "loss": 0.4098,
      "step": 40694
    },
    {
      "epoch": 1.2501151967560593,
      "grad_norm": 0.4136044383049011,
      "learning_rate": 6.188686594434067e-06,
      "loss": 0.4598,
      "step": 40695
    },
    {
      "epoch": 1.2501459158910084,
      "grad_norm": 0.5150694251060486,
      "learning_rate": 6.188239798885199e-06,
      "loss": 0.4023,
      "step": 40696
    },
    {
      "epoch": 1.2501766350259578,
      "grad_norm": 0.38586220145225525,
      "learning_rate": 6.187793012238965e-06,
      "loss": 0.4503,
      "step": 40697
    },
    {
      "epoch": 1.250207354160907,
      "grad_norm": 0.41126659512519836,
      "learning_rate": 6.187346234496405e-06,
      "loss": 0.4622,
      "step": 40698
    },
    {
      "epoch": 1.250238073295856,
      "grad_norm": 0.4323781728744507,
      "learning_rate": 6.186899465658568e-06,
      "loss": 0.3987,
      "step": 40699
    },
    {
      "epoch": 1.2502687924308051,
      "grad_norm": 0.48747774958610535,
      "learning_rate": 6.1864527057264864e-06,
      "loss": 0.5355,
      "step": 40700
    },
    {
      "epoch": 1.2502995115657543,
      "grad_norm": 0.39336395263671875,
      "learning_rate": 6.1860059547012196e-06,
      "loss": 0.5051,
      "step": 40701
    },
    {
      "epoch": 1.2503302307007034,
      "grad_norm": 0.3925727605819702,
      "learning_rate": 6.185559212583794e-06,
      "loss": 0.4535,
      "step": 40702
    },
    {
      "epoch": 1.2503609498356525,
      "grad_norm": 0.3998986780643463,
      "learning_rate": 6.185112479375268e-06,
      "loss": 0.4834,
      "step": 40703
    },
    {
      "epoch": 1.2503916689706018,
      "grad_norm": 0.4685245752334595,
      "learning_rate": 6.184665755076673e-06,
      "loss": 0.5117,
      "step": 40704
    },
    {
      "epoch": 1.250422388105551,
      "grad_norm": 0.44475874304771423,
      "learning_rate": 6.184219039689062e-06,
      "loss": 0.5291,
      "step": 40705
    },
    {
      "epoch": 1.2504531072405,
      "grad_norm": 0.4974348247051239,
      "learning_rate": 6.183772333213471e-06,
      "loss": 0.5283,
      "step": 40706
    },
    {
      "epoch": 1.2504838263754492,
      "grad_norm": 0.40245670080184937,
      "learning_rate": 6.1833256356509445e-06,
      "loss": 0.415,
      "step": 40707
    },
    {
      "epoch": 1.2505145455103985,
      "grad_norm": 0.3896234929561615,
      "learning_rate": 6.182878947002533e-06,
      "loss": 0.4375,
      "step": 40708
    },
    {
      "epoch": 1.2505452646453477,
      "grad_norm": 0.3975447118282318,
      "learning_rate": 6.182432267269267e-06,
      "loss": 0.5088,
      "step": 40709
    },
    {
      "epoch": 1.2505759837802968,
      "grad_norm": 0.4126648008823395,
      "learning_rate": 6.181985596452205e-06,
      "loss": 0.4194,
      "step": 40710
    },
    {
      "epoch": 1.250606702915246,
      "grad_norm": 0.4158124029636383,
      "learning_rate": 6.181538934552376e-06,
      "loss": 0.4698,
      "step": 40711
    },
    {
      "epoch": 1.250637422050195,
      "grad_norm": 0.418849915266037,
      "learning_rate": 6.181092281570835e-06,
      "loss": 0.423,
      "step": 40712
    },
    {
      "epoch": 1.2506681411851441,
      "grad_norm": 0.49480125308036804,
      "learning_rate": 6.180645637508615e-06,
      "loss": 0.4528,
      "step": 40713
    },
    {
      "epoch": 1.2506988603200933,
      "grad_norm": 0.44774508476257324,
      "learning_rate": 6.180199002366767e-06,
      "loss": 0.471,
      "step": 40714
    },
    {
      "epoch": 1.2507295794550426,
      "grad_norm": 0.4640721082687378,
      "learning_rate": 6.179752376146329e-06,
      "loss": 0.5384,
      "step": 40715
    },
    {
      "epoch": 1.2507602985899917,
      "grad_norm": 0.4486881196498871,
      "learning_rate": 6.179305758848349e-06,
      "loss": 0.5025,
      "step": 40716
    },
    {
      "epoch": 1.2507910177249408,
      "grad_norm": 0.40163448452949524,
      "learning_rate": 6.178859150473863e-06,
      "loss": 0.5119,
      "step": 40717
    },
    {
      "epoch": 1.25082173685989,
      "grad_norm": 0.41543349623680115,
      "learning_rate": 6.178412551023921e-06,
      "loss": 0.4489,
      "step": 40718
    },
    {
      "epoch": 1.2508524559948393,
      "grad_norm": 0.41647395491600037,
      "learning_rate": 6.1779659604995616e-06,
      "loss": 0.5096,
      "step": 40719
    },
    {
      "epoch": 1.2508831751297884,
      "grad_norm": 0.42682692408561707,
      "learning_rate": 6.177519378901833e-06,
      "loss": 0.5069,
      "step": 40720
    },
    {
      "epoch": 1.2509138942647375,
      "grad_norm": 0.41929182410240173,
      "learning_rate": 6.177072806231771e-06,
      "loss": 0.4511,
      "step": 40721
    },
    {
      "epoch": 1.2509446133996867,
      "grad_norm": 0.48905983567237854,
      "learning_rate": 6.176626242490424e-06,
      "loss": 0.5286,
      "step": 40722
    },
    {
      "epoch": 1.2509753325346358,
      "grad_norm": 0.37912049889564514,
      "learning_rate": 6.176179687678834e-06,
      "loss": 0.4303,
      "step": 40723
    },
    {
      "epoch": 1.251006051669585,
      "grad_norm": 0.36754733324050903,
      "learning_rate": 6.175733141798044e-06,
      "loss": 0.4621,
      "step": 40724
    },
    {
      "epoch": 1.251036770804534,
      "grad_norm": 0.6431137919425964,
      "learning_rate": 6.175286604849093e-06,
      "loss": 0.4556,
      "step": 40725
    },
    {
      "epoch": 1.2510674899394834,
      "grad_norm": 0.3964649736881256,
      "learning_rate": 6.174840076833029e-06,
      "loss": 0.4565,
      "step": 40726
    },
    {
      "epoch": 1.2510982090744325,
      "grad_norm": 0.4519432485103607,
      "learning_rate": 6.1743935577508955e-06,
      "loss": 0.4626,
      "step": 40727
    },
    {
      "epoch": 1.2511289282093816,
      "grad_norm": 0.4016406834125519,
      "learning_rate": 6.173947047603729e-06,
      "loss": 0.4763,
      "step": 40728
    },
    {
      "epoch": 1.2511596473443307,
      "grad_norm": 0.4406101703643799,
      "learning_rate": 6.173500546392579e-06,
      "loss": 0.5518,
      "step": 40729
    },
    {
      "epoch": 1.25119036647928,
      "grad_norm": 0.4083516597747803,
      "learning_rate": 6.1730540541184845e-06,
      "loss": 0.4983,
      "step": 40730
    },
    {
      "epoch": 1.2512210856142292,
      "grad_norm": 0.3794079124927521,
      "learning_rate": 6.172607570782492e-06,
      "loss": 0.4386,
      "step": 40731
    },
    {
      "epoch": 1.2512518047491783,
      "grad_norm": 0.42611050605773926,
      "learning_rate": 6.172161096385638e-06,
      "loss": 0.5309,
      "step": 40732
    },
    {
      "epoch": 1.2512825238841274,
      "grad_norm": 0.45808690786361694,
      "learning_rate": 6.171714630928973e-06,
      "loss": 0.5227,
      "step": 40733
    },
    {
      "epoch": 1.2513132430190765,
      "grad_norm": 0.4011788070201874,
      "learning_rate": 6.171268174413533e-06,
      "loss": 0.4503,
      "step": 40734
    },
    {
      "epoch": 1.2513439621540257,
      "grad_norm": 0.3938424289226532,
      "learning_rate": 6.170821726840368e-06,
      "loss": 0.4962,
      "step": 40735
    },
    {
      "epoch": 1.2513746812889748,
      "grad_norm": 0.417068749666214,
      "learning_rate": 6.170375288210509e-06,
      "loss": 0.4725,
      "step": 40736
    },
    {
      "epoch": 1.2514054004239241,
      "grad_norm": 0.39655959606170654,
      "learning_rate": 6.169928858525014e-06,
      "loss": 0.5129,
      "step": 40737
    },
    {
      "epoch": 1.2514361195588732,
      "grad_norm": 0.39459797739982605,
      "learning_rate": 6.16948243778491e-06,
      "loss": 0.4846,
      "step": 40738
    },
    {
      "epoch": 1.2514668386938224,
      "grad_norm": 0.4076806306838989,
      "learning_rate": 6.169036025991253e-06,
      "loss": 0.474,
      "step": 40739
    },
    {
      "epoch": 1.2514975578287715,
      "grad_norm": 0.3882402181625366,
      "learning_rate": 6.168589623145076e-06,
      "loss": 0.4926,
      "step": 40740
    },
    {
      "epoch": 1.2515282769637208,
      "grad_norm": 0.3934992551803589,
      "learning_rate": 6.16814322924743e-06,
      "loss": 0.4739,
      "step": 40741
    },
    {
      "epoch": 1.25155899609867,
      "grad_norm": 0.3906189203262329,
      "learning_rate": 6.167696844299349e-06,
      "loss": 0.5221,
      "step": 40742
    },
    {
      "epoch": 1.251589715233619,
      "grad_norm": 0.3766079545021057,
      "learning_rate": 6.167250468301882e-06,
      "loss": 0.435,
      "step": 40743
    },
    {
      "epoch": 1.2516204343685682,
      "grad_norm": 0.396517276763916,
      "learning_rate": 6.166804101256068e-06,
      "loss": 0.5592,
      "step": 40744
    },
    {
      "epoch": 1.2516511535035173,
      "grad_norm": 0.4074135422706604,
      "learning_rate": 6.166357743162948e-06,
      "loss": 0.4844,
      "step": 40745
    },
    {
      "epoch": 1.2516818726384664,
      "grad_norm": 0.3797167241573334,
      "learning_rate": 6.165911394023571e-06,
      "loss": 0.5024,
      "step": 40746
    },
    {
      "epoch": 1.2517125917734155,
      "grad_norm": 0.40967047214508057,
      "learning_rate": 6.165465053838975e-06,
      "loss": 0.5335,
      "step": 40747
    },
    {
      "epoch": 1.2517433109083649,
      "grad_norm": 0.4264467656612396,
      "learning_rate": 6.165018722610204e-06,
      "loss": 0.4945,
      "step": 40748
    },
    {
      "epoch": 1.251774030043314,
      "grad_norm": 0.40412765741348267,
      "learning_rate": 6.164572400338298e-06,
      "loss": 0.4314,
      "step": 40749
    },
    {
      "epoch": 1.2518047491782631,
      "grad_norm": 0.44691723585128784,
      "learning_rate": 6.1641260870243025e-06,
      "loss": 0.4866,
      "step": 40750
    },
    {
      "epoch": 1.2518354683132122,
      "grad_norm": 0.400037944316864,
      "learning_rate": 6.1636797826692565e-06,
      "loss": 0.4798,
      "step": 40751
    },
    {
      "epoch": 1.2518661874481616,
      "grad_norm": 0.4080473780632019,
      "learning_rate": 6.163233487274206e-06,
      "loss": 0.4724,
      "step": 40752
    },
    {
      "epoch": 1.2518969065831107,
      "grad_norm": 0.41648679971694946,
      "learning_rate": 6.1627872008401904e-06,
      "loss": 0.5466,
      "step": 40753
    },
    {
      "epoch": 1.2519276257180598,
      "grad_norm": 0.4283566474914551,
      "learning_rate": 6.162340923368255e-06,
      "loss": 0.5162,
      "step": 40754
    },
    {
      "epoch": 1.251958344853009,
      "grad_norm": 0.42572346329689026,
      "learning_rate": 6.1618946548594374e-06,
      "loss": 0.4523,
      "step": 40755
    },
    {
      "epoch": 1.251989063987958,
      "grad_norm": 0.4276498258113861,
      "learning_rate": 6.1614483953147866e-06,
      "loss": 0.4847,
      "step": 40756
    },
    {
      "epoch": 1.2520197831229072,
      "grad_norm": 0.6518390774726868,
      "learning_rate": 6.161002144735337e-06,
      "loss": 0.4425,
      "step": 40757
    },
    {
      "epoch": 1.2520505022578563,
      "grad_norm": 0.44112998247146606,
      "learning_rate": 6.1605559031221385e-06,
      "loss": 0.5066,
      "step": 40758
    },
    {
      "epoch": 1.2520812213928056,
      "grad_norm": 0.41443318128585815,
      "learning_rate": 6.1601096704762284e-06,
      "loss": 0.4893,
      "step": 40759
    },
    {
      "epoch": 1.2521119405277548,
      "grad_norm": 0.3904387354850769,
      "learning_rate": 6.1596634467986515e-06,
      "loss": 0.4451,
      "step": 40760
    },
    {
      "epoch": 1.2521426596627039,
      "grad_norm": 0.4481046497821808,
      "learning_rate": 6.159217232090446e-06,
      "loss": 0.5631,
      "step": 40761
    },
    {
      "epoch": 1.252173378797653,
      "grad_norm": 0.4465218782424927,
      "learning_rate": 6.158771026352659e-06,
      "loss": 0.4877,
      "step": 40762
    },
    {
      "epoch": 1.2522040979326023,
      "grad_norm": 0.370707631111145,
      "learning_rate": 6.158324829586331e-06,
      "loss": 0.5731,
      "step": 40763
    },
    {
      "epoch": 1.2522348170675515,
      "grad_norm": 0.39037057757377625,
      "learning_rate": 6.157878641792502e-06,
      "loss": 0.4327,
      "step": 40764
    },
    {
      "epoch": 1.2522655362025006,
      "grad_norm": 0.38558438420295715,
      "learning_rate": 6.157432462972217e-06,
      "loss": 0.4856,
      "step": 40765
    },
    {
      "epoch": 1.2522962553374497,
      "grad_norm": 0.3710537850856781,
      "learning_rate": 6.156986293126517e-06,
      "loss": 0.487,
      "step": 40766
    },
    {
      "epoch": 1.2523269744723988,
      "grad_norm": 0.3888218402862549,
      "learning_rate": 6.156540132256443e-06,
      "loss": 0.4574,
      "step": 40767
    },
    {
      "epoch": 1.252357693607348,
      "grad_norm": 0.4002613127231598,
      "learning_rate": 6.156093980363038e-06,
      "loss": 0.4663,
      "step": 40768
    },
    {
      "epoch": 1.252388412742297,
      "grad_norm": 0.35319435596466064,
      "learning_rate": 6.1556478374473475e-06,
      "loss": 0.5114,
      "step": 40769
    },
    {
      "epoch": 1.2524191318772464,
      "grad_norm": 0.408273309469223,
      "learning_rate": 6.155201703510404e-06,
      "loss": 0.4873,
      "step": 40770
    },
    {
      "epoch": 1.2524498510121955,
      "grad_norm": 0.48243090510368347,
      "learning_rate": 6.154755578553262e-06,
      "loss": 0.4262,
      "step": 40771
    },
    {
      "epoch": 1.2524805701471446,
      "grad_norm": 0.4354056119918823,
      "learning_rate": 6.154309462576949e-06,
      "loss": 0.4902,
      "step": 40772
    },
    {
      "epoch": 1.2525112892820938,
      "grad_norm": 0.37642309069633484,
      "learning_rate": 6.153863355582523e-06,
      "loss": 0.4919,
      "step": 40773
    },
    {
      "epoch": 1.252542008417043,
      "grad_norm": 0.42160138487815857,
      "learning_rate": 6.153417257571011e-06,
      "loss": 0.3842,
      "step": 40774
    },
    {
      "epoch": 1.2525727275519922,
      "grad_norm": 0.37386882305145264,
      "learning_rate": 6.152971168543467e-06,
      "loss": 0.4306,
      "step": 40775
    },
    {
      "epoch": 1.2526034466869413,
      "grad_norm": 0.5029130578041077,
      "learning_rate": 6.152525088500925e-06,
      "loss": 0.5144,
      "step": 40776
    },
    {
      "epoch": 1.2526341658218905,
      "grad_norm": 0.3775140941143036,
      "learning_rate": 6.15207901744443e-06,
      "loss": 0.4355,
      "step": 40777
    },
    {
      "epoch": 1.2526648849568396,
      "grad_norm": 0.40412887930870056,
      "learning_rate": 6.151632955375021e-06,
      "loss": 0.4565,
      "step": 40778
    },
    {
      "epoch": 1.2526956040917887,
      "grad_norm": 0.38128820061683655,
      "learning_rate": 6.151186902293744e-06,
      "loss": 0.5112,
      "step": 40779
    },
    {
      "epoch": 1.2527263232267378,
      "grad_norm": 0.4004753828048706,
      "learning_rate": 6.150740858201638e-06,
      "loss": 0.489,
      "step": 40780
    },
    {
      "epoch": 1.2527570423616872,
      "grad_norm": 0.4979478418827057,
      "learning_rate": 6.150294823099743e-06,
      "loss": 0.4607,
      "step": 40781
    },
    {
      "epoch": 1.2527877614966363,
      "grad_norm": 0.40362387895584106,
      "learning_rate": 6.149848796989109e-06,
      "loss": 0.4272,
      "step": 40782
    },
    {
      "epoch": 1.2528184806315854,
      "grad_norm": 0.3973897397518158,
      "learning_rate": 6.149402779870768e-06,
      "loss": 0.4214,
      "step": 40783
    },
    {
      "epoch": 1.2528491997665345,
      "grad_norm": 0.4142412543296814,
      "learning_rate": 6.1489567717457675e-06,
      "loss": 0.4657,
      "step": 40784
    },
    {
      "epoch": 1.2528799189014839,
      "grad_norm": 0.45398855209350586,
      "learning_rate": 6.148510772615146e-06,
      "loss": 0.4863,
      "step": 40785
    },
    {
      "epoch": 1.252910638036433,
      "grad_norm": 0.37210074067115784,
      "learning_rate": 6.1480647824799475e-06,
      "loss": 0.4807,
      "step": 40786
    },
    {
      "epoch": 1.252941357171382,
      "grad_norm": 0.4310983121395111,
      "learning_rate": 6.147618801341213e-06,
      "loss": 0.4655,
      "step": 40787
    },
    {
      "epoch": 1.2529720763063312,
      "grad_norm": 0.4372093677520752,
      "learning_rate": 6.147172829199983e-06,
      "loss": 0.443,
      "step": 40788
    },
    {
      "epoch": 1.2530027954412803,
      "grad_norm": 0.5832076072692871,
      "learning_rate": 6.1467268660573e-06,
      "loss": 0.4396,
      "step": 40789
    },
    {
      "epoch": 1.2530335145762295,
      "grad_norm": 0.4128899872303009,
      "learning_rate": 6.146280911914207e-06,
      "loss": 0.4597,
      "step": 40790
    },
    {
      "epoch": 1.2530642337111786,
      "grad_norm": 0.38329634070396423,
      "learning_rate": 6.145834966771742e-06,
      "loss": 0.4894,
      "step": 40791
    },
    {
      "epoch": 1.253094952846128,
      "grad_norm": 0.415725976228714,
      "learning_rate": 6.1453890306309505e-06,
      "loss": 0.4627,
      "step": 40792
    },
    {
      "epoch": 1.253125671981077,
      "grad_norm": 0.44628965854644775,
      "learning_rate": 6.144943103492871e-06,
      "loss": 0.5273,
      "step": 40793
    },
    {
      "epoch": 1.2531563911160262,
      "grad_norm": 0.4215070605278015,
      "learning_rate": 6.144497185358547e-06,
      "loss": 0.4686,
      "step": 40794
    },
    {
      "epoch": 1.2531871102509753,
      "grad_norm": 0.43579819798469543,
      "learning_rate": 6.144051276229017e-06,
      "loss": 0.5172,
      "step": 40795
    },
    {
      "epoch": 1.2532178293859246,
      "grad_norm": 0.39908790588378906,
      "learning_rate": 6.143605376105326e-06,
      "loss": 0.5413,
      "step": 40796
    },
    {
      "epoch": 1.2532485485208738,
      "grad_norm": 0.44566360116004944,
      "learning_rate": 6.143159484988514e-06,
      "loss": 0.5613,
      "step": 40797
    },
    {
      "epoch": 1.2532792676558229,
      "grad_norm": 0.9916423559188843,
      "learning_rate": 6.142713602879626e-06,
      "loss": 0.4197,
      "step": 40798
    },
    {
      "epoch": 1.253309986790772,
      "grad_norm": 0.3779624402523041,
      "learning_rate": 6.142267729779692e-06,
      "loss": 0.4837,
      "step": 40799
    },
    {
      "epoch": 1.253340705925721,
      "grad_norm": 0.39437440037727356,
      "learning_rate": 6.1418218656897646e-06,
      "loss": 0.4645,
      "step": 40800
    },
    {
      "epoch": 1.2533714250606702,
      "grad_norm": 0.4181564748287201,
      "learning_rate": 6.141376010610882e-06,
      "loss": 0.4582,
      "step": 40801
    },
    {
      "epoch": 1.2534021441956193,
      "grad_norm": 0.40056365728378296,
      "learning_rate": 6.140930164544085e-06,
      "loss": 0.5155,
      "step": 40802
    },
    {
      "epoch": 1.2534328633305687,
      "grad_norm": 0.41958358883857727,
      "learning_rate": 6.140484327490417e-06,
      "loss": 0.471,
      "step": 40803
    },
    {
      "epoch": 1.2534635824655178,
      "grad_norm": 0.37724676728248596,
      "learning_rate": 6.140038499450915e-06,
      "loss": 0.5025,
      "step": 40804
    },
    {
      "epoch": 1.253494301600467,
      "grad_norm": 0.3984651267528534,
      "learning_rate": 6.139592680426627e-06,
      "loss": 0.4573,
      "step": 40805
    },
    {
      "epoch": 1.253525020735416,
      "grad_norm": 0.41871753334999084,
      "learning_rate": 6.139146870418583e-06,
      "loss": 0.4806,
      "step": 40806
    },
    {
      "epoch": 1.2535557398703652,
      "grad_norm": 0.3909997344017029,
      "learning_rate": 6.138701069427837e-06,
      "loss": 0.5422,
      "step": 40807
    },
    {
      "epoch": 1.2535864590053145,
      "grad_norm": 0.47052082419395447,
      "learning_rate": 6.1382552774554204e-06,
      "loss": 0.4645,
      "step": 40808
    },
    {
      "epoch": 1.2536171781402636,
      "grad_norm": 0.3537543714046478,
      "learning_rate": 6.137809494502383e-06,
      "loss": 0.4615,
      "step": 40809
    },
    {
      "epoch": 1.2536478972752128,
      "grad_norm": 0.41235703229904175,
      "learning_rate": 6.137363720569757e-06,
      "loss": 0.4998,
      "step": 40810
    },
    {
      "epoch": 1.2536786164101619,
      "grad_norm": 0.422576367855072,
      "learning_rate": 6.13691795565859e-06,
      "loss": 0.5825,
      "step": 40811
    },
    {
      "epoch": 1.253709335545111,
      "grad_norm": 0.4042727053165436,
      "learning_rate": 6.136472199769918e-06,
      "loss": 0.5292,
      "step": 40812
    },
    {
      "epoch": 1.2537400546800601,
      "grad_norm": 0.39961299300193787,
      "learning_rate": 6.136026452904789e-06,
      "loss": 0.4803,
      "step": 40813
    },
    {
      "epoch": 1.2537707738150092,
      "grad_norm": 0.4346199631690979,
      "learning_rate": 6.135580715064235e-06,
      "loss": 0.4613,
      "step": 40814
    },
    {
      "epoch": 1.2538014929499586,
      "grad_norm": 0.41338470578193665,
      "learning_rate": 6.135134986249307e-06,
      "loss": 0.493,
      "step": 40815
    },
    {
      "epoch": 1.2538322120849077,
      "grad_norm": 0.4434889256954193,
      "learning_rate": 6.134689266461038e-06,
      "loss": 0.5462,
      "step": 40816
    },
    {
      "epoch": 1.2538629312198568,
      "grad_norm": 0.403851181268692,
      "learning_rate": 6.134243555700472e-06,
      "loss": 0.4549,
      "step": 40817
    },
    {
      "epoch": 1.253893650354806,
      "grad_norm": 0.39503318071365356,
      "learning_rate": 6.133797853968653e-06,
      "loss": 0.5004,
      "step": 40818
    },
    {
      "epoch": 1.2539243694897553,
      "grad_norm": 0.43289902806282043,
      "learning_rate": 6.133352161266617e-06,
      "loss": 0.4556,
      "step": 40819
    },
    {
      "epoch": 1.2539550886247044,
      "grad_norm": 0.3911356031894684,
      "learning_rate": 6.132906477595408e-06,
      "loss": 0.4681,
      "step": 40820
    },
    {
      "epoch": 1.2539858077596535,
      "grad_norm": 0.42403092980384827,
      "learning_rate": 6.1324608029560665e-06,
      "loss": 0.4493,
      "step": 40821
    },
    {
      "epoch": 1.2540165268946026,
      "grad_norm": 0.38982072472572327,
      "learning_rate": 6.1320151373496316e-06,
      "loss": 0.4636,
      "step": 40822
    },
    {
      "epoch": 1.2540472460295518,
      "grad_norm": 0.42305365204811096,
      "learning_rate": 6.131569480777146e-06,
      "loss": 0.5675,
      "step": 40823
    },
    {
      "epoch": 1.2540779651645009,
      "grad_norm": 0.4273693561553955,
      "learning_rate": 6.13112383323965e-06,
      "loss": 0.505,
      "step": 40824
    },
    {
      "epoch": 1.25410868429945,
      "grad_norm": 0.40280306339263916,
      "learning_rate": 6.130678194738184e-06,
      "loss": 0.4841,
      "step": 40825
    },
    {
      "epoch": 1.2541394034343993,
      "grad_norm": 0.40140634775161743,
      "learning_rate": 6.13023256527379e-06,
      "loss": 0.4945,
      "step": 40826
    },
    {
      "epoch": 1.2541701225693485,
      "grad_norm": 0.40651991963386536,
      "learning_rate": 6.129786944847509e-06,
      "loss": 0.4583,
      "step": 40827
    },
    {
      "epoch": 1.2542008417042976,
      "grad_norm": 0.41539445519447327,
      "learning_rate": 6.12934133346038e-06,
      "loss": 0.3463,
      "step": 40828
    },
    {
      "epoch": 1.2542315608392467,
      "grad_norm": 0.3922930657863617,
      "learning_rate": 6.128895731113444e-06,
      "loss": 0.4742,
      "step": 40829
    },
    {
      "epoch": 1.254262279974196,
      "grad_norm": 0.3878737986087799,
      "learning_rate": 6.128450137807743e-06,
      "loss": 0.4209,
      "step": 40830
    },
    {
      "epoch": 1.2542929991091452,
      "grad_norm": 0.4234326481819153,
      "learning_rate": 6.1280045535443156e-06,
      "loss": 0.4082,
      "step": 40831
    },
    {
      "epoch": 1.2543237182440943,
      "grad_norm": 0.41654500365257263,
      "learning_rate": 6.127558978324208e-06,
      "loss": 0.4941,
      "step": 40832
    },
    {
      "epoch": 1.2543544373790434,
      "grad_norm": 0.40643110871315,
      "learning_rate": 6.127113412148452e-06,
      "loss": 0.5633,
      "step": 40833
    },
    {
      "epoch": 1.2543851565139925,
      "grad_norm": 0.4170088768005371,
      "learning_rate": 6.126667855018098e-06,
      "loss": 0.4699,
      "step": 40834
    },
    {
      "epoch": 1.2544158756489416,
      "grad_norm": 0.39681336283683777,
      "learning_rate": 6.126222306934177e-06,
      "loss": 0.4493,
      "step": 40835
    },
    {
      "epoch": 1.2544465947838908,
      "grad_norm": 0.41630464792251587,
      "learning_rate": 6.1257767678977355e-06,
      "loss": 0.5,
      "step": 40836
    },
    {
      "epoch": 1.25447731391884,
      "grad_norm": 0.40945419669151306,
      "learning_rate": 6.125331237909815e-06,
      "loss": 0.4775,
      "step": 40837
    },
    {
      "epoch": 1.2545080330537892,
      "grad_norm": 0.41078194975852966,
      "learning_rate": 6.124885716971452e-06,
      "loss": 0.4855,
      "step": 40838
    },
    {
      "epoch": 1.2545387521887383,
      "grad_norm": 0.4052383303642273,
      "learning_rate": 6.124440205083693e-06,
      "loss": 0.4735,
      "step": 40839
    },
    {
      "epoch": 1.2545694713236875,
      "grad_norm": 0.40366411209106445,
      "learning_rate": 6.123994702247568e-06,
      "loss": 0.4413,
      "step": 40840
    },
    {
      "epoch": 1.2546001904586368,
      "grad_norm": 0.4201711118221283,
      "learning_rate": 6.1235492084641305e-06,
      "loss": 0.4886,
      "step": 40841
    },
    {
      "epoch": 1.254630909593586,
      "grad_norm": 0.39176756143569946,
      "learning_rate": 6.123103723734408e-06,
      "loss": 0.5345,
      "step": 40842
    },
    {
      "epoch": 1.254661628728535,
      "grad_norm": 0.4564948081970215,
      "learning_rate": 6.122658248059454e-06,
      "loss": 0.4909,
      "step": 40843
    },
    {
      "epoch": 1.2546923478634842,
      "grad_norm": 0.40811264514923096,
      "learning_rate": 6.122212781440296e-06,
      "loss": 0.5116,
      "step": 40844
    },
    {
      "epoch": 1.2547230669984333,
      "grad_norm": 0.4361191689968109,
      "learning_rate": 6.1217673238779875e-06,
      "loss": 0.4375,
      "step": 40845
    },
    {
      "epoch": 1.2547537861333824,
      "grad_norm": 0.4329993426799774,
      "learning_rate": 6.1213218753735585e-06,
      "loss": 0.5298,
      "step": 40846
    },
    {
      "epoch": 1.2547845052683315,
      "grad_norm": 0.39199766516685486,
      "learning_rate": 6.1208764359280545e-06,
      "loss": 0.5025,
      "step": 40847
    },
    {
      "epoch": 1.2548152244032809,
      "grad_norm": 0.4068284034729004,
      "learning_rate": 6.120431005542513e-06,
      "loss": 0.4842,
      "step": 40848
    },
    {
      "epoch": 1.25484594353823,
      "grad_norm": 0.5957140326499939,
      "learning_rate": 6.119985584217978e-06,
      "loss": 0.4693,
      "step": 40849
    },
    {
      "epoch": 1.254876662673179,
      "grad_norm": 0.40547844767570496,
      "learning_rate": 6.119540171955485e-06,
      "loss": 0.5046,
      "step": 40850
    },
    {
      "epoch": 1.2549073818081282,
      "grad_norm": 0.40849068760871887,
      "learning_rate": 6.1190947687560795e-06,
      "loss": 0.4813,
      "step": 40851
    },
    {
      "epoch": 1.2549381009430776,
      "grad_norm": 0.3927469849586487,
      "learning_rate": 6.118649374620797e-06,
      "loss": 0.4113,
      "step": 40852
    },
    {
      "epoch": 1.2549688200780267,
      "grad_norm": 0.42333608865737915,
      "learning_rate": 6.118203989550679e-06,
      "loss": 0.4699,
      "step": 40853
    },
    {
      "epoch": 1.2549995392129758,
      "grad_norm": 0.36627522110939026,
      "learning_rate": 6.1177586135467706e-06,
      "loss": 0.4333,
      "step": 40854
    },
    {
      "epoch": 1.255030258347925,
      "grad_norm": 0.39340999722480774,
      "learning_rate": 6.117313246610105e-06,
      "loss": 0.5433,
      "step": 40855
    },
    {
      "epoch": 1.255060977482874,
      "grad_norm": 0.37369993329048157,
      "learning_rate": 6.116867888741727e-06,
      "loss": 0.4956,
      "step": 40856
    },
    {
      "epoch": 1.2550916966178232,
      "grad_norm": 0.3443090319633484,
      "learning_rate": 6.116422539942675e-06,
      "loss": 0.419,
      "step": 40857
    },
    {
      "epoch": 1.2551224157527723,
      "grad_norm": 0.39805859327316284,
      "learning_rate": 6.115977200213989e-06,
      "loss": 0.5215,
      "step": 40858
    },
    {
      "epoch": 1.2551531348877216,
      "grad_norm": 0.4249812960624695,
      "learning_rate": 6.115531869556708e-06,
      "loss": 0.4377,
      "step": 40859
    },
    {
      "epoch": 1.2551838540226707,
      "grad_norm": 0.4480160176753998,
      "learning_rate": 6.115086547971877e-06,
      "loss": 0.4856,
      "step": 40860
    },
    {
      "epoch": 1.2552145731576199,
      "grad_norm": 0.41233381628990173,
      "learning_rate": 6.11464123546053e-06,
      "loss": 0.4871,
      "step": 40861
    },
    {
      "epoch": 1.255245292292569,
      "grad_norm": 0.4122588634490967,
      "learning_rate": 6.114195932023712e-06,
      "loss": 0.4774,
      "step": 40862
    },
    {
      "epoch": 1.2552760114275183,
      "grad_norm": 0.4206261932849884,
      "learning_rate": 6.113750637662458e-06,
      "loss": 0.4439,
      "step": 40863
    },
    {
      "epoch": 1.2553067305624674,
      "grad_norm": 0.3810794949531555,
      "learning_rate": 6.113305352377814e-06,
      "loss": 0.4947,
      "step": 40864
    },
    {
      "epoch": 1.2553374496974166,
      "grad_norm": 0.46327337622642517,
      "learning_rate": 6.1128600761708135e-06,
      "loss": 0.5398,
      "step": 40865
    },
    {
      "epoch": 1.2553681688323657,
      "grad_norm": 0.5020126104354858,
      "learning_rate": 6.1124148090425015e-06,
      "loss": 0.4165,
      "step": 40866
    },
    {
      "epoch": 1.2553988879673148,
      "grad_norm": 0.5064362287521362,
      "learning_rate": 6.111969550993916e-06,
      "loss": 0.4656,
      "step": 40867
    },
    {
      "epoch": 1.255429607102264,
      "grad_norm": 0.4128684103488922,
      "learning_rate": 6.1115243020261e-06,
      "loss": 0.4815,
      "step": 40868
    },
    {
      "epoch": 1.255460326237213,
      "grad_norm": 0.38593950867652893,
      "learning_rate": 6.111079062140084e-06,
      "loss": 0.431,
      "step": 40869
    },
    {
      "epoch": 1.2554910453721624,
      "grad_norm": 0.4086625874042511,
      "learning_rate": 6.110633831336922e-06,
      "loss": 0.5037,
      "step": 40870
    },
    {
      "epoch": 1.2555217645071115,
      "grad_norm": 0.4043523967266083,
      "learning_rate": 6.1101886096176395e-06,
      "loss": 0.4995,
      "step": 40871
    },
    {
      "epoch": 1.2555524836420606,
      "grad_norm": 0.42158031463623047,
      "learning_rate": 6.109743396983285e-06,
      "loss": 0.4657,
      "step": 40872
    },
    {
      "epoch": 1.2555832027770097,
      "grad_norm": 0.7047364711761475,
      "learning_rate": 6.1092981934349e-06,
      "loss": 0.49,
      "step": 40873
    },
    {
      "epoch": 1.255613921911959,
      "grad_norm": 0.37082940340042114,
      "learning_rate": 6.108852998973515e-06,
      "loss": 0.4376,
      "step": 40874
    },
    {
      "epoch": 1.2556446410469082,
      "grad_norm": 0.41225185990333557,
      "learning_rate": 6.108407813600183e-06,
      "loss": 0.4944,
      "step": 40875
    },
    {
      "epoch": 1.2556753601818573,
      "grad_norm": 0.4294772148132324,
      "learning_rate": 6.107962637315929e-06,
      "loss": 0.4631,
      "step": 40876
    },
    {
      "epoch": 1.2557060793168064,
      "grad_norm": 0.3732631206512451,
      "learning_rate": 6.107517470121806e-06,
      "loss": 0.4778,
      "step": 40877
    },
    {
      "epoch": 1.2557367984517556,
      "grad_norm": 0.37552115321159363,
      "learning_rate": 6.107072312018844e-06,
      "loss": 0.4594,
      "step": 40878
    },
    {
      "epoch": 1.2557675175867047,
      "grad_norm": 0.38818350434303284,
      "learning_rate": 6.10662716300809e-06,
      "loss": 0.5055,
      "step": 40879
    },
    {
      "epoch": 1.2557982367216538,
      "grad_norm": 0.4092342257499695,
      "learning_rate": 6.106182023090576e-06,
      "loss": 0.427,
      "step": 40880
    },
    {
      "epoch": 1.2558289558566031,
      "grad_norm": 0.3995681405067444,
      "learning_rate": 6.10573689226735e-06,
      "loss": 0.4422,
      "step": 40881
    },
    {
      "epoch": 1.2558596749915523,
      "grad_norm": 0.47829294204711914,
      "learning_rate": 6.105291770539444e-06,
      "loss": 0.536,
      "step": 40882
    },
    {
      "epoch": 1.2558903941265014,
      "grad_norm": 0.3921404480934143,
      "learning_rate": 6.104846657907904e-06,
      "loss": 0.4783,
      "step": 40883
    },
    {
      "epoch": 1.2559211132614505,
      "grad_norm": 0.3640264570713043,
      "learning_rate": 6.104401554373763e-06,
      "loss": 0.4084,
      "step": 40884
    },
    {
      "epoch": 1.2559518323963998,
      "grad_norm": 0.4101528823375702,
      "learning_rate": 6.103956459938067e-06,
      "loss": 0.4727,
      "step": 40885
    },
    {
      "epoch": 1.255982551531349,
      "grad_norm": 0.383501261472702,
      "learning_rate": 6.103511374601852e-06,
      "loss": 0.4403,
      "step": 40886
    },
    {
      "epoch": 1.256013270666298,
      "grad_norm": 0.4174969494342804,
      "learning_rate": 6.103066298366158e-06,
      "loss": 0.4771,
      "step": 40887
    },
    {
      "epoch": 1.2560439898012472,
      "grad_norm": 0.4115222990512848,
      "learning_rate": 6.102621231232025e-06,
      "loss": 0.4993,
      "step": 40888
    },
    {
      "epoch": 1.2560747089361963,
      "grad_norm": 0.6114278435707092,
      "learning_rate": 6.102176173200493e-06,
      "loss": 0.4117,
      "step": 40889
    },
    {
      "epoch": 1.2561054280711454,
      "grad_norm": 0.3825438916683197,
      "learning_rate": 6.1017311242726e-06,
      "loss": 0.4475,
      "step": 40890
    },
    {
      "epoch": 1.2561361472060946,
      "grad_norm": 0.3945809006690979,
      "learning_rate": 6.101286084449385e-06,
      "loss": 0.5093,
      "step": 40891
    },
    {
      "epoch": 1.256166866341044,
      "grad_norm": 0.42427724599838257,
      "learning_rate": 6.1008410537318905e-06,
      "loss": 0.4301,
      "step": 40892
    },
    {
      "epoch": 1.256197585475993,
      "grad_norm": 0.39723077416419983,
      "learning_rate": 6.100396032121153e-06,
      "loss": 0.4296,
      "step": 40893
    },
    {
      "epoch": 1.2562283046109421,
      "grad_norm": 0.433828741312027,
      "learning_rate": 6.099951019618214e-06,
      "loss": 0.4996,
      "step": 40894
    },
    {
      "epoch": 1.2562590237458913,
      "grad_norm": 0.43324220180511475,
      "learning_rate": 6.09950601622411e-06,
      "loss": 0.4865,
      "step": 40895
    },
    {
      "epoch": 1.2562897428808406,
      "grad_norm": 0.39611461758613586,
      "learning_rate": 6.099061021939885e-06,
      "loss": 0.4503,
      "step": 40896
    },
    {
      "epoch": 1.2563204620157897,
      "grad_norm": 0.40492838621139526,
      "learning_rate": 6.098616036766573e-06,
      "loss": 0.5737,
      "step": 40897
    },
    {
      "epoch": 1.2563511811507388,
      "grad_norm": 0.43329915404319763,
      "learning_rate": 6.098171060705217e-06,
      "loss": 0.4095,
      "step": 40898
    },
    {
      "epoch": 1.256381900285688,
      "grad_norm": 0.3951186239719391,
      "learning_rate": 6.0977260937568525e-06,
      "loss": 0.4579,
      "step": 40899
    },
    {
      "epoch": 1.256412619420637,
      "grad_norm": 0.3818395733833313,
      "learning_rate": 6.0972811359225255e-06,
      "loss": 0.4527,
      "step": 40900
    },
    {
      "epoch": 1.2564433385555862,
      "grad_norm": 0.4650294780731201,
      "learning_rate": 6.0968361872032675e-06,
      "loss": 0.4738,
      "step": 40901
    },
    {
      "epoch": 1.2564740576905353,
      "grad_norm": 0.5362857580184937,
      "learning_rate": 6.096391247600125e-06,
      "loss": 0.491,
      "step": 40902
    },
    {
      "epoch": 1.2565047768254847,
      "grad_norm": 0.39403513073921204,
      "learning_rate": 6.095946317114127e-06,
      "loss": 0.4097,
      "step": 40903
    },
    {
      "epoch": 1.2565354959604338,
      "grad_norm": 0.38886183500289917,
      "learning_rate": 6.095501395746326e-06,
      "loss": 0.4687,
      "step": 40904
    },
    {
      "epoch": 1.256566215095383,
      "grad_norm": 0.5145652890205383,
      "learning_rate": 6.095056483497749e-06,
      "loss": 0.4762,
      "step": 40905
    },
    {
      "epoch": 1.256596934230332,
      "grad_norm": 0.4470381736755371,
      "learning_rate": 6.094611580369445e-06,
      "loss": 0.4525,
      "step": 40906
    },
    {
      "epoch": 1.2566276533652814,
      "grad_norm": 0.41114068031311035,
      "learning_rate": 6.0941666863624425e-06,
      "loss": 0.462,
      "step": 40907
    },
    {
      "epoch": 1.2566583725002305,
      "grad_norm": 0.40099143981933594,
      "learning_rate": 6.093721801477789e-06,
      "loss": 0.4308,
      "step": 40908
    },
    {
      "epoch": 1.2566890916351796,
      "grad_norm": 0.49751928448677063,
      "learning_rate": 6.0932769257165244e-06,
      "loss": 0.4294,
      "step": 40909
    },
    {
      "epoch": 1.2567198107701287,
      "grad_norm": 0.41884368658065796,
      "learning_rate": 6.0928320590796786e-06,
      "loss": 0.465,
      "step": 40910
    },
    {
      "epoch": 1.2567505299050779,
      "grad_norm": 0.40424802899360657,
      "learning_rate": 6.0923872015683015e-06,
      "loss": 0.4152,
      "step": 40911
    },
    {
      "epoch": 1.256781249040027,
      "grad_norm": 0.3928757309913635,
      "learning_rate": 6.091942353183422e-06,
      "loss": 0.4776,
      "step": 40912
    },
    {
      "epoch": 1.256811968174976,
      "grad_norm": 0.4333973526954651,
      "learning_rate": 6.09149751392609e-06,
      "loss": 0.4524,
      "step": 40913
    },
    {
      "epoch": 1.2568426873099254,
      "grad_norm": 0.4058939814567566,
      "learning_rate": 6.091052683797336e-06,
      "loss": 0.4918,
      "step": 40914
    },
    {
      "epoch": 1.2568734064448746,
      "grad_norm": 0.39188310503959656,
      "learning_rate": 6.090607862798201e-06,
      "loss": 0.5052,
      "step": 40915
    },
    {
      "epoch": 1.2569041255798237,
      "grad_norm": 0.3752382695674896,
      "learning_rate": 6.090163050929724e-06,
      "loss": 0.4727,
      "step": 40916
    },
    {
      "epoch": 1.2569348447147728,
      "grad_norm": 0.4335578978061676,
      "learning_rate": 6.089718248192945e-06,
      "loss": 0.4902,
      "step": 40917
    },
    {
      "epoch": 1.256965563849722,
      "grad_norm": 0.381892591714859,
      "learning_rate": 6.089273454588901e-06,
      "loss": 0.4774,
      "step": 40918
    },
    {
      "epoch": 1.2569962829846713,
      "grad_norm": 0.4065110981464386,
      "learning_rate": 6.088828670118634e-06,
      "loss": 0.4719,
      "step": 40919
    },
    {
      "epoch": 1.2570270021196204,
      "grad_norm": 0.40219613909721375,
      "learning_rate": 6.088383894783179e-06,
      "loss": 0.494,
      "step": 40920
    },
    {
      "epoch": 1.2570577212545695,
      "grad_norm": 0.4205465018749237,
      "learning_rate": 6.087939128583578e-06,
      "loss": 0.4934,
      "step": 40921
    },
    {
      "epoch": 1.2570884403895186,
      "grad_norm": 0.4154118597507477,
      "learning_rate": 6.087494371520866e-06,
      "loss": 0.512,
      "step": 40922
    },
    {
      "epoch": 1.2571191595244677,
      "grad_norm": 0.4189232289791107,
      "learning_rate": 6.087049623596086e-06,
      "loss": 0.5104,
      "step": 40923
    },
    {
      "epoch": 1.2571498786594169,
      "grad_norm": 0.4053012430667877,
      "learning_rate": 6.086604884810274e-06,
      "loss": 0.5126,
      "step": 40924
    },
    {
      "epoch": 1.257180597794366,
      "grad_norm": 0.4344103932380676,
      "learning_rate": 6.086160155164471e-06,
      "loss": 0.5214,
      "step": 40925
    },
    {
      "epoch": 1.2572113169293153,
      "grad_norm": 0.42655014991760254,
      "learning_rate": 6.085715434659712e-06,
      "loss": 0.5206,
      "step": 40926
    },
    {
      "epoch": 1.2572420360642644,
      "grad_norm": 0.3993222415447235,
      "learning_rate": 6.085270723297039e-06,
      "loss": 0.4874,
      "step": 40927
    },
    {
      "epoch": 1.2572727551992136,
      "grad_norm": 0.37143003940582275,
      "learning_rate": 6.08482602107749e-06,
      "loss": 0.4948,
      "step": 40928
    },
    {
      "epoch": 1.2573034743341627,
      "grad_norm": 0.4182877242565155,
      "learning_rate": 6.084381328002102e-06,
      "loss": 0.4577,
      "step": 40929
    },
    {
      "epoch": 1.257334193469112,
      "grad_norm": 0.42183539271354675,
      "learning_rate": 6.083936644071918e-06,
      "loss": 0.5363,
      "step": 40930
    },
    {
      "epoch": 1.2573649126040611,
      "grad_norm": 0.3841022551059723,
      "learning_rate": 6.083491969287971e-06,
      "loss": 0.4766,
      "step": 40931
    },
    {
      "epoch": 1.2573956317390103,
      "grad_norm": 0.4953259527683258,
      "learning_rate": 6.083047303651304e-06,
      "loss": 0.4224,
      "step": 40932
    },
    {
      "epoch": 1.2574263508739594,
      "grad_norm": 0.39456337690353394,
      "learning_rate": 6.0826026471629505e-06,
      "loss": 0.4841,
      "step": 40933
    },
    {
      "epoch": 1.2574570700089085,
      "grad_norm": 0.4094822108745575,
      "learning_rate": 6.0821579998239545e-06,
      "loss": 0.6004,
      "step": 40934
    },
    {
      "epoch": 1.2574877891438576,
      "grad_norm": 0.3915879726409912,
      "learning_rate": 6.081713361635351e-06,
      "loss": 0.4171,
      "step": 40935
    },
    {
      "epoch": 1.2575185082788067,
      "grad_norm": 0.37764638662338257,
      "learning_rate": 6.0812687325981825e-06,
      "loss": 0.4167,
      "step": 40936
    },
    {
      "epoch": 1.257549227413756,
      "grad_norm": 0.41541340947151184,
      "learning_rate": 6.080824112713479e-06,
      "loss": 0.3425,
      "step": 40937
    },
    {
      "epoch": 1.2575799465487052,
      "grad_norm": 0.37884217500686646,
      "learning_rate": 6.080379501982291e-06,
      "loss": 0.4702,
      "step": 40938
    },
    {
      "epoch": 1.2576106656836543,
      "grad_norm": 0.41664770245552063,
      "learning_rate": 6.079934900405644e-06,
      "loss": 0.4644,
      "step": 40939
    },
    {
      "epoch": 1.2576413848186034,
      "grad_norm": 0.43708422780036926,
      "learning_rate": 6.079490307984588e-06,
      "loss": 0.4966,
      "step": 40940
    },
    {
      "epoch": 1.2576721039535528,
      "grad_norm": 0.43303489685058594,
      "learning_rate": 6.079045724720152e-06,
      "loss": 0.5061,
      "step": 40941
    },
    {
      "epoch": 1.257702823088502,
      "grad_norm": 0.4035683274269104,
      "learning_rate": 6.078601150613384e-06,
      "loss": 0.4039,
      "step": 40942
    },
    {
      "epoch": 1.257733542223451,
      "grad_norm": 0.4392656087875366,
      "learning_rate": 6.078156585665311e-06,
      "loss": 0.5077,
      "step": 40943
    },
    {
      "epoch": 1.2577642613584001,
      "grad_norm": 0.4103333055973053,
      "learning_rate": 6.077712029876981e-06,
      "loss": 0.4947,
      "step": 40944
    },
    {
      "epoch": 1.2577949804933493,
      "grad_norm": 0.4321502149105072,
      "learning_rate": 6.077267483249426e-06,
      "loss": 0.4794,
      "step": 40945
    },
    {
      "epoch": 1.2578256996282984,
      "grad_norm": 0.40431997179985046,
      "learning_rate": 6.076822945783685e-06,
      "loss": 0.4988,
      "step": 40946
    },
    {
      "epoch": 1.2578564187632475,
      "grad_norm": 0.3813773989677429,
      "learning_rate": 6.076378417480804e-06,
      "loss": 0.4604,
      "step": 40947
    },
    {
      "epoch": 1.2578871378981968,
      "grad_norm": 0.38044920563697815,
      "learning_rate": 6.075933898341808e-06,
      "loss": 0.5065,
      "step": 40948
    },
    {
      "epoch": 1.257917857033146,
      "grad_norm": 0.4409704804420471,
      "learning_rate": 6.07548938836775e-06,
      "loss": 0.4191,
      "step": 40949
    },
    {
      "epoch": 1.257948576168095,
      "grad_norm": 0.4390401244163513,
      "learning_rate": 6.075044887559656e-06,
      "loss": 0.4442,
      "step": 40950
    },
    {
      "epoch": 1.2579792953030442,
      "grad_norm": 0.46320345997810364,
      "learning_rate": 6.074600395918571e-06,
      "loss": 0.4674,
      "step": 40951
    },
    {
      "epoch": 1.2580100144379935,
      "grad_norm": 0.36134815216064453,
      "learning_rate": 6.07415591344553e-06,
      "loss": 0.4007,
      "step": 40952
    },
    {
      "epoch": 1.2580407335729427,
      "grad_norm": 0.4108143150806427,
      "learning_rate": 6.073711440141572e-06,
      "loss": 0.4619,
      "step": 40953
    },
    {
      "epoch": 1.2580714527078918,
      "grad_norm": 0.3950330317020416,
      "learning_rate": 6.073266976007735e-06,
      "loss": 0.4961,
      "step": 40954
    },
    {
      "epoch": 1.258102171842841,
      "grad_norm": 0.4601510465145111,
      "learning_rate": 6.072822521045057e-06,
      "loss": 0.5515,
      "step": 40955
    },
    {
      "epoch": 1.25813289097779,
      "grad_norm": 0.4521254301071167,
      "learning_rate": 6.072378075254576e-06,
      "loss": 0.5247,
      "step": 40956
    },
    {
      "epoch": 1.2581636101127391,
      "grad_norm": 0.425058513879776,
      "learning_rate": 6.071933638637332e-06,
      "loss": 0.5104,
      "step": 40957
    },
    {
      "epoch": 1.2581943292476883,
      "grad_norm": 0.37630465626716614,
      "learning_rate": 6.0714892111943595e-06,
      "loss": 0.4405,
      "step": 40958
    },
    {
      "epoch": 1.2582250483826376,
      "grad_norm": 0.38292837142944336,
      "learning_rate": 6.071044792926699e-06,
      "loss": 0.5196,
      "step": 40959
    },
    {
      "epoch": 1.2582557675175867,
      "grad_norm": 0.3899594843387604,
      "learning_rate": 6.070600383835386e-06,
      "loss": 0.4686,
      "step": 40960
    },
    {
      "epoch": 1.2582864866525358,
      "grad_norm": 0.4271659255027771,
      "learning_rate": 6.070155983921464e-06,
      "loss": 0.4599,
      "step": 40961
    },
    {
      "epoch": 1.258317205787485,
      "grad_norm": 0.3743991553783417,
      "learning_rate": 6.069711593185964e-06,
      "loss": 0.4396,
      "step": 40962
    },
    {
      "epoch": 1.2583479249224343,
      "grad_norm": 0.41633695363998413,
      "learning_rate": 6.069267211629927e-06,
      "loss": 0.4554,
      "step": 40963
    },
    {
      "epoch": 1.2583786440573834,
      "grad_norm": 0.4339645206928253,
      "learning_rate": 6.068822839254393e-06,
      "loss": 0.4243,
      "step": 40964
    },
    {
      "epoch": 1.2584093631923325,
      "grad_norm": 0.459133505821228,
      "learning_rate": 6.068378476060396e-06,
      "loss": 0.5595,
      "step": 40965
    },
    {
      "epoch": 1.2584400823272817,
      "grad_norm": 0.41779282689094543,
      "learning_rate": 6.067934122048977e-06,
      "loss": 0.5485,
      "step": 40966
    },
    {
      "epoch": 1.2584708014622308,
      "grad_norm": 0.4254443049430847,
      "learning_rate": 6.067489777221172e-06,
      "loss": 0.4865,
      "step": 40967
    },
    {
      "epoch": 1.25850152059718,
      "grad_norm": 0.5102556943893433,
      "learning_rate": 6.06704544157802e-06,
      "loss": 0.4624,
      "step": 40968
    },
    {
      "epoch": 1.258532239732129,
      "grad_norm": 0.3944985866546631,
      "learning_rate": 6.066601115120556e-06,
      "loss": 0.4365,
      "step": 40969
    },
    {
      "epoch": 1.2585629588670784,
      "grad_norm": 0.4028661549091339,
      "learning_rate": 6.0661567978498226e-06,
      "loss": 0.4279,
      "step": 40970
    },
    {
      "epoch": 1.2585936780020275,
      "grad_norm": 0.41961076855659485,
      "learning_rate": 6.065712489766852e-06,
      "loss": 0.4518,
      "step": 40971
    },
    {
      "epoch": 1.2586243971369766,
      "grad_norm": 0.513702392578125,
      "learning_rate": 6.065268190872688e-06,
      "loss": 0.581,
      "step": 40972
    },
    {
      "epoch": 1.2586551162719257,
      "grad_norm": 0.38068079948425293,
      "learning_rate": 6.064823901168361e-06,
      "loss": 0.4347,
      "step": 40973
    },
    {
      "epoch": 1.258685835406875,
      "grad_norm": 0.4212004244327545,
      "learning_rate": 6.064379620654917e-06,
      "loss": 0.4235,
      "step": 40974
    },
    {
      "epoch": 1.2587165545418242,
      "grad_norm": 0.44929778575897217,
      "learning_rate": 6.0639353493333844e-06,
      "loss": 0.4276,
      "step": 40975
    },
    {
      "epoch": 1.2587472736767733,
      "grad_norm": 0.42866718769073486,
      "learning_rate": 6.063491087204812e-06,
      "loss": 0.4222,
      "step": 40976
    },
    {
      "epoch": 1.2587779928117224,
      "grad_norm": 0.404186487197876,
      "learning_rate": 6.063046834270225e-06,
      "loss": 0.4856,
      "step": 40977
    },
    {
      "epoch": 1.2588087119466715,
      "grad_norm": 0.408649742603302,
      "learning_rate": 6.062602590530671e-06,
      "loss": 0.4979,
      "step": 40978
    },
    {
      "epoch": 1.2588394310816207,
      "grad_norm": 0.4754098951816559,
      "learning_rate": 6.06215835598718e-06,
      "loss": 0.4997,
      "step": 40979
    },
    {
      "epoch": 1.2588701502165698,
      "grad_norm": 0.3729628622531891,
      "learning_rate": 6.061714130640796e-06,
      "loss": 0.4063,
      "step": 40980
    },
    {
      "epoch": 1.2589008693515191,
      "grad_norm": 0.43297725915908813,
      "learning_rate": 6.061269914492551e-06,
      "loss": 0.469,
      "step": 40981
    },
    {
      "epoch": 1.2589315884864682,
      "grad_norm": 0.40669870376586914,
      "learning_rate": 6.060825707543485e-06,
      "loss": 0.4735,
      "step": 40982
    },
    {
      "epoch": 1.2589623076214174,
      "grad_norm": 0.39723047614097595,
      "learning_rate": 6.060381509794639e-06,
      "loss": 0.4895,
      "step": 40983
    },
    {
      "epoch": 1.2589930267563665,
      "grad_norm": 0.4579460322856903,
      "learning_rate": 6.059937321247046e-06,
      "loss": 0.4815,
      "step": 40984
    },
    {
      "epoch": 1.2590237458913158,
      "grad_norm": 0.3687833547592163,
      "learning_rate": 6.059493141901744e-06,
      "loss": 0.3931,
      "step": 40985
    },
    {
      "epoch": 1.259054465026265,
      "grad_norm": 0.4254438579082489,
      "learning_rate": 6.059048971759771e-06,
      "loss": 0.541,
      "step": 40986
    },
    {
      "epoch": 1.259085184161214,
      "grad_norm": 0.4123218059539795,
      "learning_rate": 6.058604810822166e-06,
      "loss": 0.5412,
      "step": 40987
    },
    {
      "epoch": 1.2591159032961632,
      "grad_norm": 0.3933112621307373,
      "learning_rate": 6.058160659089962e-06,
      "loss": 0.4642,
      "step": 40988
    },
    {
      "epoch": 1.2591466224311123,
      "grad_norm": 0.3862358033657074,
      "learning_rate": 6.057716516564201e-06,
      "loss": 0.4995,
      "step": 40989
    },
    {
      "epoch": 1.2591773415660614,
      "grad_norm": 0.40621572732925415,
      "learning_rate": 6.057272383245916e-06,
      "loss": 0.4905,
      "step": 40990
    },
    {
      "epoch": 1.2592080607010105,
      "grad_norm": 0.43404075503349304,
      "learning_rate": 6.056828259136151e-06,
      "loss": 0.4409,
      "step": 40991
    },
    {
      "epoch": 1.2592387798359599,
      "grad_norm": 0.3926733732223511,
      "learning_rate": 6.056384144235935e-06,
      "loss": 0.4925,
      "step": 40992
    },
    {
      "epoch": 1.259269498970909,
      "grad_norm": 0.44809892773628235,
      "learning_rate": 6.055940038546312e-06,
      "loss": 0.5225,
      "step": 40993
    },
    {
      "epoch": 1.2593002181058581,
      "grad_norm": 0.40861135721206665,
      "learning_rate": 6.055495942068315e-06,
      "loss": 0.4781,
      "step": 40994
    },
    {
      "epoch": 1.2593309372408072,
      "grad_norm": 0.5416918992996216,
      "learning_rate": 6.055051854802982e-06,
      "loss": 0.5713,
      "step": 40995
    },
    {
      "epoch": 1.2593616563757566,
      "grad_norm": 0.379123330116272,
      "learning_rate": 6.054607776751351e-06,
      "loss": 0.5402,
      "step": 40996
    },
    {
      "epoch": 1.2593923755107057,
      "grad_norm": 0.4039972126483917,
      "learning_rate": 6.054163707914462e-06,
      "loss": 0.5218,
      "step": 40997
    },
    {
      "epoch": 1.2594230946456548,
      "grad_norm": 0.4207289516925812,
      "learning_rate": 6.053719648293346e-06,
      "loss": 0.4599,
      "step": 40998
    },
    {
      "epoch": 1.259453813780604,
      "grad_norm": 0.41436541080474854,
      "learning_rate": 6.053275597889044e-06,
      "loss": 0.4258,
      "step": 40999
    },
    {
      "epoch": 1.259484532915553,
      "grad_norm": 0.4032289981842041,
      "learning_rate": 6.052831556702593e-06,
      "loss": 0.4623,
      "step": 41000
    },
    {
      "epoch": 1.2595152520505022,
      "grad_norm": 0.3998671770095825,
      "learning_rate": 6.052387524735028e-06,
      "loss": 0.4143,
      "step": 41001
    },
    {
      "epoch": 1.2595459711854513,
      "grad_norm": 0.40843862295150757,
      "learning_rate": 6.05194350198739e-06,
      "loss": 0.4659,
      "step": 41002
    },
    {
      "epoch": 1.2595766903204006,
      "grad_norm": 0.428215891122818,
      "learning_rate": 6.0514994884607125e-06,
      "loss": 0.5296,
      "step": 41003
    },
    {
      "epoch": 1.2596074094553498,
      "grad_norm": 0.44924396276474,
      "learning_rate": 6.051055484156034e-06,
      "loss": 0.5115,
      "step": 41004
    },
    {
      "epoch": 1.2596381285902989,
      "grad_norm": 0.42048248648643494,
      "learning_rate": 6.050611489074391e-06,
      "loss": 0.4376,
      "step": 41005
    },
    {
      "epoch": 1.259668847725248,
      "grad_norm": 0.38065651059150696,
      "learning_rate": 6.050167503216824e-06,
      "loss": 0.5013,
      "step": 41006
    },
    {
      "epoch": 1.2596995668601974,
      "grad_norm": 0.4326419234275818,
      "learning_rate": 6.049723526584361e-06,
      "loss": 0.4638,
      "step": 41007
    },
    {
      "epoch": 1.2597302859951465,
      "grad_norm": 0.4617605209350586,
      "learning_rate": 6.04927955917805e-06,
      "loss": 0.4626,
      "step": 41008
    },
    {
      "epoch": 1.2597610051300956,
      "grad_norm": 0.45061808824539185,
      "learning_rate": 6.048835600998917e-06,
      "loss": 0.439,
      "step": 41009
    },
    {
      "epoch": 1.2597917242650447,
      "grad_norm": 0.41215285658836365,
      "learning_rate": 6.048391652048009e-06,
      "loss": 0.4915,
      "step": 41010
    },
    {
      "epoch": 1.2598224433999938,
      "grad_norm": 0.4082925617694855,
      "learning_rate": 6.047947712326354e-06,
      "loss": 0.5064,
      "step": 41011
    },
    {
      "epoch": 1.259853162534943,
      "grad_norm": 0.4106394052505493,
      "learning_rate": 6.047503781834998e-06,
      "loss": 0.4977,
      "step": 41012
    },
    {
      "epoch": 1.259883881669892,
      "grad_norm": 0.4291274845600128,
      "learning_rate": 6.047059860574971e-06,
      "loss": 0.5501,
      "step": 41013
    },
    {
      "epoch": 1.2599146008048414,
      "grad_norm": 0.4044575095176697,
      "learning_rate": 6.046615948547312e-06,
      "loss": 0.437,
      "step": 41014
    },
    {
      "epoch": 1.2599453199397905,
      "grad_norm": 0.45969027280807495,
      "learning_rate": 6.046172045753056e-06,
      "loss": 0.599,
      "step": 41015
    },
    {
      "epoch": 1.2599760390747397,
      "grad_norm": 0.4065610468387604,
      "learning_rate": 6.045728152193242e-06,
      "loss": 0.4741,
      "step": 41016
    },
    {
      "epoch": 1.2600067582096888,
      "grad_norm": 0.38915032148361206,
      "learning_rate": 6.045284267868905e-06,
      "loss": 0.4353,
      "step": 41017
    },
    {
      "epoch": 1.2600374773446381,
      "grad_norm": 0.3926014304161072,
      "learning_rate": 6.044840392781081e-06,
      "loss": 0.5513,
      "step": 41018
    },
    {
      "epoch": 1.2600681964795872,
      "grad_norm": 0.44447752833366394,
      "learning_rate": 6.044396526930815e-06,
      "loss": 0.4523,
      "step": 41019
    },
    {
      "epoch": 1.2600989156145364,
      "grad_norm": 0.43631207942962646,
      "learning_rate": 6.043952670319133e-06,
      "loss": 0.5481,
      "step": 41020
    },
    {
      "epoch": 1.2601296347494855,
      "grad_norm": 0.39259669184684753,
      "learning_rate": 6.0435088229470775e-06,
      "loss": 0.4631,
      "step": 41021
    },
    {
      "epoch": 1.2601603538844346,
      "grad_norm": 0.34203383326530457,
      "learning_rate": 6.043064984815681e-06,
      "loss": 0.4411,
      "step": 41022
    },
    {
      "epoch": 1.2601910730193837,
      "grad_norm": 0.4232848286628723,
      "learning_rate": 6.042621155925985e-06,
      "loss": 0.5029,
      "step": 41023
    },
    {
      "epoch": 1.2602217921543328,
      "grad_norm": 0.40353453159332275,
      "learning_rate": 6.042177336279021e-06,
      "loss": 0.4927,
      "step": 41024
    },
    {
      "epoch": 1.2602525112892822,
      "grad_norm": 0.49490052461624146,
      "learning_rate": 6.04173352587583e-06,
      "loss": 0.5215,
      "step": 41025
    },
    {
      "epoch": 1.2602832304242313,
      "grad_norm": 0.4393538534641266,
      "learning_rate": 6.0412897247174476e-06,
      "loss": 0.52,
      "step": 41026
    },
    {
      "epoch": 1.2603139495591804,
      "grad_norm": 0.39438626170158386,
      "learning_rate": 6.040845932804908e-06,
      "loss": 0.4067,
      "step": 41027
    },
    {
      "epoch": 1.2603446686941295,
      "grad_norm": 0.4038383960723877,
      "learning_rate": 6.04040215013925e-06,
      "loss": 0.532,
      "step": 41028
    },
    {
      "epoch": 1.2603753878290787,
      "grad_norm": 0.467610627412796,
      "learning_rate": 6.03995837672151e-06,
      "loss": 0.5332,
      "step": 41029
    },
    {
      "epoch": 1.260406106964028,
      "grad_norm": 0.6202775835990906,
      "learning_rate": 6.039514612552722e-06,
      "loss": 0.415,
      "step": 41030
    },
    {
      "epoch": 1.2604368260989771,
      "grad_norm": 0.410434365272522,
      "learning_rate": 6.039070857633926e-06,
      "loss": 0.4731,
      "step": 41031
    },
    {
      "epoch": 1.2604675452339262,
      "grad_norm": 0.43924614787101746,
      "learning_rate": 6.0386271119661544e-06,
      "loss": 0.4277,
      "step": 41032
    },
    {
      "epoch": 1.2604982643688754,
      "grad_norm": 0.3953366279602051,
      "learning_rate": 6.038183375550448e-06,
      "loss": 0.4334,
      "step": 41033
    },
    {
      "epoch": 1.2605289835038245,
      "grad_norm": 0.41295626759529114,
      "learning_rate": 6.037739648387839e-06,
      "loss": 0.5023,
      "step": 41034
    },
    {
      "epoch": 1.2605597026387736,
      "grad_norm": 0.41953301429748535,
      "learning_rate": 6.03729593047937e-06,
      "loss": 0.5038,
      "step": 41035
    },
    {
      "epoch": 1.2605904217737227,
      "grad_norm": 0.41198667883872986,
      "learning_rate": 6.036852221826068e-06,
      "loss": 0.3984,
      "step": 41036
    },
    {
      "epoch": 1.260621140908672,
      "grad_norm": 0.42883870005607605,
      "learning_rate": 6.0364085224289745e-06,
      "loss": 0.5056,
      "step": 41037
    },
    {
      "epoch": 1.2606518600436212,
      "grad_norm": 0.3920685648918152,
      "learning_rate": 6.035964832289129e-06,
      "loss": 0.5079,
      "step": 41038
    },
    {
      "epoch": 1.2606825791785703,
      "grad_norm": 0.42557376623153687,
      "learning_rate": 6.035521151407562e-06,
      "loss": 0.4924,
      "step": 41039
    },
    {
      "epoch": 1.2607132983135194,
      "grad_norm": 0.38267236948013306,
      "learning_rate": 6.035077479785315e-06,
      "loss": 0.4717,
      "step": 41040
    },
    {
      "epoch": 1.2607440174484688,
      "grad_norm": 0.4123076796531677,
      "learning_rate": 6.034633817423419e-06,
      "loss": 0.5223,
      "step": 41041
    },
    {
      "epoch": 1.2607747365834179,
      "grad_norm": 0.4115024209022522,
      "learning_rate": 6.034190164322916e-06,
      "loss": 0.4623,
      "step": 41042
    },
    {
      "epoch": 1.260805455718367,
      "grad_norm": 0.39892590045928955,
      "learning_rate": 6.033746520484834e-06,
      "loss": 0.4384,
      "step": 41043
    },
    {
      "epoch": 1.2608361748533161,
      "grad_norm": 0.3861205279827118,
      "learning_rate": 6.03330288591022e-06,
      "loss": 0.4973,
      "step": 41044
    },
    {
      "epoch": 1.2608668939882652,
      "grad_norm": 0.3831746280193329,
      "learning_rate": 6.032859260600097e-06,
      "loss": 0.5256,
      "step": 41045
    },
    {
      "epoch": 1.2608976131232144,
      "grad_norm": 0.4569464325904846,
      "learning_rate": 6.0324156445555135e-06,
      "loss": 0.5148,
      "step": 41046
    },
    {
      "epoch": 1.2609283322581635,
      "grad_norm": 0.4010668098926544,
      "learning_rate": 6.0319720377774984e-06,
      "loss": 0.4784,
      "step": 41047
    },
    {
      "epoch": 1.2609590513931128,
      "grad_norm": 0.4500880837440491,
      "learning_rate": 6.031528440267091e-06,
      "loss": 0.5084,
      "step": 41048
    },
    {
      "epoch": 1.260989770528062,
      "grad_norm": 0.3546206057071686,
      "learning_rate": 6.031084852025324e-06,
      "loss": 0.4802,
      "step": 41049
    },
    {
      "epoch": 1.261020489663011,
      "grad_norm": 0.3754231333732605,
      "learning_rate": 6.030641273053237e-06,
      "loss": 0.4581,
      "step": 41050
    },
    {
      "epoch": 1.2610512087979602,
      "grad_norm": 0.38033387064933777,
      "learning_rate": 6.0301977033518635e-06,
      "loss": 0.4671,
      "step": 41051
    },
    {
      "epoch": 1.2610819279329095,
      "grad_norm": 0.4484790861606598,
      "learning_rate": 6.029754142922242e-06,
      "loss": 0.6028,
      "step": 41052
    },
    {
      "epoch": 1.2611126470678586,
      "grad_norm": 0.35657426714897156,
      "learning_rate": 6.029310591765405e-06,
      "loss": 0.4143,
      "step": 41053
    },
    {
      "epoch": 1.2611433662028078,
      "grad_norm": 0.4387648403644562,
      "learning_rate": 6.028867049882391e-06,
      "loss": 0.5014,
      "step": 41054
    },
    {
      "epoch": 1.2611740853377569,
      "grad_norm": 0.4116041958332062,
      "learning_rate": 6.0284235172742365e-06,
      "loss": 0.4344,
      "step": 41055
    },
    {
      "epoch": 1.261204804472706,
      "grad_norm": 0.40430426597595215,
      "learning_rate": 6.027979993941975e-06,
      "loss": 0.4471,
      "step": 41056
    },
    {
      "epoch": 1.2612355236076551,
      "grad_norm": 0.42061248421669006,
      "learning_rate": 6.0275364798866455e-06,
      "loss": 0.5063,
      "step": 41057
    },
    {
      "epoch": 1.2612662427426042,
      "grad_norm": 0.37137603759765625,
      "learning_rate": 6.027092975109279e-06,
      "loss": 0.4495,
      "step": 41058
    },
    {
      "epoch": 1.2612969618775536,
      "grad_norm": 0.5209096074104309,
      "learning_rate": 6.026649479610918e-06,
      "loss": 0.3986,
      "step": 41059
    },
    {
      "epoch": 1.2613276810125027,
      "grad_norm": 0.38012221455574036,
      "learning_rate": 6.026205993392591e-06,
      "loss": 0.5272,
      "step": 41060
    },
    {
      "epoch": 1.2613584001474518,
      "grad_norm": 0.393169641494751,
      "learning_rate": 6.02576251645534e-06,
      "loss": 0.4109,
      "step": 41061
    },
    {
      "epoch": 1.261389119282401,
      "grad_norm": 0.5225355625152588,
      "learning_rate": 6.0253190488001965e-06,
      "loss": 0.4409,
      "step": 41062
    },
    {
      "epoch": 1.2614198384173503,
      "grad_norm": 0.4109933078289032,
      "learning_rate": 6.0248755904282e-06,
      "loss": 0.4379,
      "step": 41063
    },
    {
      "epoch": 1.2614505575522994,
      "grad_norm": 0.38986703753471375,
      "learning_rate": 6.024432141340382e-06,
      "loss": 0.5052,
      "step": 41064
    },
    {
      "epoch": 1.2614812766872485,
      "grad_norm": 0.4170013964176178,
      "learning_rate": 6.023988701537782e-06,
      "loss": 0.5137,
      "step": 41065
    },
    {
      "epoch": 1.2615119958221976,
      "grad_norm": 0.4416959285736084,
      "learning_rate": 6.023545271021431e-06,
      "loss": 0.5041,
      "step": 41066
    },
    {
      "epoch": 1.2615427149571468,
      "grad_norm": 0.42457321286201477,
      "learning_rate": 6.0231018497923724e-06,
      "loss": 0.4518,
      "step": 41067
    },
    {
      "epoch": 1.2615734340920959,
      "grad_norm": 0.44102349877357483,
      "learning_rate": 6.022658437851634e-06,
      "loss": 0.5218,
      "step": 41068
    },
    {
      "epoch": 1.261604153227045,
      "grad_norm": 0.3718353807926178,
      "learning_rate": 6.022215035200258e-06,
      "loss": 0.5365,
      "step": 41069
    },
    {
      "epoch": 1.2616348723619943,
      "grad_norm": 0.406353235244751,
      "learning_rate": 6.021771641839271e-06,
      "loss": 0.4271,
      "step": 41070
    },
    {
      "epoch": 1.2616655914969435,
      "grad_norm": 0.39279961585998535,
      "learning_rate": 6.021328257769721e-06,
      "loss": 0.53,
      "step": 41071
    },
    {
      "epoch": 1.2616963106318926,
      "grad_norm": 0.46541690826416016,
      "learning_rate": 6.0208848829926305e-06,
      "loss": 0.4734,
      "step": 41072
    },
    {
      "epoch": 1.2617270297668417,
      "grad_norm": 0.4814265966415405,
      "learning_rate": 6.020441517509041e-06,
      "loss": 0.4806,
      "step": 41073
    },
    {
      "epoch": 1.261757748901791,
      "grad_norm": 0.4229239821434021,
      "learning_rate": 6.019998161319993e-06,
      "loss": 0.4656,
      "step": 41074
    },
    {
      "epoch": 1.2617884680367402,
      "grad_norm": 0.3764052391052246,
      "learning_rate": 6.019554814426514e-06,
      "loss": 0.4765,
      "step": 41075
    },
    {
      "epoch": 1.2618191871716893,
      "grad_norm": 0.3558216989040375,
      "learning_rate": 6.019111476829647e-06,
      "loss": 0.4328,
      "step": 41076
    },
    {
      "epoch": 1.2618499063066384,
      "grad_norm": 0.38681760430336,
      "learning_rate": 6.018668148530418e-06,
      "loss": 0.4268,
      "step": 41077
    },
    {
      "epoch": 1.2618806254415875,
      "grad_norm": 0.4004654884338379,
      "learning_rate": 6.018224829529872e-06,
      "loss": 0.5492,
      "step": 41078
    },
    {
      "epoch": 1.2619113445765366,
      "grad_norm": 0.40637922286987305,
      "learning_rate": 6.017781519829035e-06,
      "loss": 0.4995,
      "step": 41079
    },
    {
      "epoch": 1.2619420637114858,
      "grad_norm": 0.3939652740955353,
      "learning_rate": 6.017338219428952e-06,
      "loss": 0.5041,
      "step": 41080
    },
    {
      "epoch": 1.261972782846435,
      "grad_norm": 0.4023178815841675,
      "learning_rate": 6.01689492833065e-06,
      "loss": 0.472,
      "step": 41081
    },
    {
      "epoch": 1.2620035019813842,
      "grad_norm": 0.4313605725765228,
      "learning_rate": 6.016451646535173e-06,
      "loss": 0.4945,
      "step": 41082
    },
    {
      "epoch": 1.2620342211163333,
      "grad_norm": 0.4177061915397644,
      "learning_rate": 6.016008374043547e-06,
      "loss": 0.4751,
      "step": 41083
    },
    {
      "epoch": 1.2620649402512825,
      "grad_norm": 0.4284270703792572,
      "learning_rate": 6.015565110856814e-06,
      "loss": 0.4911,
      "step": 41084
    },
    {
      "epoch": 1.2620956593862318,
      "grad_norm": 0.37513625621795654,
      "learning_rate": 6.015121856976005e-06,
      "loss": 0.4531,
      "step": 41085
    },
    {
      "epoch": 1.262126378521181,
      "grad_norm": 0.40645235776901245,
      "learning_rate": 6.014678612402159e-06,
      "loss": 0.4312,
      "step": 41086
    },
    {
      "epoch": 1.26215709765613,
      "grad_norm": 1.2310446500778198,
      "learning_rate": 6.014235377136307e-06,
      "loss": 0.4764,
      "step": 41087
    },
    {
      "epoch": 1.2621878167910792,
      "grad_norm": 0.4255982041358948,
      "learning_rate": 6.01379215117949e-06,
      "loss": 0.4844,
      "step": 41088
    },
    {
      "epoch": 1.2622185359260283,
      "grad_norm": 0.4128991365432739,
      "learning_rate": 6.013348934532737e-06,
      "loss": 0.474,
      "step": 41089
    },
    {
      "epoch": 1.2622492550609774,
      "grad_norm": 0.4201873242855072,
      "learning_rate": 6.012905727197087e-06,
      "loss": 0.5565,
      "step": 41090
    },
    {
      "epoch": 1.2622799741959265,
      "grad_norm": 0.39262712001800537,
      "learning_rate": 6.012462529173573e-06,
      "loss": 0.4875,
      "step": 41091
    },
    {
      "epoch": 1.2623106933308759,
      "grad_norm": 0.3747802972793579,
      "learning_rate": 6.012019340463231e-06,
      "loss": 0.5224,
      "step": 41092
    },
    {
      "epoch": 1.262341412465825,
      "grad_norm": 0.39812541007995605,
      "learning_rate": 6.011576161067099e-06,
      "loss": 0.541,
      "step": 41093
    },
    {
      "epoch": 1.262372131600774,
      "grad_norm": 0.4143979251384735,
      "learning_rate": 6.0111329909862085e-06,
      "loss": 0.5037,
      "step": 41094
    },
    {
      "epoch": 1.2624028507357232,
      "grad_norm": 0.45888733863830566,
      "learning_rate": 6.0106898302215945e-06,
      "loss": 0.5257,
      "step": 41095
    },
    {
      "epoch": 1.2624335698706726,
      "grad_norm": 0.36285051703453064,
      "learning_rate": 6.010246678774293e-06,
      "loss": 0.4688,
      "step": 41096
    },
    {
      "epoch": 1.2624642890056217,
      "grad_norm": 0.4556421637535095,
      "learning_rate": 6.0098035366453414e-06,
      "loss": 0.4361,
      "step": 41097
    },
    {
      "epoch": 1.2624950081405708,
      "grad_norm": 0.4374980032444,
      "learning_rate": 6.009360403835769e-06,
      "loss": 0.4928,
      "step": 41098
    },
    {
      "epoch": 1.26252572727552,
      "grad_norm": 0.4909709393978119,
      "learning_rate": 6.008917280346617e-06,
      "loss": 0.5008,
      "step": 41099
    },
    {
      "epoch": 1.262556446410469,
      "grad_norm": 0.4540647566318512,
      "learning_rate": 6.008474166178914e-06,
      "loss": 0.4985,
      "step": 41100
    },
    {
      "epoch": 1.2625871655454182,
      "grad_norm": 0.4693620800971985,
      "learning_rate": 6.008031061333702e-06,
      "loss": 0.4736,
      "step": 41101
    },
    {
      "epoch": 1.2626178846803673,
      "grad_norm": 0.42366868257522583,
      "learning_rate": 6.007587965812009e-06,
      "loss": 0.4296,
      "step": 41102
    },
    {
      "epoch": 1.2626486038153166,
      "grad_norm": 0.40765681862831116,
      "learning_rate": 6.007144879614877e-06,
      "loss": 0.4883,
      "step": 41103
    },
    {
      "epoch": 1.2626793229502657,
      "grad_norm": 0.38548552989959717,
      "learning_rate": 6.006701802743333e-06,
      "loss": 0.4375,
      "step": 41104
    },
    {
      "epoch": 1.2627100420852149,
      "grad_norm": 0.6127895712852478,
      "learning_rate": 6.006258735198421e-06,
      "loss": 1.0133,
      "step": 41105
    },
    {
      "epoch": 1.262740761220164,
      "grad_norm": 0.4283161759376526,
      "learning_rate": 6.005815676981164e-06,
      "loss": 0.4672,
      "step": 41106
    },
    {
      "epoch": 1.2627714803551133,
      "grad_norm": 0.5591893196105957,
      "learning_rate": 6.00537262809261e-06,
      "loss": 0.4241,
      "step": 41107
    },
    {
      "epoch": 1.2628021994900624,
      "grad_norm": 0.4042103886604309,
      "learning_rate": 6.004929588533781e-06,
      "loss": 0.4285,
      "step": 41108
    },
    {
      "epoch": 1.2628329186250116,
      "grad_norm": 0.40313464403152466,
      "learning_rate": 6.00448655830572e-06,
      "loss": 0.5443,
      "step": 41109
    },
    {
      "epoch": 1.2628636377599607,
      "grad_norm": 0.3834207355976105,
      "learning_rate": 6.004043537409463e-06,
      "loss": 0.4528,
      "step": 41110
    },
    {
      "epoch": 1.2628943568949098,
      "grad_norm": 0.3874940872192383,
      "learning_rate": 6.0036005258460365e-06,
      "loss": 0.5036,
      "step": 41111
    },
    {
      "epoch": 1.262925076029859,
      "grad_norm": 0.4235891103744507,
      "learning_rate": 6.0031575236164856e-06,
      "loss": 0.4338,
      "step": 41112
    },
    {
      "epoch": 1.262955795164808,
      "grad_norm": 0.4754835367202759,
      "learning_rate": 6.002714530721834e-06,
      "loss": 0.5105,
      "step": 41113
    },
    {
      "epoch": 1.2629865142997574,
      "grad_norm": 0.4032658338546753,
      "learning_rate": 6.002271547163126e-06,
      "loss": 0.4757,
      "step": 41114
    },
    {
      "epoch": 1.2630172334347065,
      "grad_norm": 0.39202043414115906,
      "learning_rate": 6.001828572941387e-06,
      "loss": 0.4223,
      "step": 41115
    },
    {
      "epoch": 1.2630479525696556,
      "grad_norm": 0.42851924896240234,
      "learning_rate": 6.001385608057664e-06,
      "loss": 0.5041,
      "step": 41116
    },
    {
      "epoch": 1.2630786717046047,
      "grad_norm": 0.43265005946159363,
      "learning_rate": 6.000942652512977e-06,
      "loss": 0.5001,
      "step": 41117
    },
    {
      "epoch": 1.263109390839554,
      "grad_norm": 0.4703807830810547,
      "learning_rate": 6.000499706308373e-06,
      "loss": 0.4122,
      "step": 41118
    },
    {
      "epoch": 1.2631401099745032,
      "grad_norm": 0.39156660437583923,
      "learning_rate": 6.0000567694448775e-06,
      "loss": 0.4432,
      "step": 41119
    },
    {
      "epoch": 1.2631708291094523,
      "grad_norm": 0.42230287194252014,
      "learning_rate": 5.999613841923532e-06,
      "loss": 0.5203,
      "step": 41120
    },
    {
      "epoch": 1.2632015482444015,
      "grad_norm": 0.4182330369949341,
      "learning_rate": 5.999170923745364e-06,
      "loss": 0.4857,
      "step": 41121
    },
    {
      "epoch": 1.2632322673793506,
      "grad_norm": 0.41301512718200684,
      "learning_rate": 5.998728014911414e-06,
      "loss": 0.4813,
      "step": 41122
    },
    {
      "epoch": 1.2632629865142997,
      "grad_norm": 0.42850619554519653,
      "learning_rate": 5.998285115422714e-06,
      "loss": 0.452,
      "step": 41123
    },
    {
      "epoch": 1.2632937056492488,
      "grad_norm": 0.4062962234020233,
      "learning_rate": 5.997842225280299e-06,
      "loss": 0.5095,
      "step": 41124
    },
    {
      "epoch": 1.2633244247841982,
      "grad_norm": 0.4068872034549713,
      "learning_rate": 5.997399344485202e-06,
      "loss": 0.5053,
      "step": 41125
    },
    {
      "epoch": 1.2633551439191473,
      "grad_norm": 0.41656598448753357,
      "learning_rate": 5.99695647303846e-06,
      "loss": 0.4874,
      "step": 41126
    },
    {
      "epoch": 1.2633858630540964,
      "grad_norm": 0.4099152982234955,
      "learning_rate": 5.996513610941103e-06,
      "loss": 0.4882,
      "step": 41127
    },
    {
      "epoch": 1.2634165821890455,
      "grad_norm": 0.4441719651222229,
      "learning_rate": 5.996070758194168e-06,
      "loss": 0.4956,
      "step": 41128
    },
    {
      "epoch": 1.2634473013239949,
      "grad_norm": 0.3922994136810303,
      "learning_rate": 5.995627914798692e-06,
      "loss": 0.4049,
      "step": 41129
    },
    {
      "epoch": 1.263478020458944,
      "grad_norm": 0.4238133728504181,
      "learning_rate": 5.995185080755706e-06,
      "loss": 0.4054,
      "step": 41130
    },
    {
      "epoch": 1.263508739593893,
      "grad_norm": 0.4525715708732605,
      "learning_rate": 5.994742256066243e-06,
      "loss": 0.5466,
      "step": 41131
    },
    {
      "epoch": 1.2635394587288422,
      "grad_norm": 0.4081844091415405,
      "learning_rate": 5.994299440731342e-06,
      "loss": 0.498,
      "step": 41132
    },
    {
      "epoch": 1.2635701778637913,
      "grad_norm": 0.41144099831581116,
      "learning_rate": 5.9938566347520335e-06,
      "loss": 0.4701,
      "step": 41133
    },
    {
      "epoch": 1.2636008969987405,
      "grad_norm": 0.42312732338905334,
      "learning_rate": 5.993413838129352e-06,
      "loss": 0.5114,
      "step": 41134
    },
    {
      "epoch": 1.2636316161336896,
      "grad_norm": 0.40466544032096863,
      "learning_rate": 5.992971050864333e-06,
      "loss": 0.4758,
      "step": 41135
    },
    {
      "epoch": 1.263662335268639,
      "grad_norm": 0.3970196843147278,
      "learning_rate": 5.992528272958008e-06,
      "loss": 0.4949,
      "step": 41136
    },
    {
      "epoch": 1.263693054403588,
      "grad_norm": 0.4418449103832245,
      "learning_rate": 5.9920855044114155e-06,
      "loss": 0.4557,
      "step": 41137
    },
    {
      "epoch": 1.2637237735385372,
      "grad_norm": 0.44200241565704346,
      "learning_rate": 5.991642745225585e-06,
      "loss": 0.4567,
      "step": 41138
    },
    {
      "epoch": 1.2637544926734863,
      "grad_norm": 0.3768084645271301,
      "learning_rate": 5.9911999954015576e-06,
      "loss": 0.4919,
      "step": 41139
    },
    {
      "epoch": 1.2637852118084354,
      "grad_norm": 0.36867085099220276,
      "learning_rate": 5.990757254940356e-06,
      "loss": 0.4374,
      "step": 41140
    },
    {
      "epoch": 1.2638159309433847,
      "grad_norm": 0.40254512429237366,
      "learning_rate": 5.990314523843027e-06,
      "loss": 0.4388,
      "step": 41141
    },
    {
      "epoch": 1.2638466500783339,
      "grad_norm": 0.378231942653656,
      "learning_rate": 5.989871802110592e-06,
      "loss": 0.5169,
      "step": 41142
    },
    {
      "epoch": 1.263877369213283,
      "grad_norm": 0.41826921701431274,
      "learning_rate": 5.989429089744099e-06,
      "loss": 0.5389,
      "step": 41143
    },
    {
      "epoch": 1.263908088348232,
      "grad_norm": 0.38409483432769775,
      "learning_rate": 5.988986386744567e-06,
      "loss": 0.5513,
      "step": 41144
    },
    {
      "epoch": 1.2639388074831812,
      "grad_norm": 0.39796435832977295,
      "learning_rate": 5.9885436931130394e-06,
      "loss": 0.4623,
      "step": 41145
    },
    {
      "epoch": 1.2639695266181303,
      "grad_norm": 0.45610037446022034,
      "learning_rate": 5.988101008850553e-06,
      "loss": 0.5314,
      "step": 41146
    },
    {
      "epoch": 1.2640002457530797,
      "grad_norm": 0.3985165059566498,
      "learning_rate": 5.9876583339581304e-06,
      "loss": 0.5425,
      "step": 41147
    },
    {
      "epoch": 1.2640309648880288,
      "grad_norm": 0.4308818578720093,
      "learning_rate": 5.987215668436818e-06,
      "loss": 0.5243,
      "step": 41148
    },
    {
      "epoch": 1.264061684022978,
      "grad_norm": 0.39711177349090576,
      "learning_rate": 5.986773012287636e-06,
      "loss": 0.4865,
      "step": 41149
    },
    {
      "epoch": 1.264092403157927,
      "grad_norm": 0.40713605284690857,
      "learning_rate": 5.986330365511635e-06,
      "loss": 0.5056,
      "step": 41150
    },
    {
      "epoch": 1.2641231222928762,
      "grad_norm": 0.4034166634082794,
      "learning_rate": 5.985887728109834e-06,
      "loss": 0.4618,
      "step": 41151
    },
    {
      "epoch": 1.2641538414278255,
      "grad_norm": 0.4242534637451172,
      "learning_rate": 5.985445100083274e-06,
      "loss": 0.4487,
      "step": 41152
    },
    {
      "epoch": 1.2641845605627746,
      "grad_norm": 0.3867765963077545,
      "learning_rate": 5.985002481432987e-06,
      "loss": 0.5017,
      "step": 41153
    },
    {
      "epoch": 1.2642152796977237,
      "grad_norm": 0.452199250459671,
      "learning_rate": 5.984559872160008e-06,
      "loss": 0.4744,
      "step": 41154
    },
    {
      "epoch": 1.2642459988326729,
      "grad_norm": 0.3711395859718323,
      "learning_rate": 5.984117272265369e-06,
      "loss": 0.5202,
      "step": 41155
    },
    {
      "epoch": 1.264276717967622,
      "grad_norm": 0.4059681296348572,
      "learning_rate": 5.983674681750104e-06,
      "loss": 0.5298,
      "step": 41156
    },
    {
      "epoch": 1.264307437102571,
      "grad_norm": 0.37636634707450867,
      "learning_rate": 5.983232100615248e-06,
      "loss": 0.5359,
      "step": 41157
    },
    {
      "epoch": 1.2643381562375202,
      "grad_norm": 0.3920547366142273,
      "learning_rate": 5.982789528861835e-06,
      "loss": 0.426,
      "step": 41158
    },
    {
      "epoch": 1.2643688753724696,
      "grad_norm": 0.4492747485637665,
      "learning_rate": 5.982346966490895e-06,
      "loss": 0.4971,
      "step": 41159
    },
    {
      "epoch": 1.2643995945074187,
      "grad_norm": 0.3566191494464874,
      "learning_rate": 5.981904413503468e-06,
      "loss": 0.4409,
      "step": 41160
    },
    {
      "epoch": 1.2644303136423678,
      "grad_norm": 0.39848777651786804,
      "learning_rate": 5.98146186990058e-06,
      "loss": 0.5292,
      "step": 41161
    },
    {
      "epoch": 1.264461032777317,
      "grad_norm": 8.593463897705078,
      "learning_rate": 5.981019335683271e-06,
      "loss": 0.7504,
      "step": 41162
    },
    {
      "epoch": 1.2644917519122663,
      "grad_norm": 0.44134631752967834,
      "learning_rate": 5.9805768108525695e-06,
      "loss": 0.5653,
      "step": 41163
    },
    {
      "epoch": 1.2645224710472154,
      "grad_norm": 0.5607494711875916,
      "learning_rate": 5.9801342954095135e-06,
      "loss": 0.4423,
      "step": 41164
    },
    {
      "epoch": 1.2645531901821645,
      "grad_norm": 0.390760213136673,
      "learning_rate": 5.979691789355136e-06,
      "loss": 0.4498,
      "step": 41165
    },
    {
      "epoch": 1.2645839093171136,
      "grad_norm": 0.409809947013855,
      "learning_rate": 5.979249292690466e-06,
      "loss": 0.4887,
      "step": 41166
    },
    {
      "epoch": 1.2646146284520627,
      "grad_norm": 0.4505438208580017,
      "learning_rate": 5.9788068054165414e-06,
      "loss": 0.4745,
      "step": 41167
    },
    {
      "epoch": 1.2646453475870119,
      "grad_norm": 0.38671326637268066,
      "learning_rate": 5.978364327534394e-06,
      "loss": 0.4341,
      "step": 41168
    },
    {
      "epoch": 1.264676066721961,
      "grad_norm": 0.40011337399482727,
      "learning_rate": 5.977921859045059e-06,
      "loss": 0.4532,
      "step": 41169
    },
    {
      "epoch": 1.2647067858569103,
      "grad_norm": 0.4320499897003174,
      "learning_rate": 5.9774793999495666e-06,
      "loss": 0.553,
      "step": 41170
    },
    {
      "epoch": 1.2647375049918594,
      "grad_norm": 0.3854146897792816,
      "learning_rate": 5.977036950248953e-06,
      "loss": 0.5349,
      "step": 41171
    },
    {
      "epoch": 1.2647682241268086,
      "grad_norm": 0.48750150203704834,
      "learning_rate": 5.97659450994425e-06,
      "loss": 0.5249,
      "step": 41172
    },
    {
      "epoch": 1.2647989432617577,
      "grad_norm": 0.3876410126686096,
      "learning_rate": 5.976152079036494e-06,
      "loss": 0.4691,
      "step": 41173
    },
    {
      "epoch": 1.264829662396707,
      "grad_norm": 0.39006465673446655,
      "learning_rate": 5.975709657526711e-06,
      "loss": 0.5401,
      "step": 41174
    },
    {
      "epoch": 1.2648603815316561,
      "grad_norm": 0.37477168440818787,
      "learning_rate": 5.9752672454159456e-06,
      "loss": 0.4459,
      "step": 41175
    },
    {
      "epoch": 1.2648911006666053,
      "grad_norm": 0.4912278652191162,
      "learning_rate": 5.974824842705218e-06,
      "loss": 0.4066,
      "step": 41176
    },
    {
      "epoch": 1.2649218198015544,
      "grad_norm": 0.37890174984931946,
      "learning_rate": 5.974382449395574e-06,
      "loss": 0.4728,
      "step": 41177
    },
    {
      "epoch": 1.2649525389365035,
      "grad_norm": 0.4102831780910492,
      "learning_rate": 5.9739400654880355e-06,
      "loss": 0.4869,
      "step": 41178
    },
    {
      "epoch": 1.2649832580714526,
      "grad_norm": 0.3771418035030365,
      "learning_rate": 5.973497690983646e-06,
      "loss": 0.5308,
      "step": 41179
    },
    {
      "epoch": 1.2650139772064017,
      "grad_norm": 0.408230185508728,
      "learning_rate": 5.97305532588343e-06,
      "loss": 0.5427,
      "step": 41180
    },
    {
      "epoch": 1.265044696341351,
      "grad_norm": 0.41544485092163086,
      "learning_rate": 5.972612970188427e-06,
      "loss": 0.4882,
      "step": 41181
    },
    {
      "epoch": 1.2650754154763002,
      "grad_norm": 0.4055274724960327,
      "learning_rate": 5.972170623899666e-06,
      "loss": 0.4525,
      "step": 41182
    },
    {
      "epoch": 1.2651061346112493,
      "grad_norm": 0.40907707810401917,
      "learning_rate": 5.97172828701818e-06,
      "loss": 0.5362,
      "step": 41183
    },
    {
      "epoch": 1.2651368537461984,
      "grad_norm": 0.46793633699417114,
      "learning_rate": 5.971285959545009e-06,
      "loss": 0.4816,
      "step": 41184
    },
    {
      "epoch": 1.2651675728811478,
      "grad_norm": 0.40842702984809875,
      "learning_rate": 5.970843641481175e-06,
      "loss": 0.5197,
      "step": 41185
    },
    {
      "epoch": 1.265198292016097,
      "grad_norm": 0.41083189845085144,
      "learning_rate": 5.970401332827725e-06,
      "loss": 0.5115,
      "step": 41186
    },
    {
      "epoch": 1.265229011151046,
      "grad_norm": 0.44313153624534607,
      "learning_rate": 5.969959033585677e-06,
      "loss": 0.4994,
      "step": 41187
    },
    {
      "epoch": 1.2652597302859951,
      "grad_norm": 0.4158417582511902,
      "learning_rate": 5.969516743756074e-06,
      "loss": 0.5258,
      "step": 41188
    },
    {
      "epoch": 1.2652904494209443,
      "grad_norm": 0.4123689532279968,
      "learning_rate": 5.969074463339945e-06,
      "loss": 0.4916,
      "step": 41189
    },
    {
      "epoch": 1.2653211685558934,
      "grad_norm": 0.37691670656204224,
      "learning_rate": 5.968632192338326e-06,
      "loss": 0.4521,
      "step": 41190
    },
    {
      "epoch": 1.2653518876908425,
      "grad_norm": 0.4443398416042328,
      "learning_rate": 5.968189930752246e-06,
      "loss": 0.4618,
      "step": 41191
    },
    {
      "epoch": 1.2653826068257918,
      "grad_norm": 0.4095693528652191,
      "learning_rate": 5.9677476785827426e-06,
      "loss": 0.5592,
      "step": 41192
    },
    {
      "epoch": 1.265413325960741,
      "grad_norm": 0.3979819118976593,
      "learning_rate": 5.9673054358308435e-06,
      "loss": 0.4319,
      "step": 41193
    },
    {
      "epoch": 1.26544404509569,
      "grad_norm": 0.39410051703453064,
      "learning_rate": 5.966863202497586e-06,
      "loss": 0.5174,
      "step": 41194
    },
    {
      "epoch": 1.2654747642306392,
      "grad_norm": 0.36879947781562805,
      "learning_rate": 5.966420978584e-06,
      "loss": 0.4781,
      "step": 41195
    },
    {
      "epoch": 1.2655054833655885,
      "grad_norm": 0.44758257269859314,
      "learning_rate": 5.96597876409112e-06,
      "loss": 0.4882,
      "step": 41196
    },
    {
      "epoch": 1.2655362025005377,
      "grad_norm": 0.4114767611026764,
      "learning_rate": 5.965536559019977e-06,
      "loss": 0.4726,
      "step": 41197
    },
    {
      "epoch": 1.2655669216354868,
      "grad_norm": 0.3930451571941376,
      "learning_rate": 5.9650943633716084e-06,
      "loss": 0.5506,
      "step": 41198
    },
    {
      "epoch": 1.265597640770436,
      "grad_norm": 0.3721216917037964,
      "learning_rate": 5.96465217714704e-06,
      "loss": 0.3996,
      "step": 41199
    },
    {
      "epoch": 1.265628359905385,
      "grad_norm": 0.47477784752845764,
      "learning_rate": 5.964210000347309e-06,
      "loss": 0.475,
      "step": 41200
    },
    {
      "epoch": 1.2656590790403341,
      "grad_norm": 0.4267522692680359,
      "learning_rate": 5.96376783297345e-06,
      "loss": 0.5233,
      "step": 41201
    },
    {
      "epoch": 1.2656897981752833,
      "grad_norm": 0.37231022119522095,
      "learning_rate": 5.96332567502649e-06,
      "loss": 0.4658,
      "step": 41202
    },
    {
      "epoch": 1.2657205173102326,
      "grad_norm": 0.4555777609348297,
      "learning_rate": 5.962883526507467e-06,
      "loss": 0.5301,
      "step": 41203
    },
    {
      "epoch": 1.2657512364451817,
      "grad_norm": 0.4223644435405731,
      "learning_rate": 5.96244138741741e-06,
      "loss": 0.4971,
      "step": 41204
    },
    {
      "epoch": 1.2657819555801308,
      "grad_norm": 0.42559629678726196,
      "learning_rate": 5.961999257757354e-06,
      "loss": 0.462,
      "step": 41205
    },
    {
      "epoch": 1.26581267471508,
      "grad_norm": 0.40320658683776855,
      "learning_rate": 5.96155713752833e-06,
      "loss": 0.4343,
      "step": 41206
    },
    {
      "epoch": 1.2658433938500293,
      "grad_norm": 0.3885279893875122,
      "learning_rate": 5.961115026731372e-06,
      "loss": 0.4316,
      "step": 41207
    },
    {
      "epoch": 1.2658741129849784,
      "grad_norm": 0.39690640568733215,
      "learning_rate": 5.960672925367512e-06,
      "loss": 0.4421,
      "step": 41208
    },
    {
      "epoch": 1.2659048321199275,
      "grad_norm": 0.4010009169578552,
      "learning_rate": 5.960230833437785e-06,
      "loss": 0.4579,
      "step": 41209
    },
    {
      "epoch": 1.2659355512548767,
      "grad_norm": 0.405086874961853,
      "learning_rate": 5.959788750943216e-06,
      "loss": 0.5022,
      "step": 41210
    },
    {
      "epoch": 1.2659662703898258,
      "grad_norm": 0.4196261465549469,
      "learning_rate": 5.9593466778848475e-06,
      "loss": 0.5625,
      "step": 41211
    },
    {
      "epoch": 1.265996989524775,
      "grad_norm": 0.4122072756290436,
      "learning_rate": 5.958904614263701e-06,
      "loss": 0.4965,
      "step": 41212
    },
    {
      "epoch": 1.266027708659724,
      "grad_norm": 0.44894057512283325,
      "learning_rate": 5.9584625600808225e-06,
      "loss": 0.4746,
      "step": 41213
    },
    {
      "epoch": 1.2660584277946734,
      "grad_norm": 0.4136032462120056,
      "learning_rate": 5.9580205153372304e-06,
      "loss": 0.4497,
      "step": 41214
    },
    {
      "epoch": 1.2660891469296225,
      "grad_norm": 0.41462332010269165,
      "learning_rate": 5.957578480033968e-06,
      "loss": 0.4701,
      "step": 41215
    },
    {
      "epoch": 1.2661198660645716,
      "grad_norm": 0.40330997109413147,
      "learning_rate": 5.95713645417206e-06,
      "loss": 0.4223,
      "step": 41216
    },
    {
      "epoch": 1.2661505851995207,
      "grad_norm": 0.4383150339126587,
      "learning_rate": 5.956694437752545e-06,
      "loss": 0.4966,
      "step": 41217
    },
    {
      "epoch": 1.26618130433447,
      "grad_norm": 0.4431961476802826,
      "learning_rate": 5.95625243077645e-06,
      "loss": 0.5102,
      "step": 41218
    },
    {
      "epoch": 1.2662120234694192,
      "grad_norm": 0.3999287486076355,
      "learning_rate": 5.9558104332448085e-06,
      "loss": 0.5613,
      "step": 41219
    },
    {
      "epoch": 1.2662427426043683,
      "grad_norm": 0.4049593210220337,
      "learning_rate": 5.955368445158659e-06,
      "loss": 0.4648,
      "step": 41220
    },
    {
      "epoch": 1.2662734617393174,
      "grad_norm": 0.4197627007961273,
      "learning_rate": 5.954926466519027e-06,
      "loss": 0.5697,
      "step": 41221
    },
    {
      "epoch": 1.2663041808742665,
      "grad_norm": 0.37486642599105835,
      "learning_rate": 5.9544844973269466e-06,
      "loss": 0.5488,
      "step": 41222
    },
    {
      "epoch": 1.2663349000092157,
      "grad_norm": 0.3730139434337616,
      "learning_rate": 5.954042537583449e-06,
      "loss": 0.438,
      "step": 41223
    },
    {
      "epoch": 1.2663656191441648,
      "grad_norm": 0.40441420674324036,
      "learning_rate": 5.95360058728957e-06,
      "loss": 0.5068,
      "step": 41224
    },
    {
      "epoch": 1.2663963382791141,
      "grad_norm": 0.4498967230319977,
      "learning_rate": 5.9531586464463365e-06,
      "loss": 0.4908,
      "step": 41225
    },
    {
      "epoch": 1.2664270574140633,
      "grad_norm": 0.4741274118423462,
      "learning_rate": 5.952716715054786e-06,
      "loss": 0.4989,
      "step": 41226
    },
    {
      "epoch": 1.2664577765490124,
      "grad_norm": 0.38644272089004517,
      "learning_rate": 5.952274793115946e-06,
      "loss": 0.5129,
      "step": 41227
    },
    {
      "epoch": 1.2664884956839615,
      "grad_norm": 0.42322179675102234,
      "learning_rate": 5.951832880630854e-06,
      "loss": 0.5273,
      "step": 41228
    },
    {
      "epoch": 1.2665192148189108,
      "grad_norm": 0.4600127041339874,
      "learning_rate": 5.951390977600536e-06,
      "loss": 0.4796,
      "step": 41229
    },
    {
      "epoch": 1.26654993395386,
      "grad_norm": 0.43686169385910034,
      "learning_rate": 5.95094908402603e-06,
      "loss": 0.4629,
      "step": 41230
    },
    {
      "epoch": 1.266580653088809,
      "grad_norm": 0.42147961258888245,
      "learning_rate": 5.950507199908362e-06,
      "loss": 0.5267,
      "step": 41231
    },
    {
      "epoch": 1.2666113722237582,
      "grad_norm": 0.34672811627388,
      "learning_rate": 5.950065325248571e-06,
      "loss": 0.4672,
      "step": 41232
    },
    {
      "epoch": 1.2666420913587073,
      "grad_norm": 0.42169567942619324,
      "learning_rate": 5.949623460047682e-06,
      "loss": 0.5374,
      "step": 41233
    },
    {
      "epoch": 1.2666728104936564,
      "grad_norm": 0.38013532757759094,
      "learning_rate": 5.949181604306733e-06,
      "loss": 0.4264,
      "step": 41234
    },
    {
      "epoch": 1.2667035296286056,
      "grad_norm": 0.40397486090660095,
      "learning_rate": 5.94873975802675e-06,
      "loss": 0.4594,
      "step": 41235
    },
    {
      "epoch": 1.266734248763555,
      "grad_norm": 0.40511560440063477,
      "learning_rate": 5.948297921208773e-06,
      "loss": 0.5235,
      "step": 41236
    },
    {
      "epoch": 1.266764967898504,
      "grad_norm": 0.4105333089828491,
      "learning_rate": 5.947856093853823e-06,
      "loss": 0.4618,
      "step": 41237
    },
    {
      "epoch": 1.2667956870334531,
      "grad_norm": 0.3843063414096832,
      "learning_rate": 5.94741427596294e-06,
      "loss": 0.426,
      "step": 41238
    },
    {
      "epoch": 1.2668264061684023,
      "grad_norm": 0.4215652048587799,
      "learning_rate": 5.946972467537158e-06,
      "loss": 0.5352,
      "step": 41239
    },
    {
      "epoch": 1.2668571253033516,
      "grad_norm": 0.4475559592247009,
      "learning_rate": 5.946530668577499e-06,
      "loss": 0.5113,
      "step": 41240
    },
    {
      "epoch": 1.2668878444383007,
      "grad_norm": 0.4207009971141815,
      "learning_rate": 5.946088879085005e-06,
      "loss": 0.4698,
      "step": 41241
    },
    {
      "epoch": 1.2669185635732498,
      "grad_norm": 0.3840733468532562,
      "learning_rate": 5.945647099060703e-06,
      "loss": 0.4585,
      "step": 41242
    },
    {
      "epoch": 1.266949282708199,
      "grad_norm": 0.3982391059398651,
      "learning_rate": 5.945205328505628e-06,
      "loss": 0.4429,
      "step": 41243
    },
    {
      "epoch": 1.266980001843148,
      "grad_norm": 0.682357668876648,
      "learning_rate": 5.944763567420802e-06,
      "loss": 0.5434,
      "step": 41244
    },
    {
      "epoch": 1.2670107209780972,
      "grad_norm": 0.45828816294670105,
      "learning_rate": 5.94432181580727e-06,
      "loss": 0.4777,
      "step": 41245
    },
    {
      "epoch": 1.2670414401130463,
      "grad_norm": 0.37485337257385254,
      "learning_rate": 5.9438800736660525e-06,
      "loss": 0.4569,
      "step": 41246
    },
    {
      "epoch": 1.2670721592479957,
      "grad_norm": 0.43989643454551697,
      "learning_rate": 5.943438340998193e-06,
      "loss": 0.4852,
      "step": 41247
    },
    {
      "epoch": 1.2671028783829448,
      "grad_norm": 0.40788534283638,
      "learning_rate": 5.9429966178047105e-06,
      "loss": 0.5303,
      "step": 41248
    },
    {
      "epoch": 1.267133597517894,
      "grad_norm": 0.5323590040206909,
      "learning_rate": 5.9425549040866485e-06,
      "loss": 0.4962,
      "step": 41249
    },
    {
      "epoch": 1.267164316652843,
      "grad_norm": 0.3885082006454468,
      "learning_rate": 5.9421131998450276e-06,
      "loss": 0.4968,
      "step": 41250
    },
    {
      "epoch": 1.2671950357877921,
      "grad_norm": 0.40073031187057495,
      "learning_rate": 5.941671505080887e-06,
      "loss": 0.5038,
      "step": 41251
    },
    {
      "epoch": 1.2672257549227415,
      "grad_norm": 0.42345914244651794,
      "learning_rate": 5.941229819795255e-06,
      "loss": 0.5124,
      "step": 41252
    },
    {
      "epoch": 1.2672564740576906,
      "grad_norm": 0.4254395365715027,
      "learning_rate": 5.940788143989166e-06,
      "loss": 0.4534,
      "step": 41253
    },
    {
      "epoch": 1.2672871931926397,
      "grad_norm": 0.36446020007133484,
      "learning_rate": 5.940346477663647e-06,
      "loss": 0.4477,
      "step": 41254
    },
    {
      "epoch": 1.2673179123275888,
      "grad_norm": 0.41462936997413635,
      "learning_rate": 5.939904820819733e-06,
      "loss": 0.5392,
      "step": 41255
    },
    {
      "epoch": 1.267348631462538,
      "grad_norm": 0.45709899067878723,
      "learning_rate": 5.939463173458457e-06,
      "loss": 0.4796,
      "step": 41256
    },
    {
      "epoch": 1.267379350597487,
      "grad_norm": 0.3770061731338501,
      "learning_rate": 5.939021535580847e-06,
      "loss": 0.4451,
      "step": 41257
    },
    {
      "epoch": 1.2674100697324364,
      "grad_norm": 0.3679741621017456,
      "learning_rate": 5.938579907187936e-06,
      "loss": 0.4386,
      "step": 41258
    },
    {
      "epoch": 1.2674407888673855,
      "grad_norm": 0.38443177938461304,
      "learning_rate": 5.938138288280755e-06,
      "loss": 0.4433,
      "step": 41259
    },
    {
      "epoch": 1.2674715080023347,
      "grad_norm": 0.47275200486183167,
      "learning_rate": 5.937696678860336e-06,
      "loss": 0.4931,
      "step": 41260
    },
    {
      "epoch": 1.2675022271372838,
      "grad_norm": 0.3516879677772522,
      "learning_rate": 5.937255078927709e-06,
      "loss": 0.3678,
      "step": 41261
    },
    {
      "epoch": 1.267532946272233,
      "grad_norm": 0.4575052857398987,
      "learning_rate": 5.936813488483909e-06,
      "loss": 0.473,
      "step": 41262
    },
    {
      "epoch": 1.2675636654071822,
      "grad_norm": 0.43304580450057983,
      "learning_rate": 5.936371907529963e-06,
      "loss": 0.4612,
      "step": 41263
    },
    {
      "epoch": 1.2675943845421314,
      "grad_norm": 0.4009523391723633,
      "learning_rate": 5.9359303360669056e-06,
      "loss": 0.4452,
      "step": 41264
    },
    {
      "epoch": 1.2676251036770805,
      "grad_norm": 0.398806095123291,
      "learning_rate": 5.935488774095764e-06,
      "loss": 0.5246,
      "step": 41265
    },
    {
      "epoch": 1.2676558228120296,
      "grad_norm": 0.4229170083999634,
      "learning_rate": 5.935047221617576e-06,
      "loss": 0.4388,
      "step": 41266
    },
    {
      "epoch": 1.2676865419469787,
      "grad_norm": 0.48957380652427673,
      "learning_rate": 5.934605678633365e-06,
      "loss": 0.4927,
      "step": 41267
    },
    {
      "epoch": 1.2677172610819278,
      "grad_norm": 0.4040888845920563,
      "learning_rate": 5.93416414514417e-06,
      "loss": 0.4656,
      "step": 41268
    },
    {
      "epoch": 1.267747980216877,
      "grad_norm": 0.3950613737106323,
      "learning_rate": 5.933722621151017e-06,
      "loss": 0.4567,
      "step": 41269
    },
    {
      "epoch": 1.2677786993518263,
      "grad_norm": 0.3959929049015045,
      "learning_rate": 5.933281106654939e-06,
      "loss": 0.4358,
      "step": 41270
    },
    {
      "epoch": 1.2678094184867754,
      "grad_norm": 0.4278689920902252,
      "learning_rate": 5.932839601656966e-06,
      "loss": 0.5216,
      "step": 41271
    },
    {
      "epoch": 1.2678401376217245,
      "grad_norm": 0.4774182438850403,
      "learning_rate": 5.932398106158134e-06,
      "loss": 0.3406,
      "step": 41272
    },
    {
      "epoch": 1.2678708567566737,
      "grad_norm": 0.3840205669403076,
      "learning_rate": 5.931956620159465e-06,
      "loss": 0.4035,
      "step": 41273
    },
    {
      "epoch": 1.267901575891623,
      "grad_norm": 0.4243123531341553,
      "learning_rate": 5.9315151436619955e-06,
      "loss": 0.4985,
      "step": 41274
    },
    {
      "epoch": 1.2679322950265721,
      "grad_norm": 0.40647372603416443,
      "learning_rate": 5.931073676666759e-06,
      "loss": 0.4604,
      "step": 41275
    },
    {
      "epoch": 1.2679630141615212,
      "grad_norm": 0.40424782037734985,
      "learning_rate": 5.930632219174783e-06,
      "loss": 0.4525,
      "step": 41276
    },
    {
      "epoch": 1.2679937332964704,
      "grad_norm": 0.42106178402900696,
      "learning_rate": 5.930190771187103e-06,
      "loss": 0.4497,
      "step": 41277
    },
    {
      "epoch": 1.2680244524314195,
      "grad_norm": 0.39087387919425964,
      "learning_rate": 5.929749332704743e-06,
      "loss": 0.4483,
      "step": 41278
    },
    {
      "epoch": 1.2680551715663686,
      "grad_norm": 0.42293429374694824,
      "learning_rate": 5.929307903728742e-06,
      "loss": 0.5192,
      "step": 41279
    },
    {
      "epoch": 1.2680858907013177,
      "grad_norm": 0.4735105633735657,
      "learning_rate": 5.9288664842601205e-06,
      "loss": 0.4982,
      "step": 41280
    },
    {
      "epoch": 1.268116609836267,
      "grad_norm": 0.39013394713401794,
      "learning_rate": 5.928425074299922e-06,
      "loss": 0.407,
      "step": 41281
    },
    {
      "epoch": 1.2681473289712162,
      "grad_norm": 0.5452008843421936,
      "learning_rate": 5.927983673849165e-06,
      "loss": 0.4757,
      "step": 41282
    },
    {
      "epoch": 1.2681780481061653,
      "grad_norm": 0.43637317419052124,
      "learning_rate": 5.927542282908891e-06,
      "loss": 0.405,
      "step": 41283
    },
    {
      "epoch": 1.2682087672411144,
      "grad_norm": 0.42022690176963806,
      "learning_rate": 5.927100901480125e-06,
      "loss": 0.4746,
      "step": 41284
    },
    {
      "epoch": 1.2682394863760638,
      "grad_norm": 0.41953712701797485,
      "learning_rate": 5.9266595295639e-06,
      "loss": 0.467,
      "step": 41285
    },
    {
      "epoch": 1.2682702055110129,
      "grad_norm": 0.39980173110961914,
      "learning_rate": 5.926218167161244e-06,
      "loss": 0.4664,
      "step": 41286
    },
    {
      "epoch": 1.268300924645962,
      "grad_norm": 0.47074878215789795,
      "learning_rate": 5.925776814273192e-06,
      "loss": 0.4766,
      "step": 41287
    },
    {
      "epoch": 1.2683316437809111,
      "grad_norm": 0.3981199264526367,
      "learning_rate": 5.92533547090077e-06,
      "loss": 0.5322,
      "step": 41288
    },
    {
      "epoch": 1.2683623629158602,
      "grad_norm": 0.40729227662086487,
      "learning_rate": 5.924894137045016e-06,
      "loss": 0.4708,
      "step": 41289
    },
    {
      "epoch": 1.2683930820508094,
      "grad_norm": 0.3913797438144684,
      "learning_rate": 5.9244528127069525e-06,
      "loss": 0.4965,
      "step": 41290
    },
    {
      "epoch": 1.2684238011857585,
      "grad_norm": 0.41155707836151123,
      "learning_rate": 5.924011497887614e-06,
      "loss": 0.5093,
      "step": 41291
    },
    {
      "epoch": 1.2684545203207078,
      "grad_norm": 0.3754326105117798,
      "learning_rate": 5.923570192588034e-06,
      "loss": 0.4244,
      "step": 41292
    },
    {
      "epoch": 1.268485239455657,
      "grad_norm": 0.41190603375434875,
      "learning_rate": 5.923128896809238e-06,
      "loss": 0.5408,
      "step": 41293
    },
    {
      "epoch": 1.268515958590606,
      "grad_norm": 0.44522690773010254,
      "learning_rate": 5.922687610552263e-06,
      "loss": 0.524,
      "step": 41294
    },
    {
      "epoch": 1.2685466777255552,
      "grad_norm": 0.49079230427742004,
      "learning_rate": 5.922246333818131e-06,
      "loss": 0.4644,
      "step": 41295
    },
    {
      "epoch": 1.2685773968605045,
      "grad_norm": 0.3946318030357361,
      "learning_rate": 5.921805066607881e-06,
      "loss": 0.5297,
      "step": 41296
    },
    {
      "epoch": 1.2686081159954536,
      "grad_norm": 0.3753476142883301,
      "learning_rate": 5.921363808922538e-06,
      "loss": 0.4588,
      "step": 41297
    },
    {
      "epoch": 1.2686388351304028,
      "grad_norm": 0.43776893615722656,
      "learning_rate": 5.920922560763136e-06,
      "loss": 0.4398,
      "step": 41298
    },
    {
      "epoch": 1.2686695542653519,
      "grad_norm": 0.3982219099998474,
      "learning_rate": 5.920481322130703e-06,
      "loss": 0.504,
      "step": 41299
    },
    {
      "epoch": 1.268700273400301,
      "grad_norm": 0.3849521577358246,
      "learning_rate": 5.920040093026272e-06,
      "loss": 0.4345,
      "step": 41300
    },
    {
      "epoch": 1.2687309925352501,
      "grad_norm": 0.4237401783466339,
      "learning_rate": 5.919598873450871e-06,
      "loss": 0.476,
      "step": 41301
    },
    {
      "epoch": 1.2687617116701992,
      "grad_norm": 0.43996360898017883,
      "learning_rate": 5.919157663405535e-06,
      "loss": 0.4455,
      "step": 41302
    },
    {
      "epoch": 1.2687924308051486,
      "grad_norm": 0.41775989532470703,
      "learning_rate": 5.9187164628912874e-06,
      "loss": 0.4255,
      "step": 41303
    },
    {
      "epoch": 1.2688231499400977,
      "grad_norm": 0.4016360938549042,
      "learning_rate": 5.918275271909165e-06,
      "loss": 0.5373,
      "step": 41304
    },
    {
      "epoch": 1.2688538690750468,
      "grad_norm": 0.41826558113098145,
      "learning_rate": 5.917834090460194e-06,
      "loss": 0.5279,
      "step": 41305
    },
    {
      "epoch": 1.268884588209996,
      "grad_norm": 0.3903147280216217,
      "learning_rate": 5.917392918545411e-06,
      "loss": 0.5025,
      "step": 41306
    },
    {
      "epoch": 1.2689153073449453,
      "grad_norm": 0.3723048269748688,
      "learning_rate": 5.916951756165834e-06,
      "loss": 0.4613,
      "step": 41307
    },
    {
      "epoch": 1.2689460264798944,
      "grad_norm": 0.606654703617096,
      "learning_rate": 5.916510603322509e-06,
      "loss": 0.5332,
      "step": 41308
    },
    {
      "epoch": 1.2689767456148435,
      "grad_norm": 0.5409907102584839,
      "learning_rate": 5.916069460016453e-06,
      "loss": 0.4395,
      "step": 41309
    },
    {
      "epoch": 1.2690074647497926,
      "grad_norm": 0.41325515508651733,
      "learning_rate": 5.9156283262487035e-06,
      "loss": 0.4144,
      "step": 41310
    },
    {
      "epoch": 1.2690381838847418,
      "grad_norm": 0.3967384397983551,
      "learning_rate": 5.915187202020292e-06,
      "loss": 0.4864,
      "step": 41311
    },
    {
      "epoch": 1.2690689030196909,
      "grad_norm": 0.3990011513233185,
      "learning_rate": 5.914746087332241e-06,
      "loss": 0.4992,
      "step": 41312
    },
    {
      "epoch": 1.26909962215464,
      "grad_norm": 0.39157384634017944,
      "learning_rate": 5.914304982185593e-06,
      "loss": 0.4155,
      "step": 41313
    },
    {
      "epoch": 1.2691303412895893,
      "grad_norm": 0.3926106095314026,
      "learning_rate": 5.913863886581364e-06,
      "loss": 0.4915,
      "step": 41314
    },
    {
      "epoch": 1.2691610604245385,
      "grad_norm": 0.38457778096199036,
      "learning_rate": 5.913422800520599e-06,
      "loss": 0.4659,
      "step": 41315
    },
    {
      "epoch": 1.2691917795594876,
      "grad_norm": 0.44425496459007263,
      "learning_rate": 5.9129817240043116e-06,
      "loss": 0.4705,
      "step": 41316
    },
    {
      "epoch": 1.2692224986944367,
      "grad_norm": 0.4510261118412018,
      "learning_rate": 5.912540657033548e-06,
      "loss": 0.4101,
      "step": 41317
    },
    {
      "epoch": 1.269253217829386,
      "grad_norm": 0.38968053460121155,
      "learning_rate": 5.9120995996093255e-06,
      "loss": 0.4454,
      "step": 41318
    },
    {
      "epoch": 1.2692839369643352,
      "grad_norm": 0.38090163469314575,
      "learning_rate": 5.911658551732687e-06,
      "loss": 0.4813,
      "step": 41319
    },
    {
      "epoch": 1.2693146560992843,
      "grad_norm": 0.40706300735473633,
      "learning_rate": 5.911217513404649e-06,
      "loss": 0.4781,
      "step": 41320
    },
    {
      "epoch": 1.2693453752342334,
      "grad_norm": 0.409847617149353,
      "learning_rate": 5.9107764846262505e-06,
      "loss": 0.4689,
      "step": 41321
    },
    {
      "epoch": 1.2693760943691825,
      "grad_norm": 0.4320457875728607,
      "learning_rate": 5.910335465398518e-06,
      "loss": 0.5429,
      "step": 41322
    },
    {
      "epoch": 1.2694068135041316,
      "grad_norm": 0.4121999740600586,
      "learning_rate": 5.909894455722485e-06,
      "loss": 0.5065,
      "step": 41323
    },
    {
      "epoch": 1.2694375326390808,
      "grad_norm": 0.4324494004249573,
      "learning_rate": 5.909453455599177e-06,
      "loss": 0.3983,
      "step": 41324
    },
    {
      "epoch": 1.26946825177403,
      "grad_norm": 0.4169341027736664,
      "learning_rate": 5.909012465029626e-06,
      "loss": 0.5354,
      "step": 41325
    },
    {
      "epoch": 1.2694989709089792,
      "grad_norm": 0.40487343072891235,
      "learning_rate": 5.908571484014862e-06,
      "loss": 0.4553,
      "step": 41326
    },
    {
      "epoch": 1.2695296900439283,
      "grad_norm": 0.3839641511440277,
      "learning_rate": 5.908130512555917e-06,
      "loss": 0.473,
      "step": 41327
    },
    {
      "epoch": 1.2695604091788775,
      "grad_norm": 0.417965292930603,
      "learning_rate": 5.907689550653817e-06,
      "loss": 0.3993,
      "step": 41328
    },
    {
      "epoch": 1.2695911283138268,
      "grad_norm": 0.3731920123100281,
      "learning_rate": 5.907248598309594e-06,
      "loss": 0.4696,
      "step": 41329
    },
    {
      "epoch": 1.269621847448776,
      "grad_norm": 0.43148675560951233,
      "learning_rate": 5.906807655524279e-06,
      "loss": 0.526,
      "step": 41330
    },
    {
      "epoch": 1.269652566583725,
      "grad_norm": 0.3775755763053894,
      "learning_rate": 5.906366722298899e-06,
      "loss": 0.4826,
      "step": 41331
    },
    {
      "epoch": 1.2696832857186742,
      "grad_norm": 0.4127044379711151,
      "learning_rate": 5.905925798634487e-06,
      "loss": 0.4928,
      "step": 41332
    },
    {
      "epoch": 1.2697140048536233,
      "grad_norm": 0.3999073803424835,
      "learning_rate": 5.905484884532071e-06,
      "loss": 0.5011,
      "step": 41333
    },
    {
      "epoch": 1.2697447239885724,
      "grad_norm": 0.4254896640777588,
      "learning_rate": 5.905043979992682e-06,
      "loss": 0.4853,
      "step": 41334
    },
    {
      "epoch": 1.2697754431235215,
      "grad_norm": 0.39079439640045166,
      "learning_rate": 5.904603085017345e-06,
      "loss": 0.5857,
      "step": 41335
    },
    {
      "epoch": 1.2698061622584709,
      "grad_norm": 0.3940066993236542,
      "learning_rate": 5.904162199607097e-06,
      "loss": 0.5117,
      "step": 41336
    },
    {
      "epoch": 1.26983688139342,
      "grad_norm": 0.4008505046367645,
      "learning_rate": 5.9037213237629635e-06,
      "loss": 0.4301,
      "step": 41337
    },
    {
      "epoch": 1.2698676005283691,
      "grad_norm": 0.4243490397930145,
      "learning_rate": 5.903280457485975e-06,
      "loss": 0.5543,
      "step": 41338
    },
    {
      "epoch": 1.2698983196633182,
      "grad_norm": 0.5014070868492126,
      "learning_rate": 5.90283960077716e-06,
      "loss": 0.522,
      "step": 41339
    },
    {
      "epoch": 1.2699290387982676,
      "grad_norm": 0.3991544246673584,
      "learning_rate": 5.90239875363755e-06,
      "loss": 0.5658,
      "step": 41340
    },
    {
      "epoch": 1.2699597579332167,
      "grad_norm": 0.37979283928871155,
      "learning_rate": 5.901957916068172e-06,
      "loss": 0.4745,
      "step": 41341
    },
    {
      "epoch": 1.2699904770681658,
      "grad_norm": 0.3804655075073242,
      "learning_rate": 5.9015170880700635e-06,
      "loss": 0.5193,
      "step": 41342
    },
    {
      "epoch": 1.270021196203115,
      "grad_norm": 0.4190830588340759,
      "learning_rate": 5.901076269644242e-06,
      "loss": 0.3779,
      "step": 41343
    },
    {
      "epoch": 1.270051915338064,
      "grad_norm": 0.4222702085971832,
      "learning_rate": 5.900635460791746e-06,
      "loss": 0.4722,
      "step": 41344
    },
    {
      "epoch": 1.2700826344730132,
      "grad_norm": 0.43541982769966125,
      "learning_rate": 5.900194661513598e-06,
      "loss": 0.4673,
      "step": 41345
    },
    {
      "epoch": 1.2701133536079623,
      "grad_norm": 0.40015894174575806,
      "learning_rate": 5.899753871810835e-06,
      "loss": 0.4665,
      "step": 41346
    },
    {
      "epoch": 1.2701440727429116,
      "grad_norm": 0.38597890734672546,
      "learning_rate": 5.899313091684486e-06,
      "loss": 0.4744,
      "step": 41347
    },
    {
      "epoch": 1.2701747918778608,
      "grad_norm": 0.4225994944572449,
      "learning_rate": 5.898872321135571e-06,
      "loss": 0.4412,
      "step": 41348
    },
    {
      "epoch": 1.2702055110128099,
      "grad_norm": 0.39859539270401,
      "learning_rate": 5.898431560165134e-06,
      "loss": 0.4445,
      "step": 41349
    },
    {
      "epoch": 1.270236230147759,
      "grad_norm": 0.4289747178554535,
      "learning_rate": 5.897990808774189e-06,
      "loss": 0.4204,
      "step": 41350
    },
    {
      "epoch": 1.2702669492827083,
      "grad_norm": 0.3789541721343994,
      "learning_rate": 5.8975500669637795e-06,
      "loss": 0.4499,
      "step": 41351
    },
    {
      "epoch": 1.2702976684176575,
      "grad_norm": 0.42436811327934265,
      "learning_rate": 5.897109334734921e-06,
      "loss": 0.5013,
      "step": 41352
    },
    {
      "epoch": 1.2703283875526066,
      "grad_norm": 0.39281535148620605,
      "learning_rate": 5.896668612088659e-06,
      "loss": 0.4634,
      "step": 41353
    },
    {
      "epoch": 1.2703591066875557,
      "grad_norm": 0.514150857925415,
      "learning_rate": 5.896227899026008e-06,
      "loss": 0.5673,
      "step": 41354
    },
    {
      "epoch": 1.2703898258225048,
      "grad_norm": 0.4358057379722595,
      "learning_rate": 5.895787195548006e-06,
      "loss": 0.4599,
      "step": 41355
    },
    {
      "epoch": 1.270420544957454,
      "grad_norm": 0.40808215737342834,
      "learning_rate": 5.8953465016556765e-06,
      "loss": 0.449,
      "step": 41356
    },
    {
      "epoch": 1.270451264092403,
      "grad_norm": 0.4185565412044525,
      "learning_rate": 5.894905817350055e-06,
      "loss": 0.4769,
      "step": 41357
    },
    {
      "epoch": 1.2704819832273524,
      "grad_norm": 0.40877968072891235,
      "learning_rate": 5.894465142632165e-06,
      "loss": 0.4984,
      "step": 41358
    },
    {
      "epoch": 1.2705127023623015,
      "grad_norm": 0.3950963318347931,
      "learning_rate": 5.894024477503042e-06,
      "loss": 0.4481,
      "step": 41359
    },
    {
      "epoch": 1.2705434214972506,
      "grad_norm": 0.41018813848495483,
      "learning_rate": 5.893583821963708e-06,
      "loss": 0.493,
      "step": 41360
    },
    {
      "epoch": 1.2705741406321998,
      "grad_norm": 0.5480674505233765,
      "learning_rate": 5.893143176015198e-06,
      "loss": 0.3811,
      "step": 41361
    },
    {
      "epoch": 1.2706048597671489,
      "grad_norm": 0.39263471961021423,
      "learning_rate": 5.892702539658537e-06,
      "loss": 0.404,
      "step": 41362
    },
    {
      "epoch": 1.2706355789020982,
      "grad_norm": 0.4028503894805908,
      "learning_rate": 5.892261912894759e-06,
      "loss": 0.5037,
      "step": 41363
    },
    {
      "epoch": 1.2706662980370473,
      "grad_norm": 0.4596432149410248,
      "learning_rate": 5.8918212957248865e-06,
      "loss": 0.5013,
      "step": 41364
    },
    {
      "epoch": 1.2706970171719965,
      "grad_norm": 0.45266619324684143,
      "learning_rate": 5.891380688149954e-06,
      "loss": 0.5116,
      "step": 41365
    },
    {
      "epoch": 1.2707277363069456,
      "grad_norm": 0.397610604763031,
      "learning_rate": 5.890940090170989e-06,
      "loss": 0.4107,
      "step": 41366
    },
    {
      "epoch": 1.2707584554418947,
      "grad_norm": 0.43177205324172974,
      "learning_rate": 5.89049950178902e-06,
      "loss": 0.5394,
      "step": 41367
    },
    {
      "epoch": 1.2707891745768438,
      "grad_norm": 0.4176245629787445,
      "learning_rate": 5.890058923005078e-06,
      "loss": 0.4866,
      "step": 41368
    },
    {
      "epoch": 1.2708198937117932,
      "grad_norm": 0.4078516662120819,
      "learning_rate": 5.889618353820188e-06,
      "loss": 0.4836,
      "step": 41369
    },
    {
      "epoch": 1.2708506128467423,
      "grad_norm": 0.3935949206352234,
      "learning_rate": 5.889177794235384e-06,
      "loss": 0.4664,
      "step": 41370
    },
    {
      "epoch": 1.2708813319816914,
      "grad_norm": 0.4496193826198578,
      "learning_rate": 5.88873724425169e-06,
      "loss": 0.5439,
      "step": 41371
    },
    {
      "epoch": 1.2709120511166405,
      "grad_norm": 0.43826255202293396,
      "learning_rate": 5.888296703870139e-06,
      "loss": 0.4123,
      "step": 41372
    },
    {
      "epoch": 1.2709427702515896,
      "grad_norm": 0.4057577848434448,
      "learning_rate": 5.8878561730917575e-06,
      "loss": 0.5289,
      "step": 41373
    },
    {
      "epoch": 1.270973489386539,
      "grad_norm": 0.3832973837852478,
      "learning_rate": 5.887415651917575e-06,
      "loss": 0.5044,
      "step": 41374
    },
    {
      "epoch": 1.271004208521488,
      "grad_norm": 0.47846129536628723,
      "learning_rate": 5.88697514034862e-06,
      "loss": 0.5081,
      "step": 41375
    },
    {
      "epoch": 1.2710349276564372,
      "grad_norm": 0.40440383553504944,
      "learning_rate": 5.886534638385926e-06,
      "loss": 0.512,
      "step": 41376
    },
    {
      "epoch": 1.2710656467913863,
      "grad_norm": 0.4058154225349426,
      "learning_rate": 5.88609414603051e-06,
      "loss": 0.5437,
      "step": 41377
    },
    {
      "epoch": 1.2710963659263355,
      "grad_norm": 0.4063854217529297,
      "learning_rate": 5.885653663283415e-06,
      "loss": 0.4799,
      "step": 41378
    },
    {
      "epoch": 1.2711270850612846,
      "grad_norm": 0.3984985053539276,
      "learning_rate": 5.885213190145658e-06,
      "loss": 0.5127,
      "step": 41379
    },
    {
      "epoch": 1.2711578041962337,
      "grad_norm": 0.40277209877967834,
      "learning_rate": 5.8847727266182785e-06,
      "loss": 0.4496,
      "step": 41380
    },
    {
      "epoch": 1.271188523331183,
      "grad_norm": 0.38899290561676025,
      "learning_rate": 5.8843322727022935e-06,
      "loss": 0.4835,
      "step": 41381
    },
    {
      "epoch": 1.2712192424661322,
      "grad_norm": 0.39343228936195374,
      "learning_rate": 5.883891828398744e-06,
      "loss": 0.4696,
      "step": 41382
    },
    {
      "epoch": 1.2712499616010813,
      "grad_norm": 0.3888203799724579,
      "learning_rate": 5.8834513937086505e-06,
      "loss": 0.5189,
      "step": 41383
    },
    {
      "epoch": 1.2712806807360304,
      "grad_norm": 0.3933262825012207,
      "learning_rate": 5.883010968633038e-06,
      "loss": 0.5627,
      "step": 41384
    },
    {
      "epoch": 1.2713113998709797,
      "grad_norm": 0.38515815138816833,
      "learning_rate": 5.88257055317295e-06,
      "loss": 0.4123,
      "step": 41385
    },
    {
      "epoch": 1.2713421190059289,
      "grad_norm": 0.3781580328941345,
      "learning_rate": 5.8821301473293994e-06,
      "loss": 0.4602,
      "step": 41386
    },
    {
      "epoch": 1.271372838140878,
      "grad_norm": 0.48944202065467834,
      "learning_rate": 5.8816897511034275e-06,
      "loss": 0.4428,
      "step": 41387
    },
    {
      "epoch": 1.271403557275827,
      "grad_norm": 0.4055287837982178,
      "learning_rate": 5.881249364496051e-06,
      "loss": 0.4302,
      "step": 41388
    },
    {
      "epoch": 1.2714342764107762,
      "grad_norm": 0.42074576020240784,
      "learning_rate": 5.880808987508309e-06,
      "loss": 0.4841,
      "step": 41389
    },
    {
      "epoch": 1.2714649955457253,
      "grad_norm": 0.5243912935256958,
      "learning_rate": 5.880368620141221e-06,
      "loss": 0.4467,
      "step": 41390
    },
    {
      "epoch": 1.2714957146806745,
      "grad_norm": 0.4172218143939972,
      "learning_rate": 5.879928262395823e-06,
      "loss": 0.4397,
      "step": 41391
    },
    {
      "epoch": 1.2715264338156238,
      "grad_norm": 0.4775083661079407,
      "learning_rate": 5.879487914273139e-06,
      "loss": 0.4992,
      "step": 41392
    },
    {
      "epoch": 1.271557152950573,
      "grad_norm": 0.39477303624153137,
      "learning_rate": 5.879047575774199e-06,
      "loss": 0.485,
      "step": 41393
    },
    {
      "epoch": 1.271587872085522,
      "grad_norm": 0.42092782258987427,
      "learning_rate": 5.87860724690003e-06,
      "loss": 0.4866,
      "step": 41394
    },
    {
      "epoch": 1.2716185912204712,
      "grad_norm": 0.37845200300216675,
      "learning_rate": 5.878166927651663e-06,
      "loss": 0.4761,
      "step": 41395
    },
    {
      "epoch": 1.2716493103554205,
      "grad_norm": 0.4451305568218231,
      "learning_rate": 5.877726618030124e-06,
      "loss": 0.5938,
      "step": 41396
    },
    {
      "epoch": 1.2716800294903696,
      "grad_norm": 0.45733335614204407,
      "learning_rate": 5.877286318036444e-06,
      "loss": 0.5108,
      "step": 41397
    },
    {
      "epoch": 1.2717107486253187,
      "grad_norm": 0.39989838004112244,
      "learning_rate": 5.8768460276716476e-06,
      "loss": 0.5055,
      "step": 41398
    },
    {
      "epoch": 1.2717414677602679,
      "grad_norm": 0.4324319362640381,
      "learning_rate": 5.876405746936767e-06,
      "loss": 0.3837,
      "step": 41399
    },
    {
      "epoch": 1.271772186895217,
      "grad_norm": 0.4018612205982208,
      "learning_rate": 5.875965475832828e-06,
      "loss": 0.5375,
      "step": 41400
    },
    {
      "epoch": 1.271802906030166,
      "grad_norm": 0.40695348381996155,
      "learning_rate": 5.875525214360857e-06,
      "loss": 0.5169,
      "step": 41401
    },
    {
      "epoch": 1.2718336251651152,
      "grad_norm": 0.41780975461006165,
      "learning_rate": 5.875084962521889e-06,
      "loss": 0.4155,
      "step": 41402
    },
    {
      "epoch": 1.2718643443000646,
      "grad_norm": 0.4237145483493805,
      "learning_rate": 5.874644720316946e-06,
      "loss": 0.4895,
      "step": 41403
    },
    {
      "epoch": 1.2718950634350137,
      "grad_norm": 0.43892425298690796,
      "learning_rate": 5.8742044877470605e-06,
      "loss": 0.4782,
      "step": 41404
    },
    {
      "epoch": 1.2719257825699628,
      "grad_norm": 0.41225507855415344,
      "learning_rate": 5.873764264813256e-06,
      "loss": 0.4911,
      "step": 41405
    },
    {
      "epoch": 1.271956501704912,
      "grad_norm": 0.38768628239631653,
      "learning_rate": 5.873324051516566e-06,
      "loss": 0.4816,
      "step": 41406
    },
    {
      "epoch": 1.2719872208398613,
      "grad_norm": 0.3797936737537384,
      "learning_rate": 5.872883847858013e-06,
      "loss": 0.47,
      "step": 41407
    },
    {
      "epoch": 1.2720179399748104,
      "grad_norm": 0.4135116934776306,
      "learning_rate": 5.872443653838631e-06,
      "loss": 0.5152,
      "step": 41408
    },
    {
      "epoch": 1.2720486591097595,
      "grad_norm": 0.4314728379249573,
      "learning_rate": 5.872003469459442e-06,
      "loss": 0.48,
      "step": 41409
    },
    {
      "epoch": 1.2720793782447086,
      "grad_norm": 0.4136136472225189,
      "learning_rate": 5.871563294721482e-06,
      "loss": 0.4762,
      "step": 41410
    },
    {
      "epoch": 1.2721100973796577,
      "grad_norm": 0.4523507058620453,
      "learning_rate": 5.8711231296257675e-06,
      "loss": 0.5405,
      "step": 41411
    },
    {
      "epoch": 1.2721408165146069,
      "grad_norm": 0.4023306667804718,
      "learning_rate": 5.870682974173341e-06,
      "loss": 0.5268,
      "step": 41412
    },
    {
      "epoch": 1.272171535649556,
      "grad_norm": 0.4533446729183197,
      "learning_rate": 5.870242828365214e-06,
      "loss": 0.5395,
      "step": 41413
    },
    {
      "epoch": 1.2722022547845053,
      "grad_norm": 0.446620374917984,
      "learning_rate": 5.869802692202431e-06,
      "loss": 0.4626,
      "step": 41414
    },
    {
      "epoch": 1.2722329739194544,
      "grad_norm": 0.3945568799972534,
      "learning_rate": 5.869362565686007e-06,
      "loss": 0.4868,
      "step": 41415
    },
    {
      "epoch": 1.2722636930544036,
      "grad_norm": 0.438965380191803,
      "learning_rate": 5.86892244881698e-06,
      "loss": 0.4712,
      "step": 41416
    },
    {
      "epoch": 1.2722944121893527,
      "grad_norm": 0.4184338450431824,
      "learning_rate": 5.868482341596369e-06,
      "loss": 0.4673,
      "step": 41417
    },
    {
      "epoch": 1.272325131324302,
      "grad_norm": 0.39173588156700134,
      "learning_rate": 5.868042244025209e-06,
      "loss": 0.4822,
      "step": 41418
    },
    {
      "epoch": 1.2723558504592511,
      "grad_norm": 0.4329569935798645,
      "learning_rate": 5.8676021561045215e-06,
      "loss": 0.4751,
      "step": 41419
    },
    {
      "epoch": 1.2723865695942003,
      "grad_norm": 0.38372182846069336,
      "learning_rate": 5.867162077835338e-06,
      "loss": 0.423,
      "step": 41420
    },
    {
      "epoch": 1.2724172887291494,
      "grad_norm": 0.44630521535873413,
      "learning_rate": 5.86672200921869e-06,
      "loss": 0.3883,
      "step": 41421
    },
    {
      "epoch": 1.2724480078640985,
      "grad_norm": 0.38685357570648193,
      "learning_rate": 5.866281950255596e-06,
      "loss": 0.4841,
      "step": 41422
    },
    {
      "epoch": 1.2724787269990476,
      "grad_norm": 0.450103759765625,
      "learning_rate": 5.865841900947096e-06,
      "loss": 0.4295,
      "step": 41423
    },
    {
      "epoch": 1.2725094461339967,
      "grad_norm": 0.4183484613895416,
      "learning_rate": 5.8654018612942055e-06,
      "loss": 0.5448,
      "step": 41424
    },
    {
      "epoch": 1.272540165268946,
      "grad_norm": 0.42336589097976685,
      "learning_rate": 5.864961831297961e-06,
      "loss": 0.4966,
      "step": 41425
    },
    {
      "epoch": 1.2725708844038952,
      "grad_norm": 0.4075864553451538,
      "learning_rate": 5.864521810959384e-06,
      "loss": 0.4607,
      "step": 41426
    },
    {
      "epoch": 1.2726016035388443,
      "grad_norm": 0.4279569685459137,
      "learning_rate": 5.864081800279508e-06,
      "loss": 0.4959,
      "step": 41427
    },
    {
      "epoch": 1.2726323226737934,
      "grad_norm": 0.3997330367565155,
      "learning_rate": 5.8636417992593545e-06,
      "loss": 0.497,
      "step": 41428
    },
    {
      "epoch": 1.2726630418087428,
      "grad_norm": 0.4619435966014862,
      "learning_rate": 5.863201807899958e-06,
      "loss": 0.4864,
      "step": 41429
    },
    {
      "epoch": 1.272693760943692,
      "grad_norm": 0.4417138397693634,
      "learning_rate": 5.862761826202339e-06,
      "loss": 0.4463,
      "step": 41430
    },
    {
      "epoch": 1.272724480078641,
      "grad_norm": 0.4320261478424072,
      "learning_rate": 5.862321854167532e-06,
      "loss": 0.5045,
      "step": 41431
    },
    {
      "epoch": 1.2727551992135901,
      "grad_norm": 0.4057077169418335,
      "learning_rate": 5.861881891796559e-06,
      "loss": 0.4777,
      "step": 41432
    },
    {
      "epoch": 1.2727859183485393,
      "grad_norm": 0.4386136829853058,
      "learning_rate": 5.861441939090452e-06,
      "loss": 0.3844,
      "step": 41433
    },
    {
      "epoch": 1.2728166374834884,
      "grad_norm": 0.4481438994407654,
      "learning_rate": 5.861001996050234e-06,
      "loss": 0.4363,
      "step": 41434
    },
    {
      "epoch": 1.2728473566184375,
      "grad_norm": 0.4326924681663513,
      "learning_rate": 5.860562062676938e-06,
      "loss": 0.4592,
      "step": 41435
    },
    {
      "epoch": 1.2728780757533869,
      "grad_norm": 0.40775492787361145,
      "learning_rate": 5.8601221389715846e-06,
      "loss": 0.5418,
      "step": 41436
    },
    {
      "epoch": 1.272908794888336,
      "grad_norm": 0.404925674200058,
      "learning_rate": 5.8596822249352056e-06,
      "loss": 0.4417,
      "step": 41437
    },
    {
      "epoch": 1.272939514023285,
      "grad_norm": 0.41000184416770935,
      "learning_rate": 5.85924232056883e-06,
      "loss": 0.5015,
      "step": 41438
    },
    {
      "epoch": 1.2729702331582342,
      "grad_norm": 0.703825056552887,
      "learning_rate": 5.858802425873482e-06,
      "loss": 0.4536,
      "step": 41439
    },
    {
      "epoch": 1.2730009522931836,
      "grad_norm": 0.4429377317428589,
      "learning_rate": 5.858362540850191e-06,
      "loss": 0.5893,
      "step": 41440
    },
    {
      "epoch": 1.2730316714281327,
      "grad_norm": 0.4475460946559906,
      "learning_rate": 5.857922665499982e-06,
      "loss": 0.4999,
      "step": 41441
    },
    {
      "epoch": 1.2730623905630818,
      "grad_norm": 0.4199966788291931,
      "learning_rate": 5.857482799823886e-06,
      "loss": 0.4876,
      "step": 41442
    },
    {
      "epoch": 1.273093109698031,
      "grad_norm": 0.44790324568748474,
      "learning_rate": 5.857042943822926e-06,
      "loss": 0.4621,
      "step": 41443
    },
    {
      "epoch": 1.27312382883298,
      "grad_norm": 0.4280140697956085,
      "learning_rate": 5.856603097498135e-06,
      "loss": 0.5132,
      "step": 41444
    },
    {
      "epoch": 1.2731545479679292,
      "grad_norm": 0.38298773765563965,
      "learning_rate": 5.856163260850534e-06,
      "loss": 0.4426,
      "step": 41445
    },
    {
      "epoch": 1.2731852671028783,
      "grad_norm": 0.3961743116378784,
      "learning_rate": 5.855723433881155e-06,
      "loss": 0.4979,
      "step": 41446
    },
    {
      "epoch": 1.2732159862378276,
      "grad_norm": 0.43742111325263977,
      "learning_rate": 5.85528361659102e-06,
      "loss": 0.3815,
      "step": 41447
    },
    {
      "epoch": 1.2732467053727767,
      "grad_norm": 0.4040376543998718,
      "learning_rate": 5.854843808981164e-06,
      "loss": 0.4777,
      "step": 41448
    },
    {
      "epoch": 1.2732774245077259,
      "grad_norm": 0.4093991219997406,
      "learning_rate": 5.854404011052605e-06,
      "loss": 0.3826,
      "step": 41449
    },
    {
      "epoch": 1.273308143642675,
      "grad_norm": 0.39848026633262634,
      "learning_rate": 5.85396422280638e-06,
      "loss": 0.5277,
      "step": 41450
    },
    {
      "epoch": 1.2733388627776243,
      "grad_norm": 0.3701067268848419,
      "learning_rate": 5.853524444243508e-06,
      "loss": 0.5219,
      "step": 41451
    },
    {
      "epoch": 1.2733695819125734,
      "grad_norm": 0.573293924331665,
      "learning_rate": 5.85308467536502e-06,
      "loss": 0.4066,
      "step": 41452
    },
    {
      "epoch": 1.2734003010475226,
      "grad_norm": 0.41139304637908936,
      "learning_rate": 5.852644916171941e-06,
      "loss": 0.4268,
      "step": 41453
    },
    {
      "epoch": 1.2734310201824717,
      "grad_norm": 0.439886212348938,
      "learning_rate": 5.852205166665301e-06,
      "loss": 0.466,
      "step": 41454
    },
    {
      "epoch": 1.2734617393174208,
      "grad_norm": 0.40662580728530884,
      "learning_rate": 5.851765426846125e-06,
      "loss": 0.4671,
      "step": 41455
    },
    {
      "epoch": 1.27349245845237,
      "grad_norm": 0.4311266243457794,
      "learning_rate": 5.851325696715437e-06,
      "loss": 0.4768,
      "step": 41456
    },
    {
      "epoch": 1.273523177587319,
      "grad_norm": 0.43663570284843445,
      "learning_rate": 5.8508859762742745e-06,
      "loss": 0.5701,
      "step": 41457
    },
    {
      "epoch": 1.2735538967222684,
      "grad_norm": 0.4183357059955597,
      "learning_rate": 5.850446265523653e-06,
      "loss": 0.4605,
      "step": 41458
    },
    {
      "epoch": 1.2735846158572175,
      "grad_norm": 0.39875170588493347,
      "learning_rate": 5.8500065644646065e-06,
      "loss": 0.511,
      "step": 41459
    },
    {
      "epoch": 1.2736153349921666,
      "grad_norm": 0.39137065410614014,
      "learning_rate": 5.849566873098157e-06,
      "loss": 0.4323,
      "step": 41460
    },
    {
      "epoch": 1.2736460541271157,
      "grad_norm": 0.42936769127845764,
      "learning_rate": 5.8491271914253364e-06,
      "loss": 0.4506,
      "step": 41461
    },
    {
      "epoch": 1.273676773262065,
      "grad_norm": 0.4541206359863281,
      "learning_rate": 5.848687519447167e-06,
      "loss": 0.4033,
      "step": 41462
    },
    {
      "epoch": 1.2737074923970142,
      "grad_norm": 0.4133189916610718,
      "learning_rate": 5.84824785716468e-06,
      "loss": 0.4628,
      "step": 41463
    },
    {
      "epoch": 1.2737382115319633,
      "grad_norm": 0.43660691380500793,
      "learning_rate": 5.847808204578898e-06,
      "loss": 0.5237,
      "step": 41464
    },
    {
      "epoch": 1.2737689306669124,
      "grad_norm": 0.4184844493865967,
      "learning_rate": 5.847368561690852e-06,
      "loss": 0.4991,
      "step": 41465
    },
    {
      "epoch": 1.2737996498018616,
      "grad_norm": 0.4385421872138977,
      "learning_rate": 5.846928928501563e-06,
      "loss": 0.4747,
      "step": 41466
    },
    {
      "epoch": 1.2738303689368107,
      "grad_norm": 0.36520910263061523,
      "learning_rate": 5.846489305012066e-06,
      "loss": 0.4604,
      "step": 41467
    },
    {
      "epoch": 1.2738610880717598,
      "grad_norm": 0.39450234174728394,
      "learning_rate": 5.84604969122338e-06,
      "loss": 0.4663,
      "step": 41468
    },
    {
      "epoch": 1.2738918072067091,
      "grad_norm": 0.42277321219444275,
      "learning_rate": 5.845610087136538e-06,
      "loss": 0.4102,
      "step": 41469
    },
    {
      "epoch": 1.2739225263416583,
      "grad_norm": 0.44752374291419983,
      "learning_rate": 5.845170492752561e-06,
      "loss": 0.4735,
      "step": 41470
    },
    {
      "epoch": 1.2739532454766074,
      "grad_norm": 0.39013686776161194,
      "learning_rate": 5.84473090807248e-06,
      "loss": 0.5042,
      "step": 41471
    },
    {
      "epoch": 1.2739839646115565,
      "grad_norm": 0.4335809350013733,
      "learning_rate": 5.84429133309732e-06,
      "loss": 0.4699,
      "step": 41472
    },
    {
      "epoch": 1.2740146837465056,
      "grad_norm": 0.4639160633087158,
      "learning_rate": 5.84385176782811e-06,
      "loss": 0.4454,
      "step": 41473
    },
    {
      "epoch": 1.274045402881455,
      "grad_norm": 0.4070681929588318,
      "learning_rate": 5.843412212265869e-06,
      "loss": 0.5236,
      "step": 41474
    },
    {
      "epoch": 1.274076122016404,
      "grad_norm": 0.39441055059432983,
      "learning_rate": 5.8429726664116304e-06,
      "loss": 0.4821,
      "step": 41475
    },
    {
      "epoch": 1.2741068411513532,
      "grad_norm": 0.3893955647945404,
      "learning_rate": 5.842533130266423e-06,
      "loss": 0.4638,
      "step": 41476
    },
    {
      "epoch": 1.2741375602863023,
      "grad_norm": 0.4339165687561035,
      "learning_rate": 5.842093603831267e-06,
      "loss": 0.4494,
      "step": 41477
    },
    {
      "epoch": 1.2741682794212514,
      "grad_norm": 0.39272820949554443,
      "learning_rate": 5.841654087107193e-06,
      "loss": 0.479,
      "step": 41478
    },
    {
      "epoch": 1.2741989985562006,
      "grad_norm": 0.3660528063774109,
      "learning_rate": 5.841214580095226e-06,
      "loss": 0.461,
      "step": 41479
    },
    {
      "epoch": 1.27422971769115,
      "grad_norm": 0.4274250864982605,
      "learning_rate": 5.840775082796396e-06,
      "loss": 0.5399,
      "step": 41480
    },
    {
      "epoch": 1.274260436826099,
      "grad_norm": 0.40709519386291504,
      "learning_rate": 5.84033559521172e-06,
      "loss": 0.4485,
      "step": 41481
    },
    {
      "epoch": 1.2742911559610481,
      "grad_norm": 0.3975209593772888,
      "learning_rate": 5.839896117342236e-06,
      "loss": 0.4839,
      "step": 41482
    },
    {
      "epoch": 1.2743218750959973,
      "grad_norm": 0.403294175863266,
      "learning_rate": 5.8394566491889615e-06,
      "loss": 0.4945,
      "step": 41483
    },
    {
      "epoch": 1.2743525942309464,
      "grad_norm": 0.489072322845459,
      "learning_rate": 5.839017190752931e-06,
      "loss": 0.5217,
      "step": 41484
    },
    {
      "epoch": 1.2743833133658957,
      "grad_norm": 0.39827075600624084,
      "learning_rate": 5.838577742035161e-06,
      "loss": 0.4843,
      "step": 41485
    },
    {
      "epoch": 1.2744140325008448,
      "grad_norm": 0.41092485189437866,
      "learning_rate": 5.8381383030366865e-06,
      "loss": 0.5315,
      "step": 41486
    },
    {
      "epoch": 1.274444751635794,
      "grad_norm": 0.43754348158836365,
      "learning_rate": 5.837698873758529e-06,
      "loss": 0.5707,
      "step": 41487
    },
    {
      "epoch": 1.274475470770743,
      "grad_norm": 0.3902526795864105,
      "learning_rate": 5.8372594542017206e-06,
      "loss": 0.5236,
      "step": 41488
    },
    {
      "epoch": 1.2745061899056922,
      "grad_norm": 0.4041914939880371,
      "learning_rate": 5.8368200443672795e-06,
      "loss": 0.5265,
      "step": 41489
    },
    {
      "epoch": 1.2745369090406413,
      "grad_norm": 0.3943483531475067,
      "learning_rate": 5.836380644256236e-06,
      "loss": 0.4863,
      "step": 41490
    },
    {
      "epoch": 1.2745676281755904,
      "grad_norm": 0.4362550973892212,
      "learning_rate": 5.835941253869616e-06,
      "loss": 0.5017,
      "step": 41491
    },
    {
      "epoch": 1.2745983473105398,
      "grad_norm": 0.371770441532135,
      "learning_rate": 5.835501873208447e-06,
      "loss": 0.4459,
      "step": 41492
    },
    {
      "epoch": 1.274629066445489,
      "grad_norm": 0.3813365399837494,
      "learning_rate": 5.835062502273756e-06,
      "loss": 0.4975,
      "step": 41493
    },
    {
      "epoch": 1.274659785580438,
      "grad_norm": 0.39913004636764526,
      "learning_rate": 5.834623141066564e-06,
      "loss": 0.3698,
      "step": 41494
    },
    {
      "epoch": 1.2746905047153871,
      "grad_norm": 0.41396740078926086,
      "learning_rate": 5.834183789587903e-06,
      "loss": 0.508,
      "step": 41495
    },
    {
      "epoch": 1.2747212238503365,
      "grad_norm": 0.4055292308330536,
      "learning_rate": 5.8337444478387936e-06,
      "loss": 0.4669,
      "step": 41496
    },
    {
      "epoch": 1.2747519429852856,
      "grad_norm": 0.4479926824569702,
      "learning_rate": 5.8333051158202715e-06,
      "loss": 0.4321,
      "step": 41497
    },
    {
      "epoch": 1.2747826621202347,
      "grad_norm": 0.41443872451782227,
      "learning_rate": 5.832865793533351e-06,
      "loss": 0.4555,
      "step": 41498
    },
    {
      "epoch": 1.2748133812551838,
      "grad_norm": 0.40286073088645935,
      "learning_rate": 5.832426480979067e-06,
      "loss": 0.458,
      "step": 41499
    },
    {
      "epoch": 1.274844100390133,
      "grad_norm": 0.43560612201690674,
      "learning_rate": 5.831987178158436e-06,
      "loss": 0.4617,
      "step": 41500
    },
    {
      "epoch": 1.274874819525082,
      "grad_norm": 0.4012758433818817,
      "learning_rate": 5.8315478850724975e-06,
      "loss": 0.5515,
      "step": 41501
    },
    {
      "epoch": 1.2749055386600312,
      "grad_norm": 0.4063296616077423,
      "learning_rate": 5.831108601722264e-06,
      "loss": 0.4225,
      "step": 41502
    },
    {
      "epoch": 1.2749362577949805,
      "grad_norm": 0.416267991065979,
      "learning_rate": 5.830669328108773e-06,
      "loss": 0.4638,
      "step": 41503
    },
    {
      "epoch": 1.2749669769299297,
      "grad_norm": 0.3842184841632843,
      "learning_rate": 5.83023006423304e-06,
      "loss": 0.4779,
      "step": 41504
    },
    {
      "epoch": 1.2749976960648788,
      "grad_norm": 0.3823379874229431,
      "learning_rate": 5.8297908100960976e-06,
      "loss": 0.495,
      "step": 41505
    },
    {
      "epoch": 1.275028415199828,
      "grad_norm": 0.4035501778125763,
      "learning_rate": 5.829351565698968e-06,
      "loss": 0.4838,
      "step": 41506
    },
    {
      "epoch": 1.2750591343347772,
      "grad_norm": 0.4155062735080719,
      "learning_rate": 5.8289123310426855e-06,
      "loss": 0.4288,
      "step": 41507
    },
    {
      "epoch": 1.2750898534697264,
      "grad_norm": 0.40182918310165405,
      "learning_rate": 5.828473106128264e-06,
      "loss": 0.4649,
      "step": 41508
    },
    {
      "epoch": 1.2751205726046755,
      "grad_norm": 0.40601715445518494,
      "learning_rate": 5.8280338909567346e-06,
      "loss": 0.515,
      "step": 41509
    },
    {
      "epoch": 1.2751512917396246,
      "grad_norm": 0.4213080406188965,
      "learning_rate": 5.8275946855291245e-06,
      "loss": 0.4824,
      "step": 41510
    },
    {
      "epoch": 1.2751820108745737,
      "grad_norm": 0.40725046396255493,
      "learning_rate": 5.8271554898464575e-06,
      "loss": 0.4734,
      "step": 41511
    },
    {
      "epoch": 1.2752127300095228,
      "grad_norm": 0.4138723909854889,
      "learning_rate": 5.826716303909765e-06,
      "loss": 0.4559,
      "step": 41512
    },
    {
      "epoch": 1.275243449144472,
      "grad_norm": 0.4083678126335144,
      "learning_rate": 5.826277127720064e-06,
      "loss": 0.4397,
      "step": 41513
    },
    {
      "epoch": 1.2752741682794213,
      "grad_norm": 0.4123571515083313,
      "learning_rate": 5.8258379612783835e-06,
      "loss": 0.4686,
      "step": 41514
    },
    {
      "epoch": 1.2753048874143704,
      "grad_norm": 0.40940046310424805,
      "learning_rate": 5.82539880458575e-06,
      "loss": 0.5818,
      "step": 41515
    },
    {
      "epoch": 1.2753356065493195,
      "grad_norm": 0.42460009455680847,
      "learning_rate": 5.824959657643194e-06,
      "loss": 0.5093,
      "step": 41516
    },
    {
      "epoch": 1.2753663256842687,
      "grad_norm": 0.40811336040496826,
      "learning_rate": 5.824520520451732e-06,
      "loss": 0.477,
      "step": 41517
    },
    {
      "epoch": 1.275397044819218,
      "grad_norm": 0.4440211057662964,
      "learning_rate": 5.8240813930123925e-06,
      "loss": 0.4741,
      "step": 41518
    },
    {
      "epoch": 1.2754277639541671,
      "grad_norm": 0.430337131023407,
      "learning_rate": 5.823642275326205e-06,
      "loss": 0.4834,
      "step": 41519
    },
    {
      "epoch": 1.2754584830891162,
      "grad_norm": 0.422301709651947,
      "learning_rate": 5.823203167394196e-06,
      "loss": 0.514,
      "step": 41520
    },
    {
      "epoch": 1.2754892022240654,
      "grad_norm": 0.42188695073127747,
      "learning_rate": 5.822764069217383e-06,
      "loss": 0.4834,
      "step": 41521
    },
    {
      "epoch": 1.2755199213590145,
      "grad_norm": 0.4156605899333954,
      "learning_rate": 5.822324980796796e-06,
      "loss": 0.5224,
      "step": 41522
    },
    {
      "epoch": 1.2755506404939636,
      "grad_norm": 0.4081054925918579,
      "learning_rate": 5.821885902133462e-06,
      "loss": 0.4451,
      "step": 41523
    },
    {
      "epoch": 1.2755813596289127,
      "grad_norm": 0.44113945960998535,
      "learning_rate": 5.821446833228408e-06,
      "loss": 0.4512,
      "step": 41524
    },
    {
      "epoch": 1.275612078763862,
      "grad_norm": 0.404435932636261,
      "learning_rate": 5.821007774082652e-06,
      "loss": 0.4722,
      "step": 41525
    },
    {
      "epoch": 1.2756427978988112,
      "grad_norm": 0.4254986643791199,
      "learning_rate": 5.820568724697231e-06,
      "loss": 0.4729,
      "step": 41526
    },
    {
      "epoch": 1.2756735170337603,
      "grad_norm": 0.3863597810268402,
      "learning_rate": 5.820129685073153e-06,
      "loss": 0.4104,
      "step": 41527
    },
    {
      "epoch": 1.2757042361687094,
      "grad_norm": 0.4308980703353882,
      "learning_rate": 5.819690655211463e-06,
      "loss": 0.5688,
      "step": 41528
    },
    {
      "epoch": 1.2757349553036588,
      "grad_norm": 0.4092213809490204,
      "learning_rate": 5.819251635113174e-06,
      "loss": 0.4618,
      "step": 41529
    },
    {
      "epoch": 1.2757656744386079,
      "grad_norm": 0.3973539471626282,
      "learning_rate": 5.8188126247793145e-06,
      "loss": 0.4308,
      "step": 41530
    },
    {
      "epoch": 1.275796393573557,
      "grad_norm": 0.3899122476577759,
      "learning_rate": 5.818373624210909e-06,
      "loss": 0.516,
      "step": 41531
    },
    {
      "epoch": 1.2758271127085061,
      "grad_norm": 0.3952498137950897,
      "learning_rate": 5.817934633408986e-06,
      "loss": 0.4383,
      "step": 41532
    },
    {
      "epoch": 1.2758578318434552,
      "grad_norm": 0.4616275429725647,
      "learning_rate": 5.81749565237457e-06,
      "loss": 0.4535,
      "step": 41533
    },
    {
      "epoch": 1.2758885509784044,
      "grad_norm": 0.4345974028110504,
      "learning_rate": 5.817056681108684e-06,
      "loss": 0.5748,
      "step": 41534
    },
    {
      "epoch": 1.2759192701133535,
      "grad_norm": 0.42642301321029663,
      "learning_rate": 5.8166177196123565e-06,
      "loss": 0.5333,
      "step": 41535
    },
    {
      "epoch": 1.2759499892483028,
      "grad_norm": 0.41952306032180786,
      "learning_rate": 5.816178767886602e-06,
      "loss": 0.4151,
      "step": 41536
    },
    {
      "epoch": 1.275980708383252,
      "grad_norm": 0.3938862979412079,
      "learning_rate": 5.815739825932464e-06,
      "loss": 0.4187,
      "step": 41537
    },
    {
      "epoch": 1.276011427518201,
      "grad_norm": 0.40366193652153015,
      "learning_rate": 5.815300893750953e-06,
      "loss": 0.544,
      "step": 41538
    },
    {
      "epoch": 1.2760421466531502,
      "grad_norm": 0.4581213593482971,
      "learning_rate": 5.814861971343102e-06,
      "loss": 0.534,
      "step": 41539
    },
    {
      "epoch": 1.2760728657880995,
      "grad_norm": 0.380890429019928,
      "learning_rate": 5.814423058709931e-06,
      "loss": 0.4022,
      "step": 41540
    },
    {
      "epoch": 1.2761035849230487,
      "grad_norm": 0.43621236085891724,
      "learning_rate": 5.813984155852466e-06,
      "loss": 0.4703,
      "step": 41541
    },
    {
      "epoch": 1.2761343040579978,
      "grad_norm": 0.4620770812034607,
      "learning_rate": 5.813545262771734e-06,
      "loss": 0.525,
      "step": 41542
    },
    {
      "epoch": 1.276165023192947,
      "grad_norm": 0.3762878179550171,
      "learning_rate": 5.813106379468762e-06,
      "loss": 0.4883,
      "step": 41543
    },
    {
      "epoch": 1.276195742327896,
      "grad_norm": 0.4030396342277527,
      "learning_rate": 5.81266750594457e-06,
      "loss": 0.4269,
      "step": 41544
    },
    {
      "epoch": 1.2762264614628451,
      "grad_norm": 0.38934001326560974,
      "learning_rate": 5.812228642200185e-06,
      "loss": 0.5566,
      "step": 41545
    },
    {
      "epoch": 1.2762571805977942,
      "grad_norm": 0.41576704382896423,
      "learning_rate": 5.811789788236633e-06,
      "loss": 0.4926,
      "step": 41546
    },
    {
      "epoch": 1.2762878997327436,
      "grad_norm": 0.4012848734855652,
      "learning_rate": 5.811350944054938e-06,
      "loss": 0.5112,
      "step": 41547
    },
    {
      "epoch": 1.2763186188676927,
      "grad_norm": 0.360781192779541,
      "learning_rate": 5.810912109656128e-06,
      "loss": 0.5203,
      "step": 41548
    },
    {
      "epoch": 1.2763493380026418,
      "grad_norm": 0.39352259039878845,
      "learning_rate": 5.8104732850412235e-06,
      "loss": 0.4759,
      "step": 41549
    },
    {
      "epoch": 1.276380057137591,
      "grad_norm": 0.40609946846961975,
      "learning_rate": 5.81003447021125e-06,
      "loss": 0.4546,
      "step": 41550
    },
    {
      "epoch": 1.2764107762725403,
      "grad_norm": 0.3795590102672577,
      "learning_rate": 5.809595665167235e-06,
      "loss": 0.5106,
      "step": 41551
    },
    {
      "epoch": 1.2764414954074894,
      "grad_norm": 0.4010688364505768,
      "learning_rate": 5.809156869910204e-06,
      "loss": 0.4429,
      "step": 41552
    },
    {
      "epoch": 1.2764722145424385,
      "grad_norm": 0.47563380002975464,
      "learning_rate": 5.808718084441177e-06,
      "loss": 0.4268,
      "step": 41553
    },
    {
      "epoch": 1.2765029336773877,
      "grad_norm": 0.4163133502006531,
      "learning_rate": 5.808279308761182e-06,
      "loss": 0.4869,
      "step": 41554
    },
    {
      "epoch": 1.2765336528123368,
      "grad_norm": 0.4324827194213867,
      "learning_rate": 5.8078405428712424e-06,
      "loss": 0.5142,
      "step": 41555
    },
    {
      "epoch": 1.276564371947286,
      "grad_norm": 0.4450218379497528,
      "learning_rate": 5.807401786772389e-06,
      "loss": 0.4951,
      "step": 41556
    },
    {
      "epoch": 1.276595091082235,
      "grad_norm": 0.406191885471344,
      "learning_rate": 5.806963040465636e-06,
      "loss": 0.5191,
      "step": 41557
    },
    {
      "epoch": 1.2766258102171844,
      "grad_norm": 0.5369738340377808,
      "learning_rate": 5.806524303952015e-06,
      "loss": 0.5109,
      "step": 41558
    },
    {
      "epoch": 1.2766565293521335,
      "grad_norm": 0.4139976501464844,
      "learning_rate": 5.806085577232549e-06,
      "loss": 0.5262,
      "step": 41559
    },
    {
      "epoch": 1.2766872484870826,
      "grad_norm": 0.378143310546875,
      "learning_rate": 5.805646860308268e-06,
      "loss": 0.4841,
      "step": 41560
    },
    {
      "epoch": 1.2767179676220317,
      "grad_norm": 0.3983762860298157,
      "learning_rate": 5.805208153180186e-06,
      "loss": 0.4809,
      "step": 41561
    },
    {
      "epoch": 1.276748686756981,
      "grad_norm": 0.40342122316360474,
      "learning_rate": 5.804769455849338e-06,
      "loss": 0.4653,
      "step": 41562
    },
    {
      "epoch": 1.2767794058919302,
      "grad_norm": 0.43233522772789,
      "learning_rate": 5.804330768316737e-06,
      "loss": 0.4841,
      "step": 41563
    },
    {
      "epoch": 1.2768101250268793,
      "grad_norm": 0.6474491953849792,
      "learning_rate": 5.8038920905834205e-06,
      "loss": 0.427,
      "step": 41564
    },
    {
      "epoch": 1.2768408441618284,
      "grad_norm": 0.4828680157661438,
      "learning_rate": 5.803453422650405e-06,
      "loss": 0.5052,
      "step": 41565
    },
    {
      "epoch": 1.2768715632967775,
      "grad_norm": 0.40066996216773987,
      "learning_rate": 5.803014764518715e-06,
      "loss": 0.4582,
      "step": 41566
    },
    {
      "epoch": 1.2769022824317267,
      "grad_norm": 0.3781823515892029,
      "learning_rate": 5.8025761161893825e-06,
      "loss": 0.4108,
      "step": 41567
    },
    {
      "epoch": 1.2769330015666758,
      "grad_norm": 0.37966081500053406,
      "learning_rate": 5.8021374776634184e-06,
      "loss": 0.5067,
      "step": 41568
    },
    {
      "epoch": 1.2769637207016251,
      "grad_norm": 0.4662468731403351,
      "learning_rate": 5.801698848941863e-06,
      "loss": 0.454,
      "step": 41569
    },
    {
      "epoch": 1.2769944398365742,
      "grad_norm": 0.4483598470687866,
      "learning_rate": 5.80126023002573e-06,
      "loss": 0.4042,
      "step": 41570
    },
    {
      "epoch": 1.2770251589715234,
      "grad_norm": 0.4074663817882538,
      "learning_rate": 5.8008216209160505e-06,
      "loss": 0.5007,
      "step": 41571
    },
    {
      "epoch": 1.2770558781064725,
      "grad_norm": 0.3818470537662506,
      "learning_rate": 5.800383021613838e-06,
      "loss": 0.4838,
      "step": 41572
    },
    {
      "epoch": 1.2770865972414218,
      "grad_norm": 0.4324020445346832,
      "learning_rate": 5.7999444321201325e-06,
      "loss": 0.547,
      "step": 41573
    },
    {
      "epoch": 1.277117316376371,
      "grad_norm": 0.3853200674057007,
      "learning_rate": 5.799505852435945e-06,
      "loss": 0.4386,
      "step": 41574
    },
    {
      "epoch": 1.27714803551132,
      "grad_norm": 0.4049331843852997,
      "learning_rate": 5.799067282562309e-06,
      "loss": 0.3831,
      "step": 41575
    },
    {
      "epoch": 1.2771787546462692,
      "grad_norm": 0.4091884195804596,
      "learning_rate": 5.798628722500241e-06,
      "loss": 0.554,
      "step": 41576
    },
    {
      "epoch": 1.2772094737812183,
      "grad_norm": 0.42070966958999634,
      "learning_rate": 5.7981901722507685e-06,
      "loss": 0.4537,
      "step": 41577
    },
    {
      "epoch": 1.2772401929161674,
      "grad_norm": 0.4086466431617737,
      "learning_rate": 5.797751631814916e-06,
      "loss": 0.4527,
      "step": 41578
    },
    {
      "epoch": 1.2772709120511165,
      "grad_norm": 0.4189967215061188,
      "learning_rate": 5.797313101193713e-06,
      "loss": 0.4855,
      "step": 41579
    },
    {
      "epoch": 1.2773016311860659,
      "grad_norm": 0.40920960903167725,
      "learning_rate": 5.796874580388176e-06,
      "loss": 0.4373,
      "step": 41580
    },
    {
      "epoch": 1.277332350321015,
      "grad_norm": 0.38251036405563354,
      "learning_rate": 5.796436069399331e-06,
      "loss": 0.4935,
      "step": 41581
    },
    {
      "epoch": 1.2773630694559641,
      "grad_norm": 0.45218920707702637,
      "learning_rate": 5.795997568228202e-06,
      "loss": 0.4499,
      "step": 41582
    },
    {
      "epoch": 1.2773937885909132,
      "grad_norm": 0.41829416155815125,
      "learning_rate": 5.795559076875815e-06,
      "loss": 0.5302,
      "step": 41583
    },
    {
      "epoch": 1.2774245077258624,
      "grad_norm": 0.39357540011405945,
      "learning_rate": 5.7951205953431975e-06,
      "loss": 0.433,
      "step": 41584
    },
    {
      "epoch": 1.2774552268608117,
      "grad_norm": 0.41353100538253784,
      "learning_rate": 5.794682123631366e-06,
      "loss": 0.5763,
      "step": 41585
    },
    {
      "epoch": 1.2774859459957608,
      "grad_norm": 0.43896234035491943,
      "learning_rate": 5.794243661741346e-06,
      "loss": 0.428,
      "step": 41586
    },
    {
      "epoch": 1.27751666513071,
      "grad_norm": 0.4157128930091858,
      "learning_rate": 5.793805209674166e-06,
      "loss": 0.4633,
      "step": 41587
    },
    {
      "epoch": 1.277547384265659,
      "grad_norm": 0.35979214310646057,
      "learning_rate": 5.793366767430851e-06,
      "loss": 0.4267,
      "step": 41588
    },
    {
      "epoch": 1.2775781034006082,
      "grad_norm": 0.4125361144542694,
      "learning_rate": 5.7929283350124175e-06,
      "loss": 0.482,
      "step": 41589
    },
    {
      "epoch": 1.2776088225355573,
      "grad_norm": 0.4317063093185425,
      "learning_rate": 5.792489912419894e-06,
      "loss": 0.5335,
      "step": 41590
    },
    {
      "epoch": 1.2776395416705066,
      "grad_norm": 0.40681350231170654,
      "learning_rate": 5.792051499654303e-06,
      "loss": 0.4623,
      "step": 41591
    },
    {
      "epoch": 1.2776702608054558,
      "grad_norm": 0.3617892563343048,
      "learning_rate": 5.791613096716675e-06,
      "loss": 0.3917,
      "step": 41592
    },
    {
      "epoch": 1.2777009799404049,
      "grad_norm": 0.39953047037124634,
      "learning_rate": 5.791174703608025e-06,
      "loss": 0.4812,
      "step": 41593
    },
    {
      "epoch": 1.277731699075354,
      "grad_norm": 0.39392080903053284,
      "learning_rate": 5.790736320329379e-06,
      "loss": 0.5298,
      "step": 41594
    },
    {
      "epoch": 1.2777624182103031,
      "grad_norm": 0.3815309405326843,
      "learning_rate": 5.790297946881762e-06,
      "loss": 0.5103,
      "step": 41595
    },
    {
      "epoch": 1.2777931373452525,
      "grad_norm": 0.43059995770454407,
      "learning_rate": 5.7898595832662045e-06,
      "loss": 0.4864,
      "step": 41596
    },
    {
      "epoch": 1.2778238564802016,
      "grad_norm": 0.4095604717731476,
      "learning_rate": 5.7894212294837175e-06,
      "loss": 0.4737,
      "step": 41597
    },
    {
      "epoch": 1.2778545756151507,
      "grad_norm": 0.41334524750709534,
      "learning_rate": 5.7889828855353354e-06,
      "loss": 0.4589,
      "step": 41598
    },
    {
      "epoch": 1.2778852947500998,
      "grad_norm": 0.4221980571746826,
      "learning_rate": 5.788544551422071e-06,
      "loss": 0.4567,
      "step": 41599
    },
    {
      "epoch": 1.277916013885049,
      "grad_norm": 0.4041129946708679,
      "learning_rate": 5.7881062271449624e-06,
      "loss": 0.456,
      "step": 41600
    },
    {
      "epoch": 1.277946733019998,
      "grad_norm": 0.4360514283180237,
      "learning_rate": 5.787667912705022e-06,
      "loss": 0.4834,
      "step": 41601
    },
    {
      "epoch": 1.2779774521549472,
      "grad_norm": 0.4219365417957306,
      "learning_rate": 5.787229608103277e-06,
      "loss": 0.5811,
      "step": 41602
    },
    {
      "epoch": 1.2780081712898965,
      "grad_norm": 0.43930062651634216,
      "learning_rate": 5.786791313340756e-06,
      "loss": 0.4238,
      "step": 41603
    },
    {
      "epoch": 1.2780388904248456,
      "grad_norm": 0.4126797616481781,
      "learning_rate": 5.786353028418471e-06,
      "loss": 0.4587,
      "step": 41604
    },
    {
      "epoch": 1.2780696095597948,
      "grad_norm": 0.47743383049964905,
      "learning_rate": 5.785914753337459e-06,
      "loss": 0.4749,
      "step": 41605
    },
    {
      "epoch": 1.2781003286947439,
      "grad_norm": 0.3912684917449951,
      "learning_rate": 5.7854764880987346e-06,
      "loss": 0.4996,
      "step": 41606
    },
    {
      "epoch": 1.2781310478296932,
      "grad_norm": 0.41683730483055115,
      "learning_rate": 5.785038232703328e-06,
      "loss": 0.4695,
      "step": 41607
    },
    {
      "epoch": 1.2781617669646423,
      "grad_norm": 0.4260127544403076,
      "learning_rate": 5.784599987152255e-06,
      "loss": 0.479,
      "step": 41608
    },
    {
      "epoch": 1.2781924860995915,
      "grad_norm": 0.4242261052131653,
      "learning_rate": 5.784161751446542e-06,
      "loss": 0.4314,
      "step": 41609
    },
    {
      "epoch": 1.2782232052345406,
      "grad_norm": 0.4031602442264557,
      "learning_rate": 5.783723525587215e-06,
      "loss": 0.4835,
      "step": 41610
    },
    {
      "epoch": 1.2782539243694897,
      "grad_norm": 0.3904477655887604,
      "learning_rate": 5.7832853095753e-06,
      "loss": 0.4711,
      "step": 41611
    },
    {
      "epoch": 1.2782846435044388,
      "grad_norm": 0.40505340695381165,
      "learning_rate": 5.782847103411812e-06,
      "loss": 0.5229,
      "step": 41612
    },
    {
      "epoch": 1.278315362639388,
      "grad_norm": 0.39927592873573303,
      "learning_rate": 5.78240890709778e-06,
      "loss": 0.4956,
      "step": 41613
    },
    {
      "epoch": 1.2783460817743373,
      "grad_norm": 0.38272374868392944,
      "learning_rate": 5.781970720634226e-06,
      "loss": 0.4953,
      "step": 41614
    },
    {
      "epoch": 1.2783768009092864,
      "grad_norm": 0.40140292048454285,
      "learning_rate": 5.781532544022177e-06,
      "loss": 0.4835,
      "step": 41615
    },
    {
      "epoch": 1.2784075200442355,
      "grad_norm": 0.43480411171913147,
      "learning_rate": 5.78109437726265e-06,
      "loss": 0.465,
      "step": 41616
    },
    {
      "epoch": 1.2784382391791846,
      "grad_norm": 0.42602697014808655,
      "learning_rate": 5.780656220356673e-06,
      "loss": 0.466,
      "step": 41617
    },
    {
      "epoch": 1.278468958314134,
      "grad_norm": 0.3889237344264984,
      "learning_rate": 5.780218073305268e-06,
      "loss": 0.5614,
      "step": 41618
    },
    {
      "epoch": 1.278499677449083,
      "grad_norm": 0.41861674189567566,
      "learning_rate": 5.7797799361094606e-06,
      "loss": 0.452,
      "step": 41619
    },
    {
      "epoch": 1.2785303965840322,
      "grad_norm": 0.4086967706680298,
      "learning_rate": 5.779341808770269e-06,
      "loss": 0.5551,
      "step": 41620
    },
    {
      "epoch": 1.2785611157189813,
      "grad_norm": 0.4093209207057953,
      "learning_rate": 5.7789036912887194e-06,
      "loss": 0.5121,
      "step": 41621
    },
    {
      "epoch": 1.2785918348539305,
      "grad_norm": 0.4131556451320648,
      "learning_rate": 5.778465583665836e-06,
      "loss": 0.4851,
      "step": 41622
    },
    {
      "epoch": 1.2786225539888796,
      "grad_norm": 0.39927196502685547,
      "learning_rate": 5.778027485902639e-06,
      "loss": 0.5265,
      "step": 41623
    },
    {
      "epoch": 1.2786532731238287,
      "grad_norm": 0.3963724970817566,
      "learning_rate": 5.777589398000159e-06,
      "loss": 0.4795,
      "step": 41624
    },
    {
      "epoch": 1.278683992258778,
      "grad_norm": 0.4140807092189789,
      "learning_rate": 5.7771513199594084e-06,
      "loss": 0.5491,
      "step": 41625
    },
    {
      "epoch": 1.2787147113937272,
      "grad_norm": 0.39397484064102173,
      "learning_rate": 5.7767132517814175e-06,
      "loss": 0.4137,
      "step": 41626
    },
    {
      "epoch": 1.2787454305286763,
      "grad_norm": 0.46138834953308105,
      "learning_rate": 5.776275193467207e-06,
      "loss": 0.488,
      "step": 41627
    },
    {
      "epoch": 1.2787761496636254,
      "grad_norm": 0.4184183180332184,
      "learning_rate": 5.775837145017804e-06,
      "loss": 0.4616,
      "step": 41628
    },
    {
      "epoch": 1.2788068687985747,
      "grad_norm": 0.44103094935417175,
      "learning_rate": 5.775399106434225e-06,
      "loss": 0.4561,
      "step": 41629
    },
    {
      "epoch": 1.2788375879335239,
      "grad_norm": 0.4384039044380188,
      "learning_rate": 5.774961077717501e-06,
      "loss": 0.4443,
      "step": 41630
    },
    {
      "epoch": 1.278868307068473,
      "grad_norm": 0.4317285120487213,
      "learning_rate": 5.774523058868643e-06,
      "loss": 0.4246,
      "step": 41631
    },
    {
      "epoch": 1.278899026203422,
      "grad_norm": 0.38489460945129395,
      "learning_rate": 5.774085049888689e-06,
      "loss": 0.5057,
      "step": 41632
    },
    {
      "epoch": 1.2789297453383712,
      "grad_norm": 0.42392003536224365,
      "learning_rate": 5.7736470507786506e-06,
      "loss": 0.5202,
      "step": 41633
    },
    {
      "epoch": 1.2789604644733203,
      "grad_norm": 0.4237971901893616,
      "learning_rate": 5.773209061539557e-06,
      "loss": 0.4912,
      "step": 41634
    },
    {
      "epoch": 1.2789911836082695,
      "grad_norm": 0.37150999903678894,
      "learning_rate": 5.772771082172421e-06,
      "loss": 0.499,
      "step": 41635
    },
    {
      "epoch": 1.2790219027432188,
      "grad_norm": 0.39041760563850403,
      "learning_rate": 5.772333112678283e-06,
      "loss": 0.5397,
      "step": 41636
    },
    {
      "epoch": 1.279052621878168,
      "grad_norm": 0.4976254105567932,
      "learning_rate": 5.7718951530581525e-06,
      "loss": 0.5052,
      "step": 41637
    },
    {
      "epoch": 1.279083341013117,
      "grad_norm": 0.4518369734287262,
      "learning_rate": 5.771457203313055e-06,
      "loss": 0.4218,
      "step": 41638
    },
    {
      "epoch": 1.2791140601480662,
      "grad_norm": 0.422441303730011,
      "learning_rate": 5.7710192634440185e-06,
      "loss": 0.4754,
      "step": 41639
    },
    {
      "epoch": 1.2791447792830155,
      "grad_norm": 0.40507271885871887,
      "learning_rate": 5.770581333452054e-06,
      "loss": 0.4301,
      "step": 41640
    },
    {
      "epoch": 1.2791754984179646,
      "grad_norm": 0.4280170798301697,
      "learning_rate": 5.770143413338201e-06,
      "loss": 0.4862,
      "step": 41641
    },
    {
      "epoch": 1.2792062175529137,
      "grad_norm": 0.40972623229026794,
      "learning_rate": 5.769705503103469e-06,
      "loss": 0.5078,
      "step": 41642
    },
    {
      "epoch": 1.2792369366878629,
      "grad_norm": 0.40909549593925476,
      "learning_rate": 5.769267602748889e-06,
      "loss": 0.4308,
      "step": 41643
    },
    {
      "epoch": 1.279267655822812,
      "grad_norm": 0.4049364924430847,
      "learning_rate": 5.768829712275476e-06,
      "loss": 0.4613,
      "step": 41644
    },
    {
      "epoch": 1.279298374957761,
      "grad_norm": 0.40392279624938965,
      "learning_rate": 5.768391831684257e-06,
      "loss": 0.4495,
      "step": 41645
    },
    {
      "epoch": 1.2793290940927102,
      "grad_norm": 0.43879690766334534,
      "learning_rate": 5.767953960976253e-06,
      "loss": 0.4344,
      "step": 41646
    },
    {
      "epoch": 1.2793598132276596,
      "grad_norm": 0.47040459513664246,
      "learning_rate": 5.7675161001524945e-06,
      "loss": 0.4941,
      "step": 41647
    },
    {
      "epoch": 1.2793905323626087,
      "grad_norm": 0.44144004583358765,
      "learning_rate": 5.767078249213992e-06,
      "loss": 0.4106,
      "step": 41648
    },
    {
      "epoch": 1.2794212514975578,
      "grad_norm": 0.428981214761734,
      "learning_rate": 5.766640408161774e-06,
      "loss": 0.4499,
      "step": 41649
    },
    {
      "epoch": 1.279451970632507,
      "grad_norm": 0.4716280400753021,
      "learning_rate": 5.766202576996865e-06,
      "loss": 0.435,
      "step": 41650
    },
    {
      "epoch": 1.2794826897674563,
      "grad_norm": 0.40380990505218506,
      "learning_rate": 5.765764755720286e-06,
      "loss": 0.4677,
      "step": 41651
    },
    {
      "epoch": 1.2795134089024054,
      "grad_norm": 0.39689338207244873,
      "learning_rate": 5.7653269443330584e-06,
      "loss": 0.5092,
      "step": 41652
    },
    {
      "epoch": 1.2795441280373545,
      "grad_norm": 0.41929891705513,
      "learning_rate": 5.764889142836203e-06,
      "loss": 0.4688,
      "step": 41653
    },
    {
      "epoch": 1.2795748471723036,
      "grad_norm": 0.4013710618019104,
      "learning_rate": 5.764451351230747e-06,
      "loss": 0.4342,
      "step": 41654
    },
    {
      "epoch": 1.2796055663072528,
      "grad_norm": 0.39268743991851807,
      "learning_rate": 5.764013569517714e-06,
      "loss": 0.464,
      "step": 41655
    },
    {
      "epoch": 1.2796362854422019,
      "grad_norm": 0.395522803068161,
      "learning_rate": 5.763575797698117e-06,
      "loss": 0.5074,
      "step": 41656
    },
    {
      "epoch": 1.279667004577151,
      "grad_norm": 0.425194650888443,
      "learning_rate": 5.763138035772987e-06,
      "loss": 0.4932,
      "step": 41657
    },
    {
      "epoch": 1.2796977237121003,
      "grad_norm": 0.5617608428001404,
      "learning_rate": 5.762700283743344e-06,
      "loss": 0.4246,
      "step": 41658
    },
    {
      "epoch": 1.2797284428470495,
      "grad_norm": 0.4085734784603119,
      "learning_rate": 5.7622625416102096e-06,
      "loss": 0.426,
      "step": 41659
    },
    {
      "epoch": 1.2797591619819986,
      "grad_norm": 0.40930843353271484,
      "learning_rate": 5.761824809374611e-06,
      "loss": 0.5074,
      "step": 41660
    },
    {
      "epoch": 1.2797898811169477,
      "grad_norm": 0.41821300983428955,
      "learning_rate": 5.761387087037562e-06,
      "loss": 0.5201,
      "step": 41661
    },
    {
      "epoch": 1.279820600251897,
      "grad_norm": 0.3967931270599365,
      "learning_rate": 5.7609493746000914e-06,
      "loss": 0.4989,
      "step": 41662
    },
    {
      "epoch": 1.2798513193868462,
      "grad_norm": 0.4343757927417755,
      "learning_rate": 5.7605116720632185e-06,
      "loss": 0.5004,
      "step": 41663
    },
    {
      "epoch": 1.2798820385217953,
      "grad_norm": 0.39877328276634216,
      "learning_rate": 5.76007397942797e-06,
      "loss": 0.4539,
      "step": 41664
    },
    {
      "epoch": 1.2799127576567444,
      "grad_norm": 0.5334121584892273,
      "learning_rate": 5.759636296695361e-06,
      "loss": 0.4509,
      "step": 41665
    },
    {
      "epoch": 1.2799434767916935,
      "grad_norm": 0.3886544704437256,
      "learning_rate": 5.759198623866422e-06,
      "loss": 0.4755,
      "step": 41666
    },
    {
      "epoch": 1.2799741959266426,
      "grad_norm": 0.4517165720462799,
      "learning_rate": 5.758760960942162e-06,
      "loss": 0.4828,
      "step": 41667
    },
    {
      "epoch": 1.2800049150615918,
      "grad_norm": 0.44791078567504883,
      "learning_rate": 5.758323307923621e-06,
      "loss": 0.4914,
      "step": 41668
    },
    {
      "epoch": 1.280035634196541,
      "grad_norm": 0.42255455255508423,
      "learning_rate": 5.757885664811808e-06,
      "loss": 0.4902,
      "step": 41669
    },
    {
      "epoch": 1.2800663533314902,
      "grad_norm": 0.4168620705604553,
      "learning_rate": 5.757448031607754e-06,
      "loss": 0.4693,
      "step": 41670
    },
    {
      "epoch": 1.2800970724664393,
      "grad_norm": 0.42162561416625977,
      "learning_rate": 5.757010408312471e-06,
      "loss": 0.4816,
      "step": 41671
    },
    {
      "epoch": 1.2801277916013885,
      "grad_norm": 0.4057439863681793,
      "learning_rate": 5.756572794926988e-06,
      "loss": 0.4873,
      "step": 41672
    },
    {
      "epoch": 1.2801585107363378,
      "grad_norm": 0.39125874638557434,
      "learning_rate": 5.756135191452324e-06,
      "loss": 0.5483,
      "step": 41673
    },
    {
      "epoch": 1.280189229871287,
      "grad_norm": 0.3923339545726776,
      "learning_rate": 5.755697597889507e-06,
      "loss": 0.3911,
      "step": 41674
    },
    {
      "epoch": 1.280219949006236,
      "grad_norm": 0.4419228136539459,
      "learning_rate": 5.755260014239552e-06,
      "loss": 0.4724,
      "step": 41675
    },
    {
      "epoch": 1.2802506681411852,
      "grad_norm": 0.4219557046890259,
      "learning_rate": 5.754822440503478e-06,
      "loss": 0.4779,
      "step": 41676
    },
    {
      "epoch": 1.2802813872761343,
      "grad_norm": 0.4126400947570801,
      "learning_rate": 5.7543848766823216e-06,
      "loss": 0.4863,
      "step": 41677
    },
    {
      "epoch": 1.2803121064110834,
      "grad_norm": 0.4220569431781769,
      "learning_rate": 5.753947322777091e-06,
      "loss": 0.4884,
      "step": 41678
    },
    {
      "epoch": 1.2803428255460325,
      "grad_norm": 0.43845343589782715,
      "learning_rate": 5.753509778788819e-06,
      "loss": 0.5247,
      "step": 41679
    },
    {
      "epoch": 1.2803735446809819,
      "grad_norm": 0.4130748510360718,
      "learning_rate": 5.753072244718516e-06,
      "loss": 0.4806,
      "step": 41680
    },
    {
      "epoch": 1.280404263815931,
      "grad_norm": 0.4367715120315552,
      "learning_rate": 5.752634720567209e-06,
      "loss": 0.5568,
      "step": 41681
    },
    {
      "epoch": 1.28043498295088,
      "grad_norm": 0.4030859172344208,
      "learning_rate": 5.752197206335921e-06,
      "loss": 0.468,
      "step": 41682
    },
    {
      "epoch": 1.2804657020858292,
      "grad_norm": 0.3779905140399933,
      "learning_rate": 5.751759702025676e-06,
      "loss": 0.4716,
      "step": 41683
    },
    {
      "epoch": 1.2804964212207786,
      "grad_norm": 0.39707571268081665,
      "learning_rate": 5.751322207637491e-06,
      "loss": 0.4674,
      "step": 41684
    },
    {
      "epoch": 1.2805271403557277,
      "grad_norm": 0.3995458781719208,
      "learning_rate": 5.750884723172387e-06,
      "loss": 0.485,
      "step": 41685
    },
    {
      "epoch": 1.2805578594906768,
      "grad_norm": 0.37755656242370605,
      "learning_rate": 5.75044724863139e-06,
      "loss": 0.4672,
      "step": 41686
    },
    {
      "epoch": 1.280588578625626,
      "grad_norm": 0.42085009813308716,
      "learning_rate": 5.750009784015524e-06,
      "loss": 0.3946,
      "step": 41687
    },
    {
      "epoch": 1.280619297760575,
      "grad_norm": 0.4516458213329315,
      "learning_rate": 5.7495723293258035e-06,
      "loss": 0.4136,
      "step": 41688
    },
    {
      "epoch": 1.2806500168955242,
      "grad_norm": 0.4476573169231415,
      "learning_rate": 5.749134884563254e-06,
      "loss": 0.4727,
      "step": 41689
    },
    {
      "epoch": 1.2806807360304733,
      "grad_norm": 0.45651546120643616,
      "learning_rate": 5.748697449728895e-06,
      "loss": 0.4301,
      "step": 41690
    },
    {
      "epoch": 1.2807114551654226,
      "grad_norm": 0.3876606523990631,
      "learning_rate": 5.748260024823755e-06,
      "loss": 0.4895,
      "step": 41691
    },
    {
      "epoch": 1.2807421743003717,
      "grad_norm": 0.4775109589099884,
      "learning_rate": 5.747822609848848e-06,
      "loss": 0.4607,
      "step": 41692
    },
    {
      "epoch": 1.2807728934353209,
      "grad_norm": 0.41069138050079346,
      "learning_rate": 5.747385204805196e-06,
      "loss": 0.5371,
      "step": 41693
    },
    {
      "epoch": 1.28080361257027,
      "grad_norm": 0.4389697015285492,
      "learning_rate": 5.746947809693823e-06,
      "loss": 0.5151,
      "step": 41694
    },
    {
      "epoch": 1.280834331705219,
      "grad_norm": 0.41179120540618896,
      "learning_rate": 5.746510424515752e-06,
      "loss": 0.4919,
      "step": 41695
    },
    {
      "epoch": 1.2808650508401684,
      "grad_norm": 0.44254982471466064,
      "learning_rate": 5.7460730492720076e-06,
      "loss": 0.5399,
      "step": 41696
    },
    {
      "epoch": 1.2808957699751176,
      "grad_norm": 0.44072240591049194,
      "learning_rate": 5.7456356839636e-06,
      "loss": 0.4553,
      "step": 41697
    },
    {
      "epoch": 1.2809264891100667,
      "grad_norm": 0.3839569389820099,
      "learning_rate": 5.745198328591559e-06,
      "loss": 0.4933,
      "step": 41698
    },
    {
      "epoch": 1.2809572082450158,
      "grad_norm": 0.40294939279556274,
      "learning_rate": 5.744760983156905e-06,
      "loss": 0.4476,
      "step": 41699
    },
    {
      "epoch": 1.280987927379965,
      "grad_norm": 0.3667587339878082,
      "learning_rate": 5.744323647660661e-06,
      "loss": 0.3788,
      "step": 41700
    },
    {
      "epoch": 1.281018646514914,
      "grad_norm": 0.40952181816101074,
      "learning_rate": 5.743886322103844e-06,
      "loss": 0.4201,
      "step": 41701
    },
    {
      "epoch": 1.2810493656498634,
      "grad_norm": 0.4364190399646759,
      "learning_rate": 5.74344900648748e-06,
      "loss": 0.3902,
      "step": 41702
    },
    {
      "epoch": 1.2810800847848125,
      "grad_norm": 0.39213815331459045,
      "learning_rate": 5.743011700812582e-06,
      "loss": 0.4716,
      "step": 41703
    },
    {
      "epoch": 1.2811108039197616,
      "grad_norm": 0.4184989333152771,
      "learning_rate": 5.742574405080185e-06,
      "loss": 0.4831,
      "step": 41704
    },
    {
      "epoch": 1.2811415230547107,
      "grad_norm": 0.3694968819618225,
      "learning_rate": 5.742137119291299e-06,
      "loss": 0.4446,
      "step": 41705
    },
    {
      "epoch": 1.2811722421896599,
      "grad_norm": 0.41850656270980835,
      "learning_rate": 5.741699843446953e-06,
      "loss": 0.4392,
      "step": 41706
    },
    {
      "epoch": 1.2812029613246092,
      "grad_norm": 0.4288397431373596,
      "learning_rate": 5.741262577548159e-06,
      "loss": 0.5356,
      "step": 41707
    },
    {
      "epoch": 1.2812336804595583,
      "grad_norm": 0.3660949766635895,
      "learning_rate": 5.740825321595945e-06,
      "loss": 0.4385,
      "step": 41708
    },
    {
      "epoch": 1.2812643995945074,
      "grad_norm": 0.39218026399612427,
      "learning_rate": 5.740388075591331e-06,
      "loss": 0.4707,
      "step": 41709
    },
    {
      "epoch": 1.2812951187294566,
      "grad_norm": 0.3639029562473297,
      "learning_rate": 5.739950839535342e-06,
      "loss": 0.5005,
      "step": 41710
    },
    {
      "epoch": 1.2813258378644057,
      "grad_norm": 0.39451244473457336,
      "learning_rate": 5.739513613428991e-06,
      "loss": 0.4508,
      "step": 41711
    },
    {
      "epoch": 1.2813565569993548,
      "grad_norm": 0.42796221375465393,
      "learning_rate": 5.739076397273304e-06,
      "loss": 0.4433,
      "step": 41712
    },
    {
      "epoch": 1.281387276134304,
      "grad_norm": 0.4101181626319885,
      "learning_rate": 5.738639191069302e-06,
      "loss": 0.4682,
      "step": 41713
    },
    {
      "epoch": 1.2814179952692533,
      "grad_norm": 0.41973817348480225,
      "learning_rate": 5.738201994818005e-06,
      "loss": 0.4559,
      "step": 41714
    },
    {
      "epoch": 1.2814487144042024,
      "grad_norm": 0.4572262167930603,
      "learning_rate": 5.737764808520439e-06,
      "loss": 0.4759,
      "step": 41715
    },
    {
      "epoch": 1.2814794335391515,
      "grad_norm": 0.37533700466156006,
      "learning_rate": 5.7373276321776164e-06,
      "loss": 0.447,
      "step": 41716
    },
    {
      "epoch": 1.2815101526741006,
      "grad_norm": 0.4125862121582031,
      "learning_rate": 5.7368904657905635e-06,
      "loss": 0.5035,
      "step": 41717
    },
    {
      "epoch": 1.28154087180905,
      "grad_norm": 0.42981961369514465,
      "learning_rate": 5.736453309360301e-06,
      "loss": 0.4741,
      "step": 41718
    },
    {
      "epoch": 1.281571590943999,
      "grad_norm": 0.4295072555541992,
      "learning_rate": 5.736016162887852e-06,
      "loss": 0.4137,
      "step": 41719
    },
    {
      "epoch": 1.2816023100789482,
      "grad_norm": 0.3782655596733093,
      "learning_rate": 5.7355790263742316e-06,
      "loss": 0.4245,
      "step": 41720
    },
    {
      "epoch": 1.2816330292138973,
      "grad_norm": 0.4095322787761688,
      "learning_rate": 5.735141899820466e-06,
      "loss": 0.4753,
      "step": 41721
    },
    {
      "epoch": 1.2816637483488464,
      "grad_norm": 0.41630420088768005,
      "learning_rate": 5.734704783227573e-06,
      "loss": 0.4325,
      "step": 41722
    },
    {
      "epoch": 1.2816944674837956,
      "grad_norm": 0.4136822521686554,
      "learning_rate": 5.734267676596578e-06,
      "loss": 0.4933,
      "step": 41723
    },
    {
      "epoch": 1.2817251866187447,
      "grad_norm": 0.4096173048019409,
      "learning_rate": 5.7338305799284965e-06,
      "loss": 0.4275,
      "step": 41724
    },
    {
      "epoch": 1.281755905753694,
      "grad_norm": 0.4238691031932831,
      "learning_rate": 5.73339349322435e-06,
      "loss": 0.4771,
      "step": 41725
    },
    {
      "epoch": 1.2817866248886431,
      "grad_norm": 0.40261828899383545,
      "learning_rate": 5.732956416485162e-06,
      "loss": 0.4306,
      "step": 41726
    },
    {
      "epoch": 1.2818173440235923,
      "grad_norm": 0.8413150310516357,
      "learning_rate": 5.732519349711957e-06,
      "loss": 0.4597,
      "step": 41727
    },
    {
      "epoch": 1.2818480631585414,
      "grad_norm": 0.44584420323371887,
      "learning_rate": 5.732082292905745e-06,
      "loss": 0.4813,
      "step": 41728
    },
    {
      "epoch": 1.2818787822934907,
      "grad_norm": 0.4065631926059723,
      "learning_rate": 5.731645246067555e-06,
      "loss": 0.4887,
      "step": 41729
    },
    {
      "epoch": 1.2819095014284398,
      "grad_norm": 0.4805932939052582,
      "learning_rate": 5.731208209198405e-06,
      "loss": 0.5252,
      "step": 41730
    },
    {
      "epoch": 1.281940220563389,
      "grad_norm": 0.4311477243900299,
      "learning_rate": 5.730771182299315e-06,
      "loss": 0.4193,
      "step": 41731
    },
    {
      "epoch": 1.281970939698338,
      "grad_norm": 0.40092599391937256,
      "learning_rate": 5.730334165371313e-06,
      "loss": 0.4294,
      "step": 41732
    },
    {
      "epoch": 1.2820016588332872,
      "grad_norm": 0.45553359389305115,
      "learning_rate": 5.729897158415409e-06,
      "loss": 0.4832,
      "step": 41733
    },
    {
      "epoch": 1.2820323779682363,
      "grad_norm": 0.41185927391052246,
      "learning_rate": 5.729460161432632e-06,
      "loss": 0.5502,
      "step": 41734
    },
    {
      "epoch": 1.2820630971031854,
      "grad_norm": 0.40676137804985046,
      "learning_rate": 5.729023174423991e-06,
      "loss": 0.4676,
      "step": 41735
    },
    {
      "epoch": 1.2820938162381348,
      "grad_norm": 0.39033588767051697,
      "learning_rate": 5.728586197390523e-06,
      "loss": 0.5619,
      "step": 41736
    },
    {
      "epoch": 1.282124535373084,
      "grad_norm": 0.42581555247306824,
      "learning_rate": 5.728149230333237e-06,
      "loss": 0.506,
      "step": 41737
    },
    {
      "epoch": 1.282155254508033,
      "grad_norm": 0.4060814678668976,
      "learning_rate": 5.727712273253159e-06,
      "loss": 0.5673,
      "step": 41738
    },
    {
      "epoch": 1.2821859736429821,
      "grad_norm": 0.3899654150009155,
      "learning_rate": 5.7272753261513e-06,
      "loss": 0.4572,
      "step": 41739
    },
    {
      "epoch": 1.2822166927779315,
      "grad_norm": 0.39807242155075073,
      "learning_rate": 5.726838389028697e-06,
      "loss": 0.4365,
      "step": 41740
    },
    {
      "epoch": 1.2822474119128806,
      "grad_norm": 0.40634506940841675,
      "learning_rate": 5.726401461886357e-06,
      "loss": 0.4373,
      "step": 41741
    },
    {
      "epoch": 1.2822781310478297,
      "grad_norm": 0.39824557304382324,
      "learning_rate": 5.725964544725308e-06,
      "loss": 0.4916,
      "step": 41742
    },
    {
      "epoch": 1.2823088501827788,
      "grad_norm": 0.4405320882797241,
      "learning_rate": 5.725527637546564e-06,
      "loss": 0.4572,
      "step": 41743
    },
    {
      "epoch": 1.282339569317728,
      "grad_norm": 0.4045695662498474,
      "learning_rate": 5.725090740351149e-06,
      "loss": 0.4484,
      "step": 41744
    },
    {
      "epoch": 1.282370288452677,
      "grad_norm": 0.40611374378204346,
      "learning_rate": 5.724653853140083e-06,
      "loss": 0.5232,
      "step": 41745
    },
    {
      "epoch": 1.2824010075876262,
      "grad_norm": 0.44404536485671997,
      "learning_rate": 5.7242169759143895e-06,
      "loss": 0.4742,
      "step": 41746
    },
    {
      "epoch": 1.2824317267225755,
      "grad_norm": 0.43788084387779236,
      "learning_rate": 5.723780108675083e-06,
      "loss": 0.4631,
      "step": 41747
    },
    {
      "epoch": 1.2824624458575247,
      "grad_norm": 0.39053618907928467,
      "learning_rate": 5.7233432514231855e-06,
      "loss": 0.4178,
      "step": 41748
    },
    {
      "epoch": 1.2824931649924738,
      "grad_norm": 0.37303557991981506,
      "learning_rate": 5.72290640415972e-06,
      "loss": 0.4902,
      "step": 41749
    },
    {
      "epoch": 1.282523884127423,
      "grad_norm": 0.42045578360557556,
      "learning_rate": 5.722469566885704e-06,
      "loss": 0.4186,
      "step": 41750
    },
    {
      "epoch": 1.2825546032623723,
      "grad_norm": 0.4282662272453308,
      "learning_rate": 5.722032739602163e-06,
      "loss": 0.4743,
      "step": 41751
    },
    {
      "epoch": 1.2825853223973214,
      "grad_norm": 0.4111715257167816,
      "learning_rate": 5.7215959223101104e-06,
      "loss": 0.5163,
      "step": 41752
    },
    {
      "epoch": 1.2826160415322705,
      "grad_norm": 0.40127232670783997,
      "learning_rate": 5.721159115010568e-06,
      "loss": 0.5161,
      "step": 41753
    },
    {
      "epoch": 1.2826467606672196,
      "grad_norm": 0.3839024007320404,
      "learning_rate": 5.720722317704559e-06,
      "loss": 0.4122,
      "step": 41754
    },
    {
      "epoch": 1.2826774798021687,
      "grad_norm": 0.43568187952041626,
      "learning_rate": 5.720285530393106e-06,
      "loss": 0.5379,
      "step": 41755
    },
    {
      "epoch": 1.2827081989371178,
      "grad_norm": 0.390248566865921,
      "learning_rate": 5.71984875307722e-06,
      "loss": 0.4698,
      "step": 41756
    },
    {
      "epoch": 1.282738918072067,
      "grad_norm": 0.41866615414619446,
      "learning_rate": 5.7194119857579255e-06,
      "loss": 0.3656,
      "step": 41757
    },
    {
      "epoch": 1.2827696372070163,
      "grad_norm": 0.3843199908733368,
      "learning_rate": 5.718975228436244e-06,
      "loss": 0.4545,
      "step": 41758
    },
    {
      "epoch": 1.2828003563419654,
      "grad_norm": 0.40520650148391724,
      "learning_rate": 5.718538481113198e-06,
      "loss": 0.4414,
      "step": 41759
    },
    {
      "epoch": 1.2828310754769146,
      "grad_norm": 0.40821507573127747,
      "learning_rate": 5.718101743789802e-06,
      "loss": 0.4902,
      "step": 41760
    },
    {
      "epoch": 1.2828617946118637,
      "grad_norm": 0.4317282438278198,
      "learning_rate": 5.717665016467077e-06,
      "loss": 0.4361,
      "step": 41761
    },
    {
      "epoch": 1.282892513746813,
      "grad_norm": 0.40391620993614197,
      "learning_rate": 5.717228299146046e-06,
      "loss": 0.46,
      "step": 41762
    },
    {
      "epoch": 1.2829232328817621,
      "grad_norm": 0.42627960443496704,
      "learning_rate": 5.7167915918277305e-06,
      "loss": 0.4134,
      "step": 41763
    },
    {
      "epoch": 1.2829539520167113,
      "grad_norm": 0.38439881801605225,
      "learning_rate": 5.716354894513143e-06,
      "loss": 0.4003,
      "step": 41764
    },
    {
      "epoch": 1.2829846711516604,
      "grad_norm": 0.41346797347068787,
      "learning_rate": 5.715918207203313e-06,
      "loss": 0.4798,
      "step": 41765
    },
    {
      "epoch": 1.2830153902866095,
      "grad_norm": 0.4019249975681305,
      "learning_rate": 5.715481529899246e-06,
      "loss": 0.436,
      "step": 41766
    },
    {
      "epoch": 1.2830461094215586,
      "grad_norm": 0.4042009115219116,
      "learning_rate": 5.715044862601975e-06,
      "loss": 0.4899,
      "step": 41767
    },
    {
      "epoch": 1.2830768285565077,
      "grad_norm": 0.4115215539932251,
      "learning_rate": 5.714608205312522e-06,
      "loss": 0.4787,
      "step": 41768
    },
    {
      "epoch": 1.283107547691457,
      "grad_norm": 0.4137808084487915,
      "learning_rate": 5.714171558031895e-06,
      "loss": 0.4341,
      "step": 41769
    },
    {
      "epoch": 1.2831382668264062,
      "grad_norm": 0.4042606055736542,
      "learning_rate": 5.713734920761124e-06,
      "loss": 0.5394,
      "step": 41770
    },
    {
      "epoch": 1.2831689859613553,
      "grad_norm": 0.4171295762062073,
      "learning_rate": 5.713298293501216e-06,
      "loss": 0.5534,
      "step": 41771
    },
    {
      "epoch": 1.2831997050963044,
      "grad_norm": 0.430997371673584,
      "learning_rate": 5.712861676253207e-06,
      "loss": 0.5022,
      "step": 41772
    },
    {
      "epoch": 1.2832304242312538,
      "grad_norm": 0.3998313546180725,
      "learning_rate": 5.712425069018106e-06,
      "loss": 0.5451,
      "step": 41773
    },
    {
      "epoch": 1.283261143366203,
      "grad_norm": 0.3942564129829407,
      "learning_rate": 5.7119884717969385e-06,
      "loss": 0.4567,
      "step": 41774
    },
    {
      "epoch": 1.283291862501152,
      "grad_norm": 0.4348016679286957,
      "learning_rate": 5.711551884590719e-06,
      "loss": 0.4477,
      "step": 41775
    },
    {
      "epoch": 1.2833225816361011,
      "grad_norm": 0.48604780435562134,
      "learning_rate": 5.711115307400469e-06,
      "loss": 0.4537,
      "step": 41776
    },
    {
      "epoch": 1.2833533007710503,
      "grad_norm": 0.42625847458839417,
      "learning_rate": 5.710678740227209e-06,
      "loss": 0.5665,
      "step": 41777
    },
    {
      "epoch": 1.2833840199059994,
      "grad_norm": 0.41043663024902344,
      "learning_rate": 5.710242183071962e-06,
      "loss": 0.5252,
      "step": 41778
    },
    {
      "epoch": 1.2834147390409485,
      "grad_norm": 0.3987537920475006,
      "learning_rate": 5.709805635935739e-06,
      "loss": 0.5002,
      "step": 41779
    },
    {
      "epoch": 1.2834454581758978,
      "grad_norm": 0.40350741147994995,
      "learning_rate": 5.709369098819566e-06,
      "loss": 0.4697,
      "step": 41780
    },
    {
      "epoch": 1.283476177310847,
      "grad_norm": 0.38055992126464844,
      "learning_rate": 5.708932571724459e-06,
      "loss": 0.4613,
      "step": 41781
    },
    {
      "epoch": 1.283506896445796,
      "grad_norm": 0.42121976613998413,
      "learning_rate": 5.708496054651447e-06,
      "loss": 0.4456,
      "step": 41782
    },
    {
      "epoch": 1.2835376155807452,
      "grad_norm": 0.3538203239440918,
      "learning_rate": 5.708059547601535e-06,
      "loss": 0.4176,
      "step": 41783
    },
    {
      "epoch": 1.2835683347156945,
      "grad_norm": 0.4255378544330597,
      "learning_rate": 5.707623050575753e-06,
      "loss": 0.4154,
      "step": 41784
    },
    {
      "epoch": 1.2835990538506437,
      "grad_norm": 0.4422842860221863,
      "learning_rate": 5.707186563575113e-06,
      "loss": 0.5006,
      "step": 41785
    },
    {
      "epoch": 1.2836297729855928,
      "grad_norm": 0.7603399753570557,
      "learning_rate": 5.706750086600641e-06,
      "loss": 0.4244,
      "step": 41786
    },
    {
      "epoch": 1.283660492120542,
      "grad_norm": 0.40068984031677246,
      "learning_rate": 5.706313619653358e-06,
      "loss": 0.4647,
      "step": 41787
    },
    {
      "epoch": 1.283691211255491,
      "grad_norm": 0.5011443495750427,
      "learning_rate": 5.705877162734276e-06,
      "loss": 0.3837,
      "step": 41788
    },
    {
      "epoch": 1.2837219303904401,
      "grad_norm": 0.41363534331321716,
      "learning_rate": 5.705440715844417e-06,
      "loss": 0.5356,
      "step": 41789
    },
    {
      "epoch": 1.2837526495253893,
      "grad_norm": 0.4342983365058899,
      "learning_rate": 5.7050042789848e-06,
      "loss": 0.5312,
      "step": 41790
    },
    {
      "epoch": 1.2837833686603386,
      "grad_norm": 0.42373713850975037,
      "learning_rate": 5.704567852156451e-06,
      "loss": 0.4993,
      "step": 41791
    },
    {
      "epoch": 1.2838140877952877,
      "grad_norm": 0.4309961497783661,
      "learning_rate": 5.7041314353603794e-06,
      "loss": 0.5055,
      "step": 41792
    },
    {
      "epoch": 1.2838448069302368,
      "grad_norm": 0.4218498170375824,
      "learning_rate": 5.703695028597609e-06,
      "loss": 0.4756,
      "step": 41793
    },
    {
      "epoch": 1.283875526065186,
      "grad_norm": 0.40424540638923645,
      "learning_rate": 5.703258631869159e-06,
      "loss": 0.4888,
      "step": 41794
    },
    {
      "epoch": 1.2839062452001353,
      "grad_norm": 0.4072534441947937,
      "learning_rate": 5.7028222451760515e-06,
      "loss": 0.474,
      "step": 41795
    },
    {
      "epoch": 1.2839369643350844,
      "grad_norm": 0.35001200437545776,
      "learning_rate": 5.7023858685193005e-06,
      "loss": 0.4981,
      "step": 41796
    },
    {
      "epoch": 1.2839676834700335,
      "grad_norm": 0.6610698699951172,
      "learning_rate": 5.7019495018999305e-06,
      "loss": 0.5578,
      "step": 41797
    },
    {
      "epoch": 1.2839984026049827,
      "grad_norm": 0.37834790349006653,
      "learning_rate": 5.701513145318949e-06,
      "loss": 0.446,
      "step": 41798
    },
    {
      "epoch": 1.2840291217399318,
      "grad_norm": 0.39553403854370117,
      "learning_rate": 5.701076798777392e-06,
      "loss": 0.4347,
      "step": 41799
    },
    {
      "epoch": 1.284059840874881,
      "grad_norm": 0.41835710406303406,
      "learning_rate": 5.700640462276267e-06,
      "loss": 0.4892,
      "step": 41800
    },
    {
      "epoch": 1.28409056000983,
      "grad_norm": 0.4760330021381378,
      "learning_rate": 5.7002041358166e-06,
      "loss": 0.4927,
      "step": 41801
    },
    {
      "epoch": 1.2841212791447794,
      "grad_norm": 0.43014565110206604,
      "learning_rate": 5.699767819399399e-06,
      "loss": 0.4266,
      "step": 41802
    },
    {
      "epoch": 1.2841519982797285,
      "grad_norm": 0.43589842319488525,
      "learning_rate": 5.699331513025694e-06,
      "loss": 0.4452,
      "step": 41803
    },
    {
      "epoch": 1.2841827174146776,
      "grad_norm": 0.46147966384887695,
      "learning_rate": 5.698895216696505e-06,
      "loss": 0.4749,
      "step": 41804
    },
    {
      "epoch": 1.2842134365496267,
      "grad_norm": 0.4154234528541565,
      "learning_rate": 5.698458930412843e-06,
      "loss": 0.4897,
      "step": 41805
    },
    {
      "epoch": 1.284244155684576,
      "grad_norm": 0.41022789478302,
      "learning_rate": 5.6980226541757345e-06,
      "loss": 0.454,
      "step": 41806
    },
    {
      "epoch": 1.2842748748195252,
      "grad_norm": 0.4503650963306427,
      "learning_rate": 5.6975863879861845e-06,
      "loss": 0.4721,
      "step": 41807
    },
    {
      "epoch": 1.2843055939544743,
      "grad_norm": 0.4125908315181732,
      "learning_rate": 5.697150131845233e-06,
      "loss": 0.5425,
      "step": 41808
    },
    {
      "epoch": 1.2843363130894234,
      "grad_norm": 0.4300370514392853,
      "learning_rate": 5.696713885753882e-06,
      "loss": 0.5734,
      "step": 41809
    },
    {
      "epoch": 1.2843670322243725,
      "grad_norm": 0.42491614818573,
      "learning_rate": 5.69627764971316e-06,
      "loss": 0.5194,
      "step": 41810
    },
    {
      "epoch": 1.2843977513593217,
      "grad_norm": 0.3988032639026642,
      "learning_rate": 5.69584142372408e-06,
      "loss": 0.5173,
      "step": 41811
    },
    {
      "epoch": 1.2844284704942708,
      "grad_norm": 0.37600699067115784,
      "learning_rate": 5.695405207787661e-06,
      "loss": 0.52,
      "step": 41812
    },
    {
      "epoch": 1.2844591896292201,
      "grad_norm": 0.41363346576690674,
      "learning_rate": 5.6949690019049245e-06,
      "loss": 0.4774,
      "step": 41813
    },
    {
      "epoch": 1.2844899087641692,
      "grad_norm": 0.4036655128002167,
      "learning_rate": 5.694532806076894e-06,
      "loss": 0.5129,
      "step": 41814
    },
    {
      "epoch": 1.2845206278991184,
      "grad_norm": 0.38079360127449036,
      "learning_rate": 5.694096620304576e-06,
      "loss": 0.4047,
      "step": 41815
    },
    {
      "epoch": 1.2845513470340675,
      "grad_norm": 0.5027438998222351,
      "learning_rate": 5.693660444588997e-06,
      "loss": 0.4706,
      "step": 41816
    },
    {
      "epoch": 1.2845820661690166,
      "grad_norm": 0.5669264197349548,
      "learning_rate": 5.693224278931176e-06,
      "loss": 0.4124,
      "step": 41817
    },
    {
      "epoch": 1.284612785303966,
      "grad_norm": 0.47534093260765076,
      "learning_rate": 5.692788123332134e-06,
      "loss": 0.4983,
      "step": 41818
    },
    {
      "epoch": 1.284643504438915,
      "grad_norm": 0.40726232528686523,
      "learning_rate": 5.692351977792882e-06,
      "loss": 0.4628,
      "step": 41819
    },
    {
      "epoch": 1.2846742235738642,
      "grad_norm": 0.39971083402633667,
      "learning_rate": 5.691915842314442e-06,
      "loss": 0.5098,
      "step": 41820
    },
    {
      "epoch": 1.2847049427088133,
      "grad_norm": 0.4589875638484955,
      "learning_rate": 5.691479716897834e-06,
      "loss": 0.4721,
      "step": 41821
    },
    {
      "epoch": 1.2847356618437624,
      "grad_norm": 0.41079649329185486,
      "learning_rate": 5.6910436015440775e-06,
      "loss": 0.4535,
      "step": 41822
    },
    {
      "epoch": 1.2847663809787115,
      "grad_norm": 0.42120784521102905,
      "learning_rate": 5.6906074962541915e-06,
      "loss": 0.4598,
      "step": 41823
    },
    {
      "epoch": 1.2847971001136607,
      "grad_norm": 0.4293641448020935,
      "learning_rate": 5.69017140102919e-06,
      "loss": 0.4792,
      "step": 41824
    },
    {
      "epoch": 1.28482781924861,
      "grad_norm": 0.4280608296394348,
      "learning_rate": 5.689735315870093e-06,
      "loss": 0.4228,
      "step": 41825
    },
    {
      "epoch": 1.2848585383835591,
      "grad_norm": 0.49678200483322144,
      "learning_rate": 5.6892992407779215e-06,
      "loss": 0.4615,
      "step": 41826
    },
    {
      "epoch": 1.2848892575185082,
      "grad_norm": 0.4475420117378235,
      "learning_rate": 5.688863175753695e-06,
      "loss": 0.4415,
      "step": 41827
    },
    {
      "epoch": 1.2849199766534574,
      "grad_norm": 0.3901088535785675,
      "learning_rate": 5.6884271207984265e-06,
      "loss": 0.4462,
      "step": 41828
    },
    {
      "epoch": 1.2849506957884067,
      "grad_norm": 0.4585703909397125,
      "learning_rate": 5.6879910759131374e-06,
      "loss": 0.4541,
      "step": 41829
    },
    {
      "epoch": 1.2849814149233558,
      "grad_norm": 0.41253769397735596,
      "learning_rate": 5.6875550410988465e-06,
      "loss": 0.5231,
      "step": 41830
    },
    {
      "epoch": 1.285012134058305,
      "grad_norm": 0.8372612595558167,
      "learning_rate": 5.687119016356577e-06,
      "loss": 0.3717,
      "step": 41831
    },
    {
      "epoch": 1.285042853193254,
      "grad_norm": 0.39807212352752686,
      "learning_rate": 5.6866830016873365e-06,
      "loss": 0.4708,
      "step": 41832
    },
    {
      "epoch": 1.2850735723282032,
      "grad_norm": 0.43756982684135437,
      "learning_rate": 5.686246997092154e-06,
      "loss": 0.4729,
      "step": 41833
    },
    {
      "epoch": 1.2851042914631523,
      "grad_norm": 0.4308415949344635,
      "learning_rate": 5.685811002572035e-06,
      "loss": 0.424,
      "step": 41834
    },
    {
      "epoch": 1.2851350105981014,
      "grad_norm": 0.41798025369644165,
      "learning_rate": 5.685375018128014e-06,
      "loss": 0.4207,
      "step": 41835
    },
    {
      "epoch": 1.2851657297330508,
      "grad_norm": 0.414188414812088,
      "learning_rate": 5.684939043761096e-06,
      "loss": 0.4677,
      "step": 41836
    },
    {
      "epoch": 1.2851964488679999,
      "grad_norm": 0.4518424868583679,
      "learning_rate": 5.684503079472309e-06,
      "loss": 0.4646,
      "step": 41837
    },
    {
      "epoch": 1.285227168002949,
      "grad_norm": 0.4094107151031494,
      "learning_rate": 5.684067125262662e-06,
      "loss": 0.4785,
      "step": 41838
    },
    {
      "epoch": 1.2852578871378981,
      "grad_norm": 0.3801065981388092,
      "learning_rate": 5.6836311811331735e-06,
      "loss": 0.4818,
      "step": 41839
    },
    {
      "epoch": 1.2852886062728475,
      "grad_norm": 0.4318140149116516,
      "learning_rate": 5.683195247084874e-06,
      "loss": 0.494,
      "step": 41840
    },
    {
      "epoch": 1.2853193254077966,
      "grad_norm": 0.40175631642341614,
      "learning_rate": 5.682759323118769e-06,
      "loss": 0.4919,
      "step": 41841
    },
    {
      "epoch": 1.2853500445427457,
      "grad_norm": 0.4209100604057312,
      "learning_rate": 5.682323409235887e-06,
      "loss": 0.3856,
      "step": 41842
    },
    {
      "epoch": 1.2853807636776948,
      "grad_norm": 0.43228116631507874,
      "learning_rate": 5.681887505437231e-06,
      "loss": 0.4301,
      "step": 41843
    },
    {
      "epoch": 1.285411482812644,
      "grad_norm": 0.4154042899608612,
      "learning_rate": 5.681451611723836e-06,
      "loss": 0.443,
      "step": 41844
    },
    {
      "epoch": 1.285442201947593,
      "grad_norm": 0.39558032155036926,
      "learning_rate": 5.681015728096708e-06,
      "loss": 0.5184,
      "step": 41845
    },
    {
      "epoch": 1.2854729210825422,
      "grad_norm": 0.42713284492492676,
      "learning_rate": 5.6805798545568745e-06,
      "loss": 0.5328,
      "step": 41846
    },
    {
      "epoch": 1.2855036402174915,
      "grad_norm": 0.42180922627449036,
      "learning_rate": 5.680143991105345e-06,
      "loss": 0.5093,
      "step": 41847
    },
    {
      "epoch": 1.2855343593524406,
      "grad_norm": 0.4555004835128784,
      "learning_rate": 5.679708137743139e-06,
      "loss": 0.4319,
      "step": 41848
    },
    {
      "epoch": 1.2855650784873898,
      "grad_norm": 0.4167271554470062,
      "learning_rate": 5.679272294471276e-06,
      "loss": 0.4055,
      "step": 41849
    },
    {
      "epoch": 1.2855957976223389,
      "grad_norm": 0.40662896633148193,
      "learning_rate": 5.678836461290779e-06,
      "loss": 0.4264,
      "step": 41850
    },
    {
      "epoch": 1.2856265167572882,
      "grad_norm": 0.43240082263946533,
      "learning_rate": 5.678400638202659e-06,
      "loss": 0.5284,
      "step": 41851
    },
    {
      "epoch": 1.2856572358922373,
      "grad_norm": 0.4196127951145172,
      "learning_rate": 5.677964825207936e-06,
      "loss": 0.5689,
      "step": 41852
    },
    {
      "epoch": 1.2856879550271865,
      "grad_norm": 0.4216090738773346,
      "learning_rate": 5.677529022307626e-06,
      "loss": 0.4615,
      "step": 41853
    },
    {
      "epoch": 1.2857186741621356,
      "grad_norm": 0.4315132200717926,
      "learning_rate": 5.677093229502754e-06,
      "loss": 0.5564,
      "step": 41854
    },
    {
      "epoch": 1.2857493932970847,
      "grad_norm": 0.4073919951915741,
      "learning_rate": 5.676657446794328e-06,
      "loss": 0.4467,
      "step": 41855
    },
    {
      "epoch": 1.2857801124320338,
      "grad_norm": 0.4472254812717438,
      "learning_rate": 5.676221674183371e-06,
      "loss": 0.4418,
      "step": 41856
    },
    {
      "epoch": 1.285810831566983,
      "grad_norm": 0.3913980722427368,
      "learning_rate": 5.6757859116709e-06,
      "loss": 0.5513,
      "step": 41857
    },
    {
      "epoch": 1.2858415507019323,
      "grad_norm": 0.44094157218933105,
      "learning_rate": 5.675350159257933e-06,
      "loss": 0.473,
      "step": 41858
    },
    {
      "epoch": 1.2858722698368814,
      "grad_norm": 0.44270455837249756,
      "learning_rate": 5.6749144169454915e-06,
      "loss": 0.453,
      "step": 41859
    },
    {
      "epoch": 1.2859029889718305,
      "grad_norm": 0.39065033197402954,
      "learning_rate": 5.674478684734586e-06,
      "loss": 0.4999,
      "step": 41860
    },
    {
      "epoch": 1.2859337081067796,
      "grad_norm": 0.4005897045135498,
      "learning_rate": 5.6740429626262386e-06,
      "loss": 0.5407,
      "step": 41861
    },
    {
      "epoch": 1.285964427241729,
      "grad_norm": 0.4008921980857849,
      "learning_rate": 5.673607250621465e-06,
      "loss": 0.464,
      "step": 41862
    },
    {
      "epoch": 1.285995146376678,
      "grad_norm": 0.3959119915962219,
      "learning_rate": 5.6731715487212865e-06,
      "loss": 0.5652,
      "step": 41863
    },
    {
      "epoch": 1.2860258655116272,
      "grad_norm": 0.4702962338924408,
      "learning_rate": 5.672735856926715e-06,
      "loss": 0.4383,
      "step": 41864
    },
    {
      "epoch": 1.2860565846465764,
      "grad_norm": 0.4183408319950104,
      "learning_rate": 5.672300175238772e-06,
      "loss": 0.4785,
      "step": 41865
    },
    {
      "epoch": 1.2860873037815255,
      "grad_norm": 0.47834059596061707,
      "learning_rate": 5.671864503658473e-06,
      "loss": 0.5706,
      "step": 41866
    },
    {
      "epoch": 1.2861180229164746,
      "grad_norm": 0.3862392008304596,
      "learning_rate": 5.671428842186841e-06,
      "loss": 0.483,
      "step": 41867
    },
    {
      "epoch": 1.2861487420514237,
      "grad_norm": 0.4047326147556305,
      "learning_rate": 5.670993190824885e-06,
      "loss": 0.4241,
      "step": 41868
    },
    {
      "epoch": 1.286179461186373,
      "grad_norm": 0.4443052411079407,
      "learning_rate": 5.670557549573632e-06,
      "loss": 0.4686,
      "step": 41869
    },
    {
      "epoch": 1.2862101803213222,
      "grad_norm": 0.42348992824554443,
      "learning_rate": 5.670121918434085e-06,
      "loss": 0.5358,
      "step": 41870
    },
    {
      "epoch": 1.2862408994562713,
      "grad_norm": 0.4624429941177368,
      "learning_rate": 5.6696862974072795e-06,
      "loss": 0.4235,
      "step": 41871
    },
    {
      "epoch": 1.2862716185912204,
      "grad_norm": 0.38396796584129333,
      "learning_rate": 5.6692506864942184e-06,
      "loss": 0.4653,
      "step": 41872
    },
    {
      "epoch": 1.2863023377261698,
      "grad_norm": 0.42299261689186096,
      "learning_rate": 5.668815085695931e-06,
      "loss": 0.473,
      "step": 41873
    },
    {
      "epoch": 1.2863330568611189,
      "grad_norm": 0.46198806166648865,
      "learning_rate": 5.6683794950134226e-06,
      "loss": 0.4811,
      "step": 41874
    },
    {
      "epoch": 1.286363775996068,
      "grad_norm": 0.4245993196964264,
      "learning_rate": 5.667943914447713e-06,
      "loss": 0.4742,
      "step": 41875
    },
    {
      "epoch": 1.2863944951310171,
      "grad_norm": 0.4163435995578766,
      "learning_rate": 5.6675083439998324e-06,
      "loss": 0.4834,
      "step": 41876
    },
    {
      "epoch": 1.2864252142659662,
      "grad_norm": 0.3733290433883667,
      "learning_rate": 5.667072783670783e-06,
      "loss": 0.4755,
      "step": 41877
    },
    {
      "epoch": 1.2864559334009154,
      "grad_norm": 0.3985367715358734,
      "learning_rate": 5.666637233461591e-06,
      "loss": 0.4915,
      "step": 41878
    },
    {
      "epoch": 1.2864866525358645,
      "grad_norm": 0.4212981164455414,
      "learning_rate": 5.666201693373268e-06,
      "loss": 0.5258,
      "step": 41879
    },
    {
      "epoch": 1.2865173716708138,
      "grad_norm": 0.39460742473602295,
      "learning_rate": 5.6657661634068335e-06,
      "loss": 0.4981,
      "step": 41880
    },
    {
      "epoch": 1.286548090805763,
      "grad_norm": 0.4229751229286194,
      "learning_rate": 5.665330643563305e-06,
      "loss": 0.5194,
      "step": 41881
    },
    {
      "epoch": 1.286578809940712,
      "grad_norm": 0.4847364127635956,
      "learning_rate": 5.664895133843702e-06,
      "loss": 0.4871,
      "step": 41882
    },
    {
      "epoch": 1.2866095290756612,
      "grad_norm": 0.5035890936851501,
      "learning_rate": 5.664459634249037e-06,
      "loss": 0.531,
      "step": 41883
    },
    {
      "epoch": 1.2866402482106105,
      "grad_norm": 0.43466436862945557,
      "learning_rate": 5.664024144780328e-06,
      "loss": 0.5366,
      "step": 41884
    },
    {
      "epoch": 1.2866709673455596,
      "grad_norm": 0.41665300726890564,
      "learning_rate": 5.663588665438594e-06,
      "loss": 0.4431,
      "step": 41885
    },
    {
      "epoch": 1.2867016864805088,
      "grad_norm": 0.4024682343006134,
      "learning_rate": 5.663153196224855e-06,
      "loss": 0.395,
      "step": 41886
    },
    {
      "epoch": 1.2867324056154579,
      "grad_norm": 0.4692594110965729,
      "learning_rate": 5.662717737140122e-06,
      "loss": 0.4043,
      "step": 41887
    },
    {
      "epoch": 1.286763124750407,
      "grad_norm": 0.427386611700058,
      "learning_rate": 5.662282288185412e-06,
      "loss": 0.507,
      "step": 41888
    },
    {
      "epoch": 1.2867938438853561,
      "grad_norm": 0.3770598769187927,
      "learning_rate": 5.661846849361747e-06,
      "loss": 0.468,
      "step": 41889
    },
    {
      "epoch": 1.2868245630203052,
      "grad_norm": 0.46003997325897217,
      "learning_rate": 5.661411420670145e-06,
      "loss": 0.4931,
      "step": 41890
    },
    {
      "epoch": 1.2868552821552546,
      "grad_norm": 0.4608612656593323,
      "learning_rate": 5.660976002111616e-06,
      "loss": 0.4947,
      "step": 41891
    },
    {
      "epoch": 1.2868860012902037,
      "grad_norm": 0.450186163187027,
      "learning_rate": 5.6605405936871805e-06,
      "loss": 0.4569,
      "step": 41892
    },
    {
      "epoch": 1.2869167204251528,
      "grad_norm": 0.41073721647262573,
      "learning_rate": 5.6601051953978545e-06,
      "loss": 0.4969,
      "step": 41893
    },
    {
      "epoch": 1.286947439560102,
      "grad_norm": 0.43009233474731445,
      "learning_rate": 5.659669807244657e-06,
      "loss": 0.5545,
      "step": 41894
    },
    {
      "epoch": 1.2869781586950513,
      "grad_norm": 0.4361847937107086,
      "learning_rate": 5.659234429228607e-06,
      "loss": 0.5388,
      "step": 41895
    },
    {
      "epoch": 1.2870088778300004,
      "grad_norm": 0.391626238822937,
      "learning_rate": 5.658799061350715e-06,
      "loss": 0.508,
      "step": 41896
    },
    {
      "epoch": 1.2870395969649495,
      "grad_norm": 0.40227562189102173,
      "learning_rate": 5.658363703612e-06,
      "loss": 0.4565,
      "step": 41897
    },
    {
      "epoch": 1.2870703160998986,
      "grad_norm": 0.44051799178123474,
      "learning_rate": 5.65792835601348e-06,
      "loss": 0.4592,
      "step": 41898
    },
    {
      "epoch": 1.2871010352348478,
      "grad_norm": 0.4718070924282074,
      "learning_rate": 5.657493018556176e-06,
      "loss": 0.4385,
      "step": 41899
    },
    {
      "epoch": 1.2871317543697969,
      "grad_norm": 0.4107457995414734,
      "learning_rate": 5.6570576912410964e-06,
      "loss": 0.5107,
      "step": 41900
    },
    {
      "epoch": 1.287162473504746,
      "grad_norm": 0.40408873558044434,
      "learning_rate": 5.656622374069265e-06,
      "loss": 0.5406,
      "step": 41901
    },
    {
      "epoch": 1.2871931926396953,
      "grad_norm": 0.37795770168304443,
      "learning_rate": 5.656187067041688e-06,
      "loss": 0.456,
      "step": 41902
    },
    {
      "epoch": 1.2872239117746445,
      "grad_norm": 0.48737990856170654,
      "learning_rate": 5.655751770159399e-06,
      "loss": 0.4889,
      "step": 41903
    },
    {
      "epoch": 1.2872546309095936,
      "grad_norm": 0.39187362790107727,
      "learning_rate": 5.655316483423398e-06,
      "loss": 0.5055,
      "step": 41904
    },
    {
      "epoch": 1.2872853500445427,
      "grad_norm": 0.426044225692749,
      "learning_rate": 5.654881206834715e-06,
      "loss": 0.4398,
      "step": 41905
    },
    {
      "epoch": 1.287316069179492,
      "grad_norm": 0.4596061706542969,
      "learning_rate": 5.654445940394352e-06,
      "loss": 0.479,
      "step": 41906
    },
    {
      "epoch": 1.2873467883144412,
      "grad_norm": 0.5931896567344666,
      "learning_rate": 5.654010684103341e-06,
      "loss": 0.449,
      "step": 41907
    },
    {
      "epoch": 1.2873775074493903,
      "grad_norm": 0.3811695873737335,
      "learning_rate": 5.653575437962689e-06,
      "loss": 0.5456,
      "step": 41908
    },
    {
      "epoch": 1.2874082265843394,
      "grad_norm": 0.39886587858200073,
      "learning_rate": 5.653140201973419e-06,
      "loss": 0.5028,
      "step": 41909
    },
    {
      "epoch": 1.2874389457192885,
      "grad_norm": 0.38740360736846924,
      "learning_rate": 5.652704976136538e-06,
      "loss": 0.4257,
      "step": 41910
    },
    {
      "epoch": 1.2874696648542376,
      "grad_norm": 0.36772096157073975,
      "learning_rate": 5.652269760453071e-06,
      "loss": 0.4702,
      "step": 41911
    },
    {
      "epoch": 1.2875003839891868,
      "grad_norm": 0.4285084903240204,
      "learning_rate": 5.6518345549240295e-06,
      "loss": 0.4996,
      "step": 41912
    },
    {
      "epoch": 1.287531103124136,
      "grad_norm": 0.3790442943572998,
      "learning_rate": 5.651399359550431e-06,
      "loss": 0.4267,
      "step": 41913
    },
    {
      "epoch": 1.2875618222590852,
      "grad_norm": 0.4139263331890106,
      "learning_rate": 5.6509641743333e-06,
      "loss": 0.4682,
      "step": 41914
    },
    {
      "epoch": 1.2875925413940343,
      "grad_norm": 0.3756352365016937,
      "learning_rate": 5.65052899927364e-06,
      "loss": 0.4827,
      "step": 41915
    },
    {
      "epoch": 1.2876232605289835,
      "grad_norm": 0.38907280564308167,
      "learning_rate": 5.650093834372474e-06,
      "loss": 0.4455,
      "step": 41916
    },
    {
      "epoch": 1.2876539796639328,
      "grad_norm": 0.4151509702205658,
      "learning_rate": 5.649658679630816e-06,
      "loss": 0.5052,
      "step": 41917
    },
    {
      "epoch": 1.287684698798882,
      "grad_norm": 0.40205493569374084,
      "learning_rate": 5.649223535049691e-06,
      "loss": 0.5182,
      "step": 41918
    },
    {
      "epoch": 1.287715417933831,
      "grad_norm": 0.41107577085494995,
      "learning_rate": 5.648788400630102e-06,
      "loss": 0.4207,
      "step": 41919
    },
    {
      "epoch": 1.2877461370687802,
      "grad_norm": 0.3925679624080658,
      "learning_rate": 5.648353276373072e-06,
      "loss": 0.486,
      "step": 41920
    },
    {
      "epoch": 1.2877768562037293,
      "grad_norm": 0.4080375134944916,
      "learning_rate": 5.647918162279618e-06,
      "loss": 0.6009,
      "step": 41921
    },
    {
      "epoch": 1.2878075753386784,
      "grad_norm": 0.39456161856651306,
      "learning_rate": 5.647483058350757e-06,
      "loss": 0.4739,
      "step": 41922
    },
    {
      "epoch": 1.2878382944736275,
      "grad_norm": 0.6565236449241638,
      "learning_rate": 5.6470479645875e-06,
      "loss": 0.4998,
      "step": 41923
    },
    {
      "epoch": 1.2878690136085769,
      "grad_norm": 0.384128600358963,
      "learning_rate": 5.646612880990867e-06,
      "loss": 0.4405,
      "step": 41924
    },
    {
      "epoch": 1.287899732743526,
      "grad_norm": 0.457768052816391,
      "learning_rate": 5.646177807561873e-06,
      "loss": 0.4929,
      "step": 41925
    },
    {
      "epoch": 1.287930451878475,
      "grad_norm": 0.42515531182289124,
      "learning_rate": 5.64574274430154e-06,
      "loss": 0.4509,
      "step": 41926
    },
    {
      "epoch": 1.2879611710134242,
      "grad_norm": 0.428549587726593,
      "learning_rate": 5.645307691210874e-06,
      "loss": 0.4312,
      "step": 41927
    },
    {
      "epoch": 1.2879918901483733,
      "grad_norm": 0.3826967477798462,
      "learning_rate": 5.6448726482908955e-06,
      "loss": 0.4973,
      "step": 41928
    },
    {
      "epoch": 1.2880226092833227,
      "grad_norm": 0.43713462352752686,
      "learning_rate": 5.644437615542623e-06,
      "loss": 0.3677,
      "step": 41929
    },
    {
      "epoch": 1.2880533284182718,
      "grad_norm": 0.40812546014785767,
      "learning_rate": 5.644002592967068e-06,
      "loss": 0.4648,
      "step": 41930
    },
    {
      "epoch": 1.288084047553221,
      "grad_norm": 0.3865066170692444,
      "learning_rate": 5.643567580565256e-06,
      "loss": 0.4055,
      "step": 41931
    },
    {
      "epoch": 1.28811476668817,
      "grad_norm": 0.429305762052536,
      "learning_rate": 5.643132578338191e-06,
      "loss": 0.4495,
      "step": 41932
    },
    {
      "epoch": 1.2881454858231192,
      "grad_norm": 0.45954546332359314,
      "learning_rate": 5.642697586286894e-06,
      "loss": 0.4816,
      "step": 41933
    },
    {
      "epoch": 1.2881762049580683,
      "grad_norm": 0.383359432220459,
      "learning_rate": 5.642262604412381e-06,
      "loss": 0.4276,
      "step": 41934
    },
    {
      "epoch": 1.2882069240930174,
      "grad_norm": 0.4581001400947571,
      "learning_rate": 5.641827632715671e-06,
      "loss": 0.4581,
      "step": 41935
    },
    {
      "epoch": 1.2882376432279667,
      "grad_norm": 0.4176102578639984,
      "learning_rate": 5.641392671197774e-06,
      "loss": 0.5292,
      "step": 41936
    },
    {
      "epoch": 1.2882683623629159,
      "grad_norm": 0.3909841477870941,
      "learning_rate": 5.640957719859713e-06,
      "loss": 0.4277,
      "step": 41937
    },
    {
      "epoch": 1.288299081497865,
      "grad_norm": 0.40623167157173157,
      "learning_rate": 5.640522778702492e-06,
      "loss": 0.4462,
      "step": 41938
    },
    {
      "epoch": 1.288329800632814,
      "grad_norm": 0.38355308771133423,
      "learning_rate": 5.6400878477271414e-06,
      "loss": 0.5431,
      "step": 41939
    },
    {
      "epoch": 1.2883605197677634,
      "grad_norm": 0.4190918207168579,
      "learning_rate": 5.639652926934667e-06,
      "loss": 0.42,
      "step": 41940
    },
    {
      "epoch": 1.2883912389027126,
      "grad_norm": 0.43475064635276794,
      "learning_rate": 5.639218016326091e-06,
      "loss": 0.5043,
      "step": 41941
    },
    {
      "epoch": 1.2884219580376617,
      "grad_norm": 0.40145066380500793,
      "learning_rate": 5.638783115902419e-06,
      "loss": 0.4397,
      "step": 41942
    },
    {
      "epoch": 1.2884526771726108,
      "grad_norm": 0.4186069071292877,
      "learning_rate": 5.63834822566468e-06,
      "loss": 0.5107,
      "step": 41943
    },
    {
      "epoch": 1.28848339630756,
      "grad_norm": 0.3945038616657257,
      "learning_rate": 5.6379133456138815e-06,
      "loss": 0.4354,
      "step": 41944
    },
    {
      "epoch": 1.288514115442509,
      "grad_norm": 0.43227729201316833,
      "learning_rate": 5.6374784757510435e-06,
      "loss": 0.5068,
      "step": 41945
    },
    {
      "epoch": 1.2885448345774582,
      "grad_norm": 0.391543447971344,
      "learning_rate": 5.637043616077176e-06,
      "loss": 0.4635,
      "step": 41946
    },
    {
      "epoch": 1.2885755537124075,
      "grad_norm": 0.39053380489349365,
      "learning_rate": 5.636608766593297e-06,
      "loss": 0.4575,
      "step": 41947
    },
    {
      "epoch": 1.2886062728473566,
      "grad_norm": 0.45839691162109375,
      "learning_rate": 5.6361739273004234e-06,
      "loss": 0.4671,
      "step": 41948
    },
    {
      "epoch": 1.2886369919823057,
      "grad_norm": 0.4573739469051361,
      "learning_rate": 5.63573909819957e-06,
      "loss": 0.4505,
      "step": 41949
    },
    {
      "epoch": 1.2886677111172549,
      "grad_norm": 0.42587459087371826,
      "learning_rate": 5.635304279291757e-06,
      "loss": 0.4326,
      "step": 41950
    },
    {
      "epoch": 1.2886984302522042,
      "grad_norm": 0.3902655243873596,
      "learning_rate": 5.63486947057799e-06,
      "loss": 0.5461,
      "step": 41951
    },
    {
      "epoch": 1.2887291493871533,
      "grad_norm": 0.44162774085998535,
      "learning_rate": 5.6344346720592925e-06,
      "loss": 0.43,
      "step": 41952
    },
    {
      "epoch": 1.2887598685221024,
      "grad_norm": 0.3977111279964447,
      "learning_rate": 5.633999883736678e-06,
      "loss": 0.4886,
      "step": 41953
    },
    {
      "epoch": 1.2887905876570516,
      "grad_norm": 0.41985127329826355,
      "learning_rate": 5.633565105611165e-06,
      "loss": 0.5219,
      "step": 41954
    },
    {
      "epoch": 1.2888213067920007,
      "grad_norm": 0.5063556432723999,
      "learning_rate": 5.633130337683761e-06,
      "loss": 0.5066,
      "step": 41955
    },
    {
      "epoch": 1.2888520259269498,
      "grad_norm": 0.4042617380619049,
      "learning_rate": 5.632695579955486e-06,
      "loss": 0.4968,
      "step": 41956
    },
    {
      "epoch": 1.288882745061899,
      "grad_norm": 0.40048882365226746,
      "learning_rate": 5.6322608324273566e-06,
      "loss": 0.5162,
      "step": 41957
    },
    {
      "epoch": 1.2889134641968483,
      "grad_norm": 0.4121014475822449,
      "learning_rate": 5.63182609510039e-06,
      "loss": 0.4535,
      "step": 41958
    },
    {
      "epoch": 1.2889441833317974,
      "grad_norm": 0.40212956070899963,
      "learning_rate": 5.631391367975595e-06,
      "loss": 0.5044,
      "step": 41959
    },
    {
      "epoch": 1.2889749024667465,
      "grad_norm": 0.4348119795322418,
      "learning_rate": 5.630956651053991e-06,
      "loss": 0.5541,
      "step": 41960
    },
    {
      "epoch": 1.2890056216016956,
      "grad_norm": 0.3863244950771332,
      "learning_rate": 5.630521944336592e-06,
      "loss": 0.4796,
      "step": 41961
    },
    {
      "epoch": 1.289036340736645,
      "grad_norm": 0.622668445110321,
      "learning_rate": 5.6300872478244185e-06,
      "loss": 0.5731,
      "step": 41962
    },
    {
      "epoch": 1.289067059871594,
      "grad_norm": 0.40349945425987244,
      "learning_rate": 5.629652561518478e-06,
      "loss": 0.4507,
      "step": 41963
    },
    {
      "epoch": 1.2890977790065432,
      "grad_norm": 0.40226370096206665,
      "learning_rate": 5.6292178854197885e-06,
      "loss": 0.5118,
      "step": 41964
    },
    {
      "epoch": 1.2891284981414923,
      "grad_norm": 0.369308739900589,
      "learning_rate": 5.6287832195293655e-06,
      "loss": 0.5335,
      "step": 41965
    },
    {
      "epoch": 1.2891592172764414,
      "grad_norm": 0.4162428081035614,
      "learning_rate": 5.628348563848229e-06,
      "loss": 0.4276,
      "step": 41966
    },
    {
      "epoch": 1.2891899364113906,
      "grad_norm": 0.4094008505344391,
      "learning_rate": 5.627913918377387e-06,
      "loss": 0.5396,
      "step": 41967
    },
    {
      "epoch": 1.2892206555463397,
      "grad_norm": 0.43287956714630127,
      "learning_rate": 5.6274792831178556e-06,
      "loss": 0.5053,
      "step": 41968
    },
    {
      "epoch": 1.289251374681289,
      "grad_norm": 0.38882583379745483,
      "learning_rate": 5.627044658070653e-06,
      "loss": 0.5192,
      "step": 41969
    },
    {
      "epoch": 1.2892820938162382,
      "grad_norm": 0.4047497510910034,
      "learning_rate": 5.626610043236793e-06,
      "loss": 0.451,
      "step": 41970
    },
    {
      "epoch": 1.2893128129511873,
      "grad_norm": 0.5394447445869446,
      "learning_rate": 5.626175438617294e-06,
      "loss": 0.4988,
      "step": 41971
    },
    {
      "epoch": 1.2893435320861364,
      "grad_norm": 0.4194714426994324,
      "learning_rate": 5.625740844213163e-06,
      "loss": 0.4458,
      "step": 41972
    },
    {
      "epoch": 1.2893742512210857,
      "grad_norm": 0.3793583810329437,
      "learning_rate": 5.625306260025425e-06,
      "loss": 0.5074,
      "step": 41973
    },
    {
      "epoch": 1.2894049703560349,
      "grad_norm": 0.4005696475505829,
      "learning_rate": 5.624871686055081e-06,
      "loss": 0.4164,
      "step": 41974
    },
    {
      "epoch": 1.289435689490984,
      "grad_norm": 0.40541309118270874,
      "learning_rate": 5.624437122303164e-06,
      "loss": 0.5104,
      "step": 41975
    },
    {
      "epoch": 1.289466408625933,
      "grad_norm": 0.3906385898590088,
      "learning_rate": 5.6240025687706745e-06,
      "loss": 0.4163,
      "step": 41976
    },
    {
      "epoch": 1.2894971277608822,
      "grad_norm": 0.43951883912086487,
      "learning_rate": 5.623568025458636e-06,
      "loss": 0.5266,
      "step": 41977
    },
    {
      "epoch": 1.2895278468958313,
      "grad_norm": 0.40064042806625366,
      "learning_rate": 5.623133492368058e-06,
      "loss": 0.4619,
      "step": 41978
    },
    {
      "epoch": 1.2895585660307805,
      "grad_norm": 0.39702194929122925,
      "learning_rate": 5.622698969499956e-06,
      "loss": 0.4872,
      "step": 41979
    },
    {
      "epoch": 1.2895892851657298,
      "grad_norm": 0.3878476619720459,
      "learning_rate": 5.622264456855347e-06,
      "loss": 0.35,
      "step": 41980
    },
    {
      "epoch": 1.289620004300679,
      "grad_norm": 0.3930078446865082,
      "learning_rate": 5.621829954435247e-06,
      "loss": 0.4902,
      "step": 41981
    },
    {
      "epoch": 1.289650723435628,
      "grad_norm": 0.409911185503006,
      "learning_rate": 5.621395462240667e-06,
      "loss": 0.477,
      "step": 41982
    },
    {
      "epoch": 1.2896814425705772,
      "grad_norm": 0.3746229112148285,
      "learning_rate": 5.620960980272624e-06,
      "loss": 0.467,
      "step": 41983
    },
    {
      "epoch": 1.2897121617055265,
      "grad_norm": 0.4078065752983093,
      "learning_rate": 5.620526508532131e-06,
      "loss": 0.5393,
      "step": 41984
    },
    {
      "epoch": 1.2897428808404756,
      "grad_norm": 0.3896350860595703,
      "learning_rate": 5.620092047020206e-06,
      "loss": 0.4209,
      "step": 41985
    },
    {
      "epoch": 1.2897735999754247,
      "grad_norm": 0.4028441607952118,
      "learning_rate": 5.619657595737864e-06,
      "loss": 0.522,
      "step": 41986
    },
    {
      "epoch": 1.2898043191103739,
      "grad_norm": 0.42358115315437317,
      "learning_rate": 5.619223154686116e-06,
      "loss": 0.5554,
      "step": 41987
    },
    {
      "epoch": 1.289835038245323,
      "grad_norm": 0.40079277753829956,
      "learning_rate": 5.618788723865975e-06,
      "loss": 0.482,
      "step": 41988
    },
    {
      "epoch": 1.289865757380272,
      "grad_norm": 0.4529880881309509,
      "learning_rate": 5.6183543032784615e-06,
      "loss": 0.4622,
      "step": 41989
    },
    {
      "epoch": 1.2898964765152212,
      "grad_norm": 0.4691735804080963,
      "learning_rate": 5.6179198929245904e-06,
      "loss": 0.5424,
      "step": 41990
    },
    {
      "epoch": 1.2899271956501706,
      "grad_norm": 0.6111907958984375,
      "learning_rate": 5.61748549280537e-06,
      "loss": 0.4632,
      "step": 41991
    },
    {
      "epoch": 1.2899579147851197,
      "grad_norm": 0.38598865270614624,
      "learning_rate": 5.617051102921818e-06,
      "loss": 0.4472,
      "step": 41992
    },
    {
      "epoch": 1.2899886339200688,
      "grad_norm": 0.44536665081977844,
      "learning_rate": 5.616616723274949e-06,
      "loss": 0.5395,
      "step": 41993
    },
    {
      "epoch": 1.290019353055018,
      "grad_norm": 0.4264894425868988,
      "learning_rate": 5.616182353865782e-06,
      "loss": 0.5235,
      "step": 41994
    },
    {
      "epoch": 1.2900500721899673,
      "grad_norm": 0.5478636026382446,
      "learning_rate": 5.615747994695323e-06,
      "loss": 0.4818,
      "step": 41995
    },
    {
      "epoch": 1.2900807913249164,
      "grad_norm": 0.3987818658351898,
      "learning_rate": 5.615313645764591e-06,
      "loss": 0.4797,
      "step": 41996
    },
    {
      "epoch": 1.2901115104598655,
      "grad_norm": 0.4229414463043213,
      "learning_rate": 5.614879307074601e-06,
      "loss": 0.4491,
      "step": 41997
    },
    {
      "epoch": 1.2901422295948146,
      "grad_norm": 0.4159504771232605,
      "learning_rate": 5.61444497862637e-06,
      "loss": 0.4709,
      "step": 41998
    },
    {
      "epoch": 1.2901729487297637,
      "grad_norm": 0.4427196979522705,
      "learning_rate": 5.614010660420904e-06,
      "loss": 0.5332,
      "step": 41999
    },
    {
      "epoch": 1.2902036678647129,
      "grad_norm": 0.6596353054046631,
      "learning_rate": 5.613576352459228e-06,
      "loss": 0.5482,
      "step": 42000
    },
    {
      "epoch": 1.290234386999662,
      "grad_norm": 0.41810911893844604,
      "learning_rate": 5.613142054742342e-06,
      "loss": 0.4703,
      "step": 42001
    },
    {
      "epoch": 1.2902651061346113,
      "grad_norm": 0.4215320646762848,
      "learning_rate": 5.612707767271277e-06,
      "loss": 0.4822,
      "step": 42002
    },
    {
      "epoch": 1.2902958252695604,
      "grad_norm": 0.42365479469299316,
      "learning_rate": 5.6122734900470355e-06,
      "loss": 0.4781,
      "step": 42003
    },
    {
      "epoch": 1.2903265444045096,
      "grad_norm": 0.41764628887176514,
      "learning_rate": 5.6118392230706365e-06,
      "loss": 0.4381,
      "step": 42004
    },
    {
      "epoch": 1.2903572635394587,
      "grad_norm": 0.4107723832130432,
      "learning_rate": 5.611404966343092e-06,
      "loss": 0.4557,
      "step": 42005
    },
    {
      "epoch": 1.290387982674408,
      "grad_norm": 0.3713218867778778,
      "learning_rate": 5.610970719865418e-06,
      "loss": 0.4348,
      "step": 42006
    },
    {
      "epoch": 1.2904187018093571,
      "grad_norm": 0.39868006110191345,
      "learning_rate": 5.610536483638633e-06,
      "loss": 0.5097,
      "step": 42007
    },
    {
      "epoch": 1.2904494209443063,
      "grad_norm": 0.4295928180217743,
      "learning_rate": 5.610102257663743e-06,
      "loss": 0.4624,
      "step": 42008
    },
    {
      "epoch": 1.2904801400792554,
      "grad_norm": 0.4454840421676636,
      "learning_rate": 5.60966804194177e-06,
      "loss": 0.4758,
      "step": 42009
    },
    {
      "epoch": 1.2905108592142045,
      "grad_norm": 0.38169318437576294,
      "learning_rate": 5.609233836473715e-06,
      "loss": 0.4955,
      "step": 42010
    },
    {
      "epoch": 1.2905415783491536,
      "grad_norm": 0.38986650109291077,
      "learning_rate": 5.6087996412606094e-06,
      "loss": 0.4534,
      "step": 42011
    },
    {
      "epoch": 1.2905722974841027,
      "grad_norm": 0.40107864141464233,
      "learning_rate": 5.608365456303455e-06,
      "loss": 0.5366,
      "step": 42012
    },
    {
      "epoch": 1.290603016619052,
      "grad_norm": 0.4363385736942291,
      "learning_rate": 5.6079312816032725e-06,
      "loss": 0.4648,
      "step": 42013
    },
    {
      "epoch": 1.2906337357540012,
      "grad_norm": 0.3774028420448303,
      "learning_rate": 5.607497117161071e-06,
      "loss": 0.4723,
      "step": 42014
    },
    {
      "epoch": 1.2906644548889503,
      "grad_norm": 0.4441452920436859,
      "learning_rate": 5.607062962977865e-06,
      "loss": 0.4699,
      "step": 42015
    },
    {
      "epoch": 1.2906951740238994,
      "grad_norm": 0.4002891480922699,
      "learning_rate": 5.606628819054671e-06,
      "loss": 0.4518,
      "step": 42016
    },
    {
      "epoch": 1.2907258931588488,
      "grad_norm": 0.4145567715167999,
      "learning_rate": 5.606194685392507e-06,
      "loss": 0.5003,
      "step": 42017
    },
    {
      "epoch": 1.290756612293798,
      "grad_norm": 0.414883017539978,
      "learning_rate": 5.605760561992377e-06,
      "loss": 0.5483,
      "step": 42018
    },
    {
      "epoch": 1.290787331428747,
      "grad_norm": 0.3846861720085144,
      "learning_rate": 5.605326448855301e-06,
      "loss": 0.5255,
      "step": 42019
    },
    {
      "epoch": 1.2908180505636961,
      "grad_norm": 0.40884628891944885,
      "learning_rate": 5.604892345982292e-06,
      "loss": 0.5497,
      "step": 42020
    },
    {
      "epoch": 1.2908487696986453,
      "grad_norm": 0.4149968922138214,
      "learning_rate": 5.604458253374364e-06,
      "loss": 0.4653,
      "step": 42021
    },
    {
      "epoch": 1.2908794888335944,
      "grad_norm": 0.36065810918807983,
      "learning_rate": 5.6040241710325334e-06,
      "loss": 0.4251,
      "step": 42022
    },
    {
      "epoch": 1.2909102079685435,
      "grad_norm": 0.447203129529953,
      "learning_rate": 5.60359009895781e-06,
      "loss": 0.5054,
      "step": 42023
    },
    {
      "epoch": 1.2909409271034928,
      "grad_norm": 0.4047544598579407,
      "learning_rate": 5.603156037151206e-06,
      "loss": 0.489,
      "step": 42024
    },
    {
      "epoch": 1.290971646238442,
      "grad_norm": 0.41188469529151917,
      "learning_rate": 5.602721985613739e-06,
      "loss": 0.4548,
      "step": 42025
    },
    {
      "epoch": 1.291002365373391,
      "grad_norm": 0.3949550688266754,
      "learning_rate": 5.602287944346427e-06,
      "loss": 0.5016,
      "step": 42026
    },
    {
      "epoch": 1.2910330845083402,
      "grad_norm": 0.41564834117889404,
      "learning_rate": 5.601853913350275e-06,
      "loss": 0.4813,
      "step": 42027
    },
    {
      "epoch": 1.2910638036432895,
      "grad_norm": 0.44191527366638184,
      "learning_rate": 5.601419892626299e-06,
      "loss": 0.4869,
      "step": 42028
    },
    {
      "epoch": 1.2910945227782387,
      "grad_norm": 0.44509777426719666,
      "learning_rate": 5.600985882175513e-06,
      "loss": 0.5051,
      "step": 42029
    },
    {
      "epoch": 1.2911252419131878,
      "grad_norm": 0.3932483494281769,
      "learning_rate": 5.600551881998937e-06,
      "loss": 0.4674,
      "step": 42030
    },
    {
      "epoch": 1.291155961048137,
      "grad_norm": 0.3666963577270508,
      "learning_rate": 5.6001178920975766e-06,
      "loss": 0.4951,
      "step": 42031
    },
    {
      "epoch": 1.291186680183086,
      "grad_norm": 0.3903193473815918,
      "learning_rate": 5.599683912472447e-06,
      "loss": 0.4238,
      "step": 42032
    },
    {
      "epoch": 1.2912173993180351,
      "grad_norm": 0.42154502868652344,
      "learning_rate": 5.599249943124563e-06,
      "loss": 0.4944,
      "step": 42033
    },
    {
      "epoch": 1.2912481184529843,
      "grad_norm": 0.4275948107242584,
      "learning_rate": 5.598815984054942e-06,
      "loss": 0.4807,
      "step": 42034
    },
    {
      "epoch": 1.2912788375879336,
      "grad_norm": 0.39649659395217896,
      "learning_rate": 5.598382035264589e-06,
      "loss": 0.4736,
      "step": 42035
    },
    {
      "epoch": 1.2913095567228827,
      "grad_norm": 0.4055913984775543,
      "learning_rate": 5.597948096754526e-06,
      "loss": 0.4952,
      "step": 42036
    },
    {
      "epoch": 1.2913402758578318,
      "grad_norm": 0.3852173686027527,
      "learning_rate": 5.597514168525755e-06,
      "loss": 0.4029,
      "step": 42037
    },
    {
      "epoch": 1.291370994992781,
      "grad_norm": 0.40709319710731506,
      "learning_rate": 5.5970802505793065e-06,
      "loss": 0.4382,
      "step": 42038
    },
    {
      "epoch": 1.29140171412773,
      "grad_norm": 0.4374459683895111,
      "learning_rate": 5.5966463429161785e-06,
      "loss": 0.476,
      "step": 42039
    },
    {
      "epoch": 1.2914324332626794,
      "grad_norm": 0.5959595441818237,
      "learning_rate": 5.5962124455373925e-06,
      "loss": 0.4875,
      "step": 42040
    },
    {
      "epoch": 1.2914631523976285,
      "grad_norm": 0.40963301062583923,
      "learning_rate": 5.595778558443962e-06,
      "loss": 0.4801,
      "step": 42041
    },
    {
      "epoch": 1.2914938715325777,
      "grad_norm": 0.4196571111679077,
      "learning_rate": 5.595344681636892e-06,
      "loss": 0.4778,
      "step": 42042
    },
    {
      "epoch": 1.2915245906675268,
      "grad_norm": 0.6994566917419434,
      "learning_rate": 5.594910815117209e-06,
      "loss": 0.4959,
      "step": 42043
    },
    {
      "epoch": 1.291555309802476,
      "grad_norm": 0.4419405162334442,
      "learning_rate": 5.594476958885917e-06,
      "loss": 0.5391,
      "step": 42044
    },
    {
      "epoch": 1.291586028937425,
      "grad_norm": 0.41683200001716614,
      "learning_rate": 5.594043112944034e-06,
      "loss": 0.4783,
      "step": 42045
    },
    {
      "epoch": 1.2916167480723741,
      "grad_norm": 0.4094091057777405,
      "learning_rate": 5.593609277292564e-06,
      "loss": 0.409,
      "step": 42046
    },
    {
      "epoch": 1.2916474672073235,
      "grad_norm": 0.4148782193660736,
      "learning_rate": 5.593175451932534e-06,
      "loss": 0.5012,
      "step": 42047
    },
    {
      "epoch": 1.2916781863422726,
      "grad_norm": 0.4002760350704193,
      "learning_rate": 5.592741636864948e-06,
      "loss": 0.5055,
      "step": 42048
    },
    {
      "epoch": 1.2917089054772217,
      "grad_norm": 0.36963436007499695,
      "learning_rate": 5.592307832090824e-06,
      "loss": 0.4708,
      "step": 42049
    },
    {
      "epoch": 1.2917396246121708,
      "grad_norm": 0.4295002520084381,
      "learning_rate": 5.591874037611171e-06,
      "loss": 0.4249,
      "step": 42050
    },
    {
      "epoch": 1.2917703437471202,
      "grad_norm": 0.41297391057014465,
      "learning_rate": 5.591440253427003e-06,
      "loss": 0.4138,
      "step": 42051
    },
    {
      "epoch": 1.2918010628820693,
      "grad_norm": 0.3952043056488037,
      "learning_rate": 5.591006479539334e-06,
      "loss": 0.4365,
      "step": 42052
    },
    {
      "epoch": 1.2918317820170184,
      "grad_norm": 0.4115416705608368,
      "learning_rate": 5.590572715949181e-06,
      "loss": 0.487,
      "step": 42053
    },
    {
      "epoch": 1.2918625011519675,
      "grad_norm": 0.44697675108909607,
      "learning_rate": 5.59013896265755e-06,
      "loss": 0.4219,
      "step": 42054
    },
    {
      "epoch": 1.2918932202869167,
      "grad_norm": 0.4091099500656128,
      "learning_rate": 5.5897052196654575e-06,
      "loss": 0.447,
      "step": 42055
    },
    {
      "epoch": 1.2919239394218658,
      "grad_norm": 0.4040105640888214,
      "learning_rate": 5.589271486973916e-06,
      "loss": 0.5136,
      "step": 42056
    },
    {
      "epoch": 1.291954658556815,
      "grad_norm": 0.4065019488334656,
      "learning_rate": 5.588837764583943e-06,
      "loss": 0.4911,
      "step": 42057
    },
    {
      "epoch": 1.2919853776917642,
      "grad_norm": 0.41476789116859436,
      "learning_rate": 5.588404052496543e-06,
      "loss": 0.4781,
      "step": 42058
    },
    {
      "epoch": 1.2920160968267134,
      "grad_norm": 0.40729716420173645,
      "learning_rate": 5.587970350712735e-06,
      "loss": 0.4556,
      "step": 42059
    },
    {
      "epoch": 1.2920468159616625,
      "grad_norm": 0.41668206453323364,
      "learning_rate": 5.58753665923353e-06,
      "loss": 0.3751,
      "step": 42060
    },
    {
      "epoch": 1.2920775350966116,
      "grad_norm": 0.39079251885414124,
      "learning_rate": 5.587102978059939e-06,
      "loss": 0.4814,
      "step": 42061
    },
    {
      "epoch": 1.292108254231561,
      "grad_norm": 0.4038490951061249,
      "learning_rate": 5.5866693071929846e-06,
      "loss": 0.4276,
      "step": 42062
    },
    {
      "epoch": 1.29213897336651,
      "grad_norm": 0.398293137550354,
      "learning_rate": 5.586235646633666e-06,
      "loss": 0.4984,
      "step": 42063
    },
    {
      "epoch": 1.2921696925014592,
      "grad_norm": 0.4085562229156494,
      "learning_rate": 5.585801996383004e-06,
      "loss": 0.3987,
      "step": 42064
    },
    {
      "epoch": 1.2922004116364083,
      "grad_norm": 0.41977420449256897,
      "learning_rate": 5.585368356442008e-06,
      "loss": 0.4328,
      "step": 42065
    },
    {
      "epoch": 1.2922311307713574,
      "grad_norm": 0.44645214080810547,
      "learning_rate": 5.584934726811697e-06,
      "loss": 0.4321,
      "step": 42066
    },
    {
      "epoch": 1.2922618499063065,
      "grad_norm": 0.40580737590789795,
      "learning_rate": 5.584501107493075e-06,
      "loss": 0.4355,
      "step": 42067
    },
    {
      "epoch": 1.2922925690412557,
      "grad_norm": 0.4149360656738281,
      "learning_rate": 5.58406749848716e-06,
      "loss": 0.5136,
      "step": 42068
    },
    {
      "epoch": 1.292323288176205,
      "grad_norm": 0.4090927541255951,
      "learning_rate": 5.583633899794964e-06,
      "loss": 0.4694,
      "step": 42069
    },
    {
      "epoch": 1.2923540073111541,
      "grad_norm": 0.43392065167427063,
      "learning_rate": 5.583200311417503e-06,
      "loss": 0.4424,
      "step": 42070
    },
    {
      "epoch": 1.2923847264461032,
      "grad_norm": 0.41910213232040405,
      "learning_rate": 5.58276673335578e-06,
      "loss": 0.5193,
      "step": 42071
    },
    {
      "epoch": 1.2924154455810524,
      "grad_norm": 0.40248990058898926,
      "learning_rate": 5.582333165610821e-06,
      "loss": 0.5026,
      "step": 42072
    },
    {
      "epoch": 1.2924461647160017,
      "grad_norm": 0.5417808890342712,
      "learning_rate": 5.581899608183621e-06,
      "loss": 0.4492,
      "step": 42073
    },
    {
      "epoch": 1.2924768838509508,
      "grad_norm": 0.46965450048446655,
      "learning_rate": 5.581466061075213e-06,
      "loss": 0.4443,
      "step": 42074
    },
    {
      "epoch": 1.2925076029859,
      "grad_norm": 0.38700538873672485,
      "learning_rate": 5.581032524286594e-06,
      "loss": 0.4894,
      "step": 42075
    },
    {
      "epoch": 1.292538322120849,
      "grad_norm": 0.41582000255584717,
      "learning_rate": 5.580598997818783e-06,
      "loss": 0.4691,
      "step": 42076
    },
    {
      "epoch": 1.2925690412557982,
      "grad_norm": 0.4254908561706543,
      "learning_rate": 5.580165481672796e-06,
      "loss": 0.5031,
      "step": 42077
    },
    {
      "epoch": 1.2925997603907473,
      "grad_norm": 0.4443703591823578,
      "learning_rate": 5.579731975849632e-06,
      "loss": 0.4974,
      "step": 42078
    },
    {
      "epoch": 1.2926304795256964,
      "grad_norm": 0.4127125144004822,
      "learning_rate": 5.5792984803503215e-06,
      "loss": 0.5418,
      "step": 42079
    },
    {
      "epoch": 1.2926611986606458,
      "grad_norm": 0.42197003960609436,
      "learning_rate": 5.578864995175865e-06,
      "loss": 0.4346,
      "step": 42080
    },
    {
      "epoch": 1.292691917795595,
      "grad_norm": 0.38691335916519165,
      "learning_rate": 5.578431520327281e-06,
      "loss": 0.446,
      "step": 42081
    },
    {
      "epoch": 1.292722636930544,
      "grad_norm": 0.39664432406425476,
      "learning_rate": 5.577998055805575e-06,
      "loss": 0.5116,
      "step": 42082
    },
    {
      "epoch": 1.2927533560654931,
      "grad_norm": 0.3936331272125244,
      "learning_rate": 5.577564601611762e-06,
      "loss": 0.4594,
      "step": 42083
    },
    {
      "epoch": 1.2927840752004425,
      "grad_norm": 0.4067883789539337,
      "learning_rate": 5.5771311577468575e-06,
      "loss": 0.4839,
      "step": 42084
    },
    {
      "epoch": 1.2928147943353916,
      "grad_norm": 0.3732795715332031,
      "learning_rate": 5.576697724211877e-06,
      "loss": 0.4475,
      "step": 42085
    },
    {
      "epoch": 1.2928455134703407,
      "grad_norm": 0.3745919466018677,
      "learning_rate": 5.576264301007822e-06,
      "loss": 0.5053,
      "step": 42086
    },
    {
      "epoch": 1.2928762326052898,
      "grad_norm": 0.43278124928474426,
      "learning_rate": 5.575830888135712e-06,
      "loss": 0.5132,
      "step": 42087
    },
    {
      "epoch": 1.292906951740239,
      "grad_norm": 0.4380301535129547,
      "learning_rate": 5.575397485596556e-06,
      "loss": 0.424,
      "step": 42088
    },
    {
      "epoch": 1.292937670875188,
      "grad_norm": 0.40939730405807495,
      "learning_rate": 5.574964093391375e-06,
      "loss": 0.4889,
      "step": 42089
    },
    {
      "epoch": 1.2929683900101372,
      "grad_norm": 0.44530344009399414,
      "learning_rate": 5.574530711521169e-06,
      "loss": 0.5101,
      "step": 42090
    },
    {
      "epoch": 1.2929991091450865,
      "grad_norm": 0.449169784784317,
      "learning_rate": 5.574097339986955e-06,
      "loss": 0.4224,
      "step": 42091
    },
    {
      "epoch": 1.2930298282800357,
      "grad_norm": 0.38516703248023987,
      "learning_rate": 5.573663978789745e-06,
      "loss": 0.4553,
      "step": 42092
    },
    {
      "epoch": 1.2930605474149848,
      "grad_norm": 0.47392594814300537,
      "learning_rate": 5.5732306279305585e-06,
      "loss": 0.53,
      "step": 42093
    },
    {
      "epoch": 1.293091266549934,
      "grad_norm": 0.4181426465511322,
      "learning_rate": 5.572797287410395e-06,
      "loss": 0.4611,
      "step": 42094
    },
    {
      "epoch": 1.2931219856848832,
      "grad_norm": 0.534157931804657,
      "learning_rate": 5.572363957230273e-06,
      "loss": 0.5092,
      "step": 42095
    },
    {
      "epoch": 1.2931527048198324,
      "grad_norm": 0.439566045999527,
      "learning_rate": 5.571930637391206e-06,
      "loss": 0.5287,
      "step": 42096
    },
    {
      "epoch": 1.2931834239547815,
      "grad_norm": 0.3899461328983307,
      "learning_rate": 5.571497327894202e-06,
      "loss": 0.5004,
      "step": 42097
    },
    {
      "epoch": 1.2932141430897306,
      "grad_norm": 0.4609881639480591,
      "learning_rate": 5.571064028740279e-06,
      "loss": 0.4639,
      "step": 42098
    },
    {
      "epoch": 1.2932448622246797,
      "grad_norm": 0.47994908690452576,
      "learning_rate": 5.570630739930442e-06,
      "loss": 0.5049,
      "step": 42099
    },
    {
      "epoch": 1.2932755813596288,
      "grad_norm": 0.37292635440826416,
      "learning_rate": 5.570197461465708e-06,
      "loss": 0.4106,
      "step": 42100
    },
    {
      "epoch": 1.293306300494578,
      "grad_norm": 0.4071144163608551,
      "learning_rate": 5.569764193347085e-06,
      "loss": 0.5443,
      "step": 42101
    },
    {
      "epoch": 1.2933370196295273,
      "grad_norm": 0.4967424273490906,
      "learning_rate": 5.569330935575592e-06,
      "loss": 0.4199,
      "step": 42102
    },
    {
      "epoch": 1.2933677387644764,
      "grad_norm": 0.4036967158317566,
      "learning_rate": 5.568897688152232e-06,
      "loss": 0.4624,
      "step": 42103
    },
    {
      "epoch": 1.2933984578994255,
      "grad_norm": 0.38858863711357117,
      "learning_rate": 5.568464451078025e-06,
      "loss": 0.5088,
      "step": 42104
    },
    {
      "epoch": 1.2934291770343747,
      "grad_norm": 0.47853487730026245,
      "learning_rate": 5.5680312243539705e-06,
      "loss": 0.5225,
      "step": 42105
    },
    {
      "epoch": 1.293459896169324,
      "grad_norm": 0.42957720160484314,
      "learning_rate": 5.567598007981096e-06,
      "loss": 0.4882,
      "step": 42106
    },
    {
      "epoch": 1.2934906153042731,
      "grad_norm": 0.410587877035141,
      "learning_rate": 5.567164801960403e-06,
      "loss": 0.5191,
      "step": 42107
    },
    {
      "epoch": 1.2935213344392222,
      "grad_norm": 0.3986378014087677,
      "learning_rate": 5.56673160629291e-06,
      "loss": 0.5117,
      "step": 42108
    },
    {
      "epoch": 1.2935520535741714,
      "grad_norm": 0.44385600090026855,
      "learning_rate": 5.566298420979617e-06,
      "loss": 0.4977,
      "step": 42109
    },
    {
      "epoch": 1.2935827727091205,
      "grad_norm": 0.42507821321487427,
      "learning_rate": 5.565865246021551e-06,
      "loss": 0.501,
      "step": 42110
    },
    {
      "epoch": 1.2936134918440696,
      "grad_norm": 0.3576143682003021,
      "learning_rate": 5.565432081419712e-06,
      "loss": 0.5097,
      "step": 42111
    },
    {
      "epoch": 1.2936442109790187,
      "grad_norm": 0.393991082906723,
      "learning_rate": 5.5649989271751225e-06,
      "loss": 0.4439,
      "step": 42112
    },
    {
      "epoch": 1.293674930113968,
      "grad_norm": 0.3690249025821686,
      "learning_rate": 5.5645657832887825e-06,
      "loss": 0.4088,
      "step": 42113
    },
    {
      "epoch": 1.2937056492489172,
      "grad_norm": 0.40495947003364563,
      "learning_rate": 5.5641326497617045e-06,
      "loss": 0.4332,
      "step": 42114
    },
    {
      "epoch": 1.2937363683838663,
      "grad_norm": 0.443244993686676,
      "learning_rate": 5.563699526594913e-06,
      "loss": 0.4281,
      "step": 42115
    },
    {
      "epoch": 1.2937670875188154,
      "grad_norm": 0.4468725323677063,
      "learning_rate": 5.563266413789406e-06,
      "loss": 0.496,
      "step": 42116
    },
    {
      "epoch": 1.2937978066537648,
      "grad_norm": 0.4043937921524048,
      "learning_rate": 5.562833311346204e-06,
      "loss": 0.4848,
      "step": 42117
    },
    {
      "epoch": 1.2938285257887139,
      "grad_norm": 0.3809766471385956,
      "learning_rate": 5.562400219266311e-06,
      "loss": 0.4463,
      "step": 42118
    },
    {
      "epoch": 1.293859244923663,
      "grad_norm": 0.398543119430542,
      "learning_rate": 5.561967137550743e-06,
      "loss": 0.46,
      "step": 42119
    },
    {
      "epoch": 1.2938899640586121,
      "grad_norm": 0.3635006248950958,
      "learning_rate": 5.56153406620051e-06,
      "loss": 0.5103,
      "step": 42120
    },
    {
      "epoch": 1.2939206831935612,
      "grad_norm": 0.4915827810764313,
      "learning_rate": 5.561101005216629e-06,
      "loss": 0.5623,
      "step": 42121
    },
    {
      "epoch": 1.2939514023285104,
      "grad_norm": 0.3970779478549957,
      "learning_rate": 5.560667954600102e-06,
      "loss": 0.4887,
      "step": 42122
    },
    {
      "epoch": 1.2939821214634595,
      "grad_norm": 0.41089776158332825,
      "learning_rate": 5.5602349143519455e-06,
      "loss": 0.4211,
      "step": 42123
    },
    {
      "epoch": 1.2940128405984088,
      "grad_norm": 0.35413625836372375,
      "learning_rate": 5.55980188447317e-06,
      "loss": 0.4788,
      "step": 42124
    },
    {
      "epoch": 1.294043559733358,
      "grad_norm": 0.39156976342201233,
      "learning_rate": 5.559368864964791e-06,
      "loss": 0.467,
      "step": 42125
    },
    {
      "epoch": 1.294074278868307,
      "grad_norm": 0.4325234293937683,
      "learning_rate": 5.558935855827812e-06,
      "loss": 0.469,
      "step": 42126
    },
    {
      "epoch": 1.2941049980032562,
      "grad_norm": 0.4178966283798218,
      "learning_rate": 5.5585028570632495e-06,
      "loss": 0.4786,
      "step": 42127
    },
    {
      "epoch": 1.2941357171382055,
      "grad_norm": 0.44332563877105713,
      "learning_rate": 5.558069868672114e-06,
      "loss": 0.5177,
      "step": 42128
    },
    {
      "epoch": 1.2941664362731546,
      "grad_norm": 0.3979361355304718,
      "learning_rate": 5.557636890655419e-06,
      "loss": 0.4539,
      "step": 42129
    },
    {
      "epoch": 1.2941971554081038,
      "grad_norm": 0.4917502701282501,
      "learning_rate": 5.557203923014169e-06,
      "loss": 0.4702,
      "step": 42130
    },
    {
      "epoch": 1.2942278745430529,
      "grad_norm": 0.4009172320365906,
      "learning_rate": 5.556770965749381e-06,
      "loss": 0.4239,
      "step": 42131
    },
    {
      "epoch": 1.294258593678002,
      "grad_norm": 0.4135098159313202,
      "learning_rate": 5.556338018862065e-06,
      "loss": 0.471,
      "step": 42132
    },
    {
      "epoch": 1.2942893128129511,
      "grad_norm": 0.38948899507522583,
      "learning_rate": 5.555905082353231e-06,
      "loss": 0.4607,
      "step": 42133
    },
    {
      "epoch": 1.2943200319479002,
      "grad_norm": 0.3992891013622284,
      "learning_rate": 5.555472156223895e-06,
      "loss": 0.4711,
      "step": 42134
    },
    {
      "epoch": 1.2943507510828496,
      "grad_norm": 0.42987486720085144,
      "learning_rate": 5.555039240475061e-06,
      "loss": 0.5401,
      "step": 42135
    },
    {
      "epoch": 1.2943814702177987,
      "grad_norm": 0.43235287070274353,
      "learning_rate": 5.5546063351077425e-06,
      "loss": 0.5226,
      "step": 42136
    },
    {
      "epoch": 1.2944121893527478,
      "grad_norm": 0.4372669756412506,
      "learning_rate": 5.554173440122952e-06,
      "loss": 0.4981,
      "step": 42137
    },
    {
      "epoch": 1.294442908487697,
      "grad_norm": 0.40930551290512085,
      "learning_rate": 5.5537405555217025e-06,
      "loss": 0.5792,
      "step": 42138
    },
    {
      "epoch": 1.2944736276226463,
      "grad_norm": 0.40672576427459717,
      "learning_rate": 5.5533076813050005e-06,
      "loss": 0.4473,
      "step": 42139
    },
    {
      "epoch": 1.2945043467575954,
      "grad_norm": 0.7604910731315613,
      "learning_rate": 5.552874817473861e-06,
      "loss": 0.469,
      "step": 42140
    },
    {
      "epoch": 1.2945350658925445,
      "grad_norm": 0.4432006776332855,
      "learning_rate": 5.552441964029287e-06,
      "loss": 0.5139,
      "step": 42141
    },
    {
      "epoch": 1.2945657850274936,
      "grad_norm": 0.4122862219810486,
      "learning_rate": 5.552009120972301e-06,
      "loss": 0.4673,
      "step": 42142
    },
    {
      "epoch": 1.2945965041624428,
      "grad_norm": 0.4186055064201355,
      "learning_rate": 5.551576288303907e-06,
      "loss": 0.5004,
      "step": 42143
    },
    {
      "epoch": 1.2946272232973919,
      "grad_norm": 0.49480146169662476,
      "learning_rate": 5.55114346602512e-06,
      "loss": 0.4138,
      "step": 42144
    },
    {
      "epoch": 1.294657942432341,
      "grad_norm": 0.4603745639324188,
      "learning_rate": 5.550710654136944e-06,
      "loss": 0.4277,
      "step": 42145
    },
    {
      "epoch": 1.2946886615672903,
      "grad_norm": 0.4131730794906616,
      "learning_rate": 5.550277852640393e-06,
      "loss": 0.5187,
      "step": 42146
    },
    {
      "epoch": 1.2947193807022395,
      "grad_norm": 0.41612592339515686,
      "learning_rate": 5.549845061536481e-06,
      "loss": 0.5557,
      "step": 42147
    },
    {
      "epoch": 1.2947500998371886,
      "grad_norm": 0.41920796036720276,
      "learning_rate": 5.549412280826218e-06,
      "loss": 0.402,
      "step": 42148
    },
    {
      "epoch": 1.2947808189721377,
      "grad_norm": 1.4438503980636597,
      "learning_rate": 5.548979510510613e-06,
      "loss": 0.4734,
      "step": 42149
    },
    {
      "epoch": 1.2948115381070868,
      "grad_norm": 0.4231948256492615,
      "learning_rate": 5.548546750590671e-06,
      "loss": 0.5166,
      "step": 42150
    },
    {
      "epoch": 1.2948422572420362,
      "grad_norm": 0.41179150342941284,
      "learning_rate": 5.548114001067418e-06,
      "loss": 0.4598,
      "step": 42151
    },
    {
      "epoch": 1.2948729763769853,
      "grad_norm": 0.4549506604671478,
      "learning_rate": 5.54768126194185e-06,
      "loss": 0.4355,
      "step": 42152
    },
    {
      "epoch": 1.2949036955119344,
      "grad_norm": 0.3807544708251953,
      "learning_rate": 5.547248533214989e-06,
      "loss": 0.5179,
      "step": 42153
    },
    {
      "epoch": 1.2949344146468835,
      "grad_norm": 0.46765196323394775,
      "learning_rate": 5.546815814887834e-06,
      "loss": 0.4397,
      "step": 42154
    },
    {
      "epoch": 1.2949651337818326,
      "grad_norm": 0.4459429085254669,
      "learning_rate": 5.546383106961403e-06,
      "loss": 0.4943,
      "step": 42155
    },
    {
      "epoch": 1.2949958529167818,
      "grad_norm": 0.4164353013038635,
      "learning_rate": 5.545950409436705e-06,
      "loss": 0.4582,
      "step": 42156
    },
    {
      "epoch": 1.295026572051731,
      "grad_norm": 0.4118843674659729,
      "learning_rate": 5.545517722314755e-06,
      "loss": 0.4746,
      "step": 42157
    },
    {
      "epoch": 1.2950572911866802,
      "grad_norm": 0.3884953558444977,
      "learning_rate": 5.5450850455965555e-06,
      "loss": 0.4346,
      "step": 42158
    },
    {
      "epoch": 1.2950880103216293,
      "grad_norm": 0.39621779322624207,
      "learning_rate": 5.5446523792831205e-06,
      "loss": 0.4283,
      "step": 42159
    },
    {
      "epoch": 1.2951187294565785,
      "grad_norm": 0.413257360458374,
      "learning_rate": 5.544219723375462e-06,
      "loss": 0.5059,
      "step": 42160
    },
    {
      "epoch": 1.2951494485915276,
      "grad_norm": 0.45638975501060486,
      "learning_rate": 5.543787077874593e-06,
      "loss": 0.5224,
      "step": 42161
    },
    {
      "epoch": 1.295180167726477,
      "grad_norm": 0.38300272822380066,
      "learning_rate": 5.5433544427815165e-06,
      "loss": 0.5578,
      "step": 42162
    },
    {
      "epoch": 1.295210886861426,
      "grad_norm": 0.40228334069252014,
      "learning_rate": 5.542921818097246e-06,
      "loss": 0.5249,
      "step": 42163
    },
    {
      "epoch": 1.2952416059963752,
      "grad_norm": 0.42065802216529846,
      "learning_rate": 5.542489203822795e-06,
      "loss": 0.4909,
      "step": 42164
    },
    {
      "epoch": 1.2952723251313243,
      "grad_norm": 0.370631605386734,
      "learning_rate": 5.542056599959175e-06,
      "loss": 0.4857,
      "step": 42165
    },
    {
      "epoch": 1.2953030442662734,
      "grad_norm": 0.4213091731071472,
      "learning_rate": 5.541624006507389e-06,
      "loss": 0.5526,
      "step": 42166
    },
    {
      "epoch": 1.2953337634012225,
      "grad_norm": 0.39452221989631653,
      "learning_rate": 5.54119142346845e-06,
      "loss": 0.4934,
      "step": 42167
    },
    {
      "epoch": 1.2953644825361716,
      "grad_norm": 0.3886728584766388,
      "learning_rate": 5.540758850843372e-06,
      "loss": 0.4855,
      "step": 42168
    },
    {
      "epoch": 1.295395201671121,
      "grad_norm": 0.4007531404495239,
      "learning_rate": 5.540326288633162e-06,
      "loss": 0.4751,
      "step": 42169
    },
    {
      "epoch": 1.29542592080607,
      "grad_norm": 0.37965813279151917,
      "learning_rate": 5.539893736838835e-06,
      "loss": 0.4755,
      "step": 42170
    },
    {
      "epoch": 1.2954566399410192,
      "grad_norm": 0.3921491801738739,
      "learning_rate": 5.539461195461395e-06,
      "loss": 0.4289,
      "step": 42171
    },
    {
      "epoch": 1.2954873590759683,
      "grad_norm": 0.4293600022792816,
      "learning_rate": 5.539028664501854e-06,
      "loss": 0.4639,
      "step": 42172
    },
    {
      "epoch": 1.2955180782109177,
      "grad_norm": 0.39647960662841797,
      "learning_rate": 5.538596143961224e-06,
      "loss": 0.4922,
      "step": 42173
    },
    {
      "epoch": 1.2955487973458668,
      "grad_norm": 0.389241099357605,
      "learning_rate": 5.538163633840518e-06,
      "loss": 0.4977,
      "step": 42174
    },
    {
      "epoch": 1.295579516480816,
      "grad_norm": 0.43133673071861267,
      "learning_rate": 5.537731134140738e-06,
      "loss": 0.4865,
      "step": 42175
    },
    {
      "epoch": 1.295610235615765,
      "grad_norm": 0.4608769118785858,
      "learning_rate": 5.537298644862902e-06,
      "loss": 0.529,
      "step": 42176
    },
    {
      "epoch": 1.2956409547507142,
      "grad_norm": 0.3803505599498749,
      "learning_rate": 5.536866166008009e-06,
      "loss": 0.445,
      "step": 42177
    },
    {
      "epoch": 1.2956716738856633,
      "grad_norm": 0.5604917407035828,
      "learning_rate": 5.536433697577086e-06,
      "loss": 0.4258,
      "step": 42178
    },
    {
      "epoch": 1.2957023930206124,
      "grad_norm": 0.43061697483062744,
      "learning_rate": 5.536001239571128e-06,
      "loss": 0.4806,
      "step": 42179
    },
    {
      "epoch": 1.2957331121555618,
      "grad_norm": 0.39460015296936035,
      "learning_rate": 5.535568791991156e-06,
      "loss": 0.4353,
      "step": 42180
    },
    {
      "epoch": 1.2957638312905109,
      "grad_norm": 0.45538613200187683,
      "learning_rate": 5.5351363548381706e-06,
      "loss": 0.5059,
      "step": 42181
    },
    {
      "epoch": 1.29579455042546,
      "grad_norm": 0.4011426270008087,
      "learning_rate": 5.534703928113187e-06,
      "loss": 0.4961,
      "step": 42182
    },
    {
      "epoch": 1.295825269560409,
      "grad_norm": 0.3734493553638458,
      "learning_rate": 5.534271511817213e-06,
      "loss": 0.4072,
      "step": 42183
    },
    {
      "epoch": 1.2958559886953585,
      "grad_norm": 0.4048285484313965,
      "learning_rate": 5.533839105951264e-06,
      "loss": 0.4731,
      "step": 42184
    },
    {
      "epoch": 1.2958867078303076,
      "grad_norm": 0.381213903427124,
      "learning_rate": 5.533406710516342e-06,
      "loss": 0.5425,
      "step": 42185
    },
    {
      "epoch": 1.2959174269652567,
      "grad_norm": 0.4241441786289215,
      "learning_rate": 5.5329743255134605e-06,
      "loss": 0.4063,
      "step": 42186
    },
    {
      "epoch": 1.2959481461002058,
      "grad_norm": 0.4238724410533905,
      "learning_rate": 5.5325419509436285e-06,
      "loss": 0.4227,
      "step": 42187
    },
    {
      "epoch": 1.295978865235155,
      "grad_norm": 0.4015699625015259,
      "learning_rate": 5.532109586807859e-06,
      "loss": 0.469,
      "step": 42188
    },
    {
      "epoch": 1.296009584370104,
      "grad_norm": 0.41008707880973816,
      "learning_rate": 5.531677233107162e-06,
      "loss": 0.5276,
      "step": 42189
    },
    {
      "epoch": 1.2960403035050532,
      "grad_norm": 0.3788883686065674,
      "learning_rate": 5.5312448898425405e-06,
      "loss": 0.4743,
      "step": 42190
    },
    {
      "epoch": 1.2960710226400025,
      "grad_norm": 0.39659860730171204,
      "learning_rate": 5.53081255701501e-06,
      "loss": 0.4222,
      "step": 42191
    },
    {
      "epoch": 1.2961017417749516,
      "grad_norm": 0.4338480830192566,
      "learning_rate": 5.5303802346255776e-06,
      "loss": 0.4994,
      "step": 42192
    },
    {
      "epoch": 1.2961324609099008,
      "grad_norm": 0.3748171627521515,
      "learning_rate": 5.529947922675258e-06,
      "loss": 0.4988,
      "step": 42193
    },
    {
      "epoch": 1.2961631800448499,
      "grad_norm": 0.4836122393608093,
      "learning_rate": 5.5295156211650545e-06,
      "loss": 0.4792,
      "step": 42194
    },
    {
      "epoch": 1.2961938991797992,
      "grad_norm": 0.4475979804992676,
      "learning_rate": 5.529083330095979e-06,
      "loss": 0.5239,
      "step": 42195
    },
    {
      "epoch": 1.2962246183147483,
      "grad_norm": 0.4527488350868225,
      "learning_rate": 5.528651049469043e-06,
      "loss": 0.5244,
      "step": 42196
    },
    {
      "epoch": 1.2962553374496975,
      "grad_norm": 0.4179275929927826,
      "learning_rate": 5.528218779285257e-06,
      "loss": 0.4228,
      "step": 42197
    },
    {
      "epoch": 1.2962860565846466,
      "grad_norm": 0.4251907467842102,
      "learning_rate": 5.527786519545624e-06,
      "loss": 0.5483,
      "step": 42198
    },
    {
      "epoch": 1.2963167757195957,
      "grad_norm": 0.4349614381790161,
      "learning_rate": 5.52735427025116e-06,
      "loss": 0.5182,
      "step": 42199
    },
    {
      "epoch": 1.2963474948545448,
      "grad_norm": 0.4897672235965729,
      "learning_rate": 5.52692203140287e-06,
      "loss": 0.5175,
      "step": 42200
    },
    {
      "epoch": 1.296378213989494,
      "grad_norm": 0.4033985733985901,
      "learning_rate": 5.526489803001771e-06,
      "loss": 0.5379,
      "step": 42201
    },
    {
      "epoch": 1.2964089331244433,
      "grad_norm": 0.40690675377845764,
      "learning_rate": 5.526057585048864e-06,
      "loss": 0.4611,
      "step": 42202
    },
    {
      "epoch": 1.2964396522593924,
      "grad_norm": 0.4068498909473419,
      "learning_rate": 5.525625377545165e-06,
      "loss": 0.4289,
      "step": 42203
    },
    {
      "epoch": 1.2964703713943415,
      "grad_norm": 0.39587512612342834,
      "learning_rate": 5.525193180491673e-06,
      "loss": 0.419,
      "step": 42204
    },
    {
      "epoch": 1.2965010905292906,
      "grad_norm": 0.41995805501937866,
      "learning_rate": 5.5247609938894095e-06,
      "loss": 0.3912,
      "step": 42205
    },
    {
      "epoch": 1.29653180966424,
      "grad_norm": 0.3704507052898407,
      "learning_rate": 5.524328817739383e-06,
      "loss": 0.5261,
      "step": 42206
    },
    {
      "epoch": 1.296562528799189,
      "grad_norm": 0.39623597264289856,
      "learning_rate": 5.5238966520425955e-06,
      "loss": 0.4766,
      "step": 42207
    },
    {
      "epoch": 1.2965932479341382,
      "grad_norm": 0.5236325860023499,
      "learning_rate": 5.523464496800062e-06,
      "loss": 0.493,
      "step": 42208
    },
    {
      "epoch": 1.2966239670690873,
      "grad_norm": 0.5561297535896301,
      "learning_rate": 5.5230323520127825e-06,
      "loss": 0.4099,
      "step": 42209
    },
    {
      "epoch": 1.2966546862040365,
      "grad_norm": 0.3936104476451874,
      "learning_rate": 5.5226002176817824e-06,
      "loss": 0.3955,
      "step": 42210
    },
    {
      "epoch": 1.2966854053389856,
      "grad_norm": 0.3842028081417084,
      "learning_rate": 5.522168093808058e-06,
      "loss": 0.4571,
      "step": 42211
    },
    {
      "epoch": 1.2967161244739347,
      "grad_norm": 0.3991207480430603,
      "learning_rate": 5.521735980392627e-06,
      "loss": 0.4569,
      "step": 42212
    },
    {
      "epoch": 1.296746843608884,
      "grad_norm": 0.45232802629470825,
      "learning_rate": 5.521303877436486e-06,
      "loss": 0.3964,
      "step": 42213
    },
    {
      "epoch": 1.2967775627438332,
      "grad_norm": 0.4102472960948944,
      "learning_rate": 5.52087178494066e-06,
      "loss": 0.4986,
      "step": 42214
    },
    {
      "epoch": 1.2968082818787823,
      "grad_norm": 0.45244449377059937,
      "learning_rate": 5.520439702906148e-06,
      "loss": 0.5379,
      "step": 42215
    },
    {
      "epoch": 1.2968390010137314,
      "grad_norm": 0.47822287678718567,
      "learning_rate": 5.5200076313339655e-06,
      "loss": 0.5312,
      "step": 42216
    },
    {
      "epoch": 1.2968697201486807,
      "grad_norm": 0.41104501485824585,
      "learning_rate": 5.519575570225114e-06,
      "loss": 0.455,
      "step": 42217
    },
    {
      "epoch": 1.2969004392836299,
      "grad_norm": 0.47049522399902344,
      "learning_rate": 5.519143519580607e-06,
      "loss": 0.4927,
      "step": 42218
    },
    {
      "epoch": 1.296931158418579,
      "grad_norm": 0.39965733885765076,
      "learning_rate": 5.518711479401453e-06,
      "loss": 0.5066,
      "step": 42219
    },
    {
      "epoch": 1.296961877553528,
      "grad_norm": 0.39222484827041626,
      "learning_rate": 5.518279449688664e-06,
      "loss": 0.5094,
      "step": 42220
    },
    {
      "epoch": 1.2969925966884772,
      "grad_norm": 0.3920014798641205,
      "learning_rate": 5.517847430443244e-06,
      "loss": 0.4808,
      "step": 42221
    },
    {
      "epoch": 1.2970233158234263,
      "grad_norm": 0.3896908462047577,
      "learning_rate": 5.517415421666203e-06,
      "loss": 0.4321,
      "step": 42222
    },
    {
      "epoch": 1.2970540349583755,
      "grad_norm": 0.4361540377140045,
      "learning_rate": 5.516983423358553e-06,
      "loss": 0.4706,
      "step": 42223
    },
    {
      "epoch": 1.2970847540933248,
      "grad_norm": 0.40251293778419495,
      "learning_rate": 5.5165514355213005e-06,
      "loss": 0.4286,
      "step": 42224
    },
    {
      "epoch": 1.297115473228274,
      "grad_norm": 0.4032743275165558,
      "learning_rate": 5.516119458155459e-06,
      "loss": 0.3792,
      "step": 42225
    },
    {
      "epoch": 1.297146192363223,
      "grad_norm": 0.36593520641326904,
      "learning_rate": 5.51568749126203e-06,
      "loss": 0.455,
      "step": 42226
    },
    {
      "epoch": 1.2971769114981722,
      "grad_norm": 0.44751691818237305,
      "learning_rate": 5.5152555348420255e-06,
      "loss": 0.4536,
      "step": 42227
    },
    {
      "epoch": 1.2972076306331215,
      "grad_norm": 0.4321749806404114,
      "learning_rate": 5.514823588896456e-06,
      "loss": 0.4145,
      "step": 42228
    },
    {
      "epoch": 1.2972383497680706,
      "grad_norm": 0.3686736524105072,
      "learning_rate": 5.514391653426332e-06,
      "loss": 0.4918,
      "step": 42229
    },
    {
      "epoch": 1.2972690689030197,
      "grad_norm": 0.41661491990089417,
      "learning_rate": 5.5139597284326565e-06,
      "loss": 0.5404,
      "step": 42230
    },
    {
      "epoch": 1.2972997880379689,
      "grad_norm": 0.42734044790267944,
      "learning_rate": 5.51352781391644e-06,
      "loss": 0.4746,
      "step": 42231
    },
    {
      "epoch": 1.297330507172918,
      "grad_norm": 0.424618661403656,
      "learning_rate": 5.513095909878694e-06,
      "loss": 0.4805,
      "step": 42232
    },
    {
      "epoch": 1.297361226307867,
      "grad_norm": 0.39098629355430603,
      "learning_rate": 5.5126640163204305e-06,
      "loss": 0.4875,
      "step": 42233
    },
    {
      "epoch": 1.2973919454428162,
      "grad_norm": 0.48056235909461975,
      "learning_rate": 5.512232133242648e-06,
      "loss": 0.4954,
      "step": 42234
    },
    {
      "epoch": 1.2974226645777656,
      "grad_norm": 0.42070579528808594,
      "learning_rate": 5.511800260646361e-06,
      "loss": 0.4231,
      "step": 42235
    },
    {
      "epoch": 1.2974533837127147,
      "grad_norm": 0.4170009195804596,
      "learning_rate": 5.511368398532578e-06,
      "loss": 0.4293,
      "step": 42236
    },
    {
      "epoch": 1.2974841028476638,
      "grad_norm": 0.38760218024253845,
      "learning_rate": 5.510936546902312e-06,
      "loss": 0.3818,
      "step": 42237
    },
    {
      "epoch": 1.297514821982613,
      "grad_norm": 0.39594709873199463,
      "learning_rate": 5.510504705756563e-06,
      "loss": 0.4345,
      "step": 42238
    },
    {
      "epoch": 1.2975455411175623,
      "grad_norm": 0.43159037828445435,
      "learning_rate": 5.510072875096348e-06,
      "loss": 0.4839,
      "step": 42239
    },
    {
      "epoch": 1.2975762602525114,
      "grad_norm": 0.45724114775657654,
      "learning_rate": 5.5096410549226635e-06,
      "loss": 0.4691,
      "step": 42240
    },
    {
      "epoch": 1.2976069793874605,
      "grad_norm": 0.4109265208244324,
      "learning_rate": 5.50920924523653e-06,
      "loss": 0.4983,
      "step": 42241
    },
    {
      "epoch": 1.2976376985224096,
      "grad_norm": 0.4022829532623291,
      "learning_rate": 5.508777446038955e-06,
      "loss": 0.4731,
      "step": 42242
    },
    {
      "epoch": 1.2976684176573587,
      "grad_norm": 0.4958345890045166,
      "learning_rate": 5.50834565733094e-06,
      "loss": 0.4877,
      "step": 42243
    },
    {
      "epoch": 1.2976991367923079,
      "grad_norm": 0.46686607599258423,
      "learning_rate": 5.507913879113502e-06,
      "loss": 0.4184,
      "step": 42244
    },
    {
      "epoch": 1.297729855927257,
      "grad_norm": 0.405281662940979,
      "learning_rate": 5.507482111387637e-06,
      "loss": 0.4955,
      "step": 42245
    },
    {
      "epoch": 1.2977605750622063,
      "grad_norm": 0.4200589954853058,
      "learning_rate": 5.5070503541543695e-06,
      "loss": 0.479,
      "step": 42246
    },
    {
      "epoch": 1.2977912941971554,
      "grad_norm": 0.43021148443222046,
      "learning_rate": 5.506618607414696e-06,
      "loss": 0.45,
      "step": 42247
    },
    {
      "epoch": 1.2978220133321046,
      "grad_norm": 0.3714936077594757,
      "learning_rate": 5.506186871169631e-06,
      "loss": 0.4437,
      "step": 42248
    },
    {
      "epoch": 1.2978527324670537,
      "grad_norm": 0.38443025946617126,
      "learning_rate": 5.5057551454201776e-06,
      "loss": 0.4171,
      "step": 42249
    },
    {
      "epoch": 1.297883451602003,
      "grad_norm": 0.4102475643157959,
      "learning_rate": 5.505323430167347e-06,
      "loss": 0.4453,
      "step": 42250
    },
    {
      "epoch": 1.2979141707369521,
      "grad_norm": 0.4382143020629883,
      "learning_rate": 5.504891725412147e-06,
      "loss": 0.5414,
      "step": 42251
    },
    {
      "epoch": 1.2979448898719013,
      "grad_norm": 0.37632623314857483,
      "learning_rate": 5.50446003115559e-06,
      "loss": 0.4408,
      "step": 42252
    },
    {
      "epoch": 1.2979756090068504,
      "grad_norm": 0.40257999300956726,
      "learning_rate": 5.504028347398677e-06,
      "loss": 0.4645,
      "step": 42253
    },
    {
      "epoch": 1.2980063281417995,
      "grad_norm": 0.3893128037452698,
      "learning_rate": 5.50359667414242e-06,
      "loss": 0.4982,
      "step": 42254
    },
    {
      "epoch": 1.2980370472767486,
      "grad_norm": 0.4490331709384918,
      "learning_rate": 5.503165011387825e-06,
      "loss": 0.5502,
      "step": 42255
    },
    {
      "epoch": 1.2980677664116977,
      "grad_norm": 0.4319220185279846,
      "learning_rate": 5.502733359135909e-06,
      "loss": 0.5524,
      "step": 42256
    },
    {
      "epoch": 1.298098485546647,
      "grad_norm": 0.4350888729095459,
      "learning_rate": 5.502301717387668e-06,
      "loss": 0.5498,
      "step": 42257
    },
    {
      "epoch": 1.2981292046815962,
      "grad_norm": 0.4104473292827606,
      "learning_rate": 5.501870086144116e-06,
      "loss": 0.4583,
      "step": 42258
    },
    {
      "epoch": 1.2981599238165453,
      "grad_norm": 0.4652780592441559,
      "learning_rate": 5.5014384654062595e-06,
      "loss": 0.4772,
      "step": 42259
    },
    {
      "epoch": 1.2981906429514944,
      "grad_norm": 0.4222147464752197,
      "learning_rate": 5.501006855175108e-06,
      "loss": 0.5075,
      "step": 42260
    },
    {
      "epoch": 1.2982213620864436,
      "grad_norm": 0.40944480895996094,
      "learning_rate": 5.500575255451674e-06,
      "loss": 0.4514,
      "step": 42261
    },
    {
      "epoch": 1.298252081221393,
      "grad_norm": 0.3849930763244629,
      "learning_rate": 5.5001436662369565e-06,
      "loss": 0.4252,
      "step": 42262
    },
    {
      "epoch": 1.298282800356342,
      "grad_norm": 0.4017634391784668,
      "learning_rate": 5.4997120875319676e-06,
      "loss": 0.44,
      "step": 42263
    },
    {
      "epoch": 1.2983135194912911,
      "grad_norm": 0.3932199776172638,
      "learning_rate": 5.499280519337716e-06,
      "loss": 0.4183,
      "step": 42264
    },
    {
      "epoch": 1.2983442386262403,
      "grad_norm": 0.38280385732650757,
      "learning_rate": 5.498848961655211e-06,
      "loss": 0.3974,
      "step": 42265
    },
    {
      "epoch": 1.2983749577611894,
      "grad_norm": 0.45567142963409424,
      "learning_rate": 5.498417414485456e-06,
      "loss": 0.439,
      "step": 42266
    },
    {
      "epoch": 1.2984056768961385,
      "grad_norm": 0.3807850182056427,
      "learning_rate": 5.497985877829461e-06,
      "loss": 0.4241,
      "step": 42267
    },
    {
      "epoch": 1.2984363960310878,
      "grad_norm": 0.3941481113433838,
      "learning_rate": 5.497554351688236e-06,
      "loss": 0.4436,
      "step": 42268
    },
    {
      "epoch": 1.298467115166037,
      "grad_norm": 0.4890660047531128,
      "learning_rate": 5.497122836062789e-06,
      "loss": 0.4161,
      "step": 42269
    },
    {
      "epoch": 1.298497834300986,
      "grad_norm": 0.46827173233032227,
      "learning_rate": 5.496691330954123e-06,
      "loss": 0.4133,
      "step": 42270
    },
    {
      "epoch": 1.2985285534359352,
      "grad_norm": 0.44545167684555054,
      "learning_rate": 5.496259836363253e-06,
      "loss": 0.4577,
      "step": 42271
    },
    {
      "epoch": 1.2985592725708843,
      "grad_norm": 0.42025673389434814,
      "learning_rate": 5.495828352291176e-06,
      "loss": 0.4724,
      "step": 42272
    },
    {
      "epoch": 1.2985899917058337,
      "grad_norm": 0.39902737736701965,
      "learning_rate": 5.495396878738912e-06,
      "loss": 0.5504,
      "step": 42273
    },
    {
      "epoch": 1.2986207108407828,
      "grad_norm": 0.40798220038414,
      "learning_rate": 5.494965415707462e-06,
      "loss": 0.4769,
      "step": 42274
    },
    {
      "epoch": 1.298651429975732,
      "grad_norm": 0.43237951397895813,
      "learning_rate": 5.4945339631978365e-06,
      "loss": 0.4864,
      "step": 42275
    },
    {
      "epoch": 1.298682149110681,
      "grad_norm": 0.42595377564430237,
      "learning_rate": 5.4941025212110355e-06,
      "loss": 0.4475,
      "step": 42276
    },
    {
      "epoch": 1.2987128682456301,
      "grad_norm": 0.43860703706741333,
      "learning_rate": 5.493671089748075e-06,
      "loss": 0.485,
      "step": 42277
    },
    {
      "epoch": 1.2987435873805793,
      "grad_norm": 0.4430026412010193,
      "learning_rate": 5.493239668809964e-06,
      "loss": 0.402,
      "step": 42278
    },
    {
      "epoch": 1.2987743065155284,
      "grad_norm": 0.40827712416648865,
      "learning_rate": 5.492808258397705e-06,
      "loss": 0.4821,
      "step": 42279
    },
    {
      "epoch": 1.2988050256504777,
      "grad_norm": 0.40914952754974365,
      "learning_rate": 5.492376858512309e-06,
      "loss": 0.4915,
      "step": 42280
    },
    {
      "epoch": 1.2988357447854268,
      "grad_norm": 0.5427685379981995,
      "learning_rate": 5.4919454691547745e-06,
      "loss": 0.5141,
      "step": 42281
    },
    {
      "epoch": 1.298866463920376,
      "grad_norm": 0.3803894817829132,
      "learning_rate": 5.4915140903261246e-06,
      "loss": 0.4723,
      "step": 42282
    },
    {
      "epoch": 1.298897183055325,
      "grad_norm": 0.430025190114975,
      "learning_rate": 5.491082722027353e-06,
      "loss": 0.5025,
      "step": 42283
    },
    {
      "epoch": 1.2989279021902744,
      "grad_norm": 0.4084996283054352,
      "learning_rate": 5.490651364259478e-06,
      "loss": 0.4817,
      "step": 42284
    },
    {
      "epoch": 1.2989586213252236,
      "grad_norm": 0.39438509941101074,
      "learning_rate": 5.490220017023498e-06,
      "loss": 0.5377,
      "step": 42285
    },
    {
      "epoch": 1.2989893404601727,
      "grad_norm": 0.4092258810997009,
      "learning_rate": 5.489788680320422e-06,
      "loss": 0.4556,
      "step": 42286
    },
    {
      "epoch": 1.2990200595951218,
      "grad_norm": 0.4437493681907654,
      "learning_rate": 5.489357354151261e-06,
      "loss": 0.4774,
      "step": 42287
    },
    {
      "epoch": 1.299050778730071,
      "grad_norm": 0.4624745547771454,
      "learning_rate": 5.488926038517024e-06,
      "loss": 0.528,
      "step": 42288
    },
    {
      "epoch": 1.29908149786502,
      "grad_norm": 0.3824501931667328,
      "learning_rate": 5.4884947334187124e-06,
      "loss": 0.4403,
      "step": 42289
    },
    {
      "epoch": 1.2991122169999691,
      "grad_norm": 0.3866175413131714,
      "learning_rate": 5.488063438857336e-06,
      "loss": 0.4254,
      "step": 42290
    },
    {
      "epoch": 1.2991429361349185,
      "grad_norm": 0.41783958673477173,
      "learning_rate": 5.487632154833903e-06,
      "loss": 0.4948,
      "step": 42291
    },
    {
      "epoch": 1.2991736552698676,
      "grad_norm": 0.4027010202407837,
      "learning_rate": 5.487200881349424e-06,
      "loss": 0.4958,
      "step": 42292
    },
    {
      "epoch": 1.2992043744048167,
      "grad_norm": 0.41004541516304016,
      "learning_rate": 5.486769618404898e-06,
      "loss": 0.4928,
      "step": 42293
    },
    {
      "epoch": 1.2992350935397659,
      "grad_norm": 0.4274594783782959,
      "learning_rate": 5.4863383660013366e-06,
      "loss": 0.5619,
      "step": 42294
    },
    {
      "epoch": 1.2992658126747152,
      "grad_norm": 0.4116356670856476,
      "learning_rate": 5.485907124139748e-06,
      "loss": 0.474,
      "step": 42295
    },
    {
      "epoch": 1.2992965318096643,
      "grad_norm": 0.43201392889022827,
      "learning_rate": 5.485475892821138e-06,
      "loss": 0.5336,
      "step": 42296
    },
    {
      "epoch": 1.2993272509446134,
      "grad_norm": 0.4453287422657013,
      "learning_rate": 5.485044672046518e-06,
      "loss": 0.5301,
      "step": 42297
    },
    {
      "epoch": 1.2993579700795626,
      "grad_norm": 0.3790174424648285,
      "learning_rate": 5.4846134618168875e-06,
      "loss": 0.4376,
      "step": 42298
    },
    {
      "epoch": 1.2993886892145117,
      "grad_norm": 0.3895552158355713,
      "learning_rate": 5.48418226213326e-06,
      "loss": 0.5355,
      "step": 42299
    },
    {
      "epoch": 1.2994194083494608,
      "grad_norm": 0.3984655439853668,
      "learning_rate": 5.483751072996637e-06,
      "loss": 0.4691,
      "step": 42300
    },
    {
      "epoch": 1.29945012748441,
      "grad_norm": 0.43374449014663696,
      "learning_rate": 5.4833198944080344e-06,
      "loss": 0.5446,
      "step": 42301
    },
    {
      "epoch": 1.2994808466193593,
      "grad_norm": 0.4304262697696686,
      "learning_rate": 5.48288872636845e-06,
      "loss": 0.4441,
      "step": 42302
    },
    {
      "epoch": 1.2995115657543084,
      "grad_norm": 0.43358391523361206,
      "learning_rate": 5.482457568878894e-06,
      "loss": 0.464,
      "step": 42303
    },
    {
      "epoch": 1.2995422848892575,
      "grad_norm": 0.4236341416835785,
      "learning_rate": 5.482026421940373e-06,
      "loss": 0.4693,
      "step": 42304
    },
    {
      "epoch": 1.2995730040242066,
      "grad_norm": 0.5122183561325073,
      "learning_rate": 5.4815952855539e-06,
      "loss": 0.3921,
      "step": 42305
    },
    {
      "epoch": 1.299603723159156,
      "grad_norm": 0.40597376227378845,
      "learning_rate": 5.481164159720471e-06,
      "loss": 0.4795,
      "step": 42306
    },
    {
      "epoch": 1.299634442294105,
      "grad_norm": 0.43754681944847107,
      "learning_rate": 5.480733044441104e-06,
      "loss": 0.5038,
      "step": 42307
    },
    {
      "epoch": 1.2996651614290542,
      "grad_norm": 0.41202229261398315,
      "learning_rate": 5.480301939716793e-06,
      "loss": 0.5149,
      "step": 42308
    },
    {
      "epoch": 1.2996958805640033,
      "grad_norm": 0.402182012796402,
      "learning_rate": 5.47987084554856e-06,
      "loss": 0.5271,
      "step": 42309
    },
    {
      "epoch": 1.2997265996989524,
      "grad_norm": 0.41835516691207886,
      "learning_rate": 5.4794397619374005e-06,
      "loss": 0.5071,
      "step": 42310
    },
    {
      "epoch": 1.2997573188339016,
      "grad_norm": 0.4346546530723572,
      "learning_rate": 5.479008688884328e-06,
      "loss": 0.4581,
      "step": 42311
    },
    {
      "epoch": 1.2997880379688507,
      "grad_norm": 0.46184268593788147,
      "learning_rate": 5.4785776263903444e-06,
      "loss": 0.3998,
      "step": 42312
    },
    {
      "epoch": 1.2998187571038,
      "grad_norm": 0.43023550510406494,
      "learning_rate": 5.478146574456453e-06,
      "loss": 0.4794,
      "step": 42313
    },
    {
      "epoch": 1.2998494762387491,
      "grad_norm": 0.46905964612960815,
      "learning_rate": 5.477715533083675e-06,
      "loss": 0.4177,
      "step": 42314
    },
    {
      "epoch": 1.2998801953736983,
      "grad_norm": 0.412690132856369,
      "learning_rate": 5.477284502273004e-06,
      "loss": 0.422,
      "step": 42315
    },
    {
      "epoch": 1.2999109145086474,
      "grad_norm": 0.3811727464199066,
      "learning_rate": 5.476853482025455e-06,
      "loss": 0.4357,
      "step": 42316
    },
    {
      "epoch": 1.2999416336435967,
      "grad_norm": 0.4084526598453522,
      "learning_rate": 5.4764224723420226e-06,
      "loss": 0.4988,
      "step": 42317
    },
    {
      "epoch": 1.2999723527785458,
      "grad_norm": 0.4188233017921448,
      "learning_rate": 5.475991473223728e-06,
      "loss": 0.5001,
      "step": 42318
    },
    {
      "epoch": 1.300003071913495,
      "grad_norm": 0.44075778126716614,
      "learning_rate": 5.475560484671569e-06,
      "loss": 0.4622,
      "step": 42319
    },
    {
      "epoch": 1.300033791048444,
      "grad_norm": 0.46113643050193787,
      "learning_rate": 5.475129506686559e-06,
      "loss": 0.5269,
      "step": 42320
    },
    {
      "epoch": 1.3000645101833932,
      "grad_norm": 0.42489731311798096,
      "learning_rate": 5.474698539269694e-06,
      "loss": 0.4141,
      "step": 42321
    },
    {
      "epoch": 1.3000952293183423,
      "grad_norm": 0.37401866912841797,
      "learning_rate": 5.474267582421988e-06,
      "loss": 0.4697,
      "step": 42322
    },
    {
      "epoch": 1.3001259484532914,
      "grad_norm": 0.4083457887172699,
      "learning_rate": 5.473836636144445e-06,
      "loss": 0.5135,
      "step": 42323
    },
    {
      "epoch": 1.3001566675882408,
      "grad_norm": 0.4616725742816925,
      "learning_rate": 5.473405700438077e-06,
      "loss": 0.4284,
      "step": 42324
    },
    {
      "epoch": 1.30018738672319,
      "grad_norm": 0.4812386631965637,
      "learning_rate": 5.472974775303883e-06,
      "loss": 0.4747,
      "step": 42325
    },
    {
      "epoch": 1.300218105858139,
      "grad_norm": 0.3822113871574402,
      "learning_rate": 5.472543860742872e-06,
      "loss": 0.4581,
      "step": 42326
    },
    {
      "epoch": 1.3002488249930881,
      "grad_norm": 0.38285619020462036,
      "learning_rate": 5.47211295675605e-06,
      "loss": 0.4854,
      "step": 42327
    },
    {
      "epoch": 1.3002795441280375,
      "grad_norm": 0.4876321256160736,
      "learning_rate": 5.47168206334443e-06,
      "loss": 0.4231,
      "step": 42328
    },
    {
      "epoch": 1.3003102632629866,
      "grad_norm": 0.4295889139175415,
      "learning_rate": 5.47125118050901e-06,
      "loss": 0.4229,
      "step": 42329
    },
    {
      "epoch": 1.3003409823979357,
      "grad_norm": 0.38598406314849854,
      "learning_rate": 5.470820308250796e-06,
      "loss": 0.471,
      "step": 42330
    },
    {
      "epoch": 1.3003717015328848,
      "grad_norm": 0.4456181228160858,
      "learning_rate": 5.470389446570799e-06,
      "loss": 0.4206,
      "step": 42331
    },
    {
      "epoch": 1.300402420667834,
      "grad_norm": 0.40594685077667236,
      "learning_rate": 5.469958595470024e-06,
      "loss": 0.5094,
      "step": 42332
    },
    {
      "epoch": 1.300433139802783,
      "grad_norm": 0.48187148571014404,
      "learning_rate": 5.469527754949481e-06,
      "loss": 0.4496,
      "step": 42333
    },
    {
      "epoch": 1.3004638589377322,
      "grad_norm": 0.4600719213485718,
      "learning_rate": 5.469096925010167e-06,
      "loss": 0.4977,
      "step": 42334
    },
    {
      "epoch": 1.3004945780726815,
      "grad_norm": 0.4288802146911621,
      "learning_rate": 5.4686661056530955e-06,
      "loss": 0.4843,
      "step": 42335
    },
    {
      "epoch": 1.3005252972076307,
      "grad_norm": 0.4085451364517212,
      "learning_rate": 5.46823529687927e-06,
      "loss": 0.5343,
      "step": 42336
    },
    {
      "epoch": 1.3005560163425798,
      "grad_norm": 0.43002861738204956,
      "learning_rate": 5.467804498689701e-06,
      "loss": 0.5151,
      "step": 42337
    },
    {
      "epoch": 1.300586735477529,
      "grad_norm": 0.4099792540073395,
      "learning_rate": 5.467373711085387e-06,
      "loss": 0.4519,
      "step": 42338
    },
    {
      "epoch": 1.3006174546124782,
      "grad_norm": 0.4270269274711609,
      "learning_rate": 5.466942934067339e-06,
      "loss": 0.4981,
      "step": 42339
    },
    {
      "epoch": 1.3006481737474274,
      "grad_norm": 0.38604792952537537,
      "learning_rate": 5.466512167636562e-06,
      "loss": 0.4784,
      "step": 42340
    },
    {
      "epoch": 1.3006788928823765,
      "grad_norm": 0.4126288592815399,
      "learning_rate": 5.466081411794067e-06,
      "loss": 0.4719,
      "step": 42341
    },
    {
      "epoch": 1.3007096120173256,
      "grad_norm": 0.39044997096061707,
      "learning_rate": 5.465650666540851e-06,
      "loss": 0.5168,
      "step": 42342
    },
    {
      "epoch": 1.3007403311522747,
      "grad_norm": 0.4079104959964752,
      "learning_rate": 5.465219931877929e-06,
      "loss": 0.6166,
      "step": 42343
    },
    {
      "epoch": 1.3007710502872238,
      "grad_norm": 0.43567803502082825,
      "learning_rate": 5.464789207806293e-06,
      "loss": 0.4874,
      "step": 42344
    },
    {
      "epoch": 1.300801769422173,
      "grad_norm": 0.43075570464134216,
      "learning_rate": 5.464358494326969e-06,
      "loss": 0.5334,
      "step": 42345
    },
    {
      "epoch": 1.3008324885571223,
      "grad_norm": 0.38164040446281433,
      "learning_rate": 5.463927791440948e-06,
      "loss": 0.5028,
      "step": 42346
    },
    {
      "epoch": 1.3008632076920714,
      "grad_norm": 1.8897156715393066,
      "learning_rate": 5.463497099149242e-06,
      "loss": 0.534,
      "step": 42347
    },
    {
      "epoch": 1.3008939268270205,
      "grad_norm": 0.3848212659358978,
      "learning_rate": 5.463066417452853e-06,
      "loss": 0.497,
      "step": 42348
    },
    {
      "epoch": 1.3009246459619697,
      "grad_norm": 0.4113692045211792,
      "learning_rate": 5.462635746352789e-06,
      "loss": 0.5319,
      "step": 42349
    },
    {
      "epoch": 1.300955365096919,
      "grad_norm": 0.3993660509586334,
      "learning_rate": 5.462205085850057e-06,
      "loss": 0.5052,
      "step": 42350
    },
    {
      "epoch": 1.3009860842318681,
      "grad_norm": 0.3763303756713867,
      "learning_rate": 5.461774435945661e-06,
      "loss": 0.4516,
      "step": 42351
    },
    {
      "epoch": 1.3010168033668172,
      "grad_norm": 0.411658376455307,
      "learning_rate": 5.4613437966406125e-06,
      "loss": 0.5301,
      "step": 42352
    },
    {
      "epoch": 1.3010475225017664,
      "grad_norm": 0.3816780745983124,
      "learning_rate": 5.460913167935908e-06,
      "loss": 0.4577,
      "step": 42353
    },
    {
      "epoch": 1.3010782416367155,
      "grad_norm": 0.4224284887313843,
      "learning_rate": 5.460482549832558e-06,
      "loss": 0.4375,
      "step": 42354
    },
    {
      "epoch": 1.3011089607716646,
      "grad_norm": 0.3959808945655823,
      "learning_rate": 5.460051942331568e-06,
      "loss": 0.4611,
      "step": 42355
    },
    {
      "epoch": 1.3011396799066137,
      "grad_norm": 0.43859392404556274,
      "learning_rate": 5.459621345433948e-06,
      "loss": 0.5232,
      "step": 42356
    },
    {
      "epoch": 1.301170399041563,
      "grad_norm": 0.4008762240409851,
      "learning_rate": 5.459190759140695e-06,
      "loss": 0.4575,
      "step": 42357
    },
    {
      "epoch": 1.3012011181765122,
      "grad_norm": 0.3626902103424072,
      "learning_rate": 5.458760183452818e-06,
      "loss": 0.4361,
      "step": 42358
    },
    {
      "epoch": 1.3012318373114613,
      "grad_norm": 0.3808037042617798,
      "learning_rate": 5.458329618371325e-06,
      "loss": 0.5026,
      "step": 42359
    },
    {
      "epoch": 1.3012625564464104,
      "grad_norm": 0.4325016140937805,
      "learning_rate": 5.457899063897225e-06,
      "loss": 0.4413,
      "step": 42360
    },
    {
      "epoch": 1.3012932755813598,
      "grad_norm": 0.4361099898815155,
      "learning_rate": 5.457468520031515e-06,
      "loss": 0.4793,
      "step": 42361
    },
    {
      "epoch": 1.3013239947163089,
      "grad_norm": 0.4316823184490204,
      "learning_rate": 5.457037986775204e-06,
      "loss": 0.4099,
      "step": 42362
    },
    {
      "epoch": 1.301354713851258,
      "grad_norm": 0.47690442204475403,
      "learning_rate": 5.456607464129297e-06,
      "loss": 0.5299,
      "step": 42363
    },
    {
      "epoch": 1.3013854329862071,
      "grad_norm": 0.4044487476348877,
      "learning_rate": 5.456176952094805e-06,
      "loss": 0.4099,
      "step": 42364
    },
    {
      "epoch": 1.3014161521211562,
      "grad_norm": 0.4151937663555145,
      "learning_rate": 5.455746450672725e-06,
      "loss": 0.448,
      "step": 42365
    },
    {
      "epoch": 1.3014468712561054,
      "grad_norm": 0.4074103832244873,
      "learning_rate": 5.4553159598640685e-06,
      "loss": 0.4773,
      "step": 42366
    },
    {
      "epoch": 1.3014775903910545,
      "grad_norm": 0.40590259432792664,
      "learning_rate": 5.454885479669837e-06,
      "loss": 0.4323,
      "step": 42367
    },
    {
      "epoch": 1.3015083095260038,
      "grad_norm": 0.5056233406066895,
      "learning_rate": 5.454455010091038e-06,
      "loss": 0.4925,
      "step": 42368
    },
    {
      "epoch": 1.301539028660953,
      "grad_norm": 0.41733649373054504,
      "learning_rate": 5.454024551128682e-06,
      "loss": 0.4979,
      "step": 42369
    },
    {
      "epoch": 1.301569747795902,
      "grad_norm": 0.3901437819004059,
      "learning_rate": 5.4535941027837636e-06,
      "loss": 0.4348,
      "step": 42370
    },
    {
      "epoch": 1.3016004669308512,
      "grad_norm": 0.4384543299674988,
      "learning_rate": 5.453163665057295e-06,
      "loss": 0.4478,
      "step": 42371
    },
    {
      "epoch": 1.3016311860658003,
      "grad_norm": 0.4213721752166748,
      "learning_rate": 5.452733237950279e-06,
      "loss": 0.4044,
      "step": 42372
    },
    {
      "epoch": 1.3016619052007496,
      "grad_norm": 0.4028574526309967,
      "learning_rate": 5.452302821463727e-06,
      "loss": 0.5026,
      "step": 42373
    },
    {
      "epoch": 1.3016926243356988,
      "grad_norm": 0.48487207293510437,
      "learning_rate": 5.451872415598636e-06,
      "loss": 0.5178,
      "step": 42374
    },
    {
      "epoch": 1.3017233434706479,
      "grad_norm": 0.38616177439689636,
      "learning_rate": 5.451442020356017e-06,
      "loss": 0.3606,
      "step": 42375
    },
    {
      "epoch": 1.301754062605597,
      "grad_norm": 0.3726234436035156,
      "learning_rate": 5.451011635736866e-06,
      "loss": 0.4459,
      "step": 42376
    },
    {
      "epoch": 1.3017847817405461,
      "grad_norm": 0.41004467010498047,
      "learning_rate": 5.450581261742203e-06,
      "loss": 0.4986,
      "step": 42377
    },
    {
      "epoch": 1.3018155008754952,
      "grad_norm": 0.3734097480773926,
      "learning_rate": 5.45015089837302e-06,
      "loss": 0.4301,
      "step": 42378
    },
    {
      "epoch": 1.3018462200104446,
      "grad_norm": 0.4854162633419037,
      "learning_rate": 5.449720545630332e-06,
      "loss": 0.4828,
      "step": 42379
    },
    {
      "epoch": 1.3018769391453937,
      "grad_norm": 0.424850195646286,
      "learning_rate": 5.449290203515132e-06,
      "loss": 0.4929,
      "step": 42380
    },
    {
      "epoch": 1.3019076582803428,
      "grad_norm": 0.48991653323173523,
      "learning_rate": 5.4488598720284406e-06,
      "loss": 0.5189,
      "step": 42381
    },
    {
      "epoch": 1.301938377415292,
      "grad_norm": 0.42193132638931274,
      "learning_rate": 5.448429551171249e-06,
      "loss": 0.4764,
      "step": 42382
    },
    {
      "epoch": 1.301969096550241,
      "grad_norm": 0.4116247594356537,
      "learning_rate": 5.447999240944574e-06,
      "loss": 0.4959,
      "step": 42383
    },
    {
      "epoch": 1.3019998156851904,
      "grad_norm": 0.5223766565322876,
      "learning_rate": 5.4475689413494104e-06,
      "loss": 0.4416,
      "step": 42384
    },
    {
      "epoch": 1.3020305348201395,
      "grad_norm": 0.4077301323413849,
      "learning_rate": 5.447138652386766e-06,
      "loss": 0.4926,
      "step": 42385
    },
    {
      "epoch": 1.3020612539550886,
      "grad_norm": 0.42579787969589233,
      "learning_rate": 5.446708374057649e-06,
      "loss": 0.4744,
      "step": 42386
    },
    {
      "epoch": 1.3020919730900378,
      "grad_norm": 0.42393070459365845,
      "learning_rate": 5.446278106363061e-06,
      "loss": 0.5193,
      "step": 42387
    },
    {
      "epoch": 1.3021226922249869,
      "grad_norm": 0.37155312299728394,
      "learning_rate": 5.4458478493040135e-06,
      "loss": 0.4462,
      "step": 42388
    },
    {
      "epoch": 1.302153411359936,
      "grad_norm": 0.36981338262557983,
      "learning_rate": 5.4454176028815035e-06,
      "loss": 0.4745,
      "step": 42389
    },
    {
      "epoch": 1.3021841304948851,
      "grad_norm": 0.4624716639518738,
      "learning_rate": 5.444987367096537e-06,
      "loss": 0.5627,
      "step": 42390
    },
    {
      "epoch": 1.3022148496298345,
      "grad_norm": 0.423671156167984,
      "learning_rate": 5.444557141950122e-06,
      "loss": 0.5659,
      "step": 42391
    },
    {
      "epoch": 1.3022455687647836,
      "grad_norm": 0.3979261815547943,
      "learning_rate": 5.444126927443265e-06,
      "loss": 0.4011,
      "step": 42392
    },
    {
      "epoch": 1.3022762878997327,
      "grad_norm": 0.4790208339691162,
      "learning_rate": 5.443696723576963e-06,
      "loss": 0.5367,
      "step": 42393
    },
    {
      "epoch": 1.3023070070346818,
      "grad_norm": 0.41920197010040283,
      "learning_rate": 5.443266530352227e-06,
      "loss": 0.4839,
      "step": 42394
    },
    {
      "epoch": 1.3023377261696312,
      "grad_norm": 0.39614206552505493,
      "learning_rate": 5.442836347770059e-06,
      "loss": 0.4629,
      "step": 42395
    },
    {
      "epoch": 1.3023684453045803,
      "grad_norm": 0.40972867608070374,
      "learning_rate": 5.44240617583147e-06,
      "loss": 0.4601,
      "step": 42396
    },
    {
      "epoch": 1.3023991644395294,
      "grad_norm": 1.4685178995132446,
      "learning_rate": 5.441976014537455e-06,
      "loss": 0.4481,
      "step": 42397
    },
    {
      "epoch": 1.3024298835744785,
      "grad_norm": 0.4273177683353424,
      "learning_rate": 5.441545863889024e-06,
      "loss": 0.5066,
      "step": 42398
    },
    {
      "epoch": 1.3024606027094277,
      "grad_norm": 0.3820396661758423,
      "learning_rate": 5.441115723887181e-06,
      "loss": 0.4362,
      "step": 42399
    },
    {
      "epoch": 1.3024913218443768,
      "grad_norm": 0.4097953736782074,
      "learning_rate": 5.440685594532935e-06,
      "loss": 0.4905,
      "step": 42400
    },
    {
      "epoch": 1.302522040979326,
      "grad_norm": 0.479112833738327,
      "learning_rate": 5.440255475827281e-06,
      "loss": 0.4227,
      "step": 42401
    },
    {
      "epoch": 1.3025527601142752,
      "grad_norm": 0.47057756781578064,
      "learning_rate": 5.43982536777123e-06,
      "loss": 0.4429,
      "step": 42402
    },
    {
      "epoch": 1.3025834792492244,
      "grad_norm": 0.39557945728302,
      "learning_rate": 5.4393952703657835e-06,
      "loss": 0.3878,
      "step": 42403
    },
    {
      "epoch": 1.3026141983841735,
      "grad_norm": 0.42394304275512695,
      "learning_rate": 5.438965183611954e-06,
      "loss": 0.4646,
      "step": 42404
    },
    {
      "epoch": 1.3026449175191226,
      "grad_norm": 0.474673867225647,
      "learning_rate": 5.438535107510734e-06,
      "loss": 0.4483,
      "step": 42405
    },
    {
      "epoch": 1.302675636654072,
      "grad_norm": 0.42046499252319336,
      "learning_rate": 5.438105042063135e-06,
      "loss": 0.4297,
      "step": 42406
    },
    {
      "epoch": 1.302706355789021,
      "grad_norm": 0.43589818477630615,
      "learning_rate": 5.437674987270161e-06,
      "loss": 0.4575,
      "step": 42407
    },
    {
      "epoch": 1.3027370749239702,
      "grad_norm": 0.3919857442378998,
      "learning_rate": 5.437244943132813e-06,
      "loss": 0.4571,
      "step": 42408
    },
    {
      "epoch": 1.3027677940589193,
      "grad_norm": 0.38989344239234924,
      "learning_rate": 5.4368149096521035e-06,
      "loss": 0.487,
      "step": 42409
    },
    {
      "epoch": 1.3027985131938684,
      "grad_norm": 0.39820975065231323,
      "learning_rate": 5.436384886829029e-06,
      "loss": 0.4468,
      "step": 42410
    },
    {
      "epoch": 1.3028292323288175,
      "grad_norm": 0.4692305326461792,
      "learning_rate": 5.4359548746645995e-06,
      "loss": 0.4875,
      "step": 42411
    },
    {
      "epoch": 1.3028599514637667,
      "grad_norm": 0.41472944617271423,
      "learning_rate": 5.435524873159808e-06,
      "loss": 0.4291,
      "step": 42412
    },
    {
      "epoch": 1.302890670598716,
      "grad_norm": 0.4237182140350342,
      "learning_rate": 5.4350948823156745e-06,
      "loss": 0.4913,
      "step": 42413
    },
    {
      "epoch": 1.3029213897336651,
      "grad_norm": 0.4218146800994873,
      "learning_rate": 5.434664902133191e-06,
      "loss": 0.524,
      "step": 42414
    },
    {
      "epoch": 1.3029521088686142,
      "grad_norm": 0.4702317714691162,
      "learning_rate": 5.434234932613372e-06,
      "loss": 0.485,
      "step": 42415
    },
    {
      "epoch": 1.3029828280035634,
      "grad_norm": 0.4329901337623596,
      "learning_rate": 5.433804973757211e-06,
      "loss": 0.4375,
      "step": 42416
    },
    {
      "epoch": 1.3030135471385127,
      "grad_norm": 0.42471426725387573,
      "learning_rate": 5.433375025565717e-06,
      "loss": 0.5196,
      "step": 42417
    },
    {
      "epoch": 1.3030442662734618,
      "grad_norm": 0.4245086908340454,
      "learning_rate": 5.432945088039896e-06,
      "loss": 0.4751,
      "step": 42418
    },
    {
      "epoch": 1.303074985408411,
      "grad_norm": 0.39054426550865173,
      "learning_rate": 5.432515161180754e-06,
      "loss": 0.4666,
      "step": 42419
    },
    {
      "epoch": 1.30310570454336,
      "grad_norm": 0.49389418959617615,
      "learning_rate": 5.432085244989288e-06,
      "loss": 0.5191,
      "step": 42420
    },
    {
      "epoch": 1.3031364236783092,
      "grad_norm": 0.40797290205955505,
      "learning_rate": 5.431655339466506e-06,
      "loss": 0.4778,
      "step": 42421
    },
    {
      "epoch": 1.3031671428132583,
      "grad_norm": 0.5602535605430603,
      "learning_rate": 5.431225444613413e-06,
      "loss": 0.4419,
      "step": 42422
    },
    {
      "epoch": 1.3031978619482074,
      "grad_norm": 0.4095667004585266,
      "learning_rate": 5.43079556043101e-06,
      "loss": 0.4788,
      "step": 42423
    },
    {
      "epoch": 1.3032285810831568,
      "grad_norm": 0.3912084996700287,
      "learning_rate": 5.430365686920308e-06,
      "loss": 0.5107,
      "step": 42424
    },
    {
      "epoch": 1.3032593002181059,
      "grad_norm": 0.474403440952301,
      "learning_rate": 5.429935824082302e-06,
      "loss": 0.461,
      "step": 42425
    },
    {
      "epoch": 1.303290019353055,
      "grad_norm": 0.4664609432220459,
      "learning_rate": 5.429505971918001e-06,
      "loss": 0.4618,
      "step": 42426
    },
    {
      "epoch": 1.3033207384880041,
      "grad_norm": 0.43505987524986267,
      "learning_rate": 5.429076130428405e-06,
      "loss": 0.502,
      "step": 42427
    },
    {
      "epoch": 1.3033514576229535,
      "grad_norm": 0.39051714539527893,
      "learning_rate": 5.428646299614529e-06,
      "loss": 0.4746,
      "step": 42428
    },
    {
      "epoch": 1.3033821767579026,
      "grad_norm": 0.3636322021484375,
      "learning_rate": 5.428216479477362e-06,
      "loss": 0.4874,
      "step": 42429
    },
    {
      "epoch": 1.3034128958928517,
      "grad_norm": 0.39047303795814514,
      "learning_rate": 5.427786670017916e-06,
      "loss": 0.4508,
      "step": 42430
    },
    {
      "epoch": 1.3034436150278008,
      "grad_norm": 0.39498406648635864,
      "learning_rate": 5.427356871237193e-06,
      "loss": 0.4669,
      "step": 42431
    },
    {
      "epoch": 1.30347433416275,
      "grad_norm": 0.45144009590148926,
      "learning_rate": 5.426927083136202e-06,
      "loss": 0.4785,
      "step": 42432
    },
    {
      "epoch": 1.303505053297699,
      "grad_norm": 0.5478301048278809,
      "learning_rate": 5.426497305715938e-06,
      "loss": 0.5227,
      "step": 42433
    },
    {
      "epoch": 1.3035357724326482,
      "grad_norm": 0.39720726013183594,
      "learning_rate": 5.4260675389774085e-06,
      "loss": 0.4303,
      "step": 42434
    },
    {
      "epoch": 1.3035664915675975,
      "grad_norm": 0.4429178237915039,
      "learning_rate": 5.425637782921618e-06,
      "loss": 0.4689,
      "step": 42435
    },
    {
      "epoch": 1.3035972107025466,
      "grad_norm": 0.44062885642051697,
      "learning_rate": 5.425208037549573e-06,
      "loss": 0.4261,
      "step": 42436
    },
    {
      "epoch": 1.3036279298374958,
      "grad_norm": 0.43026211857795715,
      "learning_rate": 5.4247783028622715e-06,
      "loss": 0.5134,
      "step": 42437
    },
    {
      "epoch": 1.3036586489724449,
      "grad_norm": 0.41395601630210876,
      "learning_rate": 5.424348578860723e-06,
      "loss": 0.4773,
      "step": 42438
    },
    {
      "epoch": 1.3036893681073942,
      "grad_norm": 0.36474695801734924,
      "learning_rate": 5.42391886554592e-06,
      "loss": 0.4258,
      "step": 42439
    },
    {
      "epoch": 1.3037200872423433,
      "grad_norm": 0.38941335678100586,
      "learning_rate": 5.423489162918883e-06,
      "loss": 0.5202,
      "step": 42440
    },
    {
      "epoch": 1.3037508063772925,
      "grad_norm": 0.3952350318431854,
      "learning_rate": 5.4230594709806e-06,
      "loss": 0.4976,
      "step": 42441
    },
    {
      "epoch": 1.3037815255122416,
      "grad_norm": 0.4047510027885437,
      "learning_rate": 5.4226297897320846e-06,
      "loss": 0.4869,
      "step": 42442
    },
    {
      "epoch": 1.3038122446471907,
      "grad_norm": 0.40714529156684875,
      "learning_rate": 5.422200119174336e-06,
      "loss": 0.4166,
      "step": 42443
    },
    {
      "epoch": 1.3038429637821398,
      "grad_norm": 0.4394797086715698,
      "learning_rate": 5.421770459308357e-06,
      "loss": 0.4417,
      "step": 42444
    },
    {
      "epoch": 1.303873682917089,
      "grad_norm": 0.44910314679145813,
      "learning_rate": 5.421340810135158e-06,
      "loss": 0.4379,
      "step": 42445
    },
    {
      "epoch": 1.3039044020520383,
      "grad_norm": 0.4745805561542511,
      "learning_rate": 5.420911171655734e-06,
      "loss": 0.5106,
      "step": 42446
    },
    {
      "epoch": 1.3039351211869874,
      "grad_norm": 0.42603829503059387,
      "learning_rate": 5.420481543871096e-06,
      "loss": 0.4726,
      "step": 42447
    },
    {
      "epoch": 1.3039658403219365,
      "grad_norm": 0.47645455598831177,
      "learning_rate": 5.420051926782235e-06,
      "loss": 0.4857,
      "step": 42448
    },
    {
      "epoch": 1.3039965594568856,
      "grad_norm": 0.4626072645187378,
      "learning_rate": 5.41962232039017e-06,
      "loss": 0.4031,
      "step": 42449
    },
    {
      "epoch": 1.304027278591835,
      "grad_norm": 0.3732830584049225,
      "learning_rate": 5.419192724695892e-06,
      "loss": 0.446,
      "step": 42450
    },
    {
      "epoch": 1.304057997726784,
      "grad_norm": 0.38591432571411133,
      "learning_rate": 5.418763139700414e-06,
      "loss": 0.4676,
      "step": 42451
    },
    {
      "epoch": 1.3040887168617332,
      "grad_norm": 0.4478744566440582,
      "learning_rate": 5.418333565404732e-06,
      "loss": 0.52,
      "step": 42452
    },
    {
      "epoch": 1.3041194359966823,
      "grad_norm": 0.434937059879303,
      "learning_rate": 5.417904001809851e-06,
      "loss": 0.5489,
      "step": 42453
    },
    {
      "epoch": 1.3041501551316315,
      "grad_norm": 0.42087313532829285,
      "learning_rate": 5.417474448916774e-06,
      "loss": 0.5903,
      "step": 42454
    },
    {
      "epoch": 1.3041808742665806,
      "grad_norm": 0.4271734356880188,
      "learning_rate": 5.41704490672651e-06,
      "loss": 0.4554,
      "step": 42455
    },
    {
      "epoch": 1.3042115934015297,
      "grad_norm": 0.3900874853134155,
      "learning_rate": 5.416615375240055e-06,
      "loss": 0.5077,
      "step": 42456
    },
    {
      "epoch": 1.304242312536479,
      "grad_norm": 0.5443843603134155,
      "learning_rate": 5.416185854458413e-06,
      "loss": 0.4474,
      "step": 42457
    },
    {
      "epoch": 1.3042730316714282,
      "grad_norm": 0.3974962532520294,
      "learning_rate": 5.415756344382591e-06,
      "loss": 0.4456,
      "step": 42458
    },
    {
      "epoch": 1.3043037508063773,
      "grad_norm": 0.3877031207084656,
      "learning_rate": 5.41532684501359e-06,
      "loss": 0.459,
      "step": 42459
    },
    {
      "epoch": 1.3043344699413264,
      "grad_norm": 0.463243693113327,
      "learning_rate": 5.414897356352416e-06,
      "loss": 0.4577,
      "step": 42460
    },
    {
      "epoch": 1.3043651890762757,
      "grad_norm": 0.40786606073379517,
      "learning_rate": 5.414467878400067e-06,
      "loss": 0.5269,
      "step": 42461
    },
    {
      "epoch": 1.3043959082112249,
      "grad_norm": 0.3702569007873535,
      "learning_rate": 5.414038411157547e-06,
      "loss": 0.3646,
      "step": 42462
    },
    {
      "epoch": 1.304426627346174,
      "grad_norm": 0.40754497051239014,
      "learning_rate": 5.413608954625862e-06,
      "loss": 0.4777,
      "step": 42463
    },
    {
      "epoch": 1.304457346481123,
      "grad_norm": 0.3956259489059448,
      "learning_rate": 5.413179508806017e-06,
      "loss": 0.4844,
      "step": 42464
    },
    {
      "epoch": 1.3044880656160722,
      "grad_norm": 0.4176926612854004,
      "learning_rate": 5.412750073699007e-06,
      "loss": 0.507,
      "step": 42465
    },
    {
      "epoch": 1.3045187847510213,
      "grad_norm": 0.40567144751548767,
      "learning_rate": 5.41232064930584e-06,
      "loss": 0.5097,
      "step": 42466
    },
    {
      "epoch": 1.3045495038859705,
      "grad_norm": 0.40752357244491577,
      "learning_rate": 5.411891235627518e-06,
      "loss": 0.4502,
      "step": 42467
    },
    {
      "epoch": 1.3045802230209198,
      "grad_norm": 0.42399582266807556,
      "learning_rate": 5.411461832665049e-06,
      "loss": 0.5067,
      "step": 42468
    },
    {
      "epoch": 1.304610942155869,
      "grad_norm": 0.43569713830947876,
      "learning_rate": 5.411032440419428e-06,
      "loss": 0.5829,
      "step": 42469
    },
    {
      "epoch": 1.304641661290818,
      "grad_norm": 0.4300026595592499,
      "learning_rate": 5.41060305889166e-06,
      "loss": 0.4755,
      "step": 42470
    },
    {
      "epoch": 1.3046723804257672,
      "grad_norm": 0.42310962080955505,
      "learning_rate": 5.410173688082749e-06,
      "loss": 0.4613,
      "step": 42471
    },
    {
      "epoch": 1.3047030995607165,
      "grad_norm": 0.4167174696922302,
      "learning_rate": 5.409744327993703e-06,
      "loss": 0.4429,
      "step": 42472
    },
    {
      "epoch": 1.3047338186956656,
      "grad_norm": 0.4044923782348633,
      "learning_rate": 5.409314978625516e-06,
      "loss": 0.4705,
      "step": 42473
    },
    {
      "epoch": 1.3047645378306147,
      "grad_norm": 0.428064227104187,
      "learning_rate": 5.408885639979198e-06,
      "loss": 0.5438,
      "step": 42474
    },
    {
      "epoch": 1.3047952569655639,
      "grad_norm": 0.44923457503318787,
      "learning_rate": 5.40845631205574e-06,
      "loss": 0.5011,
      "step": 42475
    },
    {
      "epoch": 1.304825976100513,
      "grad_norm": 0.4330291152000427,
      "learning_rate": 5.408026994856161e-06,
      "loss": 0.4144,
      "step": 42476
    },
    {
      "epoch": 1.304856695235462,
      "grad_norm": 0.3917180299758911,
      "learning_rate": 5.407597688381452e-06,
      "loss": 0.422,
      "step": 42477
    },
    {
      "epoch": 1.3048874143704112,
      "grad_norm": 0.38786253333091736,
      "learning_rate": 5.407168392632618e-06,
      "loss": 0.5312,
      "step": 42478
    },
    {
      "epoch": 1.3049181335053606,
      "grad_norm": 0.4066873788833618,
      "learning_rate": 5.406739107610663e-06,
      "loss": 0.5245,
      "step": 42479
    },
    {
      "epoch": 1.3049488526403097,
      "grad_norm": 0.3824012577533722,
      "learning_rate": 5.406309833316592e-06,
      "loss": 0.5219,
      "step": 42480
    },
    {
      "epoch": 1.3049795717752588,
      "grad_norm": 0.39153414964675903,
      "learning_rate": 5.4058805697514075e-06,
      "loss": 0.4957,
      "step": 42481
    },
    {
      "epoch": 1.305010290910208,
      "grad_norm": 0.4070786237716675,
      "learning_rate": 5.405451316916106e-06,
      "loss": 0.4553,
      "step": 42482
    },
    {
      "epoch": 1.305041010045157,
      "grad_norm": 0.38910016417503357,
      "learning_rate": 5.405022074811697e-06,
      "loss": 0.4224,
      "step": 42483
    },
    {
      "epoch": 1.3050717291801064,
      "grad_norm": 0.3864019513130188,
      "learning_rate": 5.404592843439173e-06,
      "loss": 0.4591,
      "step": 42484
    },
    {
      "epoch": 1.3051024483150555,
      "grad_norm": 0.4165723919868469,
      "learning_rate": 5.404163622799551e-06,
      "loss": 0.5177,
      "step": 42485
    },
    {
      "epoch": 1.3051331674500046,
      "grad_norm": 0.43934929370880127,
      "learning_rate": 5.403734412893822e-06,
      "loss": 0.5132,
      "step": 42486
    },
    {
      "epoch": 1.3051638865849537,
      "grad_norm": 0.4275989830493927,
      "learning_rate": 5.403305213722996e-06,
      "loss": 0.5344,
      "step": 42487
    },
    {
      "epoch": 1.3051946057199029,
      "grad_norm": 0.4121732711791992,
      "learning_rate": 5.402876025288068e-06,
      "loss": 0.5248,
      "step": 42488
    },
    {
      "epoch": 1.305225324854852,
      "grad_norm": 0.44274309277534485,
      "learning_rate": 5.4024468475900435e-06,
      "loss": 0.4482,
      "step": 42489
    },
    {
      "epoch": 1.3052560439898013,
      "grad_norm": 0.4030844271183014,
      "learning_rate": 5.402017680629926e-06,
      "loss": 0.4329,
      "step": 42490
    },
    {
      "epoch": 1.3052867631247504,
      "grad_norm": 0.4165971577167511,
      "learning_rate": 5.401588524408721e-06,
      "loss": 0.5111,
      "step": 42491
    },
    {
      "epoch": 1.3053174822596996,
      "grad_norm": 0.49274951219558716,
      "learning_rate": 5.401159378927423e-06,
      "loss": 0.496,
      "step": 42492
    },
    {
      "epoch": 1.3053482013946487,
      "grad_norm": 0.377573162317276,
      "learning_rate": 5.40073024418704e-06,
      "loss": 0.4373,
      "step": 42493
    },
    {
      "epoch": 1.3053789205295978,
      "grad_norm": 0.44853371381759644,
      "learning_rate": 5.400301120188571e-06,
      "loss": 0.5138,
      "step": 42494
    },
    {
      "epoch": 1.3054096396645472,
      "grad_norm": 0.4149838984012604,
      "learning_rate": 5.399872006933025e-06,
      "loss": 0.4999,
      "step": 42495
    },
    {
      "epoch": 1.3054403587994963,
      "grad_norm": 0.4123440086841583,
      "learning_rate": 5.399442904421395e-06,
      "loss": 0.5325,
      "step": 42496
    },
    {
      "epoch": 1.3054710779344454,
      "grad_norm": 0.43698033690452576,
      "learning_rate": 5.399013812654686e-06,
      "loss": 0.4809,
      "step": 42497
    },
    {
      "epoch": 1.3055017970693945,
      "grad_norm": 0.4187549650669098,
      "learning_rate": 5.398584731633903e-06,
      "loss": 0.4796,
      "step": 42498
    },
    {
      "epoch": 1.3055325162043436,
      "grad_norm": 0.4189584255218506,
      "learning_rate": 5.398155661360047e-06,
      "loss": 0.4946,
      "step": 42499
    },
    {
      "epoch": 1.3055632353392927,
      "grad_norm": 0.46836593747138977,
      "learning_rate": 5.3977266018341236e-06,
      "loss": 0.4983,
      "step": 42500
    },
    {
      "epoch": 1.3055939544742419,
      "grad_norm": 0.4159368574619293,
      "learning_rate": 5.3972975530571255e-06,
      "loss": 0.4809,
      "step": 42501
    },
    {
      "epoch": 1.3056246736091912,
      "grad_norm": 0.4546613097190857,
      "learning_rate": 5.396868515030062e-06,
      "loss": 0.5133,
      "step": 42502
    },
    {
      "epoch": 1.3056553927441403,
      "grad_norm": 0.4236294627189636,
      "learning_rate": 5.3964394877539325e-06,
      "loss": 0.4482,
      "step": 42503
    },
    {
      "epoch": 1.3056861118790895,
      "grad_norm": 0.41294899582862854,
      "learning_rate": 5.396010471229746e-06,
      "loss": 0.497,
      "step": 42504
    },
    {
      "epoch": 1.3057168310140386,
      "grad_norm": 0.42581796646118164,
      "learning_rate": 5.395581465458493e-06,
      "loss": 0.5272,
      "step": 42505
    },
    {
      "epoch": 1.305747550148988,
      "grad_norm": 0.3980206251144409,
      "learning_rate": 5.3951524704411815e-06,
      "loss": 0.4909,
      "step": 42506
    },
    {
      "epoch": 1.305778269283937,
      "grad_norm": 0.4247293174266815,
      "learning_rate": 5.394723486178812e-06,
      "loss": 0.4598,
      "step": 42507
    },
    {
      "epoch": 1.3058089884188862,
      "grad_norm": 0.4178262948989868,
      "learning_rate": 5.394294512672393e-06,
      "loss": 0.4364,
      "step": 42508
    },
    {
      "epoch": 1.3058397075538353,
      "grad_norm": 0.39735084772109985,
      "learning_rate": 5.3938655499229165e-06,
      "loss": 0.4682,
      "step": 42509
    },
    {
      "epoch": 1.3058704266887844,
      "grad_norm": 0.3937684893608093,
      "learning_rate": 5.393436597931392e-06,
      "loss": 0.4853,
      "step": 42510
    },
    {
      "epoch": 1.3059011458237335,
      "grad_norm": 0.43440771102905273,
      "learning_rate": 5.393007656698811e-06,
      "loss": 0.5128,
      "step": 42511
    },
    {
      "epoch": 1.3059318649586826,
      "grad_norm": 0.3933832347393036,
      "learning_rate": 5.39257872622619e-06,
      "loss": 0.4568,
      "step": 42512
    },
    {
      "epoch": 1.305962584093632,
      "grad_norm": 0.3914310336112976,
      "learning_rate": 5.392149806514519e-06,
      "loss": 0.4428,
      "step": 42513
    },
    {
      "epoch": 1.305993303228581,
      "grad_norm": 0.3817065954208374,
      "learning_rate": 5.3917208975648036e-06,
      "loss": 0.4515,
      "step": 42514
    },
    {
      "epoch": 1.3060240223635302,
      "grad_norm": 0.4177383482456207,
      "learning_rate": 5.39129199937805e-06,
      "loss": 0.4655,
      "step": 42515
    },
    {
      "epoch": 1.3060547414984793,
      "grad_norm": 0.38451385498046875,
      "learning_rate": 5.390863111955249e-06,
      "loss": 0.4395,
      "step": 42516
    },
    {
      "epoch": 1.3060854606334287,
      "grad_norm": 0.3927903175354004,
      "learning_rate": 5.390434235297415e-06,
      "loss": 0.4813,
      "step": 42517
    },
    {
      "epoch": 1.3061161797683778,
      "grad_norm": 0.3930603563785553,
      "learning_rate": 5.390005369405542e-06,
      "loss": 0.4883,
      "step": 42518
    },
    {
      "epoch": 1.306146898903327,
      "grad_norm": 0.44124671816825867,
      "learning_rate": 5.389576514280637e-06,
      "loss": 0.4766,
      "step": 42519
    },
    {
      "epoch": 1.306177618038276,
      "grad_norm": 0.36802852153778076,
      "learning_rate": 5.389147669923689e-06,
      "loss": 0.4135,
      "step": 42520
    },
    {
      "epoch": 1.3062083371732252,
      "grad_norm": 0.4486698508262634,
      "learning_rate": 5.3887188363357155e-06,
      "loss": 0.4931,
      "step": 42521
    },
    {
      "epoch": 1.3062390563081743,
      "grad_norm": 0.4594332277774811,
      "learning_rate": 5.38829001351771e-06,
      "loss": 0.4945,
      "step": 42522
    },
    {
      "epoch": 1.3062697754431234,
      "grad_norm": 0.40427881479263306,
      "learning_rate": 5.387861201470677e-06,
      "loss": 0.4061,
      "step": 42523
    },
    {
      "epoch": 1.3063004945780727,
      "grad_norm": 0.42185404896736145,
      "learning_rate": 5.387432400195614e-06,
      "loss": 0.4678,
      "step": 42524
    },
    {
      "epoch": 1.3063312137130219,
      "grad_norm": 0.42876332998275757,
      "learning_rate": 5.3870036096935244e-06,
      "loss": 0.5024,
      "step": 42525
    },
    {
      "epoch": 1.306361932847971,
      "grad_norm": 0.4072101414203644,
      "learning_rate": 5.386574829965409e-06,
      "loss": 0.5364,
      "step": 42526
    },
    {
      "epoch": 1.30639265198292,
      "grad_norm": 0.3898715078830719,
      "learning_rate": 5.386146061012274e-06,
      "loss": 0.4562,
      "step": 42527
    },
    {
      "epoch": 1.3064233711178694,
      "grad_norm": 0.42969605326652527,
      "learning_rate": 5.385717302835114e-06,
      "loss": 0.4611,
      "step": 42528
    },
    {
      "epoch": 1.3064540902528186,
      "grad_norm": 0.3730052411556244,
      "learning_rate": 5.3852885554349345e-06,
      "loss": 0.4967,
      "step": 42529
    },
    {
      "epoch": 1.3064848093877677,
      "grad_norm": 0.41483864188194275,
      "learning_rate": 5.384859818812735e-06,
      "loss": 0.5536,
      "step": 42530
    },
    {
      "epoch": 1.3065155285227168,
      "grad_norm": 0.398539274930954,
      "learning_rate": 5.384431092969522e-06,
      "loss": 0.511,
      "step": 42531
    },
    {
      "epoch": 1.306546247657666,
      "grad_norm": 0.4177848994731903,
      "learning_rate": 5.384002377906288e-06,
      "loss": 0.5093,
      "step": 42532
    },
    {
      "epoch": 1.306576966792615,
      "grad_norm": 0.40582361817359924,
      "learning_rate": 5.383573673624038e-06,
      "loss": 0.5089,
      "step": 42533
    },
    {
      "epoch": 1.3066076859275642,
      "grad_norm": 0.46962660551071167,
      "learning_rate": 5.3831449801237755e-06,
      "loss": 0.4349,
      "step": 42534
    },
    {
      "epoch": 1.3066384050625135,
      "grad_norm": 0.3948937952518463,
      "learning_rate": 5.3827162974065e-06,
      "loss": 0.4454,
      "step": 42535
    },
    {
      "epoch": 1.3066691241974626,
      "grad_norm": 0.39397215843200684,
      "learning_rate": 5.382287625473217e-06,
      "loss": 0.4059,
      "step": 42536
    },
    {
      "epoch": 1.3066998433324117,
      "grad_norm": 0.37065058946609497,
      "learning_rate": 5.38185896432492e-06,
      "loss": 0.4191,
      "step": 42537
    },
    {
      "epoch": 1.3067305624673609,
      "grad_norm": 0.468942791223526,
      "learning_rate": 5.381430313962612e-06,
      "loss": 0.4573,
      "step": 42538
    },
    {
      "epoch": 1.3067612816023102,
      "grad_norm": 0.4110507667064667,
      "learning_rate": 5.381001674387299e-06,
      "loss": 0.4934,
      "step": 42539
    },
    {
      "epoch": 1.3067920007372593,
      "grad_norm": 0.3913099467754364,
      "learning_rate": 5.3805730455999815e-06,
      "loss": 0.4258,
      "step": 42540
    },
    {
      "epoch": 1.3068227198722084,
      "grad_norm": 0.45302751660346985,
      "learning_rate": 5.380144427601655e-06,
      "loss": 0.4817,
      "step": 42541
    },
    {
      "epoch": 1.3068534390071576,
      "grad_norm": 0.39431867003440857,
      "learning_rate": 5.379715820393323e-06,
      "loss": 0.4433,
      "step": 42542
    },
    {
      "epoch": 1.3068841581421067,
      "grad_norm": 0.4001004993915558,
      "learning_rate": 5.379287223975989e-06,
      "loss": 0.5182,
      "step": 42543
    },
    {
      "epoch": 1.3069148772770558,
      "grad_norm": 0.41938984394073486,
      "learning_rate": 5.378858638350655e-06,
      "loss": 0.5308,
      "step": 42544
    },
    {
      "epoch": 1.306945596412005,
      "grad_norm": 0.43020012974739075,
      "learning_rate": 5.378430063518314e-06,
      "loss": 0.442,
      "step": 42545
    },
    {
      "epoch": 1.3069763155469543,
      "grad_norm": 0.42293015122413635,
      "learning_rate": 5.378001499479979e-06,
      "loss": 0.5345,
      "step": 42546
    },
    {
      "epoch": 1.3070070346819034,
      "grad_norm": 0.4117324650287628,
      "learning_rate": 5.3775729462366355e-06,
      "loss": 0.514,
      "step": 42547
    },
    {
      "epoch": 1.3070377538168525,
      "grad_norm": 0.4405096173286438,
      "learning_rate": 5.377144403789301e-06,
      "loss": 0.4875,
      "step": 42548
    },
    {
      "epoch": 1.3070684729518016,
      "grad_norm": 0.43963807821273804,
      "learning_rate": 5.376715872138965e-06,
      "loss": 0.5085,
      "step": 42549
    },
    {
      "epoch": 1.307099192086751,
      "grad_norm": 0.7971407771110535,
      "learning_rate": 5.376287351286634e-06,
      "loss": 0.4479,
      "step": 42550
    },
    {
      "epoch": 1.3071299112217,
      "grad_norm": 0.403226375579834,
      "learning_rate": 5.375858841233305e-06,
      "loss": 0.5845,
      "step": 42551
    },
    {
      "epoch": 1.3071606303566492,
      "grad_norm": 0.3927215337753296,
      "learning_rate": 5.375430341979976e-06,
      "loss": 0.4749,
      "step": 42552
    },
    {
      "epoch": 1.3071913494915983,
      "grad_norm": 0.42108750343322754,
      "learning_rate": 5.375001853527659e-06,
      "loss": 0.4483,
      "step": 42553
    },
    {
      "epoch": 1.3072220686265474,
      "grad_norm": 0.40603452920913696,
      "learning_rate": 5.374573375877346e-06,
      "loss": 0.5741,
      "step": 42554
    },
    {
      "epoch": 1.3072527877614966,
      "grad_norm": 0.3997979164123535,
      "learning_rate": 5.3741449090300435e-06,
      "loss": 0.4768,
      "step": 42555
    },
    {
      "epoch": 1.3072835068964457,
      "grad_norm": 0.38790684938430786,
      "learning_rate": 5.373716452986745e-06,
      "loss": 0.4704,
      "step": 42556
    },
    {
      "epoch": 1.307314226031395,
      "grad_norm": 0.4605218768119812,
      "learning_rate": 5.373288007748454e-06,
      "loss": 0.4845,
      "step": 42557
    },
    {
      "epoch": 1.3073449451663441,
      "grad_norm": 0.4413481056690216,
      "learning_rate": 5.3728595733161725e-06,
      "loss": 0.4503,
      "step": 42558
    },
    {
      "epoch": 1.3073756643012933,
      "grad_norm": 0.4315873682498932,
      "learning_rate": 5.372431149690904e-06,
      "loss": 0.3755,
      "step": 42559
    },
    {
      "epoch": 1.3074063834362424,
      "grad_norm": 0.4216564893722534,
      "learning_rate": 5.372002736873643e-06,
      "loss": 0.4493,
      "step": 42560
    },
    {
      "epoch": 1.3074371025711917,
      "grad_norm": 0.4119024872779846,
      "learning_rate": 5.371574334865392e-06,
      "loss": 0.479,
      "step": 42561
    },
    {
      "epoch": 1.3074678217061408,
      "grad_norm": 0.4671129584312439,
      "learning_rate": 5.371145943667153e-06,
      "loss": 0.5454,
      "step": 42562
    },
    {
      "epoch": 1.30749854084109,
      "grad_norm": 0.37286025285720825,
      "learning_rate": 5.3707175632799295e-06,
      "loss": 0.4293,
      "step": 42563
    },
    {
      "epoch": 1.307529259976039,
      "grad_norm": 0.49267062544822693,
      "learning_rate": 5.370289193704714e-06,
      "loss": 0.5336,
      "step": 42564
    },
    {
      "epoch": 1.3075599791109882,
      "grad_norm": 0.4087550640106201,
      "learning_rate": 5.3698608349425106e-06,
      "loss": 0.5088,
      "step": 42565
    },
    {
      "epoch": 1.3075906982459373,
      "grad_norm": 0.46848663687705994,
      "learning_rate": 5.369432486994323e-06,
      "loss": 0.4843,
      "step": 42566
    },
    {
      "epoch": 1.3076214173808864,
      "grad_norm": 0.41691723465919495,
      "learning_rate": 5.3690041498611524e-06,
      "loss": 0.4435,
      "step": 42567
    },
    {
      "epoch": 1.3076521365158358,
      "grad_norm": 0.46701422333717346,
      "learning_rate": 5.3685758235439915e-06,
      "loss": 0.4101,
      "step": 42568
    },
    {
      "epoch": 1.307682855650785,
      "grad_norm": 0.3844689428806305,
      "learning_rate": 5.3681475080438436e-06,
      "loss": 0.4803,
      "step": 42569
    },
    {
      "epoch": 1.307713574785734,
      "grad_norm": 0.40608516335487366,
      "learning_rate": 5.367719203361713e-06,
      "loss": 0.5484,
      "step": 42570
    },
    {
      "epoch": 1.3077442939206831,
      "grad_norm": 0.4208899438381195,
      "learning_rate": 5.367290909498597e-06,
      "loss": 0.5023,
      "step": 42571
    },
    {
      "epoch": 1.3077750130556325,
      "grad_norm": 0.39823925495147705,
      "learning_rate": 5.366862626455501e-06,
      "loss": 0.4823,
      "step": 42572
    },
    {
      "epoch": 1.3078057321905816,
      "grad_norm": 0.39135411381721497,
      "learning_rate": 5.366434354233416e-06,
      "loss": 0.439,
      "step": 42573
    },
    {
      "epoch": 1.3078364513255307,
      "grad_norm": 0.42668959498405457,
      "learning_rate": 5.366006092833349e-06,
      "loss": 0.4807,
      "step": 42574
    },
    {
      "epoch": 1.3078671704604798,
      "grad_norm": 0.38246726989746094,
      "learning_rate": 5.3655778422562976e-06,
      "loss": 0.53,
      "step": 42575
    },
    {
      "epoch": 1.307897889595429,
      "grad_norm": 0.44300132989883423,
      "learning_rate": 5.365149602503265e-06,
      "loss": 0.4332,
      "step": 42576
    },
    {
      "epoch": 1.307928608730378,
      "grad_norm": 0.43537816405296326,
      "learning_rate": 5.364721373575248e-06,
      "loss": 0.5821,
      "step": 42577
    },
    {
      "epoch": 1.3079593278653272,
      "grad_norm": 0.46560347080230713,
      "learning_rate": 5.36429315547325e-06,
      "loss": 0.4979,
      "step": 42578
    },
    {
      "epoch": 1.3079900470002765,
      "grad_norm": 0.4370120167732239,
      "learning_rate": 5.363864948198261e-06,
      "loss": 0.4881,
      "step": 42579
    },
    {
      "epoch": 1.3080207661352257,
      "grad_norm": 0.4005051851272583,
      "learning_rate": 5.363436751751299e-06,
      "loss": 0.4751,
      "step": 42580
    },
    {
      "epoch": 1.3080514852701748,
      "grad_norm": 0.37116575241088867,
      "learning_rate": 5.3630085661333485e-06,
      "loss": 0.4844,
      "step": 42581
    },
    {
      "epoch": 1.308082204405124,
      "grad_norm": 0.5089971423149109,
      "learning_rate": 5.36258039134542e-06,
      "loss": 0.4004,
      "step": 42582
    },
    {
      "epoch": 1.3081129235400732,
      "grad_norm": 0.40713295340538025,
      "learning_rate": 5.362152227388501e-06,
      "loss": 0.4545,
      "step": 42583
    },
    {
      "epoch": 1.3081436426750224,
      "grad_norm": 0.4280870854854584,
      "learning_rate": 5.3617240742636065e-06,
      "loss": 0.4832,
      "step": 42584
    },
    {
      "epoch": 1.3081743618099715,
      "grad_norm": 0.39473798871040344,
      "learning_rate": 5.361295931971726e-06,
      "loss": 0.3858,
      "step": 42585
    },
    {
      "epoch": 1.3082050809449206,
      "grad_norm": 0.4730260372161865,
      "learning_rate": 5.360867800513867e-06,
      "loss": 0.4888,
      "step": 42586
    },
    {
      "epoch": 1.3082358000798697,
      "grad_norm": 0.42417389154434204,
      "learning_rate": 5.360439679891022e-06,
      "loss": 0.5144,
      "step": 42587
    },
    {
      "epoch": 1.3082665192148188,
      "grad_norm": 0.4101429581642151,
      "learning_rate": 5.360011570104189e-06,
      "loss": 0.4382,
      "step": 42588
    },
    {
      "epoch": 1.308297238349768,
      "grad_norm": 0.4412672519683838,
      "learning_rate": 5.359583471154381e-06,
      "loss": 0.4453,
      "step": 42589
    },
    {
      "epoch": 1.3083279574847173,
      "grad_norm": 0.40787383913993835,
      "learning_rate": 5.359155383042587e-06,
      "loss": 0.4463,
      "step": 42590
    },
    {
      "epoch": 1.3083586766196664,
      "grad_norm": 0.441787987947464,
      "learning_rate": 5.358727305769813e-06,
      "loss": 0.4953,
      "step": 42591
    },
    {
      "epoch": 1.3083893957546155,
      "grad_norm": 0.3938044011592865,
      "learning_rate": 5.35829923933705e-06,
      "loss": 0.5272,
      "step": 42592
    },
    {
      "epoch": 1.3084201148895647,
      "grad_norm": 0.42096132040023804,
      "learning_rate": 5.357871183745305e-06,
      "loss": 0.5365,
      "step": 42593
    },
    {
      "epoch": 1.3084508340245138,
      "grad_norm": 0.8035783767700195,
      "learning_rate": 5.357443138995577e-06,
      "loss": 0.4931,
      "step": 42594
    },
    {
      "epoch": 1.3084815531594631,
      "grad_norm": 0.5925153493881226,
      "learning_rate": 5.357015105088867e-06,
      "loss": 0.4889,
      "step": 42595
    },
    {
      "epoch": 1.3085122722944122,
      "grad_norm": 0.37338554859161377,
      "learning_rate": 5.356587082026169e-06,
      "loss": 0.5076,
      "step": 42596
    },
    {
      "epoch": 1.3085429914293614,
      "grad_norm": 0.40627655386924744,
      "learning_rate": 5.356159069808486e-06,
      "loss": 0.4696,
      "step": 42597
    },
    {
      "epoch": 1.3085737105643105,
      "grad_norm": 0.4002093970775604,
      "learning_rate": 5.355731068436818e-06,
      "loss": 0.4067,
      "step": 42598
    },
    {
      "epoch": 1.3086044296992596,
      "grad_norm": 0.37423110008239746,
      "learning_rate": 5.355303077912168e-06,
      "loss": 0.5453,
      "step": 42599
    },
    {
      "epoch": 1.3086351488342087,
      "grad_norm": 0.41627785563468933,
      "learning_rate": 5.354875098235529e-06,
      "loss": 0.5549,
      "step": 42600
    },
    {
      "epoch": 1.308665867969158,
      "grad_norm": 0.43354618549346924,
      "learning_rate": 5.354447129407904e-06,
      "loss": 0.4941,
      "step": 42601
    },
    {
      "epoch": 1.3086965871041072,
      "grad_norm": 0.396833598613739,
      "learning_rate": 5.354019171430291e-06,
      "loss": 0.4798,
      "step": 42602
    },
    {
      "epoch": 1.3087273062390563,
      "grad_norm": 0.3687353730201721,
      "learning_rate": 5.3535912243036946e-06,
      "loss": 0.4258,
      "step": 42603
    },
    {
      "epoch": 1.3087580253740054,
      "grad_norm": 0.4177442789077759,
      "learning_rate": 5.353163288029106e-06,
      "loss": 0.5026,
      "step": 42604
    },
    {
      "epoch": 1.3087887445089545,
      "grad_norm": 0.4088265895843506,
      "learning_rate": 5.352735362607531e-06,
      "loss": 0.562,
      "step": 42605
    },
    {
      "epoch": 1.308819463643904,
      "grad_norm": 0.4203476905822754,
      "learning_rate": 5.352307448039966e-06,
      "loss": 0.5299,
      "step": 42606
    },
    {
      "epoch": 1.308850182778853,
      "grad_norm": 0.4119008481502533,
      "learning_rate": 5.351879544327412e-06,
      "loss": 0.459,
      "step": 42607
    },
    {
      "epoch": 1.3088809019138021,
      "grad_norm": 0.4049301743507385,
      "learning_rate": 5.351451651470871e-06,
      "loss": 0.4376,
      "step": 42608
    },
    {
      "epoch": 1.3089116210487513,
      "grad_norm": 0.3723146915435791,
      "learning_rate": 5.351023769471335e-06,
      "loss": 0.3769,
      "step": 42609
    },
    {
      "epoch": 1.3089423401837004,
      "grad_norm": 0.39901846647262573,
      "learning_rate": 5.350595898329809e-06,
      "loss": 0.4792,
      "step": 42610
    },
    {
      "epoch": 1.3089730593186495,
      "grad_norm": 0.47482168674468994,
      "learning_rate": 5.350168038047291e-06,
      "loss": 0.4808,
      "step": 42611
    },
    {
      "epoch": 1.3090037784535986,
      "grad_norm": 0.4500598609447479,
      "learning_rate": 5.349740188624784e-06,
      "loss": 0.4009,
      "step": 42612
    },
    {
      "epoch": 1.309034497588548,
      "grad_norm": 0.4345620274543762,
      "learning_rate": 5.349312350063278e-06,
      "loss": 0.5369,
      "step": 42613
    },
    {
      "epoch": 1.309065216723497,
      "grad_norm": 0.4155031442642212,
      "learning_rate": 5.348884522363784e-06,
      "loss": 0.5214,
      "step": 42614
    },
    {
      "epoch": 1.3090959358584462,
      "grad_norm": 0.41227248311042786,
      "learning_rate": 5.348456705527286e-06,
      "loss": 0.468,
      "step": 42615
    },
    {
      "epoch": 1.3091266549933953,
      "grad_norm": 0.39071527123451233,
      "learning_rate": 5.3480288995548e-06,
      "loss": 0.4765,
      "step": 42616
    },
    {
      "epoch": 1.3091573741283447,
      "grad_norm": 0.41955116391181946,
      "learning_rate": 5.347601104447314e-06,
      "loss": 0.4844,
      "step": 42617
    },
    {
      "epoch": 1.3091880932632938,
      "grad_norm": 0.3886781334877014,
      "learning_rate": 5.347173320205834e-06,
      "loss": 0.5946,
      "step": 42618
    },
    {
      "epoch": 1.309218812398243,
      "grad_norm": 0.43059054017066956,
      "learning_rate": 5.3467455468313525e-06,
      "loss": 0.4109,
      "step": 42619
    },
    {
      "epoch": 1.309249531533192,
      "grad_norm": 0.4388757348060608,
      "learning_rate": 5.346317784324871e-06,
      "loss": 0.4603,
      "step": 42620
    },
    {
      "epoch": 1.3092802506681411,
      "grad_norm": 0.4096326529979706,
      "learning_rate": 5.3458900326873894e-06,
      "loss": 0.43,
      "step": 42621
    },
    {
      "epoch": 1.3093109698030903,
      "grad_norm": 0.4325703978538513,
      "learning_rate": 5.345462291919912e-06,
      "loss": 0.5048,
      "step": 42622
    },
    {
      "epoch": 1.3093416889380394,
      "grad_norm": 0.40389201045036316,
      "learning_rate": 5.345034562023427e-06,
      "loss": 0.5038,
      "step": 42623
    },
    {
      "epoch": 1.3093724080729887,
      "grad_norm": 0.4963304400444031,
      "learning_rate": 5.344606842998935e-06,
      "loss": 0.4206,
      "step": 42624
    },
    {
      "epoch": 1.3094031272079378,
      "grad_norm": 0.3929086923599243,
      "learning_rate": 5.344179134847447e-06,
      "loss": 0.4932,
      "step": 42625
    },
    {
      "epoch": 1.309433846342887,
      "grad_norm": 0.4287760555744171,
      "learning_rate": 5.343751437569949e-06,
      "loss": 0.5093,
      "step": 42626
    },
    {
      "epoch": 1.309464565477836,
      "grad_norm": 0.39969849586486816,
      "learning_rate": 5.34332375116745e-06,
      "loss": 0.4828,
      "step": 42627
    },
    {
      "epoch": 1.3094952846127854,
      "grad_norm": 0.4979577660560608,
      "learning_rate": 5.34289607564094e-06,
      "loss": 0.4604,
      "step": 42628
    },
    {
      "epoch": 1.3095260037477345,
      "grad_norm": 0.40866172313690186,
      "learning_rate": 5.3424684109914195e-06,
      "loss": 0.4904,
      "step": 42629
    },
    {
      "epoch": 1.3095567228826837,
      "grad_norm": 0.3923908472061157,
      "learning_rate": 5.342040757219891e-06,
      "loss": 0.3602,
      "step": 42630
    },
    {
      "epoch": 1.3095874420176328,
      "grad_norm": 0.45405539870262146,
      "learning_rate": 5.341613114327355e-06,
      "loss": 0.4563,
      "step": 42631
    },
    {
      "epoch": 1.309618161152582,
      "grad_norm": 0.4203910827636719,
      "learning_rate": 5.3411854823148035e-06,
      "loss": 0.478,
      "step": 42632
    },
    {
      "epoch": 1.309648880287531,
      "grad_norm": 0.4334791302680969,
      "learning_rate": 5.340757861183237e-06,
      "loss": 0.5148,
      "step": 42633
    },
    {
      "epoch": 1.3096795994224801,
      "grad_norm": 0.38123956322669983,
      "learning_rate": 5.340330250933657e-06,
      "loss": 0.4296,
      "step": 42634
    },
    {
      "epoch": 1.3097103185574295,
      "grad_norm": 0.4451760947704315,
      "learning_rate": 5.339902651567066e-06,
      "loss": 0.4342,
      "step": 42635
    },
    {
      "epoch": 1.3097410376923786,
      "grad_norm": 0.4375760853290558,
      "learning_rate": 5.339475063084452e-06,
      "loss": 0.4868,
      "step": 42636
    },
    {
      "epoch": 1.3097717568273277,
      "grad_norm": 0.38952040672302246,
      "learning_rate": 5.339047485486821e-06,
      "loss": 0.4326,
      "step": 42637
    },
    {
      "epoch": 1.3098024759622768,
      "grad_norm": 0.40398064255714417,
      "learning_rate": 5.3386199187751695e-06,
      "loss": 0.4985,
      "step": 42638
    },
    {
      "epoch": 1.3098331950972262,
      "grad_norm": 0.4082680344581604,
      "learning_rate": 5.338192362950501e-06,
      "loss": 0.4735,
      "step": 42639
    },
    {
      "epoch": 1.3098639142321753,
      "grad_norm": 0.4261380434036255,
      "learning_rate": 5.337764818013805e-06,
      "loss": 0.5079,
      "step": 42640
    },
    {
      "epoch": 1.3098946333671244,
      "grad_norm": 0.41019007563591003,
      "learning_rate": 5.33733728396609e-06,
      "loss": 0.4719,
      "step": 42641
    },
    {
      "epoch": 1.3099253525020735,
      "grad_norm": 0.441254198551178,
      "learning_rate": 5.336909760808341e-06,
      "loss": 0.4907,
      "step": 42642
    },
    {
      "epoch": 1.3099560716370227,
      "grad_norm": 0.41420745849609375,
      "learning_rate": 5.336482248541568e-06,
      "loss": 0.357,
      "step": 42643
    },
    {
      "epoch": 1.3099867907719718,
      "grad_norm": 0.46970704197883606,
      "learning_rate": 5.336054747166772e-06,
      "loss": 0.4922,
      "step": 42644
    },
    {
      "epoch": 1.310017509906921,
      "grad_norm": 0.39083021879196167,
      "learning_rate": 5.335627256684941e-06,
      "loss": 0.4422,
      "step": 42645
    },
    {
      "epoch": 1.3100482290418702,
      "grad_norm": 0.4106806516647339,
      "learning_rate": 5.335199777097077e-06,
      "loss": 0.534,
      "step": 42646
    },
    {
      "epoch": 1.3100789481768194,
      "grad_norm": 0.3730352520942688,
      "learning_rate": 5.334772308404181e-06,
      "loss": 0.521,
      "step": 42647
    },
    {
      "epoch": 1.3101096673117685,
      "grad_norm": 0.3978714942932129,
      "learning_rate": 5.334344850607256e-06,
      "loss": 0.4786,
      "step": 42648
    },
    {
      "epoch": 1.3101403864467176,
      "grad_norm": 0.4267534017562866,
      "learning_rate": 5.333917403707287e-06,
      "loss": 0.5299,
      "step": 42649
    },
    {
      "epoch": 1.310171105581667,
      "grad_norm": 0.4111158549785614,
      "learning_rate": 5.333489967705286e-06,
      "loss": 0.4685,
      "step": 42650
    },
    {
      "epoch": 1.310201824716616,
      "grad_norm": 0.37408265471458435,
      "learning_rate": 5.333062542602237e-06,
      "loss": 0.4532,
      "step": 42651
    },
    {
      "epoch": 1.3102325438515652,
      "grad_norm": 0.3830038607120514,
      "learning_rate": 5.332635128399153e-06,
      "loss": 0.4413,
      "step": 42652
    },
    {
      "epoch": 1.3102632629865143,
      "grad_norm": 0.43888601660728455,
      "learning_rate": 5.332207725097023e-06,
      "loss": 0.4405,
      "step": 42653
    },
    {
      "epoch": 1.3102939821214634,
      "grad_norm": 0.3962578773498535,
      "learning_rate": 5.331780332696852e-06,
      "loss": 0.4215,
      "step": 42654
    },
    {
      "epoch": 1.3103247012564125,
      "grad_norm": 0.46637436747550964,
      "learning_rate": 5.331352951199628e-06,
      "loss": 0.581,
      "step": 42655
    },
    {
      "epoch": 1.3103554203913617,
      "grad_norm": 0.447128027677536,
      "learning_rate": 5.330925580606356e-06,
      "loss": 0.4925,
      "step": 42656
    },
    {
      "epoch": 1.310386139526311,
      "grad_norm": 0.39527687430381775,
      "learning_rate": 5.3304982209180346e-06,
      "loss": 0.5086,
      "step": 42657
    },
    {
      "epoch": 1.3104168586612601,
      "grad_norm": 0.38668134808540344,
      "learning_rate": 5.330070872135664e-06,
      "loss": 0.4683,
      "step": 42658
    },
    {
      "epoch": 1.3104475777962092,
      "grad_norm": 0.41034066677093506,
      "learning_rate": 5.329643534260236e-06,
      "loss": 0.453,
      "step": 42659
    },
    {
      "epoch": 1.3104782969311584,
      "grad_norm": 0.4182870090007782,
      "learning_rate": 5.329216207292751e-06,
      "loss": 0.3748,
      "step": 42660
    },
    {
      "epoch": 1.3105090160661077,
      "grad_norm": 0.43177565932273865,
      "learning_rate": 5.3287888912342065e-06,
      "loss": 0.5156,
      "step": 42661
    },
    {
      "epoch": 1.3105397352010568,
      "grad_norm": 0.40861597657203674,
      "learning_rate": 5.328361586085604e-06,
      "loss": 0.4651,
      "step": 42662
    },
    {
      "epoch": 1.310570454336006,
      "grad_norm": 0.4090547561645508,
      "learning_rate": 5.327934291847941e-06,
      "loss": 0.4357,
      "step": 42663
    },
    {
      "epoch": 1.310601173470955,
      "grad_norm": 0.4187892973423004,
      "learning_rate": 5.327507008522212e-06,
      "loss": 0.4086,
      "step": 42664
    },
    {
      "epoch": 1.3106318926059042,
      "grad_norm": 0.4483836889266968,
      "learning_rate": 5.327079736109415e-06,
      "loss": 0.509,
      "step": 42665
    },
    {
      "epoch": 1.3106626117408533,
      "grad_norm": 0.38594797253608704,
      "learning_rate": 5.326652474610551e-06,
      "loss": 0.5409,
      "step": 42666
    },
    {
      "epoch": 1.3106933308758024,
      "grad_norm": 0.498201459646225,
      "learning_rate": 5.32622522402662e-06,
      "loss": 0.4036,
      "step": 42667
    },
    {
      "epoch": 1.3107240500107518,
      "grad_norm": 0.4549007713794708,
      "learning_rate": 5.325797984358612e-06,
      "loss": 0.4142,
      "step": 42668
    },
    {
      "epoch": 1.3107547691457009,
      "grad_norm": 0.39523229002952576,
      "learning_rate": 5.325370755607528e-06,
      "loss": 0.4109,
      "step": 42669
    },
    {
      "epoch": 1.31078548828065,
      "grad_norm": 0.4181034564971924,
      "learning_rate": 5.32494353777437e-06,
      "loss": 0.4872,
      "step": 42670
    },
    {
      "epoch": 1.3108162074155991,
      "grad_norm": 0.4547802805900574,
      "learning_rate": 5.324516330860134e-06,
      "loss": 0.4901,
      "step": 42671
    },
    {
      "epoch": 1.3108469265505485,
      "grad_norm": 0.4123234152793884,
      "learning_rate": 5.324089134865815e-06,
      "loss": 0.4442,
      "step": 42672
    },
    {
      "epoch": 1.3108776456854976,
      "grad_norm": 0.39388203620910645,
      "learning_rate": 5.3236619497924115e-06,
      "loss": 0.3855,
      "step": 42673
    },
    {
      "epoch": 1.3109083648204467,
      "grad_norm": 0.4611511528491974,
      "learning_rate": 5.323234775640922e-06,
      "loss": 0.4927,
      "step": 42674
    },
    {
      "epoch": 1.3109390839553958,
      "grad_norm": 0.4131675958633423,
      "learning_rate": 5.3228076124123485e-06,
      "loss": 0.4483,
      "step": 42675
    },
    {
      "epoch": 1.310969803090345,
      "grad_norm": 0.43636950850486755,
      "learning_rate": 5.322380460107679e-06,
      "loss": 0.5258,
      "step": 42676
    },
    {
      "epoch": 1.311000522225294,
      "grad_norm": 0.4153464138507843,
      "learning_rate": 5.321953318727923e-06,
      "loss": 0.5218,
      "step": 42677
    },
    {
      "epoch": 1.3110312413602432,
      "grad_norm": 0.40009212493896484,
      "learning_rate": 5.321526188274062e-06,
      "loss": 0.4129,
      "step": 42678
    },
    {
      "epoch": 1.3110619604951925,
      "grad_norm": 0.4010849595069885,
      "learning_rate": 5.321099068747109e-06,
      "loss": 0.4571,
      "step": 42679
    },
    {
      "epoch": 1.3110926796301416,
      "grad_norm": 0.4453969895839691,
      "learning_rate": 5.3206719601480585e-06,
      "loss": 0.5029,
      "step": 42680
    },
    {
      "epoch": 1.3111233987650908,
      "grad_norm": 0.3912443518638611,
      "learning_rate": 5.320244862477901e-06,
      "loss": 0.4251,
      "step": 42681
    },
    {
      "epoch": 1.3111541179000399,
      "grad_norm": 0.43297848105430603,
      "learning_rate": 5.319817775737644e-06,
      "loss": 0.4816,
      "step": 42682
    },
    {
      "epoch": 1.3111848370349892,
      "grad_norm": 0.4158179759979248,
      "learning_rate": 5.319390699928271e-06,
      "loss": 0.4117,
      "step": 42683
    },
    {
      "epoch": 1.3112155561699383,
      "grad_norm": 0.4450158476829529,
      "learning_rate": 5.318963635050795e-06,
      "loss": 0.4273,
      "step": 42684
    },
    {
      "epoch": 1.3112462753048875,
      "grad_norm": 0.43228819966316223,
      "learning_rate": 5.318536581106203e-06,
      "loss": 0.4702,
      "step": 42685
    },
    {
      "epoch": 1.3112769944398366,
      "grad_norm": 0.4295349419116974,
      "learning_rate": 5.318109538095499e-06,
      "loss": 0.4756,
      "step": 42686
    },
    {
      "epoch": 1.3113077135747857,
      "grad_norm": 0.38527441024780273,
      "learning_rate": 5.3176825060196704e-06,
      "loss": 0.4552,
      "step": 42687
    },
    {
      "epoch": 1.3113384327097348,
      "grad_norm": 0.3772680461406708,
      "learning_rate": 5.317255484879729e-06,
      "loss": 0.5074,
      "step": 42688
    },
    {
      "epoch": 1.311369151844684,
      "grad_norm": 0.4114965498447418,
      "learning_rate": 5.316828474676659e-06,
      "loss": 0.4529,
      "step": 42689
    },
    {
      "epoch": 1.3113998709796333,
      "grad_norm": 0.42775505781173706,
      "learning_rate": 5.316401475411469e-06,
      "loss": 0.5202,
      "step": 42690
    },
    {
      "epoch": 1.3114305901145824,
      "grad_norm": 0.37536466121673584,
      "learning_rate": 5.315974487085146e-06,
      "loss": 0.3734,
      "step": 42691
    },
    {
      "epoch": 1.3114613092495315,
      "grad_norm": 0.43529877066612244,
      "learning_rate": 5.315547509698692e-06,
      "loss": 0.5289,
      "step": 42692
    },
    {
      "epoch": 1.3114920283844806,
      "grad_norm": 0.42989251017570496,
      "learning_rate": 5.315120543253103e-06,
      "loss": 0.4806,
      "step": 42693
    },
    {
      "epoch": 1.31152274751943,
      "grad_norm": 0.409027636051178,
      "learning_rate": 5.314693587749382e-06,
      "loss": 0.4932,
      "step": 42694
    },
    {
      "epoch": 1.311553466654379,
      "grad_norm": 0.42385396361351013,
      "learning_rate": 5.314266643188517e-06,
      "loss": 0.4618,
      "step": 42695
    },
    {
      "epoch": 1.3115841857893282,
      "grad_norm": 0.4373832643032074,
      "learning_rate": 5.313839709571509e-06,
      "loss": 0.481,
      "step": 42696
    },
    {
      "epoch": 1.3116149049242773,
      "grad_norm": 0.4329453706741333,
      "learning_rate": 5.313412786899357e-06,
      "loss": 0.4745,
      "step": 42697
    },
    {
      "epoch": 1.3116456240592265,
      "grad_norm": 0.4412766396999359,
      "learning_rate": 5.312985875173056e-06,
      "loss": 0.5318,
      "step": 42698
    },
    {
      "epoch": 1.3116763431941756,
      "grad_norm": 0.40599653124809265,
      "learning_rate": 5.312558974393607e-06,
      "loss": 0.4503,
      "step": 42699
    },
    {
      "epoch": 1.3117070623291247,
      "grad_norm": 0.3730314075946808,
      "learning_rate": 5.312132084562001e-06,
      "loss": 0.4743,
      "step": 42700
    },
    {
      "epoch": 1.311737781464074,
      "grad_norm": 0.4366036057472229,
      "learning_rate": 5.311705205679237e-06,
      "loss": 0.5124,
      "step": 42701
    },
    {
      "epoch": 1.3117685005990232,
      "grad_norm": 0.3761599063873291,
      "learning_rate": 5.311278337746314e-06,
      "loss": 0.4485,
      "step": 42702
    },
    {
      "epoch": 1.3117992197339723,
      "grad_norm": 0.4148709177970886,
      "learning_rate": 5.310851480764231e-06,
      "loss": 0.4576,
      "step": 42703
    },
    {
      "epoch": 1.3118299388689214,
      "grad_norm": 0.36741846799850464,
      "learning_rate": 5.310424634733978e-06,
      "loss": 0.4893,
      "step": 42704
    },
    {
      "epoch": 1.3118606580038705,
      "grad_norm": 0.390569269657135,
      "learning_rate": 5.3099977996565566e-06,
      "loss": 0.4142,
      "step": 42705
    },
    {
      "epoch": 1.3118913771388199,
      "grad_norm": 0.41031280159950256,
      "learning_rate": 5.309570975532963e-06,
      "loss": 0.5683,
      "step": 42706
    },
    {
      "epoch": 1.311922096273769,
      "grad_norm": 0.42084988951683044,
      "learning_rate": 5.309144162364196e-06,
      "loss": 0.6219,
      "step": 42707
    },
    {
      "epoch": 1.311952815408718,
      "grad_norm": 0.4447680115699768,
      "learning_rate": 5.308717360151248e-06,
      "loss": 0.4889,
      "step": 42708
    },
    {
      "epoch": 1.3119835345436672,
      "grad_norm": 0.43000009655952454,
      "learning_rate": 5.308290568895118e-06,
      "loss": 0.4356,
      "step": 42709
    },
    {
      "epoch": 1.3120142536786163,
      "grad_norm": 0.38543465733528137,
      "learning_rate": 5.307863788596803e-06,
      "loss": 0.4931,
      "step": 42710
    },
    {
      "epoch": 1.3120449728135655,
      "grad_norm": 0.3661477267742157,
      "learning_rate": 5.307437019257303e-06,
      "loss": 0.4426,
      "step": 42711
    },
    {
      "epoch": 1.3120756919485148,
      "grad_norm": 0.4048851430416107,
      "learning_rate": 5.307010260877609e-06,
      "loss": 0.4899,
      "step": 42712
    },
    {
      "epoch": 1.312106411083464,
      "grad_norm": 0.4390852153301239,
      "learning_rate": 5.3065835134587225e-06,
      "loss": 0.4293,
      "step": 42713
    },
    {
      "epoch": 1.312137130218413,
      "grad_norm": 0.4183966815471649,
      "learning_rate": 5.306156777001632e-06,
      "loss": 0.4626,
      "step": 42714
    },
    {
      "epoch": 1.3121678493533622,
      "grad_norm": 0.42399391531944275,
      "learning_rate": 5.305730051507343e-06,
      "loss": 0.5546,
      "step": 42715
    },
    {
      "epoch": 1.3121985684883113,
      "grad_norm": 0.4154777228832245,
      "learning_rate": 5.3053033369768535e-06,
      "loss": 0.4796,
      "step": 42716
    },
    {
      "epoch": 1.3122292876232606,
      "grad_norm": 0.4066959321498871,
      "learning_rate": 5.3048766334111516e-06,
      "loss": 0.4792,
      "step": 42717
    },
    {
      "epoch": 1.3122600067582098,
      "grad_norm": 0.424184650182724,
      "learning_rate": 5.304449940811242e-06,
      "loss": 0.4559,
      "step": 42718
    },
    {
      "epoch": 1.3122907258931589,
      "grad_norm": 0.38099250197410583,
      "learning_rate": 5.304023259178111e-06,
      "loss": 0.4434,
      "step": 42719
    },
    {
      "epoch": 1.312321445028108,
      "grad_norm": 0.4026128053665161,
      "learning_rate": 5.3035965885127694e-06,
      "loss": 0.4352,
      "step": 42720
    },
    {
      "epoch": 1.3123521641630571,
      "grad_norm": 0.3837030231952667,
      "learning_rate": 5.303169928816201e-06,
      "loss": 0.4956,
      "step": 42721
    },
    {
      "epoch": 1.3123828832980062,
      "grad_norm": 0.4743192195892334,
      "learning_rate": 5.302743280089411e-06,
      "loss": 0.4784,
      "step": 42722
    },
    {
      "epoch": 1.3124136024329554,
      "grad_norm": 0.42483651638031006,
      "learning_rate": 5.30231664233339e-06,
      "loss": 0.4751,
      "step": 42723
    },
    {
      "epoch": 1.3124443215679047,
      "grad_norm": 0.4303169250488281,
      "learning_rate": 5.301890015549134e-06,
      "loss": 0.4553,
      "step": 42724
    },
    {
      "epoch": 1.3124750407028538,
      "grad_norm": 0.42966246604919434,
      "learning_rate": 5.301463399737643e-06,
      "loss": 0.5112,
      "step": 42725
    },
    {
      "epoch": 1.312505759837803,
      "grad_norm": 0.4186360836029053,
      "learning_rate": 5.301036794899917e-06,
      "loss": 0.4224,
      "step": 42726
    },
    {
      "epoch": 1.312536478972752,
      "grad_norm": 0.4455282986164093,
      "learning_rate": 5.300610201036943e-06,
      "loss": 0.4919,
      "step": 42727
    },
    {
      "epoch": 1.3125671981077014,
      "grad_norm": 0.3940542936325073,
      "learning_rate": 5.300183618149723e-06,
      "loss": 0.4071,
      "step": 42728
    },
    {
      "epoch": 1.3125979172426505,
      "grad_norm": 0.4518124759197235,
      "learning_rate": 5.299757046239251e-06,
      "loss": 0.5451,
      "step": 42729
    },
    {
      "epoch": 1.3126286363775996,
      "grad_norm": 0.4154528081417084,
      "learning_rate": 5.299330485306531e-06,
      "loss": 0.5197,
      "step": 42730
    },
    {
      "epoch": 1.3126593555125488,
      "grad_norm": 0.38142672181129456,
      "learning_rate": 5.298903935352546e-06,
      "loss": 0.4503,
      "step": 42731
    },
    {
      "epoch": 1.3126900746474979,
      "grad_norm": 0.42071250081062317,
      "learning_rate": 5.298477396378301e-06,
      "loss": 0.4651,
      "step": 42732
    },
    {
      "epoch": 1.312720793782447,
      "grad_norm": 0.4308840334415436,
      "learning_rate": 5.2980508683847895e-06,
      "loss": 0.4094,
      "step": 42733
    },
    {
      "epoch": 1.3127515129173961,
      "grad_norm": 0.5044971704483032,
      "learning_rate": 5.297624351373009e-06,
      "loss": 0.4433,
      "step": 42734
    },
    {
      "epoch": 1.3127822320523455,
      "grad_norm": 0.41783586144447327,
      "learning_rate": 5.29719784534396e-06,
      "loss": 0.4157,
      "step": 42735
    },
    {
      "epoch": 1.3128129511872946,
      "grad_norm": 0.37254008650779724,
      "learning_rate": 5.2967713502986285e-06,
      "loss": 0.4078,
      "step": 42736
    },
    {
      "epoch": 1.3128436703222437,
      "grad_norm": 0.4301234781742096,
      "learning_rate": 5.296344866238017e-06,
      "loss": 0.4642,
      "step": 42737
    },
    {
      "epoch": 1.3128743894571928,
      "grad_norm": 0.37741804122924805,
      "learning_rate": 5.2959183931631204e-06,
      "loss": 0.4366,
      "step": 42738
    },
    {
      "epoch": 1.3129051085921422,
      "grad_norm": 0.40220412611961365,
      "learning_rate": 5.295491931074939e-06,
      "loss": 0.4292,
      "step": 42739
    },
    {
      "epoch": 1.3129358277270913,
      "grad_norm": 0.39024803042411804,
      "learning_rate": 5.295065479974461e-06,
      "loss": 0.453,
      "step": 42740
    },
    {
      "epoch": 1.3129665468620404,
      "grad_norm": 0.4218512773513794,
      "learning_rate": 5.294639039862686e-06,
      "loss": 0.4409,
      "step": 42741
    },
    {
      "epoch": 1.3129972659969895,
      "grad_norm": 0.5205007195472717,
      "learning_rate": 5.294212610740609e-06,
      "loss": 0.4263,
      "step": 42742
    },
    {
      "epoch": 1.3130279851319386,
      "grad_norm": 0.3933616876602173,
      "learning_rate": 5.293786192609232e-06,
      "loss": 0.4764,
      "step": 42743
    },
    {
      "epoch": 1.3130587042668878,
      "grad_norm": 0.4034581780433655,
      "learning_rate": 5.293359785469542e-06,
      "loss": 0.5025,
      "step": 42744
    },
    {
      "epoch": 1.3130894234018369,
      "grad_norm": 0.42296701669692993,
      "learning_rate": 5.292933389322543e-06,
      "loss": 0.4125,
      "step": 42745
    },
    {
      "epoch": 1.3131201425367862,
      "grad_norm": 0.369594931602478,
      "learning_rate": 5.292507004169219e-06,
      "loss": 0.5067,
      "step": 42746
    },
    {
      "epoch": 1.3131508616717353,
      "grad_norm": 0.4229872524738312,
      "learning_rate": 5.292080630010581e-06,
      "loss": 0.4916,
      "step": 42747
    },
    {
      "epoch": 1.3131815808066845,
      "grad_norm": 0.3907736539840698,
      "learning_rate": 5.291654266847614e-06,
      "loss": 0.5059,
      "step": 42748
    },
    {
      "epoch": 1.3132122999416336,
      "grad_norm": 0.4032250642776489,
      "learning_rate": 5.291227914681321e-06,
      "loss": 0.4548,
      "step": 42749
    },
    {
      "epoch": 1.313243019076583,
      "grad_norm": 0.40108051896095276,
      "learning_rate": 5.290801573512685e-06,
      "loss": 0.4386,
      "step": 42750
    },
    {
      "epoch": 1.313273738211532,
      "grad_norm": 0.40847718715667725,
      "learning_rate": 5.290375243342717e-06,
      "loss": 0.4629,
      "step": 42751
    },
    {
      "epoch": 1.3133044573464812,
      "grad_norm": 0.4005262553691864,
      "learning_rate": 5.289948924172409e-06,
      "loss": 0.4699,
      "step": 42752
    },
    {
      "epoch": 1.3133351764814303,
      "grad_norm": 0.42252469062805176,
      "learning_rate": 5.289522616002751e-06,
      "loss": 0.5042,
      "step": 42753
    },
    {
      "epoch": 1.3133658956163794,
      "grad_norm": 0.45837825536727905,
      "learning_rate": 5.289096318834745e-06,
      "loss": 0.4991,
      "step": 42754
    },
    {
      "epoch": 1.3133966147513285,
      "grad_norm": 0.4105553925037384,
      "learning_rate": 5.288670032669377e-06,
      "loss": 0.4153,
      "step": 42755
    },
    {
      "epoch": 1.3134273338862776,
      "grad_norm": 0.41054651141166687,
      "learning_rate": 5.288243757507656e-06,
      "loss": 0.485,
      "step": 42756
    },
    {
      "epoch": 1.313458053021227,
      "grad_norm": 0.3913794159889221,
      "learning_rate": 5.287817493350567e-06,
      "loss": 0.5318,
      "step": 42757
    },
    {
      "epoch": 1.313488772156176,
      "grad_norm": 0.43368247151374817,
      "learning_rate": 5.287391240199114e-06,
      "loss": 0.4617,
      "step": 42758
    },
    {
      "epoch": 1.3135194912911252,
      "grad_norm": 0.43798431754112244,
      "learning_rate": 5.286964998054283e-06,
      "loss": 0.5209,
      "step": 42759
    },
    {
      "epoch": 1.3135502104260743,
      "grad_norm": 0.381217896938324,
      "learning_rate": 5.286538766917075e-06,
      "loss": 0.4928,
      "step": 42760
    },
    {
      "epoch": 1.3135809295610237,
      "grad_norm": 0.4364384412765503,
      "learning_rate": 5.286112546788484e-06,
      "loss": 0.5237,
      "step": 42761
    },
    {
      "epoch": 1.3136116486959728,
      "grad_norm": 0.3784344494342804,
      "learning_rate": 5.285686337669511e-06,
      "loss": 0.4678,
      "step": 42762
    },
    {
      "epoch": 1.313642367830922,
      "grad_norm": 0.4933649003505707,
      "learning_rate": 5.285260139561144e-06,
      "loss": 0.4802,
      "step": 42763
    },
    {
      "epoch": 1.313673086965871,
      "grad_norm": 0.44825607538223267,
      "learning_rate": 5.284833952464379e-06,
      "loss": 0.5095,
      "step": 42764
    },
    {
      "epoch": 1.3137038061008202,
      "grad_norm": 0.4180770516395569,
      "learning_rate": 5.2844077763802145e-06,
      "loss": 0.4791,
      "step": 42765
    },
    {
      "epoch": 1.3137345252357693,
      "grad_norm": 0.39045777916908264,
      "learning_rate": 5.28398161130965e-06,
      "loss": 0.4363,
      "step": 42766
    },
    {
      "epoch": 1.3137652443707184,
      "grad_norm": 0.45134642720222473,
      "learning_rate": 5.2835554572536705e-06,
      "loss": 0.4767,
      "step": 42767
    },
    {
      "epoch": 1.3137959635056677,
      "grad_norm": 0.5075973868370056,
      "learning_rate": 5.2831293142132775e-06,
      "loss": 0.4644,
      "step": 42768
    },
    {
      "epoch": 1.3138266826406169,
      "grad_norm": 0.421646386384964,
      "learning_rate": 5.2827031821894645e-06,
      "loss": 0.4375,
      "step": 42769
    },
    {
      "epoch": 1.313857401775566,
      "grad_norm": 0.38208410143852234,
      "learning_rate": 5.2822770611832275e-06,
      "loss": 0.5125,
      "step": 42770
    },
    {
      "epoch": 1.313888120910515,
      "grad_norm": 0.4612293243408203,
      "learning_rate": 5.281850951195567e-06,
      "loss": 0.5241,
      "step": 42771
    },
    {
      "epoch": 1.3139188400454644,
      "grad_norm": 0.37735944986343384,
      "learning_rate": 5.281424852227469e-06,
      "loss": 0.4456,
      "step": 42772
    },
    {
      "epoch": 1.3139495591804136,
      "grad_norm": 0.3696325719356537,
      "learning_rate": 5.280998764279932e-06,
      "loss": 0.5168,
      "step": 42773
    },
    {
      "epoch": 1.3139802783153627,
      "grad_norm": 0.4142361879348755,
      "learning_rate": 5.2805726873539535e-06,
      "loss": 0.4916,
      "step": 42774
    },
    {
      "epoch": 1.3140109974503118,
      "grad_norm": 0.39722293615341187,
      "learning_rate": 5.280146621450529e-06,
      "loss": 0.4726,
      "step": 42775
    },
    {
      "epoch": 1.314041716585261,
      "grad_norm": 0.4195489287376404,
      "learning_rate": 5.279720566570649e-06,
      "loss": 0.4606,
      "step": 42776
    },
    {
      "epoch": 1.31407243572021,
      "grad_norm": 0.4275203049182892,
      "learning_rate": 5.279294522715311e-06,
      "loss": 0.4665,
      "step": 42777
    },
    {
      "epoch": 1.3141031548551592,
      "grad_norm": 0.4194270968437195,
      "learning_rate": 5.27886848988551e-06,
      "loss": 0.5517,
      "step": 42778
    },
    {
      "epoch": 1.3141338739901085,
      "grad_norm": 0.3903016149997711,
      "learning_rate": 5.278442468082246e-06,
      "loss": 0.4508,
      "step": 42779
    },
    {
      "epoch": 1.3141645931250576,
      "grad_norm": 0.4246681332588196,
      "learning_rate": 5.278016457306505e-06,
      "loss": 0.484,
      "step": 42780
    },
    {
      "epoch": 1.3141953122600067,
      "grad_norm": 0.42021235823631287,
      "learning_rate": 5.27759045755929e-06,
      "loss": 0.4104,
      "step": 42781
    },
    {
      "epoch": 1.3142260313949559,
      "grad_norm": 0.434092253446579,
      "learning_rate": 5.277164468841584e-06,
      "loss": 0.536,
      "step": 42782
    },
    {
      "epoch": 1.3142567505299052,
      "grad_norm": 0.4056948125362396,
      "learning_rate": 5.2767384911544e-06,
      "loss": 0.4699,
      "step": 42783
    },
    {
      "epoch": 1.3142874696648543,
      "grad_norm": 0.430522084236145,
      "learning_rate": 5.276312524498718e-06,
      "loss": 0.4841,
      "step": 42784
    },
    {
      "epoch": 1.3143181887998034,
      "grad_norm": 0.4288354218006134,
      "learning_rate": 5.275886568875541e-06,
      "loss": 0.4899,
      "step": 42785
    },
    {
      "epoch": 1.3143489079347526,
      "grad_norm": 0.41226527094841003,
      "learning_rate": 5.275460624285858e-06,
      "loss": 0.4847,
      "step": 42786
    },
    {
      "epoch": 1.3143796270697017,
      "grad_norm": 0.4075545370578766,
      "learning_rate": 5.275034690730667e-06,
      "loss": 0.3946,
      "step": 42787
    },
    {
      "epoch": 1.3144103462046508,
      "grad_norm": 0.38793039321899414,
      "learning_rate": 5.274608768210963e-06,
      "loss": 0.4343,
      "step": 42788
    },
    {
      "epoch": 1.3144410653396,
      "grad_norm": 0.4258239269256592,
      "learning_rate": 5.274182856727738e-06,
      "loss": 0.4793,
      "step": 42789
    },
    {
      "epoch": 1.3144717844745493,
      "grad_norm": 0.4305517077445984,
      "learning_rate": 5.2737569562819946e-06,
      "loss": 0.551,
      "step": 42790
    },
    {
      "epoch": 1.3145025036094984,
      "grad_norm": 0.39537158608436584,
      "learning_rate": 5.273331066874714e-06,
      "loss": 0.4667,
      "step": 42791
    },
    {
      "epoch": 1.3145332227444475,
      "grad_norm": 0.41310787200927734,
      "learning_rate": 5.272905188506906e-06,
      "loss": 0.4261,
      "step": 42792
    },
    {
      "epoch": 1.3145639418793966,
      "grad_norm": 0.44098085165023804,
      "learning_rate": 5.272479321179555e-06,
      "loss": 0.5488,
      "step": 42793
    },
    {
      "epoch": 1.314594661014346,
      "grad_norm": 0.43188905715942383,
      "learning_rate": 5.272053464893662e-06,
      "loss": 0.4666,
      "step": 42794
    },
    {
      "epoch": 1.314625380149295,
      "grad_norm": 0.3789795935153961,
      "learning_rate": 5.271627619650215e-06,
      "loss": 0.5479,
      "step": 42795
    },
    {
      "epoch": 1.3146560992842442,
      "grad_norm": 0.4449540078639984,
      "learning_rate": 5.27120178545021e-06,
      "loss": 0.4834,
      "step": 42796
    },
    {
      "epoch": 1.3146868184191933,
      "grad_norm": 0.418063223361969,
      "learning_rate": 5.270775962294645e-06,
      "loss": 0.4739,
      "step": 42797
    },
    {
      "epoch": 1.3147175375541424,
      "grad_norm": 0.36793264746665955,
      "learning_rate": 5.270350150184518e-06,
      "loss": 0.4454,
      "step": 42798
    },
    {
      "epoch": 1.3147482566890916,
      "grad_norm": 0.4545508325099945,
      "learning_rate": 5.269924349120812e-06,
      "loss": 0.4776,
      "step": 42799
    },
    {
      "epoch": 1.3147789758240407,
      "grad_norm": 0.3984687030315399,
      "learning_rate": 5.26949855910453e-06,
      "loss": 0.5182,
      "step": 42800
    },
    {
      "epoch": 1.31480969495899,
      "grad_norm": 0.4456465244293213,
      "learning_rate": 5.269072780136664e-06,
      "loss": 0.4418,
      "step": 42801
    },
    {
      "epoch": 1.3148404140939391,
      "grad_norm": 0.4622150957584381,
      "learning_rate": 5.268647012218213e-06,
      "loss": 0.4862,
      "step": 42802
    },
    {
      "epoch": 1.3148711332288883,
      "grad_norm": 0.4748353958129883,
      "learning_rate": 5.268221255350163e-06,
      "loss": 0.4975,
      "step": 42803
    },
    {
      "epoch": 1.3149018523638374,
      "grad_norm": 0.3757140040397644,
      "learning_rate": 5.267795509533513e-06,
      "loss": 0.4696,
      "step": 42804
    },
    {
      "epoch": 1.3149325714987867,
      "grad_norm": 0.39998406171798706,
      "learning_rate": 5.267369774769258e-06,
      "loss": 0.4951,
      "step": 42805
    },
    {
      "epoch": 1.3149632906337358,
      "grad_norm": 0.3755617141723633,
      "learning_rate": 5.2669440510583895e-06,
      "loss": 0.4385,
      "step": 42806
    },
    {
      "epoch": 1.314994009768685,
      "grad_norm": 0.39334046840667725,
      "learning_rate": 5.266518338401908e-06,
      "loss": 0.4603,
      "step": 42807
    },
    {
      "epoch": 1.315024728903634,
      "grad_norm": 0.4103911817073822,
      "learning_rate": 5.2660926368008004e-06,
      "loss": 0.4781,
      "step": 42808
    },
    {
      "epoch": 1.3150554480385832,
      "grad_norm": 0.4358200132846832,
      "learning_rate": 5.2656669462560636e-06,
      "loss": 0.5014,
      "step": 42809
    },
    {
      "epoch": 1.3150861671735323,
      "grad_norm": 0.40768104791641235,
      "learning_rate": 5.265241266768692e-06,
      "loss": 0.5022,
      "step": 42810
    },
    {
      "epoch": 1.3151168863084814,
      "grad_norm": 0.384072482585907,
      "learning_rate": 5.264815598339686e-06,
      "loss": 0.4491,
      "step": 42811
    },
    {
      "epoch": 1.3151476054434308,
      "grad_norm": 0.4084770679473877,
      "learning_rate": 5.2643899409700275e-06,
      "loss": 0.5231,
      "step": 42812
    },
    {
      "epoch": 1.31517832457838,
      "grad_norm": 0.416241317987442,
      "learning_rate": 5.263964294660718e-06,
      "loss": 0.5175,
      "step": 42813
    },
    {
      "epoch": 1.315209043713329,
      "grad_norm": 0.3937109112739563,
      "learning_rate": 5.26353865941275e-06,
      "loss": 0.4228,
      "step": 42814
    },
    {
      "epoch": 1.3152397628482781,
      "grad_norm": 0.4019549489021301,
      "learning_rate": 5.263113035227123e-06,
      "loss": 0.5279,
      "step": 42815
    },
    {
      "epoch": 1.3152704819832275,
      "grad_norm": 0.4389890730381012,
      "learning_rate": 5.262687422104823e-06,
      "loss": 0.4446,
      "step": 42816
    },
    {
      "epoch": 1.3153012011181766,
      "grad_norm": 0.4346162676811218,
      "learning_rate": 5.26226182004685e-06,
      "loss": 0.503,
      "step": 42817
    },
    {
      "epoch": 1.3153319202531257,
      "grad_norm": 0.40874338150024414,
      "learning_rate": 5.261836229054189e-06,
      "loss": 0.368,
      "step": 42818
    },
    {
      "epoch": 1.3153626393880749,
      "grad_norm": 0.41922473907470703,
      "learning_rate": 5.261410649127847e-06,
      "loss": 0.5759,
      "step": 42819
    },
    {
      "epoch": 1.315393358523024,
      "grad_norm": 0.40381523966789246,
      "learning_rate": 5.260985080268808e-06,
      "loss": 0.4344,
      "step": 42820
    },
    {
      "epoch": 1.315424077657973,
      "grad_norm": 0.4080154597759247,
      "learning_rate": 5.260559522478073e-06,
      "loss": 0.4847,
      "step": 42821
    },
    {
      "epoch": 1.3154547967929222,
      "grad_norm": 0.44591933488845825,
      "learning_rate": 5.260133975756627e-06,
      "loss": 0.4786,
      "step": 42822
    },
    {
      "epoch": 1.3154855159278716,
      "grad_norm": 0.42916202545166016,
      "learning_rate": 5.259708440105471e-06,
      "loss": 0.5015,
      "step": 42823
    },
    {
      "epoch": 1.3155162350628207,
      "grad_norm": 0.40839555859565735,
      "learning_rate": 5.259282915525596e-06,
      "loss": 0.4477,
      "step": 42824
    },
    {
      "epoch": 1.3155469541977698,
      "grad_norm": 0.4906802177429199,
      "learning_rate": 5.258857402017999e-06,
      "loss": 0.6029,
      "step": 42825
    },
    {
      "epoch": 1.315577673332719,
      "grad_norm": 0.45907801389694214,
      "learning_rate": 5.258431899583673e-06,
      "loss": 0.3981,
      "step": 42826
    },
    {
      "epoch": 1.315608392467668,
      "grad_norm": 0.4424405097961426,
      "learning_rate": 5.258006408223607e-06,
      "loss": 0.5547,
      "step": 42827
    },
    {
      "epoch": 1.3156391116026174,
      "grad_norm": 0.3844311535358429,
      "learning_rate": 5.257580927938799e-06,
      "loss": 0.5006,
      "step": 42828
    },
    {
      "epoch": 1.3156698307375665,
      "grad_norm": 0.40386396646499634,
      "learning_rate": 5.257155458730241e-06,
      "loss": 0.4741,
      "step": 42829
    },
    {
      "epoch": 1.3157005498725156,
      "grad_norm": 0.4260985255241394,
      "learning_rate": 5.256730000598933e-06,
      "loss": 0.5412,
      "step": 42830
    },
    {
      "epoch": 1.3157312690074647,
      "grad_norm": 0.41220754384994507,
      "learning_rate": 5.2563045535458575e-06,
      "loss": 0.4545,
      "step": 42831
    },
    {
      "epoch": 1.3157619881424139,
      "grad_norm": 0.3914608955383301,
      "learning_rate": 5.255879117572016e-06,
      "loss": 0.491,
      "step": 42832
    },
    {
      "epoch": 1.315792707277363,
      "grad_norm": 0.4096405506134033,
      "learning_rate": 5.255453692678398e-06,
      "loss": 0.4528,
      "step": 42833
    },
    {
      "epoch": 1.315823426412312,
      "grad_norm": 0.3950265347957611,
      "learning_rate": 5.255028278866006e-06,
      "loss": 0.4858,
      "step": 42834
    },
    {
      "epoch": 1.3158541455472614,
      "grad_norm": 0.3919812738895416,
      "learning_rate": 5.25460287613582e-06,
      "loss": 0.5779,
      "step": 42835
    },
    {
      "epoch": 1.3158848646822106,
      "grad_norm": 0.4602346122264862,
      "learning_rate": 5.254177484488843e-06,
      "loss": 0.454,
      "step": 42836
    },
    {
      "epoch": 1.3159155838171597,
      "grad_norm": 0.413004070520401,
      "learning_rate": 5.2537521039260645e-06,
      "loss": 0.5208,
      "step": 42837
    },
    {
      "epoch": 1.3159463029521088,
      "grad_norm": 0.4237222969532013,
      "learning_rate": 5.253326734448483e-06,
      "loss": 0.4885,
      "step": 42838
    },
    {
      "epoch": 1.3159770220870581,
      "grad_norm": 0.39352118968963623,
      "learning_rate": 5.252901376057085e-06,
      "loss": 0.3829,
      "step": 42839
    },
    {
      "epoch": 1.3160077412220073,
      "grad_norm": 0.385285347700119,
      "learning_rate": 5.2524760287528666e-06,
      "loss": 0.5101,
      "step": 42840
    },
    {
      "epoch": 1.3160384603569564,
      "grad_norm": 0.37037986516952515,
      "learning_rate": 5.252050692536823e-06,
      "loss": 0.4924,
      "step": 42841
    },
    {
      "epoch": 1.3160691794919055,
      "grad_norm": 0.44427576661109924,
      "learning_rate": 5.2516253674099504e-06,
      "loss": 0.4906,
      "step": 42842
    },
    {
      "epoch": 1.3160998986268546,
      "grad_norm": 0.47923406958580017,
      "learning_rate": 5.251200053373234e-06,
      "loss": 0.5021,
      "step": 42843
    },
    {
      "epoch": 1.3161306177618037,
      "grad_norm": 0.39643487334251404,
      "learning_rate": 5.250774750427672e-06,
      "loss": 0.4767,
      "step": 42844
    },
    {
      "epoch": 1.3161613368967529,
      "grad_norm": 0.5171940922737122,
      "learning_rate": 5.250349458574258e-06,
      "loss": 0.4791,
      "step": 42845
    },
    {
      "epoch": 1.3161920560317022,
      "grad_norm": 0.44915318489074707,
      "learning_rate": 5.249924177813983e-06,
      "loss": 0.4364,
      "step": 42846
    },
    {
      "epoch": 1.3162227751666513,
      "grad_norm": 0.41802462935447693,
      "learning_rate": 5.249498908147846e-06,
      "loss": 0.4518,
      "step": 42847
    },
    {
      "epoch": 1.3162534943016004,
      "grad_norm": 0.4646959602832794,
      "learning_rate": 5.249073649576833e-06,
      "loss": 0.5608,
      "step": 42848
    },
    {
      "epoch": 1.3162842134365496,
      "grad_norm": 0.41738954186439514,
      "learning_rate": 5.248648402101944e-06,
      "loss": 0.4888,
      "step": 42849
    },
    {
      "epoch": 1.316314932571499,
      "grad_norm": 0.38508540391921997,
      "learning_rate": 5.24822316572416e-06,
      "loss": 0.397,
      "step": 42850
    },
    {
      "epoch": 1.316345651706448,
      "grad_norm": 0.4145135283470154,
      "learning_rate": 5.24779794044449e-06,
      "loss": 0.4995,
      "step": 42851
    },
    {
      "epoch": 1.3163763708413971,
      "grad_norm": 0.42377769947052,
      "learning_rate": 5.247372726263917e-06,
      "loss": 0.4619,
      "step": 42852
    },
    {
      "epoch": 1.3164070899763463,
      "grad_norm": 0.39749181270599365,
      "learning_rate": 5.246947523183441e-06,
      "loss": 0.4868,
      "step": 42853
    },
    {
      "epoch": 1.3164378091112954,
      "grad_norm": 0.49193188548088074,
      "learning_rate": 5.246522331204043e-06,
      "loss": 0.5301,
      "step": 42854
    },
    {
      "epoch": 1.3164685282462445,
      "grad_norm": 0.5413334369659424,
      "learning_rate": 5.2460971503267325e-06,
      "loss": 0.4642,
      "step": 42855
    },
    {
      "epoch": 1.3164992473811936,
      "grad_norm": 0.4290924668312073,
      "learning_rate": 5.245671980552489e-06,
      "loss": 0.4904,
      "step": 42856
    },
    {
      "epoch": 1.316529966516143,
      "grad_norm": 0.4199216365814209,
      "learning_rate": 5.245246821882315e-06,
      "loss": 0.4477,
      "step": 42857
    },
    {
      "epoch": 1.316560685651092,
      "grad_norm": 0.42658767104148865,
      "learning_rate": 5.244821674317195e-06,
      "loss": 0.547,
      "step": 42858
    },
    {
      "epoch": 1.3165914047860412,
      "grad_norm": 0.3771151006221771,
      "learning_rate": 5.2443965378581254e-06,
      "loss": 0.518,
      "step": 42859
    },
    {
      "epoch": 1.3166221239209903,
      "grad_norm": 0.47472330927848816,
      "learning_rate": 5.2439714125061015e-06,
      "loss": 0.521,
      "step": 42860
    },
    {
      "epoch": 1.3166528430559397,
      "grad_norm": 0.45717430114746094,
      "learning_rate": 5.243546298262113e-06,
      "loss": 0.5336,
      "step": 42861
    },
    {
      "epoch": 1.3166835621908888,
      "grad_norm": 0.46621471643447876,
      "learning_rate": 5.243121195127159e-06,
      "loss": 0.4103,
      "step": 42862
    },
    {
      "epoch": 1.316714281325838,
      "grad_norm": 0.4576527774333954,
      "learning_rate": 5.242696103102224e-06,
      "loss": 0.5966,
      "step": 42863
    },
    {
      "epoch": 1.316745000460787,
      "grad_norm": 0.41829952597618103,
      "learning_rate": 5.242271022188303e-06,
      "loss": 0.5624,
      "step": 42864
    },
    {
      "epoch": 1.3167757195957361,
      "grad_norm": 0.4103064239025116,
      "learning_rate": 5.241845952386393e-06,
      "loss": 0.4032,
      "step": 42865
    },
    {
      "epoch": 1.3168064387306853,
      "grad_norm": 0.3876875042915344,
      "learning_rate": 5.2414208936974865e-06,
      "loss": 0.4575,
      "step": 42866
    },
    {
      "epoch": 1.3168371578656344,
      "grad_norm": 0.40207356214523315,
      "learning_rate": 5.24099584612257e-06,
      "loss": 0.4166,
      "step": 42867
    },
    {
      "epoch": 1.3168678770005837,
      "grad_norm": 0.3765757083892822,
      "learning_rate": 5.2405708096626395e-06,
      "loss": 0.435,
      "step": 42868
    },
    {
      "epoch": 1.3168985961355328,
      "grad_norm": 0.4005185663700104,
      "learning_rate": 5.240145784318689e-06,
      "loss": 0.435,
      "step": 42869
    },
    {
      "epoch": 1.316929315270482,
      "grad_norm": 0.4298878610134125,
      "learning_rate": 5.239720770091713e-06,
      "loss": 0.4352,
      "step": 42870
    },
    {
      "epoch": 1.316960034405431,
      "grad_norm": 0.4225062429904938,
      "learning_rate": 5.2392957669827e-06,
      "loss": 0.4074,
      "step": 42871
    },
    {
      "epoch": 1.3169907535403804,
      "grad_norm": 0.415498286485672,
      "learning_rate": 5.238870774992641e-06,
      "loss": 0.4765,
      "step": 42872
    },
    {
      "epoch": 1.3170214726753295,
      "grad_norm": 0.4195537567138672,
      "learning_rate": 5.238445794122536e-06,
      "loss": 0.4446,
      "step": 42873
    },
    {
      "epoch": 1.3170521918102787,
      "grad_norm": 0.3777081072330475,
      "learning_rate": 5.238020824373374e-06,
      "loss": 0.4528,
      "step": 42874
    },
    {
      "epoch": 1.3170829109452278,
      "grad_norm": 0.43941280245780945,
      "learning_rate": 5.237595865746143e-06,
      "loss": 0.3976,
      "step": 42875
    },
    {
      "epoch": 1.317113630080177,
      "grad_norm": 0.4339250922203064,
      "learning_rate": 5.237170918241841e-06,
      "loss": 0.4592,
      "step": 42876
    },
    {
      "epoch": 1.317144349215126,
      "grad_norm": 0.3992917835712433,
      "learning_rate": 5.23674598186146e-06,
      "loss": 0.5057,
      "step": 42877
    },
    {
      "epoch": 1.3171750683500751,
      "grad_norm": 0.43499067425727844,
      "learning_rate": 5.236321056605993e-06,
      "loss": 0.551,
      "step": 42878
    },
    {
      "epoch": 1.3172057874850245,
      "grad_norm": 0.43522346019744873,
      "learning_rate": 5.235896142476428e-06,
      "loss": 0.5172,
      "step": 42879
    },
    {
      "epoch": 1.3172365066199736,
      "grad_norm": 0.4233243465423584,
      "learning_rate": 5.2354712394737596e-06,
      "loss": 0.4354,
      "step": 42880
    },
    {
      "epoch": 1.3172672257549227,
      "grad_norm": 0.39169690012931824,
      "learning_rate": 5.235046347598982e-06,
      "loss": 0.5156,
      "step": 42881
    },
    {
      "epoch": 1.3172979448898718,
      "grad_norm": 0.3996301591396332,
      "learning_rate": 5.2346214668530845e-06,
      "loss": 0.5128,
      "step": 42882
    },
    {
      "epoch": 1.3173286640248212,
      "grad_norm": 0.4380137622356415,
      "learning_rate": 5.234196597237067e-06,
      "loss": 0.5077,
      "step": 42883
    },
    {
      "epoch": 1.3173593831597703,
      "grad_norm": 0.375267893075943,
      "learning_rate": 5.2337717387519115e-06,
      "loss": 0.4925,
      "step": 42884
    },
    {
      "epoch": 1.3173901022947194,
      "grad_norm": 0.4037840962409973,
      "learning_rate": 5.23334689139862e-06,
      "loss": 0.4859,
      "step": 42885
    },
    {
      "epoch": 1.3174208214296685,
      "grad_norm": 0.4308210015296936,
      "learning_rate": 5.232922055178171e-06,
      "loss": 0.5181,
      "step": 42886
    },
    {
      "epoch": 1.3174515405646177,
      "grad_norm": 0.4062504470348358,
      "learning_rate": 5.232497230091573e-06,
      "loss": 0.4637,
      "step": 42887
    },
    {
      "epoch": 1.3174822596995668,
      "grad_norm": 0.44900596141815186,
      "learning_rate": 5.232072416139807e-06,
      "loss": 0.4722,
      "step": 42888
    },
    {
      "epoch": 1.317512978834516,
      "grad_norm": 0.41023486852645874,
      "learning_rate": 5.231647613323874e-06,
      "loss": 0.499,
      "step": 42889
    },
    {
      "epoch": 1.3175436979694652,
      "grad_norm": 0.44722840189933777,
      "learning_rate": 5.231222821644756e-06,
      "loss": 0.4085,
      "step": 42890
    },
    {
      "epoch": 1.3175744171044144,
      "grad_norm": 0.43013420701026917,
      "learning_rate": 5.23079804110345e-06,
      "loss": 0.4377,
      "step": 42891
    },
    {
      "epoch": 1.3176051362393635,
      "grad_norm": 0.43172380328178406,
      "learning_rate": 5.230373271700948e-06,
      "loss": 0.5877,
      "step": 42892
    },
    {
      "epoch": 1.3176358553743126,
      "grad_norm": 0.40820589661598206,
      "learning_rate": 5.229948513438248e-06,
      "loss": 0.4478,
      "step": 42893
    },
    {
      "epoch": 1.317666574509262,
      "grad_norm": 0.41666316986083984,
      "learning_rate": 5.22952376631633e-06,
      "loss": 0.5667,
      "step": 42894
    },
    {
      "epoch": 1.317697293644211,
      "grad_norm": 0.4054161012172699,
      "learning_rate": 5.229099030336193e-06,
      "loss": 0.4258,
      "step": 42895
    },
    {
      "epoch": 1.3177280127791602,
      "grad_norm": 0.44497084617614746,
      "learning_rate": 5.2286743054988294e-06,
      "loss": 0.5042,
      "step": 42896
    },
    {
      "epoch": 1.3177587319141093,
      "grad_norm": 0.4533533751964569,
      "learning_rate": 5.22824959180523e-06,
      "loss": 0.4958,
      "step": 42897
    },
    {
      "epoch": 1.3177894510490584,
      "grad_norm": 0.41549360752105713,
      "learning_rate": 5.227824889256391e-06,
      "loss": 0.5031,
      "step": 42898
    },
    {
      "epoch": 1.3178201701840075,
      "grad_norm": 0.4246852695941925,
      "learning_rate": 5.227400197853296e-06,
      "loss": 0.5278,
      "step": 42899
    },
    {
      "epoch": 1.3178508893189567,
      "grad_norm": 0.47865191102027893,
      "learning_rate": 5.2269755175969415e-06,
      "loss": 0.4274,
      "step": 42900
    },
    {
      "epoch": 1.317881608453906,
      "grad_norm": 0.42592641711235046,
      "learning_rate": 5.226550848488318e-06,
      "loss": 0.5454,
      "step": 42901
    },
    {
      "epoch": 1.3179123275888551,
      "grad_norm": 0.4466381371021271,
      "learning_rate": 5.2261261905284225e-06,
      "loss": 0.3866,
      "step": 42902
    },
    {
      "epoch": 1.3179430467238042,
      "grad_norm": 0.43486401438713074,
      "learning_rate": 5.22570154371824e-06,
      "loss": 0.4548,
      "step": 42903
    },
    {
      "epoch": 1.3179737658587534,
      "grad_norm": 0.409077912569046,
      "learning_rate": 5.225276908058764e-06,
      "loss": 0.4386,
      "step": 42904
    },
    {
      "epoch": 1.3180044849937027,
      "grad_norm": 0.4121580123901367,
      "learning_rate": 5.224852283550988e-06,
      "loss": 0.4595,
      "step": 42905
    },
    {
      "epoch": 1.3180352041286518,
      "grad_norm": 0.411685585975647,
      "learning_rate": 5.224427670195906e-06,
      "loss": 0.443,
      "step": 42906
    },
    {
      "epoch": 1.318065923263601,
      "grad_norm": 0.39106249809265137,
      "learning_rate": 5.224003067994503e-06,
      "loss": 0.4379,
      "step": 42907
    },
    {
      "epoch": 1.31809664239855,
      "grad_norm": 0.3820570409297943,
      "learning_rate": 5.2235784769477745e-06,
      "loss": 0.4325,
      "step": 42908
    },
    {
      "epoch": 1.3181273615334992,
      "grad_norm": 0.4361613392829895,
      "learning_rate": 5.223153897056712e-06,
      "loss": 0.4177,
      "step": 42909
    },
    {
      "epoch": 1.3181580806684483,
      "grad_norm": 0.3965882658958435,
      "learning_rate": 5.222729328322311e-06,
      "loss": 0.4878,
      "step": 42910
    },
    {
      "epoch": 1.3181887998033974,
      "grad_norm": 0.40779808163642883,
      "learning_rate": 5.222304770745555e-06,
      "loss": 0.471,
      "step": 42911
    },
    {
      "epoch": 1.3182195189383468,
      "grad_norm": 0.43960198760032654,
      "learning_rate": 5.2218802243274445e-06,
      "loss": 0.4309,
      "step": 42912
    },
    {
      "epoch": 1.3182502380732959,
      "grad_norm": 0.45933258533477783,
      "learning_rate": 5.221455689068959e-06,
      "loss": 0.5008,
      "step": 42913
    },
    {
      "epoch": 1.318280957208245,
      "grad_norm": 0.4341253936290741,
      "learning_rate": 5.221031164971104e-06,
      "loss": 0.4925,
      "step": 42914
    },
    {
      "epoch": 1.3183116763431941,
      "grad_norm": 0.43361422419548035,
      "learning_rate": 5.220606652034862e-06,
      "loss": 0.4784,
      "step": 42915
    },
    {
      "epoch": 1.3183423954781435,
      "grad_norm": 0.47103410959243774,
      "learning_rate": 5.220182150261226e-06,
      "loss": 0.4661,
      "step": 42916
    },
    {
      "epoch": 1.3183731146130926,
      "grad_norm": 0.45637521147727966,
      "learning_rate": 5.219757659651188e-06,
      "loss": 0.5021,
      "step": 42917
    },
    {
      "epoch": 1.3184038337480417,
      "grad_norm": 0.41247373819351196,
      "learning_rate": 5.2193331802057416e-06,
      "loss": 0.5052,
      "step": 42918
    },
    {
      "epoch": 1.3184345528829908,
      "grad_norm": 0.39744704961776733,
      "learning_rate": 5.218908711925878e-06,
      "loss": 0.4978,
      "step": 42919
    },
    {
      "epoch": 1.31846527201794,
      "grad_norm": 0.4234919250011444,
      "learning_rate": 5.218484254812586e-06,
      "loss": 0.4279,
      "step": 42920
    },
    {
      "epoch": 1.318495991152889,
      "grad_norm": 0.3937755227088928,
      "learning_rate": 5.21805980886686e-06,
      "loss": 0.4537,
      "step": 42921
    },
    {
      "epoch": 1.3185267102878382,
      "grad_norm": 0.4517884850502014,
      "learning_rate": 5.21763537408968e-06,
      "loss": 0.4733,
      "step": 42922
    },
    {
      "epoch": 1.3185574294227875,
      "grad_norm": 0.412708580493927,
      "learning_rate": 5.2172109504820565e-06,
      "loss": 0.3855,
      "step": 42923
    },
    {
      "epoch": 1.3185881485577367,
      "grad_norm": 0.4473140835762024,
      "learning_rate": 5.216786538044967e-06,
      "loss": 0.5344,
      "step": 42924
    },
    {
      "epoch": 1.3186188676926858,
      "grad_norm": 0.3721320927143097,
      "learning_rate": 5.21636213677941e-06,
      "loss": 0.5325,
      "step": 42925
    },
    {
      "epoch": 1.318649586827635,
      "grad_norm": 0.46905896067619324,
      "learning_rate": 5.215937746686369e-06,
      "loss": 0.5026,
      "step": 42926
    },
    {
      "epoch": 1.3186803059625842,
      "grad_norm": 0.4145984351634979,
      "learning_rate": 5.21551336776684e-06,
      "loss": 0.4733,
      "step": 42927
    },
    {
      "epoch": 1.3187110250975334,
      "grad_norm": 0.45882707834243774,
      "learning_rate": 5.215089000021814e-06,
      "loss": 0.4409,
      "step": 42928
    },
    {
      "epoch": 1.3187417442324825,
      "grad_norm": 0.38935133814811707,
      "learning_rate": 5.214664643452285e-06,
      "loss": 0.4998,
      "step": 42929
    },
    {
      "epoch": 1.3187724633674316,
      "grad_norm": 0.4757137894630432,
      "learning_rate": 5.2142402980592375e-06,
      "loss": 0.538,
      "step": 42930
    },
    {
      "epoch": 1.3188031825023807,
      "grad_norm": 0.3912358582019806,
      "learning_rate": 5.2138159638436655e-06,
      "loss": 0.484,
      "step": 42931
    },
    {
      "epoch": 1.3188339016373298,
      "grad_norm": 0.4448964595794678,
      "learning_rate": 5.213391640806561e-06,
      "loss": 0.4676,
      "step": 42932
    },
    {
      "epoch": 1.318864620772279,
      "grad_norm": 0.5503606796264648,
      "learning_rate": 5.212967328948919e-06,
      "loss": 0.5185,
      "step": 42933
    },
    {
      "epoch": 1.3188953399072283,
      "grad_norm": 0.4813157021999359,
      "learning_rate": 5.212543028271722e-06,
      "loss": 0.5115,
      "step": 42934
    },
    {
      "epoch": 1.3189260590421774,
      "grad_norm": 0.4192254841327667,
      "learning_rate": 5.212118738775964e-06,
      "loss": 0.4409,
      "step": 42935
    },
    {
      "epoch": 1.3189567781771265,
      "grad_norm": 0.450408399105072,
      "learning_rate": 5.211694460462638e-06,
      "loss": 0.4952,
      "step": 42936
    },
    {
      "epoch": 1.3189874973120757,
      "grad_norm": 0.5090315341949463,
      "learning_rate": 5.211270193332733e-06,
      "loss": 0.5139,
      "step": 42937
    },
    {
      "epoch": 1.3190182164470248,
      "grad_norm": 0.4371171295642853,
      "learning_rate": 5.210845937387247e-06,
      "loss": 0.4551,
      "step": 42938
    },
    {
      "epoch": 1.3190489355819741,
      "grad_norm": 0.40698111057281494,
      "learning_rate": 5.210421692627159e-06,
      "loss": 0.4909,
      "step": 42939
    },
    {
      "epoch": 1.3190796547169232,
      "grad_norm": 0.46410804986953735,
      "learning_rate": 5.209997459053467e-06,
      "loss": 0.5803,
      "step": 42940
    },
    {
      "epoch": 1.3191103738518724,
      "grad_norm": 0.4444672167301178,
      "learning_rate": 5.209573236667158e-06,
      "loss": 0.4448,
      "step": 42941
    },
    {
      "epoch": 1.3191410929868215,
      "grad_norm": 0.411355584859848,
      "learning_rate": 5.209149025469231e-06,
      "loss": 0.4565,
      "step": 42942
    },
    {
      "epoch": 1.3191718121217706,
      "grad_norm": 0.5243231058120728,
      "learning_rate": 5.208724825460667e-06,
      "loss": 0.5121,
      "step": 42943
    },
    {
      "epoch": 1.3192025312567197,
      "grad_norm": 0.40519705414772034,
      "learning_rate": 5.208300636642462e-06,
      "loss": 0.4838,
      "step": 42944
    },
    {
      "epoch": 1.3192332503916688,
      "grad_norm": 0.46073344349861145,
      "learning_rate": 5.207876459015604e-06,
      "loss": 0.5991,
      "step": 42945
    },
    {
      "epoch": 1.3192639695266182,
      "grad_norm": 0.4129672944545746,
      "learning_rate": 5.207452292581089e-06,
      "loss": 0.4499,
      "step": 42946
    },
    {
      "epoch": 1.3192946886615673,
      "grad_norm": 0.4163520932197571,
      "learning_rate": 5.2070281373399e-06,
      "loss": 0.5328,
      "step": 42947
    },
    {
      "epoch": 1.3193254077965164,
      "grad_norm": 0.41827163100242615,
      "learning_rate": 5.206603993293036e-06,
      "loss": 0.4649,
      "step": 42948
    },
    {
      "epoch": 1.3193561269314655,
      "grad_norm": 0.4192090332508087,
      "learning_rate": 5.206179860441476e-06,
      "loss": 0.4613,
      "step": 42949
    },
    {
      "epoch": 1.3193868460664149,
      "grad_norm": 0.4473671317100525,
      "learning_rate": 5.205755738786225e-06,
      "loss": 0.4435,
      "step": 42950
    },
    {
      "epoch": 1.319417565201364,
      "grad_norm": 0.4156794846057892,
      "learning_rate": 5.205331628328261e-06,
      "loss": 0.4093,
      "step": 42951
    },
    {
      "epoch": 1.3194482843363131,
      "grad_norm": 0.42299166321754456,
      "learning_rate": 5.204907529068581e-06,
      "loss": 0.522,
      "step": 42952
    },
    {
      "epoch": 1.3194790034712622,
      "grad_norm": 0.4119740426540375,
      "learning_rate": 5.2044834410081775e-06,
      "loss": 0.475,
      "step": 42953
    },
    {
      "epoch": 1.3195097226062114,
      "grad_norm": 0.4176846146583557,
      "learning_rate": 5.204059364148031e-06,
      "loss": 0.463,
      "step": 42954
    },
    {
      "epoch": 1.3195404417411605,
      "grad_norm": 0.4109290838241577,
      "learning_rate": 5.203635298489147e-06,
      "loss": 0.4354,
      "step": 42955
    },
    {
      "epoch": 1.3195711608761096,
      "grad_norm": 0.4304661154747009,
      "learning_rate": 5.2032112440325025e-06,
      "loss": 0.5099,
      "step": 42956
    },
    {
      "epoch": 1.319601880011059,
      "grad_norm": 0.4179292917251587,
      "learning_rate": 5.202787200779098e-06,
      "loss": 0.4524,
      "step": 42957
    },
    {
      "epoch": 1.319632599146008,
      "grad_norm": 0.42948299646377563,
      "learning_rate": 5.20236316872991e-06,
      "loss": 0.4958,
      "step": 42958
    },
    {
      "epoch": 1.3196633182809572,
      "grad_norm": 0.42999738454818726,
      "learning_rate": 5.201939147885947e-06,
      "loss": 0.451,
      "step": 42959
    },
    {
      "epoch": 1.3196940374159063,
      "grad_norm": 0.4303871691226959,
      "learning_rate": 5.2015151382481855e-06,
      "loss": 0.4904,
      "step": 42960
    },
    {
      "epoch": 1.3197247565508556,
      "grad_norm": 0.39087286591529846,
      "learning_rate": 5.201091139817624e-06,
      "loss": 0.3743,
      "step": 42961
    },
    {
      "epoch": 1.3197554756858048,
      "grad_norm": 0.40715184807777405,
      "learning_rate": 5.200667152595247e-06,
      "loss": 0.4638,
      "step": 42962
    },
    {
      "epoch": 1.3197861948207539,
      "grad_norm": 0.4246029853820801,
      "learning_rate": 5.200243176582047e-06,
      "loss": 0.4527,
      "step": 42963
    },
    {
      "epoch": 1.319816913955703,
      "grad_norm": 0.4739965796470642,
      "learning_rate": 5.199819211779014e-06,
      "loss": 0.4354,
      "step": 42964
    },
    {
      "epoch": 1.3198476330906521,
      "grad_norm": 0.4448193907737732,
      "learning_rate": 5.199395258187141e-06,
      "loss": 0.5138,
      "step": 42965
    },
    {
      "epoch": 1.3198783522256012,
      "grad_norm": 0.4112233817577362,
      "learning_rate": 5.198971315807413e-06,
      "loss": 0.4714,
      "step": 42966
    },
    {
      "epoch": 1.3199090713605504,
      "grad_norm": 0.46085286140441895,
      "learning_rate": 5.198547384640822e-06,
      "loss": 0.518,
      "step": 42967
    },
    {
      "epoch": 1.3199397904954997,
      "grad_norm": 0.6640638709068298,
      "learning_rate": 5.198123464688358e-06,
      "loss": 0.4974,
      "step": 42968
    },
    {
      "epoch": 1.3199705096304488,
      "grad_norm": 0.4284000098705292,
      "learning_rate": 5.197699555951019e-06,
      "loss": 0.4657,
      "step": 42969
    },
    {
      "epoch": 1.320001228765398,
      "grad_norm": 0.38946399092674255,
      "learning_rate": 5.197275658429781e-06,
      "loss": 0.4452,
      "step": 42970
    },
    {
      "epoch": 1.320031947900347,
      "grad_norm": 0.41023969650268555,
      "learning_rate": 5.196851772125644e-06,
      "loss": 0.4624,
      "step": 42971
    },
    {
      "epoch": 1.3200626670352964,
      "grad_norm": 0.38186967372894287,
      "learning_rate": 5.1964278970395935e-06,
      "loss": 0.4942,
      "step": 42972
    },
    {
      "epoch": 1.3200933861702455,
      "grad_norm": 0.45050927996635437,
      "learning_rate": 5.1960040331726215e-06,
      "loss": 0.4632,
      "step": 42973
    },
    {
      "epoch": 1.3201241053051946,
      "grad_norm": 0.4040243625640869,
      "learning_rate": 5.195580180525721e-06,
      "loss": 0.4745,
      "step": 42974
    },
    {
      "epoch": 1.3201548244401438,
      "grad_norm": 0.40373867750167847,
      "learning_rate": 5.195156339099874e-06,
      "loss": 0.4259,
      "step": 42975
    },
    {
      "epoch": 1.3201855435750929,
      "grad_norm": 0.3916347324848175,
      "learning_rate": 5.194732508896076e-06,
      "loss": 0.4885,
      "step": 42976
    },
    {
      "epoch": 1.320216262710042,
      "grad_norm": 0.43234696984291077,
      "learning_rate": 5.194308689915315e-06,
      "loss": 0.4929,
      "step": 42977
    },
    {
      "epoch": 1.3202469818449911,
      "grad_norm": 0.408820241689682,
      "learning_rate": 5.193884882158586e-06,
      "loss": 0.485,
      "step": 42978
    },
    {
      "epoch": 1.3202777009799405,
      "grad_norm": 0.3982422351837158,
      "learning_rate": 5.193461085626872e-06,
      "loss": 0.5072,
      "step": 42979
    },
    {
      "epoch": 1.3203084201148896,
      "grad_norm": 0.47104525566101074,
      "learning_rate": 5.193037300321164e-06,
      "loss": 0.3934,
      "step": 42980
    },
    {
      "epoch": 1.3203391392498387,
      "grad_norm": 0.46839678287506104,
      "learning_rate": 5.192613526242454e-06,
      "loss": 0.4581,
      "step": 42981
    },
    {
      "epoch": 1.3203698583847878,
      "grad_norm": 0.42218250036239624,
      "learning_rate": 5.192189763391733e-06,
      "loss": 0.4708,
      "step": 42982
    },
    {
      "epoch": 1.3204005775197372,
      "grad_norm": 0.40320926904678345,
      "learning_rate": 5.191766011769986e-06,
      "loss": 0.47,
      "step": 42983
    },
    {
      "epoch": 1.3204312966546863,
      "grad_norm": 0.44638732075691223,
      "learning_rate": 5.191342271378208e-06,
      "loss": 0.4656,
      "step": 42984
    },
    {
      "epoch": 1.3204620157896354,
      "grad_norm": 0.4175148904323578,
      "learning_rate": 5.19091854221738e-06,
      "loss": 0.4435,
      "step": 42985
    },
    {
      "epoch": 1.3204927349245845,
      "grad_norm": 0.3810148239135742,
      "learning_rate": 5.190494824288503e-06,
      "loss": 0.443,
      "step": 42986
    },
    {
      "epoch": 1.3205234540595336,
      "grad_norm": 0.4088728725910187,
      "learning_rate": 5.19007111759256e-06,
      "loss": 0.4721,
      "step": 42987
    },
    {
      "epoch": 1.3205541731944828,
      "grad_norm": 0.4344327449798584,
      "learning_rate": 5.1896474221305436e-06,
      "loss": 0.4795,
      "step": 42988
    },
    {
      "epoch": 1.3205848923294319,
      "grad_norm": 0.38617563247680664,
      "learning_rate": 5.18922373790344e-06,
      "loss": 0.4931,
      "step": 42989
    },
    {
      "epoch": 1.3206156114643812,
      "grad_norm": 0.43145954608917236,
      "learning_rate": 5.188800064912234e-06,
      "loss": 0.5385,
      "step": 42990
    },
    {
      "epoch": 1.3206463305993303,
      "grad_norm": 0.39506766200065613,
      "learning_rate": 5.188376403157931e-06,
      "loss": 0.3444,
      "step": 42991
    },
    {
      "epoch": 1.3206770497342795,
      "grad_norm": 0.4111807644367218,
      "learning_rate": 5.187952752641505e-06,
      "loss": 0.4278,
      "step": 42992
    },
    {
      "epoch": 1.3207077688692286,
      "grad_norm": 0.47755980491638184,
      "learning_rate": 5.187529113363958e-06,
      "loss": 0.4701,
      "step": 42993
    },
    {
      "epoch": 1.320738488004178,
      "grad_norm": 0.432107537984848,
      "learning_rate": 5.187105485326267e-06,
      "loss": 0.4216,
      "step": 42994
    },
    {
      "epoch": 1.320769207139127,
      "grad_norm": 0.40480929613113403,
      "learning_rate": 5.186681868529428e-06,
      "loss": 0.4659,
      "step": 42995
    },
    {
      "epoch": 1.3207999262740762,
      "grad_norm": 0.4448167681694031,
      "learning_rate": 5.1862582629744295e-06,
      "loss": 0.4719,
      "step": 42996
    },
    {
      "epoch": 1.3208306454090253,
      "grad_norm": 0.4364053010940552,
      "learning_rate": 5.185834668662265e-06,
      "loss": 0.4704,
      "step": 42997
    },
    {
      "epoch": 1.3208613645439744,
      "grad_norm": 0.4102368950843811,
      "learning_rate": 5.1854110855939164e-06,
      "loss": 0.3685,
      "step": 42998
    },
    {
      "epoch": 1.3208920836789235,
      "grad_norm": 0.48557332158088684,
      "learning_rate": 5.184987513770375e-06,
      "loss": 0.4904,
      "step": 42999
    },
    {
      "epoch": 1.3209228028138726,
      "grad_norm": 0.4582790732383728,
      "learning_rate": 5.1845639531926325e-06,
      "loss": 0.5051,
      "step": 43000
    },
    {
      "epoch": 1.320953521948822,
      "grad_norm": 0.4099413752555847,
      "learning_rate": 5.184140403861682e-06,
      "loss": 0.3929,
      "step": 43001
    },
    {
      "epoch": 1.320984241083771,
      "grad_norm": 0.39949995279312134,
      "learning_rate": 5.1837168657785034e-06,
      "loss": 0.4195,
      "step": 43002
    },
    {
      "epoch": 1.3210149602187202,
      "grad_norm": 0.42195844650268555,
      "learning_rate": 5.183293338944089e-06,
      "loss": 0.4379,
      "step": 43003
    },
    {
      "epoch": 1.3210456793536693,
      "grad_norm": 0.5591142177581787,
      "learning_rate": 5.182869823359431e-06,
      "loss": 0.4572,
      "step": 43004
    },
    {
      "epoch": 1.3210763984886187,
      "grad_norm": 0.4222988784313202,
      "learning_rate": 5.18244631902552e-06,
      "loss": 0.485,
      "step": 43005
    },
    {
      "epoch": 1.3211071176235678,
      "grad_norm": 0.4109508693218231,
      "learning_rate": 5.1820228259433395e-06,
      "loss": 0.4635,
      "step": 43006
    },
    {
      "epoch": 1.321137836758517,
      "grad_norm": 0.3952116370201111,
      "learning_rate": 5.181599344113879e-06,
      "loss": 0.4854,
      "step": 43007
    },
    {
      "epoch": 1.321168555893466,
      "grad_norm": 0.41638925671577454,
      "learning_rate": 5.1811758735381316e-06,
      "loss": 0.5009,
      "step": 43008
    },
    {
      "epoch": 1.3211992750284152,
      "grad_norm": 0.4449926018714905,
      "learning_rate": 5.180752414217084e-06,
      "loss": 0.4302,
      "step": 43009
    },
    {
      "epoch": 1.3212299941633643,
      "grad_norm": 0.39936020970344543,
      "learning_rate": 5.180328966151729e-06,
      "loss": 0.4175,
      "step": 43010
    },
    {
      "epoch": 1.3212607132983134,
      "grad_norm": 0.4029843211174011,
      "learning_rate": 5.17990552934305e-06,
      "loss": 0.4771,
      "step": 43011
    },
    {
      "epoch": 1.3212914324332627,
      "grad_norm": 0.4223518371582031,
      "learning_rate": 5.179482103792036e-06,
      "loss": 0.3992,
      "step": 43012
    },
    {
      "epoch": 1.3213221515682119,
      "grad_norm": 0.4814651608467102,
      "learning_rate": 5.17905868949968e-06,
      "loss": 0.5021,
      "step": 43013
    },
    {
      "epoch": 1.321352870703161,
      "grad_norm": 0.4141772985458374,
      "learning_rate": 5.178635286466972e-06,
      "loss": 0.4543,
      "step": 43014
    },
    {
      "epoch": 1.32138358983811,
      "grad_norm": 0.4231468439102173,
      "learning_rate": 5.178211894694895e-06,
      "loss": 0.4859,
      "step": 43015
    },
    {
      "epoch": 1.3214143089730594,
      "grad_norm": 0.5101913213729858,
      "learning_rate": 5.17778851418444e-06,
      "loss": 0.5535,
      "step": 43016
    },
    {
      "epoch": 1.3214450281080086,
      "grad_norm": 0.4156157076358795,
      "learning_rate": 5.177365144936597e-06,
      "loss": 0.4845,
      "step": 43017
    },
    {
      "epoch": 1.3214757472429577,
      "grad_norm": 0.4326683580875397,
      "learning_rate": 5.176941786952358e-06,
      "loss": 0.5053,
      "step": 43018
    },
    {
      "epoch": 1.3215064663779068,
      "grad_norm": 0.3843710720539093,
      "learning_rate": 5.176518440232705e-06,
      "loss": 0.4816,
      "step": 43019
    },
    {
      "epoch": 1.321537185512856,
      "grad_norm": 0.4072047770023346,
      "learning_rate": 5.176095104778634e-06,
      "loss": 0.4677,
      "step": 43020
    },
    {
      "epoch": 1.321567904647805,
      "grad_norm": 0.41529446840286255,
      "learning_rate": 5.175671780591123e-06,
      "loss": 0.5128,
      "step": 43021
    },
    {
      "epoch": 1.3215986237827542,
      "grad_norm": 0.3972415626049042,
      "learning_rate": 5.1752484676711726e-06,
      "loss": 0.5121,
      "step": 43022
    },
    {
      "epoch": 1.3216293429177035,
      "grad_norm": 0.40417012572288513,
      "learning_rate": 5.174825166019765e-06,
      "loss": 0.5676,
      "step": 43023
    },
    {
      "epoch": 1.3216600620526526,
      "grad_norm": 0.42778319120407104,
      "learning_rate": 5.174401875637892e-06,
      "loss": 0.4892,
      "step": 43024
    },
    {
      "epoch": 1.3216907811876017,
      "grad_norm": 0.4285006821155548,
      "learning_rate": 5.173978596526539e-06,
      "loss": 0.543,
      "step": 43025
    },
    {
      "epoch": 1.3217215003225509,
      "grad_norm": 0.37739190459251404,
      "learning_rate": 5.17355532868669e-06,
      "loss": 0.461,
      "step": 43026
    },
    {
      "epoch": 1.3217522194575002,
      "grad_norm": 0.3699471354484558,
      "learning_rate": 5.173132072119348e-06,
      "loss": 0.4064,
      "step": 43027
    },
    {
      "epoch": 1.3217829385924493,
      "grad_norm": 0.4338183104991913,
      "learning_rate": 5.17270882682549e-06,
      "loss": 0.4968,
      "step": 43028
    },
    {
      "epoch": 1.3218136577273984,
      "grad_norm": 0.45254236459732056,
      "learning_rate": 5.17228559280611e-06,
      "loss": 0.5434,
      "step": 43029
    },
    {
      "epoch": 1.3218443768623476,
      "grad_norm": 0.4017240107059479,
      "learning_rate": 5.171862370062191e-06,
      "loss": 0.4838,
      "step": 43030
    },
    {
      "epoch": 1.3218750959972967,
      "grad_norm": 0.4130469262599945,
      "learning_rate": 5.171439158594726e-06,
      "loss": 0.4171,
      "step": 43031
    },
    {
      "epoch": 1.3219058151322458,
      "grad_norm": 0.4312276542186737,
      "learning_rate": 5.1710159584047e-06,
      "loss": 0.4522,
      "step": 43032
    },
    {
      "epoch": 1.321936534267195,
      "grad_norm": 0.38298389315605164,
      "learning_rate": 5.170592769493108e-06,
      "loss": 0.4635,
      "step": 43033
    },
    {
      "epoch": 1.3219672534021443,
      "grad_norm": 0.3842548131942749,
      "learning_rate": 5.170169591860931e-06,
      "loss": 0.397,
      "step": 43034
    },
    {
      "epoch": 1.3219979725370934,
      "grad_norm": 0.4310978949069977,
      "learning_rate": 5.169746425509159e-06,
      "loss": 0.5043,
      "step": 43035
    },
    {
      "epoch": 1.3220286916720425,
      "grad_norm": 0.47160616517066956,
      "learning_rate": 5.169323270438782e-06,
      "loss": 0.4521,
      "step": 43036
    },
    {
      "epoch": 1.3220594108069916,
      "grad_norm": 0.41131752729415894,
      "learning_rate": 5.168900126650792e-06,
      "loss": 0.5183,
      "step": 43037
    },
    {
      "epoch": 1.322090129941941,
      "grad_norm": 0.4228709042072296,
      "learning_rate": 5.16847699414617e-06,
      "loss": 0.456,
      "step": 43038
    },
    {
      "epoch": 1.32212084907689,
      "grad_norm": 0.4361117482185364,
      "learning_rate": 5.168053872925905e-06,
      "loss": 0.4149,
      "step": 43039
    },
    {
      "epoch": 1.3221515682118392,
      "grad_norm": 0.41922158002853394,
      "learning_rate": 5.1676307629909894e-06,
      "loss": 0.411,
      "step": 43040
    },
    {
      "epoch": 1.3221822873467883,
      "grad_norm": 0.487289160490036,
      "learning_rate": 5.167207664342413e-06,
      "loss": 0.4473,
      "step": 43041
    },
    {
      "epoch": 1.3222130064817375,
      "grad_norm": 0.4695543944835663,
      "learning_rate": 5.166784576981157e-06,
      "loss": 0.4909,
      "step": 43042
    },
    {
      "epoch": 1.3222437256166866,
      "grad_norm": 0.3728543221950531,
      "learning_rate": 5.166361500908213e-06,
      "loss": 0.4477,
      "step": 43043
    },
    {
      "epoch": 1.3222744447516357,
      "grad_norm": 0.39784038066864014,
      "learning_rate": 5.16593843612457e-06,
      "loss": 0.4494,
      "step": 43044
    },
    {
      "epoch": 1.322305163886585,
      "grad_norm": 0.3997074365615845,
      "learning_rate": 5.165515382631214e-06,
      "loss": 0.4686,
      "step": 43045
    },
    {
      "epoch": 1.3223358830215342,
      "grad_norm": 0.3776274025440216,
      "learning_rate": 5.165092340429141e-06,
      "loss": 0.4215,
      "step": 43046
    },
    {
      "epoch": 1.3223666021564833,
      "grad_norm": 0.40243104100227356,
      "learning_rate": 5.1646693095193255e-06,
      "loss": 0.5121,
      "step": 43047
    },
    {
      "epoch": 1.3223973212914324,
      "grad_norm": 0.47424760460853577,
      "learning_rate": 5.1642462899027645e-06,
      "loss": 0.4724,
      "step": 43048
    },
    {
      "epoch": 1.3224280404263815,
      "grad_norm": 0.464574933052063,
      "learning_rate": 5.1638232815804425e-06,
      "loss": 0.5556,
      "step": 43049
    },
    {
      "epoch": 1.3224587595613309,
      "grad_norm": 0.39568108320236206,
      "learning_rate": 5.163400284553355e-06,
      "loss": 0.4602,
      "step": 43050
    },
    {
      "epoch": 1.32248947869628,
      "grad_norm": 0.40880465507507324,
      "learning_rate": 5.162977298822478e-06,
      "loss": 0.507,
      "step": 43051
    },
    {
      "epoch": 1.322520197831229,
      "grad_norm": 0.39776164293289185,
      "learning_rate": 5.1625543243888095e-06,
      "loss": 0.497,
      "step": 43052
    },
    {
      "epoch": 1.3225509169661782,
      "grad_norm": 0.39246490597724915,
      "learning_rate": 5.162131361253326e-06,
      "loss": 0.5124,
      "step": 43053
    },
    {
      "epoch": 1.3225816361011273,
      "grad_norm": 0.40856605768203735,
      "learning_rate": 5.16170840941703e-06,
      "loss": 0.4255,
      "step": 43054
    },
    {
      "epoch": 1.3226123552360765,
      "grad_norm": 0.3948785662651062,
      "learning_rate": 5.161285468880899e-06,
      "loss": 0.5348,
      "step": 43055
    },
    {
      "epoch": 1.3226430743710256,
      "grad_norm": 0.42695820331573486,
      "learning_rate": 5.160862539645927e-06,
      "loss": 0.5215,
      "step": 43056
    },
    {
      "epoch": 1.322673793505975,
      "grad_norm": 0.36082494258880615,
      "learning_rate": 5.16043962171309e-06,
      "loss": 0.4566,
      "step": 43057
    },
    {
      "epoch": 1.322704512640924,
      "grad_norm": 0.3850937485694885,
      "learning_rate": 5.160016715083393e-06,
      "loss": 0.4875,
      "step": 43058
    },
    {
      "epoch": 1.3227352317758732,
      "grad_norm": 0.3989220857620239,
      "learning_rate": 5.159593819757811e-06,
      "loss": 0.5167,
      "step": 43059
    },
    {
      "epoch": 1.3227659509108223,
      "grad_norm": 0.467202752828598,
      "learning_rate": 5.159170935737339e-06,
      "loss": 0.4277,
      "step": 43060
    },
    {
      "epoch": 1.3227966700457716,
      "grad_norm": 0.42015719413757324,
      "learning_rate": 5.158748063022958e-06,
      "loss": 0.5274,
      "step": 43061
    },
    {
      "epoch": 1.3228273891807207,
      "grad_norm": 0.4264383018016815,
      "learning_rate": 5.1583252016156545e-06,
      "loss": 0.5334,
      "step": 43062
    },
    {
      "epoch": 1.3228581083156699,
      "grad_norm": 0.40895891189575195,
      "learning_rate": 5.157902351516428e-06,
      "loss": 0.4745,
      "step": 43063
    },
    {
      "epoch": 1.322888827450619,
      "grad_norm": 0.388895720243454,
      "learning_rate": 5.157479512726257e-06,
      "loss": 0.4743,
      "step": 43064
    },
    {
      "epoch": 1.322919546585568,
      "grad_norm": 0.41995713114738464,
      "learning_rate": 5.157056685246134e-06,
      "loss": 0.3757,
      "step": 43065
    },
    {
      "epoch": 1.3229502657205172,
      "grad_norm": 0.396491676568985,
      "learning_rate": 5.1566338690770375e-06,
      "loss": 0.4363,
      "step": 43066
    },
    {
      "epoch": 1.3229809848554663,
      "grad_norm": 0.39975467324256897,
      "learning_rate": 5.156211064219963e-06,
      "loss": 0.4887,
      "step": 43067
    },
    {
      "epoch": 1.3230117039904157,
      "grad_norm": 0.40098798274993896,
      "learning_rate": 5.155788270675894e-06,
      "loss": 0.4572,
      "step": 43068
    },
    {
      "epoch": 1.3230424231253648,
      "grad_norm": 0.4293505847454071,
      "learning_rate": 5.155365488445825e-06,
      "loss": 0.4411,
      "step": 43069
    },
    {
      "epoch": 1.323073142260314,
      "grad_norm": 0.4123075306415558,
      "learning_rate": 5.154942717530734e-06,
      "loss": 0.4845,
      "step": 43070
    },
    {
      "epoch": 1.323103861395263,
      "grad_norm": 0.3684917092323303,
      "learning_rate": 5.154519957931613e-06,
      "loss": 0.4991,
      "step": 43071
    },
    {
      "epoch": 1.3231345805302124,
      "grad_norm": 0.39212939143180847,
      "learning_rate": 5.154097209649449e-06,
      "loss": 0.4921,
      "step": 43072
    },
    {
      "epoch": 1.3231652996651615,
      "grad_norm": 0.3743046820163727,
      "learning_rate": 5.153674472685233e-06,
      "loss": 0.4553,
      "step": 43073
    },
    {
      "epoch": 1.3231960188001106,
      "grad_norm": 0.4006820321083069,
      "learning_rate": 5.153251747039944e-06,
      "loss": 0.5026,
      "step": 43074
    },
    {
      "epoch": 1.3232267379350597,
      "grad_norm": 0.39450615644454956,
      "learning_rate": 5.152829032714576e-06,
      "loss": 0.4643,
      "step": 43075
    },
    {
      "epoch": 1.3232574570700089,
      "grad_norm": 0.45594707131385803,
      "learning_rate": 5.152406329710114e-06,
      "loss": 0.5153,
      "step": 43076
    },
    {
      "epoch": 1.323288176204958,
      "grad_norm": 0.43849632143974304,
      "learning_rate": 5.1519836380275465e-06,
      "loss": 0.4133,
      "step": 43077
    },
    {
      "epoch": 1.323318895339907,
      "grad_norm": 0.39951664209365845,
      "learning_rate": 5.151560957667858e-06,
      "loss": 0.3772,
      "step": 43078
    },
    {
      "epoch": 1.3233496144748564,
      "grad_norm": 0.38655564188957214,
      "learning_rate": 5.151138288632038e-06,
      "loss": 0.4776,
      "step": 43079
    },
    {
      "epoch": 1.3233803336098056,
      "grad_norm": 0.41360074281692505,
      "learning_rate": 5.150715630921073e-06,
      "loss": 0.5359,
      "step": 43080
    },
    {
      "epoch": 1.3234110527447547,
      "grad_norm": 0.42742618918418884,
      "learning_rate": 5.15029298453595e-06,
      "loss": 0.4961,
      "step": 43081
    },
    {
      "epoch": 1.3234417718797038,
      "grad_norm": 0.4289793074131012,
      "learning_rate": 5.149870349477662e-06,
      "loss": 0.588,
      "step": 43082
    },
    {
      "epoch": 1.3234724910146531,
      "grad_norm": 0.4039841592311859,
      "learning_rate": 5.1494477257471834e-06,
      "loss": 0.4557,
      "step": 43083
    },
    {
      "epoch": 1.3235032101496023,
      "grad_norm": 0.43013253808021545,
      "learning_rate": 5.149025113345511e-06,
      "loss": 0.4723,
      "step": 43084
    },
    {
      "epoch": 1.3235339292845514,
      "grad_norm": 0.39160242676734924,
      "learning_rate": 5.148602512273628e-06,
      "loss": 0.4342,
      "step": 43085
    },
    {
      "epoch": 1.3235646484195005,
      "grad_norm": 0.40220916271209717,
      "learning_rate": 5.148179922532526e-06,
      "loss": 0.4704,
      "step": 43086
    },
    {
      "epoch": 1.3235953675544496,
      "grad_norm": 0.4128410518169403,
      "learning_rate": 5.147757344123185e-06,
      "loss": 0.4463,
      "step": 43087
    },
    {
      "epoch": 1.3236260866893987,
      "grad_norm": 0.43399447202682495,
      "learning_rate": 5.147334777046601e-06,
      "loss": 0.4716,
      "step": 43088
    },
    {
      "epoch": 1.3236568058243479,
      "grad_norm": 0.40038010478019714,
      "learning_rate": 5.146912221303747e-06,
      "loss": 0.4376,
      "step": 43089
    },
    {
      "epoch": 1.3236875249592972,
      "grad_norm": 0.41007158160209656,
      "learning_rate": 5.1464896768956255e-06,
      "loss": 0.4883,
      "step": 43090
    },
    {
      "epoch": 1.3237182440942463,
      "grad_norm": 0.4136252999305725,
      "learning_rate": 5.146067143823213e-06,
      "loss": 0.4811,
      "step": 43091
    },
    {
      "epoch": 1.3237489632291954,
      "grad_norm": 0.41909414529800415,
      "learning_rate": 5.145644622087504e-06,
      "loss": 0.4612,
      "step": 43092
    },
    {
      "epoch": 1.3237796823641446,
      "grad_norm": 0.4091249704360962,
      "learning_rate": 5.145222111689476e-06,
      "loss": 0.5061,
      "step": 43093
    },
    {
      "epoch": 1.323810401499094,
      "grad_norm": 0.4220655858516693,
      "learning_rate": 5.144799612630122e-06,
      "loss": 0.462,
      "step": 43094
    },
    {
      "epoch": 1.323841120634043,
      "grad_norm": 0.531584620475769,
      "learning_rate": 5.1443771249104264e-06,
      "loss": 0.3882,
      "step": 43095
    },
    {
      "epoch": 1.3238718397689921,
      "grad_norm": 0.4335702657699585,
      "learning_rate": 5.143954648531382e-06,
      "loss": 0.4911,
      "step": 43096
    },
    {
      "epoch": 1.3239025589039413,
      "grad_norm": 0.397249311208725,
      "learning_rate": 5.143532183493966e-06,
      "loss": 0.5474,
      "step": 43097
    },
    {
      "epoch": 1.3239332780388904,
      "grad_norm": 0.37379345297813416,
      "learning_rate": 5.143109729799167e-06,
      "loss": 0.5437,
      "step": 43098
    },
    {
      "epoch": 1.3239639971738395,
      "grad_norm": 0.4009157717227936,
      "learning_rate": 5.142687287447981e-06,
      "loss": 0.4626,
      "step": 43099
    },
    {
      "epoch": 1.3239947163087886,
      "grad_norm": 0.3818761110305786,
      "learning_rate": 5.142264856441386e-06,
      "loss": 0.4356,
      "step": 43100
    },
    {
      "epoch": 1.324025435443738,
      "grad_norm": 0.4021497964859009,
      "learning_rate": 5.141842436780373e-06,
      "loss": 0.4961,
      "step": 43101
    },
    {
      "epoch": 1.324056154578687,
      "grad_norm": 0.383851021528244,
      "learning_rate": 5.141420028465922e-06,
      "loss": 0.4082,
      "step": 43102
    },
    {
      "epoch": 1.3240868737136362,
      "grad_norm": 0.43276676535606384,
      "learning_rate": 5.140997631499025e-06,
      "loss": 0.4345,
      "step": 43103
    },
    {
      "epoch": 1.3241175928485853,
      "grad_norm": 0.41229915618896484,
      "learning_rate": 5.140575245880667e-06,
      "loss": 0.4045,
      "step": 43104
    },
    {
      "epoch": 1.3241483119835347,
      "grad_norm": 0.44883161783218384,
      "learning_rate": 5.140152871611838e-06,
      "loss": 0.4802,
      "step": 43105
    },
    {
      "epoch": 1.3241790311184838,
      "grad_norm": 0.43036019802093506,
      "learning_rate": 5.139730508693519e-06,
      "loss": 0.5461,
      "step": 43106
    },
    {
      "epoch": 1.324209750253433,
      "grad_norm": 0.4462887644767761,
      "learning_rate": 5.1393081571266966e-06,
      "loss": 0.4895,
      "step": 43107
    },
    {
      "epoch": 1.324240469388382,
      "grad_norm": 0.3754996657371521,
      "learning_rate": 5.138885816912362e-06,
      "loss": 0.5001,
      "step": 43108
    },
    {
      "epoch": 1.3242711885233311,
      "grad_norm": 0.3986242413520813,
      "learning_rate": 5.138463488051502e-06,
      "loss": 0.5087,
      "step": 43109
    },
    {
      "epoch": 1.3243019076582803,
      "grad_norm": 0.48862534761428833,
      "learning_rate": 5.138041170545096e-06,
      "loss": 0.4668,
      "step": 43110
    },
    {
      "epoch": 1.3243326267932294,
      "grad_norm": 0.4510021507740021,
      "learning_rate": 5.137618864394134e-06,
      "loss": 0.3815,
      "step": 43111
    },
    {
      "epoch": 1.3243633459281787,
      "grad_norm": 0.4300871789455414,
      "learning_rate": 5.137196569599603e-06,
      "loss": 0.4333,
      "step": 43112
    },
    {
      "epoch": 1.3243940650631278,
      "grad_norm": 0.40080952644348145,
      "learning_rate": 5.136774286162494e-06,
      "loss": 0.4363,
      "step": 43113
    },
    {
      "epoch": 1.324424784198077,
      "grad_norm": 0.4048103392124176,
      "learning_rate": 5.136352014083783e-06,
      "loss": 0.4899,
      "step": 43114
    },
    {
      "epoch": 1.324455503333026,
      "grad_norm": 0.39665138721466064,
      "learning_rate": 5.135929753364466e-06,
      "loss": 0.4907,
      "step": 43115
    },
    {
      "epoch": 1.3244862224679754,
      "grad_norm": 0.44696876406669617,
      "learning_rate": 5.135507504005516e-06,
      "loss": 0.4169,
      "step": 43116
    },
    {
      "epoch": 1.3245169416029245,
      "grad_norm": 0.501818835735321,
      "learning_rate": 5.135085266007933e-06,
      "loss": 0.4994,
      "step": 43117
    },
    {
      "epoch": 1.3245476607378737,
      "grad_norm": 0.4651665687561035,
      "learning_rate": 5.134663039372702e-06,
      "loss": 0.4601,
      "step": 43118
    },
    {
      "epoch": 1.3245783798728228,
      "grad_norm": 0.38333019614219666,
      "learning_rate": 5.1342408241008e-06,
      "loss": 0.4497,
      "step": 43119
    },
    {
      "epoch": 1.324609099007772,
      "grad_norm": 0.4010026752948761,
      "learning_rate": 5.13381862019322e-06,
      "loss": 0.4951,
      "step": 43120
    },
    {
      "epoch": 1.324639818142721,
      "grad_norm": 0.40386250615119934,
      "learning_rate": 5.133396427650945e-06,
      "loss": 0.4881,
      "step": 43121
    },
    {
      "epoch": 1.3246705372776701,
      "grad_norm": 0.39728063344955444,
      "learning_rate": 5.132974246474968e-06,
      "loss": 0.493,
      "step": 43122
    },
    {
      "epoch": 1.3247012564126195,
      "grad_norm": 0.4785974621772766,
      "learning_rate": 5.132552076666265e-06,
      "loss": 0.4409,
      "step": 43123
    },
    {
      "epoch": 1.3247319755475686,
      "grad_norm": 0.40803036093711853,
      "learning_rate": 5.13212991822583e-06,
      "loss": 0.4754,
      "step": 43124
    },
    {
      "epoch": 1.3247626946825177,
      "grad_norm": 0.3824067711830139,
      "learning_rate": 5.131707771154639e-06,
      "loss": 0.458,
      "step": 43125
    },
    {
      "epoch": 1.3247934138174668,
      "grad_norm": 0.4040444791316986,
      "learning_rate": 5.131285635453691e-06,
      "loss": 0.4887,
      "step": 43126
    },
    {
      "epoch": 1.3248241329524162,
      "grad_norm": 0.4222276210784912,
      "learning_rate": 5.130863511123962e-06,
      "loss": 0.4415,
      "step": 43127
    },
    {
      "epoch": 1.3248548520873653,
      "grad_norm": 0.43125438690185547,
      "learning_rate": 5.130441398166446e-06,
      "loss": 0.506,
      "step": 43128
    },
    {
      "epoch": 1.3248855712223144,
      "grad_norm": 0.9650240540504456,
      "learning_rate": 5.13001929658212e-06,
      "loss": 0.5145,
      "step": 43129
    },
    {
      "epoch": 1.3249162903572635,
      "grad_norm": 0.39274632930755615,
      "learning_rate": 5.129597206371972e-06,
      "loss": 0.5053,
      "step": 43130
    },
    {
      "epoch": 1.3249470094922127,
      "grad_norm": 0.4319349527359009,
      "learning_rate": 5.129175127536992e-06,
      "loss": 0.4701,
      "step": 43131
    },
    {
      "epoch": 1.3249777286271618,
      "grad_norm": 0.4762178063392639,
      "learning_rate": 5.128753060078166e-06,
      "loss": 0.5065,
      "step": 43132
    },
    {
      "epoch": 1.325008447762111,
      "grad_norm": 0.3911314904689789,
      "learning_rate": 5.128331003996476e-06,
      "loss": 0.4304,
      "step": 43133
    },
    {
      "epoch": 1.3250391668970602,
      "grad_norm": 0.4275049865245819,
      "learning_rate": 5.127908959292908e-06,
      "loss": 0.4921,
      "step": 43134
    },
    {
      "epoch": 1.3250698860320094,
      "grad_norm": 0.41736799478530884,
      "learning_rate": 5.127486925968448e-06,
      "loss": 0.4731,
      "step": 43135
    },
    {
      "epoch": 1.3251006051669585,
      "grad_norm": 0.40993747115135193,
      "learning_rate": 5.127064904024084e-06,
      "loss": 0.4622,
      "step": 43136
    },
    {
      "epoch": 1.3251313243019076,
      "grad_norm": 0.3811512589454651,
      "learning_rate": 5.126642893460803e-06,
      "loss": 0.5216,
      "step": 43137
    },
    {
      "epoch": 1.325162043436857,
      "grad_norm": 0.43309977650642395,
      "learning_rate": 5.1262208942795835e-06,
      "loss": 0.4224,
      "step": 43138
    },
    {
      "epoch": 1.325192762571806,
      "grad_norm": 0.4547024667263031,
      "learning_rate": 5.1257989064814164e-06,
      "loss": 0.3881,
      "step": 43139
    },
    {
      "epoch": 1.3252234817067552,
      "grad_norm": 0.39776578545570374,
      "learning_rate": 5.1253769300672875e-06,
      "loss": 0.4531,
      "step": 43140
    },
    {
      "epoch": 1.3252542008417043,
      "grad_norm": 0.5046728253364563,
      "learning_rate": 5.124954965038183e-06,
      "loss": 0.5087,
      "step": 43141
    },
    {
      "epoch": 1.3252849199766534,
      "grad_norm": 0.4194552004337311,
      "learning_rate": 5.124533011395083e-06,
      "loss": 0.4593,
      "step": 43142
    },
    {
      "epoch": 1.3253156391116026,
      "grad_norm": 0.39836469292640686,
      "learning_rate": 5.124111069138977e-06,
      "loss": 0.5497,
      "step": 43143
    },
    {
      "epoch": 1.3253463582465517,
      "grad_norm": 0.38363489508628845,
      "learning_rate": 5.123689138270851e-06,
      "loss": 0.5874,
      "step": 43144
    },
    {
      "epoch": 1.325377077381501,
      "grad_norm": 0.46878254413604736,
      "learning_rate": 5.123267218791693e-06,
      "loss": 0.4363,
      "step": 43145
    },
    {
      "epoch": 1.3254077965164501,
      "grad_norm": 0.39981481432914734,
      "learning_rate": 5.122845310702481e-06,
      "loss": 0.4833,
      "step": 43146
    },
    {
      "epoch": 1.3254385156513993,
      "grad_norm": 0.44186073541641235,
      "learning_rate": 5.122423414004205e-06,
      "loss": 0.5329,
      "step": 43147
    },
    {
      "epoch": 1.3254692347863484,
      "grad_norm": 0.4085625410079956,
      "learning_rate": 5.122001528697848e-06,
      "loss": 0.5097,
      "step": 43148
    },
    {
      "epoch": 1.3254999539212977,
      "grad_norm": 0.41495418548583984,
      "learning_rate": 5.121579654784403e-06,
      "loss": 0.461,
      "step": 43149
    },
    {
      "epoch": 1.3255306730562468,
      "grad_norm": 0.4385090470314026,
      "learning_rate": 5.121157792264845e-06,
      "loss": 0.5053,
      "step": 43150
    },
    {
      "epoch": 1.325561392191196,
      "grad_norm": 0.4223659336566925,
      "learning_rate": 5.120735941140167e-06,
      "loss": 0.48,
      "step": 43151
    },
    {
      "epoch": 1.325592111326145,
      "grad_norm": 0.40632766485214233,
      "learning_rate": 5.120314101411343e-06,
      "loss": 0.4811,
      "step": 43152
    },
    {
      "epoch": 1.3256228304610942,
      "grad_norm": 0.4168040454387665,
      "learning_rate": 5.119892273079371e-06,
      "loss": 0.5641,
      "step": 43153
    },
    {
      "epoch": 1.3256535495960433,
      "grad_norm": 0.37788939476013184,
      "learning_rate": 5.119470456145234e-06,
      "loss": 0.4621,
      "step": 43154
    },
    {
      "epoch": 1.3256842687309924,
      "grad_norm": 0.39303094148635864,
      "learning_rate": 5.1190486506099125e-06,
      "loss": 0.4754,
      "step": 43155
    },
    {
      "epoch": 1.3257149878659418,
      "grad_norm": 0.4210941791534424,
      "learning_rate": 5.118626856474396e-06,
      "loss": 0.4243,
      "step": 43156
    },
    {
      "epoch": 1.325745707000891,
      "grad_norm": 0.4224548935890198,
      "learning_rate": 5.118205073739662e-06,
      "loss": 0.4981,
      "step": 43157
    },
    {
      "epoch": 1.32577642613584,
      "grad_norm": 0.3952028155326843,
      "learning_rate": 5.1177833024067056e-06,
      "loss": 0.4445,
      "step": 43158
    },
    {
      "epoch": 1.3258071452707891,
      "grad_norm": 0.42339757084846497,
      "learning_rate": 5.117361542476505e-06,
      "loss": 0.4818,
      "step": 43159
    },
    {
      "epoch": 1.3258378644057383,
      "grad_norm": 0.4382331669330597,
      "learning_rate": 5.116939793950051e-06,
      "loss": 0.4975,
      "step": 43160
    },
    {
      "epoch": 1.3258685835406876,
      "grad_norm": 0.4369461238384247,
      "learning_rate": 5.116518056828319e-06,
      "loss": 0.5589,
      "step": 43161
    },
    {
      "epoch": 1.3258993026756367,
      "grad_norm": 0.41782456636428833,
      "learning_rate": 5.116096331112306e-06,
      "loss": 0.5465,
      "step": 43162
    },
    {
      "epoch": 1.3259300218105858,
      "grad_norm": 0.40178170800209045,
      "learning_rate": 5.115674616802988e-06,
      "loss": 0.4886,
      "step": 43163
    },
    {
      "epoch": 1.325960740945535,
      "grad_norm": 0.4322246313095093,
      "learning_rate": 5.115252913901356e-06,
      "loss": 0.5442,
      "step": 43164
    },
    {
      "epoch": 1.325991460080484,
      "grad_norm": 0.44244134426116943,
      "learning_rate": 5.11483122240839e-06,
      "loss": 0.5236,
      "step": 43165
    },
    {
      "epoch": 1.3260221792154332,
      "grad_norm": 0.41040125489234924,
      "learning_rate": 5.114409542325075e-06,
      "loss": 0.5433,
      "step": 43166
    },
    {
      "epoch": 1.3260528983503825,
      "grad_norm": 0.39026039838790894,
      "learning_rate": 5.1139878736523975e-06,
      "loss": 0.5048,
      "step": 43167
    },
    {
      "epoch": 1.3260836174853317,
      "grad_norm": 0.4498607814311981,
      "learning_rate": 5.113566216391348e-06,
      "loss": 0.3645,
      "step": 43168
    },
    {
      "epoch": 1.3261143366202808,
      "grad_norm": 0.40279197692871094,
      "learning_rate": 5.113144570542901e-06,
      "loss": 0.4197,
      "step": 43169
    },
    {
      "epoch": 1.32614505575523,
      "grad_norm": 0.43182849884033203,
      "learning_rate": 5.112722936108046e-06,
      "loss": 0.4356,
      "step": 43170
    },
    {
      "epoch": 1.326175774890179,
      "grad_norm": 0.41040509939193726,
      "learning_rate": 5.112301313087769e-06,
      "loss": 0.5237,
      "step": 43171
    },
    {
      "epoch": 1.3262064940251284,
      "grad_norm": 0.4244481921195984,
      "learning_rate": 5.111879701483054e-06,
      "loss": 0.4826,
      "step": 43172
    },
    {
      "epoch": 1.3262372131600775,
      "grad_norm": 0.4613820016384125,
      "learning_rate": 5.111458101294887e-06,
      "loss": 0.4245,
      "step": 43173
    },
    {
      "epoch": 1.3262679322950266,
      "grad_norm": 0.4124862849712372,
      "learning_rate": 5.1110365125242475e-06,
      "loss": 0.5212,
      "step": 43174
    },
    {
      "epoch": 1.3262986514299757,
      "grad_norm": 0.39830559492111206,
      "learning_rate": 5.110614935172126e-06,
      "loss": 0.4821,
      "step": 43175
    },
    {
      "epoch": 1.3263293705649248,
      "grad_norm": 0.41945382952690125,
      "learning_rate": 5.1101933692395026e-06,
      "loss": 0.5292,
      "step": 43176
    },
    {
      "epoch": 1.326360089699874,
      "grad_norm": 0.5203795433044434,
      "learning_rate": 5.109771814727369e-06,
      "loss": 0.5518,
      "step": 43177
    },
    {
      "epoch": 1.326390808834823,
      "grad_norm": 0.4571158289909363,
      "learning_rate": 5.1093502716367006e-06,
      "loss": 0.5081,
      "step": 43178
    },
    {
      "epoch": 1.3264215279697724,
      "grad_norm": 0.41072556376457214,
      "learning_rate": 5.108928739968486e-06,
      "loss": 0.5382,
      "step": 43179
    },
    {
      "epoch": 1.3264522471047215,
      "grad_norm": 0.4005195200443268,
      "learning_rate": 5.10850721972371e-06,
      "loss": 0.5054,
      "step": 43180
    },
    {
      "epoch": 1.3264829662396707,
      "grad_norm": 0.4050622582435608,
      "learning_rate": 5.108085710903361e-06,
      "loss": 0.4926,
      "step": 43181
    },
    {
      "epoch": 1.3265136853746198,
      "grad_norm": 0.41072526574134827,
      "learning_rate": 5.107664213508416e-06,
      "loss": 0.5239,
      "step": 43182
    },
    {
      "epoch": 1.3265444045095691,
      "grad_norm": 0.3666248619556427,
      "learning_rate": 5.107242727539863e-06,
      "loss": 0.4359,
      "step": 43183
    },
    {
      "epoch": 1.3265751236445182,
      "grad_norm": 0.45967522263526917,
      "learning_rate": 5.106821252998686e-06,
      "loss": 0.417,
      "step": 43184
    },
    {
      "epoch": 1.3266058427794674,
      "grad_norm": 0.4086880087852478,
      "learning_rate": 5.106399789885873e-06,
      "loss": 0.4812,
      "step": 43185
    },
    {
      "epoch": 1.3266365619144165,
      "grad_norm": 0.40361377596855164,
      "learning_rate": 5.105978338202402e-06,
      "loss": 0.4419,
      "step": 43186
    },
    {
      "epoch": 1.3266672810493656,
      "grad_norm": 0.43710118532180786,
      "learning_rate": 5.1055568979492644e-06,
      "loss": 0.5208,
      "step": 43187
    },
    {
      "epoch": 1.3266980001843147,
      "grad_norm": 0.47800588607788086,
      "learning_rate": 5.105135469127431e-06,
      "loss": 0.4407,
      "step": 43188
    },
    {
      "epoch": 1.3267287193192638,
      "grad_norm": 0.43712714314460754,
      "learning_rate": 5.104714051737901e-06,
      "loss": 0.4057,
      "step": 43189
    },
    {
      "epoch": 1.3267594384542132,
      "grad_norm": 0.43070441484451294,
      "learning_rate": 5.104292645781656e-06,
      "loss": 0.52,
      "step": 43190
    },
    {
      "epoch": 1.3267901575891623,
      "grad_norm": 0.40064743161201477,
      "learning_rate": 5.103871251259675e-06,
      "loss": 0.4552,
      "step": 43191
    },
    {
      "epoch": 1.3268208767241114,
      "grad_norm": 0.4140412211418152,
      "learning_rate": 5.103449868172947e-06,
      "loss": 0.4854,
      "step": 43192
    },
    {
      "epoch": 1.3268515958590605,
      "grad_norm": 0.4127033054828644,
      "learning_rate": 5.1030284965224475e-06,
      "loss": 0.4886,
      "step": 43193
    },
    {
      "epoch": 1.3268823149940099,
      "grad_norm": 0.44583937525749207,
      "learning_rate": 5.102607136309174e-06,
      "loss": 0.4667,
      "step": 43194
    },
    {
      "epoch": 1.326913034128959,
      "grad_norm": 0.45170024037361145,
      "learning_rate": 5.1021857875340994e-06,
      "loss": 0.468,
      "step": 43195
    },
    {
      "epoch": 1.3269437532639081,
      "grad_norm": 0.4202450215816498,
      "learning_rate": 5.101764450198216e-06,
      "loss": 0.4737,
      "step": 43196
    },
    {
      "epoch": 1.3269744723988572,
      "grad_norm": 0.3935421109199524,
      "learning_rate": 5.1013431243025e-06,
      "loss": 0.5249,
      "step": 43197
    },
    {
      "epoch": 1.3270051915338064,
      "grad_norm": 0.4002693295478821,
      "learning_rate": 5.1009218098479405e-06,
      "loss": 0.4665,
      "step": 43198
    },
    {
      "epoch": 1.3270359106687555,
      "grad_norm": 0.4292404353618622,
      "learning_rate": 5.10050050683552e-06,
      "loss": 0.4903,
      "step": 43199
    },
    {
      "epoch": 1.3270666298037046,
      "grad_norm": 0.3809189200401306,
      "learning_rate": 5.100079215266225e-06,
      "loss": 0.5288,
      "step": 43200
    },
    {
      "epoch": 1.327097348938654,
      "grad_norm": 0.4324393570423126,
      "learning_rate": 5.0996579351410336e-06,
      "loss": 0.547,
      "step": 43201
    },
    {
      "epoch": 1.327128068073603,
      "grad_norm": 0.4330018162727356,
      "learning_rate": 5.099236666460934e-06,
      "loss": 0.4737,
      "step": 43202
    },
    {
      "epoch": 1.3271587872085522,
      "grad_norm": 0.43402865529060364,
      "learning_rate": 5.09881540922691e-06,
      "loss": 0.4414,
      "step": 43203
    },
    {
      "epoch": 1.3271895063435013,
      "grad_norm": 0.4357243776321411,
      "learning_rate": 5.098394163439948e-06,
      "loss": 0.4016,
      "step": 43204
    },
    {
      "epoch": 1.3272202254784506,
      "grad_norm": 0.3982101380825043,
      "learning_rate": 5.097972929101025e-06,
      "loss": 0.4169,
      "step": 43205
    },
    {
      "epoch": 1.3272509446133998,
      "grad_norm": 0.41735121607780457,
      "learning_rate": 5.097551706211128e-06,
      "loss": 0.4246,
      "step": 43206
    },
    {
      "epoch": 1.3272816637483489,
      "grad_norm": 0.40652453899383545,
      "learning_rate": 5.097130494771241e-06,
      "loss": 0.4373,
      "step": 43207
    },
    {
      "epoch": 1.327312382883298,
      "grad_norm": 0.4150170683860779,
      "learning_rate": 5.096709294782349e-06,
      "loss": 0.4925,
      "step": 43208
    },
    {
      "epoch": 1.3273431020182471,
      "grad_norm": 0.38963407278060913,
      "learning_rate": 5.096288106245439e-06,
      "loss": 0.4838,
      "step": 43209
    },
    {
      "epoch": 1.3273738211531962,
      "grad_norm": 0.405323326587677,
      "learning_rate": 5.095866929161487e-06,
      "loss": 0.4565,
      "step": 43210
    },
    {
      "epoch": 1.3274045402881454,
      "grad_norm": 0.3539777100086212,
      "learning_rate": 5.095445763531479e-06,
      "loss": 0.5069,
      "step": 43211
    },
    {
      "epoch": 1.3274352594230947,
      "grad_norm": 0.40178388357162476,
      "learning_rate": 5.095024609356401e-06,
      "loss": 0.4442,
      "step": 43212
    },
    {
      "epoch": 1.3274659785580438,
      "grad_norm": 0.395160436630249,
      "learning_rate": 5.09460346663724e-06,
      "loss": 0.4977,
      "step": 43213
    },
    {
      "epoch": 1.327496697692993,
      "grad_norm": 0.4377792775630951,
      "learning_rate": 5.09418233537497e-06,
      "loss": 0.4694,
      "step": 43214
    },
    {
      "epoch": 1.327527416827942,
      "grad_norm": 0.4976758658885956,
      "learning_rate": 5.093761215570581e-06,
      "loss": 0.5287,
      "step": 43215
    },
    {
      "epoch": 1.3275581359628914,
      "grad_norm": 0.3788228929042816,
      "learning_rate": 5.093340107225053e-06,
      "loss": 0.5017,
      "step": 43216
    },
    {
      "epoch": 1.3275888550978405,
      "grad_norm": 0.504596471786499,
      "learning_rate": 5.092919010339379e-06,
      "loss": 0.4377,
      "step": 43217
    },
    {
      "epoch": 1.3276195742327896,
      "grad_norm": 0.42698681354522705,
      "learning_rate": 5.092497924914529e-06,
      "loss": 0.485,
      "step": 43218
    },
    {
      "epoch": 1.3276502933677388,
      "grad_norm": 0.49090003967285156,
      "learning_rate": 5.092076850951497e-06,
      "loss": 0.4098,
      "step": 43219
    },
    {
      "epoch": 1.3276810125026879,
      "grad_norm": 0.41165006160736084,
      "learning_rate": 5.091655788451255e-06,
      "loss": 0.4976,
      "step": 43220
    },
    {
      "epoch": 1.327711731637637,
      "grad_norm": 0.39503681659698486,
      "learning_rate": 5.091234737414802e-06,
      "loss": 0.4716,
      "step": 43221
    },
    {
      "epoch": 1.3277424507725861,
      "grad_norm": 0.4603155255317688,
      "learning_rate": 5.090813697843109e-06,
      "loss": 0.4589,
      "step": 43222
    },
    {
      "epoch": 1.3277731699075355,
      "grad_norm": 0.4504721164703369,
      "learning_rate": 5.090392669737168e-06,
      "loss": 0.4695,
      "step": 43223
    },
    {
      "epoch": 1.3278038890424846,
      "grad_norm": 0.4607270061969757,
      "learning_rate": 5.089971653097948e-06,
      "loss": 0.4722,
      "step": 43224
    },
    {
      "epoch": 1.3278346081774337,
      "grad_norm": 0.41879209876060486,
      "learning_rate": 5.089550647926451e-06,
      "loss": 0.4829,
      "step": 43225
    },
    {
      "epoch": 1.3278653273123828,
      "grad_norm": 0.6261776685714722,
      "learning_rate": 5.0891296542236475e-06,
      "loss": 0.5107,
      "step": 43226
    },
    {
      "epoch": 1.3278960464473322,
      "grad_norm": 0.4095122516155243,
      "learning_rate": 5.0887086719905244e-06,
      "loss": 0.4556,
      "step": 43227
    },
    {
      "epoch": 1.3279267655822813,
      "grad_norm": 0.40028879046440125,
      "learning_rate": 5.08828770122807e-06,
      "loss": 0.4304,
      "step": 43228
    },
    {
      "epoch": 1.3279574847172304,
      "grad_norm": 0.42053279280662537,
      "learning_rate": 5.087866741937254e-06,
      "loss": 0.44,
      "step": 43229
    },
    {
      "epoch": 1.3279882038521795,
      "grad_norm": 0.41563838720321655,
      "learning_rate": 5.087445794119077e-06,
      "loss": 0.4573,
      "step": 43230
    },
    {
      "epoch": 1.3280189229871286,
      "grad_norm": 0.46031123399734497,
      "learning_rate": 5.087024857774507e-06,
      "loss": 0.5586,
      "step": 43231
    },
    {
      "epoch": 1.3280496421220778,
      "grad_norm": 0.43667230010032654,
      "learning_rate": 5.0866039329045406e-06,
      "loss": 0.4228,
      "step": 43232
    },
    {
      "epoch": 1.3280803612570269,
      "grad_norm": 0.45420965552330017,
      "learning_rate": 5.086183019510149e-06,
      "loss": 0.4291,
      "step": 43233
    },
    {
      "epoch": 1.3281110803919762,
      "grad_norm": 0.4310254752635956,
      "learning_rate": 5.0857621175923185e-06,
      "loss": 0.4898,
      "step": 43234
    },
    {
      "epoch": 1.3281417995269253,
      "grad_norm": 0.4140411615371704,
      "learning_rate": 5.0853412271520365e-06,
      "loss": 0.4263,
      "step": 43235
    },
    {
      "epoch": 1.3281725186618745,
      "grad_norm": 0.42847999930381775,
      "learning_rate": 5.084920348190285e-06,
      "loss": 0.4867,
      "step": 43236
    },
    {
      "epoch": 1.3282032377968236,
      "grad_norm": 0.40370333194732666,
      "learning_rate": 5.0844994807080425e-06,
      "loss": 0.4527,
      "step": 43237
    },
    {
      "epoch": 1.328233956931773,
      "grad_norm": 0.4751794934272766,
      "learning_rate": 5.084078624706295e-06,
      "loss": 0.4437,
      "step": 43238
    },
    {
      "epoch": 1.328264676066722,
      "grad_norm": 0.4012221097946167,
      "learning_rate": 5.083657780186024e-06,
      "loss": 0.5093,
      "step": 43239
    },
    {
      "epoch": 1.3282953952016712,
      "grad_norm": 0.3995908200740814,
      "learning_rate": 5.083236947148218e-06,
      "loss": 0.4373,
      "step": 43240
    },
    {
      "epoch": 1.3283261143366203,
      "grad_norm": 0.4070937931537628,
      "learning_rate": 5.082816125593852e-06,
      "loss": 0.4403,
      "step": 43241
    },
    {
      "epoch": 1.3283568334715694,
      "grad_norm": 0.431437611579895,
      "learning_rate": 5.082395315523912e-06,
      "loss": 0.5306,
      "step": 43242
    },
    {
      "epoch": 1.3283875526065185,
      "grad_norm": 0.42898470163345337,
      "learning_rate": 5.081974516939381e-06,
      "loss": 0.5219,
      "step": 43243
    },
    {
      "epoch": 1.3284182717414676,
      "grad_norm": 0.40472283959388733,
      "learning_rate": 5.081553729841242e-06,
      "loss": 0.4303,
      "step": 43244
    },
    {
      "epoch": 1.328448990876417,
      "grad_norm": 0.3954063653945923,
      "learning_rate": 5.081132954230483e-06,
      "loss": 0.5777,
      "step": 43245
    },
    {
      "epoch": 1.328479710011366,
      "grad_norm": 0.4385482370853424,
      "learning_rate": 5.080712190108077e-06,
      "loss": 0.4408,
      "step": 43246
    },
    {
      "epoch": 1.3285104291463152,
      "grad_norm": 0.40263471007347107,
      "learning_rate": 5.08029143747501e-06,
      "loss": 0.4495,
      "step": 43247
    },
    {
      "epoch": 1.3285411482812644,
      "grad_norm": 0.4224279224872589,
      "learning_rate": 5.079870696332267e-06,
      "loss": 0.4832,
      "step": 43248
    },
    {
      "epoch": 1.3285718674162137,
      "grad_norm": 0.42422327399253845,
      "learning_rate": 5.079449966680834e-06,
      "loss": 0.4651,
      "step": 43249
    },
    {
      "epoch": 1.3286025865511628,
      "grad_norm": 0.42924803495407104,
      "learning_rate": 5.079029248521683e-06,
      "loss": 0.4745,
      "step": 43250
    },
    {
      "epoch": 1.328633305686112,
      "grad_norm": 0.40785250067710876,
      "learning_rate": 5.078608541855805e-06,
      "loss": 0.4772,
      "step": 43251
    },
    {
      "epoch": 1.328664024821061,
      "grad_norm": 0.40463778376579285,
      "learning_rate": 5.078187846684179e-06,
      "loss": 0.5789,
      "step": 43252
    },
    {
      "epoch": 1.3286947439560102,
      "grad_norm": 0.4392584562301636,
      "learning_rate": 5.0777671630077956e-06,
      "loss": 0.4564,
      "step": 43253
    },
    {
      "epoch": 1.3287254630909593,
      "grad_norm": 0.3871857821941376,
      "learning_rate": 5.0773464908276236e-06,
      "loss": 0.5129,
      "step": 43254
    },
    {
      "epoch": 1.3287561822259084,
      "grad_norm": 0.420437753200531,
      "learning_rate": 5.076925830144659e-06,
      "loss": 0.4422,
      "step": 43255
    },
    {
      "epoch": 1.3287869013608578,
      "grad_norm": 0.4076496660709381,
      "learning_rate": 5.07650518095987e-06,
      "loss": 0.4671,
      "step": 43256
    },
    {
      "epoch": 1.3288176204958069,
      "grad_norm": 0.40963199734687805,
      "learning_rate": 5.076084543274253e-06,
      "loss": 0.4387,
      "step": 43257
    },
    {
      "epoch": 1.328848339630756,
      "grad_norm": 0.49322888255119324,
      "learning_rate": 5.0756639170887824e-06,
      "loss": 0.4025,
      "step": 43258
    },
    {
      "epoch": 1.3288790587657051,
      "grad_norm": 0.4700535833835602,
      "learning_rate": 5.0752433024044446e-06,
      "loss": 0.579,
      "step": 43259
    },
    {
      "epoch": 1.3289097779006545,
      "grad_norm": 0.4098963439464569,
      "learning_rate": 5.074822699222217e-06,
      "loss": 0.4992,
      "step": 43260
    },
    {
      "epoch": 1.3289404970356036,
      "grad_norm": 0.41954365372657776,
      "learning_rate": 5.074402107543086e-06,
      "loss": 0.4592,
      "step": 43261
    },
    {
      "epoch": 1.3289712161705527,
      "grad_norm": 0.40306901931762695,
      "learning_rate": 5.073981527368031e-06,
      "loss": 0.4612,
      "step": 43262
    },
    {
      "epoch": 1.3290019353055018,
      "grad_norm": 0.41352102160453796,
      "learning_rate": 5.073560958698038e-06,
      "loss": 0.3927,
      "step": 43263
    },
    {
      "epoch": 1.329032654440451,
      "grad_norm": 0.4070737063884735,
      "learning_rate": 5.073140401534092e-06,
      "loss": 0.5141,
      "step": 43264
    },
    {
      "epoch": 1.3290633735754,
      "grad_norm": 0.44465795159339905,
      "learning_rate": 5.07271985587716e-06,
      "loss": 0.484,
      "step": 43265
    },
    {
      "epoch": 1.3290940927103492,
      "grad_norm": 0.3800630569458008,
      "learning_rate": 5.072299321728244e-06,
      "loss": 0.4579,
      "step": 43266
    },
    {
      "epoch": 1.3291248118452985,
      "grad_norm": 0.4378926753997803,
      "learning_rate": 5.071878799088314e-06,
      "loss": 0.4461,
      "step": 43267
    },
    {
      "epoch": 1.3291555309802476,
      "grad_norm": 0.40120139718055725,
      "learning_rate": 5.071458287958357e-06,
      "loss": 0.4931,
      "step": 43268
    },
    {
      "epoch": 1.3291862501151968,
      "grad_norm": 0.42170995473861694,
      "learning_rate": 5.0710377883393516e-06,
      "loss": 0.4611,
      "step": 43269
    },
    {
      "epoch": 1.3292169692501459,
      "grad_norm": 0.46393463015556335,
      "learning_rate": 5.070617300232281e-06,
      "loss": 0.5232,
      "step": 43270
    },
    {
      "epoch": 1.329247688385095,
      "grad_norm": 0.40866753458976746,
      "learning_rate": 5.070196823638127e-06,
      "loss": 0.4884,
      "step": 43271
    },
    {
      "epoch": 1.3292784075200443,
      "grad_norm": 0.4230741560459137,
      "learning_rate": 5.069776358557879e-06,
      "loss": 0.359,
      "step": 43272
    },
    {
      "epoch": 1.3293091266549935,
      "grad_norm": 0.38735073804855347,
      "learning_rate": 5.069355904992507e-06,
      "loss": 0.4708,
      "step": 43273
    },
    {
      "epoch": 1.3293398457899426,
      "grad_norm": 0.5516800284385681,
      "learning_rate": 5.068935462942998e-06,
      "loss": 0.4747,
      "step": 43274
    },
    {
      "epoch": 1.3293705649248917,
      "grad_norm": 0.4300043284893036,
      "learning_rate": 5.068515032410336e-06,
      "loss": 0.516,
      "step": 43275
    },
    {
      "epoch": 1.3294012840598408,
      "grad_norm": 0.38981059193611145,
      "learning_rate": 5.068094613395505e-06,
      "loss": 0.4687,
      "step": 43276
    },
    {
      "epoch": 1.32943200319479,
      "grad_norm": 0.41151806712150574,
      "learning_rate": 5.06767420589948e-06,
      "loss": 0.4898,
      "step": 43277
    },
    {
      "epoch": 1.3294627223297393,
      "grad_norm": 0.4117013216018677,
      "learning_rate": 5.067253809923245e-06,
      "loss": 0.4881,
      "step": 43278
    },
    {
      "epoch": 1.3294934414646884,
      "grad_norm": 0.4094223976135254,
      "learning_rate": 5.066833425467784e-06,
      "loss": 0.4949,
      "step": 43279
    },
    {
      "epoch": 1.3295241605996375,
      "grad_norm": 0.44463419914245605,
      "learning_rate": 5.066413052534083e-06,
      "loss": 0.4247,
      "step": 43280
    },
    {
      "epoch": 1.3295548797345866,
      "grad_norm": 0.7800081968307495,
      "learning_rate": 5.065992691123114e-06,
      "loss": 0.4883,
      "step": 43281
    },
    {
      "epoch": 1.3295855988695358,
      "grad_norm": 0.3621596693992615,
      "learning_rate": 5.065572341235863e-06,
      "loss": 0.4636,
      "step": 43282
    },
    {
      "epoch": 1.329616318004485,
      "grad_norm": 0.4043426811695099,
      "learning_rate": 5.0651520028733125e-06,
      "loss": 0.4485,
      "step": 43283
    },
    {
      "epoch": 1.3296470371394342,
      "grad_norm": 0.4470914900302887,
      "learning_rate": 5.064731676036445e-06,
      "loss": 0.5088,
      "step": 43284
    },
    {
      "epoch": 1.3296777562743833,
      "grad_norm": 0.38955074548721313,
      "learning_rate": 5.064311360726245e-06,
      "loss": 0.4177,
      "step": 43285
    },
    {
      "epoch": 1.3297084754093325,
      "grad_norm": 0.46628862619400024,
      "learning_rate": 5.063891056943686e-06,
      "loss": 0.4165,
      "step": 43286
    },
    {
      "epoch": 1.3297391945442816,
      "grad_norm": 0.3763234615325928,
      "learning_rate": 5.063470764689755e-06,
      "loss": 0.4195,
      "step": 43287
    },
    {
      "epoch": 1.3297699136792307,
      "grad_norm": 0.3858799636363983,
      "learning_rate": 5.063050483965433e-06,
      "loss": 0.4594,
      "step": 43288
    },
    {
      "epoch": 1.3298006328141798,
      "grad_norm": 0.3786977231502533,
      "learning_rate": 5.062630214771705e-06,
      "loss": 0.3683,
      "step": 43289
    },
    {
      "epoch": 1.3298313519491292,
      "grad_norm": 0.426320344209671,
      "learning_rate": 5.062209957109545e-06,
      "loss": 0.495,
      "step": 43290
    },
    {
      "epoch": 1.3298620710840783,
      "grad_norm": 0.4037904143333435,
      "learning_rate": 5.061789710979942e-06,
      "loss": 0.386,
      "step": 43291
    },
    {
      "epoch": 1.3298927902190274,
      "grad_norm": 0.4150458574295044,
      "learning_rate": 5.061369476383866e-06,
      "loss": 0.4853,
      "step": 43292
    },
    {
      "epoch": 1.3299235093539765,
      "grad_norm": 0.41497302055358887,
      "learning_rate": 5.060949253322315e-06,
      "loss": 0.511,
      "step": 43293
    },
    {
      "epoch": 1.3299542284889259,
      "grad_norm": 0.4606127142906189,
      "learning_rate": 5.060529041796258e-06,
      "loss": 0.5008,
      "step": 43294
    },
    {
      "epoch": 1.329984947623875,
      "grad_norm": 0.449891060590744,
      "learning_rate": 5.060108841806683e-06,
      "loss": 0.544,
      "step": 43295
    },
    {
      "epoch": 1.330015666758824,
      "grad_norm": 0.4232318103313446,
      "learning_rate": 5.0596886533545666e-06,
      "loss": 0.5012,
      "step": 43296
    },
    {
      "epoch": 1.3300463858937732,
      "grad_norm": 0.4691072404384613,
      "learning_rate": 5.059268476440893e-06,
      "loss": 0.4743,
      "step": 43297
    },
    {
      "epoch": 1.3300771050287223,
      "grad_norm": 0.6546050310134888,
      "learning_rate": 5.0588483110666405e-06,
      "loss": 0.4799,
      "step": 43298
    },
    {
      "epoch": 1.3301078241636715,
      "grad_norm": 0.3924136161804199,
      "learning_rate": 5.058428157232794e-06,
      "loss": 0.5085,
      "step": 43299
    },
    {
      "epoch": 1.3301385432986206,
      "grad_norm": 0.39977991580963135,
      "learning_rate": 5.058008014940339e-06,
      "loss": 0.4585,
      "step": 43300
    },
    {
      "epoch": 1.33016926243357,
      "grad_norm": 0.42326265573501587,
      "learning_rate": 5.057587884190245e-06,
      "loss": 0.4561,
      "step": 43301
    },
    {
      "epoch": 1.330199981568519,
      "grad_norm": 0.41074666380882263,
      "learning_rate": 5.057167764983502e-06,
      "loss": 0.4397,
      "step": 43302
    },
    {
      "epoch": 1.3302307007034682,
      "grad_norm": 0.4932875335216522,
      "learning_rate": 5.056747657321086e-06,
      "loss": 0.4526,
      "step": 43303
    },
    {
      "epoch": 1.3302614198384173,
      "grad_norm": 0.4238165020942688,
      "learning_rate": 5.056327561203987e-06,
      "loss": 0.5011,
      "step": 43304
    },
    {
      "epoch": 1.3302921389733666,
      "grad_norm": 0.4115010201931,
      "learning_rate": 5.055907476633177e-06,
      "loss": 0.4469,
      "step": 43305
    },
    {
      "epoch": 1.3303228581083157,
      "grad_norm": 0.4164762496948242,
      "learning_rate": 5.055487403609639e-06,
      "loss": 0.4434,
      "step": 43306
    },
    {
      "epoch": 1.3303535772432649,
      "grad_norm": 0.42037123441696167,
      "learning_rate": 5.055067342134357e-06,
      "loss": 0.471,
      "step": 43307
    },
    {
      "epoch": 1.330384296378214,
      "grad_norm": 0.4286675453186035,
      "learning_rate": 5.054647292208312e-06,
      "loss": 0.4452,
      "step": 43308
    },
    {
      "epoch": 1.330415015513163,
      "grad_norm": 0.4128420352935791,
      "learning_rate": 5.054227253832482e-06,
      "loss": 0.4439,
      "step": 43309
    },
    {
      "epoch": 1.3304457346481122,
      "grad_norm": 0.5443260073661804,
      "learning_rate": 5.053807227007848e-06,
      "loss": 0.5252,
      "step": 43310
    },
    {
      "epoch": 1.3304764537830613,
      "grad_norm": 0.43999260663986206,
      "learning_rate": 5.053387211735394e-06,
      "loss": 0.4934,
      "step": 43311
    },
    {
      "epoch": 1.3305071729180107,
      "grad_norm": 0.4135890007019043,
      "learning_rate": 5.0529672080161015e-06,
      "loss": 0.512,
      "step": 43312
    },
    {
      "epoch": 1.3305378920529598,
      "grad_norm": 0.4119719862937927,
      "learning_rate": 5.052547215850948e-06,
      "loss": 0.4371,
      "step": 43313
    },
    {
      "epoch": 1.330568611187909,
      "grad_norm": 0.4283980429172516,
      "learning_rate": 5.052127235240916e-06,
      "loss": 0.5506,
      "step": 43314
    },
    {
      "epoch": 1.330599330322858,
      "grad_norm": 0.4049164950847626,
      "learning_rate": 5.051707266186985e-06,
      "loss": 0.4416,
      "step": 43315
    },
    {
      "epoch": 1.3306300494578074,
      "grad_norm": 0.3877280056476593,
      "learning_rate": 5.051287308690142e-06,
      "loss": 0.5263,
      "step": 43316
    },
    {
      "epoch": 1.3306607685927565,
      "grad_norm": 0.4663391709327698,
      "learning_rate": 5.050867362751359e-06,
      "loss": 0.4612,
      "step": 43317
    },
    {
      "epoch": 1.3306914877277056,
      "grad_norm": 0.4408869743347168,
      "learning_rate": 5.050447428371621e-06,
      "loss": 0.4681,
      "step": 43318
    },
    {
      "epoch": 1.3307222068626547,
      "grad_norm": 0.40115630626678467,
      "learning_rate": 5.050027505551909e-06,
      "loss": 0.4611,
      "step": 43319
    },
    {
      "epoch": 1.3307529259976039,
      "grad_norm": 0.4363097846508026,
      "learning_rate": 5.049607594293202e-06,
      "loss": 0.4764,
      "step": 43320
    },
    {
      "epoch": 1.330783645132553,
      "grad_norm": 0.4406924545764923,
      "learning_rate": 5.049187694596487e-06,
      "loss": 0.5058,
      "step": 43321
    },
    {
      "epoch": 1.330814364267502,
      "grad_norm": 0.4823414385318756,
      "learning_rate": 5.048767806462735e-06,
      "loss": 0.4779,
      "step": 43322
    },
    {
      "epoch": 1.3308450834024514,
      "grad_norm": 0.42609211802482605,
      "learning_rate": 5.048347929892938e-06,
      "loss": 0.4738,
      "step": 43323
    },
    {
      "epoch": 1.3308758025374006,
      "grad_norm": 0.40949195623397827,
      "learning_rate": 5.047928064888061e-06,
      "loss": 0.4428,
      "step": 43324
    },
    {
      "epoch": 1.3309065216723497,
      "grad_norm": 0.39845603704452515,
      "learning_rate": 5.047508211449102e-06,
      "loss": 0.4923,
      "step": 43325
    },
    {
      "epoch": 1.3309372408072988,
      "grad_norm": 0.4056805670261383,
      "learning_rate": 5.047088369577029e-06,
      "loss": 0.558,
      "step": 43326
    },
    {
      "epoch": 1.3309679599422481,
      "grad_norm": 0.4232345223426819,
      "learning_rate": 5.046668539272831e-06,
      "loss": 0.4779,
      "step": 43327
    },
    {
      "epoch": 1.3309986790771973,
      "grad_norm": 0.4037037789821625,
      "learning_rate": 5.046248720537477e-06,
      "loss": 0.4548,
      "step": 43328
    },
    {
      "epoch": 1.3310293982121464,
      "grad_norm": 0.42344212532043457,
      "learning_rate": 5.045828913371962e-06,
      "loss": 0.4015,
      "step": 43329
    },
    {
      "epoch": 1.3310601173470955,
      "grad_norm": 0.4193592369556427,
      "learning_rate": 5.045409117777257e-06,
      "loss": 0.5547,
      "step": 43330
    },
    {
      "epoch": 1.3310908364820446,
      "grad_norm": 0.4023992121219635,
      "learning_rate": 5.044989333754349e-06,
      "loss": 0.4929,
      "step": 43331
    },
    {
      "epoch": 1.3311215556169937,
      "grad_norm": 0.3840908110141754,
      "learning_rate": 5.044569561304209e-06,
      "loss": 0.5079,
      "step": 43332
    },
    {
      "epoch": 1.3311522747519429,
      "grad_norm": 0.3782825171947479,
      "learning_rate": 5.044149800427824e-06,
      "loss": 0.405,
      "step": 43333
    },
    {
      "epoch": 1.3311829938868922,
      "grad_norm": 0.3924754858016968,
      "learning_rate": 5.0437300511261735e-06,
      "loss": 0.4499,
      "step": 43334
    },
    {
      "epoch": 1.3312137130218413,
      "grad_norm": 0.451294481754303,
      "learning_rate": 5.043310313400237e-06,
      "loss": 0.5163,
      "step": 43335
    },
    {
      "epoch": 1.3312444321567904,
      "grad_norm": 0.38176268339157104,
      "learning_rate": 5.042890587250999e-06,
      "loss": 0.478,
      "step": 43336
    },
    {
      "epoch": 1.3312751512917396,
      "grad_norm": 0.5423347353935242,
      "learning_rate": 5.042470872679433e-06,
      "loss": 0.5041,
      "step": 43337
    },
    {
      "epoch": 1.331305870426689,
      "grad_norm": 0.390679270029068,
      "learning_rate": 5.0420511696865225e-06,
      "loss": 0.415,
      "step": 43338
    },
    {
      "epoch": 1.331336589561638,
      "grad_norm": 0.37827518582344055,
      "learning_rate": 5.041631478273248e-06,
      "loss": 0.4773,
      "step": 43339
    },
    {
      "epoch": 1.3313673086965871,
      "grad_norm": 0.43979108333587646,
      "learning_rate": 5.041211798440593e-06,
      "loss": 0.4919,
      "step": 43340
    },
    {
      "epoch": 1.3313980278315363,
      "grad_norm": 0.402895987033844,
      "learning_rate": 5.040792130189529e-06,
      "loss": 0.4098,
      "step": 43341
    },
    {
      "epoch": 1.3314287469664854,
      "grad_norm": 0.44084328413009644,
      "learning_rate": 5.0403724735210435e-06,
      "loss": 0.4803,
      "step": 43342
    },
    {
      "epoch": 1.3314594661014345,
      "grad_norm": 0.3862764537334442,
      "learning_rate": 5.039952828436113e-06,
      "loss": 0.444,
      "step": 43343
    },
    {
      "epoch": 1.3314901852363836,
      "grad_norm": 0.4428173005580902,
      "learning_rate": 5.039533194935724e-06,
      "loss": 0.4545,
      "step": 43344
    },
    {
      "epoch": 1.331520904371333,
      "grad_norm": 0.3702387809753418,
      "learning_rate": 5.039113573020848e-06,
      "loss": 0.4993,
      "step": 43345
    },
    {
      "epoch": 1.331551623506282,
      "grad_norm": 0.42633259296417236,
      "learning_rate": 5.038693962692467e-06,
      "loss": 0.4229,
      "step": 43346
    },
    {
      "epoch": 1.3315823426412312,
      "grad_norm": 0.4133264124393463,
      "learning_rate": 5.038274363951564e-06,
      "loss": 0.4593,
      "step": 43347
    },
    {
      "epoch": 1.3316130617761803,
      "grad_norm": 0.4593583345413208,
      "learning_rate": 5.0378547767991205e-06,
      "loss": 0.5151,
      "step": 43348
    },
    {
      "epoch": 1.3316437809111297,
      "grad_norm": 0.44046494364738464,
      "learning_rate": 5.037435201236112e-06,
      "loss": 0.5433,
      "step": 43349
    },
    {
      "epoch": 1.3316745000460788,
      "grad_norm": 0.4344848394393921,
      "learning_rate": 5.037015637263518e-06,
      "loss": 0.491,
      "step": 43350
    },
    {
      "epoch": 1.331705219181028,
      "grad_norm": 0.4569515883922577,
      "learning_rate": 5.036596084882321e-06,
      "loss": 0.4668,
      "step": 43351
    },
    {
      "epoch": 1.331735938315977,
      "grad_norm": 0.36994484066963196,
      "learning_rate": 5.0361765440935054e-06,
      "loss": 0.4618,
      "step": 43352
    },
    {
      "epoch": 1.3317666574509262,
      "grad_norm": 0.3903889060020447,
      "learning_rate": 5.0357570148980415e-06,
      "loss": 0.4138,
      "step": 43353
    },
    {
      "epoch": 1.3317973765858753,
      "grad_norm": 0.4184923470020294,
      "learning_rate": 5.0353374972969145e-06,
      "loss": 0.4854,
      "step": 43354
    },
    {
      "epoch": 1.3318280957208244,
      "grad_norm": 0.46228447556495667,
      "learning_rate": 5.034917991291103e-06,
      "loss": 0.4777,
      "step": 43355
    },
    {
      "epoch": 1.3318588148557737,
      "grad_norm": 0.40560710430145264,
      "learning_rate": 5.034498496881587e-06,
      "loss": 0.4005,
      "step": 43356
    },
    {
      "epoch": 1.3318895339907229,
      "grad_norm": 0.3833986520767212,
      "learning_rate": 5.034079014069351e-06,
      "loss": 0.5024,
      "step": 43357
    },
    {
      "epoch": 1.331920253125672,
      "grad_norm": 0.4310770332813263,
      "learning_rate": 5.033659542855366e-06,
      "loss": 0.4401,
      "step": 43358
    },
    {
      "epoch": 1.331950972260621,
      "grad_norm": 0.43084368109703064,
      "learning_rate": 5.03324008324062e-06,
      "loss": 0.5487,
      "step": 43359
    },
    {
      "epoch": 1.3319816913955704,
      "grad_norm": 0.448413610458374,
      "learning_rate": 5.0328206352260815e-06,
      "loss": 0.4586,
      "step": 43360
    },
    {
      "epoch": 1.3320124105305196,
      "grad_norm": 0.39493876695632935,
      "learning_rate": 5.032401198812744e-06,
      "loss": 0.5354,
      "step": 43361
    },
    {
      "epoch": 1.3320431296654687,
      "grad_norm": 0.3828924298286438,
      "learning_rate": 5.031981774001577e-06,
      "loss": 0.368,
      "step": 43362
    },
    {
      "epoch": 1.3320738488004178,
      "grad_norm": 0.4122077524662018,
      "learning_rate": 5.0315623607935675e-06,
      "loss": 0.487,
      "step": 43363
    },
    {
      "epoch": 1.332104567935367,
      "grad_norm": 0.42008429765701294,
      "learning_rate": 5.031142959189687e-06,
      "loss": 0.4987,
      "step": 43364
    },
    {
      "epoch": 1.332135287070316,
      "grad_norm": 0.38410457968711853,
      "learning_rate": 5.030723569190918e-06,
      "loss": 0.4685,
      "step": 43365
    },
    {
      "epoch": 1.3321660062052652,
      "grad_norm": 0.3738345801830292,
      "learning_rate": 5.030304190798243e-06,
      "loss": 0.4203,
      "step": 43366
    },
    {
      "epoch": 1.3321967253402145,
      "grad_norm": 0.4252004325389862,
      "learning_rate": 5.029884824012643e-06,
      "loss": 0.5025,
      "step": 43367
    },
    {
      "epoch": 1.3322274444751636,
      "grad_norm": 0.4301752746105194,
      "learning_rate": 5.029465468835091e-06,
      "loss": 0.5316,
      "step": 43368
    },
    {
      "epoch": 1.3322581636101127,
      "grad_norm": 0.3922788202762604,
      "learning_rate": 5.029046125266568e-06,
      "loss": 0.4949,
      "step": 43369
    },
    {
      "epoch": 1.3322888827450619,
      "grad_norm": 0.3766677975654602,
      "learning_rate": 5.028626793308055e-06,
      "loss": 0.46,
      "step": 43370
    },
    {
      "epoch": 1.3323196018800112,
      "grad_norm": 0.4048337936401367,
      "learning_rate": 5.028207472960536e-06,
      "loss": 0.4961,
      "step": 43371
    },
    {
      "epoch": 1.3323503210149603,
      "grad_norm": 0.4030338525772095,
      "learning_rate": 5.027788164224982e-06,
      "loss": 0.4913,
      "step": 43372
    },
    {
      "epoch": 1.3323810401499094,
      "grad_norm": 0.4106655716896057,
      "learning_rate": 5.027368867102376e-06,
      "loss": 0.4586,
      "step": 43373
    },
    {
      "epoch": 1.3324117592848586,
      "grad_norm": 0.4271312952041626,
      "learning_rate": 5.026949581593697e-06,
      "loss": 0.4744,
      "step": 43374
    },
    {
      "epoch": 1.3324424784198077,
      "grad_norm": 0.42583519220352173,
      "learning_rate": 5.026530307699924e-06,
      "loss": 0.5636,
      "step": 43375
    },
    {
      "epoch": 1.3324731975547568,
      "grad_norm": 0.42342856526374817,
      "learning_rate": 5.026111045422042e-06,
      "loss": 0.3938,
      "step": 43376
    },
    {
      "epoch": 1.332503916689706,
      "grad_norm": 0.40549129247665405,
      "learning_rate": 5.02569179476102e-06,
      "loss": 0.3878,
      "step": 43377
    },
    {
      "epoch": 1.3325346358246553,
      "grad_norm": 0.41920000314712524,
      "learning_rate": 5.025272555717841e-06,
      "loss": 0.5221,
      "step": 43378
    },
    {
      "epoch": 1.3325653549596044,
      "grad_norm": 0.42391350865364075,
      "learning_rate": 5.0248533282934885e-06,
      "loss": 0.52,
      "step": 43379
    },
    {
      "epoch": 1.3325960740945535,
      "grad_norm": 0.4185065031051636,
      "learning_rate": 5.02443411248894e-06,
      "loss": 0.4519,
      "step": 43380
    },
    {
      "epoch": 1.3326267932295026,
      "grad_norm": 0.3689669370651245,
      "learning_rate": 5.024014908305171e-06,
      "loss": 0.4014,
      "step": 43381
    },
    {
      "epoch": 1.3326575123644517,
      "grad_norm": 0.392117440700531,
      "learning_rate": 5.023595715743162e-06,
      "loss": 0.4962,
      "step": 43382
    },
    {
      "epoch": 1.332688231499401,
      "grad_norm": 0.4085339903831482,
      "learning_rate": 5.02317653480389e-06,
      "loss": 0.5679,
      "step": 43383
    },
    {
      "epoch": 1.3327189506343502,
      "grad_norm": 0.37051430344581604,
      "learning_rate": 5.022757365488344e-06,
      "loss": 0.5464,
      "step": 43384
    },
    {
      "epoch": 1.3327496697692993,
      "grad_norm": 0.39643898606300354,
      "learning_rate": 5.022338207797491e-06,
      "loss": 0.4968,
      "step": 43385
    },
    {
      "epoch": 1.3327803889042484,
      "grad_norm": 0.37795114517211914,
      "learning_rate": 5.021919061732319e-06,
      "loss": 0.4635,
      "step": 43386
    },
    {
      "epoch": 1.3328111080391976,
      "grad_norm": 0.4095066487789154,
      "learning_rate": 5.021499927293795e-06,
      "loss": 0.5106,
      "step": 43387
    },
    {
      "epoch": 1.3328418271741467,
      "grad_norm": 0.39268919825553894,
      "learning_rate": 5.021080804482913e-06,
      "loss": 0.4181,
      "step": 43388
    },
    {
      "epoch": 1.332872546309096,
      "grad_norm": 0.45097821950912476,
      "learning_rate": 5.02066169330064e-06,
      "loss": 0.4719,
      "step": 43389
    },
    {
      "epoch": 1.3329032654440451,
      "grad_norm": 0.3896721303462982,
      "learning_rate": 5.02024259374796e-06,
      "loss": 0.4919,
      "step": 43390
    },
    {
      "epoch": 1.3329339845789943,
      "grad_norm": 0.42796215415000916,
      "learning_rate": 5.019823505825852e-06,
      "loss": 0.5357,
      "step": 43391
    },
    {
      "epoch": 1.3329647037139434,
      "grad_norm": 0.3869364261627197,
      "learning_rate": 5.019404429535293e-06,
      "loss": 0.4816,
      "step": 43392
    },
    {
      "epoch": 1.3329954228488925,
      "grad_norm": 0.4121536910533905,
      "learning_rate": 5.0189853648772665e-06,
      "loss": 0.5234,
      "step": 43393
    },
    {
      "epoch": 1.3330261419838418,
      "grad_norm": 0.36576271057128906,
      "learning_rate": 5.018566311852744e-06,
      "loss": 0.4718,
      "step": 43394
    },
    {
      "epoch": 1.333056861118791,
      "grad_norm": 0.42263513803482056,
      "learning_rate": 5.018147270462712e-06,
      "loss": 0.452,
      "step": 43395
    },
    {
      "epoch": 1.33308758025374,
      "grad_norm": 0.3937560021877289,
      "learning_rate": 5.0177282407081375e-06,
      "loss": 0.4279,
      "step": 43396
    },
    {
      "epoch": 1.3331182993886892,
      "grad_norm": 0.4096840023994446,
      "learning_rate": 5.0173092225900135e-06,
      "loss": 0.4226,
      "step": 43397
    },
    {
      "epoch": 1.3331490185236383,
      "grad_norm": 0.396833211183548,
      "learning_rate": 5.016890216109308e-06,
      "loss": 0.4521,
      "step": 43398
    },
    {
      "epoch": 1.3331797376585874,
      "grad_norm": 0.42237821221351624,
      "learning_rate": 5.0164712212670075e-06,
      "loss": 0.5004,
      "step": 43399
    },
    {
      "epoch": 1.3332104567935366,
      "grad_norm": 0.40138307213783264,
      "learning_rate": 5.016052238064082e-06,
      "loss": 0.4549,
      "step": 43400
    },
    {
      "epoch": 1.333241175928486,
      "grad_norm": 0.40655356645584106,
      "learning_rate": 5.015633266501516e-06,
      "loss": 0.4934,
      "step": 43401
    },
    {
      "epoch": 1.333271895063435,
      "grad_norm": 0.408332884311676,
      "learning_rate": 5.015214306580285e-06,
      "loss": 0.47,
      "step": 43402
    },
    {
      "epoch": 1.3333026141983841,
      "grad_norm": 0.393044650554657,
      "learning_rate": 5.0147953583013745e-06,
      "loss": 0.4462,
      "step": 43403
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.46754398941993713,
      "learning_rate": 5.014376421665753e-06,
      "loss": 0.498,
      "step": 43404
    },
    {
      "epoch": 1.3333640524682826,
      "grad_norm": 0.42055749893188477,
      "learning_rate": 5.013957496674404e-06,
      "loss": 0.4489,
      "step": 43405
    },
    {
      "epoch": 1.3333947716032317,
      "grad_norm": 0.3870634138584137,
      "learning_rate": 5.013538583328306e-06,
      "loss": 0.4755,
      "step": 43406
    },
    {
      "epoch": 1.3334254907381808,
      "grad_norm": 0.4994174540042877,
      "learning_rate": 5.013119681628439e-06,
      "loss": 0.4452,
      "step": 43407
    },
    {
      "epoch": 1.33345620987313,
      "grad_norm": 0.43544942140579224,
      "learning_rate": 5.012700791575776e-06,
      "loss": 0.4703,
      "step": 43408
    },
    {
      "epoch": 1.333486929008079,
      "grad_norm": 0.3891925811767578,
      "learning_rate": 5.0122819131713e-06,
      "loss": 0.4668,
      "step": 43409
    },
    {
      "epoch": 1.3335176481430282,
      "grad_norm": 0.4346584379673004,
      "learning_rate": 5.011863046415986e-06,
      "loss": 0.4787,
      "step": 43410
    },
    {
      "epoch": 1.3335483672779773,
      "grad_norm": 0.3800106644630432,
      "learning_rate": 5.011444191310814e-06,
      "loss": 0.4515,
      "step": 43411
    },
    {
      "epoch": 1.3335790864129267,
      "grad_norm": 0.4088486433029175,
      "learning_rate": 5.0110253478567684e-06,
      "loss": 0.4971,
      "step": 43412
    },
    {
      "epoch": 1.3336098055478758,
      "grad_norm": 0.41911885142326355,
      "learning_rate": 5.010606516054817e-06,
      "loss": 0.4938,
      "step": 43413
    },
    {
      "epoch": 1.333640524682825,
      "grad_norm": 0.3831007778644562,
      "learning_rate": 5.010187695905941e-06,
      "loss": 0.364,
      "step": 43414
    },
    {
      "epoch": 1.333671243817774,
      "grad_norm": 0.6005820035934448,
      "learning_rate": 5.009768887411122e-06,
      "loss": 0.445,
      "step": 43415
    },
    {
      "epoch": 1.3337019629527234,
      "grad_norm": 0.41429242491722107,
      "learning_rate": 5.009350090571339e-06,
      "loss": 0.4819,
      "step": 43416
    },
    {
      "epoch": 1.3337326820876725,
      "grad_norm": 0.3957565724849701,
      "learning_rate": 5.008931305387564e-06,
      "loss": 0.4947,
      "step": 43417
    },
    {
      "epoch": 1.3337634012226216,
      "grad_norm": 0.4356911778450012,
      "learning_rate": 5.008512531860779e-06,
      "loss": 0.4962,
      "step": 43418
    },
    {
      "epoch": 1.3337941203575707,
      "grad_norm": 0.40614843368530273,
      "learning_rate": 5.008093769991962e-06,
      "loss": 0.4766,
      "step": 43419
    },
    {
      "epoch": 1.3338248394925198,
      "grad_norm": 0.4358210265636444,
      "learning_rate": 5.007675019782092e-06,
      "loss": 0.5257,
      "step": 43420
    },
    {
      "epoch": 1.333855558627469,
      "grad_norm": 0.41008374094963074,
      "learning_rate": 5.007256281232144e-06,
      "loss": 0.4741,
      "step": 43421
    },
    {
      "epoch": 1.333886277762418,
      "grad_norm": 0.3995683491230011,
      "learning_rate": 5.0068375543431006e-06,
      "loss": 0.3501,
      "step": 43422
    },
    {
      "epoch": 1.3339169968973674,
      "grad_norm": 0.38060227036476135,
      "learning_rate": 5.0064188391159295e-06,
      "loss": 0.4557,
      "step": 43423
    },
    {
      "epoch": 1.3339477160323165,
      "grad_norm": 0.38139066100120544,
      "learning_rate": 5.0060001355516245e-06,
      "loss": 0.4549,
      "step": 43424
    },
    {
      "epoch": 1.3339784351672657,
      "grad_norm": 0.41611844301223755,
      "learning_rate": 5.0055814436511495e-06,
      "loss": 0.4795,
      "step": 43425
    },
    {
      "epoch": 1.3340091543022148,
      "grad_norm": 0.4145306646823883,
      "learning_rate": 5.005162763415492e-06,
      "loss": 0.5629,
      "step": 43426
    },
    {
      "epoch": 1.3340398734371641,
      "grad_norm": 0.49712812900543213,
      "learning_rate": 5.004744094845622e-06,
      "loss": 0.4673,
      "step": 43427
    },
    {
      "epoch": 1.3340705925721132,
      "grad_norm": 0.3820705711841583,
      "learning_rate": 5.0043254379425185e-06,
      "loss": 0.4419,
      "step": 43428
    },
    {
      "epoch": 1.3341013117070624,
      "grad_norm": 0.38219261169433594,
      "learning_rate": 5.003906792707167e-06,
      "loss": 0.463,
      "step": 43429
    },
    {
      "epoch": 1.3341320308420115,
      "grad_norm": 0.4193682372570038,
      "learning_rate": 5.003488159140539e-06,
      "loss": 0.4679,
      "step": 43430
    },
    {
      "epoch": 1.3341627499769606,
      "grad_norm": 0.37791478633880615,
      "learning_rate": 5.0030695372436155e-06,
      "loss": 0.4577,
      "step": 43431
    },
    {
      "epoch": 1.3341934691119097,
      "grad_norm": 0.4169304370880127,
      "learning_rate": 5.002650927017365e-06,
      "loss": 0.5223,
      "step": 43432
    },
    {
      "epoch": 1.3342241882468588,
      "grad_norm": 0.4180302619934082,
      "learning_rate": 5.0022323284627795e-06,
      "loss": 0.4796,
      "step": 43433
    },
    {
      "epoch": 1.3342549073818082,
      "grad_norm": 0.4232085347175598,
      "learning_rate": 5.001813741580826e-06,
      "loss": 0.4848,
      "step": 43434
    },
    {
      "epoch": 1.3342856265167573,
      "grad_norm": 0.4274338483810425,
      "learning_rate": 5.001395166372489e-06,
      "loss": 0.4547,
      "step": 43435
    },
    {
      "epoch": 1.3343163456517064,
      "grad_norm": 0.4552896022796631,
      "learning_rate": 5.0009766028387385e-06,
      "loss": 0.4733,
      "step": 43436
    },
    {
      "epoch": 1.3343470647866555,
      "grad_norm": 0.38681602478027344,
      "learning_rate": 5.000558050980558e-06,
      "loss": 0.4978,
      "step": 43437
    },
    {
      "epoch": 1.3343777839216049,
      "grad_norm": 0.41670310497283936,
      "learning_rate": 5.000139510798922e-06,
      "loss": 0.53,
      "step": 43438
    },
    {
      "epoch": 1.334408503056554,
      "grad_norm": 0.3986988663673401,
      "learning_rate": 4.999720982294813e-06,
      "loss": 0.4158,
      "step": 43439
    },
    {
      "epoch": 1.3344392221915031,
      "grad_norm": 0.40782833099365234,
      "learning_rate": 4.999302465469202e-06,
      "loss": 0.4679,
      "step": 43440
    },
    {
      "epoch": 1.3344699413264522,
      "grad_norm": 0.4355664849281311,
      "learning_rate": 4.998883960323068e-06,
      "loss": 0.4873,
      "step": 43441
    },
    {
      "epoch": 1.3345006604614014,
      "grad_norm": 0.39237403869628906,
      "learning_rate": 4.998465466857391e-06,
      "loss": 0.4948,
      "step": 43442
    },
    {
      "epoch": 1.3345313795963505,
      "grad_norm": 0.41185176372528076,
      "learning_rate": 4.9980469850731505e-06,
      "loss": 0.4329,
      "step": 43443
    },
    {
      "epoch": 1.3345620987312996,
      "grad_norm": 0.4410303235054016,
      "learning_rate": 4.9976285149713165e-06,
      "loss": 0.4926,
      "step": 43444
    },
    {
      "epoch": 1.334592817866249,
      "grad_norm": 0.408512681722641,
      "learning_rate": 4.9972100565528705e-06,
      "loss": 0.482,
      "step": 43445
    },
    {
      "epoch": 1.334623537001198,
      "grad_norm": 0.44873714447021484,
      "learning_rate": 4.996791609818791e-06,
      "loss": 0.4625,
      "step": 43446
    },
    {
      "epoch": 1.3346542561361472,
      "grad_norm": 0.39762380719184875,
      "learning_rate": 4.9963731747700525e-06,
      "loss": 0.4152,
      "step": 43447
    },
    {
      "epoch": 1.3346849752710963,
      "grad_norm": 0.4278453290462494,
      "learning_rate": 4.995954751407639e-06,
      "loss": 0.3993,
      "step": 43448
    },
    {
      "epoch": 1.3347156944060456,
      "grad_norm": 0.45581793785095215,
      "learning_rate": 4.995536339732517e-06,
      "loss": 0.5266,
      "step": 43449
    },
    {
      "epoch": 1.3347464135409948,
      "grad_norm": 0.43992966413497925,
      "learning_rate": 4.995117939745672e-06,
      "loss": 0.4477,
      "step": 43450
    },
    {
      "epoch": 1.334777132675944,
      "grad_norm": 0.39099010825157166,
      "learning_rate": 4.994699551448077e-06,
      "loss": 0.4964,
      "step": 43451
    },
    {
      "epoch": 1.334807851810893,
      "grad_norm": 0.4073333442211151,
      "learning_rate": 4.994281174840715e-06,
      "loss": 0.445,
      "step": 43452
    },
    {
      "epoch": 1.3348385709458421,
      "grad_norm": 0.4287206828594208,
      "learning_rate": 4.993862809924555e-06,
      "loss": 0.4945,
      "step": 43453
    },
    {
      "epoch": 1.3348692900807912,
      "grad_norm": 0.4479084610939026,
      "learning_rate": 4.9934444567005765e-06,
      "loss": 0.5233,
      "step": 43454
    },
    {
      "epoch": 1.3349000092157404,
      "grad_norm": 0.473073273897171,
      "learning_rate": 4.99302611516976e-06,
      "loss": 0.4481,
      "step": 43455
    },
    {
      "epoch": 1.3349307283506897,
      "grad_norm": 0.48057156801223755,
      "learning_rate": 4.992607785333085e-06,
      "loss": 0.469,
      "step": 43456
    },
    {
      "epoch": 1.3349614474856388,
      "grad_norm": 0.37358981370925903,
      "learning_rate": 4.9921894671915195e-06,
      "loss": 0.4935,
      "step": 43457
    },
    {
      "epoch": 1.334992166620588,
      "grad_norm": 0.40231844782829285,
      "learning_rate": 4.991771160746049e-06,
      "loss": 0.4863,
      "step": 43458
    },
    {
      "epoch": 1.335022885755537,
      "grad_norm": 0.43159618973731995,
      "learning_rate": 4.9913528659976386e-06,
      "loss": 0.4627,
      "step": 43459
    },
    {
      "epoch": 1.3350536048904864,
      "grad_norm": 0.4896049201488495,
      "learning_rate": 4.990934582947282e-06,
      "loss": 0.537,
      "step": 43460
    },
    {
      "epoch": 1.3350843240254355,
      "grad_norm": 0.4135700464248657,
      "learning_rate": 4.990516311595943e-06,
      "loss": 0.5179,
      "step": 43461
    },
    {
      "epoch": 1.3351150431603847,
      "grad_norm": 0.4008464813232422,
      "learning_rate": 4.9900980519446074e-06,
      "loss": 0.4562,
      "step": 43462
    },
    {
      "epoch": 1.3351457622953338,
      "grad_norm": 0.40202245116233826,
      "learning_rate": 4.9896798039942426e-06,
      "loss": 0.4821,
      "step": 43463
    },
    {
      "epoch": 1.335176481430283,
      "grad_norm": 0.4028787910938263,
      "learning_rate": 4.989261567745828e-06,
      "loss": 0.4465,
      "step": 43464
    },
    {
      "epoch": 1.335207200565232,
      "grad_norm": 0.39508917927742004,
      "learning_rate": 4.98884334320035e-06,
      "loss": 0.4524,
      "step": 43465
    },
    {
      "epoch": 1.3352379197001811,
      "grad_norm": 0.4194762110710144,
      "learning_rate": 4.988425130358775e-06,
      "loss": 0.4771,
      "step": 43466
    },
    {
      "epoch": 1.3352686388351305,
      "grad_norm": 0.40811654925346375,
      "learning_rate": 4.9880069292220865e-06,
      "loss": 0.4732,
      "step": 43467
    },
    {
      "epoch": 1.3352993579700796,
      "grad_norm": 1.7313101291656494,
      "learning_rate": 4.987588739791255e-06,
      "loss": 0.3896,
      "step": 43468
    },
    {
      "epoch": 1.3353300771050287,
      "grad_norm": 0.4487774670124054,
      "learning_rate": 4.9871705620672595e-06,
      "loss": 0.4798,
      "step": 43469
    },
    {
      "epoch": 1.3353607962399778,
      "grad_norm": 0.41823694109916687,
      "learning_rate": 4.986752396051077e-06,
      "loss": 0.4923,
      "step": 43470
    },
    {
      "epoch": 1.3353915153749272,
      "grad_norm": 0.4003901183605194,
      "learning_rate": 4.986334241743687e-06,
      "loss": 0.5819,
      "step": 43471
    },
    {
      "epoch": 1.3354222345098763,
      "grad_norm": 0.43978017568588257,
      "learning_rate": 4.985916099146062e-06,
      "loss": 0.4245,
      "step": 43472
    },
    {
      "epoch": 1.3354529536448254,
      "grad_norm": 0.516805112361908,
      "learning_rate": 4.985497968259179e-06,
      "loss": 0.4253,
      "step": 43473
    },
    {
      "epoch": 1.3354836727797745,
      "grad_norm": 0.5195664763450623,
      "learning_rate": 4.9850798490840155e-06,
      "loss": 0.5142,
      "step": 43474
    },
    {
      "epoch": 1.3355143919147237,
      "grad_norm": 0.41554951667785645,
      "learning_rate": 4.984661741621553e-06,
      "loss": 0.4628,
      "step": 43475
    },
    {
      "epoch": 1.3355451110496728,
      "grad_norm": 0.4563319683074951,
      "learning_rate": 4.9842436458727585e-06,
      "loss": 0.4178,
      "step": 43476
    },
    {
      "epoch": 1.335575830184622,
      "grad_norm": 0.44393736124038696,
      "learning_rate": 4.983825561838613e-06,
      "loss": 0.4307,
      "step": 43477
    },
    {
      "epoch": 1.3356065493195712,
      "grad_norm": 0.468799352645874,
      "learning_rate": 4.983407489520094e-06,
      "loss": 0.4555,
      "step": 43478
    },
    {
      "epoch": 1.3356372684545204,
      "grad_norm": 0.4007178246974945,
      "learning_rate": 4.982989428918181e-06,
      "loss": 0.4145,
      "step": 43479
    },
    {
      "epoch": 1.3356679875894695,
      "grad_norm": 0.41729310154914856,
      "learning_rate": 4.982571380033843e-06,
      "loss": 0.5046,
      "step": 43480
    },
    {
      "epoch": 1.3356987067244186,
      "grad_norm": 0.4309733510017395,
      "learning_rate": 4.982153342868059e-06,
      "loss": 0.5198,
      "step": 43481
    },
    {
      "epoch": 1.335729425859368,
      "grad_norm": 0.4524499773979187,
      "learning_rate": 4.981735317421807e-06,
      "loss": 0.5034,
      "step": 43482
    },
    {
      "epoch": 1.335760144994317,
      "grad_norm": 0.411805123090744,
      "learning_rate": 4.981317303696063e-06,
      "loss": 0.5167,
      "step": 43483
    },
    {
      "epoch": 1.3357908641292662,
      "grad_norm": 0.41902825236320496,
      "learning_rate": 4.9808993016918065e-06,
      "loss": 0.4196,
      "step": 43484
    },
    {
      "epoch": 1.3358215832642153,
      "grad_norm": 0.4026075303554535,
      "learning_rate": 4.980481311410006e-06,
      "loss": 0.4871,
      "step": 43485
    },
    {
      "epoch": 1.3358523023991644,
      "grad_norm": 0.4372527599334717,
      "learning_rate": 4.980063332851641e-06,
      "loss": 0.5147,
      "step": 43486
    },
    {
      "epoch": 1.3358830215341135,
      "grad_norm": 0.3949458599090576,
      "learning_rate": 4.9796453660176905e-06,
      "loss": 0.4491,
      "step": 43487
    },
    {
      "epoch": 1.3359137406690627,
      "grad_norm": 0.3768022954463959,
      "learning_rate": 4.979227410909132e-06,
      "loss": 0.4002,
      "step": 43488
    },
    {
      "epoch": 1.335944459804012,
      "grad_norm": 0.397330105304718,
      "learning_rate": 4.9788094675269335e-06,
      "loss": 0.4602,
      "step": 43489
    },
    {
      "epoch": 1.3359751789389611,
      "grad_norm": 0.40705522894859314,
      "learning_rate": 4.978391535872082e-06,
      "loss": 0.4211,
      "step": 43490
    },
    {
      "epoch": 1.3360058980739102,
      "grad_norm": 0.4380508363246918,
      "learning_rate": 4.97797361594554e-06,
      "loss": 0.5185,
      "step": 43491
    },
    {
      "epoch": 1.3360366172088594,
      "grad_norm": 0.43537279963493347,
      "learning_rate": 4.977555707748297e-06,
      "loss": 0.5242,
      "step": 43492
    },
    {
      "epoch": 1.3360673363438085,
      "grad_norm": 0.419587641954422,
      "learning_rate": 4.977137811281322e-06,
      "loss": 0.4935,
      "step": 43493
    },
    {
      "epoch": 1.3360980554787578,
      "grad_norm": 0.4189107120037079,
      "learning_rate": 4.976719926545595e-06,
      "loss": 0.4671,
      "step": 43494
    },
    {
      "epoch": 1.336128774613707,
      "grad_norm": 0.4756484627723694,
      "learning_rate": 4.9763020535420814e-06,
      "loss": 0.4952,
      "step": 43495
    },
    {
      "epoch": 1.336159493748656,
      "grad_norm": 0.42332038283348083,
      "learning_rate": 4.9758841922717726e-06,
      "loss": 0.4828,
      "step": 43496
    },
    {
      "epoch": 1.3361902128836052,
      "grad_norm": 0.39402320981025696,
      "learning_rate": 4.975466342735634e-06,
      "loss": 0.467,
      "step": 43497
    },
    {
      "epoch": 1.3362209320185543,
      "grad_norm": 0.3988023102283478,
      "learning_rate": 4.97504850493465e-06,
      "loss": 0.4623,
      "step": 43498
    },
    {
      "epoch": 1.3362516511535034,
      "grad_norm": 0.42414015531539917,
      "learning_rate": 4.974630678869785e-06,
      "loss": 0.4591,
      "step": 43499
    },
    {
      "epoch": 1.3362823702884528,
      "grad_norm": 0.40324392914772034,
      "learning_rate": 4.974212864542019e-06,
      "loss": 0.4342,
      "step": 43500
    },
    {
      "epoch": 1.3363130894234019,
      "grad_norm": 0.41225001215934753,
      "learning_rate": 4.9737950619523356e-06,
      "loss": 0.5634,
      "step": 43501
    },
    {
      "epoch": 1.336343808558351,
      "grad_norm": 0.5303599238395691,
      "learning_rate": 4.973377271101702e-06,
      "loss": 0.4485,
      "step": 43502
    },
    {
      "epoch": 1.3363745276933001,
      "grad_norm": 0.4119207262992859,
      "learning_rate": 4.972959491991101e-06,
      "loss": 0.4627,
      "step": 43503
    },
    {
      "epoch": 1.3364052468282492,
      "grad_norm": 0.39334815740585327,
      "learning_rate": 4.9725417246215e-06,
      "loss": 0.4397,
      "step": 43504
    },
    {
      "epoch": 1.3364359659631986,
      "grad_norm": 0.4047257602214813,
      "learning_rate": 4.972123968993878e-06,
      "loss": 0.4237,
      "step": 43505
    },
    {
      "epoch": 1.3364666850981477,
      "grad_norm": 0.4528786242008209,
      "learning_rate": 4.971706225109213e-06,
      "loss": 0.4904,
      "step": 43506
    },
    {
      "epoch": 1.3364974042330968,
      "grad_norm": 0.4184831380844116,
      "learning_rate": 4.971288492968483e-06,
      "loss": 0.5089,
      "step": 43507
    },
    {
      "epoch": 1.336528123368046,
      "grad_norm": 0.4243503212928772,
      "learning_rate": 4.970870772572656e-06,
      "loss": 0.489,
      "step": 43508
    },
    {
      "epoch": 1.336558842502995,
      "grad_norm": 0.4380972683429718,
      "learning_rate": 4.970453063922711e-06,
      "loss": 0.4581,
      "step": 43509
    },
    {
      "epoch": 1.3365895616379442,
      "grad_norm": 0.4146377444267273,
      "learning_rate": 4.970035367019625e-06,
      "loss": 0.5113,
      "step": 43510
    },
    {
      "epoch": 1.3366202807728933,
      "grad_norm": 0.42074376344680786,
      "learning_rate": 4.969617681864376e-06,
      "loss": 0.5225,
      "step": 43511
    },
    {
      "epoch": 1.3366509999078426,
      "grad_norm": 0.4346983730792999,
      "learning_rate": 4.969200008457932e-06,
      "loss": 0.536,
      "step": 43512
    },
    {
      "epoch": 1.3366817190427918,
      "grad_norm": 0.4328075349330902,
      "learning_rate": 4.968782346801273e-06,
      "loss": 0.4589,
      "step": 43513
    },
    {
      "epoch": 1.3367124381777409,
      "grad_norm": 0.3877556025981903,
      "learning_rate": 4.968364696895374e-06,
      "loss": 0.4813,
      "step": 43514
    },
    {
      "epoch": 1.33674315731269,
      "grad_norm": 0.5068656206130981,
      "learning_rate": 4.9679470587412145e-06,
      "loss": 0.5012,
      "step": 43515
    },
    {
      "epoch": 1.3367738764476393,
      "grad_norm": 0.4353114664554596,
      "learning_rate": 4.967529432339763e-06,
      "loss": 0.4635,
      "step": 43516
    },
    {
      "epoch": 1.3368045955825885,
      "grad_norm": 0.4422699511051178,
      "learning_rate": 4.967111817691997e-06,
      "loss": 0.4561,
      "step": 43517
    },
    {
      "epoch": 1.3368353147175376,
      "grad_norm": 0.4538830816745758,
      "learning_rate": 4.966694214798894e-06,
      "loss": 0.4858,
      "step": 43518
    },
    {
      "epoch": 1.3368660338524867,
      "grad_norm": 0.41803619265556335,
      "learning_rate": 4.966276623661428e-06,
      "loss": 0.526,
      "step": 43519
    },
    {
      "epoch": 1.3368967529874358,
      "grad_norm": 0.3981284499168396,
      "learning_rate": 4.965859044280577e-06,
      "loss": 0.3989,
      "step": 43520
    },
    {
      "epoch": 1.336927472122385,
      "grad_norm": 0.4519670307636261,
      "learning_rate": 4.965441476657311e-06,
      "loss": 0.5118,
      "step": 43521
    },
    {
      "epoch": 1.336958191257334,
      "grad_norm": 0.39611268043518066,
      "learning_rate": 4.965023920792608e-06,
      "loss": 0.5397,
      "step": 43522
    },
    {
      "epoch": 1.3369889103922834,
      "grad_norm": 0.4351222515106201,
      "learning_rate": 4.964606376687443e-06,
      "loss": 0.5414,
      "step": 43523
    },
    {
      "epoch": 1.3370196295272325,
      "grad_norm": 0.4169038236141205,
      "learning_rate": 4.9641888443427955e-06,
      "loss": 0.5053,
      "step": 43524
    },
    {
      "epoch": 1.3370503486621816,
      "grad_norm": 0.39508306980133057,
      "learning_rate": 4.963771323759633e-06,
      "loss": 0.5022,
      "step": 43525
    },
    {
      "epoch": 1.3370810677971308,
      "grad_norm": 0.41088148951530457,
      "learning_rate": 4.963353814938937e-06,
      "loss": 0.4585,
      "step": 43526
    },
    {
      "epoch": 1.33711178693208,
      "grad_norm": 0.4094286262989044,
      "learning_rate": 4.962936317881674e-06,
      "loss": 0.5595,
      "step": 43527
    },
    {
      "epoch": 1.3371425060670292,
      "grad_norm": 0.4176291823387146,
      "learning_rate": 4.962518832588832e-06,
      "loss": 0.4818,
      "step": 43528
    },
    {
      "epoch": 1.3371732252019783,
      "grad_norm": 0.4179328978061676,
      "learning_rate": 4.962101359061374e-06,
      "loss": 0.4883,
      "step": 43529
    },
    {
      "epoch": 1.3372039443369275,
      "grad_norm": 0.4284325838088989,
      "learning_rate": 4.961683897300286e-06,
      "loss": 0.4744,
      "step": 43530
    },
    {
      "epoch": 1.3372346634718766,
      "grad_norm": 0.44649815559387207,
      "learning_rate": 4.961266447306532e-06,
      "loss": 0.5581,
      "step": 43531
    },
    {
      "epoch": 1.3372653826068257,
      "grad_norm": 0.42402857542037964,
      "learning_rate": 4.960849009081093e-06,
      "loss": 0.5196,
      "step": 43532
    },
    {
      "epoch": 1.3372961017417748,
      "grad_norm": 0.4227066934108734,
      "learning_rate": 4.960431582624941e-06,
      "loss": 0.5216,
      "step": 43533
    },
    {
      "epoch": 1.3373268208767242,
      "grad_norm": 0.4143788814544678,
      "learning_rate": 4.960014167939059e-06,
      "loss": 0.4924,
      "step": 43534
    },
    {
      "epoch": 1.3373575400116733,
      "grad_norm": 0.42508378624916077,
      "learning_rate": 4.959596765024411e-06,
      "loss": 0.4667,
      "step": 43535
    },
    {
      "epoch": 1.3373882591466224,
      "grad_norm": 0.37743300199508667,
      "learning_rate": 4.959179373881973e-06,
      "loss": 0.4691,
      "step": 43536
    },
    {
      "epoch": 1.3374189782815715,
      "grad_norm": 0.42475974559783936,
      "learning_rate": 4.958761994512733e-06,
      "loss": 0.5382,
      "step": 43537
    },
    {
      "epoch": 1.3374496974165209,
      "grad_norm": 0.403358519077301,
      "learning_rate": 4.95834462691765e-06,
      "loss": 0.4931,
      "step": 43538
    },
    {
      "epoch": 1.33748041655147,
      "grad_norm": 0.4591774344444275,
      "learning_rate": 4.957927271097711e-06,
      "loss": 0.4924,
      "step": 43539
    },
    {
      "epoch": 1.337511135686419,
      "grad_norm": 0.39447319507598877,
      "learning_rate": 4.95750992705388e-06,
      "loss": 0.4837,
      "step": 43540
    },
    {
      "epoch": 1.3375418548213682,
      "grad_norm": 0.42895689606666565,
      "learning_rate": 4.957092594787137e-06,
      "loss": 0.5069,
      "step": 43541
    },
    {
      "epoch": 1.3375725739563173,
      "grad_norm": 0.39289233088493347,
      "learning_rate": 4.956675274298457e-06,
      "loss": 0.4349,
      "step": 43542
    },
    {
      "epoch": 1.3376032930912665,
      "grad_norm": 0.383703351020813,
      "learning_rate": 4.956257965588818e-06,
      "loss": 0.473,
      "step": 43543
    },
    {
      "epoch": 1.3376340122262156,
      "grad_norm": 0.4253341853618622,
      "learning_rate": 4.955840668659186e-06,
      "loss": 0.4952,
      "step": 43544
    },
    {
      "epoch": 1.337664731361165,
      "grad_norm": 0.4500640630722046,
      "learning_rate": 4.955423383510541e-06,
      "loss": 0.4908,
      "step": 43545
    },
    {
      "epoch": 1.337695450496114,
      "grad_norm": 0.3920232653617859,
      "learning_rate": 4.955006110143857e-06,
      "loss": 0.4846,
      "step": 43546
    },
    {
      "epoch": 1.3377261696310632,
      "grad_norm": 0.42660850286483765,
      "learning_rate": 4.9545888485601126e-06,
      "loss": 0.4953,
      "step": 43547
    },
    {
      "epoch": 1.3377568887660123,
      "grad_norm": 0.4711524248123169,
      "learning_rate": 4.9541715987602735e-06,
      "loss": 0.4659,
      "step": 43548
    },
    {
      "epoch": 1.3377876079009616,
      "grad_norm": 0.446571946144104,
      "learning_rate": 4.95375436074532e-06,
      "loss": 0.5457,
      "step": 43549
    },
    {
      "epoch": 1.3378183270359107,
      "grad_norm": 0.41739416122436523,
      "learning_rate": 4.953337134516225e-06,
      "loss": 0.452,
      "step": 43550
    },
    {
      "epoch": 1.3378490461708599,
      "grad_norm": 0.4465734660625458,
      "learning_rate": 4.952919920073969e-06,
      "loss": 0.513,
      "step": 43551
    },
    {
      "epoch": 1.337879765305809,
      "grad_norm": 0.43276482820510864,
      "learning_rate": 4.952502717419515e-06,
      "loss": 0.4594,
      "step": 43552
    },
    {
      "epoch": 1.337910484440758,
      "grad_norm": 0.4360434114933014,
      "learning_rate": 4.952085526553845e-06,
      "loss": 0.4945,
      "step": 43553
    },
    {
      "epoch": 1.3379412035757072,
      "grad_norm": 0.396770715713501,
      "learning_rate": 4.951668347477931e-06,
      "loss": 0.494,
      "step": 43554
    },
    {
      "epoch": 1.3379719227106563,
      "grad_norm": 0.3837321102619171,
      "learning_rate": 4.951251180192747e-06,
      "loss": 0.4631,
      "step": 43555
    },
    {
      "epoch": 1.3380026418456057,
      "grad_norm": 0.4333440661430359,
      "learning_rate": 4.950834024699274e-06,
      "loss": 0.506,
      "step": 43556
    },
    {
      "epoch": 1.3380333609805548,
      "grad_norm": 0.44617941975593567,
      "learning_rate": 4.950416880998477e-06,
      "loss": 0.4348,
      "step": 43557
    },
    {
      "epoch": 1.338064080115504,
      "grad_norm": 2.1751182079315186,
      "learning_rate": 4.949999749091333e-06,
      "loss": 0.4946,
      "step": 43558
    },
    {
      "epoch": 1.338094799250453,
      "grad_norm": 0.40046167373657227,
      "learning_rate": 4.949582628978819e-06,
      "loss": 0.4786,
      "step": 43559
    },
    {
      "epoch": 1.3381255183854024,
      "grad_norm": 0.398002564907074,
      "learning_rate": 4.949165520661909e-06,
      "loss": 0.3957,
      "step": 43560
    },
    {
      "epoch": 1.3381562375203515,
      "grad_norm": 0.3929694592952728,
      "learning_rate": 4.948748424141573e-06,
      "loss": 0.4459,
      "step": 43561
    },
    {
      "epoch": 1.3381869566553006,
      "grad_norm": 0.4492722749710083,
      "learning_rate": 4.948331339418792e-06,
      "loss": 0.4542,
      "step": 43562
    },
    {
      "epoch": 1.3382176757902497,
      "grad_norm": 0.4241269528865814,
      "learning_rate": 4.947914266494528e-06,
      "loss": 0.4738,
      "step": 43563
    },
    {
      "epoch": 1.3382483949251989,
      "grad_norm": 0.43147701025009155,
      "learning_rate": 4.94749720536977e-06,
      "loss": 0.5096,
      "step": 43564
    },
    {
      "epoch": 1.338279114060148,
      "grad_norm": 0.41987669467926025,
      "learning_rate": 4.9470801560454815e-06,
      "loss": 0.4536,
      "step": 43565
    },
    {
      "epoch": 1.338309833195097,
      "grad_norm": 0.4005286991596222,
      "learning_rate": 4.946663118522645e-06,
      "loss": 0.5125,
      "step": 43566
    },
    {
      "epoch": 1.3383405523300465,
      "grad_norm": 0.4055348336696625,
      "learning_rate": 4.946246092802226e-06,
      "loss": 0.4576,
      "step": 43567
    },
    {
      "epoch": 1.3383712714649956,
      "grad_norm": 0.4322408437728882,
      "learning_rate": 4.945829078885201e-06,
      "loss": 0.3944,
      "step": 43568
    },
    {
      "epoch": 1.3384019905999447,
      "grad_norm": 0.3888033628463745,
      "learning_rate": 4.945412076772545e-06,
      "loss": 0.4086,
      "step": 43569
    },
    {
      "epoch": 1.3384327097348938,
      "grad_norm": 0.3977504074573517,
      "learning_rate": 4.944995086465237e-06,
      "loss": 0.478,
      "step": 43570
    },
    {
      "epoch": 1.3384634288698432,
      "grad_norm": 0.427336186170578,
      "learning_rate": 4.9445781079642415e-06,
      "loss": 0.397,
      "step": 43571
    },
    {
      "epoch": 1.3384941480047923,
      "grad_norm": 0.38340139389038086,
      "learning_rate": 4.9441611412705385e-06,
      "loss": 0.456,
      "step": 43572
    },
    {
      "epoch": 1.3385248671397414,
      "grad_norm": 0.3610272705554962,
      "learning_rate": 4.943744186385099e-06,
      "loss": 0.4322,
      "step": 43573
    },
    {
      "epoch": 1.3385555862746905,
      "grad_norm": 0.3809950053691864,
      "learning_rate": 4.943327243308897e-06,
      "loss": 0.4939,
      "step": 43574
    },
    {
      "epoch": 1.3385863054096396,
      "grad_norm": 0.4268794655799866,
      "learning_rate": 4.942910312042913e-06,
      "loss": 0.4096,
      "step": 43575
    },
    {
      "epoch": 1.3386170245445888,
      "grad_norm": 0.4105096161365509,
      "learning_rate": 4.9424933925881105e-06,
      "loss": 0.4795,
      "step": 43576
    },
    {
      "epoch": 1.3386477436795379,
      "grad_norm": 0.39781850576400757,
      "learning_rate": 4.942076484945469e-06,
      "loss": 0.431,
      "step": 43577
    },
    {
      "epoch": 1.3386784628144872,
      "grad_norm": 0.43636059761047363,
      "learning_rate": 4.941659589115959e-06,
      "loss": 0.5543,
      "step": 43578
    },
    {
      "epoch": 1.3387091819494363,
      "grad_norm": 0.4909801185131073,
      "learning_rate": 4.941242705100561e-06,
      "loss": 0.5284,
      "step": 43579
    },
    {
      "epoch": 1.3387399010843855,
      "grad_norm": 0.43637698888778687,
      "learning_rate": 4.94082583290024e-06,
      "loss": 0.5281,
      "step": 43580
    },
    {
      "epoch": 1.3387706202193346,
      "grad_norm": 0.4233148396015167,
      "learning_rate": 4.9404089725159745e-06,
      "loss": 0.4967,
      "step": 43581
    },
    {
      "epoch": 1.338801339354284,
      "grad_norm": 0.4071248173713684,
      "learning_rate": 4.939992123948737e-06,
      "loss": 0.5247,
      "step": 43582
    },
    {
      "epoch": 1.338832058489233,
      "grad_norm": 0.41716745495796204,
      "learning_rate": 4.939575287199504e-06,
      "loss": 0.46,
      "step": 43583
    },
    {
      "epoch": 1.3388627776241822,
      "grad_norm": 0.4114172160625458,
      "learning_rate": 4.939158462269243e-06,
      "loss": 0.4252,
      "step": 43584
    },
    {
      "epoch": 1.3388934967591313,
      "grad_norm": 0.4463633894920349,
      "learning_rate": 4.938741649158931e-06,
      "loss": 0.4544,
      "step": 43585
    },
    {
      "epoch": 1.3389242158940804,
      "grad_norm": 0.37062790989875793,
      "learning_rate": 4.938324847869542e-06,
      "loss": 0.5107,
      "step": 43586
    },
    {
      "epoch": 1.3389549350290295,
      "grad_norm": 0.42983654141426086,
      "learning_rate": 4.937908058402053e-06,
      "loss": 0.3704,
      "step": 43587
    },
    {
      "epoch": 1.3389856541639786,
      "grad_norm": 0.41760191321372986,
      "learning_rate": 4.937491280757428e-06,
      "loss": 0.5336,
      "step": 43588
    },
    {
      "epoch": 1.339016373298928,
      "grad_norm": 0.40653038024902344,
      "learning_rate": 4.937074514936649e-06,
      "loss": 0.4497,
      "step": 43589
    },
    {
      "epoch": 1.339047092433877,
      "grad_norm": 0.4533742368221283,
      "learning_rate": 4.936657760940681e-06,
      "loss": 0.5011,
      "step": 43590
    },
    {
      "epoch": 1.3390778115688262,
      "grad_norm": 0.41039028763771057,
      "learning_rate": 4.936241018770504e-06,
      "loss": 0.5331,
      "step": 43591
    },
    {
      "epoch": 1.3391085307037753,
      "grad_norm": 0.3693384826183319,
      "learning_rate": 4.935824288427095e-06,
      "loss": 0.4567,
      "step": 43592
    },
    {
      "epoch": 1.3391392498387247,
      "grad_norm": 0.38991615176200867,
      "learning_rate": 4.935407569911417e-06,
      "loss": 0.478,
      "step": 43593
    },
    {
      "epoch": 1.3391699689736738,
      "grad_norm": 0.394372820854187,
      "learning_rate": 4.934990863224449e-06,
      "loss": 0.4308,
      "step": 43594
    },
    {
      "epoch": 1.339200688108623,
      "grad_norm": 0.4147568345069885,
      "learning_rate": 4.934574168367163e-06,
      "loss": 0.5251,
      "step": 43595
    },
    {
      "epoch": 1.339231407243572,
      "grad_norm": 0.3614766597747803,
      "learning_rate": 4.934157485340537e-06,
      "loss": 0.4086,
      "step": 43596
    },
    {
      "epoch": 1.3392621263785212,
      "grad_norm": 0.3510710895061493,
      "learning_rate": 4.933740814145537e-06,
      "loss": 0.4574,
      "step": 43597
    },
    {
      "epoch": 1.3392928455134703,
      "grad_norm": 0.40299564599990845,
      "learning_rate": 4.933324154783141e-06,
      "loss": 0.4831,
      "step": 43598
    },
    {
      "epoch": 1.3393235646484194,
      "grad_norm": 0.4089168608188629,
      "learning_rate": 4.932907507254314e-06,
      "loss": 0.4995,
      "step": 43599
    },
    {
      "epoch": 1.3393542837833687,
      "grad_norm": 0.39381662011146545,
      "learning_rate": 4.932490871560043e-06,
      "loss": 0.4804,
      "step": 43600
    },
    {
      "epoch": 1.3393850029183179,
      "grad_norm": 0.37353771924972534,
      "learning_rate": 4.932074247701289e-06,
      "loss": 0.4301,
      "step": 43601
    },
    {
      "epoch": 1.339415722053267,
      "grad_norm": 0.42915457487106323,
      "learning_rate": 4.9316576356790344e-06,
      "loss": 0.4858,
      "step": 43602
    },
    {
      "epoch": 1.339446441188216,
      "grad_norm": 0.4170064926147461,
      "learning_rate": 4.931241035494243e-06,
      "loss": 0.491,
      "step": 43603
    },
    {
      "epoch": 1.3394771603231652,
      "grad_norm": 0.40470629930496216,
      "learning_rate": 4.9308244471478925e-06,
      "loss": 0.5239,
      "step": 43604
    },
    {
      "epoch": 1.3395078794581146,
      "grad_norm": 0.4099048972129822,
      "learning_rate": 4.930407870640955e-06,
      "loss": 0.5411,
      "step": 43605
    },
    {
      "epoch": 1.3395385985930637,
      "grad_norm": 0.4085959792137146,
      "learning_rate": 4.929991305974408e-06,
      "loss": 0.4938,
      "step": 43606
    },
    {
      "epoch": 1.3395693177280128,
      "grad_norm": 0.4103073179721832,
      "learning_rate": 4.929574753149216e-06,
      "loss": 0.4588,
      "step": 43607
    },
    {
      "epoch": 1.339600036862962,
      "grad_norm": 0.41995853185653687,
      "learning_rate": 4.929158212166357e-06,
      "loss": 0.5028,
      "step": 43608
    },
    {
      "epoch": 1.339630755997911,
      "grad_norm": 0.4492572844028473,
      "learning_rate": 4.928741683026803e-06,
      "loss": 0.5089,
      "step": 43609
    },
    {
      "epoch": 1.3396614751328602,
      "grad_norm": 0.41528281569480896,
      "learning_rate": 4.928325165731528e-06,
      "loss": 0.4632,
      "step": 43610
    },
    {
      "epoch": 1.3396921942678095,
      "grad_norm": 0.44813206791877747,
      "learning_rate": 4.927908660281507e-06,
      "loss": 0.4576,
      "step": 43611
    },
    {
      "epoch": 1.3397229134027586,
      "grad_norm": 0.40864497423171997,
      "learning_rate": 4.927492166677704e-06,
      "loss": 0.408,
      "step": 43612
    },
    {
      "epoch": 1.3397536325377077,
      "grad_norm": 0.4774937331676483,
      "learning_rate": 4.9270756849210985e-06,
      "loss": 0.4718,
      "step": 43613
    },
    {
      "epoch": 1.3397843516726569,
      "grad_norm": 0.4444121718406677,
      "learning_rate": 4.926659215012662e-06,
      "loss": 0.4958,
      "step": 43614
    },
    {
      "epoch": 1.339815070807606,
      "grad_norm": 0.40101027488708496,
      "learning_rate": 4.926242756953372e-06,
      "loss": 0.433,
      "step": 43615
    },
    {
      "epoch": 1.3398457899425553,
      "grad_norm": 0.4236709773540497,
      "learning_rate": 4.9258263107441916e-06,
      "loss": 0.3663,
      "step": 43616
    },
    {
      "epoch": 1.3398765090775044,
      "grad_norm": 0.42484143376350403,
      "learning_rate": 4.925409876386098e-06,
      "loss": 0.5104,
      "step": 43617
    },
    {
      "epoch": 1.3399072282124536,
      "grad_norm": 0.41813942790031433,
      "learning_rate": 4.924993453880065e-06,
      "loss": 0.4865,
      "step": 43618
    },
    {
      "epoch": 1.3399379473474027,
      "grad_norm": 0.4073089361190796,
      "learning_rate": 4.924577043227067e-06,
      "loss": 0.417,
      "step": 43619
    },
    {
      "epoch": 1.3399686664823518,
      "grad_norm": 0.3831193447113037,
      "learning_rate": 4.924160644428071e-06,
      "loss": 0.4836,
      "step": 43620
    },
    {
      "epoch": 1.339999385617301,
      "grad_norm": 0.38022351264953613,
      "learning_rate": 4.923744257484051e-06,
      "loss": 0.45,
      "step": 43621
    },
    {
      "epoch": 1.34003010475225,
      "grad_norm": 0.3898947834968567,
      "learning_rate": 4.923327882395982e-06,
      "loss": 0.4816,
      "step": 43622
    },
    {
      "epoch": 1.3400608238871994,
      "grad_norm": 0.40425029397010803,
      "learning_rate": 4.922911519164838e-06,
      "loss": 0.4266,
      "step": 43623
    },
    {
      "epoch": 1.3400915430221485,
      "grad_norm": 0.4139234721660614,
      "learning_rate": 4.922495167791585e-06,
      "loss": 0.412,
      "step": 43624
    },
    {
      "epoch": 1.3401222621570976,
      "grad_norm": 0.4049532115459442,
      "learning_rate": 4.922078828277205e-06,
      "loss": 0.4999,
      "step": 43625
    },
    {
      "epoch": 1.3401529812920467,
      "grad_norm": 0.42265766859054565,
      "learning_rate": 4.9216625006226545e-06,
      "loss": 0.4764,
      "step": 43626
    },
    {
      "epoch": 1.340183700426996,
      "grad_norm": 0.40106919407844543,
      "learning_rate": 4.92124618482892e-06,
      "loss": 0.507,
      "step": 43627
    },
    {
      "epoch": 1.3402144195619452,
      "grad_norm": 0.40420103073120117,
      "learning_rate": 4.920829880896974e-06,
      "loss": 0.564,
      "step": 43628
    },
    {
      "epoch": 1.3402451386968943,
      "grad_norm": 0.4256403148174286,
      "learning_rate": 4.920413588827782e-06,
      "loss": 0.4467,
      "step": 43629
    },
    {
      "epoch": 1.3402758578318434,
      "grad_norm": 0.40830183029174805,
      "learning_rate": 4.919997308622322e-06,
      "loss": 0.5115,
      "step": 43630
    },
    {
      "epoch": 1.3403065769667926,
      "grad_norm": 0.42229148745536804,
      "learning_rate": 4.919581040281555e-06,
      "loss": 0.5115,
      "step": 43631
    },
    {
      "epoch": 1.3403372961017417,
      "grad_norm": 0.4574381113052368,
      "learning_rate": 4.919164783806469e-06,
      "loss": 0.4933,
      "step": 43632
    },
    {
      "epoch": 1.3403680152366908,
      "grad_norm": 0.45936116576194763,
      "learning_rate": 4.918748539198024e-06,
      "loss": 0.4971,
      "step": 43633
    },
    {
      "epoch": 1.3403987343716401,
      "grad_norm": 0.46741625666618347,
      "learning_rate": 4.9183323064572005e-06,
      "loss": 0.4191,
      "step": 43634
    },
    {
      "epoch": 1.3404294535065893,
      "grad_norm": 0.39365237951278687,
      "learning_rate": 4.91791608558496e-06,
      "loss": 0.45,
      "step": 43635
    },
    {
      "epoch": 1.3404601726415384,
      "grad_norm": 0.3840617537498474,
      "learning_rate": 4.917499876582289e-06,
      "loss": 0.4911,
      "step": 43636
    },
    {
      "epoch": 1.3404908917764875,
      "grad_norm": 0.40142983198165894,
      "learning_rate": 4.917083679450148e-06,
      "loss": 0.4705,
      "step": 43637
    },
    {
      "epoch": 1.3405216109114368,
      "grad_norm": 0.5418527722358704,
      "learning_rate": 4.916667494189517e-06,
      "loss": 0.5065,
      "step": 43638
    },
    {
      "epoch": 1.340552330046386,
      "grad_norm": 0.45708438754081726,
      "learning_rate": 4.9162513208013595e-06,
      "loss": 0.4598,
      "step": 43639
    },
    {
      "epoch": 1.340583049181335,
      "grad_norm": 0.40800777077674866,
      "learning_rate": 4.915835159286653e-06,
      "loss": 0.4741,
      "step": 43640
    },
    {
      "epoch": 1.3406137683162842,
      "grad_norm": 0.4117542803287506,
      "learning_rate": 4.915419009646367e-06,
      "loss": 0.4931,
      "step": 43641
    },
    {
      "epoch": 1.3406444874512333,
      "grad_norm": 0.41101038455963135,
      "learning_rate": 4.91500287188148e-06,
      "loss": 0.4744,
      "step": 43642
    },
    {
      "epoch": 1.3406752065861824,
      "grad_norm": 0.3716902732849121,
      "learning_rate": 4.9145867459929556e-06,
      "loss": 0.4528,
      "step": 43643
    },
    {
      "epoch": 1.3407059257211316,
      "grad_norm": 0.4309532642364502,
      "learning_rate": 4.914170631981768e-06,
      "loss": 0.4365,
      "step": 43644
    },
    {
      "epoch": 1.340736644856081,
      "grad_norm": 0.4859603941440582,
      "learning_rate": 4.913754529848891e-06,
      "loss": 0.5155,
      "step": 43645
    },
    {
      "epoch": 1.34076736399103,
      "grad_norm": 0.40868011116981506,
      "learning_rate": 4.913338439595296e-06,
      "loss": 0.4702,
      "step": 43646
    },
    {
      "epoch": 1.3407980831259791,
      "grad_norm": 0.39997440576553345,
      "learning_rate": 4.912922361221957e-06,
      "loss": 0.4561,
      "step": 43647
    },
    {
      "epoch": 1.3408288022609283,
      "grad_norm": 0.4034726619720459,
      "learning_rate": 4.912506294729839e-06,
      "loss": 0.4915,
      "step": 43648
    },
    {
      "epoch": 1.3408595213958776,
      "grad_norm": 0.47224199771881104,
      "learning_rate": 4.912090240119919e-06,
      "loss": 0.5173,
      "step": 43649
    },
    {
      "epoch": 1.3408902405308267,
      "grad_norm": 0.3891242444515228,
      "learning_rate": 4.911674197393167e-06,
      "loss": 0.4311,
      "step": 43650
    },
    {
      "epoch": 1.3409209596657758,
      "grad_norm": 0.49625363945961,
      "learning_rate": 4.911258166550559e-06,
      "loss": 0.5484,
      "step": 43651
    },
    {
      "epoch": 1.340951678800725,
      "grad_norm": 0.45224979519844055,
      "learning_rate": 4.910842147593059e-06,
      "loss": 0.4646,
      "step": 43652
    },
    {
      "epoch": 1.340982397935674,
      "grad_norm": 0.411613404750824,
      "learning_rate": 4.910426140521643e-06,
      "loss": 0.5152,
      "step": 43653
    },
    {
      "epoch": 1.3410131170706232,
      "grad_norm": 0.4109126329421997,
      "learning_rate": 4.910010145337282e-06,
      "loss": 0.4772,
      "step": 43654
    },
    {
      "epoch": 1.3410438362055723,
      "grad_norm": 0.3873733878135681,
      "learning_rate": 4.909594162040952e-06,
      "loss": 0.4127,
      "step": 43655
    },
    {
      "epoch": 1.3410745553405217,
      "grad_norm": 0.4200889766216278,
      "learning_rate": 4.909178190633616e-06,
      "loss": 0.4959,
      "step": 43656
    },
    {
      "epoch": 1.3411052744754708,
      "grad_norm": 0.4077169597148895,
      "learning_rate": 4.9087622311162496e-06,
      "loss": 0.5315,
      "step": 43657
    },
    {
      "epoch": 1.34113599361042,
      "grad_norm": 0.4187692403793335,
      "learning_rate": 4.908346283489824e-06,
      "loss": 0.4694,
      "step": 43658
    },
    {
      "epoch": 1.341166712745369,
      "grad_norm": 0.38495302200317383,
      "learning_rate": 4.907930347755316e-06,
      "loss": 0.4683,
      "step": 43659
    },
    {
      "epoch": 1.3411974318803184,
      "grad_norm": 0.4295942187309265,
      "learning_rate": 4.90751442391369e-06,
      "loss": 0.4555,
      "step": 43660
    },
    {
      "epoch": 1.3412281510152675,
      "grad_norm": 0.36721837520599365,
      "learning_rate": 4.907098511965921e-06,
      "loss": 0.5375,
      "step": 43661
    },
    {
      "epoch": 1.3412588701502166,
      "grad_norm": 0.4266759753227234,
      "learning_rate": 4.906682611912973e-06,
      "loss": 0.4955,
      "step": 43662
    },
    {
      "epoch": 1.3412895892851657,
      "grad_norm": 0.6013399362564087,
      "learning_rate": 4.90626672375583e-06,
      "loss": 0.4113,
      "step": 43663
    },
    {
      "epoch": 1.3413203084201148,
      "grad_norm": 0.415918231010437,
      "learning_rate": 4.905850847495455e-06,
      "loss": 0.5282,
      "step": 43664
    },
    {
      "epoch": 1.341351027555064,
      "grad_norm": 0.44614285230636597,
      "learning_rate": 4.905434983132818e-06,
      "loss": 0.5194,
      "step": 43665
    },
    {
      "epoch": 1.341381746690013,
      "grad_norm": 0.4463012218475342,
      "learning_rate": 4.9050191306688996e-06,
      "loss": 0.4775,
      "step": 43666
    },
    {
      "epoch": 1.3414124658249624,
      "grad_norm": 0.4479060769081116,
      "learning_rate": 4.904603290104657e-06,
      "loss": 0.4759,
      "step": 43667
    },
    {
      "epoch": 1.3414431849599115,
      "grad_norm": 0.4032353162765503,
      "learning_rate": 4.904187461441077e-06,
      "loss": 0.4917,
      "step": 43668
    },
    {
      "epoch": 1.3414739040948607,
      "grad_norm": 0.36356234550476074,
      "learning_rate": 4.903771644679118e-06,
      "loss": 0.47,
      "step": 43669
    },
    {
      "epoch": 1.3415046232298098,
      "grad_norm": 0.4347541630268097,
      "learning_rate": 4.903355839819761e-06,
      "loss": 0.4884,
      "step": 43670
    },
    {
      "epoch": 1.3415353423647591,
      "grad_norm": 0.4368804097175598,
      "learning_rate": 4.902940046863968e-06,
      "loss": 0.4228,
      "step": 43671
    },
    {
      "epoch": 1.3415660614997083,
      "grad_norm": 0.3838999271392822,
      "learning_rate": 4.902524265812715e-06,
      "loss": 0.3748,
      "step": 43672
    },
    {
      "epoch": 1.3415967806346574,
      "grad_norm": 0.4133811295032501,
      "learning_rate": 4.902108496666973e-06,
      "loss": 0.4632,
      "step": 43673
    },
    {
      "epoch": 1.3416274997696065,
      "grad_norm": 0.3961779773235321,
      "learning_rate": 4.901692739427716e-06,
      "loss": 0.5205,
      "step": 43674
    },
    {
      "epoch": 1.3416582189045556,
      "grad_norm": 0.4167288541793823,
      "learning_rate": 4.901276994095907e-06,
      "loss": 0.5601,
      "step": 43675
    },
    {
      "epoch": 1.3416889380395047,
      "grad_norm": 0.4413883686065674,
      "learning_rate": 4.900861260672523e-06,
      "loss": 0.4883,
      "step": 43676
    },
    {
      "epoch": 1.3417196571744539,
      "grad_norm": 0.40341150760650635,
      "learning_rate": 4.900445539158532e-06,
      "loss": 0.412,
      "step": 43677
    },
    {
      "epoch": 1.3417503763094032,
      "grad_norm": 0.43838533759117126,
      "learning_rate": 4.900029829554912e-06,
      "loss": 0.4358,
      "step": 43678
    },
    {
      "epoch": 1.3417810954443523,
      "grad_norm": 0.4397769868373871,
      "learning_rate": 4.8996141318626245e-06,
      "loss": 0.5222,
      "step": 43679
    },
    {
      "epoch": 1.3418118145793014,
      "grad_norm": 0.40784546732902527,
      "learning_rate": 4.8991984460826434e-06,
      "loss": 0.4926,
      "step": 43680
    },
    {
      "epoch": 1.3418425337142506,
      "grad_norm": 0.4396727681159973,
      "learning_rate": 4.898782772215942e-06,
      "loss": 0.4887,
      "step": 43681
    },
    {
      "epoch": 1.3418732528492,
      "grad_norm": 0.4514431953430176,
      "learning_rate": 4.898367110263489e-06,
      "loss": 0.4757,
      "step": 43682
    },
    {
      "epoch": 1.341903971984149,
      "grad_norm": 0.40514442324638367,
      "learning_rate": 4.897951460226259e-06,
      "loss": 0.4567,
      "step": 43683
    },
    {
      "epoch": 1.3419346911190981,
      "grad_norm": 0.4266563355922699,
      "learning_rate": 4.897535822105217e-06,
      "loss": 0.5115,
      "step": 43684
    },
    {
      "epoch": 1.3419654102540473,
      "grad_norm": 0.39978277683258057,
      "learning_rate": 4.897120195901336e-06,
      "loss": 0.5429,
      "step": 43685
    },
    {
      "epoch": 1.3419961293889964,
      "grad_norm": 0.3766271471977234,
      "learning_rate": 4.896704581615587e-06,
      "loss": 0.4586,
      "step": 43686
    },
    {
      "epoch": 1.3420268485239455,
      "grad_norm": 0.440204381942749,
      "learning_rate": 4.896288979248945e-06,
      "loss": 0.497,
      "step": 43687
    },
    {
      "epoch": 1.3420575676588946,
      "grad_norm": 0.40660321712493896,
      "learning_rate": 4.895873388802373e-06,
      "loss": 0.497,
      "step": 43688
    },
    {
      "epoch": 1.342088286793844,
      "grad_norm": 0.40080851316452026,
      "learning_rate": 4.8954578102768434e-06,
      "loss": 0.5432,
      "step": 43689
    },
    {
      "epoch": 1.342119005928793,
      "grad_norm": 0.3918219804763794,
      "learning_rate": 4.89504224367333e-06,
      "loss": 0.4667,
      "step": 43690
    },
    {
      "epoch": 1.3421497250637422,
      "grad_norm": 0.42134952545166016,
      "learning_rate": 4.894626688992806e-06,
      "loss": 0.4489,
      "step": 43691
    },
    {
      "epoch": 1.3421804441986913,
      "grad_norm": 0.40586885809898376,
      "learning_rate": 4.894211146236234e-06,
      "loss": 0.4791,
      "step": 43692
    },
    {
      "epoch": 1.3422111633336407,
      "grad_norm": 0.49932464957237244,
      "learning_rate": 4.8937956154045916e-06,
      "loss": 0.4548,
      "step": 43693
    },
    {
      "epoch": 1.3422418824685898,
      "grad_norm": 0.4117696285247803,
      "learning_rate": 4.89338009649884e-06,
      "loss": 0.4618,
      "step": 43694
    },
    {
      "epoch": 1.342272601603539,
      "grad_norm": 0.4170992374420166,
      "learning_rate": 4.892964589519962e-06,
      "loss": 0.4445,
      "step": 43695
    },
    {
      "epoch": 1.342303320738488,
      "grad_norm": 0.45843830704689026,
      "learning_rate": 4.892549094468918e-06,
      "loss": 0.4678,
      "step": 43696
    },
    {
      "epoch": 1.3423340398734371,
      "grad_norm": 0.4206997752189636,
      "learning_rate": 4.8921336113466865e-06,
      "loss": 0.4843,
      "step": 43697
    },
    {
      "epoch": 1.3423647590083863,
      "grad_norm": 0.39844027161598206,
      "learning_rate": 4.891718140154227e-06,
      "loss": 0.4448,
      "step": 43698
    },
    {
      "epoch": 1.3423954781433354,
      "grad_norm": 0.5104299783706665,
      "learning_rate": 4.8913026808925225e-06,
      "loss": 0.4376,
      "step": 43699
    },
    {
      "epoch": 1.3424261972782847,
      "grad_norm": 0.4534034729003906,
      "learning_rate": 4.890887233562535e-06,
      "loss": 0.4317,
      "step": 43700
    },
    {
      "epoch": 1.3424569164132338,
      "grad_norm": 0.4580349028110504,
      "learning_rate": 4.890471798165236e-06,
      "loss": 0.4446,
      "step": 43701
    },
    {
      "epoch": 1.342487635548183,
      "grad_norm": 0.38923925161361694,
      "learning_rate": 4.890056374701602e-06,
      "loss": 0.4398,
      "step": 43702
    },
    {
      "epoch": 1.342518354683132,
      "grad_norm": 0.4075110852718353,
      "learning_rate": 4.889640963172589e-06,
      "loss": 0.5535,
      "step": 43703
    },
    {
      "epoch": 1.3425490738180814,
      "grad_norm": 0.47716742753982544,
      "learning_rate": 4.889225563579185e-06,
      "loss": 0.5165,
      "step": 43704
    },
    {
      "epoch": 1.3425797929530305,
      "grad_norm": 0.49714794754981995,
      "learning_rate": 4.888810175922348e-06,
      "loss": 0.379,
      "step": 43705
    },
    {
      "epoch": 1.3426105120879797,
      "grad_norm": 0.6178293824195862,
      "learning_rate": 4.888394800203056e-06,
      "loss": 0.5143,
      "step": 43706
    },
    {
      "epoch": 1.3426412312229288,
      "grad_norm": 0.40618062019348145,
      "learning_rate": 4.88797943642227e-06,
      "loss": 0.4559,
      "step": 43707
    },
    {
      "epoch": 1.342671950357878,
      "grad_norm": 0.479535311460495,
      "learning_rate": 4.887564084580966e-06,
      "loss": 0.4465,
      "step": 43708
    },
    {
      "epoch": 1.342702669492827,
      "grad_norm": 0.41296741366386414,
      "learning_rate": 4.887148744680112e-06,
      "loss": 0.5616,
      "step": 43709
    },
    {
      "epoch": 1.3427333886277761,
      "grad_norm": 0.4318941533565521,
      "learning_rate": 4.886733416720684e-06,
      "loss": 0.4338,
      "step": 43710
    },
    {
      "epoch": 1.3427641077627255,
      "grad_norm": 0.8323989510536194,
      "learning_rate": 4.886318100703643e-06,
      "loss": 0.5943,
      "step": 43711
    },
    {
      "epoch": 1.3427948268976746,
      "grad_norm": 0.42073169350624084,
      "learning_rate": 4.8859027966299635e-06,
      "loss": 0.5031,
      "step": 43712
    },
    {
      "epoch": 1.3428255460326237,
      "grad_norm": 0.42928391695022583,
      "learning_rate": 4.885487504500615e-06,
      "loss": 0.5238,
      "step": 43713
    },
    {
      "epoch": 1.3428562651675728,
      "grad_norm": 0.4180165231227875,
      "learning_rate": 4.885072224316572e-06,
      "loss": 0.4422,
      "step": 43714
    },
    {
      "epoch": 1.3428869843025222,
      "grad_norm": 0.4778631925582886,
      "learning_rate": 4.8846569560787945e-06,
      "loss": 0.531,
      "step": 43715
    },
    {
      "epoch": 1.3429177034374713,
      "grad_norm": 0.4217536449432373,
      "learning_rate": 4.884241699788259e-06,
      "loss": 0.4943,
      "step": 43716
    },
    {
      "epoch": 1.3429484225724204,
      "grad_norm": 0.522589921951294,
      "learning_rate": 4.8838264554459346e-06,
      "loss": 0.4099,
      "step": 43717
    },
    {
      "epoch": 1.3429791417073695,
      "grad_norm": 0.4002867043018341,
      "learning_rate": 4.883411223052794e-06,
      "loss": 0.5243,
      "step": 43718
    },
    {
      "epoch": 1.3430098608423187,
      "grad_norm": 0.3997717797756195,
      "learning_rate": 4.882996002609801e-06,
      "loss": 0.4468,
      "step": 43719
    },
    {
      "epoch": 1.3430405799772678,
      "grad_norm": 0.4313318133354187,
      "learning_rate": 4.882580794117927e-06,
      "loss": 0.4617,
      "step": 43720
    },
    {
      "epoch": 1.343071299112217,
      "grad_norm": 0.5902612209320068,
      "learning_rate": 4.882165597578143e-06,
      "loss": 0.4575,
      "step": 43721
    },
    {
      "epoch": 1.3431020182471662,
      "grad_norm": 0.3995020389556885,
      "learning_rate": 4.88175041299142e-06,
      "loss": 0.4549,
      "step": 43722
    },
    {
      "epoch": 1.3431327373821154,
      "grad_norm": 0.3989199995994568,
      "learning_rate": 4.8813352403587296e-06,
      "loss": 0.4663,
      "step": 43723
    },
    {
      "epoch": 1.3431634565170645,
      "grad_norm": 0.40883341431617737,
      "learning_rate": 4.880920079681034e-06,
      "loss": 0.517,
      "step": 43724
    },
    {
      "epoch": 1.3431941756520136,
      "grad_norm": 0.5236907601356506,
      "learning_rate": 4.880504930959308e-06,
      "loss": 0.4408,
      "step": 43725
    },
    {
      "epoch": 1.3432248947869627,
      "grad_norm": 0.4557821750640869,
      "learning_rate": 4.880089794194519e-06,
      "loss": 0.4065,
      "step": 43726
    },
    {
      "epoch": 1.343255613921912,
      "grad_norm": 0.44698017835617065,
      "learning_rate": 4.8796746693876425e-06,
      "loss": 0.5277,
      "step": 43727
    },
    {
      "epoch": 1.3432863330568612,
      "grad_norm": 0.41711968183517456,
      "learning_rate": 4.879259556539639e-06,
      "loss": 0.5206,
      "step": 43728
    },
    {
      "epoch": 1.3433170521918103,
      "grad_norm": 0.38284802436828613,
      "learning_rate": 4.878844455651487e-06,
      "loss": 0.3735,
      "step": 43729
    },
    {
      "epoch": 1.3433477713267594,
      "grad_norm": 0.4170978367328644,
      "learning_rate": 4.8784293667241435e-06,
      "loss": 0.4212,
      "step": 43730
    },
    {
      "epoch": 1.3433784904617085,
      "grad_norm": 0.3994009792804718,
      "learning_rate": 4.878014289758594e-06,
      "loss": 0.4245,
      "step": 43731
    },
    {
      "epoch": 1.3434092095966577,
      "grad_norm": 0.4138426184654236,
      "learning_rate": 4.877599224755794e-06,
      "loss": 0.4285,
      "step": 43732
    },
    {
      "epoch": 1.3434399287316068,
      "grad_norm": 0.5118585824966431,
      "learning_rate": 4.8771841717167245e-06,
      "loss": 0.4643,
      "step": 43733
    },
    {
      "epoch": 1.3434706478665561,
      "grad_norm": 0.3928660750389099,
      "learning_rate": 4.876769130642345e-06,
      "loss": 0.4494,
      "step": 43734
    },
    {
      "epoch": 1.3435013670015052,
      "grad_norm": 0.42267733812332153,
      "learning_rate": 4.876354101533629e-06,
      "loss": 0.4684,
      "step": 43735
    },
    {
      "epoch": 1.3435320861364544,
      "grad_norm": 0.4198247492313385,
      "learning_rate": 4.875939084391545e-06,
      "loss": 0.5089,
      "step": 43736
    },
    {
      "epoch": 1.3435628052714035,
      "grad_norm": 0.41629788279533386,
      "learning_rate": 4.875524079217064e-06,
      "loss": 0.4621,
      "step": 43737
    },
    {
      "epoch": 1.3435935244063528,
      "grad_norm": 0.42427945137023926,
      "learning_rate": 4.875109086011158e-06,
      "loss": 0.4775,
      "step": 43738
    },
    {
      "epoch": 1.343624243541302,
      "grad_norm": 0.489272803068161,
      "learning_rate": 4.874694104774785e-06,
      "loss": 0.4488,
      "step": 43739
    },
    {
      "epoch": 1.343654962676251,
      "grad_norm": 0.4368550777435303,
      "learning_rate": 4.87427913550893e-06,
      "loss": 0.4949,
      "step": 43740
    },
    {
      "epoch": 1.3436856818112002,
      "grad_norm": 0.41254276037216187,
      "learning_rate": 4.873864178214549e-06,
      "loss": 0.5846,
      "step": 43741
    },
    {
      "epoch": 1.3437164009461493,
      "grad_norm": 0.40747031569480896,
      "learning_rate": 4.873449232892621e-06,
      "loss": 0.4354,
      "step": 43742
    },
    {
      "epoch": 1.3437471200810984,
      "grad_norm": 0.5006558895111084,
      "learning_rate": 4.8730342995441075e-06,
      "loss": 0.4784,
      "step": 43743
    },
    {
      "epoch": 1.3437778392160475,
      "grad_norm": 0.4105336666107178,
      "learning_rate": 4.872619378169978e-06,
      "loss": 0.4527,
      "step": 43744
    },
    {
      "epoch": 1.3438085583509969,
      "grad_norm": 0.4445200562477112,
      "learning_rate": 4.872204468771206e-06,
      "loss": 0.5341,
      "step": 43745
    },
    {
      "epoch": 1.343839277485946,
      "grad_norm": 0.37998151779174805,
      "learning_rate": 4.871789571348762e-06,
      "loss": 0.4254,
      "step": 43746
    },
    {
      "epoch": 1.3438699966208951,
      "grad_norm": 0.38453441858291626,
      "learning_rate": 4.871374685903607e-06,
      "loss": 0.4312,
      "step": 43747
    },
    {
      "epoch": 1.3439007157558442,
      "grad_norm": 0.40591752529144287,
      "learning_rate": 4.870959812436715e-06,
      "loss": 0.4774,
      "step": 43748
    },
    {
      "epoch": 1.3439314348907936,
      "grad_norm": 0.4341999292373657,
      "learning_rate": 4.870544950949055e-06,
      "loss": 0.4275,
      "step": 43749
    },
    {
      "epoch": 1.3439621540257427,
      "grad_norm": 0.3958919942378998,
      "learning_rate": 4.870130101441599e-06,
      "loss": 0.5169,
      "step": 43750
    },
    {
      "epoch": 1.3439928731606918,
      "grad_norm": 0.37263116240501404,
      "learning_rate": 4.869715263915309e-06,
      "loss": 0.5051,
      "step": 43751
    },
    {
      "epoch": 1.344023592295641,
      "grad_norm": 0.41610196232795715,
      "learning_rate": 4.8693004383711565e-06,
      "loss": 0.4782,
      "step": 43752
    },
    {
      "epoch": 1.34405431143059,
      "grad_norm": 0.39488881826400757,
      "learning_rate": 4.868885624810111e-06,
      "loss": 0.4679,
      "step": 43753
    },
    {
      "epoch": 1.3440850305655392,
      "grad_norm": 0.40052154660224915,
      "learning_rate": 4.868470823233146e-06,
      "loss": 0.4858,
      "step": 43754
    },
    {
      "epoch": 1.3441157497004883,
      "grad_norm": 0.43019384145736694,
      "learning_rate": 4.868056033641222e-06,
      "loss": 0.4705,
      "step": 43755
    },
    {
      "epoch": 1.3441464688354376,
      "grad_norm": 0.40588510036468506,
      "learning_rate": 4.8676412560353115e-06,
      "loss": 0.4695,
      "step": 43756
    },
    {
      "epoch": 1.3441771879703868,
      "grad_norm": 0.40123382210731506,
      "learning_rate": 4.867226490416383e-06,
      "loss": 0.5342,
      "step": 43757
    },
    {
      "epoch": 1.3442079071053359,
      "grad_norm": 0.5417523384094238,
      "learning_rate": 4.866811736785405e-06,
      "loss": 0.4013,
      "step": 43758
    },
    {
      "epoch": 1.344238626240285,
      "grad_norm": 0.4196980893611908,
      "learning_rate": 4.866396995143352e-06,
      "loss": 0.4104,
      "step": 43759
    },
    {
      "epoch": 1.3442693453752343,
      "grad_norm": 0.435055136680603,
      "learning_rate": 4.8659822654911826e-06,
      "loss": 0.503,
      "step": 43760
    },
    {
      "epoch": 1.3443000645101835,
      "grad_norm": 0.48653194308280945,
      "learning_rate": 4.86556754782987e-06,
      "loss": 0.4271,
      "step": 43761
    },
    {
      "epoch": 1.3443307836451326,
      "grad_norm": 0.4259450137615204,
      "learning_rate": 4.865152842160383e-06,
      "loss": 0.4309,
      "step": 43762
    },
    {
      "epoch": 1.3443615027800817,
      "grad_norm": 0.4099179208278656,
      "learning_rate": 4.864738148483694e-06,
      "loss": 0.4398,
      "step": 43763
    },
    {
      "epoch": 1.3443922219150308,
      "grad_norm": 0.4156281352043152,
      "learning_rate": 4.864323466800764e-06,
      "loss": 0.4358,
      "step": 43764
    },
    {
      "epoch": 1.34442294104998,
      "grad_norm": 0.4116431176662445,
      "learning_rate": 4.86390879711257e-06,
      "loss": 0.4479,
      "step": 43765
    },
    {
      "epoch": 1.344453660184929,
      "grad_norm": 0.4111001193523407,
      "learning_rate": 4.863494139420067e-06,
      "loss": 0.3957,
      "step": 43766
    },
    {
      "epoch": 1.3444843793198784,
      "grad_norm": 0.42568323016166687,
      "learning_rate": 4.8630794937242395e-06,
      "loss": 0.4458,
      "step": 43767
    },
    {
      "epoch": 1.3445150984548275,
      "grad_norm": 0.4140576720237732,
      "learning_rate": 4.8626648600260455e-06,
      "loss": 0.4972,
      "step": 43768
    },
    {
      "epoch": 1.3445458175897766,
      "grad_norm": 0.44385412335395813,
      "learning_rate": 4.86225023832646e-06,
      "loss": 0.4544,
      "step": 43769
    },
    {
      "epoch": 1.3445765367247258,
      "grad_norm": 0.462517648935318,
      "learning_rate": 4.861835628626444e-06,
      "loss": 0.6257,
      "step": 43770
    },
    {
      "epoch": 1.344607255859675,
      "grad_norm": 0.41491204500198364,
      "learning_rate": 4.861421030926969e-06,
      "loss": 0.4489,
      "step": 43771
    },
    {
      "epoch": 1.3446379749946242,
      "grad_norm": 0.43390876054763794,
      "learning_rate": 4.8610064452290065e-06,
      "loss": 0.4928,
      "step": 43772
    },
    {
      "epoch": 1.3446686941295733,
      "grad_norm": 0.43541398644447327,
      "learning_rate": 4.86059187153352e-06,
      "loss": 0.5569,
      "step": 43773
    },
    {
      "epoch": 1.3446994132645225,
      "grad_norm": 0.40762433409690857,
      "learning_rate": 4.860177309841485e-06,
      "loss": 0.4742,
      "step": 43774
    },
    {
      "epoch": 1.3447301323994716,
      "grad_norm": 0.5295177698135376,
      "learning_rate": 4.859762760153861e-06,
      "loss": 0.4396,
      "step": 43775
    },
    {
      "epoch": 1.3447608515344207,
      "grad_norm": 0.39638930559158325,
      "learning_rate": 4.8593482224716195e-06,
      "loss": 0.4874,
      "step": 43776
    },
    {
      "epoch": 1.3447915706693698,
      "grad_norm": 0.6222134828567505,
      "learning_rate": 4.858933696795729e-06,
      "loss": 0.4802,
      "step": 43777
    },
    {
      "epoch": 1.3448222898043192,
      "grad_norm": 0.4147530794143677,
      "learning_rate": 4.8585191831271625e-06,
      "loss": 0.5227,
      "step": 43778
    },
    {
      "epoch": 1.3448530089392683,
      "grad_norm": 0.41693833470344543,
      "learning_rate": 4.85810468146688e-06,
      "loss": 0.5166,
      "step": 43779
    },
    {
      "epoch": 1.3448837280742174,
      "grad_norm": 0.39841794967651367,
      "learning_rate": 4.857690191815853e-06,
      "loss": 0.4935,
      "step": 43780
    },
    {
      "epoch": 1.3449144472091665,
      "grad_norm": 0.4189920723438263,
      "learning_rate": 4.8572757141750485e-06,
      "loss": 0.5178,
      "step": 43781
    },
    {
      "epoch": 1.3449451663441159,
      "grad_norm": 0.5164760947227478,
      "learning_rate": 4.85686124854544e-06,
      "loss": 0.5294,
      "step": 43782
    },
    {
      "epoch": 1.344975885479065,
      "grad_norm": 0.40638864040374756,
      "learning_rate": 4.856446794927988e-06,
      "loss": 0.447,
      "step": 43783
    },
    {
      "epoch": 1.3450066046140141,
      "grad_norm": 0.4344690442085266,
      "learning_rate": 4.8560323533236645e-06,
      "loss": 0.4911,
      "step": 43784
    },
    {
      "epoch": 1.3450373237489632,
      "grad_norm": 0.45743343234062195,
      "learning_rate": 4.8556179237334344e-06,
      "loss": 0.4791,
      "step": 43785
    },
    {
      "epoch": 1.3450680428839124,
      "grad_norm": 0.46607327461242676,
      "learning_rate": 4.8552035061582735e-06,
      "loss": 0.4365,
      "step": 43786
    },
    {
      "epoch": 1.3450987620188615,
      "grad_norm": 0.38813766837120056,
      "learning_rate": 4.85478910059914e-06,
      "loss": 0.4652,
      "step": 43787
    },
    {
      "epoch": 1.3451294811538106,
      "grad_norm": 0.41676175594329834,
      "learning_rate": 4.854374707057006e-06,
      "loss": 0.4663,
      "step": 43788
    },
    {
      "epoch": 1.34516020028876,
      "grad_norm": 0.3907477557659149,
      "learning_rate": 4.853960325532838e-06,
      "loss": 0.4837,
      "step": 43789
    },
    {
      "epoch": 1.345190919423709,
      "grad_norm": 0.43182069063186646,
      "learning_rate": 4.8535459560276095e-06,
      "loss": 0.4142,
      "step": 43790
    },
    {
      "epoch": 1.3452216385586582,
      "grad_norm": 0.4130868911743164,
      "learning_rate": 4.853131598542281e-06,
      "loss": 0.4752,
      "step": 43791
    },
    {
      "epoch": 1.3452523576936073,
      "grad_norm": 0.42101848125457764,
      "learning_rate": 4.852717253077822e-06,
      "loss": 0.4825,
      "step": 43792
    },
    {
      "epoch": 1.3452830768285566,
      "grad_norm": 0.5931569933891296,
      "learning_rate": 4.852302919635202e-06,
      "loss": 0.4899,
      "step": 43793
    },
    {
      "epoch": 1.3453137959635058,
      "grad_norm": 0.40630042552948,
      "learning_rate": 4.851888598215388e-06,
      "loss": 0.4138,
      "step": 43794
    },
    {
      "epoch": 1.3453445150984549,
      "grad_norm": 0.4189973771572113,
      "learning_rate": 4.851474288819352e-06,
      "loss": 0.4528,
      "step": 43795
    },
    {
      "epoch": 1.345375234233404,
      "grad_norm": 0.4062246084213257,
      "learning_rate": 4.851059991448053e-06,
      "loss": 0.4375,
      "step": 43796
    },
    {
      "epoch": 1.3454059533683531,
      "grad_norm": 0.40276145935058594,
      "learning_rate": 4.850645706102466e-06,
      "loss": 0.4904,
      "step": 43797
    },
    {
      "epoch": 1.3454366725033022,
      "grad_norm": 0.4586239159107208,
      "learning_rate": 4.850231432783549e-06,
      "loss": 0.4376,
      "step": 43798
    },
    {
      "epoch": 1.3454673916382514,
      "grad_norm": 0.40533387660980225,
      "learning_rate": 4.849817171492284e-06,
      "loss": 0.5502,
      "step": 43799
    },
    {
      "epoch": 1.3454981107732007,
      "grad_norm": 0.4413139522075653,
      "learning_rate": 4.8494029222296255e-06,
      "loss": 0.4662,
      "step": 43800
    },
    {
      "epoch": 1.3455288299081498,
      "grad_norm": 0.39190420508384705,
      "learning_rate": 4.848988684996551e-06,
      "loss": 0.4569,
      "step": 43801
    },
    {
      "epoch": 1.345559549043099,
      "grad_norm": 0.367670476436615,
      "learning_rate": 4.848574459794016e-06,
      "loss": 0.471,
      "step": 43802
    },
    {
      "epoch": 1.345590268178048,
      "grad_norm": 0.4012337923049927,
      "learning_rate": 4.848160246623002e-06,
      "loss": 0.4663,
      "step": 43803
    },
    {
      "epoch": 1.3456209873129974,
      "grad_norm": 0.4381222724914551,
      "learning_rate": 4.847746045484466e-06,
      "loss": 0.5714,
      "step": 43804
    },
    {
      "epoch": 1.3456517064479465,
      "grad_norm": 0.41460156440734863,
      "learning_rate": 4.847331856379382e-06,
      "loss": 0.5134,
      "step": 43805
    },
    {
      "epoch": 1.3456824255828956,
      "grad_norm": 0.40407049655914307,
      "learning_rate": 4.846917679308712e-06,
      "loss": 0.4614,
      "step": 43806
    },
    {
      "epoch": 1.3457131447178448,
      "grad_norm": 0.4162014424800873,
      "learning_rate": 4.846503514273424e-06,
      "loss": 0.4412,
      "step": 43807
    },
    {
      "epoch": 1.3457438638527939,
      "grad_norm": 0.4205537438392639,
      "learning_rate": 4.846089361274488e-06,
      "loss": 0.4374,
      "step": 43808
    },
    {
      "epoch": 1.345774582987743,
      "grad_norm": 0.4017959535121918,
      "learning_rate": 4.845675220312873e-06,
      "loss": 0.4948,
      "step": 43809
    },
    {
      "epoch": 1.3458053021226921,
      "grad_norm": 0.39830315113067627,
      "learning_rate": 4.845261091389541e-06,
      "loss": 0.4884,
      "step": 43810
    },
    {
      "epoch": 1.3458360212576415,
      "grad_norm": 0.4451398253440857,
      "learning_rate": 4.84484697450546e-06,
      "loss": 0.4418,
      "step": 43811
    },
    {
      "epoch": 1.3458667403925906,
      "grad_norm": 0.45989060401916504,
      "learning_rate": 4.844432869661602e-06,
      "loss": 0.4828,
      "step": 43812
    },
    {
      "epoch": 1.3458974595275397,
      "grad_norm": 0.39539605379104614,
      "learning_rate": 4.844018776858929e-06,
      "loss": 0.4326,
      "step": 43813
    },
    {
      "epoch": 1.3459281786624888,
      "grad_norm": 0.40152135491371155,
      "learning_rate": 4.843604696098414e-06,
      "loss": 0.4793,
      "step": 43814
    },
    {
      "epoch": 1.3459588977974382,
      "grad_norm": 0.3857031762599945,
      "learning_rate": 4.843190627381016e-06,
      "loss": 0.4777,
      "step": 43815
    },
    {
      "epoch": 1.3459896169323873,
      "grad_norm": 0.4530280828475952,
      "learning_rate": 4.842776570707708e-06,
      "loss": 0.4539,
      "step": 43816
    },
    {
      "epoch": 1.3460203360673364,
      "grad_norm": 0.3802741765975952,
      "learning_rate": 4.842362526079454e-06,
      "loss": 0.4577,
      "step": 43817
    },
    {
      "epoch": 1.3460510552022855,
      "grad_norm": 0.424140065908432,
      "learning_rate": 4.841948493497227e-06,
      "loss": 0.446,
      "step": 43818
    },
    {
      "epoch": 1.3460817743372346,
      "grad_norm": 0.4383156895637512,
      "learning_rate": 4.841534472961986e-06,
      "loss": 0.4036,
      "step": 43819
    },
    {
      "epoch": 1.3461124934721838,
      "grad_norm": 0.4161021113395691,
      "learning_rate": 4.841120464474701e-06,
      "loss": 0.4308,
      "step": 43820
    },
    {
      "epoch": 1.3461432126071329,
      "grad_norm": 0.439544141292572,
      "learning_rate": 4.8407064680363405e-06,
      "loss": 0.5571,
      "step": 43821
    },
    {
      "epoch": 1.3461739317420822,
      "grad_norm": 0.4382166862487793,
      "learning_rate": 4.840292483647873e-06,
      "loss": 0.4228,
      "step": 43822
    },
    {
      "epoch": 1.3462046508770313,
      "grad_norm": 0.411144495010376,
      "learning_rate": 4.8398785113102585e-06,
      "loss": 0.4336,
      "step": 43823
    },
    {
      "epoch": 1.3462353700119805,
      "grad_norm": 0.4507235288619995,
      "learning_rate": 4.83946455102447e-06,
      "loss": 0.4512,
      "step": 43824
    },
    {
      "epoch": 1.3462660891469296,
      "grad_norm": 0.42014366388320923,
      "learning_rate": 4.839050602791471e-06,
      "loss": 0.5411,
      "step": 43825
    },
    {
      "epoch": 1.346296808281879,
      "grad_norm": 0.4385756254196167,
      "learning_rate": 4.838636666612234e-06,
      "loss": 0.4546,
      "step": 43826
    },
    {
      "epoch": 1.346327527416828,
      "grad_norm": 0.40417805314064026,
      "learning_rate": 4.838222742487717e-06,
      "loss": 0.4403,
      "step": 43827
    },
    {
      "epoch": 1.3463582465517772,
      "grad_norm": 0.41854947805404663,
      "learning_rate": 4.837808830418893e-06,
      "loss": 0.4911,
      "step": 43828
    },
    {
      "epoch": 1.3463889656867263,
      "grad_norm": 0.42827972769737244,
      "learning_rate": 4.837394930406725e-06,
      "loss": 0.3965,
      "step": 43829
    },
    {
      "epoch": 1.3464196848216754,
      "grad_norm": 0.4417019486427307,
      "learning_rate": 4.8369810424521835e-06,
      "loss": 0.5001,
      "step": 43830
    },
    {
      "epoch": 1.3464504039566245,
      "grad_norm": 0.42515829205513,
      "learning_rate": 4.8365671665562365e-06,
      "loss": 0.5214,
      "step": 43831
    },
    {
      "epoch": 1.3464811230915736,
      "grad_norm": 0.5033441781997681,
      "learning_rate": 4.836153302719842e-06,
      "loss": 0.4401,
      "step": 43832
    },
    {
      "epoch": 1.346511842226523,
      "grad_norm": 0.47676005959510803,
      "learning_rate": 4.835739450943978e-06,
      "loss": 0.3971,
      "step": 43833
    },
    {
      "epoch": 1.346542561361472,
      "grad_norm": 0.4149697721004486,
      "learning_rate": 4.8353256112295975e-06,
      "loss": 0.5136,
      "step": 43834
    },
    {
      "epoch": 1.3465732804964212,
      "grad_norm": 0.4249381422996521,
      "learning_rate": 4.834911783577682e-06,
      "loss": 0.3995,
      "step": 43835
    },
    {
      "epoch": 1.3466039996313703,
      "grad_norm": 0.46598517894744873,
      "learning_rate": 4.834497967989187e-06,
      "loss": 0.4634,
      "step": 43836
    },
    {
      "epoch": 1.3466347187663195,
      "grad_norm": 0.9314191341400146,
      "learning_rate": 4.834084164465086e-06,
      "loss": 0.4951,
      "step": 43837
    },
    {
      "epoch": 1.3466654379012688,
      "grad_norm": 0.379186749458313,
      "learning_rate": 4.833670373006338e-06,
      "loss": 0.5236,
      "step": 43838
    },
    {
      "epoch": 1.346696157036218,
      "grad_norm": 0.41176339983940125,
      "learning_rate": 4.8332565936139154e-06,
      "loss": 0.4641,
      "step": 43839
    },
    {
      "epoch": 1.346726876171167,
      "grad_norm": 0.39089083671569824,
      "learning_rate": 4.832842826288781e-06,
      "loss": 0.4801,
      "step": 43840
    },
    {
      "epoch": 1.3467575953061162,
      "grad_norm": 0.3911690413951874,
      "learning_rate": 4.8324290710319075e-06,
      "loss": 0.524,
      "step": 43841
    },
    {
      "epoch": 1.3467883144410653,
      "grad_norm": 0.42243045568466187,
      "learning_rate": 4.832015327844254e-06,
      "loss": 0.4447,
      "step": 43842
    },
    {
      "epoch": 1.3468190335760144,
      "grad_norm": 0.42816436290740967,
      "learning_rate": 4.831601596726788e-06,
      "loss": 0.5354,
      "step": 43843
    },
    {
      "epoch": 1.3468497527109635,
      "grad_norm": 0.4103539288043976,
      "learning_rate": 4.831187877680479e-06,
      "loss": 0.4095,
      "step": 43844
    },
    {
      "epoch": 1.3468804718459129,
      "grad_norm": 0.41885828971862793,
      "learning_rate": 4.830774170706295e-06,
      "loss": 0.4166,
      "step": 43845
    },
    {
      "epoch": 1.346911190980862,
      "grad_norm": 0.453262597322464,
      "learning_rate": 4.830360475805195e-06,
      "loss": 0.4402,
      "step": 43846
    },
    {
      "epoch": 1.346941910115811,
      "grad_norm": 0.42257779836654663,
      "learning_rate": 4.829946792978148e-06,
      "loss": 0.5097,
      "step": 43847
    },
    {
      "epoch": 1.3469726292507602,
      "grad_norm": 0.45291149616241455,
      "learning_rate": 4.829533122226124e-06,
      "loss": 0.4779,
      "step": 43848
    },
    {
      "epoch": 1.3470033483857096,
      "grad_norm": 0.4008220434188843,
      "learning_rate": 4.8291194635500836e-06,
      "loss": 0.4764,
      "step": 43849
    },
    {
      "epoch": 1.3470340675206587,
      "grad_norm": 0.39459285140037537,
      "learning_rate": 4.828705816951001e-06,
      "loss": 0.4306,
      "step": 43850
    },
    {
      "epoch": 1.3470647866556078,
      "grad_norm": 0.4008415937423706,
      "learning_rate": 4.8282921824298335e-06,
      "loss": 0.4118,
      "step": 43851
    },
    {
      "epoch": 1.347095505790557,
      "grad_norm": 0.44642120599746704,
      "learning_rate": 4.82787855998755e-06,
      "loss": 0.4813,
      "step": 43852
    },
    {
      "epoch": 1.347126224925506,
      "grad_norm": 0.44326725602149963,
      "learning_rate": 4.827464949625118e-06,
      "loss": 0.4727,
      "step": 43853
    },
    {
      "epoch": 1.3471569440604552,
      "grad_norm": 0.4138942062854767,
      "learning_rate": 4.827051351343507e-06,
      "loss": 0.4287,
      "step": 43854
    },
    {
      "epoch": 1.3471876631954043,
      "grad_norm": 0.4105168581008911,
      "learning_rate": 4.826637765143675e-06,
      "loss": 0.4986,
      "step": 43855
    },
    {
      "epoch": 1.3472183823303536,
      "grad_norm": 0.4394398033618927,
      "learning_rate": 4.826224191026591e-06,
      "loss": 0.5205,
      "step": 43856
    },
    {
      "epoch": 1.3472491014653027,
      "grad_norm": 0.4060409367084503,
      "learning_rate": 4.825810628993222e-06,
      "loss": 0.4789,
      "step": 43857
    },
    {
      "epoch": 1.3472798206002519,
      "grad_norm": 0.4880579113960266,
      "learning_rate": 4.825397079044537e-06,
      "loss": 0.4443,
      "step": 43858
    },
    {
      "epoch": 1.347310539735201,
      "grad_norm": 0.40402811765670776,
      "learning_rate": 4.824983541181496e-06,
      "loss": 0.5039,
      "step": 43859
    },
    {
      "epoch": 1.3473412588701503,
      "grad_norm": 0.3933820128440857,
      "learning_rate": 4.82457001540507e-06,
      "loss": 0.4739,
      "step": 43860
    },
    {
      "epoch": 1.3473719780050994,
      "grad_norm": 0.41025394201278687,
      "learning_rate": 4.8241565017162155e-06,
      "loss": 0.5036,
      "step": 43861
    },
    {
      "epoch": 1.3474026971400486,
      "grad_norm": 0.45192426443099976,
      "learning_rate": 4.823743000115912e-06,
      "loss": 0.4202,
      "step": 43862
    },
    {
      "epoch": 1.3474334162749977,
      "grad_norm": 0.39649322628974915,
      "learning_rate": 4.823329510605113e-06,
      "loss": 0.524,
      "step": 43863
    },
    {
      "epoch": 1.3474641354099468,
      "grad_norm": 0.39504721760749817,
      "learning_rate": 4.8229160331847955e-06,
      "loss": 0.5222,
      "step": 43864
    },
    {
      "epoch": 1.347494854544896,
      "grad_norm": 0.42593398690223694,
      "learning_rate": 4.822502567855911e-06,
      "loss": 0.4971,
      "step": 43865
    },
    {
      "epoch": 1.347525573679845,
      "grad_norm": 0.4573480486869812,
      "learning_rate": 4.822089114619437e-06,
      "loss": 0.3984,
      "step": 43866
    },
    {
      "epoch": 1.3475562928147944,
      "grad_norm": 0.4119032323360443,
      "learning_rate": 4.821675673476339e-06,
      "loss": 0.4728,
      "step": 43867
    },
    {
      "epoch": 1.3475870119497435,
      "grad_norm": 0.44309917092323303,
      "learning_rate": 4.821262244427576e-06,
      "loss": 0.5051,
      "step": 43868
    },
    {
      "epoch": 1.3476177310846926,
      "grad_norm": 0.3846742510795593,
      "learning_rate": 4.82084882747412e-06,
      "loss": 0.4419,
      "step": 43869
    },
    {
      "epoch": 1.3476484502196417,
      "grad_norm": 0.40129587054252625,
      "learning_rate": 4.820435422616926e-06,
      "loss": 0.4409,
      "step": 43870
    },
    {
      "epoch": 1.347679169354591,
      "grad_norm": 0.4063427746295929,
      "learning_rate": 4.8200220298569735e-06,
      "loss": 0.416,
      "step": 43871
    },
    {
      "epoch": 1.3477098884895402,
      "grad_norm": 0.4182848334312439,
      "learning_rate": 4.819608649195219e-06,
      "loss": 0.4918,
      "step": 43872
    },
    {
      "epoch": 1.3477406076244893,
      "grad_norm": 0.41483935713768005,
      "learning_rate": 4.819195280632632e-06,
      "loss": 0.457,
      "step": 43873
    },
    {
      "epoch": 1.3477713267594384,
      "grad_norm": 0.4097490608692169,
      "learning_rate": 4.818781924170174e-06,
      "loss": 0.4274,
      "step": 43874
    },
    {
      "epoch": 1.3478020458943876,
      "grad_norm": 0.43087127804756165,
      "learning_rate": 4.818368579808813e-06,
      "loss": 0.5149,
      "step": 43875
    },
    {
      "epoch": 1.3478327650293367,
      "grad_norm": 0.3709135949611664,
      "learning_rate": 4.817955247549513e-06,
      "loss": 0.4197,
      "step": 43876
    },
    {
      "epoch": 1.3478634841642858,
      "grad_norm": 0.3604784607887268,
      "learning_rate": 4.8175419273932446e-06,
      "loss": 0.5279,
      "step": 43877
    },
    {
      "epoch": 1.3478942032992351,
      "grad_norm": 0.39767831563949585,
      "learning_rate": 4.817128619340965e-06,
      "loss": 0.4829,
      "step": 43878
    },
    {
      "epoch": 1.3479249224341843,
      "grad_norm": 0.4366331100463867,
      "learning_rate": 4.816715323393644e-06,
      "loss": 0.4864,
      "step": 43879
    },
    {
      "epoch": 1.3479556415691334,
      "grad_norm": 0.4036891460418701,
      "learning_rate": 4.816302039552246e-06,
      "loss": 0.4468,
      "step": 43880
    },
    {
      "epoch": 1.3479863607040825,
      "grad_norm": 0.42427438497543335,
      "learning_rate": 4.81588876781774e-06,
      "loss": 0.4872,
      "step": 43881
    },
    {
      "epoch": 1.3480170798390319,
      "grad_norm": 0.40528732538223267,
      "learning_rate": 4.815475508191085e-06,
      "loss": 0.5096,
      "step": 43882
    },
    {
      "epoch": 1.348047798973981,
      "grad_norm": 0.4311515688896179,
      "learning_rate": 4.815062260673249e-06,
      "loss": 0.4211,
      "step": 43883
    },
    {
      "epoch": 1.34807851810893,
      "grad_norm": 0.4775606393814087,
      "learning_rate": 4.814649025265197e-06,
      "loss": 0.4146,
      "step": 43884
    },
    {
      "epoch": 1.3481092372438792,
      "grad_norm": 0.4100726544857025,
      "learning_rate": 4.814235801967894e-06,
      "loss": 0.4218,
      "step": 43885
    },
    {
      "epoch": 1.3481399563788283,
      "grad_norm": 0.3966215252876282,
      "learning_rate": 4.813822590782309e-06,
      "loss": 0.4566,
      "step": 43886
    },
    {
      "epoch": 1.3481706755137775,
      "grad_norm": 0.4347645044326782,
      "learning_rate": 4.8134093917094005e-06,
      "loss": 0.4654,
      "step": 43887
    },
    {
      "epoch": 1.3482013946487266,
      "grad_norm": 0.46752896904945374,
      "learning_rate": 4.8129962047501355e-06,
      "loss": 0.4871,
      "step": 43888
    },
    {
      "epoch": 1.348232113783676,
      "grad_norm": 0.4904553294181824,
      "learning_rate": 4.812583029905481e-06,
      "loss": 0.4537,
      "step": 43889
    },
    {
      "epoch": 1.348262832918625,
      "grad_norm": 0.4628993570804596,
      "learning_rate": 4.812169867176405e-06,
      "loss": 0.4478,
      "step": 43890
    },
    {
      "epoch": 1.3482935520535742,
      "grad_norm": 0.4478393793106079,
      "learning_rate": 4.811756716563864e-06,
      "loss": 0.3863,
      "step": 43891
    },
    {
      "epoch": 1.3483242711885233,
      "grad_norm": 0.45389676094055176,
      "learning_rate": 4.811343578068828e-06,
      "loss": 0.4535,
      "step": 43892
    },
    {
      "epoch": 1.3483549903234726,
      "grad_norm": 0.39622488617897034,
      "learning_rate": 4.810930451692262e-06,
      "loss": 0.4481,
      "step": 43893
    },
    {
      "epoch": 1.3483857094584217,
      "grad_norm": 0.42351648211479187,
      "learning_rate": 4.810517337435133e-06,
      "loss": 0.5099,
      "step": 43894
    },
    {
      "epoch": 1.3484164285933709,
      "grad_norm": 0.3974570333957672,
      "learning_rate": 4.8101042352984005e-06,
      "loss": 0.4818,
      "step": 43895
    },
    {
      "epoch": 1.34844714772832,
      "grad_norm": 0.41192826628685,
      "learning_rate": 4.8096911452830355e-06,
      "loss": 0.4997,
      "step": 43896
    },
    {
      "epoch": 1.348477866863269,
      "grad_norm": 0.4350951313972473,
      "learning_rate": 4.809278067389991e-06,
      "loss": 0.5184,
      "step": 43897
    },
    {
      "epoch": 1.3485085859982182,
      "grad_norm": 0.41365906596183777,
      "learning_rate": 4.8088650016202486e-06,
      "loss": 0.4224,
      "step": 43898
    },
    {
      "epoch": 1.3485393051331673,
      "grad_norm": 0.415610671043396,
      "learning_rate": 4.8084519479747605e-06,
      "loss": 0.513,
      "step": 43899
    },
    {
      "epoch": 1.3485700242681167,
      "grad_norm": 0.4696240723133087,
      "learning_rate": 4.808038906454498e-06,
      "loss": 0.4824,
      "step": 43900
    },
    {
      "epoch": 1.3486007434030658,
      "grad_norm": 0.41732823848724365,
      "learning_rate": 4.8076258770604215e-06,
      "loss": 0.498,
      "step": 43901
    },
    {
      "epoch": 1.348631462538015,
      "grad_norm": 0.38635534048080444,
      "learning_rate": 4.807212859793493e-06,
      "loss": 0.4971,
      "step": 43902
    },
    {
      "epoch": 1.348662181672964,
      "grad_norm": 0.5647153258323669,
      "learning_rate": 4.806799854654688e-06,
      "loss": 0.4481,
      "step": 43903
    },
    {
      "epoch": 1.3486929008079134,
      "grad_norm": 0.415486603975296,
      "learning_rate": 4.806386861644961e-06,
      "loss": 0.4471,
      "step": 43904
    },
    {
      "epoch": 1.3487236199428625,
      "grad_norm": 0.4330923557281494,
      "learning_rate": 4.805973880765285e-06,
      "loss": 0.4728,
      "step": 43905
    },
    {
      "epoch": 1.3487543390778116,
      "grad_norm": 0.40806713700294495,
      "learning_rate": 4.805560912016613e-06,
      "loss": 0.4968,
      "step": 43906
    },
    {
      "epoch": 1.3487850582127607,
      "grad_norm": 0.4145087003707886,
      "learning_rate": 4.805147955399921e-06,
      "loss": 0.4631,
      "step": 43907
    },
    {
      "epoch": 1.3488157773477099,
      "grad_norm": 0.41000133752822876,
      "learning_rate": 4.8047350109161674e-06,
      "loss": 0.4592,
      "step": 43908
    },
    {
      "epoch": 1.348846496482659,
      "grad_norm": 0.40605786442756653,
      "learning_rate": 4.804322078566322e-06,
      "loss": 0.5095,
      "step": 43909
    },
    {
      "epoch": 1.348877215617608,
      "grad_norm": 0.3746846914291382,
      "learning_rate": 4.803909158351339e-06,
      "loss": 0.4418,
      "step": 43910
    },
    {
      "epoch": 1.3489079347525574,
      "grad_norm": 0.4071759581565857,
      "learning_rate": 4.80349625027219e-06,
      "loss": 0.5068,
      "step": 43911
    },
    {
      "epoch": 1.3489386538875066,
      "grad_norm": 0.41521263122558594,
      "learning_rate": 4.803083354329839e-06,
      "loss": 0.4087,
      "step": 43912
    },
    {
      "epoch": 1.3489693730224557,
      "grad_norm": 0.4012562334537506,
      "learning_rate": 4.802670470525255e-06,
      "loss": 0.4914,
      "step": 43913
    },
    {
      "epoch": 1.3490000921574048,
      "grad_norm": 0.44212570786476135,
      "learning_rate": 4.8022575988593915e-06,
      "loss": 0.5433,
      "step": 43914
    },
    {
      "epoch": 1.3490308112923541,
      "grad_norm": 0.4406464993953705,
      "learning_rate": 4.801844739333218e-06,
      "loss": 0.5349,
      "step": 43915
    },
    {
      "epoch": 1.3490615304273033,
      "grad_norm": 0.4447138011455536,
      "learning_rate": 4.8014318919476995e-06,
      "loss": 0.4453,
      "step": 43916
    },
    {
      "epoch": 1.3490922495622524,
      "grad_norm": 0.4366045296192169,
      "learning_rate": 4.801019056703805e-06,
      "loss": 0.4719,
      "step": 43917
    },
    {
      "epoch": 1.3491229686972015,
      "grad_norm": 0.3882962763309479,
      "learning_rate": 4.800606233602488e-06,
      "loss": 0.3816,
      "step": 43918
    },
    {
      "epoch": 1.3491536878321506,
      "grad_norm": 0.43917179107666016,
      "learning_rate": 4.8001934226447186e-06,
      "loss": 0.5099,
      "step": 43919
    },
    {
      "epoch": 1.3491844069670997,
      "grad_norm": 0.4329512119293213,
      "learning_rate": 4.799780623831462e-06,
      "loss": 0.4961,
      "step": 43920
    },
    {
      "epoch": 1.3492151261020489,
      "grad_norm": 0.394903302192688,
      "learning_rate": 4.79936783716368e-06,
      "loss": 0.4687,
      "step": 43921
    },
    {
      "epoch": 1.3492458452369982,
      "grad_norm": 0.4115787446498871,
      "learning_rate": 4.798955062642341e-06,
      "loss": 0.4731,
      "step": 43922
    },
    {
      "epoch": 1.3492765643719473,
      "grad_norm": 0.4554087519645691,
      "learning_rate": 4.798542300268403e-06,
      "loss": 0.5418,
      "step": 43923
    },
    {
      "epoch": 1.3493072835068964,
      "grad_norm": 0.4238317012786865,
      "learning_rate": 4.798129550042832e-06,
      "loss": 0.4761,
      "step": 43924
    },
    {
      "epoch": 1.3493380026418456,
      "grad_norm": 0.3909189701080322,
      "learning_rate": 4.7977168119665916e-06,
      "loss": 0.5426,
      "step": 43925
    },
    {
      "epoch": 1.349368721776795,
      "grad_norm": 0.3982766568660736,
      "learning_rate": 4.797304086040653e-06,
      "loss": 0.4435,
      "step": 43926
    },
    {
      "epoch": 1.349399440911744,
      "grad_norm": 0.42866069078445435,
      "learning_rate": 4.7968913722659686e-06,
      "loss": 0.5648,
      "step": 43927
    },
    {
      "epoch": 1.3494301600466931,
      "grad_norm": 0.4169137477874756,
      "learning_rate": 4.796478670643508e-06,
      "loss": 0.3952,
      "step": 43928
    },
    {
      "epoch": 1.3494608791816423,
      "grad_norm": 0.4234795868396759,
      "learning_rate": 4.7960659811742345e-06,
      "loss": 0.5197,
      "step": 43929
    },
    {
      "epoch": 1.3494915983165914,
      "grad_norm": 0.4068158268928528,
      "learning_rate": 4.795653303859118e-06,
      "loss": 0.4948,
      "step": 43930
    },
    {
      "epoch": 1.3495223174515405,
      "grad_norm": 0.4310293197631836,
      "learning_rate": 4.795240638699111e-06,
      "loss": 0.4423,
      "step": 43931
    },
    {
      "epoch": 1.3495530365864896,
      "grad_norm": 0.41746678948402405,
      "learning_rate": 4.7948279856951875e-06,
      "loss": 0.5105,
      "step": 43932
    },
    {
      "epoch": 1.349583755721439,
      "grad_norm": 0.421560138463974,
      "learning_rate": 4.7944153448483e-06,
      "loss": 0.4307,
      "step": 43933
    },
    {
      "epoch": 1.349614474856388,
      "grad_norm": 0.42909979820251465,
      "learning_rate": 4.794002716159425e-06,
      "loss": 0.4168,
      "step": 43934
    },
    {
      "epoch": 1.3496451939913372,
      "grad_norm": 0.4204750061035156,
      "learning_rate": 4.793590099629517e-06,
      "loss": 0.5051,
      "step": 43935
    },
    {
      "epoch": 1.3496759131262863,
      "grad_norm": 0.4278346598148346,
      "learning_rate": 4.793177495259548e-06,
      "loss": 0.5385,
      "step": 43936
    },
    {
      "epoch": 1.3497066322612357,
      "grad_norm": 0.38039764761924744,
      "learning_rate": 4.792764903050471e-06,
      "loss": 0.3831,
      "step": 43937
    },
    {
      "epoch": 1.3497373513961848,
      "grad_norm": 0.48042428493499756,
      "learning_rate": 4.792352323003252e-06,
      "loss": 0.4288,
      "step": 43938
    },
    {
      "epoch": 1.349768070531134,
      "grad_norm": 0.3946363925933838,
      "learning_rate": 4.791939755118866e-06,
      "loss": 0.4018,
      "step": 43939
    },
    {
      "epoch": 1.349798789666083,
      "grad_norm": 0.39774835109710693,
      "learning_rate": 4.791527199398264e-06,
      "loss": 0.4413,
      "step": 43940
    },
    {
      "epoch": 1.3498295088010321,
      "grad_norm": 0.4163127839565277,
      "learning_rate": 4.791114655842418e-06,
      "loss": 0.4345,
      "step": 43941
    },
    {
      "epoch": 1.3498602279359813,
      "grad_norm": 0.4130222499370575,
      "learning_rate": 4.790702124452284e-06,
      "loss": 0.4222,
      "step": 43942
    },
    {
      "epoch": 1.3498909470709304,
      "grad_norm": 0.4204566478729248,
      "learning_rate": 4.7902896052288285e-06,
      "loss": 0.5223,
      "step": 43943
    },
    {
      "epoch": 1.3499216662058797,
      "grad_norm": 0.4174363911151886,
      "learning_rate": 4.789877098173016e-06,
      "loss": 0.4994,
      "step": 43944
    },
    {
      "epoch": 1.3499523853408288,
      "grad_norm": 0.47760260105133057,
      "learning_rate": 4.789464603285813e-06,
      "loss": 0.4476,
      "step": 43945
    },
    {
      "epoch": 1.349983104475778,
      "grad_norm": 0.3921829164028168,
      "learning_rate": 4.789052120568175e-06,
      "loss": 0.5195,
      "step": 43946
    },
    {
      "epoch": 1.350013823610727,
      "grad_norm": 0.4374617636203766,
      "learning_rate": 4.78863965002107e-06,
      "loss": 0.4668,
      "step": 43947
    },
    {
      "epoch": 1.3500445427456762,
      "grad_norm": 0.4337577819824219,
      "learning_rate": 4.788227191645461e-06,
      "loss": 0.4637,
      "step": 43948
    },
    {
      "epoch": 1.3500752618806255,
      "grad_norm": 0.41197842359542847,
      "learning_rate": 4.787814745442316e-06,
      "loss": 0.5209,
      "step": 43949
    },
    {
      "epoch": 1.3501059810155747,
      "grad_norm": 0.39529430866241455,
      "learning_rate": 4.787402311412589e-06,
      "loss": 0.5283,
      "step": 43950
    },
    {
      "epoch": 1.3501367001505238,
      "grad_norm": 0.41853973269462585,
      "learning_rate": 4.786989889557249e-06,
      "loss": 0.5609,
      "step": 43951
    },
    {
      "epoch": 1.350167419285473,
      "grad_norm": 0.45473000407218933,
      "learning_rate": 4.786577479877257e-06,
      "loss": 0.4684,
      "step": 43952
    },
    {
      "epoch": 1.350198138420422,
      "grad_norm": 0.5183866024017334,
      "learning_rate": 4.786165082373581e-06,
      "loss": 0.375,
      "step": 43953
    },
    {
      "epoch": 1.3502288575553711,
      "grad_norm": 0.4371848404407501,
      "learning_rate": 4.785752697047178e-06,
      "loss": 0.4758,
      "step": 43954
    },
    {
      "epoch": 1.3502595766903203,
      "grad_norm": 0.46375033259391785,
      "learning_rate": 4.785340323899012e-06,
      "loss": 0.4327,
      "step": 43955
    },
    {
      "epoch": 1.3502902958252696,
      "grad_norm": 0.4583037793636322,
      "learning_rate": 4.784927962930049e-06,
      "loss": 0.4786,
      "step": 43956
    },
    {
      "epoch": 1.3503210149602187,
      "grad_norm": 0.39698782563209534,
      "learning_rate": 4.784515614141252e-06,
      "loss": 0.4359,
      "step": 43957
    },
    {
      "epoch": 1.3503517340951678,
      "grad_norm": 0.402420312166214,
      "learning_rate": 4.784103277533585e-06,
      "loss": 0.4691,
      "step": 43958
    },
    {
      "epoch": 1.350382453230117,
      "grad_norm": 0.42192313075065613,
      "learning_rate": 4.783690953108005e-06,
      "loss": 0.396,
      "step": 43959
    },
    {
      "epoch": 1.3504131723650663,
      "grad_norm": 0.39785489439964294,
      "learning_rate": 4.7832786408654805e-06,
      "loss": 0.4843,
      "step": 43960
    },
    {
      "epoch": 1.3504438915000154,
      "grad_norm": 0.44567400217056274,
      "learning_rate": 4.782866340806973e-06,
      "loss": 0.4885,
      "step": 43961
    },
    {
      "epoch": 1.3504746106349645,
      "grad_norm": 0.42495691776275635,
      "learning_rate": 4.78245405293345e-06,
      "loss": 0.5148,
      "step": 43962
    },
    {
      "epoch": 1.3505053297699137,
      "grad_norm": 0.36665695905685425,
      "learning_rate": 4.7820417772458635e-06,
      "loss": 0.4224,
      "step": 43963
    },
    {
      "epoch": 1.3505360489048628,
      "grad_norm": 0.42653417587280273,
      "learning_rate": 4.78162951374519e-06,
      "loss": 0.4647,
      "step": 43964
    },
    {
      "epoch": 1.350566768039812,
      "grad_norm": 0.38131818175315857,
      "learning_rate": 4.781217262432375e-06,
      "loss": 0.4336,
      "step": 43965
    },
    {
      "epoch": 1.350597487174761,
      "grad_norm": 0.4538137912750244,
      "learning_rate": 4.780805023308401e-06,
      "loss": 0.5082,
      "step": 43966
    },
    {
      "epoch": 1.3506282063097104,
      "grad_norm": 0.396335244178772,
      "learning_rate": 4.7803927963742155e-06,
      "loss": 0.4833,
      "step": 43967
    },
    {
      "epoch": 1.3506589254446595,
      "grad_norm": 0.4334254264831543,
      "learning_rate": 4.779980581630792e-06,
      "loss": 0.5444,
      "step": 43968
    },
    {
      "epoch": 1.3506896445796086,
      "grad_norm": 0.39810869097709656,
      "learning_rate": 4.779568379079081e-06,
      "loss": 0.4508,
      "step": 43969
    },
    {
      "epoch": 1.3507203637145577,
      "grad_norm": 0.4036618173122406,
      "learning_rate": 4.77915618872006e-06,
      "loss": 0.4365,
      "step": 43970
    },
    {
      "epoch": 1.350751082849507,
      "grad_norm": 0.41034987568855286,
      "learning_rate": 4.778744010554681e-06,
      "loss": 0.4259,
      "step": 43971
    },
    {
      "epoch": 1.3507818019844562,
      "grad_norm": 0.4478333294391632,
      "learning_rate": 4.7783318445839135e-06,
      "loss": 0.4544,
      "step": 43972
    },
    {
      "epoch": 1.3508125211194053,
      "grad_norm": 0.39497506618499756,
      "learning_rate": 4.777919690808712e-06,
      "loss": 0.3982,
      "step": 43973
    },
    {
      "epoch": 1.3508432402543544,
      "grad_norm": 0.397847980260849,
      "learning_rate": 4.777507549230041e-06,
      "loss": 0.5153,
      "step": 43974
    },
    {
      "epoch": 1.3508739593893035,
      "grad_norm": 0.3633077144622803,
      "learning_rate": 4.7770954198488735e-06,
      "loss": 0.4736,
      "step": 43975
    },
    {
      "epoch": 1.3509046785242527,
      "grad_norm": 0.415580153465271,
      "learning_rate": 4.776683302666161e-06,
      "loss": 0.4563,
      "step": 43976
    },
    {
      "epoch": 1.3509353976592018,
      "grad_norm": 0.41994771361351013,
      "learning_rate": 4.776271197682873e-06,
      "loss": 0.4799,
      "step": 43977
    },
    {
      "epoch": 1.3509661167941511,
      "grad_norm": 0.4085984528064728,
      "learning_rate": 4.775859104899963e-06,
      "loss": 0.4069,
      "step": 43978
    },
    {
      "epoch": 1.3509968359291002,
      "grad_norm": 0.3963179290294647,
      "learning_rate": 4.7754470243184e-06,
      "loss": 0.4967,
      "step": 43979
    },
    {
      "epoch": 1.3510275550640494,
      "grad_norm": 0.4117206037044525,
      "learning_rate": 4.775034955939146e-06,
      "loss": 0.4728,
      "step": 43980
    },
    {
      "epoch": 1.3510582741989985,
      "grad_norm": 0.4968491792678833,
      "learning_rate": 4.774622899763166e-06,
      "loss": 0.462,
      "step": 43981
    },
    {
      "epoch": 1.3510889933339478,
      "grad_norm": 0.4127025902271271,
      "learning_rate": 4.774210855791416e-06,
      "loss": 0.3666,
      "step": 43982
    },
    {
      "epoch": 1.351119712468897,
      "grad_norm": 0.5100809335708618,
      "learning_rate": 4.77379882402486e-06,
      "loss": 0.471,
      "step": 43983
    },
    {
      "epoch": 1.351150431603846,
      "grad_norm": 0.4021734893321991,
      "learning_rate": 4.773386804464463e-06,
      "loss": 0.4918,
      "step": 43984
    },
    {
      "epoch": 1.3511811507387952,
      "grad_norm": 0.4481639564037323,
      "learning_rate": 4.77297479711119e-06,
      "loss": 0.4567,
      "step": 43985
    },
    {
      "epoch": 1.3512118698737443,
      "grad_norm": 0.42314809560775757,
      "learning_rate": 4.772562801965995e-06,
      "loss": 0.4621,
      "step": 43986
    },
    {
      "epoch": 1.3512425890086934,
      "grad_norm": 0.42515817284584045,
      "learning_rate": 4.772150819029845e-06,
      "loss": 0.4967,
      "step": 43987
    },
    {
      "epoch": 1.3512733081436425,
      "grad_norm": 0.3970731496810913,
      "learning_rate": 4.771738848303702e-06,
      "loss": 0.5169,
      "step": 43988
    },
    {
      "epoch": 1.351304027278592,
      "grad_norm": 0.3963838517665863,
      "learning_rate": 4.771326889788531e-06,
      "loss": 0.4795,
      "step": 43989
    },
    {
      "epoch": 1.351334746413541,
      "grad_norm": 0.4069681465625763,
      "learning_rate": 4.770914943485289e-06,
      "loss": 0.4881,
      "step": 43990
    },
    {
      "epoch": 1.3513654655484901,
      "grad_norm": 0.3584389388561249,
      "learning_rate": 4.770503009394939e-06,
      "loss": 0.4141,
      "step": 43991
    },
    {
      "epoch": 1.3513961846834392,
      "grad_norm": 0.4141634404659271,
      "learning_rate": 4.770091087518445e-06,
      "loss": 0.4278,
      "step": 43992
    },
    {
      "epoch": 1.3514269038183886,
      "grad_norm": 0.4277488887310028,
      "learning_rate": 4.769679177856768e-06,
      "loss": 0.5005,
      "step": 43993
    },
    {
      "epoch": 1.3514576229533377,
      "grad_norm": 0.418099582195282,
      "learning_rate": 4.7692672804108755e-06,
      "loss": 0.4863,
      "step": 43994
    },
    {
      "epoch": 1.3514883420882868,
      "grad_norm": 0.3784821927547455,
      "learning_rate": 4.768855395181719e-06,
      "loss": 0.4504,
      "step": 43995
    },
    {
      "epoch": 1.351519061223236,
      "grad_norm": 0.439080148935318,
      "learning_rate": 4.768443522170269e-06,
      "loss": 0.4716,
      "step": 43996
    },
    {
      "epoch": 1.351549780358185,
      "grad_norm": 0.4207698106765747,
      "learning_rate": 4.768031661377481e-06,
      "loss": 0.5151,
      "step": 43997
    },
    {
      "epoch": 1.3515804994931342,
      "grad_norm": 0.39563989639282227,
      "learning_rate": 4.767619812804327e-06,
      "loss": 0.4942,
      "step": 43998
    },
    {
      "epoch": 1.3516112186280833,
      "grad_norm": 0.4390202760696411,
      "learning_rate": 4.767207976451757e-06,
      "loss": 0.4662,
      "step": 43999
    },
    {
      "epoch": 1.3516419377630327,
      "grad_norm": 0.4160604774951935,
      "learning_rate": 4.766796152320743e-06,
      "loss": 0.5469,
      "step": 44000
    },
    {
      "epoch": 1.3516726568979818,
      "grad_norm": 0.40996482968330383,
      "learning_rate": 4.766384340412233e-06,
      "loss": 0.4758,
      "step": 44001
    },
    {
      "epoch": 1.351703376032931,
      "grad_norm": 0.4312792122364044,
      "learning_rate": 4.765972540727207e-06,
      "loss": 0.4866,
      "step": 44002
    },
    {
      "epoch": 1.35173409516788,
      "grad_norm": 0.4051094949245453,
      "learning_rate": 4.765560753266614e-06,
      "loss": 0.4303,
      "step": 44003
    },
    {
      "epoch": 1.3517648143028294,
      "grad_norm": 0.39120209217071533,
      "learning_rate": 4.765148978031422e-06,
      "loss": 0.4404,
      "step": 44004
    },
    {
      "epoch": 1.3517955334377785,
      "grad_norm": 0.3928777277469635,
      "learning_rate": 4.7647372150225864e-06,
      "loss": 0.4464,
      "step": 44005
    },
    {
      "epoch": 1.3518262525727276,
      "grad_norm": 0.41661542654037476,
      "learning_rate": 4.764325464241074e-06,
      "loss": 0.4802,
      "step": 44006
    },
    {
      "epoch": 1.3518569717076767,
      "grad_norm": 0.4134090840816498,
      "learning_rate": 4.763913725687844e-06,
      "loss": 0.396,
      "step": 44007
    },
    {
      "epoch": 1.3518876908426258,
      "grad_norm": 0.3936910331249237,
      "learning_rate": 4.763501999363863e-06,
      "loss": 0.4696,
      "step": 44008
    },
    {
      "epoch": 1.351918409977575,
      "grad_norm": 0.4221450388431549,
      "learning_rate": 4.763090285270085e-06,
      "loss": 0.5297,
      "step": 44009
    },
    {
      "epoch": 1.351949129112524,
      "grad_norm": 0.3903064429759979,
      "learning_rate": 4.762678583407476e-06,
      "loss": 0.5006,
      "step": 44010
    },
    {
      "epoch": 1.3519798482474734,
      "grad_norm": 0.3716912269592285,
      "learning_rate": 4.762266893776997e-06,
      "loss": 0.4376,
      "step": 44011
    },
    {
      "epoch": 1.3520105673824225,
      "grad_norm": 0.4448827803134918,
      "learning_rate": 4.761855216379608e-06,
      "loss": 0.4866,
      "step": 44012
    },
    {
      "epoch": 1.3520412865173717,
      "grad_norm": 0.4669526517391205,
      "learning_rate": 4.761443551216277e-06,
      "loss": 0.4665,
      "step": 44013
    },
    {
      "epoch": 1.3520720056523208,
      "grad_norm": 0.47213828563690186,
      "learning_rate": 4.761031898287957e-06,
      "loss": 0.4839,
      "step": 44014
    },
    {
      "epoch": 1.3521027247872701,
      "grad_norm": 0.5803978443145752,
      "learning_rate": 4.760620257595613e-06,
      "loss": 0.3687,
      "step": 44015
    },
    {
      "epoch": 1.3521334439222192,
      "grad_norm": 0.4221051335334778,
      "learning_rate": 4.760208629140205e-06,
      "loss": 0.4828,
      "step": 44016
    },
    {
      "epoch": 1.3521641630571684,
      "grad_norm": 0.4610424041748047,
      "learning_rate": 4.7597970129227e-06,
      "loss": 0.4823,
      "step": 44017
    },
    {
      "epoch": 1.3521948821921175,
      "grad_norm": 0.4288696348667145,
      "learning_rate": 4.759385408944051e-06,
      "loss": 0.5502,
      "step": 44018
    },
    {
      "epoch": 1.3522256013270666,
      "grad_norm": 0.4317190945148468,
      "learning_rate": 4.758973817205225e-06,
      "loss": 0.4759,
      "step": 44019
    },
    {
      "epoch": 1.3522563204620157,
      "grad_norm": 0.41204288601875305,
      "learning_rate": 4.758562237707179e-06,
      "loss": 0.4729,
      "step": 44020
    },
    {
      "epoch": 1.3522870395969648,
      "grad_norm": 0.41367241740226746,
      "learning_rate": 4.758150670450883e-06,
      "loss": 0.4721,
      "step": 44021
    },
    {
      "epoch": 1.3523177587319142,
      "grad_norm": 0.3886697590351105,
      "learning_rate": 4.7577391154372874e-06,
      "loss": 0.453,
      "step": 44022
    },
    {
      "epoch": 1.3523484778668633,
      "grad_norm": 0.3836989998817444,
      "learning_rate": 4.7573275726673584e-06,
      "loss": 0.4362,
      "step": 44023
    },
    {
      "epoch": 1.3523791970018124,
      "grad_norm": 0.42666518688201904,
      "learning_rate": 4.756916042142056e-06,
      "loss": 0.5089,
      "step": 44024
    },
    {
      "epoch": 1.3524099161367615,
      "grad_norm": 0.4067015051841736,
      "learning_rate": 4.756504523862349e-06,
      "loss": 0.5314,
      "step": 44025
    },
    {
      "epoch": 1.3524406352717109,
      "grad_norm": 0.3883986175060272,
      "learning_rate": 4.756093017829186e-06,
      "loss": 0.3805,
      "step": 44026
    },
    {
      "epoch": 1.35247135440666,
      "grad_norm": 0.40870898962020874,
      "learning_rate": 4.755681524043537e-06,
      "loss": 0.446,
      "step": 44027
    },
    {
      "epoch": 1.3525020735416091,
      "grad_norm": 0.42576631903648376,
      "learning_rate": 4.755270042506353e-06,
      "loss": 0.5132,
      "step": 44028
    },
    {
      "epoch": 1.3525327926765582,
      "grad_norm": 0.4155128002166748,
      "learning_rate": 4.754858573218607e-06,
      "loss": 0.5017,
      "step": 44029
    },
    {
      "epoch": 1.3525635118115074,
      "grad_norm": 0.3826780915260315,
      "learning_rate": 4.754447116181259e-06,
      "loss": 0.44,
      "step": 44030
    },
    {
      "epoch": 1.3525942309464565,
      "grad_norm": 0.4795592129230499,
      "learning_rate": 4.754035671395262e-06,
      "loss": 0.5049,
      "step": 44031
    },
    {
      "epoch": 1.3526249500814056,
      "grad_norm": 0.41166311502456665,
      "learning_rate": 4.7536242388615805e-06,
      "loss": 0.4913,
      "step": 44032
    },
    {
      "epoch": 1.352655669216355,
      "grad_norm": 0.42839401960372925,
      "learning_rate": 4.753212818581176e-06,
      "loss": 0.4816,
      "step": 44033
    },
    {
      "epoch": 1.352686388351304,
      "grad_norm": 0.3867555856704712,
      "learning_rate": 4.7528014105550135e-06,
      "loss": 0.508,
      "step": 44034
    },
    {
      "epoch": 1.3527171074862532,
      "grad_norm": 0.43393978476524353,
      "learning_rate": 4.752390014784045e-06,
      "loss": 0.5392,
      "step": 44035
    },
    {
      "epoch": 1.3527478266212023,
      "grad_norm": 0.4001891314983368,
      "learning_rate": 4.751978631269242e-06,
      "loss": 0.4794,
      "step": 44036
    },
    {
      "epoch": 1.3527785457561516,
      "grad_norm": 0.44039350748062134,
      "learning_rate": 4.75156726001155e-06,
      "loss": 0.435,
      "step": 44037
    },
    {
      "epoch": 1.3528092648911008,
      "grad_norm": 0.37866464257240295,
      "learning_rate": 4.751155901011947e-06,
      "loss": 0.4401,
      "step": 44038
    },
    {
      "epoch": 1.3528399840260499,
      "grad_norm": 0.4729337692260742,
      "learning_rate": 4.750744554271382e-06,
      "loss": 0.4987,
      "step": 44039
    },
    {
      "epoch": 1.352870703160999,
      "grad_norm": 0.40391433238983154,
      "learning_rate": 4.750333219790825e-06,
      "loss": 0.5334,
      "step": 44040
    },
    {
      "epoch": 1.3529014222959481,
      "grad_norm": 0.40303003787994385,
      "learning_rate": 4.7499218975712265e-06,
      "loss": 0.4306,
      "step": 44041
    },
    {
      "epoch": 1.3529321414308972,
      "grad_norm": 0.5149644613265991,
      "learning_rate": 4.749510587613551e-06,
      "loss": 0.4733,
      "step": 44042
    },
    {
      "epoch": 1.3529628605658464,
      "grad_norm": 0.40535303950309753,
      "learning_rate": 4.7490992899187625e-06,
      "loss": 0.409,
      "step": 44043
    },
    {
      "epoch": 1.3529935797007957,
      "grad_norm": 0.3785632848739624,
      "learning_rate": 4.7486880044878224e-06,
      "loss": 0.5045,
      "step": 44044
    },
    {
      "epoch": 1.3530242988357448,
      "grad_norm": 0.42734020948410034,
      "learning_rate": 4.748276731321684e-06,
      "loss": 0.5131,
      "step": 44045
    },
    {
      "epoch": 1.353055017970694,
      "grad_norm": 0.4336211383342743,
      "learning_rate": 4.747865470421313e-06,
      "loss": 0.4809,
      "step": 44046
    },
    {
      "epoch": 1.353085737105643,
      "grad_norm": 0.4425714313983917,
      "learning_rate": 4.7474542217876675e-06,
      "loss": 0.5083,
      "step": 44047
    },
    {
      "epoch": 1.3531164562405924,
      "grad_norm": 0.5229772329330444,
      "learning_rate": 4.747042985421709e-06,
      "loss": 0.5139,
      "step": 44048
    },
    {
      "epoch": 1.3531471753755415,
      "grad_norm": 0.4146064817905426,
      "learning_rate": 4.746631761324404e-06,
      "loss": 0.4384,
      "step": 44049
    },
    {
      "epoch": 1.3531778945104906,
      "grad_norm": 0.3724532127380371,
      "learning_rate": 4.746220549496703e-06,
      "loss": 0.4491,
      "step": 44050
    },
    {
      "epoch": 1.3532086136454398,
      "grad_norm": 0.6056520342826843,
      "learning_rate": 4.745809349939571e-06,
      "loss": 0.491,
      "step": 44051
    },
    {
      "epoch": 1.3532393327803889,
      "grad_norm": 0.4072052240371704,
      "learning_rate": 4.745398162653968e-06,
      "loss": 0.5127,
      "step": 44052
    },
    {
      "epoch": 1.353270051915338,
      "grad_norm": 0.4073364734649658,
      "learning_rate": 4.744986987640858e-06,
      "loss": 0.5862,
      "step": 44053
    },
    {
      "epoch": 1.3533007710502871,
      "grad_norm": 0.41987571120262146,
      "learning_rate": 4.7445758249011954e-06,
      "loss": 0.4861,
      "step": 44054
    },
    {
      "epoch": 1.3533314901852365,
      "grad_norm": 0.4132019579410553,
      "learning_rate": 4.744164674435941e-06,
      "loss": 0.4702,
      "step": 44055
    },
    {
      "epoch": 1.3533622093201856,
      "grad_norm": 0.4084553122520447,
      "learning_rate": 4.743753536246058e-06,
      "loss": 0.4966,
      "step": 44056
    },
    {
      "epoch": 1.3533929284551347,
      "grad_norm": 0.4229266941547394,
      "learning_rate": 4.743342410332511e-06,
      "loss": 0.4257,
      "step": 44057
    },
    {
      "epoch": 1.3534236475900838,
      "grad_norm": 0.3850112557411194,
      "learning_rate": 4.742931296696249e-06,
      "loss": 0.4979,
      "step": 44058
    },
    {
      "epoch": 1.353454366725033,
      "grad_norm": 0.452124685049057,
      "learning_rate": 4.742520195338239e-06,
      "loss": 0.4963,
      "step": 44059
    },
    {
      "epoch": 1.3534850858599823,
      "grad_norm": 0.3700546622276306,
      "learning_rate": 4.742109106259441e-06,
      "loss": 0.4899,
      "step": 44060
    },
    {
      "epoch": 1.3535158049949314,
      "grad_norm": 0.36979174613952637,
      "learning_rate": 4.7416980294608175e-06,
      "loss": 0.3603,
      "step": 44061
    },
    {
      "epoch": 1.3535465241298805,
      "grad_norm": 0.43322494626045227,
      "learning_rate": 4.7412869649433215e-06,
      "loss": 0.5159,
      "step": 44062
    },
    {
      "epoch": 1.3535772432648296,
      "grad_norm": 0.4033587574958801,
      "learning_rate": 4.740875912707921e-06,
      "loss": 0.4925,
      "step": 44063
    },
    {
      "epoch": 1.3536079623997788,
      "grad_norm": 0.3763294517993927,
      "learning_rate": 4.740464872755564e-06,
      "loss": 0.4302,
      "step": 44064
    },
    {
      "epoch": 1.3536386815347279,
      "grad_norm": 0.4409756362438202,
      "learning_rate": 4.740053845087222e-06,
      "loss": 0.44,
      "step": 44065
    },
    {
      "epoch": 1.353669400669677,
      "grad_norm": 0.4166146218776703,
      "learning_rate": 4.739642829703857e-06,
      "loss": 0.4632,
      "step": 44066
    },
    {
      "epoch": 1.3537001198046263,
      "grad_norm": 0.44403505325317383,
      "learning_rate": 4.739231826606418e-06,
      "loss": 0.5128,
      "step": 44067
    },
    {
      "epoch": 1.3537308389395755,
      "grad_norm": 0.5275384187698364,
      "learning_rate": 4.738820835795872e-06,
      "loss": 0.4081,
      "step": 44068
    },
    {
      "epoch": 1.3537615580745246,
      "grad_norm": 0.41175100207328796,
      "learning_rate": 4.738409857273177e-06,
      "loss": 0.5102,
      "step": 44069
    },
    {
      "epoch": 1.3537922772094737,
      "grad_norm": 0.39775797724723816,
      "learning_rate": 4.737998891039297e-06,
      "loss": 0.4719,
      "step": 44070
    },
    {
      "epoch": 1.353822996344423,
      "grad_norm": 0.46425843238830566,
      "learning_rate": 4.7375879370951836e-06,
      "loss": 0.4703,
      "step": 44071
    },
    {
      "epoch": 1.3538537154793722,
      "grad_norm": 0.43290162086486816,
      "learning_rate": 4.737176995441805e-06,
      "loss": 0.3836,
      "step": 44072
    },
    {
      "epoch": 1.3538844346143213,
      "grad_norm": 0.41679519414901733,
      "learning_rate": 4.73676606608011e-06,
      "loss": 0.489,
      "step": 44073
    },
    {
      "epoch": 1.3539151537492704,
      "grad_norm": 0.4285115599632263,
      "learning_rate": 4.736355149011074e-06,
      "loss": 0.4321,
      "step": 44074
    },
    {
      "epoch": 1.3539458728842195,
      "grad_norm": 3.374389410018921,
      "learning_rate": 4.735944244235643e-06,
      "loss": 0.5409,
      "step": 44075
    },
    {
      "epoch": 1.3539765920191686,
      "grad_norm": 0.4588210880756378,
      "learning_rate": 4.735533351754786e-06,
      "loss": 0.471,
      "step": 44076
    },
    {
      "epoch": 1.3540073111541178,
      "grad_norm": 0.40070921182632446,
      "learning_rate": 4.735122471569454e-06,
      "loss": 0.4437,
      "step": 44077
    },
    {
      "epoch": 1.354038030289067,
      "grad_norm": 0.42597153782844543,
      "learning_rate": 4.734711603680613e-06,
      "loss": 0.4444,
      "step": 44078
    },
    {
      "epoch": 1.3540687494240162,
      "grad_norm": 0.36715734004974365,
      "learning_rate": 4.734300748089219e-06,
      "loss": 0.4998,
      "step": 44079
    },
    {
      "epoch": 1.3540994685589653,
      "grad_norm": 0.4477681517601013,
      "learning_rate": 4.733889904796238e-06,
      "loss": 0.4719,
      "step": 44080
    },
    {
      "epoch": 1.3541301876939145,
      "grad_norm": 0.41606810688972473,
      "learning_rate": 4.733479073802621e-06,
      "loss": 0.48,
      "step": 44081
    },
    {
      "epoch": 1.3541609068288638,
      "grad_norm": 0.4214739501476288,
      "learning_rate": 4.733068255109331e-06,
      "loss": 0.4745,
      "step": 44082
    },
    {
      "epoch": 1.354191625963813,
      "grad_norm": 0.41579684615135193,
      "learning_rate": 4.732657448717328e-06,
      "loss": 0.4409,
      "step": 44083
    },
    {
      "epoch": 1.354222345098762,
      "grad_norm": 0.5102338790893555,
      "learning_rate": 4.732246654627573e-06,
      "loss": 0.4575,
      "step": 44084
    },
    {
      "epoch": 1.3542530642337112,
      "grad_norm": 0.4232728183269501,
      "learning_rate": 4.731835872841025e-06,
      "loss": 0.485,
      "step": 44085
    },
    {
      "epoch": 1.3542837833686603,
      "grad_norm": 0.4023110866546631,
      "learning_rate": 4.73142510335864e-06,
      "loss": 0.4687,
      "step": 44086
    },
    {
      "epoch": 1.3543145025036094,
      "grad_norm": 0.40657278895378113,
      "learning_rate": 4.73101434618138e-06,
      "loss": 0.5454,
      "step": 44087
    },
    {
      "epoch": 1.3543452216385585,
      "grad_norm": 0.3955559730529785,
      "learning_rate": 4.730603601310203e-06,
      "loss": 0.3919,
      "step": 44088
    },
    {
      "epoch": 1.3543759407735079,
      "grad_norm": 0.44881126284599304,
      "learning_rate": 4.7301928687460726e-06,
      "loss": 0.4123,
      "step": 44089
    },
    {
      "epoch": 1.354406659908457,
      "grad_norm": 0.4350722134113312,
      "learning_rate": 4.729782148489942e-06,
      "loss": 0.4986,
      "step": 44090
    },
    {
      "epoch": 1.354437379043406,
      "grad_norm": 0.39582759141921997,
      "learning_rate": 4.729371440542773e-06,
      "loss": 0.5384,
      "step": 44091
    },
    {
      "epoch": 1.3544680981783552,
      "grad_norm": 0.41377606987953186,
      "learning_rate": 4.7289607449055255e-06,
      "loss": 0.4935,
      "step": 44092
    },
    {
      "epoch": 1.3544988173133046,
      "grad_norm": 0.43477192521095276,
      "learning_rate": 4.728550061579162e-06,
      "loss": 0.5068,
      "step": 44093
    },
    {
      "epoch": 1.3545295364482537,
      "grad_norm": 0.44934016466140747,
      "learning_rate": 4.7281393905646335e-06,
      "loss": 0.4046,
      "step": 44094
    },
    {
      "epoch": 1.3545602555832028,
      "grad_norm": 0.4365794062614441,
      "learning_rate": 4.727728731862904e-06,
      "loss": 0.4924,
      "step": 44095
    },
    {
      "epoch": 1.354590974718152,
      "grad_norm": 0.4258069396018982,
      "learning_rate": 4.727318085474932e-06,
      "loss": 0.5326,
      "step": 44096
    },
    {
      "epoch": 1.354621693853101,
      "grad_norm": 0.38053637742996216,
      "learning_rate": 4.726907451401682e-06,
      "loss": 0.4247,
      "step": 44097
    },
    {
      "epoch": 1.3546524129880502,
      "grad_norm": 0.4427938461303711,
      "learning_rate": 4.726496829644103e-06,
      "loss": 0.392,
      "step": 44098
    },
    {
      "epoch": 1.3546831321229993,
      "grad_norm": 0.41793927550315857,
      "learning_rate": 4.726086220203163e-06,
      "loss": 0.4449,
      "step": 44099
    },
    {
      "epoch": 1.3547138512579486,
      "grad_norm": 0.4368247091770172,
      "learning_rate": 4.72567562307981e-06,
      "loss": 0.5129,
      "step": 44100
    },
    {
      "epoch": 1.3547445703928978,
      "grad_norm": 0.39490842819213867,
      "learning_rate": 4.725265038275015e-06,
      "loss": 0.4229,
      "step": 44101
    },
    {
      "epoch": 1.3547752895278469,
      "grad_norm": 0.45063522458076477,
      "learning_rate": 4.724854465789731e-06,
      "loss": 0.5185,
      "step": 44102
    },
    {
      "epoch": 1.354806008662796,
      "grad_norm": 0.4372605085372925,
      "learning_rate": 4.724443905624916e-06,
      "loss": 0.4907,
      "step": 44103
    },
    {
      "epoch": 1.3548367277977453,
      "grad_norm": 0.4142782688140869,
      "learning_rate": 4.724033357781536e-06,
      "loss": 0.5101,
      "step": 44104
    },
    {
      "epoch": 1.3548674469326945,
      "grad_norm": 0.5109009742736816,
      "learning_rate": 4.7236228222605354e-06,
      "loss": 0.4779,
      "step": 44105
    },
    {
      "epoch": 1.3548981660676436,
      "grad_norm": 0.3976670503616333,
      "learning_rate": 4.72321229906289e-06,
      "loss": 0.5776,
      "step": 44106
    },
    {
      "epoch": 1.3549288852025927,
      "grad_norm": 0.5276805758476257,
      "learning_rate": 4.722801788189548e-06,
      "loss": 0.4523,
      "step": 44107
    },
    {
      "epoch": 1.3549596043375418,
      "grad_norm": 0.39038097858428955,
      "learning_rate": 4.722391289641475e-06,
      "loss": 0.4879,
      "step": 44108
    },
    {
      "epoch": 1.354990323472491,
      "grad_norm": 0.459307461977005,
      "learning_rate": 4.7219808034196165e-06,
      "loss": 0.4471,
      "step": 44109
    },
    {
      "epoch": 1.35502104260744,
      "grad_norm": 0.400626540184021,
      "learning_rate": 4.72157032952495e-06,
      "loss": 0.5416,
      "step": 44110
    },
    {
      "epoch": 1.3550517617423894,
      "grad_norm": 0.5263199806213379,
      "learning_rate": 4.7211598679584195e-06,
      "loss": 0.4587,
      "step": 44111
    },
    {
      "epoch": 1.3550824808773385,
      "grad_norm": 0.3763448894023895,
      "learning_rate": 4.720749418720993e-06,
      "loss": 0.4133,
      "step": 44112
    },
    {
      "epoch": 1.3551132000122876,
      "grad_norm": 0.3831501007080078,
      "learning_rate": 4.72033898181362e-06,
      "loss": 0.4954,
      "step": 44113
    },
    {
      "epoch": 1.3551439191472368,
      "grad_norm": 0.3898560106754303,
      "learning_rate": 4.719928557237265e-06,
      "loss": 0.4493,
      "step": 44114
    },
    {
      "epoch": 1.355174638282186,
      "grad_norm": 0.47001826763153076,
      "learning_rate": 4.719518144992886e-06,
      "loss": 0.3883,
      "step": 44115
    },
    {
      "epoch": 1.3552053574171352,
      "grad_norm": 0.40521150827407837,
      "learning_rate": 4.719107745081445e-06,
      "loss": 0.4002,
      "step": 44116
    },
    {
      "epoch": 1.3552360765520843,
      "grad_norm": 0.4104467034339905,
      "learning_rate": 4.718697357503893e-06,
      "loss": 0.4266,
      "step": 44117
    },
    {
      "epoch": 1.3552667956870335,
      "grad_norm": 0.4196476638317108,
      "learning_rate": 4.718286982261191e-06,
      "loss": 0.4722,
      "step": 44118
    },
    {
      "epoch": 1.3552975148219826,
      "grad_norm": 0.41661983728408813,
      "learning_rate": 4.7178766193543005e-06,
      "loss": 0.48,
      "step": 44119
    },
    {
      "epoch": 1.3553282339569317,
      "grad_norm": 0.44012513756752014,
      "learning_rate": 4.7174662687841765e-06,
      "loss": 0.5714,
      "step": 44120
    },
    {
      "epoch": 1.3553589530918808,
      "grad_norm": 0.415050745010376,
      "learning_rate": 4.717055930551783e-06,
      "loss": 0.4548,
      "step": 44121
    },
    {
      "epoch": 1.3553896722268302,
      "grad_norm": 0.4047630727291107,
      "learning_rate": 4.71664560465807e-06,
      "loss": 0.5495,
      "step": 44122
    },
    {
      "epoch": 1.3554203913617793,
      "grad_norm": 0.4530945122241974,
      "learning_rate": 4.716235291104001e-06,
      "loss": 0.5011,
      "step": 44123
    },
    {
      "epoch": 1.3554511104967284,
      "grad_norm": 0.4223901033401489,
      "learning_rate": 4.715824989890534e-06,
      "loss": 0.4178,
      "step": 44124
    },
    {
      "epoch": 1.3554818296316775,
      "grad_norm": 0.3821609616279602,
      "learning_rate": 4.715414701018629e-06,
      "loss": 0.3462,
      "step": 44125
    },
    {
      "epoch": 1.3555125487666269,
      "grad_norm": 0.39883482456207275,
      "learning_rate": 4.715004424489239e-06,
      "loss": 0.465,
      "step": 44126
    },
    {
      "epoch": 1.355543267901576,
      "grad_norm": 0.3978053629398346,
      "learning_rate": 4.7145941603033264e-06,
      "loss": 0.4925,
      "step": 44127
    },
    {
      "epoch": 1.355573987036525,
      "grad_norm": 0.4221478998661041,
      "learning_rate": 4.714183908461847e-06,
      "loss": 0.5129,
      "step": 44128
    },
    {
      "epoch": 1.3556047061714742,
      "grad_norm": 0.4342378079891205,
      "learning_rate": 4.713773668965764e-06,
      "loss": 0.4045,
      "step": 44129
    },
    {
      "epoch": 1.3556354253064233,
      "grad_norm": 0.44702431559562683,
      "learning_rate": 4.713363441816028e-06,
      "loss": 0.4256,
      "step": 44130
    },
    {
      "epoch": 1.3556661444413725,
      "grad_norm": 0.422305166721344,
      "learning_rate": 4.712953227013601e-06,
      "loss": 0.4589,
      "step": 44131
    },
    {
      "epoch": 1.3556968635763216,
      "grad_norm": 0.39973652362823486,
      "learning_rate": 4.712543024559442e-06,
      "loss": 0.4257,
      "step": 44132
    },
    {
      "epoch": 1.355727582711271,
      "grad_norm": 0.4706948697566986,
      "learning_rate": 4.71213283445451e-06,
      "loss": 0.449,
      "step": 44133
    },
    {
      "epoch": 1.35575830184622,
      "grad_norm": 0.4256591200828552,
      "learning_rate": 4.711722656699759e-06,
      "loss": 0.4894,
      "step": 44134
    },
    {
      "epoch": 1.3557890209811692,
      "grad_norm": 0.4221661686897278,
      "learning_rate": 4.711312491296151e-06,
      "loss": 0.4052,
      "step": 44135
    },
    {
      "epoch": 1.3558197401161183,
      "grad_norm": 0.43342894315719604,
      "learning_rate": 4.710902338244637e-06,
      "loss": 0.4638,
      "step": 44136
    },
    {
      "epoch": 1.3558504592510676,
      "grad_norm": 0.4338356852531433,
      "learning_rate": 4.710492197546186e-06,
      "loss": 0.4653,
      "step": 44137
    },
    {
      "epoch": 1.3558811783860167,
      "grad_norm": 0.40197980403900146,
      "learning_rate": 4.7100820692017455e-06,
      "loss": 0.4925,
      "step": 44138
    },
    {
      "epoch": 1.3559118975209659,
      "grad_norm": 0.4574841856956482,
      "learning_rate": 4.709671953212279e-06,
      "loss": 0.476,
      "step": 44139
    },
    {
      "epoch": 1.355942616655915,
      "grad_norm": 0.43166694045066833,
      "learning_rate": 4.709261849578747e-06,
      "loss": 0.5939,
      "step": 44140
    },
    {
      "epoch": 1.355973335790864,
      "grad_norm": 0.4311513304710388,
      "learning_rate": 4.708851758302096e-06,
      "loss": 0.4845,
      "step": 44141
    },
    {
      "epoch": 1.3560040549258132,
      "grad_norm": 0.4679255783557892,
      "learning_rate": 4.708441679383297e-06,
      "loss": 0.5204,
      "step": 44142
    },
    {
      "epoch": 1.3560347740607623,
      "grad_norm": 0.43950995802879333,
      "learning_rate": 4.7080316128232995e-06,
      "loss": 0.4911,
      "step": 44143
    },
    {
      "epoch": 1.3560654931957117,
      "grad_norm": 0.4678150415420532,
      "learning_rate": 4.7076215586230665e-06,
      "loss": 0.4997,
      "step": 44144
    },
    {
      "epoch": 1.3560962123306608,
      "grad_norm": 0.4126476049423218,
      "learning_rate": 4.707211516783551e-06,
      "loss": 0.3733,
      "step": 44145
    },
    {
      "epoch": 1.35612693146561,
      "grad_norm": 0.4424580931663513,
      "learning_rate": 4.706801487305711e-06,
      "loss": 0.4711,
      "step": 44146
    },
    {
      "epoch": 1.356157650600559,
      "grad_norm": 0.4594408869743347,
      "learning_rate": 4.706391470190506e-06,
      "loss": 0.4837,
      "step": 44147
    },
    {
      "epoch": 1.3561883697355084,
      "grad_norm": 0.44338202476501465,
      "learning_rate": 4.705981465438899e-06,
      "loss": 0.4775,
      "step": 44148
    },
    {
      "epoch": 1.3562190888704575,
      "grad_norm": 0.4356634318828583,
      "learning_rate": 4.705571473051836e-06,
      "loss": 0.5673,
      "step": 44149
    },
    {
      "epoch": 1.3562498080054066,
      "grad_norm": 0.41306108236312866,
      "learning_rate": 4.7051614930302825e-06,
      "loss": 0.4076,
      "step": 44150
    },
    {
      "epoch": 1.3562805271403557,
      "grad_norm": 0.36872756481170654,
      "learning_rate": 4.704751525375193e-06,
      "loss": 0.4827,
      "step": 44151
    },
    {
      "epoch": 1.3563112462753049,
      "grad_norm": 0.39772042632102966,
      "learning_rate": 4.70434157008753e-06,
      "loss": 0.5172,
      "step": 44152
    },
    {
      "epoch": 1.356341965410254,
      "grad_norm": 0.6600704193115234,
      "learning_rate": 4.703931627168243e-06,
      "loss": 0.5162,
      "step": 44153
    },
    {
      "epoch": 1.356372684545203,
      "grad_norm": 0.49368253350257874,
      "learning_rate": 4.703521696618294e-06,
      "loss": 0.4853,
      "step": 44154
    },
    {
      "epoch": 1.3564034036801524,
      "grad_norm": 0.3823394179344177,
      "learning_rate": 4.70311177843864e-06,
      "loss": 0.4376,
      "step": 44155
    },
    {
      "epoch": 1.3564341228151016,
      "grad_norm": 0.44030651450157166,
      "learning_rate": 4.702701872630242e-06,
      "loss": 0.4714,
      "step": 44156
    },
    {
      "epoch": 1.3564648419500507,
      "grad_norm": 0.4365338087081909,
      "learning_rate": 4.70229197919405e-06,
      "loss": 0.4333,
      "step": 44157
    },
    {
      "epoch": 1.3564955610849998,
      "grad_norm": 0.40780285000801086,
      "learning_rate": 4.701882098131026e-06,
      "loss": 0.4237,
      "step": 44158
    },
    {
      "epoch": 1.3565262802199491,
      "grad_norm": 0.4297802448272705,
      "learning_rate": 4.701472229442125e-06,
      "loss": 0.5331,
      "step": 44159
    },
    {
      "epoch": 1.3565569993548983,
      "grad_norm": 0.39585381746292114,
      "learning_rate": 4.7010623731283055e-06,
      "loss": 0.4995,
      "step": 44160
    },
    {
      "epoch": 1.3565877184898474,
      "grad_norm": 0.4397389590740204,
      "learning_rate": 4.7006525291905305e-06,
      "loss": 0.5474,
      "step": 44161
    },
    {
      "epoch": 1.3566184376247965,
      "grad_norm": 0.45442184805870056,
      "learning_rate": 4.700242697629747e-06,
      "loss": 0.5472,
      "step": 44162
    },
    {
      "epoch": 1.3566491567597456,
      "grad_norm": 0.5156236290931702,
      "learning_rate": 4.699832878446916e-06,
      "loss": 0.4411,
      "step": 44163
    },
    {
      "epoch": 1.3566798758946947,
      "grad_norm": 0.39799436926841736,
      "learning_rate": 4.699423071642995e-06,
      "loss": 0.4948,
      "step": 44164
    },
    {
      "epoch": 1.3567105950296439,
      "grad_norm": 0.38621076941490173,
      "learning_rate": 4.699013277218947e-06,
      "loss": 0.4459,
      "step": 44165
    },
    {
      "epoch": 1.3567413141645932,
      "grad_norm": 0.3902704119682312,
      "learning_rate": 4.6986034951757185e-06,
      "loss": 0.4565,
      "step": 44166
    },
    {
      "epoch": 1.3567720332995423,
      "grad_norm": 0.4053061306476593,
      "learning_rate": 4.698193725514277e-06,
      "loss": 0.4746,
      "step": 44167
    },
    {
      "epoch": 1.3568027524344914,
      "grad_norm": 0.4332815408706665,
      "learning_rate": 4.697783968235566e-06,
      "loss": 0.5124,
      "step": 44168
    },
    {
      "epoch": 1.3568334715694406,
      "grad_norm": 0.45444998145103455,
      "learning_rate": 4.697374223340558e-06,
      "loss": 0.4697,
      "step": 44169
    },
    {
      "epoch": 1.3568641907043897,
      "grad_norm": 0.392940878868103,
      "learning_rate": 4.6969644908302005e-06,
      "loss": 0.4105,
      "step": 44170
    },
    {
      "epoch": 1.356894909839339,
      "grad_norm": 0.43123286962509155,
      "learning_rate": 4.696554770705455e-06,
      "loss": 0.442,
      "step": 44171
    },
    {
      "epoch": 1.3569256289742881,
      "grad_norm": 0.40525639057159424,
      "learning_rate": 4.696145062967269e-06,
      "loss": 0.4907,
      "step": 44172
    },
    {
      "epoch": 1.3569563481092373,
      "grad_norm": 0.45496541261672974,
      "learning_rate": 4.695735367616615e-06,
      "loss": 0.4774,
      "step": 44173
    },
    {
      "epoch": 1.3569870672441864,
      "grad_norm": 0.4586905241012573,
      "learning_rate": 4.695325684654437e-06,
      "loss": 0.4976,
      "step": 44174
    },
    {
      "epoch": 1.3570177863791355,
      "grad_norm": 0.42119401693344116,
      "learning_rate": 4.694916014081696e-06,
      "loss": 0.5412,
      "step": 44175
    },
    {
      "epoch": 1.3570485055140846,
      "grad_norm": 0.4201776087284088,
      "learning_rate": 4.694506355899354e-06,
      "loss": 0.5326,
      "step": 44176
    },
    {
      "epoch": 1.357079224649034,
      "grad_norm": 0.4349215030670166,
      "learning_rate": 4.694096710108355e-06,
      "loss": 0.4614,
      "step": 44177
    },
    {
      "epoch": 1.357109943783983,
      "grad_norm": 0.3846774399280548,
      "learning_rate": 4.693687076709671e-06,
      "loss": 0.4348,
      "step": 44178
    },
    {
      "epoch": 1.3571406629189322,
      "grad_norm": 0.49675294756889343,
      "learning_rate": 4.693277455704247e-06,
      "loss": 0.4647,
      "step": 44179
    },
    {
      "epoch": 1.3571713820538813,
      "grad_norm": 0.4417978823184967,
      "learning_rate": 4.692867847093049e-06,
      "loss": 0.5059,
      "step": 44180
    },
    {
      "epoch": 1.3572021011888304,
      "grad_norm": 0.4705790579319,
      "learning_rate": 4.692458250877024e-06,
      "loss": 0.4481,
      "step": 44181
    },
    {
      "epoch": 1.3572328203237798,
      "grad_norm": 0.46798622608184814,
      "learning_rate": 4.6920486670571355e-06,
      "loss": 0.5055,
      "step": 44182
    },
    {
      "epoch": 1.357263539458729,
      "grad_norm": 0.38323724269866943,
      "learning_rate": 4.691639095634336e-06,
      "loss": 0.4493,
      "step": 44183
    },
    {
      "epoch": 1.357294258593678,
      "grad_norm": 0.3860997259616852,
      "learning_rate": 4.691229536609588e-06,
      "loss": 0.4883,
      "step": 44184
    },
    {
      "epoch": 1.3573249777286271,
      "grad_norm": 0.5121655464172363,
      "learning_rate": 4.690819989983841e-06,
      "loss": 0.4488,
      "step": 44185
    },
    {
      "epoch": 1.3573556968635763,
      "grad_norm": 0.4672269821166992,
      "learning_rate": 4.690410455758055e-06,
      "loss": 0.5095,
      "step": 44186
    },
    {
      "epoch": 1.3573864159985254,
      "grad_norm": 0.4289686679840088,
      "learning_rate": 4.690000933933185e-06,
      "loss": 0.4946,
      "step": 44187
    },
    {
      "epoch": 1.3574171351334745,
      "grad_norm": 1.396070122718811,
      "learning_rate": 4.6895914245101935e-06,
      "loss": 0.5393,
      "step": 44188
    },
    {
      "epoch": 1.3574478542684238,
      "grad_norm": 0.4091087579727173,
      "learning_rate": 4.689181927490028e-06,
      "loss": 0.4141,
      "step": 44189
    },
    {
      "epoch": 1.357478573403373,
      "grad_norm": 0.47643184661865234,
      "learning_rate": 4.688772442873649e-06,
      "loss": 0.5304,
      "step": 44190
    },
    {
      "epoch": 1.357509292538322,
      "grad_norm": 0.43243396282196045,
      "learning_rate": 4.688362970662014e-06,
      "loss": 0.4516,
      "step": 44191
    },
    {
      "epoch": 1.3575400116732712,
      "grad_norm": 0.41282105445861816,
      "learning_rate": 4.68795351085608e-06,
      "loss": 0.4219,
      "step": 44192
    },
    {
      "epoch": 1.3575707308082205,
      "grad_norm": 0.3855759799480438,
      "learning_rate": 4.6875440634568e-06,
      "loss": 0.4264,
      "step": 44193
    },
    {
      "epoch": 1.3576014499431697,
      "grad_norm": 0.42007002234458923,
      "learning_rate": 4.68713462846513e-06,
      "loss": 0.4632,
      "step": 44194
    },
    {
      "epoch": 1.3576321690781188,
      "grad_norm": 0.4229866862297058,
      "learning_rate": 4.686725205882029e-06,
      "loss": 0.5022,
      "step": 44195
    },
    {
      "epoch": 1.357662888213068,
      "grad_norm": 0.3828069269657135,
      "learning_rate": 4.686315795708452e-06,
      "loss": 0.5063,
      "step": 44196
    },
    {
      "epoch": 1.357693607348017,
      "grad_norm": 0.4286307394504547,
      "learning_rate": 4.685906397945359e-06,
      "loss": 0.4686,
      "step": 44197
    },
    {
      "epoch": 1.3577243264829661,
      "grad_norm": 0.4451937675476074,
      "learning_rate": 4.685497012593699e-06,
      "loss": 0.4938,
      "step": 44198
    },
    {
      "epoch": 1.3577550456179153,
      "grad_norm": 0.4334008991718292,
      "learning_rate": 4.685087639654433e-06,
      "loss": 0.4788,
      "step": 44199
    },
    {
      "epoch": 1.3577857647528646,
      "grad_norm": 0.44769906997680664,
      "learning_rate": 4.684678279128515e-06,
      "loss": 0.4196,
      "step": 44200
    },
    {
      "epoch": 1.3578164838878137,
      "grad_norm": 0.4181419014930725,
      "learning_rate": 4.684268931016906e-06,
      "loss": 0.5437,
      "step": 44201
    },
    {
      "epoch": 1.3578472030227628,
      "grad_norm": 0.42202937602996826,
      "learning_rate": 4.683859595320555e-06,
      "loss": 0.5258,
      "step": 44202
    },
    {
      "epoch": 1.357877922157712,
      "grad_norm": 0.41577354073524475,
      "learning_rate": 4.683450272040424e-06,
      "loss": 0.4627,
      "step": 44203
    },
    {
      "epoch": 1.3579086412926613,
      "grad_norm": 0.40756410360336304,
      "learning_rate": 4.68304096117746e-06,
      "loss": 0.4936,
      "step": 44204
    },
    {
      "epoch": 1.3579393604276104,
      "grad_norm": 0.43896615505218506,
      "learning_rate": 4.6826316627326316e-06,
      "loss": 0.5141,
      "step": 44205
    },
    {
      "epoch": 1.3579700795625596,
      "grad_norm": 0.4318781793117523,
      "learning_rate": 4.682222376706885e-06,
      "loss": 0.492,
      "step": 44206
    },
    {
      "epoch": 1.3580007986975087,
      "grad_norm": 0.37887170910835266,
      "learning_rate": 4.681813103101183e-06,
      "loss": 0.4742,
      "step": 44207
    },
    {
      "epoch": 1.3580315178324578,
      "grad_norm": 0.40691879391670227,
      "learning_rate": 4.681403841916474e-06,
      "loss": 0.4759,
      "step": 44208
    },
    {
      "epoch": 1.358062236967407,
      "grad_norm": 0.46485576033592224,
      "learning_rate": 4.680994593153718e-06,
      "loss": 0.5596,
      "step": 44209
    },
    {
      "epoch": 1.358092956102356,
      "grad_norm": 0.5375325083732605,
      "learning_rate": 4.68058535681387e-06,
      "loss": 0.4481,
      "step": 44210
    },
    {
      "epoch": 1.3581236752373054,
      "grad_norm": 0.3948005437850952,
      "learning_rate": 4.680176132897888e-06,
      "loss": 0.3896,
      "step": 44211
    },
    {
      "epoch": 1.3581543943722545,
      "grad_norm": 0.4159553647041321,
      "learning_rate": 4.6797669214067285e-06,
      "loss": 0.4998,
      "step": 44212
    },
    {
      "epoch": 1.3581851135072036,
      "grad_norm": 0.4552839994430542,
      "learning_rate": 4.6793577223413375e-06,
      "loss": 0.5268,
      "step": 44213
    },
    {
      "epoch": 1.3582158326421527,
      "grad_norm": 0.40419256687164307,
      "learning_rate": 4.6789485357026864e-06,
      "loss": 0.4686,
      "step": 44214
    },
    {
      "epoch": 1.358246551777102,
      "grad_norm": 0.38836151361465454,
      "learning_rate": 4.678539361491719e-06,
      "loss": 0.5003,
      "step": 44215
    },
    {
      "epoch": 1.3582772709120512,
      "grad_norm": 0.4128514528274536,
      "learning_rate": 4.678130199709396e-06,
      "loss": 0.471,
      "step": 44216
    },
    {
      "epoch": 1.3583079900470003,
      "grad_norm": 0.39774104952812195,
      "learning_rate": 4.67772105035667e-06,
      "loss": 0.4517,
      "step": 44217
    },
    {
      "epoch": 1.3583387091819494,
      "grad_norm": 0.4316697418689728,
      "learning_rate": 4.677311913434498e-06,
      "loss": 0.4376,
      "step": 44218
    },
    {
      "epoch": 1.3583694283168986,
      "grad_norm": 0.4062420725822449,
      "learning_rate": 4.676902788943836e-06,
      "loss": 0.5139,
      "step": 44219
    },
    {
      "epoch": 1.3584001474518477,
      "grad_norm": 0.38215866684913635,
      "learning_rate": 4.676493676885642e-06,
      "loss": 0.4346,
      "step": 44220
    },
    {
      "epoch": 1.3584308665867968,
      "grad_norm": 0.43986138701438904,
      "learning_rate": 4.676084577260865e-06,
      "loss": 0.4911,
      "step": 44221
    },
    {
      "epoch": 1.3584615857217461,
      "grad_norm": 0.4121568500995636,
      "learning_rate": 4.675675490070466e-06,
      "loss": 0.4977,
      "step": 44222
    },
    {
      "epoch": 1.3584923048566953,
      "grad_norm": 0.39642250537872314,
      "learning_rate": 4.675266415315397e-06,
      "loss": 0.5454,
      "step": 44223
    },
    {
      "epoch": 1.3585230239916444,
      "grad_norm": 0.41602253913879395,
      "learning_rate": 4.67485735299662e-06,
      "loss": 0.4561,
      "step": 44224
    },
    {
      "epoch": 1.3585537431265935,
      "grad_norm": 0.43152379989624023,
      "learning_rate": 4.674448303115081e-06,
      "loss": 0.5548,
      "step": 44225
    },
    {
      "epoch": 1.3585844622615428,
      "grad_norm": 0.40919095277786255,
      "learning_rate": 4.67403926567174e-06,
      "loss": 0.5036,
      "step": 44226
    },
    {
      "epoch": 1.358615181396492,
      "grad_norm": 0.4762888252735138,
      "learning_rate": 4.673630240667553e-06,
      "loss": 0.4414,
      "step": 44227
    },
    {
      "epoch": 1.358645900531441,
      "grad_norm": 0.4079647362232208,
      "learning_rate": 4.673221228103477e-06,
      "loss": 0.4924,
      "step": 44228
    },
    {
      "epoch": 1.3586766196663902,
      "grad_norm": 0.3915569484233856,
      "learning_rate": 4.672812227980462e-06,
      "loss": 0.4844,
      "step": 44229
    },
    {
      "epoch": 1.3587073388013393,
      "grad_norm": 0.42815834283828735,
      "learning_rate": 4.672403240299467e-06,
      "loss": 0.4727,
      "step": 44230
    },
    {
      "epoch": 1.3587380579362884,
      "grad_norm": 0.4151330888271332,
      "learning_rate": 4.671994265061445e-06,
      "loss": 0.504,
      "step": 44231
    },
    {
      "epoch": 1.3587687770712376,
      "grad_norm": 0.4103274643421173,
      "learning_rate": 4.671585302267353e-06,
      "loss": 0.488,
      "step": 44232
    },
    {
      "epoch": 1.358799496206187,
      "grad_norm": 0.4014933705329895,
      "learning_rate": 4.671176351918149e-06,
      "loss": 0.4357,
      "step": 44233
    },
    {
      "epoch": 1.358830215341136,
      "grad_norm": 1.3646008968353271,
      "learning_rate": 4.670767414014781e-06,
      "loss": 0.424,
      "step": 44234
    },
    {
      "epoch": 1.3588609344760851,
      "grad_norm": 0.4185582399368286,
      "learning_rate": 4.670358488558209e-06,
      "loss": 0.4538,
      "step": 44235
    },
    {
      "epoch": 1.3588916536110343,
      "grad_norm": 0.38614141941070557,
      "learning_rate": 4.6699495755493855e-06,
      "loss": 0.5107,
      "step": 44236
    },
    {
      "epoch": 1.3589223727459836,
      "grad_norm": 0.43366387486457825,
      "learning_rate": 4.669540674989272e-06,
      "loss": 0.4532,
      "step": 44237
    },
    {
      "epoch": 1.3589530918809327,
      "grad_norm": 0.378460168838501,
      "learning_rate": 4.669131786878813e-06,
      "loss": 0.3787,
      "step": 44238
    },
    {
      "epoch": 1.3589838110158818,
      "grad_norm": 0.4112659990787506,
      "learning_rate": 4.668722911218975e-06,
      "loss": 0.4242,
      "step": 44239
    },
    {
      "epoch": 1.359014530150831,
      "grad_norm": 0.5094524621963501,
      "learning_rate": 4.668314048010698e-06,
      "loss": 0.5023,
      "step": 44240
    },
    {
      "epoch": 1.35904524928578,
      "grad_norm": 0.420398473739624,
      "learning_rate": 4.6679051972549535e-06,
      "loss": 0.4719,
      "step": 44241
    },
    {
      "epoch": 1.3590759684207292,
      "grad_norm": 0.5067817568778992,
      "learning_rate": 4.667496358952685e-06,
      "loss": 0.4308,
      "step": 44242
    },
    {
      "epoch": 1.3591066875556783,
      "grad_norm": 0.48042958974838257,
      "learning_rate": 4.667087533104856e-06,
      "loss": 0.5715,
      "step": 44243
    },
    {
      "epoch": 1.3591374066906277,
      "grad_norm": 0.44944286346435547,
      "learning_rate": 4.666678719712412e-06,
      "loss": 0.4658,
      "step": 44244
    },
    {
      "epoch": 1.3591681258255768,
      "grad_norm": 0.5511119961738586,
      "learning_rate": 4.6662699187763125e-06,
      "loss": 0.4838,
      "step": 44245
    },
    {
      "epoch": 1.359198844960526,
      "grad_norm": 0.4160590171813965,
      "learning_rate": 4.665861130297512e-06,
      "loss": 0.4188,
      "step": 44246
    },
    {
      "epoch": 1.359229564095475,
      "grad_norm": 0.4674026668071747,
      "learning_rate": 4.665452354276969e-06,
      "loss": 0.5206,
      "step": 44247
    },
    {
      "epoch": 1.3592602832304244,
      "grad_norm": 0.43700122833251953,
      "learning_rate": 4.665043590715631e-06,
      "loss": 0.5393,
      "step": 44248
    },
    {
      "epoch": 1.3592910023653735,
      "grad_norm": 0.3959709405899048,
      "learning_rate": 4.6646348396144555e-06,
      "loss": 0.4861,
      "step": 44249
    },
    {
      "epoch": 1.3593217215003226,
      "grad_norm": 0.4081268906593323,
      "learning_rate": 4.664226100974399e-06,
      "loss": 0.4603,
      "step": 44250
    },
    {
      "epoch": 1.3593524406352717,
      "grad_norm": 0.42233848571777344,
      "learning_rate": 4.663817374796414e-06,
      "loss": 0.4801,
      "step": 44251
    },
    {
      "epoch": 1.3593831597702208,
      "grad_norm": 0.4458918273448944,
      "learning_rate": 4.663408661081461e-06,
      "loss": 0.5094,
      "step": 44252
    },
    {
      "epoch": 1.35941387890517,
      "grad_norm": 0.460543692111969,
      "learning_rate": 4.662999959830487e-06,
      "loss": 0.5609,
      "step": 44253
    },
    {
      "epoch": 1.359444598040119,
      "grad_norm": 0.4016268849372864,
      "learning_rate": 4.6625912710444475e-06,
      "loss": 0.4834,
      "step": 44254
    },
    {
      "epoch": 1.3594753171750684,
      "grad_norm": 0.40245184302330017,
      "learning_rate": 4.6621825947243e-06,
      "loss": 0.4726,
      "step": 44255
    },
    {
      "epoch": 1.3595060363100175,
      "grad_norm": 0.45115041732788086,
      "learning_rate": 4.661773930871e-06,
      "loss": 0.4801,
      "step": 44256
    },
    {
      "epoch": 1.3595367554449667,
      "grad_norm": 0.46330851316452026,
      "learning_rate": 4.661365279485497e-06,
      "loss": 0.5178,
      "step": 44257
    },
    {
      "epoch": 1.3595674745799158,
      "grad_norm": 0.4083106219768524,
      "learning_rate": 4.660956640568749e-06,
      "loss": 0.4474,
      "step": 44258
    },
    {
      "epoch": 1.3595981937148651,
      "grad_norm": 0.4057106375694275,
      "learning_rate": 4.660548014121709e-06,
      "loss": 0.5061,
      "step": 44259
    },
    {
      "epoch": 1.3596289128498142,
      "grad_norm": 0.4378238916397095,
      "learning_rate": 4.660139400145335e-06,
      "loss": 0.4644,
      "step": 44260
    },
    {
      "epoch": 1.3596596319847634,
      "grad_norm": 0.46434175968170166,
      "learning_rate": 4.659730798640575e-06,
      "loss": 0.4999,
      "step": 44261
    },
    {
      "epoch": 1.3596903511197125,
      "grad_norm": 0.44616442918777466,
      "learning_rate": 4.6593222096083865e-06,
      "loss": 0.5131,
      "step": 44262
    },
    {
      "epoch": 1.3597210702546616,
      "grad_norm": 0.41691678762435913,
      "learning_rate": 4.658913633049725e-06,
      "loss": 0.4914,
      "step": 44263
    },
    {
      "epoch": 1.3597517893896107,
      "grad_norm": 0.3944509029388428,
      "learning_rate": 4.658505068965548e-06,
      "loss": 0.4915,
      "step": 44264
    },
    {
      "epoch": 1.3597825085245598,
      "grad_norm": 0.4493112564086914,
      "learning_rate": 4.658096517356799e-06,
      "loss": 0.4258,
      "step": 44265
    },
    {
      "epoch": 1.3598132276595092,
      "grad_norm": 0.40081310272216797,
      "learning_rate": 4.657687978224441e-06,
      "loss": 0.5027,
      "step": 44266
    },
    {
      "epoch": 1.3598439467944583,
      "grad_norm": 0.4142519235610962,
      "learning_rate": 4.657279451569425e-06,
      "loss": 0.4634,
      "step": 44267
    },
    {
      "epoch": 1.3598746659294074,
      "grad_norm": 0.4630056321620941,
      "learning_rate": 4.656870937392706e-06,
      "loss": 0.4083,
      "step": 44268
    },
    {
      "epoch": 1.3599053850643565,
      "grad_norm": 0.43498745560646057,
      "learning_rate": 4.6564624356952425e-06,
      "loss": 0.4364,
      "step": 44269
    },
    {
      "epoch": 1.3599361041993059,
      "grad_norm": 0.41571980714797974,
      "learning_rate": 4.65605394647798e-06,
      "loss": 0.467,
      "step": 44270
    },
    {
      "epoch": 1.359966823334255,
      "grad_norm": 0.3854617178440094,
      "learning_rate": 4.655645469741879e-06,
      "loss": 0.4115,
      "step": 44271
    },
    {
      "epoch": 1.3599975424692041,
      "grad_norm": 0.43244484066963196,
      "learning_rate": 4.655237005487886e-06,
      "loss": 0.473,
      "step": 44272
    },
    {
      "epoch": 1.3600282616041532,
      "grad_norm": 0.43525412678718567,
      "learning_rate": 4.654828553716967e-06,
      "loss": 0.5322,
      "step": 44273
    },
    {
      "epoch": 1.3600589807391024,
      "grad_norm": 0.5752508044242859,
      "learning_rate": 4.654420114430065e-06,
      "loss": 0.4875,
      "step": 44274
    },
    {
      "epoch": 1.3600896998740515,
      "grad_norm": 0.3827754557132721,
      "learning_rate": 4.654011687628141e-06,
      "loss": 0.4669,
      "step": 44275
    },
    {
      "epoch": 1.3601204190090006,
      "grad_norm": 0.42690256237983704,
      "learning_rate": 4.65360327331214e-06,
      "loss": 0.4638,
      "step": 44276
    },
    {
      "epoch": 1.36015113814395,
      "grad_norm": 0.4058249294757843,
      "learning_rate": 4.65319487148303e-06,
      "loss": 0.4065,
      "step": 44277
    },
    {
      "epoch": 1.360181857278899,
      "grad_norm": 0.3965054452419281,
      "learning_rate": 4.652786482141752e-06,
      "loss": 0.4815,
      "step": 44278
    },
    {
      "epoch": 1.3602125764138482,
      "grad_norm": 0.43282368779182434,
      "learning_rate": 4.652378105289269e-06,
      "loss": 0.4896,
      "step": 44279
    },
    {
      "epoch": 1.3602432955487973,
      "grad_norm": 0.39734670519828796,
      "learning_rate": 4.651969740926527e-06,
      "loss": 0.5154,
      "step": 44280
    },
    {
      "epoch": 1.3602740146837464,
      "grad_norm": 0.44874879717826843,
      "learning_rate": 4.651561389054482e-06,
      "loss": 0.5173,
      "step": 44281
    },
    {
      "epoch": 1.3603047338186958,
      "grad_norm": 0.4271232783794403,
      "learning_rate": 4.651153049674089e-06,
      "loss": 0.4626,
      "step": 44282
    },
    {
      "epoch": 1.3603354529536449,
      "grad_norm": 0.43653571605682373,
      "learning_rate": 4.650744722786305e-06,
      "loss": 0.4701,
      "step": 44283
    },
    {
      "epoch": 1.360366172088594,
      "grad_norm": 0.49322155117988586,
      "learning_rate": 4.650336408392077e-06,
      "loss": 0.4403,
      "step": 44284
    },
    {
      "epoch": 1.3603968912235431,
      "grad_norm": 0.3901771605014801,
      "learning_rate": 4.649928106492363e-06,
      "loss": 0.4621,
      "step": 44285
    },
    {
      "epoch": 1.3604276103584922,
      "grad_norm": 0.47716689109802246,
      "learning_rate": 4.6495198170881155e-06,
      "loss": 0.4342,
      "step": 44286
    },
    {
      "epoch": 1.3604583294934414,
      "grad_norm": 0.40884530544281006,
      "learning_rate": 4.649111540180287e-06,
      "loss": 0.4854,
      "step": 44287
    },
    {
      "epoch": 1.3604890486283907,
      "grad_norm": 0.40233680605888367,
      "learning_rate": 4.648703275769835e-06,
      "loss": 0.4118,
      "step": 44288
    },
    {
      "epoch": 1.3605197677633398,
      "grad_norm": 0.4167717695236206,
      "learning_rate": 4.648295023857708e-06,
      "loss": 0.4695,
      "step": 44289
    },
    {
      "epoch": 1.360550486898289,
      "grad_norm": 0.3989986181259155,
      "learning_rate": 4.647886784444862e-06,
      "loss": 0.4971,
      "step": 44290
    },
    {
      "epoch": 1.360581206033238,
      "grad_norm": 0.41319045424461365,
      "learning_rate": 4.64747855753225e-06,
      "loss": 0.459,
      "step": 44291
    },
    {
      "epoch": 1.3606119251681872,
      "grad_norm": 0.4170874357223511,
      "learning_rate": 4.647070343120829e-06,
      "loss": 0.4566,
      "step": 44292
    },
    {
      "epoch": 1.3606426443031365,
      "grad_norm": 0.3931606709957123,
      "learning_rate": 4.646662141211545e-06,
      "loss": 0.4711,
      "step": 44293
    },
    {
      "epoch": 1.3606733634380856,
      "grad_norm": 0.4113122522830963,
      "learning_rate": 4.646253951805357e-06,
      "loss": 0.4822,
      "step": 44294
    },
    {
      "epoch": 1.3607040825730348,
      "grad_norm": 0.37088823318481445,
      "learning_rate": 4.645845774903215e-06,
      "loss": 0.4543,
      "step": 44295
    },
    {
      "epoch": 1.3607348017079839,
      "grad_norm": 0.3953760862350464,
      "learning_rate": 4.645437610506078e-06,
      "loss": 0.4262,
      "step": 44296
    },
    {
      "epoch": 1.360765520842933,
      "grad_norm": 0.3858208954334259,
      "learning_rate": 4.645029458614893e-06,
      "loss": 0.4511,
      "step": 44297
    },
    {
      "epoch": 1.3607962399778821,
      "grad_norm": 0.44958528876304626,
      "learning_rate": 4.644621319230614e-06,
      "loss": 0.479,
      "step": 44298
    },
    {
      "epoch": 1.3608269591128312,
      "grad_norm": 0.41657721996307373,
      "learning_rate": 4.644213192354198e-06,
      "loss": 0.4256,
      "step": 44299
    },
    {
      "epoch": 1.3608576782477806,
      "grad_norm": 0.4367726445198059,
      "learning_rate": 4.6438050779865986e-06,
      "loss": 0.5369,
      "step": 44300
    },
    {
      "epoch": 1.3608883973827297,
      "grad_norm": 0.4488861560821533,
      "learning_rate": 4.643396976128762e-06,
      "loss": 0.4859,
      "step": 44301
    },
    {
      "epoch": 1.3609191165176788,
      "grad_norm": 0.4966977536678314,
      "learning_rate": 4.6429888867816504e-06,
      "loss": 0.5039,
      "step": 44302
    },
    {
      "epoch": 1.360949835652628,
      "grad_norm": 0.436155766248703,
      "learning_rate": 4.642580809946206e-06,
      "loss": 0.4886,
      "step": 44303
    },
    {
      "epoch": 1.3609805547875773,
      "grad_norm": 0.425536572933197,
      "learning_rate": 4.64217274562339e-06,
      "loss": 0.5329,
      "step": 44304
    },
    {
      "epoch": 1.3610112739225264,
      "grad_norm": 0.47019249200820923,
      "learning_rate": 4.6417646938141595e-06,
      "loss": 0.5173,
      "step": 44305
    },
    {
      "epoch": 1.3610419930574755,
      "grad_norm": 0.39726895093917847,
      "learning_rate": 4.641356654519456e-06,
      "loss": 0.435,
      "step": 44306
    },
    {
      "epoch": 1.3610727121924246,
      "grad_norm": 0.48494279384613037,
      "learning_rate": 4.640948627740243e-06,
      "loss": 0.5205,
      "step": 44307
    },
    {
      "epoch": 1.3611034313273738,
      "grad_norm": 0.4075769782066345,
      "learning_rate": 4.640540613477461e-06,
      "loss": 0.4524,
      "step": 44308
    },
    {
      "epoch": 1.361134150462323,
      "grad_norm": 0.4219018816947937,
      "learning_rate": 4.640132611732079e-06,
      "loss": 0.5305,
      "step": 44309
    },
    {
      "epoch": 1.361164869597272,
      "grad_norm": 0.4139029085636139,
      "learning_rate": 4.639724622505037e-06,
      "loss": 0.4397,
      "step": 44310
    },
    {
      "epoch": 1.3611955887322214,
      "grad_norm": 0.41794726252555847,
      "learning_rate": 4.639316645797297e-06,
      "loss": 0.5298,
      "step": 44311
    },
    {
      "epoch": 1.3612263078671705,
      "grad_norm": 0.3961138427257538,
      "learning_rate": 4.638908681609803e-06,
      "loss": 0.4201,
      "step": 44312
    },
    {
      "epoch": 1.3612570270021196,
      "grad_norm": 0.41087019443511963,
      "learning_rate": 4.638500729943513e-06,
      "loss": 0.4397,
      "step": 44313
    },
    {
      "epoch": 1.3612877461370687,
      "grad_norm": 0.43706655502319336,
      "learning_rate": 4.638092790799378e-06,
      "loss": 0.5129,
      "step": 44314
    },
    {
      "epoch": 1.361318465272018,
      "grad_norm": 0.45588910579681396,
      "learning_rate": 4.637684864178355e-06,
      "loss": 0.468,
      "step": 44315
    },
    {
      "epoch": 1.3613491844069672,
      "grad_norm": 0.37749695777893066,
      "learning_rate": 4.637276950081391e-06,
      "loss": 0.442,
      "step": 44316
    },
    {
      "epoch": 1.3613799035419163,
      "grad_norm": 0.42641642689704895,
      "learning_rate": 4.636869048509441e-06,
      "loss": 0.4921,
      "step": 44317
    },
    {
      "epoch": 1.3614106226768654,
      "grad_norm": 0.43560194969177246,
      "learning_rate": 4.636461159463458e-06,
      "loss": 0.5027,
      "step": 44318
    },
    {
      "epoch": 1.3614413418118145,
      "grad_norm": 0.6996496915817261,
      "learning_rate": 4.636053282944399e-06,
      "loss": 0.4872,
      "step": 44319
    },
    {
      "epoch": 1.3614720609467637,
      "grad_norm": 0.44631245732307434,
      "learning_rate": 4.635645418953206e-06,
      "loss": 0.5829,
      "step": 44320
    },
    {
      "epoch": 1.3615027800817128,
      "grad_norm": 0.5173848271369934,
      "learning_rate": 4.63523756749084e-06,
      "loss": 0.477,
      "step": 44321
    },
    {
      "epoch": 1.3615334992166621,
      "grad_norm": 0.4556731879711151,
      "learning_rate": 4.63482972855825e-06,
      "loss": 0.4666,
      "step": 44322
    },
    {
      "epoch": 1.3615642183516112,
      "grad_norm": 0.42196953296661377,
      "learning_rate": 4.634421902156391e-06,
      "loss": 0.4961,
      "step": 44323
    },
    {
      "epoch": 1.3615949374865604,
      "grad_norm": 0.40109744668006897,
      "learning_rate": 4.634014088286217e-06,
      "loss": 0.4933,
      "step": 44324
    },
    {
      "epoch": 1.3616256566215095,
      "grad_norm": 0.3715112805366516,
      "learning_rate": 4.6336062869486745e-06,
      "loss": 0.4697,
      "step": 44325
    },
    {
      "epoch": 1.3616563757564588,
      "grad_norm": 0.41956329345703125,
      "learning_rate": 4.63319849814472e-06,
      "loss": 0.4865,
      "step": 44326
    },
    {
      "epoch": 1.361687094891408,
      "grad_norm": 0.4276455342769623,
      "learning_rate": 4.632790721875304e-06,
      "loss": 0.5567,
      "step": 44327
    },
    {
      "epoch": 1.361717814026357,
      "grad_norm": 0.4328129291534424,
      "learning_rate": 4.632382958141385e-06,
      "loss": 0.4239,
      "step": 44328
    },
    {
      "epoch": 1.3617485331613062,
      "grad_norm": 0.3959013521671295,
      "learning_rate": 4.631975206943906e-06,
      "loss": 0.4275,
      "step": 44329
    },
    {
      "epoch": 1.3617792522962553,
      "grad_norm": 0.4075029790401459,
      "learning_rate": 4.631567468283824e-06,
      "loss": 0.4701,
      "step": 44330
    },
    {
      "epoch": 1.3618099714312044,
      "grad_norm": 0.4275934100151062,
      "learning_rate": 4.631159742162091e-06,
      "loss": 0.4997,
      "step": 44331
    },
    {
      "epoch": 1.3618406905661535,
      "grad_norm": 0.4001469612121582,
      "learning_rate": 4.6307520285796634e-06,
      "loss": 0.5425,
      "step": 44332
    },
    {
      "epoch": 1.3618714097011029,
      "grad_norm": 0.4188218116760254,
      "learning_rate": 4.630344327537486e-06,
      "loss": 0.5269,
      "step": 44333
    },
    {
      "epoch": 1.361902128836052,
      "grad_norm": 0.3985929489135742,
      "learning_rate": 4.629936639036517e-06,
      "loss": 0.4942,
      "step": 44334
    },
    {
      "epoch": 1.3619328479710011,
      "grad_norm": 0.38089117407798767,
      "learning_rate": 4.6295289630777e-06,
      "loss": 0.4664,
      "step": 44335
    },
    {
      "epoch": 1.3619635671059502,
      "grad_norm": 0.5392220616340637,
      "learning_rate": 4.629121299661999e-06,
      "loss": 0.4636,
      "step": 44336
    },
    {
      "epoch": 1.3619942862408996,
      "grad_norm": 0.3968554437160492,
      "learning_rate": 4.628713648790359e-06,
      "loss": 0.5691,
      "step": 44337
    },
    {
      "epoch": 1.3620250053758487,
      "grad_norm": 0.3819598853588104,
      "learning_rate": 4.628306010463734e-06,
      "loss": 0.4353,
      "step": 44338
    },
    {
      "epoch": 1.3620557245107978,
      "grad_norm": 0.4105057716369629,
      "learning_rate": 4.6278983846830705e-06,
      "loss": 0.4073,
      "step": 44339
    },
    {
      "epoch": 1.362086443645747,
      "grad_norm": 0.45362532138824463,
      "learning_rate": 4.627490771449328e-06,
      "loss": 0.4345,
      "step": 44340
    },
    {
      "epoch": 1.362117162780696,
      "grad_norm": 0.3978688418865204,
      "learning_rate": 4.62708317076346e-06,
      "loss": 0.4913,
      "step": 44341
    },
    {
      "epoch": 1.3621478819156452,
      "grad_norm": 0.40533122420310974,
      "learning_rate": 4.626675582626411e-06,
      "loss": 0.4854,
      "step": 44342
    },
    {
      "epoch": 1.3621786010505943,
      "grad_norm": 0.47753262519836426,
      "learning_rate": 4.626268007039141e-06,
      "loss": 0.4641,
      "step": 44343
    },
    {
      "epoch": 1.3622093201855436,
      "grad_norm": 0.46057119965553284,
      "learning_rate": 4.625860444002588e-06,
      "loss": 0.5403,
      "step": 44344
    },
    {
      "epoch": 1.3622400393204928,
      "grad_norm": 0.43815112113952637,
      "learning_rate": 4.625452893517722e-06,
      "loss": 0.4525,
      "step": 44345
    },
    {
      "epoch": 1.3622707584554419,
      "grad_norm": 0.4204851984977722,
      "learning_rate": 4.625045355585483e-06,
      "loss": 0.5382,
      "step": 44346
    },
    {
      "epoch": 1.362301477590391,
      "grad_norm": 0.41918671131134033,
      "learning_rate": 4.624637830206828e-06,
      "loss": 0.4083,
      "step": 44347
    },
    {
      "epoch": 1.3623321967253403,
      "grad_norm": 0.4774830639362335,
      "learning_rate": 4.624230317382704e-06,
      "loss": 0.4281,
      "step": 44348
    },
    {
      "epoch": 1.3623629158602895,
      "grad_norm": 0.5186741948127747,
      "learning_rate": 4.6238228171140654e-06,
      "loss": 0.4683,
      "step": 44349
    },
    {
      "epoch": 1.3623936349952386,
      "grad_norm": 0.4245527982711792,
      "learning_rate": 4.6234153294018634e-06,
      "loss": 0.5498,
      "step": 44350
    },
    {
      "epoch": 1.3624243541301877,
      "grad_norm": 0.39621248841285706,
      "learning_rate": 4.6230078542470545e-06,
      "loss": 0.5152,
      "step": 44351
    },
    {
      "epoch": 1.3624550732651368,
      "grad_norm": 0.3902195394039154,
      "learning_rate": 4.622600391650584e-06,
      "loss": 0.4409,
      "step": 44352
    },
    {
      "epoch": 1.362485792400086,
      "grad_norm": 0.4197334349155426,
      "learning_rate": 4.6221929416134036e-06,
      "loss": 0.4127,
      "step": 44353
    },
    {
      "epoch": 1.362516511535035,
      "grad_norm": 0.416575163602829,
      "learning_rate": 4.6217855041364675e-06,
      "loss": 0.4506,
      "step": 44354
    },
    {
      "epoch": 1.3625472306699844,
      "grad_norm": 0.40346139669418335,
      "learning_rate": 4.621378079220732e-06,
      "loss": 0.4193,
      "step": 44355
    },
    {
      "epoch": 1.3625779498049335,
      "grad_norm": 0.36250925064086914,
      "learning_rate": 4.620970666867139e-06,
      "loss": 0.4196,
      "step": 44356
    },
    {
      "epoch": 1.3626086689398826,
      "grad_norm": 0.38800933957099915,
      "learning_rate": 4.620563267076646e-06,
      "loss": 0.4711,
      "step": 44357
    },
    {
      "epoch": 1.3626393880748318,
      "grad_norm": 0.39499431848526,
      "learning_rate": 4.620155879850201e-06,
      "loss": 0.437,
      "step": 44358
    },
    {
      "epoch": 1.362670107209781,
      "grad_norm": 0.39488646388053894,
      "learning_rate": 4.619748505188759e-06,
      "loss": 0.4523,
      "step": 44359
    },
    {
      "epoch": 1.3627008263447302,
      "grad_norm": 0.4168983995914459,
      "learning_rate": 4.619341143093274e-06,
      "loss": 0.4998,
      "step": 44360
    },
    {
      "epoch": 1.3627315454796793,
      "grad_norm": 0.36895400285720825,
      "learning_rate": 4.61893379356469e-06,
      "loss": 0.5021,
      "step": 44361
    },
    {
      "epoch": 1.3627622646146285,
      "grad_norm": 0.38240930438041687,
      "learning_rate": 4.618526456603961e-06,
      "loss": 0.4871,
      "step": 44362
    },
    {
      "epoch": 1.3627929837495776,
      "grad_norm": 0.40541574358940125,
      "learning_rate": 4.61811913221204e-06,
      "loss": 0.5181,
      "step": 44363
    },
    {
      "epoch": 1.3628237028845267,
      "grad_norm": 0.39662548899650574,
      "learning_rate": 4.617711820389881e-06,
      "loss": 0.4635,
      "step": 44364
    },
    {
      "epoch": 1.3628544220194758,
      "grad_norm": 0.4853631854057312,
      "learning_rate": 4.6173045211384285e-06,
      "loss": 0.4609,
      "step": 44365
    },
    {
      "epoch": 1.3628851411544252,
      "grad_norm": 0.44074422121047974,
      "learning_rate": 4.616897234458636e-06,
      "loss": 0.4433,
      "step": 44366
    },
    {
      "epoch": 1.3629158602893743,
      "grad_norm": 0.44916653633117676,
      "learning_rate": 4.616489960351457e-06,
      "loss": 0.4821,
      "step": 44367
    },
    {
      "epoch": 1.3629465794243234,
      "grad_norm": 0.3913264274597168,
      "learning_rate": 4.616082698817845e-06,
      "loss": 0.4658,
      "step": 44368
    },
    {
      "epoch": 1.3629772985592725,
      "grad_norm": 0.4120863974094391,
      "learning_rate": 4.615675449858746e-06,
      "loss": 0.492,
      "step": 44369
    },
    {
      "epoch": 1.3630080176942219,
      "grad_norm": 0.4284437298774719,
      "learning_rate": 4.615268213475115e-06,
      "loss": 0.4484,
      "step": 44370
    },
    {
      "epoch": 1.363038736829171,
      "grad_norm": 0.39902228116989136,
      "learning_rate": 4.6148609896678934e-06,
      "loss": 0.3847,
      "step": 44371
    },
    {
      "epoch": 1.36306945596412,
      "grad_norm": 0.40915432572364807,
      "learning_rate": 4.6144537784380485e-06,
      "loss": 0.5087,
      "step": 44372
    },
    {
      "epoch": 1.3631001750990692,
      "grad_norm": 0.4017951190471649,
      "learning_rate": 4.614046579786518e-06,
      "loss": 0.4722,
      "step": 44373
    },
    {
      "epoch": 1.3631308942340183,
      "grad_norm": 0.36788615584373474,
      "learning_rate": 4.6136393937142625e-06,
      "loss": 0.4627,
      "step": 44374
    },
    {
      "epoch": 1.3631616133689675,
      "grad_norm": 0.46655938029289246,
      "learning_rate": 4.613232220222225e-06,
      "loss": 0.4243,
      "step": 44375
    },
    {
      "epoch": 1.3631923325039166,
      "grad_norm": 0.48023542761802673,
      "learning_rate": 4.612825059311355e-06,
      "loss": 0.4235,
      "step": 44376
    },
    {
      "epoch": 1.363223051638866,
      "grad_norm": 0.4475350081920624,
      "learning_rate": 4.612417910982616e-06,
      "loss": 0.4363,
      "step": 44377
    },
    {
      "epoch": 1.363253770773815,
      "grad_norm": 0.46695268154144287,
      "learning_rate": 4.612010775236948e-06,
      "loss": 0.4597,
      "step": 44378
    },
    {
      "epoch": 1.3632844899087642,
      "grad_norm": 0.40518051385879517,
      "learning_rate": 4.611603652075309e-06,
      "loss": 0.4919,
      "step": 44379
    },
    {
      "epoch": 1.3633152090437133,
      "grad_norm": 0.40044742822647095,
      "learning_rate": 4.611196541498638e-06,
      "loss": 0.4257,
      "step": 44380
    },
    {
      "epoch": 1.3633459281786626,
      "grad_norm": 0.385009229183197,
      "learning_rate": 4.610789443507901e-06,
      "loss": 0.4044,
      "step": 44381
    },
    {
      "epoch": 1.3633766473136117,
      "grad_norm": 0.4742947518825531,
      "learning_rate": 4.61038235810404e-06,
      "loss": 0.4437,
      "step": 44382
    },
    {
      "epoch": 1.3634073664485609,
      "grad_norm": 0.454025536775589,
      "learning_rate": 4.609975285288009e-06,
      "loss": 0.3937,
      "step": 44383
    },
    {
      "epoch": 1.36343808558351,
      "grad_norm": 0.4057316184043884,
      "learning_rate": 4.609568225060754e-06,
      "loss": 0.5151,
      "step": 44384
    },
    {
      "epoch": 1.363468804718459,
      "grad_norm": 0.4281452000141144,
      "learning_rate": 4.609161177423229e-06,
      "loss": 0.4859,
      "step": 44385
    },
    {
      "epoch": 1.3634995238534082,
      "grad_norm": 0.4108196198940277,
      "learning_rate": 4.608754142376385e-06,
      "loss": 0.5102,
      "step": 44386
    },
    {
      "epoch": 1.3635302429883573,
      "grad_norm": 0.4137735366821289,
      "learning_rate": 4.6083471199211745e-06,
      "loss": 0.4695,
      "step": 44387
    },
    {
      "epoch": 1.3635609621233067,
      "grad_norm": 0.4213814437389374,
      "learning_rate": 4.607940110058543e-06,
      "loss": 0.4201,
      "step": 44388
    },
    {
      "epoch": 1.3635916812582558,
      "grad_norm": 0.42043638229370117,
      "learning_rate": 4.607533112789444e-06,
      "loss": 0.5081,
      "step": 44389
    },
    {
      "epoch": 1.363622400393205,
      "grad_norm": 0.4177257716655731,
      "learning_rate": 4.607126128114828e-06,
      "loss": 0.4389,
      "step": 44390
    },
    {
      "epoch": 1.363653119528154,
      "grad_norm": 0.4258209466934204,
      "learning_rate": 4.60671915603565e-06,
      "loss": 0.4421,
      "step": 44391
    },
    {
      "epoch": 1.3636838386631032,
      "grad_norm": 0.4508139193058014,
      "learning_rate": 4.606312196552851e-06,
      "loss": 0.593,
      "step": 44392
    },
    {
      "epoch": 1.3637145577980525,
      "grad_norm": 0.401459276676178,
      "learning_rate": 4.6059052496673875e-06,
      "loss": 0.4735,
      "step": 44393
    },
    {
      "epoch": 1.3637452769330016,
      "grad_norm": 0.3867584764957428,
      "learning_rate": 4.605498315380208e-06,
      "loss": 0.4681,
      "step": 44394
    },
    {
      "epoch": 1.3637759960679507,
      "grad_norm": 0.42610788345336914,
      "learning_rate": 4.6050913936922645e-06,
      "loss": 0.4443,
      "step": 44395
    },
    {
      "epoch": 1.3638067152028999,
      "grad_norm": 0.44728073477745056,
      "learning_rate": 4.6046844846045115e-06,
      "loss": 0.4493,
      "step": 44396
    },
    {
      "epoch": 1.363837434337849,
      "grad_norm": 0.4145658016204834,
      "learning_rate": 4.604277588117891e-06,
      "loss": 0.4302,
      "step": 44397
    },
    {
      "epoch": 1.363868153472798,
      "grad_norm": 0.43083083629608154,
      "learning_rate": 4.6038707042333556e-06,
      "loss": 0.5654,
      "step": 44398
    },
    {
      "epoch": 1.3638988726077474,
      "grad_norm": 0.38810524344444275,
      "learning_rate": 4.603463832951857e-06,
      "loss": 0.4193,
      "step": 44399
    },
    {
      "epoch": 1.3639295917426966,
      "grad_norm": 0.40401411056518555,
      "learning_rate": 4.603056974274351e-06,
      "loss": 0.5251,
      "step": 44400
    },
    {
      "epoch": 1.3639603108776457,
      "grad_norm": 0.40329456329345703,
      "learning_rate": 4.602650128201776e-06,
      "loss": 0.4486,
      "step": 44401
    },
    {
      "epoch": 1.3639910300125948,
      "grad_norm": 0.38863635063171387,
      "learning_rate": 4.60224329473509e-06,
      "loss": 0.4559,
      "step": 44402
    },
    {
      "epoch": 1.364021749147544,
      "grad_norm": 0.44669684767723083,
      "learning_rate": 4.601836473875242e-06,
      "loss": 0.4638,
      "step": 44403
    },
    {
      "epoch": 1.3640524682824933,
      "grad_norm": 0.38689690828323364,
      "learning_rate": 4.601429665623186e-06,
      "loss": 0.4679,
      "step": 44404
    },
    {
      "epoch": 1.3640831874174424,
      "grad_norm": 0.4021707773208618,
      "learning_rate": 4.601022869979863e-06,
      "loss": 0.3872,
      "step": 44405
    },
    {
      "epoch": 1.3641139065523915,
      "grad_norm": 0.4259057641029358,
      "learning_rate": 4.600616086946234e-06,
      "loss": 0.5022,
      "step": 44406
    },
    {
      "epoch": 1.3641446256873406,
      "grad_norm": 0.3830806612968445,
      "learning_rate": 4.600209316523233e-06,
      "loss": 0.4323,
      "step": 44407
    },
    {
      "epoch": 1.3641753448222897,
      "grad_norm": 0.4311738610267639,
      "learning_rate": 4.59980255871183e-06,
      "loss": 0.4082,
      "step": 44408
    },
    {
      "epoch": 1.3642060639572389,
      "grad_norm": 0.39812788367271423,
      "learning_rate": 4.59939581351296e-06,
      "loss": 0.4739,
      "step": 44409
    },
    {
      "epoch": 1.364236783092188,
      "grad_norm": 0.43815308809280396,
      "learning_rate": 4.598989080927583e-06,
      "loss": 0.4932,
      "step": 44410
    },
    {
      "epoch": 1.3642675022271373,
      "grad_norm": 0.417873740196228,
      "learning_rate": 4.5985823609566406e-06,
      "loss": 0.4477,
      "step": 44411
    },
    {
      "epoch": 1.3642982213620864,
      "grad_norm": 0.4279557764530182,
      "learning_rate": 4.598175653601082e-06,
      "loss": 0.5064,
      "step": 44412
    },
    {
      "epoch": 1.3643289404970356,
      "grad_norm": 0.47568634152412415,
      "learning_rate": 4.597768958861869e-06,
      "loss": 0.3721,
      "step": 44413
    },
    {
      "epoch": 1.3643596596319847,
      "grad_norm": 0.4150167405605316,
      "learning_rate": 4.597362276739939e-06,
      "loss": 0.3929,
      "step": 44414
    },
    {
      "epoch": 1.364390378766934,
      "grad_norm": 0.4108458161354065,
      "learning_rate": 4.596955607236252e-06,
      "loss": 0.5093,
      "step": 44415
    },
    {
      "epoch": 1.3644210979018832,
      "grad_norm": 0.46317487955093384,
      "learning_rate": 4.596548950351749e-06,
      "loss": 0.5089,
      "step": 44416
    },
    {
      "epoch": 1.3644518170368323,
      "grad_norm": 0.4592650532722473,
      "learning_rate": 4.596142306087382e-06,
      "loss": 0.5151,
      "step": 44417
    },
    {
      "epoch": 1.3644825361717814,
      "grad_norm": 0.4144459366798401,
      "learning_rate": 4.595735674444103e-06,
      "loss": 0.513,
      "step": 44418
    },
    {
      "epoch": 1.3645132553067305,
      "grad_norm": 0.43003252148628235,
      "learning_rate": 4.595329055422865e-06,
      "loss": 0.4863,
      "step": 44419
    },
    {
      "epoch": 1.3645439744416796,
      "grad_norm": 0.4326900541782379,
      "learning_rate": 4.594922449024608e-06,
      "loss": 0.4581,
      "step": 44420
    },
    {
      "epoch": 1.3645746935766287,
      "grad_norm": 0.45048031210899353,
      "learning_rate": 4.594515855250289e-06,
      "loss": 0.4719,
      "step": 44421
    },
    {
      "epoch": 1.364605412711578,
      "grad_norm": 0.3882807493209839,
      "learning_rate": 4.594109274100854e-06,
      "loss": 0.434,
      "step": 44422
    },
    {
      "epoch": 1.3646361318465272,
      "grad_norm": 0.41612550616264343,
      "learning_rate": 4.593702705577259e-06,
      "loss": 0.5198,
      "step": 44423
    },
    {
      "epoch": 1.3646668509814763,
      "grad_norm": 0.41923612356185913,
      "learning_rate": 4.593296149680445e-06,
      "loss": 0.5252,
      "step": 44424
    },
    {
      "epoch": 1.3646975701164255,
      "grad_norm": 0.4037860333919525,
      "learning_rate": 4.592889606411366e-06,
      "loss": 0.4887,
      "step": 44425
    },
    {
      "epoch": 1.3647282892513748,
      "grad_norm": 0.3773675858974457,
      "learning_rate": 4.59248307577097e-06,
      "loss": 0.5188,
      "step": 44426
    },
    {
      "epoch": 1.364759008386324,
      "grad_norm": 0.43822088837623596,
      "learning_rate": 4.592076557760211e-06,
      "loss": 0.4852,
      "step": 44427
    },
    {
      "epoch": 1.364789727521273,
      "grad_norm": 0.4035668671131134,
      "learning_rate": 4.591670052380031e-06,
      "loss": 0.4864,
      "step": 44428
    },
    {
      "epoch": 1.3648204466562222,
      "grad_norm": 0.4125800132751465,
      "learning_rate": 4.591263559631385e-06,
      "loss": 0.4376,
      "step": 44429
    },
    {
      "epoch": 1.3648511657911713,
      "grad_norm": 0.41456708312034607,
      "learning_rate": 4.59085707951522e-06,
      "loss": 0.4942,
      "step": 44430
    },
    {
      "epoch": 1.3648818849261204,
      "grad_norm": 0.41755786538124084,
      "learning_rate": 4.590450612032486e-06,
      "loss": 0.4789,
      "step": 44431
    },
    {
      "epoch": 1.3649126040610695,
      "grad_norm": 0.38559070229530334,
      "learning_rate": 4.590044157184136e-06,
      "loss": 0.4619,
      "step": 44432
    },
    {
      "epoch": 1.3649433231960189,
      "grad_norm": 0.39190995693206787,
      "learning_rate": 4.589637714971112e-06,
      "loss": 0.4729,
      "step": 44433
    },
    {
      "epoch": 1.364974042330968,
      "grad_norm": 0.42061322927474976,
      "learning_rate": 4.589231285394367e-06,
      "loss": 0.5284,
      "step": 44434
    },
    {
      "epoch": 1.365004761465917,
      "grad_norm": 0.45155811309814453,
      "learning_rate": 4.58882486845485e-06,
      "loss": 0.5003,
      "step": 44435
    },
    {
      "epoch": 1.3650354806008662,
      "grad_norm": 0.4299861490726471,
      "learning_rate": 4.588418464153514e-06,
      "loss": 0.4244,
      "step": 44436
    },
    {
      "epoch": 1.3650661997358156,
      "grad_norm": 0.4239940345287323,
      "learning_rate": 4.588012072491302e-06,
      "loss": 0.4456,
      "step": 44437
    },
    {
      "epoch": 1.3650969188707647,
      "grad_norm": 0.4166685938835144,
      "learning_rate": 4.5876056934691675e-06,
      "loss": 0.4963,
      "step": 44438
    },
    {
      "epoch": 1.3651276380057138,
      "grad_norm": 0.45987942814826965,
      "learning_rate": 4.587199327088051e-06,
      "loss": 0.4123,
      "step": 44439
    },
    {
      "epoch": 1.365158357140663,
      "grad_norm": 0.43829345703125,
      "learning_rate": 4.586792973348917e-06,
      "loss": 0.4342,
      "step": 44440
    },
    {
      "epoch": 1.365189076275612,
      "grad_norm": 0.5582181215286255,
      "learning_rate": 4.586386632252702e-06,
      "loss": 0.5549,
      "step": 44441
    },
    {
      "epoch": 1.3652197954105612,
      "grad_norm": 0.429191529750824,
      "learning_rate": 4.585980303800362e-06,
      "loss": 0.528,
      "step": 44442
    },
    {
      "epoch": 1.3652505145455103,
      "grad_norm": 0.384917676448822,
      "learning_rate": 4.585573987992837e-06,
      "loss": 0.5582,
      "step": 44443
    },
    {
      "epoch": 1.3652812336804596,
      "grad_norm": 0.4242982566356659,
      "learning_rate": 4.585167684831089e-06,
      "loss": 0.4438,
      "step": 44444
    },
    {
      "epoch": 1.3653119528154087,
      "grad_norm": 0.46113157272338867,
      "learning_rate": 4.584761394316056e-06,
      "loss": 0.4372,
      "step": 44445
    },
    {
      "epoch": 1.3653426719503579,
      "grad_norm": 0.45579349994659424,
      "learning_rate": 4.584355116448695e-06,
      "loss": 0.4903,
      "step": 44446
    },
    {
      "epoch": 1.365373391085307,
      "grad_norm": 0.41458338499069214,
      "learning_rate": 4.583948851229947e-06,
      "loss": 0.4733,
      "step": 44447
    },
    {
      "epoch": 1.3654041102202563,
      "grad_norm": 0.4189148545265198,
      "learning_rate": 4.583542598660765e-06,
      "loss": 0.4553,
      "step": 44448
    },
    {
      "epoch": 1.3654348293552054,
      "grad_norm": 0.44363343715667725,
      "learning_rate": 4.583136358742098e-06,
      "loss": 0.504,
      "step": 44449
    },
    {
      "epoch": 1.3654655484901546,
      "grad_norm": 0.4717992842197418,
      "learning_rate": 4.582730131474893e-06,
      "loss": 0.4682,
      "step": 44450
    },
    {
      "epoch": 1.3654962676251037,
      "grad_norm": 0.41484394669532776,
      "learning_rate": 4.5823239168601045e-06,
      "loss": 0.4437,
      "step": 44451
    },
    {
      "epoch": 1.3655269867600528,
      "grad_norm": 0.4112108051776886,
      "learning_rate": 4.581917714898673e-06,
      "loss": 0.52,
      "step": 44452
    },
    {
      "epoch": 1.365557705895002,
      "grad_norm": 0.39443960785865784,
      "learning_rate": 4.581511525591551e-06,
      "loss": 0.4602,
      "step": 44453
    },
    {
      "epoch": 1.365588425029951,
      "grad_norm": 0.7823474407196045,
      "learning_rate": 4.581105348939687e-06,
      "loss": 0.4446,
      "step": 44454
    },
    {
      "epoch": 1.3656191441649004,
      "grad_norm": 0.43178364634513855,
      "learning_rate": 4.580699184944034e-06,
      "loss": 0.5246,
      "step": 44455
    },
    {
      "epoch": 1.3656498632998495,
      "grad_norm": 0.49086108803749084,
      "learning_rate": 4.580293033605533e-06,
      "loss": 0.4566,
      "step": 44456
    },
    {
      "epoch": 1.3656805824347986,
      "grad_norm": 0.39769843220710754,
      "learning_rate": 4.579886894925136e-06,
      "loss": 0.5006,
      "step": 44457
    },
    {
      "epoch": 1.3657113015697477,
      "grad_norm": 0.4564206302165985,
      "learning_rate": 4.579480768903791e-06,
      "loss": 0.4446,
      "step": 44458
    },
    {
      "epoch": 1.365742020704697,
      "grad_norm": 0.4119793176651001,
      "learning_rate": 4.579074655542453e-06,
      "loss": 0.4685,
      "step": 44459
    },
    {
      "epoch": 1.3657727398396462,
      "grad_norm": 0.4235181212425232,
      "learning_rate": 4.578668554842059e-06,
      "loss": 0.4635,
      "step": 44460
    },
    {
      "epoch": 1.3658034589745953,
      "grad_norm": 0.41025272011756897,
      "learning_rate": 4.578262466803564e-06,
      "loss": 0.493,
      "step": 44461
    },
    {
      "epoch": 1.3658341781095444,
      "grad_norm": 0.4402574598789215,
      "learning_rate": 4.577856391427915e-06,
      "loss": 0.4299,
      "step": 44462
    },
    {
      "epoch": 1.3658648972444936,
      "grad_norm": 0.44493767619132996,
      "learning_rate": 4.577450328716066e-06,
      "loss": 0.4466,
      "step": 44463
    },
    {
      "epoch": 1.3658956163794427,
      "grad_norm": 0.4614555537700653,
      "learning_rate": 4.577044278668956e-06,
      "loss": 0.5032,
      "step": 44464
    },
    {
      "epoch": 1.3659263355143918,
      "grad_norm": 0.42071533203125,
      "learning_rate": 4.576638241287538e-06,
      "loss": 0.427,
      "step": 44465
    },
    {
      "epoch": 1.3659570546493411,
      "grad_norm": 0.41997525095939636,
      "learning_rate": 4.576232216572761e-06,
      "loss": 0.5789,
      "step": 44466
    },
    {
      "epoch": 1.3659877737842903,
      "grad_norm": 0.4623042345046997,
      "learning_rate": 4.57582620452557e-06,
      "loss": 0.4569,
      "step": 44467
    },
    {
      "epoch": 1.3660184929192394,
      "grad_norm": 0.40607407689094543,
      "learning_rate": 4.575420205146921e-06,
      "loss": 0.4691,
      "step": 44468
    },
    {
      "epoch": 1.3660492120541885,
      "grad_norm": 0.4523374140262604,
      "learning_rate": 4.575014218437753e-06,
      "loss": 0.4445,
      "step": 44469
    },
    {
      "epoch": 1.3660799311891378,
      "grad_norm": 0.4241962432861328,
      "learning_rate": 4.574608244399018e-06,
      "loss": 0.4776,
      "step": 44470
    },
    {
      "epoch": 1.366110650324087,
      "grad_norm": 0.4200686514377594,
      "learning_rate": 4.574202283031666e-06,
      "loss": 0.4668,
      "step": 44471
    },
    {
      "epoch": 1.366141369459036,
      "grad_norm": 0.4539892375469208,
      "learning_rate": 4.573796334336645e-06,
      "loss": 0.4357,
      "step": 44472
    },
    {
      "epoch": 1.3661720885939852,
      "grad_norm": 0.4369277358055115,
      "learning_rate": 4.573390398314898e-06,
      "loss": 0.4497,
      "step": 44473
    },
    {
      "epoch": 1.3662028077289343,
      "grad_norm": 0.3853026032447815,
      "learning_rate": 4.572984474967382e-06,
      "loss": 0.4788,
      "step": 44474
    },
    {
      "epoch": 1.3662335268638834,
      "grad_norm": 0.40700584650039673,
      "learning_rate": 4.5725785642950315e-06,
      "loss": 0.5067,
      "step": 44475
    },
    {
      "epoch": 1.3662642459988326,
      "grad_norm": 0.43693891167640686,
      "learning_rate": 4.572172666298811e-06,
      "loss": 0.4511,
      "step": 44476
    },
    {
      "epoch": 1.366294965133782,
      "grad_norm": 0.4097098112106323,
      "learning_rate": 4.571766780979655e-06,
      "loss": 0.4077,
      "step": 44477
    },
    {
      "epoch": 1.366325684268731,
      "grad_norm": 0.4130264222621918,
      "learning_rate": 4.571360908338521e-06,
      "loss": 0.4408,
      "step": 44478
    },
    {
      "epoch": 1.3663564034036801,
      "grad_norm": 0.45405876636505127,
      "learning_rate": 4.57095504837635e-06,
      "loss": 0.471,
      "step": 44479
    },
    {
      "epoch": 1.3663871225386293,
      "grad_norm": 0.4008364677429199,
      "learning_rate": 4.570549201094092e-06,
      "loss": 0.4654,
      "step": 44480
    },
    {
      "epoch": 1.3664178416735786,
      "grad_norm": 0.4939987361431122,
      "learning_rate": 4.570143366492697e-06,
      "loss": 0.4555,
      "step": 44481
    },
    {
      "epoch": 1.3664485608085277,
      "grad_norm": 0.573939859867096,
      "learning_rate": 4.569737544573113e-06,
      "loss": 0.3125,
      "step": 44482
    },
    {
      "epoch": 1.3664792799434768,
      "grad_norm": 0.3888085186481476,
      "learning_rate": 4.569331735336283e-06,
      "loss": 0.4526,
      "step": 44483
    },
    {
      "epoch": 1.366509999078426,
      "grad_norm": 0.4085579812526703,
      "learning_rate": 4.568925938783158e-06,
      "loss": 0.5195,
      "step": 44484
    },
    {
      "epoch": 1.366540718213375,
      "grad_norm": 0.40399786829948425,
      "learning_rate": 4.568520154914686e-06,
      "loss": 0.5523,
      "step": 44485
    },
    {
      "epoch": 1.3665714373483242,
      "grad_norm": 0.37049466371536255,
      "learning_rate": 4.568114383731814e-06,
      "loss": 0.4478,
      "step": 44486
    },
    {
      "epoch": 1.3666021564832733,
      "grad_norm": 0.4512999355792999,
      "learning_rate": 4.567708625235495e-06,
      "loss": 0.5571,
      "step": 44487
    },
    {
      "epoch": 1.3666328756182227,
      "grad_norm": 0.424012154340744,
      "learning_rate": 4.567302879426667e-06,
      "loss": 0.4314,
      "step": 44488
    },
    {
      "epoch": 1.3666635947531718,
      "grad_norm": 0.44172701239585876,
      "learning_rate": 4.566897146306284e-06,
      "loss": 0.5232,
      "step": 44489
    },
    {
      "epoch": 1.366694313888121,
      "grad_norm": 0.4076956808567047,
      "learning_rate": 4.566491425875292e-06,
      "loss": 0.4018,
      "step": 44490
    },
    {
      "epoch": 1.36672503302307,
      "grad_norm": 0.4406101405620575,
      "learning_rate": 4.56608571813464e-06,
      "loss": 0.484,
      "step": 44491
    },
    {
      "epoch": 1.3667557521580194,
      "grad_norm": 0.4556184411048889,
      "learning_rate": 4.565680023085273e-06,
      "loss": 0.4356,
      "step": 44492
    },
    {
      "epoch": 1.3667864712929685,
      "grad_norm": 0.4106696546077728,
      "learning_rate": 4.56527434072814e-06,
      "loss": 0.4855,
      "step": 44493
    },
    {
      "epoch": 1.3668171904279176,
      "grad_norm": 0.42328155040740967,
      "learning_rate": 4.564868671064186e-06,
      "loss": 0.4757,
      "step": 44494
    },
    {
      "epoch": 1.3668479095628667,
      "grad_norm": 0.41298189759254456,
      "learning_rate": 4.564463014094367e-06,
      "loss": 0.4641,
      "step": 44495
    },
    {
      "epoch": 1.3668786286978158,
      "grad_norm": 0.38517001271247864,
      "learning_rate": 4.564057369819619e-06,
      "loss": 0.4395,
      "step": 44496
    },
    {
      "epoch": 1.366909347832765,
      "grad_norm": 0.4359949231147766,
      "learning_rate": 4.563651738240895e-06,
      "loss": 0.4666,
      "step": 44497
    },
    {
      "epoch": 1.366940066967714,
      "grad_norm": 0.4028003215789795,
      "learning_rate": 4.563246119359143e-06,
      "loss": 0.4695,
      "step": 44498
    },
    {
      "epoch": 1.3669707861026634,
      "grad_norm": 0.43857645988464355,
      "learning_rate": 4.562840513175312e-06,
      "loss": 0.5186,
      "step": 44499
    },
    {
      "epoch": 1.3670015052376125,
      "grad_norm": 0.43080589175224304,
      "learning_rate": 4.5624349196903436e-06,
      "loss": 0.4574,
      "step": 44500
    },
    {
      "epoch": 1.3670322243725617,
      "grad_norm": 0.42785587906837463,
      "learning_rate": 4.562029338905192e-06,
      "loss": 0.501,
      "step": 44501
    },
    {
      "epoch": 1.3670629435075108,
      "grad_norm": 0.4195992648601532,
      "learning_rate": 4.561623770820792e-06,
      "loss": 0.4747,
      "step": 44502
    },
    {
      "epoch": 1.36709366264246,
      "grad_norm": 0.4050350785255432,
      "learning_rate": 4.561218215438104e-06,
      "loss": 0.4697,
      "step": 44503
    },
    {
      "epoch": 1.3671243817774092,
      "grad_norm": 0.39766210317611694,
      "learning_rate": 4.560812672758075e-06,
      "loss": 0.4872,
      "step": 44504
    },
    {
      "epoch": 1.3671551009123584,
      "grad_norm": 0.4602615535259247,
      "learning_rate": 4.560407142781643e-06,
      "loss": 0.5,
      "step": 44505
    },
    {
      "epoch": 1.3671858200473075,
      "grad_norm": 0.4468458294868469,
      "learning_rate": 4.560001625509761e-06,
      "loss": 0.4737,
      "step": 44506
    },
    {
      "epoch": 1.3672165391822566,
      "grad_norm": 0.4517909288406372,
      "learning_rate": 4.559596120943375e-06,
      "loss": 0.5125,
      "step": 44507
    },
    {
      "epoch": 1.3672472583172057,
      "grad_norm": 0.4278491139411926,
      "learning_rate": 4.559190629083436e-06,
      "loss": 0.4521,
      "step": 44508
    },
    {
      "epoch": 1.3672779774521548,
      "grad_norm": 0.4651806950569153,
      "learning_rate": 4.558785149930883e-06,
      "loss": 0.4271,
      "step": 44509
    },
    {
      "epoch": 1.3673086965871042,
      "grad_norm": 0.42029672861099243,
      "learning_rate": 4.558379683486671e-06,
      "loss": 0.4988,
      "step": 44510
    },
    {
      "epoch": 1.3673394157220533,
      "grad_norm": 0.40979132056236267,
      "learning_rate": 4.557974229751737e-06,
      "loss": 0.4491,
      "step": 44511
    },
    {
      "epoch": 1.3673701348570024,
      "grad_norm": 0.4444187581539154,
      "learning_rate": 4.557568788727041e-06,
      "loss": 0.4505,
      "step": 44512
    },
    {
      "epoch": 1.3674008539919515,
      "grad_norm": 0.40972039103507996,
      "learning_rate": 4.557163360413519e-06,
      "loss": 0.442,
      "step": 44513
    },
    {
      "epoch": 1.3674315731269007,
      "grad_norm": 0.43340808153152466,
      "learning_rate": 4.556757944812126e-06,
      "loss": 0.4987,
      "step": 44514
    },
    {
      "epoch": 1.36746229226185,
      "grad_norm": 0.4114004373550415,
      "learning_rate": 4.556352541923801e-06,
      "loss": 0.5131,
      "step": 44515
    },
    {
      "epoch": 1.3674930113967991,
      "grad_norm": 0.4682486057281494,
      "learning_rate": 4.555947151749496e-06,
      "loss": 0.4288,
      "step": 44516
    },
    {
      "epoch": 1.3675237305317482,
      "grad_norm": 0.49988842010498047,
      "learning_rate": 4.555541774290155e-06,
      "loss": 0.4234,
      "step": 44517
    },
    {
      "epoch": 1.3675544496666974,
      "grad_norm": 0.4424873888492584,
      "learning_rate": 4.555136409546731e-06,
      "loss": 0.4433,
      "step": 44518
    },
    {
      "epoch": 1.3675851688016465,
      "grad_norm": 0.4397011995315552,
      "learning_rate": 4.554731057520163e-06,
      "loss": 0.3989,
      "step": 44519
    },
    {
      "epoch": 1.3676158879365956,
      "grad_norm": 0.4150937497615814,
      "learning_rate": 4.5543257182114e-06,
      "loss": 0.4553,
      "step": 44520
    },
    {
      "epoch": 1.3676466070715447,
      "grad_norm": 0.3889758586883545,
      "learning_rate": 4.553920391621391e-06,
      "loss": 0.4621,
      "step": 44521
    },
    {
      "epoch": 1.367677326206494,
      "grad_norm": 0.46637511253356934,
      "learning_rate": 4.553515077751079e-06,
      "loss": 0.3594,
      "step": 44522
    },
    {
      "epoch": 1.3677080453414432,
      "grad_norm": 0.42332834005355835,
      "learning_rate": 4.553109776601418e-06,
      "loss": 0.5068,
      "step": 44523
    },
    {
      "epoch": 1.3677387644763923,
      "grad_norm": 0.39499378204345703,
      "learning_rate": 4.552704488173346e-06,
      "loss": 0.5028,
      "step": 44524
    },
    {
      "epoch": 1.3677694836113414,
      "grad_norm": 0.3924158811569214,
      "learning_rate": 4.552299212467813e-06,
      "loss": 0.5022,
      "step": 44525
    },
    {
      "epoch": 1.3678002027462908,
      "grad_norm": 0.46544671058654785,
      "learning_rate": 4.551893949485765e-06,
      "loss": 0.465,
      "step": 44526
    },
    {
      "epoch": 1.36783092188124,
      "grad_norm": 0.3900180757045746,
      "learning_rate": 4.5514886992281536e-06,
      "loss": 0.4208,
      "step": 44527
    },
    {
      "epoch": 1.367861641016189,
      "grad_norm": 0.40676796436309814,
      "learning_rate": 4.551083461695917e-06,
      "loss": 0.4614,
      "step": 44528
    },
    {
      "epoch": 1.3678923601511381,
      "grad_norm": 0.47431206703186035,
      "learning_rate": 4.550678236890005e-06,
      "loss": 0.4649,
      "step": 44529
    },
    {
      "epoch": 1.3679230792860873,
      "grad_norm": 0.41891857981681824,
      "learning_rate": 4.550273024811365e-06,
      "loss": 0.4999,
      "step": 44530
    },
    {
      "epoch": 1.3679537984210364,
      "grad_norm": 0.47606566548347473,
      "learning_rate": 4.549867825460946e-06,
      "loss": 0.5287,
      "step": 44531
    },
    {
      "epoch": 1.3679845175559855,
      "grad_norm": 0.39842498302459717,
      "learning_rate": 4.549462638839689e-06,
      "loss": 0.4878,
      "step": 44532
    },
    {
      "epoch": 1.3680152366909348,
      "grad_norm": 0.4369889199733734,
      "learning_rate": 4.549057464948542e-06,
      "loss": 0.5255,
      "step": 44533
    },
    {
      "epoch": 1.368045955825884,
      "grad_norm": 0.37766969203948975,
      "learning_rate": 4.548652303788451e-06,
      "loss": 0.4508,
      "step": 44534
    },
    {
      "epoch": 1.368076674960833,
      "grad_norm": 0.39284858107566833,
      "learning_rate": 4.548247155360368e-06,
      "loss": 0.4368,
      "step": 44535
    },
    {
      "epoch": 1.3681073940957822,
      "grad_norm": 0.38761192560195923,
      "learning_rate": 4.547842019665231e-06,
      "loss": 0.4887,
      "step": 44536
    },
    {
      "epoch": 1.3681381132307315,
      "grad_norm": 0.4201050400733948,
      "learning_rate": 4.547436896703993e-06,
      "loss": 0.5044,
      "step": 44537
    },
    {
      "epoch": 1.3681688323656807,
      "grad_norm": 0.4205601215362549,
      "learning_rate": 4.547031786477589e-06,
      "loss": 0.4646,
      "step": 44538
    },
    {
      "epoch": 1.3681995515006298,
      "grad_norm": 0.38780179619789124,
      "learning_rate": 4.5466266889869815e-06,
      "loss": 0.5155,
      "step": 44539
    },
    {
      "epoch": 1.368230270635579,
      "grad_norm": 0.3921576738357544,
      "learning_rate": 4.546221604233104e-06,
      "loss": 0.4068,
      "step": 44540
    },
    {
      "epoch": 1.368260989770528,
      "grad_norm": 0.4152594804763794,
      "learning_rate": 4.545816532216908e-06,
      "loss": 0.4329,
      "step": 44541
    },
    {
      "epoch": 1.3682917089054771,
      "grad_norm": 0.4422242045402527,
      "learning_rate": 4.545411472939341e-06,
      "loss": 0.6024,
      "step": 44542
    },
    {
      "epoch": 1.3683224280404263,
      "grad_norm": 0.44536328315734863,
      "learning_rate": 4.5450064264013385e-06,
      "loss": 0.5037,
      "step": 44543
    },
    {
      "epoch": 1.3683531471753756,
      "grad_norm": 0.4381020963191986,
      "learning_rate": 4.544601392603862e-06,
      "loss": 0.4512,
      "step": 44544
    },
    {
      "epoch": 1.3683838663103247,
      "grad_norm": 0.4137383699417114,
      "learning_rate": 4.5441963715478475e-06,
      "loss": 0.4529,
      "step": 44545
    },
    {
      "epoch": 1.3684145854452738,
      "grad_norm": 0.3900020122528076,
      "learning_rate": 4.543791363234246e-06,
      "loss": 0.5126,
      "step": 44546
    },
    {
      "epoch": 1.368445304580223,
      "grad_norm": 0.375931978225708,
      "learning_rate": 4.543386367663995e-06,
      "loss": 0.472,
      "step": 44547
    },
    {
      "epoch": 1.3684760237151723,
      "grad_norm": 0.3706730604171753,
      "learning_rate": 4.542981384838051e-06,
      "loss": 0.4656,
      "step": 44548
    },
    {
      "epoch": 1.3685067428501214,
      "grad_norm": 0.9299081563949585,
      "learning_rate": 4.542576414757352e-06,
      "loss": 0.435,
      "step": 44549
    },
    {
      "epoch": 1.3685374619850705,
      "grad_norm": 0.4136931300163269,
      "learning_rate": 4.542171457422853e-06,
      "loss": 0.4318,
      "step": 44550
    },
    {
      "epoch": 1.3685681811200197,
      "grad_norm": 0.401402086019516,
      "learning_rate": 4.541766512835488e-06,
      "loss": 0.4954,
      "step": 44551
    },
    {
      "epoch": 1.3685989002549688,
      "grad_norm": 0.4479735493659973,
      "learning_rate": 4.541361580996208e-06,
      "loss": 0.503,
      "step": 44552
    },
    {
      "epoch": 1.368629619389918,
      "grad_norm": 0.4333696961402893,
      "learning_rate": 4.540956661905961e-06,
      "loss": 0.5069,
      "step": 44553
    },
    {
      "epoch": 1.368660338524867,
      "grad_norm": 0.5072672963142395,
      "learning_rate": 4.540551755565694e-06,
      "loss": 0.4584,
      "step": 44554
    },
    {
      "epoch": 1.3686910576598164,
      "grad_norm": 0.4484601318836212,
      "learning_rate": 4.540146861976346e-06,
      "loss": 0.4995,
      "step": 44555
    },
    {
      "epoch": 1.3687217767947655,
      "grad_norm": 0.3983471393585205,
      "learning_rate": 4.539741981138866e-06,
      "loss": 0.4587,
      "step": 44556
    },
    {
      "epoch": 1.3687524959297146,
      "grad_norm": 0.48983997106552124,
      "learning_rate": 4.539337113054199e-06,
      "loss": 0.4065,
      "step": 44557
    },
    {
      "epoch": 1.3687832150646637,
      "grad_norm": 0.40966951847076416,
      "learning_rate": 4.538932257723293e-06,
      "loss": 0.4126,
      "step": 44558
    },
    {
      "epoch": 1.368813934199613,
      "grad_norm": 0.4287468492984772,
      "learning_rate": 4.538527415147096e-06,
      "loss": 0.5017,
      "step": 44559
    },
    {
      "epoch": 1.3688446533345622,
      "grad_norm": 0.38730043172836304,
      "learning_rate": 4.5381225853265455e-06,
      "loss": 0.48,
      "step": 44560
    },
    {
      "epoch": 1.3688753724695113,
      "grad_norm": 0.40238842368125916,
      "learning_rate": 4.53771776826259e-06,
      "loss": 0.4375,
      "step": 44561
    },
    {
      "epoch": 1.3689060916044604,
      "grad_norm": 0.4347093403339386,
      "learning_rate": 4.5373129639561785e-06,
      "loss": 0.48,
      "step": 44562
    },
    {
      "epoch": 1.3689368107394095,
      "grad_norm": 0.4236440658569336,
      "learning_rate": 4.5369081724082565e-06,
      "loss": 0.5081,
      "step": 44563
    },
    {
      "epoch": 1.3689675298743587,
      "grad_norm": 0.46207645535469055,
      "learning_rate": 4.5365033936197634e-06,
      "loss": 0.4454,
      "step": 44564
    },
    {
      "epoch": 1.3689982490093078,
      "grad_norm": 0.4348282814025879,
      "learning_rate": 4.536098627591647e-06,
      "loss": 0.3821,
      "step": 44565
    },
    {
      "epoch": 1.3690289681442571,
      "grad_norm": 0.40871191024780273,
      "learning_rate": 4.535693874324856e-06,
      "loss": 0.5474,
      "step": 44566
    },
    {
      "epoch": 1.3690596872792062,
      "grad_norm": 0.48212093114852905,
      "learning_rate": 4.535289133820335e-06,
      "loss": 0.508,
      "step": 44567
    },
    {
      "epoch": 1.3690904064141554,
      "grad_norm": 0.4216286242008209,
      "learning_rate": 4.534884406079026e-06,
      "loss": 0.497,
      "step": 44568
    },
    {
      "epoch": 1.3691211255491045,
      "grad_norm": 0.4058833420276642,
      "learning_rate": 4.534479691101875e-06,
      "loss": 0.5052,
      "step": 44569
    },
    {
      "epoch": 1.3691518446840538,
      "grad_norm": 0.4067830443382263,
      "learning_rate": 4.534074988889829e-06,
      "loss": 0.4402,
      "step": 44570
    },
    {
      "epoch": 1.369182563819003,
      "grad_norm": 0.42945683002471924,
      "learning_rate": 4.533670299443836e-06,
      "loss": 0.4494,
      "step": 44571
    },
    {
      "epoch": 1.369213282953952,
      "grad_norm": 0.44513097405433655,
      "learning_rate": 4.533265622764834e-06,
      "loss": 0.5028,
      "step": 44572
    },
    {
      "epoch": 1.3692440020889012,
      "grad_norm": 0.4022018313407898,
      "learning_rate": 4.5328609588537765e-06,
      "loss": 0.4842,
      "step": 44573
    },
    {
      "epoch": 1.3692747212238503,
      "grad_norm": 0.6795947551727295,
      "learning_rate": 4.532456307711596e-06,
      "loss": 0.5142,
      "step": 44574
    },
    {
      "epoch": 1.3693054403587994,
      "grad_norm": 0.4103456437587738,
      "learning_rate": 4.532051669339254e-06,
      "loss": 0.4593,
      "step": 44575
    },
    {
      "epoch": 1.3693361594937485,
      "grad_norm": 0.6297987699508667,
      "learning_rate": 4.5316470437376814e-06,
      "loss": 0.4001,
      "step": 44576
    },
    {
      "epoch": 1.3693668786286979,
      "grad_norm": 0.42600953578948975,
      "learning_rate": 4.53124243090783e-06,
      "loss": 0.3846,
      "step": 44577
    },
    {
      "epoch": 1.369397597763647,
      "grad_norm": 0.4527418315410614,
      "learning_rate": 4.530837830850648e-06,
      "loss": 0.4245,
      "step": 44578
    },
    {
      "epoch": 1.3694283168985961,
      "grad_norm": 0.3766458332538605,
      "learning_rate": 4.530433243567069e-06,
      "loss": 0.4472,
      "step": 44579
    },
    {
      "epoch": 1.3694590360335452,
      "grad_norm": 0.42127907276153564,
      "learning_rate": 4.530028669058052e-06,
      "loss": 0.4362,
      "step": 44580
    },
    {
      "epoch": 1.3694897551684946,
      "grad_norm": 0.4115060269832611,
      "learning_rate": 4.5296241073245315e-06,
      "loss": 0.4453,
      "step": 44581
    },
    {
      "epoch": 1.3695204743034437,
      "grad_norm": 0.4321730136871338,
      "learning_rate": 4.5292195583674605e-06,
      "loss": 0.462,
      "step": 44582
    },
    {
      "epoch": 1.3695511934383928,
      "grad_norm": 0.43043187260627747,
      "learning_rate": 4.528815022187774e-06,
      "loss": 0.3909,
      "step": 44583
    },
    {
      "epoch": 1.369581912573342,
      "grad_norm": 0.4092103838920593,
      "learning_rate": 4.528410498786423e-06,
      "loss": 0.5344,
      "step": 44584
    },
    {
      "epoch": 1.369612631708291,
      "grad_norm": 0.40736547112464905,
      "learning_rate": 4.528005988164351e-06,
      "loss": 0.5053,
      "step": 44585
    },
    {
      "epoch": 1.3696433508432402,
      "grad_norm": 0.4452211856842041,
      "learning_rate": 4.5276014903225076e-06,
      "loss": 0.4419,
      "step": 44586
    },
    {
      "epoch": 1.3696740699781893,
      "grad_norm": 0.3947588801383972,
      "learning_rate": 4.5271970052618286e-06,
      "loss": 0.4551,
      "step": 44587
    },
    {
      "epoch": 1.3697047891131386,
      "grad_norm": 0.4626825451850891,
      "learning_rate": 4.526792532983264e-06,
      "loss": 0.5123,
      "step": 44588
    },
    {
      "epoch": 1.3697355082480878,
      "grad_norm": 0.402420312166214,
      "learning_rate": 4.526388073487756e-06,
      "loss": 0.5079,
      "step": 44589
    },
    {
      "epoch": 1.3697662273830369,
      "grad_norm": 0.3925321102142334,
      "learning_rate": 4.525983626776257e-06,
      "loss": 0.4698,
      "step": 44590
    },
    {
      "epoch": 1.369796946517986,
      "grad_norm": 0.408128023147583,
      "learning_rate": 4.5255791928497005e-06,
      "loss": 0.512,
      "step": 44591
    },
    {
      "epoch": 1.3698276656529353,
      "grad_norm": 0.412779837846756,
      "learning_rate": 4.525174771709036e-06,
      "loss": 0.4968,
      "step": 44592
    },
    {
      "epoch": 1.3698583847878845,
      "grad_norm": 0.39795050024986267,
      "learning_rate": 4.524770363355209e-06,
      "loss": 0.4856,
      "step": 44593
    },
    {
      "epoch": 1.3698891039228336,
      "grad_norm": 0.44005823135375977,
      "learning_rate": 4.524365967789166e-06,
      "loss": 0.4969,
      "step": 44594
    },
    {
      "epoch": 1.3699198230577827,
      "grad_norm": 0.41985243558883667,
      "learning_rate": 4.523961585011846e-06,
      "loss": 0.395,
      "step": 44595
    },
    {
      "epoch": 1.3699505421927318,
      "grad_norm": 0.40314972400665283,
      "learning_rate": 4.523557215024194e-06,
      "loss": 0.4529,
      "step": 44596
    },
    {
      "epoch": 1.369981261327681,
      "grad_norm": 0.4653807580471039,
      "learning_rate": 4.523152857827159e-06,
      "loss": 0.4821,
      "step": 44597
    },
    {
      "epoch": 1.37001198046263,
      "grad_norm": 0.4239805340766907,
      "learning_rate": 4.522748513421682e-06,
      "loss": 0.4874,
      "step": 44598
    },
    {
      "epoch": 1.3700426995975794,
      "grad_norm": 0.4041738510131836,
      "learning_rate": 4.522344181808712e-06,
      "loss": 0.5112,
      "step": 44599
    },
    {
      "epoch": 1.3700734187325285,
      "grad_norm": 0.47050154209136963,
      "learning_rate": 4.521939862989186e-06,
      "loss": 0.4951,
      "step": 44600
    },
    {
      "epoch": 1.3701041378674776,
      "grad_norm": 0.4568730294704437,
      "learning_rate": 4.521535556964053e-06,
      "loss": 0.4833,
      "step": 44601
    },
    {
      "epoch": 1.3701348570024268,
      "grad_norm": 0.41526931524276733,
      "learning_rate": 4.521131263734255e-06,
      "loss": 0.4396,
      "step": 44602
    },
    {
      "epoch": 1.370165576137376,
      "grad_norm": 0.4042438566684723,
      "learning_rate": 4.520726983300743e-06,
      "loss": 0.4719,
      "step": 44603
    },
    {
      "epoch": 1.3701962952723252,
      "grad_norm": 0.42874494194984436,
      "learning_rate": 4.52032271566445e-06,
      "loss": 0.4478,
      "step": 44604
    },
    {
      "epoch": 1.3702270144072743,
      "grad_norm": 0.47481635212898254,
      "learning_rate": 4.5199184608263266e-06,
      "loss": 0.5222,
      "step": 44605
    },
    {
      "epoch": 1.3702577335422235,
      "grad_norm": 0.38450419902801514,
      "learning_rate": 4.519514218787317e-06,
      "loss": 0.4128,
      "step": 44606
    },
    {
      "epoch": 1.3702884526771726,
      "grad_norm": 0.4087352752685547,
      "learning_rate": 4.519109989548369e-06,
      "loss": 0.5205,
      "step": 44607
    },
    {
      "epoch": 1.3703191718121217,
      "grad_norm": 0.4229127764701843,
      "learning_rate": 4.518705773110418e-06,
      "loss": 0.5077,
      "step": 44608
    },
    {
      "epoch": 1.3703498909470708,
      "grad_norm": 0.40114304423332214,
      "learning_rate": 4.518301569474416e-06,
      "loss": 0.5186,
      "step": 44609
    },
    {
      "epoch": 1.3703806100820202,
      "grad_norm": 0.3710046112537384,
      "learning_rate": 4.517897378641296e-06,
      "loss": 0.3716,
      "step": 44610
    },
    {
      "epoch": 1.3704113292169693,
      "grad_norm": 0.3858729600906372,
      "learning_rate": 4.517493200612016e-06,
      "loss": 0.4632,
      "step": 44611
    },
    {
      "epoch": 1.3704420483519184,
      "grad_norm": 0.41939112544059753,
      "learning_rate": 4.517089035387512e-06,
      "loss": 0.4688,
      "step": 44612
    },
    {
      "epoch": 1.3704727674868675,
      "grad_norm": 0.38657042384147644,
      "learning_rate": 4.516684882968728e-06,
      "loss": 0.452,
      "step": 44613
    },
    {
      "epoch": 1.3705034866218166,
      "grad_norm": 0.48351460695266724,
      "learning_rate": 4.516280743356614e-06,
      "loss": 0.4936,
      "step": 44614
    },
    {
      "epoch": 1.370534205756766,
      "grad_norm": 0.40764936804771423,
      "learning_rate": 4.5158766165521004e-06,
      "loss": 0.5062,
      "step": 44615
    },
    {
      "epoch": 1.370564924891715,
      "grad_norm": 0.36248522996902466,
      "learning_rate": 4.515472502556149e-06,
      "loss": 0.4396,
      "step": 44616
    },
    {
      "epoch": 1.3705956440266642,
      "grad_norm": 0.45432519912719727,
      "learning_rate": 4.51506840136969e-06,
      "loss": 0.4187,
      "step": 44617
    },
    {
      "epoch": 1.3706263631616133,
      "grad_norm": 0.6033298373222351,
      "learning_rate": 4.514664312993675e-06,
      "loss": 0.4848,
      "step": 44618
    },
    {
      "epoch": 1.3706570822965625,
      "grad_norm": 0.40341201424598694,
      "learning_rate": 4.514260237429042e-06,
      "loss": 0.4656,
      "step": 44619
    },
    {
      "epoch": 1.3706878014315116,
      "grad_norm": 0.3809935748577118,
      "learning_rate": 4.5138561746767375e-06,
      "loss": 0.4887,
      "step": 44620
    },
    {
      "epoch": 1.370718520566461,
      "grad_norm": 0.4898863732814789,
      "learning_rate": 4.5134521247377035e-06,
      "loss": 0.4712,
      "step": 44621
    },
    {
      "epoch": 1.37074923970141,
      "grad_norm": 0.39775604009628296,
      "learning_rate": 4.513048087612891e-06,
      "loss": 0.5295,
      "step": 44622
    },
    {
      "epoch": 1.3707799588363592,
      "grad_norm": 0.45122355222702026,
      "learning_rate": 4.512644063303233e-06,
      "loss": 0.4515,
      "step": 44623
    },
    {
      "epoch": 1.3708106779713083,
      "grad_norm": 0.4199305772781372,
      "learning_rate": 4.512240051809677e-06,
      "loss": 0.4991,
      "step": 44624
    },
    {
      "epoch": 1.3708413971062574,
      "grad_norm": 0.4553629159927368,
      "learning_rate": 4.51183605313317e-06,
      "loss": 0.4693,
      "step": 44625
    },
    {
      "epoch": 1.3708721162412068,
      "grad_norm": 0.4135758876800537,
      "learning_rate": 4.511432067274656e-06,
      "loss": 0.5507,
      "step": 44626
    },
    {
      "epoch": 1.3709028353761559,
      "grad_norm": 0.4628138244152069,
      "learning_rate": 4.511028094235071e-06,
      "loss": 0.5241,
      "step": 44627
    },
    {
      "epoch": 1.370933554511105,
      "grad_norm": 0.45096978545188904,
      "learning_rate": 4.5106241340153645e-06,
      "loss": 0.481,
      "step": 44628
    },
    {
      "epoch": 1.370964273646054,
      "grad_norm": 0.4223839044570923,
      "learning_rate": 4.510220186616477e-06,
      "loss": 0.551,
      "step": 44629
    },
    {
      "epoch": 1.3709949927810032,
      "grad_norm": 0.5557958483695984,
      "learning_rate": 4.50981625203936e-06,
      "loss": 0.4639,
      "step": 44630
    },
    {
      "epoch": 1.3710257119159523,
      "grad_norm": 0.3991488516330719,
      "learning_rate": 4.5094123302849444e-06,
      "loss": 0.526,
      "step": 44631
    },
    {
      "epoch": 1.3710564310509015,
      "grad_norm": 0.41629815101623535,
      "learning_rate": 4.50900842135418e-06,
      "loss": 0.5073,
      "step": 44632
    },
    {
      "epoch": 1.3710871501858508,
      "grad_norm": 0.4086826741695404,
      "learning_rate": 4.508604525248012e-06,
      "loss": 0.4178,
      "step": 44633
    },
    {
      "epoch": 1.3711178693208,
      "grad_norm": 0.4749331772327423,
      "learning_rate": 4.50820064196738e-06,
      "loss": 0.4106,
      "step": 44634
    },
    {
      "epoch": 1.371148588455749,
      "grad_norm": 0.4729793965816498,
      "learning_rate": 4.507796771513233e-06,
      "loss": 0.5071,
      "step": 44635
    },
    {
      "epoch": 1.3711793075906982,
      "grad_norm": 0.47201865911483765,
      "learning_rate": 4.507392913886507e-06,
      "loss": 0.5555,
      "step": 44636
    },
    {
      "epoch": 1.3712100267256475,
      "grad_norm": 0.4389006197452545,
      "learning_rate": 4.506989069088148e-06,
      "loss": 0.5165,
      "step": 44637
    },
    {
      "epoch": 1.3712407458605966,
      "grad_norm": 0.4013577997684479,
      "learning_rate": 4.506585237119099e-06,
      "loss": 0.4058,
      "step": 44638
    },
    {
      "epoch": 1.3712714649955458,
      "grad_norm": 0.4091891050338745,
      "learning_rate": 4.5061814179803085e-06,
      "loss": 0.5679,
      "step": 44639
    },
    {
      "epoch": 1.3713021841304949,
      "grad_norm": 0.42207756638526917,
      "learning_rate": 4.5057776116727105e-06,
      "loss": 0.416,
      "step": 44640
    },
    {
      "epoch": 1.371332903265444,
      "grad_norm": 0.4067065119743347,
      "learning_rate": 4.505373818197258e-06,
      "loss": 0.4931,
      "step": 44641
    },
    {
      "epoch": 1.3713636224003931,
      "grad_norm": 0.41353169083595276,
      "learning_rate": 4.504970037554879e-06,
      "loss": 0.4126,
      "step": 44642
    },
    {
      "epoch": 1.3713943415353422,
      "grad_norm": 0.3750598132610321,
      "learning_rate": 4.5045662697465346e-06,
      "loss": 0.4128,
      "step": 44643
    },
    {
      "epoch": 1.3714250606702916,
      "grad_norm": 0.3884812593460083,
      "learning_rate": 4.504162514773156e-06,
      "loss": 0.5061,
      "step": 44644
    },
    {
      "epoch": 1.3714557798052407,
      "grad_norm": 0.47662878036499023,
      "learning_rate": 4.503758772635692e-06,
      "loss": 0.4677,
      "step": 44645
    },
    {
      "epoch": 1.3714864989401898,
      "grad_norm": 0.46483761072158813,
      "learning_rate": 4.503355043335078e-06,
      "loss": 0.468,
      "step": 44646
    },
    {
      "epoch": 1.371517218075139,
      "grad_norm": 0.38811931014060974,
      "learning_rate": 4.502951326872268e-06,
      "loss": 0.4257,
      "step": 44647
    },
    {
      "epoch": 1.3715479372100883,
      "grad_norm": 0.39576905965805054,
      "learning_rate": 4.502547623248196e-06,
      "loss": 0.5504,
      "step": 44648
    },
    {
      "epoch": 1.3715786563450374,
      "grad_norm": 0.45510995388031006,
      "learning_rate": 4.502143932463808e-06,
      "loss": 0.396,
      "step": 44649
    },
    {
      "epoch": 1.3716093754799865,
      "grad_norm": 0.4196687638759613,
      "learning_rate": 4.5017402545200504e-06,
      "loss": 0.4424,
      "step": 44650
    },
    {
      "epoch": 1.3716400946149356,
      "grad_norm": 0.40027332305908203,
      "learning_rate": 4.501336589417855e-06,
      "loss": 0.419,
      "step": 44651
    },
    {
      "epoch": 1.3716708137498848,
      "grad_norm": 0.4233124554157257,
      "learning_rate": 4.50093293715818e-06,
      "loss": 0.5432,
      "step": 44652
    },
    {
      "epoch": 1.3717015328848339,
      "grad_norm": 0.43019863963127136,
      "learning_rate": 4.500529297741955e-06,
      "loss": 0.4567,
      "step": 44653
    },
    {
      "epoch": 1.371732252019783,
      "grad_norm": 0.42186349630355835,
      "learning_rate": 4.500125671170133e-06,
      "loss": 0.3968,
      "step": 44654
    },
    {
      "epoch": 1.3717629711547323,
      "grad_norm": 0.4497595727443695,
      "learning_rate": 4.499722057443647e-06,
      "loss": 0.4871,
      "step": 44655
    },
    {
      "epoch": 1.3717936902896815,
      "grad_norm": 0.40033575892448425,
      "learning_rate": 4.499318456563445e-06,
      "loss": 0.53,
      "step": 44656
    },
    {
      "epoch": 1.3718244094246306,
      "grad_norm": 0.37428057193756104,
      "learning_rate": 4.498914868530469e-06,
      "loss": 0.4422,
      "step": 44657
    },
    {
      "epoch": 1.3718551285595797,
      "grad_norm": 0.42442643642425537,
      "learning_rate": 4.498511293345665e-06,
      "loss": 0.4664,
      "step": 44658
    },
    {
      "epoch": 1.371885847694529,
      "grad_norm": 0.4118792414665222,
      "learning_rate": 4.498107731009968e-06,
      "loss": 0.4774,
      "step": 44659
    },
    {
      "epoch": 1.3719165668294782,
      "grad_norm": 0.4260979890823364,
      "learning_rate": 4.497704181524325e-06,
      "loss": 0.4839,
      "step": 44660
    },
    {
      "epoch": 1.3719472859644273,
      "grad_norm": 0.4352834224700928,
      "learning_rate": 4.497300644889678e-06,
      "loss": 0.5304,
      "step": 44661
    },
    {
      "epoch": 1.3719780050993764,
      "grad_norm": 0.4393361508846283,
      "learning_rate": 4.496897121106974e-06,
      "loss": 0.4517,
      "step": 44662
    },
    {
      "epoch": 1.3720087242343255,
      "grad_norm": 0.38511261343955994,
      "learning_rate": 4.496493610177146e-06,
      "loss": 0.4418,
      "step": 44663
    },
    {
      "epoch": 1.3720394433692746,
      "grad_norm": 0.49071162939071655,
      "learning_rate": 4.496090112101142e-06,
      "loss": 0.4911,
      "step": 44664
    },
    {
      "epoch": 1.3720701625042238,
      "grad_norm": 0.4108554720878601,
      "learning_rate": 4.495686626879905e-06,
      "loss": 0.4504,
      "step": 44665
    },
    {
      "epoch": 1.372100881639173,
      "grad_norm": 0.4478440582752228,
      "learning_rate": 4.495283154514379e-06,
      "loss": 0.5604,
      "step": 44666
    },
    {
      "epoch": 1.3721316007741222,
      "grad_norm": 0.4205906391143799,
      "learning_rate": 4.4948796950055e-06,
      "loss": 0.5158,
      "step": 44667
    },
    {
      "epoch": 1.3721623199090713,
      "grad_norm": 0.41811344027519226,
      "learning_rate": 4.494476248354215e-06,
      "loss": 0.5398,
      "step": 44668
    },
    {
      "epoch": 1.3721930390440205,
      "grad_norm": 0.4178164601325989,
      "learning_rate": 4.494072814561464e-06,
      "loss": 0.422,
      "step": 44669
    },
    {
      "epoch": 1.3722237581789698,
      "grad_norm": 0.42248135805130005,
      "learning_rate": 4.49366939362819e-06,
      "loss": 0.5145,
      "step": 44670
    },
    {
      "epoch": 1.372254477313919,
      "grad_norm": 0.45338723063468933,
      "learning_rate": 4.4932659855553415e-06,
      "loss": 0.4565,
      "step": 44671
    },
    {
      "epoch": 1.372285196448868,
      "grad_norm": 0.36875683069229126,
      "learning_rate": 4.4928625903438495e-06,
      "loss": 0.4343,
      "step": 44672
    },
    {
      "epoch": 1.3723159155838172,
      "grad_norm": 0.41292229294776917,
      "learning_rate": 4.492459207994663e-06,
      "loss": 0.5584,
      "step": 44673
    },
    {
      "epoch": 1.3723466347187663,
      "grad_norm": 0.9710144996643066,
      "learning_rate": 4.492055838508721e-06,
      "loss": 0.4889,
      "step": 44674
    },
    {
      "epoch": 1.3723773538537154,
      "grad_norm": 0.4097006320953369,
      "learning_rate": 4.491652481886971e-06,
      "loss": 0.3738,
      "step": 44675
    },
    {
      "epoch": 1.3724080729886645,
      "grad_norm": 0.39100751280784607,
      "learning_rate": 4.4912491381303495e-06,
      "loss": 0.4768,
      "step": 44676
    },
    {
      "epoch": 1.3724387921236139,
      "grad_norm": 0.40447908639907837,
      "learning_rate": 4.490845807239802e-06,
      "loss": 0.4679,
      "step": 44677
    },
    {
      "epoch": 1.372469511258563,
      "grad_norm": 0.4296906590461731,
      "learning_rate": 4.4904424892162624e-06,
      "loss": 0.4574,
      "step": 44678
    },
    {
      "epoch": 1.372500230393512,
      "grad_norm": 0.46049246191978455,
      "learning_rate": 4.490039184060686e-06,
      "loss": 0.4704,
      "step": 44679
    },
    {
      "epoch": 1.3725309495284612,
      "grad_norm": 0.40247032046318054,
      "learning_rate": 4.489635891774004e-06,
      "loss": 0.4308,
      "step": 44680
    },
    {
      "epoch": 1.3725616686634106,
      "grad_norm": 0.40421822667121887,
      "learning_rate": 4.489232612357167e-06,
      "loss": 0.5409,
      "step": 44681
    },
    {
      "epoch": 1.3725923877983597,
      "grad_norm": 0.4039279520511627,
      "learning_rate": 4.488829345811108e-06,
      "loss": 0.4815,
      "step": 44682
    },
    {
      "epoch": 1.3726231069333088,
      "grad_norm": 0.41191181540489197,
      "learning_rate": 4.488426092136773e-06,
      "loss": 0.5105,
      "step": 44683
    },
    {
      "epoch": 1.372653826068258,
      "grad_norm": 0.4347219169139862,
      "learning_rate": 4.488022851335103e-06,
      "loss": 0.5356,
      "step": 44684
    },
    {
      "epoch": 1.372684545203207,
      "grad_norm": 0.4263545274734497,
      "learning_rate": 4.487619623407046e-06,
      "loss": 0.5282,
      "step": 44685
    },
    {
      "epoch": 1.3727152643381562,
      "grad_norm": 0.4922185242176056,
      "learning_rate": 4.487216408353533e-06,
      "loss": 0.4715,
      "step": 44686
    },
    {
      "epoch": 1.3727459834731053,
      "grad_norm": 0.44116532802581787,
      "learning_rate": 4.4868132061755076e-06,
      "loss": 0.5127,
      "step": 44687
    },
    {
      "epoch": 1.3727767026080546,
      "grad_norm": 0.46874338388442993,
      "learning_rate": 4.4864100168739236e-06,
      "loss": 0.4193,
      "step": 44688
    },
    {
      "epoch": 1.3728074217430037,
      "grad_norm": 0.4166867733001709,
      "learning_rate": 4.4860068404497094e-06,
      "loss": 0.4833,
      "step": 44689
    },
    {
      "epoch": 1.3728381408779529,
      "grad_norm": 0.39663511514663696,
      "learning_rate": 4.485603676903815e-06,
      "loss": 0.4738,
      "step": 44690
    },
    {
      "epoch": 1.372868860012902,
      "grad_norm": 0.4214058220386505,
      "learning_rate": 4.485200526237175e-06,
      "loss": 0.543,
      "step": 44691
    },
    {
      "epoch": 1.3728995791478513,
      "grad_norm": 0.40679851174354553,
      "learning_rate": 4.484797388450733e-06,
      "loss": 0.3846,
      "step": 44692
    },
    {
      "epoch": 1.3729302982828004,
      "grad_norm": 0.5923698544502258,
      "learning_rate": 4.484394263545434e-06,
      "loss": 0.4475,
      "step": 44693
    },
    {
      "epoch": 1.3729610174177496,
      "grad_norm": 0.3770340085029602,
      "learning_rate": 4.48399115152222e-06,
      "loss": 0.4317,
      "step": 44694
    },
    {
      "epoch": 1.3729917365526987,
      "grad_norm": 0.4405079782009125,
      "learning_rate": 4.483588052382026e-06,
      "loss": 0.4815,
      "step": 44695
    },
    {
      "epoch": 1.3730224556876478,
      "grad_norm": 0.495770663022995,
      "learning_rate": 4.4831849661257975e-06,
      "loss": 0.4304,
      "step": 44696
    },
    {
      "epoch": 1.373053174822597,
      "grad_norm": 0.5190812945365906,
      "learning_rate": 4.4827818927544764e-06,
      "loss": 0.4115,
      "step": 44697
    },
    {
      "epoch": 1.373083893957546,
      "grad_norm": 0.44277358055114746,
      "learning_rate": 4.482378832269007e-06,
      "loss": 0.559,
      "step": 44698
    },
    {
      "epoch": 1.3731146130924954,
      "grad_norm": 0.4324481785297394,
      "learning_rate": 4.481975784670323e-06,
      "loss": 0.4239,
      "step": 44699
    },
    {
      "epoch": 1.3731453322274445,
      "grad_norm": 0.4344547688961029,
      "learning_rate": 4.4815727499593696e-06,
      "loss": 0.5289,
      "step": 44700
    },
    {
      "epoch": 1.3731760513623936,
      "grad_norm": 0.4062638580799103,
      "learning_rate": 4.48116972813709e-06,
      "loss": 0.4375,
      "step": 44701
    },
    {
      "epoch": 1.3732067704973427,
      "grad_norm": 0.4527258574962616,
      "learning_rate": 4.480766719204426e-06,
      "loss": 0.494,
      "step": 44702
    },
    {
      "epoch": 1.373237489632292,
      "grad_norm": 0.3725423812866211,
      "learning_rate": 4.4803637231623145e-06,
      "loss": 0.3922,
      "step": 44703
    },
    {
      "epoch": 1.3732682087672412,
      "grad_norm": 0.3840555250644684,
      "learning_rate": 4.479960740011697e-06,
      "loss": 0.44,
      "step": 44704
    },
    {
      "epoch": 1.3732989279021903,
      "grad_norm": 0.5204268097877502,
      "learning_rate": 4.479557769753519e-06,
      "loss": 0.4116,
      "step": 44705
    },
    {
      "epoch": 1.3733296470371394,
      "grad_norm": 0.4087802469730377,
      "learning_rate": 4.479154812388717e-06,
      "loss": 0.4614,
      "step": 44706
    },
    {
      "epoch": 1.3733603661720886,
      "grad_norm": 0.4147855341434479,
      "learning_rate": 4.478751867918241e-06,
      "loss": 0.4469,
      "step": 44707
    },
    {
      "epoch": 1.3733910853070377,
      "grad_norm": 0.3921922445297241,
      "learning_rate": 4.47834893634302e-06,
      "loss": 0.4068,
      "step": 44708
    },
    {
      "epoch": 1.3734218044419868,
      "grad_norm": 0.38940858840942383,
      "learning_rate": 4.477946017664001e-06,
      "loss": 0.4729,
      "step": 44709
    },
    {
      "epoch": 1.3734525235769361,
      "grad_norm": 0.4567510485649109,
      "learning_rate": 4.477543111882125e-06,
      "loss": 0.4682,
      "step": 44710
    },
    {
      "epoch": 1.3734832427118853,
      "grad_norm": 0.42365962266921997,
      "learning_rate": 4.477140218998336e-06,
      "loss": 0.502,
      "step": 44711
    },
    {
      "epoch": 1.3735139618468344,
      "grad_norm": 0.4087221920490265,
      "learning_rate": 4.4767373390135685e-06,
      "loss": 0.4862,
      "step": 44712
    },
    {
      "epoch": 1.3735446809817835,
      "grad_norm": 0.41678187251091003,
      "learning_rate": 4.476334471928771e-06,
      "loss": 0.4994,
      "step": 44713
    },
    {
      "epoch": 1.3735754001167328,
      "grad_norm": 0.4882815480232239,
      "learning_rate": 4.475931617744871e-06,
      "loss": 0.4664,
      "step": 44714
    },
    {
      "epoch": 1.373606119251682,
      "grad_norm": 0.44125884771347046,
      "learning_rate": 4.475528776462827e-06,
      "loss": 0.4116,
      "step": 44715
    },
    {
      "epoch": 1.373636838386631,
      "grad_norm": 0.44300803542137146,
      "learning_rate": 4.475125948083568e-06,
      "loss": 0.483,
      "step": 44716
    },
    {
      "epoch": 1.3736675575215802,
      "grad_norm": 0.36988240480422974,
      "learning_rate": 4.474723132608041e-06,
      "loss": 0.3733,
      "step": 44717
    },
    {
      "epoch": 1.3736982766565293,
      "grad_norm": 0.39168617129325867,
      "learning_rate": 4.474320330037181e-06,
      "loss": 0.4719,
      "step": 44718
    },
    {
      "epoch": 1.3737289957914784,
      "grad_norm": 0.3981751799583435,
      "learning_rate": 4.4739175403719315e-06,
      "loss": 0.5086,
      "step": 44719
    },
    {
      "epoch": 1.3737597149264276,
      "grad_norm": 0.41500037908554077,
      "learning_rate": 4.473514763613232e-06,
      "loss": 0.5388,
      "step": 44720
    },
    {
      "epoch": 1.373790434061377,
      "grad_norm": 0.43529579043388367,
      "learning_rate": 4.473111999762031e-06,
      "loss": 0.4653,
      "step": 44721
    },
    {
      "epoch": 1.373821153196326,
      "grad_norm": 0.4223857522010803,
      "learning_rate": 4.472709248819258e-06,
      "loss": 0.4935,
      "step": 44722
    },
    {
      "epoch": 1.3738518723312751,
      "grad_norm": 0.5037080645561218,
      "learning_rate": 4.472306510785859e-06,
      "loss": 0.5181,
      "step": 44723
    },
    {
      "epoch": 1.3738825914662243,
      "grad_norm": 0.41009005904197693,
      "learning_rate": 4.471903785662774e-06,
      "loss": 0.4553,
      "step": 44724
    },
    {
      "epoch": 1.3739133106011736,
      "grad_norm": 0.4049798250198364,
      "learning_rate": 4.471501073450944e-06,
      "loss": 0.4055,
      "step": 44725
    },
    {
      "epoch": 1.3739440297361227,
      "grad_norm": 0.441486120223999,
      "learning_rate": 4.471098374151313e-06,
      "loss": 0.5671,
      "step": 44726
    },
    {
      "epoch": 1.3739747488710718,
      "grad_norm": 0.5185649991035461,
      "learning_rate": 4.4706956877648135e-06,
      "loss": 0.466,
      "step": 44727
    },
    {
      "epoch": 1.374005468006021,
      "grad_norm": 0.3903723359107971,
      "learning_rate": 4.47029301429239e-06,
      "loss": 0.4858,
      "step": 44728
    },
    {
      "epoch": 1.37403618714097,
      "grad_norm": 0.47763922810554504,
      "learning_rate": 4.469890353734985e-06,
      "loss": 0.5306,
      "step": 44729
    },
    {
      "epoch": 1.3740669062759192,
      "grad_norm": 0.4128475487232208,
      "learning_rate": 4.469487706093541e-06,
      "loss": 0.4489,
      "step": 44730
    },
    {
      "epoch": 1.3740976254108683,
      "grad_norm": 0.4030476212501526,
      "learning_rate": 4.4690850713689894e-06,
      "loss": 0.4442,
      "step": 44731
    },
    {
      "epoch": 1.3741283445458177,
      "grad_norm": 0.46613118052482605,
      "learning_rate": 4.468682449562276e-06,
      "loss": 0.4972,
      "step": 44732
    },
    {
      "epoch": 1.3741590636807668,
      "grad_norm": 0.44687002897262573,
      "learning_rate": 4.468279840674342e-06,
      "loss": 0.4936,
      "step": 44733
    },
    {
      "epoch": 1.374189782815716,
      "grad_norm": 0.3913191556930542,
      "learning_rate": 4.46787724470613e-06,
      "loss": 0.49,
      "step": 44734
    },
    {
      "epoch": 1.374220501950665,
      "grad_norm": 0.4088400900363922,
      "learning_rate": 4.467474661658574e-06,
      "loss": 0.4432,
      "step": 44735
    },
    {
      "epoch": 1.3742512210856141,
      "grad_norm": 0.4275516867637634,
      "learning_rate": 4.467072091532617e-06,
      "loss": 0.4801,
      "step": 44736
    },
    {
      "epoch": 1.3742819402205635,
      "grad_norm": 0.3937057554721832,
      "learning_rate": 4.466669534329199e-06,
      "loss": 0.4845,
      "step": 44737
    },
    {
      "epoch": 1.3743126593555126,
      "grad_norm": 0.434874951839447,
      "learning_rate": 4.466266990049265e-06,
      "loss": 0.4614,
      "step": 44738
    },
    {
      "epoch": 1.3743433784904617,
      "grad_norm": 0.46888014674186707,
      "learning_rate": 4.4658644586937474e-06,
      "loss": 0.5439,
      "step": 44739
    },
    {
      "epoch": 1.3743740976254109,
      "grad_norm": 0.4264467656612396,
      "learning_rate": 4.465461940263593e-06,
      "loss": 0.459,
      "step": 44740
    },
    {
      "epoch": 1.37440481676036,
      "grad_norm": 0.5451595783233643,
      "learning_rate": 4.465059434759731e-06,
      "loss": 0.4476,
      "step": 44741
    },
    {
      "epoch": 1.374435535895309,
      "grad_norm": 0.3855660557746887,
      "learning_rate": 4.464656942183115e-06,
      "loss": 0.3988,
      "step": 44742
    },
    {
      "epoch": 1.3744662550302582,
      "grad_norm": 0.38172629475593567,
      "learning_rate": 4.464254462534681e-06,
      "loss": 0.5191,
      "step": 44743
    },
    {
      "epoch": 1.3744969741652076,
      "grad_norm": 0.417025625705719,
      "learning_rate": 4.463851995815363e-06,
      "loss": 0.5419,
      "step": 44744
    },
    {
      "epoch": 1.3745276933001567,
      "grad_norm": 0.39772745966911316,
      "learning_rate": 4.4634495420261105e-06,
      "loss": 0.425,
      "step": 44745
    },
    {
      "epoch": 1.3745584124351058,
      "grad_norm": 0.4044083058834076,
      "learning_rate": 4.463047101167851e-06,
      "loss": 0.526,
      "step": 44746
    },
    {
      "epoch": 1.374589131570055,
      "grad_norm": 0.4119642376899719,
      "learning_rate": 4.462644673241538e-06,
      "loss": 0.5691,
      "step": 44747
    },
    {
      "epoch": 1.3746198507050043,
      "grad_norm": 0.4547561705112457,
      "learning_rate": 4.462242258248102e-06,
      "loss": 0.4624,
      "step": 44748
    },
    {
      "epoch": 1.3746505698399534,
      "grad_norm": 0.4031658172607422,
      "learning_rate": 4.46183985618849e-06,
      "loss": 0.4644,
      "step": 44749
    },
    {
      "epoch": 1.3746812889749025,
      "grad_norm": 0.39406633377075195,
      "learning_rate": 4.46143746706363e-06,
      "loss": 0.4804,
      "step": 44750
    },
    {
      "epoch": 1.3747120081098516,
      "grad_norm": 0.45645567774772644,
      "learning_rate": 4.461035090874477e-06,
      "loss": 0.4983,
      "step": 44751
    },
    {
      "epoch": 1.3747427272448007,
      "grad_norm": 0.4437921643257141,
      "learning_rate": 4.460632727621959e-06,
      "loss": 0.4688,
      "step": 44752
    },
    {
      "epoch": 1.3747734463797499,
      "grad_norm": 0.5095550417900085,
      "learning_rate": 4.460230377307025e-06,
      "loss": 0.5224,
      "step": 44753
    },
    {
      "epoch": 1.374804165514699,
      "grad_norm": 0.4244929552078247,
      "learning_rate": 4.459828039930606e-06,
      "loss": 0.4927,
      "step": 44754
    },
    {
      "epoch": 1.3748348846496483,
      "grad_norm": 0.48700034618377686,
      "learning_rate": 4.459425715493645e-06,
      "loss": 0.4825,
      "step": 44755
    },
    {
      "epoch": 1.3748656037845974,
      "grad_norm": 0.4102099537849426,
      "learning_rate": 4.459023403997083e-06,
      "loss": 0.4889,
      "step": 44756
    },
    {
      "epoch": 1.3748963229195466,
      "grad_norm": 0.39204177260398865,
      "learning_rate": 4.458621105441861e-06,
      "loss": 0.4725,
      "step": 44757
    },
    {
      "epoch": 1.3749270420544957,
      "grad_norm": 0.40285724401474,
      "learning_rate": 4.458218819828915e-06,
      "loss": 0.4227,
      "step": 44758
    },
    {
      "epoch": 1.374957761189445,
      "grad_norm": 0.488198459148407,
      "learning_rate": 4.457816547159184e-06,
      "loss": 0.5421,
      "step": 44759
    },
    {
      "epoch": 1.3749884803243941,
      "grad_norm": 0.401500403881073,
      "learning_rate": 4.45741428743361e-06,
      "loss": 0.4747,
      "step": 44760
    },
    {
      "epoch": 1.3750191994593433,
      "grad_norm": 0.4433577060699463,
      "learning_rate": 4.457012040653132e-06,
      "loss": 0.4387,
      "step": 44761
    },
    {
      "epoch": 1.3750499185942924,
      "grad_norm": 0.40245866775512695,
      "learning_rate": 4.456609806818694e-06,
      "loss": 0.3888,
      "step": 44762
    },
    {
      "epoch": 1.3750806377292415,
      "grad_norm": 0.40399542450904846,
      "learning_rate": 4.456207585931226e-06,
      "loss": 0.4764,
      "step": 44763
    },
    {
      "epoch": 1.3751113568641906,
      "grad_norm": 0.41928359866142273,
      "learning_rate": 4.455805377991673e-06,
      "loss": 0.4633,
      "step": 44764
    },
    {
      "epoch": 1.3751420759991397,
      "grad_norm": 0.8734528422355652,
      "learning_rate": 4.455403183000974e-06,
      "loss": 0.5814,
      "step": 44765
    },
    {
      "epoch": 1.375172795134089,
      "grad_norm": 0.4279337525367737,
      "learning_rate": 4.455001000960072e-06,
      "loss": 0.4356,
      "step": 44766
    },
    {
      "epoch": 1.3752035142690382,
      "grad_norm": 0.4432609975337982,
      "learning_rate": 4.454598831869897e-06,
      "loss": 0.4741,
      "step": 44767
    },
    {
      "epoch": 1.3752342334039873,
      "grad_norm": 0.4083159565925598,
      "learning_rate": 4.4541966757313955e-06,
      "loss": 0.4328,
      "step": 44768
    },
    {
      "epoch": 1.3752649525389364,
      "grad_norm": 0.4694461226463318,
      "learning_rate": 4.453794532545504e-06,
      "loss": 0.4926,
      "step": 44769
    },
    {
      "epoch": 1.3752956716738858,
      "grad_norm": 0.4289247989654541,
      "learning_rate": 4.453392402313167e-06,
      "loss": 0.4466,
      "step": 44770
    },
    {
      "epoch": 1.375326390808835,
      "grad_norm": 0.4204534590244293,
      "learning_rate": 4.452990285035316e-06,
      "loss": 0.5438,
      "step": 44771
    },
    {
      "epoch": 1.375357109943784,
      "grad_norm": 0.5029800534248352,
      "learning_rate": 4.452588180712894e-06,
      "loss": 0.4244,
      "step": 44772
    },
    {
      "epoch": 1.3753878290787331,
      "grad_norm": 0.38027170300483704,
      "learning_rate": 4.452186089346838e-06,
      "loss": 0.4312,
      "step": 44773
    },
    {
      "epoch": 1.3754185482136823,
      "grad_norm": 0.423593670129776,
      "learning_rate": 4.451784010938094e-06,
      "loss": 0.5184,
      "step": 44774
    },
    {
      "epoch": 1.3754492673486314,
      "grad_norm": 0.4156249463558197,
      "learning_rate": 4.451381945487591e-06,
      "loss": 0.4053,
      "step": 44775
    },
    {
      "epoch": 1.3754799864835805,
      "grad_norm": 0.3962090313434601,
      "learning_rate": 4.450979892996277e-06,
      "loss": 0.5215,
      "step": 44776
    },
    {
      "epoch": 1.3755107056185298,
      "grad_norm": 0.4125971794128418,
      "learning_rate": 4.45057785346508e-06,
      "loss": 0.468,
      "step": 44777
    },
    {
      "epoch": 1.375541424753479,
      "grad_norm": 0.46536320447921753,
      "learning_rate": 4.45017582689495e-06,
      "loss": 0.5332,
      "step": 44778
    },
    {
      "epoch": 1.375572143888428,
      "grad_norm": 0.4147760570049286,
      "learning_rate": 4.449773813286825e-06,
      "loss": 0.4424,
      "step": 44779
    },
    {
      "epoch": 1.3756028630233772,
      "grad_norm": 0.4191051721572876,
      "learning_rate": 4.4493718126416376e-06,
      "loss": 0.4407,
      "step": 44780
    },
    {
      "epoch": 1.3756335821583265,
      "grad_norm": 0.4075387120246887,
      "learning_rate": 4.448969824960333e-06,
      "loss": 0.4068,
      "step": 44781
    },
    {
      "epoch": 1.3756643012932757,
      "grad_norm": 0.4838922321796417,
      "learning_rate": 4.44856785024384e-06,
      "loss": 0.4856,
      "step": 44782
    },
    {
      "epoch": 1.3756950204282248,
      "grad_norm": 0.3961552381515503,
      "learning_rate": 4.448165888493112e-06,
      "loss": 0.5184,
      "step": 44783
    },
    {
      "epoch": 1.375725739563174,
      "grad_norm": 0.47133663296699524,
      "learning_rate": 4.447763939709078e-06,
      "loss": 0.4754,
      "step": 44784
    },
    {
      "epoch": 1.375756458698123,
      "grad_norm": 0.44176432490348816,
      "learning_rate": 4.4473620038926816e-06,
      "loss": 0.4983,
      "step": 44785
    },
    {
      "epoch": 1.3757871778330721,
      "grad_norm": 0.4339149296283722,
      "learning_rate": 4.446960081044854e-06,
      "loss": 0.4916,
      "step": 44786
    },
    {
      "epoch": 1.3758178969680213,
      "grad_norm": 0.5543531775474548,
      "learning_rate": 4.446558171166541e-06,
      "loss": 0.5082,
      "step": 44787
    },
    {
      "epoch": 1.3758486161029706,
      "grad_norm": 0.45470118522644043,
      "learning_rate": 4.446156274258678e-06,
      "loss": 0.4508,
      "step": 44788
    },
    {
      "epoch": 1.3758793352379197,
      "grad_norm": 0.4067704677581787,
      "learning_rate": 4.445754390322209e-06,
      "loss": 0.4638,
      "step": 44789
    },
    {
      "epoch": 1.3759100543728688,
      "grad_norm": 0.4147692620754242,
      "learning_rate": 4.445352519358065e-06,
      "loss": 0.5244,
      "step": 44790
    },
    {
      "epoch": 1.375940773507818,
      "grad_norm": 0.4661317765712738,
      "learning_rate": 4.444950661367187e-06,
      "loss": 0.5023,
      "step": 44791
    },
    {
      "epoch": 1.3759714926427673,
      "grad_norm": 0.3827679753303528,
      "learning_rate": 4.444548816350515e-06,
      "loss": 0.4596,
      "step": 44792
    },
    {
      "epoch": 1.3760022117777164,
      "grad_norm": 0.3937735855579376,
      "learning_rate": 4.444146984308992e-06,
      "loss": 0.4558,
      "step": 44793
    },
    {
      "epoch": 1.3760329309126655,
      "grad_norm": 0.3939659595489502,
      "learning_rate": 4.443745165243548e-06,
      "loss": 0.3898,
      "step": 44794
    },
    {
      "epoch": 1.3760636500476147,
      "grad_norm": 0.41190633177757263,
      "learning_rate": 4.443343359155125e-06,
      "loss": 0.4922,
      "step": 44795
    },
    {
      "epoch": 1.3760943691825638,
      "grad_norm": 0.6879589557647705,
      "learning_rate": 4.442941566044662e-06,
      "loss": 0.5136,
      "step": 44796
    },
    {
      "epoch": 1.376125088317513,
      "grad_norm": 0.42782148718833923,
      "learning_rate": 4.442539785913096e-06,
      "loss": 0.3754,
      "step": 44797
    },
    {
      "epoch": 1.376155807452462,
      "grad_norm": 0.4478640854358673,
      "learning_rate": 4.442138018761371e-06,
      "loss": 0.4329,
      "step": 44798
    },
    {
      "epoch": 1.3761865265874114,
      "grad_norm": 0.3893263638019562,
      "learning_rate": 4.441736264590416e-06,
      "loss": 0.4435,
      "step": 44799
    },
    {
      "epoch": 1.3762172457223605,
      "grad_norm": 0.44051480293273926,
      "learning_rate": 4.441334523401175e-06,
      "loss": 0.4451,
      "step": 44800
    },
    {
      "epoch": 1.3762479648573096,
      "grad_norm": 0.34758633375167847,
      "learning_rate": 4.440932795194586e-06,
      "loss": 0.4734,
      "step": 44801
    },
    {
      "epoch": 1.3762786839922587,
      "grad_norm": 0.5203729867935181,
      "learning_rate": 4.44053107997159e-06,
      "loss": 0.4445,
      "step": 44802
    },
    {
      "epoch": 1.376309403127208,
      "grad_norm": 0.4230107069015503,
      "learning_rate": 4.440129377733117e-06,
      "loss": 0.4011,
      "step": 44803
    },
    {
      "epoch": 1.3763401222621572,
      "grad_norm": 0.4048629403114319,
      "learning_rate": 4.439727688480112e-06,
      "loss": 0.4522,
      "step": 44804
    },
    {
      "epoch": 1.3763708413971063,
      "grad_norm": 0.40882545709609985,
      "learning_rate": 4.43932601221351e-06,
      "loss": 0.4504,
      "step": 44805
    },
    {
      "epoch": 1.3764015605320554,
      "grad_norm": 0.493417352437973,
      "learning_rate": 4.438924348934255e-06,
      "loss": 0.4427,
      "step": 44806
    },
    {
      "epoch": 1.3764322796670045,
      "grad_norm": 0.3704548478126526,
      "learning_rate": 4.4385226986432765e-06,
      "loss": 0.4545,
      "step": 44807
    },
    {
      "epoch": 1.3764629988019537,
      "grad_norm": 0.3795817494392395,
      "learning_rate": 4.43812106134152e-06,
      "loss": 0.4949,
      "step": 44808
    },
    {
      "epoch": 1.3764937179369028,
      "grad_norm": 0.3923948109149933,
      "learning_rate": 4.437719437029913e-06,
      "loss": 0.4843,
      "step": 44809
    },
    {
      "epoch": 1.3765244370718521,
      "grad_norm": 0.4111505150794983,
      "learning_rate": 4.437317825709408e-06,
      "loss": 0.489,
      "step": 44810
    },
    {
      "epoch": 1.3765551562068012,
      "grad_norm": 0.38156187534332275,
      "learning_rate": 4.436916227380933e-06,
      "loss": 0.4654,
      "step": 44811
    },
    {
      "epoch": 1.3765858753417504,
      "grad_norm": 0.3828831911087036,
      "learning_rate": 4.436514642045431e-06,
      "loss": 0.509,
      "step": 44812
    },
    {
      "epoch": 1.3766165944766995,
      "grad_norm": 0.4741245210170746,
      "learning_rate": 4.4361130697038315e-06,
      "loss": 0.4975,
      "step": 44813
    },
    {
      "epoch": 1.3766473136116488,
      "grad_norm": 0.42693138122558594,
      "learning_rate": 4.435711510357081e-06,
      "loss": 0.4546,
      "step": 44814
    },
    {
      "epoch": 1.376678032746598,
      "grad_norm": 0.43052932620048523,
      "learning_rate": 4.43530996400612e-06,
      "loss": 0.438,
      "step": 44815
    },
    {
      "epoch": 1.376708751881547,
      "grad_norm": 0.404580682516098,
      "learning_rate": 4.434908430651876e-06,
      "loss": 0.4847,
      "step": 44816
    },
    {
      "epoch": 1.3767394710164962,
      "grad_norm": 0.4557821750640869,
      "learning_rate": 4.4345069102952955e-06,
      "loss": 0.4794,
      "step": 44817
    },
    {
      "epoch": 1.3767701901514453,
      "grad_norm": 0.4487936496734619,
      "learning_rate": 4.434105402937307e-06,
      "loss": 0.4566,
      "step": 44818
    },
    {
      "epoch": 1.3768009092863944,
      "grad_norm": 0.41816556453704834,
      "learning_rate": 4.43370390857886e-06,
      "loss": 0.4754,
      "step": 44819
    },
    {
      "epoch": 1.3768316284213435,
      "grad_norm": 0.44001808762550354,
      "learning_rate": 4.433302427220883e-06,
      "loss": 0.4106,
      "step": 44820
    },
    {
      "epoch": 1.3768623475562929,
      "grad_norm": 0.4087825417518616,
      "learning_rate": 4.4329009588643216e-06,
      "loss": 0.4552,
      "step": 44821
    },
    {
      "epoch": 1.376893066691242,
      "grad_norm": 0.4150824248790741,
      "learning_rate": 4.4324995035101035e-06,
      "loss": 0.4836,
      "step": 44822
    },
    {
      "epoch": 1.3769237858261911,
      "grad_norm": 0.37916800379753113,
      "learning_rate": 4.4320980611591735e-06,
      "loss": 0.3773,
      "step": 44823
    },
    {
      "epoch": 1.3769545049611402,
      "grad_norm": 0.38905593752861023,
      "learning_rate": 4.431696631812465e-06,
      "loss": 0.4546,
      "step": 44824
    },
    {
      "epoch": 1.3769852240960896,
      "grad_norm": 0.4057581126689911,
      "learning_rate": 4.431295215470924e-06,
      "loss": 0.4379,
      "step": 44825
    },
    {
      "epoch": 1.3770159432310387,
      "grad_norm": 0.4996389150619507,
      "learning_rate": 4.430893812135477e-06,
      "loss": 0.5387,
      "step": 44826
    },
    {
      "epoch": 1.3770466623659878,
      "grad_norm": 0.3713061213493347,
      "learning_rate": 4.430492421807066e-06,
      "loss": 0.5045,
      "step": 44827
    },
    {
      "epoch": 1.377077381500937,
      "grad_norm": 0.41644516587257385,
      "learning_rate": 4.430091044486631e-06,
      "loss": 0.4249,
      "step": 44828
    },
    {
      "epoch": 1.377108100635886,
      "grad_norm": 0.41980457305908203,
      "learning_rate": 4.429689680175109e-06,
      "loss": 0.5188,
      "step": 44829
    },
    {
      "epoch": 1.3771388197708352,
      "grad_norm": 0.458601713180542,
      "learning_rate": 4.4292883288734325e-06,
      "loss": 0.4499,
      "step": 44830
    },
    {
      "epoch": 1.3771695389057843,
      "grad_norm": 0.4273173213005066,
      "learning_rate": 4.428886990582542e-06,
      "loss": 0.5271,
      "step": 44831
    },
    {
      "epoch": 1.3772002580407336,
      "grad_norm": 0.46542418003082275,
      "learning_rate": 4.428485665303376e-06,
      "loss": 0.5403,
      "step": 44832
    },
    {
      "epoch": 1.3772309771756828,
      "grad_norm": 0.41560491919517517,
      "learning_rate": 4.42808435303687e-06,
      "loss": 0.4515,
      "step": 44833
    },
    {
      "epoch": 1.3772616963106319,
      "grad_norm": 0.40967291593551636,
      "learning_rate": 4.4276830537839665e-06,
      "loss": 0.465,
      "step": 44834
    },
    {
      "epoch": 1.377292415445581,
      "grad_norm": 0.3667937219142914,
      "learning_rate": 4.427281767545594e-06,
      "loss": 0.4872,
      "step": 44835
    },
    {
      "epoch": 1.3773231345805304,
      "grad_norm": 0.4036532938480377,
      "learning_rate": 4.426880494322694e-06,
      "loss": 0.4485,
      "step": 44836
    },
    {
      "epoch": 1.3773538537154795,
      "grad_norm": 0.38967275619506836,
      "learning_rate": 4.426479234116204e-06,
      "loss": 0.4492,
      "step": 44837
    },
    {
      "epoch": 1.3773845728504286,
      "grad_norm": 0.38435032963752747,
      "learning_rate": 4.426077986927065e-06,
      "loss": 0.4272,
      "step": 44838
    },
    {
      "epoch": 1.3774152919853777,
      "grad_norm": 0.4258576035499573,
      "learning_rate": 4.4256767527562075e-06,
      "loss": 0.4589,
      "step": 44839
    },
    {
      "epoch": 1.3774460111203268,
      "grad_norm": 0.4445476531982422,
      "learning_rate": 4.425275531604569e-06,
      "loss": 0.45,
      "step": 44840
    },
    {
      "epoch": 1.377476730255276,
      "grad_norm": 0.38898417353630066,
      "learning_rate": 4.424874323473091e-06,
      "loss": 0.5073,
      "step": 44841
    },
    {
      "epoch": 1.377507449390225,
      "grad_norm": 0.38325223326683044,
      "learning_rate": 4.424473128362711e-06,
      "loss": 0.5283,
      "step": 44842
    },
    {
      "epoch": 1.3775381685251744,
      "grad_norm": 0.6069069504737854,
      "learning_rate": 4.4240719462743584e-06,
      "loss": 0.5214,
      "step": 44843
    },
    {
      "epoch": 1.3775688876601235,
      "grad_norm": 0.416100412607193,
      "learning_rate": 4.423670777208981e-06,
      "loss": 0.4623,
      "step": 44844
    },
    {
      "epoch": 1.3775996067950727,
      "grad_norm": 0.40101730823516846,
      "learning_rate": 4.423269621167502e-06,
      "loss": 0.4231,
      "step": 44845
    },
    {
      "epoch": 1.3776303259300218,
      "grad_norm": 0.39236077666282654,
      "learning_rate": 4.422868478150873e-06,
      "loss": 0.3973,
      "step": 44846
    },
    {
      "epoch": 1.377661045064971,
      "grad_norm": 0.4591013193130493,
      "learning_rate": 4.422467348160021e-06,
      "loss": 0.4339,
      "step": 44847
    },
    {
      "epoch": 1.3776917641999202,
      "grad_norm": 0.41561180353164673,
      "learning_rate": 4.4220662311958895e-06,
      "loss": 0.4274,
      "step": 44848
    },
    {
      "epoch": 1.3777224833348694,
      "grad_norm": 0.4407345950603485,
      "learning_rate": 4.421665127259408e-06,
      "loss": 0.4282,
      "step": 44849
    },
    {
      "epoch": 1.3777532024698185,
      "grad_norm": 0.41399261355400085,
      "learning_rate": 4.421264036351514e-06,
      "loss": 0.3773,
      "step": 44850
    },
    {
      "epoch": 1.3777839216047676,
      "grad_norm": 0.4207909107208252,
      "learning_rate": 4.420862958473154e-06,
      "loss": 0.4536,
      "step": 44851
    },
    {
      "epoch": 1.3778146407397167,
      "grad_norm": 0.4463168978691101,
      "learning_rate": 4.420461893625256e-06,
      "loss": 0.4337,
      "step": 44852
    },
    {
      "epoch": 1.3778453598746658,
      "grad_norm": 0.3864484131336212,
      "learning_rate": 4.420060841808762e-06,
      "loss": 0.3976,
      "step": 44853
    },
    {
      "epoch": 1.377876079009615,
      "grad_norm": 0.428714781999588,
      "learning_rate": 4.419659803024597e-06,
      "loss": 0.5099,
      "step": 44854
    },
    {
      "epoch": 1.3779067981445643,
      "grad_norm": 0.41963282227516174,
      "learning_rate": 4.419258777273715e-06,
      "loss": 0.48,
      "step": 44855
    },
    {
      "epoch": 1.3779375172795134,
      "grad_norm": 0.4258180558681488,
      "learning_rate": 4.41885776455704e-06,
      "loss": 0.4597,
      "step": 44856
    },
    {
      "epoch": 1.3779682364144625,
      "grad_norm": 0.4124546945095062,
      "learning_rate": 4.418456764875516e-06,
      "loss": 0.5039,
      "step": 44857
    },
    {
      "epoch": 1.3779989555494117,
      "grad_norm": 0.4108305871486664,
      "learning_rate": 4.418055778230072e-06,
      "loss": 0.4827,
      "step": 44858
    },
    {
      "epoch": 1.378029674684361,
      "grad_norm": 0.5325281023979187,
      "learning_rate": 4.417654804621649e-06,
      "loss": 0.446,
      "step": 44859
    },
    {
      "epoch": 1.3780603938193101,
      "grad_norm": 0.42330801486968994,
      "learning_rate": 4.4172538440511836e-06,
      "loss": 0.4286,
      "step": 44860
    },
    {
      "epoch": 1.3780911129542592,
      "grad_norm": 0.4272303581237793,
      "learning_rate": 4.416852896519614e-06,
      "loss": 0.5673,
      "step": 44861
    },
    {
      "epoch": 1.3781218320892084,
      "grad_norm": 0.3903185725212097,
      "learning_rate": 4.4164519620278725e-06,
      "loss": 0.4433,
      "step": 44862
    },
    {
      "epoch": 1.3781525512241575,
      "grad_norm": 0.4103317856788635,
      "learning_rate": 4.416051040576895e-06,
      "loss": 0.47,
      "step": 44863
    },
    {
      "epoch": 1.3781832703591066,
      "grad_norm": 0.3983284533023834,
      "learning_rate": 4.415650132167623e-06,
      "loss": 0.4875,
      "step": 44864
    },
    {
      "epoch": 1.3782139894940557,
      "grad_norm": 0.38511067628860474,
      "learning_rate": 4.415249236800992e-06,
      "loss": 0.4937,
      "step": 44865
    },
    {
      "epoch": 1.378244708629005,
      "grad_norm": 0.4229376018047333,
      "learning_rate": 4.414848354477933e-06,
      "loss": 0.5328,
      "step": 44866
    },
    {
      "epoch": 1.3782754277639542,
      "grad_norm": 0.3787398636341095,
      "learning_rate": 4.4144474851993854e-06,
      "loss": 0.4678,
      "step": 44867
    },
    {
      "epoch": 1.3783061468989033,
      "grad_norm": 0.45519959926605225,
      "learning_rate": 4.4140466289662865e-06,
      "loss": 0.5636,
      "step": 44868
    },
    {
      "epoch": 1.3783368660338524,
      "grad_norm": 0.45293989777565,
      "learning_rate": 4.413645785779573e-06,
      "loss": 0.4589,
      "step": 44869
    },
    {
      "epoch": 1.3783675851688018,
      "grad_norm": 0.5203312635421753,
      "learning_rate": 4.413244955640182e-06,
      "loss": 0.5278,
      "step": 44870
    },
    {
      "epoch": 1.3783983043037509,
      "grad_norm": 0.43394219875335693,
      "learning_rate": 4.4128441385490435e-06,
      "loss": 0.4771,
      "step": 44871
    },
    {
      "epoch": 1.3784290234387,
      "grad_norm": 0.3960992991924286,
      "learning_rate": 4.4124433345070985e-06,
      "loss": 0.5156,
      "step": 44872
    },
    {
      "epoch": 1.3784597425736491,
      "grad_norm": 0.42402002215385437,
      "learning_rate": 4.4120425435152825e-06,
      "loss": 0.5074,
      "step": 44873
    },
    {
      "epoch": 1.3784904617085982,
      "grad_norm": 0.41709306836128235,
      "learning_rate": 4.411641765574535e-06,
      "loss": 0.453,
      "step": 44874
    },
    {
      "epoch": 1.3785211808435474,
      "grad_norm": 0.4554719626903534,
      "learning_rate": 4.411241000685784e-06,
      "loss": 0.5133,
      "step": 44875
    },
    {
      "epoch": 1.3785518999784965,
      "grad_norm": 0.41971704363822937,
      "learning_rate": 4.41084024884997e-06,
      "loss": 0.4938,
      "step": 44876
    },
    {
      "epoch": 1.3785826191134458,
      "grad_norm": 0.4554175138473511,
      "learning_rate": 4.41043951006803e-06,
      "loss": 0.5274,
      "step": 44877
    },
    {
      "epoch": 1.378613338248395,
      "grad_norm": 0.37842699885368347,
      "learning_rate": 4.410038784340902e-06,
      "loss": 0.5047,
      "step": 44878
    },
    {
      "epoch": 1.378644057383344,
      "grad_norm": 0.4649650752544403,
      "learning_rate": 4.409638071669515e-06,
      "loss": 0.5071,
      "step": 44879
    },
    {
      "epoch": 1.3786747765182932,
      "grad_norm": 0.4229663610458374,
      "learning_rate": 4.409237372054812e-06,
      "loss": 0.5206,
      "step": 44880
    },
    {
      "epoch": 1.3787054956532425,
      "grad_norm": 0.3650919497013092,
      "learning_rate": 4.408836685497719e-06,
      "loss": 0.4543,
      "step": 44881
    },
    {
      "epoch": 1.3787362147881916,
      "grad_norm": 0.48309528827667236,
      "learning_rate": 4.408436011999186e-06,
      "loss": 0.6061,
      "step": 44882
    },
    {
      "epoch": 1.3787669339231408,
      "grad_norm": 0.44065791368484497,
      "learning_rate": 4.408035351560137e-06,
      "loss": 0.5183,
      "step": 44883
    },
    {
      "epoch": 1.3787976530580899,
      "grad_norm": 0.3764422535896301,
      "learning_rate": 4.4076347041815146e-06,
      "loss": 0.4959,
      "step": 44884
    },
    {
      "epoch": 1.378828372193039,
      "grad_norm": 0.4194631278514862,
      "learning_rate": 4.40723406986425e-06,
      "loss": 0.443,
      "step": 44885
    },
    {
      "epoch": 1.3788590913279881,
      "grad_norm": 0.49031955003738403,
      "learning_rate": 4.40683344860928e-06,
      "loss": 0.4983,
      "step": 44886
    },
    {
      "epoch": 1.3788898104629372,
      "grad_norm": 0.47434577345848083,
      "learning_rate": 4.406432840417542e-06,
      "loss": 0.5184,
      "step": 44887
    },
    {
      "epoch": 1.3789205295978866,
      "grad_norm": 0.46289852261543274,
      "learning_rate": 4.40603224528997e-06,
      "loss": 0.4293,
      "step": 44888
    },
    {
      "epoch": 1.3789512487328357,
      "grad_norm": 0.4472363293170929,
      "learning_rate": 4.405631663227503e-06,
      "loss": 0.4762,
      "step": 44889
    },
    {
      "epoch": 1.3789819678677848,
      "grad_norm": 0.41734716296195984,
      "learning_rate": 4.4052310942310716e-06,
      "loss": 0.4212,
      "step": 44890
    },
    {
      "epoch": 1.379012687002734,
      "grad_norm": 0.3894784152507782,
      "learning_rate": 4.404830538301613e-06,
      "loss": 0.4697,
      "step": 44891
    },
    {
      "epoch": 1.3790434061376833,
      "grad_norm": 0.4364241361618042,
      "learning_rate": 4.404429995440065e-06,
      "loss": 0.5301,
      "step": 44892
    },
    {
      "epoch": 1.3790741252726324,
      "grad_norm": 0.42552098631858826,
      "learning_rate": 4.404029465647364e-06,
      "loss": 0.526,
      "step": 44893
    },
    {
      "epoch": 1.3791048444075815,
      "grad_norm": 0.42452603578567505,
      "learning_rate": 4.403628948924439e-06,
      "loss": 0.4528,
      "step": 44894
    },
    {
      "epoch": 1.3791355635425306,
      "grad_norm": 0.41955292224884033,
      "learning_rate": 4.40322844527223e-06,
      "loss": 0.4785,
      "step": 44895
    },
    {
      "epoch": 1.3791662826774798,
      "grad_norm": 0.469707727432251,
      "learning_rate": 4.402827954691672e-06,
      "loss": 0.4422,
      "step": 44896
    },
    {
      "epoch": 1.3791970018124289,
      "grad_norm": 0.4768855571746826,
      "learning_rate": 4.402427477183703e-06,
      "loss": 0.5139,
      "step": 44897
    },
    {
      "epoch": 1.379227720947378,
      "grad_norm": 0.4709678590297699,
      "learning_rate": 4.402027012749253e-06,
      "loss": 0.4559,
      "step": 44898
    },
    {
      "epoch": 1.3792584400823273,
      "grad_norm": 0.3921150267124176,
      "learning_rate": 4.401626561389259e-06,
      "loss": 0.4457,
      "step": 44899
    },
    {
      "epoch": 1.3792891592172765,
      "grad_norm": 0.43180766701698303,
      "learning_rate": 4.401226123104657e-06,
      "loss": 0.5586,
      "step": 44900
    },
    {
      "epoch": 1.3793198783522256,
      "grad_norm": 0.4763498604297638,
      "learning_rate": 4.400825697896387e-06,
      "loss": 0.4796,
      "step": 44901
    },
    {
      "epoch": 1.3793505974871747,
      "grad_norm": 0.4636286497116089,
      "learning_rate": 4.400425285765375e-06,
      "loss": 0.4849,
      "step": 44902
    },
    {
      "epoch": 1.379381316622124,
      "grad_norm": 0.4338211715221405,
      "learning_rate": 4.4000248867125615e-06,
      "loss": 0.5054,
      "step": 44903
    },
    {
      "epoch": 1.3794120357570732,
      "grad_norm": 0.43133074045181274,
      "learning_rate": 4.39962450073888e-06,
      "loss": 0.5212,
      "step": 44904
    },
    {
      "epoch": 1.3794427548920223,
      "grad_norm": 0.47016674280166626,
      "learning_rate": 4.399224127845269e-06,
      "loss": 0.4521,
      "step": 44905
    },
    {
      "epoch": 1.3794734740269714,
      "grad_norm": 0.3888823091983795,
      "learning_rate": 4.398823768032663e-06,
      "loss": 0.4527,
      "step": 44906
    },
    {
      "epoch": 1.3795041931619205,
      "grad_norm": 0.40466365218162537,
      "learning_rate": 4.398423421301991e-06,
      "loss": 0.4624,
      "step": 44907
    },
    {
      "epoch": 1.3795349122968696,
      "grad_norm": 0.49136266112327576,
      "learning_rate": 4.398023087654194e-06,
      "loss": 0.4445,
      "step": 44908
    },
    {
      "epoch": 1.3795656314318188,
      "grad_norm": 0.40445753931999207,
      "learning_rate": 4.397622767090204e-06,
      "loss": 0.5151,
      "step": 44909
    },
    {
      "epoch": 1.379596350566768,
      "grad_norm": 0.5021544098854065,
      "learning_rate": 4.397222459610962e-06,
      "loss": 0.4907,
      "step": 44910
    },
    {
      "epoch": 1.3796270697017172,
      "grad_norm": 0.43868160247802734,
      "learning_rate": 4.396822165217393e-06,
      "loss": 0.5336,
      "step": 44911
    },
    {
      "epoch": 1.3796577888366663,
      "grad_norm": 0.3954765200614929,
      "learning_rate": 4.3964218839104425e-06,
      "loss": 0.4582,
      "step": 44912
    },
    {
      "epoch": 1.3796885079716155,
      "grad_norm": 0.39174771308898926,
      "learning_rate": 4.396021615691032e-06,
      "loss": 0.382,
      "step": 44913
    },
    {
      "epoch": 1.3797192271065648,
      "grad_norm": 0.3980110287666321,
      "learning_rate": 4.395621360560112e-06,
      "loss": 0.4309,
      "step": 44914
    },
    {
      "epoch": 1.379749946241514,
      "grad_norm": 0.4235647916793823,
      "learning_rate": 4.395221118518606e-06,
      "loss": 0.4843,
      "step": 44915
    },
    {
      "epoch": 1.379780665376463,
      "grad_norm": 0.4074147045612335,
      "learning_rate": 4.394820889567456e-06,
      "loss": 0.4742,
      "step": 44916
    },
    {
      "epoch": 1.3798113845114122,
      "grad_norm": 0.4692545533180237,
      "learning_rate": 4.394420673707586e-06,
      "loss": 0.3543,
      "step": 44917
    },
    {
      "epoch": 1.3798421036463613,
      "grad_norm": 0.4349537789821625,
      "learning_rate": 4.3940204709399445e-06,
      "loss": 0.4324,
      "step": 44918
    },
    {
      "epoch": 1.3798728227813104,
      "grad_norm": 0.40790775418281555,
      "learning_rate": 4.3936202812654575e-06,
      "loss": 0.4665,
      "step": 44919
    },
    {
      "epoch": 1.3799035419162595,
      "grad_norm": 0.418854296207428,
      "learning_rate": 4.393220104685064e-06,
      "loss": 0.4778,
      "step": 44920
    },
    {
      "epoch": 1.3799342610512089,
      "grad_norm": 0.4254327714443207,
      "learning_rate": 4.392819941199694e-06,
      "loss": 0.5342,
      "step": 44921
    },
    {
      "epoch": 1.379964980186158,
      "grad_norm": 0.42567992210388184,
      "learning_rate": 4.392419790810285e-06,
      "loss": 0.4489,
      "step": 44922
    },
    {
      "epoch": 1.379995699321107,
      "grad_norm": 0.41093242168426514,
      "learning_rate": 4.3920196535177706e-06,
      "loss": 0.4552,
      "step": 44923
    },
    {
      "epoch": 1.3800264184560562,
      "grad_norm": 0.4347199499607086,
      "learning_rate": 4.391619529323086e-06,
      "loss": 0.4256,
      "step": 44924
    },
    {
      "epoch": 1.3800571375910056,
      "grad_norm": 0.4066554307937622,
      "learning_rate": 4.391219418227169e-06,
      "loss": 0.5221,
      "step": 44925
    },
    {
      "epoch": 1.3800878567259547,
      "grad_norm": 0.4373356103897095,
      "learning_rate": 4.390819320230947e-06,
      "loss": 0.4754,
      "step": 44926
    },
    {
      "epoch": 1.3801185758609038,
      "grad_norm": 0.4295397698879242,
      "learning_rate": 4.390419235335359e-06,
      "loss": 0.477,
      "step": 44927
    },
    {
      "epoch": 1.380149294995853,
      "grad_norm": 0.4401175081729889,
      "learning_rate": 4.390019163541338e-06,
      "loss": 0.5145,
      "step": 44928
    },
    {
      "epoch": 1.380180014130802,
      "grad_norm": 0.4352037012577057,
      "learning_rate": 4.389619104849822e-06,
      "loss": 0.4914,
      "step": 44929
    },
    {
      "epoch": 1.3802107332657512,
      "grad_norm": 0.4034302234649658,
      "learning_rate": 4.38921905926174e-06,
      "loss": 0.3861,
      "step": 44930
    },
    {
      "epoch": 1.3802414524007003,
      "grad_norm": 0.4182409644126892,
      "learning_rate": 4.38881902677803e-06,
      "loss": 0.5433,
      "step": 44931
    },
    {
      "epoch": 1.3802721715356496,
      "grad_norm": 0.43219220638275146,
      "learning_rate": 4.388419007399623e-06,
      "loss": 0.4744,
      "step": 44932
    },
    {
      "epoch": 1.3803028906705987,
      "grad_norm": 0.3958863317966461,
      "learning_rate": 4.388019001127459e-06,
      "loss": 0.5007,
      "step": 44933
    },
    {
      "epoch": 1.3803336098055479,
      "grad_norm": 0.4097878038883209,
      "learning_rate": 4.387619007962465e-06,
      "loss": 0.5116,
      "step": 44934
    },
    {
      "epoch": 1.380364328940497,
      "grad_norm": 0.39220625162124634,
      "learning_rate": 4.38721902790558e-06,
      "loss": 0.4892,
      "step": 44935
    },
    {
      "epoch": 1.3803950480754463,
      "grad_norm": 0.48026394844055176,
      "learning_rate": 4.386819060957735e-06,
      "loss": 0.5337,
      "step": 44936
    },
    {
      "epoch": 1.3804257672103954,
      "grad_norm": 0.40454983711242676,
      "learning_rate": 4.386419107119871e-06,
      "loss": 0.4327,
      "step": 44937
    },
    {
      "epoch": 1.3804564863453446,
      "grad_norm": 0.41268372535705566,
      "learning_rate": 4.386019166392914e-06,
      "loss": 0.4647,
      "step": 44938
    },
    {
      "epoch": 1.3804872054802937,
      "grad_norm": 0.4080410897731781,
      "learning_rate": 4.3856192387778e-06,
      "loss": 0.386,
      "step": 44939
    },
    {
      "epoch": 1.3805179246152428,
      "grad_norm": 0.401532381772995,
      "learning_rate": 4.385219324275465e-06,
      "loss": 0.4356,
      "step": 44940
    },
    {
      "epoch": 1.380548643750192,
      "grad_norm": 0.44954872131347656,
      "learning_rate": 4.384819422886842e-06,
      "loss": 0.4999,
      "step": 44941
    },
    {
      "epoch": 1.380579362885141,
      "grad_norm": 0.4642622768878937,
      "learning_rate": 4.3844195346128705e-06,
      "loss": 0.3936,
      "step": 44942
    },
    {
      "epoch": 1.3806100820200904,
      "grad_norm": 0.4179628789424896,
      "learning_rate": 4.384019659454475e-06,
      "loss": 0.4848,
      "step": 44943
    },
    {
      "epoch": 1.3806408011550395,
      "grad_norm": 0.419301301240921,
      "learning_rate": 4.383619797412593e-06,
      "loss": 0.3981,
      "step": 44944
    },
    {
      "epoch": 1.3806715202899886,
      "grad_norm": 0.42312857508659363,
      "learning_rate": 4.38321994848816e-06,
      "loss": 0.4142,
      "step": 44945
    },
    {
      "epoch": 1.3807022394249377,
      "grad_norm": 0.4331713914871216,
      "learning_rate": 4.382820112682112e-06,
      "loss": 0.5478,
      "step": 44946
    },
    {
      "epoch": 1.380732958559887,
      "grad_norm": 0.43372270464897156,
      "learning_rate": 4.382420289995377e-06,
      "loss": 0.4245,
      "step": 44947
    },
    {
      "epoch": 1.3807636776948362,
      "grad_norm": 0.43949928879737854,
      "learning_rate": 4.382020480428895e-06,
      "loss": 0.4363,
      "step": 44948
    },
    {
      "epoch": 1.3807943968297853,
      "grad_norm": 0.4275069236755371,
      "learning_rate": 4.381620683983589e-06,
      "loss": 0.5007,
      "step": 44949
    },
    {
      "epoch": 1.3808251159647345,
      "grad_norm": 0.3665573298931122,
      "learning_rate": 4.381220900660409e-06,
      "loss": 0.4198,
      "step": 44950
    },
    {
      "epoch": 1.3808558350996836,
      "grad_norm": 0.42844757437705994,
      "learning_rate": 4.380821130460274e-06,
      "loss": 0.5698,
      "step": 44951
    },
    {
      "epoch": 1.3808865542346327,
      "grad_norm": 0.4227513372898102,
      "learning_rate": 4.380421373384129e-06,
      "loss": 0.4809,
      "step": 44952
    },
    {
      "epoch": 1.3809172733695818,
      "grad_norm": 0.41929107904434204,
      "learning_rate": 4.380021629432899e-06,
      "loss": 0.4458,
      "step": 44953
    },
    {
      "epoch": 1.3809479925045312,
      "grad_norm": 0.41018146276474,
      "learning_rate": 4.37962189860752e-06,
      "loss": 0.4473,
      "step": 44954
    },
    {
      "epoch": 1.3809787116394803,
      "grad_norm": 0.3972978889942169,
      "learning_rate": 4.379222180908926e-06,
      "loss": 0.5061,
      "step": 44955
    },
    {
      "epoch": 1.3810094307744294,
      "grad_norm": 0.4133570194244385,
      "learning_rate": 4.378822476338056e-06,
      "loss": 0.417,
      "step": 44956
    },
    {
      "epoch": 1.3810401499093785,
      "grad_norm": 0.4240541458129883,
      "learning_rate": 4.378422784895835e-06,
      "loss": 0.435,
      "step": 44957
    },
    {
      "epoch": 1.3810708690443276,
      "grad_norm": 0.4784439206123352,
      "learning_rate": 4.3780231065832e-06,
      "loss": 0.4795,
      "step": 44958
    },
    {
      "epoch": 1.381101588179277,
      "grad_norm": 0.3929182291030884,
      "learning_rate": 4.3776234414010845e-06,
      "loss": 0.4623,
      "step": 44959
    },
    {
      "epoch": 1.381132307314226,
      "grad_norm": 0.39274707436561584,
      "learning_rate": 4.377223789350422e-06,
      "loss": 0.4711,
      "step": 44960
    },
    {
      "epoch": 1.3811630264491752,
      "grad_norm": 0.4346473813056946,
      "learning_rate": 4.376824150432151e-06,
      "loss": 0.4471,
      "step": 44961
    },
    {
      "epoch": 1.3811937455841243,
      "grad_norm": 0.5852795839309692,
      "learning_rate": 4.376424524647195e-06,
      "loss": 0.482,
      "step": 44962
    },
    {
      "epoch": 1.3812244647190735,
      "grad_norm": 0.41951069235801697,
      "learning_rate": 4.3760249119964914e-06,
      "loss": 0.4506,
      "step": 44963
    },
    {
      "epoch": 1.3812551838540226,
      "grad_norm": 0.39858195185661316,
      "learning_rate": 4.375625312480975e-06,
      "loss": 0.4188,
      "step": 44964
    },
    {
      "epoch": 1.3812859029889717,
      "grad_norm": 0.4179579019546509,
      "learning_rate": 4.3752257261015825e-06,
      "loss": 0.4706,
      "step": 44965
    },
    {
      "epoch": 1.381316622123921,
      "grad_norm": 0.4302007257938385,
      "learning_rate": 4.37482615285924e-06,
      "loss": 0.5154,
      "step": 44966
    },
    {
      "epoch": 1.3813473412588702,
      "grad_norm": 0.5259203910827637,
      "learning_rate": 4.374426592754883e-06,
      "loss": 0.4614,
      "step": 44967
    },
    {
      "epoch": 1.3813780603938193,
      "grad_norm": 0.4038185477256775,
      "learning_rate": 4.374027045789446e-06,
      "loss": 0.4224,
      "step": 44968
    },
    {
      "epoch": 1.3814087795287684,
      "grad_norm": 0.4103636145591736,
      "learning_rate": 4.373627511963866e-06,
      "loss": 0.4938,
      "step": 44969
    },
    {
      "epoch": 1.3814394986637177,
      "grad_norm": 0.39845335483551025,
      "learning_rate": 4.373227991279067e-06,
      "loss": 0.3993,
      "step": 44970
    },
    {
      "epoch": 1.3814702177986669,
      "grad_norm": 0.4513855278491974,
      "learning_rate": 4.372828483735988e-06,
      "loss": 0.4819,
      "step": 44971
    },
    {
      "epoch": 1.381500936933616,
      "grad_norm": 0.4237186908721924,
      "learning_rate": 4.372428989335561e-06,
      "loss": 0.5164,
      "step": 44972
    },
    {
      "epoch": 1.381531656068565,
      "grad_norm": 0.3960305154323578,
      "learning_rate": 4.372029508078722e-06,
      "loss": 0.426,
      "step": 44973
    },
    {
      "epoch": 1.3815623752035142,
      "grad_norm": 0.39499858021736145,
      "learning_rate": 4.371630039966398e-06,
      "loss": 0.454,
      "step": 44974
    },
    {
      "epoch": 1.3815930943384633,
      "grad_norm": 0.5383108258247375,
      "learning_rate": 4.371230584999528e-06,
      "loss": 0.464,
      "step": 44975
    },
    {
      "epoch": 1.3816238134734125,
      "grad_norm": 0.4163593649864197,
      "learning_rate": 4.370831143179036e-06,
      "loss": 0.4999,
      "step": 44976
    },
    {
      "epoch": 1.3816545326083618,
      "grad_norm": 0.4085906445980072,
      "learning_rate": 4.370431714505869e-06,
      "loss": 0.4836,
      "step": 44977
    },
    {
      "epoch": 1.381685251743311,
      "grad_norm": 0.4436596930027008,
      "learning_rate": 4.370032298980946e-06,
      "loss": 0.5375,
      "step": 44978
    },
    {
      "epoch": 1.38171597087826,
      "grad_norm": 0.4786318242549896,
      "learning_rate": 4.369632896605207e-06,
      "loss": 0.4832,
      "step": 44979
    },
    {
      "epoch": 1.3817466900132092,
      "grad_norm": 0.40063247084617615,
      "learning_rate": 4.3692335073795835e-06,
      "loss": 0.456,
      "step": 44980
    },
    {
      "epoch": 1.3817774091481585,
      "grad_norm": 0.4000871777534485,
      "learning_rate": 4.368834131305009e-06,
      "loss": 0.4801,
      "step": 44981
    },
    {
      "epoch": 1.3818081282831076,
      "grad_norm": 0.6027899980545044,
      "learning_rate": 4.368434768382418e-06,
      "loss": 0.4907,
      "step": 44982
    },
    {
      "epoch": 1.3818388474180567,
      "grad_norm": 0.3942249119281769,
      "learning_rate": 4.368035418612738e-06,
      "loss": 0.417,
      "step": 44983
    },
    {
      "epoch": 1.3818695665530059,
      "grad_norm": 0.4618731439113617,
      "learning_rate": 4.367636081996908e-06,
      "loss": 0.4496,
      "step": 44984
    },
    {
      "epoch": 1.381900285687955,
      "grad_norm": 0.4313971996307373,
      "learning_rate": 4.36723675853585e-06,
      "loss": 0.5239,
      "step": 44985
    },
    {
      "epoch": 1.381931004822904,
      "grad_norm": 0.42302900552749634,
      "learning_rate": 4.366837448230511e-06,
      "loss": 0.507,
      "step": 44986
    },
    {
      "epoch": 1.3819617239578532,
      "grad_norm": 0.398303359746933,
      "learning_rate": 4.3664381510818135e-06,
      "loss": 0.4153,
      "step": 44987
    },
    {
      "epoch": 1.3819924430928026,
      "grad_norm": 0.39416995644569397,
      "learning_rate": 4.366038867090696e-06,
      "loss": 0.4931,
      "step": 44988
    },
    {
      "epoch": 1.3820231622277517,
      "grad_norm": 0.4246542155742645,
      "learning_rate": 4.365639596258085e-06,
      "loss": 0.483,
      "step": 44989
    },
    {
      "epoch": 1.3820538813627008,
      "grad_norm": 0.4019452929496765,
      "learning_rate": 4.365240338584917e-06,
      "loss": 0.4553,
      "step": 44990
    },
    {
      "epoch": 1.38208460049765,
      "grad_norm": 0.47418925166130066,
      "learning_rate": 4.3648410940721235e-06,
      "loss": 0.4901,
      "step": 44991
    },
    {
      "epoch": 1.3821153196325993,
      "grad_norm": 0.3998618721961975,
      "learning_rate": 4.36444186272064e-06,
      "loss": 0.4534,
      "step": 44992
    },
    {
      "epoch": 1.3821460387675484,
      "grad_norm": 0.42504286766052246,
      "learning_rate": 4.364042644531392e-06,
      "loss": 0.4548,
      "step": 44993
    },
    {
      "epoch": 1.3821767579024975,
      "grad_norm": 0.42410245537757874,
      "learning_rate": 4.3636434395053176e-06,
      "loss": 0.4302,
      "step": 44994
    },
    {
      "epoch": 1.3822074770374466,
      "grad_norm": 0.39811640977859497,
      "learning_rate": 4.363244247643347e-06,
      "loss": 0.4731,
      "step": 44995
    },
    {
      "epoch": 1.3822381961723957,
      "grad_norm": 0.3730652630329132,
      "learning_rate": 4.3628450689464115e-06,
      "loss": 0.4149,
      "step": 44996
    },
    {
      "epoch": 1.3822689153073449,
      "grad_norm": 0.4353092610836029,
      "learning_rate": 4.362445903415451e-06,
      "loss": 0.5261,
      "step": 44997
    },
    {
      "epoch": 1.382299634442294,
      "grad_norm": 0.410220742225647,
      "learning_rate": 4.3620467510513876e-06,
      "loss": 0.5093,
      "step": 44998
    },
    {
      "epoch": 1.3823303535772433,
      "grad_norm": 0.44682812690734863,
      "learning_rate": 4.361647611855158e-06,
      "loss": 0.4319,
      "step": 44999
    },
    {
      "epoch": 1.3823610727121924,
      "grad_norm": 0.3950254023075104,
      "learning_rate": 4.361248485827693e-06,
      "loss": 0.4696,
      "step": 45000
    },
    {
      "epoch": 1.3823917918471416,
      "grad_norm": 0.4081282913684845,
      "learning_rate": 4.3608493729699296e-06,
      "loss": 0.5441,
      "step": 45001
    },
    {
      "epoch": 1.3824225109820907,
      "grad_norm": 0.422132283449173,
      "learning_rate": 4.360450273282793e-06,
      "loss": 0.4741,
      "step": 45002
    },
    {
      "epoch": 1.38245323011704,
      "grad_norm": 0.41942381858825684,
      "learning_rate": 4.36005118676722e-06,
      "loss": 0.4793,
      "step": 45003
    },
    {
      "epoch": 1.3824839492519891,
      "grad_norm": 0.45523303747177124,
      "learning_rate": 4.35965211342414e-06,
      "loss": 0.5014,
      "step": 45004
    },
    {
      "epoch": 1.3825146683869383,
      "grad_norm": 0.4228026568889618,
      "learning_rate": 4.359253053254491e-06,
      "loss": 0.418,
      "step": 45005
    },
    {
      "epoch": 1.3825453875218874,
      "grad_norm": 0.3947909474372864,
      "learning_rate": 4.358854006259196e-06,
      "loss": 0.5104,
      "step": 45006
    },
    {
      "epoch": 1.3825761066568365,
      "grad_norm": 0.4248512387275696,
      "learning_rate": 4.358454972439191e-06,
      "loss": 0.5111,
      "step": 45007
    },
    {
      "epoch": 1.3826068257917856,
      "grad_norm": 0.4301093816757202,
      "learning_rate": 4.3580559517954095e-06,
      "loss": 0.468,
      "step": 45008
    },
    {
      "epoch": 1.3826375449267347,
      "grad_norm": 0.45560041069984436,
      "learning_rate": 4.3576569443287855e-06,
      "loss": 0.525,
      "step": 45009
    },
    {
      "epoch": 1.382668264061684,
      "grad_norm": 0.4488085210323334,
      "learning_rate": 4.357257950040243e-06,
      "loss": 0.4201,
      "step": 45010
    },
    {
      "epoch": 1.3826989831966332,
      "grad_norm": 0.39904144406318665,
      "learning_rate": 4.356858968930724e-06,
      "loss": 0.4288,
      "step": 45011
    },
    {
      "epoch": 1.3827297023315823,
      "grad_norm": 0.41557255387306213,
      "learning_rate": 4.356460001001147e-06,
      "loss": 0.4283,
      "step": 45012
    },
    {
      "epoch": 1.3827604214665314,
      "grad_norm": 0.4185316562652588,
      "learning_rate": 4.35606104625246e-06,
      "loss": 0.4523,
      "step": 45013
    },
    {
      "epoch": 1.3827911406014808,
      "grad_norm": 0.4531545042991638,
      "learning_rate": 4.355662104685582e-06,
      "loss": 0.4974,
      "step": 45014
    },
    {
      "epoch": 1.38282185973643,
      "grad_norm": 0.4234490990638733,
      "learning_rate": 4.355263176301449e-06,
      "loss": 0.5196,
      "step": 45015
    },
    {
      "epoch": 1.382852578871379,
      "grad_norm": 0.4005524516105652,
      "learning_rate": 4.354864261100997e-06,
      "loss": 0.5088,
      "step": 45016
    },
    {
      "epoch": 1.3828832980063281,
      "grad_norm": 0.43772485852241516,
      "learning_rate": 4.354465359085147e-06,
      "loss": 0.4351,
      "step": 45017
    },
    {
      "epoch": 1.3829140171412773,
      "grad_norm": 0.44966021180152893,
      "learning_rate": 4.354066470254844e-06,
      "loss": 0.4647,
      "step": 45018
    },
    {
      "epoch": 1.3829447362762264,
      "grad_norm": 0.426686555147171,
      "learning_rate": 4.353667594611011e-06,
      "loss": 0.4153,
      "step": 45019
    },
    {
      "epoch": 1.3829754554111755,
      "grad_norm": 0.4832238256931305,
      "learning_rate": 4.353268732154583e-06,
      "loss": 0.4199,
      "step": 45020
    },
    {
      "epoch": 1.3830061745461248,
      "grad_norm": 0.42000165581703186,
      "learning_rate": 4.3528698828864844e-06,
      "loss": 0.4863,
      "step": 45021
    },
    {
      "epoch": 1.383036893681074,
      "grad_norm": 0.37527862191200256,
      "learning_rate": 4.35247104680766e-06,
      "loss": 0.4272,
      "step": 45022
    },
    {
      "epoch": 1.383067612816023,
      "grad_norm": 0.40138593316078186,
      "learning_rate": 4.352072223919029e-06,
      "loss": 0.4549,
      "step": 45023
    },
    {
      "epoch": 1.3830983319509722,
      "grad_norm": 0.4007977247238159,
      "learning_rate": 4.3516734142215335e-06,
      "loss": 0.4476,
      "step": 45024
    },
    {
      "epoch": 1.3831290510859215,
      "grad_norm": 0.4506972134113312,
      "learning_rate": 4.351274617716093e-06,
      "loss": 0.5433,
      "step": 45025
    },
    {
      "epoch": 1.3831597702208707,
      "grad_norm": 0.4197165369987488,
      "learning_rate": 4.350875834403647e-06,
      "loss": 0.4602,
      "step": 45026
    },
    {
      "epoch": 1.3831904893558198,
      "grad_norm": 0.4063693881034851,
      "learning_rate": 4.350477064285125e-06,
      "loss": 0.4337,
      "step": 45027
    },
    {
      "epoch": 1.383221208490769,
      "grad_norm": 0.45822814106941223,
      "learning_rate": 4.350078307361461e-06,
      "loss": 0.5238,
      "step": 45028
    },
    {
      "epoch": 1.383251927625718,
      "grad_norm": 0.4153074622154236,
      "learning_rate": 4.349679563633581e-06,
      "loss": 0.4617,
      "step": 45029
    },
    {
      "epoch": 1.3832826467606671,
      "grad_norm": 0.4565032422542572,
      "learning_rate": 4.349280833102418e-06,
      "loss": 0.4936,
      "step": 45030
    },
    {
      "epoch": 1.3833133658956163,
      "grad_norm": 0.43489930033683777,
      "learning_rate": 4.348882115768906e-06,
      "loss": 0.4939,
      "step": 45031
    },
    {
      "epoch": 1.3833440850305656,
      "grad_norm": 0.4143228232860565,
      "learning_rate": 4.348483411633975e-06,
      "loss": 0.4305,
      "step": 45032
    },
    {
      "epoch": 1.3833748041655147,
      "grad_norm": 0.41434919834136963,
      "learning_rate": 4.348084720698554e-06,
      "loss": 0.5127,
      "step": 45033
    },
    {
      "epoch": 1.3834055233004638,
      "grad_norm": 0.43333396315574646,
      "learning_rate": 4.347686042963577e-06,
      "loss": 0.5123,
      "step": 45034
    },
    {
      "epoch": 1.383436242435413,
      "grad_norm": 0.41624292731285095,
      "learning_rate": 4.347287378429973e-06,
      "loss": 0.5276,
      "step": 45035
    },
    {
      "epoch": 1.3834669615703623,
      "grad_norm": 0.4251752197742462,
      "learning_rate": 4.3468887270986735e-06,
      "loss": 0.4614,
      "step": 45036
    },
    {
      "epoch": 1.3834976807053114,
      "grad_norm": 0.4165501892566681,
      "learning_rate": 4.3464900889706145e-06,
      "loss": 0.5629,
      "step": 45037
    },
    {
      "epoch": 1.3835283998402605,
      "grad_norm": 0.40603873133659363,
      "learning_rate": 4.346091464046719e-06,
      "loss": 0.5236,
      "step": 45038
    },
    {
      "epoch": 1.3835591189752097,
      "grad_norm": 0.4667354226112366,
      "learning_rate": 4.345692852327921e-06,
      "loss": 0.5908,
      "step": 45039
    },
    {
      "epoch": 1.3835898381101588,
      "grad_norm": 0.4243395924568176,
      "learning_rate": 4.345294253815153e-06,
      "loss": 0.4768,
      "step": 45040
    },
    {
      "epoch": 1.383620557245108,
      "grad_norm": 0.4061248302459717,
      "learning_rate": 4.344895668509349e-06,
      "loss": 0.4427,
      "step": 45041
    },
    {
      "epoch": 1.383651276380057,
      "grad_norm": 0.4722246825695038,
      "learning_rate": 4.344497096411432e-06,
      "loss": 0.5398,
      "step": 45042
    },
    {
      "epoch": 1.3836819955150064,
      "grad_norm": 0.4285775423049927,
      "learning_rate": 4.344098537522337e-06,
      "loss": 0.4607,
      "step": 45043
    },
    {
      "epoch": 1.3837127146499555,
      "grad_norm": 0.42504364252090454,
      "learning_rate": 4.343699991842994e-06,
      "loss": 0.5053,
      "step": 45044
    },
    {
      "epoch": 1.3837434337849046,
      "grad_norm": 0.4555623233318329,
      "learning_rate": 4.34330145937434e-06,
      "loss": 0.4732,
      "step": 45045
    },
    {
      "epoch": 1.3837741529198537,
      "grad_norm": 0.4413955807685852,
      "learning_rate": 4.342902940117296e-06,
      "loss": 0.4636,
      "step": 45046
    },
    {
      "epoch": 1.383804872054803,
      "grad_norm": 0.41681984066963196,
      "learning_rate": 4.342504434072802e-06,
      "loss": 0.4739,
      "step": 45047
    },
    {
      "epoch": 1.3838355911897522,
      "grad_norm": 0.4119839668273926,
      "learning_rate": 4.342105941241775e-06,
      "loss": 0.4887,
      "step": 45048
    },
    {
      "epoch": 1.3838663103247013,
      "grad_norm": 0.4403883218765259,
      "learning_rate": 4.341707461625163e-06,
      "loss": 0.5013,
      "step": 45049
    },
    {
      "epoch": 1.3838970294596504,
      "grad_norm": 0.4346427321434021,
      "learning_rate": 4.341308995223885e-06,
      "loss": 0.5263,
      "step": 45050
    },
    {
      "epoch": 1.3839277485945995,
      "grad_norm": 0.42318227887153625,
      "learning_rate": 4.340910542038874e-06,
      "loss": 0.4649,
      "step": 45051
    },
    {
      "epoch": 1.3839584677295487,
      "grad_norm": 0.4288671910762787,
      "learning_rate": 4.340512102071066e-06,
      "loss": 0.5188,
      "step": 45052
    },
    {
      "epoch": 1.3839891868644978,
      "grad_norm": 0.4157964289188385,
      "learning_rate": 4.34011367532138e-06,
      "loss": 0.4984,
      "step": 45053
    },
    {
      "epoch": 1.3840199059994471,
      "grad_norm": 0.46821266412734985,
      "learning_rate": 4.3397152617907615e-06,
      "loss": 0.5471,
      "step": 45054
    },
    {
      "epoch": 1.3840506251343963,
      "grad_norm": 0.4273652732372284,
      "learning_rate": 4.33931686148013e-06,
      "loss": 0.4857,
      "step": 45055
    },
    {
      "epoch": 1.3840813442693454,
      "grad_norm": 0.4160335063934326,
      "learning_rate": 4.338918474390421e-06,
      "loss": 0.4979,
      "step": 45056
    },
    {
      "epoch": 1.3841120634042945,
      "grad_norm": 0.39232155680656433,
      "learning_rate": 4.338520100522561e-06,
      "loss": 0.4869,
      "step": 45057
    },
    {
      "epoch": 1.3841427825392438,
      "grad_norm": 0.4308665096759796,
      "learning_rate": 4.338121739877482e-06,
      "loss": 0.4327,
      "step": 45058
    },
    {
      "epoch": 1.384173501674193,
      "grad_norm": 0.41968175768852234,
      "learning_rate": 4.3377233924561155e-06,
      "loss": 0.4989,
      "step": 45059
    },
    {
      "epoch": 1.384204220809142,
      "grad_norm": 0.43102511763572693,
      "learning_rate": 4.337325058259395e-06,
      "loss": 0.5017,
      "step": 45060
    },
    {
      "epoch": 1.3842349399440912,
      "grad_norm": 0.427007794380188,
      "learning_rate": 4.336926737288244e-06,
      "loss": 0.5267,
      "step": 45061
    },
    {
      "epoch": 1.3842656590790403,
      "grad_norm": 0.41407081484794617,
      "learning_rate": 4.336528429543596e-06,
      "loss": 0.4325,
      "step": 45062
    },
    {
      "epoch": 1.3842963782139894,
      "grad_norm": 0.43091732263565063,
      "learning_rate": 4.336130135026382e-06,
      "loss": 0.5039,
      "step": 45063
    },
    {
      "epoch": 1.3843270973489386,
      "grad_norm": 0.40455082058906555,
      "learning_rate": 4.335731853737534e-06,
      "loss": 0.401,
      "step": 45064
    },
    {
      "epoch": 1.384357816483888,
      "grad_norm": 0.4202820956707001,
      "learning_rate": 4.335333585677976e-06,
      "loss": 0.5067,
      "step": 45065
    },
    {
      "epoch": 1.384388535618837,
      "grad_norm": 0.44051483273506165,
      "learning_rate": 4.334935330848644e-06,
      "loss": 0.5591,
      "step": 45066
    },
    {
      "epoch": 1.3844192547537861,
      "grad_norm": 0.5162886381149292,
      "learning_rate": 4.334537089250464e-06,
      "loss": 0.4488,
      "step": 45067
    },
    {
      "epoch": 1.3844499738887353,
      "grad_norm": 0.44976961612701416,
      "learning_rate": 4.334138860884374e-06,
      "loss": 0.4783,
      "step": 45068
    },
    {
      "epoch": 1.3844806930236844,
      "grad_norm": 0.44762250781059265,
      "learning_rate": 4.333740645751293e-06,
      "loss": 0.4397,
      "step": 45069
    },
    {
      "epoch": 1.3845114121586337,
      "grad_norm": 0.5016317963600159,
      "learning_rate": 4.333342443852158e-06,
      "loss": 0.4108,
      "step": 45070
    },
    {
      "epoch": 1.3845421312935828,
      "grad_norm": 0.4598798453807831,
      "learning_rate": 4.332944255187896e-06,
      "loss": 0.511,
      "step": 45071
    },
    {
      "epoch": 1.384572850428532,
      "grad_norm": 0.38752609491348267,
      "learning_rate": 4.332546079759439e-06,
      "loss": 0.5415,
      "step": 45072
    },
    {
      "epoch": 1.384603569563481,
      "grad_norm": 0.4380740821361542,
      "learning_rate": 4.332147917567721e-06,
      "loss": 0.5124,
      "step": 45073
    },
    {
      "epoch": 1.3846342886984302,
      "grad_norm": 0.3726962208747864,
      "learning_rate": 4.331749768613662e-06,
      "loss": 0.3886,
      "step": 45074
    },
    {
      "epoch": 1.3846650078333793,
      "grad_norm": 0.4817903935909271,
      "learning_rate": 4.3313516328981984e-06,
      "loss": 0.4083,
      "step": 45075
    },
    {
      "epoch": 1.3846957269683287,
      "grad_norm": 0.4988669753074646,
      "learning_rate": 4.3309535104222585e-06,
      "loss": 0.4693,
      "step": 45076
    },
    {
      "epoch": 1.3847264461032778,
      "grad_norm": 0.4459739625453949,
      "learning_rate": 4.330555401186777e-06,
      "loss": 0.4382,
      "step": 45077
    },
    {
      "epoch": 1.384757165238227,
      "grad_norm": 0.4525638818740845,
      "learning_rate": 4.330157305192675e-06,
      "loss": 0.3999,
      "step": 45078
    },
    {
      "epoch": 1.384787884373176,
      "grad_norm": 0.4272109270095825,
      "learning_rate": 4.32975922244089e-06,
      "loss": 0.5023,
      "step": 45079
    },
    {
      "epoch": 1.3848186035081251,
      "grad_norm": 0.43780872225761414,
      "learning_rate": 4.329361152932341e-06,
      "loss": 0.3832,
      "step": 45080
    },
    {
      "epoch": 1.3848493226430745,
      "grad_norm": 0.44070330262184143,
      "learning_rate": 4.328963096667973e-06,
      "loss": 0.3901,
      "step": 45081
    },
    {
      "epoch": 1.3848800417780236,
      "grad_norm": 0.42049700021743774,
      "learning_rate": 4.328565053648704e-06,
      "loss": 0.4777,
      "step": 45082
    },
    {
      "epoch": 1.3849107609129727,
      "grad_norm": 0.43186643719673157,
      "learning_rate": 4.328167023875471e-06,
      "loss": 0.4704,
      "step": 45083
    },
    {
      "epoch": 1.3849414800479218,
      "grad_norm": 0.43395909667015076,
      "learning_rate": 4.327769007349193e-06,
      "loss": 0.5563,
      "step": 45084
    },
    {
      "epoch": 1.384972199182871,
      "grad_norm": 0.4087022840976715,
      "learning_rate": 4.3273710040708125e-06,
      "loss": 0.4918,
      "step": 45085
    },
    {
      "epoch": 1.38500291831782,
      "grad_norm": 0.3971635699272156,
      "learning_rate": 4.326973014041251e-06,
      "loss": 0.5065,
      "step": 45086
    },
    {
      "epoch": 1.3850336374527692,
      "grad_norm": 0.4104103446006775,
      "learning_rate": 4.32657503726144e-06,
      "loss": 0.4519,
      "step": 45087
    },
    {
      "epoch": 1.3850643565877185,
      "grad_norm": 0.6200987100601196,
      "learning_rate": 4.326177073732313e-06,
      "loss": 0.5017,
      "step": 45088
    },
    {
      "epoch": 1.3850950757226677,
      "grad_norm": 0.4451451301574707,
      "learning_rate": 4.325779123454787e-06,
      "loss": 0.4298,
      "step": 45089
    },
    {
      "epoch": 1.3851257948576168,
      "grad_norm": 0.4987509846687317,
      "learning_rate": 4.32538118642981e-06,
      "loss": 0.4698,
      "step": 45090
    },
    {
      "epoch": 1.385156513992566,
      "grad_norm": 0.40247073769569397,
      "learning_rate": 4.324983262658295e-06,
      "loss": 0.4001,
      "step": 45091
    },
    {
      "epoch": 1.3851872331275152,
      "grad_norm": 0.38739675283432007,
      "learning_rate": 4.324585352141184e-06,
      "loss": 0.4694,
      "step": 45092
    },
    {
      "epoch": 1.3852179522624644,
      "grad_norm": 0.4439506232738495,
      "learning_rate": 4.324187454879396e-06,
      "loss": 0.5167,
      "step": 45093
    },
    {
      "epoch": 1.3852486713974135,
      "grad_norm": 0.41334763169288635,
      "learning_rate": 4.3237895708738645e-06,
      "loss": 0.4464,
      "step": 45094
    },
    {
      "epoch": 1.3852793905323626,
      "grad_norm": 0.3955840468406677,
      "learning_rate": 4.3233917001255175e-06,
      "loss": 0.4793,
      "step": 45095
    },
    {
      "epoch": 1.3853101096673117,
      "grad_norm": 0.39977261424064636,
      "learning_rate": 4.322993842635291e-06,
      "loss": 0.4862,
      "step": 45096
    },
    {
      "epoch": 1.3853408288022608,
      "grad_norm": 0.4375919997692108,
      "learning_rate": 4.322595998404104e-06,
      "loss": 0.5402,
      "step": 45097
    },
    {
      "epoch": 1.38537154793721,
      "grad_norm": 0.39100202918052673,
      "learning_rate": 4.322198167432892e-06,
      "loss": 0.4704,
      "step": 45098
    },
    {
      "epoch": 1.3854022670721593,
      "grad_norm": 0.4087960422039032,
      "learning_rate": 4.321800349722581e-06,
      "loss": 0.4388,
      "step": 45099
    },
    {
      "epoch": 1.3854329862071084,
      "grad_norm": 0.38957592844963074,
      "learning_rate": 4.321402545274107e-06,
      "loss": 0.5079,
      "step": 45100
    },
    {
      "epoch": 1.3854637053420575,
      "grad_norm": 0.43912237882614136,
      "learning_rate": 4.32100475408839e-06,
      "loss": 0.4341,
      "step": 45101
    },
    {
      "epoch": 1.3854944244770067,
      "grad_norm": 0.4228360950946808,
      "learning_rate": 4.320606976166363e-06,
      "loss": 0.4463,
      "step": 45102
    },
    {
      "epoch": 1.385525143611956,
      "grad_norm": 0.4264111816883087,
      "learning_rate": 4.320209211508954e-06,
      "loss": 0.5595,
      "step": 45103
    },
    {
      "epoch": 1.3855558627469051,
      "grad_norm": 0.3859657049179077,
      "learning_rate": 4.319811460117098e-06,
      "loss": 0.5118,
      "step": 45104
    },
    {
      "epoch": 1.3855865818818542,
      "grad_norm": 0.46627870202064514,
      "learning_rate": 4.3194137219917144e-06,
      "loss": 0.4582,
      "step": 45105
    },
    {
      "epoch": 1.3856173010168034,
      "grad_norm": 0.43316733837127686,
      "learning_rate": 4.319015997133737e-06,
      "loss": 0.4085,
      "step": 45106
    },
    {
      "epoch": 1.3856480201517525,
      "grad_norm": 0.38253334164619446,
      "learning_rate": 4.318618285544095e-06,
      "loss": 0.4583,
      "step": 45107
    },
    {
      "epoch": 1.3856787392867016,
      "grad_norm": 0.40101122856140137,
      "learning_rate": 4.318220587223717e-06,
      "loss": 0.4999,
      "step": 45108
    },
    {
      "epoch": 1.3857094584216507,
      "grad_norm": 0.40353167057037354,
      "learning_rate": 4.317822902173534e-06,
      "loss": 0.493,
      "step": 45109
    },
    {
      "epoch": 1.3857401775566,
      "grad_norm": 0.4814711809158325,
      "learning_rate": 4.31742523039447e-06,
      "loss": 0.3744,
      "step": 45110
    },
    {
      "epoch": 1.3857708966915492,
      "grad_norm": 0.42321377992630005,
      "learning_rate": 4.3170275718874556e-06,
      "loss": 0.481,
      "step": 45111
    },
    {
      "epoch": 1.3858016158264983,
      "grad_norm": 0.8343378901481628,
      "learning_rate": 4.3166299266534205e-06,
      "loss": 0.4485,
      "step": 45112
    },
    {
      "epoch": 1.3858323349614474,
      "grad_norm": 0.41211366653442383,
      "learning_rate": 4.316232294693296e-06,
      "loss": 0.4487,
      "step": 45113
    },
    {
      "epoch": 1.3858630540963968,
      "grad_norm": 0.43853744864463806,
      "learning_rate": 4.315834676008006e-06,
      "loss": 0.4884,
      "step": 45114
    },
    {
      "epoch": 1.3858937732313459,
      "grad_norm": 0.41618916392326355,
      "learning_rate": 4.315437070598484e-06,
      "loss": 0.5071,
      "step": 45115
    },
    {
      "epoch": 1.385924492366295,
      "grad_norm": 0.42207592725753784,
      "learning_rate": 4.315039478465648e-06,
      "loss": 0.4934,
      "step": 45116
    },
    {
      "epoch": 1.3859552115012441,
      "grad_norm": 0.4105253517627716,
      "learning_rate": 4.314641899610441e-06,
      "loss": 0.4541,
      "step": 45117
    },
    {
      "epoch": 1.3859859306361932,
      "grad_norm": 0.3932763934135437,
      "learning_rate": 4.3142443340337824e-06,
      "loss": 0.4805,
      "step": 45118
    },
    {
      "epoch": 1.3860166497711424,
      "grad_norm": 0.45290160179138184,
      "learning_rate": 4.313846781736607e-06,
      "loss": 0.495,
      "step": 45119
    },
    {
      "epoch": 1.3860473689060915,
      "grad_norm": 0.4040023684501648,
      "learning_rate": 4.313449242719835e-06,
      "loss": 0.5279,
      "step": 45120
    },
    {
      "epoch": 1.3860780880410408,
      "grad_norm": 0.41554737091064453,
      "learning_rate": 4.3130517169844e-06,
      "loss": 0.524,
      "step": 45121
    },
    {
      "epoch": 1.38610880717599,
      "grad_norm": 0.4134489893913269,
      "learning_rate": 4.312654204531229e-06,
      "loss": 0.4477,
      "step": 45122
    },
    {
      "epoch": 1.386139526310939,
      "grad_norm": 0.46205994486808777,
      "learning_rate": 4.312256705361256e-06,
      "loss": 0.5423,
      "step": 45123
    },
    {
      "epoch": 1.3861702454458882,
      "grad_norm": 0.40722280740737915,
      "learning_rate": 4.3118592194754e-06,
      "loss": 0.4838,
      "step": 45124
    },
    {
      "epoch": 1.3862009645808375,
      "grad_norm": 0.4241454303264618,
      "learning_rate": 4.311461746874592e-06,
      "loss": 0.473,
      "step": 45125
    },
    {
      "epoch": 1.3862316837157866,
      "grad_norm": 0.42228633165359497,
      "learning_rate": 4.311064287559768e-06,
      "loss": 0.4979,
      "step": 45126
    },
    {
      "epoch": 1.3862624028507358,
      "grad_norm": 0.39603662490844727,
      "learning_rate": 4.310666841531849e-06,
      "loss": 0.4779,
      "step": 45127
    },
    {
      "epoch": 1.3862931219856849,
      "grad_norm": 0.3954997658729553,
      "learning_rate": 4.3102694087917675e-06,
      "loss": 0.5141,
      "step": 45128
    },
    {
      "epoch": 1.386323841120634,
      "grad_norm": 0.378249853849411,
      "learning_rate": 4.309871989340445e-06,
      "loss": 0.4762,
      "step": 45129
    },
    {
      "epoch": 1.3863545602555831,
      "grad_norm": 0.5166405439376831,
      "learning_rate": 4.309474583178814e-06,
      "loss": 0.4457,
      "step": 45130
    },
    {
      "epoch": 1.3863852793905322,
      "grad_norm": 0.4141816794872284,
      "learning_rate": 4.309077190307803e-06,
      "loss": 0.4833,
      "step": 45131
    },
    {
      "epoch": 1.3864159985254816,
      "grad_norm": 0.45578789710998535,
      "learning_rate": 4.3086798107283435e-06,
      "loss": 0.4288,
      "step": 45132
    },
    {
      "epoch": 1.3864467176604307,
      "grad_norm": 0.4472728967666626,
      "learning_rate": 4.308282444441356e-06,
      "loss": 0.5875,
      "step": 45133
    },
    {
      "epoch": 1.3864774367953798,
      "grad_norm": 0.44631391763687134,
      "learning_rate": 4.307885091447772e-06,
      "loss": 0.5014,
      "step": 45134
    },
    {
      "epoch": 1.386508155930329,
      "grad_norm": 0.4249335825443268,
      "learning_rate": 4.3074877517485205e-06,
      "loss": 0.4914,
      "step": 45135
    },
    {
      "epoch": 1.3865388750652783,
      "grad_norm": 0.41730740666389465,
      "learning_rate": 4.307090425344531e-06,
      "loss": 0.5433,
      "step": 45136
    },
    {
      "epoch": 1.3865695942002274,
      "grad_norm": 0.3901268541812897,
      "learning_rate": 4.306693112236727e-06,
      "loss": 0.6139,
      "step": 45137
    },
    {
      "epoch": 1.3866003133351765,
      "grad_norm": 0.4451604187488556,
      "learning_rate": 4.306295812426039e-06,
      "loss": 0.5299,
      "step": 45138
    },
    {
      "epoch": 1.3866310324701256,
      "grad_norm": 0.43423914909362793,
      "learning_rate": 4.305898525913395e-06,
      "loss": 0.4008,
      "step": 45139
    },
    {
      "epoch": 1.3866617516050748,
      "grad_norm": 0.42134448885917664,
      "learning_rate": 4.305501252699725e-06,
      "loss": 0.499,
      "step": 45140
    },
    {
      "epoch": 1.3866924707400239,
      "grad_norm": 0.41145059466362,
      "learning_rate": 4.3051039927859514e-06,
      "loss": 0.4545,
      "step": 45141
    },
    {
      "epoch": 1.386723189874973,
      "grad_norm": 0.42003560066223145,
      "learning_rate": 4.304706746173007e-06,
      "loss": 0.5231,
      "step": 45142
    },
    {
      "epoch": 1.3867539090099223,
      "grad_norm": 0.4443073570728302,
      "learning_rate": 4.304309512861815e-06,
      "loss": 0.4776,
      "step": 45143
    },
    {
      "epoch": 1.3867846281448715,
      "grad_norm": 0.43925172090530396,
      "learning_rate": 4.3039122928533075e-06,
      "loss": 0.4817,
      "step": 45144
    },
    {
      "epoch": 1.3868153472798206,
      "grad_norm": 0.44102755188941956,
      "learning_rate": 4.303515086148413e-06,
      "loss": 0.4453,
      "step": 45145
    },
    {
      "epoch": 1.3868460664147697,
      "grad_norm": 0.40864184498786926,
      "learning_rate": 4.303117892748054e-06,
      "loss": 0.4486,
      "step": 45146
    },
    {
      "epoch": 1.386876785549719,
      "grad_norm": 0.4562300145626068,
      "learning_rate": 4.3027207126531624e-06,
      "loss": 0.462,
      "step": 45147
    },
    {
      "epoch": 1.3869075046846682,
      "grad_norm": 0.39196133613586426,
      "learning_rate": 4.302323545864663e-06,
      "loss": 0.4082,
      "step": 45148
    },
    {
      "epoch": 1.3869382238196173,
      "grad_norm": 0.4127257466316223,
      "learning_rate": 4.3019263923834885e-06,
      "loss": 0.4674,
      "step": 45149
    },
    {
      "epoch": 1.3869689429545664,
      "grad_norm": 0.38873398303985596,
      "learning_rate": 4.301529252210559e-06,
      "loss": 0.499,
      "step": 45150
    },
    {
      "epoch": 1.3869996620895155,
      "grad_norm": 0.45380041003227234,
      "learning_rate": 4.30113212534681e-06,
      "loss": 0.4679,
      "step": 45151
    },
    {
      "epoch": 1.3870303812244646,
      "grad_norm": 0.4417973756790161,
      "learning_rate": 4.300735011793158e-06,
      "loss": 0.4107,
      "step": 45152
    },
    {
      "epoch": 1.3870611003594138,
      "grad_norm": 0.4544636905193329,
      "learning_rate": 4.300337911550544e-06,
      "loss": 0.4476,
      "step": 45153
    },
    {
      "epoch": 1.387091819494363,
      "grad_norm": 0.4099816679954529,
      "learning_rate": 4.299940824619886e-06,
      "loss": 0.4377,
      "step": 45154
    },
    {
      "epoch": 1.3871225386293122,
      "grad_norm": 0.4616055488586426,
      "learning_rate": 4.299543751002118e-06,
      "loss": 0.5098,
      "step": 45155
    },
    {
      "epoch": 1.3871532577642613,
      "grad_norm": 0.4121023714542389,
      "learning_rate": 4.299146690698158e-06,
      "loss": 0.5366,
      "step": 45156
    },
    {
      "epoch": 1.3871839768992105,
      "grad_norm": 0.4503307044506073,
      "learning_rate": 4.298749643708942e-06,
      "loss": 0.4328,
      "step": 45157
    },
    {
      "epoch": 1.3872146960341598,
      "grad_norm": 0.44981130957603455,
      "learning_rate": 4.2983526100353925e-06,
      "loss": 0.5341,
      "step": 45158
    },
    {
      "epoch": 1.387245415169109,
      "grad_norm": 0.3873870074748993,
      "learning_rate": 4.297955589678442e-06,
      "loss": 0.4662,
      "step": 45159
    },
    {
      "epoch": 1.387276134304058,
      "grad_norm": 0.4542273283004761,
      "learning_rate": 4.297558582639012e-06,
      "loss": 0.5366,
      "step": 45160
    },
    {
      "epoch": 1.3873068534390072,
      "grad_norm": 0.45455625653266907,
      "learning_rate": 4.297161588918029e-06,
      "loss": 0.3976,
      "step": 45161
    },
    {
      "epoch": 1.3873375725739563,
      "grad_norm": 0.44225013256073,
      "learning_rate": 4.296764608516428e-06,
      "loss": 0.495,
      "step": 45162
    },
    {
      "epoch": 1.3873682917089054,
      "grad_norm": 0.4107506275177002,
      "learning_rate": 4.296367641435131e-06,
      "loss": 0.4708,
      "step": 45163
    },
    {
      "epoch": 1.3873990108438545,
      "grad_norm": 0.47139960527420044,
      "learning_rate": 4.295970687675068e-06,
      "loss": 0.5091,
      "step": 45164
    },
    {
      "epoch": 1.3874297299788039,
      "grad_norm": 0.4349970817565918,
      "learning_rate": 4.29557374723716e-06,
      "loss": 0.4982,
      "step": 45165
    },
    {
      "epoch": 1.387460449113753,
      "grad_norm": 0.3940272927284241,
      "learning_rate": 4.295176820122338e-06,
      "loss": 0.4877,
      "step": 45166
    },
    {
      "epoch": 1.3874911682487021,
      "grad_norm": 0.43526822328567505,
      "learning_rate": 4.294779906331528e-06,
      "loss": 0.4752,
      "step": 45167
    },
    {
      "epoch": 1.3875218873836512,
      "grad_norm": 0.40235304832458496,
      "learning_rate": 4.2943830058656634e-06,
      "loss": 0.4556,
      "step": 45168
    },
    {
      "epoch": 1.3875526065186006,
      "grad_norm": 0.4283219277858734,
      "learning_rate": 4.293986118725661e-06,
      "loss": 0.5193,
      "step": 45169
    },
    {
      "epoch": 1.3875833256535497,
      "grad_norm": 0.40068408846855164,
      "learning_rate": 4.293589244912454e-06,
      "loss": 0.4266,
      "step": 45170
    },
    {
      "epoch": 1.3876140447884988,
      "grad_norm": 0.43365973234176636,
      "learning_rate": 4.293192384426967e-06,
      "loss": 0.4543,
      "step": 45171
    },
    {
      "epoch": 1.387644763923448,
      "grad_norm": 0.4522683918476105,
      "learning_rate": 4.2927955372701315e-06,
      "loss": 0.4903,
      "step": 45172
    },
    {
      "epoch": 1.387675483058397,
      "grad_norm": 0.43286460638046265,
      "learning_rate": 4.292398703442866e-06,
      "loss": 0.4939,
      "step": 45173
    },
    {
      "epoch": 1.3877062021933462,
      "grad_norm": 0.437726229429245,
      "learning_rate": 4.292001882946103e-06,
      "loss": 0.4658,
      "step": 45174
    },
    {
      "epoch": 1.3877369213282953,
      "grad_norm": 0.4083274304866791,
      "learning_rate": 4.291605075780767e-06,
      "loss": 0.4238,
      "step": 45175
    },
    {
      "epoch": 1.3877676404632446,
      "grad_norm": 0.41010940074920654,
      "learning_rate": 4.2912082819477904e-06,
      "loss": 0.4817,
      "step": 45176
    },
    {
      "epoch": 1.3877983595981938,
      "grad_norm": 0.432125061750412,
      "learning_rate": 4.290811501448092e-06,
      "loss": 0.4912,
      "step": 45177
    },
    {
      "epoch": 1.3878290787331429,
      "grad_norm": 0.42796775698661804,
      "learning_rate": 4.2904147342826065e-06,
      "loss": 0.4715,
      "step": 45178
    },
    {
      "epoch": 1.387859797868092,
      "grad_norm": 0.39263594150543213,
      "learning_rate": 4.290017980452248e-06,
      "loss": 0.4296,
      "step": 45179
    },
    {
      "epoch": 1.3878905170030411,
      "grad_norm": 0.41807839274406433,
      "learning_rate": 4.289621239957955e-06,
      "loss": 0.4599,
      "step": 45180
    },
    {
      "epoch": 1.3879212361379905,
      "grad_norm": 0.41742491722106934,
      "learning_rate": 4.289224512800654e-06,
      "loss": 0.4657,
      "step": 45181
    },
    {
      "epoch": 1.3879519552729396,
      "grad_norm": 0.43140527606010437,
      "learning_rate": 4.2888277989812645e-06,
      "loss": 0.4791,
      "step": 45182
    },
    {
      "epoch": 1.3879826744078887,
      "grad_norm": 0.4341827630996704,
      "learning_rate": 4.288431098500716e-06,
      "loss": 0.5186,
      "step": 45183
    },
    {
      "epoch": 1.3880133935428378,
      "grad_norm": 0.42434075474739075,
      "learning_rate": 4.288034411359936e-06,
      "loss": 0.5173,
      "step": 45184
    },
    {
      "epoch": 1.388044112677787,
      "grad_norm": 0.42364999651908875,
      "learning_rate": 4.287637737559854e-06,
      "loss": 0.4726,
      "step": 45185
    },
    {
      "epoch": 1.388074831812736,
      "grad_norm": 0.4197220206260681,
      "learning_rate": 4.287241077101391e-06,
      "loss": 0.445,
      "step": 45186
    },
    {
      "epoch": 1.3881055509476854,
      "grad_norm": 0.46508634090423584,
      "learning_rate": 4.286844429985477e-06,
      "loss": 0.4344,
      "step": 45187
    },
    {
      "epoch": 1.3881362700826345,
      "grad_norm": 0.4210665225982666,
      "learning_rate": 4.28644779621303e-06,
      "loss": 0.4688,
      "step": 45188
    },
    {
      "epoch": 1.3881669892175836,
      "grad_norm": 0.4809958040714264,
      "learning_rate": 4.286051175784991e-06,
      "loss": 0.5206,
      "step": 45189
    },
    {
      "epoch": 1.3881977083525328,
      "grad_norm": 0.4380576014518738,
      "learning_rate": 4.285654568702274e-06,
      "loss": 0.4567,
      "step": 45190
    },
    {
      "epoch": 1.3882284274874819,
      "grad_norm": 0.5443192720413208,
      "learning_rate": 4.285257974965814e-06,
      "loss": 0.4194,
      "step": 45191
    },
    {
      "epoch": 1.3882591466224312,
      "grad_norm": 0.3947749137878418,
      "learning_rate": 4.284861394576529e-06,
      "loss": 0.4606,
      "step": 45192
    },
    {
      "epoch": 1.3882898657573803,
      "grad_norm": 0.43840882182121277,
      "learning_rate": 4.284464827535351e-06,
      "loss": 0.4786,
      "step": 45193
    },
    {
      "epoch": 1.3883205848923295,
      "grad_norm": 0.38622719049453735,
      "learning_rate": 4.2840682738432024e-06,
      "loss": 0.4943,
      "step": 45194
    },
    {
      "epoch": 1.3883513040272786,
      "grad_norm": 0.4092714786529541,
      "learning_rate": 4.283671733501017e-06,
      "loss": 0.4855,
      "step": 45195
    },
    {
      "epoch": 1.3883820231622277,
      "grad_norm": 0.425075501203537,
      "learning_rate": 4.283275206509712e-06,
      "loss": 0.4807,
      "step": 45196
    },
    {
      "epoch": 1.3884127422971768,
      "grad_norm": 0.4111519455909729,
      "learning_rate": 4.282878692870215e-06,
      "loss": 0.5114,
      "step": 45197
    },
    {
      "epoch": 1.388443461432126,
      "grad_norm": 0.40931808948516846,
      "learning_rate": 4.282482192583456e-06,
      "loss": 0.4372,
      "step": 45198
    },
    {
      "epoch": 1.3884741805670753,
      "grad_norm": 0.37160611152648926,
      "learning_rate": 4.282085705650357e-06,
      "loss": 0.3474,
      "step": 45199
    },
    {
      "epoch": 1.3885048997020244,
      "grad_norm": 0.4320140480995178,
      "learning_rate": 4.281689232071852e-06,
      "loss": 0.4683,
      "step": 45200
    },
    {
      "epoch": 1.3885356188369735,
      "grad_norm": 0.42180395126342773,
      "learning_rate": 4.281292771848856e-06,
      "loss": 0.4315,
      "step": 45201
    },
    {
      "epoch": 1.3885663379719226,
      "grad_norm": 0.4276047945022583,
      "learning_rate": 4.280896324982301e-06,
      "loss": 0.5537,
      "step": 45202
    },
    {
      "epoch": 1.388597057106872,
      "grad_norm": 0.42644479870796204,
      "learning_rate": 4.2804998914731124e-06,
      "loss": 0.4578,
      "step": 45203
    },
    {
      "epoch": 1.388627776241821,
      "grad_norm": 0.39666301012039185,
      "learning_rate": 4.280103471322219e-06,
      "loss": 0.5063,
      "step": 45204
    },
    {
      "epoch": 1.3886584953767702,
      "grad_norm": 0.41731497645378113,
      "learning_rate": 4.279707064530539e-06,
      "loss": 0.412,
      "step": 45205
    },
    {
      "epoch": 1.3886892145117193,
      "grad_norm": 0.4335475564002991,
      "learning_rate": 4.279310671099003e-06,
      "loss": 0.5103,
      "step": 45206
    },
    {
      "epoch": 1.3887199336466685,
      "grad_norm": 0.42702314257621765,
      "learning_rate": 4.2789142910285375e-06,
      "loss": 0.5098,
      "step": 45207
    },
    {
      "epoch": 1.3887506527816176,
      "grad_norm": 0.39709681272506714,
      "learning_rate": 4.278517924320069e-06,
      "loss": 0.4398,
      "step": 45208
    },
    {
      "epoch": 1.3887813719165667,
      "grad_norm": 0.4217514097690582,
      "learning_rate": 4.27812157097452e-06,
      "loss": 0.4679,
      "step": 45209
    },
    {
      "epoch": 1.388812091051516,
      "grad_norm": 0.4018413722515106,
      "learning_rate": 4.277725230992817e-06,
      "loss": 0.4275,
      "step": 45210
    },
    {
      "epoch": 1.3888428101864652,
      "grad_norm": 0.3910352289676666,
      "learning_rate": 4.277328904375885e-06,
      "loss": 0.4514,
      "step": 45211
    },
    {
      "epoch": 1.3888735293214143,
      "grad_norm": 0.4252558946609497,
      "learning_rate": 4.276932591124656e-06,
      "loss": 0.4392,
      "step": 45212
    },
    {
      "epoch": 1.3889042484563634,
      "grad_norm": 0.3947705030441284,
      "learning_rate": 4.276536291240047e-06,
      "loss": 0.4318,
      "step": 45213
    },
    {
      "epoch": 1.3889349675913127,
      "grad_norm": 0.41597363352775574,
      "learning_rate": 4.2761400047229895e-06,
      "loss": 0.496,
      "step": 45214
    },
    {
      "epoch": 1.3889656867262619,
      "grad_norm": 0.4198877811431885,
      "learning_rate": 4.275743731574401e-06,
      "loss": 0.4653,
      "step": 45215
    },
    {
      "epoch": 1.388996405861211,
      "grad_norm": 0.43009281158447266,
      "learning_rate": 4.275347471795216e-06,
      "loss": 0.4621,
      "step": 45216
    },
    {
      "epoch": 1.38902712499616,
      "grad_norm": 0.4532380998134613,
      "learning_rate": 4.27495122538636e-06,
      "loss": 0.4422,
      "step": 45217
    },
    {
      "epoch": 1.3890578441311092,
      "grad_norm": 0.3603680729866028,
      "learning_rate": 4.274554992348751e-06,
      "loss": 0.451,
      "step": 45218
    },
    {
      "epoch": 1.3890885632660583,
      "grad_norm": 0.4485931098461151,
      "learning_rate": 4.274158772683323e-06,
      "loss": 0.4313,
      "step": 45219
    },
    {
      "epoch": 1.3891192824010075,
      "grad_norm": 0.4312041103839874,
      "learning_rate": 4.273762566390991e-06,
      "loss": 0.3724,
      "step": 45220
    },
    {
      "epoch": 1.3891500015359568,
      "grad_norm": 0.354239284992218,
      "learning_rate": 4.273366373472693e-06,
      "loss": 0.4139,
      "step": 45221
    },
    {
      "epoch": 1.389180720670906,
      "grad_norm": 0.4822608232498169,
      "learning_rate": 4.2729701939293436e-06,
      "loss": 0.4911,
      "step": 45222
    },
    {
      "epoch": 1.389211439805855,
      "grad_norm": 0.44207507371902466,
      "learning_rate": 4.272574027761877e-06,
      "loss": 0.5085,
      "step": 45223
    },
    {
      "epoch": 1.3892421589408042,
      "grad_norm": 0.4275830090045929,
      "learning_rate": 4.272177874971205e-06,
      "loss": 0.5111,
      "step": 45224
    },
    {
      "epoch": 1.3892728780757535,
      "grad_norm": 0.39123308658599854,
      "learning_rate": 4.271781735558269e-06,
      "loss": 0.4336,
      "step": 45225
    },
    {
      "epoch": 1.3893035972107026,
      "grad_norm": 0.40351444482803345,
      "learning_rate": 4.271385609523984e-06,
      "loss": 0.4354,
      "step": 45226
    },
    {
      "epoch": 1.3893343163456517,
      "grad_norm": 0.39934825897216797,
      "learning_rate": 4.270989496869281e-06,
      "loss": 0.4769,
      "step": 45227
    },
    {
      "epoch": 1.3893650354806009,
      "grad_norm": 0.4193866550922394,
      "learning_rate": 4.270593397595079e-06,
      "loss": 0.5226,
      "step": 45228
    },
    {
      "epoch": 1.38939575461555,
      "grad_norm": 0.39559343457221985,
      "learning_rate": 4.270197311702307e-06,
      "loss": 0.4674,
      "step": 45229
    },
    {
      "epoch": 1.389426473750499,
      "grad_norm": 0.409806489944458,
      "learning_rate": 4.269801239191888e-06,
      "loss": 0.467,
      "step": 45230
    },
    {
      "epoch": 1.3894571928854482,
      "grad_norm": 0.41962844133377075,
      "learning_rate": 4.269405180064752e-06,
      "loss": 0.4844,
      "step": 45231
    },
    {
      "epoch": 1.3894879120203976,
      "grad_norm": 0.3898679316043854,
      "learning_rate": 4.269009134321818e-06,
      "loss": 0.3945,
      "step": 45232
    },
    {
      "epoch": 1.3895186311553467,
      "grad_norm": 0.4246317148208618,
      "learning_rate": 4.268613101964012e-06,
      "loss": 0.447,
      "step": 45233
    },
    {
      "epoch": 1.3895493502902958,
      "grad_norm": 0.40414950251579285,
      "learning_rate": 4.268217082992261e-06,
      "loss": 0.4904,
      "step": 45234
    },
    {
      "epoch": 1.389580069425245,
      "grad_norm": 0.43538060784339905,
      "learning_rate": 4.267821077407489e-06,
      "loss": 0.4566,
      "step": 45235
    },
    {
      "epoch": 1.3896107885601943,
      "grad_norm": 0.4270934760570526,
      "learning_rate": 4.267425085210626e-06,
      "loss": 0.3842,
      "step": 45236
    },
    {
      "epoch": 1.3896415076951434,
      "grad_norm": 0.4196193516254425,
      "learning_rate": 4.2670291064025874e-06,
      "loss": 0.4597,
      "step": 45237
    },
    {
      "epoch": 1.3896722268300925,
      "grad_norm": 0.4141768217086792,
      "learning_rate": 4.266633140984303e-06,
      "loss": 0.4916,
      "step": 45238
    },
    {
      "epoch": 1.3897029459650416,
      "grad_norm": 0.44877490401268005,
      "learning_rate": 4.266237188956696e-06,
      "loss": 0.4936,
      "step": 45239
    },
    {
      "epoch": 1.3897336650999907,
      "grad_norm": 0.4403902590274811,
      "learning_rate": 4.265841250320698e-06,
      "loss": 0.4372,
      "step": 45240
    },
    {
      "epoch": 1.3897643842349399,
      "grad_norm": 0.4229578673839569,
      "learning_rate": 4.265445325077225e-06,
      "loss": 0.4758,
      "step": 45241
    },
    {
      "epoch": 1.389795103369889,
      "grad_norm": 0.42658451199531555,
      "learning_rate": 4.265049413227203e-06,
      "loss": 0.5439,
      "step": 45242
    },
    {
      "epoch": 1.3898258225048383,
      "grad_norm": 0.4269503951072693,
      "learning_rate": 4.2646535147715595e-06,
      "loss": 0.5452,
      "step": 45243
    },
    {
      "epoch": 1.3898565416397874,
      "grad_norm": 0.4070827066898346,
      "learning_rate": 4.2642576297112226e-06,
      "loss": 0.435,
      "step": 45244
    },
    {
      "epoch": 1.3898872607747366,
      "grad_norm": 0.5325973629951477,
      "learning_rate": 4.263861758047109e-06,
      "loss": 0.4751,
      "step": 45245
    },
    {
      "epoch": 1.3899179799096857,
      "grad_norm": 0.4580347239971161,
      "learning_rate": 4.2634658997801444e-06,
      "loss": 0.4351,
      "step": 45246
    },
    {
      "epoch": 1.389948699044635,
      "grad_norm": 0.4153304100036621,
      "learning_rate": 4.263070054911258e-06,
      "loss": 0.5399,
      "step": 45247
    },
    {
      "epoch": 1.3899794181795841,
      "grad_norm": 0.42474308609962463,
      "learning_rate": 4.262674223441375e-06,
      "loss": 0.4798,
      "step": 45248
    },
    {
      "epoch": 1.3900101373145333,
      "grad_norm": 0.4233446419239044,
      "learning_rate": 4.262278405371415e-06,
      "loss": 0.5658,
      "step": 45249
    },
    {
      "epoch": 1.3900408564494824,
      "grad_norm": 0.43353793025016785,
      "learning_rate": 4.2618826007023066e-06,
      "loss": 0.4627,
      "step": 45250
    },
    {
      "epoch": 1.3900715755844315,
      "grad_norm": 0.4181068539619446,
      "learning_rate": 4.261486809434965e-06,
      "loss": 0.5053,
      "step": 45251
    },
    {
      "epoch": 1.3901022947193806,
      "grad_norm": 0.4349607229232788,
      "learning_rate": 4.261091031570326e-06,
      "loss": 0.4374,
      "step": 45252
    },
    {
      "epoch": 1.3901330138543297,
      "grad_norm": 0.4231693744659424,
      "learning_rate": 4.260695267109313e-06,
      "loss": 0.4177,
      "step": 45253
    },
    {
      "epoch": 1.390163732989279,
      "grad_norm": 0.3875196576118469,
      "learning_rate": 4.260299516052843e-06,
      "loss": 0.4395,
      "step": 45254
    },
    {
      "epoch": 1.3901944521242282,
      "grad_norm": 0.4981025457382202,
      "learning_rate": 4.259903778401848e-06,
      "loss": 0.4307,
      "step": 45255
    },
    {
      "epoch": 1.3902251712591773,
      "grad_norm": 0.38348931074142456,
      "learning_rate": 4.259508054157242e-06,
      "loss": 0.4108,
      "step": 45256
    },
    {
      "epoch": 1.3902558903941264,
      "grad_norm": 0.409451961517334,
      "learning_rate": 4.2591123433199625e-06,
      "loss": 0.4964,
      "step": 45257
    },
    {
      "epoch": 1.3902866095290758,
      "grad_norm": 0.4361487925052643,
      "learning_rate": 4.258716645890923e-06,
      "loss": 0.5157,
      "step": 45258
    },
    {
      "epoch": 1.390317328664025,
      "grad_norm": 0.4491846263408661,
      "learning_rate": 4.258320961871056e-06,
      "loss": 0.451,
      "step": 45259
    },
    {
      "epoch": 1.390348047798974,
      "grad_norm": 0.4392811059951782,
      "learning_rate": 4.257925291261278e-06,
      "loss": 0.4677,
      "step": 45260
    },
    {
      "epoch": 1.3903787669339231,
      "grad_norm": 0.3878249228000641,
      "learning_rate": 4.257529634062516e-06,
      "loss": 0.4866,
      "step": 45261
    },
    {
      "epoch": 1.3904094860688723,
      "grad_norm": 0.41524556279182434,
      "learning_rate": 4.257133990275695e-06,
      "loss": 0.4935,
      "step": 45262
    },
    {
      "epoch": 1.3904402052038214,
      "grad_norm": 0.44290900230407715,
      "learning_rate": 4.256738359901742e-06,
      "loss": 0.5285,
      "step": 45263
    },
    {
      "epoch": 1.3904709243387705,
      "grad_norm": 0.39077651500701904,
      "learning_rate": 4.256342742941575e-06,
      "loss": 0.3837,
      "step": 45264
    },
    {
      "epoch": 1.3905016434737199,
      "grad_norm": 0.40104860067367554,
      "learning_rate": 4.255947139396119e-06,
      "loss": 0.482,
      "step": 45265
    },
    {
      "epoch": 1.390532362608669,
      "grad_norm": 0.44747304916381836,
      "learning_rate": 4.255551549266301e-06,
      "loss": 0.4121,
      "step": 45266
    },
    {
      "epoch": 1.390563081743618,
      "grad_norm": 0.4609113931655884,
      "learning_rate": 4.255155972553047e-06,
      "loss": 0.4449,
      "step": 45267
    },
    {
      "epoch": 1.3905938008785672,
      "grad_norm": 0.4186265170574188,
      "learning_rate": 4.254760409257273e-06,
      "loss": 0.4065,
      "step": 45268
    },
    {
      "epoch": 1.3906245200135166,
      "grad_norm": 0.5371567010879517,
      "learning_rate": 4.254364859379908e-06,
      "loss": 0.4749,
      "step": 45269
    },
    {
      "epoch": 1.3906552391484657,
      "grad_norm": 0.42512884736061096,
      "learning_rate": 4.253969322921875e-06,
      "loss": 0.4838,
      "step": 45270
    },
    {
      "epoch": 1.3906859582834148,
      "grad_norm": 0.3991350829601288,
      "learning_rate": 4.253573799884097e-06,
      "loss": 0.454,
      "step": 45271
    },
    {
      "epoch": 1.390716677418364,
      "grad_norm": 0.41783952713012695,
      "learning_rate": 4.253178290267503e-06,
      "loss": 0.4798,
      "step": 45272
    },
    {
      "epoch": 1.390747396553313,
      "grad_norm": 0.46270081400871277,
      "learning_rate": 4.252782794073009e-06,
      "loss": 0.4525,
      "step": 45273
    },
    {
      "epoch": 1.3907781156882622,
      "grad_norm": 0.4753827452659607,
      "learning_rate": 4.252387311301542e-06,
      "loss": 0.525,
      "step": 45274
    },
    {
      "epoch": 1.3908088348232113,
      "grad_norm": 0.3848913013935089,
      "learning_rate": 4.251991841954026e-06,
      "loss": 0.4649,
      "step": 45275
    },
    {
      "epoch": 1.3908395539581606,
      "grad_norm": 0.4896746873855591,
      "learning_rate": 4.251596386031389e-06,
      "loss": 0.5696,
      "step": 45276
    },
    {
      "epoch": 1.3908702730931097,
      "grad_norm": 0.3937777280807495,
      "learning_rate": 4.2512009435345445e-06,
      "loss": 0.4185,
      "step": 45277
    },
    {
      "epoch": 1.3909009922280589,
      "grad_norm": 0.4347987771034241,
      "learning_rate": 4.250805514464423e-06,
      "loss": 0.5068,
      "step": 45278
    },
    {
      "epoch": 1.390931711363008,
      "grad_norm": 0.4254985749721527,
      "learning_rate": 4.250410098821946e-06,
      "loss": 0.3857,
      "step": 45279
    },
    {
      "epoch": 1.3909624304979573,
      "grad_norm": 0.46114039421081543,
      "learning_rate": 4.2500146966080425e-06,
      "loss": 0.4649,
      "step": 45280
    },
    {
      "epoch": 1.3909931496329064,
      "grad_norm": 0.44032618403434753,
      "learning_rate": 4.249619307823627e-06,
      "loss": 0.3725,
      "step": 45281
    },
    {
      "epoch": 1.3910238687678556,
      "grad_norm": 0.4020245373249054,
      "learning_rate": 4.249223932469631e-06,
      "loss": 0.4309,
      "step": 45282
    },
    {
      "epoch": 1.3910545879028047,
      "grad_norm": 0.39600688219070435,
      "learning_rate": 4.248828570546966e-06,
      "loss": 0.4018,
      "step": 45283
    },
    {
      "epoch": 1.3910853070377538,
      "grad_norm": 0.40601012110710144,
      "learning_rate": 4.248433222056573e-06,
      "loss": 0.4199,
      "step": 45284
    },
    {
      "epoch": 1.391116026172703,
      "grad_norm": 0.41493451595306396,
      "learning_rate": 4.24803788699936e-06,
      "loss": 0.4367,
      "step": 45285
    },
    {
      "epoch": 1.391146745307652,
      "grad_norm": 0.41472890973091125,
      "learning_rate": 4.247642565376261e-06,
      "loss": 0.5121,
      "step": 45286
    },
    {
      "epoch": 1.3911774644426014,
      "grad_norm": 0.45021629333496094,
      "learning_rate": 4.247247257188187e-06,
      "loss": 0.4578,
      "step": 45287
    },
    {
      "epoch": 1.3912081835775505,
      "grad_norm": 0.48039737343788147,
      "learning_rate": 4.246851962436073e-06,
      "loss": 0.4297,
      "step": 45288
    },
    {
      "epoch": 1.3912389027124996,
      "grad_norm": 0.4679265022277832,
      "learning_rate": 4.246456681120841e-06,
      "loss": 0.4346,
      "step": 45289
    },
    {
      "epoch": 1.3912696218474487,
      "grad_norm": 0.3892909586429596,
      "learning_rate": 4.246061413243406e-06,
      "loss": 0.4654,
      "step": 45290
    },
    {
      "epoch": 1.3913003409823979,
      "grad_norm": 0.41128960251808167,
      "learning_rate": 4.245666158804702e-06,
      "loss": 0.4843,
      "step": 45291
    },
    {
      "epoch": 1.3913310601173472,
      "grad_norm": 0.41406896710395813,
      "learning_rate": 4.245270917805639e-06,
      "loss": 0.5684,
      "step": 45292
    },
    {
      "epoch": 1.3913617792522963,
      "grad_norm": 0.4871002435684204,
      "learning_rate": 4.244875690247155e-06,
      "loss": 0.4406,
      "step": 45293
    },
    {
      "epoch": 1.3913924983872454,
      "grad_norm": 0.4148912727832794,
      "learning_rate": 4.244480476130162e-06,
      "loss": 0.4379,
      "step": 45294
    },
    {
      "epoch": 1.3914232175221946,
      "grad_norm": 0.3892005980014801,
      "learning_rate": 4.244085275455591e-06,
      "loss": 0.4685,
      "step": 45295
    },
    {
      "epoch": 1.3914539366571437,
      "grad_norm": 0.409150093793869,
      "learning_rate": 4.243690088224357e-06,
      "loss": 0.4783,
      "step": 45296
    },
    {
      "epoch": 1.3914846557920928,
      "grad_norm": 0.37832361459732056,
      "learning_rate": 4.2432949144373854e-06,
      "loss": 0.3965,
      "step": 45297
    },
    {
      "epoch": 1.3915153749270421,
      "grad_norm": 0.4840101897716522,
      "learning_rate": 4.242899754095603e-06,
      "loss": 0.3697,
      "step": 45298
    },
    {
      "epoch": 1.3915460940619913,
      "grad_norm": 0.4262026250362396,
      "learning_rate": 4.242504607199932e-06,
      "loss": 0.5085,
      "step": 45299
    },
    {
      "epoch": 1.3915768131969404,
      "grad_norm": 0.3858969211578369,
      "learning_rate": 4.24210947375129e-06,
      "loss": 0.4417,
      "step": 45300
    },
    {
      "epoch": 1.3916075323318895,
      "grad_norm": 0.8342828750610352,
      "learning_rate": 4.2417143537506044e-06,
      "loss": 0.4078,
      "step": 45301
    },
    {
      "epoch": 1.3916382514668386,
      "grad_norm": 0.4380001127719879,
      "learning_rate": 4.241319247198797e-06,
      "loss": 0.4908,
      "step": 45302
    },
    {
      "epoch": 1.391668970601788,
      "grad_norm": 0.45055025815963745,
      "learning_rate": 4.2409241540967935e-06,
      "loss": 0.5051,
      "step": 45303
    },
    {
      "epoch": 1.391699689736737,
      "grad_norm": 0.49892765283584595,
      "learning_rate": 4.240529074445511e-06,
      "loss": 0.4226,
      "step": 45304
    },
    {
      "epoch": 1.3917304088716862,
      "grad_norm": 0.4437275528907776,
      "learning_rate": 4.240134008245875e-06,
      "loss": 0.4906,
      "step": 45305
    },
    {
      "epoch": 1.3917611280066353,
      "grad_norm": 0.40386080741882324,
      "learning_rate": 4.239738955498808e-06,
      "loss": 0.484,
      "step": 45306
    },
    {
      "epoch": 1.3917918471415844,
      "grad_norm": 0.44758254289627075,
      "learning_rate": 4.239343916205233e-06,
      "loss": 0.5056,
      "step": 45307
    },
    {
      "epoch": 1.3918225662765336,
      "grad_norm": 0.5020845532417297,
      "learning_rate": 4.238948890366076e-06,
      "loss": 0.3947,
      "step": 45308
    },
    {
      "epoch": 1.3918532854114827,
      "grad_norm": 0.41734224557876587,
      "learning_rate": 4.238553877982253e-06,
      "loss": 0.493,
      "step": 45309
    },
    {
      "epoch": 1.391884004546432,
      "grad_norm": 0.42336976528167725,
      "learning_rate": 4.23815887905469e-06,
      "loss": 0.4642,
      "step": 45310
    },
    {
      "epoch": 1.3919147236813811,
      "grad_norm": 0.40240928530693054,
      "learning_rate": 4.237763893584309e-06,
      "loss": 0.4205,
      "step": 45311
    },
    {
      "epoch": 1.3919454428163303,
      "grad_norm": 0.3697618246078491,
      "learning_rate": 4.237368921572036e-06,
      "loss": 0.4455,
      "step": 45312
    },
    {
      "epoch": 1.3919761619512794,
      "grad_norm": 0.39399513602256775,
      "learning_rate": 4.236973963018788e-06,
      "loss": 0.4354,
      "step": 45313
    },
    {
      "epoch": 1.3920068810862287,
      "grad_norm": 0.4334726631641388,
      "learning_rate": 4.236579017925488e-06,
      "loss": 0.4668,
      "step": 45314
    },
    {
      "epoch": 1.3920376002211778,
      "grad_norm": 0.44177839159965515,
      "learning_rate": 4.236184086293062e-06,
      "loss": 0.4829,
      "step": 45315
    },
    {
      "epoch": 1.392068319356127,
      "grad_norm": 0.40029263496398926,
      "learning_rate": 4.2357891681224325e-06,
      "loss": 0.4594,
      "step": 45316
    },
    {
      "epoch": 1.392099038491076,
      "grad_norm": 0.39523348212242126,
      "learning_rate": 4.235394263414519e-06,
      "loss": 0.4441,
      "step": 45317
    },
    {
      "epoch": 1.3921297576260252,
      "grad_norm": 0.39789140224456787,
      "learning_rate": 4.234999372170245e-06,
      "loss": 0.4884,
      "step": 45318
    },
    {
      "epoch": 1.3921604767609743,
      "grad_norm": 0.721245288848877,
      "learning_rate": 4.234604494390528e-06,
      "loss": 0.5009,
      "step": 45319
    },
    {
      "epoch": 1.3921911958959234,
      "grad_norm": 0.3816111385822296,
      "learning_rate": 4.2342096300763e-06,
      "loss": 0.4909,
      "step": 45320
    },
    {
      "epoch": 1.3922219150308728,
      "grad_norm": 0.39037299156188965,
      "learning_rate": 4.2338147792284765e-06,
      "loss": 0.5251,
      "step": 45321
    },
    {
      "epoch": 1.392252634165822,
      "grad_norm": 0.427533358335495,
      "learning_rate": 4.2334199418479835e-06,
      "loss": 0.4588,
      "step": 45322
    },
    {
      "epoch": 1.392283353300771,
      "grad_norm": 0.386594295501709,
      "learning_rate": 4.233025117935739e-06,
      "loss": 0.4169,
      "step": 45323
    },
    {
      "epoch": 1.3923140724357201,
      "grad_norm": 0.4930059611797333,
      "learning_rate": 4.2326303074926656e-06,
      "loss": 0.5054,
      "step": 45324
    },
    {
      "epoch": 1.3923447915706695,
      "grad_norm": 0.40854454040527344,
      "learning_rate": 4.232235510519686e-06,
      "loss": 0.466,
      "step": 45325
    },
    {
      "epoch": 1.3923755107056186,
      "grad_norm": 0.4119075536727905,
      "learning_rate": 4.231840727017725e-06,
      "loss": 0.4508,
      "step": 45326
    },
    {
      "epoch": 1.3924062298405677,
      "grad_norm": 0.3823322355747223,
      "learning_rate": 4.231445956987707e-06,
      "loss": 0.4335,
      "step": 45327
    },
    {
      "epoch": 1.3924369489755168,
      "grad_norm": 0.42642003297805786,
      "learning_rate": 4.23105120043054e-06,
      "loss": 0.4599,
      "step": 45328
    },
    {
      "epoch": 1.392467668110466,
      "grad_norm": 0.475175142288208,
      "learning_rate": 4.230656457347166e-06,
      "loss": 0.4728,
      "step": 45329
    },
    {
      "epoch": 1.392498387245415,
      "grad_norm": 0.3945218622684479,
      "learning_rate": 4.2302617277384905e-06,
      "loss": 0.4876,
      "step": 45330
    },
    {
      "epoch": 1.3925291063803642,
      "grad_norm": 0.4065747559070587,
      "learning_rate": 4.229867011605446e-06,
      "loss": 0.5331,
      "step": 45331
    },
    {
      "epoch": 1.3925598255153135,
      "grad_norm": 0.41086021065711975,
      "learning_rate": 4.229472308948948e-06,
      "loss": 0.5266,
      "step": 45332
    },
    {
      "epoch": 1.3925905446502627,
      "grad_norm": 0.9466411471366882,
      "learning_rate": 4.229077619769919e-06,
      "loss": 0.4256,
      "step": 45333
    },
    {
      "epoch": 1.3926212637852118,
      "grad_norm": 0.3959507346153259,
      "learning_rate": 4.228682944069282e-06,
      "loss": 0.4885,
      "step": 45334
    },
    {
      "epoch": 1.392651982920161,
      "grad_norm": 0.4102468192577362,
      "learning_rate": 4.228288281847965e-06,
      "loss": 0.4431,
      "step": 45335
    },
    {
      "epoch": 1.3926827020551102,
      "grad_norm": 0.41105473041534424,
      "learning_rate": 4.227893633106878e-06,
      "loss": 0.4078,
      "step": 45336
    },
    {
      "epoch": 1.3927134211900594,
      "grad_norm": 0.3989148736000061,
      "learning_rate": 4.2274989978469485e-06,
      "loss": 0.3835,
      "step": 45337
    },
    {
      "epoch": 1.3927441403250085,
      "grad_norm": 0.4466927945613861,
      "learning_rate": 4.227104376069099e-06,
      "loss": 0.5017,
      "step": 45338
    },
    {
      "epoch": 1.3927748594599576,
      "grad_norm": 0.4158930480480194,
      "learning_rate": 4.226709767774254e-06,
      "loss": 0.4296,
      "step": 45339
    },
    {
      "epoch": 1.3928055785949067,
      "grad_norm": 0.39187923073768616,
      "learning_rate": 4.226315172963328e-06,
      "loss": 0.4195,
      "step": 45340
    },
    {
      "epoch": 1.3928362977298558,
      "grad_norm": 0.41134437918663025,
      "learning_rate": 4.225920591637244e-06,
      "loss": 0.4259,
      "step": 45341
    },
    {
      "epoch": 1.392867016864805,
      "grad_norm": 0.43413856625556946,
      "learning_rate": 4.225526023796929e-06,
      "loss": 0.4285,
      "step": 45342
    },
    {
      "epoch": 1.3928977359997543,
      "grad_norm": 0.4330374300479889,
      "learning_rate": 4.2251314694433e-06,
      "loss": 0.4723,
      "step": 45343
    },
    {
      "epoch": 1.3929284551347034,
      "grad_norm": 0.40083324909210205,
      "learning_rate": 4.224736928577283e-06,
      "loss": 0.5068,
      "step": 45344
    },
    {
      "epoch": 1.3929591742696525,
      "grad_norm": 0.4395864009857178,
      "learning_rate": 4.2243424011997925e-06,
      "loss": 0.5502,
      "step": 45345
    },
    {
      "epoch": 1.3929898934046017,
      "grad_norm": 0.40941157937049866,
      "learning_rate": 4.223947887311755e-06,
      "loss": 0.5066,
      "step": 45346
    },
    {
      "epoch": 1.393020612539551,
      "grad_norm": 0.3879025876522064,
      "learning_rate": 4.223553386914089e-06,
      "loss": 0.4287,
      "step": 45347
    },
    {
      "epoch": 1.3930513316745001,
      "grad_norm": 0.4139404892921448,
      "learning_rate": 4.2231589000077225e-06,
      "loss": 0.4571,
      "step": 45348
    },
    {
      "epoch": 1.3930820508094492,
      "grad_norm": 0.40974509716033936,
      "learning_rate": 4.222764426593566e-06,
      "loss": 0.4508,
      "step": 45349
    },
    {
      "epoch": 1.3931127699443984,
      "grad_norm": 0.4163855016231537,
      "learning_rate": 4.222369966672549e-06,
      "loss": 0.4232,
      "step": 45350
    },
    {
      "epoch": 1.3931434890793475,
      "grad_norm": 0.41053706407546997,
      "learning_rate": 4.221975520245589e-06,
      "loss": 0.4567,
      "step": 45351
    },
    {
      "epoch": 1.3931742082142966,
      "grad_norm": 0.41567355394363403,
      "learning_rate": 4.221581087313613e-06,
      "loss": 0.5017,
      "step": 45352
    },
    {
      "epoch": 1.3932049273492457,
      "grad_norm": 0.4259323179721832,
      "learning_rate": 4.221186667877535e-06,
      "loss": 0.4996,
      "step": 45353
    },
    {
      "epoch": 1.393235646484195,
      "grad_norm": 0.3994540274143219,
      "learning_rate": 4.220792261938281e-06,
      "loss": 0.432,
      "step": 45354
    },
    {
      "epoch": 1.3932663656191442,
      "grad_norm": 0.43903377652168274,
      "learning_rate": 4.220397869496764e-06,
      "loss": 0.449,
      "step": 45355
    },
    {
      "epoch": 1.3932970847540933,
      "grad_norm": 0.44566094875335693,
      "learning_rate": 4.220003490553919e-06,
      "loss": 0.4752,
      "step": 45356
    },
    {
      "epoch": 1.3933278038890424,
      "grad_norm": 0.48726168274879456,
      "learning_rate": 4.219609125110655e-06,
      "loss": 0.4596,
      "step": 45357
    },
    {
      "epoch": 1.3933585230239918,
      "grad_norm": 0.4213933050632477,
      "learning_rate": 4.2192147731679026e-06,
      "loss": 0.4719,
      "step": 45358
    },
    {
      "epoch": 1.3933892421589409,
      "grad_norm": 0.4302825927734375,
      "learning_rate": 4.2188204347265725e-06,
      "loss": 0.4251,
      "step": 45359
    },
    {
      "epoch": 1.39341996129389,
      "grad_norm": 0.5016417503356934,
      "learning_rate": 4.218426109787592e-06,
      "loss": 0.5154,
      "step": 45360
    },
    {
      "epoch": 1.3934506804288391,
      "grad_norm": 0.42292433977127075,
      "learning_rate": 4.218031798351882e-06,
      "loss": 0.4805,
      "step": 45361
    },
    {
      "epoch": 1.3934813995637882,
      "grad_norm": 0.3914501368999481,
      "learning_rate": 4.217637500420361e-06,
      "loss": 0.5754,
      "step": 45362
    },
    {
      "epoch": 1.3935121186987374,
      "grad_norm": 0.41868752241134644,
      "learning_rate": 4.217243215993956e-06,
      "loss": 0.4522,
      "step": 45363
    },
    {
      "epoch": 1.3935428378336865,
      "grad_norm": 0.4386906623840332,
      "learning_rate": 4.216848945073579e-06,
      "loss": 0.4836,
      "step": 45364
    },
    {
      "epoch": 1.3935735569686358,
      "grad_norm": 0.39330968260765076,
      "learning_rate": 4.216454687660155e-06,
      "loss": 0.5069,
      "step": 45365
    },
    {
      "epoch": 1.393604276103585,
      "grad_norm": 0.41709065437316895,
      "learning_rate": 4.216060443754606e-06,
      "loss": 0.4595,
      "step": 45366
    },
    {
      "epoch": 1.393634995238534,
      "grad_norm": 0.3957584798336029,
      "learning_rate": 4.215666213357855e-06,
      "loss": 0.4592,
      "step": 45367
    },
    {
      "epoch": 1.3936657143734832,
      "grad_norm": 0.40559396147727966,
      "learning_rate": 4.215271996470815e-06,
      "loss": 0.4529,
      "step": 45368
    },
    {
      "epoch": 1.3936964335084325,
      "grad_norm": 0.4225079119205475,
      "learning_rate": 4.214877793094413e-06,
      "loss": 0.4671,
      "step": 45369
    },
    {
      "epoch": 1.3937271526433817,
      "grad_norm": 0.43105340003967285,
      "learning_rate": 4.214483603229566e-06,
      "loss": 0.4617,
      "step": 45370
    },
    {
      "epoch": 1.3937578717783308,
      "grad_norm": 0.43388640880584717,
      "learning_rate": 4.214089426877201e-06,
      "loss": 0.4951,
      "step": 45371
    },
    {
      "epoch": 1.39378859091328,
      "grad_norm": 0.40663644671440125,
      "learning_rate": 4.213695264038232e-06,
      "loss": 0.5436,
      "step": 45372
    },
    {
      "epoch": 1.393819310048229,
      "grad_norm": 0.43733933568000793,
      "learning_rate": 4.213301114713581e-06,
      "loss": 0.398,
      "step": 45373
    },
    {
      "epoch": 1.3938500291831781,
      "grad_norm": 0.398853063583374,
      "learning_rate": 4.212906978904169e-06,
      "loss": 0.4648,
      "step": 45374
    },
    {
      "epoch": 1.3938807483181272,
      "grad_norm": 0.39937567710876465,
      "learning_rate": 4.21251285661092e-06,
      "loss": 0.4901,
      "step": 45375
    },
    {
      "epoch": 1.3939114674530766,
      "grad_norm": 0.3954296112060547,
      "learning_rate": 4.212118747834748e-06,
      "loss": 0.4394,
      "step": 45376
    },
    {
      "epoch": 1.3939421865880257,
      "grad_norm": 0.4122498035430908,
      "learning_rate": 4.211724652576578e-06,
      "loss": 0.5201,
      "step": 45377
    },
    {
      "epoch": 1.3939729057229748,
      "grad_norm": 0.3929175138473511,
      "learning_rate": 4.211330570837329e-06,
      "loss": 0.4822,
      "step": 45378
    },
    {
      "epoch": 1.394003624857924,
      "grad_norm": 0.40646135807037354,
      "learning_rate": 4.21093650261792e-06,
      "loss": 0.4616,
      "step": 45379
    },
    {
      "epoch": 1.3940343439928733,
      "grad_norm": 0.4224608540534973,
      "learning_rate": 4.210542447919278e-06,
      "loss": 0.4931,
      "step": 45380
    },
    {
      "epoch": 1.3940650631278224,
      "grad_norm": 0.42652085423469543,
      "learning_rate": 4.210148406742316e-06,
      "loss": 0.4921,
      "step": 45381
    },
    {
      "epoch": 1.3940957822627715,
      "grad_norm": 0.45213600993156433,
      "learning_rate": 4.209754379087955e-06,
      "loss": 0.4756,
      "step": 45382
    },
    {
      "epoch": 1.3941265013977207,
      "grad_norm": 0.4144728183746338,
      "learning_rate": 4.209360364957118e-06,
      "loss": 0.4824,
      "step": 45383
    },
    {
      "epoch": 1.3941572205326698,
      "grad_norm": 0.42979806661605835,
      "learning_rate": 4.208966364350727e-06,
      "loss": 0.5198,
      "step": 45384
    },
    {
      "epoch": 1.394187939667619,
      "grad_norm": 0.39488765597343445,
      "learning_rate": 4.208572377269696e-06,
      "loss": 0.4337,
      "step": 45385
    },
    {
      "epoch": 1.394218658802568,
      "grad_norm": 0.4129381477832794,
      "learning_rate": 4.208178403714953e-06,
      "loss": 0.5278,
      "step": 45386
    },
    {
      "epoch": 1.3942493779375174,
      "grad_norm": 0.39706331491470337,
      "learning_rate": 4.207784443687407e-06,
      "loss": 0.4186,
      "step": 45387
    },
    {
      "epoch": 1.3942800970724665,
      "grad_norm": 0.46345430612564087,
      "learning_rate": 4.207390497187991e-06,
      "loss": 0.4947,
      "step": 45388
    },
    {
      "epoch": 1.3943108162074156,
      "grad_norm": 0.35438933968544006,
      "learning_rate": 4.206996564217616e-06,
      "loss": 0.4695,
      "step": 45389
    },
    {
      "epoch": 1.3943415353423647,
      "grad_norm": 0.4105580747127533,
      "learning_rate": 4.206602644777209e-06,
      "loss": 0.4933,
      "step": 45390
    },
    {
      "epoch": 1.394372254477314,
      "grad_norm": 0.43161213397979736,
      "learning_rate": 4.206208738867678e-06,
      "loss": 0.4855,
      "step": 45391
    },
    {
      "epoch": 1.3944029736122632,
      "grad_norm": 0.4337328374385834,
      "learning_rate": 4.20581484648996e-06,
      "loss": 0.464,
      "step": 45392
    },
    {
      "epoch": 1.3944336927472123,
      "grad_norm": 0.44261476397514343,
      "learning_rate": 4.2054209676449605e-06,
      "loss": 0.4977,
      "step": 45393
    },
    {
      "epoch": 1.3944644118821614,
      "grad_norm": 0.4101071357727051,
      "learning_rate": 4.20502710233361e-06,
      "loss": 0.451,
      "step": 45394
    },
    {
      "epoch": 1.3944951310171105,
      "grad_norm": 0.42783820629119873,
      "learning_rate": 4.204633250556819e-06,
      "loss": 0.4335,
      "step": 45395
    },
    {
      "epoch": 1.3945258501520597,
      "grad_norm": 0.44332155585289,
      "learning_rate": 4.204239412315512e-06,
      "loss": 0.5191,
      "step": 45396
    },
    {
      "epoch": 1.3945565692870088,
      "grad_norm": 0.4117490351200104,
      "learning_rate": 4.203845587610609e-06,
      "loss": 0.4683,
      "step": 45397
    },
    {
      "epoch": 1.3945872884219581,
      "grad_norm": 0.3974938988685608,
      "learning_rate": 4.20345177644303e-06,
      "loss": 0.4765,
      "step": 45398
    },
    {
      "epoch": 1.3946180075569072,
      "grad_norm": 0.39653000235557556,
      "learning_rate": 4.203057978813696e-06,
      "loss": 0.4531,
      "step": 45399
    },
    {
      "epoch": 1.3946487266918564,
      "grad_norm": 0.4405876696109772,
      "learning_rate": 4.202664194723523e-06,
      "loss": 0.5175,
      "step": 45400
    },
    {
      "epoch": 1.3946794458268055,
      "grad_norm": 0.45376473665237427,
      "learning_rate": 4.2022704241734315e-06,
      "loss": 0.4117,
      "step": 45401
    },
    {
      "epoch": 1.3947101649617546,
      "grad_norm": 0.4657754898071289,
      "learning_rate": 4.201876667164343e-06,
      "loss": 0.4962,
      "step": 45402
    },
    {
      "epoch": 1.394740884096704,
      "grad_norm": 0.42257824540138245,
      "learning_rate": 4.201482923697179e-06,
      "loss": 0.4902,
      "step": 45403
    },
    {
      "epoch": 1.394771603231653,
      "grad_norm": 0.4521564245223999,
      "learning_rate": 4.201089193772854e-06,
      "loss": 0.4456,
      "step": 45404
    },
    {
      "epoch": 1.3948023223666022,
      "grad_norm": 0.4174458682537079,
      "learning_rate": 4.2006954773922905e-06,
      "loss": 0.4612,
      "step": 45405
    },
    {
      "epoch": 1.3948330415015513,
      "grad_norm": 0.42988747358322144,
      "learning_rate": 4.200301774556407e-06,
      "loss": 0.4674,
      "step": 45406
    },
    {
      "epoch": 1.3948637606365004,
      "grad_norm": 0.3882756233215332,
      "learning_rate": 4.199908085266127e-06,
      "loss": 0.4963,
      "step": 45407
    },
    {
      "epoch": 1.3948944797714495,
      "grad_norm": 0.4470701217651367,
      "learning_rate": 4.199514409522364e-06,
      "loss": 0.5067,
      "step": 45408
    },
    {
      "epoch": 1.3949251989063989,
      "grad_norm": 0.6470312476158142,
      "learning_rate": 4.19912074732604e-06,
      "loss": 0.4766,
      "step": 45409
    },
    {
      "epoch": 1.394955918041348,
      "grad_norm": 0.3999740183353424,
      "learning_rate": 4.198727098678074e-06,
      "loss": 0.4785,
      "step": 45410
    },
    {
      "epoch": 1.3949866371762971,
      "grad_norm": 0.45966237783432007,
      "learning_rate": 4.198333463579392e-06,
      "loss": 0.5811,
      "step": 45411
    },
    {
      "epoch": 1.3950173563112462,
      "grad_norm": 0.42547014355659485,
      "learning_rate": 4.197939842030902e-06,
      "loss": 0.4478,
      "step": 45412
    },
    {
      "epoch": 1.3950480754461954,
      "grad_norm": 0.3954475224018097,
      "learning_rate": 4.197546234033528e-06,
      "loss": 0.5112,
      "step": 45413
    },
    {
      "epoch": 1.3950787945811447,
      "grad_norm": 0.5283770561218262,
      "learning_rate": 4.19715263958819e-06,
      "loss": 0.4423,
      "step": 45414
    },
    {
      "epoch": 1.3951095137160938,
      "grad_norm": 0.4443456530570984,
      "learning_rate": 4.196759058695812e-06,
      "loss": 0.4384,
      "step": 45415
    },
    {
      "epoch": 1.395140232851043,
      "grad_norm": 0.4768560528755188,
      "learning_rate": 4.196365491357305e-06,
      "loss": 0.4916,
      "step": 45416
    },
    {
      "epoch": 1.395170951985992,
      "grad_norm": 0.3969690799713135,
      "learning_rate": 4.195971937573591e-06,
      "loss": 0.4642,
      "step": 45417
    },
    {
      "epoch": 1.3952016711209412,
      "grad_norm": 0.40433838963508606,
      "learning_rate": 4.19557839734559e-06,
      "loss": 0.4403,
      "step": 45418
    },
    {
      "epoch": 1.3952323902558903,
      "grad_norm": 0.40682774782180786,
      "learning_rate": 4.195184870674222e-06,
      "loss": 0.4552,
      "step": 45419
    },
    {
      "epoch": 1.3952631093908394,
      "grad_norm": 0.4042954444885254,
      "learning_rate": 4.194791357560407e-06,
      "loss": 0.5022,
      "step": 45420
    },
    {
      "epoch": 1.3952938285257888,
      "grad_norm": 0.41956183314323425,
      "learning_rate": 4.194397858005059e-06,
      "loss": 0.532,
      "step": 45421
    },
    {
      "epoch": 1.3953245476607379,
      "grad_norm": 0.5287377238273621,
      "learning_rate": 4.194004372009105e-06,
      "loss": 0.4282,
      "step": 45422
    },
    {
      "epoch": 1.395355266795687,
      "grad_norm": 0.4512503445148468,
      "learning_rate": 4.193610899573451e-06,
      "loss": 0.5379,
      "step": 45423
    },
    {
      "epoch": 1.3953859859306361,
      "grad_norm": 0.40310394763946533,
      "learning_rate": 4.193217440699032e-06,
      "loss": 0.5064,
      "step": 45424
    },
    {
      "epoch": 1.3954167050655855,
      "grad_norm": 0.3997404873371124,
      "learning_rate": 4.192823995386756e-06,
      "loss": 0.5389,
      "step": 45425
    },
    {
      "epoch": 1.3954474242005346,
      "grad_norm": 0.4342552423477173,
      "learning_rate": 4.192430563637547e-06,
      "loss": 0.4982,
      "step": 45426
    },
    {
      "epoch": 1.3954781433354837,
      "grad_norm": 0.44596540927886963,
      "learning_rate": 4.19203714545232e-06,
      "loss": 0.5092,
      "step": 45427
    },
    {
      "epoch": 1.3955088624704328,
      "grad_norm": 0.4036351442337036,
      "learning_rate": 4.191643740831995e-06,
      "loss": 0.5052,
      "step": 45428
    },
    {
      "epoch": 1.395539581605382,
      "grad_norm": 0.40152135491371155,
      "learning_rate": 4.1912503497774934e-06,
      "loss": 0.4354,
      "step": 45429
    },
    {
      "epoch": 1.395570300740331,
      "grad_norm": 0.4875927269458771,
      "learning_rate": 4.190856972289734e-06,
      "loss": 0.5279,
      "step": 45430
    },
    {
      "epoch": 1.3956010198752802,
      "grad_norm": 0.42447641491889954,
      "learning_rate": 4.190463608369632e-06,
      "loss": 0.4467,
      "step": 45431
    },
    {
      "epoch": 1.3956317390102295,
      "grad_norm": 0.4066723585128784,
      "learning_rate": 4.190070258018106e-06,
      "loss": 0.5258,
      "step": 45432
    },
    {
      "epoch": 1.3956624581451786,
      "grad_norm": 0.45702457427978516,
      "learning_rate": 4.189676921236078e-06,
      "loss": 0.4938,
      "step": 45433
    },
    {
      "epoch": 1.3956931772801278,
      "grad_norm": 0.5396688580513,
      "learning_rate": 4.189283598024465e-06,
      "loss": 0.476,
      "step": 45434
    },
    {
      "epoch": 1.3957238964150769,
      "grad_norm": 0.4959406852722168,
      "learning_rate": 4.18889028838419e-06,
      "loss": 0.4489,
      "step": 45435
    },
    {
      "epoch": 1.3957546155500262,
      "grad_norm": 0.46066638827323914,
      "learning_rate": 4.1884969923161626e-06,
      "loss": 0.4774,
      "step": 45436
    },
    {
      "epoch": 1.3957853346849753,
      "grad_norm": 0.40761974453926086,
      "learning_rate": 4.188103709821307e-06,
      "loss": 0.533,
      "step": 45437
    },
    {
      "epoch": 1.3958160538199245,
      "grad_norm": 0.45714887976646423,
      "learning_rate": 4.187710440900542e-06,
      "loss": 0.4695,
      "step": 45438
    },
    {
      "epoch": 1.3958467729548736,
      "grad_norm": 0.39889609813690186,
      "learning_rate": 4.187317185554788e-06,
      "loss": 0.4565,
      "step": 45439
    },
    {
      "epoch": 1.3958774920898227,
      "grad_norm": 0.41082027554512024,
      "learning_rate": 4.186923943784957e-06,
      "loss": 0.5409,
      "step": 45440
    },
    {
      "epoch": 1.3959082112247718,
      "grad_norm": 0.5096995830535889,
      "learning_rate": 4.186530715591971e-06,
      "loss": 0.4732,
      "step": 45441
    },
    {
      "epoch": 1.395938930359721,
      "grad_norm": 0.4631369113922119,
      "learning_rate": 4.186137500976749e-06,
      "loss": 0.4592,
      "step": 45442
    },
    {
      "epoch": 1.3959696494946703,
      "grad_norm": 0.4311921000480652,
      "learning_rate": 4.185744299940212e-06,
      "loss": 0.5285,
      "step": 45443
    },
    {
      "epoch": 1.3960003686296194,
      "grad_norm": 0.37508079409599304,
      "learning_rate": 4.185351112483272e-06,
      "loss": 0.5082,
      "step": 45444
    },
    {
      "epoch": 1.3960310877645685,
      "grad_norm": 0.40332430601119995,
      "learning_rate": 4.18495793860685e-06,
      "loss": 0.4918,
      "step": 45445
    },
    {
      "epoch": 1.3960618068995176,
      "grad_norm": 0.4697900116443634,
      "learning_rate": 4.184564778311866e-06,
      "loss": 0.3785,
      "step": 45446
    },
    {
      "epoch": 1.396092526034467,
      "grad_norm": 0.41658878326416016,
      "learning_rate": 4.18417163159924e-06,
      "loss": 0.5078,
      "step": 45447
    },
    {
      "epoch": 1.396123245169416,
      "grad_norm": 0.3883412778377533,
      "learning_rate": 4.183778498469884e-06,
      "loss": 0.4249,
      "step": 45448
    },
    {
      "epoch": 1.3961539643043652,
      "grad_norm": 0.4624491035938263,
      "learning_rate": 4.1833853789247225e-06,
      "loss": 0.476,
      "step": 45449
    },
    {
      "epoch": 1.3961846834393143,
      "grad_norm": 0.40488579869270325,
      "learning_rate": 4.182992272964664e-06,
      "loss": 0.4753,
      "step": 45450
    },
    {
      "epoch": 1.3962154025742635,
      "grad_norm": 0.42475926876068115,
      "learning_rate": 4.182599180590641e-06,
      "loss": 0.5613,
      "step": 45451
    },
    {
      "epoch": 1.3962461217092126,
      "grad_norm": 0.4015670716762543,
      "learning_rate": 4.1822061018035585e-06,
      "loss": 0.4698,
      "step": 45452
    },
    {
      "epoch": 1.3962768408441617,
      "grad_norm": 0.4297214448451996,
      "learning_rate": 4.181813036604342e-06,
      "loss": 0.5076,
      "step": 45453
    },
    {
      "epoch": 1.396307559979111,
      "grad_norm": 0.46167808771133423,
      "learning_rate": 4.181419984993907e-06,
      "loss": 0.4204,
      "step": 45454
    },
    {
      "epoch": 1.3963382791140602,
      "grad_norm": 0.4082435071468353,
      "learning_rate": 4.181026946973171e-06,
      "loss": 0.4928,
      "step": 45455
    },
    {
      "epoch": 1.3963689982490093,
      "grad_norm": 0.43544337153434753,
      "learning_rate": 4.180633922543057e-06,
      "loss": 0.4722,
      "step": 45456
    },
    {
      "epoch": 1.3963997173839584,
      "grad_norm": 0.44443321228027344,
      "learning_rate": 4.180240911704475e-06,
      "loss": 0.4688,
      "step": 45457
    },
    {
      "epoch": 1.3964304365189077,
      "grad_norm": 0.41962364315986633,
      "learning_rate": 4.179847914458352e-06,
      "loss": 0.4646,
      "step": 45458
    },
    {
      "epoch": 1.3964611556538569,
      "grad_norm": 0.4652722477912903,
      "learning_rate": 4.179454930805592e-06,
      "loss": 0.4004,
      "step": 45459
    },
    {
      "epoch": 1.396491874788806,
      "grad_norm": 0.40956011414527893,
      "learning_rate": 4.179061960747128e-06,
      "loss": 0.4442,
      "step": 45460
    },
    {
      "epoch": 1.396522593923755,
      "grad_norm": 0.44502517580986023,
      "learning_rate": 4.17866900428387e-06,
      "loss": 0.4126,
      "step": 45461
    },
    {
      "epoch": 1.3965533130587042,
      "grad_norm": 0.4521389603614807,
      "learning_rate": 4.178276061416739e-06,
      "loss": 0.4837,
      "step": 45462
    },
    {
      "epoch": 1.3965840321936533,
      "grad_norm": 0.4226679801940918,
      "learning_rate": 4.177883132146647e-06,
      "loss": 0.5212,
      "step": 45463
    },
    {
      "epoch": 1.3966147513286025,
      "grad_norm": 0.40143269300460815,
      "learning_rate": 4.177490216474517e-06,
      "loss": 0.4612,
      "step": 45464
    },
    {
      "epoch": 1.3966454704635518,
      "grad_norm": 0.40920358896255493,
      "learning_rate": 4.177097314401265e-06,
      "loss": 0.4757,
      "step": 45465
    },
    {
      "epoch": 1.396676189598501,
      "grad_norm": 0.4815412759780884,
      "learning_rate": 4.176704425927811e-06,
      "loss": 0.4536,
      "step": 45466
    },
    {
      "epoch": 1.39670690873345,
      "grad_norm": 0.42883628606796265,
      "learning_rate": 4.176311551055069e-06,
      "loss": 0.5287,
      "step": 45467
    },
    {
      "epoch": 1.3967376278683992,
      "grad_norm": 0.382367879152298,
      "learning_rate": 4.1759186897839566e-06,
      "loss": 0.496,
      "step": 45468
    },
    {
      "epoch": 1.3967683470033485,
      "grad_norm": 0.4457269012928009,
      "learning_rate": 4.1755258421153934e-06,
      "loss": 0.4615,
      "step": 45469
    },
    {
      "epoch": 1.3967990661382976,
      "grad_norm": 0.4586758315563202,
      "learning_rate": 4.1751330080503e-06,
      "loss": 0.4452,
      "step": 45470
    },
    {
      "epoch": 1.3968297852732467,
      "grad_norm": 0.449219673871994,
      "learning_rate": 4.174740187589587e-06,
      "loss": 0.5273,
      "step": 45471
    },
    {
      "epoch": 1.3968605044081959,
      "grad_norm": 0.4165426790714264,
      "learning_rate": 4.174347380734174e-06,
      "loss": 0.4758,
      "step": 45472
    },
    {
      "epoch": 1.396891223543145,
      "grad_norm": 0.45127782225608826,
      "learning_rate": 4.17395458748498e-06,
      "loss": 0.4258,
      "step": 45473
    },
    {
      "epoch": 1.396921942678094,
      "grad_norm": 0.39246198534965515,
      "learning_rate": 4.173561807842922e-06,
      "loss": 0.4092,
      "step": 45474
    },
    {
      "epoch": 1.3969526618130432,
      "grad_norm": 0.5042487978935242,
      "learning_rate": 4.173169041808921e-06,
      "loss": 0.5906,
      "step": 45475
    },
    {
      "epoch": 1.3969833809479926,
      "grad_norm": 0.450072705745697,
      "learning_rate": 4.172776289383887e-06,
      "loss": 0.4775,
      "step": 45476
    },
    {
      "epoch": 1.3970141000829417,
      "grad_norm": 0.46073073148727417,
      "learning_rate": 4.17238355056874e-06,
      "loss": 0.4842,
      "step": 45477
    },
    {
      "epoch": 1.3970448192178908,
      "grad_norm": 0.4314554035663605,
      "learning_rate": 4.1719908253644005e-06,
      "loss": 0.4827,
      "step": 45478
    },
    {
      "epoch": 1.39707553835284,
      "grad_norm": 0.42717909812927246,
      "learning_rate": 4.171598113771785e-06,
      "loss": 0.4867,
      "step": 45479
    },
    {
      "epoch": 1.3971062574877893,
      "grad_norm": 0.43509581685066223,
      "learning_rate": 4.171205415791807e-06,
      "loss": 0.416,
      "step": 45480
    },
    {
      "epoch": 1.3971369766227384,
      "grad_norm": 0.4364968538284302,
      "learning_rate": 4.1708127314253855e-06,
      "loss": 0.525,
      "step": 45481
    },
    {
      "epoch": 1.3971676957576875,
      "grad_norm": 0.4494148790836334,
      "learning_rate": 4.170420060673437e-06,
      "loss": 0.4878,
      "step": 45482
    },
    {
      "epoch": 1.3971984148926366,
      "grad_norm": 0.44006475806236267,
      "learning_rate": 4.170027403536884e-06,
      "loss": 0.5281,
      "step": 45483
    },
    {
      "epoch": 1.3972291340275858,
      "grad_norm": 0.44719773530960083,
      "learning_rate": 4.1696347600166355e-06,
      "loss": 0.5003,
      "step": 45484
    },
    {
      "epoch": 1.3972598531625349,
      "grad_norm": 0.5208377242088318,
      "learning_rate": 4.169242130113615e-06,
      "loss": 0.5676,
      "step": 45485
    },
    {
      "epoch": 1.397290572297484,
      "grad_norm": 0.4009990096092224,
      "learning_rate": 4.168849513828731e-06,
      "loss": 0.3885,
      "step": 45486
    },
    {
      "epoch": 1.3973212914324333,
      "grad_norm": 0.4113381505012512,
      "learning_rate": 4.1684569111629125e-06,
      "loss": 0.4998,
      "step": 45487
    },
    {
      "epoch": 1.3973520105673825,
      "grad_norm": 0.4058378338813782,
      "learning_rate": 4.168064322117066e-06,
      "loss": 0.4211,
      "step": 45488
    },
    {
      "epoch": 1.3973827297023316,
      "grad_norm": 0.4870138168334961,
      "learning_rate": 4.167671746692114e-06,
      "loss": 0.5128,
      "step": 45489
    },
    {
      "epoch": 1.3974134488372807,
      "grad_norm": 0.48392409086227417,
      "learning_rate": 4.167279184888975e-06,
      "loss": 0.4644,
      "step": 45490
    },
    {
      "epoch": 1.39744416797223,
      "grad_norm": 0.41346362233161926,
      "learning_rate": 4.166886636708555e-06,
      "loss": 0.4056,
      "step": 45491
    },
    {
      "epoch": 1.3974748871071792,
      "grad_norm": 0.5125513076782227,
      "learning_rate": 4.166494102151786e-06,
      "loss": 0.4264,
      "step": 45492
    },
    {
      "epoch": 1.3975056062421283,
      "grad_norm": 0.36606869101524353,
      "learning_rate": 4.166101581219574e-06,
      "loss": 0.4138,
      "step": 45493
    },
    {
      "epoch": 1.3975363253770774,
      "grad_norm": 0.45985597372055054,
      "learning_rate": 4.165709073912842e-06,
      "loss": 0.4549,
      "step": 45494
    },
    {
      "epoch": 1.3975670445120265,
      "grad_norm": 0.41956815123558044,
      "learning_rate": 4.165316580232498e-06,
      "loss": 0.4255,
      "step": 45495
    },
    {
      "epoch": 1.3975977636469756,
      "grad_norm": 0.48735499382019043,
      "learning_rate": 4.164924100179471e-06,
      "loss": 0.4691,
      "step": 45496
    },
    {
      "epoch": 1.3976284827819248,
      "grad_norm": 0.462928831577301,
      "learning_rate": 4.1645316337546695e-06,
      "loss": 0.4403,
      "step": 45497
    },
    {
      "epoch": 1.397659201916874,
      "grad_norm": 0.4103923738002777,
      "learning_rate": 4.164139180959014e-06,
      "loss": 0.5142,
      "step": 45498
    },
    {
      "epoch": 1.3976899210518232,
      "grad_norm": 0.4524608254432678,
      "learning_rate": 4.1637467417934154e-06,
      "loss": 0.4715,
      "step": 45499
    },
    {
      "epoch": 1.3977206401867723,
      "grad_norm": 0.44572803378105164,
      "learning_rate": 4.1633543162587945e-06,
      "loss": 0.4933,
      "step": 45500
    },
    {
      "epoch": 1.3977513593217215,
      "grad_norm": 0.41541093587875366,
      "learning_rate": 4.162961904356065e-06,
      "loss": 0.4884,
      "step": 45501
    },
    {
      "epoch": 1.3977820784566708,
      "grad_norm": 0.4077591598033905,
      "learning_rate": 4.162569506086152e-06,
      "loss": 0.4775,
      "step": 45502
    },
    {
      "epoch": 1.39781279759162,
      "grad_norm": 0.41418471932411194,
      "learning_rate": 4.162177121449961e-06,
      "loss": 0.531,
      "step": 45503
    },
    {
      "epoch": 1.397843516726569,
      "grad_norm": 0.4099137485027313,
      "learning_rate": 4.161784750448413e-06,
      "loss": 0.4491,
      "step": 45504
    },
    {
      "epoch": 1.3978742358615182,
      "grad_norm": 0.3932420313358307,
      "learning_rate": 4.161392393082424e-06,
      "loss": 0.426,
      "step": 45505
    },
    {
      "epoch": 1.3979049549964673,
      "grad_norm": 0.43283334374427795,
      "learning_rate": 4.161000049352915e-06,
      "loss": 0.4839,
      "step": 45506
    },
    {
      "epoch": 1.3979356741314164,
      "grad_norm": 0.40388864278793335,
      "learning_rate": 4.160607719260794e-06,
      "loss": 0.4756,
      "step": 45507
    },
    {
      "epoch": 1.3979663932663655,
      "grad_norm": 0.43400049209594727,
      "learning_rate": 4.160215402806982e-06,
      "loss": 0.4631,
      "step": 45508
    },
    {
      "epoch": 1.3979971124013149,
      "grad_norm": 0.3967752456665039,
      "learning_rate": 4.159823099992395e-06,
      "loss": 0.4419,
      "step": 45509
    },
    {
      "epoch": 1.398027831536264,
      "grad_norm": 0.40703827142715454,
      "learning_rate": 4.159430810817949e-06,
      "loss": 0.4643,
      "step": 45510
    },
    {
      "epoch": 1.398058550671213,
      "grad_norm": 0.45963963866233826,
      "learning_rate": 4.159038535284563e-06,
      "loss": 0.4993,
      "step": 45511
    },
    {
      "epoch": 1.3980892698061622,
      "grad_norm": 0.40898269414901733,
      "learning_rate": 4.158646273393148e-06,
      "loss": 0.4476,
      "step": 45512
    },
    {
      "epoch": 1.3981199889411113,
      "grad_norm": 0.45667698979377747,
      "learning_rate": 4.158254025144622e-06,
      "loss": 0.4358,
      "step": 45513
    },
    {
      "epoch": 1.3981507080760607,
      "grad_norm": 0.4178202152252197,
      "learning_rate": 4.157861790539901e-06,
      "loss": 0.4522,
      "step": 45514
    },
    {
      "epoch": 1.3981814272110098,
      "grad_norm": 0.4050029218196869,
      "learning_rate": 4.157469569579906e-06,
      "loss": 0.5093,
      "step": 45515
    },
    {
      "epoch": 1.398212146345959,
      "grad_norm": 0.47522562742233276,
      "learning_rate": 4.157077362265546e-06,
      "loss": 0.465,
      "step": 45516
    },
    {
      "epoch": 1.398242865480908,
      "grad_norm": 0.4498029947280884,
      "learning_rate": 4.156685168597739e-06,
      "loss": 0.4712,
      "step": 45517
    },
    {
      "epoch": 1.3982735846158572,
      "grad_norm": 0.4481443464756012,
      "learning_rate": 4.156292988577402e-06,
      "loss": 0.5396,
      "step": 45518
    },
    {
      "epoch": 1.3983043037508063,
      "grad_norm": 0.4174632728099823,
      "learning_rate": 4.155900822205456e-06,
      "loss": 0.4767,
      "step": 45519
    },
    {
      "epoch": 1.3983350228857556,
      "grad_norm": 0.4210582673549652,
      "learning_rate": 4.155508669482805e-06,
      "loss": 0.4916,
      "step": 45520
    },
    {
      "epoch": 1.3983657420207047,
      "grad_norm": 0.44792044162750244,
      "learning_rate": 4.155116530410378e-06,
      "loss": 0.5157,
      "step": 45521
    },
    {
      "epoch": 1.3983964611556539,
      "grad_norm": 0.48063528537750244,
      "learning_rate": 4.1547244049890755e-06,
      "loss": 0.4361,
      "step": 45522
    },
    {
      "epoch": 1.398427180290603,
      "grad_norm": 0.44666215777397156,
      "learning_rate": 4.154332293219831e-06,
      "loss": 0.4533,
      "step": 45523
    },
    {
      "epoch": 1.398457899425552,
      "grad_norm": 0.4305869936943054,
      "learning_rate": 4.153940195103548e-06,
      "loss": 0.5003,
      "step": 45524
    },
    {
      "epoch": 1.3984886185605014,
      "grad_norm": 0.44098642468452454,
      "learning_rate": 4.153548110641145e-06,
      "loss": 0.4484,
      "step": 45525
    },
    {
      "epoch": 1.3985193376954506,
      "grad_norm": 0.4058142602443695,
      "learning_rate": 4.153156039833542e-06,
      "loss": 0.5378,
      "step": 45526
    },
    {
      "epoch": 1.3985500568303997,
      "grad_norm": 0.38996806740760803,
      "learning_rate": 4.152763982681646e-06,
      "loss": 0.48,
      "step": 45527
    },
    {
      "epoch": 1.3985807759653488,
      "grad_norm": 0.4166819453239441,
      "learning_rate": 4.152371939186384e-06,
      "loss": 0.4706,
      "step": 45528
    },
    {
      "epoch": 1.398611495100298,
      "grad_norm": 0.4208453893661499,
      "learning_rate": 4.1519799093486626e-06,
      "loss": 0.4778,
      "step": 45529
    },
    {
      "epoch": 1.398642214235247,
      "grad_norm": 0.4461536109447479,
      "learning_rate": 4.151587893169403e-06,
      "loss": 0.464,
      "step": 45530
    },
    {
      "epoch": 1.3986729333701962,
      "grad_norm": 0.4247363209724426,
      "learning_rate": 4.151195890649516e-06,
      "loss": 0.4153,
      "step": 45531
    },
    {
      "epoch": 1.3987036525051455,
      "grad_norm": 0.4066527187824249,
      "learning_rate": 4.150803901789919e-06,
      "loss": 0.4178,
      "step": 45532
    },
    {
      "epoch": 1.3987343716400946,
      "grad_norm": 0.4215526282787323,
      "learning_rate": 4.150411926591529e-06,
      "loss": 0.4718,
      "step": 45533
    },
    {
      "epoch": 1.3987650907750437,
      "grad_norm": 0.42563220858573914,
      "learning_rate": 4.150019965055263e-06,
      "loss": 0.4664,
      "step": 45534
    },
    {
      "epoch": 1.3987958099099929,
      "grad_norm": 0.43894830346107483,
      "learning_rate": 4.14962801718203e-06,
      "loss": 0.4967,
      "step": 45535
    },
    {
      "epoch": 1.3988265290449422,
      "grad_norm": 0.4545251131057739,
      "learning_rate": 4.149236082972751e-06,
      "loss": 0.4496,
      "step": 45536
    },
    {
      "epoch": 1.3988572481798913,
      "grad_norm": 0.4223872125148773,
      "learning_rate": 4.1488441624283385e-06,
      "loss": 0.4784,
      "step": 45537
    },
    {
      "epoch": 1.3988879673148404,
      "grad_norm": 0.43347713351249695,
      "learning_rate": 4.148452255549712e-06,
      "loss": 0.4812,
      "step": 45538
    },
    {
      "epoch": 1.3989186864497896,
      "grad_norm": 0.4284130334854126,
      "learning_rate": 4.148060362337782e-06,
      "loss": 0.4669,
      "step": 45539
    },
    {
      "epoch": 1.3989494055847387,
      "grad_norm": 0.4128967225551605,
      "learning_rate": 4.147668482793464e-06,
      "loss": 0.513,
      "step": 45540
    },
    {
      "epoch": 1.3989801247196878,
      "grad_norm": 0.4368690550327301,
      "learning_rate": 4.147276616917676e-06,
      "loss": 0.4379,
      "step": 45541
    },
    {
      "epoch": 1.399010843854637,
      "grad_norm": 0.4291967451572418,
      "learning_rate": 4.146884764711335e-06,
      "loss": 0.4614,
      "step": 45542
    },
    {
      "epoch": 1.3990415629895863,
      "grad_norm": 0.43732520937919617,
      "learning_rate": 4.146492926175352e-06,
      "loss": 0.4658,
      "step": 45543
    },
    {
      "epoch": 1.3990722821245354,
      "grad_norm": 0.42984485626220703,
      "learning_rate": 4.146101101310641e-06,
      "loss": 0.4341,
      "step": 45544
    },
    {
      "epoch": 1.3991030012594845,
      "grad_norm": 0.393877774477005,
      "learning_rate": 4.145709290118121e-06,
      "loss": 0.4434,
      "step": 45545
    },
    {
      "epoch": 1.3991337203944336,
      "grad_norm": 0.42327284812927246,
      "learning_rate": 4.145317492598706e-06,
      "loss": 0.4146,
      "step": 45546
    },
    {
      "epoch": 1.399164439529383,
      "grad_norm": 0.47145822644233704,
      "learning_rate": 4.144925708753313e-06,
      "loss": 0.5019,
      "step": 45547
    },
    {
      "epoch": 1.399195158664332,
      "grad_norm": 0.4062857925891876,
      "learning_rate": 4.1445339385828535e-06,
      "loss": 0.4784,
      "step": 45548
    },
    {
      "epoch": 1.3992258777992812,
      "grad_norm": 0.405953586101532,
      "learning_rate": 4.144142182088242e-06,
      "loss": 0.4291,
      "step": 45549
    },
    {
      "epoch": 1.3992565969342303,
      "grad_norm": 0.4093349874019623,
      "learning_rate": 4.143750439270396e-06,
      "loss": 0.4822,
      "step": 45550
    },
    {
      "epoch": 1.3992873160691794,
      "grad_norm": 0.4094184339046478,
      "learning_rate": 4.143358710130234e-06,
      "loss": 0.4031,
      "step": 45551
    },
    {
      "epoch": 1.3993180352041286,
      "grad_norm": 0.4061482846736908,
      "learning_rate": 4.142966994668663e-06,
      "loss": 0.4808,
      "step": 45552
    },
    {
      "epoch": 1.3993487543390777,
      "grad_norm": 0.40382033586502075,
      "learning_rate": 4.142575292886605e-06,
      "loss": 0.3988,
      "step": 45553
    },
    {
      "epoch": 1.399379473474027,
      "grad_norm": 0.3978815972805023,
      "learning_rate": 4.142183604784964e-06,
      "loss": 0.5383,
      "step": 45554
    },
    {
      "epoch": 1.3994101926089761,
      "grad_norm": 0.45375508069992065,
      "learning_rate": 4.141791930364671e-06,
      "loss": 0.4347,
      "step": 45555
    },
    {
      "epoch": 1.3994409117439253,
      "grad_norm": 0.4433753490447998,
      "learning_rate": 4.141400269626626e-06,
      "loss": 0.4619,
      "step": 45556
    },
    {
      "epoch": 1.3994716308788744,
      "grad_norm": 0.4221529960632324,
      "learning_rate": 4.141008622571755e-06,
      "loss": 0.5643,
      "step": 45557
    },
    {
      "epoch": 1.3995023500138237,
      "grad_norm": 0.4178515672683716,
      "learning_rate": 4.140616989200961e-06,
      "loss": 0.4828,
      "step": 45558
    },
    {
      "epoch": 1.3995330691487728,
      "grad_norm": 0.43230172991752625,
      "learning_rate": 4.14022536951517e-06,
      "loss": 0.4984,
      "step": 45559
    },
    {
      "epoch": 1.399563788283722,
      "grad_norm": 0.39168620109558105,
      "learning_rate": 4.139833763515291e-06,
      "loss": 0.4772,
      "step": 45560
    },
    {
      "epoch": 1.399594507418671,
      "grad_norm": 0.45842716097831726,
      "learning_rate": 4.139442171202241e-06,
      "loss": 0.552,
      "step": 45561
    },
    {
      "epoch": 1.3996252265536202,
      "grad_norm": 0.4200693368911743,
      "learning_rate": 4.1390505925769305e-06,
      "loss": 0.5505,
      "step": 45562
    },
    {
      "epoch": 1.3996559456885693,
      "grad_norm": 0.44706448912620544,
      "learning_rate": 4.1386590276402735e-06,
      "loss": 0.4992,
      "step": 45563
    },
    {
      "epoch": 1.3996866648235184,
      "grad_norm": 0.4465853273868561,
      "learning_rate": 4.138267476393194e-06,
      "loss": 0.4686,
      "step": 45564
    },
    {
      "epoch": 1.3997173839584678,
      "grad_norm": 0.4478444755077362,
      "learning_rate": 4.137875938836597e-06,
      "loss": 0.5039,
      "step": 45565
    },
    {
      "epoch": 1.399748103093417,
      "grad_norm": 0.44452086091041565,
      "learning_rate": 4.137484414971405e-06,
      "loss": 0.4247,
      "step": 45566
    },
    {
      "epoch": 1.399778822228366,
      "grad_norm": 0.48829716444015503,
      "learning_rate": 4.137092904798522e-06,
      "loss": 0.5193,
      "step": 45567
    },
    {
      "epoch": 1.3998095413633151,
      "grad_norm": 0.4050739109516144,
      "learning_rate": 4.136701408318869e-06,
      "loss": 0.4053,
      "step": 45568
    },
    {
      "epoch": 1.3998402604982645,
      "grad_norm": 0.46899673342704773,
      "learning_rate": 4.136309925533358e-06,
      "loss": 0.4978,
      "step": 45569
    },
    {
      "epoch": 1.3998709796332136,
      "grad_norm": 0.43025290966033936,
      "learning_rate": 4.13591845644291e-06,
      "loss": 0.4896,
      "step": 45570
    },
    {
      "epoch": 1.3999016987681627,
      "grad_norm": 0.5266445875167847,
      "learning_rate": 4.13552700104843e-06,
      "loss": 0.5164,
      "step": 45571
    },
    {
      "epoch": 1.3999324179031118,
      "grad_norm": 0.3915039598941803,
      "learning_rate": 4.1351355593508355e-06,
      "loss": 0.4237,
      "step": 45572
    },
    {
      "epoch": 1.399963137038061,
      "grad_norm": 0.42455777525901794,
      "learning_rate": 4.1347441313510415e-06,
      "loss": 0.4969,
      "step": 45573
    },
    {
      "epoch": 1.39999385617301,
      "grad_norm": 0.4169275760650635,
      "learning_rate": 4.1343527170499665e-06,
      "loss": 0.4893,
      "step": 45574
    },
    {
      "epoch": 1.4000245753079592,
      "grad_norm": 0.5060326457023621,
      "learning_rate": 4.133961316448517e-06,
      "loss": 0.4331,
      "step": 45575
    },
    {
      "epoch": 1.4000552944429085,
      "grad_norm": 0.3985847234725952,
      "learning_rate": 4.1335699295476095e-06,
      "loss": 0.4154,
      "step": 45576
    },
    {
      "epoch": 1.4000860135778577,
      "grad_norm": 0.39390677213668823,
      "learning_rate": 4.1331785563481596e-06,
      "loss": 0.405,
      "step": 45577
    },
    {
      "epoch": 1.4001167327128068,
      "grad_norm": 0.4643060564994812,
      "learning_rate": 4.1327871968510845e-06,
      "loss": 0.4737,
      "step": 45578
    },
    {
      "epoch": 1.400147451847756,
      "grad_norm": 0.4437738358974457,
      "learning_rate": 4.1323958510572915e-06,
      "loss": 0.4717,
      "step": 45579
    },
    {
      "epoch": 1.4001781709827053,
      "grad_norm": 0.3885997235774994,
      "learning_rate": 4.132004518967697e-06,
      "loss": 0.3543,
      "step": 45580
    },
    {
      "epoch": 1.4002088901176544,
      "grad_norm": 0.45619314908981323,
      "learning_rate": 4.131613200583217e-06,
      "loss": 0.4664,
      "step": 45581
    },
    {
      "epoch": 1.4002396092526035,
      "grad_norm": 0.44626736640930176,
      "learning_rate": 4.131221895904763e-06,
      "loss": 0.4936,
      "step": 45582
    },
    {
      "epoch": 1.4002703283875526,
      "grad_norm": 0.41327857971191406,
      "learning_rate": 4.130830604933255e-06,
      "loss": 0.4887,
      "step": 45583
    },
    {
      "epoch": 1.4003010475225017,
      "grad_norm": 0.38576066493988037,
      "learning_rate": 4.130439327669597e-06,
      "loss": 0.4348,
      "step": 45584
    },
    {
      "epoch": 1.4003317666574508,
      "grad_norm": 0.41315388679504395,
      "learning_rate": 4.130048064114709e-06,
      "loss": 0.4731,
      "step": 45585
    },
    {
      "epoch": 1.4003624857924,
      "grad_norm": 0.41691744327545166,
      "learning_rate": 4.129656814269503e-06,
      "loss": 0.4674,
      "step": 45586
    },
    {
      "epoch": 1.4003932049273493,
      "grad_norm": 0.44286826252937317,
      "learning_rate": 4.129265578134897e-06,
      "loss": 0.5772,
      "step": 45587
    },
    {
      "epoch": 1.4004239240622984,
      "grad_norm": 0.40962791442871094,
      "learning_rate": 4.128874355711798e-06,
      "loss": 0.4147,
      "step": 45588
    },
    {
      "epoch": 1.4004546431972476,
      "grad_norm": 0.3818014860153198,
      "learning_rate": 4.128483147001127e-06,
      "loss": 0.4424,
      "step": 45589
    },
    {
      "epoch": 1.4004853623321967,
      "grad_norm": 0.4205148220062256,
      "learning_rate": 4.128091952003785e-06,
      "loss": 0.4379,
      "step": 45590
    },
    {
      "epoch": 1.400516081467146,
      "grad_norm": 0.41141754388809204,
      "learning_rate": 4.1277007707207026e-06,
      "loss": 0.4264,
      "step": 45591
    },
    {
      "epoch": 1.4005468006020951,
      "grad_norm": 0.42763862013816833,
      "learning_rate": 4.1273096031527815e-06,
      "loss": 0.5257,
      "step": 45592
    },
    {
      "epoch": 1.4005775197370443,
      "grad_norm": 1.1717387437820435,
      "learning_rate": 4.126918449300943e-06,
      "loss": 0.3846,
      "step": 45593
    },
    {
      "epoch": 1.4006082388719934,
      "grad_norm": 0.46425843238830566,
      "learning_rate": 4.126527309166091e-06,
      "loss": 0.5207,
      "step": 45594
    },
    {
      "epoch": 1.4006389580069425,
      "grad_norm": 0.4813980758190155,
      "learning_rate": 4.126136182749148e-06,
      "loss": 0.4952,
      "step": 45595
    },
    {
      "epoch": 1.4006696771418916,
      "grad_norm": 0.4872015714645386,
      "learning_rate": 4.125745070051021e-06,
      "loss": 0.4919,
      "step": 45596
    },
    {
      "epoch": 1.4007003962768407,
      "grad_norm": 0.4282221496105194,
      "learning_rate": 4.125353971072632e-06,
      "loss": 0.4537,
      "step": 45597
    },
    {
      "epoch": 1.40073111541179,
      "grad_norm": 0.3982320725917816,
      "learning_rate": 4.124962885814886e-06,
      "loss": 0.4754,
      "step": 45598
    },
    {
      "epoch": 1.4007618345467392,
      "grad_norm": 0.39048075675964355,
      "learning_rate": 4.124571814278695e-06,
      "loss": 0.4325,
      "step": 45599
    },
    {
      "epoch": 1.4007925536816883,
      "grad_norm": 0.40074607729911804,
      "learning_rate": 4.124180756464984e-06,
      "loss": 0.5028,
      "step": 45600
    },
    {
      "epoch": 1.4008232728166374,
      "grad_norm": 0.4136805832386017,
      "learning_rate": 4.123789712374655e-06,
      "loss": 0.4609,
      "step": 45601
    },
    {
      "epoch": 1.4008539919515868,
      "grad_norm": 0.4202874004840851,
      "learning_rate": 4.12339868200863e-06,
      "loss": 0.4317,
      "step": 45602
    },
    {
      "epoch": 1.400884711086536,
      "grad_norm": 0.44651466608047485,
      "learning_rate": 4.123007665367814e-06,
      "loss": 0.4605,
      "step": 45603
    },
    {
      "epoch": 1.400915430221485,
      "grad_norm": 0.43354150652885437,
      "learning_rate": 4.1226166624531235e-06,
      "loss": 0.5226,
      "step": 45604
    },
    {
      "epoch": 1.4009461493564341,
      "grad_norm": 0.451524943113327,
      "learning_rate": 4.122225673265473e-06,
      "loss": 0.4847,
      "step": 45605
    },
    {
      "epoch": 1.4009768684913833,
      "grad_norm": 0.40832099318504333,
      "learning_rate": 4.121834697805779e-06,
      "loss": 0.4769,
      "step": 45606
    },
    {
      "epoch": 1.4010075876263324,
      "grad_norm": 0.4387471675872803,
      "learning_rate": 4.121443736074946e-06,
      "loss": 0.4576,
      "step": 45607
    },
    {
      "epoch": 1.4010383067612815,
      "grad_norm": 0.36439910531044006,
      "learning_rate": 4.121052788073891e-06,
      "loss": 0.394,
      "step": 45608
    },
    {
      "epoch": 1.4010690258962308,
      "grad_norm": 0.4396130442619324,
      "learning_rate": 4.12066185380353e-06,
      "loss": 0.5138,
      "step": 45609
    },
    {
      "epoch": 1.40109974503118,
      "grad_norm": 0.43779996037483215,
      "learning_rate": 4.120270933264776e-06,
      "loss": 0.4982,
      "step": 45610
    },
    {
      "epoch": 1.401130464166129,
      "grad_norm": 0.396884024143219,
      "learning_rate": 4.119880026458537e-06,
      "loss": 0.4806,
      "step": 45611
    },
    {
      "epoch": 1.4011611833010782,
      "grad_norm": 0.37321335077285767,
      "learning_rate": 4.119489133385728e-06,
      "loss": 0.4476,
      "step": 45612
    },
    {
      "epoch": 1.4011919024360275,
      "grad_norm": 0.42073190212249756,
      "learning_rate": 4.1190982540472635e-06,
      "loss": 0.4289,
      "step": 45613
    },
    {
      "epoch": 1.4012226215709767,
      "grad_norm": 0.40248873829841614,
      "learning_rate": 4.118707388444059e-06,
      "loss": 0.4555,
      "step": 45614
    },
    {
      "epoch": 1.4012533407059258,
      "grad_norm": 0.478904128074646,
      "learning_rate": 4.118316536577021e-06,
      "loss": 0.475,
      "step": 45615
    },
    {
      "epoch": 1.401284059840875,
      "grad_norm": 0.40023738145828247,
      "learning_rate": 4.117925698447068e-06,
      "loss": 0.4822,
      "step": 45616
    },
    {
      "epoch": 1.401314778975824,
      "grad_norm": 0.50542813539505,
      "learning_rate": 4.117534874055104e-06,
      "loss": 0.5854,
      "step": 45617
    },
    {
      "epoch": 1.4013454981107731,
      "grad_norm": 0.3967782258987427,
      "learning_rate": 4.117144063402052e-06,
      "loss": 0.4207,
      "step": 45618
    },
    {
      "epoch": 1.4013762172457223,
      "grad_norm": 0.42653727531433105,
      "learning_rate": 4.116753266488823e-06,
      "loss": 0.4321,
      "step": 45619
    },
    {
      "epoch": 1.4014069363806716,
      "grad_norm": 0.4362056851387024,
      "learning_rate": 4.116362483316325e-06,
      "loss": 0.476,
      "step": 45620
    },
    {
      "epoch": 1.4014376555156207,
      "grad_norm": 0.4424726963043213,
      "learning_rate": 4.115971713885474e-06,
      "loss": 0.4693,
      "step": 45621
    },
    {
      "epoch": 1.4014683746505698,
      "grad_norm": 0.43353360891342163,
      "learning_rate": 4.1155809581971814e-06,
      "loss": 0.4676,
      "step": 45622
    },
    {
      "epoch": 1.401499093785519,
      "grad_norm": 0.4048178195953369,
      "learning_rate": 4.115190216252363e-06,
      "loss": 0.4026,
      "step": 45623
    },
    {
      "epoch": 1.401529812920468,
      "grad_norm": 0.4276634752750397,
      "learning_rate": 4.114799488051927e-06,
      "loss": 0.5019,
      "step": 45624
    },
    {
      "epoch": 1.4015605320554174,
      "grad_norm": 0.3992377519607544,
      "learning_rate": 4.114408773596791e-06,
      "loss": 0.4087,
      "step": 45625
    },
    {
      "epoch": 1.4015912511903665,
      "grad_norm": 0.4245339632034302,
      "learning_rate": 4.114018072887857e-06,
      "loss": 0.5092,
      "step": 45626
    },
    {
      "epoch": 1.4016219703253157,
      "grad_norm": 0.5689626336097717,
      "learning_rate": 4.113627385926052e-06,
      "loss": 0.4154,
      "step": 45627
    },
    {
      "epoch": 1.4016526894602648,
      "grad_norm": 0.42775171995162964,
      "learning_rate": 4.113236712712278e-06,
      "loss": 0.4995,
      "step": 45628
    },
    {
      "epoch": 1.401683408595214,
      "grad_norm": 0.40703901648521423,
      "learning_rate": 4.112846053247454e-06,
      "loss": 0.5309,
      "step": 45629
    },
    {
      "epoch": 1.401714127730163,
      "grad_norm": 0.43776610493659973,
      "learning_rate": 4.112455407532485e-06,
      "loss": 0.4789,
      "step": 45630
    },
    {
      "epoch": 1.4017448468651124,
      "grad_norm": 0.41202908754348755,
      "learning_rate": 4.112064775568289e-06,
      "loss": 0.4422,
      "step": 45631
    },
    {
      "epoch": 1.4017755660000615,
      "grad_norm": 0.4526711404323578,
      "learning_rate": 4.111674157355776e-06,
      "loss": 0.4771,
      "step": 45632
    },
    {
      "epoch": 1.4018062851350106,
      "grad_norm": 0.42475512623786926,
      "learning_rate": 4.111283552895863e-06,
      "loss": 0.4967,
      "step": 45633
    },
    {
      "epoch": 1.4018370042699597,
      "grad_norm": 0.43387192487716675,
      "learning_rate": 4.1108929621894546e-06,
      "loss": 0.5163,
      "step": 45634
    },
    {
      "epoch": 1.4018677234049088,
      "grad_norm": 0.4259651303291321,
      "learning_rate": 4.110502385237467e-06,
      "loss": 0.4967,
      "step": 45635
    },
    {
      "epoch": 1.4018984425398582,
      "grad_norm": 0.4305487871170044,
      "learning_rate": 4.110111822040813e-06,
      "loss": 0.5237,
      "step": 45636
    },
    {
      "epoch": 1.4019291616748073,
      "grad_norm": 0.39170974493026733,
      "learning_rate": 4.109721272600403e-06,
      "loss": 0.4747,
      "step": 45637
    },
    {
      "epoch": 1.4019598808097564,
      "grad_norm": 0.431864470243454,
      "learning_rate": 4.109330736917156e-06,
      "loss": 0.4796,
      "step": 45638
    },
    {
      "epoch": 1.4019905999447055,
      "grad_norm": 0.3861975073814392,
      "learning_rate": 4.108940214991973e-06,
      "loss": 0.4664,
      "step": 45639
    },
    {
      "epoch": 1.4020213190796547,
      "grad_norm": 0.3899838626384735,
      "learning_rate": 4.108549706825773e-06,
      "loss": 0.4711,
      "step": 45640
    },
    {
      "epoch": 1.4020520382146038,
      "grad_norm": 0.46107468008995056,
      "learning_rate": 4.108159212419466e-06,
      "loss": 0.4541,
      "step": 45641
    },
    {
      "epoch": 1.402082757349553,
      "grad_norm": 0.4389423131942749,
      "learning_rate": 4.107768731773968e-06,
      "loss": 0.4852,
      "step": 45642
    },
    {
      "epoch": 1.4021134764845022,
      "grad_norm": 0.41237977147102356,
      "learning_rate": 4.107378264890184e-06,
      "loss": 0.4594,
      "step": 45643
    },
    {
      "epoch": 1.4021441956194514,
      "grad_norm": 0.4540516436100006,
      "learning_rate": 4.106987811769029e-06,
      "loss": 0.5166,
      "step": 45644
    },
    {
      "epoch": 1.4021749147544005,
      "grad_norm": 0.4232231676578522,
      "learning_rate": 4.106597372411416e-06,
      "loss": 0.4008,
      "step": 45645
    },
    {
      "epoch": 1.4022056338893496,
      "grad_norm": 0.3934909403324127,
      "learning_rate": 4.106206946818261e-06,
      "loss": 0.4038,
      "step": 45646
    },
    {
      "epoch": 1.402236353024299,
      "grad_norm": 0.40545639395713806,
      "learning_rate": 4.105816534990467e-06,
      "loss": 0.5213,
      "step": 45647
    },
    {
      "epoch": 1.402267072159248,
      "grad_norm": 0.4030139446258545,
      "learning_rate": 4.105426136928949e-06,
      "loss": 0.408,
      "step": 45648
    },
    {
      "epoch": 1.4022977912941972,
      "grad_norm": 0.5455765128135681,
      "learning_rate": 4.105035752634622e-06,
      "loss": 0.4279,
      "step": 45649
    },
    {
      "epoch": 1.4023285104291463,
      "grad_norm": 0.3994384706020355,
      "learning_rate": 4.1046453821083975e-06,
      "loss": 0.4218,
      "step": 45650
    },
    {
      "epoch": 1.4023592295640954,
      "grad_norm": 0.48449772596359253,
      "learning_rate": 4.104255025351184e-06,
      "loss": 0.4356,
      "step": 45651
    },
    {
      "epoch": 1.4023899486990445,
      "grad_norm": 0.42895904183387756,
      "learning_rate": 4.103864682363896e-06,
      "loss": 0.5013,
      "step": 45652
    },
    {
      "epoch": 1.4024206678339937,
      "grad_norm": 0.3929693400859833,
      "learning_rate": 4.103474353147437e-06,
      "loss": 0.4658,
      "step": 45653
    },
    {
      "epoch": 1.402451386968943,
      "grad_norm": 0.41573068499565125,
      "learning_rate": 4.10308403770273e-06,
      "loss": 0.4666,
      "step": 45654
    },
    {
      "epoch": 1.4024821061038921,
      "grad_norm": 0.4209316372871399,
      "learning_rate": 4.102693736030685e-06,
      "loss": 0.4206,
      "step": 45655
    },
    {
      "epoch": 1.4025128252388412,
      "grad_norm": 0.5047789812088013,
      "learning_rate": 4.102303448132208e-06,
      "loss": 0.5538,
      "step": 45656
    },
    {
      "epoch": 1.4025435443737904,
      "grad_norm": 0.4629477262496948,
      "learning_rate": 4.101913174008212e-06,
      "loss": 0.3946,
      "step": 45657
    },
    {
      "epoch": 1.4025742635087397,
      "grad_norm": 0.42588093876838684,
      "learning_rate": 4.10152291365961e-06,
      "loss": 0.5758,
      "step": 45658
    },
    {
      "epoch": 1.4026049826436888,
      "grad_norm": 0.4073216915130615,
      "learning_rate": 4.101132667087318e-06,
      "loss": 0.531,
      "step": 45659
    },
    {
      "epoch": 1.402635701778638,
      "grad_norm": 0.4203091561794281,
      "learning_rate": 4.100742434292237e-06,
      "loss": 0.4101,
      "step": 45660
    },
    {
      "epoch": 1.402666420913587,
      "grad_norm": 0.4312853217124939,
      "learning_rate": 4.10035221527529e-06,
      "loss": 0.4471,
      "step": 45661
    },
    {
      "epoch": 1.4026971400485362,
      "grad_norm": 0.4462880492210388,
      "learning_rate": 4.0999620100373725e-06,
      "loss": 0.5037,
      "step": 45662
    },
    {
      "epoch": 1.4027278591834853,
      "grad_norm": 0.4215978682041168,
      "learning_rate": 4.099571818579414e-06,
      "loss": 0.5192,
      "step": 45663
    },
    {
      "epoch": 1.4027585783184344,
      "grad_norm": 0.4961681067943573,
      "learning_rate": 4.0991816409023145e-06,
      "loss": 0.3819,
      "step": 45664
    },
    {
      "epoch": 1.4027892974533838,
      "grad_norm": 0.41887933015823364,
      "learning_rate": 4.098791477006992e-06,
      "loss": 0.5508,
      "step": 45665
    },
    {
      "epoch": 1.4028200165883329,
      "grad_norm": 0.4393203854560852,
      "learning_rate": 4.09840132689435e-06,
      "loss": 0.5452,
      "step": 45666
    },
    {
      "epoch": 1.402850735723282,
      "grad_norm": 0.4690425992012024,
      "learning_rate": 4.098011190565305e-06,
      "loss": 0.5068,
      "step": 45667
    },
    {
      "epoch": 1.4028814548582311,
      "grad_norm": 0.4091542959213257,
      "learning_rate": 4.097621068020766e-06,
      "loss": 0.3731,
      "step": 45668
    },
    {
      "epoch": 1.4029121739931805,
      "grad_norm": 0.3861703872680664,
      "learning_rate": 4.097230959261649e-06,
      "loss": 0.4734,
      "step": 45669
    },
    {
      "epoch": 1.4029428931281296,
      "grad_norm": 0.5794280171394348,
      "learning_rate": 4.096840864288858e-06,
      "loss": 0.4599,
      "step": 45670
    },
    {
      "epoch": 1.4029736122630787,
      "grad_norm": 0.4423368275165558,
      "learning_rate": 4.096450783103307e-06,
      "loss": 0.4767,
      "step": 45671
    },
    {
      "epoch": 1.4030043313980278,
      "grad_norm": 0.46219250559806824,
      "learning_rate": 4.096060715705908e-06,
      "loss": 0.4815,
      "step": 45672
    },
    {
      "epoch": 1.403035050532977,
      "grad_norm": 0.7244253158569336,
      "learning_rate": 4.0956706620975715e-06,
      "loss": 0.4621,
      "step": 45673
    },
    {
      "epoch": 1.403065769667926,
      "grad_norm": 0.39002829790115356,
      "learning_rate": 4.0952806222792115e-06,
      "loss": 0.4103,
      "step": 45674
    },
    {
      "epoch": 1.4030964888028752,
      "grad_norm": 0.42406466603279114,
      "learning_rate": 4.094890596251733e-06,
      "loss": 0.443,
      "step": 45675
    },
    {
      "epoch": 1.4031272079378245,
      "grad_norm": 0.40714696049690247,
      "learning_rate": 4.09450058401605e-06,
      "loss": 0.4676,
      "step": 45676
    },
    {
      "epoch": 1.4031579270727736,
      "grad_norm": 0.4004513919353485,
      "learning_rate": 4.094110585573072e-06,
      "loss": 0.41,
      "step": 45677
    },
    {
      "epoch": 1.4031886462077228,
      "grad_norm": 0.410526305437088,
      "learning_rate": 4.093720600923716e-06,
      "loss": 0.4273,
      "step": 45678
    },
    {
      "epoch": 1.4032193653426719,
      "grad_norm": 0.5201079249382019,
      "learning_rate": 4.093330630068885e-06,
      "loss": 0.4166,
      "step": 45679
    },
    {
      "epoch": 1.4032500844776212,
      "grad_norm": 0.42677196860313416,
      "learning_rate": 4.0929406730094926e-06,
      "loss": 0.4762,
      "step": 45680
    },
    {
      "epoch": 1.4032808036125703,
      "grad_norm": 0.4677574634552002,
      "learning_rate": 4.0925507297464485e-06,
      "loss": 0.4021,
      "step": 45681
    },
    {
      "epoch": 1.4033115227475195,
      "grad_norm": 0.4622911810874939,
      "learning_rate": 4.092160800280669e-06,
      "loss": 0.4445,
      "step": 45682
    },
    {
      "epoch": 1.4033422418824686,
      "grad_norm": 0.3733392059803009,
      "learning_rate": 4.091770884613058e-06,
      "loss": 0.4448,
      "step": 45683
    },
    {
      "epoch": 1.4033729610174177,
      "grad_norm": 0.3870513439178467,
      "learning_rate": 4.091380982744527e-06,
      "loss": 0.4546,
      "step": 45684
    },
    {
      "epoch": 1.4034036801523668,
      "grad_norm": 0.45650428533554077,
      "learning_rate": 4.090991094675989e-06,
      "loss": 0.4576,
      "step": 45685
    },
    {
      "epoch": 1.403434399287316,
      "grad_norm": 0.4314165413379669,
      "learning_rate": 4.090601220408358e-06,
      "loss": 0.4827,
      "step": 45686
    },
    {
      "epoch": 1.4034651184222653,
      "grad_norm": 0.38672471046447754,
      "learning_rate": 4.090211359942536e-06,
      "loss": 0.4318,
      "step": 45687
    },
    {
      "epoch": 1.4034958375572144,
      "grad_norm": 0.41292959451675415,
      "learning_rate": 4.089821513279443e-06,
      "loss": 0.4226,
      "step": 45688
    },
    {
      "epoch": 1.4035265566921635,
      "grad_norm": 0.4395959675312042,
      "learning_rate": 4.0894316804199775e-06,
      "loss": 0.4234,
      "step": 45689
    },
    {
      "epoch": 1.4035572758271126,
      "grad_norm": 0.3756789565086365,
      "learning_rate": 4.08904186136506e-06,
      "loss": 0.4135,
      "step": 45690
    },
    {
      "epoch": 1.403587994962062,
      "grad_norm": 0.41527506709098816,
      "learning_rate": 4.088652056115601e-06,
      "loss": 0.524,
      "step": 45691
    },
    {
      "epoch": 1.403618714097011,
      "grad_norm": 0.4198114573955536,
      "learning_rate": 4.088262264672506e-06,
      "loss": 0.4282,
      "step": 45692
    },
    {
      "epoch": 1.4036494332319602,
      "grad_norm": 0.41483116149902344,
      "learning_rate": 4.087872487036689e-06,
      "loss": 0.4797,
      "step": 45693
    },
    {
      "epoch": 1.4036801523669094,
      "grad_norm": 0.41438791155815125,
      "learning_rate": 4.087482723209053e-06,
      "loss": 0.3981,
      "step": 45694
    },
    {
      "epoch": 1.4037108715018585,
      "grad_norm": 0.4123876690864563,
      "learning_rate": 4.087092973190521e-06,
      "loss": 0.5072,
      "step": 45695
    },
    {
      "epoch": 1.4037415906368076,
      "grad_norm": 0.3924926221370697,
      "learning_rate": 4.086703236981991e-06,
      "loss": 0.4375,
      "step": 45696
    },
    {
      "epoch": 1.4037723097717567,
      "grad_norm": 0.436148464679718,
      "learning_rate": 4.086313514584385e-06,
      "loss": 0.4892,
      "step": 45697
    },
    {
      "epoch": 1.403803028906706,
      "grad_norm": 0.4253326952457428,
      "learning_rate": 4.085923805998598e-06,
      "loss": 0.467,
      "step": 45698
    },
    {
      "epoch": 1.4038337480416552,
      "grad_norm": 0.4427044987678528,
      "learning_rate": 4.085534111225556e-06,
      "loss": 0.4085,
      "step": 45699
    },
    {
      "epoch": 1.4038644671766043,
      "grad_norm": 0.4233471751213074,
      "learning_rate": 4.0851444302661594e-06,
      "loss": 0.4651,
      "step": 45700
    },
    {
      "epoch": 1.4038951863115534,
      "grad_norm": 0.42895179986953735,
      "learning_rate": 4.084754763121324e-06,
      "loss": 0.5778,
      "step": 45701
    },
    {
      "epoch": 1.4039259054465028,
      "grad_norm": 0.4316326081752777,
      "learning_rate": 4.0843651097919535e-06,
      "loss": 0.4358,
      "step": 45702
    },
    {
      "epoch": 1.4039566245814519,
      "grad_norm": 0.39832383394241333,
      "learning_rate": 4.083975470278961e-06,
      "loss": 0.4436,
      "step": 45703
    },
    {
      "epoch": 1.403987343716401,
      "grad_norm": 0.405040442943573,
      "learning_rate": 4.083585844583258e-06,
      "loss": 0.4791,
      "step": 45704
    },
    {
      "epoch": 1.4040180628513501,
      "grad_norm": 0.6411314606666565,
      "learning_rate": 4.083196232705756e-06,
      "loss": 0.4609,
      "step": 45705
    },
    {
      "epoch": 1.4040487819862992,
      "grad_norm": 0.40635553002357483,
      "learning_rate": 4.0828066346473596e-06,
      "loss": 0.4787,
      "step": 45706
    },
    {
      "epoch": 1.4040795011212484,
      "grad_norm": 0.4233889579772949,
      "learning_rate": 4.082417050408981e-06,
      "loss": 0.4922,
      "step": 45707
    },
    {
      "epoch": 1.4041102202561975,
      "grad_norm": 0.42937642335891724,
      "learning_rate": 4.082027479991532e-06,
      "loss": 0.5398,
      "step": 45708
    },
    {
      "epoch": 1.4041409393911468,
      "grad_norm": 0.47693949937820435,
      "learning_rate": 4.081637923395919e-06,
      "loss": 0.461,
      "step": 45709
    },
    {
      "epoch": 1.404171658526096,
      "grad_norm": 0.39790624380111694,
      "learning_rate": 4.0812483806230585e-06,
      "loss": 0.4873,
      "step": 45710
    },
    {
      "epoch": 1.404202377661045,
      "grad_norm": 0.4085404574871063,
      "learning_rate": 4.080858851673852e-06,
      "loss": 0.4851,
      "step": 45711
    },
    {
      "epoch": 1.4042330967959942,
      "grad_norm": 0.37958404421806335,
      "learning_rate": 4.080469336549214e-06,
      "loss": 0.4083,
      "step": 45712
    },
    {
      "epoch": 1.4042638159309435,
      "grad_norm": 0.4594196379184723,
      "learning_rate": 4.0800798352500525e-06,
      "loss": 0.4805,
      "step": 45713
    },
    {
      "epoch": 1.4042945350658926,
      "grad_norm": 0.4558652937412262,
      "learning_rate": 4.079690347777282e-06,
      "loss": 0.4529,
      "step": 45714
    },
    {
      "epoch": 1.4043252542008418,
      "grad_norm": 0.4179072678089142,
      "learning_rate": 4.079300874131804e-06,
      "loss": 0.4489,
      "step": 45715
    },
    {
      "epoch": 1.4043559733357909,
      "grad_norm": 0.4190850257873535,
      "learning_rate": 4.078911414314532e-06,
      "loss": 0.4374,
      "step": 45716
    },
    {
      "epoch": 1.40438669247074,
      "grad_norm": 0.4293390214443207,
      "learning_rate": 4.078521968326378e-06,
      "loss": 0.4222,
      "step": 45717
    },
    {
      "epoch": 1.4044174116056891,
      "grad_norm": 0.4286016821861267,
      "learning_rate": 4.0781325361682515e-06,
      "loss": 0.474,
      "step": 45718
    },
    {
      "epoch": 1.4044481307406382,
      "grad_norm": 0.4488123655319214,
      "learning_rate": 4.077743117841055e-06,
      "loss": 0.4563,
      "step": 45719
    },
    {
      "epoch": 1.4044788498755876,
      "grad_norm": 0.4225175976753235,
      "learning_rate": 4.077353713345705e-06,
      "loss": 0.432,
      "step": 45720
    },
    {
      "epoch": 1.4045095690105367,
      "grad_norm": 0.3969472348690033,
      "learning_rate": 4.076964322683109e-06,
      "loss": 0.4698,
      "step": 45721
    },
    {
      "epoch": 1.4045402881454858,
      "grad_norm": 0.4108085334300995,
      "learning_rate": 4.0765749458541795e-06,
      "loss": 0.4334,
      "step": 45722
    },
    {
      "epoch": 1.404571007280435,
      "grad_norm": 0.40751737356185913,
      "learning_rate": 4.076185582859819e-06,
      "loss": 0.532,
      "step": 45723
    },
    {
      "epoch": 1.4046017264153843,
      "grad_norm": 0.3964606523513794,
      "learning_rate": 4.075796233700946e-06,
      "loss": 0.5536,
      "step": 45724
    },
    {
      "epoch": 1.4046324455503334,
      "grad_norm": 0.4283568263053894,
      "learning_rate": 4.075406898378455e-06,
      "loss": 0.5162,
      "step": 45725
    },
    {
      "epoch": 1.4046631646852825,
      "grad_norm": 0.4085944890975952,
      "learning_rate": 4.075017576893271e-06,
      "loss": 0.5292,
      "step": 45726
    },
    {
      "epoch": 1.4046938838202316,
      "grad_norm": 0.4528345763683319,
      "learning_rate": 4.0746282692463e-06,
      "loss": 0.4817,
      "step": 45727
    },
    {
      "epoch": 1.4047246029551808,
      "grad_norm": 0.3854716718196869,
      "learning_rate": 4.074238975438445e-06,
      "loss": 0.4486,
      "step": 45728
    },
    {
      "epoch": 1.4047553220901299,
      "grad_norm": 0.411213219165802,
      "learning_rate": 4.073849695470621e-06,
      "loss": 0.4488,
      "step": 45729
    },
    {
      "epoch": 1.404786041225079,
      "grad_norm": 0.40070369839668274,
      "learning_rate": 4.073460429343729e-06,
      "loss": 0.4408,
      "step": 45730
    },
    {
      "epoch": 1.4048167603600283,
      "grad_norm": 0.4033569097518921,
      "learning_rate": 4.073071177058691e-06,
      "loss": 0.4753,
      "step": 45731
    },
    {
      "epoch": 1.4048474794949775,
      "grad_norm": 0.42800042033195496,
      "learning_rate": 4.072681938616405e-06,
      "loss": 0.5049,
      "step": 45732
    },
    {
      "epoch": 1.4048781986299266,
      "grad_norm": 0.6395576000213623,
      "learning_rate": 4.072292714017789e-06,
      "loss": 0.4338,
      "step": 45733
    },
    {
      "epoch": 1.4049089177648757,
      "grad_norm": 0.40296563506126404,
      "learning_rate": 4.071903503263744e-06,
      "loss": 0.4902,
      "step": 45734
    },
    {
      "epoch": 1.404939636899825,
      "grad_norm": 0.43153437972068787,
      "learning_rate": 4.071514306355181e-06,
      "loss": 0.4522,
      "step": 45735
    },
    {
      "epoch": 1.4049703560347742,
      "grad_norm": 0.4263765513896942,
      "learning_rate": 4.07112512329301e-06,
      "loss": 0.5736,
      "step": 45736
    },
    {
      "epoch": 1.4050010751697233,
      "grad_norm": 0.46080282330513,
      "learning_rate": 4.070735954078145e-06,
      "loss": 0.447,
      "step": 45737
    },
    {
      "epoch": 1.4050317943046724,
      "grad_norm": 0.39557480812072754,
      "learning_rate": 4.070346798711488e-06,
      "loss": 0.4715,
      "step": 45738
    },
    {
      "epoch": 1.4050625134396215,
      "grad_norm": 0.38506388664245605,
      "learning_rate": 4.069957657193948e-06,
      "loss": 0.4577,
      "step": 45739
    },
    {
      "epoch": 1.4050932325745706,
      "grad_norm": 0.4543263614177704,
      "learning_rate": 4.0695685295264365e-06,
      "loss": 0.4569,
      "step": 45740
    },
    {
      "epoch": 1.4051239517095198,
      "grad_norm": 0.4205414652824402,
      "learning_rate": 4.0691794157098665e-06,
      "loss": 0.4503,
      "step": 45741
    },
    {
      "epoch": 1.405154670844469,
      "grad_norm": 0.4583207666873932,
      "learning_rate": 4.068790315745137e-06,
      "loss": 0.4895,
      "step": 45742
    },
    {
      "epoch": 1.4051853899794182,
      "grad_norm": 0.5122871398925781,
      "learning_rate": 4.068401229633163e-06,
      "loss": 0.463,
      "step": 45743
    },
    {
      "epoch": 1.4052161091143673,
      "grad_norm": 0.4080888628959656,
      "learning_rate": 4.0680121573748525e-06,
      "loss": 0.5122,
      "step": 45744
    },
    {
      "epoch": 1.4052468282493165,
      "grad_norm": 0.43497195839881897,
      "learning_rate": 4.067623098971113e-06,
      "loss": 0.5373,
      "step": 45745
    },
    {
      "epoch": 1.4052775473842656,
      "grad_norm": 0.39546504616737366,
      "learning_rate": 4.067234054422857e-06,
      "loss": 0.4404,
      "step": 45746
    },
    {
      "epoch": 1.405308266519215,
      "grad_norm": 0.4343700408935547,
      "learning_rate": 4.066845023730989e-06,
      "loss": 0.4633,
      "step": 45747
    },
    {
      "epoch": 1.405338985654164,
      "grad_norm": 0.48221448063850403,
      "learning_rate": 4.0664560068964165e-06,
      "loss": 0.4522,
      "step": 45748
    },
    {
      "epoch": 1.4053697047891132,
      "grad_norm": 0.37869930267333984,
      "learning_rate": 4.066067003920051e-06,
      "loss": 0.4667,
      "step": 45749
    },
    {
      "epoch": 1.4054004239240623,
      "grad_norm": 0.46435678005218506,
      "learning_rate": 4.065678014802805e-06,
      "loss": 0.5302,
      "step": 45750
    },
    {
      "epoch": 1.4054311430590114,
      "grad_norm": 0.3957669138908386,
      "learning_rate": 4.065289039545578e-06,
      "loss": 0.4881,
      "step": 45751
    },
    {
      "epoch": 1.4054618621939605,
      "grad_norm": 0.37673524022102356,
      "learning_rate": 4.064900078149283e-06,
      "loss": 0.4546,
      "step": 45752
    },
    {
      "epoch": 1.4054925813289096,
      "grad_norm": 0.4142308533191681,
      "learning_rate": 4.064511130614829e-06,
      "loss": 0.4772,
      "step": 45753
    },
    {
      "epoch": 1.405523300463859,
      "grad_norm": 0.3836481273174286,
      "learning_rate": 4.0641221969431265e-06,
      "loss": 0.45,
      "step": 45754
    },
    {
      "epoch": 1.405554019598808,
      "grad_norm": 0.46231281757354736,
      "learning_rate": 4.063733277135078e-06,
      "loss": 0.5397,
      "step": 45755
    },
    {
      "epoch": 1.4055847387337572,
      "grad_norm": 0.45420050621032715,
      "learning_rate": 4.063344371191599e-06,
      "loss": 0.5258,
      "step": 45756
    },
    {
      "epoch": 1.4056154578687063,
      "grad_norm": 0.4053976833820343,
      "learning_rate": 4.062955479113586e-06,
      "loss": 0.4669,
      "step": 45757
    },
    {
      "epoch": 1.4056461770036557,
      "grad_norm": 0.42436954379081726,
      "learning_rate": 4.062566600901963e-06,
      "loss": 0.4483,
      "step": 45758
    },
    {
      "epoch": 1.4056768961386048,
      "grad_norm": 0.3970325291156769,
      "learning_rate": 4.062177736557625e-06,
      "loss": 0.4914,
      "step": 45759
    },
    {
      "epoch": 1.405707615273554,
      "grad_norm": 0.3959885239601135,
      "learning_rate": 4.061788886081492e-06,
      "loss": 0.4461,
      "step": 45760
    },
    {
      "epoch": 1.405738334408503,
      "grad_norm": 0.4822659194469452,
      "learning_rate": 4.0614000494744565e-06,
      "loss": 0.4762,
      "step": 45761
    },
    {
      "epoch": 1.4057690535434522,
      "grad_norm": 0.42864108085632324,
      "learning_rate": 4.061011226737443e-06,
      "loss": 0.579,
      "step": 45762
    },
    {
      "epoch": 1.4057997726784013,
      "grad_norm": 0.39144065976142883,
      "learning_rate": 4.0606224178713504e-06,
      "loss": 0.4473,
      "step": 45763
    },
    {
      "epoch": 1.4058304918133504,
      "grad_norm": 0.432927668094635,
      "learning_rate": 4.060233622877088e-06,
      "loss": 0.48,
      "step": 45764
    },
    {
      "epoch": 1.4058612109482997,
      "grad_norm": 0.42475733160972595,
      "learning_rate": 4.059844841755568e-06,
      "loss": 0.4506,
      "step": 45765
    },
    {
      "epoch": 1.4058919300832489,
      "grad_norm": 0.4007437229156494,
      "learning_rate": 4.059456074507689e-06,
      "loss": 0.4269,
      "step": 45766
    },
    {
      "epoch": 1.405922649218198,
      "grad_norm": 0.40256598591804504,
      "learning_rate": 4.059067321134373e-06,
      "loss": 0.4632,
      "step": 45767
    },
    {
      "epoch": 1.405953368353147,
      "grad_norm": 0.411149263381958,
      "learning_rate": 4.058678581636515e-06,
      "loss": 0.4199,
      "step": 45768
    },
    {
      "epoch": 1.4059840874880964,
      "grad_norm": 0.41096699237823486,
      "learning_rate": 4.058289856015032e-06,
      "loss": 0.5127,
      "step": 45769
    },
    {
      "epoch": 1.4060148066230456,
      "grad_norm": 0.617064893245697,
      "learning_rate": 4.057901144270825e-06,
      "loss": 0.4341,
      "step": 45770
    },
    {
      "epoch": 1.4060455257579947,
      "grad_norm": 0.45586705207824707,
      "learning_rate": 4.057512446404804e-06,
      "loss": 0.455,
      "step": 45771
    },
    {
      "epoch": 1.4060762448929438,
      "grad_norm": 0.4296788275241852,
      "learning_rate": 4.057123762417879e-06,
      "loss": 0.513,
      "step": 45772
    },
    {
      "epoch": 1.406106964027893,
      "grad_norm": 0.43340036273002625,
      "learning_rate": 4.05673509231096e-06,
      "loss": 0.4977,
      "step": 45773
    },
    {
      "epoch": 1.406137683162842,
      "grad_norm": 0.40639737248420715,
      "learning_rate": 4.0563464360849455e-06,
      "loss": 0.5081,
      "step": 45774
    },
    {
      "epoch": 1.4061684022977912,
      "grad_norm": 0.4095541834831238,
      "learning_rate": 4.055957793740751e-06,
      "loss": 0.422,
      "step": 45775
    },
    {
      "epoch": 1.4061991214327405,
      "grad_norm": 0.3969748318195343,
      "learning_rate": 4.055569165279282e-06,
      "loss": 0.5242,
      "step": 45776
    },
    {
      "epoch": 1.4062298405676896,
      "grad_norm": 0.4590819180011749,
      "learning_rate": 4.05518055070145e-06,
      "loss": 0.4445,
      "step": 45777
    },
    {
      "epoch": 1.4062605597026387,
      "grad_norm": 0.41256776452064514,
      "learning_rate": 4.054791950008155e-06,
      "loss": 0.4866,
      "step": 45778
    },
    {
      "epoch": 1.4062912788375879,
      "grad_norm": 0.41745126247406006,
      "learning_rate": 4.054403363200309e-06,
      "loss": 0.5022,
      "step": 45779
    },
    {
      "epoch": 1.4063219979725372,
      "grad_norm": 0.4067496359348297,
      "learning_rate": 4.054014790278819e-06,
      "loss": 0.4382,
      "step": 45780
    },
    {
      "epoch": 1.4063527171074863,
      "grad_norm": 0.42688310146331787,
      "learning_rate": 4.053626231244591e-06,
      "loss": 0.4911,
      "step": 45781
    },
    {
      "epoch": 1.4063834362424354,
      "grad_norm": 0.4781857132911682,
      "learning_rate": 4.053237686098541e-06,
      "loss": 0.4852,
      "step": 45782
    },
    {
      "epoch": 1.4064141553773846,
      "grad_norm": 0.42671164870262146,
      "learning_rate": 4.052849154841563e-06,
      "loss": 0.5057,
      "step": 45783
    },
    {
      "epoch": 1.4064448745123337,
      "grad_norm": 0.4191228449344635,
      "learning_rate": 4.052460637474575e-06,
      "loss": 0.5235,
      "step": 45784
    },
    {
      "epoch": 1.4064755936472828,
      "grad_norm": 0.47859445214271545,
      "learning_rate": 4.052072133998477e-06,
      "loss": 0.5121,
      "step": 45785
    },
    {
      "epoch": 1.406506312782232,
      "grad_norm": 0.44939833879470825,
      "learning_rate": 4.051683644414185e-06,
      "loss": 0.4847,
      "step": 45786
    },
    {
      "epoch": 1.4065370319171813,
      "grad_norm": 0.4864230453968048,
      "learning_rate": 4.051295168722598e-06,
      "loss": 0.4513,
      "step": 45787
    },
    {
      "epoch": 1.4065677510521304,
      "grad_norm": 0.43150410056114197,
      "learning_rate": 4.050906706924625e-06,
      "loss": 0.4866,
      "step": 45788
    },
    {
      "epoch": 1.4065984701870795,
      "grad_norm": 0.5098682641983032,
      "learning_rate": 4.0505182590211765e-06,
      "loss": 0.4968,
      "step": 45789
    },
    {
      "epoch": 1.4066291893220286,
      "grad_norm": 0.3646422028541565,
      "learning_rate": 4.050129825013162e-06,
      "loss": 0.4874,
      "step": 45790
    },
    {
      "epoch": 1.406659908456978,
      "grad_norm": 0.41802293062210083,
      "learning_rate": 4.04974140490148e-06,
      "loss": 0.4377,
      "step": 45791
    },
    {
      "epoch": 1.406690627591927,
      "grad_norm": 0.44352009892463684,
      "learning_rate": 4.049352998687046e-06,
      "loss": 0.5169,
      "step": 45792
    },
    {
      "epoch": 1.4067213467268762,
      "grad_norm": 0.4124475121498108,
      "learning_rate": 4.048964606370757e-06,
      "loss": 0.4816,
      "step": 45793
    },
    {
      "epoch": 1.4067520658618253,
      "grad_norm": 0.40660130977630615,
      "learning_rate": 4.048576227953534e-06,
      "loss": 0.3883,
      "step": 45794
    },
    {
      "epoch": 1.4067827849967744,
      "grad_norm": 0.4101111888885498,
      "learning_rate": 4.048187863436273e-06,
      "loss": 0.3806,
      "step": 45795
    },
    {
      "epoch": 1.4068135041317236,
      "grad_norm": 0.4519210457801819,
      "learning_rate": 4.0477995128198885e-06,
      "loss": 0.4456,
      "step": 45796
    },
    {
      "epoch": 1.4068442232666727,
      "grad_norm": 0.44728559255599976,
      "learning_rate": 4.0474111761052806e-06,
      "loss": 0.4848,
      "step": 45797
    },
    {
      "epoch": 1.406874942401622,
      "grad_norm": 0.4348906874656677,
      "learning_rate": 4.04702285329336e-06,
      "loss": 0.5179,
      "step": 45798
    },
    {
      "epoch": 1.4069056615365712,
      "grad_norm": 0.37711137533187866,
      "learning_rate": 4.046634544385033e-06,
      "loss": 0.468,
      "step": 45799
    },
    {
      "epoch": 1.4069363806715203,
      "grad_norm": 0.4017992913722992,
      "learning_rate": 4.046246249381206e-06,
      "loss": 0.5422,
      "step": 45800
    },
    {
      "epoch": 1.4069670998064694,
      "grad_norm": 0.40755516290664673,
      "learning_rate": 4.045857968282792e-06,
      "loss": 0.5594,
      "step": 45801
    },
    {
      "epoch": 1.4069978189414187,
      "grad_norm": 0.4024085998535156,
      "learning_rate": 4.045469701090683e-06,
      "loss": 0.4209,
      "step": 45802
    },
    {
      "epoch": 1.4070285380763679,
      "grad_norm": 0.4189704656600952,
      "learning_rate": 4.045081447805804e-06,
      "loss": 0.3904,
      "step": 45803
    },
    {
      "epoch": 1.407059257211317,
      "grad_norm": 0.4762369692325592,
      "learning_rate": 4.044693208429049e-06,
      "loss": 0.5474,
      "step": 45804
    },
    {
      "epoch": 1.407089976346266,
      "grad_norm": 0.4306035339832306,
      "learning_rate": 4.044304982961333e-06,
      "loss": 0.5478,
      "step": 45805
    },
    {
      "epoch": 1.4071206954812152,
      "grad_norm": 0.4270518124103546,
      "learning_rate": 4.043916771403556e-06,
      "loss": 0.4466,
      "step": 45806
    },
    {
      "epoch": 1.4071514146161643,
      "grad_norm": 0.4801110625267029,
      "learning_rate": 4.0435285737566254e-06,
      "loss": 0.4651,
      "step": 45807
    },
    {
      "epoch": 1.4071821337511135,
      "grad_norm": 0.4052661955356598,
      "learning_rate": 4.043140390021452e-06,
      "loss": 0.4598,
      "step": 45808
    },
    {
      "epoch": 1.4072128528860628,
      "grad_norm": 0.3816674053668976,
      "learning_rate": 4.042752220198942e-06,
      "loss": 0.4901,
      "step": 45809
    },
    {
      "epoch": 1.407243572021012,
      "grad_norm": 0.4243963956832886,
      "learning_rate": 4.0423640642899975e-06,
      "loss": 0.4942,
      "step": 45810
    },
    {
      "epoch": 1.407274291155961,
      "grad_norm": 0.4541238248348236,
      "learning_rate": 4.0419759222955265e-06,
      "loss": 0.4332,
      "step": 45811
    },
    {
      "epoch": 1.4073050102909102,
      "grad_norm": 0.3721122741699219,
      "learning_rate": 4.041587794216438e-06,
      "loss": 0.3432,
      "step": 45812
    },
    {
      "epoch": 1.4073357294258595,
      "grad_norm": 0.4015810787677765,
      "learning_rate": 4.041199680053641e-06,
      "loss": 0.457,
      "step": 45813
    },
    {
      "epoch": 1.4073664485608086,
      "grad_norm": 0.4019930958747864,
      "learning_rate": 4.040811579808035e-06,
      "loss": 0.4818,
      "step": 45814
    },
    {
      "epoch": 1.4073971676957577,
      "grad_norm": 0.4180448353290558,
      "learning_rate": 4.0404234934805284e-06,
      "loss": 0.4671,
      "step": 45815
    },
    {
      "epoch": 1.4074278868307069,
      "grad_norm": 0.4328944981098175,
      "learning_rate": 4.040035421072031e-06,
      "loss": 0.4769,
      "step": 45816
    },
    {
      "epoch": 1.407458605965656,
      "grad_norm": 0.424394816160202,
      "learning_rate": 4.0396473625834455e-06,
      "loss": 0.5076,
      "step": 45817
    },
    {
      "epoch": 1.407489325100605,
      "grad_norm": 0.4310714304447174,
      "learning_rate": 4.039259318015683e-06,
      "loss": 0.4232,
      "step": 45818
    },
    {
      "epoch": 1.4075200442355542,
      "grad_norm": 0.4552890658378601,
      "learning_rate": 4.0388712873696445e-06,
      "loss": 0.5232,
      "step": 45819
    },
    {
      "epoch": 1.4075507633705036,
      "grad_norm": 0.46249887347221375,
      "learning_rate": 4.038483270646237e-06,
      "loss": 0.4233,
      "step": 45820
    },
    {
      "epoch": 1.4075814825054527,
      "grad_norm": 0.3820855915546417,
      "learning_rate": 4.03809526784637e-06,
      "loss": 0.4185,
      "step": 45821
    },
    {
      "epoch": 1.4076122016404018,
      "grad_norm": 0.4406813979148865,
      "learning_rate": 4.03770727897095e-06,
      "loss": 0.4725,
      "step": 45822
    },
    {
      "epoch": 1.407642920775351,
      "grad_norm": 0.41385748982429504,
      "learning_rate": 4.037319304020878e-06,
      "loss": 0.4361,
      "step": 45823
    },
    {
      "epoch": 1.4076736399103003,
      "grad_norm": 0.38679349422454834,
      "learning_rate": 4.0369313429970635e-06,
      "loss": 0.5139,
      "step": 45824
    },
    {
      "epoch": 1.4077043590452494,
      "grad_norm": 0.4183940589427948,
      "learning_rate": 4.0365433959004115e-06,
      "loss": 0.4721,
      "step": 45825
    },
    {
      "epoch": 1.4077350781801985,
      "grad_norm": 0.4349810779094696,
      "learning_rate": 4.036155462731833e-06,
      "loss": 0.4751,
      "step": 45826
    },
    {
      "epoch": 1.4077657973151476,
      "grad_norm": 0.38959306478500366,
      "learning_rate": 4.035767543492226e-06,
      "loss": 0.4382,
      "step": 45827
    },
    {
      "epoch": 1.4077965164500967,
      "grad_norm": 0.40225890278816223,
      "learning_rate": 4.035379638182505e-06,
      "loss": 0.5003,
      "step": 45828
    },
    {
      "epoch": 1.4078272355850459,
      "grad_norm": 0.4693264961242676,
      "learning_rate": 4.034991746803564e-06,
      "loss": 0.4732,
      "step": 45829
    },
    {
      "epoch": 1.407857954719995,
      "grad_norm": 0.3733694553375244,
      "learning_rate": 4.034603869356323e-06,
      "loss": 0.4782,
      "step": 45830
    },
    {
      "epoch": 1.4078886738549443,
      "grad_norm": 0.4396485388278961,
      "learning_rate": 4.034216005841677e-06,
      "loss": 0.5902,
      "step": 45831
    },
    {
      "epoch": 1.4079193929898934,
      "grad_norm": 0.3900510370731354,
      "learning_rate": 4.033828156260541e-06,
      "loss": 0.4951,
      "step": 45832
    },
    {
      "epoch": 1.4079501121248426,
      "grad_norm": 0.42066338658332825,
      "learning_rate": 4.033440320613812e-06,
      "loss": 0.4456,
      "step": 45833
    },
    {
      "epoch": 1.4079808312597917,
      "grad_norm": 0.4653756022453308,
      "learning_rate": 4.033052498902399e-06,
      "loss": 0.4732,
      "step": 45834
    },
    {
      "epoch": 1.408011550394741,
      "grad_norm": 0.38390111923217773,
      "learning_rate": 4.032664691127209e-06,
      "loss": 0.3842,
      "step": 45835
    },
    {
      "epoch": 1.4080422695296901,
      "grad_norm": 0.4226481318473816,
      "learning_rate": 4.032276897289148e-06,
      "loss": 0.4224,
      "step": 45836
    },
    {
      "epoch": 1.4080729886646393,
      "grad_norm": 0.45885300636291504,
      "learning_rate": 4.031889117389125e-06,
      "loss": 0.4542,
      "step": 45837
    },
    {
      "epoch": 1.4081037077995884,
      "grad_norm": 0.4160328209400177,
      "learning_rate": 4.031501351428038e-06,
      "loss": 0.4394,
      "step": 45838
    },
    {
      "epoch": 1.4081344269345375,
      "grad_norm": 0.42025870084762573,
      "learning_rate": 4.031113599406795e-06,
      "loss": 0.4844,
      "step": 45839
    },
    {
      "epoch": 1.4081651460694866,
      "grad_norm": 0.41892319917678833,
      "learning_rate": 4.030725861326304e-06,
      "loss": 0.4649,
      "step": 45840
    },
    {
      "epoch": 1.4081958652044357,
      "grad_norm": 0.4153020679950714,
      "learning_rate": 4.030338137187474e-06,
      "loss": 0.4647,
      "step": 45841
    },
    {
      "epoch": 1.408226584339385,
      "grad_norm": 0.43372488021850586,
      "learning_rate": 4.029950426991201e-06,
      "loss": 0.4723,
      "step": 45842
    },
    {
      "epoch": 1.4082573034743342,
      "grad_norm": 0.40007326006889343,
      "learning_rate": 4.029562730738398e-06,
      "loss": 0.462,
      "step": 45843
    },
    {
      "epoch": 1.4082880226092833,
      "grad_norm": 0.423128217458725,
      "learning_rate": 4.029175048429966e-06,
      "loss": 0.4278,
      "step": 45844
    },
    {
      "epoch": 1.4083187417442324,
      "grad_norm": 0.3659091293811798,
      "learning_rate": 4.028787380066817e-06,
      "loss": 0.4292,
      "step": 45845
    },
    {
      "epoch": 1.4083494608791818,
      "grad_norm": 0.41577833890914917,
      "learning_rate": 4.028399725649849e-06,
      "loss": 0.4555,
      "step": 45846
    },
    {
      "epoch": 1.408380180014131,
      "grad_norm": 0.45462462306022644,
      "learning_rate": 4.02801208517997e-06,
      "loss": 0.5355,
      "step": 45847
    },
    {
      "epoch": 1.40841089914908,
      "grad_norm": 0.44072070717811584,
      "learning_rate": 4.027624458658086e-06,
      "loss": 0.445,
      "step": 45848
    },
    {
      "epoch": 1.4084416182840291,
      "grad_norm": 0.48283588886260986,
      "learning_rate": 4.027236846085107e-06,
      "loss": 0.4411,
      "step": 45849
    },
    {
      "epoch": 1.4084723374189783,
      "grad_norm": 0.45128679275512695,
      "learning_rate": 4.026849247461927e-06,
      "loss": 0.4635,
      "step": 45850
    },
    {
      "epoch": 1.4085030565539274,
      "grad_norm": 0.39416858553886414,
      "learning_rate": 4.0264616627894605e-06,
      "loss": 0.4311,
      "step": 45851
    },
    {
      "epoch": 1.4085337756888765,
      "grad_norm": 0.39579150080680847,
      "learning_rate": 4.026074092068608e-06,
      "loss": 0.3954,
      "step": 45852
    },
    {
      "epoch": 1.4085644948238258,
      "grad_norm": 0.4142250716686249,
      "learning_rate": 4.025686535300282e-06,
      "loss": 0.525,
      "step": 45853
    },
    {
      "epoch": 1.408595213958775,
      "grad_norm": 0.4081672430038452,
      "learning_rate": 4.025298992485377e-06,
      "loss": 0.5014,
      "step": 45854
    },
    {
      "epoch": 1.408625933093724,
      "grad_norm": 0.6512444615364075,
      "learning_rate": 4.0249114636248045e-06,
      "loss": 0.426,
      "step": 45855
    },
    {
      "epoch": 1.4086566522286732,
      "grad_norm": 0.4602251648902893,
      "learning_rate": 4.024523948719468e-06,
      "loss": 0.4754,
      "step": 45856
    },
    {
      "epoch": 1.4086873713636223,
      "grad_norm": 0.3955979645252228,
      "learning_rate": 4.024136447770274e-06,
      "loss": 0.4499,
      "step": 45857
    },
    {
      "epoch": 1.4087180904985717,
      "grad_norm": 0.41042637825012207,
      "learning_rate": 4.02374896077813e-06,
      "loss": 0.4486,
      "step": 45858
    },
    {
      "epoch": 1.4087488096335208,
      "grad_norm": 0.43156591057777405,
      "learning_rate": 4.023361487743934e-06,
      "loss": 0.5103,
      "step": 45859
    },
    {
      "epoch": 1.40877952876847,
      "grad_norm": 0.37652072310447693,
      "learning_rate": 4.022974028668598e-06,
      "loss": 0.4892,
      "step": 45860
    },
    {
      "epoch": 1.408810247903419,
      "grad_norm": 0.46253928542137146,
      "learning_rate": 4.022586583553016e-06,
      "loss": 0.6873,
      "step": 45861
    },
    {
      "epoch": 1.4088409670383681,
      "grad_norm": 0.4721531271934509,
      "learning_rate": 4.0221991523981086e-06,
      "loss": 0.4807,
      "step": 45862
    },
    {
      "epoch": 1.4088716861733173,
      "grad_norm": 0.385692298412323,
      "learning_rate": 4.021811735204768e-06,
      "loss": 0.4325,
      "step": 45863
    },
    {
      "epoch": 1.4089024053082664,
      "grad_norm": 0.4311946928501129,
      "learning_rate": 4.021424331973909e-06,
      "loss": 0.4529,
      "step": 45864
    },
    {
      "epoch": 1.4089331244432157,
      "grad_norm": 0.42074525356292725,
      "learning_rate": 4.021036942706423e-06,
      "loss": 0.5444,
      "step": 45865
    },
    {
      "epoch": 1.4089638435781648,
      "grad_norm": 0.6252686381340027,
      "learning_rate": 4.020649567403228e-06,
      "loss": 0.3925,
      "step": 45866
    },
    {
      "epoch": 1.408994562713114,
      "grad_norm": 0.676672637462616,
      "learning_rate": 4.020262206065222e-06,
      "loss": 0.4177,
      "step": 45867
    },
    {
      "epoch": 1.409025281848063,
      "grad_norm": 0.39106160402297974,
      "learning_rate": 4.0198748586933146e-06,
      "loss": 0.4658,
      "step": 45868
    },
    {
      "epoch": 1.4090560009830124,
      "grad_norm": 0.40902242064476013,
      "learning_rate": 4.0194875252884035e-06,
      "loss": 0.495,
      "step": 45869
    },
    {
      "epoch": 1.4090867201179615,
      "grad_norm": 0.49494749307632446,
      "learning_rate": 4.019100205851396e-06,
      "loss": 0.493,
      "step": 45870
    },
    {
      "epoch": 1.4091174392529107,
      "grad_norm": 0.41489025950431824,
      "learning_rate": 4.018712900383199e-06,
      "loss": 0.5042,
      "step": 45871
    },
    {
      "epoch": 1.4091481583878598,
      "grad_norm": 0.44770050048828125,
      "learning_rate": 4.018325608884715e-06,
      "loss": 0.4971,
      "step": 45872
    },
    {
      "epoch": 1.409178877522809,
      "grad_norm": 0.4274056553840637,
      "learning_rate": 4.017938331356853e-06,
      "loss": 0.4662,
      "step": 45873
    },
    {
      "epoch": 1.409209596657758,
      "grad_norm": 0.430623322725296,
      "learning_rate": 4.0175510678005104e-06,
      "loss": 0.4653,
      "step": 45874
    },
    {
      "epoch": 1.4092403157927071,
      "grad_norm": 0.4764498770236969,
      "learning_rate": 4.017163818216595e-06,
      "loss": 0.4556,
      "step": 45875
    },
    {
      "epoch": 1.4092710349276565,
      "grad_norm": 0.44253912568092346,
      "learning_rate": 4.016776582606012e-06,
      "loss": 0.5364,
      "step": 45876
    },
    {
      "epoch": 1.4093017540626056,
      "grad_norm": 0.4579228460788727,
      "learning_rate": 4.016389360969667e-06,
      "loss": 0.4569,
      "step": 45877
    },
    {
      "epoch": 1.4093324731975547,
      "grad_norm": 0.40399014949798584,
      "learning_rate": 4.0160021533084604e-06,
      "loss": 0.4444,
      "step": 45878
    },
    {
      "epoch": 1.4093631923325038,
      "grad_norm": 0.4540103077888489,
      "learning_rate": 4.015614959623298e-06,
      "loss": 0.511,
      "step": 45879
    },
    {
      "epoch": 1.4093939114674532,
      "grad_norm": 0.3911934792995453,
      "learning_rate": 4.0152277799150855e-06,
      "loss": 0.4837,
      "step": 45880
    },
    {
      "epoch": 1.4094246306024023,
      "grad_norm": 0.4074738323688507,
      "learning_rate": 4.01484061418473e-06,
      "loss": 0.4794,
      "step": 45881
    },
    {
      "epoch": 1.4094553497373514,
      "grad_norm": 0.40928077697753906,
      "learning_rate": 4.014453462433128e-06,
      "loss": 0.4575,
      "step": 45882
    },
    {
      "epoch": 1.4094860688723005,
      "grad_norm": 0.46752721071243286,
      "learning_rate": 4.014066324661188e-06,
      "loss": 0.5397,
      "step": 45883
    },
    {
      "epoch": 1.4095167880072497,
      "grad_norm": 0.44146543741226196,
      "learning_rate": 4.013679200869814e-06,
      "loss": 0.4791,
      "step": 45884
    },
    {
      "epoch": 1.4095475071421988,
      "grad_norm": 0.3971022963523865,
      "learning_rate": 4.013292091059915e-06,
      "loss": 0.4785,
      "step": 45885
    },
    {
      "epoch": 1.409578226277148,
      "grad_norm": 0.4056672751903534,
      "learning_rate": 4.012904995232386e-06,
      "loss": 0.466,
      "step": 45886
    },
    {
      "epoch": 1.4096089454120972,
      "grad_norm": 0.4476834535598755,
      "learning_rate": 4.012517913388135e-06,
      "loss": 0.5007,
      "step": 45887
    },
    {
      "epoch": 1.4096396645470464,
      "grad_norm": 0.44531238079071045,
      "learning_rate": 4.0121308455280675e-06,
      "loss": 0.5537,
      "step": 45888
    },
    {
      "epoch": 1.4096703836819955,
      "grad_norm": 0.44011950492858887,
      "learning_rate": 4.01174379165309e-06,
      "loss": 0.4269,
      "step": 45889
    },
    {
      "epoch": 1.4097011028169446,
      "grad_norm": 0.4974718987941742,
      "learning_rate": 4.0113567517641e-06,
      "loss": 0.463,
      "step": 45890
    },
    {
      "epoch": 1.409731821951894,
      "grad_norm": 0.3743056058883667,
      "learning_rate": 4.010969725862004e-06,
      "loss": 0.4821,
      "step": 45891
    },
    {
      "epoch": 1.409762541086843,
      "grad_norm": 0.3991503119468689,
      "learning_rate": 4.010582713947706e-06,
      "loss": 0.4768,
      "step": 45892
    },
    {
      "epoch": 1.4097932602217922,
      "grad_norm": 0.41338810324668884,
      "learning_rate": 4.01019571602211e-06,
      "loss": 0.5183,
      "step": 45893
    },
    {
      "epoch": 1.4098239793567413,
      "grad_norm": 0.38387927412986755,
      "learning_rate": 4.0098087320861255e-06,
      "loss": 0.4792,
      "step": 45894
    },
    {
      "epoch": 1.4098546984916904,
      "grad_norm": 0.42656680941581726,
      "learning_rate": 4.0094217621406465e-06,
      "loss": 0.4561,
      "step": 45895
    },
    {
      "epoch": 1.4098854176266395,
      "grad_norm": 0.42668259143829346,
      "learning_rate": 4.009034806186585e-06,
      "loss": 0.4997,
      "step": 45896
    },
    {
      "epoch": 1.4099161367615887,
      "grad_norm": 0.4645039439201355,
      "learning_rate": 4.008647864224834e-06,
      "loss": 0.4845,
      "step": 45897
    },
    {
      "epoch": 1.409946855896538,
      "grad_norm": 0.40306007862091064,
      "learning_rate": 4.008260936256312e-06,
      "loss": 0.5077,
      "step": 45898
    },
    {
      "epoch": 1.4099775750314871,
      "grad_norm": 0.4169909358024597,
      "learning_rate": 4.0078740222819106e-06,
      "loss": 0.4347,
      "step": 45899
    },
    {
      "epoch": 1.4100082941664362,
      "grad_norm": 0.46914738416671753,
      "learning_rate": 4.007487122302541e-06,
      "loss": 0.4372,
      "step": 45900
    },
    {
      "epoch": 1.4100390133013854,
      "grad_norm": 0.409559428691864,
      "learning_rate": 4.007100236319102e-06,
      "loss": 0.4608,
      "step": 45901
    },
    {
      "epoch": 1.4100697324363347,
      "grad_norm": 0.4169743061065674,
      "learning_rate": 4.006713364332498e-06,
      "loss": 0.454,
      "step": 45902
    },
    {
      "epoch": 1.4101004515712838,
      "grad_norm": 0.49158769845962524,
      "learning_rate": 4.006326506343633e-06,
      "loss": 0.5032,
      "step": 45903
    },
    {
      "epoch": 1.410131170706233,
      "grad_norm": 0.37363430857658386,
      "learning_rate": 4.005939662353415e-06,
      "loss": 0.3944,
      "step": 45904
    },
    {
      "epoch": 1.410161889841182,
      "grad_norm": 0.43926116824150085,
      "learning_rate": 4.00555283236274e-06,
      "loss": 0.5135,
      "step": 45905
    },
    {
      "epoch": 1.4101926089761312,
      "grad_norm": 0.4251594841480255,
      "learning_rate": 4.0051660163725155e-06,
      "loss": 0.475,
      "step": 45906
    },
    {
      "epoch": 1.4102233281110803,
      "grad_norm": 0.45159393548965454,
      "learning_rate": 4.004779214383644e-06,
      "loss": 0.5569,
      "step": 45907
    },
    {
      "epoch": 1.4102540472460294,
      "grad_norm": 0.5036372542381287,
      "learning_rate": 4.004392426397033e-06,
      "loss": 0.4592,
      "step": 45908
    },
    {
      "epoch": 1.4102847663809788,
      "grad_norm": 0.43978646397590637,
      "learning_rate": 4.004005652413578e-06,
      "loss": 0.3979,
      "step": 45909
    },
    {
      "epoch": 1.410315485515928,
      "grad_norm": 0.4435279369354248,
      "learning_rate": 4.003618892434188e-06,
      "loss": 0.5203,
      "step": 45910
    },
    {
      "epoch": 1.410346204650877,
      "grad_norm": 0.4316015839576721,
      "learning_rate": 4.003232146459763e-06,
      "loss": 0.4871,
      "step": 45911
    },
    {
      "epoch": 1.4103769237858261,
      "grad_norm": 0.4425209164619446,
      "learning_rate": 4.00284541449121e-06,
      "loss": 0.4821,
      "step": 45912
    },
    {
      "epoch": 1.4104076429207755,
      "grad_norm": 0.4119817912578583,
      "learning_rate": 4.002458696529432e-06,
      "loss": 0.5265,
      "step": 45913
    },
    {
      "epoch": 1.4104383620557246,
      "grad_norm": 0.3937318027019501,
      "learning_rate": 4.002071992575328e-06,
      "loss": 0.473,
      "step": 45914
    },
    {
      "epoch": 1.4104690811906737,
      "grad_norm": 0.43604084849357605,
      "learning_rate": 4.001685302629804e-06,
      "loss": 0.4965,
      "step": 45915
    },
    {
      "epoch": 1.4104998003256228,
      "grad_norm": 0.4202836751937866,
      "learning_rate": 4.001298626693764e-06,
      "loss": 0.51,
      "step": 45916
    },
    {
      "epoch": 1.410530519460572,
      "grad_norm": 0.3991776406764984,
      "learning_rate": 4.000911964768111e-06,
      "loss": 0.4461,
      "step": 45917
    },
    {
      "epoch": 1.410561238595521,
      "grad_norm": 0.3752760589122772,
      "learning_rate": 4.000525316853745e-06,
      "loss": 0.4093,
      "step": 45918
    },
    {
      "epoch": 1.4105919577304702,
      "grad_norm": 0.42403948307037354,
      "learning_rate": 4.000138682951571e-06,
      "loss": 0.4561,
      "step": 45919
    },
    {
      "epoch": 1.4106226768654195,
      "grad_norm": 0.4401933252811432,
      "learning_rate": 3.999752063062492e-06,
      "loss": 0.4363,
      "step": 45920
    },
    {
      "epoch": 1.4106533960003687,
      "grad_norm": 0.447709858417511,
      "learning_rate": 3.999365457187415e-06,
      "loss": 0.4602,
      "step": 45921
    },
    {
      "epoch": 1.4106841151353178,
      "grad_norm": 0.4030444324016571,
      "learning_rate": 3.998978865327235e-06,
      "loss": 0.4488,
      "step": 45922
    },
    {
      "epoch": 1.410714834270267,
      "grad_norm": 0.4165297746658325,
      "learning_rate": 3.998592287482863e-06,
      "loss": 0.4619,
      "step": 45923
    },
    {
      "epoch": 1.4107455534052162,
      "grad_norm": 0.44516995549201965,
      "learning_rate": 3.99820572365519e-06,
      "loss": 0.5332,
      "step": 45924
    },
    {
      "epoch": 1.4107762725401654,
      "grad_norm": 0.3965561091899872,
      "learning_rate": 3.997819173845135e-06,
      "loss": 0.4553,
      "step": 45925
    },
    {
      "epoch": 1.4108069916751145,
      "grad_norm": 0.7151824235916138,
      "learning_rate": 3.997432638053588e-06,
      "loss": 0.5227,
      "step": 45926
    },
    {
      "epoch": 1.4108377108100636,
      "grad_norm": 0.4270603060722351,
      "learning_rate": 3.9970461162814555e-06,
      "loss": 0.493,
      "step": 45927
    },
    {
      "epoch": 1.4108684299450127,
      "grad_norm": 0.9625473022460938,
      "learning_rate": 3.996659608529643e-06,
      "loss": 0.4153,
      "step": 45928
    },
    {
      "epoch": 1.4108991490799618,
      "grad_norm": 0.4143114686012268,
      "learning_rate": 3.99627311479905e-06,
      "loss": 0.4652,
      "step": 45929
    },
    {
      "epoch": 1.410929868214911,
      "grad_norm": 0.4493677020072937,
      "learning_rate": 3.995886635090584e-06,
      "loss": 0.4862,
      "step": 45930
    },
    {
      "epoch": 1.4109605873498603,
      "grad_norm": 0.4234280586242676,
      "learning_rate": 3.995500169405141e-06,
      "loss": 0.4568,
      "step": 45931
    },
    {
      "epoch": 1.4109913064848094,
      "grad_norm": 0.443593829870224,
      "learning_rate": 3.99511371774363e-06,
      "loss": 0.5019,
      "step": 45932
    },
    {
      "epoch": 1.4110220256197585,
      "grad_norm": 0.941631555557251,
      "learning_rate": 3.994727280106944e-06,
      "loss": 0.4862,
      "step": 45933
    },
    {
      "epoch": 1.4110527447547077,
      "grad_norm": 0.42173343896865845,
      "learning_rate": 3.994340856495997e-06,
      "loss": 0.4342,
      "step": 45934
    },
    {
      "epoch": 1.411083463889657,
      "grad_norm": 0.4223341941833496,
      "learning_rate": 3.993954446911684e-06,
      "loss": 0.4716,
      "step": 45935
    },
    {
      "epoch": 1.4111141830246061,
      "grad_norm": 0.4455968737602234,
      "learning_rate": 3.993568051354913e-06,
      "loss": 0.4865,
      "step": 45936
    },
    {
      "epoch": 1.4111449021595552,
      "grad_norm": 0.472832053899765,
      "learning_rate": 3.993181669826581e-06,
      "loss": 0.4879,
      "step": 45937
    },
    {
      "epoch": 1.4111756212945044,
      "grad_norm": 0.43096640706062317,
      "learning_rate": 3.992795302327592e-06,
      "loss": 0.4892,
      "step": 45938
    },
    {
      "epoch": 1.4112063404294535,
      "grad_norm": 0.42483726143836975,
      "learning_rate": 3.992408948858849e-06,
      "loss": 0.5163,
      "step": 45939
    },
    {
      "epoch": 1.4112370595644026,
      "grad_norm": 0.42537951469421387,
      "learning_rate": 3.992022609421258e-06,
      "loss": 0.4725,
      "step": 45940
    },
    {
      "epoch": 1.4112677786993517,
      "grad_norm": 0.43104228377342224,
      "learning_rate": 3.991636284015714e-06,
      "loss": 0.4856,
      "step": 45941
    },
    {
      "epoch": 1.411298497834301,
      "grad_norm": 0.385147362947464,
      "learning_rate": 3.991249972643123e-06,
      "loss": 0.4941,
      "step": 45942
    },
    {
      "epoch": 1.4113292169692502,
      "grad_norm": 0.4164043366909027,
      "learning_rate": 3.990863675304389e-06,
      "loss": 0.4852,
      "step": 45943
    },
    {
      "epoch": 1.4113599361041993,
      "grad_norm": 0.3886888921260834,
      "learning_rate": 3.990477392000414e-06,
      "loss": 0.4579,
      "step": 45944
    },
    {
      "epoch": 1.4113906552391484,
      "grad_norm": 0.3748985528945923,
      "learning_rate": 3.9900911227320956e-06,
      "loss": 0.4214,
      "step": 45945
    },
    {
      "epoch": 1.4114213743740978,
      "grad_norm": 0.4035336971282959,
      "learning_rate": 3.989704867500339e-06,
      "loss": 0.4866,
      "step": 45946
    },
    {
      "epoch": 1.4114520935090469,
      "grad_norm": 0.40557053685188293,
      "learning_rate": 3.989318626306048e-06,
      "loss": 0.493,
      "step": 45947
    },
    {
      "epoch": 1.411482812643996,
      "grad_norm": 0.4489428997039795,
      "learning_rate": 3.988932399150122e-06,
      "loss": 0.407,
      "step": 45948
    },
    {
      "epoch": 1.4115135317789451,
      "grad_norm": 0.4419998228549957,
      "learning_rate": 3.988546186033468e-06,
      "loss": 0.5052,
      "step": 45949
    },
    {
      "epoch": 1.4115442509138942,
      "grad_norm": 0.42238983511924744,
      "learning_rate": 3.98815998695698e-06,
      "loss": 0.4666,
      "step": 45950
    },
    {
      "epoch": 1.4115749700488434,
      "grad_norm": 0.4353596866130829,
      "learning_rate": 3.987773801921564e-06,
      "loss": 0.4695,
      "step": 45951
    },
    {
      "epoch": 1.4116056891837925,
      "grad_norm": 0.44311171770095825,
      "learning_rate": 3.987387630928123e-06,
      "loss": 0.5138,
      "step": 45952
    },
    {
      "epoch": 1.4116364083187418,
      "grad_norm": 0.40873828530311584,
      "learning_rate": 3.987001473977562e-06,
      "loss": 0.416,
      "step": 45953
    },
    {
      "epoch": 1.411667127453691,
      "grad_norm": 0.3994824290275574,
      "learning_rate": 3.986615331070775e-06,
      "loss": 0.41,
      "step": 45954
    },
    {
      "epoch": 1.41169784658864,
      "grad_norm": 0.4042426645755768,
      "learning_rate": 3.9862292022086665e-06,
      "loss": 0.4038,
      "step": 45955
    },
    {
      "epoch": 1.4117285657235892,
      "grad_norm": 0.45823875069618225,
      "learning_rate": 3.985843087392142e-06,
      "loss": 0.4539,
      "step": 45956
    },
    {
      "epoch": 1.4117592848585385,
      "grad_norm": 0.40669047832489014,
      "learning_rate": 3.985456986622104e-06,
      "loss": 0.4714,
      "step": 45957
    },
    {
      "epoch": 1.4117900039934876,
      "grad_norm": 0.6573594808578491,
      "learning_rate": 3.985070899899447e-06,
      "loss": 0.4486,
      "step": 45958
    },
    {
      "epoch": 1.4118207231284368,
      "grad_norm": 0.414140522480011,
      "learning_rate": 3.984684827225081e-06,
      "loss": 0.4674,
      "step": 45959
    },
    {
      "epoch": 1.4118514422633859,
      "grad_norm": 0.447595477104187,
      "learning_rate": 3.984298768599896e-06,
      "loss": 0.5466,
      "step": 45960
    },
    {
      "epoch": 1.411882161398335,
      "grad_norm": 0.4390259385108948,
      "learning_rate": 3.983912724024809e-06,
      "loss": 0.4804,
      "step": 45961
    },
    {
      "epoch": 1.4119128805332841,
      "grad_norm": 0.4571128785610199,
      "learning_rate": 3.98352669350071e-06,
      "loss": 0.5402,
      "step": 45962
    },
    {
      "epoch": 1.4119435996682332,
      "grad_norm": 0.48667943477630615,
      "learning_rate": 3.9831406770285045e-06,
      "loss": 0.3917,
      "step": 45963
    },
    {
      "epoch": 1.4119743188031826,
      "grad_norm": 0.4856230616569519,
      "learning_rate": 3.982754674609099e-06,
      "loss": 0.4436,
      "step": 45964
    },
    {
      "epoch": 1.4120050379381317,
      "grad_norm": 0.4182497560977936,
      "learning_rate": 3.982368686243382e-06,
      "loss": 0.5245,
      "step": 45965
    },
    {
      "epoch": 1.4120357570730808,
      "grad_norm": 0.3876281976699829,
      "learning_rate": 3.98198271193227e-06,
      "loss": 0.4168,
      "step": 45966
    },
    {
      "epoch": 1.41206647620803,
      "grad_norm": 0.4069983661174774,
      "learning_rate": 3.981596751676654e-06,
      "loss": 0.4539,
      "step": 45967
    },
    {
      "epoch": 1.412097195342979,
      "grad_norm": 0.41040533781051636,
      "learning_rate": 3.981210805477443e-06,
      "loss": 0.4327,
      "step": 45968
    },
    {
      "epoch": 1.4121279144779284,
      "grad_norm": 0.43141892552375793,
      "learning_rate": 3.980824873335528e-06,
      "loss": 0.4969,
      "step": 45969
    },
    {
      "epoch": 1.4121586336128775,
      "grad_norm": 0.4114454984664917,
      "learning_rate": 3.980438955251824e-06,
      "loss": 0.5258,
      "step": 45970
    },
    {
      "epoch": 1.4121893527478266,
      "grad_norm": 0.4670497179031372,
      "learning_rate": 3.980053051227222e-06,
      "loss": 0.4578,
      "step": 45971
    },
    {
      "epoch": 1.4122200718827758,
      "grad_norm": 0.44442108273506165,
      "learning_rate": 3.979667161262629e-06,
      "loss": 0.4823,
      "step": 45972
    },
    {
      "epoch": 1.4122507910177249,
      "grad_norm": 0.41711661219596863,
      "learning_rate": 3.97928128535894e-06,
      "loss": 0.5055,
      "step": 45973
    },
    {
      "epoch": 1.412281510152674,
      "grad_norm": 0.5333224534988403,
      "learning_rate": 3.97889542351706e-06,
      "loss": 0.4662,
      "step": 45974
    },
    {
      "epoch": 1.4123122292876231,
      "grad_norm": 0.4015578627586365,
      "learning_rate": 3.9785095757378925e-06,
      "loss": 0.4841,
      "step": 45975
    },
    {
      "epoch": 1.4123429484225725,
      "grad_norm": 0.39545518159866333,
      "learning_rate": 3.978123742022339e-06,
      "loss": 0.4404,
      "step": 45976
    },
    {
      "epoch": 1.4123736675575216,
      "grad_norm": 0.3788611590862274,
      "learning_rate": 3.977737922371293e-06,
      "loss": 0.3801,
      "step": 45977
    },
    {
      "epoch": 1.4124043866924707,
      "grad_norm": 0.42958542704582214,
      "learning_rate": 3.977352116785661e-06,
      "loss": 0.5137,
      "step": 45978
    },
    {
      "epoch": 1.4124351058274198,
      "grad_norm": 0.4218950867652893,
      "learning_rate": 3.976966325266345e-06,
      "loss": 0.4039,
      "step": 45979
    },
    {
      "epoch": 1.4124658249623692,
      "grad_norm": 0.4259354770183563,
      "learning_rate": 3.976580547814247e-06,
      "loss": 0.5048,
      "step": 45980
    },
    {
      "epoch": 1.4124965440973183,
      "grad_norm": 0.41156166791915894,
      "learning_rate": 3.976194784430263e-06,
      "loss": 0.5015,
      "step": 45981
    },
    {
      "epoch": 1.4125272632322674,
      "grad_norm": 0.43915045261383057,
      "learning_rate": 3.975809035115296e-06,
      "loss": 0.4693,
      "step": 45982
    },
    {
      "epoch": 1.4125579823672165,
      "grad_norm": 0.4948035478591919,
      "learning_rate": 3.975423299870249e-06,
      "loss": 0.4841,
      "step": 45983
    },
    {
      "epoch": 1.4125887015021656,
      "grad_norm": 0.4373203217983246,
      "learning_rate": 3.975037578696021e-06,
      "loss": 0.4101,
      "step": 45984
    },
    {
      "epoch": 1.4126194206371148,
      "grad_norm": 0.44529327750205994,
      "learning_rate": 3.9746518715935175e-06,
      "loss": 0.4777,
      "step": 45985
    },
    {
      "epoch": 1.4126501397720639,
      "grad_norm": 0.46908044815063477,
      "learning_rate": 3.974266178563632e-06,
      "loss": 0.421,
      "step": 45986
    },
    {
      "epoch": 1.4126808589070132,
      "grad_norm": 0.43443816900253296,
      "learning_rate": 3.973880499607267e-06,
      "loss": 0.4836,
      "step": 45987
    },
    {
      "epoch": 1.4127115780419623,
      "grad_norm": 0.4136560559272766,
      "learning_rate": 3.973494834725327e-06,
      "loss": 0.4543,
      "step": 45988
    },
    {
      "epoch": 1.4127422971769115,
      "grad_norm": 0.40486863255500793,
      "learning_rate": 3.973109183918713e-06,
      "loss": 0.4515,
      "step": 45989
    },
    {
      "epoch": 1.4127730163118606,
      "grad_norm": 0.41181790828704834,
      "learning_rate": 3.972723547188321e-06,
      "loss": 0.5331,
      "step": 45990
    },
    {
      "epoch": 1.41280373544681,
      "grad_norm": 0.468580037355423,
      "learning_rate": 3.972337924535052e-06,
      "loss": 0.4868,
      "step": 45991
    },
    {
      "epoch": 1.412834454581759,
      "grad_norm": 0.4169375002384186,
      "learning_rate": 3.9719523159598105e-06,
      "loss": 0.5075,
      "step": 45992
    },
    {
      "epoch": 1.4128651737167082,
      "grad_norm": 0.3733978271484375,
      "learning_rate": 3.971566721463499e-06,
      "loss": 0.4567,
      "step": 45993
    },
    {
      "epoch": 1.4128958928516573,
      "grad_norm": 0.4095837473869324,
      "learning_rate": 3.971181141047011e-06,
      "loss": 0.5638,
      "step": 45994
    },
    {
      "epoch": 1.4129266119866064,
      "grad_norm": 0.39283841848373413,
      "learning_rate": 3.970795574711252e-06,
      "loss": 0.4061,
      "step": 45995
    },
    {
      "epoch": 1.4129573311215555,
      "grad_norm": 0.4683802127838135,
      "learning_rate": 3.970410022457115e-06,
      "loss": 0.4485,
      "step": 45996
    },
    {
      "epoch": 1.4129880502565046,
      "grad_norm": 0.4373203217983246,
      "learning_rate": 3.970024484285514e-06,
      "loss": 0.4738,
      "step": 45997
    },
    {
      "epoch": 1.413018769391454,
      "grad_norm": 0.3962516784667969,
      "learning_rate": 3.969638960197338e-06,
      "loss": 0.4673,
      "step": 45998
    },
    {
      "epoch": 1.413049488526403,
      "grad_norm": 0.42966359853744507,
      "learning_rate": 3.969253450193495e-06,
      "loss": 0.4279,
      "step": 45999
    },
    {
      "epoch": 1.4130802076613522,
      "grad_norm": 0.4798227548599243,
      "learning_rate": 3.968867954274879e-06,
      "loss": 0.4408,
      "step": 46000
    },
    {
      "epoch": 1.4131109267963013,
      "grad_norm": 0.4718282222747803,
      "learning_rate": 3.9684824724423885e-06,
      "loss": 0.5073,
      "step": 46001
    },
    {
      "epoch": 1.4131416459312507,
      "grad_norm": 0.4224676191806793,
      "learning_rate": 3.968097004696937e-06,
      "loss": 0.4689,
      "step": 46002
    },
    {
      "epoch": 1.4131723650661998,
      "grad_norm": 0.3968919515609741,
      "learning_rate": 3.967711551039412e-06,
      "loss": 0.4373,
      "step": 46003
    },
    {
      "epoch": 1.413203084201149,
      "grad_norm": 0.5068076848983765,
      "learning_rate": 3.96732611147072e-06,
      "loss": 0.5067,
      "step": 46004
    },
    {
      "epoch": 1.413233803336098,
      "grad_norm": 0.4993228316307068,
      "learning_rate": 3.966940685991757e-06,
      "loss": 0.4372,
      "step": 46005
    },
    {
      "epoch": 1.4132645224710472,
      "grad_norm": 0.4514293372631073,
      "learning_rate": 3.966555274603425e-06,
      "loss": 0.4361,
      "step": 46006
    },
    {
      "epoch": 1.4132952416059963,
      "grad_norm": 0.39256593585014343,
      "learning_rate": 3.966169877306625e-06,
      "loss": 0.4744,
      "step": 46007
    },
    {
      "epoch": 1.4133259607409454,
      "grad_norm": 0.3945760428905487,
      "learning_rate": 3.96578449410226e-06,
      "loss": 0.4267,
      "step": 46008
    },
    {
      "epoch": 1.4133566798758948,
      "grad_norm": 0.42923808097839355,
      "learning_rate": 3.9653991249912225e-06,
      "loss": 0.5168,
      "step": 46009
    },
    {
      "epoch": 1.4133873990108439,
      "grad_norm": 0.411003440618515,
      "learning_rate": 3.965013769974417e-06,
      "loss": 0.4591,
      "step": 46010
    },
    {
      "epoch": 1.413418118145793,
      "grad_norm": 0.426451712846756,
      "learning_rate": 3.964628429052744e-06,
      "loss": 0.4611,
      "step": 46011
    },
    {
      "epoch": 1.413448837280742,
      "grad_norm": 0.3831323981285095,
      "learning_rate": 3.9642431022271064e-06,
      "loss": 0.436,
      "step": 46012
    },
    {
      "epoch": 1.4134795564156915,
      "grad_norm": 0.465651273727417,
      "learning_rate": 3.963857789498396e-06,
      "loss": 0.3931,
      "step": 46013
    },
    {
      "epoch": 1.4135102755506406,
      "grad_norm": 0.4407891035079956,
      "learning_rate": 3.963472490867518e-06,
      "loss": 0.5978,
      "step": 46014
    },
    {
      "epoch": 1.4135409946855897,
      "grad_norm": 0.4523944854736328,
      "learning_rate": 3.963087206335372e-06,
      "loss": 0.5271,
      "step": 46015
    },
    {
      "epoch": 1.4135717138205388,
      "grad_norm": 0.3621348440647125,
      "learning_rate": 3.962701935902861e-06,
      "loss": 0.4677,
      "step": 46016
    },
    {
      "epoch": 1.413602432955488,
      "grad_norm": 0.5054211020469666,
      "learning_rate": 3.962316679570877e-06,
      "loss": 0.4557,
      "step": 46017
    },
    {
      "epoch": 1.413633152090437,
      "grad_norm": 0.4494799077510834,
      "learning_rate": 3.961931437340324e-06,
      "loss": 0.4277,
      "step": 46018
    },
    {
      "epoch": 1.4136638712253862,
      "grad_norm": 0.4350338876247406,
      "learning_rate": 3.961546209212102e-06,
      "loss": 0.4644,
      "step": 46019
    },
    {
      "epoch": 1.4136945903603355,
      "grad_norm": 0.4100567400455475,
      "learning_rate": 3.96116099518711e-06,
      "loss": 0.5077,
      "step": 46020
    },
    {
      "epoch": 1.4137253094952846,
      "grad_norm": 0.4237891733646393,
      "learning_rate": 3.960775795266253e-06,
      "loss": 0.5058,
      "step": 46021
    },
    {
      "epoch": 1.4137560286302338,
      "grad_norm": 0.42639243602752686,
      "learning_rate": 3.960390609450422e-06,
      "loss": 0.4283,
      "step": 46022
    },
    {
      "epoch": 1.4137867477651829,
      "grad_norm": 0.46927380561828613,
      "learning_rate": 3.960005437740521e-06,
      "loss": 0.5166,
      "step": 46023
    },
    {
      "epoch": 1.4138174669001322,
      "grad_norm": 0.41146713495254517,
      "learning_rate": 3.959620280137447e-06,
      "loss": 0.5155,
      "step": 46024
    },
    {
      "epoch": 1.4138481860350813,
      "grad_norm": 0.3941076397895813,
      "learning_rate": 3.9592351366421066e-06,
      "loss": 0.5006,
      "step": 46025
    },
    {
      "epoch": 1.4138789051700305,
      "grad_norm": 0.3985656201839447,
      "learning_rate": 3.958850007255391e-06,
      "loss": 0.4407,
      "step": 46026
    },
    {
      "epoch": 1.4139096243049796,
      "grad_norm": 0.38087835907936096,
      "learning_rate": 3.958464891978208e-06,
      "loss": 0.5268,
      "step": 46027
    },
    {
      "epoch": 1.4139403434399287,
      "grad_norm": 0.4400928020477295,
      "learning_rate": 3.958079790811443e-06,
      "loss": 0.4077,
      "step": 46028
    },
    {
      "epoch": 1.4139710625748778,
      "grad_norm": 0.4271196126937866,
      "learning_rate": 3.957694703756012e-06,
      "loss": 0.438,
      "step": 46029
    },
    {
      "epoch": 1.414001781709827,
      "grad_norm": 0.43509581685066223,
      "learning_rate": 3.957309630812804e-06,
      "loss": 0.4861,
      "step": 46030
    },
    {
      "epoch": 1.4140325008447763,
      "grad_norm": 0.42482030391693115,
      "learning_rate": 3.9569245719827256e-06,
      "loss": 0.4893,
      "step": 46031
    },
    {
      "epoch": 1.4140632199797254,
      "grad_norm": 0.41855502128601074,
      "learning_rate": 3.956539527266664e-06,
      "loss": 0.4585,
      "step": 46032
    },
    {
      "epoch": 1.4140939391146745,
      "grad_norm": 0.3782113194465637,
      "learning_rate": 3.956154496665533e-06,
      "loss": 0.4618,
      "step": 46033
    },
    {
      "epoch": 1.4141246582496236,
      "grad_norm": 0.44033876061439514,
      "learning_rate": 3.955769480180223e-06,
      "loss": 0.516,
      "step": 46034
    },
    {
      "epoch": 1.414155377384573,
      "grad_norm": 0.3555702269077301,
      "learning_rate": 3.955384477811638e-06,
      "loss": 0.3989,
      "step": 46035
    },
    {
      "epoch": 1.414186096519522,
      "grad_norm": 0.4148228168487549,
      "learning_rate": 3.954999489560671e-06,
      "loss": 0.4865,
      "step": 46036
    },
    {
      "epoch": 1.4142168156544712,
      "grad_norm": 0.4213608205318451,
      "learning_rate": 3.954614515428222e-06,
      "loss": 0.5042,
      "step": 46037
    },
    {
      "epoch": 1.4142475347894203,
      "grad_norm": 0.4134233295917511,
      "learning_rate": 3.9542295554152e-06,
      "loss": 0.4765,
      "step": 46038
    },
    {
      "epoch": 1.4142782539243695,
      "grad_norm": 0.45564812421798706,
      "learning_rate": 3.953844609522494e-06,
      "loss": 0.5158,
      "step": 46039
    },
    {
      "epoch": 1.4143089730593186,
      "grad_norm": 0.41407015919685364,
      "learning_rate": 3.953459677751008e-06,
      "loss": 0.4378,
      "step": 46040
    },
    {
      "epoch": 1.4143396921942677,
      "grad_norm": 0.4311370551586151,
      "learning_rate": 3.953074760101637e-06,
      "loss": 0.4878,
      "step": 46041
    },
    {
      "epoch": 1.414370411329217,
      "grad_norm": 0.3890099823474884,
      "learning_rate": 3.952689856575283e-06,
      "loss": 0.4702,
      "step": 46042
    },
    {
      "epoch": 1.4144011304641662,
      "grad_norm": 0.4087982177734375,
      "learning_rate": 3.952304967172842e-06,
      "loss": 0.4755,
      "step": 46043
    },
    {
      "epoch": 1.4144318495991153,
      "grad_norm": 0.4749264419078827,
      "learning_rate": 3.95192009189522e-06,
      "loss": 0.4526,
      "step": 46044
    },
    {
      "epoch": 1.4144625687340644,
      "grad_norm": 0.4265385568141937,
      "learning_rate": 3.951535230743307e-06,
      "loss": 0.4727,
      "step": 46045
    },
    {
      "epoch": 1.4144932878690137,
      "grad_norm": 0.46182507276535034,
      "learning_rate": 3.951150383718007e-06,
      "loss": 0.5429,
      "step": 46046
    },
    {
      "epoch": 1.4145240070039629,
      "grad_norm": 0.415190190076828,
      "learning_rate": 3.950765550820217e-06,
      "loss": 0.5503,
      "step": 46047
    },
    {
      "epoch": 1.414554726138912,
      "grad_norm": 0.5011724233627319,
      "learning_rate": 3.95038073205084e-06,
      "loss": 0.3963,
      "step": 46048
    },
    {
      "epoch": 1.414585445273861,
      "grad_norm": 0.39201903343200684,
      "learning_rate": 3.949995927410768e-06,
      "loss": 0.4511,
      "step": 46049
    },
    {
      "epoch": 1.4146161644088102,
      "grad_norm": 0.43643397092819214,
      "learning_rate": 3.9496111369009026e-06,
      "loss": 0.5193,
      "step": 46050
    },
    {
      "epoch": 1.4146468835437593,
      "grad_norm": 0.4035413861274719,
      "learning_rate": 3.949226360522143e-06,
      "loss": 0.499,
      "step": 46051
    },
    {
      "epoch": 1.4146776026787085,
      "grad_norm": 0.41891270875930786,
      "learning_rate": 3.948841598275391e-06,
      "loss": 0.541,
      "step": 46052
    },
    {
      "epoch": 1.4147083218136578,
      "grad_norm": 0.4034757912158966,
      "learning_rate": 3.94845685016154e-06,
      "loss": 0.5052,
      "step": 46053
    },
    {
      "epoch": 1.414739040948607,
      "grad_norm": 0.4657739996910095,
      "learning_rate": 3.948072116181489e-06,
      "loss": 0.4786,
      "step": 46054
    },
    {
      "epoch": 1.414769760083556,
      "grad_norm": 0.4317275881767273,
      "learning_rate": 3.94768739633614e-06,
      "loss": 0.4245,
      "step": 46055
    },
    {
      "epoch": 1.4148004792185052,
      "grad_norm": 0.4284766912460327,
      "learning_rate": 3.947302690626388e-06,
      "loss": 0.4673,
      "step": 46056
    },
    {
      "epoch": 1.4148311983534545,
      "grad_norm": 0.45809170603752136,
      "learning_rate": 3.946917999053137e-06,
      "loss": 0.4088,
      "step": 46057
    },
    {
      "epoch": 1.4148619174884036,
      "grad_norm": 0.41118472814559937,
      "learning_rate": 3.946533321617278e-06,
      "loss": 0.4576,
      "step": 46058
    },
    {
      "epoch": 1.4148926366233527,
      "grad_norm": 0.43281301856040955,
      "learning_rate": 3.9461486583197155e-06,
      "loss": 0.3946,
      "step": 46059
    },
    {
      "epoch": 1.4149233557583019,
      "grad_norm": 0.3737379014492035,
      "learning_rate": 3.9457640091613434e-06,
      "loss": 0.4356,
      "step": 46060
    },
    {
      "epoch": 1.414954074893251,
      "grad_norm": 0.3949001729488373,
      "learning_rate": 3.945379374143067e-06,
      "loss": 0.3883,
      "step": 46061
    },
    {
      "epoch": 1.4149847940282,
      "grad_norm": 0.36590179800987244,
      "learning_rate": 3.9449947532657755e-06,
      "loss": 0.406,
      "step": 46062
    },
    {
      "epoch": 1.4150155131631492,
      "grad_norm": 0.44707149267196655,
      "learning_rate": 3.944610146530375e-06,
      "loss": 0.4615,
      "step": 46063
    },
    {
      "epoch": 1.4150462322980986,
      "grad_norm": 0.41901853680610657,
      "learning_rate": 3.944225553937754e-06,
      "loss": 0.4602,
      "step": 46064
    },
    {
      "epoch": 1.4150769514330477,
      "grad_norm": 0.44678637385368347,
      "learning_rate": 3.943840975488824e-06,
      "loss": 0.3935,
      "step": 46065
    },
    {
      "epoch": 1.4151076705679968,
      "grad_norm": 0.41945457458496094,
      "learning_rate": 3.943456411184473e-06,
      "loss": 0.4539,
      "step": 46066
    },
    {
      "epoch": 1.415138389702946,
      "grad_norm": 0.4500839114189148,
      "learning_rate": 3.943071861025606e-06,
      "loss": 0.4824,
      "step": 46067
    },
    {
      "epoch": 1.4151691088378953,
      "grad_norm": 0.41699251532554626,
      "learning_rate": 3.942687325013115e-06,
      "loss": 0.4178,
      "step": 46068
    },
    {
      "epoch": 1.4151998279728444,
      "grad_norm": 0.39794760942459106,
      "learning_rate": 3.942302803147899e-06,
      "loss": 0.4473,
      "step": 46069
    },
    {
      "epoch": 1.4152305471077935,
      "grad_norm": 0.4648718237876892,
      "learning_rate": 3.941918295430859e-06,
      "loss": 0.4478,
      "step": 46070
    },
    {
      "epoch": 1.4152612662427426,
      "grad_norm": 0.4254074990749359,
      "learning_rate": 3.941533801862896e-06,
      "loss": 0.3915,
      "step": 46071
    },
    {
      "epoch": 1.4152919853776917,
      "grad_norm": 0.4050072729587555,
      "learning_rate": 3.941149322444899e-06,
      "loss": 0.4544,
      "step": 46072
    },
    {
      "epoch": 1.4153227045126409,
      "grad_norm": 0.47734811902046204,
      "learning_rate": 3.940764857177768e-06,
      "loss": 0.4581,
      "step": 46073
    },
    {
      "epoch": 1.41535342364759,
      "grad_norm": 0.42015713453292847,
      "learning_rate": 3.940380406062411e-06,
      "loss": 0.4161,
      "step": 46074
    },
    {
      "epoch": 1.4153841427825393,
      "grad_norm": 0.4039512574672699,
      "learning_rate": 3.939995969099715e-06,
      "loss": 0.4479,
      "step": 46075
    },
    {
      "epoch": 1.4154148619174884,
      "grad_norm": 0.4472979009151459,
      "learning_rate": 3.9396115462905845e-06,
      "loss": 0.4888,
      "step": 46076
    },
    {
      "epoch": 1.4154455810524376,
      "grad_norm": 0.4143747389316559,
      "learning_rate": 3.9392271376359125e-06,
      "loss": 0.3935,
      "step": 46077
    },
    {
      "epoch": 1.4154763001873867,
      "grad_norm": 0.5104978680610657,
      "learning_rate": 3.9388427431365985e-06,
      "loss": 0.4488,
      "step": 46078
    },
    {
      "epoch": 1.4155070193223358,
      "grad_norm": 0.4187796115875244,
      "learning_rate": 3.9384583627935394e-06,
      "loss": 0.4843,
      "step": 46079
    },
    {
      "epoch": 1.4155377384572851,
      "grad_norm": 0.43721556663513184,
      "learning_rate": 3.938073996607638e-06,
      "loss": 0.5071,
      "step": 46080
    },
    {
      "epoch": 1.4155684575922343,
      "grad_norm": 0.39762794971466064,
      "learning_rate": 3.937689644579785e-06,
      "loss": 0.5814,
      "step": 46081
    },
    {
      "epoch": 1.4155991767271834,
      "grad_norm": 0.3880096971988678,
      "learning_rate": 3.937305306710882e-06,
      "loss": 0.5022,
      "step": 46082
    },
    {
      "epoch": 1.4156298958621325,
      "grad_norm": 0.40585121512413025,
      "learning_rate": 3.936920983001825e-06,
      "loss": 0.4843,
      "step": 46083
    },
    {
      "epoch": 1.4156606149970816,
      "grad_norm": 0.42505407333374023,
      "learning_rate": 3.936536673453516e-06,
      "loss": 0.4966,
      "step": 46084
    },
    {
      "epoch": 1.4156913341320307,
      "grad_norm": 0.4806312322616577,
      "learning_rate": 3.936152378066846e-06,
      "loss": 0.4644,
      "step": 46085
    },
    {
      "epoch": 1.41572205326698,
      "grad_norm": 0.6343528032302856,
      "learning_rate": 3.935768096842715e-06,
      "loss": 0.4434,
      "step": 46086
    },
    {
      "epoch": 1.4157527724019292,
      "grad_norm": 0.3801504373550415,
      "learning_rate": 3.935383829782022e-06,
      "loss": 0.4713,
      "step": 46087
    },
    {
      "epoch": 1.4157834915368783,
      "grad_norm": 0.3975033462047577,
      "learning_rate": 3.934999576885665e-06,
      "loss": 0.4531,
      "step": 46088
    },
    {
      "epoch": 1.4158142106718274,
      "grad_norm": 0.38995906710624695,
      "learning_rate": 3.9346153381545386e-06,
      "loss": 0.4588,
      "step": 46089
    },
    {
      "epoch": 1.4158449298067766,
      "grad_norm": 0.43978387117385864,
      "learning_rate": 3.934231113589545e-06,
      "loss": 0.5432,
      "step": 46090
    },
    {
      "epoch": 1.415875648941726,
      "grad_norm": 0.43124693632125854,
      "learning_rate": 3.933846903191571e-06,
      "loss": 0.4619,
      "step": 46091
    },
    {
      "epoch": 1.415906368076675,
      "grad_norm": 0.42873886227607727,
      "learning_rate": 3.9334627069615236e-06,
      "loss": 0.4936,
      "step": 46092
    },
    {
      "epoch": 1.4159370872116241,
      "grad_norm": 0.428860068321228,
      "learning_rate": 3.933078524900304e-06,
      "loss": 0.4849,
      "step": 46093
    },
    {
      "epoch": 1.4159678063465733,
      "grad_norm": 0.4191485643386841,
      "learning_rate": 3.9326943570087975e-06,
      "loss": 0.4955,
      "step": 46094
    },
    {
      "epoch": 1.4159985254815224,
      "grad_norm": 0.4198305904865265,
      "learning_rate": 3.932310203287907e-06,
      "loss": 0.5289,
      "step": 46095
    },
    {
      "epoch": 1.4160292446164715,
      "grad_norm": 0.45461952686309814,
      "learning_rate": 3.93192606373853e-06,
      "loss": 0.5008,
      "step": 46096
    },
    {
      "epoch": 1.4160599637514206,
      "grad_norm": 0.39711567759513855,
      "learning_rate": 3.931541938361567e-06,
      "loss": 0.4492,
      "step": 46097
    },
    {
      "epoch": 1.41609068288637,
      "grad_norm": 0.46372631192207336,
      "learning_rate": 3.931157827157909e-06,
      "loss": 0.469,
      "step": 46098
    },
    {
      "epoch": 1.416121402021319,
      "grad_norm": 0.62037593126297,
      "learning_rate": 3.930773730128458e-06,
      "loss": 0.4022,
      "step": 46099
    },
    {
      "epoch": 1.4161521211562682,
      "grad_norm": 0.3861255347728729,
      "learning_rate": 3.930389647274103e-06,
      "loss": 0.4943,
      "step": 46100
    },
    {
      "epoch": 1.4161828402912173,
      "grad_norm": 0.4272291362285614,
      "learning_rate": 3.930005578595753e-06,
      "loss": 0.4815,
      "step": 46101
    },
    {
      "epoch": 1.4162135594261667,
      "grad_norm": 0.39580994844436646,
      "learning_rate": 3.929621524094296e-06,
      "loss": 0.5263,
      "step": 46102
    },
    {
      "epoch": 1.4162442785611158,
      "grad_norm": 0.43803876638412476,
      "learning_rate": 3.929237483770635e-06,
      "loss": 0.4643,
      "step": 46103
    },
    {
      "epoch": 1.416274997696065,
      "grad_norm": 0.4314292073249817,
      "learning_rate": 3.928853457625661e-06,
      "loss": 0.5178,
      "step": 46104
    },
    {
      "epoch": 1.416305716831014,
      "grad_norm": 0.39734774827957153,
      "learning_rate": 3.928469445660272e-06,
      "loss": 0.4794,
      "step": 46105
    },
    {
      "epoch": 1.4163364359659631,
      "grad_norm": 0.3985360264778137,
      "learning_rate": 3.928085447875368e-06,
      "loss": 0.4682,
      "step": 46106
    },
    {
      "epoch": 1.4163671551009123,
      "grad_norm": 0.4169217050075531,
      "learning_rate": 3.927701464271848e-06,
      "loss": 0.4469,
      "step": 46107
    },
    {
      "epoch": 1.4163978742358614,
      "grad_norm": 0.5232431292533875,
      "learning_rate": 3.927317494850602e-06,
      "loss": 0.5503,
      "step": 46108
    },
    {
      "epoch": 1.4164285933708107,
      "grad_norm": 0.42162948846817017,
      "learning_rate": 3.92693353961253e-06,
      "loss": 0.4353,
      "step": 46109
    },
    {
      "epoch": 1.4164593125057598,
      "grad_norm": 0.4445165991783142,
      "learning_rate": 3.926549598558529e-06,
      "loss": 0.3497,
      "step": 46110
    },
    {
      "epoch": 1.416490031640709,
      "grad_norm": 0.43089592456817627,
      "learning_rate": 3.9261656716894944e-06,
      "loss": 0.4554,
      "step": 46111
    },
    {
      "epoch": 1.416520750775658,
      "grad_norm": 0.41879045963287354,
      "learning_rate": 3.925781759006328e-06,
      "loss": 0.4987,
      "step": 46112
    },
    {
      "epoch": 1.4165514699106074,
      "grad_norm": 0.44496554136276245,
      "learning_rate": 3.92539786050992e-06,
      "loss": 0.5261,
      "step": 46113
    },
    {
      "epoch": 1.4165821890455566,
      "grad_norm": 0.3813716769218445,
      "learning_rate": 3.925013976201168e-06,
      "loss": 0.3106,
      "step": 46114
    },
    {
      "epoch": 1.4166129081805057,
      "grad_norm": 0.46701982617378235,
      "learning_rate": 3.924630106080972e-06,
      "loss": 0.3838,
      "step": 46115
    },
    {
      "epoch": 1.4166436273154548,
      "grad_norm": 0.4167572259902954,
      "learning_rate": 3.924246250150228e-06,
      "loss": 0.5165,
      "step": 46116
    },
    {
      "epoch": 1.416674346450404,
      "grad_norm": 0.4366651773452759,
      "learning_rate": 3.92386240840983e-06,
      "loss": 0.5624,
      "step": 46117
    },
    {
      "epoch": 1.416705065585353,
      "grad_norm": 0.3888370990753174,
      "learning_rate": 3.923478580860675e-06,
      "loss": 0.4685,
      "step": 46118
    },
    {
      "epoch": 1.4167357847203021,
      "grad_norm": 0.4597150385379791,
      "learning_rate": 3.923094767503659e-06,
      "loss": 0.4672,
      "step": 46119
    },
    {
      "epoch": 1.4167665038552515,
      "grad_norm": 0.42904132604599,
      "learning_rate": 3.9227109683396845e-06,
      "loss": 0.5383,
      "step": 46120
    },
    {
      "epoch": 1.4167972229902006,
      "grad_norm": 0.43066805601119995,
      "learning_rate": 3.922327183369639e-06,
      "loss": 0.4584,
      "step": 46121
    },
    {
      "epoch": 1.4168279421251497,
      "grad_norm": 0.42502301931381226,
      "learning_rate": 3.921943412594422e-06,
      "loss": 0.4322,
      "step": 46122
    },
    {
      "epoch": 1.4168586612600989,
      "grad_norm": 0.41720855236053467,
      "learning_rate": 3.9215596560149315e-06,
      "loss": 0.4946,
      "step": 46123
    },
    {
      "epoch": 1.4168893803950482,
      "grad_norm": 0.4185847043991089,
      "learning_rate": 3.921175913632066e-06,
      "loss": 0.4922,
      "step": 46124
    },
    {
      "epoch": 1.4169200995299973,
      "grad_norm": 0.4218662977218628,
      "learning_rate": 3.920792185446716e-06,
      "loss": 0.4976,
      "step": 46125
    },
    {
      "epoch": 1.4169508186649464,
      "grad_norm": 0.44409990310668945,
      "learning_rate": 3.9204084714597836e-06,
      "loss": 0.483,
      "step": 46126
    },
    {
      "epoch": 1.4169815377998956,
      "grad_norm": 0.4935237765312195,
      "learning_rate": 3.920024771672154e-06,
      "loss": 0.4549,
      "step": 46127
    },
    {
      "epoch": 1.4170122569348447,
      "grad_norm": 0.4194099009037018,
      "learning_rate": 3.919641086084735e-06,
      "loss": 0.502,
      "step": 46128
    },
    {
      "epoch": 1.4170429760697938,
      "grad_norm": 0.4455834627151489,
      "learning_rate": 3.919257414698423e-06,
      "loss": 0.5006,
      "step": 46129
    },
    {
      "epoch": 1.417073695204743,
      "grad_norm": 0.44903916120529175,
      "learning_rate": 3.918873757514105e-06,
      "loss": 0.5005,
      "step": 46130
    },
    {
      "epoch": 1.4171044143396923,
      "grad_norm": 0.4324592649936676,
      "learning_rate": 3.918490114532688e-06,
      "loss": 0.4628,
      "step": 46131
    },
    {
      "epoch": 1.4171351334746414,
      "grad_norm": 0.414489209651947,
      "learning_rate": 3.918106485755053e-06,
      "loss": 0.401,
      "step": 46132
    },
    {
      "epoch": 1.4171658526095905,
      "grad_norm": 0.4218069314956665,
      "learning_rate": 3.917722871182113e-06,
      "loss": 0.4205,
      "step": 46133
    },
    {
      "epoch": 1.4171965717445396,
      "grad_norm": 0.4152872562408447,
      "learning_rate": 3.917339270814753e-06,
      "loss": 0.433,
      "step": 46134
    },
    {
      "epoch": 1.417227290879489,
      "grad_norm": 0.41105690598487854,
      "learning_rate": 3.9169556846538736e-06,
      "loss": 0.5173,
      "step": 46135
    },
    {
      "epoch": 1.417258010014438,
      "grad_norm": 0.42296552658081055,
      "learning_rate": 3.9165721127003645e-06,
      "loss": 0.4,
      "step": 46136
    },
    {
      "epoch": 1.4172887291493872,
      "grad_norm": 0.4226309657096863,
      "learning_rate": 3.916188554955132e-06,
      "loss": 0.3848,
      "step": 46137
    },
    {
      "epoch": 1.4173194482843363,
      "grad_norm": 0.42024746537208557,
      "learning_rate": 3.915805011419061e-06,
      "loss": 0.5378,
      "step": 46138
    },
    {
      "epoch": 1.4173501674192854,
      "grad_norm": 0.39053449034690857,
      "learning_rate": 3.915421482093057e-06,
      "loss": 0.4708,
      "step": 46139
    },
    {
      "epoch": 1.4173808865542346,
      "grad_norm": 0.4376399517059326,
      "learning_rate": 3.9150379669780085e-06,
      "loss": 0.4675,
      "step": 46140
    },
    {
      "epoch": 1.4174116056891837,
      "grad_norm": 0.44936251640319824,
      "learning_rate": 3.914654466074812e-06,
      "loss": 0.473,
      "step": 46141
    },
    {
      "epoch": 1.417442324824133,
      "grad_norm": 0.4064583480358124,
      "learning_rate": 3.9142709793843656e-06,
      "loss": 0.484,
      "step": 46142
    },
    {
      "epoch": 1.4174730439590821,
      "grad_norm": 0.41043204069137573,
      "learning_rate": 3.913887506907569e-06,
      "loss": 0.447,
      "step": 46143
    },
    {
      "epoch": 1.4175037630940313,
      "grad_norm": 0.4384734630584717,
      "learning_rate": 3.913504048645309e-06,
      "loss": 0.4846,
      "step": 46144
    },
    {
      "epoch": 1.4175344822289804,
      "grad_norm": 0.3984564244747162,
      "learning_rate": 3.913120604598485e-06,
      "loss": 0.473,
      "step": 46145
    },
    {
      "epoch": 1.4175652013639297,
      "grad_norm": 0.4090937376022339,
      "learning_rate": 3.912737174767993e-06,
      "loss": 0.4874,
      "step": 46146
    },
    {
      "epoch": 1.4175959204988788,
      "grad_norm": 0.4157435894012451,
      "learning_rate": 3.912353759154729e-06,
      "loss": 0.4361,
      "step": 46147
    },
    {
      "epoch": 1.417626639633828,
      "grad_norm": 0.429755300283432,
      "learning_rate": 3.911970357759591e-06,
      "loss": 0.4676,
      "step": 46148
    },
    {
      "epoch": 1.417657358768777,
      "grad_norm": 0.3999880254268646,
      "learning_rate": 3.9115869705834675e-06,
      "loss": 0.4738,
      "step": 46149
    },
    {
      "epoch": 1.4176880779037262,
      "grad_norm": 0.40173405408859253,
      "learning_rate": 3.9112035976272586e-06,
      "loss": 0.416,
      "step": 46150
    },
    {
      "epoch": 1.4177187970386753,
      "grad_norm": 0.39458364248275757,
      "learning_rate": 3.910820238891858e-06,
      "loss": 0.5288,
      "step": 46151
    },
    {
      "epoch": 1.4177495161736244,
      "grad_norm": 0.39661112427711487,
      "learning_rate": 3.910436894378166e-06,
      "loss": 0.4511,
      "step": 46152
    },
    {
      "epoch": 1.4177802353085738,
      "grad_norm": 0.42300349473953247,
      "learning_rate": 3.910053564087072e-06,
      "loss": 0.5036,
      "step": 46153
    },
    {
      "epoch": 1.417810954443523,
      "grad_norm": 0.4686872065067291,
      "learning_rate": 3.909670248019471e-06,
      "loss": 0.5262,
      "step": 46154
    },
    {
      "epoch": 1.417841673578472,
      "grad_norm": 0.43561220169067383,
      "learning_rate": 3.9092869461762615e-06,
      "loss": 0.4436,
      "step": 46155
    },
    {
      "epoch": 1.4178723927134211,
      "grad_norm": 0.38575583696365356,
      "learning_rate": 3.908903658558341e-06,
      "loss": 0.4586,
      "step": 46156
    },
    {
      "epoch": 1.4179031118483705,
      "grad_norm": 0.3939550220966339,
      "learning_rate": 3.9085203851665975e-06,
      "loss": 0.5075,
      "step": 46157
    },
    {
      "epoch": 1.4179338309833196,
      "grad_norm": 0.4195258915424347,
      "learning_rate": 3.9081371260019305e-06,
      "loss": 0.4284,
      "step": 46158
    },
    {
      "epoch": 1.4179645501182687,
      "grad_norm": 0.4116622507572174,
      "learning_rate": 3.907753881065235e-06,
      "loss": 0.4888,
      "step": 46159
    },
    {
      "epoch": 1.4179952692532178,
      "grad_norm": 0.39253148436546326,
      "learning_rate": 3.907370650357409e-06,
      "loss": 0.4957,
      "step": 46160
    },
    {
      "epoch": 1.418025988388167,
      "grad_norm": 0.45014500617980957,
      "learning_rate": 3.90698743387934e-06,
      "loss": 0.5026,
      "step": 46161
    },
    {
      "epoch": 1.418056707523116,
      "grad_norm": 0.4053468704223633,
      "learning_rate": 3.906604231631932e-06,
      "loss": 0.5138,
      "step": 46162
    },
    {
      "epoch": 1.4180874266580652,
      "grad_norm": 0.47325399518013,
      "learning_rate": 3.906221043616068e-06,
      "loss": 0.5576,
      "step": 46163
    },
    {
      "epoch": 1.4181181457930145,
      "grad_norm": 0.3971184492111206,
      "learning_rate": 3.905837869832654e-06,
      "loss": 0.4366,
      "step": 46164
    },
    {
      "epoch": 1.4181488649279637,
      "grad_norm": 0.4376578629016876,
      "learning_rate": 3.905454710282585e-06,
      "loss": 0.4361,
      "step": 46165
    },
    {
      "epoch": 1.4181795840629128,
      "grad_norm": 0.4497790038585663,
      "learning_rate": 3.905071564966748e-06,
      "loss": 0.4463,
      "step": 46166
    },
    {
      "epoch": 1.418210303197862,
      "grad_norm": 0.4149599075317383,
      "learning_rate": 3.9046884338860455e-06,
      "loss": 0.5029,
      "step": 46167
    },
    {
      "epoch": 1.4182410223328112,
      "grad_norm": 0.4275926351547241,
      "learning_rate": 3.904305317041363e-06,
      "loss": 0.4186,
      "step": 46168
    },
    {
      "epoch": 1.4182717414677604,
      "grad_norm": 0.43471038341522217,
      "learning_rate": 3.903922214433607e-06,
      "loss": 0.5386,
      "step": 46169
    },
    {
      "epoch": 1.4183024606027095,
      "grad_norm": 0.3862197697162628,
      "learning_rate": 3.903539126063664e-06,
      "loss": 0.4394,
      "step": 46170
    },
    {
      "epoch": 1.4183331797376586,
      "grad_norm": 0.3924676477909088,
      "learning_rate": 3.903156051932433e-06,
      "loss": 0.4253,
      "step": 46171
    },
    {
      "epoch": 1.4183638988726077,
      "grad_norm": 0.3972989618778229,
      "learning_rate": 3.9027729920408045e-06,
      "loss": 0.5323,
      "step": 46172
    },
    {
      "epoch": 1.4183946180075568,
      "grad_norm": 0.4152369797229767,
      "learning_rate": 3.902389946389676e-06,
      "loss": 0.478,
      "step": 46173
    },
    {
      "epoch": 1.418425337142506,
      "grad_norm": 0.4827362895011902,
      "learning_rate": 3.90200691497994e-06,
      "loss": 0.4353,
      "step": 46174
    },
    {
      "epoch": 1.4184560562774553,
      "grad_norm": 0.45862358808517456,
      "learning_rate": 3.901623897812497e-06,
      "loss": 0.4459,
      "step": 46175
    },
    {
      "epoch": 1.4184867754124044,
      "grad_norm": 0.4128536581993103,
      "learning_rate": 3.901240894888234e-06,
      "loss": 0.461,
      "step": 46176
    },
    {
      "epoch": 1.4185174945473535,
      "grad_norm": 0.3929276466369629,
      "learning_rate": 3.900857906208049e-06,
      "loss": 0.5133,
      "step": 46177
    },
    {
      "epoch": 1.4185482136823027,
      "grad_norm": 0.4338860809803009,
      "learning_rate": 3.900474931772835e-06,
      "loss": 0.4952,
      "step": 46178
    },
    {
      "epoch": 1.418578932817252,
      "grad_norm": 0.4254874587059021,
      "learning_rate": 3.900091971583493e-06,
      "loss": 0.4779,
      "step": 46179
    },
    {
      "epoch": 1.4186096519522011,
      "grad_norm": 0.39691856503486633,
      "learning_rate": 3.899709025640908e-06,
      "loss": 0.5132,
      "step": 46180
    },
    {
      "epoch": 1.4186403710871502,
      "grad_norm": 0.4560970962047577,
      "learning_rate": 3.899326093945979e-06,
      "loss": 0.4646,
      "step": 46181
    },
    {
      "epoch": 1.4186710902220994,
      "grad_norm": 0.3873997628688812,
      "learning_rate": 3.898943176499599e-06,
      "loss": 0.5364,
      "step": 46182
    },
    {
      "epoch": 1.4187018093570485,
      "grad_norm": 0.4058627784252167,
      "learning_rate": 3.898560273302664e-06,
      "loss": 0.4453,
      "step": 46183
    },
    {
      "epoch": 1.4187325284919976,
      "grad_norm": 0.4370465576648712,
      "learning_rate": 3.898177384356071e-06,
      "loss": 0.5007,
      "step": 46184
    },
    {
      "epoch": 1.4187632476269467,
      "grad_norm": 0.8270905613899231,
      "learning_rate": 3.897794509660707e-06,
      "loss": 0.4728,
      "step": 46185
    },
    {
      "epoch": 1.418793966761896,
      "grad_norm": 0.3987627625465393,
      "learning_rate": 3.897411649217471e-06,
      "loss": 0.5317,
      "step": 46186
    },
    {
      "epoch": 1.4188246858968452,
      "grad_norm": 0.3864021599292755,
      "learning_rate": 3.8970288030272555e-06,
      "loss": 0.4987,
      "step": 46187
    },
    {
      "epoch": 1.4188554050317943,
      "grad_norm": 0.4679848849773407,
      "learning_rate": 3.896645971090959e-06,
      "loss": 0.4339,
      "step": 46188
    },
    {
      "epoch": 1.4188861241667434,
      "grad_norm": 0.462373822927475,
      "learning_rate": 3.896263153409468e-06,
      "loss": 0.4036,
      "step": 46189
    },
    {
      "epoch": 1.4189168433016925,
      "grad_norm": 0.4651554524898529,
      "learning_rate": 3.895880349983683e-06,
      "loss": 0.4835,
      "step": 46190
    },
    {
      "epoch": 1.4189475624366419,
      "grad_norm": 0.40695682168006897,
      "learning_rate": 3.895497560814494e-06,
      "loss": 0.4479,
      "step": 46191
    },
    {
      "epoch": 1.418978281571591,
      "grad_norm": 0.38660314679145813,
      "learning_rate": 3.895114785902801e-06,
      "loss": 0.5202,
      "step": 46192
    },
    {
      "epoch": 1.4190090007065401,
      "grad_norm": 0.39646002650260925,
      "learning_rate": 3.894732025249489e-06,
      "loss": 0.4364,
      "step": 46193
    },
    {
      "epoch": 1.4190397198414892,
      "grad_norm": 0.40400466322898865,
      "learning_rate": 3.894349278855458e-06,
      "loss": 0.4884,
      "step": 46194
    },
    {
      "epoch": 1.4190704389764384,
      "grad_norm": 0.38785189390182495,
      "learning_rate": 3.8939665467216e-06,
      "loss": 0.5014,
      "step": 46195
    },
    {
      "epoch": 1.4191011581113875,
      "grad_norm": 0.4821648597717285,
      "learning_rate": 3.893583828848814e-06,
      "loss": 0.4723,
      "step": 46196
    },
    {
      "epoch": 1.4191318772463368,
      "grad_norm": 0.4182094931602478,
      "learning_rate": 3.893201125237984e-06,
      "loss": 0.5301,
      "step": 46197
    },
    {
      "epoch": 1.419162596381286,
      "grad_norm": 0.3983207046985626,
      "learning_rate": 3.892818435890014e-06,
      "loss": 0.4792,
      "step": 46198
    },
    {
      "epoch": 1.419193315516235,
      "grad_norm": 0.3944849371910095,
      "learning_rate": 3.892435760805786e-06,
      "loss": 0.4946,
      "step": 46199
    },
    {
      "epoch": 1.4192240346511842,
      "grad_norm": 0.416297048330307,
      "learning_rate": 3.892053099986209e-06,
      "loss": 0.4737,
      "step": 46200
    },
    {
      "epoch": 1.4192547537861333,
      "grad_norm": 0.47428640723228455,
      "learning_rate": 3.891670453432164e-06,
      "loss": 0.4463,
      "step": 46201
    },
    {
      "epoch": 1.4192854729210826,
      "grad_norm": 0.39471665024757385,
      "learning_rate": 3.891287821144548e-06,
      "loss": 0.4563,
      "step": 46202
    },
    {
      "epoch": 1.4193161920560318,
      "grad_norm": 0.4938621520996094,
      "learning_rate": 3.890905203124261e-06,
      "loss": 0.4013,
      "step": 46203
    },
    {
      "epoch": 1.4193469111909809,
      "grad_norm": 0.407757431268692,
      "learning_rate": 3.890522599372184e-06,
      "loss": 0.4703,
      "step": 46204
    },
    {
      "epoch": 1.41937763032593,
      "grad_norm": 0.4351348280906677,
      "learning_rate": 3.890140009889225e-06,
      "loss": 0.5109,
      "step": 46205
    },
    {
      "epoch": 1.4194083494608791,
      "grad_norm": 0.4525314271450043,
      "learning_rate": 3.889757434676268e-06,
      "loss": 0.521,
      "step": 46206
    },
    {
      "epoch": 1.4194390685958282,
      "grad_norm": 0.3956024944782257,
      "learning_rate": 3.889374873734212e-06,
      "loss": 0.4326,
      "step": 46207
    },
    {
      "epoch": 1.4194697877307774,
      "grad_norm": 0.43473362922668457,
      "learning_rate": 3.888992327063945e-06,
      "loss": 0.4558,
      "step": 46208
    },
    {
      "epoch": 1.4195005068657267,
      "grad_norm": 0.4286656975746155,
      "learning_rate": 3.888609794666363e-06,
      "loss": 0.4888,
      "step": 46209
    },
    {
      "epoch": 1.4195312260006758,
      "grad_norm": 0.42148661613464355,
      "learning_rate": 3.888227276542359e-06,
      "loss": 0.5354,
      "step": 46210
    },
    {
      "epoch": 1.419561945135625,
      "grad_norm": 0.41734305024147034,
      "learning_rate": 3.88784477269283e-06,
      "loss": 0.4237,
      "step": 46211
    },
    {
      "epoch": 1.419592664270574,
      "grad_norm": 0.4158684015274048,
      "learning_rate": 3.887462283118665e-06,
      "loss": 0.4506,
      "step": 46212
    },
    {
      "epoch": 1.4196233834055234,
      "grad_norm": 0.4551486670970917,
      "learning_rate": 3.887079807820757e-06,
      "loss": 0.4582,
      "step": 46213
    },
    {
      "epoch": 1.4196541025404725,
      "grad_norm": 0.4124070703983307,
      "learning_rate": 3.886697346800001e-06,
      "loss": 0.4189,
      "step": 46214
    },
    {
      "epoch": 1.4196848216754216,
      "grad_norm": 0.4426118731498718,
      "learning_rate": 3.886314900057296e-06,
      "loss": 0.4459,
      "step": 46215
    },
    {
      "epoch": 1.4197155408103708,
      "grad_norm": 0.4291462004184723,
      "learning_rate": 3.885932467593524e-06,
      "loss": 0.4481,
      "step": 46216
    },
    {
      "epoch": 1.4197462599453199,
      "grad_norm": 0.5410910844802856,
      "learning_rate": 3.885550049409583e-06,
      "loss": 0.4215,
      "step": 46217
    },
    {
      "epoch": 1.419776979080269,
      "grad_norm": 0.43341562151908875,
      "learning_rate": 3.885167645506369e-06,
      "loss": 0.4889,
      "step": 46218
    },
    {
      "epoch": 1.4198076982152181,
      "grad_norm": 0.4416378438472748,
      "learning_rate": 3.884785255884772e-06,
      "loss": 0.4544,
      "step": 46219
    },
    {
      "epoch": 1.4198384173501675,
      "grad_norm": 0.3975708782672882,
      "learning_rate": 3.884402880545689e-06,
      "loss": 0.4662,
      "step": 46220
    },
    {
      "epoch": 1.4198691364851166,
      "grad_norm": 0.5566316246986389,
      "learning_rate": 3.884020519490007e-06,
      "loss": 0.4676,
      "step": 46221
    },
    {
      "epoch": 1.4198998556200657,
      "grad_norm": 0.41670629382133484,
      "learning_rate": 3.883638172718623e-06,
      "loss": 0.5307,
      "step": 46222
    },
    {
      "epoch": 1.4199305747550148,
      "grad_norm": 0.4231984317302704,
      "learning_rate": 3.88325584023243e-06,
      "loss": 0.4462,
      "step": 46223
    },
    {
      "epoch": 1.4199612938899642,
      "grad_norm": 0.4432244896888733,
      "learning_rate": 3.882873522032321e-06,
      "loss": 0.4365,
      "step": 46224
    },
    {
      "epoch": 1.4199920130249133,
      "grad_norm": 0.4095000922679901,
      "learning_rate": 3.882491218119187e-06,
      "loss": 0.4816,
      "step": 46225
    },
    {
      "epoch": 1.4200227321598624,
      "grad_norm": 0.4369599521160126,
      "learning_rate": 3.882108928493921e-06,
      "loss": 0.4535,
      "step": 46226
    },
    {
      "epoch": 1.4200534512948115,
      "grad_norm": 0.4376826584339142,
      "learning_rate": 3.881726653157416e-06,
      "loss": 0.4606,
      "step": 46227
    },
    {
      "epoch": 1.4200841704297607,
      "grad_norm": 0.42361879348754883,
      "learning_rate": 3.88134439211057e-06,
      "loss": 0.5047,
      "step": 46228
    },
    {
      "epoch": 1.4201148895647098,
      "grad_norm": 0.3939442038536072,
      "learning_rate": 3.880962145354268e-06,
      "loss": 0.4273,
      "step": 46229
    },
    {
      "epoch": 1.420145608699659,
      "grad_norm": 0.48117929697036743,
      "learning_rate": 3.8805799128894106e-06,
      "loss": 0.4701,
      "step": 46230
    },
    {
      "epoch": 1.4201763278346082,
      "grad_norm": 0.3933808207511902,
      "learning_rate": 3.880197694716879e-06,
      "loss": 0.4269,
      "step": 46231
    },
    {
      "epoch": 1.4202070469695574,
      "grad_norm": 0.5793293714523315,
      "learning_rate": 3.879815490837578e-06,
      "loss": 0.4756,
      "step": 46232
    },
    {
      "epoch": 1.4202377661045065,
      "grad_norm": 0.4477095305919647,
      "learning_rate": 3.879433301252395e-06,
      "loss": 0.5037,
      "step": 46233
    },
    {
      "epoch": 1.4202684852394556,
      "grad_norm": 0.4340699017047882,
      "learning_rate": 3.879051125962223e-06,
      "loss": 0.3849,
      "step": 46234
    },
    {
      "epoch": 1.420299204374405,
      "grad_norm": 0.5166239142417908,
      "learning_rate": 3.87866896496795e-06,
      "loss": 0.3575,
      "step": 46235
    },
    {
      "epoch": 1.420329923509354,
      "grad_norm": 0.4151780605316162,
      "learning_rate": 3.8782868182704805e-06,
      "loss": 0.4248,
      "step": 46236
    },
    {
      "epoch": 1.4203606426443032,
      "grad_norm": 0.4040852189064026,
      "learning_rate": 3.8779046858706945e-06,
      "loss": 0.4942,
      "step": 46237
    },
    {
      "epoch": 1.4203913617792523,
      "grad_norm": 0.39415037631988525,
      "learning_rate": 3.87752256776949e-06,
      "loss": 0.4411,
      "step": 46238
    },
    {
      "epoch": 1.4204220809142014,
      "grad_norm": 0.4613736867904663,
      "learning_rate": 3.8771404639677636e-06,
      "loss": 0.4886,
      "step": 46239
    },
    {
      "epoch": 1.4204528000491505,
      "grad_norm": 0.41079971194267273,
      "learning_rate": 3.876758374466395e-06,
      "loss": 0.4735,
      "step": 46240
    },
    {
      "epoch": 1.4204835191840997,
      "grad_norm": 0.3927641808986664,
      "learning_rate": 3.876376299266293e-06,
      "loss": 0.5405,
      "step": 46241
    },
    {
      "epoch": 1.420514238319049,
      "grad_norm": 0.41931578516960144,
      "learning_rate": 3.875994238368338e-06,
      "loss": 0.5542,
      "step": 46242
    },
    {
      "epoch": 1.4205449574539981,
      "grad_norm": 0.4269773066043854,
      "learning_rate": 3.875612191773429e-06,
      "loss": 0.441,
      "step": 46243
    },
    {
      "epoch": 1.4205756765889472,
      "grad_norm": 6.263737201690674,
      "learning_rate": 3.875230159482453e-06,
      "loss": 0.501,
      "step": 46244
    },
    {
      "epoch": 1.4206063957238964,
      "grad_norm": 0.44167259335517883,
      "learning_rate": 3.874848141496304e-06,
      "loss": 0.4545,
      "step": 46245
    },
    {
      "epoch": 1.4206371148588457,
      "grad_norm": 0.4024523198604584,
      "learning_rate": 3.874466137815875e-06,
      "loss": 0.4237,
      "step": 46246
    },
    {
      "epoch": 1.4206678339937948,
      "grad_norm": 0.41669705510139465,
      "learning_rate": 3.874084148442062e-06,
      "loss": 0.4365,
      "step": 46247
    },
    {
      "epoch": 1.420698553128744,
      "grad_norm": 0.4422939717769623,
      "learning_rate": 3.87370217337575e-06,
      "loss": 0.4292,
      "step": 46248
    },
    {
      "epoch": 1.420729272263693,
      "grad_norm": 0.4433537721633911,
      "learning_rate": 3.873320212617833e-06,
      "loss": 0.5697,
      "step": 46249
    },
    {
      "epoch": 1.4207599913986422,
      "grad_norm": 0.38798391819000244,
      "learning_rate": 3.872938266169206e-06,
      "loss": 0.5111,
      "step": 46250
    },
    {
      "epoch": 1.4207907105335913,
      "grad_norm": 0.42493125796318054,
      "learning_rate": 3.872556334030763e-06,
      "loss": 0.4901,
      "step": 46251
    },
    {
      "epoch": 1.4208214296685404,
      "grad_norm": 0.405582457780838,
      "learning_rate": 3.872174416203388e-06,
      "loss": 0.4795,
      "step": 46252
    },
    {
      "epoch": 1.4208521488034898,
      "grad_norm": 0.46127596497535706,
      "learning_rate": 3.871792512687979e-06,
      "loss": 0.4925,
      "step": 46253
    },
    {
      "epoch": 1.4208828679384389,
      "grad_norm": 0.47582554817199707,
      "learning_rate": 3.871410623485425e-06,
      "loss": 0.4599,
      "step": 46254
    },
    {
      "epoch": 1.420913587073388,
      "grad_norm": 0.3947931230068207,
      "learning_rate": 3.871028748596622e-06,
      "loss": 0.4799,
      "step": 46255
    },
    {
      "epoch": 1.4209443062083371,
      "grad_norm": 0.4631119966506958,
      "learning_rate": 3.8706468880224604e-06,
      "loss": 0.5099,
      "step": 46256
    },
    {
      "epoch": 1.4209750253432865,
      "grad_norm": 0.4364153742790222,
      "learning_rate": 3.870265041763829e-06,
      "loss": 0.4884,
      "step": 46257
    },
    {
      "epoch": 1.4210057444782356,
      "grad_norm": 0.4573342502117157,
      "learning_rate": 3.869883209821621e-06,
      "loss": 0.4103,
      "step": 46258
    },
    {
      "epoch": 1.4210364636131847,
      "grad_norm": 0.43517616391181946,
      "learning_rate": 3.869501392196728e-06,
      "loss": 0.4823,
      "step": 46259
    },
    {
      "epoch": 1.4210671827481338,
      "grad_norm": 0.4103665053844452,
      "learning_rate": 3.869119588890048e-06,
      "loss": 0.49,
      "step": 46260
    },
    {
      "epoch": 1.421097901883083,
      "grad_norm": 0.46423274278640747,
      "learning_rate": 3.868737799902463e-06,
      "loss": 0.5593,
      "step": 46261
    },
    {
      "epoch": 1.421128621018032,
      "grad_norm": 0.41760244965553284,
      "learning_rate": 3.86835602523487e-06,
      "loss": 0.5344,
      "step": 46262
    },
    {
      "epoch": 1.4211593401529812,
      "grad_norm": 0.40281909704208374,
      "learning_rate": 3.867974264888158e-06,
      "loss": 0.4991,
      "step": 46263
    },
    {
      "epoch": 1.4211900592879305,
      "grad_norm": 0.3807879686355591,
      "learning_rate": 3.867592518863225e-06,
      "loss": 0.4744,
      "step": 46264
    },
    {
      "epoch": 1.4212207784228796,
      "grad_norm": 0.41283711791038513,
      "learning_rate": 3.867210787160954e-06,
      "loss": 0.4132,
      "step": 46265
    },
    {
      "epoch": 1.4212514975578288,
      "grad_norm": 0.45803117752075195,
      "learning_rate": 3.8668290697822445e-06,
      "loss": 0.5211,
      "step": 46266
    },
    {
      "epoch": 1.4212822166927779,
      "grad_norm": 0.4277206361293793,
      "learning_rate": 3.8664473667279766e-06,
      "loss": 0.4613,
      "step": 46267
    },
    {
      "epoch": 1.4213129358277272,
      "grad_norm": 0.3970971703529358,
      "learning_rate": 3.866065677999056e-06,
      "loss": 0.3249,
      "step": 46268
    },
    {
      "epoch": 1.4213436549626763,
      "grad_norm": 0.4545654356479645,
      "learning_rate": 3.865684003596365e-06,
      "loss": 0.4673,
      "step": 46269
    },
    {
      "epoch": 1.4213743740976255,
      "grad_norm": 0.4494066834449768,
      "learning_rate": 3.865302343520799e-06,
      "loss": 0.5346,
      "step": 46270
    },
    {
      "epoch": 1.4214050932325746,
      "grad_norm": 0.4094456136226654,
      "learning_rate": 3.864920697773247e-06,
      "loss": 0.4812,
      "step": 46271
    },
    {
      "epoch": 1.4214358123675237,
      "grad_norm": 0.4016333222389221,
      "learning_rate": 3.8645390663545985e-06,
      "loss": 0.3578,
      "step": 46272
    },
    {
      "epoch": 1.4214665315024728,
      "grad_norm": 0.3808319568634033,
      "learning_rate": 3.864157449265749e-06,
      "loss": 0.4344,
      "step": 46273
    },
    {
      "epoch": 1.421497250637422,
      "grad_norm": 0.3899660110473633,
      "learning_rate": 3.863775846507588e-06,
      "loss": 0.4946,
      "step": 46274
    },
    {
      "epoch": 1.4215279697723713,
      "grad_norm": 0.4446980357170105,
      "learning_rate": 3.863394258081011e-06,
      "loss": 0.3606,
      "step": 46275
    },
    {
      "epoch": 1.4215586889073204,
      "grad_norm": 0.40408048033714294,
      "learning_rate": 3.863012683986897e-06,
      "loss": 0.4464,
      "step": 46276
    },
    {
      "epoch": 1.4215894080422695,
      "grad_norm": 0.4770665168762207,
      "learning_rate": 3.8626311242261535e-06,
      "loss": 0.5051,
      "step": 46277
    },
    {
      "epoch": 1.4216201271772186,
      "grad_norm": 0.4364345669746399,
      "learning_rate": 3.86224957879966e-06,
      "loss": 0.4811,
      "step": 46278
    },
    {
      "epoch": 1.421650846312168,
      "grad_norm": 0.3824522793292999,
      "learning_rate": 3.861868047708314e-06,
      "loss": 0.4366,
      "step": 46279
    },
    {
      "epoch": 1.421681565447117,
      "grad_norm": 0.39114996790885925,
      "learning_rate": 3.861486530953002e-06,
      "loss": 0.4913,
      "step": 46280
    },
    {
      "epoch": 1.4217122845820662,
      "grad_norm": 0.40881025791168213,
      "learning_rate": 3.861105028534616e-06,
      "loss": 0.4557,
      "step": 46281
    },
    {
      "epoch": 1.4217430037170153,
      "grad_norm": 0.4262053370475769,
      "learning_rate": 3.860723540454049e-06,
      "loss": 0.5086,
      "step": 46282
    },
    {
      "epoch": 1.4217737228519645,
      "grad_norm": 0.4184701144695282,
      "learning_rate": 3.860342066712193e-06,
      "loss": 0.4904,
      "step": 46283
    },
    {
      "epoch": 1.4218044419869136,
      "grad_norm": 0.4019964337348938,
      "learning_rate": 3.859960607309934e-06,
      "loss": 0.4178,
      "step": 46284
    },
    {
      "epoch": 1.4218351611218627,
      "grad_norm": 0.429897665977478,
      "learning_rate": 3.859579162248165e-06,
      "loss": 0.4951,
      "step": 46285
    },
    {
      "epoch": 1.421865880256812,
      "grad_norm": 0.43373367190361023,
      "learning_rate": 3.859197731527778e-06,
      "loss": 0.4912,
      "step": 46286
    },
    {
      "epoch": 1.4218965993917612,
      "grad_norm": 0.42251506447792053,
      "learning_rate": 3.858816315149668e-06,
      "loss": 0.456,
      "step": 46287
    },
    {
      "epoch": 1.4219273185267103,
      "grad_norm": 0.406932532787323,
      "learning_rate": 3.858434913114717e-06,
      "loss": 0.3997,
      "step": 46288
    },
    {
      "epoch": 1.4219580376616594,
      "grad_norm": 0.469887912273407,
      "learning_rate": 3.858053525423821e-06,
      "loss": 0.5478,
      "step": 46289
    },
    {
      "epoch": 1.4219887567966087,
      "grad_norm": 0.4905421733856201,
      "learning_rate": 3.8576721520778696e-06,
      "loss": 0.3964,
      "step": 46290
    },
    {
      "epoch": 1.4220194759315579,
      "grad_norm": 0.4283098578453064,
      "learning_rate": 3.857290793077757e-06,
      "loss": 0.4724,
      "step": 46291
    },
    {
      "epoch": 1.422050195066507,
      "grad_norm": 0.41995400190353394,
      "learning_rate": 3.856909448424368e-06,
      "loss": 0.4432,
      "step": 46292
    },
    {
      "epoch": 1.422080914201456,
      "grad_norm": 0.44737109541893005,
      "learning_rate": 3.856528118118594e-06,
      "loss": 0.4511,
      "step": 46293
    },
    {
      "epoch": 1.4221116333364052,
      "grad_norm": 0.46008870005607605,
      "learning_rate": 3.856146802161329e-06,
      "loss": 0.5571,
      "step": 46294
    },
    {
      "epoch": 1.4221423524713543,
      "grad_norm": 0.9014167189598083,
      "learning_rate": 3.8557655005534625e-06,
      "loss": 0.5337,
      "step": 46295
    },
    {
      "epoch": 1.4221730716063035,
      "grad_norm": 0.3936990201473236,
      "learning_rate": 3.855384213295889e-06,
      "loss": 0.4661,
      "step": 46296
    },
    {
      "epoch": 1.4222037907412528,
      "grad_norm": 0.42974165081977844,
      "learning_rate": 3.85500294038949e-06,
      "loss": 0.4551,
      "step": 46297
    },
    {
      "epoch": 1.422234509876202,
      "grad_norm": 0.43288949131965637,
      "learning_rate": 3.8546216818351615e-06,
      "loss": 0.4493,
      "step": 46298
    },
    {
      "epoch": 1.422265229011151,
      "grad_norm": 0.3977404534816742,
      "learning_rate": 3.854240437633793e-06,
      "loss": 0.5065,
      "step": 46299
    },
    {
      "epoch": 1.4222959481461002,
      "grad_norm": 0.40402230620384216,
      "learning_rate": 3.853859207786278e-06,
      "loss": 0.4667,
      "step": 46300
    },
    {
      "epoch": 1.4223266672810493,
      "grad_norm": 0.39369794726371765,
      "learning_rate": 3.8534779922935006e-06,
      "loss": 0.4275,
      "step": 46301
    },
    {
      "epoch": 1.4223573864159986,
      "grad_norm": 0.3922217786312103,
      "learning_rate": 3.853096791156359e-06,
      "loss": 0.4904,
      "step": 46302
    },
    {
      "epoch": 1.4223881055509477,
      "grad_norm": 0.4496493339538574,
      "learning_rate": 3.852715604375732e-06,
      "loss": 0.4528,
      "step": 46303
    },
    {
      "epoch": 1.4224188246858969,
      "grad_norm": 0.43482691049575806,
      "learning_rate": 3.852334431952524e-06,
      "loss": 0.4717,
      "step": 46304
    },
    {
      "epoch": 1.422449543820846,
      "grad_norm": 0.37811774015426636,
      "learning_rate": 3.851953273887614e-06,
      "loss": 0.4465,
      "step": 46305
    },
    {
      "epoch": 1.422480262955795,
      "grad_norm": 0.43299439549446106,
      "learning_rate": 3.851572130181901e-06,
      "loss": 0.4804,
      "step": 46306
    },
    {
      "epoch": 1.4225109820907442,
      "grad_norm": 0.6033604741096497,
      "learning_rate": 3.851191000836266e-06,
      "loss": 0.4372,
      "step": 46307
    },
    {
      "epoch": 1.4225417012256936,
      "grad_norm": 0.4633025825023651,
      "learning_rate": 3.850809885851605e-06,
      "loss": 0.4489,
      "step": 46308
    },
    {
      "epoch": 1.4225724203606427,
      "grad_norm": 0.4197913110256195,
      "learning_rate": 3.850428785228807e-06,
      "loss": 0.4225,
      "step": 46309
    },
    {
      "epoch": 1.4226031394955918,
      "grad_norm": 0.37699905037879944,
      "learning_rate": 3.850047698968762e-06,
      "loss": 0.4291,
      "step": 46310
    },
    {
      "epoch": 1.422633858630541,
      "grad_norm": 0.4231690466403961,
      "learning_rate": 3.849666627072363e-06,
      "loss": 0.4461,
      "step": 46311
    },
    {
      "epoch": 1.42266457776549,
      "grad_norm": 0.39775124192237854,
      "learning_rate": 3.849285569540494e-06,
      "loss": 0.4374,
      "step": 46312
    },
    {
      "epoch": 1.4226952969004394,
      "grad_norm": 0.4205751121044159,
      "learning_rate": 3.8489045263740474e-06,
      "loss": 0.4285,
      "step": 46313
    },
    {
      "epoch": 1.4227260160353885,
      "grad_norm": 0.40537723898887634,
      "learning_rate": 3.848523497573915e-06,
      "loss": 0.4294,
      "step": 46314
    },
    {
      "epoch": 1.4227567351703376,
      "grad_norm": 0.4417477548122406,
      "learning_rate": 3.848142483140988e-06,
      "loss": 0.4438,
      "step": 46315
    },
    {
      "epoch": 1.4227874543052867,
      "grad_norm": 0.4186374843120575,
      "learning_rate": 3.847761483076151e-06,
      "loss": 0.417,
      "step": 46316
    },
    {
      "epoch": 1.4228181734402359,
      "grad_norm": 0.4096197187900543,
      "learning_rate": 3.847380497380297e-06,
      "loss": 0.463,
      "step": 46317
    },
    {
      "epoch": 1.422848892575185,
      "grad_norm": 0.42606714367866516,
      "learning_rate": 3.846999526054316e-06,
      "loss": 0.5114,
      "step": 46318
    },
    {
      "epoch": 1.422879611710134,
      "grad_norm": 0.43642956018447876,
      "learning_rate": 3.8466185690991e-06,
      "loss": 0.5411,
      "step": 46319
    },
    {
      "epoch": 1.4229103308450834,
      "grad_norm": 0.40153592824935913,
      "learning_rate": 3.846237626515532e-06,
      "loss": 0.5063,
      "step": 46320
    },
    {
      "epoch": 1.4229410499800326,
      "grad_norm": 0.4041323959827423,
      "learning_rate": 3.845856698304507e-06,
      "loss": 0.4726,
      "step": 46321
    },
    {
      "epoch": 1.4229717691149817,
      "grad_norm": 0.40947258472442627,
      "learning_rate": 3.845475784466912e-06,
      "loss": 0.484,
      "step": 46322
    },
    {
      "epoch": 1.4230024882499308,
      "grad_norm": 0.38553866744041443,
      "learning_rate": 3.845094885003643e-06,
      "loss": 0.3918,
      "step": 46323
    },
    {
      "epoch": 1.4230332073848801,
      "grad_norm": 0.45433226227760315,
      "learning_rate": 3.84471399991558e-06,
      "loss": 0.4586,
      "step": 46324
    },
    {
      "epoch": 1.4230639265198293,
      "grad_norm": 0.43382728099823,
      "learning_rate": 3.844333129203619e-06,
      "loss": 0.504,
      "step": 46325
    },
    {
      "epoch": 1.4230946456547784,
      "grad_norm": 0.47983428835868835,
      "learning_rate": 3.843952272868646e-06,
      "loss": 0.4768,
      "step": 46326
    },
    {
      "epoch": 1.4231253647897275,
      "grad_norm": 0.45748981833457947,
      "learning_rate": 3.843571430911558e-06,
      "loss": 0.4871,
      "step": 46327
    },
    {
      "epoch": 1.4231560839246766,
      "grad_norm": 0.43552905321121216,
      "learning_rate": 3.843190603333234e-06,
      "loss": 0.4476,
      "step": 46328
    },
    {
      "epoch": 1.4231868030596257,
      "grad_norm": 0.3912144899368286,
      "learning_rate": 3.842809790134568e-06,
      "loss": 0.5276,
      "step": 46329
    },
    {
      "epoch": 1.4232175221945749,
      "grad_norm": 0.416133314371109,
      "learning_rate": 3.842428991316451e-06,
      "loss": 0.4623,
      "step": 46330
    },
    {
      "epoch": 1.4232482413295242,
      "grad_norm": 0.4130198061466217,
      "learning_rate": 3.84204820687977e-06,
      "loss": 0.4256,
      "step": 46331
    },
    {
      "epoch": 1.4232789604644733,
      "grad_norm": 0.41198015213012695,
      "learning_rate": 3.84166743682542e-06,
      "loss": 0.5282,
      "step": 46332
    },
    {
      "epoch": 1.4233096795994225,
      "grad_norm": 0.45419493317604065,
      "learning_rate": 3.841286681154281e-06,
      "loss": 0.4937,
      "step": 46333
    },
    {
      "epoch": 1.4233403987343716,
      "grad_norm": 0.4353668689727783,
      "learning_rate": 3.840905939867252e-06,
      "loss": 0.5015,
      "step": 46334
    },
    {
      "epoch": 1.423371117869321,
      "grad_norm": 0.42072153091430664,
      "learning_rate": 3.84052521296521e-06,
      "loss": 0.5121,
      "step": 46335
    },
    {
      "epoch": 1.42340183700427,
      "grad_norm": 0.4151541590690613,
      "learning_rate": 3.840144500449058e-06,
      "loss": 0.5011,
      "step": 46336
    },
    {
      "epoch": 1.4234325561392192,
      "grad_norm": 0.41830265522003174,
      "learning_rate": 3.839763802319675e-06,
      "loss": 0.4504,
      "step": 46337
    },
    {
      "epoch": 1.4234632752741683,
      "grad_norm": 0.4532862603664398,
      "learning_rate": 3.8393831185779585e-06,
      "loss": 0.4773,
      "step": 46338
    },
    {
      "epoch": 1.4234939944091174,
      "grad_norm": 0.39243778586387634,
      "learning_rate": 3.839002449224785e-06,
      "loss": 0.47,
      "step": 46339
    },
    {
      "epoch": 1.4235247135440665,
      "grad_norm": 0.40941351652145386,
      "learning_rate": 3.838621794261058e-06,
      "loss": 0.3747,
      "step": 46340
    },
    {
      "epoch": 1.4235554326790156,
      "grad_norm": 0.4314139187335968,
      "learning_rate": 3.838241153687658e-06,
      "loss": 0.453,
      "step": 46341
    },
    {
      "epoch": 1.423586151813965,
      "grad_norm": 0.3990316689014435,
      "learning_rate": 3.837860527505479e-06,
      "loss": 0.4742,
      "step": 46342
    },
    {
      "epoch": 1.423616870948914,
      "grad_norm": 0.43508481979370117,
      "learning_rate": 3.837479915715404e-06,
      "loss": 0.4835,
      "step": 46343
    },
    {
      "epoch": 1.4236475900838632,
      "grad_norm": 0.4040129482746124,
      "learning_rate": 3.837099318318325e-06,
      "loss": 0.4286,
      "step": 46344
    },
    {
      "epoch": 1.4236783092188123,
      "grad_norm": 0.46330153942108154,
      "learning_rate": 3.83671873531513e-06,
      "loss": 0.451,
      "step": 46345
    },
    {
      "epoch": 1.4237090283537617,
      "grad_norm": 0.425417959690094,
      "learning_rate": 3.836338166706713e-06,
      "loss": 0.4103,
      "step": 46346
    },
    {
      "epoch": 1.4237397474887108,
      "grad_norm": 0.4506617486476898,
      "learning_rate": 3.835957612493956e-06,
      "loss": 0.476,
      "step": 46347
    },
    {
      "epoch": 1.42377046662366,
      "grad_norm": 0.4009537100791931,
      "learning_rate": 3.835577072677748e-06,
      "loss": 0.4332,
      "step": 46348
    },
    {
      "epoch": 1.423801185758609,
      "grad_norm": 0.3741210699081421,
      "learning_rate": 3.8351965472589824e-06,
      "loss": 0.4603,
      "step": 46349
    },
    {
      "epoch": 1.4238319048935582,
      "grad_norm": 0.4426353871822357,
      "learning_rate": 3.834816036238546e-06,
      "loss": 0.4866,
      "step": 46350
    },
    {
      "epoch": 1.4238626240285073,
      "grad_norm": 0.46916744112968445,
      "learning_rate": 3.834435539617329e-06,
      "loss": 0.5561,
      "step": 46351
    },
    {
      "epoch": 1.4238933431634564,
      "grad_norm": 0.45676183700561523,
      "learning_rate": 3.834055057396217e-06,
      "loss": 0.4715,
      "step": 46352
    },
    {
      "epoch": 1.4239240622984057,
      "grad_norm": 0.43891820311546326,
      "learning_rate": 3.833674589576099e-06,
      "loss": 0.4633,
      "step": 46353
    },
    {
      "epoch": 1.4239547814333549,
      "grad_norm": 0.42951539158821106,
      "learning_rate": 3.833294136157864e-06,
      "loss": 0.5323,
      "step": 46354
    },
    {
      "epoch": 1.423985500568304,
      "grad_norm": 0.41084030270576477,
      "learning_rate": 3.832913697142406e-06,
      "loss": 0.3908,
      "step": 46355
    },
    {
      "epoch": 1.424016219703253,
      "grad_norm": 0.3926289975643158,
      "learning_rate": 3.832533272530605e-06,
      "loss": 0.4894,
      "step": 46356
    },
    {
      "epoch": 1.4240469388382024,
      "grad_norm": 0.39282578229904175,
      "learning_rate": 3.832152862323353e-06,
      "loss": 0.4685,
      "step": 46357
    },
    {
      "epoch": 1.4240776579731516,
      "grad_norm": 0.4031835198402405,
      "learning_rate": 3.831772466521539e-06,
      "loss": 0.5617,
      "step": 46358
    },
    {
      "epoch": 1.4241083771081007,
      "grad_norm": 0.4369116425514221,
      "learning_rate": 3.831392085126054e-06,
      "loss": 0.4445,
      "step": 46359
    },
    {
      "epoch": 1.4241390962430498,
      "grad_norm": 0.4473831057548523,
      "learning_rate": 3.831011718137781e-06,
      "loss": 0.516,
      "step": 46360
    },
    {
      "epoch": 1.424169815377999,
      "grad_norm": 0.4747200608253479,
      "learning_rate": 3.83063136555761e-06,
      "loss": 0.553,
      "step": 46361
    },
    {
      "epoch": 1.424200534512948,
      "grad_norm": 0.47850877046585083,
      "learning_rate": 3.83025102738643e-06,
      "loss": 0.4593,
      "step": 46362
    },
    {
      "epoch": 1.4242312536478972,
      "grad_norm": 0.42890480160713196,
      "learning_rate": 3.8298707036251345e-06,
      "loss": 0.4763,
      "step": 46363
    },
    {
      "epoch": 1.4242619727828465,
      "grad_norm": 0.422295480966568,
      "learning_rate": 3.829490394274603e-06,
      "loss": 0.4685,
      "step": 46364
    },
    {
      "epoch": 1.4242926919177956,
      "grad_norm": 0.9869930148124695,
      "learning_rate": 3.829110099335728e-06,
      "loss": 0.4856,
      "step": 46365
    },
    {
      "epoch": 1.4243234110527447,
      "grad_norm": 0.4966473877429962,
      "learning_rate": 3.828729818809396e-06,
      "loss": 0.4212,
      "step": 46366
    },
    {
      "epoch": 1.4243541301876939,
      "grad_norm": 0.4008024036884308,
      "learning_rate": 3.828349552696498e-06,
      "loss": 0.5268,
      "step": 46367
    },
    {
      "epoch": 1.4243848493226432,
      "grad_norm": 0.42291170358657837,
      "learning_rate": 3.827969300997922e-06,
      "loss": 0.472,
      "step": 46368
    },
    {
      "epoch": 1.4244155684575923,
      "grad_norm": 0.4345605671405792,
      "learning_rate": 3.827589063714553e-06,
      "loss": 0.4835,
      "step": 46369
    },
    {
      "epoch": 1.4244462875925414,
      "grad_norm": 0.420180082321167,
      "learning_rate": 3.827208840847284e-06,
      "loss": 0.4517,
      "step": 46370
    },
    {
      "epoch": 1.4244770067274906,
      "grad_norm": 0.37638846039772034,
      "learning_rate": 3.8268286323969925e-06,
      "loss": 0.4714,
      "step": 46371
    },
    {
      "epoch": 1.4245077258624397,
      "grad_norm": 0.43391498923301697,
      "learning_rate": 3.826448438364582e-06,
      "loss": 0.5135,
      "step": 46372
    },
    {
      "epoch": 1.4245384449973888,
      "grad_norm": 0.42955106496810913,
      "learning_rate": 3.826068258750928e-06,
      "loss": 0.4937,
      "step": 46373
    },
    {
      "epoch": 1.424569164132338,
      "grad_norm": 0.4626993238925934,
      "learning_rate": 3.825688093556926e-06,
      "loss": 0.4891,
      "step": 46374
    },
    {
      "epoch": 1.4245998832672873,
      "grad_norm": 0.41499945521354675,
      "learning_rate": 3.825307942783457e-06,
      "loss": 0.5055,
      "step": 46375
    },
    {
      "epoch": 1.4246306024022364,
      "grad_norm": 0.4147201478481293,
      "learning_rate": 3.824927806431413e-06,
      "loss": 0.4968,
      "step": 46376
    },
    {
      "epoch": 1.4246613215371855,
      "grad_norm": 0.3918655812740326,
      "learning_rate": 3.824547684501682e-06,
      "loss": 0.4721,
      "step": 46377
    },
    {
      "epoch": 1.4246920406721346,
      "grad_norm": 0.42654040455818176,
      "learning_rate": 3.8241675769951535e-06,
      "loss": 0.4587,
      "step": 46378
    },
    {
      "epoch": 1.424722759807084,
      "grad_norm": 0.4903406798839569,
      "learning_rate": 3.8237874839127095e-06,
      "loss": 0.4671,
      "step": 46379
    },
    {
      "epoch": 1.424753478942033,
      "grad_norm": 0.5018618106842041,
      "learning_rate": 3.8234074052552425e-06,
      "loss": 0.509,
      "step": 46380
    },
    {
      "epoch": 1.4247841980769822,
      "grad_norm": 0.44660720229148865,
      "learning_rate": 3.823027341023638e-06,
      "loss": 0.4515,
      "step": 46381
    },
    {
      "epoch": 1.4248149172119313,
      "grad_norm": 0.4560619294643402,
      "learning_rate": 3.822647291218789e-06,
      "loss": 0.5265,
      "step": 46382
    },
    {
      "epoch": 1.4248456363468804,
      "grad_norm": 0.4430846869945526,
      "learning_rate": 3.822267255841573e-06,
      "loss": 0.4908,
      "step": 46383
    },
    {
      "epoch": 1.4248763554818296,
      "grad_norm": 0.47581946849823,
      "learning_rate": 3.821887234892885e-06,
      "loss": 0.4797,
      "step": 46384
    },
    {
      "epoch": 1.4249070746167787,
      "grad_norm": 0.3749464452266693,
      "learning_rate": 3.82150722837361e-06,
      "loss": 0.4233,
      "step": 46385
    },
    {
      "epoch": 1.424937793751728,
      "grad_norm": 0.41340944170951843,
      "learning_rate": 3.821127236284636e-06,
      "loss": 0.4428,
      "step": 46386
    },
    {
      "epoch": 1.4249685128866771,
      "grad_norm": 0.4356541633605957,
      "learning_rate": 3.820747258626856e-06,
      "loss": 0.4754,
      "step": 46387
    },
    {
      "epoch": 1.4249992320216263,
      "grad_norm": 0.39909306168556213,
      "learning_rate": 3.8203672954011475e-06,
      "loss": 0.4724,
      "step": 46388
    },
    {
      "epoch": 1.4250299511565754,
      "grad_norm": 0.4075073301792145,
      "learning_rate": 3.819987346608404e-06,
      "loss": 0.443,
      "step": 46389
    },
    {
      "epoch": 1.4250606702915247,
      "grad_norm": 0.4221667945384979,
      "learning_rate": 3.81960741224951e-06,
      "loss": 0.4654,
      "step": 46390
    },
    {
      "epoch": 1.4250913894264738,
      "grad_norm": 0.4329014718532562,
      "learning_rate": 3.819227492325359e-06,
      "loss": 0.4307,
      "step": 46391
    },
    {
      "epoch": 1.425122108561423,
      "grad_norm": 0.41634777188301086,
      "learning_rate": 3.81884758683683e-06,
      "loss": 0.4903,
      "step": 46392
    },
    {
      "epoch": 1.425152827696372,
      "grad_norm": 0.4434964954853058,
      "learning_rate": 3.818467695784814e-06,
      "loss": 0.494,
      "step": 46393
    },
    {
      "epoch": 1.4251835468313212,
      "grad_norm": 0.39573678374290466,
      "learning_rate": 3.8180878191701984e-06,
      "loss": 0.422,
      "step": 46394
    },
    {
      "epoch": 1.4252142659662703,
      "grad_norm": 0.38513192534446716,
      "learning_rate": 3.817707956993875e-06,
      "loss": 0.4704,
      "step": 46395
    },
    {
      "epoch": 1.4252449851012194,
      "grad_norm": 0.4286717176437378,
      "learning_rate": 3.817328109256721e-06,
      "loss": 0.4426,
      "step": 46396
    },
    {
      "epoch": 1.4252757042361688,
      "grad_norm": 0.4439001977443695,
      "learning_rate": 3.816948275959635e-06,
      "loss": 0.5508,
      "step": 46397
    },
    {
      "epoch": 1.425306423371118,
      "grad_norm": 0.4536537528038025,
      "learning_rate": 3.81656845710349e-06,
      "loss": 0.5396,
      "step": 46398
    },
    {
      "epoch": 1.425337142506067,
      "grad_norm": 0.5508306622505188,
      "learning_rate": 3.816188652689187e-06,
      "loss": 0.3334,
      "step": 46399
    },
    {
      "epoch": 1.4253678616410161,
      "grad_norm": 0.4885486364364624,
      "learning_rate": 3.815808862717606e-06,
      "loss": 0.5343,
      "step": 46400
    },
    {
      "epoch": 1.4253985807759655,
      "grad_norm": 0.41150471568107605,
      "learning_rate": 3.815429087189634e-06,
      "loss": 0.4541,
      "step": 46401
    },
    {
      "epoch": 1.4254292999109146,
      "grad_norm": 0.4519699811935425,
      "learning_rate": 3.81504932610616e-06,
      "loss": 0.5287,
      "step": 46402
    },
    {
      "epoch": 1.4254600190458637,
      "grad_norm": 0.4329091012477875,
      "learning_rate": 3.8146695794680687e-06,
      "loss": 0.488,
      "step": 46403
    },
    {
      "epoch": 1.4254907381808128,
      "grad_norm": 0.467244952917099,
      "learning_rate": 3.8142898472762536e-06,
      "loss": 0.4924,
      "step": 46404
    },
    {
      "epoch": 1.425521457315762,
      "grad_norm": 0.4476528465747833,
      "learning_rate": 3.8139101295315918e-06,
      "loss": 0.5236,
      "step": 46405
    },
    {
      "epoch": 1.425552176450711,
      "grad_norm": 0.44716212153434753,
      "learning_rate": 3.8135304262349793e-06,
      "loss": 0.42,
      "step": 46406
    },
    {
      "epoch": 1.4255828955856602,
      "grad_norm": 0.43436142802238464,
      "learning_rate": 3.813150737387291e-06,
      "loss": 0.5095,
      "step": 46407
    },
    {
      "epoch": 1.4256136147206095,
      "grad_norm": 0.45185956358909607,
      "learning_rate": 3.812771062989429e-06,
      "loss": 0.4995,
      "step": 46408
    },
    {
      "epoch": 1.4256443338555587,
      "grad_norm": 0.40793341398239136,
      "learning_rate": 3.812391403042268e-06,
      "loss": 0.4655,
      "step": 46409
    },
    {
      "epoch": 1.4256750529905078,
      "grad_norm": 0.3984566032886505,
      "learning_rate": 3.812011757546703e-06,
      "loss": 0.4585,
      "step": 46410
    },
    {
      "epoch": 1.425705772125457,
      "grad_norm": 0.600867748260498,
      "learning_rate": 3.811632126503614e-06,
      "loss": 0.548,
      "step": 46411
    },
    {
      "epoch": 1.425736491260406,
      "grad_norm": 0.4226735234260559,
      "learning_rate": 3.8112525099138887e-06,
      "loss": 0.5007,
      "step": 46412
    },
    {
      "epoch": 1.4257672103953554,
      "grad_norm": 0.401551753282547,
      "learning_rate": 3.810872907778417e-06,
      "loss": 0.4562,
      "step": 46413
    },
    {
      "epoch": 1.4257979295303045,
      "grad_norm": 0.4221324026584625,
      "learning_rate": 3.8104933200980852e-06,
      "loss": 0.4842,
      "step": 46414
    },
    {
      "epoch": 1.4258286486652536,
      "grad_norm": 0.42753201723098755,
      "learning_rate": 3.810113746873777e-06,
      "loss": 0.4608,
      "step": 46415
    },
    {
      "epoch": 1.4258593678002027,
      "grad_norm": 0.39716410636901855,
      "learning_rate": 3.8097341881063798e-06,
      "loss": 0.4312,
      "step": 46416
    },
    {
      "epoch": 1.4258900869351518,
      "grad_norm": 0.3971368968486786,
      "learning_rate": 3.809354643796781e-06,
      "loss": 0.4901,
      "step": 46417
    },
    {
      "epoch": 1.425920806070101,
      "grad_norm": 0.4450935125350952,
      "learning_rate": 3.8089751139458695e-06,
      "loss": 0.4942,
      "step": 46418
    },
    {
      "epoch": 1.4259515252050503,
      "grad_norm": 0.44909822940826416,
      "learning_rate": 3.8085955985545264e-06,
      "loss": 0.5013,
      "step": 46419
    },
    {
      "epoch": 1.4259822443399994,
      "grad_norm": 0.4113524258136749,
      "learning_rate": 3.8082160976236404e-06,
      "loss": 0.4213,
      "step": 46420
    },
    {
      "epoch": 1.4260129634749485,
      "grad_norm": 0.42745426297187805,
      "learning_rate": 3.8078366111540974e-06,
      "loss": 0.5019,
      "step": 46421
    },
    {
      "epoch": 1.4260436826098977,
      "grad_norm": 0.38769885897636414,
      "learning_rate": 3.8074571391467853e-06,
      "loss": 0.4761,
      "step": 46422
    },
    {
      "epoch": 1.4260744017448468,
      "grad_norm": 0.40410441160202026,
      "learning_rate": 3.807077681602592e-06,
      "loss": 0.5102,
      "step": 46423
    },
    {
      "epoch": 1.4261051208797961,
      "grad_norm": 0.44856101274490356,
      "learning_rate": 3.806698238522399e-06,
      "loss": 0.4,
      "step": 46424
    },
    {
      "epoch": 1.4261358400147452,
      "grad_norm": 0.407642662525177,
      "learning_rate": 3.8063188099070946e-06,
      "loss": 0.4698,
      "step": 46425
    },
    {
      "epoch": 1.4261665591496944,
      "grad_norm": 0.42233186960220337,
      "learning_rate": 3.8059393957575652e-06,
      "loss": 0.4738,
      "step": 46426
    },
    {
      "epoch": 1.4261972782846435,
      "grad_norm": 0.4456698000431061,
      "learning_rate": 3.8055599960747004e-06,
      "loss": 0.4138,
      "step": 46427
    },
    {
      "epoch": 1.4262279974195926,
      "grad_norm": 0.4266923666000366,
      "learning_rate": 3.805180610859379e-06,
      "loss": 0.4507,
      "step": 46428
    },
    {
      "epoch": 1.4262587165545417,
      "grad_norm": 0.3981735110282898,
      "learning_rate": 3.8048012401124913e-06,
      "loss": 0.4236,
      "step": 46429
    },
    {
      "epoch": 1.4262894356894908,
      "grad_norm": 0.4244014620780945,
      "learning_rate": 3.8044218838349223e-06,
      "loss": 0.5426,
      "step": 46430
    },
    {
      "epoch": 1.4263201548244402,
      "grad_norm": 0.40480437874794006,
      "learning_rate": 3.8040425420275627e-06,
      "loss": 0.4222,
      "step": 46431
    },
    {
      "epoch": 1.4263508739593893,
      "grad_norm": 0.5430375337600708,
      "learning_rate": 3.803663214691291e-06,
      "loss": 0.4987,
      "step": 46432
    },
    {
      "epoch": 1.4263815930943384,
      "grad_norm": 0.40138936042785645,
      "learning_rate": 3.8032839018269998e-06,
      "loss": 0.4618,
      "step": 46433
    },
    {
      "epoch": 1.4264123122292875,
      "grad_norm": 0.3945266604423523,
      "learning_rate": 3.8029046034355654e-06,
      "loss": 0.5066,
      "step": 46434
    },
    {
      "epoch": 1.426443031364237,
      "grad_norm": 0.4557899832725525,
      "learning_rate": 3.8025253195178857e-06,
      "loss": 0.4111,
      "step": 46435
    },
    {
      "epoch": 1.426473750499186,
      "grad_norm": 0.415164053440094,
      "learning_rate": 3.8021460500748387e-06,
      "loss": 0.4113,
      "step": 46436
    },
    {
      "epoch": 1.4265044696341351,
      "grad_norm": 0.4525848925113678,
      "learning_rate": 3.801766795107316e-06,
      "loss": 0.4754,
      "step": 46437
    },
    {
      "epoch": 1.4265351887690843,
      "grad_norm": 0.4144297242164612,
      "learning_rate": 3.801387554616196e-06,
      "loss": 0.5157,
      "step": 46438
    },
    {
      "epoch": 1.4265659079040334,
      "grad_norm": 0.3935185968875885,
      "learning_rate": 3.8010083286023648e-06,
      "loss": 0.4578,
      "step": 46439
    },
    {
      "epoch": 1.4265966270389825,
      "grad_norm": 0.4142798185348511,
      "learning_rate": 3.800629117066719e-06,
      "loss": 0.4965,
      "step": 46440
    },
    {
      "epoch": 1.4266273461739316,
      "grad_norm": 0.41782698035240173,
      "learning_rate": 3.800249920010133e-06,
      "loss": 0.4172,
      "step": 46441
    },
    {
      "epoch": 1.426658065308881,
      "grad_norm": 0.4165186285972595,
      "learning_rate": 3.7998707374335e-06,
      "loss": 0.4548,
      "step": 46442
    },
    {
      "epoch": 1.42668878444383,
      "grad_norm": 0.4441128969192505,
      "learning_rate": 3.7994915693376943e-06,
      "loss": 0.4283,
      "step": 46443
    },
    {
      "epoch": 1.4267195035787792,
      "grad_norm": 0.40812933444976807,
      "learning_rate": 3.799112415723616e-06,
      "loss": 0.5205,
      "step": 46444
    },
    {
      "epoch": 1.4267502227137283,
      "grad_norm": 0.40135428309440613,
      "learning_rate": 3.79873327659214e-06,
      "loss": 0.4359,
      "step": 46445
    },
    {
      "epoch": 1.4267809418486777,
      "grad_norm": 0.4383387565612793,
      "learning_rate": 3.7983541519441602e-06,
      "loss": 0.4688,
      "step": 46446
    },
    {
      "epoch": 1.4268116609836268,
      "grad_norm": 0.4142245650291443,
      "learning_rate": 3.797975041780554e-06,
      "loss": 0.5022,
      "step": 46447
    },
    {
      "epoch": 1.426842380118576,
      "grad_norm": 0.41362613439559937,
      "learning_rate": 3.7975959461022095e-06,
      "loss": 0.4482,
      "step": 46448
    },
    {
      "epoch": 1.426873099253525,
      "grad_norm": 0.4182348847389221,
      "learning_rate": 3.797216864910013e-06,
      "loss": 0.4109,
      "step": 46449
    },
    {
      "epoch": 1.4269038183884741,
      "grad_norm": 0.45516008138656616,
      "learning_rate": 3.796837798204853e-06,
      "loss": 0.4982,
      "step": 46450
    },
    {
      "epoch": 1.4269345375234233,
      "grad_norm": 0.43999239802360535,
      "learning_rate": 3.796458745987608e-06,
      "loss": 0.4641,
      "step": 46451
    },
    {
      "epoch": 1.4269652566583724,
      "grad_norm": 0.40454065799713135,
      "learning_rate": 3.796079708259167e-06,
      "loss": 0.4639,
      "step": 46452
    },
    {
      "epoch": 1.4269959757933217,
      "grad_norm": 0.4187926650047302,
      "learning_rate": 3.795700685020415e-06,
      "loss": 0.448,
      "step": 46453
    },
    {
      "epoch": 1.4270266949282708,
      "grad_norm": 0.46610227227211,
      "learning_rate": 3.7953216762722412e-06,
      "loss": 0.4322,
      "step": 46454
    },
    {
      "epoch": 1.42705741406322,
      "grad_norm": 0.41363325715065,
      "learning_rate": 3.7949426820155235e-06,
      "loss": 0.5022,
      "step": 46455
    },
    {
      "epoch": 1.427088133198169,
      "grad_norm": 0.4077587127685547,
      "learning_rate": 3.7945637022511494e-06,
      "loss": 0.5103,
      "step": 46456
    },
    {
      "epoch": 1.4271188523331184,
      "grad_norm": 0.42984092235565186,
      "learning_rate": 3.7941847369800067e-06,
      "loss": 0.5382,
      "step": 46457
    },
    {
      "epoch": 1.4271495714680675,
      "grad_norm": 0.4218205213546753,
      "learning_rate": 3.7938057862029788e-06,
      "loss": 0.4286,
      "step": 46458
    },
    {
      "epoch": 1.4271802906030167,
      "grad_norm": 0.46893981099128723,
      "learning_rate": 3.7934268499209538e-06,
      "loss": 0.4082,
      "step": 46459
    },
    {
      "epoch": 1.4272110097379658,
      "grad_norm": 0.39100271463394165,
      "learning_rate": 3.7930479281348097e-06,
      "loss": 0.5133,
      "step": 46460
    },
    {
      "epoch": 1.427241728872915,
      "grad_norm": 0.4248569905757904,
      "learning_rate": 3.7926690208454363e-06,
      "loss": 0.5358,
      "step": 46461
    },
    {
      "epoch": 1.427272448007864,
      "grad_norm": 0.42883166670799255,
      "learning_rate": 3.7922901280537183e-06,
      "loss": 0.4736,
      "step": 46462
    },
    {
      "epoch": 1.4273031671428131,
      "grad_norm": 0.4496757686138153,
      "learning_rate": 3.791911249760544e-06,
      "loss": 0.4997,
      "step": 46463
    },
    {
      "epoch": 1.4273338862777625,
      "grad_norm": 0.4695233106613159,
      "learning_rate": 3.7915323859667895e-06,
      "loss": 0.4754,
      "step": 46464
    },
    {
      "epoch": 1.4273646054127116,
      "grad_norm": 0.39774778485298157,
      "learning_rate": 3.7911535366733465e-06,
      "loss": 0.4681,
      "step": 46465
    },
    {
      "epoch": 1.4273953245476607,
      "grad_norm": 0.4467059373855591,
      "learning_rate": 3.790774701881097e-06,
      "loss": 0.4907,
      "step": 46466
    },
    {
      "epoch": 1.4274260436826098,
      "grad_norm": 0.4195898771286011,
      "learning_rate": 3.7903958815909304e-06,
      "loss": 0.4279,
      "step": 46467
    },
    {
      "epoch": 1.4274567628175592,
      "grad_norm": 0.4266913831233978,
      "learning_rate": 3.7900170758037245e-06,
      "loss": 0.5337,
      "step": 46468
    },
    {
      "epoch": 1.4274874819525083,
      "grad_norm": 0.39211714267730713,
      "learning_rate": 3.789638284520372e-06,
      "loss": 0.4373,
      "step": 46469
    },
    {
      "epoch": 1.4275182010874574,
      "grad_norm": 0.45907706022262573,
      "learning_rate": 3.7892595077417447e-06,
      "loss": 0.5115,
      "step": 46470
    },
    {
      "epoch": 1.4275489202224065,
      "grad_norm": 0.4024854004383087,
      "learning_rate": 3.7888807454687427e-06,
      "loss": 0.4887,
      "step": 46471
    },
    {
      "epoch": 1.4275796393573557,
      "grad_norm": 0.44556960463523865,
      "learning_rate": 3.7885019977022396e-06,
      "loss": 0.502,
      "step": 46472
    },
    {
      "epoch": 1.4276103584923048,
      "grad_norm": 0.4087890684604645,
      "learning_rate": 3.7881232644431286e-06,
      "loss": 0.5079,
      "step": 46473
    },
    {
      "epoch": 1.427641077627254,
      "grad_norm": 0.4701886773109436,
      "learning_rate": 3.787744545692286e-06,
      "loss": 0.4503,
      "step": 46474
    },
    {
      "epoch": 1.4276717967622032,
      "grad_norm": 0.45155489444732666,
      "learning_rate": 3.7873658414505953e-06,
      "loss": 0.4584,
      "step": 46475
    },
    {
      "epoch": 1.4277025158971524,
      "grad_norm": 0.418201744556427,
      "learning_rate": 3.7869871517189527e-06,
      "loss": 0.5457,
      "step": 46476
    },
    {
      "epoch": 1.4277332350321015,
      "grad_norm": 0.41833874583244324,
      "learning_rate": 3.7866084764982325e-06,
      "loss": 0.4423,
      "step": 46477
    },
    {
      "epoch": 1.4277639541670506,
      "grad_norm": 0.41709041595458984,
      "learning_rate": 3.7862298157893264e-06,
      "loss": 0.42,
      "step": 46478
    },
    {
      "epoch": 1.427794673302,
      "grad_norm": 0.45680081844329834,
      "learning_rate": 3.78585116959311e-06,
      "loss": 0.4232,
      "step": 46479
    },
    {
      "epoch": 1.427825392436949,
      "grad_norm": 0.4468136131763458,
      "learning_rate": 3.7854725379104717e-06,
      "loss": 0.5852,
      "step": 46480
    },
    {
      "epoch": 1.4278561115718982,
      "grad_norm": 0.42546287178993225,
      "learning_rate": 3.7850939207422977e-06,
      "loss": 0.4512,
      "step": 46481
    },
    {
      "epoch": 1.4278868307068473,
      "grad_norm": 0.4359864294528961,
      "learning_rate": 3.7847153180894736e-06,
      "loss": 0.5494,
      "step": 46482
    },
    {
      "epoch": 1.4279175498417964,
      "grad_norm": 0.4161263704299927,
      "learning_rate": 3.7843367299528766e-06,
      "loss": 0.4835,
      "step": 46483
    },
    {
      "epoch": 1.4279482689767455,
      "grad_norm": 0.45057815313339233,
      "learning_rate": 3.783958156333396e-06,
      "loss": 0.4517,
      "step": 46484
    },
    {
      "epoch": 1.4279789881116947,
      "grad_norm": 0.4126989543437958,
      "learning_rate": 3.7835795972319156e-06,
      "loss": 0.4973,
      "step": 46485
    },
    {
      "epoch": 1.428009707246644,
      "grad_norm": 0.4529453217983246,
      "learning_rate": 3.7832010526493224e-06,
      "loss": 0.4978,
      "step": 46486
    },
    {
      "epoch": 1.4280404263815931,
      "grad_norm": 0.40623176097869873,
      "learning_rate": 3.7828225225864947e-06,
      "loss": 0.4772,
      "step": 46487
    },
    {
      "epoch": 1.4280711455165422,
      "grad_norm": 0.4309171140193939,
      "learning_rate": 3.782444007044318e-06,
      "loss": 0.4994,
      "step": 46488
    },
    {
      "epoch": 1.4281018646514914,
      "grad_norm": 0.3988184630870819,
      "learning_rate": 3.7820655060236777e-06,
      "loss": 0.4618,
      "step": 46489
    },
    {
      "epoch": 1.4281325837864407,
      "grad_norm": 0.4270469844341278,
      "learning_rate": 3.7816870195254617e-06,
      "loss": 0.4942,
      "step": 46490
    },
    {
      "epoch": 1.4281633029213898,
      "grad_norm": 0.4007999897003174,
      "learning_rate": 3.7813085475505463e-06,
      "loss": 0.4117,
      "step": 46491
    },
    {
      "epoch": 1.428194022056339,
      "grad_norm": 0.39779549837112427,
      "learning_rate": 3.780930090099819e-06,
      "loss": 0.5016,
      "step": 46492
    },
    {
      "epoch": 1.428224741191288,
      "grad_norm": 0.4622005820274353,
      "learning_rate": 3.7805516471741643e-06,
      "loss": 0.4755,
      "step": 46493
    },
    {
      "epoch": 1.4282554603262372,
      "grad_norm": 0.4568188488483429,
      "learning_rate": 3.7801732187744645e-06,
      "loss": 0.4917,
      "step": 46494
    },
    {
      "epoch": 1.4282861794611863,
      "grad_norm": 0.4170210063457489,
      "learning_rate": 3.7797948049016086e-06,
      "loss": 0.4402,
      "step": 46495
    },
    {
      "epoch": 1.4283168985961354,
      "grad_norm": 0.4138351082801819,
      "learning_rate": 3.779416405556473e-06,
      "loss": 0.473,
      "step": 46496
    },
    {
      "epoch": 1.4283476177310848,
      "grad_norm": 0.46647146344184875,
      "learning_rate": 3.7790380207399447e-06,
      "loss": 0.5076,
      "step": 46497
    },
    {
      "epoch": 1.4283783368660339,
      "grad_norm": 0.4401687979698181,
      "learning_rate": 3.778659650452907e-06,
      "loss": 0.5427,
      "step": 46498
    },
    {
      "epoch": 1.428409056000983,
      "grad_norm": 0.3662014901638031,
      "learning_rate": 3.778281294696249e-06,
      "loss": 0.464,
      "step": 46499
    },
    {
      "epoch": 1.4284397751359321,
      "grad_norm": 0.3795797824859619,
      "learning_rate": 3.7779029534708456e-06,
      "loss": 0.5281,
      "step": 46500
    },
    {
      "epoch": 1.4284704942708815,
      "grad_norm": 0.4114103615283966,
      "learning_rate": 3.777524626777587e-06,
      "loss": 0.5456,
      "step": 46501
    },
    {
      "epoch": 1.4285012134058306,
      "grad_norm": 0.4088037610054016,
      "learning_rate": 3.777146314617348e-06,
      "loss": 0.5317,
      "step": 46502
    },
    {
      "epoch": 1.4285319325407797,
      "grad_norm": 0.39187493920326233,
      "learning_rate": 3.7767680169910247e-06,
      "loss": 0.4749,
      "step": 46503
    },
    {
      "epoch": 1.4285626516757288,
      "grad_norm": 0.4397393465042114,
      "learning_rate": 3.7763897338994913e-06,
      "loss": 0.4888,
      "step": 46504
    },
    {
      "epoch": 1.428593370810678,
      "grad_norm": 0.42519038915634155,
      "learning_rate": 3.7760114653436386e-06,
      "loss": 0.5132,
      "step": 46505
    },
    {
      "epoch": 1.428624089945627,
      "grad_norm": 0.4056095480918884,
      "learning_rate": 3.7756332113243376e-06,
      "loss": 0.4203,
      "step": 46506
    },
    {
      "epoch": 1.4286548090805762,
      "grad_norm": 0.4359270930290222,
      "learning_rate": 3.775254971842488e-06,
      "loss": 0.4303,
      "step": 46507
    },
    {
      "epoch": 1.4286855282155255,
      "grad_norm": 0.40274274349212646,
      "learning_rate": 3.77487674689896e-06,
      "loss": 0.4444,
      "step": 46508
    },
    {
      "epoch": 1.4287162473504746,
      "grad_norm": 0.3897020220756531,
      "learning_rate": 3.7744985364946476e-06,
      "loss": 0.4695,
      "step": 46509
    },
    {
      "epoch": 1.4287469664854238,
      "grad_norm": 0.4217778742313385,
      "learning_rate": 3.774120340630424e-06,
      "loss": 0.4391,
      "step": 46510
    },
    {
      "epoch": 1.4287776856203729,
      "grad_norm": 0.4588288366794586,
      "learning_rate": 3.7737421593071732e-06,
      "loss": 0.5333,
      "step": 46511
    },
    {
      "epoch": 1.4288084047553222,
      "grad_norm": 0.4419965445995331,
      "learning_rate": 3.77336399252579e-06,
      "loss": 0.5128,
      "step": 46512
    },
    {
      "epoch": 1.4288391238902713,
      "grad_norm": 0.41196390986442566,
      "learning_rate": 3.7729858402871467e-06,
      "loss": 0.4011,
      "step": 46513
    },
    {
      "epoch": 1.4288698430252205,
      "grad_norm": 0.42030879855155945,
      "learning_rate": 3.7726077025921335e-06,
      "loss": 0.4506,
      "step": 46514
    },
    {
      "epoch": 1.4289005621601696,
      "grad_norm": 0.4035528600215912,
      "learning_rate": 3.7722295794416264e-06,
      "loss": 0.4836,
      "step": 46515
    },
    {
      "epoch": 1.4289312812951187,
      "grad_norm": 0.4429675340652466,
      "learning_rate": 3.7718514708365117e-06,
      "loss": 0.4477,
      "step": 46516
    },
    {
      "epoch": 1.4289620004300678,
      "grad_norm": 0.4425089955329895,
      "learning_rate": 3.7714733767776734e-06,
      "loss": 0.5629,
      "step": 46517
    },
    {
      "epoch": 1.428992719565017,
      "grad_norm": 0.47564074397087097,
      "learning_rate": 3.7710952972659963e-06,
      "loss": 0.507,
      "step": 46518
    },
    {
      "epoch": 1.4290234386999663,
      "grad_norm": 0.4300686717033386,
      "learning_rate": 3.770717232302359e-06,
      "loss": 0.4914,
      "step": 46519
    },
    {
      "epoch": 1.4290541578349154,
      "grad_norm": 0.38743385672569275,
      "learning_rate": 3.7703391818876468e-06,
      "loss": 0.4515,
      "step": 46520
    },
    {
      "epoch": 1.4290848769698645,
      "grad_norm": 0.4049651622772217,
      "learning_rate": 3.7699611460227413e-06,
      "loss": 0.525,
      "step": 46521
    },
    {
      "epoch": 1.4291155961048136,
      "grad_norm": 0.39475148916244507,
      "learning_rate": 3.7695831247085313e-06,
      "loss": 0.4473,
      "step": 46522
    },
    {
      "epoch": 1.4291463152397628,
      "grad_norm": 0.45379751920700073,
      "learning_rate": 3.76920511794589e-06,
      "loss": 0.4486,
      "step": 46523
    },
    {
      "epoch": 1.429177034374712,
      "grad_norm": 0.40982770919799805,
      "learning_rate": 3.768827125735707e-06,
      "loss": 0.4346,
      "step": 46524
    },
    {
      "epoch": 1.4292077535096612,
      "grad_norm": 0.4163609743118286,
      "learning_rate": 3.768449148078862e-06,
      "loss": 0.3893,
      "step": 46525
    },
    {
      "epoch": 1.4292384726446103,
      "grad_norm": 0.4370836019515991,
      "learning_rate": 3.768071184976244e-06,
      "loss": 0.3587,
      "step": 46526
    },
    {
      "epoch": 1.4292691917795595,
      "grad_norm": 0.4433988034725189,
      "learning_rate": 3.7676932364287265e-06,
      "loss": 0.5618,
      "step": 46527
    },
    {
      "epoch": 1.4292999109145086,
      "grad_norm": 0.46237799525260925,
      "learning_rate": 3.767315302437198e-06,
      "loss": 0.5019,
      "step": 46528
    },
    {
      "epoch": 1.4293306300494577,
      "grad_norm": 0.45156288146972656,
      "learning_rate": 3.7669373830025378e-06,
      "loss": 0.4359,
      "step": 46529
    },
    {
      "epoch": 1.429361349184407,
      "grad_norm": 0.42093873023986816,
      "learning_rate": 3.766559478125632e-06,
      "loss": 0.4244,
      "step": 46530
    },
    {
      "epoch": 1.4293920683193562,
      "grad_norm": 0.4187774956226349,
      "learning_rate": 3.766181587807366e-06,
      "loss": 0.5006,
      "step": 46531
    },
    {
      "epoch": 1.4294227874543053,
      "grad_norm": 0.4174426198005676,
      "learning_rate": 3.7658037120486137e-06,
      "loss": 0.49,
      "step": 46532
    },
    {
      "epoch": 1.4294535065892544,
      "grad_norm": 0.421212762594223,
      "learning_rate": 3.7654258508502626e-06,
      "loss": 0.5151,
      "step": 46533
    },
    {
      "epoch": 1.4294842257242035,
      "grad_norm": 0.4121565520763397,
      "learning_rate": 3.7650480042131944e-06,
      "loss": 0.4427,
      "step": 46534
    },
    {
      "epoch": 1.4295149448591529,
      "grad_norm": 0.4651801884174347,
      "learning_rate": 3.7646701721382963e-06,
      "loss": 0.506,
      "step": 46535
    },
    {
      "epoch": 1.429545663994102,
      "grad_norm": 0.4396337568759918,
      "learning_rate": 3.764292354626442e-06,
      "loss": 0.4731,
      "step": 46536
    },
    {
      "epoch": 1.429576383129051,
      "grad_norm": 0.43608662486076355,
      "learning_rate": 3.7639145516785225e-06,
      "loss": 0.3651,
      "step": 46537
    },
    {
      "epoch": 1.4296071022640002,
      "grad_norm": 0.40504470467567444,
      "learning_rate": 3.7635367632954088e-06,
      "loss": 0.3718,
      "step": 46538
    },
    {
      "epoch": 1.4296378213989493,
      "grad_norm": 0.44606244564056396,
      "learning_rate": 3.7631589894779985e-06,
      "loss": 0.4583,
      "step": 46539
    },
    {
      "epoch": 1.4296685405338985,
      "grad_norm": 0.4283830523490906,
      "learning_rate": 3.7627812302271616e-06,
      "loss": 0.526,
      "step": 46540
    },
    {
      "epoch": 1.4296992596688476,
      "grad_norm": 0.42828014492988586,
      "learning_rate": 3.7624034855437884e-06,
      "loss": 0.4594,
      "step": 46541
    },
    {
      "epoch": 1.429729978803797,
      "grad_norm": 0.37624090909957886,
      "learning_rate": 3.762025755428754e-06,
      "loss": 0.4344,
      "step": 46542
    },
    {
      "epoch": 1.429760697938746,
      "grad_norm": 0.40114665031433105,
      "learning_rate": 3.7616480398829438e-06,
      "loss": 0.4081,
      "step": 46543
    },
    {
      "epoch": 1.4297914170736952,
      "grad_norm": 0.42107802629470825,
      "learning_rate": 3.7612703389072414e-06,
      "loss": 0.4432,
      "step": 46544
    },
    {
      "epoch": 1.4298221362086443,
      "grad_norm": 0.4888668954372406,
      "learning_rate": 3.76089265250253e-06,
      "loss": 0.4218,
      "step": 46545
    },
    {
      "epoch": 1.4298528553435936,
      "grad_norm": 0.4039425551891327,
      "learning_rate": 3.7605149806696862e-06,
      "loss": 0.4753,
      "step": 46546
    },
    {
      "epoch": 1.4298835744785428,
      "grad_norm": 0.4080584943294525,
      "learning_rate": 3.7601373234095927e-06,
      "loss": 0.4061,
      "step": 46547
    },
    {
      "epoch": 1.4299142936134919,
      "grad_norm": 0.40093931555747986,
      "learning_rate": 3.7597596807231407e-06,
      "loss": 0.5131,
      "step": 46548
    },
    {
      "epoch": 1.429945012748441,
      "grad_norm": 0.41401177644729614,
      "learning_rate": 3.7593820526112025e-06,
      "loss": 0.4672,
      "step": 46549
    },
    {
      "epoch": 1.42997573188339,
      "grad_norm": 0.4331601560115814,
      "learning_rate": 3.7590044390746673e-06,
      "loss": 0.3886,
      "step": 46550
    },
    {
      "epoch": 1.4300064510183392,
      "grad_norm": 0.4869828224182129,
      "learning_rate": 3.758626840114409e-06,
      "loss": 0.4248,
      "step": 46551
    },
    {
      "epoch": 1.4300371701532884,
      "grad_norm": 0.4028763473033905,
      "learning_rate": 3.7582492557313133e-06,
      "loss": 0.4652,
      "step": 46552
    },
    {
      "epoch": 1.4300678892882377,
      "grad_norm": 0.47530612349510193,
      "learning_rate": 3.7578716859262633e-06,
      "loss": 0.472,
      "step": 46553
    },
    {
      "epoch": 1.4300986084231868,
      "grad_norm": 0.4417145848274231,
      "learning_rate": 3.7574941307001423e-06,
      "loss": 0.4916,
      "step": 46554
    },
    {
      "epoch": 1.430129327558136,
      "grad_norm": 0.4397246539592743,
      "learning_rate": 3.7571165900538266e-06,
      "loss": 0.4961,
      "step": 46555
    },
    {
      "epoch": 1.430160046693085,
      "grad_norm": 0.4067676067352295,
      "learning_rate": 3.756739063988202e-06,
      "loss": 0.3447,
      "step": 46556
    },
    {
      "epoch": 1.4301907658280344,
      "grad_norm": 0.42476147413253784,
      "learning_rate": 3.7563615525041485e-06,
      "loss": 0.4713,
      "step": 46557
    },
    {
      "epoch": 1.4302214849629835,
      "grad_norm": 0.40021800994873047,
      "learning_rate": 3.7559840556025517e-06,
      "loss": 0.4832,
      "step": 46558
    },
    {
      "epoch": 1.4302522040979326,
      "grad_norm": 0.4432121515274048,
      "learning_rate": 3.7556065732842872e-06,
      "loss": 0.4591,
      "step": 46559
    },
    {
      "epoch": 1.4302829232328818,
      "grad_norm": 0.4051969349384308,
      "learning_rate": 3.75522910555024e-06,
      "loss": 0.4531,
      "step": 46560
    },
    {
      "epoch": 1.4303136423678309,
      "grad_norm": 0.4259048104286194,
      "learning_rate": 3.7548516524012914e-06,
      "loss": 0.471,
      "step": 46561
    },
    {
      "epoch": 1.43034436150278,
      "grad_norm": 0.3967142403125763,
      "learning_rate": 3.754474213838326e-06,
      "loss": 0.418,
      "step": 46562
    },
    {
      "epoch": 1.4303750806377291,
      "grad_norm": 0.4057334065437317,
      "learning_rate": 3.7540967898622193e-06,
      "loss": 0.4105,
      "step": 46563
    },
    {
      "epoch": 1.4304057997726785,
      "grad_norm": 0.42100846767425537,
      "learning_rate": 3.753719380473858e-06,
      "loss": 0.4675,
      "step": 46564
    },
    {
      "epoch": 1.4304365189076276,
      "grad_norm": 0.412045419216156,
      "learning_rate": 3.753341985674116e-06,
      "loss": 0.4065,
      "step": 46565
    },
    {
      "epoch": 1.4304672380425767,
      "grad_norm": 0.4172323942184448,
      "learning_rate": 3.7529646054638824e-06,
      "loss": 0.4852,
      "step": 46566
    },
    {
      "epoch": 1.4304979571775258,
      "grad_norm": 0.3809255361557007,
      "learning_rate": 3.75258723984404e-06,
      "loss": 0.4682,
      "step": 46567
    },
    {
      "epoch": 1.4305286763124752,
      "grad_norm": 0.5445944666862488,
      "learning_rate": 3.7522098888154633e-06,
      "loss": 0.5021,
      "step": 46568
    },
    {
      "epoch": 1.4305593954474243,
      "grad_norm": 0.4350604712963104,
      "learning_rate": 3.751832552379037e-06,
      "loss": 0.5083,
      "step": 46569
    },
    {
      "epoch": 1.4305901145823734,
      "grad_norm": 0.42683765292167664,
      "learning_rate": 3.751455230535641e-06,
      "loss": 0.4703,
      "step": 46570
    },
    {
      "epoch": 1.4306208337173225,
      "grad_norm": 0.4160262942314148,
      "learning_rate": 3.7510779232861616e-06,
      "loss": 0.5022,
      "step": 46571
    },
    {
      "epoch": 1.4306515528522716,
      "grad_norm": 0.4914558529853821,
      "learning_rate": 3.750700630631473e-06,
      "loss": 0.3993,
      "step": 46572
    },
    {
      "epoch": 1.4306822719872208,
      "grad_norm": 0.41559502482414246,
      "learning_rate": 3.7503233525724625e-06,
      "loss": 0.4521,
      "step": 46573
    },
    {
      "epoch": 1.4307129911221699,
      "grad_norm": 0.3766098916530609,
      "learning_rate": 3.7499460891100013e-06,
      "loss": 0.3873,
      "step": 46574
    },
    {
      "epoch": 1.4307437102571192,
      "grad_norm": 0.4491593837738037,
      "learning_rate": 3.749568840244985e-06,
      "loss": 0.4762,
      "step": 46575
    },
    {
      "epoch": 1.4307744293920683,
      "grad_norm": 0.43887314200401306,
      "learning_rate": 3.749191605978284e-06,
      "loss": 0.5151,
      "step": 46576
    },
    {
      "epoch": 1.4308051485270175,
      "grad_norm": 0.46758610010147095,
      "learning_rate": 3.748814386310785e-06,
      "loss": 0.5193,
      "step": 46577
    },
    {
      "epoch": 1.4308358676619666,
      "grad_norm": 0.3943038582801819,
      "learning_rate": 3.748437181243364e-06,
      "loss": 0.4562,
      "step": 46578
    },
    {
      "epoch": 1.430866586796916,
      "grad_norm": 0.42031538486480713,
      "learning_rate": 3.748059990776904e-06,
      "loss": 0.4888,
      "step": 46579
    },
    {
      "epoch": 1.430897305931865,
      "grad_norm": 0.4010298252105713,
      "learning_rate": 3.747682814912287e-06,
      "loss": 0.4346,
      "step": 46580
    },
    {
      "epoch": 1.4309280250668142,
      "grad_norm": 0.38839057087898254,
      "learning_rate": 3.747305653650397e-06,
      "loss": 0.4542,
      "step": 46581
    },
    {
      "epoch": 1.4309587442017633,
      "grad_norm": 0.4524748921394348,
      "learning_rate": 3.7469285069921068e-06,
      "loss": 0.4768,
      "step": 46582
    },
    {
      "epoch": 1.4309894633367124,
      "grad_norm": 0.4177570343017578,
      "learning_rate": 3.746551374938303e-06,
      "loss": 0.4751,
      "step": 46583
    },
    {
      "epoch": 1.4310201824716615,
      "grad_norm": 0.4123759865760803,
      "learning_rate": 3.7461742574898653e-06,
      "loss": 0.5039,
      "step": 46584
    },
    {
      "epoch": 1.4310509016066106,
      "grad_norm": 0.3942098617553711,
      "learning_rate": 3.7457971546476734e-06,
      "loss": 0.4447,
      "step": 46585
    },
    {
      "epoch": 1.43108162074156,
      "grad_norm": 0.40473827719688416,
      "learning_rate": 3.745420066412613e-06,
      "loss": 0.4155,
      "step": 46586
    },
    {
      "epoch": 1.431112339876509,
      "grad_norm": 0.40326932072639465,
      "learning_rate": 3.745042992785557e-06,
      "loss": 0.3818,
      "step": 46587
    },
    {
      "epoch": 1.4311430590114582,
      "grad_norm": 0.42878228425979614,
      "learning_rate": 3.7446659337673897e-06,
      "loss": 0.4879,
      "step": 46588
    },
    {
      "epoch": 1.4311737781464073,
      "grad_norm": 0.40216872096061707,
      "learning_rate": 3.7442888893589934e-06,
      "loss": 0.4562,
      "step": 46589
    },
    {
      "epoch": 1.4312044972813567,
      "grad_norm": 0.5886552333831787,
      "learning_rate": 3.743911859561249e-06,
      "loss": 0.4819,
      "step": 46590
    },
    {
      "epoch": 1.4312352164163058,
      "grad_norm": 0.4130038022994995,
      "learning_rate": 3.743534844375033e-06,
      "loss": 0.4252,
      "step": 46591
    },
    {
      "epoch": 1.431265935551255,
      "grad_norm": 0.4651221036911011,
      "learning_rate": 3.7431578438012284e-06,
      "loss": 0.4506,
      "step": 46592
    },
    {
      "epoch": 1.431296654686204,
      "grad_norm": 0.4319223165512085,
      "learning_rate": 3.7427808578407152e-06,
      "loss": 0.4512,
      "step": 46593
    },
    {
      "epoch": 1.4313273738211532,
      "grad_norm": 0.46507516503334045,
      "learning_rate": 3.742403886494378e-06,
      "loss": 0.5419,
      "step": 46594
    },
    {
      "epoch": 1.4313580929561023,
      "grad_norm": 0.41186052560806274,
      "learning_rate": 3.7420269297630895e-06,
      "loss": 0.4288,
      "step": 46595
    },
    {
      "epoch": 1.4313888120910514,
      "grad_norm": 0.45669519901275635,
      "learning_rate": 3.741649987647735e-06,
      "loss": 0.4322,
      "step": 46596
    },
    {
      "epoch": 1.4314195312260007,
      "grad_norm": 0.44587400555610657,
      "learning_rate": 3.741273060149193e-06,
      "loss": 0.4151,
      "step": 46597
    },
    {
      "epoch": 1.4314502503609499,
      "grad_norm": 0.45673564076423645,
      "learning_rate": 3.740896147268349e-06,
      "loss": 0.3816,
      "step": 46598
    },
    {
      "epoch": 1.431480969495899,
      "grad_norm": 0.4668623208999634,
      "learning_rate": 3.740519249006076e-06,
      "loss": 0.5299,
      "step": 46599
    },
    {
      "epoch": 1.431511688630848,
      "grad_norm": 0.38325777649879456,
      "learning_rate": 3.7401423653632605e-06,
      "loss": 0.4948,
      "step": 46600
    },
    {
      "epoch": 1.4315424077657974,
      "grad_norm": 0.5525982975959778,
      "learning_rate": 3.7397654963407736e-06,
      "loss": 0.4985,
      "step": 46601
    },
    {
      "epoch": 1.4315731269007466,
      "grad_norm": 0.44817250967025757,
      "learning_rate": 3.7393886419395043e-06,
      "loss": 0.5065,
      "step": 46602
    },
    {
      "epoch": 1.4316038460356957,
      "grad_norm": 0.4093174338340759,
      "learning_rate": 3.7390118021603327e-06,
      "loss": 0.5035,
      "step": 46603
    },
    {
      "epoch": 1.4316345651706448,
      "grad_norm": 0.4214560389518738,
      "learning_rate": 3.738634977004134e-06,
      "loss": 0.4056,
      "step": 46604
    },
    {
      "epoch": 1.431665284305594,
      "grad_norm": 0.4355604946613312,
      "learning_rate": 3.7382581664717943e-06,
      "loss": 0.4808,
      "step": 46605
    },
    {
      "epoch": 1.431696003440543,
      "grad_norm": 0.6370208859443665,
      "learning_rate": 3.7378813705641826e-06,
      "loss": 0.4791,
      "step": 46606
    },
    {
      "epoch": 1.4317267225754922,
      "grad_norm": 0.4015575647354126,
      "learning_rate": 3.7375045892821927e-06,
      "loss": 0.4893,
      "step": 46607
    },
    {
      "epoch": 1.4317574417104415,
      "grad_norm": 0.38918736577033997,
      "learning_rate": 3.737127822626695e-06,
      "loss": 0.3805,
      "step": 46608
    },
    {
      "epoch": 1.4317881608453906,
      "grad_norm": 0.44221556186676025,
      "learning_rate": 3.7367510705985767e-06,
      "loss": 0.4524,
      "step": 46609
    },
    {
      "epoch": 1.4318188799803397,
      "grad_norm": 0.45130807161331177,
      "learning_rate": 3.7363743331987058e-06,
      "loss": 0.5109,
      "step": 46610
    },
    {
      "epoch": 1.4318495991152889,
      "grad_norm": 0.3856426775455475,
      "learning_rate": 3.735997610427978e-06,
      "loss": 0.4045,
      "step": 46611
    },
    {
      "epoch": 1.4318803182502382,
      "grad_norm": 0.39558205008506775,
      "learning_rate": 3.7356209022872616e-06,
      "loss": 0.5039,
      "step": 46612
    },
    {
      "epoch": 1.4319110373851873,
      "grad_norm": 0.41460373997688293,
      "learning_rate": 3.7352442087774434e-06,
      "loss": 0.5269,
      "step": 46613
    },
    {
      "epoch": 1.4319417565201364,
      "grad_norm": 0.4289667308330536,
      "learning_rate": 3.7348675298993964e-06,
      "loss": 0.5037,
      "step": 46614
    },
    {
      "epoch": 1.4319724756550856,
      "grad_norm": 0.48768797516822815,
      "learning_rate": 3.7344908656540037e-06,
      "loss": 0.5254,
      "step": 46615
    },
    {
      "epoch": 1.4320031947900347,
      "grad_norm": 0.4296087324619293,
      "learning_rate": 3.7341142160421453e-06,
      "loss": 0.5002,
      "step": 46616
    },
    {
      "epoch": 1.4320339139249838,
      "grad_norm": 0.4081479609012604,
      "learning_rate": 3.7337375810647038e-06,
      "loss": 0.4313,
      "step": 46617
    },
    {
      "epoch": 1.432064633059933,
      "grad_norm": 0.42060691118240356,
      "learning_rate": 3.733360960722553e-06,
      "loss": 0.477,
      "step": 46618
    },
    {
      "epoch": 1.4320953521948823,
      "grad_norm": 0.39220407605171204,
      "learning_rate": 3.7329843550165745e-06,
      "loss": 0.4309,
      "step": 46619
    },
    {
      "epoch": 1.4321260713298314,
      "grad_norm": 0.4180140793323517,
      "learning_rate": 3.732607763947649e-06,
      "loss": 0.4394,
      "step": 46620
    },
    {
      "epoch": 1.4321567904647805,
      "grad_norm": 0.3954324424266815,
      "learning_rate": 3.732231187516656e-06,
      "loss": 0.4463,
      "step": 46621
    },
    {
      "epoch": 1.4321875095997296,
      "grad_norm": 0.44558650255203247,
      "learning_rate": 3.731854625724478e-06,
      "loss": 0.5295,
      "step": 46622
    },
    {
      "epoch": 1.432218228734679,
      "grad_norm": 0.38357898592948914,
      "learning_rate": 3.7314780785719883e-06,
      "loss": 0.4264,
      "step": 46623
    },
    {
      "epoch": 1.432248947869628,
      "grad_norm": 0.4404584765434265,
      "learning_rate": 3.7311015460600695e-06,
      "loss": 0.4788,
      "step": 46624
    },
    {
      "epoch": 1.4322796670045772,
      "grad_norm": 0.4285919666290283,
      "learning_rate": 3.7307250281896e-06,
      "loss": 0.4356,
      "step": 46625
    },
    {
      "epoch": 1.4323103861395263,
      "grad_norm": 0.4216688275337219,
      "learning_rate": 3.7303485249614645e-06,
      "loss": 0.3614,
      "step": 46626
    },
    {
      "epoch": 1.4323411052744754,
      "grad_norm": 0.453429639339447,
      "learning_rate": 3.7299720363765333e-06,
      "loss": 0.4859,
      "step": 46627
    },
    {
      "epoch": 1.4323718244094246,
      "grad_norm": 0.41233381628990173,
      "learning_rate": 3.7295955624356918e-06,
      "loss": 0.4613,
      "step": 46628
    },
    {
      "epoch": 1.4324025435443737,
      "grad_norm": 0.41714808344841003,
      "learning_rate": 3.729219103139816e-06,
      "loss": 0.4562,
      "step": 46629
    },
    {
      "epoch": 1.432433262679323,
      "grad_norm": 0.44985431432724,
      "learning_rate": 3.728842658489792e-06,
      "loss": 0.4743,
      "step": 46630
    },
    {
      "epoch": 1.4324639818142721,
      "grad_norm": 0.42527052760124207,
      "learning_rate": 3.7284662284864894e-06,
      "loss": 0.4596,
      "step": 46631
    },
    {
      "epoch": 1.4324947009492213,
      "grad_norm": 0.5472830533981323,
      "learning_rate": 3.728089813130793e-06,
      "loss": 0.5055,
      "step": 46632
    },
    {
      "epoch": 1.4325254200841704,
      "grad_norm": 0.40148672461509705,
      "learning_rate": 3.727713412423579e-06,
      "loss": 0.4094,
      "step": 46633
    },
    {
      "epoch": 1.4325561392191195,
      "grad_norm": 0.44672891497612,
      "learning_rate": 3.7273370263657337e-06,
      "loss": 0.4868,
      "step": 46634
    },
    {
      "epoch": 1.4325868583540688,
      "grad_norm": 0.43552544713020325,
      "learning_rate": 3.726960654958127e-06,
      "loss": 0.4766,
      "step": 46635
    },
    {
      "epoch": 1.432617577489018,
      "grad_norm": 0.4043108820915222,
      "learning_rate": 3.7265842982016443e-06,
      "loss": 0.3751,
      "step": 46636
    },
    {
      "epoch": 1.432648296623967,
      "grad_norm": 0.4011468291282654,
      "learning_rate": 3.7262079560971564e-06,
      "loss": 0.4806,
      "step": 46637
    },
    {
      "epoch": 1.4326790157589162,
      "grad_norm": 0.4129365384578705,
      "learning_rate": 3.7258316286455542e-06,
      "loss": 0.4271,
      "step": 46638
    },
    {
      "epoch": 1.4327097348938653,
      "grad_norm": 0.4466169774532318,
      "learning_rate": 3.7254553158477067e-06,
      "loss": 0.4972,
      "step": 46639
    },
    {
      "epoch": 1.4327404540288144,
      "grad_norm": 0.39193791151046753,
      "learning_rate": 3.725079017704497e-06,
      "loss": 0.4439,
      "step": 46640
    },
    {
      "epoch": 1.4327711731637638,
      "grad_norm": 0.39229169487953186,
      "learning_rate": 3.7247027342168075e-06,
      "loss": 0.4509,
      "step": 46641
    },
    {
      "epoch": 1.432801892298713,
      "grad_norm": 0.3889690637588501,
      "learning_rate": 3.724326465385505e-06,
      "loss": 0.5354,
      "step": 46642
    },
    {
      "epoch": 1.432832611433662,
      "grad_norm": 0.3978738486766815,
      "learning_rate": 3.7239502112114835e-06,
      "loss": 0.3979,
      "step": 46643
    },
    {
      "epoch": 1.4328633305686111,
      "grad_norm": 0.4413345754146576,
      "learning_rate": 3.723573971695612e-06,
      "loss": 0.5284,
      "step": 46644
    },
    {
      "epoch": 1.4328940497035603,
      "grad_norm": 0.4041043221950531,
      "learning_rate": 3.723197746838774e-06,
      "loss": 0.4484,
      "step": 46645
    },
    {
      "epoch": 1.4329247688385096,
      "grad_norm": 0.38695046305656433,
      "learning_rate": 3.722821536641843e-06,
      "loss": 0.4606,
      "step": 46646
    },
    {
      "epoch": 1.4329554879734587,
      "grad_norm": 0.4267454445362091,
      "learning_rate": 3.7224453411057014e-06,
      "loss": 0.4907,
      "step": 46647
    },
    {
      "epoch": 1.4329862071084079,
      "grad_norm": 0.47223716974258423,
      "learning_rate": 3.7220691602312263e-06,
      "loss": 0.5281,
      "step": 46648
    },
    {
      "epoch": 1.433016926243357,
      "grad_norm": 0.4220808148384094,
      "learning_rate": 3.7216929940193014e-06,
      "loss": 0.4825,
      "step": 46649
    },
    {
      "epoch": 1.433047645378306,
      "grad_norm": 0.4289831519126892,
      "learning_rate": 3.7213168424707967e-06,
      "loss": 0.5105,
      "step": 46650
    },
    {
      "epoch": 1.4330783645132552,
      "grad_norm": 0.4394613802433014,
      "learning_rate": 3.7209407055865953e-06,
      "loss": 0.483,
      "step": 46651
    },
    {
      "epoch": 1.4331090836482043,
      "grad_norm": 0.4620317816734314,
      "learning_rate": 3.720564583367575e-06,
      "loss": 0.5157,
      "step": 46652
    },
    {
      "epoch": 1.4331398027831537,
      "grad_norm": 0.4388017952442169,
      "learning_rate": 3.720188475814619e-06,
      "loss": 0.4615,
      "step": 46653
    },
    {
      "epoch": 1.4331705219181028,
      "grad_norm": 0.41909271478652954,
      "learning_rate": 3.719812382928597e-06,
      "loss": 0.4624,
      "step": 46654
    },
    {
      "epoch": 1.433201241053052,
      "grad_norm": 0.4044317901134491,
      "learning_rate": 3.7194363047103933e-06,
      "loss": 0.4499,
      "step": 46655
    },
    {
      "epoch": 1.433231960188001,
      "grad_norm": 0.6007899045944214,
      "learning_rate": 3.7190602411608835e-06,
      "loss": 0.498,
      "step": 46656
    },
    {
      "epoch": 1.4332626793229504,
      "grad_norm": 0.4194123148918152,
      "learning_rate": 3.7186841922809468e-06,
      "loss": 0.4734,
      "step": 46657
    },
    {
      "epoch": 1.4332933984578995,
      "grad_norm": 0.41086381673812866,
      "learning_rate": 3.7183081580714665e-06,
      "loss": 0.4432,
      "step": 46658
    },
    {
      "epoch": 1.4333241175928486,
      "grad_norm": 0.425618439912796,
      "learning_rate": 3.717932138533312e-06,
      "loss": 0.4893,
      "step": 46659
    },
    {
      "epoch": 1.4333548367277977,
      "grad_norm": 0.4244092106819153,
      "learning_rate": 3.717556133667366e-06,
      "loss": 0.5244,
      "step": 46660
    },
    {
      "epoch": 1.4333855558627469,
      "grad_norm": 0.46307024359703064,
      "learning_rate": 3.717180143474506e-06,
      "loss": 0.4453,
      "step": 46661
    },
    {
      "epoch": 1.433416274997696,
      "grad_norm": 0.41891130805015564,
      "learning_rate": 3.7168041679556142e-06,
      "loss": 0.4434,
      "step": 46662
    },
    {
      "epoch": 1.433446994132645,
      "grad_norm": 0.3823789954185486,
      "learning_rate": 3.716428207111562e-06,
      "loss": 0.4737,
      "step": 46663
    },
    {
      "epoch": 1.4334777132675944,
      "grad_norm": 0.46840900182724,
      "learning_rate": 3.7160522609432304e-06,
      "loss": 0.4965,
      "step": 46664
    },
    {
      "epoch": 1.4335084324025436,
      "grad_norm": 0.46909090876579285,
      "learning_rate": 3.7156763294514976e-06,
      "loss": 0.445,
      "step": 46665
    },
    {
      "epoch": 1.4335391515374927,
      "grad_norm": 0.44229403138160706,
      "learning_rate": 3.715300412637245e-06,
      "loss": 0.4695,
      "step": 46666
    },
    {
      "epoch": 1.4335698706724418,
      "grad_norm": 0.4130460023880005,
      "learning_rate": 3.714924510501343e-06,
      "loss": 0.4713,
      "step": 46667
    },
    {
      "epoch": 1.4336005898073911,
      "grad_norm": 0.39451420307159424,
      "learning_rate": 3.714548623044678e-06,
      "loss": 0.4584,
      "step": 46668
    },
    {
      "epoch": 1.4336313089423403,
      "grad_norm": 0.4134102761745453,
      "learning_rate": 3.714172750268117e-06,
      "loss": 0.4785,
      "step": 46669
    },
    {
      "epoch": 1.4336620280772894,
      "grad_norm": 0.42684346437454224,
      "learning_rate": 3.713796892172551e-06,
      "loss": 0.4102,
      "step": 46670
    },
    {
      "epoch": 1.4336927472122385,
      "grad_norm": 0.4269534647464752,
      "learning_rate": 3.7134210487588484e-06,
      "loss": 0.5389,
      "step": 46671
    },
    {
      "epoch": 1.4337234663471876,
      "grad_norm": 0.3844296932220459,
      "learning_rate": 3.713045220027893e-06,
      "loss": 0.4177,
      "step": 46672
    },
    {
      "epoch": 1.4337541854821367,
      "grad_norm": 0.42096176743507385,
      "learning_rate": 3.7126694059805524e-06,
      "loss": 0.483,
      "step": 46673
    },
    {
      "epoch": 1.4337849046170859,
      "grad_norm": 0.4576060473918915,
      "learning_rate": 3.7122936066177186e-06,
      "loss": 0.4604,
      "step": 46674
    },
    {
      "epoch": 1.4338156237520352,
      "grad_norm": 0.41159775853157043,
      "learning_rate": 3.7119178219402597e-06,
      "loss": 0.4767,
      "step": 46675
    },
    {
      "epoch": 1.4338463428869843,
      "grad_norm": 0.46622857451438904,
      "learning_rate": 3.711542051949054e-06,
      "loss": 0.515,
      "step": 46676
    },
    {
      "epoch": 1.4338770620219334,
      "grad_norm": 0.42562136054039,
      "learning_rate": 3.711166296644986e-06,
      "loss": 0.4457,
      "step": 46677
    },
    {
      "epoch": 1.4339077811568826,
      "grad_norm": 0.4383307099342346,
      "learning_rate": 3.7107905560289213e-06,
      "loss": 0.5179,
      "step": 46678
    },
    {
      "epoch": 1.433938500291832,
      "grad_norm": 0.3646388053894043,
      "learning_rate": 3.7104148301017506e-06,
      "loss": 0.4433,
      "step": 46679
    },
    {
      "epoch": 1.433969219426781,
      "grad_norm": 0.4026409685611725,
      "learning_rate": 3.7100391188643424e-06,
      "loss": 0.5465,
      "step": 46680
    },
    {
      "epoch": 1.4339999385617301,
      "grad_norm": 0.43821728229522705,
      "learning_rate": 3.709663422317581e-06,
      "loss": 0.4304,
      "step": 46681
    },
    {
      "epoch": 1.4340306576966793,
      "grad_norm": 0.4650098383426666,
      "learning_rate": 3.709287740462336e-06,
      "loss": 0.5008,
      "step": 46682
    },
    {
      "epoch": 1.4340613768316284,
      "grad_norm": 0.3980243504047394,
      "learning_rate": 3.7089120732994887e-06,
      "loss": 0.4923,
      "step": 46683
    },
    {
      "epoch": 1.4340920959665775,
      "grad_norm": 0.4055453836917877,
      "learning_rate": 3.7085364208299167e-06,
      "loss": 0.4653,
      "step": 46684
    },
    {
      "epoch": 1.4341228151015266,
      "grad_norm": 0.45947355031967163,
      "learning_rate": 3.7081607830545007e-06,
      "loss": 0.54,
      "step": 46685
    },
    {
      "epoch": 1.434153534236476,
      "grad_norm": 0.44516608119010925,
      "learning_rate": 3.707785159974112e-06,
      "loss": 0.5486,
      "step": 46686
    },
    {
      "epoch": 1.434184253371425,
      "grad_norm": 0.4168025851249695,
      "learning_rate": 3.7074095515896293e-06,
      "loss": 0.3584,
      "step": 46687
    },
    {
      "epoch": 1.4342149725063742,
      "grad_norm": 0.4548482596874237,
      "learning_rate": 3.707033957901932e-06,
      "loss": 0.4759,
      "step": 46688
    },
    {
      "epoch": 1.4342456916413233,
      "grad_norm": 0.3937741816043854,
      "learning_rate": 3.706658378911899e-06,
      "loss": 0.5212,
      "step": 46689
    },
    {
      "epoch": 1.4342764107762727,
      "grad_norm": 0.4266583323478699,
      "learning_rate": 3.706282814620402e-06,
      "loss": 0.4244,
      "step": 46690
    },
    {
      "epoch": 1.4343071299112218,
      "grad_norm": 0.41055363416671753,
      "learning_rate": 3.7059072650283213e-06,
      "loss": 0.4433,
      "step": 46691
    },
    {
      "epoch": 1.434337849046171,
      "grad_norm": 0.4537961483001709,
      "learning_rate": 3.7055317301365324e-06,
      "loss": 0.4609,
      "step": 46692
    },
    {
      "epoch": 1.43436856818112,
      "grad_norm": 0.42786094546318054,
      "learning_rate": 3.7051562099459147e-06,
      "loss": 0.5333,
      "step": 46693
    },
    {
      "epoch": 1.4343992873160691,
      "grad_norm": 0.45500028133392334,
      "learning_rate": 3.704780704457348e-06,
      "loss": 0.4522,
      "step": 46694
    },
    {
      "epoch": 1.4344300064510183,
      "grad_norm": 0.4446362853050232,
      "learning_rate": 3.7044052136717024e-06,
      "loss": 0.4017,
      "step": 46695
    },
    {
      "epoch": 1.4344607255859674,
      "grad_norm": 0.3986711800098419,
      "learning_rate": 3.704029737589857e-06,
      "loss": 0.4349,
      "step": 46696
    },
    {
      "epoch": 1.4344914447209167,
      "grad_norm": 0.45780518651008606,
      "learning_rate": 3.7036542762126903e-06,
      "loss": 0.4801,
      "step": 46697
    },
    {
      "epoch": 1.4345221638558658,
      "grad_norm": 0.39634084701538086,
      "learning_rate": 3.7032788295410825e-06,
      "loss": 0.5488,
      "step": 46698
    },
    {
      "epoch": 1.434552882990815,
      "grad_norm": 0.45448508858680725,
      "learning_rate": 3.7029033975759033e-06,
      "loss": 0.5373,
      "step": 46699
    },
    {
      "epoch": 1.434583602125764,
      "grad_norm": 0.3955884575843811,
      "learning_rate": 3.7025279803180325e-06,
      "loss": 0.4743,
      "step": 46700
    },
    {
      "epoch": 1.4346143212607134,
      "grad_norm": 0.428311288356781,
      "learning_rate": 3.702152577768349e-06,
      "loss": 0.4257,
      "step": 46701
    },
    {
      "epoch": 1.4346450403956625,
      "grad_norm": 0.43618693947792053,
      "learning_rate": 3.701777189927729e-06,
      "loss": 0.4862,
      "step": 46702
    },
    {
      "epoch": 1.4346757595306117,
      "grad_norm": 0.5898022055625916,
      "learning_rate": 3.7014018167970466e-06,
      "loss": 0.4962,
      "step": 46703
    },
    {
      "epoch": 1.4347064786655608,
      "grad_norm": 0.4342898726463318,
      "learning_rate": 3.7010264583771828e-06,
      "loss": 0.5668,
      "step": 46704
    },
    {
      "epoch": 1.43473719780051,
      "grad_norm": 0.4086589813232422,
      "learning_rate": 3.700651114669005e-06,
      "loss": 0.5146,
      "step": 46705
    },
    {
      "epoch": 1.434767916935459,
      "grad_norm": 0.4095769226551056,
      "learning_rate": 3.7002757856734027e-06,
      "loss": 0.4369,
      "step": 46706
    },
    {
      "epoch": 1.4347986360704081,
      "grad_norm": 0.4249454140663147,
      "learning_rate": 3.6999004713912433e-06,
      "loss": 0.5144,
      "step": 46707
    },
    {
      "epoch": 1.4348293552053575,
      "grad_norm": 0.45851248502731323,
      "learning_rate": 3.6995251718234103e-06,
      "loss": 0.4419,
      "step": 46708
    },
    {
      "epoch": 1.4348600743403066,
      "grad_norm": 0.3929811120033264,
      "learning_rate": 3.699149886970772e-06,
      "loss": 0.453,
      "step": 46709
    },
    {
      "epoch": 1.4348907934752557,
      "grad_norm": 0.41837745904922485,
      "learning_rate": 3.6987746168342096e-06,
      "loss": 0.4715,
      "step": 46710
    },
    {
      "epoch": 1.4349215126102048,
      "grad_norm": 0.42510277032852173,
      "learning_rate": 3.6983993614145995e-06,
      "loss": 0.5153,
      "step": 46711
    },
    {
      "epoch": 1.4349522317451542,
      "grad_norm": 0.40833085775375366,
      "learning_rate": 3.6980241207128174e-06,
      "loss": 0.5062,
      "step": 46712
    },
    {
      "epoch": 1.4349829508801033,
      "grad_norm": 0.3914884626865387,
      "learning_rate": 3.697648894729744e-06,
      "loss": 0.4942,
      "step": 46713
    },
    {
      "epoch": 1.4350136700150524,
      "grad_norm": 0.43502479791641235,
      "learning_rate": 3.6972736834662447e-06,
      "loss": 0.4713,
      "step": 46714
    },
    {
      "epoch": 1.4350443891500015,
      "grad_norm": 0.41786032915115356,
      "learning_rate": 3.6968984869232095e-06,
      "loss": 0.4764,
      "step": 46715
    },
    {
      "epoch": 1.4350751082849507,
      "grad_norm": 0.42430564761161804,
      "learning_rate": 3.696523305101505e-06,
      "loss": 0.4291,
      "step": 46716
    },
    {
      "epoch": 1.4351058274198998,
      "grad_norm": 0.49455443024635315,
      "learning_rate": 3.6961481380020125e-06,
      "loss": 0.4837,
      "step": 46717
    },
    {
      "epoch": 1.435136546554849,
      "grad_norm": 0.44542384147644043,
      "learning_rate": 3.695772985625604e-06,
      "loss": 0.5119,
      "step": 46718
    },
    {
      "epoch": 1.4351672656897982,
      "grad_norm": 0.42549487948417664,
      "learning_rate": 3.695397847973159e-06,
      "loss": 0.4752,
      "step": 46719
    },
    {
      "epoch": 1.4351979848247474,
      "grad_norm": 0.4135521352291107,
      "learning_rate": 3.6950227250455504e-06,
      "loss": 0.4583,
      "step": 46720
    },
    {
      "epoch": 1.4352287039596965,
      "grad_norm": 0.4339316785335541,
      "learning_rate": 3.694647616843662e-06,
      "loss": 0.4625,
      "step": 46721
    },
    {
      "epoch": 1.4352594230946456,
      "grad_norm": 0.42340463399887085,
      "learning_rate": 3.6942725233683597e-06,
      "loss": 0.4375,
      "step": 46722
    },
    {
      "epoch": 1.435290142229595,
      "grad_norm": 0.4533837139606476,
      "learning_rate": 3.6938974446205257e-06,
      "loss": 0.5301,
      "step": 46723
    },
    {
      "epoch": 1.435320861364544,
      "grad_norm": 0.3704018294811249,
      "learning_rate": 3.6935223806010336e-06,
      "loss": 0.4077,
      "step": 46724
    },
    {
      "epoch": 1.4353515804994932,
      "grad_norm": 0.4046282172203064,
      "learning_rate": 3.6931473313107634e-06,
      "loss": 0.4636,
      "step": 46725
    },
    {
      "epoch": 1.4353822996344423,
      "grad_norm": 0.4845666289329529,
      "learning_rate": 3.6927722967505855e-06,
      "loss": 0.4708,
      "step": 46726
    },
    {
      "epoch": 1.4354130187693914,
      "grad_norm": 0.43677574396133423,
      "learning_rate": 3.6923972769213777e-06,
      "loss": 0.3831,
      "step": 46727
    },
    {
      "epoch": 1.4354437379043405,
      "grad_norm": 0.4144868552684784,
      "learning_rate": 3.6920222718240173e-06,
      "loss": 0.4877,
      "step": 46728
    },
    {
      "epoch": 1.4354744570392897,
      "grad_norm": 0.39879897236824036,
      "learning_rate": 3.691647281459383e-06,
      "loss": 0.5062,
      "step": 46729
    },
    {
      "epoch": 1.435505176174239,
      "grad_norm": 0.44003474712371826,
      "learning_rate": 3.6912723058283427e-06,
      "loss": 0.4229,
      "step": 46730
    },
    {
      "epoch": 1.4355358953091881,
      "grad_norm": 0.4084625244140625,
      "learning_rate": 3.6908973449317775e-06,
      "loss": 0.4913,
      "step": 46731
    },
    {
      "epoch": 1.4355666144441372,
      "grad_norm": 0.4704192876815796,
      "learning_rate": 3.6905223987705618e-06,
      "loss": 0.4028,
      "step": 46732
    },
    {
      "epoch": 1.4355973335790864,
      "grad_norm": 0.40963077545166016,
      "learning_rate": 3.6901474673455716e-06,
      "loss": 0.4294,
      "step": 46733
    },
    {
      "epoch": 1.4356280527140357,
      "grad_norm": 0.40848857164382935,
      "learning_rate": 3.6897725506576863e-06,
      "loss": 0.5058,
      "step": 46734
    },
    {
      "epoch": 1.4356587718489848,
      "grad_norm": 0.4211711585521698,
      "learning_rate": 3.689397648707774e-06,
      "loss": 0.5271,
      "step": 46735
    },
    {
      "epoch": 1.435689490983934,
      "grad_norm": 0.42298731207847595,
      "learning_rate": 3.6890227614967146e-06,
      "loss": 0.4578,
      "step": 46736
    },
    {
      "epoch": 1.435720210118883,
      "grad_norm": 0.4234800338745117,
      "learning_rate": 3.688647889025383e-06,
      "loss": 0.5167,
      "step": 46737
    },
    {
      "epoch": 1.4357509292538322,
      "grad_norm": 0.42741286754608154,
      "learning_rate": 3.688273031294659e-06,
      "loss": 0.4833,
      "step": 46738
    },
    {
      "epoch": 1.4357816483887813,
      "grad_norm": 0.4970338046550751,
      "learning_rate": 3.68789818830541e-06,
      "loss": 0.4121,
      "step": 46739
    },
    {
      "epoch": 1.4358123675237304,
      "grad_norm": 0.4248213768005371,
      "learning_rate": 3.6875233600585193e-06,
      "loss": 0.469,
      "step": 46740
    },
    {
      "epoch": 1.4358430866586798,
      "grad_norm": 0.42925387620925903,
      "learning_rate": 3.687148546554852e-06,
      "loss": 0.5298,
      "step": 46741
    },
    {
      "epoch": 1.4358738057936289,
      "grad_norm": 0.417814701795578,
      "learning_rate": 3.6867737477952968e-06,
      "loss": 0.44,
      "step": 46742
    },
    {
      "epoch": 1.435904524928578,
      "grad_norm": 0.4426182806491852,
      "learning_rate": 3.6863989637807197e-06,
      "loss": 0.4758,
      "step": 46743
    },
    {
      "epoch": 1.4359352440635271,
      "grad_norm": 0.44022074341773987,
      "learning_rate": 3.686024194512001e-06,
      "loss": 0.4621,
      "step": 46744
    },
    {
      "epoch": 1.4359659631984765,
      "grad_norm": 0.41072630882263184,
      "learning_rate": 3.685649439990011e-06,
      "loss": 0.47,
      "step": 46745
    },
    {
      "epoch": 1.4359966823334256,
      "grad_norm": 0.39024001359939575,
      "learning_rate": 3.6852747002156273e-06,
      "loss": 0.4663,
      "step": 46746
    },
    {
      "epoch": 1.4360274014683747,
      "grad_norm": 0.4849679470062256,
      "learning_rate": 3.684899975189726e-06,
      "loss": 0.5576,
      "step": 46747
    },
    {
      "epoch": 1.4360581206033238,
      "grad_norm": 0.41242489218711853,
      "learning_rate": 3.6845252649131826e-06,
      "loss": 0.4547,
      "step": 46748
    },
    {
      "epoch": 1.436088839738273,
      "grad_norm": 0.47337523102760315,
      "learning_rate": 3.684150569386874e-06,
      "loss": 0.4522,
      "step": 46749
    },
    {
      "epoch": 1.436119558873222,
      "grad_norm": 0.41598913073539734,
      "learning_rate": 3.6837758886116658e-06,
      "loss": 0.4649,
      "step": 46750
    },
    {
      "epoch": 1.4361502780081712,
      "grad_norm": 0.41183340549468994,
      "learning_rate": 3.6834012225884475e-06,
      "loss": 0.4186,
      "step": 46751
    },
    {
      "epoch": 1.4361809971431205,
      "grad_norm": 0.40329718589782715,
      "learning_rate": 3.6830265713180825e-06,
      "loss": 0.5624,
      "step": 46752
    },
    {
      "epoch": 1.4362117162780696,
      "grad_norm": 0.3993628919124603,
      "learning_rate": 3.6826519348014544e-06,
      "loss": 0.4535,
      "step": 46753
    },
    {
      "epoch": 1.4362424354130188,
      "grad_norm": 0.39296138286590576,
      "learning_rate": 3.6822773130394294e-06,
      "loss": 0.4414,
      "step": 46754
    },
    {
      "epoch": 1.436273154547968,
      "grad_norm": 0.40325748920440674,
      "learning_rate": 3.6819027060328883e-06,
      "loss": 0.4739,
      "step": 46755
    },
    {
      "epoch": 1.436303873682917,
      "grad_norm": 0.36685630679130554,
      "learning_rate": 3.6815281137827042e-06,
      "loss": 0.4087,
      "step": 46756
    },
    {
      "epoch": 1.4363345928178664,
      "grad_norm": 0.41397425532341003,
      "learning_rate": 3.6811535362897556e-06,
      "loss": 0.5018,
      "step": 46757
    },
    {
      "epoch": 1.4363653119528155,
      "grad_norm": 0.4058346450328827,
      "learning_rate": 3.6807789735549114e-06,
      "loss": 0.516,
      "step": 46758
    },
    {
      "epoch": 1.4363960310877646,
      "grad_norm": 0.40797051787376404,
      "learning_rate": 3.6804044255790493e-06,
      "loss": 0.4773,
      "step": 46759
    },
    {
      "epoch": 1.4364267502227137,
      "grad_norm": 0.43732360005378723,
      "learning_rate": 3.680029892363043e-06,
      "loss": 0.4689,
      "step": 46760
    },
    {
      "epoch": 1.4364574693576628,
      "grad_norm": 0.4344969689846039,
      "learning_rate": 3.6796553739077723e-06,
      "loss": 0.4567,
      "step": 46761
    },
    {
      "epoch": 1.436488188492612,
      "grad_norm": 0.41079774498939514,
      "learning_rate": 3.679280870214105e-06,
      "loss": 0.4502,
      "step": 46762
    },
    {
      "epoch": 1.436518907627561,
      "grad_norm": 0.42882993817329407,
      "learning_rate": 3.6789063812829185e-06,
      "loss": 0.4953,
      "step": 46763
    },
    {
      "epoch": 1.4365496267625104,
      "grad_norm": 0.40340888500213623,
      "learning_rate": 3.678531907115087e-06,
      "loss": 0.4013,
      "step": 46764
    },
    {
      "epoch": 1.4365803458974595,
      "grad_norm": 0.432131290435791,
      "learning_rate": 3.678157447711489e-06,
      "loss": 0.3885,
      "step": 46765
    },
    {
      "epoch": 1.4366110650324087,
      "grad_norm": 0.44809094071388245,
      "learning_rate": 3.6777830030729923e-06,
      "loss": 0.4355,
      "step": 46766
    },
    {
      "epoch": 1.4366417841673578,
      "grad_norm": 0.38048645853996277,
      "learning_rate": 3.677408573200476e-06,
      "loss": 0.4426,
      "step": 46767
    },
    {
      "epoch": 1.4366725033023071,
      "grad_norm": 0.4138108193874359,
      "learning_rate": 3.677034158094813e-06,
      "loss": 0.4464,
      "step": 46768
    },
    {
      "epoch": 1.4367032224372562,
      "grad_norm": 0.46961721777915955,
      "learning_rate": 3.6766597577568776e-06,
      "loss": 0.494,
      "step": 46769
    },
    {
      "epoch": 1.4367339415722054,
      "grad_norm": 0.42237088084220886,
      "learning_rate": 3.676285372187549e-06,
      "loss": 0.5007,
      "step": 46770
    },
    {
      "epoch": 1.4367646607071545,
      "grad_norm": 0.4374324083328247,
      "learning_rate": 3.675911001387694e-06,
      "loss": 0.4675,
      "step": 46771
    },
    {
      "epoch": 1.4367953798421036,
      "grad_norm": 0.391791969537735,
      "learning_rate": 3.675536645358191e-06,
      "loss": 0.4957,
      "step": 46772
    },
    {
      "epoch": 1.4368260989770527,
      "grad_norm": 0.4208656847476959,
      "learning_rate": 3.675162304099914e-06,
      "loss": 0.4952,
      "step": 46773
    },
    {
      "epoch": 1.4368568181120018,
      "grad_norm": 0.42702382802963257,
      "learning_rate": 3.6747879776137396e-06,
      "loss": 0.4421,
      "step": 46774
    },
    {
      "epoch": 1.4368875372469512,
      "grad_norm": 0.4390856623649597,
      "learning_rate": 3.674413665900537e-06,
      "loss": 0.4834,
      "step": 46775
    },
    {
      "epoch": 1.4369182563819003,
      "grad_norm": 0.4626513719558716,
      "learning_rate": 3.6740393689611863e-06,
      "loss": 0.5147,
      "step": 46776
    },
    {
      "epoch": 1.4369489755168494,
      "grad_norm": 0.41159236431121826,
      "learning_rate": 3.6736650867965518e-06,
      "loss": 0.4793,
      "step": 46777
    },
    {
      "epoch": 1.4369796946517985,
      "grad_norm": 0.4185622036457062,
      "learning_rate": 3.67329081940752e-06,
      "loss": 0.5093,
      "step": 46778
    },
    {
      "epoch": 1.4370104137867479,
      "grad_norm": 0.4135884940624237,
      "learning_rate": 3.6729165667949575e-06,
      "loss": 0.418,
      "step": 46779
    },
    {
      "epoch": 1.437041132921697,
      "grad_norm": 0.42427313327789307,
      "learning_rate": 3.6725423289597428e-06,
      "loss": 0.4368,
      "step": 46780
    },
    {
      "epoch": 1.4370718520566461,
      "grad_norm": 0.4421619176864624,
      "learning_rate": 3.6721681059027436e-06,
      "loss": 0.5605,
      "step": 46781
    },
    {
      "epoch": 1.4371025711915952,
      "grad_norm": 0.46078187227249146,
      "learning_rate": 3.671793897624839e-06,
      "loss": 0.3966,
      "step": 46782
    },
    {
      "epoch": 1.4371332903265444,
      "grad_norm": 0.40748852491378784,
      "learning_rate": 3.671419704126901e-06,
      "loss": 0.4179,
      "step": 46783
    },
    {
      "epoch": 1.4371640094614935,
      "grad_norm": 0.4931863844394684,
      "learning_rate": 3.6710455254098076e-06,
      "loss": 0.4695,
      "step": 46784
    },
    {
      "epoch": 1.4371947285964426,
      "grad_norm": 0.417336106300354,
      "learning_rate": 3.670671361474426e-06,
      "loss": 0.3981,
      "step": 46785
    },
    {
      "epoch": 1.437225447731392,
      "grad_norm": 0.44482049345970154,
      "learning_rate": 3.670297212321633e-06,
      "loss": 0.4316,
      "step": 46786
    },
    {
      "epoch": 1.437256166866341,
      "grad_norm": 0.43973058462142944,
      "learning_rate": 3.669923077952303e-06,
      "loss": 0.4998,
      "step": 46787
    },
    {
      "epoch": 1.4372868860012902,
      "grad_norm": 0.5965213179588318,
      "learning_rate": 3.6695489583673104e-06,
      "loss": 0.4611,
      "step": 46788
    },
    {
      "epoch": 1.4373176051362393,
      "grad_norm": 0.3736255466938019,
      "learning_rate": 3.669174853567532e-06,
      "loss": 0.4556,
      "step": 46789
    },
    {
      "epoch": 1.4373483242711886,
      "grad_norm": 0.4001249074935913,
      "learning_rate": 3.6688007635538336e-06,
      "loss": 0.5373,
      "step": 46790
    },
    {
      "epoch": 1.4373790434061378,
      "grad_norm": 0.42165905237197876,
      "learning_rate": 3.6684266883270938e-06,
      "loss": 0.4465,
      "step": 46791
    },
    {
      "epoch": 1.4374097625410869,
      "grad_norm": 0.43908607959747314,
      "learning_rate": 3.6680526278881846e-06,
      "loss": 0.406,
      "step": 46792
    },
    {
      "epoch": 1.437440481676036,
      "grad_norm": 0.5263099670410156,
      "learning_rate": 3.667678582237986e-06,
      "loss": 0.4777,
      "step": 46793
    },
    {
      "epoch": 1.4374712008109851,
      "grad_norm": 0.4101657271385193,
      "learning_rate": 3.667304551377361e-06,
      "loss": 0.466,
      "step": 46794
    },
    {
      "epoch": 1.4375019199459342,
      "grad_norm": 0.4668668210506439,
      "learning_rate": 3.6669305353071895e-06,
      "loss": 0.5374,
      "step": 46795
    },
    {
      "epoch": 1.4375326390808834,
      "grad_norm": 0.39173948764801025,
      "learning_rate": 3.6665565340283437e-06,
      "loss": 0.4939,
      "step": 46796
    },
    {
      "epoch": 1.4375633582158327,
      "grad_norm": 0.4468941390514374,
      "learning_rate": 3.6661825475417013e-06,
      "loss": 0.57,
      "step": 46797
    },
    {
      "epoch": 1.4375940773507818,
      "grad_norm": 0.45169660449028015,
      "learning_rate": 3.6658085758481277e-06,
      "loss": 0.4659,
      "step": 46798
    },
    {
      "epoch": 1.437624796485731,
      "grad_norm": 0.4171167314052582,
      "learning_rate": 3.6654346189485012e-06,
      "loss": 0.5354,
      "step": 46799
    },
    {
      "epoch": 1.43765551562068,
      "grad_norm": 0.44638746976852417,
      "learning_rate": 3.6650606768436947e-06,
      "loss": 0.5675,
      "step": 46800
    },
    {
      "epoch": 1.4376862347556294,
      "grad_norm": 0.4146428406238556,
      "learning_rate": 3.664686749534584e-06,
      "loss": 0.474,
      "step": 46801
    },
    {
      "epoch": 1.4377169538905785,
      "grad_norm": 0.4123954176902771,
      "learning_rate": 3.664312837022037e-06,
      "loss": 0.4134,
      "step": 46802
    },
    {
      "epoch": 1.4377476730255276,
      "grad_norm": 0.5144383907318115,
      "learning_rate": 3.66393893930693e-06,
      "loss": 0.404,
      "step": 46803
    },
    {
      "epoch": 1.4377783921604768,
      "grad_norm": 0.4359193444252014,
      "learning_rate": 3.663565056390136e-06,
      "loss": 0.4503,
      "step": 46804
    },
    {
      "epoch": 1.4378091112954259,
      "grad_norm": 0.4078669548034668,
      "learning_rate": 3.663191188272528e-06,
      "loss": 0.3823,
      "step": 46805
    },
    {
      "epoch": 1.437839830430375,
      "grad_norm": 0.41831323504447937,
      "learning_rate": 3.6628173349549834e-06,
      "loss": 0.455,
      "step": 46806
    },
    {
      "epoch": 1.4378705495653241,
      "grad_norm": 0.40218013525009155,
      "learning_rate": 3.662443496438367e-06,
      "loss": 0.4472,
      "step": 46807
    },
    {
      "epoch": 1.4379012687002735,
      "grad_norm": 0.3787425458431244,
      "learning_rate": 3.6620696727235615e-06,
      "loss": 0.4439,
      "step": 46808
    },
    {
      "epoch": 1.4379319878352226,
      "grad_norm": 0.4544333815574646,
      "learning_rate": 3.6616958638114266e-06,
      "loss": 0.4763,
      "step": 46809
    },
    {
      "epoch": 1.4379627069701717,
      "grad_norm": 0.43171587586402893,
      "learning_rate": 3.6613220697028517e-06,
      "loss": 0.4739,
      "step": 46810
    },
    {
      "epoch": 1.4379934261051208,
      "grad_norm": 0.4019935727119446,
      "learning_rate": 3.660948290398698e-06,
      "loss": 0.426,
      "step": 46811
    },
    {
      "epoch": 1.4380241452400702,
      "grad_norm": 0.4242991507053375,
      "learning_rate": 3.660574525899845e-06,
      "loss": 0.5022,
      "step": 46812
    },
    {
      "epoch": 1.4380548643750193,
      "grad_norm": 0.6656668782234192,
      "learning_rate": 3.6602007762071567e-06,
      "loss": 0.5153,
      "step": 46813
    },
    {
      "epoch": 1.4380855835099684,
      "grad_norm": 0.40048691630363464,
      "learning_rate": 3.65982704132152e-06,
      "loss": 0.4447,
      "step": 46814
    },
    {
      "epoch": 1.4381163026449175,
      "grad_norm": 0.46254417300224304,
      "learning_rate": 3.6594533212437946e-06,
      "loss": 0.4805,
      "step": 46815
    },
    {
      "epoch": 1.4381470217798666,
      "grad_norm": 0.4470142126083374,
      "learning_rate": 3.659079615974863e-06,
      "loss": 0.4724,
      "step": 46816
    },
    {
      "epoch": 1.4381777409148158,
      "grad_norm": 0.42189082503318787,
      "learning_rate": 3.658705925515591e-06,
      "loss": 0.4529,
      "step": 46817
    },
    {
      "epoch": 1.4382084600497649,
      "grad_norm": 0.422491192817688,
      "learning_rate": 3.6583322498668537e-06,
      "loss": 0.4359,
      "step": 46818
    },
    {
      "epoch": 1.4382391791847142,
      "grad_norm": 0.3954610824584961,
      "learning_rate": 3.6579585890295246e-06,
      "loss": 0.4236,
      "step": 46819
    },
    {
      "epoch": 1.4382698983196633,
      "grad_norm": 0.3973344564437866,
      "learning_rate": 3.6575849430044796e-06,
      "loss": 0.5157,
      "step": 46820
    },
    {
      "epoch": 1.4383006174546125,
      "grad_norm": 0.4207167327404022,
      "learning_rate": 3.6572113117925844e-06,
      "loss": 0.5058,
      "step": 46821
    },
    {
      "epoch": 1.4383313365895616,
      "grad_norm": 0.3849499821662903,
      "learning_rate": 3.6568376953947147e-06,
      "loss": 0.4533,
      "step": 46822
    },
    {
      "epoch": 1.438362055724511,
      "grad_norm": 0.41146254539489746,
      "learning_rate": 3.6564640938117444e-06,
      "loss": 0.4419,
      "step": 46823
    },
    {
      "epoch": 1.43839277485946,
      "grad_norm": 0.40002959966659546,
      "learning_rate": 3.656090507044545e-06,
      "loss": 0.4986,
      "step": 46824
    },
    {
      "epoch": 1.4384234939944092,
      "grad_norm": 0.4935244023799896,
      "learning_rate": 3.6557169350939924e-06,
      "loss": 0.4643,
      "step": 46825
    },
    {
      "epoch": 1.4384542131293583,
      "grad_norm": 0.42179229855537415,
      "learning_rate": 3.6553433779609526e-06,
      "loss": 0.4026,
      "step": 46826
    },
    {
      "epoch": 1.4384849322643074,
      "grad_norm": 0.4313434958457947,
      "learning_rate": 3.6549698356463015e-06,
      "loss": 0.4472,
      "step": 46827
    },
    {
      "epoch": 1.4385156513992565,
      "grad_norm": 0.4826003909111023,
      "learning_rate": 3.654596308150912e-06,
      "loss": 0.6106,
      "step": 46828
    },
    {
      "epoch": 1.4385463705342056,
      "grad_norm": 0.4128284454345703,
      "learning_rate": 3.654222795475658e-06,
      "loss": 0.5117,
      "step": 46829
    },
    {
      "epoch": 1.438577089669155,
      "grad_norm": 0.44879621267318726,
      "learning_rate": 3.6538492976214067e-06,
      "loss": 0.5033,
      "step": 46830
    },
    {
      "epoch": 1.438607808804104,
      "grad_norm": 0.4555043876171112,
      "learning_rate": 3.6534758145890347e-06,
      "loss": 0.4644,
      "step": 46831
    },
    {
      "epoch": 1.4386385279390532,
      "grad_norm": 0.46982142329216003,
      "learning_rate": 3.6531023463794124e-06,
      "loss": 0.4651,
      "step": 46832
    },
    {
      "epoch": 1.4386692470740023,
      "grad_norm": 0.438741534948349,
      "learning_rate": 3.6527288929934167e-06,
      "loss": 0.445,
      "step": 46833
    },
    {
      "epoch": 1.4386999662089517,
      "grad_norm": 0.4197380244731903,
      "learning_rate": 3.652355454431913e-06,
      "loss": 0.4513,
      "step": 46834
    },
    {
      "epoch": 1.4387306853439008,
      "grad_norm": 0.41986507177352905,
      "learning_rate": 3.6519820306957755e-06,
      "loss": 0.5073,
      "step": 46835
    },
    {
      "epoch": 1.43876140447885,
      "grad_norm": 0.3743385672569275,
      "learning_rate": 3.651608621785877e-06,
      "loss": 0.4627,
      "step": 46836
    },
    {
      "epoch": 1.438792123613799,
      "grad_norm": 0.4437398314476013,
      "learning_rate": 3.651235227703094e-06,
      "loss": 0.5124,
      "step": 46837
    },
    {
      "epoch": 1.4388228427487482,
      "grad_norm": 0.5323979258537292,
      "learning_rate": 3.6508618484482915e-06,
      "loss": 0.4934,
      "step": 46838
    },
    {
      "epoch": 1.4388535618836973,
      "grad_norm": 0.39452025294303894,
      "learning_rate": 3.650488484022344e-06,
      "loss": 0.4409,
      "step": 46839
    },
    {
      "epoch": 1.4388842810186464,
      "grad_norm": 0.45189332962036133,
      "learning_rate": 3.650115134426124e-06,
      "loss": 0.5841,
      "step": 46840
    },
    {
      "epoch": 1.4389150001535957,
      "grad_norm": 0.4295531213283539,
      "learning_rate": 3.6497417996605032e-06,
      "loss": 0.5182,
      "step": 46841
    },
    {
      "epoch": 1.4389457192885449,
      "grad_norm": 0.446184903383255,
      "learning_rate": 3.6493684797263586e-06,
      "loss": 0.4791,
      "step": 46842
    },
    {
      "epoch": 1.438976438423494,
      "grad_norm": 0.4988602101802826,
      "learning_rate": 3.648995174624553e-06,
      "loss": 0.4498,
      "step": 46843
    },
    {
      "epoch": 1.439007157558443,
      "grad_norm": 0.41508305072784424,
      "learning_rate": 3.6486218843559663e-06,
      "loss": 0.4733,
      "step": 46844
    },
    {
      "epoch": 1.4390378766933924,
      "grad_norm": 0.39453285932540894,
      "learning_rate": 3.6482486089214607e-06,
      "loss": 0.4606,
      "step": 46845
    },
    {
      "epoch": 1.4390685958283416,
      "grad_norm": 0.5678496360778809,
      "learning_rate": 3.6478753483219197e-06,
      "loss": 0.4471,
      "step": 46846
    },
    {
      "epoch": 1.4390993149632907,
      "grad_norm": 0.39863321185112,
      "learning_rate": 3.647502102558207e-06,
      "loss": 0.4743,
      "step": 46847
    },
    {
      "epoch": 1.4391300340982398,
      "grad_norm": 0.4321359395980835,
      "learning_rate": 3.6471288716312005e-06,
      "loss": 0.5032,
      "step": 46848
    },
    {
      "epoch": 1.439160753233189,
      "grad_norm": 0.41066861152648926,
      "learning_rate": 3.6467556555417637e-06,
      "loss": 0.4277,
      "step": 46849
    },
    {
      "epoch": 1.439191472368138,
      "grad_norm": 0.4083280563354492,
      "learning_rate": 3.6463824542907733e-06,
      "loss": 0.5223,
      "step": 46850
    },
    {
      "epoch": 1.4392221915030872,
      "grad_norm": 0.39624544978141785,
      "learning_rate": 3.6460092678791005e-06,
      "loss": 0.477,
      "step": 46851
    },
    {
      "epoch": 1.4392529106380365,
      "grad_norm": 0.4239785671234131,
      "learning_rate": 3.64563609630762e-06,
      "loss": 0.5206,
      "step": 46852
    },
    {
      "epoch": 1.4392836297729856,
      "grad_norm": 0.43424445390701294,
      "learning_rate": 3.6452629395771966e-06,
      "loss": 0.5054,
      "step": 46853
    },
    {
      "epoch": 1.4393143489079347,
      "grad_norm": 0.4721728265285492,
      "learning_rate": 3.6448897976887053e-06,
      "loss": 0.4894,
      "step": 46854
    },
    {
      "epoch": 1.4393450680428839,
      "grad_norm": 0.4104333817958832,
      "learning_rate": 3.644516670643018e-06,
      "loss": 0.4403,
      "step": 46855
    },
    {
      "epoch": 1.4393757871778332,
      "grad_norm": 0.4314238429069519,
      "learning_rate": 3.6441435584410088e-06,
      "loss": 0.4102,
      "step": 46856
    },
    {
      "epoch": 1.4394065063127823,
      "grad_norm": 0.40392622351646423,
      "learning_rate": 3.6437704610835433e-06,
      "loss": 0.4802,
      "step": 46857
    },
    {
      "epoch": 1.4394372254477314,
      "grad_norm": 0.43198704719543457,
      "learning_rate": 3.643397378571496e-06,
      "loss": 0.432,
      "step": 46858
    },
    {
      "epoch": 1.4394679445826806,
      "grad_norm": 0.3742613196372986,
      "learning_rate": 3.6430243109057382e-06,
      "loss": 0.4539,
      "step": 46859
    },
    {
      "epoch": 1.4394986637176297,
      "grad_norm": 0.42064088582992554,
      "learning_rate": 3.642651258087141e-06,
      "loss": 0.4499,
      "step": 46860
    },
    {
      "epoch": 1.4395293828525788,
      "grad_norm": 0.4600937068462372,
      "learning_rate": 3.6422782201165784e-06,
      "loss": 0.4827,
      "step": 46861
    },
    {
      "epoch": 1.439560101987528,
      "grad_norm": 0.41422006487846375,
      "learning_rate": 3.641905196994917e-06,
      "loss": 0.4827,
      "step": 46862
    },
    {
      "epoch": 1.4395908211224773,
      "grad_norm": 0.400638610124588,
      "learning_rate": 3.641532188723029e-06,
      "loss": 0.4841,
      "step": 46863
    },
    {
      "epoch": 1.4396215402574264,
      "grad_norm": 0.42682957649230957,
      "learning_rate": 3.6411591953017867e-06,
      "loss": 0.4605,
      "step": 46864
    },
    {
      "epoch": 1.4396522593923755,
      "grad_norm": 0.4038187563419342,
      "learning_rate": 3.640786216732065e-06,
      "loss": 0.493,
      "step": 46865
    },
    {
      "epoch": 1.4396829785273246,
      "grad_norm": 0.3948845863342285,
      "learning_rate": 3.6404132530147274e-06,
      "loss": 0.5182,
      "step": 46866
    },
    {
      "epoch": 1.4397136976622738,
      "grad_norm": 0.4588767886161804,
      "learning_rate": 3.6400403041506494e-06,
      "loss": 0.4676,
      "step": 46867
    },
    {
      "epoch": 1.439744416797223,
      "grad_norm": 0.43971309065818787,
      "learning_rate": 3.6396673701407003e-06,
      "loss": 0.5272,
      "step": 46868
    },
    {
      "epoch": 1.4397751359321722,
      "grad_norm": 0.40167129039764404,
      "learning_rate": 3.6392944509857562e-06,
      "loss": 0.4687,
      "step": 46869
    },
    {
      "epoch": 1.4398058550671213,
      "grad_norm": 0.4083365499973297,
      "learning_rate": 3.638921546686681e-06,
      "loss": 0.4415,
      "step": 46870
    },
    {
      "epoch": 1.4398365742020705,
      "grad_norm": 0.45214325189590454,
      "learning_rate": 3.638548657244353e-06,
      "loss": 0.4845,
      "step": 46871
    },
    {
      "epoch": 1.4398672933370196,
      "grad_norm": 0.42387357354164124,
      "learning_rate": 3.638175782659631e-06,
      "loss": 0.4437,
      "step": 46872
    },
    {
      "epoch": 1.4398980124719687,
      "grad_norm": 0.4275818169116974,
      "learning_rate": 3.6378029229334e-06,
      "loss": 0.4395,
      "step": 46873
    },
    {
      "epoch": 1.4399287316069178,
      "grad_norm": 0.41160547733306885,
      "learning_rate": 3.6374300780665227e-06,
      "loss": 0.5374,
      "step": 46874
    },
    {
      "epoch": 1.4399594507418672,
      "grad_norm": 0.39114344120025635,
      "learning_rate": 3.6370572480598744e-06,
      "loss": 0.4757,
      "step": 46875
    },
    {
      "epoch": 1.4399901698768163,
      "grad_norm": 0.42477530241012573,
      "learning_rate": 3.636684432914316e-06,
      "loss": 0.4808,
      "step": 46876
    },
    {
      "epoch": 1.4400208890117654,
      "grad_norm": 0.4076807200908661,
      "learning_rate": 3.63631163263073e-06,
      "loss": 0.5312,
      "step": 46877
    },
    {
      "epoch": 1.4400516081467145,
      "grad_norm": 0.406011700630188,
      "learning_rate": 3.6359388472099856e-06,
      "loss": 0.4762,
      "step": 46878
    },
    {
      "epoch": 1.4400823272816639,
      "grad_norm": 0.4335770010948181,
      "learning_rate": 3.6355660766529465e-06,
      "loss": 0.5412,
      "step": 46879
    },
    {
      "epoch": 1.440113046416613,
      "grad_norm": 0.4090788662433624,
      "learning_rate": 3.6351933209604916e-06,
      "loss": 0.4548,
      "step": 46880
    },
    {
      "epoch": 1.440143765551562,
      "grad_norm": 0.4114738404750824,
      "learning_rate": 3.63482058013348e-06,
      "loss": 0.4998,
      "step": 46881
    },
    {
      "epoch": 1.4401744846865112,
      "grad_norm": 0.4578232169151306,
      "learning_rate": 3.6344478541727956e-06,
      "loss": 0.4722,
      "step": 46882
    },
    {
      "epoch": 1.4402052038214603,
      "grad_norm": 0.44152942299842834,
      "learning_rate": 3.6340751430793007e-06,
      "loss": 0.4342,
      "step": 46883
    },
    {
      "epoch": 1.4402359229564095,
      "grad_norm": 0.39969947934150696,
      "learning_rate": 3.6337024468538704e-06,
      "loss": 0.5409,
      "step": 46884
    },
    {
      "epoch": 1.4402666420913586,
      "grad_norm": 0.3905697166919708,
      "learning_rate": 3.63332976549737e-06,
      "loss": 0.4846,
      "step": 46885
    },
    {
      "epoch": 1.440297361226308,
      "grad_norm": 0.40876877307891846,
      "learning_rate": 3.6329570990106723e-06,
      "loss": 0.4385,
      "step": 46886
    },
    {
      "epoch": 1.440328080361257,
      "grad_norm": 0.4081577658653259,
      "learning_rate": 3.632584447394647e-06,
      "loss": 0.5125,
      "step": 46887
    },
    {
      "epoch": 1.4403587994962062,
      "grad_norm": 0.4001806378364563,
      "learning_rate": 3.63221181065017e-06,
      "loss": 0.4232,
      "step": 46888
    },
    {
      "epoch": 1.4403895186311553,
      "grad_norm": 0.40607336163520813,
      "learning_rate": 3.6318391887781022e-06,
      "loss": 0.4921,
      "step": 46889
    },
    {
      "epoch": 1.4404202377661046,
      "grad_norm": 0.44363632798194885,
      "learning_rate": 3.6314665817793204e-06,
      "loss": 0.4636,
      "step": 46890
    },
    {
      "epoch": 1.4404509569010537,
      "grad_norm": 0.4565998911857605,
      "learning_rate": 3.6310939896546925e-06,
      "loss": 0.4715,
      "step": 46891
    },
    {
      "epoch": 1.4404816760360029,
      "grad_norm": 0.39897891879081726,
      "learning_rate": 3.6307214124050926e-06,
      "loss": 0.5295,
      "step": 46892
    },
    {
      "epoch": 1.440512395170952,
      "grad_norm": 0.39312589168548584,
      "learning_rate": 3.6303488500313844e-06,
      "loss": 0.5091,
      "step": 46893
    },
    {
      "epoch": 1.440543114305901,
      "grad_norm": 1.2697116136550903,
      "learning_rate": 3.6299763025344416e-06,
      "loss": 0.4115,
      "step": 46894
    },
    {
      "epoch": 1.4405738334408502,
      "grad_norm": 0.4722556173801422,
      "learning_rate": 3.6296037699151344e-06,
      "loss": 0.4409,
      "step": 46895
    },
    {
      "epoch": 1.4406045525757993,
      "grad_norm": 0.4524533152580261,
      "learning_rate": 3.629231252174331e-06,
      "loss": 0.4426,
      "step": 46896
    },
    {
      "epoch": 1.4406352717107487,
      "grad_norm": 0.49139517545700073,
      "learning_rate": 3.628858749312908e-06,
      "loss": 0.4972,
      "step": 46897
    },
    {
      "epoch": 1.4406659908456978,
      "grad_norm": 0.41831842064857483,
      "learning_rate": 3.628486261331726e-06,
      "loss": 0.47,
      "step": 46898
    },
    {
      "epoch": 1.440696709980647,
      "grad_norm": 0.4060385823249817,
      "learning_rate": 3.6281137882316598e-06,
      "loss": 0.4282,
      "step": 46899
    },
    {
      "epoch": 1.440727429115596,
      "grad_norm": 0.4003332853317261,
      "learning_rate": 3.6277413300135777e-06,
      "loss": 0.5332,
      "step": 46900
    },
    {
      "epoch": 1.4407581482505454,
      "grad_norm": 0.41647830605506897,
      "learning_rate": 3.627368886678355e-06,
      "loss": 0.4823,
      "step": 46901
    },
    {
      "epoch": 1.4407888673854945,
      "grad_norm": 0.39124056696891785,
      "learning_rate": 3.6269964582268547e-06,
      "loss": 0.4999,
      "step": 46902
    },
    {
      "epoch": 1.4408195865204436,
      "grad_norm": 0.5363976359367371,
      "learning_rate": 3.6266240446599476e-06,
      "loss": 0.4817,
      "step": 46903
    },
    {
      "epoch": 1.4408503056553927,
      "grad_norm": 0.39481300115585327,
      "learning_rate": 3.626251645978507e-06,
      "loss": 0.5108,
      "step": 46904
    },
    {
      "epoch": 1.4408810247903419,
      "grad_norm": 0.4360710680484772,
      "learning_rate": 3.6258792621834028e-06,
      "loss": 0.5446,
      "step": 46905
    },
    {
      "epoch": 1.440911743925291,
      "grad_norm": 0.45527803897857666,
      "learning_rate": 3.6255068932755e-06,
      "loss": 0.4631,
      "step": 46906
    },
    {
      "epoch": 1.44094246306024,
      "grad_norm": 0.42988908290863037,
      "learning_rate": 3.6251345392556738e-06,
      "loss": 0.4488,
      "step": 46907
    },
    {
      "epoch": 1.4409731821951894,
      "grad_norm": 0.41319894790649414,
      "learning_rate": 3.624762200124785e-06,
      "loss": 0.4974,
      "step": 46908
    },
    {
      "epoch": 1.4410039013301386,
      "grad_norm": 0.44485175609588623,
      "learning_rate": 3.624389875883716e-06,
      "loss": 0.4002,
      "step": 46909
    },
    {
      "epoch": 1.4410346204650877,
      "grad_norm": 0.38221868872642517,
      "learning_rate": 3.6240175665333266e-06,
      "loss": 0.4539,
      "step": 46910
    },
    {
      "epoch": 1.4410653396000368,
      "grad_norm": 0.4457285702228546,
      "learning_rate": 3.6236452720744917e-06,
      "loss": 0.4538,
      "step": 46911
    },
    {
      "epoch": 1.4410960587349861,
      "grad_norm": 0.4779433310031891,
      "learning_rate": 3.6232729925080766e-06,
      "loss": 0.4338,
      "step": 46912
    },
    {
      "epoch": 1.4411267778699353,
      "grad_norm": 0.40891367197036743,
      "learning_rate": 3.622900727834948e-06,
      "loss": 0.5713,
      "step": 46913
    },
    {
      "epoch": 1.4411574970048844,
      "grad_norm": 0.4020546078681946,
      "learning_rate": 3.622528478055988e-06,
      "loss": 0.4766,
      "step": 46914
    },
    {
      "epoch": 1.4411882161398335,
      "grad_norm": 0.4165022671222687,
      "learning_rate": 3.622156243172055e-06,
      "loss": 0.4686,
      "step": 46915
    },
    {
      "epoch": 1.4412189352747826,
      "grad_norm": 0.39069873094558716,
      "learning_rate": 3.621784023184024e-06,
      "loss": 0.4867,
      "step": 46916
    },
    {
      "epoch": 1.4412496544097317,
      "grad_norm": 0.44787558913230896,
      "learning_rate": 3.621411818092755e-06,
      "loss": 0.4407,
      "step": 46917
    },
    {
      "epoch": 1.4412803735446809,
      "grad_norm": 0.4915401041507721,
      "learning_rate": 3.621039627899131e-06,
      "loss": 0.463,
      "step": 46918
    },
    {
      "epoch": 1.4413110926796302,
      "grad_norm": 0.40331003069877625,
      "learning_rate": 3.620667452604012e-06,
      "loss": 0.4605,
      "step": 46919
    },
    {
      "epoch": 1.4413418118145793,
      "grad_norm": 0.3908301889896393,
      "learning_rate": 3.6202952922082724e-06,
      "loss": 0.4637,
      "step": 46920
    },
    {
      "epoch": 1.4413725309495284,
      "grad_norm": 0.5811468958854675,
      "learning_rate": 3.619923146712775e-06,
      "loss": 0.4994,
      "step": 46921
    },
    {
      "epoch": 1.4414032500844776,
      "grad_norm": 0.4713244140148163,
      "learning_rate": 3.6195510161183934e-06,
      "loss": 0.5256,
      "step": 46922
    },
    {
      "epoch": 1.441433969219427,
      "grad_norm": 0.40311411023139954,
      "learning_rate": 3.619178900425996e-06,
      "loss": 0.4318,
      "step": 46923
    },
    {
      "epoch": 1.441464688354376,
      "grad_norm": 0.4399731159210205,
      "learning_rate": 3.618806799636454e-06,
      "loss": 0.4014,
      "step": 46924
    },
    {
      "epoch": 1.4414954074893251,
      "grad_norm": 0.4270787537097931,
      "learning_rate": 3.6184347137506325e-06,
      "loss": 0.4001,
      "step": 46925
    },
    {
      "epoch": 1.4415261266242743,
      "grad_norm": 0.45397159457206726,
      "learning_rate": 3.6180626427694023e-06,
      "loss": 0.4438,
      "step": 46926
    },
    {
      "epoch": 1.4415568457592234,
      "grad_norm": 0.45029526948928833,
      "learning_rate": 3.617690586693632e-06,
      "loss": 0.5009,
      "step": 46927
    },
    {
      "epoch": 1.4415875648941725,
      "grad_norm": 0.47509390115737915,
      "learning_rate": 3.6173185455241943e-06,
      "loss": 0.4212,
      "step": 46928
    },
    {
      "epoch": 1.4416182840291216,
      "grad_norm": 0.5369296669960022,
      "learning_rate": 3.616946519261951e-06,
      "loss": 0.4876,
      "step": 46929
    },
    {
      "epoch": 1.441649003164071,
      "grad_norm": 0.4519372880458832,
      "learning_rate": 3.6165745079077764e-06,
      "loss": 0.4954,
      "step": 46930
    },
    {
      "epoch": 1.44167972229902,
      "grad_norm": 0.4033958315849304,
      "learning_rate": 3.6162025114625364e-06,
      "loss": 0.4769,
      "step": 46931
    },
    {
      "epoch": 1.4417104414339692,
      "grad_norm": 0.4211256504058838,
      "learning_rate": 3.6158305299271024e-06,
      "loss": 0.5008,
      "step": 46932
    },
    {
      "epoch": 1.4417411605689183,
      "grad_norm": 0.42004820704460144,
      "learning_rate": 3.6154585633023443e-06,
      "loss": 0.528,
      "step": 46933
    },
    {
      "epoch": 1.4417718797038677,
      "grad_norm": 0.4073962867259979,
      "learning_rate": 3.615086611589126e-06,
      "loss": 0.5098,
      "step": 46934
    },
    {
      "epoch": 1.4418025988388168,
      "grad_norm": 0.40749967098236084,
      "learning_rate": 3.6147146747883187e-06,
      "loss": 0.4291,
      "step": 46935
    },
    {
      "epoch": 1.441833317973766,
      "grad_norm": 0.4175678789615631,
      "learning_rate": 3.614342752900791e-06,
      "loss": 0.4952,
      "step": 46936
    },
    {
      "epoch": 1.441864037108715,
      "grad_norm": 0.41275718808174133,
      "learning_rate": 3.613970845927416e-06,
      "loss": 0.4685,
      "step": 46937
    },
    {
      "epoch": 1.4418947562436641,
      "grad_norm": 0.47374945878982544,
      "learning_rate": 3.613598953869054e-06,
      "loss": 0.4877,
      "step": 46938
    },
    {
      "epoch": 1.4419254753786133,
      "grad_norm": 0.43707242608070374,
      "learning_rate": 3.6132270767265776e-06,
      "loss": 0.4663,
      "step": 46939
    },
    {
      "epoch": 1.4419561945135624,
      "grad_norm": 0.3814900517463684,
      "learning_rate": 3.6128552145008554e-06,
      "loss": 0.4755,
      "step": 46940
    },
    {
      "epoch": 1.4419869136485117,
      "grad_norm": 0.460660845041275,
      "learning_rate": 3.6124833671927606e-06,
      "loss": 0.5232,
      "step": 46941
    },
    {
      "epoch": 1.4420176327834608,
      "grad_norm": 0.37488093972206116,
      "learning_rate": 3.6121115348031522e-06,
      "loss": 0.5085,
      "step": 46942
    },
    {
      "epoch": 1.44204835191841,
      "grad_norm": 0.40804845094680786,
      "learning_rate": 3.6117397173329073e-06,
      "loss": 0.4587,
      "step": 46943
    },
    {
      "epoch": 1.442079071053359,
      "grad_norm": 0.4671480357646942,
      "learning_rate": 3.611367914782883e-06,
      "loss": 0.4895,
      "step": 46944
    },
    {
      "epoch": 1.4421097901883084,
      "grad_norm": 0.3943299949169159,
      "learning_rate": 3.610996127153963e-06,
      "loss": 0.4808,
      "step": 46945
    },
    {
      "epoch": 1.4421405093232575,
      "grad_norm": 0.41195711493492126,
      "learning_rate": 3.6106243544470033e-06,
      "loss": 0.522,
      "step": 46946
    },
    {
      "epoch": 1.4421712284582067,
      "grad_norm": 0.41553887724876404,
      "learning_rate": 3.610252596662881e-06,
      "loss": 0.4973,
      "step": 46947
    },
    {
      "epoch": 1.4422019475931558,
      "grad_norm": 0.41647619009017944,
      "learning_rate": 3.6098808538024556e-06,
      "loss": 0.4065,
      "step": 46948
    },
    {
      "epoch": 1.442232666728105,
      "grad_norm": 0.41881120204925537,
      "learning_rate": 3.609509125866597e-06,
      "loss": 0.4886,
      "step": 46949
    },
    {
      "epoch": 1.442263385863054,
      "grad_norm": 0.4125804603099823,
      "learning_rate": 3.609137412856183e-06,
      "loss": 0.4449,
      "step": 46950
    },
    {
      "epoch": 1.4422941049980031,
      "grad_norm": 0.42467692494392395,
      "learning_rate": 3.608765714772071e-06,
      "loss": 0.4745,
      "step": 46951
    },
    {
      "epoch": 1.4423248241329525,
      "grad_norm": 0.4124036431312561,
      "learning_rate": 3.6083940316151366e-06,
      "loss": 0.4841,
      "step": 46952
    },
    {
      "epoch": 1.4423555432679016,
      "grad_norm": 0.44698870182037354,
      "learning_rate": 3.608022363386241e-06,
      "loss": 0.5039,
      "step": 46953
    },
    {
      "epoch": 1.4423862624028507,
      "grad_norm": 0.3997388482093811,
      "learning_rate": 3.607650710086256e-06,
      "loss": 0.4466,
      "step": 46954
    },
    {
      "epoch": 1.4424169815377998,
      "grad_norm": 0.44246572256088257,
      "learning_rate": 3.607279071716049e-06,
      "loss": 0.5046,
      "step": 46955
    },
    {
      "epoch": 1.4424477006727492,
      "grad_norm": 0.4337342381477356,
      "learning_rate": 3.606907448276491e-06,
      "loss": 0.4233,
      "step": 46956
    },
    {
      "epoch": 1.4424784198076983,
      "grad_norm": 0.4164472818374634,
      "learning_rate": 3.6065358397684446e-06,
      "loss": 0.4846,
      "step": 46957
    },
    {
      "epoch": 1.4425091389426474,
      "grad_norm": 0.4190985858440399,
      "learning_rate": 3.606164246192779e-06,
      "loss": 0.4303,
      "step": 46958
    },
    {
      "epoch": 1.4425398580775965,
      "grad_norm": 0.40549436211586,
      "learning_rate": 3.605792667550365e-06,
      "loss": 0.4918,
      "step": 46959
    },
    {
      "epoch": 1.4425705772125457,
      "grad_norm": 0.3827851414680481,
      "learning_rate": 3.6054211038420717e-06,
      "loss": 0.481,
      "step": 46960
    },
    {
      "epoch": 1.4426012963474948,
      "grad_norm": 0.42934927344322205,
      "learning_rate": 3.6050495550687593e-06,
      "loss": 0.4332,
      "step": 46961
    },
    {
      "epoch": 1.442632015482444,
      "grad_norm": 0.39754942059516907,
      "learning_rate": 3.6046780212313016e-06,
      "loss": 0.4741,
      "step": 46962
    },
    {
      "epoch": 1.4426627346173932,
      "grad_norm": 0.4120253324508667,
      "learning_rate": 3.6043065023305644e-06,
      "loss": 0.4264,
      "step": 46963
    },
    {
      "epoch": 1.4426934537523424,
      "grad_norm": 0.4233764410018921,
      "learning_rate": 3.60393499836742e-06,
      "loss": 0.4195,
      "step": 46964
    },
    {
      "epoch": 1.4427241728872915,
      "grad_norm": 0.4267773926258087,
      "learning_rate": 3.603563509342729e-06,
      "loss": 0.3995,
      "step": 46965
    },
    {
      "epoch": 1.4427548920222406,
      "grad_norm": 0.44873616099357605,
      "learning_rate": 3.6031920352573613e-06,
      "loss": 0.4941,
      "step": 46966
    },
    {
      "epoch": 1.44278561115719,
      "grad_norm": 0.5199524760246277,
      "learning_rate": 3.602820576112186e-06,
      "loss": 0.5173,
      "step": 46967
    },
    {
      "epoch": 1.442816330292139,
      "grad_norm": 0.4227771461009979,
      "learning_rate": 3.602449131908069e-06,
      "loss": 0.4884,
      "step": 46968
    },
    {
      "epoch": 1.4428470494270882,
      "grad_norm": 0.4825298488140106,
      "learning_rate": 3.602077702645883e-06,
      "loss": 0.5726,
      "step": 46969
    },
    {
      "epoch": 1.4428777685620373,
      "grad_norm": 0.48523324728012085,
      "learning_rate": 3.6017062883264877e-06,
      "loss": 0.4223,
      "step": 46970
    },
    {
      "epoch": 1.4429084876969864,
      "grad_norm": 0.5133141875267029,
      "learning_rate": 3.6013348889507547e-06,
      "loss": 0.3748,
      "step": 46971
    },
    {
      "epoch": 1.4429392068319356,
      "grad_norm": 0.42840513586997986,
      "learning_rate": 3.60096350451955e-06,
      "loss": 0.4536,
      "step": 46972
    },
    {
      "epoch": 1.4429699259668847,
      "grad_norm": 0.4422522783279419,
      "learning_rate": 3.6005921350337456e-06,
      "loss": 0.5256,
      "step": 46973
    },
    {
      "epoch": 1.443000645101834,
      "grad_norm": 0.4377460777759552,
      "learning_rate": 3.6002207804942025e-06,
      "loss": 0.4459,
      "step": 46974
    },
    {
      "epoch": 1.4430313642367831,
      "grad_norm": 0.42454925179481506,
      "learning_rate": 3.5998494409017936e-06,
      "loss": 0.5291,
      "step": 46975
    },
    {
      "epoch": 1.4430620833717323,
      "grad_norm": 0.40564101934432983,
      "learning_rate": 3.5994781162573767e-06,
      "loss": 0.4726,
      "step": 46976
    },
    {
      "epoch": 1.4430928025066814,
      "grad_norm": 0.4109177589416504,
      "learning_rate": 3.599106806561833e-06,
      "loss": 0.4618,
      "step": 46977
    },
    {
      "epoch": 1.4431235216416305,
      "grad_norm": 0.4428861439228058,
      "learning_rate": 3.598735511816018e-06,
      "loss": 0.553,
      "step": 46978
    },
    {
      "epoch": 1.4431542407765798,
      "grad_norm": 0.4175433814525604,
      "learning_rate": 3.5983642320208078e-06,
      "loss": 0.484,
      "step": 46979
    },
    {
      "epoch": 1.443184959911529,
      "grad_norm": 0.43228259682655334,
      "learning_rate": 3.5979929671770575e-06,
      "loss": 0.4406,
      "step": 46980
    },
    {
      "epoch": 1.443215679046478,
      "grad_norm": 0.4226534068584442,
      "learning_rate": 3.5976217172856487e-06,
      "loss": 0.524,
      "step": 46981
    },
    {
      "epoch": 1.4432463981814272,
      "grad_norm": 0.4211077392101288,
      "learning_rate": 3.5972504823474372e-06,
      "loss": 0.5014,
      "step": 46982
    },
    {
      "epoch": 1.4432771173163763,
      "grad_norm": 0.4241202175617218,
      "learning_rate": 3.5968792623632985e-06,
      "loss": 0.5202,
      "step": 46983
    },
    {
      "epoch": 1.4433078364513254,
      "grad_norm": 0.46969473361968994,
      "learning_rate": 3.5965080573340928e-06,
      "loss": 0.4571,
      "step": 46984
    },
    {
      "epoch": 1.4433385555862746,
      "grad_norm": 0.48351871967315674,
      "learning_rate": 3.5961368672606856e-06,
      "loss": 0.5374,
      "step": 46985
    },
    {
      "epoch": 1.443369274721224,
      "grad_norm": 0.39860859513282776,
      "learning_rate": 3.5957656921439545e-06,
      "loss": 0.5001,
      "step": 46986
    },
    {
      "epoch": 1.443399993856173,
      "grad_norm": 0.40138083696365356,
      "learning_rate": 3.595394531984757e-06,
      "loss": 0.4706,
      "step": 46987
    },
    {
      "epoch": 1.4434307129911221,
      "grad_norm": 0.43596896529197693,
      "learning_rate": 3.5950233867839656e-06,
      "loss": 0.5327,
      "step": 46988
    },
    {
      "epoch": 1.4434614321260713,
      "grad_norm": 0.4018344283103943,
      "learning_rate": 3.5946522565424425e-06,
      "loss": 0.3663,
      "step": 46989
    },
    {
      "epoch": 1.4434921512610206,
      "grad_norm": 0.4635382294654846,
      "learning_rate": 3.5942811412610544e-06,
      "loss": 0.4655,
      "step": 46990
    },
    {
      "epoch": 1.4435228703959697,
      "grad_norm": 0.43809041380882263,
      "learning_rate": 3.593910040940671e-06,
      "loss": 0.469,
      "step": 46991
    },
    {
      "epoch": 1.4435535895309188,
      "grad_norm": 0.4148918390274048,
      "learning_rate": 3.593538955582162e-06,
      "loss": 0.5236,
      "step": 46992
    },
    {
      "epoch": 1.443584308665868,
      "grad_norm": 0.41588595509529114,
      "learning_rate": 3.5931678851863862e-06,
      "loss": 0.4182,
      "step": 46993
    },
    {
      "epoch": 1.443615027800817,
      "grad_norm": 0.42516788840293884,
      "learning_rate": 3.592796829754215e-06,
      "loss": 0.5841,
      "step": 46994
    },
    {
      "epoch": 1.4436457469357662,
      "grad_norm": 0.4121360182762146,
      "learning_rate": 3.5924257892865135e-06,
      "loss": 0.4744,
      "step": 46995
    },
    {
      "epoch": 1.4436764660707153,
      "grad_norm": 0.4907034635543823,
      "learning_rate": 3.592054763784153e-06,
      "loss": 0.4865,
      "step": 46996
    },
    {
      "epoch": 1.4437071852056647,
      "grad_norm": 0.3918057978153229,
      "learning_rate": 3.591683753247992e-06,
      "loss": 0.3898,
      "step": 46997
    },
    {
      "epoch": 1.4437379043406138,
      "grad_norm": 0.4129541516304016,
      "learning_rate": 3.591312757678901e-06,
      "loss": 0.5605,
      "step": 46998
    },
    {
      "epoch": 1.443768623475563,
      "grad_norm": 0.3906230330467224,
      "learning_rate": 3.590941777077748e-06,
      "loss": 0.4792,
      "step": 46999
    },
    {
      "epoch": 1.443799342610512,
      "grad_norm": 0.4028174579143524,
      "learning_rate": 3.5905708114453996e-06,
      "loss": 0.4858,
      "step": 47000
    },
    {
      "epoch": 1.4438300617454614,
      "grad_norm": 0.41024142503738403,
      "learning_rate": 3.5901998607827193e-06,
      "loss": 0.4879,
      "step": 47001
    },
    {
      "epoch": 1.4438607808804105,
      "grad_norm": 0.3861681818962097,
      "learning_rate": 3.5898289250905738e-06,
      "loss": 0.4063,
      "step": 47002
    },
    {
      "epoch": 1.4438915000153596,
      "grad_norm": 0.4257622957229614,
      "learning_rate": 3.58945800436983e-06,
      "loss": 0.5156,
      "step": 47003
    },
    {
      "epoch": 1.4439222191503087,
      "grad_norm": 0.3718927204608917,
      "learning_rate": 3.5890870986213555e-06,
      "loss": 0.4686,
      "step": 47004
    },
    {
      "epoch": 1.4439529382852578,
      "grad_norm": 0.41297194361686707,
      "learning_rate": 3.588716207846019e-06,
      "loss": 0.433,
      "step": 47005
    },
    {
      "epoch": 1.443983657420207,
      "grad_norm": 0.41141974925994873,
      "learning_rate": 3.5883453320446803e-06,
      "loss": 0.433,
      "step": 47006
    },
    {
      "epoch": 1.444014376555156,
      "grad_norm": 0.4200429618358612,
      "learning_rate": 3.5879744712182084e-06,
      "loss": 0.5389,
      "step": 47007
    },
    {
      "epoch": 1.4440450956901054,
      "grad_norm": 0.43177860975265503,
      "learning_rate": 3.5876036253674705e-06,
      "loss": 0.4573,
      "step": 47008
    },
    {
      "epoch": 1.4440758148250545,
      "grad_norm": 0.39270737767219543,
      "learning_rate": 3.587232794493336e-06,
      "loss": 0.4716,
      "step": 47009
    },
    {
      "epoch": 1.4441065339600037,
      "grad_norm": 0.45732393860816956,
      "learning_rate": 3.586861978596663e-06,
      "loss": 0.548,
      "step": 47010
    },
    {
      "epoch": 1.4441372530949528,
      "grad_norm": 0.42835327982902527,
      "learning_rate": 3.586491177678325e-06,
      "loss": 0.465,
      "step": 47011
    },
    {
      "epoch": 1.4441679722299021,
      "grad_norm": 0.4283141791820526,
      "learning_rate": 3.5861203917391784e-06,
      "loss": 0.3993,
      "step": 47012
    },
    {
      "epoch": 1.4441986913648512,
      "grad_norm": 0.49074310064315796,
      "learning_rate": 3.5857496207801023e-06,
      "loss": 0.4247,
      "step": 47013
    },
    {
      "epoch": 1.4442294104998004,
      "grad_norm": 0.4345904290676117,
      "learning_rate": 3.5853788648019526e-06,
      "loss": 0.5094,
      "step": 47014
    },
    {
      "epoch": 1.4442601296347495,
      "grad_norm": 0.4008941948413849,
      "learning_rate": 3.5850081238056024e-06,
      "loss": 0.3984,
      "step": 47015
    },
    {
      "epoch": 1.4442908487696986,
      "grad_norm": 0.4167834222316742,
      "learning_rate": 3.5846373977919093e-06,
      "loss": 0.4582,
      "step": 47016
    },
    {
      "epoch": 1.4443215679046477,
      "grad_norm": 0.41277721524238586,
      "learning_rate": 3.5842666867617437e-06,
      "loss": 0.3897,
      "step": 47017
    },
    {
      "epoch": 1.4443522870395968,
      "grad_norm": 0.43153077363967896,
      "learning_rate": 3.583895990715972e-06,
      "loss": 0.479,
      "step": 47018
    },
    {
      "epoch": 1.4443830061745462,
      "grad_norm": 0.4310196340084076,
      "learning_rate": 3.5835253096554623e-06,
      "loss": 0.4601,
      "step": 47019
    },
    {
      "epoch": 1.4444137253094953,
      "grad_norm": 0.4956705570220947,
      "learning_rate": 3.5831546435810737e-06,
      "loss": 0.5399,
      "step": 47020
    },
    {
      "epoch": 1.4444444444444444,
      "grad_norm": 0.491210013628006,
      "learning_rate": 3.582783992493677e-06,
      "loss": 0.4678,
      "step": 47021
    },
    {
      "epoch": 1.4444751635793935,
      "grad_norm": 1.1911604404449463,
      "learning_rate": 3.5824133563941354e-06,
      "loss": 0.4659,
      "step": 47022
    },
    {
      "epoch": 1.4445058827143429,
      "grad_norm": 0.47857028245925903,
      "learning_rate": 3.5820427352833155e-06,
      "loss": 0.4507,
      "step": 47023
    },
    {
      "epoch": 1.444536601849292,
      "grad_norm": 0.4843686819076538,
      "learning_rate": 3.581672129162086e-06,
      "loss": 0.4565,
      "step": 47024
    },
    {
      "epoch": 1.4445673209842411,
      "grad_norm": 0.45307597517967224,
      "learning_rate": 3.5813015380313065e-06,
      "loss": 0.4364,
      "step": 47025
    },
    {
      "epoch": 1.4445980401191902,
      "grad_norm": 0.4221023619174957,
      "learning_rate": 3.5809309618918464e-06,
      "loss": 0.5224,
      "step": 47026
    },
    {
      "epoch": 1.4446287592541394,
      "grad_norm": 0.47170448303222656,
      "learning_rate": 3.5805604007445695e-06,
      "loss": 0.4421,
      "step": 47027
    },
    {
      "epoch": 1.4446594783890885,
      "grad_norm": 0.4169037938117981,
      "learning_rate": 3.580189854590346e-06,
      "loss": 0.3622,
      "step": 47028
    },
    {
      "epoch": 1.4446901975240376,
      "grad_norm": 0.4375443458557129,
      "learning_rate": 3.5798193234300326e-06,
      "loss": 0.419,
      "step": 47029
    },
    {
      "epoch": 1.444720916658987,
      "grad_norm": 0.44068360328674316,
      "learning_rate": 3.5794488072645005e-06,
      "loss": 0.4812,
      "step": 47030
    },
    {
      "epoch": 1.444751635793936,
      "grad_norm": 0.39617496728897095,
      "learning_rate": 3.5790783060946145e-06,
      "loss": 0.4347,
      "step": 47031
    },
    {
      "epoch": 1.4447823549288852,
      "grad_norm": 0.40798136591911316,
      "learning_rate": 3.5787078199212434e-06,
      "loss": 0.4581,
      "step": 47032
    },
    {
      "epoch": 1.4448130740638343,
      "grad_norm": 0.41819658875465393,
      "learning_rate": 3.5783373487452442e-06,
      "loss": 0.4685,
      "step": 47033
    },
    {
      "epoch": 1.4448437931987836,
      "grad_norm": 0.4054775536060333,
      "learning_rate": 3.577966892567487e-06,
      "loss": 0.4695,
      "step": 47034
    },
    {
      "epoch": 1.4448745123337328,
      "grad_norm": 0.48093441128730774,
      "learning_rate": 3.577596451388836e-06,
      "loss": 0.4677,
      "step": 47035
    },
    {
      "epoch": 1.4449052314686819,
      "grad_norm": 0.4111379086971283,
      "learning_rate": 3.577226025210161e-06,
      "loss": 0.4823,
      "step": 47036
    },
    {
      "epoch": 1.444935950603631,
      "grad_norm": 0.41947031021118164,
      "learning_rate": 3.5768556140323195e-06,
      "loss": 0.4776,
      "step": 47037
    },
    {
      "epoch": 1.4449666697385801,
      "grad_norm": 0.4174295663833618,
      "learning_rate": 3.5764852178561847e-06,
      "loss": 0.5382,
      "step": 47038
    },
    {
      "epoch": 1.4449973888735292,
      "grad_norm": 0.43050724267959595,
      "learning_rate": 3.5761148366826094e-06,
      "loss": 0.5841,
      "step": 47039
    },
    {
      "epoch": 1.4450281080084784,
      "grad_norm": 0.4628523886203766,
      "learning_rate": 3.57574447051247e-06,
      "loss": 0.4778,
      "step": 47040
    },
    {
      "epoch": 1.4450588271434277,
      "grad_norm": 0.42054271697998047,
      "learning_rate": 3.5753741193466316e-06,
      "loss": 0.4745,
      "step": 47041
    },
    {
      "epoch": 1.4450895462783768,
      "grad_norm": 0.4354828894138336,
      "learning_rate": 3.575003783185953e-06,
      "loss": 0.5153,
      "step": 47042
    },
    {
      "epoch": 1.445120265413326,
      "grad_norm": 0.5458844900131226,
      "learning_rate": 3.5746334620313005e-06,
      "loss": 0.4033,
      "step": 47043
    },
    {
      "epoch": 1.445150984548275,
      "grad_norm": 0.4104478061199188,
      "learning_rate": 3.574263155883542e-06,
      "loss": 0.4734,
      "step": 47044
    },
    {
      "epoch": 1.4451817036832244,
      "grad_norm": 0.4067947566509247,
      "learning_rate": 3.573892864743542e-06,
      "loss": 0.4556,
      "step": 47045
    },
    {
      "epoch": 1.4452124228181735,
      "grad_norm": 0.41685208678245544,
      "learning_rate": 3.5735225886121625e-06,
      "loss": 0.475,
      "step": 47046
    },
    {
      "epoch": 1.4452431419531226,
      "grad_norm": 0.3666037917137146,
      "learning_rate": 3.5731523274902723e-06,
      "loss": 0.4688,
      "step": 47047
    },
    {
      "epoch": 1.4452738610880718,
      "grad_norm": 0.4053894579410553,
      "learning_rate": 3.5727820813787262e-06,
      "loss": 0.4926,
      "step": 47048
    },
    {
      "epoch": 1.4453045802230209,
      "grad_norm": 0.45030272006988525,
      "learning_rate": 3.5724118502784044e-06,
      "loss": 0.4455,
      "step": 47049
    },
    {
      "epoch": 1.44533529935797,
      "grad_norm": 0.40476658940315247,
      "learning_rate": 3.5720416341901596e-06,
      "loss": 0.5234,
      "step": 47050
    },
    {
      "epoch": 1.4453660184929191,
      "grad_norm": 0.41135284304618835,
      "learning_rate": 3.5716714331148637e-06,
      "loss": 0.4684,
      "step": 47051
    },
    {
      "epoch": 1.4453967376278685,
      "grad_norm": 0.39571624994277954,
      "learning_rate": 3.5713012470533758e-06,
      "loss": 0.4789,
      "step": 47052
    },
    {
      "epoch": 1.4454274567628176,
      "grad_norm": 0.46608108282089233,
      "learning_rate": 3.570931076006562e-06,
      "loss": 0.4688,
      "step": 47053
    },
    {
      "epoch": 1.4454581758977667,
      "grad_norm": 0.4211113452911377,
      "learning_rate": 3.5705609199752877e-06,
      "loss": 0.4955,
      "step": 47054
    },
    {
      "epoch": 1.4454888950327158,
      "grad_norm": 0.40046757459640503,
      "learning_rate": 3.5701907789604205e-06,
      "loss": 0.4874,
      "step": 47055
    },
    {
      "epoch": 1.4455196141676652,
      "grad_norm": 0.5139809250831604,
      "learning_rate": 3.5698206529628186e-06,
      "loss": 0.4657,
      "step": 47056
    },
    {
      "epoch": 1.4455503333026143,
      "grad_norm": 0.4068472981452942,
      "learning_rate": 3.56945054198335e-06,
      "loss": 0.4738,
      "step": 47057
    },
    {
      "epoch": 1.4455810524375634,
      "grad_norm": 0.403911292552948,
      "learning_rate": 3.569080446022879e-06,
      "loss": 0.4623,
      "step": 47058
    },
    {
      "epoch": 1.4456117715725125,
      "grad_norm": 0.38888823986053467,
      "learning_rate": 3.56871036508227e-06,
      "loss": 0.5061,
      "step": 47059
    },
    {
      "epoch": 1.4456424907074616,
      "grad_norm": 0.44388875365257263,
      "learning_rate": 3.5683402991623893e-06,
      "loss": 0.4651,
      "step": 47060
    },
    {
      "epoch": 1.4456732098424108,
      "grad_norm": 0.4073919355869293,
      "learning_rate": 3.5679702482640956e-06,
      "loss": 0.486,
      "step": 47061
    },
    {
      "epoch": 1.4457039289773599,
      "grad_norm": 0.43842363357543945,
      "learning_rate": 3.567600212388257e-06,
      "loss": 0.441,
      "step": 47062
    },
    {
      "epoch": 1.4457346481123092,
      "grad_norm": 0.4473862051963806,
      "learning_rate": 3.5672301915357376e-06,
      "loss": 0.4478,
      "step": 47063
    },
    {
      "epoch": 1.4457653672472583,
      "grad_norm": 0.42450201511383057,
      "learning_rate": 3.5668601857074046e-06,
      "loss": 0.5241,
      "step": 47064
    },
    {
      "epoch": 1.4457960863822075,
      "grad_norm": 0.38591888546943665,
      "learning_rate": 3.566490194904115e-06,
      "loss": 0.4076,
      "step": 47065
    },
    {
      "epoch": 1.4458268055171566,
      "grad_norm": 0.42026564478874207,
      "learning_rate": 3.5661202191267375e-06,
      "loss": 0.5106,
      "step": 47066
    },
    {
      "epoch": 1.445857524652106,
      "grad_norm": 0.43716639280319214,
      "learning_rate": 3.565750258376136e-06,
      "loss": 0.4436,
      "step": 47067
    },
    {
      "epoch": 1.445888243787055,
      "grad_norm": 0.4276410937309265,
      "learning_rate": 3.565380312653177e-06,
      "loss": 0.3885,
      "step": 47068
    },
    {
      "epoch": 1.4459189629220042,
      "grad_norm": 0.48211169242858887,
      "learning_rate": 3.5650103819587177e-06,
      "loss": 0.4833,
      "step": 47069
    },
    {
      "epoch": 1.4459496820569533,
      "grad_norm": 0.43255066871643066,
      "learning_rate": 3.5646404662936275e-06,
      "loss": 0.5038,
      "step": 47070
    },
    {
      "epoch": 1.4459804011919024,
      "grad_norm": 0.39710015058517456,
      "learning_rate": 3.5642705656587673e-06,
      "loss": 0.5356,
      "step": 47071
    },
    {
      "epoch": 1.4460111203268515,
      "grad_norm": 0.3858765959739685,
      "learning_rate": 3.563900680055007e-06,
      "loss": 0.508,
      "step": 47072
    },
    {
      "epoch": 1.4460418394618006,
      "grad_norm": 0.4338577687740326,
      "learning_rate": 3.5635308094832023e-06,
      "loss": 0.4612,
      "step": 47073
    },
    {
      "epoch": 1.44607255859675,
      "grad_norm": 0.4283938407897949,
      "learning_rate": 3.5631609539442246e-06,
      "loss": 0.5257,
      "step": 47074
    },
    {
      "epoch": 1.446103277731699,
      "grad_norm": 0.40873491764068604,
      "learning_rate": 3.562791113438927e-06,
      "loss": 0.4396,
      "step": 47075
    },
    {
      "epoch": 1.4461339968666482,
      "grad_norm": 0.398471862077713,
      "learning_rate": 3.5624212879681873e-06,
      "loss": 0.4801,
      "step": 47076
    },
    {
      "epoch": 1.4461647160015974,
      "grad_norm": 0.43203628063201904,
      "learning_rate": 3.5620514775328598e-06,
      "loss": 0.4931,
      "step": 47077
    },
    {
      "epoch": 1.4461954351365467,
      "grad_norm": 0.4215773940086365,
      "learning_rate": 3.5616816821338096e-06,
      "loss": 0.43,
      "step": 47078
    },
    {
      "epoch": 1.4462261542714958,
      "grad_norm": 0.4024560749530792,
      "learning_rate": 3.5613119017719045e-06,
      "loss": 0.5033,
      "step": 47079
    },
    {
      "epoch": 1.446256873406445,
      "grad_norm": 0.36871615052223206,
      "learning_rate": 3.560942136447999e-06,
      "loss": 0.4014,
      "step": 47080
    },
    {
      "epoch": 1.446287592541394,
      "grad_norm": 0.40461844205856323,
      "learning_rate": 3.5605723861629694e-06,
      "loss": 0.4181,
      "step": 47081
    },
    {
      "epoch": 1.4463183116763432,
      "grad_norm": 0.4384593069553375,
      "learning_rate": 3.5602026509176703e-06,
      "loss": 0.4626,
      "step": 47082
    },
    {
      "epoch": 1.4463490308112923,
      "grad_norm": 0.398730605840683,
      "learning_rate": 3.5598329307129697e-06,
      "loss": 0.502,
      "step": 47083
    },
    {
      "epoch": 1.4463797499462414,
      "grad_norm": 0.42900463938713074,
      "learning_rate": 3.559463225549723e-06,
      "loss": 0.5583,
      "step": 47084
    },
    {
      "epoch": 1.4464104690811908,
      "grad_norm": 0.38855698704719543,
      "learning_rate": 3.5590935354288057e-06,
      "loss": 0.4147,
      "step": 47085
    },
    {
      "epoch": 1.4464411882161399,
      "grad_norm": 0.40666428208351135,
      "learning_rate": 3.558723860351073e-06,
      "loss": 0.4333,
      "step": 47086
    },
    {
      "epoch": 1.446471907351089,
      "grad_norm": 0.41460779309272766,
      "learning_rate": 3.5583542003173934e-06,
      "loss": 0.4847,
      "step": 47087
    },
    {
      "epoch": 1.4465026264860381,
      "grad_norm": 0.4270111322402954,
      "learning_rate": 3.5579845553286243e-06,
      "loss": 0.4687,
      "step": 47088
    },
    {
      "epoch": 1.4465333456209872,
      "grad_norm": 0.4867623746395111,
      "learning_rate": 3.557614925385632e-06,
      "loss": 0.5031,
      "step": 47089
    },
    {
      "epoch": 1.4465640647559366,
      "grad_norm": 0.4182179272174835,
      "learning_rate": 3.55724531048928e-06,
      "loss": 0.5055,
      "step": 47090
    },
    {
      "epoch": 1.4465947838908857,
      "grad_norm": 0.4626270830631256,
      "learning_rate": 3.5568757106404352e-06,
      "loss": 0.4675,
      "step": 47091
    },
    {
      "epoch": 1.4466255030258348,
      "grad_norm": 0.3795279860496521,
      "learning_rate": 3.5565061258399524e-06,
      "loss": 0.383,
      "step": 47092
    },
    {
      "epoch": 1.446656222160784,
      "grad_norm": 0.44520410895347595,
      "learning_rate": 3.556136556088702e-06,
      "loss": 0.4294,
      "step": 47093
    },
    {
      "epoch": 1.446686941295733,
      "grad_norm": 0.43349212408065796,
      "learning_rate": 3.555767001387542e-06,
      "loss": 0.5142,
      "step": 47094
    },
    {
      "epoch": 1.4467176604306822,
      "grad_norm": 0.38160017132759094,
      "learning_rate": 3.55539746173734e-06,
      "loss": 0.3918,
      "step": 47095
    },
    {
      "epoch": 1.4467483795656315,
      "grad_norm": 0.4260237514972687,
      "learning_rate": 3.5550279371389607e-06,
      "loss": 0.5342,
      "step": 47096
    },
    {
      "epoch": 1.4467790987005806,
      "grad_norm": 0.4673876166343689,
      "learning_rate": 3.5546584275932594e-06,
      "loss": 0.5303,
      "step": 47097
    },
    {
      "epoch": 1.4468098178355298,
      "grad_norm": 0.41173693537712097,
      "learning_rate": 3.5542889331011044e-06,
      "loss": 0.4751,
      "step": 47098
    },
    {
      "epoch": 1.4468405369704789,
      "grad_norm": 0.43365171551704407,
      "learning_rate": 3.553919453663357e-06,
      "loss": 0.461,
      "step": 47099
    },
    {
      "epoch": 1.446871256105428,
      "grad_norm": 0.4305632710456848,
      "learning_rate": 3.5535499892808845e-06,
      "loss": 0.431,
      "step": 47100
    },
    {
      "epoch": 1.4469019752403773,
      "grad_norm": 0.4561481177806854,
      "learning_rate": 3.553180539954544e-06,
      "loss": 0.4798,
      "step": 47101
    },
    {
      "epoch": 1.4469326943753265,
      "grad_norm": 0.41177695989608765,
      "learning_rate": 3.552811105685199e-06,
      "loss": 0.4597,
      "step": 47102
    },
    {
      "epoch": 1.4469634135102756,
      "grad_norm": 0.41872847080230713,
      "learning_rate": 3.5524416864737145e-06,
      "loss": 0.4589,
      "step": 47103
    },
    {
      "epoch": 1.4469941326452247,
      "grad_norm": 0.4247339367866516,
      "learning_rate": 3.5520722823209563e-06,
      "loss": 0.4515,
      "step": 47104
    },
    {
      "epoch": 1.4470248517801738,
      "grad_norm": 0.47666555643081665,
      "learning_rate": 3.55170289322778e-06,
      "loss": 0.4644,
      "step": 47105
    },
    {
      "epoch": 1.447055570915123,
      "grad_norm": 0.42109909653663635,
      "learning_rate": 3.5513335191950517e-06,
      "loss": 0.5,
      "step": 47106
    },
    {
      "epoch": 1.447086290050072,
      "grad_norm": 0.4012517035007477,
      "learning_rate": 3.5509641602236345e-06,
      "loss": 0.5199,
      "step": 47107
    },
    {
      "epoch": 1.4471170091850214,
      "grad_norm": 0.4306296110153198,
      "learning_rate": 3.5505948163143943e-06,
      "loss": 0.4563,
      "step": 47108
    },
    {
      "epoch": 1.4471477283199705,
      "grad_norm": 0.42353785037994385,
      "learning_rate": 3.5502254874681874e-06,
      "loss": 0.474,
      "step": 47109
    },
    {
      "epoch": 1.4471784474549196,
      "grad_norm": 0.42840200662612915,
      "learning_rate": 3.5498561736858826e-06,
      "loss": 0.497,
      "step": 47110
    },
    {
      "epoch": 1.4472091665898688,
      "grad_norm": 0.4736889600753784,
      "learning_rate": 3.549486874968332e-06,
      "loss": 0.4036,
      "step": 47111
    },
    {
      "epoch": 1.447239885724818,
      "grad_norm": 0.3806871175765991,
      "learning_rate": 3.549117591316412e-06,
      "loss": 0.4428,
      "step": 47112
    },
    {
      "epoch": 1.4472706048597672,
      "grad_norm": 0.42658019065856934,
      "learning_rate": 3.5487483227309748e-06,
      "loss": 0.4637,
      "step": 47113
    },
    {
      "epoch": 1.4473013239947163,
      "grad_norm": 0.44598811864852905,
      "learning_rate": 3.5483790692128873e-06,
      "loss": 0.4101,
      "step": 47114
    },
    {
      "epoch": 1.4473320431296655,
      "grad_norm": 0.41024836897850037,
      "learning_rate": 3.548009830763014e-06,
      "loss": 0.3714,
      "step": 47115
    },
    {
      "epoch": 1.4473627622646146,
      "grad_norm": 0.4501691162586212,
      "learning_rate": 3.5476406073822077e-06,
      "loss": 0.4168,
      "step": 47116
    },
    {
      "epoch": 1.4473934813995637,
      "grad_norm": 0.42542386054992676,
      "learning_rate": 3.5472713990713435e-06,
      "loss": 0.3849,
      "step": 47117
    },
    {
      "epoch": 1.4474242005345128,
      "grad_norm": 0.4053618609905243,
      "learning_rate": 3.5469022058312753e-06,
      "loss": 0.4236,
      "step": 47118
    },
    {
      "epoch": 1.4474549196694622,
      "grad_norm": 0.4316994547843933,
      "learning_rate": 3.5465330276628705e-06,
      "loss": 0.5278,
      "step": 47119
    },
    {
      "epoch": 1.4474856388044113,
      "grad_norm": 0.4400242865085602,
      "learning_rate": 3.546163864566985e-06,
      "loss": 0.5112,
      "step": 47120
    },
    {
      "epoch": 1.4475163579393604,
      "grad_norm": 0.41305476427078247,
      "learning_rate": 3.545794716544485e-06,
      "loss": 0.4681,
      "step": 47121
    },
    {
      "epoch": 1.4475470770743095,
      "grad_norm": 0.45902660489082336,
      "learning_rate": 3.5454255835962313e-06,
      "loss": 0.3905,
      "step": 47122
    },
    {
      "epoch": 1.4475777962092589,
      "grad_norm": 0.4477684497833252,
      "learning_rate": 3.5450564657230914e-06,
      "loss": 0.5261,
      "step": 47123
    },
    {
      "epoch": 1.447608515344208,
      "grad_norm": 0.39379605650901794,
      "learning_rate": 3.5446873629259195e-06,
      "loss": 0.4386,
      "step": 47124
    },
    {
      "epoch": 1.447639234479157,
      "grad_norm": 0.44204607605934143,
      "learning_rate": 3.5443182752055804e-06,
      "loss": 0.4695,
      "step": 47125
    },
    {
      "epoch": 1.4476699536141062,
      "grad_norm": 0.5270889401435852,
      "learning_rate": 3.5439492025629373e-06,
      "loss": 0.4448,
      "step": 47126
    },
    {
      "epoch": 1.4477006727490553,
      "grad_norm": 0.3852818012237549,
      "learning_rate": 3.543580144998855e-06,
      "loss": 0.4194,
      "step": 47127
    },
    {
      "epoch": 1.4477313918840045,
      "grad_norm": 0.41497066617012024,
      "learning_rate": 3.543211102514188e-06,
      "loss": 0.5542,
      "step": 47128
    },
    {
      "epoch": 1.4477621110189536,
      "grad_norm": 0.42232954502105713,
      "learning_rate": 3.5428420751098035e-06,
      "loss": 0.4723,
      "step": 47129
    },
    {
      "epoch": 1.447792830153903,
      "grad_norm": 0.435806006193161,
      "learning_rate": 3.5424730627865623e-06,
      "loss": 0.4505,
      "step": 47130
    },
    {
      "epoch": 1.447823549288852,
      "grad_norm": 0.43885061144828796,
      "learning_rate": 3.5421040655453255e-06,
      "loss": 0.5063,
      "step": 47131
    },
    {
      "epoch": 1.4478542684238012,
      "grad_norm": 0.5470870733261108,
      "learning_rate": 3.541735083386959e-06,
      "loss": 0.4728,
      "step": 47132
    },
    {
      "epoch": 1.4478849875587503,
      "grad_norm": 0.41192060708999634,
      "learning_rate": 3.541366116312318e-06,
      "loss": 0.5176,
      "step": 47133
    },
    {
      "epoch": 1.4479157066936996,
      "grad_norm": 0.40594282746315,
      "learning_rate": 3.5409971643222684e-06,
      "loss": 0.4639,
      "step": 47134
    },
    {
      "epoch": 1.4479464258286487,
      "grad_norm": 0.44083499908447266,
      "learning_rate": 3.5406282274176707e-06,
      "loss": 0.4917,
      "step": 47135
    },
    {
      "epoch": 1.4479771449635979,
      "grad_norm": 0.44378170371055603,
      "learning_rate": 3.5402593055993896e-06,
      "loss": 0.5103,
      "step": 47136
    },
    {
      "epoch": 1.448007864098547,
      "grad_norm": 0.4489729404449463,
      "learning_rate": 3.539890398868281e-06,
      "loss": 0.504,
      "step": 47137
    },
    {
      "epoch": 1.448038583233496,
      "grad_norm": 0.46211230754852295,
      "learning_rate": 3.53952150722521e-06,
      "loss": 0.5285,
      "step": 47138
    },
    {
      "epoch": 1.4480693023684452,
      "grad_norm": 0.38862982392311096,
      "learning_rate": 3.5391526306710367e-06,
      "loss": 0.4705,
      "step": 47139
    },
    {
      "epoch": 1.4481000215033943,
      "grad_norm": 0.5088213086128235,
      "learning_rate": 3.5387837692066275e-06,
      "loss": 0.3671,
      "step": 47140
    },
    {
      "epoch": 1.4481307406383437,
      "grad_norm": 0.41368862986564636,
      "learning_rate": 3.5384149228328367e-06,
      "loss": 0.471,
      "step": 47141
    },
    {
      "epoch": 1.4481614597732928,
      "grad_norm": 0.4572671055793762,
      "learning_rate": 3.538046091550533e-06,
      "loss": 0.452,
      "step": 47142
    },
    {
      "epoch": 1.448192178908242,
      "grad_norm": 0.44137242436408997,
      "learning_rate": 3.537677275360566e-06,
      "loss": 0.5358,
      "step": 47143
    },
    {
      "epoch": 1.448222898043191,
      "grad_norm": 0.4038809835910797,
      "learning_rate": 3.537308474263813e-06,
      "loss": 0.4352,
      "step": 47144
    },
    {
      "epoch": 1.4482536171781404,
      "grad_norm": 0.45332929491996765,
      "learning_rate": 3.536939688261124e-06,
      "loss": 0.5318,
      "step": 47145
    },
    {
      "epoch": 1.4482843363130895,
      "grad_norm": 0.4188506007194519,
      "learning_rate": 3.536570917353367e-06,
      "loss": 0.4797,
      "step": 47146
    },
    {
      "epoch": 1.4483150554480386,
      "grad_norm": 0.7789732217788696,
      "learning_rate": 3.5362021615413924e-06,
      "loss": 0.4129,
      "step": 47147
    },
    {
      "epoch": 1.4483457745829877,
      "grad_norm": 0.4559887945652008,
      "learning_rate": 3.535833420826076e-06,
      "loss": 0.4735,
      "step": 47148
    },
    {
      "epoch": 1.4483764937179369,
      "grad_norm": 0.3889719247817993,
      "learning_rate": 3.5354646952082695e-06,
      "loss": 0.4305,
      "step": 47149
    },
    {
      "epoch": 1.448407212852886,
      "grad_norm": 0.43125084042549133,
      "learning_rate": 3.5350959846888365e-06,
      "loss": 0.4817,
      "step": 47150
    },
    {
      "epoch": 1.448437931987835,
      "grad_norm": 0.42114347219467163,
      "learning_rate": 3.534727289268641e-06,
      "loss": 0.484,
      "step": 47151
    },
    {
      "epoch": 1.4484686511227844,
      "grad_norm": 0.3998834192752838,
      "learning_rate": 3.534358608948536e-06,
      "loss": 0.4885,
      "step": 47152
    },
    {
      "epoch": 1.4484993702577336,
      "grad_norm": 0.443996399641037,
      "learning_rate": 3.533989943729393e-06,
      "loss": 0.4841,
      "step": 47153
    },
    {
      "epoch": 1.4485300893926827,
      "grad_norm": 0.4147988259792328,
      "learning_rate": 3.533621293612066e-06,
      "loss": 0.4717,
      "step": 47154
    },
    {
      "epoch": 1.4485608085276318,
      "grad_norm": 0.443365216255188,
      "learning_rate": 3.5332526585974214e-06,
      "loss": 0.4501,
      "step": 47155
    },
    {
      "epoch": 1.4485915276625811,
      "grad_norm": 0.3803638219833374,
      "learning_rate": 3.5328840386863127e-06,
      "loss": 0.4944,
      "step": 47156
    },
    {
      "epoch": 1.4486222467975303,
      "grad_norm": 0.4595103859901428,
      "learning_rate": 3.5325154338796065e-06,
      "loss": 0.4871,
      "step": 47157
    },
    {
      "epoch": 1.4486529659324794,
      "grad_norm": 0.4079839289188385,
      "learning_rate": 3.5321468441781604e-06,
      "loss": 0.4104,
      "step": 47158
    },
    {
      "epoch": 1.4486836850674285,
      "grad_norm": 0.3945207893848419,
      "learning_rate": 3.5317782695828417e-06,
      "loss": 0.5016,
      "step": 47159
    },
    {
      "epoch": 1.4487144042023776,
      "grad_norm": 0.4614993631839752,
      "learning_rate": 3.5314097100945022e-06,
      "loss": 0.4723,
      "step": 47160
    },
    {
      "epoch": 1.4487451233373267,
      "grad_norm": 0.41949018836021423,
      "learning_rate": 3.5310411657140076e-06,
      "loss": 0.5404,
      "step": 47161
    },
    {
      "epoch": 1.4487758424722759,
      "grad_norm": 0.41079118847846985,
      "learning_rate": 3.5306726364422183e-06,
      "loss": 0.4936,
      "step": 47162
    },
    {
      "epoch": 1.4488065616072252,
      "grad_norm": 0.44690877199172974,
      "learning_rate": 3.5303041222799984e-06,
      "loss": 0.4175,
      "step": 47163
    },
    {
      "epoch": 1.4488372807421743,
      "grad_norm": 0.43717139959335327,
      "learning_rate": 3.5299356232282013e-06,
      "loss": 0.4753,
      "step": 47164
    },
    {
      "epoch": 1.4488679998771234,
      "grad_norm": 0.40991270542144775,
      "learning_rate": 3.5295671392876917e-06,
      "loss": 0.4747,
      "step": 47165
    },
    {
      "epoch": 1.4488987190120726,
      "grad_norm": 0.42123523354530334,
      "learning_rate": 3.5291986704593295e-06,
      "loss": 0.4567,
      "step": 47166
    },
    {
      "epoch": 1.448929438147022,
      "grad_norm": 0.39068403840065,
      "learning_rate": 3.528830216743979e-06,
      "loss": 0.4324,
      "step": 47167
    },
    {
      "epoch": 1.448960157281971,
      "grad_norm": 0.42656955122947693,
      "learning_rate": 3.5284617781424945e-06,
      "loss": 0.455,
      "step": 47168
    },
    {
      "epoch": 1.4489908764169201,
      "grad_norm": 0.4208810031414032,
      "learning_rate": 3.5280933546557394e-06,
      "loss": 0.3659,
      "step": 47169
    },
    {
      "epoch": 1.4490215955518693,
      "grad_norm": 0.4203014075756073,
      "learning_rate": 3.527724946284574e-06,
      "loss": 0.5182,
      "step": 47170
    },
    {
      "epoch": 1.4490523146868184,
      "grad_norm": 3.1659317016601562,
      "learning_rate": 3.5273565530298593e-06,
      "loss": 0.4808,
      "step": 47171
    },
    {
      "epoch": 1.4490830338217675,
      "grad_norm": 0.43398261070251465,
      "learning_rate": 3.5269881748924593e-06,
      "loss": 0.4516,
      "step": 47172
    },
    {
      "epoch": 1.4491137529567166,
      "grad_norm": 0.4231516718864441,
      "learning_rate": 3.5266198118732264e-06,
      "loss": 0.4931,
      "step": 47173
    },
    {
      "epoch": 1.449144472091666,
      "grad_norm": 0.3794015049934387,
      "learning_rate": 3.526251463973025e-06,
      "loss": 0.4733,
      "step": 47174
    },
    {
      "epoch": 1.449175191226615,
      "grad_norm": 0.4582330286502838,
      "learning_rate": 3.5258831311927156e-06,
      "loss": 0.476,
      "step": 47175
    },
    {
      "epoch": 1.4492059103615642,
      "grad_norm": 0.4438491761684418,
      "learning_rate": 3.5255148135331617e-06,
      "loss": 0.4977,
      "step": 47176
    },
    {
      "epoch": 1.4492366294965133,
      "grad_norm": 0.44322606921195984,
      "learning_rate": 3.5251465109952166e-06,
      "loss": 0.4945,
      "step": 47177
    },
    {
      "epoch": 1.4492673486314627,
      "grad_norm": 0.45907995104789734,
      "learning_rate": 3.524778223579748e-06,
      "loss": 0.4866,
      "step": 47178
    },
    {
      "epoch": 1.4492980677664118,
      "grad_norm": 0.44552314281463623,
      "learning_rate": 3.5244099512876052e-06,
      "loss": 0.4941,
      "step": 47179
    },
    {
      "epoch": 1.449328786901361,
      "grad_norm": 0.4301063120365143,
      "learning_rate": 3.524041694119661e-06,
      "loss": 0.4818,
      "step": 47180
    },
    {
      "epoch": 1.44935950603631,
      "grad_norm": 0.3851450979709625,
      "learning_rate": 3.5236734520767667e-06,
      "loss": 0.4102,
      "step": 47181
    },
    {
      "epoch": 1.4493902251712592,
      "grad_norm": 0.37282830476760864,
      "learning_rate": 3.52330522515979e-06,
      "loss": 0.4514,
      "step": 47182
    },
    {
      "epoch": 1.4494209443062083,
      "grad_norm": 0.5108607411384583,
      "learning_rate": 3.5229370133695817e-06,
      "loss": 0.4922,
      "step": 47183
    },
    {
      "epoch": 1.4494516634411574,
      "grad_norm": 0.4260479211807251,
      "learning_rate": 3.522568816707006e-06,
      "loss": 0.4542,
      "step": 47184
    },
    {
      "epoch": 1.4494823825761067,
      "grad_norm": 0.43171751499176025,
      "learning_rate": 3.5222006351729245e-06,
      "loss": 0.4847,
      "step": 47185
    },
    {
      "epoch": 1.4495131017110559,
      "grad_norm": 0.4102417528629303,
      "learning_rate": 3.521832468768195e-06,
      "loss": 0.5028,
      "step": 47186
    },
    {
      "epoch": 1.449543820846005,
      "grad_norm": 0.41536104679107666,
      "learning_rate": 3.5214643174936814e-06,
      "loss": 0.3893,
      "step": 47187
    },
    {
      "epoch": 1.449574539980954,
      "grad_norm": 0.37293538451194763,
      "learning_rate": 3.521096181350233e-06,
      "loss": 0.4557,
      "step": 47188
    },
    {
      "epoch": 1.4496052591159034,
      "grad_norm": 0.430217981338501,
      "learning_rate": 3.5207280603387253e-06,
      "loss": 0.4476,
      "step": 47189
    },
    {
      "epoch": 1.4496359782508526,
      "grad_norm": 0.5061022043228149,
      "learning_rate": 3.5203599544600054e-06,
      "loss": 0.4601,
      "step": 47190
    },
    {
      "epoch": 1.4496666973858017,
      "grad_norm": 0.49147939682006836,
      "learning_rate": 3.519991863714941e-06,
      "loss": 0.5675,
      "step": 47191
    },
    {
      "epoch": 1.4496974165207508,
      "grad_norm": 0.4420156478881836,
      "learning_rate": 3.519623788104385e-06,
      "loss": 0.509,
      "step": 47192
    },
    {
      "epoch": 1.4497281356557,
      "grad_norm": 0.4565134644508362,
      "learning_rate": 3.5192557276291993e-06,
      "loss": 0.439,
      "step": 47193
    },
    {
      "epoch": 1.449758854790649,
      "grad_norm": 0.426461398601532,
      "learning_rate": 3.518887682290245e-06,
      "loss": 0.4563,
      "step": 47194
    },
    {
      "epoch": 1.4497895739255982,
      "grad_norm": 0.5190335512161255,
      "learning_rate": 3.5185196520883845e-06,
      "loss": 0.4573,
      "step": 47195
    },
    {
      "epoch": 1.4498202930605475,
      "grad_norm": 0.4331235885620117,
      "learning_rate": 3.518151637024472e-06,
      "loss": 0.4981,
      "step": 47196
    },
    {
      "epoch": 1.4498510121954966,
      "grad_norm": 0.42637041211128235,
      "learning_rate": 3.517783637099367e-06,
      "loss": 0.4323,
      "step": 47197
    },
    {
      "epoch": 1.4498817313304457,
      "grad_norm": 0.39567333459854126,
      "learning_rate": 3.517415652313931e-06,
      "loss": 0.4132,
      "step": 47198
    },
    {
      "epoch": 1.4499124504653949,
      "grad_norm": 0.4162543714046478,
      "learning_rate": 3.517047682669028e-06,
      "loss": 0.5088,
      "step": 47199
    },
    {
      "epoch": 1.449943169600344,
      "grad_norm": 0.4252967834472656,
      "learning_rate": 3.5166797281655097e-06,
      "loss": 0.4991,
      "step": 47200
    },
    {
      "epoch": 1.4499738887352933,
      "grad_norm": 0.4077516496181488,
      "learning_rate": 3.516311788804239e-06,
      "loss": 0.4759,
      "step": 47201
    },
    {
      "epoch": 1.4500046078702424,
      "grad_norm": 0.39868804812431335,
      "learning_rate": 3.5159438645860735e-06,
      "loss": 0.4671,
      "step": 47202
    },
    {
      "epoch": 1.4500353270051916,
      "grad_norm": 0.43344008922576904,
      "learning_rate": 3.5155759555118772e-06,
      "loss": 0.4773,
      "step": 47203
    },
    {
      "epoch": 1.4500660461401407,
      "grad_norm": 0.4301547408103943,
      "learning_rate": 3.5152080615825047e-06,
      "loss": 0.4674,
      "step": 47204
    },
    {
      "epoch": 1.4500967652750898,
      "grad_norm": 0.483993798494339,
      "learning_rate": 3.5148401827988144e-06,
      "loss": 0.5308,
      "step": 47205
    },
    {
      "epoch": 1.450127484410039,
      "grad_norm": 0.44541478157043457,
      "learning_rate": 3.514472319161669e-06,
      "loss": 0.4472,
      "step": 47206
    },
    {
      "epoch": 1.4501582035449883,
      "grad_norm": 0.44056546688079834,
      "learning_rate": 3.514104470671926e-06,
      "loss": 0.4515,
      "step": 47207
    },
    {
      "epoch": 1.4501889226799374,
      "grad_norm": 0.41262272000312805,
      "learning_rate": 3.5137366373304493e-06,
      "loss": 0.4674,
      "step": 47208
    },
    {
      "epoch": 1.4502196418148865,
      "grad_norm": 0.4092956483364105,
      "learning_rate": 3.51336881913809e-06,
      "loss": 0.4349,
      "step": 47209
    },
    {
      "epoch": 1.4502503609498356,
      "grad_norm": 0.45598360896110535,
      "learning_rate": 3.5130010160957096e-06,
      "loss": 0.4688,
      "step": 47210
    },
    {
      "epoch": 1.4502810800847847,
      "grad_norm": 0.43898841738700867,
      "learning_rate": 3.5126332282041695e-06,
      "loss": 0.5229,
      "step": 47211
    },
    {
      "epoch": 1.450311799219734,
      "grad_norm": 0.4076044261455536,
      "learning_rate": 3.512265455464331e-06,
      "loss": 0.459,
      "step": 47212
    },
    {
      "epoch": 1.4503425183546832,
      "grad_norm": 0.4907708764076233,
      "learning_rate": 3.5118976978770457e-06,
      "loss": 0.4458,
      "step": 47213
    },
    {
      "epoch": 1.4503732374896323,
      "grad_norm": 0.42275214195251465,
      "learning_rate": 3.5115299554431804e-06,
      "loss": 0.4287,
      "step": 47214
    },
    {
      "epoch": 1.4504039566245814,
      "grad_norm": 0.44848906993865967,
      "learning_rate": 3.5111622281635825e-06,
      "loss": 0.4378,
      "step": 47215
    },
    {
      "epoch": 1.4504346757595306,
      "grad_norm": 0.41141849756240845,
      "learning_rate": 3.5107945160391256e-06,
      "loss": 0.4677,
      "step": 47216
    },
    {
      "epoch": 1.4504653948944797,
      "grad_norm": 0.4491733908653259,
      "learning_rate": 3.510426819070658e-06,
      "loss": 0.3956,
      "step": 47217
    },
    {
      "epoch": 1.4504961140294288,
      "grad_norm": 0.41346949338912964,
      "learning_rate": 3.5100591372590455e-06,
      "loss": 0.4889,
      "step": 47218
    },
    {
      "epoch": 1.4505268331643781,
      "grad_norm": 0.44500407576560974,
      "learning_rate": 3.5096914706051388e-06,
      "loss": 0.4979,
      "step": 47219
    },
    {
      "epoch": 1.4505575522993273,
      "grad_norm": 0.432211309671402,
      "learning_rate": 3.5093238191098023e-06,
      "loss": 0.4089,
      "step": 47220
    },
    {
      "epoch": 1.4505882714342764,
      "grad_norm": 0.41888269782066345,
      "learning_rate": 3.5089561827738915e-06,
      "loss": 0.537,
      "step": 47221
    },
    {
      "epoch": 1.4506189905692255,
      "grad_norm": 0.45429015159606934,
      "learning_rate": 3.5085885615982717e-06,
      "loss": 0.5146,
      "step": 47222
    },
    {
      "epoch": 1.4506497097041748,
      "grad_norm": 0.40121686458587646,
      "learning_rate": 3.5082209555837933e-06,
      "loss": 0.4089,
      "step": 47223
    },
    {
      "epoch": 1.450680428839124,
      "grad_norm": 0.45001736283302307,
      "learning_rate": 3.5078533647313174e-06,
      "loss": 0.5368,
      "step": 47224
    },
    {
      "epoch": 1.450711147974073,
      "grad_norm": 0.4156252443790436,
      "learning_rate": 3.5074857890417036e-06,
      "loss": 0.3634,
      "step": 47225
    },
    {
      "epoch": 1.4507418671090222,
      "grad_norm": 0.4194670617580414,
      "learning_rate": 3.507118228515811e-06,
      "loss": 0.481,
      "step": 47226
    },
    {
      "epoch": 1.4507725862439713,
      "grad_norm": 0.4221617579460144,
      "learning_rate": 3.5067506831544996e-06,
      "loss": 0.4914,
      "step": 47227
    },
    {
      "epoch": 1.4508033053789204,
      "grad_norm": 0.41643625497817993,
      "learning_rate": 3.5063831529586222e-06,
      "loss": 0.4702,
      "step": 47228
    },
    {
      "epoch": 1.4508340245138696,
      "grad_norm": 0.4670390486717224,
      "learning_rate": 3.5060156379290412e-06,
      "loss": 0.5302,
      "step": 47229
    },
    {
      "epoch": 1.450864743648819,
      "grad_norm": 0.44697725772857666,
      "learning_rate": 3.505648138066613e-06,
      "loss": 0.424,
      "step": 47230
    },
    {
      "epoch": 1.450895462783768,
      "grad_norm": 0.4285815358161926,
      "learning_rate": 3.5052806533722017e-06,
      "loss": 0.4868,
      "step": 47231
    },
    {
      "epoch": 1.4509261819187171,
      "grad_norm": 0.41644221544265747,
      "learning_rate": 3.504913183846658e-06,
      "loss": 0.501,
      "step": 47232
    },
    {
      "epoch": 1.4509569010536663,
      "grad_norm": 0.4045933187007904,
      "learning_rate": 3.5045457294908414e-06,
      "loss": 0.4483,
      "step": 47233
    },
    {
      "epoch": 1.4509876201886156,
      "grad_norm": 0.45832133293151855,
      "learning_rate": 3.5041782903056134e-06,
      "loss": 0.4186,
      "step": 47234
    },
    {
      "epoch": 1.4510183393235647,
      "grad_norm": 0.4067687690258026,
      "learning_rate": 3.5038108662918334e-06,
      "loss": 0.4925,
      "step": 47235
    },
    {
      "epoch": 1.4510490584585138,
      "grad_norm": 0.467128723859787,
      "learning_rate": 3.5034434574503528e-06,
      "loss": 0.4641,
      "step": 47236
    },
    {
      "epoch": 1.451079777593463,
      "grad_norm": 0.3908812701702118,
      "learning_rate": 3.503076063782035e-06,
      "loss": 0.3707,
      "step": 47237
    },
    {
      "epoch": 1.451110496728412,
      "grad_norm": 0.4305885136127472,
      "learning_rate": 3.502708685287736e-06,
      "loss": 0.4953,
      "step": 47238
    },
    {
      "epoch": 1.4511412158633612,
      "grad_norm": 0.4476401209831238,
      "learning_rate": 3.5023413219683177e-06,
      "loss": 0.4799,
      "step": 47239
    },
    {
      "epoch": 1.4511719349983103,
      "grad_norm": 0.48499515652656555,
      "learning_rate": 3.5019739738246328e-06,
      "loss": 0.4829,
      "step": 47240
    },
    {
      "epoch": 1.4512026541332597,
      "grad_norm": 0.4152323603630066,
      "learning_rate": 3.5016066408575413e-06,
      "loss": 0.3452,
      "step": 47241
    },
    {
      "epoch": 1.4512333732682088,
      "grad_norm": 0.40248212218284607,
      "learning_rate": 3.5012393230679008e-06,
      "loss": 0.4867,
      "step": 47242
    },
    {
      "epoch": 1.451264092403158,
      "grad_norm": 0.7330121994018555,
      "learning_rate": 3.5008720204565693e-06,
      "loss": 0.4822,
      "step": 47243
    },
    {
      "epoch": 1.451294811538107,
      "grad_norm": 0.4034031629562378,
      "learning_rate": 3.5005047330244093e-06,
      "loss": 0.5199,
      "step": 47244
    },
    {
      "epoch": 1.4513255306730564,
      "grad_norm": 0.5502511858940125,
      "learning_rate": 3.5001374607722705e-06,
      "loss": 0.4822,
      "step": 47245
    },
    {
      "epoch": 1.4513562498080055,
      "grad_norm": 0.4073840081691742,
      "learning_rate": 3.4997702037010184e-06,
      "loss": 0.4732,
      "step": 47246
    },
    {
      "epoch": 1.4513869689429546,
      "grad_norm": 0.40947338938713074,
      "learning_rate": 3.4994029618115e-06,
      "loss": 0.4366,
      "step": 47247
    },
    {
      "epoch": 1.4514176880779037,
      "grad_norm": 0.4349486529827118,
      "learning_rate": 3.4990357351045866e-06,
      "loss": 0.5204,
      "step": 47248
    },
    {
      "epoch": 1.4514484072128528,
      "grad_norm": 0.4188559651374817,
      "learning_rate": 3.498668523581126e-06,
      "loss": 0.3997,
      "step": 47249
    },
    {
      "epoch": 1.451479126347802,
      "grad_norm": 0.414864718914032,
      "learning_rate": 3.498301327241983e-06,
      "loss": 0.4001,
      "step": 47250
    },
    {
      "epoch": 1.451509845482751,
      "grad_norm": 0.4134606420993805,
      "learning_rate": 3.4979341460880033e-06,
      "loss": 0.4766,
      "step": 47251
    },
    {
      "epoch": 1.4515405646177004,
      "grad_norm": 0.42432957887649536,
      "learning_rate": 3.497566980120061e-06,
      "loss": 0.5689,
      "step": 47252
    },
    {
      "epoch": 1.4515712837526495,
      "grad_norm": 0.49538707733154297,
      "learning_rate": 3.4971998293390007e-06,
      "loss": 0.502,
      "step": 47253
    },
    {
      "epoch": 1.4516020028875987,
      "grad_norm": 0.4381553828716278,
      "learning_rate": 3.4968326937456876e-06,
      "loss": 0.421,
      "step": 47254
    },
    {
      "epoch": 1.4516327220225478,
      "grad_norm": 0.42673459649086,
      "learning_rate": 3.4964655733409725e-06,
      "loss": 0.4861,
      "step": 47255
    },
    {
      "epoch": 1.4516634411574971,
      "grad_norm": 0.47102299332618713,
      "learning_rate": 3.496098468125717e-06,
      "loss": 0.4845,
      "step": 47256
    },
    {
      "epoch": 1.4516941602924462,
      "grad_norm": 0.49459901452064514,
      "learning_rate": 3.4957313781007774e-06,
      "loss": 0.4604,
      "step": 47257
    },
    {
      "epoch": 1.4517248794273954,
      "grad_norm": 0.39150986075401306,
      "learning_rate": 3.4953643032670147e-06,
      "loss": 0.4463,
      "step": 47258
    },
    {
      "epoch": 1.4517555985623445,
      "grad_norm": 0.42621296644210815,
      "learning_rate": 3.49499724362528e-06,
      "loss": 0.5234,
      "step": 47259
    },
    {
      "epoch": 1.4517863176972936,
      "grad_norm": 0.43572986125946045,
      "learning_rate": 3.494630199176433e-06,
      "loss": 0.4973,
      "step": 47260
    },
    {
      "epoch": 1.4518170368322427,
      "grad_norm": 0.41248390078544617,
      "learning_rate": 3.4942631699213316e-06,
      "loss": 0.4952,
      "step": 47261
    },
    {
      "epoch": 1.4518477559671918,
      "grad_norm": 0.5255135297775269,
      "learning_rate": 3.493896155860833e-06,
      "loss": 0.4464,
      "step": 47262
    },
    {
      "epoch": 1.4518784751021412,
      "grad_norm": 0.4431421756744385,
      "learning_rate": 3.4935291569957973e-06,
      "loss": 0.4098,
      "step": 47263
    },
    {
      "epoch": 1.4519091942370903,
      "grad_norm": 0.450269490480423,
      "learning_rate": 3.493162173327076e-06,
      "loss": 0.4702,
      "step": 47264
    },
    {
      "epoch": 1.4519399133720394,
      "grad_norm": 0.43175721168518066,
      "learning_rate": 3.492795204855528e-06,
      "loss": 0.5264,
      "step": 47265
    },
    {
      "epoch": 1.4519706325069885,
      "grad_norm": 0.42534103989601135,
      "learning_rate": 3.492428251582012e-06,
      "loss": 0.4587,
      "step": 47266
    },
    {
      "epoch": 1.4520013516419379,
      "grad_norm": 0.5565952658653259,
      "learning_rate": 3.4920613135073864e-06,
      "loss": 0.4394,
      "step": 47267
    },
    {
      "epoch": 1.452032070776887,
      "grad_norm": 0.4209725856781006,
      "learning_rate": 3.4916943906325042e-06,
      "loss": 0.4643,
      "step": 47268
    },
    {
      "epoch": 1.4520627899118361,
      "grad_norm": 0.4555867910385132,
      "learning_rate": 3.4913274829582245e-06,
      "loss": 0.4093,
      "step": 47269
    },
    {
      "epoch": 1.4520935090467852,
      "grad_norm": 0.405109167098999,
      "learning_rate": 3.4909605904854025e-06,
      "loss": 0.4869,
      "step": 47270
    },
    {
      "epoch": 1.4521242281817344,
      "grad_norm": 0.4760550856590271,
      "learning_rate": 3.4905937132149016e-06,
      "loss": 0.5348,
      "step": 47271
    },
    {
      "epoch": 1.4521549473166835,
      "grad_norm": 0.4074289798736572,
      "learning_rate": 3.490226851147569e-06,
      "loss": 0.4737,
      "step": 47272
    },
    {
      "epoch": 1.4521856664516326,
      "grad_norm": 0.4525488615036011,
      "learning_rate": 3.489860004284267e-06,
      "loss": 0.4458,
      "step": 47273
    },
    {
      "epoch": 1.452216385586582,
      "grad_norm": 0.4631056487560272,
      "learning_rate": 3.489493172625852e-06,
      "loss": 0.4488,
      "step": 47274
    },
    {
      "epoch": 1.452247104721531,
      "grad_norm": 0.4655628204345703,
      "learning_rate": 3.4891263561731823e-06,
      "loss": 0.5297,
      "step": 47275
    },
    {
      "epoch": 1.4522778238564802,
      "grad_norm": 0.3919529914855957,
      "learning_rate": 3.4887595549271114e-06,
      "loss": 0.4603,
      "step": 47276
    },
    {
      "epoch": 1.4523085429914293,
      "grad_norm": 0.48415708541870117,
      "learning_rate": 3.4883927688884956e-06,
      "loss": 0.5194,
      "step": 47277
    },
    {
      "epoch": 1.4523392621263786,
      "grad_norm": 0.4220148026943207,
      "learning_rate": 3.488025998058194e-06,
      "loss": 0.491,
      "step": 47278
    },
    {
      "epoch": 1.4523699812613278,
      "grad_norm": 0.4506731331348419,
      "learning_rate": 3.4876592424370625e-06,
      "loss": 0.4284,
      "step": 47279
    },
    {
      "epoch": 1.452400700396277,
      "grad_norm": 0.4421254098415375,
      "learning_rate": 3.487292502025961e-06,
      "loss": 0.508,
      "step": 47280
    },
    {
      "epoch": 1.452431419531226,
      "grad_norm": 0.39859864115715027,
      "learning_rate": 3.486925776825738e-06,
      "loss": 0.4235,
      "step": 47281
    },
    {
      "epoch": 1.4524621386661751,
      "grad_norm": 0.41735365986824036,
      "learning_rate": 3.4865590668372596e-06,
      "loss": 0.4239,
      "step": 47282
    },
    {
      "epoch": 1.4524928578011242,
      "grad_norm": 0.4572330713272095,
      "learning_rate": 3.48619237206137e-06,
      "loss": 0.4553,
      "step": 47283
    },
    {
      "epoch": 1.4525235769360734,
      "grad_norm": 0.4272643029689789,
      "learning_rate": 3.4858256924989407e-06,
      "loss": 0.4603,
      "step": 47284
    },
    {
      "epoch": 1.4525542960710227,
      "grad_norm": 0.41310063004493713,
      "learning_rate": 3.485459028150816e-06,
      "loss": 0.4805,
      "step": 47285
    },
    {
      "epoch": 1.4525850152059718,
      "grad_norm": 0.41031119227409363,
      "learning_rate": 3.4850923790178604e-06,
      "loss": 0.4935,
      "step": 47286
    },
    {
      "epoch": 1.452615734340921,
      "grad_norm": 0.42194342613220215,
      "learning_rate": 3.4847257451009197e-06,
      "loss": 0.4777,
      "step": 47287
    },
    {
      "epoch": 1.45264645347587,
      "grad_norm": 0.41147318482398987,
      "learning_rate": 3.484359126400865e-06,
      "loss": 0.4176,
      "step": 47288
    },
    {
      "epoch": 1.4526771726108194,
      "grad_norm": 0.46672993898391724,
      "learning_rate": 3.48399252291854e-06,
      "loss": 0.47,
      "step": 47289
    },
    {
      "epoch": 1.4527078917457685,
      "grad_norm": 0.4663252830505371,
      "learning_rate": 3.4836259346548084e-06,
      "loss": 0.4665,
      "step": 47290
    },
    {
      "epoch": 1.4527386108807177,
      "grad_norm": 0.4219073951244354,
      "learning_rate": 3.4832593616105215e-06,
      "loss": 0.446,
      "step": 47291
    },
    {
      "epoch": 1.4527693300156668,
      "grad_norm": 0.4072422683238983,
      "learning_rate": 3.482892803786536e-06,
      "loss": 0.4952,
      "step": 47292
    },
    {
      "epoch": 1.452800049150616,
      "grad_norm": 0.4283059239387512,
      "learning_rate": 3.482526261183711e-06,
      "loss": 0.4284,
      "step": 47293
    },
    {
      "epoch": 1.452830768285565,
      "grad_norm": 0.4289498031139374,
      "learning_rate": 3.482159733802903e-06,
      "loss": 0.4746,
      "step": 47294
    },
    {
      "epoch": 1.4528614874205141,
      "grad_norm": 0.42866620421409607,
      "learning_rate": 3.4817932216449645e-06,
      "loss": 0.4937,
      "step": 47295
    },
    {
      "epoch": 1.4528922065554635,
      "grad_norm": 0.3811715543270111,
      "learning_rate": 3.4814267247107523e-06,
      "loss": 0.4976,
      "step": 47296
    },
    {
      "epoch": 1.4529229256904126,
      "grad_norm": 0.42310425639152527,
      "learning_rate": 3.481060243001123e-06,
      "loss": 0.5234,
      "step": 47297
    },
    {
      "epoch": 1.4529536448253617,
      "grad_norm": 0.3870277404785156,
      "learning_rate": 3.4806937765169326e-06,
      "loss": 0.4736,
      "step": 47298
    },
    {
      "epoch": 1.4529843639603108,
      "grad_norm": 0.41300666332244873,
      "learning_rate": 3.4803273252590407e-06,
      "loss": 0.4385,
      "step": 47299
    },
    {
      "epoch": 1.4530150830952602,
      "grad_norm": 0.387624591588974,
      "learning_rate": 3.4799608892282966e-06,
      "loss": 0.402,
      "step": 47300
    },
    {
      "epoch": 1.4530458022302093,
      "grad_norm": 0.46696075797080994,
      "learning_rate": 3.47959446842556e-06,
      "loss": 0.4102,
      "step": 47301
    },
    {
      "epoch": 1.4530765213651584,
      "grad_norm": 0.4228304922580719,
      "learning_rate": 3.479228062851685e-06,
      "loss": 0.4336,
      "step": 47302
    },
    {
      "epoch": 1.4531072405001075,
      "grad_norm": 0.4931896924972534,
      "learning_rate": 3.478861672507531e-06,
      "loss": 0.4418,
      "step": 47303
    },
    {
      "epoch": 1.4531379596350567,
      "grad_norm": 0.4089992046356201,
      "learning_rate": 3.478495297393949e-06,
      "loss": 0.4489,
      "step": 47304
    },
    {
      "epoch": 1.4531686787700058,
      "grad_norm": 0.431962788105011,
      "learning_rate": 3.4781289375117956e-06,
      "loss": 0.5185,
      "step": 47305
    },
    {
      "epoch": 1.453199397904955,
      "grad_norm": 0.42434951663017273,
      "learning_rate": 3.4777625928619274e-06,
      "loss": 0.5491,
      "step": 47306
    },
    {
      "epoch": 1.4532301170399042,
      "grad_norm": 0.4168678820133209,
      "learning_rate": 3.477396263445204e-06,
      "loss": 0.4403,
      "step": 47307
    },
    {
      "epoch": 1.4532608361748534,
      "grad_norm": 0.46910548210144043,
      "learning_rate": 3.4770299492624748e-06,
      "loss": 0.5051,
      "step": 47308
    },
    {
      "epoch": 1.4532915553098025,
      "grad_norm": 0.4103281795978546,
      "learning_rate": 3.4766636503145967e-06,
      "loss": 0.4673,
      "step": 47309
    },
    {
      "epoch": 1.4533222744447516,
      "grad_norm": 0.41914185881614685,
      "learning_rate": 3.476297366602426e-06,
      "loss": 0.4266,
      "step": 47310
    },
    {
      "epoch": 1.4533529935797007,
      "grad_norm": 0.46564266085624695,
      "learning_rate": 3.4759310981268224e-06,
      "loss": 0.4772,
      "step": 47311
    },
    {
      "epoch": 1.45338371271465,
      "grad_norm": 0.43266239762306213,
      "learning_rate": 3.4755648448886335e-06,
      "loss": 0.4544,
      "step": 47312
    },
    {
      "epoch": 1.4534144318495992,
      "grad_norm": 0.45382994413375854,
      "learning_rate": 3.4751986068887222e-06,
      "loss": 0.4685,
      "step": 47313
    },
    {
      "epoch": 1.4534451509845483,
      "grad_norm": 0.429372638463974,
      "learning_rate": 3.474832384127933e-06,
      "loss": 0.4939,
      "step": 47314
    },
    {
      "epoch": 1.4534758701194974,
      "grad_norm": 0.3861699402332306,
      "learning_rate": 3.474466176607132e-06,
      "loss": 0.4568,
      "step": 47315
    },
    {
      "epoch": 1.4535065892544465,
      "grad_norm": 0.4258342981338501,
      "learning_rate": 3.474099984327175e-06,
      "loss": 0.4299,
      "step": 47316
    },
    {
      "epoch": 1.4535373083893957,
      "grad_norm": 0.40563133358955383,
      "learning_rate": 3.473733807288909e-06,
      "loss": 0.4428,
      "step": 47317
    },
    {
      "epoch": 1.453568027524345,
      "grad_norm": 0.39918431639671326,
      "learning_rate": 3.4733676454931975e-06,
      "loss": 0.4998,
      "step": 47318
    },
    {
      "epoch": 1.4535987466592941,
      "grad_norm": 0.3826710879802704,
      "learning_rate": 3.4730014989408856e-06,
      "loss": 0.4832,
      "step": 47319
    },
    {
      "epoch": 1.4536294657942432,
      "grad_norm": 0.40036478638648987,
      "learning_rate": 3.4726353676328396e-06,
      "loss": 0.4901,
      "step": 47320
    },
    {
      "epoch": 1.4536601849291924,
      "grad_norm": 0.4442664682865143,
      "learning_rate": 3.4722692515699076e-06,
      "loss": 0.4675,
      "step": 47321
    },
    {
      "epoch": 1.4536909040641415,
      "grad_norm": 0.4226694107055664,
      "learning_rate": 3.4719031507529487e-06,
      "loss": 0.5412,
      "step": 47322
    },
    {
      "epoch": 1.4537216231990908,
      "grad_norm": 0.41098180413246155,
      "learning_rate": 3.471537065182814e-06,
      "loss": 0.5092,
      "step": 47323
    },
    {
      "epoch": 1.45375234233404,
      "grad_norm": 0.4301379919052124,
      "learning_rate": 3.47117099486036e-06,
      "loss": 0.5162,
      "step": 47324
    },
    {
      "epoch": 1.453783061468989,
      "grad_norm": 0.37770408391952515,
      "learning_rate": 3.470804939786442e-06,
      "loss": 0.4797,
      "step": 47325
    },
    {
      "epoch": 1.4538137806039382,
      "grad_norm": 0.3831612765789032,
      "learning_rate": 3.4704388999619177e-06,
      "loss": 0.4085,
      "step": 47326
    },
    {
      "epoch": 1.4538444997388873,
      "grad_norm": 0.4199313819408417,
      "learning_rate": 3.4700728753876366e-06,
      "loss": 0.4557,
      "step": 47327
    },
    {
      "epoch": 1.4538752188738364,
      "grad_norm": 0.4393533766269684,
      "learning_rate": 3.4697068660644564e-06,
      "loss": 0.4703,
      "step": 47328
    },
    {
      "epoch": 1.4539059380087855,
      "grad_norm": 0.43065181374549866,
      "learning_rate": 3.4693408719932318e-06,
      "loss": 0.3786,
      "step": 47329
    },
    {
      "epoch": 1.4539366571437349,
      "grad_norm": 0.41653674840927124,
      "learning_rate": 3.4689748931748213e-06,
      "loss": 0.4843,
      "step": 47330
    },
    {
      "epoch": 1.453967376278684,
      "grad_norm": 0.4203091263771057,
      "learning_rate": 3.4686089296100723e-06,
      "loss": 0.392,
      "step": 47331
    },
    {
      "epoch": 1.4539980954136331,
      "grad_norm": 0.42155125737190247,
      "learning_rate": 3.468242981299843e-06,
      "loss": 0.4675,
      "step": 47332
    },
    {
      "epoch": 1.4540288145485822,
      "grad_norm": 0.4294195771217346,
      "learning_rate": 3.4678770482449886e-06,
      "loss": 0.5458,
      "step": 47333
    },
    {
      "epoch": 1.4540595336835316,
      "grad_norm": 0.4639296233654022,
      "learning_rate": 3.4675111304463637e-06,
      "loss": 0.4442,
      "step": 47334
    },
    {
      "epoch": 1.4540902528184807,
      "grad_norm": 0.4372624456882477,
      "learning_rate": 3.467145227904827e-06,
      "loss": 0.3458,
      "step": 47335
    },
    {
      "epoch": 1.4541209719534298,
      "grad_norm": 0.4541624188423157,
      "learning_rate": 3.4667793406212246e-06,
      "loss": 0.5211,
      "step": 47336
    },
    {
      "epoch": 1.454151691088379,
      "grad_norm": 0.42405498027801514,
      "learning_rate": 3.4664134685964155e-06,
      "loss": 0.5319,
      "step": 47337
    },
    {
      "epoch": 1.454182410223328,
      "grad_norm": 0.39792007207870483,
      "learning_rate": 3.4660476118312535e-06,
      "loss": 0.5171,
      "step": 47338
    },
    {
      "epoch": 1.4542131293582772,
      "grad_norm": 0.4390380382537842,
      "learning_rate": 3.4656817703265975e-06,
      "loss": 0.4818,
      "step": 47339
    },
    {
      "epoch": 1.4542438484932263,
      "grad_norm": 0.43729522824287415,
      "learning_rate": 3.465315944083295e-06,
      "loss": 0.5259,
      "step": 47340
    },
    {
      "epoch": 1.4542745676281756,
      "grad_norm": 0.40335139632225037,
      "learning_rate": 3.4649501331022027e-06,
      "loss": 0.4495,
      "step": 47341
    },
    {
      "epoch": 1.4543052867631248,
      "grad_norm": 0.395440936088562,
      "learning_rate": 3.464584337384177e-06,
      "loss": 0.5078,
      "step": 47342
    },
    {
      "epoch": 1.4543360058980739,
      "grad_norm": 0.4737730622291565,
      "learning_rate": 3.4642185569300733e-06,
      "loss": 0.4369,
      "step": 47343
    },
    {
      "epoch": 1.454366725033023,
      "grad_norm": 0.3832383155822754,
      "learning_rate": 3.4638527917407404e-06,
      "loss": 0.4288,
      "step": 47344
    },
    {
      "epoch": 1.4543974441679723,
      "grad_norm": 0.4003676176071167,
      "learning_rate": 3.4634870418170398e-06,
      "loss": 0.4905,
      "step": 47345
    },
    {
      "epoch": 1.4544281633029215,
      "grad_norm": 0.41827675700187683,
      "learning_rate": 3.4631213071598146e-06,
      "loss": 0.441,
      "step": 47346
    },
    {
      "epoch": 1.4544588824378706,
      "grad_norm": 0.4253608286380768,
      "learning_rate": 3.4627555877699327e-06,
      "loss": 0.4702,
      "step": 47347
    },
    {
      "epoch": 1.4544896015728197,
      "grad_norm": 0.4598022401332855,
      "learning_rate": 3.4623898836482385e-06,
      "loss": 0.4227,
      "step": 47348
    },
    {
      "epoch": 1.4545203207077688,
      "grad_norm": 0.48821786046028137,
      "learning_rate": 3.4620241947955926e-06,
      "loss": 0.5102,
      "step": 47349
    },
    {
      "epoch": 1.454551039842718,
      "grad_norm": 0.4186065196990967,
      "learning_rate": 3.4616585212128382e-06,
      "loss": 0.5402,
      "step": 47350
    },
    {
      "epoch": 1.454581758977667,
      "grad_norm": 0.406676709651947,
      "learning_rate": 3.4612928629008415e-06,
      "loss": 0.5154,
      "step": 47351
    },
    {
      "epoch": 1.4546124781126164,
      "grad_norm": 0.4288724958896637,
      "learning_rate": 3.460927219860455e-06,
      "loss": 0.4664,
      "step": 47352
    },
    {
      "epoch": 1.4546431972475655,
      "grad_norm": 0.41932669281959534,
      "learning_rate": 3.460561592092526e-06,
      "loss": 0.4754,
      "step": 47353
    },
    {
      "epoch": 1.4546739163825146,
      "grad_norm": 0.46119779348373413,
      "learning_rate": 3.4601959795979157e-06,
      "loss": 0.4946,
      "step": 47354
    },
    {
      "epoch": 1.4547046355174638,
      "grad_norm": 0.41381630301475525,
      "learning_rate": 3.459830382377468e-06,
      "loss": 0.4692,
      "step": 47355
    },
    {
      "epoch": 1.454735354652413,
      "grad_norm": 0.452555775642395,
      "learning_rate": 3.4594648004320498e-06,
      "loss": 0.4705,
      "step": 47356
    },
    {
      "epoch": 1.4547660737873622,
      "grad_norm": 0.41633638739585876,
      "learning_rate": 3.459099233762505e-06,
      "loss": 0.4586,
      "step": 47357
    },
    {
      "epoch": 1.4547967929223113,
      "grad_norm": 0.5298863053321838,
      "learning_rate": 3.458733682369694e-06,
      "loss": 0.3151,
      "step": 47358
    },
    {
      "epoch": 1.4548275120572605,
      "grad_norm": 0.4200206995010376,
      "learning_rate": 3.458368146254464e-06,
      "loss": 0.446,
      "step": 47359
    },
    {
      "epoch": 1.4548582311922096,
      "grad_norm": 0.4022688865661621,
      "learning_rate": 3.4580026254176722e-06,
      "loss": 0.4251,
      "step": 47360
    },
    {
      "epoch": 1.4548889503271587,
      "grad_norm": 0.41957125067710876,
      "learning_rate": 3.4576371198601723e-06,
      "loss": 0.525,
      "step": 47361
    },
    {
      "epoch": 1.4549196694621078,
      "grad_norm": 0.4673331677913666,
      "learning_rate": 3.4572716295828203e-06,
      "loss": 0.522,
      "step": 47362
    },
    {
      "epoch": 1.4549503885970572,
      "grad_norm": 0.4561188220977783,
      "learning_rate": 3.4569061545864644e-06,
      "loss": 0.5065,
      "step": 47363
    },
    {
      "epoch": 1.4549811077320063,
      "grad_norm": 0.39774176478385925,
      "learning_rate": 3.4565406948719614e-06,
      "loss": 0.3726,
      "step": 47364
    },
    {
      "epoch": 1.4550118268669554,
      "grad_norm": 0.43769049644470215,
      "learning_rate": 3.4561752504401647e-06,
      "loss": 0.4425,
      "step": 47365
    },
    {
      "epoch": 1.4550425460019045,
      "grad_norm": 0.41572317481040955,
      "learning_rate": 3.45580982129193e-06,
      "loss": 0.448,
      "step": 47366
    },
    {
      "epoch": 1.4550732651368539,
      "grad_norm": 0.5303406119346619,
      "learning_rate": 3.4554444074281068e-06,
      "loss": 0.4984,
      "step": 47367
    },
    {
      "epoch": 1.455103984271803,
      "grad_norm": 0.397187203168869,
      "learning_rate": 3.455079008849549e-06,
      "loss": 0.448,
      "step": 47368
    },
    {
      "epoch": 1.455134703406752,
      "grad_norm": 0.4462204575538635,
      "learning_rate": 3.4547136255571113e-06,
      "loss": 0.4689,
      "step": 47369
    },
    {
      "epoch": 1.4551654225417012,
      "grad_norm": 0.4545738101005554,
      "learning_rate": 3.4543482575516473e-06,
      "loss": 0.4654,
      "step": 47370
    },
    {
      "epoch": 1.4551961416766503,
      "grad_norm": 0.41343358159065247,
      "learning_rate": 3.4539829048340146e-06,
      "loss": 0.4472,
      "step": 47371
    },
    {
      "epoch": 1.4552268608115995,
      "grad_norm": 0.40737655758857727,
      "learning_rate": 3.4536175674050577e-06,
      "loss": 0.474,
      "step": 47372
    },
    {
      "epoch": 1.4552575799465486,
      "grad_norm": 0.395476758480072,
      "learning_rate": 3.4532522452656337e-06,
      "loss": 0.4727,
      "step": 47373
    },
    {
      "epoch": 1.455288299081498,
      "grad_norm": 0.434263676404953,
      "learning_rate": 3.4528869384165965e-06,
      "loss": 0.5044,
      "step": 47374
    },
    {
      "epoch": 1.455319018216447,
      "grad_norm": 0.41885286569595337,
      "learning_rate": 3.452521646858803e-06,
      "loss": 0.46,
      "step": 47375
    },
    {
      "epoch": 1.4553497373513962,
      "grad_norm": 0.44264841079711914,
      "learning_rate": 3.4521563705930985e-06,
      "loss": 0.4183,
      "step": 47376
    },
    {
      "epoch": 1.4553804564863453,
      "grad_norm": 0.4132607877254486,
      "learning_rate": 3.4517911096203406e-06,
      "loss": 0.4891,
      "step": 47377
    },
    {
      "epoch": 1.4554111756212946,
      "grad_norm": 0.40864697098731995,
      "learning_rate": 3.451425863941381e-06,
      "loss": 0.4709,
      "step": 47378
    },
    {
      "epoch": 1.4554418947562437,
      "grad_norm": 0.38507845997810364,
      "learning_rate": 3.4510606335570784e-06,
      "loss": 0.4428,
      "step": 47379
    },
    {
      "epoch": 1.4554726138911929,
      "grad_norm": 0.45159703493118286,
      "learning_rate": 3.450695418468276e-06,
      "loss": 0.4474,
      "step": 47380
    },
    {
      "epoch": 1.455503333026142,
      "grad_norm": 0.43240705132484436,
      "learning_rate": 3.450330218675837e-06,
      "loss": 0.4563,
      "step": 47381
    },
    {
      "epoch": 1.455534052161091,
      "grad_norm": 0.4038262963294983,
      "learning_rate": 3.4499650341806014e-06,
      "loss": 0.4668,
      "step": 47382
    },
    {
      "epoch": 1.4555647712960402,
      "grad_norm": 0.45138171315193176,
      "learning_rate": 3.4495998649834373e-06,
      "loss": 0.471,
      "step": 47383
    },
    {
      "epoch": 1.4555954904309893,
      "grad_norm": 0.40739718079566956,
      "learning_rate": 3.4492347110851863e-06,
      "loss": 0.4866,
      "step": 47384
    },
    {
      "epoch": 1.4556262095659387,
      "grad_norm": 0.41178929805755615,
      "learning_rate": 3.4488695724867084e-06,
      "loss": 0.4644,
      "step": 47385
    },
    {
      "epoch": 1.4556569287008878,
      "grad_norm": 0.4068693220615387,
      "learning_rate": 3.44850444918885e-06,
      "loss": 0.5072,
      "step": 47386
    },
    {
      "epoch": 1.455687647835837,
      "grad_norm": 0.4395977854728699,
      "learning_rate": 3.4481393411924636e-06,
      "loss": 0.5322,
      "step": 47387
    },
    {
      "epoch": 1.455718366970786,
      "grad_norm": 0.4285008907318115,
      "learning_rate": 3.4477742484984124e-06,
      "loss": 0.3926,
      "step": 47388
    },
    {
      "epoch": 1.4557490861057354,
      "grad_norm": 0.37286481261253357,
      "learning_rate": 3.4474091711075373e-06,
      "loss": 0.4175,
      "step": 47389
    },
    {
      "epoch": 1.4557798052406845,
      "grad_norm": 0.4038068354129791,
      "learning_rate": 3.4470441090207006e-06,
      "loss": 0.446,
      "step": 47390
    },
    {
      "epoch": 1.4558105243756336,
      "grad_norm": 0.40475958585739136,
      "learning_rate": 3.4466790622387426e-06,
      "loss": 0.474,
      "step": 47391
    },
    {
      "epoch": 1.4558412435105827,
      "grad_norm": 0.41017311811447144,
      "learning_rate": 3.446314030762531e-06,
      "loss": 0.4727,
      "step": 47392
    },
    {
      "epoch": 1.4558719626455319,
      "grad_norm": 0.41923996806144714,
      "learning_rate": 3.4459490145929066e-06,
      "loss": 0.4366,
      "step": 47393
    },
    {
      "epoch": 1.455902681780481,
      "grad_norm": 0.41120296716690063,
      "learning_rate": 3.4455840137307294e-06,
      "loss": 0.465,
      "step": 47394
    },
    {
      "epoch": 1.45593340091543,
      "grad_norm": 0.437529057264328,
      "learning_rate": 3.445219028176845e-06,
      "loss": 0.4475,
      "step": 47395
    },
    {
      "epoch": 1.4559641200503795,
      "grad_norm": 0.4668283462524414,
      "learning_rate": 3.444854057932109e-06,
      "loss": 0.5535,
      "step": 47396
    },
    {
      "epoch": 1.4559948391853286,
      "grad_norm": 0.4441712200641632,
      "learning_rate": 3.444489102997375e-06,
      "loss": 0.5309,
      "step": 47397
    },
    {
      "epoch": 1.4560255583202777,
      "grad_norm": 0.47330808639526367,
      "learning_rate": 3.4441241633734978e-06,
      "loss": 0.4615,
      "step": 47398
    },
    {
      "epoch": 1.4560562774552268,
      "grad_norm": 0.4356337785720825,
      "learning_rate": 3.4437592390613227e-06,
      "loss": 0.4938,
      "step": 47399
    },
    {
      "epoch": 1.4560869965901762,
      "grad_norm": 0.5448028445243835,
      "learning_rate": 3.443394330061706e-06,
      "loss": 0.4909,
      "step": 47400
    },
    {
      "epoch": 1.4561177157251253,
      "grad_norm": 0.4039336144924164,
      "learning_rate": 3.443029436375499e-06,
      "loss": 0.4633,
      "step": 47401
    },
    {
      "epoch": 1.4561484348600744,
      "grad_norm": 0.4313017725944519,
      "learning_rate": 3.442664558003559e-06,
      "loss": 0.5061,
      "step": 47402
    },
    {
      "epoch": 1.4561791539950235,
      "grad_norm": 0.4205058217048645,
      "learning_rate": 3.4422996949467304e-06,
      "loss": 0.4588,
      "step": 47403
    },
    {
      "epoch": 1.4562098731299726,
      "grad_norm": 0.4718199670314789,
      "learning_rate": 3.4419348472058687e-06,
      "loss": 0.4628,
      "step": 47404
    },
    {
      "epoch": 1.4562405922649218,
      "grad_norm": 0.4378136396408081,
      "learning_rate": 3.4415700147818255e-06,
      "loss": 0.4948,
      "step": 47405
    },
    {
      "epoch": 1.4562713113998709,
      "grad_norm": 0.38798460364341736,
      "learning_rate": 3.4412051976754544e-06,
      "loss": 0.4896,
      "step": 47406
    },
    {
      "epoch": 1.4563020305348202,
      "grad_norm": 0.4167967736721039,
      "learning_rate": 3.4408403958876103e-06,
      "loss": 0.454,
      "step": 47407
    },
    {
      "epoch": 1.4563327496697693,
      "grad_norm": 0.44146811962127686,
      "learning_rate": 3.440475609419137e-06,
      "loss": 0.4736,
      "step": 47408
    },
    {
      "epoch": 1.4563634688047185,
      "grad_norm": 0.40625089406967163,
      "learning_rate": 3.4401108382708913e-06,
      "loss": 0.4504,
      "step": 47409
    },
    {
      "epoch": 1.4563941879396676,
      "grad_norm": 0.4348819851875305,
      "learning_rate": 3.4397460824437258e-06,
      "loss": 0.5092,
      "step": 47410
    },
    {
      "epoch": 1.456424907074617,
      "grad_norm": 0.42282938957214355,
      "learning_rate": 3.4393813419384947e-06,
      "loss": 0.4953,
      "step": 47411
    },
    {
      "epoch": 1.456455626209566,
      "grad_norm": 0.39693430066108704,
      "learning_rate": 3.4390166167560423e-06,
      "loss": 0.4087,
      "step": 47412
    },
    {
      "epoch": 1.4564863453445152,
      "grad_norm": 0.4154311716556549,
      "learning_rate": 3.4386519068972256e-06,
      "loss": 0.4791,
      "step": 47413
    },
    {
      "epoch": 1.4565170644794643,
      "grad_norm": 0.4233117997646332,
      "learning_rate": 3.438287212362895e-06,
      "loss": 0.4181,
      "step": 47414
    },
    {
      "epoch": 1.4565477836144134,
      "grad_norm": 0.41458258032798767,
      "learning_rate": 3.4379225331539068e-06,
      "loss": 0.4576,
      "step": 47415
    },
    {
      "epoch": 1.4565785027493625,
      "grad_norm": 0.41624805331230164,
      "learning_rate": 3.4375578692711055e-06,
      "loss": 0.5204,
      "step": 47416
    },
    {
      "epoch": 1.4566092218843116,
      "grad_norm": 0.3999722898006439,
      "learning_rate": 3.4371932207153493e-06,
      "loss": 0.4253,
      "step": 47417
    },
    {
      "epoch": 1.456639941019261,
      "grad_norm": 0.4260391294956207,
      "learning_rate": 3.436828587487481e-06,
      "loss": 0.5047,
      "step": 47418
    },
    {
      "epoch": 1.45667066015421,
      "grad_norm": 0.3897337019443512,
      "learning_rate": 3.4364639695883627e-06,
      "loss": 0.4399,
      "step": 47419
    },
    {
      "epoch": 1.4567013792891592,
      "grad_norm": 0.5432617664337158,
      "learning_rate": 3.4360993670188392e-06,
      "loss": 0.4704,
      "step": 47420
    },
    {
      "epoch": 1.4567320984241083,
      "grad_norm": 0.38700780272483826,
      "learning_rate": 3.4357347797797667e-06,
      "loss": 0.4001,
      "step": 47421
    },
    {
      "epoch": 1.4567628175590575,
      "grad_norm": 0.5018980503082275,
      "learning_rate": 3.435370207871991e-06,
      "loss": 0.4237,
      "step": 47422
    },
    {
      "epoch": 1.4567935366940068,
      "grad_norm": 0.4468412697315216,
      "learning_rate": 3.4350056512963624e-06,
      "loss": 0.4015,
      "step": 47423
    },
    {
      "epoch": 1.456824255828956,
      "grad_norm": 0.43137091398239136,
      "learning_rate": 3.4346411100537446e-06,
      "loss": 0.4683,
      "step": 47424
    },
    {
      "epoch": 1.456854974963905,
      "grad_norm": 0.43281999230384827,
      "learning_rate": 3.434276584144978e-06,
      "loss": 0.4181,
      "step": 47425
    },
    {
      "epoch": 1.4568856940988542,
      "grad_norm": 0.4411705732345581,
      "learning_rate": 3.4339120735709188e-06,
      "loss": 0.428,
      "step": 47426
    },
    {
      "epoch": 1.4569164132338033,
      "grad_norm": 0.4281708002090454,
      "learning_rate": 3.4335475783324137e-06,
      "loss": 0.441,
      "step": 47427
    },
    {
      "epoch": 1.4569471323687524,
      "grad_norm": 0.4326404929161072,
      "learning_rate": 3.433183098430317e-06,
      "loss": 0.5322,
      "step": 47428
    },
    {
      "epoch": 1.4569778515037017,
      "grad_norm": 0.43667837977409363,
      "learning_rate": 3.43281863386548e-06,
      "loss": 0.4223,
      "step": 47429
    },
    {
      "epoch": 1.4570085706386509,
      "grad_norm": 0.3885597288608551,
      "learning_rate": 3.4324541846387573e-06,
      "loss": 0.517,
      "step": 47430
    },
    {
      "epoch": 1.4570392897736,
      "grad_norm": 0.40887200832366943,
      "learning_rate": 3.432089750750992e-06,
      "loss": 0.438,
      "step": 47431
    },
    {
      "epoch": 1.457070008908549,
      "grad_norm": 0.4200114905834198,
      "learning_rate": 3.4317253322030407e-06,
      "loss": 0.517,
      "step": 47432
    },
    {
      "epoch": 1.4571007280434982,
      "grad_norm": 0.4217780530452728,
      "learning_rate": 3.4313609289957537e-06,
      "loss": 0.4454,
      "step": 47433
    },
    {
      "epoch": 1.4571314471784476,
      "grad_norm": 0.4277443289756775,
      "learning_rate": 3.430996541129985e-06,
      "loss": 0.6156,
      "step": 47434
    },
    {
      "epoch": 1.4571621663133967,
      "grad_norm": 0.4243089258670807,
      "learning_rate": 3.430632168606579e-06,
      "loss": 0.4643,
      "step": 47435
    },
    {
      "epoch": 1.4571928854483458,
      "grad_norm": 0.45353278517723083,
      "learning_rate": 3.430267811426391e-06,
      "loss": 0.5416,
      "step": 47436
    },
    {
      "epoch": 1.457223604583295,
      "grad_norm": 0.6076363921165466,
      "learning_rate": 3.429903469590271e-06,
      "loss": 0.4827,
      "step": 47437
    },
    {
      "epoch": 1.457254323718244,
      "grad_norm": 0.44792550802230835,
      "learning_rate": 3.4295391430990742e-06,
      "loss": 0.4475,
      "step": 47438
    },
    {
      "epoch": 1.4572850428531932,
      "grad_norm": 0.4480566084384918,
      "learning_rate": 3.4291748319536435e-06,
      "loss": 0.4979,
      "step": 47439
    },
    {
      "epoch": 1.4573157619881423,
      "grad_norm": 0.40898892283439636,
      "learning_rate": 3.428810536154834e-06,
      "loss": 0.4848,
      "step": 47440
    },
    {
      "epoch": 1.4573464811230916,
      "grad_norm": 0.4798213243484497,
      "learning_rate": 3.428446255703497e-06,
      "loss": 0.5014,
      "step": 47441
    },
    {
      "epoch": 1.4573772002580407,
      "grad_norm": 0.41562631726264954,
      "learning_rate": 3.4280819906004824e-06,
      "loss": 0.473,
      "step": 47442
    },
    {
      "epoch": 1.4574079193929899,
      "grad_norm": 0.46873438358306885,
      "learning_rate": 3.4277177408466444e-06,
      "loss": 0.4829,
      "step": 47443
    },
    {
      "epoch": 1.457438638527939,
      "grad_norm": 0.4542340934276581,
      "learning_rate": 3.4273535064428277e-06,
      "loss": 0.5012,
      "step": 47444
    },
    {
      "epoch": 1.4574693576628883,
      "grad_norm": 0.5175942182540894,
      "learning_rate": 3.4269892873898856e-06,
      "loss": 0.4248,
      "step": 47445
    },
    {
      "epoch": 1.4575000767978374,
      "grad_norm": 0.44888561964035034,
      "learning_rate": 3.4266250836886695e-06,
      "loss": 0.4623,
      "step": 47446
    },
    {
      "epoch": 1.4575307959327866,
      "grad_norm": 0.42067837715148926,
      "learning_rate": 3.4262608953400323e-06,
      "loss": 0.4549,
      "step": 47447
    },
    {
      "epoch": 1.4575615150677357,
      "grad_norm": 0.38979190587997437,
      "learning_rate": 3.4258967223448193e-06,
      "loss": 0.4616,
      "step": 47448
    },
    {
      "epoch": 1.4575922342026848,
      "grad_norm": 0.44489365816116333,
      "learning_rate": 3.425532564703886e-06,
      "loss": 0.512,
      "step": 47449
    },
    {
      "epoch": 1.457622953337634,
      "grad_norm": 0.4182990491390228,
      "learning_rate": 3.425168422418075e-06,
      "loss": 0.5337,
      "step": 47450
    },
    {
      "epoch": 1.457653672472583,
      "grad_norm": 0.4018918573856354,
      "learning_rate": 3.424804295488248e-06,
      "loss": 0.4695,
      "step": 47451
    },
    {
      "epoch": 1.4576843916075324,
      "grad_norm": 0.4754689335823059,
      "learning_rate": 3.424440183915246e-06,
      "loss": 0.4641,
      "step": 47452
    },
    {
      "epoch": 1.4577151107424815,
      "grad_norm": 0.4721526503562927,
      "learning_rate": 3.424076087699928e-06,
      "loss": 0.4493,
      "step": 47453
    },
    {
      "epoch": 1.4577458298774306,
      "grad_norm": 0.389234721660614,
      "learning_rate": 3.4237120068431316e-06,
      "loss": 0.436,
      "step": 47454
    },
    {
      "epoch": 1.4577765490123797,
      "grad_norm": 0.3827895224094391,
      "learning_rate": 3.4233479413457225e-06,
      "loss": 0.4333,
      "step": 47455
    },
    {
      "epoch": 1.457807268147329,
      "grad_norm": 0.4602396786212921,
      "learning_rate": 3.42298389120854e-06,
      "loss": 0.4952,
      "step": 47456
    },
    {
      "epoch": 1.4578379872822782,
      "grad_norm": 0.44865474104881287,
      "learning_rate": 3.422619856432442e-06,
      "loss": 0.4753,
      "step": 47457
    },
    {
      "epoch": 1.4578687064172273,
      "grad_norm": 0.3974396884441376,
      "learning_rate": 3.42225583701827e-06,
      "loss": 0.4736,
      "step": 47458
    },
    {
      "epoch": 1.4578994255521764,
      "grad_norm": 0.4033460021018982,
      "learning_rate": 3.4218918329668803e-06,
      "loss": 0.461,
      "step": 47459
    },
    {
      "epoch": 1.4579301446871256,
      "grad_norm": 0.3770512342453003,
      "learning_rate": 3.421527844279121e-06,
      "loss": 0.4534,
      "step": 47460
    },
    {
      "epoch": 1.4579608638220747,
      "grad_norm": 0.4771274924278259,
      "learning_rate": 3.4211638709558428e-06,
      "loss": 0.5193,
      "step": 47461
    },
    {
      "epoch": 1.4579915829570238,
      "grad_norm": 0.40519195795059204,
      "learning_rate": 3.4207999129978984e-06,
      "loss": 0.4307,
      "step": 47462
    },
    {
      "epoch": 1.4580223020919731,
      "grad_norm": 0.43229565024375916,
      "learning_rate": 3.420435970406133e-06,
      "loss": 0.4199,
      "step": 47463
    },
    {
      "epoch": 1.4580530212269223,
      "grad_norm": 0.41154909133911133,
      "learning_rate": 3.4200720431813993e-06,
      "loss": 0.4805,
      "step": 47464
    },
    {
      "epoch": 1.4580837403618714,
      "grad_norm": 0.460005521774292,
      "learning_rate": 3.419708131324546e-06,
      "loss": 0.4745,
      "step": 47465
    },
    {
      "epoch": 1.4581144594968205,
      "grad_norm": 0.45723289251327515,
      "learning_rate": 3.4193442348364283e-06,
      "loss": 0.5319,
      "step": 47466
    },
    {
      "epoch": 1.4581451786317698,
      "grad_norm": 0.46429580450057983,
      "learning_rate": 3.4189803537178867e-06,
      "loss": 0.4254,
      "step": 47467
    },
    {
      "epoch": 1.458175897766719,
      "grad_norm": 0.4364244341850281,
      "learning_rate": 3.418616487969777e-06,
      "loss": 0.4705,
      "step": 47468
    },
    {
      "epoch": 1.458206616901668,
      "grad_norm": 0.3762490749359131,
      "learning_rate": 3.418252637592948e-06,
      "loss": 0.4948,
      "step": 47469
    },
    {
      "epoch": 1.4582373360366172,
      "grad_norm": 0.4086187481880188,
      "learning_rate": 3.417888802588254e-06,
      "loss": 0.4901,
      "step": 47470
    },
    {
      "epoch": 1.4582680551715663,
      "grad_norm": 0.425106942653656,
      "learning_rate": 3.417524982956536e-06,
      "loss": 0.4713,
      "step": 47471
    },
    {
      "epoch": 1.4582987743065154,
      "grad_norm": 0.38884156942367554,
      "learning_rate": 3.417161178698648e-06,
      "loss": 0.4496,
      "step": 47472
    },
    {
      "epoch": 1.4583294934414646,
      "grad_norm": 0.5061874389648438,
      "learning_rate": 3.4167973898154393e-06,
      "loss": 0.4967,
      "step": 47473
    },
    {
      "epoch": 1.458360212576414,
      "grad_norm": 0.42422354221343994,
      "learning_rate": 3.4164336163077648e-06,
      "loss": 0.5559,
      "step": 47474
    },
    {
      "epoch": 1.458390931711363,
      "grad_norm": 0.4924875795841217,
      "learning_rate": 3.4160698581764653e-06,
      "loss": 0.4781,
      "step": 47475
    },
    {
      "epoch": 1.4584216508463121,
      "grad_norm": 0.416985422372818,
      "learning_rate": 3.4157061154223946e-06,
      "loss": 0.3906,
      "step": 47476
    },
    {
      "epoch": 1.4584523699812613,
      "grad_norm": 0.4698875844478607,
      "learning_rate": 3.415342388046402e-06,
      "loss": 0.4993,
      "step": 47477
    },
    {
      "epoch": 1.4584830891162106,
      "grad_norm": 0.4440533518791199,
      "learning_rate": 3.4149786760493376e-06,
      "loss": 0.5329,
      "step": 47478
    },
    {
      "epoch": 1.4585138082511597,
      "grad_norm": 0.5050364136695862,
      "learning_rate": 3.4146149794320526e-06,
      "loss": 0.4639,
      "step": 47479
    },
    {
      "epoch": 1.4585445273861088,
      "grad_norm": 0.4166823625564575,
      "learning_rate": 3.4142512981953925e-06,
      "loss": 0.4919,
      "step": 47480
    },
    {
      "epoch": 1.458575246521058,
      "grad_norm": 0.4102698564529419,
      "learning_rate": 3.413887632340207e-06,
      "loss": 0.5241,
      "step": 47481
    },
    {
      "epoch": 1.458605965656007,
      "grad_norm": 0.4297763407230377,
      "learning_rate": 3.413523981867347e-06,
      "loss": 0.4489,
      "step": 47482
    },
    {
      "epoch": 1.4586366847909562,
      "grad_norm": 0.4134822487831116,
      "learning_rate": 3.4131603467776666e-06,
      "loss": 0.4782,
      "step": 47483
    },
    {
      "epoch": 1.4586674039259053,
      "grad_norm": 0.39426687359809875,
      "learning_rate": 3.4127967270720053e-06,
      "loss": 0.4629,
      "step": 47484
    },
    {
      "epoch": 1.4586981230608547,
      "grad_norm": 0.4613257348537445,
      "learning_rate": 3.412433122751221e-06,
      "loss": 0.431,
      "step": 47485
    },
    {
      "epoch": 1.4587288421958038,
      "grad_norm": 0.420723557472229,
      "learning_rate": 3.4120695338161525e-06,
      "loss": 0.4615,
      "step": 47486
    },
    {
      "epoch": 1.458759561330753,
      "grad_norm": 0.3934377431869507,
      "learning_rate": 3.4117059602676627e-06,
      "loss": 0.4807,
      "step": 47487
    },
    {
      "epoch": 1.458790280465702,
      "grad_norm": 0.4331195652484894,
      "learning_rate": 3.411342402106591e-06,
      "loss": 0.4488,
      "step": 47488
    },
    {
      "epoch": 1.4588209996006514,
      "grad_norm": 0.4584593176841736,
      "learning_rate": 3.4109788593337912e-06,
      "loss": 0.5298,
      "step": 47489
    },
    {
      "epoch": 1.4588517187356005,
      "grad_norm": 0.4174668490886688,
      "learning_rate": 3.4106153319501078e-06,
      "loss": 0.3755,
      "step": 47490
    },
    {
      "epoch": 1.4588824378705496,
      "grad_norm": 0.4246630370616913,
      "learning_rate": 3.410251819956393e-06,
      "loss": 0.4683,
      "step": 47491
    },
    {
      "epoch": 1.4589131570054987,
      "grad_norm": 0.3931812644004822,
      "learning_rate": 3.4098883233534942e-06,
      "loss": 0.4452,
      "step": 47492
    },
    {
      "epoch": 1.4589438761404478,
      "grad_norm": 0.3875441253185272,
      "learning_rate": 3.4095248421422654e-06,
      "loss": 0.415,
      "step": 47493
    },
    {
      "epoch": 1.458974595275397,
      "grad_norm": 0.39724597334861755,
      "learning_rate": 3.4091613763235488e-06,
      "loss": 0.4624,
      "step": 47494
    },
    {
      "epoch": 1.459005314410346,
      "grad_norm": 0.46041375398635864,
      "learning_rate": 3.4087979258981953e-06,
      "loss": 0.4625,
      "step": 47495
    },
    {
      "epoch": 1.4590360335452954,
      "grad_norm": 0.452284038066864,
      "learning_rate": 3.4084344908670553e-06,
      "loss": 0.5231,
      "step": 47496
    },
    {
      "epoch": 1.4590667526802445,
      "grad_norm": 0.4114307463169098,
      "learning_rate": 3.408071071230976e-06,
      "loss": 0.4632,
      "step": 47497
    },
    {
      "epoch": 1.4590974718151937,
      "grad_norm": 0.4391321837902069,
      "learning_rate": 3.4077076669908105e-06,
      "loss": 0.544,
      "step": 47498
    },
    {
      "epoch": 1.4591281909501428,
      "grad_norm": 0.411356121301651,
      "learning_rate": 3.407344278147402e-06,
      "loss": 0.5919,
      "step": 47499
    },
    {
      "epoch": 1.4591589100850921,
      "grad_norm": 0.39743900299072266,
      "learning_rate": 3.4069809047016e-06,
      "loss": 0.5449,
      "step": 47500
    },
    {
      "epoch": 1.4591896292200413,
      "grad_norm": 0.41307374835014343,
      "learning_rate": 3.406617546654255e-06,
      "loss": 0.4885,
      "step": 47501
    },
    {
      "epoch": 1.4592203483549904,
      "grad_norm": 0.46652156114578247,
      "learning_rate": 3.4062542040062187e-06,
      "loss": 0.4838,
      "step": 47502
    },
    {
      "epoch": 1.4592510674899395,
      "grad_norm": 0.4138329029083252,
      "learning_rate": 3.405890876758333e-06,
      "loss": 0.494,
      "step": 47503
    },
    {
      "epoch": 1.4592817866248886,
      "grad_norm": 0.42603600025177,
      "learning_rate": 3.4055275649114493e-06,
      "loss": 0.4184,
      "step": 47504
    },
    {
      "epoch": 1.4593125057598377,
      "grad_norm": 0.4373551309108734,
      "learning_rate": 3.4051642684664166e-06,
      "loss": 0.4879,
      "step": 47505
    },
    {
      "epoch": 1.4593432248947869,
      "grad_norm": 0.4111386835575104,
      "learning_rate": 3.4048009874240872e-06,
      "loss": 0.4829,
      "step": 47506
    },
    {
      "epoch": 1.4593739440297362,
      "grad_norm": 0.38827475905418396,
      "learning_rate": 3.404437721785302e-06,
      "loss": 0.4353,
      "step": 47507
    },
    {
      "epoch": 1.4594046631646853,
      "grad_norm": 0.4130265712738037,
      "learning_rate": 3.4040744715509123e-06,
      "loss": 0.4589,
      "step": 47508
    },
    {
      "epoch": 1.4594353822996344,
      "grad_norm": 0.42052552103996277,
      "learning_rate": 3.4037112367217684e-06,
      "loss": 0.483,
      "step": 47509
    },
    {
      "epoch": 1.4594661014345836,
      "grad_norm": 0.39760181307792664,
      "learning_rate": 3.403348017298721e-06,
      "loss": 0.4805,
      "step": 47510
    },
    {
      "epoch": 1.459496820569533,
      "grad_norm": 0.4527657926082611,
      "learning_rate": 3.4029848132826106e-06,
      "loss": 0.4852,
      "step": 47511
    },
    {
      "epoch": 1.459527539704482,
      "grad_norm": 0.3920341730117798,
      "learning_rate": 3.4026216246742936e-06,
      "loss": 0.5073,
      "step": 47512
    },
    {
      "epoch": 1.4595582588394311,
      "grad_norm": 0.4665105938911438,
      "learning_rate": 3.4022584514746084e-06,
      "loss": 0.4566,
      "step": 47513
    },
    {
      "epoch": 1.4595889779743803,
      "grad_norm": 0.41717463731765747,
      "learning_rate": 3.4018952936844163e-06,
      "loss": 0.4037,
      "step": 47514
    },
    {
      "epoch": 1.4596196971093294,
      "grad_norm": 0.4556490182876587,
      "learning_rate": 3.401532151304554e-06,
      "loss": 0.4793,
      "step": 47515
    },
    {
      "epoch": 1.4596504162442785,
      "grad_norm": 0.45566725730895996,
      "learning_rate": 3.4011690243358753e-06,
      "loss": 0.4683,
      "step": 47516
    },
    {
      "epoch": 1.4596811353792276,
      "grad_norm": 0.41283348202705383,
      "learning_rate": 3.400805912779227e-06,
      "loss": 0.5149,
      "step": 47517
    },
    {
      "epoch": 1.459711854514177,
      "grad_norm": 0.47231048345565796,
      "learning_rate": 3.4004428166354576e-06,
      "loss": 0.5012,
      "step": 47518
    },
    {
      "epoch": 1.459742573649126,
      "grad_norm": 0.4683358073234558,
      "learning_rate": 3.4000797359054174e-06,
      "loss": 0.4399,
      "step": 47519
    },
    {
      "epoch": 1.4597732927840752,
      "grad_norm": 0.41297128796577454,
      "learning_rate": 3.3997166705899486e-06,
      "loss": 0.4379,
      "step": 47520
    },
    {
      "epoch": 1.4598040119190243,
      "grad_norm": 0.4075508415699005,
      "learning_rate": 3.399353620689907e-06,
      "loss": 0.3952,
      "step": 47521
    },
    {
      "epoch": 1.4598347310539737,
      "grad_norm": 0.38778913021087646,
      "learning_rate": 3.398990586206128e-06,
      "loss": 0.4547,
      "step": 47522
    },
    {
      "epoch": 1.4598654501889228,
      "grad_norm": 0.4217461049556732,
      "learning_rate": 3.398627567139475e-06,
      "loss": 0.4975,
      "step": 47523
    },
    {
      "epoch": 1.459896169323872,
      "grad_norm": 0.43691903352737427,
      "learning_rate": 3.3982645634907853e-06,
      "loss": 0.4497,
      "step": 47524
    },
    {
      "epoch": 1.459926888458821,
      "grad_norm": 0.40811780095100403,
      "learning_rate": 3.3979015752609124e-06,
      "loss": 0.4539,
      "step": 47525
    },
    {
      "epoch": 1.4599576075937701,
      "grad_norm": 0.4861857295036316,
      "learning_rate": 3.3975386024506975e-06,
      "loss": 0.4843,
      "step": 47526
    },
    {
      "epoch": 1.4599883267287193,
      "grad_norm": 0.4262505769729614,
      "learning_rate": 3.397175645060994e-06,
      "loss": 0.5016,
      "step": 47527
    },
    {
      "epoch": 1.4600190458636684,
      "grad_norm": 0.4584801197052002,
      "learning_rate": 3.3968127030926466e-06,
      "loss": 0.4625,
      "step": 47528
    },
    {
      "epoch": 1.4600497649986177,
      "grad_norm": 0.4205322563648224,
      "learning_rate": 3.3964497765465077e-06,
      "loss": 0.4792,
      "step": 47529
    },
    {
      "epoch": 1.4600804841335668,
      "grad_norm": 0.3742133677005768,
      "learning_rate": 3.396086865423419e-06,
      "loss": 0.4368,
      "step": 47530
    },
    {
      "epoch": 1.460111203268516,
      "grad_norm": 0.4309687614440918,
      "learning_rate": 3.3957239697242297e-06,
      "loss": 0.4588,
      "step": 47531
    },
    {
      "epoch": 1.460141922403465,
      "grad_norm": 0.4284334182739258,
      "learning_rate": 3.3953610894497892e-06,
      "loss": 0.4688,
      "step": 47532
    },
    {
      "epoch": 1.4601726415384142,
      "grad_norm": 0.4078228771686554,
      "learning_rate": 3.394998224600944e-06,
      "loss": 0.5113,
      "step": 47533
    },
    {
      "epoch": 1.4602033606733635,
      "grad_norm": 0.488952100276947,
      "learning_rate": 3.3946353751785446e-06,
      "loss": 0.4193,
      "step": 47534
    },
    {
      "epoch": 1.4602340798083127,
      "grad_norm": 0.4445904791355133,
      "learning_rate": 3.3942725411834323e-06,
      "loss": 0.4722,
      "step": 47535
    },
    {
      "epoch": 1.4602647989432618,
      "grad_norm": 0.4838220775127411,
      "learning_rate": 3.3939097226164576e-06,
      "loss": 0.5446,
      "step": 47536
    },
    {
      "epoch": 1.460295518078211,
      "grad_norm": 0.45019206404685974,
      "learning_rate": 3.393546919478469e-06,
      "loss": 0.3243,
      "step": 47537
    },
    {
      "epoch": 1.46032623721316,
      "grad_norm": 0.4729405343532562,
      "learning_rate": 3.393184131770315e-06,
      "loss": 0.4557,
      "step": 47538
    },
    {
      "epoch": 1.4603569563481091,
      "grad_norm": 0.4101797640323639,
      "learning_rate": 3.392821359492838e-06,
      "loss": 0.4108,
      "step": 47539
    },
    {
      "epoch": 1.4603876754830585,
      "grad_norm": 0.39835071563720703,
      "learning_rate": 3.3924586026468885e-06,
      "loss": 0.4223,
      "step": 47540
    },
    {
      "epoch": 1.4604183946180076,
      "grad_norm": 0.4465189576148987,
      "learning_rate": 3.3920958612333133e-06,
      "loss": 0.4688,
      "step": 47541
    },
    {
      "epoch": 1.4604491137529567,
      "grad_norm": 0.4261229336261749,
      "learning_rate": 3.3917331352529635e-06,
      "loss": 0.4193,
      "step": 47542
    },
    {
      "epoch": 1.4604798328879058,
      "grad_norm": 0.3963412344455719,
      "learning_rate": 3.3913704247066793e-06,
      "loss": 0.4957,
      "step": 47543
    },
    {
      "epoch": 1.460510552022855,
      "grad_norm": 0.502663791179657,
      "learning_rate": 3.39100772959531e-06,
      "loss": 0.3825,
      "step": 47544
    },
    {
      "epoch": 1.4605412711578043,
      "grad_norm": 0.41227471828460693,
      "learning_rate": 3.390645049919704e-06,
      "loss": 0.4426,
      "step": 47545
    },
    {
      "epoch": 1.4605719902927534,
      "grad_norm": 0.4561145603656769,
      "learning_rate": 3.390282385680712e-06,
      "loss": 0.4182,
      "step": 47546
    },
    {
      "epoch": 1.4606027094277025,
      "grad_norm": 0.4127964675426483,
      "learning_rate": 3.3899197368791727e-06,
      "loss": 0.5472,
      "step": 47547
    },
    {
      "epoch": 1.4606334285626517,
      "grad_norm": 0.4056522250175476,
      "learning_rate": 3.3895571035159414e-06,
      "loss": 0.4246,
      "step": 47548
    },
    {
      "epoch": 1.4606641476976008,
      "grad_norm": 0.41760846972465515,
      "learning_rate": 3.3891944855918544e-06,
      "loss": 0.4068,
      "step": 47549
    },
    {
      "epoch": 1.46069486683255,
      "grad_norm": 0.4293901324272156,
      "learning_rate": 3.388831883107773e-06,
      "loss": 0.5373,
      "step": 47550
    },
    {
      "epoch": 1.460725585967499,
      "grad_norm": 0.421521931886673,
      "learning_rate": 3.3884692960645315e-06,
      "loss": 0.4571,
      "step": 47551
    },
    {
      "epoch": 1.4607563051024484,
      "grad_norm": 0.42103686928749084,
      "learning_rate": 3.3881067244629828e-06,
      "loss": 0.4203,
      "step": 47552
    },
    {
      "epoch": 1.4607870242373975,
      "grad_norm": 0.42190203070640564,
      "learning_rate": 3.387744168303976e-06,
      "loss": 0.4748,
      "step": 47553
    },
    {
      "epoch": 1.4608177433723466,
      "grad_norm": 0.44584518671035767,
      "learning_rate": 3.3873816275883477e-06,
      "loss": 0.4499,
      "step": 47554
    },
    {
      "epoch": 1.4608484625072957,
      "grad_norm": 0.39938509464263916,
      "learning_rate": 3.3870191023169576e-06,
      "loss": 0.3398,
      "step": 47555
    },
    {
      "epoch": 1.460879181642245,
      "grad_norm": 0.3963545858860016,
      "learning_rate": 3.3866565924906436e-06,
      "loss": 0.3773,
      "step": 47556
    },
    {
      "epoch": 1.4609099007771942,
      "grad_norm": 0.40497052669525146,
      "learning_rate": 3.3862940981102575e-06,
      "loss": 0.5087,
      "step": 47557
    },
    {
      "epoch": 1.4609406199121433,
      "grad_norm": 0.40972790122032166,
      "learning_rate": 3.3859316191766365e-06,
      "loss": 0.455,
      "step": 47558
    },
    {
      "epoch": 1.4609713390470924,
      "grad_norm": 0.4356485903263092,
      "learning_rate": 3.385569155690642e-06,
      "loss": 0.5132,
      "step": 47559
    },
    {
      "epoch": 1.4610020581820415,
      "grad_norm": 0.40497061610221863,
      "learning_rate": 3.385206707653109e-06,
      "loss": 0.5091,
      "step": 47560
    },
    {
      "epoch": 1.4610327773169907,
      "grad_norm": 0.42507269978523254,
      "learning_rate": 3.384844275064891e-06,
      "loss": 0.4802,
      "step": 47561
    },
    {
      "epoch": 1.4610634964519398,
      "grad_norm": 0.4735725224018097,
      "learning_rate": 3.3844818579268278e-06,
      "loss": 0.4806,
      "step": 47562
    },
    {
      "epoch": 1.4610942155868891,
      "grad_norm": 0.38501179218292236,
      "learning_rate": 3.3841194562397694e-06,
      "loss": 0.5216,
      "step": 47563
    },
    {
      "epoch": 1.4611249347218382,
      "grad_norm": 0.49707427620887756,
      "learning_rate": 3.3837570700045617e-06,
      "loss": 0.4167,
      "step": 47564
    },
    {
      "epoch": 1.4611556538567874,
      "grad_norm": 0.4290965497493744,
      "learning_rate": 3.3833946992220544e-06,
      "loss": 0.4428,
      "step": 47565
    },
    {
      "epoch": 1.4611863729917365,
      "grad_norm": 0.40595579147338867,
      "learning_rate": 3.383032343893088e-06,
      "loss": 0.4731,
      "step": 47566
    },
    {
      "epoch": 1.4612170921266858,
      "grad_norm": 0.3934948742389679,
      "learning_rate": 3.382670004018512e-06,
      "loss": 0.3978,
      "step": 47567
    },
    {
      "epoch": 1.461247811261635,
      "grad_norm": 0.4364834427833557,
      "learning_rate": 3.3823076795991714e-06,
      "loss": 0.4797,
      "step": 47568
    },
    {
      "epoch": 1.461278530396584,
      "grad_norm": 0.3912912905216217,
      "learning_rate": 3.3819453706359153e-06,
      "loss": 0.4659,
      "step": 47569
    },
    {
      "epoch": 1.4613092495315332,
      "grad_norm": 0.4337240755558014,
      "learning_rate": 3.38158307712959e-06,
      "loss": 0.4743,
      "step": 47570
    },
    {
      "epoch": 1.4613399686664823,
      "grad_norm": 0.41021957993507385,
      "learning_rate": 3.3812207990810353e-06,
      "loss": 0.4192,
      "step": 47571
    },
    {
      "epoch": 1.4613706878014314,
      "grad_norm": 0.4442835748195648,
      "learning_rate": 3.380858536491103e-06,
      "loss": 0.4409,
      "step": 47572
    },
    {
      "epoch": 1.4614014069363805,
      "grad_norm": 0.41762569546699524,
      "learning_rate": 3.3804962893606375e-06,
      "loss": 0.4658,
      "step": 47573
    },
    {
      "epoch": 1.4614321260713299,
      "grad_norm": 0.46696633100509644,
      "learning_rate": 3.3801340576904896e-06,
      "loss": 0.436,
      "step": 47574
    },
    {
      "epoch": 1.461462845206279,
      "grad_norm": 0.4129999279975891,
      "learning_rate": 3.3797718414814964e-06,
      "loss": 0.4884,
      "step": 47575
    },
    {
      "epoch": 1.4614935643412281,
      "grad_norm": 0.3999335467815399,
      "learning_rate": 3.379409640734509e-06,
      "loss": 0.4955,
      "step": 47576
    },
    {
      "epoch": 1.4615242834761772,
      "grad_norm": 0.4396577775478363,
      "learning_rate": 3.3790474554503717e-06,
      "loss": 0.4897,
      "step": 47577
    },
    {
      "epoch": 1.4615550026111266,
      "grad_norm": 0.39410847425460815,
      "learning_rate": 3.3786852856299357e-06,
      "loss": 0.5085,
      "step": 47578
    },
    {
      "epoch": 1.4615857217460757,
      "grad_norm": 0.39169806241989136,
      "learning_rate": 3.3783231312740394e-06,
      "loss": 0.422,
      "step": 47579
    },
    {
      "epoch": 1.4616164408810248,
      "grad_norm": 0.47604358196258545,
      "learning_rate": 3.3779609923835323e-06,
      "loss": 0.4998,
      "step": 47580
    },
    {
      "epoch": 1.461647160015974,
      "grad_norm": 0.8410199284553528,
      "learning_rate": 3.3775988689592587e-06,
      "loss": 0.5306,
      "step": 47581
    },
    {
      "epoch": 1.461677879150923,
      "grad_norm": 0.5113047361373901,
      "learning_rate": 3.3772367610020683e-06,
      "loss": 0.4527,
      "step": 47582
    },
    {
      "epoch": 1.4617085982858722,
      "grad_norm": 0.42754098773002625,
      "learning_rate": 3.3768746685128016e-06,
      "loss": 0.5069,
      "step": 47583
    },
    {
      "epoch": 1.4617393174208213,
      "grad_norm": 0.445516437292099,
      "learning_rate": 3.37651259149231e-06,
      "loss": 0.4733,
      "step": 47584
    },
    {
      "epoch": 1.4617700365557706,
      "grad_norm": 0.4343177080154419,
      "learning_rate": 3.37615052994143e-06,
      "loss": 0.4035,
      "step": 47585
    },
    {
      "epoch": 1.4618007556907198,
      "grad_norm": 0.4265826642513275,
      "learning_rate": 3.375788483861019e-06,
      "loss": 0.4533,
      "step": 47586
    },
    {
      "epoch": 1.4618314748256689,
      "grad_norm": 0.4008599817752838,
      "learning_rate": 3.3754264532519123e-06,
      "loss": 0.5045,
      "step": 47587
    },
    {
      "epoch": 1.461862193960618,
      "grad_norm": 0.43950191140174866,
      "learning_rate": 3.375064438114961e-06,
      "loss": 0.448,
      "step": 47588
    },
    {
      "epoch": 1.4618929130955673,
      "grad_norm": 0.4076898396015167,
      "learning_rate": 3.374702438451012e-06,
      "loss": 0.5131,
      "step": 47589
    },
    {
      "epoch": 1.4619236322305165,
      "grad_norm": 0.4416252374649048,
      "learning_rate": 3.3743404542609014e-06,
      "loss": 0.4742,
      "step": 47590
    },
    {
      "epoch": 1.4619543513654656,
      "grad_norm": 0.42550718784332275,
      "learning_rate": 3.3739784855454892e-06,
      "loss": 0.472,
      "step": 47591
    },
    {
      "epoch": 1.4619850705004147,
      "grad_norm": 0.4241582155227661,
      "learning_rate": 3.373616532305609e-06,
      "loss": 0.3881,
      "step": 47592
    },
    {
      "epoch": 1.4620157896353638,
      "grad_norm": 0.4373156428337097,
      "learning_rate": 3.3732545945421136e-06,
      "loss": 0.493,
      "step": 47593
    },
    {
      "epoch": 1.462046508770313,
      "grad_norm": 0.4396592676639557,
      "learning_rate": 3.372892672255841e-06,
      "loss": 0.472,
      "step": 47594
    },
    {
      "epoch": 1.462077227905262,
      "grad_norm": 0.5034305453300476,
      "learning_rate": 3.3725307654476404e-06,
      "loss": 0.4644,
      "step": 47595
    },
    {
      "epoch": 1.4621079470402114,
      "grad_norm": 0.4162287712097168,
      "learning_rate": 3.3721688741183577e-06,
      "loss": 0.4521,
      "step": 47596
    },
    {
      "epoch": 1.4621386661751605,
      "grad_norm": 0.469117671251297,
      "learning_rate": 3.3718069982688405e-06,
      "loss": 0.5484,
      "step": 47597
    },
    {
      "epoch": 1.4621693853101096,
      "grad_norm": 0.39772239327430725,
      "learning_rate": 3.371445137899928e-06,
      "loss": 0.429,
      "step": 47598
    },
    {
      "epoch": 1.4622001044450588,
      "grad_norm": 0.4340977370738983,
      "learning_rate": 3.371083293012468e-06,
      "loss": 0.4706,
      "step": 47599
    },
    {
      "epoch": 1.462230823580008,
      "grad_norm": 0.42228713631629944,
      "learning_rate": 3.370721463607306e-06,
      "loss": 0.4068,
      "step": 47600
    },
    {
      "epoch": 1.4622615427149572,
      "grad_norm": 0.44954243302345276,
      "learning_rate": 3.37035964968529e-06,
      "loss": 0.4936,
      "step": 47601
    },
    {
      "epoch": 1.4622922618499063,
      "grad_norm": 0.4400242865085602,
      "learning_rate": 3.3699978512472585e-06,
      "loss": 0.5076,
      "step": 47602
    },
    {
      "epoch": 1.4623229809848555,
      "grad_norm": 0.38343968987464905,
      "learning_rate": 3.369636068294061e-06,
      "loss": 0.4494,
      "step": 47603
    },
    {
      "epoch": 1.4623537001198046,
      "grad_norm": 0.44989579916000366,
      "learning_rate": 3.3692743008265416e-06,
      "loss": 0.4524,
      "step": 47604
    },
    {
      "epoch": 1.4623844192547537,
      "grad_norm": 0.4408155679702759,
      "learning_rate": 3.3689125488455475e-06,
      "loss": 0.4625,
      "step": 47605
    },
    {
      "epoch": 1.4624151383897028,
      "grad_norm": 0.4671291410923004,
      "learning_rate": 3.3685508123519186e-06,
      "loss": 0.5724,
      "step": 47606
    },
    {
      "epoch": 1.4624458575246522,
      "grad_norm": 0.4037649631500244,
      "learning_rate": 3.3681890913465023e-06,
      "loss": 0.5034,
      "step": 47607
    },
    {
      "epoch": 1.4624765766596013,
      "grad_norm": 0.3910805583000183,
      "learning_rate": 3.3678273858301434e-06,
      "loss": 0.4563,
      "step": 47608
    },
    {
      "epoch": 1.4625072957945504,
      "grad_norm": 0.42841991782188416,
      "learning_rate": 3.3674656958036866e-06,
      "loss": 0.4488,
      "step": 47609
    },
    {
      "epoch": 1.4625380149294995,
      "grad_norm": 0.40758490562438965,
      "learning_rate": 3.3671040212679805e-06,
      "loss": 0.5206,
      "step": 47610
    },
    {
      "epoch": 1.4625687340644489,
      "grad_norm": 0.4103884696960449,
      "learning_rate": 3.366742362223863e-06,
      "loss": 0.4789,
      "step": 47611
    },
    {
      "epoch": 1.462599453199398,
      "grad_norm": 0.43322423100471497,
      "learning_rate": 3.366380718672182e-06,
      "loss": 0.4434,
      "step": 47612
    },
    {
      "epoch": 1.4626301723343471,
      "grad_norm": 0.4261328876018524,
      "learning_rate": 3.3660190906137813e-06,
      "loss": 0.4935,
      "step": 47613
    },
    {
      "epoch": 1.4626608914692962,
      "grad_norm": 0.416271835565567,
      "learning_rate": 3.36565747804951e-06,
      "loss": 0.5165,
      "step": 47614
    },
    {
      "epoch": 1.4626916106042454,
      "grad_norm": 0.40947091579437256,
      "learning_rate": 3.365295880980206e-06,
      "loss": 0.4971,
      "step": 47615
    },
    {
      "epoch": 1.4627223297391945,
      "grad_norm": 0.4395885169506073,
      "learning_rate": 3.3649342994067204e-06,
      "loss": 0.5218,
      "step": 47616
    },
    {
      "epoch": 1.4627530488741436,
      "grad_norm": 0.4654715359210968,
      "learning_rate": 3.364572733329887e-06,
      "loss": 0.478,
      "step": 47617
    },
    {
      "epoch": 1.462783768009093,
      "grad_norm": 0.45649847388267517,
      "learning_rate": 3.364211182750564e-06,
      "loss": 0.4515,
      "step": 47618
    },
    {
      "epoch": 1.462814487144042,
      "grad_norm": 0.4294845461845398,
      "learning_rate": 3.363849647669587e-06,
      "loss": 0.4989,
      "step": 47619
    },
    {
      "epoch": 1.4628452062789912,
      "grad_norm": 0.42117398977279663,
      "learning_rate": 3.363488128087804e-06,
      "loss": 0.4693,
      "step": 47620
    },
    {
      "epoch": 1.4628759254139403,
      "grad_norm": 0.47238466143608093,
      "learning_rate": 3.3631266240060534e-06,
      "loss": 0.461,
      "step": 47621
    },
    {
      "epoch": 1.4629066445488896,
      "grad_norm": 0.42378923296928406,
      "learning_rate": 3.362765135425189e-06,
      "loss": 0.4537,
      "step": 47622
    },
    {
      "epoch": 1.4629373636838388,
      "grad_norm": 0.3920479416847229,
      "learning_rate": 3.362403662346048e-06,
      "loss": 0.411,
      "step": 47623
    },
    {
      "epoch": 1.4629680828187879,
      "grad_norm": 0.42434054613113403,
      "learning_rate": 3.3620422047694756e-06,
      "loss": 0.4973,
      "step": 47624
    },
    {
      "epoch": 1.462998801953737,
      "grad_norm": 0.4378295838832855,
      "learning_rate": 3.3616807626963223e-06,
      "loss": 0.4274,
      "step": 47625
    },
    {
      "epoch": 1.4630295210886861,
      "grad_norm": 0.40122199058532715,
      "learning_rate": 3.361319336127419e-06,
      "loss": 0.4243,
      "step": 47626
    },
    {
      "epoch": 1.4630602402236352,
      "grad_norm": 0.4198353588581085,
      "learning_rate": 3.3609579250636247e-06,
      "loss": 0.481,
      "step": 47627
    },
    {
      "epoch": 1.4630909593585844,
      "grad_norm": 0.42689886689186096,
      "learning_rate": 3.360596529505774e-06,
      "loss": 0.4898,
      "step": 47628
    },
    {
      "epoch": 1.4631216784935337,
      "grad_norm": 0.396579384803772,
      "learning_rate": 3.360235149454718e-06,
      "loss": 0.4806,
      "step": 47629
    },
    {
      "epoch": 1.4631523976284828,
      "grad_norm": 0.4364827871322632,
      "learning_rate": 3.359873784911292e-06,
      "loss": 0.438,
      "step": 47630
    },
    {
      "epoch": 1.463183116763432,
      "grad_norm": 0.43987560272216797,
      "learning_rate": 3.3595124358763455e-06,
      "loss": 0.4795,
      "step": 47631
    },
    {
      "epoch": 1.463213835898381,
      "grad_norm": 0.3875817060470581,
      "learning_rate": 3.3591511023507206e-06,
      "loss": 0.3702,
      "step": 47632
    },
    {
      "epoch": 1.4632445550333304,
      "grad_norm": 0.4145951569080353,
      "learning_rate": 3.3587897843352655e-06,
      "loss": 0.4348,
      "step": 47633
    },
    {
      "epoch": 1.4632752741682795,
      "grad_norm": 0.45825403928756714,
      "learning_rate": 3.3584284818308175e-06,
      "loss": 0.489,
      "step": 47634
    },
    {
      "epoch": 1.4633059933032286,
      "grad_norm": 0.38689401745796204,
      "learning_rate": 3.3580671948382237e-06,
      "loss": 0.3624,
      "step": 47635
    },
    {
      "epoch": 1.4633367124381778,
      "grad_norm": 0.3993106186389923,
      "learning_rate": 3.3577059233583276e-06,
      "loss": 0.4747,
      "step": 47636
    },
    {
      "epoch": 1.4633674315731269,
      "grad_norm": 0.41392257809638977,
      "learning_rate": 3.3573446673919763e-06,
      "loss": 0.4912,
      "step": 47637
    },
    {
      "epoch": 1.463398150708076,
      "grad_norm": 0.5076411962509155,
      "learning_rate": 3.356983426940008e-06,
      "loss": 0.5347,
      "step": 47638
    },
    {
      "epoch": 1.4634288698430251,
      "grad_norm": 0.4340992271900177,
      "learning_rate": 3.356622202003268e-06,
      "loss": 0.5496,
      "step": 47639
    },
    {
      "epoch": 1.4634595889779745,
      "grad_norm": 0.44301360845565796,
      "learning_rate": 3.356260992582602e-06,
      "loss": 0.4782,
      "step": 47640
    },
    {
      "epoch": 1.4634903081129236,
      "grad_norm": 0.4058777093887329,
      "learning_rate": 3.3558997986788544e-06,
      "loss": 0.4596,
      "step": 47641
    },
    {
      "epoch": 1.4635210272478727,
      "grad_norm": 0.38788509368896484,
      "learning_rate": 3.355538620292864e-06,
      "loss": 0.4716,
      "step": 47642
    },
    {
      "epoch": 1.4635517463828218,
      "grad_norm": 0.4246008098125458,
      "learning_rate": 3.355177457425477e-06,
      "loss": 0.4177,
      "step": 47643
    },
    {
      "epoch": 1.463582465517771,
      "grad_norm": 0.4217897951602936,
      "learning_rate": 3.3548163100775375e-06,
      "loss": 0.4639,
      "step": 47644
    },
    {
      "epoch": 1.4636131846527203,
      "grad_norm": 0.469461590051651,
      "learning_rate": 3.354455178249889e-06,
      "loss": 0.4812,
      "step": 47645
    },
    {
      "epoch": 1.4636439037876694,
      "grad_norm": 0.44076940417289734,
      "learning_rate": 3.354094061943377e-06,
      "loss": 0.4256,
      "step": 47646
    },
    {
      "epoch": 1.4636746229226185,
      "grad_norm": 0.4291120171546936,
      "learning_rate": 3.3537329611588396e-06,
      "loss": 0.4625,
      "step": 47647
    },
    {
      "epoch": 1.4637053420575676,
      "grad_norm": 0.3931834399700165,
      "learning_rate": 3.3533718758971223e-06,
      "loss": 0.4714,
      "step": 47648
    },
    {
      "epoch": 1.4637360611925168,
      "grad_norm": 0.4106772243976593,
      "learning_rate": 3.3530108061590706e-06,
      "loss": 0.4411,
      "step": 47649
    },
    {
      "epoch": 1.4637667803274659,
      "grad_norm": 0.44005343317985535,
      "learning_rate": 3.352649751945528e-06,
      "loss": 0.4702,
      "step": 47650
    },
    {
      "epoch": 1.4637974994624152,
      "grad_norm": 0.39912962913513184,
      "learning_rate": 3.3522887132573346e-06,
      "loss": 0.4887,
      "step": 47651
    },
    {
      "epoch": 1.4638282185973643,
      "grad_norm": 0.4807073771953583,
      "learning_rate": 3.351927690095337e-06,
      "loss": 0.4426,
      "step": 47652
    },
    {
      "epoch": 1.4638589377323135,
      "grad_norm": 0.4032457172870636,
      "learning_rate": 3.351566682460371e-06,
      "loss": 0.4692,
      "step": 47653
    },
    {
      "epoch": 1.4638896568672626,
      "grad_norm": 0.4080166518688202,
      "learning_rate": 3.351205690353292e-06,
      "loss": 0.446,
      "step": 47654
    },
    {
      "epoch": 1.4639203760022117,
      "grad_norm": 0.43496906757354736,
      "learning_rate": 3.3508447137749323e-06,
      "loss": 0.5128,
      "step": 47655
    },
    {
      "epoch": 1.463951095137161,
      "grad_norm": 0.4499630630016327,
      "learning_rate": 3.3504837527261426e-06,
      "loss": 0.4525,
      "step": 47656
    },
    {
      "epoch": 1.4639818142721102,
      "grad_norm": 0.43607473373413086,
      "learning_rate": 3.3501228072077596e-06,
      "loss": 0.5058,
      "step": 47657
    },
    {
      "epoch": 1.4640125334070593,
      "grad_norm": 0.4465780556201935,
      "learning_rate": 3.3497618772206286e-06,
      "loss": 0.3756,
      "step": 47658
    },
    {
      "epoch": 1.4640432525420084,
      "grad_norm": 0.4115709066390991,
      "learning_rate": 3.3494009627655945e-06,
      "loss": 0.4585,
      "step": 47659
    },
    {
      "epoch": 1.4640739716769575,
      "grad_norm": 0.42518970370292664,
      "learning_rate": 3.3490400638435006e-06,
      "loss": 0.4856,
      "step": 47660
    },
    {
      "epoch": 1.4641046908119066,
      "grad_norm": 0.4224869906902313,
      "learning_rate": 3.3486791804551854e-06,
      "loss": 0.5079,
      "step": 47661
    },
    {
      "epoch": 1.4641354099468558,
      "grad_norm": 0.44979536533355713,
      "learning_rate": 3.3483183126014918e-06,
      "loss": 0.5008,
      "step": 47662
    },
    {
      "epoch": 1.464166129081805,
      "grad_norm": 0.3787344992160797,
      "learning_rate": 3.347957460283271e-06,
      "loss": 0.4754,
      "step": 47663
    },
    {
      "epoch": 1.4641968482167542,
      "grad_norm": 0.4589507281780243,
      "learning_rate": 3.347596623501358e-06,
      "loss": 0.4807,
      "step": 47664
    },
    {
      "epoch": 1.4642275673517033,
      "grad_norm": 0.4039764702320099,
      "learning_rate": 3.3472358022565997e-06,
      "loss": 0.5297,
      "step": 47665
    },
    {
      "epoch": 1.4642582864866525,
      "grad_norm": 0.418867290019989,
      "learning_rate": 3.346874996549835e-06,
      "loss": 0.4759,
      "step": 47666
    },
    {
      "epoch": 1.4642890056216018,
      "grad_norm": 0.4418005645275116,
      "learning_rate": 3.3465142063819065e-06,
      "loss": 0.5481,
      "step": 47667
    },
    {
      "epoch": 1.464319724756551,
      "grad_norm": 0.3798914849758148,
      "learning_rate": 3.3461534317536603e-06,
      "loss": 0.4206,
      "step": 47668
    },
    {
      "epoch": 1.4643504438915,
      "grad_norm": 0.40955448150634766,
      "learning_rate": 3.3457926726659406e-06,
      "loss": 0.4881,
      "step": 47669
    },
    {
      "epoch": 1.4643811630264492,
      "grad_norm": 0.43357136845588684,
      "learning_rate": 3.3454319291195823e-06,
      "loss": 0.437,
      "step": 47670
    },
    {
      "epoch": 1.4644118821613983,
      "grad_norm": 0.4993599057197571,
      "learning_rate": 3.345071201115434e-06,
      "loss": 0.4582,
      "step": 47671
    },
    {
      "epoch": 1.4644426012963474,
      "grad_norm": 0.44310590624809265,
      "learning_rate": 3.3447104886543358e-06,
      "loss": 0.4732,
      "step": 47672
    },
    {
      "epoch": 1.4644733204312965,
      "grad_norm": 0.41910386085510254,
      "learning_rate": 3.344349791737135e-06,
      "loss": 0.4467,
      "step": 47673
    },
    {
      "epoch": 1.4645040395662459,
      "grad_norm": 0.45542529225349426,
      "learning_rate": 3.343989110364666e-06,
      "loss": 0.4879,
      "step": 47674
    },
    {
      "epoch": 1.464534758701195,
      "grad_norm": 0.4084084630012512,
      "learning_rate": 3.343628444537775e-06,
      "loss": 0.4551,
      "step": 47675
    },
    {
      "epoch": 1.464565477836144,
      "grad_norm": 0.4057076871395111,
      "learning_rate": 3.3432677942573054e-06,
      "loss": 0.4107,
      "step": 47676
    },
    {
      "epoch": 1.4645961969710932,
      "grad_norm": 0.4218234419822693,
      "learning_rate": 3.3429071595241025e-06,
      "loss": 0.4279,
      "step": 47677
    },
    {
      "epoch": 1.4646269161060426,
      "grad_norm": 0.4112130105495453,
      "learning_rate": 3.3425465403390012e-06,
      "loss": 0.4609,
      "step": 47678
    },
    {
      "epoch": 1.4646576352409917,
      "grad_norm": 0.45093104243278503,
      "learning_rate": 3.3421859367028465e-06,
      "loss": 0.4449,
      "step": 47679
    },
    {
      "epoch": 1.4646883543759408,
      "grad_norm": 0.4036825895309448,
      "learning_rate": 3.3418253486164833e-06,
      "loss": 0.4581,
      "step": 47680
    },
    {
      "epoch": 1.46471907351089,
      "grad_norm": 0.4539303481578827,
      "learning_rate": 3.3414647760807504e-06,
      "loss": 0.4362,
      "step": 47681
    },
    {
      "epoch": 1.464749792645839,
      "grad_norm": 0.43031221628189087,
      "learning_rate": 3.3411042190964947e-06,
      "loss": 0.5055,
      "step": 47682
    },
    {
      "epoch": 1.4647805117807882,
      "grad_norm": 0.4561412036418915,
      "learning_rate": 3.340743677664553e-06,
      "loss": 0.5138,
      "step": 47683
    },
    {
      "epoch": 1.4648112309157373,
      "grad_norm": 0.386845201253891,
      "learning_rate": 3.340383151785769e-06,
      "loss": 0.4962,
      "step": 47684
    },
    {
      "epoch": 1.4648419500506866,
      "grad_norm": 0.4067757725715637,
      "learning_rate": 3.340022641460986e-06,
      "loss": 0.3997,
      "step": 47685
    },
    {
      "epoch": 1.4648726691856357,
      "grad_norm": 0.42235440015792847,
      "learning_rate": 3.3396621466910473e-06,
      "loss": 0.422,
      "step": 47686
    },
    {
      "epoch": 1.4649033883205849,
      "grad_norm": 0.448331356048584,
      "learning_rate": 3.33930166747679e-06,
      "loss": 0.5428,
      "step": 47687
    },
    {
      "epoch": 1.464934107455534,
      "grad_norm": 0.4373178482055664,
      "learning_rate": 3.3389412038190626e-06,
      "loss": 0.4965,
      "step": 47688
    },
    {
      "epoch": 1.4649648265904833,
      "grad_norm": 0.40805134177207947,
      "learning_rate": 3.3385807557186955e-06,
      "loss": 0.5063,
      "step": 47689
    },
    {
      "epoch": 1.4649955457254324,
      "grad_norm": 0.43168842792510986,
      "learning_rate": 3.3382203231765464e-06,
      "loss": 0.5152,
      "step": 47690
    },
    {
      "epoch": 1.4650262648603816,
      "grad_norm": 0.4264112114906311,
      "learning_rate": 3.337859906193445e-06,
      "loss": 0.5331,
      "step": 47691
    },
    {
      "epoch": 1.4650569839953307,
      "grad_norm": 0.44948291778564453,
      "learning_rate": 3.33749950477024e-06,
      "loss": 0.4202,
      "step": 47692
    },
    {
      "epoch": 1.4650877031302798,
      "grad_norm": 0.44933319091796875,
      "learning_rate": 3.337139118907766e-06,
      "loss": 0.4369,
      "step": 47693
    },
    {
      "epoch": 1.465118422265229,
      "grad_norm": 0.4024738073348999,
      "learning_rate": 3.3367787486068703e-06,
      "loss": 0.4563,
      "step": 47694
    },
    {
      "epoch": 1.465149141400178,
      "grad_norm": 0.4219793677330017,
      "learning_rate": 3.3364183938683935e-06,
      "loss": 0.5208,
      "step": 47695
    },
    {
      "epoch": 1.4651798605351274,
      "grad_norm": 0.4067392647266388,
      "learning_rate": 3.33605805469318e-06,
      "loss": 0.4959,
      "step": 47696
    },
    {
      "epoch": 1.4652105796700765,
      "grad_norm": 0.4970618188381195,
      "learning_rate": 3.335697731082065e-06,
      "loss": 0.3846,
      "step": 47697
    },
    {
      "epoch": 1.4652412988050256,
      "grad_norm": 0.40361785888671875,
      "learning_rate": 3.3353374230358926e-06,
      "loss": 0.4892,
      "step": 47698
    },
    {
      "epoch": 1.4652720179399747,
      "grad_norm": 0.476145476102829,
      "learning_rate": 3.3349771305555055e-06,
      "loss": 0.4535,
      "step": 47699
    },
    {
      "epoch": 1.465302737074924,
      "grad_norm": 0.40717339515686035,
      "learning_rate": 3.3346168536417446e-06,
      "loss": 0.4199,
      "step": 47700
    },
    {
      "epoch": 1.4653334562098732,
      "grad_norm": 0.42657896876335144,
      "learning_rate": 3.334256592295455e-06,
      "loss": 0.4889,
      "step": 47701
    },
    {
      "epoch": 1.4653641753448223,
      "grad_norm": 0.4357427954673767,
      "learning_rate": 3.333896346517471e-06,
      "loss": 0.439,
      "step": 47702
    },
    {
      "epoch": 1.4653948944797714,
      "grad_norm": 0.4216923713684082,
      "learning_rate": 3.333536116308639e-06,
      "loss": 0.4829,
      "step": 47703
    },
    {
      "epoch": 1.4654256136147206,
      "grad_norm": 0.4698317050933838,
      "learning_rate": 3.3331759016697975e-06,
      "loss": 0.5722,
      "step": 47704
    },
    {
      "epoch": 1.4654563327496697,
      "grad_norm": 0.47872647643089294,
      "learning_rate": 3.3328157026017937e-06,
      "loss": 0.4888,
      "step": 47705
    },
    {
      "epoch": 1.4654870518846188,
      "grad_norm": 0.4090331792831421,
      "learning_rate": 3.3324555191054607e-06,
      "loss": 0.4152,
      "step": 47706
    },
    {
      "epoch": 1.4655177710195681,
      "grad_norm": 0.4936637282371521,
      "learning_rate": 3.3320953511816433e-06,
      "loss": 0.5375,
      "step": 47707
    },
    {
      "epoch": 1.4655484901545173,
      "grad_norm": 0.41871485114097595,
      "learning_rate": 3.331735198831183e-06,
      "loss": 0.4503,
      "step": 47708
    },
    {
      "epoch": 1.4655792092894664,
      "grad_norm": 0.44269195199012756,
      "learning_rate": 3.3313750620549245e-06,
      "loss": 0.4908,
      "step": 47709
    },
    {
      "epoch": 1.4656099284244155,
      "grad_norm": 0.41437986493110657,
      "learning_rate": 3.3310149408537007e-06,
      "loss": 0.4199,
      "step": 47710
    },
    {
      "epoch": 1.4656406475593649,
      "grad_norm": 0.4065580368041992,
      "learning_rate": 3.3306548352283587e-06,
      "loss": 0.5199,
      "step": 47711
    },
    {
      "epoch": 1.465671366694314,
      "grad_norm": 0.4273112416267395,
      "learning_rate": 3.3302947451797374e-06,
      "loss": 0.5054,
      "step": 47712
    },
    {
      "epoch": 1.465702085829263,
      "grad_norm": 0.41872742772102356,
      "learning_rate": 3.3299346707086823e-06,
      "loss": 0.54,
      "step": 47713
    },
    {
      "epoch": 1.4657328049642122,
      "grad_norm": 0.4623037576675415,
      "learning_rate": 3.3295746118160266e-06,
      "loss": 0.5143,
      "step": 47714
    },
    {
      "epoch": 1.4657635240991613,
      "grad_norm": 0.4035891592502594,
      "learning_rate": 3.3292145685026155e-06,
      "loss": 0.5038,
      "step": 47715
    },
    {
      "epoch": 1.4657942432341104,
      "grad_norm": 0.4181080758571625,
      "learning_rate": 3.328854540769291e-06,
      "loss": 0.4402,
      "step": 47716
    },
    {
      "epoch": 1.4658249623690596,
      "grad_norm": 0.4059489965438843,
      "learning_rate": 3.328494528616891e-06,
      "loss": 0.5305,
      "step": 47717
    },
    {
      "epoch": 1.465855681504009,
      "grad_norm": 0.45797520875930786,
      "learning_rate": 3.328134532046261e-06,
      "loss": 0.5216,
      "step": 47718
    },
    {
      "epoch": 1.465886400638958,
      "grad_norm": 0.4458008408546448,
      "learning_rate": 3.327774551058237e-06,
      "loss": 0.4122,
      "step": 47719
    },
    {
      "epoch": 1.4659171197739072,
      "grad_norm": 0.42889031767845154,
      "learning_rate": 3.3274145856536633e-06,
      "loss": 0.4312,
      "step": 47720
    },
    {
      "epoch": 1.4659478389088563,
      "grad_norm": 0.46306583285331726,
      "learning_rate": 3.3270546358333734e-06,
      "loss": 0.4929,
      "step": 47721
    },
    {
      "epoch": 1.4659785580438056,
      "grad_norm": 0.45018601417541504,
      "learning_rate": 3.32669470159822e-06,
      "loss": 0.3872,
      "step": 47722
    },
    {
      "epoch": 1.4660092771787547,
      "grad_norm": 0.4491299092769623,
      "learning_rate": 3.3263347829490335e-06,
      "loss": 0.4814,
      "step": 47723
    },
    {
      "epoch": 1.4660399963137039,
      "grad_norm": 0.44131216406822205,
      "learning_rate": 3.325974879886661e-06,
      "loss": 0.4875,
      "step": 47724
    },
    {
      "epoch": 1.466070715448653,
      "grad_norm": 0.40266481041908264,
      "learning_rate": 3.3256149924119343e-06,
      "loss": 0.4434,
      "step": 47725
    },
    {
      "epoch": 1.466101434583602,
      "grad_norm": 0.3966955542564392,
      "learning_rate": 3.3252551205257068e-06,
      "loss": 0.4363,
      "step": 47726
    },
    {
      "epoch": 1.4661321537185512,
      "grad_norm": 0.4258348345756531,
      "learning_rate": 3.324895264228808e-06,
      "loss": 0.5006,
      "step": 47727
    },
    {
      "epoch": 1.4661628728535003,
      "grad_norm": 0.3929966390132904,
      "learning_rate": 3.324535423522086e-06,
      "loss": 0.4048,
      "step": 47728
    },
    {
      "epoch": 1.4661935919884497,
      "grad_norm": 0.4755740463733673,
      "learning_rate": 3.324175598406375e-06,
      "loss": 0.5138,
      "step": 47729
    },
    {
      "epoch": 1.4662243111233988,
      "grad_norm": 0.46665945649147034,
      "learning_rate": 3.323815788882517e-06,
      "loss": 0.4546,
      "step": 47730
    },
    {
      "epoch": 1.466255030258348,
      "grad_norm": 0.5437197089195251,
      "learning_rate": 3.3234559949513546e-06,
      "loss": 0.4155,
      "step": 47731
    },
    {
      "epoch": 1.466285749393297,
      "grad_norm": 0.39823830127716064,
      "learning_rate": 3.3230962166137303e-06,
      "loss": 0.5085,
      "step": 47732
    },
    {
      "epoch": 1.4663164685282464,
      "grad_norm": 0.42494574189186096,
      "learning_rate": 3.3227364538704775e-06,
      "loss": 0.4185,
      "step": 47733
    },
    {
      "epoch": 1.4663471876631955,
      "grad_norm": 0.42942631244659424,
      "learning_rate": 3.32237670672244e-06,
      "loss": 0.498,
      "step": 47734
    },
    {
      "epoch": 1.4663779067981446,
      "grad_norm": 0.40607041120529175,
      "learning_rate": 3.3220169751704577e-06,
      "loss": 0.4345,
      "step": 47735
    },
    {
      "epoch": 1.4664086259330937,
      "grad_norm": 0.3967422544956207,
      "learning_rate": 3.3216572592153716e-06,
      "loss": 0.4825,
      "step": 47736
    },
    {
      "epoch": 1.4664393450680429,
      "grad_norm": 0.4095049202442169,
      "learning_rate": 3.321297558858024e-06,
      "loss": 0.4595,
      "step": 47737
    },
    {
      "epoch": 1.466470064202992,
      "grad_norm": 0.44733548164367676,
      "learning_rate": 3.3209378740992505e-06,
      "loss": 0.3944,
      "step": 47738
    },
    {
      "epoch": 1.466500783337941,
      "grad_norm": 0.45080050826072693,
      "learning_rate": 3.3205782049398916e-06,
      "loss": 0.4587,
      "step": 47739
    },
    {
      "epoch": 1.4665315024728904,
      "grad_norm": 0.4231608808040619,
      "learning_rate": 3.3202185513807892e-06,
      "loss": 0.3859,
      "step": 47740
    },
    {
      "epoch": 1.4665622216078396,
      "grad_norm": 0.3970663547515869,
      "learning_rate": 3.3198589134227864e-06,
      "loss": 0.4125,
      "step": 47741
    },
    {
      "epoch": 1.4665929407427887,
      "grad_norm": 0.447418749332428,
      "learning_rate": 3.3194992910667168e-06,
      "loss": 0.4805,
      "step": 47742
    },
    {
      "epoch": 1.4666236598777378,
      "grad_norm": 0.37021639943122864,
      "learning_rate": 3.3191396843134226e-06,
      "loss": 0.4461,
      "step": 47743
    },
    {
      "epoch": 1.4666543790126871,
      "grad_norm": 0.4086734354496002,
      "learning_rate": 3.3187800931637437e-06,
      "loss": 0.4046,
      "step": 47744
    },
    {
      "epoch": 1.4666850981476363,
      "grad_norm": 0.43631038069725037,
      "learning_rate": 3.3184205176185247e-06,
      "loss": 0.4498,
      "step": 47745
    },
    {
      "epoch": 1.4667158172825854,
      "grad_norm": 0.3995056450366974,
      "learning_rate": 3.318060957678598e-06,
      "loss": 0.452,
      "step": 47746
    },
    {
      "epoch": 1.4667465364175345,
      "grad_norm": 0.43005678057670593,
      "learning_rate": 3.317701413344806e-06,
      "loss": 0.4549,
      "step": 47747
    },
    {
      "epoch": 1.4667772555524836,
      "grad_norm": 0.4585985243320465,
      "learning_rate": 3.3173418846179896e-06,
      "loss": 0.5292,
      "step": 47748
    },
    {
      "epoch": 1.4668079746874327,
      "grad_norm": 0.4580952823162079,
      "learning_rate": 3.3169823714989904e-06,
      "loss": 0.4608,
      "step": 47749
    },
    {
      "epoch": 1.4668386938223819,
      "grad_norm": 0.47767210006713867,
      "learning_rate": 3.316622873988643e-06,
      "loss": 0.4149,
      "step": 47750
    },
    {
      "epoch": 1.4668694129573312,
      "grad_norm": 0.4813610911369324,
      "learning_rate": 3.316263392087793e-06,
      "loss": 0.4334,
      "step": 47751
    },
    {
      "epoch": 1.4669001320922803,
      "grad_norm": 0.47888654470443726,
      "learning_rate": 3.3159039257972694e-06,
      "loss": 0.429,
      "step": 47752
    },
    {
      "epoch": 1.4669308512272294,
      "grad_norm": 0.41667431592941284,
      "learning_rate": 3.3155444751179234e-06,
      "loss": 0.4644,
      "step": 47753
    },
    {
      "epoch": 1.4669615703621786,
      "grad_norm": 0.44400402903556824,
      "learning_rate": 3.3151850400505924e-06,
      "loss": 0.3535,
      "step": 47754
    },
    {
      "epoch": 1.466992289497128,
      "grad_norm": 0.4219283163547516,
      "learning_rate": 3.3148256205961106e-06,
      "loss": 0.5126,
      "step": 47755
    },
    {
      "epoch": 1.467023008632077,
      "grad_norm": 0.410121887922287,
      "learning_rate": 3.314466216755323e-06,
      "loss": 0.4352,
      "step": 47756
    },
    {
      "epoch": 1.4670537277670261,
      "grad_norm": 0.44824090600013733,
      "learning_rate": 3.3141068285290614e-06,
      "loss": 0.4315,
      "step": 47757
    },
    {
      "epoch": 1.4670844469019753,
      "grad_norm": 0.4576401114463806,
      "learning_rate": 3.313747455918176e-06,
      "loss": 0.4718,
      "step": 47758
    },
    {
      "epoch": 1.4671151660369244,
      "grad_norm": 0.4236694574356079,
      "learning_rate": 3.313388098923497e-06,
      "loss": 0.5131,
      "step": 47759
    },
    {
      "epoch": 1.4671458851718735,
      "grad_norm": 0.44105151295661926,
      "learning_rate": 3.3130287575458707e-06,
      "loss": 0.4661,
      "step": 47760
    },
    {
      "epoch": 1.4671766043068226,
      "grad_norm": 0.3978322744369507,
      "learning_rate": 3.31266943178613e-06,
      "loss": 0.4318,
      "step": 47761
    },
    {
      "epoch": 1.467207323441772,
      "grad_norm": 0.377590537071228,
      "learning_rate": 3.3123101216451158e-06,
      "loss": 0.4743,
      "step": 47762
    },
    {
      "epoch": 1.467238042576721,
      "grad_norm": 0.4038892388343811,
      "learning_rate": 3.3119508271236688e-06,
      "loss": 0.4609,
      "step": 47763
    },
    {
      "epoch": 1.4672687617116702,
      "grad_norm": 0.44568774104118347,
      "learning_rate": 3.3115915482226304e-06,
      "loss": 0.5179,
      "step": 47764
    },
    {
      "epoch": 1.4672994808466193,
      "grad_norm": 0.43883076310157776,
      "learning_rate": 3.311232284942835e-06,
      "loss": 0.4794,
      "step": 47765
    },
    {
      "epoch": 1.4673301999815684,
      "grad_norm": 0.43335482478141785,
      "learning_rate": 3.3108730372851226e-06,
      "loss": 0.5432,
      "step": 47766
    },
    {
      "epoch": 1.4673609191165178,
      "grad_norm": 0.45718395709991455,
      "learning_rate": 3.3105138052503337e-06,
      "loss": 0.5387,
      "step": 47767
    },
    {
      "epoch": 1.467391638251467,
      "grad_norm": 0.46655240654945374,
      "learning_rate": 3.3101545888393107e-06,
      "loss": 0.4163,
      "step": 47768
    },
    {
      "epoch": 1.467422357386416,
      "grad_norm": 0.4396287202835083,
      "learning_rate": 3.3097953880528856e-06,
      "loss": 0.4349,
      "step": 47769
    },
    {
      "epoch": 1.4674530765213651,
      "grad_norm": 0.4214039146900177,
      "learning_rate": 3.3094362028919e-06,
      "loss": 0.591,
      "step": 47770
    },
    {
      "epoch": 1.4674837956563143,
      "grad_norm": 0.4134562909603119,
      "learning_rate": 3.309077033357193e-06,
      "loss": 0.4538,
      "step": 47771
    },
    {
      "epoch": 1.4675145147912634,
      "grad_norm": 0.39372262358665466,
      "learning_rate": 3.3087178794496054e-06,
      "loss": 0.4581,
      "step": 47772
    },
    {
      "epoch": 1.4675452339262125,
      "grad_norm": 0.43013444542884827,
      "learning_rate": 3.3083587411699767e-06,
      "loss": 0.3846,
      "step": 47773
    },
    {
      "epoch": 1.4675759530611618,
      "grad_norm": 0.4137035608291626,
      "learning_rate": 3.307999618519141e-06,
      "loss": 0.4719,
      "step": 47774
    },
    {
      "epoch": 1.467606672196111,
      "grad_norm": 0.47557681798934937,
      "learning_rate": 3.307640511497938e-06,
      "loss": 0.4876,
      "step": 47775
    },
    {
      "epoch": 1.46763739133106,
      "grad_norm": 0.9913159012794495,
      "learning_rate": 3.3072814201072103e-06,
      "loss": 0.5059,
      "step": 47776
    },
    {
      "epoch": 1.4676681104660092,
      "grad_norm": 0.4030003845691681,
      "learning_rate": 3.306922344347796e-06,
      "loss": 0.4674,
      "step": 47777
    },
    {
      "epoch": 1.4676988296009585,
      "grad_norm": 0.4351699948310852,
      "learning_rate": 3.3065632842205285e-06,
      "loss": 0.4275,
      "step": 47778
    },
    {
      "epoch": 1.4677295487359077,
      "grad_norm": 0.668849527835846,
      "learning_rate": 3.3062042397262507e-06,
      "loss": 0.4508,
      "step": 47779
    },
    {
      "epoch": 1.4677602678708568,
      "grad_norm": 0.4708620309829712,
      "learning_rate": 3.3058452108658003e-06,
      "loss": 0.4713,
      "step": 47780
    },
    {
      "epoch": 1.467790987005806,
      "grad_norm": 0.4102250933647156,
      "learning_rate": 3.3054861976400187e-06,
      "loss": 0.493,
      "step": 47781
    },
    {
      "epoch": 1.467821706140755,
      "grad_norm": 0.4223863482475281,
      "learning_rate": 3.305127200049738e-06,
      "loss": 0.4357,
      "step": 47782
    },
    {
      "epoch": 1.4678524252757041,
      "grad_norm": 0.37029486894607544,
      "learning_rate": 3.3047682180958018e-06,
      "loss": 0.4063,
      "step": 47783
    },
    {
      "epoch": 1.4678831444106533,
      "grad_norm": 0.41178515553474426,
      "learning_rate": 3.304409251779046e-06,
      "loss": 0.5188,
      "step": 47784
    },
    {
      "epoch": 1.4679138635456026,
      "grad_norm": 0.3873906433582306,
      "learning_rate": 3.304050301100313e-06,
      "loss": 0.4973,
      "step": 47785
    },
    {
      "epoch": 1.4679445826805517,
      "grad_norm": 0.4420399069786072,
      "learning_rate": 3.3036913660604354e-06,
      "loss": 0.4387,
      "step": 47786
    },
    {
      "epoch": 1.4679753018155008,
      "grad_norm": 0.6531014442443848,
      "learning_rate": 3.303332446660258e-06,
      "loss": 0.4561,
      "step": 47787
    },
    {
      "epoch": 1.46800602095045,
      "grad_norm": 0.45327791571617126,
      "learning_rate": 3.302973542900608e-06,
      "loss": 0.5306,
      "step": 47788
    },
    {
      "epoch": 1.4680367400853993,
      "grad_norm": 0.4478497803211212,
      "learning_rate": 3.3026146547823344e-06,
      "loss": 0.4486,
      "step": 47789
    },
    {
      "epoch": 1.4680674592203484,
      "grad_norm": 0.41244789958000183,
      "learning_rate": 3.302255782306276e-06,
      "loss": 0.4886,
      "step": 47790
    },
    {
      "epoch": 1.4680981783552975,
      "grad_norm": 0.42110675573349,
      "learning_rate": 3.3018969254732626e-06,
      "loss": 0.4509,
      "step": 47791
    },
    {
      "epoch": 1.4681288974902467,
      "grad_norm": 0.4088885486125946,
      "learning_rate": 3.3015380842841403e-06,
      "loss": 0.4822,
      "step": 47792
    },
    {
      "epoch": 1.4681596166251958,
      "grad_norm": 0.4717051088809967,
      "learning_rate": 3.3011792587397374e-06,
      "loss": 0.5385,
      "step": 47793
    },
    {
      "epoch": 1.468190335760145,
      "grad_norm": 0.42133525013923645,
      "learning_rate": 3.3008204488409045e-06,
      "loss": 0.502,
      "step": 47794
    },
    {
      "epoch": 1.468221054895094,
      "grad_norm": 0.4038379192352295,
      "learning_rate": 3.3004616545884707e-06,
      "loss": 0.4475,
      "step": 47795
    },
    {
      "epoch": 1.4682517740300434,
      "grad_norm": 0.44264206290245056,
      "learning_rate": 3.30010287598328e-06,
      "loss": 0.4792,
      "step": 47796
    },
    {
      "epoch": 1.4682824931649925,
      "grad_norm": 0.42450591921806335,
      "learning_rate": 3.299744113026162e-06,
      "loss": 0.575,
      "step": 47797
    },
    {
      "epoch": 1.4683132122999416,
      "grad_norm": 0.45938387513160706,
      "learning_rate": 3.2993853657179607e-06,
      "loss": 0.5505,
      "step": 47798
    },
    {
      "epoch": 1.4683439314348907,
      "grad_norm": 0.42041704058647156,
      "learning_rate": 3.2990266340595133e-06,
      "loss": 0.4974,
      "step": 47799
    },
    {
      "epoch": 1.46837465056984,
      "grad_norm": 0.41742801666259766,
      "learning_rate": 3.2986679180516603e-06,
      "loss": 0.5173,
      "step": 47800
    },
    {
      "epoch": 1.4684053697047892,
      "grad_norm": 0.3857066035270691,
      "learning_rate": 3.2983092176952325e-06,
      "loss": 0.5074,
      "step": 47801
    },
    {
      "epoch": 1.4684360888397383,
      "grad_norm": 0.4244210422039032,
      "learning_rate": 3.297950532991071e-06,
      "loss": 0.4614,
      "step": 47802
    },
    {
      "epoch": 1.4684668079746874,
      "grad_norm": 0.429487019777298,
      "learning_rate": 3.297591863940015e-06,
      "loss": 0.4424,
      "step": 47803
    },
    {
      "epoch": 1.4684975271096365,
      "grad_norm": 0.3836338520050049,
      "learning_rate": 3.297233210542905e-06,
      "loss": 0.443,
      "step": 47804
    },
    {
      "epoch": 1.4685282462445857,
      "grad_norm": 0.3961489498615265,
      "learning_rate": 3.2968745728005713e-06,
      "loss": 0.4691,
      "step": 47805
    },
    {
      "epoch": 1.4685589653795348,
      "grad_norm": 0.42194631695747375,
      "learning_rate": 3.2965159507138545e-06,
      "loss": 0.4488,
      "step": 47806
    },
    {
      "epoch": 1.4685896845144841,
      "grad_norm": 0.40982866287231445,
      "learning_rate": 3.2961573442835936e-06,
      "loss": 0.487,
      "step": 47807
    },
    {
      "epoch": 1.4686204036494332,
      "grad_norm": 0.4231889247894287,
      "learning_rate": 3.2957987535106252e-06,
      "loss": 0.5033,
      "step": 47808
    },
    {
      "epoch": 1.4686511227843824,
      "grad_norm": 0.40635523200035095,
      "learning_rate": 3.29544017839579e-06,
      "loss": 0.4974,
      "step": 47809
    },
    {
      "epoch": 1.4686818419193315,
      "grad_norm": 0.40917298197746277,
      "learning_rate": 3.2950816189399203e-06,
      "loss": 0.4892,
      "step": 47810
    },
    {
      "epoch": 1.4687125610542808,
      "grad_norm": 0.4421563148498535,
      "learning_rate": 3.294723075143854e-06,
      "loss": 0.4245,
      "step": 47811
    },
    {
      "epoch": 1.46874328018923,
      "grad_norm": 0.45410260558128357,
      "learning_rate": 3.2943645470084318e-06,
      "loss": 0.4725,
      "step": 47812
    },
    {
      "epoch": 1.468773999324179,
      "grad_norm": 0.410534143447876,
      "learning_rate": 3.294006034534493e-06,
      "loss": 0.4887,
      "step": 47813
    },
    {
      "epoch": 1.4688047184591282,
      "grad_norm": 0.4155341684818268,
      "learning_rate": 3.293647537722866e-06,
      "loss": 0.496,
      "step": 47814
    },
    {
      "epoch": 1.4688354375940773,
      "grad_norm": 0.39767029881477356,
      "learning_rate": 3.293289056574396e-06,
      "loss": 0.5274,
      "step": 47815
    },
    {
      "epoch": 1.4688661567290264,
      "grad_norm": 0.36154618859291077,
      "learning_rate": 3.2929305910899167e-06,
      "loss": 0.4211,
      "step": 47816
    },
    {
      "epoch": 1.4688968758639755,
      "grad_norm": 0.4237719476222992,
      "learning_rate": 3.2925721412702692e-06,
      "loss": 0.5291,
      "step": 47817
    },
    {
      "epoch": 1.468927594998925,
      "grad_norm": 0.4016188085079193,
      "learning_rate": 3.292213707116285e-06,
      "loss": 0.4855,
      "step": 47818
    },
    {
      "epoch": 1.468958314133874,
      "grad_norm": 0.43020254373550415,
      "learning_rate": 3.291855288628808e-06,
      "loss": 0.4616,
      "step": 47819
    },
    {
      "epoch": 1.4689890332688231,
      "grad_norm": 0.46434929966926575,
      "learning_rate": 3.291496885808664e-06,
      "loss": 0.5594,
      "step": 47820
    },
    {
      "epoch": 1.4690197524037722,
      "grad_norm": 0.42447349429130554,
      "learning_rate": 3.2911384986567053e-06,
      "loss": 0.4631,
      "step": 47821
    },
    {
      "epoch": 1.4690504715387216,
      "grad_norm": 0.41668787598609924,
      "learning_rate": 3.2907801271737573e-06,
      "loss": 0.5238,
      "step": 47822
    },
    {
      "epoch": 1.4690811906736707,
      "grad_norm": 0.4557770788669586,
      "learning_rate": 3.2904217713606634e-06,
      "loss": 0.4431,
      "step": 47823
    },
    {
      "epoch": 1.4691119098086198,
      "grad_norm": 0.3587096929550171,
      "learning_rate": 3.290063431218252e-06,
      "loss": 0.4437,
      "step": 47824
    },
    {
      "epoch": 1.469142628943569,
      "grad_norm": 0.43214666843414307,
      "learning_rate": 3.2897051067473695e-06,
      "loss": 0.5111,
      "step": 47825
    },
    {
      "epoch": 1.469173348078518,
      "grad_norm": 0.46130675077438354,
      "learning_rate": 3.2893467979488525e-06,
      "loss": 0.4411,
      "step": 47826
    },
    {
      "epoch": 1.4692040672134672,
      "grad_norm": 0.41160714626312256,
      "learning_rate": 3.2889885048235316e-06,
      "loss": 0.452,
      "step": 47827
    },
    {
      "epoch": 1.4692347863484163,
      "grad_norm": 0.4525587260723114,
      "learning_rate": 3.2886302273722505e-06,
      "loss": 0.5335,
      "step": 47828
    },
    {
      "epoch": 1.4692655054833657,
      "grad_norm": 0.4511522352695465,
      "learning_rate": 3.288271965595835e-06,
      "loss": 0.4486,
      "step": 47829
    },
    {
      "epoch": 1.4692962246183148,
      "grad_norm": 0.40987083315849304,
      "learning_rate": 3.287913719495136e-06,
      "loss": 0.4826,
      "step": 47830
    },
    {
      "epoch": 1.469326943753264,
      "grad_norm": 0.4556289613246918,
      "learning_rate": 3.287555489070979e-06,
      "loss": 0.4591,
      "step": 47831
    },
    {
      "epoch": 1.469357662888213,
      "grad_norm": 0.4605649709701538,
      "learning_rate": 3.2871972743242096e-06,
      "loss": 0.5011,
      "step": 47832
    },
    {
      "epoch": 1.4693883820231624,
      "grad_norm": 0.40871158242225647,
      "learning_rate": 3.2868390752556557e-06,
      "loss": 0.4058,
      "step": 47833
    },
    {
      "epoch": 1.4694191011581115,
      "grad_norm": 0.43082141876220703,
      "learning_rate": 3.2864808918661586e-06,
      "loss": 0.4625,
      "step": 47834
    },
    {
      "epoch": 1.4694498202930606,
      "grad_norm": 0.4470224380493164,
      "learning_rate": 3.286122724156553e-06,
      "loss": 0.4547,
      "step": 47835
    },
    {
      "epoch": 1.4694805394280097,
      "grad_norm": 0.48210644721984863,
      "learning_rate": 3.285764572127681e-06,
      "loss": 0.4793,
      "step": 47836
    },
    {
      "epoch": 1.4695112585629588,
      "grad_norm": 0.3969463109970093,
      "learning_rate": 3.2854064357803715e-06,
      "loss": 0.4784,
      "step": 47837
    },
    {
      "epoch": 1.469541977697908,
      "grad_norm": 0.4056059420108795,
      "learning_rate": 3.2850483151154645e-06,
      "loss": 0.446,
      "step": 47838
    },
    {
      "epoch": 1.469572696832857,
      "grad_norm": 0.4202505350112915,
      "learning_rate": 3.284690210133795e-06,
      "loss": 0.4576,
      "step": 47839
    },
    {
      "epoch": 1.4696034159678064,
      "grad_norm": 0.4450020492076874,
      "learning_rate": 3.2843321208362046e-06,
      "loss": 0.4688,
      "step": 47840
    },
    {
      "epoch": 1.4696341351027555,
      "grad_norm": 0.4448511302471161,
      "learning_rate": 3.2839740472235216e-06,
      "loss": 0.498,
      "step": 47841
    },
    {
      "epoch": 1.4696648542377047,
      "grad_norm": 0.39808422327041626,
      "learning_rate": 3.283615989296587e-06,
      "loss": 0.5018,
      "step": 47842
    },
    {
      "epoch": 1.4696955733726538,
      "grad_norm": 0.44065093994140625,
      "learning_rate": 3.2832579470562366e-06,
      "loss": 0.4459,
      "step": 47843
    },
    {
      "epoch": 1.4697262925076031,
      "grad_norm": 0.44831138849258423,
      "learning_rate": 3.2828999205033054e-06,
      "loss": 0.5143,
      "step": 47844
    },
    {
      "epoch": 1.4697570116425522,
      "grad_norm": 0.43951496481895447,
      "learning_rate": 3.2825419096386334e-06,
      "loss": 0.4819,
      "step": 47845
    },
    {
      "epoch": 1.4697877307775014,
      "grad_norm": 0.4474225342273712,
      "learning_rate": 3.2821839144630517e-06,
      "loss": 0.4428,
      "step": 47846
    },
    {
      "epoch": 1.4698184499124505,
      "grad_norm": 0.452424556016922,
      "learning_rate": 3.2818259349773984e-06,
      "loss": 0.4581,
      "step": 47847
    },
    {
      "epoch": 1.4698491690473996,
      "grad_norm": 0.5215223431587219,
      "learning_rate": 3.2814679711825104e-06,
      "loss": 0.4859,
      "step": 47848
    },
    {
      "epoch": 1.4698798881823487,
      "grad_norm": 0.39822837710380554,
      "learning_rate": 3.281110023079226e-06,
      "loss": 0.5071,
      "step": 47849
    },
    {
      "epoch": 1.4699106073172978,
      "grad_norm": 0.39692580699920654,
      "learning_rate": 3.2807520906683743e-06,
      "loss": 0.448,
      "step": 47850
    },
    {
      "epoch": 1.4699413264522472,
      "grad_norm": 0.42044559121131897,
      "learning_rate": 3.280394173950796e-06,
      "loss": 0.4883,
      "step": 47851
    },
    {
      "epoch": 1.4699720455871963,
      "grad_norm": 0.4195040464401245,
      "learning_rate": 3.280036272927326e-06,
      "loss": 0.4381,
      "step": 47852
    },
    {
      "epoch": 1.4700027647221454,
      "grad_norm": 0.4448976218700409,
      "learning_rate": 3.2796783875988046e-06,
      "loss": 0.5047,
      "step": 47853
    },
    {
      "epoch": 1.4700334838570945,
      "grad_norm": 0.41211438179016113,
      "learning_rate": 3.2793205179660604e-06,
      "loss": 0.488,
      "step": 47854
    },
    {
      "epoch": 1.4700642029920439,
      "grad_norm": 0.41939470171928406,
      "learning_rate": 3.2789626640299354e-06,
      "loss": 0.5129,
      "step": 47855
    },
    {
      "epoch": 1.470094922126993,
      "grad_norm": 0.4228290021419525,
      "learning_rate": 3.278604825791256e-06,
      "loss": 0.4098,
      "step": 47856
    },
    {
      "epoch": 1.4701256412619421,
      "grad_norm": 0.4426538944244385,
      "learning_rate": 3.2782470032508706e-06,
      "loss": 0.5423,
      "step": 47857
    },
    {
      "epoch": 1.4701563603968912,
      "grad_norm": 0.4017394185066223,
      "learning_rate": 3.277889196409606e-06,
      "loss": 0.5277,
      "step": 47858
    },
    {
      "epoch": 1.4701870795318404,
      "grad_norm": 0.41932031512260437,
      "learning_rate": 3.277531405268304e-06,
      "loss": 0.4345,
      "step": 47859
    },
    {
      "epoch": 1.4702177986667895,
      "grad_norm": 0.42274031043052673,
      "learning_rate": 3.2771736298277935e-06,
      "loss": 0.4736,
      "step": 47860
    },
    {
      "epoch": 1.4702485178017386,
      "grad_norm": 0.41730213165283203,
      "learning_rate": 3.2768158700889095e-06,
      "loss": 0.4103,
      "step": 47861
    },
    {
      "epoch": 1.470279236936688,
      "grad_norm": 0.4452076256275177,
      "learning_rate": 3.2764581260524998e-06,
      "loss": 0.4424,
      "step": 47862
    },
    {
      "epoch": 1.470309956071637,
      "grad_norm": 0.4450559616088867,
      "learning_rate": 3.276100397719387e-06,
      "loss": 0.3887,
      "step": 47863
    },
    {
      "epoch": 1.4703406752065862,
      "grad_norm": 0.4279603958129883,
      "learning_rate": 3.2757426850904152e-06,
      "loss": 0.4772,
      "step": 47864
    },
    {
      "epoch": 1.4703713943415353,
      "grad_norm": 0.4436034560203552,
      "learning_rate": 3.275384988166409e-06,
      "loss": 0.5443,
      "step": 47865
    },
    {
      "epoch": 1.4704021134764846,
      "grad_norm": 0.425985723733902,
      "learning_rate": 3.2750273069482175e-06,
      "loss": 0.3924,
      "step": 47866
    },
    {
      "epoch": 1.4704328326114338,
      "grad_norm": 0.3942869305610657,
      "learning_rate": 3.2746696414366663e-06,
      "loss": 0.4445,
      "step": 47867
    },
    {
      "epoch": 1.4704635517463829,
      "grad_norm": 0.41830599308013916,
      "learning_rate": 3.2743119916325974e-06,
      "loss": 0.4597,
      "step": 47868
    },
    {
      "epoch": 1.470494270881332,
      "grad_norm": 0.4886345863342285,
      "learning_rate": 3.2739543575368383e-06,
      "loss": 0.4701,
      "step": 47869
    },
    {
      "epoch": 1.4705249900162811,
      "grad_norm": 0.4400396943092346,
      "learning_rate": 3.2735967391502298e-06,
      "loss": 0.4518,
      "step": 47870
    },
    {
      "epoch": 1.4705557091512302,
      "grad_norm": 0.42233192920684814,
      "learning_rate": 3.273239136473605e-06,
      "loss": 0.4734,
      "step": 47871
    },
    {
      "epoch": 1.4705864282861794,
      "grad_norm": 0.4307481050491333,
      "learning_rate": 3.272881549507804e-06,
      "loss": 0.4974,
      "step": 47872
    },
    {
      "epoch": 1.4706171474211287,
      "grad_norm": 0.4314122498035431,
      "learning_rate": 3.2725239782536533e-06,
      "loss": 0.3868,
      "step": 47873
    },
    {
      "epoch": 1.4706478665560778,
      "grad_norm": 0.4225219190120697,
      "learning_rate": 3.2721664227119945e-06,
      "loss": 0.5113,
      "step": 47874
    },
    {
      "epoch": 1.470678585691027,
      "grad_norm": 0.4171265661716461,
      "learning_rate": 3.271808882883659e-06,
      "loss": 0.4701,
      "step": 47875
    },
    {
      "epoch": 1.470709304825976,
      "grad_norm": 0.44059380888938904,
      "learning_rate": 3.2714513587694887e-06,
      "loss": 0.4642,
      "step": 47876
    },
    {
      "epoch": 1.4707400239609252,
      "grad_norm": 0.3995656371116638,
      "learning_rate": 3.2710938503703095e-06,
      "loss": 0.4983,
      "step": 47877
    },
    {
      "epoch": 1.4707707430958745,
      "grad_norm": 0.4389261305332184,
      "learning_rate": 3.2707363576869598e-06,
      "loss": 0.473,
      "step": 47878
    },
    {
      "epoch": 1.4708014622308236,
      "grad_norm": 0.41722238063812256,
      "learning_rate": 3.2703788807202763e-06,
      "loss": 0.465,
      "step": 47879
    },
    {
      "epoch": 1.4708321813657728,
      "grad_norm": 0.4316291809082031,
      "learning_rate": 3.2700214194710934e-06,
      "loss": 0.5082,
      "step": 47880
    },
    {
      "epoch": 1.4708629005007219,
      "grad_norm": 0.5095438957214355,
      "learning_rate": 3.269663973940248e-06,
      "loss": 0.4903,
      "step": 47881
    },
    {
      "epoch": 1.470893619635671,
      "grad_norm": 0.42898476123809814,
      "learning_rate": 3.2693065441285696e-06,
      "loss": 0.48,
      "step": 47882
    },
    {
      "epoch": 1.4709243387706201,
      "grad_norm": 0.4230990409851074,
      "learning_rate": 3.2689491300368958e-06,
      "loss": 0.5181,
      "step": 47883
    },
    {
      "epoch": 1.4709550579055692,
      "grad_norm": 0.39313948154449463,
      "learning_rate": 3.268591731666061e-06,
      "loss": 0.4895,
      "step": 47884
    },
    {
      "epoch": 1.4709857770405186,
      "grad_norm": 0.5911035537719727,
      "learning_rate": 3.2682343490169033e-06,
      "loss": 0.4759,
      "step": 47885
    },
    {
      "epoch": 1.4710164961754677,
      "grad_norm": 0.4095684289932251,
      "learning_rate": 3.2678769820902524e-06,
      "loss": 0.4751,
      "step": 47886
    },
    {
      "epoch": 1.4710472153104168,
      "grad_norm": 0.43816593289375305,
      "learning_rate": 3.2675196308869438e-06,
      "loss": 0.4471,
      "step": 47887
    },
    {
      "epoch": 1.471077934445366,
      "grad_norm": 0.41604503989219666,
      "learning_rate": 3.267162295407814e-06,
      "loss": 0.4278,
      "step": 47888
    },
    {
      "epoch": 1.4711086535803153,
      "grad_norm": 0.42134639620780945,
      "learning_rate": 3.266804975653699e-06,
      "loss": 0.4602,
      "step": 47889
    },
    {
      "epoch": 1.4711393727152644,
      "grad_norm": 0.41082921624183655,
      "learning_rate": 3.266447671625429e-06,
      "loss": 0.5308,
      "step": 47890
    },
    {
      "epoch": 1.4711700918502135,
      "grad_norm": 0.45464229583740234,
      "learning_rate": 3.2660903833238443e-06,
      "loss": 0.4787,
      "step": 47891
    },
    {
      "epoch": 1.4712008109851626,
      "grad_norm": 0.4370565414428711,
      "learning_rate": 3.265733110749768e-06,
      "loss": 0.4413,
      "step": 47892
    },
    {
      "epoch": 1.4712315301201118,
      "grad_norm": 0.4189539849758148,
      "learning_rate": 3.26537585390405e-06,
      "loss": 0.5142,
      "step": 47893
    },
    {
      "epoch": 1.4712622492550609,
      "grad_norm": 0.45222365856170654,
      "learning_rate": 3.265018612787514e-06,
      "loss": 0.5073,
      "step": 47894
    },
    {
      "epoch": 1.47129296839001,
      "grad_norm": 0.4276762008666992,
      "learning_rate": 3.264661387400999e-06,
      "loss": 0.4762,
      "step": 47895
    },
    {
      "epoch": 1.4713236875249593,
      "grad_norm": 0.4524816572666168,
      "learning_rate": 3.2643041777453365e-06,
      "loss": 0.4324,
      "step": 47896
    },
    {
      "epoch": 1.4713544066599085,
      "grad_norm": 0.4218742251396179,
      "learning_rate": 3.263946983821361e-06,
      "loss": 0.4467,
      "step": 47897
    },
    {
      "epoch": 1.4713851257948576,
      "grad_norm": 0.4677139222621918,
      "learning_rate": 3.2635898056299076e-06,
      "loss": 0.43,
      "step": 47898
    },
    {
      "epoch": 1.4714158449298067,
      "grad_norm": 0.45766663551330566,
      "learning_rate": 3.2632326431718108e-06,
      "loss": 0.4713,
      "step": 47899
    },
    {
      "epoch": 1.471446564064756,
      "grad_norm": 0.4012690782546997,
      "learning_rate": 3.2628754964479082e-06,
      "loss": 0.4361,
      "step": 47900
    },
    {
      "epoch": 1.4714772831997052,
      "grad_norm": 0.42240121960639954,
      "learning_rate": 3.2625183654590263e-06,
      "loss": 0.3883,
      "step": 47901
    },
    {
      "epoch": 1.4715080023346543,
      "grad_norm": 0.4333382248878479,
      "learning_rate": 3.262161250206004e-06,
      "loss": 0.4282,
      "step": 47902
    },
    {
      "epoch": 1.4715387214696034,
      "grad_norm": 0.43588975071907043,
      "learning_rate": 3.261804150689675e-06,
      "loss": 0.5461,
      "step": 47903
    },
    {
      "epoch": 1.4715694406045525,
      "grad_norm": 0.40959420800209045,
      "learning_rate": 3.2614470669108756e-06,
      "loss": 0.4693,
      "step": 47904
    },
    {
      "epoch": 1.4716001597395016,
      "grad_norm": 0.43182459473609924,
      "learning_rate": 3.261089998870434e-06,
      "loss": 0.4789,
      "step": 47905
    },
    {
      "epoch": 1.4716308788744508,
      "grad_norm": 0.3987261652946472,
      "learning_rate": 3.2607329465691873e-06,
      "loss": 0.5201,
      "step": 47906
    },
    {
      "epoch": 1.4716615980094,
      "grad_norm": 0.45978134870529175,
      "learning_rate": 3.26037591000797e-06,
      "loss": 0.4477,
      "step": 47907
    },
    {
      "epoch": 1.4716923171443492,
      "grad_norm": 0.4250304102897644,
      "learning_rate": 3.260018889187618e-06,
      "loss": 0.424,
      "step": 47908
    },
    {
      "epoch": 1.4717230362792983,
      "grad_norm": 0.49128416180610657,
      "learning_rate": 3.25966188410896e-06,
      "loss": 0.4442,
      "step": 47909
    },
    {
      "epoch": 1.4717537554142475,
      "grad_norm": 0.43950942158699036,
      "learning_rate": 3.2593048947728325e-06,
      "loss": 0.4494,
      "step": 47910
    },
    {
      "epoch": 1.4717844745491968,
      "grad_norm": 0.41876670718193054,
      "learning_rate": 3.258947921180069e-06,
      "loss": 0.4728,
      "step": 47911
    },
    {
      "epoch": 1.471815193684146,
      "grad_norm": 0.4046092927455902,
      "learning_rate": 3.258590963331506e-06,
      "loss": 0.4128,
      "step": 47912
    },
    {
      "epoch": 1.471845912819095,
      "grad_norm": 0.4589827358722687,
      "learning_rate": 3.2582340212279718e-06,
      "loss": 0.4933,
      "step": 47913
    },
    {
      "epoch": 1.4718766319540442,
      "grad_norm": 0.41242021322250366,
      "learning_rate": 3.257877094870303e-06,
      "loss": 0.466,
      "step": 47914
    },
    {
      "epoch": 1.4719073510889933,
      "grad_norm": 0.4344860315322876,
      "learning_rate": 3.257520184259333e-06,
      "loss": 0.5059,
      "step": 47915
    },
    {
      "epoch": 1.4719380702239424,
      "grad_norm": 0.42345887422561646,
      "learning_rate": 3.257163289395896e-06,
      "loss": 0.4966,
      "step": 47916
    },
    {
      "epoch": 1.4719687893588915,
      "grad_norm": 0.4700463116168976,
      "learning_rate": 3.256806410280827e-06,
      "loss": 0.4184,
      "step": 47917
    },
    {
      "epoch": 1.4719995084938409,
      "grad_norm": 0.41592302918434143,
      "learning_rate": 3.256449546914956e-06,
      "loss": 0.4726,
      "step": 47918
    },
    {
      "epoch": 1.47203022762879,
      "grad_norm": 0.4196271002292633,
      "learning_rate": 3.256092699299117e-06,
      "loss": 0.4202,
      "step": 47919
    },
    {
      "epoch": 1.472060946763739,
      "grad_norm": 0.4125458300113678,
      "learning_rate": 3.2557358674341444e-06,
      "loss": 0.4572,
      "step": 47920
    },
    {
      "epoch": 1.4720916658986882,
      "grad_norm": 0.4290781617164612,
      "learning_rate": 3.255379051320875e-06,
      "loss": 0.5238,
      "step": 47921
    },
    {
      "epoch": 1.4721223850336376,
      "grad_norm": 0.4333447515964508,
      "learning_rate": 3.2550222509601358e-06,
      "loss": 0.4173,
      "step": 47922
    },
    {
      "epoch": 1.4721531041685867,
      "grad_norm": 0.4205346405506134,
      "learning_rate": 3.2546654663527666e-06,
      "loss": 0.5393,
      "step": 47923
    },
    {
      "epoch": 1.4721838233035358,
      "grad_norm": 0.5912960767745972,
      "learning_rate": 3.2543086974995906e-06,
      "loss": 0.4555,
      "step": 47924
    },
    {
      "epoch": 1.472214542438485,
      "grad_norm": 0.4083026647567749,
      "learning_rate": 3.2539519444014545e-06,
      "loss": 0.4354,
      "step": 47925
    },
    {
      "epoch": 1.472245261573434,
      "grad_norm": 0.4200648367404938,
      "learning_rate": 3.2535952070591815e-06,
      "loss": 0.4031,
      "step": 47926
    },
    {
      "epoch": 1.4722759807083832,
      "grad_norm": 0.4057566821575165,
      "learning_rate": 3.253238485473611e-06,
      "loss": 0.4567,
      "step": 47927
    },
    {
      "epoch": 1.4723066998433323,
      "grad_norm": 0.4104529321193695,
      "learning_rate": 3.252881779645567e-06,
      "loss": 0.5082,
      "step": 47928
    },
    {
      "epoch": 1.4723374189782816,
      "grad_norm": 0.41608840227127075,
      "learning_rate": 3.252525089575895e-06,
      "loss": 0.4106,
      "step": 47929
    },
    {
      "epoch": 1.4723681381132308,
      "grad_norm": 0.40374547243118286,
      "learning_rate": 3.252168415265419e-06,
      "loss": 0.4402,
      "step": 47930
    },
    {
      "epoch": 1.4723988572481799,
      "grad_norm": 0.4113905429840088,
      "learning_rate": 3.2518117567149786e-06,
      "loss": 0.473,
      "step": 47931
    },
    {
      "epoch": 1.472429576383129,
      "grad_norm": 0.43783047795295715,
      "learning_rate": 3.251455113925399e-06,
      "loss": 0.4656,
      "step": 47932
    },
    {
      "epoch": 1.4724602955180783,
      "grad_norm": 0.43319371342658997,
      "learning_rate": 3.251098486897517e-06,
      "loss": 0.441,
      "step": 47933
    },
    {
      "epoch": 1.4724910146530275,
      "grad_norm": 0.4125826358795166,
      "learning_rate": 3.2507418756321674e-06,
      "loss": 0.5253,
      "step": 47934
    },
    {
      "epoch": 1.4725217337879766,
      "grad_norm": 0.3967810571193695,
      "learning_rate": 3.2503852801301807e-06,
      "loss": 0.4354,
      "step": 47935
    },
    {
      "epoch": 1.4725524529229257,
      "grad_norm": 0.42473649978637695,
      "learning_rate": 3.2500287003923937e-06,
      "loss": 0.4391,
      "step": 47936
    },
    {
      "epoch": 1.4725831720578748,
      "grad_norm": 0.3976562023162842,
      "learning_rate": 3.2496721364196325e-06,
      "loss": 0.4458,
      "step": 47937
    },
    {
      "epoch": 1.472613891192824,
      "grad_norm": 0.40673553943634033,
      "learning_rate": 3.2493155882127338e-06,
      "loss": 0.4813,
      "step": 47938
    },
    {
      "epoch": 1.472644610327773,
      "grad_norm": 0.3973483443260193,
      "learning_rate": 3.248959055772529e-06,
      "loss": 0.5097,
      "step": 47939
    },
    {
      "epoch": 1.4726753294627224,
      "grad_norm": 0.43795740604400635,
      "learning_rate": 3.2486025390998564e-06,
      "loss": 0.4917,
      "step": 47940
    },
    {
      "epoch": 1.4727060485976715,
      "grad_norm": 0.46381649374961853,
      "learning_rate": 3.2482460381955405e-06,
      "loss": 0.465,
      "step": 47941
    },
    {
      "epoch": 1.4727367677326206,
      "grad_norm": 0.39126595854759216,
      "learning_rate": 3.247889553060417e-06,
      "loss": 0.4733,
      "step": 47942
    },
    {
      "epoch": 1.4727674868675698,
      "grad_norm": 0.3905464708805084,
      "learning_rate": 3.24753308369532e-06,
      "loss": 0.459,
      "step": 47943
    },
    {
      "epoch": 1.472798206002519,
      "grad_norm": 0.4067867696285248,
      "learning_rate": 3.2471766301010842e-06,
      "loss": 0.4809,
      "step": 47944
    },
    {
      "epoch": 1.4728289251374682,
      "grad_norm": 0.405046671628952,
      "learning_rate": 3.246820192278535e-06,
      "loss": 0.5122,
      "step": 47945
    },
    {
      "epoch": 1.4728596442724173,
      "grad_norm": 0.43536457419395447,
      "learning_rate": 3.2464637702285094e-06,
      "loss": 0.4831,
      "step": 47946
    },
    {
      "epoch": 1.4728903634073665,
      "grad_norm": 0.4368223249912262,
      "learning_rate": 3.246107363951839e-06,
      "loss": 0.467,
      "step": 47947
    },
    {
      "epoch": 1.4729210825423156,
      "grad_norm": 0.4769000709056854,
      "learning_rate": 3.2457509734493597e-06,
      "loss": 0.4491,
      "step": 47948
    },
    {
      "epoch": 1.4729518016772647,
      "grad_norm": 0.427483469247818,
      "learning_rate": 3.245394598721898e-06,
      "loss": 0.4741,
      "step": 47949
    },
    {
      "epoch": 1.4729825208122138,
      "grad_norm": 0.439275860786438,
      "learning_rate": 3.2450382397702885e-06,
      "loss": 0.4635,
      "step": 47950
    },
    {
      "epoch": 1.4730132399471632,
      "grad_norm": 0.4548875689506531,
      "learning_rate": 3.2446818965953642e-06,
      "loss": 0.4711,
      "step": 47951
    },
    {
      "epoch": 1.4730439590821123,
      "grad_norm": 0.4115365147590637,
      "learning_rate": 3.2443255691979604e-06,
      "loss": 0.4455,
      "step": 47952
    },
    {
      "epoch": 1.4730746782170614,
      "grad_norm": 0.3995850086212158,
      "learning_rate": 3.243969257578903e-06,
      "loss": 0.4333,
      "step": 47953
    },
    {
      "epoch": 1.4731053973520105,
      "grad_norm": 0.42265114188194275,
      "learning_rate": 3.2436129617390266e-06,
      "loss": 0.4689,
      "step": 47954
    },
    {
      "epoch": 1.4731361164869599,
      "grad_norm": 0.3911438584327698,
      "learning_rate": 3.2432566816791644e-06,
      "loss": 0.419,
      "step": 47955
    },
    {
      "epoch": 1.473166835621909,
      "grad_norm": 0.39278197288513184,
      "learning_rate": 3.2429004174001477e-06,
      "loss": 0.4078,
      "step": 47956
    },
    {
      "epoch": 1.473197554756858,
      "grad_norm": 0.451322078704834,
      "learning_rate": 3.2425441689028126e-06,
      "loss": 0.5335,
      "step": 47957
    },
    {
      "epoch": 1.4732282738918072,
      "grad_norm": 2.0091171264648438,
      "learning_rate": 3.2421879361879836e-06,
      "loss": 0.3609,
      "step": 47958
    },
    {
      "epoch": 1.4732589930267563,
      "grad_norm": 0.37763166427612305,
      "learning_rate": 3.2418317192565006e-06,
      "loss": 0.4792,
      "step": 47959
    },
    {
      "epoch": 1.4732897121617055,
      "grad_norm": 0.41705408692359924,
      "learning_rate": 3.2414755181091852e-06,
      "loss": 0.4645,
      "step": 47960
    },
    {
      "epoch": 1.4733204312966546,
      "grad_norm": 0.44524914026260376,
      "learning_rate": 3.2411193327468815e-06,
      "loss": 0.5231,
      "step": 47961
    },
    {
      "epoch": 1.473351150431604,
      "grad_norm": 0.44816988706588745,
      "learning_rate": 3.2407631631704127e-06,
      "loss": 0.4243,
      "step": 47962
    },
    {
      "epoch": 1.473381869566553,
      "grad_norm": 0.45683014392852783,
      "learning_rate": 3.240407009380617e-06,
      "loss": 0.446,
      "step": 47963
    },
    {
      "epoch": 1.4734125887015022,
      "grad_norm": 0.4242606461048126,
      "learning_rate": 3.240050871378321e-06,
      "loss": 0.4933,
      "step": 47964
    },
    {
      "epoch": 1.4734433078364513,
      "grad_norm": 0.4214499294757843,
      "learning_rate": 3.239694749164356e-06,
      "loss": 0.4505,
      "step": 47965
    },
    {
      "epoch": 1.4734740269714006,
      "grad_norm": 0.4260452091693878,
      "learning_rate": 3.2393386427395566e-06,
      "loss": 0.4851,
      "step": 47966
    },
    {
      "epoch": 1.4735047461063497,
      "grad_norm": 0.42097702622413635,
      "learning_rate": 3.238982552104758e-06,
      "loss": 0.5041,
      "step": 47967
    },
    {
      "epoch": 1.4735354652412989,
      "grad_norm": 0.4380802810192108,
      "learning_rate": 3.2386264772607845e-06,
      "loss": 0.4848,
      "step": 47968
    },
    {
      "epoch": 1.473566184376248,
      "grad_norm": 0.41164761781692505,
      "learning_rate": 3.23827041820847e-06,
      "loss": 0.4117,
      "step": 47969
    },
    {
      "epoch": 1.473596903511197,
      "grad_norm": 0.42588499188423157,
      "learning_rate": 3.2379143749486487e-06,
      "loss": 0.5021,
      "step": 47970
    },
    {
      "epoch": 1.4736276226461462,
      "grad_norm": 0.4214984178543091,
      "learning_rate": 3.2375583474821493e-06,
      "loss": 0.3867,
      "step": 47971
    },
    {
      "epoch": 1.4736583417810953,
      "grad_norm": 0.4821551442146301,
      "learning_rate": 3.2372023358098095e-06,
      "loss": 0.4405,
      "step": 47972
    },
    {
      "epoch": 1.4736890609160447,
      "grad_norm": 0.38124457001686096,
      "learning_rate": 3.2368463399324513e-06,
      "loss": 0.4298,
      "step": 47973
    },
    {
      "epoch": 1.4737197800509938,
      "grad_norm": 0.4252782166004181,
      "learning_rate": 3.2364903598509112e-06,
      "loss": 0.4038,
      "step": 47974
    },
    {
      "epoch": 1.473750499185943,
      "grad_norm": 0.40256866812705994,
      "learning_rate": 3.2361343955660198e-06,
      "loss": 0.4389,
      "step": 47975
    },
    {
      "epoch": 1.473781218320892,
      "grad_norm": 0.428345263004303,
      "learning_rate": 3.2357784470786126e-06,
      "loss": 0.4091,
      "step": 47976
    },
    {
      "epoch": 1.4738119374558414,
      "grad_norm": 0.3972541391849518,
      "learning_rate": 3.2354225143895133e-06,
      "loss": 0.4712,
      "step": 47977
    },
    {
      "epoch": 1.4738426565907905,
      "grad_norm": 0.39342278242111206,
      "learning_rate": 3.2350665974995576e-06,
      "loss": 0.4463,
      "step": 47978
    },
    {
      "epoch": 1.4738733757257396,
      "grad_norm": 0.47129303216934204,
      "learning_rate": 3.2347106964095777e-06,
      "loss": 0.4607,
      "step": 47979
    },
    {
      "epoch": 1.4739040948606887,
      "grad_norm": 0.4067539870738983,
      "learning_rate": 3.234354811120405e-06,
      "loss": 0.4474,
      "step": 47980
    },
    {
      "epoch": 1.4739348139956379,
      "grad_norm": 0.5044997930526733,
      "learning_rate": 3.2339989416328663e-06,
      "loss": 0.5087,
      "step": 47981
    },
    {
      "epoch": 1.473965533130587,
      "grad_norm": 0.4356735944747925,
      "learning_rate": 3.2336430879477955e-06,
      "loss": 0.485,
      "step": 47982
    },
    {
      "epoch": 1.473996252265536,
      "grad_norm": 3.5290615558624268,
      "learning_rate": 3.233287250066024e-06,
      "loss": 0.4102,
      "step": 47983
    },
    {
      "epoch": 1.4740269714004854,
      "grad_norm": 0.4206245541572571,
      "learning_rate": 3.232931427988386e-06,
      "loss": 0.4499,
      "step": 47984
    },
    {
      "epoch": 1.4740576905354346,
      "grad_norm": 0.38831162452697754,
      "learning_rate": 3.2325756217157057e-06,
      "loss": 0.4538,
      "step": 47985
    },
    {
      "epoch": 1.4740884096703837,
      "grad_norm": 0.4035382866859436,
      "learning_rate": 3.2322198312488216e-06,
      "loss": 0.4816,
      "step": 47986
    },
    {
      "epoch": 1.4741191288053328,
      "grad_norm": 0.42640215158462524,
      "learning_rate": 3.231864056588554e-06,
      "loss": 0.4801,
      "step": 47987
    },
    {
      "epoch": 1.474149847940282,
      "grad_norm": 0.4416153132915497,
      "learning_rate": 3.231508297735747e-06,
      "loss": 0.4592,
      "step": 47988
    },
    {
      "epoch": 1.4741805670752313,
      "grad_norm": 0.43690648674964905,
      "learning_rate": 3.2311525546912214e-06,
      "loss": 0.5068,
      "step": 47989
    },
    {
      "epoch": 1.4742112862101804,
      "grad_norm": 0.41739973425865173,
      "learning_rate": 3.2307968274558122e-06,
      "loss": 0.4142,
      "step": 47990
    },
    {
      "epoch": 1.4742420053451295,
      "grad_norm": 0.44156888127326965,
      "learning_rate": 3.2304411160303493e-06,
      "loss": 0.4171,
      "step": 47991
    },
    {
      "epoch": 1.4742727244800786,
      "grad_norm": 0.4094967842102051,
      "learning_rate": 3.230085420415665e-06,
      "loss": 0.4826,
      "step": 47992
    },
    {
      "epoch": 1.4743034436150277,
      "grad_norm": 0.5187434554100037,
      "learning_rate": 3.2297297406125917e-06,
      "loss": 0.4572,
      "step": 47993
    },
    {
      "epoch": 1.4743341627499769,
      "grad_norm": 0.4074093997478485,
      "learning_rate": 3.2293740766219538e-06,
      "loss": 0.4895,
      "step": 47994
    },
    {
      "epoch": 1.474364881884926,
      "grad_norm": 0.441455602645874,
      "learning_rate": 3.2290184284445892e-06,
      "loss": 0.5029,
      "step": 47995
    },
    {
      "epoch": 1.4743956010198753,
      "grad_norm": 0.41635215282440186,
      "learning_rate": 3.2286627960813175e-06,
      "loss": 0.4992,
      "step": 47996
    },
    {
      "epoch": 1.4744263201548244,
      "grad_norm": 0.4161434471607208,
      "learning_rate": 3.2283071795329844e-06,
      "loss": 0.4051,
      "step": 47997
    },
    {
      "epoch": 1.4744570392897736,
      "grad_norm": 0.44223514199256897,
      "learning_rate": 3.227951578800409e-06,
      "loss": 0.4625,
      "step": 47998
    },
    {
      "epoch": 1.4744877584247227,
      "grad_norm": 0.4367869794368744,
      "learning_rate": 3.2275959938844294e-06,
      "loss": 0.501,
      "step": 47999
    },
    {
      "epoch": 1.474518477559672,
      "grad_norm": 0.5145500302314758,
      "learning_rate": 3.227240424785869e-06,
      "loss": 0.4253,
      "step": 48000
    },
    {
      "epoch": 1.4745491966946211,
      "grad_norm": 0.5104518532752991,
      "learning_rate": 3.226884871505561e-06,
      "loss": 0.4467,
      "step": 48001
    },
    {
      "epoch": 1.4745799158295703,
      "grad_norm": 0.4802406430244446,
      "learning_rate": 3.226529334044337e-06,
      "loss": 0.5026,
      "step": 48002
    },
    {
      "epoch": 1.4746106349645194,
      "grad_norm": 0.46030279994010925,
      "learning_rate": 3.2261738124030297e-06,
      "loss": 0.4899,
      "step": 48003
    },
    {
      "epoch": 1.4746413540994685,
      "grad_norm": 0.44693487882614136,
      "learning_rate": 3.2258183065824633e-06,
      "loss": 0.4408,
      "step": 48004
    },
    {
      "epoch": 1.4746720732344176,
      "grad_norm": 0.45600879192352295,
      "learning_rate": 3.2254628165834724e-06,
      "loss": 0.4266,
      "step": 48005
    },
    {
      "epoch": 1.4747027923693667,
      "grad_norm": 0.4194144308567047,
      "learning_rate": 3.2251073424068846e-06,
      "loss": 0.4666,
      "step": 48006
    },
    {
      "epoch": 1.474733511504316,
      "grad_norm": 0.4229283332824707,
      "learning_rate": 3.224751884053533e-06,
      "loss": 0.4381,
      "step": 48007
    },
    {
      "epoch": 1.4747642306392652,
      "grad_norm": 0.38253509998321533,
      "learning_rate": 3.224396441524249e-06,
      "loss": 0.4782,
      "step": 48008
    },
    {
      "epoch": 1.4747949497742143,
      "grad_norm": 0.40768110752105713,
      "learning_rate": 3.2240410148198575e-06,
      "loss": 0.4509,
      "step": 48009
    },
    {
      "epoch": 1.4748256689091634,
      "grad_norm": 0.40417423844337463,
      "learning_rate": 3.2236856039411914e-06,
      "loss": 0.5112,
      "step": 48010
    },
    {
      "epoch": 1.4748563880441128,
      "grad_norm": 0.3947696089744568,
      "learning_rate": 3.2233302088890805e-06,
      "loss": 0.397,
      "step": 48011
    },
    {
      "epoch": 1.474887107179062,
      "grad_norm": 0.40778636932373047,
      "learning_rate": 3.222974829664358e-06,
      "loss": 0.4734,
      "step": 48012
    },
    {
      "epoch": 1.474917826314011,
      "grad_norm": 0.44678840041160583,
      "learning_rate": 3.222619466267849e-06,
      "loss": 0.5037,
      "step": 48013
    },
    {
      "epoch": 1.4749485454489601,
      "grad_norm": 0.397383451461792,
      "learning_rate": 3.2222641187003846e-06,
      "loss": 0.4403,
      "step": 48014
    },
    {
      "epoch": 1.4749792645839093,
      "grad_norm": 0.463449090719223,
      "learning_rate": 3.2219087869627964e-06,
      "loss": 0.4919,
      "step": 48015
    },
    {
      "epoch": 1.4750099837188584,
      "grad_norm": 0.4431757628917694,
      "learning_rate": 3.221553471055917e-06,
      "loss": 0.4734,
      "step": 48016
    },
    {
      "epoch": 1.4750407028538075,
      "grad_norm": 0.4542787969112396,
      "learning_rate": 3.2211981709805682e-06,
      "loss": 0.4793,
      "step": 48017
    },
    {
      "epoch": 1.4750714219887568,
      "grad_norm": 0.4716103672981262,
      "learning_rate": 3.220842886737586e-06,
      "loss": 0.5028,
      "step": 48018
    },
    {
      "epoch": 1.475102141123706,
      "grad_norm": 0.423524409532547,
      "learning_rate": 3.2204876183277976e-06,
      "loss": 0.4172,
      "step": 48019
    },
    {
      "epoch": 1.475132860258655,
      "grad_norm": 0.41433852910995483,
      "learning_rate": 3.2201323657520376e-06,
      "loss": 0.542,
      "step": 48020
    },
    {
      "epoch": 1.4751635793936042,
      "grad_norm": 0.5051724314689636,
      "learning_rate": 3.219777129011129e-06,
      "loss": 0.5313,
      "step": 48021
    },
    {
      "epoch": 1.4751942985285535,
      "grad_norm": 0.4192614257335663,
      "learning_rate": 3.2194219081059074e-06,
      "loss": 0.4125,
      "step": 48022
    },
    {
      "epoch": 1.4752250176635027,
      "grad_norm": 0.40504831075668335,
      "learning_rate": 3.2190667030371935e-06,
      "loss": 0.456,
      "step": 48023
    },
    {
      "epoch": 1.4752557367984518,
      "grad_norm": 0.43976694345474243,
      "learning_rate": 3.218711513805829e-06,
      "loss": 0.4043,
      "step": 48024
    },
    {
      "epoch": 1.475286455933401,
      "grad_norm": 0.39865371584892273,
      "learning_rate": 3.2183563404126338e-06,
      "loss": 0.4358,
      "step": 48025
    },
    {
      "epoch": 1.47531717506835,
      "grad_norm": 0.4326993525028229,
      "learning_rate": 3.2180011828584414e-06,
      "loss": 0.4745,
      "step": 48026
    },
    {
      "epoch": 1.4753478942032991,
      "grad_norm": 0.6182079911231995,
      "learning_rate": 3.2176460411440845e-06,
      "loss": 0.4017,
      "step": 48027
    },
    {
      "epoch": 1.4753786133382483,
      "grad_norm": 0.390789657831192,
      "learning_rate": 3.2172909152703812e-06,
      "loss": 0.5619,
      "step": 48028
    },
    {
      "epoch": 1.4754093324731976,
      "grad_norm": 0.4365951418876648,
      "learning_rate": 3.216935805238176e-06,
      "loss": 0.4316,
      "step": 48029
    },
    {
      "epoch": 1.4754400516081467,
      "grad_norm": 0.43233245611190796,
      "learning_rate": 3.2165807110482883e-06,
      "loss": 0.4135,
      "step": 48030
    },
    {
      "epoch": 1.4754707707430958,
      "grad_norm": 0.4420871138572693,
      "learning_rate": 3.2162256327015517e-06,
      "loss": 0.4813,
      "step": 48031
    },
    {
      "epoch": 1.475501489878045,
      "grad_norm": 0.4338698983192444,
      "learning_rate": 3.215870570198789e-06,
      "loss": 0.3715,
      "step": 48032
    },
    {
      "epoch": 1.4755322090129943,
      "grad_norm": 0.437569797039032,
      "learning_rate": 3.21551552354084e-06,
      "loss": 0.3615,
      "step": 48033
    },
    {
      "epoch": 1.4755629281479434,
      "grad_norm": 0.46485841274261475,
      "learning_rate": 3.215160492728525e-06,
      "loss": 0.507,
      "step": 48034
    },
    {
      "epoch": 1.4755936472828926,
      "grad_norm": 0.45726850628852844,
      "learning_rate": 3.2148054777626803e-06,
      "loss": 0.5127,
      "step": 48035
    },
    {
      "epoch": 1.4756243664178417,
      "grad_norm": 0.3971380889415741,
      "learning_rate": 3.214450478644128e-06,
      "loss": 0.4556,
      "step": 48036
    },
    {
      "epoch": 1.4756550855527908,
      "grad_norm": 0.4153590798377991,
      "learning_rate": 3.2140954953737e-06,
      "loss": 0.4058,
      "step": 48037
    },
    {
      "epoch": 1.47568580468774,
      "grad_norm": 0.6562758088111877,
      "learning_rate": 3.213740527952226e-06,
      "loss": 0.531,
      "step": 48038
    },
    {
      "epoch": 1.475716523822689,
      "grad_norm": 0.3840895891189575,
      "learning_rate": 3.2133855763805387e-06,
      "loss": 0.4084,
      "step": 48039
    },
    {
      "epoch": 1.4757472429576384,
      "grad_norm": 0.43953102827072144,
      "learning_rate": 3.2130306406594602e-06,
      "loss": 0.4255,
      "step": 48040
    },
    {
      "epoch": 1.4757779620925875,
      "grad_norm": 0.4576236307621002,
      "learning_rate": 3.212675720789822e-06,
      "loss": 0.513,
      "step": 48041
    },
    {
      "epoch": 1.4758086812275366,
      "grad_norm": 0.4178257882595062,
      "learning_rate": 3.212320816772454e-06,
      "loss": 0.4997,
      "step": 48042
    },
    {
      "epoch": 1.4758394003624857,
      "grad_norm": 0.449299156665802,
      "learning_rate": 3.2119659286081883e-06,
      "loss": 0.3955,
      "step": 48043
    },
    {
      "epoch": 1.475870119497435,
      "grad_norm": 0.4452144205570221,
      "learning_rate": 3.2116110562978466e-06,
      "loss": 0.5052,
      "step": 48044
    },
    {
      "epoch": 1.4759008386323842,
      "grad_norm": 0.4059138596057892,
      "learning_rate": 3.211256199842261e-06,
      "loss": 0.5,
      "step": 48045
    },
    {
      "epoch": 1.4759315577673333,
      "grad_norm": 0.44243746995925903,
      "learning_rate": 3.210901359242261e-06,
      "loss": 0.4135,
      "step": 48046
    },
    {
      "epoch": 1.4759622769022824,
      "grad_norm": 0.4239775836467743,
      "learning_rate": 3.2105465344986754e-06,
      "loss": 0.4751,
      "step": 48047
    },
    {
      "epoch": 1.4759929960372316,
      "grad_norm": 0.4514758586883545,
      "learning_rate": 3.210191725612335e-06,
      "loss": 0.4437,
      "step": 48048
    },
    {
      "epoch": 1.4760237151721807,
      "grad_norm": 0.4426761269569397,
      "learning_rate": 3.209836932584064e-06,
      "loss": 0.4393,
      "step": 48049
    },
    {
      "epoch": 1.4760544343071298,
      "grad_norm": 0.42661750316619873,
      "learning_rate": 3.2094821554146913e-06,
      "loss": 0.4801,
      "step": 48050
    },
    {
      "epoch": 1.4760851534420791,
      "grad_norm": 0.5359233021736145,
      "learning_rate": 3.209127394105048e-06,
      "loss": 0.5125,
      "step": 48051
    },
    {
      "epoch": 1.4761158725770283,
      "grad_norm": 0.42025479674339294,
      "learning_rate": 3.208772648655967e-06,
      "loss": 0.3898,
      "step": 48052
    },
    {
      "epoch": 1.4761465917119774,
      "grad_norm": 0.5078251957893372,
      "learning_rate": 3.208417919068266e-06,
      "loss": 0.4811,
      "step": 48053
    },
    {
      "epoch": 1.4761773108469265,
      "grad_norm": 0.40483370423316956,
      "learning_rate": 3.2080632053427808e-06,
      "loss": 0.4517,
      "step": 48054
    },
    {
      "epoch": 1.4762080299818758,
      "grad_norm": 0.38032951951026917,
      "learning_rate": 3.207708507480337e-06,
      "loss": 0.4193,
      "step": 48055
    },
    {
      "epoch": 1.476238749116825,
      "grad_norm": 0.42648908495903015,
      "learning_rate": 3.207353825481769e-06,
      "loss": 0.3526,
      "step": 48056
    },
    {
      "epoch": 1.476269468251774,
      "grad_norm": 0.44290274381637573,
      "learning_rate": 3.2069991593478967e-06,
      "loss": 0.5498,
      "step": 48057
    },
    {
      "epoch": 1.4763001873867232,
      "grad_norm": 0.4312364459037781,
      "learning_rate": 3.206644509079555e-06,
      "loss": 0.4963,
      "step": 48058
    },
    {
      "epoch": 1.4763309065216723,
      "grad_norm": 0.441652774810791,
      "learning_rate": 3.206289874677564e-06,
      "loss": 0.4252,
      "step": 48059
    },
    {
      "epoch": 1.4763616256566214,
      "grad_norm": 0.40078291296958923,
      "learning_rate": 3.2059352561427637e-06,
      "loss": 0.4886,
      "step": 48060
    },
    {
      "epoch": 1.4763923447915706,
      "grad_norm": 0.44570305943489075,
      "learning_rate": 3.2055806534759727e-06,
      "loss": 0.4409,
      "step": 48061
    },
    {
      "epoch": 1.47642306392652,
      "grad_norm": 0.40276169776916504,
      "learning_rate": 3.205226066678022e-06,
      "loss": 0.4045,
      "step": 48062
    },
    {
      "epoch": 1.476453783061469,
      "grad_norm": 0.403645783662796,
      "learning_rate": 3.204871495749744e-06,
      "loss": 0.4957,
      "step": 48063
    },
    {
      "epoch": 1.4764845021964181,
      "grad_norm": 0.41939210891723633,
      "learning_rate": 3.2045169406919573e-06,
      "loss": 0.5514,
      "step": 48064
    },
    {
      "epoch": 1.4765152213313673,
      "grad_norm": 0.4165023863315582,
      "learning_rate": 3.2041624015055017e-06,
      "loss": 0.4431,
      "step": 48065
    },
    {
      "epoch": 1.4765459404663166,
      "grad_norm": 0.4471632242202759,
      "learning_rate": 3.2038078781911962e-06,
      "loss": 0.4491,
      "step": 48066
    },
    {
      "epoch": 1.4765766596012657,
      "grad_norm": 0.44478243589401245,
      "learning_rate": 3.203453370749876e-06,
      "loss": 0.465,
      "step": 48067
    },
    {
      "epoch": 1.4766073787362148,
      "grad_norm": 0.4529546797275543,
      "learning_rate": 3.2030988791823604e-06,
      "loss": 0.4844,
      "step": 48068
    },
    {
      "epoch": 1.476638097871164,
      "grad_norm": 0.4191470742225647,
      "learning_rate": 3.202744403489484e-06,
      "loss": 0.4374,
      "step": 48069
    },
    {
      "epoch": 1.476668817006113,
      "grad_norm": 0.49565836787223816,
      "learning_rate": 3.2023899436720708e-06,
      "loss": 0.524,
      "step": 48070
    },
    {
      "epoch": 1.4766995361410622,
      "grad_norm": 0.42472338676452637,
      "learning_rate": 3.2020354997309557e-06,
      "loss": 0.4444,
      "step": 48071
    },
    {
      "epoch": 1.4767302552760113,
      "grad_norm": 0.44431325793266296,
      "learning_rate": 3.2016810716669565e-06,
      "loss": 0.4705,
      "step": 48072
    },
    {
      "epoch": 1.4767609744109607,
      "grad_norm": 0.4011440575122833,
      "learning_rate": 3.2013266594809068e-06,
      "loss": 0.4525,
      "step": 48073
    },
    {
      "epoch": 1.4767916935459098,
      "grad_norm": 0.42827311158180237,
      "learning_rate": 3.200972263173634e-06,
      "loss": 0.4453,
      "step": 48074
    },
    {
      "epoch": 1.476822412680859,
      "grad_norm": 0.6754900813102722,
      "learning_rate": 3.2006178827459677e-06,
      "loss": 0.3706,
      "step": 48075
    },
    {
      "epoch": 1.476853131815808,
      "grad_norm": 0.43393248319625854,
      "learning_rate": 3.2002635181987305e-06,
      "loss": 0.4789,
      "step": 48076
    },
    {
      "epoch": 1.4768838509507574,
      "grad_norm": 0.4692077934741974,
      "learning_rate": 3.199909169532752e-06,
      "loss": 0.4898,
      "step": 48077
    },
    {
      "epoch": 1.4769145700857065,
      "grad_norm": 0.40367722511291504,
      "learning_rate": 3.1995548367488617e-06,
      "loss": 0.4618,
      "step": 48078
    },
    {
      "epoch": 1.4769452892206556,
      "grad_norm": 0.39768335223197937,
      "learning_rate": 3.199200519847888e-06,
      "loss": 0.4172,
      "step": 48079
    },
    {
      "epoch": 1.4769760083556047,
      "grad_norm": 0.39593392610549927,
      "learning_rate": 3.1988462188306546e-06,
      "loss": 0.4218,
      "step": 48080
    },
    {
      "epoch": 1.4770067274905538,
      "grad_norm": 0.4786469638347626,
      "learning_rate": 3.19849193369799e-06,
      "loss": 0.5005,
      "step": 48081
    },
    {
      "epoch": 1.477037446625503,
      "grad_norm": 0.4022139012813568,
      "learning_rate": 3.198137664450722e-06,
      "loss": 0.4849,
      "step": 48082
    },
    {
      "epoch": 1.477068165760452,
      "grad_norm": 0.4728560745716095,
      "learning_rate": 3.19778341108968e-06,
      "loss": 0.4492,
      "step": 48083
    },
    {
      "epoch": 1.4770988848954014,
      "grad_norm": 0.4033152759075165,
      "learning_rate": 3.1974291736156917e-06,
      "loss": 0.4752,
      "step": 48084
    },
    {
      "epoch": 1.4771296040303505,
      "grad_norm": 0.4268069267272949,
      "learning_rate": 3.1970749520295797e-06,
      "loss": 0.384,
      "step": 48085
    },
    {
      "epoch": 1.4771603231652997,
      "grad_norm": 0.47185635566711426,
      "learning_rate": 3.196720746332175e-06,
      "loss": 0.403,
      "step": 48086
    },
    {
      "epoch": 1.4771910423002488,
      "grad_norm": 0.42653369903564453,
      "learning_rate": 3.196366556524303e-06,
      "loss": 0.5295,
      "step": 48087
    },
    {
      "epoch": 1.4772217614351981,
      "grad_norm": 0.4771879017353058,
      "learning_rate": 3.196012382606797e-06,
      "loss": 0.4847,
      "step": 48088
    },
    {
      "epoch": 1.4772524805701472,
      "grad_norm": 0.41141316294670105,
      "learning_rate": 3.1956582245804745e-06,
      "loss": 0.4352,
      "step": 48089
    },
    {
      "epoch": 1.4772831997050964,
      "grad_norm": 0.48353680968284607,
      "learning_rate": 3.195304082446171e-06,
      "loss": 0.4915,
      "step": 48090
    },
    {
      "epoch": 1.4773139188400455,
      "grad_norm": 0.3771136701107025,
      "learning_rate": 3.1949499562047038e-06,
      "loss": 0.4531,
      "step": 48091
    },
    {
      "epoch": 1.4773446379749946,
      "grad_norm": 0.567682683467865,
      "learning_rate": 3.1945958458569127e-06,
      "loss": 0.458,
      "step": 48092
    },
    {
      "epoch": 1.4773753571099437,
      "grad_norm": 0.40521422028541565,
      "learning_rate": 3.1942417514036152e-06,
      "loss": 0.4822,
      "step": 48093
    },
    {
      "epoch": 1.4774060762448928,
      "grad_norm": 0.4282083809375763,
      "learning_rate": 3.193887672845645e-06,
      "loss": 0.3819,
      "step": 48094
    },
    {
      "epoch": 1.4774367953798422,
      "grad_norm": 0.4339674115180969,
      "learning_rate": 3.1935336101838177e-06,
      "loss": 0.4589,
      "step": 48095
    },
    {
      "epoch": 1.4774675145147913,
      "grad_norm": 0.42249998450279236,
      "learning_rate": 3.1931795634189754e-06,
      "loss": 0.4205,
      "step": 48096
    },
    {
      "epoch": 1.4774982336497404,
      "grad_norm": 0.4170912802219391,
      "learning_rate": 3.1928255325519343e-06,
      "loss": 0.5331,
      "step": 48097
    },
    {
      "epoch": 1.4775289527846895,
      "grad_norm": 0.4361303448677063,
      "learning_rate": 3.1924715175835276e-06,
      "loss": 0.5013,
      "step": 48098
    },
    {
      "epoch": 1.4775596719196387,
      "grad_norm": 0.45023420453071594,
      "learning_rate": 3.192117518514576e-06,
      "loss": 0.4782,
      "step": 48099
    },
    {
      "epoch": 1.477590391054588,
      "grad_norm": 0.4317220449447632,
      "learning_rate": 3.1917635353459054e-06,
      "loss": 0.4653,
      "step": 48100
    },
    {
      "epoch": 1.4776211101895371,
      "grad_norm": 0.40482833981513977,
      "learning_rate": 3.191409568078354e-06,
      "loss": 0.4999,
      "step": 48101
    },
    {
      "epoch": 1.4776518293244862,
      "grad_norm": 0.42122894525527954,
      "learning_rate": 3.191055616712738e-06,
      "loss": 0.4797,
      "step": 48102
    },
    {
      "epoch": 1.4776825484594354,
      "grad_norm": 0.4867885410785675,
      "learning_rate": 3.1907016812498894e-06,
      "loss": 0.4572,
      "step": 48103
    },
    {
      "epoch": 1.4777132675943845,
      "grad_norm": 0.4693147540092468,
      "learning_rate": 3.1903477616906297e-06,
      "loss": 0.4556,
      "step": 48104
    },
    {
      "epoch": 1.4777439867293336,
      "grad_norm": 0.4478437006473541,
      "learning_rate": 3.189993858035789e-06,
      "loss": 0.5109,
      "step": 48105
    },
    {
      "epoch": 1.477774705864283,
      "grad_norm": 0.4413944184780121,
      "learning_rate": 3.1896399702861924e-06,
      "loss": 0.4811,
      "step": 48106
    },
    {
      "epoch": 1.477805424999232,
      "grad_norm": 0.42186081409454346,
      "learning_rate": 3.189286098442671e-06,
      "loss": 0.5044,
      "step": 48107
    },
    {
      "epoch": 1.4778361441341812,
      "grad_norm": 0.46440184116363525,
      "learning_rate": 3.188932242506044e-06,
      "loss": 0.4332,
      "step": 48108
    },
    {
      "epoch": 1.4778668632691303,
      "grad_norm": 0.42680853605270386,
      "learning_rate": 3.1885784024771426e-06,
      "loss": 0.4261,
      "step": 48109
    },
    {
      "epoch": 1.4778975824040794,
      "grad_norm": 0.43334636092185974,
      "learning_rate": 3.1882245783567913e-06,
      "loss": 0.4986,
      "step": 48110
    },
    {
      "epoch": 1.4779283015390288,
      "grad_norm": 0.4694594442844391,
      "learning_rate": 3.18787077014582e-06,
      "loss": 0.5282,
      "step": 48111
    },
    {
      "epoch": 1.4779590206739779,
      "grad_norm": 0.44826874136924744,
      "learning_rate": 3.187516977845049e-06,
      "loss": 0.4921,
      "step": 48112
    },
    {
      "epoch": 1.477989739808927,
      "grad_norm": 0.44258296489715576,
      "learning_rate": 3.187163201455309e-06,
      "loss": 0.4225,
      "step": 48113
    },
    {
      "epoch": 1.4780204589438761,
      "grad_norm": 0.4292754530906677,
      "learning_rate": 3.186809440977424e-06,
      "loss": 0.4507,
      "step": 48114
    },
    {
      "epoch": 1.4780511780788252,
      "grad_norm": 0.8289297819137573,
      "learning_rate": 3.1864556964122252e-06,
      "loss": 0.5648,
      "step": 48115
    },
    {
      "epoch": 1.4780818972137744,
      "grad_norm": 0.40371230244636536,
      "learning_rate": 3.186101967760531e-06,
      "loss": 0.551,
      "step": 48116
    },
    {
      "epoch": 1.4781126163487235,
      "grad_norm": 0.4281274080276489,
      "learning_rate": 3.1857482550231724e-06,
      "loss": 0.3893,
      "step": 48117
    },
    {
      "epoch": 1.4781433354836728,
      "grad_norm": 0.6715962290763855,
      "learning_rate": 3.185394558200974e-06,
      "loss": 0.4947,
      "step": 48118
    },
    {
      "epoch": 1.478174054618622,
      "grad_norm": 0.46025317907333374,
      "learning_rate": 3.1850408772947628e-06,
      "loss": 0.4946,
      "step": 48119
    },
    {
      "epoch": 1.478204773753571,
      "grad_norm": 0.38007739186286926,
      "learning_rate": 3.184687212305367e-06,
      "loss": 0.4613,
      "step": 48120
    },
    {
      "epoch": 1.4782354928885202,
      "grad_norm": 0.4590499997138977,
      "learning_rate": 3.184333563233609e-06,
      "loss": 0.4754,
      "step": 48121
    },
    {
      "epoch": 1.4782662120234695,
      "grad_norm": 0.37126320600509644,
      "learning_rate": 3.183979930080314e-06,
      "loss": 0.4077,
      "step": 48122
    },
    {
      "epoch": 1.4782969311584186,
      "grad_norm": 0.42824992537498474,
      "learning_rate": 3.183626312846311e-06,
      "loss": 0.436,
      "step": 48123
    },
    {
      "epoch": 1.4783276502933678,
      "grad_norm": 0.427714079618454,
      "learning_rate": 3.183272711532428e-06,
      "loss": 0.4609,
      "step": 48124
    },
    {
      "epoch": 1.4783583694283169,
      "grad_norm": 0.5879198312759399,
      "learning_rate": 3.1829191261394845e-06,
      "loss": 0.4835,
      "step": 48125
    },
    {
      "epoch": 1.478389088563266,
      "grad_norm": 0.39919888973236084,
      "learning_rate": 3.182565556668312e-06,
      "loss": 0.4296,
      "step": 48126
    },
    {
      "epoch": 1.4784198076982151,
      "grad_norm": 0.42565637826919556,
      "learning_rate": 3.182212003119728e-06,
      "loss": 0.4931,
      "step": 48127
    },
    {
      "epoch": 1.4784505268331642,
      "grad_norm": 0.3986983597278595,
      "learning_rate": 3.1818584654945694e-06,
      "loss": 0.4192,
      "step": 48128
    },
    {
      "epoch": 1.4784812459681136,
      "grad_norm": 0.423563152551651,
      "learning_rate": 3.181504943793654e-06,
      "loss": 0.4761,
      "step": 48129
    },
    {
      "epoch": 1.4785119651030627,
      "grad_norm": 0.37339964509010315,
      "learning_rate": 3.181151438017813e-06,
      "loss": 0.4469,
      "step": 48130
    },
    {
      "epoch": 1.4785426842380118,
      "grad_norm": 0.4083802103996277,
      "learning_rate": 3.1807979481678665e-06,
      "loss": 0.4796,
      "step": 48131
    },
    {
      "epoch": 1.478573403372961,
      "grad_norm": 0.41488033533096313,
      "learning_rate": 3.1804444742446416e-06,
      "loss": 0.432,
      "step": 48132
    },
    {
      "epoch": 1.4786041225079103,
      "grad_norm": 0.4745718836784363,
      "learning_rate": 3.180091016248966e-06,
      "loss": 0.5012,
      "step": 48133
    },
    {
      "epoch": 1.4786348416428594,
      "grad_norm": 0.5482994914054871,
      "learning_rate": 3.1797375741816673e-06,
      "loss": 0.4644,
      "step": 48134
    },
    {
      "epoch": 1.4786655607778085,
      "grad_norm": 0.4266008734703064,
      "learning_rate": 3.179384148043564e-06,
      "loss": 0.4228,
      "step": 48135
    },
    {
      "epoch": 1.4786962799127576,
      "grad_norm": 0.402499794960022,
      "learning_rate": 3.1790307378354824e-06,
      "loss": 0.5021,
      "step": 48136
    },
    {
      "epoch": 1.4787269990477068,
      "grad_norm": 0.46904274821281433,
      "learning_rate": 3.1786773435582564e-06,
      "loss": 0.5152,
      "step": 48137
    },
    {
      "epoch": 1.478757718182656,
      "grad_norm": 0.3980209529399872,
      "learning_rate": 3.178323965212704e-06,
      "loss": 0.4741,
      "step": 48138
    },
    {
      "epoch": 1.478788437317605,
      "grad_norm": 0.41260167956352234,
      "learning_rate": 3.1779706027996548e-06,
      "loss": 0.4391,
      "step": 48139
    },
    {
      "epoch": 1.4788191564525544,
      "grad_norm": 0.397664338350296,
      "learning_rate": 3.177617256319929e-06,
      "loss": 0.4819,
      "step": 48140
    },
    {
      "epoch": 1.4788498755875035,
      "grad_norm": 0.4579358696937561,
      "learning_rate": 3.177263925774354e-06,
      "loss": 0.4516,
      "step": 48141
    },
    {
      "epoch": 1.4788805947224526,
      "grad_norm": 0.4233582317829132,
      "learning_rate": 3.176910611163756e-06,
      "loss": 0.4225,
      "step": 48142
    },
    {
      "epoch": 1.4789113138574017,
      "grad_norm": 0.3963182270526886,
      "learning_rate": 3.1765573124889624e-06,
      "loss": 0.4303,
      "step": 48143
    },
    {
      "epoch": 1.478942032992351,
      "grad_norm": 0.4619291424751282,
      "learning_rate": 3.1762040297507934e-06,
      "loss": 0.4422,
      "step": 48144
    },
    {
      "epoch": 1.4789727521273002,
      "grad_norm": 0.40464577078819275,
      "learning_rate": 3.175850762950077e-06,
      "loss": 0.4618,
      "step": 48145
    },
    {
      "epoch": 1.4790034712622493,
      "grad_norm": 0.4028554856777191,
      "learning_rate": 3.1754975120876364e-06,
      "loss": 0.4461,
      "step": 48146
    },
    {
      "epoch": 1.4790341903971984,
      "grad_norm": 0.3984373211860657,
      "learning_rate": 3.1751442771643014e-06,
      "loss": 0.4308,
      "step": 48147
    },
    {
      "epoch": 1.4790649095321475,
      "grad_norm": 0.38835471868515015,
      "learning_rate": 3.1747910581808907e-06,
      "loss": 0.4813,
      "step": 48148
    },
    {
      "epoch": 1.4790956286670967,
      "grad_norm": 0.4223300516605377,
      "learning_rate": 3.1744378551382326e-06,
      "loss": 0.45,
      "step": 48149
    },
    {
      "epoch": 1.4791263478020458,
      "grad_norm": 0.446812242269516,
      "learning_rate": 3.1740846680371505e-06,
      "loss": 0.4234,
      "step": 48150
    },
    {
      "epoch": 1.4791570669369951,
      "grad_norm": 0.38449907302856445,
      "learning_rate": 3.1737314968784737e-06,
      "loss": 0.4516,
      "step": 48151
    },
    {
      "epoch": 1.4791877860719442,
      "grad_norm": 0.4377017319202423,
      "learning_rate": 3.1733783416630215e-06,
      "loss": 0.5008,
      "step": 48152
    },
    {
      "epoch": 1.4792185052068934,
      "grad_norm": 0.4004208743572235,
      "learning_rate": 3.1730252023916207e-06,
      "loss": 0.4368,
      "step": 48153
    },
    {
      "epoch": 1.4792492243418425,
      "grad_norm": 0.4046323895454407,
      "learning_rate": 3.1726720790650955e-06,
      "loss": 0.442,
      "step": 48154
    },
    {
      "epoch": 1.4792799434767918,
      "grad_norm": 0.3987594544887543,
      "learning_rate": 3.1723189716842717e-06,
      "loss": 0.4463,
      "step": 48155
    },
    {
      "epoch": 1.479310662611741,
      "grad_norm": 0.434073805809021,
      "learning_rate": 3.1719658802499774e-06,
      "loss": 0.453,
      "step": 48156
    },
    {
      "epoch": 1.47934138174669,
      "grad_norm": 0.43253660202026367,
      "learning_rate": 3.1716128047630303e-06,
      "loss": 0.4888,
      "step": 48157
    },
    {
      "epoch": 1.4793721008816392,
      "grad_norm": 0.40202486515045166,
      "learning_rate": 3.1712597452242588e-06,
      "loss": 0.4911,
      "step": 48158
    },
    {
      "epoch": 1.4794028200165883,
      "grad_norm": 0.4305802583694458,
      "learning_rate": 3.170906701634486e-06,
      "loss": 0.4322,
      "step": 48159
    },
    {
      "epoch": 1.4794335391515374,
      "grad_norm": 0.419988214969635,
      "learning_rate": 3.1705536739945418e-06,
      "loss": 0.4227,
      "step": 48160
    },
    {
      "epoch": 1.4794642582864865,
      "grad_norm": 0.4288672208786011,
      "learning_rate": 3.170200662305243e-06,
      "loss": 0.5969,
      "step": 48161
    },
    {
      "epoch": 1.4794949774214359,
      "grad_norm": 0.5580876469612122,
      "learning_rate": 3.1698476665674206e-06,
      "loss": 0.4259,
      "step": 48162
    },
    {
      "epoch": 1.479525696556385,
      "grad_norm": 0.44124120473861694,
      "learning_rate": 3.16949468678189e-06,
      "loss": 0.5319,
      "step": 48163
    },
    {
      "epoch": 1.4795564156913341,
      "grad_norm": 0.36205095052719116,
      "learning_rate": 3.169141722949487e-06,
      "loss": 0.4395,
      "step": 48164
    },
    {
      "epoch": 1.4795871348262832,
      "grad_norm": 0.46821001172065735,
      "learning_rate": 3.168788775071029e-06,
      "loss": 0.4462,
      "step": 48165
    },
    {
      "epoch": 1.4796178539612326,
      "grad_norm": 0.39249086380004883,
      "learning_rate": 3.168435843147344e-06,
      "loss": 0.434,
      "step": 48166
    },
    {
      "epoch": 1.4796485730961817,
      "grad_norm": 0.4309593439102173,
      "learning_rate": 3.16808292717925e-06,
      "loss": 0.4318,
      "step": 48167
    },
    {
      "epoch": 1.4796792922311308,
      "grad_norm": 0.4569073021411896,
      "learning_rate": 3.167730027167577e-06,
      "loss": 0.4196,
      "step": 48168
    },
    {
      "epoch": 1.47971001136608,
      "grad_norm": 0.45473212003707886,
      "learning_rate": 3.1673771431131472e-06,
      "loss": 0.4457,
      "step": 48169
    },
    {
      "epoch": 1.479740730501029,
      "grad_norm": 0.39924725890159607,
      "learning_rate": 3.167024275016789e-06,
      "loss": 0.5081,
      "step": 48170
    },
    {
      "epoch": 1.4797714496359782,
      "grad_norm": 0.38490575551986694,
      "learning_rate": 3.1666714228793184e-06,
      "loss": 0.4329,
      "step": 48171
    },
    {
      "epoch": 1.4798021687709273,
      "grad_norm": 0.43787938356399536,
      "learning_rate": 3.1663185867015643e-06,
      "loss": 0.5129,
      "step": 48172
    },
    {
      "epoch": 1.4798328879058766,
      "grad_norm": 0.42189088463783264,
      "learning_rate": 3.165965766484351e-06,
      "loss": 0.4684,
      "step": 48173
    },
    {
      "epoch": 1.4798636070408258,
      "grad_norm": 0.49514085054397583,
      "learning_rate": 3.1656129622285016e-06,
      "loss": 0.4292,
      "step": 48174
    },
    {
      "epoch": 1.4798943261757749,
      "grad_norm": 0.4271818697452545,
      "learning_rate": 3.1652601739348443e-06,
      "loss": 0.4802,
      "step": 48175
    },
    {
      "epoch": 1.479925045310724,
      "grad_norm": 0.4043889045715332,
      "learning_rate": 3.1649074016041946e-06,
      "loss": 0.5011,
      "step": 48176
    },
    {
      "epoch": 1.4799557644456733,
      "grad_norm": 0.4132910966873169,
      "learning_rate": 3.164554645237382e-06,
      "loss": 0.4786,
      "step": 48177
    },
    {
      "epoch": 1.4799864835806225,
      "grad_norm": 0.5064674019813538,
      "learning_rate": 3.1642019048352302e-06,
      "loss": 0.5538,
      "step": 48178
    },
    {
      "epoch": 1.4800172027155716,
      "grad_norm": 0.41701480746269226,
      "learning_rate": 3.163849180398564e-06,
      "loss": 0.4714,
      "step": 48179
    },
    {
      "epoch": 1.4800479218505207,
      "grad_norm": 0.44488367438316345,
      "learning_rate": 3.1634964719282023e-06,
      "loss": 0.47,
      "step": 48180
    },
    {
      "epoch": 1.4800786409854698,
      "grad_norm": 0.40712064504623413,
      "learning_rate": 3.163143779424973e-06,
      "loss": 0.4563,
      "step": 48181
    },
    {
      "epoch": 1.480109360120419,
      "grad_norm": 0.4069560170173645,
      "learning_rate": 3.1627911028896986e-06,
      "loss": 0.3907,
      "step": 48182
    },
    {
      "epoch": 1.480140079255368,
      "grad_norm": 0.4589094817638397,
      "learning_rate": 3.1624384423232056e-06,
      "loss": 0.525,
      "step": 48183
    },
    {
      "epoch": 1.4801707983903174,
      "grad_norm": 0.4532729387283325,
      "learning_rate": 3.162085797726313e-06,
      "loss": 0.4838,
      "step": 48184
    },
    {
      "epoch": 1.4802015175252665,
      "grad_norm": 0.418921560049057,
      "learning_rate": 3.1617331690998454e-06,
      "loss": 0.4594,
      "step": 48185
    },
    {
      "epoch": 1.4802322366602156,
      "grad_norm": 0.3934386372566223,
      "learning_rate": 3.161380556444629e-06,
      "loss": 0.3848,
      "step": 48186
    },
    {
      "epoch": 1.4802629557951648,
      "grad_norm": 0.45015785098075867,
      "learning_rate": 3.161027959761488e-06,
      "loss": 0.5351,
      "step": 48187
    },
    {
      "epoch": 1.480293674930114,
      "grad_norm": 0.4094991683959961,
      "learning_rate": 3.1606753790512402e-06,
      "loss": 0.4656,
      "step": 48188
    },
    {
      "epoch": 1.4803243940650632,
      "grad_norm": 0.447734534740448,
      "learning_rate": 3.160322814314717e-06,
      "loss": 0.4081,
      "step": 48189
    },
    {
      "epoch": 1.4803551132000123,
      "grad_norm": 0.4557395577430725,
      "learning_rate": 3.1599702655527308e-06,
      "loss": 0.4916,
      "step": 48190
    },
    {
      "epoch": 1.4803858323349615,
      "grad_norm": 0.3874286413192749,
      "learning_rate": 3.1596177327661148e-06,
      "loss": 0.4608,
      "step": 48191
    },
    {
      "epoch": 1.4804165514699106,
      "grad_norm": 0.42477869987487793,
      "learning_rate": 3.1592652159556926e-06,
      "loss": 0.4363,
      "step": 48192
    },
    {
      "epoch": 1.4804472706048597,
      "grad_norm": 0.4397941529750824,
      "learning_rate": 3.158912715122281e-06,
      "loss": 0.5106,
      "step": 48193
    },
    {
      "epoch": 1.4804779897398088,
      "grad_norm": 0.3778878152370453,
      "learning_rate": 3.1585602302667096e-06,
      "loss": 0.4328,
      "step": 48194
    },
    {
      "epoch": 1.4805087088747582,
      "grad_norm": 0.39085835218429565,
      "learning_rate": 3.158207761389792e-06,
      "loss": 0.4943,
      "step": 48195
    },
    {
      "epoch": 1.4805394280097073,
      "grad_norm": 0.4220167100429535,
      "learning_rate": 3.1578553084923645e-06,
      "loss": 0.5249,
      "step": 48196
    },
    {
      "epoch": 1.4805701471446564,
      "grad_norm": 0.4048042893409729,
      "learning_rate": 3.157502871575242e-06,
      "loss": 0.4626,
      "step": 48197
    },
    {
      "epoch": 1.4806008662796055,
      "grad_norm": 0.44562017917633057,
      "learning_rate": 3.1571504506392516e-06,
      "loss": 0.4746,
      "step": 48198
    },
    {
      "epoch": 1.4806315854145549,
      "grad_norm": 0.4636351764202118,
      "learning_rate": 3.1567980456852065e-06,
      "loss": 0.4845,
      "step": 48199
    },
    {
      "epoch": 1.480662304549504,
      "grad_norm": 0.4250798225402832,
      "learning_rate": 3.156445656713946e-06,
      "loss": 0.4477,
      "step": 48200
    },
    {
      "epoch": 1.480693023684453,
      "grad_norm": 0.3801048696041107,
      "learning_rate": 3.1560932837262804e-06,
      "loss": 0.4952,
      "step": 48201
    },
    {
      "epoch": 1.4807237428194022,
      "grad_norm": 0.43411561846733093,
      "learning_rate": 3.1557409267230397e-06,
      "loss": 0.4366,
      "step": 48202
    },
    {
      "epoch": 1.4807544619543513,
      "grad_norm": 0.3821616768836975,
      "learning_rate": 3.1553885857050413e-06,
      "loss": 0.4196,
      "step": 48203
    },
    {
      "epoch": 1.4807851810893005,
      "grad_norm": 0.4390767216682434,
      "learning_rate": 3.155036260673111e-06,
      "loss": 0.5036,
      "step": 48204
    },
    {
      "epoch": 1.4808159002242496,
      "grad_norm": 0.4267433285713196,
      "learning_rate": 3.1546839516280715e-06,
      "loss": 0.5398,
      "step": 48205
    },
    {
      "epoch": 1.480846619359199,
      "grad_norm": 0.5143471956253052,
      "learning_rate": 3.1543316585707493e-06,
      "loss": 0.4726,
      "step": 48206
    },
    {
      "epoch": 1.480877338494148,
      "grad_norm": 0.39025938510894775,
      "learning_rate": 3.153979381501959e-06,
      "loss": 0.4126,
      "step": 48207
    },
    {
      "epoch": 1.4809080576290972,
      "grad_norm": 0.40756547451019287,
      "learning_rate": 3.15362712042253e-06,
      "loss": 0.4637,
      "step": 48208
    },
    {
      "epoch": 1.4809387767640463,
      "grad_norm": 0.4263317286968231,
      "learning_rate": 3.153274875333282e-06,
      "loss": 0.5393,
      "step": 48209
    },
    {
      "epoch": 1.4809694958989954,
      "grad_norm": 0.39936643838882446,
      "learning_rate": 3.152922646235038e-06,
      "loss": 0.4375,
      "step": 48210
    },
    {
      "epoch": 1.4810002150339447,
      "grad_norm": 0.42109835147857666,
      "learning_rate": 3.1525704331286257e-06,
      "loss": 0.4875,
      "step": 48211
    },
    {
      "epoch": 1.4810309341688939,
      "grad_norm": 0.4989553987979889,
      "learning_rate": 3.15221823601486e-06,
      "loss": 0.4339,
      "step": 48212
    },
    {
      "epoch": 1.481061653303843,
      "grad_norm": 0.42744705080986023,
      "learning_rate": 3.1518660548945656e-06,
      "loss": 0.4424,
      "step": 48213
    },
    {
      "epoch": 1.481092372438792,
      "grad_norm": 0.4329054653644562,
      "learning_rate": 3.151513889768568e-06,
      "loss": 0.5014,
      "step": 48214
    },
    {
      "epoch": 1.4811230915737412,
      "grad_norm": 0.4334559142589569,
      "learning_rate": 3.1511617406376906e-06,
      "loss": 0.4793,
      "step": 48215
    },
    {
      "epoch": 1.4811538107086903,
      "grad_norm": 0.5804935097694397,
      "learning_rate": 3.1508096075027494e-06,
      "loss": 0.4481,
      "step": 48216
    },
    {
      "epoch": 1.4811845298436397,
      "grad_norm": 0.4795985221862793,
      "learning_rate": 3.1504574903645714e-06,
      "loss": 0.4676,
      "step": 48217
    },
    {
      "epoch": 1.4812152489785888,
      "grad_norm": 0.44102466106414795,
      "learning_rate": 3.1501053892239785e-06,
      "loss": 0.4924,
      "step": 48218
    },
    {
      "epoch": 1.481245968113538,
      "grad_norm": 0.4280630350112915,
      "learning_rate": 3.1497533040817953e-06,
      "loss": 0.435,
      "step": 48219
    },
    {
      "epoch": 1.481276687248487,
      "grad_norm": 0.40571242570877075,
      "learning_rate": 3.1494012349388394e-06,
      "loss": 0.5067,
      "step": 48220
    },
    {
      "epoch": 1.4813074063834362,
      "grad_norm": 0.3944767713546753,
      "learning_rate": 3.1490491817959347e-06,
      "loss": 0.4418,
      "step": 48221
    },
    {
      "epoch": 1.4813381255183855,
      "grad_norm": 0.4273851811885834,
      "learning_rate": 3.1486971446539038e-06,
      "loss": 0.544,
      "step": 48222
    },
    {
      "epoch": 1.4813688446533346,
      "grad_norm": 0.5252020955085754,
      "learning_rate": 3.1483451235135733e-06,
      "loss": 0.4364,
      "step": 48223
    },
    {
      "epoch": 1.4813995637882837,
      "grad_norm": 0.3962189257144928,
      "learning_rate": 3.1479931183757574e-06,
      "loss": 0.4687,
      "step": 48224
    },
    {
      "epoch": 1.4814302829232329,
      "grad_norm": 0.42818138003349304,
      "learning_rate": 3.1476411292412855e-06,
      "loss": 0.46,
      "step": 48225
    },
    {
      "epoch": 1.481461002058182,
      "grad_norm": 0.3810494840145111,
      "learning_rate": 3.1472891561109698e-06,
      "loss": 0.4728,
      "step": 48226
    },
    {
      "epoch": 1.481491721193131,
      "grad_norm": 0.5138896703720093,
      "learning_rate": 3.146937198985642e-06,
      "loss": 0.493,
      "step": 48227
    },
    {
      "epoch": 1.4815224403280802,
      "grad_norm": 0.44125306606292725,
      "learning_rate": 3.146585257866125e-06,
      "loss": 0.492,
      "step": 48228
    },
    {
      "epoch": 1.4815531594630296,
      "grad_norm": 0.4428308308124542,
      "learning_rate": 3.1462333327532324e-06,
      "loss": 0.456,
      "step": 48229
    },
    {
      "epoch": 1.4815838785979787,
      "grad_norm": 0.4286636710166931,
      "learning_rate": 3.145881423647794e-06,
      "loss": 0.4397,
      "step": 48230
    },
    {
      "epoch": 1.4816145977329278,
      "grad_norm": 0.49070078134536743,
      "learning_rate": 3.1455295305506218e-06,
      "loss": 0.5,
      "step": 48231
    },
    {
      "epoch": 1.481645316867877,
      "grad_norm": 0.6940670013427734,
      "learning_rate": 3.1451776534625513e-06,
      "loss": 0.5102,
      "step": 48232
    },
    {
      "epoch": 1.4816760360028263,
      "grad_norm": 0.4228314161300659,
      "learning_rate": 3.1448257923843928e-06,
      "loss": 0.5038,
      "step": 48233
    },
    {
      "epoch": 1.4817067551377754,
      "grad_norm": 0.3827880620956421,
      "learning_rate": 3.1444739473169773e-06,
      "loss": 0.4329,
      "step": 48234
    },
    {
      "epoch": 1.4817374742727245,
      "grad_norm": 0.39685869216918945,
      "learning_rate": 3.144122118261117e-06,
      "loss": 0.4944,
      "step": 48235
    },
    {
      "epoch": 1.4817681934076736,
      "grad_norm": 1.0140764713287354,
      "learning_rate": 3.1437703052176384e-06,
      "loss": 0.5146,
      "step": 48236
    },
    {
      "epoch": 1.4817989125426227,
      "grad_norm": 0.4160403609275818,
      "learning_rate": 3.1434185081873637e-06,
      "loss": 0.4553,
      "step": 48237
    },
    {
      "epoch": 1.4818296316775719,
      "grad_norm": 0.4321720600128174,
      "learning_rate": 3.143066727171117e-06,
      "loss": 0.4739,
      "step": 48238
    },
    {
      "epoch": 1.481860350812521,
      "grad_norm": 1.261731505393982,
      "learning_rate": 3.1427149621697126e-06,
      "loss": 0.5398,
      "step": 48239
    },
    {
      "epoch": 1.4818910699474703,
      "grad_norm": 0.4283626973628998,
      "learning_rate": 3.1423632131839777e-06,
      "loss": 0.518,
      "step": 48240
    },
    {
      "epoch": 1.4819217890824194,
      "grad_norm": 0.4188613295555115,
      "learning_rate": 3.1420114802147316e-06,
      "loss": 0.5064,
      "step": 48241
    },
    {
      "epoch": 1.4819525082173686,
      "grad_norm": 0.4035475552082062,
      "learning_rate": 3.1416597632627998e-06,
      "loss": 0.4866,
      "step": 48242
    },
    {
      "epoch": 1.4819832273523177,
      "grad_norm": 0.4150782823562622,
      "learning_rate": 3.1413080623289983e-06,
      "loss": 0.4589,
      "step": 48243
    },
    {
      "epoch": 1.482013946487267,
      "grad_norm": 0.41377153992652893,
      "learning_rate": 3.1409563774141505e-06,
      "loss": 0.4393,
      "step": 48244
    },
    {
      "epoch": 1.4820446656222162,
      "grad_norm": 0.40387603640556335,
      "learning_rate": 3.1406047085190772e-06,
      "loss": 0.4335,
      "step": 48245
    },
    {
      "epoch": 1.4820753847571653,
      "grad_norm": 0.3901784121990204,
      "learning_rate": 3.140253055644602e-06,
      "loss": 0.4184,
      "step": 48246
    },
    {
      "epoch": 1.4821061038921144,
      "grad_norm": 0.39590826630592346,
      "learning_rate": 3.1399014187915477e-06,
      "loss": 0.5003,
      "step": 48247
    },
    {
      "epoch": 1.4821368230270635,
      "grad_norm": 0.424018532037735,
      "learning_rate": 3.139549797960729e-06,
      "loss": 0.5031,
      "step": 48248
    },
    {
      "epoch": 1.4821675421620126,
      "grad_norm": 0.4848388135433197,
      "learning_rate": 3.1391981931529712e-06,
      "loss": 0.4232,
      "step": 48249
    },
    {
      "epoch": 1.4821982612969617,
      "grad_norm": 0.4450610280036926,
      "learning_rate": 3.1388466043690946e-06,
      "loss": 0.4471,
      "step": 48250
    },
    {
      "epoch": 1.482228980431911,
      "grad_norm": 0.4594420790672302,
      "learning_rate": 3.138495031609925e-06,
      "loss": 0.423,
      "step": 48251
    },
    {
      "epoch": 1.4822596995668602,
      "grad_norm": 0.4396936595439911,
      "learning_rate": 3.1381434748762764e-06,
      "loss": 0.3988,
      "step": 48252
    },
    {
      "epoch": 1.4822904187018093,
      "grad_norm": 0.4865127503871918,
      "learning_rate": 3.137791934168972e-06,
      "loss": 0.398,
      "step": 48253
    },
    {
      "epoch": 1.4823211378367585,
      "grad_norm": 0.4050018787384033,
      "learning_rate": 3.1374404094888343e-06,
      "loss": 0.4763,
      "step": 48254
    },
    {
      "epoch": 1.4823518569717078,
      "grad_norm": 0.4493614435195923,
      "learning_rate": 3.137088900836687e-06,
      "loss": 0.4585,
      "step": 48255
    },
    {
      "epoch": 1.482382576106657,
      "grad_norm": 0.4125380516052246,
      "learning_rate": 3.136737408213344e-06,
      "loss": 0.5049,
      "step": 48256
    },
    {
      "epoch": 1.482413295241606,
      "grad_norm": 0.4623507559299469,
      "learning_rate": 3.1363859316196343e-06,
      "loss": 0.4358,
      "step": 48257
    },
    {
      "epoch": 1.4824440143765552,
      "grad_norm": 0.4385215640068054,
      "learning_rate": 3.1360344710563674e-06,
      "loss": 0.4504,
      "step": 48258
    },
    {
      "epoch": 1.4824747335115043,
      "grad_norm": 0.45004409551620483,
      "learning_rate": 3.1356830265243786e-06,
      "loss": 0.5013,
      "step": 48259
    },
    {
      "epoch": 1.4825054526464534,
      "grad_norm": 0.6506836414337158,
      "learning_rate": 3.135331598024478e-06,
      "loss": 0.4377,
      "step": 48260
    },
    {
      "epoch": 1.4825361717814025,
      "grad_norm": 0.423507422208786,
      "learning_rate": 3.1349801855574926e-06,
      "loss": 0.5067,
      "step": 48261
    },
    {
      "epoch": 1.4825668909163519,
      "grad_norm": 0.3902781009674072,
      "learning_rate": 3.1346287891242345e-06,
      "loss": 0.4159,
      "step": 48262
    },
    {
      "epoch": 1.482597610051301,
      "grad_norm": 0.42796722054481506,
      "learning_rate": 3.1342774087255333e-06,
      "loss": 0.4738,
      "step": 48263
    },
    {
      "epoch": 1.48262832918625,
      "grad_norm": 0.42069846391677856,
      "learning_rate": 3.13392604436221e-06,
      "loss": 0.5003,
      "step": 48264
    },
    {
      "epoch": 1.4826590483211992,
      "grad_norm": 0.39454421401023865,
      "learning_rate": 3.1335746960350787e-06,
      "loss": 0.4087,
      "step": 48265
    },
    {
      "epoch": 1.4826897674561486,
      "grad_norm": 0.424072802066803,
      "learning_rate": 3.1332233637449672e-06,
      "loss": 0.4752,
      "step": 48266
    },
    {
      "epoch": 1.4827204865910977,
      "grad_norm": 0.43824198842048645,
      "learning_rate": 3.1328720474926844e-06,
      "loss": 0.4403,
      "step": 48267
    },
    {
      "epoch": 1.4827512057260468,
      "grad_norm": 0.5658690333366394,
      "learning_rate": 3.1325207472790652e-06,
      "loss": 0.3985,
      "step": 48268
    },
    {
      "epoch": 1.482781924860996,
      "grad_norm": 0.40959224104881287,
      "learning_rate": 3.1321694631049204e-06,
      "loss": 0.3977,
      "step": 48269
    },
    {
      "epoch": 1.482812643995945,
      "grad_norm": 0.4552608132362366,
      "learning_rate": 3.131818194971077e-06,
      "loss": 0.4205,
      "step": 48270
    },
    {
      "epoch": 1.4828433631308942,
      "grad_norm": 0.4916282296180725,
      "learning_rate": 3.1314669428783483e-06,
      "loss": 0.5293,
      "step": 48271
    },
    {
      "epoch": 1.4828740822658433,
      "grad_norm": 1.0049086809158325,
      "learning_rate": 3.131115706827559e-06,
      "loss": 0.5131,
      "step": 48272
    },
    {
      "epoch": 1.4829048014007926,
      "grad_norm": 0.4206516444683075,
      "learning_rate": 3.1307644868195275e-06,
      "loss": 0.5193,
      "step": 48273
    },
    {
      "epoch": 1.4829355205357417,
      "grad_norm": 0.4235095679759979,
      "learning_rate": 3.130413282855079e-06,
      "loss": 0.4906,
      "step": 48274
    },
    {
      "epoch": 1.4829662396706909,
      "grad_norm": 0.4235324561595917,
      "learning_rate": 3.130062094935028e-06,
      "loss": 0.4225,
      "step": 48275
    },
    {
      "epoch": 1.48299695880564,
      "grad_norm": 0.48253491520881653,
      "learning_rate": 3.129710923060195e-06,
      "loss": 0.5463,
      "step": 48276
    },
    {
      "epoch": 1.4830276779405893,
      "grad_norm": 0.4213063418865204,
      "learning_rate": 3.1293597672314025e-06,
      "loss": 0.4359,
      "step": 48277
    },
    {
      "epoch": 1.4830583970755384,
      "grad_norm": 0.43111172318458557,
      "learning_rate": 3.1290086274494735e-06,
      "loss": 0.4173,
      "step": 48278
    },
    {
      "epoch": 1.4830891162104876,
      "grad_norm": 0.3914232850074768,
      "learning_rate": 3.1286575037152222e-06,
      "loss": 0.3907,
      "step": 48279
    },
    {
      "epoch": 1.4831198353454367,
      "grad_norm": 0.4257323443889618,
      "learning_rate": 3.12830639602947e-06,
      "loss": 0.5382,
      "step": 48280
    },
    {
      "epoch": 1.4831505544803858,
      "grad_norm": 0.43287980556488037,
      "learning_rate": 3.127955304393039e-06,
      "loss": 0.5081,
      "step": 48281
    },
    {
      "epoch": 1.483181273615335,
      "grad_norm": 0.40238896012306213,
      "learning_rate": 3.1276042288067476e-06,
      "loss": 0.4973,
      "step": 48282
    },
    {
      "epoch": 1.483211992750284,
      "grad_norm": 0.42057743668556213,
      "learning_rate": 3.1272531692714202e-06,
      "loss": 0.4129,
      "step": 48283
    },
    {
      "epoch": 1.4832427118852334,
      "grad_norm": 0.4341834485530853,
      "learning_rate": 3.1269021257878694e-06,
      "loss": 0.3802,
      "step": 48284
    },
    {
      "epoch": 1.4832734310201825,
      "grad_norm": 0.405500590801239,
      "learning_rate": 3.126551098356919e-06,
      "loss": 0.3855,
      "step": 48285
    },
    {
      "epoch": 1.4833041501551316,
      "grad_norm": 0.4220924973487854,
      "learning_rate": 3.1262000869793885e-06,
      "loss": 0.4867,
      "step": 48286
    },
    {
      "epoch": 1.4833348692900807,
      "grad_norm": 0.4450547397136688,
      "learning_rate": 3.1258490916561012e-06,
      "loss": 0.4752,
      "step": 48287
    },
    {
      "epoch": 1.48336558842503,
      "grad_norm": 0.4513095021247864,
      "learning_rate": 3.125498112387869e-06,
      "loss": 0.5129,
      "step": 48288
    },
    {
      "epoch": 1.4833963075599792,
      "grad_norm": 0.4432263672351837,
      "learning_rate": 3.125147149175518e-06,
      "loss": 0.4887,
      "step": 48289
    },
    {
      "epoch": 1.4834270266949283,
      "grad_norm": 0.4140219986438751,
      "learning_rate": 3.124796202019865e-06,
      "loss": 0.4575,
      "step": 48290
    },
    {
      "epoch": 1.4834577458298774,
      "grad_norm": 0.45614007115364075,
      "learning_rate": 3.1244452709217334e-06,
      "loss": 0.4191,
      "step": 48291
    },
    {
      "epoch": 1.4834884649648266,
      "grad_norm": 0.4205631911754608,
      "learning_rate": 3.124094355881937e-06,
      "loss": 0.5058,
      "step": 48292
    },
    {
      "epoch": 1.4835191840997757,
      "grad_norm": 0.4592694044113159,
      "learning_rate": 3.1237434569013027e-06,
      "loss": 0.5166,
      "step": 48293
    },
    {
      "epoch": 1.4835499032347248,
      "grad_norm": 0.4440232217311859,
      "learning_rate": 3.123392573980638e-06,
      "loss": 0.46,
      "step": 48294
    },
    {
      "epoch": 1.4835806223696741,
      "grad_norm": 0.41664329171180725,
      "learning_rate": 3.1230417071207774e-06,
      "loss": 0.4455,
      "step": 48295
    },
    {
      "epoch": 1.4836113415046233,
      "grad_norm": 0.4521596431732178,
      "learning_rate": 3.12269085632253e-06,
      "loss": 0.4955,
      "step": 48296
    },
    {
      "epoch": 1.4836420606395724,
      "grad_norm": 0.39597564935684204,
      "learning_rate": 3.1223400215867215e-06,
      "loss": 0.4772,
      "step": 48297
    },
    {
      "epoch": 1.4836727797745215,
      "grad_norm": 0.4283561110496521,
      "learning_rate": 3.121989202914164e-06,
      "loss": 0.5085,
      "step": 48298
    },
    {
      "epoch": 1.4837034989094708,
      "grad_norm": 0.45544570684432983,
      "learning_rate": 3.121638400305679e-06,
      "loss": 0.4986,
      "step": 48299
    },
    {
      "epoch": 1.48373421804442,
      "grad_norm": 0.38702571392059326,
      "learning_rate": 3.121287613762094e-06,
      "loss": 0.3997,
      "step": 48300
    },
    {
      "epoch": 1.483764937179369,
      "grad_norm": 0.39995837211608887,
      "learning_rate": 3.120936843284219e-06,
      "loss": 0.459,
      "step": 48301
    },
    {
      "epoch": 1.4837956563143182,
      "grad_norm": 0.39439311623573303,
      "learning_rate": 3.12058608887288e-06,
      "loss": 0.4862,
      "step": 48302
    },
    {
      "epoch": 1.4838263754492673,
      "grad_norm": 0.43406662344932556,
      "learning_rate": 3.1202353505288864e-06,
      "loss": 0.4915,
      "step": 48303
    },
    {
      "epoch": 1.4838570945842164,
      "grad_norm": 0.6053516268730164,
      "learning_rate": 3.1198846282530694e-06,
      "loss": 0.4127,
      "step": 48304
    },
    {
      "epoch": 1.4838878137191656,
      "grad_norm": 0.41181302070617676,
      "learning_rate": 3.1195339220462395e-06,
      "loss": 0.4474,
      "step": 48305
    },
    {
      "epoch": 1.483918532854115,
      "grad_norm": 0.39647844433784485,
      "learning_rate": 3.119183231909221e-06,
      "loss": 0.5159,
      "step": 48306
    },
    {
      "epoch": 1.483949251989064,
      "grad_norm": 0.5195605158805847,
      "learning_rate": 3.1188325578428282e-06,
      "loss": 0.479,
      "step": 48307
    },
    {
      "epoch": 1.4839799711240131,
      "grad_norm": 0.40217575430870056,
      "learning_rate": 3.118481899847883e-06,
      "loss": 0.5146,
      "step": 48308
    },
    {
      "epoch": 1.4840106902589623,
      "grad_norm": 0.4283638298511505,
      "learning_rate": 3.1181312579252023e-06,
      "loss": 0.3811,
      "step": 48309
    },
    {
      "epoch": 1.4840414093939116,
      "grad_norm": 0.43517956137657166,
      "learning_rate": 3.117780632075611e-06,
      "loss": 0.5071,
      "step": 48310
    },
    {
      "epoch": 1.4840721285288607,
      "grad_norm": 0.4162297248840332,
      "learning_rate": 3.117430022299921e-06,
      "loss": 0.4741,
      "step": 48311
    },
    {
      "epoch": 1.4841028476638098,
      "grad_norm": 0.4039324223995209,
      "learning_rate": 3.1170794285989523e-06,
      "loss": 0.4504,
      "step": 48312
    },
    {
      "epoch": 1.484133566798759,
      "grad_norm": 0.45270463824272156,
      "learning_rate": 3.116728850973527e-06,
      "loss": 0.4276,
      "step": 48313
    },
    {
      "epoch": 1.484164285933708,
      "grad_norm": 0.37121832370758057,
      "learning_rate": 3.116378289424464e-06,
      "loss": 0.5275,
      "step": 48314
    },
    {
      "epoch": 1.4841950050686572,
      "grad_norm": 0.4065883159637451,
      "learning_rate": 3.1160277439525778e-06,
      "loss": 0.4561,
      "step": 48315
    },
    {
      "epoch": 1.4842257242036063,
      "grad_norm": 0.41503632068634033,
      "learning_rate": 3.11567721455869e-06,
      "loss": 0.4746,
      "step": 48316
    },
    {
      "epoch": 1.4842564433385557,
      "grad_norm": 0.4477579891681671,
      "learning_rate": 3.1153267012436184e-06,
      "loss": 0.5267,
      "step": 48317
    },
    {
      "epoch": 1.4842871624735048,
      "grad_norm": 0.44617483019828796,
      "learning_rate": 3.114976204008181e-06,
      "loss": 0.5315,
      "step": 48318
    },
    {
      "epoch": 1.484317881608454,
      "grad_norm": 0.44207578897476196,
      "learning_rate": 3.1146257228532016e-06,
      "loss": 0.5195,
      "step": 48319
    },
    {
      "epoch": 1.484348600743403,
      "grad_norm": 0.45777615904808044,
      "learning_rate": 3.114275257779492e-06,
      "loss": 0.572,
      "step": 48320
    },
    {
      "epoch": 1.4843793198783521,
      "grad_norm": 0.4327886402606964,
      "learning_rate": 3.1139248087878738e-06,
      "loss": 0.4504,
      "step": 48321
    },
    {
      "epoch": 1.4844100390133015,
      "grad_norm": 0.3960203528404236,
      "learning_rate": 3.1135743758791635e-06,
      "loss": 0.3756,
      "step": 48322
    },
    {
      "epoch": 1.4844407581482506,
      "grad_norm": 0.43378278613090515,
      "learning_rate": 3.113223959054186e-06,
      "loss": 0.4521,
      "step": 48323
    },
    {
      "epoch": 1.4844714772831997,
      "grad_norm": 0.4340554177761078,
      "learning_rate": 3.11287355831375e-06,
      "loss": 0.4663,
      "step": 48324
    },
    {
      "epoch": 1.4845021964181488,
      "grad_norm": 0.4451276957988739,
      "learning_rate": 3.1125231736586803e-06,
      "loss": 0.4449,
      "step": 48325
    },
    {
      "epoch": 1.484532915553098,
      "grad_norm": 0.41188931465148926,
      "learning_rate": 3.1121728050897927e-06,
      "loss": 0.4701,
      "step": 48326
    },
    {
      "epoch": 1.484563634688047,
      "grad_norm": 0.47414901852607727,
      "learning_rate": 3.111822452607911e-06,
      "loss": 0.4827,
      "step": 48327
    },
    {
      "epoch": 1.4845943538229964,
      "grad_norm": 0.4722521901130676,
      "learning_rate": 3.111472116213845e-06,
      "loss": 0.469,
      "step": 48328
    },
    {
      "epoch": 1.4846250729579455,
      "grad_norm": 0.4386495351791382,
      "learning_rate": 3.1111217959084205e-06,
      "loss": 0.4799,
      "step": 48329
    },
    {
      "epoch": 1.4846557920928947,
      "grad_norm": 0.43174755573272705,
      "learning_rate": 3.1107714916924447e-06,
      "loss": 0.4754,
      "step": 48330
    },
    {
      "epoch": 1.4846865112278438,
      "grad_norm": 0.4384523630142212,
      "learning_rate": 3.1104212035667504e-06,
      "loss": 0.5255,
      "step": 48331
    },
    {
      "epoch": 1.484717230362793,
      "grad_norm": 0.3840065598487854,
      "learning_rate": 3.1100709315321453e-06,
      "loss": 0.5003,
      "step": 48332
    },
    {
      "epoch": 1.4847479494977422,
      "grad_norm": 0.4586183428764343,
      "learning_rate": 3.109720675589455e-06,
      "loss": 0.5405,
      "step": 48333
    },
    {
      "epoch": 1.4847786686326914,
      "grad_norm": 0.5517264008522034,
      "learning_rate": 3.1093704357394884e-06,
      "loss": 0.3817,
      "step": 48334
    },
    {
      "epoch": 1.4848093877676405,
      "grad_norm": 0.4225813150405884,
      "learning_rate": 3.1090202119830694e-06,
      "loss": 0.4619,
      "step": 48335
    },
    {
      "epoch": 1.4848401069025896,
      "grad_norm": 0.41326597332954407,
      "learning_rate": 3.1086700043210136e-06,
      "loss": 0.527,
      "step": 48336
    },
    {
      "epoch": 1.4848708260375387,
      "grad_norm": 0.5047652125358582,
      "learning_rate": 3.1083198127541425e-06,
      "loss": 0.4445,
      "step": 48337
    },
    {
      "epoch": 1.4849015451724878,
      "grad_norm": 0.41230684518814087,
      "learning_rate": 3.1079696372832737e-06,
      "loss": 0.453,
      "step": 48338
    },
    {
      "epoch": 1.484932264307437,
      "grad_norm": 0.4961910843849182,
      "learning_rate": 3.1076194779092195e-06,
      "loss": 0.4967,
      "step": 48339
    },
    {
      "epoch": 1.4849629834423863,
      "grad_norm": 0.4716155529022217,
      "learning_rate": 3.107269334632802e-06,
      "loss": 0.4969,
      "step": 48340
    },
    {
      "epoch": 1.4849937025773354,
      "grad_norm": 0.4514460861682892,
      "learning_rate": 3.1069192074548382e-06,
      "loss": 0.473,
      "step": 48341
    },
    {
      "epoch": 1.4850244217122845,
      "grad_norm": 0.45230957865715027,
      "learning_rate": 3.1065690963761497e-06,
      "loss": 0.4389,
      "step": 48342
    },
    {
      "epoch": 1.4850551408472337,
      "grad_norm": 0.46399497985839844,
      "learning_rate": 3.1062190013975467e-06,
      "loss": 0.431,
      "step": 48343
    },
    {
      "epoch": 1.485085859982183,
      "grad_norm": 0.41750985383987427,
      "learning_rate": 3.1058689225198503e-06,
      "loss": 0.4606,
      "step": 48344
    },
    {
      "epoch": 1.4851165791171321,
      "grad_norm": 0.4423585832118988,
      "learning_rate": 3.105518859743879e-06,
      "loss": 0.4295,
      "step": 48345
    },
    {
      "epoch": 1.4851472982520812,
      "grad_norm": 0.4774256646633148,
      "learning_rate": 3.105168813070454e-06,
      "loss": 0.465,
      "step": 48346
    },
    {
      "epoch": 1.4851780173870304,
      "grad_norm": 0.430160254240036,
      "learning_rate": 3.104818782500384e-06,
      "loss": 0.5086,
      "step": 48347
    },
    {
      "epoch": 1.4852087365219795,
      "grad_norm": 0.42670777440071106,
      "learning_rate": 3.104468768034492e-06,
      "loss": 0.4667,
      "step": 48348
    },
    {
      "epoch": 1.4852394556569286,
      "grad_norm": 0.4399239122867584,
      "learning_rate": 3.104118769673595e-06,
      "loss": 0.4786,
      "step": 48349
    },
    {
      "epoch": 1.4852701747918777,
      "grad_norm": 0.43283379077911377,
      "learning_rate": 3.103768787418513e-06,
      "loss": 0.4917,
      "step": 48350
    },
    {
      "epoch": 1.485300893926827,
      "grad_norm": 0.4345671236515045,
      "learning_rate": 3.1034188212700576e-06,
      "loss": 0.4065,
      "step": 48351
    },
    {
      "epoch": 1.4853316130617762,
      "grad_norm": 0.46635425090789795,
      "learning_rate": 3.103068871229049e-06,
      "loss": 0.5076,
      "step": 48352
    },
    {
      "epoch": 1.4853623321967253,
      "grad_norm": 0.4497930109500885,
      "learning_rate": 3.102718937296305e-06,
      "loss": 0.5195,
      "step": 48353
    },
    {
      "epoch": 1.4853930513316744,
      "grad_norm": 0.4688097834587097,
      "learning_rate": 3.1023690194726432e-06,
      "loss": 0.4701,
      "step": 48354
    },
    {
      "epoch": 1.4854237704666238,
      "grad_norm": 0.40564072132110596,
      "learning_rate": 3.102019117758882e-06,
      "loss": 0.4515,
      "step": 48355
    },
    {
      "epoch": 1.485454489601573,
      "grad_norm": 0.4691818356513977,
      "learning_rate": 3.101669232155835e-06,
      "loss": 0.4672,
      "step": 48356
    },
    {
      "epoch": 1.485485208736522,
      "grad_norm": 0.4131900370121002,
      "learning_rate": 3.101319362664321e-06,
      "loss": 0.3968,
      "step": 48357
    },
    {
      "epoch": 1.4855159278714711,
      "grad_norm": 0.45458582043647766,
      "learning_rate": 3.1009695092851565e-06,
      "loss": 0.4748,
      "step": 48358
    },
    {
      "epoch": 1.4855466470064203,
      "grad_norm": 0.39991265535354614,
      "learning_rate": 3.100619672019164e-06,
      "loss": 0.4739,
      "step": 48359
    },
    {
      "epoch": 1.4855773661413694,
      "grad_norm": 0.4915896952152252,
      "learning_rate": 3.1002698508671524e-06,
      "loss": 0.417,
      "step": 48360
    },
    {
      "epoch": 1.4856080852763185,
      "grad_norm": 0.46109193563461304,
      "learning_rate": 3.0999200458299427e-06,
      "loss": 0.5413,
      "step": 48361
    },
    {
      "epoch": 1.4856388044112678,
      "grad_norm": 0.45247554779052734,
      "learning_rate": 3.099570256908351e-06,
      "loss": 0.4353,
      "step": 48362
    },
    {
      "epoch": 1.485669523546217,
      "grad_norm": 0.42234253883361816,
      "learning_rate": 3.099220484103198e-06,
      "loss": 0.4701,
      "step": 48363
    },
    {
      "epoch": 1.485700242681166,
      "grad_norm": 0.39845505356788635,
      "learning_rate": 3.098870727415295e-06,
      "loss": 0.4954,
      "step": 48364
    },
    {
      "epoch": 1.4857309618161152,
      "grad_norm": 0.44823694229125977,
      "learning_rate": 3.098520986845465e-06,
      "loss": 0.5039,
      "step": 48365
    },
    {
      "epoch": 1.4857616809510645,
      "grad_norm": 0.4278750717639923,
      "learning_rate": 3.0981712623945136e-06,
      "loss": 0.4728,
      "step": 48366
    },
    {
      "epoch": 1.4857924000860137,
      "grad_norm": 0.4637846350669861,
      "learning_rate": 3.0978215540632728e-06,
      "loss": 0.4518,
      "step": 48367
    },
    {
      "epoch": 1.4858231192209628,
      "grad_norm": 0.44173887372016907,
      "learning_rate": 3.097471861852548e-06,
      "loss": 0.4421,
      "step": 48368
    },
    {
      "epoch": 1.485853838355912,
      "grad_norm": 0.3999326229095459,
      "learning_rate": 3.097122185763163e-06,
      "loss": 0.4662,
      "step": 48369
    },
    {
      "epoch": 1.485884557490861,
      "grad_norm": 0.4127252995967865,
      "learning_rate": 3.096772525795928e-06,
      "loss": 0.3827,
      "step": 48370
    },
    {
      "epoch": 1.4859152766258101,
      "grad_norm": 0.4548324644565582,
      "learning_rate": 3.0964228819516627e-06,
      "loss": 0.3919,
      "step": 48371
    },
    {
      "epoch": 1.4859459957607593,
      "grad_norm": 0.3951904773712158,
      "learning_rate": 3.0960732542311833e-06,
      "loss": 0.4892,
      "step": 48372
    },
    {
      "epoch": 1.4859767148957086,
      "grad_norm": 0.38751691579818726,
      "learning_rate": 3.0957236426353076e-06,
      "loss": 0.4332,
      "step": 48373
    },
    {
      "epoch": 1.4860074340306577,
      "grad_norm": 0.3872354328632355,
      "learning_rate": 3.095374047164855e-06,
      "loss": 0.456,
      "step": 48374
    },
    {
      "epoch": 1.4860381531656068,
      "grad_norm": 0.4355565905570984,
      "learning_rate": 3.0950244678206355e-06,
      "loss": 0.4236,
      "step": 48375
    },
    {
      "epoch": 1.486068872300556,
      "grad_norm": 0.4075111448764801,
      "learning_rate": 3.0946749046034684e-06,
      "loss": 0.4418,
      "step": 48376
    },
    {
      "epoch": 1.4860995914355053,
      "grad_norm": 0.387140691280365,
      "learning_rate": 3.0943253575141695e-06,
      "loss": 0.4977,
      "step": 48377
    },
    {
      "epoch": 1.4861303105704544,
      "grad_norm": 0.46563002467155457,
      "learning_rate": 3.0939758265535603e-06,
      "loss": 0.4901,
      "step": 48378
    },
    {
      "epoch": 1.4861610297054035,
      "grad_norm": 0.4115579128265381,
      "learning_rate": 3.09362631172245e-06,
      "loss": 0.4574,
      "step": 48379
    },
    {
      "epoch": 1.4861917488403527,
      "grad_norm": 0.4676898121833801,
      "learning_rate": 3.0932768130216563e-06,
      "loss": 0.4841,
      "step": 48380
    },
    {
      "epoch": 1.4862224679753018,
      "grad_norm": 0.3730054199695587,
      "learning_rate": 3.092927330451998e-06,
      "loss": 0.4154,
      "step": 48381
    },
    {
      "epoch": 1.486253187110251,
      "grad_norm": 0.4283333718776703,
      "learning_rate": 3.0925778640142933e-06,
      "loss": 0.4262,
      "step": 48382
    },
    {
      "epoch": 1.4862839062452,
      "grad_norm": 0.39166340231895447,
      "learning_rate": 3.092228413709352e-06,
      "loss": 0.4536,
      "step": 48383
    },
    {
      "epoch": 1.4863146253801494,
      "grad_norm": 0.41383031010627747,
      "learning_rate": 3.0918789795379935e-06,
      "loss": 0.4792,
      "step": 48384
    },
    {
      "epoch": 1.4863453445150985,
      "grad_norm": 0.40717455744743347,
      "learning_rate": 3.0915295615010343e-06,
      "loss": 0.4375,
      "step": 48385
    },
    {
      "epoch": 1.4863760636500476,
      "grad_norm": 0.4159783124923706,
      "learning_rate": 3.091180159599294e-06,
      "loss": 0.5015,
      "step": 48386
    },
    {
      "epoch": 1.4864067827849967,
      "grad_norm": 0.4080093204975128,
      "learning_rate": 3.0908307738335806e-06,
      "loss": 0.5333,
      "step": 48387
    },
    {
      "epoch": 1.486437501919946,
      "grad_norm": 0.4475427269935608,
      "learning_rate": 3.0904814042047158e-06,
      "loss": 0.4034,
      "step": 48388
    },
    {
      "epoch": 1.4864682210548952,
      "grad_norm": 0.4200279712677002,
      "learning_rate": 3.0901320507135133e-06,
      "loss": 0.4672,
      "step": 48389
    },
    {
      "epoch": 1.4864989401898443,
      "grad_norm": 0.4007783830165863,
      "learning_rate": 3.089782713360794e-06,
      "loss": 0.4793,
      "step": 48390
    },
    {
      "epoch": 1.4865296593247934,
      "grad_norm": 0.43649810552597046,
      "learning_rate": 3.0894333921473664e-06,
      "loss": 0.4826,
      "step": 48391
    },
    {
      "epoch": 1.4865603784597425,
      "grad_norm": 0.4543139934539795,
      "learning_rate": 3.089084087074049e-06,
      "loss": 0.4156,
      "step": 48392
    },
    {
      "epoch": 1.4865910975946917,
      "grad_norm": 0.42674973607063293,
      "learning_rate": 3.088734798141658e-06,
      "loss": 0.5026,
      "step": 48393
    },
    {
      "epoch": 1.4866218167296408,
      "grad_norm": 0.4249182641506195,
      "learning_rate": 3.0883855253510107e-06,
      "loss": 0.4993,
      "step": 48394
    },
    {
      "epoch": 1.4866525358645901,
      "grad_norm": 0.4352610409259796,
      "learning_rate": 3.0880362687029253e-06,
      "loss": 0.4889,
      "step": 48395
    },
    {
      "epoch": 1.4866832549995392,
      "grad_norm": 0.40401899814605713,
      "learning_rate": 3.0876870281982096e-06,
      "loss": 0.4322,
      "step": 48396
    },
    {
      "epoch": 1.4867139741344884,
      "grad_norm": 0.45427945256233215,
      "learning_rate": 3.087337803837687e-06,
      "loss": 0.4893,
      "step": 48397
    },
    {
      "epoch": 1.4867446932694375,
      "grad_norm": 0.4589274525642395,
      "learning_rate": 3.0869885956221636e-06,
      "loss": 0.5466,
      "step": 48398
    },
    {
      "epoch": 1.4867754124043868,
      "grad_norm": 0.4256547689437866,
      "learning_rate": 3.086639403552467e-06,
      "loss": 0.566,
      "step": 48399
    },
    {
      "epoch": 1.486806131539336,
      "grad_norm": 0.43755975365638733,
      "learning_rate": 3.086290227629405e-06,
      "loss": 0.3775,
      "step": 48400
    },
    {
      "epoch": 1.486836850674285,
      "grad_norm": 0.41028550267219543,
      "learning_rate": 3.085941067853797e-06,
      "loss": 0.4779,
      "step": 48401
    },
    {
      "epoch": 1.4868675698092342,
      "grad_norm": 0.41038838028907776,
      "learning_rate": 3.0855919242264497e-06,
      "loss": 0.5011,
      "step": 48402
    },
    {
      "epoch": 1.4868982889441833,
      "grad_norm": 0.4348861575126648,
      "learning_rate": 3.0852427967481935e-06,
      "loss": 0.4824,
      "step": 48403
    },
    {
      "epoch": 1.4869290080791324,
      "grad_norm": 0.3804973065853119,
      "learning_rate": 3.0848936854198308e-06,
      "loss": 0.4397,
      "step": 48404
    },
    {
      "epoch": 1.4869597272140815,
      "grad_norm": 0.4328577518463135,
      "learning_rate": 3.0845445902421854e-06,
      "loss": 0.4092,
      "step": 48405
    },
    {
      "epoch": 1.4869904463490309,
      "grad_norm": 0.44061142206192017,
      "learning_rate": 3.084195511216067e-06,
      "loss": 0.447,
      "step": 48406
    },
    {
      "epoch": 1.48702116548398,
      "grad_norm": 0.4236152172088623,
      "learning_rate": 3.0838464483422923e-06,
      "loss": 0.4183,
      "step": 48407
    },
    {
      "epoch": 1.4870518846189291,
      "grad_norm": 0.3993367552757263,
      "learning_rate": 3.083497401621677e-06,
      "loss": 0.4283,
      "step": 48408
    },
    {
      "epoch": 1.4870826037538782,
      "grad_norm": 0.3926803469657898,
      "learning_rate": 3.083148371055037e-06,
      "loss": 0.4549,
      "step": 48409
    },
    {
      "epoch": 1.4871133228888276,
      "grad_norm": 0.4010441303253174,
      "learning_rate": 3.082799356643189e-06,
      "loss": 0.4042,
      "step": 48410
    },
    {
      "epoch": 1.4871440420237767,
      "grad_norm": 0.462484747171402,
      "learning_rate": 3.082450358386945e-06,
      "loss": 0.4699,
      "step": 48411
    },
    {
      "epoch": 1.4871747611587258,
      "grad_norm": 0.41418546438217163,
      "learning_rate": 3.08210137628712e-06,
      "loss": 0.4691,
      "step": 48412
    },
    {
      "epoch": 1.487205480293675,
      "grad_norm": 0.42721983790397644,
      "learning_rate": 3.0817524103445305e-06,
      "loss": 0.4386,
      "step": 48413
    },
    {
      "epoch": 1.487236199428624,
      "grad_norm": 0.4567689001560211,
      "learning_rate": 3.081403460559994e-06,
      "loss": 0.4694,
      "step": 48414
    },
    {
      "epoch": 1.4872669185635732,
      "grad_norm": 0.40645989775657654,
      "learning_rate": 3.0810545269343206e-06,
      "loss": 0.4234,
      "step": 48415
    },
    {
      "epoch": 1.4872976376985223,
      "grad_norm": 0.4211258590221405,
      "learning_rate": 3.0807056094683274e-06,
      "loss": 0.4491,
      "step": 48416
    },
    {
      "epoch": 1.4873283568334716,
      "grad_norm": 0.440518319606781,
      "learning_rate": 3.0803567081628292e-06,
      "loss": 0.4561,
      "step": 48417
    },
    {
      "epoch": 1.4873590759684208,
      "grad_norm": 0.48065173625946045,
      "learning_rate": 3.0800078230186447e-06,
      "loss": 0.4866,
      "step": 48418
    },
    {
      "epoch": 1.4873897951033699,
      "grad_norm": 0.40207862854003906,
      "learning_rate": 3.079658954036583e-06,
      "loss": 0.4079,
      "step": 48419
    },
    {
      "epoch": 1.487420514238319,
      "grad_norm": 0.43429020047187805,
      "learning_rate": 3.0793101012174596e-06,
      "loss": 0.4519,
      "step": 48420
    },
    {
      "epoch": 1.4874512333732683,
      "grad_norm": 0.40126779675483704,
      "learning_rate": 3.0789612645620912e-06,
      "loss": 0.5479,
      "step": 48421
    },
    {
      "epoch": 1.4874819525082175,
      "grad_norm": 0.3905273377895355,
      "learning_rate": 3.078612444071295e-06,
      "loss": 0.4615,
      "step": 48422
    },
    {
      "epoch": 1.4875126716431666,
      "grad_norm": 0.41912248730659485,
      "learning_rate": 3.078263639745881e-06,
      "loss": 0.3934,
      "step": 48423
    },
    {
      "epoch": 1.4875433907781157,
      "grad_norm": 0.4988805055618286,
      "learning_rate": 3.0779148515866643e-06,
      "loss": 0.5504,
      "step": 48424
    },
    {
      "epoch": 1.4875741099130648,
      "grad_norm": 0.388936311006546,
      "learning_rate": 3.0775660795944607e-06,
      "loss": 0.5532,
      "step": 48425
    },
    {
      "epoch": 1.487604829048014,
      "grad_norm": 0.5783122181892395,
      "learning_rate": 3.0772173237700887e-06,
      "loss": 0.4202,
      "step": 48426
    },
    {
      "epoch": 1.487635548182963,
      "grad_norm": 0.41370323300361633,
      "learning_rate": 3.0768685841143563e-06,
      "loss": 0.4815,
      "step": 48427
    },
    {
      "epoch": 1.4876662673179124,
      "grad_norm": 0.4107776880264282,
      "learning_rate": 3.076519860628081e-06,
      "loss": 0.4319,
      "step": 48428
    },
    {
      "epoch": 1.4876969864528615,
      "grad_norm": 0.4124159812927246,
      "learning_rate": 3.0761711533120763e-06,
      "loss": 0.4355,
      "step": 48429
    },
    {
      "epoch": 1.4877277055878106,
      "grad_norm": 0.40574610233306885,
      "learning_rate": 3.075822462167157e-06,
      "loss": 0.5035,
      "step": 48430
    },
    {
      "epoch": 1.4877584247227598,
      "grad_norm": 0.4483148753643036,
      "learning_rate": 3.0754737871941433e-06,
      "loss": 0.5008,
      "step": 48431
    },
    {
      "epoch": 1.4877891438577089,
      "grad_norm": 0.4464009404182434,
      "learning_rate": 3.0751251283938387e-06,
      "loss": 0.4387,
      "step": 48432
    },
    {
      "epoch": 1.4878198629926582,
      "grad_norm": 0.48674285411834717,
      "learning_rate": 3.074776485767067e-06,
      "loss": 0.4178,
      "step": 48433
    },
    {
      "epoch": 1.4878505821276073,
      "grad_norm": 0.44553059339523315,
      "learning_rate": 3.0744278593146326e-06,
      "loss": 0.5502,
      "step": 48434
    },
    {
      "epoch": 1.4878813012625565,
      "grad_norm": 0.569527804851532,
      "learning_rate": 3.0740792490373617e-06,
      "loss": 0.4989,
      "step": 48435
    },
    {
      "epoch": 1.4879120203975056,
      "grad_norm": 0.41016581654548645,
      "learning_rate": 3.073730654936059e-06,
      "loss": 0.3912,
      "step": 48436
    },
    {
      "epoch": 1.4879427395324547,
      "grad_norm": 0.42260774970054626,
      "learning_rate": 3.0733820770115452e-06,
      "loss": 0.4896,
      "step": 48437
    },
    {
      "epoch": 1.4879734586674038,
      "grad_norm": 0.44340482354164124,
      "learning_rate": 3.0730335152646285e-06,
      "loss": 0.3748,
      "step": 48438
    },
    {
      "epoch": 1.4880041778023532,
      "grad_norm": 0.38945725560188293,
      "learning_rate": 3.0726849696961245e-06,
      "loss": 0.4615,
      "step": 48439
    },
    {
      "epoch": 1.4880348969373023,
      "grad_norm": 0.45728886127471924,
      "learning_rate": 3.0723364403068502e-06,
      "loss": 0.4307,
      "step": 48440
    },
    {
      "epoch": 1.4880656160722514,
      "grad_norm": 0.3814491927623749,
      "learning_rate": 3.0719879270976205e-06,
      "loss": 0.4553,
      "step": 48441
    },
    {
      "epoch": 1.4880963352072005,
      "grad_norm": 0.4995567500591278,
      "learning_rate": 3.0716394300692433e-06,
      "loss": 0.5405,
      "step": 48442
    },
    {
      "epoch": 1.4881270543421496,
      "grad_norm": 0.4188932776451111,
      "learning_rate": 3.071290949222536e-06,
      "loss": 0.5212,
      "step": 48443
    },
    {
      "epoch": 1.488157773477099,
      "grad_norm": 0.4065428078174591,
      "learning_rate": 3.0709424845583134e-06,
      "loss": 0.4668,
      "step": 48444
    },
    {
      "epoch": 1.488188492612048,
      "grad_norm": 0.46296414732933044,
      "learning_rate": 3.070594036077389e-06,
      "loss": 0.4399,
      "step": 48445
    },
    {
      "epoch": 1.4882192117469972,
      "grad_norm": 0.3950278162956238,
      "learning_rate": 3.0702456037805783e-06,
      "loss": 0.4359,
      "step": 48446
    },
    {
      "epoch": 1.4882499308819463,
      "grad_norm": 0.4459751844406128,
      "learning_rate": 3.0698971876686903e-06,
      "loss": 0.4836,
      "step": 48447
    },
    {
      "epoch": 1.4882806500168955,
      "grad_norm": 0.39115968346595764,
      "learning_rate": 3.0695487877425413e-06,
      "loss": 0.4161,
      "step": 48448
    },
    {
      "epoch": 1.4883113691518446,
      "grad_norm": 0.406647264957428,
      "learning_rate": 3.0692004040029443e-06,
      "loss": 0.5064,
      "step": 48449
    },
    {
      "epoch": 1.4883420882867937,
      "grad_norm": 0.46349480748176575,
      "learning_rate": 3.068852036450718e-06,
      "loss": 0.508,
      "step": 48450
    },
    {
      "epoch": 1.488372807421743,
      "grad_norm": 0.5106970071792603,
      "learning_rate": 3.068503685086668e-06,
      "loss": 0.471,
      "step": 48451
    },
    {
      "epoch": 1.4884035265566922,
      "grad_norm": 0.4034593105316162,
      "learning_rate": 3.0681553499116123e-06,
      "loss": 0.4807,
      "step": 48452
    },
    {
      "epoch": 1.4884342456916413,
      "grad_norm": 0.45265939831733704,
      "learning_rate": 3.067807030926363e-06,
      "loss": 0.5125,
      "step": 48453
    },
    {
      "epoch": 1.4884649648265904,
      "grad_norm": 0.44083815813064575,
      "learning_rate": 3.067458728131739e-06,
      "loss": 0.4467,
      "step": 48454
    },
    {
      "epoch": 1.4884956839615398,
      "grad_norm": 0.44344666600227356,
      "learning_rate": 3.0671104415285446e-06,
      "loss": 0.4602,
      "step": 48455
    },
    {
      "epoch": 1.4885264030964889,
      "grad_norm": 0.4518434703350067,
      "learning_rate": 3.0667621711175988e-06,
      "loss": 0.4828,
      "step": 48456
    },
    {
      "epoch": 1.488557122231438,
      "grad_norm": 0.43890380859375,
      "learning_rate": 3.0664139168997142e-06,
      "loss": 0.4324,
      "step": 48457
    },
    {
      "epoch": 1.488587841366387,
      "grad_norm": 0.4200975000858307,
      "learning_rate": 3.0660656788757084e-06,
      "loss": 0.422,
      "step": 48458
    },
    {
      "epoch": 1.4886185605013362,
      "grad_norm": 0.4543275535106659,
      "learning_rate": 3.0657174570463855e-06,
      "loss": 0.408,
      "step": 48459
    },
    {
      "epoch": 1.4886492796362853,
      "grad_norm": 0.43767285346984863,
      "learning_rate": 3.0653692514125676e-06,
      "loss": 0.4829,
      "step": 48460
    },
    {
      "epoch": 1.4886799987712345,
      "grad_norm": 0.4162936508655548,
      "learning_rate": 3.0650210619750577e-06,
      "loss": 0.515,
      "step": 48461
    },
    {
      "epoch": 1.4887107179061838,
      "grad_norm": 0.41702786087989807,
      "learning_rate": 3.064672888734682e-06,
      "loss": 0.4403,
      "step": 48462
    },
    {
      "epoch": 1.488741437041133,
      "grad_norm": 0.43224290013313293,
      "learning_rate": 3.064324731692244e-06,
      "loss": 0.5539,
      "step": 48463
    },
    {
      "epoch": 1.488772156176082,
      "grad_norm": 0.3942111134529114,
      "learning_rate": 3.0639765908485595e-06,
      "loss": 0.4514,
      "step": 48464
    },
    {
      "epoch": 1.4888028753110312,
      "grad_norm": 0.4233044385910034,
      "learning_rate": 3.0636284662044423e-06,
      "loss": 0.5272,
      "step": 48465
    },
    {
      "epoch": 1.4888335944459805,
      "grad_norm": 0.4081308841705322,
      "learning_rate": 3.0632803577607052e-06,
      "loss": 0.4296,
      "step": 48466
    },
    {
      "epoch": 1.4888643135809296,
      "grad_norm": 0.4954136312007904,
      "learning_rate": 3.0629322655181648e-06,
      "loss": 0.5163,
      "step": 48467
    },
    {
      "epoch": 1.4888950327158788,
      "grad_norm": 0.4202922582626343,
      "learning_rate": 3.0625841894776277e-06,
      "loss": 0.483,
      "step": 48468
    },
    {
      "epoch": 1.4889257518508279,
      "grad_norm": 0.3889394700527191,
      "learning_rate": 3.0622361296399115e-06,
      "loss": 0.4194,
      "step": 48469
    },
    {
      "epoch": 1.488956470985777,
      "grad_norm": 0.39062976837158203,
      "learning_rate": 3.061888086005822e-06,
      "loss": 0.4304,
      "step": 48470
    },
    {
      "epoch": 1.4889871901207261,
      "grad_norm": 0.43846291303634644,
      "learning_rate": 3.0615400585761832e-06,
      "loss": 0.4477,
      "step": 48471
    },
    {
      "epoch": 1.4890179092556752,
      "grad_norm": 0.4036261737346649,
      "learning_rate": 3.0611920473518e-06,
      "loss": 0.4956,
      "step": 48472
    },
    {
      "epoch": 1.4890486283906246,
      "grad_norm": 0.42384597659111023,
      "learning_rate": 3.0608440523334905e-06,
      "loss": 0.3955,
      "step": 48473
    },
    {
      "epoch": 1.4890793475255737,
      "grad_norm": 0.41022294759750366,
      "learning_rate": 3.06049607352206e-06,
      "loss": 0.4829,
      "step": 48474
    },
    {
      "epoch": 1.4891100666605228,
      "grad_norm": 0.42430126667022705,
      "learning_rate": 3.0601481109183264e-06,
      "loss": 0.5643,
      "step": 48475
    },
    {
      "epoch": 1.489140785795472,
      "grad_norm": 0.4078716039657593,
      "learning_rate": 3.0598001645231014e-06,
      "loss": 0.4949,
      "step": 48476
    },
    {
      "epoch": 1.4891715049304213,
      "grad_norm": 0.3937259316444397,
      "learning_rate": 3.059452234337201e-06,
      "loss": 0.4366,
      "step": 48477
    },
    {
      "epoch": 1.4892022240653704,
      "grad_norm": 0.4189867377281189,
      "learning_rate": 3.059104320361431e-06,
      "loss": 0.5254,
      "step": 48478
    },
    {
      "epoch": 1.4892329432003195,
      "grad_norm": 0.44710415601730347,
      "learning_rate": 3.058756422596608e-06,
      "loss": 0.5234,
      "step": 48479
    },
    {
      "epoch": 1.4892636623352686,
      "grad_norm": 0.40448877215385437,
      "learning_rate": 3.058408541043545e-06,
      "loss": 0.4417,
      "step": 48480
    },
    {
      "epoch": 1.4892943814702178,
      "grad_norm": 0.4069060981273651,
      "learning_rate": 3.058060675703056e-06,
      "loss": 0.5111,
      "step": 48481
    },
    {
      "epoch": 1.4893251006051669,
      "grad_norm": 0.40013808012008667,
      "learning_rate": 3.057712826575947e-06,
      "loss": 0.501,
      "step": 48482
    },
    {
      "epoch": 1.489355819740116,
      "grad_norm": 0.4415048062801361,
      "learning_rate": 3.0573649936630355e-06,
      "loss": 0.4603,
      "step": 48483
    },
    {
      "epoch": 1.4893865388750653,
      "grad_norm": 0.48445695638656616,
      "learning_rate": 3.0570171769651337e-06,
      "loss": 0.4649,
      "step": 48484
    },
    {
      "epoch": 1.4894172580100145,
      "grad_norm": 0.42487192153930664,
      "learning_rate": 3.0566693764830525e-06,
      "loss": 0.4387,
      "step": 48485
    },
    {
      "epoch": 1.4894479771449636,
      "grad_norm": 0.42674046754837036,
      "learning_rate": 3.0563215922176073e-06,
      "loss": 0.5797,
      "step": 48486
    },
    {
      "epoch": 1.4894786962799127,
      "grad_norm": 0.430756151676178,
      "learning_rate": 3.0559738241696056e-06,
      "loss": 0.5447,
      "step": 48487
    },
    {
      "epoch": 1.489509415414862,
      "grad_norm": 0.39955413341522217,
      "learning_rate": 3.0556260723398624e-06,
      "loss": 0.4431,
      "step": 48488
    },
    {
      "epoch": 1.4895401345498112,
      "grad_norm": 0.4351794421672821,
      "learning_rate": 3.055278336729188e-06,
      "loss": 0.4422,
      "step": 48489
    },
    {
      "epoch": 1.4895708536847603,
      "grad_norm": 0.42149803042411804,
      "learning_rate": 3.054930617338401e-06,
      "loss": 0.4749,
      "step": 48490
    },
    {
      "epoch": 1.4896015728197094,
      "grad_norm": 0.45705124735832214,
      "learning_rate": 3.0545829141683038e-06,
      "loss": 0.4582,
      "step": 48491
    },
    {
      "epoch": 1.4896322919546585,
      "grad_norm": 0.45438671112060547,
      "learning_rate": 3.054235227219714e-06,
      "loss": 0.518,
      "step": 48492
    },
    {
      "epoch": 1.4896630110896076,
      "grad_norm": 0.4335370659828186,
      "learning_rate": 3.0538875564934436e-06,
      "loss": 0.4698,
      "step": 48493
    },
    {
      "epoch": 1.4896937302245568,
      "grad_norm": 0.4492464065551758,
      "learning_rate": 3.0535399019903067e-06,
      "loss": 0.4376,
      "step": 48494
    },
    {
      "epoch": 1.489724449359506,
      "grad_norm": 0.4110569953918457,
      "learning_rate": 3.053192263711109e-06,
      "loss": 0.4893,
      "step": 48495
    },
    {
      "epoch": 1.4897551684944552,
      "grad_norm": 0.4524635672569275,
      "learning_rate": 3.0528446416566693e-06,
      "loss": 0.4223,
      "step": 48496
    },
    {
      "epoch": 1.4897858876294043,
      "grad_norm": 0.40322524309158325,
      "learning_rate": 3.0524970358277896e-06,
      "loss": 0.4855,
      "step": 48497
    },
    {
      "epoch": 1.4898166067643535,
      "grad_norm": 0.43994149565696716,
      "learning_rate": 3.0521494462252942e-06,
      "loss": 0.4587,
      "step": 48498
    },
    {
      "epoch": 1.4898473258993028,
      "grad_norm": 0.4343046247959137,
      "learning_rate": 3.0518018728499867e-06,
      "loss": 0.415,
      "step": 48499
    },
    {
      "epoch": 1.489878045034252,
      "grad_norm": 0.43859466910362244,
      "learning_rate": 3.05145431570268e-06,
      "loss": 0.4243,
      "step": 48500
    },
    {
      "epoch": 1.489908764169201,
      "grad_norm": 0.41969865560531616,
      "learning_rate": 3.0511067747841917e-06,
      "loss": 0.4606,
      "step": 48501
    },
    {
      "epoch": 1.4899394833041502,
      "grad_norm": 0.4220159649848938,
      "learning_rate": 3.050759250095321e-06,
      "loss": 0.4674,
      "step": 48502
    },
    {
      "epoch": 1.4899702024390993,
      "grad_norm": 0.4368709623813629,
      "learning_rate": 3.050411741636895e-06,
      "loss": 0.475,
      "step": 48503
    },
    {
      "epoch": 1.4900009215740484,
      "grad_norm": 0.46197760105133057,
      "learning_rate": 3.0500642494097145e-06,
      "loss": 0.5081,
      "step": 48504
    },
    {
      "epoch": 1.4900316407089975,
      "grad_norm": 0.41598615050315857,
      "learning_rate": 3.049716773414596e-06,
      "loss": 0.4247,
      "step": 48505
    },
    {
      "epoch": 1.4900623598439469,
      "grad_norm": 0.4508513808250427,
      "learning_rate": 3.049369313652345e-06,
      "loss": 0.4017,
      "step": 48506
    },
    {
      "epoch": 1.490093078978896,
      "grad_norm": 0.45176342129707336,
      "learning_rate": 3.0490218701237827e-06,
      "loss": 0.4882,
      "step": 48507
    },
    {
      "epoch": 1.490123798113845,
      "grad_norm": 0.39120879769325256,
      "learning_rate": 3.0486744428297124e-06,
      "loss": 0.4453,
      "step": 48508
    },
    {
      "epoch": 1.4901545172487942,
      "grad_norm": 0.438278466463089,
      "learning_rate": 3.048327031770951e-06,
      "loss": 0.459,
      "step": 48509
    },
    {
      "epoch": 1.4901852363837436,
      "grad_norm": 0.38180607557296753,
      "learning_rate": 3.047979636948305e-06,
      "loss": 0.4957,
      "step": 48510
    },
    {
      "epoch": 1.4902159555186927,
      "grad_norm": 0.4760667383670807,
      "learning_rate": 3.0476322583625875e-06,
      "loss": 0.449,
      "step": 48511
    },
    {
      "epoch": 1.4902466746536418,
      "grad_norm": 0.4347458779811859,
      "learning_rate": 3.0472848960146108e-06,
      "loss": 0.4769,
      "step": 48512
    },
    {
      "epoch": 1.490277393788591,
      "grad_norm": 0.41366472840309143,
      "learning_rate": 3.046937549905188e-06,
      "loss": 0.4294,
      "step": 48513
    },
    {
      "epoch": 1.49030811292354,
      "grad_norm": 0.4421551823616028,
      "learning_rate": 3.046590220035126e-06,
      "loss": 0.4811,
      "step": 48514
    },
    {
      "epoch": 1.4903388320584892,
      "grad_norm": 0.4349188506603241,
      "learning_rate": 3.046242906405238e-06,
      "loss": 0.5176,
      "step": 48515
    },
    {
      "epoch": 1.4903695511934383,
      "grad_norm": 0.4388967454433441,
      "learning_rate": 3.045895609016335e-06,
      "loss": 0.5021,
      "step": 48516
    },
    {
      "epoch": 1.4904002703283876,
      "grad_norm": 0.3843047022819519,
      "learning_rate": 3.045548327869232e-06,
      "loss": 0.4629,
      "step": 48517
    },
    {
      "epoch": 1.4904309894633367,
      "grad_norm": 0.41299334168434143,
      "learning_rate": 3.045201062964733e-06,
      "loss": 0.4041,
      "step": 48518
    },
    {
      "epoch": 1.4904617085982859,
      "grad_norm": 0.4207742214202881,
      "learning_rate": 3.044853814303653e-06,
      "loss": 0.5765,
      "step": 48519
    },
    {
      "epoch": 1.490492427733235,
      "grad_norm": 0.4157448410987854,
      "learning_rate": 3.0445065818868023e-06,
      "loss": 0.5098,
      "step": 48520
    },
    {
      "epoch": 1.4905231468681843,
      "grad_norm": 0.44030484557151794,
      "learning_rate": 3.0441593657149927e-06,
      "loss": 0.4921,
      "step": 48521
    },
    {
      "epoch": 1.4905538660031334,
      "grad_norm": 0.40308183431625366,
      "learning_rate": 3.0438121657890374e-06,
      "loss": 0.4293,
      "step": 48522
    },
    {
      "epoch": 1.4905845851380826,
      "grad_norm": 0.4535328149795532,
      "learning_rate": 3.0434649821097416e-06,
      "loss": 0.4882,
      "step": 48523
    },
    {
      "epoch": 1.4906153042730317,
      "grad_norm": 0.40216079354286194,
      "learning_rate": 3.0431178146779196e-06,
      "loss": 0.462,
      "step": 48524
    },
    {
      "epoch": 1.4906460234079808,
      "grad_norm": 0.4961526393890381,
      "learning_rate": 3.042770663494381e-06,
      "loss": 0.4122,
      "step": 48525
    },
    {
      "epoch": 1.49067674254293,
      "grad_norm": 0.4677933156490326,
      "learning_rate": 3.0424235285599414e-06,
      "loss": 0.4894,
      "step": 48526
    },
    {
      "epoch": 1.490707461677879,
      "grad_norm": 0.5760367512702942,
      "learning_rate": 3.0420764098754042e-06,
      "loss": 0.4533,
      "step": 48527
    },
    {
      "epoch": 1.4907381808128284,
      "grad_norm": 0.4953837990760803,
      "learning_rate": 3.0417293074415834e-06,
      "loss": 0.4673,
      "step": 48528
    },
    {
      "epoch": 1.4907688999477775,
      "grad_norm": 0.5832136869430542,
      "learning_rate": 3.041382221259289e-06,
      "loss": 0.4861,
      "step": 48529
    },
    {
      "epoch": 1.4907996190827266,
      "grad_norm": 0.46657246351242065,
      "learning_rate": 3.041035151329337e-06,
      "loss": 0.4606,
      "step": 48530
    },
    {
      "epoch": 1.4908303382176757,
      "grad_norm": 0.41317620873451233,
      "learning_rate": 3.0406880976525286e-06,
      "loss": 0.5682,
      "step": 48531
    },
    {
      "epoch": 1.490861057352625,
      "grad_norm": 0.39945706725120544,
      "learning_rate": 3.0403410602296834e-06,
      "loss": 0.3949,
      "step": 48532
    },
    {
      "epoch": 1.4908917764875742,
      "grad_norm": 0.3959749937057495,
      "learning_rate": 3.039994039061601e-06,
      "loss": 0.4884,
      "step": 48533
    },
    {
      "epoch": 1.4909224956225233,
      "grad_norm": 0.3990732729434967,
      "learning_rate": 3.039647034149106e-06,
      "loss": 0.3959,
      "step": 48534
    },
    {
      "epoch": 1.4909532147574724,
      "grad_norm": 0.6439951658248901,
      "learning_rate": 3.039300045492997e-06,
      "loss": 0.4414,
      "step": 48535
    },
    {
      "epoch": 1.4909839338924216,
      "grad_norm": 0.4327133893966675,
      "learning_rate": 3.038953073094093e-06,
      "loss": 0.4631,
      "step": 48536
    },
    {
      "epoch": 1.4910146530273707,
      "grad_norm": 0.42289477586746216,
      "learning_rate": 3.0386061169531964e-06,
      "loss": 0.4423,
      "step": 48537
    },
    {
      "epoch": 1.4910453721623198,
      "grad_norm": 0.39317241311073303,
      "learning_rate": 3.038259177071118e-06,
      "loss": 0.3644,
      "step": 48538
    },
    {
      "epoch": 1.4910760912972691,
      "grad_norm": 0.398485392332077,
      "learning_rate": 3.037912253448678e-06,
      "loss": 0.4594,
      "step": 48539
    },
    {
      "epoch": 1.4911068104322183,
      "grad_norm": 0.4514101445674896,
      "learning_rate": 3.037565346086677e-06,
      "loss": 0.4065,
      "step": 48540
    },
    {
      "epoch": 1.4911375295671674,
      "grad_norm": 0.4343824088573456,
      "learning_rate": 3.0372184549859317e-06,
      "loss": 0.4488,
      "step": 48541
    },
    {
      "epoch": 1.4911682487021165,
      "grad_norm": 0.4438244700431824,
      "learning_rate": 3.036871580147247e-06,
      "loss": 0.4805,
      "step": 48542
    },
    {
      "epoch": 1.4911989678370656,
      "grad_norm": 0.4678540825843811,
      "learning_rate": 3.0365247215714333e-06,
      "loss": 0.4981,
      "step": 48543
    },
    {
      "epoch": 1.491229686972015,
      "grad_norm": 0.38171228766441345,
      "learning_rate": 3.036177879259303e-06,
      "loss": 0.4959,
      "step": 48544
    },
    {
      "epoch": 1.491260406106964,
      "grad_norm": 0.40151605010032654,
      "learning_rate": 3.0358310532116686e-06,
      "loss": 0.5499,
      "step": 48545
    },
    {
      "epoch": 1.4912911252419132,
      "grad_norm": 0.4091804325580597,
      "learning_rate": 3.035484243429334e-06,
      "loss": 0.3924,
      "step": 48546
    },
    {
      "epoch": 1.4913218443768623,
      "grad_norm": 0.4171963036060333,
      "learning_rate": 3.0351374499131127e-06,
      "loss": 0.3836,
      "step": 48547
    },
    {
      "epoch": 1.4913525635118114,
      "grad_norm": 0.4020169973373413,
      "learning_rate": 3.0347906726638144e-06,
      "loss": 0.464,
      "step": 48548
    },
    {
      "epoch": 1.4913832826467606,
      "grad_norm": 0.45129522681236267,
      "learning_rate": 3.0344439116822523e-06,
      "loss": 0.5652,
      "step": 48549
    },
    {
      "epoch": 1.49141400178171,
      "grad_norm": 0.46902376413345337,
      "learning_rate": 3.034097166969229e-06,
      "loss": 0.4686,
      "step": 48550
    },
    {
      "epoch": 1.491444720916659,
      "grad_norm": 0.4114673435688019,
      "learning_rate": 3.033750438525559e-06,
      "loss": 0.5237,
      "step": 48551
    },
    {
      "epoch": 1.4914754400516081,
      "grad_norm": 0.41388389468193054,
      "learning_rate": 3.03340372635205e-06,
      "loss": 0.4384,
      "step": 48552
    },
    {
      "epoch": 1.4915061591865573,
      "grad_norm": 0.41154587268829346,
      "learning_rate": 3.033057030449518e-06,
      "loss": 0.4411,
      "step": 48553
    },
    {
      "epoch": 1.4915368783215064,
      "grad_norm": 0.43256258964538574,
      "learning_rate": 3.032710350818764e-06,
      "loss": 0.5457,
      "step": 48554
    },
    {
      "epoch": 1.4915675974564557,
      "grad_norm": 0.4176168739795685,
      "learning_rate": 3.032363687460601e-06,
      "loss": 0.4365,
      "step": 48555
    },
    {
      "epoch": 1.4915983165914048,
      "grad_norm": 0.4125942885875702,
      "learning_rate": 3.03201704037584e-06,
      "loss": 0.5183,
      "step": 48556
    },
    {
      "epoch": 1.491629035726354,
      "grad_norm": 0.4239695072174072,
      "learning_rate": 3.0316704095652893e-06,
      "loss": 0.5045,
      "step": 48557
    },
    {
      "epoch": 1.491659754861303,
      "grad_norm": 0.4236443340778351,
      "learning_rate": 3.0313237950297623e-06,
      "loss": 0.425,
      "step": 48558
    },
    {
      "epoch": 1.4916904739962522,
      "grad_norm": 0.4395184814929962,
      "learning_rate": 3.030977196770062e-06,
      "loss": 0.4137,
      "step": 48559
    },
    {
      "epoch": 1.4917211931312013,
      "grad_norm": 0.42018184065818787,
      "learning_rate": 3.0306306147870013e-06,
      "loss": 0.4802,
      "step": 48560
    },
    {
      "epoch": 1.4917519122661504,
      "grad_norm": 0.4673660695552826,
      "learning_rate": 3.03028404908139e-06,
      "loss": 0.5268,
      "step": 48561
    },
    {
      "epoch": 1.4917826314010998,
      "grad_norm": 0.40040329098701477,
      "learning_rate": 3.0299374996540396e-06,
      "loss": 0.4244,
      "step": 48562
    },
    {
      "epoch": 1.491813350536049,
      "grad_norm": 0.4242017865180969,
      "learning_rate": 3.0295909665057543e-06,
      "loss": 0.5022,
      "step": 48563
    },
    {
      "epoch": 1.491844069670998,
      "grad_norm": 0.41655853390693665,
      "learning_rate": 3.0292444496373486e-06,
      "loss": 0.4882,
      "step": 48564
    },
    {
      "epoch": 1.4918747888059471,
      "grad_norm": 0.4249395430088043,
      "learning_rate": 3.028897949049624e-06,
      "loss": 0.4709,
      "step": 48565
    },
    {
      "epoch": 1.4919055079408965,
      "grad_norm": 0.41077134013175964,
      "learning_rate": 3.0285514647434012e-06,
      "loss": 0.5164,
      "step": 48566
    },
    {
      "epoch": 1.4919362270758456,
      "grad_norm": 0.4425637423992157,
      "learning_rate": 3.0282049967194795e-06,
      "loss": 0.4706,
      "step": 48567
    },
    {
      "epoch": 1.4919669462107947,
      "grad_norm": 0.40634849667549133,
      "learning_rate": 3.0278585449786757e-06,
      "loss": 0.538,
      "step": 48568
    },
    {
      "epoch": 1.4919976653457439,
      "grad_norm": 0.44702985882759094,
      "learning_rate": 3.0275121095217884e-06,
      "loss": 0.4449,
      "step": 48569
    },
    {
      "epoch": 1.492028384480693,
      "grad_norm": 0.45275959372520447,
      "learning_rate": 3.0271656903496394e-06,
      "loss": 0.412,
      "step": 48570
    },
    {
      "epoch": 1.492059103615642,
      "grad_norm": 0.43834397196769714,
      "learning_rate": 3.02681928746303e-06,
      "loss": 0.4378,
      "step": 48571
    },
    {
      "epoch": 1.4920898227505912,
      "grad_norm": 0.39160290360450745,
      "learning_rate": 3.0264729008627735e-06,
      "loss": 0.4522,
      "step": 48572
    },
    {
      "epoch": 1.4921205418855406,
      "grad_norm": 0.43533265590667725,
      "learning_rate": 3.0261265305496736e-06,
      "loss": 0.4817,
      "step": 48573
    },
    {
      "epoch": 1.4921512610204897,
      "grad_norm": 0.4181259572505951,
      "learning_rate": 3.0257801765245387e-06,
      "loss": 0.4579,
      "step": 48574
    },
    {
      "epoch": 1.4921819801554388,
      "grad_norm": 0.44349756836891174,
      "learning_rate": 3.0254338387881875e-06,
      "loss": 0.4631,
      "step": 48575
    },
    {
      "epoch": 1.492212699290388,
      "grad_norm": 0.3819870054721832,
      "learning_rate": 3.0250875173414208e-06,
      "loss": 0.3588,
      "step": 48576
    },
    {
      "epoch": 1.4922434184253373,
      "grad_norm": 0.4163427948951721,
      "learning_rate": 3.0247412121850517e-06,
      "loss": 0.5193,
      "step": 48577
    },
    {
      "epoch": 1.4922741375602864,
      "grad_norm": 0.39003685116767883,
      "learning_rate": 3.0243949233198834e-06,
      "loss": 0.5071,
      "step": 48578
    },
    {
      "epoch": 1.4923048566952355,
      "grad_norm": 0.49302738904953003,
      "learning_rate": 3.024048650746728e-06,
      "loss": 0.5094,
      "step": 48579
    },
    {
      "epoch": 1.4923355758301846,
      "grad_norm": 0.4417443871498108,
      "learning_rate": 3.0237023944663937e-06,
      "loss": 0.4283,
      "step": 48580
    },
    {
      "epoch": 1.4923662949651337,
      "grad_norm": 0.4539543092250824,
      "learning_rate": 3.023356154479693e-06,
      "loss": 0.4824,
      "step": 48581
    },
    {
      "epoch": 1.4923970141000829,
      "grad_norm": 0.47652918100357056,
      "learning_rate": 3.0230099307874284e-06,
      "loss": 0.4829,
      "step": 48582
    },
    {
      "epoch": 1.492427733235032,
      "grad_norm": 0.44105830788612366,
      "learning_rate": 3.022663723390412e-06,
      "loss": 0.5233,
      "step": 48583
    },
    {
      "epoch": 1.4924584523699813,
      "grad_norm": 0.4518689513206482,
      "learning_rate": 3.0223175322894506e-06,
      "loss": 0.4817,
      "step": 48584
    },
    {
      "epoch": 1.4924891715049304,
      "grad_norm": 0.4130328893661499,
      "learning_rate": 3.021971357485358e-06,
      "loss": 0.5468,
      "step": 48585
    },
    {
      "epoch": 1.4925198906398796,
      "grad_norm": 0.4378962218761444,
      "learning_rate": 3.0216251989789348e-06,
      "loss": 0.4941,
      "step": 48586
    },
    {
      "epoch": 1.4925506097748287,
      "grad_norm": 0.40998807549476624,
      "learning_rate": 3.0212790567709936e-06,
      "loss": 0.4561,
      "step": 48587
    },
    {
      "epoch": 1.492581328909778,
      "grad_norm": 0.5211696624755859,
      "learning_rate": 3.0209329308623426e-06,
      "loss": 0.4966,
      "step": 48588
    },
    {
      "epoch": 1.4926120480447271,
      "grad_norm": 0.5430550575256348,
      "learning_rate": 3.0205868212537925e-06,
      "loss": 0.3908,
      "step": 48589
    },
    {
      "epoch": 1.4926427671796763,
      "grad_norm": 0.3971346616744995,
      "learning_rate": 3.0202407279461476e-06,
      "loss": 0.4132,
      "step": 48590
    },
    {
      "epoch": 1.4926734863146254,
      "grad_norm": 0.481818288564682,
      "learning_rate": 3.019894650940217e-06,
      "loss": 0.4427,
      "step": 48591
    },
    {
      "epoch": 1.4927042054495745,
      "grad_norm": 0.4359174072742462,
      "learning_rate": 3.0195485902368104e-06,
      "loss": 0.4355,
      "step": 48592
    },
    {
      "epoch": 1.4927349245845236,
      "grad_norm": 0.4728286564350128,
      "learning_rate": 3.0192025458367348e-06,
      "loss": 0.4548,
      "step": 48593
    },
    {
      "epoch": 1.4927656437194727,
      "grad_norm": 0.41139593720436096,
      "learning_rate": 3.0188565177408037e-06,
      "loss": 0.4858,
      "step": 48594
    },
    {
      "epoch": 1.492796362854422,
      "grad_norm": 0.4272594153881073,
      "learning_rate": 3.0185105059498165e-06,
      "loss": 0.442,
      "step": 48595
    },
    {
      "epoch": 1.4928270819893712,
      "grad_norm": 0.41214877367019653,
      "learning_rate": 3.0181645104645853e-06,
      "loss": 0.5099,
      "step": 48596
    },
    {
      "epoch": 1.4928578011243203,
      "grad_norm": 0.4318372905254364,
      "learning_rate": 3.01781853128592e-06,
      "loss": 0.5138,
      "step": 48597
    },
    {
      "epoch": 1.4928885202592694,
      "grad_norm": 0.4647459089756012,
      "learning_rate": 3.017472568414629e-06,
      "loss": 0.4749,
      "step": 48598
    },
    {
      "epoch": 1.4929192393942188,
      "grad_norm": 0.45015445351600647,
      "learning_rate": 3.017126621851515e-06,
      "loss": 0.4954,
      "step": 48599
    },
    {
      "epoch": 1.492949958529168,
      "grad_norm": 0.4340458810329437,
      "learning_rate": 3.016780691597394e-06,
      "loss": 0.4375,
      "step": 48600
    },
    {
      "epoch": 1.492980677664117,
      "grad_norm": 0.43528804183006287,
      "learning_rate": 3.0164347776530623e-06,
      "loss": 0.4817,
      "step": 48601
    },
    {
      "epoch": 1.4930113967990661,
      "grad_norm": 0.4200591742992401,
      "learning_rate": 3.0160888800193413e-06,
      "loss": 0.4826,
      "step": 48602
    },
    {
      "epoch": 1.4930421159340153,
      "grad_norm": 0.47433334589004517,
      "learning_rate": 3.0157429986970286e-06,
      "loss": 0.4678,
      "step": 48603
    },
    {
      "epoch": 1.4930728350689644,
      "grad_norm": 0.4201808273792267,
      "learning_rate": 3.0153971336869404e-06,
      "loss": 0.4367,
      "step": 48604
    },
    {
      "epoch": 1.4931035542039135,
      "grad_norm": 0.4323626458644867,
      "learning_rate": 3.015051284989876e-06,
      "loss": 0.4057,
      "step": 48605
    },
    {
      "epoch": 1.4931342733388628,
      "grad_norm": 0.4447256326675415,
      "learning_rate": 3.0147054526066475e-06,
      "loss": 0.5469,
      "step": 48606
    },
    {
      "epoch": 1.493164992473812,
      "grad_norm": 0.4680606424808502,
      "learning_rate": 3.0143596365380624e-06,
      "loss": 0.4067,
      "step": 48607
    },
    {
      "epoch": 1.493195711608761,
      "grad_norm": 0.44392314553260803,
      "learning_rate": 3.0140138367849303e-06,
      "loss": 0.5417,
      "step": 48608
    },
    {
      "epoch": 1.4932264307437102,
      "grad_norm": 0.4623536765575409,
      "learning_rate": 3.0136680533480544e-06,
      "loss": 0.4303,
      "step": 48609
    },
    {
      "epoch": 1.4932571498786595,
      "grad_norm": 0.3894933760166168,
      "learning_rate": 3.0133222862282417e-06,
      "loss": 0.4128,
      "step": 48610
    },
    {
      "epoch": 1.4932878690136087,
      "grad_norm": 0.45474982261657715,
      "learning_rate": 3.0129765354263095e-06,
      "loss": 0.4964,
      "step": 48611
    },
    {
      "epoch": 1.4933185881485578,
      "grad_norm": 0.47302255034446716,
      "learning_rate": 3.012630800943055e-06,
      "loss": 0.5028,
      "step": 48612
    },
    {
      "epoch": 1.493349307283507,
      "grad_norm": 0.4478158950805664,
      "learning_rate": 3.0122850827792917e-06,
      "loss": 0.458,
      "step": 48613
    },
    {
      "epoch": 1.493380026418456,
      "grad_norm": 0.41416946053504944,
      "learning_rate": 3.0119393809358224e-06,
      "loss": 0.4713,
      "step": 48614
    },
    {
      "epoch": 1.4934107455534051,
      "grad_norm": 0.44300952553749084,
      "learning_rate": 3.011593695413456e-06,
      "loss": 0.4747,
      "step": 48615
    },
    {
      "epoch": 1.4934414646883543,
      "grad_norm": 0.4069468379020691,
      "learning_rate": 3.0112480262130004e-06,
      "loss": 0.497,
      "step": 48616
    },
    {
      "epoch": 1.4934721838233036,
      "grad_norm": 0.42822256684303284,
      "learning_rate": 3.010902373335267e-06,
      "loss": 0.4461,
      "step": 48617
    },
    {
      "epoch": 1.4935029029582527,
      "grad_norm": 0.4267165958881378,
      "learning_rate": 3.010556736781056e-06,
      "loss": 0.4192,
      "step": 48618
    },
    {
      "epoch": 1.4935336220932018,
      "grad_norm": 0.4469969868659973,
      "learning_rate": 3.0102111165511784e-06,
      "loss": 0.4625,
      "step": 48619
    },
    {
      "epoch": 1.493564341228151,
      "grad_norm": 0.37422969937324524,
      "learning_rate": 3.0098655126464395e-06,
      "loss": 0.4411,
      "step": 48620
    },
    {
      "epoch": 1.4935950603631003,
      "grad_norm": 0.46929556131362915,
      "learning_rate": 3.009519925067652e-06,
      "loss": 0.4917,
      "step": 48621
    },
    {
      "epoch": 1.4936257794980494,
      "grad_norm": 0.4321785271167755,
      "learning_rate": 3.0091743538156148e-06,
      "loss": 0.4498,
      "step": 48622
    },
    {
      "epoch": 1.4936564986329985,
      "grad_norm": 0.42159613966941833,
      "learning_rate": 3.00882879889114e-06,
      "loss": 0.4144,
      "step": 48623
    },
    {
      "epoch": 1.4936872177679477,
      "grad_norm": 0.43049076199531555,
      "learning_rate": 3.008483260295034e-06,
      "loss": 0.4427,
      "step": 48624
    },
    {
      "epoch": 1.4937179369028968,
      "grad_norm": 0.41847971081733704,
      "learning_rate": 3.008137738028106e-06,
      "loss": 0.4505,
      "step": 48625
    },
    {
      "epoch": 1.493748656037846,
      "grad_norm": 0.39445239305496216,
      "learning_rate": 3.0077922320911577e-06,
      "loss": 0.4361,
      "step": 48626
    },
    {
      "epoch": 1.493779375172795,
      "grad_norm": 0.42286011576652527,
      "learning_rate": 3.0074467424850027e-06,
      "loss": 0.4097,
      "step": 48627
    },
    {
      "epoch": 1.4938100943077444,
      "grad_norm": 0.4292412996292114,
      "learning_rate": 3.0071012692104375e-06,
      "loss": 0.4441,
      "step": 48628
    },
    {
      "epoch": 1.4938408134426935,
      "grad_norm": 0.39898526668548584,
      "learning_rate": 3.0067558122682794e-06,
      "loss": 0.4825,
      "step": 48629
    },
    {
      "epoch": 1.4938715325776426,
      "grad_norm": 0.4308124780654907,
      "learning_rate": 3.006410371659334e-06,
      "loss": 0.5086,
      "step": 48630
    },
    {
      "epoch": 1.4939022517125917,
      "grad_norm": 0.4106904864311218,
      "learning_rate": 3.006064947384403e-06,
      "loss": 0.5067,
      "step": 48631
    },
    {
      "epoch": 1.493932970847541,
      "grad_norm": 0.435740202665329,
      "learning_rate": 3.005719539444295e-06,
      "loss": 0.4396,
      "step": 48632
    },
    {
      "epoch": 1.4939636899824902,
      "grad_norm": 0.4736446142196655,
      "learning_rate": 3.005374147839817e-06,
      "loss": 0.4417,
      "step": 48633
    },
    {
      "epoch": 1.4939944091174393,
      "grad_norm": 0.5309832692146301,
      "learning_rate": 3.005028772571781e-06,
      "loss": 0.5289,
      "step": 48634
    },
    {
      "epoch": 1.4940251282523884,
      "grad_norm": 0.39348673820495605,
      "learning_rate": 3.0046834136409842e-06,
      "loss": 0.4286,
      "step": 48635
    },
    {
      "epoch": 1.4940558473873375,
      "grad_norm": 0.4324422776699066,
      "learning_rate": 3.004338071048242e-06,
      "loss": 0.4968,
      "step": 48636
    },
    {
      "epoch": 1.4940865665222867,
      "grad_norm": 0.4628080725669861,
      "learning_rate": 3.0039927447943495e-06,
      "loss": 0.4423,
      "step": 48637
    },
    {
      "epoch": 1.4941172856572358,
      "grad_norm": 0.40170398354530334,
      "learning_rate": 3.003647434880128e-06,
      "loss": 0.4015,
      "step": 48638
    },
    {
      "epoch": 1.4941480047921851,
      "grad_norm": 0.4135306775569916,
      "learning_rate": 3.0033021413063724e-06,
      "loss": 0.3996,
      "step": 48639
    },
    {
      "epoch": 1.4941787239271342,
      "grad_norm": 0.4694088399410248,
      "learning_rate": 3.002956864073897e-06,
      "loss": 0.4785,
      "step": 48640
    },
    {
      "epoch": 1.4942094430620834,
      "grad_norm": 0.4176383316516876,
      "learning_rate": 3.0026116031835005e-06,
      "loss": 0.4347,
      "step": 48641
    },
    {
      "epoch": 1.4942401621970325,
      "grad_norm": 0.47404009103775024,
      "learning_rate": 3.0022663586359945e-06,
      "loss": 0.5327,
      "step": 48642
    },
    {
      "epoch": 1.4942708813319818,
      "grad_norm": 0.4170047342777252,
      "learning_rate": 3.001921130432184e-06,
      "loss": 0.4016,
      "step": 48643
    },
    {
      "epoch": 1.494301600466931,
      "grad_norm": 0.5277335047721863,
      "learning_rate": 3.0015759185728775e-06,
      "loss": 0.3819,
      "step": 48644
    },
    {
      "epoch": 1.49433231960188,
      "grad_norm": 0.40665146708488464,
      "learning_rate": 3.0012307230588767e-06,
      "loss": 0.4789,
      "step": 48645
    },
    {
      "epoch": 1.4943630387368292,
      "grad_norm": 0.4368394613265991,
      "learning_rate": 3.000885543890991e-06,
      "loss": 0.4879,
      "step": 48646
    },
    {
      "epoch": 1.4943937578717783,
      "grad_norm": 0.43492624163627625,
      "learning_rate": 3.0005403810700252e-06,
      "loss": 0.4509,
      "step": 48647
    },
    {
      "epoch": 1.4944244770067274,
      "grad_norm": 0.40099000930786133,
      "learning_rate": 3.0001952345967868e-06,
      "loss": 0.3799,
      "step": 48648
    },
    {
      "epoch": 1.4944551961416765,
      "grad_norm": 0.48582586646080017,
      "learning_rate": 2.999850104472084e-06,
      "loss": 0.5027,
      "step": 48649
    },
    {
      "epoch": 1.4944859152766259,
      "grad_norm": 0.44789251685142517,
      "learning_rate": 2.9995049906967167e-06,
      "loss": 0.4996,
      "step": 48650
    },
    {
      "epoch": 1.494516634411575,
      "grad_norm": 0.4198991060256958,
      "learning_rate": 2.999159893271495e-06,
      "loss": 0.455,
      "step": 48651
    },
    {
      "epoch": 1.4945473535465241,
      "grad_norm": 0.4486773908138275,
      "learning_rate": 2.998814812197224e-06,
      "loss": 0.4963,
      "step": 48652
    },
    {
      "epoch": 1.4945780726814732,
      "grad_norm": 0.4502972662448883,
      "learning_rate": 2.9984697474747126e-06,
      "loss": 0.4905,
      "step": 48653
    },
    {
      "epoch": 1.4946087918164226,
      "grad_norm": 0.4334222376346588,
      "learning_rate": 2.9981246991047607e-06,
      "loss": 0.4339,
      "step": 48654
    },
    {
      "epoch": 1.4946395109513717,
      "grad_norm": 0.45348095893859863,
      "learning_rate": 2.9977796670881786e-06,
      "loss": 0.4324,
      "step": 48655
    },
    {
      "epoch": 1.4946702300863208,
      "grad_norm": 0.40694460272789,
      "learning_rate": 2.997434651425771e-06,
      "loss": 0.483,
      "step": 48656
    },
    {
      "epoch": 1.49470094922127,
      "grad_norm": 0.45938631892204285,
      "learning_rate": 2.997089652118347e-06,
      "loss": 0.459,
      "step": 48657
    },
    {
      "epoch": 1.494731668356219,
      "grad_norm": 0.46443992853164673,
      "learning_rate": 2.9967446691667056e-06,
      "loss": 0.4759,
      "step": 48658
    },
    {
      "epoch": 1.4947623874911682,
      "grad_norm": 0.41374555230140686,
      "learning_rate": 2.9963997025716564e-06,
      "loss": 0.476,
      "step": 48659
    },
    {
      "epoch": 1.4947931066261173,
      "grad_norm": 0.42309874296188354,
      "learning_rate": 2.9960547523340043e-06,
      "loss": 0.5328,
      "step": 48660
    },
    {
      "epoch": 1.4948238257610666,
      "grad_norm": 0.41059237718582153,
      "learning_rate": 2.9957098184545596e-06,
      "loss": 0.4189,
      "step": 48661
    },
    {
      "epoch": 1.4948545448960158,
      "grad_norm": 0.4292497932910919,
      "learning_rate": 2.99536490093412e-06,
      "loss": 0.4255,
      "step": 48662
    },
    {
      "epoch": 1.4948852640309649,
      "grad_norm": 0.4320763349533081,
      "learning_rate": 2.9950199997734986e-06,
      "loss": 0.4394,
      "step": 48663
    },
    {
      "epoch": 1.494915983165914,
      "grad_norm": 0.41834786534309387,
      "learning_rate": 2.99467511497349e-06,
      "loss": 0.446,
      "step": 48664
    },
    {
      "epoch": 1.4949467023008631,
      "grad_norm": 0.4491298198699951,
      "learning_rate": 2.994330246534911e-06,
      "loss": 0.4934,
      "step": 48665
    },
    {
      "epoch": 1.4949774214358125,
      "grad_norm": 0.4272618293762207,
      "learning_rate": 2.9939853944585652e-06,
      "loss": 0.5075,
      "step": 48666
    },
    {
      "epoch": 1.4950081405707616,
      "grad_norm": 0.4021192789077759,
      "learning_rate": 2.9936405587452534e-06,
      "loss": 0.5159,
      "step": 48667
    },
    {
      "epoch": 1.4950388597057107,
      "grad_norm": 0.4115458130836487,
      "learning_rate": 2.9932957393957864e-06,
      "loss": 0.5352,
      "step": 48668
    },
    {
      "epoch": 1.4950695788406598,
      "grad_norm": 0.46743088960647583,
      "learning_rate": 2.99295093641096e-06,
      "loss": 0.4865,
      "step": 48669
    },
    {
      "epoch": 1.495100297975609,
      "grad_norm": 0.4558713138103485,
      "learning_rate": 2.9926061497915926e-06,
      "loss": 0.4794,
      "step": 48670
    },
    {
      "epoch": 1.495131017110558,
      "grad_norm": 0.41000068187713623,
      "learning_rate": 2.992261379538479e-06,
      "loss": 0.3508,
      "step": 48671
    },
    {
      "epoch": 1.4951617362455072,
      "grad_norm": 0.4034136235713959,
      "learning_rate": 2.9919166256524324e-06,
      "loss": 0.4457,
      "step": 48672
    },
    {
      "epoch": 1.4951924553804565,
      "grad_norm": 0.4129490852355957,
      "learning_rate": 2.9915718881342483e-06,
      "loss": 0.5025,
      "step": 48673
    },
    {
      "epoch": 1.4952231745154057,
      "grad_norm": 0.3879713714122772,
      "learning_rate": 2.9912271669847426e-06,
      "loss": 0.3964,
      "step": 48674
    },
    {
      "epoch": 1.4952538936503548,
      "grad_norm": 0.4485117495059967,
      "learning_rate": 2.9908824622047128e-06,
      "loss": 0.4863,
      "step": 48675
    },
    {
      "epoch": 1.495284612785304,
      "grad_norm": 0.4452667832374573,
      "learning_rate": 2.9905377737949693e-06,
      "loss": 0.4255,
      "step": 48676
    },
    {
      "epoch": 1.4953153319202532,
      "grad_norm": 0.4943910241127014,
      "learning_rate": 2.990193101756311e-06,
      "loss": 0.4989,
      "step": 48677
    },
    {
      "epoch": 1.4953460510552024,
      "grad_norm": 0.4510217607021332,
      "learning_rate": 2.989848446089546e-06,
      "loss": 0.3659,
      "step": 48678
    },
    {
      "epoch": 1.4953767701901515,
      "grad_norm": 0.4434300363063812,
      "learning_rate": 2.989503806795481e-06,
      "loss": 0.4361,
      "step": 48679
    },
    {
      "epoch": 1.4954074893251006,
      "grad_norm": 0.3891525864601135,
      "learning_rate": 2.989159183874921e-06,
      "loss": 0.4134,
      "step": 48680
    },
    {
      "epoch": 1.4954382084600497,
      "grad_norm": 0.4109804034233093,
      "learning_rate": 2.988814577328667e-06,
      "loss": 0.4652,
      "step": 48681
    },
    {
      "epoch": 1.4954689275949988,
      "grad_norm": 0.4461570084095001,
      "learning_rate": 2.988469987157526e-06,
      "loss": 0.4988,
      "step": 48682
    },
    {
      "epoch": 1.495499646729948,
      "grad_norm": 0.4578239321708679,
      "learning_rate": 2.988125413362304e-06,
      "loss": 0.5225,
      "step": 48683
    },
    {
      "epoch": 1.4955303658648973,
      "grad_norm": 0.4181232154369354,
      "learning_rate": 2.9877808559438036e-06,
      "loss": 0.5036,
      "step": 48684
    },
    {
      "epoch": 1.4955610849998464,
      "grad_norm": 0.40848508477211,
      "learning_rate": 2.987436314902834e-06,
      "loss": 0.4664,
      "step": 48685
    },
    {
      "epoch": 1.4955918041347955,
      "grad_norm": 0.42268261313438416,
      "learning_rate": 2.9870917902401942e-06,
      "loss": 0.4725,
      "step": 48686
    },
    {
      "epoch": 1.4956225232697447,
      "grad_norm": 0.4729574918746948,
      "learning_rate": 2.986747281956691e-06,
      "loss": 0.4284,
      "step": 48687
    },
    {
      "epoch": 1.495653242404694,
      "grad_norm": 0.490337073802948,
      "learning_rate": 2.986402790053129e-06,
      "loss": 0.5021,
      "step": 48688
    },
    {
      "epoch": 1.4956839615396431,
      "grad_norm": 0.46363380551338196,
      "learning_rate": 2.9860583145303166e-06,
      "loss": 0.4531,
      "step": 48689
    },
    {
      "epoch": 1.4957146806745922,
      "grad_norm": 0.4127749800682068,
      "learning_rate": 2.985713855389052e-06,
      "loss": 0.466,
      "step": 48690
    },
    {
      "epoch": 1.4957453998095414,
      "grad_norm": 0.43908917903900146,
      "learning_rate": 2.9853694126301415e-06,
      "loss": 0.5107,
      "step": 48691
    },
    {
      "epoch": 1.4957761189444905,
      "grad_norm": 0.42516258358955383,
      "learning_rate": 2.985024986254391e-06,
      "loss": 0.4621,
      "step": 48692
    },
    {
      "epoch": 1.4958068380794396,
      "grad_norm": 0.694532036781311,
      "learning_rate": 2.9846805762626084e-06,
      "loss": 0.5342,
      "step": 48693
    },
    {
      "epoch": 1.4958375572143887,
      "grad_norm": 0.4028613865375519,
      "learning_rate": 2.9843361826555905e-06,
      "loss": 0.3909,
      "step": 48694
    },
    {
      "epoch": 1.495868276349338,
      "grad_norm": 0.37462952733039856,
      "learning_rate": 2.9839918054341454e-06,
      "loss": 0.4742,
      "step": 48695
    },
    {
      "epoch": 1.4958989954842872,
      "grad_norm": 0.4384169578552246,
      "learning_rate": 2.9836474445990783e-06,
      "loss": 0.498,
      "step": 48696
    },
    {
      "epoch": 1.4959297146192363,
      "grad_norm": 0.43185722827911377,
      "learning_rate": 2.9833031001511946e-06,
      "loss": 0.4604,
      "step": 48697
    },
    {
      "epoch": 1.4959604337541854,
      "grad_norm": 0.4117773175239563,
      "learning_rate": 2.9829587720912932e-06,
      "loss": 0.4666,
      "step": 48698
    },
    {
      "epoch": 1.4959911528891348,
      "grad_norm": 0.5007755756378174,
      "learning_rate": 2.9826144604201855e-06,
      "loss": 0.4255,
      "step": 48699
    },
    {
      "epoch": 1.4960218720240839,
      "grad_norm": 0.41298606991767883,
      "learning_rate": 2.9822701651386664e-06,
      "loss": 0.4551,
      "step": 48700
    },
    {
      "epoch": 1.496052591159033,
      "grad_norm": 0.41779083013534546,
      "learning_rate": 2.9819258862475474e-06,
      "loss": 0.3728,
      "step": 48701
    },
    {
      "epoch": 1.4960833102939821,
      "grad_norm": 0.40614554286003113,
      "learning_rate": 2.9815816237476335e-06,
      "loss": 0.5236,
      "step": 48702
    },
    {
      "epoch": 1.4961140294289312,
      "grad_norm": 0.4149385094642639,
      "learning_rate": 2.981237377639724e-06,
      "loss": 0.4779,
      "step": 48703
    },
    {
      "epoch": 1.4961447485638804,
      "grad_norm": 0.42169275879859924,
      "learning_rate": 2.9808931479246275e-06,
      "loss": 0.4171,
      "step": 48704
    },
    {
      "epoch": 1.4961754676988295,
      "grad_norm": 0.4794537425041199,
      "learning_rate": 2.980548934603138e-06,
      "loss": 0.4123,
      "step": 48705
    },
    {
      "epoch": 1.4962061868337788,
      "grad_norm": 0.4380824565887451,
      "learning_rate": 2.9802047376760733e-06,
      "loss": 0.4552,
      "step": 48706
    },
    {
      "epoch": 1.496236905968728,
      "grad_norm": 0.42366862297058105,
      "learning_rate": 2.9798605571442285e-06,
      "loss": 0.4349,
      "step": 48707
    },
    {
      "epoch": 1.496267625103677,
      "grad_norm": 0.40124937891960144,
      "learning_rate": 2.9795163930084124e-06,
      "loss": 0.4554,
      "step": 48708
    },
    {
      "epoch": 1.4962983442386262,
      "grad_norm": 0.48757901787757874,
      "learning_rate": 2.9791722452694228e-06,
      "loss": 0.4377,
      "step": 48709
    },
    {
      "epoch": 1.4963290633735755,
      "grad_norm": 0.4177521765232086,
      "learning_rate": 2.978828113928066e-06,
      "loss": 0.4345,
      "step": 48710
    },
    {
      "epoch": 1.4963597825085246,
      "grad_norm": 0.45603880286216736,
      "learning_rate": 2.9784839989851477e-06,
      "loss": 0.4431,
      "step": 48711
    },
    {
      "epoch": 1.4963905016434738,
      "grad_norm": 0.425780326128006,
      "learning_rate": 2.9781399004414734e-06,
      "loss": 0.5247,
      "step": 48712
    },
    {
      "epoch": 1.4964212207784229,
      "grad_norm": 0.37720540165901184,
      "learning_rate": 2.9777958182978396e-06,
      "loss": 0.4631,
      "step": 48713
    },
    {
      "epoch": 1.496451939913372,
      "grad_norm": 0.4439745247364044,
      "learning_rate": 2.977451752555055e-06,
      "loss": 0.4973,
      "step": 48714
    },
    {
      "epoch": 1.4964826590483211,
      "grad_norm": 0.4214194118976593,
      "learning_rate": 2.977107703213922e-06,
      "loss": 0.4947,
      "step": 48715
    },
    {
      "epoch": 1.4965133781832702,
      "grad_norm": 0.40720313787460327,
      "learning_rate": 2.9767636702752478e-06,
      "loss": 0.3953,
      "step": 48716
    },
    {
      "epoch": 1.4965440973182196,
      "grad_norm": 0.40974581241607666,
      "learning_rate": 2.9764196537398295e-06,
      "loss": 0.4573,
      "step": 48717
    },
    {
      "epoch": 1.4965748164531687,
      "grad_norm": 0.4033389091491699,
      "learning_rate": 2.9760756536084736e-06,
      "loss": 0.4923,
      "step": 48718
    },
    {
      "epoch": 1.4966055355881178,
      "grad_norm": 0.3670641779899597,
      "learning_rate": 2.9757316698819825e-06,
      "loss": 0.5062,
      "step": 48719
    },
    {
      "epoch": 1.496636254723067,
      "grad_norm": 0.3928927779197693,
      "learning_rate": 2.975387702561161e-06,
      "loss": 0.4376,
      "step": 48720
    },
    {
      "epoch": 1.4966669738580163,
      "grad_norm": 0.4015648663043976,
      "learning_rate": 2.9750437516468167e-06,
      "loss": 0.5375,
      "step": 48721
    },
    {
      "epoch": 1.4966976929929654,
      "grad_norm": 0.3947986662387848,
      "learning_rate": 2.9746998171397432e-06,
      "loss": 0.4683,
      "step": 48722
    },
    {
      "epoch": 1.4967284121279145,
      "grad_norm": 0.4297974407672882,
      "learning_rate": 2.974355899040751e-06,
      "loss": 0.5028,
      "step": 48723
    },
    {
      "epoch": 1.4967591312628636,
      "grad_norm": 0.4456779360771179,
      "learning_rate": 2.97401199735064e-06,
      "loss": 0.5528,
      "step": 48724
    },
    {
      "epoch": 1.4967898503978128,
      "grad_norm": 0.5477045178413391,
      "learning_rate": 2.9736681120702173e-06,
      "loss": 0.4867,
      "step": 48725
    },
    {
      "epoch": 1.4968205695327619,
      "grad_norm": 0.4197830557823181,
      "learning_rate": 2.9733242432002817e-06,
      "loss": 0.4698,
      "step": 48726
    },
    {
      "epoch": 1.496851288667711,
      "grad_norm": 0.45660629868507385,
      "learning_rate": 2.9729803907416366e-06,
      "loss": 0.4868,
      "step": 48727
    },
    {
      "epoch": 1.4968820078026603,
      "grad_norm": 0.4376608431339264,
      "learning_rate": 2.9726365546950875e-06,
      "loss": 0.4772,
      "step": 48728
    },
    {
      "epoch": 1.4969127269376095,
      "grad_norm": 0.4456124007701874,
      "learning_rate": 2.9722927350614394e-06,
      "loss": 0.5573,
      "step": 48729
    },
    {
      "epoch": 1.4969434460725586,
      "grad_norm": 0.4518524706363678,
      "learning_rate": 2.9719489318414896e-06,
      "loss": 0.4657,
      "step": 48730
    },
    {
      "epoch": 1.4969741652075077,
      "grad_norm": 0.4175011217594147,
      "learning_rate": 2.9716051450360463e-06,
      "loss": 0.49,
      "step": 48731
    },
    {
      "epoch": 1.497004884342457,
      "grad_norm": 0.4312763810157776,
      "learning_rate": 2.971261374645905e-06,
      "loss": 0.5006,
      "step": 48732
    },
    {
      "epoch": 1.4970356034774062,
      "grad_norm": 0.44456589221954346,
      "learning_rate": 2.9709176206718794e-06,
      "loss": 0.5224,
      "step": 48733
    },
    {
      "epoch": 1.4970663226123553,
      "grad_norm": 0.40149104595184326,
      "learning_rate": 2.970573883114762e-06,
      "loss": 0.4084,
      "step": 48734
    },
    {
      "epoch": 1.4970970417473044,
      "grad_norm": 0.41548168659210205,
      "learning_rate": 2.9702301619753648e-06,
      "loss": 0.4767,
      "step": 48735
    },
    {
      "epoch": 1.4971277608822535,
      "grad_norm": 0.4404512643814087,
      "learning_rate": 2.9698864572544792e-06,
      "loss": 0.4806,
      "step": 48736
    },
    {
      "epoch": 1.4971584800172026,
      "grad_norm": 0.3878902196884155,
      "learning_rate": 2.9695427689529187e-06,
      "loss": 0.4137,
      "step": 48737
    },
    {
      "epoch": 1.4971891991521518,
      "grad_norm": 0.46853676438331604,
      "learning_rate": 2.9691990970714844e-06,
      "loss": 0.5759,
      "step": 48738
    },
    {
      "epoch": 1.497219918287101,
      "grad_norm": 0.4376048445701599,
      "learning_rate": 2.968855441610974e-06,
      "loss": 0.4536,
      "step": 48739
    },
    {
      "epoch": 1.4972506374220502,
      "grad_norm": 0.456775039434433,
      "learning_rate": 2.968511802572196e-06,
      "loss": 0.4848,
      "step": 48740
    },
    {
      "epoch": 1.4972813565569993,
      "grad_norm": 0.4669620096683502,
      "learning_rate": 2.9681681799559437e-06,
      "loss": 0.4703,
      "step": 48741
    },
    {
      "epoch": 1.4973120756919485,
      "grad_norm": 0.405121386051178,
      "learning_rate": 2.967824573763031e-06,
      "loss": 0.4618,
      "step": 48742
    },
    {
      "epoch": 1.4973427948268978,
      "grad_norm": 0.5256711840629578,
      "learning_rate": 2.967480983994253e-06,
      "loss": 0.4594,
      "step": 48743
    },
    {
      "epoch": 1.497373513961847,
      "grad_norm": 0.43722134828567505,
      "learning_rate": 2.967137410650417e-06,
      "loss": 0.4649,
      "step": 48744
    },
    {
      "epoch": 1.497404233096796,
      "grad_norm": 0.43047353625297546,
      "learning_rate": 2.9667938537323194e-06,
      "loss": 0.5035,
      "step": 48745
    },
    {
      "epoch": 1.4974349522317452,
      "grad_norm": 0.48955270648002625,
      "learning_rate": 2.966450313240766e-06,
      "loss": 0.4641,
      "step": 48746
    },
    {
      "epoch": 1.4974656713666943,
      "grad_norm": 0.4164883494377136,
      "learning_rate": 2.966106789176559e-06,
      "loss": 0.4927,
      "step": 48747
    },
    {
      "epoch": 1.4974963905016434,
      "grad_norm": 0.44031432271003723,
      "learning_rate": 2.9657632815405046e-06,
      "loss": 0.4186,
      "step": 48748
    },
    {
      "epoch": 1.4975271096365925,
      "grad_norm": 0.38767409324645996,
      "learning_rate": 2.965419790333397e-06,
      "loss": 0.4542,
      "step": 48749
    },
    {
      "epoch": 1.4975578287715419,
      "grad_norm": 0.4280693233013153,
      "learning_rate": 2.9650763155560436e-06,
      "loss": 0.4912,
      "step": 48750
    },
    {
      "epoch": 1.497588547906491,
      "grad_norm": 0.4294290542602539,
      "learning_rate": 2.9647328572092458e-06,
      "loss": 0.4987,
      "step": 48751
    },
    {
      "epoch": 1.49761926704144,
      "grad_norm": 0.40652748942375183,
      "learning_rate": 2.9643894152938092e-06,
      "loss": 0.5024,
      "step": 48752
    },
    {
      "epoch": 1.4976499861763892,
      "grad_norm": 0.4156801998615265,
      "learning_rate": 2.964045989810529e-06,
      "loss": 0.5134,
      "step": 48753
    },
    {
      "epoch": 1.4976807053113386,
      "grad_norm": 0.4623951017856598,
      "learning_rate": 2.9637025807602105e-06,
      "loss": 0.5218,
      "step": 48754
    },
    {
      "epoch": 1.4977114244462877,
      "grad_norm": 0.43319693207740784,
      "learning_rate": 2.9633591881436564e-06,
      "loss": 0.4569,
      "step": 48755
    },
    {
      "epoch": 1.4977421435812368,
      "grad_norm": 0.4031290113925934,
      "learning_rate": 2.963015811961668e-06,
      "loss": 0.4899,
      "step": 48756
    },
    {
      "epoch": 1.497772862716186,
      "grad_norm": 0.44111964106559753,
      "learning_rate": 2.9626724522150507e-06,
      "loss": 0.4582,
      "step": 48757
    },
    {
      "epoch": 1.497803581851135,
      "grad_norm": 0.40374839305877686,
      "learning_rate": 2.9623291089046004e-06,
      "loss": 0.5097,
      "step": 48758
    },
    {
      "epoch": 1.4978343009860842,
      "grad_norm": 0.5799208283424377,
      "learning_rate": 2.9619857820311226e-06,
      "loss": 0.5334,
      "step": 48759
    },
    {
      "epoch": 1.4978650201210333,
      "grad_norm": 0.43922412395477295,
      "learning_rate": 2.9616424715954173e-06,
      "loss": 0.4564,
      "step": 48760
    },
    {
      "epoch": 1.4978957392559826,
      "grad_norm": 0.4985881447792053,
      "learning_rate": 2.9612991775982914e-06,
      "loss": 0.5076,
      "step": 48761
    },
    {
      "epoch": 1.4979264583909317,
      "grad_norm": 0.3743612766265869,
      "learning_rate": 2.9609559000405396e-06,
      "loss": 0.4674,
      "step": 48762
    },
    {
      "epoch": 1.4979571775258809,
      "grad_norm": 0.4412378966808319,
      "learning_rate": 2.9606126389229673e-06,
      "loss": 0.5241,
      "step": 48763
    },
    {
      "epoch": 1.49798789666083,
      "grad_norm": 0.4197155237197876,
      "learning_rate": 2.9602693942463756e-06,
      "loss": 0.451,
      "step": 48764
    },
    {
      "epoch": 1.4980186157957793,
      "grad_norm": 0.43793827295303345,
      "learning_rate": 2.9599261660115697e-06,
      "loss": 0.4504,
      "step": 48765
    },
    {
      "epoch": 1.4980493349307284,
      "grad_norm": 0.4138469398021698,
      "learning_rate": 2.9595829542193445e-06,
      "loss": 0.4316,
      "step": 48766
    },
    {
      "epoch": 1.4980800540656776,
      "grad_norm": 0.403178870677948,
      "learning_rate": 2.959239758870508e-06,
      "loss": 0.4189,
      "step": 48767
    },
    {
      "epoch": 1.4981107732006267,
      "grad_norm": 0.4146975874900818,
      "learning_rate": 2.958896579965852e-06,
      "loss": 0.4586,
      "step": 48768
    },
    {
      "epoch": 1.4981414923355758,
      "grad_norm": 0.3836401104927063,
      "learning_rate": 2.9585534175061926e-06,
      "loss": 0.4903,
      "step": 48769
    },
    {
      "epoch": 1.498172211470525,
      "grad_norm": 0.4480888545513153,
      "learning_rate": 2.958210271492319e-06,
      "loss": 0.5035,
      "step": 48770
    },
    {
      "epoch": 1.498202930605474,
      "grad_norm": 0.40137580037117004,
      "learning_rate": 2.9578671419250402e-06,
      "loss": 0.4575,
      "step": 48771
    },
    {
      "epoch": 1.4982336497404234,
      "grad_norm": 0.4011315405368805,
      "learning_rate": 2.9575240288051522e-06,
      "loss": 0.4043,
      "step": 48772
    },
    {
      "epoch": 1.4982643688753725,
      "grad_norm": 0.41631338000297546,
      "learning_rate": 2.9571809321334586e-06,
      "loss": 0.3795,
      "step": 48773
    },
    {
      "epoch": 1.4982950880103216,
      "grad_norm": 0.4506344795227051,
      "learning_rate": 2.95683785191076e-06,
      "loss": 0.4849,
      "step": 48774
    },
    {
      "epoch": 1.4983258071452707,
      "grad_norm": 0.48021912574768066,
      "learning_rate": 2.956494788137859e-06,
      "loss": 0.4501,
      "step": 48775
    },
    {
      "epoch": 1.4983565262802199,
      "grad_norm": 0.3977316915988922,
      "learning_rate": 2.9561517408155593e-06,
      "loss": 0.4509,
      "step": 48776
    },
    {
      "epoch": 1.4983872454151692,
      "grad_norm": 0.44020700454711914,
      "learning_rate": 2.955808709944653e-06,
      "loss": 0.425,
      "step": 48777
    },
    {
      "epoch": 1.4984179645501183,
      "grad_norm": 0.40617629885673523,
      "learning_rate": 2.955465695525954e-06,
      "loss": 0.4013,
      "step": 48778
    },
    {
      "epoch": 1.4984486836850675,
      "grad_norm": 0.41234147548675537,
      "learning_rate": 2.9551226975602534e-06,
      "loss": 0.4186,
      "step": 48779
    },
    {
      "epoch": 1.4984794028200166,
      "grad_norm": 0.4725647270679474,
      "learning_rate": 2.9547797160483594e-06,
      "loss": 0.4939,
      "step": 48780
    },
    {
      "epoch": 1.4985101219549657,
      "grad_norm": 0.41640445590019226,
      "learning_rate": 2.9544367509910655e-06,
      "loss": 0.4787,
      "step": 48781
    },
    {
      "epoch": 1.4985408410899148,
      "grad_norm": 0.398234099149704,
      "learning_rate": 2.9540938023891773e-06,
      "loss": 0.4616,
      "step": 48782
    },
    {
      "epoch": 1.498571560224864,
      "grad_norm": 0.3488723039627075,
      "learning_rate": 2.9537508702434947e-06,
      "loss": 0.417,
      "step": 48783
    },
    {
      "epoch": 1.4986022793598133,
      "grad_norm": 0.46512556076049805,
      "learning_rate": 2.953407954554822e-06,
      "loss": 0.4897,
      "step": 48784
    },
    {
      "epoch": 1.4986329984947624,
      "grad_norm": 0.43733537197113037,
      "learning_rate": 2.953065055323954e-06,
      "loss": 0.4968,
      "step": 48785
    },
    {
      "epoch": 1.4986637176297115,
      "grad_norm": 0.41504156589508057,
      "learning_rate": 2.952722172551695e-06,
      "loss": 0.4916,
      "step": 48786
    },
    {
      "epoch": 1.4986944367646606,
      "grad_norm": 0.44363054633140564,
      "learning_rate": 2.952379306238845e-06,
      "loss": 0.446,
      "step": 48787
    },
    {
      "epoch": 1.49872515589961,
      "grad_norm": 0.4081573188304901,
      "learning_rate": 2.9520364563862093e-06,
      "loss": 0.4586,
      "step": 48788
    },
    {
      "epoch": 1.498755875034559,
      "grad_norm": 0.464724600315094,
      "learning_rate": 2.9516936229945814e-06,
      "loss": 0.5586,
      "step": 48789
    },
    {
      "epoch": 1.4987865941695082,
      "grad_norm": 0.431565523147583,
      "learning_rate": 2.9513508060647657e-06,
      "loss": 0.4639,
      "step": 48790
    },
    {
      "epoch": 1.4988173133044573,
      "grad_norm": 0.4389767050743103,
      "learning_rate": 2.951008005597561e-06,
      "loss": 0.4786,
      "step": 48791
    },
    {
      "epoch": 1.4988480324394065,
      "grad_norm": 0.43618065118789673,
      "learning_rate": 2.9506652215937704e-06,
      "loss": 0.4426,
      "step": 48792
    },
    {
      "epoch": 1.4988787515743556,
      "grad_norm": 0.487199991941452,
      "learning_rate": 2.9503224540541964e-06,
      "loss": 0.3904,
      "step": 48793
    },
    {
      "epoch": 1.4989094707093047,
      "grad_norm": 0.4240356981754303,
      "learning_rate": 2.949979702979634e-06,
      "loss": 0.4534,
      "step": 48794
    },
    {
      "epoch": 1.498940189844254,
      "grad_norm": 0.44885218143463135,
      "learning_rate": 2.949636968370886e-06,
      "loss": 0.4267,
      "step": 48795
    },
    {
      "epoch": 1.4989709089792032,
      "grad_norm": 0.44669488072395325,
      "learning_rate": 2.9492942502287527e-06,
      "loss": 0.5094,
      "step": 48796
    },
    {
      "epoch": 1.4990016281141523,
      "grad_norm": 0.4310682713985443,
      "learning_rate": 2.948951548554039e-06,
      "loss": 0.4531,
      "step": 48797
    },
    {
      "epoch": 1.4990323472491014,
      "grad_norm": 0.4584926664829254,
      "learning_rate": 2.9486088633475373e-06,
      "loss": 0.501,
      "step": 48798
    },
    {
      "epoch": 1.4990630663840507,
      "grad_norm": 0.39561977982521057,
      "learning_rate": 2.9482661946100532e-06,
      "loss": 0.4506,
      "step": 48799
    },
    {
      "epoch": 1.4990937855189999,
      "grad_norm": 0.4367325007915497,
      "learning_rate": 2.9479235423423858e-06,
      "loss": 0.4112,
      "step": 48800
    },
    {
      "epoch": 1.499124504653949,
      "grad_norm": 0.4216107726097107,
      "learning_rate": 2.9475809065453375e-06,
      "loss": 0.4641,
      "step": 48801
    },
    {
      "epoch": 1.499155223788898,
      "grad_norm": 0.45695459842681885,
      "learning_rate": 2.9472382872197047e-06,
      "loss": 0.4506,
      "step": 48802
    },
    {
      "epoch": 1.4991859429238472,
      "grad_norm": 0.4225256145000458,
      "learning_rate": 2.9468956843662923e-06,
      "loss": 0.4348,
      "step": 48803
    },
    {
      "epoch": 1.4992166620587963,
      "grad_norm": 0.4132924973964691,
      "learning_rate": 2.9465530979858903e-06,
      "loss": 0.465,
      "step": 48804
    },
    {
      "epoch": 1.4992473811937455,
      "grad_norm": 0.4065350890159607,
      "learning_rate": 2.946210528079314e-06,
      "loss": 0.4436,
      "step": 48805
    },
    {
      "epoch": 1.4992781003286948,
      "grad_norm": 0.45506706833839417,
      "learning_rate": 2.945867974647352e-06,
      "loss": 0.4238,
      "step": 48806
    },
    {
      "epoch": 1.499308819463644,
      "grad_norm": 0.40822023153305054,
      "learning_rate": 2.9455254376908103e-06,
      "loss": 0.4619,
      "step": 48807
    },
    {
      "epoch": 1.499339538598593,
      "grad_norm": 0.42922866344451904,
      "learning_rate": 2.945182917210484e-06,
      "loss": 0.4343,
      "step": 48808
    },
    {
      "epoch": 1.4993702577335422,
      "grad_norm": 0.3881016969680786,
      "learning_rate": 2.9448404132071763e-06,
      "loss": 0.4492,
      "step": 48809
    },
    {
      "epoch": 1.4994009768684915,
      "grad_norm": 0.47457370162010193,
      "learning_rate": 2.9444979256816853e-06,
      "loss": 0.5158,
      "step": 48810
    },
    {
      "epoch": 1.4994316960034406,
      "grad_norm": 0.47823572158813477,
      "learning_rate": 2.9441554546348128e-06,
      "loss": 0.4631,
      "step": 48811
    },
    {
      "epoch": 1.4994624151383897,
      "grad_norm": 0.382174015045166,
      "learning_rate": 2.9438130000673614e-06,
      "loss": 0.5011,
      "step": 48812
    },
    {
      "epoch": 1.4994931342733389,
      "grad_norm": 0.40601855516433716,
      "learning_rate": 2.943470561980124e-06,
      "loss": 0.4311,
      "step": 48813
    },
    {
      "epoch": 1.499523853408288,
      "grad_norm": 0.45919057726860046,
      "learning_rate": 2.9431281403739043e-06,
      "loss": 0.4418,
      "step": 48814
    },
    {
      "epoch": 1.499554572543237,
      "grad_norm": 0.40617021918296814,
      "learning_rate": 2.9427857352495016e-06,
      "loss": 0.4792,
      "step": 48815
    },
    {
      "epoch": 1.4995852916781862,
      "grad_norm": 0.38725605607032776,
      "learning_rate": 2.9424433466077185e-06,
      "loss": 0.5173,
      "step": 48816
    },
    {
      "epoch": 1.4996160108131356,
      "grad_norm": 0.4787129759788513,
      "learning_rate": 2.942100974449349e-06,
      "loss": 0.4265,
      "step": 48817
    },
    {
      "epoch": 1.4996467299480847,
      "grad_norm": 0.4581146836280823,
      "learning_rate": 2.9417586187751956e-06,
      "loss": 0.4707,
      "step": 48818
    },
    {
      "epoch": 1.4996774490830338,
      "grad_norm": 0.4556785523891449,
      "learning_rate": 2.9414162795860568e-06,
      "loss": 0.3933,
      "step": 48819
    },
    {
      "epoch": 1.499708168217983,
      "grad_norm": 0.4391557276248932,
      "learning_rate": 2.9410739568827384e-06,
      "loss": 0.4348,
      "step": 48820
    },
    {
      "epoch": 1.4997388873529323,
      "grad_norm": 0.41884467005729675,
      "learning_rate": 2.94073165066603e-06,
      "loss": 0.4914,
      "step": 48821
    },
    {
      "epoch": 1.4997696064878814,
      "grad_norm": 0.4289771318435669,
      "learning_rate": 2.940389360936736e-06,
      "loss": 0.4522,
      "step": 48822
    },
    {
      "epoch": 1.4998003256228305,
      "grad_norm": 0.38575443625450134,
      "learning_rate": 2.9400470876956568e-06,
      "loss": 0.4119,
      "step": 48823
    },
    {
      "epoch": 1.4998310447577796,
      "grad_norm": 0.4339918792247772,
      "learning_rate": 2.9397048309435925e-06,
      "loss": 0.4862,
      "step": 48824
    },
    {
      "epoch": 1.4998617638927287,
      "grad_norm": 0.4133918583393097,
      "learning_rate": 2.9393625906813383e-06,
      "loss": 0.5042,
      "step": 48825
    },
    {
      "epoch": 1.4998924830276779,
      "grad_norm": 0.4011411964893341,
      "learning_rate": 2.939020366909696e-06,
      "loss": 0.4558,
      "step": 48826
    },
    {
      "epoch": 1.499923202162627,
      "grad_norm": 0.412514865398407,
      "learning_rate": 2.9386781596294645e-06,
      "loss": 0.4989,
      "step": 48827
    },
    {
      "epoch": 1.4999539212975763,
      "grad_norm": 0.4236289858818054,
      "learning_rate": 2.938335968841447e-06,
      "loss": 0.4202,
      "step": 48828
    },
    {
      "epoch": 1.4999846404325254,
      "grad_norm": 0.4106888771057129,
      "learning_rate": 2.9379937945464356e-06,
      "loss": 0.5253,
      "step": 48829
    },
    {
      "epoch": 1.5000153595674746,
      "grad_norm": 0.40546363592147827,
      "learning_rate": 2.9376516367452325e-06,
      "loss": 0.4339,
      "step": 48830
    },
    {
      "epoch": 1.500046078702424,
      "grad_norm": 0.43074125051498413,
      "learning_rate": 2.9373094954386373e-06,
      "loss": 0.4749,
      "step": 48831
    },
    {
      "epoch": 1.500076797837373,
      "grad_norm": 0.39494743943214417,
      "learning_rate": 2.936967370627448e-06,
      "loss": 0.4702,
      "step": 48832
    },
    {
      "epoch": 1.5001075169723221,
      "grad_norm": 0.4523470103740692,
      "learning_rate": 2.936625262312469e-06,
      "loss": 0.4311,
      "step": 48833
    },
    {
      "epoch": 1.5001382361072713,
      "grad_norm": 0.40860044956207275,
      "learning_rate": 2.9362831704944926e-06,
      "loss": 0.5513,
      "step": 48834
    },
    {
      "epoch": 1.5001689552422204,
      "grad_norm": 0.40419307351112366,
      "learning_rate": 2.9359410951743217e-06,
      "loss": 0.4507,
      "step": 48835
    },
    {
      "epoch": 1.5001996743771695,
      "grad_norm": 0.38957464694976807,
      "learning_rate": 2.9355990363527488e-06,
      "loss": 0.4448,
      "step": 48836
    },
    {
      "epoch": 1.5002303935121186,
      "grad_norm": 0.47765427827835083,
      "learning_rate": 2.935256994030583e-06,
      "loss": 0.4497,
      "step": 48837
    },
    {
      "epoch": 1.5002611126470677,
      "grad_norm": 0.41726160049438477,
      "learning_rate": 2.9349149682086155e-06,
      "loss": 0.5673,
      "step": 48838
    },
    {
      "epoch": 1.5002918317820169,
      "grad_norm": 0.40289875864982605,
      "learning_rate": 2.9345729588876505e-06,
      "loss": 0.4929,
      "step": 48839
    },
    {
      "epoch": 1.5003225509169662,
      "grad_norm": 0.42887166142463684,
      "learning_rate": 2.9342309660684776e-06,
      "loss": 0.4697,
      "step": 48840
    },
    {
      "epoch": 1.5003532700519153,
      "grad_norm": 0.41078200936317444,
      "learning_rate": 2.9338889897519075e-06,
      "loss": 0.4604,
      "step": 48841
    },
    {
      "epoch": 1.5003839891868647,
      "grad_norm": 0.4051130712032318,
      "learning_rate": 2.9335470299387304e-06,
      "loss": 0.6145,
      "step": 48842
    },
    {
      "epoch": 1.5004147083218138,
      "grad_norm": 0.4512467086315155,
      "learning_rate": 2.93320508662975e-06,
      "loss": 0.5504,
      "step": 48843
    },
    {
      "epoch": 1.500445427456763,
      "grad_norm": 0.4611671566963196,
      "learning_rate": 2.9328631598257608e-06,
      "loss": 0.4556,
      "step": 48844
    },
    {
      "epoch": 1.500476146591712,
      "grad_norm": 0.5028576850891113,
      "learning_rate": 2.9325212495275624e-06,
      "loss": 0.4906,
      "step": 48845
    },
    {
      "epoch": 1.5005068657266611,
      "grad_norm": 0.42952579259872437,
      "learning_rate": 2.9321793557359546e-06,
      "loss": 0.4498,
      "step": 48846
    },
    {
      "epoch": 1.5005375848616103,
      "grad_norm": 0.42529717087745667,
      "learning_rate": 2.9318374784517356e-06,
      "loss": 0.4604,
      "step": 48847
    },
    {
      "epoch": 1.5005683039965594,
      "grad_norm": 0.4408751428127289,
      "learning_rate": 2.931495617675707e-06,
      "loss": 0.5112,
      "step": 48848
    },
    {
      "epoch": 1.5005990231315085,
      "grad_norm": 0.4059983789920807,
      "learning_rate": 2.9311537734086603e-06,
      "loss": 0.3972,
      "step": 48849
    },
    {
      "epoch": 1.5006297422664576,
      "grad_norm": 0.4827762544155121,
      "learning_rate": 2.9308119456513984e-06,
      "loss": 0.5037,
      "step": 48850
    },
    {
      "epoch": 1.500660461401407,
      "grad_norm": 0.4324595034122467,
      "learning_rate": 2.9304701344047183e-06,
      "loss": 0.4227,
      "step": 48851
    },
    {
      "epoch": 1.500691180536356,
      "grad_norm": 0.42617401480674744,
      "learning_rate": 2.9301283396694225e-06,
      "loss": 0.4012,
      "step": 48852
    },
    {
      "epoch": 1.5007218996713052,
      "grad_norm": 0.4094671607017517,
      "learning_rate": 2.9297865614463027e-06,
      "loss": 0.3767,
      "step": 48853
    },
    {
      "epoch": 1.5007526188062545,
      "grad_norm": 0.44540756940841675,
      "learning_rate": 2.9294447997361596e-06,
      "loss": 0.5193,
      "step": 48854
    },
    {
      "epoch": 1.5007833379412037,
      "grad_norm": 0.4195752739906311,
      "learning_rate": 2.9291030545397924e-06,
      "loss": 0.4336,
      "step": 48855
    },
    {
      "epoch": 1.5008140570761528,
      "grad_norm": 0.457152783870697,
      "learning_rate": 2.9287613258580016e-06,
      "loss": 0.4625,
      "step": 48856
    },
    {
      "epoch": 1.500844776211102,
      "grad_norm": 0.4209028482437134,
      "learning_rate": 2.92841961369158e-06,
      "loss": 0.4157,
      "step": 48857
    },
    {
      "epoch": 1.500875495346051,
      "grad_norm": 0.41202715039253235,
      "learning_rate": 2.9280779180413277e-06,
      "loss": 0.4055,
      "step": 48858
    },
    {
      "epoch": 1.5009062144810001,
      "grad_norm": 0.4032427966594696,
      "learning_rate": 2.927736238908044e-06,
      "loss": 0.4357,
      "step": 48859
    },
    {
      "epoch": 1.5009369336159493,
      "grad_norm": 0.49695995450019836,
      "learning_rate": 2.9273945762925283e-06,
      "loss": 0.4378,
      "step": 48860
    },
    {
      "epoch": 1.5009676527508984,
      "grad_norm": 0.41700685024261475,
      "learning_rate": 2.927052930195574e-06,
      "loss": 0.428,
      "step": 48861
    },
    {
      "epoch": 1.5009983718858477,
      "grad_norm": 0.41811931133270264,
      "learning_rate": 2.9267113006179815e-06,
      "loss": 0.4261,
      "step": 48862
    },
    {
      "epoch": 1.5010290910207968,
      "grad_norm": 0.4594061076641083,
      "learning_rate": 2.9263696875605498e-06,
      "loss": 0.4671,
      "step": 48863
    },
    {
      "epoch": 1.501059810155746,
      "grad_norm": 0.43739762902259827,
      "learning_rate": 2.9260280910240777e-06,
      "loss": 0.4097,
      "step": 48864
    },
    {
      "epoch": 1.5010905292906953,
      "grad_norm": 0.4438694417476654,
      "learning_rate": 2.925686511009358e-06,
      "loss": 0.471,
      "step": 48865
    },
    {
      "epoch": 1.5011212484256444,
      "grad_norm": 0.4943592846393585,
      "learning_rate": 2.9253449475171914e-06,
      "loss": 0.5257,
      "step": 48866
    },
    {
      "epoch": 1.5011519675605935,
      "grad_norm": 0.5115324258804321,
      "learning_rate": 2.9250034005483763e-06,
      "loss": 0.4079,
      "step": 48867
    },
    {
      "epoch": 1.5011826866955427,
      "grad_norm": 0.5849529504776001,
      "learning_rate": 2.9246618701037087e-06,
      "loss": 0.5284,
      "step": 48868
    },
    {
      "epoch": 1.5012134058304918,
      "grad_norm": 0.4273843467235565,
      "learning_rate": 2.9243203561839915e-06,
      "loss": 0.4757,
      "step": 48869
    },
    {
      "epoch": 1.501244124965441,
      "grad_norm": 0.4855125844478607,
      "learning_rate": 2.9239788587900154e-06,
      "loss": 0.3903,
      "step": 48870
    },
    {
      "epoch": 1.50127484410039,
      "grad_norm": 0.472522109746933,
      "learning_rate": 2.9236373779225834e-06,
      "loss": 0.5045,
      "step": 48871
    },
    {
      "epoch": 1.5013055632353391,
      "grad_norm": 0.5228146910667419,
      "learning_rate": 2.9232959135824846e-06,
      "loss": 0.5084,
      "step": 48872
    },
    {
      "epoch": 1.5013362823702885,
      "grad_norm": 0.3874753415584564,
      "learning_rate": 2.922954465770529e-06,
      "loss": 0.4278,
      "step": 48873
    },
    {
      "epoch": 1.5013670015052376,
      "grad_norm": 0.4219394326210022,
      "learning_rate": 2.9226130344875037e-06,
      "loss": 0.474,
      "step": 48874
    },
    {
      "epoch": 1.5013977206401867,
      "grad_norm": 0.392324298620224,
      "learning_rate": 2.922271619734213e-06,
      "loss": 0.529,
      "step": 48875
    },
    {
      "epoch": 1.501428439775136,
      "grad_norm": 0.41871094703674316,
      "learning_rate": 2.9219302215114454e-06,
      "loss": 0.5374,
      "step": 48876
    },
    {
      "epoch": 1.5014591589100852,
      "grad_norm": 0.4232179522514343,
      "learning_rate": 2.92158883982001e-06,
      "loss": 0.4502,
      "step": 48877
    },
    {
      "epoch": 1.5014898780450343,
      "grad_norm": 0.4217176139354706,
      "learning_rate": 2.9212474746606956e-06,
      "loss": 0.4353,
      "step": 48878
    },
    {
      "epoch": 1.5015205971799834,
      "grad_norm": 0.4528387784957886,
      "learning_rate": 2.9209061260343042e-06,
      "loss": 0.457,
      "step": 48879
    },
    {
      "epoch": 1.5015513163149325,
      "grad_norm": 0.4136821925640106,
      "learning_rate": 2.9205647939416293e-06,
      "loss": 0.3884,
      "step": 48880
    },
    {
      "epoch": 1.5015820354498817,
      "grad_norm": 0.4401170313358307,
      "learning_rate": 2.920223478383468e-06,
      "loss": 0.4474,
      "step": 48881
    },
    {
      "epoch": 1.5016127545848308,
      "grad_norm": 0.4637707471847534,
      "learning_rate": 2.91988217936062e-06,
      "loss": 0.4789,
      "step": 48882
    },
    {
      "epoch": 1.50164347371978,
      "grad_norm": 0.42149925231933594,
      "learning_rate": 2.9195408968738825e-06,
      "loss": 0.4054,
      "step": 48883
    },
    {
      "epoch": 1.5016741928547293,
      "grad_norm": 0.37904947996139526,
      "learning_rate": 2.9191996309240546e-06,
      "loss": 0.3719,
      "step": 48884
    },
    {
      "epoch": 1.5017049119896784,
      "grad_norm": 0.44682201743125916,
      "learning_rate": 2.9188583815119266e-06,
      "loss": 0.4245,
      "step": 48885
    },
    {
      "epoch": 1.5017356311246275,
      "grad_norm": 0.43546271324157715,
      "learning_rate": 2.9185171486383004e-06,
      "loss": 0.4711,
      "step": 48886
    },
    {
      "epoch": 1.5017663502595768,
      "grad_norm": 0.4031427502632141,
      "learning_rate": 2.9181759323039703e-06,
      "loss": 0.4714,
      "step": 48887
    },
    {
      "epoch": 1.501797069394526,
      "grad_norm": 0.45654916763305664,
      "learning_rate": 2.917834732509739e-06,
      "loss": 0.5039,
      "step": 48888
    },
    {
      "epoch": 1.501827788529475,
      "grad_norm": 0.4147964119911194,
      "learning_rate": 2.9174935492563963e-06,
      "loss": 0.4278,
      "step": 48889
    },
    {
      "epoch": 1.5018585076644242,
      "grad_norm": 0.43108388781547546,
      "learning_rate": 2.917152382544742e-06,
      "loss": 0.4643,
      "step": 48890
    },
    {
      "epoch": 1.5018892267993733,
      "grad_norm": 0.3912968337535858,
      "learning_rate": 2.9168112323755726e-06,
      "loss": 0.4782,
      "step": 48891
    },
    {
      "epoch": 1.5019199459343224,
      "grad_norm": 0.5585345029830933,
      "learning_rate": 2.9164700987496895e-06,
      "loss": 0.4399,
      "step": 48892
    },
    {
      "epoch": 1.5019506650692716,
      "grad_norm": 0.4630407392978668,
      "learning_rate": 2.9161289816678807e-06,
      "loss": 0.4491,
      "step": 48893
    },
    {
      "epoch": 1.5019813842042207,
      "grad_norm": 0.4194595515727997,
      "learning_rate": 2.915787881130948e-06,
      "loss": 0.5613,
      "step": 48894
    },
    {
      "epoch": 1.50201210333917,
      "grad_norm": 0.641301155090332,
      "learning_rate": 2.915446797139687e-06,
      "loss": 0.4755,
      "step": 48895
    },
    {
      "epoch": 1.5020428224741191,
      "grad_norm": 0.39305567741394043,
      "learning_rate": 2.9151057296948992e-06,
      "loss": 0.5062,
      "step": 48896
    },
    {
      "epoch": 1.5020735416090683,
      "grad_norm": 0.4490240812301636,
      "learning_rate": 2.9147646787973727e-06,
      "loss": 0.3942,
      "step": 48897
    },
    {
      "epoch": 1.5021042607440176,
      "grad_norm": 0.4165615141391754,
      "learning_rate": 2.914423644447908e-06,
      "loss": 0.4615,
      "step": 48898
    },
    {
      "epoch": 1.5021349798789667,
      "grad_norm": 6.465775966644287,
      "learning_rate": 2.914082626647302e-06,
      "loss": 0.4725,
      "step": 48899
    },
    {
      "epoch": 1.5021656990139158,
      "grad_norm": 0.4226536154747009,
      "learning_rate": 2.9137416253963537e-06,
      "loss": 0.4674,
      "step": 48900
    },
    {
      "epoch": 1.502196418148865,
      "grad_norm": 0.4375269114971161,
      "learning_rate": 2.9134006406958538e-06,
      "loss": 0.4192,
      "step": 48901
    },
    {
      "epoch": 1.502227137283814,
      "grad_norm": 0.40707075595855713,
      "learning_rate": 2.913059672546602e-06,
      "loss": 0.5067,
      "step": 48902
    },
    {
      "epoch": 1.5022578564187632,
      "grad_norm": 0.46532338857650757,
      "learning_rate": 2.9127187209493933e-06,
      "loss": 0.5818,
      "step": 48903
    },
    {
      "epoch": 1.5022885755537123,
      "grad_norm": 0.42449048161506653,
      "learning_rate": 2.9123777859050264e-06,
      "loss": 0.5637,
      "step": 48904
    },
    {
      "epoch": 1.5023192946886614,
      "grad_norm": 0.44034650921821594,
      "learning_rate": 2.9120368674142985e-06,
      "loss": 0.5067,
      "step": 48905
    },
    {
      "epoch": 1.5023500138236108,
      "grad_norm": 0.41725674271583557,
      "learning_rate": 2.911695965478e-06,
      "loss": 0.4341,
      "step": 48906
    },
    {
      "epoch": 1.50238073295856,
      "grad_norm": 0.45710042119026184,
      "learning_rate": 2.9113550800969348e-06,
      "loss": 0.4617,
      "step": 48907
    },
    {
      "epoch": 1.502411452093509,
      "grad_norm": 0.43032294511795044,
      "learning_rate": 2.9110142112718876e-06,
      "loss": 0.4959,
      "step": 48908
    },
    {
      "epoch": 1.5024421712284584,
      "grad_norm": 0.40688350796699524,
      "learning_rate": 2.9106733590036685e-06,
      "loss": 0.5579,
      "step": 48909
    },
    {
      "epoch": 1.5024728903634075,
      "grad_norm": 0.42879047989845276,
      "learning_rate": 2.9103325232930635e-06,
      "loss": 0.5305,
      "step": 48910
    },
    {
      "epoch": 1.5025036094983566,
      "grad_norm": 0.42796099185943604,
      "learning_rate": 2.909991704140875e-06,
      "loss": 0.4927,
      "step": 48911
    },
    {
      "epoch": 1.5025343286333057,
      "grad_norm": 0.39138180017471313,
      "learning_rate": 2.9096509015478935e-06,
      "loss": 0.4502,
      "step": 48912
    },
    {
      "epoch": 1.5025650477682548,
      "grad_norm": 0.45098888874053955,
      "learning_rate": 2.9093101155149175e-06,
      "loss": 0.4363,
      "step": 48913
    },
    {
      "epoch": 1.502595766903204,
      "grad_norm": 0.465526282787323,
      "learning_rate": 2.9089693460427425e-06,
      "loss": 0.4976,
      "step": 48914
    },
    {
      "epoch": 1.502626486038153,
      "grad_norm": 0.4661544859409332,
      "learning_rate": 2.908628593132168e-06,
      "loss": 0.5192,
      "step": 48915
    },
    {
      "epoch": 1.5026572051731022,
      "grad_norm": 0.42072850465774536,
      "learning_rate": 2.9082878567839846e-06,
      "loss": 0.5122,
      "step": 48916
    },
    {
      "epoch": 1.5026879243080515,
      "grad_norm": 0.4157538414001465,
      "learning_rate": 2.9079471369989886e-06,
      "loss": 0.4754,
      "step": 48917
    },
    {
      "epoch": 1.5027186434430007,
      "grad_norm": 0.45025232434272766,
      "learning_rate": 2.9076064337779784e-06,
      "loss": 0.485,
      "step": 48918
    },
    {
      "epoch": 1.5027493625779498,
      "grad_norm": 0.43014585971832275,
      "learning_rate": 2.9072657471217513e-06,
      "loss": 0.5385,
      "step": 48919
    },
    {
      "epoch": 1.5027800817128991,
      "grad_norm": 0.4045913517475128,
      "learning_rate": 2.9069250770310974e-06,
      "loss": 0.5286,
      "step": 48920
    },
    {
      "epoch": 1.5028108008478482,
      "grad_norm": 0.417930006980896,
      "learning_rate": 2.906584423506815e-06,
      "loss": 0.5028,
      "step": 48921
    },
    {
      "epoch": 1.5028415199827974,
      "grad_norm": 0.5114063620567322,
      "learning_rate": 2.9062437865497007e-06,
      "loss": 0.4721,
      "step": 48922
    },
    {
      "epoch": 1.5028722391177465,
      "grad_norm": 0.4067085087299347,
      "learning_rate": 2.90590316616055e-06,
      "loss": 0.4818,
      "step": 48923
    },
    {
      "epoch": 1.5029029582526956,
      "grad_norm": 0.41773638129234314,
      "learning_rate": 2.9055625623401597e-06,
      "loss": 0.5274,
      "step": 48924
    },
    {
      "epoch": 1.5029336773876447,
      "grad_norm": 0.45107680559158325,
      "learning_rate": 2.905221975089321e-06,
      "loss": 0.4514,
      "step": 48925
    },
    {
      "epoch": 1.5029643965225938,
      "grad_norm": 0.4023705720901489,
      "learning_rate": 2.9048814044088325e-06,
      "loss": 0.4544,
      "step": 48926
    },
    {
      "epoch": 1.502995115657543,
      "grad_norm": 0.4135036766529083,
      "learning_rate": 2.9045408502994876e-06,
      "loss": 0.5252,
      "step": 48927
    },
    {
      "epoch": 1.503025834792492,
      "grad_norm": 0.416999876499176,
      "learning_rate": 2.9042003127620878e-06,
      "loss": 0.4759,
      "step": 48928
    },
    {
      "epoch": 1.5030565539274414,
      "grad_norm": 0.40562689304351807,
      "learning_rate": 2.9038597917974186e-06,
      "loss": 0.4991,
      "step": 48929
    },
    {
      "epoch": 1.5030872730623905,
      "grad_norm": 0.41480663418769836,
      "learning_rate": 2.9035192874062823e-06,
      "loss": 0.5322,
      "step": 48930
    },
    {
      "epoch": 1.5031179921973399,
      "grad_norm": 0.42537495493888855,
      "learning_rate": 2.9031787995894713e-06,
      "loss": 0.5057,
      "step": 48931
    },
    {
      "epoch": 1.503148711332289,
      "grad_norm": 0.4156567454338074,
      "learning_rate": 2.9028383283477855e-06,
      "loss": 0.4832,
      "step": 48932
    },
    {
      "epoch": 1.5031794304672381,
      "grad_norm": 0.4017907679080963,
      "learning_rate": 2.902497873682013e-06,
      "loss": 0.5219,
      "step": 48933
    },
    {
      "epoch": 1.5032101496021872,
      "grad_norm": 0.46127501130104065,
      "learning_rate": 2.902157435592956e-06,
      "loss": 0.4868,
      "step": 48934
    },
    {
      "epoch": 1.5032408687371364,
      "grad_norm": 0.41419538855552673,
      "learning_rate": 2.9018170140813994e-06,
      "loss": 0.5125,
      "step": 48935
    },
    {
      "epoch": 1.5032715878720855,
      "grad_norm": 0.44924697279930115,
      "learning_rate": 2.9014766091481506e-06,
      "loss": 0.4308,
      "step": 48936
    },
    {
      "epoch": 1.5033023070070346,
      "grad_norm": 0.43232235312461853,
      "learning_rate": 2.9011362207939966e-06,
      "loss": 0.4663,
      "step": 48937
    },
    {
      "epoch": 1.5033330261419837,
      "grad_norm": 0.4096568524837494,
      "learning_rate": 2.900795849019734e-06,
      "loss": 0.4728,
      "step": 48938
    },
    {
      "epoch": 1.5033637452769328,
      "grad_norm": 0.4892653524875641,
      "learning_rate": 2.9004554938261598e-06,
      "loss": 0.4538,
      "step": 48939
    },
    {
      "epoch": 1.5033944644118822,
      "grad_norm": 0.4081293046474457,
      "learning_rate": 2.900115155214066e-06,
      "loss": 0.4089,
      "step": 48940
    },
    {
      "epoch": 1.5034251835468313,
      "grad_norm": 0.40722277760505676,
      "learning_rate": 2.8997748331842536e-06,
      "loss": 0.5105,
      "step": 48941
    },
    {
      "epoch": 1.5034559026817806,
      "grad_norm": 0.48506951332092285,
      "learning_rate": 2.899434527737509e-06,
      "loss": 0.5579,
      "step": 48942
    },
    {
      "epoch": 1.5034866218167298,
      "grad_norm": 0.4113394618034363,
      "learning_rate": 2.8990942388746348e-06,
      "loss": 0.4384,
      "step": 48943
    },
    {
      "epoch": 1.5035173409516789,
      "grad_norm": 0.4039759039878845,
      "learning_rate": 2.8987539665964147e-06,
      "loss": 0.4293,
      "step": 48944
    },
    {
      "epoch": 1.503548060086628,
      "grad_norm": 0.612668514251709,
      "learning_rate": 2.898413710903658e-06,
      "loss": 0.4428,
      "step": 48945
    },
    {
      "epoch": 1.5035787792215771,
      "grad_norm": 0.5051444172859192,
      "learning_rate": 2.898073471797148e-06,
      "loss": 0.4236,
      "step": 48946
    },
    {
      "epoch": 1.5036094983565262,
      "grad_norm": 0.4455242455005646,
      "learning_rate": 2.8977332492776867e-06,
      "loss": 0.4541,
      "step": 48947
    },
    {
      "epoch": 1.5036402174914754,
      "grad_norm": 0.42590388655662537,
      "learning_rate": 2.8973930433460628e-06,
      "loss": 0.4148,
      "step": 48948
    },
    {
      "epoch": 1.5036709366264245,
      "grad_norm": 0.4186161458492279,
      "learning_rate": 2.897052854003073e-06,
      "loss": 0.4999,
      "step": 48949
    },
    {
      "epoch": 1.5037016557613736,
      "grad_norm": 0.42489007115364075,
      "learning_rate": 2.896712681249513e-06,
      "loss": 0.4406,
      "step": 48950
    },
    {
      "epoch": 1.503732374896323,
      "grad_norm": 0.38802894949913025,
      "learning_rate": 2.8963725250861785e-06,
      "loss": 0.3845,
      "step": 48951
    },
    {
      "epoch": 1.503763094031272,
      "grad_norm": 0.4331643283367157,
      "learning_rate": 2.8960323855138593e-06,
      "loss": 0.3861,
      "step": 48952
    },
    {
      "epoch": 1.5037938131662214,
      "grad_norm": 0.44498875737190247,
      "learning_rate": 2.895692262533354e-06,
      "loss": 0.5639,
      "step": 48953
    },
    {
      "epoch": 1.5038245323011705,
      "grad_norm": 0.4528059959411621,
      "learning_rate": 2.8953521561454545e-06,
      "loss": 0.4406,
      "step": 48954
    },
    {
      "epoch": 1.5038552514361196,
      "grad_norm": 0.43054983019828796,
      "learning_rate": 2.8950120663509585e-06,
      "loss": 0.4216,
      "step": 48955
    },
    {
      "epoch": 1.5038859705710688,
      "grad_norm": 0.4442678987979889,
      "learning_rate": 2.894671993150656e-06,
      "loss": 0.5035,
      "step": 48956
    },
    {
      "epoch": 1.5039166897060179,
      "grad_norm": 0.4317984879016876,
      "learning_rate": 2.8943319365453437e-06,
      "loss": 0.4924,
      "step": 48957
    },
    {
      "epoch": 1.503947408840967,
      "grad_norm": 0.405686616897583,
      "learning_rate": 2.893991896535815e-06,
      "loss": 0.4972,
      "step": 48958
    },
    {
      "epoch": 1.5039781279759161,
      "grad_norm": 1.0755680799484253,
      "learning_rate": 2.8936518731228636e-06,
      "loss": 0.3993,
      "step": 48959
    },
    {
      "epoch": 1.5040088471108652,
      "grad_norm": 0.44258156418800354,
      "learning_rate": 2.893311866307289e-06,
      "loss": 0.4135,
      "step": 48960
    },
    {
      "epoch": 1.5040395662458144,
      "grad_norm": 0.4158790707588196,
      "learning_rate": 2.892971876089877e-06,
      "loss": 0.4328,
      "step": 48961
    },
    {
      "epoch": 1.5040702853807637,
      "grad_norm": 0.4405190944671631,
      "learning_rate": 2.8926319024714255e-06,
      "loss": 0.4857,
      "step": 48962
    },
    {
      "epoch": 1.5041010045157128,
      "grad_norm": 0.4340810775756836,
      "learning_rate": 2.8922919454527287e-06,
      "loss": 0.5958,
      "step": 48963
    },
    {
      "epoch": 1.504131723650662,
      "grad_norm": 0.44354119896888733,
      "learning_rate": 2.891952005034584e-06,
      "loss": 0.3972,
      "step": 48964
    },
    {
      "epoch": 1.5041624427856113,
      "grad_norm": 0.4026426374912262,
      "learning_rate": 2.891612081217778e-06,
      "loss": 0.4475,
      "step": 48965
    },
    {
      "epoch": 1.5041931619205604,
      "grad_norm": 0.4648548662662506,
      "learning_rate": 2.891272174003108e-06,
      "loss": 0.4544,
      "step": 48966
    },
    {
      "epoch": 1.5042238810555095,
      "grad_norm": 0.476075679063797,
      "learning_rate": 2.89093228339137e-06,
      "loss": 0.4761,
      "step": 48967
    },
    {
      "epoch": 1.5042546001904586,
      "grad_norm": 0.4755919277667999,
      "learning_rate": 2.890592409383358e-06,
      "loss": 0.5107,
      "step": 48968
    },
    {
      "epoch": 1.5042853193254078,
      "grad_norm": 0.45059219002723694,
      "learning_rate": 2.890252551979861e-06,
      "loss": 0.4981,
      "step": 48969
    },
    {
      "epoch": 1.5043160384603569,
      "grad_norm": 0.48591193556785583,
      "learning_rate": 2.8899127111816794e-06,
      "loss": 0.43,
      "step": 48970
    },
    {
      "epoch": 1.504346757595306,
      "grad_norm": 0.40464937686920166,
      "learning_rate": 2.8895728869895957e-06,
      "loss": 0.4319,
      "step": 48971
    },
    {
      "epoch": 1.5043774767302551,
      "grad_norm": 0.4245835840702057,
      "learning_rate": 2.889233079404419e-06,
      "loss": 0.4292,
      "step": 48972
    },
    {
      "epoch": 1.5044081958652045,
      "grad_norm": 0.4198310077190399,
      "learning_rate": 2.8888932884269306e-06,
      "loss": 0.4322,
      "step": 48973
    },
    {
      "epoch": 1.5044389150001536,
      "grad_norm": 0.4428587257862091,
      "learning_rate": 2.8885535140579323e-06,
      "loss": 0.4746,
      "step": 48974
    },
    {
      "epoch": 1.5044696341351027,
      "grad_norm": 0.39494162797927856,
      "learning_rate": 2.8882137562982103e-06,
      "loss": 0.4608,
      "step": 48975
    },
    {
      "epoch": 1.504500353270052,
      "grad_norm": 0.37934809923171997,
      "learning_rate": 2.8878740151485596e-06,
      "loss": 0.4143,
      "step": 48976
    },
    {
      "epoch": 1.5045310724050012,
      "grad_norm": 0.483871191740036,
      "learning_rate": 2.8875342906097815e-06,
      "loss": 0.5245,
      "step": 48977
    },
    {
      "epoch": 1.5045617915399503,
      "grad_norm": 0.4656183421611786,
      "learning_rate": 2.887194582682661e-06,
      "loss": 0.4942,
      "step": 48978
    },
    {
      "epoch": 1.5045925106748994,
      "grad_norm": 0.4157111346721649,
      "learning_rate": 2.8868548913679962e-06,
      "loss": 0.4775,
      "step": 48979
    },
    {
      "epoch": 1.5046232298098485,
      "grad_norm": 0.46204352378845215,
      "learning_rate": 2.8865152166665734e-06,
      "loss": 0.5078,
      "step": 48980
    },
    {
      "epoch": 1.5046539489447976,
      "grad_norm": 0.4118528366088867,
      "learning_rate": 2.8861755585791974e-06,
      "loss": 0.4691,
      "step": 48981
    },
    {
      "epoch": 1.5046846680797468,
      "grad_norm": 0.44382530450820923,
      "learning_rate": 2.8858359171066517e-06,
      "loss": 0.4533,
      "step": 48982
    },
    {
      "epoch": 1.5047153872146959,
      "grad_norm": 0.5120997428894043,
      "learning_rate": 2.8854962922497365e-06,
      "loss": 0.4458,
      "step": 48983
    },
    {
      "epoch": 1.5047461063496452,
      "grad_norm": 0.4987194538116455,
      "learning_rate": 2.885156684009238e-06,
      "loss": 0.4976,
      "step": 48984
    },
    {
      "epoch": 1.5047768254845943,
      "grad_norm": 0.39893704652786255,
      "learning_rate": 2.884817092385954e-06,
      "loss": 0.4713,
      "step": 48985
    },
    {
      "epoch": 1.5048075446195435,
      "grad_norm": 0.48278751969337463,
      "learning_rate": 2.8844775173806762e-06,
      "loss": 0.4872,
      "step": 48986
    },
    {
      "epoch": 1.5048382637544928,
      "grad_norm": 0.4247002899646759,
      "learning_rate": 2.8841379589941997e-06,
      "loss": 0.4767,
      "step": 48987
    },
    {
      "epoch": 1.504868982889442,
      "grad_norm": 0.44467097520828247,
      "learning_rate": 2.8837984172273147e-06,
      "loss": 0.4787,
      "step": 48988
    },
    {
      "epoch": 1.504899702024391,
      "grad_norm": 0.3710019886493683,
      "learning_rate": 2.883458892080815e-06,
      "loss": 0.4385,
      "step": 48989
    },
    {
      "epoch": 1.5049304211593402,
      "grad_norm": 0.4798312485218048,
      "learning_rate": 2.8831193835554936e-06,
      "loss": 0.5465,
      "step": 48990
    },
    {
      "epoch": 1.5049611402942893,
      "grad_norm": 0.4292333424091339,
      "learning_rate": 2.8827798916521478e-06,
      "loss": 0.5074,
      "step": 48991
    },
    {
      "epoch": 1.5049918594292384,
      "grad_norm": 0.40518200397491455,
      "learning_rate": 2.8824404163715626e-06,
      "loss": 0.4662,
      "step": 48992
    },
    {
      "epoch": 1.5050225785641875,
      "grad_norm": 0.4452616572380066,
      "learning_rate": 2.8821009577145353e-06,
      "loss": 0.4883,
      "step": 48993
    },
    {
      "epoch": 1.5050532976991366,
      "grad_norm": 0.43966853618621826,
      "learning_rate": 2.881761515681858e-06,
      "loss": 0.451,
      "step": 48994
    },
    {
      "epoch": 1.505084016834086,
      "grad_norm": 0.46314412355422974,
      "learning_rate": 2.881422090274325e-06,
      "loss": 0.4852,
      "step": 48995
    },
    {
      "epoch": 1.5051147359690351,
      "grad_norm": 0.41066423058509827,
      "learning_rate": 2.8810826814927297e-06,
      "loss": 0.5081,
      "step": 48996
    },
    {
      "epoch": 1.5051454551039842,
      "grad_norm": 0.4335906207561493,
      "learning_rate": 2.8807432893378607e-06,
      "loss": 0.4164,
      "step": 48997
    },
    {
      "epoch": 1.5051761742389336,
      "grad_norm": 0.42992401123046875,
      "learning_rate": 2.8804039138105124e-06,
      "loss": 0.3768,
      "step": 48998
    },
    {
      "epoch": 1.5052068933738827,
      "grad_norm": 0.45083773136138916,
      "learning_rate": 2.880064554911478e-06,
      "loss": 0.3906,
      "step": 48999
    },
    {
      "epoch": 1.5052376125088318,
      "grad_norm": 0.40710964798927307,
      "learning_rate": 2.879725212641553e-06,
      "loss": 0.4514,
      "step": 49000
    },
    {
      "epoch": 1.505268331643781,
      "grad_norm": 0.4110507369041443,
      "learning_rate": 2.8793858870015247e-06,
      "loss": 0.4223,
      "step": 49001
    },
    {
      "epoch": 1.50529905077873,
      "grad_norm": 0.41817671060562134,
      "learning_rate": 2.879046577992187e-06,
      "loss": 0.4711,
      "step": 49002
    },
    {
      "epoch": 1.5053297699136792,
      "grad_norm": 0.39662909507751465,
      "learning_rate": 2.878707285614334e-06,
      "loss": 0.4654,
      "step": 49003
    },
    {
      "epoch": 1.5053604890486283,
      "grad_norm": 0.4391544461250305,
      "learning_rate": 2.8783680098687603e-06,
      "loss": 0.4748,
      "step": 49004
    },
    {
      "epoch": 1.5053912081835774,
      "grad_norm": 0.4828660786151886,
      "learning_rate": 2.878028750756253e-06,
      "loss": 0.4561,
      "step": 49005
    },
    {
      "epoch": 1.5054219273185268,
      "grad_norm": 0.4361368715763092,
      "learning_rate": 2.87768950827761e-06,
      "loss": 0.5177,
      "step": 49006
    },
    {
      "epoch": 1.5054526464534759,
      "grad_norm": 0.45207419991493225,
      "learning_rate": 2.877350282433614e-06,
      "loss": 0.5485,
      "step": 49007
    },
    {
      "epoch": 1.505483365588425,
      "grad_norm": 0.439819872379303,
      "learning_rate": 2.87701107322507e-06,
      "loss": 0.4166,
      "step": 49008
    },
    {
      "epoch": 1.5055140847233743,
      "grad_norm": 0.42273467779159546,
      "learning_rate": 2.8766718806527604e-06,
      "loss": 0.4625,
      "step": 49009
    },
    {
      "epoch": 1.5055448038583235,
      "grad_norm": 0.4821110963821411,
      "learning_rate": 2.876332704717485e-06,
      "loss": 0.4412,
      "step": 49010
    },
    {
      "epoch": 1.5055755229932726,
      "grad_norm": 0.40762263536453247,
      "learning_rate": 2.8759935454200295e-06,
      "loss": 0.4788,
      "step": 49011
    },
    {
      "epoch": 1.5056062421282217,
      "grad_norm": 0.409768283367157,
      "learning_rate": 2.8756544027611843e-06,
      "loss": 0.4827,
      "step": 49012
    },
    {
      "epoch": 1.5056369612631708,
      "grad_norm": 0.45260366797447205,
      "learning_rate": 2.8753152767417524e-06,
      "loss": 0.3966,
      "step": 49013
    },
    {
      "epoch": 1.50566768039812,
      "grad_norm": 0.3906444311141968,
      "learning_rate": 2.8749761673625166e-06,
      "loss": 0.5015,
      "step": 49014
    },
    {
      "epoch": 1.505698399533069,
      "grad_norm": 0.39677950739860535,
      "learning_rate": 2.8746370746242734e-06,
      "loss": 0.4823,
      "step": 49015
    },
    {
      "epoch": 1.5057291186680182,
      "grad_norm": 0.4446823000907898,
      "learning_rate": 2.874297998527812e-06,
      "loss": 0.4486,
      "step": 49016
    },
    {
      "epoch": 1.5057598378029675,
      "grad_norm": 0.4300829768180847,
      "learning_rate": 2.8739589390739233e-06,
      "loss": 0.5039,
      "step": 49017
    },
    {
      "epoch": 1.5057905569379166,
      "grad_norm": 0.42182624340057373,
      "learning_rate": 2.873619896263402e-06,
      "loss": 0.5284,
      "step": 49018
    },
    {
      "epoch": 1.5058212760728658,
      "grad_norm": 0.40682950615882874,
      "learning_rate": 2.873280870097043e-06,
      "loss": 0.3811,
      "step": 49019
    },
    {
      "epoch": 1.505851995207815,
      "grad_norm": 0.41906824707984924,
      "learning_rate": 2.87294186057563e-06,
      "loss": 0.4696,
      "step": 49020
    },
    {
      "epoch": 1.5058827143427642,
      "grad_norm": 0.3926191031932831,
      "learning_rate": 2.8726028676999585e-06,
      "loss": 0.516,
      "step": 49021
    },
    {
      "epoch": 1.5059134334777133,
      "grad_norm": 0.5314734578132629,
      "learning_rate": 2.8722638914708224e-06,
      "loss": 0.4292,
      "step": 49022
    },
    {
      "epoch": 1.5059441526126625,
      "grad_norm": 0.42827358841896057,
      "learning_rate": 2.871924931889014e-06,
      "loss": 0.4295,
      "step": 49023
    },
    {
      "epoch": 1.5059748717476116,
      "grad_norm": 0.4077228903770447,
      "learning_rate": 2.87158598895532e-06,
      "loss": 0.4667,
      "step": 49024
    },
    {
      "epoch": 1.5060055908825607,
      "grad_norm": 0.4074627757072449,
      "learning_rate": 2.8712470626705337e-06,
      "loss": 0.4541,
      "step": 49025
    },
    {
      "epoch": 1.5060363100175098,
      "grad_norm": 0.451172798871994,
      "learning_rate": 2.870908153035449e-06,
      "loss": 0.4148,
      "step": 49026
    },
    {
      "epoch": 1.506067029152459,
      "grad_norm": 0.4083419144153595,
      "learning_rate": 2.8705692600508584e-06,
      "loss": 0.4816,
      "step": 49027
    },
    {
      "epoch": 1.5060977482874083,
      "grad_norm": 0.40296298265457153,
      "learning_rate": 2.8702303837175494e-06,
      "loss": 0.4391,
      "step": 49028
    },
    {
      "epoch": 1.5061284674223574,
      "grad_norm": 0.45022034645080566,
      "learning_rate": 2.8698915240363136e-06,
      "loss": 0.4326,
      "step": 49029
    },
    {
      "epoch": 1.5061591865573065,
      "grad_norm": 0.40292978286743164,
      "learning_rate": 2.8695526810079454e-06,
      "loss": 0.5301,
      "step": 49030
    },
    {
      "epoch": 1.5061899056922559,
      "grad_norm": 0.44670620560646057,
      "learning_rate": 2.869213854633234e-06,
      "loss": 0.4208,
      "step": 49031
    },
    {
      "epoch": 1.506220624827205,
      "grad_norm": 0.41116371750831604,
      "learning_rate": 2.8688750449129756e-06,
      "loss": 0.4295,
      "step": 49032
    },
    {
      "epoch": 1.506251343962154,
      "grad_norm": 0.45587509870529175,
      "learning_rate": 2.868536251847954e-06,
      "loss": 0.4199,
      "step": 49033
    },
    {
      "epoch": 1.5062820630971032,
      "grad_norm": 0.4611658751964569,
      "learning_rate": 2.868197475438964e-06,
      "loss": 0.5116,
      "step": 49034
    },
    {
      "epoch": 1.5063127822320523,
      "grad_norm": 0.4417842924594879,
      "learning_rate": 2.8678587156867967e-06,
      "loss": 0.5021,
      "step": 49035
    },
    {
      "epoch": 1.5063435013670015,
      "grad_norm": 0.3931772708892822,
      "learning_rate": 2.8675199725922477e-06,
      "loss": 0.4231,
      "step": 49036
    },
    {
      "epoch": 1.5063742205019506,
      "grad_norm": 0.45470109581947327,
      "learning_rate": 2.8671812461560986e-06,
      "loss": 0.444,
      "step": 49037
    },
    {
      "epoch": 1.5064049396368997,
      "grad_norm": 0.4770267903804779,
      "learning_rate": 2.866842536379151e-06,
      "loss": 0.4257,
      "step": 49038
    },
    {
      "epoch": 1.506435658771849,
      "grad_norm": 0.43666717410087585,
      "learning_rate": 2.866503843262184e-06,
      "loss": 0.4964,
      "step": 49039
    },
    {
      "epoch": 1.5064663779067982,
      "grad_norm": 0.45731571316719055,
      "learning_rate": 2.866165166806002e-06,
      "loss": 0.4341,
      "step": 49040
    },
    {
      "epoch": 1.5064970970417473,
      "grad_norm": 0.4156153202056885,
      "learning_rate": 2.8658265070113857e-06,
      "loss": 0.4761,
      "step": 49041
    },
    {
      "epoch": 1.5065278161766966,
      "grad_norm": 0.3999459147453308,
      "learning_rate": 2.865487863879133e-06,
      "loss": 0.4007,
      "step": 49042
    },
    {
      "epoch": 1.5065585353116457,
      "grad_norm": 0.43917617201805115,
      "learning_rate": 2.8651492374100255e-06,
      "loss": 0.392,
      "step": 49043
    },
    {
      "epoch": 1.5065892544465949,
      "grad_norm": 0.4505007565021515,
      "learning_rate": 2.864810627604867e-06,
      "loss": 0.446,
      "step": 49044
    },
    {
      "epoch": 1.506619973581544,
      "grad_norm": 0.4583494961261749,
      "learning_rate": 2.864472034464438e-06,
      "loss": 0.517,
      "step": 49045
    },
    {
      "epoch": 1.506650692716493,
      "grad_norm": 0.4262569546699524,
      "learning_rate": 2.8641334579895365e-06,
      "loss": 0.4994,
      "step": 49046
    },
    {
      "epoch": 1.5066814118514422,
      "grad_norm": 0.4191051423549652,
      "learning_rate": 2.863794898180946e-06,
      "loss": 0.4858,
      "step": 49047
    },
    {
      "epoch": 1.5067121309863913,
      "grad_norm": 0.4274008870124817,
      "learning_rate": 2.8634563550394577e-06,
      "loss": 0.4624,
      "step": 49048
    },
    {
      "epoch": 1.5067428501213405,
      "grad_norm": 0.4020310938358307,
      "learning_rate": 2.8631178285658723e-06,
      "loss": 0.459,
      "step": 49049
    },
    {
      "epoch": 1.5067735692562896,
      "grad_norm": 0.3942665159702301,
      "learning_rate": 2.862779318760971e-06,
      "loss": 0.452,
      "step": 49050
    },
    {
      "epoch": 1.506804288391239,
      "grad_norm": 0.41584348678588867,
      "learning_rate": 2.8624408256255487e-06,
      "loss": 0.4319,
      "step": 49051
    },
    {
      "epoch": 1.506835007526188,
      "grad_norm": 0.5096807479858398,
      "learning_rate": 2.8621023491603917e-06,
      "loss": 0.5315,
      "step": 49052
    },
    {
      "epoch": 1.5068657266611374,
      "grad_norm": 0.4813597500324249,
      "learning_rate": 2.8617638893662935e-06,
      "loss": 0.5046,
      "step": 49053
    },
    {
      "epoch": 1.5068964457960865,
      "grad_norm": 0.4220290184020996,
      "learning_rate": 2.861425446244045e-06,
      "loss": 0.4922,
      "step": 49054
    },
    {
      "epoch": 1.5069271649310356,
      "grad_norm": 0.42655453085899353,
      "learning_rate": 2.8610870197944373e-06,
      "loss": 0.4187,
      "step": 49055
    },
    {
      "epoch": 1.5069578840659847,
      "grad_norm": 0.4212590456008911,
      "learning_rate": 2.860748610018258e-06,
      "loss": 0.4239,
      "step": 49056
    },
    {
      "epoch": 1.5069886032009339,
      "grad_norm": 0.4009961783885956,
      "learning_rate": 2.8604102169162973e-06,
      "loss": 0.4603,
      "step": 49057
    },
    {
      "epoch": 1.507019322335883,
      "grad_norm": 0.42316514253616333,
      "learning_rate": 2.860071840489349e-06,
      "loss": 0.5028,
      "step": 49058
    },
    {
      "epoch": 1.507050041470832,
      "grad_norm": 0.4266810417175293,
      "learning_rate": 2.859733480738204e-06,
      "loss": 0.4398,
      "step": 49059
    },
    {
      "epoch": 1.5070807606057812,
      "grad_norm": 0.432614266872406,
      "learning_rate": 2.8593951376636462e-06,
      "loss": 0.5216,
      "step": 49060
    },
    {
      "epoch": 1.5071114797407303,
      "grad_norm": 0.4066409766674042,
      "learning_rate": 2.85905681126647e-06,
      "loss": 0.5043,
      "step": 49061
    },
    {
      "epoch": 1.5071421988756797,
      "grad_norm": 0.4083939492702484,
      "learning_rate": 2.858718501547466e-06,
      "loss": 0.4867,
      "step": 49062
    },
    {
      "epoch": 1.5071729180106288,
      "grad_norm": 0.4120950400829315,
      "learning_rate": 2.8583802085074263e-06,
      "loss": 0.4919,
      "step": 49063
    },
    {
      "epoch": 1.5072036371455781,
      "grad_norm": 0.4360889196395874,
      "learning_rate": 2.858041932147135e-06,
      "loss": 0.4154,
      "step": 49064
    },
    {
      "epoch": 1.5072343562805273,
      "grad_norm": 0.3965633511543274,
      "learning_rate": 2.8577036724673855e-06,
      "loss": 0.4362,
      "step": 49065
    },
    {
      "epoch": 1.5072650754154764,
      "grad_norm": 0.41479048132896423,
      "learning_rate": 2.857365429468969e-06,
      "loss": 0.4806,
      "step": 49066
    },
    {
      "epoch": 1.5072957945504255,
      "grad_norm": 0.5206706523895264,
      "learning_rate": 2.8570272031526735e-06,
      "loss": 0.4856,
      "step": 49067
    },
    {
      "epoch": 1.5073265136853746,
      "grad_norm": 0.39377260208129883,
      "learning_rate": 2.8566889935192933e-06,
      "loss": 0.4653,
      "step": 49068
    },
    {
      "epoch": 1.5073572328203237,
      "grad_norm": 0.41865864396095276,
      "learning_rate": 2.8563508005696116e-06,
      "loss": 0.5241,
      "step": 49069
    },
    {
      "epoch": 1.5073879519552729,
      "grad_norm": 0.5710474252700806,
      "learning_rate": 2.856012624304422e-06,
      "loss": 0.4272,
      "step": 49070
    },
    {
      "epoch": 1.507418671090222,
      "grad_norm": 0.43613892793655396,
      "learning_rate": 2.8556744647245127e-06,
      "loss": 0.4153,
      "step": 49071
    },
    {
      "epoch": 1.507449390225171,
      "grad_norm": 0.41696181893348694,
      "learning_rate": 2.8553363218306784e-06,
      "loss": 0.5108,
      "step": 49072
    },
    {
      "epoch": 1.5074801093601204,
      "grad_norm": 0.4114032983779907,
      "learning_rate": 2.854998195623702e-06,
      "loss": 0.4472,
      "step": 49073
    },
    {
      "epoch": 1.5075108284950696,
      "grad_norm": 0.398466557264328,
      "learning_rate": 2.8546600861043792e-06,
      "loss": 0.4156,
      "step": 49074
    },
    {
      "epoch": 1.5075415476300187,
      "grad_norm": 0.4500603675842285,
      "learning_rate": 2.8543219932734913e-06,
      "loss": 0.4946,
      "step": 49075
    },
    {
      "epoch": 1.507572266764968,
      "grad_norm": 0.439956933259964,
      "learning_rate": 2.8539839171318383e-06,
      "loss": 0.5072,
      "step": 49076
    },
    {
      "epoch": 1.5076029858999171,
      "grad_norm": 0.40738189220428467,
      "learning_rate": 2.853645857680203e-06,
      "loss": 0.5053,
      "step": 49077
    },
    {
      "epoch": 1.5076337050348663,
      "grad_norm": 0.3920944929122925,
      "learning_rate": 2.8533078149193793e-06,
      "loss": 0.4098,
      "step": 49078
    },
    {
      "epoch": 1.5076644241698154,
      "grad_norm": 0.4461822211742401,
      "learning_rate": 2.852969788850152e-06,
      "loss": 0.4867,
      "step": 49079
    },
    {
      "epoch": 1.5076951433047645,
      "grad_norm": 0.5101287961006165,
      "learning_rate": 2.852631779473313e-06,
      "loss": 0.4858,
      "step": 49080
    },
    {
      "epoch": 1.5077258624397136,
      "grad_norm": 0.40634292364120483,
      "learning_rate": 2.8522937867896506e-06,
      "loss": 0.3711,
      "step": 49081
    },
    {
      "epoch": 1.5077565815746627,
      "grad_norm": 0.424173504114151,
      "learning_rate": 2.851955810799959e-06,
      "loss": 0.4325,
      "step": 49082
    },
    {
      "epoch": 1.5077873007096119,
      "grad_norm": 0.4810546934604645,
      "learning_rate": 2.8516178515050197e-06,
      "loss": 0.514,
      "step": 49083
    },
    {
      "epoch": 1.5078180198445612,
      "grad_norm": 0.4404585063457489,
      "learning_rate": 2.8512799089056244e-06,
      "loss": 0.3978,
      "step": 49084
    },
    {
      "epoch": 1.5078487389795103,
      "grad_norm": 0.4338681101799011,
      "learning_rate": 2.85094198300257e-06,
      "loss": 0.4379,
      "step": 49085
    },
    {
      "epoch": 1.5078794581144594,
      "grad_norm": 0.4021580219268799,
      "learning_rate": 2.8506040737966367e-06,
      "loss": 0.4625,
      "step": 49086
    },
    {
      "epoch": 1.5079101772494088,
      "grad_norm": 0.43260905146598816,
      "learning_rate": 2.8502661812886202e-06,
      "loss": 0.4308,
      "step": 49087
    },
    {
      "epoch": 1.507940896384358,
      "grad_norm": 0.4486876428127289,
      "learning_rate": 2.8499283054793026e-06,
      "loss": 0.4879,
      "step": 49088
    },
    {
      "epoch": 1.507971615519307,
      "grad_norm": 0.42642873525619507,
      "learning_rate": 2.8495904463694767e-06,
      "loss": 0.4753,
      "step": 49089
    },
    {
      "epoch": 1.5080023346542561,
      "grad_norm": 0.42453938722610474,
      "learning_rate": 2.8492526039599324e-06,
      "loss": 0.556,
      "step": 49090
    },
    {
      "epoch": 1.5080330537892053,
      "grad_norm": 0.40885087847709656,
      "learning_rate": 2.8489147782514616e-06,
      "loss": 0.4862,
      "step": 49091
    },
    {
      "epoch": 1.5080637729241544,
      "grad_norm": 0.47769924998283386,
      "learning_rate": 2.848576969244845e-06,
      "loss": 0.522,
      "step": 49092
    },
    {
      "epoch": 1.5080944920591035,
      "grad_norm": 0.47849249839782715,
      "learning_rate": 2.8482391769408778e-06,
      "loss": 0.4468,
      "step": 49093
    },
    {
      "epoch": 1.5081252111940526,
      "grad_norm": 0.40384620428085327,
      "learning_rate": 2.8479014013403473e-06,
      "loss": 0.4764,
      "step": 49094
    },
    {
      "epoch": 1.508155930329002,
      "grad_norm": 0.421056866645813,
      "learning_rate": 2.8475636424440444e-06,
      "loss": 0.4905,
      "step": 49095
    },
    {
      "epoch": 1.508186649463951,
      "grad_norm": 0.43308621644973755,
      "learning_rate": 2.8472259002527546e-06,
      "loss": 0.4599,
      "step": 49096
    },
    {
      "epoch": 1.5082173685989002,
      "grad_norm": 0.43444088101387024,
      "learning_rate": 2.8468881747672673e-06,
      "loss": 0.4326,
      "step": 49097
    },
    {
      "epoch": 1.5082480877338496,
      "grad_norm": 0.41210976243019104,
      "learning_rate": 2.8465504659883724e-06,
      "loss": 0.4367,
      "step": 49098
    },
    {
      "epoch": 1.5082788068687987,
      "grad_norm": 0.4052664041519165,
      "learning_rate": 2.846212773916862e-06,
      "loss": 0.4423,
      "step": 49099
    },
    {
      "epoch": 1.5083095260037478,
      "grad_norm": 0.42655763030052185,
      "learning_rate": 2.8458750985535176e-06,
      "loss": 0.5702,
      "step": 49100
    },
    {
      "epoch": 1.508340245138697,
      "grad_norm": 0.46429216861724854,
      "learning_rate": 2.8455374398991353e-06,
      "loss": 0.4304,
      "step": 49101
    },
    {
      "epoch": 1.508370964273646,
      "grad_norm": 0.44852328300476074,
      "learning_rate": 2.8451997979544934e-06,
      "loss": 0.4889,
      "step": 49102
    },
    {
      "epoch": 1.5084016834085952,
      "grad_norm": 0.39258986711502075,
      "learning_rate": 2.8448621727203906e-06,
      "loss": 0.4663,
      "step": 49103
    },
    {
      "epoch": 1.5084324025435443,
      "grad_norm": 0.4199444055557251,
      "learning_rate": 2.844524564197615e-06,
      "loss": 0.5216,
      "step": 49104
    },
    {
      "epoch": 1.5084631216784934,
      "grad_norm": 0.4127460718154907,
      "learning_rate": 2.8441869723869488e-06,
      "loss": 0.4824,
      "step": 49105
    },
    {
      "epoch": 1.5084938408134427,
      "grad_norm": 0.45815443992614746,
      "learning_rate": 2.8438493972891823e-06,
      "loss": 0.5055,
      "step": 49106
    },
    {
      "epoch": 1.5085245599483919,
      "grad_norm": 0.40693339705467224,
      "learning_rate": 2.8435118389051063e-06,
      "loss": 0.4201,
      "step": 49107
    },
    {
      "epoch": 1.508555279083341,
      "grad_norm": 0.4002224802970886,
      "learning_rate": 2.8431742972355124e-06,
      "loss": 0.469,
      "step": 49108
    },
    {
      "epoch": 1.5085859982182903,
      "grad_norm": 0.48315492272377014,
      "learning_rate": 2.84283677228118e-06,
      "loss": 0.5233,
      "step": 49109
    },
    {
      "epoch": 1.5086167173532394,
      "grad_norm": 0.40622678399086,
      "learning_rate": 2.8424992640429062e-06,
      "loss": 0.4718,
      "step": 49110
    },
    {
      "epoch": 1.5086474364881886,
      "grad_norm": 0.42084699869155884,
      "learning_rate": 2.842161772521469e-06,
      "loss": 0.5111,
      "step": 49111
    },
    {
      "epoch": 1.5086781556231377,
      "grad_norm": 0.3999476432800293,
      "learning_rate": 2.841824297717669e-06,
      "loss": 0.5044,
      "step": 49112
    },
    {
      "epoch": 1.5087088747580868,
      "grad_norm": 0.5113666653633118,
      "learning_rate": 2.8414868396322847e-06,
      "loss": 0.546,
      "step": 49113
    },
    {
      "epoch": 1.508739593893036,
      "grad_norm": 0.46515941619873047,
      "learning_rate": 2.841149398266111e-06,
      "loss": 0.4477,
      "step": 49114
    },
    {
      "epoch": 1.508770313027985,
      "grad_norm": 0.42209163308143616,
      "learning_rate": 2.8408119736199304e-06,
      "loss": 0.4141,
      "step": 49115
    },
    {
      "epoch": 1.5088010321629342,
      "grad_norm": 0.4591369032859802,
      "learning_rate": 2.8404745656945333e-06,
      "loss": 0.4896,
      "step": 49116
    },
    {
      "epoch": 1.5088317512978835,
      "grad_norm": 0.4665452241897583,
      "learning_rate": 2.840137174490707e-06,
      "loss": 0.4815,
      "step": 49117
    },
    {
      "epoch": 1.5088624704328326,
      "grad_norm": 0.4196869134902954,
      "learning_rate": 2.839799800009244e-06,
      "loss": 0.3701,
      "step": 49118
    },
    {
      "epoch": 1.5088931895677817,
      "grad_norm": 0.42692431807518005,
      "learning_rate": 2.8394624422509263e-06,
      "loss": 0.496,
      "step": 49119
    },
    {
      "epoch": 1.508923908702731,
      "grad_norm": 0.4459514319896698,
      "learning_rate": 2.839125101216543e-06,
      "loss": 0.4222,
      "step": 49120
    },
    {
      "epoch": 1.5089546278376802,
      "grad_norm": 0.43415340781211853,
      "learning_rate": 2.838787776906884e-06,
      "loss": 0.4276,
      "step": 49121
    },
    {
      "epoch": 1.5089853469726293,
      "grad_norm": 0.4245026111602783,
      "learning_rate": 2.8384504693227355e-06,
      "loss": 0.4481,
      "step": 49122
    },
    {
      "epoch": 1.5090160661075784,
      "grad_norm": 0.4309973120689392,
      "learning_rate": 2.8381131784648895e-06,
      "loss": 0.4499,
      "step": 49123
    },
    {
      "epoch": 1.5090467852425276,
      "grad_norm": 0.4410781264305115,
      "learning_rate": 2.837775904334128e-06,
      "loss": 0.5374,
      "step": 49124
    },
    {
      "epoch": 1.5090775043774767,
      "grad_norm": 0.41707509756088257,
      "learning_rate": 2.83743864693124e-06,
      "loss": 0.4648,
      "step": 49125
    },
    {
      "epoch": 1.5091082235124258,
      "grad_norm": 0.5275226831436157,
      "learning_rate": 2.8371014062570145e-06,
      "loss": 0.4786,
      "step": 49126
    },
    {
      "epoch": 1.509138942647375,
      "grad_norm": 0.46331557631492615,
      "learning_rate": 2.8367641823122426e-06,
      "loss": 0.4835,
      "step": 49127
    },
    {
      "epoch": 1.5091696617823243,
      "grad_norm": 0.4193294644355774,
      "learning_rate": 2.8364269750977046e-06,
      "loss": 0.4165,
      "step": 49128
    },
    {
      "epoch": 1.5092003809172734,
      "grad_norm": 0.4100398123264313,
      "learning_rate": 2.836089784614192e-06,
      "loss": 0.4849,
      "step": 49129
    },
    {
      "epoch": 1.5092311000522225,
      "grad_norm": 0.45559898018836975,
      "learning_rate": 2.835752610862492e-06,
      "loss": 0.513,
      "step": 49130
    },
    {
      "epoch": 1.5092618191871718,
      "grad_norm": 0.4680081307888031,
      "learning_rate": 2.8354154538433954e-06,
      "loss": 0.4843,
      "step": 49131
    },
    {
      "epoch": 1.509292538322121,
      "grad_norm": 0.38023045659065247,
      "learning_rate": 2.835078313557682e-06,
      "loss": 0.4392,
      "step": 49132
    },
    {
      "epoch": 1.50932325745707,
      "grad_norm": 0.38926059007644653,
      "learning_rate": 2.834741190006145e-06,
      "loss": 0.4538,
      "step": 49133
    },
    {
      "epoch": 1.5093539765920192,
      "grad_norm": 0.43949899077415466,
      "learning_rate": 2.8344040831895702e-06,
      "loss": 0.4889,
      "step": 49134
    },
    {
      "epoch": 1.5093846957269683,
      "grad_norm": 0.4314165413379669,
      "learning_rate": 2.8340669931087473e-06,
      "loss": 0.5102,
      "step": 49135
    },
    {
      "epoch": 1.5094154148619174,
      "grad_norm": 0.40655258297920227,
      "learning_rate": 2.83372991976446e-06,
      "loss": 0.5021,
      "step": 49136
    },
    {
      "epoch": 1.5094461339968666,
      "grad_norm": 0.4458560347557068,
      "learning_rate": 2.833392863157498e-06,
      "loss": 0.4553,
      "step": 49137
    },
    {
      "epoch": 1.5094768531318157,
      "grad_norm": 0.4531891942024231,
      "learning_rate": 2.833055823288643e-06,
      "loss": 0.4393,
      "step": 49138
    },
    {
      "epoch": 1.509507572266765,
      "grad_norm": 0.4175359904766083,
      "learning_rate": 2.8327188001586882e-06,
      "loss": 0.4442,
      "step": 49139
    },
    {
      "epoch": 1.5095382914017141,
      "grad_norm": 0.41500788927078247,
      "learning_rate": 2.832381793768423e-06,
      "loss": 0.4693,
      "step": 49140
    },
    {
      "epoch": 1.5095690105366633,
      "grad_norm": 0.5302501916885376,
      "learning_rate": 2.832044804118628e-06,
      "loss": 0.4909,
      "step": 49141
    },
    {
      "epoch": 1.5095997296716126,
      "grad_norm": 0.4515113830566406,
      "learning_rate": 2.8317078312100956e-06,
      "loss": 0.4981,
      "step": 49142
    },
    {
      "epoch": 1.5096304488065617,
      "grad_norm": 0.5027297139167786,
      "learning_rate": 2.831370875043604e-06,
      "loss": 0.3825,
      "step": 49143
    },
    {
      "epoch": 1.5096611679415108,
      "grad_norm": 0.42909303307533264,
      "learning_rate": 2.8310339356199536e-06,
      "loss": 0.5255,
      "step": 49144
    },
    {
      "epoch": 1.50969188707646,
      "grad_norm": 0.4075130820274353,
      "learning_rate": 2.830697012939919e-06,
      "loss": 0.4351,
      "step": 49145
    },
    {
      "epoch": 1.509722606211409,
      "grad_norm": 0.4178294241428375,
      "learning_rate": 2.8303601070042973e-06,
      "loss": 0.3422,
      "step": 49146
    },
    {
      "epoch": 1.5097533253463582,
      "grad_norm": 0.4437796473503113,
      "learning_rate": 2.830023217813863e-06,
      "loss": 0.3698,
      "step": 49147
    },
    {
      "epoch": 1.5097840444813073,
      "grad_norm": 0.5024391412734985,
      "learning_rate": 2.8296863453694166e-06,
      "loss": 0.4852,
      "step": 49148
    },
    {
      "epoch": 1.5098147636162564,
      "grad_norm": 0.4121960997581482,
      "learning_rate": 2.8293494896717357e-06,
      "loss": 0.4651,
      "step": 49149
    },
    {
      "epoch": 1.5098454827512058,
      "grad_norm": 0.37551385164260864,
      "learning_rate": 2.829012650721613e-06,
      "loss": 0.4736,
      "step": 49150
    },
    {
      "epoch": 1.509876201886155,
      "grad_norm": 0.43241026997566223,
      "learning_rate": 2.828675828519829e-06,
      "loss": 0.4353,
      "step": 49151
    },
    {
      "epoch": 1.509906921021104,
      "grad_norm": 0.4059932231903076,
      "learning_rate": 2.8283390230671726e-06,
      "loss": 0.408,
      "step": 49152
    },
    {
      "epoch": 1.5099376401560534,
      "grad_norm": 0.43039411306381226,
      "learning_rate": 2.828002234364432e-06,
      "loss": 0.4241,
      "step": 49153
    },
    {
      "epoch": 1.5099683592910025,
      "grad_norm": 0.405680775642395,
      "learning_rate": 2.8276654624123957e-06,
      "loss": 0.4463,
      "step": 49154
    },
    {
      "epoch": 1.5099990784259516,
      "grad_norm": 0.4191755950450897,
      "learning_rate": 2.827328707211845e-06,
      "loss": 0.4604,
      "step": 49155
    },
    {
      "epoch": 1.5100297975609007,
      "grad_norm": 0.3864062428474426,
      "learning_rate": 2.8269919687635696e-06,
      "loss": 0.4408,
      "step": 49156
    },
    {
      "epoch": 1.5100605166958498,
      "grad_norm": 0.43371063470840454,
      "learning_rate": 2.826655247068354e-06,
      "loss": 0.437,
      "step": 49157
    },
    {
      "epoch": 1.510091235830799,
      "grad_norm": 0.41235315799713135,
      "learning_rate": 2.826318542126987e-06,
      "loss": 0.4182,
      "step": 49158
    },
    {
      "epoch": 1.510121954965748,
      "grad_norm": 0.40614497661590576,
      "learning_rate": 2.825981853940256e-06,
      "loss": 0.4598,
      "step": 49159
    },
    {
      "epoch": 1.5101526741006972,
      "grad_norm": 0.4044307470321655,
      "learning_rate": 2.825645182508944e-06,
      "loss": 0.4717,
      "step": 49160
    },
    {
      "epoch": 1.5101833932356463,
      "grad_norm": 0.4467169940471649,
      "learning_rate": 2.825308527833838e-06,
      "loss": 0.5118,
      "step": 49161
    },
    {
      "epoch": 1.5102141123705957,
      "grad_norm": 0.38741883635520935,
      "learning_rate": 2.8249718899157252e-06,
      "loss": 0.4009,
      "step": 49162
    },
    {
      "epoch": 1.5102448315055448,
      "grad_norm": 0.47517064213752747,
      "learning_rate": 2.8246352687553934e-06,
      "loss": 0.4431,
      "step": 49163
    },
    {
      "epoch": 1.5102755506404941,
      "grad_norm": 0.43518632650375366,
      "learning_rate": 2.8242986643536253e-06,
      "loss": 0.4957,
      "step": 49164
    },
    {
      "epoch": 1.5103062697754432,
      "grad_norm": 0.4636273980140686,
      "learning_rate": 2.8239620767112087e-06,
      "loss": 0.4545,
      "step": 49165
    },
    {
      "epoch": 1.5103369889103924,
      "grad_norm": 0.4261137843132019,
      "learning_rate": 2.8236255058289298e-06,
      "loss": 0.4734,
      "step": 49166
    },
    {
      "epoch": 1.5103677080453415,
      "grad_norm": 0.4207094609737396,
      "learning_rate": 2.823288951707578e-06,
      "loss": 0.5086,
      "step": 49167
    },
    {
      "epoch": 1.5103984271802906,
      "grad_norm": 0.5104948282241821,
      "learning_rate": 2.8229524143479326e-06,
      "loss": 0.4986,
      "step": 49168
    },
    {
      "epoch": 1.5104291463152397,
      "grad_norm": 0.4351600408554077,
      "learning_rate": 2.822615893750783e-06,
      "loss": 0.461,
      "step": 49169
    },
    {
      "epoch": 1.5104598654501888,
      "grad_norm": 0.42141667008399963,
      "learning_rate": 2.8222793899169154e-06,
      "loss": 0.491,
      "step": 49170
    },
    {
      "epoch": 1.510490584585138,
      "grad_norm": 0.41529276967048645,
      "learning_rate": 2.821942902847119e-06,
      "loss": 0.4063,
      "step": 49171
    },
    {
      "epoch": 1.510521303720087,
      "grad_norm": 0.4198437035083771,
      "learning_rate": 2.821606432542172e-06,
      "loss": 0.4805,
      "step": 49172
    },
    {
      "epoch": 1.5105520228550364,
      "grad_norm": 0.5223895907402039,
      "learning_rate": 2.8212699790028685e-06,
      "loss": 0.5113,
      "step": 49173
    },
    {
      "epoch": 1.5105827419899855,
      "grad_norm": 0.4186688959598541,
      "learning_rate": 2.8209335422299846e-06,
      "loss": 0.4431,
      "step": 49174
    },
    {
      "epoch": 1.5106134611249349,
      "grad_norm": 0.42824846506118774,
      "learning_rate": 2.8205971222243143e-06,
      "loss": 0.5052,
      "step": 49175
    },
    {
      "epoch": 1.510644180259884,
      "grad_norm": 0.41072508692741394,
      "learning_rate": 2.820260718986644e-06,
      "loss": 0.4619,
      "step": 49176
    },
    {
      "epoch": 1.5106748993948331,
      "grad_norm": 0.4440103769302368,
      "learning_rate": 2.8199243325177528e-06,
      "loss": 0.5369,
      "step": 49177
    },
    {
      "epoch": 1.5107056185297822,
      "grad_norm": 0.46817803382873535,
      "learning_rate": 2.819587962818433e-06,
      "loss": 0.4683,
      "step": 49178
    },
    {
      "epoch": 1.5107363376647314,
      "grad_norm": 0.4050728678703308,
      "learning_rate": 2.8192516098894616e-06,
      "loss": 0.5587,
      "step": 49179
    },
    {
      "epoch": 1.5107670567996805,
      "grad_norm": 0.42468327283859253,
      "learning_rate": 2.818915273731635e-06,
      "loss": 0.4329,
      "step": 49180
    },
    {
      "epoch": 1.5107977759346296,
      "grad_norm": 0.40680453181266785,
      "learning_rate": 2.8185789543457297e-06,
      "loss": 0.4503,
      "step": 49181
    },
    {
      "epoch": 1.5108284950695787,
      "grad_norm": 0.472260445356369,
      "learning_rate": 2.818242651732539e-06,
      "loss": 0.4619,
      "step": 49182
    },
    {
      "epoch": 1.5108592142045278,
      "grad_norm": 0.438231885433197,
      "learning_rate": 2.8179063658928408e-06,
      "loss": 0.4941,
      "step": 49183
    },
    {
      "epoch": 1.5108899333394772,
      "grad_norm": 0.4268225133419037,
      "learning_rate": 2.817570096827423e-06,
      "loss": 0.5338,
      "step": 49184
    },
    {
      "epoch": 1.5109206524744263,
      "grad_norm": 0.42392969131469727,
      "learning_rate": 2.817233844537073e-06,
      "loss": 0.4769,
      "step": 49185
    },
    {
      "epoch": 1.5109513716093754,
      "grad_norm": 0.4969649314880371,
      "learning_rate": 2.8168976090225774e-06,
      "loss": 0.4672,
      "step": 49186
    },
    {
      "epoch": 1.5109820907443248,
      "grad_norm": 0.43488121032714844,
      "learning_rate": 2.8165613902847168e-06,
      "loss": 0.4676,
      "step": 49187
    },
    {
      "epoch": 1.5110128098792739,
      "grad_norm": 0.42379993200302124,
      "learning_rate": 2.8162251883242774e-06,
      "loss": 0.3824,
      "step": 49188
    },
    {
      "epoch": 1.511043529014223,
      "grad_norm": 0.7410019040107727,
      "learning_rate": 2.815889003142047e-06,
      "loss": 0.4427,
      "step": 49189
    },
    {
      "epoch": 1.5110742481491721,
      "grad_norm": 0.43965256214141846,
      "learning_rate": 2.8155528347388118e-06,
      "loss": 0.5201,
      "step": 49190
    },
    {
      "epoch": 1.5111049672841212,
      "grad_norm": 0.42239224910736084,
      "learning_rate": 2.8152166831153526e-06,
      "loss": 0.4937,
      "step": 49191
    },
    {
      "epoch": 1.5111356864190704,
      "grad_norm": 0.46196797490119934,
      "learning_rate": 2.814880548272455e-06,
      "loss": 0.5054,
      "step": 49192
    },
    {
      "epoch": 1.5111664055540195,
      "grad_norm": 0.38330456614494324,
      "learning_rate": 2.814544430210907e-06,
      "loss": 0.455,
      "step": 49193
    },
    {
      "epoch": 1.5111971246889686,
      "grad_norm": 0.396862655878067,
      "learning_rate": 2.8142083289314925e-06,
      "loss": 0.4312,
      "step": 49194
    },
    {
      "epoch": 1.511227843823918,
      "grad_norm": 0.4778306484222412,
      "learning_rate": 2.813872244434999e-06,
      "loss": 0.4105,
      "step": 49195
    },
    {
      "epoch": 1.511258562958867,
      "grad_norm": 0.4204060733318329,
      "learning_rate": 2.8135361767222046e-06,
      "loss": 0.4683,
      "step": 49196
    },
    {
      "epoch": 1.5112892820938162,
      "grad_norm": 0.41330793499946594,
      "learning_rate": 2.8132001257939e-06,
      "loss": 0.4366,
      "step": 49197
    },
    {
      "epoch": 1.5113200012287655,
      "grad_norm": 0.44265973567962646,
      "learning_rate": 2.8128640916508674e-06,
      "loss": 0.3886,
      "step": 49198
    },
    {
      "epoch": 1.5113507203637147,
      "grad_norm": 0.42369478940963745,
      "learning_rate": 2.8125280742938965e-06,
      "loss": 0.4875,
      "step": 49199
    },
    {
      "epoch": 1.5113814394986638,
      "grad_norm": 0.44039472937583923,
      "learning_rate": 2.812192073723765e-06,
      "loss": 0.465,
      "step": 49200
    },
    {
      "epoch": 1.511412158633613,
      "grad_norm": 0.420825332403183,
      "learning_rate": 2.8118560899412607e-06,
      "loss": 0.497,
      "step": 49201
    },
    {
      "epoch": 1.511442877768562,
      "grad_norm": 0.4389376640319824,
      "learning_rate": 2.811520122947168e-06,
      "loss": 0.5134,
      "step": 49202
    },
    {
      "epoch": 1.5114735969035111,
      "grad_norm": 0.4595851004123688,
      "learning_rate": 2.811184172742276e-06,
      "loss": 0.3904,
      "step": 49203
    },
    {
      "epoch": 1.5115043160384602,
      "grad_norm": 0.41418734192848206,
      "learning_rate": 2.8108482393273617e-06,
      "loss": 0.4636,
      "step": 49204
    },
    {
      "epoch": 1.5115350351734094,
      "grad_norm": 0.45706114172935486,
      "learning_rate": 2.810512322703217e-06,
      "loss": 0.4951,
      "step": 49205
    },
    {
      "epoch": 1.5115657543083587,
      "grad_norm": 0.43149253726005554,
      "learning_rate": 2.8101764228706165e-06,
      "loss": 0.5098,
      "step": 49206
    },
    {
      "epoch": 1.5115964734433078,
      "grad_norm": 0.4195241630077362,
      "learning_rate": 2.8098405398303574e-06,
      "loss": 0.4509,
      "step": 49207
    },
    {
      "epoch": 1.511627192578257,
      "grad_norm": 0.4346250891685486,
      "learning_rate": 2.8095046735832142e-06,
      "loss": 0.5154,
      "step": 49208
    },
    {
      "epoch": 1.5116579117132063,
      "grad_norm": 0.4342679977416992,
      "learning_rate": 2.8091688241299786e-06,
      "loss": 0.4709,
      "step": 49209
    },
    {
      "epoch": 1.5116886308481554,
      "grad_norm": 0.43033474683761597,
      "learning_rate": 2.808832991471425e-06,
      "loss": 0.4845,
      "step": 49210
    },
    {
      "epoch": 1.5117193499831045,
      "grad_norm": 0.44075649976730347,
      "learning_rate": 2.8084971756083512e-06,
      "loss": 0.4713,
      "step": 49211
    },
    {
      "epoch": 1.5117500691180537,
      "grad_norm": 0.4400216042995453,
      "learning_rate": 2.8081613765415303e-06,
      "loss": 0.51,
      "step": 49212
    },
    {
      "epoch": 1.5117807882530028,
      "grad_norm": 0.46319758892059326,
      "learning_rate": 2.8078255942717514e-06,
      "loss": 0.485,
      "step": 49213
    },
    {
      "epoch": 1.511811507387952,
      "grad_norm": 0.4140705466270447,
      "learning_rate": 2.807489828799801e-06,
      "loss": 0.4315,
      "step": 49214
    },
    {
      "epoch": 1.511842226522901,
      "grad_norm": 0.40782684087753296,
      "learning_rate": 2.8071540801264543e-06,
      "loss": 0.3839,
      "step": 49215
    },
    {
      "epoch": 1.5118729456578501,
      "grad_norm": 0.45883631706237793,
      "learning_rate": 2.806818348252508e-06,
      "loss": 0.4992,
      "step": 49216
    },
    {
      "epoch": 1.5119036647927995,
      "grad_norm": 0.39406779408454895,
      "learning_rate": 2.8064826331787364e-06,
      "loss": 0.4528,
      "step": 49217
    },
    {
      "epoch": 1.5119343839277486,
      "grad_norm": 0.41404253244400024,
      "learning_rate": 2.80614693490593e-06,
      "loss": 0.4952,
      "step": 49218
    },
    {
      "epoch": 1.5119651030626977,
      "grad_norm": 0.41218093037605286,
      "learning_rate": 2.805811253434867e-06,
      "loss": 0.441,
      "step": 49219
    },
    {
      "epoch": 1.511995822197647,
      "grad_norm": 0.40740370750427246,
      "learning_rate": 2.8054755887663345e-06,
      "loss": 0.4572,
      "step": 49220
    },
    {
      "epoch": 1.5120265413325962,
      "grad_norm": 0.43021446466445923,
      "learning_rate": 2.805139940901115e-06,
      "loss": 0.4959,
      "step": 49221
    },
    {
      "epoch": 1.5120572604675453,
      "grad_norm": 0.3820153474807739,
      "learning_rate": 2.804804309839998e-06,
      "loss": 0.5654,
      "step": 49222
    },
    {
      "epoch": 1.5120879796024944,
      "grad_norm": 0.3710496425628662,
      "learning_rate": 2.8044686955837595e-06,
      "loss": 0.4396,
      "step": 49223
    },
    {
      "epoch": 1.5121186987374435,
      "grad_norm": 0.4897623658180237,
      "learning_rate": 2.804133098133187e-06,
      "loss": 0.4141,
      "step": 49224
    },
    {
      "epoch": 1.5121494178723927,
      "grad_norm": 0.4095977544784546,
      "learning_rate": 2.803797517489064e-06,
      "loss": 0.5133,
      "step": 49225
    },
    {
      "epoch": 1.5121801370073418,
      "grad_norm": 0.43160974979400635,
      "learning_rate": 2.803461953652178e-06,
      "loss": 0.5071,
      "step": 49226
    },
    {
      "epoch": 1.512210856142291,
      "grad_norm": 0.42013394832611084,
      "learning_rate": 2.8031264066233055e-06,
      "loss": 0.5203,
      "step": 49227
    },
    {
      "epoch": 1.5122415752772402,
      "grad_norm": 0.4343854784965515,
      "learning_rate": 2.8027908764032343e-06,
      "loss": 0.4228,
      "step": 49228
    },
    {
      "epoch": 1.5122722944121894,
      "grad_norm": 0.4008621275424957,
      "learning_rate": 2.8024553629927475e-06,
      "loss": 0.5355,
      "step": 49229
    },
    {
      "epoch": 1.5123030135471385,
      "grad_norm": 0.5120266079902649,
      "learning_rate": 2.8021198663926295e-06,
      "loss": 0.5021,
      "step": 49230
    },
    {
      "epoch": 1.5123337326820878,
      "grad_norm": 0.38591861724853516,
      "learning_rate": 2.8017843866036655e-06,
      "loss": 0.4979,
      "step": 49231
    },
    {
      "epoch": 1.512364451817037,
      "grad_norm": 0.4405612647533417,
      "learning_rate": 2.801448923626634e-06,
      "loss": 0.4696,
      "step": 49232
    },
    {
      "epoch": 1.512395170951986,
      "grad_norm": 0.378161758184433,
      "learning_rate": 2.801113477462322e-06,
      "loss": 0.4786,
      "step": 49233
    },
    {
      "epoch": 1.5124258900869352,
      "grad_norm": 0.46565908193588257,
      "learning_rate": 2.800778048111511e-06,
      "loss": 0.5449,
      "step": 49234
    },
    {
      "epoch": 1.5124566092218843,
      "grad_norm": 0.41703641414642334,
      "learning_rate": 2.8004426355749893e-06,
      "loss": 0.4653,
      "step": 49235
    },
    {
      "epoch": 1.5124873283568334,
      "grad_norm": 0.41090887784957886,
      "learning_rate": 2.8001072398535333e-06,
      "loss": 0.4745,
      "step": 49236
    },
    {
      "epoch": 1.5125180474917825,
      "grad_norm": 0.4287514388561249,
      "learning_rate": 2.799771860947931e-06,
      "loss": 0.4783,
      "step": 49237
    },
    {
      "epoch": 1.5125487666267317,
      "grad_norm": 0.39294248819351196,
      "learning_rate": 2.799436498858963e-06,
      "loss": 0.4968,
      "step": 49238
    },
    {
      "epoch": 1.512579485761681,
      "grad_norm": 0.4130302667617798,
      "learning_rate": 2.7991011535874168e-06,
      "loss": 0.5564,
      "step": 49239
    },
    {
      "epoch": 1.5126102048966301,
      "grad_norm": 0.4552643597126007,
      "learning_rate": 2.79876582513407e-06,
      "loss": 0.4243,
      "step": 49240
    },
    {
      "epoch": 1.5126409240315792,
      "grad_norm": 0.4021894931793213,
      "learning_rate": 2.7984305134997124e-06,
      "loss": 0.4493,
      "step": 49241
    },
    {
      "epoch": 1.5126716431665286,
      "grad_norm": 0.41158923506736755,
      "learning_rate": 2.7980952186851164e-06,
      "loss": 0.449,
      "step": 49242
    },
    {
      "epoch": 1.5127023623014777,
      "grad_norm": 0.42500051856040955,
      "learning_rate": 2.797759940691078e-06,
      "loss": 0.5075,
      "step": 49243
    },
    {
      "epoch": 1.5127330814364268,
      "grad_norm": 0.45641443133354187,
      "learning_rate": 2.7974246795183714e-06,
      "loss": 0.433,
      "step": 49244
    },
    {
      "epoch": 1.512763800571376,
      "grad_norm": 0.45548540353775024,
      "learning_rate": 2.7970894351677856e-06,
      "loss": 0.4803,
      "step": 49245
    },
    {
      "epoch": 1.512794519706325,
      "grad_norm": 0.4039198160171509,
      "learning_rate": 2.7967542076400978e-06,
      "loss": 0.4326,
      "step": 49246
    },
    {
      "epoch": 1.5128252388412742,
      "grad_norm": 0.5444037914276123,
      "learning_rate": 2.7964189969360933e-06,
      "loss": 0.5111,
      "step": 49247
    },
    {
      "epoch": 1.5128559579762233,
      "grad_norm": 0.41758009791374207,
      "learning_rate": 2.796083803056555e-06,
      "loss": 0.451,
      "step": 49248
    },
    {
      "epoch": 1.5128866771111724,
      "grad_norm": 0.550346314907074,
      "learning_rate": 2.795748626002266e-06,
      "loss": 0.5463,
      "step": 49249
    },
    {
      "epoch": 1.5129173962461218,
      "grad_norm": 0.41262951493263245,
      "learning_rate": 2.7954134657740128e-06,
      "loss": 0.4063,
      "step": 49250
    },
    {
      "epoch": 1.5129481153810709,
      "grad_norm": 0.39837583899497986,
      "learning_rate": 2.7950783223725688e-06,
      "loss": 0.5477,
      "step": 49251
    },
    {
      "epoch": 1.51297883451602,
      "grad_norm": 0.441948801279068,
      "learning_rate": 2.794743195798728e-06,
      "loss": 0.5486,
      "step": 49252
    },
    {
      "epoch": 1.5130095536509693,
      "grad_norm": 0.3943547010421753,
      "learning_rate": 2.794408086053265e-06,
      "loss": 0.501,
      "step": 49253
    },
    {
      "epoch": 1.5130402727859185,
      "grad_norm": 0.39911264181137085,
      "learning_rate": 2.794072993136968e-06,
      "loss": 0.4675,
      "step": 49254
    },
    {
      "epoch": 1.5130709919208676,
      "grad_norm": 0.4100019931793213,
      "learning_rate": 2.793737917050614e-06,
      "loss": 0.4246,
      "step": 49255
    },
    {
      "epoch": 1.5131017110558167,
      "grad_norm": 0.39087948203086853,
      "learning_rate": 2.7934028577949877e-06,
      "loss": 0.5266,
      "step": 49256
    },
    {
      "epoch": 1.5131324301907658,
      "grad_norm": 0.5062850117683411,
      "learning_rate": 2.7930678153708723e-06,
      "loss": 0.5015,
      "step": 49257
    },
    {
      "epoch": 1.513163149325715,
      "grad_norm": 0.42291685938835144,
      "learning_rate": 2.7927327897790545e-06,
      "loss": 0.4895,
      "step": 49258
    },
    {
      "epoch": 1.513193868460664,
      "grad_norm": 0.44229161739349365,
      "learning_rate": 2.7923977810203085e-06,
      "loss": 0.4513,
      "step": 49259
    },
    {
      "epoch": 1.5132245875956132,
      "grad_norm": 0.4400143325328827,
      "learning_rate": 2.792062789095421e-06,
      "loss": 0.5446,
      "step": 49260
    },
    {
      "epoch": 1.5132553067305625,
      "grad_norm": 0.4087659418582916,
      "learning_rate": 2.791727814005175e-06,
      "loss": 0.4072,
      "step": 49261
    },
    {
      "epoch": 1.5132860258655116,
      "grad_norm": 0.40495964884757996,
      "learning_rate": 2.7913928557503544e-06,
      "loss": 0.386,
      "step": 49262
    },
    {
      "epoch": 1.5133167450004608,
      "grad_norm": 0.3959749639034271,
      "learning_rate": 2.7910579143317373e-06,
      "loss": 0.4043,
      "step": 49263
    },
    {
      "epoch": 1.51334746413541,
      "grad_norm": 0.4554641544818878,
      "learning_rate": 2.7907229897501066e-06,
      "loss": 0.4627,
      "step": 49264
    },
    {
      "epoch": 1.5133781832703592,
      "grad_norm": 0.45068874955177307,
      "learning_rate": 2.7903880820062466e-06,
      "loss": 0.5112,
      "step": 49265
    },
    {
      "epoch": 1.5134089024053083,
      "grad_norm": 0.44857779145240784,
      "learning_rate": 2.790053191100941e-06,
      "loss": 0.4304,
      "step": 49266
    },
    {
      "epoch": 1.5134396215402575,
      "grad_norm": 0.4086782932281494,
      "learning_rate": 2.7897183170349672e-06,
      "loss": 0.4809,
      "step": 49267
    },
    {
      "epoch": 1.5134703406752066,
      "grad_norm": 0.39171135425567627,
      "learning_rate": 2.7893834598091098e-06,
      "loss": 0.444,
      "step": 49268
    },
    {
      "epoch": 1.5135010598101557,
      "grad_norm": 0.5019395351409912,
      "learning_rate": 2.789048619424152e-06,
      "loss": 0.4492,
      "step": 49269
    },
    {
      "epoch": 1.5135317789451048,
      "grad_norm": 0.41938474774360657,
      "learning_rate": 2.788713795880873e-06,
      "loss": 0.4722,
      "step": 49270
    },
    {
      "epoch": 1.513562498080054,
      "grad_norm": 0.42345887422561646,
      "learning_rate": 2.7883789891800608e-06,
      "loss": 0.4822,
      "step": 49271
    },
    {
      "epoch": 1.513593217215003,
      "grad_norm": 0.4872696101665497,
      "learning_rate": 2.7880441993224893e-06,
      "loss": 0.4232,
      "step": 49272
    },
    {
      "epoch": 1.5136239363499524,
      "grad_norm": 0.4357830584049225,
      "learning_rate": 2.7877094263089444e-06,
      "loss": 0.5228,
      "step": 49273
    },
    {
      "epoch": 1.5136546554849015,
      "grad_norm": 0.4174947142601013,
      "learning_rate": 2.787374670140208e-06,
      "loss": 0.5,
      "step": 49274
    },
    {
      "epoch": 1.5136853746198509,
      "grad_norm": 0.44587916135787964,
      "learning_rate": 2.787039930817065e-06,
      "loss": 0.4497,
      "step": 49275
    },
    {
      "epoch": 1.5137160937548,
      "grad_norm": 0.4383014738559723,
      "learning_rate": 2.78670520834029e-06,
      "loss": 0.4385,
      "step": 49276
    },
    {
      "epoch": 1.513746812889749,
      "grad_norm": 0.4071986675262451,
      "learning_rate": 2.7863705027106726e-06,
      "loss": 0.5403,
      "step": 49277
    },
    {
      "epoch": 1.5137775320246982,
      "grad_norm": 0.42096877098083496,
      "learning_rate": 2.7860358139289845e-06,
      "loss": 0.4798,
      "step": 49278
    },
    {
      "epoch": 1.5138082511596473,
      "grad_norm": 0.3896861672401428,
      "learning_rate": 2.78570114199602e-06,
      "loss": 0.4786,
      "step": 49279
    },
    {
      "epoch": 1.5138389702945965,
      "grad_norm": 0.4184606373310089,
      "learning_rate": 2.7853664869125508e-06,
      "loss": 0.5046,
      "step": 49280
    },
    {
      "epoch": 1.5138696894295456,
      "grad_norm": 0.45837655663490295,
      "learning_rate": 2.785031848679366e-06,
      "loss": 0.4647,
      "step": 49281
    },
    {
      "epoch": 1.5139004085644947,
      "grad_norm": 0.411300390958786,
      "learning_rate": 2.7846972272972395e-06,
      "loss": 0.4375,
      "step": 49282
    },
    {
      "epoch": 1.5139311276994438,
      "grad_norm": 0.4218333661556244,
      "learning_rate": 2.7843626227669563e-06,
      "loss": 0.4793,
      "step": 49283
    },
    {
      "epoch": 1.5139618468343932,
      "grad_norm": 0.4151608347892761,
      "learning_rate": 2.7840280350892977e-06,
      "loss": 0.4396,
      "step": 49284
    },
    {
      "epoch": 1.5139925659693423,
      "grad_norm": 0.42501527070999146,
      "learning_rate": 2.783693464265046e-06,
      "loss": 0.4924,
      "step": 49285
    },
    {
      "epoch": 1.5140232851042916,
      "grad_norm": 0.4278547763824463,
      "learning_rate": 2.7833589102949853e-06,
      "loss": 0.4509,
      "step": 49286
    },
    {
      "epoch": 1.5140540042392407,
      "grad_norm": 0.5028080344200134,
      "learning_rate": 2.7830243731798912e-06,
      "loss": 0.4897,
      "step": 49287
    },
    {
      "epoch": 1.5140847233741899,
      "grad_norm": 0.398943156003952,
      "learning_rate": 2.782689852920547e-06,
      "loss": 0.4654,
      "step": 49288
    },
    {
      "epoch": 1.514115442509139,
      "grad_norm": 0.42021945118904114,
      "learning_rate": 2.7823553495177357e-06,
      "loss": 0.4468,
      "step": 49289
    },
    {
      "epoch": 1.514146161644088,
      "grad_norm": 0.40635600686073303,
      "learning_rate": 2.78202086297224e-06,
      "loss": 0.4198,
      "step": 49290
    },
    {
      "epoch": 1.5141768807790372,
      "grad_norm": 0.4493602216243744,
      "learning_rate": 2.781686393284836e-06,
      "loss": 0.455,
      "step": 49291
    },
    {
      "epoch": 1.5142075999139863,
      "grad_norm": 0.4363883435726166,
      "learning_rate": 2.781351940456307e-06,
      "loss": 0.4453,
      "step": 49292
    },
    {
      "epoch": 1.5142383190489355,
      "grad_norm": 0.42530688643455505,
      "learning_rate": 2.7810175044874345e-06,
      "loss": 0.5219,
      "step": 49293
    },
    {
      "epoch": 1.5142690381838846,
      "grad_norm": 0.49825555086135864,
      "learning_rate": 2.7806830853790035e-06,
      "loss": 0.4539,
      "step": 49294
    },
    {
      "epoch": 1.514299757318834,
      "grad_norm": 0.46714097261428833,
      "learning_rate": 2.780348683131788e-06,
      "loss": 0.4523,
      "step": 49295
    },
    {
      "epoch": 1.514330476453783,
      "grad_norm": 0.4350375533103943,
      "learning_rate": 2.780014297746573e-06,
      "loss": 0.4613,
      "step": 49296
    },
    {
      "epoch": 1.5143611955887322,
      "grad_norm": 0.4106738567352295,
      "learning_rate": 2.7796799292241374e-06,
      "loss": 0.4678,
      "step": 49297
    },
    {
      "epoch": 1.5143919147236815,
      "grad_norm": 0.4168343245983124,
      "learning_rate": 2.7793455775652677e-06,
      "loss": 0.4734,
      "step": 49298
    },
    {
      "epoch": 1.5144226338586306,
      "grad_norm": 0.43609508872032166,
      "learning_rate": 2.779011242770737e-06,
      "loss": 0.501,
      "step": 49299
    },
    {
      "epoch": 1.5144533529935797,
      "grad_norm": 0.37142932415008545,
      "learning_rate": 2.77867692484133e-06,
      "loss": 0.4405,
      "step": 49300
    },
    {
      "epoch": 1.5144840721285289,
      "grad_norm": 0.39952579140663147,
      "learning_rate": 2.778342623777829e-06,
      "loss": 0.4245,
      "step": 49301
    },
    {
      "epoch": 1.514514791263478,
      "grad_norm": 0.43026453256607056,
      "learning_rate": 2.7780083395810144e-06,
      "loss": 0.4679,
      "step": 49302
    },
    {
      "epoch": 1.514545510398427,
      "grad_norm": 0.42513906955718994,
      "learning_rate": 2.7776740722516625e-06,
      "loss": 0.494,
      "step": 49303
    },
    {
      "epoch": 1.5145762295333762,
      "grad_norm": 0.40867897868156433,
      "learning_rate": 2.777339821790558e-06,
      "loss": 0.4127,
      "step": 49304
    },
    {
      "epoch": 1.5146069486683253,
      "grad_norm": 0.44013774394989014,
      "learning_rate": 2.7770055881984804e-06,
      "loss": 0.4649,
      "step": 49305
    },
    {
      "epoch": 1.5146376678032747,
      "grad_norm": 0.4532378613948822,
      "learning_rate": 2.7766713714762117e-06,
      "loss": 0.4666,
      "step": 49306
    },
    {
      "epoch": 1.5146683869382238,
      "grad_norm": 0.40631699562072754,
      "learning_rate": 2.7763371716245333e-06,
      "loss": 0.5072,
      "step": 49307
    },
    {
      "epoch": 1.514699106073173,
      "grad_norm": 0.4230048954486847,
      "learning_rate": 2.7760029886442207e-06,
      "loss": 0.4486,
      "step": 49308
    },
    {
      "epoch": 1.5147298252081223,
      "grad_norm": 0.4198543131351471,
      "learning_rate": 2.775668822536062e-06,
      "loss": 0.4783,
      "step": 49309
    },
    {
      "epoch": 1.5147605443430714,
      "grad_norm": 0.42679038643836975,
      "learning_rate": 2.7753346733008257e-06,
      "loss": 0.3921,
      "step": 49310
    },
    {
      "epoch": 1.5147912634780205,
      "grad_norm": 0.48724740743637085,
      "learning_rate": 2.775000540939308e-06,
      "loss": 0.4587,
      "step": 49311
    },
    {
      "epoch": 1.5148219826129696,
      "grad_norm": 0.4155827760696411,
      "learning_rate": 2.7746664254522757e-06,
      "loss": 0.4543,
      "step": 49312
    },
    {
      "epoch": 1.5148527017479188,
      "grad_norm": 0.48862677812576294,
      "learning_rate": 2.774332326840519e-06,
      "loss": 0.4429,
      "step": 49313
    },
    {
      "epoch": 1.5148834208828679,
      "grad_norm": 0.4452212452888489,
      "learning_rate": 2.7739982451048075e-06,
      "loss": 0.4784,
      "step": 49314
    },
    {
      "epoch": 1.514914140017817,
      "grad_norm": 0.4188964068889618,
      "learning_rate": 2.773664180245934e-06,
      "loss": 0.488,
      "step": 49315
    },
    {
      "epoch": 1.514944859152766,
      "grad_norm": 0.4491158127784729,
      "learning_rate": 2.773330132264669e-06,
      "loss": 0.4818,
      "step": 49316
    },
    {
      "epoch": 1.5149755782877155,
      "grad_norm": 0.4381546378135681,
      "learning_rate": 2.772996101161799e-06,
      "loss": 0.4528,
      "step": 49317
    },
    {
      "epoch": 1.5150062974226646,
      "grad_norm": 0.4103259742259979,
      "learning_rate": 2.772662086938099e-06,
      "loss": 0.4457,
      "step": 49318
    },
    {
      "epoch": 1.5150370165576137,
      "grad_norm": 0.4318760931491852,
      "learning_rate": 2.7723280895943514e-06,
      "loss": 0.4641,
      "step": 49319
    },
    {
      "epoch": 1.515067735692563,
      "grad_norm": 0.4222102463245392,
      "learning_rate": 2.7719941091313363e-06,
      "loss": 0.4806,
      "step": 49320
    },
    {
      "epoch": 1.5150984548275122,
      "grad_norm": 0.41926324367523193,
      "learning_rate": 2.7716601455498326e-06,
      "loss": 0.4326,
      "step": 49321
    },
    {
      "epoch": 1.5151291739624613,
      "grad_norm": 0.4379322826862335,
      "learning_rate": 2.7713261988506256e-06,
      "loss": 0.511,
      "step": 49322
    },
    {
      "epoch": 1.5151598930974104,
      "grad_norm": 0.40464645624160767,
      "learning_rate": 2.7709922690344883e-06,
      "loss": 0.4754,
      "step": 49323
    },
    {
      "epoch": 1.5151906122323595,
      "grad_norm": 0.41811802983283997,
      "learning_rate": 2.7706583561022027e-06,
      "loss": 0.457,
      "step": 49324
    },
    {
      "epoch": 1.5152213313673086,
      "grad_norm": 0.4656729996204376,
      "learning_rate": 2.77032446005455e-06,
      "loss": 0.4658,
      "step": 49325
    },
    {
      "epoch": 1.5152520505022578,
      "grad_norm": 0.42796191573143005,
      "learning_rate": 2.7699905808923122e-06,
      "loss": 0.5166,
      "step": 49326
    },
    {
      "epoch": 1.5152827696372069,
      "grad_norm": 0.44191378355026245,
      "learning_rate": 2.7696567186162637e-06,
      "loss": 0.4691,
      "step": 49327
    },
    {
      "epoch": 1.5153134887721562,
      "grad_norm": 0.43048927187919617,
      "learning_rate": 2.769322873227186e-06,
      "loss": 0.4723,
      "step": 49328
    },
    {
      "epoch": 1.5153442079071053,
      "grad_norm": 0.5688309669494629,
      "learning_rate": 2.7689890447258604e-06,
      "loss": 0.465,
      "step": 49329
    },
    {
      "epoch": 1.5153749270420545,
      "grad_norm": 0.3992636203765869,
      "learning_rate": 2.768655233113069e-06,
      "loss": 0.4626,
      "step": 49330
    },
    {
      "epoch": 1.5154056461770038,
      "grad_norm": 0.4154430329799652,
      "learning_rate": 2.768321438389585e-06,
      "loss": 0.4472,
      "step": 49331
    },
    {
      "epoch": 1.515436365311953,
      "grad_norm": 0.5357292890548706,
      "learning_rate": 2.7679876605561908e-06,
      "loss": 0.5236,
      "step": 49332
    },
    {
      "epoch": 1.515467084446902,
      "grad_norm": 0.4431120753288269,
      "learning_rate": 2.767653899613667e-06,
      "loss": 0.481,
      "step": 49333
    },
    {
      "epoch": 1.5154978035818512,
      "grad_norm": 0.43751686811447144,
      "learning_rate": 2.767320155562796e-06,
      "loss": 0.5327,
      "step": 49334
    },
    {
      "epoch": 1.5155285227168003,
      "grad_norm": 0.4441479444503784,
      "learning_rate": 2.76698642840435e-06,
      "loss": 0.55,
      "step": 49335
    },
    {
      "epoch": 1.5155592418517494,
      "grad_norm": 0.49043312668800354,
      "learning_rate": 2.7666527181391132e-06,
      "loss": 0.4755,
      "step": 49336
    },
    {
      "epoch": 1.5155899609866985,
      "grad_norm": 0.4721227288246155,
      "learning_rate": 2.766319024767864e-06,
      "loss": 0.5259,
      "step": 49337
    },
    {
      "epoch": 1.5156206801216476,
      "grad_norm": 0.4421135485172272,
      "learning_rate": 2.7659853482913845e-06,
      "loss": 0.4685,
      "step": 49338
    },
    {
      "epoch": 1.515651399256597,
      "grad_norm": 0.45755890011787415,
      "learning_rate": 2.765651688710449e-06,
      "loss": 0.4156,
      "step": 49339
    },
    {
      "epoch": 1.515682118391546,
      "grad_norm": 0.44011709094047546,
      "learning_rate": 2.7653180460258388e-06,
      "loss": 0.5373,
      "step": 49340
    },
    {
      "epoch": 1.5157128375264952,
      "grad_norm": 0.4094291925430298,
      "learning_rate": 2.7649844202383335e-06,
      "loss": 0.4879,
      "step": 49341
    },
    {
      "epoch": 1.5157435566614446,
      "grad_norm": 0.438124418258667,
      "learning_rate": 2.7646508113487137e-06,
      "loss": 0.4621,
      "step": 49342
    },
    {
      "epoch": 1.5157742757963937,
      "grad_norm": 0.45449239015579224,
      "learning_rate": 2.764317219357758e-06,
      "loss": 0.4837,
      "step": 49343
    },
    {
      "epoch": 1.5158049949313428,
      "grad_norm": 0.4143838584423065,
      "learning_rate": 2.7639836442662437e-06,
      "loss": 0.3935,
      "step": 49344
    },
    {
      "epoch": 1.515835714066292,
      "grad_norm": 0.39970508217811584,
      "learning_rate": 2.7636500860749526e-06,
      "loss": 0.4502,
      "step": 49345
    },
    {
      "epoch": 1.515866433201241,
      "grad_norm": 0.4992579221725464,
      "learning_rate": 2.7633165447846568e-06,
      "loss": 0.4526,
      "step": 49346
    },
    {
      "epoch": 1.5158971523361902,
      "grad_norm": 0.43356162309646606,
      "learning_rate": 2.762983020396147e-06,
      "loss": 0.4618,
      "step": 49347
    },
    {
      "epoch": 1.5159278714711393,
      "grad_norm": 0.4350152015686035,
      "learning_rate": 2.7626495129101916e-06,
      "loss": 0.4276,
      "step": 49348
    },
    {
      "epoch": 1.5159585906060884,
      "grad_norm": 0.42024558782577515,
      "learning_rate": 2.762316022327578e-06,
      "loss": 0.4361,
      "step": 49349
    },
    {
      "epoch": 1.5159893097410377,
      "grad_norm": 0.4161982834339142,
      "learning_rate": 2.761982548649077e-06,
      "loss": 0.3986,
      "step": 49350
    },
    {
      "epoch": 1.5160200288759869,
      "grad_norm": 0.4526141285896301,
      "learning_rate": 2.761649091875471e-06,
      "loss": 0.4956,
      "step": 49351
    },
    {
      "epoch": 1.516050748010936,
      "grad_norm": 0.43233901262283325,
      "learning_rate": 2.76131565200754e-06,
      "loss": 0.521,
      "step": 49352
    },
    {
      "epoch": 1.5160814671458853,
      "grad_norm": 0.3952571451663971,
      "learning_rate": 2.7609822290460643e-06,
      "loss": 0.5,
      "step": 49353
    },
    {
      "epoch": 1.5161121862808344,
      "grad_norm": 0.40742209553718567,
      "learning_rate": 2.7606488229918173e-06,
      "loss": 0.4531,
      "step": 49354
    },
    {
      "epoch": 1.5161429054157836,
      "grad_norm": 0.46335798501968384,
      "learning_rate": 2.7603154338455807e-06,
      "loss": 0.4796,
      "step": 49355
    },
    {
      "epoch": 1.5161736245507327,
      "grad_norm": 0.4261803925037384,
      "learning_rate": 2.759982061608132e-06,
      "loss": 0.4592,
      "step": 49356
    },
    {
      "epoch": 1.5162043436856818,
      "grad_norm": 0.47463658452033997,
      "learning_rate": 2.7596487062802545e-06,
      "loss": 0.5105,
      "step": 49357
    },
    {
      "epoch": 1.516235062820631,
      "grad_norm": 0.4566624164581299,
      "learning_rate": 2.7593153678627204e-06,
      "loss": 0.4962,
      "step": 49358
    },
    {
      "epoch": 1.51626578195558,
      "grad_norm": 0.42154890298843384,
      "learning_rate": 2.7589820463563112e-06,
      "loss": 0.4585,
      "step": 49359
    },
    {
      "epoch": 1.5162965010905292,
      "grad_norm": 0.4286278188228607,
      "learning_rate": 2.7586487417618047e-06,
      "loss": 0.5016,
      "step": 49360
    },
    {
      "epoch": 1.5163272202254785,
      "grad_norm": 0.4722723960876465,
      "learning_rate": 2.7583154540799797e-06,
      "loss": 0.4021,
      "step": 49361
    },
    {
      "epoch": 1.5163579393604276,
      "grad_norm": 0.41407570242881775,
      "learning_rate": 2.7579821833116183e-06,
      "loss": 0.4557,
      "step": 49362
    },
    {
      "epoch": 1.5163886584953767,
      "grad_norm": 0.43676653504371643,
      "learning_rate": 2.7576489294574914e-06,
      "loss": 0.574,
      "step": 49363
    },
    {
      "epoch": 1.516419377630326,
      "grad_norm": 0.49021512269973755,
      "learning_rate": 2.757315692518382e-06,
      "loss": 0.4773,
      "step": 49364
    },
    {
      "epoch": 1.5164500967652752,
      "grad_norm": 0.442826509475708,
      "learning_rate": 2.7569824724950666e-06,
      "loss": 0.5324,
      "step": 49365
    },
    {
      "epoch": 1.5164808159002243,
      "grad_norm": 0.41188907623291016,
      "learning_rate": 2.7566492693883285e-06,
      "loss": 0.4061,
      "step": 49366
    },
    {
      "epoch": 1.5165115350351734,
      "grad_norm": 0.42793190479278564,
      "learning_rate": 2.756316083198939e-06,
      "loss": 0.4781,
      "step": 49367
    },
    {
      "epoch": 1.5165422541701226,
      "grad_norm": 0.43355873227119446,
      "learning_rate": 2.7559829139276782e-06,
      "loss": 0.4787,
      "step": 49368
    },
    {
      "epoch": 1.5165729733050717,
      "grad_norm": 0.41519656777381897,
      "learning_rate": 2.7556497615753254e-06,
      "loss": 0.4407,
      "step": 49369
    },
    {
      "epoch": 1.5166036924400208,
      "grad_norm": 0.4246470630168915,
      "learning_rate": 2.7553166261426624e-06,
      "loss": 0.5473,
      "step": 49370
    },
    {
      "epoch": 1.51663441157497,
      "grad_norm": 0.49107950925827026,
      "learning_rate": 2.75498350763046e-06,
      "loss": 0.4716,
      "step": 49371
    },
    {
      "epoch": 1.5166651307099193,
      "grad_norm": 0.41905978322029114,
      "learning_rate": 2.7546504060394984e-06,
      "loss": 0.5253,
      "step": 49372
    },
    {
      "epoch": 1.5166958498448684,
      "grad_norm": 0.4104144871234894,
      "learning_rate": 2.754317321370559e-06,
      "loss": 0.4651,
      "step": 49373
    },
    {
      "epoch": 1.5167265689798175,
      "grad_norm": 0.4347357153892517,
      "learning_rate": 2.753984253624419e-06,
      "loss": 0.4309,
      "step": 49374
    },
    {
      "epoch": 1.5167572881147668,
      "grad_norm": 0.3690589964389801,
      "learning_rate": 2.7536512028018524e-06,
      "loss": 0.4452,
      "step": 49375
    },
    {
      "epoch": 1.516788007249716,
      "grad_norm": 0.41494059562683105,
      "learning_rate": 2.753318168903639e-06,
      "loss": 0.3965,
      "step": 49376
    },
    {
      "epoch": 1.516818726384665,
      "grad_norm": 0.44520965218544006,
      "learning_rate": 2.7529851519305574e-06,
      "loss": 0.5127,
      "step": 49377
    },
    {
      "epoch": 1.5168494455196142,
      "grad_norm": 0.47653260827064514,
      "learning_rate": 2.7526521518833847e-06,
      "loss": 0.5306,
      "step": 49378
    },
    {
      "epoch": 1.5168801646545633,
      "grad_norm": 0.4295419156551361,
      "learning_rate": 2.7523191687629026e-06,
      "loss": 0.4196,
      "step": 49379
    },
    {
      "epoch": 1.5169108837895124,
      "grad_norm": 0.46129167079925537,
      "learning_rate": 2.751986202569882e-06,
      "loss": 0.451,
      "step": 49380
    },
    {
      "epoch": 1.5169416029244616,
      "grad_norm": 0.4002896845340729,
      "learning_rate": 2.7516532533051076e-06,
      "loss": 0.4482,
      "step": 49381
    },
    {
      "epoch": 1.5169723220594107,
      "grad_norm": 0.43243682384490967,
      "learning_rate": 2.751320320969346e-06,
      "loss": 0.4033,
      "step": 49382
    },
    {
      "epoch": 1.5170030411943598,
      "grad_norm": 0.45699819922447205,
      "learning_rate": 2.750987405563389e-06,
      "loss": 0.5179,
      "step": 49383
    },
    {
      "epoch": 1.5170337603293091,
      "grad_norm": 0.42197877168655396,
      "learning_rate": 2.750654507088003e-06,
      "loss": 0.4802,
      "step": 49384
    },
    {
      "epoch": 1.5170644794642583,
      "grad_norm": 0.40153148770332336,
      "learning_rate": 2.7503216255439745e-06,
      "loss": 0.51,
      "step": 49385
    },
    {
      "epoch": 1.5170951985992076,
      "grad_norm": 0.47181132435798645,
      "learning_rate": 2.749988760932072e-06,
      "loss": 0.5096,
      "step": 49386
    },
    {
      "epoch": 1.5171259177341567,
      "grad_norm": 0.3946731388568878,
      "learning_rate": 2.7496559132530763e-06,
      "loss": 0.4731,
      "step": 49387
    },
    {
      "epoch": 1.5171566368691058,
      "grad_norm": 0.410045325756073,
      "learning_rate": 2.7493230825077668e-06,
      "loss": 0.4473,
      "step": 49388
    },
    {
      "epoch": 1.517187356004055,
      "grad_norm": 0.4483962059020996,
      "learning_rate": 2.7489902686969227e-06,
      "loss": 0.4468,
      "step": 49389
    },
    {
      "epoch": 1.517218075139004,
      "grad_norm": 0.4169757068157196,
      "learning_rate": 2.7486574718213145e-06,
      "loss": 0.49,
      "step": 49390
    },
    {
      "epoch": 1.5172487942739532,
      "grad_norm": 0.4334353804588318,
      "learning_rate": 2.748324691881724e-06,
      "loss": 0.4427,
      "step": 49391
    },
    {
      "epoch": 1.5172795134089023,
      "grad_norm": 0.3778739273548126,
      "learning_rate": 2.747991928878927e-06,
      "loss": 0.4469,
      "step": 49392
    },
    {
      "epoch": 1.5173102325438514,
      "grad_norm": 0.5327522158622742,
      "learning_rate": 2.7476591828137047e-06,
      "loss": 0.5064,
      "step": 49393
    },
    {
      "epoch": 1.5173409516788006,
      "grad_norm": 0.42568570375442505,
      "learning_rate": 2.7473264536868273e-06,
      "loss": 0.4609,
      "step": 49394
    },
    {
      "epoch": 1.51737167081375,
      "grad_norm": 0.40659457445144653,
      "learning_rate": 2.7469937414990754e-06,
      "loss": 0.5277,
      "step": 49395
    },
    {
      "epoch": 1.517402389948699,
      "grad_norm": 0.4463045001029968,
      "learning_rate": 2.7466610462512277e-06,
      "loss": 0.4576,
      "step": 49396
    },
    {
      "epoch": 1.5174331090836484,
      "grad_norm": 0.3983890414237976,
      "learning_rate": 2.7463283679440576e-06,
      "loss": 0.4345,
      "step": 49397
    },
    {
      "epoch": 1.5174638282185975,
      "grad_norm": 0.4575938880443573,
      "learning_rate": 2.7459957065783494e-06,
      "loss": 0.4732,
      "step": 49398
    },
    {
      "epoch": 1.5174945473535466,
      "grad_norm": 0.4107765853404999,
      "learning_rate": 2.7456630621548697e-06,
      "loss": 0.4256,
      "step": 49399
    },
    {
      "epoch": 1.5175252664884957,
      "grad_norm": 0.4001942276954651,
      "learning_rate": 2.7453304346744016e-06,
      "loss": 0.5206,
      "step": 49400
    },
    {
      "epoch": 1.5175559856234448,
      "grad_norm": 0.4614139497280121,
      "learning_rate": 2.7449978241377205e-06,
      "loss": 0.5085,
      "step": 49401
    },
    {
      "epoch": 1.517586704758394,
      "grad_norm": 0.4785151481628418,
      "learning_rate": 2.744665230545608e-06,
      "loss": 0.4859,
      "step": 49402
    },
    {
      "epoch": 1.517617423893343,
      "grad_norm": 0.4342496991157532,
      "learning_rate": 2.7443326538988323e-06,
      "loss": 0.4444,
      "step": 49403
    },
    {
      "epoch": 1.5176481430282922,
      "grad_norm": 0.42183998227119446,
      "learning_rate": 2.744000094198175e-06,
      "loss": 0.4799,
      "step": 49404
    },
    {
      "epoch": 1.5176788621632413,
      "grad_norm": 0.43284958600997925,
      "learning_rate": 2.7436675514444113e-06,
      "loss": 0.4708,
      "step": 49405
    },
    {
      "epoch": 1.5177095812981907,
      "grad_norm": 0.4690344035625458,
      "learning_rate": 2.7433350256383227e-06,
      "loss": 0.4661,
      "step": 49406
    },
    {
      "epoch": 1.5177403004331398,
      "grad_norm": 0.38948747515678406,
      "learning_rate": 2.7430025167806786e-06,
      "loss": 0.391,
      "step": 49407
    },
    {
      "epoch": 1.517771019568089,
      "grad_norm": 0.4893857538700104,
      "learning_rate": 2.7426700248722615e-06,
      "loss": 0.4808,
      "step": 49408
    },
    {
      "epoch": 1.5178017387030383,
      "grad_norm": 0.4820247292518616,
      "learning_rate": 2.7423375499138407e-06,
      "loss": 0.4141,
      "step": 49409
    },
    {
      "epoch": 1.5178324578379874,
      "grad_norm": 0.45924821496009827,
      "learning_rate": 2.7420050919062025e-06,
      "loss": 0.3997,
      "step": 49410
    },
    {
      "epoch": 1.5178631769729365,
      "grad_norm": 0.4134930372238159,
      "learning_rate": 2.7416726508501158e-06,
      "loss": 0.4618,
      "step": 49411
    },
    {
      "epoch": 1.5178938961078856,
      "grad_norm": 0.4482611417770386,
      "learning_rate": 2.7413402267463617e-06,
      "loss": 0.4644,
      "step": 49412
    },
    {
      "epoch": 1.5179246152428347,
      "grad_norm": 0.4704113006591797,
      "learning_rate": 2.741007819595709e-06,
      "loss": 0.4905,
      "step": 49413
    },
    {
      "epoch": 1.5179553343777838,
      "grad_norm": 0.42388641834259033,
      "learning_rate": 2.7406754293989423e-06,
      "loss": 0.4889,
      "step": 49414
    },
    {
      "epoch": 1.517986053512733,
      "grad_norm": 0.4105469584465027,
      "learning_rate": 2.7403430561568376e-06,
      "loss": 0.4598,
      "step": 49415
    },
    {
      "epoch": 1.518016772647682,
      "grad_norm": 0.45429712533950806,
      "learning_rate": 2.740010699870167e-06,
      "loss": 0.4795,
      "step": 49416
    },
    {
      "epoch": 1.5180474917826314,
      "grad_norm": 0.42074424028396606,
      "learning_rate": 2.7396783605397104e-06,
      "loss": 0.4752,
      "step": 49417
    },
    {
      "epoch": 1.5180782109175806,
      "grad_norm": 0.42941948771476746,
      "learning_rate": 2.7393460381662363e-06,
      "loss": 0.428,
      "step": 49418
    },
    {
      "epoch": 1.5181089300525297,
      "grad_norm": 0.43097469210624695,
      "learning_rate": 2.739013732750533e-06,
      "loss": 0.4597,
      "step": 49419
    },
    {
      "epoch": 1.518139649187479,
      "grad_norm": 0.40858975052833557,
      "learning_rate": 2.7386814442933675e-06,
      "loss": 0.4147,
      "step": 49420
    },
    {
      "epoch": 1.5181703683224281,
      "grad_norm": 0.42892566323280334,
      "learning_rate": 2.7383491727955204e-06,
      "loss": 0.4804,
      "step": 49421
    },
    {
      "epoch": 1.5182010874573773,
      "grad_norm": 0.4138141870498657,
      "learning_rate": 2.7380169182577645e-06,
      "loss": 0.4825,
      "step": 49422
    },
    {
      "epoch": 1.5182318065923264,
      "grad_norm": 0.4064251184463501,
      "learning_rate": 2.7376846806808755e-06,
      "loss": 0.4484,
      "step": 49423
    },
    {
      "epoch": 1.5182625257272755,
      "grad_norm": 0.4669242799282074,
      "learning_rate": 2.737352460065632e-06,
      "loss": 0.5052,
      "step": 49424
    },
    {
      "epoch": 1.5182932448622246,
      "grad_norm": 0.4207437038421631,
      "learning_rate": 2.7370202564128125e-06,
      "loss": 0.4584,
      "step": 49425
    },
    {
      "epoch": 1.5183239639971737,
      "grad_norm": 0.41807612776756287,
      "learning_rate": 2.7366880697231855e-06,
      "loss": 0.4429,
      "step": 49426
    },
    {
      "epoch": 1.5183546831321229,
      "grad_norm": 0.4130042493343353,
      "learning_rate": 2.7363558999975316e-06,
      "loss": 0.4046,
      "step": 49427
    },
    {
      "epoch": 1.5183854022670722,
      "grad_norm": 0.3992272913455963,
      "learning_rate": 2.736023747236626e-06,
      "loss": 0.3621,
      "step": 49428
    },
    {
      "epoch": 1.5184161214020213,
      "grad_norm": 0.4011901617050171,
      "learning_rate": 2.735691611441246e-06,
      "loss": 0.4289,
      "step": 49429
    },
    {
      "epoch": 1.5184468405369704,
      "grad_norm": 0.4478399157524109,
      "learning_rate": 2.735359492612164e-06,
      "loss": 0.4617,
      "step": 49430
    },
    {
      "epoch": 1.5184775596719198,
      "grad_norm": 0.45709532499313354,
      "learning_rate": 2.7350273907501558e-06,
      "loss": 0.4362,
      "step": 49431
    },
    {
      "epoch": 1.518508278806869,
      "grad_norm": 0.42285019159317017,
      "learning_rate": 2.734695305856e-06,
      "loss": 0.4948,
      "step": 49432
    },
    {
      "epoch": 1.518538997941818,
      "grad_norm": 0.39429178833961487,
      "learning_rate": 2.7343632379304695e-06,
      "loss": 0.455,
      "step": 49433
    },
    {
      "epoch": 1.5185697170767671,
      "grad_norm": 0.3988901674747467,
      "learning_rate": 2.734031186974344e-06,
      "loss": 0.4459,
      "step": 49434
    },
    {
      "epoch": 1.5186004362117163,
      "grad_norm": 0.4465341567993164,
      "learning_rate": 2.733699152988394e-06,
      "loss": 0.4354,
      "step": 49435
    },
    {
      "epoch": 1.5186311553466654,
      "grad_norm": 0.4235500693321228,
      "learning_rate": 2.733367135973397e-06,
      "loss": 0.4865,
      "step": 49436
    },
    {
      "epoch": 1.5186618744816145,
      "grad_norm": 0.442711740732193,
      "learning_rate": 2.7330351359301277e-06,
      "loss": 0.4849,
      "step": 49437
    },
    {
      "epoch": 1.5186925936165636,
      "grad_norm": 0.4058332145214081,
      "learning_rate": 2.7327031528593663e-06,
      "loss": 0.5259,
      "step": 49438
    },
    {
      "epoch": 1.518723312751513,
      "grad_norm": 0.39069047570228577,
      "learning_rate": 2.732371186761881e-06,
      "loss": 0.4755,
      "step": 49439
    },
    {
      "epoch": 1.518754031886462,
      "grad_norm": 0.4338076710700989,
      "learning_rate": 2.732039237638451e-06,
      "loss": 0.4584,
      "step": 49440
    },
    {
      "epoch": 1.5187847510214112,
      "grad_norm": 0.4235057532787323,
      "learning_rate": 2.731707305489849e-06,
      "loss": 0.4518,
      "step": 49441
    },
    {
      "epoch": 1.5188154701563605,
      "grad_norm": 0.40787699818611145,
      "learning_rate": 2.7313753903168573e-06,
      "loss": 0.455,
      "step": 49442
    },
    {
      "epoch": 1.5188461892913097,
      "grad_norm": 0.40980327129364014,
      "learning_rate": 2.7310434921202422e-06,
      "loss": 0.4657,
      "step": 49443
    },
    {
      "epoch": 1.5188769084262588,
      "grad_norm": 0.4246547520160675,
      "learning_rate": 2.7307116109007847e-06,
      "loss": 0.4321,
      "step": 49444
    },
    {
      "epoch": 1.518907627561208,
      "grad_norm": 0.45641833543777466,
      "learning_rate": 2.730379746659253e-06,
      "loss": 0.4246,
      "step": 49445
    },
    {
      "epoch": 1.518938346696157,
      "grad_norm": 0.4123014509677887,
      "learning_rate": 2.730047899396433e-06,
      "loss": 0.4495,
      "step": 49446
    },
    {
      "epoch": 1.5189690658311061,
      "grad_norm": 0.39935678243637085,
      "learning_rate": 2.729716069113091e-06,
      "loss": 0.4469,
      "step": 49447
    },
    {
      "epoch": 1.5189997849660553,
      "grad_norm": 0.3985869884490967,
      "learning_rate": 2.729384255810008e-06,
      "loss": 0.5138,
      "step": 49448
    },
    {
      "epoch": 1.5190305041010044,
      "grad_norm": 0.4727383553981781,
      "learning_rate": 2.729052459487952e-06,
      "loss": 0.5079,
      "step": 49449
    },
    {
      "epoch": 1.5190612232359537,
      "grad_norm": 0.4313342869281769,
      "learning_rate": 2.7287206801476995e-06,
      "loss": 0.475,
      "step": 49450
    },
    {
      "epoch": 1.5190919423709028,
      "grad_norm": 0.4253104627132416,
      "learning_rate": 2.7283889177900335e-06,
      "loss": 0.464,
      "step": 49451
    },
    {
      "epoch": 1.519122661505852,
      "grad_norm": 0.4481125473976135,
      "learning_rate": 2.7280571724157202e-06,
      "loss": 0.4507,
      "step": 49452
    },
    {
      "epoch": 1.5191533806408013,
      "grad_norm": 0.41166430711746216,
      "learning_rate": 2.7277254440255394e-06,
      "loss": 0.4572,
      "step": 49453
    },
    {
      "epoch": 1.5191840997757504,
      "grad_norm": 0.4177056550979614,
      "learning_rate": 2.727393732620258e-06,
      "loss": 0.4687,
      "step": 49454
    },
    {
      "epoch": 1.5192148189106995,
      "grad_norm": 0.43409407138824463,
      "learning_rate": 2.727062038200663e-06,
      "loss": 0.4568,
      "step": 49455
    },
    {
      "epoch": 1.5192455380456487,
      "grad_norm": 0.4117612838745117,
      "learning_rate": 2.72673036076752e-06,
      "loss": 0.475,
      "step": 49456
    },
    {
      "epoch": 1.5192762571805978,
      "grad_norm": 0.44663411378860474,
      "learning_rate": 2.7263987003216076e-06,
      "loss": 0.5087,
      "step": 49457
    },
    {
      "epoch": 1.519306976315547,
      "grad_norm": 0.3995130658149719,
      "learning_rate": 2.726067056863697e-06,
      "loss": 0.3979,
      "step": 49458
    },
    {
      "epoch": 1.519337695450496,
      "grad_norm": 0.4121509790420532,
      "learning_rate": 2.725735430394565e-06,
      "loss": 0.4093,
      "step": 49459
    },
    {
      "epoch": 1.5193684145854451,
      "grad_norm": 0.4327675998210907,
      "learning_rate": 2.725403820914986e-06,
      "loss": 0.4436,
      "step": 49460
    },
    {
      "epoch": 1.5193991337203945,
      "grad_norm": 0.41247206926345825,
      "learning_rate": 2.725072228425737e-06,
      "loss": 0.4519,
      "step": 49461
    },
    {
      "epoch": 1.5194298528553436,
      "grad_norm": 0.40355414152145386,
      "learning_rate": 2.7247406529275866e-06,
      "loss": 0.4038,
      "step": 49462
    },
    {
      "epoch": 1.5194605719902927,
      "grad_norm": 0.5097099542617798,
      "learning_rate": 2.724409094421313e-06,
      "loss": 0.4135,
      "step": 49463
    },
    {
      "epoch": 1.519491291125242,
      "grad_norm": 0.4263906478881836,
      "learning_rate": 2.72407755290769e-06,
      "loss": 0.4159,
      "step": 49464
    },
    {
      "epoch": 1.5195220102601912,
      "grad_norm": 0.541149377822876,
      "learning_rate": 2.723746028387495e-06,
      "loss": 0.4422,
      "step": 49465
    },
    {
      "epoch": 1.5195527293951403,
      "grad_norm": 0.4621351957321167,
      "learning_rate": 2.723414520861496e-06,
      "loss": 0.5007,
      "step": 49466
    },
    {
      "epoch": 1.5195834485300894,
      "grad_norm": 0.44685670733451843,
      "learning_rate": 2.723083030330471e-06,
      "loss": 0.437,
      "step": 49467
    },
    {
      "epoch": 1.5196141676650385,
      "grad_norm": 0.46638500690460205,
      "learning_rate": 2.7227515567951933e-06,
      "loss": 0.4866,
      "step": 49468
    },
    {
      "epoch": 1.5196448867999877,
      "grad_norm": 0.4737400412559509,
      "learning_rate": 2.722420100256439e-06,
      "loss": 0.4915,
      "step": 49469
    },
    {
      "epoch": 1.5196756059349368,
      "grad_norm": 0.4381982982158661,
      "learning_rate": 2.7220886607149823e-06,
      "loss": 0.4364,
      "step": 49470
    },
    {
      "epoch": 1.519706325069886,
      "grad_norm": 0.467133104801178,
      "learning_rate": 2.721757238171593e-06,
      "loss": 0.4289,
      "step": 49471
    },
    {
      "epoch": 1.5197370442048352,
      "grad_norm": 0.5920689105987549,
      "learning_rate": 2.7214258326270483e-06,
      "loss": 0.4354,
      "step": 49472
    },
    {
      "epoch": 1.5197677633397844,
      "grad_norm": 0.3998098373413086,
      "learning_rate": 2.721094444082122e-06,
      "loss": 0.4213,
      "step": 49473
    },
    {
      "epoch": 1.5197984824747335,
      "grad_norm": 0.7209857702255249,
      "learning_rate": 2.720763072537591e-06,
      "loss": 0.4785,
      "step": 49474
    },
    {
      "epoch": 1.5198292016096828,
      "grad_norm": 0.4918924868106842,
      "learning_rate": 2.720431717994223e-06,
      "loss": 0.4997,
      "step": 49475
    },
    {
      "epoch": 1.519859920744632,
      "grad_norm": 0.46146324276924133,
      "learning_rate": 2.7201003804527947e-06,
      "loss": 0.5425,
      "step": 49476
    },
    {
      "epoch": 1.519890639879581,
      "grad_norm": 0.42426371574401855,
      "learning_rate": 2.7197690599140814e-06,
      "loss": 0.4578,
      "step": 49477
    },
    {
      "epoch": 1.5199213590145302,
      "grad_norm": 0.45219308137893677,
      "learning_rate": 2.7194377563788587e-06,
      "loss": 0.4822,
      "step": 49478
    },
    {
      "epoch": 1.5199520781494793,
      "grad_norm": 0.45434653759002686,
      "learning_rate": 2.719106469847894e-06,
      "loss": 0.5445,
      "step": 49479
    },
    {
      "epoch": 1.5199827972844284,
      "grad_norm": 0.46687278151512146,
      "learning_rate": 2.718775200321968e-06,
      "loss": 0.5188,
      "step": 49480
    },
    {
      "epoch": 1.5200135164193775,
      "grad_norm": 0.3889997899532318,
      "learning_rate": 2.718443947801844e-06,
      "loss": 0.5203,
      "step": 49481
    },
    {
      "epoch": 1.5200442355543267,
      "grad_norm": 0.4116603434085846,
      "learning_rate": 2.71811271228831e-06,
      "loss": 0.4613,
      "step": 49482
    },
    {
      "epoch": 1.520074954689276,
      "grad_norm": 0.42622414231300354,
      "learning_rate": 2.7177814937821288e-06,
      "loss": 0.4614,
      "step": 49483
    },
    {
      "epoch": 1.5201056738242251,
      "grad_norm": 0.4462123215198517,
      "learning_rate": 2.717450292284081e-06,
      "loss": 0.4271,
      "step": 49484
    },
    {
      "epoch": 1.5201363929591742,
      "grad_norm": 0.4038101136684418,
      "learning_rate": 2.7171191077949334e-06,
      "loss": 0.5136,
      "step": 49485
    },
    {
      "epoch": 1.5201671120941236,
      "grad_norm": 0.41214093565940857,
      "learning_rate": 2.7167879403154595e-06,
      "loss": 0.4807,
      "step": 49486
    },
    {
      "epoch": 1.5201978312290727,
      "grad_norm": 0.4393301010131836,
      "learning_rate": 2.716456789846442e-06,
      "loss": 0.4308,
      "step": 49487
    },
    {
      "epoch": 1.5202285503640218,
      "grad_norm": 0.48002636432647705,
      "learning_rate": 2.7161256563886463e-06,
      "loss": 0.4606,
      "step": 49488
    },
    {
      "epoch": 1.520259269498971,
      "grad_norm": 0.4201889932155609,
      "learning_rate": 2.71579453994285e-06,
      "loss": 0.4705,
      "step": 49489
    },
    {
      "epoch": 1.52028998863392,
      "grad_norm": 0.4326620399951935,
      "learning_rate": 2.715463440509821e-06,
      "loss": 0.5139,
      "step": 49490
    },
    {
      "epoch": 1.5203207077688692,
      "grad_norm": 0.4336419403553009,
      "learning_rate": 2.7151323580903356e-06,
      "loss": 0.4023,
      "step": 49491
    },
    {
      "epoch": 1.5203514269038183,
      "grad_norm": 0.4187212884426117,
      "learning_rate": 2.7148012926851686e-06,
      "loss": 0.5254,
      "step": 49492
    },
    {
      "epoch": 1.5203821460387674,
      "grad_norm": 0.42357897758483887,
      "learning_rate": 2.7144702442950945e-06,
      "loss": 0.4412,
      "step": 49493
    },
    {
      "epoch": 1.5204128651737165,
      "grad_norm": 0.44862672686576843,
      "learning_rate": 2.7141392129208797e-06,
      "loss": 0.4557,
      "step": 49494
    },
    {
      "epoch": 1.5204435843086659,
      "grad_norm": 0.40275904536247253,
      "learning_rate": 2.7138081985633036e-06,
      "loss": 0.4565,
      "step": 49495
    },
    {
      "epoch": 1.520474303443615,
      "grad_norm": 0.4054282307624817,
      "learning_rate": 2.7134772012231357e-06,
      "loss": 0.471,
      "step": 49496
    },
    {
      "epoch": 1.5205050225785643,
      "grad_norm": 0.4534004330635071,
      "learning_rate": 2.713146220901155e-06,
      "loss": 0.4665,
      "step": 49497
    },
    {
      "epoch": 1.5205357417135135,
      "grad_norm": 0.374636173248291,
      "learning_rate": 2.712815257598126e-06,
      "loss": 0.4014,
      "step": 49498
    },
    {
      "epoch": 1.5205664608484626,
      "grad_norm": 0.47104671597480774,
      "learning_rate": 2.712484311314827e-06,
      "loss": 0.4656,
      "step": 49499
    },
    {
      "epoch": 1.5205971799834117,
      "grad_norm": 0.4687599837779999,
      "learning_rate": 2.7121533820520296e-06,
      "loss": 0.4752,
      "step": 49500
    },
    {
      "epoch": 1.5206278991183608,
      "grad_norm": 0.4415384531021118,
      "learning_rate": 2.711822469810509e-06,
      "loss": 0.475,
      "step": 49501
    },
    {
      "epoch": 1.52065861825331,
      "grad_norm": 0.4000471830368042,
      "learning_rate": 2.711491574591034e-06,
      "loss": 0.466,
      "step": 49502
    },
    {
      "epoch": 1.520689337388259,
      "grad_norm": 0.40781381726264954,
      "learning_rate": 2.711160696394379e-06,
      "loss": 0.4853,
      "step": 49503
    },
    {
      "epoch": 1.5207200565232082,
      "grad_norm": 0.4434644877910614,
      "learning_rate": 2.710829835221318e-06,
      "loss": 0.4933,
      "step": 49504
    },
    {
      "epoch": 1.5207507756581573,
      "grad_norm": 0.4811857044696808,
      "learning_rate": 2.710498991072622e-06,
      "loss": 0.3787,
      "step": 49505
    },
    {
      "epoch": 1.5207814947931066,
      "grad_norm": 0.39060431718826294,
      "learning_rate": 2.7101681639490684e-06,
      "loss": 0.4473,
      "step": 49506
    },
    {
      "epoch": 1.5208122139280558,
      "grad_norm": 0.4073983430862427,
      "learning_rate": 2.709837353851422e-06,
      "loss": 0.4679,
      "step": 49507
    },
    {
      "epoch": 1.520842933063005,
      "grad_norm": 0.40550941228866577,
      "learning_rate": 2.7095065607804605e-06,
      "loss": 0.4298,
      "step": 49508
    },
    {
      "epoch": 1.5208736521979542,
      "grad_norm": 0.4302714169025421,
      "learning_rate": 2.709175784736956e-06,
      "loss": 0.4239,
      "step": 49509
    },
    {
      "epoch": 1.5209043713329033,
      "grad_norm": 0.47593653202056885,
      "learning_rate": 2.7088450257216835e-06,
      "loss": 0.5011,
      "step": 49510
    },
    {
      "epoch": 1.5209350904678525,
      "grad_norm": 0.3979412317276001,
      "learning_rate": 2.7085142837354095e-06,
      "loss": 0.4798,
      "step": 49511
    },
    {
      "epoch": 1.5209658096028016,
      "grad_norm": 0.4415832757949829,
      "learning_rate": 2.7081835587789116e-06,
      "loss": 0.4241,
      "step": 49512
    },
    {
      "epoch": 1.5209965287377507,
      "grad_norm": 0.44284501671791077,
      "learning_rate": 2.7078528508529556e-06,
      "loss": 0.4552,
      "step": 49513
    },
    {
      "epoch": 1.5210272478726998,
      "grad_norm": 0.4184475243091583,
      "learning_rate": 2.7075221599583233e-06,
      "loss": 0.457,
      "step": 49514
    },
    {
      "epoch": 1.521057967007649,
      "grad_norm": 0.4338573217391968,
      "learning_rate": 2.7071914860957803e-06,
      "loss": 0.5106,
      "step": 49515
    },
    {
      "epoch": 1.521088686142598,
      "grad_norm": 0.4205886423587799,
      "learning_rate": 2.7068608292661034e-06,
      "loss": 0.4594,
      "step": 49516
    },
    {
      "epoch": 1.5211194052775474,
      "grad_norm": 0.41269487142562866,
      "learning_rate": 2.7065301894700567e-06,
      "loss": 0.4841,
      "step": 49517
    },
    {
      "epoch": 1.5211501244124965,
      "grad_norm": 0.4163013994693756,
      "learning_rate": 2.7061995667084253e-06,
      "loss": 0.3898,
      "step": 49518
    },
    {
      "epoch": 1.5211808435474456,
      "grad_norm": 0.4079601764678955,
      "learning_rate": 2.705868960981969e-06,
      "loss": 0.5031,
      "step": 49519
    },
    {
      "epoch": 1.521211562682395,
      "grad_norm": 0.4115407466888428,
      "learning_rate": 2.7055383722914696e-06,
      "loss": 0.5214,
      "step": 49520
    },
    {
      "epoch": 1.521242281817344,
      "grad_norm": 0.4970279037952423,
      "learning_rate": 2.7052078006376916e-06,
      "loss": 0.4226,
      "step": 49521
    },
    {
      "epoch": 1.5212730009522932,
      "grad_norm": 0.44710037112236023,
      "learning_rate": 2.7048772460214066e-06,
      "loss": 0.5603,
      "step": 49522
    },
    {
      "epoch": 1.5213037200872424,
      "grad_norm": 0.4460713565349579,
      "learning_rate": 2.7045467084433965e-06,
      "loss": 0.478,
      "step": 49523
    },
    {
      "epoch": 1.5213344392221915,
      "grad_norm": 0.4037334620952606,
      "learning_rate": 2.704216187904424e-06,
      "loss": 0.4985,
      "step": 49524
    },
    {
      "epoch": 1.5213651583571406,
      "grad_norm": 0.4433377683162689,
      "learning_rate": 2.7038856844052674e-06,
      "loss": 0.4729,
      "step": 49525
    },
    {
      "epoch": 1.5213958774920897,
      "grad_norm": 0.42532750964164734,
      "learning_rate": 2.703555197946692e-06,
      "loss": 0.5185,
      "step": 49526
    },
    {
      "epoch": 1.5214265966270388,
      "grad_norm": 0.3986095190048218,
      "learning_rate": 2.7032247285294732e-06,
      "loss": 0.4948,
      "step": 49527
    },
    {
      "epoch": 1.5214573157619882,
      "grad_norm": 0.4882756173610687,
      "learning_rate": 2.702894276154383e-06,
      "loss": 0.4799,
      "step": 49528
    },
    {
      "epoch": 1.5214880348969373,
      "grad_norm": 0.44087469577789307,
      "learning_rate": 2.7025638408221953e-06,
      "loss": 0.5432,
      "step": 49529
    },
    {
      "epoch": 1.5215187540318864,
      "grad_norm": 0.4439779818058014,
      "learning_rate": 2.7022334225336765e-06,
      "loss": 0.5273,
      "step": 49530
    },
    {
      "epoch": 1.5215494731668358,
      "grad_norm": 0.41937071084976196,
      "learning_rate": 2.701903021289601e-06,
      "loss": 0.5093,
      "step": 49531
    },
    {
      "epoch": 1.5215801923017849,
      "grad_norm": 0.4136817753314972,
      "learning_rate": 2.701572637090741e-06,
      "loss": 0.4255,
      "step": 49532
    },
    {
      "epoch": 1.521610911436734,
      "grad_norm": 0.42595458030700684,
      "learning_rate": 2.7012422699378717e-06,
      "loss": 0.4762,
      "step": 49533
    },
    {
      "epoch": 1.5216416305716831,
      "grad_norm": 0.4038589298725128,
      "learning_rate": 2.7009119198317567e-06,
      "loss": 0.4065,
      "step": 49534
    },
    {
      "epoch": 1.5216723497066322,
      "grad_norm": 0.41651350259780884,
      "learning_rate": 2.700581586773172e-06,
      "loss": 0.5446,
      "step": 49535
    },
    {
      "epoch": 1.5217030688415814,
      "grad_norm": 0.5157681107521057,
      "learning_rate": 2.7002512707628894e-06,
      "loss": 0.4031,
      "step": 49536
    },
    {
      "epoch": 1.5217337879765305,
      "grad_norm": 0.43799906969070435,
      "learning_rate": 2.6999209718016817e-06,
      "loss": 0.469,
      "step": 49537
    },
    {
      "epoch": 1.5217645071114796,
      "grad_norm": 0.471871942281723,
      "learning_rate": 2.699590689890316e-06,
      "loss": 0.4764,
      "step": 49538
    },
    {
      "epoch": 1.521795226246429,
      "grad_norm": 0.44667235016822815,
      "learning_rate": 2.699260425029566e-06,
      "loss": 0.5091,
      "step": 49539
    },
    {
      "epoch": 1.521825945381378,
      "grad_norm": 0.3872148096561432,
      "learning_rate": 2.6989301772202025e-06,
      "loss": 0.4983,
      "step": 49540
    },
    {
      "epoch": 1.5218566645163272,
      "grad_norm": 0.3976094126701355,
      "learning_rate": 2.6985999464629987e-06,
      "loss": 0.4873,
      "step": 49541
    },
    {
      "epoch": 1.5218873836512765,
      "grad_norm": 0.47792842984199524,
      "learning_rate": 2.698269732758727e-06,
      "loss": 0.4599,
      "step": 49542
    },
    {
      "epoch": 1.5219181027862256,
      "grad_norm": 0.4182330071926117,
      "learning_rate": 2.697939536108153e-06,
      "loss": 0.494,
      "step": 49543
    },
    {
      "epoch": 1.5219488219211748,
      "grad_norm": 0.4566457271575928,
      "learning_rate": 2.6976093565120508e-06,
      "loss": 0.5591,
      "step": 49544
    },
    {
      "epoch": 1.5219795410561239,
      "grad_norm": 0.39994707703590393,
      "learning_rate": 2.697279193971193e-06,
      "loss": 0.4769,
      "step": 49545
    },
    {
      "epoch": 1.522010260191073,
      "grad_norm": 0.41231998801231384,
      "learning_rate": 2.6969490484863523e-06,
      "loss": 0.4395,
      "step": 49546
    },
    {
      "epoch": 1.5220409793260221,
      "grad_norm": 0.4783509373664856,
      "learning_rate": 2.696618920058294e-06,
      "loss": 0.4343,
      "step": 49547
    },
    {
      "epoch": 1.5220716984609712,
      "grad_norm": 0.553810715675354,
      "learning_rate": 2.696288808687796e-06,
      "loss": 0.4208,
      "step": 49548
    },
    {
      "epoch": 1.5221024175959204,
      "grad_norm": 0.4309743046760559,
      "learning_rate": 2.695958714375618e-06,
      "loss": 0.4606,
      "step": 49549
    },
    {
      "epoch": 1.5221331367308697,
      "grad_norm": 0.43746471405029297,
      "learning_rate": 2.695628637122546e-06,
      "loss": 0.5163,
      "step": 49550
    },
    {
      "epoch": 1.5221638558658188,
      "grad_norm": 0.3894050717353821,
      "learning_rate": 2.6952985769293393e-06,
      "loss": 0.4444,
      "step": 49551
    },
    {
      "epoch": 1.522194575000768,
      "grad_norm": 0.43273505568504333,
      "learning_rate": 2.694968533796777e-06,
      "loss": 0.5046,
      "step": 49552
    },
    {
      "epoch": 1.5222252941357173,
      "grad_norm": 0.4445185959339142,
      "learning_rate": 2.6946385077256222e-06,
      "loss": 0.4351,
      "step": 49553
    },
    {
      "epoch": 1.5222560132706664,
      "grad_norm": 0.4379459321498871,
      "learning_rate": 2.6943084987166503e-06,
      "loss": 0.5204,
      "step": 49554
    },
    {
      "epoch": 1.5222867324056155,
      "grad_norm": 0.40926721692085266,
      "learning_rate": 2.6939785067706303e-06,
      "loss": 0.4835,
      "step": 49555
    },
    {
      "epoch": 1.5223174515405646,
      "grad_norm": 0.49303293228149414,
      "learning_rate": 2.6936485318883367e-06,
      "loss": 0.4765,
      "step": 49556
    },
    {
      "epoch": 1.5223481706755138,
      "grad_norm": 0.3882773518562317,
      "learning_rate": 2.693318574070535e-06,
      "loss": 0.4484,
      "step": 49557
    },
    {
      "epoch": 1.5223788898104629,
      "grad_norm": 0.4144831597805023,
      "learning_rate": 2.6929886333179965e-06,
      "loss": 0.4988,
      "step": 49558
    },
    {
      "epoch": 1.522409608945412,
      "grad_norm": 0.3835555613040924,
      "learning_rate": 2.692658709631495e-06,
      "loss": 0.4048,
      "step": 49559
    },
    {
      "epoch": 1.5224403280803611,
      "grad_norm": 0.40212807059288025,
      "learning_rate": 2.692328803011798e-06,
      "loss": 0.4812,
      "step": 49560
    },
    {
      "epoch": 1.5224710472153105,
      "grad_norm": 0.40638139843940735,
      "learning_rate": 2.6919989134596814e-06,
      "loss": 0.4297,
      "step": 49561
    },
    {
      "epoch": 1.5225017663502596,
      "grad_norm": 0.4447123110294342,
      "learning_rate": 2.6916690409759085e-06,
      "loss": 0.4596,
      "step": 49562
    },
    {
      "epoch": 1.5225324854852087,
      "grad_norm": 0.41781148314476013,
      "learning_rate": 2.6913391855612526e-06,
      "loss": 0.464,
      "step": 49563
    },
    {
      "epoch": 1.522563204620158,
      "grad_norm": 0.44491952657699585,
      "learning_rate": 2.6910093472164854e-06,
      "loss": 0.4598,
      "step": 49564
    },
    {
      "epoch": 1.5225939237551072,
      "grad_norm": 0.42123156785964966,
      "learning_rate": 2.690679525942379e-06,
      "loss": 0.4723,
      "step": 49565
    },
    {
      "epoch": 1.5226246428900563,
      "grad_norm": 0.47111770510673523,
      "learning_rate": 2.6903497217396967e-06,
      "loss": 0.4302,
      "step": 49566
    },
    {
      "epoch": 1.5226553620250054,
      "grad_norm": 0.40254896879196167,
      "learning_rate": 2.6900199346092147e-06,
      "loss": 0.4051,
      "step": 49567
    },
    {
      "epoch": 1.5226860811599545,
      "grad_norm": 0.3973981440067291,
      "learning_rate": 2.6896901645517015e-06,
      "loss": 0.4348,
      "step": 49568
    },
    {
      "epoch": 1.5227168002949036,
      "grad_norm": 0.42318597435951233,
      "learning_rate": 2.6893604115679293e-06,
      "loss": 0.3622,
      "step": 49569
    },
    {
      "epoch": 1.5227475194298528,
      "grad_norm": 0.4293838441371918,
      "learning_rate": 2.6890306756586647e-06,
      "loss": 0.4726,
      "step": 49570
    },
    {
      "epoch": 1.5227782385648019,
      "grad_norm": 0.3923851549625397,
      "learning_rate": 2.688700956824679e-06,
      "loss": 0.4201,
      "step": 49571
    },
    {
      "epoch": 1.5228089576997512,
      "grad_norm": 0.42300570011138916,
      "learning_rate": 2.6883712550667428e-06,
      "loss": 0.4277,
      "step": 49572
    },
    {
      "epoch": 1.5228396768347003,
      "grad_norm": 0.41726529598236084,
      "learning_rate": 2.68804157038563e-06,
      "loss": 0.5314,
      "step": 49573
    },
    {
      "epoch": 1.5228703959696495,
      "grad_norm": 0.37767866253852844,
      "learning_rate": 2.687711902782103e-06,
      "loss": 0.4126,
      "step": 49574
    },
    {
      "epoch": 1.5229011151045988,
      "grad_norm": 0.4059719145298004,
      "learning_rate": 2.687382252256938e-06,
      "loss": 0.4235,
      "step": 49575
    },
    {
      "epoch": 1.522931834239548,
      "grad_norm": 0.4150848090648651,
      "learning_rate": 2.6870526188108968e-06,
      "loss": 0.4325,
      "step": 49576
    },
    {
      "epoch": 1.522962553374497,
      "grad_norm": 0.4875926673412323,
      "learning_rate": 2.6867230024447586e-06,
      "loss": 0.4423,
      "step": 49577
    },
    {
      "epoch": 1.5229932725094462,
      "grad_norm": 0.4337139427661896,
      "learning_rate": 2.686393403159293e-06,
      "loss": 0.4837,
      "step": 49578
    },
    {
      "epoch": 1.5230239916443953,
      "grad_norm": 0.3815775513648987,
      "learning_rate": 2.6860638209552626e-06,
      "loss": 0.4805,
      "step": 49579
    },
    {
      "epoch": 1.5230547107793444,
      "grad_norm": 0.4720799922943115,
      "learning_rate": 2.685734255833441e-06,
      "loss": 0.4843,
      "step": 49580
    },
    {
      "epoch": 1.5230854299142935,
      "grad_norm": 0.42484837770462036,
      "learning_rate": 2.6854047077945978e-06,
      "loss": 0.4256,
      "step": 49581
    },
    {
      "epoch": 1.5231161490492426,
      "grad_norm": 0.4382975101470947,
      "learning_rate": 2.6850751768395054e-06,
      "loss": 0.57,
      "step": 49582
    },
    {
      "epoch": 1.523146868184192,
      "grad_norm": 0.4592752158641815,
      "learning_rate": 2.6847456629689283e-06,
      "loss": 0.5045,
      "step": 49583
    },
    {
      "epoch": 1.523177587319141,
      "grad_norm": 0.45077598094940186,
      "learning_rate": 2.684416166183641e-06,
      "loss": 0.495,
      "step": 49584
    },
    {
      "epoch": 1.5232083064540902,
      "grad_norm": 0.46189913153648376,
      "learning_rate": 2.684086686484405e-06,
      "loss": 0.4351,
      "step": 49585
    },
    {
      "epoch": 1.5232390255890396,
      "grad_norm": 0.4578956961631775,
      "learning_rate": 2.683757223872002e-06,
      "loss": 0.5018,
      "step": 49586
    },
    {
      "epoch": 1.5232697447239887,
      "grad_norm": 0.42436763644218445,
      "learning_rate": 2.683427778347192e-06,
      "loss": 0.4445,
      "step": 49587
    },
    {
      "epoch": 1.5233004638589378,
      "grad_norm": 0.4204254448413849,
      "learning_rate": 2.683098349910749e-06,
      "loss": 0.4774,
      "step": 49588
    },
    {
      "epoch": 1.523331182993887,
      "grad_norm": 0.40593281388282776,
      "learning_rate": 2.6827689385634393e-06,
      "loss": 0.4892,
      "step": 49589
    },
    {
      "epoch": 1.523361902128836,
      "grad_norm": 0.49303215742111206,
      "learning_rate": 2.6824395443060324e-06,
      "loss": 0.475,
      "step": 49590
    },
    {
      "epoch": 1.5233926212637852,
      "grad_norm": 0.4467170536518097,
      "learning_rate": 2.6821101671393003e-06,
      "loss": 0.5137,
      "step": 49591
    },
    {
      "epoch": 1.5234233403987343,
      "grad_norm": 0.4100430905818939,
      "learning_rate": 2.681780807064014e-06,
      "loss": 0.4023,
      "step": 49592
    },
    {
      "epoch": 1.5234540595336834,
      "grad_norm": 0.4782714247703552,
      "learning_rate": 2.6814514640809363e-06,
      "loss": 0.5132,
      "step": 49593
    },
    {
      "epoch": 1.5234847786686327,
      "grad_norm": 0.437171995639801,
      "learning_rate": 2.681122138190839e-06,
      "loss": 0.4818,
      "step": 49594
    },
    {
      "epoch": 1.5235154978035819,
      "grad_norm": 0.41779205203056335,
      "learning_rate": 2.680792829394493e-06,
      "loss": 0.4969,
      "step": 49595
    },
    {
      "epoch": 1.523546216938531,
      "grad_norm": 0.46377599239349365,
      "learning_rate": 2.680463537692667e-06,
      "loss": 0.396,
      "step": 49596
    },
    {
      "epoch": 1.5235769360734803,
      "grad_norm": 0.4276721775531769,
      "learning_rate": 2.6801342630861317e-06,
      "loss": 0.4422,
      "step": 49597
    },
    {
      "epoch": 1.5236076552084294,
      "grad_norm": 0.415818989276886,
      "learning_rate": 2.679805005575651e-06,
      "loss": 0.5062,
      "step": 49598
    },
    {
      "epoch": 1.5236383743433786,
      "grad_norm": 0.42313095927238464,
      "learning_rate": 2.679475765161997e-06,
      "loss": 0.5528,
      "step": 49599
    },
    {
      "epoch": 1.5236690934783277,
      "grad_norm": 0.402547687292099,
      "learning_rate": 2.6791465418459395e-06,
      "loss": 0.4646,
      "step": 49600
    },
    {
      "epoch": 1.5236998126132768,
      "grad_norm": 0.4481371343135834,
      "learning_rate": 2.6788173356282485e-06,
      "loss": 0.4196,
      "step": 49601
    },
    {
      "epoch": 1.523730531748226,
      "grad_norm": 0.4268251955509186,
      "learning_rate": 2.678488146509689e-06,
      "loss": 0.5431,
      "step": 49602
    },
    {
      "epoch": 1.523761250883175,
      "grad_norm": 0.40745609998703003,
      "learning_rate": 2.6781589744910306e-06,
      "loss": 0.4404,
      "step": 49603
    },
    {
      "epoch": 1.5237919700181242,
      "grad_norm": 0.43050485849380493,
      "learning_rate": 2.6778298195730435e-06,
      "loss": 0.4044,
      "step": 49604
    },
    {
      "epoch": 1.5238226891530733,
      "grad_norm": 0.4776478409767151,
      "learning_rate": 2.6775006817564995e-06,
      "loss": 0.4358,
      "step": 49605
    },
    {
      "epoch": 1.5238534082880226,
      "grad_norm": 0.4133501648902893,
      "learning_rate": 2.677171561042161e-06,
      "loss": 0.4477,
      "step": 49606
    },
    {
      "epoch": 1.5238841274229717,
      "grad_norm": 0.41179341077804565,
      "learning_rate": 2.6768424574308006e-06,
      "loss": 0.4285,
      "step": 49607
    },
    {
      "epoch": 1.523914846557921,
      "grad_norm": 0.9085816740989685,
      "learning_rate": 2.676513370923185e-06,
      "loss": 0.381,
      "step": 49608
    },
    {
      "epoch": 1.5239455656928702,
      "grad_norm": 0.43211933970451355,
      "learning_rate": 2.676184301520087e-06,
      "loss": 0.5355,
      "step": 49609
    },
    {
      "epoch": 1.5239762848278193,
      "grad_norm": 0.4086313545703888,
      "learning_rate": 2.675855249222269e-06,
      "loss": 0.4879,
      "step": 49610
    },
    {
      "epoch": 1.5240070039627684,
      "grad_norm": 0.4417973756790161,
      "learning_rate": 2.675526214030506e-06,
      "loss": 0.5076,
      "step": 49611
    },
    {
      "epoch": 1.5240377230977176,
      "grad_norm": 0.3984232246875763,
      "learning_rate": 2.6751971959455568e-06,
      "loss": 0.4611,
      "step": 49612
    },
    {
      "epoch": 1.5240684422326667,
      "grad_norm": 0.4349948763847351,
      "learning_rate": 2.674868194968199e-06,
      "loss": 0.4978,
      "step": 49613
    },
    {
      "epoch": 1.5240991613676158,
      "grad_norm": 0.40491020679473877,
      "learning_rate": 2.6745392110992007e-06,
      "loss": 0.4539,
      "step": 49614
    },
    {
      "epoch": 1.524129880502565,
      "grad_norm": 0.43050357699394226,
      "learning_rate": 2.6742102443393257e-06,
      "loss": 0.4857,
      "step": 49615
    },
    {
      "epoch": 1.524160599637514,
      "grad_norm": 0.5011926889419556,
      "learning_rate": 2.673881294689347e-06,
      "loss": 0.4524,
      "step": 49616
    },
    {
      "epoch": 1.5241913187724634,
      "grad_norm": 0.44885048270225525,
      "learning_rate": 2.673552362150024e-06,
      "loss": 0.4997,
      "step": 49617
    },
    {
      "epoch": 1.5242220379074125,
      "grad_norm": 0.4221496880054474,
      "learning_rate": 2.6732234467221373e-06,
      "loss": 0.4431,
      "step": 49618
    },
    {
      "epoch": 1.5242527570423618,
      "grad_norm": 0.4201365113258362,
      "learning_rate": 2.672894548406445e-06,
      "loss": 0.4403,
      "step": 49619
    },
    {
      "epoch": 1.524283476177311,
      "grad_norm": 0.426034539937973,
      "learning_rate": 2.672565667203724e-06,
      "loss": 0.4431,
      "step": 49620
    },
    {
      "epoch": 1.52431419531226,
      "grad_norm": 0.4973146617412567,
      "learning_rate": 2.6722368031147304e-06,
      "loss": 0.5378,
      "step": 49621
    },
    {
      "epoch": 1.5243449144472092,
      "grad_norm": 0.42028456926345825,
      "learning_rate": 2.671907956140245e-06,
      "loss": 0.4778,
      "step": 49622
    },
    {
      "epoch": 1.5243756335821583,
      "grad_norm": 0.3770855963230133,
      "learning_rate": 2.671579126281029e-06,
      "loss": 0.4004,
      "step": 49623
    },
    {
      "epoch": 1.5244063527171074,
      "grad_norm": 0.40572383999824524,
      "learning_rate": 2.671250313537853e-06,
      "loss": 0.4415,
      "step": 49624
    },
    {
      "epoch": 1.5244370718520566,
      "grad_norm": 0.44580087065696716,
      "learning_rate": 2.670921517911482e-06,
      "loss": 0.4177,
      "step": 49625
    },
    {
      "epoch": 1.5244677909870057,
      "grad_norm": 0.4304588735103607,
      "learning_rate": 2.6705927394026853e-06,
      "loss": 0.4079,
      "step": 49626
    },
    {
      "epoch": 1.5244985101219548,
      "grad_norm": 0.38788947463035583,
      "learning_rate": 2.670263978012231e-06,
      "loss": 0.4036,
      "step": 49627
    },
    {
      "epoch": 1.5245292292569042,
      "grad_norm": 0.37954235076904297,
      "learning_rate": 2.6699352337408903e-06,
      "loss": 0.4344,
      "step": 49628
    },
    {
      "epoch": 1.5245599483918533,
      "grad_norm": 0.4512348175048828,
      "learning_rate": 2.669606506589425e-06,
      "loss": 0.6471,
      "step": 49629
    },
    {
      "epoch": 1.5245906675268024,
      "grad_norm": 0.4259229600429535,
      "learning_rate": 2.6692777965586046e-06,
      "loss": 0.4681,
      "step": 49630
    },
    {
      "epoch": 1.5246213866617517,
      "grad_norm": 0.4183789789676666,
      "learning_rate": 2.668949103649199e-06,
      "loss": 0.53,
      "step": 49631
    },
    {
      "epoch": 1.5246521057967009,
      "grad_norm": 0.3925917446613312,
      "learning_rate": 2.6686204278619744e-06,
      "loss": 0.3667,
      "step": 49632
    },
    {
      "epoch": 1.52468282493165,
      "grad_norm": 0.4864891767501831,
      "learning_rate": 2.6682917691977018e-06,
      "loss": 0.5291,
      "step": 49633
    },
    {
      "epoch": 1.524713544066599,
      "grad_norm": 0.419680655002594,
      "learning_rate": 2.667963127657143e-06,
      "loss": 0.4508,
      "step": 49634
    },
    {
      "epoch": 1.5247442632015482,
      "grad_norm": 0.4370950162410736,
      "learning_rate": 2.6676345032410677e-06,
      "loss": 0.4394,
      "step": 49635
    },
    {
      "epoch": 1.5247749823364973,
      "grad_norm": 0.4191930890083313,
      "learning_rate": 2.667305895950244e-06,
      "loss": 0.4454,
      "step": 49636
    },
    {
      "epoch": 1.5248057014714465,
      "grad_norm": 0.4315131902694702,
      "learning_rate": 2.6669773057854433e-06,
      "loss": 0.4962,
      "step": 49637
    },
    {
      "epoch": 1.5248364206063956,
      "grad_norm": 0.3772929012775421,
      "learning_rate": 2.6666487327474254e-06,
      "loss": 0.4702,
      "step": 49638
    },
    {
      "epoch": 1.524867139741345,
      "grad_norm": 0.4311320185661316,
      "learning_rate": 2.6663201768369627e-06,
      "loss": 0.446,
      "step": 49639
    },
    {
      "epoch": 1.524897858876294,
      "grad_norm": 0.40458598732948303,
      "learning_rate": 2.665991638054821e-06,
      "loss": 0.504,
      "step": 49640
    },
    {
      "epoch": 1.5249285780112432,
      "grad_norm": 0.41666004061698914,
      "learning_rate": 2.665663116401771e-06,
      "loss": 0.406,
      "step": 49641
    },
    {
      "epoch": 1.5249592971461925,
      "grad_norm": 0.4555925130844116,
      "learning_rate": 2.665334611878574e-06,
      "loss": 0.5442,
      "step": 49642
    },
    {
      "epoch": 1.5249900162811416,
      "grad_norm": 0.42774641513824463,
      "learning_rate": 2.6650061244859992e-06,
      "loss": 0.4948,
      "step": 49643
    },
    {
      "epoch": 1.5250207354160907,
      "grad_norm": 0.41194114089012146,
      "learning_rate": 2.6646776542248166e-06,
      "loss": 0.4783,
      "step": 49644
    },
    {
      "epoch": 1.5250514545510399,
      "grad_norm": 0.40669959783554077,
      "learning_rate": 2.664349201095794e-06,
      "loss": 0.4972,
      "step": 49645
    },
    {
      "epoch": 1.525082173685989,
      "grad_norm": 0.46735700964927673,
      "learning_rate": 2.664020765099692e-06,
      "loss": 0.4314,
      "step": 49646
    },
    {
      "epoch": 1.525112892820938,
      "grad_norm": 0.4529603123664856,
      "learning_rate": 2.6636923462372865e-06,
      "loss": 0.5022,
      "step": 49647
    },
    {
      "epoch": 1.5251436119558872,
      "grad_norm": 0.44555357098579407,
      "learning_rate": 2.663363944509333e-06,
      "loss": 0.3925,
      "step": 49648
    },
    {
      "epoch": 1.5251743310908363,
      "grad_norm": 0.42488035559654236,
      "learning_rate": 2.6630355599166113e-06,
      "loss": 0.4288,
      "step": 49649
    },
    {
      "epoch": 1.5252050502257857,
      "grad_norm": 0.41846776008605957,
      "learning_rate": 2.66270719245988e-06,
      "loss": 0.4623,
      "step": 49650
    },
    {
      "epoch": 1.5252357693607348,
      "grad_norm": 0.43288010358810425,
      "learning_rate": 2.6623788421399076e-06,
      "loss": 0.483,
      "step": 49651
    },
    {
      "epoch": 1.525266488495684,
      "grad_norm": 0.43817296624183655,
      "learning_rate": 2.6620505089574656e-06,
      "loss": 0.4906,
      "step": 49652
    },
    {
      "epoch": 1.5252972076306333,
      "grad_norm": 0.43157511949539185,
      "learning_rate": 2.661722192913312e-06,
      "loss": 0.487,
      "step": 49653
    },
    {
      "epoch": 1.5253279267655824,
      "grad_norm": 0.38780054450035095,
      "learning_rate": 2.6613938940082227e-06,
      "loss": 0.4482,
      "step": 49654
    },
    {
      "epoch": 1.5253586459005315,
      "grad_norm": 0.4300025403499603,
      "learning_rate": 2.661065612242959e-06,
      "loss": 0.4578,
      "step": 49655
    },
    {
      "epoch": 1.5253893650354806,
      "grad_norm": 0.39623361825942993,
      "learning_rate": 2.660737347618292e-06,
      "loss": 0.4894,
      "step": 49656
    },
    {
      "epoch": 1.5254200841704297,
      "grad_norm": 0.45966729521751404,
      "learning_rate": 2.660409100134982e-06,
      "loss": 0.5175,
      "step": 49657
    },
    {
      "epoch": 1.5254508033053789,
      "grad_norm": 0.4577590525150299,
      "learning_rate": 2.6600808697937987e-06,
      "loss": 0.5181,
      "step": 49658
    },
    {
      "epoch": 1.525481522440328,
      "grad_norm": 0.42647436261177063,
      "learning_rate": 2.65975265659551e-06,
      "loss": 0.4526,
      "step": 49659
    },
    {
      "epoch": 1.525512241575277,
      "grad_norm": 0.46118834614753723,
      "learning_rate": 2.6594244605408836e-06,
      "loss": 0.5632,
      "step": 49660
    },
    {
      "epoch": 1.5255429607102264,
      "grad_norm": 0.5014451146125793,
      "learning_rate": 2.659096281630682e-06,
      "loss": 0.4466,
      "step": 49661
    },
    {
      "epoch": 1.5255736798451756,
      "grad_norm": 0.45221829414367676,
      "learning_rate": 2.6587681198656735e-06,
      "loss": 0.4427,
      "step": 49662
    },
    {
      "epoch": 1.5256043989801247,
      "grad_norm": 0.41304847598075867,
      "learning_rate": 2.658439975246625e-06,
      "loss": 0.4201,
      "step": 49663
    },
    {
      "epoch": 1.525635118115074,
      "grad_norm": 0.3960106670856476,
      "learning_rate": 2.658111847774305e-06,
      "loss": 0.4565,
      "step": 49664
    },
    {
      "epoch": 1.5256658372500231,
      "grad_norm": 0.43566256761550903,
      "learning_rate": 2.6577837374494755e-06,
      "loss": 0.4456,
      "step": 49665
    },
    {
      "epoch": 1.5256965563849723,
      "grad_norm": 0.4351155459880829,
      "learning_rate": 2.657455644272904e-06,
      "loss": 0.4784,
      "step": 49666
    },
    {
      "epoch": 1.5257272755199214,
      "grad_norm": 0.44000333547592163,
      "learning_rate": 2.657127568245358e-06,
      "loss": 0.4219,
      "step": 49667
    },
    {
      "epoch": 1.5257579946548705,
      "grad_norm": 0.43434157967567444,
      "learning_rate": 2.6567995093676038e-06,
      "loss": 0.5231,
      "step": 49668
    },
    {
      "epoch": 1.5257887137898196,
      "grad_norm": 0.44939756393432617,
      "learning_rate": 2.6564714676404093e-06,
      "loss": 0.3781,
      "step": 49669
    },
    {
      "epoch": 1.5258194329247687,
      "grad_norm": 0.3858637511730194,
      "learning_rate": 2.6561434430645363e-06,
      "loss": 0.387,
      "step": 49670
    },
    {
      "epoch": 1.5258501520597179,
      "grad_norm": 0.47155076265335083,
      "learning_rate": 2.655815435640752e-06,
      "loss": 0.3896,
      "step": 49671
    },
    {
      "epoch": 1.5258808711946672,
      "grad_norm": 0.4517029821872711,
      "learning_rate": 2.6554874453698242e-06,
      "loss": 0.4701,
      "step": 49672
    },
    {
      "epoch": 1.5259115903296163,
      "grad_norm": 0.47277677059173584,
      "learning_rate": 2.655159472252522e-06,
      "loss": 0.4403,
      "step": 49673
    },
    {
      "epoch": 1.5259423094645654,
      "grad_norm": 0.4623544216156006,
      "learning_rate": 2.6548315162896043e-06,
      "loss": 0.4263,
      "step": 49674
    },
    {
      "epoch": 1.5259730285995148,
      "grad_norm": 0.3883630037307739,
      "learning_rate": 2.6545035774818405e-06,
      "loss": 0.4807,
      "step": 49675
    },
    {
      "epoch": 1.526003747734464,
      "grad_norm": 0.4303072988986969,
      "learning_rate": 2.654175655829997e-06,
      "loss": 0.5232,
      "step": 49676
    },
    {
      "epoch": 1.526034466869413,
      "grad_norm": 0.47062233090400696,
      "learning_rate": 2.6538477513348427e-06,
      "loss": 0.4865,
      "step": 49677
    },
    {
      "epoch": 1.5260651860043621,
      "grad_norm": 0.4355866014957428,
      "learning_rate": 2.653519863997136e-06,
      "loss": 0.5143,
      "step": 49678
    },
    {
      "epoch": 1.5260959051393113,
      "grad_norm": 0.43917882442474365,
      "learning_rate": 2.653191993817651e-06,
      "loss": 0.4787,
      "step": 49679
    },
    {
      "epoch": 1.5261266242742604,
      "grad_norm": 0.4220937192440033,
      "learning_rate": 2.6528641407971423e-06,
      "loss": 0.4963,
      "step": 49680
    },
    {
      "epoch": 1.5261573434092095,
      "grad_norm": 0.4421076774597168,
      "learning_rate": 2.6525363049363886e-06,
      "loss": 0.5389,
      "step": 49681
    },
    {
      "epoch": 1.5261880625441586,
      "grad_norm": 0.4313012361526489,
      "learning_rate": 2.6522084862361463e-06,
      "loss": 0.4636,
      "step": 49682
    },
    {
      "epoch": 1.526218781679108,
      "grad_norm": 0.43739938735961914,
      "learning_rate": 2.651880684697188e-06,
      "loss": 0.4389,
      "step": 49683
    },
    {
      "epoch": 1.526249500814057,
      "grad_norm": 0.426499605178833,
      "learning_rate": 2.651552900320268e-06,
      "loss": 0.4806,
      "step": 49684
    },
    {
      "epoch": 1.5262802199490062,
      "grad_norm": 0.44745853543281555,
      "learning_rate": 2.651225133106167e-06,
      "loss": 0.473,
      "step": 49685
    },
    {
      "epoch": 1.5263109390839555,
      "grad_norm": 0.41626593470573425,
      "learning_rate": 2.6508973830556393e-06,
      "loss": 0.461,
      "step": 49686
    },
    {
      "epoch": 1.5263416582189047,
      "grad_norm": 0.44251060485839844,
      "learning_rate": 2.6505696501694535e-06,
      "loss": 0.5,
      "step": 49687
    },
    {
      "epoch": 1.5263723773538538,
      "grad_norm": 0.4529324769973755,
      "learning_rate": 2.6502419344483798e-06,
      "loss": 0.454,
      "step": 49688
    },
    {
      "epoch": 1.526403096488803,
      "grad_norm": 0.44400477409362793,
      "learning_rate": 2.649914235893173e-06,
      "loss": 0.4942,
      "step": 49689
    },
    {
      "epoch": 1.526433815623752,
      "grad_norm": 0.43133479356765747,
      "learning_rate": 2.6495865545046094e-06,
      "loss": 0.4739,
      "step": 49690
    },
    {
      "epoch": 1.5264645347587011,
      "grad_norm": 0.4599667489528656,
      "learning_rate": 2.649258890283448e-06,
      "loss": 0.4584,
      "step": 49691
    },
    {
      "epoch": 1.5264952538936503,
      "grad_norm": 0.4193623661994934,
      "learning_rate": 2.648931243230459e-06,
      "loss": 0.5324,
      "step": 49692
    },
    {
      "epoch": 1.5265259730285994,
      "grad_norm": 0.48442748188972473,
      "learning_rate": 2.648603613346401e-06,
      "loss": 0.4848,
      "step": 49693
    },
    {
      "epoch": 1.5265566921635487,
      "grad_norm": 0.49513429403305054,
      "learning_rate": 2.6482760006320427e-06,
      "loss": 0.3544,
      "step": 49694
    },
    {
      "epoch": 1.5265874112984978,
      "grad_norm": 0.4403737485408783,
      "learning_rate": 2.6479484050881497e-06,
      "loss": 0.4617,
      "step": 49695
    },
    {
      "epoch": 1.526618130433447,
      "grad_norm": 0.4324658215045929,
      "learning_rate": 2.647620826715489e-06,
      "loss": 0.4553,
      "step": 49696
    },
    {
      "epoch": 1.5266488495683963,
      "grad_norm": 0.4133029878139496,
      "learning_rate": 2.6472932655148208e-06,
      "loss": 0.4944,
      "step": 49697
    },
    {
      "epoch": 1.5266795687033454,
      "grad_norm": 0.4237525761127472,
      "learning_rate": 2.6469657214869125e-06,
      "loss": 0.4777,
      "step": 49698
    },
    {
      "epoch": 1.5267102878382945,
      "grad_norm": 0.6633653044700623,
      "learning_rate": 2.646638194632529e-06,
      "loss": 0.4289,
      "step": 49699
    },
    {
      "epoch": 1.5267410069732437,
      "grad_norm": 0.4298001825809479,
      "learning_rate": 2.64631068495244e-06,
      "loss": 0.478,
      "step": 49700
    },
    {
      "epoch": 1.5267717261081928,
      "grad_norm": 0.398574560880661,
      "learning_rate": 2.6459831924474013e-06,
      "loss": 0.4654,
      "step": 49701
    },
    {
      "epoch": 1.526802445243142,
      "grad_norm": 0.4492250382900238,
      "learning_rate": 2.645655717118183e-06,
      "loss": 0.4008,
      "step": 49702
    },
    {
      "epoch": 1.526833164378091,
      "grad_norm": 0.44221845269203186,
      "learning_rate": 2.6453282589655495e-06,
      "loss": 0.512,
      "step": 49703
    },
    {
      "epoch": 1.5268638835130401,
      "grad_norm": 0.43701422214508057,
      "learning_rate": 2.6450008179902687e-06,
      "loss": 0.4525,
      "step": 49704
    },
    {
      "epoch": 1.5268946026479895,
      "grad_norm": 0.4082021415233612,
      "learning_rate": 2.644673394193099e-06,
      "loss": 0.4743,
      "step": 49705
    },
    {
      "epoch": 1.5269253217829386,
      "grad_norm": 0.4423079490661621,
      "learning_rate": 2.644345987574808e-06,
      "loss": 0.4258,
      "step": 49706
    },
    {
      "epoch": 1.5269560409178877,
      "grad_norm": 0.42066898941993713,
      "learning_rate": 2.644018598136161e-06,
      "loss": 0.5104,
      "step": 49707
    },
    {
      "epoch": 1.526986760052837,
      "grad_norm": 0.6599766612052917,
      "learning_rate": 2.6436912258779213e-06,
      "loss": 0.446,
      "step": 49708
    },
    {
      "epoch": 1.5270174791877862,
      "grad_norm": 0.41645297408103943,
      "learning_rate": 2.643363870800859e-06,
      "loss": 0.4794,
      "step": 49709
    },
    {
      "epoch": 1.5270481983227353,
      "grad_norm": 0.3931392431259155,
      "learning_rate": 2.6430365329057305e-06,
      "loss": 0.3953,
      "step": 49710
    },
    {
      "epoch": 1.5270789174576844,
      "grad_norm": 0.43139827251434326,
      "learning_rate": 2.642709212193304e-06,
      "loss": 0.4365,
      "step": 49711
    },
    {
      "epoch": 1.5271096365926335,
      "grad_norm": 0.4133346974849701,
      "learning_rate": 2.642381908664343e-06,
      "loss": 0.4904,
      "step": 49712
    },
    {
      "epoch": 1.5271403557275827,
      "grad_norm": 0.39827388525009155,
      "learning_rate": 2.6420546223196173e-06,
      "loss": 0.4831,
      "step": 49713
    },
    {
      "epoch": 1.5271710748625318,
      "grad_norm": 0.43622347712516785,
      "learning_rate": 2.6417273531598843e-06,
      "loss": 0.409,
      "step": 49714
    },
    {
      "epoch": 1.527201793997481,
      "grad_norm": 0.42997822165489197,
      "learning_rate": 2.6414001011859124e-06,
      "loss": 0.5114,
      "step": 49715
    },
    {
      "epoch": 1.52723251313243,
      "grad_norm": 0.4053696095943451,
      "learning_rate": 2.6410728663984596e-06,
      "loss": 0.3892,
      "step": 49716
    },
    {
      "epoch": 1.5272632322673794,
      "grad_norm": 0.4130803346633911,
      "learning_rate": 2.6407456487983006e-06,
      "loss": 0.4735,
      "step": 49717
    },
    {
      "epoch": 1.5272939514023285,
      "grad_norm": 0.4253842532634735,
      "learning_rate": 2.6404184483861904e-06,
      "loss": 0.4774,
      "step": 49718
    },
    {
      "epoch": 1.5273246705372778,
      "grad_norm": 0.5291974544525146,
      "learning_rate": 2.640091265162901e-06,
      "loss": 0.5218,
      "step": 49719
    },
    {
      "epoch": 1.527355389672227,
      "grad_norm": 0.4268227219581604,
      "learning_rate": 2.6397640991291895e-06,
      "loss": 0.4425,
      "step": 49720
    },
    {
      "epoch": 1.527386108807176,
      "grad_norm": 0.3898400664329529,
      "learning_rate": 2.639436950285822e-06,
      "loss": 0.4728,
      "step": 49721
    },
    {
      "epoch": 1.5274168279421252,
      "grad_norm": 0.4435741901397705,
      "learning_rate": 2.639109818633564e-06,
      "loss": 0.399,
      "step": 49722
    },
    {
      "epoch": 1.5274475470770743,
      "grad_norm": 0.4397337734699249,
      "learning_rate": 2.6387827041731797e-06,
      "loss": 0.5943,
      "step": 49723
    },
    {
      "epoch": 1.5274782662120234,
      "grad_norm": 0.4380747079849243,
      "learning_rate": 2.6384556069054345e-06,
      "loss": 0.4606,
      "step": 49724
    },
    {
      "epoch": 1.5275089853469725,
      "grad_norm": 0.39838066697120667,
      "learning_rate": 2.638128526831085e-06,
      "loss": 0.4577,
      "step": 49725
    },
    {
      "epoch": 1.5275397044819217,
      "grad_norm": 0.4792800843715668,
      "learning_rate": 2.6378014639509066e-06,
      "loss": 0.4769,
      "step": 49726
    },
    {
      "epoch": 1.5275704236168708,
      "grad_norm": 0.38553059101104736,
      "learning_rate": 2.637474418265654e-06,
      "loss": 0.3791,
      "step": 49727
    },
    {
      "epoch": 1.5276011427518201,
      "grad_norm": 0.5091516971588135,
      "learning_rate": 2.637147389776097e-06,
      "loss": 0.4832,
      "step": 49728
    },
    {
      "epoch": 1.5276318618867692,
      "grad_norm": 0.4592728912830353,
      "learning_rate": 2.6368203784829925e-06,
      "loss": 0.4543,
      "step": 49729
    },
    {
      "epoch": 1.5276625810217186,
      "grad_norm": 0.4005279242992401,
      "learning_rate": 2.63649338438711e-06,
      "loss": 0.3855,
      "step": 49730
    },
    {
      "epoch": 1.5276933001566677,
      "grad_norm": 0.43200138211250305,
      "learning_rate": 2.6361664074892103e-06,
      "loss": 0.486,
      "step": 49731
    },
    {
      "epoch": 1.5277240192916168,
      "grad_norm": 0.4294689893722534,
      "learning_rate": 2.635839447790062e-06,
      "loss": 0.4436,
      "step": 49732
    },
    {
      "epoch": 1.527754738426566,
      "grad_norm": 0.42285996675491333,
      "learning_rate": 2.635512505290421e-06,
      "loss": 0.4716,
      "step": 49733
    },
    {
      "epoch": 1.527785457561515,
      "grad_norm": 0.46079567074775696,
      "learning_rate": 2.6351855799910553e-06,
      "loss": 0.4557,
      "step": 49734
    },
    {
      "epoch": 1.5278161766964642,
      "grad_norm": 0.4175165295600891,
      "learning_rate": 2.6348586718927283e-06,
      "loss": 0.4191,
      "step": 49735
    },
    {
      "epoch": 1.5278468958314133,
      "grad_norm": 0.3940368592739105,
      "learning_rate": 2.6345317809962056e-06,
      "loss": 0.4723,
      "step": 49736
    },
    {
      "epoch": 1.5278776149663624,
      "grad_norm": 0.44280433654785156,
      "learning_rate": 2.6342049073022457e-06,
      "loss": 0.4894,
      "step": 49737
    },
    {
      "epoch": 1.5279083341013115,
      "grad_norm": 0.41158226132392883,
      "learning_rate": 2.6338780508116156e-06,
      "loss": 0.5187,
      "step": 49738
    },
    {
      "epoch": 1.527939053236261,
      "grad_norm": 0.3995913863182068,
      "learning_rate": 2.633551211525076e-06,
      "loss": 0.5143,
      "step": 49739
    },
    {
      "epoch": 1.52796977237121,
      "grad_norm": 0.4179743826389313,
      "learning_rate": 2.6332243894433962e-06,
      "loss": 0.4692,
      "step": 49740
    },
    {
      "epoch": 1.5280004915061594,
      "grad_norm": 0.4376731216907501,
      "learning_rate": 2.632897584567332e-06,
      "loss": 0.4379,
      "step": 49741
    },
    {
      "epoch": 1.5280312106411085,
      "grad_norm": 0.4334960877895355,
      "learning_rate": 2.63257079689765e-06,
      "loss": 0.5548,
      "step": 49742
    },
    {
      "epoch": 1.5280619297760576,
      "grad_norm": 0.4030936062335968,
      "learning_rate": 2.6322440264351134e-06,
      "loss": 0.5548,
      "step": 49743
    },
    {
      "epoch": 1.5280926489110067,
      "grad_norm": 0.4280194640159607,
      "learning_rate": 2.6319172731804854e-06,
      "loss": 0.4661,
      "step": 49744
    },
    {
      "epoch": 1.5281233680459558,
      "grad_norm": 0.479126513004303,
      "learning_rate": 2.6315905371345328e-06,
      "loss": 0.4606,
      "step": 49745
    },
    {
      "epoch": 1.528154087180905,
      "grad_norm": 0.429938405752182,
      "learning_rate": 2.631263818298012e-06,
      "loss": 0.5508,
      "step": 49746
    },
    {
      "epoch": 1.528184806315854,
      "grad_norm": 0.4601800739765167,
      "learning_rate": 2.630937116671688e-06,
      "loss": 0.4953,
      "step": 49747
    },
    {
      "epoch": 1.5282155254508032,
      "grad_norm": 0.45470714569091797,
      "learning_rate": 2.6306104322563266e-06,
      "loss": 0.5332,
      "step": 49748
    },
    {
      "epoch": 1.5282462445857523,
      "grad_norm": 0.3900509476661682,
      "learning_rate": 2.6302837650526913e-06,
      "loss": 0.446,
      "step": 49749
    },
    {
      "epoch": 1.5282769637207017,
      "grad_norm": 0.44127118587493896,
      "learning_rate": 2.62995711506154e-06,
      "loss": 0.5051,
      "step": 49750
    },
    {
      "epoch": 1.5283076828556508,
      "grad_norm": 0.4281104505062103,
      "learning_rate": 2.6296304822836417e-06,
      "loss": 0.5184,
      "step": 49751
    },
    {
      "epoch": 1.5283384019906,
      "grad_norm": 0.42230451107025146,
      "learning_rate": 2.62930386671975e-06,
      "loss": 0.449,
      "step": 49752
    },
    {
      "epoch": 1.5283691211255492,
      "grad_norm": 0.41691651940345764,
      "learning_rate": 2.6289772683706395e-06,
      "loss": 0.4546,
      "step": 49753
    },
    {
      "epoch": 1.5283998402604984,
      "grad_norm": 0.48143270611763,
      "learning_rate": 2.6286506872370653e-06,
      "loss": 0.4477,
      "step": 49754
    },
    {
      "epoch": 1.5284305593954475,
      "grad_norm": 0.5480562448501587,
      "learning_rate": 2.628324123319794e-06,
      "loss": 0.5704,
      "step": 49755
    },
    {
      "epoch": 1.5284612785303966,
      "grad_norm": 0.4436089098453522,
      "learning_rate": 2.6279975766195853e-06,
      "loss": 0.5463,
      "step": 49756
    },
    {
      "epoch": 1.5284919976653457,
      "grad_norm": 0.3608399033546448,
      "learning_rate": 2.6276710471372015e-06,
      "loss": 0.4018,
      "step": 49757
    },
    {
      "epoch": 1.5285227168002948,
      "grad_norm": 0.43748489022254944,
      "learning_rate": 2.6273445348734085e-06,
      "loss": 0.3622,
      "step": 49758
    },
    {
      "epoch": 1.528553435935244,
      "grad_norm": 0.37558111548423767,
      "learning_rate": 2.6270180398289656e-06,
      "loss": 0.4466,
      "step": 49759
    },
    {
      "epoch": 1.528584155070193,
      "grad_norm": 0.40344440937042236,
      "learning_rate": 2.6266915620046408e-06,
      "loss": 0.4282,
      "step": 49760
    },
    {
      "epoch": 1.5286148742051424,
      "grad_norm": 0.445492684841156,
      "learning_rate": 2.6263651014011894e-06,
      "loss": 0.5296,
      "step": 49761
    },
    {
      "epoch": 1.5286455933400915,
      "grad_norm": 0.4044240117073059,
      "learning_rate": 2.6260386580193773e-06,
      "loss": 0.423,
      "step": 49762
    },
    {
      "epoch": 1.5286763124750407,
      "grad_norm": 0.45239493250846863,
      "learning_rate": 2.625712231859967e-06,
      "loss": 0.4209,
      "step": 49763
    },
    {
      "epoch": 1.52870703160999,
      "grad_norm": 0.42794498801231384,
      "learning_rate": 2.625385822923724e-06,
      "loss": 0.5126,
      "step": 49764
    },
    {
      "epoch": 1.5287377507449391,
      "grad_norm": 0.4310358464717865,
      "learning_rate": 2.625059431211404e-06,
      "loss": 0.4434,
      "step": 49765
    },
    {
      "epoch": 1.5287684698798882,
      "grad_norm": 0.4071100354194641,
      "learning_rate": 2.624733056723774e-06,
      "loss": 0.5065,
      "step": 49766
    },
    {
      "epoch": 1.5287991890148374,
      "grad_norm": 0.45700839161872864,
      "learning_rate": 2.6244066994615936e-06,
      "loss": 0.5214,
      "step": 49767
    },
    {
      "epoch": 1.5288299081497865,
      "grad_norm": 0.44957655668258667,
      "learning_rate": 2.6240803594256303e-06,
      "loss": 0.4924,
      "step": 49768
    },
    {
      "epoch": 1.5288606272847356,
      "grad_norm": 0.449967622756958,
      "learning_rate": 2.623754036616639e-06,
      "loss": 0.4878,
      "step": 49769
    },
    {
      "epoch": 1.5288913464196847,
      "grad_norm": 0.5120744109153748,
      "learning_rate": 2.623427731035385e-06,
      "loss": 0.4371,
      "step": 49770
    },
    {
      "epoch": 1.5289220655546338,
      "grad_norm": 0.40841245651245117,
      "learning_rate": 2.6231014426826318e-06,
      "loss": 0.449,
      "step": 49771
    },
    {
      "epoch": 1.5289527846895832,
      "grad_norm": 0.46991872787475586,
      "learning_rate": 2.622775171559142e-06,
      "loss": 0.4615,
      "step": 49772
    },
    {
      "epoch": 1.5289835038245323,
      "grad_norm": 0.4160209894180298,
      "learning_rate": 2.6224489176656743e-06,
      "loss": 0.5068,
      "step": 49773
    },
    {
      "epoch": 1.5290142229594814,
      "grad_norm": 0.4207003712654114,
      "learning_rate": 2.622122681002992e-06,
      "loss": 0.4473,
      "step": 49774
    },
    {
      "epoch": 1.5290449420944308,
      "grad_norm": 0.41819828748703003,
      "learning_rate": 2.621796461571857e-06,
      "loss": 0.5038,
      "step": 49775
    },
    {
      "epoch": 1.5290756612293799,
      "grad_norm": 0.45742952823638916,
      "learning_rate": 2.6214702593730346e-06,
      "loss": 0.301,
      "step": 49776
    },
    {
      "epoch": 1.529106380364329,
      "grad_norm": 0.4774657189846039,
      "learning_rate": 2.621144074407281e-06,
      "loss": 0.4507,
      "step": 49777
    },
    {
      "epoch": 1.5291370994992781,
      "grad_norm": 0.4173862338066101,
      "learning_rate": 2.6208179066753613e-06,
      "loss": 0.4566,
      "step": 49778
    },
    {
      "epoch": 1.5291678186342272,
      "grad_norm": 0.4958736300468445,
      "learning_rate": 2.6204917561780365e-06,
      "loss": 0.4642,
      "step": 49779
    },
    {
      "epoch": 1.5291985377691764,
      "grad_norm": 0.4441037178039551,
      "learning_rate": 2.6201656229160678e-06,
      "loss": 0.4837,
      "step": 49780
    },
    {
      "epoch": 1.5292292569041255,
      "grad_norm": 0.4312498867511749,
      "learning_rate": 2.6198395068902217e-06,
      "loss": 0.4124,
      "step": 49781
    },
    {
      "epoch": 1.5292599760390746,
      "grad_norm": 0.42774102091789246,
      "learning_rate": 2.6195134081012518e-06,
      "loss": 0.4128,
      "step": 49782
    },
    {
      "epoch": 1.529290695174024,
      "grad_norm": 0.46271952986717224,
      "learning_rate": 2.619187326549928e-06,
      "loss": 0.469,
      "step": 49783
    },
    {
      "epoch": 1.529321414308973,
      "grad_norm": 0.4318072497844696,
      "learning_rate": 2.618861262237e-06,
      "loss": 0.4061,
      "step": 49784
    },
    {
      "epoch": 1.5293521334439222,
      "grad_norm": 0.42573782801628113,
      "learning_rate": 2.618535215163245e-06,
      "loss": 0.4312,
      "step": 49785
    },
    {
      "epoch": 1.5293828525788715,
      "grad_norm": 0.4332868754863739,
      "learning_rate": 2.6182091853294123e-06,
      "loss": 0.4773,
      "step": 49786
    },
    {
      "epoch": 1.5294135717138206,
      "grad_norm": 0.41365957260131836,
      "learning_rate": 2.6178831727362706e-06,
      "loss": 0.4452,
      "step": 49787
    },
    {
      "epoch": 1.5294442908487698,
      "grad_norm": 0.4337714910507202,
      "learning_rate": 2.617557177384572e-06,
      "loss": 0.4109,
      "step": 49788
    },
    {
      "epoch": 1.5294750099837189,
      "grad_norm": 0.4627363979816437,
      "learning_rate": 2.6172311992750908e-06,
      "loss": 0.5052,
      "step": 49789
    },
    {
      "epoch": 1.529505729118668,
      "grad_norm": 0.43408527970314026,
      "learning_rate": 2.616905238408579e-06,
      "loss": 0.5056,
      "step": 49790
    },
    {
      "epoch": 1.5295364482536171,
      "grad_norm": 0.4267318844795227,
      "learning_rate": 2.6165792947858036e-06,
      "loss": 0.532,
      "step": 49791
    },
    {
      "epoch": 1.5295671673885662,
      "grad_norm": 0.42223697900772095,
      "learning_rate": 2.61625336840752e-06,
      "loss": 0.5404,
      "step": 49792
    },
    {
      "epoch": 1.5295978865235154,
      "grad_norm": 0.40778428316116333,
      "learning_rate": 2.615927459274491e-06,
      "loss": 0.4377,
      "step": 49793
    },
    {
      "epoch": 1.5296286056584647,
      "grad_norm": 0.4245193302631378,
      "learning_rate": 2.61560156738748e-06,
      "loss": 0.5127,
      "step": 49794
    },
    {
      "epoch": 1.5296593247934138,
      "grad_norm": 0.3771524131298065,
      "learning_rate": 2.6152756927472513e-06,
      "loss": 0.4625,
      "step": 49795
    },
    {
      "epoch": 1.529690043928363,
      "grad_norm": 0.48157453536987305,
      "learning_rate": 2.6149498353545576e-06,
      "loss": 0.4775,
      "step": 49796
    },
    {
      "epoch": 1.5297207630633123,
      "grad_norm": 0.41840875148773193,
      "learning_rate": 2.614623995210165e-06,
      "loss": 0.4816,
      "step": 49797
    },
    {
      "epoch": 1.5297514821982614,
      "grad_norm": 0.4421718418598175,
      "learning_rate": 2.614298172314833e-06,
      "loss": 0.3952,
      "step": 49798
    },
    {
      "epoch": 1.5297822013332105,
      "grad_norm": 0.47429731488227844,
      "learning_rate": 2.613972366669324e-06,
      "loss": 0.4493,
      "step": 49799
    },
    {
      "epoch": 1.5298129204681596,
      "grad_norm": 0.39483997225761414,
      "learning_rate": 2.6136465782744014e-06,
      "loss": 0.4847,
      "step": 49800
    },
    {
      "epoch": 1.5298436396031088,
      "grad_norm": 0.4351485073566437,
      "learning_rate": 2.6133208071308202e-06,
      "loss": 0.472,
      "step": 49801
    },
    {
      "epoch": 1.5298743587380579,
      "grad_norm": 0.43601539731025696,
      "learning_rate": 2.6129950532393444e-06,
      "loss": 0.5048,
      "step": 49802
    },
    {
      "epoch": 1.529905077873007,
      "grad_norm": 0.39470216631889343,
      "learning_rate": 2.612669316600733e-06,
      "loss": 0.3802,
      "step": 49803
    },
    {
      "epoch": 1.5299357970079561,
      "grad_norm": 0.4413672983646393,
      "learning_rate": 2.612343597215753e-06,
      "loss": 0.4887,
      "step": 49804
    },
    {
      "epoch": 1.5299665161429055,
      "grad_norm": 0.42784383893013,
      "learning_rate": 2.6120178950851573e-06,
      "loss": 0.5349,
      "step": 49805
    },
    {
      "epoch": 1.5299972352778546,
      "grad_norm": 0.4269898235797882,
      "learning_rate": 2.61169221020971e-06,
      "loss": 0.4633,
      "step": 49806
    },
    {
      "epoch": 1.5300279544128037,
      "grad_norm": 0.5052198171615601,
      "learning_rate": 2.6113665425901703e-06,
      "loss": 0.4699,
      "step": 49807
    },
    {
      "epoch": 1.530058673547753,
      "grad_norm": 0.4134235084056854,
      "learning_rate": 2.6110408922273036e-06,
      "loss": 0.4023,
      "step": 49808
    },
    {
      "epoch": 1.5300893926827022,
      "grad_norm": 0.4624588191509247,
      "learning_rate": 2.610715259121864e-06,
      "loss": 0.5826,
      "step": 49809
    },
    {
      "epoch": 1.5301201118176513,
      "grad_norm": 0.5132232904434204,
      "learning_rate": 2.6103896432746155e-06,
      "loss": 0.4528,
      "step": 49810
    },
    {
      "epoch": 1.5301508309526004,
      "grad_norm": 0.39266136288642883,
      "learning_rate": 2.610064044686318e-06,
      "loss": 0.473,
      "step": 49811
    },
    {
      "epoch": 1.5301815500875495,
      "grad_norm": 0.4227035641670227,
      "learning_rate": 2.609738463357734e-06,
      "loss": 0.4106,
      "step": 49812
    },
    {
      "epoch": 1.5302122692224986,
      "grad_norm": 0.4036683738231659,
      "learning_rate": 2.6094128992896195e-06,
      "loss": 0.4729,
      "step": 49813
    },
    {
      "epoch": 1.5302429883574478,
      "grad_norm": 0.4450540542602539,
      "learning_rate": 2.6090873524827376e-06,
      "loss": 0.448,
      "step": 49814
    },
    {
      "epoch": 1.5302737074923969,
      "grad_norm": 0.43064647912979126,
      "learning_rate": 2.6087618229378486e-06,
      "loss": 0.4143,
      "step": 49815
    },
    {
      "epoch": 1.5303044266273462,
      "grad_norm": 0.5377625823020935,
      "learning_rate": 2.608436310655712e-06,
      "loss": 0.5017,
      "step": 49816
    },
    {
      "epoch": 1.5303351457622953,
      "grad_norm": 0.44636866450309753,
      "learning_rate": 2.6081108156370916e-06,
      "loss": 0.4199,
      "step": 49817
    },
    {
      "epoch": 1.5303658648972445,
      "grad_norm": 0.4521120488643646,
      "learning_rate": 2.6077853378827412e-06,
      "loss": 0.4198,
      "step": 49818
    },
    {
      "epoch": 1.5303965840321938,
      "grad_norm": 0.4044974744319916,
      "learning_rate": 2.607459877393428e-06,
      "loss": 0.4259,
      "step": 49819
    },
    {
      "epoch": 1.530427303167143,
      "grad_norm": 0.40253305435180664,
      "learning_rate": 2.6071344341699036e-06,
      "loss": 0.464,
      "step": 49820
    },
    {
      "epoch": 1.530458022302092,
      "grad_norm": 0.43797075748443604,
      "learning_rate": 2.606809008212937e-06,
      "loss": 0.4531,
      "step": 49821
    },
    {
      "epoch": 1.5304887414370412,
      "grad_norm": 0.4139881432056427,
      "learning_rate": 2.606483599523283e-06,
      "loss": 0.4507,
      "step": 49822
    },
    {
      "epoch": 1.5305194605719903,
      "grad_norm": 0.38761717081069946,
      "learning_rate": 2.6061582081017047e-06,
      "loss": 0.4538,
      "step": 49823
    },
    {
      "epoch": 1.5305501797069394,
      "grad_norm": 0.4279254376888275,
      "learning_rate": 2.605832833948958e-06,
      "loss": 0.5376,
      "step": 49824
    },
    {
      "epoch": 1.5305808988418885,
      "grad_norm": 0.47798749804496765,
      "learning_rate": 2.605507477065805e-06,
      "loss": 0.521,
      "step": 49825
    },
    {
      "epoch": 1.5306116179768376,
      "grad_norm": 0.411077618598938,
      "learning_rate": 2.605182137453005e-06,
      "loss": 0.4694,
      "step": 49826
    },
    {
      "epoch": 1.5306423371117868,
      "grad_norm": 0.44559019804000854,
      "learning_rate": 2.604856815111323e-06,
      "loss": 0.493,
      "step": 49827
    },
    {
      "epoch": 1.530673056246736,
      "grad_norm": 0.40278807282447815,
      "learning_rate": 2.60453151004151e-06,
      "loss": 0.4268,
      "step": 49828
    },
    {
      "epoch": 1.5307037753816852,
      "grad_norm": 0.5006096363067627,
      "learning_rate": 2.6042062222443308e-06,
      "loss": 0.4757,
      "step": 49829
    },
    {
      "epoch": 1.5307344945166346,
      "grad_norm": 0.40830305218696594,
      "learning_rate": 2.6038809517205445e-06,
      "loss": 0.4833,
      "step": 49830
    },
    {
      "epoch": 1.5307652136515837,
      "grad_norm": 0.4720366895198822,
      "learning_rate": 2.603555698470913e-06,
      "loss": 0.5034,
      "step": 49831
    },
    {
      "epoch": 1.5307959327865328,
      "grad_norm": 0.4362407624721527,
      "learning_rate": 2.6032304624961924e-06,
      "loss": 0.4865,
      "step": 49832
    },
    {
      "epoch": 1.530826651921482,
      "grad_norm": 0.446471631526947,
      "learning_rate": 2.6029052437971424e-06,
      "loss": 0.4911,
      "step": 49833
    },
    {
      "epoch": 1.530857371056431,
      "grad_norm": 0.45349928736686707,
      "learning_rate": 2.602580042374524e-06,
      "loss": 0.3819,
      "step": 49834
    },
    {
      "epoch": 1.5308880901913802,
      "grad_norm": 0.4105410575866699,
      "learning_rate": 2.602254858229096e-06,
      "loss": 0.4364,
      "step": 49835
    },
    {
      "epoch": 1.5309188093263293,
      "grad_norm": 0.3834070861339569,
      "learning_rate": 2.601929691361622e-06,
      "loss": 0.401,
      "step": 49836
    },
    {
      "epoch": 1.5309495284612784,
      "grad_norm": 0.39949822425842285,
      "learning_rate": 2.6016045417728554e-06,
      "loss": 0.4744,
      "step": 49837
    },
    {
      "epoch": 1.5309802475962275,
      "grad_norm": 0.4474874436855316,
      "learning_rate": 2.6012794094635576e-06,
      "loss": 0.5276,
      "step": 49838
    },
    {
      "epoch": 1.5310109667311769,
      "grad_norm": 0.5050307512283325,
      "learning_rate": 2.600954294434488e-06,
      "loss": 0.5053,
      "step": 49839
    },
    {
      "epoch": 1.531041685866126,
      "grad_norm": 0.45812487602233887,
      "learning_rate": 2.6006291966864107e-06,
      "loss": 0.4429,
      "step": 49840
    },
    {
      "epoch": 1.5310724050010753,
      "grad_norm": 0.4418955147266388,
      "learning_rate": 2.600304116220076e-06,
      "loss": 0.442,
      "step": 49841
    },
    {
      "epoch": 1.5311031241360245,
      "grad_norm": 0.559015154838562,
      "learning_rate": 2.599979053036249e-06,
      "loss": 0.3786,
      "step": 49842
    },
    {
      "epoch": 1.5311338432709736,
      "grad_norm": 0.4204733371734619,
      "learning_rate": 2.5996540071356866e-06,
      "loss": 0.4373,
      "step": 49843
    },
    {
      "epoch": 1.5311645624059227,
      "grad_norm": 0.4483170509338379,
      "learning_rate": 2.5993289785191534e-06,
      "loss": 0.4706,
      "step": 49844
    },
    {
      "epoch": 1.5311952815408718,
      "grad_norm": 0.45199668407440186,
      "learning_rate": 2.599003967187401e-06,
      "loss": 0.4476,
      "step": 49845
    },
    {
      "epoch": 1.531226000675821,
      "grad_norm": 0.4355321228504181,
      "learning_rate": 2.5986789731411945e-06,
      "loss": 0.462,
      "step": 49846
    },
    {
      "epoch": 1.53125671981077,
      "grad_norm": 0.42619097232818604,
      "learning_rate": 2.5983539963812842e-06,
      "loss": 0.5118,
      "step": 49847
    },
    {
      "epoch": 1.5312874389457192,
      "grad_norm": 0.40692657232284546,
      "learning_rate": 2.5980290369084405e-06,
      "loss": 0.4474,
      "step": 49848
    },
    {
      "epoch": 1.5313181580806683,
      "grad_norm": 0.45108234882354736,
      "learning_rate": 2.5977040947234144e-06,
      "loss": 0.5366,
      "step": 49849
    },
    {
      "epoch": 1.5313488772156176,
      "grad_norm": 0.4059349000453949,
      "learning_rate": 2.59737916982697e-06,
      "loss": 0.4922,
      "step": 49850
    },
    {
      "epoch": 1.5313795963505668,
      "grad_norm": 0.41542017459869385,
      "learning_rate": 2.597054262219858e-06,
      "loss": 0.4167,
      "step": 49851
    },
    {
      "epoch": 1.531410315485516,
      "grad_norm": 0.41373708844184875,
      "learning_rate": 2.596729371902845e-06,
      "loss": 0.4493,
      "step": 49852
    },
    {
      "epoch": 1.5314410346204652,
      "grad_norm": 0.44899463653564453,
      "learning_rate": 2.5964044988766925e-06,
      "loss": 0.5319,
      "step": 49853
    },
    {
      "epoch": 1.5314717537554143,
      "grad_norm": 0.4482109844684601,
      "learning_rate": 2.59607964314215e-06,
      "loss": 0.4618,
      "step": 49854
    },
    {
      "epoch": 1.5315024728903635,
      "grad_norm": 0.4436793327331543,
      "learning_rate": 2.5957548046999835e-06,
      "loss": 0.477,
      "step": 49855
    },
    {
      "epoch": 1.5315331920253126,
      "grad_norm": 0.5670822858810425,
      "learning_rate": 2.595429983550942e-06,
      "loss": 0.4342,
      "step": 49856
    },
    {
      "epoch": 1.5315639111602617,
      "grad_norm": 0.43998855352401733,
      "learning_rate": 2.5951051796957984e-06,
      "loss": 0.5631,
      "step": 49857
    },
    {
      "epoch": 1.5315946302952108,
      "grad_norm": 0.5439947843551636,
      "learning_rate": 2.5947803931353e-06,
      "loss": 0.5237,
      "step": 49858
    },
    {
      "epoch": 1.53162534943016,
      "grad_norm": 0.41713401675224304,
      "learning_rate": 2.5944556238702124e-06,
      "loss": 0.5461,
      "step": 49859
    },
    {
      "epoch": 1.531656068565109,
      "grad_norm": 0.6381468176841736,
      "learning_rate": 2.594130871901288e-06,
      "loss": 0.5452,
      "step": 49860
    },
    {
      "epoch": 1.5316867877000584,
      "grad_norm": 0.4024293124675751,
      "learning_rate": 2.593806137229289e-06,
      "loss": 0.5038,
      "step": 49861
    },
    {
      "epoch": 1.5317175068350075,
      "grad_norm": 0.44802406430244446,
      "learning_rate": 2.5934814198549716e-06,
      "loss": 0.4988,
      "step": 49862
    },
    {
      "epoch": 1.5317482259699566,
      "grad_norm": 0.4266869127750397,
      "learning_rate": 2.5931567197790986e-06,
      "loss": 0.4462,
      "step": 49863
    },
    {
      "epoch": 1.531778945104906,
      "grad_norm": 0.44335514307022095,
      "learning_rate": 2.592832037002423e-06,
      "loss": 0.5222,
      "step": 49864
    },
    {
      "epoch": 1.531809664239855,
      "grad_norm": 0.44356435537338257,
      "learning_rate": 2.5925073715257054e-06,
      "loss": 0.5383,
      "step": 49865
    },
    {
      "epoch": 1.5318403833748042,
      "grad_norm": 0.4118313491344452,
      "learning_rate": 2.5921827233497044e-06,
      "loss": 0.5136,
      "step": 49866
    },
    {
      "epoch": 1.5318711025097533,
      "grad_norm": 0.38480496406555176,
      "learning_rate": 2.59185809247518e-06,
      "loss": 0.3826,
      "step": 49867
    },
    {
      "epoch": 1.5319018216447025,
      "grad_norm": 0.50758957862854,
      "learning_rate": 2.591533478902887e-06,
      "loss": 0.5272,
      "step": 49868
    },
    {
      "epoch": 1.5319325407796516,
      "grad_norm": 0.42199426889419556,
      "learning_rate": 2.5912088826335837e-06,
      "loss": 0.4343,
      "step": 49869
    },
    {
      "epoch": 1.5319632599146007,
      "grad_norm": 0.42653706669807434,
      "learning_rate": 2.59088430366803e-06,
      "loss": 0.4765,
      "step": 49870
    },
    {
      "epoch": 1.5319939790495498,
      "grad_norm": 0.49237746000289917,
      "learning_rate": 2.5905597420069826e-06,
      "loss": 0.4416,
      "step": 49871
    },
    {
      "epoch": 1.5320246981844992,
      "grad_norm": 0.3987477421760559,
      "learning_rate": 2.590235197651205e-06,
      "loss": 0.4467,
      "step": 49872
    },
    {
      "epoch": 1.5320554173194483,
      "grad_norm": 0.5481939315795898,
      "learning_rate": 2.5899106706014467e-06,
      "loss": 0.4839,
      "step": 49873
    },
    {
      "epoch": 1.5320861364543974,
      "grad_norm": 0.509165346622467,
      "learning_rate": 2.5895861608584695e-06,
      "loss": 0.5277,
      "step": 49874
    },
    {
      "epoch": 1.5321168555893467,
      "grad_norm": 0.5779304504394531,
      "learning_rate": 2.589261668423031e-06,
      "loss": 0.5666,
      "step": 49875
    },
    {
      "epoch": 1.5321475747242959,
      "grad_norm": 0.4406489431858063,
      "learning_rate": 2.5889371932958928e-06,
      "loss": 0.5053,
      "step": 49876
    },
    {
      "epoch": 1.532178293859245,
      "grad_norm": 0.41218453645706177,
      "learning_rate": 2.588612735477807e-06,
      "loss": 0.4328,
      "step": 49877
    },
    {
      "epoch": 1.532209012994194,
      "grad_norm": 0.555838942527771,
      "learning_rate": 2.5882882949695333e-06,
      "loss": 0.5072,
      "step": 49878
    },
    {
      "epoch": 1.5322397321291432,
      "grad_norm": 0.4447290003299713,
      "learning_rate": 2.587963871771829e-06,
      "loss": 0.5076,
      "step": 49879
    },
    {
      "epoch": 1.5322704512640923,
      "grad_norm": 0.42488083243370056,
      "learning_rate": 2.5876394658854564e-06,
      "loss": 0.5336,
      "step": 49880
    },
    {
      "epoch": 1.5323011703990415,
      "grad_norm": 0.40562519431114197,
      "learning_rate": 2.5873150773111666e-06,
      "loss": 0.4222,
      "step": 49881
    },
    {
      "epoch": 1.5323318895339906,
      "grad_norm": 0.3823734521865845,
      "learning_rate": 2.5869907060497233e-06,
      "loss": 0.4582,
      "step": 49882
    },
    {
      "epoch": 1.53236260866894,
      "grad_norm": 0.44285938143730164,
      "learning_rate": 2.5866663521018753e-06,
      "loss": 0.4868,
      "step": 49883
    },
    {
      "epoch": 1.532393327803889,
      "grad_norm": 0.43236517906188965,
      "learning_rate": 2.5863420154683903e-06,
      "loss": 0.4565,
      "step": 49884
    },
    {
      "epoch": 1.5324240469388382,
      "grad_norm": 0.40612155199050903,
      "learning_rate": 2.5860176961500194e-06,
      "loss": 0.5033,
      "step": 49885
    },
    {
      "epoch": 1.5324547660737875,
      "grad_norm": 0.4105382263660431,
      "learning_rate": 2.585693394147525e-06,
      "loss": 0.4499,
      "step": 49886
    },
    {
      "epoch": 1.5324854852087366,
      "grad_norm": 0.42423751950263977,
      "learning_rate": 2.5853691094616583e-06,
      "loss": 0.5322,
      "step": 49887
    },
    {
      "epoch": 1.5325162043436857,
      "grad_norm": 0.45758599042892456,
      "learning_rate": 2.5850448420931775e-06,
      "loss": 0.3937,
      "step": 49888
    },
    {
      "epoch": 1.5325469234786349,
      "grad_norm": 0.4095049500465393,
      "learning_rate": 2.5847205920428473e-06,
      "loss": 0.4188,
      "step": 49889
    },
    {
      "epoch": 1.532577642613584,
      "grad_norm": 0.5447326898574829,
      "learning_rate": 2.5843963593114174e-06,
      "loss": 0.4161,
      "step": 49890
    },
    {
      "epoch": 1.532608361748533,
      "grad_norm": 0.4092757999897003,
      "learning_rate": 2.584072143899651e-06,
      "loss": 0.4032,
      "step": 49891
    },
    {
      "epoch": 1.5326390808834822,
      "grad_norm": 0.42078033089637756,
      "learning_rate": 2.583747945808295e-06,
      "loss": 0.4394,
      "step": 49892
    },
    {
      "epoch": 1.5326698000184313,
      "grad_norm": 0.4826137125492096,
      "learning_rate": 2.583423765038121e-06,
      "loss": 0.4768,
      "step": 49893
    },
    {
      "epoch": 1.5327005191533807,
      "grad_norm": 0.43757006525993347,
      "learning_rate": 2.5830996015898746e-06,
      "loss": 0.4191,
      "step": 49894
    },
    {
      "epoch": 1.5327312382883298,
      "grad_norm": 0.4176581799983978,
      "learning_rate": 2.5827754554643202e-06,
      "loss": 0.4749,
      "step": 49895
    },
    {
      "epoch": 1.532761957423279,
      "grad_norm": 0.43618014454841614,
      "learning_rate": 2.5824513266622096e-06,
      "loss": 0.4668,
      "step": 49896
    },
    {
      "epoch": 1.5327926765582283,
      "grad_norm": 0.4403965175151825,
      "learning_rate": 2.582127215184301e-06,
      "loss": 0.504,
      "step": 49897
    },
    {
      "epoch": 1.5328233956931774,
      "grad_norm": 0.44429266452789307,
      "learning_rate": 2.581803121031353e-06,
      "loss": 0.4918,
      "step": 49898
    },
    {
      "epoch": 1.5328541148281265,
      "grad_norm": 0.46446216106414795,
      "learning_rate": 2.5814790442041248e-06,
      "loss": 0.4566,
      "step": 49899
    },
    {
      "epoch": 1.5328848339630756,
      "grad_norm": 0.4507487118244171,
      "learning_rate": 2.581154984703368e-06,
      "loss": 0.514,
      "step": 49900
    },
    {
      "epoch": 1.5329155530980247,
      "grad_norm": 0.4818503260612488,
      "learning_rate": 2.5808309425298404e-06,
      "loss": 0.5092,
      "step": 49901
    },
    {
      "epoch": 1.5329462722329739,
      "grad_norm": 0.4438728392124176,
      "learning_rate": 2.580506917684301e-06,
      "loss": 0.4033,
      "step": 49902
    },
    {
      "epoch": 1.532976991367923,
      "grad_norm": 0.3998097777366638,
      "learning_rate": 2.580182910167509e-06,
      "loss": 0.4224,
      "step": 49903
    },
    {
      "epoch": 1.533007710502872,
      "grad_norm": 0.39747071266174316,
      "learning_rate": 2.5798589199802147e-06,
      "loss": 0.5124,
      "step": 49904
    },
    {
      "epoch": 1.5330384296378214,
      "grad_norm": 0.5034499764442444,
      "learning_rate": 2.5795349471231788e-06,
      "loss": 0.5663,
      "step": 49905
    },
    {
      "epoch": 1.5330691487727706,
      "grad_norm": 0.449281245470047,
      "learning_rate": 2.5792109915971573e-06,
      "loss": 0.4584,
      "step": 49906
    },
    {
      "epoch": 1.5330998679077197,
      "grad_norm": 0.46364450454711914,
      "learning_rate": 2.5788870534029064e-06,
      "loss": 0.4416,
      "step": 49907
    },
    {
      "epoch": 1.533130587042669,
      "grad_norm": 0.43941909074783325,
      "learning_rate": 2.5785631325411853e-06,
      "loss": 0.4861,
      "step": 49908
    },
    {
      "epoch": 1.5331613061776181,
      "grad_norm": 0.40878552198410034,
      "learning_rate": 2.5782392290127466e-06,
      "loss": 0.4432,
      "step": 49909
    },
    {
      "epoch": 1.5331920253125673,
      "grad_norm": 0.5057161450386047,
      "learning_rate": 2.577915342818348e-06,
      "loss": 0.4336,
      "step": 49910
    },
    {
      "epoch": 1.5332227444475164,
      "grad_norm": 0.42771536111831665,
      "learning_rate": 2.577591473958746e-06,
      "loss": 0.4101,
      "step": 49911
    },
    {
      "epoch": 1.5332534635824655,
      "grad_norm": 0.49679145216941833,
      "learning_rate": 2.5772676224347002e-06,
      "loss": 0.5431,
      "step": 49912
    },
    {
      "epoch": 1.5332841827174146,
      "grad_norm": 0.4321203827857971,
      "learning_rate": 2.576943788246963e-06,
      "loss": 0.4743,
      "step": 49913
    },
    {
      "epoch": 1.5333149018523637,
      "grad_norm": 0.4681335985660553,
      "learning_rate": 2.5766199713962905e-06,
      "loss": 0.5082,
      "step": 49914
    },
    {
      "epoch": 1.5333456209873129,
      "grad_norm": 0.4709201157093048,
      "learning_rate": 2.5762961718834414e-06,
      "loss": 0.3967,
      "step": 49915
    },
    {
      "epoch": 1.5333763401222622,
      "grad_norm": 0.4089527130126953,
      "learning_rate": 2.5759723897091725e-06,
      "loss": 0.3953,
      "step": 49916
    },
    {
      "epoch": 1.5334070592572113,
      "grad_norm": 0.38475143909454346,
      "learning_rate": 2.5756486248742373e-06,
      "loss": 0.4476,
      "step": 49917
    },
    {
      "epoch": 1.5334377783921604,
      "grad_norm": 0.4293130934238434,
      "learning_rate": 2.575324877379396e-06,
      "loss": 0.417,
      "step": 49918
    },
    {
      "epoch": 1.5334684975271098,
      "grad_norm": 0.4265309274196625,
      "learning_rate": 2.5750011472253954e-06,
      "loss": 0.3958,
      "step": 49919
    },
    {
      "epoch": 1.533499216662059,
      "grad_norm": 0.40733659267425537,
      "learning_rate": 2.574677434413004e-06,
      "loss": 0.4127,
      "step": 49920
    },
    {
      "epoch": 1.533529935797008,
      "grad_norm": 0.40665438771247864,
      "learning_rate": 2.5743537389429696e-06,
      "loss": 0.3959,
      "step": 49921
    },
    {
      "epoch": 1.5335606549319571,
      "grad_norm": 0.4408540427684784,
      "learning_rate": 2.5740300608160528e-06,
      "loss": 0.4909,
      "step": 49922
    },
    {
      "epoch": 1.5335913740669063,
      "grad_norm": 0.5174211263656616,
      "learning_rate": 2.573706400033006e-06,
      "loss": 0.4514,
      "step": 49923
    },
    {
      "epoch": 1.5336220932018554,
      "grad_norm": 0.46739470958709717,
      "learning_rate": 2.5733827565945823e-06,
      "loss": 0.548,
      "step": 49924
    },
    {
      "epoch": 1.5336528123368045,
      "grad_norm": 0.4471076428890228,
      "learning_rate": 2.5730591305015483e-06,
      "loss": 0.4626,
      "step": 49925
    },
    {
      "epoch": 1.5336835314717536,
      "grad_norm": 0.4495529234409332,
      "learning_rate": 2.57273552175465e-06,
      "loss": 0.4737,
      "step": 49926
    },
    {
      "epoch": 1.533714250606703,
      "grad_norm": 0.4308341145515442,
      "learning_rate": 2.57241193035465e-06,
      "loss": 0.486,
      "step": 49927
    },
    {
      "epoch": 1.533744969741652,
      "grad_norm": 0.42573562264442444,
      "learning_rate": 2.5720883563022968e-06,
      "loss": 0.4339,
      "step": 49928
    },
    {
      "epoch": 1.5337756888766012,
      "grad_norm": 0.484165221452713,
      "learning_rate": 2.571764799598351e-06,
      "loss": 0.4853,
      "step": 49929
    },
    {
      "epoch": 1.5338064080115505,
      "grad_norm": 0.4273177683353424,
      "learning_rate": 2.5714412602435667e-06,
      "loss": 0.4501,
      "step": 49930
    },
    {
      "epoch": 1.5338371271464997,
      "grad_norm": 0.4243091642856598,
      "learning_rate": 2.571117738238704e-06,
      "loss": 0.4637,
      "step": 49931
    },
    {
      "epoch": 1.5338678462814488,
      "grad_norm": 0.43151596188545227,
      "learning_rate": 2.5707942335845113e-06,
      "loss": 0.5046,
      "step": 49932
    },
    {
      "epoch": 1.533898565416398,
      "grad_norm": 0.451270192861557,
      "learning_rate": 2.570470746281747e-06,
      "loss": 0.4092,
      "step": 49933
    },
    {
      "epoch": 1.533929284551347,
      "grad_norm": 0.4545973539352417,
      "learning_rate": 2.5701472763311676e-06,
      "loss": 0.3861,
      "step": 49934
    },
    {
      "epoch": 1.5339600036862961,
      "grad_norm": 0.40547576546669006,
      "learning_rate": 2.5698238237335314e-06,
      "loss": 0.5156,
      "step": 49935
    },
    {
      "epoch": 1.5339907228212453,
      "grad_norm": 0.46316054463386536,
      "learning_rate": 2.5695003884895866e-06,
      "loss": 0.4382,
      "step": 49936
    },
    {
      "epoch": 1.5340214419561944,
      "grad_norm": 0.3918793797492981,
      "learning_rate": 2.5691769706000936e-06,
      "loss": 0.4109,
      "step": 49937
    },
    {
      "epoch": 1.5340521610911435,
      "grad_norm": 0.41639989614486694,
      "learning_rate": 2.5688535700658056e-06,
      "loss": 0.4359,
      "step": 49938
    },
    {
      "epoch": 1.5340828802260928,
      "grad_norm": 0.42049092054367065,
      "learning_rate": 2.5685301868874835e-06,
      "loss": 0.4943,
      "step": 49939
    },
    {
      "epoch": 1.534113599361042,
      "grad_norm": 0.48333612084388733,
      "learning_rate": 2.568206821065874e-06,
      "loss": 0.4363,
      "step": 49940
    },
    {
      "epoch": 1.5341443184959913,
      "grad_norm": 0.45081278681755066,
      "learning_rate": 2.5678834726017366e-06,
      "loss": 0.4765,
      "step": 49941
    },
    {
      "epoch": 1.5341750376309404,
      "grad_norm": 0.40412187576293945,
      "learning_rate": 2.567560141495827e-06,
      "loss": 0.4769,
      "step": 49942
    },
    {
      "epoch": 1.5342057567658896,
      "grad_norm": 0.4967261254787445,
      "learning_rate": 2.5672368277489e-06,
      "loss": 0.4239,
      "step": 49943
    },
    {
      "epoch": 1.5342364759008387,
      "grad_norm": 0.4957939088344574,
      "learning_rate": 2.5669135313617123e-06,
      "loss": 0.4739,
      "step": 49944
    },
    {
      "epoch": 1.5342671950357878,
      "grad_norm": 0.44658735394477844,
      "learning_rate": 2.566590252335015e-06,
      "loss": 0.4696,
      "step": 49945
    },
    {
      "epoch": 1.534297914170737,
      "grad_norm": 0.38530707359313965,
      "learning_rate": 2.5662669906695658e-06,
      "loss": 0.5093,
      "step": 49946
    },
    {
      "epoch": 1.534328633305686,
      "grad_norm": 0.40147265791893005,
      "learning_rate": 2.5659437463661185e-06,
      "loss": 0.5081,
      "step": 49947
    },
    {
      "epoch": 1.5343593524406351,
      "grad_norm": 0.4244891405105591,
      "learning_rate": 2.5656205194254312e-06,
      "loss": 0.5041,
      "step": 49948
    },
    {
      "epoch": 1.5343900715755843,
      "grad_norm": 0.3950093686580658,
      "learning_rate": 2.565297309848255e-06,
      "loss": 0.4613,
      "step": 49949
    },
    {
      "epoch": 1.5344207907105336,
      "grad_norm": 0.4203224778175354,
      "learning_rate": 2.564974117635345e-06,
      "loss": 0.4121,
      "step": 49950
    },
    {
      "epoch": 1.5344515098454827,
      "grad_norm": 0.4142511188983917,
      "learning_rate": 2.5646509427874568e-06,
      "loss": 0.4583,
      "step": 49951
    },
    {
      "epoch": 1.534482228980432,
      "grad_norm": 0.4280681610107422,
      "learning_rate": 2.5643277853053495e-06,
      "loss": 0.5245,
      "step": 49952
    },
    {
      "epoch": 1.5345129481153812,
      "grad_norm": 0.44728362560272217,
      "learning_rate": 2.5640046451897703e-06,
      "loss": 0.4748,
      "step": 49953
    },
    {
      "epoch": 1.5345436672503303,
      "grad_norm": 0.506079912185669,
      "learning_rate": 2.5636815224414814e-06,
      "loss": 0.5306,
      "step": 49954
    },
    {
      "epoch": 1.5345743863852794,
      "grad_norm": 0.413159042596817,
      "learning_rate": 2.563358417061227e-06,
      "loss": 0.4462,
      "step": 49955
    },
    {
      "epoch": 1.5346051055202286,
      "grad_norm": 0.41509392857551575,
      "learning_rate": 2.5630353290497746e-06,
      "loss": 0.5046,
      "step": 49956
    },
    {
      "epoch": 1.5346358246551777,
      "grad_norm": 0.4074530005455017,
      "learning_rate": 2.562712258407869e-06,
      "loss": 0.4958,
      "step": 49957
    },
    {
      "epoch": 1.5346665437901268,
      "grad_norm": 0.415824294090271,
      "learning_rate": 2.562389205136272e-06,
      "loss": 0.5097,
      "step": 49958
    },
    {
      "epoch": 1.534697262925076,
      "grad_norm": 0.46298253536224365,
      "learning_rate": 2.562066169235732e-06,
      "loss": 0.4811,
      "step": 49959
    },
    {
      "epoch": 1.534727982060025,
      "grad_norm": 0.4612889885902405,
      "learning_rate": 2.5617431507070023e-06,
      "loss": 0.4348,
      "step": 49960
    },
    {
      "epoch": 1.5347587011949744,
      "grad_norm": 0.44748806953430176,
      "learning_rate": 2.561420149550846e-06,
      "loss": 0.4594,
      "step": 49961
    },
    {
      "epoch": 1.5347894203299235,
      "grad_norm": 0.39067456126213074,
      "learning_rate": 2.5610971657680104e-06,
      "loss": 0.4423,
      "step": 49962
    },
    {
      "epoch": 1.5348201394648728,
      "grad_norm": 0.4120018482208252,
      "learning_rate": 2.560774199359255e-06,
      "loss": 0.4787,
      "step": 49963
    },
    {
      "epoch": 1.534850858599822,
      "grad_norm": 0.4494587182998657,
      "learning_rate": 2.5604512503253287e-06,
      "loss": 0.496,
      "step": 49964
    },
    {
      "epoch": 1.534881577734771,
      "grad_norm": 0.4016118347644806,
      "learning_rate": 2.5601283186669866e-06,
      "loss": 0.4235,
      "step": 49965
    },
    {
      "epoch": 1.5349122968697202,
      "grad_norm": 0.399749219417572,
      "learning_rate": 2.559805404384985e-06,
      "loss": 0.4892,
      "step": 49966
    },
    {
      "epoch": 1.5349430160046693,
      "grad_norm": 0.3908216655254364,
      "learning_rate": 2.559482507480081e-06,
      "loss": 0.3756,
      "step": 49967
    },
    {
      "epoch": 1.5349737351396184,
      "grad_norm": 0.43450021743774414,
      "learning_rate": 2.559159627953022e-06,
      "loss": 0.4313,
      "step": 49968
    },
    {
      "epoch": 1.5350044542745676,
      "grad_norm": 0.4284680187702179,
      "learning_rate": 2.5588367658045642e-06,
      "loss": 0.5398,
      "step": 49969
    },
    {
      "epoch": 1.5350351734095167,
      "grad_norm": 0.3986535668373108,
      "learning_rate": 2.5585139210354637e-06,
      "loss": 0.4385,
      "step": 49970
    },
    {
      "epoch": 1.5350658925444658,
      "grad_norm": 0.41820028424263,
      "learning_rate": 2.5581910936464773e-06,
      "loss": 0.4755,
      "step": 49971
    },
    {
      "epoch": 1.5350966116794151,
      "grad_norm": 0.4367331564426422,
      "learning_rate": 2.557868283638352e-06,
      "loss": 0.4438,
      "step": 49972
    },
    {
      "epoch": 1.5351273308143643,
      "grad_norm": 0.4028822183609009,
      "learning_rate": 2.5575454910118445e-06,
      "loss": 0.4041,
      "step": 49973
    },
    {
      "epoch": 1.5351580499493134,
      "grad_norm": 0.41684842109680176,
      "learning_rate": 2.5572227157677098e-06,
      "loss": 0.4603,
      "step": 49974
    },
    {
      "epoch": 1.5351887690842627,
      "grad_norm": 0.42851126194000244,
      "learning_rate": 2.5568999579067032e-06,
      "loss": 0.4912,
      "step": 49975
    },
    {
      "epoch": 1.5352194882192118,
      "grad_norm": 0.37144818902015686,
      "learning_rate": 2.5565772174295745e-06,
      "loss": 0.4734,
      "step": 49976
    },
    {
      "epoch": 1.535250207354161,
      "grad_norm": 0.4066769778728485,
      "learning_rate": 2.556254494337079e-06,
      "loss": 0.4967,
      "step": 49977
    },
    {
      "epoch": 1.53528092648911,
      "grad_norm": 0.42072001099586487,
      "learning_rate": 2.5559317886299715e-06,
      "loss": 0.5338,
      "step": 49978
    },
    {
      "epoch": 1.5353116456240592,
      "grad_norm": 0.4281522333621979,
      "learning_rate": 2.5556091003090054e-06,
      "loss": 0.447,
      "step": 49979
    },
    {
      "epoch": 1.5353423647590083,
      "grad_norm": 0.4476102590560913,
      "learning_rate": 2.5552864293749367e-06,
      "loss": 0.4604,
      "step": 49980
    },
    {
      "epoch": 1.5353730838939574,
      "grad_norm": 0.4219203591346741,
      "learning_rate": 2.554963775828514e-06,
      "loss": 0.4956,
      "step": 49981
    },
    {
      "epoch": 1.5354038030289066,
      "grad_norm": 0.3882583975791931,
      "learning_rate": 2.554641139670493e-06,
      "loss": 0.4201,
      "step": 49982
    },
    {
      "epoch": 1.535434522163856,
      "grad_norm": 0.38606858253479004,
      "learning_rate": 2.5543185209016273e-06,
      "loss": 0.4669,
      "step": 49983
    },
    {
      "epoch": 1.535465241298805,
      "grad_norm": 0.43494299054145813,
      "learning_rate": 2.553995919522675e-06,
      "loss": 0.4997,
      "step": 49984
    },
    {
      "epoch": 1.5354959604337541,
      "grad_norm": 0.41990405321121216,
      "learning_rate": 2.5536733355343814e-06,
      "loss": 0.54,
      "step": 49985
    },
    {
      "epoch": 1.5355266795687035,
      "grad_norm": 0.4025026559829712,
      "learning_rate": 2.553350768937506e-06,
      "loss": 0.3365,
      "step": 49986
    },
    {
      "epoch": 1.5355573987036526,
      "grad_norm": 0.41215434670448303,
      "learning_rate": 2.553028219732795e-06,
      "loss": 0.4771,
      "step": 49987
    },
    {
      "epoch": 1.5355881178386017,
      "grad_norm": 0.43927305936813354,
      "learning_rate": 2.552705687921012e-06,
      "loss": 0.4106,
      "step": 49988
    },
    {
      "epoch": 1.5356188369735508,
      "grad_norm": 0.37514936923980713,
      "learning_rate": 2.5523831735029027e-06,
      "loss": 0.4165,
      "step": 49989
    },
    {
      "epoch": 1.5356495561085,
      "grad_norm": 0.4377883970737457,
      "learning_rate": 2.5520606764792243e-06,
      "loss": 0.4315,
      "step": 49990
    },
    {
      "epoch": 1.535680275243449,
      "grad_norm": 0.48390695452690125,
      "learning_rate": 2.5517381968507236e-06,
      "loss": 0.3967,
      "step": 49991
    },
    {
      "epoch": 1.5357109943783982,
      "grad_norm": 0.4179258346557617,
      "learning_rate": 2.5514157346181646e-06,
      "loss": 0.5015,
      "step": 49992
    },
    {
      "epoch": 1.5357417135133473,
      "grad_norm": 0.3847757577896118,
      "learning_rate": 2.5510932897822905e-06,
      "loss": 0.4627,
      "step": 49993
    },
    {
      "epoch": 1.5357724326482967,
      "grad_norm": 0.40064483880996704,
      "learning_rate": 2.550770862343862e-06,
      "loss": 0.5162,
      "step": 49994
    },
    {
      "epoch": 1.5358031517832458,
      "grad_norm": 0.4244721829891205,
      "learning_rate": 2.5504484523036242e-06,
      "loss": 0.5151,
      "step": 49995
    },
    {
      "epoch": 1.535833870918195,
      "grad_norm": 0.39967167377471924,
      "learning_rate": 2.5501260596623354e-06,
      "loss": 0.5166,
      "step": 49996
    },
    {
      "epoch": 1.5358645900531442,
      "grad_norm": 0.46730124950408936,
      "learning_rate": 2.5498036844207475e-06,
      "loss": 0.4708,
      "step": 49997
    },
    {
      "epoch": 1.5358953091880934,
      "grad_norm": 0.42355191707611084,
      "learning_rate": 2.5494813265796138e-06,
      "loss": 0.4971,
      "step": 49998
    },
    {
      "epoch": 1.5359260283230425,
      "grad_norm": 0.42081668972969055,
      "learning_rate": 2.549158986139688e-06,
      "loss": 0.4432,
      "step": 49999
    },
    {
      "epoch": 1.5359567474579916,
      "grad_norm": 0.42800015211105347,
      "learning_rate": 2.5488366631017204e-06,
      "loss": 0.503,
      "step": 50000
    },
    {
      "epoch": 1.5359874665929407,
      "grad_norm": 0.45349207520484924,
      "learning_rate": 2.548514357466465e-06,
      "loss": 0.5073,
      "step": 50001
    },
    {
      "epoch": 1.5360181857278898,
      "grad_norm": 0.42641302943229675,
      "learning_rate": 2.548192069234674e-06,
      "loss": 0.4709,
      "step": 50002
    },
    {
      "epoch": 1.536048904862839,
      "grad_norm": 0.5210781097412109,
      "learning_rate": 2.5478697984071045e-06,
      "loss": 0.4542,
      "step": 50003
    },
    {
      "epoch": 1.536079623997788,
      "grad_norm": 0.4226527214050293,
      "learning_rate": 2.547547544984502e-06,
      "loss": 0.4628,
      "step": 50004
    },
    {
      "epoch": 1.5361103431327374,
      "grad_norm": 0.47008538246154785,
      "learning_rate": 2.5472253089676236e-06,
      "loss": 0.4257,
      "step": 50005
    },
    {
      "epoch": 1.5361410622676865,
      "grad_norm": 0.40627530217170715,
      "learning_rate": 2.54690309035722e-06,
      "loss": 0.4976,
      "step": 50006
    },
    {
      "epoch": 1.5361717814026357,
      "grad_norm": 0.474662184715271,
      "learning_rate": 2.5465808891540477e-06,
      "loss": 0.4517,
      "step": 50007
    },
    {
      "epoch": 1.536202500537585,
      "grad_norm": 0.44406935572624207,
      "learning_rate": 2.546258705358854e-06,
      "loss": 0.5293,
      "step": 50008
    },
    {
      "epoch": 1.5362332196725341,
      "grad_norm": 0.415237158536911,
      "learning_rate": 2.5459365389723932e-06,
      "loss": 0.4702,
      "step": 50009
    },
    {
      "epoch": 1.5362639388074832,
      "grad_norm": 0.4441382884979248,
      "learning_rate": 2.545614389995419e-06,
      "loss": 0.489,
      "step": 50010
    },
    {
      "epoch": 1.5362946579424324,
      "grad_norm": 0.4071389138698578,
      "learning_rate": 2.5452922584286843e-06,
      "loss": 0.5046,
      "step": 50011
    },
    {
      "epoch": 1.5363253770773815,
      "grad_norm": 0.39037105441093445,
      "learning_rate": 2.544970144272939e-06,
      "loss": 0.4756,
      "step": 50012
    },
    {
      "epoch": 1.5363560962123306,
      "grad_norm": 0.4311472177505493,
      "learning_rate": 2.5446480475289357e-06,
      "loss": 0.4529,
      "step": 50013
    },
    {
      "epoch": 1.5363868153472797,
      "grad_norm": 0.4729299545288086,
      "learning_rate": 2.5443259681974274e-06,
      "loss": 0.5353,
      "step": 50014
    },
    {
      "epoch": 1.5364175344822288,
      "grad_norm": 0.41219207644462585,
      "learning_rate": 2.5440039062791665e-06,
      "loss": 0.4584,
      "step": 50015
    },
    {
      "epoch": 1.5364482536171782,
      "grad_norm": 0.4164358079433441,
      "learning_rate": 2.543681861774908e-06,
      "loss": 0.4712,
      "step": 50016
    },
    {
      "epoch": 1.5364789727521273,
      "grad_norm": 0.42508646845817566,
      "learning_rate": 2.5433598346853994e-06,
      "loss": 0.4435,
      "step": 50017
    },
    {
      "epoch": 1.5365096918870764,
      "grad_norm": 0.42920762300491333,
      "learning_rate": 2.5430378250113942e-06,
      "loss": 0.4076,
      "step": 50018
    },
    {
      "epoch": 1.5365404110220258,
      "grad_norm": 0.43656519055366516,
      "learning_rate": 2.542715832753644e-06,
      "loss": 0.4665,
      "step": 50019
    },
    {
      "epoch": 1.5365711301569749,
      "grad_norm": 0.41753530502319336,
      "learning_rate": 2.542393857912906e-06,
      "loss": 0.4058,
      "step": 50020
    },
    {
      "epoch": 1.536601849291924,
      "grad_norm": 0.43154874444007874,
      "learning_rate": 2.542071900489924e-06,
      "loss": 0.4931,
      "step": 50021
    },
    {
      "epoch": 1.5366325684268731,
      "grad_norm": 0.4267215430736542,
      "learning_rate": 2.541749960485458e-06,
      "loss": 0.3876,
      "step": 50022
    },
    {
      "epoch": 1.5366632875618222,
      "grad_norm": 0.3877769708633423,
      "learning_rate": 2.5414280379002485e-06,
      "loss": 0.4633,
      "step": 50023
    },
    {
      "epoch": 1.5366940066967714,
      "grad_norm": 0.399728000164032,
      "learning_rate": 2.541106132735062e-06,
      "loss": 0.438,
      "step": 50024
    },
    {
      "epoch": 1.5367247258317205,
      "grad_norm": 0.4208891689777374,
      "learning_rate": 2.5407842449906397e-06,
      "loss": 0.4731,
      "step": 50025
    },
    {
      "epoch": 1.5367554449666696,
      "grad_norm": 0.4128839671611786,
      "learning_rate": 2.540462374667739e-06,
      "loss": 0.4681,
      "step": 50026
    },
    {
      "epoch": 1.536786164101619,
      "grad_norm": 0.42136135697364807,
      "learning_rate": 2.5401405217671073e-06,
      "loss": 0.5074,
      "step": 50027
    },
    {
      "epoch": 1.536816883236568,
      "grad_norm": 0.49020570516586304,
      "learning_rate": 2.539818686289498e-06,
      "loss": 0.3868,
      "step": 50028
    },
    {
      "epoch": 1.5368476023715172,
      "grad_norm": 0.44337931275367737,
      "learning_rate": 2.5394968682356637e-06,
      "loss": 0.442,
      "step": 50029
    },
    {
      "epoch": 1.5368783215064665,
      "grad_norm": 0.4128696322441101,
      "learning_rate": 2.5391750676063575e-06,
      "loss": 0.4504,
      "step": 50030
    },
    {
      "epoch": 1.5369090406414156,
      "grad_norm": 0.41328945755958557,
      "learning_rate": 2.538853284402326e-06,
      "loss": 0.5,
      "step": 50031
    },
    {
      "epoch": 1.5369397597763648,
      "grad_norm": 0.40903887152671814,
      "learning_rate": 2.5385315186243244e-06,
      "loss": 0.4734,
      "step": 50032
    },
    {
      "epoch": 1.5369704789113139,
      "grad_norm": 0.43760132789611816,
      "learning_rate": 2.5382097702731035e-06,
      "loss": 0.4433,
      "step": 50033
    },
    {
      "epoch": 1.537001198046263,
      "grad_norm": 0.4988808035850525,
      "learning_rate": 2.5378880393494144e-06,
      "loss": 0.5159,
      "step": 50034
    },
    {
      "epoch": 1.5370319171812121,
      "grad_norm": 0.4011166989803314,
      "learning_rate": 2.5375663258540127e-06,
      "loss": 0.429,
      "step": 50035
    },
    {
      "epoch": 1.5370626363161612,
      "grad_norm": 0.449014276266098,
      "learning_rate": 2.537244629787643e-06,
      "loss": 0.4499,
      "step": 50036
    },
    {
      "epoch": 1.5370933554511104,
      "grad_norm": 0.48285311460494995,
      "learning_rate": 2.5369229511510583e-06,
      "loss": 0.5235,
      "step": 50037
    },
    {
      "epoch": 1.5371240745860597,
      "grad_norm": 0.43173348903656006,
      "learning_rate": 2.536601289945012e-06,
      "loss": 0.3924,
      "step": 50038
    },
    {
      "epoch": 1.5371547937210088,
      "grad_norm": 0.4391781985759735,
      "learning_rate": 2.536279646170259e-06,
      "loss": 0.4823,
      "step": 50039
    },
    {
      "epoch": 1.537185512855958,
      "grad_norm": 0.44215404987335205,
      "learning_rate": 2.5359580198275413e-06,
      "loss": 0.3778,
      "step": 50040
    },
    {
      "epoch": 1.5372162319909073,
      "grad_norm": 0.4171309471130371,
      "learning_rate": 2.535636410917616e-06,
      "loss": 0.4943,
      "step": 50041
    },
    {
      "epoch": 1.5372469511258564,
      "grad_norm": 0.4414767920970917,
      "learning_rate": 2.5353148194412323e-06,
      "loss": 0.5167,
      "step": 50042
    },
    {
      "epoch": 1.5372776702608055,
      "grad_norm": 0.4891737103462219,
      "learning_rate": 2.5349932453991455e-06,
      "loss": 0.3655,
      "step": 50043
    },
    {
      "epoch": 1.5373083893957546,
      "grad_norm": 0.44352713227272034,
      "learning_rate": 2.5346716887921006e-06,
      "loss": 0.5288,
      "step": 50044
    },
    {
      "epoch": 1.5373391085307038,
      "grad_norm": 0.42273032665252686,
      "learning_rate": 2.534350149620851e-06,
      "loss": 0.5096,
      "step": 50045
    },
    {
      "epoch": 1.5373698276656529,
      "grad_norm": 0.5056672692298889,
      "learning_rate": 2.534028627886148e-06,
      "loss": 0.4578,
      "step": 50046
    },
    {
      "epoch": 1.537400546800602,
      "grad_norm": 0.4734528064727783,
      "learning_rate": 2.5337071235887456e-06,
      "loss": 0.4922,
      "step": 50047
    },
    {
      "epoch": 1.5374312659355511,
      "grad_norm": 0.39602553844451904,
      "learning_rate": 2.5333856367293887e-06,
      "loss": 0.3625,
      "step": 50048
    },
    {
      "epoch": 1.5374619850705005,
      "grad_norm": 0.478038489818573,
      "learning_rate": 2.5330641673088342e-06,
      "loss": 0.4158,
      "step": 50049
    },
    {
      "epoch": 1.5374927042054496,
      "grad_norm": 0.42823266983032227,
      "learning_rate": 2.5327427153278237e-06,
      "loss": 0.4892,
      "step": 50050
    },
    {
      "epoch": 1.5375234233403987,
      "grad_norm": 0.4036554992198944,
      "learning_rate": 2.5324212807871174e-06,
      "loss": 0.4876,
      "step": 50051
    },
    {
      "epoch": 1.537554142475348,
      "grad_norm": 0.500315248966217,
      "learning_rate": 2.5320998636874662e-06,
      "loss": 0.4549,
      "step": 50052
    },
    {
      "epoch": 1.5375848616102972,
      "grad_norm": 0.4883423149585724,
      "learning_rate": 2.531778464029613e-06,
      "loss": 0.4415,
      "step": 50053
    },
    {
      "epoch": 1.5376155807452463,
      "grad_norm": 0.4760359823703766,
      "learning_rate": 2.5314570818143136e-06,
      "loss": 0.4255,
      "step": 50054
    },
    {
      "epoch": 1.5376462998801954,
      "grad_norm": 0.40879571437835693,
      "learning_rate": 2.531135717042318e-06,
      "loss": 0.3747,
      "step": 50055
    },
    {
      "epoch": 1.5376770190151445,
      "grad_norm": 0.4062041938304901,
      "learning_rate": 2.530814369714378e-06,
      "loss": 0.4959,
      "step": 50056
    },
    {
      "epoch": 1.5377077381500937,
      "grad_norm": 0.38930830359458923,
      "learning_rate": 2.530493039831242e-06,
      "loss": 0.5408,
      "step": 50057
    },
    {
      "epoch": 1.5377384572850428,
      "grad_norm": 0.3678272068500519,
      "learning_rate": 2.530171727393663e-06,
      "loss": 0.4013,
      "step": 50058
    },
    {
      "epoch": 1.537769176419992,
      "grad_norm": 0.4212905466556549,
      "learning_rate": 2.5298504324023833e-06,
      "loss": 0.4924,
      "step": 50059
    },
    {
      "epoch": 1.537799895554941,
      "grad_norm": 0.42525744438171387,
      "learning_rate": 2.5295291548581657e-06,
      "loss": 0.3887,
      "step": 50060
    },
    {
      "epoch": 1.5378306146898904,
      "grad_norm": 0.43875521421432495,
      "learning_rate": 2.5292078947617515e-06,
      "loss": 0.4436,
      "step": 50061
    },
    {
      "epoch": 1.5378613338248395,
      "grad_norm": 0.4497219920158386,
      "learning_rate": 2.528886652113898e-06,
      "loss": 0.4639,
      "step": 50062
    },
    {
      "epoch": 1.5378920529597888,
      "grad_norm": 0.4332706034183502,
      "learning_rate": 2.5285654269153482e-06,
      "loss": 0.4633,
      "step": 50063
    },
    {
      "epoch": 1.537922772094738,
      "grad_norm": 0.43165528774261475,
      "learning_rate": 2.5282442191668543e-06,
      "loss": 0.3674,
      "step": 50064
    },
    {
      "epoch": 1.537953491229687,
      "grad_norm": 0.4416959285736084,
      "learning_rate": 2.5279230288691694e-06,
      "loss": 0.5056,
      "step": 50065
    },
    {
      "epoch": 1.5379842103646362,
      "grad_norm": 0.4217385947704315,
      "learning_rate": 2.527601856023044e-06,
      "loss": 0.5331,
      "step": 50066
    },
    {
      "epoch": 1.5380149294995853,
      "grad_norm": 0.6643967628479004,
      "learning_rate": 2.5272807006292246e-06,
      "loss": 0.5142,
      "step": 50067
    },
    {
      "epoch": 1.5380456486345344,
      "grad_norm": 0.3932986557483673,
      "learning_rate": 2.5269595626884614e-06,
      "loss": 0.4856,
      "step": 50068
    },
    {
      "epoch": 1.5380763677694835,
      "grad_norm": 0.42507532238960266,
      "learning_rate": 2.5266384422015066e-06,
      "loss": 0.4649,
      "step": 50069
    },
    {
      "epoch": 1.5381070869044327,
      "grad_norm": 0.4761011004447937,
      "learning_rate": 2.5263173391691107e-06,
      "loss": 0.471,
      "step": 50070
    },
    {
      "epoch": 1.5381378060393818,
      "grad_norm": 0.423813134431839,
      "learning_rate": 2.5259962535920247e-06,
      "loss": 0.4882,
      "step": 50071
    },
    {
      "epoch": 1.5381685251743311,
      "grad_norm": 0.43376624584198,
      "learning_rate": 2.525675185470994e-06,
      "loss": 0.4838,
      "step": 50072
    },
    {
      "epoch": 1.5381992443092802,
      "grad_norm": 0.42357492446899414,
      "learning_rate": 2.52535413480677e-06,
      "loss": 0.4629,
      "step": 50073
    },
    {
      "epoch": 1.5382299634442296,
      "grad_norm": 0.41513630747795105,
      "learning_rate": 2.525033101600104e-06,
      "loss": 0.3939,
      "step": 50074
    },
    {
      "epoch": 1.5382606825791787,
      "grad_norm": 0.4269810914993286,
      "learning_rate": 2.5247120858517482e-06,
      "loss": 0.4674,
      "step": 50075
    },
    {
      "epoch": 1.5382914017141278,
      "grad_norm": 0.4251796305179596,
      "learning_rate": 2.5243910875624454e-06,
      "loss": 0.4553,
      "step": 50076
    },
    {
      "epoch": 1.538322120849077,
      "grad_norm": 0.4420255422592163,
      "learning_rate": 2.524070106732951e-06,
      "loss": 0.4183,
      "step": 50077
    },
    {
      "epoch": 1.538352839984026,
      "grad_norm": 0.6542078256607056,
      "learning_rate": 2.5237491433640117e-06,
      "loss": 0.448,
      "step": 50078
    },
    {
      "epoch": 1.5383835591189752,
      "grad_norm": 0.4024592339992523,
      "learning_rate": 2.523428197456382e-06,
      "loss": 0.3715,
      "step": 50079
    },
    {
      "epoch": 1.5384142782539243,
      "grad_norm": 0.46964651346206665,
      "learning_rate": 2.523107269010805e-06,
      "loss": 0.5511,
      "step": 50080
    },
    {
      "epoch": 1.5384449973888734,
      "grad_norm": 0.44041329622268677,
      "learning_rate": 2.522786358028033e-06,
      "loss": 0.4558,
      "step": 50081
    },
    {
      "epoch": 1.5384757165238225,
      "grad_norm": 0.4656400978565216,
      "learning_rate": 2.5224654645088153e-06,
      "loss": 0.4678,
      "step": 50082
    },
    {
      "epoch": 1.5385064356587719,
      "grad_norm": 0.4446849822998047,
      "learning_rate": 2.5221445884539054e-06,
      "loss": 0.4561,
      "step": 50083
    },
    {
      "epoch": 1.538537154793721,
      "grad_norm": 0.4824351966381073,
      "learning_rate": 2.5218237298640457e-06,
      "loss": 0.4727,
      "step": 50084
    },
    {
      "epoch": 1.5385678739286701,
      "grad_norm": 0.4035433232784271,
      "learning_rate": 2.521502888739992e-06,
      "loss": 0.4906,
      "step": 50085
    },
    {
      "epoch": 1.5385985930636195,
      "grad_norm": 0.4492471218109131,
      "learning_rate": 2.5211820650824847e-06,
      "loss": 0.5034,
      "step": 50086
    },
    {
      "epoch": 1.5386293121985686,
      "grad_norm": 0.5005199313163757,
      "learning_rate": 2.5208612588922854e-06,
      "loss": 0.4959,
      "step": 50087
    },
    {
      "epoch": 1.5386600313335177,
      "grad_norm": 0.4125315546989441,
      "learning_rate": 2.5205404701701332e-06,
      "loss": 0.4021,
      "step": 50088
    },
    {
      "epoch": 1.5386907504684668,
      "grad_norm": 0.40277159214019775,
      "learning_rate": 2.5202196989167816e-06,
      "loss": 0.3855,
      "step": 50089
    },
    {
      "epoch": 1.538721469603416,
      "grad_norm": 0.4298231303691864,
      "learning_rate": 2.5198989451329813e-06,
      "loss": 0.4356,
      "step": 50090
    },
    {
      "epoch": 1.538752188738365,
      "grad_norm": 0.42784419655799866,
      "learning_rate": 2.5195782088194744e-06,
      "loss": 0.4422,
      "step": 50091
    },
    {
      "epoch": 1.5387829078733142,
      "grad_norm": 0.4732838571071625,
      "learning_rate": 2.5192574899770208e-06,
      "loss": 0.4361,
      "step": 50092
    },
    {
      "epoch": 1.5388136270082633,
      "grad_norm": 0.4198721647262573,
      "learning_rate": 2.518936788606361e-06,
      "loss": 0.4587,
      "step": 50093
    },
    {
      "epoch": 1.5388443461432126,
      "grad_norm": 0.4417244493961334,
      "learning_rate": 2.518616104708249e-06,
      "loss": 0.3866,
      "step": 50094
    },
    {
      "epoch": 1.5388750652781618,
      "grad_norm": 0.42082479596138,
      "learning_rate": 2.518295438283427e-06,
      "loss": 0.5047,
      "step": 50095
    },
    {
      "epoch": 1.5389057844131109,
      "grad_norm": 0.3941141963005066,
      "learning_rate": 2.5179747893326533e-06,
      "loss": 0.4468,
      "step": 50096
    },
    {
      "epoch": 1.5389365035480602,
      "grad_norm": 0.4199787676334381,
      "learning_rate": 2.5176541578566693e-06,
      "loss": 0.4993,
      "step": 50097
    },
    {
      "epoch": 1.5389672226830093,
      "grad_norm": 0.4546196162700653,
      "learning_rate": 2.5173335438562294e-06,
      "loss": 0.4952,
      "step": 50098
    },
    {
      "epoch": 1.5389979418179585,
      "grad_norm": 0.42338618636131287,
      "learning_rate": 2.517012947332077e-06,
      "loss": 0.4876,
      "step": 50099
    },
    {
      "epoch": 1.5390286609529076,
      "grad_norm": 0.47025856375694275,
      "learning_rate": 2.5166923682849633e-06,
      "loss": 0.4484,
      "step": 50100
    },
    {
      "epoch": 1.5390593800878567,
      "grad_norm": 0.4016585648059845,
      "learning_rate": 2.516371806715637e-06,
      "loss": 0.4731,
      "step": 50101
    },
    {
      "epoch": 1.5390900992228058,
      "grad_norm": 0.4145303964614868,
      "learning_rate": 2.5160512626248502e-06,
      "loss": 0.5079,
      "step": 50102
    },
    {
      "epoch": 1.539120818357755,
      "grad_norm": 0.45159250497817993,
      "learning_rate": 2.5157307360133454e-06,
      "loss": 0.4908,
      "step": 50103
    },
    {
      "epoch": 1.539151537492704,
      "grad_norm": 0.4093247652053833,
      "learning_rate": 2.5154102268818737e-06,
      "loss": 0.4786,
      "step": 50104
    },
    {
      "epoch": 1.5391822566276534,
      "grad_norm": 0.4459937512874603,
      "learning_rate": 2.5150897352311854e-06,
      "loss": 0.4528,
      "step": 50105
    },
    {
      "epoch": 1.5392129757626025,
      "grad_norm": 0.4268784523010254,
      "learning_rate": 2.5147692610620268e-06,
      "loss": 0.4843,
      "step": 50106
    },
    {
      "epoch": 1.5392436948975516,
      "grad_norm": 0.4255947470664978,
      "learning_rate": 2.51444880437515e-06,
      "loss": 0.46,
      "step": 50107
    },
    {
      "epoch": 1.539274414032501,
      "grad_norm": 0.37698301672935486,
      "learning_rate": 2.5141283651712977e-06,
      "loss": 0.4802,
      "step": 50108
    },
    {
      "epoch": 1.53930513316745,
      "grad_norm": 0.4337024390697479,
      "learning_rate": 2.513807943451223e-06,
      "loss": 0.4727,
      "step": 50109
    },
    {
      "epoch": 1.5393358523023992,
      "grad_norm": 0.4208572804927826,
      "learning_rate": 2.513487539215671e-06,
      "loss": 0.5112,
      "step": 50110
    },
    {
      "epoch": 1.5393665714373483,
      "grad_norm": 0.5341833829879761,
      "learning_rate": 2.5131671524653957e-06,
      "loss": 0.5324,
      "step": 50111
    },
    {
      "epoch": 1.5393972905722975,
      "grad_norm": 0.47665780782699585,
      "learning_rate": 2.5128467832011384e-06,
      "loss": 0.454,
      "step": 50112
    },
    {
      "epoch": 1.5394280097072466,
      "grad_norm": 0.4229780435562134,
      "learning_rate": 2.51252643142365e-06,
      "loss": 0.4744,
      "step": 50113
    },
    {
      "epoch": 1.5394587288421957,
      "grad_norm": 0.41373395919799805,
      "learning_rate": 2.512206097133678e-06,
      "loss": 0.4755,
      "step": 50114
    },
    {
      "epoch": 1.5394894479771448,
      "grad_norm": 0.4464713931083679,
      "learning_rate": 2.5118857803319765e-06,
      "loss": 0.4918,
      "step": 50115
    },
    {
      "epoch": 1.5395201671120942,
      "grad_norm": 0.5122625231742859,
      "learning_rate": 2.5115654810192847e-06,
      "loss": 0.4421,
      "step": 50116
    },
    {
      "epoch": 1.5395508862470433,
      "grad_norm": 0.43847420811653137,
      "learning_rate": 2.511245199196355e-06,
      "loss": 0.5271,
      "step": 50117
    },
    {
      "epoch": 1.5395816053819924,
      "grad_norm": 0.44384676218032837,
      "learning_rate": 2.510924934863934e-06,
      "loss": 0.4816,
      "step": 50118
    },
    {
      "epoch": 1.5396123245169417,
      "grad_norm": 0.44184887409210205,
      "learning_rate": 2.5106046880227752e-06,
      "loss": 0.3947,
      "step": 50119
    },
    {
      "epoch": 1.5396430436518909,
      "grad_norm": 0.44661402702331543,
      "learning_rate": 2.5102844586736187e-06,
      "loss": 0.4554,
      "step": 50120
    },
    {
      "epoch": 1.53967376278684,
      "grad_norm": 0.4422948658466339,
      "learning_rate": 2.5099642468172193e-06,
      "loss": 0.4395,
      "step": 50121
    },
    {
      "epoch": 1.539704481921789,
      "grad_norm": 0.40756306052207947,
      "learning_rate": 2.5096440524543152e-06,
      "loss": 0.4081,
      "step": 50122
    },
    {
      "epoch": 1.5397352010567382,
      "grad_norm": 0.3987981677055359,
      "learning_rate": 2.5093238755856663e-06,
      "loss": 0.3268,
      "step": 50123
    },
    {
      "epoch": 1.5397659201916873,
      "grad_norm": 0.42953068017959595,
      "learning_rate": 2.5090037162120127e-06,
      "loss": 0.5567,
      "step": 50124
    },
    {
      "epoch": 1.5397966393266365,
      "grad_norm": 0.4092894196510315,
      "learning_rate": 2.508683574334103e-06,
      "loss": 0.4601,
      "step": 50125
    },
    {
      "epoch": 1.5398273584615856,
      "grad_norm": 0.40839213132858276,
      "learning_rate": 2.5083634499526887e-06,
      "loss": 0.443,
      "step": 50126
    },
    {
      "epoch": 1.539858077596535,
      "grad_norm": 0.3845483064651489,
      "learning_rate": 2.5080433430685103e-06,
      "loss": 0.3853,
      "step": 50127
    },
    {
      "epoch": 1.539888796731484,
      "grad_norm": 0.47599390149116516,
      "learning_rate": 2.507723253682325e-06,
      "loss": 0.5,
      "step": 50128
    },
    {
      "epoch": 1.5399195158664332,
      "grad_norm": 0.5539246797561646,
      "learning_rate": 2.5074031817948717e-06,
      "loss": 0.4666,
      "step": 50129
    },
    {
      "epoch": 1.5399502350013825,
      "grad_norm": 0.44231101870536804,
      "learning_rate": 2.5070831274069053e-06,
      "loss": 0.5126,
      "step": 50130
    },
    {
      "epoch": 1.5399809541363316,
      "grad_norm": 0.4372912049293518,
      "learning_rate": 2.5067630905191664e-06,
      "loss": 0.4465,
      "step": 50131
    },
    {
      "epoch": 1.5400116732712807,
      "grad_norm": 0.4091099202632904,
      "learning_rate": 2.506443071132406e-06,
      "loss": 0.4591,
      "step": 50132
    },
    {
      "epoch": 1.5400423924062299,
      "grad_norm": 0.42479458451271057,
      "learning_rate": 2.5061230692473702e-06,
      "loss": 0.4912,
      "step": 50133
    },
    {
      "epoch": 1.540073111541179,
      "grad_norm": 0.47866538166999817,
      "learning_rate": 2.505803084864811e-06,
      "loss": 0.5157,
      "step": 50134
    },
    {
      "epoch": 1.540103830676128,
      "grad_norm": 0.4437049925327301,
      "learning_rate": 2.5054831179854687e-06,
      "loss": 0.5003,
      "step": 50135
    },
    {
      "epoch": 1.5401345498110772,
      "grad_norm": 0.39797794818878174,
      "learning_rate": 2.5051631686100954e-06,
      "loss": 0.4515,
      "step": 50136
    },
    {
      "epoch": 1.5401652689460263,
      "grad_norm": 0.4504827857017517,
      "learning_rate": 2.504843236739435e-06,
      "loss": 0.5426,
      "step": 50137
    },
    {
      "epoch": 1.5401959880809757,
      "grad_norm": 0.4228663146495819,
      "learning_rate": 2.5045233223742403e-06,
      "loss": 0.4602,
      "step": 50138
    },
    {
      "epoch": 1.5402267072159248,
      "grad_norm": 0.44317111372947693,
      "learning_rate": 2.5042034255152524e-06,
      "loss": 0.4712,
      "step": 50139
    },
    {
      "epoch": 1.540257426350874,
      "grad_norm": 0.4604341685771942,
      "learning_rate": 2.5038835461632204e-06,
      "loss": 0.4706,
      "step": 50140
    },
    {
      "epoch": 1.5402881454858233,
      "grad_norm": 0.4091988503932953,
      "learning_rate": 2.5035636843188927e-06,
      "loss": 0.3884,
      "step": 50141
    },
    {
      "epoch": 1.5403188646207724,
      "grad_norm": 0.4247250258922577,
      "learning_rate": 2.5032438399830172e-06,
      "loss": 0.5147,
      "step": 50142
    },
    {
      "epoch": 1.5403495837557215,
      "grad_norm": 0.4663369059562683,
      "learning_rate": 2.502924013156337e-06,
      "loss": 0.5455,
      "step": 50143
    },
    {
      "epoch": 1.5403803028906706,
      "grad_norm": 0.4499705135822296,
      "learning_rate": 2.5026042038396016e-06,
      "loss": 0.4169,
      "step": 50144
    },
    {
      "epoch": 1.5404110220256197,
      "grad_norm": 0.4263071119785309,
      "learning_rate": 2.5022844120335577e-06,
      "loss": 0.4469,
      "step": 50145
    },
    {
      "epoch": 1.5404417411605689,
      "grad_norm": 0.4616346061229706,
      "learning_rate": 2.501964637738952e-06,
      "loss": 0.4837,
      "step": 50146
    },
    {
      "epoch": 1.540472460295518,
      "grad_norm": 0.44448354840278625,
      "learning_rate": 2.501644880956534e-06,
      "loss": 0.5405,
      "step": 50147
    },
    {
      "epoch": 1.540503179430467,
      "grad_norm": 0.45640382170677185,
      "learning_rate": 2.5013251416870455e-06,
      "loss": 0.4161,
      "step": 50148
    },
    {
      "epoch": 1.5405338985654164,
      "grad_norm": 0.4638679027557373,
      "learning_rate": 2.501005419931236e-06,
      "loss": 0.4614,
      "step": 50149
    },
    {
      "epoch": 1.5405646177003656,
      "grad_norm": 0.4086611270904541,
      "learning_rate": 2.5006857156898524e-06,
      "loss": 0.4618,
      "step": 50150
    },
    {
      "epoch": 1.5405953368353147,
      "grad_norm": 0.41557416319847107,
      "learning_rate": 2.5003660289636434e-06,
      "loss": 0.5132,
      "step": 50151
    },
    {
      "epoch": 1.540626055970264,
      "grad_norm": 0.41606152057647705,
      "learning_rate": 2.500046359753351e-06,
      "loss": 0.4283,
      "step": 50152
    },
    {
      "epoch": 1.5406567751052131,
      "grad_norm": 0.4852375090122223,
      "learning_rate": 2.4997267080597267e-06,
      "loss": 0.5126,
      "step": 50153
    },
    {
      "epoch": 1.5406874942401623,
      "grad_norm": 0.43928050994873047,
      "learning_rate": 2.4994070738835073e-06,
      "loss": 0.4628,
      "step": 50154
    },
    {
      "epoch": 1.5407182133751114,
      "grad_norm": 0.4319947063922882,
      "learning_rate": 2.4990874572254544e-06,
      "loss": 0.4843,
      "step": 50155
    },
    {
      "epoch": 1.5407489325100605,
      "grad_norm": 0.446628600358963,
      "learning_rate": 2.4987678580863027e-06,
      "loss": 0.4584,
      "step": 50156
    },
    {
      "epoch": 1.5407796516450096,
      "grad_norm": 0.4221840798854828,
      "learning_rate": 2.498448276466805e-06,
      "loss": 0.4913,
      "step": 50157
    },
    {
      "epoch": 1.5408103707799587,
      "grad_norm": 0.4050824046134949,
      "learning_rate": 2.4981287123677e-06,
      "loss": 0.4601,
      "step": 50158
    },
    {
      "epoch": 1.5408410899149079,
      "grad_norm": 0.4157405495643616,
      "learning_rate": 2.4978091657897453e-06,
      "loss": 0.4182,
      "step": 50159
    },
    {
      "epoch": 1.5408718090498572,
      "grad_norm": 0.4158344864845276,
      "learning_rate": 2.4974896367336787e-06,
      "loss": 0.4085,
      "step": 50160
    },
    {
      "epoch": 1.5409025281848063,
      "grad_norm": 0.454597145318985,
      "learning_rate": 2.497170125200249e-06,
      "loss": 0.4437,
      "step": 50161
    },
    {
      "epoch": 1.5409332473197555,
      "grad_norm": 0.5018113851547241,
      "learning_rate": 2.496850631190204e-06,
      "loss": 0.5709,
      "step": 50162
    },
    {
      "epoch": 1.5409639664547048,
      "grad_norm": 0.4102664887905121,
      "learning_rate": 2.4965311547042836e-06,
      "loss": 0.4188,
      "step": 50163
    },
    {
      "epoch": 1.540994685589654,
      "grad_norm": 0.4794374704360962,
      "learning_rate": 2.496211695743245e-06,
      "loss": 0.4641,
      "step": 50164
    },
    {
      "epoch": 1.541025404724603,
      "grad_norm": 0.42939990758895874,
      "learning_rate": 2.4958922543078247e-06,
      "loss": 0.551,
      "step": 50165
    },
    {
      "epoch": 1.5410561238595522,
      "grad_norm": 0.4057371914386749,
      "learning_rate": 2.495572830398775e-06,
      "loss": 0.4756,
      "step": 50166
    },
    {
      "epoch": 1.5410868429945013,
      "grad_norm": 0.43280744552612305,
      "learning_rate": 2.4952534240168357e-06,
      "loss": 0.4799,
      "step": 50167
    },
    {
      "epoch": 1.5411175621294504,
      "grad_norm": 0.4446091949939728,
      "learning_rate": 2.494934035162756e-06,
      "loss": 0.5067,
      "step": 50168
    },
    {
      "epoch": 1.5411482812643995,
      "grad_norm": 0.425690621137619,
      "learning_rate": 2.4946146638372825e-06,
      "loss": 0.4534,
      "step": 50169
    },
    {
      "epoch": 1.5411790003993486,
      "grad_norm": 0.4612048864364624,
      "learning_rate": 2.494295310041164e-06,
      "loss": 0.4084,
      "step": 50170
    },
    {
      "epoch": 1.5412097195342978,
      "grad_norm": 0.3891768753528595,
      "learning_rate": 2.493975973775139e-06,
      "loss": 0.3717,
      "step": 50171
    },
    {
      "epoch": 1.541240438669247,
      "grad_norm": 0.3914802670478821,
      "learning_rate": 2.493656655039958e-06,
      "loss": 0.4489,
      "step": 50172
    },
    {
      "epoch": 1.5412711578041962,
      "grad_norm": 0.43732160329818726,
      "learning_rate": 2.493337353836366e-06,
      "loss": 0.4892,
      "step": 50173
    },
    {
      "epoch": 1.5413018769391456,
      "grad_norm": 0.46020159125328064,
      "learning_rate": 2.493018070165112e-06,
      "loss": 0.4207,
      "step": 50174
    },
    {
      "epoch": 1.5413325960740947,
      "grad_norm": 0.4264189302921295,
      "learning_rate": 2.492698804026935e-06,
      "loss": 0.4689,
      "step": 50175
    },
    {
      "epoch": 1.5413633152090438,
      "grad_norm": 0.4648496210575104,
      "learning_rate": 2.492379555422585e-06,
      "loss": 0.4628,
      "step": 50176
    },
    {
      "epoch": 1.541394034343993,
      "grad_norm": 0.47676026821136475,
      "learning_rate": 2.4920603243528065e-06,
      "loss": 0.427,
      "step": 50177
    },
    {
      "epoch": 1.541424753478942,
      "grad_norm": 0.4406086206436157,
      "learning_rate": 2.4917411108183487e-06,
      "loss": 0.3858,
      "step": 50178
    },
    {
      "epoch": 1.5414554726138912,
      "grad_norm": 0.4382348954677582,
      "learning_rate": 2.4914219148199504e-06,
      "loss": 0.4877,
      "step": 50179
    },
    {
      "epoch": 1.5414861917488403,
      "grad_norm": 0.4005034267902374,
      "learning_rate": 2.4911027363583618e-06,
      "loss": 0.3729,
      "step": 50180
    },
    {
      "epoch": 1.5415169108837894,
      "grad_norm": 0.4742198884487152,
      "learning_rate": 2.4907835754343256e-06,
      "loss": 0.5119,
      "step": 50181
    },
    {
      "epoch": 1.5415476300187385,
      "grad_norm": 0.4437452554702759,
      "learning_rate": 2.4904644320485895e-06,
      "loss": 0.4897,
      "step": 50182
    },
    {
      "epoch": 1.5415783491536879,
      "grad_norm": 0.4136640727519989,
      "learning_rate": 2.490145306201901e-06,
      "loss": 0.4259,
      "step": 50183
    },
    {
      "epoch": 1.541609068288637,
      "grad_norm": 0.5215798020362854,
      "learning_rate": 2.489826197895e-06,
      "loss": 0.5586,
      "step": 50184
    },
    {
      "epoch": 1.5416397874235863,
      "grad_norm": 0.4407827854156494,
      "learning_rate": 2.4895071071286348e-06,
      "loss": 0.4269,
      "step": 50185
    },
    {
      "epoch": 1.5416705065585354,
      "grad_norm": 0.392412930727005,
      "learning_rate": 2.489188033903549e-06,
      "loss": 0.44,
      "step": 50186
    },
    {
      "epoch": 1.5417012256934846,
      "grad_norm": 0.4759966731071472,
      "learning_rate": 2.488868978220493e-06,
      "loss": 0.4423,
      "step": 50187
    },
    {
      "epoch": 1.5417319448284337,
      "grad_norm": 0.44442296028137207,
      "learning_rate": 2.488549940080205e-06,
      "loss": 0.4568,
      "step": 50188
    },
    {
      "epoch": 1.5417626639633828,
      "grad_norm": 0.44004595279693604,
      "learning_rate": 2.4882309194834366e-06,
      "loss": 0.5156,
      "step": 50189
    },
    {
      "epoch": 1.541793383098332,
      "grad_norm": 0.4497588872909546,
      "learning_rate": 2.487911916430923e-06,
      "loss": 0.4347,
      "step": 50190
    },
    {
      "epoch": 1.541824102233281,
      "grad_norm": 0.4195694923400879,
      "learning_rate": 2.4875929309234214e-06,
      "loss": 0.4696,
      "step": 50191
    },
    {
      "epoch": 1.5418548213682302,
      "grad_norm": 0.44314542412757874,
      "learning_rate": 2.4872739629616684e-06,
      "loss": 0.4989,
      "step": 50192
    },
    {
      "epoch": 1.5418855405031793,
      "grad_norm": 0.41242891550064087,
      "learning_rate": 2.486955012546415e-06,
      "loss": 0.4658,
      "step": 50193
    },
    {
      "epoch": 1.5419162596381286,
      "grad_norm": 0.4085294008255005,
      "learning_rate": 2.4866360796783994e-06,
      "loss": 0.4983,
      "step": 50194
    },
    {
      "epoch": 1.5419469787730777,
      "grad_norm": 0.3734314739704132,
      "learning_rate": 2.4863171643583706e-06,
      "loss": 0.417,
      "step": 50195
    },
    {
      "epoch": 1.5419776979080269,
      "grad_norm": 0.4412000775337219,
      "learning_rate": 2.485998266587073e-06,
      "loss": 0.4434,
      "step": 50196
    },
    {
      "epoch": 1.5420084170429762,
      "grad_norm": 0.4638010859489441,
      "learning_rate": 2.4856793863652505e-06,
      "loss": 0.4707,
      "step": 50197
    },
    {
      "epoch": 1.5420391361779253,
      "grad_norm": 0.44145941734313965,
      "learning_rate": 2.485360523693652e-06,
      "loss": 0.5123,
      "step": 50198
    },
    {
      "epoch": 1.5420698553128744,
      "grad_norm": 0.41519466042518616,
      "learning_rate": 2.4850416785730124e-06,
      "loss": 0.4488,
      "step": 50199
    },
    {
      "epoch": 1.5421005744478236,
      "grad_norm": 0.41978490352630615,
      "learning_rate": 2.4847228510040887e-06,
      "loss": 0.4419,
      "step": 50200
    },
    {
      "epoch": 1.5421312935827727,
      "grad_norm": 0.6333197355270386,
      "learning_rate": 2.484404040987617e-06,
      "loss": 0.4508,
      "step": 50201
    },
    {
      "epoch": 1.5421620127177218,
      "grad_norm": 0.4680371582508087,
      "learning_rate": 2.4840852485243485e-06,
      "loss": 0.4873,
      "step": 50202
    },
    {
      "epoch": 1.542192731852671,
      "grad_norm": 0.4363231062889099,
      "learning_rate": 2.4837664736150193e-06,
      "loss": 0.3772,
      "step": 50203
    },
    {
      "epoch": 1.54222345098762,
      "grad_norm": 0.4639425575733185,
      "learning_rate": 2.483447716260379e-06,
      "loss": 0.4659,
      "step": 50204
    },
    {
      "epoch": 1.5422541701225694,
      "grad_norm": 0.4281875789165497,
      "learning_rate": 2.483128976461171e-06,
      "loss": 0.51,
      "step": 50205
    },
    {
      "epoch": 1.5422848892575185,
      "grad_norm": 0.44541752338409424,
      "learning_rate": 2.4828102542181443e-06,
      "loss": 0.4811,
      "step": 50206
    },
    {
      "epoch": 1.5423156083924676,
      "grad_norm": 0.4574671983718872,
      "learning_rate": 2.4824915495320355e-06,
      "loss": 0.4611,
      "step": 50207
    },
    {
      "epoch": 1.542346327527417,
      "grad_norm": 0.4180797040462494,
      "learning_rate": 2.4821728624035936e-06,
      "loss": 0.4441,
      "step": 50208
    },
    {
      "epoch": 1.542377046662366,
      "grad_norm": 0.41592586040496826,
      "learning_rate": 2.4818541928335606e-06,
      "loss": 0.3839,
      "step": 50209
    },
    {
      "epoch": 1.5424077657973152,
      "grad_norm": 0.4294327199459076,
      "learning_rate": 2.481535540822686e-06,
      "loss": 0.503,
      "step": 50210
    },
    {
      "epoch": 1.5424384849322643,
      "grad_norm": 0.48860111832618713,
      "learning_rate": 2.4812169063717075e-06,
      "loss": 0.4872,
      "step": 50211
    },
    {
      "epoch": 1.5424692040672134,
      "grad_norm": 0.40311354398727417,
      "learning_rate": 2.4808982894813717e-06,
      "loss": 0.4208,
      "step": 50212
    },
    {
      "epoch": 1.5424999232021626,
      "grad_norm": 0.41300445795059204,
      "learning_rate": 2.4805796901524226e-06,
      "loss": 0.405,
      "step": 50213
    },
    {
      "epoch": 1.5425306423371117,
      "grad_norm": 0.42693740129470825,
      "learning_rate": 2.4802611083856077e-06,
      "loss": 0.4501,
      "step": 50214
    },
    {
      "epoch": 1.5425613614720608,
      "grad_norm": 0.44697141647338867,
      "learning_rate": 2.479942544181666e-06,
      "loss": 0.5161,
      "step": 50215
    },
    {
      "epoch": 1.5425920806070101,
      "grad_norm": 0.3982350826263428,
      "learning_rate": 2.479623997541344e-06,
      "loss": 0.4598,
      "step": 50216
    },
    {
      "epoch": 1.5426227997419593,
      "grad_norm": 0.4232880771160126,
      "learning_rate": 2.4793054684653837e-06,
      "loss": 0.458,
      "step": 50217
    },
    {
      "epoch": 1.5426535188769084,
      "grad_norm": 0.47963014245033264,
      "learning_rate": 2.478986956954532e-06,
      "loss": 0.4227,
      "step": 50218
    },
    {
      "epoch": 1.5426842380118577,
      "grad_norm": 0.4060468077659607,
      "learning_rate": 2.4786684630095348e-06,
      "loss": 0.388,
      "step": 50219
    },
    {
      "epoch": 1.5427149571468068,
      "grad_norm": 0.4492741823196411,
      "learning_rate": 2.478349986631129e-06,
      "loss": 0.4981,
      "step": 50220
    },
    {
      "epoch": 1.542745676281756,
      "grad_norm": 0.42176711559295654,
      "learning_rate": 2.4780315278200617e-06,
      "loss": 0.4741,
      "step": 50221
    },
    {
      "epoch": 1.542776395416705,
      "grad_norm": 0.6781680583953857,
      "learning_rate": 2.4777130865770783e-06,
      "loss": 0.4026,
      "step": 50222
    },
    {
      "epoch": 1.5428071145516542,
      "grad_norm": 0.4185720384120941,
      "learning_rate": 2.4773946629029233e-06,
      "loss": 0.4549,
      "step": 50223
    },
    {
      "epoch": 1.5428378336866033,
      "grad_norm": 0.3941434323787689,
      "learning_rate": 2.477076256798335e-06,
      "loss": 0.4451,
      "step": 50224
    },
    {
      "epoch": 1.5428685528215524,
      "grad_norm": 0.46126192808151245,
      "learning_rate": 2.476757868264065e-06,
      "loss": 0.4569,
      "step": 50225
    },
    {
      "epoch": 1.5428992719565016,
      "grad_norm": 0.3560293912887573,
      "learning_rate": 2.4764394973008455e-06,
      "loss": 0.4873,
      "step": 50226
    },
    {
      "epoch": 1.542929991091451,
      "grad_norm": 0.39262712001800537,
      "learning_rate": 2.4761211439094335e-06,
      "loss": 0.4883,
      "step": 50227
    },
    {
      "epoch": 1.5429607102264,
      "grad_norm": 0.42936971783638,
      "learning_rate": 2.4758028080905627e-06,
      "loss": 0.3788,
      "step": 50228
    },
    {
      "epoch": 1.5429914293613491,
      "grad_norm": 0.38734525442123413,
      "learning_rate": 2.4754844898449825e-06,
      "loss": 0.3965,
      "step": 50229
    },
    {
      "epoch": 1.5430221484962985,
      "grad_norm": 0.41769757866859436,
      "learning_rate": 2.4751661891734314e-06,
      "loss": 0.4482,
      "step": 50230
    },
    {
      "epoch": 1.5430528676312476,
      "grad_norm": 0.40403902530670166,
      "learning_rate": 2.474847906076655e-06,
      "loss": 0.4861,
      "step": 50231
    },
    {
      "epoch": 1.5430835867661967,
      "grad_norm": 0.45019227266311646,
      "learning_rate": 2.4745296405553975e-06,
      "loss": 0.3948,
      "step": 50232
    },
    {
      "epoch": 1.5431143059011458,
      "grad_norm": 0.4616183340549469,
      "learning_rate": 2.474211392610404e-06,
      "loss": 0.4834,
      "step": 50233
    },
    {
      "epoch": 1.543145025036095,
      "grad_norm": 0.39582040905952454,
      "learning_rate": 2.4738931622424125e-06,
      "loss": 0.4787,
      "step": 50234
    },
    {
      "epoch": 1.543175744171044,
      "grad_norm": 0.4615139067173004,
      "learning_rate": 2.4735749494521686e-06,
      "loss": 0.4759,
      "step": 50235
    },
    {
      "epoch": 1.5432064633059932,
      "grad_norm": 0.44027331471443176,
      "learning_rate": 2.473256754240416e-06,
      "loss": 0.4818,
      "step": 50236
    },
    {
      "epoch": 1.5432371824409423,
      "grad_norm": 0.41902992129325867,
      "learning_rate": 2.4729385766078993e-06,
      "loss": 0.4661,
      "step": 50237
    },
    {
      "epoch": 1.5432679015758917,
      "grad_norm": 0.4449838399887085,
      "learning_rate": 2.4726204165553624e-06,
      "loss": 0.4885,
      "step": 50238
    },
    {
      "epoch": 1.5432986207108408,
      "grad_norm": 0.4236762523651123,
      "learning_rate": 2.4723022740835433e-06,
      "loss": 0.4552,
      "step": 50239
    },
    {
      "epoch": 1.54332933984579,
      "grad_norm": 0.4304288625717163,
      "learning_rate": 2.4719841491931873e-06,
      "loss": 0.451,
      "step": 50240
    },
    {
      "epoch": 1.5433600589807392,
      "grad_norm": 0.4288628101348877,
      "learning_rate": 2.4716660418850393e-06,
      "loss": 0.4222,
      "step": 50241
    },
    {
      "epoch": 1.5433907781156884,
      "grad_norm": 0.4278765022754669,
      "learning_rate": 2.4713479521598426e-06,
      "loss": 0.4659,
      "step": 50242
    },
    {
      "epoch": 1.5434214972506375,
      "grad_norm": 0.4175063371658325,
      "learning_rate": 2.4710298800183363e-06,
      "loss": 0.4716,
      "step": 50243
    },
    {
      "epoch": 1.5434522163855866,
      "grad_norm": 0.4377628266811371,
      "learning_rate": 2.470711825461266e-06,
      "loss": 0.4648,
      "step": 50244
    },
    {
      "epoch": 1.5434829355205357,
      "grad_norm": 0.8005987405776978,
      "learning_rate": 2.4703937884893737e-06,
      "loss": 0.4706,
      "step": 50245
    },
    {
      "epoch": 1.5435136546554848,
      "grad_norm": 0.39492475986480713,
      "learning_rate": 2.470075769103405e-06,
      "loss": 0.5049,
      "step": 50246
    },
    {
      "epoch": 1.543544373790434,
      "grad_norm": 0.4477628469467163,
      "learning_rate": 2.4697577673040974e-06,
      "loss": 0.4415,
      "step": 50247
    },
    {
      "epoch": 1.543575092925383,
      "grad_norm": 0.506962239742279,
      "learning_rate": 2.4694397830921966e-06,
      "loss": 0.5536,
      "step": 50248
    },
    {
      "epoch": 1.5436058120603324,
      "grad_norm": 0.4302351772785187,
      "learning_rate": 2.4691218164684462e-06,
      "loss": 0.4471,
      "step": 50249
    },
    {
      "epoch": 1.5436365311952815,
      "grad_norm": 0.4581579566001892,
      "learning_rate": 2.468803867433589e-06,
      "loss": 0.4081,
      "step": 50250
    },
    {
      "epoch": 1.5436672503302307,
      "grad_norm": 0.4960251450538635,
      "learning_rate": 2.468485935988364e-06,
      "loss": 0.4908,
      "step": 50251
    },
    {
      "epoch": 1.54369796946518,
      "grad_norm": 0.44514739513397217,
      "learning_rate": 2.4681680221335167e-06,
      "loss": 0.4605,
      "step": 50252
    },
    {
      "epoch": 1.5437286886001291,
      "grad_norm": 0.41502606868743896,
      "learning_rate": 2.4678501258697884e-06,
      "loss": 0.4415,
      "step": 50253
    },
    {
      "epoch": 1.5437594077350782,
      "grad_norm": 0.42656639218330383,
      "learning_rate": 2.4675322471979222e-06,
      "loss": 0.4173,
      "step": 50254
    },
    {
      "epoch": 1.5437901268700274,
      "grad_norm": 0.40040338039398193,
      "learning_rate": 2.4672143861186635e-06,
      "loss": 0.4825,
      "step": 50255
    },
    {
      "epoch": 1.5438208460049765,
      "grad_norm": 0.4234124422073364,
      "learning_rate": 2.4668965426327484e-06,
      "loss": 0.4467,
      "step": 50256
    },
    {
      "epoch": 1.5438515651399256,
      "grad_norm": 0.42250144481658936,
      "learning_rate": 2.466578716740926e-06,
      "loss": 0.4925,
      "step": 50257
    },
    {
      "epoch": 1.5438822842748747,
      "grad_norm": 0.4044356346130371,
      "learning_rate": 2.466260908443929e-06,
      "loss": 0.4539,
      "step": 50258
    },
    {
      "epoch": 1.5439130034098238,
      "grad_norm": 0.426127165555954,
      "learning_rate": 2.465943117742512e-06,
      "loss": 0.4015,
      "step": 50259
    },
    {
      "epoch": 1.5439437225447732,
      "grad_norm": 0.42836514115333557,
      "learning_rate": 2.4656253446374077e-06,
      "loss": 0.563,
      "step": 50260
    },
    {
      "epoch": 1.5439744416797223,
      "grad_norm": 0.4176653325557709,
      "learning_rate": 2.4653075891293655e-06,
      "loss": 0.4322,
      "step": 50261
    },
    {
      "epoch": 1.5440051608146714,
      "grad_norm": 0.40709105134010315,
      "learning_rate": 2.4649898512191162e-06,
      "loss": 0.5152,
      "step": 50262
    },
    {
      "epoch": 1.5440358799496208,
      "grad_norm": 0.4196329414844513,
      "learning_rate": 2.464672130907416e-06,
      "loss": 0.4483,
      "step": 50263
    },
    {
      "epoch": 1.54406659908457,
      "grad_norm": 0.3979925811290741,
      "learning_rate": 2.4643544281949983e-06,
      "loss": 0.565,
      "step": 50264
    },
    {
      "epoch": 1.544097318219519,
      "grad_norm": 0.4598315954208374,
      "learning_rate": 2.4640367430826086e-06,
      "loss": 0.4385,
      "step": 50265
    },
    {
      "epoch": 1.5441280373544681,
      "grad_norm": 0.5254934430122375,
      "learning_rate": 2.463719075570985e-06,
      "loss": 0.4637,
      "step": 50266
    },
    {
      "epoch": 1.5441587564894173,
      "grad_norm": 0.4538790285587311,
      "learning_rate": 2.463401425660872e-06,
      "loss": 0.5267,
      "step": 50267
    },
    {
      "epoch": 1.5441894756243664,
      "grad_norm": 0.4085626006126404,
      "learning_rate": 2.4630837933530105e-06,
      "loss": 0.4717,
      "step": 50268
    },
    {
      "epoch": 1.5442201947593155,
      "grad_norm": 0.433337926864624,
      "learning_rate": 2.4627661786481474e-06,
      "loss": 0.509,
      "step": 50269
    },
    {
      "epoch": 1.5442509138942646,
      "grad_norm": 0.5182675123214722,
      "learning_rate": 2.4624485815470167e-06,
      "loss": 0.3743,
      "step": 50270
    },
    {
      "epoch": 1.544281633029214,
      "grad_norm": 0.42341697216033936,
      "learning_rate": 2.462131002050363e-06,
      "loss": 0.4892,
      "step": 50271
    },
    {
      "epoch": 1.544312352164163,
      "grad_norm": 0.430241197347641,
      "learning_rate": 2.46181344015893e-06,
      "loss": 0.447,
      "step": 50272
    },
    {
      "epoch": 1.5443430712991122,
      "grad_norm": 0.4157542884349823,
      "learning_rate": 2.461495895873458e-06,
      "loss": 0.4749,
      "step": 50273
    },
    {
      "epoch": 1.5443737904340615,
      "grad_norm": 0.43049564957618713,
      "learning_rate": 2.461178369194691e-06,
      "loss": 0.48,
      "step": 50274
    },
    {
      "epoch": 1.5444045095690107,
      "grad_norm": 0.4279327988624573,
      "learning_rate": 2.4608608601233665e-06,
      "loss": 0.3806,
      "step": 50275
    },
    {
      "epoch": 1.5444352287039598,
      "grad_norm": 0.49998757243156433,
      "learning_rate": 2.4605433686602264e-06,
      "loss": 0.5058,
      "step": 50276
    },
    {
      "epoch": 1.544465947838909,
      "grad_norm": 0.4808589518070221,
      "learning_rate": 2.4602258948060153e-06,
      "loss": 0.4993,
      "step": 50277
    },
    {
      "epoch": 1.544496666973858,
      "grad_norm": 0.43582141399383545,
      "learning_rate": 2.459908438561476e-06,
      "loss": 0.4837,
      "step": 50278
    },
    {
      "epoch": 1.5445273861088071,
      "grad_norm": 0.44276636838912964,
      "learning_rate": 2.4595909999273437e-06,
      "loss": 0.4741,
      "step": 50279
    },
    {
      "epoch": 1.5445581052437563,
      "grad_norm": 0.4208299219608307,
      "learning_rate": 2.459273578904363e-06,
      "loss": 0.4334,
      "step": 50280
    },
    {
      "epoch": 1.5445888243787054,
      "grad_norm": 0.40784019231796265,
      "learning_rate": 2.4589561754932756e-06,
      "loss": 0.4199,
      "step": 50281
    },
    {
      "epoch": 1.5446195435136545,
      "grad_norm": 0.4432283341884613,
      "learning_rate": 2.4586387896948263e-06,
      "loss": 0.4463,
      "step": 50282
    },
    {
      "epoch": 1.5446502626486038,
      "grad_norm": 0.5834959745407104,
      "learning_rate": 2.4583214215097494e-06,
      "loss": 0.4863,
      "step": 50283
    },
    {
      "epoch": 1.544680981783553,
      "grad_norm": 0.38167232275009155,
      "learning_rate": 2.4580040709387897e-06,
      "loss": 0.461,
      "step": 50284
    },
    {
      "epoch": 1.5447117009185023,
      "grad_norm": 0.4270186424255371,
      "learning_rate": 2.4576867379826885e-06,
      "loss": 0.4254,
      "step": 50285
    },
    {
      "epoch": 1.5447424200534514,
      "grad_norm": 0.4345974624156952,
      "learning_rate": 2.4573694226421884e-06,
      "loss": 0.4913,
      "step": 50286
    },
    {
      "epoch": 1.5447731391884005,
      "grad_norm": 0.4409458041191101,
      "learning_rate": 2.4570521249180267e-06,
      "loss": 0.4365,
      "step": 50287
    },
    {
      "epoch": 1.5448038583233497,
      "grad_norm": 0.4738890826702118,
      "learning_rate": 2.4567348448109497e-06,
      "loss": 0.57,
      "step": 50288
    },
    {
      "epoch": 1.5448345774582988,
      "grad_norm": 0.42893874645233154,
      "learning_rate": 2.4564175823216895e-06,
      "loss": 0.4414,
      "step": 50289
    },
    {
      "epoch": 1.544865296593248,
      "grad_norm": 0.452644020318985,
      "learning_rate": 2.456100337450995e-06,
      "loss": 0.5315,
      "step": 50290
    },
    {
      "epoch": 1.544896015728197,
      "grad_norm": 0.4387204945087433,
      "learning_rate": 2.4557831101996086e-06,
      "loss": 0.4414,
      "step": 50291
    },
    {
      "epoch": 1.5449267348631461,
      "grad_norm": 0.459561288356781,
      "learning_rate": 2.4554659005682647e-06,
      "loss": 0.4573,
      "step": 50292
    },
    {
      "epoch": 1.5449574539980953,
      "grad_norm": 0.4787662625312805,
      "learning_rate": 2.45514870855771e-06,
      "loss": 0.518,
      "step": 50293
    },
    {
      "epoch": 1.5449881731330446,
      "grad_norm": 0.40958333015441895,
      "learning_rate": 2.454831534168677e-06,
      "loss": 0.4248,
      "step": 50294
    },
    {
      "epoch": 1.5450188922679937,
      "grad_norm": 0.4219777286052704,
      "learning_rate": 2.4545143774019166e-06,
      "loss": 0.4607,
      "step": 50295
    },
    {
      "epoch": 1.545049611402943,
      "grad_norm": 0.41878417134284973,
      "learning_rate": 2.4541972382581626e-06,
      "loss": 0.5023,
      "step": 50296
    },
    {
      "epoch": 1.5450803305378922,
      "grad_norm": 0.5262888669967651,
      "learning_rate": 2.453880116738161e-06,
      "loss": 0.4479,
      "step": 50297
    },
    {
      "epoch": 1.5451110496728413,
      "grad_norm": 0.49455326795578003,
      "learning_rate": 2.453563012842646e-06,
      "loss": 0.479,
      "step": 50298
    },
    {
      "epoch": 1.5451417688077904,
      "grad_norm": 0.4046749174594879,
      "learning_rate": 2.4532459265723618e-06,
      "loss": 0.4711,
      "step": 50299
    },
    {
      "epoch": 1.5451724879427395,
      "grad_norm": 0.4401277005672455,
      "learning_rate": 2.4529288579280485e-06,
      "loss": 0.4633,
      "step": 50300
    },
    {
      "epoch": 1.5452032070776887,
      "grad_norm": 0.4127945601940155,
      "learning_rate": 2.452611806910451e-06,
      "loss": 0.534,
      "step": 50301
    },
    {
      "epoch": 1.5452339262126378,
      "grad_norm": 0.4129302501678467,
      "learning_rate": 2.4522947735203016e-06,
      "loss": 0.4322,
      "step": 50302
    },
    {
      "epoch": 1.545264645347587,
      "grad_norm": 0.40385156869888306,
      "learning_rate": 2.451977757758345e-06,
      "loss": 0.4321,
      "step": 50303
    },
    {
      "epoch": 1.545295364482536,
      "grad_norm": 0.47015535831451416,
      "learning_rate": 2.451660759625322e-06,
      "loss": 0.4463,
      "step": 50304
    },
    {
      "epoch": 1.5453260836174854,
      "grad_norm": 0.5073055624961853,
      "learning_rate": 2.451343779121975e-06,
      "loss": 0.4665,
      "step": 50305
    },
    {
      "epoch": 1.5453568027524345,
      "grad_norm": 0.43298375606536865,
      "learning_rate": 2.4510268162490393e-06,
      "loss": 0.4907,
      "step": 50306
    },
    {
      "epoch": 1.5453875218873836,
      "grad_norm": 0.4893004596233368,
      "learning_rate": 2.4507098710072574e-06,
      "loss": 0.4527,
      "step": 50307
    },
    {
      "epoch": 1.545418241022333,
      "grad_norm": 0.47468236088752747,
      "learning_rate": 2.4503929433973705e-06,
      "loss": 0.4417,
      "step": 50308
    },
    {
      "epoch": 1.545448960157282,
      "grad_norm": 0.414111465215683,
      "learning_rate": 2.4500760334201167e-06,
      "loss": 0.4485,
      "step": 50309
    },
    {
      "epoch": 1.5454796792922312,
      "grad_norm": 0.4529212713241577,
      "learning_rate": 2.4497591410762424e-06,
      "loss": 0.4859,
      "step": 50310
    },
    {
      "epoch": 1.5455103984271803,
      "grad_norm": 0.45694223046302795,
      "learning_rate": 2.4494422663664786e-06,
      "loss": 0.4049,
      "step": 50311
    },
    {
      "epoch": 1.5455411175621294,
      "grad_norm": 0.4197128713130951,
      "learning_rate": 2.4491254092915696e-06,
      "loss": 0.4937,
      "step": 50312
    },
    {
      "epoch": 1.5455718366970785,
      "grad_norm": 0.4674297869205475,
      "learning_rate": 2.4488085698522556e-06,
      "loss": 0.4789,
      "step": 50313
    },
    {
      "epoch": 1.5456025558320277,
      "grad_norm": 0.4491802453994751,
      "learning_rate": 2.448491748049281e-06,
      "loss": 0.4964,
      "step": 50314
    },
    {
      "epoch": 1.5456332749669768,
      "grad_norm": 0.41463935375213623,
      "learning_rate": 2.448174943883377e-06,
      "loss": 0.4599,
      "step": 50315
    },
    {
      "epoch": 1.5456639941019261,
      "grad_norm": 0.43993276357650757,
      "learning_rate": 2.4478581573552884e-06,
      "loss": 0.5243,
      "step": 50316
    },
    {
      "epoch": 1.5456947132368752,
      "grad_norm": 0.4263516962528229,
      "learning_rate": 2.447541388465754e-06,
      "loss": 0.5144,
      "step": 50317
    },
    {
      "epoch": 1.5457254323718244,
      "grad_norm": 0.39956122636795044,
      "learning_rate": 2.4472246372155173e-06,
      "loss": 0.3849,
      "step": 50318
    },
    {
      "epoch": 1.5457561515067737,
      "grad_norm": 0.4466768205165863,
      "learning_rate": 2.4469079036053124e-06,
      "loss": 0.4329,
      "step": 50319
    },
    {
      "epoch": 1.5457868706417228,
      "grad_norm": 0.4151947796344757,
      "learning_rate": 2.446591187635884e-06,
      "loss": 0.4261,
      "step": 50320
    },
    {
      "epoch": 1.545817589776672,
      "grad_norm": 0.39443427324295044,
      "learning_rate": 2.446274489307963e-06,
      "loss": 0.4288,
      "step": 50321
    },
    {
      "epoch": 1.545848308911621,
      "grad_norm": 0.41364648938179016,
      "learning_rate": 2.445957808622302e-06,
      "loss": 0.4933,
      "step": 50322
    },
    {
      "epoch": 1.5458790280465702,
      "grad_norm": 0.41331663727760315,
      "learning_rate": 2.4456411455796314e-06,
      "loss": 0.4335,
      "step": 50323
    },
    {
      "epoch": 1.5459097471815193,
      "grad_norm": 0.4169386625289917,
      "learning_rate": 2.445324500180696e-06,
      "loss": 0.5239,
      "step": 50324
    },
    {
      "epoch": 1.5459404663164684,
      "grad_norm": 0.46227946877479553,
      "learning_rate": 2.445007872426227e-06,
      "loss": 0.4998,
      "step": 50325
    },
    {
      "epoch": 1.5459711854514175,
      "grad_norm": 0.4172455668449402,
      "learning_rate": 2.444691262316974e-06,
      "loss": 0.4763,
      "step": 50326
    },
    {
      "epoch": 1.5460019045863669,
      "grad_norm": 0.418525367975235,
      "learning_rate": 2.444374669853673e-06,
      "loss": 0.5178,
      "step": 50327
    },
    {
      "epoch": 1.546032623721316,
      "grad_norm": 0.39667052030563354,
      "learning_rate": 2.444058095037061e-06,
      "loss": 0.4516,
      "step": 50328
    },
    {
      "epoch": 1.5460633428562651,
      "grad_norm": 0.4163476526737213,
      "learning_rate": 2.443741537867882e-06,
      "loss": 0.4913,
      "step": 50329
    },
    {
      "epoch": 1.5460940619912145,
      "grad_norm": 0.4400988221168518,
      "learning_rate": 2.443424998346866e-06,
      "loss": 0.4806,
      "step": 50330
    },
    {
      "epoch": 1.5461247811261636,
      "grad_norm": 0.4652102291584015,
      "learning_rate": 2.4431084764747647e-06,
      "loss": 0.4356,
      "step": 50331
    },
    {
      "epoch": 1.5461555002611127,
      "grad_norm": 0.4510505497455597,
      "learning_rate": 2.4427919722523085e-06,
      "loss": 0.4142,
      "step": 50332
    },
    {
      "epoch": 1.5461862193960618,
      "grad_norm": 0.49017563462257385,
      "learning_rate": 2.4424754856802422e-06,
      "loss": 0.4648,
      "step": 50333
    },
    {
      "epoch": 1.546216938531011,
      "grad_norm": 0.4045565128326416,
      "learning_rate": 2.442159016759299e-06,
      "loss": 0.4486,
      "step": 50334
    },
    {
      "epoch": 1.54624765766596,
      "grad_norm": 0.4879342317581177,
      "learning_rate": 2.4418425654902222e-06,
      "loss": 0.5171,
      "step": 50335
    },
    {
      "epoch": 1.5462783768009092,
      "grad_norm": 0.43079501390457153,
      "learning_rate": 2.4415261318737495e-06,
      "loss": 0.4465,
      "step": 50336
    },
    {
      "epoch": 1.5463090959358583,
      "grad_norm": 0.42316609621047974,
      "learning_rate": 2.441209715910623e-06,
      "loss": 0.4882,
      "step": 50337
    },
    {
      "epoch": 1.5463398150708076,
      "grad_norm": 0.4942684471607208,
      "learning_rate": 2.440893317601576e-06,
      "loss": 0.4048,
      "step": 50338
    },
    {
      "epoch": 1.5463705342057568,
      "grad_norm": 0.4308053255081177,
      "learning_rate": 2.440576936947351e-06,
      "loss": 0.4596,
      "step": 50339
    },
    {
      "epoch": 1.5464012533407059,
      "grad_norm": 0.46833834052085876,
      "learning_rate": 2.4402605739486864e-06,
      "loss": 0.4803,
      "step": 50340
    },
    {
      "epoch": 1.5464319724756552,
      "grad_norm": 0.4673694372177124,
      "learning_rate": 2.4399442286063245e-06,
      "loss": 0.4399,
      "step": 50341
    },
    {
      "epoch": 1.5464626916106043,
      "grad_norm": 0.4808107018470764,
      "learning_rate": 2.439627900920998e-06,
      "loss": 0.4364,
      "step": 50342
    },
    {
      "epoch": 1.5464934107455535,
      "grad_norm": 0.4193381667137146,
      "learning_rate": 2.4393115908934474e-06,
      "loss": 0.4753,
      "step": 50343
    },
    {
      "epoch": 1.5465241298805026,
      "grad_norm": 0.4280330240726471,
      "learning_rate": 2.4389952985244137e-06,
      "loss": 0.508,
      "step": 50344
    },
    {
      "epoch": 1.5465548490154517,
      "grad_norm": 0.47309014201164246,
      "learning_rate": 2.4386790238146342e-06,
      "loss": 0.4303,
      "step": 50345
    },
    {
      "epoch": 1.5465855681504008,
      "grad_norm": 0.43681156635284424,
      "learning_rate": 2.43836276676485e-06,
      "loss": 0.5178,
      "step": 50346
    },
    {
      "epoch": 1.54661628728535,
      "grad_norm": 0.4196072816848755,
      "learning_rate": 2.438046527375796e-06,
      "loss": 0.4372,
      "step": 50347
    },
    {
      "epoch": 1.546647006420299,
      "grad_norm": 0.4530870020389557,
      "learning_rate": 2.4377303056482116e-06,
      "loss": 0.4471,
      "step": 50348
    },
    {
      "epoch": 1.5466777255552484,
      "grad_norm": 0.47258180379867554,
      "learning_rate": 2.4374141015828366e-06,
      "loss": 0.4504,
      "step": 50349
    },
    {
      "epoch": 1.5467084446901975,
      "grad_norm": 0.37706005573272705,
      "learning_rate": 2.4370979151804118e-06,
      "loss": 0.4311,
      "step": 50350
    },
    {
      "epoch": 1.5467391638251466,
      "grad_norm": 0.4495033323764801,
      "learning_rate": 2.436781746441671e-06,
      "loss": 0.4601,
      "step": 50351
    },
    {
      "epoch": 1.546769882960096,
      "grad_norm": 0.4345487058162689,
      "learning_rate": 2.4364655953673545e-06,
      "loss": 0.4979,
      "step": 50352
    },
    {
      "epoch": 1.546800602095045,
      "grad_norm": 0.48633909225463867,
      "learning_rate": 2.4361494619581993e-06,
      "loss": 0.4508,
      "step": 50353
    },
    {
      "epoch": 1.5468313212299942,
      "grad_norm": 0.43826326727867126,
      "learning_rate": 2.4358333462149495e-06,
      "loss": 0.4925,
      "step": 50354
    },
    {
      "epoch": 1.5468620403649433,
      "grad_norm": 0.4072798788547516,
      "learning_rate": 2.435517248138336e-06,
      "loss": 0.428,
      "step": 50355
    },
    {
      "epoch": 1.5468927594998925,
      "grad_norm": 0.4594166874885559,
      "learning_rate": 2.435201167729103e-06,
      "loss": 0.4878,
      "step": 50356
    },
    {
      "epoch": 1.5469234786348416,
      "grad_norm": 0.4193148612976074,
      "learning_rate": 2.434885104987981e-06,
      "loss": 0.5084,
      "step": 50357
    },
    {
      "epoch": 1.5469541977697907,
      "grad_norm": 0.4583747088909149,
      "learning_rate": 2.434569059915718e-06,
      "loss": 0.51,
      "step": 50358
    },
    {
      "epoch": 1.5469849169047398,
      "grad_norm": 0.43108588457107544,
      "learning_rate": 2.4342530325130453e-06,
      "loss": 0.4837,
      "step": 50359
    },
    {
      "epoch": 1.5470156360396892,
      "grad_norm": 0.430470734834671,
      "learning_rate": 2.4339370227807047e-06,
      "loss": 0.5063,
      "step": 50360
    },
    {
      "epoch": 1.5470463551746383,
      "grad_norm": 0.39702802896499634,
      "learning_rate": 2.433621030719431e-06,
      "loss": 0.5026,
      "step": 50361
    },
    {
      "epoch": 1.5470770743095874,
      "grad_norm": 0.3973376750946045,
      "learning_rate": 2.4333050563299598e-06,
      "loss": 0.4793,
      "step": 50362
    },
    {
      "epoch": 1.5471077934445367,
      "grad_norm": 0.4246636927127838,
      "learning_rate": 2.43298909961304e-06,
      "loss": 0.4712,
      "step": 50363
    },
    {
      "epoch": 1.5471385125794859,
      "grad_norm": 0.42973506450653076,
      "learning_rate": 2.432673160569399e-06,
      "loss": 0.4613,
      "step": 50364
    },
    {
      "epoch": 1.547169231714435,
      "grad_norm": 0.42569500207901,
      "learning_rate": 2.4323572391997805e-06,
      "loss": 0.461,
      "step": 50365
    },
    {
      "epoch": 1.547199950849384,
      "grad_norm": 0.4013580083847046,
      "learning_rate": 2.4320413355049154e-06,
      "loss": 0.4505,
      "step": 50366
    },
    {
      "epoch": 1.5472306699843332,
      "grad_norm": 0.4160219728946686,
      "learning_rate": 2.4317254494855526e-06,
      "loss": 0.48,
      "step": 50367
    },
    {
      "epoch": 1.5472613891192823,
      "grad_norm": 0.45055684447288513,
      "learning_rate": 2.4314095811424197e-06,
      "loss": 0.436,
      "step": 50368
    },
    {
      "epoch": 1.5472921082542315,
      "grad_norm": 0.420663058757782,
      "learning_rate": 2.4310937304762615e-06,
      "loss": 0.4744,
      "step": 50369
    },
    {
      "epoch": 1.5473228273891806,
      "grad_norm": 0.4251241981983185,
      "learning_rate": 2.4307778974878095e-06,
      "loss": 0.4779,
      "step": 50370
    },
    {
      "epoch": 1.54735354652413,
      "grad_norm": 0.4172923266887665,
      "learning_rate": 2.4304620821778047e-06,
      "loss": 0.4318,
      "step": 50371
    },
    {
      "epoch": 1.547384265659079,
      "grad_norm": 0.44497841596603394,
      "learning_rate": 2.430146284546984e-06,
      "loss": 0.4585,
      "step": 50372
    },
    {
      "epoch": 1.5474149847940282,
      "grad_norm": 0.39327970147132874,
      "learning_rate": 2.429830504596088e-06,
      "loss": 0.4721,
      "step": 50373
    },
    {
      "epoch": 1.5474457039289775,
      "grad_norm": 0.5141381025314331,
      "learning_rate": 2.429514742325849e-06,
      "loss": 0.4873,
      "step": 50374
    },
    {
      "epoch": 1.5474764230639266,
      "grad_norm": 0.45469945669174194,
      "learning_rate": 2.4291989977370076e-06,
      "loss": 0.4812,
      "step": 50375
    },
    {
      "epoch": 1.5475071421988758,
      "grad_norm": 0.428866446018219,
      "learning_rate": 2.4288832708303e-06,
      "loss": 0.5966,
      "step": 50376
    },
    {
      "epoch": 1.5475378613338249,
      "grad_norm": 0.4109977185726166,
      "learning_rate": 2.4285675616064674e-06,
      "loss": 0.5613,
      "step": 50377
    },
    {
      "epoch": 1.547568580468774,
      "grad_norm": 0.4255603849887848,
      "learning_rate": 2.4282518700662403e-06,
      "loss": 0.444,
      "step": 50378
    },
    {
      "epoch": 1.547599299603723,
      "grad_norm": 0.4773688316345215,
      "learning_rate": 2.4279361962103607e-06,
      "loss": 0.4856,
      "step": 50379
    },
    {
      "epoch": 1.5476300187386722,
      "grad_norm": 0.4214724004268646,
      "learning_rate": 2.4276205400395647e-06,
      "loss": 0.5014,
      "step": 50380
    },
    {
      "epoch": 1.5476607378736214,
      "grad_norm": 0.38378018140792847,
      "learning_rate": 2.42730490155459e-06,
      "loss": 0.4044,
      "step": 50381
    },
    {
      "epoch": 1.5476914570085707,
      "grad_norm": 0.4075733721256256,
      "learning_rate": 2.4269892807561767e-06,
      "loss": 0.4547,
      "step": 50382
    },
    {
      "epoch": 1.5477221761435198,
      "grad_norm": 0.42851293087005615,
      "learning_rate": 2.426673677645055e-06,
      "loss": 0.4671,
      "step": 50383
    },
    {
      "epoch": 1.547752895278469,
      "grad_norm": 0.4389713406562805,
      "learning_rate": 2.4263580922219665e-06,
      "loss": 0.5457,
      "step": 50384
    },
    {
      "epoch": 1.5477836144134183,
      "grad_norm": 0.389117032289505,
      "learning_rate": 2.4260425244876473e-06,
      "loss": 0.4054,
      "step": 50385
    },
    {
      "epoch": 1.5478143335483674,
      "grad_norm": 0.41408833861351013,
      "learning_rate": 2.425726974442838e-06,
      "loss": 0.4323,
      "step": 50386
    },
    {
      "epoch": 1.5478450526833165,
      "grad_norm": 0.40550684928894043,
      "learning_rate": 2.425411442088269e-06,
      "loss": 0.4354,
      "step": 50387
    },
    {
      "epoch": 1.5478757718182656,
      "grad_norm": 0.418643981218338,
      "learning_rate": 2.425095927424681e-06,
      "loss": 0.4718,
      "step": 50388
    },
    {
      "epoch": 1.5479064909532148,
      "grad_norm": 0.45996659994125366,
      "learning_rate": 2.424780430452811e-06,
      "loss": 0.4959,
      "step": 50389
    },
    {
      "epoch": 1.5479372100881639,
      "grad_norm": 0.4406459331512451,
      "learning_rate": 2.4244649511733977e-06,
      "loss": 0.5262,
      "step": 50390
    },
    {
      "epoch": 1.547967929223113,
      "grad_norm": 0.4574933350086212,
      "learning_rate": 2.424149489587172e-06,
      "loss": 0.4991,
      "step": 50391
    },
    {
      "epoch": 1.5479986483580621,
      "grad_norm": 0.4245227575302124,
      "learning_rate": 2.4238340456948784e-06,
      "loss": 0.4914,
      "step": 50392
    },
    {
      "epoch": 1.5480293674930112,
      "grad_norm": 0.400036096572876,
      "learning_rate": 2.4235186194972427e-06,
      "loss": 0.4318,
      "step": 50393
    },
    {
      "epoch": 1.5480600866279606,
      "grad_norm": 0.4420301616191864,
      "learning_rate": 2.423203210995014e-06,
      "loss": 0.4231,
      "step": 50394
    },
    {
      "epoch": 1.5480908057629097,
      "grad_norm": 0.42128291726112366,
      "learning_rate": 2.422887820188922e-06,
      "loss": 0.5034,
      "step": 50395
    },
    {
      "epoch": 1.548121524897859,
      "grad_norm": 0.390297532081604,
      "learning_rate": 2.4225724470797062e-06,
      "loss": 0.4946,
      "step": 50396
    },
    {
      "epoch": 1.5481522440328082,
      "grad_norm": 0.43391329050064087,
      "learning_rate": 2.422257091668099e-06,
      "loss": 0.4674,
      "step": 50397
    },
    {
      "epoch": 1.5481829631677573,
      "grad_norm": 0.3951006531715393,
      "learning_rate": 2.4219417539548363e-06,
      "loss": 0.453,
      "step": 50398
    },
    {
      "epoch": 1.5482136823027064,
      "grad_norm": 0.414445698261261,
      "learning_rate": 2.4216264339406647e-06,
      "loss": 0.4768,
      "step": 50399
    },
    {
      "epoch": 1.5482444014376555,
      "grad_norm": 0.4322672188282013,
      "learning_rate": 2.4213111316263104e-06,
      "loss": 0.4776,
      "step": 50400
    },
    {
      "epoch": 1.5482751205726046,
      "grad_norm": 0.418268620967865,
      "learning_rate": 2.4209958470125162e-06,
      "loss": 0.4814,
      "step": 50401
    },
    {
      "epoch": 1.5483058397075538,
      "grad_norm": 0.4422614872455597,
      "learning_rate": 2.420680580100012e-06,
      "loss": 0.4601,
      "step": 50402
    },
    {
      "epoch": 1.5483365588425029,
      "grad_norm": 0.4644125998020172,
      "learning_rate": 2.420365330889538e-06,
      "loss": 0.528,
      "step": 50403
    },
    {
      "epoch": 1.548367277977452,
      "grad_norm": 0.4283014237880707,
      "learning_rate": 2.420050099381831e-06,
      "loss": 0.5216,
      "step": 50404
    },
    {
      "epoch": 1.5483979971124013,
      "grad_norm": 0.39321792125701904,
      "learning_rate": 2.4197348855776283e-06,
      "loss": 0.523,
      "step": 50405
    },
    {
      "epoch": 1.5484287162473505,
      "grad_norm": 0.41129767894744873,
      "learning_rate": 2.419419689477661e-06,
      "loss": 0.5268,
      "step": 50406
    },
    {
      "epoch": 1.5484594353822998,
      "grad_norm": 0.41107362508773804,
      "learning_rate": 2.4191045110826694e-06,
      "loss": 0.4222,
      "step": 50407
    },
    {
      "epoch": 1.548490154517249,
      "grad_norm": 0.43921130895614624,
      "learning_rate": 2.418789350393388e-06,
      "loss": 0.4766,
      "step": 50408
    },
    {
      "epoch": 1.548520873652198,
      "grad_norm": 0.5036501884460449,
      "learning_rate": 2.4184742074105572e-06,
      "loss": 0.545,
      "step": 50409
    },
    {
      "epoch": 1.5485515927871472,
      "grad_norm": 0.4275650382041931,
      "learning_rate": 2.4181590821349057e-06,
      "loss": 0.4061,
      "step": 50410
    },
    {
      "epoch": 1.5485823119220963,
      "grad_norm": 0.5646233558654785,
      "learning_rate": 2.4178439745671733e-06,
      "loss": 0.446,
      "step": 50411
    },
    {
      "epoch": 1.5486130310570454,
      "grad_norm": 0.43780481815338135,
      "learning_rate": 2.4175288847080957e-06,
      "loss": 0.4567,
      "step": 50412
    },
    {
      "epoch": 1.5486437501919945,
      "grad_norm": 0.48869654536247253,
      "learning_rate": 2.417213812558412e-06,
      "loss": 0.4254,
      "step": 50413
    },
    {
      "epoch": 1.5486744693269436,
      "grad_norm": 0.4138833284378052,
      "learning_rate": 2.416898758118853e-06,
      "loss": 0.3666,
      "step": 50414
    },
    {
      "epoch": 1.5487051884618928,
      "grad_norm": 0.4371572434902191,
      "learning_rate": 2.4165837213901557e-06,
      "loss": 0.4103,
      "step": 50415
    },
    {
      "epoch": 1.548735907596842,
      "grad_norm": 0.4591975212097168,
      "learning_rate": 2.416268702373057e-06,
      "loss": 0.4992,
      "step": 50416
    },
    {
      "epoch": 1.5487666267317912,
      "grad_norm": 0.4212970733642578,
      "learning_rate": 2.415953701068292e-06,
      "loss": 0.5224,
      "step": 50417
    },
    {
      "epoch": 1.5487973458667403,
      "grad_norm": 0.4467731714248657,
      "learning_rate": 2.4156387174765996e-06,
      "loss": 0.4959,
      "step": 50418
    },
    {
      "epoch": 1.5488280650016897,
      "grad_norm": 0.44915854930877686,
      "learning_rate": 2.4153237515987103e-06,
      "loss": 0.4426,
      "step": 50419
    },
    {
      "epoch": 1.5488587841366388,
      "grad_norm": 0.4266272783279419,
      "learning_rate": 2.4150088034353614e-06,
      "loss": 0.4295,
      "step": 50420
    },
    {
      "epoch": 1.548889503271588,
      "grad_norm": 0.4616853594779968,
      "learning_rate": 2.4146938729872903e-06,
      "loss": 0.4549,
      "step": 50421
    },
    {
      "epoch": 1.548920222406537,
      "grad_norm": 0.4413484036922455,
      "learning_rate": 2.4143789602552335e-06,
      "loss": 0.3925,
      "step": 50422
    },
    {
      "epoch": 1.5489509415414862,
      "grad_norm": 0.4630817174911499,
      "learning_rate": 2.4140640652399215e-06,
      "loss": 0.5499,
      "step": 50423
    },
    {
      "epoch": 1.5489816606764353,
      "grad_norm": 0.4344657063484192,
      "learning_rate": 2.413749187942096e-06,
      "loss": 0.5208,
      "step": 50424
    },
    {
      "epoch": 1.5490123798113844,
      "grad_norm": 0.44668519496917725,
      "learning_rate": 2.4134343283624827e-06,
      "loss": 0.4661,
      "step": 50425
    },
    {
      "epoch": 1.5490430989463335,
      "grad_norm": 0.43155908584594727,
      "learning_rate": 2.4131194865018293e-06,
      "loss": 0.4823,
      "step": 50426
    },
    {
      "epoch": 1.5490738180812829,
      "grad_norm": 0.47254636883735657,
      "learning_rate": 2.4128046623608625e-06,
      "loss": 0.403,
      "step": 50427
    },
    {
      "epoch": 1.549104537216232,
      "grad_norm": 0.44166889786720276,
      "learning_rate": 2.412489855940323e-06,
      "loss": 0.5078,
      "step": 50428
    },
    {
      "epoch": 1.549135256351181,
      "grad_norm": 0.5623186826705933,
      "learning_rate": 2.4121750672409384e-06,
      "loss": 0.4959,
      "step": 50429
    },
    {
      "epoch": 1.5491659754861304,
      "grad_norm": 0.4484204649925232,
      "learning_rate": 2.4118602962634528e-06,
      "loss": 0.4532,
      "step": 50430
    },
    {
      "epoch": 1.5491966946210796,
      "grad_norm": 0.4203687608242035,
      "learning_rate": 2.4115455430085964e-06,
      "loss": 0.4531,
      "step": 50431
    },
    {
      "epoch": 1.5492274137560287,
      "grad_norm": 0.4851614534854889,
      "learning_rate": 2.4112308074771073e-06,
      "loss": 0.4849,
      "step": 50432
    },
    {
      "epoch": 1.5492581328909778,
      "grad_norm": 0.44450679421424866,
      "learning_rate": 2.410916089669716e-06,
      "loss": 0.5289,
      "step": 50433
    },
    {
      "epoch": 1.549288852025927,
      "grad_norm": 0.4224793314933777,
      "learning_rate": 2.4106013895871604e-06,
      "loss": 0.5027,
      "step": 50434
    },
    {
      "epoch": 1.549319571160876,
      "grad_norm": 0.4158381521701813,
      "learning_rate": 2.410286707230175e-06,
      "loss": 0.4606,
      "step": 50435
    },
    {
      "epoch": 1.5493502902958252,
      "grad_norm": 0.4123615324497223,
      "learning_rate": 2.4099720425994954e-06,
      "loss": 0.4672,
      "step": 50436
    },
    {
      "epoch": 1.5493810094307743,
      "grad_norm": 0.4946911334991455,
      "learning_rate": 2.409657395695858e-06,
      "loss": 0.4826,
      "step": 50437
    },
    {
      "epoch": 1.5494117285657236,
      "grad_norm": 0.44609513878822327,
      "learning_rate": 2.4093427665199942e-06,
      "loss": 0.4398,
      "step": 50438
    },
    {
      "epoch": 1.5494424477006727,
      "grad_norm": 0.4182564914226532,
      "learning_rate": 2.40902815507264e-06,
      "loss": 0.4703,
      "step": 50439
    },
    {
      "epoch": 1.5494731668356219,
      "grad_norm": 0.4041532278060913,
      "learning_rate": 2.408713561354531e-06,
      "loss": 0.4581,
      "step": 50440
    },
    {
      "epoch": 1.5495038859705712,
      "grad_norm": 0.4755329489707947,
      "learning_rate": 2.4083989853664037e-06,
      "loss": 0.5068,
      "step": 50441
    },
    {
      "epoch": 1.5495346051055203,
      "grad_norm": 0.4205048978328705,
      "learning_rate": 2.408084427108989e-06,
      "loss": 0.495,
      "step": 50442
    },
    {
      "epoch": 1.5495653242404694,
      "grad_norm": 0.4473297595977783,
      "learning_rate": 2.4077698865830224e-06,
      "loss": 0.4838,
      "step": 50443
    },
    {
      "epoch": 1.5495960433754186,
      "grad_norm": 0.44309431314468384,
      "learning_rate": 2.4074553637892405e-06,
      "loss": 0.4635,
      "step": 50444
    },
    {
      "epoch": 1.5496267625103677,
      "grad_norm": 0.4544536769390106,
      "learning_rate": 2.4071408587283784e-06,
      "loss": 0.5052,
      "step": 50445
    },
    {
      "epoch": 1.5496574816453168,
      "grad_norm": 0.416995644569397,
      "learning_rate": 2.4068263714011675e-06,
      "loss": 0.3722,
      "step": 50446
    },
    {
      "epoch": 1.549688200780266,
      "grad_norm": 0.4508390724658966,
      "learning_rate": 2.4065119018083426e-06,
      "loss": 0.509,
      "step": 50447
    },
    {
      "epoch": 1.549718919915215,
      "grad_norm": 0.4277782142162323,
      "learning_rate": 2.4061974499506402e-06,
      "loss": 0.478,
      "step": 50448
    },
    {
      "epoch": 1.5497496390501644,
      "grad_norm": 0.4654216468334198,
      "learning_rate": 2.405883015828797e-06,
      "loss": 0.4044,
      "step": 50449
    },
    {
      "epoch": 1.5497803581851135,
      "grad_norm": 0.4208621680736542,
      "learning_rate": 2.4055685994435416e-06,
      "loss": 0.4742,
      "step": 50450
    },
    {
      "epoch": 1.5498110773200626,
      "grad_norm": 0.4660415053367615,
      "learning_rate": 2.4052542007956117e-06,
      "loss": 0.46,
      "step": 50451
    },
    {
      "epoch": 1.549841796455012,
      "grad_norm": 0.4739822745323181,
      "learning_rate": 2.40493981988574e-06,
      "loss": 0.4622,
      "step": 50452
    },
    {
      "epoch": 1.549872515589961,
      "grad_norm": 0.43133530020713806,
      "learning_rate": 2.404625456714661e-06,
      "loss": 0.432,
      "step": 50453
    },
    {
      "epoch": 1.5499032347249102,
      "grad_norm": 0.4336351752281189,
      "learning_rate": 2.404311111283114e-06,
      "loss": 0.4307,
      "step": 50454
    },
    {
      "epoch": 1.5499339538598593,
      "grad_norm": 0.5336564779281616,
      "learning_rate": 2.4039967835918254e-06,
      "loss": 0.4708,
      "step": 50455
    },
    {
      "epoch": 1.5499646729948084,
      "grad_norm": 0.43978944420814514,
      "learning_rate": 2.4036824736415332e-06,
      "loss": 0.4888,
      "step": 50456
    },
    {
      "epoch": 1.5499953921297576,
      "grad_norm": 0.39921504259109497,
      "learning_rate": 2.4033681814329713e-06,
      "loss": 0.4025,
      "step": 50457
    },
    {
      "epoch": 1.5500261112647067,
      "grad_norm": 0.428759902715683,
      "learning_rate": 2.4030539069668756e-06,
      "loss": 0.4807,
      "step": 50458
    },
    {
      "epoch": 1.5500568303996558,
      "grad_norm": 0.4272094964981079,
      "learning_rate": 2.402739650243976e-06,
      "loss": 0.4526,
      "step": 50459
    },
    {
      "epoch": 1.5500875495346051,
      "grad_norm": 0.3915524482727051,
      "learning_rate": 2.4024254112650104e-06,
      "loss": 0.4501,
      "step": 50460
    },
    {
      "epoch": 1.5501182686695543,
      "grad_norm": 0.5445845127105713,
      "learning_rate": 2.4021111900307058e-06,
      "loss": 0.4318,
      "step": 50461
    },
    {
      "epoch": 1.5501489878045034,
      "grad_norm": 0.39924678206443787,
      "learning_rate": 2.4017969865418066e-06,
      "loss": 0.3767,
      "step": 50462
    },
    {
      "epoch": 1.5501797069394527,
      "grad_norm": 0.4391382038593292,
      "learning_rate": 2.401482800799039e-06,
      "loss": 0.4531,
      "step": 50463
    },
    {
      "epoch": 1.5502104260744018,
      "grad_norm": 0.43427619338035583,
      "learning_rate": 2.4011686328031415e-06,
      "loss": 0.4343,
      "step": 50464
    },
    {
      "epoch": 1.550241145209351,
      "grad_norm": 0.4171786308288574,
      "learning_rate": 2.4008544825548396e-06,
      "loss": 0.4798,
      "step": 50465
    },
    {
      "epoch": 1.5502718643443,
      "grad_norm": 0.45815637707710266,
      "learning_rate": 2.4005403500548786e-06,
      "loss": 0.381,
      "step": 50466
    },
    {
      "epoch": 1.5503025834792492,
      "grad_norm": 0.39975589513778687,
      "learning_rate": 2.400226235303983e-06,
      "loss": 0.4264,
      "step": 50467
    },
    {
      "epoch": 1.5503333026141983,
      "grad_norm": 0.4886340796947479,
      "learning_rate": 2.3999121383028933e-06,
      "loss": 0.3736,
      "step": 50468
    },
    {
      "epoch": 1.5503640217491474,
      "grad_norm": 0.4987832009792328,
      "learning_rate": 2.399598059052336e-06,
      "loss": 0.4353,
      "step": 50469
    },
    {
      "epoch": 1.5503947408840966,
      "grad_norm": 0.42415651679039,
      "learning_rate": 2.399283997553049e-06,
      "loss": 0.3944,
      "step": 50470
    },
    {
      "epoch": 1.550425460019046,
      "grad_norm": 0.4015716016292572,
      "learning_rate": 2.3989699538057642e-06,
      "loss": 0.4696,
      "step": 50471
    },
    {
      "epoch": 1.550456179153995,
      "grad_norm": 0.441636323928833,
      "learning_rate": 2.3986559278112165e-06,
      "loss": 0.4243,
      "step": 50472
    },
    {
      "epoch": 1.5504868982889441,
      "grad_norm": 0.40867799520492554,
      "learning_rate": 2.398341919570142e-06,
      "loss": 0.3695,
      "step": 50473
    },
    {
      "epoch": 1.5505176174238935,
      "grad_norm": 0.4339563548564911,
      "learning_rate": 2.3980279290832677e-06,
      "loss": 0.4228,
      "step": 50474
    },
    {
      "epoch": 1.5505483365588426,
      "grad_norm": 0.4774801433086395,
      "learning_rate": 2.3977139563513295e-06,
      "loss": 0.4547,
      "step": 50475
    },
    {
      "epoch": 1.5505790556937917,
      "grad_norm": 0.43802782893180847,
      "learning_rate": 2.397400001375062e-06,
      "loss": 0.4395,
      "step": 50476
    },
    {
      "epoch": 1.5506097748287408,
      "grad_norm": 0.44114992022514343,
      "learning_rate": 2.3970860641551995e-06,
      "loss": 0.4976,
      "step": 50477
    },
    {
      "epoch": 1.55064049396369,
      "grad_norm": 0.4375346004962921,
      "learning_rate": 2.3967721446924717e-06,
      "loss": 0.4954,
      "step": 50478
    },
    {
      "epoch": 1.550671213098639,
      "grad_norm": 0.45748546719551086,
      "learning_rate": 2.396458242987614e-06,
      "loss": 0.5015,
      "step": 50479
    },
    {
      "epoch": 1.5507019322335882,
      "grad_norm": 0.4319501519203186,
      "learning_rate": 2.396144359041358e-06,
      "loss": 0.4556,
      "step": 50480
    },
    {
      "epoch": 1.5507326513685373,
      "grad_norm": 0.4174214005470276,
      "learning_rate": 2.3958304928544407e-06,
      "loss": 0.4943,
      "step": 50481
    },
    {
      "epoch": 1.5507633705034867,
      "grad_norm": 0.404756098985672,
      "learning_rate": 2.3955166444275903e-06,
      "loss": 0.4778,
      "step": 50482
    },
    {
      "epoch": 1.5507940896384358,
      "grad_norm": 0.3858329951763153,
      "learning_rate": 2.3952028137615414e-06,
      "loss": 0.4724,
      "step": 50483
    },
    {
      "epoch": 1.550824808773385,
      "grad_norm": 0.409712016582489,
      "learning_rate": 2.394889000857028e-06,
      "loss": 0.44,
      "step": 50484
    },
    {
      "epoch": 1.5508555279083343,
      "grad_norm": 0.4570133090019226,
      "learning_rate": 2.394575205714784e-06,
      "loss": 0.414,
      "step": 50485
    },
    {
      "epoch": 1.5508862470432834,
      "grad_norm": 0.44804123044013977,
      "learning_rate": 2.3942614283355393e-06,
      "loss": 0.4635,
      "step": 50486
    },
    {
      "epoch": 1.5509169661782325,
      "grad_norm": 0.48060712218284607,
      "learning_rate": 2.393947668720028e-06,
      "loss": 0.4455,
      "step": 50487
    },
    {
      "epoch": 1.5509476853131816,
      "grad_norm": 0.44743841886520386,
      "learning_rate": 2.3936339268689824e-06,
      "loss": 0.4366,
      "step": 50488
    },
    {
      "epoch": 1.5509784044481307,
      "grad_norm": 0.4099777638912201,
      "learning_rate": 2.393320202783137e-06,
      "loss": 0.4469,
      "step": 50489
    },
    {
      "epoch": 1.5510091235830799,
      "grad_norm": 0.4475065767765045,
      "learning_rate": 2.393006496463225e-06,
      "loss": 0.5447,
      "step": 50490
    },
    {
      "epoch": 1.551039842718029,
      "grad_norm": 0.4129977524280548,
      "learning_rate": 2.3926928079099754e-06,
      "loss": 0.4747,
      "step": 50491
    },
    {
      "epoch": 1.551070561852978,
      "grad_norm": 0.42092564702033997,
      "learning_rate": 2.3923791371241236e-06,
      "loss": 0.52,
      "step": 50492
    },
    {
      "epoch": 1.5511012809879274,
      "grad_norm": 0.4462905526161194,
      "learning_rate": 2.392065484106402e-06,
      "loss": 0.5077,
      "step": 50493
    },
    {
      "epoch": 1.5511320001228766,
      "grad_norm": 0.4026419520378113,
      "learning_rate": 2.391751848857544e-06,
      "loss": 0.4603,
      "step": 50494
    },
    {
      "epoch": 1.5511627192578257,
      "grad_norm": 0.4254516065120697,
      "learning_rate": 2.391438231378279e-06,
      "loss": 0.4688,
      "step": 50495
    },
    {
      "epoch": 1.551193438392775,
      "grad_norm": 0.42451873421669006,
      "learning_rate": 2.3911246316693436e-06,
      "loss": 0.4489,
      "step": 50496
    },
    {
      "epoch": 1.5512241575277241,
      "grad_norm": 0.4651111364364624,
      "learning_rate": 2.390811049731463e-06,
      "loss": 0.4198,
      "step": 50497
    },
    {
      "epoch": 1.5512548766626733,
      "grad_norm": 0.4408380389213562,
      "learning_rate": 2.390497485565381e-06,
      "loss": 0.4358,
      "step": 50498
    },
    {
      "epoch": 1.5512855957976224,
      "grad_norm": 0.4396752417087555,
      "learning_rate": 2.3901839391718197e-06,
      "loss": 0.4997,
      "step": 50499
    },
    {
      "epoch": 1.5513163149325715,
      "grad_norm": 0.41453826427459717,
      "learning_rate": 2.389870410551518e-06,
      "loss": 0.4519,
      "step": 50500
    },
    {
      "epoch": 1.5513470340675206,
      "grad_norm": 0.4898601770401001,
      "learning_rate": 2.389556899705203e-06,
      "loss": 0.4705,
      "step": 50501
    },
    {
      "epoch": 1.5513777532024697,
      "grad_norm": 0.41106048226356506,
      "learning_rate": 2.389243406633609e-06,
      "loss": 0.4798,
      "step": 50502
    },
    {
      "epoch": 1.5514084723374189,
      "grad_norm": 0.47028982639312744,
      "learning_rate": 2.3889299313374693e-06,
      "loss": 0.4401,
      "step": 50503
    },
    {
      "epoch": 1.551439191472368,
      "grad_norm": 0.4319782555103302,
      "learning_rate": 2.388616473817518e-06,
      "loss": 0.4868,
      "step": 50504
    },
    {
      "epoch": 1.5514699106073173,
      "grad_norm": 0.4289584159851074,
      "learning_rate": 2.3883030340744807e-06,
      "loss": 0.5351,
      "step": 50505
    },
    {
      "epoch": 1.5515006297422664,
      "grad_norm": 0.4341270625591278,
      "learning_rate": 2.387989612109094e-06,
      "loss": 0.4536,
      "step": 50506
    },
    {
      "epoch": 1.5515313488772158,
      "grad_norm": 0.45352354645729065,
      "learning_rate": 2.3876762079220883e-06,
      "loss": 0.4468,
      "step": 50507
    },
    {
      "epoch": 1.551562068012165,
      "grad_norm": 0.40860816836357117,
      "learning_rate": 2.3873628215141976e-06,
      "loss": 0.4637,
      "step": 50508
    },
    {
      "epoch": 1.551592787147114,
      "grad_norm": 0.42317911982536316,
      "learning_rate": 2.3870494528861553e-06,
      "loss": 0.467,
      "step": 50509
    },
    {
      "epoch": 1.5516235062820631,
      "grad_norm": 0.5173045992851257,
      "learning_rate": 2.386736102038687e-06,
      "loss": 0.4813,
      "step": 50510
    },
    {
      "epoch": 1.5516542254170123,
      "grad_norm": 0.4056086242198944,
      "learning_rate": 2.3864227689725295e-06,
      "loss": 0.4281,
      "step": 50511
    },
    {
      "epoch": 1.5516849445519614,
      "grad_norm": 0.44973626732826233,
      "learning_rate": 2.3861094536884123e-06,
      "loss": 0.5199,
      "step": 50512
    },
    {
      "epoch": 1.5517156636869105,
      "grad_norm": 0.4188922643661499,
      "learning_rate": 2.3857961561870724e-06,
      "loss": 0.511,
      "step": 50513
    },
    {
      "epoch": 1.5517463828218596,
      "grad_norm": 0.4925990104675293,
      "learning_rate": 2.385482876469233e-06,
      "loss": 0.5189,
      "step": 50514
    },
    {
      "epoch": 1.5517771019568087,
      "grad_norm": 0.48598694801330566,
      "learning_rate": 2.3851696145356308e-06,
      "loss": 0.4342,
      "step": 50515
    },
    {
      "epoch": 1.551807821091758,
      "grad_norm": 0.4296284019947052,
      "learning_rate": 2.3848563703869964e-06,
      "loss": 0.4785,
      "step": 50516
    },
    {
      "epoch": 1.5518385402267072,
      "grad_norm": 0.4480978846549988,
      "learning_rate": 2.384543144024065e-06,
      "loss": 0.4673,
      "step": 50517
    },
    {
      "epoch": 1.5518692593616565,
      "grad_norm": 0.42099833488464355,
      "learning_rate": 2.3842299354475627e-06,
      "loss": 0.5134,
      "step": 50518
    },
    {
      "epoch": 1.5518999784966057,
      "grad_norm": 0.5665222406387329,
      "learning_rate": 2.3839167446582224e-06,
      "loss": 0.5099,
      "step": 50519
    },
    {
      "epoch": 1.5519306976315548,
      "grad_norm": 0.43439701199531555,
      "learning_rate": 2.383603571656776e-06,
      "loss": 0.4537,
      "step": 50520
    },
    {
      "epoch": 1.551961416766504,
      "grad_norm": 0.4241476356983185,
      "learning_rate": 2.3832904164439597e-06,
      "loss": 0.5001,
      "step": 50521
    },
    {
      "epoch": 1.551992135901453,
      "grad_norm": 0.4567590355873108,
      "learning_rate": 2.3829772790204962e-06,
      "loss": 0.4667,
      "step": 50522
    },
    {
      "epoch": 1.5520228550364021,
      "grad_norm": 0.4760861098766327,
      "learning_rate": 2.382664159387126e-06,
      "loss": 0.5043,
      "step": 50523
    },
    {
      "epoch": 1.5520535741713513,
      "grad_norm": 0.4154035747051239,
      "learning_rate": 2.3823510575445686e-06,
      "loss": 0.471,
      "step": 50524
    },
    {
      "epoch": 1.5520842933063004,
      "grad_norm": 0.41598808765411377,
      "learning_rate": 2.382037973493567e-06,
      "loss": 0.5393,
      "step": 50525
    },
    {
      "epoch": 1.5521150124412495,
      "grad_norm": 0.4477926790714264,
      "learning_rate": 2.381724907234847e-06,
      "loss": 0.5062,
      "step": 50526
    },
    {
      "epoch": 1.5521457315761988,
      "grad_norm": 0.42201098799705505,
      "learning_rate": 2.381411858769139e-06,
      "loss": 0.4866,
      "step": 50527
    },
    {
      "epoch": 1.552176450711148,
      "grad_norm": 0.48484644293785095,
      "learning_rate": 2.381098828097177e-06,
      "loss": 0.4838,
      "step": 50528
    },
    {
      "epoch": 1.552207169846097,
      "grad_norm": 0.48971930146217346,
      "learning_rate": 2.3807858152196895e-06,
      "loss": 0.4154,
      "step": 50529
    },
    {
      "epoch": 1.5522378889810464,
      "grad_norm": 0.40427449345588684,
      "learning_rate": 2.380472820137413e-06,
      "loss": 0.4581,
      "step": 50530
    },
    {
      "epoch": 1.5522686081159955,
      "grad_norm": 0.46411585807800293,
      "learning_rate": 2.38015984285107e-06,
      "loss": 0.476,
      "step": 50531
    },
    {
      "epoch": 1.5522993272509447,
      "grad_norm": 0.4448859691619873,
      "learning_rate": 2.3798468833613997e-06,
      "loss": 0.4719,
      "step": 50532
    },
    {
      "epoch": 1.5523300463858938,
      "grad_norm": 0.44199731945991516,
      "learning_rate": 2.379533941669123e-06,
      "loss": 0.4366,
      "step": 50533
    },
    {
      "epoch": 1.552360765520843,
      "grad_norm": 0.40628427267074585,
      "learning_rate": 2.379221017774983e-06,
      "loss": 0.5133,
      "step": 50534
    },
    {
      "epoch": 1.552391484655792,
      "grad_norm": 0.42557165026664734,
      "learning_rate": 2.378908111679702e-06,
      "loss": 0.4485,
      "step": 50535
    },
    {
      "epoch": 1.5524222037907411,
      "grad_norm": 0.40518414974212646,
      "learning_rate": 2.378595223384016e-06,
      "loss": 0.4325,
      "step": 50536
    },
    {
      "epoch": 1.5524529229256903,
      "grad_norm": 0.43373724818229675,
      "learning_rate": 2.37828235288865e-06,
      "loss": 0.4743,
      "step": 50537
    },
    {
      "epoch": 1.5524836420606396,
      "grad_norm": 0.471157431602478,
      "learning_rate": 2.377969500194338e-06,
      "loss": 0.5198,
      "step": 50538
    },
    {
      "epoch": 1.5525143611955887,
      "grad_norm": 0.45632433891296387,
      "learning_rate": 2.377656665301811e-06,
      "loss": 0.5535,
      "step": 50539
    },
    {
      "epoch": 1.5525450803305378,
      "grad_norm": 0.46477264165878296,
      "learning_rate": 2.3773438482118005e-06,
      "loss": 0.4338,
      "step": 50540
    },
    {
      "epoch": 1.5525757994654872,
      "grad_norm": 0.4152126610279083,
      "learning_rate": 2.3770310489250348e-06,
      "loss": 0.4875,
      "step": 50541
    },
    {
      "epoch": 1.5526065186004363,
      "grad_norm": 0.4463297128677368,
      "learning_rate": 2.376718267442244e-06,
      "loss": 0.4475,
      "step": 50542
    },
    {
      "epoch": 1.5526372377353854,
      "grad_norm": 0.4295051097869873,
      "learning_rate": 2.376405503764161e-06,
      "loss": 0.5002,
      "step": 50543
    },
    {
      "epoch": 1.5526679568703345,
      "grad_norm": 0.4414615333080292,
      "learning_rate": 2.3760927578915148e-06,
      "loss": 0.4489,
      "step": 50544
    },
    {
      "epoch": 1.5526986760052837,
      "grad_norm": 0.43585702776908875,
      "learning_rate": 2.37578002982504e-06,
      "loss": 0.4357,
      "step": 50545
    },
    {
      "epoch": 1.5527293951402328,
      "grad_norm": 0.49996471405029297,
      "learning_rate": 2.375467319565461e-06,
      "loss": 0.4738,
      "step": 50546
    },
    {
      "epoch": 1.552760114275182,
      "grad_norm": 0.4168553948402405,
      "learning_rate": 2.3751546271135096e-06,
      "loss": 0.4779,
      "step": 50547
    },
    {
      "epoch": 1.552790833410131,
      "grad_norm": 0.44573819637298584,
      "learning_rate": 2.374841952469917e-06,
      "loss": 0.4822,
      "step": 50548
    },
    {
      "epoch": 1.5528215525450804,
      "grad_norm": 0.4378485381603241,
      "learning_rate": 2.374529295635416e-06,
      "loss": 0.4442,
      "step": 50549
    },
    {
      "epoch": 1.5528522716800295,
      "grad_norm": 0.4266917109489441,
      "learning_rate": 2.3742166566107327e-06,
      "loss": 0.4599,
      "step": 50550
    },
    {
      "epoch": 1.5528829908149786,
      "grad_norm": 0.43295523524284363,
      "learning_rate": 2.373904035396598e-06,
      "loss": 0.4436,
      "step": 50551
    },
    {
      "epoch": 1.552913709949928,
      "grad_norm": 0.4346657991409302,
      "learning_rate": 2.3735914319937437e-06,
      "loss": 0.4749,
      "step": 50552
    },
    {
      "epoch": 1.552944429084877,
      "grad_norm": 0.42815807461738586,
      "learning_rate": 2.373278846402902e-06,
      "loss": 0.4706,
      "step": 50553
    },
    {
      "epoch": 1.5529751482198262,
      "grad_norm": 0.4357061982154846,
      "learning_rate": 2.3729662786247976e-06,
      "loss": 0.5179,
      "step": 50554
    },
    {
      "epoch": 1.5530058673547753,
      "grad_norm": 0.4083864986896515,
      "learning_rate": 2.3726537286601627e-06,
      "loss": 0.4507,
      "step": 50555
    },
    {
      "epoch": 1.5530365864897244,
      "grad_norm": 0.4963826537132263,
      "learning_rate": 2.3723411965097276e-06,
      "loss": 0.5253,
      "step": 50556
    },
    {
      "epoch": 1.5530673056246735,
      "grad_norm": 0.45705702900886536,
      "learning_rate": 2.3720286821742258e-06,
      "loss": 0.4492,
      "step": 50557
    },
    {
      "epoch": 1.5530980247596227,
      "grad_norm": 0.4162379205226898,
      "learning_rate": 2.3717161856543802e-06,
      "loss": 0.5242,
      "step": 50558
    },
    {
      "epoch": 1.5531287438945718,
      "grad_norm": 0.45178088545799255,
      "learning_rate": 2.3714037069509266e-06,
      "loss": 0.5128,
      "step": 50559
    },
    {
      "epoch": 1.5531594630295211,
      "grad_norm": 0.4456366002559662,
      "learning_rate": 2.3710912460645874e-06,
      "loss": 0.5461,
      "step": 50560
    },
    {
      "epoch": 1.5531901821644702,
      "grad_norm": 0.4186311364173889,
      "learning_rate": 2.3707788029961033e-06,
      "loss": 0.4881,
      "step": 50561
    },
    {
      "epoch": 1.5532209012994194,
      "grad_norm": 0.41945964097976685,
      "learning_rate": 2.3704663777461957e-06,
      "loss": 0.4517,
      "step": 50562
    },
    {
      "epoch": 1.5532516204343687,
      "grad_norm": 0.43217870593070984,
      "learning_rate": 2.370153970315595e-06,
      "loss": 0.5005,
      "step": 50563
    },
    {
      "epoch": 1.5532823395693178,
      "grad_norm": 0.5029056072235107,
      "learning_rate": 2.369841580705037e-06,
      "loss": 0.4593,
      "step": 50564
    },
    {
      "epoch": 1.553313058704267,
      "grad_norm": 0.4008468687534332,
      "learning_rate": 2.369529208915241e-06,
      "loss": 0.521,
      "step": 50565
    },
    {
      "epoch": 1.553343777839216,
      "grad_norm": 0.4596572518348694,
      "learning_rate": 2.3692168549469473e-06,
      "loss": 0.4357,
      "step": 50566
    },
    {
      "epoch": 1.5533744969741652,
      "grad_norm": 0.3991638123989105,
      "learning_rate": 2.3689045188008785e-06,
      "loss": 0.4899,
      "step": 50567
    },
    {
      "epoch": 1.5534052161091143,
      "grad_norm": 0.49933886528015137,
      "learning_rate": 2.3685922004777682e-06,
      "loss": 0.3972,
      "step": 50568
    },
    {
      "epoch": 1.5534359352440634,
      "grad_norm": 0.403982937335968,
      "learning_rate": 2.3682798999783394e-06,
      "loss": 0.5028,
      "step": 50569
    },
    {
      "epoch": 1.5534666543790125,
      "grad_norm": 0.5200343728065491,
      "learning_rate": 2.3679676173033307e-06,
      "loss": 0.4763,
      "step": 50570
    },
    {
      "epoch": 1.5534973735139619,
      "grad_norm": 0.41271793842315674,
      "learning_rate": 2.367655352453464e-06,
      "loss": 0.4431,
      "step": 50571
    },
    {
      "epoch": 1.553528092648911,
      "grad_norm": 0.4640231430530548,
      "learning_rate": 2.367343105429474e-06,
      "loss": 0.4233,
      "step": 50572
    },
    {
      "epoch": 1.5535588117838601,
      "grad_norm": 0.41401827335357666,
      "learning_rate": 2.3670308762320838e-06,
      "loss": 0.4595,
      "step": 50573
    },
    {
      "epoch": 1.5535895309188095,
      "grad_norm": 0.4611247479915619,
      "learning_rate": 2.3667186648620268e-06,
      "loss": 0.4238,
      "step": 50574
    },
    {
      "epoch": 1.5536202500537586,
      "grad_norm": 0.4542523920536041,
      "learning_rate": 2.3664064713200317e-06,
      "loss": 0.5138,
      "step": 50575
    },
    {
      "epoch": 1.5536509691887077,
      "grad_norm": 0.4310797154903412,
      "learning_rate": 2.36609429560683e-06,
      "loss": 0.4347,
      "step": 50576
    },
    {
      "epoch": 1.5536816883236568,
      "grad_norm": 0.4363671541213989,
      "learning_rate": 2.365782137723145e-06,
      "loss": 0.4586,
      "step": 50577
    },
    {
      "epoch": 1.553712407458606,
      "grad_norm": 0.4161800742149353,
      "learning_rate": 2.365469997669709e-06,
      "loss": 0.5007,
      "step": 50578
    },
    {
      "epoch": 1.553743126593555,
      "grad_norm": 0.3855782747268677,
      "learning_rate": 2.3651578754472516e-06,
      "loss": 0.4983,
      "step": 50579
    },
    {
      "epoch": 1.5537738457285042,
      "grad_norm": 0.4416719377040863,
      "learning_rate": 2.364845771056503e-06,
      "loss": 0.4219,
      "step": 50580
    },
    {
      "epoch": 1.5538045648634533,
      "grad_norm": 0.4793389141559601,
      "learning_rate": 2.364533684498188e-06,
      "loss": 0.4834,
      "step": 50581
    },
    {
      "epoch": 1.5538352839984026,
      "grad_norm": 0.48145967721939087,
      "learning_rate": 2.364221615773039e-06,
      "loss": 0.4859,
      "step": 50582
    },
    {
      "epoch": 1.5538660031333518,
      "grad_norm": 0.5917162299156189,
      "learning_rate": 2.3639095648817824e-06,
      "loss": 0.4712,
      "step": 50583
    },
    {
      "epoch": 1.553896722268301,
      "grad_norm": 0.39401116967201233,
      "learning_rate": 2.363597531825148e-06,
      "loss": 0.5262,
      "step": 50584
    },
    {
      "epoch": 1.5539274414032502,
      "grad_norm": 0.4253289997577667,
      "learning_rate": 2.363285516603869e-06,
      "loss": 0.5069,
      "step": 50585
    },
    {
      "epoch": 1.5539581605381994,
      "grad_norm": 0.4004809856414795,
      "learning_rate": 2.3629735192186665e-06,
      "loss": 0.4563,
      "step": 50586
    },
    {
      "epoch": 1.5539888796731485,
      "grad_norm": 0.4235362708568573,
      "learning_rate": 2.362661539670272e-06,
      "loss": 0.444,
      "step": 50587
    },
    {
      "epoch": 1.5540195988080976,
      "grad_norm": 0.41859057545661926,
      "learning_rate": 2.3623495779594164e-06,
      "loss": 0.4863,
      "step": 50588
    },
    {
      "epoch": 1.5540503179430467,
      "grad_norm": 0.43167930841445923,
      "learning_rate": 2.362037634086829e-06,
      "loss": 0.4562,
      "step": 50589
    },
    {
      "epoch": 1.5540810370779958,
      "grad_norm": 0.42292720079421997,
      "learning_rate": 2.361725708053233e-06,
      "loss": 0.4492,
      "step": 50590
    },
    {
      "epoch": 1.554111756212945,
      "grad_norm": 0.39155906438827515,
      "learning_rate": 2.36141379985936e-06,
      "loss": 0.3948,
      "step": 50591
    },
    {
      "epoch": 1.554142475347894,
      "grad_norm": 0.4319654107093811,
      "learning_rate": 2.3611019095059385e-06,
      "loss": 0.4398,
      "step": 50592
    },
    {
      "epoch": 1.5541731944828434,
      "grad_norm": 0.3967014253139496,
      "learning_rate": 2.3607900369937e-06,
      "loss": 0.4378,
      "step": 50593
    },
    {
      "epoch": 1.5542039136177925,
      "grad_norm": 0.4853133261203766,
      "learning_rate": 2.360478182323367e-06,
      "loss": 0.4326,
      "step": 50594
    },
    {
      "epoch": 1.5542346327527417,
      "grad_norm": 0.41353839635849,
      "learning_rate": 2.3601663454956736e-06,
      "loss": 0.4064,
      "step": 50595
    },
    {
      "epoch": 1.554265351887691,
      "grad_norm": 0.4216916561126709,
      "learning_rate": 2.3598545265113394e-06,
      "loss": 0.4678,
      "step": 50596
    },
    {
      "epoch": 1.5542960710226401,
      "grad_norm": 0.45753213763237,
      "learning_rate": 2.3595427253711045e-06,
      "loss": 0.4918,
      "step": 50597
    },
    {
      "epoch": 1.5543267901575892,
      "grad_norm": 0.4193284809589386,
      "learning_rate": 2.3592309420756888e-06,
      "loss": 0.4987,
      "step": 50598
    },
    {
      "epoch": 1.5543575092925384,
      "grad_norm": 0.4743526577949524,
      "learning_rate": 2.3589191766258223e-06,
      "loss": 0.4297,
      "step": 50599
    },
    {
      "epoch": 1.5543882284274875,
      "grad_norm": 0.42394110560417175,
      "learning_rate": 2.3586074290222362e-06,
      "loss": 0.5453,
      "step": 50600
    },
    {
      "epoch": 1.5544189475624366,
      "grad_norm": 0.4423327147960663,
      "learning_rate": 2.3582956992656504e-06,
      "loss": 0.4932,
      "step": 50601
    },
    {
      "epoch": 1.5544496666973857,
      "grad_norm": 0.42952054738998413,
      "learning_rate": 2.3579839873568056e-06,
      "loss": 0.5479,
      "step": 50602
    },
    {
      "epoch": 1.5544803858323348,
      "grad_norm": 0.40041738748550415,
      "learning_rate": 2.3576722932964193e-06,
      "loss": 0.4216,
      "step": 50603
    },
    {
      "epoch": 1.5545111049672842,
      "grad_norm": 0.42422306537628174,
      "learning_rate": 2.3573606170852258e-06,
      "loss": 0.4733,
      "step": 50604
    },
    {
      "epoch": 1.5545418241022333,
      "grad_norm": 0.4412532448768616,
      "learning_rate": 2.3570489587239476e-06,
      "loss": 0.4209,
      "step": 50605
    },
    {
      "epoch": 1.5545725432371824,
      "grad_norm": 0.40553584694862366,
      "learning_rate": 2.3567373182133145e-06,
      "loss": 0.4328,
      "step": 50606
    },
    {
      "epoch": 1.5546032623721318,
      "grad_norm": 0.3776704668998718,
      "learning_rate": 2.3564256955540567e-06,
      "loss": 0.405,
      "step": 50607
    },
    {
      "epoch": 1.5546339815070809,
      "grad_norm": 0.4289393126964569,
      "learning_rate": 2.3561140907469025e-06,
      "loss": 0.4764,
      "step": 50608
    },
    {
      "epoch": 1.55466470064203,
      "grad_norm": 0.4934465289115906,
      "learning_rate": 2.3558025037925745e-06,
      "loss": 0.4928,
      "step": 50609
    },
    {
      "epoch": 1.5546954197769791,
      "grad_norm": 0.4995286166667938,
      "learning_rate": 2.355490934691804e-06,
      "loss": 0.4943,
      "step": 50610
    },
    {
      "epoch": 1.5547261389119282,
      "grad_norm": 0.4360097348690033,
      "learning_rate": 2.3551793834453184e-06,
      "loss": 0.447,
      "step": 50611
    },
    {
      "epoch": 1.5547568580468774,
      "grad_norm": 0.4096298813819885,
      "learning_rate": 2.354867850053849e-06,
      "loss": 0.3824,
      "step": 50612
    },
    {
      "epoch": 1.5547875771818265,
      "grad_norm": 0.427510142326355,
      "learning_rate": 2.3545563345181153e-06,
      "loss": 0.5157,
      "step": 50613
    },
    {
      "epoch": 1.5548182963167756,
      "grad_norm": 0.4458273947238922,
      "learning_rate": 2.3542448368388505e-06,
      "loss": 0.5226,
      "step": 50614
    },
    {
      "epoch": 1.5548490154517247,
      "grad_norm": 0.43236449360847473,
      "learning_rate": 2.35393335701678e-06,
      "loss": 0.5754,
      "step": 50615
    },
    {
      "epoch": 1.554879734586674,
      "grad_norm": 1.6031848192214966,
      "learning_rate": 2.3536218950526348e-06,
      "loss": 0.4319,
      "step": 50616
    },
    {
      "epoch": 1.5549104537216232,
      "grad_norm": 0.4705088138580322,
      "learning_rate": 2.353310450947137e-06,
      "loss": 0.4749,
      "step": 50617
    },
    {
      "epoch": 1.5549411728565725,
      "grad_norm": 0.4070741534233093,
      "learning_rate": 2.352999024701017e-06,
      "loss": 0.3935,
      "step": 50618
    },
    {
      "epoch": 1.5549718919915216,
      "grad_norm": 0.4084184765815735,
      "learning_rate": 2.3526876163150026e-06,
      "loss": 0.4139,
      "step": 50619
    },
    {
      "epoch": 1.5550026111264708,
      "grad_norm": 0.4144253730773926,
      "learning_rate": 2.3523762257898186e-06,
      "loss": 0.4865,
      "step": 50620
    },
    {
      "epoch": 1.5550333302614199,
      "grad_norm": 0.3801916837692261,
      "learning_rate": 2.352064853126198e-06,
      "loss": 0.4675,
      "step": 50621
    },
    {
      "epoch": 1.555064049396369,
      "grad_norm": 0.4284084141254425,
      "learning_rate": 2.3517534983248614e-06,
      "loss": 0.5314,
      "step": 50622
    },
    {
      "epoch": 1.5550947685313181,
      "grad_norm": 0.39390912652015686,
      "learning_rate": 2.351442161386538e-06,
      "loss": 0.4307,
      "step": 50623
    },
    {
      "epoch": 1.5551254876662672,
      "grad_norm": 0.4352814853191376,
      "learning_rate": 2.351130842311956e-06,
      "loss": 0.416,
      "step": 50624
    },
    {
      "epoch": 1.5551562068012164,
      "grad_norm": 0.42104852199554443,
      "learning_rate": 2.350819541101845e-06,
      "loss": 0.4091,
      "step": 50625
    },
    {
      "epoch": 1.5551869259361655,
      "grad_norm": 0.42673853039741516,
      "learning_rate": 2.350508257756926e-06,
      "loss": 0.4445,
      "step": 50626
    },
    {
      "epoch": 1.5552176450711148,
      "grad_norm": 0.4177715480327606,
      "learning_rate": 2.3501969922779323e-06,
      "loss": 0.3577,
      "step": 50627
    },
    {
      "epoch": 1.555248364206064,
      "grad_norm": 0.4053245484828949,
      "learning_rate": 2.349885744665582e-06,
      "loss": 0.4591,
      "step": 50628
    },
    {
      "epoch": 1.5552790833410133,
      "grad_norm": 0.40453842282295227,
      "learning_rate": 2.349574514920613e-06,
      "loss": 0.5257,
      "step": 50629
    },
    {
      "epoch": 1.5553098024759624,
      "grad_norm": 0.39187201857566833,
      "learning_rate": 2.349263303043745e-06,
      "loss": 0.4735,
      "step": 50630
    },
    {
      "epoch": 1.5553405216109115,
      "grad_norm": 0.4592593312263489,
      "learning_rate": 2.3489521090357093e-06,
      "loss": 0.5289,
      "step": 50631
    },
    {
      "epoch": 1.5553712407458606,
      "grad_norm": 0.4120655953884125,
      "learning_rate": 2.348640932897225e-06,
      "loss": 0.4902,
      "step": 50632
    },
    {
      "epoch": 1.5554019598808098,
      "grad_norm": 0.42169252038002014,
      "learning_rate": 2.348329774629029e-06,
      "loss": 0.4347,
      "step": 50633
    },
    {
      "epoch": 1.5554326790157589,
      "grad_norm": 0.431220680475235,
      "learning_rate": 2.3480186342318412e-06,
      "loss": 0.5062,
      "step": 50634
    },
    {
      "epoch": 1.555463398150708,
      "grad_norm": 0.4559897482395172,
      "learning_rate": 2.3477075117063897e-06,
      "loss": 0.5506,
      "step": 50635
    },
    {
      "epoch": 1.5554941172856571,
      "grad_norm": 0.40803560614585876,
      "learning_rate": 2.347396407053405e-06,
      "loss": 0.3997,
      "step": 50636
    },
    {
      "epoch": 1.5555248364206062,
      "grad_norm": 0.43079808354377747,
      "learning_rate": 2.3470853202736044e-06,
      "loss": 0.4322,
      "step": 50637
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.45623505115509033,
      "learning_rate": 2.346774251367727e-06,
      "loss": 0.4661,
      "step": 50638
    },
    {
      "epoch": 1.5555862746905047,
      "grad_norm": 0.41838163137435913,
      "learning_rate": 2.3464632003364896e-06,
      "loss": 0.4243,
      "step": 50639
    },
    {
      "epoch": 1.5556169938254538,
      "grad_norm": 0.4330369532108307,
      "learning_rate": 2.346152167180624e-06,
      "loss": 0.5178,
      "step": 50640
    },
    {
      "epoch": 1.5556477129604032,
      "grad_norm": 0.4530923366546631,
      "learning_rate": 2.345841151900853e-06,
      "loss": 0.479,
      "step": 50641
    },
    {
      "epoch": 1.5556784320953523,
      "grad_norm": 0.4367510974407196,
      "learning_rate": 2.3455301544979035e-06,
      "loss": 0.3925,
      "step": 50642
    },
    {
      "epoch": 1.5557091512303014,
      "grad_norm": 0.432999849319458,
      "learning_rate": 2.345219174972503e-06,
      "loss": 0.455,
      "step": 50643
    },
    {
      "epoch": 1.5557398703652505,
      "grad_norm": 0.411765992641449,
      "learning_rate": 2.3449082133253807e-06,
      "loss": 0.4686,
      "step": 50644
    },
    {
      "epoch": 1.5557705895001996,
      "grad_norm": 0.39544904232025146,
      "learning_rate": 2.344597269557257e-06,
      "loss": 0.3673,
      "step": 50645
    },
    {
      "epoch": 1.5558013086351488,
      "grad_norm": 0.4668910801410675,
      "learning_rate": 2.344286343668861e-06,
      "loss": 0.4865,
      "step": 50646
    },
    {
      "epoch": 1.5558320277700979,
      "grad_norm": 0.42259714007377625,
      "learning_rate": 2.343975435660919e-06,
      "loss": 0.4361,
      "step": 50647
    },
    {
      "epoch": 1.555862746905047,
      "grad_norm": 0.5375886559486389,
      "learning_rate": 2.34366454553416e-06,
      "loss": 0.4784,
      "step": 50648
    },
    {
      "epoch": 1.5558934660399963,
      "grad_norm": 0.41220423579216003,
      "learning_rate": 2.343353673289305e-06,
      "loss": 0.4589,
      "step": 50649
    },
    {
      "epoch": 1.5559241851749455,
      "grad_norm": 0.4449329078197479,
      "learning_rate": 2.3430428189270813e-06,
      "loss": 0.4052,
      "step": 50650
    },
    {
      "epoch": 1.5559549043098946,
      "grad_norm": 0.41762053966522217,
      "learning_rate": 2.3427319824482166e-06,
      "loss": 0.5343,
      "step": 50651
    },
    {
      "epoch": 1.555985623444844,
      "grad_norm": 0.536939263343811,
      "learning_rate": 2.342421163853438e-06,
      "loss": 0.4864,
      "step": 50652
    },
    {
      "epoch": 1.556016342579793,
      "grad_norm": 0.47570717334747314,
      "learning_rate": 2.342110363143467e-06,
      "loss": 0.4894,
      "step": 50653
    },
    {
      "epoch": 1.5560470617147422,
      "grad_norm": 0.47340404987335205,
      "learning_rate": 2.341799580319033e-06,
      "loss": 0.4695,
      "step": 50654
    },
    {
      "epoch": 1.5560777808496913,
      "grad_norm": 0.419622004032135,
      "learning_rate": 2.34148881538086e-06,
      "loss": 0.5551,
      "step": 50655
    },
    {
      "epoch": 1.5561084999846404,
      "grad_norm": 0.4279354214668274,
      "learning_rate": 2.3411780683296747e-06,
      "loss": 0.4359,
      "step": 50656
    },
    {
      "epoch": 1.5561392191195895,
      "grad_norm": 0.39995652437210083,
      "learning_rate": 2.340867339166206e-06,
      "loss": 0.5168,
      "step": 50657
    },
    {
      "epoch": 1.5561699382545386,
      "grad_norm": 0.4799981415271759,
      "learning_rate": 2.340556627891174e-06,
      "loss": 0.4613,
      "step": 50658
    },
    {
      "epoch": 1.5562006573894878,
      "grad_norm": 0.40229538083076477,
      "learning_rate": 2.3402459345053064e-06,
      "loss": 0.4742,
      "step": 50659
    },
    {
      "epoch": 1.556231376524437,
      "grad_norm": 0.47418108582496643,
      "learning_rate": 2.3399352590093296e-06,
      "loss": 0.5104,
      "step": 50660
    },
    {
      "epoch": 1.5562620956593862,
      "grad_norm": 0.43938517570495605,
      "learning_rate": 2.3396246014039714e-06,
      "loss": 0.4664,
      "step": 50661
    },
    {
      "epoch": 1.5562928147943353,
      "grad_norm": 0.42326828837394714,
      "learning_rate": 2.339313961689953e-06,
      "loss": 0.4339,
      "step": 50662
    },
    {
      "epoch": 1.5563235339292847,
      "grad_norm": 0.45266613364219666,
      "learning_rate": 2.3390033398680033e-06,
      "loss": 0.3997,
      "step": 50663
    },
    {
      "epoch": 1.5563542530642338,
      "grad_norm": 0.38088077306747437,
      "learning_rate": 2.338692735938842e-06,
      "loss": 0.4463,
      "step": 50664
    },
    {
      "epoch": 1.556384972199183,
      "grad_norm": 0.4394315183162689,
      "learning_rate": 2.3383821499032046e-06,
      "loss": 0.4342,
      "step": 50665
    },
    {
      "epoch": 1.556415691334132,
      "grad_norm": 0.42742720246315,
      "learning_rate": 2.3380715817618073e-06,
      "loss": 0.5203,
      "step": 50666
    },
    {
      "epoch": 1.5564464104690812,
      "grad_norm": 0.461130827665329,
      "learning_rate": 2.337761031515381e-06,
      "loss": 0.5048,
      "step": 50667
    },
    {
      "epoch": 1.5564771296040303,
      "grad_norm": 0.4458392560482025,
      "learning_rate": 2.3374504991646473e-06,
      "loss": 0.4799,
      "step": 50668
    },
    {
      "epoch": 1.5565078487389794,
      "grad_norm": 0.49616456031799316,
      "learning_rate": 2.3371399847103327e-06,
      "loss": 0.4811,
      "step": 50669
    },
    {
      "epoch": 1.5565385678739285,
      "grad_norm": 0.4007331430912018,
      "learning_rate": 2.3368294881531627e-06,
      "loss": 0.4686,
      "step": 50670
    },
    {
      "epoch": 1.5565692870088779,
      "grad_norm": 0.4221625030040741,
      "learning_rate": 2.336519009493866e-06,
      "loss": 0.4937,
      "step": 50671
    },
    {
      "epoch": 1.556600006143827,
      "grad_norm": 0.46042880415916443,
      "learning_rate": 2.336208548733161e-06,
      "loss": 0.551,
      "step": 50672
    },
    {
      "epoch": 1.556630725278776,
      "grad_norm": 0.43437328934669495,
      "learning_rate": 2.3358981058717733e-06,
      "loss": 0.4704,
      "step": 50673
    },
    {
      "epoch": 1.5566614444137254,
      "grad_norm": 0.426461398601532,
      "learning_rate": 2.335587680910437e-06,
      "loss": 0.4523,
      "step": 50674
    },
    {
      "epoch": 1.5566921635486746,
      "grad_norm": 0.4995656907558441,
      "learning_rate": 2.3352772738498675e-06,
      "loss": 0.442,
      "step": 50675
    },
    {
      "epoch": 1.5567228826836237,
      "grad_norm": 0.4750358462333679,
      "learning_rate": 2.334966884690797e-06,
      "loss": 0.4955,
      "step": 50676
    },
    {
      "epoch": 1.5567536018185728,
      "grad_norm": 0.4206114411354065,
      "learning_rate": 2.3346565134339426e-06,
      "loss": 0.4974,
      "step": 50677
    },
    {
      "epoch": 1.556784320953522,
      "grad_norm": 0.4370590150356293,
      "learning_rate": 2.3343461600800344e-06,
      "loss": 0.4735,
      "step": 50678
    },
    {
      "epoch": 1.556815040088471,
      "grad_norm": 0.38354313373565674,
      "learning_rate": 2.3340358246297956e-06,
      "loss": 0.445,
      "step": 50679
    },
    {
      "epoch": 1.5568457592234202,
      "grad_norm": 0.4120716154575348,
      "learning_rate": 2.333725507083955e-06,
      "loss": 0.3853,
      "step": 50680
    },
    {
      "epoch": 1.5568764783583693,
      "grad_norm": 0.43165719509124756,
      "learning_rate": 2.3334152074432292e-06,
      "loss": 0.5212,
      "step": 50681
    },
    {
      "epoch": 1.5569071974933186,
      "grad_norm": 0.4636821746826172,
      "learning_rate": 2.3331049257083492e-06,
      "loss": 0.4896,
      "step": 50682
    },
    {
      "epoch": 1.5569379166282677,
      "grad_norm": 0.43154481053352356,
      "learning_rate": 2.332794661880038e-06,
      "loss": 0.4513,
      "step": 50683
    },
    {
      "epoch": 1.5569686357632169,
      "grad_norm": 0.406637042760849,
      "learning_rate": 2.332484415959023e-06,
      "loss": 0.4306,
      "step": 50684
    },
    {
      "epoch": 1.5569993548981662,
      "grad_norm": 0.4237481653690338,
      "learning_rate": 2.3321741879460227e-06,
      "loss": 0.4293,
      "step": 50685
    },
    {
      "epoch": 1.5570300740331153,
      "grad_norm": 0.4266202747821808,
      "learning_rate": 2.3318639778417663e-06,
      "loss": 0.5406,
      "step": 50686
    },
    {
      "epoch": 1.5570607931680644,
      "grad_norm": 0.46058234572410583,
      "learning_rate": 2.3315537856469763e-06,
      "loss": 0.506,
      "step": 50687
    },
    {
      "epoch": 1.5570915123030136,
      "grad_norm": 0.43056103587150574,
      "learning_rate": 2.3312436113623803e-06,
      "loss": 0.4931,
      "step": 50688
    },
    {
      "epoch": 1.5571222314379627,
      "grad_norm": 0.45739269256591797,
      "learning_rate": 2.330933454988699e-06,
      "loss": 0.5133,
      "step": 50689
    },
    {
      "epoch": 1.5571529505729118,
      "grad_norm": 0.3901137709617615,
      "learning_rate": 2.3306233165266568e-06,
      "loss": 0.4418,
      "step": 50690
    },
    {
      "epoch": 1.557183669707861,
      "grad_norm": 0.4321649372577667,
      "learning_rate": 2.3303131959769797e-06,
      "loss": 0.4591,
      "step": 50691
    },
    {
      "epoch": 1.55721438884281,
      "grad_norm": 0.3952864706516266,
      "learning_rate": 2.3300030933403927e-06,
      "loss": 0.499,
      "step": 50692
    },
    {
      "epoch": 1.5572451079777594,
      "grad_norm": 0.4122132360935211,
      "learning_rate": 2.3296930086176216e-06,
      "loss": 0.4865,
      "step": 50693
    },
    {
      "epoch": 1.5572758271127085,
      "grad_norm": 0.3858349323272705,
      "learning_rate": 2.329382941809385e-06,
      "loss": 0.4811,
      "step": 50694
    },
    {
      "epoch": 1.5573065462476576,
      "grad_norm": 0.44446372985839844,
      "learning_rate": 2.3290728929164107e-06,
      "loss": 0.4761,
      "step": 50695
    },
    {
      "epoch": 1.557337265382607,
      "grad_norm": 0.4424700140953064,
      "learning_rate": 2.328762861939422e-06,
      "loss": 0.3702,
      "step": 50696
    },
    {
      "epoch": 1.557367984517556,
      "grad_norm": 0.44556939601898193,
      "learning_rate": 2.328452848879146e-06,
      "loss": 0.502,
      "step": 50697
    },
    {
      "epoch": 1.5573987036525052,
      "grad_norm": 0.3856055438518524,
      "learning_rate": 2.3281428537363017e-06,
      "loss": 0.5153,
      "step": 50698
    },
    {
      "epoch": 1.5574294227874543,
      "grad_norm": 0.423006534576416,
      "learning_rate": 2.3278328765116187e-06,
      "loss": 0.4334,
      "step": 50699
    },
    {
      "epoch": 1.5574601419224035,
      "grad_norm": 0.42195984721183777,
      "learning_rate": 2.327522917205811e-06,
      "loss": 0.5083,
      "step": 50700
    },
    {
      "epoch": 1.5574908610573526,
      "grad_norm": 0.43519940972328186,
      "learning_rate": 2.327212975819616e-06,
      "loss": 0.5168,
      "step": 50701
    },
    {
      "epoch": 1.5575215801923017,
      "grad_norm": 0.43581315875053406,
      "learning_rate": 2.3269030523537482e-06,
      "loss": 0.4914,
      "step": 50702
    },
    {
      "epoch": 1.5575522993272508,
      "grad_norm": 0.4492044150829315,
      "learning_rate": 2.3265931468089366e-06,
      "loss": 0.373,
      "step": 50703
    },
    {
      "epoch": 1.5575830184622002,
      "grad_norm": 0.397368848323822,
      "learning_rate": 2.326283259185901e-06,
      "loss": 0.4544,
      "step": 50704
    },
    {
      "epoch": 1.5576137375971493,
      "grad_norm": 0.41529783606529236,
      "learning_rate": 2.3259733894853653e-06,
      "loss": 0.4543,
      "step": 50705
    },
    {
      "epoch": 1.5576444567320984,
      "grad_norm": 0.41162532567977905,
      "learning_rate": 2.325663537708055e-06,
      "loss": 0.4376,
      "step": 50706
    },
    {
      "epoch": 1.5576751758670477,
      "grad_norm": 0.47075706720352173,
      "learning_rate": 2.3253537038546957e-06,
      "loss": 0.4178,
      "step": 50707
    },
    {
      "epoch": 1.5577058950019969,
      "grad_norm": 0.435523122549057,
      "learning_rate": 2.325043887926007e-06,
      "loss": 0.4309,
      "step": 50708
    },
    {
      "epoch": 1.557736614136946,
      "grad_norm": 1.0455915927886963,
      "learning_rate": 2.3247340899227143e-06,
      "loss": 0.3905,
      "step": 50709
    },
    {
      "epoch": 1.557767333271895,
      "grad_norm": 0.4926415681838989,
      "learning_rate": 2.324424309845541e-06,
      "loss": 0.3747,
      "step": 50710
    },
    {
      "epoch": 1.5577980524068442,
      "grad_norm": 0.4422512948513031,
      "learning_rate": 2.324114547695211e-06,
      "loss": 0.4888,
      "step": 50711
    },
    {
      "epoch": 1.5578287715417933,
      "grad_norm": 0.4674685597419739,
      "learning_rate": 2.3238048034724503e-06,
      "loss": 0.5304,
      "step": 50712
    },
    {
      "epoch": 1.5578594906767425,
      "grad_norm": 0.4371359944343567,
      "learning_rate": 2.323495077177976e-06,
      "loss": 0.4021,
      "step": 50713
    },
    {
      "epoch": 1.5578902098116916,
      "grad_norm": 0.4264141917228699,
      "learning_rate": 2.3231853688125163e-06,
      "loss": 0.4636,
      "step": 50714
    },
    {
      "epoch": 1.557920928946641,
      "grad_norm": 0.4417020082473755,
      "learning_rate": 2.3228756783767923e-06,
      "loss": 0.5066,
      "step": 50715
    },
    {
      "epoch": 1.55795164808159,
      "grad_norm": 0.452830970287323,
      "learning_rate": 2.3225660058715315e-06,
      "loss": 0.5018,
      "step": 50716
    },
    {
      "epoch": 1.5579823672165392,
      "grad_norm": 0.4686867892742157,
      "learning_rate": 2.3222563512974504e-06,
      "loss": 0.3842,
      "step": 50717
    },
    {
      "epoch": 1.5580130863514885,
      "grad_norm": 0.44536060094833374,
      "learning_rate": 2.3219467146552765e-06,
      "loss": 0.4565,
      "step": 50718
    },
    {
      "epoch": 1.5580438054864376,
      "grad_norm": 0.46701061725616455,
      "learning_rate": 2.3216370959457325e-06,
      "loss": 0.4223,
      "step": 50719
    },
    {
      "epoch": 1.5580745246213867,
      "grad_norm": 0.44278594851493835,
      "learning_rate": 2.3213274951695442e-06,
      "loss": 0.5128,
      "step": 50720
    },
    {
      "epoch": 1.5581052437563359,
      "grad_norm": 0.4484312832355499,
      "learning_rate": 2.321017912327429e-06,
      "loss": 0.4594,
      "step": 50721
    },
    {
      "epoch": 1.558135962891285,
      "grad_norm": 0.4025433659553528,
      "learning_rate": 2.320708347420112e-06,
      "loss": 0.4524,
      "step": 50722
    },
    {
      "epoch": 1.558166682026234,
      "grad_norm": 0.4234791100025177,
      "learning_rate": 2.320398800448318e-06,
      "loss": 0.4947,
      "step": 50723
    },
    {
      "epoch": 1.5581974011611832,
      "grad_norm": 0.4503440260887146,
      "learning_rate": 2.3200892714127708e-06,
      "loss": 0.5299,
      "step": 50724
    },
    {
      "epoch": 1.5582281202961323,
      "grad_norm": 0.43046584725379944,
      "learning_rate": 2.319779760314189e-06,
      "loss": 0.5093,
      "step": 50725
    },
    {
      "epoch": 1.5582588394310815,
      "grad_norm": 0.46775615215301514,
      "learning_rate": 2.319470267153301e-06,
      "loss": 0.4104,
      "step": 50726
    },
    {
      "epoch": 1.5582895585660308,
      "grad_norm": 0.4797087013721466,
      "learning_rate": 2.3191607919308214e-06,
      "loss": 0.4582,
      "step": 50727
    },
    {
      "epoch": 1.55832027770098,
      "grad_norm": 0.4280878007411957,
      "learning_rate": 2.3188513346474794e-06,
      "loss": 0.5343,
      "step": 50728
    },
    {
      "epoch": 1.5583509968359293,
      "grad_norm": 0.4470727741718292,
      "learning_rate": 2.3185418953040005e-06,
      "loss": 0.5513,
      "step": 50729
    },
    {
      "epoch": 1.5583817159708784,
      "grad_norm": 0.42556968331336975,
      "learning_rate": 2.318232473901101e-06,
      "loss": 0.4846,
      "step": 50730
    },
    {
      "epoch": 1.5584124351058275,
      "grad_norm": 0.45486152172088623,
      "learning_rate": 2.3179230704395084e-06,
      "loss": 0.4993,
      "step": 50731
    },
    {
      "epoch": 1.5584431542407766,
      "grad_norm": 0.4340360760688782,
      "learning_rate": 2.3176136849199372e-06,
      "loss": 0.4688,
      "step": 50732
    },
    {
      "epoch": 1.5584738733757257,
      "grad_norm": 0.44728076457977295,
      "learning_rate": 2.317304317343121e-06,
      "loss": 0.526,
      "step": 50733
    },
    {
      "epoch": 1.5585045925106749,
      "grad_norm": 0.4431842565536499,
      "learning_rate": 2.3169949677097747e-06,
      "loss": 0.4364,
      "step": 50734
    },
    {
      "epoch": 1.558535311645624,
      "grad_norm": 0.42261356115341187,
      "learning_rate": 2.3166856360206267e-06,
      "loss": 0.4497,
      "step": 50735
    },
    {
      "epoch": 1.558566030780573,
      "grad_norm": 0.4092831015586853,
      "learning_rate": 2.31637632227639e-06,
      "loss": 0.4607,
      "step": 50736
    },
    {
      "epoch": 1.5585967499155222,
      "grad_norm": 0.5160731077194214,
      "learning_rate": 2.3160670264777983e-06,
      "loss": 0.5354,
      "step": 50737
    },
    {
      "epoch": 1.5586274690504716,
      "grad_norm": 0.5584772229194641,
      "learning_rate": 2.3157577486255656e-06,
      "loss": 0.4406,
      "step": 50738
    },
    {
      "epoch": 1.5586581881854207,
      "grad_norm": 0.4288819432258606,
      "learning_rate": 2.315448488720421e-06,
      "loss": 0.4562,
      "step": 50739
    },
    {
      "epoch": 1.55868890732037,
      "grad_norm": 0.3902001678943634,
      "learning_rate": 2.3151392467630796e-06,
      "loss": 0.4774,
      "step": 50740
    },
    {
      "epoch": 1.5587196264553191,
      "grad_norm": 0.42120563983917236,
      "learning_rate": 2.3148300227542673e-06,
      "loss": 0.4498,
      "step": 50741
    },
    {
      "epoch": 1.5587503455902683,
      "grad_norm": 0.44886523485183716,
      "learning_rate": 2.3145208166947074e-06,
      "loss": 0.5797,
      "step": 50742
    },
    {
      "epoch": 1.5587810647252174,
      "grad_norm": 0.45607951283454895,
      "learning_rate": 2.3142116285851224e-06,
      "loss": 0.4248,
      "step": 50743
    },
    {
      "epoch": 1.5588117838601665,
      "grad_norm": 0.42188119888305664,
      "learning_rate": 2.3139024584262306e-06,
      "loss": 0.4526,
      "step": 50744
    },
    {
      "epoch": 1.5588425029951156,
      "grad_norm": 0.45170167088508606,
      "learning_rate": 2.3135933062187567e-06,
      "loss": 0.4454,
      "step": 50745
    },
    {
      "epoch": 1.5588732221300647,
      "grad_norm": 0.4185442626476288,
      "learning_rate": 2.3132841719634214e-06,
      "loss": 0.4537,
      "step": 50746
    },
    {
      "epoch": 1.5589039412650139,
      "grad_norm": 0.44688186049461365,
      "learning_rate": 2.3129750556609487e-06,
      "loss": 0.4296,
      "step": 50747
    },
    {
      "epoch": 1.558934660399963,
      "grad_norm": 0.4337398111820221,
      "learning_rate": 2.3126659573120613e-06,
      "loss": 0.5018,
      "step": 50748
    },
    {
      "epoch": 1.5589653795349123,
      "grad_norm": 0.41803497076034546,
      "learning_rate": 2.3123568769174776e-06,
      "loss": 0.4614,
      "step": 50749
    },
    {
      "epoch": 1.5589960986698614,
      "grad_norm": 0.42148926854133606,
      "learning_rate": 2.3120478144779215e-06,
      "loss": 0.4643,
      "step": 50750
    },
    {
      "epoch": 1.5590268178048108,
      "grad_norm": 0.4392493665218353,
      "learning_rate": 2.311738769994114e-06,
      "loss": 0.4597,
      "step": 50751
    },
    {
      "epoch": 1.55905753693976,
      "grad_norm": 0.40268251299858093,
      "learning_rate": 2.311429743466781e-06,
      "loss": 0.4659,
      "step": 50752
    },
    {
      "epoch": 1.559088256074709,
      "grad_norm": 0.4016946256160736,
      "learning_rate": 2.3111207348966367e-06,
      "loss": 0.482,
      "step": 50753
    },
    {
      "epoch": 1.5591189752096581,
      "grad_norm": 0.47216933965682983,
      "learning_rate": 2.310811744284408e-06,
      "loss": 0.449,
      "step": 50754
    },
    {
      "epoch": 1.5591496943446073,
      "grad_norm": 0.4247852861881256,
      "learning_rate": 2.310502771630816e-06,
      "loss": 0.5093,
      "step": 50755
    },
    {
      "epoch": 1.5591804134795564,
      "grad_norm": 0.43215906620025635,
      "learning_rate": 2.3101938169365833e-06,
      "loss": 0.4381,
      "step": 50756
    },
    {
      "epoch": 1.5592111326145055,
      "grad_norm": 0.44709521532058716,
      "learning_rate": 2.3098848802024276e-06,
      "loss": 0.5045,
      "step": 50757
    },
    {
      "epoch": 1.5592418517494546,
      "grad_norm": 0.40897223353385925,
      "learning_rate": 2.3095759614290737e-06,
      "loss": 0.4831,
      "step": 50758
    },
    {
      "epoch": 1.5592725708844037,
      "grad_norm": 0.4277857840061188,
      "learning_rate": 2.3092670606172405e-06,
      "loss": 0.3917,
      "step": 50759
    },
    {
      "epoch": 1.559303290019353,
      "grad_norm": 0.6357498168945312,
      "learning_rate": 2.3089581777676563e-06,
      "loss": 0.4576,
      "step": 50760
    },
    {
      "epoch": 1.5593340091543022,
      "grad_norm": 0.44054388999938965,
      "learning_rate": 2.308649312881033e-06,
      "loss": 0.425,
      "step": 50761
    },
    {
      "epoch": 1.5593647282892513,
      "grad_norm": 0.45158618688583374,
      "learning_rate": 2.308340465958099e-06,
      "loss": 0.4676,
      "step": 50762
    },
    {
      "epoch": 1.5593954474242007,
      "grad_norm": 0.41864752769470215,
      "learning_rate": 2.308031636999568e-06,
      "loss": 0.4524,
      "step": 50763
    },
    {
      "epoch": 1.5594261665591498,
      "grad_norm": 0.40448305010795593,
      "learning_rate": 2.307722826006169e-06,
      "loss": 0.3969,
      "step": 50764
    },
    {
      "epoch": 1.559456885694099,
      "grad_norm": 0.3872217833995819,
      "learning_rate": 2.307414032978623e-06,
      "loss": 0.4125,
      "step": 50765
    },
    {
      "epoch": 1.559487604829048,
      "grad_norm": 0.42857760190963745,
      "learning_rate": 2.307105257917647e-06,
      "loss": 0.4246,
      "step": 50766
    },
    {
      "epoch": 1.5595183239639971,
      "grad_norm": 0.5077848434448242,
      "learning_rate": 2.3067965008239666e-06,
      "loss": 0.4571,
      "step": 50767
    },
    {
      "epoch": 1.5595490430989463,
      "grad_norm": 0.42257770895957947,
      "learning_rate": 2.3064877616982938e-06,
      "loss": 0.4245,
      "step": 50768
    },
    {
      "epoch": 1.5595797622338954,
      "grad_norm": 0.41439175605773926,
      "learning_rate": 2.306179040541362e-06,
      "loss": 0.5111,
      "step": 50769
    },
    {
      "epoch": 1.5596104813688445,
      "grad_norm": 0.441622793674469,
      "learning_rate": 2.3058703373538837e-06,
      "loss": 0.4673,
      "step": 50770
    },
    {
      "epoch": 1.5596412005037938,
      "grad_norm": 0.4859742820262909,
      "learning_rate": 2.305561652136585e-06,
      "loss": 0.3995,
      "step": 50771
    },
    {
      "epoch": 1.559671919638743,
      "grad_norm": 0.46960946917533875,
      "learning_rate": 2.305252984890183e-06,
      "loss": 0.3591,
      "step": 50772
    },
    {
      "epoch": 1.559702638773692,
      "grad_norm": 0.45764946937561035,
      "learning_rate": 2.304944335615399e-06,
      "loss": 0.4827,
      "step": 50773
    },
    {
      "epoch": 1.5597333579086414,
      "grad_norm": 0.4146001636981964,
      "learning_rate": 2.3046357043129552e-06,
      "loss": 0.4543,
      "step": 50774
    },
    {
      "epoch": 1.5597640770435905,
      "grad_norm": 0.42351818084716797,
      "learning_rate": 2.3043270909835746e-06,
      "loss": 0.4991,
      "step": 50775
    },
    {
      "epoch": 1.5597947961785397,
      "grad_norm": 0.447873055934906,
      "learning_rate": 2.304018495627972e-06,
      "loss": 0.4942,
      "step": 50776
    },
    {
      "epoch": 1.5598255153134888,
      "grad_norm": 0.7286558747291565,
      "learning_rate": 2.3037099182468735e-06,
      "loss": 0.5785,
      "step": 50777
    },
    {
      "epoch": 1.559856234448438,
      "grad_norm": 0.40684154629707336,
      "learning_rate": 2.3034013588409965e-06,
      "loss": 0.4377,
      "step": 50778
    },
    {
      "epoch": 1.559886953583387,
      "grad_norm": 0.38494616746902466,
      "learning_rate": 2.303092817411067e-06,
      "loss": 0.4443,
      "step": 50779
    },
    {
      "epoch": 1.5599176727183361,
      "grad_norm": 0.4290657341480255,
      "learning_rate": 2.302784293957798e-06,
      "loss": 0.4416,
      "step": 50780
    },
    {
      "epoch": 1.5599483918532853,
      "grad_norm": 0.6952120065689087,
      "learning_rate": 2.302475788481915e-06,
      "loss": 0.4532,
      "step": 50781
    },
    {
      "epoch": 1.5599791109882346,
      "grad_norm": 0.5663222074508667,
      "learning_rate": 2.302167300984136e-06,
      "loss": 0.4654,
      "step": 50782
    },
    {
      "epoch": 1.5600098301231837,
      "grad_norm": 0.39410874247550964,
      "learning_rate": 2.3018588314651835e-06,
      "loss": 0.3902,
      "step": 50783
    },
    {
      "epoch": 1.5600405492581328,
      "grad_norm": 0.39575812220573425,
      "learning_rate": 2.301550379925781e-06,
      "loss": 0.4259,
      "step": 50784
    },
    {
      "epoch": 1.5600712683930822,
      "grad_norm": 0.402742475271225,
      "learning_rate": 2.301241946366641e-06,
      "loss": 0.4627,
      "step": 50785
    },
    {
      "epoch": 1.5601019875280313,
      "grad_norm": 0.41043493151664734,
      "learning_rate": 2.3009335307884896e-06,
      "loss": 0.4001,
      "step": 50786
    },
    {
      "epoch": 1.5601327066629804,
      "grad_norm": 0.40170416235923767,
      "learning_rate": 2.300625133192045e-06,
      "loss": 0.4888,
      "step": 50787
    },
    {
      "epoch": 1.5601634257979295,
      "grad_norm": 0.41700437664985657,
      "learning_rate": 2.30031675357803e-06,
      "loss": 0.4739,
      "step": 50788
    },
    {
      "epoch": 1.5601941449328787,
      "grad_norm": 0.4607846736907959,
      "learning_rate": 2.3000083919471603e-06,
      "loss": 0.4661,
      "step": 50789
    },
    {
      "epoch": 1.5602248640678278,
      "grad_norm": 0.4135545790195465,
      "learning_rate": 2.2997000483001596e-06,
      "loss": 0.3876,
      "step": 50790
    },
    {
      "epoch": 1.560255583202777,
      "grad_norm": 0.4439569413661957,
      "learning_rate": 2.299391722637747e-06,
      "loss": 0.4516,
      "step": 50791
    },
    {
      "epoch": 1.560286302337726,
      "grad_norm": 0.427691787481308,
      "learning_rate": 2.2990834149606454e-06,
      "loss": 0.5119,
      "step": 50792
    },
    {
      "epoch": 1.5603170214726754,
      "grad_norm": 0.4045344591140747,
      "learning_rate": 2.29877512526957e-06,
      "loss": 0.4649,
      "step": 50793
    },
    {
      "epoch": 1.5603477406076245,
      "grad_norm": 0.42382681369781494,
      "learning_rate": 2.2984668535652467e-06,
      "loss": 0.4946,
      "step": 50794
    },
    {
      "epoch": 1.5603784597425736,
      "grad_norm": 0.4040963649749756,
      "learning_rate": 2.2981585998483845e-06,
      "loss": 0.44,
      "step": 50795
    },
    {
      "epoch": 1.560409178877523,
      "grad_norm": 0.44767096638679504,
      "learning_rate": 2.297850364119717e-06,
      "loss": 0.5169,
      "step": 50796
    },
    {
      "epoch": 1.560439898012472,
      "grad_norm": 0.40459826588630676,
      "learning_rate": 2.297542146379955e-06,
      "loss": 0.468,
      "step": 50797
    },
    {
      "epoch": 1.5604706171474212,
      "grad_norm": 0.45016565918922424,
      "learning_rate": 2.2972339466298244e-06,
      "loss": 0.5576,
      "step": 50798
    },
    {
      "epoch": 1.5605013362823703,
      "grad_norm": 0.44910702109336853,
      "learning_rate": 2.2969257648700374e-06,
      "loss": 0.5152,
      "step": 50799
    },
    {
      "epoch": 1.5605320554173194,
      "grad_norm": 0.45065057277679443,
      "learning_rate": 2.2966176011013187e-06,
      "loss": 0.4933,
      "step": 50800
    },
    {
      "epoch": 1.5605627745522686,
      "grad_norm": 0.4126696288585663,
      "learning_rate": 2.2963094553243916e-06,
      "loss": 0.521,
      "step": 50801
    },
    {
      "epoch": 1.5605934936872177,
      "grad_norm": 0.5199311375617981,
      "learning_rate": 2.2960013275399695e-06,
      "loss": 0.4388,
      "step": 50802
    },
    {
      "epoch": 1.5606242128221668,
      "grad_norm": 0.4122191071510315,
      "learning_rate": 2.295693217748777e-06,
      "loss": 0.3939,
      "step": 50803
    },
    {
      "epoch": 1.5606549319571161,
      "grad_norm": 0.41007107496261597,
      "learning_rate": 2.295385125951525e-06,
      "loss": 0.5132,
      "step": 50804
    },
    {
      "epoch": 1.5606856510920653,
      "grad_norm": 0.4208325743675232,
      "learning_rate": 2.295077052148944e-06,
      "loss": 0.4689,
      "step": 50805
    },
    {
      "epoch": 1.5607163702270144,
      "grad_norm": 0.4655758738517761,
      "learning_rate": 2.2947689963417463e-06,
      "loss": 0.4363,
      "step": 50806
    },
    {
      "epoch": 1.5607470893619637,
      "grad_norm": 0.40115392208099365,
      "learning_rate": 2.2944609585306575e-06,
      "loss": 0.4236,
      "step": 50807
    },
    {
      "epoch": 1.5607778084969128,
      "grad_norm": 0.4291549623012543,
      "learning_rate": 2.2941529387163897e-06,
      "loss": 0.4691,
      "step": 50808
    },
    {
      "epoch": 1.560808527631862,
      "grad_norm": 0.4625619351863861,
      "learning_rate": 2.2938449368996662e-06,
      "loss": 0.4962,
      "step": 50809
    },
    {
      "epoch": 1.560839246766811,
      "grad_norm": 0.46485772728919983,
      "learning_rate": 2.2935369530812057e-06,
      "loss": 0.4428,
      "step": 50810
    },
    {
      "epoch": 1.5608699659017602,
      "grad_norm": 0.43222758173942566,
      "learning_rate": 2.2932289872617308e-06,
      "loss": 0.3877,
      "step": 50811
    },
    {
      "epoch": 1.5609006850367093,
      "grad_norm": 0.43040820956230164,
      "learning_rate": 2.292921039441954e-06,
      "loss": 0.5516,
      "step": 50812
    },
    {
      "epoch": 1.5609314041716584,
      "grad_norm": 0.465221643447876,
      "learning_rate": 2.2926131096226e-06,
      "loss": 0.4767,
      "step": 50813
    },
    {
      "epoch": 1.5609621233066076,
      "grad_norm": 0.44073688983917236,
      "learning_rate": 2.2923051978043854e-06,
      "loss": 0.4945,
      "step": 50814
    },
    {
      "epoch": 1.560992842441557,
      "grad_norm": 0.41306695342063904,
      "learning_rate": 2.2919973039880338e-06,
      "loss": 0.4584,
      "step": 50815
    },
    {
      "epoch": 1.561023561576506,
      "grad_norm": 0.4074138402938843,
      "learning_rate": 2.2916894281742573e-06,
      "loss": 0.4457,
      "step": 50816
    },
    {
      "epoch": 1.5610542807114551,
      "grad_norm": 0.4004680812358856,
      "learning_rate": 2.29138157036378e-06,
      "loss": 0.513,
      "step": 50817
    },
    {
      "epoch": 1.5610849998464045,
      "grad_norm": 0.4274362325668335,
      "learning_rate": 2.2910737305573174e-06,
      "loss": 0.4157,
      "step": 50818
    },
    {
      "epoch": 1.5611157189813536,
      "grad_norm": 0.42527616024017334,
      "learning_rate": 2.2907659087555912e-06,
      "loss": 0.4939,
      "step": 50819
    },
    {
      "epoch": 1.5611464381163027,
      "grad_norm": 0.4353417158126831,
      "learning_rate": 2.2904581049593232e-06,
      "loss": 0.5338,
      "step": 50820
    },
    {
      "epoch": 1.5611771572512518,
      "grad_norm": 0.39396896958351135,
      "learning_rate": 2.2901503191692253e-06,
      "loss": 0.4783,
      "step": 50821
    },
    {
      "epoch": 1.561207876386201,
      "grad_norm": 0.41419705748558044,
      "learning_rate": 2.28984255138602e-06,
      "loss": 0.4101,
      "step": 50822
    },
    {
      "epoch": 1.56123859552115,
      "grad_norm": 0.42604732513427734,
      "learning_rate": 2.289534801610426e-06,
      "loss": 0.4624,
      "step": 50823
    },
    {
      "epoch": 1.5612693146560992,
      "grad_norm": 0.3885853588581085,
      "learning_rate": 2.289227069843164e-06,
      "loss": 0.4736,
      "step": 50824
    },
    {
      "epoch": 1.5613000337910483,
      "grad_norm": 0.4036790430545807,
      "learning_rate": 2.288919356084948e-06,
      "loss": 0.4188,
      "step": 50825
    },
    {
      "epoch": 1.5613307529259977,
      "grad_norm": 0.4069156050682068,
      "learning_rate": 2.2886116603364994e-06,
      "loss": 0.3917,
      "step": 50826
    },
    {
      "epoch": 1.5613614720609468,
      "grad_norm": 0.6175665855407715,
      "learning_rate": 2.2883039825985376e-06,
      "loss": 0.4636,
      "step": 50827
    },
    {
      "epoch": 1.561392191195896,
      "grad_norm": 0.45272985100746155,
      "learning_rate": 2.2879963228717828e-06,
      "loss": 0.4508,
      "step": 50828
    },
    {
      "epoch": 1.5614229103308452,
      "grad_norm": 0.49765831232070923,
      "learning_rate": 2.2876886811569476e-06,
      "loss": 0.4585,
      "step": 50829
    },
    {
      "epoch": 1.5614536294657944,
      "grad_norm": 0.46770262718200684,
      "learning_rate": 2.2873810574547586e-06,
      "loss": 0.4078,
      "step": 50830
    },
    {
      "epoch": 1.5614843486007435,
      "grad_norm": 0.41930705308914185,
      "learning_rate": 2.2870734517659232e-06,
      "loss": 0.4206,
      "step": 50831
    },
    {
      "epoch": 1.5615150677356926,
      "grad_norm": 0.43861863017082214,
      "learning_rate": 2.2867658640911718e-06,
      "loss": 0.4799,
      "step": 50832
    },
    {
      "epoch": 1.5615457868706417,
      "grad_norm": 0.4645155072212219,
      "learning_rate": 2.2864582944312153e-06,
      "loss": 0.466,
      "step": 50833
    },
    {
      "epoch": 1.5615765060055908,
      "grad_norm": 0.4214036166667938,
      "learning_rate": 2.286150742786776e-06,
      "loss": 0.4741,
      "step": 50834
    },
    {
      "epoch": 1.56160722514054,
      "grad_norm": 0.42936375737190247,
      "learning_rate": 2.285843209158568e-06,
      "loss": 0.4005,
      "step": 50835
    },
    {
      "epoch": 1.561637944275489,
      "grad_norm": 0.4219055771827698,
      "learning_rate": 2.2855356935473092e-06,
      "loss": 0.4099,
      "step": 50836
    },
    {
      "epoch": 1.5616686634104382,
      "grad_norm": 0.4108732342720032,
      "learning_rate": 2.285228195953726e-06,
      "loss": 0.4698,
      "step": 50837
    },
    {
      "epoch": 1.5616993825453875,
      "grad_norm": 0.553929328918457,
      "learning_rate": 2.2849207163785294e-06,
      "loss": 0.4871,
      "step": 50838
    },
    {
      "epoch": 1.5617301016803367,
      "grad_norm": 0.44123512506484985,
      "learning_rate": 2.2846132548224407e-06,
      "loss": 0.4947,
      "step": 50839
    },
    {
      "epoch": 1.561760820815286,
      "grad_norm": 0.4157233238220215,
      "learning_rate": 2.2843058112861717e-06,
      "loss": 0.4744,
      "step": 50840
    },
    {
      "epoch": 1.5617915399502351,
      "grad_norm": 0.40829068422317505,
      "learning_rate": 2.2839983857704506e-06,
      "loss": 0.5249,
      "step": 50841
    },
    {
      "epoch": 1.5618222590851842,
      "grad_norm": 0.42059454321861267,
      "learning_rate": 2.2836909782759874e-06,
      "loss": 0.4438,
      "step": 50842
    },
    {
      "epoch": 1.5618529782201334,
      "grad_norm": 0.42313483357429504,
      "learning_rate": 2.2833835888035062e-06,
      "loss": 0.452,
      "step": 50843
    },
    {
      "epoch": 1.5618836973550825,
      "grad_norm": 0.4128258228302002,
      "learning_rate": 2.283076217353718e-06,
      "loss": 0.4675,
      "step": 50844
    },
    {
      "epoch": 1.5619144164900316,
      "grad_norm": 0.405265748500824,
      "learning_rate": 2.2827688639273437e-06,
      "loss": 0.4539,
      "step": 50845
    },
    {
      "epoch": 1.5619451356249807,
      "grad_norm": 0.4717211425304413,
      "learning_rate": 2.2824615285251028e-06,
      "loss": 0.4853,
      "step": 50846
    },
    {
      "epoch": 1.5619758547599298,
      "grad_norm": 0.3864704370498657,
      "learning_rate": 2.2821542111477145e-06,
      "loss": 0.4143,
      "step": 50847
    },
    {
      "epoch": 1.562006573894879,
      "grad_norm": 0.5203448534011841,
      "learning_rate": 2.281846911795892e-06,
      "loss": 0.4037,
      "step": 50848
    },
    {
      "epoch": 1.5620372930298283,
      "grad_norm": 0.4794977605342865,
      "learning_rate": 2.281539630470354e-06,
      "loss": 0.3847,
      "step": 50849
    },
    {
      "epoch": 1.5620680121647774,
      "grad_norm": 0.4381263554096222,
      "learning_rate": 2.2812323671718194e-06,
      "loss": 0.4601,
      "step": 50850
    },
    {
      "epoch": 1.5620987312997268,
      "grad_norm": 0.43740400671958923,
      "learning_rate": 2.280925121901009e-06,
      "loss": 0.5065,
      "step": 50851
    },
    {
      "epoch": 1.5621294504346759,
      "grad_norm": 0.42847922444343567,
      "learning_rate": 2.280617894658633e-06,
      "loss": 0.3855,
      "step": 50852
    },
    {
      "epoch": 1.562160169569625,
      "grad_norm": 0.4334447979927063,
      "learning_rate": 2.2803106854454137e-06,
      "loss": 0.4397,
      "step": 50853
    },
    {
      "epoch": 1.5621908887045741,
      "grad_norm": 0.39322274923324585,
      "learning_rate": 2.2800034942620686e-06,
      "loss": 0.5023,
      "step": 50854
    },
    {
      "epoch": 1.5622216078395232,
      "grad_norm": 0.46601441502571106,
      "learning_rate": 2.279696321109314e-06,
      "loss": 0.4497,
      "step": 50855
    },
    {
      "epoch": 1.5622523269744724,
      "grad_norm": 0.4114844799041748,
      "learning_rate": 2.279389165987871e-06,
      "loss": 0.4448,
      "step": 50856
    },
    {
      "epoch": 1.5622830461094215,
      "grad_norm": 0.4324246942996979,
      "learning_rate": 2.2790820288984503e-06,
      "loss": 0.4957,
      "step": 50857
    },
    {
      "epoch": 1.5623137652443706,
      "grad_norm": 0.4275398254394531,
      "learning_rate": 2.2787749098417733e-06,
      "loss": 0.4604,
      "step": 50858
    },
    {
      "epoch": 1.5623444843793197,
      "grad_norm": 0.4302772879600525,
      "learning_rate": 2.2784678088185565e-06,
      "loss": 0.434,
      "step": 50859
    },
    {
      "epoch": 1.562375203514269,
      "grad_norm": 0.44464224576950073,
      "learning_rate": 2.2781607258295203e-06,
      "loss": 0.4121,
      "step": 50860
    },
    {
      "epoch": 1.5624059226492182,
      "grad_norm": 0.44775304198265076,
      "learning_rate": 2.2778536608753766e-06,
      "loss": 0.5092,
      "step": 50861
    },
    {
      "epoch": 1.5624366417841675,
      "grad_norm": 0.4408617317676544,
      "learning_rate": 2.2775466139568438e-06,
      "loss": 0.3892,
      "step": 50862
    },
    {
      "epoch": 1.5624673609191166,
      "grad_norm": 0.4120151996612549,
      "learning_rate": 2.277239585074641e-06,
      "loss": 0.415,
      "step": 50863
    },
    {
      "epoch": 1.5624980800540658,
      "grad_norm": 0.4304625689983368,
      "learning_rate": 2.2769325742294866e-06,
      "loss": 0.4261,
      "step": 50864
    },
    {
      "epoch": 1.5625287991890149,
      "grad_norm": 0.39552703499794006,
      "learning_rate": 2.2766255814220938e-06,
      "loss": 0.438,
      "step": 50865
    },
    {
      "epoch": 1.562559518323964,
      "grad_norm": 0.443082720041275,
      "learning_rate": 2.276318606653184e-06,
      "loss": 0.5227,
      "step": 50866
    },
    {
      "epoch": 1.5625902374589131,
      "grad_norm": 0.46602314710617065,
      "learning_rate": 2.276011649923465e-06,
      "loss": 0.4513,
      "step": 50867
    },
    {
      "epoch": 1.5626209565938622,
      "grad_norm": 0.4486866593360901,
      "learning_rate": 2.275704711233667e-06,
      "loss": 0.4676,
      "step": 50868
    },
    {
      "epoch": 1.5626516757288114,
      "grad_norm": 0.4290790557861328,
      "learning_rate": 2.275397790584497e-06,
      "loss": 0.3757,
      "step": 50869
    },
    {
      "epoch": 1.5626823948637605,
      "grad_norm": 0.405718058347702,
      "learning_rate": 2.2750908879766774e-06,
      "loss": 0.4756,
      "step": 50870
    },
    {
      "epoch": 1.5627131139987098,
      "grad_norm": 0.4219682514667511,
      "learning_rate": 2.27478400341092e-06,
      "loss": 0.5232,
      "step": 50871
    },
    {
      "epoch": 1.562743833133659,
      "grad_norm": 0.42058631777763367,
      "learning_rate": 2.274477136887944e-06,
      "loss": 0.4425,
      "step": 50872
    },
    {
      "epoch": 1.562774552268608,
      "grad_norm": 0.4286111295223236,
      "learning_rate": 2.274170288408466e-06,
      "loss": 0.4626,
      "step": 50873
    },
    {
      "epoch": 1.5628052714035574,
      "grad_norm": 0.4193636178970337,
      "learning_rate": 2.2738634579732034e-06,
      "loss": 0.4712,
      "step": 50874
    },
    {
      "epoch": 1.5628359905385065,
      "grad_norm": 0.42259642481803894,
      "learning_rate": 2.2735566455828737e-06,
      "loss": 0.5166,
      "step": 50875
    },
    {
      "epoch": 1.5628667096734556,
      "grad_norm": 0.485798716545105,
      "learning_rate": 2.2732498512381905e-06,
      "loss": 0.4845,
      "step": 50876
    },
    {
      "epoch": 1.5628974288084048,
      "grad_norm": 0.41751500964164734,
      "learning_rate": 2.2729430749398716e-06,
      "loss": 0.4935,
      "step": 50877
    },
    {
      "epoch": 1.5629281479433539,
      "grad_norm": 0.495291531085968,
      "learning_rate": 2.2726363166886345e-06,
      "loss": 0.3862,
      "step": 50878
    },
    {
      "epoch": 1.562958867078303,
      "grad_norm": 0.42845678329467773,
      "learning_rate": 2.272329576485197e-06,
      "loss": 0.5167,
      "step": 50879
    },
    {
      "epoch": 1.5629895862132521,
      "grad_norm": 0.4293230473995209,
      "learning_rate": 2.27202285433027e-06,
      "loss": 0.473,
      "step": 50880
    },
    {
      "epoch": 1.5630203053482012,
      "grad_norm": 0.430915504693985,
      "learning_rate": 2.2717161502245744e-06,
      "loss": 0.43,
      "step": 50881
    },
    {
      "epoch": 1.5630510244831506,
      "grad_norm": 0.3976963460445404,
      "learning_rate": 2.2714094641688255e-06,
      "loss": 0.4965,
      "step": 50882
    },
    {
      "epoch": 1.5630817436180997,
      "grad_norm": 0.4121535122394562,
      "learning_rate": 2.271102796163742e-06,
      "loss": 0.4819,
      "step": 50883
    },
    {
      "epoch": 1.5631124627530488,
      "grad_norm": 0.4366017282009125,
      "learning_rate": 2.2707961462100347e-06,
      "loss": 0.5226,
      "step": 50884
    },
    {
      "epoch": 1.5631431818879982,
      "grad_norm": 0.39088794589042664,
      "learning_rate": 2.270489514308423e-06,
      "loss": 0.4423,
      "step": 50885
    },
    {
      "epoch": 1.5631739010229473,
      "grad_norm": 0.4183253049850464,
      "learning_rate": 2.270182900459623e-06,
      "loss": 0.4718,
      "step": 50886
    },
    {
      "epoch": 1.5632046201578964,
      "grad_norm": 0.4165765941143036,
      "learning_rate": 2.2698763046643534e-06,
      "loss": 0.4804,
      "step": 50887
    },
    {
      "epoch": 1.5632353392928455,
      "grad_norm": 0.4194299280643463,
      "learning_rate": 2.269569726923325e-06,
      "loss": 0.475,
      "step": 50888
    },
    {
      "epoch": 1.5632660584277946,
      "grad_norm": 0.4362959861755371,
      "learning_rate": 2.2692631672372555e-06,
      "loss": 0.4581,
      "step": 50889
    },
    {
      "epoch": 1.5632967775627438,
      "grad_norm": 0.6443665027618408,
      "learning_rate": 2.268956625606863e-06,
      "loss": 0.5495,
      "step": 50890
    },
    {
      "epoch": 1.5633274966976929,
      "grad_norm": 0.5236024260520935,
      "learning_rate": 2.268650102032861e-06,
      "loss": 0.3806,
      "step": 50891
    },
    {
      "epoch": 1.563358215832642,
      "grad_norm": 0.45283570885658264,
      "learning_rate": 2.2683435965159707e-06,
      "loss": 0.4674,
      "step": 50892
    },
    {
      "epoch": 1.5633889349675913,
      "grad_norm": 0.4387686550617218,
      "learning_rate": 2.2680371090569e-06,
      "loss": 0.4724,
      "step": 50893
    },
    {
      "epoch": 1.5634196541025405,
      "grad_norm": 0.4919350743293762,
      "learning_rate": 2.267730639656369e-06,
      "loss": 0.4751,
      "step": 50894
    },
    {
      "epoch": 1.5634503732374896,
      "grad_norm": 0.431959331035614,
      "learning_rate": 2.267424188315094e-06,
      "loss": 0.4146,
      "step": 50895
    },
    {
      "epoch": 1.563481092372439,
      "grad_norm": 0.42263054847717285,
      "learning_rate": 2.2671177550337907e-06,
      "loss": 0.4896,
      "step": 50896
    },
    {
      "epoch": 1.563511811507388,
      "grad_norm": 0.38383349776268005,
      "learning_rate": 2.266811339813173e-06,
      "loss": 0.4693,
      "step": 50897
    },
    {
      "epoch": 1.5635425306423372,
      "grad_norm": 0.40041303634643555,
      "learning_rate": 2.26650494265396e-06,
      "loss": 0.4869,
      "step": 50898
    },
    {
      "epoch": 1.5635732497772863,
      "grad_norm": 0.4510345160961151,
      "learning_rate": 2.2661985635568585e-06,
      "loss": 0.4772,
      "step": 50899
    },
    {
      "epoch": 1.5636039689122354,
      "grad_norm": 0.4522828757762909,
      "learning_rate": 2.265892202522596e-06,
      "loss": 0.5274,
      "step": 50900
    },
    {
      "epoch": 1.5636346880471845,
      "grad_norm": 0.4127621054649353,
      "learning_rate": 2.2655858595518797e-06,
      "loss": 0.44,
      "step": 50901
    },
    {
      "epoch": 1.5636654071821336,
      "grad_norm": 0.4625715911388397,
      "learning_rate": 2.2652795346454304e-06,
      "loss": 0.5233,
      "step": 50902
    },
    {
      "epoch": 1.5636961263170828,
      "grad_norm": 0.44434863328933716,
      "learning_rate": 2.264973227803956e-06,
      "loss": 0.4578,
      "step": 50903
    },
    {
      "epoch": 1.563726845452032,
      "grad_norm": 0.4639343023300171,
      "learning_rate": 2.2646669390281826e-06,
      "loss": 0.5268,
      "step": 50904
    },
    {
      "epoch": 1.5637575645869812,
      "grad_norm": 0.4711540639400482,
      "learning_rate": 2.264360668318816e-06,
      "loss": 0.4415,
      "step": 50905
    },
    {
      "epoch": 1.5637882837219304,
      "grad_norm": 0.42116647958755493,
      "learning_rate": 2.2640544156765786e-06,
      "loss": 0.5014,
      "step": 50906
    },
    {
      "epoch": 1.5638190028568797,
      "grad_norm": 0.45423316955566406,
      "learning_rate": 2.26374818110218e-06,
      "loss": 0.4821,
      "step": 50907
    },
    {
      "epoch": 1.5638497219918288,
      "grad_norm": 0.4328659474849701,
      "learning_rate": 2.263441964596337e-06,
      "loss": 0.4583,
      "step": 50908
    },
    {
      "epoch": 1.563880441126778,
      "grad_norm": 0.40940481424331665,
      "learning_rate": 2.2631357661597664e-06,
      "loss": 0.4491,
      "step": 50909
    },
    {
      "epoch": 1.563911160261727,
      "grad_norm": 0.417825847864151,
      "learning_rate": 2.2628295857931826e-06,
      "loss": 0.3911,
      "step": 50910
    },
    {
      "epoch": 1.5639418793966762,
      "grad_norm": 0.44313186407089233,
      "learning_rate": 2.2625234234973027e-06,
      "loss": 0.5656,
      "step": 50911
    },
    {
      "epoch": 1.5639725985316253,
      "grad_norm": 0.44754841923713684,
      "learning_rate": 2.262217279272837e-06,
      "loss": 0.4596,
      "step": 50912
    },
    {
      "epoch": 1.5640033176665744,
      "grad_norm": 0.4580174386501312,
      "learning_rate": 2.261911153120504e-06,
      "loss": 0.56,
      "step": 50913
    },
    {
      "epoch": 1.5640340368015235,
      "grad_norm": 0.39477065205574036,
      "learning_rate": 2.2616050450410176e-06,
      "loss": 0.4879,
      "step": 50914
    },
    {
      "epoch": 1.5640647559364729,
      "grad_norm": 0.4283272325992584,
      "learning_rate": 2.261298955035095e-06,
      "loss": 0.5276,
      "step": 50915
    },
    {
      "epoch": 1.564095475071422,
      "grad_norm": 0.3968566954135895,
      "learning_rate": 2.260992883103448e-06,
      "loss": 0.5052,
      "step": 50916
    },
    {
      "epoch": 1.5641261942063711,
      "grad_norm": 0.4237518906593323,
      "learning_rate": 2.260686829246791e-06,
      "loss": 0.4881,
      "step": 50917
    },
    {
      "epoch": 1.5641569133413205,
      "grad_norm": 0.3990557789802551,
      "learning_rate": 2.2603807934658407e-06,
      "loss": 0.4309,
      "step": 50918
    },
    {
      "epoch": 1.5641876324762696,
      "grad_norm": 0.5039076805114746,
      "learning_rate": 2.260074775761315e-06,
      "loss": 0.4891,
      "step": 50919
    },
    {
      "epoch": 1.5642183516112187,
      "grad_norm": 0.43493881821632385,
      "learning_rate": 2.2597687761339224e-06,
      "loss": 0.4396,
      "step": 50920
    },
    {
      "epoch": 1.5642490707461678,
      "grad_norm": 0.40088531374931335,
      "learning_rate": 2.2594627945843804e-06,
      "loss": 0.4499,
      "step": 50921
    },
    {
      "epoch": 1.564279789881117,
      "grad_norm": 0.4617845416069031,
      "learning_rate": 2.2591568311134026e-06,
      "loss": 0.5308,
      "step": 50922
    },
    {
      "epoch": 1.564310509016066,
      "grad_norm": 0.4307374060153961,
      "learning_rate": 2.2588508857217086e-06,
      "loss": 0.4752,
      "step": 50923
    },
    {
      "epoch": 1.5643412281510152,
      "grad_norm": 0.4055265188217163,
      "learning_rate": 2.258544958410006e-06,
      "loss": 0.4932,
      "step": 50924
    },
    {
      "epoch": 1.5643719472859643,
      "grad_norm": 0.6967331171035767,
      "learning_rate": 2.258239049179012e-06,
      "loss": 0.4445,
      "step": 50925
    },
    {
      "epoch": 1.5644026664209136,
      "grad_norm": 0.4705848693847656,
      "learning_rate": 2.257933158029442e-06,
      "loss": 0.5131,
      "step": 50926
    },
    {
      "epoch": 1.5644333855558628,
      "grad_norm": 0.4002806842327118,
      "learning_rate": 2.2576272849620084e-06,
      "loss": 0.4708,
      "step": 50927
    },
    {
      "epoch": 1.5644641046908119,
      "grad_norm": 0.4014127254486084,
      "learning_rate": 2.2573214299774316e-06,
      "loss": 0.4147,
      "step": 50928
    },
    {
      "epoch": 1.5644948238257612,
      "grad_norm": 0.42976686358451843,
      "learning_rate": 2.257015593076417e-06,
      "loss": 0.4719,
      "step": 50929
    },
    {
      "epoch": 1.5645255429607103,
      "grad_norm": 0.4227256178855896,
      "learning_rate": 2.2567097742596842e-06,
      "loss": 0.4326,
      "step": 50930
    },
    {
      "epoch": 1.5645562620956595,
      "grad_norm": 0.4090968370437622,
      "learning_rate": 2.2564039735279463e-06,
      "loss": 0.4754,
      "step": 50931
    },
    {
      "epoch": 1.5645869812306086,
      "grad_norm": 0.42317694425582886,
      "learning_rate": 2.25609819088192e-06,
      "loss": 0.4436,
      "step": 50932
    },
    {
      "epoch": 1.5646177003655577,
      "grad_norm": 0.44576847553253174,
      "learning_rate": 2.255792426322315e-06,
      "loss": 0.4908,
      "step": 50933
    },
    {
      "epoch": 1.5646484195005068,
      "grad_norm": 0.4838888645172119,
      "learning_rate": 2.255486679849851e-06,
      "loss": 0.5067,
      "step": 50934
    },
    {
      "epoch": 1.564679138635456,
      "grad_norm": 0.4186519384384155,
      "learning_rate": 2.2551809514652325e-06,
      "loss": 0.471,
      "step": 50935
    },
    {
      "epoch": 1.564709857770405,
      "grad_norm": 0.4507361650466919,
      "learning_rate": 2.2548752411691856e-06,
      "loss": 0.5005,
      "step": 50936
    },
    {
      "epoch": 1.5647405769053544,
      "grad_norm": 0.40764984488487244,
      "learning_rate": 2.254569548962414e-06,
      "loss": 0.4538,
      "step": 50937
    },
    {
      "epoch": 1.5647712960403035,
      "grad_norm": 0.43351873755455017,
      "learning_rate": 2.2542638748456415e-06,
      "loss": 0.4896,
      "step": 50938
    },
    {
      "epoch": 1.5648020151752526,
      "grad_norm": 0.41016000509262085,
      "learning_rate": 2.253958218819572e-06,
      "loss": 0.4486,
      "step": 50939
    },
    {
      "epoch": 1.564832734310202,
      "grad_norm": 0.41047513484954834,
      "learning_rate": 2.253652580884925e-06,
      "loss": 0.4725,
      "step": 50940
    },
    {
      "epoch": 1.564863453445151,
      "grad_norm": 0.4509336054325104,
      "learning_rate": 2.253346961042413e-06,
      "loss": 0.4176,
      "step": 50941
    },
    {
      "epoch": 1.5648941725801002,
      "grad_norm": 0.44242867827415466,
      "learning_rate": 2.2530413592927537e-06,
      "loss": 0.4619,
      "step": 50942
    },
    {
      "epoch": 1.5649248917150493,
      "grad_norm": 0.436196506023407,
      "learning_rate": 2.252735775636654e-06,
      "loss": 0.4461,
      "step": 50943
    },
    {
      "epoch": 1.5649556108499985,
      "grad_norm": 0.48448774218559265,
      "learning_rate": 2.2524302100748306e-06,
      "loss": 0.4766,
      "step": 50944
    },
    {
      "epoch": 1.5649863299849476,
      "grad_norm": 0.43099603056907654,
      "learning_rate": 2.2521246626079984e-06,
      "loss": 0.451,
      "step": 50945
    },
    {
      "epoch": 1.5650170491198967,
      "grad_norm": 1.216068983078003,
      "learning_rate": 2.251819133236869e-06,
      "loss": 0.4818,
      "step": 50946
    },
    {
      "epoch": 1.5650477682548458,
      "grad_norm": 0.4547082483768463,
      "learning_rate": 2.25151362196216e-06,
      "loss": 0.5459,
      "step": 50947
    },
    {
      "epoch": 1.5650784873897952,
      "grad_norm": 0.42458996176719666,
      "learning_rate": 2.251208128784581e-06,
      "loss": 0.4034,
      "step": 50948
    },
    {
      "epoch": 1.5651092065247443,
      "grad_norm": 0.4239928722381592,
      "learning_rate": 2.250902653704845e-06,
      "loss": 0.4315,
      "step": 50949
    },
    {
      "epoch": 1.5651399256596934,
      "grad_norm": 0.4104050397872925,
      "learning_rate": 2.2505971967236674e-06,
      "loss": 0.428,
      "step": 50950
    },
    {
      "epoch": 1.5651706447946427,
      "grad_norm": 0.4366055130958557,
      "learning_rate": 2.2502917578417648e-06,
      "loss": 0.4294,
      "step": 50951
    },
    {
      "epoch": 1.5652013639295919,
      "grad_norm": 0.4622115194797516,
      "learning_rate": 2.249986337059843e-06,
      "loss": 0.4544,
      "step": 50952
    },
    {
      "epoch": 1.565232083064541,
      "grad_norm": 0.4294537901878357,
      "learning_rate": 2.2496809343786207e-06,
      "loss": 0.492,
      "step": 50953
    },
    {
      "epoch": 1.56526280219949,
      "grad_norm": 0.4356934726238251,
      "learning_rate": 2.249375549798809e-06,
      "loss": 0.5243,
      "step": 50954
    },
    {
      "epoch": 1.5652935213344392,
      "grad_norm": 0.3966006338596344,
      "learning_rate": 2.2490701833211247e-06,
      "loss": 0.4204,
      "step": 50955
    },
    {
      "epoch": 1.5653242404693883,
      "grad_norm": 0.4623942971229553,
      "learning_rate": 2.2487648349462752e-06,
      "loss": 0.4386,
      "step": 50956
    },
    {
      "epoch": 1.5653549596043375,
      "grad_norm": 0.4466259777545929,
      "learning_rate": 2.248459504674978e-06,
      "loss": 0.4664,
      "step": 50957
    },
    {
      "epoch": 1.5653856787392866,
      "grad_norm": 0.4668595492839813,
      "learning_rate": 2.2481541925079443e-06,
      "loss": 0.4821,
      "step": 50958
    },
    {
      "epoch": 1.5654163978742357,
      "grad_norm": 0.4431869387626648,
      "learning_rate": 2.24784889844589e-06,
      "loss": 0.4846,
      "step": 50959
    },
    {
      "epoch": 1.565447117009185,
      "grad_norm": 0.4591902494430542,
      "learning_rate": 2.247543622489524e-06,
      "loss": 0.5121,
      "step": 50960
    },
    {
      "epoch": 1.5654778361441342,
      "grad_norm": 0.46142202615737915,
      "learning_rate": 2.2472383646395646e-06,
      "loss": 0.5277,
      "step": 50961
    },
    {
      "epoch": 1.5655085552790835,
      "grad_norm": 0.4957524538040161,
      "learning_rate": 2.246933124896715e-06,
      "loss": 0.4645,
      "step": 50962
    },
    {
      "epoch": 1.5655392744140326,
      "grad_norm": 0.42404916882514954,
      "learning_rate": 2.2466279032617e-06,
      "loss": 0.3995,
      "step": 50963
    },
    {
      "epoch": 1.5655699935489817,
      "grad_norm": 0.38784679770469666,
      "learning_rate": 2.246322699735225e-06,
      "loss": 0.4946,
      "step": 50964
    },
    {
      "epoch": 1.5656007126839309,
      "grad_norm": 0.39431068301200867,
      "learning_rate": 2.246017514318004e-06,
      "loss": 0.514,
      "step": 50965
    },
    {
      "epoch": 1.56563143181888,
      "grad_norm": 0.44582557678222656,
      "learning_rate": 2.2457123470107513e-06,
      "loss": 0.4571,
      "step": 50966
    },
    {
      "epoch": 1.565662150953829,
      "grad_norm": 0.3994846045970917,
      "learning_rate": 2.245407197814179e-06,
      "loss": 0.4853,
      "step": 50967
    },
    {
      "epoch": 1.5656928700887782,
      "grad_norm": 0.40069687366485596,
      "learning_rate": 2.2451020667290014e-06,
      "loss": 0.4766,
      "step": 50968
    },
    {
      "epoch": 1.5657235892237273,
      "grad_norm": 0.40601831674575806,
      "learning_rate": 2.2447969537559277e-06,
      "loss": 0.3741,
      "step": 50969
    },
    {
      "epoch": 1.5657543083586765,
      "grad_norm": 0.4324904978275299,
      "learning_rate": 2.2444918588956753e-06,
      "loss": 0.5336,
      "step": 50970
    },
    {
      "epoch": 1.5657850274936258,
      "grad_norm": 0.43006598949432373,
      "learning_rate": 2.2441867821489484e-06,
      "loss": 0.5187,
      "step": 50971
    },
    {
      "epoch": 1.565815746628575,
      "grad_norm": 0.4195994734764099,
      "learning_rate": 2.24388172351647e-06,
      "loss": 0.4915,
      "step": 50972
    },
    {
      "epoch": 1.5658464657635243,
      "grad_norm": 0.45263805985450745,
      "learning_rate": 2.243576682998945e-06,
      "loss": 0.4929,
      "step": 50973
    },
    {
      "epoch": 1.5658771848984734,
      "grad_norm": 0.4231981039047241,
      "learning_rate": 2.2432716605970908e-06,
      "loss": 0.3612,
      "step": 50974
    },
    {
      "epoch": 1.5659079040334225,
      "grad_norm": 0.4201319217681885,
      "learning_rate": 2.242966656311614e-06,
      "loss": 0.4011,
      "step": 50975
    },
    {
      "epoch": 1.5659386231683716,
      "grad_norm": 0.4300798773765564,
      "learning_rate": 2.2426616701432314e-06,
      "loss": 0.4577,
      "step": 50976
    },
    {
      "epoch": 1.5659693423033207,
      "grad_norm": 0.438915491104126,
      "learning_rate": 2.242356702092654e-06,
      "loss": 0.5137,
      "step": 50977
    },
    {
      "epoch": 1.5660000614382699,
      "grad_norm": 0.4666766822338104,
      "learning_rate": 2.2420517521605966e-06,
      "loss": 0.4191,
      "step": 50978
    },
    {
      "epoch": 1.566030780573219,
      "grad_norm": 0.4651626944541931,
      "learning_rate": 2.2417468203477664e-06,
      "loss": 0.418,
      "step": 50979
    },
    {
      "epoch": 1.566061499708168,
      "grad_norm": 0.4900588393211365,
      "learning_rate": 2.241441906654879e-06,
      "loss": 0.4638,
      "step": 50980
    },
    {
      "epoch": 1.5660922188431172,
      "grad_norm": 0.8930285573005676,
      "learning_rate": 2.241137011082646e-06,
      "loss": 0.4758,
      "step": 50981
    },
    {
      "epoch": 1.5661229379780666,
      "grad_norm": 0.41135209798812866,
      "learning_rate": 2.2408321336317784e-06,
      "loss": 0.4891,
      "step": 50982
    },
    {
      "epoch": 1.5661536571130157,
      "grad_norm": 0.41794490814208984,
      "learning_rate": 2.2405272743029926e-06,
      "loss": 0.4655,
      "step": 50983
    },
    {
      "epoch": 1.5661843762479648,
      "grad_norm": 0.4370115399360657,
      "learning_rate": 2.2402224330969947e-06,
      "loss": 0.4417,
      "step": 50984
    },
    {
      "epoch": 1.5662150953829141,
      "grad_norm": 0.35994499921798706,
      "learning_rate": 2.2399176100144983e-06,
      "loss": 0.423,
      "step": 50985
    },
    {
      "epoch": 1.5662458145178633,
      "grad_norm": 0.4657035768032074,
      "learning_rate": 2.239612805056217e-06,
      "loss": 0.4316,
      "step": 50986
    },
    {
      "epoch": 1.5662765336528124,
      "grad_norm": 0.44212907552719116,
      "learning_rate": 2.2393080182228645e-06,
      "loss": 0.4452,
      "step": 50987
    },
    {
      "epoch": 1.5663072527877615,
      "grad_norm": 0.4289708733558655,
      "learning_rate": 2.239003249515148e-06,
      "loss": 0.4799,
      "step": 50988
    },
    {
      "epoch": 1.5663379719227106,
      "grad_norm": 0.434703528881073,
      "learning_rate": 2.238698498933781e-06,
      "loss": 0.4661,
      "step": 50989
    },
    {
      "epoch": 1.5663686910576597,
      "grad_norm": 0.4829135239124298,
      "learning_rate": 2.2383937664794754e-06,
      "loss": 0.4386,
      "step": 50990
    },
    {
      "epoch": 1.5663994101926089,
      "grad_norm": 0.40260109305381775,
      "learning_rate": 2.2380890521529465e-06,
      "loss": 0.4876,
      "step": 50991
    },
    {
      "epoch": 1.566430129327558,
      "grad_norm": 0.45015525817871094,
      "learning_rate": 2.2377843559548997e-06,
      "loss": 0.4485,
      "step": 50992
    },
    {
      "epoch": 1.5664608484625073,
      "grad_norm": 0.43869537115097046,
      "learning_rate": 2.23747967788605e-06,
      "loss": 0.4976,
      "step": 50993
    },
    {
      "epoch": 1.5664915675974564,
      "grad_norm": 0.4321540296077728,
      "learning_rate": 2.2371750179471076e-06,
      "loss": 0.4805,
      "step": 50994
    },
    {
      "epoch": 1.5665222867324056,
      "grad_norm": 0.394832968711853,
      "learning_rate": 2.2368703761387887e-06,
      "loss": 0.4109,
      "step": 50995
    },
    {
      "epoch": 1.566553005867355,
      "grad_norm": 0.41107282042503357,
      "learning_rate": 2.236565752461798e-06,
      "loss": 0.4859,
      "step": 50996
    },
    {
      "epoch": 1.566583725002304,
      "grad_norm": 0.39262568950653076,
      "learning_rate": 2.236261146916854e-06,
      "loss": 0.4327,
      "step": 50997
    },
    {
      "epoch": 1.5666144441372531,
      "grad_norm": 0.48105329275131226,
      "learning_rate": 2.2359565595046575e-06,
      "loss": 0.5367,
      "step": 50998
    },
    {
      "epoch": 1.5666451632722023,
      "grad_norm": 0.42875581979751587,
      "learning_rate": 2.2356519902259322e-06,
      "loss": 0.4853,
      "step": 50999
    },
    {
      "epoch": 1.5666758824071514,
      "grad_norm": 0.4425030052661896,
      "learning_rate": 2.2353474390813823e-06,
      "loss": 0.4675,
      "step": 51000
    },
    {
      "epoch": 1.5667066015421005,
      "grad_norm": 0.4126029312610626,
      "learning_rate": 2.2350429060717206e-06,
      "loss": 0.487,
      "step": 51001
    },
    {
      "epoch": 1.5667373206770496,
      "grad_norm": 0.45180752873420715,
      "learning_rate": 2.2347383911976573e-06,
      "loss": 0.4674,
      "step": 51002
    },
    {
      "epoch": 1.5667680398119987,
      "grad_norm": 0.4193217158317566,
      "learning_rate": 2.2344338944599055e-06,
      "loss": 0.4491,
      "step": 51003
    },
    {
      "epoch": 1.566798758946948,
      "grad_norm": 0.48129212856292725,
      "learning_rate": 2.2341294158591786e-06,
      "loss": 0.5166,
      "step": 51004
    },
    {
      "epoch": 1.5668294780818972,
      "grad_norm": 0.4273703992366791,
      "learning_rate": 2.233824955396182e-06,
      "loss": 0.4305,
      "step": 51005
    },
    {
      "epoch": 1.5668601972168463,
      "grad_norm": 0.44060394167900085,
      "learning_rate": 2.233520513071632e-06,
      "loss": 0.4961,
      "step": 51006
    },
    {
      "epoch": 1.5668909163517957,
      "grad_norm": 0.42312535643577576,
      "learning_rate": 2.233216088886232e-06,
      "loss": 0.3768,
      "step": 51007
    },
    {
      "epoch": 1.5669216354867448,
      "grad_norm": 0.4491557776927948,
      "learning_rate": 2.232911682840704e-06,
      "loss": 0.4527,
      "step": 51008
    },
    {
      "epoch": 1.566952354621694,
      "grad_norm": 0.4421062767505646,
      "learning_rate": 2.2326072949357503e-06,
      "loss": 0.5168,
      "step": 51009
    },
    {
      "epoch": 1.566983073756643,
      "grad_norm": 0.437679648399353,
      "learning_rate": 2.232302925172087e-06,
      "loss": 0.4246,
      "step": 51010
    },
    {
      "epoch": 1.5670137928915921,
      "grad_norm": 0.4416723847389221,
      "learning_rate": 2.23199857355042e-06,
      "loss": 0.4723,
      "step": 51011
    },
    {
      "epoch": 1.5670445120265413,
      "grad_norm": 0.41510671377182007,
      "learning_rate": 2.2316942400714638e-06,
      "loss": 0.4249,
      "step": 51012
    },
    {
      "epoch": 1.5670752311614904,
      "grad_norm": 0.47122836112976074,
      "learning_rate": 2.231389924735927e-06,
      "loss": 0.5194,
      "step": 51013
    },
    {
      "epoch": 1.5671059502964395,
      "grad_norm": 0.4396863579750061,
      "learning_rate": 2.231085627544526e-06,
      "loss": 0.4068,
      "step": 51014
    },
    {
      "epoch": 1.5671366694313889,
      "grad_norm": 0.557954728603363,
      "learning_rate": 2.230781348497962e-06,
      "loss": 0.4566,
      "step": 51015
    },
    {
      "epoch": 1.567167388566338,
      "grad_norm": 0.4715762436389923,
      "learning_rate": 2.230477087596953e-06,
      "loss": 0.4958,
      "step": 51016
    },
    {
      "epoch": 1.567198107701287,
      "grad_norm": 0.47087693214416504,
      "learning_rate": 2.2301728448422066e-06,
      "loss": 0.4476,
      "step": 51017
    },
    {
      "epoch": 1.5672288268362364,
      "grad_norm": 0.4369699954986572,
      "learning_rate": 2.229868620234437e-06,
      "loss": 0.4907,
      "step": 51018
    },
    {
      "epoch": 1.5672595459711856,
      "grad_norm": 0.42070749402046204,
      "learning_rate": 2.229564413774349e-06,
      "loss": 0.43,
      "step": 51019
    },
    {
      "epoch": 1.5672902651061347,
      "grad_norm": 0.40698251128196716,
      "learning_rate": 2.229260225462655e-06,
      "loss": 0.5168,
      "step": 51020
    },
    {
      "epoch": 1.5673209842410838,
      "grad_norm": 0.44793882966041565,
      "learning_rate": 2.228956055300068e-06,
      "loss": 0.4952,
      "step": 51021
    },
    {
      "epoch": 1.567351703376033,
      "grad_norm": 0.3976944088935852,
      "learning_rate": 2.2286519032872954e-06,
      "loss": 0.5428,
      "step": 51022
    },
    {
      "epoch": 1.567382422510982,
      "grad_norm": 0.4908771216869354,
      "learning_rate": 2.2283477694250533e-06,
      "loss": 0.4204,
      "step": 51023
    },
    {
      "epoch": 1.5674131416459312,
      "grad_norm": 0.43913307785987854,
      "learning_rate": 2.2280436537140436e-06,
      "loss": 0.5627,
      "step": 51024
    },
    {
      "epoch": 1.5674438607808803,
      "grad_norm": 0.39959514141082764,
      "learning_rate": 2.227739556154982e-06,
      "loss": 0.4631,
      "step": 51025
    },
    {
      "epoch": 1.5674745799158296,
      "grad_norm": 0.4402921795845032,
      "learning_rate": 2.2274354767485764e-06,
      "loss": 0.5377,
      "step": 51026
    },
    {
      "epoch": 1.5675052990507787,
      "grad_norm": 0.43863192200660706,
      "learning_rate": 2.2271314154955413e-06,
      "loss": 0.4289,
      "step": 51027
    },
    {
      "epoch": 1.5675360181857279,
      "grad_norm": 0.430177241563797,
      "learning_rate": 2.2268273723965814e-06,
      "loss": 0.4406,
      "step": 51028
    },
    {
      "epoch": 1.5675667373206772,
      "grad_norm": 0.46030333638191223,
      "learning_rate": 2.226523347452408e-06,
      "loss": 0.4722,
      "step": 51029
    },
    {
      "epoch": 1.5675974564556263,
      "grad_norm": 0.4064781069755554,
      "learning_rate": 2.2262193406637336e-06,
      "loss": 0.3295,
      "step": 51030
    },
    {
      "epoch": 1.5676281755905754,
      "grad_norm": 0.43552669882774353,
      "learning_rate": 2.225915352031268e-06,
      "loss": 0.386,
      "step": 51031
    },
    {
      "epoch": 1.5676588947255246,
      "grad_norm": 0.45023131370544434,
      "learning_rate": 2.225611381555718e-06,
      "loss": 0.4093,
      "step": 51032
    },
    {
      "epoch": 1.5676896138604737,
      "grad_norm": 0.40663740038871765,
      "learning_rate": 2.2253074292377984e-06,
      "loss": 0.4761,
      "step": 51033
    },
    {
      "epoch": 1.5677203329954228,
      "grad_norm": 0.4086572825908661,
      "learning_rate": 2.2250034950782107e-06,
      "loss": 0.4266,
      "step": 51034
    },
    {
      "epoch": 1.567751052130372,
      "grad_norm": 0.39208972454071045,
      "learning_rate": 2.224699579077676e-06,
      "loss": 0.3666,
      "step": 51035
    },
    {
      "epoch": 1.567781771265321,
      "grad_norm": 0.4137401282787323,
      "learning_rate": 2.224395681236896e-06,
      "loss": 0.4167,
      "step": 51036
    },
    {
      "epoch": 1.5678124904002704,
      "grad_norm": 0.41815024614334106,
      "learning_rate": 2.2240918015565814e-06,
      "loss": 0.4493,
      "step": 51037
    },
    {
      "epoch": 1.5678432095352195,
      "grad_norm": 0.44964295625686646,
      "learning_rate": 2.2237879400374487e-06,
      "loss": 0.4487,
      "step": 51038
    },
    {
      "epoch": 1.5678739286701686,
      "grad_norm": 0.42438989877700806,
      "learning_rate": 2.2234840966801953e-06,
      "loss": 0.4678,
      "step": 51039
    },
    {
      "epoch": 1.567904647805118,
      "grad_norm": 0.47984829545021057,
      "learning_rate": 2.2231802714855433e-06,
      "loss": 0.4788,
      "step": 51040
    },
    {
      "epoch": 1.567935366940067,
      "grad_norm": 0.3873368501663208,
      "learning_rate": 2.2228764644541944e-06,
      "loss": 0.4175,
      "step": 51041
    },
    {
      "epoch": 1.5679660860750162,
      "grad_norm": 0.40747612714767456,
      "learning_rate": 2.2225726755868627e-06,
      "loss": 0.4706,
      "step": 51042
    },
    {
      "epoch": 1.5679968052099653,
      "grad_norm": 0.4109320342540741,
      "learning_rate": 2.2222689048842517e-06,
      "loss": 0.4538,
      "step": 51043
    },
    {
      "epoch": 1.5680275243449144,
      "grad_norm": 0.43117082118988037,
      "learning_rate": 2.221965152347079e-06,
      "loss": 0.4744,
      "step": 51044
    },
    {
      "epoch": 1.5680582434798636,
      "grad_norm": 0.45119336247444153,
      "learning_rate": 2.2216614179760475e-06,
      "loss": 0.452,
      "step": 51045
    },
    {
      "epoch": 1.5680889626148127,
      "grad_norm": 0.4394264817237854,
      "learning_rate": 2.2213577017718725e-06,
      "loss": 0.4934,
      "step": 51046
    },
    {
      "epoch": 1.5681196817497618,
      "grad_norm": 0.4266313314437866,
      "learning_rate": 2.2210540037352567e-06,
      "loss": 0.4267,
      "step": 51047
    },
    {
      "epoch": 1.5681504008847111,
      "grad_norm": 0.40175071358680725,
      "learning_rate": 2.2207503238669127e-06,
      "loss": 0.4446,
      "step": 51048
    },
    {
      "epoch": 1.5681811200196603,
      "grad_norm": 0.4255812466144562,
      "learning_rate": 2.220446662167549e-06,
      "loss": 0.4874,
      "step": 51049
    },
    {
      "epoch": 1.5682118391546094,
      "grad_norm": 0.41234514117240906,
      "learning_rate": 2.220143018637878e-06,
      "loss": 0.5014,
      "step": 51050
    },
    {
      "epoch": 1.5682425582895587,
      "grad_norm": 0.43993067741394043,
      "learning_rate": 2.2198393932786044e-06,
      "loss": 0.4907,
      "step": 51051
    },
    {
      "epoch": 1.5682732774245078,
      "grad_norm": 0.5172754526138306,
      "learning_rate": 2.2195357860904387e-06,
      "loss": 0.5016,
      "step": 51052
    },
    {
      "epoch": 1.568303996559457,
      "grad_norm": 0.4282904863357544,
      "learning_rate": 2.2192321970740905e-06,
      "loss": 0.46,
      "step": 51053
    },
    {
      "epoch": 1.568334715694406,
      "grad_norm": 0.439505398273468,
      "learning_rate": 2.218928626230272e-06,
      "loss": 0.4911,
      "step": 51054
    },
    {
      "epoch": 1.5683654348293552,
      "grad_norm": 0.4240418076515198,
      "learning_rate": 2.2186250735596872e-06,
      "loss": 0.5013,
      "step": 51055
    },
    {
      "epoch": 1.5683961539643043,
      "grad_norm": 0.41847601532936096,
      "learning_rate": 2.2183215390630454e-06,
      "loss": 0.4088,
      "step": 51056
    },
    {
      "epoch": 1.5684268730992534,
      "grad_norm": 0.4611755311489105,
      "learning_rate": 2.2180180227410574e-06,
      "loss": 0.4452,
      "step": 51057
    },
    {
      "epoch": 1.5684575922342026,
      "grad_norm": 0.40367674827575684,
      "learning_rate": 2.217714524594433e-06,
      "loss": 0.4465,
      "step": 51058
    },
    {
      "epoch": 1.568488311369152,
      "grad_norm": 0.449459433555603,
      "learning_rate": 2.2174110446238817e-06,
      "loss": 0.4294,
      "step": 51059
    },
    {
      "epoch": 1.568519030504101,
      "grad_norm": 0.437806099653244,
      "learning_rate": 2.217107582830107e-06,
      "loss": 0.4602,
      "step": 51060
    },
    {
      "epoch": 1.5685497496390501,
      "grad_norm": 0.39152270555496216,
      "learning_rate": 2.216804139213823e-06,
      "loss": 0.4778,
      "step": 51061
    },
    {
      "epoch": 1.5685804687739995,
      "grad_norm": 0.4242876172065735,
      "learning_rate": 2.216500713775734e-06,
      "loss": 0.5094,
      "step": 51062
    },
    {
      "epoch": 1.5686111879089486,
      "grad_norm": 0.4166049659252167,
      "learning_rate": 2.2161973065165565e-06,
      "loss": 0.4486,
      "step": 51063
    },
    {
      "epoch": 1.5686419070438977,
      "grad_norm": 0.39892590045928955,
      "learning_rate": 2.21589391743699e-06,
      "loss": 0.4109,
      "step": 51064
    },
    {
      "epoch": 1.5686726261788468,
      "grad_norm": 0.41664496064186096,
      "learning_rate": 2.215590546537746e-06,
      "loss": 0.4527,
      "step": 51065
    },
    {
      "epoch": 1.568703345313796,
      "grad_norm": 0.4306621551513672,
      "learning_rate": 2.215287193819535e-06,
      "loss": 0.5365,
      "step": 51066
    },
    {
      "epoch": 1.568734064448745,
      "grad_norm": 0.4753821790218353,
      "learning_rate": 2.2149838592830665e-06,
      "loss": 0.4904,
      "step": 51067
    },
    {
      "epoch": 1.5687647835836942,
      "grad_norm": 0.4317217171192169,
      "learning_rate": 2.214680542929044e-06,
      "loss": 0.4326,
      "step": 51068
    },
    {
      "epoch": 1.5687955027186433,
      "grad_norm": 0.5273143649101257,
      "learning_rate": 2.2143772447581825e-06,
      "loss": 0.4374,
      "step": 51069
    },
    {
      "epoch": 1.5688262218535924,
      "grad_norm": 0.5141717195510864,
      "learning_rate": 2.214073964771181e-06,
      "loss": 0.4847,
      "step": 51070
    },
    {
      "epoch": 1.5688569409885418,
      "grad_norm": 0.42673632502555847,
      "learning_rate": 2.2137707029687585e-06,
      "loss": 0.5048,
      "step": 51071
    },
    {
      "epoch": 1.568887660123491,
      "grad_norm": 0.4209223985671997,
      "learning_rate": 2.213467459351616e-06,
      "loss": 0.4622,
      "step": 51072
    },
    {
      "epoch": 1.5689183792584402,
      "grad_norm": 0.4339192807674408,
      "learning_rate": 2.213164233920464e-06,
      "loss": 0.541,
      "step": 51073
    },
    {
      "epoch": 1.5689490983933894,
      "grad_norm": 0.42812925577163696,
      "learning_rate": 2.212861026676013e-06,
      "loss": 0.4695,
      "step": 51074
    },
    {
      "epoch": 1.5689798175283385,
      "grad_norm": 0.4143619239330292,
      "learning_rate": 2.212557837618964e-06,
      "loss": 0.5018,
      "step": 51075
    },
    {
      "epoch": 1.5690105366632876,
      "grad_norm": 0.4569019675254822,
      "learning_rate": 2.2122546667500355e-06,
      "loss": 0.4772,
      "step": 51076
    },
    {
      "epoch": 1.5690412557982367,
      "grad_norm": 0.44055086374282837,
      "learning_rate": 2.211951514069928e-06,
      "loss": 0.4116,
      "step": 51077
    },
    {
      "epoch": 1.5690719749331858,
      "grad_norm": 0.48848122358322144,
      "learning_rate": 2.211648379579353e-06,
      "loss": 0.4473,
      "step": 51078
    },
    {
      "epoch": 1.569102694068135,
      "grad_norm": 0.4363675117492676,
      "learning_rate": 2.2113452632790146e-06,
      "loss": 0.4507,
      "step": 51079
    },
    {
      "epoch": 1.569133413203084,
      "grad_norm": 0.4115358889102936,
      "learning_rate": 2.2110421651696235e-06,
      "loss": 0.4527,
      "step": 51080
    },
    {
      "epoch": 1.5691641323380332,
      "grad_norm": 0.477319598197937,
      "learning_rate": 2.210739085251888e-06,
      "loss": 0.4642,
      "step": 51081
    },
    {
      "epoch": 1.5691948514729825,
      "grad_norm": 0.42061012983322144,
      "learning_rate": 2.2104360235265178e-06,
      "loss": 0.5424,
      "step": 51082
    },
    {
      "epoch": 1.5692255706079317,
      "grad_norm": 0.4645335376262665,
      "learning_rate": 2.210132979994215e-06,
      "loss": 0.4382,
      "step": 51083
    },
    {
      "epoch": 1.569256289742881,
      "grad_norm": 0.44553494453430176,
      "learning_rate": 2.209829954655691e-06,
      "loss": 0.4372,
      "step": 51084
    },
    {
      "epoch": 1.5692870088778301,
      "grad_norm": 0.3939021825790405,
      "learning_rate": 2.2095269475116543e-06,
      "loss": 0.3812,
      "step": 51085
    },
    {
      "epoch": 1.5693177280127792,
      "grad_norm": 0.41627806425094604,
      "learning_rate": 2.209223958562813e-06,
      "loss": 0.4944,
      "step": 51086
    },
    {
      "epoch": 1.5693484471477284,
      "grad_norm": 0.48095226287841797,
      "learning_rate": 2.2089209878098704e-06,
      "loss": 0.5243,
      "step": 51087
    },
    {
      "epoch": 1.5693791662826775,
      "grad_norm": 0.4693187475204468,
      "learning_rate": 2.208618035253537e-06,
      "loss": 0.4143,
      "step": 51088
    },
    {
      "epoch": 1.5694098854176266,
      "grad_norm": 0.5040614604949951,
      "learning_rate": 2.2083151008945212e-06,
      "loss": 0.4538,
      "step": 51089
    },
    {
      "epoch": 1.5694406045525757,
      "grad_norm": 0.4848451614379883,
      "learning_rate": 2.208012184733531e-06,
      "loss": 0.494,
      "step": 51090
    },
    {
      "epoch": 1.5694713236875248,
      "grad_norm": 0.46476325392723083,
      "learning_rate": 2.2077092867712714e-06,
      "loss": 0.5229,
      "step": 51091
    },
    {
      "epoch": 1.569502042822474,
      "grad_norm": 0.4769844710826874,
      "learning_rate": 2.20740640700845e-06,
      "loss": 0.5213,
      "step": 51092
    },
    {
      "epoch": 1.5695327619574233,
      "grad_norm": 0.38913020491600037,
      "learning_rate": 2.2071035454457757e-06,
      "loss": 0.4575,
      "step": 51093
    },
    {
      "epoch": 1.5695634810923724,
      "grad_norm": 0.40372949838638306,
      "learning_rate": 2.2068007020839545e-06,
      "loss": 0.3918,
      "step": 51094
    },
    {
      "epoch": 1.5695942002273215,
      "grad_norm": 0.436649888753891,
      "learning_rate": 2.2064978769236978e-06,
      "loss": 0.4442,
      "step": 51095
    },
    {
      "epoch": 1.5696249193622709,
      "grad_norm": 0.43659982085227966,
      "learning_rate": 2.2061950699657064e-06,
      "loss": 0.4607,
      "step": 51096
    },
    {
      "epoch": 1.56965563849722,
      "grad_norm": 0.4303416609764099,
      "learning_rate": 2.205892281210692e-06,
      "loss": 0.4286,
      "step": 51097
    },
    {
      "epoch": 1.5696863576321691,
      "grad_norm": 0.4591512084007263,
      "learning_rate": 2.2055895106593596e-06,
      "loss": 0.456,
      "step": 51098
    },
    {
      "epoch": 1.5697170767671182,
      "grad_norm": 0.4262900650501251,
      "learning_rate": 2.2052867583124195e-06,
      "loss": 0.4112,
      "step": 51099
    },
    {
      "epoch": 1.5697477959020674,
      "grad_norm": 0.4134870767593384,
      "learning_rate": 2.2049840241705744e-06,
      "loss": 0.4384,
      "step": 51100
    },
    {
      "epoch": 1.5697785150370165,
      "grad_norm": 0.4110567569732666,
      "learning_rate": 2.2046813082345364e-06,
      "loss": 0.4769,
      "step": 51101
    },
    {
      "epoch": 1.5698092341719656,
      "grad_norm": 0.41720709204673767,
      "learning_rate": 2.2043786105050037e-06,
      "loss": 0.4033,
      "step": 51102
    },
    {
      "epoch": 1.5698399533069147,
      "grad_norm": 0.42625048756599426,
      "learning_rate": 2.2040759309826954e-06,
      "loss": 0.4547,
      "step": 51103
    },
    {
      "epoch": 1.569870672441864,
      "grad_norm": 0.4620930254459381,
      "learning_rate": 2.203773269668309e-06,
      "loss": 0.448,
      "step": 51104
    },
    {
      "epoch": 1.5699013915768132,
      "grad_norm": 0.4078544080257416,
      "learning_rate": 2.203470626562557e-06,
      "loss": 0.4312,
      "step": 51105
    },
    {
      "epoch": 1.5699321107117623,
      "grad_norm": 0.4030551612377167,
      "learning_rate": 2.2031680016661383e-06,
      "loss": 0.469,
      "step": 51106
    },
    {
      "epoch": 1.5699628298467116,
      "grad_norm": 0.44252344965934753,
      "learning_rate": 2.2028653949797716e-06,
      "loss": 0.4966,
      "step": 51107
    },
    {
      "epoch": 1.5699935489816608,
      "grad_norm": 0.4449460804462433,
      "learning_rate": 2.202562806504154e-06,
      "loss": 0.5079,
      "step": 51108
    },
    {
      "epoch": 1.57002426811661,
      "grad_norm": 0.4384559988975525,
      "learning_rate": 2.202260236239998e-06,
      "loss": 0.4506,
      "step": 51109
    },
    {
      "epoch": 1.570054987251559,
      "grad_norm": 0.4681512117385864,
      "learning_rate": 2.2019576841880054e-06,
      "loss": 0.5184,
      "step": 51110
    },
    {
      "epoch": 1.5700857063865081,
      "grad_norm": 0.4574395418167114,
      "learning_rate": 2.2016551503488825e-06,
      "loss": 0.4823,
      "step": 51111
    },
    {
      "epoch": 1.5701164255214572,
      "grad_norm": 0.3977571725845337,
      "learning_rate": 2.201352634723345e-06,
      "loss": 0.4612,
      "step": 51112
    },
    {
      "epoch": 1.5701471446564064,
      "grad_norm": 0.42328473925590515,
      "learning_rate": 2.2010501373120887e-06,
      "loss": 0.4217,
      "step": 51113
    },
    {
      "epoch": 1.5701778637913555,
      "grad_norm": 0.41217029094696045,
      "learning_rate": 2.200747658115828e-06,
      "loss": 0.4408,
      "step": 51114
    },
    {
      "epoch": 1.5702085829263048,
      "grad_norm": 0.45153242349624634,
      "learning_rate": 2.2004451971352636e-06,
      "loss": 0.463,
      "step": 51115
    },
    {
      "epoch": 1.570239302061254,
      "grad_norm": 0.43433085083961487,
      "learning_rate": 2.200142754371104e-06,
      "loss": 0.4749,
      "step": 51116
    },
    {
      "epoch": 1.570270021196203,
      "grad_norm": 0.403352290391922,
      "learning_rate": 2.1998403298240544e-06,
      "loss": 0.4641,
      "step": 51117
    },
    {
      "epoch": 1.5703007403311524,
      "grad_norm": 0.4878380596637726,
      "learning_rate": 2.199537923494827e-06,
      "loss": 0.4183,
      "step": 51118
    },
    {
      "epoch": 1.5703314594661015,
      "grad_norm": 0.4624303877353668,
      "learning_rate": 2.19923553538412e-06,
      "loss": 0.4589,
      "step": 51119
    },
    {
      "epoch": 1.5703621786010507,
      "grad_norm": 0.438368558883667,
      "learning_rate": 2.1989331654926426e-06,
      "loss": 0.428,
      "step": 51120
    },
    {
      "epoch": 1.5703928977359998,
      "grad_norm": 0.4037720859050751,
      "learning_rate": 2.198630813821102e-06,
      "loss": 0.5178,
      "step": 51121
    },
    {
      "epoch": 1.570423616870949,
      "grad_norm": 0.49442002177238464,
      "learning_rate": 2.1983284803702078e-06,
      "loss": 0.4725,
      "step": 51122
    },
    {
      "epoch": 1.570454336005898,
      "grad_norm": 0.4813038110733032,
      "learning_rate": 2.1980261651406586e-06,
      "loss": 0.4282,
      "step": 51123
    },
    {
      "epoch": 1.5704850551408471,
      "grad_norm": 0.4201909303665161,
      "learning_rate": 2.197723868133165e-06,
      "loss": 0.4816,
      "step": 51124
    },
    {
      "epoch": 1.5705157742757963,
      "grad_norm": 0.4832616448402405,
      "learning_rate": 2.1974215893484306e-06,
      "loss": 0.4702,
      "step": 51125
    },
    {
      "epoch": 1.5705464934107456,
      "grad_norm": 0.4090949594974518,
      "learning_rate": 2.197119328787167e-06,
      "loss": 0.4498,
      "step": 51126
    },
    {
      "epoch": 1.5705772125456947,
      "grad_norm": 0.4323732554912567,
      "learning_rate": 2.1968170864500725e-06,
      "loss": 0.449,
      "step": 51127
    },
    {
      "epoch": 1.5706079316806438,
      "grad_norm": 0.4076296389102936,
      "learning_rate": 2.1965148623378573e-06,
      "loss": 0.5127,
      "step": 51128
    },
    {
      "epoch": 1.5706386508155932,
      "grad_norm": 0.46117040514945984,
      "learning_rate": 2.1962126564512263e-06,
      "loss": 0.4169,
      "step": 51129
    },
    {
      "epoch": 1.5706693699505423,
      "grad_norm": 0.41688865423202515,
      "learning_rate": 2.195910468790886e-06,
      "loss": 0.4703,
      "step": 51130
    },
    {
      "epoch": 1.5707000890854914,
      "grad_norm": 0.4470817446708679,
      "learning_rate": 2.1956082993575444e-06,
      "loss": 0.4682,
      "step": 51131
    },
    {
      "epoch": 1.5707308082204405,
      "grad_norm": 0.4227360486984253,
      "learning_rate": 2.195306148151902e-06,
      "loss": 0.5024,
      "step": 51132
    },
    {
      "epoch": 1.5707615273553897,
      "grad_norm": 0.44536474347114563,
      "learning_rate": 2.1950040151746675e-06,
      "loss": 0.4811,
      "step": 51133
    },
    {
      "epoch": 1.5707922464903388,
      "grad_norm": 0.4394756257534027,
      "learning_rate": 2.194701900426546e-06,
      "loss": 0.5025,
      "step": 51134
    },
    {
      "epoch": 1.570822965625288,
      "grad_norm": 0.44835785031318665,
      "learning_rate": 2.194399803908246e-06,
      "loss": 0.406,
      "step": 51135
    },
    {
      "epoch": 1.570853684760237,
      "grad_norm": 0.4221373200416565,
      "learning_rate": 2.1940977256204677e-06,
      "loss": 0.4975,
      "step": 51136
    },
    {
      "epoch": 1.5708844038951864,
      "grad_norm": 0.43310678005218506,
      "learning_rate": 2.1937956655639214e-06,
      "loss": 0.4825,
      "step": 51137
    },
    {
      "epoch": 1.5709151230301355,
      "grad_norm": 0.4002628028392792,
      "learning_rate": 2.1934936237393057e-06,
      "loss": 0.4176,
      "step": 51138
    },
    {
      "epoch": 1.5709458421650846,
      "grad_norm": 0.8594396114349365,
      "learning_rate": 2.1931916001473363e-06,
      "loss": 0.4878,
      "step": 51139
    },
    {
      "epoch": 1.570976561300034,
      "grad_norm": 0.5501646399497986,
      "learning_rate": 2.192889594788711e-06,
      "loss": 0.4667,
      "step": 51140
    },
    {
      "epoch": 1.571007280434983,
      "grad_norm": 0.400106817483902,
      "learning_rate": 2.1925876076641395e-06,
      "loss": 0.4816,
      "step": 51141
    },
    {
      "epoch": 1.5710379995699322,
      "grad_norm": 0.43395698070526123,
      "learning_rate": 2.192285638774322e-06,
      "loss": 0.4603,
      "step": 51142
    },
    {
      "epoch": 1.5710687187048813,
      "grad_norm": 0.4151780307292938,
      "learning_rate": 2.191983688119966e-06,
      "loss": 0.4326,
      "step": 51143
    },
    {
      "epoch": 1.5710994378398304,
      "grad_norm": 0.4100247025489807,
      "learning_rate": 2.191681755701778e-06,
      "loss": 0.4458,
      "step": 51144
    },
    {
      "epoch": 1.5711301569747795,
      "grad_norm": 0.3935288190841675,
      "learning_rate": 2.1913798415204657e-06,
      "loss": 0.457,
      "step": 51145
    },
    {
      "epoch": 1.5711608761097287,
      "grad_norm": 0.7830619215965271,
      "learning_rate": 2.1910779455767282e-06,
      "loss": 0.4302,
      "step": 51146
    },
    {
      "epoch": 1.5711915952446778,
      "grad_norm": 0.43128493428230286,
      "learning_rate": 2.1907760678712707e-06,
      "loss": 0.4551,
      "step": 51147
    },
    {
      "epoch": 1.5712223143796271,
      "grad_norm": 0.4356004595756531,
      "learning_rate": 2.190474208404806e-06,
      "loss": 0.4408,
      "step": 51148
    },
    {
      "epoch": 1.5712530335145762,
      "grad_norm": 0.4502919316291809,
      "learning_rate": 2.190172367178033e-06,
      "loss": 0.5127,
      "step": 51149
    },
    {
      "epoch": 1.5712837526495254,
      "grad_norm": 0.42921119928359985,
      "learning_rate": 2.189870544191659e-06,
      "loss": 0.4487,
      "step": 51150
    },
    {
      "epoch": 1.5713144717844747,
      "grad_norm": 0.39093032479286194,
      "learning_rate": 2.189568739446386e-06,
      "loss": 0.4717,
      "step": 51151
    },
    {
      "epoch": 1.5713451909194238,
      "grad_norm": 0.4326925277709961,
      "learning_rate": 2.18926695294292e-06,
      "loss": 0.4635,
      "step": 51152
    },
    {
      "epoch": 1.571375910054373,
      "grad_norm": 0.4336925745010376,
      "learning_rate": 2.188965184681967e-06,
      "loss": 0.479,
      "step": 51153
    },
    {
      "epoch": 1.571406629189322,
      "grad_norm": 0.402128666639328,
      "learning_rate": 2.1886634346642344e-06,
      "loss": 0.4227,
      "step": 51154
    },
    {
      "epoch": 1.5714373483242712,
      "grad_norm": 0.4230092763900757,
      "learning_rate": 2.1883617028904204e-06,
      "loss": 0.4419,
      "step": 51155
    },
    {
      "epoch": 1.5714680674592203,
      "grad_norm": 0.40937742590904236,
      "learning_rate": 2.188059989361233e-06,
      "loss": 0.4456,
      "step": 51156
    },
    {
      "epoch": 1.5714987865941694,
      "grad_norm": 0.5540826916694641,
      "learning_rate": 2.187758294077378e-06,
      "loss": 0.4092,
      "step": 51157
    },
    {
      "epoch": 1.5715295057291185,
      "grad_norm": 0.4173465073108673,
      "learning_rate": 2.187456617039562e-06,
      "loss": 0.465,
      "step": 51158
    },
    {
      "epoch": 1.5715602248640679,
      "grad_norm": 0.42602914571762085,
      "learning_rate": 2.187154958248483e-06,
      "loss": 0.4391,
      "step": 51159
    },
    {
      "epoch": 1.571590943999017,
      "grad_norm": 0.419554203748703,
      "learning_rate": 2.186853317704849e-06,
      "loss": 0.4348,
      "step": 51160
    },
    {
      "epoch": 1.5716216631339661,
      "grad_norm": 0.4177328646183014,
      "learning_rate": 2.1865516954093657e-06,
      "loss": 0.4546,
      "step": 51161
    },
    {
      "epoch": 1.5716523822689155,
      "grad_norm": 0.43922075629234314,
      "learning_rate": 2.1862500913627394e-06,
      "loss": 0.4872,
      "step": 51162
    },
    {
      "epoch": 1.5716831014038646,
      "grad_norm": 0.40120530128479004,
      "learning_rate": 2.1859485055656683e-06,
      "loss": 0.4165,
      "step": 51163
    },
    {
      "epoch": 1.5717138205388137,
      "grad_norm": 0.4277522563934326,
      "learning_rate": 2.1856469380188627e-06,
      "loss": 0.4497,
      "step": 51164
    },
    {
      "epoch": 1.5717445396737628,
      "grad_norm": 0.5417241454124451,
      "learning_rate": 2.1853453887230192e-06,
      "loss": 0.4798,
      "step": 51165
    },
    {
      "epoch": 1.571775258808712,
      "grad_norm": 0.40495869517326355,
      "learning_rate": 2.1850438576788503e-06,
      "loss": 0.4713,
      "step": 51166
    },
    {
      "epoch": 1.571805977943661,
      "grad_norm": 0.6771047115325928,
      "learning_rate": 2.1847423448870606e-06,
      "loss": 0.4493,
      "step": 51167
    },
    {
      "epoch": 1.5718366970786102,
      "grad_norm": 0.4345097839832306,
      "learning_rate": 2.1844408503483473e-06,
      "loss": 0.5363,
      "step": 51168
    },
    {
      "epoch": 1.5718674162135593,
      "grad_norm": 0.4874346852302551,
      "learning_rate": 2.1841393740634185e-06,
      "loss": 0.4202,
      "step": 51169
    },
    {
      "epoch": 1.5718981353485086,
      "grad_norm": 0.4007548987865448,
      "learning_rate": 2.183837916032978e-06,
      "loss": 0.489,
      "step": 51170
    },
    {
      "epoch": 1.5719288544834578,
      "grad_norm": 0.4070875644683838,
      "learning_rate": 2.1835364762577328e-06,
      "loss": 0.4402,
      "step": 51171
    },
    {
      "epoch": 1.5719595736184069,
      "grad_norm": 0.4419863522052765,
      "learning_rate": 2.183235054738382e-06,
      "loss": 0.4146,
      "step": 51172
    },
    {
      "epoch": 1.5719902927533562,
      "grad_norm": 0.44919881224632263,
      "learning_rate": 2.182933651475633e-06,
      "loss": 0.4077,
      "step": 51173
    },
    {
      "epoch": 1.5720210118883053,
      "grad_norm": 0.396553099155426,
      "learning_rate": 2.1826322664701838e-06,
      "loss": 0.4596,
      "step": 51174
    },
    {
      "epoch": 1.5720517310232545,
      "grad_norm": 0.39423778653144836,
      "learning_rate": 2.1823308997227476e-06,
      "loss": 0.4587,
      "step": 51175
    },
    {
      "epoch": 1.5720824501582036,
      "grad_norm": 0.41305696964263916,
      "learning_rate": 2.182029551234022e-06,
      "loss": 0.4526,
      "step": 51176
    },
    {
      "epoch": 1.5721131692931527,
      "grad_norm": 0.4491053819656372,
      "learning_rate": 2.181728221004714e-06,
      "loss": 0.5051,
      "step": 51177
    },
    {
      "epoch": 1.5721438884281018,
      "grad_norm": 0.42297548055648804,
      "learning_rate": 2.1814269090355246e-06,
      "loss": 0.4887,
      "step": 51178
    },
    {
      "epoch": 1.572174607563051,
      "grad_norm": 0.4518032670021057,
      "learning_rate": 2.1811256153271563e-06,
      "loss": 0.4321,
      "step": 51179
    },
    {
      "epoch": 1.572205326698,
      "grad_norm": 0.40682709217071533,
      "learning_rate": 2.1808243398803174e-06,
      "loss": 0.4308,
      "step": 51180
    },
    {
      "epoch": 1.5722360458329492,
      "grad_norm": 0.4394591450691223,
      "learning_rate": 2.180523082695711e-06,
      "loss": 0.4286,
      "step": 51181
    },
    {
      "epoch": 1.5722667649678985,
      "grad_norm": 0.4230804145336151,
      "learning_rate": 2.1802218437740365e-06,
      "loss": 0.4979,
      "step": 51182
    },
    {
      "epoch": 1.5722974841028476,
      "grad_norm": 0.43764185905456543,
      "learning_rate": 2.179920623116e-06,
      "loss": 0.4609,
      "step": 51183
    },
    {
      "epoch": 1.572328203237797,
      "grad_norm": 0.4287908673286438,
      "learning_rate": 2.1796194207223052e-06,
      "loss": 0.5007,
      "step": 51184
    },
    {
      "epoch": 1.572358922372746,
      "grad_norm": 0.4269600808620453,
      "learning_rate": 2.179318236593655e-06,
      "loss": 0.48,
      "step": 51185
    },
    {
      "epoch": 1.5723896415076952,
      "grad_norm": 0.4351450502872467,
      "learning_rate": 2.1790170707307566e-06,
      "loss": 0.4966,
      "step": 51186
    },
    {
      "epoch": 1.5724203606426443,
      "grad_norm": 0.48809880018234253,
      "learning_rate": 2.178715923134307e-06,
      "loss": 0.4842,
      "step": 51187
    },
    {
      "epoch": 1.5724510797775935,
      "grad_norm": 0.42076554894447327,
      "learning_rate": 2.1784147938050124e-06,
      "loss": 0.5204,
      "step": 51188
    },
    {
      "epoch": 1.5724817989125426,
      "grad_norm": 0.4371070861816406,
      "learning_rate": 2.1781136827435766e-06,
      "loss": 0.5238,
      "step": 51189
    },
    {
      "epoch": 1.5725125180474917,
      "grad_norm": 0.4698943495750427,
      "learning_rate": 2.177812589950705e-06,
      "loss": 0.5254,
      "step": 51190
    },
    {
      "epoch": 1.5725432371824408,
      "grad_norm": 0.41589003801345825,
      "learning_rate": 2.1775115154270955e-06,
      "loss": 0.4781,
      "step": 51191
    },
    {
      "epoch": 1.57257395631739,
      "grad_norm": 0.4888370931148529,
      "learning_rate": 2.1772104591734546e-06,
      "loss": 0.4717,
      "step": 51192
    },
    {
      "epoch": 1.5726046754523393,
      "grad_norm": 0.4496086537837982,
      "learning_rate": 2.176909421190485e-06,
      "loss": 0.469,
      "step": 51193
    },
    {
      "epoch": 1.5726353945872884,
      "grad_norm": 0.479978084564209,
      "learning_rate": 2.1766084014788924e-06,
      "loss": 0.4412,
      "step": 51194
    },
    {
      "epoch": 1.5726661137222377,
      "grad_norm": 0.44487959146499634,
      "learning_rate": 2.1763074000393747e-06,
      "loss": 0.5689,
      "step": 51195
    },
    {
      "epoch": 1.5726968328571869,
      "grad_norm": 0.4452986419200897,
      "learning_rate": 2.176006416872637e-06,
      "loss": 0.4799,
      "step": 51196
    },
    {
      "epoch": 1.572727551992136,
      "grad_norm": 0.40775203704833984,
      "learning_rate": 2.175705451979383e-06,
      "loss": 0.542,
      "step": 51197
    },
    {
      "epoch": 1.572758271127085,
      "grad_norm": 0.43106991052627563,
      "learning_rate": 2.1754045053603178e-06,
      "loss": 0.4731,
      "step": 51198
    },
    {
      "epoch": 1.5727889902620342,
      "grad_norm": 0.49295949935913086,
      "learning_rate": 2.17510357701614e-06,
      "loss": 0.4307,
      "step": 51199
    },
    {
      "epoch": 1.5728197093969833,
      "grad_norm": 0.4424605071544647,
      "learning_rate": 2.1748026669475563e-06,
      "loss": 0.38,
      "step": 51200
    },
    {
      "epoch": 1.5728504285319325,
      "grad_norm": 0.41642335057258606,
      "learning_rate": 2.1745017751552623e-06,
      "loss": 0.4306,
      "step": 51201
    },
    {
      "epoch": 1.5728811476668816,
      "grad_norm": 0.4566936194896698,
      "learning_rate": 2.1742009016399678e-06,
      "loss": 0.4255,
      "step": 51202
    },
    {
      "epoch": 1.5729118668018307,
      "grad_norm": 0.4289725720882416,
      "learning_rate": 2.1739000464023775e-06,
      "loss": 0.5223,
      "step": 51203
    },
    {
      "epoch": 1.57294258593678,
      "grad_norm": 0.47124531865119934,
      "learning_rate": 2.173599209443187e-06,
      "loss": 0.4929,
      "step": 51204
    },
    {
      "epoch": 1.5729733050717292,
      "grad_norm": 0.42710578441619873,
      "learning_rate": 2.1732983907631054e-06,
      "loss": 0.4838,
      "step": 51205
    },
    {
      "epoch": 1.5730040242066783,
      "grad_norm": 0.4292546212673187,
      "learning_rate": 2.1729975903628254e-06,
      "loss": 0.4477,
      "step": 51206
    },
    {
      "epoch": 1.5730347433416276,
      "grad_norm": 0.4012409448623657,
      "learning_rate": 2.172696808243063e-06,
      "loss": 0.4165,
      "step": 51207
    },
    {
      "epoch": 1.5730654624765767,
      "grad_norm": 0.5335862636566162,
      "learning_rate": 2.17239604440451e-06,
      "loss": 0.4888,
      "step": 51208
    },
    {
      "epoch": 1.5730961816115259,
      "grad_norm": 0.4048107862472534,
      "learning_rate": 2.172095298847876e-06,
      "loss": 0.5102,
      "step": 51209
    },
    {
      "epoch": 1.573126900746475,
      "grad_norm": 0.4530685842037201,
      "learning_rate": 2.1717945715738542e-06,
      "loss": 0.4607,
      "step": 51210
    },
    {
      "epoch": 1.573157619881424,
      "grad_norm": 0.44173169136047363,
      "learning_rate": 2.1714938625831596e-06,
      "loss": 0.4369,
      "step": 51211
    },
    {
      "epoch": 1.5731883390163732,
      "grad_norm": 0.44568905234336853,
      "learning_rate": 2.1711931718764834e-06,
      "loss": 0.478,
      "step": 51212
    },
    {
      "epoch": 1.5732190581513223,
      "grad_norm": 0.4333825707435608,
      "learning_rate": 2.1708924994545368e-06,
      "loss": 0.4589,
      "step": 51213
    },
    {
      "epoch": 1.5732497772862715,
      "grad_norm": 0.41689741611480713,
      "learning_rate": 2.170591845318013e-06,
      "loss": 0.4767,
      "step": 51214
    },
    {
      "epoch": 1.5732804964212208,
      "grad_norm": 0.456911563873291,
      "learning_rate": 2.1702912094676198e-06,
      "loss": 0.4384,
      "step": 51215
    },
    {
      "epoch": 1.57331121555617,
      "grad_norm": 0.43668821454048157,
      "learning_rate": 2.169990591904059e-06,
      "loss": 0.4807,
      "step": 51216
    },
    {
      "epoch": 1.573341934691119,
      "grad_norm": 0.5715304017066956,
      "learning_rate": 2.1696899926280333e-06,
      "loss": 0.4427,
      "step": 51217
    },
    {
      "epoch": 1.5733726538260684,
      "grad_norm": 0.4206157624721527,
      "learning_rate": 2.1693894116402415e-06,
      "loss": 0.5194,
      "step": 51218
    },
    {
      "epoch": 1.5734033729610175,
      "grad_norm": 0.49882394075393677,
      "learning_rate": 2.1690888489413877e-06,
      "loss": 0.4876,
      "step": 51219
    },
    {
      "epoch": 1.5734340920959666,
      "grad_norm": 0.5672227144241333,
      "learning_rate": 2.1687883045321732e-06,
      "loss": 0.5041,
      "step": 51220
    },
    {
      "epoch": 1.5734648112309157,
      "grad_norm": 0.4382663369178772,
      "learning_rate": 2.168487778413301e-06,
      "loss": 0.4753,
      "step": 51221
    },
    {
      "epoch": 1.5734955303658649,
      "grad_norm": 0.4313664734363556,
      "learning_rate": 2.1681872705854747e-06,
      "loss": 0.4774,
      "step": 51222
    },
    {
      "epoch": 1.573526249500814,
      "grad_norm": 0.43925052881240845,
      "learning_rate": 2.167886781049392e-06,
      "loss": 0.4863,
      "step": 51223
    },
    {
      "epoch": 1.573556968635763,
      "grad_norm": 0.5036988258361816,
      "learning_rate": 2.1675863098057558e-06,
      "loss": 0.4835,
      "step": 51224
    },
    {
      "epoch": 1.5735876877707122,
      "grad_norm": 0.41357365250587463,
      "learning_rate": 2.167285856855269e-06,
      "loss": 0.4998,
      "step": 51225
    },
    {
      "epoch": 1.5736184069056616,
      "grad_norm": 0.45544323325157166,
      "learning_rate": 2.1669854221986364e-06,
      "loss": 0.3999,
      "step": 51226
    },
    {
      "epoch": 1.5736491260406107,
      "grad_norm": 0.4307384192943573,
      "learning_rate": 2.166685005836554e-06,
      "loss": 0.3655,
      "step": 51227
    },
    {
      "epoch": 1.5736798451755598,
      "grad_norm": 0.41572463512420654,
      "learning_rate": 2.166384607769725e-06,
      "loss": 0.5097,
      "step": 51228
    },
    {
      "epoch": 1.5737105643105092,
      "grad_norm": 0.38779404759407043,
      "learning_rate": 2.1660842279988526e-06,
      "loss": 0.3879,
      "step": 51229
    },
    {
      "epoch": 1.5737412834454583,
      "grad_norm": 0.428202360868454,
      "learning_rate": 2.16578386652464e-06,
      "loss": 0.4513,
      "step": 51230
    },
    {
      "epoch": 1.5737720025804074,
      "grad_norm": 0.4200466275215149,
      "learning_rate": 2.165483523347783e-06,
      "loss": 0.4847,
      "step": 51231
    },
    {
      "epoch": 1.5738027217153565,
      "grad_norm": 0.40522801876068115,
      "learning_rate": 2.1651831984689876e-06,
      "loss": 0.4417,
      "step": 51232
    },
    {
      "epoch": 1.5738334408503056,
      "grad_norm": 0.44220563769340515,
      "learning_rate": 2.164882891888953e-06,
      "loss": 0.543,
      "step": 51233
    },
    {
      "epoch": 1.5738641599852548,
      "grad_norm": 0.414229154586792,
      "learning_rate": 2.164582603608384e-06,
      "loss": 0.4844,
      "step": 51234
    },
    {
      "epoch": 1.5738948791202039,
      "grad_norm": 0.4576783776283264,
      "learning_rate": 2.1642823336279783e-06,
      "loss": 0.483,
      "step": 51235
    },
    {
      "epoch": 1.573925598255153,
      "grad_norm": 0.51848304271698,
      "learning_rate": 2.1639820819484402e-06,
      "loss": 0.4068,
      "step": 51236
    },
    {
      "epoch": 1.5739563173901023,
      "grad_norm": 0.3987635374069214,
      "learning_rate": 2.1636818485704635e-06,
      "loss": 0.4452,
      "step": 51237
    },
    {
      "epoch": 1.5739870365250515,
      "grad_norm": 0.4064214527606964,
      "learning_rate": 2.163381633494759e-06,
      "loss": 0.4825,
      "step": 51238
    },
    {
      "epoch": 1.5740177556600006,
      "grad_norm": 0.4963644742965698,
      "learning_rate": 2.1630814367220254e-06,
      "loss": 0.4164,
      "step": 51239
    },
    {
      "epoch": 1.57404847479495,
      "grad_norm": 0.42375698685646057,
      "learning_rate": 2.1627812582529607e-06,
      "loss": 0.5044,
      "step": 51240
    },
    {
      "epoch": 1.574079193929899,
      "grad_norm": 0.47272616624832153,
      "learning_rate": 2.162481098088269e-06,
      "loss": 0.4394,
      "step": 51241
    },
    {
      "epoch": 1.5741099130648482,
      "grad_norm": 0.4298015534877777,
      "learning_rate": 2.1621809562286457e-06,
      "loss": 0.4618,
      "step": 51242
    },
    {
      "epoch": 1.5741406321997973,
      "grad_norm": 0.4386032819747925,
      "learning_rate": 2.161880832674802e-06,
      "loss": 0.4626,
      "step": 51243
    },
    {
      "epoch": 1.5741713513347464,
      "grad_norm": 0.4831472337245941,
      "learning_rate": 2.161580727427429e-06,
      "loss": 0.4535,
      "step": 51244
    },
    {
      "epoch": 1.5742020704696955,
      "grad_norm": 0.4366350769996643,
      "learning_rate": 2.1612806404872354e-06,
      "loss": 0.4737,
      "step": 51245
    },
    {
      "epoch": 1.5742327896046446,
      "grad_norm": 0.6059355139732361,
      "learning_rate": 2.160980571854916e-06,
      "loss": 0.5166,
      "step": 51246
    },
    {
      "epoch": 1.5742635087395938,
      "grad_norm": 0.4466790556907654,
      "learning_rate": 2.1606805215311734e-06,
      "loss": 0.4261,
      "step": 51247
    },
    {
      "epoch": 1.574294227874543,
      "grad_norm": 0.4381049871444702,
      "learning_rate": 2.160380489516709e-06,
      "loss": 0.4246,
      "step": 51248
    },
    {
      "epoch": 1.5743249470094922,
      "grad_norm": 0.4377153217792511,
      "learning_rate": 2.160080475812226e-06,
      "loss": 0.513,
      "step": 51249
    },
    {
      "epoch": 1.5743556661444413,
      "grad_norm": 0.4543810486793518,
      "learning_rate": 2.15978048041842e-06,
      "loss": 0.5151,
      "step": 51250
    },
    {
      "epoch": 1.5743863852793907,
      "grad_norm": 0.43319153785705566,
      "learning_rate": 2.1594805033359933e-06,
      "loss": 0.4639,
      "step": 51251
    },
    {
      "epoch": 1.5744171044143398,
      "grad_norm": 0.42238301038742065,
      "learning_rate": 2.1591805445656488e-06,
      "loss": 0.4625,
      "step": 51252
    },
    {
      "epoch": 1.574447823549289,
      "grad_norm": 0.4350808262825012,
      "learning_rate": 2.158880604108088e-06,
      "loss": 0.4996,
      "step": 51253
    },
    {
      "epoch": 1.574478542684238,
      "grad_norm": 0.4613887667655945,
      "learning_rate": 2.1585806819640066e-06,
      "loss": 0.4292,
      "step": 51254
    },
    {
      "epoch": 1.5745092618191872,
      "grad_norm": 0.43034544587135315,
      "learning_rate": 2.1582807781341074e-06,
      "loss": 0.5044,
      "step": 51255
    },
    {
      "epoch": 1.5745399809541363,
      "grad_norm": 0.3828003704547882,
      "learning_rate": 2.1579808926190914e-06,
      "loss": 0.4278,
      "step": 51256
    },
    {
      "epoch": 1.5745707000890854,
      "grad_norm": 0.45677950978279114,
      "learning_rate": 2.157681025419658e-06,
      "loss": 0.4595,
      "step": 51257
    },
    {
      "epoch": 1.5746014192240345,
      "grad_norm": 0.4888814091682434,
      "learning_rate": 2.1573811765365117e-06,
      "loss": 0.5266,
      "step": 51258
    },
    {
      "epoch": 1.5746321383589839,
      "grad_norm": 0.4068430960178375,
      "learning_rate": 2.1570813459703466e-06,
      "loss": 0.3705,
      "step": 51259
    },
    {
      "epoch": 1.574662857493933,
      "grad_norm": 0.4267853796482086,
      "learning_rate": 2.1567815337218657e-06,
      "loss": 0.5167,
      "step": 51260
    },
    {
      "epoch": 1.574693576628882,
      "grad_norm": 0.43890029191970825,
      "learning_rate": 2.156481739791769e-06,
      "loss": 0.381,
      "step": 51261
    },
    {
      "epoch": 1.5747242957638314,
      "grad_norm": 0.45548015832901,
      "learning_rate": 2.1561819641807602e-06,
      "loss": 0.4653,
      "step": 51262
    },
    {
      "epoch": 1.5747550148987806,
      "grad_norm": 0.46697118878364563,
      "learning_rate": 2.1558822068895324e-06,
      "loss": 0.4951,
      "step": 51263
    },
    {
      "epoch": 1.5747857340337297,
      "grad_norm": 0.4152239263057709,
      "learning_rate": 2.155582467918791e-06,
      "loss": 0.4569,
      "step": 51264
    },
    {
      "epoch": 1.5748164531686788,
      "grad_norm": 0.43224817514419556,
      "learning_rate": 2.155282747269234e-06,
      "loss": 0.3799,
      "step": 51265
    },
    {
      "epoch": 1.574847172303628,
      "grad_norm": 0.405838280916214,
      "learning_rate": 2.1549830449415644e-06,
      "loss": 0.471,
      "step": 51266
    },
    {
      "epoch": 1.574877891438577,
      "grad_norm": 0.4191800653934479,
      "learning_rate": 2.154683360936477e-06,
      "loss": 0.4518,
      "step": 51267
    },
    {
      "epoch": 1.5749086105735262,
      "grad_norm": 0.43080416321754456,
      "learning_rate": 2.154383695254678e-06,
      "loss": 0.4383,
      "step": 51268
    },
    {
      "epoch": 1.5749393297084753,
      "grad_norm": 0.6087342500686646,
      "learning_rate": 2.1540840478968585e-06,
      "loss": 0.401,
      "step": 51269
    },
    {
      "epoch": 1.5749700488434246,
      "grad_norm": 0.4523673355579376,
      "learning_rate": 2.153784418863728e-06,
      "loss": 0.4223,
      "step": 51270
    },
    {
      "epoch": 1.5750007679783737,
      "grad_norm": 0.3806646466255188,
      "learning_rate": 2.15348480815598e-06,
      "loss": 0.4588,
      "step": 51271
    },
    {
      "epoch": 1.5750314871133229,
      "grad_norm": 0.4537707269191742,
      "learning_rate": 2.1531852157743184e-06,
      "loss": 0.4944,
      "step": 51272
    },
    {
      "epoch": 1.5750622062482722,
      "grad_norm": 0.4165448546409607,
      "learning_rate": 2.1528856417194356e-06,
      "loss": 0.4444,
      "step": 51273
    },
    {
      "epoch": 1.5750929253832213,
      "grad_norm": 0.44250404834747314,
      "learning_rate": 2.152586085992039e-06,
      "loss": 0.5397,
      "step": 51274
    },
    {
      "epoch": 1.5751236445181704,
      "grad_norm": 0.48928341269493103,
      "learning_rate": 2.152286548592829e-06,
      "loss": 0.4514,
      "step": 51275
    },
    {
      "epoch": 1.5751543636531196,
      "grad_norm": 0.4746861159801483,
      "learning_rate": 2.151987029522499e-06,
      "loss": 0.534,
      "step": 51276
    },
    {
      "epoch": 1.5751850827880687,
      "grad_norm": 0.4278504550457001,
      "learning_rate": 2.1516875287817527e-06,
      "loss": 0.4874,
      "step": 51277
    },
    {
      "epoch": 1.5752158019230178,
      "grad_norm": 0.45738863945007324,
      "learning_rate": 2.1513880463712845e-06,
      "loss": 0.4436,
      "step": 51278
    },
    {
      "epoch": 1.575246521057967,
      "grad_norm": 0.36373743414878845,
      "learning_rate": 2.1510885822918028e-06,
      "loss": 0.4528,
      "step": 51279
    },
    {
      "epoch": 1.575277240192916,
      "grad_norm": 0.43019425868988037,
      "learning_rate": 2.1507891365439982e-06,
      "loss": 0.4228,
      "step": 51280
    },
    {
      "epoch": 1.5753079593278654,
      "grad_norm": 0.41338470578193665,
      "learning_rate": 2.150489709128578e-06,
      "loss": 0.4328,
      "step": 51281
    },
    {
      "epoch": 1.5753386784628145,
      "grad_norm": 0.44518789649009705,
      "learning_rate": 2.1501903000462333e-06,
      "loss": 0.4498,
      "step": 51282
    },
    {
      "epoch": 1.5753693975977636,
      "grad_norm": 0.4276729226112366,
      "learning_rate": 2.1498909092976685e-06,
      "loss": 0.4724,
      "step": 51283
    },
    {
      "epoch": 1.575400116732713,
      "grad_norm": 0.4536174237728119,
      "learning_rate": 2.1495915368835807e-06,
      "loss": 0.5086,
      "step": 51284
    },
    {
      "epoch": 1.575430835867662,
      "grad_norm": 0.4290802776813507,
      "learning_rate": 2.149292182804673e-06,
      "loss": 0.4633,
      "step": 51285
    },
    {
      "epoch": 1.5754615550026112,
      "grad_norm": 0.5412916541099548,
      "learning_rate": 2.1489928470616395e-06,
      "loss": 0.5159,
      "step": 51286
    },
    {
      "epoch": 1.5754922741375603,
      "grad_norm": 0.38983118534088135,
      "learning_rate": 2.1486935296551804e-06,
      "loss": 0.4588,
      "step": 51287
    },
    {
      "epoch": 1.5755229932725094,
      "grad_norm": 0.4851240813732147,
      "learning_rate": 2.1483942305859974e-06,
      "loss": 0.4281,
      "step": 51288
    },
    {
      "epoch": 1.5755537124074586,
      "grad_norm": 0.44890424609184265,
      "learning_rate": 2.1480949498547897e-06,
      "loss": 0.4651,
      "step": 51289
    },
    {
      "epoch": 1.5755844315424077,
      "grad_norm": 0.47243085503578186,
      "learning_rate": 2.147795687462252e-06,
      "loss": 0.3892,
      "step": 51290
    },
    {
      "epoch": 1.5756151506773568,
      "grad_norm": 0.4045146107673645,
      "learning_rate": 2.147496443409086e-06,
      "loss": 0.4655,
      "step": 51291
    },
    {
      "epoch": 1.575645869812306,
      "grad_norm": 0.4062455892562866,
      "learning_rate": 2.147197217695991e-06,
      "loss": 0.4668,
      "step": 51292
    },
    {
      "epoch": 1.5756765889472553,
      "grad_norm": 0.40397554636001587,
      "learning_rate": 2.1468980103236648e-06,
      "loss": 0.4108,
      "step": 51293
    },
    {
      "epoch": 1.5757073080822044,
      "grad_norm": 0.44377467036247253,
      "learning_rate": 2.146598821292809e-06,
      "loss": 0.4782,
      "step": 51294
    },
    {
      "epoch": 1.5757380272171537,
      "grad_norm": 0.4360724985599518,
      "learning_rate": 2.1462996506041178e-06,
      "loss": 0.4466,
      "step": 51295
    },
    {
      "epoch": 1.5757687463521028,
      "grad_norm": 0.43763288855552673,
      "learning_rate": 2.1460004982582927e-06,
      "loss": 0.4591,
      "step": 51296
    },
    {
      "epoch": 1.575799465487052,
      "grad_norm": 0.41555774211883545,
      "learning_rate": 2.145701364256032e-06,
      "loss": 0.5247,
      "step": 51297
    },
    {
      "epoch": 1.575830184622001,
      "grad_norm": 0.44878706336021423,
      "learning_rate": 2.1454022485980365e-06,
      "loss": 0.5267,
      "step": 51298
    },
    {
      "epoch": 1.5758609037569502,
      "grad_norm": 0.4124695062637329,
      "learning_rate": 2.145103151285001e-06,
      "loss": 0.4511,
      "step": 51299
    },
    {
      "epoch": 1.5758916228918993,
      "grad_norm": 0.4367934763431549,
      "learning_rate": 2.1448040723176244e-06,
      "loss": 0.4696,
      "step": 51300
    },
    {
      "epoch": 1.5759223420268484,
      "grad_norm": 0.45265960693359375,
      "learning_rate": 2.144505011696606e-06,
      "loss": 0.4873,
      "step": 51301
    },
    {
      "epoch": 1.5759530611617976,
      "grad_norm": 0.4745190143585205,
      "learning_rate": 2.1442059694226492e-06,
      "loss": 0.4865,
      "step": 51302
    },
    {
      "epoch": 1.5759837802967467,
      "grad_norm": 0.40156975388526917,
      "learning_rate": 2.1439069454964435e-06,
      "loss": 0.5127,
      "step": 51303
    },
    {
      "epoch": 1.576014499431696,
      "grad_norm": 0.45124465227127075,
      "learning_rate": 2.143607939918696e-06,
      "loss": 0.4581,
      "step": 51304
    },
    {
      "epoch": 1.5760452185666451,
      "grad_norm": 0.42657798528671265,
      "learning_rate": 2.143308952690094e-06,
      "loss": 0.483,
      "step": 51305
    },
    {
      "epoch": 1.5760759377015945,
      "grad_norm": 0.439020037651062,
      "learning_rate": 2.1430099838113495e-06,
      "loss": 0.4962,
      "step": 51306
    },
    {
      "epoch": 1.5761066568365436,
      "grad_norm": 0.4163787364959717,
      "learning_rate": 2.1427110332831503e-06,
      "loss": 0.4933,
      "step": 51307
    },
    {
      "epoch": 1.5761373759714927,
      "grad_norm": 0.402164489030838,
      "learning_rate": 2.1424121011062016e-06,
      "loss": 0.4349,
      "step": 51308
    },
    {
      "epoch": 1.5761680951064418,
      "grad_norm": 0.3914424180984497,
      "learning_rate": 2.142113187281195e-06,
      "loss": 0.502,
      "step": 51309
    },
    {
      "epoch": 1.576198814241391,
      "grad_norm": 0.4266953766345978,
      "learning_rate": 2.1418142918088324e-06,
      "loss": 0.4754,
      "step": 51310
    },
    {
      "epoch": 1.57622953337634,
      "grad_norm": 0.4144758880138397,
      "learning_rate": 2.141515414689811e-06,
      "loss": 0.5235,
      "step": 51311
    },
    {
      "epoch": 1.5762602525112892,
      "grad_norm": 0.4117782711982727,
      "learning_rate": 2.1412165559248286e-06,
      "loss": 0.3811,
      "step": 51312
    },
    {
      "epoch": 1.5762909716462383,
      "grad_norm": 0.4277721345424652,
      "learning_rate": 2.1409177155145866e-06,
      "loss": 0.447,
      "step": 51313
    },
    {
      "epoch": 1.5763216907811874,
      "grad_norm": 0.43020665645599365,
      "learning_rate": 2.140618893459776e-06,
      "loss": 0.4872,
      "step": 51314
    },
    {
      "epoch": 1.5763524099161368,
      "grad_norm": 0.45079994201660156,
      "learning_rate": 2.140320089761103e-06,
      "loss": 0.4865,
      "step": 51315
    },
    {
      "epoch": 1.576383129051086,
      "grad_norm": 0.4312870502471924,
      "learning_rate": 2.1400213044192585e-06,
      "loss": 0.4041,
      "step": 51316
    },
    {
      "epoch": 1.576413848186035,
      "grad_norm": 0.47581174969673157,
      "learning_rate": 2.139722537434947e-06,
      "loss": 0.4389,
      "step": 51317
    },
    {
      "epoch": 1.5764445673209844,
      "grad_norm": 0.4029776453971863,
      "learning_rate": 2.1394237888088586e-06,
      "loss": 0.5703,
      "step": 51318
    },
    {
      "epoch": 1.5764752864559335,
      "grad_norm": 0.43929627537727356,
      "learning_rate": 2.139125058541696e-06,
      "loss": 0.3959,
      "step": 51319
    },
    {
      "epoch": 1.5765060055908826,
      "grad_norm": 0.4035773277282715,
      "learning_rate": 2.138826346634155e-06,
      "loss": 0.4434,
      "step": 51320
    },
    {
      "epoch": 1.5765367247258317,
      "grad_norm": 0.4434213936328888,
      "learning_rate": 2.138527653086937e-06,
      "loss": 0.4622,
      "step": 51321
    },
    {
      "epoch": 1.5765674438607808,
      "grad_norm": 0.444219708442688,
      "learning_rate": 2.138228977900735e-06,
      "loss": 0.4693,
      "step": 51322
    },
    {
      "epoch": 1.57659816299573,
      "grad_norm": 0.39524024724960327,
      "learning_rate": 2.137930321076247e-06,
      "loss": 0.4957,
      "step": 51323
    },
    {
      "epoch": 1.576628882130679,
      "grad_norm": 0.4499746263027191,
      "learning_rate": 2.1376316826141718e-06,
      "loss": 0.4783,
      "step": 51324
    },
    {
      "epoch": 1.5766596012656282,
      "grad_norm": 0.4261901080608368,
      "learning_rate": 2.13733306251521e-06,
      "loss": 0.4431,
      "step": 51325
    },
    {
      "epoch": 1.5766903204005775,
      "grad_norm": 0.4506816267967224,
      "learning_rate": 2.137034460780053e-06,
      "loss": 0.4084,
      "step": 51326
    },
    {
      "epoch": 1.5767210395355267,
      "grad_norm": 0.47752678394317627,
      "learning_rate": 2.1367358774094018e-06,
      "loss": 0.4853,
      "step": 51327
    },
    {
      "epoch": 1.5767517586704758,
      "grad_norm": 0.4357850253582001,
      "learning_rate": 2.136437312403953e-06,
      "loss": 0.5111,
      "step": 51328
    },
    {
      "epoch": 1.5767824778054251,
      "grad_norm": 0.4812875986099243,
      "learning_rate": 2.136138765764404e-06,
      "loss": 0.4521,
      "step": 51329
    },
    {
      "epoch": 1.5768131969403743,
      "grad_norm": 0.4362388551235199,
      "learning_rate": 2.1358402374914546e-06,
      "loss": 0.5384,
      "step": 51330
    },
    {
      "epoch": 1.5768439160753234,
      "grad_norm": 0.43303021788597107,
      "learning_rate": 2.135541727585797e-06,
      "loss": 0.4303,
      "step": 51331
    },
    {
      "epoch": 1.5768746352102725,
      "grad_norm": 0.44977059960365295,
      "learning_rate": 2.13524323604813e-06,
      "loss": 0.4665,
      "step": 51332
    },
    {
      "epoch": 1.5769053543452216,
      "grad_norm": 0.4584183692932129,
      "learning_rate": 2.134944762879153e-06,
      "loss": 0.4329,
      "step": 51333
    },
    {
      "epoch": 1.5769360734801707,
      "grad_norm": 0.46428191661834717,
      "learning_rate": 2.1346463080795645e-06,
      "loss": 0.4343,
      "step": 51334
    },
    {
      "epoch": 1.5769667926151199,
      "grad_norm": 0.43530774116516113,
      "learning_rate": 2.1343478716500556e-06,
      "loss": 0.4418,
      "step": 51335
    },
    {
      "epoch": 1.576997511750069,
      "grad_norm": 0.3977733552455902,
      "learning_rate": 2.134049453591326e-06,
      "loss": 0.4373,
      "step": 51336
    },
    {
      "epoch": 1.5770282308850183,
      "grad_norm": 0.47722509503364563,
      "learning_rate": 2.133751053904074e-06,
      "loss": 0.4479,
      "step": 51337
    },
    {
      "epoch": 1.5770589500199674,
      "grad_norm": 0.932952344417572,
      "learning_rate": 2.133452672588998e-06,
      "loss": 0.4194,
      "step": 51338
    },
    {
      "epoch": 1.5770896691549166,
      "grad_norm": 0.43566468358039856,
      "learning_rate": 2.133154309646791e-06,
      "loss": 0.5793,
      "step": 51339
    },
    {
      "epoch": 1.577120388289866,
      "grad_norm": 0.4459930956363678,
      "learning_rate": 2.1328559650781534e-06,
      "loss": 0.4863,
      "step": 51340
    },
    {
      "epoch": 1.577151107424815,
      "grad_norm": 0.5525937676429749,
      "learning_rate": 2.1325576388837743e-06,
      "loss": 0.493,
      "step": 51341
    },
    {
      "epoch": 1.5771818265597641,
      "grad_norm": 0.40844830870628357,
      "learning_rate": 2.1322593310643625e-06,
      "loss": 0.5233,
      "step": 51342
    },
    {
      "epoch": 1.5772125456947133,
      "grad_norm": 0.4455200135707855,
      "learning_rate": 2.131961041620606e-06,
      "loss": 0.4564,
      "step": 51343
    },
    {
      "epoch": 1.5772432648296624,
      "grad_norm": 0.4410606026649475,
      "learning_rate": 2.1316627705532054e-06,
      "loss": 0.4335,
      "step": 51344
    },
    {
      "epoch": 1.5772739839646115,
      "grad_norm": 0.441655695438385,
      "learning_rate": 2.131364517862855e-06,
      "loss": 0.4652,
      "step": 51345
    },
    {
      "epoch": 1.5773047030995606,
      "grad_norm": 0.5158549547195435,
      "learning_rate": 2.1310662835502517e-06,
      "loss": 0.5426,
      "step": 51346
    },
    {
      "epoch": 1.5773354222345097,
      "grad_norm": 0.4337717890739441,
      "learning_rate": 2.1307680676160914e-06,
      "loss": 0.4907,
      "step": 51347
    },
    {
      "epoch": 1.577366141369459,
      "grad_norm": 0.4640983045101166,
      "learning_rate": 2.1304698700610727e-06,
      "loss": 0.5025,
      "step": 51348
    },
    {
      "epoch": 1.5773968605044082,
      "grad_norm": 0.5081857442855835,
      "learning_rate": 2.1301716908858948e-06,
      "loss": 0.5385,
      "step": 51349
    },
    {
      "epoch": 1.5774275796393573,
      "grad_norm": 0.4024123549461365,
      "learning_rate": 2.1298735300912467e-06,
      "loss": 0.5029,
      "step": 51350
    },
    {
      "epoch": 1.5774582987743067,
      "grad_norm": 0.4241276681423187,
      "learning_rate": 2.1295753876778293e-06,
      "loss": 0.4603,
      "step": 51351
    },
    {
      "epoch": 1.5774890179092558,
      "grad_norm": 0.4458562731742859,
      "learning_rate": 2.1292772636463377e-06,
      "loss": 0.3998,
      "step": 51352
    },
    {
      "epoch": 1.577519737044205,
      "grad_norm": 0.40590426325798035,
      "learning_rate": 2.128979157997472e-06,
      "loss": 0.4502,
      "step": 51353
    },
    {
      "epoch": 1.577550456179154,
      "grad_norm": 0.4920029640197754,
      "learning_rate": 2.128681070731922e-06,
      "loss": 0.4692,
      "step": 51354
    },
    {
      "epoch": 1.5775811753141031,
      "grad_norm": 0.45061948895454407,
      "learning_rate": 2.128383001850387e-06,
      "loss": 0.4359,
      "step": 51355
    },
    {
      "epoch": 1.5776118944490523,
      "grad_norm": 0.40164899826049805,
      "learning_rate": 2.128084951353564e-06,
      "loss": 0.433,
      "step": 51356
    },
    {
      "epoch": 1.5776426135840014,
      "grad_norm": 0.3887663185596466,
      "learning_rate": 2.1277869192421496e-06,
      "loss": 0.5008,
      "step": 51357
    },
    {
      "epoch": 1.5776733327189505,
      "grad_norm": 0.46067947149276733,
      "learning_rate": 2.127488905516837e-06,
      "loss": 0.4746,
      "step": 51358
    },
    {
      "epoch": 1.5777040518538998,
      "grad_norm": 0.4206741750240326,
      "learning_rate": 2.1271909101783237e-06,
      "loss": 0.5625,
      "step": 51359
    },
    {
      "epoch": 1.577734770988849,
      "grad_norm": 0.41079431772232056,
      "learning_rate": 2.126892933227306e-06,
      "loss": 0.5024,
      "step": 51360
    },
    {
      "epoch": 1.577765490123798,
      "grad_norm": 0.4112060070037842,
      "learning_rate": 2.1265949746644832e-06,
      "loss": 0.4092,
      "step": 51361
    },
    {
      "epoch": 1.5777962092587474,
      "grad_norm": 0.4396992623806,
      "learning_rate": 2.126297034490543e-06,
      "loss": 0.4659,
      "step": 51362
    },
    {
      "epoch": 1.5778269283936965,
      "grad_norm": 0.5108360648155212,
      "learning_rate": 2.1259991127061873e-06,
      "loss": 0.5053,
      "step": 51363
    },
    {
      "epoch": 1.5778576475286457,
      "grad_norm": 0.5019897222518921,
      "learning_rate": 2.125701209312111e-06,
      "loss": 0.4734,
      "step": 51364
    },
    {
      "epoch": 1.5778883666635948,
      "grad_norm": 0.4243268668651581,
      "learning_rate": 2.125403324309009e-06,
      "loss": 0.5553,
      "step": 51365
    },
    {
      "epoch": 1.577919085798544,
      "grad_norm": 0.3981884717941284,
      "learning_rate": 2.1251054576975795e-06,
      "loss": 0.4914,
      "step": 51366
    },
    {
      "epoch": 1.577949804933493,
      "grad_norm": 0.4290470480918884,
      "learning_rate": 2.1248076094785143e-06,
      "loss": 0.4602,
      "step": 51367
    },
    {
      "epoch": 1.5779805240684421,
      "grad_norm": 0.43846285343170166,
      "learning_rate": 2.1245097796525103e-06,
      "loss": 0.4291,
      "step": 51368
    },
    {
      "epoch": 1.5780112432033913,
      "grad_norm": 0.4499295949935913,
      "learning_rate": 2.1242119682202643e-06,
      "loss": 0.4906,
      "step": 51369
    },
    {
      "epoch": 1.5780419623383406,
      "grad_norm": 0.392808198928833,
      "learning_rate": 2.1239141751824733e-06,
      "loss": 0.4543,
      "step": 51370
    },
    {
      "epoch": 1.5780726814732897,
      "grad_norm": 0.493793249130249,
      "learning_rate": 2.1236164005398286e-06,
      "loss": 0.4837,
      "step": 51371
    },
    {
      "epoch": 1.5781034006082388,
      "grad_norm": 0.42775020003318787,
      "learning_rate": 2.123318644293031e-06,
      "loss": 0.4286,
      "step": 51372
    },
    {
      "epoch": 1.5781341197431882,
      "grad_norm": 0.4138946831226349,
      "learning_rate": 2.1230209064427666e-06,
      "loss": 0.5224,
      "step": 51373
    },
    {
      "epoch": 1.5781648388781373,
      "grad_norm": 0.41673290729522705,
      "learning_rate": 2.1227231869897437e-06,
      "loss": 0.4533,
      "step": 51374
    },
    {
      "epoch": 1.5781955580130864,
      "grad_norm": 0.4645288586616516,
      "learning_rate": 2.1224254859346473e-06,
      "loss": 0.4236,
      "step": 51375
    },
    {
      "epoch": 1.5782262771480355,
      "grad_norm": 0.41056233644485474,
      "learning_rate": 2.1221278032781776e-06,
      "loss": 0.4802,
      "step": 51376
    },
    {
      "epoch": 1.5782569962829847,
      "grad_norm": 0.4381227195262909,
      "learning_rate": 2.121830139021025e-06,
      "loss": 0.4284,
      "step": 51377
    },
    {
      "epoch": 1.5782877154179338,
      "grad_norm": 0.3658640682697296,
      "learning_rate": 2.1215324931638936e-06,
      "loss": 0.4922,
      "step": 51378
    },
    {
      "epoch": 1.578318434552883,
      "grad_norm": 0.44136831164360046,
      "learning_rate": 2.12123486570747e-06,
      "loss": 0.5248,
      "step": 51379
    },
    {
      "epoch": 1.578349153687832,
      "grad_norm": 0.4299582839012146,
      "learning_rate": 2.1209372566524554e-06,
      "loss": 0.5165,
      "step": 51380
    },
    {
      "epoch": 1.5783798728227814,
      "grad_norm": 0.4362647831439972,
      "learning_rate": 2.12063966599954e-06,
      "loss": 0.5296,
      "step": 51381
    },
    {
      "epoch": 1.5784105919577305,
      "grad_norm": 0.5391342043876648,
      "learning_rate": 2.1203420937494213e-06,
      "loss": 0.4538,
      "step": 51382
    },
    {
      "epoch": 1.5784413110926796,
      "grad_norm": 0.39556777477264404,
      "learning_rate": 2.1200445399027926e-06,
      "loss": 0.4828,
      "step": 51383
    },
    {
      "epoch": 1.578472030227629,
      "grad_norm": 0.430062472820282,
      "learning_rate": 2.1197470044603506e-06,
      "loss": 0.4251,
      "step": 51384
    },
    {
      "epoch": 1.578502749362578,
      "grad_norm": 0.41072216629981995,
      "learning_rate": 2.119449487422793e-06,
      "loss": 0.5031,
      "step": 51385
    },
    {
      "epoch": 1.5785334684975272,
      "grad_norm": 0.4734558165073395,
      "learning_rate": 2.1191519887908085e-06,
      "loss": 0.5014,
      "step": 51386
    },
    {
      "epoch": 1.5785641876324763,
      "grad_norm": 0.43973562121391296,
      "learning_rate": 2.118854508565096e-06,
      "loss": 0.503,
      "step": 51387
    },
    {
      "epoch": 1.5785949067674254,
      "grad_norm": 0.4466553330421448,
      "learning_rate": 2.118557046746348e-06,
      "loss": 0.4653,
      "step": 51388
    },
    {
      "epoch": 1.5786256259023745,
      "grad_norm": 0.4288141429424286,
      "learning_rate": 2.118259603335263e-06,
      "loss": 0.4475,
      "step": 51389
    },
    {
      "epoch": 1.5786563450373237,
      "grad_norm": 0.42601633071899414,
      "learning_rate": 2.117962178332531e-06,
      "loss": 0.3465,
      "step": 51390
    },
    {
      "epoch": 1.5786870641722728,
      "grad_norm": 0.40925806760787964,
      "learning_rate": 2.117664771738849e-06,
      "loss": 0.4813,
      "step": 51391
    },
    {
      "epoch": 1.5787177833072221,
      "grad_norm": 0.41564199328422546,
      "learning_rate": 2.11736738355491e-06,
      "loss": 0.4669,
      "step": 51392
    },
    {
      "epoch": 1.5787485024421712,
      "grad_norm": 0.40629974007606506,
      "learning_rate": 2.1170700137814137e-06,
      "loss": 0.4146,
      "step": 51393
    },
    {
      "epoch": 1.5787792215771204,
      "grad_norm": 0.43789613246917725,
      "learning_rate": 2.1167726624190487e-06,
      "loss": 0.4337,
      "step": 51394
    },
    {
      "epoch": 1.5788099407120697,
      "grad_norm": 0.4454376697540283,
      "learning_rate": 2.1164753294685115e-06,
      "loss": 0.4928,
      "step": 51395
    },
    {
      "epoch": 1.5788406598470188,
      "grad_norm": 0.42053288221359253,
      "learning_rate": 2.1161780149304956e-06,
      "loss": 0.4501,
      "step": 51396
    },
    {
      "epoch": 1.578871378981968,
      "grad_norm": 0.48664048314094543,
      "learning_rate": 2.1158807188057008e-06,
      "loss": 0.4783,
      "step": 51397
    },
    {
      "epoch": 1.578902098116917,
      "grad_norm": 0.39289218187332153,
      "learning_rate": 2.115583441094814e-06,
      "loss": 0.4102,
      "step": 51398
    },
    {
      "epoch": 1.5789328172518662,
      "grad_norm": 0.38971424102783203,
      "learning_rate": 2.1152861817985327e-06,
      "loss": 0.4557,
      "step": 51399
    },
    {
      "epoch": 1.5789635363868153,
      "grad_norm": 0.4396865963935852,
      "learning_rate": 2.1149889409175508e-06,
      "loss": 0.505,
      "step": 51400
    },
    {
      "epoch": 1.5789942555217644,
      "grad_norm": 0.4209437072277069,
      "learning_rate": 2.114691718452566e-06,
      "loss": 0.4545,
      "step": 51401
    },
    {
      "epoch": 1.5790249746567135,
      "grad_norm": 0.4435839056968689,
      "learning_rate": 2.1143945144042666e-06,
      "loss": 0.4725,
      "step": 51402
    },
    {
      "epoch": 1.5790556937916627,
      "grad_norm": 0.4378321170806885,
      "learning_rate": 2.114097328773349e-06,
      "loss": 0.4601,
      "step": 51403
    },
    {
      "epoch": 1.579086412926612,
      "grad_norm": 0.4538492262363434,
      "learning_rate": 2.1138001615605084e-06,
      "loss": 0.4115,
      "step": 51404
    },
    {
      "epoch": 1.5791171320615611,
      "grad_norm": 0.4239315986633301,
      "learning_rate": 2.113503012766438e-06,
      "loss": 0.4469,
      "step": 51405
    },
    {
      "epoch": 1.5791478511965105,
      "grad_norm": 0.4112902879714966,
      "learning_rate": 2.1132058823918356e-06,
      "loss": 0.4506,
      "step": 51406
    },
    {
      "epoch": 1.5791785703314596,
      "grad_norm": 0.42952749133110046,
      "learning_rate": 2.1129087704373875e-06,
      "loss": 0.4283,
      "step": 51407
    },
    {
      "epoch": 1.5792092894664087,
      "grad_norm": 0.4370364546775818,
      "learning_rate": 2.1126116769037963e-06,
      "loss": 0.419,
      "step": 51408
    },
    {
      "epoch": 1.5792400086013578,
      "grad_norm": 0.47138065099716187,
      "learning_rate": 2.112314601791745e-06,
      "loss": 0.5044,
      "step": 51409
    },
    {
      "epoch": 1.579270727736307,
      "grad_norm": 0.37963587045669556,
      "learning_rate": 2.1120175451019386e-06,
      "loss": 0.4575,
      "step": 51410
    },
    {
      "epoch": 1.579301446871256,
      "grad_norm": 0.4330957531929016,
      "learning_rate": 2.1117205068350645e-06,
      "loss": 0.4401,
      "step": 51411
    },
    {
      "epoch": 1.5793321660062052,
      "grad_norm": 0.4451788663864136,
      "learning_rate": 2.1114234869918206e-06,
      "loss": 0.4405,
      "step": 51412
    },
    {
      "epoch": 1.5793628851411543,
      "grad_norm": 0.5435349941253662,
      "learning_rate": 2.1111264855728952e-06,
      "loss": 0.4765,
      "step": 51413
    },
    {
      "epoch": 1.5793936042761034,
      "grad_norm": 0.46363013982772827,
      "learning_rate": 2.1108295025789837e-06,
      "loss": 0.4786,
      "step": 51414
    },
    {
      "epoch": 1.5794243234110528,
      "grad_norm": 0.4040916860103607,
      "learning_rate": 2.1105325380107823e-06,
      "loss": 0.4562,
      "step": 51415
    },
    {
      "epoch": 1.5794550425460019,
      "grad_norm": 0.425996869802475,
      "learning_rate": 2.1102355918689853e-06,
      "loss": 0.5085,
      "step": 51416
    },
    {
      "epoch": 1.5794857616809512,
      "grad_norm": 0.4261171519756317,
      "learning_rate": 2.109938664154282e-06,
      "loss": 0.5121,
      "step": 51417
    },
    {
      "epoch": 1.5795164808159003,
      "grad_norm": 0.44861504435539246,
      "learning_rate": 2.1096417548673674e-06,
      "loss": 0.4071,
      "step": 51418
    },
    {
      "epoch": 1.5795471999508495,
      "grad_norm": 0.36663058400154114,
      "learning_rate": 2.1093448640089353e-06,
      "loss": 0.4565,
      "step": 51419
    },
    {
      "epoch": 1.5795779190857986,
      "grad_norm": 0.47201114892959595,
      "learning_rate": 2.1090479915796803e-06,
      "loss": 0.4396,
      "step": 51420
    },
    {
      "epoch": 1.5796086382207477,
      "grad_norm": 0.6653637290000916,
      "learning_rate": 2.1087511375802973e-06,
      "loss": 0.4728,
      "step": 51421
    },
    {
      "epoch": 1.5796393573556968,
      "grad_norm": 0.40672624111175537,
      "learning_rate": 2.1084543020114733e-06,
      "loss": 0.5044,
      "step": 51422
    },
    {
      "epoch": 1.579670076490646,
      "grad_norm": 0.47796887159347534,
      "learning_rate": 2.1081574848739063e-06,
      "loss": 0.4982,
      "step": 51423
    },
    {
      "epoch": 1.579700795625595,
      "grad_norm": 0.46075552701950073,
      "learning_rate": 2.1078606861682894e-06,
      "loss": 0.4678,
      "step": 51424
    },
    {
      "epoch": 1.5797315147605442,
      "grad_norm": 0.42981207370758057,
      "learning_rate": 2.107563905895317e-06,
      "loss": 0.5616,
      "step": 51425
    },
    {
      "epoch": 1.5797622338954935,
      "grad_norm": 0.424905389547348,
      "learning_rate": 2.1072671440556767e-06,
      "loss": 0.474,
      "step": 51426
    },
    {
      "epoch": 1.5797929530304426,
      "grad_norm": 0.4224288761615753,
      "learning_rate": 2.1069704006500657e-06,
      "loss": 0.4488,
      "step": 51427
    },
    {
      "epoch": 1.5798236721653918,
      "grad_norm": 0.9015733003616333,
      "learning_rate": 2.1066736756791773e-06,
      "loss": 0.4776,
      "step": 51428
    },
    {
      "epoch": 1.579854391300341,
      "grad_norm": 0.9866117835044861,
      "learning_rate": 2.1063769691437064e-06,
      "loss": 0.4725,
      "step": 51429
    },
    {
      "epoch": 1.5798851104352902,
      "grad_norm": 0.4051744341850281,
      "learning_rate": 2.1060802810443405e-06,
      "loss": 0.3863,
      "step": 51430
    },
    {
      "epoch": 1.5799158295702393,
      "grad_norm": 0.41762271523475647,
      "learning_rate": 2.1057836113817753e-06,
      "loss": 0.5294,
      "step": 51431
    },
    {
      "epoch": 1.5799465487051885,
      "grad_norm": 0.4229094982147217,
      "learning_rate": 2.105486960156703e-06,
      "loss": 0.4608,
      "step": 51432
    },
    {
      "epoch": 1.5799772678401376,
      "grad_norm": 0.4315008223056793,
      "learning_rate": 2.1051903273698217e-06,
      "loss": 0.4787,
      "step": 51433
    },
    {
      "epoch": 1.5800079869750867,
      "grad_norm": 0.46842506527900696,
      "learning_rate": 2.104893713021816e-06,
      "loss": 0.4306,
      "step": 51434
    },
    {
      "epoch": 1.5800387061100358,
      "grad_norm": 0.4303223490715027,
      "learning_rate": 2.104597117113385e-06,
      "loss": 0.4994,
      "step": 51435
    },
    {
      "epoch": 1.580069425244985,
      "grad_norm": 0.40594932436943054,
      "learning_rate": 2.1043005396452132e-06,
      "loss": 0.4777,
      "step": 51436
    },
    {
      "epoch": 1.5801001443799343,
      "grad_norm": 0.444540411233902,
      "learning_rate": 2.1040039806180047e-06,
      "loss": 0.4777,
      "step": 51437
    },
    {
      "epoch": 1.5801308635148834,
      "grad_norm": 0.3839181065559387,
      "learning_rate": 2.103707440032444e-06,
      "loss": 0.4475,
      "step": 51438
    },
    {
      "epoch": 1.5801615826498325,
      "grad_norm": 0.4252026379108429,
      "learning_rate": 2.103410917889226e-06,
      "loss": 0.429,
      "step": 51439
    },
    {
      "epoch": 1.5801923017847819,
      "grad_norm": 0.4417828619480133,
      "learning_rate": 2.1031144141890423e-06,
      "loss": 0.4765,
      "step": 51440
    },
    {
      "epoch": 1.580223020919731,
      "grad_norm": 0.40642064809799194,
      "learning_rate": 2.1028179289325878e-06,
      "loss": 0.4279,
      "step": 51441
    },
    {
      "epoch": 1.5802537400546801,
      "grad_norm": 0.42763736844062805,
      "learning_rate": 2.102521462120556e-06,
      "loss": 0.4199,
      "step": 51442
    },
    {
      "epoch": 1.5802844591896292,
      "grad_norm": 0.40156033635139465,
      "learning_rate": 2.1022250137536335e-06,
      "loss": 0.435,
      "step": 51443
    },
    {
      "epoch": 1.5803151783245784,
      "grad_norm": 0.4254780411720276,
      "learning_rate": 2.101928583832519e-06,
      "loss": 0.4812,
      "step": 51444
    },
    {
      "epoch": 1.5803458974595275,
      "grad_norm": 0.41864246129989624,
      "learning_rate": 2.1016321723578957e-06,
      "loss": 0.4277,
      "step": 51445
    },
    {
      "epoch": 1.5803766165944766,
      "grad_norm": 0.46957504749298096,
      "learning_rate": 2.101335779330469e-06,
      "loss": 0.4184,
      "step": 51446
    },
    {
      "epoch": 1.5804073357294257,
      "grad_norm": 0.42955440282821655,
      "learning_rate": 2.1010394047509206e-06,
      "loss": 0.4184,
      "step": 51447
    },
    {
      "epoch": 1.580438054864375,
      "grad_norm": 0.4664521813392639,
      "learning_rate": 2.1007430486199497e-06,
      "loss": 0.4807,
      "step": 51448
    },
    {
      "epoch": 1.5804687739993242,
      "grad_norm": 0.4508129358291626,
      "learning_rate": 2.100446710938242e-06,
      "loss": 0.483,
      "step": 51449
    },
    {
      "epoch": 1.5804994931342733,
      "grad_norm": 0.408189058303833,
      "learning_rate": 2.1001503917064924e-06,
      "loss": 0.4958,
      "step": 51450
    },
    {
      "epoch": 1.5805302122692226,
      "grad_norm": 0.5549511909484863,
      "learning_rate": 2.0998540909253938e-06,
      "loss": 0.4111,
      "step": 51451
    },
    {
      "epoch": 1.5805609314041718,
      "grad_norm": 0.43458905816078186,
      "learning_rate": 2.0995578085956404e-06,
      "loss": 0.4439,
      "step": 51452
    },
    {
      "epoch": 1.5805916505391209,
      "grad_norm": 0.4601070284843445,
      "learning_rate": 2.099261544717918e-06,
      "loss": 0.5827,
      "step": 51453
    },
    {
      "epoch": 1.58062236967407,
      "grad_norm": 0.5331297516822815,
      "learning_rate": 2.098965299292922e-06,
      "loss": 0.5667,
      "step": 51454
    },
    {
      "epoch": 1.5806530888090191,
      "grad_norm": 0.44351354241371155,
      "learning_rate": 2.0986690723213456e-06,
      "loss": 0.4382,
      "step": 51455
    },
    {
      "epoch": 1.5806838079439682,
      "grad_norm": 0.45281025767326355,
      "learning_rate": 2.0983728638038813e-06,
      "loss": 0.499,
      "step": 51456
    },
    {
      "epoch": 1.5807145270789174,
      "grad_norm": 0.4395676851272583,
      "learning_rate": 2.0980766737412164e-06,
      "loss": 0.4336,
      "step": 51457
    },
    {
      "epoch": 1.5807452462138665,
      "grad_norm": 0.4143924415111542,
      "learning_rate": 2.0977805021340458e-06,
      "loss": 0.5114,
      "step": 51458
    },
    {
      "epoch": 1.5807759653488158,
      "grad_norm": 0.41866275668144226,
      "learning_rate": 2.09748434898306e-06,
      "loss": 0.444,
      "step": 51459
    },
    {
      "epoch": 1.580806684483765,
      "grad_norm": 0.46673426032066345,
      "learning_rate": 2.097188214288952e-06,
      "loss": 0.4331,
      "step": 51460
    },
    {
      "epoch": 1.580837403618714,
      "grad_norm": 0.6282445788383484,
      "learning_rate": 2.0968920980524154e-06,
      "loss": 0.523,
      "step": 51461
    },
    {
      "epoch": 1.5808681227536634,
      "grad_norm": 0.4483008086681366,
      "learning_rate": 2.0965960002741357e-06,
      "loss": 0.4768,
      "step": 51462
    },
    {
      "epoch": 1.5808988418886125,
      "grad_norm": 0.440687894821167,
      "learning_rate": 2.0962999209548084e-06,
      "loss": 0.4681,
      "step": 51463
    },
    {
      "epoch": 1.5809295610235616,
      "grad_norm": 0.441599577665329,
      "learning_rate": 2.0960038600951247e-06,
      "loss": 0.4649,
      "step": 51464
    },
    {
      "epoch": 1.5809602801585108,
      "grad_norm": 0.4011429250240326,
      "learning_rate": 2.09570781769578e-06,
      "loss": 0.4141,
      "step": 51465
    },
    {
      "epoch": 1.5809909992934599,
      "grad_norm": 0.44771072268486023,
      "learning_rate": 2.095411793757458e-06,
      "loss": 0.4627,
      "step": 51466
    },
    {
      "epoch": 1.581021718428409,
      "grad_norm": 0.4247036576271057,
      "learning_rate": 2.095115788280854e-06,
      "loss": 0.5665,
      "step": 51467
    },
    {
      "epoch": 1.5810524375633581,
      "grad_norm": 0.4410945773124695,
      "learning_rate": 2.094819801266658e-06,
      "loss": 0.4632,
      "step": 51468
    },
    {
      "epoch": 1.5810831566983072,
      "grad_norm": 0.39428621530532837,
      "learning_rate": 2.094523832715566e-06,
      "loss": 0.4203,
      "step": 51469
    },
    {
      "epoch": 1.5811138758332566,
      "grad_norm": 0.42027759552001953,
      "learning_rate": 2.0942278826282637e-06,
      "loss": 0.4873,
      "step": 51470
    },
    {
      "epoch": 1.5811445949682057,
      "grad_norm": 0.43814486265182495,
      "learning_rate": 2.0939319510054455e-06,
      "loss": 0.4365,
      "step": 51471
    },
    {
      "epoch": 1.5811753141031548,
      "grad_norm": 0.45264339447021484,
      "learning_rate": 2.0936360378477973e-06,
      "loss": 0.4692,
      "step": 51472
    },
    {
      "epoch": 1.5812060332381042,
      "grad_norm": 0.3834422826766968,
      "learning_rate": 2.0933401431560196e-06,
      "loss": 0.4594,
      "step": 51473
    },
    {
      "epoch": 1.5812367523730533,
      "grad_norm": 0.4302569031715393,
      "learning_rate": 2.0930442669307947e-06,
      "loss": 0.4846,
      "step": 51474
    },
    {
      "epoch": 1.5812674715080024,
      "grad_norm": 0.45215702056884766,
      "learning_rate": 2.092748409172818e-06,
      "loss": 0.4701,
      "step": 51475
    },
    {
      "epoch": 1.5812981906429515,
      "grad_norm": 0.4532243311405182,
      "learning_rate": 2.092452569882781e-06,
      "loss": 0.4035,
      "step": 51476
    },
    {
      "epoch": 1.5813289097779006,
      "grad_norm": 0.4619532525539398,
      "learning_rate": 2.0921567490613694e-06,
      "loss": 0.4017,
      "step": 51477
    },
    {
      "epoch": 1.5813596289128498,
      "grad_norm": 0.4261418581008911,
      "learning_rate": 2.091860946709282e-06,
      "loss": 0.5293,
      "step": 51478
    },
    {
      "epoch": 1.5813903480477989,
      "grad_norm": 0.4465941786766052,
      "learning_rate": 2.091565162827204e-06,
      "loss": 0.4644,
      "step": 51479
    },
    {
      "epoch": 1.581421067182748,
      "grad_norm": 0.43599647283554077,
      "learning_rate": 2.0912693974158305e-06,
      "loss": 0.5479,
      "step": 51480
    },
    {
      "epoch": 1.5814517863176973,
      "grad_norm": 0.45870912075042725,
      "learning_rate": 2.090973650475844e-06,
      "loss": 0.4516,
      "step": 51481
    },
    {
      "epoch": 1.5814825054526465,
      "grad_norm": 0.4863225221633911,
      "learning_rate": 2.0906779220079463e-06,
      "loss": 0.5058,
      "step": 51482
    },
    {
      "epoch": 1.5815132245875956,
      "grad_norm": 0.42039796710014343,
      "learning_rate": 2.0903822120128205e-06,
      "loss": 0.4349,
      "step": 51483
    },
    {
      "epoch": 1.581543943722545,
      "grad_norm": 0.4135832190513611,
      "learning_rate": 2.0900865204911613e-06,
      "loss": 0.496,
      "step": 51484
    },
    {
      "epoch": 1.581574662857494,
      "grad_norm": 0.3989185094833374,
      "learning_rate": 2.0897908474436545e-06,
      "loss": 0.3947,
      "step": 51485
    },
    {
      "epoch": 1.5816053819924432,
      "grad_norm": 0.41744866967201233,
      "learning_rate": 2.089495192870995e-06,
      "loss": 0.4288,
      "step": 51486
    },
    {
      "epoch": 1.5816361011273923,
      "grad_norm": 0.43444713950157166,
      "learning_rate": 2.089199556773871e-06,
      "loss": 0.5292,
      "step": 51487
    },
    {
      "epoch": 1.5816668202623414,
      "grad_norm": 0.40280696749687195,
      "learning_rate": 2.0889039391529763e-06,
      "loss": 0.4803,
      "step": 51488
    },
    {
      "epoch": 1.5816975393972905,
      "grad_norm": 0.4224092364311218,
      "learning_rate": 2.0886083400089976e-06,
      "loss": 0.4438,
      "step": 51489
    },
    {
      "epoch": 1.5817282585322396,
      "grad_norm": 0.42407169938087463,
      "learning_rate": 2.0883127593426255e-06,
      "loss": 0.497,
      "step": 51490
    },
    {
      "epoch": 1.5817589776671888,
      "grad_norm": 0.4515432119369507,
      "learning_rate": 2.0880171971545515e-06,
      "loss": 0.4832,
      "step": 51491
    },
    {
      "epoch": 1.581789696802138,
      "grad_norm": 0.4536547064781189,
      "learning_rate": 2.087721653445469e-06,
      "loss": 0.5339,
      "step": 51492
    },
    {
      "epoch": 1.5818204159370872,
      "grad_norm": 0.4285491108894348,
      "learning_rate": 2.0874261282160625e-06,
      "loss": 0.443,
      "step": 51493
    },
    {
      "epoch": 1.5818511350720363,
      "grad_norm": 0.4541536867618561,
      "learning_rate": 2.087130621467025e-06,
      "loss": 0.4352,
      "step": 51494
    },
    {
      "epoch": 1.5818818542069857,
      "grad_norm": 0.4431252181529999,
      "learning_rate": 2.0868351331990468e-06,
      "loss": 0.4153,
      "step": 51495
    },
    {
      "epoch": 1.5819125733419348,
      "grad_norm": 0.7716202735900879,
      "learning_rate": 2.0865396634128166e-06,
      "loss": 0.5184,
      "step": 51496
    },
    {
      "epoch": 1.581943292476884,
      "grad_norm": 0.4108041524887085,
      "learning_rate": 2.08624421210903e-06,
      "loss": 0.4387,
      "step": 51497
    },
    {
      "epoch": 1.581974011611833,
      "grad_norm": 0.4174015522003174,
      "learning_rate": 2.085948779288368e-06,
      "loss": 0.5123,
      "step": 51498
    },
    {
      "epoch": 1.5820047307467822,
      "grad_norm": 0.4815404415130615,
      "learning_rate": 2.0856533649515263e-06,
      "loss": 0.43,
      "step": 51499
    },
    {
      "epoch": 1.5820354498817313,
      "grad_norm": 0.4784410297870636,
      "learning_rate": 2.085357969099194e-06,
      "loss": 0.3984,
      "step": 51500
    },
    {
      "epoch": 1.5820661690166804,
      "grad_norm": 0.40121790766716003,
      "learning_rate": 2.0850625917320644e-06,
      "loss": 0.4792,
      "step": 51501
    },
    {
      "epoch": 1.5820968881516295,
      "grad_norm": 0.43008914589881897,
      "learning_rate": 2.0847672328508205e-06,
      "loss": 0.4215,
      "step": 51502
    },
    {
      "epoch": 1.5821276072865789,
      "grad_norm": 0.5269017219543457,
      "learning_rate": 2.084471892456156e-06,
      "loss": 0.5023,
      "step": 51503
    },
    {
      "epoch": 1.582158326421528,
      "grad_norm": 0.4109269380569458,
      "learning_rate": 2.0841765705487594e-06,
      "loss": 0.5094,
      "step": 51504
    },
    {
      "epoch": 1.582189045556477,
      "grad_norm": 0.4718579649925232,
      "learning_rate": 2.083881267129324e-06,
      "loss": 0.4783,
      "step": 51505
    },
    {
      "epoch": 1.5822197646914264,
      "grad_norm": 0.5395808815956116,
      "learning_rate": 2.083585982198535e-06,
      "loss": 0.4471,
      "step": 51506
    },
    {
      "epoch": 1.5822504838263756,
      "grad_norm": 0.41130533814430237,
      "learning_rate": 2.0832907157570847e-06,
      "loss": 0.4626,
      "step": 51507
    },
    {
      "epoch": 1.5822812029613247,
      "grad_norm": 0.39914223551750183,
      "learning_rate": 2.0829954678056583e-06,
      "loss": 0.4258,
      "step": 51508
    },
    {
      "epoch": 1.5823119220962738,
      "grad_norm": 0.45941847562789917,
      "learning_rate": 2.0827002383449535e-06,
      "loss": 0.5096,
      "step": 51509
    },
    {
      "epoch": 1.582342641231223,
      "grad_norm": 0.4361794590950012,
      "learning_rate": 2.0824050273756522e-06,
      "loss": 0.4388,
      "step": 51510
    },
    {
      "epoch": 1.582373360366172,
      "grad_norm": 0.41708970069885254,
      "learning_rate": 2.082109834898448e-06,
      "loss": 0.4398,
      "step": 51511
    },
    {
      "epoch": 1.5824040795011212,
      "grad_norm": 0.46452537178993225,
      "learning_rate": 2.081814660914031e-06,
      "loss": 0.4851,
      "step": 51512
    },
    {
      "epoch": 1.5824347986360703,
      "grad_norm": 0.41200384497642517,
      "learning_rate": 2.0815195054230843e-06,
      "loss": 0.4717,
      "step": 51513
    },
    {
      "epoch": 1.5824655177710194,
      "grad_norm": 0.44316646456718445,
      "learning_rate": 2.0812243684263057e-06,
      "loss": 0.4427,
      "step": 51514
    },
    {
      "epoch": 1.5824962369059687,
      "grad_norm": 0.42999404668807983,
      "learning_rate": 2.0809292499243793e-06,
      "loss": 0.4069,
      "step": 51515
    },
    {
      "epoch": 1.5825269560409179,
      "grad_norm": 0.453403115272522,
      "learning_rate": 2.0806341499179984e-06,
      "loss": 0.4802,
      "step": 51516
    },
    {
      "epoch": 1.5825576751758672,
      "grad_norm": 0.39791369438171387,
      "learning_rate": 2.080339068407846e-06,
      "loss": 0.4812,
      "step": 51517
    },
    {
      "epoch": 1.5825883943108163,
      "grad_norm": 0.398024320602417,
      "learning_rate": 2.0800440053946147e-06,
      "loss": 0.3897,
      "step": 51518
    },
    {
      "epoch": 1.5826191134457654,
      "grad_norm": 0.43323808908462524,
      "learning_rate": 2.0797489608789944e-06,
      "loss": 0.4639,
      "step": 51519
    },
    {
      "epoch": 1.5826498325807146,
      "grad_norm": 0.40758374333381653,
      "learning_rate": 2.079453934861676e-06,
      "loss": 0.4704,
      "step": 51520
    },
    {
      "epoch": 1.5826805517156637,
      "grad_norm": 0.3949626684188843,
      "learning_rate": 2.0791589273433445e-06,
      "loss": 0.4893,
      "step": 51521
    },
    {
      "epoch": 1.5827112708506128,
      "grad_norm": 0.4451478123664856,
      "learning_rate": 2.078863938324689e-06,
      "loss": 0.464,
      "step": 51522
    },
    {
      "epoch": 1.582741989985562,
      "grad_norm": 0.4443039000034332,
      "learning_rate": 2.0785689678064004e-06,
      "loss": 0.4612,
      "step": 51523
    },
    {
      "epoch": 1.582772709120511,
      "grad_norm": 0.4112541079521179,
      "learning_rate": 2.07827401578917e-06,
      "loss": 0.4542,
      "step": 51524
    },
    {
      "epoch": 1.5828034282554602,
      "grad_norm": 0.4185120761394501,
      "learning_rate": 2.077979082273681e-06,
      "loss": 0.3998,
      "step": 51525
    },
    {
      "epoch": 1.5828341473904095,
      "grad_norm": 0.4321264624595642,
      "learning_rate": 2.077684167260625e-06,
      "loss": 0.4497,
      "step": 51526
    },
    {
      "epoch": 1.5828648665253586,
      "grad_norm": 0.40179508924484253,
      "learning_rate": 2.0773892707506915e-06,
      "loss": 0.3784,
      "step": 51527
    },
    {
      "epoch": 1.582895585660308,
      "grad_norm": 0.44571831822395325,
      "learning_rate": 2.0770943927445707e-06,
      "loss": 0.392,
      "step": 51528
    },
    {
      "epoch": 1.582926304795257,
      "grad_norm": 0.3974166512489319,
      "learning_rate": 2.076799533242948e-06,
      "loss": 0.4355,
      "step": 51529
    },
    {
      "epoch": 1.5829570239302062,
      "grad_norm": 0.4473199248313904,
      "learning_rate": 2.0765046922465116e-06,
      "loss": 0.4388,
      "step": 51530
    },
    {
      "epoch": 1.5829877430651553,
      "grad_norm": 0.4487309753894806,
      "learning_rate": 2.076209869755953e-06,
      "loss": 0.5302,
      "step": 51531
    },
    {
      "epoch": 1.5830184622001044,
      "grad_norm": 0.42821627855300903,
      "learning_rate": 2.0759150657719594e-06,
      "loss": 0.4168,
      "step": 51532
    },
    {
      "epoch": 1.5830491813350536,
      "grad_norm": 0.440848708152771,
      "learning_rate": 2.075620280295222e-06,
      "loss": 0.5039,
      "step": 51533
    },
    {
      "epoch": 1.5830799004700027,
      "grad_norm": 0.39908090233802795,
      "learning_rate": 2.075325513326424e-06,
      "loss": 0.4337,
      "step": 51534
    },
    {
      "epoch": 1.5831106196049518,
      "grad_norm": 0.41304948925971985,
      "learning_rate": 2.075030764866257e-06,
      "loss": 0.4147,
      "step": 51535
    },
    {
      "epoch": 1.583141338739901,
      "grad_norm": 0.4523853361606598,
      "learning_rate": 2.0747360349154087e-06,
      "loss": 0.4863,
      "step": 51536
    },
    {
      "epoch": 1.5831720578748503,
      "grad_norm": 0.4360220432281494,
      "learning_rate": 2.074441323474571e-06,
      "loss": 0.4107,
      "step": 51537
    },
    {
      "epoch": 1.5832027770097994,
      "grad_norm": 0.4236361086368561,
      "learning_rate": 2.0741466305444268e-06,
      "loss": 0.4605,
      "step": 51538
    },
    {
      "epoch": 1.5832334961447485,
      "grad_norm": 0.4403752386569977,
      "learning_rate": 2.0738519561256666e-06,
      "loss": 0.4902,
      "step": 51539
    },
    {
      "epoch": 1.5832642152796979,
      "grad_norm": 0.4137212932109833,
      "learning_rate": 2.073557300218978e-06,
      "loss": 0.4605,
      "step": 51540
    },
    {
      "epoch": 1.583294934414647,
      "grad_norm": 0.4093203842639923,
      "learning_rate": 2.073262662825053e-06,
      "loss": 0.4679,
      "step": 51541
    },
    {
      "epoch": 1.583325653549596,
      "grad_norm": 0.47377508878707886,
      "learning_rate": 2.0729680439445744e-06,
      "loss": 0.4604,
      "step": 51542
    },
    {
      "epoch": 1.5833563726845452,
      "grad_norm": 0.4636998772621155,
      "learning_rate": 2.072673443578234e-06,
      "loss": 0.4891,
      "step": 51543
    },
    {
      "epoch": 1.5833870918194943,
      "grad_norm": 0.4792397618293762,
      "learning_rate": 2.0723788617267137e-06,
      "loss": 0.4457,
      "step": 51544
    },
    {
      "epoch": 1.5834178109544434,
      "grad_norm": 0.4235636591911316,
      "learning_rate": 2.0720842983907118e-06,
      "loss": 0.4983,
      "step": 51545
    },
    {
      "epoch": 1.5834485300893926,
      "grad_norm": 0.46859878301620483,
      "learning_rate": 2.0717897535709076e-06,
      "loss": 0.4789,
      "step": 51546
    },
    {
      "epoch": 1.5834792492243417,
      "grad_norm": 0.46436020731925964,
      "learning_rate": 2.0714952272679954e-06,
      "loss": 0.4156,
      "step": 51547
    },
    {
      "epoch": 1.583509968359291,
      "grad_norm": 0.43552178144454956,
      "learning_rate": 2.0712007194826567e-06,
      "loss": 0.5031,
      "step": 51548
    },
    {
      "epoch": 1.5835406874942402,
      "grad_norm": 0.42469778656959534,
      "learning_rate": 2.0709062302155804e-06,
      "loss": 0.5013,
      "step": 51549
    },
    {
      "epoch": 1.5835714066291893,
      "grad_norm": 0.4094451069831848,
      "learning_rate": 2.070611759467461e-06,
      "loss": 0.4204,
      "step": 51550
    },
    {
      "epoch": 1.5836021257641386,
      "grad_norm": 0.41477760672569275,
      "learning_rate": 2.0703173072389794e-06,
      "loss": 0.4577,
      "step": 51551
    },
    {
      "epoch": 1.5836328448990877,
      "grad_norm": 0.4494282901287079,
      "learning_rate": 2.0700228735308283e-06,
      "loss": 0.4551,
      "step": 51552
    },
    {
      "epoch": 1.5836635640340369,
      "grad_norm": 0.4207671284675598,
      "learning_rate": 2.0697284583436895e-06,
      "loss": 0.4052,
      "step": 51553
    },
    {
      "epoch": 1.583694283168986,
      "grad_norm": 0.4129757285118103,
      "learning_rate": 2.069434061678254e-06,
      "loss": 0.4336,
      "step": 51554
    },
    {
      "epoch": 1.583725002303935,
      "grad_norm": 0.4255526065826416,
      "learning_rate": 2.0691396835352086e-06,
      "loss": 0.5019,
      "step": 51555
    },
    {
      "epoch": 1.5837557214388842,
      "grad_norm": 0.7346504330635071,
      "learning_rate": 2.068845323915244e-06,
      "loss": 0.4671,
      "step": 51556
    },
    {
      "epoch": 1.5837864405738333,
      "grad_norm": 0.4654715955257416,
      "learning_rate": 2.068550982819043e-06,
      "loss": 0.4241,
      "step": 51557
    },
    {
      "epoch": 1.5838171597087825,
      "grad_norm": 0.39096376299858093,
      "learning_rate": 2.068256660247295e-06,
      "loss": 0.4711,
      "step": 51558
    },
    {
      "epoch": 1.5838478788437318,
      "grad_norm": 0.413032591342926,
      "learning_rate": 2.0679623562006877e-06,
      "loss": 0.4462,
      "step": 51559
    },
    {
      "epoch": 1.583878597978681,
      "grad_norm": 0.4005853235721588,
      "learning_rate": 2.06766807067991e-06,
      "loss": 0.3955,
      "step": 51560
    },
    {
      "epoch": 1.58390931711363,
      "grad_norm": 0.4957294166088104,
      "learning_rate": 2.067373803685646e-06,
      "loss": 0.2821,
      "step": 51561
    },
    {
      "epoch": 1.5839400362485794,
      "grad_norm": 0.4148017466068268,
      "learning_rate": 2.067079555218584e-06,
      "loss": 0.5069,
      "step": 51562
    },
    {
      "epoch": 1.5839707553835285,
      "grad_norm": 0.4179534614086151,
      "learning_rate": 2.066785325279411e-06,
      "loss": 0.4335,
      "step": 51563
    },
    {
      "epoch": 1.5840014745184776,
      "grad_norm": 0.3905048072338104,
      "learning_rate": 2.0664911138688194e-06,
      "loss": 0.4974,
      "step": 51564
    },
    {
      "epoch": 1.5840321936534267,
      "grad_norm": 0.384879469871521,
      "learning_rate": 2.0661969209874876e-06,
      "loss": 0.4478,
      "step": 51565
    },
    {
      "epoch": 1.5840629127883759,
      "grad_norm": 0.4394342601299286,
      "learning_rate": 2.065902746636107e-06,
      "loss": 0.4643,
      "step": 51566
    },
    {
      "epoch": 1.584093631923325,
      "grad_norm": 0.456699401140213,
      "learning_rate": 2.0656085908153656e-06,
      "loss": 0.4578,
      "step": 51567
    },
    {
      "epoch": 1.584124351058274,
      "grad_norm": 0.3985871374607086,
      "learning_rate": 2.0653144535259496e-06,
      "loss": 0.4372,
      "step": 51568
    },
    {
      "epoch": 1.5841550701932232,
      "grad_norm": 0.38657820224761963,
      "learning_rate": 2.0650203347685473e-06,
      "loss": 0.4383,
      "step": 51569
    },
    {
      "epoch": 1.5841857893281726,
      "grad_norm": 0.4106266498565674,
      "learning_rate": 2.064726234543842e-06,
      "loss": 0.4076,
      "step": 51570
    },
    {
      "epoch": 1.5842165084631217,
      "grad_norm": 0.39808106422424316,
      "learning_rate": 2.0644321528525237e-06,
      "loss": 0.4627,
      "step": 51571
    },
    {
      "epoch": 1.5842472275980708,
      "grad_norm": 0.38895106315612793,
      "learning_rate": 2.0641380896952767e-06,
      "loss": 0.4333,
      "step": 51572
    },
    {
      "epoch": 1.5842779467330201,
      "grad_norm": 0.4391072392463684,
      "learning_rate": 2.0638440450727936e-06,
      "loss": 0.5001,
      "step": 51573
    },
    {
      "epoch": 1.5843086658679693,
      "grad_norm": 0.41541630029678345,
      "learning_rate": 2.0635500189857526e-06,
      "loss": 0.4198,
      "step": 51574
    },
    {
      "epoch": 1.5843393850029184,
      "grad_norm": 0.3881719708442688,
      "learning_rate": 2.063256011434849e-06,
      "loss": 0.4559,
      "step": 51575
    },
    {
      "epoch": 1.5843701041378675,
      "grad_norm": 0.42098477482795715,
      "learning_rate": 2.062962022420759e-06,
      "loss": 0.462,
      "step": 51576
    },
    {
      "epoch": 1.5844008232728166,
      "grad_norm": 0.4537997841835022,
      "learning_rate": 2.062668051944182e-06,
      "loss": 0.5856,
      "step": 51577
    },
    {
      "epoch": 1.5844315424077657,
      "grad_norm": 0.40008217096328735,
      "learning_rate": 2.062374100005795e-06,
      "loss": 0.4563,
      "step": 51578
    },
    {
      "epoch": 1.5844622615427149,
      "grad_norm": 0.4675828516483307,
      "learning_rate": 2.0620801666062896e-06,
      "loss": 0.4502,
      "step": 51579
    },
    {
      "epoch": 1.584492980677664,
      "grad_norm": 0.44907137751579285,
      "learning_rate": 2.0617862517463462e-06,
      "loss": 0.4749,
      "step": 51580
    },
    {
      "epoch": 1.5845236998126133,
      "grad_norm": 0.3938145935535431,
      "learning_rate": 2.06149235542666e-06,
      "loss": 0.4783,
      "step": 51581
    },
    {
      "epoch": 1.5845544189475624,
      "grad_norm": 0.4128713011741638,
      "learning_rate": 2.06119847764791e-06,
      "loss": 0.4992,
      "step": 51582
    },
    {
      "epoch": 1.5845851380825116,
      "grad_norm": 0.4354855418205261,
      "learning_rate": 2.0609046184107873e-06,
      "loss": 0.4931,
      "step": 51583
    },
    {
      "epoch": 1.584615857217461,
      "grad_norm": 0.45315659046173096,
      "learning_rate": 2.0606107777159743e-06,
      "loss": 0.464,
      "step": 51584
    },
    {
      "epoch": 1.58464657635241,
      "grad_norm": 0.4643416702747345,
      "learning_rate": 2.0603169555641576e-06,
      "loss": 0.5449,
      "step": 51585
    },
    {
      "epoch": 1.5846772954873591,
      "grad_norm": 0.4349600374698639,
      "learning_rate": 2.06002315195603e-06,
      "loss": 0.484,
      "step": 51586
    },
    {
      "epoch": 1.5847080146223083,
      "grad_norm": 0.4302810728549957,
      "learning_rate": 2.0597293668922704e-06,
      "loss": 0.4392,
      "step": 51587
    },
    {
      "epoch": 1.5847387337572574,
      "grad_norm": 0.5635990500450134,
      "learning_rate": 2.0594356003735696e-06,
      "loss": 0.487,
      "step": 51588
    },
    {
      "epoch": 1.5847694528922065,
      "grad_norm": 0.4567144215106964,
      "learning_rate": 2.0591418524006077e-06,
      "loss": 0.455,
      "step": 51589
    },
    {
      "epoch": 1.5848001720271556,
      "grad_norm": 0.41389960050582886,
      "learning_rate": 2.0588481229740764e-06,
      "loss": 0.5476,
      "step": 51590
    },
    {
      "epoch": 1.5848308911621047,
      "grad_norm": 0.4545830190181732,
      "learning_rate": 2.05855441209466e-06,
      "loss": 0.4755,
      "step": 51591
    },
    {
      "epoch": 1.584861610297054,
      "grad_norm": 0.4815431833267212,
      "learning_rate": 2.0582607197630456e-06,
      "loss": 0.467,
      "step": 51592
    },
    {
      "epoch": 1.5848923294320032,
      "grad_norm": 0.45430830121040344,
      "learning_rate": 2.057967045979916e-06,
      "loss": 0.4655,
      "step": 51593
    },
    {
      "epoch": 1.5849230485669523,
      "grad_norm": 0.48435765504837036,
      "learning_rate": 2.057673390745959e-06,
      "loss": 0.4577,
      "step": 51594
    },
    {
      "epoch": 1.5849537677019017,
      "grad_norm": 0.4234974682331085,
      "learning_rate": 2.0573797540618614e-06,
      "loss": 0.4067,
      "step": 51595
    },
    {
      "epoch": 1.5849844868368508,
      "grad_norm": 0.45650944113731384,
      "learning_rate": 2.057086135928309e-06,
      "loss": 0.4559,
      "step": 51596
    },
    {
      "epoch": 1.5850152059718,
      "grad_norm": 0.42365631461143494,
      "learning_rate": 2.056792536345985e-06,
      "loss": 0.5299,
      "step": 51597
    },
    {
      "epoch": 1.585045925106749,
      "grad_norm": 0.4155162572860718,
      "learning_rate": 2.0564989553155768e-06,
      "loss": 0.4496,
      "step": 51598
    },
    {
      "epoch": 1.5850766442416981,
      "grad_norm": 0.5348222851753235,
      "learning_rate": 2.05620539283777e-06,
      "loss": 0.536,
      "step": 51599
    },
    {
      "epoch": 1.5851073633766473,
      "grad_norm": 0.41480159759521484,
      "learning_rate": 2.0559118489132534e-06,
      "loss": 0.433,
      "step": 51600
    },
    {
      "epoch": 1.5851380825115964,
      "grad_norm": 0.46286889910697937,
      "learning_rate": 2.0556183235427062e-06,
      "loss": 0.4967,
      "step": 51601
    },
    {
      "epoch": 1.5851688016465455,
      "grad_norm": 0.41934263706207275,
      "learning_rate": 2.055324816726817e-06,
      "loss": 0.3955,
      "step": 51602
    },
    {
      "epoch": 1.5851995207814948,
      "grad_norm": 0.41012948751449585,
      "learning_rate": 2.0550313284662725e-06,
      "loss": 0.4959,
      "step": 51603
    },
    {
      "epoch": 1.585230239916444,
      "grad_norm": 0.48152512311935425,
      "learning_rate": 2.054737858761756e-06,
      "loss": 0.5074,
      "step": 51604
    },
    {
      "epoch": 1.585260959051393,
      "grad_norm": 0.45746901631355286,
      "learning_rate": 2.054444407613958e-06,
      "loss": 0.4527,
      "step": 51605
    },
    {
      "epoch": 1.5852916781863424,
      "grad_norm": 0.3822425305843353,
      "learning_rate": 2.0541509750235567e-06,
      "loss": 0.4867,
      "step": 51606
    },
    {
      "epoch": 1.5853223973212915,
      "grad_norm": 0.47191762924194336,
      "learning_rate": 2.0538575609912405e-06,
      "loss": 0.4647,
      "step": 51607
    },
    {
      "epoch": 1.5853531164562407,
      "grad_norm": 0.4135303199291229,
      "learning_rate": 2.053564165517695e-06,
      "loss": 0.4796,
      "step": 51608
    },
    {
      "epoch": 1.5853838355911898,
      "grad_norm": 0.4281146228313446,
      "learning_rate": 2.0532707886036086e-06,
      "loss": 0.4558,
      "step": 51609
    },
    {
      "epoch": 1.585414554726139,
      "grad_norm": 0.43455037474632263,
      "learning_rate": 2.0529774302496597e-06,
      "loss": 0.4876,
      "step": 51610
    },
    {
      "epoch": 1.585445273861088,
      "grad_norm": 0.4120994210243225,
      "learning_rate": 2.0526840904565405e-06,
      "loss": 0.3907,
      "step": 51611
    },
    {
      "epoch": 1.5854759929960371,
      "grad_norm": 0.3845430910587311,
      "learning_rate": 2.052390769224927e-06,
      "loss": 0.4058,
      "step": 51612
    },
    {
      "epoch": 1.5855067121309863,
      "grad_norm": 0.4072971045970917,
      "learning_rate": 2.052097466555515e-06,
      "loss": 0.4562,
      "step": 51613
    },
    {
      "epoch": 1.5855374312659356,
      "grad_norm": 0.39084139466285706,
      "learning_rate": 2.0518041824489822e-06,
      "loss": 0.4207,
      "step": 51614
    },
    {
      "epoch": 1.5855681504008847,
      "grad_norm": 0.47823792695999146,
      "learning_rate": 2.0515109169060177e-06,
      "loss": 0.4163,
      "step": 51615
    },
    {
      "epoch": 1.5855988695358338,
      "grad_norm": 0.44051963090896606,
      "learning_rate": 2.0512176699273033e-06,
      "loss": 0.4618,
      "step": 51616
    },
    {
      "epoch": 1.5856295886707832,
      "grad_norm": 0.3932197093963623,
      "learning_rate": 2.0509244415135245e-06,
      "loss": 0.4785,
      "step": 51617
    },
    {
      "epoch": 1.5856603078057323,
      "grad_norm": 0.4129541516304016,
      "learning_rate": 2.0506312316653666e-06,
      "loss": 0.4621,
      "step": 51618
    },
    {
      "epoch": 1.5856910269406814,
      "grad_norm": 0.47960302233695984,
      "learning_rate": 2.050338040383517e-06,
      "loss": 0.4774,
      "step": 51619
    },
    {
      "epoch": 1.5857217460756305,
      "grad_norm": 0.4137187600135803,
      "learning_rate": 2.050044867668656e-06,
      "loss": 0.4403,
      "step": 51620
    },
    {
      "epoch": 1.5857524652105797,
      "grad_norm": 0.45450320839881897,
      "learning_rate": 2.0497517135214673e-06,
      "loss": 0.5191,
      "step": 51621
    },
    {
      "epoch": 1.5857831843455288,
      "grad_norm": 0.4136688709259033,
      "learning_rate": 2.0494585779426448e-06,
      "loss": 0.5054,
      "step": 51622
    },
    {
      "epoch": 1.585813903480478,
      "grad_norm": 0.4864935874938965,
      "learning_rate": 2.049165460932864e-06,
      "loss": 0.4445,
      "step": 51623
    },
    {
      "epoch": 1.585844622615427,
      "grad_norm": 0.44273641705513,
      "learning_rate": 2.048872362492815e-06,
      "loss": 0.469,
      "step": 51624
    },
    {
      "epoch": 1.5858753417503761,
      "grad_norm": 0.45925524830818176,
      "learning_rate": 2.0485792826231776e-06,
      "loss": 0.4442,
      "step": 51625
    },
    {
      "epoch": 1.5859060608853255,
      "grad_norm": 0.4254767894744873,
      "learning_rate": 2.048286221324638e-06,
      "loss": 0.439,
      "step": 51626
    },
    {
      "epoch": 1.5859367800202746,
      "grad_norm": 0.4396025240421295,
      "learning_rate": 2.0479931785978813e-06,
      "loss": 0.493,
      "step": 51627
    },
    {
      "epoch": 1.585967499155224,
      "grad_norm": 0.42737269401550293,
      "learning_rate": 2.0477001544435948e-06,
      "loss": 0.482,
      "step": 51628
    },
    {
      "epoch": 1.585998218290173,
      "grad_norm": 0.41876348853111267,
      "learning_rate": 2.047407148862458e-06,
      "loss": 0.4797,
      "step": 51629
    },
    {
      "epoch": 1.5860289374251222,
      "grad_norm": 0.43762457370758057,
      "learning_rate": 2.047114161855157e-06,
      "loss": 0.4282,
      "step": 51630
    },
    {
      "epoch": 1.5860596565600713,
      "grad_norm": 0.4260306656360626,
      "learning_rate": 2.0468211934223757e-06,
      "loss": 0.4073,
      "step": 51631
    },
    {
      "epoch": 1.5860903756950204,
      "grad_norm": 0.5300312638282776,
      "learning_rate": 2.0465282435648014e-06,
      "loss": 0.4681,
      "step": 51632
    },
    {
      "epoch": 1.5861210948299695,
      "grad_norm": 0.42027902603149414,
      "learning_rate": 2.0462353122831137e-06,
      "loss": 0.5177,
      "step": 51633
    },
    {
      "epoch": 1.5861518139649187,
      "grad_norm": 0.4541870355606079,
      "learning_rate": 2.045942399577999e-06,
      "loss": 0.5205,
      "step": 51634
    },
    {
      "epoch": 1.5861825330998678,
      "grad_norm": 0.43562763929367065,
      "learning_rate": 2.045649505450141e-06,
      "loss": 0.4428,
      "step": 51635
    },
    {
      "epoch": 1.586213252234817,
      "grad_norm": 0.4790336489677429,
      "learning_rate": 2.045356629900227e-06,
      "loss": 0.4777,
      "step": 51636
    },
    {
      "epoch": 1.5862439713697662,
      "grad_norm": 0.4951023459434509,
      "learning_rate": 2.045063772928936e-06,
      "loss": 0.4749,
      "step": 51637
    },
    {
      "epoch": 1.5862746905047154,
      "grad_norm": 0.4548061490058899,
      "learning_rate": 2.044770934536956e-06,
      "loss": 0.4726,
      "step": 51638
    },
    {
      "epoch": 1.5863054096396647,
      "grad_norm": 0.41884568333625793,
      "learning_rate": 2.0444781147249637e-06,
      "loss": 0.5614,
      "step": 51639
    },
    {
      "epoch": 1.5863361287746138,
      "grad_norm": 0.4464145600795746,
      "learning_rate": 2.044185313493652e-06,
      "loss": 0.5085,
      "step": 51640
    },
    {
      "epoch": 1.586366847909563,
      "grad_norm": 0.4543716311454773,
      "learning_rate": 2.043892530843702e-06,
      "loss": 0.4611,
      "step": 51641
    },
    {
      "epoch": 1.586397567044512,
      "grad_norm": 0.5031290054321289,
      "learning_rate": 2.043599766775796e-06,
      "loss": 0.4874,
      "step": 51642
    },
    {
      "epoch": 1.5864282861794612,
      "grad_norm": 0.4146180748939514,
      "learning_rate": 2.043307021290617e-06,
      "loss": 0.527,
      "step": 51643
    },
    {
      "epoch": 1.5864590053144103,
      "grad_norm": 0.4245883822441101,
      "learning_rate": 2.043014294388851e-06,
      "loss": 0.4206,
      "step": 51644
    },
    {
      "epoch": 1.5864897244493594,
      "grad_norm": 0.4552573263645172,
      "learning_rate": 2.0427215860711826e-06,
      "loss": 0.4415,
      "step": 51645
    },
    {
      "epoch": 1.5865204435843085,
      "grad_norm": 0.4458865523338318,
      "learning_rate": 2.042428896338291e-06,
      "loss": 0.449,
      "step": 51646
    },
    {
      "epoch": 1.5865511627192577,
      "grad_norm": 0.4629725217819214,
      "learning_rate": 2.042136225190866e-06,
      "loss": 0.4951,
      "step": 51647
    },
    {
      "epoch": 1.586581881854207,
      "grad_norm": 0.44200360774993896,
      "learning_rate": 2.0418435726295815e-06,
      "loss": 0.4873,
      "step": 51648
    },
    {
      "epoch": 1.5866126009891561,
      "grad_norm": 0.45123255252838135,
      "learning_rate": 2.0415509386551336e-06,
      "loss": 0.565,
      "step": 51649
    },
    {
      "epoch": 1.5866433201241052,
      "grad_norm": 0.4591948688030243,
      "learning_rate": 2.041258323268196e-06,
      "loss": 0.4914,
      "step": 51650
    },
    {
      "epoch": 1.5866740392590546,
      "grad_norm": 0.47923529148101807,
      "learning_rate": 2.040965726469457e-06,
      "loss": 0.5254,
      "step": 51651
    },
    {
      "epoch": 1.5867047583940037,
      "grad_norm": 0.4242306053638458,
      "learning_rate": 2.0406731482595976e-06,
      "loss": 0.4786,
      "step": 51652
    },
    {
      "epoch": 1.5867354775289528,
      "grad_norm": 0.4132898151874542,
      "learning_rate": 2.0403805886393014e-06,
      "loss": 0.5863,
      "step": 51653
    },
    {
      "epoch": 1.586766196663902,
      "grad_norm": 0.4410291910171509,
      "learning_rate": 2.040088047609251e-06,
      "loss": 0.4819,
      "step": 51654
    },
    {
      "epoch": 1.586796915798851,
      "grad_norm": 0.43262332677841187,
      "learning_rate": 2.039795525170135e-06,
      "loss": 0.5352,
      "step": 51655
    },
    {
      "epoch": 1.5868276349338002,
      "grad_norm": 0.8856884241104126,
      "learning_rate": 2.0395030213226285e-06,
      "loss": 0.4618,
      "step": 51656
    },
    {
      "epoch": 1.5868583540687493,
      "grad_norm": 0.3973086476325989,
      "learning_rate": 2.0392105360674196e-06,
      "loss": 0.4544,
      "step": 51657
    },
    {
      "epoch": 1.5868890732036984,
      "grad_norm": 0.42536717653274536,
      "learning_rate": 2.0389180694051904e-06,
      "loss": 0.3981,
      "step": 51658
    },
    {
      "epoch": 1.5869197923386478,
      "grad_norm": 0.4004124701023102,
      "learning_rate": 2.038625621336624e-06,
      "loss": 0.4116,
      "step": 51659
    },
    {
      "epoch": 1.586950511473597,
      "grad_norm": 0.4148132801055908,
      "learning_rate": 2.038333191862406e-06,
      "loss": 0.5046,
      "step": 51660
    },
    {
      "epoch": 1.586981230608546,
      "grad_norm": 0.4929097294807434,
      "learning_rate": 2.0380407809832146e-06,
      "loss": 0.4651,
      "step": 51661
    },
    {
      "epoch": 1.5870119497434954,
      "grad_norm": 0.47315526008605957,
      "learning_rate": 2.037748388699734e-06,
      "loss": 0.5207,
      "step": 51662
    },
    {
      "epoch": 1.5870426688784445,
      "grad_norm": 0.4292652904987335,
      "learning_rate": 2.037456015012649e-06,
      "loss": 0.5061,
      "step": 51663
    },
    {
      "epoch": 1.5870733880133936,
      "grad_norm": 0.42359277606010437,
      "learning_rate": 2.037163659922644e-06,
      "loss": 0.5755,
      "step": 51664
    },
    {
      "epoch": 1.5871041071483427,
      "grad_norm": 0.4561982750892639,
      "learning_rate": 2.036871323430397e-06,
      "loss": 0.5328,
      "step": 51665
    },
    {
      "epoch": 1.5871348262832918,
      "grad_norm": 0.5146589875221252,
      "learning_rate": 2.036579005536593e-06,
      "loss": 0.4584,
      "step": 51666
    },
    {
      "epoch": 1.587165545418241,
      "grad_norm": 0.42676782608032227,
      "learning_rate": 2.0362867062419145e-06,
      "loss": 0.4375,
      "step": 51667
    },
    {
      "epoch": 1.58719626455319,
      "grad_norm": 0.4841517210006714,
      "learning_rate": 2.035994425547048e-06,
      "loss": 0.4204,
      "step": 51668
    },
    {
      "epoch": 1.5872269836881392,
      "grad_norm": 0.4181726276874542,
      "learning_rate": 2.03570216345267e-06,
      "loss": 0.5637,
      "step": 51669
    },
    {
      "epoch": 1.5872577028230885,
      "grad_norm": 0.4328630566596985,
      "learning_rate": 2.0354099199594644e-06,
      "loss": 0.5066,
      "step": 51670
    },
    {
      "epoch": 1.5872884219580377,
      "grad_norm": 0.4520435631275177,
      "learning_rate": 2.035117695068116e-06,
      "loss": 0.5172,
      "step": 51671
    },
    {
      "epoch": 1.5873191410929868,
      "grad_norm": 0.47843968868255615,
      "learning_rate": 2.0348254887793094e-06,
      "loss": 0.4203,
      "step": 51672
    },
    {
      "epoch": 1.5873498602279361,
      "grad_norm": 0.4466131329536438,
      "learning_rate": 2.034533301093722e-06,
      "loss": 0.4494,
      "step": 51673
    },
    {
      "epoch": 1.5873805793628852,
      "grad_norm": 0.5061109066009521,
      "learning_rate": 2.0342411320120402e-06,
      "loss": 0.4906,
      "step": 51674
    },
    {
      "epoch": 1.5874112984978344,
      "grad_norm": 0.46745261549949646,
      "learning_rate": 2.03394898153494e-06,
      "loss": 0.4719,
      "step": 51675
    },
    {
      "epoch": 1.5874420176327835,
      "grad_norm": 0.437360942363739,
      "learning_rate": 2.0336568496631105e-06,
      "loss": 0.4451,
      "step": 51676
    },
    {
      "epoch": 1.5874727367677326,
      "grad_norm": 0.4248431622982025,
      "learning_rate": 2.033364736397234e-06,
      "loss": 0.4649,
      "step": 51677
    },
    {
      "epoch": 1.5875034559026817,
      "grad_norm": 0.5029560327529907,
      "learning_rate": 2.0330726417379874e-06,
      "loss": 0.4468,
      "step": 51678
    },
    {
      "epoch": 1.5875341750376308,
      "grad_norm": 0.4176318943500519,
      "learning_rate": 2.03278056568606e-06,
      "loss": 0.4231,
      "step": 51679
    },
    {
      "epoch": 1.58756489417258,
      "grad_norm": 0.3951646685600281,
      "learning_rate": 2.032488508242124e-06,
      "loss": 0.4886,
      "step": 51680
    },
    {
      "epoch": 1.5875956133075293,
      "grad_norm": 0.44359564781188965,
      "learning_rate": 2.032196469406874e-06,
      "loss": 0.5113,
      "step": 51681
    },
    {
      "epoch": 1.5876263324424784,
      "grad_norm": 0.39878663420677185,
      "learning_rate": 2.031904449180981e-06,
      "loss": 0.4503,
      "step": 51682
    },
    {
      "epoch": 1.5876570515774275,
      "grad_norm": 0.40982145071029663,
      "learning_rate": 2.0316124475651367e-06,
      "loss": 0.4142,
      "step": 51683
    },
    {
      "epoch": 1.5876877707123769,
      "grad_norm": 0.4469928443431854,
      "learning_rate": 2.0313204645600104e-06,
      "loss": 0.4865,
      "step": 51684
    },
    {
      "epoch": 1.587718489847326,
      "grad_norm": 0.42257949709892273,
      "learning_rate": 2.031028500166299e-06,
      "loss": 0.5461,
      "step": 51685
    },
    {
      "epoch": 1.5877492089822751,
      "grad_norm": 0.4316432476043701,
      "learning_rate": 2.0307365543846725e-06,
      "loss": 0.4427,
      "step": 51686
    },
    {
      "epoch": 1.5877799281172242,
      "grad_norm": 0.42649516463279724,
      "learning_rate": 2.0304446272158217e-06,
      "loss": 0.4629,
      "step": 51687
    },
    {
      "epoch": 1.5878106472521734,
      "grad_norm": 0.42971205711364746,
      "learning_rate": 2.030152718660421e-06,
      "loss": 0.4215,
      "step": 51688
    },
    {
      "epoch": 1.5878413663871225,
      "grad_norm": 0.5197527408599854,
      "learning_rate": 2.0298608287191547e-06,
      "loss": 0.5352,
      "step": 51689
    },
    {
      "epoch": 1.5878720855220716,
      "grad_norm": 0.41308924555778503,
      "learning_rate": 2.0295689573927048e-06,
      "loss": 0.5045,
      "step": 51690
    },
    {
      "epoch": 1.5879028046570207,
      "grad_norm": 0.4891667366027832,
      "learning_rate": 2.0292771046817562e-06,
      "loss": 0.4735,
      "step": 51691
    },
    {
      "epoch": 1.58793352379197,
      "grad_norm": 0.4231415092945099,
      "learning_rate": 2.028985270586985e-06,
      "loss": 0.5208,
      "step": 51692
    },
    {
      "epoch": 1.5879642429269192,
      "grad_norm": 0.420337975025177,
      "learning_rate": 2.0286934551090752e-06,
      "loss": 0.4969,
      "step": 51693
    },
    {
      "epoch": 1.5879949620618683,
      "grad_norm": 0.42113858461380005,
      "learning_rate": 2.0284016582487086e-06,
      "loss": 0.4164,
      "step": 51694
    },
    {
      "epoch": 1.5880256811968176,
      "grad_norm": 0.3972536325454712,
      "learning_rate": 2.028109880006568e-06,
      "loss": 0.4322,
      "step": 51695
    },
    {
      "epoch": 1.5880564003317668,
      "grad_norm": 0.42958372831344604,
      "learning_rate": 2.027818120383335e-06,
      "loss": 0.5006,
      "step": 51696
    },
    {
      "epoch": 1.5880871194667159,
      "grad_norm": 0.42840978503227234,
      "learning_rate": 2.027526379379686e-06,
      "loss": 0.4622,
      "step": 51697
    },
    {
      "epoch": 1.588117838601665,
      "grad_norm": 0.426841139793396,
      "learning_rate": 2.0272346569963074e-06,
      "loss": 0.4629,
      "step": 51698
    },
    {
      "epoch": 1.5881485577366141,
      "grad_norm": 0.46288856863975525,
      "learning_rate": 2.026942953233878e-06,
      "loss": 0.4696,
      "step": 51699
    },
    {
      "epoch": 1.5881792768715632,
      "grad_norm": 0.4041084051132202,
      "learning_rate": 2.0266512680930837e-06,
      "loss": 0.4408,
      "step": 51700
    },
    {
      "epoch": 1.5882099960065124,
      "grad_norm": 0.4480385482311249,
      "learning_rate": 2.026359601574599e-06,
      "loss": 0.5404,
      "step": 51701
    },
    {
      "epoch": 1.5882407151414615,
      "grad_norm": 0.49749255180358887,
      "learning_rate": 2.0260679536791083e-06,
      "loss": 0.4491,
      "step": 51702
    },
    {
      "epoch": 1.5882714342764108,
      "grad_norm": 0.4131890535354614,
      "learning_rate": 2.0257763244072935e-06,
      "loss": 0.4899,
      "step": 51703
    },
    {
      "epoch": 1.58830215341136,
      "grad_norm": 0.44741523265838623,
      "learning_rate": 2.0254847137598375e-06,
      "loss": 0.4733,
      "step": 51704
    },
    {
      "epoch": 1.588332872546309,
      "grad_norm": 0.42575499415397644,
      "learning_rate": 2.0251931217374155e-06,
      "loss": 0.5028,
      "step": 51705
    },
    {
      "epoch": 1.5883635916812584,
      "grad_norm": 0.3907252252101898,
      "learning_rate": 2.024901548340713e-06,
      "loss": 0.4476,
      "step": 51706
    },
    {
      "epoch": 1.5883943108162075,
      "grad_norm": 0.5307596921920776,
      "learning_rate": 2.0246099935704087e-06,
      "loss": 0.4597,
      "step": 51707
    },
    {
      "epoch": 1.5884250299511566,
      "grad_norm": 0.42410412430763245,
      "learning_rate": 2.024318457427188e-06,
      "loss": 0.4761,
      "step": 51708
    },
    {
      "epoch": 1.5884557490861058,
      "grad_norm": 0.44838494062423706,
      "learning_rate": 2.0240269399117264e-06,
      "loss": 0.4276,
      "step": 51709
    },
    {
      "epoch": 1.5884864682210549,
      "grad_norm": 0.43476033210754395,
      "learning_rate": 2.023735441024709e-06,
      "loss": 0.5392,
      "step": 51710
    },
    {
      "epoch": 1.588517187356004,
      "grad_norm": 0.42658528685569763,
      "learning_rate": 2.023443960766809e-06,
      "loss": 0.5098,
      "step": 51711
    },
    {
      "epoch": 1.5885479064909531,
      "grad_norm": 0.38199296593666077,
      "learning_rate": 2.0231524991387153e-06,
      "loss": 0.5702,
      "step": 51712
    },
    {
      "epoch": 1.5885786256259022,
      "grad_norm": 0.44651877880096436,
      "learning_rate": 2.022861056141109e-06,
      "loss": 0.4858,
      "step": 51713
    },
    {
      "epoch": 1.5886093447608516,
      "grad_norm": 0.411713570356369,
      "learning_rate": 2.022569631774666e-06,
      "loss": 0.5023,
      "step": 51714
    },
    {
      "epoch": 1.5886400638958007,
      "grad_norm": 0.41568461060523987,
      "learning_rate": 2.02227822604007e-06,
      "loss": 0.5609,
      "step": 51715
    },
    {
      "epoch": 1.5886707830307498,
      "grad_norm": 0.4023081064224243,
      "learning_rate": 2.021986838937996e-06,
      "loss": 0.4346,
      "step": 51716
    },
    {
      "epoch": 1.5887015021656992,
      "grad_norm": 0.44454681873321533,
      "learning_rate": 2.0216954704691338e-06,
      "loss": 0.3718,
      "step": 51717
    },
    {
      "epoch": 1.5887322213006483,
      "grad_norm": 0.5036762356758118,
      "learning_rate": 2.021404120634156e-06,
      "loss": 0.3933,
      "step": 51718
    },
    {
      "epoch": 1.5887629404355974,
      "grad_norm": 0.4302188456058502,
      "learning_rate": 2.021112789433749e-06,
      "loss": 0.4368,
      "step": 51719
    },
    {
      "epoch": 1.5887936595705465,
      "grad_norm": 0.4278576970100403,
      "learning_rate": 2.0208214768685884e-06,
      "loss": 0.5402,
      "step": 51720
    },
    {
      "epoch": 1.5888243787054956,
      "grad_norm": 0.4036613702774048,
      "learning_rate": 2.0205301829393553e-06,
      "loss": 0.4434,
      "step": 51721
    },
    {
      "epoch": 1.5888550978404448,
      "grad_norm": 0.43117982149124146,
      "learning_rate": 2.020238907646732e-06,
      "loss": 0.4252,
      "step": 51722
    },
    {
      "epoch": 1.5888858169753939,
      "grad_norm": 0.431373655796051,
      "learning_rate": 2.0199476509914006e-06,
      "loss": 0.485,
      "step": 51723
    },
    {
      "epoch": 1.588916536110343,
      "grad_norm": 0.42301663756370544,
      "learning_rate": 2.019656412974037e-06,
      "loss": 0.4713,
      "step": 51724
    },
    {
      "epoch": 1.5889472552452923,
      "grad_norm": 0.510743260383606,
      "learning_rate": 2.019365193595322e-06,
      "loss": 0.523,
      "step": 51725
    },
    {
      "epoch": 1.5889779743802415,
      "grad_norm": 0.4678959548473358,
      "learning_rate": 2.0190739928559365e-06,
      "loss": 0.446,
      "step": 51726
    },
    {
      "epoch": 1.5890086935151906,
      "grad_norm": 0.4429163336753845,
      "learning_rate": 2.0187828107565653e-06,
      "loss": 0.5035,
      "step": 51727
    },
    {
      "epoch": 1.58903941265014,
      "grad_norm": 0.45092108845710754,
      "learning_rate": 2.01849164729788e-06,
      "loss": 0.4331,
      "step": 51728
    },
    {
      "epoch": 1.589070131785089,
      "grad_norm": 0.41167595982551575,
      "learning_rate": 2.018200502480566e-06,
      "loss": 0.5016,
      "step": 51729
    },
    {
      "epoch": 1.5891008509200382,
      "grad_norm": 0.4038201868534088,
      "learning_rate": 2.0179093763053015e-06,
      "loss": 0.4724,
      "step": 51730
    },
    {
      "epoch": 1.5891315700549873,
      "grad_norm": 0.4307141900062561,
      "learning_rate": 2.0176182687727674e-06,
      "loss": 0.5036,
      "step": 51731
    },
    {
      "epoch": 1.5891622891899364,
      "grad_norm": 0.4121023118495941,
      "learning_rate": 2.017327179883647e-06,
      "loss": 0.4451,
      "step": 51732
    },
    {
      "epoch": 1.5891930083248855,
      "grad_norm": 0.4430031180381775,
      "learning_rate": 2.017036109638613e-06,
      "loss": 0.5322,
      "step": 51733
    },
    {
      "epoch": 1.5892237274598346,
      "grad_norm": 0.4071022868156433,
      "learning_rate": 2.0167450580383476e-06,
      "loss": 0.4698,
      "step": 51734
    },
    {
      "epoch": 1.5892544465947838,
      "grad_norm": 0.43288713693618774,
      "learning_rate": 2.0164540250835328e-06,
      "loss": 0.4978,
      "step": 51735
    },
    {
      "epoch": 1.5892851657297329,
      "grad_norm": 0.3901468515396118,
      "learning_rate": 2.0161630107748498e-06,
      "loss": 0.4474,
      "step": 51736
    },
    {
      "epoch": 1.5893158848646822,
      "grad_norm": 0.4251845180988312,
      "learning_rate": 2.015872015112973e-06,
      "loss": 0.5057,
      "step": 51737
    },
    {
      "epoch": 1.5893466039996313,
      "grad_norm": 0.4145318269729614,
      "learning_rate": 2.015581038098584e-06,
      "loss": 0.4529,
      "step": 51738
    },
    {
      "epoch": 1.5893773231345807,
      "grad_norm": 0.4404887557029724,
      "learning_rate": 2.015290079732364e-06,
      "loss": 0.4898,
      "step": 51739
    },
    {
      "epoch": 1.5894080422695298,
      "grad_norm": 0.4361916482448578,
      "learning_rate": 2.0149991400149938e-06,
      "loss": 0.5212,
      "step": 51740
    },
    {
      "epoch": 1.589438761404479,
      "grad_norm": 0.43337345123291016,
      "learning_rate": 2.014708218947148e-06,
      "loss": 0.5195,
      "step": 51741
    },
    {
      "epoch": 1.589469480539428,
      "grad_norm": 0.42405277490615845,
      "learning_rate": 2.0144173165295123e-06,
      "loss": 0.5183,
      "step": 51742
    },
    {
      "epoch": 1.5895001996743772,
      "grad_norm": 0.4012652635574341,
      "learning_rate": 2.014126432762756e-06,
      "loss": 0.3811,
      "step": 51743
    },
    {
      "epoch": 1.5895309188093263,
      "grad_norm": 0.42851677536964417,
      "learning_rate": 2.013835567647572e-06,
      "loss": 0.4434,
      "step": 51744
    },
    {
      "epoch": 1.5895616379442754,
      "grad_norm": 0.41060179471969604,
      "learning_rate": 2.0135447211846292e-06,
      "loss": 0.4772,
      "step": 51745
    },
    {
      "epoch": 1.5895923570792245,
      "grad_norm": 0.4227462708950043,
      "learning_rate": 2.0132538933746137e-06,
      "loss": 0.5371,
      "step": 51746
    },
    {
      "epoch": 1.5896230762141736,
      "grad_norm": 0.4412018954753876,
      "learning_rate": 2.0129630842181956e-06,
      "loss": 0.4092,
      "step": 51747
    },
    {
      "epoch": 1.589653795349123,
      "grad_norm": 0.43401819467544556,
      "learning_rate": 2.012672293716066e-06,
      "loss": 0.4315,
      "step": 51748
    },
    {
      "epoch": 1.589684514484072,
      "grad_norm": 0.4703676104545593,
      "learning_rate": 2.0123815218688946e-06,
      "loss": 0.4509,
      "step": 51749
    },
    {
      "epoch": 1.5897152336190215,
      "grad_norm": 0.45224297046661377,
      "learning_rate": 2.0120907686773648e-06,
      "loss": 0.3879,
      "step": 51750
    },
    {
      "epoch": 1.5897459527539706,
      "grad_norm": 0.4033013582229614,
      "learning_rate": 2.0118000341421574e-06,
      "loss": 0.4831,
      "step": 51751
    },
    {
      "epoch": 1.5897766718889197,
      "grad_norm": 0.47039905190467834,
      "learning_rate": 2.0115093182639434e-06,
      "loss": 0.5034,
      "step": 51752
    },
    {
      "epoch": 1.5898073910238688,
      "grad_norm": 0.41112589836120605,
      "learning_rate": 2.0112186210434126e-06,
      "loss": 0.3914,
      "step": 51753
    },
    {
      "epoch": 1.589838110158818,
      "grad_norm": 0.42461249232292175,
      "learning_rate": 2.0109279424812354e-06,
      "loss": 0.4754,
      "step": 51754
    },
    {
      "epoch": 1.589868829293767,
      "grad_norm": 0.4067043364048004,
      "learning_rate": 2.0106372825780972e-06,
      "loss": 0.43,
      "step": 51755
    },
    {
      "epoch": 1.5898995484287162,
      "grad_norm": 0.44713708758354187,
      "learning_rate": 2.0103466413346705e-06,
      "loss": 0.4844,
      "step": 51756
    },
    {
      "epoch": 1.5899302675636653,
      "grad_norm": 0.397217720746994,
      "learning_rate": 2.0100560187516383e-06,
      "loss": 0.4458,
      "step": 51757
    },
    {
      "epoch": 1.5899609866986144,
      "grad_norm": 0.49369755387306213,
      "learning_rate": 2.0097654148296776e-06,
      "loss": 0.4492,
      "step": 51758
    },
    {
      "epoch": 1.5899917058335638,
      "grad_norm": 0.43780583143234253,
      "learning_rate": 2.00947482956947e-06,
      "loss": 0.4657,
      "step": 51759
    },
    {
      "epoch": 1.5900224249685129,
      "grad_norm": 0.4575705826282501,
      "learning_rate": 2.0091842629716896e-06,
      "loss": 0.5075,
      "step": 51760
    },
    {
      "epoch": 1.5900531441034622,
      "grad_norm": 0.45817428827285767,
      "learning_rate": 2.008893715037018e-06,
      "loss": 0.4619,
      "step": 51761
    },
    {
      "epoch": 1.5900838632384113,
      "grad_norm": 0.4508592486381531,
      "learning_rate": 2.0086031857661326e-06,
      "loss": 0.5045,
      "step": 51762
    },
    {
      "epoch": 1.5901145823733605,
      "grad_norm": 0.42643511295318604,
      "learning_rate": 2.008312675159716e-06,
      "loss": 0.4304,
      "step": 51763
    },
    {
      "epoch": 1.5901453015083096,
      "grad_norm": 0.5082799196243286,
      "learning_rate": 2.00802218321844e-06,
      "loss": 0.4685,
      "step": 51764
    },
    {
      "epoch": 1.5901760206432587,
      "grad_norm": 0.434880793094635,
      "learning_rate": 2.007731709942986e-06,
      "loss": 0.4414,
      "step": 51765
    },
    {
      "epoch": 1.5902067397782078,
      "grad_norm": 0.43213391304016113,
      "learning_rate": 2.007441255334033e-06,
      "loss": 0.448,
      "step": 51766
    },
    {
      "epoch": 1.590237458913157,
      "grad_norm": 0.4097510874271393,
      "learning_rate": 2.0071508193922597e-06,
      "loss": 0.4212,
      "step": 51767
    },
    {
      "epoch": 1.590268178048106,
      "grad_norm": 0.4442910850048065,
      "learning_rate": 2.0068604021183457e-06,
      "loss": 0.4801,
      "step": 51768
    },
    {
      "epoch": 1.5902988971830552,
      "grad_norm": 0.5396817922592163,
      "learning_rate": 2.0065700035129654e-06,
      "loss": 0.4198,
      "step": 51769
    },
    {
      "epoch": 1.5903296163180045,
      "grad_norm": 0.42960041761398315,
      "learning_rate": 2.006279623576799e-06,
      "loss": 0.4368,
      "step": 51770
    },
    {
      "epoch": 1.5903603354529536,
      "grad_norm": 0.420598566532135,
      "learning_rate": 2.005989262310525e-06,
      "loss": 0.4649,
      "step": 51771
    },
    {
      "epoch": 1.5903910545879028,
      "grad_norm": 0.3986513316631317,
      "learning_rate": 2.0056989197148235e-06,
      "loss": 0.473,
      "step": 51772
    },
    {
      "epoch": 1.590421773722852,
      "grad_norm": 0.44433385133743286,
      "learning_rate": 2.0054085957903692e-06,
      "loss": 0.5322,
      "step": 51773
    },
    {
      "epoch": 1.5904524928578012,
      "grad_norm": 0.42919644713401794,
      "learning_rate": 2.00511829053784e-06,
      "loss": 0.4732,
      "step": 51774
    },
    {
      "epoch": 1.5904832119927503,
      "grad_norm": 0.43765825033187866,
      "learning_rate": 2.004828003957916e-06,
      "loss": 0.4507,
      "step": 51775
    },
    {
      "epoch": 1.5905139311276995,
      "grad_norm": 0.4588463008403778,
      "learning_rate": 2.0045377360512765e-06,
      "loss": 0.4581,
      "step": 51776
    },
    {
      "epoch": 1.5905446502626486,
      "grad_norm": 0.3775562047958374,
      "learning_rate": 2.004247486818596e-06,
      "loss": 0.4198,
      "step": 51777
    },
    {
      "epoch": 1.5905753693975977,
      "grad_norm": 0.466725617647171,
      "learning_rate": 2.003957256260556e-06,
      "loss": 0.5029,
      "step": 51778
    },
    {
      "epoch": 1.5906060885325468,
      "grad_norm": 0.40555110573768616,
      "learning_rate": 2.003667044377826e-06,
      "loss": 0.4506,
      "step": 51779
    },
    {
      "epoch": 1.590636807667496,
      "grad_norm": 0.5326870083808899,
      "learning_rate": 2.003376851171097e-06,
      "loss": 0.5412,
      "step": 51780
    },
    {
      "epoch": 1.5906675268024453,
      "grad_norm": 0.45078155398368835,
      "learning_rate": 2.003086676641036e-06,
      "loss": 0.436,
      "step": 51781
    },
    {
      "epoch": 1.5906982459373944,
      "grad_norm": 0.388960599899292,
      "learning_rate": 2.0027965207883283e-06,
      "loss": 0.389,
      "step": 51782
    },
    {
      "epoch": 1.5907289650723435,
      "grad_norm": 0.42077744007110596,
      "learning_rate": 2.002506383613644e-06,
      "loss": 0.4665,
      "step": 51783
    },
    {
      "epoch": 1.5907596842072929,
      "grad_norm": 0.4470194876194,
      "learning_rate": 2.0022162651176657e-06,
      "loss": 0.4929,
      "step": 51784
    },
    {
      "epoch": 1.590790403342242,
      "grad_norm": 0.44999104738235474,
      "learning_rate": 2.001926165301069e-06,
      "loss": 0.5146,
      "step": 51785
    },
    {
      "epoch": 1.590821122477191,
      "grad_norm": 0.5003659129142761,
      "learning_rate": 2.001636084164532e-06,
      "loss": 0.4619,
      "step": 51786
    },
    {
      "epoch": 1.5908518416121402,
      "grad_norm": 0.4526515007019043,
      "learning_rate": 2.001346021708737e-06,
      "loss": 0.5546,
      "step": 51787
    },
    {
      "epoch": 1.5908825607470893,
      "grad_norm": 0.44959452748298645,
      "learning_rate": 2.00105597793435e-06,
      "loss": 0.4573,
      "step": 51788
    },
    {
      "epoch": 1.5909132798820385,
      "grad_norm": 0.4480496346950531,
      "learning_rate": 2.000765952842061e-06,
      "loss": 0.5223,
      "step": 51789
    },
    {
      "epoch": 1.5909439990169876,
      "grad_norm": 0.38370752334594727,
      "learning_rate": 2.0004759464325394e-06,
      "loss": 0.4495,
      "step": 51790
    },
    {
      "epoch": 1.5909747181519367,
      "grad_norm": 0.4558678865432739,
      "learning_rate": 2.0001859587064674e-06,
      "loss": 0.4263,
      "step": 51791
    },
    {
      "epoch": 1.591005437286886,
      "grad_norm": 0.4210686981678009,
      "learning_rate": 1.9998959896645175e-06,
      "loss": 0.4248,
      "step": 51792
    },
    {
      "epoch": 1.5910361564218352,
      "grad_norm": 0.4047652781009674,
      "learning_rate": 1.999606039307369e-06,
      "loss": 0.5308,
      "step": 51793
    },
    {
      "epoch": 1.5910668755567843,
      "grad_norm": 0.4155624806880951,
      "learning_rate": 1.9993161076356992e-06,
      "loss": 0.4247,
      "step": 51794
    },
    {
      "epoch": 1.5910975946917336,
      "grad_norm": 0.42598557472229004,
      "learning_rate": 1.9990261946501886e-06,
      "loss": 0.4858,
      "step": 51795
    },
    {
      "epoch": 1.5911283138266827,
      "grad_norm": 0.40549394488334656,
      "learning_rate": 1.998736300351508e-06,
      "loss": 0.5229,
      "step": 51796
    },
    {
      "epoch": 1.5911590329616319,
      "grad_norm": 0.3928954005241394,
      "learning_rate": 1.9984464247403378e-06,
      "loss": 0.5582,
      "step": 51797
    },
    {
      "epoch": 1.591189752096581,
      "grad_norm": 0.44840750098228455,
      "learning_rate": 1.998156567817354e-06,
      "loss": 0.5046,
      "step": 51798
    },
    {
      "epoch": 1.59122047123153,
      "grad_norm": 0.43261680006980896,
      "learning_rate": 1.9978667295832375e-06,
      "loss": 0.4199,
      "step": 51799
    },
    {
      "epoch": 1.5912511903664792,
      "grad_norm": 0.4646092355251312,
      "learning_rate": 1.99757691003866e-06,
      "loss": 0.48,
      "step": 51800
    },
    {
      "epoch": 1.5912819095014283,
      "grad_norm": 0.4497012495994568,
      "learning_rate": 1.9972871091843005e-06,
      "loss": 0.4009,
      "step": 51801
    },
    {
      "epoch": 1.5913126286363775,
      "grad_norm": 0.4394594728946686,
      "learning_rate": 1.9969973270208356e-06,
      "loss": 0.4415,
      "step": 51802
    },
    {
      "epoch": 1.5913433477713268,
      "grad_norm": 0.40744954347610474,
      "learning_rate": 1.996707563548942e-06,
      "loss": 0.4557,
      "step": 51803
    },
    {
      "epoch": 1.591374066906276,
      "grad_norm": 0.39096227288246155,
      "learning_rate": 1.9964178187692996e-06,
      "loss": 0.4421,
      "step": 51804
    },
    {
      "epoch": 1.591404786041225,
      "grad_norm": 0.4471110701560974,
      "learning_rate": 1.99612809268258e-06,
      "loss": 0.4907,
      "step": 51805
    },
    {
      "epoch": 1.5914355051761744,
      "grad_norm": 0.4209693670272827,
      "learning_rate": 1.9958383852894615e-06,
      "loss": 0.4572,
      "step": 51806
    },
    {
      "epoch": 1.5914662243111235,
      "grad_norm": 0.4584004580974579,
      "learning_rate": 1.9955486965906223e-06,
      "loss": 0.4279,
      "step": 51807
    },
    {
      "epoch": 1.5914969434460726,
      "grad_norm": 0.4383775591850281,
      "learning_rate": 1.99525902658674e-06,
      "loss": 0.5304,
      "step": 51808
    },
    {
      "epoch": 1.5915276625810217,
      "grad_norm": 0.46664053201675415,
      "learning_rate": 1.994969375278487e-06,
      "loss": 0.4751,
      "step": 51809
    },
    {
      "epoch": 1.5915583817159709,
      "grad_norm": 0.4336487054824829,
      "learning_rate": 1.994679742666543e-06,
      "loss": 0.474,
      "step": 51810
    },
    {
      "epoch": 1.59158910085092,
      "grad_norm": 0.38049551844596863,
      "learning_rate": 1.994390128751582e-06,
      "loss": 0.4404,
      "step": 51811
    },
    {
      "epoch": 1.591619819985869,
      "grad_norm": 0.45573005080223083,
      "learning_rate": 1.9941005335342857e-06,
      "loss": 0.4735,
      "step": 51812
    },
    {
      "epoch": 1.5916505391208182,
      "grad_norm": 0.4134927988052368,
      "learning_rate": 1.9938109570153242e-06,
      "loss": 0.555,
      "step": 51813
    },
    {
      "epoch": 1.5916812582557676,
      "grad_norm": 0.39761462807655334,
      "learning_rate": 1.993521399195378e-06,
      "loss": 0.4805,
      "step": 51814
    },
    {
      "epoch": 1.5917119773907167,
      "grad_norm": 0.4069465696811676,
      "learning_rate": 1.9932318600751176e-06,
      "loss": 0.5101,
      "step": 51815
    },
    {
      "epoch": 1.5917426965256658,
      "grad_norm": 0.4734784662723541,
      "learning_rate": 1.9929423396552274e-06,
      "loss": 0.3794,
      "step": 51816
    },
    {
      "epoch": 1.5917734156606151,
      "grad_norm": 0.5232639312744141,
      "learning_rate": 1.9926528379363775e-06,
      "loss": 0.4627,
      "step": 51817
    },
    {
      "epoch": 1.5918041347955643,
      "grad_norm": 0.4325466454029083,
      "learning_rate": 1.992363354919249e-06,
      "loss": 0.4499,
      "step": 51818
    },
    {
      "epoch": 1.5918348539305134,
      "grad_norm": 0.42552876472473145,
      "learning_rate": 1.9920738906045125e-06,
      "loss": 0.4452,
      "step": 51819
    },
    {
      "epoch": 1.5918655730654625,
      "grad_norm": 0.3977943956851959,
      "learning_rate": 1.9917844449928467e-06,
      "loss": 0.4747,
      "step": 51820
    },
    {
      "epoch": 1.5918962922004116,
      "grad_norm": 0.4104357659816742,
      "learning_rate": 1.9914950180849267e-06,
      "loss": 0.4163,
      "step": 51821
    },
    {
      "epoch": 1.5919270113353607,
      "grad_norm": 0.4832276403903961,
      "learning_rate": 1.99120560988143e-06,
      "loss": 0.479,
      "step": 51822
    },
    {
      "epoch": 1.5919577304703099,
      "grad_norm": 0.4182213246822357,
      "learning_rate": 1.9909162203830358e-06,
      "loss": 0.562,
      "step": 51823
    },
    {
      "epoch": 1.591988449605259,
      "grad_norm": 0.41391971707344055,
      "learning_rate": 1.9906268495904124e-06,
      "loss": 0.4964,
      "step": 51824
    },
    {
      "epoch": 1.5920191687402083,
      "grad_norm": 0.44644495844841003,
      "learning_rate": 1.990337497504239e-06,
      "loss": 0.4768,
      "step": 51825
    },
    {
      "epoch": 1.5920498878751574,
      "grad_norm": 0.3997829854488373,
      "learning_rate": 1.990048164125192e-06,
      "loss": 0.4936,
      "step": 51826
    },
    {
      "epoch": 1.5920806070101066,
      "grad_norm": 0.4316352307796478,
      "learning_rate": 1.98975884945395e-06,
      "loss": 0.4714,
      "step": 51827
    },
    {
      "epoch": 1.592111326145056,
      "grad_norm": 0.5950544476509094,
      "learning_rate": 1.9894695534911823e-06,
      "loss": 0.4497,
      "step": 51828
    },
    {
      "epoch": 1.592142045280005,
      "grad_norm": 0.4347144365310669,
      "learning_rate": 1.989180276237569e-06,
      "loss": 0.4893,
      "step": 51829
    },
    {
      "epoch": 1.5921727644149541,
      "grad_norm": 0.4966653883457184,
      "learning_rate": 1.9888910176937836e-06,
      "loss": 0.4746,
      "step": 51830
    },
    {
      "epoch": 1.5922034835499033,
      "grad_norm": 0.4547301232814789,
      "learning_rate": 1.988601777860505e-06,
      "loss": 0.4413,
      "step": 51831
    },
    {
      "epoch": 1.5922342026848524,
      "grad_norm": 0.45135676860809326,
      "learning_rate": 1.9883125567384055e-06,
      "loss": 0.4337,
      "step": 51832
    },
    {
      "epoch": 1.5922649218198015,
      "grad_norm": 0.3900907039642334,
      "learning_rate": 1.98802335432816e-06,
      "loss": 0.4457,
      "step": 51833
    },
    {
      "epoch": 1.5922956409547506,
      "grad_norm": 0.43371111154556274,
      "learning_rate": 1.9877341706304463e-06,
      "loss": 0.479,
      "step": 51834
    },
    {
      "epoch": 1.5923263600896997,
      "grad_norm": 0.48592206835746765,
      "learning_rate": 1.9874450056459417e-06,
      "loss": 0.4717,
      "step": 51835
    },
    {
      "epoch": 1.592357079224649,
      "grad_norm": 0.4422655999660492,
      "learning_rate": 1.9871558593753147e-06,
      "loss": 0.4573,
      "step": 51836
    },
    {
      "epoch": 1.5923877983595982,
      "grad_norm": 0.4193565547466278,
      "learning_rate": 1.986866731819247e-06,
      "loss": 0.4326,
      "step": 51837
    },
    {
      "epoch": 1.5924185174945473,
      "grad_norm": 0.4381276071071625,
      "learning_rate": 1.986577622978411e-06,
      "loss": 0.4666,
      "step": 51838
    },
    {
      "epoch": 1.5924492366294967,
      "grad_norm": 0.42317357659339905,
      "learning_rate": 1.9862885328534842e-06,
      "loss": 0.4389,
      "step": 51839
    },
    {
      "epoch": 1.5924799557644458,
      "grad_norm": 0.44725021719932556,
      "learning_rate": 1.9859994614451384e-06,
      "loss": 0.5372,
      "step": 51840
    },
    {
      "epoch": 1.592510674899395,
      "grad_norm": 0.48545074462890625,
      "learning_rate": 1.9857104087540503e-06,
      "loss": 0.5273,
      "step": 51841
    },
    {
      "epoch": 1.592541394034344,
      "grad_norm": 0.44768697023391724,
      "learning_rate": 1.985421374780896e-06,
      "loss": 0.5864,
      "step": 51842
    },
    {
      "epoch": 1.5925721131692931,
      "grad_norm": 0.469139039516449,
      "learning_rate": 1.9851323595263493e-06,
      "loss": 0.5137,
      "step": 51843
    },
    {
      "epoch": 1.5926028323042423,
      "grad_norm": 0.46981173753738403,
      "learning_rate": 1.984843362991088e-06,
      "loss": 0.4706,
      "step": 51844
    },
    {
      "epoch": 1.5926335514391914,
      "grad_norm": 0.42889276146888733,
      "learning_rate": 1.984554385175782e-06,
      "loss": 0.5067,
      "step": 51845
    },
    {
      "epoch": 1.5926642705741405,
      "grad_norm": 0.43768298625946045,
      "learning_rate": 1.9842654260811122e-06,
      "loss": 0.4764,
      "step": 51846
    },
    {
      "epoch": 1.5926949897090896,
      "grad_norm": 0.4277627766132355,
      "learning_rate": 1.983976485707746e-06,
      "loss": 0.4178,
      "step": 51847
    },
    {
      "epoch": 1.592725708844039,
      "grad_norm": 0.4387841522693634,
      "learning_rate": 1.9836875640563658e-06,
      "loss": 0.4187,
      "step": 51848
    },
    {
      "epoch": 1.592756427978988,
      "grad_norm": 0.4466176927089691,
      "learning_rate": 1.9833986611276424e-06,
      "loss": 0.4374,
      "step": 51849
    },
    {
      "epoch": 1.5927871471139374,
      "grad_norm": 0.41040435433387756,
      "learning_rate": 1.983109776922253e-06,
      "loss": 0.4889,
      "step": 51850
    },
    {
      "epoch": 1.5928178662488865,
      "grad_norm": 0.4041118025779724,
      "learning_rate": 1.9828209114408646e-06,
      "loss": 0.4318,
      "step": 51851
    },
    {
      "epoch": 1.5928485853838357,
      "grad_norm": 0.38601019978523254,
      "learning_rate": 1.982532064684164e-06,
      "loss": 0.4613,
      "step": 51852
    },
    {
      "epoch": 1.5928793045187848,
      "grad_norm": 0.39733847975730896,
      "learning_rate": 1.9822432366528176e-06,
      "loss": 0.469,
      "step": 51853
    },
    {
      "epoch": 1.592910023653734,
      "grad_norm": 0.3974947929382324,
      "learning_rate": 1.9819544273475035e-06,
      "loss": 0.4432,
      "step": 51854
    },
    {
      "epoch": 1.592940742788683,
      "grad_norm": 0.4393675923347473,
      "learning_rate": 1.9816656367688923e-06,
      "loss": 0.5214,
      "step": 51855
    },
    {
      "epoch": 1.5929714619236321,
      "grad_norm": 0.432910680770874,
      "learning_rate": 1.9813768649176625e-06,
      "loss": 0.5005,
      "step": 51856
    },
    {
      "epoch": 1.5930021810585813,
      "grad_norm": 0.4256114661693573,
      "learning_rate": 1.9810881117944857e-06,
      "loss": 0.4484,
      "step": 51857
    },
    {
      "epoch": 1.5930329001935304,
      "grad_norm": 0.4322282075881958,
      "learning_rate": 1.980799377400038e-06,
      "loss": 0.47,
      "step": 51858
    },
    {
      "epoch": 1.5930636193284797,
      "grad_norm": 0.44755303859710693,
      "learning_rate": 1.9805106617349954e-06,
      "loss": 0.509,
      "step": 51859
    },
    {
      "epoch": 1.5930943384634288,
      "grad_norm": 0.43372172117233276,
      "learning_rate": 1.9802219648000287e-06,
      "loss": 0.4545,
      "step": 51860
    },
    {
      "epoch": 1.5931250575983782,
      "grad_norm": 0.4345618188381195,
      "learning_rate": 1.9799332865958133e-06,
      "loss": 0.4259,
      "step": 51861
    },
    {
      "epoch": 1.5931557767333273,
      "grad_norm": 0.42538365721702576,
      "learning_rate": 1.979644627123024e-06,
      "loss": 0.4782,
      "step": 51862
    },
    {
      "epoch": 1.5931864958682764,
      "grad_norm": 0.4260363280773163,
      "learning_rate": 1.9793559863823365e-06,
      "loss": 0.4402,
      "step": 51863
    },
    {
      "epoch": 1.5932172150032256,
      "grad_norm": 0.435091108083725,
      "learning_rate": 1.9790673643744216e-06,
      "loss": 0.5104,
      "step": 51864
    },
    {
      "epoch": 1.5932479341381747,
      "grad_norm": 0.40148651599884033,
      "learning_rate": 1.978778761099954e-06,
      "loss": 0.5852,
      "step": 51865
    },
    {
      "epoch": 1.5932786532731238,
      "grad_norm": 0.42610815167427063,
      "learning_rate": 1.97849017655961e-06,
      "loss": 0.4983,
      "step": 51866
    },
    {
      "epoch": 1.593309372408073,
      "grad_norm": 0.4062559902667999,
      "learning_rate": 1.978201610754065e-06,
      "loss": 0.5511,
      "step": 51867
    },
    {
      "epoch": 1.593340091543022,
      "grad_norm": 0.44596046209335327,
      "learning_rate": 1.9779130636839874e-06,
      "loss": 0.4544,
      "step": 51868
    },
    {
      "epoch": 1.5933708106779711,
      "grad_norm": 0.4333550035953522,
      "learning_rate": 1.9776245353500534e-06,
      "loss": 0.3989,
      "step": 51869
    },
    {
      "epoch": 1.5934015298129205,
      "grad_norm": 0.4197663366794586,
      "learning_rate": 1.9773360257529384e-06,
      "loss": 0.4269,
      "step": 51870
    },
    {
      "epoch": 1.5934322489478696,
      "grad_norm": 0.4338397979736328,
      "learning_rate": 1.9770475348933184e-06,
      "loss": 0.4648,
      "step": 51871
    },
    {
      "epoch": 1.593462968082819,
      "grad_norm": 0.4499399662017822,
      "learning_rate": 1.9767590627718603e-06,
      "loss": 0.5011,
      "step": 51872
    },
    {
      "epoch": 1.593493687217768,
      "grad_norm": 0.38589558005332947,
      "learning_rate": 1.9764706093892426e-06,
      "loss": 0.4396,
      "step": 51873
    },
    {
      "epoch": 1.5935244063527172,
      "grad_norm": 0.46001553535461426,
      "learning_rate": 1.9761821747461384e-06,
      "loss": 0.4678,
      "step": 51874
    },
    {
      "epoch": 1.5935551254876663,
      "grad_norm": 0.4118364155292511,
      "learning_rate": 1.9758937588432226e-06,
      "loss": 0.4772,
      "step": 51875
    },
    {
      "epoch": 1.5935858446226154,
      "grad_norm": 0.4049627482891083,
      "learning_rate": 1.9756053616811653e-06,
      "loss": 0.4226,
      "step": 51876
    },
    {
      "epoch": 1.5936165637575646,
      "grad_norm": 0.39299193024635315,
      "learning_rate": 1.975316983260642e-06,
      "loss": 0.4561,
      "step": 51877
    },
    {
      "epoch": 1.5936472828925137,
      "grad_norm": 0.5078586339950562,
      "learning_rate": 1.975028623582327e-06,
      "loss": 0.5734,
      "step": 51878
    },
    {
      "epoch": 1.5936780020274628,
      "grad_norm": 0.4315052926540375,
      "learning_rate": 1.974740282646893e-06,
      "loss": 0.5004,
      "step": 51879
    },
    {
      "epoch": 1.593708721162412,
      "grad_norm": 0.40646055340766907,
      "learning_rate": 1.974451960455016e-06,
      "loss": 0.4813,
      "step": 51880
    },
    {
      "epoch": 1.5937394402973613,
      "grad_norm": 0.558870792388916,
      "learning_rate": 1.974163657007364e-06,
      "loss": 0.4823,
      "step": 51881
    },
    {
      "epoch": 1.5937701594323104,
      "grad_norm": 0.3969973027706146,
      "learning_rate": 1.9738753723046154e-06,
      "loss": 0.5028,
      "step": 51882
    },
    {
      "epoch": 1.5938008785672595,
      "grad_norm": 0.4256449341773987,
      "learning_rate": 1.9735871063474377e-06,
      "loss": 0.4245,
      "step": 51883
    },
    {
      "epoch": 1.5938315977022088,
      "grad_norm": 0.475094199180603,
      "learning_rate": 1.973298859136512e-06,
      "loss": 0.4001,
      "step": 51884
    },
    {
      "epoch": 1.593862316837158,
      "grad_norm": 0.4284847676753998,
      "learning_rate": 1.973010630672505e-06,
      "loss": 0.4858,
      "step": 51885
    },
    {
      "epoch": 1.593893035972107,
      "grad_norm": 0.4492747485637665,
      "learning_rate": 1.9727224209560946e-06,
      "loss": 0.5278,
      "step": 51886
    },
    {
      "epoch": 1.5939237551070562,
      "grad_norm": 0.4980525076389313,
      "learning_rate": 1.9724342299879495e-06,
      "loss": 0.4399,
      "step": 51887
    },
    {
      "epoch": 1.5939544742420053,
      "grad_norm": 0.4071159064769745,
      "learning_rate": 1.9721460577687445e-06,
      "loss": 0.4477,
      "step": 51888
    },
    {
      "epoch": 1.5939851933769544,
      "grad_norm": 0.431398868560791,
      "learning_rate": 1.9718579042991524e-06,
      "loss": 0.4517,
      "step": 51889
    },
    {
      "epoch": 1.5940159125119036,
      "grad_norm": 0.4328189194202423,
      "learning_rate": 1.9715697695798506e-06,
      "loss": 0.4707,
      "step": 51890
    },
    {
      "epoch": 1.5940466316468527,
      "grad_norm": 0.47137802839279175,
      "learning_rate": 1.971281653611505e-06,
      "loss": 0.4854,
      "step": 51891
    },
    {
      "epoch": 1.594077350781802,
      "grad_norm": 0.4534158408641815,
      "learning_rate": 1.9709935563947925e-06,
      "loss": 0.4576,
      "step": 51892
    },
    {
      "epoch": 1.5941080699167511,
      "grad_norm": 0.4713526666164398,
      "learning_rate": 1.970705477930386e-06,
      "loss": 0.5504,
      "step": 51893
    },
    {
      "epoch": 1.5941387890517003,
      "grad_norm": 0.4232482314109802,
      "learning_rate": 1.9704174182189585e-06,
      "loss": 0.4957,
      "step": 51894
    },
    {
      "epoch": 1.5941695081866496,
      "grad_norm": 0.45221394300460815,
      "learning_rate": 1.97012937726118e-06,
      "loss": 0.4548,
      "step": 51895
    },
    {
      "epoch": 1.5942002273215987,
      "grad_norm": 0.4191029667854309,
      "learning_rate": 1.9698413550577257e-06,
      "loss": 0.5021,
      "step": 51896
    },
    {
      "epoch": 1.5942309464565478,
      "grad_norm": 0.7041352391242981,
      "learning_rate": 1.969553351609267e-06,
      "loss": 0.4083,
      "step": 51897
    },
    {
      "epoch": 1.594261665591497,
      "grad_norm": 0.4270707964897156,
      "learning_rate": 1.9692653669164772e-06,
      "loss": 0.4525,
      "step": 51898
    },
    {
      "epoch": 1.594292384726446,
      "grad_norm": 0.4394940435886383,
      "learning_rate": 1.968977400980031e-06,
      "loss": 0.501,
      "step": 51899
    },
    {
      "epoch": 1.5943231038613952,
      "grad_norm": 0.45801568031311035,
      "learning_rate": 1.9686894538005974e-06,
      "loss": 0.4423,
      "step": 51900
    },
    {
      "epoch": 1.5943538229963443,
      "grad_norm": 0.47617530822753906,
      "learning_rate": 1.9684015253788503e-06,
      "loss": 0.4489,
      "step": 51901
    },
    {
      "epoch": 1.5943845421312934,
      "grad_norm": 0.38217902183532715,
      "learning_rate": 1.9681136157154623e-06,
      "loss": 0.4521,
      "step": 51902
    },
    {
      "epoch": 1.5944152612662428,
      "grad_norm": 0.4041083753108978,
      "learning_rate": 1.9678257248111088e-06,
      "loss": 0.4417,
      "step": 51903
    },
    {
      "epoch": 1.594445980401192,
      "grad_norm": 0.41260504722595215,
      "learning_rate": 1.967537852666457e-06,
      "loss": 0.4752,
      "step": 51904
    },
    {
      "epoch": 1.594476699536141,
      "grad_norm": 0.41935768723487854,
      "learning_rate": 1.9672499992821803e-06,
      "loss": 0.474,
      "step": 51905
    },
    {
      "epoch": 1.5945074186710904,
      "grad_norm": 0.41946643590927124,
      "learning_rate": 1.966962164658953e-06,
      "loss": 0.4867,
      "step": 51906
    },
    {
      "epoch": 1.5945381378060395,
      "grad_norm": 0.5187976956367493,
      "learning_rate": 1.966674348797449e-06,
      "loss": 0.4391,
      "step": 51907
    },
    {
      "epoch": 1.5945688569409886,
      "grad_norm": 0.4492717385292053,
      "learning_rate": 1.966386551698336e-06,
      "loss": 0.4428,
      "step": 51908
    },
    {
      "epoch": 1.5945995760759377,
      "grad_norm": 0.4090752899646759,
      "learning_rate": 1.9660987733622906e-06,
      "loss": 0.4695,
      "step": 51909
    },
    {
      "epoch": 1.5946302952108868,
      "grad_norm": 0.44723770022392273,
      "learning_rate": 1.9658110137899767e-06,
      "loss": 0.5303,
      "step": 51910
    },
    {
      "epoch": 1.594661014345836,
      "grad_norm": 0.4351215362548828,
      "learning_rate": 1.965523272982078e-06,
      "loss": 0.4719,
      "step": 51911
    },
    {
      "epoch": 1.594691733480785,
      "grad_norm": 0.4323543906211853,
      "learning_rate": 1.9652355509392586e-06,
      "loss": 0.4117,
      "step": 51912
    },
    {
      "epoch": 1.5947224526157342,
      "grad_norm": 0.3925250172615051,
      "learning_rate": 1.9649478476621918e-06,
      "loss": 0.4713,
      "step": 51913
    },
    {
      "epoch": 1.5947531717506835,
      "grad_norm": 0.434581458568573,
      "learning_rate": 1.9646601631515503e-06,
      "loss": 0.4727,
      "step": 51914
    },
    {
      "epoch": 1.5947838908856327,
      "grad_norm": 0.42604243755340576,
      "learning_rate": 1.964372497408008e-06,
      "loss": 0.4797,
      "step": 51915
    },
    {
      "epoch": 1.5948146100205818,
      "grad_norm": 0.460355281829834,
      "learning_rate": 1.964084850432236e-06,
      "loss": 0.4443,
      "step": 51916
    },
    {
      "epoch": 1.5948453291555311,
      "grad_norm": 0.4859221577644348,
      "learning_rate": 1.9637972222249025e-06,
      "loss": 0.4589,
      "step": 51917
    },
    {
      "epoch": 1.5948760482904802,
      "grad_norm": 0.4302721321582794,
      "learning_rate": 1.963509612786685e-06,
      "loss": 0.4451,
      "step": 51918
    },
    {
      "epoch": 1.5949067674254294,
      "grad_norm": 0.43942347168922424,
      "learning_rate": 1.9632220221182464e-06,
      "loss": 0.4563,
      "step": 51919
    },
    {
      "epoch": 1.5949374865603785,
      "grad_norm": 0.40373948216438293,
      "learning_rate": 1.9629344502202698e-06,
      "loss": 0.4354,
      "step": 51920
    },
    {
      "epoch": 1.5949682056953276,
      "grad_norm": 0.5002950429916382,
      "learning_rate": 1.9626468970934174e-06,
      "loss": 0.5019,
      "step": 51921
    },
    {
      "epoch": 1.5949989248302767,
      "grad_norm": 0.42700082063674927,
      "learning_rate": 1.9623593627383686e-06,
      "loss": 0.4247,
      "step": 51922
    },
    {
      "epoch": 1.5950296439652258,
      "grad_norm": 0.3934948444366455,
      "learning_rate": 1.9620718471557874e-06,
      "loss": 0.4795,
      "step": 51923
    },
    {
      "epoch": 1.595060363100175,
      "grad_norm": 0.4226178824901581,
      "learning_rate": 1.9617843503463486e-06,
      "loss": 0.4842,
      "step": 51924
    },
    {
      "epoch": 1.5950910822351243,
      "grad_norm": 0.474556028842926,
      "learning_rate": 1.961496872310724e-06,
      "loss": 0.5227,
      "step": 51925
    },
    {
      "epoch": 1.5951218013700734,
      "grad_norm": 0.4210343062877655,
      "learning_rate": 1.9612094130495884e-06,
      "loss": 0.4914,
      "step": 51926
    },
    {
      "epoch": 1.5951525205050225,
      "grad_norm": 0.5912480354309082,
      "learning_rate": 1.9609219725636062e-06,
      "loss": 0.4576,
      "step": 51927
    },
    {
      "epoch": 1.5951832396399719,
      "grad_norm": 0.4572092592716217,
      "learning_rate": 1.960634550853452e-06,
      "loss": 0.4645,
      "step": 51928
    },
    {
      "epoch": 1.595213958774921,
      "grad_norm": 0.48376479744911194,
      "learning_rate": 1.960347147919798e-06,
      "loss": 0.5323,
      "step": 51929
    },
    {
      "epoch": 1.5952446779098701,
      "grad_norm": 0.46021711826324463,
      "learning_rate": 1.9600597637633155e-06,
      "loss": 0.4473,
      "step": 51930
    },
    {
      "epoch": 1.5952753970448192,
      "grad_norm": 0.4532402455806732,
      "learning_rate": 1.959772398384674e-06,
      "loss": 0.4253,
      "step": 51931
    },
    {
      "epoch": 1.5953061161797684,
      "grad_norm": 0.4056069850921631,
      "learning_rate": 1.9594850517845453e-06,
      "loss": 0.4727,
      "step": 51932
    },
    {
      "epoch": 1.5953368353147175,
      "grad_norm": 0.527105450630188,
      "learning_rate": 1.9591977239636005e-06,
      "loss": 0.3899,
      "step": 51933
    },
    {
      "epoch": 1.5953675544496666,
      "grad_norm": 0.45585542917251587,
      "learning_rate": 1.9589104149225115e-06,
      "loss": 0.4921,
      "step": 51934
    },
    {
      "epoch": 1.5953982735846157,
      "grad_norm": 0.38529708981513977,
      "learning_rate": 1.9586231246619514e-06,
      "loss": 0.507,
      "step": 51935
    },
    {
      "epoch": 1.595428992719565,
      "grad_norm": 0.4273926615715027,
      "learning_rate": 1.958335853182586e-06,
      "loss": 0.4065,
      "step": 51936
    },
    {
      "epoch": 1.5954597118545142,
      "grad_norm": 0.4227600693702698,
      "learning_rate": 1.9580486004850876e-06,
      "loss": 0.477,
      "step": 51937
    },
    {
      "epoch": 1.5954904309894633,
      "grad_norm": 0.3919731378555298,
      "learning_rate": 1.957761366570129e-06,
      "loss": 0.3889,
      "step": 51938
    },
    {
      "epoch": 1.5955211501244126,
      "grad_norm": 0.4287146329879761,
      "learning_rate": 1.9574741514383834e-06,
      "loss": 0.5401,
      "step": 51939
    },
    {
      "epoch": 1.5955518692593618,
      "grad_norm": 0.5129635334014893,
      "learning_rate": 1.9571869550905164e-06,
      "loss": 0.4255,
      "step": 51940
    },
    {
      "epoch": 1.5955825883943109,
      "grad_norm": 0.43006327748298645,
      "learning_rate": 1.9568997775272003e-06,
      "loss": 0.4369,
      "step": 51941
    },
    {
      "epoch": 1.59561330752926,
      "grad_norm": 0.4247663617134094,
      "learning_rate": 1.9566126187491065e-06,
      "loss": 0.4576,
      "step": 51942
    },
    {
      "epoch": 1.5956440266642091,
      "grad_norm": 0.41945064067840576,
      "learning_rate": 1.9563254787569088e-06,
      "loss": 0.4299,
      "step": 51943
    },
    {
      "epoch": 1.5956747457991582,
      "grad_norm": 0.45984572172164917,
      "learning_rate": 1.9560383575512708e-06,
      "loss": 0.492,
      "step": 51944
    },
    {
      "epoch": 1.5957054649341074,
      "grad_norm": 0.4627695083618164,
      "learning_rate": 1.9557512551328705e-06,
      "loss": 0.4005,
      "step": 51945
    },
    {
      "epoch": 1.5957361840690565,
      "grad_norm": 0.4501015841960907,
      "learning_rate": 1.9554641715023705e-06,
      "loss": 0.4671,
      "step": 51946
    },
    {
      "epoch": 1.5957669032040058,
      "grad_norm": 0.434899240732193,
      "learning_rate": 1.9551771066604495e-06,
      "loss": 0.4377,
      "step": 51947
    },
    {
      "epoch": 1.595797622338955,
      "grad_norm": 0.4171653985977173,
      "learning_rate": 1.9548900606077725e-06,
      "loss": 0.5128,
      "step": 51948
    },
    {
      "epoch": 1.595828341473904,
      "grad_norm": 0.43276938796043396,
      "learning_rate": 1.9546030333450115e-06,
      "loss": 0.3776,
      "step": 51949
    },
    {
      "epoch": 1.5958590606088534,
      "grad_norm": 0.4599989354610443,
      "learning_rate": 1.9543160248728397e-06,
      "loss": 0.4641,
      "step": 51950
    },
    {
      "epoch": 1.5958897797438025,
      "grad_norm": 0.4060131311416626,
      "learning_rate": 1.954029035191919e-06,
      "loss": 0.4525,
      "step": 51951
    },
    {
      "epoch": 1.5959204988787516,
      "grad_norm": 0.42577657103538513,
      "learning_rate": 1.9537420643029313e-06,
      "loss": 0.436,
      "step": 51952
    },
    {
      "epoch": 1.5959512180137008,
      "grad_norm": 0.4532223641872406,
      "learning_rate": 1.953455112206538e-06,
      "loss": 0.4714,
      "step": 51953
    },
    {
      "epoch": 1.5959819371486499,
      "grad_norm": 0.43454843759536743,
      "learning_rate": 1.953168178903415e-06,
      "loss": 0.4091,
      "step": 51954
    },
    {
      "epoch": 1.596012656283599,
      "grad_norm": 0.39527079463005066,
      "learning_rate": 1.952881264394224e-06,
      "loss": 0.4326,
      "step": 51955
    },
    {
      "epoch": 1.5960433754185481,
      "grad_norm": 0.4047694504261017,
      "learning_rate": 1.9525943686796466e-06,
      "loss": 0.4408,
      "step": 51956
    },
    {
      "epoch": 1.5960740945534972,
      "grad_norm": 0.44493481516838074,
      "learning_rate": 1.9523074917603447e-06,
      "loss": 0.498,
      "step": 51957
    },
    {
      "epoch": 1.5961048136884466,
      "grad_norm": 0.45098230242729187,
      "learning_rate": 1.952020633636992e-06,
      "loss": 0.4536,
      "step": 51958
    },
    {
      "epoch": 1.5961355328233957,
      "grad_norm": 0.4312838315963745,
      "learning_rate": 1.9517337943102553e-06,
      "loss": 0.4454,
      "step": 51959
    },
    {
      "epoch": 1.5961662519583448,
      "grad_norm": 0.40801483392715454,
      "learning_rate": 1.9514469737808074e-06,
      "loss": 0.4243,
      "step": 51960
    },
    {
      "epoch": 1.5961969710932942,
      "grad_norm": 0.4246452748775482,
      "learning_rate": 1.9511601720493155e-06,
      "loss": 0.4383,
      "step": 51961
    },
    {
      "epoch": 1.5962276902282433,
      "grad_norm": 0.41111403703689575,
      "learning_rate": 1.9508733891164553e-06,
      "loss": 0.5532,
      "step": 51962
    },
    {
      "epoch": 1.5962584093631924,
      "grad_norm": 0.41408267617225647,
      "learning_rate": 1.9505866249828888e-06,
      "loss": 0.4163,
      "step": 51963
    },
    {
      "epoch": 1.5962891284981415,
      "grad_norm": 0.45805859565734863,
      "learning_rate": 1.95029987964929e-06,
      "loss": 0.4868,
      "step": 51964
    },
    {
      "epoch": 1.5963198476330906,
      "grad_norm": 0.4248405396938324,
      "learning_rate": 1.950013153116327e-06,
      "loss": 0.4971,
      "step": 51965
    },
    {
      "epoch": 1.5963505667680398,
      "grad_norm": 0.4563652276992798,
      "learning_rate": 1.9497264453846743e-06,
      "loss": 0.4917,
      "step": 51966
    },
    {
      "epoch": 1.596381285902989,
      "grad_norm": 0.44108909368515015,
      "learning_rate": 1.949439756454995e-06,
      "loss": 0.5582,
      "step": 51967
    },
    {
      "epoch": 1.596412005037938,
      "grad_norm": 0.4283027946949005,
      "learning_rate": 1.9491530863279608e-06,
      "loss": 0.5076,
      "step": 51968
    },
    {
      "epoch": 1.5964427241728871,
      "grad_norm": 0.43087753653526306,
      "learning_rate": 1.948866435004242e-06,
      "loss": 0.4259,
      "step": 51969
    },
    {
      "epoch": 1.5964734433078365,
      "grad_norm": 0.43657153844833374,
      "learning_rate": 1.948579802484508e-06,
      "loss": 0.368,
      "step": 51970
    },
    {
      "epoch": 1.5965041624427856,
      "grad_norm": 0.41174888610839844,
      "learning_rate": 1.948293188769431e-06,
      "loss": 0.4886,
      "step": 51971
    },
    {
      "epoch": 1.596534881577735,
      "grad_norm": 0.45537227392196655,
      "learning_rate": 1.948006593859675e-06,
      "loss": 0.4282,
      "step": 51972
    },
    {
      "epoch": 1.596565600712684,
      "grad_norm": 0.4626789689064026,
      "learning_rate": 1.947720017755911e-06,
      "loss": 0.4699,
      "step": 51973
    },
    {
      "epoch": 1.5965963198476332,
      "grad_norm": 0.43346384167671204,
      "learning_rate": 1.94743346045881e-06,
      "loss": 0.4138,
      "step": 51974
    },
    {
      "epoch": 1.5966270389825823,
      "grad_norm": 0.39735689759254456,
      "learning_rate": 1.947146921969043e-06,
      "loss": 0.4423,
      "step": 51975
    },
    {
      "epoch": 1.5966577581175314,
      "grad_norm": 0.43731290102005005,
      "learning_rate": 1.946860402287274e-06,
      "loss": 0.4547,
      "step": 51976
    },
    {
      "epoch": 1.5966884772524805,
      "grad_norm": 0.4202866554260254,
      "learning_rate": 1.946573901414176e-06,
      "loss": 0.4235,
      "step": 51977
    },
    {
      "epoch": 1.5967191963874297,
      "grad_norm": 0.45379185676574707,
      "learning_rate": 1.9462874193504155e-06,
      "loss": 0.4841,
      "step": 51978
    },
    {
      "epoch": 1.5967499155223788,
      "grad_norm": 0.41005659103393555,
      "learning_rate": 1.9460009560966674e-06,
      "loss": 0.4939,
      "step": 51979
    },
    {
      "epoch": 1.596780634657328,
      "grad_norm": 0.40872514247894287,
      "learning_rate": 1.9457145116535923e-06,
      "loss": 0.4195,
      "step": 51980
    },
    {
      "epoch": 1.5968113537922772,
      "grad_norm": 0.4363631308078766,
      "learning_rate": 1.945428086021868e-06,
      "loss": 0.4098,
      "step": 51981
    },
    {
      "epoch": 1.5968420729272264,
      "grad_norm": 0.4010281264781952,
      "learning_rate": 1.9451416792021515e-06,
      "loss": 0.429,
      "step": 51982
    },
    {
      "epoch": 1.5968727920621757,
      "grad_norm": 0.437039852142334,
      "learning_rate": 1.944855291195126e-06,
      "loss": 0.478,
      "step": 51983
    },
    {
      "epoch": 1.5969035111971248,
      "grad_norm": 0.442463755607605,
      "learning_rate": 1.9445689220014507e-06,
      "loss": 0.4332,
      "step": 51984
    },
    {
      "epoch": 1.596934230332074,
      "grad_norm": 0.428374320268631,
      "learning_rate": 1.9442825716217994e-06,
      "loss": 0.467,
      "step": 51985
    },
    {
      "epoch": 1.596964949467023,
      "grad_norm": 0.4355930685997009,
      "learning_rate": 1.943996240056837e-06,
      "loss": 0.4557,
      "step": 51986
    },
    {
      "epoch": 1.5969956686019722,
      "grad_norm": 0.43991121649742126,
      "learning_rate": 1.94370992730723e-06,
      "loss": 0.4451,
      "step": 51987
    },
    {
      "epoch": 1.5970263877369213,
      "grad_norm": 0.4165831208229065,
      "learning_rate": 1.9434236333736567e-06,
      "loss": 0.5185,
      "step": 51988
    },
    {
      "epoch": 1.5970571068718704,
      "grad_norm": 0.4088746905326843,
      "learning_rate": 1.943137358256778e-06,
      "loss": 0.4242,
      "step": 51989
    },
    {
      "epoch": 1.5970878260068195,
      "grad_norm": 0.44667571783065796,
      "learning_rate": 1.9428511019572684e-06,
      "loss": 0.4797,
      "step": 51990
    },
    {
      "epoch": 1.5971185451417687,
      "grad_norm": 0.43185901641845703,
      "learning_rate": 1.9425648644757876e-06,
      "loss": 0.416,
      "step": 51991
    },
    {
      "epoch": 1.597149264276718,
      "grad_norm": 0.4657529592514038,
      "learning_rate": 1.942278645813012e-06,
      "loss": 0.4843,
      "step": 51992
    },
    {
      "epoch": 1.5971799834116671,
      "grad_norm": 0.42814818024635315,
      "learning_rate": 1.9419924459696048e-06,
      "loss": 0.5187,
      "step": 51993
    },
    {
      "epoch": 1.5972107025466162,
      "grad_norm": 0.5169277787208557,
      "learning_rate": 1.9417062649462415e-06,
      "loss": 0.4231,
      "step": 51994
    },
    {
      "epoch": 1.5972414216815656,
      "grad_norm": 0.4553391635417938,
      "learning_rate": 1.941420102743583e-06,
      "loss": 0.3747,
      "step": 51995
    },
    {
      "epoch": 1.5972721408165147,
      "grad_norm": 0.4704150855541229,
      "learning_rate": 1.9411339593623e-06,
      "loss": 0.5256,
      "step": 51996
    },
    {
      "epoch": 1.5973028599514638,
      "grad_norm": 0.4248863160610199,
      "learning_rate": 1.9408478348030624e-06,
      "loss": 0.5154,
      "step": 51997
    },
    {
      "epoch": 1.597333579086413,
      "grad_norm": 0.4142187535762787,
      "learning_rate": 1.940561729066539e-06,
      "loss": 0.4018,
      "step": 51998
    },
    {
      "epoch": 1.597364298221362,
      "grad_norm": 0.4243006408214569,
      "learning_rate": 1.9402756421533954e-06,
      "loss": 0.4742,
      "step": 51999
    },
    {
      "epoch": 1.5973950173563112,
      "grad_norm": 0.44112756848335266,
      "learning_rate": 1.9399895740642993e-06,
      "loss": 0.4755,
      "step": 52000
    },
    {
      "epoch": 1.5974257364912603,
      "grad_norm": 0.4703811705112457,
      "learning_rate": 1.939703524799921e-06,
      "loss": 0.4342,
      "step": 52001
    },
    {
      "epoch": 1.5974564556262094,
      "grad_norm": 0.39144575595855713,
      "learning_rate": 1.939417494360931e-06,
      "loss": 0.4331,
      "step": 52002
    },
    {
      "epoch": 1.5974871747611588,
      "grad_norm": 0.4038940966129303,
      "learning_rate": 1.939131482747992e-06,
      "loss": 0.4807,
      "step": 52003
    },
    {
      "epoch": 1.5975178938961079,
      "grad_norm": 0.4339340627193451,
      "learning_rate": 1.938845489961774e-06,
      "loss": 0.5122,
      "step": 52004
    },
    {
      "epoch": 1.597548613031057,
      "grad_norm": 0.46067607402801514,
      "learning_rate": 1.9385595160029448e-06,
      "loss": 0.4837,
      "step": 52005
    },
    {
      "epoch": 1.5975793321660063,
      "grad_norm": 0.4122158885002136,
      "learning_rate": 1.9382735608721737e-06,
      "loss": 0.4906,
      "step": 52006
    },
    {
      "epoch": 1.5976100513009555,
      "grad_norm": 0.4421999156475067,
      "learning_rate": 1.93798762457013e-06,
      "loss": 0.5151,
      "step": 52007
    },
    {
      "epoch": 1.5976407704359046,
      "grad_norm": 0.48553651571273804,
      "learning_rate": 1.937701707097477e-06,
      "loss": 0.5315,
      "step": 52008
    },
    {
      "epoch": 1.5976714895708537,
      "grad_norm": 0.45758670568466187,
      "learning_rate": 1.9374158084548843e-06,
      "loss": 0.4093,
      "step": 52009
    },
    {
      "epoch": 1.5977022087058028,
      "grad_norm": 0.43502506613731384,
      "learning_rate": 1.93712992864302e-06,
      "loss": 0.4737,
      "step": 52010
    },
    {
      "epoch": 1.597732927840752,
      "grad_norm": 0.4063529074192047,
      "learning_rate": 1.9368440676625544e-06,
      "loss": 0.4237,
      "step": 52011
    },
    {
      "epoch": 1.597763646975701,
      "grad_norm": 0.420462042093277,
      "learning_rate": 1.9365582255141513e-06,
      "loss": 0.4499,
      "step": 52012
    },
    {
      "epoch": 1.5977943661106502,
      "grad_norm": 0.41141000390052795,
      "learning_rate": 1.93627240219848e-06,
      "loss": 0.4177,
      "step": 52013
    },
    {
      "epoch": 1.5978250852455995,
      "grad_norm": 0.4636508524417877,
      "learning_rate": 1.9359865977162042e-06,
      "loss": 0.4841,
      "step": 52014
    },
    {
      "epoch": 1.5978558043805486,
      "grad_norm": 0.41135209798812866,
      "learning_rate": 1.9357008120679997e-06,
      "loss": 0.471,
      "step": 52015
    },
    {
      "epoch": 1.5978865235154978,
      "grad_norm": 0.4102770984172821,
      "learning_rate": 1.935415045254526e-06,
      "loss": 0.4383,
      "step": 52016
    },
    {
      "epoch": 1.597917242650447,
      "grad_norm": 0.45572465658187866,
      "learning_rate": 1.935129297276457e-06,
      "loss": 0.4201,
      "step": 52017
    },
    {
      "epoch": 1.5979479617853962,
      "grad_norm": 0.5072685480117798,
      "learning_rate": 1.9348435681344514e-06,
      "loss": 0.4788,
      "step": 52018
    },
    {
      "epoch": 1.5979786809203453,
      "grad_norm": 0.46821343898773193,
      "learning_rate": 1.934557857829187e-06,
      "loss": 0.4087,
      "step": 52019
    },
    {
      "epoch": 1.5980094000552945,
      "grad_norm": 0.4262717366218567,
      "learning_rate": 1.934272166361323e-06,
      "loss": 0.3661,
      "step": 52020
    },
    {
      "epoch": 1.5980401191902436,
      "grad_norm": 0.4424799978733063,
      "learning_rate": 1.9339864937315324e-06,
      "loss": 0.4608,
      "step": 52021
    },
    {
      "epoch": 1.5980708383251927,
      "grad_norm": 0.39082199335098267,
      "learning_rate": 1.9337008399404776e-06,
      "loss": 0.4505,
      "step": 52022
    },
    {
      "epoch": 1.5981015574601418,
      "grad_norm": 0.44963279366493225,
      "learning_rate": 1.9334152049888242e-06,
      "loss": 0.4927,
      "step": 52023
    },
    {
      "epoch": 1.598132276595091,
      "grad_norm": 0.4420471489429474,
      "learning_rate": 1.9331295888772495e-06,
      "loss": 0.3982,
      "step": 52024
    },
    {
      "epoch": 1.5981629957300403,
      "grad_norm": 0.4296965003013611,
      "learning_rate": 1.932843991606411e-06,
      "loss": 0.459,
      "step": 52025
    },
    {
      "epoch": 1.5981937148649894,
      "grad_norm": 0.3926188349723816,
      "learning_rate": 1.9325584131769813e-06,
      "loss": 0.4124,
      "step": 52026
    },
    {
      "epoch": 1.5982244339999385,
      "grad_norm": 0.4066082537174225,
      "learning_rate": 1.932272853589622e-06,
      "loss": 0.4105,
      "step": 52027
    },
    {
      "epoch": 1.5982551531348879,
      "grad_norm": 0.37241867184638977,
      "learning_rate": 1.931987312845003e-06,
      "loss": 0.3783,
      "step": 52028
    },
    {
      "epoch": 1.598285872269837,
      "grad_norm": 0.4409692585468292,
      "learning_rate": 1.931701790943791e-06,
      "loss": 0.4951,
      "step": 52029
    },
    {
      "epoch": 1.598316591404786,
      "grad_norm": 0.4233214557170868,
      "learning_rate": 1.9314162878866548e-06,
      "loss": 0.4533,
      "step": 52030
    },
    {
      "epoch": 1.5983473105397352,
      "grad_norm": 0.4563429653644562,
      "learning_rate": 1.931130803674258e-06,
      "loss": 0.4931,
      "step": 52031
    },
    {
      "epoch": 1.5983780296746843,
      "grad_norm": 0.422917902469635,
      "learning_rate": 1.930845338307269e-06,
      "loss": 0.4766,
      "step": 52032
    },
    {
      "epoch": 1.5984087488096335,
      "grad_norm": 0.47699442505836487,
      "learning_rate": 1.9305598917863533e-06,
      "loss": 0.4552,
      "step": 52033
    },
    {
      "epoch": 1.5984394679445826,
      "grad_norm": 0.4006974399089813,
      "learning_rate": 1.930274464112182e-06,
      "loss": 0.3715,
      "step": 52034
    },
    {
      "epoch": 1.5984701870795317,
      "grad_norm": 0.5347225069999695,
      "learning_rate": 1.929989055285414e-06,
      "loss": 0.5591,
      "step": 52035
    },
    {
      "epoch": 1.598500906214481,
      "grad_norm": 0.44529539346694946,
      "learning_rate": 1.929703665306721e-06,
      "loss": 0.4126,
      "step": 52036
    },
    {
      "epoch": 1.5985316253494302,
      "grad_norm": 0.443739116191864,
      "learning_rate": 1.929418294176769e-06,
      "loss": 0.4962,
      "step": 52037
    },
    {
      "epoch": 1.5985623444843793,
      "grad_norm": 0.41948798298835754,
      "learning_rate": 1.929132941896228e-06,
      "loss": 0.4422,
      "step": 52038
    },
    {
      "epoch": 1.5985930636193286,
      "grad_norm": 0.44211429357528687,
      "learning_rate": 1.928847608465756e-06,
      "loss": 0.4798,
      "step": 52039
    },
    {
      "epoch": 1.5986237827542777,
      "grad_norm": 0.4340175688266754,
      "learning_rate": 1.928562293886025e-06,
      "loss": 0.4516,
      "step": 52040
    },
    {
      "epoch": 1.5986545018892269,
      "grad_norm": 0.4990765154361725,
      "learning_rate": 1.928276998157701e-06,
      "loss": 0.523,
      "step": 52041
    },
    {
      "epoch": 1.598685221024176,
      "grad_norm": 0.42529669404029846,
      "learning_rate": 1.927991721281449e-06,
      "loss": 0.4295,
      "step": 52042
    },
    {
      "epoch": 1.598715940159125,
      "grad_norm": 0.42371684312820435,
      "learning_rate": 1.927706463257939e-06,
      "loss": 0.454,
      "step": 52043
    },
    {
      "epoch": 1.5987466592940742,
      "grad_norm": 0.3950495719909668,
      "learning_rate": 1.927421224087831e-06,
      "loss": 0.5797,
      "step": 52044
    },
    {
      "epoch": 1.5987773784290233,
      "grad_norm": 0.4286430776119232,
      "learning_rate": 1.9271360037717957e-06,
      "loss": 0.4815,
      "step": 52045
    },
    {
      "epoch": 1.5988080975639725,
      "grad_norm": 0.4525409936904907,
      "learning_rate": 1.926850802310497e-06,
      "loss": 0.4245,
      "step": 52046
    },
    {
      "epoch": 1.5988388166989218,
      "grad_norm": 0.44346433877944946,
      "learning_rate": 1.926565619704606e-06,
      "loss": 0.5083,
      "step": 52047
    },
    {
      "epoch": 1.598869535833871,
      "grad_norm": 0.4602661728858948,
      "learning_rate": 1.926280455954781e-06,
      "loss": 0.4322,
      "step": 52048
    },
    {
      "epoch": 1.59890025496882,
      "grad_norm": 0.4431624710559845,
      "learning_rate": 1.925995311061695e-06,
      "loss": 0.4651,
      "step": 52049
    },
    {
      "epoch": 1.5989309741037694,
      "grad_norm": 0.42230626940727234,
      "learning_rate": 1.9257101850260052e-06,
      "loss": 0.4267,
      "step": 52050
    },
    {
      "epoch": 1.5989616932387185,
      "grad_norm": 0.468841016292572,
      "learning_rate": 1.9254250778483887e-06,
      "loss": 0.4413,
      "step": 52051
    },
    {
      "epoch": 1.5989924123736676,
      "grad_norm": 0.45653727650642395,
      "learning_rate": 1.9251399895295033e-06,
      "loss": 0.4565,
      "step": 52052
    },
    {
      "epoch": 1.5990231315086167,
      "grad_norm": 0.3997609615325928,
      "learning_rate": 1.9248549200700195e-06,
      "loss": 0.4307,
      "step": 52053
    },
    {
      "epoch": 1.5990538506435659,
      "grad_norm": 0.3967241048812866,
      "learning_rate": 1.9245698694705993e-06,
      "loss": 0.4525,
      "step": 52054
    },
    {
      "epoch": 1.599084569778515,
      "grad_norm": 0.3872951567173004,
      "learning_rate": 1.92428483773191e-06,
      "loss": 0.5264,
      "step": 52055
    },
    {
      "epoch": 1.599115288913464,
      "grad_norm": 0.44424667954444885,
      "learning_rate": 1.9239998248546168e-06,
      "loss": 0.4525,
      "step": 52056
    },
    {
      "epoch": 1.5991460080484132,
      "grad_norm": 0.42286503314971924,
      "learning_rate": 1.9237148308393894e-06,
      "loss": 0.4986,
      "step": 52057
    },
    {
      "epoch": 1.5991767271833626,
      "grad_norm": 0.4248368442058563,
      "learning_rate": 1.923429855686887e-06,
      "loss": 0.4509,
      "step": 52058
    },
    {
      "epoch": 1.5992074463183117,
      "grad_norm": 0.39221125841140747,
      "learning_rate": 1.9231448993977753e-06,
      "loss": 0.4385,
      "step": 52059
    },
    {
      "epoch": 1.5992381654532608,
      "grad_norm": 0.47121334075927734,
      "learning_rate": 1.9228599619727286e-06,
      "loss": 0.419,
      "step": 52060
    },
    {
      "epoch": 1.5992688845882101,
      "grad_norm": 0.43246161937713623,
      "learning_rate": 1.9225750434124036e-06,
      "loss": 0.5313,
      "step": 52061
    },
    {
      "epoch": 1.5992996037231593,
      "grad_norm": 0.4448728859424591,
      "learning_rate": 1.9222901437174713e-06,
      "loss": 0.4466,
      "step": 52062
    },
    {
      "epoch": 1.5993303228581084,
      "grad_norm": 0.42230838537216187,
      "learning_rate": 1.922005262888592e-06,
      "loss": 0.4453,
      "step": 52063
    },
    {
      "epoch": 1.5993610419930575,
      "grad_norm": 0.4459656774997711,
      "learning_rate": 1.9217204009264334e-06,
      "loss": 0.4195,
      "step": 52064
    },
    {
      "epoch": 1.5993917611280066,
      "grad_norm": 0.4044875502586365,
      "learning_rate": 1.921435557831661e-06,
      "loss": 0.3921,
      "step": 52065
    },
    {
      "epoch": 1.5994224802629557,
      "grad_norm": 0.4050888419151306,
      "learning_rate": 1.9211507336049427e-06,
      "loss": 0.4653,
      "step": 52066
    },
    {
      "epoch": 1.5994531993979049,
      "grad_norm": 0.44694384932518005,
      "learning_rate": 1.9208659282469387e-06,
      "loss": 0.4507,
      "step": 52067
    },
    {
      "epoch": 1.599483918532854,
      "grad_norm": 0.4287426769733429,
      "learning_rate": 1.9205811417583164e-06,
      "loss": 0.4703,
      "step": 52068
    },
    {
      "epoch": 1.5995146376678033,
      "grad_norm": 0.425645112991333,
      "learning_rate": 1.9202963741397408e-06,
      "loss": 0.523,
      "step": 52069
    },
    {
      "epoch": 1.5995453568027524,
      "grad_norm": 0.4002949595451355,
      "learning_rate": 1.920011625391881e-06,
      "loss": 0.4747,
      "step": 52070
    },
    {
      "epoch": 1.5995760759377016,
      "grad_norm": 0.4879206418991089,
      "learning_rate": 1.919726895515395e-06,
      "loss": 0.4356,
      "step": 52071
    },
    {
      "epoch": 1.599606795072651,
      "grad_norm": 0.43602147698402405,
      "learning_rate": 1.91944218451095e-06,
      "loss": 0.4279,
      "step": 52072
    },
    {
      "epoch": 1.5996375142076,
      "grad_norm": 0.4571440517902374,
      "learning_rate": 1.9191574923792143e-06,
      "loss": 0.5323,
      "step": 52073
    },
    {
      "epoch": 1.5996682333425492,
      "grad_norm": 0.45185911655426025,
      "learning_rate": 1.918872819120852e-06,
      "loss": 0.4483,
      "step": 52074
    },
    {
      "epoch": 1.5996989524774983,
      "grad_norm": 0.42155373096466064,
      "learning_rate": 1.9185881647365244e-06,
      "loss": 0.4684,
      "step": 52075
    },
    {
      "epoch": 1.5997296716124474,
      "grad_norm": 0.4404793381690979,
      "learning_rate": 1.918303529226898e-06,
      "loss": 0.4522,
      "step": 52076
    },
    {
      "epoch": 1.5997603907473965,
      "grad_norm": 0.4403258264064789,
      "learning_rate": 1.9180189125926386e-06,
      "loss": 0.5342,
      "step": 52077
    },
    {
      "epoch": 1.5997911098823456,
      "grad_norm": 0.45013582706451416,
      "learning_rate": 1.9177343148344097e-06,
      "loss": 0.4033,
      "step": 52078
    },
    {
      "epoch": 1.5998218290172947,
      "grad_norm": 0.45162007212638855,
      "learning_rate": 1.917449735952881e-06,
      "loss": 0.4628,
      "step": 52079
    },
    {
      "epoch": 1.5998525481522439,
      "grad_norm": 0.4234839677810669,
      "learning_rate": 1.9171651759487087e-06,
      "loss": 0.4319,
      "step": 52080
    },
    {
      "epoch": 1.5998832672871932,
      "grad_norm": 0.413847953081131,
      "learning_rate": 1.9168806348225622e-06,
      "loss": 0.3942,
      "step": 52081
    },
    {
      "epoch": 1.5999139864221423,
      "grad_norm": 0.40815743803977966,
      "learning_rate": 1.916596112575105e-06,
      "loss": 0.5251,
      "step": 52082
    },
    {
      "epoch": 1.5999447055570917,
      "grad_norm": 0.43208035826683044,
      "learning_rate": 1.9163116092070054e-06,
      "loss": 0.4711,
      "step": 52083
    },
    {
      "epoch": 1.5999754246920408,
      "grad_norm": 0.4544915556907654,
      "learning_rate": 1.9160271247189223e-06,
      "loss": 0.4896,
      "step": 52084
    },
    {
      "epoch": 1.60000614382699,
      "grad_norm": 0.521416425704956,
      "learning_rate": 1.9157426591115246e-06,
      "loss": 0.4775,
      "step": 52085
    },
    {
      "epoch": 1.600036862961939,
      "grad_norm": 0.4759237766265869,
      "learning_rate": 1.915458212385469e-06,
      "loss": 0.5425,
      "step": 52086
    },
    {
      "epoch": 1.6000675820968882,
      "grad_norm": 0.4227464199066162,
      "learning_rate": 1.9151737845414307e-06,
      "loss": 0.4224,
      "step": 52087
    },
    {
      "epoch": 1.6000983012318373,
      "grad_norm": 0.4543505012989044,
      "learning_rate": 1.914889375580067e-06,
      "loss": 0.4729,
      "step": 52088
    },
    {
      "epoch": 1.6001290203667864,
      "grad_norm": 0.4213895797729492,
      "learning_rate": 1.9146049855020454e-06,
      "loss": 0.5047,
      "step": 52089
    },
    {
      "epoch": 1.6001597395017355,
      "grad_norm": 0.4017542004585266,
      "learning_rate": 1.914320614308026e-06,
      "loss": 0.4345,
      "step": 52090
    },
    {
      "epoch": 1.6001904586366846,
      "grad_norm": 0.5045787692070007,
      "learning_rate": 1.9140362619986764e-06,
      "loss": 0.4429,
      "step": 52091
    },
    {
      "epoch": 1.600221177771634,
      "grad_norm": 0.39069050550460815,
      "learning_rate": 1.913751928574659e-06,
      "loss": 0.4572,
      "step": 52092
    },
    {
      "epoch": 1.600251896906583,
      "grad_norm": 0.5420511364936829,
      "learning_rate": 1.9134676140366414e-06,
      "loss": 0.4848,
      "step": 52093
    },
    {
      "epoch": 1.6002826160415324,
      "grad_norm": 0.4471411108970642,
      "learning_rate": 1.9131833183852823e-06,
      "loss": 0.4989,
      "step": 52094
    },
    {
      "epoch": 1.6003133351764816,
      "grad_norm": 0.41735976934432983,
      "learning_rate": 1.9128990416212455e-06,
      "loss": 0.477,
      "step": 52095
    },
    {
      "epoch": 1.6003440543114307,
      "grad_norm": 0.48627525568008423,
      "learning_rate": 1.9126147837452036e-06,
      "loss": 0.4488,
      "step": 52096
    },
    {
      "epoch": 1.6003747734463798,
      "grad_norm": 0.4569448232650757,
      "learning_rate": 1.912330544757812e-06,
      "loss": 0.4724,
      "step": 52097
    },
    {
      "epoch": 1.600405492581329,
      "grad_norm": 0.4817620813846588,
      "learning_rate": 1.91204632465974e-06,
      "loss": 0.4327,
      "step": 52098
    },
    {
      "epoch": 1.600436211716278,
      "grad_norm": 0.43763893842697144,
      "learning_rate": 1.9117621234516447e-06,
      "loss": 0.5692,
      "step": 52099
    },
    {
      "epoch": 1.6004669308512272,
      "grad_norm": 0.44135332107543945,
      "learning_rate": 1.9114779411341956e-06,
      "loss": 0.4678,
      "step": 52100
    },
    {
      "epoch": 1.6004976499861763,
      "grad_norm": 0.4648834466934204,
      "learning_rate": 1.9111937777080537e-06,
      "loss": 0.4842,
      "step": 52101
    },
    {
      "epoch": 1.6005283691211254,
      "grad_norm": 0.41634970903396606,
      "learning_rate": 1.9109096331738864e-06,
      "loss": 0.5074,
      "step": 52102
    },
    {
      "epoch": 1.6005590882560747,
      "grad_norm": 0.4373498260974884,
      "learning_rate": 1.910625507532352e-06,
      "loss": 0.4955,
      "step": 52103
    },
    {
      "epoch": 1.6005898073910239,
      "grad_norm": 0.4470478892326355,
      "learning_rate": 1.910341400784117e-06,
      "loss": 0.5253,
      "step": 52104
    },
    {
      "epoch": 1.600620526525973,
      "grad_norm": 0.4151803255081177,
      "learning_rate": 1.910057312929844e-06,
      "loss": 0.4793,
      "step": 52105
    },
    {
      "epoch": 1.6006512456609223,
      "grad_norm": 0.48005053400993347,
      "learning_rate": 1.9097732439702e-06,
      "loss": 0.4266,
      "step": 52106
    },
    {
      "epoch": 1.6006819647958714,
      "grad_norm": 0.42191824316978455,
      "learning_rate": 1.9094891939058435e-06,
      "loss": 0.4599,
      "step": 52107
    },
    {
      "epoch": 1.6007126839308206,
      "grad_norm": 0.39342284202575684,
      "learning_rate": 1.9092051627374398e-06,
      "loss": 0.4973,
      "step": 52108
    },
    {
      "epoch": 1.6007434030657697,
      "grad_norm": 0.40013352036476135,
      "learning_rate": 1.9089211504656525e-06,
      "loss": 0.5106,
      "step": 52109
    },
    {
      "epoch": 1.6007741222007188,
      "grad_norm": 0.4073518216609955,
      "learning_rate": 1.9086371570911465e-06,
      "loss": 0.3589,
      "step": 52110
    },
    {
      "epoch": 1.600804841335668,
      "grad_norm": 0.4573172926902771,
      "learning_rate": 1.9083531826145817e-06,
      "loss": 0.4463,
      "step": 52111
    },
    {
      "epoch": 1.600835560470617,
      "grad_norm": 0.4385443925857544,
      "learning_rate": 1.9080692270366264e-06,
      "loss": 0.4116,
      "step": 52112
    },
    {
      "epoch": 1.6008662796055662,
      "grad_norm": 0.4243599772453308,
      "learning_rate": 1.907785290357934e-06,
      "loss": 0.4016,
      "step": 52113
    },
    {
      "epoch": 1.6008969987405155,
      "grad_norm": 0.4724445939064026,
      "learning_rate": 1.907501372579178e-06,
      "loss": 0.4996,
      "step": 52114
    },
    {
      "epoch": 1.6009277178754646,
      "grad_norm": 0.44299066066741943,
      "learning_rate": 1.9072174737010196e-06,
      "loss": 0.4991,
      "step": 52115
    },
    {
      "epoch": 1.6009584370104137,
      "grad_norm": 0.404488742351532,
      "learning_rate": 1.9069335937241184e-06,
      "loss": 0.4881,
      "step": 52116
    },
    {
      "epoch": 1.600989156145363,
      "grad_norm": 0.41408976912498474,
      "learning_rate": 1.9066497326491384e-06,
      "loss": 0.4784,
      "step": 52117
    },
    {
      "epoch": 1.6010198752803122,
      "grad_norm": 0.4375063180923462,
      "learning_rate": 1.9063658904767423e-06,
      "loss": 0.4629,
      "step": 52118
    },
    {
      "epoch": 1.6010505944152613,
      "grad_norm": 0.4015118181705475,
      "learning_rate": 1.9060820672075975e-06,
      "loss": 0.4283,
      "step": 52119
    },
    {
      "epoch": 1.6010813135502104,
      "grad_norm": 0.44316112995147705,
      "learning_rate": 1.905798262842361e-06,
      "loss": 0.4464,
      "step": 52120
    },
    {
      "epoch": 1.6011120326851596,
      "grad_norm": 0.4103914201259613,
      "learning_rate": 1.9055144773816992e-06,
      "loss": 0.4667,
      "step": 52121
    },
    {
      "epoch": 1.6011427518201087,
      "grad_norm": 0.4294153153896332,
      "learning_rate": 1.9052307108262703e-06,
      "loss": 0.4299,
      "step": 52122
    },
    {
      "epoch": 1.6011734709550578,
      "grad_norm": 0.38324421644210815,
      "learning_rate": 1.9049469631767436e-06,
      "loss": 0.4852,
      "step": 52123
    },
    {
      "epoch": 1.601204190090007,
      "grad_norm": 0.5039907693862915,
      "learning_rate": 1.9046632344337778e-06,
      "loss": 0.5034,
      "step": 52124
    },
    {
      "epoch": 1.6012349092249563,
      "grad_norm": 0.41327378153800964,
      "learning_rate": 1.9043795245980378e-06,
      "loss": 0.4618,
      "step": 52125
    },
    {
      "epoch": 1.6012656283599054,
      "grad_norm": 0.49285462498664856,
      "learning_rate": 1.9040958336701832e-06,
      "loss": 0.4206,
      "step": 52126
    },
    {
      "epoch": 1.6012963474948545,
      "grad_norm": 0.41449546813964844,
      "learning_rate": 1.9038121616508775e-06,
      "loss": 0.4836,
      "step": 52127
    },
    {
      "epoch": 1.6013270666298038,
      "grad_norm": 0.4450894594192505,
      "learning_rate": 1.9035285085407839e-06,
      "loss": 0.4977,
      "step": 52128
    },
    {
      "epoch": 1.601357785764753,
      "grad_norm": 0.41246846318244934,
      "learning_rate": 1.9032448743405674e-06,
      "loss": 0.5038,
      "step": 52129
    },
    {
      "epoch": 1.601388504899702,
      "grad_norm": 0.5307242274284363,
      "learning_rate": 1.9029612590508861e-06,
      "loss": 0.5008,
      "step": 52130
    },
    {
      "epoch": 1.6014192240346512,
      "grad_norm": 0.3777112364768982,
      "learning_rate": 1.902677662672403e-06,
      "loss": 0.4845,
      "step": 52131
    },
    {
      "epoch": 1.6014499431696003,
      "grad_norm": 0.4713734984397888,
      "learning_rate": 1.902394085205783e-06,
      "loss": 0.3896,
      "step": 52132
    },
    {
      "epoch": 1.6014806623045494,
      "grad_norm": 0.43857690691947937,
      "learning_rate": 1.902110526651687e-06,
      "loss": 0.4982,
      "step": 52133
    },
    {
      "epoch": 1.6015113814394986,
      "grad_norm": 0.449755996465683,
      "learning_rate": 1.9018269870107797e-06,
      "loss": 0.408,
      "step": 52134
    },
    {
      "epoch": 1.6015421005744477,
      "grad_norm": 0.452703058719635,
      "learning_rate": 1.9015434662837184e-06,
      "loss": 0.5032,
      "step": 52135
    },
    {
      "epoch": 1.601572819709397,
      "grad_norm": 0.46282434463500977,
      "learning_rate": 1.901259964471167e-06,
      "loss": 0.5071,
      "step": 52136
    },
    {
      "epoch": 1.6016035388443461,
      "grad_norm": 0.40699610114097595,
      "learning_rate": 1.9009764815737897e-06,
      "loss": 0.3584,
      "step": 52137
    },
    {
      "epoch": 1.6016342579792953,
      "grad_norm": 0.41058599948883057,
      "learning_rate": 1.90069301759225e-06,
      "loss": 0.4425,
      "step": 52138
    },
    {
      "epoch": 1.6016649771142446,
      "grad_norm": 0.42164942622184753,
      "learning_rate": 1.9004095725272054e-06,
      "loss": 0.4176,
      "step": 52139
    },
    {
      "epoch": 1.6016956962491937,
      "grad_norm": 0.3998217284679413,
      "learning_rate": 1.9001261463793185e-06,
      "loss": 0.4642,
      "step": 52140
    },
    {
      "epoch": 1.6017264153841428,
      "grad_norm": 0.4171498417854309,
      "learning_rate": 1.8998427391492535e-06,
      "loss": 0.393,
      "step": 52141
    },
    {
      "epoch": 1.601757134519092,
      "grad_norm": 0.45176395773887634,
      "learning_rate": 1.8995593508376742e-06,
      "loss": 0.4216,
      "step": 52142
    },
    {
      "epoch": 1.601787853654041,
      "grad_norm": 0.43761032819747925,
      "learning_rate": 1.8992759814452367e-06,
      "loss": 0.5032,
      "step": 52143
    },
    {
      "epoch": 1.6018185727889902,
      "grad_norm": 0.4804360866546631,
      "learning_rate": 1.898992630972606e-06,
      "loss": 0.51,
      "step": 52144
    },
    {
      "epoch": 1.6018492919239393,
      "grad_norm": 0.44618603587150574,
      "learning_rate": 1.8987092994204437e-06,
      "loss": 0.46,
      "step": 52145
    },
    {
      "epoch": 1.6018800110588884,
      "grad_norm": 0.4552411735057831,
      "learning_rate": 1.898425986789415e-06,
      "loss": 0.4549,
      "step": 52146
    },
    {
      "epoch": 1.6019107301938378,
      "grad_norm": 0.4109685719013214,
      "learning_rate": 1.898142693080175e-06,
      "loss": 0.4907,
      "step": 52147
    },
    {
      "epoch": 1.601941449328787,
      "grad_norm": 0.42478370666503906,
      "learning_rate": 1.8978594182933906e-06,
      "loss": 0.5224,
      "step": 52148
    },
    {
      "epoch": 1.601972168463736,
      "grad_norm": 0.4423442482948303,
      "learning_rate": 1.8975761624297174e-06,
      "loss": 0.3692,
      "step": 52149
    },
    {
      "epoch": 1.6020028875986854,
      "grad_norm": 0.4217146337032318,
      "learning_rate": 1.8972929254898232e-06,
      "loss": 0.4151,
      "step": 52150
    },
    {
      "epoch": 1.6020336067336345,
      "grad_norm": 0.39985841512680054,
      "learning_rate": 1.8970097074743687e-06,
      "loss": 0.4543,
      "step": 52151
    },
    {
      "epoch": 1.6020643258685836,
      "grad_norm": 0.4376455545425415,
      "learning_rate": 1.8967265083840126e-06,
      "loss": 0.4998,
      "step": 52152
    },
    {
      "epoch": 1.6020950450035327,
      "grad_norm": 0.47418132424354553,
      "learning_rate": 1.8964433282194194e-06,
      "loss": 0.5031,
      "step": 52153
    },
    {
      "epoch": 1.6021257641384818,
      "grad_norm": 0.40316689014434814,
      "learning_rate": 1.8961601669812446e-06,
      "loss": 0.4395,
      "step": 52154
    },
    {
      "epoch": 1.602156483273431,
      "grad_norm": 0.4346901774406433,
      "learning_rate": 1.8958770246701585e-06,
      "loss": 0.4892,
      "step": 52155
    },
    {
      "epoch": 1.60218720240838,
      "grad_norm": 0.43721213936805725,
      "learning_rate": 1.8955939012868142e-06,
      "loss": 0.4681,
      "step": 52156
    },
    {
      "epoch": 1.6022179215433292,
      "grad_norm": 0.4772328734397888,
      "learning_rate": 1.8953107968318796e-06,
      "loss": 0.438,
      "step": 52157
    },
    {
      "epoch": 1.6022486406782785,
      "grad_norm": 0.44872617721557617,
      "learning_rate": 1.895027711306008e-06,
      "loss": 0.4253,
      "step": 52158
    },
    {
      "epoch": 1.6022793598132277,
      "grad_norm": 0.37881481647491455,
      "learning_rate": 1.8947446447098695e-06,
      "loss": 0.427,
      "step": 52159
    },
    {
      "epoch": 1.6023100789481768,
      "grad_norm": 0.402739018201828,
      "learning_rate": 1.8944615970441183e-06,
      "loss": 0.4575,
      "step": 52160
    },
    {
      "epoch": 1.6023407980831261,
      "grad_norm": 0.41997355222702026,
      "learning_rate": 1.8941785683094215e-06,
      "loss": 0.4062,
      "step": 52161
    },
    {
      "epoch": 1.6023715172180752,
      "grad_norm": 0.4487374722957611,
      "learning_rate": 1.8938955585064333e-06,
      "loss": 0.4296,
      "step": 52162
    },
    {
      "epoch": 1.6024022363530244,
      "grad_norm": 0.42571887373924255,
      "learning_rate": 1.8936125676358186e-06,
      "loss": 0.4533,
      "step": 52163
    },
    {
      "epoch": 1.6024329554879735,
      "grad_norm": 0.42317456007003784,
      "learning_rate": 1.8933295956982379e-06,
      "loss": 0.4154,
      "step": 52164
    },
    {
      "epoch": 1.6024636746229226,
      "grad_norm": 0.4448423385620117,
      "learning_rate": 1.893046642694355e-06,
      "loss": 0.4402,
      "step": 52165
    },
    {
      "epoch": 1.6024943937578717,
      "grad_norm": 0.3968058228492737,
      "learning_rate": 1.8927637086248253e-06,
      "loss": 0.4235,
      "step": 52166
    },
    {
      "epoch": 1.6025251128928208,
      "grad_norm": 0.4168495237827301,
      "learning_rate": 1.8924807934903111e-06,
      "loss": 0.4518,
      "step": 52167
    },
    {
      "epoch": 1.60255583202777,
      "grad_norm": 0.4079110026359558,
      "learning_rate": 1.8921978972914756e-06,
      "loss": 0.4743,
      "step": 52168
    },
    {
      "epoch": 1.6025865511627193,
      "grad_norm": 0.4435745179653168,
      "learning_rate": 1.8919150200289771e-06,
      "loss": 0.4563,
      "step": 52169
    },
    {
      "epoch": 1.6026172702976684,
      "grad_norm": 0.418104350566864,
      "learning_rate": 1.8916321617034805e-06,
      "loss": 0.4719,
      "step": 52170
    },
    {
      "epoch": 1.6026479894326175,
      "grad_norm": 0.412567138671875,
      "learning_rate": 1.8913493223156409e-06,
      "loss": 0.437,
      "step": 52171
    },
    {
      "epoch": 1.602678708567567,
      "grad_norm": 0.4155207872390747,
      "learning_rate": 1.8910665018661201e-06,
      "loss": 0.4704,
      "step": 52172
    },
    {
      "epoch": 1.602709427702516,
      "grad_norm": 0.4198996126651764,
      "learning_rate": 1.8907837003555807e-06,
      "loss": 0.4138,
      "step": 52173
    },
    {
      "epoch": 1.6027401468374651,
      "grad_norm": 0.418549120426178,
      "learning_rate": 1.8905009177846845e-06,
      "loss": 0.4023,
      "step": 52174
    },
    {
      "epoch": 1.6027708659724142,
      "grad_norm": 0.5341049432754517,
      "learning_rate": 1.8902181541540877e-06,
      "loss": 0.4349,
      "step": 52175
    },
    {
      "epoch": 1.6028015851073634,
      "grad_norm": 0.4182336926460266,
      "learning_rate": 1.8899354094644529e-06,
      "loss": 0.4802,
      "step": 52176
    },
    {
      "epoch": 1.6028323042423125,
      "grad_norm": 0.46654677391052246,
      "learning_rate": 1.8896526837164398e-06,
      "loss": 0.5225,
      "step": 52177
    },
    {
      "epoch": 1.6028630233772616,
      "grad_norm": 0.4867345988750458,
      "learning_rate": 1.889369976910712e-06,
      "loss": 0.5575,
      "step": 52178
    },
    {
      "epoch": 1.6028937425122107,
      "grad_norm": 0.4140782058238983,
      "learning_rate": 1.8890872890479251e-06,
      "loss": 0.5131,
      "step": 52179
    },
    {
      "epoch": 1.60292446164716,
      "grad_norm": 0.4813612699508667,
      "learning_rate": 1.8888046201287402e-06,
      "loss": 0.4248,
      "step": 52180
    },
    {
      "epoch": 1.6029551807821092,
      "grad_norm": 0.47022536396980286,
      "learning_rate": 1.8885219701538194e-06,
      "loss": 0.4818,
      "step": 52181
    },
    {
      "epoch": 1.6029858999170583,
      "grad_norm": 0.40322190523147583,
      "learning_rate": 1.888239339123824e-06,
      "loss": 0.4493,
      "step": 52182
    },
    {
      "epoch": 1.6030166190520077,
      "grad_norm": 0.4423174560070038,
      "learning_rate": 1.8879567270394095e-06,
      "loss": 0.4528,
      "step": 52183
    },
    {
      "epoch": 1.6030473381869568,
      "grad_norm": 0.41659170389175415,
      "learning_rate": 1.8876741339012416e-06,
      "loss": 0.4671,
      "step": 52184
    },
    {
      "epoch": 1.603078057321906,
      "grad_norm": 0.4258001744747162,
      "learning_rate": 1.8873915597099723e-06,
      "loss": 0.4476,
      "step": 52185
    },
    {
      "epoch": 1.603108776456855,
      "grad_norm": 0.44349390268325806,
      "learning_rate": 1.887109004466272e-06,
      "loss": 0.5788,
      "step": 52186
    },
    {
      "epoch": 1.6031394955918041,
      "grad_norm": 0.4499887526035309,
      "learning_rate": 1.8868264681707914e-06,
      "loss": 0.3843,
      "step": 52187
    },
    {
      "epoch": 1.6031702147267533,
      "grad_norm": 0.4135010540485382,
      "learning_rate": 1.8865439508241957e-06,
      "loss": 0.4783,
      "step": 52188
    },
    {
      "epoch": 1.6032009338617024,
      "grad_norm": 0.46156224608421326,
      "learning_rate": 1.886261452427145e-06,
      "loss": 0.4637,
      "step": 52189
    },
    {
      "epoch": 1.6032316529966515,
      "grad_norm": 0.6953304409980774,
      "learning_rate": 1.8859789729802924e-06,
      "loss": 0.4655,
      "step": 52190
    },
    {
      "epoch": 1.6032623721316006,
      "grad_norm": 0.4686621129512787,
      "learning_rate": 1.8856965124843075e-06,
      "loss": 0.5223,
      "step": 52191
    },
    {
      "epoch": 1.60329309126655,
      "grad_norm": 0.4434613883495331,
      "learning_rate": 1.8854140709398428e-06,
      "loss": 0.4431,
      "step": 52192
    },
    {
      "epoch": 1.603323810401499,
      "grad_norm": 0.4768386483192444,
      "learning_rate": 1.8851316483475624e-06,
      "loss": 0.5496,
      "step": 52193
    },
    {
      "epoch": 1.6033545295364484,
      "grad_norm": 0.41304969787597656,
      "learning_rate": 1.8848492447081213e-06,
      "loss": 0.4418,
      "step": 52194
    },
    {
      "epoch": 1.6033852486713975,
      "grad_norm": 0.42292943596839905,
      "learning_rate": 1.8845668600221823e-06,
      "loss": 0.432,
      "step": 52195
    },
    {
      "epoch": 1.6034159678063467,
      "grad_norm": 0.4853842556476593,
      "learning_rate": 1.8842844942904037e-06,
      "loss": 0.51,
      "step": 52196
    },
    {
      "epoch": 1.6034466869412958,
      "grad_norm": 0.4039233326911926,
      "learning_rate": 1.8840021475134474e-06,
      "loss": 0.4239,
      "step": 52197
    },
    {
      "epoch": 1.603477406076245,
      "grad_norm": 0.42580103874206543,
      "learning_rate": 1.8837198196919692e-06,
      "loss": 0.4461,
      "step": 52198
    },
    {
      "epoch": 1.603508125211194,
      "grad_norm": 0.418934166431427,
      "learning_rate": 1.88343751082663e-06,
      "loss": 0.4507,
      "step": 52199
    },
    {
      "epoch": 1.6035388443461431,
      "grad_norm": 0.4451909363269806,
      "learning_rate": 1.8831552209180893e-06,
      "loss": 0.4944,
      "step": 52200
    },
    {
      "epoch": 1.6035695634810923,
      "grad_norm": 0.4980269968509674,
      "learning_rate": 1.8828729499670084e-06,
      "loss": 0.4605,
      "step": 52201
    },
    {
      "epoch": 1.6036002826160414,
      "grad_norm": 0.43792489171028137,
      "learning_rate": 1.8825906979740428e-06,
      "loss": 0.4365,
      "step": 52202
    },
    {
      "epoch": 1.6036310017509907,
      "grad_norm": 0.4814901649951935,
      "learning_rate": 1.8823084649398537e-06,
      "loss": 0.5056,
      "step": 52203
    },
    {
      "epoch": 1.6036617208859398,
      "grad_norm": 0.4438838064670563,
      "learning_rate": 1.8820262508650988e-06,
      "loss": 0.5121,
      "step": 52204
    },
    {
      "epoch": 1.6036924400208892,
      "grad_norm": 0.40264880657196045,
      "learning_rate": 1.8817440557504396e-06,
      "loss": 0.4668,
      "step": 52205
    },
    {
      "epoch": 1.6037231591558383,
      "grad_norm": 0.450924277305603,
      "learning_rate": 1.8814618795965367e-06,
      "loss": 0.4191,
      "step": 52206
    },
    {
      "epoch": 1.6037538782907874,
      "grad_norm": 0.3912995159626007,
      "learning_rate": 1.881179722404044e-06,
      "loss": 0.4206,
      "step": 52207
    },
    {
      "epoch": 1.6037845974257365,
      "grad_norm": 0.43623051047325134,
      "learning_rate": 1.8808975841736233e-06,
      "loss": 0.5033,
      "step": 52208
    },
    {
      "epoch": 1.6038153165606857,
      "grad_norm": 0.4623398780822754,
      "learning_rate": 1.8806154649059327e-06,
      "loss": 0.4412,
      "step": 52209
    },
    {
      "epoch": 1.6038460356956348,
      "grad_norm": 0.40341898798942566,
      "learning_rate": 1.880333364601634e-06,
      "loss": 0.4772,
      "step": 52210
    },
    {
      "epoch": 1.603876754830584,
      "grad_norm": 0.4371728301048279,
      "learning_rate": 1.8800512832613827e-06,
      "loss": 0.4258,
      "step": 52211
    },
    {
      "epoch": 1.603907473965533,
      "grad_norm": 0.39717698097229004,
      "learning_rate": 1.8797692208858376e-06,
      "loss": 0.4006,
      "step": 52212
    },
    {
      "epoch": 1.6039381931004821,
      "grad_norm": 0.38512012362480164,
      "learning_rate": 1.8794871774756585e-06,
      "loss": 0.4921,
      "step": 52213
    },
    {
      "epoch": 1.6039689122354315,
      "grad_norm": 0.4069778025150299,
      "learning_rate": 1.879205153031507e-06,
      "loss": 0.4687,
      "step": 52214
    },
    {
      "epoch": 1.6039996313703806,
      "grad_norm": 0.4269189238548279,
      "learning_rate": 1.878923147554037e-06,
      "loss": 0.5253,
      "step": 52215
    },
    {
      "epoch": 1.6040303505053297,
      "grad_norm": 0.4325767457485199,
      "learning_rate": 1.8786411610439115e-06,
      "loss": 0.4626,
      "step": 52216
    },
    {
      "epoch": 1.604061069640279,
      "grad_norm": 0.44128331542015076,
      "learning_rate": 1.8783591935017808e-06,
      "loss": 0.5154,
      "step": 52217
    },
    {
      "epoch": 1.6040917887752282,
      "grad_norm": 0.45526954531669617,
      "learning_rate": 1.8780772449283158e-06,
      "loss": 0.4601,
      "step": 52218
    },
    {
      "epoch": 1.6041225079101773,
      "grad_norm": 0.40411001443862915,
      "learning_rate": 1.8777953153241647e-06,
      "loss": 0.5451,
      "step": 52219
    },
    {
      "epoch": 1.6041532270451264,
      "grad_norm": 0.4730280637741089,
      "learning_rate": 1.8775134046899934e-06,
      "loss": 0.5111,
      "step": 52220
    },
    {
      "epoch": 1.6041839461800755,
      "grad_norm": 0.41768887639045715,
      "learning_rate": 1.8772315130264519e-06,
      "loss": 0.4867,
      "step": 52221
    },
    {
      "epoch": 1.6042146653150247,
      "grad_norm": 0.5399468541145325,
      "learning_rate": 1.876949640334208e-06,
      "loss": 0.4907,
      "step": 52222
    },
    {
      "epoch": 1.6042453844499738,
      "grad_norm": 0.4551980793476105,
      "learning_rate": 1.8766677866139127e-06,
      "loss": 0.4132,
      "step": 52223
    },
    {
      "epoch": 1.604276103584923,
      "grad_norm": 0.44837823510169983,
      "learning_rate": 1.8763859518662275e-06,
      "loss": 0.5832,
      "step": 52224
    },
    {
      "epoch": 1.6043068227198722,
      "grad_norm": 0.4298132658004761,
      "learning_rate": 1.8761041360918132e-06,
      "loss": 0.4654,
      "step": 52225
    },
    {
      "epoch": 1.6043375418548214,
      "grad_norm": 0.4012893736362457,
      "learning_rate": 1.87582233929132e-06,
      "loss": 0.4517,
      "step": 52226
    },
    {
      "epoch": 1.6043682609897705,
      "grad_norm": 0.46029046177864075,
      "learning_rate": 1.8755405614654153e-06,
      "loss": 0.4629,
      "step": 52227
    },
    {
      "epoch": 1.6043989801247198,
      "grad_norm": 0.4557710289955139,
      "learning_rate": 1.8752588026147512e-06,
      "loss": 0.4537,
      "step": 52228
    },
    {
      "epoch": 1.604429699259669,
      "grad_norm": 0.35440364480018616,
      "learning_rate": 1.8749770627399899e-06,
      "loss": 0.4041,
      "step": 52229
    },
    {
      "epoch": 1.604460418394618,
      "grad_norm": 0.4279012382030487,
      "learning_rate": 1.8746953418417847e-06,
      "loss": 0.4826,
      "step": 52230
    },
    {
      "epoch": 1.6044911375295672,
      "grad_norm": 0.44305619597435,
      "learning_rate": 1.8744136399207958e-06,
      "loss": 0.4987,
      "step": 52231
    },
    {
      "epoch": 1.6045218566645163,
      "grad_norm": 0.4495251178741455,
      "learning_rate": 1.8741319569776817e-06,
      "loss": 0.5141,
      "step": 52232
    },
    {
      "epoch": 1.6045525757994654,
      "grad_norm": 0.39076539874076843,
      "learning_rate": 1.8738502930131019e-06,
      "loss": 0.4772,
      "step": 52233
    },
    {
      "epoch": 1.6045832949344145,
      "grad_norm": 0.45762476325035095,
      "learning_rate": 1.8735686480277104e-06,
      "loss": 0.5087,
      "step": 52234
    },
    {
      "epoch": 1.6046140140693637,
      "grad_norm": 0.4427106976509094,
      "learning_rate": 1.8732870220221654e-06,
      "loss": 0.4699,
      "step": 52235
    },
    {
      "epoch": 1.604644733204313,
      "grad_norm": 0.40687257051467896,
      "learning_rate": 1.8730054149971277e-06,
      "loss": 0.5023,
      "step": 52236
    },
    {
      "epoch": 1.6046754523392621,
      "grad_norm": 0.45499691367149353,
      "learning_rate": 1.8727238269532554e-06,
      "loss": 0.4485,
      "step": 52237
    },
    {
      "epoch": 1.6047061714742112,
      "grad_norm": 0.46017536520957947,
      "learning_rate": 1.8724422578912016e-06,
      "loss": 0.5126,
      "step": 52238
    },
    {
      "epoch": 1.6047368906091606,
      "grad_norm": 0.5583511590957642,
      "learning_rate": 1.8721607078116267e-06,
      "loss": 0.4757,
      "step": 52239
    },
    {
      "epoch": 1.6047676097441097,
      "grad_norm": 0.42425012588500977,
      "learning_rate": 1.871879176715188e-06,
      "loss": 0.4413,
      "step": 52240
    },
    {
      "epoch": 1.6047983288790588,
      "grad_norm": 0.4587022662162781,
      "learning_rate": 1.8715976646025435e-06,
      "loss": 0.4678,
      "step": 52241
    },
    {
      "epoch": 1.604829048014008,
      "grad_norm": 0.4288707375526428,
      "learning_rate": 1.871316171474352e-06,
      "loss": 0.504,
      "step": 52242
    },
    {
      "epoch": 1.604859767148957,
      "grad_norm": 0.4418855905532837,
      "learning_rate": 1.8710346973312677e-06,
      "loss": 0.4089,
      "step": 52243
    },
    {
      "epoch": 1.6048904862839062,
      "grad_norm": 0.43536376953125,
      "learning_rate": 1.8707532421739494e-06,
      "loss": 0.4418,
      "step": 52244
    },
    {
      "epoch": 1.6049212054188553,
      "grad_norm": 0.4161968529224396,
      "learning_rate": 1.8704718060030548e-06,
      "loss": 0.4112,
      "step": 52245
    },
    {
      "epoch": 1.6049519245538044,
      "grad_norm": 0.37434259057044983,
      "learning_rate": 1.870190388819243e-06,
      "loss": 0.4664,
      "step": 52246
    },
    {
      "epoch": 1.6049826436887538,
      "grad_norm": 0.4199257791042328,
      "learning_rate": 1.869908990623167e-06,
      "loss": 0.3786,
      "step": 52247
    },
    {
      "epoch": 1.6050133628237029,
      "grad_norm": 0.44364896416664124,
      "learning_rate": 1.8696276114154866e-06,
      "loss": 0.5189,
      "step": 52248
    },
    {
      "epoch": 1.605044081958652,
      "grad_norm": 0.39178267121315,
      "learning_rate": 1.8693462511968585e-06,
      "loss": 0.4351,
      "step": 52249
    },
    {
      "epoch": 1.6050748010936013,
      "grad_norm": 0.3928394615650177,
      "learning_rate": 1.8690649099679426e-06,
      "loss": 0.4758,
      "step": 52250
    },
    {
      "epoch": 1.6051055202285505,
      "grad_norm": 0.5316212177276611,
      "learning_rate": 1.8687835877293914e-06,
      "loss": 0.4696,
      "step": 52251
    },
    {
      "epoch": 1.6051362393634996,
      "grad_norm": 0.4452327489852905,
      "learning_rate": 1.8685022844818656e-06,
      "loss": 0.4769,
      "step": 52252
    },
    {
      "epoch": 1.6051669584984487,
      "grad_norm": 0.44376084208488464,
      "learning_rate": 1.868221000226016e-06,
      "loss": 0.4599,
      "step": 52253
    },
    {
      "epoch": 1.6051976776333978,
      "grad_norm": 0.4460911452770233,
      "learning_rate": 1.8679397349625094e-06,
      "loss": 0.4403,
      "step": 52254
    },
    {
      "epoch": 1.605228396768347,
      "grad_norm": 0.3764398992061615,
      "learning_rate": 1.8676584886919947e-06,
      "loss": 0.4224,
      "step": 52255
    },
    {
      "epoch": 1.605259115903296,
      "grad_norm": 0.47205600142478943,
      "learning_rate": 1.8673772614151341e-06,
      "loss": 0.4508,
      "step": 52256
    },
    {
      "epoch": 1.6052898350382452,
      "grad_norm": 0.44347476959228516,
      "learning_rate": 1.86709605313258e-06,
      "loss": 0.4713,
      "step": 52257
    },
    {
      "epoch": 1.6053205541731945,
      "grad_norm": 0.4099448025226593,
      "learning_rate": 1.8668148638449902e-06,
      "loss": 0.4725,
      "step": 52258
    },
    {
      "epoch": 1.6053512733081436,
      "grad_norm": 0.3857315182685852,
      "learning_rate": 1.8665336935530231e-06,
      "loss": 0.4387,
      "step": 52259
    },
    {
      "epoch": 1.6053819924430928,
      "grad_norm": 0.46411842107772827,
      "learning_rate": 1.8662525422573342e-06,
      "loss": 0.4343,
      "step": 52260
    },
    {
      "epoch": 1.605412711578042,
      "grad_norm": 0.4146459102630615,
      "learning_rate": 1.8659714099585825e-06,
      "loss": 0.417,
      "step": 52261
    },
    {
      "epoch": 1.6054434307129912,
      "grad_norm": 0.49678441882133484,
      "learning_rate": 1.8656902966574176e-06,
      "loss": 0.4177,
      "step": 52262
    },
    {
      "epoch": 1.6054741498479403,
      "grad_norm": 0.3873647153377533,
      "learning_rate": 1.8654092023545067e-06,
      "loss": 0.5165,
      "step": 52263
    },
    {
      "epoch": 1.6055048689828895,
      "grad_norm": 0.41191256046295166,
      "learning_rate": 1.8651281270504984e-06,
      "loss": 0.4465,
      "step": 52264
    },
    {
      "epoch": 1.6055355881178386,
      "grad_norm": 0.446611613035202,
      "learning_rate": 1.8648470707460541e-06,
      "loss": 0.3538,
      "step": 52265
    },
    {
      "epoch": 1.6055663072527877,
      "grad_norm": 0.4263530671596527,
      "learning_rate": 1.8645660334418247e-06,
      "loss": 0.5028,
      "step": 52266
    },
    {
      "epoch": 1.6055970263877368,
      "grad_norm": 0.42738211154937744,
      "learning_rate": 1.8642850151384694e-06,
      "loss": 0.5271,
      "step": 52267
    },
    {
      "epoch": 1.605627745522686,
      "grad_norm": 0.4154217839241028,
      "learning_rate": 1.8640040158366446e-06,
      "loss": 0.5075,
      "step": 52268
    },
    {
      "epoch": 1.6056584646576353,
      "grad_norm": 0.4581364691257477,
      "learning_rate": 1.8637230355370094e-06,
      "loss": 0.4598,
      "step": 52269
    },
    {
      "epoch": 1.6056891837925844,
      "grad_norm": 0.41487863659858704,
      "learning_rate": 1.863442074240215e-06,
      "loss": 0.4139,
      "step": 52270
    },
    {
      "epoch": 1.6057199029275335,
      "grad_norm": 0.39596858620643616,
      "learning_rate": 1.86316113194692e-06,
      "loss": 0.487,
      "step": 52271
    },
    {
      "epoch": 1.6057506220624829,
      "grad_norm": 0.5526456236839294,
      "learning_rate": 1.862880208657779e-06,
      "loss": 0.4563,
      "step": 52272
    },
    {
      "epoch": 1.605781341197432,
      "grad_norm": 0.4934738874435425,
      "learning_rate": 1.8625993043734536e-06,
      "loss": 0.5234,
      "step": 52273
    },
    {
      "epoch": 1.605812060332381,
      "grad_norm": 0.4162888824939728,
      "learning_rate": 1.8623184190945932e-06,
      "loss": 0.4798,
      "step": 52274
    },
    {
      "epoch": 1.6058427794673302,
      "grad_norm": 0.4120601713657379,
      "learning_rate": 1.862037552821856e-06,
      "loss": 0.5474,
      "step": 52275
    },
    {
      "epoch": 1.6058734986022793,
      "grad_norm": 0.4113464653491974,
      "learning_rate": 1.8617567055558983e-06,
      "loss": 0.478,
      "step": 52276
    },
    {
      "epoch": 1.6059042177372285,
      "grad_norm": 0.40337514877319336,
      "learning_rate": 1.8614758772973797e-06,
      "loss": 0.4652,
      "step": 52277
    },
    {
      "epoch": 1.6059349368721776,
      "grad_norm": 0.40713974833488464,
      "learning_rate": 1.8611950680469482e-06,
      "loss": 0.3923,
      "step": 52278
    },
    {
      "epoch": 1.6059656560071267,
      "grad_norm": 0.398408442735672,
      "learning_rate": 1.8609142778052658e-06,
      "loss": 0.4484,
      "step": 52279
    },
    {
      "epoch": 1.605996375142076,
      "grad_norm": 0.46424221992492676,
      "learning_rate": 1.8606335065729852e-06,
      "loss": 0.4056,
      "step": 52280
    },
    {
      "epoch": 1.6060270942770252,
      "grad_norm": 0.4170586168766022,
      "learning_rate": 1.860352754350765e-06,
      "loss": 0.4264,
      "step": 52281
    },
    {
      "epoch": 1.6060578134119743,
      "grad_norm": 0.4460243880748749,
      "learning_rate": 1.860072021139261e-06,
      "loss": 0.435,
      "step": 52282
    },
    {
      "epoch": 1.6060885325469236,
      "grad_norm": 0.4139046370983124,
      "learning_rate": 1.8597913069391249e-06,
      "loss": 0.5691,
      "step": 52283
    },
    {
      "epoch": 1.6061192516818728,
      "grad_norm": 0.3934907019138336,
      "learning_rate": 1.8595106117510141e-06,
      "loss": 0.5405,
      "step": 52284
    },
    {
      "epoch": 1.6061499708168219,
      "grad_norm": 0.4190736413002014,
      "learning_rate": 1.859229935575586e-06,
      "loss": 0.425,
      "step": 52285
    },
    {
      "epoch": 1.606180689951771,
      "grad_norm": 0.4335128366947174,
      "learning_rate": 1.8589492784134966e-06,
      "loss": 0.4625,
      "step": 52286
    },
    {
      "epoch": 1.60621140908672,
      "grad_norm": 0.42885977029800415,
      "learning_rate": 1.8586686402653975e-06,
      "loss": 0.5134,
      "step": 52287
    },
    {
      "epoch": 1.6062421282216692,
      "grad_norm": 0.4298584461212158,
      "learning_rate": 1.8583880211319482e-06,
      "loss": 0.4417,
      "step": 52288
    },
    {
      "epoch": 1.6062728473566183,
      "grad_norm": 0.40298280119895935,
      "learning_rate": 1.8581074210137983e-06,
      "loss": 0.4152,
      "step": 52289
    },
    {
      "epoch": 1.6063035664915675,
      "grad_norm": 0.45998498797416687,
      "learning_rate": 1.8578268399116117e-06,
      "loss": 0.5508,
      "step": 52290
    },
    {
      "epoch": 1.6063342856265168,
      "grad_norm": 0.41652244329452515,
      "learning_rate": 1.8575462778260367e-06,
      "loss": 0.4749,
      "step": 52291
    },
    {
      "epoch": 1.606365004761466,
      "grad_norm": 0.4067612588405609,
      "learning_rate": 1.8572657347577339e-06,
      "loss": 0.5522,
      "step": 52292
    },
    {
      "epoch": 1.606395723896415,
      "grad_norm": 0.45126596093177795,
      "learning_rate": 1.8569852107073516e-06,
      "loss": 0.4397,
      "step": 52293
    },
    {
      "epoch": 1.6064264430313644,
      "grad_norm": 0.42310842871665955,
      "learning_rate": 1.8567047056755505e-06,
      "loss": 0.4989,
      "step": 52294
    },
    {
      "epoch": 1.6064571621663135,
      "grad_norm": 0.4508897364139557,
      "learning_rate": 1.8564242196629845e-06,
      "loss": 0.4531,
      "step": 52295
    },
    {
      "epoch": 1.6064878813012626,
      "grad_norm": 0.4615485370159149,
      "learning_rate": 1.8561437526703074e-06,
      "loss": 0.4415,
      "step": 52296
    },
    {
      "epoch": 1.6065186004362118,
      "grad_norm": 0.40728044509887695,
      "learning_rate": 1.855863304698179e-06,
      "loss": 0.4826,
      "step": 52297
    },
    {
      "epoch": 1.6065493195711609,
      "grad_norm": 0.4090287387371063,
      "learning_rate": 1.855582875747247e-06,
      "loss": 0.4963,
      "step": 52298
    },
    {
      "epoch": 1.60658003870611,
      "grad_norm": 0.43537598848342896,
      "learning_rate": 1.8553024658181707e-06,
      "loss": 0.4907,
      "step": 52299
    },
    {
      "epoch": 1.6066107578410591,
      "grad_norm": 0.4403902590274811,
      "learning_rate": 1.8550220749116044e-06,
      "loss": 0.3767,
      "step": 52300
    },
    {
      "epoch": 1.6066414769760082,
      "grad_norm": 0.4134182929992676,
      "learning_rate": 1.8547417030282045e-06,
      "loss": 0.4705,
      "step": 52301
    },
    {
      "epoch": 1.6066721961109574,
      "grad_norm": 0.4256487190723419,
      "learning_rate": 1.8544613501686226e-06,
      "loss": 0.4505,
      "step": 52302
    },
    {
      "epoch": 1.6067029152459067,
      "grad_norm": 0.46798375248908997,
      "learning_rate": 1.854181016333515e-06,
      "loss": 0.4026,
      "step": 52303
    },
    {
      "epoch": 1.6067336343808558,
      "grad_norm": 0.38887736201286316,
      "learning_rate": 1.8539007015235354e-06,
      "loss": 0.4524,
      "step": 52304
    },
    {
      "epoch": 1.6067643535158052,
      "grad_norm": 0.43630683422088623,
      "learning_rate": 1.8536204057393437e-06,
      "loss": 0.5241,
      "step": 52305
    },
    {
      "epoch": 1.6067950726507543,
      "grad_norm": 0.43911972641944885,
      "learning_rate": 1.8533401289815877e-06,
      "loss": 0.458,
      "step": 52306
    },
    {
      "epoch": 1.6068257917857034,
      "grad_norm": 0.42283180356025696,
      "learning_rate": 1.853059871250924e-06,
      "loss": 0.4696,
      "step": 52307
    },
    {
      "epoch": 1.6068565109206525,
      "grad_norm": 0.44179853796958923,
      "learning_rate": 1.8527796325480086e-06,
      "loss": 0.4409,
      "step": 52308
    },
    {
      "epoch": 1.6068872300556016,
      "grad_norm": 0.4945034384727478,
      "learning_rate": 1.8524994128734975e-06,
      "loss": 0.4078,
      "step": 52309
    },
    {
      "epoch": 1.6069179491905508,
      "grad_norm": 0.40005865693092346,
      "learning_rate": 1.8522192122280402e-06,
      "loss": 0.4143,
      "step": 52310
    },
    {
      "epoch": 1.6069486683254999,
      "grad_norm": 0.4184034466743469,
      "learning_rate": 1.8519390306122953e-06,
      "loss": 0.4375,
      "step": 52311
    },
    {
      "epoch": 1.606979387460449,
      "grad_norm": 0.43703606724739075,
      "learning_rate": 1.8516588680269143e-06,
      "loss": 0.4491,
      "step": 52312
    },
    {
      "epoch": 1.6070101065953981,
      "grad_norm": 0.44821250438690186,
      "learning_rate": 1.8513787244725568e-06,
      "loss": 0.4595,
      "step": 52313
    },
    {
      "epoch": 1.6070408257303475,
      "grad_norm": 0.3842889666557312,
      "learning_rate": 1.8510985999498698e-06,
      "loss": 0.3848,
      "step": 52314
    },
    {
      "epoch": 1.6070715448652966,
      "grad_norm": 0.4976363778114319,
      "learning_rate": 1.850818494459512e-06,
      "loss": 0.4797,
      "step": 52315
    },
    {
      "epoch": 1.607102264000246,
      "grad_norm": 0.4155903160572052,
      "learning_rate": 1.850538408002136e-06,
      "loss": 0.5079,
      "step": 52316
    },
    {
      "epoch": 1.607132983135195,
      "grad_norm": 0.4280179738998413,
      "learning_rate": 1.850258340578398e-06,
      "loss": 0.4366,
      "step": 52317
    },
    {
      "epoch": 1.6071637022701442,
      "grad_norm": 0.4127473533153534,
      "learning_rate": 1.849978292188952e-06,
      "loss": 0.4686,
      "step": 52318
    },
    {
      "epoch": 1.6071944214050933,
      "grad_norm": 0.4212663769721985,
      "learning_rate": 1.8496982628344485e-06,
      "loss": 0.4371,
      "step": 52319
    },
    {
      "epoch": 1.6072251405400424,
      "grad_norm": 0.42863228917121887,
      "learning_rate": 1.8494182525155468e-06,
      "loss": 0.4851,
      "step": 52320
    },
    {
      "epoch": 1.6072558596749915,
      "grad_norm": 0.487284392118454,
      "learning_rate": 1.8491382612328934e-06,
      "loss": 0.4352,
      "step": 52321
    },
    {
      "epoch": 1.6072865788099406,
      "grad_norm": 0.39237701892852783,
      "learning_rate": 1.848858288987151e-06,
      "loss": 0.4421,
      "step": 52322
    },
    {
      "epoch": 1.6073172979448898,
      "grad_norm": 0.4446587562561035,
      "learning_rate": 1.8485783357789678e-06,
      "loss": 0.5344,
      "step": 52323
    },
    {
      "epoch": 1.6073480170798389,
      "grad_norm": 0.4967423379421234,
      "learning_rate": 1.848298401609001e-06,
      "loss": 0.4479,
      "step": 52324
    },
    {
      "epoch": 1.6073787362147882,
      "grad_norm": 0.4440557360649109,
      "learning_rate": 1.8480184864778971e-06,
      "loss": 0.4506,
      "step": 52325
    },
    {
      "epoch": 1.6074094553497373,
      "grad_norm": 0.4293051064014435,
      "learning_rate": 1.847738590386321e-06,
      "loss": 0.4287,
      "step": 52326
    },
    {
      "epoch": 1.6074401744846865,
      "grad_norm": 0.4345611333847046,
      "learning_rate": 1.8474587133349187e-06,
      "loss": 0.3898,
      "step": 52327
    },
    {
      "epoch": 1.6074708936196358,
      "grad_norm": 0.4766983985900879,
      "learning_rate": 1.8471788553243475e-06,
      "loss": 0.4891,
      "step": 52328
    },
    {
      "epoch": 1.607501612754585,
      "grad_norm": 0.40671104192733765,
      "learning_rate": 1.846899016355258e-06,
      "loss": 0.5379,
      "step": 52329
    },
    {
      "epoch": 1.607532331889534,
      "grad_norm": 0.406256765127182,
      "learning_rate": 1.8466191964283043e-06,
      "loss": 0.5386,
      "step": 52330
    },
    {
      "epoch": 1.6075630510244832,
      "grad_norm": 0.42870572209358215,
      "learning_rate": 1.846339395544141e-06,
      "loss": 0.5133,
      "step": 52331
    },
    {
      "epoch": 1.6075937701594323,
      "grad_norm": 0.4406724274158478,
      "learning_rate": 1.8460596137034248e-06,
      "loss": 0.4141,
      "step": 52332
    },
    {
      "epoch": 1.6076244892943814,
      "grad_norm": 0.4495595097541809,
      "learning_rate": 1.8457798509068025e-06,
      "loss": 0.4886,
      "step": 52333
    },
    {
      "epoch": 1.6076552084293305,
      "grad_norm": 0.47757792472839355,
      "learning_rate": 1.8455001071549317e-06,
      "loss": 0.4467,
      "step": 52334
    },
    {
      "epoch": 1.6076859275642796,
      "grad_norm": 0.3807528614997864,
      "learning_rate": 1.8452203824484639e-06,
      "loss": 0.4632,
      "step": 52335
    },
    {
      "epoch": 1.607716646699229,
      "grad_norm": 0.4252505600452423,
      "learning_rate": 1.844940676788054e-06,
      "loss": 0.4394,
      "step": 52336
    },
    {
      "epoch": 1.607747365834178,
      "grad_norm": 0.39038094878196716,
      "learning_rate": 1.8446609901743573e-06,
      "loss": 0.3994,
      "step": 52337
    },
    {
      "epoch": 1.6077780849691272,
      "grad_norm": 0.3946795165538788,
      "learning_rate": 1.8443813226080209e-06,
      "loss": 0.4232,
      "step": 52338
    },
    {
      "epoch": 1.6078088041040766,
      "grad_norm": 0.47793176770210266,
      "learning_rate": 1.8441016740897033e-06,
      "loss": 0.5431,
      "step": 52339
    },
    {
      "epoch": 1.6078395232390257,
      "grad_norm": 0.4204143285751343,
      "learning_rate": 1.843822044620054e-06,
      "loss": 0.5204,
      "step": 52340
    },
    {
      "epoch": 1.6078702423739748,
      "grad_norm": 0.43350329995155334,
      "learning_rate": 1.843542434199732e-06,
      "loss": 0.4684,
      "step": 52341
    },
    {
      "epoch": 1.607900961508924,
      "grad_norm": 0.4123888611793518,
      "learning_rate": 1.843262842829383e-06,
      "loss": 0.4247,
      "step": 52342
    },
    {
      "epoch": 1.607931680643873,
      "grad_norm": 0.4915047883987427,
      "learning_rate": 1.842983270509663e-06,
      "loss": 0.505,
      "step": 52343
    },
    {
      "epoch": 1.6079623997788222,
      "grad_norm": 0.4550814926624298,
      "learning_rate": 1.8427037172412254e-06,
      "loss": 0.439,
      "step": 52344
    },
    {
      "epoch": 1.6079931189137713,
      "grad_norm": 0.40397322177886963,
      "learning_rate": 1.8424241830247258e-06,
      "loss": 0.4333,
      "step": 52345
    },
    {
      "epoch": 1.6080238380487204,
      "grad_norm": 0.4256298243999481,
      "learning_rate": 1.8421446678608113e-06,
      "loss": 0.3759,
      "step": 52346
    },
    {
      "epoch": 1.6080545571836697,
      "grad_norm": 0.4073382019996643,
      "learning_rate": 1.841865171750138e-06,
      "loss": 0.4628,
      "step": 52347
    },
    {
      "epoch": 1.6080852763186189,
      "grad_norm": 0.5139085054397583,
      "learning_rate": 1.8415856946933586e-06,
      "loss": 0.4071,
      "step": 52348
    },
    {
      "epoch": 1.608115995453568,
      "grad_norm": 0.46759772300720215,
      "learning_rate": 1.8413062366911283e-06,
      "loss": 0.479,
      "step": 52349
    },
    {
      "epoch": 1.6081467145885173,
      "grad_norm": 0.4292548596858978,
      "learning_rate": 1.8410267977440932e-06,
      "loss": 0.4813,
      "step": 52350
    },
    {
      "epoch": 1.6081774337234664,
      "grad_norm": 0.44851529598236084,
      "learning_rate": 1.8407473778529116e-06,
      "loss": 0.4473,
      "step": 52351
    },
    {
      "epoch": 1.6082081528584156,
      "grad_norm": 0.42507004737854004,
      "learning_rate": 1.8404679770182332e-06,
      "loss": 0.4539,
      "step": 52352
    },
    {
      "epoch": 1.6082388719933647,
      "grad_norm": 0.5019464492797852,
      "learning_rate": 1.8401885952407117e-06,
      "loss": 0.4245,
      "step": 52353
    },
    {
      "epoch": 1.6082695911283138,
      "grad_norm": 0.45307695865631104,
      "learning_rate": 1.8399092325210021e-06,
      "loss": 0.5269,
      "step": 52354
    },
    {
      "epoch": 1.608300310263263,
      "grad_norm": 0.4383751153945923,
      "learning_rate": 1.839629888859752e-06,
      "loss": 0.4378,
      "step": 52355
    },
    {
      "epoch": 1.608331029398212,
      "grad_norm": 0.4323039650917053,
      "learning_rate": 1.8393505642576193e-06,
      "loss": 0.4491,
      "step": 52356
    },
    {
      "epoch": 1.6083617485331612,
      "grad_norm": 0.4580022990703583,
      "learning_rate": 1.8390712587152482e-06,
      "loss": 0.4488,
      "step": 52357
    },
    {
      "epoch": 1.6083924676681105,
      "grad_norm": 0.43785908818244934,
      "learning_rate": 1.8387919722333004e-06,
      "loss": 0.4424,
      "step": 52358
    },
    {
      "epoch": 1.6084231868030596,
      "grad_norm": 0.3828723430633545,
      "learning_rate": 1.8385127048124219e-06,
      "loss": 0.4857,
      "step": 52359
    },
    {
      "epoch": 1.6084539059380087,
      "grad_norm": 0.4463837742805481,
      "learning_rate": 1.838233456453269e-06,
      "loss": 0.4912,
      "step": 52360
    },
    {
      "epoch": 1.608484625072958,
      "grad_norm": 0.42957374453544617,
      "learning_rate": 1.8379542271564899e-06,
      "loss": 0.4881,
      "step": 52361
    },
    {
      "epoch": 1.6085153442079072,
      "grad_norm": 0.4603225588798523,
      "learning_rate": 1.8376750169227386e-06,
      "loss": 0.4653,
      "step": 52362
    },
    {
      "epoch": 1.6085460633428563,
      "grad_norm": 0.42247286438941956,
      "learning_rate": 1.8373958257526669e-06,
      "loss": 0.3983,
      "step": 52363
    },
    {
      "epoch": 1.6085767824778054,
      "grad_norm": 0.4431842267513275,
      "learning_rate": 1.8371166536469308e-06,
      "loss": 0.4431,
      "step": 52364
    },
    {
      "epoch": 1.6086075016127546,
      "grad_norm": 0.4382431209087372,
      "learning_rate": 1.8368375006061755e-06,
      "loss": 0.4935,
      "step": 52365
    },
    {
      "epoch": 1.6086382207477037,
      "grad_norm": 0.43066251277923584,
      "learning_rate": 1.8365583666310572e-06,
      "loss": 0.4785,
      "step": 52366
    },
    {
      "epoch": 1.6086689398826528,
      "grad_norm": 0.45328962802886963,
      "learning_rate": 1.8362792517222261e-06,
      "loss": 0.4923,
      "step": 52367
    },
    {
      "epoch": 1.608699659017602,
      "grad_norm": 0.4251551628112793,
      "learning_rate": 1.8360001558803376e-06,
      "loss": 0.5557,
      "step": 52368
    },
    {
      "epoch": 1.6087303781525513,
      "grad_norm": 0.429870069026947,
      "learning_rate": 1.8357210791060388e-06,
      "loss": 0.461,
      "step": 52369
    },
    {
      "epoch": 1.6087610972875004,
      "grad_norm": 0.40713149309158325,
      "learning_rate": 1.8354420213999824e-06,
      "loss": 0.4697,
      "step": 52370
    },
    {
      "epoch": 1.6087918164224495,
      "grad_norm": 0.4221669137477875,
      "learning_rate": 1.8351629827628226e-06,
      "loss": 0.4496,
      "step": 52371
    },
    {
      "epoch": 1.6088225355573988,
      "grad_norm": 0.40100371837615967,
      "learning_rate": 1.8348839631952097e-06,
      "loss": 0.5046,
      "step": 52372
    },
    {
      "epoch": 1.608853254692348,
      "grad_norm": 0.41936689615249634,
      "learning_rate": 1.834604962697798e-06,
      "loss": 0.4184,
      "step": 52373
    },
    {
      "epoch": 1.608883973827297,
      "grad_norm": 0.4419673681259155,
      "learning_rate": 1.8343259812712344e-06,
      "loss": 0.4628,
      "step": 52374
    },
    {
      "epoch": 1.6089146929622462,
      "grad_norm": 0.43979382514953613,
      "learning_rate": 1.8340470189161718e-06,
      "loss": 0.5731,
      "step": 52375
    },
    {
      "epoch": 1.6089454120971953,
      "grad_norm": 0.4564370810985565,
      "learning_rate": 1.8337680756332633e-06,
      "loss": 0.4579,
      "step": 52376
    },
    {
      "epoch": 1.6089761312321444,
      "grad_norm": 0.41545093059539795,
      "learning_rate": 1.8334891514231622e-06,
      "loss": 0.4585,
      "step": 52377
    },
    {
      "epoch": 1.6090068503670936,
      "grad_norm": 0.4841553866863251,
      "learning_rate": 1.8332102462865154e-06,
      "loss": 0.3894,
      "step": 52378
    },
    {
      "epoch": 1.6090375695020427,
      "grad_norm": 0.5542533993721008,
      "learning_rate": 1.8329313602239762e-06,
      "loss": 0.4574,
      "step": 52379
    },
    {
      "epoch": 1.609068288636992,
      "grad_norm": 0.42605194449424744,
      "learning_rate": 1.8326524932361966e-06,
      "loss": 0.5149,
      "step": 52380
    },
    {
      "epoch": 1.6090990077719411,
      "grad_norm": 0.45032843947410583,
      "learning_rate": 1.8323736453238294e-06,
      "loss": 0.4544,
      "step": 52381
    },
    {
      "epoch": 1.6091297269068903,
      "grad_norm": 0.5227700471878052,
      "learning_rate": 1.832094816487522e-06,
      "loss": 0.4142,
      "step": 52382
    },
    {
      "epoch": 1.6091604460418396,
      "grad_norm": 0.41893383860588074,
      "learning_rate": 1.831816006727929e-06,
      "loss": 0.4209,
      "step": 52383
    },
    {
      "epoch": 1.6091911651767887,
      "grad_norm": 0.43814408779144287,
      "learning_rate": 1.8315372160456969e-06,
      "loss": 0.4328,
      "step": 52384
    },
    {
      "epoch": 1.6092218843117378,
      "grad_norm": 0.53621906042099,
      "learning_rate": 1.831258444441484e-06,
      "loss": 0.4759,
      "step": 52385
    },
    {
      "epoch": 1.609252603446687,
      "grad_norm": 0.4649001359939575,
      "learning_rate": 1.830979691915935e-06,
      "loss": 0.5115,
      "step": 52386
    },
    {
      "epoch": 1.609283322581636,
      "grad_norm": 0.433979868888855,
      "learning_rate": 1.8307009584697033e-06,
      "loss": 0.5238,
      "step": 52387
    },
    {
      "epoch": 1.6093140417165852,
      "grad_norm": 0.41790077090263367,
      "learning_rate": 1.8304222441034402e-06,
      "loss": 0.4633,
      "step": 52388
    },
    {
      "epoch": 1.6093447608515343,
      "grad_norm": 0.42741185426712036,
      "learning_rate": 1.8301435488177966e-06,
      "loss": 0.5529,
      "step": 52389
    },
    {
      "epoch": 1.6093754799864834,
      "grad_norm": 0.47655022144317627,
      "learning_rate": 1.829864872613426e-06,
      "loss": 0.4629,
      "step": 52390
    },
    {
      "epoch": 1.6094061991214328,
      "grad_norm": 0.42358431220054626,
      "learning_rate": 1.8295862154909739e-06,
      "loss": 0.5195,
      "step": 52391
    },
    {
      "epoch": 1.609436918256382,
      "grad_norm": 0.44368019700050354,
      "learning_rate": 1.829307577451096e-06,
      "loss": 0.5057,
      "step": 52392
    },
    {
      "epoch": 1.609467637391331,
      "grad_norm": 0.4206230640411377,
      "learning_rate": 1.8290289584944364e-06,
      "loss": 0.4449,
      "step": 52393
    },
    {
      "epoch": 1.6094983565262804,
      "grad_norm": 0.43341052532196045,
      "learning_rate": 1.828750358621655e-06,
      "loss": 0.5153,
      "step": 52394
    },
    {
      "epoch": 1.6095290756612295,
      "grad_norm": 0.4262188673019409,
      "learning_rate": 1.828471777833396e-06,
      "loss": 0.4676,
      "step": 52395
    },
    {
      "epoch": 1.6095597947961786,
      "grad_norm": 0.4387403428554535,
      "learning_rate": 1.828193216130314e-06,
      "loss": 0.4623,
      "step": 52396
    },
    {
      "epoch": 1.6095905139311277,
      "grad_norm": 0.42692121863365173,
      "learning_rate": 1.827914673513055e-06,
      "loss": 0.4579,
      "step": 52397
    },
    {
      "epoch": 1.6096212330660769,
      "grad_norm": 0.43608707189559937,
      "learning_rate": 1.8276361499822715e-06,
      "loss": 0.4432,
      "step": 52398
    },
    {
      "epoch": 1.609651952201026,
      "grad_norm": 0.4061715602874756,
      "learning_rate": 1.8273576455386143e-06,
      "loss": 0.4685,
      "step": 52399
    },
    {
      "epoch": 1.609682671335975,
      "grad_norm": 0.45767226815223694,
      "learning_rate": 1.8270791601827377e-06,
      "loss": 0.4709,
      "step": 52400
    },
    {
      "epoch": 1.6097133904709242,
      "grad_norm": 0.45076656341552734,
      "learning_rate": 1.8268006939152848e-06,
      "loss": 0.4089,
      "step": 52401
    },
    {
      "epoch": 1.6097441096058736,
      "grad_norm": 0.4291946589946747,
      "learning_rate": 1.8265222467369104e-06,
      "loss": 0.4408,
      "step": 52402
    },
    {
      "epoch": 1.6097748287408227,
      "grad_norm": 0.4903891384601593,
      "learning_rate": 1.8262438186482645e-06,
      "loss": 0.4802,
      "step": 52403
    },
    {
      "epoch": 1.6098055478757718,
      "grad_norm": 0.4407714903354645,
      "learning_rate": 1.825965409649999e-06,
      "loss": 0.4653,
      "step": 52404
    },
    {
      "epoch": 1.6098362670107211,
      "grad_norm": 0.42551201581954956,
      "learning_rate": 1.825687019742759e-06,
      "loss": 0.411,
      "step": 52405
    },
    {
      "epoch": 1.6098669861456703,
      "grad_norm": 0.4015815556049347,
      "learning_rate": 1.8254086489271993e-06,
      "loss": 0.4281,
      "step": 52406
    },
    {
      "epoch": 1.6098977052806194,
      "grad_norm": 0.42124050855636597,
      "learning_rate": 1.8251302972039674e-06,
      "loss": 0.5326,
      "step": 52407
    },
    {
      "epoch": 1.6099284244155685,
      "grad_norm": 0.44226089119911194,
      "learning_rate": 1.824851964573715e-06,
      "loss": 0.4893,
      "step": 52408
    },
    {
      "epoch": 1.6099591435505176,
      "grad_norm": 0.41544339060783386,
      "learning_rate": 1.8245736510370948e-06,
      "loss": 0.5203,
      "step": 52409
    },
    {
      "epoch": 1.6099898626854667,
      "grad_norm": 0.4213865399360657,
      "learning_rate": 1.8242953565947507e-06,
      "loss": 0.5199,
      "step": 52410
    },
    {
      "epoch": 1.6100205818204159,
      "grad_norm": 0.43948617577552795,
      "learning_rate": 1.8240170812473356e-06,
      "loss": 0.5323,
      "step": 52411
    },
    {
      "epoch": 1.610051300955365,
      "grad_norm": 0.432994544506073,
      "learning_rate": 1.8237388249955e-06,
      "loss": 0.4689,
      "step": 52412
    },
    {
      "epoch": 1.610082020090314,
      "grad_norm": 0.4563016891479492,
      "learning_rate": 1.823460587839896e-06,
      "loss": 0.4839,
      "step": 52413
    },
    {
      "epoch": 1.6101127392252634,
      "grad_norm": 0.47563880681991577,
      "learning_rate": 1.823182369781168e-06,
      "loss": 0.4518,
      "step": 52414
    },
    {
      "epoch": 1.6101434583602126,
      "grad_norm": 0.4096719026565552,
      "learning_rate": 1.822904170819969e-06,
      "loss": 0.3934,
      "step": 52415
    },
    {
      "epoch": 1.610174177495162,
      "grad_norm": 0.49896132946014404,
      "learning_rate": 1.8226259909569477e-06,
      "loss": 0.3825,
      "step": 52416
    },
    {
      "epoch": 1.610204896630111,
      "grad_norm": 0.4581737816333771,
      "learning_rate": 1.8223478301927578e-06,
      "loss": 0.5297,
      "step": 52417
    },
    {
      "epoch": 1.6102356157650601,
      "grad_norm": 0.4244575798511505,
      "learning_rate": 1.8220696885280431e-06,
      "loss": 0.394,
      "step": 52418
    },
    {
      "epoch": 1.6102663349000093,
      "grad_norm": 0.4338129162788391,
      "learning_rate": 1.8217915659634577e-06,
      "loss": 0.4465,
      "step": 52419
    },
    {
      "epoch": 1.6102970540349584,
      "grad_norm": 0.4272182285785675,
      "learning_rate": 1.8215134624996444e-06,
      "loss": 0.5314,
      "step": 52420
    },
    {
      "epoch": 1.6103277731699075,
      "grad_norm": 0.4228293299674988,
      "learning_rate": 1.8212353781372628e-06,
      "loss": 0.5112,
      "step": 52421
    },
    {
      "epoch": 1.6103584923048566,
      "grad_norm": 0.5513662695884705,
      "learning_rate": 1.8209573128769554e-06,
      "loss": 0.4525,
      "step": 52422
    },
    {
      "epoch": 1.6103892114398057,
      "grad_norm": 0.41548189520835876,
      "learning_rate": 1.820679266719375e-06,
      "loss": 0.4368,
      "step": 52423
    },
    {
      "epoch": 1.6104199305747549,
      "grad_norm": 0.4337252974510193,
      "learning_rate": 1.820401239665167e-06,
      "loss": 0.4425,
      "step": 52424
    },
    {
      "epoch": 1.6104506497097042,
      "grad_norm": 0.4241611063480377,
      "learning_rate": 1.8201232317149808e-06,
      "loss": 0.4573,
      "step": 52425
    },
    {
      "epoch": 1.6104813688446533,
      "grad_norm": 0.4157267212867737,
      "learning_rate": 1.8198452428694725e-06,
      "loss": 0.4519,
      "step": 52426
    },
    {
      "epoch": 1.6105120879796027,
      "grad_norm": 0.45674240589141846,
      "learning_rate": 1.8195672731292857e-06,
      "loss": 0.4657,
      "step": 52427
    },
    {
      "epoch": 1.6105428071145518,
      "grad_norm": 0.4509458839893341,
      "learning_rate": 1.8192893224950725e-06,
      "loss": 0.5386,
      "step": 52428
    },
    {
      "epoch": 1.610573526249501,
      "grad_norm": 0.43088337779045105,
      "learning_rate": 1.8190113909674756e-06,
      "loss": 0.4493,
      "step": 52429
    },
    {
      "epoch": 1.61060424538445,
      "grad_norm": 0.4184100925922394,
      "learning_rate": 1.8187334785471534e-06,
      "loss": 0.4543,
      "step": 52430
    },
    {
      "epoch": 1.6106349645193991,
      "grad_norm": 0.39496785402297974,
      "learning_rate": 1.8184555852347486e-06,
      "loss": 0.4347,
      "step": 52431
    },
    {
      "epoch": 1.6106656836543483,
      "grad_norm": 0.47210419178009033,
      "learning_rate": 1.8181777110309152e-06,
      "loss": 0.4492,
      "step": 52432
    },
    {
      "epoch": 1.6106964027892974,
      "grad_norm": 0.4068353474140167,
      "learning_rate": 1.8178998559362958e-06,
      "loss": 0.4187,
      "step": 52433
    },
    {
      "epoch": 1.6107271219242465,
      "grad_norm": 0.4022116959095001,
      "learning_rate": 1.8176220199515427e-06,
      "loss": 0.4391,
      "step": 52434
    },
    {
      "epoch": 1.6107578410591956,
      "grad_norm": 0.42978933453559875,
      "learning_rate": 1.8173442030773048e-06,
      "loss": 0.4282,
      "step": 52435
    },
    {
      "epoch": 1.610788560194145,
      "grad_norm": 0.4127891957759857,
      "learning_rate": 1.817066405314234e-06,
      "loss": 0.492,
      "step": 52436
    },
    {
      "epoch": 1.610819279329094,
      "grad_norm": 0.4181230962276459,
      "learning_rate": 1.816788626662973e-06,
      "loss": 0.4122,
      "step": 52437
    },
    {
      "epoch": 1.6108499984640432,
      "grad_norm": 0.41063573956489563,
      "learning_rate": 1.8165108671241748e-06,
      "loss": 0.4929,
      "step": 52438
    },
    {
      "epoch": 1.6108807175989925,
      "grad_norm": 0.4075296223163605,
      "learning_rate": 1.8162331266984856e-06,
      "loss": 0.4261,
      "step": 52439
    },
    {
      "epoch": 1.6109114367339417,
      "grad_norm": 0.4379664361476898,
      "learning_rate": 1.8159554053865591e-06,
      "loss": 0.5165,
      "step": 52440
    },
    {
      "epoch": 1.6109421558688908,
      "grad_norm": 0.4216757118701935,
      "learning_rate": 1.8156777031890372e-06,
      "loss": 0.561,
      "step": 52441
    },
    {
      "epoch": 1.61097287500384,
      "grad_norm": 0.5211048126220703,
      "learning_rate": 1.8154000201065714e-06,
      "loss": 0.4716,
      "step": 52442
    },
    {
      "epoch": 1.611003594138789,
      "grad_norm": 0.38302817940711975,
      "learning_rate": 1.8151223561398112e-06,
      "loss": 0.4225,
      "step": 52443
    },
    {
      "epoch": 1.6110343132737381,
      "grad_norm": 0.4051375985145569,
      "learning_rate": 1.8148447112894041e-06,
      "loss": 0.5358,
      "step": 52444
    },
    {
      "epoch": 1.6110650324086873,
      "grad_norm": 0.499332994222641,
      "learning_rate": 1.8145670855560006e-06,
      "loss": 0.4678,
      "step": 52445
    },
    {
      "epoch": 1.6110957515436364,
      "grad_norm": 0.42845603823661804,
      "learning_rate": 1.8142894789402454e-06,
      "loss": 0.4868,
      "step": 52446
    },
    {
      "epoch": 1.6111264706785857,
      "grad_norm": 0.4086042046546936,
      "learning_rate": 1.8140118914427896e-06,
      "loss": 0.5648,
      "step": 52447
    },
    {
      "epoch": 1.6111571898135348,
      "grad_norm": 0.4525318443775177,
      "learning_rate": 1.81373432306428e-06,
      "loss": 0.5482,
      "step": 52448
    },
    {
      "epoch": 1.611187908948484,
      "grad_norm": 0.3708301782608032,
      "learning_rate": 1.8134567738053677e-06,
      "loss": 0.4543,
      "step": 52449
    },
    {
      "epoch": 1.6112186280834333,
      "grad_norm": 0.43362319469451904,
      "learning_rate": 1.813179243666696e-06,
      "loss": 0.4481,
      "step": 52450
    },
    {
      "epoch": 1.6112493472183824,
      "grad_norm": 0.411195307970047,
      "learning_rate": 1.8129017326489174e-06,
      "loss": 0.4859,
      "step": 52451
    },
    {
      "epoch": 1.6112800663533315,
      "grad_norm": 0.47803401947021484,
      "learning_rate": 1.8126242407526774e-06,
      "loss": 0.4513,
      "step": 52452
    },
    {
      "epoch": 1.6113107854882807,
      "grad_norm": 0.4121362566947937,
      "learning_rate": 1.8123467679786288e-06,
      "loss": 0.5061,
      "step": 52453
    },
    {
      "epoch": 1.6113415046232298,
      "grad_norm": 0.427062064409256,
      "learning_rate": 1.8120693143274126e-06,
      "loss": 0.4687,
      "step": 52454
    },
    {
      "epoch": 1.611372223758179,
      "grad_norm": 0.4352479875087738,
      "learning_rate": 1.8117918797996836e-06,
      "loss": 0.4301,
      "step": 52455
    },
    {
      "epoch": 1.611402942893128,
      "grad_norm": 0.3951463997364044,
      "learning_rate": 1.8115144643960814e-06,
      "loss": 0.4525,
      "step": 52456
    },
    {
      "epoch": 1.6114336620280771,
      "grad_norm": 0.5737931132316589,
      "learning_rate": 1.8112370681172642e-06,
      "loss": 0.516,
      "step": 52457
    },
    {
      "epoch": 1.6114643811630265,
      "grad_norm": 0.4496946632862091,
      "learning_rate": 1.8109596909638716e-06,
      "loss": 0.4947,
      "step": 52458
    },
    {
      "epoch": 1.6114951002979756,
      "grad_norm": 0.4367176592350006,
      "learning_rate": 1.8106823329365575e-06,
      "loss": 0.4437,
      "step": 52459
    },
    {
      "epoch": 1.6115258194329247,
      "grad_norm": 0.4174686074256897,
      "learning_rate": 1.8104049940359635e-06,
      "loss": 0.4728,
      "step": 52460
    },
    {
      "epoch": 1.611556538567874,
      "grad_norm": 0.4722759425640106,
      "learning_rate": 1.8101276742627393e-06,
      "loss": 0.4613,
      "step": 52461
    },
    {
      "epoch": 1.6115872577028232,
      "grad_norm": 0.45064041018486023,
      "learning_rate": 1.8098503736175377e-06,
      "loss": 0.5026,
      "step": 52462
    },
    {
      "epoch": 1.6116179768377723,
      "grad_norm": 0.4259139597415924,
      "learning_rate": 1.8095730921010013e-06,
      "loss": 0.4536,
      "step": 52463
    },
    {
      "epoch": 1.6116486959727214,
      "grad_norm": 0.3807345926761627,
      "learning_rate": 1.8092958297137809e-06,
      "loss": 0.4828,
      "step": 52464
    },
    {
      "epoch": 1.6116794151076705,
      "grad_norm": 0.5083072781562805,
      "learning_rate": 1.809018586456519e-06,
      "loss": 0.4946,
      "step": 52465
    },
    {
      "epoch": 1.6117101342426197,
      "grad_norm": 0.4094691276550293,
      "learning_rate": 1.8087413623298667e-06,
      "loss": 0.4348,
      "step": 52466
    },
    {
      "epoch": 1.6117408533775688,
      "grad_norm": 0.3823474943637848,
      "learning_rate": 1.808464157334472e-06,
      "loss": 0.4341,
      "step": 52467
    },
    {
      "epoch": 1.611771572512518,
      "grad_norm": 0.4661707282066345,
      "learning_rate": 1.808186971470982e-06,
      "loss": 0.4599,
      "step": 52468
    },
    {
      "epoch": 1.6118022916474672,
      "grad_norm": 0.4247947633266449,
      "learning_rate": 1.8079098047400424e-06,
      "loss": 0.4848,
      "step": 52469
    },
    {
      "epoch": 1.6118330107824164,
      "grad_norm": 0.4572230875492096,
      "learning_rate": 1.807632657142301e-06,
      "loss": 0.4727,
      "step": 52470
    },
    {
      "epoch": 1.6118637299173655,
      "grad_norm": 0.42353135347366333,
      "learning_rate": 1.8073555286784061e-06,
      "loss": 0.3763,
      "step": 52471
    },
    {
      "epoch": 1.6118944490523148,
      "grad_norm": 0.4357926547527313,
      "learning_rate": 1.8070784193490066e-06,
      "loss": 0.5648,
      "step": 52472
    },
    {
      "epoch": 1.611925168187264,
      "grad_norm": 0.4449542462825775,
      "learning_rate": 1.8068013291547447e-06,
      "loss": 0.3641,
      "step": 52473
    },
    {
      "epoch": 1.611955887322213,
      "grad_norm": 0.41405439376831055,
      "learning_rate": 1.8065242580962715e-06,
      "loss": 0.4666,
      "step": 52474
    },
    {
      "epoch": 1.6119866064571622,
      "grad_norm": 0.515297532081604,
      "learning_rate": 1.806247206174232e-06,
      "loss": 0.4872,
      "step": 52475
    },
    {
      "epoch": 1.6120173255921113,
      "grad_norm": 0.43392041325569153,
      "learning_rate": 1.8059701733892776e-06,
      "loss": 0.4523,
      "step": 52476
    },
    {
      "epoch": 1.6120480447270604,
      "grad_norm": 0.38481512665748596,
      "learning_rate": 1.8056931597420502e-06,
      "loss": 0.4826,
      "step": 52477
    },
    {
      "epoch": 1.6120787638620095,
      "grad_norm": 0.44194430112838745,
      "learning_rate": 1.8054161652331981e-06,
      "loss": 0.4936,
      "step": 52478
    },
    {
      "epoch": 1.6121094829969587,
      "grad_norm": 0.4373789429664612,
      "learning_rate": 1.8051391898633685e-06,
      "loss": 0.4002,
      "step": 52479
    },
    {
      "epoch": 1.612140202131908,
      "grad_norm": 0.5714016556739807,
      "learning_rate": 1.804862233633209e-06,
      "loss": 0.4535,
      "step": 52480
    },
    {
      "epoch": 1.6121709212668571,
      "grad_norm": 0.4982869327068329,
      "learning_rate": 1.8045852965433685e-06,
      "loss": 0.4433,
      "step": 52481
    },
    {
      "epoch": 1.6122016404018062,
      "grad_norm": 0.40880295634269714,
      "learning_rate": 1.8043083785944894e-06,
      "loss": 0.445,
      "step": 52482
    },
    {
      "epoch": 1.6122323595367556,
      "grad_norm": 0.4308794438838959,
      "learning_rate": 1.8040314797872195e-06,
      "loss": 0.5166,
      "step": 52483
    },
    {
      "epoch": 1.6122630786717047,
      "grad_norm": 0.5018513798713684,
      "learning_rate": 1.8037546001222072e-06,
      "loss": 0.4064,
      "step": 52484
    },
    {
      "epoch": 1.6122937978066538,
      "grad_norm": 0.5053611397743225,
      "learning_rate": 1.8034777396001002e-06,
      "loss": 0.5046,
      "step": 52485
    },
    {
      "epoch": 1.612324516941603,
      "grad_norm": 0.4869888424873352,
      "learning_rate": 1.8032008982215421e-06,
      "loss": 0.4858,
      "step": 52486
    },
    {
      "epoch": 1.612355236076552,
      "grad_norm": 0.42679113149642944,
      "learning_rate": 1.8029240759871825e-06,
      "loss": 0.5161,
      "step": 52487
    },
    {
      "epoch": 1.6123859552115012,
      "grad_norm": 0.4492270052433014,
      "learning_rate": 1.8026472728976608e-06,
      "loss": 0.4909,
      "step": 52488
    },
    {
      "epoch": 1.6124166743464503,
      "grad_norm": 0.43071237206459045,
      "learning_rate": 1.8023704889536341e-06,
      "loss": 0.4981,
      "step": 52489
    },
    {
      "epoch": 1.6124473934813994,
      "grad_norm": 0.44195011258125305,
      "learning_rate": 1.8020937241557412e-06,
      "loss": 0.4377,
      "step": 52490
    },
    {
      "epoch": 1.6124781126163488,
      "grad_norm": 0.42783984541893005,
      "learning_rate": 1.8018169785046347e-06,
      "loss": 0.4415,
      "step": 52491
    },
    {
      "epoch": 1.6125088317512979,
      "grad_norm": 0.523189902305603,
      "learning_rate": 1.8015402520009505e-06,
      "loss": 0.3803,
      "step": 52492
    },
    {
      "epoch": 1.612539550886247,
      "grad_norm": 0.46325600147247314,
      "learning_rate": 1.8012635446453475e-06,
      "loss": 0.5187,
      "step": 52493
    },
    {
      "epoch": 1.6125702700211964,
      "grad_norm": 0.3830536901950836,
      "learning_rate": 1.8009868564384636e-06,
      "loss": 0.3806,
      "step": 52494
    },
    {
      "epoch": 1.6126009891561455,
      "grad_norm": 0.39684605598449707,
      "learning_rate": 1.8007101873809497e-06,
      "loss": 0.4827,
      "step": 52495
    },
    {
      "epoch": 1.6126317082910946,
      "grad_norm": 0.4314613938331604,
      "learning_rate": 1.8004335374734471e-06,
      "loss": 0.5097,
      "step": 52496
    },
    {
      "epoch": 1.6126624274260437,
      "grad_norm": 0.4030829966068268,
      "learning_rate": 1.8001569067166025e-06,
      "loss": 0.488,
      "step": 52497
    },
    {
      "epoch": 1.6126931465609928,
      "grad_norm": 0.4581379294395447,
      "learning_rate": 1.7998802951110684e-06,
      "loss": 0.4869,
      "step": 52498
    },
    {
      "epoch": 1.612723865695942,
      "grad_norm": 0.4476437270641327,
      "learning_rate": 1.7996037026574854e-06,
      "loss": 0.4099,
      "step": 52499
    },
    {
      "epoch": 1.612754584830891,
      "grad_norm": 0.41557174921035767,
      "learning_rate": 1.7993271293565017e-06,
      "loss": 0.4394,
      "step": 52500
    },
    {
      "epoch": 1.6127853039658402,
      "grad_norm": 0.4179089665412903,
      "learning_rate": 1.7990505752087606e-06,
      "loss": 0.4519,
      "step": 52501
    },
    {
      "epoch": 1.6128160231007895,
      "grad_norm": 0.4219779372215271,
      "learning_rate": 1.7987740402149101e-06,
      "loss": 0.4685,
      "step": 52502
    },
    {
      "epoch": 1.6128467422357387,
      "grad_norm": 0.3827461898326874,
      "learning_rate": 1.7984975243755942e-06,
      "loss": 0.5089,
      "step": 52503
    },
    {
      "epoch": 1.6128774613706878,
      "grad_norm": 0.45178723335266113,
      "learning_rate": 1.7982210276914636e-06,
      "loss": 0.4133,
      "step": 52504
    },
    {
      "epoch": 1.6129081805056371,
      "grad_norm": 0.45623907446861267,
      "learning_rate": 1.7979445501631576e-06,
      "loss": 0.4177,
      "step": 52505
    },
    {
      "epoch": 1.6129388996405862,
      "grad_norm": 0.42407432198524475,
      "learning_rate": 1.7976680917913259e-06,
      "loss": 0.4778,
      "step": 52506
    },
    {
      "epoch": 1.6129696187755354,
      "grad_norm": 0.40759435296058655,
      "learning_rate": 1.7973916525766121e-06,
      "loss": 0.45,
      "step": 52507
    },
    {
      "epoch": 1.6130003379104845,
      "grad_norm": 0.44868260622024536,
      "learning_rate": 1.797115232519666e-06,
      "loss": 0.4394,
      "step": 52508
    },
    {
      "epoch": 1.6130310570454336,
      "grad_norm": 0.46163681149482727,
      "learning_rate": 1.7968388316211272e-06,
      "loss": 0.4574,
      "step": 52509
    },
    {
      "epoch": 1.6130617761803827,
      "grad_norm": 0.4208265244960785,
      "learning_rate": 1.7965624498816448e-06,
      "loss": 0.5287,
      "step": 52510
    },
    {
      "epoch": 1.6130924953153318,
      "grad_norm": 0.45693323016166687,
      "learning_rate": 1.796286087301864e-06,
      "loss": 0.495,
      "step": 52511
    },
    {
      "epoch": 1.613123214450281,
      "grad_norm": 0.45324087142944336,
      "learning_rate": 1.7960097438824308e-06,
      "loss": 0.466,
      "step": 52512
    },
    {
      "epoch": 1.6131539335852303,
      "grad_norm": 0.4326610565185547,
      "learning_rate": 1.7957334196239895e-06,
      "loss": 0.5187,
      "step": 52513
    },
    {
      "epoch": 1.6131846527201794,
      "grad_norm": 0.41642695665359497,
      "learning_rate": 1.7954571145271836e-06,
      "loss": 0.4986,
      "step": 52514
    },
    {
      "epoch": 1.6132153718551285,
      "grad_norm": 0.4082304537296295,
      "learning_rate": 1.7951808285926619e-06,
      "loss": 0.3244,
      "step": 52515
    },
    {
      "epoch": 1.6132460909900779,
      "grad_norm": 0.4252135455608368,
      "learning_rate": 1.7949045618210692e-06,
      "loss": 0.4484,
      "step": 52516
    },
    {
      "epoch": 1.613276810125027,
      "grad_norm": 0.40637508034706116,
      "learning_rate": 1.7946283142130505e-06,
      "loss": 0.4474,
      "step": 52517
    },
    {
      "epoch": 1.6133075292599761,
      "grad_norm": 0.48768526315689087,
      "learning_rate": 1.7943520857692498e-06,
      "loss": 0.5644,
      "step": 52518
    },
    {
      "epoch": 1.6133382483949252,
      "grad_norm": 0.4605660140514374,
      "learning_rate": 1.794075876490311e-06,
      "loss": 0.4414,
      "step": 52519
    },
    {
      "epoch": 1.6133689675298744,
      "grad_norm": 0.4649478495121002,
      "learning_rate": 1.7937996863768824e-06,
      "loss": 0.4771,
      "step": 52520
    },
    {
      "epoch": 1.6133996866648235,
      "grad_norm": 0.41936102509498596,
      "learning_rate": 1.7935235154296104e-06,
      "loss": 0.384,
      "step": 52521
    },
    {
      "epoch": 1.6134304057997726,
      "grad_norm": 0.41129201650619507,
      "learning_rate": 1.7932473636491343e-06,
      "loss": 0.4464,
      "step": 52522
    },
    {
      "epoch": 1.6134611249347217,
      "grad_norm": 0.39871272444725037,
      "learning_rate": 1.7929712310361047e-06,
      "loss": 0.5217,
      "step": 52523
    },
    {
      "epoch": 1.6134918440696708,
      "grad_norm": 0.41477832198143005,
      "learning_rate": 1.7926951175911589e-06,
      "loss": 0.4141,
      "step": 52524
    },
    {
      "epoch": 1.6135225632046202,
      "grad_norm": 0.641942024230957,
      "learning_rate": 1.792419023314952e-06,
      "loss": 0.3703,
      "step": 52525
    },
    {
      "epoch": 1.6135532823395693,
      "grad_norm": 0.44392895698547363,
      "learning_rate": 1.792142948208121e-06,
      "loss": 0.4299,
      "step": 52526
    },
    {
      "epoch": 1.6135840014745186,
      "grad_norm": 0.40849950909614563,
      "learning_rate": 1.7918668922713156e-06,
      "loss": 0.4862,
      "step": 52527
    },
    {
      "epoch": 1.6136147206094678,
      "grad_norm": 0.4272611141204834,
      "learning_rate": 1.7915908555051765e-06,
      "loss": 0.4535,
      "step": 52528
    },
    {
      "epoch": 1.6136454397444169,
      "grad_norm": 0.42304715514183044,
      "learning_rate": 1.7913148379103495e-06,
      "loss": 0.3998,
      "step": 52529
    },
    {
      "epoch": 1.613676158879366,
      "grad_norm": 0.5357306003570557,
      "learning_rate": 1.791038839487481e-06,
      "loss": 0.4089,
      "step": 52530
    },
    {
      "epoch": 1.6137068780143151,
      "grad_norm": 0.5354893803596497,
      "learning_rate": 1.7907628602372163e-06,
      "loss": 0.4161,
      "step": 52531
    },
    {
      "epoch": 1.6137375971492642,
      "grad_norm": 0.3674086034297943,
      "learning_rate": 1.7904869001601955e-06,
      "loss": 0.4285,
      "step": 52532
    },
    {
      "epoch": 1.6137683162842134,
      "grad_norm": 0.420637309551239,
      "learning_rate": 1.7902109592570638e-06,
      "loss": 0.4303,
      "step": 52533
    },
    {
      "epoch": 1.6137990354191625,
      "grad_norm": 0.4571963846683502,
      "learning_rate": 1.789935037528473e-06,
      "loss": 0.457,
      "step": 52534
    },
    {
      "epoch": 1.6138297545541116,
      "grad_norm": 0.3952316343784332,
      "learning_rate": 1.7896591349750603e-06,
      "loss": 0.448,
      "step": 52535
    },
    {
      "epoch": 1.613860473689061,
      "grad_norm": 0.42084410786628723,
      "learning_rate": 1.789383251597473e-06,
      "loss": 0.4621,
      "step": 52536
    },
    {
      "epoch": 1.61389119282401,
      "grad_norm": 0.4212040901184082,
      "learning_rate": 1.7891073873963538e-06,
      "loss": 0.4649,
      "step": 52537
    },
    {
      "epoch": 1.6139219119589594,
      "grad_norm": 0.4072727859020233,
      "learning_rate": 1.7888315423723468e-06,
      "loss": 0.3975,
      "step": 52538
    },
    {
      "epoch": 1.6139526310939085,
      "grad_norm": 0.4115821123123169,
      "learning_rate": 1.788555716526097e-06,
      "loss": 0.4088,
      "step": 52539
    },
    {
      "epoch": 1.6139833502288576,
      "grad_norm": 0.47973281145095825,
      "learning_rate": 1.7882799098582514e-06,
      "loss": 0.4459,
      "step": 52540
    },
    {
      "epoch": 1.6140140693638068,
      "grad_norm": 0.4168490469455719,
      "learning_rate": 1.7880041223694489e-06,
      "loss": 0.4322,
      "step": 52541
    },
    {
      "epoch": 1.6140447884987559,
      "grad_norm": 0.4075968563556671,
      "learning_rate": 1.7877283540603373e-06,
      "loss": 0.4907,
      "step": 52542
    },
    {
      "epoch": 1.614075507633705,
      "grad_norm": 0.4679049551486969,
      "learning_rate": 1.7874526049315588e-06,
      "loss": 0.4028,
      "step": 52543
    },
    {
      "epoch": 1.6141062267686541,
      "grad_norm": 0.4744686484336853,
      "learning_rate": 1.7871768749837614e-06,
      "loss": 0.4456,
      "step": 52544
    },
    {
      "epoch": 1.6141369459036032,
      "grad_norm": 0.4308145046234131,
      "learning_rate": 1.7869011642175826e-06,
      "loss": 0.4397,
      "step": 52545
    },
    {
      "epoch": 1.6141676650385524,
      "grad_norm": 0.41963884234428406,
      "learning_rate": 1.7866254726336707e-06,
      "loss": 0.4378,
      "step": 52546
    },
    {
      "epoch": 1.6141983841735017,
      "grad_norm": 0.5792568325996399,
      "learning_rate": 1.7863498002326674e-06,
      "loss": 0.4956,
      "step": 52547
    },
    {
      "epoch": 1.6142291033084508,
      "grad_norm": 0.404737651348114,
      "learning_rate": 1.786074147015221e-06,
      "loss": 0.475,
      "step": 52548
    },
    {
      "epoch": 1.6142598224434,
      "grad_norm": 0.4166440963745117,
      "learning_rate": 1.78579851298197e-06,
      "loss": 0.4709,
      "step": 52549
    },
    {
      "epoch": 1.6142905415783493,
      "grad_norm": 0.5032448768615723,
      "learning_rate": 1.7855228981335626e-06,
      "loss": 0.4633,
      "step": 52550
    },
    {
      "epoch": 1.6143212607132984,
      "grad_norm": 0.4939611554145813,
      "learning_rate": 1.7852473024706352e-06,
      "loss": 0.3918,
      "step": 52551
    },
    {
      "epoch": 1.6143519798482475,
      "grad_norm": 0.5042920708656311,
      "learning_rate": 1.7849717259938382e-06,
      "loss": 0.4599,
      "step": 52552
    },
    {
      "epoch": 1.6143826989831966,
      "grad_norm": 0.42331528663635254,
      "learning_rate": 1.7846961687038167e-06,
      "loss": 0.4075,
      "step": 52553
    },
    {
      "epoch": 1.6144134181181458,
      "grad_norm": 0.4006447196006775,
      "learning_rate": 1.784420630601208e-06,
      "loss": 0.4659,
      "step": 52554
    },
    {
      "epoch": 1.6144441372530949,
      "grad_norm": 0.43350139260292053,
      "learning_rate": 1.7841451116866592e-06,
      "loss": 0.4635,
      "step": 52555
    },
    {
      "epoch": 1.614474856388044,
      "grad_norm": 0.4204939901828766,
      "learning_rate": 1.7838696119608123e-06,
      "loss": 0.4776,
      "step": 52556
    },
    {
      "epoch": 1.6145055755229931,
      "grad_norm": 0.40473973751068115,
      "learning_rate": 1.7835941314243154e-06,
      "loss": 0.5091,
      "step": 52557
    },
    {
      "epoch": 1.6145362946579425,
      "grad_norm": 0.455949991941452,
      "learning_rate": 1.783318670077805e-06,
      "loss": 0.4485,
      "step": 52558
    },
    {
      "epoch": 1.6145670137928916,
      "grad_norm": 0.3953450620174408,
      "learning_rate": 1.7830432279219311e-06,
      "loss": 0.462,
      "step": 52559
    },
    {
      "epoch": 1.6145977329278407,
      "grad_norm": 0.4630110263824463,
      "learning_rate": 1.7827678049573283e-06,
      "loss": 0.4376,
      "step": 52560
    },
    {
      "epoch": 1.61462845206279,
      "grad_norm": 0.5469942092895508,
      "learning_rate": 1.7824924011846489e-06,
      "loss": 0.4105,
      "step": 52561
    },
    {
      "epoch": 1.6146591711977392,
      "grad_norm": 0.5645701885223389,
      "learning_rate": 1.7822170166045316e-06,
      "loss": 0.4409,
      "step": 52562
    },
    {
      "epoch": 1.6146898903326883,
      "grad_norm": 0.43904855847358704,
      "learning_rate": 1.7819416512176225e-06,
      "loss": 0.5176,
      "step": 52563
    },
    {
      "epoch": 1.6147206094676374,
      "grad_norm": 0.4419916570186615,
      "learning_rate": 1.7816663050245598e-06,
      "loss": 0.4635,
      "step": 52564
    },
    {
      "epoch": 1.6147513286025865,
      "grad_norm": 0.44817134737968445,
      "learning_rate": 1.7813909780259886e-06,
      "loss": 0.4624,
      "step": 52565
    },
    {
      "epoch": 1.6147820477375356,
      "grad_norm": 0.4110254943370819,
      "learning_rate": 1.781115670222554e-06,
      "loss": 0.4481,
      "step": 52566
    },
    {
      "epoch": 1.6148127668724848,
      "grad_norm": 0.4038783609867096,
      "learning_rate": 1.7808403816149e-06,
      "loss": 0.4953,
      "step": 52567
    },
    {
      "epoch": 1.6148434860074339,
      "grad_norm": 0.3934672176837921,
      "learning_rate": 1.7805651122036638e-06,
      "loss": 0.4921,
      "step": 52568
    },
    {
      "epoch": 1.6148742051423832,
      "grad_norm": 0.4494534730911255,
      "learning_rate": 1.7802898619894925e-06,
      "loss": 0.4978,
      "step": 52569
    },
    {
      "epoch": 1.6149049242773323,
      "grad_norm": 0.41798242926597595,
      "learning_rate": 1.7800146309730293e-06,
      "loss": 0.5002,
      "step": 52570
    },
    {
      "epoch": 1.6149356434122815,
      "grad_norm": 0.4425964653491974,
      "learning_rate": 1.7797394191549145e-06,
      "loss": 0.4341,
      "step": 52571
    },
    {
      "epoch": 1.6149663625472308,
      "grad_norm": 0.4323301613330841,
      "learning_rate": 1.7794642265357952e-06,
      "loss": 0.4558,
      "step": 52572
    },
    {
      "epoch": 1.61499708168218,
      "grad_norm": 0.4130842089653015,
      "learning_rate": 1.779189053116309e-06,
      "loss": 0.4479,
      "step": 52573
    },
    {
      "epoch": 1.615027800817129,
      "grad_norm": 0.40285247564315796,
      "learning_rate": 1.7789138988971011e-06,
      "loss": 0.5046,
      "step": 52574
    },
    {
      "epoch": 1.6150585199520782,
      "grad_norm": 0.392020046710968,
      "learning_rate": 1.778638763878814e-06,
      "loss": 0.4073,
      "step": 52575
    },
    {
      "epoch": 1.6150892390870273,
      "grad_norm": 0.4134109914302826,
      "learning_rate": 1.7783636480620924e-06,
      "loss": 0.4205,
      "step": 52576
    },
    {
      "epoch": 1.6151199582219764,
      "grad_norm": 0.42144206166267395,
      "learning_rate": 1.7780885514475754e-06,
      "loss": 0.4456,
      "step": 52577
    },
    {
      "epoch": 1.6151506773569255,
      "grad_norm": 0.4126850366592407,
      "learning_rate": 1.7778134740359054e-06,
      "loss": 0.4201,
      "step": 52578
    },
    {
      "epoch": 1.6151813964918746,
      "grad_norm": 0.4517378807067871,
      "learning_rate": 1.7775384158277264e-06,
      "loss": 0.43,
      "step": 52579
    },
    {
      "epoch": 1.615212115626824,
      "grad_norm": 0.44253942370414734,
      "learning_rate": 1.7772633768236835e-06,
      "loss": 0.4923,
      "step": 52580
    },
    {
      "epoch": 1.615242834761773,
      "grad_norm": 0.4269948899745941,
      "learning_rate": 1.776988357024414e-06,
      "loss": 0.4311,
      "step": 52581
    },
    {
      "epoch": 1.6152735538967222,
      "grad_norm": 0.5247031450271606,
      "learning_rate": 1.7767133564305617e-06,
      "loss": 0.4103,
      "step": 52582
    },
    {
      "epoch": 1.6153042730316716,
      "grad_norm": 0.42929553985595703,
      "learning_rate": 1.7764383750427705e-06,
      "loss": 0.4644,
      "step": 52583
    },
    {
      "epoch": 1.6153349921666207,
      "grad_norm": 0.4646165668964386,
      "learning_rate": 1.7761634128616833e-06,
      "loss": 0.4581,
      "step": 52584
    },
    {
      "epoch": 1.6153657113015698,
      "grad_norm": 0.4358963668346405,
      "learning_rate": 1.7758884698879398e-06,
      "loss": 0.3549,
      "step": 52585
    },
    {
      "epoch": 1.615396430436519,
      "grad_norm": 0.4274948835372925,
      "learning_rate": 1.7756135461221847e-06,
      "loss": 0.4598,
      "step": 52586
    },
    {
      "epoch": 1.615427149571468,
      "grad_norm": 0.4321189522743225,
      "learning_rate": 1.775338641565053e-06,
      "loss": 0.4323,
      "step": 52587
    },
    {
      "epoch": 1.6154578687064172,
      "grad_norm": 0.44723090529441833,
      "learning_rate": 1.7750637562171957e-06,
      "loss": 0.4904,
      "step": 52588
    },
    {
      "epoch": 1.6154885878413663,
      "grad_norm": 0.43189430236816406,
      "learning_rate": 1.7747888900792531e-06,
      "loss": 0.5112,
      "step": 52589
    },
    {
      "epoch": 1.6155193069763154,
      "grad_norm": 0.441741019487381,
      "learning_rate": 1.7745140431518636e-06,
      "loss": 0.4145,
      "step": 52590
    },
    {
      "epoch": 1.6155500261112647,
      "grad_norm": 0.4285796582698822,
      "learning_rate": 1.7742392154356713e-06,
      "loss": 0.5247,
      "step": 52591
    },
    {
      "epoch": 1.6155807452462139,
      "grad_norm": 0.4056667387485504,
      "learning_rate": 1.7739644069313177e-06,
      "loss": 0.4989,
      "step": 52592
    },
    {
      "epoch": 1.615611464381163,
      "grad_norm": 0.40287309885025024,
      "learning_rate": 1.773689617639447e-06,
      "loss": 0.3938,
      "step": 52593
    },
    {
      "epoch": 1.6156421835161123,
      "grad_norm": 0.42122578620910645,
      "learning_rate": 1.773414847560696e-06,
      "loss": 0.4484,
      "step": 52594
    },
    {
      "epoch": 1.6156729026510614,
      "grad_norm": 0.4498330354690552,
      "learning_rate": 1.7731400966957124e-06,
      "loss": 0.4935,
      "step": 52595
    },
    {
      "epoch": 1.6157036217860106,
      "grad_norm": 0.4153263568878174,
      "learning_rate": 1.772865365045129e-06,
      "loss": 0.5649,
      "step": 52596
    },
    {
      "epoch": 1.6157343409209597,
      "grad_norm": 0.45241397619247437,
      "learning_rate": 1.7725906526095981e-06,
      "loss": 0.5519,
      "step": 52597
    },
    {
      "epoch": 1.6157650600559088,
      "grad_norm": 0.5037919878959656,
      "learning_rate": 1.7723159593897532e-06,
      "loss": 0.4602,
      "step": 52598
    },
    {
      "epoch": 1.615795779190858,
      "grad_norm": 0.5668643116950989,
      "learning_rate": 1.7720412853862422e-06,
      "loss": 0.4333,
      "step": 52599
    },
    {
      "epoch": 1.615826498325807,
      "grad_norm": 0.42513713240623474,
      "learning_rate": 1.7717666305997016e-06,
      "loss": 0.4374,
      "step": 52600
    },
    {
      "epoch": 1.6158572174607562,
      "grad_norm": 0.40741828083992004,
      "learning_rate": 1.7714919950307742e-06,
      "loss": 0.4529,
      "step": 52601
    },
    {
      "epoch": 1.6158879365957055,
      "grad_norm": 0.4307897686958313,
      "learning_rate": 1.7712173786801012e-06,
      "loss": 0.4092,
      "step": 52602
    },
    {
      "epoch": 1.6159186557306546,
      "grad_norm": 0.42155230045318604,
      "learning_rate": 1.7709427815483282e-06,
      "loss": 0.5043,
      "step": 52603
    },
    {
      "epoch": 1.6159493748656037,
      "grad_norm": 0.43546685576438904,
      "learning_rate": 1.77066820363609e-06,
      "loss": 0.3914,
      "step": 52604
    },
    {
      "epoch": 1.615980094000553,
      "grad_norm": 0.44657567143440247,
      "learning_rate": 1.7703936449440306e-06,
      "loss": 0.4383,
      "step": 52605
    },
    {
      "epoch": 1.6160108131355022,
      "grad_norm": 0.447334349155426,
      "learning_rate": 1.7701191054727928e-06,
      "loss": 0.437,
      "step": 52606
    },
    {
      "epoch": 1.6160415322704513,
      "grad_norm": 0.4536210596561432,
      "learning_rate": 1.7698445852230151e-06,
      "loss": 0.4406,
      "step": 52607
    },
    {
      "epoch": 1.6160722514054005,
      "grad_norm": 0.43896806240081787,
      "learning_rate": 1.7695700841953434e-06,
      "loss": 0.4304,
      "step": 52608
    },
    {
      "epoch": 1.6161029705403496,
      "grad_norm": 0.5652998685836792,
      "learning_rate": 1.7692956023904128e-06,
      "loss": 0.4055,
      "step": 52609
    },
    {
      "epoch": 1.6161336896752987,
      "grad_norm": 0.45462292432785034,
      "learning_rate": 1.7690211398088674e-06,
      "loss": 0.5079,
      "step": 52610
    },
    {
      "epoch": 1.6161644088102478,
      "grad_norm": 0.4399851858615875,
      "learning_rate": 1.7687466964513488e-06,
      "loss": 0.4915,
      "step": 52611
    },
    {
      "epoch": 1.616195127945197,
      "grad_norm": 0.47258058190345764,
      "learning_rate": 1.7684722723184989e-06,
      "loss": 0.477,
      "step": 52612
    },
    {
      "epoch": 1.6162258470801463,
      "grad_norm": 0.5219093561172485,
      "learning_rate": 1.7681978674109546e-06,
      "loss": 0.514,
      "step": 52613
    },
    {
      "epoch": 1.6162565662150954,
      "grad_norm": 0.47444069385528564,
      "learning_rate": 1.7679234817293578e-06,
      "loss": 0.4793,
      "step": 52614
    },
    {
      "epoch": 1.6162872853500445,
      "grad_norm": 0.43206366896629333,
      "learning_rate": 1.7676491152743525e-06,
      "loss": 0.3908,
      "step": 52615
    },
    {
      "epoch": 1.6163180044849939,
      "grad_norm": 0.4469148814678192,
      "learning_rate": 1.7673747680465791e-06,
      "loss": 0.5389,
      "step": 52616
    },
    {
      "epoch": 1.616348723619943,
      "grad_norm": 0.4805748760700226,
      "learning_rate": 1.767100440046674e-06,
      "loss": 0.3843,
      "step": 52617
    },
    {
      "epoch": 1.616379442754892,
      "grad_norm": 0.4399206042289734,
      "learning_rate": 1.766826131275282e-06,
      "loss": 0.4053,
      "step": 52618
    },
    {
      "epoch": 1.6164101618898412,
      "grad_norm": 0.43204790353775024,
      "learning_rate": 1.7665518417330419e-06,
      "loss": 0.4588,
      "step": 52619
    },
    {
      "epoch": 1.6164408810247903,
      "grad_norm": 0.4785057604312897,
      "learning_rate": 1.7662775714205972e-06,
      "loss": 0.4727,
      "step": 52620
    },
    {
      "epoch": 1.6164716001597395,
      "grad_norm": 0.4040675461292267,
      "learning_rate": 1.766003320338584e-06,
      "loss": 0.5388,
      "step": 52621
    },
    {
      "epoch": 1.6165023192946886,
      "grad_norm": 0.4055030345916748,
      "learning_rate": 1.7657290884876476e-06,
      "loss": 0.4325,
      "step": 52622
    },
    {
      "epoch": 1.6165330384296377,
      "grad_norm": 0.3954343795776367,
      "learning_rate": 1.765454875868421e-06,
      "loss": 0.4407,
      "step": 52623
    },
    {
      "epoch": 1.616563757564587,
      "grad_norm": 0.4084990620613098,
      "learning_rate": 1.7651806824815555e-06,
      "loss": 0.5092,
      "step": 52624
    },
    {
      "epoch": 1.6165944766995362,
      "grad_norm": 0.41468346118927,
      "learning_rate": 1.7649065083276818e-06,
      "loss": 0.4697,
      "step": 52625
    },
    {
      "epoch": 1.6166251958344853,
      "grad_norm": 0.5224657654762268,
      "learning_rate": 1.764632353407445e-06,
      "loss": 0.4691,
      "step": 52626
    },
    {
      "epoch": 1.6166559149694346,
      "grad_norm": 0.5127270221710205,
      "learning_rate": 1.764358217721487e-06,
      "loss": 0.3838,
      "step": 52627
    },
    {
      "epoch": 1.6166866341043837,
      "grad_norm": 0.4064590334892273,
      "learning_rate": 1.764084101270439e-06,
      "loss": 0.3605,
      "step": 52628
    },
    {
      "epoch": 1.6167173532393329,
      "grad_norm": 0.49175745248794556,
      "learning_rate": 1.7638100040549545e-06,
      "loss": 0.4545,
      "step": 52629
    },
    {
      "epoch": 1.616748072374282,
      "grad_norm": 0.41033241152763367,
      "learning_rate": 1.7635359260756636e-06,
      "loss": 0.4689,
      "step": 52630
    },
    {
      "epoch": 1.616778791509231,
      "grad_norm": 0.4509381949901581,
      "learning_rate": 1.7632618673332126e-06,
      "loss": 0.488,
      "step": 52631
    },
    {
      "epoch": 1.6168095106441802,
      "grad_norm": 0.40293818712234497,
      "learning_rate": 1.7629878278282342e-06,
      "loss": 0.4844,
      "step": 52632
    },
    {
      "epoch": 1.6168402297791293,
      "grad_norm": 0.4089079201221466,
      "learning_rate": 1.762713807561377e-06,
      "loss": 0.4857,
      "step": 52633
    },
    {
      "epoch": 1.6168709489140785,
      "grad_norm": 0.43005630373954773,
      "learning_rate": 1.7624398065332748e-06,
      "loss": 0.4156,
      "step": 52634
    },
    {
      "epoch": 1.6169016680490276,
      "grad_norm": 0.45182400941848755,
      "learning_rate": 1.7621658247445728e-06,
      "loss": 0.4692,
      "step": 52635
    },
    {
      "epoch": 1.616932387183977,
      "grad_norm": 0.4428912401199341,
      "learning_rate": 1.7618918621959047e-06,
      "loss": 0.4778,
      "step": 52636
    },
    {
      "epoch": 1.616963106318926,
      "grad_norm": 0.43979185819625854,
      "learning_rate": 1.7616179188879146e-06,
      "loss": 0.4305,
      "step": 52637
    },
    {
      "epoch": 1.6169938254538754,
      "grad_norm": 0.4789225459098816,
      "learning_rate": 1.7613439948212396e-06,
      "loss": 0.4234,
      "step": 52638
    },
    {
      "epoch": 1.6170245445888245,
      "grad_norm": 0.4318101704120636,
      "learning_rate": 1.761070089996525e-06,
      "loss": 0.4228,
      "step": 52639
    },
    {
      "epoch": 1.6170552637237736,
      "grad_norm": 0.4339956045150757,
      "learning_rate": 1.7607962044144034e-06,
      "loss": 0.471,
      "step": 52640
    },
    {
      "epoch": 1.6170859828587227,
      "grad_norm": 0.43060338497161865,
      "learning_rate": 1.7605223380755177e-06,
      "loss": 0.4667,
      "step": 52641
    },
    {
      "epoch": 1.6171167019936719,
      "grad_norm": 0.4321308135986328,
      "learning_rate": 1.7602484909805074e-06,
      "loss": 0.4496,
      "step": 52642
    },
    {
      "epoch": 1.617147421128621,
      "grad_norm": 0.43043825030326843,
      "learning_rate": 1.759974663130012e-06,
      "loss": 0.3779,
      "step": 52643
    },
    {
      "epoch": 1.61717814026357,
      "grad_norm": 0.4673581123352051,
      "learning_rate": 1.759700854524674e-06,
      "loss": 0.4877,
      "step": 52644
    },
    {
      "epoch": 1.6172088593985192,
      "grad_norm": 0.4221765398979187,
      "learning_rate": 1.7594270651651279e-06,
      "loss": 0.4358,
      "step": 52645
    },
    {
      "epoch": 1.6172395785334683,
      "grad_norm": 0.45164647698402405,
      "learning_rate": 1.7591532950520151e-06,
      "loss": 0.4755,
      "step": 52646
    },
    {
      "epoch": 1.6172702976684177,
      "grad_norm": 0.49408623576164246,
      "learning_rate": 1.7588795441859764e-06,
      "loss": 0.5007,
      "step": 52647
    },
    {
      "epoch": 1.6173010168033668,
      "grad_norm": 0.3886790871620178,
      "learning_rate": 1.7586058125676509e-06,
      "loss": 0.5036,
      "step": 52648
    },
    {
      "epoch": 1.6173317359383161,
      "grad_norm": 0.4238531291484833,
      "learning_rate": 1.758332100197676e-06,
      "loss": 0.4685,
      "step": 52649
    },
    {
      "epoch": 1.6173624550732653,
      "grad_norm": 0.47321709990501404,
      "learning_rate": 1.7580584070766916e-06,
      "loss": 0.5312,
      "step": 52650
    },
    {
      "epoch": 1.6173931742082144,
      "grad_norm": 0.4378150999546051,
      "learning_rate": 1.7577847332053366e-06,
      "loss": 0.4554,
      "step": 52651
    },
    {
      "epoch": 1.6174238933431635,
      "grad_norm": 0.44727566838264465,
      "learning_rate": 1.7575110785842542e-06,
      "loss": 0.527,
      "step": 52652
    },
    {
      "epoch": 1.6174546124781126,
      "grad_norm": 0.4006430506706238,
      "learning_rate": 1.7572374432140781e-06,
      "loss": 0.4358,
      "step": 52653
    },
    {
      "epoch": 1.6174853316130617,
      "grad_norm": 0.4844735860824585,
      "learning_rate": 1.7569638270954492e-06,
      "loss": 0.4625,
      "step": 52654
    },
    {
      "epoch": 1.6175160507480109,
      "grad_norm": 0.46077948808670044,
      "learning_rate": 1.7566902302290068e-06,
      "loss": 0.5062,
      "step": 52655
    },
    {
      "epoch": 1.61754676988296,
      "grad_norm": 0.4518393576145172,
      "learning_rate": 1.7564166526153926e-06,
      "loss": 0.4433,
      "step": 52656
    },
    {
      "epoch": 1.617577489017909,
      "grad_norm": 0.42968592047691345,
      "learning_rate": 1.7561430942552416e-06,
      "loss": 0.4625,
      "step": 52657
    },
    {
      "epoch": 1.6176082081528584,
      "grad_norm": 0.4236932396888733,
      "learning_rate": 1.7558695551491955e-06,
      "loss": 0.3936,
      "step": 52658
    },
    {
      "epoch": 1.6176389272878076,
      "grad_norm": 0.4292054772377014,
      "learning_rate": 1.7555960352978874e-06,
      "loss": 0.5581,
      "step": 52659
    },
    {
      "epoch": 1.617669646422757,
      "grad_norm": 0.41195058822631836,
      "learning_rate": 1.7553225347019654e-06,
      "loss": 0.3739,
      "step": 52660
    },
    {
      "epoch": 1.617700365557706,
      "grad_norm": 0.4606758952140808,
      "learning_rate": 1.75504905336206e-06,
      "loss": 0.4791,
      "step": 52661
    },
    {
      "epoch": 1.6177310846926551,
      "grad_norm": 0.46429458260536194,
      "learning_rate": 1.7547755912788144e-06,
      "loss": 0.4858,
      "step": 52662
    },
    {
      "epoch": 1.6177618038276043,
      "grad_norm": 0.4283050000667572,
      "learning_rate": 1.754502148452868e-06,
      "loss": 0.4115,
      "step": 52663
    },
    {
      "epoch": 1.6177925229625534,
      "grad_norm": 0.41869089007377625,
      "learning_rate": 1.7542287248848533e-06,
      "loss": 0.431,
      "step": 52664
    },
    {
      "epoch": 1.6178232420975025,
      "grad_norm": 0.4569046199321747,
      "learning_rate": 1.753955320575419e-06,
      "loss": 0.4765,
      "step": 52665
    },
    {
      "epoch": 1.6178539612324516,
      "grad_norm": 0.590097963809967,
      "learning_rate": 1.7536819355251944e-06,
      "loss": 0.4851,
      "step": 52666
    },
    {
      "epoch": 1.6178846803674007,
      "grad_norm": 0.4224086403846741,
      "learning_rate": 1.7534085697348236e-06,
      "loss": 0.3791,
      "step": 52667
    },
    {
      "epoch": 1.6179153995023499,
      "grad_norm": 0.4291795790195465,
      "learning_rate": 1.7531352232049415e-06,
      "loss": 0.5148,
      "step": 52668
    },
    {
      "epoch": 1.6179461186372992,
      "grad_norm": 0.4435614049434662,
      "learning_rate": 1.7528618959361875e-06,
      "loss": 0.4724,
      "step": 52669
    },
    {
      "epoch": 1.6179768377722483,
      "grad_norm": 0.45828595757484436,
      "learning_rate": 1.7525885879292015e-06,
      "loss": 0.4576,
      "step": 52670
    },
    {
      "epoch": 1.6180075569071974,
      "grad_norm": 0.4785618185997009,
      "learning_rate": 1.7523152991846225e-06,
      "loss": 0.5769,
      "step": 52671
    },
    {
      "epoch": 1.6180382760421468,
      "grad_norm": 0.44629988074302673,
      "learning_rate": 1.752042029703085e-06,
      "loss": 0.4717,
      "step": 52672
    },
    {
      "epoch": 1.618068995177096,
      "grad_norm": 0.4505048394203186,
      "learning_rate": 1.751768779485229e-06,
      "loss": 0.5003,
      "step": 52673
    },
    {
      "epoch": 1.618099714312045,
      "grad_norm": 0.5530110001564026,
      "learning_rate": 1.7514955485316932e-06,
      "loss": 0.4473,
      "step": 52674
    },
    {
      "epoch": 1.6181304334469941,
      "grad_norm": 0.43430718779563904,
      "learning_rate": 1.751222336843118e-06,
      "loss": 0.5017,
      "step": 52675
    },
    {
      "epoch": 1.6181611525819433,
      "grad_norm": 0.39711132645606995,
      "learning_rate": 1.7509491444201366e-06,
      "loss": 0.4644,
      "step": 52676
    },
    {
      "epoch": 1.6181918717168924,
      "grad_norm": 0.5626780986785889,
      "learning_rate": 1.7506759712633891e-06,
      "loss": 0.5381,
      "step": 52677
    },
    {
      "epoch": 1.6182225908518415,
      "grad_norm": 0.4075664281845093,
      "learning_rate": 1.7504028173735144e-06,
      "loss": 0.4618,
      "step": 52678
    },
    {
      "epoch": 1.6182533099867906,
      "grad_norm": 0.42241591215133667,
      "learning_rate": 1.7501296827511504e-06,
      "loss": 0.4736,
      "step": 52679
    },
    {
      "epoch": 1.61828402912174,
      "grad_norm": 0.4535680413246155,
      "learning_rate": 1.749856567396937e-06,
      "loss": 0.5369,
      "step": 52680
    },
    {
      "epoch": 1.618314748256689,
      "grad_norm": 0.46851733326911926,
      "learning_rate": 1.7495834713115078e-06,
      "loss": 0.4881,
      "step": 52681
    },
    {
      "epoch": 1.6183454673916382,
      "grad_norm": 0.46815040707588196,
      "learning_rate": 1.7493103944955015e-06,
      "loss": 0.4426,
      "step": 52682
    },
    {
      "epoch": 1.6183761865265875,
      "grad_norm": 0.4710880219936371,
      "learning_rate": 1.7490373369495583e-06,
      "loss": 0.4671,
      "step": 52683
    },
    {
      "epoch": 1.6184069056615367,
      "grad_norm": 0.4271968901157379,
      "learning_rate": 1.748764298674316e-06,
      "loss": 0.4773,
      "step": 52684
    },
    {
      "epoch": 1.6184376247964858,
      "grad_norm": 0.43691688776016235,
      "learning_rate": 1.748491279670409e-06,
      "loss": 0.4577,
      "step": 52685
    },
    {
      "epoch": 1.618468343931435,
      "grad_norm": 0.43633678555488586,
      "learning_rate": 1.748218279938476e-06,
      "loss": 0.4577,
      "step": 52686
    },
    {
      "epoch": 1.618499063066384,
      "grad_norm": 0.39956703782081604,
      "learning_rate": 1.7479452994791567e-06,
      "loss": 0.4783,
      "step": 52687
    },
    {
      "epoch": 1.6185297822013331,
      "grad_norm": 0.4162481725215912,
      "learning_rate": 1.7476723382930893e-06,
      "loss": 0.4647,
      "step": 52688
    },
    {
      "epoch": 1.6185605013362823,
      "grad_norm": 0.42513754963874817,
      "learning_rate": 1.7473993963809077e-06,
      "loss": 0.5054,
      "step": 52689
    },
    {
      "epoch": 1.6185912204712314,
      "grad_norm": 0.42533355951309204,
      "learning_rate": 1.7471264737432536e-06,
      "loss": 0.4833,
      "step": 52690
    },
    {
      "epoch": 1.6186219396061807,
      "grad_norm": 0.5003048777580261,
      "learning_rate": 1.7468535703807564e-06,
      "loss": 0.4988,
      "step": 52691
    },
    {
      "epoch": 1.6186526587411298,
      "grad_norm": 0.417193740606308,
      "learning_rate": 1.7465806862940638e-06,
      "loss": 0.4888,
      "step": 52692
    },
    {
      "epoch": 1.618683377876079,
      "grad_norm": 0.41349390149116516,
      "learning_rate": 1.746307821483807e-06,
      "loss": 0.4216,
      "step": 52693
    },
    {
      "epoch": 1.6187140970110283,
      "grad_norm": 0.45102593302726746,
      "learning_rate": 1.7460349759506268e-06,
      "loss": 0.4997,
      "step": 52694
    },
    {
      "epoch": 1.6187448161459774,
      "grad_norm": 0.43652069568634033,
      "learning_rate": 1.7457621496951526e-06,
      "loss": 0.4919,
      "step": 52695
    },
    {
      "epoch": 1.6187755352809265,
      "grad_norm": 0.5074685215950012,
      "learning_rate": 1.7454893427180332e-06,
      "loss": 0.4669,
      "step": 52696
    },
    {
      "epoch": 1.6188062544158757,
      "grad_norm": 0.58690345287323,
      "learning_rate": 1.7452165550198975e-06,
      "loss": 0.5082,
      "step": 52697
    },
    {
      "epoch": 1.6188369735508248,
      "grad_norm": 0.5322421789169312,
      "learning_rate": 1.744943786601384e-06,
      "loss": 0.4262,
      "step": 52698
    },
    {
      "epoch": 1.618867692685774,
      "grad_norm": 0.4460495710372925,
      "learning_rate": 1.7446710374631338e-06,
      "loss": 0.4704,
      "step": 52699
    },
    {
      "epoch": 1.618898411820723,
      "grad_norm": 0.4423004984855652,
      "learning_rate": 1.7443983076057769e-06,
      "loss": 0.4546,
      "step": 52700
    },
    {
      "epoch": 1.6189291309556721,
      "grad_norm": 0.4466356337070465,
      "learning_rate": 1.7441255970299587e-06,
      "loss": 0.477,
      "step": 52701
    },
    {
      "epoch": 1.6189598500906215,
      "grad_norm": 0.46988433599472046,
      "learning_rate": 1.7438529057363085e-06,
      "loss": 0.4827,
      "step": 52702
    },
    {
      "epoch": 1.6189905692255706,
      "grad_norm": 0.4243105351924896,
      "learning_rate": 1.7435802337254692e-06,
      "loss": 0.4444,
      "step": 52703
    },
    {
      "epoch": 1.6190212883605197,
      "grad_norm": 0.4623260498046875,
      "learning_rate": 1.7433075809980738e-06,
      "loss": 0.4647,
      "step": 52704
    },
    {
      "epoch": 1.619052007495469,
      "grad_norm": 0.44274112582206726,
      "learning_rate": 1.7430349475547582e-06,
      "loss": 0.4413,
      "step": 52705
    },
    {
      "epoch": 1.6190827266304182,
      "grad_norm": 0.41580915451049805,
      "learning_rate": 1.742762333396163e-06,
      "loss": 0.4465,
      "step": 52706
    },
    {
      "epoch": 1.6191134457653673,
      "grad_norm": 0.4008429944515228,
      "learning_rate": 1.7424897385229246e-06,
      "loss": 0.5427,
      "step": 52707
    },
    {
      "epoch": 1.6191441649003164,
      "grad_norm": 0.400070458650589,
      "learning_rate": 1.7422171629356754e-06,
      "loss": 0.5414,
      "step": 52708
    },
    {
      "epoch": 1.6191748840352655,
      "grad_norm": 0.44387489557266235,
      "learning_rate": 1.7419446066350543e-06,
      "loss": 0.4413,
      "step": 52709
    },
    {
      "epoch": 1.6192056031702147,
      "grad_norm": 0.47693246603012085,
      "learning_rate": 1.7416720696216993e-06,
      "loss": 0.4187,
      "step": 52710
    },
    {
      "epoch": 1.6192363223051638,
      "grad_norm": 1.0478614568710327,
      "learning_rate": 1.7413995518962478e-06,
      "loss": 0.5438,
      "step": 52711
    },
    {
      "epoch": 1.619267041440113,
      "grad_norm": 0.3908657431602478,
      "learning_rate": 1.7411270534593328e-06,
      "loss": 0.4634,
      "step": 52712
    },
    {
      "epoch": 1.6192977605750623,
      "grad_norm": 0.41553962230682373,
      "learning_rate": 1.7408545743115911e-06,
      "loss": 0.4844,
      "step": 52713
    },
    {
      "epoch": 1.6193284797100114,
      "grad_norm": 0.42339757084846497,
      "learning_rate": 1.7405821144536616e-06,
      "loss": 0.4785,
      "step": 52714
    },
    {
      "epoch": 1.6193591988449605,
      "grad_norm": 0.40563225746154785,
      "learning_rate": 1.7403096738861813e-06,
      "loss": 0.5241,
      "step": 52715
    },
    {
      "epoch": 1.6193899179799098,
      "grad_norm": 0.40411877632141113,
      "learning_rate": 1.7400372526097819e-06,
      "loss": 0.471,
      "step": 52716
    },
    {
      "epoch": 1.619420637114859,
      "grad_norm": 0.4581839442253113,
      "learning_rate": 1.739764850625103e-06,
      "loss": 0.4298,
      "step": 52717
    },
    {
      "epoch": 1.619451356249808,
      "grad_norm": 0.4284224212169647,
      "learning_rate": 1.7394924679327795e-06,
      "loss": 0.4163,
      "step": 52718
    },
    {
      "epoch": 1.6194820753847572,
      "grad_norm": 0.40373459458351135,
      "learning_rate": 1.739220104533449e-06,
      "loss": 0.4555,
      "step": 52719
    },
    {
      "epoch": 1.6195127945197063,
      "grad_norm": 0.45215681195259094,
      "learning_rate": 1.7389477604277493e-06,
      "loss": 0.4318,
      "step": 52720
    },
    {
      "epoch": 1.6195435136546554,
      "grad_norm": 0.41596171259880066,
      "learning_rate": 1.7386754356163104e-06,
      "loss": 0.4586,
      "step": 52721
    },
    {
      "epoch": 1.6195742327896046,
      "grad_norm": 0.44521674513816833,
      "learning_rate": 1.7384031300997727e-06,
      "loss": 0.4597,
      "step": 52722
    },
    {
      "epoch": 1.6196049519245537,
      "grad_norm": 0.4813234508037567,
      "learning_rate": 1.7381308438787714e-06,
      "loss": 0.4376,
      "step": 52723
    },
    {
      "epoch": 1.619635671059503,
      "grad_norm": 0.40289777517318726,
      "learning_rate": 1.7378585769539459e-06,
      "loss": 0.4689,
      "step": 52724
    },
    {
      "epoch": 1.6196663901944521,
      "grad_norm": 0.47450244426727295,
      "learning_rate": 1.7375863293259253e-06,
      "loss": 0.5198,
      "step": 52725
    },
    {
      "epoch": 1.6196971093294013,
      "grad_norm": 0.43613916635513306,
      "learning_rate": 1.737314100995352e-06,
      "loss": 0.5136,
      "step": 52726
    },
    {
      "epoch": 1.6197278284643506,
      "grad_norm": 0.43165749311447144,
      "learning_rate": 1.737041891962853e-06,
      "loss": 0.4808,
      "step": 52727
    },
    {
      "epoch": 1.6197585475992997,
      "grad_norm": 0.4345806837081909,
      "learning_rate": 1.7367697022290742e-06,
      "loss": 0.5143,
      "step": 52728
    },
    {
      "epoch": 1.6197892667342488,
      "grad_norm": 0.39397794008255005,
      "learning_rate": 1.7364975317946453e-06,
      "loss": 0.4659,
      "step": 52729
    },
    {
      "epoch": 1.619819985869198,
      "grad_norm": 0.4466148316860199,
      "learning_rate": 1.7362253806602058e-06,
      "loss": 0.4756,
      "step": 52730
    },
    {
      "epoch": 1.619850705004147,
      "grad_norm": 0.4165184795856476,
      "learning_rate": 1.7359532488263876e-06,
      "loss": 0.4445,
      "step": 52731
    },
    {
      "epoch": 1.6198814241390962,
      "grad_norm": 0.4204852283000946,
      "learning_rate": 1.7356811362938263e-06,
      "loss": 0.4838,
      "step": 52732
    },
    {
      "epoch": 1.6199121432740453,
      "grad_norm": 0.4773303270339966,
      "learning_rate": 1.7354090430631586e-06,
      "loss": 0.5317,
      "step": 52733
    },
    {
      "epoch": 1.6199428624089944,
      "grad_norm": 0.41253700852394104,
      "learning_rate": 1.7351369691350218e-06,
      "loss": 0.4984,
      "step": 52734
    },
    {
      "epoch": 1.6199735815439438,
      "grad_norm": 0.390605628490448,
      "learning_rate": 1.7348649145100516e-06,
      "loss": 0.5063,
      "step": 52735
    },
    {
      "epoch": 1.620004300678893,
      "grad_norm": 0.47716352343559265,
      "learning_rate": 1.7345928791888767e-06,
      "loss": 0.5511,
      "step": 52736
    },
    {
      "epoch": 1.620035019813842,
      "grad_norm": 0.4821639955043793,
      "learning_rate": 1.734320863172142e-06,
      "loss": 0.5332,
      "step": 52737
    },
    {
      "epoch": 1.6200657389487914,
      "grad_norm": 0.41641849279403687,
      "learning_rate": 1.734048866460476e-06,
      "loss": 0.523,
      "step": 52738
    },
    {
      "epoch": 1.6200964580837405,
      "grad_norm": 0.4864204525947571,
      "learning_rate": 1.7337768890545182e-06,
      "loss": 0.5526,
      "step": 52739
    },
    {
      "epoch": 1.6201271772186896,
      "grad_norm": 0.4279896318912506,
      "learning_rate": 1.7335049309549002e-06,
      "loss": 0.4592,
      "step": 52740
    },
    {
      "epoch": 1.6201578963536387,
      "grad_norm": 0.4400140941143036,
      "learning_rate": 1.733232992162258e-06,
      "loss": 0.4442,
      "step": 52741
    },
    {
      "epoch": 1.6201886154885878,
      "grad_norm": 0.41938018798828125,
      "learning_rate": 1.7329610726772272e-06,
      "loss": 0.4323,
      "step": 52742
    },
    {
      "epoch": 1.620219334623537,
      "grad_norm": 0.4287515878677368,
      "learning_rate": 1.7326891725004458e-06,
      "loss": 0.4686,
      "step": 52743
    },
    {
      "epoch": 1.620250053758486,
      "grad_norm": 0.42296311259269714,
      "learning_rate": 1.7324172916325444e-06,
      "loss": 0.5214,
      "step": 52744
    },
    {
      "epoch": 1.6202807728934352,
      "grad_norm": 0.4176670014858246,
      "learning_rate": 1.7321454300741602e-06,
      "loss": 0.4563,
      "step": 52745
    },
    {
      "epoch": 1.6203114920283843,
      "grad_norm": 0.41443684697151184,
      "learning_rate": 1.7318735878259263e-06,
      "loss": 0.4594,
      "step": 52746
    },
    {
      "epoch": 1.6203422111633337,
      "grad_norm": 0.41109299659729004,
      "learning_rate": 1.731601764888483e-06,
      "loss": 0.5315,
      "step": 52747
    },
    {
      "epoch": 1.6203729302982828,
      "grad_norm": 0.44589129090309143,
      "learning_rate": 1.7313299612624578e-06,
      "loss": 0.4457,
      "step": 52748
    },
    {
      "epoch": 1.6204036494332321,
      "grad_norm": 0.43231692910194397,
      "learning_rate": 1.731058176948489e-06,
      "loss": 0.4429,
      "step": 52749
    },
    {
      "epoch": 1.6204343685681812,
      "grad_norm": 0.5427956581115723,
      "learning_rate": 1.7307864119472117e-06,
      "loss": 0.4724,
      "step": 52750
    },
    {
      "epoch": 1.6204650877031304,
      "grad_norm": 0.4213424623012543,
      "learning_rate": 1.730514666259263e-06,
      "loss": 0.4358,
      "step": 52751
    },
    {
      "epoch": 1.6204958068380795,
      "grad_norm": 0.4119175374507904,
      "learning_rate": 1.7302429398852716e-06,
      "loss": 0.4766,
      "step": 52752
    },
    {
      "epoch": 1.6205265259730286,
      "grad_norm": 0.4390815794467926,
      "learning_rate": 1.7299712328258755e-06,
      "loss": 0.4757,
      "step": 52753
    },
    {
      "epoch": 1.6205572451079777,
      "grad_norm": 0.3928334712982178,
      "learning_rate": 1.72969954508171e-06,
      "loss": 0.4626,
      "step": 52754
    },
    {
      "epoch": 1.6205879642429268,
      "grad_norm": 0.4408207833766937,
      "learning_rate": 1.7294278766534078e-06,
      "loss": 0.4105,
      "step": 52755
    },
    {
      "epoch": 1.620618683377876,
      "grad_norm": 0.44701772928237915,
      "learning_rate": 1.7291562275416073e-06,
      "loss": 0.4983,
      "step": 52756
    },
    {
      "epoch": 1.620649402512825,
      "grad_norm": 0.42870160937309265,
      "learning_rate": 1.7288845977469382e-06,
      "loss": 0.4513,
      "step": 52757
    },
    {
      "epoch": 1.6206801216477744,
      "grad_norm": 0.49217212200164795,
      "learning_rate": 1.7286129872700352e-06,
      "loss": 0.5294,
      "step": 52758
    },
    {
      "epoch": 1.6207108407827235,
      "grad_norm": 0.38320133090019226,
      "learning_rate": 1.7283413961115359e-06,
      "loss": 0.3818,
      "step": 52759
    },
    {
      "epoch": 1.6207415599176729,
      "grad_norm": 0.4355020523071289,
      "learning_rate": 1.728069824272074e-06,
      "loss": 0.5094,
      "step": 52760
    },
    {
      "epoch": 1.620772279052622,
      "grad_norm": 0.4204194247722626,
      "learning_rate": 1.7277982717522813e-06,
      "loss": 0.48,
      "step": 52761
    },
    {
      "epoch": 1.6208029981875711,
      "grad_norm": 0.4677395224571228,
      "learning_rate": 1.7275267385527961e-06,
      "loss": 0.4439,
      "step": 52762
    },
    {
      "epoch": 1.6208337173225202,
      "grad_norm": 0.4094585180282593,
      "learning_rate": 1.7272552246742435e-06,
      "loss": 0.3942,
      "step": 52763
    },
    {
      "epoch": 1.6208644364574694,
      "grad_norm": 0.4780771732330322,
      "learning_rate": 1.7269837301172709e-06,
      "loss": 0.4336,
      "step": 52764
    },
    {
      "epoch": 1.6208951555924185,
      "grad_norm": 0.4261172413825989,
      "learning_rate": 1.7267122548825021e-06,
      "loss": 0.3972,
      "step": 52765
    },
    {
      "epoch": 1.6209258747273676,
      "grad_norm": 0.4112967252731323,
      "learning_rate": 1.7264407989705768e-06,
      "loss": 0.4838,
      "step": 52766
    },
    {
      "epoch": 1.6209565938623167,
      "grad_norm": 0.4095844030380249,
      "learning_rate": 1.7261693623821253e-06,
      "loss": 0.4591,
      "step": 52767
    },
    {
      "epoch": 1.6209873129972658,
      "grad_norm": 0.3908267021179199,
      "learning_rate": 1.7258979451177826e-06,
      "loss": 0.43,
      "step": 52768
    },
    {
      "epoch": 1.6210180321322152,
      "grad_norm": 0.45144641399383545,
      "learning_rate": 1.725626547178183e-06,
      "loss": 0.4654,
      "step": 52769
    },
    {
      "epoch": 1.6210487512671643,
      "grad_norm": 0.4348106384277344,
      "learning_rate": 1.7253551685639624e-06,
      "loss": 0.4805,
      "step": 52770
    },
    {
      "epoch": 1.6210794704021136,
      "grad_norm": 0.47251561284065247,
      "learning_rate": 1.7250838092757516e-06,
      "loss": 0.5109,
      "step": 52771
    },
    {
      "epoch": 1.6211101895370628,
      "grad_norm": 0.4213559627532959,
      "learning_rate": 1.7248124693141844e-06,
      "loss": 0.4217,
      "step": 52772
    },
    {
      "epoch": 1.6211409086720119,
      "grad_norm": 0.4806619882583618,
      "learning_rate": 1.7245411486798957e-06,
      "loss": 0.4735,
      "step": 52773
    },
    {
      "epoch": 1.621171627806961,
      "grad_norm": 0.4289068877696991,
      "learning_rate": 1.7242698473735199e-06,
      "loss": 0.5079,
      "step": 52774
    },
    {
      "epoch": 1.6212023469419101,
      "grad_norm": 0.4402616024017334,
      "learning_rate": 1.7239985653956914e-06,
      "loss": 0.4644,
      "step": 52775
    },
    {
      "epoch": 1.6212330660768592,
      "grad_norm": 0.4881012737751007,
      "learning_rate": 1.7237273027470403e-06,
      "loss": 0.4979,
      "step": 52776
    },
    {
      "epoch": 1.6212637852118084,
      "grad_norm": 0.5772343873977661,
      "learning_rate": 1.7234560594282013e-06,
      "loss": 0.4542,
      "step": 52777
    },
    {
      "epoch": 1.6212945043467575,
      "grad_norm": 0.41683822870254517,
      "learning_rate": 1.7231848354398096e-06,
      "loss": 0.5102,
      "step": 52778
    },
    {
      "epoch": 1.6213252234817066,
      "grad_norm": 0.5712096095085144,
      "learning_rate": 1.7229136307825e-06,
      "loss": 0.3818,
      "step": 52779
    },
    {
      "epoch": 1.621355942616656,
      "grad_norm": 0.4193539619445801,
      "learning_rate": 1.7226424454569014e-06,
      "loss": 0.4437,
      "step": 52780
    },
    {
      "epoch": 1.621386661751605,
      "grad_norm": 0.4393603205680847,
      "learning_rate": 1.7223712794636494e-06,
      "loss": 0.4433,
      "step": 52781
    },
    {
      "epoch": 1.6214173808865542,
      "grad_norm": 0.4600200951099396,
      "learning_rate": 1.7221001328033771e-06,
      "loss": 0.4513,
      "step": 52782
    },
    {
      "epoch": 1.6214481000215035,
      "grad_norm": 0.4039551913738251,
      "learning_rate": 1.7218290054767206e-06,
      "loss": 0.4095,
      "step": 52783
    },
    {
      "epoch": 1.6214788191564526,
      "grad_norm": 0.4204828143119812,
      "learning_rate": 1.7215578974843072e-06,
      "loss": 0.4991,
      "step": 52784
    },
    {
      "epoch": 1.6215095382914018,
      "grad_norm": 0.44622159004211426,
      "learning_rate": 1.7212868088267752e-06,
      "loss": 0.5219,
      "step": 52785
    },
    {
      "epoch": 1.6215402574263509,
      "grad_norm": 0.49531522393226624,
      "learning_rate": 1.7210157395047556e-06,
      "loss": 0.4737,
      "step": 52786
    },
    {
      "epoch": 1.6215709765613,
      "grad_norm": 0.44216179847717285,
      "learning_rate": 1.720744689518884e-06,
      "loss": 0.5101,
      "step": 52787
    },
    {
      "epoch": 1.6216016956962491,
      "grad_norm": 0.396101713180542,
      "learning_rate": 1.720473658869789e-06,
      "loss": 0.4818,
      "step": 52788
    },
    {
      "epoch": 1.6216324148311982,
      "grad_norm": 0.4798869788646698,
      "learning_rate": 1.7202026475581058e-06,
      "loss": 0.4579,
      "step": 52789
    },
    {
      "epoch": 1.6216631339661474,
      "grad_norm": 0.42313602566719055,
      "learning_rate": 1.719931655584467e-06,
      "loss": 0.4543,
      "step": 52790
    },
    {
      "epoch": 1.6216938531010967,
      "grad_norm": 0.4511931240558624,
      "learning_rate": 1.7196606829495078e-06,
      "loss": 0.4381,
      "step": 52791
    },
    {
      "epoch": 1.6217245722360458,
      "grad_norm": 0.41648069024086,
      "learning_rate": 1.7193897296538609e-06,
      "loss": 0.5003,
      "step": 52792
    },
    {
      "epoch": 1.621755291370995,
      "grad_norm": 0.42517033219337463,
      "learning_rate": 1.7191187956981547e-06,
      "loss": 0.4501,
      "step": 52793
    },
    {
      "epoch": 1.6217860105059443,
      "grad_norm": 0.41825804114341736,
      "learning_rate": 1.7188478810830278e-06,
      "loss": 0.4921,
      "step": 52794
    },
    {
      "epoch": 1.6218167296408934,
      "grad_norm": 0.4457760751247406,
      "learning_rate": 1.7185769858091051e-06,
      "loss": 0.4208,
      "step": 52795
    },
    {
      "epoch": 1.6218474487758425,
      "grad_norm": 0.4030088782310486,
      "learning_rate": 1.7183061098770293e-06,
      "loss": 0.4812,
      "step": 52796
    },
    {
      "epoch": 1.6218781679107916,
      "grad_norm": 0.4123600125312805,
      "learning_rate": 1.7180352532874256e-06,
      "loss": 0.4611,
      "step": 52797
    },
    {
      "epoch": 1.6219088870457408,
      "grad_norm": 0.4766686260700226,
      "learning_rate": 1.7177644160409311e-06,
      "loss": 0.5244,
      "step": 52798
    },
    {
      "epoch": 1.6219396061806899,
      "grad_norm": 0.4317100942134857,
      "learning_rate": 1.7174935981381713e-06,
      "loss": 0.5045,
      "step": 52799
    },
    {
      "epoch": 1.621970325315639,
      "grad_norm": 0.4243156611919403,
      "learning_rate": 1.7172227995797886e-06,
      "loss": 0.3704,
      "step": 52800
    },
    {
      "epoch": 1.6220010444505881,
      "grad_norm": 0.5289067029953003,
      "learning_rate": 1.716952020366408e-06,
      "loss": 0.5045,
      "step": 52801
    },
    {
      "epoch": 1.6220317635855375,
      "grad_norm": 0.4268988370895386,
      "learning_rate": 1.7166812604986672e-06,
      "loss": 0.5398,
      "step": 52802
    },
    {
      "epoch": 1.6220624827204866,
      "grad_norm": 0.42752256989479065,
      "learning_rate": 1.716410519977193e-06,
      "loss": 0.4392,
      "step": 52803
    },
    {
      "epoch": 1.6220932018554357,
      "grad_norm": 0.39156365394592285,
      "learning_rate": 1.7161397988026208e-06,
      "loss": 0.429,
      "step": 52804
    },
    {
      "epoch": 1.622123920990385,
      "grad_norm": 0.6130636930465698,
      "learning_rate": 1.715869096975582e-06,
      "loss": 0.4073,
      "step": 52805
    },
    {
      "epoch": 1.6221546401253342,
      "grad_norm": 0.4638320207595825,
      "learning_rate": 1.7155984144967131e-06,
      "loss": 0.4372,
      "step": 52806
    },
    {
      "epoch": 1.6221853592602833,
      "grad_norm": 0.527717113494873,
      "learning_rate": 1.715327751366639e-06,
      "loss": 0.5477,
      "step": 52807
    },
    {
      "epoch": 1.6222160783952324,
      "grad_norm": 0.43149498105049133,
      "learning_rate": 1.7150571075859967e-06,
      "loss": 0.4903,
      "step": 52808
    },
    {
      "epoch": 1.6222467975301815,
      "grad_norm": 0.4394442141056061,
      "learning_rate": 1.7147864831554162e-06,
      "loss": 0.45,
      "step": 52809
    },
    {
      "epoch": 1.6222775166651306,
      "grad_norm": 0.4205341637134552,
      "learning_rate": 1.714515878075531e-06,
      "loss": 0.5108,
      "step": 52810
    },
    {
      "epoch": 1.6223082358000798,
      "grad_norm": 0.5242716670036316,
      "learning_rate": 1.7142452923469744e-06,
      "loss": 0.4484,
      "step": 52811
    },
    {
      "epoch": 1.6223389549350289,
      "grad_norm": 0.44869017601013184,
      "learning_rate": 1.7139747259703755e-06,
      "loss": 0.4686,
      "step": 52812
    },
    {
      "epoch": 1.6223696740699782,
      "grad_norm": 0.43025073409080505,
      "learning_rate": 1.7137041789463659e-06,
      "loss": 0.4917,
      "step": 52813
    },
    {
      "epoch": 1.6224003932049273,
      "grad_norm": 0.498980849981308,
      "learning_rate": 1.71343365127558e-06,
      "loss": 0.4637,
      "step": 52814
    },
    {
      "epoch": 1.6224311123398765,
      "grad_norm": 0.43369734287261963,
      "learning_rate": 1.7131631429586504e-06,
      "loss": 0.4562,
      "step": 52815
    },
    {
      "epoch": 1.6224618314748258,
      "grad_norm": 0.3924112617969513,
      "learning_rate": 1.7128926539962042e-06,
      "loss": 0.5282,
      "step": 52816
    },
    {
      "epoch": 1.622492550609775,
      "grad_norm": 0.41189801692962646,
      "learning_rate": 1.7126221843888768e-06,
      "loss": 0.5184,
      "step": 52817
    },
    {
      "epoch": 1.622523269744724,
      "grad_norm": 0.48239365220069885,
      "learning_rate": 1.7123517341372987e-06,
      "loss": 0.4842,
      "step": 52818
    },
    {
      "epoch": 1.6225539888796732,
      "grad_norm": 0.4785408079624176,
      "learning_rate": 1.7120813032421046e-06,
      "loss": 0.4872,
      "step": 52819
    },
    {
      "epoch": 1.6225847080146223,
      "grad_norm": 0.4313514530658722,
      "learning_rate": 1.71181089170392e-06,
      "loss": 0.4637,
      "step": 52820
    },
    {
      "epoch": 1.6226154271495714,
      "grad_norm": 0.43610724806785583,
      "learning_rate": 1.711540499523381e-06,
      "loss": 0.484,
      "step": 52821
    },
    {
      "epoch": 1.6226461462845205,
      "grad_norm": 0.46362030506134033,
      "learning_rate": 1.7112701267011178e-06,
      "loss": 0.4361,
      "step": 52822
    },
    {
      "epoch": 1.6226768654194696,
      "grad_norm": 0.4698885679244995,
      "learning_rate": 1.7109997732377648e-06,
      "loss": 0.4131,
      "step": 52823
    },
    {
      "epoch": 1.622707584554419,
      "grad_norm": 0.45239490270614624,
      "learning_rate": 1.710729439133948e-06,
      "loss": 0.4863,
      "step": 52824
    },
    {
      "epoch": 1.6227383036893681,
      "grad_norm": 0.43984028697013855,
      "learning_rate": 1.7104591243903013e-06,
      "loss": 0.5132,
      "step": 52825
    },
    {
      "epoch": 1.6227690228243172,
      "grad_norm": 0.4246686100959778,
      "learning_rate": 1.7101888290074564e-06,
      "loss": 0.4599,
      "step": 52826
    },
    {
      "epoch": 1.6227997419592666,
      "grad_norm": 0.40741416811943054,
      "learning_rate": 1.709918552986044e-06,
      "loss": 0.4469,
      "step": 52827
    },
    {
      "epoch": 1.6228304610942157,
      "grad_norm": 0.431545615196228,
      "learning_rate": 1.709648296326698e-06,
      "loss": 0.4611,
      "step": 52828
    },
    {
      "epoch": 1.6228611802291648,
      "grad_norm": 0.4231680631637573,
      "learning_rate": 1.7093780590300458e-06,
      "loss": 0.5612,
      "step": 52829
    },
    {
      "epoch": 1.622891899364114,
      "grad_norm": 0.42843756079673767,
      "learning_rate": 1.7091078410967232e-06,
      "loss": 0.4319,
      "step": 52830
    },
    {
      "epoch": 1.622922618499063,
      "grad_norm": 0.46950289607048035,
      "learning_rate": 1.7088376425273524e-06,
      "loss": 0.4766,
      "step": 52831
    },
    {
      "epoch": 1.6229533376340122,
      "grad_norm": 0.419212281703949,
      "learning_rate": 1.7085674633225746e-06,
      "loss": 0.5462,
      "step": 52832
    },
    {
      "epoch": 1.6229840567689613,
      "grad_norm": 0.44486963748931885,
      "learning_rate": 1.7082973034830153e-06,
      "loss": 0.4561,
      "step": 52833
    },
    {
      "epoch": 1.6230147759039104,
      "grad_norm": 0.42994675040245056,
      "learning_rate": 1.7080271630093093e-06,
      "loss": 0.5313,
      "step": 52834
    },
    {
      "epoch": 1.6230454950388598,
      "grad_norm": 0.46249932050704956,
      "learning_rate": 1.7077570419020817e-06,
      "loss": 0.4265,
      "step": 52835
    },
    {
      "epoch": 1.6230762141738089,
      "grad_norm": 0.4184545576572418,
      "learning_rate": 1.7074869401619665e-06,
      "loss": 0.395,
      "step": 52836
    },
    {
      "epoch": 1.623106933308758,
      "grad_norm": 0.5130535364151001,
      "learning_rate": 1.7072168577895954e-06,
      "loss": 0.4624,
      "step": 52837
    },
    {
      "epoch": 1.6231376524437073,
      "grad_norm": 0.4264039099216461,
      "learning_rate": 1.706946794785601e-06,
      "loss": 0.4817,
      "step": 52838
    },
    {
      "epoch": 1.6231683715786565,
      "grad_norm": 0.4803733825683594,
      "learning_rate": 1.7066767511506088e-06,
      "loss": 0.5615,
      "step": 52839
    },
    {
      "epoch": 1.6231990907136056,
      "grad_norm": 0.4226588010787964,
      "learning_rate": 1.7064067268852525e-06,
      "loss": 0.4151,
      "step": 52840
    },
    {
      "epoch": 1.6232298098485547,
      "grad_norm": 0.4841756522655487,
      "learning_rate": 1.7061367219901614e-06,
      "loss": 0.4677,
      "step": 52841
    },
    {
      "epoch": 1.6232605289835038,
      "grad_norm": 0.3932638168334961,
      "learning_rate": 1.705866736465971e-06,
      "loss": 0.4858,
      "step": 52842
    },
    {
      "epoch": 1.623291248118453,
      "grad_norm": 0.42200931906700134,
      "learning_rate": 1.7055967703133047e-06,
      "loss": 0.468,
      "step": 52843
    },
    {
      "epoch": 1.623321967253402,
      "grad_norm": 0.41386500000953674,
      "learning_rate": 1.7053268235327969e-06,
      "loss": 0.408,
      "step": 52844
    },
    {
      "epoch": 1.6233526863883512,
      "grad_norm": 0.49873074889183044,
      "learning_rate": 1.7050568961250779e-06,
      "loss": 0.4429,
      "step": 52845
    },
    {
      "epoch": 1.6233834055233005,
      "grad_norm": 0.4604945480823517,
      "learning_rate": 1.7047869880907776e-06,
      "loss": 0.3833,
      "step": 52846
    },
    {
      "epoch": 1.6234141246582496,
      "grad_norm": 0.4279811978340149,
      "learning_rate": 1.7045170994305293e-06,
      "loss": 0.4144,
      "step": 52847
    },
    {
      "epoch": 1.6234448437931988,
      "grad_norm": 0.41827934980392456,
      "learning_rate": 1.7042472301449576e-06,
      "loss": 0.4486,
      "step": 52848
    },
    {
      "epoch": 1.623475562928148,
      "grad_norm": 0.44809481501579285,
      "learning_rate": 1.703977380234696e-06,
      "loss": 0.4279,
      "step": 52849
    },
    {
      "epoch": 1.6235062820630972,
      "grad_norm": 0.43755245208740234,
      "learning_rate": 1.7037075497003752e-06,
      "loss": 0.4983,
      "step": 52850
    },
    {
      "epoch": 1.6235370011980463,
      "grad_norm": 0.4468478858470917,
      "learning_rate": 1.703437738542627e-06,
      "loss": 0.4437,
      "step": 52851
    },
    {
      "epoch": 1.6235677203329955,
      "grad_norm": 0.45763835310935974,
      "learning_rate": 1.7031679467620764e-06,
      "loss": 0.3975,
      "step": 52852
    },
    {
      "epoch": 1.6235984394679446,
      "grad_norm": 0.41362226009368896,
      "learning_rate": 1.7028981743593565e-06,
      "loss": 0.3697,
      "step": 52853
    },
    {
      "epoch": 1.6236291586028937,
      "grad_norm": 0.44734060764312744,
      "learning_rate": 1.7026284213350986e-06,
      "loss": 0.495,
      "step": 52854
    },
    {
      "epoch": 1.6236598777378428,
      "grad_norm": 0.4530119299888611,
      "learning_rate": 1.7023586876899322e-06,
      "loss": 0.4548,
      "step": 52855
    },
    {
      "epoch": 1.623690596872792,
      "grad_norm": 0.41884109377861023,
      "learning_rate": 1.702088973424485e-06,
      "loss": 0.4656,
      "step": 52856
    },
    {
      "epoch": 1.623721316007741,
      "grad_norm": 0.4144706428050995,
      "learning_rate": 1.7018192785393916e-06,
      "loss": 0.4431,
      "step": 52857
    },
    {
      "epoch": 1.6237520351426904,
      "grad_norm": 0.409768283367157,
      "learning_rate": 1.701549603035273e-06,
      "loss": 0.4728,
      "step": 52858
    },
    {
      "epoch": 1.6237827542776395,
      "grad_norm": 0.42248669266700745,
      "learning_rate": 1.7012799469127706e-06,
      "loss": 0.4741,
      "step": 52859
    },
    {
      "epoch": 1.6238134734125889,
      "grad_norm": 0.4526514410972595,
      "learning_rate": 1.701010310172505e-06,
      "loss": 0.4521,
      "step": 52860
    },
    {
      "epoch": 1.623844192547538,
      "grad_norm": 0.4145238697528839,
      "learning_rate": 1.7007406928151126e-06,
      "loss": 0.5262,
      "step": 52861
    },
    {
      "epoch": 1.623874911682487,
      "grad_norm": 0.4466416835784912,
      "learning_rate": 1.7004710948412151e-06,
      "loss": 0.5447,
      "step": 52862
    },
    {
      "epoch": 1.6239056308174362,
      "grad_norm": 0.4129619300365448,
      "learning_rate": 1.7002015162514485e-06,
      "loss": 0.479,
      "step": 52863
    },
    {
      "epoch": 1.6239363499523853,
      "grad_norm": 0.4483216106891632,
      "learning_rate": 1.6999319570464445e-06,
      "loss": 0.4359,
      "step": 52864
    },
    {
      "epoch": 1.6239670690873345,
      "grad_norm": 0.45884621143341064,
      "learning_rate": 1.699662417226826e-06,
      "loss": 0.4769,
      "step": 52865
    },
    {
      "epoch": 1.6239977882222836,
      "grad_norm": 0.4422648549079895,
      "learning_rate": 1.6993928967932282e-06,
      "loss": 0.4992,
      "step": 52866
    },
    {
      "epoch": 1.6240285073572327,
      "grad_norm": 0.43032652139663696,
      "learning_rate": 1.6991233957462727e-06,
      "loss": 0.4812,
      "step": 52867
    },
    {
      "epoch": 1.6240592264921818,
      "grad_norm": 0.49478259682655334,
      "learning_rate": 1.6988539140866e-06,
      "loss": 0.4535,
      "step": 52868
    },
    {
      "epoch": 1.6240899456271312,
      "grad_norm": 0.4094851016998291,
      "learning_rate": 1.6985844518148308e-06,
      "loss": 0.5658,
      "step": 52869
    },
    {
      "epoch": 1.6241206647620803,
      "grad_norm": 0.39290907979011536,
      "learning_rate": 1.6983150089315992e-06,
      "loss": 0.5199,
      "step": 52870
    },
    {
      "epoch": 1.6241513838970296,
      "grad_norm": 0.432041734457016,
      "learning_rate": 1.698045585437531e-06,
      "loss": 0.5066,
      "step": 52871
    },
    {
      "epoch": 1.6241821030319787,
      "grad_norm": 0.39777252078056335,
      "learning_rate": 1.6977761813332572e-06,
      "loss": 0.411,
      "step": 52872
    },
    {
      "epoch": 1.6242128221669279,
      "grad_norm": 0.4758470356464386,
      "learning_rate": 1.697506796619407e-06,
      "loss": 0.4437,
      "step": 52873
    },
    {
      "epoch": 1.624243541301877,
      "grad_norm": 0.47248825430870056,
      "learning_rate": 1.6972374312966112e-06,
      "loss": 0.4863,
      "step": 52874
    },
    {
      "epoch": 1.624274260436826,
      "grad_norm": 0.4506840109825134,
      "learning_rate": 1.6969680853654957e-06,
      "loss": 0.4353,
      "step": 52875
    },
    {
      "epoch": 1.6243049795717752,
      "grad_norm": 0.4110329747200012,
      "learning_rate": 1.6966987588266903e-06,
      "loss": 0.4618,
      "step": 52876
    },
    {
      "epoch": 1.6243356987067243,
      "grad_norm": 0.41332074999809265,
      "learning_rate": 1.6964294516808256e-06,
      "loss": 0.4908,
      "step": 52877
    },
    {
      "epoch": 1.6243664178416735,
      "grad_norm": 0.4092804491519928,
      "learning_rate": 1.6961601639285319e-06,
      "loss": 0.5546,
      "step": 52878
    },
    {
      "epoch": 1.6243971369766226,
      "grad_norm": 0.4339575171470642,
      "learning_rate": 1.6958908955704333e-06,
      "loss": 0.3503,
      "step": 52879
    },
    {
      "epoch": 1.624427856111572,
      "grad_norm": 0.38915765285491943,
      "learning_rate": 1.6956216466071618e-06,
      "loss": 0.4268,
      "step": 52880
    },
    {
      "epoch": 1.624458575246521,
      "grad_norm": 0.4492282271385193,
      "learning_rate": 1.6953524170393466e-06,
      "loss": 0.4497,
      "step": 52881
    },
    {
      "epoch": 1.6244892943814704,
      "grad_norm": 0.3980579376220703,
      "learning_rate": 1.695083206867615e-06,
      "loss": 0.4921,
      "step": 52882
    },
    {
      "epoch": 1.6245200135164195,
      "grad_norm": 0.41732412576675415,
      "learning_rate": 1.6948140160925996e-06,
      "loss": 0.4045,
      "step": 52883
    },
    {
      "epoch": 1.6245507326513686,
      "grad_norm": 0.4426502585411072,
      "learning_rate": 1.6945448447149226e-06,
      "loss": 0.4929,
      "step": 52884
    },
    {
      "epoch": 1.6245814517863177,
      "grad_norm": 0.41497543454170227,
      "learning_rate": 1.6942756927352167e-06,
      "loss": 0.4652,
      "step": 52885
    },
    {
      "epoch": 1.6246121709212669,
      "grad_norm": 0.4916430115699768,
      "learning_rate": 1.69400656015411e-06,
      "loss": 0.4679,
      "step": 52886
    },
    {
      "epoch": 1.624642890056216,
      "grad_norm": 0.4407311975955963,
      "learning_rate": 1.6937374469722344e-06,
      "loss": 0.4479,
      "step": 52887
    },
    {
      "epoch": 1.624673609191165,
      "grad_norm": 0.4566994905471802,
      "learning_rate": 1.6934683531902119e-06,
      "loss": 0.4741,
      "step": 52888
    },
    {
      "epoch": 1.6247043283261142,
      "grad_norm": 0.48549994826316833,
      "learning_rate": 1.6931992788086737e-06,
      "loss": 0.4336,
      "step": 52889
    },
    {
      "epoch": 1.6247350474610633,
      "grad_norm": 0.44277745485305786,
      "learning_rate": 1.6929302238282485e-06,
      "loss": 0.5856,
      "step": 52890
    },
    {
      "epoch": 1.6247657665960127,
      "grad_norm": 0.4083728492259979,
      "learning_rate": 1.692661188249569e-06,
      "loss": 0.3833,
      "step": 52891
    },
    {
      "epoch": 1.6247964857309618,
      "grad_norm": 0.3764069080352783,
      "learning_rate": 1.6923921720732561e-06,
      "loss": 0.4252,
      "step": 52892
    },
    {
      "epoch": 1.624827204865911,
      "grad_norm": 0.5659852623939514,
      "learning_rate": 1.6921231752999434e-06,
      "loss": 0.4471,
      "step": 52893
    },
    {
      "epoch": 1.6248579240008603,
      "grad_norm": 0.49462440609931946,
      "learning_rate": 1.6918541979302527e-06,
      "loss": 0.503,
      "step": 52894
    },
    {
      "epoch": 1.6248886431358094,
      "grad_norm": 0.43799060583114624,
      "learning_rate": 1.6915852399648213e-06,
      "loss": 0.4207,
      "step": 52895
    },
    {
      "epoch": 1.6249193622707585,
      "grad_norm": 0.4556388854980469,
      "learning_rate": 1.691316301404271e-06,
      "loss": 0.5298,
      "step": 52896
    },
    {
      "epoch": 1.6249500814057076,
      "grad_norm": 0.45673272013664246,
      "learning_rate": 1.6910473822492345e-06,
      "loss": 0.4984,
      "step": 52897
    },
    {
      "epoch": 1.6249808005406567,
      "grad_norm": 0.4331735074520111,
      "learning_rate": 1.6907784825003337e-06,
      "loss": 0.4573,
      "step": 52898
    },
    {
      "epoch": 1.6250115196756059,
      "grad_norm": 0.42173129320144653,
      "learning_rate": 1.6905096021581991e-06,
      "loss": 0.4507,
      "step": 52899
    },
    {
      "epoch": 1.625042238810555,
      "grad_norm": 0.40215715765953064,
      "learning_rate": 1.6902407412234634e-06,
      "loss": 0.4502,
      "step": 52900
    },
    {
      "epoch": 1.625072957945504,
      "grad_norm": 0.44295212626457214,
      "learning_rate": 1.6899718996967485e-06,
      "loss": 0.3847,
      "step": 52901
    },
    {
      "epoch": 1.6251036770804534,
      "grad_norm": 0.39975297451019287,
      "learning_rate": 1.6897030775786871e-06,
      "loss": 0.488,
      "step": 52902
    },
    {
      "epoch": 1.6251343962154026,
      "grad_norm": 0.42488935589790344,
      "learning_rate": 1.689434274869899e-06,
      "loss": 0.464,
      "step": 52903
    },
    {
      "epoch": 1.6251651153503517,
      "grad_norm": 0.44710150361061096,
      "learning_rate": 1.6891654915710232e-06,
      "loss": 0.4433,
      "step": 52904
    },
    {
      "epoch": 1.625195834485301,
      "grad_norm": 0.419587641954422,
      "learning_rate": 1.6888967276826795e-06,
      "loss": 0.5417,
      "step": 52905
    },
    {
      "epoch": 1.6252265536202501,
      "grad_norm": 0.4608282148838043,
      "learning_rate": 1.6886279832054997e-06,
      "loss": 0.4881,
      "step": 52906
    },
    {
      "epoch": 1.6252572727551993,
      "grad_norm": 0.4715317189693451,
      "learning_rate": 1.6883592581401075e-06,
      "loss": 0.5,
      "step": 52907
    },
    {
      "epoch": 1.6252879918901484,
      "grad_norm": 0.4519421458244324,
      "learning_rate": 1.6880905524871337e-06,
      "loss": 0.4066,
      "step": 52908
    },
    {
      "epoch": 1.6253187110250975,
      "grad_norm": 0.4399053454399109,
      "learning_rate": 1.6878218662472035e-06,
      "loss": 0.5027,
      "step": 52909
    },
    {
      "epoch": 1.6253494301600466,
      "grad_norm": 0.4778147339820862,
      "learning_rate": 1.6875531994209492e-06,
      "loss": 0.454,
      "step": 52910
    },
    {
      "epoch": 1.6253801492949957,
      "grad_norm": 0.429004967212677,
      "learning_rate": 1.6872845520089919e-06,
      "loss": 0.455,
      "step": 52911
    },
    {
      "epoch": 1.6254108684299449,
      "grad_norm": 0.5131707191467285,
      "learning_rate": 1.6870159240119631e-06,
      "loss": 0.4019,
      "step": 52912
    },
    {
      "epoch": 1.6254415875648942,
      "grad_norm": 0.4302538335323334,
      "learning_rate": 1.686747315430488e-06,
      "loss": 0.463,
      "step": 52913
    },
    {
      "epoch": 1.6254723066998433,
      "grad_norm": 0.4076596200466156,
      "learning_rate": 1.6864787262651982e-06,
      "loss": 0.4967,
      "step": 52914
    },
    {
      "epoch": 1.6255030258347924,
      "grad_norm": 0.4366079866886139,
      "learning_rate": 1.6862101565167156e-06,
      "loss": 0.4539,
      "step": 52915
    },
    {
      "epoch": 1.6255337449697418,
      "grad_norm": 0.447009414434433,
      "learning_rate": 1.6859416061856692e-06,
      "loss": 0.4715,
      "step": 52916
    },
    {
      "epoch": 1.625564464104691,
      "grad_norm": 0.3921588957309723,
      "learning_rate": 1.6856730752726869e-06,
      "loss": 0.5144,
      "step": 52917
    },
    {
      "epoch": 1.62559518323964,
      "grad_norm": 0.4241558611392975,
      "learning_rate": 1.6854045637783967e-06,
      "loss": 0.4774,
      "step": 52918
    },
    {
      "epoch": 1.6256259023745891,
      "grad_norm": 0.44520270824432373,
      "learning_rate": 1.685136071703426e-06,
      "loss": 0.4627,
      "step": 52919
    },
    {
      "epoch": 1.6256566215095383,
      "grad_norm": 0.4369450807571411,
      "learning_rate": 1.6848675990483997e-06,
      "loss": 0.4551,
      "step": 52920
    },
    {
      "epoch": 1.6256873406444874,
      "grad_norm": 0.4364747107028961,
      "learning_rate": 1.6845991458139444e-06,
      "loss": 0.443,
      "step": 52921
    },
    {
      "epoch": 1.6257180597794365,
      "grad_norm": 0.4486147165298462,
      "learning_rate": 1.684330712000689e-06,
      "loss": 0.3985,
      "step": 52922
    },
    {
      "epoch": 1.6257487789143856,
      "grad_norm": 0.40148159861564636,
      "learning_rate": 1.6840622976092636e-06,
      "loss": 0.4368,
      "step": 52923
    },
    {
      "epoch": 1.625779498049335,
      "grad_norm": 0.46346738934516907,
      "learning_rate": 1.6837939026402872e-06,
      "loss": 0.4917,
      "step": 52924
    },
    {
      "epoch": 1.625810217184284,
      "grad_norm": 0.4177796542644501,
      "learning_rate": 1.6835255270943917e-06,
      "loss": 0.5154,
      "step": 52925
    },
    {
      "epoch": 1.6258409363192332,
      "grad_norm": 0.43984875082969666,
      "learning_rate": 1.6832571709722034e-06,
      "loss": 0.4621,
      "step": 52926
    },
    {
      "epoch": 1.6258716554541826,
      "grad_norm": 0.45991894602775574,
      "learning_rate": 1.6829888342743516e-06,
      "loss": 0.4965,
      "step": 52927
    },
    {
      "epoch": 1.6259023745891317,
      "grad_norm": 0.4390656054019928,
      "learning_rate": 1.682720517001457e-06,
      "loss": 0.3798,
      "step": 52928
    },
    {
      "epoch": 1.6259330937240808,
      "grad_norm": 0.446139395236969,
      "learning_rate": 1.6824522191541526e-06,
      "loss": 0.5016,
      "step": 52929
    },
    {
      "epoch": 1.62596381285903,
      "grad_norm": 0.42014238238334656,
      "learning_rate": 1.6821839407330566e-06,
      "loss": 0.4121,
      "step": 52930
    },
    {
      "epoch": 1.625994531993979,
      "grad_norm": 0.4294544756412506,
      "learning_rate": 1.681915681738806e-06,
      "loss": 0.5073,
      "step": 52931
    },
    {
      "epoch": 1.6260252511289282,
      "grad_norm": 0.5413081049919128,
      "learning_rate": 1.6816474421720198e-06,
      "loss": 0.4926,
      "step": 52932
    },
    {
      "epoch": 1.6260559702638773,
      "grad_norm": 0.44155871868133545,
      "learning_rate": 1.6813792220333292e-06,
      "loss": 0.4402,
      "step": 52933
    },
    {
      "epoch": 1.6260866893988264,
      "grad_norm": 0.39998164772987366,
      "learning_rate": 1.681111021323356e-06,
      "loss": 0.4893,
      "step": 52934
    },
    {
      "epoch": 1.6261174085337757,
      "grad_norm": 0.3962278366088867,
      "learning_rate": 1.6808428400427267e-06,
      "loss": 0.4461,
      "step": 52935
    },
    {
      "epoch": 1.6261481276687249,
      "grad_norm": 0.43795958161354065,
      "learning_rate": 1.680574678192074e-06,
      "loss": 0.4592,
      "step": 52936
    },
    {
      "epoch": 1.626178846803674,
      "grad_norm": 0.38992181420326233,
      "learning_rate": 1.6803065357720194e-06,
      "loss": 0.4832,
      "step": 52937
    },
    {
      "epoch": 1.6262095659386233,
      "grad_norm": 0.4207608699798584,
      "learning_rate": 1.6800384127831904e-06,
      "loss": 0.5037,
      "step": 52938
    },
    {
      "epoch": 1.6262402850735724,
      "grad_norm": 0.4833424985408783,
      "learning_rate": 1.679770309226212e-06,
      "loss": 0.4178,
      "step": 52939
    },
    {
      "epoch": 1.6262710042085216,
      "grad_norm": 0.45055386424064636,
      "learning_rate": 1.6795022251017101e-06,
      "loss": 0.4631,
      "step": 52940
    },
    {
      "epoch": 1.6263017233434707,
      "grad_norm": 0.4026584029197693,
      "learning_rate": 1.6792341604103125e-06,
      "loss": 0.4859,
      "step": 52941
    },
    {
      "epoch": 1.6263324424784198,
      "grad_norm": 0.43336033821105957,
      "learning_rate": 1.6789661151526471e-06,
      "loss": 0.4958,
      "step": 52942
    },
    {
      "epoch": 1.626363161613369,
      "grad_norm": 0.4235857129096985,
      "learning_rate": 1.6786980893293337e-06,
      "loss": 0.3668,
      "step": 52943
    },
    {
      "epoch": 1.626393880748318,
      "grad_norm": 0.40856486558914185,
      "learning_rate": 1.6784300829410038e-06,
      "loss": 0.4551,
      "step": 52944
    },
    {
      "epoch": 1.6264245998832672,
      "grad_norm": 0.4144671857357025,
      "learning_rate": 1.6781620959882805e-06,
      "loss": 0.5535,
      "step": 52945
    },
    {
      "epoch": 1.6264553190182165,
      "grad_norm": 0.45322686433792114,
      "learning_rate": 1.6778941284717943e-06,
      "loss": 0.3691,
      "step": 52946
    },
    {
      "epoch": 1.6264860381531656,
      "grad_norm": 0.4349827468395233,
      "learning_rate": 1.6776261803921635e-06,
      "loss": 0.4932,
      "step": 52947
    },
    {
      "epoch": 1.6265167572881147,
      "grad_norm": 0.47740843892097473,
      "learning_rate": 1.6773582517500198e-06,
      "loss": 0.4602,
      "step": 52948
    },
    {
      "epoch": 1.626547476423064,
      "grad_norm": 0.4748704731464386,
      "learning_rate": 1.6770903425459861e-06,
      "loss": 0.4326,
      "step": 52949
    },
    {
      "epoch": 1.6265781955580132,
      "grad_norm": 0.4722171723842621,
      "learning_rate": 1.676822452780692e-06,
      "loss": 0.5269,
      "step": 52950
    },
    {
      "epoch": 1.6266089146929623,
      "grad_norm": 0.4348345994949341,
      "learning_rate": 1.676554582454757e-06,
      "loss": 0.4542,
      "step": 52951
    },
    {
      "epoch": 1.6266396338279114,
      "grad_norm": 0.4112837016582489,
      "learning_rate": 1.6762867315688114e-06,
      "loss": 0.5245,
      "step": 52952
    },
    {
      "epoch": 1.6266703529628606,
      "grad_norm": 0.4435560405254364,
      "learning_rate": 1.6760189001234784e-06,
      "loss": 0.5145,
      "step": 52953
    },
    {
      "epoch": 1.6267010720978097,
      "grad_norm": 0.3921767771244049,
      "learning_rate": 1.675751088119385e-06,
      "loss": 0.4367,
      "step": 52954
    },
    {
      "epoch": 1.6267317912327588,
      "grad_norm": 0.43328553438186646,
      "learning_rate": 1.6754832955571587e-06,
      "loss": 0.429,
      "step": 52955
    },
    {
      "epoch": 1.626762510367708,
      "grad_norm": 0.4525547921657562,
      "learning_rate": 1.67521552243742e-06,
      "loss": 0.5101,
      "step": 52956
    },
    {
      "epoch": 1.6267932295026573,
      "grad_norm": 0.4245924949645996,
      "learning_rate": 1.6749477687607973e-06,
      "loss": 0.4666,
      "step": 52957
    },
    {
      "epoch": 1.6268239486376064,
      "grad_norm": 0.4523371756076813,
      "learning_rate": 1.6746800345279156e-06,
      "loss": 0.4653,
      "step": 52958
    },
    {
      "epoch": 1.6268546677725555,
      "grad_norm": 0.4718312919139862,
      "learning_rate": 1.6744123197394025e-06,
      "loss": 0.4229,
      "step": 52959
    },
    {
      "epoch": 1.6268853869075048,
      "grad_norm": 0.4705621600151062,
      "learning_rate": 1.674144624395877e-06,
      "loss": 0.5421,
      "step": 52960
    },
    {
      "epoch": 1.626916106042454,
      "grad_norm": 0.4789319932460785,
      "learning_rate": 1.6738769484979721e-06,
      "loss": 0.4374,
      "step": 52961
    },
    {
      "epoch": 1.626946825177403,
      "grad_norm": 0.42570561170578003,
      "learning_rate": 1.6736092920463043e-06,
      "loss": 0.3748,
      "step": 52962
    },
    {
      "epoch": 1.6269775443123522,
      "grad_norm": 0.4130995571613312,
      "learning_rate": 1.673341655041507e-06,
      "loss": 0.4207,
      "step": 52963
    },
    {
      "epoch": 1.6270082634473013,
      "grad_norm": 0.45085155963897705,
      "learning_rate": 1.6730740374842014e-06,
      "loss": 0.4713,
      "step": 52964
    },
    {
      "epoch": 1.6270389825822504,
      "grad_norm": 0.40380382537841797,
      "learning_rate": 1.6728064393750144e-06,
      "loss": 0.4635,
      "step": 52965
    },
    {
      "epoch": 1.6270697017171996,
      "grad_norm": 0.4090798497200012,
      "learning_rate": 1.6725388607145642e-06,
      "loss": 0.4572,
      "step": 52966
    },
    {
      "epoch": 1.6271004208521487,
      "grad_norm": 0.4680226147174835,
      "learning_rate": 1.6722713015034864e-06,
      "loss": 0.4598,
      "step": 52967
    },
    {
      "epoch": 1.627131139987098,
      "grad_norm": 0.4442560076713562,
      "learning_rate": 1.672003761742398e-06,
      "loss": 0.4161,
      "step": 52968
    },
    {
      "epoch": 1.6271618591220471,
      "grad_norm": 0.4470174014568329,
      "learning_rate": 1.6717362414319282e-06,
      "loss": 0.4785,
      "step": 52969
    },
    {
      "epoch": 1.6271925782569963,
      "grad_norm": 0.42682945728302,
      "learning_rate": 1.6714687405726981e-06,
      "loss": 0.4399,
      "step": 52970
    },
    {
      "epoch": 1.6272232973919456,
      "grad_norm": 0.42244818806648254,
      "learning_rate": 1.6712012591653326e-06,
      "loss": 0.5005,
      "step": 52971
    },
    {
      "epoch": 1.6272540165268947,
      "grad_norm": 0.3978751003742218,
      "learning_rate": 1.6709337972104623e-06,
      "loss": 0.4958,
      "step": 52972
    },
    {
      "epoch": 1.6272847356618438,
      "grad_norm": 0.4166240096092224,
      "learning_rate": 1.6706663547087066e-06,
      "loss": 0.4341,
      "step": 52973
    },
    {
      "epoch": 1.627315454796793,
      "grad_norm": 0.6113497614860535,
      "learning_rate": 1.6703989316606929e-06,
      "loss": 0.379,
      "step": 52974
    },
    {
      "epoch": 1.627346173931742,
      "grad_norm": 0.4549625515937805,
      "learning_rate": 1.6701315280670415e-06,
      "loss": 0.5382,
      "step": 52975
    },
    {
      "epoch": 1.6273768930666912,
      "grad_norm": 0.42684000730514526,
      "learning_rate": 1.6698641439283802e-06,
      "loss": 0.4221,
      "step": 52976
    },
    {
      "epoch": 1.6274076122016403,
      "grad_norm": 0.3978148102760315,
      "learning_rate": 1.6695967792453326e-06,
      "loss": 0.5114,
      "step": 52977
    },
    {
      "epoch": 1.6274383313365894,
      "grad_norm": 0.42276331782341003,
      "learning_rate": 1.6693294340185262e-06,
      "loss": 0.5096,
      "step": 52978
    },
    {
      "epoch": 1.6274690504715386,
      "grad_norm": 0.40654829144477844,
      "learning_rate": 1.6690621082485803e-06,
      "loss": 0.4509,
      "step": 52979
    },
    {
      "epoch": 1.627499769606488,
      "grad_norm": 0.48337674140930176,
      "learning_rate": 1.668794801936121e-06,
      "loss": 0.4302,
      "step": 52980
    },
    {
      "epoch": 1.627530488741437,
      "grad_norm": 0.4108264446258545,
      "learning_rate": 1.6685275150817738e-06,
      "loss": 0.4854,
      "step": 52981
    },
    {
      "epoch": 1.6275612078763864,
      "grad_norm": 0.40288594365119934,
      "learning_rate": 1.6682602476861654e-06,
      "loss": 0.51,
      "step": 52982
    },
    {
      "epoch": 1.6275919270113355,
      "grad_norm": 0.4635065793991089,
      "learning_rate": 1.6679929997499133e-06,
      "loss": 0.4659,
      "step": 52983
    },
    {
      "epoch": 1.6276226461462846,
      "grad_norm": 0.481781929731369,
      "learning_rate": 1.6677257712736473e-06,
      "loss": 0.4839,
      "step": 52984
    },
    {
      "epoch": 1.6276533652812337,
      "grad_norm": 0.43855270743370056,
      "learning_rate": 1.6674585622579886e-06,
      "loss": 0.5215,
      "step": 52985
    },
    {
      "epoch": 1.6276840844161828,
      "grad_norm": 0.4304974377155304,
      "learning_rate": 1.667191372703565e-06,
      "loss": 0.4701,
      "step": 52986
    },
    {
      "epoch": 1.627714803551132,
      "grad_norm": 0.43996354937553406,
      "learning_rate": 1.6669242026109945e-06,
      "loss": 0.4657,
      "step": 52987
    },
    {
      "epoch": 1.627745522686081,
      "grad_norm": 0.4051591753959656,
      "learning_rate": 1.6666570519809055e-06,
      "loss": 0.4312,
      "step": 52988
    },
    {
      "epoch": 1.6277762418210302,
      "grad_norm": 0.4256700277328491,
      "learning_rate": 1.666389920813921e-06,
      "loss": 0.5584,
      "step": 52989
    },
    {
      "epoch": 1.6278069609559793,
      "grad_norm": 0.4883904755115509,
      "learning_rate": 1.666122809110664e-06,
      "loss": 0.4972,
      "step": 52990
    },
    {
      "epoch": 1.6278376800909287,
      "grad_norm": 0.42202502489089966,
      "learning_rate": 1.6658557168717626e-06,
      "loss": 0.5059,
      "step": 52991
    },
    {
      "epoch": 1.6278683992258778,
      "grad_norm": 0.4465673267841339,
      "learning_rate": 1.6655886440978354e-06,
      "loss": 0.5096,
      "step": 52992
    },
    {
      "epoch": 1.6278991183608271,
      "grad_norm": 0.42498189210891724,
      "learning_rate": 1.665321590789506e-06,
      "loss": 0.503,
      "step": 52993
    },
    {
      "epoch": 1.6279298374957762,
      "grad_norm": 0.44019123911857605,
      "learning_rate": 1.665054556947402e-06,
      "loss": 0.5214,
      "step": 52994
    },
    {
      "epoch": 1.6279605566307254,
      "grad_norm": 0.43667641282081604,
      "learning_rate": 1.664787542572146e-06,
      "loss": 0.419,
      "step": 52995
    },
    {
      "epoch": 1.6279912757656745,
      "grad_norm": 0.4516439139842987,
      "learning_rate": 1.66452054766436e-06,
      "loss": 0.5021,
      "step": 52996
    },
    {
      "epoch": 1.6280219949006236,
      "grad_norm": 0.4560588002204895,
      "learning_rate": 1.66425357222467e-06,
      "loss": 0.4798,
      "step": 52997
    },
    {
      "epoch": 1.6280527140355727,
      "grad_norm": 0.42510685324668884,
      "learning_rate": 1.6639866162536934e-06,
      "loss": 0.5192,
      "step": 52998
    },
    {
      "epoch": 1.6280834331705218,
      "grad_norm": 0.4404463469982147,
      "learning_rate": 1.6637196797520627e-06,
      "loss": 0.4245,
      "step": 52999
    },
    {
      "epoch": 1.628114152305471,
      "grad_norm": 0.435234934091568,
      "learning_rate": 1.6634527627203945e-06,
      "loss": 0.5061,
      "step": 53000
    },
    {
      "epoch": 1.62814487144042,
      "grad_norm": 0.43071097135543823,
      "learning_rate": 1.6631858651593168e-06,
      "loss": 0.4993,
      "step": 53001
    },
    {
      "epoch": 1.6281755905753694,
      "grad_norm": 0.42133209109306335,
      "learning_rate": 1.6629189870694484e-06,
      "loss": 0.5163,
      "step": 53002
    },
    {
      "epoch": 1.6282063097103185,
      "grad_norm": 0.4014412760734558,
      "learning_rate": 1.6626521284514152e-06,
      "loss": 0.4874,
      "step": 53003
    },
    {
      "epoch": 1.6282370288452677,
      "grad_norm": 0.4823538661003113,
      "learning_rate": 1.6623852893058402e-06,
      "loss": 0.488,
      "step": 53004
    },
    {
      "epoch": 1.628267747980217,
      "grad_norm": 0.45008257031440735,
      "learning_rate": 1.6621184696333493e-06,
      "loss": 0.4142,
      "step": 53005
    },
    {
      "epoch": 1.6282984671151661,
      "grad_norm": 0.41913503408432007,
      "learning_rate": 1.66185166943456e-06,
      "loss": 0.3895,
      "step": 53006
    },
    {
      "epoch": 1.6283291862501152,
      "grad_norm": 0.46957385540008545,
      "learning_rate": 1.6615848887100994e-06,
      "loss": 0.4718,
      "step": 53007
    },
    {
      "epoch": 1.6283599053850644,
      "grad_norm": 0.41341760754585266,
      "learning_rate": 1.6613181274605882e-06,
      "loss": 0.4539,
      "step": 53008
    },
    {
      "epoch": 1.6283906245200135,
      "grad_norm": 0.40703117847442627,
      "learning_rate": 1.6610513856866517e-06,
      "loss": 0.4457,
      "step": 53009
    },
    {
      "epoch": 1.6284213436549626,
      "grad_norm": 0.41456839442253113,
      "learning_rate": 1.6607846633889145e-06,
      "loss": 0.4524,
      "step": 53010
    },
    {
      "epoch": 1.6284520627899117,
      "grad_norm": 0.4485890567302704,
      "learning_rate": 1.6605179605679955e-06,
      "loss": 0.4808,
      "step": 53011
    },
    {
      "epoch": 1.6284827819248608,
      "grad_norm": 0.4214150905609131,
      "learning_rate": 1.6602512772245183e-06,
      "loss": 0.4355,
      "step": 53012
    },
    {
      "epoch": 1.6285135010598102,
      "grad_norm": 0.38376325368881226,
      "learning_rate": 1.6599846133591068e-06,
      "loss": 0.446,
      "step": 53013
    },
    {
      "epoch": 1.6285442201947593,
      "grad_norm": 0.4794243276119232,
      "learning_rate": 1.6597179689723863e-06,
      "loss": 0.4741,
      "step": 53014
    },
    {
      "epoch": 1.6285749393297084,
      "grad_norm": 0.4204147160053253,
      "learning_rate": 1.659451344064974e-06,
      "loss": 0.4703,
      "step": 53015
    },
    {
      "epoch": 1.6286056584646578,
      "grad_norm": 0.45442086458206177,
      "learning_rate": 1.6591847386374959e-06,
      "loss": 0.5482,
      "step": 53016
    },
    {
      "epoch": 1.6286363775996069,
      "grad_norm": 0.40842700004577637,
      "learning_rate": 1.658918152690575e-06,
      "loss": 0.4896,
      "step": 53017
    },
    {
      "epoch": 1.628667096734556,
      "grad_norm": 0.43811967968940735,
      "learning_rate": 1.6586515862248354e-06,
      "loss": 0.4873,
      "step": 53018
    },
    {
      "epoch": 1.6286978158695051,
      "grad_norm": 0.4665337800979614,
      "learning_rate": 1.658385039240895e-06,
      "loss": 0.4462,
      "step": 53019
    },
    {
      "epoch": 1.6287285350044542,
      "grad_norm": 0.4780789613723755,
      "learning_rate": 1.6581185117393784e-06,
      "loss": 0.411,
      "step": 53020
    },
    {
      "epoch": 1.6287592541394034,
      "grad_norm": 0.4597397744655609,
      "learning_rate": 1.657852003720909e-06,
      "loss": 0.4463,
      "step": 53021
    },
    {
      "epoch": 1.6287899732743525,
      "grad_norm": 0.4305810332298279,
      "learning_rate": 1.6575855151861108e-06,
      "loss": 0.5546,
      "step": 53022
    },
    {
      "epoch": 1.6288206924093016,
      "grad_norm": 0.4150780439376831,
      "learning_rate": 1.6573190461356026e-06,
      "loss": 0.4605,
      "step": 53023
    },
    {
      "epoch": 1.628851411544251,
      "grad_norm": 0.4262295365333557,
      "learning_rate": 1.6570525965700112e-06,
      "loss": 0.448,
      "step": 53024
    },
    {
      "epoch": 1.6288821306792,
      "grad_norm": 0.4224712550640106,
      "learning_rate": 1.6567861664899499e-06,
      "loss": 0.4412,
      "step": 53025
    },
    {
      "epoch": 1.6289128498141492,
      "grad_norm": 0.40797969698905945,
      "learning_rate": 1.656519755896051e-06,
      "loss": 0.4407,
      "step": 53026
    },
    {
      "epoch": 1.6289435689490985,
      "grad_norm": 0.4136163294315338,
      "learning_rate": 1.6562533647889345e-06,
      "loss": 0.492,
      "step": 53027
    },
    {
      "epoch": 1.6289742880840477,
      "grad_norm": 0.4243924915790558,
      "learning_rate": 1.6559869931692186e-06,
      "loss": 0.476,
      "step": 53028
    },
    {
      "epoch": 1.6290050072189968,
      "grad_norm": 0.43266382813453674,
      "learning_rate": 1.6557206410375281e-06,
      "loss": 0.5166,
      "step": 53029
    },
    {
      "epoch": 1.629035726353946,
      "grad_norm": 0.4659782946109772,
      "learning_rate": 1.6554543083944852e-06,
      "loss": 0.4234,
      "step": 53030
    },
    {
      "epoch": 1.629066445488895,
      "grad_norm": 0.4782039225101471,
      "learning_rate": 1.6551879952407134e-06,
      "loss": 0.4644,
      "step": 53031
    },
    {
      "epoch": 1.6290971646238441,
      "grad_norm": 0.4247833490371704,
      "learning_rate": 1.6549217015768304e-06,
      "loss": 0.4006,
      "step": 53032
    },
    {
      "epoch": 1.6291278837587932,
      "grad_norm": 0.4544842541217804,
      "learning_rate": 1.6546554274034632e-06,
      "loss": 0.4686,
      "step": 53033
    },
    {
      "epoch": 1.6291586028937424,
      "grad_norm": 0.381608247756958,
      "learning_rate": 1.6543891727212258e-06,
      "loss": 0.3959,
      "step": 53034
    },
    {
      "epoch": 1.6291893220286917,
      "grad_norm": 0.4000990688800812,
      "learning_rate": 1.6541229375307498e-06,
      "loss": 0.4707,
      "step": 53035
    },
    {
      "epoch": 1.6292200411636408,
      "grad_norm": 0.4334245026111603,
      "learning_rate": 1.6538567218326518e-06,
      "loss": 0.4325,
      "step": 53036
    },
    {
      "epoch": 1.62925076029859,
      "grad_norm": 0.4197136163711548,
      "learning_rate": 1.6535905256275552e-06,
      "loss": 0.4475,
      "step": 53037
    },
    {
      "epoch": 1.6292814794335393,
      "grad_norm": 0.43589362502098083,
      "learning_rate": 1.6533243489160788e-06,
      "loss": 0.4531,
      "step": 53038
    },
    {
      "epoch": 1.6293121985684884,
      "grad_norm": 0.4393775761127472,
      "learning_rate": 1.6530581916988464e-06,
      "loss": 0.498,
      "step": 53039
    },
    {
      "epoch": 1.6293429177034375,
      "grad_norm": 0.41976064443588257,
      "learning_rate": 1.6527920539764796e-06,
      "loss": 0.4323,
      "step": 53040
    },
    {
      "epoch": 1.6293736368383867,
      "grad_norm": 0.4107179641723633,
      "learning_rate": 1.6525259357496026e-06,
      "loss": 0.4554,
      "step": 53041
    },
    {
      "epoch": 1.6294043559733358,
      "grad_norm": 0.4356469213962555,
      "learning_rate": 1.6522598370188314e-06,
      "loss": 0.4724,
      "step": 53042
    },
    {
      "epoch": 1.629435075108285,
      "grad_norm": 0.4235198199748993,
      "learning_rate": 1.6519937577847912e-06,
      "loss": 0.447,
      "step": 53043
    },
    {
      "epoch": 1.629465794243234,
      "grad_norm": 0.48765066266059875,
      "learning_rate": 1.6517276980481012e-06,
      "loss": 0.462,
      "step": 53044
    },
    {
      "epoch": 1.6294965133781831,
      "grad_norm": 0.4277251958847046,
      "learning_rate": 1.6514616578093856e-06,
      "loss": 0.4528,
      "step": 53045
    },
    {
      "epoch": 1.6295272325131325,
      "grad_norm": 0.4947965741157532,
      "learning_rate": 1.651195637069266e-06,
      "loss": 0.4916,
      "step": 53046
    },
    {
      "epoch": 1.6295579516480816,
      "grad_norm": 0.6309751868247986,
      "learning_rate": 1.6509296358283599e-06,
      "loss": 0.4275,
      "step": 53047
    },
    {
      "epoch": 1.6295886707830307,
      "grad_norm": 0.3829715847969055,
      "learning_rate": 1.65066365408729e-06,
      "loss": 0.4186,
      "step": 53048
    },
    {
      "epoch": 1.62961938991798,
      "grad_norm": 0.4207100570201874,
      "learning_rate": 1.650397691846679e-06,
      "loss": 0.3954,
      "step": 53049
    },
    {
      "epoch": 1.6296501090529292,
      "grad_norm": 0.42705661058425903,
      "learning_rate": 1.65013174910715e-06,
      "loss": 0.4544,
      "step": 53050
    },
    {
      "epoch": 1.6296808281878783,
      "grad_norm": 0.4672991931438446,
      "learning_rate": 1.6498658258693178e-06,
      "loss": 0.4746,
      "step": 53051
    },
    {
      "epoch": 1.6297115473228274,
      "grad_norm": 0.5737653970718384,
      "learning_rate": 1.6495999221338087e-06,
      "loss": 0.4981,
      "step": 53052
    },
    {
      "epoch": 1.6297422664577765,
      "grad_norm": 0.39987990260124207,
      "learning_rate": 1.6493340379012413e-06,
      "loss": 0.4055,
      "step": 53053
    },
    {
      "epoch": 1.6297729855927257,
      "grad_norm": 0.5308340191841125,
      "learning_rate": 1.6490681731722402e-06,
      "loss": 0.4514,
      "step": 53054
    },
    {
      "epoch": 1.6298037047276748,
      "grad_norm": 0.38470780849456787,
      "learning_rate": 1.6488023279474208e-06,
      "loss": 0.4386,
      "step": 53055
    },
    {
      "epoch": 1.629834423862624,
      "grad_norm": 0.4209868907928467,
      "learning_rate": 1.648536502227407e-06,
      "loss": 0.4525,
      "step": 53056
    },
    {
      "epoch": 1.6298651429975732,
      "grad_norm": 0.44817548990249634,
      "learning_rate": 1.6482706960128192e-06,
      "loss": 0.4528,
      "step": 53057
    },
    {
      "epoch": 1.6298958621325224,
      "grad_norm": 0.4087337851524353,
      "learning_rate": 1.6480049093042816e-06,
      "loss": 0.4889,
      "step": 53058
    },
    {
      "epoch": 1.6299265812674715,
      "grad_norm": 0.47935476899147034,
      "learning_rate": 1.647739142102408e-06,
      "loss": 0.424,
      "step": 53059
    },
    {
      "epoch": 1.6299573004024208,
      "grad_norm": 0.41086676716804504,
      "learning_rate": 1.647473394407827e-06,
      "loss": 0.411,
      "step": 53060
    },
    {
      "epoch": 1.62998801953737,
      "grad_norm": 0.4527305066585541,
      "learning_rate": 1.647207666221149e-06,
      "loss": 0.4995,
      "step": 53061
    },
    {
      "epoch": 1.630018738672319,
      "grad_norm": 0.4146023094654083,
      "learning_rate": 1.6469419575430069e-06,
      "loss": 0.4005,
      "step": 53062
    },
    {
      "epoch": 1.6300494578072682,
      "grad_norm": 0.4155066907405853,
      "learning_rate": 1.6466762683740122e-06,
      "loss": 0.4716,
      "step": 53063
    },
    {
      "epoch": 1.6300801769422173,
      "grad_norm": 0.4138868749141693,
      "learning_rate": 1.6464105987147882e-06,
      "loss": 0.4367,
      "step": 53064
    },
    {
      "epoch": 1.6301108960771664,
      "grad_norm": 0.41317394375801086,
      "learning_rate": 1.6461449485659586e-06,
      "loss": 0.4629,
      "step": 53065
    },
    {
      "epoch": 1.6301416152121155,
      "grad_norm": 0.4852251708507538,
      "learning_rate": 1.6458793179281362e-06,
      "loss": 0.4738,
      "step": 53066
    },
    {
      "epoch": 1.6301723343470647,
      "grad_norm": 0.48216521739959717,
      "learning_rate": 1.6456137068019506e-06,
      "loss": 0.5172,
      "step": 53067
    },
    {
      "epoch": 1.630203053482014,
      "grad_norm": 0.45225486159324646,
      "learning_rate": 1.6453481151880147e-06,
      "loss": 0.4446,
      "step": 53068
    },
    {
      "epoch": 1.6302337726169631,
      "grad_norm": 0.4388361871242523,
      "learning_rate": 1.6450825430869543e-06,
      "loss": 0.4686,
      "step": 53069
    },
    {
      "epoch": 1.6302644917519122,
      "grad_norm": 0.4831927418708801,
      "learning_rate": 1.6448169904993828e-06,
      "loss": 0.4791,
      "step": 53070
    },
    {
      "epoch": 1.6302952108868616,
      "grad_norm": 0.4568057060241699,
      "learning_rate": 1.6445514574259302e-06,
      "loss": 0.4418,
      "step": 53071
    },
    {
      "epoch": 1.6303259300218107,
      "grad_norm": 0.4641684889793396,
      "learning_rate": 1.6442859438672076e-06,
      "loss": 0.393,
      "step": 53072
    },
    {
      "epoch": 1.6303566491567598,
      "grad_norm": 0.41814756393432617,
      "learning_rate": 1.644020449823842e-06,
      "loss": 0.4465,
      "step": 53073
    },
    {
      "epoch": 1.630387368291709,
      "grad_norm": 0.4875646233558655,
      "learning_rate": 1.6437549752964476e-06,
      "loss": 0.4846,
      "step": 53074
    },
    {
      "epoch": 1.630418087426658,
      "grad_norm": 0.408425509929657,
      "learning_rate": 1.643489520285646e-06,
      "loss": 0.4949,
      "step": 53075
    },
    {
      "epoch": 1.6304488065616072,
      "grad_norm": 0.4365147054195404,
      "learning_rate": 1.64322408479206e-06,
      "loss": 0.4402,
      "step": 53076
    },
    {
      "epoch": 1.6304795256965563,
      "grad_norm": 0.47285574674606323,
      "learning_rate": 1.6429586688163091e-06,
      "loss": 0.4717,
      "step": 53077
    },
    {
      "epoch": 1.6305102448315054,
      "grad_norm": 0.483249694108963,
      "learning_rate": 1.6426932723590095e-06,
      "loss": 0.4437,
      "step": 53078
    },
    {
      "epoch": 1.6305409639664548,
      "grad_norm": 0.40118616819381714,
      "learning_rate": 1.642427895420784e-06,
      "loss": 0.4923,
      "step": 53079
    },
    {
      "epoch": 1.6305716831014039,
      "grad_norm": 0.39779219031333923,
      "learning_rate": 1.642162538002251e-06,
      "loss": 0.4572,
      "step": 53080
    },
    {
      "epoch": 1.630602402236353,
      "grad_norm": 0.406749427318573,
      "learning_rate": 1.6418972001040312e-06,
      "loss": 0.4661,
      "step": 53081
    },
    {
      "epoch": 1.6306331213713023,
      "grad_norm": 0.41860947012901306,
      "learning_rate": 1.6416318817267473e-06,
      "loss": 0.4459,
      "step": 53082
    },
    {
      "epoch": 1.6306638405062515,
      "grad_norm": 0.44157201051712036,
      "learning_rate": 1.6413665828710124e-06,
      "loss": 0.515,
      "step": 53083
    },
    {
      "epoch": 1.6306945596412006,
      "grad_norm": 0.41163647174835205,
      "learning_rate": 1.6411013035374513e-06,
      "loss": 0.43,
      "step": 53084
    },
    {
      "epoch": 1.6307252787761497,
      "grad_norm": 0.4244069457054138,
      "learning_rate": 1.6408360437266802e-06,
      "loss": 0.4675,
      "step": 53085
    },
    {
      "epoch": 1.6307559979110988,
      "grad_norm": 0.44149500131607056,
      "learning_rate": 1.640570803439324e-06,
      "loss": 0.4821,
      "step": 53086
    },
    {
      "epoch": 1.630786717046048,
      "grad_norm": 0.46718573570251465,
      "learning_rate": 1.640305582675995e-06,
      "loss": 0.4532,
      "step": 53087
    },
    {
      "epoch": 1.630817436180997,
      "grad_norm": 0.4473598897457123,
      "learning_rate": 1.6400403814373168e-06,
      "loss": 0.4686,
      "step": 53088
    },
    {
      "epoch": 1.6308481553159462,
      "grad_norm": 0.44400766491889954,
      "learning_rate": 1.6397751997239075e-06,
      "loss": 0.455,
      "step": 53089
    },
    {
      "epoch": 1.6308788744508953,
      "grad_norm": 0.4118711054325104,
      "learning_rate": 1.6395100375363904e-06,
      "loss": 0.4711,
      "step": 53090
    },
    {
      "epoch": 1.6309095935858446,
      "grad_norm": 0.41226840019226074,
      "learning_rate": 1.6392448948753792e-06,
      "loss": 0.4907,
      "step": 53091
    },
    {
      "epoch": 1.6309403127207938,
      "grad_norm": 0.4317214787006378,
      "learning_rate": 1.6389797717414946e-06,
      "loss": 0.4541,
      "step": 53092
    },
    {
      "epoch": 1.630971031855743,
      "grad_norm": 0.4190109968185425,
      "learning_rate": 1.6387146681353573e-06,
      "loss": 0.3651,
      "step": 53093
    },
    {
      "epoch": 1.6310017509906922,
      "grad_norm": 0.4181903600692749,
      "learning_rate": 1.6384495840575876e-06,
      "loss": 0.4316,
      "step": 53094
    },
    {
      "epoch": 1.6310324701256413,
      "grad_norm": 0.4396352469921112,
      "learning_rate": 1.638184519508801e-06,
      "loss": 0.4162,
      "step": 53095
    },
    {
      "epoch": 1.6310631892605905,
      "grad_norm": 0.4526941478252411,
      "learning_rate": 1.637919474489621e-06,
      "loss": 0.4759,
      "step": 53096
    },
    {
      "epoch": 1.6310939083955396,
      "grad_norm": 0.47768425941467285,
      "learning_rate": 1.6376544490006584e-06,
      "loss": 0.4738,
      "step": 53097
    },
    {
      "epoch": 1.6311246275304887,
      "grad_norm": 0.4488387405872345,
      "learning_rate": 1.637389443042543e-06,
      "loss": 0.5445,
      "step": 53098
    },
    {
      "epoch": 1.6311553466654378,
      "grad_norm": 0.44773197174072266,
      "learning_rate": 1.637124456615886e-06,
      "loss": 0.4686,
      "step": 53099
    },
    {
      "epoch": 1.631186065800387,
      "grad_norm": 0.4143720269203186,
      "learning_rate": 1.6368594897213096e-06,
      "loss": 0.4484,
      "step": 53100
    },
    {
      "epoch": 1.631216784935336,
      "grad_norm": 0.4265277683734894,
      "learning_rate": 1.6365945423594342e-06,
      "loss": 0.4596,
      "step": 53101
    },
    {
      "epoch": 1.6312475040702854,
      "grad_norm": 0.4802737534046173,
      "learning_rate": 1.6363296145308715e-06,
      "loss": 0.4782,
      "step": 53102
    },
    {
      "epoch": 1.6312782232052345,
      "grad_norm": 0.3927367031574249,
      "learning_rate": 1.63606470623625e-06,
      "loss": 0.4626,
      "step": 53103
    },
    {
      "epoch": 1.6313089423401839,
      "grad_norm": 0.6067307591438293,
      "learning_rate": 1.6357998174761803e-06,
      "loss": 0.5069,
      "step": 53104
    },
    {
      "epoch": 1.631339661475133,
      "grad_norm": 0.410532683134079,
      "learning_rate": 1.6355349482512871e-06,
      "loss": 0.4294,
      "step": 53105
    },
    {
      "epoch": 1.631370380610082,
      "grad_norm": 0.41576188802719116,
      "learning_rate": 1.6352700985621838e-06,
      "loss": 0.4453,
      "step": 53106
    },
    {
      "epoch": 1.6314010997450312,
      "grad_norm": 0.42888715863227844,
      "learning_rate": 1.635005268409492e-06,
      "loss": 0.4321,
      "step": 53107
    },
    {
      "epoch": 1.6314318188799803,
      "grad_norm": 0.46041950583457947,
      "learning_rate": 1.6347404577938286e-06,
      "loss": 0.5082,
      "step": 53108
    },
    {
      "epoch": 1.6314625380149295,
      "grad_norm": 0.4119328558444977,
      "learning_rate": 1.6344756667158168e-06,
      "loss": 0.5016,
      "step": 53109
    },
    {
      "epoch": 1.6314932571498786,
      "grad_norm": 0.4338102638721466,
      "learning_rate": 1.6342108951760683e-06,
      "loss": 0.402,
      "step": 53110
    },
    {
      "epoch": 1.6315239762848277,
      "grad_norm": 0.43240734934806824,
      "learning_rate": 1.6339461431752036e-06,
      "loss": 0.5127,
      "step": 53111
    },
    {
      "epoch": 1.6315546954197768,
      "grad_norm": 0.4775315523147583,
      "learning_rate": 1.6336814107138432e-06,
      "loss": 0.4873,
      "step": 53112
    },
    {
      "epoch": 1.6315854145547262,
      "grad_norm": 0.46577054262161255,
      "learning_rate": 1.6334166977926058e-06,
      "loss": 0.5312,
      "step": 53113
    },
    {
      "epoch": 1.6316161336896753,
      "grad_norm": 0.4467353820800781,
      "learning_rate": 1.6331520044121064e-06,
      "loss": 0.4895,
      "step": 53114
    },
    {
      "epoch": 1.6316468528246244,
      "grad_norm": 0.40026170015335083,
      "learning_rate": 1.6328873305729643e-06,
      "loss": 0.4109,
      "step": 53115
    },
    {
      "epoch": 1.6316775719595737,
      "grad_norm": 0.4234243929386139,
      "learning_rate": 1.6326226762757979e-06,
      "loss": 0.4536,
      "step": 53116
    },
    {
      "epoch": 1.6317082910945229,
      "grad_norm": 0.46932417154312134,
      "learning_rate": 1.632358041521226e-06,
      "loss": 0.4356,
      "step": 53117
    },
    {
      "epoch": 1.631739010229472,
      "grad_norm": 0.46595636010169983,
      "learning_rate": 1.6320934263098687e-06,
      "loss": 0.4939,
      "step": 53118
    },
    {
      "epoch": 1.631769729364421,
      "grad_norm": 0.4191681742668152,
      "learning_rate": 1.631828830642338e-06,
      "loss": 0.4538,
      "step": 53119
    },
    {
      "epoch": 1.6318004484993702,
      "grad_norm": 0.392009973526001,
      "learning_rate": 1.6315642545192567e-06,
      "loss": 0.4206,
      "step": 53120
    },
    {
      "epoch": 1.6318311676343193,
      "grad_norm": 0.43482834100723267,
      "learning_rate": 1.631299697941242e-06,
      "loss": 0.4305,
      "step": 53121
    },
    {
      "epoch": 1.6318618867692685,
      "grad_norm": 0.4257642924785614,
      "learning_rate": 1.6310351609089125e-06,
      "loss": 0.4444,
      "step": 53122
    },
    {
      "epoch": 1.6318926059042176,
      "grad_norm": 0.42308083176612854,
      "learning_rate": 1.6307706434228831e-06,
      "loss": 0.4797,
      "step": 53123
    },
    {
      "epoch": 1.631923325039167,
      "grad_norm": 0.4477449357509613,
      "learning_rate": 1.6305061454837734e-06,
      "loss": 0.503,
      "step": 53124
    },
    {
      "epoch": 1.631954044174116,
      "grad_norm": 0.4548274874687195,
      "learning_rate": 1.6302416670922016e-06,
      "loss": 0.4819,
      "step": 53125
    },
    {
      "epoch": 1.6319847633090652,
      "grad_norm": 0.39528194069862366,
      "learning_rate": 1.6299772082487863e-06,
      "loss": 0.5106,
      "step": 53126
    },
    {
      "epoch": 1.6320154824440145,
      "grad_norm": 0.48981791734695435,
      "learning_rate": 1.6297127689541426e-06,
      "loss": 0.4887,
      "step": 53127
    },
    {
      "epoch": 1.6320462015789636,
      "grad_norm": 0.4168735444545746,
      "learning_rate": 1.6294483492088887e-06,
      "loss": 0.5645,
      "step": 53128
    },
    {
      "epoch": 1.6320769207139127,
      "grad_norm": 0.42941510677337646,
      "learning_rate": 1.6291839490136418e-06,
      "loss": 0.42,
      "step": 53129
    },
    {
      "epoch": 1.6321076398488619,
      "grad_norm": 0.39259016513824463,
      "learning_rate": 1.628919568369024e-06,
      "loss": 0.4712,
      "step": 53130
    },
    {
      "epoch": 1.632138358983811,
      "grad_norm": 0.40353626012802124,
      "learning_rate": 1.6286552072756468e-06,
      "loss": 0.5116,
      "step": 53131
    },
    {
      "epoch": 1.63216907811876,
      "grad_norm": 0.41579318046569824,
      "learning_rate": 1.6283908657341319e-06,
      "loss": 0.432,
      "step": 53132
    },
    {
      "epoch": 1.6321997972537092,
      "grad_norm": 0.41779541969299316,
      "learning_rate": 1.62812654374509e-06,
      "loss": 0.4145,
      "step": 53133
    },
    {
      "epoch": 1.6322305163886583,
      "grad_norm": 0.4105624854564667,
      "learning_rate": 1.6278622413091482e-06,
      "loss": 0.4057,
      "step": 53134
    },
    {
      "epoch": 1.6322612355236077,
      "grad_norm": 0.40290528535842896,
      "learning_rate": 1.6275979584269164e-06,
      "loss": 0.4426,
      "step": 53135
    },
    {
      "epoch": 1.6322919546585568,
      "grad_norm": 0.44396257400512695,
      "learning_rate": 1.6273336950990137e-06,
      "loss": 0.5001,
      "step": 53136
    },
    {
      "epoch": 1.632322673793506,
      "grad_norm": 0.43060368299484253,
      "learning_rate": 1.627069451326061e-06,
      "loss": 0.3726,
      "step": 53137
    },
    {
      "epoch": 1.6323533929284553,
      "grad_norm": 0.455903023481369,
      "learning_rate": 1.6268052271086676e-06,
      "loss": 0.4538,
      "step": 53138
    },
    {
      "epoch": 1.6323841120634044,
      "grad_norm": 0.4373709261417389,
      "learning_rate": 1.6265410224474597e-06,
      "loss": 0.5287,
      "step": 53139
    },
    {
      "epoch": 1.6324148311983535,
      "grad_norm": 0.5376062393188477,
      "learning_rate": 1.6262768373430483e-06,
      "loss": 0.444,
      "step": 53140
    },
    {
      "epoch": 1.6324455503333026,
      "grad_norm": 0.44332894682884216,
      "learning_rate": 1.6260126717960546e-06,
      "loss": 0.4864,
      "step": 53141
    },
    {
      "epoch": 1.6324762694682518,
      "grad_norm": 0.4474014341831207,
      "learning_rate": 1.6257485258070904e-06,
      "loss": 0.482,
      "step": 53142
    },
    {
      "epoch": 1.6325069886032009,
      "grad_norm": 0.4177546203136444,
      "learning_rate": 1.6254843993767755e-06,
      "loss": 0.4376,
      "step": 53143
    },
    {
      "epoch": 1.63253770773815,
      "grad_norm": 0.41284772753715515,
      "learning_rate": 1.625220292505726e-06,
      "loss": 0.4393,
      "step": 53144
    },
    {
      "epoch": 1.632568426873099,
      "grad_norm": 0.4060237407684326,
      "learning_rate": 1.6249562051945622e-06,
      "loss": 0.5461,
      "step": 53145
    },
    {
      "epoch": 1.6325991460080485,
      "grad_norm": 0.5134410262107849,
      "learning_rate": 1.6246921374438961e-06,
      "loss": 0.4526,
      "step": 53146
    },
    {
      "epoch": 1.6326298651429976,
      "grad_norm": 0.4370191693305969,
      "learning_rate": 1.6244280892543462e-06,
      "loss": 0.447,
      "step": 53147
    },
    {
      "epoch": 1.6326605842779467,
      "grad_norm": 0.3924954831600189,
      "learning_rate": 1.6241640606265286e-06,
      "loss": 0.5305,
      "step": 53148
    },
    {
      "epoch": 1.632691303412896,
      "grad_norm": 0.4306543171405792,
      "learning_rate": 1.6239000515610648e-06,
      "loss": 0.4256,
      "step": 53149
    },
    {
      "epoch": 1.6327220225478452,
      "grad_norm": 0.4373922348022461,
      "learning_rate": 1.6236360620585634e-06,
      "loss": 0.3912,
      "step": 53150
    },
    {
      "epoch": 1.6327527416827943,
      "grad_norm": 0.418321430683136,
      "learning_rate": 1.6233720921196461e-06,
      "loss": 0.5161,
      "step": 53151
    },
    {
      "epoch": 1.6327834608177434,
      "grad_norm": 0.40801554918289185,
      "learning_rate": 1.623108141744928e-06,
      "loss": 0.4176,
      "step": 53152
    },
    {
      "epoch": 1.6328141799526925,
      "grad_norm": 0.4313528835773468,
      "learning_rate": 1.6228442109350285e-06,
      "loss": 0.5712,
      "step": 53153
    },
    {
      "epoch": 1.6328448990876416,
      "grad_norm": 0.4350413680076599,
      "learning_rate": 1.6225802996905582e-06,
      "loss": 0.475,
      "step": 53154
    },
    {
      "epoch": 1.6328756182225908,
      "grad_norm": 0.46484923362731934,
      "learning_rate": 1.6223164080121368e-06,
      "loss": 0.4037,
      "step": 53155
    },
    {
      "epoch": 1.6329063373575399,
      "grad_norm": 0.42587077617645264,
      "learning_rate": 1.6220525359003814e-06,
      "loss": 0.4557,
      "step": 53156
    },
    {
      "epoch": 1.6329370564924892,
      "grad_norm": 0.41311272978782654,
      "learning_rate": 1.6217886833559072e-06,
      "loss": 0.3849,
      "step": 53157
    },
    {
      "epoch": 1.6329677756274383,
      "grad_norm": 0.4208218455314636,
      "learning_rate": 1.6215248503793325e-06,
      "loss": 0.4036,
      "step": 53158
    },
    {
      "epoch": 1.6329984947623875,
      "grad_norm": 0.43624037504196167,
      "learning_rate": 1.621261036971269e-06,
      "loss": 0.5065,
      "step": 53159
    },
    {
      "epoch": 1.6330292138973368,
      "grad_norm": 0.4399786591529846,
      "learning_rate": 1.6209972431323363e-06,
      "loss": 0.4729,
      "step": 53160
    },
    {
      "epoch": 1.633059933032286,
      "grad_norm": 0.41820111870765686,
      "learning_rate": 1.6207334688631493e-06,
      "loss": 0.367,
      "step": 53161
    },
    {
      "epoch": 1.633090652167235,
      "grad_norm": 0.5092399716377258,
      "learning_rate": 1.6204697141643278e-06,
      "loss": 0.5027,
      "step": 53162
    },
    {
      "epoch": 1.6331213713021842,
      "grad_norm": 0.4871131181716919,
      "learning_rate": 1.620205979036481e-06,
      "loss": 0.4778,
      "step": 53163
    },
    {
      "epoch": 1.6331520904371333,
      "grad_norm": 0.4890683889389038,
      "learning_rate": 1.6199422634802309e-06,
      "loss": 0.4805,
      "step": 53164
    },
    {
      "epoch": 1.6331828095720824,
      "grad_norm": 0.38803741335868835,
      "learning_rate": 1.6196785674961868e-06,
      "loss": 0.4765,
      "step": 53165
    },
    {
      "epoch": 1.6332135287070315,
      "grad_norm": 0.4291905462741852,
      "learning_rate": 1.6194148910849727e-06,
      "loss": 0.4509,
      "step": 53166
    },
    {
      "epoch": 1.6332442478419806,
      "grad_norm": 0.43586626648902893,
      "learning_rate": 1.6191512342471983e-06,
      "loss": 0.4924,
      "step": 53167
    },
    {
      "epoch": 1.63327496697693,
      "grad_norm": 0.43417683243751526,
      "learning_rate": 1.6188875969834838e-06,
      "loss": 0.5358,
      "step": 53168
    },
    {
      "epoch": 1.633305686111879,
      "grad_norm": 0.4542887508869171,
      "learning_rate": 1.618623979294438e-06,
      "loss": 0.5024,
      "step": 53169
    },
    {
      "epoch": 1.6333364052468282,
      "grad_norm": 0.6971802711486816,
      "learning_rate": 1.6183603811806859e-06,
      "loss": 0.4784,
      "step": 53170
    },
    {
      "epoch": 1.6333671243817776,
      "grad_norm": 0.41305088996887207,
      "learning_rate": 1.6180968026428367e-06,
      "loss": 0.4058,
      "step": 53171
    },
    {
      "epoch": 1.6333978435167267,
      "grad_norm": 0.44148480892181396,
      "learning_rate": 1.617833243681507e-06,
      "loss": 0.4745,
      "step": 53172
    },
    {
      "epoch": 1.6334285626516758,
      "grad_norm": 0.41597074270248413,
      "learning_rate": 1.617569704297316e-06,
      "loss": 0.4871,
      "step": 53173
    },
    {
      "epoch": 1.633459281786625,
      "grad_norm": 0.4537203311920166,
      "learning_rate": 1.617306184490871e-06,
      "loss": 0.4796,
      "step": 53174
    },
    {
      "epoch": 1.633490000921574,
      "grad_norm": 0.41901010274887085,
      "learning_rate": 1.6170426842627985e-06,
      "loss": 0.4816,
      "step": 53175
    },
    {
      "epoch": 1.6335207200565232,
      "grad_norm": 0.43213361501693726,
      "learning_rate": 1.6167792036137054e-06,
      "loss": 0.4785,
      "step": 53176
    },
    {
      "epoch": 1.6335514391914723,
      "grad_norm": 0.45559367537498474,
      "learning_rate": 1.6165157425442124e-06,
      "loss": 0.4195,
      "step": 53177
    },
    {
      "epoch": 1.6335821583264214,
      "grad_norm": 0.4153226315975189,
      "learning_rate": 1.6162523010549303e-06,
      "loss": 0.5084,
      "step": 53178
    },
    {
      "epoch": 1.6336128774613707,
      "grad_norm": 0.4536585509777069,
      "learning_rate": 1.6159888791464762e-06,
      "loss": 0.5292,
      "step": 53179
    },
    {
      "epoch": 1.6336435965963199,
      "grad_norm": 0.4150330424308777,
      "learning_rate": 1.6157254768194653e-06,
      "loss": 0.4663,
      "step": 53180
    },
    {
      "epoch": 1.633674315731269,
      "grad_norm": 0.4637587368488312,
      "learning_rate": 1.6154620940745158e-06,
      "loss": 0.4573,
      "step": 53181
    },
    {
      "epoch": 1.6337050348662183,
      "grad_norm": 0.5251564979553223,
      "learning_rate": 1.6151987309122374e-06,
      "loss": 0.3465,
      "step": 53182
    },
    {
      "epoch": 1.6337357540011674,
      "grad_norm": 0.5655230283737183,
      "learning_rate": 1.6149353873332485e-06,
      "loss": 0.3911,
      "step": 53183
    },
    {
      "epoch": 1.6337664731361166,
      "grad_norm": 0.39981910586357117,
      "learning_rate": 1.614672063338163e-06,
      "loss": 0.4468,
      "step": 53184
    },
    {
      "epoch": 1.6337971922710657,
      "grad_norm": 0.39704978466033936,
      "learning_rate": 1.6144087589275993e-06,
      "loss": 0.4556,
      "step": 53185
    },
    {
      "epoch": 1.6338279114060148,
      "grad_norm": 0.41456523537635803,
      "learning_rate": 1.6141454741021678e-06,
      "loss": 0.4781,
      "step": 53186
    },
    {
      "epoch": 1.633858630540964,
      "grad_norm": 0.48513758182525635,
      "learning_rate": 1.6138822088624838e-06,
      "loss": 0.4358,
      "step": 53187
    },
    {
      "epoch": 1.633889349675913,
      "grad_norm": 0.4327417314052582,
      "learning_rate": 1.6136189632091648e-06,
      "loss": 0.4971,
      "step": 53188
    },
    {
      "epoch": 1.6339200688108622,
      "grad_norm": 0.45132067799568176,
      "learning_rate": 1.6133557371428266e-06,
      "loss": 0.4425,
      "step": 53189
    },
    {
      "epoch": 1.6339507879458115,
      "grad_norm": 0.4124238193035126,
      "learning_rate": 1.6130925306640788e-06,
      "loss": 0.504,
      "step": 53190
    },
    {
      "epoch": 1.6339815070807606,
      "grad_norm": 1.3787713050842285,
      "learning_rate": 1.6128293437735398e-06,
      "loss": 0.418,
      "step": 53191
    },
    {
      "epoch": 1.6340122262157097,
      "grad_norm": 0.42550233006477356,
      "learning_rate": 1.6125661764718238e-06,
      "loss": 0.4655,
      "step": 53192
    },
    {
      "epoch": 1.634042945350659,
      "grad_norm": 0.40060293674468994,
      "learning_rate": 1.6123030287595442e-06,
      "loss": 0.4182,
      "step": 53193
    },
    {
      "epoch": 1.6340736644856082,
      "grad_norm": 0.4096146523952484,
      "learning_rate": 1.61203990063732e-06,
      "loss": 0.4332,
      "step": 53194
    },
    {
      "epoch": 1.6341043836205573,
      "grad_norm": 0.45174428820610046,
      "learning_rate": 1.6117767921057591e-06,
      "loss": 0.4062,
      "step": 53195
    },
    {
      "epoch": 1.6341351027555064,
      "grad_norm": 0.42152783274650574,
      "learning_rate": 1.6115137031654804e-06,
      "loss": 0.4749,
      "step": 53196
    },
    {
      "epoch": 1.6341658218904556,
      "grad_norm": 0.4574491083621979,
      "learning_rate": 1.6112506338170964e-06,
      "loss": 0.4394,
      "step": 53197
    },
    {
      "epoch": 1.6341965410254047,
      "grad_norm": 0.4213099479675293,
      "learning_rate": 1.6109875840612254e-06,
      "loss": 0.4679,
      "step": 53198
    },
    {
      "epoch": 1.6342272601603538,
      "grad_norm": 0.41544046998023987,
      "learning_rate": 1.6107245538984761e-06,
      "loss": 0.4142,
      "step": 53199
    },
    {
      "epoch": 1.634257979295303,
      "grad_norm": 0.8308473825454712,
      "learning_rate": 1.6104615433294679e-06,
      "loss": 0.4494,
      "step": 53200
    },
    {
      "epoch": 1.634288698430252,
      "grad_norm": 0.42916205525398254,
      "learning_rate": 1.610198552354808e-06,
      "loss": 0.4978,
      "step": 53201
    },
    {
      "epoch": 1.6343194175652014,
      "grad_norm": 0.4426361322402954,
      "learning_rate": 1.6099355809751206e-06,
      "loss": 0.5259,
      "step": 53202
    },
    {
      "epoch": 1.6343501367001505,
      "grad_norm": 0.5164425373077393,
      "learning_rate": 1.6096726291910114e-06,
      "loss": 0.4495,
      "step": 53203
    },
    {
      "epoch": 1.6343808558350998,
      "grad_norm": 0.4183069169521332,
      "learning_rate": 1.6094096970031003e-06,
      "loss": 0.4972,
      "step": 53204
    },
    {
      "epoch": 1.634411574970049,
      "grad_norm": 0.43594691157341003,
      "learning_rate": 1.6091467844119969e-06,
      "loss": 0.5168,
      "step": 53205
    },
    {
      "epoch": 1.634442294104998,
      "grad_norm": 0.45462465286254883,
      "learning_rate": 1.6088838914183168e-06,
      "loss": 0.4407,
      "step": 53206
    },
    {
      "epoch": 1.6344730132399472,
      "grad_norm": 0.42384371161460876,
      "learning_rate": 1.6086210180226746e-06,
      "loss": 0.4146,
      "step": 53207
    },
    {
      "epoch": 1.6345037323748963,
      "grad_norm": 0.4031842052936554,
      "learning_rate": 1.6083581642256862e-06,
      "loss": 0.458,
      "step": 53208
    },
    {
      "epoch": 1.6345344515098454,
      "grad_norm": 0.4525027573108673,
      "learning_rate": 1.608095330027961e-06,
      "loss": 0.5095,
      "step": 53209
    },
    {
      "epoch": 1.6345651706447946,
      "grad_norm": 0.482637494802475,
      "learning_rate": 1.6078325154301134e-06,
      "loss": 0.4599,
      "step": 53210
    },
    {
      "epoch": 1.6345958897797437,
      "grad_norm": 0.42189162969589233,
      "learning_rate": 1.6075697204327622e-06,
      "loss": 0.427,
      "step": 53211
    },
    {
      "epoch": 1.6346266089146928,
      "grad_norm": 0.43823474645614624,
      "learning_rate": 1.6073069450365174e-06,
      "loss": 0.4326,
      "step": 53212
    },
    {
      "epoch": 1.6346573280496421,
      "grad_norm": 0.47812145948410034,
      "learning_rate": 1.6070441892419953e-06,
      "loss": 0.4253,
      "step": 53213
    },
    {
      "epoch": 1.6346880471845913,
      "grad_norm": 0.435289591550827,
      "learning_rate": 1.6067814530498049e-06,
      "loss": 0.5401,
      "step": 53214
    },
    {
      "epoch": 1.6347187663195406,
      "grad_norm": 0.4229014813899994,
      "learning_rate": 1.6065187364605627e-06,
      "loss": 0.4728,
      "step": 53215
    },
    {
      "epoch": 1.6347494854544897,
      "grad_norm": 0.41236668825149536,
      "learning_rate": 1.6062560394748827e-06,
      "loss": 0.4257,
      "step": 53216
    },
    {
      "epoch": 1.6347802045894388,
      "grad_norm": 0.439762145280838,
      "learning_rate": 1.6059933620933799e-06,
      "loss": 0.4294,
      "step": 53217
    },
    {
      "epoch": 1.634810923724388,
      "grad_norm": 0.4272385835647583,
      "learning_rate": 1.6057307043166636e-06,
      "loss": 0.4931,
      "step": 53218
    },
    {
      "epoch": 1.634841642859337,
      "grad_norm": 0.40921470522880554,
      "learning_rate": 1.6054680661453493e-06,
      "loss": 0.5038,
      "step": 53219
    },
    {
      "epoch": 1.6348723619942862,
      "grad_norm": 0.3973977267742157,
      "learning_rate": 1.6052054475800506e-06,
      "loss": 0.4689,
      "step": 53220
    },
    {
      "epoch": 1.6349030811292353,
      "grad_norm": 0.4190640449523926,
      "learning_rate": 1.6049428486213837e-06,
      "loss": 0.4863,
      "step": 53221
    },
    {
      "epoch": 1.6349338002641844,
      "grad_norm": 0.4317040741443634,
      "learning_rate": 1.604680269269956e-06,
      "loss": 0.3625,
      "step": 53222
    },
    {
      "epoch": 1.6349645193991336,
      "grad_norm": 0.5561887621879578,
      "learning_rate": 1.6044177095263846e-06,
      "loss": 0.5175,
      "step": 53223
    },
    {
      "epoch": 1.634995238534083,
      "grad_norm": 0.5356379151344299,
      "learning_rate": 1.6041551693912815e-06,
      "loss": 0.4461,
      "step": 53224
    },
    {
      "epoch": 1.635025957669032,
      "grad_norm": 0.4226488471031189,
      "learning_rate": 1.6038926488652628e-06,
      "loss": 0.4683,
      "step": 53225
    },
    {
      "epoch": 1.6350566768039811,
      "grad_norm": 0.687537670135498,
      "learning_rate": 1.603630147948937e-06,
      "loss": 0.4187,
      "step": 53226
    },
    {
      "epoch": 1.6350873959389305,
      "grad_norm": 0.43885546922683716,
      "learning_rate": 1.6033676666429188e-06,
      "loss": 0.5282,
      "step": 53227
    },
    {
      "epoch": 1.6351181150738796,
      "grad_norm": 0.40516194701194763,
      "learning_rate": 1.6031052049478224e-06,
      "loss": 0.4787,
      "step": 53228
    },
    {
      "epoch": 1.6351488342088287,
      "grad_norm": 0.4418479800224304,
      "learning_rate": 1.6028427628642606e-06,
      "loss": 0.49,
      "step": 53229
    },
    {
      "epoch": 1.6351795533437778,
      "grad_norm": 0.4615507423877716,
      "learning_rate": 1.6025803403928475e-06,
      "loss": 0.5144,
      "step": 53230
    },
    {
      "epoch": 1.635210272478727,
      "grad_norm": 0.42760297656059265,
      "learning_rate": 1.6023179375341924e-06,
      "loss": 0.4149,
      "step": 53231
    },
    {
      "epoch": 1.635240991613676,
      "grad_norm": 0.47133103013038635,
      "learning_rate": 1.6020555542889105e-06,
      "loss": 0.4297,
      "step": 53232
    },
    {
      "epoch": 1.6352717107486252,
      "grad_norm": 0.4841664433479309,
      "learning_rate": 1.6017931906576145e-06,
      "loss": 0.4462,
      "step": 53233
    },
    {
      "epoch": 1.6353024298835743,
      "grad_norm": 0.40694689750671387,
      "learning_rate": 1.6015308466409186e-06,
      "loss": 0.4531,
      "step": 53234
    },
    {
      "epoch": 1.6353331490185237,
      "grad_norm": 0.433377206325531,
      "learning_rate": 1.601268522239432e-06,
      "loss": 0.4981,
      "step": 53235
    },
    {
      "epoch": 1.6353638681534728,
      "grad_norm": 0.4289441704750061,
      "learning_rate": 1.601006217453772e-06,
      "loss": 0.481,
      "step": 53236
    },
    {
      "epoch": 1.635394587288422,
      "grad_norm": 0.46742045879364014,
      "learning_rate": 1.600743932284543e-06,
      "loss": 0.5005,
      "step": 53237
    },
    {
      "epoch": 1.6354253064233713,
      "grad_norm": 0.42607274651527405,
      "learning_rate": 1.6004816667323686e-06,
      "loss": 0.5007,
      "step": 53238
    },
    {
      "epoch": 1.6354560255583204,
      "grad_norm": 0.5004162192344666,
      "learning_rate": 1.6002194207978539e-06,
      "loss": 0.4674,
      "step": 53239
    },
    {
      "epoch": 1.6354867446932695,
      "grad_norm": 0.42213237285614014,
      "learning_rate": 1.599957194481615e-06,
      "loss": 0.4615,
      "step": 53240
    },
    {
      "epoch": 1.6355174638282186,
      "grad_norm": 0.44324639439582825,
      "learning_rate": 1.5996949877842604e-06,
      "loss": 0.482,
      "step": 53241
    },
    {
      "epoch": 1.6355481829631677,
      "grad_norm": 0.4352967143058777,
      "learning_rate": 1.5994328007064052e-06,
      "loss": 0.5007,
      "step": 53242
    },
    {
      "epoch": 1.6355789020981168,
      "grad_norm": 0.4387897253036499,
      "learning_rate": 1.599170633248661e-06,
      "loss": 0.4625,
      "step": 53243
    },
    {
      "epoch": 1.635609621233066,
      "grad_norm": 0.426137238740921,
      "learning_rate": 1.5989084854116432e-06,
      "loss": 0.5042,
      "step": 53244
    },
    {
      "epoch": 1.635640340368015,
      "grad_norm": 0.39117202162742615,
      "learning_rate": 1.5986463571959587e-06,
      "loss": 0.4954,
      "step": 53245
    },
    {
      "epoch": 1.6356710595029644,
      "grad_norm": 0.47703856229782104,
      "learning_rate": 1.5983842486022227e-06,
      "loss": 0.4781,
      "step": 53246
    },
    {
      "epoch": 1.6357017786379136,
      "grad_norm": 0.40435492992401123,
      "learning_rate": 1.598122159631047e-06,
      "loss": 0.4585,
      "step": 53247
    },
    {
      "epoch": 1.6357324977728627,
      "grad_norm": 0.4501217007637024,
      "learning_rate": 1.5978600902830433e-06,
      "loss": 0.4926,
      "step": 53248
    },
    {
      "epoch": 1.635763216907812,
      "grad_norm": 0.436027854681015,
      "learning_rate": 1.5975980405588264e-06,
      "loss": 0.4417,
      "step": 53249
    },
    {
      "epoch": 1.6357939360427611,
      "grad_norm": 0.45056474208831787,
      "learning_rate": 1.597336010459004e-06,
      "loss": 0.5408,
      "step": 53250
    },
    {
      "epoch": 1.6358246551777103,
      "grad_norm": 0.43428996205329895,
      "learning_rate": 1.597073999984191e-06,
      "loss": 0.4624,
      "step": 53251
    },
    {
      "epoch": 1.6358553743126594,
      "grad_norm": 0.41505593061447144,
      "learning_rate": 1.5968120091349982e-06,
      "loss": 0.5173,
      "step": 53252
    },
    {
      "epoch": 1.6358860934476085,
      "grad_norm": 0.41163891553878784,
      "learning_rate": 1.5965500379120391e-06,
      "loss": 0.4447,
      "step": 53253
    },
    {
      "epoch": 1.6359168125825576,
      "grad_norm": 0.4303090572357178,
      "learning_rate": 1.5962880863159224e-06,
      "loss": 0.4383,
      "step": 53254
    },
    {
      "epoch": 1.6359475317175067,
      "grad_norm": 0.4148523509502411,
      "learning_rate": 1.5960261543472622e-06,
      "loss": 0.4302,
      "step": 53255
    },
    {
      "epoch": 1.6359782508524559,
      "grad_norm": 0.41049686074256897,
      "learning_rate": 1.5957642420066699e-06,
      "loss": 0.5118,
      "step": 53256
    },
    {
      "epoch": 1.6360089699874052,
      "grad_norm": 0.43104103207588196,
      "learning_rate": 1.5955023492947596e-06,
      "loss": 0.4284,
      "step": 53257
    },
    {
      "epoch": 1.6360396891223543,
      "grad_norm": 0.4423947334289551,
      "learning_rate": 1.5952404762121376e-06,
      "loss": 0.496,
      "step": 53258
    },
    {
      "epoch": 1.6360704082573034,
      "grad_norm": 0.4101673364639282,
      "learning_rate": 1.5949786227594188e-06,
      "loss": 0.4087,
      "step": 53259
    },
    {
      "epoch": 1.6361011273922528,
      "grad_norm": 0.390584796667099,
      "learning_rate": 1.5947167889372139e-06,
      "loss": 0.4655,
      "step": 53260
    },
    {
      "epoch": 1.636131846527202,
      "grad_norm": 0.4323120713233948,
      "learning_rate": 1.594454974746138e-06,
      "loss": 0.5428,
      "step": 53261
    },
    {
      "epoch": 1.636162565662151,
      "grad_norm": 0.42639145255088806,
      "learning_rate": 1.5941931801867972e-06,
      "loss": 0.4077,
      "step": 53262
    },
    {
      "epoch": 1.6361932847971001,
      "grad_norm": 0.4244549870491028,
      "learning_rate": 1.5939314052598053e-06,
      "loss": 0.4699,
      "step": 53263
    },
    {
      "epoch": 1.6362240039320493,
      "grad_norm": 0.3972645103931427,
      "learning_rate": 1.5936696499657734e-06,
      "loss": 0.4574,
      "step": 53264
    },
    {
      "epoch": 1.6362547230669984,
      "grad_norm": 0.46382442116737366,
      "learning_rate": 1.5934079143053128e-06,
      "loss": 0.4288,
      "step": 53265
    },
    {
      "epoch": 1.6362854422019475,
      "grad_norm": 0.4258590340614319,
      "learning_rate": 1.5931461982790376e-06,
      "loss": 0.4808,
      "step": 53266
    },
    {
      "epoch": 1.6363161613368966,
      "grad_norm": 0.40878477692604065,
      "learning_rate": 1.592884501887555e-06,
      "loss": 0.4714,
      "step": 53267
    },
    {
      "epoch": 1.636346880471846,
      "grad_norm": 0.41623732447624207,
      "learning_rate": 1.5926228251314791e-06,
      "loss": 0.5182,
      "step": 53268
    },
    {
      "epoch": 1.636377599606795,
      "grad_norm": 0.46808359026908875,
      "learning_rate": 1.5923611680114158e-06,
      "loss": 0.5315,
      "step": 53269
    },
    {
      "epoch": 1.6364083187417442,
      "grad_norm": 0.40242430567741394,
      "learning_rate": 1.5920995305279852e-06,
      "loss": 0.4722,
      "step": 53270
    },
    {
      "epoch": 1.6364390378766935,
      "grad_norm": 0.4598882496356964,
      "learning_rate": 1.5918379126817896e-06,
      "loss": 0.4819,
      "step": 53271
    },
    {
      "epoch": 1.6364697570116427,
      "grad_norm": 0.38983437418937683,
      "learning_rate": 1.5915763144734476e-06,
      "loss": 0.4914,
      "step": 53272
    },
    {
      "epoch": 1.6365004761465918,
      "grad_norm": 0.4947485029697418,
      "learning_rate": 1.5913147359035609e-06,
      "loss": 0.4347,
      "step": 53273
    },
    {
      "epoch": 1.636531195281541,
      "grad_norm": 0.45775705575942993,
      "learning_rate": 1.5910531769727499e-06,
      "loss": 0.4473,
      "step": 53274
    },
    {
      "epoch": 1.63656191441649,
      "grad_norm": 0.39377859234809875,
      "learning_rate": 1.5907916376816203e-06,
      "loss": 0.4445,
      "step": 53275
    },
    {
      "epoch": 1.6365926335514391,
      "grad_norm": 0.44021859765052795,
      "learning_rate": 1.5905301180307863e-06,
      "loss": 0.5362,
      "step": 53276
    },
    {
      "epoch": 1.6366233526863883,
      "grad_norm": 0.4093818664550781,
      "learning_rate": 1.5902686180208537e-06,
      "loss": 0.4311,
      "step": 53277
    },
    {
      "epoch": 1.6366540718213374,
      "grad_norm": 0.3819205164909363,
      "learning_rate": 1.5900071376524362e-06,
      "loss": 0.3741,
      "step": 53278
    },
    {
      "epoch": 1.6366847909562867,
      "grad_norm": 0.43002086877822876,
      "learning_rate": 1.5897456769261455e-06,
      "loss": 0.4554,
      "step": 53279
    },
    {
      "epoch": 1.6367155100912358,
      "grad_norm": 0.439518541097641,
      "learning_rate": 1.5894842358425922e-06,
      "loss": 0.4512,
      "step": 53280
    },
    {
      "epoch": 1.636746229226185,
      "grad_norm": 0.5434578061103821,
      "learning_rate": 1.5892228144023836e-06,
      "loss": 0.519,
      "step": 53281
    },
    {
      "epoch": 1.6367769483611343,
      "grad_norm": 0.44355225563049316,
      "learning_rate": 1.5889614126061325e-06,
      "loss": 0.4658,
      "step": 53282
    },
    {
      "epoch": 1.6368076674960834,
      "grad_norm": 0.43246233463287354,
      "learning_rate": 1.5887000304544497e-06,
      "loss": 0.4492,
      "step": 53283
    },
    {
      "epoch": 1.6368383866310325,
      "grad_norm": 0.452718049287796,
      "learning_rate": 1.5884386679479458e-06,
      "loss": 0.511,
      "step": 53284
    },
    {
      "epoch": 1.6368691057659817,
      "grad_norm": 0.4386384189128876,
      "learning_rate": 1.5881773250872322e-06,
      "loss": 0.4366,
      "step": 53285
    },
    {
      "epoch": 1.6368998249009308,
      "grad_norm": 0.4590122401714325,
      "learning_rate": 1.5879160018729168e-06,
      "loss": 0.4513,
      "step": 53286
    },
    {
      "epoch": 1.63693054403588,
      "grad_norm": 0.4076438546180725,
      "learning_rate": 1.5876546983056095e-06,
      "loss": 0.4811,
      "step": 53287
    },
    {
      "epoch": 1.636961263170829,
      "grad_norm": 0.4170180857181549,
      "learning_rate": 1.5873934143859237e-06,
      "loss": 0.4479,
      "step": 53288
    },
    {
      "epoch": 1.6369919823057781,
      "grad_norm": 0.45051121711730957,
      "learning_rate": 1.58713215011447e-06,
      "loss": 0.43,
      "step": 53289
    },
    {
      "epoch": 1.6370227014407275,
      "grad_norm": 0.4666981101036072,
      "learning_rate": 1.586870905491854e-06,
      "loss": 0.4741,
      "step": 53290
    },
    {
      "epoch": 1.6370534205756766,
      "grad_norm": 0.45289430022239685,
      "learning_rate": 1.5866096805186892e-06,
      "loss": 0.4481,
      "step": 53291
    },
    {
      "epoch": 1.6370841397106257,
      "grad_norm": 0.4184211492538452,
      "learning_rate": 1.5863484751955839e-06,
      "loss": 0.3974,
      "step": 53292
    },
    {
      "epoch": 1.637114858845575,
      "grad_norm": 0.450351357460022,
      "learning_rate": 1.5860872895231526e-06,
      "loss": 0.4774,
      "step": 53293
    },
    {
      "epoch": 1.6371455779805242,
      "grad_norm": 0.4021461606025696,
      "learning_rate": 1.5858261235020001e-06,
      "loss": 0.4143,
      "step": 53294
    },
    {
      "epoch": 1.6371762971154733,
      "grad_norm": 0.39737945795059204,
      "learning_rate": 1.5855649771327375e-06,
      "loss": 0.4728,
      "step": 53295
    },
    {
      "epoch": 1.6372070162504224,
      "grad_norm": 0.38842880725860596,
      "learning_rate": 1.5853038504159756e-06,
      "loss": 0.4588,
      "step": 53296
    },
    {
      "epoch": 1.6372377353853715,
      "grad_norm": 0.4450356662273407,
      "learning_rate": 1.5850427433523274e-06,
      "loss": 0.5411,
      "step": 53297
    },
    {
      "epoch": 1.6372684545203207,
      "grad_norm": 0.4332629144191742,
      "learning_rate": 1.5847816559423967e-06,
      "loss": 0.4563,
      "step": 53298
    },
    {
      "epoch": 1.6372991736552698,
      "grad_norm": 0.45934128761291504,
      "learning_rate": 1.5845205881867976e-06,
      "loss": 0.4569,
      "step": 53299
    },
    {
      "epoch": 1.637329892790219,
      "grad_norm": 0.4577048420906067,
      "learning_rate": 1.584259540086135e-06,
      "loss": 0.5692,
      "step": 53300
    },
    {
      "epoch": 1.6373606119251682,
      "grad_norm": 0.42652642726898193,
      "learning_rate": 1.583998511641024e-06,
      "loss": 0.5213,
      "step": 53301
    },
    {
      "epoch": 1.6373913310601174,
      "grad_norm": 0.41674700379371643,
      "learning_rate": 1.5837375028520741e-06,
      "loss": 0.5066,
      "step": 53302
    },
    {
      "epoch": 1.6374220501950665,
      "grad_norm": 0.4161617159843445,
      "learning_rate": 1.5834765137198916e-06,
      "loss": 0.4633,
      "step": 53303
    },
    {
      "epoch": 1.6374527693300158,
      "grad_norm": 0.4170326292514801,
      "learning_rate": 1.5832155442450892e-06,
      "loss": 0.4522,
      "step": 53304
    },
    {
      "epoch": 1.637483488464965,
      "grad_norm": 0.4350314736366272,
      "learning_rate": 1.5829545944282698e-06,
      "loss": 0.4346,
      "step": 53305
    },
    {
      "epoch": 1.637514207599914,
      "grad_norm": 0.4145455062389374,
      "learning_rate": 1.582693664270053e-06,
      "loss": 0.469,
      "step": 53306
    },
    {
      "epoch": 1.6375449267348632,
      "grad_norm": 0.4321574866771698,
      "learning_rate": 1.5824327537710405e-06,
      "loss": 0.4893,
      "step": 53307
    },
    {
      "epoch": 1.6375756458698123,
      "grad_norm": 0.4441584050655365,
      "learning_rate": 1.582171862931846e-06,
      "loss": 0.4248,
      "step": 53308
    },
    {
      "epoch": 1.6376063650047614,
      "grad_norm": 0.47618311643600464,
      "learning_rate": 1.5819109917530762e-06,
      "loss": 0.4559,
      "step": 53309
    },
    {
      "epoch": 1.6376370841397105,
      "grad_norm": 0.5053534507751465,
      "learning_rate": 1.58165014023534e-06,
      "loss": 0.482,
      "step": 53310
    },
    {
      "epoch": 1.6376678032746597,
      "grad_norm": 0.46078166365623474,
      "learning_rate": 1.5813893083792475e-06,
      "loss": 0.4598,
      "step": 53311
    },
    {
      "epoch": 1.6376985224096088,
      "grad_norm": 0.4183785617351532,
      "learning_rate": 1.5811284961854113e-06,
      "loss": 0.459,
      "step": 53312
    },
    {
      "epoch": 1.6377292415445581,
      "grad_norm": 0.4116756021976471,
      "learning_rate": 1.580867703654435e-06,
      "loss": 0.4629,
      "step": 53313
    },
    {
      "epoch": 1.6377599606795072,
      "grad_norm": 0.4485977292060852,
      "learning_rate": 1.58060693078693e-06,
      "loss": 0.4526,
      "step": 53314
    },
    {
      "epoch": 1.6377906798144566,
      "grad_norm": 0.5353191494941711,
      "learning_rate": 1.580346177583505e-06,
      "loss": 0.4748,
      "step": 53315
    },
    {
      "epoch": 1.6378213989494057,
      "grad_norm": 0.4237081706523895,
      "learning_rate": 1.5800854440447734e-06,
      "loss": 0.4461,
      "step": 53316
    },
    {
      "epoch": 1.6378521180843548,
      "grad_norm": 0.4627324640750885,
      "learning_rate": 1.5798247301713366e-06,
      "loss": 0.5768,
      "step": 53317
    },
    {
      "epoch": 1.637882837219304,
      "grad_norm": 0.4219966232776642,
      "learning_rate": 1.5795640359638076e-06,
      "loss": 0.4664,
      "step": 53318
    },
    {
      "epoch": 1.637913556354253,
      "grad_norm": 0.4155158996582031,
      "learning_rate": 1.5793033614227949e-06,
      "loss": 0.4078,
      "step": 53319
    },
    {
      "epoch": 1.6379442754892022,
      "grad_norm": 0.5018161535263062,
      "learning_rate": 1.5790427065489067e-06,
      "loss": 0.4758,
      "step": 53320
    },
    {
      "epoch": 1.6379749946241513,
      "grad_norm": 0.4474010169506073,
      "learning_rate": 1.578782071342756e-06,
      "loss": 0.4175,
      "step": 53321
    },
    {
      "epoch": 1.6380057137591004,
      "grad_norm": 0.42121419310569763,
      "learning_rate": 1.5785214558049445e-06,
      "loss": 0.4142,
      "step": 53322
    },
    {
      "epoch": 1.6380364328940495,
      "grad_norm": 0.40536215901374817,
      "learning_rate": 1.5782608599360838e-06,
      "loss": 0.4845,
      "step": 53323
    },
    {
      "epoch": 1.6380671520289989,
      "grad_norm": 0.46616658568382263,
      "learning_rate": 1.5780002837367847e-06,
      "loss": 0.4998,
      "step": 53324
    },
    {
      "epoch": 1.638097871163948,
      "grad_norm": 0.44672834873199463,
      "learning_rate": 1.5777397272076556e-06,
      "loss": 0.4825,
      "step": 53325
    },
    {
      "epoch": 1.6381285902988973,
      "grad_norm": 0.4580327570438385,
      "learning_rate": 1.5774791903493003e-06,
      "loss": 0.433,
      "step": 53326
    },
    {
      "epoch": 1.6381593094338465,
      "grad_norm": 0.4598536789417267,
      "learning_rate": 1.5772186731623317e-06,
      "loss": 0.4747,
      "step": 53327
    },
    {
      "epoch": 1.6381900285687956,
      "grad_norm": 0.40525439381599426,
      "learning_rate": 1.5769581756473573e-06,
      "loss": 0.401,
      "step": 53328
    },
    {
      "epoch": 1.6382207477037447,
      "grad_norm": 0.43192559480667114,
      "learning_rate": 1.5766976978049876e-06,
      "loss": 0.4545,
      "step": 53329
    },
    {
      "epoch": 1.6382514668386938,
      "grad_norm": 0.43973231315612793,
      "learning_rate": 1.5764372396358252e-06,
      "loss": 0.3726,
      "step": 53330
    },
    {
      "epoch": 1.638282185973643,
      "grad_norm": 0.42129188776016235,
      "learning_rate": 1.5761768011404853e-06,
      "loss": 0.4665,
      "step": 53331
    },
    {
      "epoch": 1.638312905108592,
      "grad_norm": 0.6224532723426819,
      "learning_rate": 1.5759163823195677e-06,
      "loss": 0.4102,
      "step": 53332
    },
    {
      "epoch": 1.6383436242435412,
      "grad_norm": 0.4603673815727234,
      "learning_rate": 1.5756559831736916e-06,
      "loss": 0.5006,
      "step": 53333
    },
    {
      "epoch": 1.6383743433784903,
      "grad_norm": 0.41060012578964233,
      "learning_rate": 1.5753956037034556e-06,
      "loss": 0.5793,
      "step": 53334
    },
    {
      "epoch": 1.6384050625134396,
      "grad_norm": 0.39930441975593567,
      "learning_rate": 1.5751352439094747e-06,
      "loss": 0.4312,
      "step": 53335
    },
    {
      "epoch": 1.6384357816483888,
      "grad_norm": 0.6333514451980591,
      "learning_rate": 1.5748749037923484e-06,
      "loss": 0.6076,
      "step": 53336
    },
    {
      "epoch": 1.6384665007833379,
      "grad_norm": 0.4167230427265167,
      "learning_rate": 1.5746145833526927e-06,
      "loss": 0.4517,
      "step": 53337
    },
    {
      "epoch": 1.6384972199182872,
      "grad_norm": 0.4217863082885742,
      "learning_rate": 1.5743542825911152e-06,
      "loss": 0.4373,
      "step": 53338
    },
    {
      "epoch": 1.6385279390532363,
      "grad_norm": 0.4478165805339813,
      "learning_rate": 1.5740940015082196e-06,
      "loss": 0.4908,
      "step": 53339
    },
    {
      "epoch": 1.6385586581881855,
      "grad_norm": 0.4372767508029938,
      "learning_rate": 1.5738337401046188e-06,
      "loss": 0.4528,
      "step": 53340
    },
    {
      "epoch": 1.6385893773231346,
      "grad_norm": 0.9094725847244263,
      "learning_rate": 1.5735734983809125e-06,
      "loss": 0.4897,
      "step": 53341
    },
    {
      "epoch": 1.6386200964580837,
      "grad_norm": 0.536590039730072,
      "learning_rate": 1.573313276337719e-06,
      "loss": 0.5354,
      "step": 53342
    },
    {
      "epoch": 1.6386508155930328,
      "grad_norm": 0.41520780324935913,
      "learning_rate": 1.5730530739756377e-06,
      "loss": 0.4603,
      "step": 53343
    },
    {
      "epoch": 1.638681534727982,
      "grad_norm": 0.47299712896347046,
      "learning_rate": 1.5727928912952828e-06,
      "loss": 0.4795,
      "step": 53344
    },
    {
      "epoch": 1.638712253862931,
      "grad_norm": 0.4421783983707428,
      "learning_rate": 1.5725327282972557e-06,
      "loss": 0.4695,
      "step": 53345
    },
    {
      "epoch": 1.6387429729978804,
      "grad_norm": 0.389938086271286,
      "learning_rate": 1.5722725849821674e-06,
      "loss": 0.5126,
      "step": 53346
    },
    {
      "epoch": 1.6387736921328295,
      "grad_norm": 0.417640745639801,
      "learning_rate": 1.5720124613506237e-06,
      "loss": 0.5322,
      "step": 53347
    },
    {
      "epoch": 1.6388044112677786,
      "grad_norm": 0.45029062032699585,
      "learning_rate": 1.5717523574032379e-06,
      "loss": 0.4042,
      "step": 53348
    },
    {
      "epoch": 1.638835130402728,
      "grad_norm": 0.42890140414237976,
      "learning_rate": 1.571492273140609e-06,
      "loss": 0.4793,
      "step": 53349
    },
    {
      "epoch": 1.638865849537677,
      "grad_norm": 0.4854644238948822,
      "learning_rate": 1.5712322085633492e-06,
      "loss": 0.4857,
      "step": 53350
    },
    {
      "epoch": 1.6388965686726262,
      "grad_norm": 0.448671817779541,
      "learning_rate": 1.5709721636720654e-06,
      "loss": 0.5613,
      "step": 53351
    },
    {
      "epoch": 1.6389272878075754,
      "grad_norm": 0.4233493506908417,
      "learning_rate": 1.5707121384673674e-06,
      "loss": 0.5426,
      "step": 53352
    },
    {
      "epoch": 1.6389580069425245,
      "grad_norm": 0.4490891993045807,
      "learning_rate": 1.5704521329498569e-06,
      "loss": 0.4541,
      "step": 53353
    },
    {
      "epoch": 1.6389887260774736,
      "grad_norm": 0.4312678575515747,
      "learning_rate": 1.5701921471201442e-06,
      "loss": 0.4405,
      "step": 53354
    },
    {
      "epoch": 1.6390194452124227,
      "grad_norm": 0.46936386823654175,
      "learning_rate": 1.569932180978837e-06,
      "loss": 0.4968,
      "step": 53355
    },
    {
      "epoch": 1.6390501643473718,
      "grad_norm": 0.4181308448314667,
      "learning_rate": 1.5696722345265414e-06,
      "loss": 0.4993,
      "step": 53356
    },
    {
      "epoch": 1.6390808834823212,
      "grad_norm": 0.4299542009830475,
      "learning_rate": 1.5694123077638679e-06,
      "loss": 0.4411,
      "step": 53357
    },
    {
      "epoch": 1.6391116026172703,
      "grad_norm": 0.4898044764995575,
      "learning_rate": 1.5691524006914182e-06,
      "loss": 0.4965,
      "step": 53358
    },
    {
      "epoch": 1.6391423217522194,
      "grad_norm": 0.46718764305114746,
      "learning_rate": 1.568892513309801e-06,
      "loss": 0.5198,
      "step": 53359
    },
    {
      "epoch": 1.6391730408871688,
      "grad_norm": 0.42103585600852966,
      "learning_rate": 1.5686326456196254e-06,
      "loss": 0.5224,
      "step": 53360
    },
    {
      "epoch": 1.6392037600221179,
      "grad_norm": 0.41064706444740295,
      "learning_rate": 1.568372797621499e-06,
      "loss": 0.4725,
      "step": 53361
    },
    {
      "epoch": 1.639234479157067,
      "grad_norm": 0.43578433990478516,
      "learning_rate": 1.5681129693160246e-06,
      "loss": 0.4582,
      "step": 53362
    },
    {
      "epoch": 1.6392651982920161,
      "grad_norm": 0.40990567207336426,
      "learning_rate": 1.5678531607038105e-06,
      "loss": 0.5558,
      "step": 53363
    },
    {
      "epoch": 1.6392959174269652,
      "grad_norm": 0.45844215154647827,
      "learning_rate": 1.5675933717854653e-06,
      "loss": 0.4448,
      "step": 53364
    },
    {
      "epoch": 1.6393266365619144,
      "grad_norm": 0.4249621629714966,
      "learning_rate": 1.567333602561597e-06,
      "loss": 0.4701,
      "step": 53365
    },
    {
      "epoch": 1.6393573556968635,
      "grad_norm": 0.43749698996543884,
      "learning_rate": 1.5670738530328068e-06,
      "loss": 0.3703,
      "step": 53366
    },
    {
      "epoch": 1.6393880748318126,
      "grad_norm": 0.45014992356300354,
      "learning_rate": 1.566814123199707e-06,
      "loss": 0.4956,
      "step": 53367
    },
    {
      "epoch": 1.639418793966762,
      "grad_norm": 0.60526442527771,
      "learning_rate": 1.5665544130628974e-06,
      "loss": 0.4905,
      "step": 53368
    },
    {
      "epoch": 1.639449513101711,
      "grad_norm": 0.40154963731765747,
      "learning_rate": 1.566294722622994e-06,
      "loss": 0.485,
      "step": 53369
    },
    {
      "epoch": 1.6394802322366602,
      "grad_norm": 0.4475862681865692,
      "learning_rate": 1.5660350518805955e-06,
      "loss": 0.5072,
      "step": 53370
    },
    {
      "epoch": 1.6395109513716095,
      "grad_norm": 0.4034575819969177,
      "learning_rate": 1.5657754008363136e-06,
      "loss": 0.4497,
      "step": 53371
    },
    {
      "epoch": 1.6395416705065586,
      "grad_norm": 0.5685712695121765,
      "learning_rate": 1.5655157694907497e-06,
      "loss": 0.4585,
      "step": 53372
    },
    {
      "epoch": 1.6395723896415078,
      "grad_norm": 0.4675777852535248,
      "learning_rate": 1.5652561578445113e-06,
      "loss": 0.477,
      "step": 53373
    },
    {
      "epoch": 1.6396031087764569,
      "grad_norm": 0.428569495677948,
      "learning_rate": 1.5649965658982102e-06,
      "loss": 0.5364,
      "step": 53374
    },
    {
      "epoch": 1.639633827911406,
      "grad_norm": 0.427872896194458,
      "learning_rate": 1.5647369936524458e-06,
      "loss": 0.3912,
      "step": 53375
    },
    {
      "epoch": 1.6396645470463551,
      "grad_norm": 0.46520379185676575,
      "learning_rate": 1.5644774411078311e-06,
      "loss": 0.527,
      "step": 53376
    },
    {
      "epoch": 1.6396952661813042,
      "grad_norm": 0.46103334426879883,
      "learning_rate": 1.5642179082649622e-06,
      "loss": 0.5066,
      "step": 53377
    },
    {
      "epoch": 1.6397259853162534,
      "grad_norm": 0.4777487814426422,
      "learning_rate": 1.5639583951244574e-06,
      "loss": 0.5053,
      "step": 53378
    },
    {
      "epoch": 1.6397567044512027,
      "grad_norm": 0.4533466398715973,
      "learning_rate": 1.5636989016869142e-06,
      "loss": 0.522,
      "step": 53379
    },
    {
      "epoch": 1.6397874235861518,
      "grad_norm": 0.43070679903030396,
      "learning_rate": 1.5634394279529442e-06,
      "loss": 0.4086,
      "step": 53380
    },
    {
      "epoch": 1.639818142721101,
      "grad_norm": 0.43875551223754883,
      "learning_rate": 1.5631799739231467e-06,
      "loss": 0.4694,
      "step": 53381
    },
    {
      "epoch": 1.6398488618560503,
      "grad_norm": 0.4718630313873291,
      "learning_rate": 1.562920539598133e-06,
      "loss": 0.4178,
      "step": 53382
    },
    {
      "epoch": 1.6398795809909994,
      "grad_norm": 0.39968791604042053,
      "learning_rate": 1.5626611249785074e-06,
      "loss": 0.4123,
      "step": 53383
    },
    {
      "epoch": 1.6399103001259485,
      "grad_norm": 0.4073648452758789,
      "learning_rate": 1.5624017300648787e-06,
      "loss": 0.4923,
      "step": 53384
    },
    {
      "epoch": 1.6399410192608976,
      "grad_norm": 0.4197178781032562,
      "learning_rate": 1.5621423548578463e-06,
      "loss": 0.485,
      "step": 53385
    },
    {
      "epoch": 1.6399717383958468,
      "grad_norm": 0.6182822585105896,
      "learning_rate": 1.5618829993580208e-06,
      "loss": 0.5084,
      "step": 53386
    },
    {
      "epoch": 1.6400024575307959,
      "grad_norm": 0.4379996657371521,
      "learning_rate": 1.5616236635660065e-06,
      "loss": 0.4857,
      "step": 53387
    },
    {
      "epoch": 1.640033176665745,
      "grad_norm": 0.44505029916763306,
      "learning_rate": 1.5613643474824125e-06,
      "loss": 0.516,
      "step": 53388
    },
    {
      "epoch": 1.6400638958006941,
      "grad_norm": 0.44993582367897034,
      "learning_rate": 1.5611050511078385e-06,
      "loss": 0.4573,
      "step": 53389
    },
    {
      "epoch": 1.6400946149356435,
      "grad_norm": 0.4263113737106323,
      "learning_rate": 1.560845774442893e-06,
      "loss": 0.3902,
      "step": 53390
    },
    {
      "epoch": 1.6401253340705926,
      "grad_norm": 0.4288913607597351,
      "learning_rate": 1.5605865174881818e-06,
      "loss": 0.3662,
      "step": 53391
    },
    {
      "epoch": 1.6401560532055417,
      "grad_norm": 0.41629958152770996,
      "learning_rate": 1.5603272802443103e-06,
      "loss": 0.5382,
      "step": 53392
    },
    {
      "epoch": 1.640186772340491,
      "grad_norm": 0.40530624985694885,
      "learning_rate": 1.5600680627118857e-06,
      "loss": 0.4372,
      "step": 53393
    },
    {
      "epoch": 1.6402174914754402,
      "grad_norm": 0.4028867185115814,
      "learning_rate": 1.5598088648915099e-06,
      "loss": 0.4211,
      "step": 53394
    },
    {
      "epoch": 1.6402482106103893,
      "grad_norm": 0.4431866705417633,
      "learning_rate": 1.559549686783789e-06,
      "loss": 0.457,
      "step": 53395
    },
    {
      "epoch": 1.6402789297453384,
      "grad_norm": 0.4270612597465515,
      "learning_rate": 1.55929052838933e-06,
      "loss": 0.4882,
      "step": 53396
    },
    {
      "epoch": 1.6403096488802875,
      "grad_norm": 0.4309542775154114,
      "learning_rate": 1.5590313897087394e-06,
      "loss": 0.5051,
      "step": 53397
    },
    {
      "epoch": 1.6403403680152366,
      "grad_norm": 0.4466702342033386,
      "learning_rate": 1.558772270742619e-06,
      "loss": 0.4834,
      "step": 53398
    },
    {
      "epoch": 1.6403710871501858,
      "grad_norm": 0.4334215521812439,
      "learning_rate": 1.5585131714915747e-06,
      "loss": 0.4633,
      "step": 53399
    },
    {
      "epoch": 1.6404018062851349,
      "grad_norm": 0.42120322585105896,
      "learning_rate": 1.5582540919562127e-06,
      "loss": 0.4295,
      "step": 53400
    },
    {
      "epoch": 1.6404325254200842,
      "grad_norm": 0.409403532743454,
      "learning_rate": 1.5579950321371396e-06,
      "loss": 0.4797,
      "step": 53401
    },
    {
      "epoch": 1.6404632445550333,
      "grad_norm": 0.4178650379180908,
      "learning_rate": 1.5577359920349567e-06,
      "loss": 0.4595,
      "step": 53402
    },
    {
      "epoch": 1.6404939636899825,
      "grad_norm": 0.4520416855812073,
      "learning_rate": 1.5574769716502735e-06,
      "loss": 0.5052,
      "step": 53403
    },
    {
      "epoch": 1.6405246828249318,
      "grad_norm": 0.374051570892334,
      "learning_rate": 1.5572179709836876e-06,
      "loss": 0.4624,
      "step": 53404
    },
    {
      "epoch": 1.640555401959881,
      "grad_norm": 0.45513710379600525,
      "learning_rate": 1.556958990035814e-06,
      "loss": 0.437,
      "step": 53405
    },
    {
      "epoch": 1.64058612109483,
      "grad_norm": 0.4415973722934723,
      "learning_rate": 1.5567000288072499e-06,
      "loss": 0.4317,
      "step": 53406
    },
    {
      "epoch": 1.6406168402297792,
      "grad_norm": 0.42804601788520813,
      "learning_rate": 1.5564410872986046e-06,
      "loss": 0.4549,
      "step": 53407
    },
    {
      "epoch": 1.6406475593647283,
      "grad_norm": 0.43341508507728577,
      "learning_rate": 1.556182165510478e-06,
      "loss": 0.4315,
      "step": 53408
    },
    {
      "epoch": 1.6406782784996774,
      "grad_norm": 0.42290204763412476,
      "learning_rate": 1.5559232634434762e-06,
      "loss": 0.5044,
      "step": 53409
    },
    {
      "epoch": 1.6407089976346265,
      "grad_norm": 0.4658697545528412,
      "learning_rate": 1.5556643810982097e-06,
      "loss": 0.4989,
      "step": 53410
    },
    {
      "epoch": 1.6407397167695756,
      "grad_norm": 0.3986561596393585,
      "learning_rate": 1.555405518475276e-06,
      "loss": 0.4585,
      "step": 53411
    },
    {
      "epoch": 1.640770435904525,
      "grad_norm": 0.4386899173259735,
      "learning_rate": 1.5551466755752853e-06,
      "loss": 0.3667,
      "step": 53412
    },
    {
      "epoch": 1.640801155039474,
      "grad_norm": 0.45134982466697693,
      "learning_rate": 1.5548878523988364e-06,
      "loss": 0.5181,
      "step": 53413
    },
    {
      "epoch": 1.6408318741744232,
      "grad_norm": 0.41933563351631165,
      "learning_rate": 1.5546290489465378e-06,
      "loss": 0.4529,
      "step": 53414
    },
    {
      "epoch": 1.6408625933093726,
      "grad_norm": 0.4890083372592926,
      "learning_rate": 1.5543702652189918e-06,
      "loss": 0.4199,
      "step": 53415
    },
    {
      "epoch": 1.6408933124443217,
      "grad_norm": 0.41357722878456116,
      "learning_rate": 1.5541115012168074e-06,
      "loss": 0.5824,
      "step": 53416
    },
    {
      "epoch": 1.6409240315792708,
      "grad_norm": 0.49881836771965027,
      "learning_rate": 1.5538527569405814e-06,
      "loss": 0.4717,
      "step": 53417
    },
    {
      "epoch": 1.64095475071422,
      "grad_norm": 0.46349698305130005,
      "learning_rate": 1.5535940323909237e-06,
      "loss": 0.4823,
      "step": 53418
    },
    {
      "epoch": 1.640985469849169,
      "grad_norm": 0.43873685598373413,
      "learning_rate": 1.553335327568436e-06,
      "loss": 0.5171,
      "step": 53419
    },
    {
      "epoch": 1.6410161889841182,
      "grad_norm": 0.4399486184120178,
      "learning_rate": 1.5530766424737264e-06,
      "loss": 0.4952,
      "step": 53420
    },
    {
      "epoch": 1.6410469081190673,
      "grad_norm": 0.44881880283355713,
      "learning_rate": 1.5528179771073937e-06,
      "loss": 0.47,
      "step": 53421
    },
    {
      "epoch": 1.6410776272540164,
      "grad_norm": 0.4025789201259613,
      "learning_rate": 1.552559331470045e-06,
      "loss": 0.4596,
      "step": 53422
    },
    {
      "epoch": 1.6411083463889655,
      "grad_norm": 0.449856698513031,
      "learning_rate": 1.552300705562284e-06,
      "loss": 0.45,
      "step": 53423
    },
    {
      "epoch": 1.6411390655239149,
      "grad_norm": 0.41120073199272156,
      "learning_rate": 1.5520420993847163e-06,
      "loss": 0.4585,
      "step": 53424
    },
    {
      "epoch": 1.641169784658864,
      "grad_norm": 0.38001248240470886,
      "learning_rate": 1.5517835129379423e-06,
      "loss": 0.436,
      "step": 53425
    },
    {
      "epoch": 1.6412005037938133,
      "grad_norm": 0.4172053039073944,
      "learning_rate": 1.5515249462225678e-06,
      "loss": 0.4573,
      "step": 53426
    },
    {
      "epoch": 1.6412312229287624,
      "grad_norm": 0.4033748507499695,
      "learning_rate": 1.5512663992391975e-06,
      "loss": 0.47,
      "step": 53427
    },
    {
      "epoch": 1.6412619420637116,
      "grad_norm": 0.42857804894447327,
      "learning_rate": 1.5510078719884336e-06,
      "loss": 0.4841,
      "step": 53428
    },
    {
      "epoch": 1.6412926611986607,
      "grad_norm": 0.44227272272109985,
      "learning_rate": 1.5507493644708838e-06,
      "loss": 0.4822,
      "step": 53429
    },
    {
      "epoch": 1.6413233803336098,
      "grad_norm": 0.4192986786365509,
      "learning_rate": 1.5504908766871463e-06,
      "loss": 0.4266,
      "step": 53430
    },
    {
      "epoch": 1.641354099468559,
      "grad_norm": 0.4362539052963257,
      "learning_rate": 1.5502324086378273e-06,
      "loss": 0.4901,
      "step": 53431
    },
    {
      "epoch": 1.641384818603508,
      "grad_norm": 0.3917602598667145,
      "learning_rate": 1.5499739603235308e-06,
      "loss": 0.3695,
      "step": 53432
    },
    {
      "epoch": 1.6414155377384572,
      "grad_norm": 0.44989314675331116,
      "learning_rate": 1.549715531744863e-06,
      "loss": 0.4837,
      "step": 53433
    },
    {
      "epoch": 1.6414462568734063,
      "grad_norm": 0.4084519147872925,
      "learning_rate": 1.5494571229024224e-06,
      "loss": 0.3612,
      "step": 53434
    },
    {
      "epoch": 1.6414769760083556,
      "grad_norm": 0.43417152762413025,
      "learning_rate": 1.5491987337968173e-06,
      "loss": 0.4207,
      "step": 53435
    },
    {
      "epoch": 1.6415076951433047,
      "grad_norm": 0.5186833143234253,
      "learning_rate": 1.5489403644286438e-06,
      "loss": 0.4565,
      "step": 53436
    },
    {
      "epoch": 1.641538414278254,
      "grad_norm": 0.41968461871147156,
      "learning_rate": 1.548682014798515e-06,
      "loss": 0.4815,
      "step": 53437
    },
    {
      "epoch": 1.6415691334132032,
      "grad_norm": 0.43422529101371765,
      "learning_rate": 1.5484236849070266e-06,
      "loss": 0.4383,
      "step": 53438
    },
    {
      "epoch": 1.6415998525481523,
      "grad_norm": 0.36950069665908813,
      "learning_rate": 1.5481653747547875e-06,
      "loss": 0.4177,
      "step": 53439
    },
    {
      "epoch": 1.6416305716831014,
      "grad_norm": 0.4306175410747528,
      "learning_rate": 1.547907084342395e-06,
      "loss": 0.4567,
      "step": 53440
    },
    {
      "epoch": 1.6416612908180506,
      "grad_norm": 0.39921650290489197,
      "learning_rate": 1.5476488136704593e-06,
      "loss": 0.4712,
      "step": 53441
    },
    {
      "epoch": 1.6416920099529997,
      "grad_norm": 0.3972609043121338,
      "learning_rate": 1.547390562739578e-06,
      "loss": 0.5094,
      "step": 53442
    },
    {
      "epoch": 1.6417227290879488,
      "grad_norm": 0.4296790361404419,
      "learning_rate": 1.5471323315503584e-06,
      "loss": 0.4979,
      "step": 53443
    },
    {
      "epoch": 1.641753448222898,
      "grad_norm": 0.39028435945510864,
      "learning_rate": 1.5468741201034e-06,
      "loss": 0.4262,
      "step": 53444
    },
    {
      "epoch": 1.641784167357847,
      "grad_norm": 0.45775115489959717,
      "learning_rate": 1.5466159283993065e-06,
      "loss": 0.3823,
      "step": 53445
    },
    {
      "epoch": 1.6418148864927964,
      "grad_norm": 0.41474205255508423,
      "learning_rate": 1.5463577564386822e-06,
      "loss": 0.4666,
      "step": 53446
    },
    {
      "epoch": 1.6418456056277455,
      "grad_norm": 0.43955257534980774,
      "learning_rate": 1.5460996042221299e-06,
      "loss": 0.4412,
      "step": 53447
    },
    {
      "epoch": 1.6418763247626946,
      "grad_norm": 0.5314950942993164,
      "learning_rate": 1.5458414717502557e-06,
      "loss": 0.363,
      "step": 53448
    },
    {
      "epoch": 1.641907043897644,
      "grad_norm": 0.40183550119400024,
      "learning_rate": 1.5455833590236557e-06,
      "loss": 0.4446,
      "step": 53449
    },
    {
      "epoch": 1.641937763032593,
      "grad_norm": 0.4728781282901764,
      "learning_rate": 1.5453252660429363e-06,
      "loss": 0.5009,
      "step": 53450
    },
    {
      "epoch": 1.6419684821675422,
      "grad_norm": 0.48618200421333313,
      "learning_rate": 1.5450671928087003e-06,
      "loss": 0.4576,
      "step": 53451
    },
    {
      "epoch": 1.6419992013024913,
      "grad_norm": 0.46348559856414795,
      "learning_rate": 1.5448091393215526e-06,
      "loss": 0.4686,
      "step": 53452
    },
    {
      "epoch": 1.6420299204374404,
      "grad_norm": 0.45483073592185974,
      "learning_rate": 1.5445511055820916e-06,
      "loss": 0.4895,
      "step": 53453
    },
    {
      "epoch": 1.6420606395723896,
      "grad_norm": 0.44684815406799316,
      "learning_rate": 1.5442930915909215e-06,
      "loss": 0.3774,
      "step": 53454
    },
    {
      "epoch": 1.6420913587073387,
      "grad_norm": 0.5280557870864868,
      "learning_rate": 1.5440350973486463e-06,
      "loss": 0.5072,
      "step": 53455
    },
    {
      "epoch": 1.6421220778422878,
      "grad_norm": 0.4201555848121643,
      "learning_rate": 1.5437771228558696e-06,
      "loss": 0.4874,
      "step": 53456
    },
    {
      "epoch": 1.6421527969772372,
      "grad_norm": 0.41596588492393494,
      "learning_rate": 1.543519168113189e-06,
      "loss": 0.5133,
      "step": 53457
    },
    {
      "epoch": 1.6421835161121863,
      "grad_norm": 0.43449491262435913,
      "learning_rate": 1.5432612331212104e-06,
      "loss": 0.5204,
      "step": 53458
    },
    {
      "epoch": 1.6422142352471354,
      "grad_norm": 0.42129936814308167,
      "learning_rate": 1.543003317880536e-06,
      "loss": 0.4802,
      "step": 53459
    },
    {
      "epoch": 1.6422449543820847,
      "grad_norm": 0.4044349491596222,
      "learning_rate": 1.5427454223917704e-06,
      "loss": 0.4602,
      "step": 53460
    },
    {
      "epoch": 1.6422756735170339,
      "grad_norm": 0.42878296971321106,
      "learning_rate": 1.5424875466555112e-06,
      "loss": 0.4599,
      "step": 53461
    },
    {
      "epoch": 1.642306392651983,
      "grad_norm": 0.391408234834671,
      "learning_rate": 1.5422296906723633e-06,
      "loss": 0.502,
      "step": 53462
    },
    {
      "epoch": 1.642337111786932,
      "grad_norm": 0.42631226778030396,
      "learning_rate": 1.5419718544429275e-06,
      "loss": 0.4432,
      "step": 53463
    },
    {
      "epoch": 1.6423678309218812,
      "grad_norm": 0.41987279057502747,
      "learning_rate": 1.5417140379678086e-06,
      "loss": 0.4594,
      "step": 53464
    },
    {
      "epoch": 1.6423985500568303,
      "grad_norm": 0.44881895184516907,
      "learning_rate": 1.5414562412476087e-06,
      "loss": 0.4803,
      "step": 53465
    },
    {
      "epoch": 1.6424292691917795,
      "grad_norm": 0.43707019090652466,
      "learning_rate": 1.5411984642829258e-06,
      "loss": 0.4331,
      "step": 53466
    },
    {
      "epoch": 1.6424599883267286,
      "grad_norm": 0.4205598533153534,
      "learning_rate": 1.5409407070743654e-06,
      "loss": 0.4252,
      "step": 53467
    },
    {
      "epoch": 1.642490707461678,
      "grad_norm": 0.4650450050830841,
      "learning_rate": 1.5406829696225278e-06,
      "loss": 0.4823,
      "step": 53468
    },
    {
      "epoch": 1.642521426596627,
      "grad_norm": 0.45802727341651917,
      "learning_rate": 1.5404252519280194e-06,
      "loss": 0.4266,
      "step": 53469
    },
    {
      "epoch": 1.6425521457315762,
      "grad_norm": 0.4590885639190674,
      "learning_rate": 1.5401675539914362e-06,
      "loss": 0.5136,
      "step": 53470
    },
    {
      "epoch": 1.6425828648665255,
      "grad_norm": 0.4391750991344452,
      "learning_rate": 1.5399098758133846e-06,
      "loss": 0.4699,
      "step": 53471
    },
    {
      "epoch": 1.6426135840014746,
      "grad_norm": 0.4393724799156189,
      "learning_rate": 1.5396522173944595e-06,
      "loss": 0.4712,
      "step": 53472
    },
    {
      "epoch": 1.6426443031364237,
      "grad_norm": 0.4473000168800354,
      "learning_rate": 1.5393945787352715e-06,
      "loss": 0.4819,
      "step": 53473
    },
    {
      "epoch": 1.6426750222713729,
      "grad_norm": 0.4466298818588257,
      "learning_rate": 1.539136959836417e-06,
      "loss": 0.468,
      "step": 53474
    },
    {
      "epoch": 1.642705741406322,
      "grad_norm": 0.44303059577941895,
      "learning_rate": 1.538879360698501e-06,
      "loss": 0.5038,
      "step": 53475
    },
    {
      "epoch": 1.642736460541271,
      "grad_norm": 0.44589605927467346,
      "learning_rate": 1.5386217813221217e-06,
      "loss": 0.4563,
      "step": 53476
    },
    {
      "epoch": 1.6427671796762202,
      "grad_norm": 0.4353741705417633,
      "learning_rate": 1.538364221707881e-06,
      "loss": 0.4723,
      "step": 53477
    },
    {
      "epoch": 1.6427978988111693,
      "grad_norm": 0.44588157534599304,
      "learning_rate": 1.5381066818563816e-06,
      "loss": 0.4455,
      "step": 53478
    },
    {
      "epoch": 1.6428286179461187,
      "grad_norm": 0.39305955171585083,
      "learning_rate": 1.5378491617682278e-06,
      "loss": 0.4603,
      "step": 53479
    },
    {
      "epoch": 1.6428593370810678,
      "grad_norm": 0.39819657802581787,
      "learning_rate": 1.5375916614440168e-06,
      "loss": 0.4004,
      "step": 53480
    },
    {
      "epoch": 1.642890056216017,
      "grad_norm": 0.4432685077190399,
      "learning_rate": 1.53733418088435e-06,
      "loss": 0.506,
      "step": 53481
    },
    {
      "epoch": 1.6429207753509663,
      "grad_norm": 0.38394683599472046,
      "learning_rate": 1.5370767200898307e-06,
      "loss": 0.4372,
      "step": 53482
    },
    {
      "epoch": 1.6429514944859154,
      "grad_norm": 0.40245598554611206,
      "learning_rate": 1.5368192790610603e-06,
      "loss": 0.4518,
      "step": 53483
    },
    {
      "epoch": 1.6429822136208645,
      "grad_norm": 0.4277777373790741,
      "learning_rate": 1.5365618577986418e-06,
      "loss": 0.4352,
      "step": 53484
    },
    {
      "epoch": 1.6430129327558136,
      "grad_norm": 0.4553951621055603,
      "learning_rate": 1.5363044563031714e-06,
      "loss": 0.4584,
      "step": 53485
    },
    {
      "epoch": 1.6430436518907627,
      "grad_norm": 0.41964173316955566,
      "learning_rate": 1.5360470745752532e-06,
      "loss": 0.4561,
      "step": 53486
    },
    {
      "epoch": 1.6430743710257119,
      "grad_norm": 0.39975035190582275,
      "learning_rate": 1.5357897126154875e-06,
      "loss": 0.4646,
      "step": 53487
    },
    {
      "epoch": 1.643105090160661,
      "grad_norm": 0.41859012842178345,
      "learning_rate": 1.5355323704244796e-06,
      "loss": 0.4556,
      "step": 53488
    },
    {
      "epoch": 1.64313580929561,
      "grad_norm": 0.45073747634887695,
      "learning_rate": 1.5352750480028234e-06,
      "loss": 0.5103,
      "step": 53489
    },
    {
      "epoch": 1.6431665284305594,
      "grad_norm": 0.4960850179195404,
      "learning_rate": 1.535017745351124e-06,
      "loss": 0.4814,
      "step": 53490
    },
    {
      "epoch": 1.6431972475655086,
      "grad_norm": 0.4135546088218689,
      "learning_rate": 1.534760462469982e-06,
      "loss": 0.4595,
      "step": 53491
    },
    {
      "epoch": 1.6432279667004577,
      "grad_norm": 0.4088551104068756,
      "learning_rate": 1.5345031993600012e-06,
      "loss": 0.5357,
      "step": 53492
    },
    {
      "epoch": 1.643258685835407,
      "grad_norm": 0.42262759804725647,
      "learning_rate": 1.5342459560217759e-06,
      "loss": 0.4459,
      "step": 53493
    },
    {
      "epoch": 1.6432894049703561,
      "grad_norm": 0.4209209084510803,
      "learning_rate": 1.533988732455911e-06,
      "loss": 0.4496,
      "step": 53494
    },
    {
      "epoch": 1.6433201241053053,
      "grad_norm": 0.45688337087631226,
      "learning_rate": 1.5337315286630062e-06,
      "loss": 0.5026,
      "step": 53495
    },
    {
      "epoch": 1.6433508432402544,
      "grad_norm": 0.42013034224510193,
      "learning_rate": 1.5334743446436662e-06,
      "loss": 0.4444,
      "step": 53496
    },
    {
      "epoch": 1.6433815623752035,
      "grad_norm": 0.4409199655056,
      "learning_rate": 1.5332171803984842e-06,
      "loss": 0.5511,
      "step": 53497
    },
    {
      "epoch": 1.6434122815101526,
      "grad_norm": 0.43375930190086365,
      "learning_rate": 1.5329600359280683e-06,
      "loss": 0.4804,
      "step": 53498
    },
    {
      "epoch": 1.6434430006451017,
      "grad_norm": 0.41846194863319397,
      "learning_rate": 1.5327029112330105e-06,
      "loss": 0.4437,
      "step": 53499
    },
    {
      "epoch": 1.6434737197800509,
      "grad_norm": 0.4367220401763916,
      "learning_rate": 1.5324458063139213e-06,
      "loss": 0.4275,
      "step": 53500
    },
    {
      "epoch": 1.6435044389150002,
      "grad_norm": 0.43069443106651306,
      "learning_rate": 1.5321887211713937e-06,
      "loss": 0.5003,
      "step": 53501
    },
    {
      "epoch": 1.6435351580499493,
      "grad_norm": 0.42212018370628357,
      "learning_rate": 1.5319316558060305e-06,
      "loss": 0.4539,
      "step": 53502
    },
    {
      "epoch": 1.6435658771848984,
      "grad_norm": 0.4678937792778015,
      "learning_rate": 1.5316746102184332e-06,
      "loss": 0.4367,
      "step": 53503
    },
    {
      "epoch": 1.6435965963198478,
      "grad_norm": 0.41522181034088135,
      "learning_rate": 1.5314175844092005e-06,
      "loss": 0.5206,
      "step": 53504
    },
    {
      "epoch": 1.643627315454797,
      "grad_norm": 0.4089936912059784,
      "learning_rate": 1.5311605783789352e-06,
      "loss": 0.5692,
      "step": 53505
    },
    {
      "epoch": 1.643658034589746,
      "grad_norm": 0.43471866846084595,
      "learning_rate": 1.5309035921282346e-06,
      "loss": 0.4528,
      "step": 53506
    },
    {
      "epoch": 1.6436887537246951,
      "grad_norm": 0.4656062424182892,
      "learning_rate": 1.5306466256577023e-06,
      "loss": 0.5021,
      "step": 53507
    },
    {
      "epoch": 1.6437194728596443,
      "grad_norm": 0.46819305419921875,
      "learning_rate": 1.5303896789679317e-06,
      "loss": 0.4716,
      "step": 53508
    },
    {
      "epoch": 1.6437501919945934,
      "grad_norm": 0.428007036447525,
      "learning_rate": 1.5301327520595312e-06,
      "loss": 0.4765,
      "step": 53509
    },
    {
      "epoch": 1.6437809111295425,
      "grad_norm": 0.39835795760154724,
      "learning_rate": 1.5298758449330964e-06,
      "loss": 0.4554,
      "step": 53510
    },
    {
      "epoch": 1.6438116302644916,
      "grad_norm": 0.5243136286735535,
      "learning_rate": 1.5296189575892296e-06,
      "loss": 0.4591,
      "step": 53511
    },
    {
      "epoch": 1.643842349399441,
      "grad_norm": 0.476421982049942,
      "learning_rate": 1.5293620900285266e-06,
      "loss": 0.4488,
      "step": 53512
    },
    {
      "epoch": 1.64387306853439,
      "grad_norm": 0.4085891842842102,
      "learning_rate": 1.5291052422515907e-06,
      "loss": 0.5105,
      "step": 53513
    },
    {
      "epoch": 1.6439037876693392,
      "grad_norm": 0.5004994869232178,
      "learning_rate": 1.528848414259021e-06,
      "loss": 0.4687,
      "step": 53514
    },
    {
      "epoch": 1.6439345068042885,
      "grad_norm": 0.41349074244499207,
      "learning_rate": 1.5285916060514195e-06,
      "loss": 0.4197,
      "step": 53515
    },
    {
      "epoch": 1.6439652259392377,
      "grad_norm": 0.4177049398422241,
      "learning_rate": 1.528334817629381e-06,
      "loss": 0.4834,
      "step": 53516
    },
    {
      "epoch": 1.6439959450741868,
      "grad_norm": 0.4282076954841614,
      "learning_rate": 1.5280780489935087e-06,
      "loss": 0.4541,
      "step": 53517
    },
    {
      "epoch": 1.644026664209136,
      "grad_norm": 0.5208199620246887,
      "learning_rate": 1.527821300144402e-06,
      "loss": 0.5087,
      "step": 53518
    },
    {
      "epoch": 1.644057383344085,
      "grad_norm": 0.4437394142150879,
      "learning_rate": 1.5275645710826604e-06,
      "loss": 0.5193,
      "step": 53519
    },
    {
      "epoch": 1.6440881024790341,
      "grad_norm": 0.4385455250740051,
      "learning_rate": 1.5273078618088866e-06,
      "loss": 0.4047,
      "step": 53520
    },
    {
      "epoch": 1.6441188216139833,
      "grad_norm": 0.4671168625354767,
      "learning_rate": 1.5270511723236736e-06,
      "loss": 0.4538,
      "step": 53521
    },
    {
      "epoch": 1.6441495407489324,
      "grad_norm": 0.44613203406333923,
      "learning_rate": 1.5267945026276242e-06,
      "loss": 0.4961,
      "step": 53522
    },
    {
      "epoch": 1.6441802598838817,
      "grad_norm": 0.4405893385410309,
      "learning_rate": 1.5265378527213381e-06,
      "loss": 0.4563,
      "step": 53523
    },
    {
      "epoch": 1.6442109790188308,
      "grad_norm": 0.4544311463832855,
      "learning_rate": 1.526281222605418e-06,
      "loss": 0.4606,
      "step": 53524
    },
    {
      "epoch": 1.64424169815378,
      "grad_norm": 0.4136293828487396,
      "learning_rate": 1.5260246122804566e-06,
      "loss": 0.4907,
      "step": 53525
    },
    {
      "epoch": 1.6442724172887293,
      "grad_norm": 0.41815346479415894,
      "learning_rate": 1.5257680217470562e-06,
      "loss": 0.3753,
      "step": 53526
    },
    {
      "epoch": 1.6443031364236784,
      "grad_norm": 0.44704294204711914,
      "learning_rate": 1.5255114510058168e-06,
      "loss": 0.486,
      "step": 53527
    },
    {
      "epoch": 1.6443338555586275,
      "grad_norm": 0.4333735704421997,
      "learning_rate": 1.5252549000573402e-06,
      "loss": 0.4635,
      "step": 53528
    },
    {
      "epoch": 1.6443645746935767,
      "grad_norm": 0.575362503528595,
      "learning_rate": 1.5249983689022197e-06,
      "loss": 0.4682,
      "step": 53529
    },
    {
      "epoch": 1.6443952938285258,
      "grad_norm": 0.4344821870326996,
      "learning_rate": 1.5247418575410576e-06,
      "loss": 0.4547,
      "step": 53530
    },
    {
      "epoch": 1.644426012963475,
      "grad_norm": 0.4803514778614044,
      "learning_rate": 1.5244853659744529e-06,
      "loss": 0.4923,
      "step": 53531
    },
    {
      "epoch": 1.644456732098424,
      "grad_norm": 0.4178963601589203,
      "learning_rate": 1.524228894203006e-06,
      "loss": 0.5129,
      "step": 53532
    },
    {
      "epoch": 1.6444874512333731,
      "grad_norm": 0.4298155903816223,
      "learning_rate": 1.5239724422273129e-06,
      "loss": 0.5086,
      "step": 53533
    },
    {
      "epoch": 1.6445181703683223,
      "grad_norm": 0.42444711923599243,
      "learning_rate": 1.5237160100479763e-06,
      "loss": 0.4518,
      "step": 53534
    },
    {
      "epoch": 1.6445488895032716,
      "grad_norm": 0.4197878837585449,
      "learning_rate": 1.5234595976655885e-06,
      "loss": 0.5447,
      "step": 53535
    },
    {
      "epoch": 1.6445796086382207,
      "grad_norm": 0.4280676245689392,
      "learning_rate": 1.5232032050807578e-06,
      "loss": 0.4582,
      "step": 53536
    },
    {
      "epoch": 1.64461032777317,
      "grad_norm": 0.4334915578365326,
      "learning_rate": 1.5229468322940743e-06,
      "loss": 0.4533,
      "step": 53537
    },
    {
      "epoch": 1.6446410469081192,
      "grad_norm": 0.4015209674835205,
      "learning_rate": 1.5226904793061413e-06,
      "loss": 0.4852,
      "step": 53538
    },
    {
      "epoch": 1.6446717660430683,
      "grad_norm": 0.44333651661872864,
      "learning_rate": 1.5224341461175595e-06,
      "loss": 0.4475,
      "step": 53539
    },
    {
      "epoch": 1.6447024851780174,
      "grad_norm": 0.4538489580154419,
      "learning_rate": 1.5221778327289204e-06,
      "loss": 0.4795,
      "step": 53540
    },
    {
      "epoch": 1.6447332043129665,
      "grad_norm": 0.40056073665618896,
      "learning_rate": 1.5219215391408303e-06,
      "loss": 0.4537,
      "step": 53541
    },
    {
      "epoch": 1.6447639234479157,
      "grad_norm": 0.46479731798171997,
      "learning_rate": 1.5216652653538832e-06,
      "loss": 0.4374,
      "step": 53542
    },
    {
      "epoch": 1.6447946425828648,
      "grad_norm": 0.4329915940761566,
      "learning_rate": 1.5214090113686818e-06,
      "loss": 0.4295,
      "step": 53543
    },
    {
      "epoch": 1.644825361717814,
      "grad_norm": 0.45207494497299194,
      "learning_rate": 1.5211527771858158e-06,
      "loss": 0.4789,
      "step": 53544
    },
    {
      "epoch": 1.644856080852763,
      "grad_norm": 0.46368515491485596,
      "learning_rate": 1.5208965628058959e-06,
      "loss": 0.3703,
      "step": 53545
    },
    {
      "epoch": 1.6448867999877124,
      "grad_norm": 0.42406174540519714,
      "learning_rate": 1.5206403682295112e-06,
      "loss": 0.4792,
      "step": 53546
    },
    {
      "epoch": 1.6449175191226615,
      "grad_norm": 0.4327995479106903,
      "learning_rate": 1.520384193457265e-06,
      "loss": 0.4389,
      "step": 53547
    },
    {
      "epoch": 1.6449482382576108,
      "grad_norm": 0.43455350399017334,
      "learning_rate": 1.520128038489752e-06,
      "loss": 0.3939,
      "step": 53548
    },
    {
      "epoch": 1.64497895739256,
      "grad_norm": 0.4576190114021301,
      "learning_rate": 1.519871903327571e-06,
      "loss": 0.4807,
      "step": 53549
    },
    {
      "epoch": 1.645009676527509,
      "grad_norm": 0.4814096689224243,
      "learning_rate": 1.5196157879713226e-06,
      "loss": 0.5004,
      "step": 53550
    },
    {
      "epoch": 1.6450403956624582,
      "grad_norm": 0.4117593467235565,
      "learning_rate": 1.519359692421606e-06,
      "loss": 0.4258,
      "step": 53551
    },
    {
      "epoch": 1.6450711147974073,
      "grad_norm": 0.4885745346546173,
      "learning_rate": 1.519103616679014e-06,
      "loss": 0.4843,
      "step": 53552
    },
    {
      "epoch": 1.6451018339323564,
      "grad_norm": 0.4816727042198181,
      "learning_rate": 1.5188475607441488e-06,
      "loss": 0.454,
      "step": 53553
    },
    {
      "epoch": 1.6451325530673055,
      "grad_norm": 0.41069653630256653,
      "learning_rate": 1.5185915246176074e-06,
      "loss": 0.4397,
      "step": 53554
    },
    {
      "epoch": 1.6451632722022547,
      "grad_norm": 0.43306228518486023,
      "learning_rate": 1.5183355082999873e-06,
      "loss": 0.4024,
      "step": 53555
    },
    {
      "epoch": 1.6451939913372038,
      "grad_norm": 0.4349060356616974,
      "learning_rate": 1.518079511791889e-06,
      "loss": 0.3748,
      "step": 53556
    },
    {
      "epoch": 1.6452247104721531,
      "grad_norm": 0.45326799154281616,
      "learning_rate": 1.5178235350939074e-06,
      "loss": 0.4833,
      "step": 53557
    },
    {
      "epoch": 1.6452554296071022,
      "grad_norm": 0.4586000144481659,
      "learning_rate": 1.51756757820664e-06,
      "loss": 0.4722,
      "step": 53558
    },
    {
      "epoch": 1.6452861487420514,
      "grad_norm": 0.5556653141975403,
      "learning_rate": 1.5173116411306864e-06,
      "loss": 0.462,
      "step": 53559
    },
    {
      "epoch": 1.6453168678770007,
      "grad_norm": 0.41867077350616455,
      "learning_rate": 1.517055723866646e-06,
      "loss": 0.4289,
      "step": 53560
    },
    {
      "epoch": 1.6453475870119498,
      "grad_norm": 0.4432627260684967,
      "learning_rate": 1.5167998264151129e-06,
      "loss": 0.4081,
      "step": 53561
    },
    {
      "epoch": 1.645378306146899,
      "grad_norm": 0.4553566575050354,
      "learning_rate": 1.5165439487766854e-06,
      "loss": 0.4599,
      "step": 53562
    },
    {
      "epoch": 1.645409025281848,
      "grad_norm": 0.48467057943344116,
      "learning_rate": 1.5162880909519617e-06,
      "loss": 0.4134,
      "step": 53563
    },
    {
      "epoch": 1.6454397444167972,
      "grad_norm": 0.4692661166191101,
      "learning_rate": 1.5160322529415428e-06,
      "loss": 0.5352,
      "step": 53564
    },
    {
      "epoch": 1.6454704635517463,
      "grad_norm": 0.4217812716960907,
      "learning_rate": 1.5157764347460203e-06,
      "loss": 0.4641,
      "step": 53565
    },
    {
      "epoch": 1.6455011826866954,
      "grad_norm": 0.3994724154472351,
      "learning_rate": 1.5155206363659947e-06,
      "loss": 0.4228,
      "step": 53566
    },
    {
      "epoch": 1.6455319018216445,
      "grad_norm": 0.4355028569698334,
      "learning_rate": 1.5152648578020634e-06,
      "loss": 0.5228,
      "step": 53567
    },
    {
      "epoch": 1.645562620956594,
      "grad_norm": 0.45496878027915955,
      "learning_rate": 1.515009099054825e-06,
      "loss": 0.519,
      "step": 53568
    },
    {
      "epoch": 1.645593340091543,
      "grad_norm": 0.45158183574676514,
      "learning_rate": 1.5147533601248744e-06,
      "loss": 0.5586,
      "step": 53569
    },
    {
      "epoch": 1.6456240592264921,
      "grad_norm": 0.42968329787254333,
      "learning_rate": 1.514497641012811e-06,
      "loss": 0.4262,
      "step": 53570
    },
    {
      "epoch": 1.6456547783614415,
      "grad_norm": 0.43727222084999084,
      "learning_rate": 1.5142419417192267e-06,
      "loss": 0.4372,
      "step": 53571
    },
    {
      "epoch": 1.6456854974963906,
      "grad_norm": 0.42696207761764526,
      "learning_rate": 1.5139862622447287e-06,
      "loss": 0.444,
      "step": 53572
    },
    {
      "epoch": 1.6457162166313397,
      "grad_norm": 0.42845097184181213,
      "learning_rate": 1.5137306025899045e-06,
      "loss": 0.4557,
      "step": 53573
    },
    {
      "epoch": 1.6457469357662888,
      "grad_norm": 0.44027256965637207,
      "learning_rate": 1.5134749627553569e-06,
      "loss": 0.4702,
      "step": 53574
    },
    {
      "epoch": 1.645777654901238,
      "grad_norm": 0.41732797026634216,
      "learning_rate": 1.513219342741682e-06,
      "loss": 0.4922,
      "step": 53575
    },
    {
      "epoch": 1.645808374036187,
      "grad_norm": 0.4396650493144989,
      "learning_rate": 1.5129637425494725e-06,
      "loss": 0.4934,
      "step": 53576
    },
    {
      "epoch": 1.6458390931711362,
      "grad_norm": 0.4062022864818573,
      "learning_rate": 1.5127081621793327e-06,
      "loss": 0.4436,
      "step": 53577
    },
    {
      "epoch": 1.6458698123060853,
      "grad_norm": 0.41286200284957886,
      "learning_rate": 1.512452601631853e-06,
      "loss": 0.4237,
      "step": 53578
    },
    {
      "epoch": 1.6459005314410347,
      "grad_norm": 0.46423235535621643,
      "learning_rate": 1.5121970609076365e-06,
      "loss": 0.463,
      "step": 53579
    },
    {
      "epoch": 1.6459312505759838,
      "grad_norm": 0.46236810088157654,
      "learning_rate": 1.5119415400072735e-06,
      "loss": 0.4475,
      "step": 53580
    },
    {
      "epoch": 1.645961969710933,
      "grad_norm": 0.41690054535865784,
      "learning_rate": 1.5116860389313649e-06,
      "loss": 0.575,
      "step": 53581
    },
    {
      "epoch": 1.6459926888458822,
      "grad_norm": 0.46884989738464355,
      "learning_rate": 1.5114305576805055e-06,
      "loss": 0.5193,
      "step": 53582
    },
    {
      "epoch": 1.6460234079808314,
      "grad_norm": 0.43223729729652405,
      "learning_rate": 1.5111750962552952e-06,
      "loss": 0.4792,
      "step": 53583
    },
    {
      "epoch": 1.6460541271157805,
      "grad_norm": 0.4265197813510895,
      "learning_rate": 1.5109196546563253e-06,
      "loss": 0.3613,
      "step": 53584
    },
    {
      "epoch": 1.6460848462507296,
      "grad_norm": 0.39930278062820435,
      "learning_rate": 1.510664232884197e-06,
      "loss": 0.5087,
      "step": 53585
    },
    {
      "epoch": 1.6461155653856787,
      "grad_norm": 0.4276380240917206,
      "learning_rate": 1.5104088309395038e-06,
      "loss": 0.4933,
      "step": 53586
    },
    {
      "epoch": 1.6461462845206278,
      "grad_norm": 0.379181444644928,
      "learning_rate": 1.5101534488228475e-06,
      "loss": 0.4097,
      "step": 53587
    },
    {
      "epoch": 1.646177003655577,
      "grad_norm": 0.4268634021282196,
      "learning_rate": 1.5098980865348168e-06,
      "loss": 0.4142,
      "step": 53588
    },
    {
      "epoch": 1.646207722790526,
      "grad_norm": 0.4704084098339081,
      "learning_rate": 1.5096427440760131e-06,
      "loss": 0.4654,
      "step": 53589
    },
    {
      "epoch": 1.6462384419254754,
      "grad_norm": 0.4159131944179535,
      "learning_rate": 1.5093874214470317e-06,
      "loss": 0.4681,
      "step": 53590
    },
    {
      "epoch": 1.6462691610604245,
      "grad_norm": 0.4359181225299835,
      "learning_rate": 1.5091321186484708e-06,
      "loss": 0.4095,
      "step": 53591
    },
    {
      "epoch": 1.6462998801953737,
      "grad_norm": 0.6224238276481628,
      "learning_rate": 1.5088768356809224e-06,
      "loss": 0.5183,
      "step": 53592
    },
    {
      "epoch": 1.646330599330323,
      "grad_norm": 0.4176895022392273,
      "learning_rate": 1.508621572544986e-06,
      "loss": 0.4557,
      "step": 53593
    },
    {
      "epoch": 1.6463613184652721,
      "grad_norm": 0.43862926959991455,
      "learning_rate": 1.5083663292412566e-06,
      "loss": 0.4835,
      "step": 53594
    },
    {
      "epoch": 1.6463920376002212,
      "grad_norm": 0.41350728273391724,
      "learning_rate": 1.5081111057703303e-06,
      "loss": 0.5289,
      "step": 53595
    },
    {
      "epoch": 1.6464227567351704,
      "grad_norm": 0.39017894864082336,
      "learning_rate": 1.5078559021328066e-06,
      "loss": 0.4507,
      "step": 53596
    },
    {
      "epoch": 1.6464534758701195,
      "grad_norm": 0.4369960427284241,
      "learning_rate": 1.5076007183292752e-06,
      "loss": 0.5155,
      "step": 53597
    },
    {
      "epoch": 1.6464841950050686,
      "grad_norm": 0.44079530239105225,
      "learning_rate": 1.5073455543603365e-06,
      "loss": 0.4323,
      "step": 53598
    },
    {
      "epoch": 1.6465149141400177,
      "grad_norm": 0.476401150226593,
      "learning_rate": 1.5070904102265848e-06,
      "loss": 0.4309,
      "step": 53599
    },
    {
      "epoch": 1.6465456332749668,
      "grad_norm": 0.43872562050819397,
      "learning_rate": 1.5068352859286184e-06,
      "loss": 0.4967,
      "step": 53600
    },
    {
      "epoch": 1.6465763524099162,
      "grad_norm": 0.43080127239227295,
      "learning_rate": 1.50658018146703e-06,
      "loss": 0.4264,
      "step": 53601
    },
    {
      "epoch": 1.6466070715448653,
      "grad_norm": 0.45450839400291443,
      "learning_rate": 1.5063250968424192e-06,
      "loss": 0.4577,
      "step": 53602
    },
    {
      "epoch": 1.6466377906798144,
      "grad_norm": 0.44152817130088806,
      "learning_rate": 1.5060700320553733e-06,
      "loss": 0.5311,
      "step": 53603
    },
    {
      "epoch": 1.6466685098147638,
      "grad_norm": 0.44203129410743713,
      "learning_rate": 1.5058149871064997e-06,
      "loss": 0.506,
      "step": 53604
    },
    {
      "epoch": 1.6466992289497129,
      "grad_norm": 0.45152345299720764,
      "learning_rate": 1.5055599619963868e-06,
      "loss": 0.465,
      "step": 53605
    },
    {
      "epoch": 1.646729948084662,
      "grad_norm": 0.47764700651168823,
      "learning_rate": 1.5053049567256328e-06,
      "loss": 0.3978,
      "step": 53606
    },
    {
      "epoch": 1.6467606672196111,
      "grad_norm": 0.4206259548664093,
      "learning_rate": 1.5050499712948286e-06,
      "loss": 0.4628,
      "step": 53607
    },
    {
      "epoch": 1.6467913863545602,
      "grad_norm": 0.39228591322898865,
      "learning_rate": 1.5047950057045778e-06,
      "loss": 0.5271,
      "step": 53608
    },
    {
      "epoch": 1.6468221054895094,
      "grad_norm": 0.4239753484725952,
      "learning_rate": 1.5045400599554683e-06,
      "loss": 0.4614,
      "step": 53609
    },
    {
      "epoch": 1.6468528246244585,
      "grad_norm": 0.45124536752700806,
      "learning_rate": 1.5042851340481003e-06,
      "loss": 0.5161,
      "step": 53610
    },
    {
      "epoch": 1.6468835437594076,
      "grad_norm": 0.41357630491256714,
      "learning_rate": 1.5040302279830698e-06,
      "loss": 0.4387,
      "step": 53611
    },
    {
      "epoch": 1.646914262894357,
      "grad_norm": 0.4304549992084503,
      "learning_rate": 1.5037753417609646e-06,
      "loss": 0.4529,
      "step": 53612
    },
    {
      "epoch": 1.646944982029306,
      "grad_norm": 0.3979763984680176,
      "learning_rate": 1.5035204753823906e-06,
      "loss": 0.5066,
      "step": 53613
    },
    {
      "epoch": 1.6469757011642552,
      "grad_norm": 0.4155336022377014,
      "learning_rate": 1.5032656288479352e-06,
      "loss": 0.4211,
      "step": 53614
    },
    {
      "epoch": 1.6470064202992045,
      "grad_norm": 0.42174023389816284,
      "learning_rate": 1.5030108021581991e-06,
      "loss": 0.52,
      "step": 53615
    },
    {
      "epoch": 1.6470371394341536,
      "grad_norm": 0.4006054997444153,
      "learning_rate": 1.5027559953137727e-06,
      "loss": 0.3819,
      "step": 53616
    },
    {
      "epoch": 1.6470678585691028,
      "grad_norm": 0.48446857929229736,
      "learning_rate": 1.5025012083152523e-06,
      "loss": 0.3759,
      "step": 53617
    },
    {
      "epoch": 1.6470985777040519,
      "grad_norm": 0.4354941248893738,
      "learning_rate": 1.5022464411632343e-06,
      "loss": 0.4324,
      "step": 53618
    },
    {
      "epoch": 1.647129296839001,
      "grad_norm": 0.4798146188259125,
      "learning_rate": 1.5019916938583157e-06,
      "loss": 0.4491,
      "step": 53619
    },
    {
      "epoch": 1.6471600159739501,
      "grad_norm": 0.4466705322265625,
      "learning_rate": 1.5017369664010862e-06,
      "loss": 0.4841,
      "step": 53620
    },
    {
      "epoch": 1.6471907351088992,
      "grad_norm": 0.4302944242954254,
      "learning_rate": 1.5014822587921428e-06,
      "loss": 0.4224,
      "step": 53621
    },
    {
      "epoch": 1.6472214542438484,
      "grad_norm": 0.42137396335601807,
      "learning_rate": 1.5012275710320823e-06,
      "loss": 0.4347,
      "step": 53622
    },
    {
      "epoch": 1.6472521733787977,
      "grad_norm": 0.44488978385925293,
      "learning_rate": 1.5009729031215003e-06,
      "loss": 0.4144,
      "step": 53623
    },
    {
      "epoch": 1.6472828925137468,
      "grad_norm": 0.5496071577072144,
      "learning_rate": 1.5007182550609878e-06,
      "loss": 0.5097,
      "step": 53624
    },
    {
      "epoch": 1.647313611648696,
      "grad_norm": 0.4123118817806244,
      "learning_rate": 1.5004636268511407e-06,
      "loss": 0.4749,
      "step": 53625
    },
    {
      "epoch": 1.6473443307836453,
      "grad_norm": 0.4943453073501587,
      "learning_rate": 1.5002090184925555e-06,
      "loss": 0.387,
      "step": 53626
    },
    {
      "epoch": 1.6473750499185944,
      "grad_norm": 0.4937814176082611,
      "learning_rate": 1.4999544299858271e-06,
      "loss": 0.5349,
      "step": 53627
    },
    {
      "epoch": 1.6474057690535435,
      "grad_norm": 0.4879758358001709,
      "learning_rate": 1.499699861331546e-06,
      "loss": 0.4213,
      "step": 53628
    },
    {
      "epoch": 1.6474364881884926,
      "grad_norm": 0.4404401183128357,
      "learning_rate": 1.4994453125303098e-06,
      "loss": 0.5213,
      "step": 53629
    },
    {
      "epoch": 1.6474672073234418,
      "grad_norm": 0.4000239372253418,
      "learning_rate": 1.4991907835827135e-06,
      "loss": 0.4403,
      "step": 53630
    },
    {
      "epoch": 1.6474979264583909,
      "grad_norm": 0.42665886878967285,
      "learning_rate": 1.4989362744893509e-06,
      "loss": 0.4433,
      "step": 53631
    },
    {
      "epoch": 1.64752864559334,
      "grad_norm": 0.44156205654144287,
      "learning_rate": 1.4986817852508184e-06,
      "loss": 0.5571,
      "step": 53632
    },
    {
      "epoch": 1.6475593647282891,
      "grad_norm": 0.4246461093425751,
      "learning_rate": 1.4984273158677054e-06,
      "loss": 0.4615,
      "step": 53633
    },
    {
      "epoch": 1.6475900838632385,
      "grad_norm": 0.5578051805496216,
      "learning_rate": 1.4981728663406093e-06,
      "loss": 0.4527,
      "step": 53634
    },
    {
      "epoch": 1.6476208029981876,
      "grad_norm": 0.41984865069389343,
      "learning_rate": 1.4979184366701249e-06,
      "loss": 0.4869,
      "step": 53635
    },
    {
      "epoch": 1.6476515221331367,
      "grad_norm": 0.42082908749580383,
      "learning_rate": 1.4976640268568475e-06,
      "loss": 0.4676,
      "step": 53636
    },
    {
      "epoch": 1.647682241268086,
      "grad_norm": 0.4191032350063324,
      "learning_rate": 1.4974096369013668e-06,
      "loss": 0.4208,
      "step": 53637
    },
    {
      "epoch": 1.6477129604030352,
      "grad_norm": 0.5553865432739258,
      "learning_rate": 1.4971552668042832e-06,
      "loss": 0.4559,
      "step": 53638
    },
    {
      "epoch": 1.6477436795379843,
      "grad_norm": 0.4255698323249817,
      "learning_rate": 1.4969009165661818e-06,
      "loss": 0.4787,
      "step": 53639
    },
    {
      "epoch": 1.6477743986729334,
      "grad_norm": 0.40893226861953735,
      "learning_rate": 1.4966465861876667e-06,
      "loss": 0.4805,
      "step": 53640
    },
    {
      "epoch": 1.6478051178078825,
      "grad_norm": 0.4247312843799591,
      "learning_rate": 1.496392275669326e-06,
      "loss": 0.5105,
      "step": 53641
    },
    {
      "epoch": 1.6478358369428316,
      "grad_norm": 0.42670437693595886,
      "learning_rate": 1.4961379850117564e-06,
      "loss": 0.4648,
      "step": 53642
    },
    {
      "epoch": 1.6478665560777808,
      "grad_norm": 0.5595929622650146,
      "learning_rate": 1.495883714215549e-06,
      "loss": 0.4355,
      "step": 53643
    },
    {
      "epoch": 1.6478972752127299,
      "grad_norm": 0.4961565434932709,
      "learning_rate": 1.4956294632812983e-06,
      "loss": 0.4586,
      "step": 53644
    },
    {
      "epoch": 1.647927994347679,
      "grad_norm": 0.4421859085559845,
      "learning_rate": 1.4953752322095994e-06,
      "loss": 0.5102,
      "step": 53645
    },
    {
      "epoch": 1.6479587134826283,
      "grad_norm": 0.4526959955692291,
      "learning_rate": 1.495121021001047e-06,
      "loss": 0.4735,
      "step": 53646
    },
    {
      "epoch": 1.6479894326175775,
      "grad_norm": 0.39583703875541687,
      "learning_rate": 1.494866829656232e-06,
      "loss": 0.4958,
      "step": 53647
    },
    {
      "epoch": 1.6480201517525268,
      "grad_norm": 0.4096812307834625,
      "learning_rate": 1.4946126581757469e-06,
      "loss": 0.4203,
      "step": 53648
    },
    {
      "epoch": 1.648050870887476,
      "grad_norm": 0.4567881226539612,
      "learning_rate": 1.494358506560193e-06,
      "loss": 0.4612,
      "step": 53649
    },
    {
      "epoch": 1.648081590022425,
      "grad_norm": 0.41866394877433777,
      "learning_rate": 1.494104374810157e-06,
      "loss": 0.4744,
      "step": 53650
    },
    {
      "epoch": 1.6481123091573742,
      "grad_norm": 0.6855870485305786,
      "learning_rate": 1.4938502629262352e-06,
      "loss": 0.4571,
      "step": 53651
    },
    {
      "epoch": 1.6481430282923233,
      "grad_norm": 0.45146384835243225,
      "learning_rate": 1.4935961709090185e-06,
      "loss": 0.5003,
      "step": 53652
    },
    {
      "epoch": 1.6481737474272724,
      "grad_norm": 0.42582300305366516,
      "learning_rate": 1.4933420987591018e-06,
      "loss": 0.4771,
      "step": 53653
    },
    {
      "epoch": 1.6482044665622215,
      "grad_norm": 0.41797006130218506,
      "learning_rate": 1.4930880464770792e-06,
      "loss": 0.4664,
      "step": 53654
    },
    {
      "epoch": 1.6482351856971706,
      "grad_norm": 0.4511758089065552,
      "learning_rate": 1.4928340140635455e-06,
      "loss": 0.453,
      "step": 53655
    },
    {
      "epoch": 1.6482659048321198,
      "grad_norm": 0.4264747202396393,
      "learning_rate": 1.4925800015190905e-06,
      "loss": 0.4933,
      "step": 53656
    },
    {
      "epoch": 1.648296623967069,
      "grad_norm": 0.4112662374973297,
      "learning_rate": 1.492326008844308e-06,
      "loss": 0.4258,
      "step": 53657
    },
    {
      "epoch": 1.6483273431020182,
      "grad_norm": 0.4198136627674103,
      "learning_rate": 1.4920720360397922e-06,
      "loss": 0.436,
      "step": 53658
    },
    {
      "epoch": 1.6483580622369676,
      "grad_norm": 0.46254387497901917,
      "learning_rate": 1.4918180831061401e-06,
      "loss": 0.502,
      "step": 53659
    },
    {
      "epoch": 1.6483887813719167,
      "grad_norm": 0.38186874985694885,
      "learning_rate": 1.491564150043937e-06,
      "loss": 0.3859,
      "step": 53660
    },
    {
      "epoch": 1.6484195005068658,
      "grad_norm": 0.39664244651794434,
      "learning_rate": 1.4913102368537814e-06,
      "loss": 0.4675,
      "step": 53661
    },
    {
      "epoch": 1.648450219641815,
      "grad_norm": 0.43643781542778015,
      "learning_rate": 1.4910563435362645e-06,
      "loss": 0.4696,
      "step": 53662
    },
    {
      "epoch": 1.648480938776764,
      "grad_norm": 0.46665653586387634,
      "learning_rate": 1.4908024700919821e-06,
      "loss": 0.4259,
      "step": 53663
    },
    {
      "epoch": 1.6485116579117132,
      "grad_norm": 0.45574039220809937,
      "learning_rate": 1.4905486165215221e-06,
      "loss": 0.5176,
      "step": 53664
    },
    {
      "epoch": 1.6485423770466623,
      "grad_norm": 0.4491417109966278,
      "learning_rate": 1.4902947828254811e-06,
      "loss": 0.4887,
      "step": 53665
    },
    {
      "epoch": 1.6485730961816114,
      "grad_norm": 0.4208679497241974,
      "learning_rate": 1.4900409690044503e-06,
      "loss": 0.4462,
      "step": 53666
    },
    {
      "epoch": 1.6486038153165605,
      "grad_norm": 0.450387567281723,
      "learning_rate": 1.4897871750590232e-06,
      "loss": 0.5126,
      "step": 53667
    },
    {
      "epoch": 1.6486345344515099,
      "grad_norm": 0.44866400957107544,
      "learning_rate": 1.4895334009897943e-06,
      "loss": 0.4667,
      "step": 53668
    },
    {
      "epoch": 1.648665253586459,
      "grad_norm": 0.4251924157142639,
      "learning_rate": 1.4892796467973525e-06,
      "loss": 0.4772,
      "step": 53669
    },
    {
      "epoch": 1.6486959727214083,
      "grad_norm": 0.4349713921546936,
      "learning_rate": 1.4890259124822925e-06,
      "loss": 0.4108,
      "step": 53670
    },
    {
      "epoch": 1.6487266918563575,
      "grad_norm": 0.43154650926589966,
      "learning_rate": 1.4887721980452074e-06,
      "loss": 0.4398,
      "step": 53671
    },
    {
      "epoch": 1.6487574109913066,
      "grad_norm": 0.44314876198768616,
      "learning_rate": 1.488518503486691e-06,
      "loss": 0.49,
      "step": 53672
    },
    {
      "epoch": 1.6487881301262557,
      "grad_norm": 0.4315762221813202,
      "learning_rate": 1.488264828807332e-06,
      "loss": 0.3898,
      "step": 53673
    },
    {
      "epoch": 1.6488188492612048,
      "grad_norm": 0.43637964129447937,
      "learning_rate": 1.4880111740077273e-06,
      "loss": 0.4936,
      "step": 53674
    },
    {
      "epoch": 1.648849568396154,
      "grad_norm": 0.43113720417022705,
      "learning_rate": 1.4877575390884624e-06,
      "loss": 0.4563,
      "step": 53675
    },
    {
      "epoch": 1.648880287531103,
      "grad_norm": 0.47415414452552795,
      "learning_rate": 1.4875039240501388e-06,
      "loss": 0.465,
      "step": 53676
    },
    {
      "epoch": 1.6489110066660522,
      "grad_norm": 0.4485257565975189,
      "learning_rate": 1.4872503288933415e-06,
      "loss": 0.4443,
      "step": 53677
    },
    {
      "epoch": 1.6489417258010013,
      "grad_norm": 0.4727950394153595,
      "learning_rate": 1.486996753618668e-06,
      "loss": 0.4279,
      "step": 53678
    },
    {
      "epoch": 1.6489724449359506,
      "grad_norm": 0.6845833659172058,
      "learning_rate": 1.4867431982267066e-06,
      "loss": 0.5629,
      "step": 53679
    },
    {
      "epoch": 1.6490031640708998,
      "grad_norm": 0.4112362861633301,
      "learning_rate": 1.4864896627180502e-06,
      "loss": 0.4725,
      "step": 53680
    },
    {
      "epoch": 1.6490338832058489,
      "grad_norm": 0.44680944085121155,
      "learning_rate": 1.4862361470932928e-06,
      "loss": 0.4749,
      "step": 53681
    },
    {
      "epoch": 1.6490646023407982,
      "grad_norm": 0.4184660315513611,
      "learning_rate": 1.4859826513530263e-06,
      "loss": 0.4909,
      "step": 53682
    },
    {
      "epoch": 1.6490953214757473,
      "grad_norm": 0.43066710233688354,
      "learning_rate": 1.485729175497841e-06,
      "loss": 0.3702,
      "step": 53683
    },
    {
      "epoch": 1.6491260406106965,
      "grad_norm": 0.5600410103797913,
      "learning_rate": 1.4854757195283266e-06,
      "loss": 0.4492,
      "step": 53684
    },
    {
      "epoch": 1.6491567597456456,
      "grad_norm": 0.44763273000717163,
      "learning_rate": 1.4852222834450837e-06,
      "loss": 0.4956,
      "step": 53685
    },
    {
      "epoch": 1.6491874788805947,
      "grad_norm": 0.47705066204071045,
      "learning_rate": 1.484968867248696e-06,
      "loss": 0.5081,
      "step": 53686
    },
    {
      "epoch": 1.6492181980155438,
      "grad_norm": 0.44143542647361755,
      "learning_rate": 1.4847154709397603e-06,
      "loss": 0.4413,
      "step": 53687
    },
    {
      "epoch": 1.649248917150493,
      "grad_norm": 0.46996843814849854,
      "learning_rate": 1.4844620945188647e-06,
      "loss": 0.4897,
      "step": 53688
    },
    {
      "epoch": 1.649279636285442,
      "grad_norm": 0.4239327907562256,
      "learning_rate": 1.4842087379866021e-06,
      "loss": 0.4433,
      "step": 53689
    },
    {
      "epoch": 1.6493103554203914,
      "grad_norm": 0.4677022397518158,
      "learning_rate": 1.4839554013435642e-06,
      "loss": 0.526,
      "step": 53690
    },
    {
      "epoch": 1.6493410745553405,
      "grad_norm": 0.4352058470249176,
      "learning_rate": 1.483702084590346e-06,
      "loss": 0.4172,
      "step": 53691
    },
    {
      "epoch": 1.6493717936902896,
      "grad_norm": 0.4454749524593353,
      "learning_rate": 1.483448787727535e-06,
      "loss": 0.4184,
      "step": 53692
    },
    {
      "epoch": 1.649402512825239,
      "grad_norm": 0.441481351852417,
      "learning_rate": 1.4831955107557229e-06,
      "loss": 0.4688,
      "step": 53693
    },
    {
      "epoch": 1.649433231960188,
      "grad_norm": 0.42927107214927673,
      "learning_rate": 1.4829422536755034e-06,
      "loss": 0.4256,
      "step": 53694
    },
    {
      "epoch": 1.6494639510951372,
      "grad_norm": 0.3965197503566742,
      "learning_rate": 1.4826890164874685e-06,
      "loss": 0.4856,
      "step": 53695
    },
    {
      "epoch": 1.6494946702300863,
      "grad_norm": 0.4512413740158081,
      "learning_rate": 1.4824357991922067e-06,
      "loss": 0.4546,
      "step": 53696
    },
    {
      "epoch": 1.6495253893650355,
      "grad_norm": 0.4647045433521271,
      "learning_rate": 1.4821826017903106e-06,
      "loss": 0.4833,
      "step": 53697
    },
    {
      "epoch": 1.6495561084999846,
      "grad_norm": 0.49477115273475647,
      "learning_rate": 1.481929424282371e-06,
      "loss": 0.4543,
      "step": 53698
    },
    {
      "epoch": 1.6495868276349337,
      "grad_norm": 0.43220263719558716,
      "learning_rate": 1.4816762666689843e-06,
      "loss": 0.4914,
      "step": 53699
    },
    {
      "epoch": 1.6496175467698828,
      "grad_norm": 0.43423306941986084,
      "learning_rate": 1.481423128950734e-06,
      "loss": 0.487,
      "step": 53700
    },
    {
      "epoch": 1.6496482659048322,
      "grad_norm": 0.4420461058616638,
      "learning_rate": 1.4811700111282146e-06,
      "loss": 0.463,
      "step": 53701
    },
    {
      "epoch": 1.6496789850397813,
      "grad_norm": 0.44087547063827515,
      "learning_rate": 1.4809169132020185e-06,
      "loss": 0.4006,
      "step": 53702
    },
    {
      "epoch": 1.6497097041747304,
      "grad_norm": 0.44983235001564026,
      "learning_rate": 1.4806638351727353e-06,
      "loss": 0.4403,
      "step": 53703
    },
    {
      "epoch": 1.6497404233096797,
      "grad_norm": 0.4308721721172333,
      "learning_rate": 1.4804107770409605e-06,
      "loss": 0.5014,
      "step": 53704
    },
    {
      "epoch": 1.6497711424446289,
      "grad_norm": 0.396231472492218,
      "learning_rate": 1.4801577388072775e-06,
      "loss": 0.4041,
      "step": 53705
    },
    {
      "epoch": 1.649801861579578,
      "grad_norm": 0.45020756125450134,
      "learning_rate": 1.4799047204722816e-06,
      "loss": 0.4773,
      "step": 53706
    },
    {
      "epoch": 1.649832580714527,
      "grad_norm": 0.4655396640300751,
      "learning_rate": 1.4796517220365626e-06,
      "loss": 0.5359,
      "step": 53707
    },
    {
      "epoch": 1.6498632998494762,
      "grad_norm": 0.45177823305130005,
      "learning_rate": 1.479398743500715e-06,
      "loss": 0.4186,
      "step": 53708
    },
    {
      "epoch": 1.6498940189844253,
      "grad_norm": 0.40718671679496765,
      "learning_rate": 1.4791457848653246e-06,
      "loss": 0.4632,
      "step": 53709
    },
    {
      "epoch": 1.6499247381193745,
      "grad_norm": 0.5210646390914917,
      "learning_rate": 1.4788928461309858e-06,
      "loss": 0.4978,
      "step": 53710
    },
    {
      "epoch": 1.6499554572543236,
      "grad_norm": 0.44285473227500916,
      "learning_rate": 1.4786399272982844e-06,
      "loss": 0.4988,
      "step": 53711
    },
    {
      "epoch": 1.649986176389273,
      "grad_norm": 0.4199228286743164,
      "learning_rate": 1.4783870283678182e-06,
      "loss": 0.4148,
      "step": 53712
    },
    {
      "epoch": 1.650016895524222,
      "grad_norm": 0.4481270909309387,
      "learning_rate": 1.4781341493401724e-06,
      "loss": 0.5236,
      "step": 53713
    },
    {
      "epoch": 1.6500476146591712,
      "grad_norm": 0.465903103351593,
      "learning_rate": 1.4778812902159413e-06,
      "loss": 0.4529,
      "step": 53714
    },
    {
      "epoch": 1.6500783337941205,
      "grad_norm": 0.4545278549194336,
      "learning_rate": 1.4776284509957117e-06,
      "loss": 0.4618,
      "step": 53715
    },
    {
      "epoch": 1.6501090529290696,
      "grad_norm": 0.46684765815734863,
      "learning_rate": 1.4773756316800758e-06,
      "loss": 0.4224,
      "step": 53716
    },
    {
      "epoch": 1.6501397720640187,
      "grad_norm": 0.4057878255844116,
      "learning_rate": 1.4771228322696252e-06,
      "loss": 0.3695,
      "step": 53717
    },
    {
      "epoch": 1.6501704911989679,
      "grad_norm": 0.4125003516674042,
      "learning_rate": 1.4768700527649504e-06,
      "loss": 0.4284,
      "step": 53718
    },
    {
      "epoch": 1.650201210333917,
      "grad_norm": 0.43030649423599243,
      "learning_rate": 1.47661729316664e-06,
      "loss": 0.4774,
      "step": 53719
    },
    {
      "epoch": 1.650231929468866,
      "grad_norm": 0.43534398078918457,
      "learning_rate": 1.4763645534752846e-06,
      "loss": 0.5021,
      "step": 53720
    },
    {
      "epoch": 1.6502626486038152,
      "grad_norm": 0.43214157223701477,
      "learning_rate": 1.476111833691475e-06,
      "loss": 0.4767,
      "step": 53721
    },
    {
      "epoch": 1.6502933677387643,
      "grad_norm": 0.4366772770881653,
      "learning_rate": 1.4758591338158012e-06,
      "loss": 0.4645,
      "step": 53722
    },
    {
      "epoch": 1.6503240868737137,
      "grad_norm": 0.3812347650527954,
      "learning_rate": 1.4756064538488557e-06,
      "loss": 0.3939,
      "step": 53723
    },
    {
      "epoch": 1.6503548060086628,
      "grad_norm": 0.4241428077220917,
      "learning_rate": 1.4753537937912254e-06,
      "loss": 0.5119,
      "step": 53724
    },
    {
      "epoch": 1.650385525143612,
      "grad_norm": 0.40941932797431946,
      "learning_rate": 1.4751011536435012e-06,
      "loss": 0.5359,
      "step": 53725
    },
    {
      "epoch": 1.6504162442785613,
      "grad_norm": 0.4688819646835327,
      "learning_rate": 1.4748485334062735e-06,
      "loss": 0.4269,
      "step": 53726
    },
    {
      "epoch": 1.6504469634135104,
      "grad_norm": 0.45877307653427124,
      "learning_rate": 1.474595933080134e-06,
      "loss": 0.5412,
      "step": 53727
    },
    {
      "epoch": 1.6504776825484595,
      "grad_norm": 0.41400083899497986,
      "learning_rate": 1.4743433526656702e-06,
      "loss": 0.4568,
      "step": 53728
    },
    {
      "epoch": 1.6505084016834086,
      "grad_norm": 0.4471316933631897,
      "learning_rate": 1.4740907921634728e-06,
      "loss": 0.4453,
      "step": 53729
    },
    {
      "epoch": 1.6505391208183577,
      "grad_norm": 0.41070592403411865,
      "learning_rate": 1.4738382515741311e-06,
      "loss": 0.5096,
      "step": 53730
    },
    {
      "epoch": 1.6505698399533069,
      "grad_norm": 0.4172516167163849,
      "learning_rate": 1.4735857308982383e-06,
      "loss": 0.5112,
      "step": 53731
    },
    {
      "epoch": 1.650600559088256,
      "grad_norm": 0.46419045329093933,
      "learning_rate": 1.473333230136379e-06,
      "loss": 0.4813,
      "step": 53732
    },
    {
      "epoch": 1.650631278223205,
      "grad_norm": 0.47019219398498535,
      "learning_rate": 1.4730807492891451e-06,
      "loss": 0.4692,
      "step": 53733
    },
    {
      "epoch": 1.6506619973581544,
      "grad_norm": 0.44822219014167786,
      "learning_rate": 1.4728282883571277e-06,
      "loss": 0.5136,
      "step": 53734
    },
    {
      "epoch": 1.6506927164931036,
      "grad_norm": 0.446540892124176,
      "learning_rate": 1.4725758473409168e-06,
      "loss": 0.518,
      "step": 53735
    },
    {
      "epoch": 1.6507234356280527,
      "grad_norm": 0.42742857336997986,
      "learning_rate": 1.472323426241098e-06,
      "loss": 0.502,
      "step": 53736
    },
    {
      "epoch": 1.650754154763002,
      "grad_norm": 0.4155285060405731,
      "learning_rate": 1.472071025058266e-06,
      "loss": 0.3566,
      "step": 53737
    },
    {
      "epoch": 1.6507848738979511,
      "grad_norm": 0.5015381574630737,
      "learning_rate": 1.4718186437930037e-06,
      "loss": 0.4188,
      "step": 53738
    },
    {
      "epoch": 1.6508155930329003,
      "grad_norm": 0.5042046308517456,
      "learning_rate": 1.4715662824459064e-06,
      "loss": 0.508,
      "step": 53739
    },
    {
      "epoch": 1.6508463121678494,
      "grad_norm": 0.6405575275421143,
      "learning_rate": 1.4713139410175637e-06,
      "loss": 0.5142,
      "step": 53740
    },
    {
      "epoch": 1.6508770313027985,
      "grad_norm": 0.4469951093196869,
      "learning_rate": 1.4710616195085613e-06,
      "loss": 0.4964,
      "step": 53741
    },
    {
      "epoch": 1.6509077504377476,
      "grad_norm": 0.8602375388145447,
      "learning_rate": 1.4708093179194915e-06,
      "loss": 0.443,
      "step": 53742
    },
    {
      "epoch": 1.6509384695726967,
      "grad_norm": 0.40013766288757324,
      "learning_rate": 1.4705570362509381e-06,
      "loss": 0.4156,
      "step": 53743
    },
    {
      "epoch": 1.6509691887076459,
      "grad_norm": 0.5009929537773132,
      "learning_rate": 1.4703047745034993e-06,
      "loss": 0.4694,
      "step": 53744
    },
    {
      "epoch": 1.6509999078425952,
      "grad_norm": 0.42974042892456055,
      "learning_rate": 1.470052532677757e-06,
      "loss": 0.5427,
      "step": 53745
    },
    {
      "epoch": 1.6510306269775443,
      "grad_norm": 0.44124412536621094,
      "learning_rate": 1.4698003107743054e-06,
      "loss": 0.4309,
      "step": 53746
    },
    {
      "epoch": 1.6510613461124934,
      "grad_norm": 0.39460012316703796,
      "learning_rate": 1.4695481087937259e-06,
      "loss": 0.4758,
      "step": 53747
    },
    {
      "epoch": 1.6510920652474428,
      "grad_norm": 0.508384644985199,
      "learning_rate": 1.469295926736617e-06,
      "loss": 0.4622,
      "step": 53748
    },
    {
      "epoch": 1.651122784382392,
      "grad_norm": 0.44698280096054077,
      "learning_rate": 1.4690437646035605e-06,
      "loss": 0.4593,
      "step": 53749
    },
    {
      "epoch": 1.651153503517341,
      "grad_norm": 0.40860387682914734,
      "learning_rate": 1.4687916223951516e-06,
      "loss": 0.451,
      "step": 53750
    },
    {
      "epoch": 1.6511842226522901,
      "grad_norm": 0.41496580839157104,
      "learning_rate": 1.4685395001119718e-06,
      "loss": 0.4261,
      "step": 53751
    },
    {
      "epoch": 1.6512149417872393,
      "grad_norm": 0.44582271575927734,
      "learning_rate": 1.4682873977546152e-06,
      "loss": 0.4979,
      "step": 53752
    },
    {
      "epoch": 1.6512456609221884,
      "grad_norm": 0.38669437170028687,
      "learning_rate": 1.4680353153236693e-06,
      "loss": 0.4912,
      "step": 53753
    },
    {
      "epoch": 1.6512763800571375,
      "grad_norm": 0.43361398577690125,
      "learning_rate": 1.4677832528197244e-06,
      "loss": 0.5202,
      "step": 53754
    },
    {
      "epoch": 1.6513070991920866,
      "grad_norm": 0.47087186574935913,
      "learning_rate": 1.4675312102433647e-06,
      "loss": 0.5154,
      "step": 53755
    },
    {
      "epoch": 1.6513378183270357,
      "grad_norm": 0.47531747817993164,
      "learning_rate": 1.467279187595183e-06,
      "loss": 0.4972,
      "step": 53756
    },
    {
      "epoch": 1.651368537461985,
      "grad_norm": 0.4465642273426056,
      "learning_rate": 1.4670271848757656e-06,
      "loss": 0.4958,
      "step": 53757
    },
    {
      "epoch": 1.6513992565969342,
      "grad_norm": 0.41129815578460693,
      "learning_rate": 1.466775202085703e-06,
      "loss": 0.4817,
      "step": 53758
    },
    {
      "epoch": 1.6514299757318835,
      "grad_norm": 0.4147641956806183,
      "learning_rate": 1.4665232392255856e-06,
      "loss": 0.4041,
      "step": 53759
    },
    {
      "epoch": 1.6514606948668327,
      "grad_norm": 0.5339109897613525,
      "learning_rate": 1.4662712962959958e-06,
      "loss": 0.5264,
      "step": 53760
    },
    {
      "epoch": 1.6514914140017818,
      "grad_norm": 0.408750057220459,
      "learning_rate": 1.466019373297526e-06,
      "loss": 0.4206,
      "step": 53761
    },
    {
      "epoch": 1.651522133136731,
      "grad_norm": 0.4730338752269745,
      "learning_rate": 1.4657674702307633e-06,
      "loss": 0.4022,
      "step": 53762
    },
    {
      "epoch": 1.65155285227168,
      "grad_norm": 0.4803867042064667,
      "learning_rate": 1.4655155870962988e-06,
      "loss": 0.4664,
      "step": 53763
    },
    {
      "epoch": 1.6515835714066291,
      "grad_norm": 0.44268715381622314,
      "learning_rate": 1.4652637238947175e-06,
      "loss": 0.4203,
      "step": 53764
    },
    {
      "epoch": 1.6516142905415783,
      "grad_norm": 0.4814489483833313,
      "learning_rate": 1.4650118806266077e-06,
      "loss": 0.4829,
      "step": 53765
    },
    {
      "epoch": 1.6516450096765274,
      "grad_norm": 0.49978920817375183,
      "learning_rate": 1.4647600572925603e-06,
      "loss": 0.4314,
      "step": 53766
    },
    {
      "epoch": 1.6516757288114765,
      "grad_norm": 0.4789072871208191,
      "learning_rate": 1.4645082538931633e-06,
      "loss": 0.4058,
      "step": 53767
    },
    {
      "epoch": 1.6517064479464258,
      "grad_norm": 0.4260901212692261,
      "learning_rate": 1.4642564704290008e-06,
      "loss": 0.4569,
      "step": 53768
    },
    {
      "epoch": 1.651737167081375,
      "grad_norm": 0.4139784276485443,
      "learning_rate": 1.4640047069006635e-06,
      "loss": 0.4412,
      "step": 53769
    },
    {
      "epoch": 1.6517678862163243,
      "grad_norm": 0.441348671913147,
      "learning_rate": 1.46375296330874e-06,
      "loss": 0.5149,
      "step": 53770
    },
    {
      "epoch": 1.6517986053512734,
      "grad_norm": 0.4180219769477844,
      "learning_rate": 1.4635012396538184e-06,
      "loss": 0.4689,
      "step": 53771
    },
    {
      "epoch": 1.6518293244862225,
      "grad_norm": 0.45234137773513794,
      "learning_rate": 1.4632495359364852e-06,
      "loss": 0.4583,
      "step": 53772
    },
    {
      "epoch": 1.6518600436211717,
      "grad_norm": 0.41649624705314636,
      "learning_rate": 1.4629978521573307e-06,
      "loss": 0.447,
      "step": 53773
    },
    {
      "epoch": 1.6518907627561208,
      "grad_norm": 0.41273725032806396,
      "learning_rate": 1.4627461883169358e-06,
      "loss": 0.4443,
      "step": 53774
    },
    {
      "epoch": 1.65192148189107,
      "grad_norm": 0.4493018388748169,
      "learning_rate": 1.4624945444158967e-06,
      "loss": 0.4168,
      "step": 53775
    },
    {
      "epoch": 1.651952201026019,
      "grad_norm": 0.5008100271224976,
      "learning_rate": 1.4622429204547995e-06,
      "loss": 0.5288,
      "step": 53776
    },
    {
      "epoch": 1.6519829201609681,
      "grad_norm": 0.3935849666595459,
      "learning_rate": 1.461991316434227e-06,
      "loss": 0.4321,
      "step": 53777
    },
    {
      "epoch": 1.6520136392959173,
      "grad_norm": 0.41545483469963074,
      "learning_rate": 1.4617397323547732e-06,
      "loss": 0.4256,
      "step": 53778
    },
    {
      "epoch": 1.6520443584308666,
      "grad_norm": 0.4317525029182434,
      "learning_rate": 1.461488168217019e-06,
      "loss": 0.4282,
      "step": 53779
    },
    {
      "epoch": 1.6520750775658157,
      "grad_norm": 0.47044092416763306,
      "learning_rate": 1.4612366240215593e-06,
      "loss": 0.4804,
      "step": 53780
    },
    {
      "epoch": 1.652105796700765,
      "grad_norm": 0.3967779278755188,
      "learning_rate": 1.4609850997689745e-06,
      "loss": 0.5254,
      "step": 53781
    },
    {
      "epoch": 1.6521365158357142,
      "grad_norm": 0.43538612127304077,
      "learning_rate": 1.460733595459859e-06,
      "loss": 0.4618,
      "step": 53782
    },
    {
      "epoch": 1.6521672349706633,
      "grad_norm": 0.4517899453639984,
      "learning_rate": 1.4604821110947943e-06,
      "loss": 0.4862,
      "step": 53783
    },
    {
      "epoch": 1.6521979541056124,
      "grad_norm": 0.4480939507484436,
      "learning_rate": 1.4602306466743687e-06,
      "loss": 0.4694,
      "step": 53784
    },
    {
      "epoch": 1.6522286732405616,
      "grad_norm": 0.4205087423324585,
      "learning_rate": 1.4599792021991721e-06,
      "loss": 0.4754,
      "step": 53785
    },
    {
      "epoch": 1.6522593923755107,
      "grad_norm": 0.5510981678962708,
      "learning_rate": 1.4597277776697926e-06,
      "loss": 0.508,
      "step": 53786
    },
    {
      "epoch": 1.6522901115104598,
      "grad_norm": 0.44670426845550537,
      "learning_rate": 1.4594763730868123e-06,
      "loss": 0.4367,
      "step": 53787
    },
    {
      "epoch": 1.652320830645409,
      "grad_norm": 0.41653987765312195,
      "learning_rate": 1.4592249884508224e-06,
      "loss": 0.4338,
      "step": 53788
    },
    {
      "epoch": 1.652351549780358,
      "grad_norm": 0.41992950439453125,
      "learning_rate": 1.4589736237624085e-06,
      "loss": 0.4102,
      "step": 53789
    },
    {
      "epoch": 1.6523822689153074,
      "grad_norm": 0.44890230894088745,
      "learning_rate": 1.45872227902216e-06,
      "loss": 0.5237,
      "step": 53790
    },
    {
      "epoch": 1.6524129880502565,
      "grad_norm": 0.4528820514678955,
      "learning_rate": 1.4584709542306608e-06,
      "loss": 0.4595,
      "step": 53791
    },
    {
      "epoch": 1.6524437071852056,
      "grad_norm": 0.4575769007205963,
      "learning_rate": 1.4582196493884992e-06,
      "loss": 0.513,
      "step": 53792
    },
    {
      "epoch": 1.652474426320155,
      "grad_norm": 0.463733434677124,
      "learning_rate": 1.4579683644962616e-06,
      "loss": 0.4183,
      "step": 53793
    },
    {
      "epoch": 1.652505145455104,
      "grad_norm": 0.39781704545021057,
      "learning_rate": 1.4577170995545352e-06,
      "loss": 0.4116,
      "step": 53794
    },
    {
      "epoch": 1.6525358645900532,
      "grad_norm": 0.4431103467941284,
      "learning_rate": 1.4574658545639097e-06,
      "loss": 0.4639,
      "step": 53795
    },
    {
      "epoch": 1.6525665837250023,
      "grad_norm": 0.46259868144989014,
      "learning_rate": 1.4572146295249677e-06,
      "loss": 0.4336,
      "step": 53796
    },
    {
      "epoch": 1.6525973028599514,
      "grad_norm": 0.4414092004299164,
      "learning_rate": 1.4569634244382969e-06,
      "loss": 0.4446,
      "step": 53797
    },
    {
      "epoch": 1.6526280219949006,
      "grad_norm": 0.4417111277580261,
      "learning_rate": 1.4567122393044842e-06,
      "loss": 0.434,
      "step": 53798
    },
    {
      "epoch": 1.6526587411298497,
      "grad_norm": 0.44158151745796204,
      "learning_rate": 1.4564610741241204e-06,
      "loss": 0.5128,
      "step": 53799
    },
    {
      "epoch": 1.6526894602647988,
      "grad_norm": 0.43701887130737305,
      "learning_rate": 1.456209928897785e-06,
      "loss": 0.5107,
      "step": 53800
    },
    {
      "epoch": 1.6527201793997481,
      "grad_norm": 0.6193437576293945,
      "learning_rate": 1.4559588036260675e-06,
      "loss": 0.4957,
      "step": 53801
    },
    {
      "epoch": 1.6527508985346973,
      "grad_norm": 0.46525582671165466,
      "learning_rate": 1.4557076983095563e-06,
      "loss": 0.5189,
      "step": 53802
    },
    {
      "epoch": 1.6527816176696464,
      "grad_norm": 0.5397964119911194,
      "learning_rate": 1.4554566129488379e-06,
      "loss": 0.4856,
      "step": 53803
    },
    {
      "epoch": 1.6528123368045957,
      "grad_norm": 0.43363630771636963,
      "learning_rate": 1.455205547544496e-06,
      "loss": 0.4808,
      "step": 53804
    },
    {
      "epoch": 1.6528430559395448,
      "grad_norm": 0.3524068295955658,
      "learning_rate": 1.454954502097119e-06,
      "loss": 0.429,
      "step": 53805
    },
    {
      "epoch": 1.652873775074494,
      "grad_norm": 0.4240378141403198,
      "learning_rate": 1.4547034766072887e-06,
      "loss": 0.4961,
      "step": 53806
    },
    {
      "epoch": 1.652904494209443,
      "grad_norm": 0.44559192657470703,
      "learning_rate": 1.4544524710756003e-06,
      "loss": 0.4855,
      "step": 53807
    },
    {
      "epoch": 1.6529352133443922,
      "grad_norm": 0.457051157951355,
      "learning_rate": 1.454201485502632e-06,
      "loss": 0.4297,
      "step": 53808
    },
    {
      "epoch": 1.6529659324793413,
      "grad_norm": 0.49815303087234497,
      "learning_rate": 1.4539505198889758e-06,
      "loss": 0.471,
      "step": 53809
    },
    {
      "epoch": 1.6529966516142904,
      "grad_norm": 0.4494982361793518,
      "learning_rate": 1.4536995742352112e-06,
      "loss": 0.471,
      "step": 53810
    },
    {
      "epoch": 1.6530273707492396,
      "grad_norm": 0.4145490527153015,
      "learning_rate": 1.4534486485419285e-06,
      "loss": 0.4912,
      "step": 53811
    },
    {
      "epoch": 1.653058089884189,
      "grad_norm": 0.42679670453071594,
      "learning_rate": 1.4531977428097167e-06,
      "loss": 0.4299,
      "step": 53812
    },
    {
      "epoch": 1.653088809019138,
      "grad_norm": 0.5281941890716553,
      "learning_rate": 1.452946857039156e-06,
      "loss": 0.461,
      "step": 53813
    },
    {
      "epoch": 1.6531195281540871,
      "grad_norm": 0.4670107066631317,
      "learning_rate": 1.4526959912308381e-06,
      "loss": 0.4246,
      "step": 53814
    },
    {
      "epoch": 1.6531502472890365,
      "grad_norm": 0.43448787927627563,
      "learning_rate": 1.4524451453853395e-06,
      "loss": 0.4487,
      "step": 53815
    },
    {
      "epoch": 1.6531809664239856,
      "grad_norm": 0.4181179106235504,
      "learning_rate": 1.4521943195032573e-06,
      "loss": 0.4879,
      "step": 53816
    },
    {
      "epoch": 1.6532116855589347,
      "grad_norm": 0.4085700511932373,
      "learning_rate": 1.45194351358517e-06,
      "loss": 0.4756,
      "step": 53817
    },
    {
      "epoch": 1.6532424046938838,
      "grad_norm": 0.41172319650650024,
      "learning_rate": 1.4516927276316685e-06,
      "loss": 0.4209,
      "step": 53818
    },
    {
      "epoch": 1.653273123828833,
      "grad_norm": 0.5497831106185913,
      "learning_rate": 1.4514419616433328e-06,
      "loss": 0.4012,
      "step": 53819
    },
    {
      "epoch": 1.653303842963782,
      "grad_norm": 0.47073128819465637,
      "learning_rate": 1.4511912156207519e-06,
      "loss": 0.5864,
      "step": 53820
    },
    {
      "epoch": 1.6533345620987312,
      "grad_norm": 0.4103851318359375,
      "learning_rate": 1.4509404895645108e-06,
      "loss": 0.4467,
      "step": 53821
    },
    {
      "epoch": 1.6533652812336803,
      "grad_norm": 0.3955453038215637,
      "learning_rate": 1.4506897834751965e-06,
      "loss": 0.4175,
      "step": 53822
    },
    {
      "epoch": 1.6533960003686297,
      "grad_norm": 0.45056772232055664,
      "learning_rate": 1.450439097353392e-06,
      "loss": 0.4849,
      "step": 53823
    },
    {
      "epoch": 1.6534267195035788,
      "grad_norm": 0.4140622615814209,
      "learning_rate": 1.450188431199684e-06,
      "loss": 0.4523,
      "step": 53824
    },
    {
      "epoch": 1.653457438638528,
      "grad_norm": 0.4078502953052521,
      "learning_rate": 1.449937785014658e-06,
      "loss": 0.3944,
      "step": 53825
    },
    {
      "epoch": 1.6534881577734772,
      "grad_norm": 0.4368720054626465,
      "learning_rate": 1.4496871587989014e-06,
      "loss": 0.5072,
      "step": 53826
    },
    {
      "epoch": 1.6535188769084264,
      "grad_norm": 0.430752158164978,
      "learning_rate": 1.4494365525529953e-06,
      "loss": 0.4016,
      "step": 53827
    },
    {
      "epoch": 1.6535495960433755,
      "grad_norm": 0.4285910129547119,
      "learning_rate": 1.4491859662775275e-06,
      "loss": 0.4993,
      "step": 53828
    },
    {
      "epoch": 1.6535803151783246,
      "grad_norm": 0.3893949091434479,
      "learning_rate": 1.4489353999730837e-06,
      "loss": 0.3448,
      "step": 53829
    },
    {
      "epoch": 1.6536110343132737,
      "grad_norm": 0.4220036268234253,
      "learning_rate": 1.4486848536402476e-06,
      "loss": 0.4486,
      "step": 53830
    },
    {
      "epoch": 1.6536417534482228,
      "grad_norm": 0.40536123514175415,
      "learning_rate": 1.4484343272796076e-06,
      "loss": 0.4832,
      "step": 53831
    },
    {
      "epoch": 1.653672472583172,
      "grad_norm": 0.4476754665374756,
      "learning_rate": 1.4481838208917444e-06,
      "loss": 0.4353,
      "step": 53832
    },
    {
      "epoch": 1.653703191718121,
      "grad_norm": 0.43901312351226807,
      "learning_rate": 1.447933334477245e-06,
      "loss": 0.5257,
      "step": 53833
    },
    {
      "epoch": 1.6537339108530704,
      "grad_norm": 0.42797115445137024,
      "learning_rate": 1.447682868036695e-06,
      "loss": 0.4851,
      "step": 53834
    },
    {
      "epoch": 1.6537646299880195,
      "grad_norm": 0.4753227233886719,
      "learning_rate": 1.4474324215706803e-06,
      "loss": 0.4597,
      "step": 53835
    },
    {
      "epoch": 1.6537953491229687,
      "grad_norm": 0.42174243927001953,
      "learning_rate": 1.4471819950797828e-06,
      "loss": 0.4921,
      "step": 53836
    },
    {
      "epoch": 1.653826068257918,
      "grad_norm": 0.41945216059684753,
      "learning_rate": 1.4469315885645897e-06,
      "loss": 0.467,
      "step": 53837
    },
    {
      "epoch": 1.6538567873928671,
      "grad_norm": 0.40972310304641724,
      "learning_rate": 1.4466812020256848e-06,
      "loss": 0.4796,
      "step": 53838
    },
    {
      "epoch": 1.6538875065278162,
      "grad_norm": 0.46974965929985046,
      "learning_rate": 1.4464308354636548e-06,
      "loss": 0.4921,
      "step": 53839
    },
    {
      "epoch": 1.6539182256627654,
      "grad_norm": 0.4584848880767822,
      "learning_rate": 1.4461804888790808e-06,
      "loss": 0.523,
      "step": 53840
    },
    {
      "epoch": 1.6539489447977145,
      "grad_norm": 0.42149531841278076,
      "learning_rate": 1.4459301622725531e-06,
      "loss": 0.5274,
      "step": 53841
    },
    {
      "epoch": 1.6539796639326636,
      "grad_norm": 0.4272952973842621,
      "learning_rate": 1.4456798556446472e-06,
      "loss": 0.4905,
      "step": 53842
    },
    {
      "epoch": 1.6540103830676127,
      "grad_norm": 0.44569218158721924,
      "learning_rate": 1.4454295689959586e-06,
      "loss": 0.4574,
      "step": 53843
    },
    {
      "epoch": 1.6540411022025618,
      "grad_norm": 0.46058157086372375,
      "learning_rate": 1.4451793023270644e-06,
      "loss": 0.5472,
      "step": 53844
    },
    {
      "epoch": 1.6540718213375112,
      "grad_norm": 0.43230384588241577,
      "learning_rate": 1.4449290556385531e-06,
      "loss": 0.5108,
      "step": 53845
    },
    {
      "epoch": 1.6541025404724603,
      "grad_norm": 0.4433605372905731,
      "learning_rate": 1.4446788289310065e-06,
      "loss": 0.4269,
      "step": 53846
    },
    {
      "epoch": 1.6541332596074094,
      "grad_norm": 0.4603644907474518,
      "learning_rate": 1.4444286222050063e-06,
      "loss": 0.4836,
      "step": 53847
    },
    {
      "epoch": 1.6541639787423588,
      "grad_norm": 0.4024104177951813,
      "learning_rate": 1.4441784354611454e-06,
      "loss": 0.4794,
      "step": 53848
    },
    {
      "epoch": 1.6541946978773079,
      "grad_norm": 0.43241941928863525,
      "learning_rate": 1.443928268700001e-06,
      "loss": 0.4692,
      "step": 53849
    },
    {
      "epoch": 1.654225417012257,
      "grad_norm": 0.42194056510925293,
      "learning_rate": 1.4436781219221628e-06,
      "loss": 0.4591,
      "step": 53850
    },
    {
      "epoch": 1.6542561361472061,
      "grad_norm": 0.4111851453781128,
      "learning_rate": 1.4434279951282072e-06,
      "loss": 0.446,
      "step": 53851
    },
    {
      "epoch": 1.6542868552821552,
      "grad_norm": 0.42806610465049744,
      "learning_rate": 1.4431778883187265e-06,
      "loss": 0.4258,
      "step": 53852
    },
    {
      "epoch": 1.6543175744171044,
      "grad_norm": 0.434063583612442,
      "learning_rate": 1.4429278014943004e-06,
      "loss": 0.5327,
      "step": 53853
    },
    {
      "epoch": 1.6543482935520535,
      "grad_norm": 0.5099853873252869,
      "learning_rate": 1.4426777346555155e-06,
      "loss": 0.5297,
      "step": 53854
    },
    {
      "epoch": 1.6543790126870026,
      "grad_norm": 0.4734625816345215,
      "learning_rate": 1.442427687802953e-06,
      "loss": 0.5157,
      "step": 53855
    },
    {
      "epoch": 1.654409731821952,
      "grad_norm": 0.5243715047836304,
      "learning_rate": 1.4421776609371973e-06,
      "loss": 0.4832,
      "step": 53856
    },
    {
      "epoch": 1.654440450956901,
      "grad_norm": 0.43264850974082947,
      "learning_rate": 1.4419276540588335e-06,
      "loss": 0.4877,
      "step": 53857
    },
    {
      "epoch": 1.6544711700918502,
      "grad_norm": 0.48376399278640747,
      "learning_rate": 1.4416776671684485e-06,
      "loss": 0.5346,
      "step": 53858
    },
    {
      "epoch": 1.6545018892267995,
      "grad_norm": 0.575019359588623,
      "learning_rate": 1.44142770026662e-06,
      "loss": 0.4835,
      "step": 53859
    },
    {
      "epoch": 1.6545326083617486,
      "grad_norm": 0.4044758677482605,
      "learning_rate": 1.441177753353935e-06,
      "loss": 0.4742,
      "step": 53860
    },
    {
      "epoch": 1.6545633274966978,
      "grad_norm": 0.4475667476654053,
      "learning_rate": 1.4409278264309767e-06,
      "loss": 0.4615,
      "step": 53861
    },
    {
      "epoch": 1.6545940466316469,
      "grad_norm": 0.4137883484363556,
      "learning_rate": 1.4406779194983322e-06,
      "loss": 0.4644,
      "step": 53862
    },
    {
      "epoch": 1.654624765766596,
      "grad_norm": 0.48617857694625854,
      "learning_rate": 1.4404280325565788e-06,
      "loss": 0.4864,
      "step": 53863
    },
    {
      "epoch": 1.6546554849015451,
      "grad_norm": 0.43778565526008606,
      "learning_rate": 1.4401781656063052e-06,
      "loss": 0.4924,
      "step": 53864
    },
    {
      "epoch": 1.6546862040364942,
      "grad_norm": 0.4805271327495575,
      "learning_rate": 1.4399283186480916e-06,
      "loss": 0.4572,
      "step": 53865
    },
    {
      "epoch": 1.6547169231714434,
      "grad_norm": 0.455095499753952,
      "learning_rate": 1.4396784916825245e-06,
      "loss": 0.3924,
      "step": 53866
    },
    {
      "epoch": 1.6547476423063925,
      "grad_norm": 0.4157178997993469,
      "learning_rate": 1.439428684710188e-06,
      "loss": 0.5119,
      "step": 53867
    },
    {
      "epoch": 1.6547783614413418,
      "grad_norm": 0.4452151954174042,
      "learning_rate": 1.4391788977316613e-06,
      "loss": 0.3818,
      "step": 53868
    },
    {
      "epoch": 1.654809080576291,
      "grad_norm": 0.41807234287261963,
      "learning_rate": 1.4389291307475306e-06,
      "loss": 0.462,
      "step": 53869
    },
    {
      "epoch": 1.6548397997112403,
      "grad_norm": 0.4612225890159607,
      "learning_rate": 1.438679383758378e-06,
      "loss": 0.4173,
      "step": 53870
    },
    {
      "epoch": 1.6548705188461894,
      "grad_norm": 0.4226953089237213,
      "learning_rate": 1.4384296567647904e-06,
      "loss": 0.4848,
      "step": 53871
    },
    {
      "epoch": 1.6549012379811385,
      "grad_norm": 0.4405267834663391,
      "learning_rate": 1.4381799497673454e-06,
      "loss": 0.5109,
      "step": 53872
    },
    {
      "epoch": 1.6549319571160876,
      "grad_norm": 0.4033658504486084,
      "learning_rate": 1.4379302627666304e-06,
      "loss": 0.5062,
      "step": 53873
    },
    {
      "epoch": 1.6549626762510368,
      "grad_norm": 0.40803468227386475,
      "learning_rate": 1.4376805957632256e-06,
      "loss": 0.5203,
      "step": 53874
    },
    {
      "epoch": 1.6549933953859859,
      "grad_norm": 0.4091781973838806,
      "learning_rate": 1.4374309487577186e-06,
      "loss": 0.4853,
      "step": 53875
    },
    {
      "epoch": 1.655024114520935,
      "grad_norm": 0.42211687564849854,
      "learning_rate": 1.4371813217506881e-06,
      "loss": 0.4672,
      "step": 53876
    },
    {
      "epoch": 1.6550548336558841,
      "grad_norm": 0.4444270431995392,
      "learning_rate": 1.4369317147427209e-06,
      "loss": 0.4879,
      "step": 53877
    },
    {
      "epoch": 1.6550855527908332,
      "grad_norm": 0.4608042240142822,
      "learning_rate": 1.4366821277343924e-06,
      "loss": 0.4266,
      "step": 53878
    },
    {
      "epoch": 1.6551162719257826,
      "grad_norm": 0.4179428219795227,
      "learning_rate": 1.4364325607262953e-06,
      "loss": 0.4426,
      "step": 53879
    },
    {
      "epoch": 1.6551469910607317,
      "grad_norm": 0.5733457803726196,
      "learning_rate": 1.4361830137190069e-06,
      "loss": 0.4866,
      "step": 53880
    },
    {
      "epoch": 1.655177710195681,
      "grad_norm": 0.42548176646232605,
      "learning_rate": 1.4359334867131126e-06,
      "loss": 0.5021,
      "step": 53881
    },
    {
      "epoch": 1.6552084293306302,
      "grad_norm": 0.4475688338279724,
      "learning_rate": 1.4356839797091916e-06,
      "loss": 0.4868,
      "step": 53882
    },
    {
      "epoch": 1.6552391484655793,
      "grad_norm": 0.5098059177398682,
      "learning_rate": 1.4354344927078278e-06,
      "loss": 0.4486,
      "step": 53883
    },
    {
      "epoch": 1.6552698676005284,
      "grad_norm": 0.47729387879371643,
      "learning_rate": 1.4351850257096068e-06,
      "loss": 0.5561,
      "step": 53884
    },
    {
      "epoch": 1.6553005867354775,
      "grad_norm": 0.45878350734710693,
      "learning_rate": 1.4349355787151077e-06,
      "loss": 0.4563,
      "step": 53885
    },
    {
      "epoch": 1.6553313058704267,
      "grad_norm": 0.43129637837409973,
      "learning_rate": 1.4346861517249177e-06,
      "loss": 0.4404,
      "step": 53886
    },
    {
      "epoch": 1.6553620250053758,
      "grad_norm": 0.4251154661178589,
      "learning_rate": 1.4344367447396146e-06,
      "loss": 0.4102,
      "step": 53887
    },
    {
      "epoch": 1.655392744140325,
      "grad_norm": 0.47046542167663574,
      "learning_rate": 1.434187357759782e-06,
      "loss": 0.4642,
      "step": 53888
    },
    {
      "epoch": 1.655423463275274,
      "grad_norm": 0.40126582980155945,
      "learning_rate": 1.4339379907860028e-06,
      "loss": 0.4776,
      "step": 53889
    },
    {
      "epoch": 1.6554541824102234,
      "grad_norm": 0.42056804895401,
      "learning_rate": 1.4336886438188625e-06,
      "loss": 0.4445,
      "step": 53890
    },
    {
      "epoch": 1.6554849015451725,
      "grad_norm": 0.4144814908504486,
      "learning_rate": 1.4334393168589378e-06,
      "loss": 0.4851,
      "step": 53891
    },
    {
      "epoch": 1.6555156206801218,
      "grad_norm": 0.4678265452384949,
      "learning_rate": 1.4331900099068152e-06,
      "loss": 0.4729,
      "step": 53892
    },
    {
      "epoch": 1.655546339815071,
      "grad_norm": 0.4974615275859833,
      "learning_rate": 1.4329407229630743e-06,
      "loss": 0.4446,
      "step": 53893
    },
    {
      "epoch": 1.65557705895002,
      "grad_norm": 0.460444837808609,
      "learning_rate": 1.4326914560283013e-06,
      "loss": 0.4707,
      "step": 53894
    },
    {
      "epoch": 1.6556077780849692,
      "grad_norm": 0.5137416124343872,
      "learning_rate": 1.4324422091030733e-06,
      "loss": 0.5141,
      "step": 53895
    },
    {
      "epoch": 1.6556384972199183,
      "grad_norm": 0.5256776213645935,
      "learning_rate": 1.4321929821879754e-06,
      "loss": 0.4415,
      "step": 53896
    },
    {
      "epoch": 1.6556692163548674,
      "grad_norm": 0.4092031419277191,
      "learning_rate": 1.4319437752835886e-06,
      "loss": 0.4864,
      "step": 53897
    },
    {
      "epoch": 1.6556999354898165,
      "grad_norm": 0.4215118885040283,
      "learning_rate": 1.4316945883904975e-06,
      "loss": 0.4455,
      "step": 53898
    },
    {
      "epoch": 1.6557306546247657,
      "grad_norm": 0.4218604862689972,
      "learning_rate": 1.431445421509281e-06,
      "loss": 0.475,
      "step": 53899
    },
    {
      "epoch": 1.6557613737597148,
      "grad_norm": 0.4426683485507965,
      "learning_rate": 1.4311962746405216e-06,
      "loss": 0.4185,
      "step": 53900
    },
    {
      "epoch": 1.6557920928946641,
      "grad_norm": 0.3899219334125519,
      "learning_rate": 1.4309471477848014e-06,
      "loss": 0.4638,
      "step": 53901
    },
    {
      "epoch": 1.6558228120296132,
      "grad_norm": 0.39220407605171204,
      "learning_rate": 1.430698040942703e-06,
      "loss": 0.4042,
      "step": 53902
    },
    {
      "epoch": 1.6558535311645624,
      "grad_norm": 0.39916205406188965,
      "learning_rate": 1.4304489541148092e-06,
      "loss": 0.5691,
      "step": 53903
    },
    {
      "epoch": 1.6558842502995117,
      "grad_norm": 0.4503614008426666,
      "learning_rate": 1.4301998873016998e-06,
      "loss": 0.4942,
      "step": 53904
    },
    {
      "epoch": 1.6559149694344608,
      "grad_norm": 0.429786741733551,
      "learning_rate": 1.4299508405039552e-06,
      "loss": 0.4719,
      "step": 53905
    },
    {
      "epoch": 1.65594568856941,
      "grad_norm": 0.40725958347320557,
      "learning_rate": 1.4297018137221597e-06,
      "loss": 0.5241,
      "step": 53906
    },
    {
      "epoch": 1.655976407704359,
      "grad_norm": 0.427595853805542,
      "learning_rate": 1.4294528069568969e-06,
      "loss": 0.4228,
      "step": 53907
    },
    {
      "epoch": 1.6560071268393082,
      "grad_norm": 0.39295700192451477,
      "learning_rate": 1.4292038202087433e-06,
      "loss": 0.4873,
      "step": 53908
    },
    {
      "epoch": 1.6560378459742573,
      "grad_norm": 0.44504159688949585,
      "learning_rate": 1.4289548534782837e-06,
      "loss": 0.4098,
      "step": 53909
    },
    {
      "epoch": 1.6560685651092064,
      "grad_norm": 0.41289108991622925,
      "learning_rate": 1.4287059067660958e-06,
      "loss": 0.4394,
      "step": 53910
    },
    {
      "epoch": 1.6560992842441555,
      "grad_norm": 0.41017264127731323,
      "learning_rate": 1.4284569800727677e-06,
      "loss": 0.434,
      "step": 53911
    },
    {
      "epoch": 1.6561300033791049,
      "grad_norm": 0.43266239762306213,
      "learning_rate": 1.4282080733988745e-06,
      "loss": 0.4514,
      "step": 53912
    },
    {
      "epoch": 1.656160722514054,
      "grad_norm": 0.45857980847358704,
      "learning_rate": 1.4279591867450026e-06,
      "loss": 0.4372,
      "step": 53913
    },
    {
      "epoch": 1.6561914416490031,
      "grad_norm": 0.44994446635246277,
      "learning_rate": 1.427710320111726e-06,
      "loss": 0.4179,
      "step": 53914
    },
    {
      "epoch": 1.6562221607839525,
      "grad_norm": 0.42852163314819336,
      "learning_rate": 1.427461473499635e-06,
      "loss": 0.4179,
      "step": 53915
    },
    {
      "epoch": 1.6562528799189016,
      "grad_norm": 0.40870535373687744,
      "learning_rate": 1.4272126469093038e-06,
      "loss": 0.4696,
      "step": 53916
    },
    {
      "epoch": 1.6562835990538507,
      "grad_norm": 0.41957977414131165,
      "learning_rate": 1.42696384034132e-06,
      "loss": 0.4232,
      "step": 53917
    },
    {
      "epoch": 1.6563143181887998,
      "grad_norm": 0.42601218819618225,
      "learning_rate": 1.426715053796257e-06,
      "loss": 0.439,
      "step": 53918
    },
    {
      "epoch": 1.656345037323749,
      "grad_norm": 0.46565619111061096,
      "learning_rate": 1.4264662872747004e-06,
      "loss": 0.4208,
      "step": 53919
    },
    {
      "epoch": 1.656375756458698,
      "grad_norm": 0.44234758615493774,
      "learning_rate": 1.4262175407772305e-06,
      "loss": 0.4729,
      "step": 53920
    },
    {
      "epoch": 1.6564064755936472,
      "grad_norm": 0.4128362834453583,
      "learning_rate": 1.425968814304428e-06,
      "loss": 0.4677,
      "step": 53921
    },
    {
      "epoch": 1.6564371947285963,
      "grad_norm": 0.4165198504924774,
      "learning_rate": 1.4257201078568771e-06,
      "loss": 0.4717,
      "step": 53922
    },
    {
      "epoch": 1.6564679138635456,
      "grad_norm": 0.40656816959381104,
      "learning_rate": 1.4254714214351527e-06,
      "loss": 0.444,
      "step": 53923
    },
    {
      "epoch": 1.6564986329984948,
      "grad_norm": 0.7590739130973816,
      "learning_rate": 1.425222755039839e-06,
      "loss": 0.5032,
      "step": 53924
    },
    {
      "epoch": 1.6565293521334439,
      "grad_norm": 0.45734530687332153,
      "learning_rate": 1.4249741086715163e-06,
      "loss": 0.4512,
      "step": 53925
    },
    {
      "epoch": 1.6565600712683932,
      "grad_norm": 0.40316545963287354,
      "learning_rate": 1.4247254823307676e-06,
      "loss": 0.4803,
      "step": 53926
    },
    {
      "epoch": 1.6565907904033423,
      "grad_norm": 0.4099123179912567,
      "learning_rate": 1.4244768760181693e-06,
      "loss": 0.4782,
      "step": 53927
    },
    {
      "epoch": 1.6566215095382915,
      "grad_norm": 0.47348931431770325,
      "learning_rate": 1.424228289734304e-06,
      "loss": 0.4188,
      "step": 53928
    },
    {
      "epoch": 1.6566522286732406,
      "grad_norm": 0.4679189920425415,
      "learning_rate": 1.4239797234797536e-06,
      "loss": 0.4815,
      "step": 53929
    },
    {
      "epoch": 1.6566829478081897,
      "grad_norm": 0.42858079075813293,
      "learning_rate": 1.4237311772550987e-06,
      "loss": 0.4796,
      "step": 53930
    },
    {
      "epoch": 1.6567136669431388,
      "grad_norm": 0.4201168119907379,
      "learning_rate": 1.4234826510609157e-06,
      "loss": 0.4724,
      "step": 53931
    },
    {
      "epoch": 1.656744386078088,
      "grad_norm": 0.461249977350235,
      "learning_rate": 1.4232341448977892e-06,
      "loss": 0.469,
      "step": 53932
    },
    {
      "epoch": 1.656775105213037,
      "grad_norm": 0.42390382289886475,
      "learning_rate": 1.4229856587662983e-06,
      "loss": 0.5026,
      "step": 53933
    },
    {
      "epoch": 1.6568058243479864,
      "grad_norm": 0.41883549094200134,
      "learning_rate": 1.4227371926670242e-06,
      "loss": 0.3956,
      "step": 53934
    },
    {
      "epoch": 1.6568365434829355,
      "grad_norm": 0.4839131832122803,
      "learning_rate": 1.4224887466005455e-06,
      "loss": 0.4964,
      "step": 53935
    },
    {
      "epoch": 1.6568672626178846,
      "grad_norm": 0.3831617534160614,
      "learning_rate": 1.4222403205674429e-06,
      "loss": 0.4222,
      "step": 53936
    },
    {
      "epoch": 1.656897981752834,
      "grad_norm": 0.3804706335067749,
      "learning_rate": 1.421991914568297e-06,
      "loss": 0.4071,
      "step": 53937
    },
    {
      "epoch": 1.656928700887783,
      "grad_norm": 0.46119844913482666,
      "learning_rate": 1.4217435286036908e-06,
      "loss": 0.4591,
      "step": 53938
    },
    {
      "epoch": 1.6569594200227322,
      "grad_norm": 0.43435582518577576,
      "learning_rate": 1.4214951626741991e-06,
      "loss": 0.5241,
      "step": 53939
    },
    {
      "epoch": 1.6569901391576813,
      "grad_norm": 0.43411388993263245,
      "learning_rate": 1.421246816780405e-06,
      "loss": 0.4808,
      "step": 53940
    },
    {
      "epoch": 1.6570208582926305,
      "grad_norm": 0.4113767147064209,
      "learning_rate": 1.420998490922888e-06,
      "loss": 0.5676,
      "step": 53941
    },
    {
      "epoch": 1.6570515774275796,
      "grad_norm": 0.4641733765602112,
      "learning_rate": 1.4207501851022276e-06,
      "loss": 0.4937,
      "step": 53942
    },
    {
      "epoch": 1.6570822965625287,
      "grad_norm": 0.4782463610172272,
      "learning_rate": 1.4205018993190068e-06,
      "loss": 0.4629,
      "step": 53943
    },
    {
      "epoch": 1.6571130156974778,
      "grad_norm": 0.39667049050331116,
      "learning_rate": 1.4202536335738015e-06,
      "loss": 0.4121,
      "step": 53944
    },
    {
      "epoch": 1.6571437348324272,
      "grad_norm": 0.43110522627830505,
      "learning_rate": 1.4200053878671937e-06,
      "loss": 0.5285,
      "step": 53945
    },
    {
      "epoch": 1.6571744539673763,
      "grad_norm": 0.4230067729949951,
      "learning_rate": 1.4197571621997598e-06,
      "loss": 0.4265,
      "step": 53946
    },
    {
      "epoch": 1.6572051731023254,
      "grad_norm": 0.4092537462711334,
      "learning_rate": 1.4195089565720854e-06,
      "loss": 0.4103,
      "step": 53947
    },
    {
      "epoch": 1.6572358922372747,
      "grad_norm": 0.42440491914749146,
      "learning_rate": 1.4192607709847462e-06,
      "loss": 0.5009,
      "step": 53948
    },
    {
      "epoch": 1.6572666113722239,
      "grad_norm": 0.4211250841617584,
      "learning_rate": 1.4190126054383234e-06,
      "loss": 0.5108,
      "step": 53949
    },
    {
      "epoch": 1.657297330507173,
      "grad_norm": 0.4102467894554138,
      "learning_rate": 1.418764459933395e-06,
      "loss": 0.4337,
      "step": 53950
    },
    {
      "epoch": 1.657328049642122,
      "grad_norm": 0.5484973788261414,
      "learning_rate": 1.418516334470541e-06,
      "loss": 0.3895,
      "step": 53951
    },
    {
      "epoch": 1.6573587687770712,
      "grad_norm": 0.5147042274475098,
      "learning_rate": 1.4182682290503414e-06,
      "loss": 0.4637,
      "step": 53952
    },
    {
      "epoch": 1.6573894879120203,
      "grad_norm": 0.4415753185749054,
      "learning_rate": 1.4180201436733776e-06,
      "loss": 0.4586,
      "step": 53953
    },
    {
      "epoch": 1.6574202070469695,
      "grad_norm": 0.4500885009765625,
      "learning_rate": 1.417772078340225e-06,
      "loss": 0.3834,
      "step": 53954
    },
    {
      "epoch": 1.6574509261819186,
      "grad_norm": 0.4286719262599945,
      "learning_rate": 1.4175240330514662e-06,
      "loss": 0.4815,
      "step": 53955
    },
    {
      "epoch": 1.657481645316868,
      "grad_norm": 0.4176105558872223,
      "learning_rate": 1.4172760078076775e-06,
      "loss": 0.4755,
      "step": 53956
    },
    {
      "epoch": 1.657512364451817,
      "grad_norm": 0.46172550320625305,
      "learning_rate": 1.4170280026094418e-06,
      "loss": 0.4011,
      "step": 53957
    },
    {
      "epoch": 1.6575430835867662,
      "grad_norm": 0.4586247503757477,
      "learning_rate": 1.4167800174573376e-06,
      "loss": 0.446,
      "step": 53958
    },
    {
      "epoch": 1.6575738027217155,
      "grad_norm": 0.4349960684776306,
      "learning_rate": 1.4165320523519421e-06,
      "loss": 0.5211,
      "step": 53959
    },
    {
      "epoch": 1.6576045218566646,
      "grad_norm": 0.4300205111503601,
      "learning_rate": 1.4162841072938348e-06,
      "loss": 0.472,
      "step": 53960
    },
    {
      "epoch": 1.6576352409916137,
      "grad_norm": 0.42304518818855286,
      "learning_rate": 1.4160361822835956e-06,
      "loss": 0.4392,
      "step": 53961
    },
    {
      "epoch": 1.6576659601265629,
      "grad_norm": 0.4135473966598511,
      "learning_rate": 1.4157882773218045e-06,
      "loss": 0.4573,
      "step": 53962
    },
    {
      "epoch": 1.657696679261512,
      "grad_norm": 0.4408777058124542,
      "learning_rate": 1.4155403924090384e-06,
      "loss": 0.4866,
      "step": 53963
    },
    {
      "epoch": 1.657727398396461,
      "grad_norm": 0.42985954880714417,
      "learning_rate": 1.4152925275458773e-06,
      "loss": 0.4952,
      "step": 53964
    },
    {
      "epoch": 1.6577581175314102,
      "grad_norm": 0.4400089979171753,
      "learning_rate": 1.4150446827329e-06,
      "loss": 0.5114,
      "step": 53965
    },
    {
      "epoch": 1.6577888366663593,
      "grad_norm": 0.46542277932167053,
      "learning_rate": 1.4147968579706872e-06,
      "loss": 0.4989,
      "step": 53966
    },
    {
      "epoch": 1.6578195558013087,
      "grad_norm": 0.4505910277366638,
      "learning_rate": 1.414549053259814e-06,
      "loss": 0.4648,
      "step": 53967
    },
    {
      "epoch": 1.6578502749362578,
      "grad_norm": 0.4201858639717102,
      "learning_rate": 1.4143012686008605e-06,
      "loss": 0.5419,
      "step": 53968
    },
    {
      "epoch": 1.657880994071207,
      "grad_norm": 0.46654072403907776,
      "learning_rate": 1.414053503994407e-06,
      "loss": 0.4654,
      "step": 53969
    },
    {
      "epoch": 1.6579117132061563,
      "grad_norm": 0.4123648405075073,
      "learning_rate": 1.4138057594410326e-06,
      "loss": 0.4885,
      "step": 53970
    },
    {
      "epoch": 1.6579424323411054,
      "grad_norm": 0.4467543363571167,
      "learning_rate": 1.4135580349413125e-06,
      "loss": 0.4445,
      "step": 53971
    },
    {
      "epoch": 1.6579731514760545,
      "grad_norm": 0.4655643701553345,
      "learning_rate": 1.4133103304958295e-06,
      "loss": 0.4793,
      "step": 53972
    },
    {
      "epoch": 1.6580038706110036,
      "grad_norm": 0.40430283546447754,
      "learning_rate": 1.4130626461051556e-06,
      "loss": 0.515,
      "step": 53973
    },
    {
      "epoch": 1.6580345897459527,
      "grad_norm": 0.46107518672943115,
      "learning_rate": 1.4128149817698776e-06,
      "loss": 0.4947,
      "step": 53974
    },
    {
      "epoch": 1.6580653088809019,
      "grad_norm": 0.4456750750541687,
      "learning_rate": 1.412567337490568e-06,
      "loss": 0.5307,
      "step": 53975
    },
    {
      "epoch": 1.658096028015851,
      "grad_norm": 0.4143410921096802,
      "learning_rate": 1.412319713267808e-06,
      "loss": 0.5309,
      "step": 53976
    },
    {
      "epoch": 1.6581267471508,
      "grad_norm": 0.47530731558799744,
      "learning_rate": 1.412072109102174e-06,
      "loss": 0.5003,
      "step": 53977
    },
    {
      "epoch": 1.6581574662857494,
      "grad_norm": 0.5000606179237366,
      "learning_rate": 1.4118245249942454e-06,
      "loss": 0.4995,
      "step": 53978
    },
    {
      "epoch": 1.6581881854206986,
      "grad_norm": 0.41734325885772705,
      "learning_rate": 1.411576960944603e-06,
      "loss": 0.4309,
      "step": 53979
    },
    {
      "epoch": 1.6582189045556477,
      "grad_norm": 0.44061970710754395,
      "learning_rate": 1.4113294169538204e-06,
      "loss": 0.4396,
      "step": 53980
    },
    {
      "epoch": 1.658249623690597,
      "grad_norm": 0.4482607841491699,
      "learning_rate": 1.411081893022479e-06,
      "loss": 0.5015,
      "step": 53981
    },
    {
      "epoch": 1.6582803428255461,
      "grad_norm": 0.5148937106132507,
      "learning_rate": 1.4108343891511522e-06,
      "loss": 0.5259,
      "step": 53982
    },
    {
      "epoch": 1.6583110619604953,
      "grad_norm": 0.46009111404418945,
      "learning_rate": 1.4105869053404252e-06,
      "loss": 0.4493,
      "step": 53983
    },
    {
      "epoch": 1.6583417810954444,
      "grad_norm": 0.44507789611816406,
      "learning_rate": 1.410339441590871e-06,
      "loss": 0.4229,
      "step": 53984
    },
    {
      "epoch": 1.6583725002303935,
      "grad_norm": 0.4472709894180298,
      "learning_rate": 1.4100919979030713e-06,
      "loss": 0.4537,
      "step": 53985
    },
    {
      "epoch": 1.6584032193653426,
      "grad_norm": 0.4102930724620819,
      "learning_rate": 1.4098445742775978e-06,
      "loss": 0.5066,
      "step": 53986
    },
    {
      "epoch": 1.6584339385002917,
      "grad_norm": 0.45339757204055786,
      "learning_rate": 1.4095971707150336e-06,
      "loss": 0.4838,
      "step": 53987
    },
    {
      "epoch": 1.6584646576352409,
      "grad_norm": 0.46768608689308167,
      "learning_rate": 1.4093497872159556e-06,
      "loss": 0.4402,
      "step": 53988
    },
    {
      "epoch": 1.65849537677019,
      "grad_norm": 0.46997687220573425,
      "learning_rate": 1.4091024237809426e-06,
      "loss": 0.4533,
      "step": 53989
    },
    {
      "epoch": 1.6585260959051393,
      "grad_norm": 0.430448979139328,
      "learning_rate": 1.4088550804105684e-06,
      "loss": 0.4488,
      "step": 53990
    },
    {
      "epoch": 1.6585568150400885,
      "grad_norm": 0.47847267985343933,
      "learning_rate": 1.4086077571054135e-06,
      "loss": 0.4534,
      "step": 53991
    },
    {
      "epoch": 1.6585875341750378,
      "grad_norm": 0.4293910264968872,
      "learning_rate": 1.4083604538660545e-06,
      "loss": 0.4314,
      "step": 53992
    },
    {
      "epoch": 1.658618253309987,
      "grad_norm": 0.42412057518959045,
      "learning_rate": 1.4081131706930706e-06,
      "loss": 0.4677,
      "step": 53993
    },
    {
      "epoch": 1.658648972444936,
      "grad_norm": 0.42715802788734436,
      "learning_rate": 1.4078659075870404e-06,
      "loss": 0.5694,
      "step": 53994
    },
    {
      "epoch": 1.6586796915798852,
      "grad_norm": 0.4488106369972229,
      "learning_rate": 1.407618664548538e-06,
      "loss": 0.4556,
      "step": 53995
    },
    {
      "epoch": 1.6587104107148343,
      "grad_norm": 0.4333478808403015,
      "learning_rate": 1.4073714415781414e-06,
      "loss": 0.5045,
      "step": 53996
    },
    {
      "epoch": 1.6587411298497834,
      "grad_norm": 0.4165442883968353,
      "learning_rate": 1.4071242386764283e-06,
      "loss": 0.4219,
      "step": 53997
    },
    {
      "epoch": 1.6587718489847325,
      "grad_norm": 0.47015732526779175,
      "learning_rate": 1.4068770558439804e-06,
      "loss": 0.4811,
      "step": 53998
    },
    {
      "epoch": 1.6588025681196816,
      "grad_norm": 0.45106175541877747,
      "learning_rate": 1.4066298930813682e-06,
      "loss": 0.5274,
      "step": 53999
    },
    {
      "epoch": 1.6588332872546308,
      "grad_norm": 0.39991629123687744,
      "learning_rate": 1.4063827503891713e-06,
      "loss": 0.4144,
      "step": 54000
    },
    {
      "epoch": 1.65886400638958,
      "grad_norm": 0.41764697432518005,
      "learning_rate": 1.4061356277679683e-06,
      "loss": 0.4863,
      "step": 54001
    },
    {
      "epoch": 1.6588947255245292,
      "grad_norm": 0.3937346935272217,
      "learning_rate": 1.4058885252183386e-06,
      "loss": 0.5287,
      "step": 54002
    },
    {
      "epoch": 1.6589254446594786,
      "grad_norm": 0.4625321924686432,
      "learning_rate": 1.405641442740854e-06,
      "loss": 0.4644,
      "step": 54003
    },
    {
      "epoch": 1.6589561637944277,
      "grad_norm": 0.43162405490875244,
      "learning_rate": 1.4053943803360936e-06,
      "loss": 0.4778,
      "step": 54004
    },
    {
      "epoch": 1.6589868829293768,
      "grad_norm": 0.4372870624065399,
      "learning_rate": 1.4051473380046344e-06,
      "loss": 0.4556,
      "step": 54005
    },
    {
      "epoch": 1.659017602064326,
      "grad_norm": 0.39977943897247314,
      "learning_rate": 1.4049003157470575e-06,
      "loss": 0.463,
      "step": 54006
    },
    {
      "epoch": 1.659048321199275,
      "grad_norm": 0.4113326370716095,
      "learning_rate": 1.404653313563933e-06,
      "loss": 0.5238,
      "step": 54007
    },
    {
      "epoch": 1.6590790403342242,
      "grad_norm": 0.4289613366127014,
      "learning_rate": 1.4044063314558431e-06,
      "loss": 0.4537,
      "step": 54008
    },
    {
      "epoch": 1.6591097594691733,
      "grad_norm": 0.3895930051803589,
      "learning_rate": 1.404159369423358e-06,
      "loss": 0.5174,
      "step": 54009
    },
    {
      "epoch": 1.6591404786041224,
      "grad_norm": 0.44233155250549316,
      "learning_rate": 1.4039124274670647e-06,
      "loss": 0.4638,
      "step": 54010
    },
    {
      "epoch": 1.6591711977390715,
      "grad_norm": 0.41912680864334106,
      "learning_rate": 1.4036655055875303e-06,
      "loss": 0.3799,
      "step": 54011
    },
    {
      "epoch": 1.6592019168740209,
      "grad_norm": 0.44468995928764343,
      "learning_rate": 1.403418603785337e-06,
      "loss": 0.5168,
      "step": 54012
    },
    {
      "epoch": 1.65923263600897,
      "grad_norm": 0.4001619219779968,
      "learning_rate": 1.4031717220610608e-06,
      "loss": 0.4011,
      "step": 54013
    },
    {
      "epoch": 1.659263355143919,
      "grad_norm": 0.4583207964897156,
      "learning_rate": 1.4029248604152735e-06,
      "loss": 0.4237,
      "step": 54014
    },
    {
      "epoch": 1.6592940742788684,
      "grad_norm": 0.3883790373802185,
      "learning_rate": 1.4026780188485612e-06,
      "loss": 0.4507,
      "step": 54015
    },
    {
      "epoch": 1.6593247934138176,
      "grad_norm": 0.4536454975605011,
      "learning_rate": 1.4024311973614913e-06,
      "loss": 0.4564,
      "step": 54016
    },
    {
      "epoch": 1.6593555125487667,
      "grad_norm": 0.4447687566280365,
      "learning_rate": 1.4021843959546467e-06,
      "loss": 0.4929,
      "step": 54017
    },
    {
      "epoch": 1.6593862316837158,
      "grad_norm": 0.4368821084499359,
      "learning_rate": 1.4019376146285956e-06,
      "loss": 0.4487,
      "step": 54018
    },
    {
      "epoch": 1.659416950818665,
      "grad_norm": 0.4820694327354431,
      "learning_rate": 1.4016908533839247e-06,
      "loss": 0.4747,
      "step": 54019
    },
    {
      "epoch": 1.659447669953614,
      "grad_norm": 0.38071408867836,
      "learning_rate": 1.401444112221203e-06,
      "loss": 0.5038,
      "step": 54020
    },
    {
      "epoch": 1.6594783890885632,
      "grad_norm": 0.4238378703594208,
      "learning_rate": 1.4011973911410115e-06,
      "loss": 0.403,
      "step": 54021
    },
    {
      "epoch": 1.6595091082235123,
      "grad_norm": 0.43387526273727417,
      "learning_rate": 1.4009506901439207e-06,
      "loss": 0.4834,
      "step": 54022
    },
    {
      "epoch": 1.6595398273584616,
      "grad_norm": 0.4419163465499878,
      "learning_rate": 1.4007040092305114e-06,
      "loss": 0.4455,
      "step": 54023
    },
    {
      "epoch": 1.6595705464934107,
      "grad_norm": 0.460504949092865,
      "learning_rate": 1.4004573484013584e-06,
      "loss": 0.4295,
      "step": 54024
    },
    {
      "epoch": 1.6596012656283599,
      "grad_norm": 0.5166170001029968,
      "learning_rate": 1.4002107076570392e-06,
      "loss": 0.3771,
      "step": 54025
    },
    {
      "epoch": 1.6596319847633092,
      "grad_norm": 0.4428737461566925,
      "learning_rate": 1.3999640869981268e-06,
      "loss": 0.4762,
      "step": 54026
    },
    {
      "epoch": 1.6596627038982583,
      "grad_norm": 0.4223344326019287,
      "learning_rate": 1.3997174864251993e-06,
      "loss": 0.4409,
      "step": 54027
    },
    {
      "epoch": 1.6596934230332074,
      "grad_norm": 0.40701666474342346,
      "learning_rate": 1.3994709059388322e-06,
      "loss": 0.4752,
      "step": 54028
    },
    {
      "epoch": 1.6597241421681566,
      "grad_norm": 0.5244753360748291,
      "learning_rate": 1.3992243455396025e-06,
      "loss": 0.4337,
      "step": 54029
    },
    {
      "epoch": 1.6597548613031057,
      "grad_norm": 0.4765426218509674,
      "learning_rate": 1.3989778052280845e-06,
      "loss": 0.4494,
      "step": 54030
    },
    {
      "epoch": 1.6597855804380548,
      "grad_norm": 0.4240477979183197,
      "learning_rate": 1.3987312850048528e-06,
      "loss": 0.4414,
      "step": 54031
    },
    {
      "epoch": 1.659816299573004,
      "grad_norm": 0.46993106603622437,
      "learning_rate": 1.3984847848704863e-06,
      "loss": 0.4675,
      "step": 54032
    },
    {
      "epoch": 1.659847018707953,
      "grad_norm": 0.41316744685173035,
      "learning_rate": 1.3982383048255588e-06,
      "loss": 0.5013,
      "step": 54033
    },
    {
      "epoch": 1.6598777378429024,
      "grad_norm": 0.4522201418876648,
      "learning_rate": 1.3979918448706487e-06,
      "loss": 0.3897,
      "step": 54034
    },
    {
      "epoch": 1.6599084569778515,
      "grad_norm": 0.4265138804912567,
      "learning_rate": 1.3977454050063265e-06,
      "loss": 0.4497,
      "step": 54035
    },
    {
      "epoch": 1.6599391761128006,
      "grad_norm": 0.4544830620288849,
      "learning_rate": 1.3974989852331723e-06,
      "loss": 0.4828,
      "step": 54036
    },
    {
      "epoch": 1.65996989524775,
      "grad_norm": 0.43244224786758423,
      "learning_rate": 1.3972525855517583e-06,
      "loss": 0.5025,
      "step": 54037
    },
    {
      "epoch": 1.660000614382699,
      "grad_norm": 0.6410217881202698,
      "learning_rate": 1.3970062059626643e-06,
      "loss": 0.4431,
      "step": 54038
    },
    {
      "epoch": 1.6600313335176482,
      "grad_norm": 0.46638625860214233,
      "learning_rate": 1.3967598464664623e-06,
      "loss": 0.4505,
      "step": 54039
    },
    {
      "epoch": 1.6600620526525973,
      "grad_norm": 0.4247898459434509,
      "learning_rate": 1.396513507063727e-06,
      "loss": 0.4541,
      "step": 54040
    },
    {
      "epoch": 1.6600927717875464,
      "grad_norm": 0.5234952569007874,
      "learning_rate": 1.396267187755036e-06,
      "loss": 0.4549,
      "step": 54041
    },
    {
      "epoch": 1.6601234909224956,
      "grad_norm": 0.40806150436401367,
      "learning_rate": 1.3960208885409654e-06,
      "loss": 0.4204,
      "step": 54042
    },
    {
      "epoch": 1.6601542100574447,
      "grad_norm": 0.4820745885372162,
      "learning_rate": 1.395774609422087e-06,
      "loss": 0.4337,
      "step": 54043
    },
    {
      "epoch": 1.6601849291923938,
      "grad_norm": 0.4208982586860657,
      "learning_rate": 1.3955283503989802e-06,
      "loss": 0.5046,
      "step": 54044
    },
    {
      "epoch": 1.6602156483273431,
      "grad_norm": 0.4104246497154236,
      "learning_rate": 1.3952821114722137e-06,
      "loss": 0.385,
      "step": 54045
    },
    {
      "epoch": 1.6602463674622923,
      "grad_norm": 0.5500351190567017,
      "learning_rate": 1.3950358926423713e-06,
      "loss": 0.5392,
      "step": 54046
    },
    {
      "epoch": 1.6602770865972414,
      "grad_norm": 0.46083134412765503,
      "learning_rate": 1.3947896939100202e-06,
      "loss": 0.5151,
      "step": 54047
    },
    {
      "epoch": 1.6603078057321907,
      "grad_norm": 0.40753117203712463,
      "learning_rate": 1.3945435152757403e-06,
      "loss": 0.4754,
      "step": 54048
    },
    {
      "epoch": 1.6603385248671398,
      "grad_norm": 0.4107913374900818,
      "learning_rate": 1.3942973567401063e-06,
      "loss": 0.5123,
      "step": 54049
    },
    {
      "epoch": 1.660369244002089,
      "grad_norm": 0.45670419931411743,
      "learning_rate": 1.394051218303687e-06,
      "loss": 0.4471,
      "step": 54050
    },
    {
      "epoch": 1.660399963137038,
      "grad_norm": 0.4478181004524231,
      "learning_rate": 1.3938050999670671e-06,
      "loss": 0.43,
      "step": 54051
    },
    {
      "epoch": 1.6604306822719872,
      "grad_norm": 0.5601351261138916,
      "learning_rate": 1.3935590017308153e-06,
      "loss": 0.3878,
      "step": 54052
    },
    {
      "epoch": 1.6604614014069363,
      "grad_norm": 0.4487556219100952,
      "learning_rate": 1.3933129235955078e-06,
      "loss": 0.4663,
      "step": 54053
    },
    {
      "epoch": 1.6604921205418854,
      "grad_norm": 0.40029677748680115,
      "learning_rate": 1.3930668655617186e-06,
      "loss": 0.4908,
      "step": 54054
    },
    {
      "epoch": 1.6605228396768346,
      "grad_norm": 0.393942654132843,
      "learning_rate": 1.3928208276300215e-06,
      "loss": 0.427,
      "step": 54055
    },
    {
      "epoch": 1.660553558811784,
      "grad_norm": 0.42650681734085083,
      "learning_rate": 1.392574809800993e-06,
      "loss": 0.4356,
      "step": 54056
    },
    {
      "epoch": 1.660584277946733,
      "grad_norm": 0.4142642915248871,
      "learning_rate": 1.3923288120752099e-06,
      "loss": 0.5337,
      "step": 54057
    },
    {
      "epoch": 1.6606149970816821,
      "grad_norm": 0.4707578122615814,
      "learning_rate": 1.3920828344532412e-06,
      "loss": 0.5061,
      "step": 54058
    },
    {
      "epoch": 1.6606457162166315,
      "grad_norm": 0.4289090931415558,
      "learning_rate": 1.3918368769356638e-06,
      "loss": 0.4309,
      "step": 54059
    },
    {
      "epoch": 1.6606764353515806,
      "grad_norm": 0.46841487288475037,
      "learning_rate": 1.3915909395230532e-06,
      "loss": 0.442,
      "step": 54060
    },
    {
      "epoch": 1.6607071544865297,
      "grad_norm": 0.4358263313770294,
      "learning_rate": 1.3913450222159853e-06,
      "loss": 0.5132,
      "step": 54061
    },
    {
      "epoch": 1.6607378736214788,
      "grad_norm": 0.42163071036338806,
      "learning_rate": 1.3910991250150296e-06,
      "loss": 0.4543,
      "step": 54062
    },
    {
      "epoch": 1.660768592756428,
      "grad_norm": 0.4906828701496124,
      "learning_rate": 1.3908532479207638e-06,
      "loss": 0.3748,
      "step": 54063
    },
    {
      "epoch": 1.660799311891377,
      "grad_norm": 0.4343475103378296,
      "learning_rate": 1.3906073909337602e-06,
      "loss": 0.4312,
      "step": 54064
    },
    {
      "epoch": 1.6608300310263262,
      "grad_norm": 0.4343549311161041,
      "learning_rate": 1.3903615540545978e-06,
      "loss": 0.4999,
      "step": 54065
    },
    {
      "epoch": 1.6608607501612753,
      "grad_norm": 0.4598352611064911,
      "learning_rate": 1.3901157372838448e-06,
      "loss": 0.4894,
      "step": 54066
    },
    {
      "epoch": 1.6608914692962247,
      "grad_norm": 0.3947344422340393,
      "learning_rate": 1.3898699406220784e-06,
      "loss": 0.5406,
      "step": 54067
    },
    {
      "epoch": 1.6609221884311738,
      "grad_norm": 0.5841013193130493,
      "learning_rate": 1.3896241640698715e-06,
      "loss": 0.3856,
      "step": 54068
    },
    {
      "epoch": 1.660952907566123,
      "grad_norm": 0.4284094572067261,
      "learning_rate": 1.3893784076277983e-06,
      "loss": 0.444,
      "step": 54069
    },
    {
      "epoch": 1.6609836267010722,
      "grad_norm": 0.5291263461112976,
      "learning_rate": 1.389132671296436e-06,
      "loss": 0.5193,
      "step": 54070
    },
    {
      "epoch": 1.6610143458360214,
      "grad_norm": 0.4193035364151001,
      "learning_rate": 1.3888869550763528e-06,
      "loss": 0.5009,
      "step": 54071
    },
    {
      "epoch": 1.6610450649709705,
      "grad_norm": 0.4415856599807739,
      "learning_rate": 1.3886412589681263e-06,
      "loss": 0.3426,
      "step": 54072
    },
    {
      "epoch": 1.6610757841059196,
      "grad_norm": 0.45957234501838684,
      "learning_rate": 1.3883955829723294e-06,
      "loss": 0.5212,
      "step": 54073
    },
    {
      "epoch": 1.6611065032408687,
      "grad_norm": 0.43222686648368835,
      "learning_rate": 1.3881499270895382e-06,
      "loss": 0.5075,
      "step": 54074
    },
    {
      "epoch": 1.6611372223758178,
      "grad_norm": 0.41817957162857056,
      "learning_rate": 1.3879042913203223e-06,
      "loss": 0.4632,
      "step": 54075
    },
    {
      "epoch": 1.661167941510767,
      "grad_norm": 0.44542571902275085,
      "learning_rate": 1.3876586756652588e-06,
      "loss": 0.4397,
      "step": 54076
    },
    {
      "epoch": 1.661198660645716,
      "grad_norm": 0.4497328996658325,
      "learning_rate": 1.3874130801249165e-06,
      "loss": 0.4179,
      "step": 54077
    },
    {
      "epoch": 1.6612293797806654,
      "grad_norm": 0.45238423347473145,
      "learning_rate": 1.3871675046998757e-06,
      "loss": 0.4488,
      "step": 54078
    },
    {
      "epoch": 1.6612600989156145,
      "grad_norm": 0.47738826274871826,
      "learning_rate": 1.386921949390706e-06,
      "loss": 0.4984,
      "step": 54079
    },
    {
      "epoch": 1.6612908180505637,
      "grad_norm": 0.45663321018218994,
      "learning_rate": 1.3866764141979827e-06,
      "loss": 0.4468,
      "step": 54080
    },
    {
      "epoch": 1.661321537185513,
      "grad_norm": 0.47083181142807007,
      "learning_rate": 1.3864308991222742e-06,
      "loss": 0.4427,
      "step": 54081
    },
    {
      "epoch": 1.6613522563204621,
      "grad_norm": 0.45986074209213257,
      "learning_rate": 1.386185404164162e-06,
      "loss": 0.4567,
      "step": 54082
    },
    {
      "epoch": 1.6613829754554112,
      "grad_norm": 0.4554656147956848,
      "learning_rate": 1.3859399293242138e-06,
      "loss": 0.4572,
      "step": 54083
    },
    {
      "epoch": 1.6614136945903604,
      "grad_norm": 0.45064955949783325,
      "learning_rate": 1.3856944746030055e-06,
      "loss": 0.4931,
      "step": 54084
    },
    {
      "epoch": 1.6614444137253095,
      "grad_norm": 0.4401390850543976,
      "learning_rate": 1.3854490400011078e-06,
      "loss": 0.4555,
      "step": 54085
    },
    {
      "epoch": 1.6614751328602586,
      "grad_norm": 0.4187668561935425,
      "learning_rate": 1.3852036255190938e-06,
      "loss": 0.4505,
      "step": 54086
    },
    {
      "epoch": 1.6615058519952077,
      "grad_norm": 0.418290376663208,
      "learning_rate": 1.3849582311575427e-06,
      "loss": 0.4393,
      "step": 54087
    },
    {
      "epoch": 1.6615365711301568,
      "grad_norm": 0.43004310131073,
      "learning_rate": 1.384712856917021e-06,
      "loss": 0.4835,
      "step": 54088
    },
    {
      "epoch": 1.6615672902651062,
      "grad_norm": 0.4438101053237915,
      "learning_rate": 1.3844675027981059e-06,
      "loss": 0.4709,
      "step": 54089
    },
    {
      "epoch": 1.6615980094000553,
      "grad_norm": 0.48528581857681274,
      "learning_rate": 1.3842221688013668e-06,
      "loss": 0.4767,
      "step": 54090
    },
    {
      "epoch": 1.6616287285350044,
      "grad_norm": 0.4404822885990143,
      "learning_rate": 1.383976854927378e-06,
      "loss": 0.4727,
      "step": 54091
    },
    {
      "epoch": 1.6616594476699538,
      "grad_norm": 0.46028485894203186,
      "learning_rate": 1.3837315611767133e-06,
      "loss": 0.4181,
      "step": 54092
    },
    {
      "epoch": 1.661690166804903,
      "grad_norm": 0.41554272174835205,
      "learning_rate": 1.3834862875499477e-06,
      "loss": 0.5111,
      "step": 54093
    },
    {
      "epoch": 1.661720885939852,
      "grad_norm": 0.46320492029190063,
      "learning_rate": 1.3832410340476498e-06,
      "loss": 0.4656,
      "step": 54094
    },
    {
      "epoch": 1.6617516050748011,
      "grad_norm": 0.4567539691925049,
      "learning_rate": 1.3829958006703937e-06,
      "loss": 0.4515,
      "step": 54095
    },
    {
      "epoch": 1.6617823242097503,
      "grad_norm": 0.42372918128967285,
      "learning_rate": 1.3827505874187518e-06,
      "loss": 0.4191,
      "step": 54096
    },
    {
      "epoch": 1.6618130433446994,
      "grad_norm": 0.4265921413898468,
      "learning_rate": 1.382505394293302e-06,
      "loss": 0.4364,
      "step": 54097
    },
    {
      "epoch": 1.6618437624796485,
      "grad_norm": 0.4408833980560303,
      "learning_rate": 1.382260221294609e-06,
      "loss": 0.4712,
      "step": 54098
    },
    {
      "epoch": 1.6618744816145976,
      "grad_norm": 0.45700690150260925,
      "learning_rate": 1.3820150684232491e-06,
      "loss": 0.442,
      "step": 54099
    },
    {
      "epoch": 1.6619052007495467,
      "grad_norm": 0.4223768711090088,
      "learning_rate": 1.3817699356797953e-06,
      "loss": 0.4827,
      "step": 54100
    },
    {
      "epoch": 1.661935919884496,
      "grad_norm": 0.3978579640388489,
      "learning_rate": 1.3815248230648226e-06,
      "loss": 0.426,
      "step": 54101
    },
    {
      "epoch": 1.6619666390194452,
      "grad_norm": 0.42793652415275574,
      "learning_rate": 1.3812797305788972e-06,
      "loss": 0.415,
      "step": 54102
    },
    {
      "epoch": 1.6619973581543945,
      "grad_norm": 0.47438257932662964,
      "learning_rate": 1.3810346582225953e-06,
      "loss": 0.4919,
      "step": 54103
    },
    {
      "epoch": 1.6620280772893437,
      "grad_norm": 0.4470171630382538,
      "learning_rate": 1.3807896059964899e-06,
      "loss": 0.4577,
      "step": 54104
    },
    {
      "epoch": 1.6620587964242928,
      "grad_norm": 0.4438285529613495,
      "learning_rate": 1.3805445739011513e-06,
      "loss": 0.5702,
      "step": 54105
    },
    {
      "epoch": 1.662089515559242,
      "grad_norm": 0.4427761137485504,
      "learning_rate": 1.380299561937155e-06,
      "loss": 0.4699,
      "step": 54106
    },
    {
      "epoch": 1.662120234694191,
      "grad_norm": 0.4540465176105499,
      "learning_rate": 1.3800545701050694e-06,
      "loss": 0.5397,
      "step": 54107
    },
    {
      "epoch": 1.6621509538291401,
      "grad_norm": 0.4403551518917084,
      "learning_rate": 1.379809598405467e-06,
      "loss": 0.5118,
      "step": 54108
    },
    {
      "epoch": 1.6621816729640893,
      "grad_norm": 0.4933044910430908,
      "learning_rate": 1.3795646468389224e-06,
      "loss": 0.4218,
      "step": 54109
    },
    {
      "epoch": 1.6622123920990384,
      "grad_norm": 0.4895416796207428,
      "learning_rate": 1.3793197154060088e-06,
      "loss": 0.4685,
      "step": 54110
    },
    {
      "epoch": 1.6622431112339875,
      "grad_norm": 0.39044520258903503,
      "learning_rate": 1.3790748041072942e-06,
      "loss": 0.4528,
      "step": 54111
    },
    {
      "epoch": 1.6622738303689368,
      "grad_norm": 0.44756248593330383,
      "learning_rate": 1.3788299129433547e-06,
      "loss": 0.4818,
      "step": 54112
    },
    {
      "epoch": 1.662304549503886,
      "grad_norm": 0.47278067469596863,
      "learning_rate": 1.378585041914755e-06,
      "loss": 0.4222,
      "step": 54113
    },
    {
      "epoch": 1.6623352686388353,
      "grad_norm": 0.5197498798370361,
      "learning_rate": 1.3783401910220762e-06,
      "loss": 0.5286,
      "step": 54114
    },
    {
      "epoch": 1.6623659877737844,
      "grad_norm": 0.43124091625213623,
      "learning_rate": 1.3780953602658842e-06,
      "loss": 0.5165,
      "step": 54115
    },
    {
      "epoch": 1.6623967069087335,
      "grad_norm": 0.43987932801246643,
      "learning_rate": 1.3778505496467554e-06,
      "loss": 0.524,
      "step": 54116
    },
    {
      "epoch": 1.6624274260436827,
      "grad_norm": 0.42908236384391785,
      "learning_rate": 1.377605759165256e-06,
      "loss": 0.4312,
      "step": 54117
    },
    {
      "epoch": 1.6624581451786318,
      "grad_norm": 0.39791473746299744,
      "learning_rate": 1.3773609888219609e-06,
      "loss": 0.4537,
      "step": 54118
    },
    {
      "epoch": 1.662488864313581,
      "grad_norm": 0.5699720978736877,
      "learning_rate": 1.3771162386174408e-06,
      "loss": 0.4622,
      "step": 54119
    },
    {
      "epoch": 1.66251958344853,
      "grad_norm": 0.46138453483581543,
      "learning_rate": 1.37687150855227e-06,
      "loss": 0.478,
      "step": 54120
    },
    {
      "epoch": 1.6625503025834791,
      "grad_norm": 0.44798481464385986,
      "learning_rate": 1.3766267986270164e-06,
      "loss": 0.4771,
      "step": 54121
    },
    {
      "epoch": 1.6625810217184283,
      "grad_norm": 0.4434677064418793,
      "learning_rate": 1.3763821088422514e-06,
      "loss": 0.5203,
      "step": 54122
    },
    {
      "epoch": 1.6626117408533776,
      "grad_norm": 0.40474796295166016,
      "learning_rate": 1.3761374391985515e-06,
      "loss": 0.477,
      "step": 54123
    },
    {
      "epoch": 1.6626424599883267,
      "grad_norm": 0.4383643567562103,
      "learning_rate": 1.3758927896964835e-06,
      "loss": 0.49,
      "step": 54124
    },
    {
      "epoch": 1.6626731791232758,
      "grad_norm": 0.4091048836708069,
      "learning_rate": 1.3756481603366223e-06,
      "loss": 0.4246,
      "step": 54125
    },
    {
      "epoch": 1.6627038982582252,
      "grad_norm": 0.47438377141952515,
      "learning_rate": 1.3754035511195353e-06,
      "loss": 0.4717,
      "step": 54126
    },
    {
      "epoch": 1.6627346173931743,
      "grad_norm": 0.4684639871120453,
      "learning_rate": 1.375158962045795e-06,
      "loss": 0.4727,
      "step": 54127
    },
    {
      "epoch": 1.6627653365281234,
      "grad_norm": 0.48758187890052795,
      "learning_rate": 1.3749143931159736e-06,
      "loss": 0.465,
      "step": 54128
    },
    {
      "epoch": 1.6627960556630725,
      "grad_norm": 0.45955953001976013,
      "learning_rate": 1.3746698443306438e-06,
      "loss": 0.4972,
      "step": 54129
    },
    {
      "epoch": 1.6628267747980217,
      "grad_norm": 0.5280472040176392,
      "learning_rate": 1.374425315690373e-06,
      "loss": 0.4989,
      "step": 54130
    },
    {
      "epoch": 1.6628574939329708,
      "grad_norm": 0.42388391494750977,
      "learning_rate": 1.3741808071957341e-06,
      "loss": 0.4918,
      "step": 54131
    },
    {
      "epoch": 1.66288821306792,
      "grad_norm": 0.42750653624534607,
      "learning_rate": 1.3739363188472988e-06,
      "loss": 0.4839,
      "step": 54132
    },
    {
      "epoch": 1.662918932202869,
      "grad_norm": 0.4552074372768402,
      "learning_rate": 1.3736918506456398e-06,
      "loss": 0.4405,
      "step": 54133
    },
    {
      "epoch": 1.6629496513378184,
      "grad_norm": 0.47005128860473633,
      "learning_rate": 1.3734474025913235e-06,
      "loss": 0.4473,
      "step": 54134
    },
    {
      "epoch": 1.6629803704727675,
      "grad_norm": 0.43851780891418457,
      "learning_rate": 1.373202974684923e-06,
      "loss": 0.5231,
      "step": 54135
    },
    {
      "epoch": 1.6630110896077166,
      "grad_norm": 0.47689780592918396,
      "learning_rate": 1.3729585669270097e-06,
      "loss": 0.4816,
      "step": 54136
    },
    {
      "epoch": 1.663041808742666,
      "grad_norm": 0.40509140491485596,
      "learning_rate": 1.3727141793181565e-06,
      "loss": 0.541,
      "step": 54137
    },
    {
      "epoch": 1.663072527877615,
      "grad_norm": 0.43590113520622253,
      "learning_rate": 1.3724698118589296e-06,
      "loss": 0.4313,
      "step": 54138
    },
    {
      "epoch": 1.6631032470125642,
      "grad_norm": 0.4380848705768585,
      "learning_rate": 1.3722254645499023e-06,
      "loss": 0.4557,
      "step": 54139
    },
    {
      "epoch": 1.6631339661475133,
      "grad_norm": 0.411598801612854,
      "learning_rate": 1.3719811373916448e-06,
      "loss": 0.4881,
      "step": 54140
    },
    {
      "epoch": 1.6631646852824624,
      "grad_norm": 0.41758260130882263,
      "learning_rate": 1.3717368303847278e-06,
      "loss": 0.4556,
      "step": 54141
    },
    {
      "epoch": 1.6631954044174115,
      "grad_norm": 0.418093204498291,
      "learning_rate": 1.3714925435297243e-06,
      "loss": 0.4461,
      "step": 54142
    },
    {
      "epoch": 1.6632261235523607,
      "grad_norm": 0.41193944215774536,
      "learning_rate": 1.3712482768272006e-06,
      "loss": 0.4542,
      "step": 54143
    },
    {
      "epoch": 1.6632568426873098,
      "grad_norm": 0.4373147487640381,
      "learning_rate": 1.3710040302777282e-06,
      "loss": 0.4482,
      "step": 54144
    },
    {
      "epoch": 1.6632875618222591,
      "grad_norm": 0.4355912506580353,
      "learning_rate": 1.3707598038818793e-06,
      "loss": 0.4759,
      "step": 54145
    },
    {
      "epoch": 1.6633182809572082,
      "grad_norm": 0.4473413825035095,
      "learning_rate": 1.3705155976402262e-06,
      "loss": 0.4542,
      "step": 54146
    },
    {
      "epoch": 1.6633490000921574,
      "grad_norm": 0.4488491117954254,
      "learning_rate": 1.3702714115533334e-06,
      "loss": 0.4552,
      "step": 54147
    },
    {
      "epoch": 1.6633797192271067,
      "grad_norm": 0.426400750875473,
      "learning_rate": 1.3700272456217767e-06,
      "loss": 0.3934,
      "step": 54148
    },
    {
      "epoch": 1.6634104383620558,
      "grad_norm": 0.5401368141174316,
      "learning_rate": 1.3697830998461203e-06,
      "loss": 0.4018,
      "step": 54149
    },
    {
      "epoch": 1.663441157497005,
      "grad_norm": 0.45096567273139954,
      "learning_rate": 1.3695389742269427e-06,
      "loss": 0.524,
      "step": 54150
    },
    {
      "epoch": 1.663471876631954,
      "grad_norm": 0.4039250314235687,
      "learning_rate": 1.3692948687648066e-06,
      "loss": 0.4507,
      "step": 54151
    },
    {
      "epoch": 1.6635025957669032,
      "grad_norm": 0.4474930465221405,
      "learning_rate": 1.3690507834602883e-06,
      "loss": 0.5076,
      "step": 54152
    },
    {
      "epoch": 1.6635333149018523,
      "grad_norm": 0.42699459195137024,
      "learning_rate": 1.3688067183139519e-06,
      "loss": 0.4261,
      "step": 54153
    },
    {
      "epoch": 1.6635640340368014,
      "grad_norm": 0.42173877358436584,
      "learning_rate": 1.3685626733263702e-06,
      "loss": 0.4264,
      "step": 54154
    },
    {
      "epoch": 1.6635947531717505,
      "grad_norm": 0.4259066879749298,
      "learning_rate": 1.3683186484981125e-06,
      "loss": 0.463,
      "step": 54155
    },
    {
      "epoch": 1.6636254723066999,
      "grad_norm": 0.4320923686027527,
      "learning_rate": 1.368074643829752e-06,
      "loss": 0.4465,
      "step": 54156
    },
    {
      "epoch": 1.663656191441649,
      "grad_norm": 0.4602978229522705,
      "learning_rate": 1.367830659321855e-06,
      "loss": 0.5313,
      "step": 54157
    },
    {
      "epoch": 1.6636869105765981,
      "grad_norm": 0.4180348515510559,
      "learning_rate": 1.3675866949749905e-06,
      "loss": 0.4644,
      "step": 54158
    },
    {
      "epoch": 1.6637176297115475,
      "grad_norm": 0.4105664789676666,
      "learning_rate": 1.3673427507897319e-06,
      "loss": 0.4778,
      "step": 54159
    },
    {
      "epoch": 1.6637483488464966,
      "grad_norm": 0.4463430345058441,
      "learning_rate": 1.3670988267666463e-06,
      "loss": 0.4143,
      "step": 54160
    },
    {
      "epoch": 1.6637790679814457,
      "grad_norm": 0.4284942150115967,
      "learning_rate": 1.3668549229063066e-06,
      "loss": 0.503,
      "step": 54161
    },
    {
      "epoch": 1.6638097871163948,
      "grad_norm": 0.40856143832206726,
      "learning_rate": 1.366611039209278e-06,
      "loss": 0.4699,
      "step": 54162
    },
    {
      "epoch": 1.663840506251344,
      "grad_norm": 0.42531245946884155,
      "learning_rate": 1.3663671756761322e-06,
      "loss": 0.4587,
      "step": 54163
    },
    {
      "epoch": 1.663871225386293,
      "grad_norm": 0.40270426869392395,
      "learning_rate": 1.3661233323074385e-06,
      "loss": 0.4625,
      "step": 54164
    },
    {
      "epoch": 1.6639019445212422,
      "grad_norm": 0.4692002832889557,
      "learning_rate": 1.3658795091037702e-06,
      "loss": 0.4094,
      "step": 54165
    },
    {
      "epoch": 1.6639326636561913,
      "grad_norm": 0.44975346326828003,
      "learning_rate": 1.36563570606569e-06,
      "loss": 0.4806,
      "step": 54166
    },
    {
      "epoch": 1.6639633827911406,
      "grad_norm": 0.41308915615081787,
      "learning_rate": 1.3653919231937708e-06,
      "loss": 0.5047,
      "step": 54167
    },
    {
      "epoch": 1.6639941019260898,
      "grad_norm": 0.44726550579071045,
      "learning_rate": 1.3651481604885818e-06,
      "loss": 0.4917,
      "step": 54168
    },
    {
      "epoch": 1.6640248210610389,
      "grad_norm": 0.40629327297210693,
      "learning_rate": 1.3649044179506942e-06,
      "loss": 0.4619,
      "step": 54169
    },
    {
      "epoch": 1.6640555401959882,
      "grad_norm": 0.42796045541763306,
      "learning_rate": 1.364660695580674e-06,
      "loss": 0.3935,
      "step": 54170
    },
    {
      "epoch": 1.6640862593309373,
      "grad_norm": 0.4123545289039612,
      "learning_rate": 1.3644169933790908e-06,
      "loss": 0.5254,
      "step": 54171
    },
    {
      "epoch": 1.6641169784658865,
      "grad_norm": 0.4318884313106537,
      "learning_rate": 1.3641733113465162e-06,
      "loss": 0.4579,
      "step": 54172
    },
    {
      "epoch": 1.6641476976008356,
      "grad_norm": 0.40729472041130066,
      "learning_rate": 1.3639296494835187e-06,
      "loss": 0.5017,
      "step": 54173
    },
    {
      "epoch": 1.6641784167357847,
      "grad_norm": 0.45498326420783997,
      "learning_rate": 1.3636860077906656e-06,
      "loss": 0.4211,
      "step": 54174
    },
    {
      "epoch": 1.6642091358707338,
      "grad_norm": 0.4575249254703522,
      "learning_rate": 1.3634423862685287e-06,
      "loss": 0.5435,
      "step": 54175
    },
    {
      "epoch": 1.664239855005683,
      "grad_norm": 0.43829619884490967,
      "learning_rate": 1.3631987849176708e-06,
      "loss": 0.4381,
      "step": 54176
    },
    {
      "epoch": 1.664270574140632,
      "grad_norm": 0.4044971168041229,
      "learning_rate": 1.3629552037386673e-06,
      "loss": 0.4376,
      "step": 54177
    },
    {
      "epoch": 1.6643012932755814,
      "grad_norm": 0.4458272159099579,
      "learning_rate": 1.3627116427320874e-06,
      "loss": 0.4076,
      "step": 54178
    },
    {
      "epoch": 1.6643320124105305,
      "grad_norm": 0.40624868869781494,
      "learning_rate": 1.3624681018984964e-06,
      "loss": 0.4228,
      "step": 54179
    },
    {
      "epoch": 1.6643627315454796,
      "grad_norm": 0.43894150853157043,
      "learning_rate": 1.3622245812384639e-06,
      "loss": 0.415,
      "step": 54180
    },
    {
      "epoch": 1.664393450680429,
      "grad_norm": 0.4294540584087372,
      "learning_rate": 1.3619810807525579e-06,
      "loss": 0.5271,
      "step": 54181
    },
    {
      "epoch": 1.664424169815378,
      "grad_norm": 0.4453640878200531,
      "learning_rate": 1.3617376004413519e-06,
      "loss": 0.4356,
      "step": 54182
    },
    {
      "epoch": 1.6644548889503272,
      "grad_norm": 0.4317678213119507,
      "learning_rate": 1.3614941403054082e-06,
      "loss": 0.4216,
      "step": 54183
    },
    {
      "epoch": 1.6644856080852763,
      "grad_norm": 0.43104827404022217,
      "learning_rate": 1.3612507003453013e-06,
      "loss": 0.41,
      "step": 54184
    },
    {
      "epoch": 1.6645163272202255,
      "grad_norm": 0.45655831694602966,
      "learning_rate": 1.3610072805615914e-06,
      "loss": 0.4363,
      "step": 54185
    },
    {
      "epoch": 1.6645470463551746,
      "grad_norm": 0.3842253088951111,
      "learning_rate": 1.3607638809548573e-06,
      "loss": 0.4526,
      "step": 54186
    },
    {
      "epoch": 1.6645777654901237,
      "grad_norm": 0.44911402463912964,
      "learning_rate": 1.3605205015256607e-06,
      "loss": 0.4722,
      "step": 54187
    },
    {
      "epoch": 1.6646084846250728,
      "grad_norm": 0.5417253971099854,
      "learning_rate": 1.3602771422745732e-06,
      "loss": 0.4925,
      "step": 54188
    },
    {
      "epoch": 1.6646392037600222,
      "grad_norm": 0.43365228176116943,
      "learning_rate": 1.3600338032021599e-06,
      "loss": 0.4471,
      "step": 54189
    },
    {
      "epoch": 1.6646699228949713,
      "grad_norm": 0.4185253977775574,
      "learning_rate": 1.3597904843089905e-06,
      "loss": 0.41,
      "step": 54190
    },
    {
      "epoch": 1.6647006420299204,
      "grad_norm": 0.476037859916687,
      "learning_rate": 1.3595471855956344e-06,
      "loss": 0.3545,
      "step": 54191
    },
    {
      "epoch": 1.6647313611648697,
      "grad_norm": 0.5407761931419373,
      "learning_rate": 1.3593039070626624e-06,
      "loss": 0.4391,
      "step": 54192
    },
    {
      "epoch": 1.6647620802998189,
      "grad_norm": 0.45716866850852966,
      "learning_rate": 1.359060648710636e-06,
      "loss": 0.4653,
      "step": 54193
    },
    {
      "epoch": 1.664792799434768,
      "grad_norm": 0.42245131731033325,
      "learning_rate": 1.3588174105401276e-06,
      "loss": 0.4547,
      "step": 54194
    },
    {
      "epoch": 1.664823518569717,
      "grad_norm": 0.4616350829601288,
      "learning_rate": 1.3585741925517037e-06,
      "loss": 0.4283,
      "step": 54195
    },
    {
      "epoch": 1.6648542377046662,
      "grad_norm": 0.4744545817375183,
      "learning_rate": 1.3583309947459344e-06,
      "loss": 0.5155,
      "step": 54196
    },
    {
      "epoch": 1.6648849568396153,
      "grad_norm": 0.47866591811180115,
      "learning_rate": 1.358087817123388e-06,
      "loss": 0.4919,
      "step": 54197
    },
    {
      "epoch": 1.6649156759745645,
      "grad_norm": 0.40271642804145813,
      "learning_rate": 1.3578446596846295e-06,
      "loss": 0.4227,
      "step": 54198
    },
    {
      "epoch": 1.6649463951095136,
      "grad_norm": 0.45843812823295593,
      "learning_rate": 1.3576015224302285e-06,
      "loss": 0.4448,
      "step": 54199
    },
    {
      "epoch": 1.664977114244463,
      "grad_norm": 0.45989134907722473,
      "learning_rate": 1.3573584053607525e-06,
      "loss": 0.5184,
      "step": 54200
    },
    {
      "epoch": 1.665007833379412,
      "grad_norm": 0.49059009552001953,
      "learning_rate": 1.357115308476772e-06,
      "loss": 0.4718,
      "step": 54201
    },
    {
      "epoch": 1.6650385525143612,
      "grad_norm": 0.40743348002433777,
      "learning_rate": 1.3568722317788485e-06,
      "loss": 0.4513,
      "step": 54202
    },
    {
      "epoch": 1.6650692716493105,
      "grad_norm": 0.43841660022735596,
      "learning_rate": 1.3566291752675554e-06,
      "loss": 0.4795,
      "step": 54203
    },
    {
      "epoch": 1.6650999907842596,
      "grad_norm": 0.4535890519618988,
      "learning_rate": 1.3563861389434574e-06,
      "loss": 0.4521,
      "step": 54204
    },
    {
      "epoch": 1.6651307099192088,
      "grad_norm": 0.4198518991470337,
      "learning_rate": 1.3561431228071264e-06,
      "loss": 0.4568,
      "step": 54205
    },
    {
      "epoch": 1.6651614290541579,
      "grad_norm": 0.4843345582485199,
      "learning_rate": 1.3559001268591244e-06,
      "loss": 0.4597,
      "step": 54206
    },
    {
      "epoch": 1.665192148189107,
      "grad_norm": 0.40048128366470337,
      "learning_rate": 1.3556571511000205e-06,
      "loss": 0.4653,
      "step": 54207
    },
    {
      "epoch": 1.665222867324056,
      "grad_norm": 0.4013744294643402,
      "learning_rate": 1.3554141955303833e-06,
      "loss": 0.5097,
      "step": 54208
    },
    {
      "epoch": 1.6652535864590052,
      "grad_norm": 0.4405478835105896,
      "learning_rate": 1.3551712601507828e-06,
      "loss": 0.5483,
      "step": 54209
    },
    {
      "epoch": 1.6652843055939544,
      "grad_norm": 0.4196966588497162,
      "learning_rate": 1.3549283449617812e-06,
      "loss": 0.4098,
      "step": 54210
    },
    {
      "epoch": 1.6653150247289035,
      "grad_norm": 0.4172455370426178,
      "learning_rate": 1.3546854499639495e-06,
      "loss": 0.4943,
      "step": 54211
    },
    {
      "epoch": 1.6653457438638528,
      "grad_norm": 0.4282788932323456,
      "learning_rate": 1.3544425751578506e-06,
      "loss": 0.4272,
      "step": 54212
    },
    {
      "epoch": 1.665376462998802,
      "grad_norm": 0.4591469466686249,
      "learning_rate": 1.354199720544056e-06,
      "loss": 0.5005,
      "step": 54213
    },
    {
      "epoch": 1.6654071821337513,
      "grad_norm": 0.4128009080886841,
      "learning_rate": 1.3539568861231344e-06,
      "loss": 0.4705,
      "step": 54214
    },
    {
      "epoch": 1.6654379012687004,
      "grad_norm": 0.5280136466026306,
      "learning_rate": 1.3537140718956488e-06,
      "loss": 0.5941,
      "step": 54215
    },
    {
      "epoch": 1.6654686204036495,
      "grad_norm": 0.43470466136932373,
      "learning_rate": 1.3534712778621696e-06,
      "loss": 0.5035,
      "step": 54216
    },
    {
      "epoch": 1.6654993395385986,
      "grad_norm": 0.4371020197868347,
      "learning_rate": 1.3532285040232573e-06,
      "loss": 0.5025,
      "step": 54217
    },
    {
      "epoch": 1.6655300586735478,
      "grad_norm": 0.46116551756858826,
      "learning_rate": 1.3529857503794885e-06,
      "loss": 0.4226,
      "step": 54218
    },
    {
      "epoch": 1.6655607778084969,
      "grad_norm": 0.43989425897598267,
      "learning_rate": 1.3527430169314226e-06,
      "loss": 0.4719,
      "step": 54219
    },
    {
      "epoch": 1.665591496943446,
      "grad_norm": 0.4019334018230438,
      "learning_rate": 1.3525003036796325e-06,
      "loss": 0.4941,
      "step": 54220
    },
    {
      "epoch": 1.6656222160783951,
      "grad_norm": 0.4313887059688568,
      "learning_rate": 1.3522576106246766e-06,
      "loss": 0.4684,
      "step": 54221
    },
    {
      "epoch": 1.6656529352133442,
      "grad_norm": 0.40277376770973206,
      "learning_rate": 1.3520149377671321e-06,
      "loss": 0.4365,
      "step": 54222
    },
    {
      "epoch": 1.6656836543482936,
      "grad_norm": 0.5840567946434021,
      "learning_rate": 1.3517722851075576e-06,
      "loss": 0.469,
      "step": 54223
    },
    {
      "epoch": 1.6657143734832427,
      "grad_norm": 0.5099034309387207,
      "learning_rate": 1.351529652646526e-06,
      "loss": 0.5301,
      "step": 54224
    },
    {
      "epoch": 1.665745092618192,
      "grad_norm": 0.4159829616546631,
      "learning_rate": 1.351287040384598e-06,
      "loss": 0.5108,
      "step": 54225
    },
    {
      "epoch": 1.6657758117531412,
      "grad_norm": 0.41926655173301697,
      "learning_rate": 1.3510444483223428e-06,
      "loss": 0.4928,
      "step": 54226
    },
    {
      "epoch": 1.6658065308880903,
      "grad_norm": 0.40849995613098145,
      "learning_rate": 1.3508018764603282e-06,
      "loss": 0.3964,
      "step": 54227
    },
    {
      "epoch": 1.6658372500230394,
      "grad_norm": 0.4758867919445038,
      "learning_rate": 1.3505593247991223e-06,
      "loss": 0.486,
      "step": 54228
    },
    {
      "epoch": 1.6658679691579885,
      "grad_norm": 0.4505259394645691,
      "learning_rate": 1.3503167933392859e-06,
      "loss": 0.4539,
      "step": 54229
    },
    {
      "epoch": 1.6658986882929376,
      "grad_norm": 0.45422226190567017,
      "learning_rate": 1.3500742820813894e-06,
      "loss": 0.5693,
      "step": 54230
    },
    {
      "epoch": 1.6659294074278868,
      "grad_norm": 0.4356684386730194,
      "learning_rate": 1.3498317910259984e-06,
      "loss": 0.5371,
      "step": 54231
    },
    {
      "epoch": 1.6659601265628359,
      "grad_norm": 0.49783939123153687,
      "learning_rate": 1.3495893201736798e-06,
      "loss": 0.5009,
      "step": 54232
    },
    {
      "epoch": 1.665990845697785,
      "grad_norm": 0.43599265813827515,
      "learning_rate": 1.3493468695250012e-06,
      "loss": 0.544,
      "step": 54233
    },
    {
      "epoch": 1.6660215648327343,
      "grad_norm": 0.4080424904823303,
      "learning_rate": 1.3491044390805253e-06,
      "loss": 0.4711,
      "step": 54234
    },
    {
      "epoch": 1.6660522839676835,
      "grad_norm": 0.40201643109321594,
      "learning_rate": 1.3488620288408193e-06,
      "loss": 0.4186,
      "step": 54235
    },
    {
      "epoch": 1.6660830031026326,
      "grad_norm": 0.41822728514671326,
      "learning_rate": 1.348619638806451e-06,
      "loss": 0.4446,
      "step": 54236
    },
    {
      "epoch": 1.666113722237582,
      "grad_norm": 0.4178600609302521,
      "learning_rate": 1.3483772689779885e-06,
      "loss": 0.4049,
      "step": 54237
    },
    {
      "epoch": 1.666144441372531,
      "grad_norm": 0.4370037019252777,
      "learning_rate": 1.3481349193559912e-06,
      "loss": 0.4973,
      "step": 54238
    },
    {
      "epoch": 1.6661751605074802,
      "grad_norm": 0.4463649392127991,
      "learning_rate": 1.34789258994103e-06,
      "loss": 0.54,
      "step": 54239
    },
    {
      "epoch": 1.6662058796424293,
      "grad_norm": 0.42592769861221313,
      "learning_rate": 1.34765028073367e-06,
      "loss": 0.4709,
      "step": 54240
    },
    {
      "epoch": 1.6662365987773784,
      "grad_norm": 0.42219752073287964,
      "learning_rate": 1.3474079917344795e-06,
      "loss": 0.4106,
      "step": 54241
    },
    {
      "epoch": 1.6662673179123275,
      "grad_norm": 0.4213643968105316,
      "learning_rate": 1.3471657229440194e-06,
      "loss": 0.4682,
      "step": 54242
    },
    {
      "epoch": 1.6662980370472766,
      "grad_norm": 0.4345978796482086,
      "learning_rate": 1.346923474362858e-06,
      "loss": 0.3962,
      "step": 54243
    },
    {
      "epoch": 1.6663287561822258,
      "grad_norm": 0.4156724512577057,
      "learning_rate": 1.3466812459915613e-06,
      "loss": 0.4995,
      "step": 54244
    },
    {
      "epoch": 1.666359475317175,
      "grad_norm": 0.43665188550949097,
      "learning_rate": 1.3464390378306968e-06,
      "loss": 0.4513,
      "step": 54245
    },
    {
      "epoch": 1.6663901944521242,
      "grad_norm": 0.43065011501312256,
      "learning_rate": 1.3461968498808264e-06,
      "loss": 0.4616,
      "step": 54246
    },
    {
      "epoch": 1.6664209135870733,
      "grad_norm": 0.4763909578323364,
      "learning_rate": 1.3459546821425195e-06,
      "loss": 0.4585,
      "step": 54247
    },
    {
      "epoch": 1.6664516327220227,
      "grad_norm": 0.5213964581489563,
      "learning_rate": 1.3457125346163357e-06,
      "loss": 0.4267,
      "step": 54248
    },
    {
      "epoch": 1.6664823518569718,
      "grad_norm": 0.43458113074302673,
      "learning_rate": 1.3454704073028469e-06,
      "loss": 0.475,
      "step": 54249
    },
    {
      "epoch": 1.666513070991921,
      "grad_norm": 0.40266653895378113,
      "learning_rate": 1.345228300202618e-06,
      "loss": 0.4465,
      "step": 54250
    },
    {
      "epoch": 1.66654379012687,
      "grad_norm": 0.40213876962661743,
      "learning_rate": 1.3449862133162117e-06,
      "loss": 0.486,
      "step": 54251
    },
    {
      "epoch": 1.6665745092618192,
      "grad_norm": 0.40100711584091187,
      "learning_rate": 1.3447441466441957e-06,
      "loss": 0.4741,
      "step": 54252
    },
    {
      "epoch": 1.6666052283967683,
      "grad_norm": 0.4227490723133087,
      "learning_rate": 1.3445021001871305e-06,
      "loss": 0.4675,
      "step": 54253
    },
    {
      "epoch": 1.6666359475317174,
      "grad_norm": 0.40463513135910034,
      "learning_rate": 1.3442600739455891e-06,
      "loss": 0.3857,
      "step": 54254
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.4273422956466675,
      "learning_rate": 1.3440180679201308e-06,
      "loss": 0.4671,
      "step": 54255
    },
    {
      "epoch": 1.6666973858016159,
      "grad_norm": 0.4651884436607361,
      "learning_rate": 1.3437760821113255e-06,
      "loss": 0.4909,
      "step": 54256
    },
    {
      "epoch": 1.666728104936565,
      "grad_norm": 0.5786333680152893,
      "learning_rate": 1.3435341165197324e-06,
      "loss": 0.4935,
      "step": 54257
    },
    {
      "epoch": 1.666758824071514,
      "grad_norm": 0.4244515299797058,
      "learning_rate": 1.3432921711459213e-06,
      "loss": 0.4098,
      "step": 54258
    },
    {
      "epoch": 1.6667895432064634,
      "grad_norm": 0.37780332565307617,
      "learning_rate": 1.3430502459904548e-06,
      "loss": 0.4037,
      "step": 54259
    },
    {
      "epoch": 1.6668202623414126,
      "grad_norm": 0.45337390899658203,
      "learning_rate": 1.3428083410539017e-06,
      "loss": 0.4482,
      "step": 54260
    },
    {
      "epoch": 1.6668509814763617,
      "grad_norm": 0.47784337401390076,
      "learning_rate": 1.3425664563368224e-06,
      "loss": 0.51,
      "step": 54261
    },
    {
      "epoch": 1.6668817006113108,
      "grad_norm": 0.4815671443939209,
      "learning_rate": 1.3423245918397832e-06,
      "loss": 0.4881,
      "step": 54262
    },
    {
      "epoch": 1.66691241974626,
      "grad_norm": 0.4099365472793579,
      "learning_rate": 1.3420827475633502e-06,
      "loss": 0.4996,
      "step": 54263
    },
    {
      "epoch": 1.666943138881209,
      "grad_norm": 0.40634873509407043,
      "learning_rate": 1.3418409235080899e-06,
      "loss": 0.4818,
      "step": 54264
    },
    {
      "epoch": 1.6669738580161582,
      "grad_norm": 0.42893946170806885,
      "learning_rate": 1.3415991196745615e-06,
      "loss": 0.4246,
      "step": 54265
    },
    {
      "epoch": 1.6670045771511073,
      "grad_norm": 0.4021660387516022,
      "learning_rate": 1.3413573360633337e-06,
      "loss": 0.355,
      "step": 54266
    },
    {
      "epoch": 1.6670352962860566,
      "grad_norm": 0.5212284922599792,
      "learning_rate": 1.3411155726749702e-06,
      "loss": 0.4614,
      "step": 54267
    },
    {
      "epoch": 1.6670660154210057,
      "grad_norm": 0.43047699332237244,
      "learning_rate": 1.3408738295100364e-06,
      "loss": 0.4009,
      "step": 54268
    },
    {
      "epoch": 1.6670967345559549,
      "grad_norm": 0.486980140209198,
      "learning_rate": 1.3406321065690985e-06,
      "loss": 0.4722,
      "step": 54269
    },
    {
      "epoch": 1.6671274536909042,
      "grad_norm": 0.42578956484794617,
      "learning_rate": 1.3403904038527182e-06,
      "loss": 0.4601,
      "step": 54270
    },
    {
      "epoch": 1.6671581728258533,
      "grad_norm": 0.40161165595054626,
      "learning_rate": 1.3401487213614594e-06,
      "loss": 0.4506,
      "step": 54271
    },
    {
      "epoch": 1.6671888919608024,
      "grad_norm": 0.4764033257961273,
      "learning_rate": 1.3399070590958885e-06,
      "loss": 0.4684,
      "step": 54272
    },
    {
      "epoch": 1.6672196110957516,
      "grad_norm": 0.4829670786857605,
      "learning_rate": 1.3396654170565715e-06,
      "loss": 0.4565,
      "step": 54273
    },
    {
      "epoch": 1.6672503302307007,
      "grad_norm": 0.46068841218948364,
      "learning_rate": 1.3394237952440682e-06,
      "loss": 0.4626,
      "step": 54274
    },
    {
      "epoch": 1.6672810493656498,
      "grad_norm": 0.4567927420139313,
      "learning_rate": 1.3391821936589467e-06,
      "loss": 0.4547,
      "step": 54275
    },
    {
      "epoch": 1.667311768500599,
      "grad_norm": 0.40199750661849976,
      "learning_rate": 1.338940612301769e-06,
      "loss": 0.5163,
      "step": 54276
    },
    {
      "epoch": 1.667342487635548,
      "grad_norm": 0.46102792024612427,
      "learning_rate": 1.3386990511731024e-06,
      "loss": 0.5019,
      "step": 54277
    },
    {
      "epoch": 1.6673732067704974,
      "grad_norm": 0.3941836655139923,
      "learning_rate": 1.3384575102735076e-06,
      "loss": 0.43,
      "step": 54278
    },
    {
      "epoch": 1.6674039259054465,
      "grad_norm": 0.4404342770576477,
      "learning_rate": 1.3382159896035519e-06,
      "loss": 0.4702,
      "step": 54279
    },
    {
      "epoch": 1.6674346450403956,
      "grad_norm": 0.43778884410858154,
      "learning_rate": 1.3379744891637936e-06,
      "loss": 0.4211,
      "step": 54280
    },
    {
      "epoch": 1.667465364175345,
      "grad_norm": 0.4817923605442047,
      "learning_rate": 1.3377330089548046e-06,
      "loss": 0.4621,
      "step": 54281
    },
    {
      "epoch": 1.667496083310294,
      "grad_norm": 0.43653109669685364,
      "learning_rate": 1.3374915489771446e-06,
      "loss": 0.5001,
      "step": 54282
    },
    {
      "epoch": 1.6675268024452432,
      "grad_norm": 0.39458754658699036,
      "learning_rate": 1.3372501092313783e-06,
      "loss": 0.4738,
      "step": 54283
    },
    {
      "epoch": 1.6675575215801923,
      "grad_norm": 0.44063273072242737,
      "learning_rate": 1.3370086897180656e-06,
      "loss": 0.4529,
      "step": 54284
    },
    {
      "epoch": 1.6675882407151414,
      "grad_norm": 0.41877132654190063,
      "learning_rate": 1.3367672904377771e-06,
      "loss": 0.4344,
      "step": 54285
    },
    {
      "epoch": 1.6676189598500906,
      "grad_norm": 0.3829908072948456,
      "learning_rate": 1.3365259113910756e-06,
      "loss": 0.4028,
      "step": 54286
    },
    {
      "epoch": 1.6676496789850397,
      "grad_norm": 0.43951573967933655,
      "learning_rate": 1.3362845525785196e-06,
      "loss": 0.492,
      "step": 54287
    },
    {
      "epoch": 1.6676803981199888,
      "grad_norm": 0.42937180399894714,
      "learning_rate": 1.3360432140006796e-06,
      "loss": 0.4385,
      "step": 54288
    },
    {
      "epoch": 1.6677111172549381,
      "grad_norm": 0.4552462697029114,
      "learning_rate": 1.3358018956581098e-06,
      "loss": 0.4912,
      "step": 54289
    },
    {
      "epoch": 1.6677418363898873,
      "grad_norm": 0.4211706519126892,
      "learning_rate": 1.3355605975513853e-06,
      "loss": 0.5532,
      "step": 54290
    },
    {
      "epoch": 1.6677725555248364,
      "grad_norm": 0.4331173598766327,
      "learning_rate": 1.3353193196810622e-06,
      "loss": 0.443,
      "step": 54291
    },
    {
      "epoch": 1.6678032746597857,
      "grad_norm": 0.4918997287750244,
      "learning_rate": 1.3350780620477078e-06,
      "loss": 0.4709,
      "step": 54292
    },
    {
      "epoch": 1.6678339937947348,
      "grad_norm": 0.47483301162719727,
      "learning_rate": 1.3348368246518817e-06,
      "loss": 0.4256,
      "step": 54293
    },
    {
      "epoch": 1.667864712929684,
      "grad_norm": 0.42664211988449097,
      "learning_rate": 1.334595607494149e-06,
      "loss": 0.3994,
      "step": 54294
    },
    {
      "epoch": 1.667895432064633,
      "grad_norm": 0.445701539516449,
      "learning_rate": 1.3343544105750738e-06,
      "loss": 0.5361,
      "step": 54295
    },
    {
      "epoch": 1.6679261511995822,
      "grad_norm": 0.4233505129814148,
      "learning_rate": 1.3341132338952212e-06,
      "loss": 0.4518,
      "step": 54296
    },
    {
      "epoch": 1.6679568703345313,
      "grad_norm": 0.420486718416214,
      "learning_rate": 1.3338720774551494e-06,
      "loss": 0.3617,
      "step": 54297
    },
    {
      "epoch": 1.6679875894694804,
      "grad_norm": 0.6165467500686646,
      "learning_rate": 1.3336309412554248e-06,
      "loss": 0.4785,
      "step": 54298
    },
    {
      "epoch": 1.6680183086044296,
      "grad_norm": 0.42139169573783875,
      "learning_rate": 1.3333898252966115e-06,
      "loss": 0.419,
      "step": 54299
    },
    {
      "epoch": 1.668049027739379,
      "grad_norm": 0.44888007640838623,
      "learning_rate": 1.3331487295792734e-06,
      "loss": 0.4511,
      "step": 54300
    },
    {
      "epoch": 1.668079746874328,
      "grad_norm": 0.4599781334400177,
      "learning_rate": 1.3329076541039686e-06,
      "loss": 0.4382,
      "step": 54301
    },
    {
      "epoch": 1.6681104660092771,
      "grad_norm": 0.5240744352340698,
      "learning_rate": 1.332666598871264e-06,
      "loss": 0.5077,
      "step": 54302
    },
    {
      "epoch": 1.6681411851442265,
      "grad_norm": 0.43768784403800964,
      "learning_rate": 1.332425563881722e-06,
      "loss": 0.4522,
      "step": 54303
    },
    {
      "epoch": 1.6681719042791756,
      "grad_norm": 0.41249606013298035,
      "learning_rate": 1.3321845491359053e-06,
      "loss": 0.4163,
      "step": 54304
    },
    {
      "epoch": 1.6682026234141247,
      "grad_norm": 0.4086698889732361,
      "learning_rate": 1.3319435546343785e-06,
      "loss": 0.5247,
      "step": 54305
    },
    {
      "epoch": 1.6682333425490738,
      "grad_norm": 0.4157974421977997,
      "learning_rate": 1.3317025803777017e-06,
      "loss": 0.467,
      "step": 54306
    },
    {
      "epoch": 1.668264061684023,
      "grad_norm": 0.3982767164707184,
      "learning_rate": 1.3314616263664381e-06,
      "loss": 0.5221,
      "step": 54307
    },
    {
      "epoch": 1.668294780818972,
      "grad_norm": 0.44355812668800354,
      "learning_rate": 1.3312206926011517e-06,
      "loss": 0.4698,
      "step": 54308
    },
    {
      "epoch": 1.6683254999539212,
      "grad_norm": 0.4603734016418457,
      "learning_rate": 1.3309797790824064e-06,
      "loss": 0.5071,
      "step": 54309
    },
    {
      "epoch": 1.6683562190888703,
      "grad_norm": 0.4307257831096649,
      "learning_rate": 1.3307388858107617e-06,
      "loss": 0.5526,
      "step": 54310
    },
    {
      "epoch": 1.6683869382238197,
      "grad_norm": 0.46217137575149536,
      "learning_rate": 1.3304980127867818e-06,
      "loss": 0.4863,
      "step": 54311
    },
    {
      "epoch": 1.6684176573587688,
      "grad_norm": 0.4107188880443573,
      "learning_rate": 1.3302571600110292e-06,
      "loss": 0.4816,
      "step": 54312
    },
    {
      "epoch": 1.668448376493718,
      "grad_norm": 0.4330778121948242,
      "learning_rate": 1.3300163274840683e-06,
      "loss": 0.4259,
      "step": 54313
    },
    {
      "epoch": 1.6684790956286673,
      "grad_norm": 0.4634239375591278,
      "learning_rate": 1.3297755152064583e-06,
      "loss": 0.4924,
      "step": 54314
    },
    {
      "epoch": 1.6685098147636164,
      "grad_norm": 0.4485389292240143,
      "learning_rate": 1.3295347231787648e-06,
      "loss": 0.4708,
      "step": 54315
    },
    {
      "epoch": 1.6685405338985655,
      "grad_norm": 0.43646669387817383,
      "learning_rate": 1.3292939514015435e-06,
      "loss": 0.4014,
      "step": 54316
    },
    {
      "epoch": 1.6685712530335146,
      "grad_norm": 0.4202877879142761,
      "learning_rate": 1.3290531998753675e-06,
      "loss": 0.4625,
      "step": 54317
    },
    {
      "epoch": 1.6686019721684637,
      "grad_norm": 0.5020508170127869,
      "learning_rate": 1.3288124686007897e-06,
      "loss": 0.4858,
      "step": 54318
    },
    {
      "epoch": 1.6686326913034129,
      "grad_norm": 0.43564146757125854,
      "learning_rate": 1.3285717575783797e-06,
      "loss": 0.4813,
      "step": 54319
    },
    {
      "epoch": 1.668663410438362,
      "grad_norm": 0.3838028907775879,
      "learning_rate": 1.3283310668086923e-06,
      "loss": 0.427,
      "step": 54320
    },
    {
      "epoch": 1.668694129573311,
      "grad_norm": 0.7100500464439392,
      "learning_rate": 1.3280903962922943e-06,
      "loss": 0.5031,
      "step": 54321
    },
    {
      "epoch": 1.6687248487082602,
      "grad_norm": 0.41123300790786743,
      "learning_rate": 1.3278497460297468e-06,
      "loss": 0.5224,
      "step": 54322
    },
    {
      "epoch": 1.6687555678432096,
      "grad_norm": 0.384831041097641,
      "learning_rate": 1.3276091160216108e-06,
      "loss": 0.5048,
      "step": 54323
    },
    {
      "epoch": 1.6687862869781587,
      "grad_norm": 0.46772491931915283,
      "learning_rate": 1.3273685062684528e-06,
      "loss": 0.5152,
      "step": 54324
    },
    {
      "epoch": 1.668817006113108,
      "grad_norm": 0.4226700961589813,
      "learning_rate": 1.3271279167708263e-06,
      "loss": 0.513,
      "step": 54325
    },
    {
      "epoch": 1.6688477252480571,
      "grad_norm": 0.45568883419036865,
      "learning_rate": 1.3268873475293032e-06,
      "loss": 0.4789,
      "step": 54326
    },
    {
      "epoch": 1.6688784443830063,
      "grad_norm": 0.4484321177005768,
      "learning_rate": 1.3266467985444375e-06,
      "loss": 0.4354,
      "step": 54327
    },
    {
      "epoch": 1.6689091635179554,
      "grad_norm": 0.4911480247974396,
      "learning_rate": 1.3264062698167967e-06,
      "loss": 0.442,
      "step": 54328
    },
    {
      "epoch": 1.6689398826529045,
      "grad_norm": 0.46112826466560364,
      "learning_rate": 1.326165761346937e-06,
      "loss": 0.4201,
      "step": 54329
    },
    {
      "epoch": 1.6689706017878536,
      "grad_norm": 0.4952325224876404,
      "learning_rate": 1.3259252731354234e-06,
      "loss": 0.4383,
      "step": 54330
    },
    {
      "epoch": 1.6690013209228027,
      "grad_norm": 0.4735056459903717,
      "learning_rate": 1.3256848051828176e-06,
      "loss": 0.4775,
      "step": 54331
    },
    {
      "epoch": 1.6690320400577519,
      "grad_norm": 0.4086689352989197,
      "learning_rate": 1.3254443574896826e-06,
      "loss": 0.4053,
      "step": 54332
    },
    {
      "epoch": 1.669062759192701,
      "grad_norm": 0.5060744881629944,
      "learning_rate": 1.3252039300565756e-06,
      "loss": 0.4753,
      "step": 54333
    },
    {
      "epoch": 1.6690934783276503,
      "grad_norm": 0.49627044796943665,
      "learning_rate": 1.3249635228840606e-06,
      "loss": 0.5888,
      "step": 54334
    },
    {
      "epoch": 1.6691241974625994,
      "grad_norm": 0.40890607237815857,
      "learning_rate": 1.3247231359726998e-06,
      "loss": 0.464,
      "step": 54335
    },
    {
      "epoch": 1.6691549165975488,
      "grad_norm": 0.4044049382209778,
      "learning_rate": 1.3244827693230555e-06,
      "loss": 0.4567,
      "step": 54336
    },
    {
      "epoch": 1.669185635732498,
      "grad_norm": 0.4151325523853302,
      "learning_rate": 1.3242424229356854e-06,
      "loss": 0.4367,
      "step": 54337
    },
    {
      "epoch": 1.669216354867447,
      "grad_norm": 0.6155727505683899,
      "learning_rate": 1.3240020968111534e-06,
      "loss": 0.4215,
      "step": 54338
    },
    {
      "epoch": 1.6692470740023961,
      "grad_norm": 0.4359005093574524,
      "learning_rate": 1.32376179095002e-06,
      "loss": 0.4013,
      "step": 54339
    },
    {
      "epoch": 1.6692777931373453,
      "grad_norm": 0.4150978624820709,
      "learning_rate": 1.3235215053528471e-06,
      "loss": 0.4847,
      "step": 54340
    },
    {
      "epoch": 1.6693085122722944,
      "grad_norm": 0.4213534891605377,
      "learning_rate": 1.3232812400201977e-06,
      "loss": 0.5299,
      "step": 54341
    },
    {
      "epoch": 1.6693392314072435,
      "grad_norm": 0.4808160066604614,
      "learning_rate": 1.323040994952629e-06,
      "loss": 0.5099,
      "step": 54342
    },
    {
      "epoch": 1.6693699505421926,
      "grad_norm": 0.43564295768737793,
      "learning_rate": 1.322800770150704e-06,
      "loss": 0.4127,
      "step": 54343
    },
    {
      "epoch": 1.6694006696771417,
      "grad_norm": 0.425988107919693,
      "learning_rate": 1.3225605656149843e-06,
      "loss": 0.5071,
      "step": 54344
    },
    {
      "epoch": 1.669431388812091,
      "grad_norm": 0.41838476061820984,
      "learning_rate": 1.3223203813460318e-06,
      "loss": 0.446,
      "step": 54345
    },
    {
      "epoch": 1.6694621079470402,
      "grad_norm": 0.48170945048332214,
      "learning_rate": 1.3220802173444048e-06,
      "loss": 0.4752,
      "step": 54346
    },
    {
      "epoch": 1.6694928270819893,
      "grad_norm": 0.4292597770690918,
      "learning_rate": 1.3218400736106652e-06,
      "loss": 0.3916,
      "step": 54347
    },
    {
      "epoch": 1.6695235462169387,
      "grad_norm": 0.4533405601978302,
      "learning_rate": 1.3215999501453735e-06,
      "loss": 0.5233,
      "step": 54348
    },
    {
      "epoch": 1.6695542653518878,
      "grad_norm": 0.4346359074115753,
      "learning_rate": 1.321359846949094e-06,
      "loss": 0.4903,
      "step": 54349
    },
    {
      "epoch": 1.669584984486837,
      "grad_norm": 0.43272072076797485,
      "learning_rate": 1.3211197640223827e-06,
      "loss": 0.4997,
      "step": 54350
    },
    {
      "epoch": 1.669615703621786,
      "grad_norm": 0.403714120388031,
      "learning_rate": 1.3208797013658038e-06,
      "loss": 0.4293,
      "step": 54351
    },
    {
      "epoch": 1.6696464227567351,
      "grad_norm": 0.4234665632247925,
      "learning_rate": 1.320639658979912e-06,
      "loss": 0.4587,
      "step": 54352
    },
    {
      "epoch": 1.6696771418916843,
      "grad_norm": 0.44913390278816223,
      "learning_rate": 1.3203996368652772e-06,
      "loss": 0.5301,
      "step": 54353
    },
    {
      "epoch": 1.6697078610266334,
      "grad_norm": 0.4479752480983734,
      "learning_rate": 1.3201596350224532e-06,
      "loss": 0.2974,
      "step": 54354
    },
    {
      "epoch": 1.6697385801615825,
      "grad_norm": 0.44454899430274963,
      "learning_rate": 1.3199196534520053e-06,
      "loss": 0.4885,
      "step": 54355
    },
    {
      "epoch": 1.6697692992965318,
      "grad_norm": 0.41484132409095764,
      "learning_rate": 1.3196796921544885e-06,
      "loss": 0.4417,
      "step": 54356
    },
    {
      "epoch": 1.669800018431481,
      "grad_norm": 0.45197317004203796,
      "learning_rate": 1.3194397511304656e-06,
      "loss": 0.4923,
      "step": 54357
    },
    {
      "epoch": 1.66983073756643,
      "grad_norm": 0.43910282850265503,
      "learning_rate": 1.3191998303804976e-06,
      "loss": 0.4979,
      "step": 54358
    },
    {
      "epoch": 1.6698614567013794,
      "grad_norm": 0.4536969065666199,
      "learning_rate": 1.3189599299051447e-06,
      "loss": 0.4535,
      "step": 54359
    },
    {
      "epoch": 1.6698921758363285,
      "grad_norm": 0.4557800889015198,
      "learning_rate": 1.3187200497049702e-06,
      "loss": 0.4375,
      "step": 54360
    },
    {
      "epoch": 1.6699228949712777,
      "grad_norm": 0.38002148270606995,
      "learning_rate": 1.3184801897805277e-06,
      "loss": 0.4542,
      "step": 54361
    },
    {
      "epoch": 1.6699536141062268,
      "grad_norm": 0.43201327323913574,
      "learning_rate": 1.3182403501323825e-06,
      "loss": 0.4861,
      "step": 54362
    },
    {
      "epoch": 1.669984333241176,
      "grad_norm": 0.4563651978969574,
      "learning_rate": 1.318000530761092e-06,
      "loss": 0.4206,
      "step": 54363
    },
    {
      "epoch": 1.670015052376125,
      "grad_norm": 0.4045008420944214,
      "learning_rate": 1.3177607316672202e-06,
      "loss": 0.5047,
      "step": 54364
    },
    {
      "epoch": 1.6700457715110741,
      "grad_norm": 0.43886107206344604,
      "learning_rate": 1.3175209528513222e-06,
      "loss": 0.4864,
      "step": 54365
    },
    {
      "epoch": 1.6700764906460233,
      "grad_norm": 0.4509549140930176,
      "learning_rate": 1.3172811943139606e-06,
      "loss": 0.4755,
      "step": 54366
    },
    {
      "epoch": 1.6701072097809726,
      "grad_norm": 0.4531894624233246,
      "learning_rate": 1.3170414560556955e-06,
      "loss": 0.5498,
      "step": 54367
    },
    {
      "epoch": 1.6701379289159217,
      "grad_norm": 0.4032810926437378,
      "learning_rate": 1.3168017380770893e-06,
      "loss": 0.411,
      "step": 54368
    },
    {
      "epoch": 1.6701686480508708,
      "grad_norm": 0.4566320776939392,
      "learning_rate": 1.3165620403786948e-06,
      "loss": 0.3834,
      "step": 54369
    },
    {
      "epoch": 1.6701993671858202,
      "grad_norm": 0.41383734345436096,
      "learning_rate": 1.3163223629610777e-06,
      "loss": 0.4288,
      "step": 54370
    },
    {
      "epoch": 1.6702300863207693,
      "grad_norm": 0.45296990871429443,
      "learning_rate": 1.316082705824796e-06,
      "loss": 0.4794,
      "step": 54371
    },
    {
      "epoch": 1.6702608054557184,
      "grad_norm": 0.42399436235427856,
      "learning_rate": 1.3158430689704117e-06,
      "loss": 0.4617,
      "step": 54372
    },
    {
      "epoch": 1.6702915245906675,
      "grad_norm": 0.47743159532546997,
      "learning_rate": 1.3156034523984794e-06,
      "loss": 0.4794,
      "step": 54373
    },
    {
      "epoch": 1.6703222437256167,
      "grad_norm": 0.4342379570007324,
      "learning_rate": 1.3153638561095628e-06,
      "loss": 0.4628,
      "step": 54374
    },
    {
      "epoch": 1.6703529628605658,
      "grad_norm": 0.4243640601634979,
      "learning_rate": 1.3151242801042207e-06,
      "loss": 0.3987,
      "step": 54375
    },
    {
      "epoch": 1.670383681995515,
      "grad_norm": 0.4670792520046234,
      "learning_rate": 1.3148847243830132e-06,
      "loss": 0.3948,
      "step": 54376
    },
    {
      "epoch": 1.670414401130464,
      "grad_norm": 0.46429845690727234,
      "learning_rate": 1.3146451889464984e-06,
      "loss": 0.4225,
      "step": 54377
    },
    {
      "epoch": 1.6704451202654134,
      "grad_norm": 0.42769482731819153,
      "learning_rate": 1.3144056737952348e-06,
      "loss": 0.4715,
      "step": 54378
    },
    {
      "epoch": 1.6704758394003625,
      "grad_norm": 0.4270959794521332,
      "learning_rate": 1.3141661789297844e-06,
      "loss": 0.5456,
      "step": 54379
    },
    {
      "epoch": 1.6705065585353116,
      "grad_norm": 0.42902839183807373,
      "learning_rate": 1.3139267043507054e-06,
      "loss": 0.521,
      "step": 54380
    },
    {
      "epoch": 1.670537277670261,
      "grad_norm": 0.45253118872642517,
      "learning_rate": 1.3136872500585585e-06,
      "loss": 0.451,
      "step": 54381
    },
    {
      "epoch": 1.67056799680521,
      "grad_norm": 0.4435786008834839,
      "learning_rate": 1.313447816053901e-06,
      "loss": 0.4524,
      "step": 54382
    },
    {
      "epoch": 1.6705987159401592,
      "grad_norm": 0.41917040944099426,
      "learning_rate": 1.3132084023372938e-06,
      "loss": 0.3873,
      "step": 54383
    },
    {
      "epoch": 1.6706294350751083,
      "grad_norm": 0.44240322709083557,
      "learning_rate": 1.3129690089092905e-06,
      "loss": 0.4531,
      "step": 54384
    },
    {
      "epoch": 1.6706601542100574,
      "grad_norm": 0.41442540287971497,
      "learning_rate": 1.3127296357704599e-06,
      "loss": 0.4087,
      "step": 54385
    },
    {
      "epoch": 1.6706908733450065,
      "grad_norm": 0.4491106867790222,
      "learning_rate": 1.3124902829213538e-06,
      "loss": 0.5001,
      "step": 54386
    },
    {
      "epoch": 1.6707215924799557,
      "grad_norm": 0.43481236696243286,
      "learning_rate": 1.3122509503625346e-06,
      "loss": 0.4685,
      "step": 54387
    },
    {
      "epoch": 1.6707523116149048,
      "grad_norm": 0.4443034529685974,
      "learning_rate": 1.3120116380945568e-06,
      "loss": 0.4165,
      "step": 54388
    },
    {
      "epoch": 1.6707830307498541,
      "grad_norm": 0.4413386881351471,
      "learning_rate": 1.3117723461179865e-06,
      "loss": 0.4404,
      "step": 54389
    },
    {
      "epoch": 1.6708137498848032,
      "grad_norm": 0.4285559356212616,
      "learning_rate": 1.3115330744333765e-06,
      "loss": 0.4441,
      "step": 54390
    },
    {
      "epoch": 1.6708444690197524,
      "grad_norm": 0.41869765520095825,
      "learning_rate": 1.3112938230412897e-06,
      "loss": 0.419,
      "step": 54391
    },
    {
      "epoch": 1.6708751881547017,
      "grad_norm": 0.410656601190567,
      "learning_rate": 1.3110545919422813e-06,
      "loss": 0.4537,
      "step": 54392
    },
    {
      "epoch": 1.6709059072896508,
      "grad_norm": 0.42649728059768677,
      "learning_rate": 1.3108153811369117e-06,
      "loss": 0.4559,
      "step": 54393
    },
    {
      "epoch": 1.6709366264246,
      "grad_norm": 0.4368041157722473,
      "learning_rate": 1.3105761906257397e-06,
      "loss": 0.3937,
      "step": 54394
    },
    {
      "epoch": 1.670967345559549,
      "grad_norm": 0.4393388032913208,
      "learning_rate": 1.3103370204093236e-06,
      "loss": 0.4464,
      "step": 54395
    },
    {
      "epoch": 1.6709980646944982,
      "grad_norm": 0.4140395522117615,
      "learning_rate": 1.310097870488224e-06,
      "loss": 0.4911,
      "step": 54396
    },
    {
      "epoch": 1.6710287838294473,
      "grad_norm": 0.48010289669036865,
      "learning_rate": 1.309858740862996e-06,
      "loss": 0.4234,
      "step": 54397
    },
    {
      "epoch": 1.6710595029643964,
      "grad_norm": 0.43331870436668396,
      "learning_rate": 1.3096196315342003e-06,
      "loss": 0.452,
      "step": 54398
    },
    {
      "epoch": 1.6710902220993455,
      "grad_norm": 0.4172593951225281,
      "learning_rate": 1.3093805425023941e-06,
      "loss": 0.4778,
      "step": 54399
    },
    {
      "epoch": 1.6711209412342949,
      "grad_norm": 0.40419042110443115,
      "learning_rate": 1.3091414737681385e-06,
      "loss": 0.483,
      "step": 54400
    },
    {
      "epoch": 1.671151660369244,
      "grad_norm": 0.48304328322410583,
      "learning_rate": 1.3089024253319894e-06,
      "loss": 0.41,
      "step": 54401
    },
    {
      "epoch": 1.6711823795041931,
      "grad_norm": 0.4408376216888428,
      "learning_rate": 1.308663397194504e-06,
      "loss": 0.4282,
      "step": 54402
    },
    {
      "epoch": 1.6712130986391425,
      "grad_norm": 0.4441916346549988,
      "learning_rate": 1.308424389356243e-06,
      "loss": 0.5761,
      "step": 54403
    },
    {
      "epoch": 1.6712438177740916,
      "grad_norm": 0.4393273890018463,
      "learning_rate": 1.3081854018177653e-06,
      "loss": 0.5035,
      "step": 54404
    },
    {
      "epoch": 1.6712745369090407,
      "grad_norm": 0.47196656465530396,
      "learning_rate": 1.3079464345796266e-06,
      "loss": 0.4281,
      "step": 54405
    },
    {
      "epoch": 1.6713052560439898,
      "grad_norm": 0.4263796806335449,
      "learning_rate": 1.3077074876423857e-06,
      "loss": 0.4514,
      "step": 54406
    },
    {
      "epoch": 1.671335975178939,
      "grad_norm": 0.46177029609680176,
      "learning_rate": 1.3074685610066007e-06,
      "loss": 0.4669,
      "step": 54407
    },
    {
      "epoch": 1.671366694313888,
      "grad_norm": 0.4265259802341461,
      "learning_rate": 1.3072296546728315e-06,
      "loss": 0.421,
      "step": 54408
    },
    {
      "epoch": 1.6713974134488372,
      "grad_norm": 0.4917981028556824,
      "learning_rate": 1.306990768641634e-06,
      "loss": 0.4286,
      "step": 54409
    },
    {
      "epoch": 1.6714281325837863,
      "grad_norm": 0.4864543378353119,
      "learning_rate": 1.3067519029135656e-06,
      "loss": 0.4659,
      "step": 54410
    },
    {
      "epoch": 1.6714588517187356,
      "grad_norm": 0.4020720422267914,
      "learning_rate": 1.306513057489185e-06,
      "loss": 0.459,
      "step": 54411
    },
    {
      "epoch": 1.6714895708536848,
      "grad_norm": 0.44430413842201233,
      "learning_rate": 1.3062742323690525e-06,
      "loss": 0.4294,
      "step": 54412
    },
    {
      "epoch": 1.671520289988634,
      "grad_norm": 0.48480942845344543,
      "learning_rate": 1.3060354275537223e-06,
      "loss": 0.4963,
      "step": 54413
    },
    {
      "epoch": 1.6715510091235832,
      "grad_norm": 0.47804924845695496,
      "learning_rate": 1.305796643043753e-06,
      "loss": 0.51,
      "step": 54414
    },
    {
      "epoch": 1.6715817282585324,
      "grad_norm": 0.4239758849143982,
      "learning_rate": 1.3055578788397026e-06,
      "loss": 0.5382,
      "step": 54415
    },
    {
      "epoch": 1.6716124473934815,
      "grad_norm": 0.4740908443927765,
      "learning_rate": 1.3053191349421302e-06,
      "loss": 0.3998,
      "step": 54416
    },
    {
      "epoch": 1.6716431665284306,
      "grad_norm": 0.4550797939300537,
      "learning_rate": 1.3050804113515926e-06,
      "loss": 0.4808,
      "step": 54417
    },
    {
      "epoch": 1.6716738856633797,
      "grad_norm": 0.44966983795166016,
      "learning_rate": 1.304841708068646e-06,
      "loss": 0.4171,
      "step": 54418
    },
    {
      "epoch": 1.6717046047983288,
      "grad_norm": 0.43167734146118164,
      "learning_rate": 1.3046030250938513e-06,
      "loss": 0.4569,
      "step": 54419
    },
    {
      "epoch": 1.671735323933278,
      "grad_norm": 0.4648425281047821,
      "learning_rate": 1.304364362427758e-06,
      "loss": 0.4695,
      "step": 54420
    },
    {
      "epoch": 1.671766043068227,
      "grad_norm": 0.4014299213886261,
      "learning_rate": 1.3041257200709346e-06,
      "loss": 0.4482,
      "step": 54421
    },
    {
      "epoch": 1.6717967622031764,
      "grad_norm": 0.41433990001678467,
      "learning_rate": 1.3038870980239292e-06,
      "loss": 0.4588,
      "step": 54422
    },
    {
      "epoch": 1.6718274813381255,
      "grad_norm": 0.4286716878414154,
      "learning_rate": 1.3036484962873064e-06,
      "loss": 0.4679,
      "step": 54423
    },
    {
      "epoch": 1.6718582004730747,
      "grad_norm": 0.45731690526008606,
      "learning_rate": 1.3034099148616174e-06,
      "loss": 0.4797,
      "step": 54424
    },
    {
      "epoch": 1.671888919608024,
      "grad_norm": 0.4088975489139557,
      "learning_rate": 1.303171353747421e-06,
      "loss": 0.4788,
      "step": 54425
    },
    {
      "epoch": 1.6719196387429731,
      "grad_norm": 0.6398635506629944,
      "learning_rate": 1.3029328129452768e-06,
      "loss": 0.4953,
      "step": 54426
    },
    {
      "epoch": 1.6719503578779222,
      "grad_norm": 0.449864000082016,
      "learning_rate": 1.3026942924557407e-06,
      "loss": 0.4497,
      "step": 54427
    },
    {
      "epoch": 1.6719810770128714,
      "grad_norm": 0.4521929621696472,
      "learning_rate": 1.302455792279369e-06,
      "loss": 0.493,
      "step": 54428
    },
    {
      "epoch": 1.6720117961478205,
      "grad_norm": 0.46655571460723877,
      "learning_rate": 1.302217312416718e-06,
      "loss": 0.4604,
      "step": 54429
    },
    {
      "epoch": 1.6720425152827696,
      "grad_norm": 0.4898834228515625,
      "learning_rate": 1.3019788528683474e-06,
      "loss": 0.4484,
      "step": 54430
    },
    {
      "epoch": 1.6720732344177187,
      "grad_norm": 0.46417713165283203,
      "learning_rate": 1.301740413634811e-06,
      "loss": 0.4282,
      "step": 54431
    },
    {
      "epoch": 1.6721039535526678,
      "grad_norm": 0.4446687698364258,
      "learning_rate": 1.3015019947166707e-06,
      "loss": 0.4471,
      "step": 54432
    },
    {
      "epoch": 1.672134672687617,
      "grad_norm": 0.44657814502716064,
      "learning_rate": 1.3012635961144772e-06,
      "loss": 0.535,
      "step": 54433
    },
    {
      "epoch": 1.6721653918225663,
      "grad_norm": 0.39961695671081543,
      "learning_rate": 1.3010252178287908e-06,
      "loss": 0.4114,
      "step": 54434
    },
    {
      "epoch": 1.6721961109575154,
      "grad_norm": 0.3957762122154236,
      "learning_rate": 1.300786859860167e-06,
      "loss": 0.4219,
      "step": 54435
    },
    {
      "epoch": 1.6722268300924648,
      "grad_norm": 0.4453742206096649,
      "learning_rate": 1.3005485222091652e-06,
      "loss": 0.4139,
      "step": 54436
    },
    {
      "epoch": 1.6722575492274139,
      "grad_norm": 0.46630367636680603,
      "learning_rate": 1.3003102048763371e-06,
      "loss": 0.4868,
      "step": 54437
    },
    {
      "epoch": 1.672288268362363,
      "grad_norm": 0.4495808482170105,
      "learning_rate": 1.3000719078622426e-06,
      "loss": 0.499,
      "step": 54438
    },
    {
      "epoch": 1.6723189874973121,
      "grad_norm": 0.42383238673210144,
      "learning_rate": 1.2998336311674387e-06,
      "loss": 0.4844,
      "step": 54439
    },
    {
      "epoch": 1.6723497066322612,
      "grad_norm": 0.409486323595047,
      "learning_rate": 1.2995953747924817e-06,
      "loss": 0.4676,
      "step": 54440
    },
    {
      "epoch": 1.6723804257672104,
      "grad_norm": 0.4449448883533478,
      "learning_rate": 1.2993571387379255e-06,
      "loss": 0.4962,
      "step": 54441
    },
    {
      "epoch": 1.6724111449021595,
      "grad_norm": 0.4410984516143799,
      "learning_rate": 1.2991189230043289e-06,
      "loss": 0.4296,
      "step": 54442
    },
    {
      "epoch": 1.6724418640371086,
      "grad_norm": 0.46810758113861084,
      "learning_rate": 1.2988807275922478e-06,
      "loss": 0.4661,
      "step": 54443
    },
    {
      "epoch": 1.6724725831720577,
      "grad_norm": 0.43995845317840576,
      "learning_rate": 1.2986425525022394e-06,
      "loss": 0.4764,
      "step": 54444
    },
    {
      "epoch": 1.672503302307007,
      "grad_norm": 0.44160762429237366,
      "learning_rate": 1.2984043977348581e-06,
      "loss": 0.4001,
      "step": 54445
    },
    {
      "epoch": 1.6725340214419562,
      "grad_norm": 0.4364962577819824,
      "learning_rate": 1.2981662632906634e-06,
      "loss": 0.5169,
      "step": 54446
    },
    {
      "epoch": 1.6725647405769055,
      "grad_norm": 0.43182873725891113,
      "learning_rate": 1.2979281491702035e-06,
      "loss": 0.5,
      "step": 54447
    },
    {
      "epoch": 1.6725954597118546,
      "grad_norm": 0.4124847948551178,
      "learning_rate": 1.2976900553740456e-06,
      "loss": 0.4431,
      "step": 54448
    },
    {
      "epoch": 1.6726261788468038,
      "grad_norm": 0.4413508474826813,
      "learning_rate": 1.2974519819027375e-06,
      "loss": 0.4721,
      "step": 54449
    },
    {
      "epoch": 1.6726568979817529,
      "grad_norm": 0.5324807167053223,
      "learning_rate": 1.2972139287568385e-06,
      "loss": 0.3896,
      "step": 54450
    },
    {
      "epoch": 1.672687617116702,
      "grad_norm": 0.4742293357849121,
      "learning_rate": 1.296975895936904e-06,
      "loss": 0.4713,
      "step": 54451
    },
    {
      "epoch": 1.6727183362516511,
      "grad_norm": 0.41823142766952515,
      "learning_rate": 1.2967378834434896e-06,
      "loss": 0.4356,
      "step": 54452
    },
    {
      "epoch": 1.6727490553866002,
      "grad_norm": 0.441262423992157,
      "learning_rate": 1.2964998912771555e-06,
      "loss": 0.4722,
      "step": 54453
    },
    {
      "epoch": 1.6727797745215494,
      "grad_norm": 0.4522722661495209,
      "learning_rate": 1.2962619194384497e-06,
      "loss": 0.4626,
      "step": 54454
    },
    {
      "epoch": 1.6728104936564985,
      "grad_norm": 0.4266628623008728,
      "learning_rate": 1.2960239679279352e-06,
      "loss": 0.4609,
      "step": 54455
    },
    {
      "epoch": 1.6728412127914478,
      "grad_norm": 0.45697155594825745,
      "learning_rate": 1.2957860367461595e-06,
      "loss": 0.4076,
      "step": 54456
    },
    {
      "epoch": 1.672871931926397,
      "grad_norm": 0.4353219270706177,
      "learning_rate": 1.2955481258936887e-06,
      "loss": 0.4717,
      "step": 54457
    },
    {
      "epoch": 1.672902651061346,
      "grad_norm": 0.4091307818889618,
      "learning_rate": 1.29531023537107e-06,
      "loss": 0.4467,
      "step": 54458
    },
    {
      "epoch": 1.6729333701962954,
      "grad_norm": 0.3693670332431793,
      "learning_rate": 1.2950723651788655e-06,
      "loss": 0.4521,
      "step": 54459
    },
    {
      "epoch": 1.6729640893312445,
      "grad_norm": 0.3998169004917145,
      "learning_rate": 1.2948345153176245e-06,
      "loss": 0.4109,
      "step": 54460
    },
    {
      "epoch": 1.6729948084661936,
      "grad_norm": 0.5231122374534607,
      "learning_rate": 1.2945966857879056e-06,
      "loss": 0.5415,
      "step": 54461
    },
    {
      "epoch": 1.6730255276011428,
      "grad_norm": 0.47089001536369324,
      "learning_rate": 1.2943588765902648e-06,
      "loss": 0.4559,
      "step": 54462
    },
    {
      "epoch": 1.6730562467360919,
      "grad_norm": 0.4614548981189728,
      "learning_rate": 1.2941210877252575e-06,
      "loss": 0.4994,
      "step": 54463
    },
    {
      "epoch": 1.673086965871041,
      "grad_norm": 0.43589556217193604,
      "learning_rate": 1.2938833191934375e-06,
      "loss": 0.4413,
      "step": 54464
    },
    {
      "epoch": 1.6731176850059901,
      "grad_norm": 0.4130564033985138,
      "learning_rate": 1.293645570995361e-06,
      "loss": 0.4823,
      "step": 54465
    },
    {
      "epoch": 1.6731484041409392,
      "grad_norm": 0.4394238293170929,
      "learning_rate": 1.2934078431315823e-06,
      "loss": 0.409,
      "step": 54466
    },
    {
      "epoch": 1.6731791232758886,
      "grad_norm": 0.42293861508369446,
      "learning_rate": 1.2931701356026605e-06,
      "loss": 0.4819,
      "step": 54467
    },
    {
      "epoch": 1.6732098424108377,
      "grad_norm": 0.42212891578674316,
      "learning_rate": 1.2929324484091465e-06,
      "loss": 0.4938,
      "step": 54468
    },
    {
      "epoch": 1.6732405615457868,
      "grad_norm": 0.41143694519996643,
      "learning_rate": 1.2926947815515956e-06,
      "loss": 0.4152,
      "step": 54469
    },
    {
      "epoch": 1.6732712806807362,
      "grad_norm": 0.46037569642066956,
      "learning_rate": 1.2924571350305647e-06,
      "loss": 0.4528,
      "step": 54470
    },
    {
      "epoch": 1.6733019998156853,
      "grad_norm": 0.39704129099845886,
      "learning_rate": 1.2922195088466083e-06,
      "loss": 0.4267,
      "step": 54471
    },
    {
      "epoch": 1.6733327189506344,
      "grad_norm": 0.45447927713394165,
      "learning_rate": 1.2919819030002833e-06,
      "loss": 0.4597,
      "step": 54472
    },
    {
      "epoch": 1.6733634380855835,
      "grad_norm": 0.4284869432449341,
      "learning_rate": 1.2917443174921407e-06,
      "loss": 0.4923,
      "step": 54473
    },
    {
      "epoch": 1.6733941572205326,
      "grad_norm": 0.450054794549942,
      "learning_rate": 1.2915067523227375e-06,
      "loss": 0.432,
      "step": 54474
    },
    {
      "epoch": 1.6734248763554818,
      "grad_norm": 0.43818992376327515,
      "learning_rate": 1.291269207492628e-06,
      "loss": 0.4053,
      "step": 54475
    },
    {
      "epoch": 1.6734555954904309,
      "grad_norm": 0.4418097138404846,
      "learning_rate": 1.2910316830023705e-06,
      "loss": 0.4818,
      "step": 54476
    },
    {
      "epoch": 1.67348631462538,
      "grad_norm": 0.5094979405403137,
      "learning_rate": 1.2907941788525148e-06,
      "loss": 0.4122,
      "step": 54477
    },
    {
      "epoch": 1.6735170337603293,
      "grad_norm": 0.48221391439437866,
      "learning_rate": 1.2905566950436166e-06,
      "loss": 0.4434,
      "step": 54478
    },
    {
      "epoch": 1.6735477528952785,
      "grad_norm": 0.4278148114681244,
      "learning_rate": 1.2903192315762314e-06,
      "loss": 0.4255,
      "step": 54479
    },
    {
      "epoch": 1.6735784720302276,
      "grad_norm": 0.44932886958122253,
      "learning_rate": 1.2900817884509165e-06,
      "loss": 0.4902,
      "step": 54480
    },
    {
      "epoch": 1.673609191165177,
      "grad_norm": 0.43650001287460327,
      "learning_rate": 1.2898443656682213e-06,
      "loss": 0.4326,
      "step": 54481
    },
    {
      "epoch": 1.673639910300126,
      "grad_norm": 0.47065091133117676,
      "learning_rate": 1.2896069632287055e-06,
      "loss": 0.4506,
      "step": 54482
    },
    {
      "epoch": 1.6736706294350752,
      "grad_norm": 0.4288994073867798,
      "learning_rate": 1.2893695811329166e-06,
      "loss": 0.4036,
      "step": 54483
    },
    {
      "epoch": 1.6737013485700243,
      "grad_norm": 0.42272642254829407,
      "learning_rate": 1.2891322193814183e-06,
      "loss": 0.5053,
      "step": 54484
    },
    {
      "epoch": 1.6737320677049734,
      "grad_norm": 0.43973246216773987,
      "learning_rate": 1.2888948779747568e-06,
      "loss": 0.4829,
      "step": 54485
    },
    {
      "epoch": 1.6737627868399225,
      "grad_norm": 0.5002983808517456,
      "learning_rate": 1.2886575569134908e-06,
      "loss": 0.4373,
      "step": 54486
    },
    {
      "epoch": 1.6737935059748716,
      "grad_norm": 0.41937121748924255,
      "learning_rate": 1.288420256198174e-06,
      "loss": 0.4125,
      "step": 54487
    },
    {
      "epoch": 1.6738242251098208,
      "grad_norm": 0.4136377274990082,
      "learning_rate": 1.2881829758293575e-06,
      "loss": 0.5151,
      "step": 54488
    },
    {
      "epoch": 1.67385494424477,
      "grad_norm": 0.42855381965637207,
      "learning_rate": 1.2879457158076013e-06,
      "loss": 0.479,
      "step": 54489
    },
    {
      "epoch": 1.6738856633797192,
      "grad_norm": 0.4411045014858246,
      "learning_rate": 1.2877084761334547e-06,
      "loss": 0.4687,
      "step": 54490
    },
    {
      "epoch": 1.6739163825146683,
      "grad_norm": 0.41664358973503113,
      "learning_rate": 1.2874712568074753e-06,
      "loss": 0.4818,
      "step": 54491
    },
    {
      "epoch": 1.6739471016496177,
      "grad_norm": 0.38454923033714294,
      "learning_rate": 1.2872340578302112e-06,
      "loss": 0.4557,
      "step": 54492
    },
    {
      "epoch": 1.6739778207845668,
      "grad_norm": 0.4279874265193939,
      "learning_rate": 1.2869968792022248e-06,
      "loss": 0.516,
      "step": 54493
    },
    {
      "epoch": 1.674008539919516,
      "grad_norm": 0.4290878176689148,
      "learning_rate": 1.2867597209240635e-06,
      "loss": 0.4356,
      "step": 54494
    },
    {
      "epoch": 1.674039259054465,
      "grad_norm": 0.45956870913505554,
      "learning_rate": 1.2865225829962847e-06,
      "loss": 0.4837,
      "step": 54495
    },
    {
      "epoch": 1.6740699781894142,
      "grad_norm": 0.42685452103614807,
      "learning_rate": 1.28628546541944e-06,
      "loss": 0.4309,
      "step": 54496
    },
    {
      "epoch": 1.6741006973243633,
      "grad_norm": 0.4611596465110779,
      "learning_rate": 1.2860483681940838e-06,
      "loss": 0.4223,
      "step": 54497
    },
    {
      "epoch": 1.6741314164593124,
      "grad_norm": 0.599921703338623,
      "learning_rate": 1.28581129132077e-06,
      "loss": 0.451,
      "step": 54498
    },
    {
      "epoch": 1.6741621355942615,
      "grad_norm": 0.4147140383720398,
      "learning_rate": 1.2855742348000543e-06,
      "loss": 0.4811,
      "step": 54499
    },
    {
      "epoch": 1.6741928547292109,
      "grad_norm": 0.4611560106277466,
      "learning_rate": 1.285337198632487e-06,
      "loss": 0.4606,
      "step": 54500
    },
    {
      "epoch": 1.67422357386416,
      "grad_norm": 0.41875550150871277,
      "learning_rate": 1.285100182818624e-06,
      "loss": 0.511,
      "step": 54501
    },
    {
      "epoch": 1.674254292999109,
      "grad_norm": 0.45242658257484436,
      "learning_rate": 1.2848631873590168e-06,
      "loss": 0.5071,
      "step": 54502
    },
    {
      "epoch": 1.6742850121340584,
      "grad_norm": 0.40129438042640686,
      "learning_rate": 1.284626212254223e-06,
      "loss": 0.4504,
      "step": 54503
    },
    {
      "epoch": 1.6743157312690076,
      "grad_norm": 0.4207504689693451,
      "learning_rate": 1.2843892575047912e-06,
      "loss": 0.4942,
      "step": 54504
    },
    {
      "epoch": 1.6743464504039567,
      "grad_norm": 0.39734962582588196,
      "learning_rate": 1.2841523231112763e-06,
      "loss": 0.4887,
      "step": 54505
    },
    {
      "epoch": 1.6743771695389058,
      "grad_norm": 0.41602379083633423,
      "learning_rate": 1.2839154090742333e-06,
      "loss": 0.4644,
      "step": 54506
    },
    {
      "epoch": 1.674407888673855,
      "grad_norm": 0.5163953304290771,
      "learning_rate": 1.2836785153942144e-06,
      "loss": 0.4599,
      "step": 54507
    },
    {
      "epoch": 1.674438607808804,
      "grad_norm": 0.46656420826911926,
      "learning_rate": 1.2834416420717754e-06,
      "loss": 0.4988,
      "step": 54508
    },
    {
      "epoch": 1.6744693269437532,
      "grad_norm": 0.4385773837566376,
      "learning_rate": 1.2832047891074651e-06,
      "loss": 0.4896,
      "step": 54509
    },
    {
      "epoch": 1.6745000460787023,
      "grad_norm": 0.41431277990341187,
      "learning_rate": 1.2829679565018383e-06,
      "loss": 0.56,
      "step": 54510
    },
    {
      "epoch": 1.6745307652136516,
      "grad_norm": 0.41597673296928406,
      "learning_rate": 1.282731144255448e-06,
      "loss": 0.4875,
      "step": 54511
    },
    {
      "epoch": 1.6745614843486007,
      "grad_norm": 0.42232832312583923,
      "learning_rate": 1.2824943523688516e-06,
      "loss": 0.5122,
      "step": 54512
    },
    {
      "epoch": 1.6745922034835499,
      "grad_norm": 0.45675399899482727,
      "learning_rate": 1.2822575808425952e-06,
      "loss": 0.4399,
      "step": 54513
    },
    {
      "epoch": 1.6746229226184992,
      "grad_norm": 0.4039266109466553,
      "learning_rate": 1.2820208296772353e-06,
      "loss": 0.4546,
      "step": 54514
    },
    {
      "epoch": 1.6746536417534483,
      "grad_norm": 0.4844875633716583,
      "learning_rate": 1.2817840988733253e-06,
      "loss": 0.5234,
      "step": 54515
    },
    {
      "epoch": 1.6746843608883974,
      "grad_norm": 0.4547734260559082,
      "learning_rate": 1.281547388431419e-06,
      "loss": 0.4138,
      "step": 54516
    },
    {
      "epoch": 1.6747150800233466,
      "grad_norm": 0.4532345235347748,
      "learning_rate": 1.2813106983520652e-06,
      "loss": 0.498,
      "step": 54517
    },
    {
      "epoch": 1.6747457991582957,
      "grad_norm": 0.4923001825809479,
      "learning_rate": 1.2810740286358214e-06,
      "loss": 0.3984,
      "step": 54518
    },
    {
      "epoch": 1.6747765182932448,
      "grad_norm": 0.44513556361198425,
      "learning_rate": 1.280837379283234e-06,
      "loss": 0.5167,
      "step": 54519
    },
    {
      "epoch": 1.674807237428194,
      "grad_norm": 0.4449937641620636,
      "learning_rate": 1.2806007502948647e-06,
      "loss": 0.4507,
      "step": 54520
    },
    {
      "epoch": 1.674837956563143,
      "grad_norm": 0.4013192057609558,
      "learning_rate": 1.2803641416712587e-06,
      "loss": 0.4645,
      "step": 54521
    },
    {
      "epoch": 1.6748686756980924,
      "grad_norm": 0.4463951587677002,
      "learning_rate": 1.2801275534129732e-06,
      "loss": 0.4304,
      "step": 54522
    },
    {
      "epoch": 1.6748993948330415,
      "grad_norm": 0.4191121757030487,
      "learning_rate": 1.2798909855205566e-06,
      "loss": 0.4392,
      "step": 54523
    },
    {
      "epoch": 1.6749301139679906,
      "grad_norm": 0.45972564816474915,
      "learning_rate": 1.279654437994562e-06,
      "loss": 0.5025,
      "step": 54524
    },
    {
      "epoch": 1.67496083310294,
      "grad_norm": 0.43923425674438477,
      "learning_rate": 1.2794179108355475e-06,
      "loss": 0.4854,
      "step": 54525
    },
    {
      "epoch": 1.674991552237889,
      "grad_norm": 0.44287195801734924,
      "learning_rate": 1.2791814040440587e-06,
      "loss": 0.4984,
      "step": 54526
    },
    {
      "epoch": 1.6750222713728382,
      "grad_norm": 0.4788612723350525,
      "learning_rate": 1.2789449176206536e-06,
      "loss": 0.3997,
      "step": 54527
    },
    {
      "epoch": 1.6750529905077873,
      "grad_norm": 0.48381611704826355,
      "learning_rate": 1.2787084515658798e-06,
      "loss": 0.4964,
      "step": 54528
    },
    {
      "epoch": 1.6750837096427365,
      "grad_norm": 0.4034484922885895,
      "learning_rate": 1.2784720058802914e-06,
      "loss": 0.3894,
      "step": 54529
    },
    {
      "epoch": 1.6751144287776856,
      "grad_norm": 0.4784183204174042,
      "learning_rate": 1.2782355805644397e-06,
      "loss": 0.4944,
      "step": 54530
    },
    {
      "epoch": 1.6751451479126347,
      "grad_norm": 0.4588300287723541,
      "learning_rate": 1.2779991756188814e-06,
      "loss": 0.5093,
      "step": 54531
    },
    {
      "epoch": 1.6751758670475838,
      "grad_norm": 0.41351789236068726,
      "learning_rate": 1.2777627910441625e-06,
      "loss": 0.423,
      "step": 54532
    },
    {
      "epoch": 1.6752065861825332,
      "grad_norm": 0.4428105652332306,
      "learning_rate": 1.277526426840837e-06,
      "loss": 0.4464,
      "step": 54533
    },
    {
      "epoch": 1.6752373053174823,
      "grad_norm": 0.39631950855255127,
      "learning_rate": 1.2772900830094592e-06,
      "loss": 0.4726,
      "step": 54534
    },
    {
      "epoch": 1.6752680244524314,
      "grad_norm": 0.4237046539783478,
      "learning_rate": 1.2770537595505806e-06,
      "loss": 0.4207,
      "step": 54535
    },
    {
      "epoch": 1.6752987435873807,
      "grad_norm": 0.3844837248325348,
      "learning_rate": 1.2768174564647507e-06,
      "loss": 0.3975,
      "step": 54536
    },
    {
      "epoch": 1.6753294627223299,
      "grad_norm": 0.42951226234436035,
      "learning_rate": 1.2765811737525225e-06,
      "loss": 0.4154,
      "step": 54537
    },
    {
      "epoch": 1.675360181857279,
      "grad_norm": 0.4158012568950653,
      "learning_rate": 1.276344911414449e-06,
      "loss": 0.4596,
      "step": 54538
    },
    {
      "epoch": 1.675390900992228,
      "grad_norm": 0.41610148549079895,
      "learning_rate": 1.2761086694510816e-06,
      "loss": 0.4475,
      "step": 54539
    },
    {
      "epoch": 1.6754216201271772,
      "grad_norm": 0.4588581621646881,
      "learning_rate": 1.2758724478629714e-06,
      "loss": 0.4364,
      "step": 54540
    },
    {
      "epoch": 1.6754523392621263,
      "grad_norm": 0.4566246569156647,
      "learning_rate": 1.2756362466506688e-06,
      "loss": 0.4397,
      "step": 54541
    },
    {
      "epoch": 1.6754830583970755,
      "grad_norm": 0.42898935079574585,
      "learning_rate": 1.275400065814728e-06,
      "loss": 0.3486,
      "step": 54542
    },
    {
      "epoch": 1.6755137775320246,
      "grad_norm": 0.4000513553619385,
      "learning_rate": 1.2751639053556998e-06,
      "loss": 0.4524,
      "step": 54543
    },
    {
      "epoch": 1.6755444966669737,
      "grad_norm": 0.4133687913417816,
      "learning_rate": 1.2749277652741366e-06,
      "loss": 0.4919,
      "step": 54544
    },
    {
      "epoch": 1.675575215801923,
      "grad_norm": 0.4515705704689026,
      "learning_rate": 1.2746916455705882e-06,
      "loss": 0.4038,
      "step": 54545
    },
    {
      "epoch": 1.6756059349368722,
      "grad_norm": 0.4346209764480591,
      "learning_rate": 1.2744555462456064e-06,
      "loss": 0.5145,
      "step": 54546
    },
    {
      "epoch": 1.6756366540718215,
      "grad_norm": 0.4087739884853363,
      "learning_rate": 1.274219467299742e-06,
      "loss": 0.4235,
      "step": 54547
    },
    {
      "epoch": 1.6756673732067706,
      "grad_norm": 0.4511774778366089,
      "learning_rate": 1.2739834087335512e-06,
      "loss": 0.468,
      "step": 54548
    },
    {
      "epoch": 1.6756980923417197,
      "grad_norm": 0.4473309814929962,
      "learning_rate": 1.273747370547579e-06,
      "loss": 0.4413,
      "step": 54549
    },
    {
      "epoch": 1.6757288114766689,
      "grad_norm": 0.4237206280231476,
      "learning_rate": 1.2735113527423804e-06,
      "loss": 0.4621,
      "step": 54550
    },
    {
      "epoch": 1.675759530611618,
      "grad_norm": 0.44751685857772827,
      "learning_rate": 1.2732753553185018e-06,
      "loss": 0.4524,
      "step": 54551
    },
    {
      "epoch": 1.675790249746567,
      "grad_norm": 0.4449921250343323,
      "learning_rate": 1.2730393782765027e-06,
      "loss": 0.4549,
      "step": 54552
    },
    {
      "epoch": 1.6758209688815162,
      "grad_norm": 0.4448173940181732,
      "learning_rate": 1.272803421616927e-06,
      "loss": 0.4163,
      "step": 54553
    },
    {
      "epoch": 1.6758516880164653,
      "grad_norm": 0.41293713450431824,
      "learning_rate": 1.2725674853403313e-06,
      "loss": 0.4835,
      "step": 54554
    },
    {
      "epoch": 1.6758824071514145,
      "grad_norm": 0.440584272146225,
      "learning_rate": 1.2723315694472594e-06,
      "loss": 0.5499,
      "step": 54555
    },
    {
      "epoch": 1.6759131262863638,
      "grad_norm": 0.4591657221317291,
      "learning_rate": 1.2720956739382696e-06,
      "loss": 0.4429,
      "step": 54556
    },
    {
      "epoch": 1.675943845421313,
      "grad_norm": 0.4336734712123871,
      "learning_rate": 1.2718597988139092e-06,
      "loss": 0.5099,
      "step": 54557
    },
    {
      "epoch": 1.6759745645562623,
      "grad_norm": 0.4779026210308075,
      "learning_rate": 1.2716239440747312e-06,
      "loss": 0.4679,
      "step": 54558
    },
    {
      "epoch": 1.6760052836912114,
      "grad_norm": 0.44473788142204285,
      "learning_rate": 1.2713881097212833e-06,
      "loss": 0.5212,
      "step": 54559
    },
    {
      "epoch": 1.6760360028261605,
      "grad_norm": 0.4063839018344879,
      "learning_rate": 1.2711522957541156e-06,
      "loss": 0.538,
      "step": 54560
    },
    {
      "epoch": 1.6760667219611096,
      "grad_norm": 0.4368738830089569,
      "learning_rate": 1.2709165021737857e-06,
      "loss": 0.4553,
      "step": 54561
    },
    {
      "epoch": 1.6760974410960587,
      "grad_norm": 0.6858692169189453,
      "learning_rate": 1.2706807289808376e-06,
      "loss": 0.4414,
      "step": 54562
    },
    {
      "epoch": 1.6761281602310079,
      "grad_norm": 0.4364069104194641,
      "learning_rate": 1.2704449761758276e-06,
      "loss": 0.4597,
      "step": 54563
    },
    {
      "epoch": 1.676158879365957,
      "grad_norm": 0.4392416179180145,
      "learning_rate": 1.2702092437592995e-06,
      "loss": 0.4397,
      "step": 54564
    },
    {
      "epoch": 1.676189598500906,
      "grad_norm": 0.41415414214134216,
      "learning_rate": 1.2699735317318084e-06,
      "loss": 0.5021,
      "step": 54565
    },
    {
      "epoch": 1.6762203176358552,
      "grad_norm": 0.40652111172676086,
      "learning_rate": 1.269737840093903e-06,
      "loss": 0.5043,
      "step": 54566
    },
    {
      "epoch": 1.6762510367708046,
      "grad_norm": 0.4080815613269806,
      "learning_rate": 1.2695021688461373e-06,
      "loss": 0.4513,
      "step": 54567
    },
    {
      "epoch": 1.6762817559057537,
      "grad_norm": 0.5049395561218262,
      "learning_rate": 1.2692665179890563e-06,
      "loss": 0.4526,
      "step": 54568
    },
    {
      "epoch": 1.6763124750407028,
      "grad_norm": 0.4308834671974182,
      "learning_rate": 1.2690308875232137e-06,
      "loss": 0.3618,
      "step": 54569
    },
    {
      "epoch": 1.6763431941756521,
      "grad_norm": 0.47684454917907715,
      "learning_rate": 1.2687952774491584e-06,
      "loss": 0.5058,
      "step": 54570
    },
    {
      "epoch": 1.6763739133106013,
      "grad_norm": 0.40301162004470825,
      "learning_rate": 1.2685596877674445e-06,
      "loss": 0.454,
      "step": 54571
    },
    {
      "epoch": 1.6764046324455504,
      "grad_norm": 0.4355452358722687,
      "learning_rate": 1.2683241184786166e-06,
      "loss": 0.4432,
      "step": 54572
    },
    {
      "epoch": 1.6764353515804995,
      "grad_norm": 0.4289933443069458,
      "learning_rate": 1.2680885695832278e-06,
      "loss": 0.4228,
      "step": 54573
    },
    {
      "epoch": 1.6764660707154486,
      "grad_norm": 0.3828786015510559,
      "learning_rate": 1.267853041081828e-06,
      "loss": 0.4527,
      "step": 54574
    },
    {
      "epoch": 1.6764967898503977,
      "grad_norm": 0.43790102005004883,
      "learning_rate": 1.2676175329749697e-06,
      "loss": 0.4579,
      "step": 54575
    },
    {
      "epoch": 1.6765275089853469,
      "grad_norm": 0.3966556191444397,
      "learning_rate": 1.267382045263198e-06,
      "loss": 0.4199,
      "step": 54576
    },
    {
      "epoch": 1.676558228120296,
      "grad_norm": 0.4365162253379822,
      "learning_rate": 1.2671465779470648e-06,
      "loss": 0.5055,
      "step": 54577
    },
    {
      "epoch": 1.6765889472552453,
      "grad_norm": 0.45365241169929504,
      "learning_rate": 1.2669111310271209e-06,
      "loss": 0.5048,
      "step": 54578
    },
    {
      "epoch": 1.6766196663901944,
      "grad_norm": 0.406415194272995,
      "learning_rate": 1.2666757045039169e-06,
      "loss": 0.4136,
      "step": 54579
    },
    {
      "epoch": 1.6766503855251436,
      "grad_norm": 0.42393770813941956,
      "learning_rate": 1.2664402983780034e-06,
      "loss": 0.4586,
      "step": 54580
    },
    {
      "epoch": 1.676681104660093,
      "grad_norm": 0.4408531188964844,
      "learning_rate": 1.2662049126499266e-06,
      "loss": 0.5513,
      "step": 54581
    },
    {
      "epoch": 1.676711823795042,
      "grad_norm": 0.5010747313499451,
      "learning_rate": 1.2659695473202371e-06,
      "loss": 0.5066,
      "step": 54582
    },
    {
      "epoch": 1.6767425429299911,
      "grad_norm": 0.41549792885780334,
      "learning_rate": 1.265734202389487e-06,
      "loss": 0.4468,
      "step": 54583
    },
    {
      "epoch": 1.6767732620649403,
      "grad_norm": 0.4250175952911377,
      "learning_rate": 1.2654988778582255e-06,
      "loss": 0.4321,
      "step": 54584
    },
    {
      "epoch": 1.6768039811998894,
      "grad_norm": 0.43344181776046753,
      "learning_rate": 1.2652635737270002e-06,
      "loss": 0.4889,
      "step": 54585
    },
    {
      "epoch": 1.6768347003348385,
      "grad_norm": 0.4499085247516632,
      "learning_rate": 1.265028289996364e-06,
      "loss": 0.5209,
      "step": 54586
    },
    {
      "epoch": 1.6768654194697876,
      "grad_norm": 0.44950154423713684,
      "learning_rate": 1.2647930266668596e-06,
      "loss": 0.5227,
      "step": 54587
    },
    {
      "epoch": 1.6768961386047367,
      "grad_norm": 0.4395952522754669,
      "learning_rate": 1.2645577837390456e-06,
      "loss": 0.4853,
      "step": 54588
    },
    {
      "epoch": 1.676926857739686,
      "grad_norm": 0.5153121948242188,
      "learning_rate": 1.2643225612134647e-06,
      "loss": 0.4422,
      "step": 54589
    },
    {
      "epoch": 1.6769575768746352,
      "grad_norm": 0.43109774589538574,
      "learning_rate": 1.264087359090671e-06,
      "loss": 0.4855,
      "step": 54590
    },
    {
      "epoch": 1.6769882960095843,
      "grad_norm": 0.48484906554222107,
      "learning_rate": 1.2638521773712098e-06,
      "loss": 0.5015,
      "step": 54591
    },
    {
      "epoch": 1.6770190151445337,
      "grad_norm": 0.4379305839538574,
      "learning_rate": 1.2636170160556305e-06,
      "loss": 0.4171,
      "step": 54592
    },
    {
      "epoch": 1.6770497342794828,
      "grad_norm": 0.41498464345932007,
      "learning_rate": 1.2633818751444848e-06,
      "loss": 0.4228,
      "step": 54593
    },
    {
      "epoch": 1.677080453414432,
      "grad_norm": 0.4564196467399597,
      "learning_rate": 1.2631467546383226e-06,
      "loss": 0.4186,
      "step": 54594
    },
    {
      "epoch": 1.677111172549381,
      "grad_norm": 0.4358091652393341,
      "learning_rate": 1.2629116545376897e-06,
      "loss": 0.4902,
      "step": 54595
    },
    {
      "epoch": 1.6771418916843301,
      "grad_norm": 0.4826938807964325,
      "learning_rate": 1.2626765748431346e-06,
      "loss": 0.5829,
      "step": 54596
    },
    {
      "epoch": 1.6771726108192793,
      "grad_norm": 0.40387722849845886,
      "learning_rate": 1.2624415155552116e-06,
      "loss": 0.5209,
      "step": 54597
    },
    {
      "epoch": 1.6772033299542284,
      "grad_norm": 0.40483832359313965,
      "learning_rate": 1.2622064766744658e-06,
      "loss": 0.466,
      "step": 54598
    },
    {
      "epoch": 1.6772340490891775,
      "grad_norm": 0.425150066614151,
      "learning_rate": 1.2619714582014485e-06,
      "loss": 0.4836,
      "step": 54599
    },
    {
      "epoch": 1.6772647682241268,
      "grad_norm": 0.4107671082019806,
      "learning_rate": 1.2617364601367054e-06,
      "loss": 0.503,
      "step": 54600
    },
    {
      "epoch": 1.677295487359076,
      "grad_norm": 0.4479057490825653,
      "learning_rate": 1.2615014824807882e-06,
      "loss": 0.4663,
      "step": 54601
    },
    {
      "epoch": 1.677326206494025,
      "grad_norm": 0.4404926002025604,
      "learning_rate": 1.2612665252342426e-06,
      "loss": 0.5183,
      "step": 54602
    },
    {
      "epoch": 1.6773569256289744,
      "grad_norm": 0.41716036200523376,
      "learning_rate": 1.2610315883976221e-06,
      "loss": 0.4656,
      "step": 54603
    },
    {
      "epoch": 1.6773876447639235,
      "grad_norm": 0.5099199414253235,
      "learning_rate": 1.2607966719714716e-06,
      "loss": 0.456,
      "step": 54604
    },
    {
      "epoch": 1.6774183638988727,
      "grad_norm": 0.43527957797050476,
      "learning_rate": 1.2605617759563394e-06,
      "loss": 0.4958,
      "step": 54605
    },
    {
      "epoch": 1.6774490830338218,
      "grad_norm": 0.413472443819046,
      "learning_rate": 1.2603269003527763e-06,
      "loss": 0.4332,
      "step": 54606
    },
    {
      "epoch": 1.677479802168771,
      "grad_norm": 0.38353267312049866,
      "learning_rate": 1.2600920451613319e-06,
      "loss": 0.4779,
      "step": 54607
    },
    {
      "epoch": 1.67751052130372,
      "grad_norm": 0.44301164150238037,
      "learning_rate": 1.2598572103825501e-06,
      "loss": 0.5029,
      "step": 54608
    },
    {
      "epoch": 1.6775412404386691,
      "grad_norm": 0.4658477306365967,
      "learning_rate": 1.259622396016983e-06,
      "loss": 0.4537,
      "step": 54609
    },
    {
      "epoch": 1.6775719595736183,
      "grad_norm": 0.5384933948516846,
      "learning_rate": 1.2593876020651784e-06,
      "loss": 0.3918,
      "step": 54610
    },
    {
      "epoch": 1.6776026787085676,
      "grad_norm": 0.4302140474319458,
      "learning_rate": 1.2591528285276866e-06,
      "loss": 0.4052,
      "step": 54611
    },
    {
      "epoch": 1.6776333978435167,
      "grad_norm": 0.4456470012664795,
      "learning_rate": 1.2589180754050511e-06,
      "loss": 0.4678,
      "step": 54612
    },
    {
      "epoch": 1.6776641169784658,
      "grad_norm": 0.46347641944885254,
      "learning_rate": 1.2586833426978262e-06,
      "loss": 0.4318,
      "step": 54613
    },
    {
      "epoch": 1.6776948361134152,
      "grad_norm": 0.4525514543056488,
      "learning_rate": 1.2584486304065514e-06,
      "loss": 0.4591,
      "step": 54614
    },
    {
      "epoch": 1.6777255552483643,
      "grad_norm": 0.45106929540634155,
      "learning_rate": 1.2582139385317826e-06,
      "loss": 0.382,
      "step": 54615
    },
    {
      "epoch": 1.6777562743833134,
      "grad_norm": 0.4298460781574249,
      "learning_rate": 1.2579792670740677e-06,
      "loss": 0.5174,
      "step": 54616
    },
    {
      "epoch": 1.6777869935182625,
      "grad_norm": 0.43543004989624023,
      "learning_rate": 1.2577446160339513e-06,
      "loss": 0.4579,
      "step": 54617
    },
    {
      "epoch": 1.6778177126532117,
      "grad_norm": 0.4058957099914551,
      "learning_rate": 1.2575099854119821e-06,
      "loss": 0.5002,
      "step": 54618
    },
    {
      "epoch": 1.6778484317881608,
      "grad_norm": 0.4515193998813629,
      "learning_rate": 1.2572753752087097e-06,
      "loss": 0.5306,
      "step": 54619
    },
    {
      "epoch": 1.67787915092311,
      "grad_norm": 0.47761425375938416,
      "learning_rate": 1.2570407854246835e-06,
      "loss": 0.3725,
      "step": 54620
    },
    {
      "epoch": 1.677909870058059,
      "grad_norm": 0.38795188069343567,
      "learning_rate": 1.2568062160604467e-06,
      "loss": 0.524,
      "step": 54621
    },
    {
      "epoch": 1.6779405891930084,
      "grad_norm": 0.4541143476963043,
      "learning_rate": 1.2565716671165507e-06,
      "loss": 0.4422,
      "step": 54622
    },
    {
      "epoch": 1.6779713083279575,
      "grad_norm": 0.410984069108963,
      "learning_rate": 1.2563371385935397e-06,
      "loss": 0.4531,
      "step": 54623
    },
    {
      "epoch": 1.6780020274629066,
      "grad_norm": 0.4448162615299225,
      "learning_rate": 1.2561026304919666e-06,
      "loss": 0.4439,
      "step": 54624
    },
    {
      "epoch": 1.678032746597856,
      "grad_norm": 0.3976343274116516,
      "learning_rate": 1.2558681428123753e-06,
      "loss": 0.4826,
      "step": 54625
    },
    {
      "epoch": 1.678063465732805,
      "grad_norm": 0.425086110830307,
      "learning_rate": 1.2556336755553167e-06,
      "loss": 0.4977,
      "step": 54626
    },
    {
      "epoch": 1.6780941848677542,
      "grad_norm": 0.4883338212966919,
      "learning_rate": 1.2553992287213335e-06,
      "loss": 0.4419,
      "step": 54627
    },
    {
      "epoch": 1.6781249040027033,
      "grad_norm": 0.4374009668827057,
      "learning_rate": 1.2551648023109774e-06,
      "loss": 0.4783,
      "step": 54628
    },
    {
      "epoch": 1.6781556231376524,
      "grad_norm": 0.421756386756897,
      "learning_rate": 1.254930396324794e-06,
      "loss": 0.4978,
      "step": 54629
    },
    {
      "epoch": 1.6781863422726016,
      "grad_norm": 0.4339587688446045,
      "learning_rate": 1.2546960107633333e-06,
      "loss": 0.4815,
      "step": 54630
    },
    {
      "epoch": 1.6782170614075507,
      "grad_norm": 0.42920804023742676,
      "learning_rate": 1.2544616456271387e-06,
      "loss": 0.4592,
      "step": 54631
    },
    {
      "epoch": 1.6782477805424998,
      "grad_norm": 0.5039634704589844,
      "learning_rate": 1.2542273009167594e-06,
      "loss": 0.4296,
      "step": 54632
    },
    {
      "epoch": 1.6782784996774491,
      "grad_norm": 0.4597633481025696,
      "learning_rate": 1.2539929766327441e-06,
      "loss": 0.4655,
      "step": 54633
    },
    {
      "epoch": 1.6783092188123983,
      "grad_norm": 0.4465855062007904,
      "learning_rate": 1.253758672775638e-06,
      "loss": 0.5005,
      "step": 54634
    },
    {
      "epoch": 1.6783399379473474,
      "grad_norm": 0.4319339990615845,
      "learning_rate": 1.2535243893459924e-06,
      "loss": 0.4794,
      "step": 54635
    },
    {
      "epoch": 1.6783706570822967,
      "grad_norm": 0.4866664707660675,
      "learning_rate": 1.2532901263443486e-06,
      "loss": 0.4588,
      "step": 54636
    },
    {
      "epoch": 1.6784013762172458,
      "grad_norm": 0.47147658467292786,
      "learning_rate": 1.253055883771257e-06,
      "loss": 0.4332,
      "step": 54637
    },
    {
      "epoch": 1.678432095352195,
      "grad_norm": 0.4751654863357544,
      "learning_rate": 1.2528216616272637e-06,
      "loss": 0.4535,
      "step": 54638
    },
    {
      "epoch": 1.678462814487144,
      "grad_norm": 0.46944430470466614,
      "learning_rate": 1.2525874599129184e-06,
      "loss": 0.4666,
      "step": 54639
    },
    {
      "epoch": 1.6784935336220932,
      "grad_norm": 0.4104003608226776,
      "learning_rate": 1.252353278628765e-06,
      "loss": 0.4299,
      "step": 54640
    },
    {
      "epoch": 1.6785242527570423,
      "grad_norm": 0.43209537863731384,
      "learning_rate": 1.25211911777535e-06,
      "loss": 0.5221,
      "step": 54641
    },
    {
      "epoch": 1.6785549718919914,
      "grad_norm": 0.5368211269378662,
      "learning_rate": 1.2518849773532228e-06,
      "loss": 0.4404,
      "step": 54642
    },
    {
      "epoch": 1.6785856910269406,
      "grad_norm": 0.4285929203033447,
      "learning_rate": 1.2516508573629315e-06,
      "loss": 0.5312,
      "step": 54643
    },
    {
      "epoch": 1.67861641016189,
      "grad_norm": 0.4319232106208801,
      "learning_rate": 1.2514167578050175e-06,
      "loss": 0.4008,
      "step": 54644
    },
    {
      "epoch": 1.678647129296839,
      "grad_norm": 0.4097268283367157,
      "learning_rate": 1.2511826786800307e-06,
      "loss": 0.4837,
      "step": 54645
    },
    {
      "epoch": 1.6786778484317881,
      "grad_norm": 0.4248495399951935,
      "learning_rate": 1.250948619988519e-06,
      "loss": 0.4449,
      "step": 54646
    },
    {
      "epoch": 1.6787085675667375,
      "grad_norm": 0.43338555097579956,
      "learning_rate": 1.2507145817310284e-06,
      "loss": 0.4916,
      "step": 54647
    },
    {
      "epoch": 1.6787392867016866,
      "grad_norm": 0.5218405723571777,
      "learning_rate": 1.250480563908104e-06,
      "loss": 0.5021,
      "step": 54648
    },
    {
      "epoch": 1.6787700058366357,
      "grad_norm": 0.5486396551132202,
      "learning_rate": 1.2502465665202945e-06,
      "loss": 0.4966,
      "step": 54649
    },
    {
      "epoch": 1.6788007249715848,
      "grad_norm": 0.4587010443210602,
      "learning_rate": 1.2500125895681413e-06,
      "loss": 0.4209,
      "step": 54650
    },
    {
      "epoch": 1.678831444106534,
      "grad_norm": 0.4441392123699188,
      "learning_rate": 1.2497786330521977e-06,
      "loss": 0.4114,
      "step": 54651
    },
    {
      "epoch": 1.678862163241483,
      "grad_norm": 0.44374221563339233,
      "learning_rate": 1.2495446969730085e-06,
      "loss": 0.4825,
      "step": 54652
    },
    {
      "epoch": 1.6788928823764322,
      "grad_norm": 0.4522838890552521,
      "learning_rate": 1.2493107813311167e-06,
      "loss": 0.4265,
      "step": 54653
    },
    {
      "epoch": 1.6789236015113813,
      "grad_norm": 0.4067230522632599,
      "learning_rate": 1.249076886127073e-06,
      "loss": 0.4601,
      "step": 54654
    },
    {
      "epoch": 1.6789543206463304,
      "grad_norm": 0.4420084059238434,
      "learning_rate": 1.248843011361417e-06,
      "loss": 0.4511,
      "step": 54655
    },
    {
      "epoch": 1.6789850397812798,
      "grad_norm": 0.4644539952278137,
      "learning_rate": 1.2486091570347036e-06,
      "loss": 0.5153,
      "step": 54656
    },
    {
      "epoch": 1.679015758916229,
      "grad_norm": 0.44896426796913147,
      "learning_rate": 1.2483753231474726e-06,
      "loss": 0.4199,
      "step": 54657
    },
    {
      "epoch": 1.6790464780511782,
      "grad_norm": 0.438903272151947,
      "learning_rate": 1.2481415097002746e-06,
      "loss": 0.4099,
      "step": 54658
    },
    {
      "epoch": 1.6790771971861274,
      "grad_norm": 0.4220608174800873,
      "learning_rate": 1.2479077166936492e-06,
      "loss": 0.4692,
      "step": 54659
    },
    {
      "epoch": 1.6791079163210765,
      "grad_norm": 0.4819123446941376,
      "learning_rate": 1.2476739441281504e-06,
      "loss": 0.423,
      "step": 54660
    },
    {
      "epoch": 1.6791386354560256,
      "grad_norm": 0.43687957525253296,
      "learning_rate": 1.2474401920043178e-06,
      "loss": 0.4569,
      "step": 54661
    },
    {
      "epoch": 1.6791693545909747,
      "grad_norm": 0.3874607980251312,
      "learning_rate": 1.247206460322703e-06,
      "loss": 0.4875,
      "step": 54662
    },
    {
      "epoch": 1.6792000737259238,
      "grad_norm": 0.8521997928619385,
      "learning_rate": 1.2469727490838468e-06,
      "loss": 0.5012,
      "step": 54663
    },
    {
      "epoch": 1.679230792860873,
      "grad_norm": 0.45880475640296936,
      "learning_rate": 1.2467390582882966e-06,
      "loss": 0.4737,
      "step": 54664
    },
    {
      "epoch": 1.679261511995822,
      "grad_norm": 0.42940330505371094,
      "learning_rate": 1.2465053879365984e-06,
      "loss": 0.4781,
      "step": 54665
    },
    {
      "epoch": 1.6792922311307712,
      "grad_norm": 0.47964009642601013,
      "learning_rate": 1.2462717380293e-06,
      "loss": 0.4957,
      "step": 54666
    },
    {
      "epoch": 1.6793229502657205,
      "grad_norm": 0.44223371148109436,
      "learning_rate": 1.2460381085669437e-06,
      "loss": 0.4539,
      "step": 54667
    },
    {
      "epoch": 1.6793536694006697,
      "grad_norm": 0.41868728399276733,
      "learning_rate": 1.2458044995500762e-06,
      "loss": 0.4094,
      "step": 54668
    },
    {
      "epoch": 1.679384388535619,
      "grad_norm": 0.4447856545448303,
      "learning_rate": 1.2455709109792448e-06,
      "loss": 0.4702,
      "step": 54669
    },
    {
      "epoch": 1.6794151076705681,
      "grad_norm": 0.43973344564437866,
      "learning_rate": 1.245337342854993e-06,
      "loss": 0.4597,
      "step": 54670
    },
    {
      "epoch": 1.6794458268055172,
      "grad_norm": 0.4420877993106842,
      "learning_rate": 1.24510379517787e-06,
      "loss": 0.5179,
      "step": 54671
    },
    {
      "epoch": 1.6794765459404664,
      "grad_norm": 0.43773964047431946,
      "learning_rate": 1.244870267948416e-06,
      "loss": 0.4615,
      "step": 54672
    },
    {
      "epoch": 1.6795072650754155,
      "grad_norm": 0.47632908821105957,
      "learning_rate": 1.2446367611671795e-06,
      "loss": 0.5114,
      "step": 54673
    },
    {
      "epoch": 1.6795379842103646,
      "grad_norm": 0.4278142750263214,
      "learning_rate": 1.2444032748347045e-06,
      "loss": 0.4102,
      "step": 54674
    },
    {
      "epoch": 1.6795687033453137,
      "grad_norm": 0.41578057408332825,
      "learning_rate": 1.2441698089515397e-06,
      "loss": 0.4381,
      "step": 54675
    },
    {
      "epoch": 1.6795994224802628,
      "grad_norm": 0.4536517560482025,
      "learning_rate": 1.2439363635182255e-06,
      "loss": 0.3863,
      "step": 54676
    },
    {
      "epoch": 1.679630141615212,
      "grad_norm": 0.4164913594722748,
      "learning_rate": 1.2437029385353095e-06,
      "loss": 0.4494,
      "step": 54677
    },
    {
      "epoch": 1.6796608607501613,
      "grad_norm": 0.42552274465560913,
      "learning_rate": 1.2434695340033376e-06,
      "loss": 0.485,
      "step": 54678
    },
    {
      "epoch": 1.6796915798851104,
      "grad_norm": 0.4139142334461212,
      "learning_rate": 1.243236149922855e-06,
      "loss": 0.5369,
      "step": 54679
    },
    {
      "epoch": 1.6797222990200598,
      "grad_norm": 0.4639575481414795,
      "learning_rate": 1.2430027862944049e-06,
      "loss": 0.4912,
      "step": 54680
    },
    {
      "epoch": 1.6797530181550089,
      "grad_norm": 0.4295906126499176,
      "learning_rate": 1.2427694431185323e-06,
      "loss": 0.4561,
      "step": 54681
    },
    {
      "epoch": 1.679783737289958,
      "grad_norm": 0.42735156416893005,
      "learning_rate": 1.242536120395784e-06,
      "loss": 0.5274,
      "step": 54682
    },
    {
      "epoch": 1.6798144564249071,
      "grad_norm": 0.41886597871780396,
      "learning_rate": 1.242302818126706e-06,
      "loss": 0.4323,
      "step": 54683
    },
    {
      "epoch": 1.6798451755598562,
      "grad_norm": 0.48391610383987427,
      "learning_rate": 1.2420695363118396e-06,
      "loss": 0.3865,
      "step": 54684
    },
    {
      "epoch": 1.6798758946948054,
      "grad_norm": 0.42862746119499207,
      "learning_rate": 1.2418362749517332e-06,
      "loss": 0.3748,
      "step": 54685
    },
    {
      "epoch": 1.6799066138297545,
      "grad_norm": 0.4188653230667114,
      "learning_rate": 1.2416030340469253e-06,
      "loss": 0.396,
      "step": 54686
    },
    {
      "epoch": 1.6799373329647036,
      "grad_norm": 0.4395570755004883,
      "learning_rate": 1.241369813597968e-06,
      "loss": 0.4879,
      "step": 54687
    },
    {
      "epoch": 1.6799680520996527,
      "grad_norm": 0.5031214952468872,
      "learning_rate": 1.241136613605406e-06,
      "loss": 0.4567,
      "step": 54688
    },
    {
      "epoch": 1.679998771234602,
      "grad_norm": 0.43906864523887634,
      "learning_rate": 1.240903434069778e-06,
      "loss": 0.4265,
      "step": 54689
    },
    {
      "epoch": 1.6800294903695512,
      "grad_norm": 0.4445141553878784,
      "learning_rate": 1.2406702749916333e-06,
      "loss": 0.498,
      "step": 54690
    },
    {
      "epoch": 1.6800602095045003,
      "grad_norm": 0.4100283086299896,
      "learning_rate": 1.2404371363715117e-06,
      "loss": 0.4772,
      "step": 54691
    },
    {
      "epoch": 1.6800909286394496,
      "grad_norm": 0.43247154355049133,
      "learning_rate": 1.240204018209965e-06,
      "loss": 0.4424,
      "step": 54692
    },
    {
      "epoch": 1.6801216477743988,
      "grad_norm": 0.42500007152557373,
      "learning_rate": 1.2399709205075317e-06,
      "loss": 0.478,
      "step": 54693
    },
    {
      "epoch": 1.6801523669093479,
      "grad_norm": 0.44288524985313416,
      "learning_rate": 1.239737843264759e-06,
      "loss": 0.4862,
      "step": 54694
    },
    {
      "epoch": 1.680183086044297,
      "grad_norm": 0.4301339387893677,
      "learning_rate": 1.2395047864821895e-06,
      "loss": 0.4438,
      "step": 54695
    },
    {
      "epoch": 1.6802138051792461,
      "grad_norm": 0.42492401599884033,
      "learning_rate": 1.2392717501603678e-06,
      "loss": 0.4649,
      "step": 54696
    },
    {
      "epoch": 1.6802445243141952,
      "grad_norm": 0.47918611764907837,
      "learning_rate": 1.2390387342998389e-06,
      "loss": 0.4349,
      "step": 54697
    },
    {
      "epoch": 1.6802752434491444,
      "grad_norm": 0.38912200927734375,
      "learning_rate": 1.2388057389011498e-06,
      "loss": 0.4339,
      "step": 54698
    },
    {
      "epoch": 1.6803059625840935,
      "grad_norm": 0.42929068207740784,
      "learning_rate": 1.2385727639648382e-06,
      "loss": 0.4896,
      "step": 54699
    },
    {
      "epoch": 1.6803366817190428,
      "grad_norm": 0.4452332556247711,
      "learning_rate": 1.2383398094914533e-06,
      "loss": 0.4766,
      "step": 54700
    },
    {
      "epoch": 1.680367400853992,
      "grad_norm": 0.45609840750694275,
      "learning_rate": 1.2381068754815362e-06,
      "loss": 0.4577,
      "step": 54701
    },
    {
      "epoch": 1.680398119988941,
      "grad_norm": 0.45175498723983765,
      "learning_rate": 1.2378739619356361e-06,
      "loss": 0.4971,
      "step": 54702
    },
    {
      "epoch": 1.6804288391238904,
      "grad_norm": 0.42814135551452637,
      "learning_rate": 1.2376410688542894e-06,
      "loss": 0.4843,
      "step": 54703
    },
    {
      "epoch": 1.6804595582588395,
      "grad_norm": 0.40901216864585876,
      "learning_rate": 1.2374081962380458e-06,
      "loss": 0.5073,
      "step": 54704
    },
    {
      "epoch": 1.6804902773937886,
      "grad_norm": 0.48207220435142517,
      "learning_rate": 1.2371753440874457e-06,
      "loss": 0.4224,
      "step": 54705
    },
    {
      "epoch": 1.6805209965287378,
      "grad_norm": 0.4379943013191223,
      "learning_rate": 1.2369425124030354e-06,
      "loss": 0.4479,
      "step": 54706
    },
    {
      "epoch": 1.6805517156636869,
      "grad_norm": 0.4517727196216583,
      "learning_rate": 1.2367097011853601e-06,
      "loss": 0.4613,
      "step": 54707
    },
    {
      "epoch": 1.680582434798636,
      "grad_norm": 0.455288290977478,
      "learning_rate": 1.2364769104349595e-06,
      "loss": 0.4484,
      "step": 54708
    },
    {
      "epoch": 1.6806131539335851,
      "grad_norm": 0.44394442439079285,
      "learning_rate": 1.2362441401523784e-06,
      "loss": 0.4521,
      "step": 54709
    },
    {
      "epoch": 1.6806438730685342,
      "grad_norm": 0.4271829128265381,
      "learning_rate": 1.2360113903381609e-06,
      "loss": 0.4935,
      "step": 54710
    },
    {
      "epoch": 1.6806745922034836,
      "grad_norm": 0.4585135877132416,
      "learning_rate": 1.2357786609928535e-06,
      "loss": 0.5296,
      "step": 54711
    },
    {
      "epoch": 1.6807053113384327,
      "grad_norm": 0.4088886082172394,
      "learning_rate": 1.2355459521169955e-06,
      "loss": 0.4489,
      "step": 54712
    },
    {
      "epoch": 1.6807360304733818,
      "grad_norm": 0.442501038312912,
      "learning_rate": 1.235313263711131e-06,
      "loss": 0.5292,
      "step": 54713
    },
    {
      "epoch": 1.6807667496083312,
      "grad_norm": 0.41423171758651733,
      "learning_rate": 1.235080595775805e-06,
      "loss": 0.5025,
      "step": 54714
    },
    {
      "epoch": 1.6807974687432803,
      "grad_norm": 0.4248606562614441,
      "learning_rate": 1.2348479483115627e-06,
      "loss": 0.4192,
      "step": 54715
    },
    {
      "epoch": 1.6808281878782294,
      "grad_norm": 0.442482590675354,
      "learning_rate": 1.2346153213189426e-06,
      "loss": 0.4932,
      "step": 54716
    },
    {
      "epoch": 1.6808589070131785,
      "grad_norm": 0.44535669684410095,
      "learning_rate": 1.234382714798491e-06,
      "loss": 0.4603,
      "step": 54717
    },
    {
      "epoch": 1.6808896261481276,
      "grad_norm": 0.3897550106048584,
      "learning_rate": 1.2341501287507506e-06,
      "loss": 0.5086,
      "step": 54718
    },
    {
      "epoch": 1.6809203452830768,
      "grad_norm": 0.4106653332710266,
      "learning_rate": 1.2339175631762667e-06,
      "loss": 0.4407,
      "step": 54719
    },
    {
      "epoch": 1.6809510644180259,
      "grad_norm": 0.49160078167915344,
      "learning_rate": 1.2336850180755789e-06,
      "loss": 0.4277,
      "step": 54720
    },
    {
      "epoch": 1.680981783552975,
      "grad_norm": 0.38990500569343567,
      "learning_rate": 1.233452493449233e-06,
      "loss": 0.4873,
      "step": 54721
    },
    {
      "epoch": 1.6810125026879243,
      "grad_norm": 0.42954760789871216,
      "learning_rate": 1.2332199892977682e-06,
      "loss": 0.4725,
      "step": 54722
    },
    {
      "epoch": 1.6810432218228735,
      "grad_norm": 0.3946859836578369,
      "learning_rate": 1.2329875056217321e-06,
      "loss": 0.5036,
      "step": 54723
    },
    {
      "epoch": 1.6810739409578226,
      "grad_norm": 0.4269314408302307,
      "learning_rate": 1.2327550424216672e-06,
      "loss": 0.4914,
      "step": 54724
    },
    {
      "epoch": 1.681104660092772,
      "grad_norm": 0.45932909846305847,
      "learning_rate": 1.2325225996981137e-06,
      "loss": 0.5038,
      "step": 54725
    },
    {
      "epoch": 1.681135379227721,
      "grad_norm": 0.436564177274704,
      "learning_rate": 1.2322901774516184e-06,
      "loss": 0.4541,
      "step": 54726
    },
    {
      "epoch": 1.6811660983626702,
      "grad_norm": 0.45435982942581177,
      "learning_rate": 1.232057775682718e-06,
      "loss": 0.4234,
      "step": 54727
    },
    {
      "epoch": 1.6811968174976193,
      "grad_norm": 0.4101741909980774,
      "learning_rate": 1.2318253943919622e-06,
      "loss": 0.4268,
      "step": 54728
    },
    {
      "epoch": 1.6812275366325684,
      "grad_norm": 0.5259126424789429,
      "learning_rate": 1.2315930335798887e-06,
      "loss": 0.479,
      "step": 54729
    },
    {
      "epoch": 1.6812582557675175,
      "grad_norm": 0.4199520945549011,
      "learning_rate": 1.2313606932470446e-06,
      "loss": 0.4508,
      "step": 54730
    },
    {
      "epoch": 1.6812889749024666,
      "grad_norm": 0.4583429992198944,
      "learning_rate": 1.2311283733939672e-06,
      "loss": 0.4447,
      "step": 54731
    },
    {
      "epoch": 1.6813196940374158,
      "grad_norm": 0.48804280161857605,
      "learning_rate": 1.2308960740212018e-06,
      "loss": 0.4353,
      "step": 54732
    },
    {
      "epoch": 1.681350413172365,
      "grad_norm": 0.4620596766471863,
      "learning_rate": 1.2306637951292922e-06,
      "loss": 0.4833,
      "step": 54733
    },
    {
      "epoch": 1.6813811323073142,
      "grad_norm": 0.42339861392974854,
      "learning_rate": 1.2304315367187802e-06,
      "loss": 0.3988,
      "step": 54734
    },
    {
      "epoch": 1.6814118514422633,
      "grad_norm": 0.4437982738018036,
      "learning_rate": 1.2301992987902067e-06,
      "loss": 0.4408,
      "step": 54735
    },
    {
      "epoch": 1.6814425705772127,
      "grad_norm": 0.4370022416114807,
      "learning_rate": 1.2299670813441156e-06,
      "loss": 0.4765,
      "step": 54736
    },
    {
      "epoch": 1.6814732897121618,
      "grad_norm": 0.41425520181655884,
      "learning_rate": 1.2297348843810485e-06,
      "loss": 0.47,
      "step": 54737
    },
    {
      "epoch": 1.681504008847111,
      "grad_norm": 0.49611496925354004,
      "learning_rate": 1.2295027079015497e-06,
      "loss": 0.4398,
      "step": 54738
    },
    {
      "epoch": 1.68153472798206,
      "grad_norm": 0.5299155712127686,
      "learning_rate": 1.2292705519061576e-06,
      "loss": 0.52,
      "step": 54739
    },
    {
      "epoch": 1.6815654471170092,
      "grad_norm": 0.425787091255188,
      "learning_rate": 1.2290384163954172e-06,
      "loss": 0.4723,
      "step": 54740
    },
    {
      "epoch": 1.6815961662519583,
      "grad_norm": 0.45667213201522827,
      "learning_rate": 1.2288063013698704e-06,
      "loss": 0.4872,
      "step": 54741
    },
    {
      "epoch": 1.6816268853869074,
      "grad_norm": 0.5098472237586975,
      "learning_rate": 1.2285742068300588e-06,
      "loss": 0.543,
      "step": 54742
    },
    {
      "epoch": 1.6816576045218565,
      "grad_norm": 0.413466215133667,
      "learning_rate": 1.2283421327765267e-06,
      "loss": 0.5134,
      "step": 54743
    },
    {
      "epoch": 1.6816883236568059,
      "grad_norm": 0.4282147288322449,
      "learning_rate": 1.2281100792098122e-06,
      "loss": 0.4927,
      "step": 54744
    },
    {
      "epoch": 1.681719042791755,
      "grad_norm": 0.5463280081748962,
      "learning_rate": 1.2278780461304595e-06,
      "loss": 0.4567,
      "step": 54745
    },
    {
      "epoch": 1.6817497619267041,
      "grad_norm": 0.42375648021698,
      "learning_rate": 1.2276460335390095e-06,
      "loss": 0.4716,
      "step": 54746
    },
    {
      "epoch": 1.6817804810616535,
      "grad_norm": 0.4407143294811249,
      "learning_rate": 1.227414041436008e-06,
      "loss": 0.5056,
      "step": 54747
    },
    {
      "epoch": 1.6818112001966026,
      "grad_norm": 0.4272008240222931,
      "learning_rate": 1.2271820698219906e-06,
      "loss": 0.4121,
      "step": 54748
    },
    {
      "epoch": 1.6818419193315517,
      "grad_norm": 0.45909103751182556,
      "learning_rate": 1.226950118697502e-06,
      "loss": 0.4991,
      "step": 54749
    },
    {
      "epoch": 1.6818726384665008,
      "grad_norm": 0.45438021421432495,
      "learning_rate": 1.2267181880630853e-06,
      "loss": 0.6563,
      "step": 54750
    },
    {
      "epoch": 1.68190335760145,
      "grad_norm": 0.5657265782356262,
      "learning_rate": 1.226486277919282e-06,
      "loss": 0.4614,
      "step": 54751
    },
    {
      "epoch": 1.681934076736399,
      "grad_norm": 0.49070847034454346,
      "learning_rate": 1.226254388266631e-06,
      "loss": 0.5341,
      "step": 54752
    },
    {
      "epoch": 1.6819647958713482,
      "grad_norm": 0.44989249110221863,
      "learning_rate": 1.2260225191056784e-06,
      "loss": 0.4421,
      "step": 54753
    },
    {
      "epoch": 1.6819955150062973,
      "grad_norm": 0.4412037432193756,
      "learning_rate": 1.2257906704369583e-06,
      "loss": 0.5039,
      "step": 54754
    },
    {
      "epoch": 1.6820262341412466,
      "grad_norm": 0.43977415561676025,
      "learning_rate": 1.22555884226102e-06,
      "loss": 0.4429,
      "step": 54755
    },
    {
      "epoch": 1.6820569532761958,
      "grad_norm": 0.43149906396865845,
      "learning_rate": 1.2253270345784006e-06,
      "loss": 0.4599,
      "step": 54756
    },
    {
      "epoch": 1.6820876724111449,
      "grad_norm": 0.4517810344696045,
      "learning_rate": 1.2250952473896448e-06,
      "loss": 0.353,
      "step": 54757
    },
    {
      "epoch": 1.6821183915460942,
      "grad_norm": 0.4305267333984375,
      "learning_rate": 1.2248634806952887e-06,
      "loss": 0.5495,
      "step": 54758
    },
    {
      "epoch": 1.6821491106810433,
      "grad_norm": 0.44549405574798584,
      "learning_rate": 1.2246317344958792e-06,
      "loss": 0.4736,
      "step": 54759
    },
    {
      "epoch": 1.6821798298159925,
      "grad_norm": 0.43456605076789856,
      "learning_rate": 1.224400008791954e-06,
      "loss": 0.4519,
      "step": 54760
    },
    {
      "epoch": 1.6822105489509416,
      "grad_norm": 0.4215942323207855,
      "learning_rate": 1.2241683035840557e-06,
      "loss": 0.4516,
      "step": 54761
    },
    {
      "epoch": 1.6822412680858907,
      "grad_norm": 0.4615679383277893,
      "learning_rate": 1.2239366188727263e-06,
      "loss": 0.4853,
      "step": 54762
    },
    {
      "epoch": 1.6822719872208398,
      "grad_norm": 0.42732158303260803,
      "learning_rate": 1.2237049546585033e-06,
      "loss": 0.4072,
      "step": 54763
    },
    {
      "epoch": 1.682302706355789,
      "grad_norm": 0.4590824246406555,
      "learning_rate": 1.2234733109419328e-06,
      "loss": 0.4584,
      "step": 54764
    },
    {
      "epoch": 1.682333425490738,
      "grad_norm": 0.5017825961112976,
      "learning_rate": 1.223241687723552e-06,
      "loss": 0.4161,
      "step": 54765
    },
    {
      "epoch": 1.6823641446256872,
      "grad_norm": 0.39883655309677124,
      "learning_rate": 1.223010085003905e-06,
      "loss": 0.4688,
      "step": 54766
    },
    {
      "epoch": 1.6823948637606365,
      "grad_norm": 0.41244685649871826,
      "learning_rate": 1.2227785027835293e-06,
      "loss": 0.4737,
      "step": 54767
    },
    {
      "epoch": 1.6824255828955856,
      "grad_norm": 0.435425341129303,
      "learning_rate": 1.2225469410629677e-06,
      "loss": 0.4321,
      "step": 54768
    },
    {
      "epoch": 1.682456302030535,
      "grad_norm": 0.4380754828453064,
      "learning_rate": 1.2223153998427594e-06,
      "loss": 0.5084,
      "step": 54769
    },
    {
      "epoch": 1.682487021165484,
      "grad_norm": 0.4193704128265381,
      "learning_rate": 1.2220838791234502e-06,
      "loss": 0.4769,
      "step": 54770
    },
    {
      "epoch": 1.6825177403004332,
      "grad_norm": 0.4455958902835846,
      "learning_rate": 1.2218523789055737e-06,
      "loss": 0.5022,
      "step": 54771
    },
    {
      "epoch": 1.6825484594353823,
      "grad_norm": 0.4644172191619873,
      "learning_rate": 1.221620899189675e-06,
      "loss": 0.4875,
      "step": 54772
    },
    {
      "epoch": 1.6825791785703315,
      "grad_norm": 0.4779122471809387,
      "learning_rate": 1.2213894399762938e-06,
      "loss": 0.4444,
      "step": 54773
    },
    {
      "epoch": 1.6826098977052806,
      "grad_norm": 0.4011699855327606,
      "learning_rate": 1.2211580012659718e-06,
      "loss": 0.4627,
      "step": 54774
    },
    {
      "epoch": 1.6826406168402297,
      "grad_norm": 0.4678921401500702,
      "learning_rate": 1.2209265830592466e-06,
      "loss": 0.465,
      "step": 54775
    },
    {
      "epoch": 1.6826713359751788,
      "grad_norm": 0.5133007168769836,
      "learning_rate": 1.2206951853566606e-06,
      "loss": 0.4881,
      "step": 54776
    },
    {
      "epoch": 1.682702055110128,
      "grad_norm": 0.4294969439506531,
      "learning_rate": 1.220463808158755e-06,
      "loss": 0.465,
      "step": 54777
    },
    {
      "epoch": 1.6827327742450773,
      "grad_norm": 0.38516902923583984,
      "learning_rate": 1.2202324514660679e-06,
      "loss": 0.4874,
      "step": 54778
    },
    {
      "epoch": 1.6827634933800264,
      "grad_norm": 0.4118412733078003,
      "learning_rate": 1.2200011152791436e-06,
      "loss": 0.4612,
      "step": 54779
    },
    {
      "epoch": 1.6827942125149757,
      "grad_norm": 0.423412024974823,
      "learning_rate": 1.2197697995985181e-06,
      "loss": 0.4327,
      "step": 54780
    },
    {
      "epoch": 1.6828249316499249,
      "grad_norm": 0.41691648960113525,
      "learning_rate": 1.2195385044247333e-06,
      "loss": 0.4368,
      "step": 54781
    },
    {
      "epoch": 1.682855650784874,
      "grad_norm": 0.4395841658115387,
      "learning_rate": 1.2193072297583297e-06,
      "loss": 0.4996,
      "step": 54782
    },
    {
      "epoch": 1.682886369919823,
      "grad_norm": 0.4446462094783783,
      "learning_rate": 1.2190759755998493e-06,
      "loss": 0.4321,
      "step": 54783
    },
    {
      "epoch": 1.6829170890547722,
      "grad_norm": 0.41045814752578735,
      "learning_rate": 1.2188447419498283e-06,
      "loss": 0.4132,
      "step": 54784
    },
    {
      "epoch": 1.6829478081897213,
      "grad_norm": 0.45147451758384705,
      "learning_rate": 1.2186135288088085e-06,
      "loss": 0.4875,
      "step": 54785
    },
    {
      "epoch": 1.6829785273246705,
      "grad_norm": 0.44619104266166687,
      "learning_rate": 1.2183823361773305e-06,
      "loss": 0.3808,
      "step": 54786
    },
    {
      "epoch": 1.6830092464596196,
      "grad_norm": 0.4118676483631134,
      "learning_rate": 1.2181511640559352e-06,
      "loss": 0.4355,
      "step": 54787
    },
    {
      "epoch": 1.6830399655945687,
      "grad_norm": 0.5437297821044922,
      "learning_rate": 1.2179200124451596e-06,
      "loss": 0.4239,
      "step": 54788
    },
    {
      "epoch": 1.683070684729518,
      "grad_norm": 0.44137880206108093,
      "learning_rate": 1.2176888813455467e-06,
      "loss": 0.5083,
      "step": 54789
    },
    {
      "epoch": 1.6831014038644672,
      "grad_norm": 0.42288738489151,
      "learning_rate": 1.2174577707576306e-06,
      "loss": 0.4837,
      "step": 54790
    },
    {
      "epoch": 1.6831321229994165,
      "grad_norm": 0.4362679421901703,
      "learning_rate": 1.21722668068196e-06,
      "loss": 0.5231,
      "step": 54791
    },
    {
      "epoch": 1.6831628421343656,
      "grad_norm": 0.42247274518013,
      "learning_rate": 1.2169956111190672e-06,
      "loss": 0.4178,
      "step": 54792
    },
    {
      "epoch": 1.6831935612693147,
      "grad_norm": 0.4524954557418823,
      "learning_rate": 1.216764562069498e-06,
      "loss": 0.4409,
      "step": 54793
    },
    {
      "epoch": 1.6832242804042639,
      "grad_norm": 0.42241790890693665,
      "learning_rate": 1.2165335335337846e-06,
      "loss": 0.4594,
      "step": 54794
    },
    {
      "epoch": 1.683254999539213,
      "grad_norm": 0.48218971490859985,
      "learning_rate": 1.2163025255124717e-06,
      "loss": 0.5304,
      "step": 54795
    },
    {
      "epoch": 1.683285718674162,
      "grad_norm": 0.4240601360797882,
      "learning_rate": 1.2160715380060971e-06,
      "loss": 0.4442,
      "step": 54796
    },
    {
      "epoch": 1.6833164378091112,
      "grad_norm": 0.42819997668266296,
      "learning_rate": 1.215840571015202e-06,
      "loss": 0.4352,
      "step": 54797
    },
    {
      "epoch": 1.6833471569440603,
      "grad_norm": 0.4148293137550354,
      "learning_rate": 1.215609624540326e-06,
      "loss": 0.4094,
      "step": 54798
    },
    {
      "epoch": 1.6833778760790095,
      "grad_norm": 0.47812366485595703,
      "learning_rate": 1.2153786985820025e-06,
      "loss": 0.4867,
      "step": 54799
    },
    {
      "epoch": 1.6834085952139588,
      "grad_norm": 0.4950191378593445,
      "learning_rate": 1.2151477931407808e-06,
      "loss": 0.4347,
      "step": 54800
    },
    {
      "epoch": 1.683439314348908,
      "grad_norm": 0.4558590352535248,
      "learning_rate": 1.2149169082171919e-06,
      "loss": 0.4907,
      "step": 54801
    },
    {
      "epoch": 1.683470033483857,
      "grad_norm": 0.4435386061668396,
      "learning_rate": 1.2146860438117814e-06,
      "loss": 0.4645,
      "step": 54802
    },
    {
      "epoch": 1.6835007526188064,
      "grad_norm": 0.4387601613998413,
      "learning_rate": 1.214455199925082e-06,
      "loss": 0.4801,
      "step": 54803
    },
    {
      "epoch": 1.6835314717537555,
      "grad_norm": 0.4139848053455353,
      "learning_rate": 1.2142243765576366e-06,
      "loss": 0.4363,
      "step": 54804
    },
    {
      "epoch": 1.6835621908887046,
      "grad_norm": 0.47715312242507935,
      "learning_rate": 1.2139935737099828e-06,
      "loss": 0.469,
      "step": 54805
    },
    {
      "epoch": 1.6835929100236537,
      "grad_norm": 0.47471800446510315,
      "learning_rate": 1.2137627913826644e-06,
      "loss": 0.4402,
      "step": 54806
    },
    {
      "epoch": 1.6836236291586029,
      "grad_norm": 0.4202711582183838,
      "learning_rate": 1.2135320295762132e-06,
      "loss": 0.415,
      "step": 54807
    },
    {
      "epoch": 1.683654348293552,
      "grad_norm": 0.4037822186946869,
      "learning_rate": 1.2133012882911721e-06,
      "loss": 0.392,
      "step": 54808
    },
    {
      "epoch": 1.683685067428501,
      "grad_norm": 0.42345017194747925,
      "learning_rate": 1.2130705675280797e-06,
      "loss": 0.4729,
      "step": 54809
    },
    {
      "epoch": 1.6837157865634502,
      "grad_norm": 0.40894976258277893,
      "learning_rate": 1.2128398672874764e-06,
      "loss": 0.4961,
      "step": 54810
    },
    {
      "epoch": 1.6837465056983996,
      "grad_norm": 0.46058109402656555,
      "learning_rate": 1.2126091875698965e-06,
      "loss": 0.5037,
      "step": 54811
    },
    {
      "epoch": 1.6837772248333487,
      "grad_norm": 0.4419402480125427,
      "learning_rate": 1.2123785283758826e-06,
      "loss": 0.3614,
      "step": 54812
    },
    {
      "epoch": 1.6838079439682978,
      "grad_norm": 0.4444139897823334,
      "learning_rate": 1.2121478897059725e-06,
      "loss": 0.4525,
      "step": 54813
    },
    {
      "epoch": 1.6838386631032471,
      "grad_norm": 0.4595537483692169,
      "learning_rate": 1.2119172715607064e-06,
      "loss": 0.3966,
      "step": 54814
    },
    {
      "epoch": 1.6838693822381963,
      "grad_norm": 0.43353864550590515,
      "learning_rate": 1.2116866739406185e-06,
      "loss": 0.4608,
      "step": 54815
    },
    {
      "epoch": 1.6839001013731454,
      "grad_norm": 0.40655598044395447,
      "learning_rate": 1.2114560968462509e-06,
      "loss": 0.4845,
      "step": 54816
    },
    {
      "epoch": 1.6839308205080945,
      "grad_norm": 0.43605828285217285,
      "learning_rate": 1.2112255402781415e-06,
      "loss": 0.4242,
      "step": 54817
    },
    {
      "epoch": 1.6839615396430436,
      "grad_norm": 0.381314218044281,
      "learning_rate": 1.2109950042368279e-06,
      "loss": 0.5063,
      "step": 54818
    },
    {
      "epoch": 1.6839922587779927,
      "grad_norm": 0.411252498626709,
      "learning_rate": 1.210764488722852e-06,
      "loss": 0.4823,
      "step": 54819
    },
    {
      "epoch": 1.6840229779129419,
      "grad_norm": 0.40519025921821594,
      "learning_rate": 1.2105339937367478e-06,
      "loss": 0.4474,
      "step": 54820
    },
    {
      "epoch": 1.684053697047891,
      "grad_norm": 0.4568619430065155,
      "learning_rate": 1.2103035192790546e-06,
      "loss": 0.4895,
      "step": 54821
    },
    {
      "epoch": 1.6840844161828403,
      "grad_norm": 0.44204986095428467,
      "learning_rate": 1.2100730653503113e-06,
      "loss": 0.3929,
      "step": 54822
    },
    {
      "epoch": 1.6841151353177894,
      "grad_norm": 0.4281037151813507,
      "learning_rate": 1.2098426319510592e-06,
      "loss": 0.4906,
      "step": 54823
    },
    {
      "epoch": 1.6841458544527386,
      "grad_norm": 0.37964192032814026,
      "learning_rate": 1.2096122190818304e-06,
      "loss": 0.4511,
      "step": 54824
    },
    {
      "epoch": 1.684176573587688,
      "grad_norm": 0.42950350046157837,
      "learning_rate": 1.2093818267431689e-06,
      "loss": 0.4077,
      "step": 54825
    },
    {
      "epoch": 1.684207292722637,
      "grad_norm": 0.44639483094215393,
      "learning_rate": 1.2091514549356054e-06,
      "loss": 0.4379,
      "step": 54826
    },
    {
      "epoch": 1.6842380118575861,
      "grad_norm": 0.3964971601963043,
      "learning_rate": 1.208921103659687e-06,
      "loss": 0.4461,
      "step": 54827
    },
    {
      "epoch": 1.6842687309925353,
      "grad_norm": 0.420828640460968,
      "learning_rate": 1.2086907729159458e-06,
      "loss": 0.4802,
      "step": 54828
    },
    {
      "epoch": 1.6842994501274844,
      "grad_norm": 0.44151341915130615,
      "learning_rate": 1.2084604627049234e-06,
      "loss": 0.4146,
      "step": 54829
    },
    {
      "epoch": 1.6843301692624335,
      "grad_norm": 0.502199649810791,
      "learning_rate": 1.208230173027153e-06,
      "loss": 0.4444,
      "step": 54830
    },
    {
      "epoch": 1.6843608883973826,
      "grad_norm": 0.450377881526947,
      "learning_rate": 1.2079999038831747e-06,
      "loss": 0.4751,
      "step": 54831
    },
    {
      "epoch": 1.6843916075323317,
      "grad_norm": 0.3979617655277252,
      "learning_rate": 1.2077696552735273e-06,
      "loss": 0.5025,
      "step": 54832
    },
    {
      "epoch": 1.684422326667281,
      "grad_norm": 0.44424769282341003,
      "learning_rate": 1.2075394271987472e-06,
      "loss": 0.4857,
      "step": 54833
    },
    {
      "epoch": 1.6844530458022302,
      "grad_norm": 0.47323620319366455,
      "learning_rate": 1.207309219659375e-06,
      "loss": 0.4407,
      "step": 54834
    },
    {
      "epoch": 1.6844837649371793,
      "grad_norm": 0.48260629177093506,
      "learning_rate": 1.2070790326559444e-06,
      "loss": 0.473,
      "step": 54835
    },
    {
      "epoch": 1.6845144840721287,
      "grad_norm": 0.5011167526245117,
      "learning_rate": 1.2068488661889953e-06,
      "loss": 0.4979,
      "step": 54836
    },
    {
      "epoch": 1.6845452032070778,
      "grad_norm": 0.44776690006256104,
      "learning_rate": 1.206618720259064e-06,
      "loss": 0.5505,
      "step": 54837
    },
    {
      "epoch": 1.684575922342027,
      "grad_norm": 0.5376908779144287,
      "learning_rate": 1.206388594866692e-06,
      "loss": 0.4838,
      "step": 54838
    },
    {
      "epoch": 1.684606641476976,
      "grad_norm": 0.4417889714241028,
      "learning_rate": 1.20615849001241e-06,
      "loss": 0.4904,
      "step": 54839
    },
    {
      "epoch": 1.6846373606119251,
      "grad_norm": 0.40460312366485596,
      "learning_rate": 1.2059284056967602e-06,
      "loss": 0.4474,
      "step": 54840
    },
    {
      "epoch": 1.6846680797468743,
      "grad_norm": 0.4395935833454132,
      "learning_rate": 1.2056983419202784e-06,
      "loss": 0.4728,
      "step": 54841
    },
    {
      "epoch": 1.6846987988818234,
      "grad_norm": 0.46900224685668945,
      "learning_rate": 1.2054682986835043e-06,
      "loss": 0.4716,
      "step": 54842
    },
    {
      "epoch": 1.6847295180167725,
      "grad_norm": 0.4062475562095642,
      "learning_rate": 1.2052382759869708e-06,
      "loss": 0.4093,
      "step": 54843
    },
    {
      "epoch": 1.6847602371517219,
      "grad_norm": 0.4208558201789856,
      "learning_rate": 1.2050082738312175e-06,
      "loss": 0.4443,
      "step": 54844
    },
    {
      "epoch": 1.684790956286671,
      "grad_norm": 0.44961509108543396,
      "learning_rate": 1.2047782922167817e-06,
      "loss": 0.4707,
      "step": 54845
    },
    {
      "epoch": 1.68482167542162,
      "grad_norm": 0.48317548632621765,
      "learning_rate": 1.204548331144203e-06,
      "loss": 0.4672,
      "step": 54846
    },
    {
      "epoch": 1.6848523945565694,
      "grad_norm": 0.40575405955314636,
      "learning_rate": 1.2043183906140142e-06,
      "loss": 0.4728,
      "step": 54847
    },
    {
      "epoch": 1.6848831136915186,
      "grad_norm": 0.37915581464767456,
      "learning_rate": 1.204088470626753e-06,
      "loss": 0.4376,
      "step": 54848
    },
    {
      "epoch": 1.6849138328264677,
      "grad_norm": 0.4208448827266693,
      "learning_rate": 1.2038585711829576e-06,
      "loss": 0.4705,
      "step": 54849
    },
    {
      "epoch": 1.6849445519614168,
      "grad_norm": 0.415498822927475,
      "learning_rate": 1.2036286922831675e-06,
      "loss": 0.402,
      "step": 54850
    },
    {
      "epoch": 1.684975271096366,
      "grad_norm": 0.4199298918247223,
      "learning_rate": 1.2033988339279145e-06,
      "loss": 0.4617,
      "step": 54851
    },
    {
      "epoch": 1.685005990231315,
      "grad_norm": 0.45583587884902954,
      "learning_rate": 1.2031689961177384e-06,
      "loss": 0.4235,
      "step": 54852
    },
    {
      "epoch": 1.6850367093662642,
      "grad_norm": 0.3960401713848114,
      "learning_rate": 1.2029391788531752e-06,
      "loss": 0.4601,
      "step": 54853
    },
    {
      "epoch": 1.6850674285012133,
      "grad_norm": 0.46342068910598755,
      "learning_rate": 1.2027093821347613e-06,
      "loss": 0.4638,
      "step": 54854
    },
    {
      "epoch": 1.6850981476361626,
      "grad_norm": 0.4000902771949768,
      "learning_rate": 1.2024796059630372e-06,
      "loss": 0.4039,
      "step": 54855
    },
    {
      "epoch": 1.6851288667711117,
      "grad_norm": 0.41117048263549805,
      "learning_rate": 1.2022498503385338e-06,
      "loss": 0.4589,
      "step": 54856
    },
    {
      "epoch": 1.6851595859060609,
      "grad_norm": 0.47096216678619385,
      "learning_rate": 1.2020201152617915e-06,
      "loss": 0.4734,
      "step": 54857
    },
    {
      "epoch": 1.6851903050410102,
      "grad_norm": 0.44371744990348816,
      "learning_rate": 1.2017904007333425e-06,
      "loss": 0.4556,
      "step": 54858
    },
    {
      "epoch": 1.6852210241759593,
      "grad_norm": 0.4260176122188568,
      "learning_rate": 1.2015607067537304e-06,
      "loss": 0.4092,
      "step": 54859
    },
    {
      "epoch": 1.6852517433109084,
      "grad_norm": 0.4350285530090332,
      "learning_rate": 1.2013310333234862e-06,
      "loss": 0.4337,
      "step": 54860
    },
    {
      "epoch": 1.6852824624458576,
      "grad_norm": 0.49552321434020996,
      "learning_rate": 1.2011013804431494e-06,
      "loss": 0.5124,
      "step": 54861
    },
    {
      "epoch": 1.6853131815808067,
      "grad_norm": 0.5798865556716919,
      "learning_rate": 1.2008717481132504e-06,
      "loss": 0.4676,
      "step": 54862
    },
    {
      "epoch": 1.6853439007157558,
      "grad_norm": 0.41687729954719543,
      "learning_rate": 1.2006421363343347e-06,
      "loss": 0.4953,
      "step": 54863
    },
    {
      "epoch": 1.685374619850705,
      "grad_norm": 0.4167197346687317,
      "learning_rate": 1.2004125451069314e-06,
      "loss": 0.4744,
      "step": 54864
    },
    {
      "epoch": 1.685405338985654,
      "grad_norm": 0.4371127784252167,
      "learning_rate": 1.2001829744315817e-06,
      "loss": 0.513,
      "step": 54865
    },
    {
      "epoch": 1.6854360581206034,
      "grad_norm": 0.43194466829299927,
      "learning_rate": 1.1999534243088163e-06,
      "loss": 0.3955,
      "step": 54866
    },
    {
      "epoch": 1.6854667772555525,
      "grad_norm": 0.45524850487709045,
      "learning_rate": 1.1997238947391743e-06,
      "loss": 0.4413,
      "step": 54867
    },
    {
      "epoch": 1.6854974963905016,
      "grad_norm": 0.4842586815357208,
      "learning_rate": 1.1994943857231923e-06,
      "loss": 0.425,
      "step": 54868
    },
    {
      "epoch": 1.685528215525451,
      "grad_norm": 0.45185357332229614,
      "learning_rate": 1.1992648972614064e-06,
      "loss": 0.4385,
      "step": 54869
    },
    {
      "epoch": 1.6855589346604,
      "grad_norm": 0.4746874272823334,
      "learning_rate": 1.1990354293543526e-06,
      "loss": 0.4479,
      "step": 54870
    },
    {
      "epoch": 1.6855896537953492,
      "grad_norm": 0.5425884127616882,
      "learning_rate": 1.1988059820025654e-06,
      "loss": 0.4273,
      "step": 54871
    },
    {
      "epoch": 1.6856203729302983,
      "grad_norm": 0.42648637294769287,
      "learning_rate": 1.198576555206581e-06,
      "loss": 0.3884,
      "step": 54872
    },
    {
      "epoch": 1.6856510920652474,
      "grad_norm": 0.5073956251144409,
      "learning_rate": 1.198347148966935e-06,
      "loss": 0.4998,
      "step": 54873
    },
    {
      "epoch": 1.6856818112001966,
      "grad_norm": 0.4471588432788849,
      "learning_rate": 1.1981177632841668e-06,
      "loss": 0.485,
      "step": 54874
    },
    {
      "epoch": 1.6857125303351457,
      "grad_norm": 0.43710842728614807,
      "learning_rate": 1.1978883981588075e-06,
      "loss": 0.4847,
      "step": 54875
    },
    {
      "epoch": 1.6857432494700948,
      "grad_norm": 0.44543159008026123,
      "learning_rate": 1.1976590535913946e-06,
      "loss": 0.4454,
      "step": 54876
    },
    {
      "epoch": 1.6857739686050441,
      "grad_norm": 0.4433836340904236,
      "learning_rate": 1.1974297295824634e-06,
      "loss": 0.4459,
      "step": 54877
    },
    {
      "epoch": 1.6858046877399933,
      "grad_norm": 0.4467536509037018,
      "learning_rate": 1.197200426132551e-06,
      "loss": 0.443,
      "step": 54878
    },
    {
      "epoch": 1.6858354068749424,
      "grad_norm": 0.4169778525829315,
      "learning_rate": 1.1969711432421904e-06,
      "loss": 0.4497,
      "step": 54879
    },
    {
      "epoch": 1.6858661260098917,
      "grad_norm": 0.44444161653518677,
      "learning_rate": 1.196741880911919e-06,
      "loss": 0.4585,
      "step": 54880
    },
    {
      "epoch": 1.6858968451448408,
      "grad_norm": 0.4445001482963562,
      "learning_rate": 1.196512639142271e-06,
      "loss": 0.46,
      "step": 54881
    },
    {
      "epoch": 1.68592756427979,
      "grad_norm": 0.45824360847473145,
      "learning_rate": 1.1962834179337856e-06,
      "loss": 0.4395,
      "step": 54882
    },
    {
      "epoch": 1.685958283414739,
      "grad_norm": 0.44629722833633423,
      "learning_rate": 1.1960542172869927e-06,
      "loss": 0.4382,
      "step": 54883
    },
    {
      "epoch": 1.6859890025496882,
      "grad_norm": 0.44520285725593567,
      "learning_rate": 1.1958250372024294e-06,
      "loss": 0.4838,
      "step": 54884
    },
    {
      "epoch": 1.6860197216846373,
      "grad_norm": 0.4453292191028595,
      "learning_rate": 1.195595877680632e-06,
      "loss": 0.4549,
      "step": 54885
    },
    {
      "epoch": 1.6860504408195864,
      "grad_norm": 0.4446019232273102,
      "learning_rate": 1.195366738722138e-06,
      "loss": 0.467,
      "step": 54886
    },
    {
      "epoch": 1.6860811599545356,
      "grad_norm": 0.4411013126373291,
      "learning_rate": 1.1951376203274768e-06,
      "loss": 0.446,
      "step": 54887
    },
    {
      "epoch": 1.6861118790894847,
      "grad_norm": 0.43588247895240784,
      "learning_rate": 1.1949085224971867e-06,
      "loss": 0.4798,
      "step": 54888
    },
    {
      "epoch": 1.686142598224434,
      "grad_norm": 0.432915598154068,
      "learning_rate": 1.1946794452318033e-06,
      "loss": 0.4786,
      "step": 54889
    },
    {
      "epoch": 1.6861733173593831,
      "grad_norm": 0.45968541502952576,
      "learning_rate": 1.1944503885318604e-06,
      "loss": 0.4812,
      "step": 54890
    },
    {
      "epoch": 1.6862040364943325,
      "grad_norm": 0.4551224708557129,
      "learning_rate": 1.1942213523978964e-06,
      "loss": 0.4124,
      "step": 54891
    },
    {
      "epoch": 1.6862347556292816,
      "grad_norm": 0.548936128616333,
      "learning_rate": 1.1939923368304407e-06,
      "loss": 0.4515,
      "step": 54892
    },
    {
      "epoch": 1.6862654747642307,
      "grad_norm": 0.4247969090938568,
      "learning_rate": 1.1937633418300332e-06,
      "loss": 0.425,
      "step": 54893
    },
    {
      "epoch": 1.6862961938991798,
      "grad_norm": 0.5903679132461548,
      "learning_rate": 1.1935343673972023e-06,
      "loss": 0.4697,
      "step": 54894
    },
    {
      "epoch": 1.686326913034129,
      "grad_norm": 0.44594547152519226,
      "learning_rate": 1.1933054135324906e-06,
      "loss": 0.4118,
      "step": 54895
    },
    {
      "epoch": 1.686357632169078,
      "grad_norm": 0.42706847190856934,
      "learning_rate": 1.1930764802364282e-06,
      "loss": 0.4719,
      "step": 54896
    },
    {
      "epoch": 1.6863883513040272,
      "grad_norm": 0.4221293330192566,
      "learning_rate": 1.1928475675095518e-06,
      "loss": 0.4802,
      "step": 54897
    },
    {
      "epoch": 1.6864190704389763,
      "grad_norm": 0.4860096275806427,
      "learning_rate": 1.1926186753523938e-06,
      "loss": 0.4701,
      "step": 54898
    },
    {
      "epoch": 1.6864497895739254,
      "grad_norm": 0.45548275113105774,
      "learning_rate": 1.192389803765489e-06,
      "loss": 0.4725,
      "step": 54899
    },
    {
      "epoch": 1.6864805087088748,
      "grad_norm": 0.4486459195613861,
      "learning_rate": 1.1921609527493739e-06,
      "loss": 0.5071,
      "step": 54900
    },
    {
      "epoch": 1.686511227843824,
      "grad_norm": 0.4400615692138672,
      "learning_rate": 1.1919321223045831e-06,
      "loss": 0.477,
      "step": 54901
    },
    {
      "epoch": 1.6865419469787732,
      "grad_norm": 0.4465276598930359,
      "learning_rate": 1.1917033124316479e-06,
      "loss": 0.434,
      "step": 54902
    },
    {
      "epoch": 1.6865726661137224,
      "grad_norm": 0.462585985660553,
      "learning_rate": 1.1914745231311054e-06,
      "loss": 0.4324,
      "step": 54903
    },
    {
      "epoch": 1.6866033852486715,
      "grad_norm": 0.46053001284599304,
      "learning_rate": 1.1912457544034895e-06,
      "loss": 0.4747,
      "step": 54904
    },
    {
      "epoch": 1.6866341043836206,
      "grad_norm": 0.406619668006897,
      "learning_rate": 1.1910170062493364e-06,
      "loss": 0.4385,
      "step": 54905
    },
    {
      "epoch": 1.6866648235185697,
      "grad_norm": 0.39477893710136414,
      "learning_rate": 1.190788278669176e-06,
      "loss": 0.4466,
      "step": 54906
    },
    {
      "epoch": 1.6866955426535188,
      "grad_norm": 0.3970065116882324,
      "learning_rate": 1.1905595716635443e-06,
      "loss": 0.4773,
      "step": 54907
    },
    {
      "epoch": 1.686726261788468,
      "grad_norm": 0.500706136226654,
      "learning_rate": 1.1903308852329764e-06,
      "loss": 0.4707,
      "step": 54908
    },
    {
      "epoch": 1.686756980923417,
      "grad_norm": 0.4453457295894623,
      "learning_rate": 1.1901022193780066e-06,
      "loss": 0.3812,
      "step": 54909
    },
    {
      "epoch": 1.6867877000583662,
      "grad_norm": 0.3976696729660034,
      "learning_rate": 1.1898735740991697e-06,
      "loss": 0.4647,
      "step": 54910
    },
    {
      "epoch": 1.6868184191933155,
      "grad_norm": 0.4574793577194214,
      "learning_rate": 1.1896449493969964e-06,
      "loss": 0.4763,
      "step": 54911
    },
    {
      "epoch": 1.6868491383282647,
      "grad_norm": 0.4583117961883545,
      "learning_rate": 1.189416345272022e-06,
      "loss": 0.4065,
      "step": 54912
    },
    {
      "epoch": 1.6868798574632138,
      "grad_norm": 0.4439266324043274,
      "learning_rate": 1.1891877617247815e-06,
      "loss": 0.4747,
      "step": 54913
    },
    {
      "epoch": 1.6869105765981631,
      "grad_norm": 0.48168495297431946,
      "learning_rate": 1.1889591987558113e-06,
      "loss": 0.4033,
      "step": 54914
    },
    {
      "epoch": 1.6869412957331122,
      "grad_norm": 0.4322540760040283,
      "learning_rate": 1.1887306563656387e-06,
      "loss": 0.4779,
      "step": 54915
    },
    {
      "epoch": 1.6869720148680614,
      "grad_norm": 0.4556117057800293,
      "learning_rate": 1.188502134554802e-06,
      "loss": 0.5246,
      "step": 54916
    },
    {
      "epoch": 1.6870027340030105,
      "grad_norm": 0.43982648849487305,
      "learning_rate": 1.1882736333238343e-06,
      "loss": 0.4105,
      "step": 54917
    },
    {
      "epoch": 1.6870334531379596,
      "grad_norm": 0.5521616339683533,
      "learning_rate": 1.1880451526732705e-06,
      "loss": 0.4349,
      "step": 54918
    },
    {
      "epoch": 1.6870641722729087,
      "grad_norm": 0.4555787742137909,
      "learning_rate": 1.1878166926036404e-06,
      "loss": 0.4991,
      "step": 54919
    },
    {
      "epoch": 1.6870948914078578,
      "grad_norm": 0.5127396583557129,
      "learning_rate": 1.1875882531154814e-06,
      "loss": 0.5044,
      "step": 54920
    },
    {
      "epoch": 1.687125610542807,
      "grad_norm": 0.4023917317390442,
      "learning_rate": 1.1873598342093218e-06,
      "loss": 0.4522,
      "step": 54921
    },
    {
      "epoch": 1.6871563296777563,
      "grad_norm": 0.3751161992549896,
      "learning_rate": 1.1871314358857034e-06,
      "loss": 0.3741,
      "step": 54922
    },
    {
      "epoch": 1.6871870488127054,
      "grad_norm": 0.45512354373931885,
      "learning_rate": 1.1869030581451523e-06,
      "loss": 0.4857,
      "step": 54923
    },
    {
      "epoch": 1.6872177679476545,
      "grad_norm": 0.43838733434677124,
      "learning_rate": 1.186674700988205e-06,
      "loss": 0.4697,
      "step": 54924
    },
    {
      "epoch": 1.6872484870826039,
      "grad_norm": 0.42811352014541626,
      "learning_rate": 1.1864463644153945e-06,
      "loss": 0.4696,
      "step": 54925
    },
    {
      "epoch": 1.687279206217553,
      "grad_norm": 0.41054922342300415,
      "learning_rate": 1.1862180484272544e-06,
      "loss": 0.4991,
      "step": 54926
    },
    {
      "epoch": 1.6873099253525021,
      "grad_norm": 0.49487268924713135,
      "learning_rate": 1.1859897530243191e-06,
      "loss": 0.4387,
      "step": 54927
    },
    {
      "epoch": 1.6873406444874512,
      "grad_norm": 0.5033013224601746,
      "learning_rate": 1.1857614782071182e-06,
      "loss": 0.5001,
      "step": 54928
    },
    {
      "epoch": 1.6873713636224004,
      "grad_norm": 0.4528128206729889,
      "learning_rate": 1.1855332239761896e-06,
      "loss": 0.4225,
      "step": 54929
    },
    {
      "epoch": 1.6874020827573495,
      "grad_norm": 0.4362771213054657,
      "learning_rate": 1.185304990332059e-06,
      "loss": 0.5024,
      "step": 54930
    },
    {
      "epoch": 1.6874328018922986,
      "grad_norm": 0.4676496982574463,
      "learning_rate": 1.185076777275268e-06,
      "loss": 0.4391,
      "step": 54931
    },
    {
      "epoch": 1.6874635210272477,
      "grad_norm": 0.44107937812805176,
      "learning_rate": 1.1848485848063452e-06,
      "loss": 0.5047,
      "step": 54932
    },
    {
      "epoch": 1.687494240162197,
      "grad_norm": 0.43195611238479614,
      "learning_rate": 1.1846204129258244e-06,
      "loss": 0.4347,
      "step": 54933
    },
    {
      "epoch": 1.6875249592971462,
      "grad_norm": 0.4023028612136841,
      "learning_rate": 1.1843922616342373e-06,
      "loss": 0.4842,
      "step": 54934
    },
    {
      "epoch": 1.6875556784320953,
      "grad_norm": 0.4760981500148773,
      "learning_rate": 1.1841641309321173e-06,
      "loss": 0.4491,
      "step": 54935
    },
    {
      "epoch": 1.6875863975670446,
      "grad_norm": 0.4436219334602356,
      "learning_rate": 1.183936020819998e-06,
      "loss": 0.4642,
      "step": 54936
    },
    {
      "epoch": 1.6876171167019938,
      "grad_norm": 0.422649085521698,
      "learning_rate": 1.1837079312984146e-06,
      "loss": 0.4685,
      "step": 54937
    },
    {
      "epoch": 1.6876478358369429,
      "grad_norm": 0.5190823078155518,
      "learning_rate": 1.1834798623678933e-06,
      "loss": 0.46,
      "step": 54938
    },
    {
      "epoch": 1.687678554971892,
      "grad_norm": 0.4430663585662842,
      "learning_rate": 1.1832518140289718e-06,
      "loss": 0.4483,
      "step": 54939
    },
    {
      "epoch": 1.6877092741068411,
      "grad_norm": 0.5827473402023315,
      "learning_rate": 1.1830237862821814e-06,
      "loss": 0.4556,
      "step": 54940
    },
    {
      "epoch": 1.6877399932417902,
      "grad_norm": 0.4271569848060608,
      "learning_rate": 1.1827957791280565e-06,
      "loss": 0.4744,
      "step": 54941
    },
    {
      "epoch": 1.6877707123767394,
      "grad_norm": 0.43935367465019226,
      "learning_rate": 1.1825677925671254e-06,
      "loss": 0.4482,
      "step": 54942
    },
    {
      "epoch": 1.6878014315116885,
      "grad_norm": 0.4545283317565918,
      "learning_rate": 1.182339826599923e-06,
      "loss": 0.4719,
      "step": 54943
    },
    {
      "epoch": 1.6878321506466378,
      "grad_norm": 0.42827436327934265,
      "learning_rate": 1.1821118812269827e-06,
      "loss": 0.4362,
      "step": 54944
    },
    {
      "epoch": 1.687862869781587,
      "grad_norm": 0.4136323630809784,
      "learning_rate": 1.1818839564488348e-06,
      "loss": 0.4599,
      "step": 54945
    },
    {
      "epoch": 1.687893588916536,
      "grad_norm": 0.47195595502853394,
      "learning_rate": 1.1816560522660159e-06,
      "loss": 0.5453,
      "step": 54946
    },
    {
      "epoch": 1.6879243080514854,
      "grad_norm": 0.5721394419670105,
      "learning_rate": 1.1814281686790518e-06,
      "loss": 0.4189,
      "step": 54947
    },
    {
      "epoch": 1.6879550271864345,
      "grad_norm": 0.44663873314857483,
      "learning_rate": 1.1812003056884791e-06,
      "loss": 0.4192,
      "step": 54948
    },
    {
      "epoch": 1.6879857463213837,
      "grad_norm": 0.41360005736351013,
      "learning_rate": 1.1809724632948295e-06,
      "loss": 0.4471,
      "step": 54949
    },
    {
      "epoch": 1.6880164654563328,
      "grad_norm": 0.45128560066223145,
      "learning_rate": 1.1807446414986356e-06,
      "loss": 0.4742,
      "step": 54950
    },
    {
      "epoch": 1.688047184591282,
      "grad_norm": 0.4300757944583893,
      "learning_rate": 1.1805168403004263e-06,
      "loss": 0.4203,
      "step": 54951
    },
    {
      "epoch": 1.688077903726231,
      "grad_norm": 0.42718201875686646,
      "learning_rate": 1.1802890597007366e-06,
      "loss": 0.4475,
      "step": 54952
    },
    {
      "epoch": 1.6881086228611801,
      "grad_norm": 0.40081560611724854,
      "learning_rate": 1.1800612997000971e-06,
      "loss": 0.4899,
      "step": 54953
    },
    {
      "epoch": 1.6881393419961293,
      "grad_norm": 0.4532846212387085,
      "learning_rate": 1.179833560299043e-06,
      "loss": 0.441,
      "step": 54954
    },
    {
      "epoch": 1.6881700611310786,
      "grad_norm": 0.4646737277507782,
      "learning_rate": 1.1796058414981015e-06,
      "loss": 0.4799,
      "step": 54955
    },
    {
      "epoch": 1.6882007802660277,
      "grad_norm": 0.4298328459262848,
      "learning_rate": 1.179378143297809e-06,
      "loss": 0.4135,
      "step": 54956
    },
    {
      "epoch": 1.6882314994009768,
      "grad_norm": 0.4200849235057831,
      "learning_rate": 1.1791504656986907e-06,
      "loss": 0.4358,
      "step": 54957
    },
    {
      "epoch": 1.6882622185359262,
      "grad_norm": 0.4007112979888916,
      "learning_rate": 1.178922808701286e-06,
      "loss": 0.4386,
      "step": 54958
    },
    {
      "epoch": 1.6882929376708753,
      "grad_norm": 0.4245953857898712,
      "learning_rate": 1.1786951723061212e-06,
      "loss": 0.3552,
      "step": 54959
    },
    {
      "epoch": 1.6883236568058244,
      "grad_norm": 0.40900683403015137,
      "learning_rate": 1.1784675565137328e-06,
      "loss": 0.3987,
      "step": 54960
    },
    {
      "epoch": 1.6883543759407735,
      "grad_norm": 0.4178999960422516,
      "learning_rate": 1.1782399613246466e-06,
      "loss": 0.4678,
      "step": 54961
    },
    {
      "epoch": 1.6883850950757227,
      "grad_norm": 0.4322391152381897,
      "learning_rate": 1.1780123867393944e-06,
      "loss": 0.5264,
      "step": 54962
    },
    {
      "epoch": 1.6884158142106718,
      "grad_norm": 0.42130905389785767,
      "learning_rate": 1.177784832758515e-06,
      "loss": 0.4987,
      "step": 54963
    },
    {
      "epoch": 1.688446533345621,
      "grad_norm": 0.5012207627296448,
      "learning_rate": 1.1775572993825336e-06,
      "loss": 0.4963,
      "step": 54964
    },
    {
      "epoch": 1.68847725248057,
      "grad_norm": 0.446983277797699,
      "learning_rate": 1.177329786611986e-06,
      "loss": 0.4711,
      "step": 54965
    },
    {
      "epoch": 1.6885079716155194,
      "grad_norm": 0.4484865367412567,
      "learning_rate": 1.1771022944473954e-06,
      "loss": 0.4784,
      "step": 54966
    },
    {
      "epoch": 1.6885386907504685,
      "grad_norm": 0.42355793714523315,
      "learning_rate": 1.1768748228893035e-06,
      "loss": 0.4938,
      "step": 54967
    },
    {
      "epoch": 1.6885694098854176,
      "grad_norm": 0.40093955397605896,
      "learning_rate": 1.1766473719382343e-06,
      "loss": 0.4712,
      "step": 54968
    },
    {
      "epoch": 1.688600129020367,
      "grad_norm": 0.47908154129981995,
      "learning_rate": 1.1764199415947231e-06,
      "loss": 0.4439,
      "step": 54969
    },
    {
      "epoch": 1.688630848155316,
      "grad_norm": 0.4497736394405365,
      "learning_rate": 1.1761925318592982e-06,
      "loss": 0.4406,
      "step": 54970
    },
    {
      "epoch": 1.6886615672902652,
      "grad_norm": 0.38991594314575195,
      "learning_rate": 1.1759651427324915e-06,
      "loss": 0.4364,
      "step": 54971
    },
    {
      "epoch": 1.6886922864252143,
      "grad_norm": 0.45721426606178284,
      "learning_rate": 1.1757377742148334e-06,
      "loss": 0.5172,
      "step": 54972
    },
    {
      "epoch": 1.6887230055601634,
      "grad_norm": 0.47445210814476013,
      "learning_rate": 1.1755104263068594e-06,
      "loss": 0.582,
      "step": 54973
    },
    {
      "epoch": 1.6887537246951125,
      "grad_norm": 0.4747923016548157,
      "learning_rate": 1.1752830990090946e-06,
      "loss": 0.5416,
      "step": 54974
    },
    {
      "epoch": 1.6887844438300617,
      "grad_norm": 0.43161484599113464,
      "learning_rate": 1.175055792322073e-06,
      "loss": 0.5221,
      "step": 54975
    },
    {
      "epoch": 1.6888151629650108,
      "grad_norm": 0.3944248557090759,
      "learning_rate": 1.1748285062463238e-06,
      "loss": 0.4201,
      "step": 54976
    },
    {
      "epoch": 1.6888458820999601,
      "grad_norm": 0.4427584111690521,
      "learning_rate": 1.1746012407823815e-06,
      "loss": 0.4934,
      "step": 54977
    },
    {
      "epoch": 1.6888766012349092,
      "grad_norm": 0.4553014039993286,
      "learning_rate": 1.174373995930773e-06,
      "loss": 0.5266,
      "step": 54978
    },
    {
      "epoch": 1.6889073203698584,
      "grad_norm": 0.4271681010723114,
      "learning_rate": 1.1741467716920296e-06,
      "loss": 0.4921,
      "step": 54979
    },
    {
      "epoch": 1.6889380395048077,
      "grad_norm": 0.5040033459663391,
      "learning_rate": 1.1739195680666826e-06,
      "loss": 0.4563,
      "step": 54980
    },
    {
      "epoch": 1.6889687586397568,
      "grad_norm": 0.48918983340263367,
      "learning_rate": 1.173692385055264e-06,
      "loss": 0.5009,
      "step": 54981
    },
    {
      "epoch": 1.688999477774706,
      "grad_norm": 0.3816736936569214,
      "learning_rate": 1.1734652226583044e-06,
      "loss": 0.445,
      "step": 54982
    },
    {
      "epoch": 1.689030196909655,
      "grad_norm": 0.4631160497665405,
      "learning_rate": 1.173238080876331e-06,
      "loss": 0.4514,
      "step": 54983
    },
    {
      "epoch": 1.6890609160446042,
      "grad_norm": 0.4340460002422333,
      "learning_rate": 1.173010959709877e-06,
      "loss": 0.3767,
      "step": 54984
    },
    {
      "epoch": 1.6890916351795533,
      "grad_norm": 0.38233041763305664,
      "learning_rate": 1.172783859159472e-06,
      "loss": 0.4226,
      "step": 54985
    },
    {
      "epoch": 1.6891223543145024,
      "grad_norm": 0.42150911688804626,
      "learning_rate": 1.1725567792256498e-06,
      "loss": 0.4857,
      "step": 54986
    },
    {
      "epoch": 1.6891530734494515,
      "grad_norm": 0.42931586503982544,
      "learning_rate": 1.1723297199089344e-06,
      "loss": 0.5103,
      "step": 54987
    },
    {
      "epoch": 1.6891837925844009,
      "grad_norm": 0.59202641248703,
      "learning_rate": 1.17210268120986e-06,
      "loss": 0.4772,
      "step": 54988
    },
    {
      "epoch": 1.68921451171935,
      "grad_norm": 0.48894867300987244,
      "learning_rate": 1.1718756631289562e-06,
      "loss": 0.4777,
      "step": 54989
    },
    {
      "epoch": 1.6892452308542991,
      "grad_norm": 0.4458387792110443,
      "learning_rate": 1.171648665666756e-06,
      "loss": 0.511,
      "step": 54990
    },
    {
      "epoch": 1.6892759499892485,
      "grad_norm": 0.4748593270778656,
      "learning_rate": 1.171421688823785e-06,
      "loss": 0.4129,
      "step": 54991
    },
    {
      "epoch": 1.6893066691241976,
      "grad_norm": 0.41933581233024597,
      "learning_rate": 1.171194732600577e-06,
      "loss": 0.4572,
      "step": 54992
    },
    {
      "epoch": 1.6893373882591467,
      "grad_norm": 0.38708603382110596,
      "learning_rate": 1.1709677969976553e-06,
      "loss": 0.4328,
      "step": 54993
    },
    {
      "epoch": 1.6893681073940958,
      "grad_norm": 0.4960406720638275,
      "learning_rate": 1.1707408820155597e-06,
      "loss": 0.4482,
      "step": 54994
    },
    {
      "epoch": 1.689398826529045,
      "grad_norm": 0.42772606015205383,
      "learning_rate": 1.1705139876548133e-06,
      "loss": 0.4558,
      "step": 54995
    },
    {
      "epoch": 1.689429545663994,
      "grad_norm": 0.440901517868042,
      "learning_rate": 1.1702871139159499e-06,
      "loss": 0.4694,
      "step": 54996
    },
    {
      "epoch": 1.6894602647989432,
      "grad_norm": 0.4492206573486328,
      "learning_rate": 1.170060260799496e-06,
      "loss": 0.5196,
      "step": 54997
    },
    {
      "epoch": 1.6894909839338923,
      "grad_norm": 0.4431178867816925,
      "learning_rate": 1.1698334283059808e-06,
      "loss": 0.368,
      "step": 54998
    },
    {
      "epoch": 1.6895217030688414,
      "grad_norm": 0.4257490932941437,
      "learning_rate": 1.16960661643594e-06,
      "loss": 0.4023,
      "step": 54999
    },
    {
      "epoch": 1.6895524222037908,
      "grad_norm": 0.43045946955680847,
      "learning_rate": 1.169379825189898e-06,
      "loss": 0.4486,
      "step": 55000
    },
    {
      "epoch": 1.6895831413387399,
      "grad_norm": 0.42988261580467224,
      "learning_rate": 1.1691530545683882e-06,
      "loss": 0.4904,
      "step": 55001
    },
    {
      "epoch": 1.6896138604736892,
      "grad_norm": 0.4356972873210907,
      "learning_rate": 1.1689263045719358e-06,
      "loss": 0.4948,
      "step": 55002
    },
    {
      "epoch": 1.6896445796086383,
      "grad_norm": 0.4740530550479889,
      "learning_rate": 1.1686995752010733e-06,
      "loss": 0.503,
      "step": 55003
    },
    {
      "epoch": 1.6896752987435875,
      "grad_norm": 0.4394429326057434,
      "learning_rate": 1.1684728664563294e-06,
      "loss": 0.5701,
      "step": 55004
    },
    {
      "epoch": 1.6897060178785366,
      "grad_norm": 0.44288942217826843,
      "learning_rate": 1.168246178338236e-06,
      "loss": 0.5136,
      "step": 55005
    },
    {
      "epoch": 1.6897367370134857,
      "grad_norm": 0.42169272899627686,
      "learning_rate": 1.1680195108473192e-06,
      "loss": 0.4775,
      "step": 55006
    },
    {
      "epoch": 1.6897674561484348,
      "grad_norm": 0.5288980603218079,
      "learning_rate": 1.1677928639841086e-06,
      "loss": 0.5105,
      "step": 55007
    },
    {
      "epoch": 1.689798175283384,
      "grad_norm": 0.4485035836696625,
      "learning_rate": 1.1675662377491349e-06,
      "loss": 0.4658,
      "step": 55008
    },
    {
      "epoch": 1.689828894418333,
      "grad_norm": 0.43331143260002136,
      "learning_rate": 1.1673396321429288e-06,
      "loss": 0.4546,
      "step": 55009
    },
    {
      "epoch": 1.6898596135532822,
      "grad_norm": 0.44607144594192505,
      "learning_rate": 1.1671130471660164e-06,
      "loss": 0.466,
      "step": 55010
    },
    {
      "epoch": 1.6898903326882315,
      "grad_norm": 0.47638100385665894,
      "learning_rate": 1.1668864828189285e-06,
      "loss": 0.49,
      "step": 55011
    },
    {
      "epoch": 1.6899210518231806,
      "grad_norm": 0.4423987567424774,
      "learning_rate": 1.1666599391021937e-06,
      "loss": 0.4531,
      "step": 55012
    },
    {
      "epoch": 1.68995177095813,
      "grad_norm": 0.48402702808380127,
      "learning_rate": 1.1664334160163438e-06,
      "loss": 0.5227,
      "step": 55013
    },
    {
      "epoch": 1.689982490093079,
      "grad_norm": 0.4940643012523651,
      "learning_rate": 1.1662069135619025e-06,
      "loss": 0.4569,
      "step": 55014
    },
    {
      "epoch": 1.6900132092280282,
      "grad_norm": 0.5354958772659302,
      "learning_rate": 1.165980431739403e-06,
      "loss": 0.4814,
      "step": 55015
    },
    {
      "epoch": 1.6900439283629773,
      "grad_norm": 0.45602279901504517,
      "learning_rate": 1.1657539705493725e-06,
      "loss": 0.5056,
      "step": 55016
    },
    {
      "epoch": 1.6900746474979265,
      "grad_norm": 0.500564455986023,
      "learning_rate": 1.1655275299923418e-06,
      "loss": 0.4489,
      "step": 55017
    },
    {
      "epoch": 1.6901053666328756,
      "grad_norm": 0.4299834668636322,
      "learning_rate": 1.1653011100688393e-06,
      "loss": 0.4894,
      "step": 55018
    },
    {
      "epoch": 1.6901360857678247,
      "grad_norm": 0.41125062108039856,
      "learning_rate": 1.1650747107793915e-06,
      "loss": 0.5024,
      "step": 55019
    },
    {
      "epoch": 1.6901668049027738,
      "grad_norm": 0.41569048166275024,
      "learning_rate": 1.1648483321245285e-06,
      "loss": 0.4665,
      "step": 55020
    },
    {
      "epoch": 1.690197524037723,
      "grad_norm": 0.47440922260284424,
      "learning_rate": 1.1646219741047804e-06,
      "loss": 0.4527,
      "step": 55021
    },
    {
      "epoch": 1.6902282431726723,
      "grad_norm": 0.4082234799861908,
      "learning_rate": 1.1643956367206754e-06,
      "loss": 0.4205,
      "step": 55022
    },
    {
      "epoch": 1.6902589623076214,
      "grad_norm": 0.43618088960647583,
      "learning_rate": 1.16416931997274e-06,
      "loss": 0.4485,
      "step": 55023
    },
    {
      "epoch": 1.6902896814425705,
      "grad_norm": 0.41426631808280945,
      "learning_rate": 1.1639430238615057e-06,
      "loss": 0.4337,
      "step": 55024
    },
    {
      "epoch": 1.6903204005775199,
      "grad_norm": 0.4133990705013275,
      "learning_rate": 1.1637167483874968e-06,
      "loss": 0.461,
      "step": 55025
    },
    {
      "epoch": 1.690351119712469,
      "grad_norm": 0.4612308442592621,
      "learning_rate": 1.163490493551247e-06,
      "loss": 0.4431,
      "step": 55026
    },
    {
      "epoch": 1.690381838847418,
      "grad_norm": 0.41060370206832886,
      "learning_rate": 1.1632642593532818e-06,
      "loss": 0.4224,
      "step": 55027
    },
    {
      "epoch": 1.6904125579823672,
      "grad_norm": 0.4465939998626709,
      "learning_rate": 1.1630380457941315e-06,
      "loss": 0.5534,
      "step": 55028
    },
    {
      "epoch": 1.6904432771173163,
      "grad_norm": 0.43818363547325134,
      "learning_rate": 1.1628118528743181e-06,
      "loss": 0.4698,
      "step": 55029
    },
    {
      "epoch": 1.6904739962522655,
      "grad_norm": 0.4452900290489197,
      "learning_rate": 1.1625856805943802e-06,
      "loss": 0.4631,
      "step": 55030
    },
    {
      "epoch": 1.6905047153872146,
      "grad_norm": 0.45252174139022827,
      "learning_rate": 1.1623595289548372e-06,
      "loss": 0.4147,
      "step": 55031
    },
    {
      "epoch": 1.6905354345221637,
      "grad_norm": 0.44245731830596924,
      "learning_rate": 1.1621333979562244e-06,
      "loss": 0.4587,
      "step": 55032
    },
    {
      "epoch": 1.690566153657113,
      "grad_norm": 0.40281006693840027,
      "learning_rate": 1.1619072875990633e-06,
      "loss": 0.4189,
      "step": 55033
    },
    {
      "epoch": 1.6905968727920622,
      "grad_norm": 0.4496292173862457,
      "learning_rate": 1.1616811978838826e-06,
      "loss": 0.3847,
      "step": 55034
    },
    {
      "epoch": 1.6906275919270113,
      "grad_norm": 0.4423280358314514,
      "learning_rate": 1.1614551288112175e-06,
      "loss": 0.5319,
      "step": 55035
    },
    {
      "epoch": 1.6906583110619606,
      "grad_norm": 0.41876935958862305,
      "learning_rate": 1.1612290803815884e-06,
      "loss": 0.4517,
      "step": 55036
    },
    {
      "epoch": 1.6906890301969097,
      "grad_norm": 0.4273255169391632,
      "learning_rate": 1.1610030525955286e-06,
      "loss": 0.4323,
      "step": 55037
    },
    {
      "epoch": 1.6907197493318589,
      "grad_norm": 0.4500408172607422,
      "learning_rate": 1.1607770454535616e-06,
      "loss": 0.4162,
      "step": 55038
    },
    {
      "epoch": 1.690750468466808,
      "grad_norm": 0.45453718304634094,
      "learning_rate": 1.1605510589562175e-06,
      "loss": 0.4481,
      "step": 55039
    },
    {
      "epoch": 1.690781187601757,
      "grad_norm": 0.42846694588661194,
      "learning_rate": 1.1603250931040233e-06,
      "loss": 0.4229,
      "step": 55040
    },
    {
      "epoch": 1.6908119067367062,
      "grad_norm": 0.4330717623233795,
      "learning_rate": 1.1600991478975088e-06,
      "loss": 0.4335,
      "step": 55041
    },
    {
      "epoch": 1.6908426258716553,
      "grad_norm": 0.38230404257774353,
      "learning_rate": 1.159873223337199e-06,
      "loss": 0.42,
      "step": 55042
    },
    {
      "epoch": 1.6908733450066045,
      "grad_norm": 0.45920825004577637,
      "learning_rate": 1.1596473194236214e-06,
      "loss": 0.4297,
      "step": 55043
    },
    {
      "epoch": 1.6909040641415538,
      "grad_norm": 0.4382125437259674,
      "learning_rate": 1.1594214361573054e-06,
      "loss": 0.4884,
      "step": 55044
    },
    {
      "epoch": 1.690934783276503,
      "grad_norm": 0.43176010251045227,
      "learning_rate": 1.1591955735387805e-06,
      "loss": 0.5138,
      "step": 55045
    },
    {
      "epoch": 1.690965502411452,
      "grad_norm": 0.43021583557128906,
      "learning_rate": 1.15896973156857e-06,
      "loss": 0.4517,
      "step": 55046
    },
    {
      "epoch": 1.6909962215464014,
      "grad_norm": 0.44831645488739014,
      "learning_rate": 1.158743910247202e-06,
      "loss": 0.5177,
      "step": 55047
    },
    {
      "epoch": 1.6910269406813505,
      "grad_norm": 0.4932868480682373,
      "learning_rate": 1.1585181095752063e-06,
      "loss": 0.4991,
      "step": 55048
    },
    {
      "epoch": 1.6910576598162996,
      "grad_norm": 0.4918290674686432,
      "learning_rate": 1.1582923295531102e-06,
      "loss": 0.4974,
      "step": 55049
    },
    {
      "epoch": 1.6910883789512487,
      "grad_norm": 0.4918003976345062,
      "learning_rate": 1.1580665701814387e-06,
      "loss": 0.4794,
      "step": 55050
    },
    {
      "epoch": 1.6911190980861979,
      "grad_norm": 0.44978973269462585,
      "learning_rate": 1.1578408314607192e-06,
      "loss": 0.4764,
      "step": 55051
    },
    {
      "epoch": 1.691149817221147,
      "grad_norm": 0.4261055588722229,
      "learning_rate": 1.1576151133914804e-06,
      "loss": 0.5293,
      "step": 55052
    },
    {
      "epoch": 1.691180536356096,
      "grad_norm": 0.4239637851715088,
      "learning_rate": 1.1573894159742494e-06,
      "loss": 0.4979,
      "step": 55053
    },
    {
      "epoch": 1.6912112554910452,
      "grad_norm": 0.43437549471855164,
      "learning_rate": 1.1571637392095547e-06,
      "loss": 0.4197,
      "step": 55054
    },
    {
      "epoch": 1.6912419746259946,
      "grad_norm": 0.41601744294166565,
      "learning_rate": 1.1569380830979194e-06,
      "loss": 0.4643,
      "step": 55055
    },
    {
      "epoch": 1.6912726937609437,
      "grad_norm": 0.3997546434402466,
      "learning_rate": 1.1567124476398729e-06,
      "loss": 0.3368,
      "step": 55056
    },
    {
      "epoch": 1.6913034128958928,
      "grad_norm": 0.4752595126628876,
      "learning_rate": 1.1564868328359425e-06,
      "loss": 0.4377,
      "step": 55057
    },
    {
      "epoch": 1.6913341320308422,
      "grad_norm": 0.5971787571907043,
      "learning_rate": 1.1562612386866568e-06,
      "loss": 0.4945,
      "step": 55058
    },
    {
      "epoch": 1.6913648511657913,
      "grad_norm": 0.4121684432029724,
      "learning_rate": 1.1560356651925375e-06,
      "loss": 0.5135,
      "step": 55059
    },
    {
      "epoch": 1.6913955703007404,
      "grad_norm": 0.4177251160144806,
      "learning_rate": 1.1558101123541176e-06,
      "loss": 0.445,
      "step": 55060
    },
    {
      "epoch": 1.6914262894356895,
      "grad_norm": 0.421365886926651,
      "learning_rate": 1.1555845801719167e-06,
      "loss": 0.4403,
      "step": 55061
    },
    {
      "epoch": 1.6914570085706386,
      "grad_norm": 0.4308249354362488,
      "learning_rate": 1.1553590686464699e-06,
      "loss": 0.43,
      "step": 55062
    },
    {
      "epoch": 1.6914877277055878,
      "grad_norm": 0.42067477107048035,
      "learning_rate": 1.1551335777782968e-06,
      "loss": 0.5665,
      "step": 55063
    },
    {
      "epoch": 1.6915184468405369,
      "grad_norm": 0.43045711517333984,
      "learning_rate": 1.1549081075679303e-06,
      "loss": 0.4987,
      "step": 55064
    },
    {
      "epoch": 1.691549165975486,
      "grad_norm": 0.4130636751651764,
      "learning_rate": 1.1546826580158909e-06,
      "loss": 0.4432,
      "step": 55065
    },
    {
      "epoch": 1.6915798851104353,
      "grad_norm": 0.44085073471069336,
      "learning_rate": 1.1544572291227074e-06,
      "loss": 0.4595,
      "step": 55066
    },
    {
      "epoch": 1.6916106042453845,
      "grad_norm": 0.4256875514984131,
      "learning_rate": 1.154231820888908e-06,
      "loss": 0.4114,
      "step": 55067
    },
    {
      "epoch": 1.6916413233803336,
      "grad_norm": 0.4045906960964203,
      "learning_rate": 1.1540064333150192e-06,
      "loss": 0.3811,
      "step": 55068
    },
    {
      "epoch": 1.691672042515283,
      "grad_norm": 0.420171856880188,
      "learning_rate": 1.1537810664015637e-06,
      "loss": 0.4,
      "step": 55069
    },
    {
      "epoch": 1.691702761650232,
      "grad_norm": 0.42484259605407715,
      "learning_rate": 1.1535557201490689e-06,
      "loss": 0.4397,
      "step": 55070
    },
    {
      "epoch": 1.6917334807851812,
      "grad_norm": 0.4421426057815552,
      "learning_rate": 1.1533303945580666e-06,
      "loss": 0.4654,
      "step": 55071
    },
    {
      "epoch": 1.6917641999201303,
      "grad_norm": 0.4130498468875885,
      "learning_rate": 1.1531050896290773e-06,
      "loss": 0.5024,
      "step": 55072
    },
    {
      "epoch": 1.6917949190550794,
      "grad_norm": 0.5241612195968628,
      "learning_rate": 1.15287980536263e-06,
      "loss": 0.4878,
      "step": 55073
    },
    {
      "epoch": 1.6918256381900285,
      "grad_norm": 0.40812766551971436,
      "learning_rate": 1.1526545417592483e-06,
      "loss": 0.4835,
      "step": 55074
    },
    {
      "epoch": 1.6918563573249776,
      "grad_norm": 0.46172261238098145,
      "learning_rate": 1.1524292988194596e-06,
      "loss": 0.4981,
      "step": 55075
    },
    {
      "epoch": 1.6918870764599268,
      "grad_norm": 0.4431673586368561,
      "learning_rate": 1.1522040765437915e-06,
      "loss": 0.4857,
      "step": 55076
    },
    {
      "epoch": 1.691917795594876,
      "grad_norm": 0.44245949387550354,
      "learning_rate": 1.1519788749327687e-06,
      "loss": 0.4365,
      "step": 55077
    },
    {
      "epoch": 1.6919485147298252,
      "grad_norm": 0.48293524980545044,
      "learning_rate": 1.1517536939869168e-06,
      "loss": 0.4985,
      "step": 55078
    },
    {
      "epoch": 1.6919792338647743,
      "grad_norm": 0.4449375569820404,
      "learning_rate": 1.1515285337067604e-06,
      "loss": 0.4756,
      "step": 55079
    },
    {
      "epoch": 1.6920099529997237,
      "grad_norm": 0.4143562912940979,
      "learning_rate": 1.1513033940928286e-06,
      "loss": 0.4371,
      "step": 55080
    },
    {
      "epoch": 1.6920406721346728,
      "grad_norm": 0.4291096329689026,
      "learning_rate": 1.1510782751456473e-06,
      "loss": 0.4833,
      "step": 55081
    },
    {
      "epoch": 1.692071391269622,
      "grad_norm": 0.49145030975341797,
      "learning_rate": 1.1508531768657382e-06,
      "loss": 0.5032,
      "step": 55082
    },
    {
      "epoch": 1.692102110404571,
      "grad_norm": 0.43589359521865845,
      "learning_rate": 1.15062809925363e-06,
      "loss": 0.4021,
      "step": 55083
    },
    {
      "epoch": 1.6921328295395202,
      "grad_norm": 0.43390822410583496,
      "learning_rate": 1.1504030423098479e-06,
      "loss": 0.4285,
      "step": 55084
    },
    {
      "epoch": 1.6921635486744693,
      "grad_norm": 0.4198523759841919,
      "learning_rate": 1.1501780060349198e-06,
      "loss": 0.4727,
      "step": 55085
    },
    {
      "epoch": 1.6921942678094184,
      "grad_norm": 0.4008050858974457,
      "learning_rate": 1.149952990429367e-06,
      "loss": 0.4059,
      "step": 55086
    },
    {
      "epoch": 1.6922249869443675,
      "grad_norm": 0.49869969487190247,
      "learning_rate": 1.149727995493718e-06,
      "loss": 0.3751,
      "step": 55087
    },
    {
      "epoch": 1.6922557060793169,
      "grad_norm": 0.4577197730541229,
      "learning_rate": 1.1495030212284941e-06,
      "loss": 0.4319,
      "step": 55088
    },
    {
      "epoch": 1.692286425214266,
      "grad_norm": 0.4617237448692322,
      "learning_rate": 1.1492780676342264e-06,
      "loss": 0.4696,
      "step": 55089
    },
    {
      "epoch": 1.692317144349215,
      "grad_norm": 0.4065348505973816,
      "learning_rate": 1.1490531347114397e-06,
      "loss": 0.46,
      "step": 55090
    },
    {
      "epoch": 1.6923478634841644,
      "grad_norm": 0.44895869493484497,
      "learning_rate": 1.148828222460655e-06,
      "loss": 0.4859,
      "step": 55091
    },
    {
      "epoch": 1.6923785826191136,
      "grad_norm": 0.4145399332046509,
      "learning_rate": 1.1486033308824007e-06,
      "loss": 0.5011,
      "step": 55092
    },
    {
      "epoch": 1.6924093017540627,
      "grad_norm": 0.41203072667121887,
      "learning_rate": 1.1483784599772018e-06,
      "loss": 0.4385,
      "step": 55093
    },
    {
      "epoch": 1.6924400208890118,
      "grad_norm": 0.41494059562683105,
      "learning_rate": 1.1481536097455847e-06,
      "loss": 0.4854,
      "step": 55094
    },
    {
      "epoch": 1.692470740023961,
      "grad_norm": 0.454873651266098,
      "learning_rate": 1.1479287801880712e-06,
      "loss": 0.4249,
      "step": 55095
    },
    {
      "epoch": 1.69250145915891,
      "grad_norm": 0.4518081247806549,
      "learning_rate": 1.1477039713051897e-06,
      "loss": 0.4535,
      "step": 55096
    },
    {
      "epoch": 1.6925321782938592,
      "grad_norm": 0.4873674809932709,
      "learning_rate": 1.1474791830974596e-06,
      "loss": 0.4434,
      "step": 55097
    },
    {
      "epoch": 1.6925628974288083,
      "grad_norm": 0.44544997811317444,
      "learning_rate": 1.1472544155654154e-06,
      "loss": 0.4357,
      "step": 55098
    },
    {
      "epoch": 1.6925936165637576,
      "grad_norm": 0.4727718234062195,
      "learning_rate": 1.147029668709574e-06,
      "loss": 0.4526,
      "step": 55099
    },
    {
      "epoch": 1.6926243356987067,
      "grad_norm": 0.3862273097038269,
      "learning_rate": 1.146804942530465e-06,
      "loss": 0.4827,
      "step": 55100
    },
    {
      "epoch": 1.6926550548336559,
      "grad_norm": 0.5128543972969055,
      "learning_rate": 1.1465802370286093e-06,
      "loss": 0.4265,
      "step": 55101
    },
    {
      "epoch": 1.6926857739686052,
      "grad_norm": 0.5547906756401062,
      "learning_rate": 1.1463555522045344e-06,
      "loss": 0.5078,
      "step": 55102
    },
    {
      "epoch": 1.6927164931035543,
      "grad_norm": 0.46219033002853394,
      "learning_rate": 1.1461308880587641e-06,
      "loss": 0.4999,
      "step": 55103
    },
    {
      "epoch": 1.6927472122385034,
      "grad_norm": 0.44242164492607117,
      "learning_rate": 1.1459062445918256e-06,
      "loss": 0.4585,
      "step": 55104
    },
    {
      "epoch": 1.6927779313734526,
      "grad_norm": 0.41874024271965027,
      "learning_rate": 1.1456816218042388e-06,
      "loss": 0.4596,
      "step": 55105
    },
    {
      "epoch": 1.6928086505084017,
      "grad_norm": 0.41895434260368347,
      "learning_rate": 1.145457019696532e-06,
      "loss": 0.4893,
      "step": 55106
    },
    {
      "epoch": 1.6928393696433508,
      "grad_norm": 0.42676180601119995,
      "learning_rate": 1.1452324382692281e-06,
      "loss": 0.516,
      "step": 55107
    },
    {
      "epoch": 1.6928700887783,
      "grad_norm": 0.4033330976963043,
      "learning_rate": 1.1450078775228524e-06,
      "loss": 0.429,
      "step": 55108
    },
    {
      "epoch": 1.692900807913249,
      "grad_norm": 0.43658408522605896,
      "learning_rate": 1.1447833374579308e-06,
      "loss": 0.4544,
      "step": 55109
    },
    {
      "epoch": 1.6929315270481982,
      "grad_norm": 0.5001917481422424,
      "learning_rate": 1.1445588180749846e-06,
      "loss": 0.5092,
      "step": 55110
    },
    {
      "epoch": 1.6929622461831475,
      "grad_norm": 0.4505741000175476,
      "learning_rate": 1.1443343193745394e-06,
      "loss": 0.5096,
      "step": 55111
    },
    {
      "epoch": 1.6929929653180966,
      "grad_norm": 0.4829042851924896,
      "learning_rate": 1.1441098413571205e-06,
      "loss": 0.4349,
      "step": 55112
    },
    {
      "epoch": 1.693023684453046,
      "grad_norm": 0.40293484926223755,
      "learning_rate": 1.1438853840232533e-06,
      "loss": 0.4419,
      "step": 55113
    },
    {
      "epoch": 1.693054403587995,
      "grad_norm": 0.4289185404777527,
      "learning_rate": 1.1436609473734584e-06,
      "loss": 0.4193,
      "step": 55114
    },
    {
      "epoch": 1.6930851227229442,
      "grad_norm": 0.46705037355422974,
      "learning_rate": 1.1434365314082608e-06,
      "loss": 0.4827,
      "step": 55115
    },
    {
      "epoch": 1.6931158418578933,
      "grad_norm": 0.4289432764053345,
      "learning_rate": 1.1432121361281867e-06,
      "loss": 0.4668,
      "step": 55116
    },
    {
      "epoch": 1.6931465609928424,
      "grad_norm": 0.4126743674278259,
      "learning_rate": 1.1429877615337615e-06,
      "loss": 0.4913,
      "step": 55117
    },
    {
      "epoch": 1.6931772801277916,
      "grad_norm": 0.3982242941856384,
      "learning_rate": 1.1427634076255046e-06,
      "loss": 0.4728,
      "step": 55118
    },
    {
      "epoch": 1.6932079992627407,
      "grad_norm": 0.4170316159725189,
      "learning_rate": 1.1425390744039421e-06,
      "loss": 0.4302,
      "step": 55119
    },
    {
      "epoch": 1.6932387183976898,
      "grad_norm": 0.46849483251571655,
      "learning_rate": 1.1423147618695985e-06,
      "loss": 0.4932,
      "step": 55120
    },
    {
      "epoch": 1.693269437532639,
      "grad_norm": 0.42425936460494995,
      "learning_rate": 1.1420904700229984e-06,
      "loss": 0.4655,
      "step": 55121
    },
    {
      "epoch": 1.6933001566675883,
      "grad_norm": 0.41907769441604614,
      "learning_rate": 1.141866198864664e-06,
      "loss": 0.4137,
      "step": 55122
    },
    {
      "epoch": 1.6933308758025374,
      "grad_norm": 0.4058026373386383,
      "learning_rate": 1.1416419483951213e-06,
      "loss": 0.5309,
      "step": 55123
    },
    {
      "epoch": 1.6933615949374867,
      "grad_norm": 0.4337049424648285,
      "learning_rate": 1.1414177186148878e-06,
      "loss": 0.4513,
      "step": 55124
    },
    {
      "epoch": 1.6933923140724358,
      "grad_norm": 0.4221295714378357,
      "learning_rate": 1.1411935095244953e-06,
      "loss": 0.4506,
      "step": 55125
    },
    {
      "epoch": 1.693423033207385,
      "grad_norm": 0.4563487768173218,
      "learning_rate": 1.1409693211244642e-06,
      "loss": 0.4814,
      "step": 55126
    },
    {
      "epoch": 1.693453752342334,
      "grad_norm": 0.43100935220718384,
      "learning_rate": 1.140745153415318e-06,
      "loss": 0.4409,
      "step": 55127
    },
    {
      "epoch": 1.6934844714772832,
      "grad_norm": 0.445592999458313,
      "learning_rate": 1.1405210063975802e-06,
      "loss": 0.4461,
      "step": 55128
    },
    {
      "epoch": 1.6935151906122323,
      "grad_norm": 0.4483312964439392,
      "learning_rate": 1.1402968800717717e-06,
      "loss": 0.4379,
      "step": 55129
    },
    {
      "epoch": 1.6935459097471814,
      "grad_norm": 0.3928736746311188,
      "learning_rate": 1.1400727744384222e-06,
      "loss": 0.4896,
      "step": 55130
    },
    {
      "epoch": 1.6935766288821306,
      "grad_norm": 0.40498873591423035,
      "learning_rate": 1.1398486894980499e-06,
      "loss": 0.4796,
      "step": 55131
    },
    {
      "epoch": 1.6936073480170797,
      "grad_norm": 0.45277196168899536,
      "learning_rate": 1.1396246252511812e-06,
      "loss": 0.4817,
      "step": 55132
    },
    {
      "epoch": 1.693638067152029,
      "grad_norm": 0.41489267349243164,
      "learning_rate": 1.1394005816983346e-06,
      "loss": 0.4515,
      "step": 55133
    },
    {
      "epoch": 1.6936687862869781,
      "grad_norm": 0.4618226885795593,
      "learning_rate": 1.1391765588400393e-06,
      "loss": 0.4501,
      "step": 55134
    },
    {
      "epoch": 1.6936995054219273,
      "grad_norm": 0.4791754484176636,
      "learning_rate": 1.1389525566768156e-06,
      "loss": 0.541,
      "step": 55135
    },
    {
      "epoch": 1.6937302245568766,
      "grad_norm": 0.45349815487861633,
      "learning_rate": 1.1387285752091881e-06,
      "loss": 0.5008,
      "step": 55136
    },
    {
      "epoch": 1.6937609436918257,
      "grad_norm": 0.4084603190422058,
      "learning_rate": 1.1385046144376776e-06,
      "loss": 0.4766,
      "step": 55137
    },
    {
      "epoch": 1.6937916628267748,
      "grad_norm": 0.5047856569290161,
      "learning_rate": 1.1382806743628083e-06,
      "loss": 0.5413,
      "step": 55138
    },
    {
      "epoch": 1.693822381961724,
      "grad_norm": 0.4261816442012787,
      "learning_rate": 1.138056754985103e-06,
      "loss": 0.4366,
      "step": 55139
    },
    {
      "epoch": 1.693853101096673,
      "grad_norm": 0.42915305495262146,
      "learning_rate": 1.1378328563050878e-06,
      "loss": 0.4238,
      "step": 55140
    },
    {
      "epoch": 1.6938838202316222,
      "grad_norm": 0.4130978286266327,
      "learning_rate": 1.1376089783232802e-06,
      "loss": 0.5049,
      "step": 55141
    },
    {
      "epoch": 1.6939145393665713,
      "grad_norm": 0.467730849981308,
      "learning_rate": 1.1373851210402053e-06,
      "loss": 0.4283,
      "step": 55142
    },
    {
      "epoch": 1.6939452585015204,
      "grad_norm": 0.496191143989563,
      "learning_rate": 1.1371612844563873e-06,
      "loss": 0.4868,
      "step": 55143
    },
    {
      "epoch": 1.6939759776364698,
      "grad_norm": 0.43312960863113403,
      "learning_rate": 1.1369374685723478e-06,
      "loss": 0.4625,
      "step": 55144
    },
    {
      "epoch": 1.694006696771419,
      "grad_norm": 0.4412955641746521,
      "learning_rate": 1.136713673388612e-06,
      "loss": 0.4616,
      "step": 55145
    },
    {
      "epoch": 1.694037415906368,
      "grad_norm": 0.4669230282306671,
      "learning_rate": 1.1364898989056983e-06,
      "loss": 0.4438,
      "step": 55146
    },
    {
      "epoch": 1.6940681350413174,
      "grad_norm": 0.4103972911834717,
      "learning_rate": 1.1362661451241307e-06,
      "loss": 0.4241,
      "step": 55147
    },
    {
      "epoch": 1.6940988541762665,
      "grad_norm": 0.44717803597450256,
      "learning_rate": 1.1360424120444336e-06,
      "loss": 0.42,
      "step": 55148
    },
    {
      "epoch": 1.6941295733112156,
      "grad_norm": 0.4291650652885437,
      "learning_rate": 1.1358186996671305e-06,
      "loss": 0.4687,
      "step": 55149
    },
    {
      "epoch": 1.6941602924461647,
      "grad_norm": 0.46681660413742065,
      "learning_rate": 1.135595007992739e-06,
      "loss": 0.4595,
      "step": 55150
    },
    {
      "epoch": 1.6941910115811138,
      "grad_norm": 0.47557157278060913,
      "learning_rate": 1.1353713370217855e-06,
      "loss": 0.4549,
      "step": 55151
    },
    {
      "epoch": 1.694221730716063,
      "grad_norm": 0.4613480865955353,
      "learning_rate": 1.1351476867547906e-06,
      "loss": 0.5006,
      "step": 55152
    },
    {
      "epoch": 1.694252449851012,
      "grad_norm": 0.43345361948013306,
      "learning_rate": 1.1349240571922803e-06,
      "loss": 0.4825,
      "step": 55153
    },
    {
      "epoch": 1.6942831689859612,
      "grad_norm": 0.4214954972267151,
      "learning_rate": 1.1347004483347712e-06,
      "loss": 0.4232,
      "step": 55154
    },
    {
      "epoch": 1.6943138881209105,
      "grad_norm": 0.9417850971221924,
      "learning_rate": 1.1344768601827883e-06,
      "loss": 0.5149,
      "step": 55155
    },
    {
      "epoch": 1.6943446072558597,
      "grad_norm": 0.40712299942970276,
      "learning_rate": 1.1342532927368544e-06,
      "loss": 0.4424,
      "step": 55156
    },
    {
      "epoch": 1.6943753263908088,
      "grad_norm": 0.42192694544792175,
      "learning_rate": 1.1340297459974925e-06,
      "loss": 0.4156,
      "step": 55157
    },
    {
      "epoch": 1.6944060455257581,
      "grad_norm": 0.41558021306991577,
      "learning_rate": 1.1338062199652212e-06,
      "loss": 0.5305,
      "step": 55158
    },
    {
      "epoch": 1.6944367646607073,
      "grad_norm": 0.4352562129497528,
      "learning_rate": 1.1335827146405676e-06,
      "loss": 0.4809,
      "step": 55159
    },
    {
      "epoch": 1.6944674837956564,
      "grad_norm": 0.48668596148490906,
      "learning_rate": 1.133359230024046e-06,
      "loss": 0.398,
      "step": 55160
    },
    {
      "epoch": 1.6944982029306055,
      "grad_norm": 0.4389582574367523,
      "learning_rate": 1.1331357661161858e-06,
      "loss": 0.4668,
      "step": 55161
    },
    {
      "epoch": 1.6945289220655546,
      "grad_norm": 0.45717746019363403,
      "learning_rate": 1.1329123229175076e-06,
      "loss": 0.4699,
      "step": 55162
    },
    {
      "epoch": 1.6945596412005037,
      "grad_norm": 0.4252076745033264,
      "learning_rate": 1.1326889004285302e-06,
      "loss": 0.4297,
      "step": 55163
    },
    {
      "epoch": 1.6945903603354528,
      "grad_norm": 0.4192855954170227,
      "learning_rate": 1.1324654986497784e-06,
      "loss": 0.4729,
      "step": 55164
    },
    {
      "epoch": 1.694621079470402,
      "grad_norm": 0.43500006198883057,
      "learning_rate": 1.13224211758177e-06,
      "loss": 0.4414,
      "step": 55165
    },
    {
      "epoch": 1.6946517986053513,
      "grad_norm": 0.3914209008216858,
      "learning_rate": 1.132018757225033e-06,
      "loss": 0.4454,
      "step": 55166
    },
    {
      "epoch": 1.6946825177403004,
      "grad_norm": 0.43355587124824524,
      "learning_rate": 1.1317954175800839e-06,
      "loss": 0.4718,
      "step": 55167
    },
    {
      "epoch": 1.6947132368752496,
      "grad_norm": 0.43943044543266296,
      "learning_rate": 1.1315720986474465e-06,
      "loss": 0.5116,
      "step": 55168
    },
    {
      "epoch": 1.694743956010199,
      "grad_norm": 0.46246346831321716,
      "learning_rate": 1.1313488004276418e-06,
      "loss": 0.4641,
      "step": 55169
    },
    {
      "epoch": 1.694774675145148,
      "grad_norm": 0.4061363935470581,
      "learning_rate": 1.1311255229211904e-06,
      "loss": 0.5172,
      "step": 55170
    },
    {
      "epoch": 1.6948053942800971,
      "grad_norm": 0.4504222273826599,
      "learning_rate": 1.130902266128614e-06,
      "loss": 0.4966,
      "step": 55171
    },
    {
      "epoch": 1.6948361134150463,
      "grad_norm": 0.47687456011772156,
      "learning_rate": 1.1306790300504378e-06,
      "loss": 0.4686,
      "step": 55172
    },
    {
      "epoch": 1.6948668325499954,
      "grad_norm": 0.4141664206981659,
      "learning_rate": 1.130455814687178e-06,
      "loss": 0.4917,
      "step": 55173
    },
    {
      "epoch": 1.6948975516849445,
      "grad_norm": 0.5047475099563599,
      "learning_rate": 1.1302326200393575e-06,
      "loss": 0.441,
      "step": 55174
    },
    {
      "epoch": 1.6949282708198936,
      "grad_norm": 0.45121416449546814,
      "learning_rate": 1.1300094461074994e-06,
      "loss": 0.4535,
      "step": 55175
    },
    {
      "epoch": 1.6949589899548427,
      "grad_norm": 0.44297143816947937,
      "learning_rate": 1.1297862928921243e-06,
      "loss": 0.4629,
      "step": 55176
    },
    {
      "epoch": 1.694989709089792,
      "grad_norm": 0.4308377504348755,
      "learning_rate": 1.1295631603937519e-06,
      "loss": 0.4735,
      "step": 55177
    },
    {
      "epoch": 1.6950204282247412,
      "grad_norm": 0.46900591254234314,
      "learning_rate": 1.1293400486129037e-06,
      "loss": 0.4769,
      "step": 55178
    },
    {
      "epoch": 1.6950511473596903,
      "grad_norm": 0.4308951795101166,
      "learning_rate": 1.1291169575501014e-06,
      "loss": 0.4654,
      "step": 55179
    },
    {
      "epoch": 1.6950818664946397,
      "grad_norm": 0.5164135098457336,
      "learning_rate": 1.1288938872058663e-06,
      "loss": 0.4613,
      "step": 55180
    },
    {
      "epoch": 1.6951125856295888,
      "grad_norm": 0.4505799412727356,
      "learning_rate": 1.128670837580721e-06,
      "loss": 0.439,
      "step": 55181
    },
    {
      "epoch": 1.695143304764538,
      "grad_norm": 0.41855424642562866,
      "learning_rate": 1.1284478086751815e-06,
      "loss": 0.453,
      "step": 55182
    },
    {
      "epoch": 1.695174023899487,
      "grad_norm": 0.4210779070854187,
      "learning_rate": 1.1282248004897733e-06,
      "loss": 0.4898,
      "step": 55183
    },
    {
      "epoch": 1.6952047430344361,
      "grad_norm": 0.4833524227142334,
      "learning_rate": 1.1280018130250147e-06,
      "loss": 0.5104,
      "step": 55184
    },
    {
      "epoch": 1.6952354621693853,
      "grad_norm": 0.45207276940345764,
      "learning_rate": 1.1277788462814298e-06,
      "loss": 0.5378,
      "step": 55185
    },
    {
      "epoch": 1.6952661813043344,
      "grad_norm": 0.42848220467567444,
      "learning_rate": 1.1275559002595348e-06,
      "loss": 0.4146,
      "step": 55186
    },
    {
      "epoch": 1.6952969004392835,
      "grad_norm": 0.5552546381950378,
      "learning_rate": 1.1273329749598528e-06,
      "loss": 0.5236,
      "step": 55187
    },
    {
      "epoch": 1.6953276195742328,
      "grad_norm": 0.4727720618247986,
      "learning_rate": 1.127110070382904e-06,
      "loss": 0.4563,
      "step": 55188
    },
    {
      "epoch": 1.695358338709182,
      "grad_norm": 0.42015671730041504,
      "learning_rate": 1.1268871865292118e-06,
      "loss": 0.4522,
      "step": 55189
    },
    {
      "epoch": 1.695389057844131,
      "grad_norm": 0.45167261362075806,
      "learning_rate": 1.1266643233992913e-06,
      "loss": 0.4455,
      "step": 55190
    },
    {
      "epoch": 1.6954197769790804,
      "grad_norm": 0.4256552755832672,
      "learning_rate": 1.1264414809936696e-06,
      "loss": 0.4985,
      "step": 55191
    },
    {
      "epoch": 1.6954504961140295,
      "grad_norm": 0.5057176351547241,
      "learning_rate": 1.1262186593128577e-06,
      "loss": 0.4745,
      "step": 55192
    },
    {
      "epoch": 1.6954812152489787,
      "grad_norm": 0.3921962082386017,
      "learning_rate": 1.125995858357387e-06,
      "loss": 0.4225,
      "step": 55193
    },
    {
      "epoch": 1.6955119343839278,
      "grad_norm": 0.4348759949207306,
      "learning_rate": 1.125773078127771e-06,
      "loss": 0.4341,
      "step": 55194
    },
    {
      "epoch": 1.695542653518877,
      "grad_norm": 0.4782788157463074,
      "learning_rate": 1.1255503186245331e-06,
      "loss": 0.4683,
      "step": 55195
    },
    {
      "epoch": 1.695573372653826,
      "grad_norm": 0.41669341921806335,
      "learning_rate": 1.1253275798481888e-06,
      "loss": 0.4627,
      "step": 55196
    },
    {
      "epoch": 1.6956040917887751,
      "grad_norm": 0.4769900143146515,
      "learning_rate": 1.1251048617992656e-06,
      "loss": 0.4881,
      "step": 55197
    },
    {
      "epoch": 1.6956348109237243,
      "grad_norm": 0.4252781867980957,
      "learning_rate": 1.124882164478277e-06,
      "loss": 0.4206,
      "step": 55198
    },
    {
      "epoch": 1.6956655300586736,
      "grad_norm": 0.45784106850624084,
      "learning_rate": 1.1246594878857465e-06,
      "loss": 0.4527,
      "step": 55199
    },
    {
      "epoch": 1.6956962491936227,
      "grad_norm": 0.4346517026424408,
      "learning_rate": 1.1244368320221954e-06,
      "loss": 0.3858,
      "step": 55200
    },
    {
      "epoch": 1.6957269683285718,
      "grad_norm": 0.45673468708992004,
      "learning_rate": 1.1242141968881382e-06,
      "loss": 0.457,
      "step": 55201
    },
    {
      "epoch": 1.6957576874635212,
      "grad_norm": 0.463962197303772,
      "learning_rate": 1.123991582484103e-06,
      "loss": 0.4647,
      "step": 55202
    },
    {
      "epoch": 1.6957884065984703,
      "grad_norm": 0.4087279438972473,
      "learning_rate": 1.123768988810603e-06,
      "loss": 0.4275,
      "step": 55203
    },
    {
      "epoch": 1.6958191257334194,
      "grad_norm": 0.437244713306427,
      "learning_rate": 1.123546415868162e-06,
      "loss": 0.5502,
      "step": 55204
    },
    {
      "epoch": 1.6958498448683685,
      "grad_norm": 0.4528012275695801,
      "learning_rate": 1.1233238636572963e-06,
      "loss": 0.5113,
      "step": 55205
    },
    {
      "epoch": 1.6958805640033177,
      "grad_norm": 0.4567136764526367,
      "learning_rate": 1.1231013321785277e-06,
      "loss": 0.4519,
      "step": 55206
    },
    {
      "epoch": 1.6959112831382668,
      "grad_norm": 0.4437412917613983,
      "learning_rate": 1.122878821432377e-06,
      "loss": 0.4675,
      "step": 55207
    },
    {
      "epoch": 1.695942002273216,
      "grad_norm": 0.434369295835495,
      "learning_rate": 1.1226563314193638e-06,
      "loss": 0.3796,
      "step": 55208
    },
    {
      "epoch": 1.695972721408165,
      "grad_norm": 0.42771410942077637,
      "learning_rate": 1.1224338621400044e-06,
      "loss": 0.4619,
      "step": 55209
    },
    {
      "epoch": 1.6960034405431144,
      "grad_norm": 0.4070896804332733,
      "learning_rate": 1.1222114135948215e-06,
      "loss": 0.3751,
      "step": 55210
    },
    {
      "epoch": 1.6960341596780635,
      "grad_norm": 1.3586523532867432,
      "learning_rate": 1.1219889857843336e-06,
      "loss": 0.3916,
      "step": 55211
    },
    {
      "epoch": 1.6960648788130126,
      "grad_norm": 0.4165809750556946,
      "learning_rate": 1.1217665787090626e-06,
      "loss": 0.5069,
      "step": 55212
    },
    {
      "epoch": 1.696095597947962,
      "grad_norm": 0.3897482454776764,
      "learning_rate": 1.1215441923695236e-06,
      "loss": 0.4725,
      "step": 55213
    },
    {
      "epoch": 1.696126317082911,
      "grad_norm": 0.4304896295070648,
      "learning_rate": 1.1213218267662384e-06,
      "loss": 0.5339,
      "step": 55214
    },
    {
      "epoch": 1.6961570362178602,
      "grad_norm": 0.49040287733078003,
      "learning_rate": 1.1210994818997257e-06,
      "loss": 0.4556,
      "step": 55215
    },
    {
      "epoch": 1.6961877553528093,
      "grad_norm": 0.3983980715274811,
      "learning_rate": 1.1208771577705058e-06,
      "loss": 0.4752,
      "step": 55216
    },
    {
      "epoch": 1.6962184744877584,
      "grad_norm": 0.44458964467048645,
      "learning_rate": 1.1206548543790985e-06,
      "loss": 0.4378,
      "step": 55217
    },
    {
      "epoch": 1.6962491936227075,
      "grad_norm": 0.4428819715976715,
      "learning_rate": 1.1204325717260212e-06,
      "loss": 0.544,
      "step": 55218
    },
    {
      "epoch": 1.6962799127576567,
      "grad_norm": 0.469555526971817,
      "learning_rate": 1.1202103098117923e-06,
      "loss": 0.4471,
      "step": 55219
    },
    {
      "epoch": 1.6963106318926058,
      "grad_norm": 0.4778134822845459,
      "learning_rate": 1.1199880686369336e-06,
      "loss": 0.5155,
      "step": 55220
    },
    {
      "epoch": 1.696341351027555,
      "grad_norm": 0.4573771059513092,
      "learning_rate": 1.1197658482019647e-06,
      "loss": 0.4533,
      "step": 55221
    },
    {
      "epoch": 1.6963720701625042,
      "grad_norm": 0.5074125528335571,
      "learning_rate": 1.1195436485074007e-06,
      "loss": 0.415,
      "step": 55222
    },
    {
      "epoch": 1.6964027892974534,
      "grad_norm": 0.4413853585720062,
      "learning_rate": 1.1193214695537625e-06,
      "loss": 0.4625,
      "step": 55223
    },
    {
      "epoch": 1.6964335084324027,
      "grad_norm": 0.47114065289497375,
      "learning_rate": 1.1190993113415694e-06,
      "loss": 0.3851,
      "step": 55224
    },
    {
      "epoch": 1.6964642275673518,
      "grad_norm": 0.44442540407180786,
      "learning_rate": 1.1188771738713422e-06,
      "loss": 0.5725,
      "step": 55225
    },
    {
      "epoch": 1.696494946702301,
      "grad_norm": 0.42055922746658325,
      "learning_rate": 1.118655057143595e-06,
      "loss": 0.4529,
      "step": 55226
    },
    {
      "epoch": 1.69652566583725,
      "grad_norm": 0.4527277648448944,
      "learning_rate": 1.118432961158852e-06,
      "loss": 0.3662,
      "step": 55227
    },
    {
      "epoch": 1.6965563849721992,
      "grad_norm": 0.45120498538017273,
      "learning_rate": 1.1182108859176255e-06,
      "loss": 0.4522,
      "step": 55228
    },
    {
      "epoch": 1.6965871041071483,
      "grad_norm": 0.4475536048412323,
      "learning_rate": 1.1179888314204402e-06,
      "loss": 0.4245,
      "step": 55229
    },
    {
      "epoch": 1.6966178232420974,
      "grad_norm": 0.45250773429870605,
      "learning_rate": 1.1177667976678119e-06,
      "loss": 0.4214,
      "step": 55230
    },
    {
      "epoch": 1.6966485423770465,
      "grad_norm": 0.47580018639564514,
      "learning_rate": 1.1175447846602604e-06,
      "loss": 0.4434,
      "step": 55231
    },
    {
      "epoch": 1.6966792615119957,
      "grad_norm": 0.4781111180782318,
      "learning_rate": 1.1173227923983022e-06,
      "loss": 0.4247,
      "step": 55232
    },
    {
      "epoch": 1.696709980646945,
      "grad_norm": 0.4179022014141083,
      "learning_rate": 1.1171008208824564e-06,
      "loss": 0.4547,
      "step": 55233
    },
    {
      "epoch": 1.6967406997818941,
      "grad_norm": 0.416568785905838,
      "learning_rate": 1.1168788701132427e-06,
      "loss": 0.4735,
      "step": 55234
    },
    {
      "epoch": 1.6967714189168435,
      "grad_norm": 0.39445027709007263,
      "learning_rate": 1.1166569400911775e-06,
      "loss": 0.3749,
      "step": 55235
    },
    {
      "epoch": 1.6968021380517926,
      "grad_norm": 0.42795106768608093,
      "learning_rate": 1.1164350308167837e-06,
      "loss": 0.4753,
      "step": 55236
    },
    {
      "epoch": 1.6968328571867417,
      "grad_norm": 0.43161189556121826,
      "learning_rate": 1.116213142290572e-06,
      "loss": 0.4367,
      "step": 55237
    },
    {
      "epoch": 1.6968635763216908,
      "grad_norm": 0.4346923530101776,
      "learning_rate": 1.1159912745130685e-06,
      "loss": 0.5069,
      "step": 55238
    },
    {
      "epoch": 1.69689429545664,
      "grad_norm": 0.4619584381580353,
      "learning_rate": 1.1157694274847863e-06,
      "loss": 0.4776,
      "step": 55239
    },
    {
      "epoch": 1.696925014591589,
      "grad_norm": 0.41516923904418945,
      "learning_rate": 1.1155476012062472e-06,
      "loss": 0.4656,
      "step": 55240
    },
    {
      "epoch": 1.6969557337265382,
      "grad_norm": 0.437738299369812,
      "learning_rate": 1.115325795677964e-06,
      "loss": 0.4138,
      "step": 55241
    },
    {
      "epoch": 1.6969864528614873,
      "grad_norm": 0.4402099847793579,
      "learning_rate": 1.1151040109004596e-06,
      "loss": 0.532,
      "step": 55242
    },
    {
      "epoch": 1.6970171719964364,
      "grad_norm": 0.43887001276016235,
      "learning_rate": 1.1148822468742493e-06,
      "loss": 0.4762,
      "step": 55243
    },
    {
      "epoch": 1.6970478911313858,
      "grad_norm": 0.4142892062664032,
      "learning_rate": 1.1146605035998536e-06,
      "loss": 0.4747,
      "step": 55244
    },
    {
      "epoch": 1.6970786102663349,
      "grad_norm": 0.4244236946105957,
      "learning_rate": 1.114438781077788e-06,
      "loss": 0.4807,
      "step": 55245
    },
    {
      "epoch": 1.697109329401284,
      "grad_norm": 0.4086083173751831,
      "learning_rate": 1.1142170793085706e-06,
      "loss": 0.4496,
      "step": 55246
    },
    {
      "epoch": 1.6971400485362333,
      "grad_norm": 0.4696774184703827,
      "learning_rate": 1.1139953982927198e-06,
      "loss": 0.4453,
      "step": 55247
    },
    {
      "epoch": 1.6971707676711825,
      "grad_norm": 0.4256843328475952,
      "learning_rate": 1.1137737380307556e-06,
      "loss": 0.5281,
      "step": 55248
    },
    {
      "epoch": 1.6972014868061316,
      "grad_norm": 0.47507497668266296,
      "learning_rate": 1.1135520985231908e-06,
      "loss": 0.4721,
      "step": 55249
    },
    {
      "epoch": 1.6972322059410807,
      "grad_norm": 0.44549688696861267,
      "learning_rate": 1.1133304797705458e-06,
      "loss": 0.5214,
      "step": 55250
    },
    {
      "epoch": 1.6972629250760298,
      "grad_norm": 0.49761322140693665,
      "learning_rate": 1.1131088817733382e-06,
      "loss": 0.4564,
      "step": 55251
    },
    {
      "epoch": 1.697293644210979,
      "grad_norm": 0.4096355140209198,
      "learning_rate": 1.1128873045320888e-06,
      "loss": 0.4468,
      "step": 55252
    },
    {
      "epoch": 1.697324363345928,
      "grad_norm": 0.4027230739593506,
      "learning_rate": 1.112665748047308e-06,
      "loss": 0.5608,
      "step": 55253
    },
    {
      "epoch": 1.6973550824808772,
      "grad_norm": 0.5881909132003784,
      "learning_rate": 1.1124442123195178e-06,
      "loss": 0.5592,
      "step": 55254
    },
    {
      "epoch": 1.6973858016158265,
      "grad_norm": 0.427720308303833,
      "learning_rate": 1.1122226973492344e-06,
      "loss": 0.5014,
      "step": 55255
    },
    {
      "epoch": 1.6974165207507756,
      "grad_norm": 0.42242199182510376,
      "learning_rate": 1.1120012031369764e-06,
      "loss": 0.4905,
      "step": 55256
    },
    {
      "epoch": 1.6974472398857248,
      "grad_norm": 0.46029132604599,
      "learning_rate": 1.1117797296832612e-06,
      "loss": 0.4047,
      "step": 55257
    },
    {
      "epoch": 1.697477959020674,
      "grad_norm": 0.4206429719924927,
      "learning_rate": 1.1115582769886036e-06,
      "loss": 0.474,
      "step": 55258
    },
    {
      "epoch": 1.6975086781556232,
      "grad_norm": 0.49132248759269714,
      "learning_rate": 1.1113368450535234e-06,
      "loss": 0.4677,
      "step": 55259
    },
    {
      "epoch": 1.6975393972905723,
      "grad_norm": 0.5464470982551575,
      "learning_rate": 1.1111154338785358e-06,
      "loss": 0.4295,
      "step": 55260
    },
    {
      "epoch": 1.6975701164255215,
      "grad_norm": 0.4524970054626465,
      "learning_rate": 1.1108940434641613e-06,
      "loss": 0.4834,
      "step": 55261
    },
    {
      "epoch": 1.6976008355604706,
      "grad_norm": 0.437962144613266,
      "learning_rate": 1.110672673810912e-06,
      "loss": 0.4384,
      "step": 55262
    },
    {
      "epoch": 1.6976315546954197,
      "grad_norm": 0.4491931200027466,
      "learning_rate": 1.1104513249193095e-06,
      "loss": 0.4101,
      "step": 55263
    },
    {
      "epoch": 1.6976622738303688,
      "grad_norm": 0.4648664891719818,
      "learning_rate": 1.1102299967898656e-06,
      "loss": 0.4208,
      "step": 55264
    },
    {
      "epoch": 1.697692992965318,
      "grad_norm": 0.5292240381240845,
      "learning_rate": 1.1100086894231032e-06,
      "loss": 0.5325,
      "step": 55265
    },
    {
      "epoch": 1.6977237121002673,
      "grad_norm": 0.42146092653274536,
      "learning_rate": 1.1097874028195355e-06,
      "loss": 0.4134,
      "step": 55266
    },
    {
      "epoch": 1.6977544312352164,
      "grad_norm": 0.4284985661506653,
      "learning_rate": 1.1095661369796818e-06,
      "loss": 0.4987,
      "step": 55267
    },
    {
      "epoch": 1.6977851503701655,
      "grad_norm": 0.4399990439414978,
      "learning_rate": 1.109344891904055e-06,
      "loss": 0.5141,
      "step": 55268
    },
    {
      "epoch": 1.6978158695051149,
      "grad_norm": 0.42522454261779785,
      "learning_rate": 1.109123667593175e-06,
      "loss": 0.4337,
      "step": 55269
    },
    {
      "epoch": 1.697846588640064,
      "grad_norm": 0.46760663390159607,
      "learning_rate": 1.1089024640475566e-06,
      "loss": 0.4072,
      "step": 55270
    },
    {
      "epoch": 1.6978773077750131,
      "grad_norm": 0.406612753868103,
      "learning_rate": 1.1086812812677184e-06,
      "loss": 0.3878,
      "step": 55271
    },
    {
      "epoch": 1.6979080269099622,
      "grad_norm": 0.43943458795547485,
      "learning_rate": 1.1084601192541778e-06,
      "loss": 0.4179,
      "step": 55272
    },
    {
      "epoch": 1.6979387460449114,
      "grad_norm": 0.43980762362480164,
      "learning_rate": 1.1082389780074443e-06,
      "loss": 0.3986,
      "step": 55273
    },
    {
      "epoch": 1.6979694651798605,
      "grad_norm": 0.5294506549835205,
      "learning_rate": 1.1080178575280453e-06,
      "loss": 0.4717,
      "step": 55274
    },
    {
      "epoch": 1.6980001843148096,
      "grad_norm": 0.4604637622833252,
      "learning_rate": 1.1077967578164883e-06,
      "loss": 0.4686,
      "step": 55275
    },
    {
      "epoch": 1.6980309034497587,
      "grad_norm": 0.593311071395874,
      "learning_rate": 1.1075756788732961e-06,
      "loss": 0.3898,
      "step": 55276
    },
    {
      "epoch": 1.698061622584708,
      "grad_norm": 0.42230355739593506,
      "learning_rate": 1.1073546206989793e-06,
      "loss": 0.4265,
      "step": 55277
    },
    {
      "epoch": 1.6980923417196572,
      "grad_norm": 0.4063311219215393,
      "learning_rate": 1.1071335832940567e-06,
      "loss": 0.4371,
      "step": 55278
    },
    {
      "epoch": 1.6981230608546063,
      "grad_norm": 0.43753403425216675,
      "learning_rate": 1.1069125666590452e-06,
      "loss": 0.4225,
      "step": 55279
    },
    {
      "epoch": 1.6981537799895556,
      "grad_norm": 0.43062451481819153,
      "learning_rate": 1.1066915707944625e-06,
      "loss": 0.5107,
      "step": 55280
    },
    {
      "epoch": 1.6981844991245048,
      "grad_norm": 0.4585999846458435,
      "learning_rate": 1.1064705957008203e-06,
      "loss": 0.4777,
      "step": 55281
    },
    {
      "epoch": 1.6982152182594539,
      "grad_norm": 0.457407683134079,
      "learning_rate": 1.1062496413786371e-06,
      "loss": 0.4543,
      "step": 55282
    },
    {
      "epoch": 1.698245937394403,
      "grad_norm": 0.4594332277774811,
      "learning_rate": 1.1060287078284293e-06,
      "loss": 0.4389,
      "step": 55283
    },
    {
      "epoch": 1.6982766565293521,
      "grad_norm": 0.419661283493042,
      "learning_rate": 1.1058077950507151e-06,
      "loss": 0.4202,
      "step": 55284
    },
    {
      "epoch": 1.6983073756643012,
      "grad_norm": 0.4897991716861725,
      "learning_rate": 1.1055869030460054e-06,
      "loss": 0.5307,
      "step": 55285
    },
    {
      "epoch": 1.6983380947992504,
      "grad_norm": 0.4802359640598297,
      "learning_rate": 1.1053660318148185e-06,
      "loss": 0.4044,
      "step": 55286
    },
    {
      "epoch": 1.6983688139341995,
      "grad_norm": 0.3987627923488617,
      "learning_rate": 1.1051451813576708e-06,
      "loss": 0.4114,
      "step": 55287
    },
    {
      "epoch": 1.6983995330691488,
      "grad_norm": 0.4480798542499542,
      "learning_rate": 1.1049243516750797e-06,
      "loss": 0.4348,
      "step": 55288
    },
    {
      "epoch": 1.698430252204098,
      "grad_norm": 0.4060134291648865,
      "learning_rate": 1.1047035427675568e-06,
      "loss": 0.4618,
      "step": 55289
    },
    {
      "epoch": 1.698460971339047,
      "grad_norm": 0.4393202066421509,
      "learning_rate": 1.1044827546356195e-06,
      "loss": 0.4491,
      "step": 55290
    },
    {
      "epoch": 1.6984916904739964,
      "grad_norm": 0.43883776664733887,
      "learning_rate": 1.1042619872797843e-06,
      "loss": 0.446,
      "step": 55291
    },
    {
      "epoch": 1.6985224096089455,
      "grad_norm": 0.40982863306999207,
      "learning_rate": 1.1040412407005674e-06,
      "loss": 0.4218,
      "step": 55292
    },
    {
      "epoch": 1.6985531287438946,
      "grad_norm": 0.5730215907096863,
      "learning_rate": 1.103820514898485e-06,
      "loss": 0.575,
      "step": 55293
    },
    {
      "epoch": 1.6985838478788438,
      "grad_norm": 0.4295474886894226,
      "learning_rate": 1.1035998098740486e-06,
      "loss": 0.4503,
      "step": 55294
    },
    {
      "epoch": 1.6986145670137929,
      "grad_norm": 0.4823054075241089,
      "learning_rate": 1.103379125627776e-06,
      "loss": 0.4783,
      "step": 55295
    },
    {
      "epoch": 1.698645286148742,
      "grad_norm": 0.43795087933540344,
      "learning_rate": 1.1031584621601832e-06,
      "loss": 0.4611,
      "step": 55296
    },
    {
      "epoch": 1.6986760052836911,
      "grad_norm": 0.4448700547218323,
      "learning_rate": 1.1029378194717877e-06,
      "loss": 0.5246,
      "step": 55297
    },
    {
      "epoch": 1.6987067244186402,
      "grad_norm": 0.44063758850097656,
      "learning_rate": 1.102717197563099e-06,
      "loss": 0.4732,
      "step": 55298
    },
    {
      "epoch": 1.6987374435535896,
      "grad_norm": 0.41989728808403015,
      "learning_rate": 1.102496596434639e-06,
      "loss": 0.4574,
      "step": 55299
    },
    {
      "epoch": 1.6987681626885387,
      "grad_norm": 0.47235581278800964,
      "learning_rate": 1.102276016086915e-06,
      "loss": 0.5238,
      "step": 55300
    },
    {
      "epoch": 1.6987988818234878,
      "grad_norm": 0.42556753754615784,
      "learning_rate": 1.1020554565204511e-06,
      "loss": 0.4697,
      "step": 55301
    },
    {
      "epoch": 1.6988296009584372,
      "grad_norm": 0.4082919955253601,
      "learning_rate": 1.1018349177357556e-06,
      "loss": 0.5105,
      "step": 55302
    },
    {
      "epoch": 1.6988603200933863,
      "grad_norm": 0.4969059228897095,
      "learning_rate": 1.1016143997333484e-06,
      "loss": 0.4885,
      "step": 55303
    },
    {
      "epoch": 1.6988910392283354,
      "grad_norm": 0.46101221442222595,
      "learning_rate": 1.10139390251374e-06,
      "loss": 0.5212,
      "step": 55304
    },
    {
      "epoch": 1.6989217583632845,
      "grad_norm": 0.39167270064353943,
      "learning_rate": 1.1011734260774475e-06,
      "loss": 0.4517,
      "step": 55305
    },
    {
      "epoch": 1.6989524774982336,
      "grad_norm": 0.4520711898803711,
      "learning_rate": 1.1009529704249867e-06,
      "loss": 0.4696,
      "step": 55306
    },
    {
      "epoch": 1.6989831966331828,
      "grad_norm": 0.4464801847934723,
      "learning_rate": 1.100732535556871e-06,
      "loss": 0.4472,
      "step": 55307
    },
    {
      "epoch": 1.6990139157681319,
      "grad_norm": 0.47723859548568726,
      "learning_rate": 1.1005121214736182e-06,
      "loss": 0.4789,
      "step": 55308
    },
    {
      "epoch": 1.699044634903081,
      "grad_norm": 0.400987446308136,
      "learning_rate": 1.1002917281757385e-06,
      "loss": 0.4748,
      "step": 55309
    },
    {
      "epoch": 1.6990753540380303,
      "grad_norm": 0.4167305827140808,
      "learning_rate": 1.1000713556637499e-06,
      "loss": 0.4328,
      "step": 55310
    },
    {
      "epoch": 1.6991060731729795,
      "grad_norm": 0.45328018069267273,
      "learning_rate": 1.099851003938166e-06,
      "loss": 0.4661,
      "step": 55311
    },
    {
      "epoch": 1.6991367923079286,
      "grad_norm": 0.48483866453170776,
      "learning_rate": 1.0996306729995032e-06,
      "loss": 0.326,
      "step": 55312
    },
    {
      "epoch": 1.699167511442878,
      "grad_norm": 0.4113911986351013,
      "learning_rate": 1.0994103628482723e-06,
      "loss": 0.503,
      "step": 55313
    },
    {
      "epoch": 1.699198230577827,
      "grad_norm": 0.4243093430995941,
      "learning_rate": 1.0991900734849902e-06,
      "loss": 0.423,
      "step": 55314
    },
    {
      "epoch": 1.6992289497127762,
      "grad_norm": 0.42876383662223816,
      "learning_rate": 1.0989698049101726e-06,
      "loss": 0.3811,
      "step": 55315
    },
    {
      "epoch": 1.6992596688477253,
      "grad_norm": 0.38599535822868347,
      "learning_rate": 1.0987495571243335e-06,
      "loss": 0.4945,
      "step": 55316
    },
    {
      "epoch": 1.6992903879826744,
      "grad_norm": 0.5099228024482727,
      "learning_rate": 1.0985293301279842e-06,
      "loss": 0.4829,
      "step": 55317
    },
    {
      "epoch": 1.6993211071176235,
      "grad_norm": 0.4377709627151489,
      "learning_rate": 1.0983091239216427e-06,
      "loss": 0.4872,
      "step": 55318
    },
    {
      "epoch": 1.6993518262525726,
      "grad_norm": 0.42175430059432983,
      "learning_rate": 1.0980889385058201e-06,
      "loss": 0.432,
      "step": 55319
    },
    {
      "epoch": 1.6993825453875218,
      "grad_norm": 0.4694630801677704,
      "learning_rate": 1.0978687738810356e-06,
      "loss": 0.4892,
      "step": 55320
    },
    {
      "epoch": 1.699413264522471,
      "grad_norm": 0.4348115026950836,
      "learning_rate": 1.0976486300477984e-06,
      "loss": 0.4661,
      "step": 55321
    },
    {
      "epoch": 1.6994439836574202,
      "grad_norm": 0.4326417148113251,
      "learning_rate": 1.0974285070066238e-06,
      "loss": 0.5163,
      "step": 55322
    },
    {
      "epoch": 1.6994747027923693,
      "grad_norm": 0.4077792763710022,
      "learning_rate": 1.0972084047580278e-06,
      "loss": 0.5106,
      "step": 55323
    },
    {
      "epoch": 1.6995054219273187,
      "grad_norm": 0.4358038306236267,
      "learning_rate": 1.0969883233025247e-06,
      "loss": 0.4123,
      "step": 55324
    },
    {
      "epoch": 1.6995361410622678,
      "grad_norm": 0.38791346549987793,
      "learning_rate": 1.096768262640625e-06,
      "loss": 0.4499,
      "step": 55325
    },
    {
      "epoch": 1.699566860197217,
      "grad_norm": 0.4118160903453827,
      "learning_rate": 1.0965482227728452e-06,
      "loss": 0.3866,
      "step": 55326
    },
    {
      "epoch": 1.699597579332166,
      "grad_norm": 0.41571512818336487,
      "learning_rate": 1.096328203699698e-06,
      "loss": 0.3588,
      "step": 55327
    },
    {
      "epoch": 1.6996282984671152,
      "grad_norm": 0.44720762968063354,
      "learning_rate": 1.0961082054216987e-06,
      "loss": 0.417,
      "step": 55328
    },
    {
      "epoch": 1.6996590176020643,
      "grad_norm": 0.4206228256225586,
      "learning_rate": 1.0958882279393624e-06,
      "loss": 0.4608,
      "step": 55329
    },
    {
      "epoch": 1.6996897367370134,
      "grad_norm": 0.4366145730018616,
      "learning_rate": 1.0956682712531997e-06,
      "loss": 0.4678,
      "step": 55330
    },
    {
      "epoch": 1.6997204558719625,
      "grad_norm": 0.4397546350955963,
      "learning_rate": 1.0954483353637268e-06,
      "loss": 0.3725,
      "step": 55331
    },
    {
      "epoch": 1.6997511750069116,
      "grad_norm": 0.42035964131355286,
      "learning_rate": 1.0952284202714525e-06,
      "loss": 0.4676,
      "step": 55332
    },
    {
      "epoch": 1.699781894141861,
      "grad_norm": 0.425680935382843,
      "learning_rate": 1.0950085259768984e-06,
      "loss": 0.5086,
      "step": 55333
    },
    {
      "epoch": 1.69981261327681,
      "grad_norm": 0.5011991858482361,
      "learning_rate": 1.0947886524805707e-06,
      "loss": 0.4574,
      "step": 55334
    },
    {
      "epoch": 1.6998433324117594,
      "grad_norm": 0.40043872594833374,
      "learning_rate": 1.094568799782989e-06,
      "loss": 0.4566,
      "step": 55335
    },
    {
      "epoch": 1.6998740515467086,
      "grad_norm": 0.4996640980243683,
      "learning_rate": 1.0943489678846598e-06,
      "loss": 0.4038,
      "step": 55336
    },
    {
      "epoch": 1.6999047706816577,
      "grad_norm": 0.43555036187171936,
      "learning_rate": 1.0941291567861045e-06,
      "loss": 0.4558,
      "step": 55337
    },
    {
      "epoch": 1.6999354898166068,
      "grad_norm": 0.4274901747703552,
      "learning_rate": 1.0939093664878297e-06,
      "loss": 0.4839,
      "step": 55338
    },
    {
      "epoch": 1.699966208951556,
      "grad_norm": 0.5071609020233154,
      "learning_rate": 1.093689596990355e-06,
      "loss": 0.5276,
      "step": 55339
    },
    {
      "epoch": 1.699996928086505,
      "grad_norm": 0.4395562708377838,
      "learning_rate": 1.0934698482941876e-06,
      "loss": 0.4888,
      "step": 55340
    },
    {
      "epoch": 1.7000276472214542,
      "grad_norm": 0.4271792769432068,
      "learning_rate": 1.0932501203998424e-06,
      "loss": 0.4448,
      "step": 55341
    },
    {
      "epoch": 1.7000583663564033,
      "grad_norm": 0.4690616726875305,
      "learning_rate": 1.0930304133078351e-06,
      "loss": 0.4886,
      "step": 55342
    },
    {
      "epoch": 1.7000890854913524,
      "grad_norm": 0.42562559247016907,
      "learning_rate": 1.0928107270186783e-06,
      "loss": 0.5245,
      "step": 55343
    },
    {
      "epoch": 1.7001198046263017,
      "grad_norm": 0.4984992742538452,
      "learning_rate": 1.0925910615328828e-06,
      "loss": 0.4946,
      "step": 55344
    },
    {
      "epoch": 1.7001505237612509,
      "grad_norm": 0.37405943870544434,
      "learning_rate": 1.0923714168509625e-06,
      "loss": 0.4518,
      "step": 55345
    },
    {
      "epoch": 1.7001812428962002,
      "grad_norm": 0.40688854455947876,
      "learning_rate": 1.0921517929734316e-06,
      "loss": 0.3687,
      "step": 55346
    },
    {
      "epoch": 1.7002119620311493,
      "grad_norm": 0.413939893245697,
      "learning_rate": 1.0919321899008018e-06,
      "loss": 0.4495,
      "step": 55347
    },
    {
      "epoch": 1.7002426811660984,
      "grad_norm": 0.46523866057395935,
      "learning_rate": 1.0917126076335882e-06,
      "loss": 0.4358,
      "step": 55348
    },
    {
      "epoch": 1.7002734003010476,
      "grad_norm": 0.4390244483947754,
      "learning_rate": 1.0914930461723005e-06,
      "loss": 0.5116,
      "step": 55349
    },
    {
      "epoch": 1.7003041194359967,
      "grad_norm": 0.4673244059085846,
      "learning_rate": 1.0912735055174528e-06,
      "loss": 0.4431,
      "step": 55350
    },
    {
      "epoch": 1.7003348385709458,
      "grad_norm": 0.44847479462623596,
      "learning_rate": 1.0910539856695578e-06,
      "loss": 0.4063,
      "step": 55351
    },
    {
      "epoch": 1.700365557705895,
      "grad_norm": 0.4053458273410797,
      "learning_rate": 1.0908344866291299e-06,
      "loss": 0.4149,
      "step": 55352
    },
    {
      "epoch": 1.700396276840844,
      "grad_norm": 0.41933488845825195,
      "learning_rate": 1.0906150083966793e-06,
      "loss": 0.5068,
      "step": 55353
    },
    {
      "epoch": 1.7004269959757932,
      "grad_norm": 0.5084409713745117,
      "learning_rate": 1.0903955509727192e-06,
      "loss": 0.5193,
      "step": 55354
    },
    {
      "epoch": 1.7004577151107425,
      "grad_norm": 0.44858208298683167,
      "learning_rate": 1.0901761143577627e-06,
      "loss": 0.4751,
      "step": 55355
    },
    {
      "epoch": 1.7004884342456916,
      "grad_norm": 0.41994261741638184,
      "learning_rate": 1.0899566985523235e-06,
      "loss": 0.4534,
      "step": 55356
    },
    {
      "epoch": 1.7005191533806407,
      "grad_norm": 0.4438157379627228,
      "learning_rate": 1.0897373035569115e-06,
      "loss": 0.4224,
      "step": 55357
    },
    {
      "epoch": 1.70054987251559,
      "grad_norm": 0.4477883577346802,
      "learning_rate": 1.0895179293720394e-06,
      "loss": 0.5112,
      "step": 55358
    },
    {
      "epoch": 1.7005805916505392,
      "grad_norm": 0.4287768304347992,
      "learning_rate": 1.089298575998221e-06,
      "loss": 0.5212,
      "step": 55359
    },
    {
      "epoch": 1.7006113107854883,
      "grad_norm": 0.4565649926662445,
      "learning_rate": 1.0890792434359698e-06,
      "loss": 0.5442,
      "step": 55360
    },
    {
      "epoch": 1.7006420299204374,
      "grad_norm": 0.40243256092071533,
      "learning_rate": 1.088859931685795e-06,
      "loss": 0.4894,
      "step": 55361
    },
    {
      "epoch": 1.7006727490553866,
      "grad_norm": 0.452728807926178,
      "learning_rate": 1.0886406407482097e-06,
      "loss": 0.5768,
      "step": 55362
    },
    {
      "epoch": 1.7007034681903357,
      "grad_norm": 0.4404393136501312,
      "learning_rate": 1.0884213706237267e-06,
      "loss": 0.4909,
      "step": 55363
    },
    {
      "epoch": 1.7007341873252848,
      "grad_norm": 0.461444228887558,
      "learning_rate": 1.088202121312858e-06,
      "loss": 0.4827,
      "step": 55364
    },
    {
      "epoch": 1.700764906460234,
      "grad_norm": 0.4075343906879425,
      "learning_rate": 1.0879828928161173e-06,
      "loss": 0.4922,
      "step": 55365
    },
    {
      "epoch": 1.7007956255951833,
      "grad_norm": 0.43184635043144226,
      "learning_rate": 1.0877636851340134e-06,
      "loss": 0.4717,
      "step": 55366
    },
    {
      "epoch": 1.7008263447301324,
      "grad_norm": 0.4202289283275604,
      "learning_rate": 1.0875444982670625e-06,
      "loss": 0.4925,
      "step": 55367
    },
    {
      "epoch": 1.7008570638650815,
      "grad_norm": 0.4375269114971161,
      "learning_rate": 1.0873253322157685e-06,
      "loss": 0.4668,
      "step": 55368
    },
    {
      "epoch": 1.7008877830000309,
      "grad_norm": 0.4341300427913666,
      "learning_rate": 1.0871061869806532e-06,
      "loss": 0.4373,
      "step": 55369
    },
    {
      "epoch": 1.70091850213498,
      "grad_norm": 0.3948563039302826,
      "learning_rate": 1.086887062562222e-06,
      "loss": 0.4282,
      "step": 55370
    },
    {
      "epoch": 1.700949221269929,
      "grad_norm": 0.4023456275463104,
      "learning_rate": 1.0866679589609897e-06,
      "loss": 0.4961,
      "step": 55371
    },
    {
      "epoch": 1.7009799404048782,
      "grad_norm": 0.4119502007961273,
      "learning_rate": 1.086448876177466e-06,
      "loss": 0.3836,
      "step": 55372
    },
    {
      "epoch": 1.7010106595398273,
      "grad_norm": 0.45739981532096863,
      "learning_rate": 1.086229814212163e-06,
      "loss": 0.4595,
      "step": 55373
    },
    {
      "epoch": 1.7010413786747764,
      "grad_norm": 0.438970685005188,
      "learning_rate": 1.0860107730655932e-06,
      "loss": 0.5074,
      "step": 55374
    },
    {
      "epoch": 1.7010720978097256,
      "grad_norm": 0.4063633382320404,
      "learning_rate": 1.0857917527382688e-06,
      "loss": 0.3906,
      "step": 55375
    },
    {
      "epoch": 1.7011028169446747,
      "grad_norm": 0.481239378452301,
      "learning_rate": 1.0855727532306991e-06,
      "loss": 0.5146,
      "step": 55376
    },
    {
      "epoch": 1.701133536079624,
      "grad_norm": 0.4496866464614868,
      "learning_rate": 1.0853537745433973e-06,
      "loss": 0.4497,
      "step": 55377
    },
    {
      "epoch": 1.7011642552145732,
      "grad_norm": 0.4377889335155487,
      "learning_rate": 1.0851348166768739e-06,
      "loss": 0.4896,
      "step": 55378
    },
    {
      "epoch": 1.7011949743495223,
      "grad_norm": 0.41666179895401,
      "learning_rate": 1.0849158796316417e-06,
      "loss": 0.4738,
      "step": 55379
    },
    {
      "epoch": 1.7012256934844716,
      "grad_norm": 0.45512399077415466,
      "learning_rate": 1.0846969634082104e-06,
      "loss": 0.4709,
      "step": 55380
    },
    {
      "epoch": 1.7012564126194207,
      "grad_norm": 0.4702477753162384,
      "learning_rate": 1.084478068007091e-06,
      "loss": 0.5131,
      "step": 55381
    },
    {
      "epoch": 1.7012871317543699,
      "grad_norm": 0.5496556758880615,
      "learning_rate": 1.084259193428796e-06,
      "loss": 0.4847,
      "step": 55382
    },
    {
      "epoch": 1.701317850889319,
      "grad_norm": 0.43446043133735657,
      "learning_rate": 1.0840403396738374e-06,
      "loss": 0.4689,
      "step": 55383
    },
    {
      "epoch": 1.701348570024268,
      "grad_norm": 0.46014466881752014,
      "learning_rate": 1.0838215067427261e-06,
      "loss": 0.4634,
      "step": 55384
    },
    {
      "epoch": 1.7013792891592172,
      "grad_norm": 0.47881805896759033,
      "learning_rate": 1.0836026946359713e-06,
      "loss": 0.4984,
      "step": 55385
    },
    {
      "epoch": 1.7014100082941663,
      "grad_norm": 0.4699900150299072,
      "learning_rate": 1.0833839033540837e-06,
      "loss": 0.5286,
      "step": 55386
    },
    {
      "epoch": 1.7014407274291155,
      "grad_norm": 0.4207175076007843,
      "learning_rate": 1.0831651328975767e-06,
      "loss": 0.4016,
      "step": 55387
    },
    {
      "epoch": 1.7014714465640648,
      "grad_norm": 0.5047181248664856,
      "learning_rate": 1.0829463832669618e-06,
      "loss": 0.4306,
      "step": 55388
    },
    {
      "epoch": 1.701502165699014,
      "grad_norm": 0.41476523876190186,
      "learning_rate": 1.0827276544627474e-06,
      "loss": 0.4903,
      "step": 55389
    },
    {
      "epoch": 1.701532884833963,
      "grad_norm": 0.44422850012779236,
      "learning_rate": 1.0825089464854444e-06,
      "loss": 0.514,
      "step": 55390
    },
    {
      "epoch": 1.7015636039689124,
      "grad_norm": 0.44550803303718567,
      "learning_rate": 1.0822902593355645e-06,
      "loss": 0.4278,
      "step": 55391
    },
    {
      "epoch": 1.7015943231038615,
      "grad_norm": 0.4109185039997101,
      "learning_rate": 1.0820715930136217e-06,
      "loss": 0.4514,
      "step": 55392
    },
    {
      "epoch": 1.7016250422388106,
      "grad_norm": 0.44246694445610046,
      "learning_rate": 1.08185294752012e-06,
      "loss": 0.4071,
      "step": 55393
    },
    {
      "epoch": 1.7016557613737597,
      "grad_norm": 0.40871375799179077,
      "learning_rate": 1.0816343228555758e-06,
      "loss": 0.451,
      "step": 55394
    },
    {
      "epoch": 1.7016864805087089,
      "grad_norm": 0.4562215209007263,
      "learning_rate": 1.0814157190204943e-06,
      "loss": 0.5488,
      "step": 55395
    },
    {
      "epoch": 1.701717199643658,
      "grad_norm": 0.4506340026855469,
      "learning_rate": 1.0811971360153928e-06,
      "loss": 0.4971,
      "step": 55396
    },
    {
      "epoch": 1.701747918778607,
      "grad_norm": 0.4656449258327484,
      "learning_rate": 1.0809785738407763e-06,
      "loss": 0.4814,
      "step": 55397
    },
    {
      "epoch": 1.7017786379135562,
      "grad_norm": 0.43247759342193604,
      "learning_rate": 1.080760032497159e-06,
      "loss": 0.5157,
      "step": 55398
    },
    {
      "epoch": 1.7018093570485056,
      "grad_norm": 0.43282830715179443,
      "learning_rate": 1.080541511985046e-06,
      "loss": 0.5099,
      "step": 55399
    },
    {
      "epoch": 1.7018400761834547,
      "grad_norm": 0.4736475348472595,
      "learning_rate": 1.0803230123049536e-06,
      "loss": 0.5091,
      "step": 55400
    },
    {
      "epoch": 1.7018707953184038,
      "grad_norm": 0.4152679145336151,
      "learning_rate": 1.080104533457391e-06,
      "loss": 0.4519,
      "step": 55401
    },
    {
      "epoch": 1.7019015144533531,
      "grad_norm": 0.42810308933258057,
      "learning_rate": 1.0798860754428653e-06,
      "loss": 0.4606,
      "step": 55402
    },
    {
      "epoch": 1.7019322335883023,
      "grad_norm": 0.44211849570274353,
      "learning_rate": 1.0796676382618909e-06,
      "loss": 0.4861,
      "step": 55403
    },
    {
      "epoch": 1.7019629527232514,
      "grad_norm": 0.43307822942733765,
      "learning_rate": 1.079449221914971e-06,
      "loss": 0.4667,
      "step": 55404
    },
    {
      "epoch": 1.7019936718582005,
      "grad_norm": 0.4637771248817444,
      "learning_rate": 1.0792308264026252e-06,
      "loss": 0.5206,
      "step": 55405
    },
    {
      "epoch": 1.7020243909931496,
      "grad_norm": 0.45605987310409546,
      "learning_rate": 1.0790124517253564e-06,
      "loss": 0.4784,
      "step": 55406
    },
    {
      "epoch": 1.7020551101280987,
      "grad_norm": 0.4542120099067688,
      "learning_rate": 1.0787940978836796e-06,
      "loss": 0.4545,
      "step": 55407
    },
    {
      "epoch": 1.7020858292630479,
      "grad_norm": 0.4331231713294983,
      "learning_rate": 1.0785757648781003e-06,
      "loss": 0.4715,
      "step": 55408
    },
    {
      "epoch": 1.702116548397997,
      "grad_norm": 0.4448276460170746,
      "learning_rate": 1.07835745270913e-06,
      "loss": 0.5196,
      "step": 55409
    },
    {
      "epoch": 1.7021472675329463,
      "grad_norm": 0.4121807813644409,
      "learning_rate": 1.0781391613772784e-06,
      "loss": 0.4697,
      "step": 55410
    },
    {
      "epoch": 1.7021779866678954,
      "grad_norm": 0.4492732286453247,
      "learning_rate": 1.0779208908830586e-06,
      "loss": 0.449,
      "step": 55411
    },
    {
      "epoch": 1.7022087058028446,
      "grad_norm": 0.4117871820926666,
      "learning_rate": 1.0777026412269754e-06,
      "loss": 0.4564,
      "step": 55412
    },
    {
      "epoch": 1.702239424937794,
      "grad_norm": 0.4413900375366211,
      "learning_rate": 1.0774844124095407e-06,
      "loss": 0.5254,
      "step": 55413
    },
    {
      "epoch": 1.702270144072743,
      "grad_norm": 0.44022613763809204,
      "learning_rate": 1.0772662044312643e-06,
      "loss": 0.3631,
      "step": 55414
    },
    {
      "epoch": 1.7023008632076921,
      "grad_norm": 0.43696916103363037,
      "learning_rate": 1.077048017292659e-06,
      "loss": 0.4606,
      "step": 55415
    },
    {
      "epoch": 1.7023315823426413,
      "grad_norm": 0.41392868757247925,
      "learning_rate": 1.0768298509942277e-06,
      "loss": 0.4106,
      "step": 55416
    },
    {
      "epoch": 1.7023623014775904,
      "grad_norm": 0.43655896186828613,
      "learning_rate": 1.0766117055364844e-06,
      "loss": 0.487,
      "step": 55417
    },
    {
      "epoch": 1.7023930206125395,
      "grad_norm": 0.4321914613246918,
      "learning_rate": 1.0763935809199366e-06,
      "loss": 0.5309,
      "step": 55418
    },
    {
      "epoch": 1.7024237397474886,
      "grad_norm": 0.40642455220222473,
      "learning_rate": 1.0761754771450962e-06,
      "loss": 0.4764,
      "step": 55419
    },
    {
      "epoch": 1.7024544588824377,
      "grad_norm": 0.43769899010658264,
      "learning_rate": 1.0759573942124723e-06,
      "loss": 0.4717,
      "step": 55420
    },
    {
      "epoch": 1.702485178017387,
      "grad_norm": 0.4817740023136139,
      "learning_rate": 1.0757393321225706e-06,
      "loss": 0.4474,
      "step": 55421
    },
    {
      "epoch": 1.7025158971523362,
      "grad_norm": 0.5588823556900024,
      "learning_rate": 1.075521290875904e-06,
      "loss": 0.4004,
      "step": 55422
    },
    {
      "epoch": 1.7025466162872853,
      "grad_norm": 0.42764413356781006,
      "learning_rate": 1.0753032704729803e-06,
      "loss": 0.4587,
      "step": 55423
    },
    {
      "epoch": 1.7025773354222347,
      "grad_norm": 0.5063033699989319,
      "learning_rate": 1.075085270914311e-06,
      "loss": 0.4201,
      "step": 55424
    },
    {
      "epoch": 1.7026080545571838,
      "grad_norm": 0.4805457890033722,
      "learning_rate": 1.0748672922004023e-06,
      "loss": 0.4957,
      "step": 55425
    },
    {
      "epoch": 1.702638773692133,
      "grad_norm": 0.44050508737564087,
      "learning_rate": 1.0746493343317632e-06,
      "loss": 0.5269,
      "step": 55426
    },
    {
      "epoch": 1.702669492827082,
      "grad_norm": 0.4499180316925049,
      "learning_rate": 1.074431397308905e-06,
      "loss": 0.4277,
      "step": 55427
    },
    {
      "epoch": 1.7027002119620311,
      "grad_norm": 0.5776916146278381,
      "learning_rate": 1.0742134811323367e-06,
      "loss": 0.4986,
      "step": 55428
    },
    {
      "epoch": 1.7027309310969803,
      "grad_norm": 0.40998005867004395,
      "learning_rate": 1.0739955858025641e-06,
      "loss": 0.5157,
      "step": 55429
    },
    {
      "epoch": 1.7027616502319294,
      "grad_norm": 0.4310629367828369,
      "learning_rate": 1.0737777113201009e-06,
      "loss": 0.4433,
      "step": 55430
    },
    {
      "epoch": 1.7027923693668785,
      "grad_norm": 0.4549529254436493,
      "learning_rate": 1.0735598576854489e-06,
      "loss": 0.5302,
      "step": 55431
    },
    {
      "epoch": 1.7028230885018278,
      "grad_norm": 0.45297104120254517,
      "learning_rate": 1.0733420248991256e-06,
      "loss": 0.4968,
      "step": 55432
    },
    {
      "epoch": 1.702853807636777,
      "grad_norm": 0.4297792613506317,
      "learning_rate": 1.0731242129616326e-06,
      "loss": 0.4489,
      "step": 55433
    },
    {
      "epoch": 1.702884526771726,
      "grad_norm": 0.41879209876060486,
      "learning_rate": 1.0729064218734841e-06,
      "loss": 0.4467,
      "step": 55434
    },
    {
      "epoch": 1.7029152459066754,
      "grad_norm": 0.41122758388519287,
      "learning_rate": 1.0726886516351842e-06,
      "loss": 0.4416,
      "step": 55435
    },
    {
      "epoch": 1.7029459650416245,
      "grad_norm": 0.4213103652000427,
      "learning_rate": 1.0724709022472413e-06,
      "loss": 0.4995,
      "step": 55436
    },
    {
      "epoch": 1.7029766841765737,
      "grad_norm": 0.4128270745277405,
      "learning_rate": 1.0722531737101693e-06,
      "loss": 0.4243,
      "step": 55437
    },
    {
      "epoch": 1.7030074033115228,
      "grad_norm": 0.41890040040016174,
      "learning_rate": 1.0720354660244724e-06,
      "loss": 0.5416,
      "step": 55438
    },
    {
      "epoch": 1.703038122446472,
      "grad_norm": 0.4479735195636749,
      "learning_rate": 1.0718177791906625e-06,
      "loss": 0.5101,
      "step": 55439
    },
    {
      "epoch": 1.703068841581421,
      "grad_norm": 0.46460285782814026,
      "learning_rate": 1.0716001132092412e-06,
      "loss": 0.3946,
      "step": 55440
    },
    {
      "epoch": 1.7030995607163701,
      "grad_norm": 0.42207086086273193,
      "learning_rate": 1.071382468080725e-06,
      "loss": 0.4676,
      "step": 55441
    },
    {
      "epoch": 1.7031302798513193,
      "grad_norm": 0.43891942501068115,
      "learning_rate": 1.0711648438056178e-06,
      "loss": 0.5297,
      "step": 55442
    },
    {
      "epoch": 1.7031609989862684,
      "grad_norm": 0.4445715844631195,
      "learning_rate": 1.0709472403844302e-06,
      "loss": 0.5048,
      "step": 55443
    },
    {
      "epoch": 1.7031917181212177,
      "grad_norm": 0.41227710247039795,
      "learning_rate": 1.0707296578176662e-06,
      "loss": 0.4099,
      "step": 55444
    },
    {
      "epoch": 1.7032224372561668,
      "grad_norm": 0.446956068277359,
      "learning_rate": 1.0705120961058368e-06,
      "loss": 0.4535,
      "step": 55445
    },
    {
      "epoch": 1.7032531563911162,
      "grad_norm": 0.498904287815094,
      "learning_rate": 1.0702945552494503e-06,
      "loss": 0.4815,
      "step": 55446
    },
    {
      "epoch": 1.7032838755260653,
      "grad_norm": 0.49059003591537476,
      "learning_rate": 1.0700770352490164e-06,
      "loss": 0.433,
      "step": 55447
    },
    {
      "epoch": 1.7033145946610144,
      "grad_norm": 0.4967445135116577,
      "learning_rate": 1.0698595361050402e-06,
      "loss": 0.4814,
      "step": 55448
    },
    {
      "epoch": 1.7033453137959635,
      "grad_norm": 0.4495922923088074,
      "learning_rate": 1.06964205781803e-06,
      "loss": 0.4086,
      "step": 55449
    },
    {
      "epoch": 1.7033760329309127,
      "grad_norm": 0.4635363519191742,
      "learning_rate": 1.0694246003884946e-06,
      "loss": 0.4024,
      "step": 55450
    },
    {
      "epoch": 1.7034067520658618,
      "grad_norm": 0.3961847126483917,
      "learning_rate": 1.0692071638169433e-06,
      "loss": 0.3793,
      "step": 55451
    },
    {
      "epoch": 1.703437471200811,
      "grad_norm": 0.5704019069671631,
      "learning_rate": 1.0689897481038803e-06,
      "loss": 0.3994,
      "step": 55452
    },
    {
      "epoch": 1.70346819033576,
      "grad_norm": 0.43355512619018555,
      "learning_rate": 1.0687723532498163e-06,
      "loss": 0.4731,
      "step": 55453
    },
    {
      "epoch": 1.7034989094707091,
      "grad_norm": 0.39071765542030334,
      "learning_rate": 1.0685549792552575e-06,
      "loss": 0.4182,
      "step": 55454
    },
    {
      "epoch": 1.7035296286056585,
      "grad_norm": 0.3869319558143616,
      "learning_rate": 1.0683376261207123e-06,
      "loss": 0.4551,
      "step": 55455
    },
    {
      "epoch": 1.7035603477406076,
      "grad_norm": 0.4235607385635376,
      "learning_rate": 1.0681202938466905e-06,
      "loss": 0.454,
      "step": 55456
    },
    {
      "epoch": 1.703591066875557,
      "grad_norm": 0.543142557144165,
      "learning_rate": 1.0679029824336961e-06,
      "loss": 0.5744,
      "step": 55457
    },
    {
      "epoch": 1.703621786010506,
      "grad_norm": 0.45329439640045166,
      "learning_rate": 1.0676856918822376e-06,
      "loss": 0.52,
      "step": 55458
    },
    {
      "epoch": 1.7036525051454552,
      "grad_norm": 0.4512418210506439,
      "learning_rate": 1.0674684221928234e-06,
      "loss": 0.544,
      "step": 55459
    },
    {
      "epoch": 1.7036832242804043,
      "grad_norm": 0.48998695611953735,
      "learning_rate": 1.0672511733659618e-06,
      "loss": 0.475,
      "step": 55460
    },
    {
      "epoch": 1.7037139434153534,
      "grad_norm": 0.4303361773490906,
      "learning_rate": 1.0670339454021572e-06,
      "loss": 0.4412,
      "step": 55461
    },
    {
      "epoch": 1.7037446625503025,
      "grad_norm": 0.4347226619720459,
      "learning_rate": 1.066816738301919e-06,
      "loss": 0.3865,
      "step": 55462
    },
    {
      "epoch": 1.7037753816852517,
      "grad_norm": 0.42214235663414,
      "learning_rate": 1.0665995520657534e-06,
      "loss": 0.4223,
      "step": 55463
    },
    {
      "epoch": 1.7038061008202008,
      "grad_norm": 0.46726709604263306,
      "learning_rate": 1.0663823866941714e-06,
      "loss": 0.5323,
      "step": 55464
    },
    {
      "epoch": 1.70383681995515,
      "grad_norm": 0.45144152641296387,
      "learning_rate": 1.0661652421876745e-06,
      "loss": 0.4658,
      "step": 55465
    },
    {
      "epoch": 1.7038675390900992,
      "grad_norm": 0.44192829728126526,
      "learning_rate": 1.0659481185467757e-06,
      "loss": 0.5105,
      "step": 55466
    },
    {
      "epoch": 1.7038982582250484,
      "grad_norm": 0.4235788881778717,
      "learning_rate": 1.0657310157719746e-06,
      "loss": 0.4861,
      "step": 55467
    },
    {
      "epoch": 1.7039289773599975,
      "grad_norm": 0.4297078847885132,
      "learning_rate": 1.0655139338637854e-06,
      "loss": 0.3883,
      "step": 55468
    },
    {
      "epoch": 1.7039596964949468,
      "grad_norm": 0.4632641673088074,
      "learning_rate": 1.065296872822712e-06,
      "loss": 0.3755,
      "step": 55469
    },
    {
      "epoch": 1.703990415629896,
      "grad_norm": 0.43965327739715576,
      "learning_rate": 1.065079832649263e-06,
      "loss": 0.4096,
      "step": 55470
    },
    {
      "epoch": 1.704021134764845,
      "grad_norm": 0.43983176350593567,
      "learning_rate": 1.064862813343942e-06,
      "loss": 0.5077,
      "step": 55471
    },
    {
      "epoch": 1.7040518538997942,
      "grad_norm": 0.3684823513031006,
      "learning_rate": 1.0646458149072569e-06,
      "loss": 0.4347,
      "step": 55472
    },
    {
      "epoch": 1.7040825730347433,
      "grad_norm": 0.41153374314308167,
      "learning_rate": 1.0644288373397183e-06,
      "loss": 0.4499,
      "step": 55473
    },
    {
      "epoch": 1.7041132921696924,
      "grad_norm": 0.4394829571247101,
      "learning_rate": 1.0642118806418289e-06,
      "loss": 0.4791,
      "step": 55474
    },
    {
      "epoch": 1.7041440113046415,
      "grad_norm": 0.4804515540599823,
      "learning_rate": 1.0639949448140986e-06,
      "loss": 0.4283,
      "step": 55475
    },
    {
      "epoch": 1.7041747304395907,
      "grad_norm": 0.4395653009414673,
      "learning_rate": 1.06377802985703e-06,
      "loss": 0.5024,
      "step": 55476
    },
    {
      "epoch": 1.70420544957454,
      "grad_norm": 0.397671639919281,
      "learning_rate": 1.0635611357711318e-06,
      "loss": 0.3792,
      "step": 55477
    },
    {
      "epoch": 1.7042361687094891,
      "grad_norm": 0.4485902786254883,
      "learning_rate": 1.0633442625569113e-06,
      "loss": 0.4963,
      "step": 55478
    },
    {
      "epoch": 1.7042668878444382,
      "grad_norm": 0.4636766016483307,
      "learning_rate": 1.0631274102148759e-06,
      "loss": 0.4599,
      "step": 55479
    },
    {
      "epoch": 1.7042976069793876,
      "grad_norm": 0.4253825545310974,
      "learning_rate": 1.0629105787455284e-06,
      "loss": 0.5259,
      "step": 55480
    },
    {
      "epoch": 1.7043283261143367,
      "grad_norm": 0.43036314845085144,
      "learning_rate": 1.0626937681493777e-06,
      "loss": 0.438,
      "step": 55481
    },
    {
      "epoch": 1.7043590452492858,
      "grad_norm": 0.41733402013778687,
      "learning_rate": 1.0624769784269295e-06,
      "loss": 0.455,
      "step": 55482
    },
    {
      "epoch": 1.704389764384235,
      "grad_norm": 0.4815613627433777,
      "learning_rate": 1.0622602095786926e-06,
      "loss": 0.4553,
      "step": 55483
    },
    {
      "epoch": 1.704420483519184,
      "grad_norm": 0.42635783553123474,
      "learning_rate": 1.06204346160517e-06,
      "loss": 0.4751,
      "step": 55484
    },
    {
      "epoch": 1.7044512026541332,
      "grad_norm": 0.4511849880218506,
      "learning_rate": 1.0618267345068689e-06,
      "loss": 0.437,
      "step": 55485
    },
    {
      "epoch": 1.7044819217890823,
      "grad_norm": 0.48880183696746826,
      "learning_rate": 1.0616100282842944e-06,
      "loss": 0.4739,
      "step": 55486
    },
    {
      "epoch": 1.7045126409240314,
      "grad_norm": 0.41686540842056274,
      "learning_rate": 1.0613933429379574e-06,
      "loss": 0.4752,
      "step": 55487
    },
    {
      "epoch": 1.7045433600589808,
      "grad_norm": 0.4337799847126007,
      "learning_rate": 1.0611766784683575e-06,
      "loss": 0.4801,
      "step": 55488
    },
    {
      "epoch": 1.70457407919393,
      "grad_norm": 0.43541109561920166,
      "learning_rate": 1.060960034876004e-06,
      "loss": 0.4289,
      "step": 55489
    },
    {
      "epoch": 1.704604798328879,
      "grad_norm": 0.4425114393234253,
      "learning_rate": 1.0607434121614036e-06,
      "loss": 0.4684,
      "step": 55490
    },
    {
      "epoch": 1.7046355174638284,
      "grad_norm": 0.47864830493927,
      "learning_rate": 1.0605268103250598e-06,
      "loss": 0.3858,
      "step": 55491
    },
    {
      "epoch": 1.7046662365987775,
      "grad_norm": 0.43269163370132446,
      "learning_rate": 1.0603102293674827e-06,
      "loss": 0.4808,
      "step": 55492
    },
    {
      "epoch": 1.7046969557337266,
      "grad_norm": 0.4510168731212616,
      "learning_rate": 1.060093669289174e-06,
      "loss": 0.4385,
      "step": 55493
    },
    {
      "epoch": 1.7047276748686757,
      "grad_norm": 0.5053204298019409,
      "learning_rate": 1.0598771300906408e-06,
      "loss": 0.4454,
      "step": 55494
    },
    {
      "epoch": 1.7047583940036248,
      "grad_norm": 0.4421940743923187,
      "learning_rate": 1.0596606117723873e-06,
      "loss": 0.4458,
      "step": 55495
    },
    {
      "epoch": 1.704789113138574,
      "grad_norm": 0.4334453344345093,
      "learning_rate": 1.0594441143349244e-06,
      "loss": 0.5105,
      "step": 55496
    },
    {
      "epoch": 1.704819832273523,
      "grad_norm": 0.4661063253879547,
      "learning_rate": 1.0592276377787514e-06,
      "loss": 0.501,
      "step": 55497
    },
    {
      "epoch": 1.7048505514084722,
      "grad_norm": 0.456746369600296,
      "learning_rate": 1.059011182104379e-06,
      "loss": 0.5035,
      "step": 55498
    },
    {
      "epoch": 1.7048812705434215,
      "grad_norm": 0.4255458116531372,
      "learning_rate": 1.0587947473123072e-06,
      "loss": 0.4151,
      "step": 55499
    },
    {
      "epoch": 1.7049119896783707,
      "grad_norm": 0.46731698513031006,
      "learning_rate": 1.0585783334030475e-06,
      "loss": 0.4522,
      "step": 55500
    },
    {
      "epoch": 1.7049427088133198,
      "grad_norm": 0.4506145119667053,
      "learning_rate": 1.0583619403771007e-06,
      "loss": 0.4697,
      "step": 55501
    },
    {
      "epoch": 1.7049734279482691,
      "grad_norm": 0.4608210623264313,
      "learning_rate": 1.0581455682349763e-06,
      "loss": 0.42,
      "step": 55502
    },
    {
      "epoch": 1.7050041470832182,
      "grad_norm": 0.43886882066726685,
      "learning_rate": 1.0579292169771738e-06,
      "loss": 0.4684,
      "step": 55503
    },
    {
      "epoch": 1.7050348662181674,
      "grad_norm": 0.8751165270805359,
      "learning_rate": 1.0577128866042053e-06,
      "loss": 0.4476,
      "step": 55504
    },
    {
      "epoch": 1.7050655853531165,
      "grad_norm": 0.4597550332546234,
      "learning_rate": 1.0574965771165723e-06,
      "loss": 0.4821,
      "step": 55505
    },
    {
      "epoch": 1.7050963044880656,
      "grad_norm": 0.4596378207206726,
      "learning_rate": 1.0572802885147814e-06,
      "loss": 0.4536,
      "step": 55506
    },
    {
      "epoch": 1.7051270236230147,
      "grad_norm": 0.4388171434402466,
      "learning_rate": 1.0570640207993354e-06,
      "loss": 0.4994,
      "step": 55507
    },
    {
      "epoch": 1.7051577427579638,
      "grad_norm": 0.386353999376297,
      "learning_rate": 1.0568477739707383e-06,
      "loss": 0.4273,
      "step": 55508
    },
    {
      "epoch": 1.705188461892913,
      "grad_norm": 0.45239388942718506,
      "learning_rate": 1.056631548029502e-06,
      "loss": 0.4281,
      "step": 55509
    },
    {
      "epoch": 1.7052191810278623,
      "grad_norm": 0.43468591570854187,
      "learning_rate": 1.056415342976126e-06,
      "loss": 0.4761,
      "step": 55510
    },
    {
      "epoch": 1.7052499001628114,
      "grad_norm": 0.42990416288375854,
      "learning_rate": 1.0561991588111175e-06,
      "loss": 0.4945,
      "step": 55511
    },
    {
      "epoch": 1.7052806192977605,
      "grad_norm": 0.45930933952331543,
      "learning_rate": 1.0559829955349798e-06,
      "loss": 0.5637,
      "step": 55512
    },
    {
      "epoch": 1.7053113384327099,
      "grad_norm": 0.42759811878204346,
      "learning_rate": 1.055766853148218e-06,
      "loss": 0.3753,
      "step": 55513
    },
    {
      "epoch": 1.705342057567659,
      "grad_norm": 0.47350138425827026,
      "learning_rate": 1.055550731651337e-06,
      "loss": 0.4541,
      "step": 55514
    },
    {
      "epoch": 1.7053727767026081,
      "grad_norm": 0.7814286351203918,
      "learning_rate": 1.0553346310448443e-06,
      "loss": 0.4264,
      "step": 55515
    },
    {
      "epoch": 1.7054034958375572,
      "grad_norm": 0.4465062618255615,
      "learning_rate": 1.0551185513292395e-06,
      "loss": 0.4378,
      "step": 55516
    },
    {
      "epoch": 1.7054342149725064,
      "grad_norm": 0.4089476764202118,
      "learning_rate": 1.054902492505031e-06,
      "loss": 0.4896,
      "step": 55517
    },
    {
      "epoch": 1.7054649341074555,
      "grad_norm": 0.46751514077186584,
      "learning_rate": 1.054686454572722e-06,
      "loss": 0.4574,
      "step": 55518
    },
    {
      "epoch": 1.7054956532424046,
      "grad_norm": 0.42162424325942993,
      "learning_rate": 1.0544704375328196e-06,
      "loss": 0.4523,
      "step": 55519
    },
    {
      "epoch": 1.7055263723773537,
      "grad_norm": 0.4279765784740448,
      "learning_rate": 1.0542544413858235e-06,
      "loss": 0.4828,
      "step": 55520
    },
    {
      "epoch": 1.705557091512303,
      "grad_norm": 0.595234215259552,
      "learning_rate": 1.0540384661322424e-06,
      "loss": 0.408,
      "step": 55521
    },
    {
      "epoch": 1.7055878106472522,
      "grad_norm": 0.4418288469314575,
      "learning_rate": 1.0538225117725775e-06,
      "loss": 0.4407,
      "step": 55522
    },
    {
      "epoch": 1.7056185297822013,
      "grad_norm": 0.43166613578796387,
      "learning_rate": 1.053606578307338e-06,
      "loss": 0.4389,
      "step": 55523
    },
    {
      "epoch": 1.7056492489171506,
      "grad_norm": 0.4844581186771393,
      "learning_rate": 1.053390665737023e-06,
      "loss": 0.5177,
      "step": 55524
    },
    {
      "epoch": 1.7056799680520998,
      "grad_norm": 0.5151116847991943,
      "learning_rate": 1.0531747740621389e-06,
      "loss": 0.4754,
      "step": 55525
    },
    {
      "epoch": 1.7057106871870489,
      "grad_norm": 0.42822617292404175,
      "learning_rate": 1.05295890328319e-06,
      "loss": 0.4992,
      "step": 55526
    },
    {
      "epoch": 1.705741406321998,
      "grad_norm": 0.4399493932723999,
      "learning_rate": 1.052743053400681e-06,
      "loss": 0.4129,
      "step": 55527
    },
    {
      "epoch": 1.7057721254569471,
      "grad_norm": 0.40356335043907166,
      "learning_rate": 1.0525272244151164e-06,
      "loss": 0.4896,
      "step": 55528
    },
    {
      "epoch": 1.7058028445918962,
      "grad_norm": 0.4615105092525482,
      "learning_rate": 1.0523114163269977e-06,
      "loss": 0.4608,
      "step": 55529
    },
    {
      "epoch": 1.7058335637268454,
      "grad_norm": 0.4352198839187622,
      "learning_rate": 1.0520956291368312e-06,
      "loss": 0.4071,
      "step": 55530
    },
    {
      "epoch": 1.7058642828617945,
      "grad_norm": 0.8877499103546143,
      "learning_rate": 1.05187986284512e-06,
      "loss": 0.4174,
      "step": 55531
    },
    {
      "epoch": 1.7058950019967438,
      "grad_norm": 0.4714955687522888,
      "learning_rate": 1.05166411745237e-06,
      "loss": 0.5381,
      "step": 55532
    },
    {
      "epoch": 1.705925721131693,
      "grad_norm": 0.5327236652374268,
      "learning_rate": 1.0514483929590812e-06,
      "loss": 0.3955,
      "step": 55533
    },
    {
      "epoch": 1.705956440266642,
      "grad_norm": 0.4212123453617096,
      "learning_rate": 1.051232689365762e-06,
      "loss": 0.5049,
      "step": 55534
    },
    {
      "epoch": 1.7059871594015914,
      "grad_norm": 0.5051223039627075,
      "learning_rate": 1.0510170066729097e-06,
      "loss": 0.4658,
      "step": 55535
    },
    {
      "epoch": 1.7060178785365405,
      "grad_norm": 0.48960596323013306,
      "learning_rate": 1.0508013448810362e-06,
      "loss": 0.4585,
      "step": 55536
    },
    {
      "epoch": 1.7060485976714896,
      "grad_norm": 0.4552953541278839,
      "learning_rate": 1.0505857039906398e-06,
      "loss": 0.4635,
      "step": 55537
    },
    {
      "epoch": 1.7060793168064388,
      "grad_norm": 0.4778151214122772,
      "learning_rate": 1.0503700840022269e-06,
      "loss": 0.4186,
      "step": 55538
    },
    {
      "epoch": 1.7061100359413879,
      "grad_norm": 0.4324420094490051,
      "learning_rate": 1.050154484916297e-06,
      "loss": 0.4363,
      "step": 55539
    },
    {
      "epoch": 1.706140755076337,
      "grad_norm": 0.4122893810272217,
      "learning_rate": 1.0499389067333577e-06,
      "loss": 0.4819,
      "step": 55540
    },
    {
      "epoch": 1.7061714742112861,
      "grad_norm": 0.4495846629142761,
      "learning_rate": 1.0497233494539105e-06,
      "loss": 0.4623,
      "step": 55541
    },
    {
      "epoch": 1.7062021933462352,
      "grad_norm": 0.4267773926258087,
      "learning_rate": 1.0495078130784608e-06,
      "loss": 0.4811,
      "step": 55542
    },
    {
      "epoch": 1.7062329124811846,
      "grad_norm": 0.42472726106643677,
      "learning_rate": 1.0492922976075094e-06,
      "loss": 0.5145,
      "step": 55543
    },
    {
      "epoch": 1.7062636316161337,
      "grad_norm": 0.4643300473690033,
      "learning_rate": 1.049076803041561e-06,
      "loss": 0.356,
      "step": 55544
    },
    {
      "epoch": 1.7062943507510828,
      "grad_norm": 0.3984389007091522,
      "learning_rate": 1.048861329381119e-06,
      "loss": 0.3827,
      "step": 55545
    },
    {
      "epoch": 1.7063250698860322,
      "grad_norm": 0.4312717914581299,
      "learning_rate": 1.048645876626686e-06,
      "loss": 0.4401,
      "step": 55546
    },
    {
      "epoch": 1.7063557890209813,
      "grad_norm": 0.4001750946044922,
      "learning_rate": 1.0484304447787685e-06,
      "loss": 0.4346,
      "step": 55547
    },
    {
      "epoch": 1.7063865081559304,
      "grad_norm": 0.4766017496585846,
      "learning_rate": 1.0482150338378638e-06,
      "loss": 0.4179,
      "step": 55548
    },
    {
      "epoch": 1.7064172272908795,
      "grad_norm": 0.4331872761249542,
      "learning_rate": 1.0479996438044793e-06,
      "loss": 0.4499,
      "step": 55549
    },
    {
      "epoch": 1.7064479464258286,
      "grad_norm": 0.42311906814575195,
      "learning_rate": 1.0477842746791155e-06,
      "loss": 0.5263,
      "step": 55550
    },
    {
      "epoch": 1.7064786655607778,
      "grad_norm": 0.4607309401035309,
      "learning_rate": 1.0475689264622802e-06,
      "loss": 0.3755,
      "step": 55551
    },
    {
      "epoch": 1.7065093846957269,
      "grad_norm": 0.42171770334243774,
      "learning_rate": 1.0473535991544703e-06,
      "loss": 0.4667,
      "step": 55552
    },
    {
      "epoch": 1.706540103830676,
      "grad_norm": 0.4813336730003357,
      "learning_rate": 1.0471382927561913e-06,
      "loss": 0.4433,
      "step": 55553
    },
    {
      "epoch": 1.7065708229656251,
      "grad_norm": 0.47111397981643677,
      "learning_rate": 1.046923007267946e-06,
      "loss": 0.4233,
      "step": 55554
    },
    {
      "epoch": 1.7066015421005745,
      "grad_norm": 0.4109789729118347,
      "learning_rate": 1.0467077426902383e-06,
      "loss": 0.3964,
      "step": 55555
    },
    {
      "epoch": 1.7066322612355236,
      "grad_norm": 0.4072800278663635,
      "learning_rate": 1.0464924990235692e-06,
      "loss": 0.4956,
      "step": 55556
    },
    {
      "epoch": 1.706662980370473,
      "grad_norm": 0.44751250743865967,
      "learning_rate": 1.0462772762684415e-06,
      "loss": 0.51,
      "step": 55557
    },
    {
      "epoch": 1.706693699505422,
      "grad_norm": 0.3998832404613495,
      "learning_rate": 1.046062074425359e-06,
      "loss": 0.4467,
      "step": 55558
    },
    {
      "epoch": 1.7067244186403712,
      "grad_norm": 0.4802856743335724,
      "learning_rate": 1.0458468934948262e-06,
      "loss": 0.4167,
      "step": 55559
    },
    {
      "epoch": 1.7067551377753203,
      "grad_norm": 0.4529699385166168,
      "learning_rate": 1.0456317334773403e-06,
      "loss": 0.554,
      "step": 55560
    },
    {
      "epoch": 1.7067858569102694,
      "grad_norm": 0.44293150305747986,
      "learning_rate": 1.0454165943734096e-06,
      "loss": 0.4849,
      "step": 55561
    },
    {
      "epoch": 1.7068165760452185,
      "grad_norm": 0.493942528963089,
      "learning_rate": 1.0452014761835305e-06,
      "loss": 0.488,
      "step": 55562
    },
    {
      "epoch": 1.7068472951801676,
      "grad_norm": 0.42283448576927185,
      "learning_rate": 1.0449863789082094e-06,
      "loss": 0.4474,
      "step": 55563
    },
    {
      "epoch": 1.7068780143151168,
      "grad_norm": 0.4939040541648865,
      "learning_rate": 1.04477130254795e-06,
      "loss": 0.5363,
      "step": 55564
    },
    {
      "epoch": 1.7069087334500659,
      "grad_norm": 0.5413583517074585,
      "learning_rate": 1.0445562471032522e-06,
      "loss": 0.4278,
      "step": 55565
    },
    {
      "epoch": 1.7069394525850152,
      "grad_norm": 0.4999258518218994,
      "learning_rate": 1.0443412125746177e-06,
      "loss": 0.4415,
      "step": 55566
    },
    {
      "epoch": 1.7069701717199643,
      "grad_norm": 0.4691518545150757,
      "learning_rate": 1.0441261989625494e-06,
      "loss": 0.3724,
      "step": 55567
    },
    {
      "epoch": 1.7070008908549137,
      "grad_norm": 0.467461496591568,
      "learning_rate": 1.0439112062675515e-06,
      "loss": 0.4639,
      "step": 55568
    },
    {
      "epoch": 1.7070316099898628,
      "grad_norm": 0.4461955428123474,
      "learning_rate": 1.0436962344901235e-06,
      "loss": 0.4405,
      "step": 55569
    },
    {
      "epoch": 1.707062329124812,
      "grad_norm": 0.43745526671409607,
      "learning_rate": 1.0434812836307706e-06,
      "loss": 0.4564,
      "step": 55570
    },
    {
      "epoch": 1.707093048259761,
      "grad_norm": 0.4661993980407715,
      "learning_rate": 1.0432663536899878e-06,
      "loss": 0.5075,
      "step": 55571
    },
    {
      "epoch": 1.7071237673947102,
      "grad_norm": 0.4080567955970764,
      "learning_rate": 1.043051444668287e-06,
      "loss": 0.4998,
      "step": 55572
    },
    {
      "epoch": 1.7071544865296593,
      "grad_norm": 0.448884516954422,
      "learning_rate": 1.0428365565661624e-06,
      "loss": 0.5041,
      "step": 55573
    },
    {
      "epoch": 1.7071852056646084,
      "grad_norm": 0.4350009262561798,
      "learning_rate": 1.0426216893841201e-06,
      "loss": 0.4483,
      "step": 55574
    },
    {
      "epoch": 1.7072159247995575,
      "grad_norm": 0.48904696106910706,
      "learning_rate": 1.0424068431226585e-06,
      "loss": 0.5184,
      "step": 55575
    },
    {
      "epoch": 1.7072466439345066,
      "grad_norm": 0.45230838656425476,
      "learning_rate": 1.042192017782282e-06,
      "loss": 0.4863,
      "step": 55576
    },
    {
      "epoch": 1.707277363069456,
      "grad_norm": 0.449495404958725,
      "learning_rate": 1.041977213363492e-06,
      "loss": 0.5294,
      "step": 55577
    },
    {
      "epoch": 1.707308082204405,
      "grad_norm": 0.49460265040397644,
      "learning_rate": 1.0417624298667905e-06,
      "loss": 0.4492,
      "step": 55578
    },
    {
      "epoch": 1.7073388013393542,
      "grad_norm": 0.4228111505508423,
      "learning_rate": 1.0415476672926784e-06,
      "loss": 0.5801,
      "step": 55579
    },
    {
      "epoch": 1.7073695204743036,
      "grad_norm": 0.41481396555900574,
      "learning_rate": 1.041332925641656e-06,
      "loss": 0.4524,
      "step": 55580
    },
    {
      "epoch": 1.7074002396092527,
      "grad_norm": 0.45666787028312683,
      "learning_rate": 1.0411182049142266e-06,
      "loss": 0.4655,
      "step": 55581
    },
    {
      "epoch": 1.7074309587442018,
      "grad_norm": 0.4484555125236511,
      "learning_rate": 1.0409035051108908e-06,
      "loss": 0.4354,
      "step": 55582
    },
    {
      "epoch": 1.707461677879151,
      "grad_norm": 0.4649147391319275,
      "learning_rate": 1.0406888262321524e-06,
      "loss": 0.4348,
      "step": 55583
    },
    {
      "epoch": 1.7074923970141,
      "grad_norm": 0.47684845328330994,
      "learning_rate": 1.0404741682785103e-06,
      "loss": 0.4903,
      "step": 55584
    },
    {
      "epoch": 1.7075231161490492,
      "grad_norm": 0.4917062222957611,
      "learning_rate": 1.040259531250465e-06,
      "loss": 0.4602,
      "step": 55585
    },
    {
      "epoch": 1.7075538352839983,
      "grad_norm": 0.4489766061306,
      "learning_rate": 1.0400449151485204e-06,
      "loss": 0.4647,
      "step": 55586
    },
    {
      "epoch": 1.7075845544189474,
      "grad_norm": 0.5306834578514099,
      "learning_rate": 1.0398303199731775e-06,
      "loss": 0.4741,
      "step": 55587
    },
    {
      "epoch": 1.7076152735538968,
      "grad_norm": 0.422000527381897,
      "learning_rate": 1.0396157457249357e-06,
      "loss": 0.4643,
      "step": 55588
    },
    {
      "epoch": 1.7076459926888459,
      "grad_norm": 0.4035315215587616,
      "learning_rate": 1.039401192404297e-06,
      "loss": 0.4559,
      "step": 55589
    },
    {
      "epoch": 1.707676711823795,
      "grad_norm": 0.4339764714241028,
      "learning_rate": 1.0391866600117628e-06,
      "loss": 0.4854,
      "step": 55590
    },
    {
      "epoch": 1.7077074309587443,
      "grad_norm": 0.4284643828868866,
      "learning_rate": 1.0389721485478354e-06,
      "loss": 0.456,
      "step": 55591
    },
    {
      "epoch": 1.7077381500936935,
      "grad_norm": 0.5077653527259827,
      "learning_rate": 1.0387576580130122e-06,
      "loss": 0.3649,
      "step": 55592
    },
    {
      "epoch": 1.7077688692286426,
      "grad_norm": 0.4126301109790802,
      "learning_rate": 1.0385431884077969e-06,
      "loss": 0.4616,
      "step": 55593
    },
    {
      "epoch": 1.7077995883635917,
      "grad_norm": 0.5514966249465942,
      "learning_rate": 1.038328739732689e-06,
      "loss": 0.4373,
      "step": 55594
    },
    {
      "epoch": 1.7078303074985408,
      "grad_norm": 0.4642791152000427,
      "learning_rate": 1.038114311988193e-06,
      "loss": 0.4404,
      "step": 55595
    },
    {
      "epoch": 1.70786102663349,
      "grad_norm": 0.41421008110046387,
      "learning_rate": 1.0378999051748052e-06,
      "loss": 0.44,
      "step": 55596
    },
    {
      "epoch": 1.707891745768439,
      "grad_norm": 0.45881974697113037,
      "learning_rate": 1.037685519293029e-06,
      "loss": 0.4733,
      "step": 55597
    },
    {
      "epoch": 1.7079224649033882,
      "grad_norm": 0.4098886549472809,
      "learning_rate": 1.0374711543433613e-06,
      "loss": 0.3531,
      "step": 55598
    },
    {
      "epoch": 1.7079531840383375,
      "grad_norm": 0.5182074308395386,
      "learning_rate": 1.037256810326307e-06,
      "loss": 0.4694,
      "step": 55599
    },
    {
      "epoch": 1.7079839031732866,
      "grad_norm": 0.4604826271533966,
      "learning_rate": 1.037042487242368e-06,
      "loss": 0.4389,
      "step": 55600
    },
    {
      "epoch": 1.7080146223082358,
      "grad_norm": 0.41286301612854004,
      "learning_rate": 1.0368281850920393e-06,
      "loss": 0.4444,
      "step": 55601
    },
    {
      "epoch": 1.708045341443185,
      "grad_norm": 0.5248097777366638,
      "learning_rate": 1.036613903875827e-06,
      "loss": 0.3796,
      "step": 55602
    },
    {
      "epoch": 1.7080760605781342,
      "grad_norm": 0.4780976474285126,
      "learning_rate": 1.0363996435942248e-06,
      "loss": 0.5043,
      "step": 55603
    },
    {
      "epoch": 1.7081067797130833,
      "grad_norm": 0.527622401714325,
      "learning_rate": 1.0361854042477416e-06,
      "loss": 0.4548,
      "step": 55604
    },
    {
      "epoch": 1.7081374988480325,
      "grad_norm": 0.4199635982513428,
      "learning_rate": 1.0359711858368703e-06,
      "loss": 0.5133,
      "step": 55605
    },
    {
      "epoch": 1.7081682179829816,
      "grad_norm": 0.4754277467727661,
      "learning_rate": 1.0357569883621177e-06,
      "loss": 0.4215,
      "step": 55606
    },
    {
      "epoch": 1.7081989371179307,
      "grad_norm": 0.42016682028770447,
      "learning_rate": 1.0355428118239763e-06,
      "loss": 0.4906,
      "step": 55607
    },
    {
      "epoch": 1.7082296562528798,
      "grad_norm": 0.4852253198623657,
      "learning_rate": 1.0353286562229537e-06,
      "loss": 0.4993,
      "step": 55608
    },
    {
      "epoch": 1.708260375387829,
      "grad_norm": 0.41018664836883545,
      "learning_rate": 1.035114521559546e-06,
      "loss": 0.4358,
      "step": 55609
    },
    {
      "epoch": 1.7082910945227783,
      "grad_norm": 0.3992713987827301,
      "learning_rate": 1.0349004078342562e-06,
      "loss": 0.4457,
      "step": 55610
    },
    {
      "epoch": 1.7083218136577274,
      "grad_norm": 0.4099522531032562,
      "learning_rate": 1.0346863150475817e-06,
      "loss": 0.4704,
      "step": 55611
    },
    {
      "epoch": 1.7083525327926765,
      "grad_norm": 0.4301137924194336,
      "learning_rate": 1.034472243200022e-06,
      "loss": 0.4458,
      "step": 55612
    },
    {
      "epoch": 1.7083832519276259,
      "grad_norm": 0.45522424578666687,
      "learning_rate": 1.0342581922920791e-06,
      "loss": 0.4456,
      "step": 55613
    },
    {
      "epoch": 1.708413971062575,
      "grad_norm": 0.43656283617019653,
      "learning_rate": 1.0340441623242547e-06,
      "loss": 0.4478,
      "step": 55614
    },
    {
      "epoch": 1.708444690197524,
      "grad_norm": 0.43473565578460693,
      "learning_rate": 1.033830153297043e-06,
      "loss": 0.3738,
      "step": 55615
    },
    {
      "epoch": 1.7084754093324732,
      "grad_norm": 0.4337555766105652,
      "learning_rate": 1.033616165210949e-06,
      "loss": 0.4929,
      "step": 55616
    },
    {
      "epoch": 1.7085061284674223,
      "grad_norm": 0.5363054871559143,
      "learning_rate": 1.0334021980664689e-06,
      "loss": 0.4135,
      "step": 55617
    },
    {
      "epoch": 1.7085368476023715,
      "grad_norm": 0.4013804793357849,
      "learning_rate": 1.0331882518641057e-06,
      "loss": 0.4918,
      "step": 55618
    },
    {
      "epoch": 1.7085675667373206,
      "grad_norm": 0.444845587015152,
      "learning_rate": 1.032974326604359e-06,
      "loss": 0.4467,
      "step": 55619
    },
    {
      "epoch": 1.7085982858722697,
      "grad_norm": 0.4280616044998169,
      "learning_rate": 1.032760422287724e-06,
      "loss": 0.4736,
      "step": 55620
    },
    {
      "epoch": 1.708629005007219,
      "grad_norm": 0.47153034806251526,
      "learning_rate": 1.0325465389147049e-06,
      "loss": 0.4022,
      "step": 55621
    },
    {
      "epoch": 1.7086597241421682,
      "grad_norm": 0.43339622020721436,
      "learning_rate": 1.0323326764857988e-06,
      "loss": 0.5013,
      "step": 55622
    },
    {
      "epoch": 1.7086904432771173,
      "grad_norm": 0.45751258730888367,
      "learning_rate": 1.0321188350015076e-06,
      "loss": 0.5574,
      "step": 55623
    },
    {
      "epoch": 1.7087211624120666,
      "grad_norm": 0.4625803828239441,
      "learning_rate": 1.0319050144623277e-06,
      "loss": 0.4234,
      "step": 55624
    },
    {
      "epoch": 1.7087518815470157,
      "grad_norm": 0.45241692662239075,
      "learning_rate": 1.0316912148687607e-06,
      "loss": 0.4829,
      "step": 55625
    },
    {
      "epoch": 1.7087826006819649,
      "grad_norm": 0.44946417212486267,
      "learning_rate": 1.0314774362213042e-06,
      "loss": 0.4011,
      "step": 55626
    },
    {
      "epoch": 1.708813319816914,
      "grad_norm": 0.4169558882713318,
      "learning_rate": 1.031263678520461e-06,
      "loss": 0.4782,
      "step": 55627
    },
    {
      "epoch": 1.708844038951863,
      "grad_norm": 0.4448345899581909,
      "learning_rate": 1.0310499417667253e-06,
      "loss": 0.419,
      "step": 55628
    },
    {
      "epoch": 1.7088747580868122,
      "grad_norm": 0.4446658790111542,
      "learning_rate": 1.0308362259605997e-06,
      "loss": 0.4243,
      "step": 55629
    },
    {
      "epoch": 1.7089054772217613,
      "grad_norm": 0.41732531785964966,
      "learning_rate": 1.0306225311025819e-06,
      "loss": 0.4871,
      "step": 55630
    },
    {
      "epoch": 1.7089361963567105,
      "grad_norm": 0.38146722316741943,
      "learning_rate": 1.0304088571931737e-06,
      "loss": 0.4345,
      "step": 55631
    },
    {
      "epoch": 1.7089669154916598,
      "grad_norm": 0.3939587473869324,
      "learning_rate": 1.03019520423287e-06,
      "loss": 0.4775,
      "step": 55632
    },
    {
      "epoch": 1.708997634626609,
      "grad_norm": 0.4157833158969879,
      "learning_rate": 1.029981572222174e-06,
      "loss": 0.5246,
      "step": 55633
    },
    {
      "epoch": 1.709028353761558,
      "grad_norm": 0.46755027770996094,
      "learning_rate": 1.0297679611615785e-06,
      "loss": 0.3855,
      "step": 55634
    },
    {
      "epoch": 1.7090590728965074,
      "grad_norm": 0.44156593084335327,
      "learning_rate": 1.0295543710515898e-06,
      "loss": 0.4906,
      "step": 55635
    },
    {
      "epoch": 1.7090897920314565,
      "grad_norm": 0.4062148928642273,
      "learning_rate": 1.0293408018927021e-06,
      "loss": 0.4101,
      "step": 55636
    },
    {
      "epoch": 1.7091205111664056,
      "grad_norm": 0.44490674138069153,
      "learning_rate": 1.0291272536854147e-06,
      "loss": 0.5084,
      "step": 55637
    },
    {
      "epoch": 1.7091512303013547,
      "grad_norm": 0.42132288217544556,
      "learning_rate": 1.0289137264302297e-06,
      "loss": 0.4379,
      "step": 55638
    },
    {
      "epoch": 1.7091819494363039,
      "grad_norm": 0.44317206740379333,
      "learning_rate": 1.0287002201276398e-06,
      "loss": 0.5419,
      "step": 55639
    },
    {
      "epoch": 1.709212668571253,
      "grad_norm": 0.46114030480384827,
      "learning_rate": 1.0284867347781502e-06,
      "loss": 0.4686,
      "step": 55640
    },
    {
      "epoch": 1.709243387706202,
      "grad_norm": 0.4817725419998169,
      "learning_rate": 1.028273270382254e-06,
      "loss": 0.486,
      "step": 55641
    },
    {
      "epoch": 1.7092741068411512,
      "grad_norm": 0.4113349914550781,
      "learning_rate": 1.028059826940455e-06,
      "loss": 0.462,
      "step": 55642
    },
    {
      "epoch": 1.7093048259761006,
      "grad_norm": 0.4197496771812439,
      "learning_rate": 1.0278464044532466e-06,
      "loss": 0.4997,
      "step": 55643
    },
    {
      "epoch": 1.7093355451110497,
      "grad_norm": 0.4314102530479431,
      "learning_rate": 1.02763300292113e-06,
      "loss": 0.4488,
      "step": 55644
    },
    {
      "epoch": 1.7093662642459988,
      "grad_norm": 1.1868219375610352,
      "learning_rate": 1.027419622344602e-06,
      "loss": 0.4609,
      "step": 55645
    },
    {
      "epoch": 1.7093969833809481,
      "grad_norm": 0.40150439739227295,
      "learning_rate": 1.0272062627241653e-06,
      "loss": 0.4524,
      "step": 55646
    },
    {
      "epoch": 1.7094277025158973,
      "grad_norm": 0.4533103406429291,
      "learning_rate": 1.0269929240603128e-06,
      "loss": 0.5294,
      "step": 55647
    },
    {
      "epoch": 1.7094584216508464,
      "grad_norm": 0.4183756113052368,
      "learning_rate": 1.026779606353544e-06,
      "loss": 0.4053,
      "step": 55648
    },
    {
      "epoch": 1.7094891407857955,
      "grad_norm": 0.4171695113182068,
      "learning_rate": 1.0265663096043598e-06,
      "loss": 0.5264,
      "step": 55649
    },
    {
      "epoch": 1.7095198599207446,
      "grad_norm": 0.4439469575881958,
      "learning_rate": 1.0263530338132577e-06,
      "loss": 0.4325,
      "step": 55650
    },
    {
      "epoch": 1.7095505790556937,
      "grad_norm": 0.4566819369792938,
      "learning_rate": 1.0261397789807325e-06,
      "loss": 0.3735,
      "step": 55651
    },
    {
      "epoch": 1.7095812981906429,
      "grad_norm": 0.44367730617523193,
      "learning_rate": 1.0259265451072852e-06,
      "loss": 0.4303,
      "step": 55652
    },
    {
      "epoch": 1.709612017325592,
      "grad_norm": 0.4371938705444336,
      "learning_rate": 1.025713332193412e-06,
      "loss": 0.446,
      "step": 55653
    },
    {
      "epoch": 1.7096427364605413,
      "grad_norm": 0.41369763016700745,
      "learning_rate": 1.0255001402396136e-06,
      "loss": 0.4322,
      "step": 55654
    },
    {
      "epoch": 1.7096734555954904,
      "grad_norm": 0.44305700063705444,
      "learning_rate": 1.0252869692463873e-06,
      "loss": 0.4138,
      "step": 55655
    },
    {
      "epoch": 1.7097041747304396,
      "grad_norm": 0.42929303646087646,
      "learning_rate": 1.0250738192142283e-06,
      "loss": 0.4706,
      "step": 55656
    },
    {
      "epoch": 1.709734893865389,
      "grad_norm": 0.4634746015071869,
      "learning_rate": 1.0248606901436376e-06,
      "loss": 0.4178,
      "step": 55657
    },
    {
      "epoch": 1.709765613000338,
      "grad_norm": 0.42107120156288147,
      "learning_rate": 1.0246475820351099e-06,
      "loss": 0.4804,
      "step": 55658
    },
    {
      "epoch": 1.7097963321352871,
      "grad_norm": 0.4969431161880493,
      "learning_rate": 1.024434494889147e-06,
      "loss": 0.4596,
      "step": 55659
    },
    {
      "epoch": 1.7098270512702363,
      "grad_norm": 0.46103087067604065,
      "learning_rate": 1.0242214287062424e-06,
      "loss": 0.5369,
      "step": 55660
    },
    {
      "epoch": 1.7098577704051854,
      "grad_norm": 0.44358137249946594,
      "learning_rate": 1.0240083834868952e-06,
      "loss": 0.3751,
      "step": 55661
    },
    {
      "epoch": 1.7098884895401345,
      "grad_norm": 0.44799959659576416,
      "learning_rate": 1.023795359231604e-06,
      "loss": 0.4475,
      "step": 55662
    },
    {
      "epoch": 1.7099192086750836,
      "grad_norm": 0.39407220482826233,
      "learning_rate": 1.0235823559408665e-06,
      "loss": 0.4813,
      "step": 55663
    },
    {
      "epoch": 1.7099499278100327,
      "grad_norm": 0.4246344268321991,
      "learning_rate": 1.0233693736151784e-06,
      "loss": 0.4367,
      "step": 55664
    },
    {
      "epoch": 1.7099806469449819,
      "grad_norm": 0.45584097504615784,
      "learning_rate": 1.0231564122550398e-06,
      "loss": 0.4811,
      "step": 55665
    },
    {
      "epoch": 1.7100113660799312,
      "grad_norm": 0.45447537302970886,
      "learning_rate": 1.022943471860942e-06,
      "loss": 0.4928,
      "step": 55666
    },
    {
      "epoch": 1.7100420852148803,
      "grad_norm": 0.4466848373413086,
      "learning_rate": 1.0227305524333908e-06,
      "loss": 0.4215,
      "step": 55667
    },
    {
      "epoch": 1.7100728043498297,
      "grad_norm": 0.434099018573761,
      "learning_rate": 1.0225176539728776e-06,
      "loss": 0.5355,
      "step": 55668
    },
    {
      "epoch": 1.7101035234847788,
      "grad_norm": 0.4062484800815582,
      "learning_rate": 1.0223047764799031e-06,
      "loss": 0.4544,
      "step": 55669
    },
    {
      "epoch": 1.710134242619728,
      "grad_norm": 0.43652185797691345,
      "learning_rate": 1.0220919199549584e-06,
      "loss": 0.4356,
      "step": 55670
    },
    {
      "epoch": 1.710164961754677,
      "grad_norm": 0.533335268497467,
      "learning_rate": 1.0218790843985494e-06,
      "loss": 0.4763,
      "step": 55671
    },
    {
      "epoch": 1.7101956808896261,
      "grad_norm": 0.43996840715408325,
      "learning_rate": 1.0216662698111669e-06,
      "loss": 0.4242,
      "step": 55672
    },
    {
      "epoch": 1.7102264000245753,
      "grad_norm": 0.4240790009498596,
      "learning_rate": 1.0214534761933104e-06,
      "loss": 0.4865,
      "step": 55673
    },
    {
      "epoch": 1.7102571191595244,
      "grad_norm": 0.5326853394508362,
      "learning_rate": 1.0212407035454774e-06,
      "loss": 0.5418,
      "step": 55674
    },
    {
      "epoch": 1.7102878382944735,
      "grad_norm": 0.41435110569000244,
      "learning_rate": 1.0210279518681598e-06,
      "loss": 0.4409,
      "step": 55675
    },
    {
      "epoch": 1.7103185574294226,
      "grad_norm": 0.44033002853393555,
      "learning_rate": 1.0208152211618638e-06,
      "loss": 0.5316,
      "step": 55676
    },
    {
      "epoch": 1.710349276564372,
      "grad_norm": 0.43776944279670715,
      "learning_rate": 1.020602511427078e-06,
      "loss": 0.456,
      "step": 55677
    },
    {
      "epoch": 1.710379995699321,
      "grad_norm": 0.4505026638507843,
      "learning_rate": 1.020389822664304e-06,
      "loss": 0.5448,
      "step": 55678
    },
    {
      "epoch": 1.7104107148342704,
      "grad_norm": 0.4274553060531616,
      "learning_rate": 1.0201771548740346e-06,
      "loss": 0.5176,
      "step": 55679
    },
    {
      "epoch": 1.7104414339692195,
      "grad_norm": 0.4397844076156616,
      "learning_rate": 1.0199645080567688e-06,
      "loss": 0.4478,
      "step": 55680
    },
    {
      "epoch": 1.7104721531041687,
      "grad_norm": 0.44704264402389526,
      "learning_rate": 1.0197518822130037e-06,
      "loss": 0.5308,
      "step": 55681
    },
    {
      "epoch": 1.7105028722391178,
      "grad_norm": 0.39095550775527954,
      "learning_rate": 1.0195392773432366e-06,
      "loss": 0.4293,
      "step": 55682
    },
    {
      "epoch": 1.710533591374067,
      "grad_norm": 0.4184356927871704,
      "learning_rate": 1.0193266934479607e-06,
      "loss": 0.4704,
      "step": 55683
    },
    {
      "epoch": 1.710564310509016,
      "grad_norm": 0.43979981541633606,
      "learning_rate": 1.0191141305276752e-06,
      "loss": 0.5416,
      "step": 55684
    },
    {
      "epoch": 1.7105950296439651,
      "grad_norm": 0.4206252098083496,
      "learning_rate": 1.0189015885828746e-06,
      "loss": 0.4308,
      "step": 55685
    },
    {
      "epoch": 1.7106257487789143,
      "grad_norm": 0.4101240634918213,
      "learning_rate": 1.0186890676140592e-06,
      "loss": 0.5004,
      "step": 55686
    },
    {
      "epoch": 1.7106564679138634,
      "grad_norm": 0.4185217022895813,
      "learning_rate": 1.0184765676217212e-06,
      "loss": 0.5057,
      "step": 55687
    },
    {
      "epoch": 1.7106871870488127,
      "grad_norm": 0.43746376037597656,
      "learning_rate": 1.0182640886063577e-06,
      "loss": 0.4424,
      "step": 55688
    },
    {
      "epoch": 1.7107179061837618,
      "grad_norm": 0.4194307029247284,
      "learning_rate": 1.0180516305684662e-06,
      "loss": 0.4676,
      "step": 55689
    },
    {
      "epoch": 1.7107486253187112,
      "grad_norm": 0.4746641218662262,
      "learning_rate": 1.0178391935085442e-06,
      "loss": 0.5042,
      "step": 55690
    },
    {
      "epoch": 1.7107793444536603,
      "grad_norm": 0.4160250723361969,
      "learning_rate": 1.0176267774270842e-06,
      "loss": 0.5184,
      "step": 55691
    },
    {
      "epoch": 1.7108100635886094,
      "grad_norm": 0.40770554542541504,
      "learning_rate": 1.0174143823245842e-06,
      "loss": 0.4366,
      "step": 55692
    },
    {
      "epoch": 1.7108407827235586,
      "grad_norm": 0.4229280352592468,
      "learning_rate": 1.017202008201541e-06,
      "loss": 0.5569,
      "step": 55693
    },
    {
      "epoch": 1.7108715018585077,
      "grad_norm": 0.42180365324020386,
      "learning_rate": 1.0169896550584491e-06,
      "loss": 0.4638,
      "step": 55694
    },
    {
      "epoch": 1.7109022209934568,
      "grad_norm": 0.4716643691062927,
      "learning_rate": 1.0167773228958066e-06,
      "loss": 0.4837,
      "step": 55695
    },
    {
      "epoch": 1.710932940128406,
      "grad_norm": 0.46581539511680603,
      "learning_rate": 1.0165650117141068e-06,
      "loss": 0.4979,
      "step": 55696
    },
    {
      "epoch": 1.710963659263355,
      "grad_norm": 0.40899574756622314,
      "learning_rate": 1.0163527215138469e-06,
      "loss": 0.4397,
      "step": 55697
    },
    {
      "epoch": 1.7109943783983041,
      "grad_norm": 0.5148518681526184,
      "learning_rate": 1.016140452295522e-06,
      "loss": 0.4729,
      "step": 55698
    },
    {
      "epoch": 1.7110250975332535,
      "grad_norm": 0.5254153609275818,
      "learning_rate": 1.0159282040596308e-06,
      "loss": 0.471,
      "step": 55699
    },
    {
      "epoch": 1.7110558166682026,
      "grad_norm": 0.4795546531677246,
      "learning_rate": 1.0157159768066648e-06,
      "loss": 0.4496,
      "step": 55700
    },
    {
      "epoch": 1.7110865358031517,
      "grad_norm": 0.5049745440483093,
      "learning_rate": 1.0155037705371228e-06,
      "loss": 0.4781,
      "step": 55701
    },
    {
      "epoch": 1.711117254938101,
      "grad_norm": 0.4995758831501007,
      "learning_rate": 1.0152915852514967e-06,
      "loss": 0.4483,
      "step": 55702
    },
    {
      "epoch": 1.7111479740730502,
      "grad_norm": 0.41500353813171387,
      "learning_rate": 1.0150794209502879e-06,
      "loss": 0.4658,
      "step": 55703
    },
    {
      "epoch": 1.7111786932079993,
      "grad_norm": 0.4750013053417206,
      "learning_rate": 1.0148672776339864e-06,
      "loss": 0.471,
      "step": 55704
    },
    {
      "epoch": 1.7112094123429484,
      "grad_norm": 0.4527476727962494,
      "learning_rate": 1.0146551553030926e-06,
      "loss": 0.4852,
      "step": 55705
    },
    {
      "epoch": 1.7112401314778976,
      "grad_norm": 0.4300133287906647,
      "learning_rate": 1.0144430539580963e-06,
      "loss": 0.4968,
      "step": 55706
    },
    {
      "epoch": 1.7112708506128467,
      "grad_norm": 0.43331241607666016,
      "learning_rate": 1.014230973599496e-06,
      "loss": 0.5163,
      "step": 55707
    },
    {
      "epoch": 1.7113015697477958,
      "grad_norm": 0.40415674448013306,
      "learning_rate": 1.0140189142277868e-06,
      "loss": 0.499,
      "step": 55708
    },
    {
      "epoch": 1.711332288882745,
      "grad_norm": 0.49756917357444763,
      "learning_rate": 1.0138068758434638e-06,
      "loss": 0.4904,
      "step": 55709
    },
    {
      "epoch": 1.7113630080176943,
      "grad_norm": 0.4111216366291046,
      "learning_rate": 1.0135948584470256e-06,
      "loss": 0.5554,
      "step": 55710
    },
    {
      "epoch": 1.7113937271526434,
      "grad_norm": 0.43792012333869934,
      "learning_rate": 1.0133828620389597e-06,
      "loss": 0.4627,
      "step": 55711
    },
    {
      "epoch": 1.7114244462875925,
      "grad_norm": 0.4327220022678375,
      "learning_rate": 1.0131708866197687e-06,
      "loss": 0.4442,
      "step": 55712
    },
    {
      "epoch": 1.7114551654225418,
      "grad_norm": 0.4395090341567993,
      "learning_rate": 1.0129589321899435e-06,
      "loss": 0.4578,
      "step": 55713
    },
    {
      "epoch": 1.711485884557491,
      "grad_norm": 0.42517557740211487,
      "learning_rate": 1.0127469987499827e-06,
      "loss": 0.4676,
      "step": 55714
    },
    {
      "epoch": 1.71151660369244,
      "grad_norm": 0.4178713262081146,
      "learning_rate": 1.012535086300377e-06,
      "loss": 0.4355,
      "step": 55715
    },
    {
      "epoch": 1.7115473228273892,
      "grad_norm": 0.464025616645813,
      "learning_rate": 1.0123231948416224e-06,
      "loss": 0.4483,
      "step": 55716
    },
    {
      "epoch": 1.7115780419623383,
      "grad_norm": 0.4883210361003876,
      "learning_rate": 1.0121113243742154e-06,
      "loss": 0.4339,
      "step": 55717
    },
    {
      "epoch": 1.7116087610972874,
      "grad_norm": 0.4705239534378052,
      "learning_rate": 1.0118994748986522e-06,
      "loss": 0.464,
      "step": 55718
    },
    {
      "epoch": 1.7116394802322366,
      "grad_norm": 0.49183306097984314,
      "learning_rate": 1.0116876464154223e-06,
      "loss": 0.4825,
      "step": 55719
    },
    {
      "epoch": 1.7116701993671857,
      "grad_norm": 0.4627965986728668,
      "learning_rate": 1.0114758389250246e-06,
      "loss": 0.4075,
      "step": 55720
    },
    {
      "epoch": 1.711700918502135,
      "grad_norm": 0.4536268413066864,
      "learning_rate": 1.0112640524279526e-06,
      "loss": 0.4756,
      "step": 55721
    },
    {
      "epoch": 1.7117316376370841,
      "grad_norm": 0.4293973743915558,
      "learning_rate": 1.011052286924704e-06,
      "loss": 0.3652,
      "step": 55722
    },
    {
      "epoch": 1.7117623567720333,
      "grad_norm": 0.4440925419330597,
      "learning_rate": 1.0108405424157674e-06,
      "loss": 0.4151,
      "step": 55723
    },
    {
      "epoch": 1.7117930759069826,
      "grad_norm": 0.4967173933982849,
      "learning_rate": 1.0106288189016412e-06,
      "loss": 0.4777,
      "step": 55724
    },
    {
      "epoch": 1.7118237950419317,
      "grad_norm": 0.5242800116539001,
      "learning_rate": 1.0104171163828192e-06,
      "loss": 0.4315,
      "step": 55725
    },
    {
      "epoch": 1.7118545141768808,
      "grad_norm": 0.42297863960266113,
      "learning_rate": 1.0102054348597968e-06,
      "loss": 0.475,
      "step": 55726
    },
    {
      "epoch": 1.71188523331183,
      "grad_norm": 0.48214471340179443,
      "learning_rate": 1.0099937743330668e-06,
      "loss": 0.4717,
      "step": 55727
    },
    {
      "epoch": 1.711915952446779,
      "grad_norm": 0.42832261323928833,
      "learning_rate": 1.0097821348031234e-06,
      "loss": 0.5111,
      "step": 55728
    },
    {
      "epoch": 1.7119466715817282,
      "grad_norm": 0.4021673798561096,
      "learning_rate": 1.0095705162704617e-06,
      "loss": 0.426,
      "step": 55729
    },
    {
      "epoch": 1.7119773907166773,
      "grad_norm": 0.4859231412410736,
      "learning_rate": 1.0093589187355768e-06,
      "loss": 0.4546,
      "step": 55730
    },
    {
      "epoch": 1.7120081098516264,
      "grad_norm": 0.4696158170700073,
      "learning_rate": 1.0091473421989627e-06,
      "loss": 0.4318,
      "step": 55731
    },
    {
      "epoch": 1.7120388289865758,
      "grad_norm": 0.40763410925865173,
      "learning_rate": 1.0089357866611126e-06,
      "loss": 0.4109,
      "step": 55732
    },
    {
      "epoch": 1.712069548121525,
      "grad_norm": 0.4418821632862091,
      "learning_rate": 1.0087242521225194e-06,
      "loss": 0.4646,
      "step": 55733
    },
    {
      "epoch": 1.712100267256474,
      "grad_norm": 0.4254024922847748,
      "learning_rate": 1.008512738583679e-06,
      "loss": 0.4858,
      "step": 55734
    },
    {
      "epoch": 1.7121309863914234,
      "grad_norm": 0.43676719069480896,
      "learning_rate": 1.008301246045088e-06,
      "loss": 0.3616,
      "step": 55735
    },
    {
      "epoch": 1.7121617055263725,
      "grad_norm": 0.4391336441040039,
      "learning_rate": 1.008089774507235e-06,
      "loss": 0.4849,
      "step": 55736
    },
    {
      "epoch": 1.7121924246613216,
      "grad_norm": 0.4930306673049927,
      "learning_rate": 1.007878323970617e-06,
      "loss": 0.5014,
      "step": 55737
    },
    {
      "epoch": 1.7122231437962707,
      "grad_norm": 0.4666791558265686,
      "learning_rate": 1.0076668944357248e-06,
      "loss": 0.4488,
      "step": 55738
    },
    {
      "epoch": 1.7122538629312198,
      "grad_norm": 0.45551469922065735,
      "learning_rate": 1.0074554859030573e-06,
      "loss": 0.5493,
      "step": 55739
    },
    {
      "epoch": 1.712284582066169,
      "grad_norm": 0.3807060420513153,
      "learning_rate": 1.0072440983731046e-06,
      "loss": 0.4072,
      "step": 55740
    },
    {
      "epoch": 1.712315301201118,
      "grad_norm": 0.37692317366600037,
      "learning_rate": 1.0070327318463624e-06,
      "loss": 0.4527,
      "step": 55741
    },
    {
      "epoch": 1.7123460203360672,
      "grad_norm": 0.47788214683532715,
      "learning_rate": 1.0068213863233223e-06,
      "loss": 0.483,
      "step": 55742
    },
    {
      "epoch": 1.7123767394710165,
      "grad_norm": 0.4105221629142761,
      "learning_rate": 1.0066100618044782e-06,
      "loss": 0.3841,
      "step": 55743
    },
    {
      "epoch": 1.7124074586059657,
      "grad_norm": 0.4345754086971283,
      "learning_rate": 1.0063987582903256e-06,
      "loss": 0.3901,
      "step": 55744
    },
    {
      "epoch": 1.7124381777409148,
      "grad_norm": 0.39861711859703064,
      "learning_rate": 1.006187475781355e-06,
      "loss": 0.4911,
      "step": 55745
    },
    {
      "epoch": 1.7124688968758641,
      "grad_norm": 0.434384822845459,
      "learning_rate": 1.005976214278065e-06,
      "loss": 0.5352,
      "step": 55746
    },
    {
      "epoch": 1.7124996160108132,
      "grad_norm": 0.4988241195678711,
      "learning_rate": 1.0057649737809426e-06,
      "loss": 0.4872,
      "step": 55747
    },
    {
      "epoch": 1.7125303351457624,
      "grad_norm": 0.4756755530834198,
      "learning_rate": 1.0055537542904858e-06,
      "loss": 0.4474,
      "step": 55748
    },
    {
      "epoch": 1.7125610542807115,
      "grad_norm": 0.4078010022640228,
      "learning_rate": 1.005342555807185e-06,
      "loss": 0.3986,
      "step": 55749
    },
    {
      "epoch": 1.7125917734156606,
      "grad_norm": 0.4065437316894531,
      "learning_rate": 1.0051313783315376e-06,
      "loss": 0.5001,
      "step": 55750
    },
    {
      "epoch": 1.7126224925506097,
      "grad_norm": 0.42370128631591797,
      "learning_rate": 1.004920221864032e-06,
      "loss": 0.4613,
      "step": 55751
    },
    {
      "epoch": 1.7126532116855588,
      "grad_norm": 0.40523672103881836,
      "learning_rate": 1.0047090864051634e-06,
      "loss": 0.3965,
      "step": 55752
    },
    {
      "epoch": 1.712683930820508,
      "grad_norm": 0.438975065946579,
      "learning_rate": 1.0044979719554238e-06,
      "loss": 0.535,
      "step": 55753
    },
    {
      "epoch": 1.7127146499554573,
      "grad_norm": 0.42918920516967773,
      "learning_rate": 1.0042868785153104e-06,
      "loss": 0.5055,
      "step": 55754
    },
    {
      "epoch": 1.7127453690904064,
      "grad_norm": 0.4628395438194275,
      "learning_rate": 1.0040758060853118e-06,
      "loss": 0.4418,
      "step": 55755
    },
    {
      "epoch": 1.7127760882253555,
      "grad_norm": 0.44546717405319214,
      "learning_rate": 1.003864754665922e-06,
      "loss": 0.533,
      "step": 55756
    },
    {
      "epoch": 1.7128068073603049,
      "grad_norm": 0.43365663290023804,
      "learning_rate": 1.0036537242576338e-06,
      "loss": 0.487,
      "step": 55757
    },
    {
      "epoch": 1.712837526495254,
      "grad_norm": 0.39907407760620117,
      "learning_rate": 1.0034427148609426e-06,
      "loss": 0.4714,
      "step": 55758
    },
    {
      "epoch": 1.7128682456302031,
      "grad_norm": 0.4074743688106537,
      "learning_rate": 1.003231726476338e-06,
      "loss": 0.4189,
      "step": 55759
    },
    {
      "epoch": 1.7128989647651522,
      "grad_norm": 0.46370866894721985,
      "learning_rate": 1.003020759104314e-06,
      "loss": 0.4443,
      "step": 55760
    },
    {
      "epoch": 1.7129296839001014,
      "grad_norm": 0.4695484936237335,
      "learning_rate": 1.0028098127453633e-06,
      "loss": 0.5537,
      "step": 55761
    },
    {
      "epoch": 1.7129604030350505,
      "grad_norm": 0.45359230041503906,
      "learning_rate": 1.0025988873999804e-06,
      "loss": 0.4924,
      "step": 55762
    },
    {
      "epoch": 1.7129911221699996,
      "grad_norm": 0.4656883776187897,
      "learning_rate": 1.0023879830686544e-06,
      "loss": 0.4886,
      "step": 55763
    },
    {
      "epoch": 1.7130218413049487,
      "grad_norm": 0.4187217652797699,
      "learning_rate": 1.0021770997518787e-06,
      "loss": 0.5308,
      "step": 55764
    },
    {
      "epoch": 1.713052560439898,
      "grad_norm": 0.41206684708595276,
      "learning_rate": 1.0019662374501482e-06,
      "loss": 0.5368,
      "step": 55765
    },
    {
      "epoch": 1.7130832795748472,
      "grad_norm": 0.5119408369064331,
      "learning_rate": 1.0017553961639526e-06,
      "loss": 0.5039,
      "step": 55766
    },
    {
      "epoch": 1.7131139987097963,
      "grad_norm": 0.4253191351890564,
      "learning_rate": 1.0015445758937893e-06,
      "loss": 0.411,
      "step": 55767
    },
    {
      "epoch": 1.7131447178447456,
      "grad_norm": 0.4270223379135132,
      "learning_rate": 1.0013337766401432e-06,
      "loss": 0.4559,
      "step": 55768
    },
    {
      "epoch": 1.7131754369796948,
      "grad_norm": 0.42471596598625183,
      "learning_rate": 1.0011229984035142e-06,
      "loss": 0.4098,
      "step": 55769
    },
    {
      "epoch": 1.7132061561146439,
      "grad_norm": 0.4182041883468628,
      "learning_rate": 1.0009122411843864e-06,
      "loss": 0.4389,
      "step": 55770
    },
    {
      "epoch": 1.713236875249593,
      "grad_norm": 0.38055503368377686,
      "learning_rate": 1.0007015049832602e-06,
      "loss": 0.4762,
      "step": 55771
    },
    {
      "epoch": 1.7132675943845421,
      "grad_norm": 0.642672061920166,
      "learning_rate": 1.0004907898006222e-06,
      "loss": 0.5125,
      "step": 55772
    },
    {
      "epoch": 1.7132983135194912,
      "grad_norm": 0.4176807403564453,
      "learning_rate": 1.0002800956369684e-06,
      "loss": 0.4909,
      "step": 55773
    },
    {
      "epoch": 1.7133290326544404,
      "grad_norm": 0.45251917839050293,
      "learning_rate": 1.0000694224927853e-06,
      "loss": 0.5178,
      "step": 55774
    },
    {
      "epoch": 1.7133597517893895,
      "grad_norm": 0.4301658272743225,
      "learning_rate": 9.998587703685725e-07,
      "loss": 0.5495,
      "step": 55775
    },
    {
      "epoch": 1.7133904709243386,
      "grad_norm": 0.4466797411441803,
      "learning_rate": 9.996481392648161e-07,
      "loss": 0.5046,
      "step": 55776
    },
    {
      "epoch": 1.713421190059288,
      "grad_norm": 0.7003416419029236,
      "learning_rate": 9.994375291820113e-07,
      "loss": 0.4775,
      "step": 55777
    },
    {
      "epoch": 1.713451909194237,
      "grad_norm": 0.44535911083221436,
      "learning_rate": 9.992269401206478e-07,
      "loss": 0.5042,
      "step": 55778
    },
    {
      "epoch": 1.7134826283291864,
      "grad_norm": 0.46138134598731995,
      "learning_rate": 9.990163720812186e-07,
      "loss": 0.4536,
      "step": 55779
    },
    {
      "epoch": 1.7135133474641355,
      "grad_norm": 0.4448094069957733,
      "learning_rate": 9.988058250642141e-07,
      "loss": 0.4999,
      "step": 55780
    },
    {
      "epoch": 1.7135440665990846,
      "grad_norm": 0.4304054379463196,
      "learning_rate": 9.985952990701297e-07,
      "loss": 0.4595,
      "step": 55781
    },
    {
      "epoch": 1.7135747857340338,
      "grad_norm": 0.43340009450912476,
      "learning_rate": 9.983847940994528e-07,
      "loss": 0.4584,
      "step": 55782
    },
    {
      "epoch": 1.7136055048689829,
      "grad_norm": 0.5520992279052734,
      "learning_rate": 9.981743101526775e-07,
      "loss": 0.4274,
      "step": 55783
    },
    {
      "epoch": 1.713636224003932,
      "grad_norm": 0.46988123655319214,
      "learning_rate": 9.979638472302943e-07,
      "loss": 0.475,
      "step": 55784
    },
    {
      "epoch": 1.7136669431388811,
      "grad_norm": 0.4421137869358063,
      "learning_rate": 9.977534053327942e-07,
      "loss": 0.3969,
      "step": 55785
    },
    {
      "epoch": 1.7136976622738302,
      "grad_norm": 0.4291836619377136,
      "learning_rate": 9.975429844606733e-07,
      "loss": 0.4609,
      "step": 55786
    },
    {
      "epoch": 1.7137283814087794,
      "grad_norm": 0.46565955877304077,
      "learning_rate": 9.973325846144165e-07,
      "loss": 0.5313,
      "step": 55787
    },
    {
      "epoch": 1.7137591005437287,
      "grad_norm": 0.4835379421710968,
      "learning_rate": 9.971222057945185e-07,
      "loss": 0.4989,
      "step": 55788
    },
    {
      "epoch": 1.7137898196786778,
      "grad_norm": 0.45487499237060547,
      "learning_rate": 9.969118480014706e-07,
      "loss": 0.484,
      "step": 55789
    },
    {
      "epoch": 1.7138205388136272,
      "grad_norm": 0.4824235141277313,
      "learning_rate": 9.967015112357648e-07,
      "loss": 0.4811,
      "step": 55790
    },
    {
      "epoch": 1.7138512579485763,
      "grad_norm": 0.46947428584098816,
      "learning_rate": 9.964911954978907e-07,
      "loss": 0.5533,
      "step": 55791
    },
    {
      "epoch": 1.7138819770835254,
      "grad_norm": 0.46201640367507935,
      "learning_rate": 9.9628090078834e-07,
      "loss": 0.4742,
      "step": 55792
    },
    {
      "epoch": 1.7139126962184745,
      "grad_norm": 0.461241751909256,
      "learning_rate": 9.960706271076036e-07,
      "loss": 0.5173,
      "step": 55793
    },
    {
      "epoch": 1.7139434153534236,
      "grad_norm": 0.4649331569671631,
      "learning_rate": 9.958603744561746e-07,
      "loss": 0.4702,
      "step": 55794
    },
    {
      "epoch": 1.7139741344883728,
      "grad_norm": 0.5388139486312866,
      "learning_rate": 9.956501428345422e-07,
      "loss": 0.4186,
      "step": 55795
    },
    {
      "epoch": 1.714004853623322,
      "grad_norm": 0.4356144070625305,
      "learning_rate": 9.954399322431963e-07,
      "loss": 0.4603,
      "step": 55796
    },
    {
      "epoch": 1.714035572758271,
      "grad_norm": 0.42023104429244995,
      "learning_rate": 9.952297426826297e-07,
      "loss": 0.4563,
      "step": 55797
    },
    {
      "epoch": 1.7140662918932201,
      "grad_norm": 0.4360480010509491,
      "learning_rate": 9.950195741533353e-07,
      "loss": 0.4151,
      "step": 55798
    },
    {
      "epoch": 1.7140970110281695,
      "grad_norm": 0.4141336679458618,
      "learning_rate": 9.948094266557984e-07,
      "loss": 0.3918,
      "step": 55799
    },
    {
      "epoch": 1.7141277301631186,
      "grad_norm": 0.4759990870952606,
      "learning_rate": 9.94599300190514e-07,
      "loss": 0.5325,
      "step": 55800
    },
    {
      "epoch": 1.714158449298068,
      "grad_norm": 0.4311312735080719,
      "learning_rate": 9.94389194757972e-07,
      "loss": 0.5015,
      "step": 55801
    },
    {
      "epoch": 1.714189168433017,
      "grad_norm": 0.4609455466270447,
      "learning_rate": 9.94179110358663e-07,
      "loss": 0.4927,
      "step": 55802
    },
    {
      "epoch": 1.7142198875679662,
      "grad_norm": 0.4433959722518921,
      "learning_rate": 9.939690469930785e-07,
      "loss": 0.4142,
      "step": 55803
    },
    {
      "epoch": 1.7142506067029153,
      "grad_norm": 0.41632306575775146,
      "learning_rate": 9.937590046617073e-07,
      "loss": 0.455,
      "step": 55804
    },
    {
      "epoch": 1.7142813258378644,
      "grad_norm": 0.4567614197731018,
      "learning_rate": 9.935489833650424e-07,
      "loss": 0.4741,
      "step": 55805
    },
    {
      "epoch": 1.7143120449728135,
      "grad_norm": 0.4197867214679718,
      "learning_rate": 9.9333898310357e-07,
      "loss": 0.5715,
      "step": 55806
    },
    {
      "epoch": 1.7143427641077627,
      "grad_norm": 0.45824477076530457,
      "learning_rate": 9.931290038777863e-07,
      "loss": 0.5053,
      "step": 55807
    },
    {
      "epoch": 1.7143734832427118,
      "grad_norm": 0.40904903411865234,
      "learning_rate": 9.929190456881776e-07,
      "loss": 0.4434,
      "step": 55808
    },
    {
      "epoch": 1.714404202377661,
      "grad_norm": 0.4456086754798889,
      "learning_rate": 9.92709108535237e-07,
      "loss": 0.5344,
      "step": 55809
    },
    {
      "epoch": 1.7144349215126102,
      "grad_norm": 0.4066484570503235,
      "learning_rate": 9.924991924194493e-07,
      "loss": 0.4767,
      "step": 55810
    },
    {
      "epoch": 1.7144656406475594,
      "grad_norm": 0.48728853464126587,
      "learning_rate": 9.922892973413124e-07,
      "loss": 0.4958,
      "step": 55811
    },
    {
      "epoch": 1.7144963597825085,
      "grad_norm": 0.43108606338500977,
      "learning_rate": 9.92079423301312e-07,
      "loss": 0.4849,
      "step": 55812
    },
    {
      "epoch": 1.7145270789174578,
      "grad_norm": 0.4115232229232788,
      "learning_rate": 9.918695702999404e-07,
      "loss": 0.4331,
      "step": 55813
    },
    {
      "epoch": 1.714557798052407,
      "grad_norm": 0.4802602231502533,
      "learning_rate": 9.916597383376847e-07,
      "loss": 0.4568,
      "step": 55814
    },
    {
      "epoch": 1.714588517187356,
      "grad_norm": 0.4542880952358246,
      "learning_rate": 9.91449927415037e-07,
      "loss": 0.3723,
      "step": 55815
    },
    {
      "epoch": 1.7146192363223052,
      "grad_norm": 0.4258789122104645,
      "learning_rate": 9.912401375324866e-07,
      "loss": 0.5136,
      "step": 55816
    },
    {
      "epoch": 1.7146499554572543,
      "grad_norm": 0.4513739347457886,
      "learning_rate": 9.910303686905264e-07,
      "loss": 0.4215,
      "step": 55817
    },
    {
      "epoch": 1.7146806745922034,
      "grad_norm": 0.436970591545105,
      "learning_rate": 9.90820620889642e-07,
      "loss": 0.5473,
      "step": 55818
    },
    {
      "epoch": 1.7147113937271525,
      "grad_norm": 0.4013786017894745,
      "learning_rate": 9.90610894130326e-07,
      "loss": 0.4156,
      "step": 55819
    },
    {
      "epoch": 1.7147421128621017,
      "grad_norm": 0.42836451530456543,
      "learning_rate": 9.90401188413067e-07,
      "loss": 0.4612,
      "step": 55820
    },
    {
      "epoch": 1.714772831997051,
      "grad_norm": 0.4499600827693939,
      "learning_rate": 9.901915037383547e-07,
      "loss": 0.4432,
      "step": 55821
    },
    {
      "epoch": 1.7148035511320001,
      "grad_norm": 0.44242340326309204,
      "learning_rate": 9.89981840106682e-07,
      "loss": 0.4933,
      "step": 55822
    },
    {
      "epoch": 1.7148342702669492,
      "grad_norm": 0.4140161871910095,
      "learning_rate": 9.897721975185327e-07,
      "loss": 0.4793,
      "step": 55823
    },
    {
      "epoch": 1.7148649894018986,
      "grad_norm": 0.43793025612831116,
      "learning_rate": 9.89562575974401e-07,
      "loss": 0.5134,
      "step": 55824
    },
    {
      "epoch": 1.7148957085368477,
      "grad_norm": 0.5190007090568542,
      "learning_rate": 9.893529754747745e-07,
      "loss": 0.4777,
      "step": 55825
    },
    {
      "epoch": 1.7149264276717968,
      "grad_norm": 0.46654972434043884,
      "learning_rate": 9.891433960201457e-07,
      "loss": 0.434,
      "step": 55826
    },
    {
      "epoch": 1.714957146806746,
      "grad_norm": 0.4778834581375122,
      "learning_rate": 9.889338376110002e-07,
      "loss": 0.459,
      "step": 55827
    },
    {
      "epoch": 1.714987865941695,
      "grad_norm": 0.4251505136489868,
      "learning_rate": 9.887243002478287e-07,
      "loss": 0.4585,
      "step": 55828
    },
    {
      "epoch": 1.7150185850766442,
      "grad_norm": 0.46670085191726685,
      "learning_rate": 9.885147839311216e-07,
      "loss": 0.4004,
      "step": 55829
    },
    {
      "epoch": 1.7150493042115933,
      "grad_norm": 0.4434534013271332,
      "learning_rate": 9.883052886613687e-07,
      "loss": 0.4873,
      "step": 55830
    },
    {
      "epoch": 1.7150800233465424,
      "grad_norm": 0.4665859043598175,
      "learning_rate": 9.880958144390563e-07,
      "loss": 0.4455,
      "step": 55831
    },
    {
      "epoch": 1.7151107424814918,
      "grad_norm": 0.4397948682308197,
      "learning_rate": 9.87886361264675e-07,
      "loss": 0.5914,
      "step": 55832
    },
    {
      "epoch": 1.7151414616164409,
      "grad_norm": 0.3878130316734314,
      "learning_rate": 9.876769291387156e-07,
      "loss": 0.4528,
      "step": 55833
    },
    {
      "epoch": 1.71517218075139,
      "grad_norm": 0.41905736923217773,
      "learning_rate": 9.874675180616678e-07,
      "loss": 0.4641,
      "step": 55834
    },
    {
      "epoch": 1.7152028998863393,
      "grad_norm": 0.44116082787513733,
      "learning_rate": 9.872581280340166e-07,
      "loss": 0.4162,
      "step": 55835
    },
    {
      "epoch": 1.7152336190212885,
      "grad_norm": 0.4209952652454376,
      "learning_rate": 9.87048759056256e-07,
      "loss": 0.492,
      "step": 55836
    },
    {
      "epoch": 1.7152643381562376,
      "grad_norm": 0.5099069476127625,
      "learning_rate": 9.868394111288682e-07,
      "loss": 0.4733,
      "step": 55837
    },
    {
      "epoch": 1.7152950572911867,
      "grad_norm": 0.5119954943656921,
      "learning_rate": 9.86630084252348e-07,
      "loss": 0.5913,
      "step": 55838
    },
    {
      "epoch": 1.7153257764261358,
      "grad_norm": 0.45864352583885193,
      "learning_rate": 9.864207784271852e-07,
      "loss": 0.5058,
      "step": 55839
    },
    {
      "epoch": 1.715356495561085,
      "grad_norm": 0.439619779586792,
      "learning_rate": 9.862114936538646e-07,
      "loss": 0.4267,
      "step": 55840
    },
    {
      "epoch": 1.715387214696034,
      "grad_norm": 0.45129379630088806,
      "learning_rate": 9.860022299328775e-07,
      "loss": 0.4905,
      "step": 55841
    },
    {
      "epoch": 1.7154179338309832,
      "grad_norm": 0.41390344500541687,
      "learning_rate": 9.857929872647088e-07,
      "loss": 0.4274,
      "step": 55842
    },
    {
      "epoch": 1.7154486529659325,
      "grad_norm": 0.4655487537384033,
      "learning_rate": 9.855837656498534e-07,
      "loss": 0.4385,
      "step": 55843
    },
    {
      "epoch": 1.7154793721008816,
      "grad_norm": 0.4402012228965759,
      "learning_rate": 9.853745650887948e-07,
      "loss": 0.5305,
      "step": 55844
    },
    {
      "epoch": 1.7155100912358308,
      "grad_norm": 0.43179965019226074,
      "learning_rate": 9.851653855820264e-07,
      "loss": 0.4137,
      "step": 55845
    },
    {
      "epoch": 1.71554081037078,
      "grad_norm": 0.4910229742527008,
      "learning_rate": 9.849562271300306e-07,
      "loss": 0.4026,
      "step": 55846
    },
    {
      "epoch": 1.7155715295057292,
      "grad_norm": 0.490064799785614,
      "learning_rate": 9.847470897333e-07,
      "loss": 0.468,
      "step": 55847
    },
    {
      "epoch": 1.7156022486406783,
      "grad_norm": 0.46987348794937134,
      "learning_rate": 9.84537973392321e-07,
      "loss": 0.4423,
      "step": 55848
    },
    {
      "epoch": 1.7156329677756275,
      "grad_norm": 0.44755178689956665,
      "learning_rate": 9.843288781075865e-07,
      "loss": 0.4592,
      "step": 55849
    },
    {
      "epoch": 1.7156636869105766,
      "grad_norm": 0.5298498868942261,
      "learning_rate": 9.841198038795785e-07,
      "loss": 0.4724,
      "step": 55850
    },
    {
      "epoch": 1.7156944060455257,
      "grad_norm": 0.3994385600090027,
      "learning_rate": 9.839107507087898e-07,
      "loss": 0.4148,
      "step": 55851
    },
    {
      "epoch": 1.7157251251804748,
      "grad_norm": 0.4173738956451416,
      "learning_rate": 9.837017185957054e-07,
      "loss": 0.4532,
      "step": 55852
    },
    {
      "epoch": 1.715755844315424,
      "grad_norm": 0.3921709656715393,
      "learning_rate": 9.834927075408186e-07,
      "loss": 0.5078,
      "step": 55853
    },
    {
      "epoch": 1.7157865634503733,
      "grad_norm": 0.4112556278705597,
      "learning_rate": 9.83283717544612e-07,
      "loss": 0.4911,
      "step": 55854
    },
    {
      "epoch": 1.7158172825853224,
      "grad_norm": 0.44161683320999146,
      "learning_rate": 9.830747486075764e-07,
      "loss": 0.4432,
      "step": 55855
    },
    {
      "epoch": 1.7158480017202715,
      "grad_norm": 0.39358577132225037,
      "learning_rate": 9.828658007301983e-07,
      "loss": 0.4849,
      "step": 55856
    },
    {
      "epoch": 1.7158787208552209,
      "grad_norm": 0.4998224675655365,
      "learning_rate": 9.826568739129682e-07,
      "loss": 0.4757,
      "step": 55857
    },
    {
      "epoch": 1.71590943999017,
      "grad_norm": 0.4440845251083374,
      "learning_rate": 9.824479681563738e-07,
      "loss": 0.4748,
      "step": 55858
    },
    {
      "epoch": 1.715940159125119,
      "grad_norm": 0.4074428081512451,
      "learning_rate": 9.822390834608997e-07,
      "loss": 0.4498,
      "step": 55859
    },
    {
      "epoch": 1.7159708782600682,
      "grad_norm": 0.5502120852470398,
      "learning_rate": 9.820302198270372e-07,
      "loss": 0.4931,
      "step": 55860
    },
    {
      "epoch": 1.7160015973950173,
      "grad_norm": 0.41959571838378906,
      "learning_rate": 9.81821377255272e-07,
      "loss": 0.5148,
      "step": 55861
    },
    {
      "epoch": 1.7160323165299665,
      "grad_norm": 0.46940553188323975,
      "learning_rate": 9.816125557460954e-07,
      "loss": 0.4902,
      "step": 55862
    },
    {
      "epoch": 1.7160630356649156,
      "grad_norm": 0.4619532525539398,
      "learning_rate": 9.8140375529999e-07,
      "loss": 0.5047,
      "step": 55863
    },
    {
      "epoch": 1.7160937547998647,
      "grad_norm": 0.46695488691329956,
      "learning_rate": 9.811949759174467e-07,
      "loss": 0.4633,
      "step": 55864
    },
    {
      "epoch": 1.716124473934814,
      "grad_norm": 0.4276665449142456,
      "learning_rate": 9.809862175989515e-07,
      "loss": 0.5186,
      "step": 55865
    },
    {
      "epoch": 1.7161551930697632,
      "grad_norm": 0.38336870074272156,
      "learning_rate": 9.807774803449955e-07,
      "loss": 0.4345,
      "step": 55866
    },
    {
      "epoch": 1.7161859122047123,
      "grad_norm": 0.43529167771339417,
      "learning_rate": 9.805687641560613e-07,
      "loss": 0.4423,
      "step": 55867
    },
    {
      "epoch": 1.7162166313396616,
      "grad_norm": 0.503848135471344,
      "learning_rate": 9.803600690326398e-07,
      "loss": 0.4322,
      "step": 55868
    },
    {
      "epoch": 1.7162473504746107,
      "grad_norm": 0.4126688241958618,
      "learning_rate": 9.80151394975215e-07,
      "loss": 0.4798,
      "step": 55869
    },
    {
      "epoch": 1.7162780696095599,
      "grad_norm": 0.45008334517478943,
      "learning_rate": 9.799427419842799e-07,
      "loss": 0.4764,
      "step": 55870
    },
    {
      "epoch": 1.716308788744509,
      "grad_norm": 0.43975892663002014,
      "learning_rate": 9.797341100603163e-07,
      "loss": 0.5233,
      "step": 55871
    },
    {
      "epoch": 1.716339507879458,
      "grad_norm": 0.5112027525901794,
      "learning_rate": 9.79525499203815e-07,
      "loss": 0.437,
      "step": 55872
    },
    {
      "epoch": 1.7163702270144072,
      "grad_norm": 0.43119505047798157,
      "learning_rate": 9.793169094152589e-07,
      "loss": 0.5134,
      "step": 55873
    },
    {
      "epoch": 1.7164009461493563,
      "grad_norm": 0.3768460750579834,
      "learning_rate": 9.791083406951397e-07,
      "loss": 0.416,
      "step": 55874
    },
    {
      "epoch": 1.7164316652843055,
      "grad_norm": 0.4397483468055725,
      "learning_rate": 9.788997930439448e-07,
      "loss": 0.4899,
      "step": 55875
    },
    {
      "epoch": 1.7164623844192548,
      "grad_norm": 0.4619245231151581,
      "learning_rate": 9.786912664621585e-07,
      "loss": 0.501,
      "step": 55876
    },
    {
      "epoch": 1.716493103554204,
      "grad_norm": 0.4535577893257141,
      "learning_rate": 9.784827609502701e-07,
      "loss": 0.4825,
      "step": 55877
    },
    {
      "epoch": 1.716523822689153,
      "grad_norm": 0.485226035118103,
      "learning_rate": 9.782742765087605e-07,
      "loss": 0.5122,
      "step": 55878
    },
    {
      "epoch": 1.7165545418241024,
      "grad_norm": 0.4234246015548706,
      "learning_rate": 9.78065813138126e-07,
      "loss": 0.4012,
      "step": 55879
    },
    {
      "epoch": 1.7165852609590515,
      "grad_norm": 0.40609726309776306,
      "learning_rate": 9.778573708388472e-07,
      "loss": 0.4684,
      "step": 55880
    },
    {
      "epoch": 1.7166159800940006,
      "grad_norm": 0.4548516869544983,
      "learning_rate": 9.77648949611414e-07,
      "loss": 0.5023,
      "step": 55881
    },
    {
      "epoch": 1.7166466992289497,
      "grad_norm": 0.4225795865058899,
      "learning_rate": 9.77440549456311e-07,
      "loss": 0.4837,
      "step": 55882
    },
    {
      "epoch": 1.7166774183638989,
      "grad_norm": 0.48174065351486206,
      "learning_rate": 9.772321703740251e-07,
      "loss": 0.427,
      "step": 55883
    },
    {
      "epoch": 1.716708137498848,
      "grad_norm": 0.4549664258956909,
      "learning_rate": 9.770238123650434e-07,
      "loss": 0.5013,
      "step": 55884
    },
    {
      "epoch": 1.716738856633797,
      "grad_norm": 0.4185384213924408,
      "learning_rate": 9.768154754298542e-07,
      "loss": 0.4279,
      "step": 55885
    },
    {
      "epoch": 1.7167695757687462,
      "grad_norm": 0.48244088888168335,
      "learning_rate": 9.766071595689407e-07,
      "loss": 0.4247,
      "step": 55886
    },
    {
      "epoch": 1.7168002949036956,
      "grad_norm": 0.442984402179718,
      "learning_rate": 9.763988647827927e-07,
      "loss": 0.5711,
      "step": 55887
    },
    {
      "epoch": 1.7168310140386447,
      "grad_norm": 0.4092586636543274,
      "learning_rate": 9.761905910718938e-07,
      "loss": 0.4916,
      "step": 55888
    },
    {
      "epoch": 1.7168617331735938,
      "grad_norm": 0.4175417721271515,
      "learning_rate": 9.75982338436735e-07,
      "loss": 0.5299,
      "step": 55889
    },
    {
      "epoch": 1.7168924523085431,
      "grad_norm": 0.4418193995952606,
      "learning_rate": 9.75774106877797e-07,
      "loss": 0.4669,
      "step": 55890
    },
    {
      "epoch": 1.7169231714434923,
      "grad_norm": 0.4258750081062317,
      "learning_rate": 9.755658963955695e-07,
      "loss": 0.4413,
      "step": 55891
    },
    {
      "epoch": 1.7169538905784414,
      "grad_norm": 0.4329507648944855,
      "learning_rate": 9.753577069905384e-07,
      "loss": 0.4775,
      "step": 55892
    },
    {
      "epoch": 1.7169846097133905,
      "grad_norm": 0.45120754837989807,
      "learning_rate": 9.751495386631882e-07,
      "loss": 0.4543,
      "step": 55893
    },
    {
      "epoch": 1.7170153288483396,
      "grad_norm": 0.4256492257118225,
      "learning_rate": 9.749413914140093e-07,
      "loss": 0.4467,
      "step": 55894
    },
    {
      "epoch": 1.7170460479832887,
      "grad_norm": 0.444472074508667,
      "learning_rate": 9.747332652434837e-07,
      "loss": 0.4471,
      "step": 55895
    },
    {
      "epoch": 1.7170767671182379,
      "grad_norm": 0.42934510111808777,
      "learning_rate": 9.745251601520978e-07,
      "loss": 0.4119,
      "step": 55896
    },
    {
      "epoch": 1.717107486253187,
      "grad_norm": 0.411590039730072,
      "learning_rate": 9.743170761403398e-07,
      "loss": 0.4286,
      "step": 55897
    },
    {
      "epoch": 1.717138205388136,
      "grad_norm": 0.4560769200325012,
      "learning_rate": 9.74109013208696e-07,
      "loss": 0.5612,
      "step": 55898
    },
    {
      "epoch": 1.7171689245230854,
      "grad_norm": 0.4295481741428375,
      "learning_rate": 9.739009713576486e-07,
      "loss": 0.4568,
      "step": 55899
    },
    {
      "epoch": 1.7171996436580346,
      "grad_norm": 0.4505360722541809,
      "learning_rate": 9.736929505876869e-07,
      "loss": 0.4274,
      "step": 55900
    },
    {
      "epoch": 1.717230362792984,
      "grad_norm": 0.43862318992614746,
      "learning_rate": 9.73484950899295e-07,
      "loss": 0.4266,
      "step": 55901
    },
    {
      "epoch": 1.717261081927933,
      "grad_norm": 0.4144267439842224,
      "learning_rate": 9.732769722929613e-07,
      "loss": 0.439,
      "step": 55902
    },
    {
      "epoch": 1.7172918010628822,
      "grad_norm": 0.4445706903934479,
      "learning_rate": 9.730690147691678e-07,
      "loss": 0.4377,
      "step": 55903
    },
    {
      "epoch": 1.7173225201978313,
      "grad_norm": 0.4217587113380432,
      "learning_rate": 9.728610783284043e-07,
      "loss": 0.4634,
      "step": 55904
    },
    {
      "epoch": 1.7173532393327804,
      "grad_norm": 0.46939247846603394,
      "learning_rate": 9.7265316297115e-07,
      "loss": 0.4679,
      "step": 55905
    },
    {
      "epoch": 1.7173839584677295,
      "grad_norm": 0.701148271560669,
      "learning_rate": 9.724452686978991e-07,
      "loss": 0.4383,
      "step": 55906
    },
    {
      "epoch": 1.7174146776026786,
      "grad_norm": 0.4484589695930481,
      "learning_rate": 9.722373955091301e-07,
      "loss": 0.4153,
      "step": 55907
    },
    {
      "epoch": 1.7174453967376277,
      "grad_norm": 0.42116227746009827,
      "learning_rate": 9.720295434053329e-07,
      "loss": 0.5114,
      "step": 55908
    },
    {
      "epoch": 1.7174761158725769,
      "grad_norm": 0.4180029332637787,
      "learning_rate": 9.7182171238699e-07,
      "loss": 0.3993,
      "step": 55909
    },
    {
      "epoch": 1.7175068350075262,
      "grad_norm": 0.44457539916038513,
      "learning_rate": 9.716139024545856e-07,
      "loss": 0.4049,
      "step": 55910
    },
    {
      "epoch": 1.7175375541424753,
      "grad_norm": 0.450751930475235,
      "learning_rate": 9.714061136086118e-07,
      "loss": 0.5045,
      "step": 55911
    },
    {
      "epoch": 1.7175682732774247,
      "grad_norm": 0.4280439615249634,
      "learning_rate": 9.711983458495477e-07,
      "loss": 0.567,
      "step": 55912
    },
    {
      "epoch": 1.7175989924123738,
      "grad_norm": 0.40127283334732056,
      "learning_rate": 9.709905991778822e-07,
      "loss": 0.527,
      "step": 55913
    },
    {
      "epoch": 1.717629711547323,
      "grad_norm": 0.42399898171424866,
      "learning_rate": 9.707828735940938e-07,
      "loss": 0.5287,
      "step": 55914
    },
    {
      "epoch": 1.717660430682272,
      "grad_norm": 0.48810628056526184,
      "learning_rate": 9.705751690986775e-07,
      "loss": 0.4385,
      "step": 55915
    },
    {
      "epoch": 1.7176911498172212,
      "grad_norm": 0.4518861174583435,
      "learning_rate": 9.703674856921118e-07,
      "loss": 0.517,
      "step": 55916
    },
    {
      "epoch": 1.7177218689521703,
      "grad_norm": 0.4233321249485016,
      "learning_rate": 9.701598233748854e-07,
      "loss": 0.4968,
      "step": 55917
    },
    {
      "epoch": 1.7177525880871194,
      "grad_norm": 0.44125276803970337,
      "learning_rate": 9.699521821474788e-07,
      "loss": 0.4504,
      "step": 55918
    },
    {
      "epoch": 1.7177833072220685,
      "grad_norm": 0.4677492082118988,
      "learning_rate": 9.697445620103796e-07,
      "loss": 0.4515,
      "step": 55919
    },
    {
      "epoch": 1.7178140263570176,
      "grad_norm": 0.44820261001586914,
      "learning_rate": 9.695369629640728e-07,
      "loss": 0.4652,
      "step": 55920
    },
    {
      "epoch": 1.717844745491967,
      "grad_norm": 0.42889609932899475,
      "learning_rate": 9.693293850090456e-07,
      "loss": 0.4786,
      "step": 55921
    },
    {
      "epoch": 1.717875464626916,
      "grad_norm": 0.4073363244533539,
      "learning_rate": 9.69121828145777e-07,
      "loss": 0.4985,
      "step": 55922
    },
    {
      "epoch": 1.7179061837618652,
      "grad_norm": 0.5419797301292419,
      "learning_rate": 9.689142923747563e-07,
      "loss": 0.4925,
      "step": 55923
    },
    {
      "epoch": 1.7179369028968146,
      "grad_norm": 0.4380784034729004,
      "learning_rate": 9.687067776964665e-07,
      "loss": 0.4895,
      "step": 55924
    },
    {
      "epoch": 1.7179676220317637,
      "grad_norm": 0.44655030965805054,
      "learning_rate": 9.684992841113949e-07,
      "loss": 0.5027,
      "step": 55925
    },
    {
      "epoch": 1.7179983411667128,
      "grad_norm": 0.4315391480922699,
      "learning_rate": 9.682918116200223e-07,
      "loss": 0.4945,
      "step": 55926
    },
    {
      "epoch": 1.718029060301662,
      "grad_norm": 0.42361146211624146,
      "learning_rate": 9.68084360222834e-07,
      "loss": 0.4549,
      "step": 55927
    },
    {
      "epoch": 1.718059779436611,
      "grad_norm": 0.5025429129600525,
      "learning_rate": 9.67876929920316e-07,
      "loss": 0.4738,
      "step": 55928
    },
    {
      "epoch": 1.7180904985715602,
      "grad_norm": 0.5233994126319885,
      "learning_rate": 9.676695207129528e-07,
      "loss": 0.3853,
      "step": 55929
    },
    {
      "epoch": 1.7181212177065093,
      "grad_norm": 0.4348772168159485,
      "learning_rate": 9.6746213260123e-07,
      "loss": 0.3937,
      "step": 55930
    },
    {
      "epoch": 1.7181519368414584,
      "grad_norm": 0.4842880368232727,
      "learning_rate": 9.67254765585628e-07,
      "loss": 0.5181,
      "step": 55931
    },
    {
      "epoch": 1.7181826559764077,
      "grad_norm": 0.4603150188922882,
      "learning_rate": 9.670474196666335e-07,
      "loss": 0.4796,
      "step": 55932
    },
    {
      "epoch": 1.7182133751113569,
      "grad_norm": 0.44489747285842896,
      "learning_rate": 9.668400948447298e-07,
      "loss": 0.4951,
      "step": 55933
    },
    {
      "epoch": 1.718244094246306,
      "grad_norm": 0.5577574372291565,
      "learning_rate": 9.666327911204043e-07,
      "loss": 0.4648,
      "step": 55934
    },
    {
      "epoch": 1.7182748133812553,
      "grad_norm": 0.4472386837005615,
      "learning_rate": 9.664255084941376e-07,
      "loss": 0.5166,
      "step": 55935
    },
    {
      "epoch": 1.7183055325162044,
      "grad_norm": 0.44849827885627747,
      "learning_rate": 9.662182469664138e-07,
      "loss": 0.3825,
      "step": 55936
    },
    {
      "epoch": 1.7183362516511536,
      "grad_norm": 0.4168699383735657,
      "learning_rate": 9.660110065377192e-07,
      "loss": 0.4697,
      "step": 55937
    },
    {
      "epoch": 1.7183669707861027,
      "grad_norm": 0.40355709195137024,
      "learning_rate": 9.65803787208538e-07,
      "loss": 0.4643,
      "step": 55938
    },
    {
      "epoch": 1.7183976899210518,
      "grad_norm": 0.45337972044944763,
      "learning_rate": 9.655965889793518e-07,
      "loss": 0.4675,
      "step": 55939
    },
    {
      "epoch": 1.718428409056001,
      "grad_norm": 0.4849078357219696,
      "learning_rate": 9.653894118506467e-07,
      "loss": 0.4649,
      "step": 55940
    },
    {
      "epoch": 1.71845912819095,
      "grad_norm": 0.47887057065963745,
      "learning_rate": 9.651822558229029e-07,
      "loss": 0.4177,
      "step": 55941
    },
    {
      "epoch": 1.7184898473258992,
      "grad_norm": 0.43182024359703064,
      "learning_rate": 9.649751208966107e-07,
      "loss": 0.4825,
      "step": 55942
    },
    {
      "epoch": 1.7185205664608485,
      "grad_norm": 0.5262570381164551,
      "learning_rate": 9.647680070722476e-07,
      "loss": 0.5292,
      "step": 55943
    },
    {
      "epoch": 1.7185512855957976,
      "grad_norm": 0.4072705805301666,
      "learning_rate": 9.64560914350302e-07,
      "loss": 0.4653,
      "step": 55944
    },
    {
      "epoch": 1.7185820047307467,
      "grad_norm": 0.4510751962661743,
      "learning_rate": 9.643538427312527e-07,
      "loss": 0.4016,
      "step": 55945
    },
    {
      "epoch": 1.718612723865696,
      "grad_norm": 0.4505249857902527,
      "learning_rate": 9.641467922155844e-07,
      "loss": 0.481,
      "step": 55946
    },
    {
      "epoch": 1.7186434430006452,
      "grad_norm": 0.4269247055053711,
      "learning_rate": 9.639397628037873e-07,
      "loss": 0.4978,
      "step": 55947
    },
    {
      "epoch": 1.7186741621355943,
      "grad_norm": 0.44513943791389465,
      "learning_rate": 9.637327544963372e-07,
      "loss": 0.4245,
      "step": 55948
    },
    {
      "epoch": 1.7187048812705434,
      "grad_norm": 0.47409480810165405,
      "learning_rate": 9.635257672937226e-07,
      "loss": 0.4366,
      "step": 55949
    },
    {
      "epoch": 1.7187356004054926,
      "grad_norm": 0.4611363112926483,
      "learning_rate": 9.633188011964224e-07,
      "loss": 0.4796,
      "step": 55950
    },
    {
      "epoch": 1.7187663195404417,
      "grad_norm": 0.4223473370075226,
      "learning_rate": 9.631118562049224e-07,
      "loss": 0.4691,
      "step": 55951
    },
    {
      "epoch": 1.7187970386753908,
      "grad_norm": 0.43057823181152344,
      "learning_rate": 9.62904932319706e-07,
      "loss": 0.5007,
      "step": 55952
    },
    {
      "epoch": 1.71882775781034,
      "grad_norm": 0.49742066860198975,
      "learning_rate": 9.626980295412569e-07,
      "loss": 0.4514,
      "step": 55953
    },
    {
      "epoch": 1.7188584769452893,
      "grad_norm": 0.7542693614959717,
      "learning_rate": 9.62491147870057e-07,
      "loss": 0.4481,
      "step": 55954
    },
    {
      "epoch": 1.7188891960802384,
      "grad_norm": 0.40627196431159973,
      "learning_rate": 9.622842873065907e-07,
      "loss": 0.4534,
      "step": 55955
    },
    {
      "epoch": 1.7189199152151875,
      "grad_norm": 0.42510953545570374,
      "learning_rate": 9.620774478513396e-07,
      "loss": 0.3972,
      "step": 55956
    },
    {
      "epoch": 1.7189506343501368,
      "grad_norm": 0.44881725311279297,
      "learning_rate": 9.618706295047896e-07,
      "loss": 0.4541,
      "step": 55957
    },
    {
      "epoch": 1.718981353485086,
      "grad_norm": 0.426829069852829,
      "learning_rate": 9.61663832267421e-07,
      "loss": 0.4152,
      "step": 55958
    },
    {
      "epoch": 1.719012072620035,
      "grad_norm": 0.4443439245223999,
      "learning_rate": 9.614570561397173e-07,
      "loss": 0.4769,
      "step": 55959
    },
    {
      "epoch": 1.7190427917549842,
      "grad_norm": 0.43154019117355347,
      "learning_rate": 9.612503011221619e-07,
      "loss": 0.4719,
      "step": 55960
    },
    {
      "epoch": 1.7190735108899333,
      "grad_norm": 0.4473344087600708,
      "learning_rate": 9.610435672152397e-07,
      "loss": 0.49,
      "step": 55961
    },
    {
      "epoch": 1.7191042300248824,
      "grad_norm": 0.45575273036956787,
      "learning_rate": 9.608368544194292e-07,
      "loss": 0.5061,
      "step": 55962
    },
    {
      "epoch": 1.7191349491598316,
      "grad_norm": 0.4019474387168884,
      "learning_rate": 9.606301627352154e-07,
      "loss": 0.381,
      "step": 55963
    },
    {
      "epoch": 1.7191656682947807,
      "grad_norm": 0.5349682569503784,
      "learning_rate": 9.604234921630818e-07,
      "loss": 0.3668,
      "step": 55964
    },
    {
      "epoch": 1.71919638742973,
      "grad_norm": 0.4326830506324768,
      "learning_rate": 9.602168427035109e-07,
      "loss": 0.4401,
      "step": 55965
    },
    {
      "epoch": 1.7192271065646791,
      "grad_norm": 0.4550476670265198,
      "learning_rate": 9.600102143569855e-07,
      "loss": 0.4565,
      "step": 55966
    },
    {
      "epoch": 1.7192578256996283,
      "grad_norm": 0.4583018124103546,
      "learning_rate": 9.598036071239859e-07,
      "loss": 0.4076,
      "step": 55967
    },
    {
      "epoch": 1.7192885448345776,
      "grad_norm": 0.4430977404117584,
      "learning_rate": 9.595970210049977e-07,
      "loss": 0.4997,
      "step": 55968
    },
    {
      "epoch": 1.7193192639695267,
      "grad_norm": 0.4488292336463928,
      "learning_rate": 9.593904560005008e-07,
      "loss": 0.4342,
      "step": 55969
    },
    {
      "epoch": 1.7193499831044758,
      "grad_norm": 0.40779873728752136,
      "learning_rate": 9.591839121109803e-07,
      "loss": 0.501,
      "step": 55970
    },
    {
      "epoch": 1.719380702239425,
      "grad_norm": 0.5347692966461182,
      "learning_rate": 9.58977389336916e-07,
      "loss": 0.4216,
      "step": 55971
    },
    {
      "epoch": 1.719411421374374,
      "grad_norm": 0.4375212490558624,
      "learning_rate": 9.587708876787938e-07,
      "loss": 0.403,
      "step": 55972
    },
    {
      "epoch": 1.7194421405093232,
      "grad_norm": 0.4403313100337982,
      "learning_rate": 9.585644071370893e-07,
      "loss": 0.4504,
      "step": 55973
    },
    {
      "epoch": 1.7194728596442723,
      "grad_norm": 0.47679197788238525,
      "learning_rate": 9.58357947712293e-07,
      "loss": 0.4583,
      "step": 55974
    },
    {
      "epoch": 1.7195035787792214,
      "grad_norm": 0.4163148105144501,
      "learning_rate": 9.58151509404881e-07,
      "loss": 0.482,
      "step": 55975
    },
    {
      "epoch": 1.7195342979141708,
      "grad_norm": 0.44597211480140686,
      "learning_rate": 9.5794509221534e-07,
      "loss": 0.4693,
      "step": 55976
    },
    {
      "epoch": 1.71956501704912,
      "grad_norm": 0.46762147545814514,
      "learning_rate": 9.577386961441459e-07,
      "loss": 0.4695,
      "step": 55977
    },
    {
      "epoch": 1.719595736184069,
      "grad_norm": 0.4782388210296631,
      "learning_rate": 9.575323211917875e-07,
      "loss": 0.4495,
      "step": 55978
    },
    {
      "epoch": 1.7196264553190184,
      "grad_norm": 0.45245295763015747,
      "learning_rate": 9.573259673587432e-07,
      "loss": 0.4889,
      "step": 55979
    },
    {
      "epoch": 1.7196571744539675,
      "grad_norm": 0.43106818199157715,
      "learning_rate": 9.57119634645497e-07,
      "loss": 0.447,
      "step": 55980
    },
    {
      "epoch": 1.7196878935889166,
      "grad_norm": 0.5505599975585938,
      "learning_rate": 9.569133230525273e-07,
      "loss": 0.4589,
      "step": 55981
    },
    {
      "epoch": 1.7197186127238657,
      "grad_norm": 0.405762642621994,
      "learning_rate": 9.567070325803186e-07,
      "loss": 0.4739,
      "step": 55982
    },
    {
      "epoch": 1.7197493318588148,
      "grad_norm": 0.43387460708618164,
      "learning_rate": 9.56500763229351e-07,
      "loss": 0.4179,
      "step": 55983
    },
    {
      "epoch": 1.719780050993764,
      "grad_norm": 0.43250006437301636,
      "learning_rate": 9.56294515000109e-07,
      "loss": 0.4786,
      "step": 55984
    },
    {
      "epoch": 1.719810770128713,
      "grad_norm": 0.4367433190345764,
      "learning_rate": 9.560882878930732e-07,
      "loss": 0.5021,
      "step": 55985
    },
    {
      "epoch": 1.7198414892636622,
      "grad_norm": 0.44271254539489746,
      "learning_rate": 9.558820819087244e-07,
      "loss": 0.473,
      "step": 55986
    },
    {
      "epoch": 1.7198722083986115,
      "grad_norm": 0.5066976547241211,
      "learning_rate": 9.556758970475443e-07,
      "loss": 0.4461,
      "step": 55987
    },
    {
      "epoch": 1.7199029275335607,
      "grad_norm": 0.5295998454093933,
      "learning_rate": 9.554697333100138e-07,
      "loss": 0.5562,
      "step": 55988
    },
    {
      "epoch": 1.7199336466685098,
      "grad_norm": 0.3895791471004486,
      "learning_rate": 9.55263590696618e-07,
      "loss": 0.4534,
      "step": 55989
    },
    {
      "epoch": 1.7199643658034591,
      "grad_norm": 0.43324580788612366,
      "learning_rate": 9.55057469207834e-07,
      "loss": 0.4133,
      "step": 55990
    },
    {
      "epoch": 1.7199950849384082,
      "grad_norm": 0.43861809372901917,
      "learning_rate": 9.548513688441451e-07,
      "loss": 0.4419,
      "step": 55991
    },
    {
      "epoch": 1.7200258040733574,
      "grad_norm": 0.46094006299972534,
      "learning_rate": 9.546452896060322e-07,
      "loss": 0.4685,
      "step": 55992
    },
    {
      "epoch": 1.7200565232083065,
      "grad_norm": 0.4266861379146576,
      "learning_rate": 9.544392314939788e-07,
      "loss": 0.3732,
      "step": 55993
    },
    {
      "epoch": 1.7200872423432556,
      "grad_norm": 0.44352400302886963,
      "learning_rate": 9.542331945084627e-07,
      "loss": 0.4442,
      "step": 55994
    },
    {
      "epoch": 1.7201179614782047,
      "grad_norm": 0.42752307653427124,
      "learning_rate": 9.540271786499654e-07,
      "loss": 0.4662,
      "step": 55995
    },
    {
      "epoch": 1.7201486806131538,
      "grad_norm": 0.44316622614860535,
      "learning_rate": 9.538211839189714e-07,
      "loss": 0.4642,
      "step": 55996
    },
    {
      "epoch": 1.720179399748103,
      "grad_norm": 0.4432021975517273,
      "learning_rate": 9.536152103159602e-07,
      "loss": 0.4741,
      "step": 55997
    },
    {
      "epoch": 1.7202101188830523,
      "grad_norm": 0.4276459813117981,
      "learning_rate": 9.534092578414112e-07,
      "loss": 0.4378,
      "step": 55998
    },
    {
      "epoch": 1.7202408380180014,
      "grad_norm": 0.4625990092754364,
      "learning_rate": 9.532033264958074e-07,
      "loss": 0.5189,
      "step": 55999
    },
    {
      "epoch": 1.7202715571529505,
      "grad_norm": 0.4146014153957367,
      "learning_rate": 9.529974162796274e-07,
      "loss": 0.3847,
      "step": 56000
    },
    {
      "epoch": 1.7203022762879,
      "grad_norm": 6.139970302581787,
      "learning_rate": 9.527915271933553e-07,
      "loss": 0.4139,
      "step": 56001
    },
    {
      "epoch": 1.720332995422849,
      "grad_norm": 0.42454928159713745,
      "learning_rate": 9.525856592374716e-07,
      "loss": 0.3621,
      "step": 56002
    },
    {
      "epoch": 1.7203637145577981,
      "grad_norm": 0.42999744415283203,
      "learning_rate": 9.523798124124539e-07,
      "loss": 0.4238,
      "step": 56003
    },
    {
      "epoch": 1.7203944336927472,
      "grad_norm": 0.4548300504684448,
      "learning_rate": 9.521739867187851e-07,
      "loss": 0.4958,
      "step": 56004
    },
    {
      "epoch": 1.7204251528276964,
      "grad_norm": 0.4470362663269043,
      "learning_rate": 9.519681821569459e-07,
      "loss": 0.4542,
      "step": 56005
    },
    {
      "epoch": 1.7204558719626455,
      "grad_norm": 0.4837168753147125,
      "learning_rate": 9.517623987274194e-07,
      "loss": 0.4443,
      "step": 56006
    },
    {
      "epoch": 1.7204865910975946,
      "grad_norm": 0.4228602647781372,
      "learning_rate": 9.515566364306816e-07,
      "loss": 0.4472,
      "step": 56007
    },
    {
      "epoch": 1.7205173102325437,
      "grad_norm": 0.47417402267456055,
      "learning_rate": 9.513508952672168e-07,
      "loss": 0.4238,
      "step": 56008
    },
    {
      "epoch": 1.7205480293674928,
      "grad_norm": 0.5042754411697388,
      "learning_rate": 9.511451752375001e-07,
      "loss": 0.3873,
      "step": 56009
    },
    {
      "epoch": 1.7205787485024422,
      "grad_norm": 0.43492591381073,
      "learning_rate": 9.509394763420199e-07,
      "loss": 0.4218,
      "step": 56010
    },
    {
      "epoch": 1.7206094676373913,
      "grad_norm": 0.38235244154930115,
      "learning_rate": 9.507337985812504e-07,
      "loss": 0.3981,
      "step": 56011
    },
    {
      "epoch": 1.7206401867723407,
      "grad_norm": 0.45754870772361755,
      "learning_rate": 9.505281419556766e-07,
      "loss": 0.4669,
      "step": 56012
    },
    {
      "epoch": 1.7206709059072898,
      "grad_norm": 0.43482506275177,
      "learning_rate": 9.503225064657739e-07,
      "loss": 0.4901,
      "step": 56013
    },
    {
      "epoch": 1.720701625042239,
      "grad_norm": 0.4429115056991577,
      "learning_rate": 9.501168921120252e-07,
      "loss": 0.535,
      "step": 56014
    },
    {
      "epoch": 1.720732344177188,
      "grad_norm": 0.40155330300331116,
      "learning_rate": 9.4991129889491e-07,
      "loss": 0.5809,
      "step": 56015
    },
    {
      "epoch": 1.7207630633121371,
      "grad_norm": 0.4310895502567291,
      "learning_rate": 9.497057268149112e-07,
      "loss": 0.4882,
      "step": 56016
    },
    {
      "epoch": 1.7207937824470863,
      "grad_norm": 0.4282985031604767,
      "learning_rate": 9.495001758725053e-07,
      "loss": 0.4805,
      "step": 56017
    },
    {
      "epoch": 1.7208245015820354,
      "grad_norm": 0.43860989809036255,
      "learning_rate": 9.492946460681729e-07,
      "loss": 0.5397,
      "step": 56018
    },
    {
      "epoch": 1.7208552207169845,
      "grad_norm": 0.4650121331214905,
      "learning_rate": 9.490891374023958e-07,
      "loss": 0.481,
      "step": 56019
    },
    {
      "epoch": 1.7208859398519336,
      "grad_norm": 0.41804203391075134,
      "learning_rate": 9.488836498756526e-07,
      "loss": 0.4098,
      "step": 56020
    },
    {
      "epoch": 1.720916658986883,
      "grad_norm": 0.42953476309776306,
      "learning_rate": 9.486781834884263e-07,
      "loss": 0.4929,
      "step": 56021
    },
    {
      "epoch": 1.720947378121832,
      "grad_norm": 0.4326101541519165,
      "learning_rate": 9.484727382411918e-07,
      "loss": 0.3861,
      "step": 56022
    },
    {
      "epoch": 1.7209780972567814,
      "grad_norm": 0.44712191820144653,
      "learning_rate": 9.482673141344312e-07,
      "loss": 0.518,
      "step": 56023
    },
    {
      "epoch": 1.7210088163917305,
      "grad_norm": 0.4201991856098175,
      "learning_rate": 9.480619111686251e-07,
      "loss": 0.4779,
      "step": 56024
    },
    {
      "epoch": 1.7210395355266797,
      "grad_norm": 0.4663847088813782,
      "learning_rate": 9.478565293442532e-07,
      "loss": 0.4743,
      "step": 56025
    },
    {
      "epoch": 1.7210702546616288,
      "grad_norm": 0.39828038215637207,
      "learning_rate": 9.47651168661794e-07,
      "loss": 0.4754,
      "step": 56026
    },
    {
      "epoch": 1.721100973796578,
      "grad_norm": 0.4057837426662445,
      "learning_rate": 9.47445829121727e-07,
      "loss": 0.4343,
      "step": 56027
    },
    {
      "epoch": 1.721131692931527,
      "grad_norm": 0.4678432047367096,
      "learning_rate": 9.47240510724533e-07,
      "loss": 0.4526,
      "step": 56028
    },
    {
      "epoch": 1.7211624120664761,
      "grad_norm": 0.422966331243515,
      "learning_rate": 9.470352134706929e-07,
      "loss": 0.4984,
      "step": 56029
    },
    {
      "epoch": 1.7211931312014253,
      "grad_norm": 0.47307121753692627,
      "learning_rate": 9.468299373606827e-07,
      "loss": 0.4849,
      "step": 56030
    },
    {
      "epoch": 1.7212238503363744,
      "grad_norm": 0.4365330934524536,
      "learning_rate": 9.466246823949821e-07,
      "loss": 0.5127,
      "step": 56031
    },
    {
      "epoch": 1.7212545694713237,
      "grad_norm": 0.4587182104587555,
      "learning_rate": 9.46419448574073e-07,
      "loss": 0.4961,
      "step": 56032
    },
    {
      "epoch": 1.7212852886062728,
      "grad_norm": 0.42979422211647034,
      "learning_rate": 9.462142358984349e-07,
      "loss": 0.3674,
      "step": 56033
    },
    {
      "epoch": 1.721316007741222,
      "grad_norm": 0.4666750133037567,
      "learning_rate": 9.460090443685444e-07,
      "loss": 0.5009,
      "step": 56034
    },
    {
      "epoch": 1.7213467268761713,
      "grad_norm": 0.43577656149864197,
      "learning_rate": 9.45803873984884e-07,
      "loss": 0.4187,
      "step": 56035
    },
    {
      "epoch": 1.7213774460111204,
      "grad_norm": 0.5154346227645874,
      "learning_rate": 9.45598724747927e-07,
      "loss": 0.5002,
      "step": 56036
    },
    {
      "epoch": 1.7214081651460695,
      "grad_norm": 0.5693272948265076,
      "learning_rate": 9.453935966581584e-07,
      "loss": 0.4252,
      "step": 56037
    },
    {
      "epoch": 1.7214388842810187,
      "grad_norm": 0.4640732705593109,
      "learning_rate": 9.451884897160568e-07,
      "loss": 0.4216,
      "step": 56038
    },
    {
      "epoch": 1.7214696034159678,
      "grad_norm": 0.4239595830440521,
      "learning_rate": 9.449834039220984e-07,
      "loss": 0.448,
      "step": 56039
    },
    {
      "epoch": 1.721500322550917,
      "grad_norm": 0.41101181507110596,
      "learning_rate": 9.44778339276764e-07,
      "loss": 0.479,
      "step": 56040
    },
    {
      "epoch": 1.721531041685866,
      "grad_norm": 0.5029805302619934,
      "learning_rate": 9.44573295780532e-07,
      "loss": 0.4505,
      "step": 56041
    },
    {
      "epoch": 1.7215617608208151,
      "grad_norm": 0.3904835879802704,
      "learning_rate": 9.443682734338832e-07,
      "loss": 0.4714,
      "step": 56042
    },
    {
      "epoch": 1.7215924799557645,
      "grad_norm": 0.4555414319038391,
      "learning_rate": 9.441632722372929e-07,
      "loss": 0.4744,
      "step": 56043
    },
    {
      "epoch": 1.7216231990907136,
      "grad_norm": 0.4162745773792267,
      "learning_rate": 9.439582921912438e-07,
      "loss": 0.4595,
      "step": 56044
    },
    {
      "epoch": 1.7216539182256627,
      "grad_norm": 0.4673532545566559,
      "learning_rate": 9.43753333296209e-07,
      "loss": 0.4449,
      "step": 56045
    },
    {
      "epoch": 1.721684637360612,
      "grad_norm": 0.4429018199443817,
      "learning_rate": 9.435483955526736e-07,
      "loss": 0.4057,
      "step": 56046
    },
    {
      "epoch": 1.7217153564955612,
      "grad_norm": 0.4252307116985321,
      "learning_rate": 9.433434789611118e-07,
      "loss": 0.5113,
      "step": 56047
    },
    {
      "epoch": 1.7217460756305103,
      "grad_norm": 0.4265754222869873,
      "learning_rate": 9.431385835220064e-07,
      "loss": 0.4924,
      "step": 56048
    },
    {
      "epoch": 1.7217767947654594,
      "grad_norm": 0.4587625563144684,
      "learning_rate": 9.429337092358315e-07,
      "loss": 0.5321,
      "step": 56049
    },
    {
      "epoch": 1.7218075139004085,
      "grad_norm": 0.41199544072151184,
      "learning_rate": 9.427288561030667e-07,
      "loss": 0.5202,
      "step": 56050
    },
    {
      "epoch": 1.7218382330353577,
      "grad_norm": 0.5606616735458374,
      "learning_rate": 9.425240241241917e-07,
      "loss": 0.4934,
      "step": 56051
    },
    {
      "epoch": 1.7218689521703068,
      "grad_norm": 0.4219444692134857,
      "learning_rate": 9.423192132996861e-07,
      "loss": 0.4925,
      "step": 56052
    },
    {
      "epoch": 1.721899671305256,
      "grad_norm": 0.4220271408557892,
      "learning_rate": 9.421144236300251e-07,
      "loss": 0.4676,
      "step": 56053
    },
    {
      "epoch": 1.7219303904402052,
      "grad_norm": 0.42566531896591187,
      "learning_rate": 9.419096551156881e-07,
      "loss": 0.4605,
      "step": 56054
    },
    {
      "epoch": 1.7219611095751544,
      "grad_norm": 0.45381754636764526,
      "learning_rate": 9.417049077571527e-07,
      "loss": 0.4302,
      "step": 56055
    },
    {
      "epoch": 1.7219918287101035,
      "grad_norm": 0.4197041094303131,
      "learning_rate": 9.415001815548997e-07,
      "loss": 0.4468,
      "step": 56056
    },
    {
      "epoch": 1.7220225478450528,
      "grad_norm": 0.47851887345314026,
      "learning_rate": 9.412954765094073e-07,
      "loss": 0.4367,
      "step": 56057
    },
    {
      "epoch": 1.722053266980002,
      "grad_norm": 0.4608108103275299,
      "learning_rate": 9.410907926211498e-07,
      "loss": 0.4814,
      "step": 56058
    },
    {
      "epoch": 1.722083986114951,
      "grad_norm": 0.4437856674194336,
      "learning_rate": 9.408861298906069e-07,
      "loss": 0.5143,
      "step": 56059
    },
    {
      "epoch": 1.7221147052499002,
      "grad_norm": 0.43985694646835327,
      "learning_rate": 9.40681488318258e-07,
      "loss": 0.5367,
      "step": 56060
    },
    {
      "epoch": 1.7221454243848493,
      "grad_norm": 0.4707163870334625,
      "learning_rate": 9.404768679045817e-07,
      "loss": 0.478,
      "step": 56061
    },
    {
      "epoch": 1.7221761435197984,
      "grad_norm": 0.4274556338787079,
      "learning_rate": 9.402722686500521e-07,
      "loss": 0.4736,
      "step": 56062
    },
    {
      "epoch": 1.7222068626547475,
      "grad_norm": 0.42656999826431274,
      "learning_rate": 9.400676905551497e-07,
      "loss": 0.5155,
      "step": 56063
    },
    {
      "epoch": 1.7222375817896967,
      "grad_norm": 0.46138015389442444,
      "learning_rate": 9.398631336203523e-07,
      "loss": 0.4273,
      "step": 56064
    },
    {
      "epoch": 1.722268300924646,
      "grad_norm": 0.44184499979019165,
      "learning_rate": 9.396585978461381e-07,
      "loss": 0.4101,
      "step": 56065
    },
    {
      "epoch": 1.7222990200595951,
      "grad_norm": 0.4250757098197937,
      "learning_rate": 9.394540832329835e-07,
      "loss": 0.4747,
      "step": 56066
    },
    {
      "epoch": 1.7223297391945442,
      "grad_norm": 0.4566234350204468,
      "learning_rate": 9.392495897813658e-07,
      "loss": 0.496,
      "step": 56067
    },
    {
      "epoch": 1.7223604583294936,
      "grad_norm": 0.3995974361896515,
      "learning_rate": 9.390451174917636e-07,
      "loss": 0.5267,
      "step": 56068
    },
    {
      "epoch": 1.7223911774644427,
      "grad_norm": 0.42922258377075195,
      "learning_rate": 9.388406663646565e-07,
      "loss": 0.3936,
      "step": 56069
    },
    {
      "epoch": 1.7224218965993918,
      "grad_norm": 0.4283770024776459,
      "learning_rate": 9.386362364005175e-07,
      "loss": 0.5101,
      "step": 56070
    },
    {
      "epoch": 1.722452615734341,
      "grad_norm": 0.42510607838630676,
      "learning_rate": 9.384318275998283e-07,
      "loss": 0.5447,
      "step": 56071
    },
    {
      "epoch": 1.72248333486929,
      "grad_norm": 0.4384949505329132,
      "learning_rate": 9.382274399630609e-07,
      "loss": 0.4747,
      "step": 56072
    },
    {
      "epoch": 1.7225140540042392,
      "grad_norm": 0.4584118723869324,
      "learning_rate": 9.380230734907003e-07,
      "loss": 0.4083,
      "step": 56073
    },
    {
      "epoch": 1.7225447731391883,
      "grad_norm": 0.442793071269989,
      "learning_rate": 9.378187281832174e-07,
      "loss": 0.4932,
      "step": 56074
    },
    {
      "epoch": 1.7225754922741374,
      "grad_norm": 0.5371186137199402,
      "learning_rate": 9.376144040410918e-07,
      "loss": 0.4685,
      "step": 56075
    },
    {
      "epoch": 1.7226062114090868,
      "grad_norm": 0.43551215529441833,
      "learning_rate": 9.374101010648029e-07,
      "loss": 0.437,
      "step": 56076
    },
    {
      "epoch": 1.7226369305440359,
      "grad_norm": 0.4679713249206543,
      "learning_rate": 9.372058192548216e-07,
      "loss": 0.4612,
      "step": 56077
    },
    {
      "epoch": 1.722667649678985,
      "grad_norm": 0.415537029504776,
      "learning_rate": 9.370015586116332e-07,
      "loss": 0.4283,
      "step": 56078
    },
    {
      "epoch": 1.7226983688139343,
      "grad_norm": 0.42311301827430725,
      "learning_rate": 9.367973191357082e-07,
      "loss": 0.4612,
      "step": 56079
    },
    {
      "epoch": 1.7227290879488835,
      "grad_norm": 0.41900962591171265,
      "learning_rate": 9.365931008275275e-07,
      "loss": 0.4566,
      "step": 56080
    },
    {
      "epoch": 1.7227598070838326,
      "grad_norm": 0.46281811594963074,
      "learning_rate": 9.36388903687564e-07,
      "loss": 0.4466,
      "step": 56081
    },
    {
      "epoch": 1.7227905262187817,
      "grad_norm": 0.5767859816551208,
      "learning_rate": 9.361847277162995e-07,
      "loss": 0.456,
      "step": 56082
    },
    {
      "epoch": 1.7228212453537308,
      "grad_norm": 0.42068541049957275,
      "learning_rate": 9.35980572914208e-07,
      "loss": 0.4202,
      "step": 56083
    },
    {
      "epoch": 1.72285196448868,
      "grad_norm": 0.47166693210601807,
      "learning_rate": 9.357764392817681e-07,
      "loss": 0.4756,
      "step": 56084
    },
    {
      "epoch": 1.722882683623629,
      "grad_norm": 0.39571890234947205,
      "learning_rate": 9.355723268194538e-07,
      "loss": 0.4747,
      "step": 56085
    },
    {
      "epoch": 1.7229134027585782,
      "grad_norm": 0.4300554394721985,
      "learning_rate": 9.353682355277438e-07,
      "loss": 0.3736,
      "step": 56086
    },
    {
      "epoch": 1.7229441218935275,
      "grad_norm": 0.4333980977535248,
      "learning_rate": 9.35164165407113e-07,
      "loss": 0.4727,
      "step": 56087
    },
    {
      "epoch": 1.7229748410284766,
      "grad_norm": 0.46823927760124207,
      "learning_rate": 9.349601164580424e-07,
      "loss": 0.5578,
      "step": 56088
    },
    {
      "epoch": 1.7230055601634258,
      "grad_norm": 0.4998028874397278,
      "learning_rate": 9.347560886810037e-07,
      "loss": 0.5559,
      "step": 56089
    },
    {
      "epoch": 1.723036279298375,
      "grad_norm": 0.4390031099319458,
      "learning_rate": 9.345520820764742e-07,
      "loss": 0.4926,
      "step": 56090
    },
    {
      "epoch": 1.7230669984333242,
      "grad_norm": 0.4985034465789795,
      "learning_rate": 9.343480966449326e-07,
      "loss": 0.42,
      "step": 56091
    },
    {
      "epoch": 1.7230977175682733,
      "grad_norm": 0.42952677607536316,
      "learning_rate": 9.341441323868539e-07,
      "loss": 0.4099,
      "step": 56092
    },
    {
      "epoch": 1.7231284367032225,
      "grad_norm": 0.4259415864944458,
      "learning_rate": 9.339401893027156e-07,
      "loss": 0.4266,
      "step": 56093
    },
    {
      "epoch": 1.7231591558381716,
      "grad_norm": 0.4647941291332245,
      "learning_rate": 9.337362673929928e-07,
      "loss": 0.4166,
      "step": 56094
    },
    {
      "epoch": 1.7231898749731207,
      "grad_norm": 0.44699424505233765,
      "learning_rate": 9.335323666581608e-07,
      "loss": 0.573,
      "step": 56095
    },
    {
      "epoch": 1.7232205941080698,
      "grad_norm": 0.4414292573928833,
      "learning_rate": 9.333284870986981e-07,
      "loss": 0.5424,
      "step": 56096
    },
    {
      "epoch": 1.723251313243019,
      "grad_norm": 0.40607959032058716,
      "learning_rate": 9.331246287150819e-07,
      "loss": 0.4589,
      "step": 56097
    },
    {
      "epoch": 1.7232820323779683,
      "grad_norm": 0.4306531548500061,
      "learning_rate": 9.329207915077832e-07,
      "loss": 0.4035,
      "step": 56098
    },
    {
      "epoch": 1.7233127515129174,
      "grad_norm": 0.4428699016571045,
      "learning_rate": 9.327169754772825e-07,
      "loss": 0.4499,
      "step": 56099
    },
    {
      "epoch": 1.7233434706478665,
      "grad_norm": 0.4269712269306183,
      "learning_rate": 9.32513180624054e-07,
      "loss": 0.4983,
      "step": 56100
    },
    {
      "epoch": 1.7233741897828159,
      "grad_norm": 0.4503369927406311,
      "learning_rate": 9.323094069485761e-07,
      "loss": 0.4663,
      "step": 56101
    },
    {
      "epoch": 1.723404908917765,
      "grad_norm": 0.44034823775291443,
      "learning_rate": 9.321056544513218e-07,
      "loss": 0.4896,
      "step": 56102
    },
    {
      "epoch": 1.723435628052714,
      "grad_norm": 0.4390659034252167,
      "learning_rate": 9.319019231327676e-07,
      "loss": 0.4197,
      "step": 56103
    },
    {
      "epoch": 1.7234663471876632,
      "grad_norm": 0.44115984439849854,
      "learning_rate": 9.316982129933893e-07,
      "loss": 0.4077,
      "step": 56104
    },
    {
      "epoch": 1.7234970663226123,
      "grad_norm": 0.46502912044525146,
      "learning_rate": 9.314945240336648e-07,
      "loss": 0.4743,
      "step": 56105
    },
    {
      "epoch": 1.7235277854575615,
      "grad_norm": 0.44828474521636963,
      "learning_rate": 9.312908562540667e-07,
      "loss": 0.438,
      "step": 56106
    },
    {
      "epoch": 1.7235585045925106,
      "grad_norm": 0.42568239569664,
      "learning_rate": 9.310872096550738e-07,
      "loss": 0.4932,
      "step": 56107
    },
    {
      "epoch": 1.7235892237274597,
      "grad_norm": 0.42854344844818115,
      "learning_rate": 9.308835842371566e-07,
      "loss": 0.5288,
      "step": 56108
    },
    {
      "epoch": 1.723619942862409,
      "grad_norm": 0.42307159304618835,
      "learning_rate": 9.306799800007982e-07,
      "loss": 0.4659,
      "step": 56109
    },
    {
      "epoch": 1.7236506619973582,
      "grad_norm": 0.43263694643974304,
      "learning_rate": 9.304763969464681e-07,
      "loss": 0.4783,
      "step": 56110
    },
    {
      "epoch": 1.7236813811323073,
      "grad_norm": 0.4979274570941925,
      "learning_rate": 9.302728350746438e-07,
      "loss": 0.592,
      "step": 56111
    },
    {
      "epoch": 1.7237121002672566,
      "grad_norm": 0.44055595993995667,
      "learning_rate": 9.300692943858025e-07,
      "loss": 0.5105,
      "step": 56112
    },
    {
      "epoch": 1.7237428194022058,
      "grad_norm": 0.42904648184776306,
      "learning_rate": 9.298657748804141e-07,
      "loss": 0.4614,
      "step": 56113
    },
    {
      "epoch": 1.7237735385371549,
      "grad_norm": 0.4255925118923187,
      "learning_rate": 9.296622765589613e-07,
      "loss": 0.4501,
      "step": 56114
    },
    {
      "epoch": 1.723804257672104,
      "grad_norm": 0.4491219222545624,
      "learning_rate": 9.29458799421914e-07,
      "loss": 0.4733,
      "step": 56115
    },
    {
      "epoch": 1.723834976807053,
      "grad_norm": 0.4647828936576843,
      "learning_rate": 9.292553434697504e-07,
      "loss": 0.3975,
      "step": 56116
    },
    {
      "epoch": 1.7238656959420022,
      "grad_norm": 0.4301708936691284,
      "learning_rate": 9.290519087029426e-07,
      "loss": 0.4998,
      "step": 56117
    },
    {
      "epoch": 1.7238964150769513,
      "grad_norm": 0.5044416785240173,
      "learning_rate": 9.288484951219678e-07,
      "loss": 0.5122,
      "step": 56118
    },
    {
      "epoch": 1.7239271342119005,
      "grad_norm": 0.41323140263557434,
      "learning_rate": 9.286451027273014e-07,
      "loss": 0.4318,
      "step": 56119
    },
    {
      "epoch": 1.7239578533468496,
      "grad_norm": 0.39930757880210876,
      "learning_rate": 9.284417315194194e-07,
      "loss": 0.4251,
      "step": 56120
    },
    {
      "epoch": 1.723988572481799,
      "grad_norm": 0.436286985874176,
      "learning_rate": 9.282383814987938e-07,
      "loss": 0.5203,
      "step": 56121
    },
    {
      "epoch": 1.724019291616748,
      "grad_norm": 0.4265027642250061,
      "learning_rate": 9.28035052665901e-07,
      "loss": 0.4776,
      "step": 56122
    },
    {
      "epoch": 1.7240500107516974,
      "grad_norm": 0.47102007269859314,
      "learning_rate": 9.278317450212149e-07,
      "loss": 0.4455,
      "step": 56123
    },
    {
      "epoch": 1.7240807298866465,
      "grad_norm": 1.048832893371582,
      "learning_rate": 9.27628458565214e-07,
      "loss": 0.5415,
      "step": 56124
    },
    {
      "epoch": 1.7241114490215956,
      "grad_norm": 0.4149203896522522,
      "learning_rate": 9.27425193298368e-07,
      "loss": 0.4019,
      "step": 56125
    },
    {
      "epoch": 1.7241421681565448,
      "grad_norm": 0.4798920452594757,
      "learning_rate": 9.272219492211554e-07,
      "loss": 0.4751,
      "step": 56126
    },
    {
      "epoch": 1.7241728872914939,
      "grad_norm": 0.4928133189678192,
      "learning_rate": 9.27018726334048e-07,
      "loss": 0.4983,
      "step": 56127
    },
    {
      "epoch": 1.724203606426443,
      "grad_norm": 0.4226321876049042,
      "learning_rate": 9.268155246375254e-07,
      "loss": 0.4399,
      "step": 56128
    },
    {
      "epoch": 1.7242343255613921,
      "grad_norm": 0.4575273096561432,
      "learning_rate": 9.266123441320563e-07,
      "loss": 0.4579,
      "step": 56129
    },
    {
      "epoch": 1.7242650446963412,
      "grad_norm": 0.4421267509460449,
      "learning_rate": 9.264091848181167e-07,
      "loss": 0.456,
      "step": 56130
    },
    {
      "epoch": 1.7242957638312904,
      "grad_norm": 0.4480295479297638,
      "learning_rate": 9.262060466961831e-07,
      "loss": 0.4807,
      "step": 56131
    },
    {
      "epoch": 1.7243264829662397,
      "grad_norm": 0.4690489172935486,
      "learning_rate": 9.260029297667295e-07,
      "loss": 0.5176,
      "step": 56132
    },
    {
      "epoch": 1.7243572021011888,
      "grad_norm": 0.4407826364040375,
      "learning_rate": 9.25799834030231e-07,
      "loss": 0.436,
      "step": 56133
    },
    {
      "epoch": 1.7243879212361382,
      "grad_norm": 0.4221692681312561,
      "learning_rate": 9.255967594871585e-07,
      "loss": 0.4401,
      "step": 56134
    },
    {
      "epoch": 1.7244186403710873,
      "grad_norm": 0.4265922009944916,
      "learning_rate": 9.253937061379892e-07,
      "loss": 0.4292,
      "step": 56135
    },
    {
      "epoch": 1.7244493595060364,
      "grad_norm": 0.4171302914619446,
      "learning_rate": 9.251906739831961e-07,
      "loss": 0.5377,
      "step": 56136
    },
    {
      "epoch": 1.7244800786409855,
      "grad_norm": 0.4355239272117615,
      "learning_rate": 9.249876630232557e-07,
      "loss": 0.4636,
      "step": 56137
    },
    {
      "epoch": 1.7245107977759346,
      "grad_norm": 0.5108993053436279,
      "learning_rate": 9.247846732586396e-07,
      "loss": 0.4981,
      "step": 56138
    },
    {
      "epoch": 1.7245415169108838,
      "grad_norm": 0.4166148006916046,
      "learning_rate": 9.245817046898242e-07,
      "loss": 0.5043,
      "step": 56139
    },
    {
      "epoch": 1.7245722360458329,
      "grad_norm": 0.42600753903388977,
      "learning_rate": 9.24378757317278e-07,
      "loss": 0.4741,
      "step": 56140
    },
    {
      "epoch": 1.724602955180782,
      "grad_norm": 0.4326780140399933,
      "learning_rate": 9.241758311414827e-07,
      "loss": 0.4743,
      "step": 56141
    },
    {
      "epoch": 1.7246336743157311,
      "grad_norm": 0.4232822358608246,
      "learning_rate": 9.239729261629071e-07,
      "loss": 0.453,
      "step": 56142
    },
    {
      "epoch": 1.7246643934506805,
      "grad_norm": 0.4326203465461731,
      "learning_rate": 9.237700423820272e-07,
      "loss": 0.4712,
      "step": 56143
    },
    {
      "epoch": 1.7246951125856296,
      "grad_norm": 0.4430578052997589,
      "learning_rate": 9.23567179799314e-07,
      "loss": 0.4715,
      "step": 56144
    },
    {
      "epoch": 1.7247258317205787,
      "grad_norm": 0.4420703947544098,
      "learning_rate": 9.233643384152468e-07,
      "loss": 0.5194,
      "step": 56145
    },
    {
      "epoch": 1.724756550855528,
      "grad_norm": 0.4862399697303772,
      "learning_rate": 9.231615182302945e-07,
      "loss": 0.4383,
      "step": 56146
    },
    {
      "epoch": 1.7247872699904772,
      "grad_norm": 0.42069321870803833,
      "learning_rate": 9.229587192449318e-07,
      "loss": 0.4246,
      "step": 56147
    },
    {
      "epoch": 1.7248179891254263,
      "grad_norm": 0.4536031186580658,
      "learning_rate": 9.227559414596355e-07,
      "loss": 0.4454,
      "step": 56148
    },
    {
      "epoch": 1.7248487082603754,
      "grad_norm": 0.602297306060791,
      "learning_rate": 9.225531848748726e-07,
      "loss": 0.4386,
      "step": 56149
    },
    {
      "epoch": 1.7248794273953245,
      "grad_norm": 0.4794616103172302,
      "learning_rate": 9.22350449491124e-07,
      "loss": 0.51,
      "step": 56150
    },
    {
      "epoch": 1.7249101465302736,
      "grad_norm": 0.4464634954929352,
      "learning_rate": 9.221477353088581e-07,
      "loss": 0.4687,
      "step": 56151
    },
    {
      "epoch": 1.7249408656652228,
      "grad_norm": 0.6290957927703857,
      "learning_rate": 9.219450423285526e-07,
      "loss": 0.4461,
      "step": 56152
    },
    {
      "epoch": 1.7249715848001719,
      "grad_norm": 0.4022134840488434,
      "learning_rate": 9.217423705506767e-07,
      "loss": 0.4663,
      "step": 56153
    },
    {
      "epoch": 1.7250023039351212,
      "grad_norm": 0.9242076873779297,
      "learning_rate": 9.215397199757048e-07,
      "loss": 0.4349,
      "step": 56154
    },
    {
      "epoch": 1.7250330230700703,
      "grad_norm": 0.4590569734573364,
      "learning_rate": 9.213370906041108e-07,
      "loss": 0.4523,
      "step": 56155
    },
    {
      "epoch": 1.7250637422050195,
      "grad_norm": 0.39128589630126953,
      "learning_rate": 9.21134482436371e-07,
      "loss": 0.5146,
      "step": 56156
    },
    {
      "epoch": 1.7250944613399688,
      "grad_norm": 0.43470534682273865,
      "learning_rate": 9.209318954729529e-07,
      "loss": 0.4568,
      "step": 56157
    },
    {
      "epoch": 1.725125180474918,
      "grad_norm": 0.44987961649894714,
      "learning_rate": 9.207293297143328e-07,
      "loss": 0.4736,
      "step": 56158
    },
    {
      "epoch": 1.725155899609867,
      "grad_norm": 0.44397062063217163,
      "learning_rate": 9.205267851609834e-07,
      "loss": 0.4787,
      "step": 56159
    },
    {
      "epoch": 1.7251866187448162,
      "grad_norm": 0.42379772663116455,
      "learning_rate": 9.2032426181338e-07,
      "loss": 0.4151,
      "step": 56160
    },
    {
      "epoch": 1.7252173378797653,
      "grad_norm": 0.49205389618873596,
      "learning_rate": 9.201217596719902e-07,
      "loss": 0.5015,
      "step": 56161
    },
    {
      "epoch": 1.7252480570147144,
      "grad_norm": 0.47123584151268005,
      "learning_rate": 9.199192787372913e-07,
      "loss": 0.3999,
      "step": 56162
    },
    {
      "epoch": 1.7252787761496635,
      "grad_norm": 0.44116753339767456,
      "learning_rate": 9.197168190097549e-07,
      "loss": 0.4884,
      "step": 56163
    },
    {
      "epoch": 1.7253094952846126,
      "grad_norm": 0.41071179509162903,
      "learning_rate": 9.195143804898565e-07,
      "loss": 0.4046,
      "step": 56164
    },
    {
      "epoch": 1.725340214419562,
      "grad_norm": 0.4132353365421295,
      "learning_rate": 9.193119631780634e-07,
      "loss": 0.4811,
      "step": 56165
    },
    {
      "epoch": 1.725370933554511,
      "grad_norm": 0.45840001106262207,
      "learning_rate": 9.191095670748529e-07,
      "loss": 0.5264,
      "step": 56166
    },
    {
      "epoch": 1.7254016526894602,
      "grad_norm": 0.5072743892669678,
      "learning_rate": 9.189071921806947e-07,
      "loss": 0.5118,
      "step": 56167
    },
    {
      "epoch": 1.7254323718244096,
      "grad_norm": 0.4093133211135864,
      "learning_rate": 9.18704838496064e-07,
      "loss": 0.5508,
      "step": 56168
    },
    {
      "epoch": 1.7254630909593587,
      "grad_norm": 0.4406593441963196,
      "learning_rate": 9.185025060214336e-07,
      "loss": 0.5037,
      "step": 56169
    },
    {
      "epoch": 1.7254938100943078,
      "grad_norm": 0.4517538249492645,
      "learning_rate": 9.183001947572734e-07,
      "loss": 0.3998,
      "step": 56170
    },
    {
      "epoch": 1.725524529229257,
      "grad_norm": 0.4949435293674469,
      "learning_rate": 9.180979047040562e-07,
      "loss": 0.3982,
      "step": 56171
    },
    {
      "epoch": 1.725555248364206,
      "grad_norm": 0.4465850293636322,
      "learning_rate": 9.178956358622571e-07,
      "loss": 0.4512,
      "step": 56172
    },
    {
      "epoch": 1.7255859674991552,
      "grad_norm": 0.4536168575286865,
      "learning_rate": 9.17693388232348e-07,
      "loss": 0.4198,
      "step": 56173
    },
    {
      "epoch": 1.7256166866341043,
      "grad_norm": 0.45715847611427307,
      "learning_rate": 9.174911618147986e-07,
      "loss": 0.4548,
      "step": 56174
    },
    {
      "epoch": 1.7256474057690534,
      "grad_norm": 0.44111114740371704,
      "learning_rate": 9.172889566100851e-07,
      "loss": 0.3979,
      "step": 56175
    },
    {
      "epoch": 1.7256781249040027,
      "grad_norm": 0.36501768231391907,
      "learning_rate": 9.170867726186739e-07,
      "loss": 0.4393,
      "step": 56176
    },
    {
      "epoch": 1.7257088440389519,
      "grad_norm": 0.48361116647720337,
      "learning_rate": 9.168846098410445e-07,
      "loss": 0.455,
      "step": 56177
    },
    {
      "epoch": 1.725739563173901,
      "grad_norm": 0.4459666311740875,
      "learning_rate": 9.166824682776632e-07,
      "loss": 0.4683,
      "step": 56178
    },
    {
      "epoch": 1.7257702823088503,
      "grad_norm": 0.4422995150089264,
      "learning_rate": 9.164803479290064e-07,
      "loss": 0.4638,
      "step": 56179
    },
    {
      "epoch": 1.7258010014437994,
      "grad_norm": 0.4623047113418579,
      "learning_rate": 9.162782487955424e-07,
      "loss": 0.482,
      "step": 56180
    },
    {
      "epoch": 1.7258317205787486,
      "grad_norm": 0.4100037217140198,
      "learning_rate": 9.160761708777455e-07,
      "loss": 0.5406,
      "step": 56181
    },
    {
      "epoch": 1.7258624397136977,
      "grad_norm": 0.4411429464817047,
      "learning_rate": 9.158741141760863e-07,
      "loss": 0.4595,
      "step": 56182
    },
    {
      "epoch": 1.7258931588486468,
      "grad_norm": 0.4296795725822449,
      "learning_rate": 9.156720786910378e-07,
      "loss": 0.4718,
      "step": 56183
    },
    {
      "epoch": 1.725923877983596,
      "grad_norm": 0.4422190189361572,
      "learning_rate": 9.154700644230729e-07,
      "loss": 0.4366,
      "step": 56184
    },
    {
      "epoch": 1.725954597118545,
      "grad_norm": 0.42938998341560364,
      "learning_rate": 9.152680713726592e-07,
      "loss": 0.56,
      "step": 56185
    },
    {
      "epoch": 1.7259853162534942,
      "grad_norm": 0.4308883845806122,
      "learning_rate": 9.15066099540275e-07,
      "loss": 0.4482,
      "step": 56186
    },
    {
      "epoch": 1.7260160353884435,
      "grad_norm": 0.45926806330680847,
      "learning_rate": 9.148641489263866e-07,
      "loss": 0.4789,
      "step": 56187
    },
    {
      "epoch": 1.7260467545233926,
      "grad_norm": 0.5488658547401428,
      "learning_rate": 9.146622195314692e-07,
      "loss": 0.4324,
      "step": 56188
    },
    {
      "epoch": 1.7260774736583417,
      "grad_norm": 0.39493611454963684,
      "learning_rate": 9.144603113559902e-07,
      "loss": 0.4095,
      "step": 56189
    },
    {
      "epoch": 1.726108192793291,
      "grad_norm": 0.43367403745651245,
      "learning_rate": 9.142584244004249e-07,
      "loss": 0.5473,
      "step": 56190
    },
    {
      "epoch": 1.7261389119282402,
      "grad_norm": 0.46568983793258667,
      "learning_rate": 9.140565586652428e-07,
      "loss": 0.4625,
      "step": 56191
    },
    {
      "epoch": 1.7261696310631893,
      "grad_norm": 0.539625883102417,
      "learning_rate": 9.13854714150918e-07,
      "loss": 0.3938,
      "step": 56192
    },
    {
      "epoch": 1.7262003501981384,
      "grad_norm": 0.41424044966697693,
      "learning_rate": 9.136528908579179e-07,
      "loss": 0.4232,
      "step": 56193
    },
    {
      "epoch": 1.7262310693330876,
      "grad_norm": 0.4417702257633209,
      "learning_rate": 9.134510887867165e-07,
      "loss": 0.493,
      "step": 56194
    },
    {
      "epoch": 1.7262617884680367,
      "grad_norm": 0.42377597093582153,
      "learning_rate": 9.132493079377846e-07,
      "loss": 0.4782,
      "step": 56195
    },
    {
      "epoch": 1.7262925076029858,
      "grad_norm": 0.42008477449417114,
      "learning_rate": 9.130475483115964e-07,
      "loss": 0.3968,
      "step": 56196
    },
    {
      "epoch": 1.726323226737935,
      "grad_norm": 0.4294533431529999,
      "learning_rate": 9.128458099086168e-07,
      "loss": 0.4694,
      "step": 56197
    },
    {
      "epoch": 1.7263539458728843,
      "grad_norm": 0.47847428917884827,
      "learning_rate": 9.126440927293212e-07,
      "loss": 0.5058,
      "step": 56198
    },
    {
      "epoch": 1.7263846650078334,
      "grad_norm": 0.40653255581855774,
      "learning_rate": 9.124423967741803e-07,
      "loss": 0.4293,
      "step": 56199
    },
    {
      "epoch": 1.7264153841427825,
      "grad_norm": 0.4482901990413666,
      "learning_rate": 9.122407220436658e-07,
      "loss": 0.4603,
      "step": 56200
    },
    {
      "epoch": 1.7264461032777318,
      "grad_norm": 0.4627036154270172,
      "learning_rate": 9.120390685382475e-07,
      "loss": 0.5139,
      "step": 56201
    },
    {
      "epoch": 1.726476822412681,
      "grad_norm": 0.45658424496650696,
      "learning_rate": 9.118374362583949e-07,
      "loss": 0.4515,
      "step": 56202
    },
    {
      "epoch": 1.72650754154763,
      "grad_norm": 0.41706612706184387,
      "learning_rate": 9.116358252045821e-07,
      "loss": 0.5574,
      "step": 56203
    },
    {
      "epoch": 1.7265382606825792,
      "grad_norm": 0.4655575156211853,
      "learning_rate": 9.114342353772776e-07,
      "loss": 0.512,
      "step": 56204
    },
    {
      "epoch": 1.7265689798175283,
      "grad_norm": 0.43741580843925476,
      "learning_rate": 9.112326667769556e-07,
      "loss": 0.4348,
      "step": 56205
    },
    {
      "epoch": 1.7265996989524774,
      "grad_norm": 0.41639378666877747,
      "learning_rate": 9.110311194040822e-07,
      "loss": 0.4407,
      "step": 56206
    },
    {
      "epoch": 1.7266304180874266,
      "grad_norm": 0.44359204173088074,
      "learning_rate": 9.108295932591305e-07,
      "loss": 0.4075,
      "step": 56207
    },
    {
      "epoch": 1.7266611372223757,
      "grad_norm": 0.4919353127479553,
      "learning_rate": 9.106280883425711e-07,
      "loss": 0.4728,
      "step": 56208
    },
    {
      "epoch": 1.726691856357325,
      "grad_norm": 0.4319983720779419,
      "learning_rate": 9.10426604654876e-07,
      "loss": 0.548,
      "step": 56209
    },
    {
      "epoch": 1.7267225754922741,
      "grad_norm": 0.4086054861545563,
      "learning_rate": 9.102251421965125e-07,
      "loss": 0.4419,
      "step": 56210
    },
    {
      "epoch": 1.7267532946272233,
      "grad_norm": 0.45645877718925476,
      "learning_rate": 9.100237009679558e-07,
      "loss": 0.4026,
      "step": 56211
    },
    {
      "epoch": 1.7267840137621726,
      "grad_norm": 0.4480441212654114,
      "learning_rate": 9.098222809696688e-07,
      "loss": 0.4316,
      "step": 56212
    },
    {
      "epoch": 1.7268147328971217,
      "grad_norm": 0.46588611602783203,
      "learning_rate": 9.096208822021313e-07,
      "loss": 0.4288,
      "step": 56213
    },
    {
      "epoch": 1.7268454520320708,
      "grad_norm": 0.39255470037460327,
      "learning_rate": 9.094195046658072e-07,
      "loss": 0.4481,
      "step": 56214
    },
    {
      "epoch": 1.72687617116702,
      "grad_norm": 0.4598352313041687,
      "learning_rate": 9.092181483611706e-07,
      "loss": 0.4654,
      "step": 56215
    },
    {
      "epoch": 1.726906890301969,
      "grad_norm": 0.524662435054779,
      "learning_rate": 9.090168132886879e-07,
      "loss": 0.4887,
      "step": 56216
    },
    {
      "epoch": 1.7269376094369182,
      "grad_norm": 0.48245537281036377,
      "learning_rate": 9.088154994488308e-07,
      "loss": 0.4067,
      "step": 56217
    },
    {
      "epoch": 1.7269683285718673,
      "grad_norm": 0.4195074737071991,
      "learning_rate": 9.0861420684207e-07,
      "loss": 0.4813,
      "step": 56218
    },
    {
      "epoch": 1.7269990477068164,
      "grad_norm": 0.3854992389678955,
      "learning_rate": 9.084129354688787e-07,
      "loss": 0.4654,
      "step": 56219
    },
    {
      "epoch": 1.7270297668417658,
      "grad_norm": 0.5465233325958252,
      "learning_rate": 9.082116853297207e-07,
      "loss": 0.4436,
      "step": 56220
    },
    {
      "epoch": 1.727060485976715,
      "grad_norm": 0.4235248863697052,
      "learning_rate": 9.080104564250702e-07,
      "loss": 0.4454,
      "step": 56221
    },
    {
      "epoch": 1.727091205111664,
      "grad_norm": 0.46511027216911316,
      "learning_rate": 9.078092487553957e-07,
      "loss": 0.4326,
      "step": 56222
    },
    {
      "epoch": 1.7271219242466134,
      "grad_norm": 0.4416414499282837,
      "learning_rate": 9.07608062321168e-07,
      "loss": 0.4766,
      "step": 56223
    },
    {
      "epoch": 1.7271526433815625,
      "grad_norm": 0.4219762682914734,
      "learning_rate": 9.074068971228589e-07,
      "loss": 0.4974,
      "step": 56224
    },
    {
      "epoch": 1.7271833625165116,
      "grad_norm": 0.49302899837493896,
      "learning_rate": 9.072057531609335e-07,
      "loss": 0.4767,
      "step": 56225
    },
    {
      "epoch": 1.7272140816514607,
      "grad_norm": 0.5691262483596802,
      "learning_rate": 9.070046304358637e-07,
      "loss": 0.3997,
      "step": 56226
    },
    {
      "epoch": 1.7272448007864099,
      "grad_norm": 0.4855520725250244,
      "learning_rate": 9.068035289481203e-07,
      "loss": 0.4249,
      "step": 56227
    },
    {
      "epoch": 1.727275519921359,
      "grad_norm": 0.5218714475631714,
      "learning_rate": 9.066024486981751e-07,
      "loss": 0.4542,
      "step": 56228
    },
    {
      "epoch": 1.727306239056308,
      "grad_norm": 0.46029701828956604,
      "learning_rate": 9.06401389686492e-07,
      "loss": 0.4798,
      "step": 56229
    },
    {
      "epoch": 1.7273369581912572,
      "grad_norm": 0.3995363712310791,
      "learning_rate": 9.062003519135431e-07,
      "loss": 0.3947,
      "step": 56230
    },
    {
      "epoch": 1.7273676773262063,
      "grad_norm": 0.5367108583450317,
      "learning_rate": 9.059993353797991e-07,
      "loss": 0.4456,
      "step": 56231
    },
    {
      "epoch": 1.7273983964611557,
      "grad_norm": 0.4237811267375946,
      "learning_rate": 9.057983400857306e-07,
      "loss": 0.5141,
      "step": 56232
    },
    {
      "epoch": 1.7274291155961048,
      "grad_norm": 0.3904825448989868,
      "learning_rate": 9.05597366031803e-07,
      "loss": 0.4338,
      "step": 56233
    },
    {
      "epoch": 1.7274598347310541,
      "grad_norm": 0.3938215672969818,
      "learning_rate": 9.053964132184878e-07,
      "loss": 0.5132,
      "step": 56234
    },
    {
      "epoch": 1.7274905538660033,
      "grad_norm": 0.48822951316833496,
      "learning_rate": 9.05195481646255e-07,
      "loss": 0.4534,
      "step": 56235
    },
    {
      "epoch": 1.7275212730009524,
      "grad_norm": 0.3950832784175873,
      "learning_rate": 9.04994571315575e-07,
      "loss": 0.41,
      "step": 56236
    },
    {
      "epoch": 1.7275519921359015,
      "grad_norm": 0.5081918835639954,
      "learning_rate": 9.047936822269132e-07,
      "loss": 0.5218,
      "step": 56237
    },
    {
      "epoch": 1.7275827112708506,
      "grad_norm": 0.4253843128681183,
      "learning_rate": 9.045928143807414e-07,
      "loss": 0.4786,
      "step": 56238
    },
    {
      "epoch": 1.7276134304057997,
      "grad_norm": 0.44540107250213623,
      "learning_rate": 9.043919677775281e-07,
      "loss": 0.4846,
      "step": 56239
    },
    {
      "epoch": 1.7276441495407489,
      "grad_norm": 0.4410507380962372,
      "learning_rate": 9.04191142417743e-07,
      "loss": 0.4577,
      "step": 56240
    },
    {
      "epoch": 1.727674868675698,
      "grad_norm": 0.6739416122436523,
      "learning_rate": 9.039903383018566e-07,
      "loss": 0.4689,
      "step": 56241
    },
    {
      "epoch": 1.727705587810647,
      "grad_norm": 0.4293113350868225,
      "learning_rate": 9.037895554303333e-07,
      "loss": 0.4243,
      "step": 56242
    },
    {
      "epoch": 1.7277363069455964,
      "grad_norm": 0.42670807242393494,
      "learning_rate": 9.03588793803647e-07,
      "loss": 0.4179,
      "step": 56243
    },
    {
      "epoch": 1.7277670260805456,
      "grad_norm": 0.45755675435066223,
      "learning_rate": 9.033880534222605e-07,
      "loss": 0.4907,
      "step": 56244
    },
    {
      "epoch": 1.727797745215495,
      "grad_norm": 0.43365585803985596,
      "learning_rate": 9.031873342866504e-07,
      "loss": 0.4062,
      "step": 56245
    },
    {
      "epoch": 1.727828464350444,
      "grad_norm": 0.393424928188324,
      "learning_rate": 9.029866363972806e-07,
      "loss": 0.4401,
      "step": 56246
    },
    {
      "epoch": 1.7278591834853931,
      "grad_norm": 0.48553183674812317,
      "learning_rate": 9.027859597546218e-07,
      "loss": 0.471,
      "step": 56247
    },
    {
      "epoch": 1.7278899026203423,
      "grad_norm": 0.40859225392341614,
      "learning_rate": 9.025853043591382e-07,
      "loss": 0.436,
      "step": 56248
    },
    {
      "epoch": 1.7279206217552914,
      "grad_norm": 0.4384227693080902,
      "learning_rate": 9.023846702113049e-07,
      "loss": 0.4965,
      "step": 56249
    },
    {
      "epoch": 1.7279513408902405,
      "grad_norm": 0.41341957449913025,
      "learning_rate": 9.02184057311587e-07,
      "loss": 0.4927,
      "step": 56250
    },
    {
      "epoch": 1.7279820600251896,
      "grad_norm": 0.4424198865890503,
      "learning_rate": 9.019834656604542e-07,
      "loss": 0.5777,
      "step": 56251
    },
    {
      "epoch": 1.7280127791601387,
      "grad_norm": 0.44171714782714844,
      "learning_rate": 9.01782895258374e-07,
      "loss": 0.5068,
      "step": 56252
    },
    {
      "epoch": 1.7280434982950879,
      "grad_norm": 0.44854095578193665,
      "learning_rate": 9.015823461058138e-07,
      "loss": 0.4753,
      "step": 56253
    },
    {
      "epoch": 1.7280742174300372,
      "grad_norm": 0.4440862536430359,
      "learning_rate": 9.013818182032441e-07,
      "loss": 0.5109,
      "step": 56254
    },
    {
      "epoch": 1.7281049365649863,
      "grad_norm": 0.4782678186893463,
      "learning_rate": 9.011813115511347e-07,
      "loss": 0.4168,
      "step": 56255
    },
    {
      "epoch": 1.7281356556999354,
      "grad_norm": 0.43055468797683716,
      "learning_rate": 9.009808261499498e-07,
      "loss": 0.4272,
      "step": 56256
    },
    {
      "epoch": 1.7281663748348848,
      "grad_norm": 0.5443745255470276,
      "learning_rate": 9.007803620001598e-07,
      "loss": 0.4096,
      "step": 56257
    },
    {
      "epoch": 1.728197093969834,
      "grad_norm": 0.726614236831665,
      "learning_rate": 9.005799191022324e-07,
      "loss": 0.4902,
      "step": 56258
    },
    {
      "epoch": 1.728227813104783,
      "grad_norm": 0.43394410610198975,
      "learning_rate": 9.00379497456636e-07,
      "loss": 0.4395,
      "step": 56259
    },
    {
      "epoch": 1.7282585322397321,
      "grad_norm": 0.4575555622577667,
      "learning_rate": 9.001790970638414e-07,
      "loss": 0.4726,
      "step": 56260
    },
    {
      "epoch": 1.7282892513746813,
      "grad_norm": 0.4022285044193268,
      "learning_rate": 8.999787179243113e-07,
      "loss": 0.4068,
      "step": 56261
    },
    {
      "epoch": 1.7283199705096304,
      "grad_norm": 0.39728233218193054,
      "learning_rate": 8.997783600385168e-07,
      "loss": 0.4824,
      "step": 56262
    },
    {
      "epoch": 1.7283506896445795,
      "grad_norm": 0.4869854748249054,
      "learning_rate": 8.995780234069252e-07,
      "loss": 0.4035,
      "step": 56263
    },
    {
      "epoch": 1.7283814087795286,
      "grad_norm": 0.41868653893470764,
      "learning_rate": 8.99377708030007e-07,
      "loss": 0.4635,
      "step": 56264
    },
    {
      "epoch": 1.728412127914478,
      "grad_norm": 0.4362913966178894,
      "learning_rate": 8.991774139082265e-07,
      "loss": 0.4421,
      "step": 56265
    },
    {
      "epoch": 1.728442847049427,
      "grad_norm": 0.4141470193862915,
      "learning_rate": 8.989771410420511e-07,
      "loss": 0.4455,
      "step": 56266
    },
    {
      "epoch": 1.7284735661843762,
      "grad_norm": 0.440681129693985,
      "learning_rate": 8.987768894319515e-07,
      "loss": 0.521,
      "step": 56267
    },
    {
      "epoch": 1.7285042853193255,
      "grad_norm": 0.3937124013900757,
      "learning_rate": 8.985766590783951e-07,
      "loss": 0.4401,
      "step": 56268
    },
    {
      "epoch": 1.7285350044542747,
      "grad_norm": 0.42930760979652405,
      "learning_rate": 8.983764499818482e-07,
      "loss": 0.5448,
      "step": 56269
    },
    {
      "epoch": 1.7285657235892238,
      "grad_norm": 0.5089764595031738,
      "learning_rate": 8.981762621427769e-07,
      "loss": 0.4699,
      "step": 56270
    },
    {
      "epoch": 1.728596442724173,
      "grad_norm": 0.5491431951522827,
      "learning_rate": 8.979760955616513e-07,
      "loss": 0.4717,
      "step": 56271
    },
    {
      "epoch": 1.728627161859122,
      "grad_norm": 0.4089605510234833,
      "learning_rate": 8.977759502389405e-07,
      "loss": 0.4303,
      "step": 56272
    },
    {
      "epoch": 1.7286578809940711,
      "grad_norm": 0.40867143869400024,
      "learning_rate": 8.975758261751077e-07,
      "loss": 0.5284,
      "step": 56273
    },
    {
      "epoch": 1.7286886001290203,
      "grad_norm": 0.4593695104122162,
      "learning_rate": 8.973757233706237e-07,
      "loss": 0.4475,
      "step": 56274
    },
    {
      "epoch": 1.7287193192639694,
      "grad_norm": 0.46455222368240356,
      "learning_rate": 8.971756418259514e-07,
      "loss": 0.4463,
      "step": 56275
    },
    {
      "epoch": 1.7287500383989187,
      "grad_norm": 0.5409507155418396,
      "learning_rate": 8.969755815415615e-07,
      "loss": 0.419,
      "step": 56276
    },
    {
      "epoch": 1.7287807575338678,
      "grad_norm": 0.454162061214447,
      "learning_rate": 8.967755425179236e-07,
      "loss": 0.4755,
      "step": 56277
    },
    {
      "epoch": 1.728811476668817,
      "grad_norm": 0.4244069755077362,
      "learning_rate": 8.965755247555008e-07,
      "loss": 0.4554,
      "step": 56278
    },
    {
      "epoch": 1.7288421958037663,
      "grad_norm": 0.501154363155365,
      "learning_rate": 8.963755282547638e-07,
      "loss": 0.5161,
      "step": 56279
    },
    {
      "epoch": 1.7288729149387154,
      "grad_norm": 0.47178518772125244,
      "learning_rate": 8.961755530161731e-07,
      "loss": 0.4429,
      "step": 56280
    },
    {
      "epoch": 1.7289036340736645,
      "grad_norm": 0.4346139132976532,
      "learning_rate": 8.95975599040203e-07,
      "loss": 0.4808,
      "step": 56281
    },
    {
      "epoch": 1.7289343532086137,
      "grad_norm": 0.43225961923599243,
      "learning_rate": 8.957756663273176e-07,
      "loss": 0.491,
      "step": 56282
    },
    {
      "epoch": 1.7289650723435628,
      "grad_norm": 0.4474698007106781,
      "learning_rate": 8.955757548779843e-07,
      "loss": 0.5233,
      "step": 56283
    },
    {
      "epoch": 1.728995791478512,
      "grad_norm": 0.40521717071533203,
      "learning_rate": 8.953758646926692e-07,
      "loss": 0.3666,
      "step": 56284
    },
    {
      "epoch": 1.729026510613461,
      "grad_norm": 0.40688949823379517,
      "learning_rate": 8.951759957718386e-07,
      "loss": 0.4522,
      "step": 56285
    },
    {
      "epoch": 1.7290572297484101,
      "grad_norm": 0.45339468121528625,
      "learning_rate": 8.949761481159613e-07,
      "loss": 0.4839,
      "step": 56286
    },
    {
      "epoch": 1.7290879488833595,
      "grad_norm": 0.456297367811203,
      "learning_rate": 8.947763217255035e-07,
      "loss": 0.4329,
      "step": 56287
    },
    {
      "epoch": 1.7291186680183086,
      "grad_norm": 0.43552467226982117,
      "learning_rate": 8.945765166009313e-07,
      "loss": 0.5768,
      "step": 56288
    },
    {
      "epoch": 1.7291493871532577,
      "grad_norm": 0.4458226263523102,
      "learning_rate": 8.9437673274271e-07,
      "loss": 0.4577,
      "step": 56289
    },
    {
      "epoch": 1.729180106288207,
      "grad_norm": 0.4333151578903198,
      "learning_rate": 8.941769701513093e-07,
      "loss": 0.4932,
      "step": 56290
    },
    {
      "epoch": 1.7292108254231562,
      "grad_norm": 0.4358968734741211,
      "learning_rate": 8.939772288271952e-07,
      "loss": 0.5127,
      "step": 56291
    },
    {
      "epoch": 1.7292415445581053,
      "grad_norm": 0.4441421926021576,
      "learning_rate": 8.937775087708312e-07,
      "loss": 0.4646,
      "step": 56292
    },
    {
      "epoch": 1.7292722636930544,
      "grad_norm": 0.39746034145355225,
      "learning_rate": 8.935778099826864e-07,
      "loss": 0.5459,
      "step": 56293
    },
    {
      "epoch": 1.7293029828280035,
      "grad_norm": 0.5081448554992676,
      "learning_rate": 8.933781324632262e-07,
      "loss": 0.4712,
      "step": 56294
    },
    {
      "epoch": 1.7293337019629527,
      "grad_norm": 0.4386121928691864,
      "learning_rate": 8.93178476212917e-07,
      "loss": 0.5094,
      "step": 56295
    },
    {
      "epoch": 1.7293644210979018,
      "grad_norm": 0.442860871553421,
      "learning_rate": 8.929788412322282e-07,
      "loss": 0.4891,
      "step": 56296
    },
    {
      "epoch": 1.729395140232851,
      "grad_norm": 0.9357380867004395,
      "learning_rate": 8.927792275216208e-07,
      "loss": 0.4724,
      "step": 56297
    },
    {
      "epoch": 1.7294258593678002,
      "grad_norm": 0.43145981431007385,
      "learning_rate": 8.92579635081564e-07,
      "loss": 0.5192,
      "step": 56298
    },
    {
      "epoch": 1.7294565785027494,
      "grad_norm": 0.47570332884788513,
      "learning_rate": 8.923800639125235e-07,
      "loss": 0.4818,
      "step": 56299
    },
    {
      "epoch": 1.7294872976376985,
      "grad_norm": 0.41456300020217896,
      "learning_rate": 8.921805140149675e-07,
      "loss": 0.4482,
      "step": 56300
    },
    {
      "epoch": 1.7295180167726478,
      "grad_norm": 0.45411837100982666,
      "learning_rate": 8.919809853893579e-07,
      "loss": 0.4817,
      "step": 56301
    },
    {
      "epoch": 1.729548735907597,
      "grad_norm": 0.44237372279167175,
      "learning_rate": 8.917814780361622e-07,
      "loss": 0.466,
      "step": 56302
    },
    {
      "epoch": 1.729579455042546,
      "grad_norm": 0.46011677384376526,
      "learning_rate": 8.915819919558477e-07,
      "loss": 0.423,
      "step": 56303
    },
    {
      "epoch": 1.7296101741774952,
      "grad_norm": 0.4033450186252594,
      "learning_rate": 8.913825271488807e-07,
      "loss": 0.4973,
      "step": 56304
    },
    {
      "epoch": 1.7296408933124443,
      "grad_norm": 0.423753559589386,
      "learning_rate": 8.911830836157254e-07,
      "loss": 0.4256,
      "step": 56305
    },
    {
      "epoch": 1.7296716124473934,
      "grad_norm": 0.44015857577323914,
      "learning_rate": 8.909836613568468e-07,
      "loss": 0.5346,
      "step": 56306
    },
    {
      "epoch": 1.7297023315823425,
      "grad_norm": 0.431221067905426,
      "learning_rate": 8.907842603727124e-07,
      "loss": 0.4225,
      "step": 56307
    },
    {
      "epoch": 1.7297330507172917,
      "grad_norm": 0.4527120590209961,
      "learning_rate": 8.905848806637895e-07,
      "loss": 0.5018,
      "step": 56308
    },
    {
      "epoch": 1.729763769852241,
      "grad_norm": 0.4752584397792816,
      "learning_rate": 8.903855222305402e-07,
      "loss": 0.4556,
      "step": 56309
    },
    {
      "epoch": 1.7297944889871901,
      "grad_norm": 0.4391700327396393,
      "learning_rate": 8.901861850734339e-07,
      "loss": 0.5055,
      "step": 56310
    },
    {
      "epoch": 1.7298252081221392,
      "grad_norm": 0.466119647026062,
      "learning_rate": 8.899868691929292e-07,
      "loss": 0.502,
      "step": 56311
    },
    {
      "epoch": 1.7298559272570886,
      "grad_norm": 0.42635273933410645,
      "learning_rate": 8.89787574589499e-07,
      "loss": 0.5006,
      "step": 56312
    },
    {
      "epoch": 1.7298866463920377,
      "grad_norm": 0.47788769006729126,
      "learning_rate": 8.895883012636087e-07,
      "loss": 0.4348,
      "step": 56313
    },
    {
      "epoch": 1.7299173655269868,
      "grad_norm": 0.46236634254455566,
      "learning_rate": 8.893890492157176e-07,
      "loss": 0.4516,
      "step": 56314
    },
    {
      "epoch": 1.729948084661936,
      "grad_norm": 0.4537629187107086,
      "learning_rate": 8.891898184462978e-07,
      "loss": 0.4774,
      "step": 56315
    },
    {
      "epoch": 1.729978803796885,
      "grad_norm": 0.45414048433303833,
      "learning_rate": 8.889906089558075e-07,
      "loss": 0.4576,
      "step": 56316
    },
    {
      "epoch": 1.7300095229318342,
      "grad_norm": 0.44350138306617737,
      "learning_rate": 8.887914207447191e-07,
      "loss": 0.4633,
      "step": 56317
    },
    {
      "epoch": 1.7300402420667833,
      "grad_norm": 0.39540836215019226,
      "learning_rate": 8.88592253813494e-07,
      "loss": 0.5586,
      "step": 56318
    },
    {
      "epoch": 1.7300709612017324,
      "grad_norm": 0.4156914949417114,
      "learning_rate": 8.883931081625985e-07,
      "loss": 0.3536,
      "step": 56319
    },
    {
      "epoch": 1.7301016803366818,
      "grad_norm": 0.48633816838264465,
      "learning_rate": 8.881939837924958e-07,
      "loss": 0.439,
      "step": 56320
    },
    {
      "epoch": 1.7301323994716309,
      "grad_norm": 0.4156169891357422,
      "learning_rate": 8.879948807036531e-07,
      "loss": 0.4645,
      "step": 56321
    },
    {
      "epoch": 1.73016311860658,
      "grad_norm": 0.4632459878921509,
      "learning_rate": 8.877957988965336e-07,
      "loss": 0.4337,
      "step": 56322
    },
    {
      "epoch": 1.7301938377415294,
      "grad_norm": 0.4286767542362213,
      "learning_rate": 8.875967383716066e-07,
      "loss": 0.4151,
      "step": 56323
    },
    {
      "epoch": 1.7302245568764785,
      "grad_norm": 0.5203047394752502,
      "learning_rate": 8.873976991293309e-07,
      "loss": 0.5616,
      "step": 56324
    },
    {
      "epoch": 1.7302552760114276,
      "grad_norm": 0.5328221917152405,
      "learning_rate": 8.871986811701749e-07,
      "loss": 0.3942,
      "step": 56325
    },
    {
      "epoch": 1.7302859951463767,
      "grad_norm": 0.4022914171218872,
      "learning_rate": 8.869996844946027e-07,
      "loss": 0.4588,
      "step": 56326
    },
    {
      "epoch": 1.7303167142813258,
      "grad_norm": 0.42181944847106934,
      "learning_rate": 8.868007091030806e-07,
      "loss": 0.5031,
      "step": 56327
    },
    {
      "epoch": 1.730347433416275,
      "grad_norm": 0.4491271674633026,
      "learning_rate": 8.866017549960703e-07,
      "loss": 0.4396,
      "step": 56328
    },
    {
      "epoch": 1.730378152551224,
      "grad_norm": 0.43318572640419006,
      "learning_rate": 8.864028221740383e-07,
      "loss": 0.5429,
      "step": 56329
    },
    {
      "epoch": 1.7304088716861732,
      "grad_norm": 0.4381812512874603,
      "learning_rate": 8.862039106374487e-07,
      "loss": 0.5364,
      "step": 56330
    },
    {
      "epoch": 1.7304395908211225,
      "grad_norm": 0.4485565423965454,
      "learning_rate": 8.860050203867665e-07,
      "loss": 0.3881,
      "step": 56331
    },
    {
      "epoch": 1.7304703099560717,
      "grad_norm": 0.4176557660102844,
      "learning_rate": 8.85806151422458e-07,
      "loss": 0.4953,
      "step": 56332
    },
    {
      "epoch": 1.7305010290910208,
      "grad_norm": 0.444182813167572,
      "learning_rate": 8.856073037449842e-07,
      "loss": 0.4307,
      "step": 56333
    },
    {
      "epoch": 1.7305317482259701,
      "grad_norm": 0.4381738603115082,
      "learning_rate": 8.8540847735481e-07,
      "loss": 0.4633,
      "step": 56334
    },
    {
      "epoch": 1.7305624673609192,
      "grad_norm": 0.46188661456108093,
      "learning_rate": 8.852096722524017e-07,
      "loss": 0.4537,
      "step": 56335
    },
    {
      "epoch": 1.7305931864958684,
      "grad_norm": 0.40286609530448914,
      "learning_rate": 8.850108884382247e-07,
      "loss": 0.4654,
      "step": 56336
    },
    {
      "epoch": 1.7306239056308175,
      "grad_norm": 0.385529488325119,
      "learning_rate": 8.848121259127395e-07,
      "loss": 0.4008,
      "step": 56337
    },
    {
      "epoch": 1.7306546247657666,
      "grad_norm": 0.4685816764831543,
      "learning_rate": 8.846133846764115e-07,
      "loss": 0.3806,
      "step": 56338
    },
    {
      "epoch": 1.7306853439007157,
      "grad_norm": 0.45188161730766296,
      "learning_rate": 8.844146647297059e-07,
      "loss": 0.478,
      "step": 56339
    },
    {
      "epoch": 1.7307160630356648,
      "grad_norm": 0.5220999717712402,
      "learning_rate": 8.842159660730887e-07,
      "loss": 0.5493,
      "step": 56340
    },
    {
      "epoch": 1.730746782170614,
      "grad_norm": 0.44127339124679565,
      "learning_rate": 8.840172887070197e-07,
      "loss": 0.4875,
      "step": 56341
    },
    {
      "epoch": 1.730777501305563,
      "grad_norm": 0.4072112739086151,
      "learning_rate": 8.838186326319665e-07,
      "loss": 0.4706,
      "step": 56342
    },
    {
      "epoch": 1.7308082204405124,
      "grad_norm": 0.4167666435241699,
      "learning_rate": 8.836199978483883e-07,
      "loss": 0.5314,
      "step": 56343
    },
    {
      "epoch": 1.7308389395754615,
      "grad_norm": 0.4379953444004059,
      "learning_rate": 8.834213843567562e-07,
      "loss": 0.5098,
      "step": 56344
    },
    {
      "epoch": 1.7308696587104109,
      "grad_norm": 0.4351004660129547,
      "learning_rate": 8.832227921575276e-07,
      "loss": 0.4956,
      "step": 56345
    },
    {
      "epoch": 1.73090037784536,
      "grad_norm": 0.4075761139392853,
      "learning_rate": 8.830242212511708e-07,
      "loss": 0.5179,
      "step": 56346
    },
    {
      "epoch": 1.7309310969803091,
      "grad_norm": 0.48428162932395935,
      "learning_rate": 8.828256716381444e-07,
      "loss": 0.444,
      "step": 56347
    },
    {
      "epoch": 1.7309618161152582,
      "grad_norm": 0.44776782393455505,
      "learning_rate": 8.82627143318917e-07,
      "loss": 0.5849,
      "step": 56348
    },
    {
      "epoch": 1.7309925352502074,
      "grad_norm": 0.4153946340084076,
      "learning_rate": 8.824286362939527e-07,
      "loss": 0.4029,
      "step": 56349
    },
    {
      "epoch": 1.7310232543851565,
      "grad_norm": 0.5125724673271179,
      "learning_rate": 8.82230150563711e-07,
      "loss": 0.4241,
      "step": 56350
    },
    {
      "epoch": 1.7310539735201056,
      "grad_norm": 0.39381662011146545,
      "learning_rate": 8.820316861286593e-07,
      "loss": 0.4343,
      "step": 56351
    },
    {
      "epoch": 1.7310846926550547,
      "grad_norm": 0.46737757325172424,
      "learning_rate": 8.818332429892562e-07,
      "loss": 0.4308,
      "step": 56352
    },
    {
      "epoch": 1.7311154117900038,
      "grad_norm": 0.4176735281944275,
      "learning_rate": 8.816348211459714e-07,
      "loss": 0.4533,
      "step": 56353
    },
    {
      "epoch": 1.7311461309249532,
      "grad_norm": 0.4205296039581299,
      "learning_rate": 8.814364205992643e-07,
      "loss": 0.4478,
      "step": 56354
    },
    {
      "epoch": 1.7311768500599023,
      "grad_norm": 0.3843335211277008,
      "learning_rate": 8.812380413496002e-07,
      "loss": 0.3787,
      "step": 56355
    },
    {
      "epoch": 1.7312075691948516,
      "grad_norm": 0.8510516881942749,
      "learning_rate": 8.810396833974399e-07,
      "loss": 0.4792,
      "step": 56356
    },
    {
      "epoch": 1.7312382883298008,
      "grad_norm": 0.43699774146080017,
      "learning_rate": 8.808413467432486e-07,
      "loss": 0.3947,
      "step": 56357
    },
    {
      "epoch": 1.7312690074647499,
      "grad_norm": 0.406809538602829,
      "learning_rate": 8.806430313874892e-07,
      "loss": 0.3967,
      "step": 56358
    },
    {
      "epoch": 1.731299726599699,
      "grad_norm": 0.44237279891967773,
      "learning_rate": 8.804447373306269e-07,
      "loss": 0.4629,
      "step": 56359
    },
    {
      "epoch": 1.7313304457346481,
      "grad_norm": 0.4707309603691101,
      "learning_rate": 8.802464645731201e-07,
      "loss": 0.4427,
      "step": 56360
    },
    {
      "epoch": 1.7313611648695972,
      "grad_norm": 0.45859867334365845,
      "learning_rate": 8.800482131154353e-07,
      "loss": 0.4443,
      "step": 56361
    },
    {
      "epoch": 1.7313918840045464,
      "grad_norm": 0.4818471670150757,
      "learning_rate": 8.798499829580343e-07,
      "loss": 0.5141,
      "step": 56362
    },
    {
      "epoch": 1.7314226031394955,
      "grad_norm": 0.45740875601768494,
      "learning_rate": 8.796517741013833e-07,
      "loss": 0.4338,
      "step": 56363
    },
    {
      "epoch": 1.7314533222744446,
      "grad_norm": 0.3984355032444,
      "learning_rate": 8.794535865459397e-07,
      "loss": 0.4819,
      "step": 56364
    },
    {
      "epoch": 1.731484041409394,
      "grad_norm": 0.40794044733047485,
      "learning_rate": 8.792554202921699e-07,
      "loss": 0.4235,
      "step": 56365
    },
    {
      "epoch": 1.731514760544343,
      "grad_norm": 0.4782562553882599,
      "learning_rate": 8.790572753405357e-07,
      "loss": 0.4171,
      "step": 56366
    },
    {
      "epoch": 1.7315454796792922,
      "grad_norm": 0.4239922761917114,
      "learning_rate": 8.788591516915013e-07,
      "loss": 0.3749,
      "step": 56367
    },
    {
      "epoch": 1.7315761988142415,
      "grad_norm": 0.442595511674881,
      "learning_rate": 8.786610493455294e-07,
      "loss": 0.5052,
      "step": 56368
    },
    {
      "epoch": 1.7316069179491906,
      "grad_norm": 0.48681169748306274,
      "learning_rate": 8.784629683030787e-07,
      "loss": 0.4811,
      "step": 56369
    },
    {
      "epoch": 1.7316376370841398,
      "grad_norm": 0.42761147022247314,
      "learning_rate": 8.782649085646167e-07,
      "loss": 0.4258,
      "step": 56370
    },
    {
      "epoch": 1.7316683562190889,
      "grad_norm": 0.45617133378982544,
      "learning_rate": 8.780668701306027e-07,
      "loss": 0.4692,
      "step": 56371
    },
    {
      "epoch": 1.731699075354038,
      "grad_norm": 0.5095930099487305,
      "learning_rate": 8.778688530015034e-07,
      "loss": 0.5074,
      "step": 56372
    },
    {
      "epoch": 1.7317297944889871,
      "grad_norm": 0.4051453769207001,
      "learning_rate": 8.776708571777758e-07,
      "loss": 0.5047,
      "step": 56373
    },
    {
      "epoch": 1.7317605136239362,
      "grad_norm": 0.4426013231277466,
      "learning_rate": 8.774728826598855e-07,
      "loss": 0.5543,
      "step": 56374
    },
    {
      "epoch": 1.7317912327588854,
      "grad_norm": 0.40411368012428284,
      "learning_rate": 8.77274929448294e-07,
      "loss": 0.4162,
      "step": 56375
    },
    {
      "epoch": 1.7318219518938347,
      "grad_norm": 0.40092170238494873,
      "learning_rate": 8.770769975434667e-07,
      "loss": 0.4173,
      "step": 56376
    },
    {
      "epoch": 1.7318526710287838,
      "grad_norm": 0.4322882294654846,
      "learning_rate": 8.768790869458598e-07,
      "loss": 0.5062,
      "step": 56377
    },
    {
      "epoch": 1.731883390163733,
      "grad_norm": 0.4038248062133789,
      "learning_rate": 8.76681197655942e-07,
      "loss": 0.5088,
      "step": 56378
    },
    {
      "epoch": 1.7319141092986823,
      "grad_norm": 0.4821245074272156,
      "learning_rate": 8.764833296741693e-07,
      "loss": 0.468,
      "step": 56379
    },
    {
      "epoch": 1.7319448284336314,
      "grad_norm": 0.44115951657295227,
      "learning_rate": 8.762854830010093e-07,
      "loss": 0.402,
      "step": 56380
    },
    {
      "epoch": 1.7319755475685805,
      "grad_norm": 0.4462549686431885,
      "learning_rate": 8.760876576369204e-07,
      "loss": 0.4855,
      "step": 56381
    },
    {
      "epoch": 1.7320062667035296,
      "grad_norm": 0.4961947500705719,
      "learning_rate": 8.758898535823679e-07,
      "loss": 0.4469,
      "step": 56382
    },
    {
      "epoch": 1.7320369858384788,
      "grad_norm": 0.42963144183158875,
      "learning_rate": 8.756920708378103e-07,
      "loss": 0.5091,
      "step": 56383
    },
    {
      "epoch": 1.7320677049734279,
      "grad_norm": 0.45734676718711853,
      "learning_rate": 8.754943094037094e-07,
      "loss": 0.3891,
      "step": 56384
    },
    {
      "epoch": 1.732098424108377,
      "grad_norm": 0.43001270294189453,
      "learning_rate": 8.752965692805315e-07,
      "loss": 0.4562,
      "step": 56385
    },
    {
      "epoch": 1.7321291432433261,
      "grad_norm": 0.4698764681816101,
      "learning_rate": 8.750988504687341e-07,
      "loss": 0.4139,
      "step": 56386
    },
    {
      "epoch": 1.7321598623782755,
      "grad_norm": 0.4451736807823181,
      "learning_rate": 8.749011529687834e-07,
      "loss": 0.4156,
      "step": 56387
    },
    {
      "epoch": 1.7321905815132246,
      "grad_norm": 0.4200718402862549,
      "learning_rate": 8.747034767811335e-07,
      "loss": 0.4219,
      "step": 56388
    },
    {
      "epoch": 1.7322213006481737,
      "grad_norm": 0.4421858787536621,
      "learning_rate": 8.745058219062553e-07,
      "loss": 0.5395,
      "step": 56389
    },
    {
      "epoch": 1.732252019783123,
      "grad_norm": 0.45563432574272156,
      "learning_rate": 8.743081883446048e-07,
      "loss": 0.4964,
      "step": 56390
    },
    {
      "epoch": 1.7322827389180722,
      "grad_norm": 0.4344857335090637,
      "learning_rate": 8.74110576096645e-07,
      "loss": 0.4143,
      "step": 56391
    },
    {
      "epoch": 1.7323134580530213,
      "grad_norm": 0.45486390590667725,
      "learning_rate": 8.73912985162837e-07,
      "loss": 0.4722,
      "step": 56392
    },
    {
      "epoch": 1.7323441771879704,
      "grad_norm": 0.4682658016681671,
      "learning_rate": 8.737154155436423e-07,
      "loss": 0.4303,
      "step": 56393
    },
    {
      "epoch": 1.7323748963229195,
      "grad_norm": 0.47081270813941956,
      "learning_rate": 8.735178672395217e-07,
      "loss": 0.4928,
      "step": 56394
    },
    {
      "epoch": 1.7324056154578686,
      "grad_norm": 0.40419450402259827,
      "learning_rate": 8.733203402509404e-07,
      "loss": 0.4166,
      "step": 56395
    },
    {
      "epoch": 1.7324363345928178,
      "grad_norm": 0.4368768632411957,
      "learning_rate": 8.731228345783549e-07,
      "loss": 0.4194,
      "step": 56396
    },
    {
      "epoch": 1.7324670537277669,
      "grad_norm": 0.4959864616394043,
      "learning_rate": 8.729253502222279e-07,
      "loss": 0.4096,
      "step": 56397
    },
    {
      "epoch": 1.7324977728627162,
      "grad_norm": 0.4307889938354492,
      "learning_rate": 8.727278871830213e-07,
      "loss": 0.4534,
      "step": 56398
    },
    {
      "epoch": 1.7325284919976653,
      "grad_norm": 0.4704453945159912,
      "learning_rate": 8.725304454611982e-07,
      "loss": 0.4896,
      "step": 56399
    },
    {
      "epoch": 1.7325592111326145,
      "grad_norm": 0.4680406153202057,
      "learning_rate": 8.72333025057216e-07,
      "loss": 0.4402,
      "step": 56400
    },
    {
      "epoch": 1.7325899302675638,
      "grad_norm": 0.42313477396965027,
      "learning_rate": 8.721356259715363e-07,
      "loss": 0.4194,
      "step": 56401
    },
    {
      "epoch": 1.732620649402513,
      "grad_norm": 0.44832122325897217,
      "learning_rate": 8.719382482046223e-07,
      "loss": 0.5532,
      "step": 56402
    },
    {
      "epoch": 1.732651368537462,
      "grad_norm": 0.4859684109687805,
      "learning_rate": 8.717408917569347e-07,
      "loss": 0.4729,
      "step": 56403
    },
    {
      "epoch": 1.7326820876724112,
      "grad_norm": 0.45618411898612976,
      "learning_rate": 8.715435566289343e-07,
      "loss": 0.5049,
      "step": 56404
    },
    {
      "epoch": 1.7327128068073603,
      "grad_norm": 0.42799678444862366,
      "learning_rate": 8.713462428210805e-07,
      "loss": 0.3991,
      "step": 56405
    },
    {
      "epoch": 1.7327435259423094,
      "grad_norm": 0.46029141545295715,
      "learning_rate": 8.711489503338344e-07,
      "loss": 0.4828,
      "step": 56406
    },
    {
      "epoch": 1.7327742450772585,
      "grad_norm": 0.4365977346897125,
      "learning_rate": 8.709516791676587e-07,
      "loss": 0.4491,
      "step": 56407
    },
    {
      "epoch": 1.7328049642122076,
      "grad_norm": 0.45721715688705444,
      "learning_rate": 8.707544293230142e-07,
      "loss": 0.3608,
      "step": 56408
    },
    {
      "epoch": 1.732835683347157,
      "grad_norm": 0.4566730558872223,
      "learning_rate": 8.705572008003571e-07,
      "loss": 0.5035,
      "step": 56409
    },
    {
      "epoch": 1.732866402482106,
      "grad_norm": 0.4045201539993286,
      "learning_rate": 8.703599936001528e-07,
      "loss": 0.4364,
      "step": 56410
    },
    {
      "epoch": 1.7328971216170552,
      "grad_norm": 0.44847962260246277,
      "learning_rate": 8.701628077228596e-07,
      "loss": 0.4637,
      "step": 56411
    },
    {
      "epoch": 1.7329278407520046,
      "grad_norm": 1.426828384399414,
      "learning_rate": 8.699656431689407e-07,
      "loss": 0.3858,
      "step": 56412
    },
    {
      "epoch": 1.7329585598869537,
      "grad_norm": 0.4215613305568695,
      "learning_rate": 8.697684999388533e-07,
      "loss": 0.5185,
      "step": 56413
    },
    {
      "epoch": 1.7329892790219028,
      "grad_norm": 0.4632052481174469,
      "learning_rate": 8.695713780330606e-07,
      "loss": 0.5071,
      "step": 56414
    },
    {
      "epoch": 1.733019998156852,
      "grad_norm": 0.4938875138759613,
      "learning_rate": 8.693742774520187e-07,
      "loss": 0.5102,
      "step": 56415
    },
    {
      "epoch": 1.733050717291801,
      "grad_norm": 0.4690924882888794,
      "learning_rate": 8.691771981961939e-07,
      "loss": 0.53,
      "step": 56416
    },
    {
      "epoch": 1.7330814364267502,
      "grad_norm": 0.4269696772098541,
      "learning_rate": 8.689801402660414e-07,
      "loss": 0.4406,
      "step": 56417
    },
    {
      "epoch": 1.7331121555616993,
      "grad_norm": 0.4518410265445709,
      "learning_rate": 8.687831036620253e-07,
      "loss": 0.5034,
      "step": 56418
    },
    {
      "epoch": 1.7331428746966484,
      "grad_norm": 0.4340411126613617,
      "learning_rate": 8.685860883846031e-07,
      "loss": 0.514,
      "step": 56419
    },
    {
      "epoch": 1.7331735938315977,
      "grad_norm": 0.46917784214019775,
      "learning_rate": 8.683890944342355e-07,
      "loss": 0.5298,
      "step": 56420
    },
    {
      "epoch": 1.7332043129665469,
      "grad_norm": 0.36854174733161926,
      "learning_rate": 8.68192121811382e-07,
      "loss": 0.5364,
      "step": 56421
    },
    {
      "epoch": 1.733235032101496,
      "grad_norm": 0.4508639872074127,
      "learning_rate": 8.679951705165046e-07,
      "loss": 0.535,
      "step": 56422
    },
    {
      "epoch": 1.7332657512364453,
      "grad_norm": 0.45652294158935547,
      "learning_rate": 8.677982405500629e-07,
      "loss": 0.5075,
      "step": 56423
    },
    {
      "epoch": 1.7332964703713944,
      "grad_norm": 0.4143297076225281,
      "learning_rate": 8.676013319125154e-07,
      "loss": 0.4434,
      "step": 56424
    },
    {
      "epoch": 1.7333271895063436,
      "grad_norm": 0.4319387674331665,
      "learning_rate": 8.674044446043228e-07,
      "loss": 0.5358,
      "step": 56425
    },
    {
      "epoch": 1.7333579086412927,
      "grad_norm": 0.4616406559944153,
      "learning_rate": 8.672075786259437e-07,
      "loss": 0.4645,
      "step": 56426
    },
    {
      "epoch": 1.7333886277762418,
      "grad_norm": 0.45939046144485474,
      "learning_rate": 8.670107339778421e-07,
      "loss": 0.5206,
      "step": 56427
    },
    {
      "epoch": 1.733419346911191,
      "grad_norm": 0.45826879143714905,
      "learning_rate": 8.668139106604734e-07,
      "loss": 0.5317,
      "step": 56428
    },
    {
      "epoch": 1.73345006604614,
      "grad_norm": 0.42800259590148926,
      "learning_rate": 8.66617108674298e-07,
      "loss": 0.5069,
      "step": 56429
    },
    {
      "epoch": 1.7334807851810892,
      "grad_norm": 0.42699873447418213,
      "learning_rate": 8.664203280197758e-07,
      "loss": 0.3737,
      "step": 56430
    },
    {
      "epoch": 1.7335115043160385,
      "grad_norm": 0.5126444697380066,
      "learning_rate": 8.662235686973686e-07,
      "loss": 0.4012,
      "step": 56431
    },
    {
      "epoch": 1.7335422234509876,
      "grad_norm": 0.43632304668426514,
      "learning_rate": 8.660268307075326e-07,
      "loss": 0.4429,
      "step": 56432
    },
    {
      "epoch": 1.7335729425859367,
      "grad_norm": 0.4380393922328949,
      "learning_rate": 8.658301140507297e-07,
      "loss": 0.4346,
      "step": 56433
    },
    {
      "epoch": 1.733603661720886,
      "grad_norm": 0.4842790961265564,
      "learning_rate": 8.656334187274174e-07,
      "loss": 0.4932,
      "step": 56434
    },
    {
      "epoch": 1.7336343808558352,
      "grad_norm": 0.4859846532344818,
      "learning_rate": 8.654367447380584e-07,
      "loss": 0.4947,
      "step": 56435
    },
    {
      "epoch": 1.7336650999907843,
      "grad_norm": 0.4326359033584595,
      "learning_rate": 8.652400920831083e-07,
      "loss": 0.3911,
      "step": 56436
    },
    {
      "epoch": 1.7336958191257335,
      "grad_norm": 0.441400408744812,
      "learning_rate": 8.650434607630276e-07,
      "loss": 0.5454,
      "step": 56437
    },
    {
      "epoch": 1.7337265382606826,
      "grad_norm": 0.5243256688117981,
      "learning_rate": 8.648468507782759e-07,
      "loss": 0.5214,
      "step": 56438
    },
    {
      "epoch": 1.7337572573956317,
      "grad_norm": 0.42047318816185,
      "learning_rate": 8.646502621293118e-07,
      "loss": 0.4396,
      "step": 56439
    },
    {
      "epoch": 1.7337879765305808,
      "grad_norm": 0.4063499867916107,
      "learning_rate": 8.644536948165982e-07,
      "loss": 0.4584,
      "step": 56440
    },
    {
      "epoch": 1.73381869566553,
      "grad_norm": 0.4402499496936798,
      "learning_rate": 8.642571488405882e-07,
      "loss": 0.5312,
      "step": 56441
    },
    {
      "epoch": 1.7338494148004793,
      "grad_norm": 0.4288688004016876,
      "learning_rate": 8.640606242017436e-07,
      "loss": 0.4815,
      "step": 56442
    },
    {
      "epoch": 1.7338801339354284,
      "grad_norm": 0.40623044967651367,
      "learning_rate": 8.638641209005239e-07,
      "loss": 0.4719,
      "step": 56443
    },
    {
      "epoch": 1.7339108530703775,
      "grad_norm": 0.4232909083366394,
      "learning_rate": 8.636676389373888e-07,
      "loss": 0.4533,
      "step": 56444
    },
    {
      "epoch": 1.7339415722053269,
      "grad_norm": 0.46019962430000305,
      "learning_rate": 8.634711783127947e-07,
      "loss": 0.468,
      "step": 56445
    },
    {
      "epoch": 1.733972291340276,
      "grad_norm": 0.4178197681903839,
      "learning_rate": 8.632747390272034e-07,
      "loss": 0.4676,
      "step": 56446
    },
    {
      "epoch": 1.734003010475225,
      "grad_norm": 0.4096132218837738,
      "learning_rate": 8.63078321081069e-07,
      "loss": 0.4583,
      "step": 56447
    },
    {
      "epoch": 1.7340337296101742,
      "grad_norm": 0.43190550804138184,
      "learning_rate": 8.628819244748565e-07,
      "loss": 0.4808,
      "step": 56448
    },
    {
      "epoch": 1.7340644487451233,
      "grad_norm": 0.44446757435798645,
      "learning_rate": 8.626855492090191e-07,
      "loss": 0.4423,
      "step": 56449
    },
    {
      "epoch": 1.7340951678800725,
      "grad_norm": 0.44826963543891907,
      "learning_rate": 8.624891952840198e-07,
      "loss": 0.4562,
      "step": 56450
    },
    {
      "epoch": 1.7341258870150216,
      "grad_norm": 0.41566187143325806,
      "learning_rate": 8.622928627003125e-07,
      "loss": 0.4443,
      "step": 56451
    },
    {
      "epoch": 1.7341566061499707,
      "grad_norm": 0.44909873604774475,
      "learning_rate": 8.620965514583612e-07,
      "loss": 0.4848,
      "step": 56452
    },
    {
      "epoch": 1.7341873252849198,
      "grad_norm": 0.46753668785095215,
      "learning_rate": 8.619002615586191e-07,
      "loss": 0.4475,
      "step": 56453
    },
    {
      "epoch": 1.7342180444198692,
      "grad_norm": 0.41660448908805847,
      "learning_rate": 8.617039930015503e-07,
      "loss": 0.4781,
      "step": 56454
    },
    {
      "epoch": 1.7342487635548183,
      "grad_norm": 0.4494498074054718,
      "learning_rate": 8.615077457876075e-07,
      "loss": 0.4619,
      "step": 56455
    },
    {
      "epoch": 1.7342794826897676,
      "grad_norm": 0.4056394696235657,
      "learning_rate": 8.613115199172517e-07,
      "loss": 0.4423,
      "step": 56456
    },
    {
      "epoch": 1.7343102018247167,
      "grad_norm": 0.4853270649909973,
      "learning_rate": 8.611153153909402e-07,
      "loss": 0.3911,
      "step": 56457
    },
    {
      "epoch": 1.7343409209596659,
      "grad_norm": 0.4260139763355255,
      "learning_rate": 8.609191322091337e-07,
      "loss": 0.4186,
      "step": 56458
    },
    {
      "epoch": 1.734371640094615,
      "grad_norm": 0.4498307406902313,
      "learning_rate": 8.607229703722897e-07,
      "loss": 0.4264,
      "step": 56459
    },
    {
      "epoch": 1.734402359229564,
      "grad_norm": 0.40854063630104065,
      "learning_rate": 8.605268298808633e-07,
      "loss": 0.4629,
      "step": 56460
    },
    {
      "epoch": 1.7344330783645132,
      "grad_norm": 0.4711441397666931,
      "learning_rate": 8.603307107353154e-07,
      "loss": 0.47,
      "step": 56461
    },
    {
      "epoch": 1.7344637974994623,
      "grad_norm": 0.43368226289749146,
      "learning_rate": 8.601346129361032e-07,
      "loss": 0.4696,
      "step": 56462
    },
    {
      "epoch": 1.7344945166344115,
      "grad_norm": 0.561684787273407,
      "learning_rate": 8.599385364836876e-07,
      "loss": 0.4655,
      "step": 56463
    },
    {
      "epoch": 1.7345252357693606,
      "grad_norm": 0.43647301197052,
      "learning_rate": 8.597424813785216e-07,
      "loss": 0.4928,
      "step": 56464
    },
    {
      "epoch": 1.73455595490431,
      "grad_norm": 0.4912463426589966,
      "learning_rate": 8.595464476210647e-07,
      "loss": 0.4693,
      "step": 56465
    },
    {
      "epoch": 1.734586674039259,
      "grad_norm": 0.4278528094291687,
      "learning_rate": 8.593504352117765e-07,
      "loss": 0.523,
      "step": 56466
    },
    {
      "epoch": 1.7346173931742084,
      "grad_norm": 0.5614191889762878,
      "learning_rate": 8.591544441511146e-07,
      "loss": 0.4448,
      "step": 56467
    },
    {
      "epoch": 1.7346481123091575,
      "grad_norm": 0.43994349241256714,
      "learning_rate": 8.589584744395341e-07,
      "loss": 0.4589,
      "step": 56468
    },
    {
      "epoch": 1.7346788314441066,
      "grad_norm": 0.4708177149295807,
      "learning_rate": 8.587625260774956e-07,
      "loss": 0.5041,
      "step": 56469
    },
    {
      "epoch": 1.7347095505790557,
      "grad_norm": 0.4421263635158539,
      "learning_rate": 8.585665990654546e-07,
      "loss": 0.4421,
      "step": 56470
    },
    {
      "epoch": 1.7347402697140049,
      "grad_norm": 0.47046443819999695,
      "learning_rate": 8.583706934038716e-07,
      "loss": 0.4861,
      "step": 56471
    },
    {
      "epoch": 1.734770988848954,
      "grad_norm": 0.5931541919708252,
      "learning_rate": 8.581748090932007e-07,
      "loss": 0.5036,
      "step": 56472
    },
    {
      "epoch": 1.734801707983903,
      "grad_norm": 0.4293566644191742,
      "learning_rate": 8.579789461339005e-07,
      "loss": 0.4287,
      "step": 56473
    },
    {
      "epoch": 1.7348324271188522,
      "grad_norm": 0.4280758798122406,
      "learning_rate": 8.577831045264296e-07,
      "loss": 0.5191,
      "step": 56474
    },
    {
      "epoch": 1.7348631462538013,
      "grad_norm": 0.42054319381713867,
      "learning_rate": 8.575872842712451e-07,
      "loss": 0.4565,
      "step": 56475
    },
    {
      "epoch": 1.7348938653887507,
      "grad_norm": 0.41455814242362976,
      "learning_rate": 8.573914853688048e-07,
      "loss": 0.4553,
      "step": 56476
    },
    {
      "epoch": 1.7349245845236998,
      "grad_norm": 0.4399590790271759,
      "learning_rate": 8.571957078195636e-07,
      "loss": 0.4766,
      "step": 56477
    },
    {
      "epoch": 1.734955303658649,
      "grad_norm": 0.4585479497909546,
      "learning_rate": 8.569999516239813e-07,
      "loss": 0.5086,
      "step": 56478
    },
    {
      "epoch": 1.7349860227935983,
      "grad_norm": 0.41532471776008606,
      "learning_rate": 8.56804216782513e-07,
      "loss": 0.4641,
      "step": 56479
    },
    {
      "epoch": 1.7350167419285474,
      "grad_norm": 0.4796246290206909,
      "learning_rate": 8.566085032956195e-07,
      "loss": 0.5385,
      "step": 56480
    },
    {
      "epoch": 1.7350474610634965,
      "grad_norm": 0.44699808955192566,
      "learning_rate": 8.564128111637538e-07,
      "loss": 0.4073,
      "step": 56481
    },
    {
      "epoch": 1.7350781801984456,
      "grad_norm": 0.4088823199272156,
      "learning_rate": 8.562171403873754e-07,
      "loss": 0.5305,
      "step": 56482
    },
    {
      "epoch": 1.7351088993333947,
      "grad_norm": 0.42058658599853516,
      "learning_rate": 8.560214909669373e-07,
      "loss": 0.4032,
      "step": 56483
    },
    {
      "epoch": 1.7351396184683439,
      "grad_norm": 0.4449937045574188,
      "learning_rate": 8.558258629029037e-07,
      "loss": 0.4985,
      "step": 56484
    },
    {
      "epoch": 1.735170337603293,
      "grad_norm": 0.4418502748012543,
      "learning_rate": 8.556302561957252e-07,
      "loss": 0.4127,
      "step": 56485
    },
    {
      "epoch": 1.735201056738242,
      "grad_norm": 0.4491868317127228,
      "learning_rate": 8.554346708458627e-07,
      "loss": 0.4207,
      "step": 56486
    },
    {
      "epoch": 1.7352317758731914,
      "grad_norm": 0.39489710330963135,
      "learning_rate": 8.552391068537691e-07,
      "loss": 0.3752,
      "step": 56487
    },
    {
      "epoch": 1.7352624950081406,
      "grad_norm": 0.43620139360427856,
      "learning_rate": 8.55043564219904e-07,
      "loss": 0.5052,
      "step": 56488
    },
    {
      "epoch": 1.7352932141430897,
      "grad_norm": 0.41423898935317993,
      "learning_rate": 8.548480429447226e-07,
      "loss": 0.4117,
      "step": 56489
    },
    {
      "epoch": 1.735323933278039,
      "grad_norm": 0.43042489886283875,
      "learning_rate": 8.546525430286845e-07,
      "loss": 0.3997,
      "step": 56490
    },
    {
      "epoch": 1.7353546524129881,
      "grad_norm": 0.4785027503967285,
      "learning_rate": 8.544570644722417e-07,
      "loss": 0.5016,
      "step": 56491
    },
    {
      "epoch": 1.7353853715479373,
      "grad_norm": 0.43326032161712646,
      "learning_rate": 8.542616072758536e-07,
      "loss": 0.466,
      "step": 56492
    },
    {
      "epoch": 1.7354160906828864,
      "grad_norm": 0.4366353452205658,
      "learning_rate": 8.540661714399768e-07,
      "loss": 0.4873,
      "step": 56493
    },
    {
      "epoch": 1.7354468098178355,
      "grad_norm": 0.42083051800727844,
      "learning_rate": 8.538707569650661e-07,
      "loss": 0.5091,
      "step": 56494
    },
    {
      "epoch": 1.7354775289527846,
      "grad_norm": 0.4364616572856903,
      "learning_rate": 8.536753638515816e-07,
      "loss": 0.4415,
      "step": 56495
    },
    {
      "epoch": 1.7355082480877337,
      "grad_norm": 0.4172971844673157,
      "learning_rate": 8.534799920999748e-07,
      "loss": 0.5248,
      "step": 56496
    },
    {
      "epoch": 1.7355389672226829,
      "grad_norm": 0.39401480555534363,
      "learning_rate": 8.532846417107044e-07,
      "loss": 0.4843,
      "step": 56497
    },
    {
      "epoch": 1.7355696863576322,
      "grad_norm": 0.4290648102760315,
      "learning_rate": 8.530893126842266e-07,
      "loss": 0.4906,
      "step": 56498
    },
    {
      "epoch": 1.7356004054925813,
      "grad_norm": 0.4694846272468567,
      "learning_rate": 8.528940050209989e-07,
      "loss": 0.4541,
      "step": 56499
    },
    {
      "epoch": 1.7356311246275304,
      "grad_norm": 0.4518360495567322,
      "learning_rate": 8.526987187214753e-07,
      "loss": 0.5068,
      "step": 56500
    },
    {
      "epoch": 1.7356618437624798,
      "grad_norm": 0.4104233980178833,
      "learning_rate": 8.525034537861121e-07,
      "loss": 0.5027,
      "step": 56501
    },
    {
      "epoch": 1.735692562897429,
      "grad_norm": 0.41769877076148987,
      "learning_rate": 8.523082102153656e-07,
      "loss": 0.4626,
      "step": 56502
    },
    {
      "epoch": 1.735723282032378,
      "grad_norm": 0.5410337448120117,
      "learning_rate": 8.521129880096946e-07,
      "loss": 0.4879,
      "step": 56503
    },
    {
      "epoch": 1.7357540011673271,
      "grad_norm": 0.4098431169986725,
      "learning_rate": 8.519177871695506e-07,
      "loss": 0.4125,
      "step": 56504
    },
    {
      "epoch": 1.7357847203022763,
      "grad_norm": 0.4493621289730072,
      "learning_rate": 8.517226076953911e-07,
      "loss": 0.4181,
      "step": 56505
    },
    {
      "epoch": 1.7358154394372254,
      "grad_norm": 0.43152859807014465,
      "learning_rate": 8.515274495876724e-07,
      "loss": 0.4131,
      "step": 56506
    },
    {
      "epoch": 1.7358461585721745,
      "grad_norm": 0.43109625577926636,
      "learning_rate": 8.51332312846852e-07,
      "loss": 0.451,
      "step": 56507
    },
    {
      "epoch": 1.7358768777071236,
      "grad_norm": 0.40689054131507874,
      "learning_rate": 8.511371974733828e-07,
      "loss": 0.4474,
      "step": 56508
    },
    {
      "epoch": 1.735907596842073,
      "grad_norm": 0.44103577733039856,
      "learning_rate": 8.509421034677223e-07,
      "loss": 0.5075,
      "step": 56509
    },
    {
      "epoch": 1.735938315977022,
      "grad_norm": 0.4452926218509674,
      "learning_rate": 8.507470308303234e-07,
      "loss": 0.513,
      "step": 56510
    },
    {
      "epoch": 1.7359690351119712,
      "grad_norm": 0.432226300239563,
      "learning_rate": 8.505519795616457e-07,
      "loss": 0.4876,
      "step": 56511
    },
    {
      "epoch": 1.7359997542469205,
      "grad_norm": 0.4366403818130493,
      "learning_rate": 8.503569496621422e-07,
      "loss": 0.4618,
      "step": 56512
    },
    {
      "epoch": 1.7360304733818697,
      "grad_norm": 0.41216331720352173,
      "learning_rate": 8.501619411322692e-07,
      "loss": 0.5565,
      "step": 56513
    },
    {
      "epoch": 1.7360611925168188,
      "grad_norm": 0.4273361265659332,
      "learning_rate": 8.499669539724808e-07,
      "loss": 0.4285,
      "step": 56514
    },
    {
      "epoch": 1.736091911651768,
      "grad_norm": 0.3938898742198944,
      "learning_rate": 8.497719881832344e-07,
      "loss": 0.4751,
      "step": 56515
    },
    {
      "epoch": 1.736122630786717,
      "grad_norm": 0.425078421831131,
      "learning_rate": 8.495770437649864e-07,
      "loss": 0.4873,
      "step": 56516
    },
    {
      "epoch": 1.7361533499216661,
      "grad_norm": 0.43873751163482666,
      "learning_rate": 8.493821207181885e-07,
      "loss": 0.4907,
      "step": 56517
    },
    {
      "epoch": 1.7361840690566153,
      "grad_norm": 0.4480544924736023,
      "learning_rate": 8.491872190432992e-07,
      "loss": 0.4321,
      "step": 56518
    },
    {
      "epoch": 1.7362147881915644,
      "grad_norm": 0.43013495206832886,
      "learning_rate": 8.489923387407695e-07,
      "loss": 0.457,
      "step": 56519
    },
    {
      "epoch": 1.7362455073265137,
      "grad_norm": 0.4319963753223419,
      "learning_rate": 8.487974798110599e-07,
      "loss": 0.4374,
      "step": 56520
    },
    {
      "epoch": 1.7362762264614628,
      "grad_norm": 0.4706825017929077,
      "learning_rate": 8.486026422546211e-07,
      "loss": 0.5443,
      "step": 56521
    },
    {
      "epoch": 1.736306945596412,
      "grad_norm": 0.43788138031959534,
      "learning_rate": 8.484078260719119e-07,
      "loss": 0.463,
      "step": 56522
    },
    {
      "epoch": 1.7363376647313613,
      "grad_norm": 0.4193810820579529,
      "learning_rate": 8.482130312633841e-07,
      "loss": 0.4926,
      "step": 56523
    },
    {
      "epoch": 1.7363683838663104,
      "grad_norm": 0.4294057786464691,
      "learning_rate": 8.480182578294938e-07,
      "loss": 0.4844,
      "step": 56524
    },
    {
      "epoch": 1.7363991030012595,
      "grad_norm": 0.44706711173057556,
      "learning_rate": 8.478235057706963e-07,
      "loss": 0.427,
      "step": 56525
    },
    {
      "epoch": 1.7364298221362087,
      "grad_norm": 0.6646106839179993,
      "learning_rate": 8.476287750874468e-07,
      "loss": 0.4252,
      "step": 56526
    },
    {
      "epoch": 1.7364605412711578,
      "grad_norm": 0.4617803990840912,
      "learning_rate": 8.474340657801983e-07,
      "loss": 0.4822,
      "step": 56527
    },
    {
      "epoch": 1.736491260406107,
      "grad_norm": 0.4235909879207611,
      "learning_rate": 8.47239377849407e-07,
      "loss": 0.4165,
      "step": 56528
    },
    {
      "epoch": 1.736521979541056,
      "grad_norm": 0.4459506571292877,
      "learning_rate": 8.470447112955271e-07,
      "loss": 0.5337,
      "step": 56529
    },
    {
      "epoch": 1.7365526986760051,
      "grad_norm": 0.4450555443763733,
      "learning_rate": 8.468500661190138e-07,
      "loss": 0.4474,
      "step": 56530
    },
    {
      "epoch": 1.7365834178109545,
      "grad_norm": 0.3977139890193939,
      "learning_rate": 8.466554423203232e-07,
      "loss": 0.4149,
      "step": 56531
    },
    {
      "epoch": 1.7366141369459036,
      "grad_norm": 0.43161410093307495,
      "learning_rate": 8.464608398999063e-07,
      "loss": 0.5311,
      "step": 56532
    },
    {
      "epoch": 1.7366448560808527,
      "grad_norm": 0.4632638990879059,
      "learning_rate": 8.462662588582193e-07,
      "loss": 0.4298,
      "step": 56533
    },
    {
      "epoch": 1.736675575215802,
      "grad_norm": 0.46674013137817383,
      "learning_rate": 8.460716991957163e-07,
      "loss": 0.5612,
      "step": 56534
    },
    {
      "epoch": 1.7367062943507512,
      "grad_norm": 0.45433878898620605,
      "learning_rate": 8.458771609128547e-07,
      "loss": 0.4918,
      "step": 56535
    },
    {
      "epoch": 1.7367370134857003,
      "grad_norm": 0.4196849465370178,
      "learning_rate": 8.456826440100841e-07,
      "loss": 0.4336,
      "step": 56536
    },
    {
      "epoch": 1.7367677326206494,
      "grad_norm": 0.4168856143951416,
      "learning_rate": 8.454881484878608e-07,
      "loss": 0.503,
      "step": 56537
    },
    {
      "epoch": 1.7367984517555985,
      "grad_norm": 0.4100710153579712,
      "learning_rate": 8.452936743466389e-07,
      "loss": 0.3954,
      "step": 56538
    },
    {
      "epoch": 1.7368291708905477,
      "grad_norm": 0.5455772280693054,
      "learning_rate": 8.450992215868759e-07,
      "loss": 0.457,
      "step": 56539
    },
    {
      "epoch": 1.7368598900254968,
      "grad_norm": 0.4177546203136444,
      "learning_rate": 8.449047902090202e-07,
      "loss": 0.4081,
      "step": 56540
    },
    {
      "epoch": 1.736890609160446,
      "grad_norm": 0.41044291853904724,
      "learning_rate": 8.447103802135293e-07,
      "loss": 0.4547,
      "step": 56541
    },
    {
      "epoch": 1.7369213282953953,
      "grad_norm": 0.47043144702911377,
      "learning_rate": 8.445159916008571e-07,
      "loss": 0.4732,
      "step": 56542
    },
    {
      "epoch": 1.7369520474303444,
      "grad_norm": 0.4311014413833618,
      "learning_rate": 8.44321624371458e-07,
      "loss": 0.5186,
      "step": 56543
    },
    {
      "epoch": 1.7369827665652935,
      "grad_norm": 0.43725910782814026,
      "learning_rate": 8.441272785257837e-07,
      "loss": 0.4914,
      "step": 56544
    },
    {
      "epoch": 1.7370134857002428,
      "grad_norm": 0.4322315752506256,
      "learning_rate": 8.439329540642916e-07,
      "loss": 0.4804,
      "step": 56545
    },
    {
      "epoch": 1.737044204835192,
      "grad_norm": 0.4333855211734772,
      "learning_rate": 8.437386509874301e-07,
      "loss": 0.4883,
      "step": 56546
    },
    {
      "epoch": 1.737074923970141,
      "grad_norm": 0.4303877055644989,
      "learning_rate": 8.435443692956602e-07,
      "loss": 0.4457,
      "step": 56547
    },
    {
      "epoch": 1.7371056431050902,
      "grad_norm": 0.4308634102344513,
      "learning_rate": 8.433501089894302e-07,
      "loss": 0.5227,
      "step": 56548
    },
    {
      "epoch": 1.7371363622400393,
      "grad_norm": 0.43612563610076904,
      "learning_rate": 8.431558700691944e-07,
      "loss": 0.4997,
      "step": 56549
    },
    {
      "epoch": 1.7371670813749884,
      "grad_norm": 0.4558924734592438,
      "learning_rate": 8.429616525354101e-07,
      "loss": 0.5038,
      "step": 56550
    },
    {
      "epoch": 1.7371978005099376,
      "grad_norm": 0.43647870421409607,
      "learning_rate": 8.427674563885246e-07,
      "loss": 0.4454,
      "step": 56551
    },
    {
      "epoch": 1.7372285196448867,
      "grad_norm": 0.3891865015029907,
      "learning_rate": 8.425732816289989e-07,
      "loss": 0.4181,
      "step": 56552
    },
    {
      "epoch": 1.737259238779836,
      "grad_norm": 0.4340529143810272,
      "learning_rate": 8.423791282572814e-07,
      "loss": 0.4434,
      "step": 56553
    },
    {
      "epoch": 1.7372899579147851,
      "grad_norm": 0.43733665347099304,
      "learning_rate": 8.421849962738293e-07,
      "loss": 0.4658,
      "step": 56554
    },
    {
      "epoch": 1.7373206770497343,
      "grad_norm": 0.4415319561958313,
      "learning_rate": 8.419908856790893e-07,
      "loss": 0.5599,
      "step": 56555
    },
    {
      "epoch": 1.7373513961846836,
      "grad_norm": 0.44975200295448303,
      "learning_rate": 8.417967964735229e-07,
      "loss": 0.4595,
      "step": 56556
    },
    {
      "epoch": 1.7373821153196327,
      "grad_norm": 0.49825137853622437,
      "learning_rate": 8.416027286575779e-07,
      "loss": 0.3805,
      "step": 56557
    },
    {
      "epoch": 1.7374128344545818,
      "grad_norm": 0.421041339635849,
      "learning_rate": 8.414086822317103e-07,
      "loss": 0.5216,
      "step": 56558
    },
    {
      "epoch": 1.737443553589531,
      "grad_norm": 0.455291748046875,
      "learning_rate": 8.41214657196372e-07,
      "loss": 0.409,
      "step": 56559
    },
    {
      "epoch": 1.73747427272448,
      "grad_norm": 0.49966564774513245,
      "learning_rate": 8.410206535520149e-07,
      "loss": 0.4605,
      "step": 56560
    },
    {
      "epoch": 1.7375049918594292,
      "grad_norm": 0.4234888553619385,
      "learning_rate": 8.408266712990953e-07,
      "loss": 0.5029,
      "step": 56561
    },
    {
      "epoch": 1.7375357109943783,
      "grad_norm": 0.4575797915458679,
      "learning_rate": 8.406327104380651e-07,
      "loss": 0.4105,
      "step": 56562
    },
    {
      "epoch": 1.7375664301293274,
      "grad_norm": 0.4347330331802368,
      "learning_rate": 8.404387709693762e-07,
      "loss": 0.4723,
      "step": 56563
    },
    {
      "epoch": 1.7375971492642766,
      "grad_norm": 0.4376751184463501,
      "learning_rate": 8.402448528934825e-07,
      "loss": 0.3899,
      "step": 56564
    },
    {
      "epoch": 1.737627868399226,
      "grad_norm": 0.4099385142326355,
      "learning_rate": 8.400509562108361e-07,
      "loss": 0.4399,
      "step": 56565
    },
    {
      "epoch": 1.737658587534175,
      "grad_norm": 0.46108192205429077,
      "learning_rate": 8.39857080921892e-07,
      "loss": 0.4259,
      "step": 56566
    },
    {
      "epoch": 1.7376893066691244,
      "grad_norm": 0.4430907666683197,
      "learning_rate": 8.396632270270999e-07,
      "loss": 0.4737,
      "step": 56567
    },
    {
      "epoch": 1.7377200258040735,
      "grad_norm": 0.4252305030822754,
      "learning_rate": 8.394693945269139e-07,
      "loss": 0.4737,
      "step": 56568
    },
    {
      "epoch": 1.7377507449390226,
      "grad_norm": 0.4609736204147339,
      "learning_rate": 8.392755834217869e-07,
      "loss": 0.4623,
      "step": 56569
    },
    {
      "epoch": 1.7377814640739717,
      "grad_norm": 0.440923810005188,
      "learning_rate": 8.390817937121709e-07,
      "loss": 0.4803,
      "step": 56570
    },
    {
      "epoch": 1.7378121832089208,
      "grad_norm": 0.4083709120750427,
      "learning_rate": 8.388880253985221e-07,
      "loss": 0.451,
      "step": 56571
    },
    {
      "epoch": 1.73784290234387,
      "grad_norm": 0.42371994256973267,
      "learning_rate": 8.386942784812879e-07,
      "loss": 0.435,
      "step": 56572
    },
    {
      "epoch": 1.737873621478819,
      "grad_norm": 0.48179006576538086,
      "learning_rate": 8.385005529609224e-07,
      "loss": 0.4919,
      "step": 56573
    },
    {
      "epoch": 1.7379043406137682,
      "grad_norm": 0.4905507266521454,
      "learning_rate": 8.383068488378799e-07,
      "loss": 0.4167,
      "step": 56574
    },
    {
      "epoch": 1.7379350597487173,
      "grad_norm": 0.40026476979255676,
      "learning_rate": 8.381131661126129e-07,
      "loss": 0.3974,
      "step": 56575
    },
    {
      "epoch": 1.7379657788836667,
      "grad_norm": 0.4066495895385742,
      "learning_rate": 8.379195047855704e-07,
      "loss": 0.42,
      "step": 56576
    },
    {
      "epoch": 1.7379964980186158,
      "grad_norm": 0.459564745426178,
      "learning_rate": 8.377258648572074e-07,
      "loss": 0.4965,
      "step": 56577
    },
    {
      "epoch": 1.7380272171535651,
      "grad_norm": 0.4474621117115021,
      "learning_rate": 8.375322463279744e-07,
      "loss": 0.3773,
      "step": 56578
    },
    {
      "epoch": 1.7380579362885142,
      "grad_norm": 0.4301241636276245,
      "learning_rate": 8.373386491983271e-07,
      "loss": 0.5928,
      "step": 56579
    },
    {
      "epoch": 1.7380886554234634,
      "grad_norm": 0.41434404253959656,
      "learning_rate": 8.371450734687136e-07,
      "loss": 0.4875,
      "step": 56580
    },
    {
      "epoch": 1.7381193745584125,
      "grad_norm": 0.43039023876190186,
      "learning_rate": 8.369515191395894e-07,
      "loss": 0.5143,
      "step": 56581
    },
    {
      "epoch": 1.7381500936933616,
      "grad_norm": 0.5280080437660217,
      "learning_rate": 8.367579862114017e-07,
      "loss": 0.4741,
      "step": 56582
    },
    {
      "epoch": 1.7381808128283107,
      "grad_norm": 0.4527977406978607,
      "learning_rate": 8.365644746846091e-07,
      "loss": 0.4538,
      "step": 56583
    },
    {
      "epoch": 1.7382115319632598,
      "grad_norm": 0.44327056407928467,
      "learning_rate": 8.363709845596579e-07,
      "loss": 0.47,
      "step": 56584
    },
    {
      "epoch": 1.738242251098209,
      "grad_norm": 0.4467504918575287,
      "learning_rate": 8.361775158370023e-07,
      "loss": 0.5053,
      "step": 56585
    },
    {
      "epoch": 1.738272970233158,
      "grad_norm": 0.41102349758148193,
      "learning_rate": 8.359840685170961e-07,
      "loss": 0.4567,
      "step": 56586
    },
    {
      "epoch": 1.7383036893681074,
      "grad_norm": 0.4741474688053131,
      "learning_rate": 8.357906426003859e-07,
      "loss": 0.4476,
      "step": 56587
    },
    {
      "epoch": 1.7383344085030565,
      "grad_norm": 0.4302350878715515,
      "learning_rate": 8.355972380873301e-07,
      "loss": 0.4723,
      "step": 56588
    },
    {
      "epoch": 1.7383651276380057,
      "grad_norm": 0.5203745365142822,
      "learning_rate": 8.354038549783749e-07,
      "loss": 0.5423,
      "step": 56589
    },
    {
      "epoch": 1.738395846772955,
      "grad_norm": 0.4468132555484772,
      "learning_rate": 8.352104932739758e-07,
      "loss": 0.5056,
      "step": 56590
    },
    {
      "epoch": 1.7384265659079041,
      "grad_norm": 0.4220321774482727,
      "learning_rate": 8.35017152974581e-07,
      "loss": 0.4519,
      "step": 56591
    },
    {
      "epoch": 1.7384572850428532,
      "grad_norm": 0.4463399350643158,
      "learning_rate": 8.348238340806436e-07,
      "loss": 0.5235,
      "step": 56592
    },
    {
      "epoch": 1.7384880041778024,
      "grad_norm": 0.4713272154331207,
      "learning_rate": 8.346305365926155e-07,
      "loss": 0.4491,
      "step": 56593
    },
    {
      "epoch": 1.7385187233127515,
      "grad_norm": 0.5006008148193359,
      "learning_rate": 8.344372605109496e-07,
      "loss": 0.4668,
      "step": 56594
    },
    {
      "epoch": 1.7385494424477006,
      "grad_norm": 0.403897225856781,
      "learning_rate": 8.342440058360935e-07,
      "loss": 0.4592,
      "step": 56595
    },
    {
      "epoch": 1.7385801615826497,
      "grad_norm": 0.4962012469768524,
      "learning_rate": 8.34050772568501e-07,
      "loss": 0.506,
      "step": 56596
    },
    {
      "epoch": 1.7386108807175988,
      "grad_norm": 0.503887414932251,
      "learning_rate": 8.33857560708623e-07,
      "loss": 0.4548,
      "step": 56597
    },
    {
      "epoch": 1.7386415998525482,
      "grad_norm": 0.91653972864151,
      "learning_rate": 8.336643702569125e-07,
      "loss": 0.4442,
      "step": 56598
    },
    {
      "epoch": 1.7386723189874973,
      "grad_norm": 0.4193149209022522,
      "learning_rate": 8.334712012138168e-07,
      "loss": 0.452,
      "step": 56599
    },
    {
      "epoch": 1.7387030381224464,
      "grad_norm": 0.43696320056915283,
      "learning_rate": 8.332780535797902e-07,
      "loss": 0.5241,
      "step": 56600
    },
    {
      "epoch": 1.7387337572573958,
      "grad_norm": 0.41797202825546265,
      "learning_rate": 8.330849273552821e-07,
      "loss": 0.4951,
      "step": 56601
    },
    {
      "epoch": 1.7387644763923449,
      "grad_norm": 0.456983357667923,
      "learning_rate": 8.328918225407468e-07,
      "loss": 0.445,
      "step": 56602
    },
    {
      "epoch": 1.738795195527294,
      "grad_norm": 0.46860185265541077,
      "learning_rate": 8.326987391366304e-07,
      "loss": 0.4191,
      "step": 56603
    },
    {
      "epoch": 1.7388259146622431,
      "grad_norm": 0.40109530091285706,
      "learning_rate": 8.32505677143387e-07,
      "loss": 0.3807,
      "step": 56604
    },
    {
      "epoch": 1.7388566337971922,
      "grad_norm": 0.44796034693717957,
      "learning_rate": 8.323126365614664e-07,
      "loss": 0.3918,
      "step": 56605
    },
    {
      "epoch": 1.7388873529321414,
      "grad_norm": 0.3914903700351715,
      "learning_rate": 8.321196173913204e-07,
      "loss": 0.4724,
      "step": 56606
    },
    {
      "epoch": 1.7389180720670905,
      "grad_norm": 0.41385453939437866,
      "learning_rate": 8.319266196334008e-07,
      "loss": 0.4452,
      "step": 56607
    },
    {
      "epoch": 1.7389487912020396,
      "grad_norm": 0.45953530073165894,
      "learning_rate": 8.317336432881551e-07,
      "loss": 0.5598,
      "step": 56608
    },
    {
      "epoch": 1.738979510336989,
      "grad_norm": 0.4327622056007385,
      "learning_rate": 8.315406883560362e-07,
      "loss": 0.4739,
      "step": 56609
    },
    {
      "epoch": 1.739010229471938,
      "grad_norm": 0.42282551527023315,
      "learning_rate": 8.313477548374938e-07,
      "loss": 0.4801,
      "step": 56610
    },
    {
      "epoch": 1.7390409486068872,
      "grad_norm": 0.4837516248226166,
      "learning_rate": 8.311548427329808e-07,
      "loss": 0.4522,
      "step": 56611
    },
    {
      "epoch": 1.7390716677418365,
      "grad_norm": 0.46225643157958984,
      "learning_rate": 8.309619520429446e-07,
      "loss": 0.408,
      "step": 56612
    },
    {
      "epoch": 1.7391023868767856,
      "grad_norm": 0.4162982404232025,
      "learning_rate": 8.307690827678383e-07,
      "loss": 0.448,
      "step": 56613
    },
    {
      "epoch": 1.7391331060117348,
      "grad_norm": 0.42602866888046265,
      "learning_rate": 8.305762349081082e-07,
      "loss": 0.4536,
      "step": 56614
    },
    {
      "epoch": 1.7391638251466839,
      "grad_norm": 0.46680307388305664,
      "learning_rate": 8.303834084642103e-07,
      "loss": 0.5155,
      "step": 56615
    },
    {
      "epoch": 1.739194544281633,
      "grad_norm": 0.48965874314308167,
      "learning_rate": 8.301906034365914e-07,
      "loss": 0.5168,
      "step": 56616
    },
    {
      "epoch": 1.7392252634165821,
      "grad_norm": 0.4131677448749542,
      "learning_rate": 8.299978198257053e-07,
      "loss": 0.4852,
      "step": 56617
    },
    {
      "epoch": 1.7392559825515312,
      "grad_norm": 0.3934350609779358,
      "learning_rate": 8.298050576319949e-07,
      "loss": 0.4714,
      "step": 56618
    },
    {
      "epoch": 1.7392867016864804,
      "grad_norm": 0.41327810287475586,
      "learning_rate": 8.296123168559189e-07,
      "loss": 0.5273,
      "step": 56619
    },
    {
      "epoch": 1.7393174208214297,
      "grad_norm": 0.4334251582622528,
      "learning_rate": 8.294195974979225e-07,
      "loss": 0.477,
      "step": 56620
    },
    {
      "epoch": 1.7393481399563788,
      "grad_norm": 0.43444696068763733,
      "learning_rate": 8.292268995584574e-07,
      "loss": 0.5375,
      "step": 56621
    },
    {
      "epoch": 1.739378859091328,
      "grad_norm": 0.4071442782878876,
      "learning_rate": 8.290342230379745e-07,
      "loss": 0.5036,
      "step": 56622
    },
    {
      "epoch": 1.7394095782262773,
      "grad_norm": 0.4247902035713196,
      "learning_rate": 8.288415679369188e-07,
      "loss": 0.4109,
      "step": 56623
    },
    {
      "epoch": 1.7394402973612264,
      "grad_norm": 0.4248960614204407,
      "learning_rate": 8.28648934255748e-07,
      "loss": 0.4552,
      "step": 56624
    },
    {
      "epoch": 1.7394710164961755,
      "grad_norm": 0.48817628622055054,
      "learning_rate": 8.284563219949072e-07,
      "loss": 0.4994,
      "step": 56625
    },
    {
      "epoch": 1.7395017356311246,
      "grad_norm": 0.443950355052948,
      "learning_rate": 8.28263731154848e-07,
      "loss": 0.515,
      "step": 56626
    },
    {
      "epoch": 1.7395324547660738,
      "grad_norm": 0.4675157070159912,
      "learning_rate": 8.280711617360171e-07,
      "loss": 0.5764,
      "step": 56627
    },
    {
      "epoch": 1.7395631739010229,
      "grad_norm": 0.45415443181991577,
      "learning_rate": 8.278786137388672e-07,
      "loss": 0.4733,
      "step": 56628
    },
    {
      "epoch": 1.739593893035972,
      "grad_norm": 0.389428973197937,
      "learning_rate": 8.276860871638481e-07,
      "loss": 0.3804,
      "step": 56629
    },
    {
      "epoch": 1.7396246121709211,
      "grad_norm": 0.4854835271835327,
      "learning_rate": 8.274935820114094e-07,
      "loss": 0.4187,
      "step": 56630
    },
    {
      "epoch": 1.7396553313058705,
      "grad_norm": 0.40266212821006775,
      "learning_rate": 8.273010982819996e-07,
      "loss": 0.4203,
      "step": 56631
    },
    {
      "epoch": 1.7396860504408196,
      "grad_norm": 0.4471495449542999,
      "learning_rate": 8.271086359760672e-07,
      "loss": 0.4663,
      "step": 56632
    },
    {
      "epoch": 1.7397167695757687,
      "grad_norm": 0.43738123774528503,
      "learning_rate": 8.26916195094064e-07,
      "loss": 0.5091,
      "step": 56633
    },
    {
      "epoch": 1.739747488710718,
      "grad_norm": 0.4152367115020752,
      "learning_rate": 8.267237756364399e-07,
      "loss": 0.403,
      "step": 56634
    },
    {
      "epoch": 1.7397782078456672,
      "grad_norm": 0.44237804412841797,
      "learning_rate": 8.265313776036421e-07,
      "loss": 0.4008,
      "step": 56635
    },
    {
      "epoch": 1.7398089269806163,
      "grad_norm": 0.4511393904685974,
      "learning_rate": 8.263390009961203e-07,
      "loss": 0.5187,
      "step": 56636
    },
    {
      "epoch": 1.7398396461155654,
      "grad_norm": 0.47405683994293213,
      "learning_rate": 8.261466458143252e-07,
      "loss": 0.4857,
      "step": 56637
    },
    {
      "epoch": 1.7398703652505145,
      "grad_norm": 0.4061373472213745,
      "learning_rate": 8.259543120587066e-07,
      "loss": 0.4221,
      "step": 56638
    },
    {
      "epoch": 1.7399010843854636,
      "grad_norm": 0.4662868082523346,
      "learning_rate": 8.257619997297106e-07,
      "loss": 0.5128,
      "step": 56639
    },
    {
      "epoch": 1.7399318035204128,
      "grad_norm": 0.671271800994873,
      "learning_rate": 8.25569708827788e-07,
      "loss": 0.541,
      "step": 56640
    },
    {
      "epoch": 1.7399625226553619,
      "grad_norm": 0.4725751280784607,
      "learning_rate": 8.253774393533887e-07,
      "loss": 0.5173,
      "step": 56641
    },
    {
      "epoch": 1.7399932417903112,
      "grad_norm": 0.4119945764541626,
      "learning_rate": 8.251851913069598e-07,
      "loss": 0.484,
      "step": 56642
    },
    {
      "epoch": 1.7400239609252603,
      "grad_norm": 0.42328473925590515,
      "learning_rate": 8.249929646889543e-07,
      "loss": 0.4374,
      "step": 56643
    },
    {
      "epoch": 1.7400546800602095,
      "grad_norm": 0.40510520339012146,
      "learning_rate": 8.248007594998175e-07,
      "loss": 0.4467,
      "step": 56644
    },
    {
      "epoch": 1.7400853991951588,
      "grad_norm": 0.4296806752681732,
      "learning_rate": 8.246085757399979e-07,
      "loss": 0.4431,
      "step": 56645
    },
    {
      "epoch": 1.740116118330108,
      "grad_norm": 0.41007792949676514,
      "learning_rate": 8.244164134099464e-07,
      "loss": 0.4873,
      "step": 56646
    },
    {
      "epoch": 1.740146837465057,
      "grad_norm": 0.4327184855937958,
      "learning_rate": 8.242242725101135e-07,
      "loss": 0.394,
      "step": 56647
    },
    {
      "epoch": 1.7401775566000062,
      "grad_norm": 0.4709465801715851,
      "learning_rate": 8.240321530409434e-07,
      "loss": 0.4492,
      "step": 56648
    },
    {
      "epoch": 1.7402082757349553,
      "grad_norm": 0.4297616481781006,
      "learning_rate": 8.238400550028891e-07,
      "loss": 0.4633,
      "step": 56649
    },
    {
      "epoch": 1.7402389948699044,
      "grad_norm": 0.4214478135108948,
      "learning_rate": 8.236479783963925e-07,
      "loss": 0.5062,
      "step": 56650
    },
    {
      "epoch": 1.7402697140048535,
      "grad_norm": 0.44266995787620544,
      "learning_rate": 8.23455923221912e-07,
      "loss": 0.5466,
      "step": 56651
    },
    {
      "epoch": 1.7403004331398026,
      "grad_norm": 0.43662261962890625,
      "learning_rate": 8.232638894798883e-07,
      "loss": 0.4239,
      "step": 56652
    },
    {
      "epoch": 1.740331152274752,
      "grad_norm": 0.42535704374313354,
      "learning_rate": 8.230718771707746e-07,
      "loss": 0.4661,
      "step": 56653
    },
    {
      "epoch": 1.7403618714097011,
      "grad_norm": 0.41509294509887695,
      "learning_rate": 8.22879886295016e-07,
      "loss": 0.4844,
      "step": 56654
    },
    {
      "epoch": 1.7403925905446502,
      "grad_norm": 0.42602455615997314,
      "learning_rate": 8.226879168530621e-07,
      "loss": 0.4723,
      "step": 56655
    },
    {
      "epoch": 1.7404233096795996,
      "grad_norm": 0.42377087473869324,
      "learning_rate": 8.224959688453615e-07,
      "loss": 0.4835,
      "step": 56656
    },
    {
      "epoch": 1.7404540288145487,
      "grad_norm": 0.5527666807174683,
      "learning_rate": 8.223040422723649e-07,
      "loss": 0.4956,
      "step": 56657
    },
    {
      "epoch": 1.7404847479494978,
      "grad_norm": 0.4422769248485565,
      "learning_rate": 8.221121371345153e-07,
      "loss": 0.4229,
      "step": 56658
    },
    {
      "epoch": 1.740515467084447,
      "grad_norm": 0.4258222281932831,
      "learning_rate": 8.219202534322623e-07,
      "loss": 0.5771,
      "step": 56659
    },
    {
      "epoch": 1.740546186219396,
      "grad_norm": 0.4572279155254364,
      "learning_rate": 8.2172839116606e-07,
      "loss": 0.436,
      "step": 56660
    },
    {
      "epoch": 1.7405769053543452,
      "grad_norm": 0.43353161215782166,
      "learning_rate": 8.215365503363493e-07,
      "loss": 0.5249,
      "step": 56661
    },
    {
      "epoch": 1.7406076244892943,
      "grad_norm": 0.4166620671749115,
      "learning_rate": 8.213447309435829e-07,
      "loss": 0.4776,
      "step": 56662
    },
    {
      "epoch": 1.7406383436242434,
      "grad_norm": 0.4266601800918579,
      "learning_rate": 8.211529329882062e-07,
      "loss": 0.4957,
      "step": 56663
    },
    {
      "epoch": 1.7406690627591928,
      "grad_norm": 0.4548221826553345,
      "learning_rate": 8.209611564706665e-07,
      "loss": 0.502,
      "step": 56664
    },
    {
      "epoch": 1.7406997818941419,
      "grad_norm": 0.5133795738220215,
      "learning_rate": 8.207694013914136e-07,
      "loss": 0.4718,
      "step": 56665
    },
    {
      "epoch": 1.740730501029091,
      "grad_norm": 0.3941324055194855,
      "learning_rate": 8.205776677508969e-07,
      "loss": 0.4557,
      "step": 56666
    },
    {
      "epoch": 1.7407612201640403,
      "grad_norm": 0.5587872862815857,
      "learning_rate": 8.203859555495597e-07,
      "loss": 0.4498,
      "step": 56667
    },
    {
      "epoch": 1.7407919392989895,
      "grad_norm": 0.4132519066333771,
      "learning_rate": 8.201942647878525e-07,
      "loss": 0.5196,
      "step": 56668
    },
    {
      "epoch": 1.7408226584339386,
      "grad_norm": 0.457319438457489,
      "learning_rate": 8.200025954662228e-07,
      "loss": 0.5102,
      "step": 56669
    },
    {
      "epoch": 1.7408533775688877,
      "grad_norm": 0.4036116898059845,
      "learning_rate": 8.198109475851202e-07,
      "loss": 0.4187,
      "step": 56670
    },
    {
      "epoch": 1.7408840967038368,
      "grad_norm": 0.4527440667152405,
      "learning_rate": 8.196193211449876e-07,
      "loss": 0.497,
      "step": 56671
    },
    {
      "epoch": 1.740914815838786,
      "grad_norm": 0.4320874512195587,
      "learning_rate": 8.19427716146276e-07,
      "loss": 0.5102,
      "step": 56672
    },
    {
      "epoch": 1.740945534973735,
      "grad_norm": 0.41664767265319824,
      "learning_rate": 8.192361325894327e-07,
      "loss": 0.4219,
      "step": 56673
    },
    {
      "epoch": 1.7409762541086842,
      "grad_norm": 0.4282662868499756,
      "learning_rate": 8.19044570474905e-07,
      "loss": 0.4917,
      "step": 56674
    },
    {
      "epoch": 1.7410069732436333,
      "grad_norm": 0.4666128158569336,
      "learning_rate": 8.188530298031383e-07,
      "loss": 0.4368,
      "step": 56675
    },
    {
      "epoch": 1.7410376923785826,
      "grad_norm": 0.42599454522132874,
      "learning_rate": 8.186615105745821e-07,
      "loss": 0.4372,
      "step": 56676
    },
    {
      "epoch": 1.7410684115135318,
      "grad_norm": 0.4308927357196808,
      "learning_rate": 8.184700127896839e-07,
      "loss": 0.4458,
      "step": 56677
    },
    {
      "epoch": 1.741099130648481,
      "grad_norm": 0.4546804130077362,
      "learning_rate": 8.182785364488887e-07,
      "loss": 0.4122,
      "step": 56678
    },
    {
      "epoch": 1.7411298497834302,
      "grad_norm": 0.4299701154232025,
      "learning_rate": 8.180870815526476e-07,
      "loss": 0.4512,
      "step": 56679
    },
    {
      "epoch": 1.7411605689183793,
      "grad_norm": 0.40905439853668213,
      "learning_rate": 8.178956481014044e-07,
      "loss": 0.468,
      "step": 56680
    },
    {
      "epoch": 1.7411912880533285,
      "grad_norm": 0.46363070607185364,
      "learning_rate": 8.177042360956056e-07,
      "loss": 0.485,
      "step": 56681
    },
    {
      "epoch": 1.7412220071882776,
      "grad_norm": 0.413398802280426,
      "learning_rate": 8.175128455357006e-07,
      "loss": 0.4752,
      "step": 56682
    },
    {
      "epoch": 1.7412527263232267,
      "grad_norm": 0.4414695203304291,
      "learning_rate": 8.173214764221382e-07,
      "loss": 0.453,
      "step": 56683
    },
    {
      "epoch": 1.7412834454581758,
      "grad_norm": 0.4690496027469635,
      "learning_rate": 8.171301287553602e-07,
      "loss": 0.5141,
      "step": 56684
    },
    {
      "epoch": 1.741314164593125,
      "grad_norm": 0.39115238189697266,
      "learning_rate": 8.169388025358182e-07,
      "loss": 0.387,
      "step": 56685
    },
    {
      "epoch": 1.741344883728074,
      "grad_norm": 0.4398394227027893,
      "learning_rate": 8.167474977639534e-07,
      "loss": 0.4152,
      "step": 56686
    },
    {
      "epoch": 1.7413756028630234,
      "grad_norm": 0.4364558160305023,
      "learning_rate": 8.165562144402195e-07,
      "loss": 0.5124,
      "step": 56687
    },
    {
      "epoch": 1.7414063219979725,
      "grad_norm": 0.5083994269371033,
      "learning_rate": 8.163649525650574e-07,
      "loss": 0.4577,
      "step": 56688
    },
    {
      "epoch": 1.7414370411329219,
      "grad_norm": 0.4047125279903412,
      "learning_rate": 8.161737121389191e-07,
      "loss": 0.4409,
      "step": 56689
    },
    {
      "epoch": 1.741467760267871,
      "grad_norm": 0.4383891522884369,
      "learning_rate": 8.159824931622473e-07,
      "loss": 0.4469,
      "step": 56690
    },
    {
      "epoch": 1.74149847940282,
      "grad_norm": 0.4567188322544098,
      "learning_rate": 8.157912956354885e-07,
      "loss": 0.4349,
      "step": 56691
    },
    {
      "epoch": 1.7415291985377692,
      "grad_norm": 0.4018498957157135,
      "learning_rate": 8.156001195590913e-07,
      "loss": 0.4487,
      "step": 56692
    },
    {
      "epoch": 1.7415599176727183,
      "grad_norm": 0.4335956275463104,
      "learning_rate": 8.154089649335028e-07,
      "loss": 0.4693,
      "step": 56693
    },
    {
      "epoch": 1.7415906368076675,
      "grad_norm": 0.4107140004634857,
      "learning_rate": 8.152178317591663e-07,
      "loss": 0.4341,
      "step": 56694
    },
    {
      "epoch": 1.7416213559426166,
      "grad_norm": 0.6236796975135803,
      "learning_rate": 8.150267200365303e-07,
      "loss": 0.4008,
      "step": 56695
    },
    {
      "epoch": 1.7416520750775657,
      "grad_norm": 0.4545144736766815,
      "learning_rate": 8.148356297660409e-07,
      "loss": 0.4647,
      "step": 56696
    },
    {
      "epoch": 1.7416827942125148,
      "grad_norm": 0.46774527430534363,
      "learning_rate": 8.146445609481446e-07,
      "loss": 0.4508,
      "step": 56697
    },
    {
      "epoch": 1.7417135133474642,
      "grad_norm": 0.41966328024864197,
      "learning_rate": 8.144535135832887e-07,
      "loss": 0.4706,
      "step": 56698
    },
    {
      "epoch": 1.7417442324824133,
      "grad_norm": 0.4110853672027588,
      "learning_rate": 8.142624876719163e-07,
      "loss": 0.496,
      "step": 56699
    },
    {
      "epoch": 1.7417749516173626,
      "grad_norm": 0.48310694098472595,
      "learning_rate": 8.140714832144758e-07,
      "loss": 0.4697,
      "step": 56700
    },
    {
      "epoch": 1.7418056707523117,
      "grad_norm": 0.5548809170722961,
      "learning_rate": 8.138805002114125e-07,
      "loss": 0.4825,
      "step": 56701
    },
    {
      "epoch": 1.7418363898872609,
      "grad_norm": 0.4422053098678589,
      "learning_rate": 8.136895386631749e-07,
      "loss": 0.4491,
      "step": 56702
    },
    {
      "epoch": 1.74186710902221,
      "grad_norm": 0.39707037806510925,
      "learning_rate": 8.134985985702048e-07,
      "loss": 0.4845,
      "step": 56703
    },
    {
      "epoch": 1.741897828157159,
      "grad_norm": 0.4302685558795929,
      "learning_rate": 8.133076799329509e-07,
      "loss": 0.424,
      "step": 56704
    },
    {
      "epoch": 1.7419285472921082,
      "grad_norm": 0.40766558051109314,
      "learning_rate": 8.131167827518582e-07,
      "loss": 0.4812,
      "step": 56705
    },
    {
      "epoch": 1.7419592664270573,
      "grad_norm": 0.4126400351524353,
      "learning_rate": 8.129259070273742e-07,
      "loss": 0.4449,
      "step": 56706
    },
    {
      "epoch": 1.7419899855620065,
      "grad_norm": 0.46198248863220215,
      "learning_rate": 8.127350527599431e-07,
      "loss": 0.3814,
      "step": 56707
    },
    {
      "epoch": 1.7420207046969556,
      "grad_norm": 0.4494842290878296,
      "learning_rate": 8.125442199500089e-07,
      "loss": 0.4439,
      "step": 56708
    },
    {
      "epoch": 1.742051423831905,
      "grad_norm": 0.41710174083709717,
      "learning_rate": 8.123534085980212e-07,
      "loss": 0.4653,
      "step": 56709
    },
    {
      "epoch": 1.742082142966854,
      "grad_norm": 0.41735249757766724,
      "learning_rate": 8.12162618704424e-07,
      "loss": 0.4276,
      "step": 56710
    },
    {
      "epoch": 1.7421128621018032,
      "grad_norm": 0.4481396973133087,
      "learning_rate": 8.119718502696616e-07,
      "loss": 0.3869,
      "step": 56711
    },
    {
      "epoch": 1.7421435812367525,
      "grad_norm": 0.44300201535224915,
      "learning_rate": 8.117811032941824e-07,
      "loss": 0.4842,
      "step": 56712
    },
    {
      "epoch": 1.7421743003717016,
      "grad_norm": 0.474901407957077,
      "learning_rate": 8.115903777784262e-07,
      "loss": 0.4739,
      "step": 56713
    },
    {
      "epoch": 1.7422050195066507,
      "grad_norm": 0.4721614122390747,
      "learning_rate": 8.113996737228446e-07,
      "loss": 0.4577,
      "step": 56714
    },
    {
      "epoch": 1.7422357386415999,
      "grad_norm": 0.458882212638855,
      "learning_rate": 8.11208991127882e-07,
      "loss": 0.3949,
      "step": 56715
    },
    {
      "epoch": 1.742266457776549,
      "grad_norm": 0.4293757379055023,
      "learning_rate": 8.110183299939811e-07,
      "loss": 0.4667,
      "step": 56716
    },
    {
      "epoch": 1.742297176911498,
      "grad_norm": 0.5332810282707214,
      "learning_rate": 8.108276903215906e-07,
      "loss": 0.4978,
      "step": 56717
    },
    {
      "epoch": 1.7423278960464472,
      "grad_norm": 0.45699846744537354,
      "learning_rate": 8.1063707211115e-07,
      "loss": 0.4337,
      "step": 56718
    },
    {
      "epoch": 1.7423586151813963,
      "grad_norm": 0.46155446767807007,
      "learning_rate": 8.104464753631125e-07,
      "loss": 0.4791,
      "step": 56719
    },
    {
      "epoch": 1.7423893343163457,
      "grad_norm": 0.4367125928401947,
      "learning_rate": 8.102559000779165e-07,
      "loss": 0.4742,
      "step": 56720
    },
    {
      "epoch": 1.7424200534512948,
      "grad_norm": 0.41791850328445435,
      "learning_rate": 8.100653462560115e-07,
      "loss": 0.523,
      "step": 56721
    },
    {
      "epoch": 1.742450772586244,
      "grad_norm": 0.38847532868385315,
      "learning_rate": 8.098748138978374e-07,
      "loss": 0.4024,
      "step": 56722
    },
    {
      "epoch": 1.7424814917211933,
      "grad_norm": 0.4755062758922577,
      "learning_rate": 8.096843030038459e-07,
      "loss": 0.4748,
      "step": 56723
    },
    {
      "epoch": 1.7425122108561424,
      "grad_norm": 0.43896082043647766,
      "learning_rate": 8.094938135744779e-07,
      "loss": 0.5273,
      "step": 56724
    },
    {
      "epoch": 1.7425429299910915,
      "grad_norm": 0.40720391273498535,
      "learning_rate": 8.093033456101795e-07,
      "loss": 0.4738,
      "step": 56725
    },
    {
      "epoch": 1.7425736491260406,
      "grad_norm": 0.4474058747291565,
      "learning_rate": 8.091128991113928e-07,
      "loss": 0.4878,
      "step": 56726
    },
    {
      "epoch": 1.7426043682609897,
      "grad_norm": 0.4544925391674042,
      "learning_rate": 8.089224740785662e-07,
      "loss": 0.4662,
      "step": 56727
    },
    {
      "epoch": 1.7426350873959389,
      "grad_norm": 0.4525972902774811,
      "learning_rate": 8.087320705121415e-07,
      "loss": 0.4546,
      "step": 56728
    },
    {
      "epoch": 1.742665806530888,
      "grad_norm": 0.4310230016708374,
      "learning_rate": 8.085416884125674e-07,
      "loss": 0.3559,
      "step": 56729
    },
    {
      "epoch": 1.742696525665837,
      "grad_norm": 0.4099777638912201,
      "learning_rate": 8.083513277802845e-07,
      "loss": 0.4825,
      "step": 56730
    },
    {
      "epoch": 1.7427272448007864,
      "grad_norm": 0.4147506058216095,
      "learning_rate": 8.081609886157394e-07,
      "loss": 0.4293,
      "step": 56731
    },
    {
      "epoch": 1.7427579639357356,
      "grad_norm": 0.4392581880092621,
      "learning_rate": 8.079706709193758e-07,
      "loss": 0.4397,
      "step": 56732
    },
    {
      "epoch": 1.7427886830706847,
      "grad_norm": 0.4447536766529083,
      "learning_rate": 8.07780374691639e-07,
      "loss": 0.4621,
      "step": 56733
    },
    {
      "epoch": 1.742819402205634,
      "grad_norm": 0.4135124683380127,
      "learning_rate": 8.075900999329745e-07,
      "loss": 0.5251,
      "step": 56734
    },
    {
      "epoch": 1.7428501213405831,
      "grad_norm": 0.46879538893699646,
      "learning_rate": 8.073998466438238e-07,
      "loss": 0.4712,
      "step": 56735
    },
    {
      "epoch": 1.7428808404755323,
      "grad_norm": 0.41523486375808716,
      "learning_rate": 8.072096148246322e-07,
      "loss": 0.4606,
      "step": 56736
    },
    {
      "epoch": 1.7429115596104814,
      "grad_norm": 0.44478923082351685,
      "learning_rate": 8.07019404475845e-07,
      "loss": 0.4839,
      "step": 56737
    },
    {
      "epoch": 1.7429422787454305,
      "grad_norm": 0.4458511471748352,
      "learning_rate": 8.068292155979074e-07,
      "loss": 0.5011,
      "step": 56738
    },
    {
      "epoch": 1.7429729978803796,
      "grad_norm": 0.44240835309028625,
      "learning_rate": 8.066390481912611e-07,
      "loss": 0.4999,
      "step": 56739
    },
    {
      "epoch": 1.7430037170153287,
      "grad_norm": 0.44116100668907166,
      "learning_rate": 8.064489022563505e-07,
      "loss": 0.4392,
      "step": 56740
    },
    {
      "epoch": 1.7430344361502779,
      "grad_norm": 0.447016179561615,
      "learning_rate": 8.062587777936215e-07,
      "loss": 0.452,
      "step": 56741
    },
    {
      "epoch": 1.7430651552852272,
      "grad_norm": 0.42485877871513367,
      "learning_rate": 8.060686748035185e-07,
      "loss": 0.472,
      "step": 56742
    },
    {
      "epoch": 1.7430958744201763,
      "grad_norm": 0.4735074043273926,
      "learning_rate": 8.058785932864822e-07,
      "loss": 0.5056,
      "step": 56743
    },
    {
      "epoch": 1.7431265935551254,
      "grad_norm": 0.42291754484176636,
      "learning_rate": 8.056885332429587e-07,
      "loss": 0.4433,
      "step": 56744
    },
    {
      "epoch": 1.7431573126900748,
      "grad_norm": 0.41864582896232605,
      "learning_rate": 8.054984946733924e-07,
      "loss": 0.4755,
      "step": 56745
    },
    {
      "epoch": 1.743188031825024,
      "grad_norm": 0.5122003555297852,
      "learning_rate": 8.053084775782283e-07,
      "loss": 0.4673,
      "step": 56746
    },
    {
      "epoch": 1.743218750959973,
      "grad_norm": 0.49236181378364563,
      "learning_rate": 8.051184819579061e-07,
      "loss": 0.4506,
      "step": 56747
    },
    {
      "epoch": 1.7432494700949221,
      "grad_norm": 0.4172952473163605,
      "learning_rate": 8.049285078128733e-07,
      "loss": 0.3947,
      "step": 56748
    },
    {
      "epoch": 1.7432801892298713,
      "grad_norm": 0.4269680082798004,
      "learning_rate": 8.047385551435693e-07,
      "loss": 0.4654,
      "step": 56749
    },
    {
      "epoch": 1.7433109083648204,
      "grad_norm": 0.4509253203868866,
      "learning_rate": 8.045486239504419e-07,
      "loss": 0.3964,
      "step": 56750
    },
    {
      "epoch": 1.7433416274997695,
      "grad_norm": 0.4580945670604706,
      "learning_rate": 8.043587142339349e-07,
      "loss": 0.4347,
      "step": 56751
    },
    {
      "epoch": 1.7433723466347186,
      "grad_norm": 0.4311913549900055,
      "learning_rate": 8.041688259944891e-07,
      "loss": 0.4303,
      "step": 56752
    },
    {
      "epoch": 1.743403065769668,
      "grad_norm": 0.44826874136924744,
      "learning_rate": 8.039789592325508e-07,
      "loss": 0.5043,
      "step": 56753
    },
    {
      "epoch": 1.743433784904617,
      "grad_norm": 0.47130319476127625,
      "learning_rate": 8.037891139485588e-07,
      "loss": 0.5268,
      "step": 56754
    },
    {
      "epoch": 1.7434645040395662,
      "grad_norm": 0.4804031252861023,
      "learning_rate": 8.035992901429623e-07,
      "loss": 0.5685,
      "step": 56755
    },
    {
      "epoch": 1.7434952231745156,
      "grad_norm": 0.44716712832450867,
      "learning_rate": 8.034094878162002e-07,
      "loss": 0.5228,
      "step": 56756
    },
    {
      "epoch": 1.7435259423094647,
      "grad_norm": 0.46316295862197876,
      "learning_rate": 8.032197069687197e-07,
      "loss": 0.4626,
      "step": 56757
    },
    {
      "epoch": 1.7435566614444138,
      "grad_norm": 0.46729525923728943,
      "learning_rate": 8.030299476009606e-07,
      "loss": 0.4807,
      "step": 56758
    },
    {
      "epoch": 1.743587380579363,
      "grad_norm": 0.40926826000213623,
      "learning_rate": 8.028402097133669e-07,
      "loss": 0.4022,
      "step": 56759
    },
    {
      "epoch": 1.743618099714312,
      "grad_norm": 0.3932875990867615,
      "learning_rate": 8.026504933063817e-07,
      "loss": 0.4642,
      "step": 56760
    },
    {
      "epoch": 1.7436488188492612,
      "grad_norm": 0.4233701229095459,
      "learning_rate": 8.024607983804511e-07,
      "loss": 0.3661,
      "step": 56761
    },
    {
      "epoch": 1.7436795379842103,
      "grad_norm": 0.41858115792274475,
      "learning_rate": 8.022711249360138e-07,
      "loss": 0.4391,
      "step": 56762
    },
    {
      "epoch": 1.7437102571191594,
      "grad_norm": 0.43872570991516113,
      "learning_rate": 8.020814729735137e-07,
      "loss": 0.4292,
      "step": 56763
    },
    {
      "epoch": 1.7437409762541087,
      "grad_norm": 0.42009133100509644,
      "learning_rate": 8.018918424933953e-07,
      "loss": 0.4581,
      "step": 56764
    },
    {
      "epoch": 1.7437716953890579,
      "grad_norm": 0.45388534665107727,
      "learning_rate": 8.017022334961033e-07,
      "loss": 0.4448,
      "step": 56765
    },
    {
      "epoch": 1.743802414524007,
      "grad_norm": 0.44792070984840393,
      "learning_rate": 8.015126459820754e-07,
      "loss": 0.5032,
      "step": 56766
    },
    {
      "epoch": 1.7438331336589563,
      "grad_norm": 0.4065092206001282,
      "learning_rate": 8.013230799517579e-07,
      "loss": 0.4884,
      "step": 56767
    },
    {
      "epoch": 1.7438638527939054,
      "grad_norm": 0.4062098562717438,
      "learning_rate": 8.011335354055927e-07,
      "loss": 0.5395,
      "step": 56768
    },
    {
      "epoch": 1.7438945719288546,
      "grad_norm": 0.5076138973236084,
      "learning_rate": 8.009440123440227e-07,
      "loss": 0.4899,
      "step": 56769
    },
    {
      "epoch": 1.7439252910638037,
      "grad_norm": 0.3860425055027008,
      "learning_rate": 8.007545107674908e-07,
      "loss": 0.4172,
      "step": 56770
    },
    {
      "epoch": 1.7439560101987528,
      "grad_norm": 0.41469284892082214,
      "learning_rate": 8.00565030676439e-07,
      "loss": 0.4166,
      "step": 56771
    },
    {
      "epoch": 1.743986729333702,
      "grad_norm": 0.48406824469566345,
      "learning_rate": 8.003755720713092e-07,
      "loss": 0.4812,
      "step": 56772
    },
    {
      "epoch": 1.744017448468651,
      "grad_norm": 0.4305395781993866,
      "learning_rate": 8.001861349525453e-07,
      "loss": 0.4413,
      "step": 56773
    },
    {
      "epoch": 1.7440481676036002,
      "grad_norm": 0.45107558369636536,
      "learning_rate": 7.999967193205905e-07,
      "loss": 0.4991,
      "step": 56774
    },
    {
      "epoch": 1.7440788867385495,
      "grad_norm": 0.4656410217285156,
      "learning_rate": 7.998073251758842e-07,
      "loss": 0.3667,
      "step": 56775
    },
    {
      "epoch": 1.7441096058734986,
      "grad_norm": 0.44743940234184265,
      "learning_rate": 7.996179525188707e-07,
      "loss": 0.4218,
      "step": 56776
    },
    {
      "epoch": 1.7441403250084477,
      "grad_norm": 0.4460003972053528,
      "learning_rate": 7.994286013499919e-07,
      "loss": 0.4331,
      "step": 56777
    },
    {
      "epoch": 1.744171044143397,
      "grad_norm": 0.4641919434070587,
      "learning_rate": 7.992392716696917e-07,
      "loss": 0.4501,
      "step": 56778
    },
    {
      "epoch": 1.7442017632783462,
      "grad_norm": 0.41805410385131836,
      "learning_rate": 7.990499634784099e-07,
      "loss": 0.3969,
      "step": 56779
    },
    {
      "epoch": 1.7442324824132953,
      "grad_norm": 0.4593287706375122,
      "learning_rate": 7.988606767765905e-07,
      "loss": 0.4589,
      "step": 56780
    },
    {
      "epoch": 1.7442632015482444,
      "grad_norm": 0.42722606658935547,
      "learning_rate": 7.986714115646709e-07,
      "loss": 0.4687,
      "step": 56781
    },
    {
      "epoch": 1.7442939206831936,
      "grad_norm": 0.46163028478622437,
      "learning_rate": 7.98482167843101e-07,
      "loss": 0.4734,
      "step": 56782
    },
    {
      "epoch": 1.7443246398181427,
      "grad_norm": 0.4232841432094574,
      "learning_rate": 7.982929456123156e-07,
      "loss": 0.4601,
      "step": 56783
    },
    {
      "epoch": 1.7443553589530918,
      "grad_norm": 0.4522078335285187,
      "learning_rate": 7.981037448727625e-07,
      "loss": 0.5228,
      "step": 56784
    },
    {
      "epoch": 1.744386078088041,
      "grad_norm": 0.4754024147987366,
      "learning_rate": 7.979145656248777e-07,
      "loss": 0.534,
      "step": 56785
    },
    {
      "epoch": 1.74441679722299,
      "grad_norm": 0.46235567331314087,
      "learning_rate": 7.977254078691066e-07,
      "loss": 0.5265,
      "step": 56786
    },
    {
      "epoch": 1.7444475163579394,
      "grad_norm": 0.48904895782470703,
      "learning_rate": 7.975362716058932e-07,
      "loss": 0.4545,
      "step": 56787
    },
    {
      "epoch": 1.7444782354928885,
      "grad_norm": 0.4578346014022827,
      "learning_rate": 7.973471568356738e-07,
      "loss": 0.4316,
      "step": 56788
    },
    {
      "epoch": 1.7445089546278378,
      "grad_norm": 0.4261620342731476,
      "learning_rate": 7.971580635588949e-07,
      "loss": 0.48,
      "step": 56789
    },
    {
      "epoch": 1.744539673762787,
      "grad_norm": 0.39280641078948975,
      "learning_rate": 7.969689917759938e-07,
      "loss": 0.4582,
      "step": 56790
    },
    {
      "epoch": 1.744570392897736,
      "grad_norm": 0.43291163444519043,
      "learning_rate": 7.967799414874167e-07,
      "loss": 0.4046,
      "step": 56791
    },
    {
      "epoch": 1.7446011120326852,
      "grad_norm": 0.42196470499038696,
      "learning_rate": 7.965909126936011e-07,
      "loss": 0.5169,
      "step": 56792
    },
    {
      "epoch": 1.7446318311676343,
      "grad_norm": 0.4405481517314911,
      "learning_rate": 7.964019053949923e-07,
      "loss": 0.4514,
      "step": 56793
    },
    {
      "epoch": 1.7446625503025834,
      "grad_norm": 0.4278545677661896,
      "learning_rate": 7.962129195920276e-07,
      "loss": 0.4525,
      "step": 56794
    },
    {
      "epoch": 1.7446932694375326,
      "grad_norm": 0.404226154088974,
      "learning_rate": 7.960239552851501e-07,
      "loss": 0.5197,
      "step": 56795
    },
    {
      "epoch": 1.7447239885724817,
      "grad_norm": 0.48223140835762024,
      "learning_rate": 7.958350124748016e-07,
      "loss": 0.5292,
      "step": 56796
    },
    {
      "epoch": 1.7447547077074308,
      "grad_norm": 0.3910890221595764,
      "learning_rate": 7.95646091161425e-07,
      "loss": 0.439,
      "step": 56797
    },
    {
      "epoch": 1.7447854268423801,
      "grad_norm": 0.4417373836040497,
      "learning_rate": 7.954571913454578e-07,
      "loss": 0.4689,
      "step": 56798
    },
    {
      "epoch": 1.7448161459773293,
      "grad_norm": 0.4305192828178406,
      "learning_rate": 7.952683130273442e-07,
      "loss": 0.4903,
      "step": 56799
    },
    {
      "epoch": 1.7448468651122786,
      "grad_norm": 0.40988773107528687,
      "learning_rate": 7.950794562075237e-07,
      "loss": 0.5118,
      "step": 56800
    },
    {
      "epoch": 1.7448775842472277,
      "grad_norm": 0.38978129625320435,
      "learning_rate": 7.948906208864393e-07,
      "loss": 0.4134,
      "step": 56801
    },
    {
      "epoch": 1.7449083033821768,
      "grad_norm": 0.41142240166664124,
      "learning_rate": 7.947018070645296e-07,
      "loss": 0.4533,
      "step": 56802
    },
    {
      "epoch": 1.744939022517126,
      "grad_norm": 0.43371015787124634,
      "learning_rate": 7.945130147422364e-07,
      "loss": 0.452,
      "step": 56803
    },
    {
      "epoch": 1.744969741652075,
      "grad_norm": 0.4468465745449066,
      "learning_rate": 7.943242439200016e-07,
      "loss": 0.4636,
      "step": 56804
    },
    {
      "epoch": 1.7450004607870242,
      "grad_norm": 0.40662261843681335,
      "learning_rate": 7.941354945982649e-07,
      "loss": 0.4479,
      "step": 56805
    },
    {
      "epoch": 1.7450311799219733,
      "grad_norm": 0.474256694316864,
      "learning_rate": 7.939467667774692e-07,
      "loss": 0.5108,
      "step": 56806
    },
    {
      "epoch": 1.7450618990569224,
      "grad_norm": 0.5062719583511353,
      "learning_rate": 7.93758060458052e-07,
      "loss": 0.504,
      "step": 56807
    },
    {
      "epoch": 1.7450926181918716,
      "grad_norm": 0.4373723864555359,
      "learning_rate": 7.935693756404561e-07,
      "loss": 0.4459,
      "step": 56808
    },
    {
      "epoch": 1.745123337326821,
      "grad_norm": 0.4136539697647095,
      "learning_rate": 7.933807123251225e-07,
      "loss": 0.4784,
      "step": 56809
    },
    {
      "epoch": 1.74515405646177,
      "grad_norm": 0.46451565623283386,
      "learning_rate": 7.931920705124918e-07,
      "loss": 0.3966,
      "step": 56810
    },
    {
      "epoch": 1.7451847755967194,
      "grad_norm": 0.4348832666873932,
      "learning_rate": 7.930034502030027e-07,
      "loss": 0.4626,
      "step": 56811
    },
    {
      "epoch": 1.7452154947316685,
      "grad_norm": 0.44443920254707336,
      "learning_rate": 7.928148513970979e-07,
      "loss": 0.4569,
      "step": 56812
    },
    {
      "epoch": 1.7452462138666176,
      "grad_norm": 0.4496588408946991,
      "learning_rate": 7.926262740952162e-07,
      "loss": 0.4676,
      "step": 56813
    },
    {
      "epoch": 1.7452769330015667,
      "grad_norm": 0.42623090744018555,
      "learning_rate": 7.924377182978004e-07,
      "loss": 0.4745,
      "step": 56814
    },
    {
      "epoch": 1.7453076521365158,
      "grad_norm": 0.43290820717811584,
      "learning_rate": 7.922491840052882e-07,
      "loss": 0.4608,
      "step": 56815
    },
    {
      "epoch": 1.745338371271465,
      "grad_norm": 0.42609092593193054,
      "learning_rate": 7.920606712181223e-07,
      "loss": 0.5076,
      "step": 56816
    },
    {
      "epoch": 1.745369090406414,
      "grad_norm": 0.4264536499977112,
      "learning_rate": 7.91872179936739e-07,
      "loss": 0.4818,
      "step": 56817
    },
    {
      "epoch": 1.7453998095413632,
      "grad_norm": 0.5267029404640198,
      "learning_rate": 7.916837101615838e-07,
      "loss": 0.4428,
      "step": 56818
    },
    {
      "epoch": 1.7454305286763123,
      "grad_norm": 0.4009537398815155,
      "learning_rate": 7.914952618930938e-07,
      "loss": 0.4484,
      "step": 56819
    },
    {
      "epoch": 1.7454612478112617,
      "grad_norm": 0.4260178804397583,
      "learning_rate": 7.913068351317099e-07,
      "loss": 0.4513,
      "step": 56820
    },
    {
      "epoch": 1.7454919669462108,
      "grad_norm": 0.4593541622161865,
      "learning_rate": 7.911184298778718e-07,
      "loss": 0.4508,
      "step": 56821
    },
    {
      "epoch": 1.74552268608116,
      "grad_norm": 0.4613839089870453,
      "learning_rate": 7.90930046132018e-07,
      "loss": 0.4456,
      "step": 56822
    },
    {
      "epoch": 1.7455534052161092,
      "grad_norm": 0.43784838914871216,
      "learning_rate": 7.907416838945925e-07,
      "loss": 0.4413,
      "step": 56823
    },
    {
      "epoch": 1.7455841243510584,
      "grad_norm": 0.5729753971099854,
      "learning_rate": 7.905533431660317e-07,
      "loss": 0.4563,
      "step": 56824
    },
    {
      "epoch": 1.7456148434860075,
      "grad_norm": 0.45594272017478943,
      "learning_rate": 7.903650239467786e-07,
      "loss": 0.4231,
      "step": 56825
    },
    {
      "epoch": 1.7456455626209566,
      "grad_norm": 0.6966509222984314,
      "learning_rate": 7.901767262372684e-07,
      "loss": 0.4422,
      "step": 56826
    },
    {
      "epoch": 1.7456762817559057,
      "grad_norm": 0.4231477975845337,
      "learning_rate": 7.899884500379462e-07,
      "loss": 0.4804,
      "step": 56827
    },
    {
      "epoch": 1.7457070008908548,
      "grad_norm": 0.41090521216392517,
      "learning_rate": 7.898001953492484e-07,
      "loss": 0.5003,
      "step": 56828
    },
    {
      "epoch": 1.745737720025804,
      "grad_norm": 0.4924643933773041,
      "learning_rate": 7.896119621716159e-07,
      "loss": 0.4512,
      "step": 56829
    },
    {
      "epoch": 1.745768439160753,
      "grad_norm": 0.4369875490665436,
      "learning_rate": 7.894237505054869e-07,
      "loss": 0.4457,
      "step": 56830
    },
    {
      "epoch": 1.7457991582957024,
      "grad_norm": 0.44092437624931335,
      "learning_rate": 7.892355603513024e-07,
      "loss": 0.5426,
      "step": 56831
    },
    {
      "epoch": 1.7458298774306515,
      "grad_norm": 0.3930249512195587,
      "learning_rate": 7.89047391709501e-07,
      "loss": 0.4834,
      "step": 56832
    },
    {
      "epoch": 1.7458605965656007,
      "grad_norm": 0.4245316982269287,
      "learning_rate": 7.888592445805243e-07,
      "loss": 0.5006,
      "step": 56833
    },
    {
      "epoch": 1.74589131570055,
      "grad_norm": 0.44737690687179565,
      "learning_rate": 7.886711189648089e-07,
      "loss": 0.5285,
      "step": 56834
    },
    {
      "epoch": 1.7459220348354991,
      "grad_norm": 0.46164652705192566,
      "learning_rate": 7.884830148627953e-07,
      "loss": 0.4338,
      "step": 56835
    },
    {
      "epoch": 1.7459527539704482,
      "grad_norm": 0.4849020838737488,
      "learning_rate": 7.882949322749223e-07,
      "loss": 0.4617,
      "step": 56836
    },
    {
      "epoch": 1.7459834731053974,
      "grad_norm": 0.4509887099266052,
      "learning_rate": 7.881068712016327e-07,
      "loss": 0.3923,
      "step": 56837
    },
    {
      "epoch": 1.7460141922403465,
      "grad_norm": 0.48812970519065857,
      "learning_rate": 7.879188316433595e-07,
      "loss": 0.5449,
      "step": 56838
    },
    {
      "epoch": 1.7460449113752956,
      "grad_norm": 0.46754634380340576,
      "learning_rate": 7.877308136005468e-07,
      "loss": 0.5114,
      "step": 56839
    },
    {
      "epoch": 1.7460756305102447,
      "grad_norm": 0.4681455194950104,
      "learning_rate": 7.87542817073631e-07,
      "loss": 0.46,
      "step": 56840
    },
    {
      "epoch": 1.7461063496451938,
      "grad_norm": 0.5074442028999329,
      "learning_rate": 7.873548420630528e-07,
      "loss": 0.4836,
      "step": 56841
    },
    {
      "epoch": 1.7461370687801432,
      "grad_norm": 0.4395567774772644,
      "learning_rate": 7.87166888569253e-07,
      "loss": 0.4966,
      "step": 56842
    },
    {
      "epoch": 1.7461677879150923,
      "grad_norm": 0.39654746651649475,
      "learning_rate": 7.869789565926667e-07,
      "loss": 0.4908,
      "step": 56843
    },
    {
      "epoch": 1.7461985070500414,
      "grad_norm": 0.452749639749527,
      "learning_rate": 7.867910461337335e-07,
      "loss": 0.458,
      "step": 56844
    },
    {
      "epoch": 1.7462292261849908,
      "grad_norm": 0.41746842861175537,
      "learning_rate": 7.866031571928934e-07,
      "loss": 0.4455,
      "step": 56845
    },
    {
      "epoch": 1.7462599453199399,
      "grad_norm": 0.42862528562545776,
      "learning_rate": 7.864152897705879e-07,
      "loss": 0.4024,
      "step": 56846
    },
    {
      "epoch": 1.746290664454889,
      "grad_norm": 0.4802888035774231,
      "learning_rate": 7.862274438672502e-07,
      "loss": 0.4469,
      "step": 56847
    },
    {
      "epoch": 1.7463213835898381,
      "grad_norm": 0.4282923638820648,
      "learning_rate": 7.86039619483322e-07,
      "loss": 0.5975,
      "step": 56848
    },
    {
      "epoch": 1.7463521027247872,
      "grad_norm": 0.4123533070087433,
      "learning_rate": 7.85851816619242e-07,
      "loss": 0.4631,
      "step": 56849
    },
    {
      "epoch": 1.7463828218597364,
      "grad_norm": 0.49918311834335327,
      "learning_rate": 7.856640352754496e-07,
      "loss": 0.4414,
      "step": 56850
    },
    {
      "epoch": 1.7464135409946855,
      "grad_norm": 0.44120946526527405,
      "learning_rate": 7.854762754523815e-07,
      "loss": 0.5383,
      "step": 56851
    },
    {
      "epoch": 1.7464442601296346,
      "grad_norm": 0.5259985327720642,
      "learning_rate": 7.852885371504781e-07,
      "loss": 0.5476,
      "step": 56852
    },
    {
      "epoch": 1.746474979264584,
      "grad_norm": 1.362429141998291,
      "learning_rate": 7.851008203701749e-07,
      "loss": 0.451,
      "step": 56853
    },
    {
      "epoch": 1.746505698399533,
      "grad_norm": 0.4684171974658966,
      "learning_rate": 7.849131251119146e-07,
      "loss": 0.4524,
      "step": 56854
    },
    {
      "epoch": 1.7465364175344822,
      "grad_norm": 0.41789570450782776,
      "learning_rate": 7.847254513761315e-07,
      "loss": 0.455,
      "step": 56855
    },
    {
      "epoch": 1.7465671366694315,
      "grad_norm": 0.41653579473495483,
      "learning_rate": 7.845377991632675e-07,
      "loss": 0.4753,
      "step": 56856
    },
    {
      "epoch": 1.7465978558043807,
      "grad_norm": 0.49151161313056946,
      "learning_rate": 7.843501684737575e-07,
      "loss": 0.4116,
      "step": 56857
    },
    {
      "epoch": 1.7466285749393298,
      "grad_norm": 0.43212443590164185,
      "learning_rate": 7.841625593080404e-07,
      "loss": 0.4606,
      "step": 56858
    },
    {
      "epoch": 1.746659294074279,
      "grad_norm": 0.49470284581184387,
      "learning_rate": 7.839749716665568e-07,
      "loss": 0.4103,
      "step": 56859
    },
    {
      "epoch": 1.746690013209228,
      "grad_norm": 0.41235366463661194,
      "learning_rate": 7.837874055497418e-07,
      "loss": 0.5053,
      "step": 56860
    },
    {
      "epoch": 1.7467207323441771,
      "grad_norm": 0.514022171497345,
      "learning_rate": 7.835998609580375e-07,
      "loss": 0.46,
      "step": 56861
    },
    {
      "epoch": 1.7467514514791262,
      "grad_norm": 0.5294763445854187,
      "learning_rate": 7.834123378918779e-07,
      "loss": 0.4934,
      "step": 56862
    },
    {
      "epoch": 1.7467821706140754,
      "grad_norm": 0.4540198743343353,
      "learning_rate": 7.832248363517025e-07,
      "loss": 0.3785,
      "step": 56863
    },
    {
      "epoch": 1.7468128897490247,
      "grad_norm": 0.4104832708835602,
      "learning_rate": 7.830373563379489e-07,
      "loss": 0.4415,
      "step": 56864
    },
    {
      "epoch": 1.7468436088839738,
      "grad_norm": 0.42801758646965027,
      "learning_rate": 7.828498978510568e-07,
      "loss": 0.3867,
      "step": 56865
    },
    {
      "epoch": 1.746874328018923,
      "grad_norm": 0.550167977809906,
      "learning_rate": 7.826624608914612e-07,
      "loss": 0.496,
      "step": 56866
    },
    {
      "epoch": 1.7469050471538723,
      "grad_norm": 0.4454164505004883,
      "learning_rate": 7.824750454596008e-07,
      "loss": 0.4819,
      "step": 56867
    },
    {
      "epoch": 1.7469357662888214,
      "grad_norm": 0.4401850998401642,
      "learning_rate": 7.82287651555913e-07,
      "loss": 0.5496,
      "step": 56868
    },
    {
      "epoch": 1.7469664854237705,
      "grad_norm": 0.44887658953666687,
      "learning_rate": 7.821002791808385e-07,
      "loss": 0.436,
      "step": 56869
    },
    {
      "epoch": 1.7469972045587197,
      "grad_norm": 0.391752153635025,
      "learning_rate": 7.819129283348114e-07,
      "loss": 0.4937,
      "step": 56870
    },
    {
      "epoch": 1.7470279236936688,
      "grad_norm": 0.42794203758239746,
      "learning_rate": 7.817255990182704e-07,
      "loss": 0.5083,
      "step": 56871
    },
    {
      "epoch": 1.747058642828618,
      "grad_norm": 0.47652244567871094,
      "learning_rate": 7.815382912316526e-07,
      "loss": 0.4129,
      "step": 56872
    },
    {
      "epoch": 1.747089361963567,
      "grad_norm": 0.45036229491233826,
      "learning_rate": 7.81351004975397e-07,
      "loss": 0.4819,
      "step": 56873
    },
    {
      "epoch": 1.7471200810985161,
      "grad_norm": 0.46777287125587463,
      "learning_rate": 7.811637402499394e-07,
      "loss": 0.507,
      "step": 56874
    },
    {
      "epoch": 1.7471508002334655,
      "grad_norm": 0.44591382145881653,
      "learning_rate": 7.809764970557166e-07,
      "loss": 0.4727,
      "step": 56875
    },
    {
      "epoch": 1.7471815193684146,
      "grad_norm": 0.4301622211933136,
      "learning_rate": 7.807892753931679e-07,
      "loss": 0.405,
      "step": 56876
    },
    {
      "epoch": 1.7472122385033637,
      "grad_norm": 0.44662952423095703,
      "learning_rate": 7.806020752627297e-07,
      "loss": 0.4976,
      "step": 56877
    },
    {
      "epoch": 1.747242957638313,
      "grad_norm": 0.3940821588039398,
      "learning_rate": 7.804148966648406e-07,
      "loss": 0.4518,
      "step": 56878
    },
    {
      "epoch": 1.7472736767732622,
      "grad_norm": 0.42573192715644836,
      "learning_rate": 7.802277395999347e-07,
      "loss": 0.4457,
      "step": 56879
    },
    {
      "epoch": 1.7473043959082113,
      "grad_norm": 0.41490188241004944,
      "learning_rate": 7.800406040684517e-07,
      "loss": 0.4303,
      "step": 56880
    },
    {
      "epoch": 1.7473351150431604,
      "grad_norm": 0.44117671251296997,
      "learning_rate": 7.798534900708266e-07,
      "loss": 0.4561,
      "step": 56881
    },
    {
      "epoch": 1.7473658341781095,
      "grad_norm": 0.45502471923828125,
      "learning_rate": 7.796663976075003e-07,
      "loss": 0.4314,
      "step": 56882
    },
    {
      "epoch": 1.7473965533130587,
      "grad_norm": 0.4407428503036499,
      "learning_rate": 7.794793266789047e-07,
      "loss": 0.453,
      "step": 56883
    },
    {
      "epoch": 1.7474272724480078,
      "grad_norm": 0.3987853229045868,
      "learning_rate": 7.792922772854783e-07,
      "loss": 0.5037,
      "step": 56884
    },
    {
      "epoch": 1.747457991582957,
      "grad_norm": 0.43676531314849854,
      "learning_rate": 7.791052494276596e-07,
      "loss": 0.4672,
      "step": 56885
    },
    {
      "epoch": 1.7474887107179062,
      "grad_norm": 0.4501822590827942,
      "learning_rate": 7.789182431058872e-07,
      "loss": 0.4226,
      "step": 56886
    },
    {
      "epoch": 1.7475194298528554,
      "grad_norm": 0.4323827624320984,
      "learning_rate": 7.78731258320592e-07,
      "loss": 0.4483,
      "step": 56887
    },
    {
      "epoch": 1.7475501489878045,
      "grad_norm": 0.4184398353099823,
      "learning_rate": 7.785442950722167e-07,
      "loss": 0.4761,
      "step": 56888
    },
    {
      "epoch": 1.7475808681227538,
      "grad_norm": 0.41209676861763,
      "learning_rate": 7.78357353361191e-07,
      "loss": 0.4737,
      "step": 56889
    },
    {
      "epoch": 1.747611587257703,
      "grad_norm": 0.4435574412345886,
      "learning_rate": 7.781704331879602e-07,
      "loss": 0.3817,
      "step": 56890
    },
    {
      "epoch": 1.747642306392652,
      "grad_norm": 0.4656999111175537,
      "learning_rate": 7.77983534552954e-07,
      "loss": 0.426,
      "step": 56891
    },
    {
      "epoch": 1.7476730255276012,
      "grad_norm": 0.5675879716873169,
      "learning_rate": 7.777966574566132e-07,
      "loss": 0.5248,
      "step": 56892
    },
    {
      "epoch": 1.7477037446625503,
      "grad_norm": 0.46255379915237427,
      "learning_rate": 7.776098018993705e-07,
      "loss": 0.4266,
      "step": 56893
    },
    {
      "epoch": 1.7477344637974994,
      "grad_norm": 0.4040352404117584,
      "learning_rate": 7.774229678816636e-07,
      "loss": 0.4257,
      "step": 56894
    },
    {
      "epoch": 1.7477651829324485,
      "grad_norm": 0.47291499376296997,
      "learning_rate": 7.772361554039298e-07,
      "loss": 0.4673,
      "step": 56895
    },
    {
      "epoch": 1.7477959020673977,
      "grad_norm": 0.4307437241077423,
      "learning_rate": 7.770493644666055e-07,
      "loss": 0.4792,
      "step": 56896
    },
    {
      "epoch": 1.747826621202347,
      "grad_norm": 0.41722461581230164,
      "learning_rate": 7.768625950701281e-07,
      "loss": 0.5129,
      "step": 56897
    },
    {
      "epoch": 1.7478573403372961,
      "grad_norm": 0.48442062735557556,
      "learning_rate": 7.766758472149305e-07,
      "loss": 0.4489,
      "step": 56898
    },
    {
      "epoch": 1.7478880594722452,
      "grad_norm": 0.42849528789520264,
      "learning_rate": 7.764891209014513e-07,
      "loss": 0.4456,
      "step": 56899
    },
    {
      "epoch": 1.7479187786071946,
      "grad_norm": 0.41445404291152954,
      "learning_rate": 7.763024161301247e-07,
      "loss": 0.3738,
      "step": 56900
    },
    {
      "epoch": 1.7479494977421437,
      "grad_norm": 0.4735305905342102,
      "learning_rate": 7.761157329013902e-07,
      "loss": 0.4638,
      "step": 56901
    },
    {
      "epoch": 1.7479802168770928,
      "grad_norm": 0.4127661883831024,
      "learning_rate": 7.759290712156797e-07,
      "loss": 0.501,
      "step": 56902
    },
    {
      "epoch": 1.748010936012042,
      "grad_norm": 0.43886062502861023,
      "learning_rate": 7.757424310734318e-07,
      "loss": 0.3717,
      "step": 56903
    },
    {
      "epoch": 1.748041655146991,
      "grad_norm": 0.4346266984939575,
      "learning_rate": 7.755558124750818e-07,
      "loss": 0.5185,
      "step": 56904
    },
    {
      "epoch": 1.7480723742819402,
      "grad_norm": 0.43856069445610046,
      "learning_rate": 7.753692154210657e-07,
      "loss": 0.4919,
      "step": 56905
    },
    {
      "epoch": 1.7481030934168893,
      "grad_norm": 0.41307541728019714,
      "learning_rate": 7.751826399118179e-07,
      "loss": 0.4824,
      "step": 56906
    },
    {
      "epoch": 1.7481338125518384,
      "grad_norm": 0.43855562806129456,
      "learning_rate": 7.749960859477756e-07,
      "loss": 0.5322,
      "step": 56907
    },
    {
      "epoch": 1.7481645316867875,
      "grad_norm": 0.47797808051109314,
      "learning_rate": 7.748095535293742e-07,
      "loss": 0.4742,
      "step": 56908
    },
    {
      "epoch": 1.7481952508217369,
      "grad_norm": 0.44755467772483826,
      "learning_rate": 7.746230426570511e-07,
      "loss": 0.4738,
      "step": 56909
    },
    {
      "epoch": 1.748225969956686,
      "grad_norm": 0.4411797821521759,
      "learning_rate": 7.744365533312381e-07,
      "loss": 0.4821,
      "step": 56910
    },
    {
      "epoch": 1.7482566890916353,
      "grad_norm": 0.4383317530155182,
      "learning_rate": 7.742500855523738e-07,
      "loss": 0.5043,
      "step": 56911
    },
    {
      "epoch": 1.7482874082265845,
      "grad_norm": 0.41668668389320374,
      "learning_rate": 7.740636393208922e-07,
      "loss": 0.4751,
      "step": 56912
    },
    {
      "epoch": 1.7483181273615336,
      "grad_norm": 0.40778815746307373,
      "learning_rate": 7.738772146372287e-07,
      "loss": 0.5057,
      "step": 56913
    },
    {
      "epoch": 1.7483488464964827,
      "grad_norm": 0.4637386202812195,
      "learning_rate": 7.736908115018216e-07,
      "loss": 0.439,
      "step": 56914
    },
    {
      "epoch": 1.7483795656314318,
      "grad_norm": 0.4679551422595978,
      "learning_rate": 7.735044299151017e-07,
      "loss": 0.4493,
      "step": 56915
    },
    {
      "epoch": 1.748410284766381,
      "grad_norm": 0.3974476158618927,
      "learning_rate": 7.733180698775078e-07,
      "loss": 0.4639,
      "step": 56916
    },
    {
      "epoch": 1.74844100390133,
      "grad_norm": 0.49701330065727234,
      "learning_rate": 7.731317313894726e-07,
      "loss": 0.4811,
      "step": 56917
    },
    {
      "epoch": 1.7484717230362792,
      "grad_norm": 0.432194322347641,
      "learning_rate": 7.729454144514348e-07,
      "loss": 0.4167,
      "step": 56918
    },
    {
      "epoch": 1.7485024421712283,
      "grad_norm": 0.3953058123588562,
      "learning_rate": 7.727591190638261e-07,
      "loss": 0.5134,
      "step": 56919
    },
    {
      "epoch": 1.7485331613061776,
      "grad_norm": 0.3969394862651825,
      "learning_rate": 7.725728452270842e-07,
      "loss": 0.4745,
      "step": 56920
    },
    {
      "epoch": 1.7485638804411268,
      "grad_norm": 0.40310025215148926,
      "learning_rate": 7.723865929416396e-07,
      "loss": 0.4571,
      "step": 56921
    },
    {
      "epoch": 1.748594599576076,
      "grad_norm": 0.45481517910957336,
      "learning_rate": 7.722003622079343e-07,
      "loss": 0.4765,
      "step": 56922
    },
    {
      "epoch": 1.7486253187110252,
      "grad_norm": 0.45390036702156067,
      "learning_rate": 7.720141530263969e-07,
      "loss": 0.4298,
      "step": 56923
    },
    {
      "epoch": 1.7486560378459743,
      "grad_norm": 0.4469985365867615,
      "learning_rate": 7.71827965397467e-07,
      "loss": 0.4701,
      "step": 56924
    },
    {
      "epoch": 1.7486867569809235,
      "grad_norm": 0.4357983469963074,
      "learning_rate": 7.716417993215741e-07,
      "loss": 0.4814,
      "step": 56925
    },
    {
      "epoch": 1.7487174761158726,
      "grad_norm": 0.4410644769668579,
      "learning_rate": 7.714556547991602e-07,
      "loss": 0.4601,
      "step": 56926
    },
    {
      "epoch": 1.7487481952508217,
      "grad_norm": 0.4788658618927002,
      "learning_rate": 7.71269531830654e-07,
      "loss": 0.4887,
      "step": 56927
    },
    {
      "epoch": 1.7487789143857708,
      "grad_norm": 0.5165832042694092,
      "learning_rate": 7.710834304164938e-07,
      "loss": 0.4217,
      "step": 56928
    },
    {
      "epoch": 1.74880963352072,
      "grad_norm": 0.4893830716609955,
      "learning_rate": 7.708973505571116e-07,
      "loss": 0.4135,
      "step": 56929
    },
    {
      "epoch": 1.748840352655669,
      "grad_norm": 0.4740561544895172,
      "learning_rate": 7.707112922529425e-07,
      "loss": 0.5348,
      "step": 56930
    },
    {
      "epoch": 1.7488710717906184,
      "grad_norm": 0.4471012353897095,
      "learning_rate": 7.705252555044218e-07,
      "loss": 0.5025,
      "step": 56931
    },
    {
      "epoch": 1.7489017909255675,
      "grad_norm": 0.3994130492210388,
      "learning_rate": 7.703392403119847e-07,
      "loss": 0.3741,
      "step": 56932
    },
    {
      "epoch": 1.7489325100605166,
      "grad_norm": 0.39557498693466187,
      "learning_rate": 7.701532466760652e-07,
      "loss": 0.5241,
      "step": 56933
    },
    {
      "epoch": 1.748963229195466,
      "grad_norm": 0.44945672154426575,
      "learning_rate": 7.699672745970977e-07,
      "loss": 0.5383,
      "step": 56934
    },
    {
      "epoch": 1.748993948330415,
      "grad_norm": 0.41762468218803406,
      "learning_rate": 7.697813240755147e-07,
      "loss": 0.4396,
      "step": 56935
    },
    {
      "epoch": 1.7490246674653642,
      "grad_norm": 0.41909775137901306,
      "learning_rate": 7.69595395111753e-07,
      "loss": 0.4366,
      "step": 56936
    },
    {
      "epoch": 1.7490553866003133,
      "grad_norm": 0.43101581931114197,
      "learning_rate": 7.694094877062463e-07,
      "loss": 0.4505,
      "step": 56937
    },
    {
      "epoch": 1.7490861057352625,
      "grad_norm": 0.4209885597229004,
      "learning_rate": 7.692236018594279e-07,
      "loss": 0.4559,
      "step": 56938
    },
    {
      "epoch": 1.7491168248702116,
      "grad_norm": 0.4264635443687439,
      "learning_rate": 7.690377375717317e-07,
      "loss": 0.4398,
      "step": 56939
    },
    {
      "epoch": 1.7491475440051607,
      "grad_norm": 0.4864218235015869,
      "learning_rate": 7.68851894843593e-07,
      "loss": 0.4311,
      "step": 56940
    },
    {
      "epoch": 1.7491782631401098,
      "grad_norm": 0.4167185425758362,
      "learning_rate": 7.68666073675447e-07,
      "loss": 0.4584,
      "step": 56941
    },
    {
      "epoch": 1.7492089822750592,
      "grad_norm": 0.4673984944820404,
      "learning_rate": 7.684802740677244e-07,
      "loss": 0.4897,
      "step": 56942
    },
    {
      "epoch": 1.7492397014100083,
      "grad_norm": 0.40790843963623047,
      "learning_rate": 7.682944960208616e-07,
      "loss": 0.4436,
      "step": 56943
    },
    {
      "epoch": 1.7492704205449574,
      "grad_norm": 0.43189167976379395,
      "learning_rate": 7.681087395352905e-07,
      "loss": 0.4473,
      "step": 56944
    },
    {
      "epoch": 1.7493011396799067,
      "grad_norm": 0.4245867431163788,
      "learning_rate": 7.679230046114483e-07,
      "loss": 0.4912,
      "step": 56945
    },
    {
      "epoch": 1.7493318588148559,
      "grad_norm": 0.46003401279449463,
      "learning_rate": 7.67737291249765e-07,
      "loss": 0.497,
      "step": 56946
    },
    {
      "epoch": 1.749362577949805,
      "grad_norm": 0.4636038541793823,
      "learning_rate": 7.675515994506766e-07,
      "loss": 0.4878,
      "step": 56947
    },
    {
      "epoch": 1.749393297084754,
      "grad_norm": 0.4253980219364166,
      "learning_rate": 7.673659292146152e-07,
      "loss": 0.4311,
      "step": 56948
    },
    {
      "epoch": 1.7494240162197032,
      "grad_norm": 0.4026701748371124,
      "learning_rate": 7.67180280542018e-07,
      "loss": 0.4378,
      "step": 56949
    },
    {
      "epoch": 1.7494547353546523,
      "grad_norm": 0.4600491523742676,
      "learning_rate": 7.669946534333139e-07,
      "loss": 0.4347,
      "step": 56950
    },
    {
      "epoch": 1.7494854544896015,
      "grad_norm": 0.4656069278717041,
      "learning_rate": 7.66809047888939e-07,
      "loss": 0.4497,
      "step": 56951
    },
    {
      "epoch": 1.7495161736245506,
      "grad_norm": 0.45572125911712646,
      "learning_rate": 7.666234639093262e-07,
      "loss": 0.4764,
      "step": 56952
    },
    {
      "epoch": 1.7495468927595,
      "grad_norm": 0.43890970945358276,
      "learning_rate": 7.664379014949086e-07,
      "loss": 0.4975,
      "step": 56953
    },
    {
      "epoch": 1.749577611894449,
      "grad_norm": 0.488489031791687,
      "learning_rate": 7.662523606461225e-07,
      "loss": 0.43,
      "step": 56954
    },
    {
      "epoch": 1.7496083310293982,
      "grad_norm": 0.46657317876815796,
      "learning_rate": 7.660668413633976e-07,
      "loss": 0.4325,
      "step": 56955
    },
    {
      "epoch": 1.7496390501643475,
      "grad_norm": 0.444476455450058,
      "learning_rate": 7.658813436471691e-07,
      "loss": 0.4095,
      "step": 56956
    },
    {
      "epoch": 1.7496697692992966,
      "grad_norm": 0.4490804672241211,
      "learning_rate": 7.656958674978665e-07,
      "loss": 0.5293,
      "step": 56957
    },
    {
      "epoch": 1.7497004884342457,
      "grad_norm": 0.4529624879360199,
      "learning_rate": 7.655104129159296e-07,
      "loss": 0.5144,
      "step": 56958
    },
    {
      "epoch": 1.7497312075691949,
      "grad_norm": 0.43808725476264954,
      "learning_rate": 7.65324979901787e-07,
      "loss": 0.4735,
      "step": 56959
    },
    {
      "epoch": 1.749761926704144,
      "grad_norm": 0.47401922941207886,
      "learning_rate": 7.651395684558738e-07,
      "loss": 0.4782,
      "step": 56960
    },
    {
      "epoch": 1.749792645839093,
      "grad_norm": 0.4257189929485321,
      "learning_rate": 7.649541785786208e-07,
      "loss": 0.4482,
      "step": 56961
    },
    {
      "epoch": 1.7498233649740422,
      "grad_norm": 0.419425904750824,
      "learning_rate": 7.64768810270462e-07,
      "loss": 0.4732,
      "step": 56962
    },
    {
      "epoch": 1.7498540841089913,
      "grad_norm": 0.45534688234329224,
      "learning_rate": 7.645834635318306e-07,
      "loss": 0.4403,
      "step": 56963
    },
    {
      "epoch": 1.7498848032439407,
      "grad_norm": 0.4393501281738281,
      "learning_rate": 7.643981383631615e-07,
      "loss": 0.469,
      "step": 56964
    },
    {
      "epoch": 1.7499155223788898,
      "grad_norm": 0.46009624004364014,
      "learning_rate": 7.642128347648837e-07,
      "loss": 0.4242,
      "step": 56965
    },
    {
      "epoch": 1.749946241513839,
      "grad_norm": 0.47081637382507324,
      "learning_rate": 7.640275527374319e-07,
      "loss": 0.5355,
      "step": 56966
    },
    {
      "epoch": 1.7499769606487883,
      "grad_norm": 0.44115880131721497,
      "learning_rate": 7.638422922812394e-07,
      "loss": 0.5314,
      "step": 56967
    },
    {
      "epoch": 1.7500076797837374,
      "grad_norm": 0.4898828864097595,
      "learning_rate": 7.63657053396738e-07,
      "loss": 0.4661,
      "step": 56968
    },
    {
      "epoch": 1.7500383989186865,
      "grad_norm": 0.431732714176178,
      "learning_rate": 7.634718360843618e-07,
      "loss": 0.4743,
      "step": 56969
    },
    {
      "epoch": 1.7500691180536356,
      "grad_norm": 0.4552168846130371,
      "learning_rate": 7.632866403445405e-07,
      "loss": 0.4648,
      "step": 56970
    },
    {
      "epoch": 1.7500998371885848,
      "grad_norm": 0.4504014253616333,
      "learning_rate": 7.631014661777081e-07,
      "loss": 0.4689,
      "step": 56971
    },
    {
      "epoch": 1.7501305563235339,
      "grad_norm": 0.4539783298969269,
      "learning_rate": 7.629163135842976e-07,
      "loss": 0.4256,
      "step": 56972
    },
    {
      "epoch": 1.750161275458483,
      "grad_norm": 0.45383965969085693,
      "learning_rate": 7.627311825647432e-07,
      "loss": 0.5266,
      "step": 56973
    },
    {
      "epoch": 1.750191994593432,
      "grad_norm": 0.48152998089790344,
      "learning_rate": 7.625460731194734e-07,
      "loss": 0.4533,
      "step": 56974
    },
    {
      "epoch": 1.7502227137283815,
      "grad_norm": 0.5289570689201355,
      "learning_rate": 7.623609852489223e-07,
      "loss": 0.501,
      "step": 56975
    },
    {
      "epoch": 1.7502534328633306,
      "grad_norm": 0.4301227927207947,
      "learning_rate": 7.621759189535228e-07,
      "loss": 0.5051,
      "step": 56976
    },
    {
      "epoch": 1.7502841519982797,
      "grad_norm": 0.43964874744415283,
      "learning_rate": 7.619908742337078e-07,
      "loss": 0.4591,
      "step": 56977
    },
    {
      "epoch": 1.750314871133229,
      "grad_norm": 0.46612226963043213,
      "learning_rate": 7.618058510899062e-07,
      "loss": 0.423,
      "step": 56978
    },
    {
      "epoch": 1.7503455902681782,
      "grad_norm": 0.4125286638736725,
      "learning_rate": 7.61620849522553e-07,
      "loss": 0.4463,
      "step": 56979
    },
    {
      "epoch": 1.7503763094031273,
      "grad_norm": 0.429379403591156,
      "learning_rate": 7.614358695320789e-07,
      "loss": 0.4252,
      "step": 56980
    },
    {
      "epoch": 1.7504070285380764,
      "grad_norm": 0.44359084963798523,
      "learning_rate": 7.612509111189182e-07,
      "loss": 0.4227,
      "step": 56981
    },
    {
      "epoch": 1.7504377476730255,
      "grad_norm": 0.4557379186153412,
      "learning_rate": 7.610659742835003e-07,
      "loss": 0.492,
      "step": 56982
    },
    {
      "epoch": 1.7504684668079746,
      "grad_norm": 0.4340827763080597,
      "learning_rate": 7.608810590262583e-07,
      "loss": 0.4836,
      "step": 56983
    },
    {
      "epoch": 1.7504991859429238,
      "grad_norm": 0.4449593722820282,
      "learning_rate": 7.606961653476219e-07,
      "loss": 0.4406,
      "step": 56984
    },
    {
      "epoch": 1.7505299050778729,
      "grad_norm": 0.4946663975715637,
      "learning_rate": 7.605112932480274e-07,
      "loss": 0.4436,
      "step": 56985
    },
    {
      "epoch": 1.7505606242128222,
      "grad_norm": 0.48130616545677185,
      "learning_rate": 7.603264427279033e-07,
      "loss": 0.4999,
      "step": 56986
    },
    {
      "epoch": 1.7505913433477713,
      "grad_norm": 0.3997412621974945,
      "learning_rate": 7.601416137876816e-07,
      "loss": 0.3848,
      "step": 56987
    },
    {
      "epoch": 1.7506220624827205,
      "grad_norm": 0.4695230722427368,
      "learning_rate": 7.59956806427794e-07,
      "loss": 0.5103,
      "step": 56988
    },
    {
      "epoch": 1.7506527816176698,
      "grad_norm": 0.4023563861846924,
      "learning_rate": 7.597720206486725e-07,
      "loss": 0.4155,
      "step": 56989
    },
    {
      "epoch": 1.750683500752619,
      "grad_norm": 0.4062679708003998,
      "learning_rate": 7.595872564507512e-07,
      "loss": 0.4515,
      "step": 56990
    },
    {
      "epoch": 1.750714219887568,
      "grad_norm": 0.47455576062202454,
      "learning_rate": 7.594025138344574e-07,
      "loss": 0.5379,
      "step": 56991
    },
    {
      "epoch": 1.7507449390225172,
      "grad_norm": 0.426471471786499,
      "learning_rate": 7.592177928002253e-07,
      "loss": 0.5034,
      "step": 56992
    },
    {
      "epoch": 1.7507756581574663,
      "grad_norm": 0.521081805229187,
      "learning_rate": 7.590330933484835e-07,
      "loss": 0.4106,
      "step": 56993
    },
    {
      "epoch": 1.7508063772924154,
      "grad_norm": 0.4309101700782776,
      "learning_rate": 7.588484154796672e-07,
      "loss": 0.4799,
      "step": 56994
    },
    {
      "epoch": 1.7508370964273645,
      "grad_norm": 0.4438289999961853,
      "learning_rate": 7.586637591942047e-07,
      "loss": 0.3912,
      "step": 56995
    },
    {
      "epoch": 1.7508678155623136,
      "grad_norm": 0.44371312856674194,
      "learning_rate": 7.584791244925305e-07,
      "loss": 0.519,
      "step": 56996
    },
    {
      "epoch": 1.750898534697263,
      "grad_norm": 0.4513305723667145,
      "learning_rate": 7.582945113750717e-07,
      "loss": 0.4454,
      "step": 56997
    },
    {
      "epoch": 1.750929253832212,
      "grad_norm": 0.6766025424003601,
      "learning_rate": 7.581099198422615e-07,
      "loss": 0.5129,
      "step": 56998
    },
    {
      "epoch": 1.7509599729671612,
      "grad_norm": 0.44563984870910645,
      "learning_rate": 7.579253498945305e-07,
      "loss": 0.4693,
      "step": 56999
    },
    {
      "epoch": 1.7509906921021106,
      "grad_norm": 1.656112551689148,
      "learning_rate": 7.577408015323129e-07,
      "loss": 0.4489,
      "step": 57000
    },
    {
      "epoch": 1.7510214112370597,
      "grad_norm": 0.46769487857818604,
      "learning_rate": 7.57556274756035e-07,
      "loss": 0.4752,
      "step": 57001
    },
    {
      "epoch": 1.7510521303720088,
      "grad_norm": 0.45127537846565247,
      "learning_rate": 7.573717695661297e-07,
      "loss": 0.3984,
      "step": 57002
    },
    {
      "epoch": 1.751082849506958,
      "grad_norm": 0.4172486364841461,
      "learning_rate": 7.57187285963028e-07,
      "loss": 0.4184,
      "step": 57003
    },
    {
      "epoch": 1.751113568641907,
      "grad_norm": 0.45929980278015137,
      "learning_rate": 7.570028239471639e-07,
      "loss": 0.4811,
      "step": 57004
    },
    {
      "epoch": 1.7511442877768562,
      "grad_norm": 0.424223393201828,
      "learning_rate": 7.568183835189625e-07,
      "loss": 0.4876,
      "step": 57005
    },
    {
      "epoch": 1.7511750069118053,
      "grad_norm": 0.41575896739959717,
      "learning_rate": 7.566339646788567e-07,
      "loss": 0.4643,
      "step": 57006
    },
    {
      "epoch": 1.7512057260467544,
      "grad_norm": 0.4619593024253845,
      "learning_rate": 7.564495674272787e-07,
      "loss": 0.481,
      "step": 57007
    },
    {
      "epoch": 1.7512364451817037,
      "grad_norm": 0.45853191614151,
      "learning_rate": 7.562651917646579e-07,
      "loss": 0.434,
      "step": 57008
    },
    {
      "epoch": 1.7512671643166529,
      "grad_norm": 0.44423192739486694,
      "learning_rate": 7.560808376914275e-07,
      "loss": 0.5525,
      "step": 57009
    },
    {
      "epoch": 1.751297883451602,
      "grad_norm": 0.4680936932563782,
      "learning_rate": 7.558965052080136e-07,
      "loss": 0.4383,
      "step": 57010
    },
    {
      "epoch": 1.7513286025865513,
      "grad_norm": 0.44125446677207947,
      "learning_rate": 7.557121943148493e-07,
      "loss": 0.4683,
      "step": 57011
    },
    {
      "epoch": 1.7513593217215004,
      "grad_norm": 0.42058271169662476,
      "learning_rate": 7.555279050123654e-07,
      "loss": 0.391,
      "step": 57012
    },
    {
      "epoch": 1.7513900408564496,
      "grad_norm": 0.4441086947917938,
      "learning_rate": 7.553436373009926e-07,
      "loss": 0.432,
      "step": 57013
    },
    {
      "epoch": 1.7514207599913987,
      "grad_norm": 0.39138728380203247,
      "learning_rate": 7.551593911811594e-07,
      "loss": 0.4396,
      "step": 57014
    },
    {
      "epoch": 1.7514514791263478,
      "grad_norm": 0.41820114850997925,
      "learning_rate": 7.549751666532967e-07,
      "loss": 0.4829,
      "step": 57015
    },
    {
      "epoch": 1.751482198261297,
      "grad_norm": 0.4627201557159424,
      "learning_rate": 7.547909637178342e-07,
      "loss": 0.5051,
      "step": 57016
    },
    {
      "epoch": 1.751512917396246,
      "grad_norm": 0.4572714567184448,
      "learning_rate": 7.546067823752057e-07,
      "loss": 0.4955,
      "step": 57017
    },
    {
      "epoch": 1.7515436365311952,
      "grad_norm": 0.4540078938007355,
      "learning_rate": 7.544226226258377e-07,
      "loss": 0.4757,
      "step": 57018
    },
    {
      "epoch": 1.7515743556661443,
      "grad_norm": 0.39771202206611633,
      "learning_rate": 7.542384844701622e-07,
      "loss": 0.4492,
      "step": 57019
    },
    {
      "epoch": 1.7516050748010936,
      "grad_norm": 0.4563504457473755,
      "learning_rate": 7.540543679086054e-07,
      "loss": 0.4539,
      "step": 57020
    },
    {
      "epoch": 1.7516357939360427,
      "grad_norm": 0.41747909784317017,
      "learning_rate": 7.538702729416037e-07,
      "loss": 0.4932,
      "step": 57021
    },
    {
      "epoch": 1.751666513070992,
      "grad_norm": 0.4710010290145874,
      "learning_rate": 7.53686199569581e-07,
      "loss": 0.4503,
      "step": 57022
    },
    {
      "epoch": 1.7516972322059412,
      "grad_norm": 0.4779815971851349,
      "learning_rate": 7.535021477929716e-07,
      "loss": 0.468,
      "step": 57023
    },
    {
      "epoch": 1.7517279513408903,
      "grad_norm": 0.3924191892147064,
      "learning_rate": 7.53318117612204e-07,
      "loss": 0.4789,
      "step": 57024
    },
    {
      "epoch": 1.7517586704758394,
      "grad_norm": 0.46354588866233826,
      "learning_rate": 7.531341090277056e-07,
      "loss": 0.4453,
      "step": 57025
    },
    {
      "epoch": 1.7517893896107886,
      "grad_norm": 0.4507783055305481,
      "learning_rate": 7.529501220399104e-07,
      "loss": 0.5161,
      "step": 57026
    },
    {
      "epoch": 1.7518201087457377,
      "grad_norm": 0.4166684150695801,
      "learning_rate": 7.52766156649245e-07,
      "loss": 0.5415,
      "step": 57027
    },
    {
      "epoch": 1.7518508278806868,
      "grad_norm": 0.4228086471557617,
      "learning_rate": 7.52582212856141e-07,
      "loss": 0.4665,
      "step": 57028
    },
    {
      "epoch": 1.751881547015636,
      "grad_norm": 0.43386033177375793,
      "learning_rate": 7.52398290661025e-07,
      "loss": 0.5929,
      "step": 57029
    },
    {
      "epoch": 1.751912266150585,
      "grad_norm": 0.41367149353027344,
      "learning_rate": 7.522143900643309e-07,
      "loss": 0.4637,
      "step": 57030
    },
    {
      "epoch": 1.7519429852855344,
      "grad_norm": 0.4171085059642792,
      "learning_rate": 7.52030511066485e-07,
      "loss": 0.4879,
      "step": 57031
    },
    {
      "epoch": 1.7519737044204835,
      "grad_norm": 0.45683467388153076,
      "learning_rate": 7.518466536679192e-07,
      "loss": 0.46,
      "step": 57032
    },
    {
      "epoch": 1.7520044235554328,
      "grad_norm": 0.4646216928958893,
      "learning_rate": 7.516628178690599e-07,
      "loss": 0.4062,
      "step": 57033
    },
    {
      "epoch": 1.752035142690382,
      "grad_norm": 0.4486735165119171,
      "learning_rate": 7.514790036703378e-07,
      "loss": 0.5217,
      "step": 57034
    },
    {
      "epoch": 1.752065861825331,
      "grad_norm": 0.44648346304893494,
      "learning_rate": 7.512952110721816e-07,
      "loss": 0.4168,
      "step": 57035
    },
    {
      "epoch": 1.7520965809602802,
      "grad_norm": 0.4249182939529419,
      "learning_rate": 7.511114400750241e-07,
      "loss": 0.4569,
      "step": 57036
    },
    {
      "epoch": 1.7521273000952293,
      "grad_norm": 0.45740601420402527,
      "learning_rate": 7.509276906792895e-07,
      "loss": 0.4711,
      "step": 57037
    },
    {
      "epoch": 1.7521580192301784,
      "grad_norm": 0.4169081747531891,
      "learning_rate": 7.507439628854097e-07,
      "loss": 0.4654,
      "step": 57038
    },
    {
      "epoch": 1.7521887383651276,
      "grad_norm": 0.42652180790901184,
      "learning_rate": 7.50560256693813e-07,
      "loss": 0.4453,
      "step": 57039
    },
    {
      "epoch": 1.7522194575000767,
      "grad_norm": 0.43354111909866333,
      "learning_rate": 7.503765721049305e-07,
      "loss": 0.4743,
      "step": 57040
    },
    {
      "epoch": 1.7522501766350258,
      "grad_norm": 0.4732484221458435,
      "learning_rate": 7.501929091191884e-07,
      "loss": 0.4458,
      "step": 57041
    },
    {
      "epoch": 1.7522808957699751,
      "grad_norm": 0.4795863926410675,
      "learning_rate": 7.500092677370164e-07,
      "loss": 0.5363,
      "step": 57042
    },
    {
      "epoch": 1.7523116149049243,
      "grad_norm": 0.47836798429489136,
      "learning_rate": 7.498256479588439e-07,
      "loss": 0.4075,
      "step": 57043
    },
    {
      "epoch": 1.7523423340398734,
      "grad_norm": 0.42482027411460876,
      "learning_rate": 7.496420497850987e-07,
      "loss": 0.4809,
      "step": 57044
    },
    {
      "epoch": 1.7523730531748227,
      "grad_norm": 0.4567660391330719,
      "learning_rate": 7.494584732162135e-07,
      "loss": 0.4174,
      "step": 57045
    },
    {
      "epoch": 1.7524037723097718,
      "grad_norm": 0.4936893880367279,
      "learning_rate": 7.492749182526115e-07,
      "loss": 0.4975,
      "step": 57046
    },
    {
      "epoch": 1.752434491444721,
      "grad_norm": 0.4093339741230011,
      "learning_rate": 7.490913848947245e-07,
      "loss": 0.447,
      "step": 57047
    },
    {
      "epoch": 1.75246521057967,
      "grad_norm": 0.4120325446128845,
      "learning_rate": 7.489078731429799e-07,
      "loss": 0.4002,
      "step": 57048
    },
    {
      "epoch": 1.7524959297146192,
      "grad_norm": 0.4552728831768036,
      "learning_rate": 7.487243829978097e-07,
      "loss": 0.533,
      "step": 57049
    },
    {
      "epoch": 1.7525266488495683,
      "grad_norm": 0.4154016673564911,
      "learning_rate": 7.485409144596379e-07,
      "loss": 0.4763,
      "step": 57050
    },
    {
      "epoch": 1.7525573679845174,
      "grad_norm": 0.4421415328979492,
      "learning_rate": 7.48357467528894e-07,
      "loss": 0.4405,
      "step": 57051
    },
    {
      "epoch": 1.7525880871194666,
      "grad_norm": 0.4540237486362457,
      "learning_rate": 7.48174042206008e-07,
      "loss": 0.4468,
      "step": 57052
    },
    {
      "epoch": 1.752618806254416,
      "grad_norm": 0.4252103865146637,
      "learning_rate": 7.479906384914104e-07,
      "loss": 0.475,
      "step": 57053
    },
    {
      "epoch": 1.752649525389365,
      "grad_norm": 0.421660453081131,
      "learning_rate": 7.478072563855233e-07,
      "loss": 0.4292,
      "step": 57054
    },
    {
      "epoch": 1.7526802445243141,
      "grad_norm": 0.5833058953285217,
      "learning_rate": 7.476238958887816e-07,
      "loss": 0.4492,
      "step": 57055
    },
    {
      "epoch": 1.7527109636592635,
      "grad_norm": 0.4251921772956848,
      "learning_rate": 7.474405570016064e-07,
      "loss": 0.3959,
      "step": 57056
    },
    {
      "epoch": 1.7527416827942126,
      "grad_norm": 0.4544154703617096,
      "learning_rate": 7.472572397244337e-07,
      "loss": 0.5017,
      "step": 57057
    },
    {
      "epoch": 1.7527724019291617,
      "grad_norm": 0.41978833079338074,
      "learning_rate": 7.470739440576857e-07,
      "loss": 0.4492,
      "step": 57058
    },
    {
      "epoch": 1.7528031210641108,
      "grad_norm": 0.4142707884311676,
      "learning_rate": 7.468906700017931e-07,
      "loss": 0.4289,
      "step": 57059
    },
    {
      "epoch": 1.75283384019906,
      "grad_norm": 0.44238990545272827,
      "learning_rate": 7.467074175571854e-07,
      "loss": 0.4379,
      "step": 57060
    },
    {
      "epoch": 1.752864559334009,
      "grad_norm": 0.4125184714794159,
      "learning_rate": 7.465241867242845e-07,
      "loss": 0.4965,
      "step": 57061
    },
    {
      "epoch": 1.7528952784689582,
      "grad_norm": 0.4588490426540375,
      "learning_rate": 7.463409775035268e-07,
      "loss": 0.4571,
      "step": 57062
    },
    {
      "epoch": 1.7529259976039073,
      "grad_norm": 0.4178043007850647,
      "learning_rate": 7.461577898953343e-07,
      "loss": 0.4353,
      "step": 57063
    },
    {
      "epoch": 1.7529567167388567,
      "grad_norm": 0.4343208372592926,
      "learning_rate": 7.459746239001386e-07,
      "loss": 0.4441,
      "step": 57064
    },
    {
      "epoch": 1.7529874358738058,
      "grad_norm": 0.43393439054489136,
      "learning_rate": 7.457914795183629e-07,
      "loss": 0.4868,
      "step": 57065
    },
    {
      "epoch": 1.753018155008755,
      "grad_norm": 0.4460274577140808,
      "learning_rate": 7.45608356750438e-07,
      "loss": 0.4419,
      "step": 57066
    },
    {
      "epoch": 1.7530488741437042,
      "grad_norm": 0.4249018132686615,
      "learning_rate": 7.454252555967912e-07,
      "loss": 0.4366,
      "step": 57067
    },
    {
      "epoch": 1.7530795932786534,
      "grad_norm": 0.42382970452308655,
      "learning_rate": 7.452421760578521e-07,
      "loss": 0.4522,
      "step": 57068
    },
    {
      "epoch": 1.7531103124136025,
      "grad_norm": 0.41504985094070435,
      "learning_rate": 7.450591181340438e-07,
      "loss": 0.4951,
      "step": 57069
    },
    {
      "epoch": 1.7531410315485516,
      "grad_norm": 0.43635764718055725,
      "learning_rate": 7.44876081825796e-07,
      "loss": 0.4201,
      "step": 57070
    },
    {
      "epoch": 1.7531717506835007,
      "grad_norm": 0.41035497188568115,
      "learning_rate": 7.446930671335373e-07,
      "loss": 0.3992,
      "step": 57071
    },
    {
      "epoch": 1.7532024698184498,
      "grad_norm": 0.469741553068161,
      "learning_rate": 7.44510074057696e-07,
      "loss": 0.4457,
      "step": 57072
    },
    {
      "epoch": 1.753233188953399,
      "grad_norm": 0.3946652412414551,
      "learning_rate": 7.443271025986953e-07,
      "loss": 0.488,
      "step": 57073
    },
    {
      "epoch": 1.753263908088348,
      "grad_norm": 0.4252347946166992,
      "learning_rate": 7.44144152756966e-07,
      "loss": 0.5221,
      "step": 57074
    },
    {
      "epoch": 1.7532946272232974,
      "grad_norm": 0.49955856800079346,
      "learning_rate": 7.439612245329342e-07,
      "loss": 0.4151,
      "step": 57075
    },
    {
      "epoch": 1.7533253463582466,
      "grad_norm": 0.42199042439460754,
      "learning_rate": 7.437783179270286e-07,
      "loss": 0.459,
      "step": 57076
    },
    {
      "epoch": 1.7533560654931957,
      "grad_norm": 0.47713014483451843,
      "learning_rate": 7.435954329396733e-07,
      "loss": 0.4371,
      "step": 57077
    },
    {
      "epoch": 1.753386784628145,
      "grad_norm": 0.4054478704929352,
      "learning_rate": 7.434125695712979e-07,
      "loss": 0.5714,
      "step": 57078
    },
    {
      "epoch": 1.7534175037630941,
      "grad_norm": 0.49564021825790405,
      "learning_rate": 7.432297278223288e-07,
      "loss": 0.6,
      "step": 57079
    },
    {
      "epoch": 1.7534482228980433,
      "grad_norm": 0.41914883255958557,
      "learning_rate": 7.430469076931935e-07,
      "loss": 0.4997,
      "step": 57080
    },
    {
      "epoch": 1.7534789420329924,
      "grad_norm": 0.39867886900901794,
      "learning_rate": 7.428641091843202e-07,
      "loss": 0.5184,
      "step": 57081
    },
    {
      "epoch": 1.7535096611679415,
      "grad_norm": 0.4525245130062103,
      "learning_rate": 7.426813322961324e-07,
      "loss": 0.4763,
      "step": 57082
    },
    {
      "epoch": 1.7535403803028906,
      "grad_norm": 0.4316975772380829,
      "learning_rate": 7.424985770290594e-07,
      "loss": 0.5095,
      "step": 57083
    },
    {
      "epoch": 1.7535710994378397,
      "grad_norm": 0.39707380533218384,
      "learning_rate": 7.423158433835265e-07,
      "loss": 0.4054,
      "step": 57084
    },
    {
      "epoch": 1.7536018185727889,
      "grad_norm": 0.42912590503692627,
      "learning_rate": 7.421331313599644e-07,
      "loss": 0.4514,
      "step": 57085
    },
    {
      "epoch": 1.7536325377077382,
      "grad_norm": 0.44648101925849915,
      "learning_rate": 7.419504409587941e-07,
      "loss": 0.5081,
      "step": 57086
    },
    {
      "epoch": 1.7536632568426873,
      "grad_norm": 0.4276241064071655,
      "learning_rate": 7.417677721804473e-07,
      "loss": 0.4822,
      "step": 57087
    },
    {
      "epoch": 1.7536939759776364,
      "grad_norm": 0.43736568093299866,
      "learning_rate": 7.415851250253448e-07,
      "loss": 0.5277,
      "step": 57088
    },
    {
      "epoch": 1.7537246951125858,
      "grad_norm": 0.46489477157592773,
      "learning_rate": 7.414024994939207e-07,
      "loss": 0.4504,
      "step": 57089
    },
    {
      "epoch": 1.753755414247535,
      "grad_norm": 0.44645145535469055,
      "learning_rate": 7.412198955865957e-07,
      "loss": 0.5203,
      "step": 57090
    },
    {
      "epoch": 1.753786133382484,
      "grad_norm": 0.4587956368923187,
      "learning_rate": 7.410373133038007e-07,
      "loss": 0.5098,
      "step": 57091
    },
    {
      "epoch": 1.7538168525174331,
      "grad_norm": 0.45197635889053345,
      "learning_rate": 7.408547526459553e-07,
      "loss": 0.4741,
      "step": 57092
    },
    {
      "epoch": 1.7538475716523823,
      "grad_norm": 0.4812471866607666,
      "learning_rate": 7.406722136134936e-07,
      "loss": 0.4456,
      "step": 57093
    },
    {
      "epoch": 1.7538782907873314,
      "grad_norm": 0.4596070647239685,
      "learning_rate": 7.404896962068375e-07,
      "loss": 0.4391,
      "step": 57094
    },
    {
      "epoch": 1.7539090099222805,
      "grad_norm": 0.45254844427108765,
      "learning_rate": 7.403072004264155e-07,
      "loss": 0.3877,
      "step": 57095
    },
    {
      "epoch": 1.7539397290572296,
      "grad_norm": 1.5757020711898804,
      "learning_rate": 7.401247262726519e-07,
      "loss": 0.4444,
      "step": 57096
    },
    {
      "epoch": 1.753970448192179,
      "grad_norm": 0.4454088807106018,
      "learning_rate": 7.399422737459716e-07,
      "loss": 0.4108,
      "step": 57097
    },
    {
      "epoch": 1.754001167327128,
      "grad_norm": 0.47713252902030945,
      "learning_rate": 7.397598428468055e-07,
      "loss": 0.4005,
      "step": 57098
    },
    {
      "epoch": 1.7540318864620772,
      "grad_norm": 0.402204304933548,
      "learning_rate": 7.395774335755767e-07,
      "loss": 0.3845,
      "step": 57099
    },
    {
      "epoch": 1.7540626055970265,
      "grad_norm": 0.4338277578353882,
      "learning_rate": 7.393950459327126e-07,
      "loss": 0.5376,
      "step": 57100
    },
    {
      "epoch": 1.7540933247319757,
      "grad_norm": 0.3792550563812256,
      "learning_rate": 7.392126799186361e-07,
      "loss": 0.4386,
      "step": 57101
    },
    {
      "epoch": 1.7541240438669248,
      "grad_norm": 0.41441255807876587,
      "learning_rate": 7.390303355337758e-07,
      "loss": 0.4653,
      "step": 57102
    },
    {
      "epoch": 1.754154763001874,
      "grad_norm": 0.48521754145622253,
      "learning_rate": 7.388480127785557e-07,
      "loss": 0.5108,
      "step": 57103
    },
    {
      "epoch": 1.754185482136823,
      "grad_norm": 0.4559110701084137,
      "learning_rate": 7.386657116534057e-07,
      "loss": 0.3963,
      "step": 57104
    },
    {
      "epoch": 1.7542162012717721,
      "grad_norm": 0.41153499484062195,
      "learning_rate": 7.384834321587464e-07,
      "loss": 0.4434,
      "step": 57105
    },
    {
      "epoch": 1.7542469204067213,
      "grad_norm": 0.4204517900943756,
      "learning_rate": 7.383011742950063e-07,
      "loss": 0.4639,
      "step": 57106
    },
    {
      "epoch": 1.7542776395416704,
      "grad_norm": 0.4402939975261688,
      "learning_rate": 7.381189380626108e-07,
      "loss": 0.4123,
      "step": 57107
    },
    {
      "epoch": 1.7543083586766197,
      "grad_norm": 0.4405428171157837,
      "learning_rate": 7.379367234619872e-07,
      "loss": 0.5245,
      "step": 57108
    },
    {
      "epoch": 1.7543390778115688,
      "grad_norm": 0.458440899848938,
      "learning_rate": 7.377545304935563e-07,
      "loss": 0.4618,
      "step": 57109
    },
    {
      "epoch": 1.754369796946518,
      "grad_norm": 0.40094059705734253,
      "learning_rate": 7.375723591577478e-07,
      "loss": 0.4047,
      "step": 57110
    },
    {
      "epoch": 1.7544005160814673,
      "grad_norm": 0.4633118808269501,
      "learning_rate": 7.373902094549856e-07,
      "loss": 0.4847,
      "step": 57111
    },
    {
      "epoch": 1.7544312352164164,
      "grad_norm": 0.4429873526096344,
      "learning_rate": 7.372080813856963e-07,
      "loss": 0.4533,
      "step": 57112
    },
    {
      "epoch": 1.7544619543513655,
      "grad_norm": 0.39984390139579773,
      "learning_rate": 7.370259749503039e-07,
      "loss": 0.4286,
      "step": 57113
    },
    {
      "epoch": 1.7544926734863147,
      "grad_norm": 0.4482118785381317,
      "learning_rate": 7.368438901492336e-07,
      "loss": 0.514,
      "step": 57114
    },
    {
      "epoch": 1.7545233926212638,
      "grad_norm": 0.5735181570053101,
      "learning_rate": 7.366618269829117e-07,
      "loss": 0.4869,
      "step": 57115
    },
    {
      "epoch": 1.754554111756213,
      "grad_norm": 0.40610989928245544,
      "learning_rate": 7.364797854517635e-07,
      "loss": 0.5026,
      "step": 57116
    },
    {
      "epoch": 1.754584830891162,
      "grad_norm": 0.42268431186676025,
      "learning_rate": 7.362977655562142e-07,
      "loss": 0.4639,
      "step": 57117
    },
    {
      "epoch": 1.7546155500261111,
      "grad_norm": 0.41059547662734985,
      "learning_rate": 7.361157672966878e-07,
      "loss": 0.4858,
      "step": 57118
    },
    {
      "epoch": 1.7546462691610605,
      "grad_norm": 0.4600105881690979,
      "learning_rate": 7.359337906736097e-07,
      "loss": 0.4413,
      "step": 57119
    },
    {
      "epoch": 1.7546769882960096,
      "grad_norm": 0.41664883494377136,
      "learning_rate": 7.357518356874049e-07,
      "loss": 0.4495,
      "step": 57120
    },
    {
      "epoch": 1.7547077074309587,
      "grad_norm": 0.4282672703266144,
      "learning_rate": 7.35569902338501e-07,
      "loss": 0.5358,
      "step": 57121
    },
    {
      "epoch": 1.754738426565908,
      "grad_norm": 0.4236518442630768,
      "learning_rate": 7.353879906273187e-07,
      "loss": 0.4576,
      "step": 57122
    },
    {
      "epoch": 1.7547691457008572,
      "grad_norm": 0.4365582764148712,
      "learning_rate": 7.352061005542854e-07,
      "loss": 0.4262,
      "step": 57123
    },
    {
      "epoch": 1.7547998648358063,
      "grad_norm": 0.461357980966568,
      "learning_rate": 7.350242321198231e-07,
      "loss": 0.537,
      "step": 57124
    },
    {
      "epoch": 1.7548305839707554,
      "grad_norm": 0.45058390498161316,
      "learning_rate": 7.348423853243624e-07,
      "loss": 0.4469,
      "step": 57125
    },
    {
      "epoch": 1.7548613031057045,
      "grad_norm": 0.4442356526851654,
      "learning_rate": 7.346605601683221e-07,
      "loss": 0.378,
      "step": 57126
    },
    {
      "epoch": 1.7548920222406537,
      "grad_norm": 0.47921210527420044,
      "learning_rate": 7.344787566521305e-07,
      "loss": 0.4082,
      "step": 57127
    },
    {
      "epoch": 1.7549227413756028,
      "grad_norm": 0.413979709148407,
      "learning_rate": 7.342969747762096e-07,
      "loss": 0.477,
      "step": 57128
    },
    {
      "epoch": 1.754953460510552,
      "grad_norm": 0.4583795666694641,
      "learning_rate": 7.341152145409847e-07,
      "loss": 0.4528,
      "step": 57129
    },
    {
      "epoch": 1.754984179645501,
      "grad_norm": 0.4534689486026764,
      "learning_rate": 7.339334759468819e-07,
      "loss": 0.4422,
      "step": 57130
    },
    {
      "epoch": 1.7550148987804504,
      "grad_norm": 0.44850000739097595,
      "learning_rate": 7.337517589943255e-07,
      "loss": 0.3667,
      "step": 57131
    },
    {
      "epoch": 1.7550456179153995,
      "grad_norm": 0.4625900387763977,
      "learning_rate": 7.335700636837373e-07,
      "loss": 0.4906,
      "step": 57132
    },
    {
      "epoch": 1.7550763370503488,
      "grad_norm": 0.41180092096328735,
      "learning_rate": 7.333883900155425e-07,
      "loss": 0.4481,
      "step": 57133
    },
    {
      "epoch": 1.755107056185298,
      "grad_norm": 0.46149271726608276,
      "learning_rate": 7.332067379901686e-07,
      "loss": 0.4035,
      "step": 57134
    },
    {
      "epoch": 1.755137775320247,
      "grad_norm": 0.3780532479286194,
      "learning_rate": 7.330251076080364e-07,
      "loss": 0.4386,
      "step": 57135
    },
    {
      "epoch": 1.7551684944551962,
      "grad_norm": 0.4664851427078247,
      "learning_rate": 7.328434988695732e-07,
      "loss": 0.5132,
      "step": 57136
    },
    {
      "epoch": 1.7551992135901453,
      "grad_norm": 0.47277215123176575,
      "learning_rate": 7.326619117751987e-07,
      "loss": 0.4397,
      "step": 57137
    },
    {
      "epoch": 1.7552299327250944,
      "grad_norm": 0.42754054069519043,
      "learning_rate": 7.324803463253405e-07,
      "loss": 0.3806,
      "step": 57138
    },
    {
      "epoch": 1.7552606518600435,
      "grad_norm": 0.453250914812088,
      "learning_rate": 7.322988025204214e-07,
      "loss": 0.4264,
      "step": 57139
    },
    {
      "epoch": 1.7552913709949927,
      "grad_norm": 0.41948118805885315,
      "learning_rate": 7.321172803608667e-07,
      "loss": 0.4555,
      "step": 57140
    },
    {
      "epoch": 1.7553220901299418,
      "grad_norm": 0.4087364375591278,
      "learning_rate": 7.319357798470983e-07,
      "loss": 0.5377,
      "step": 57141
    },
    {
      "epoch": 1.7553528092648911,
      "grad_norm": 0.5100950598716736,
      "learning_rate": 7.317543009795414e-07,
      "loss": 0.4835,
      "step": 57142
    },
    {
      "epoch": 1.7553835283998402,
      "grad_norm": 0.42439061403274536,
      "learning_rate": 7.315728437586189e-07,
      "loss": 0.4037,
      "step": 57143
    },
    {
      "epoch": 1.7554142475347896,
      "grad_norm": 0.40634340047836304,
      "learning_rate": 7.313914081847573e-07,
      "loss": 0.4247,
      "step": 57144
    },
    {
      "epoch": 1.7554449666697387,
      "grad_norm": 0.4439619779586792,
      "learning_rate": 7.312099942583773e-07,
      "loss": 0.4543,
      "step": 57145
    },
    {
      "epoch": 1.7554756858046878,
      "grad_norm": 0.4425699710845947,
      "learning_rate": 7.310286019799028e-07,
      "loss": 0.3662,
      "step": 57146
    },
    {
      "epoch": 1.755506404939637,
      "grad_norm": 0.41585129499435425,
      "learning_rate": 7.308472313497595e-07,
      "loss": 0.3479,
      "step": 57147
    },
    {
      "epoch": 1.755537124074586,
      "grad_norm": 0.4593067169189453,
      "learning_rate": 7.306658823683699e-07,
      "loss": 0.4974,
      "step": 57148
    },
    {
      "epoch": 1.7555678432095352,
      "grad_norm": 0.4652518033981323,
      "learning_rate": 7.304845550361572e-07,
      "loss": 0.4341,
      "step": 57149
    },
    {
      "epoch": 1.7555985623444843,
      "grad_norm": 0.4702151417732239,
      "learning_rate": 7.303032493535456e-07,
      "loss": 0.4102,
      "step": 57150
    },
    {
      "epoch": 1.7556292814794334,
      "grad_norm": 0.47705984115600586,
      "learning_rate": 7.301219653209557e-07,
      "loss": 0.4953,
      "step": 57151
    },
    {
      "epoch": 1.7556600006143825,
      "grad_norm": 0.43424922227859497,
      "learning_rate": 7.29940702938815e-07,
      "loss": 0.5353,
      "step": 57152
    },
    {
      "epoch": 1.7556907197493319,
      "grad_norm": 0.43730464577674866,
      "learning_rate": 7.297594622075466e-07,
      "loss": 0.5105,
      "step": 57153
    },
    {
      "epoch": 1.755721438884281,
      "grad_norm": 0.42255714535713196,
      "learning_rate": 7.295782431275711e-07,
      "loss": 0.4766,
      "step": 57154
    },
    {
      "epoch": 1.7557521580192301,
      "grad_norm": 0.47859475016593933,
      "learning_rate": 7.293970456993127e-07,
      "loss": 0.472,
      "step": 57155
    },
    {
      "epoch": 1.7557828771541795,
      "grad_norm": 0.42020225524902344,
      "learning_rate": 7.292158699231955e-07,
      "loss": 0.4394,
      "step": 57156
    },
    {
      "epoch": 1.7558135962891286,
      "grad_norm": 0.5185717344284058,
      "learning_rate": 7.290347157996425e-07,
      "loss": 0.4668,
      "step": 57157
    },
    {
      "epoch": 1.7558443154240777,
      "grad_norm": 0.47075316309928894,
      "learning_rate": 7.288535833290755e-07,
      "loss": 0.4629,
      "step": 57158
    },
    {
      "epoch": 1.7558750345590268,
      "grad_norm": 0.44481366872787476,
      "learning_rate": 7.28672472511921e-07,
      "loss": 0.4942,
      "step": 57159
    },
    {
      "epoch": 1.755905753693976,
      "grad_norm": 0.4620104432106018,
      "learning_rate": 7.284913833485951e-07,
      "loss": 0.4647,
      "step": 57160
    },
    {
      "epoch": 1.755936472828925,
      "grad_norm": 0.44199156761169434,
      "learning_rate": 7.283103158395277e-07,
      "loss": 0.5396,
      "step": 57161
    },
    {
      "epoch": 1.7559671919638742,
      "grad_norm": 0.5095746517181396,
      "learning_rate": 7.281292699851383e-07,
      "loss": 0.4692,
      "step": 57162
    },
    {
      "epoch": 1.7559979110988233,
      "grad_norm": 0.459494948387146,
      "learning_rate": 7.279482457858522e-07,
      "loss": 0.4346,
      "step": 57163
    },
    {
      "epoch": 1.7560286302337726,
      "grad_norm": 0.46903470158576965,
      "learning_rate": 7.27767243242089e-07,
      "loss": 0.4226,
      "step": 57164
    },
    {
      "epoch": 1.7560593493687218,
      "grad_norm": 0.4671626687049866,
      "learning_rate": 7.275862623542729e-07,
      "loss": 0.4457,
      "step": 57165
    },
    {
      "epoch": 1.7560900685036709,
      "grad_norm": 0.5134368538856506,
      "learning_rate": 7.274053031228267e-07,
      "loss": 0.4812,
      "step": 57166
    },
    {
      "epoch": 1.7561207876386202,
      "grad_norm": 0.48075759410858154,
      "learning_rate": 7.272243655481748e-07,
      "loss": 0.4573,
      "step": 57167
    },
    {
      "epoch": 1.7561515067735693,
      "grad_norm": 0.5075822472572327,
      "learning_rate": 7.270434496307355e-07,
      "loss": 0.4594,
      "step": 57168
    },
    {
      "epoch": 1.7561822259085185,
      "grad_norm": 0.5596300363540649,
      "learning_rate": 7.268625553709352e-07,
      "loss": 0.3986,
      "step": 57169
    },
    {
      "epoch": 1.7562129450434676,
      "grad_norm": 0.42890995740890503,
      "learning_rate": 7.266816827691936e-07,
      "loss": 0.4936,
      "step": 57170
    },
    {
      "epoch": 1.7562436641784167,
      "grad_norm": 0.4503653645515442,
      "learning_rate": 7.265008318259359e-07,
      "loss": 0.4462,
      "step": 57171
    },
    {
      "epoch": 1.7562743833133658,
      "grad_norm": 0.4833323359489441,
      "learning_rate": 7.263200025415839e-07,
      "loss": 0.4372,
      "step": 57172
    },
    {
      "epoch": 1.756305102448315,
      "grad_norm": 0.40271738171577454,
      "learning_rate": 7.261391949165575e-07,
      "loss": 0.4947,
      "step": 57173
    },
    {
      "epoch": 1.756335821583264,
      "grad_norm": 0.48342329263687134,
      "learning_rate": 7.259584089512817e-07,
      "loss": 0.5347,
      "step": 57174
    },
    {
      "epoch": 1.7563665407182134,
      "grad_norm": 0.4667811691761017,
      "learning_rate": 7.257776446461761e-07,
      "loss": 0.5428,
      "step": 57175
    },
    {
      "epoch": 1.7563972598531625,
      "grad_norm": 0.4566102921962738,
      "learning_rate": 7.255969020016674e-07,
      "loss": 0.4792,
      "step": 57176
    },
    {
      "epoch": 1.7564279789881116,
      "grad_norm": 0.41288790106773376,
      "learning_rate": 7.254161810181726e-07,
      "loss": 0.4802,
      "step": 57177
    },
    {
      "epoch": 1.756458698123061,
      "grad_norm": 0.46061286330223083,
      "learning_rate": 7.252354816961171e-07,
      "loss": 0.4461,
      "step": 57178
    },
    {
      "epoch": 1.75648941725801,
      "grad_norm": 0.4387555420398712,
      "learning_rate": 7.250548040359207e-07,
      "loss": 0.4384,
      "step": 57179
    },
    {
      "epoch": 1.7565201363929592,
      "grad_norm": 0.6950668692588806,
      "learning_rate": 7.248741480380083e-07,
      "loss": 0.4207,
      "step": 57180
    },
    {
      "epoch": 1.7565508555279084,
      "grad_norm": 0.438742995262146,
      "learning_rate": 7.246935137027988e-07,
      "loss": 0.547,
      "step": 57181
    },
    {
      "epoch": 1.7565815746628575,
      "grad_norm": 0.48462623357772827,
      "learning_rate": 7.24512901030715e-07,
      "loss": 0.4398,
      "step": 57182
    },
    {
      "epoch": 1.7566122937978066,
      "grad_norm": 0.41845768690109253,
      "learning_rate": 7.2433231002218e-07,
      "loss": 0.5144,
      "step": 57183
    },
    {
      "epoch": 1.7566430129327557,
      "grad_norm": 0.4163662791252136,
      "learning_rate": 7.241517406776155e-07,
      "loss": 0.4308,
      "step": 57184
    },
    {
      "epoch": 1.7566737320677048,
      "grad_norm": 0.4406232535839081,
      "learning_rate": 7.239711929974413e-07,
      "loss": 0.4392,
      "step": 57185
    },
    {
      "epoch": 1.7567044512026542,
      "grad_norm": 0.44640788435935974,
      "learning_rate": 7.237906669820815e-07,
      "loss": 0.5644,
      "step": 57186
    },
    {
      "epoch": 1.7567351703376033,
      "grad_norm": 0.44597089290618896,
      "learning_rate": 7.236101626319536e-07,
      "loss": 0.5039,
      "step": 57187
    },
    {
      "epoch": 1.7567658894725524,
      "grad_norm": 0.4347143769264221,
      "learning_rate": 7.234296799474827e-07,
      "loss": 0.4294,
      "step": 57188
    },
    {
      "epoch": 1.7567966086075018,
      "grad_norm": 0.48157432675361633,
      "learning_rate": 7.232492189290929e-07,
      "loss": 0.5088,
      "step": 57189
    },
    {
      "epoch": 1.7568273277424509,
      "grad_norm": 0.4358680546283722,
      "learning_rate": 7.230687795771995e-07,
      "loss": 0.5176,
      "step": 57190
    },
    {
      "epoch": 1.7568580468774,
      "grad_norm": 0.4447413980960846,
      "learning_rate": 7.228883618922288e-07,
      "loss": 0.4812,
      "step": 57191
    },
    {
      "epoch": 1.7568887660123491,
      "grad_norm": 0.4404701590538025,
      "learning_rate": 7.227079658745973e-07,
      "loss": 0.4641,
      "step": 57192
    },
    {
      "epoch": 1.7569194851472982,
      "grad_norm": 0.42713725566864014,
      "learning_rate": 7.22527591524732e-07,
      "loss": 0.5228,
      "step": 57193
    },
    {
      "epoch": 1.7569502042822474,
      "grad_norm": 0.44066935777664185,
      "learning_rate": 7.223472388430497e-07,
      "loss": 0.5019,
      "step": 57194
    },
    {
      "epoch": 1.7569809234171965,
      "grad_norm": 0.3978559970855713,
      "learning_rate": 7.221669078299754e-07,
      "loss": 0.4172,
      "step": 57195
    },
    {
      "epoch": 1.7570116425521456,
      "grad_norm": 0.4044663906097412,
      "learning_rate": 7.219865984859253e-07,
      "loss": 0.4432,
      "step": 57196
    },
    {
      "epoch": 1.757042361687095,
      "grad_norm": 0.4879997968673706,
      "learning_rate": 7.21806310811326e-07,
      "loss": 0.421,
      "step": 57197
    },
    {
      "epoch": 1.757073080822044,
      "grad_norm": 0.6902371644973755,
      "learning_rate": 7.216260448065948e-07,
      "loss": 0.3741,
      "step": 57198
    },
    {
      "epoch": 1.7571037999569932,
      "grad_norm": 0.4504527449607849,
      "learning_rate": 7.214458004721559e-07,
      "loss": 0.439,
      "step": 57199
    },
    {
      "epoch": 1.7571345190919425,
      "grad_norm": 0.4428023099899292,
      "learning_rate": 7.212655778084254e-07,
      "loss": 0.4203,
      "step": 57200
    },
    {
      "epoch": 1.7571652382268916,
      "grad_norm": 0.41158226132392883,
      "learning_rate": 7.210853768158287e-07,
      "loss": 0.4876,
      "step": 57201
    },
    {
      "epoch": 1.7571959573618408,
      "grad_norm": 0.4415433704853058,
      "learning_rate": 7.209051974947845e-07,
      "loss": 0.4253,
      "step": 57202
    },
    {
      "epoch": 1.7572266764967899,
      "grad_norm": 0.4286959171295166,
      "learning_rate": 7.207250398457155e-07,
      "loss": 0.3561,
      "step": 57203
    },
    {
      "epoch": 1.757257395631739,
      "grad_norm": 0.4393738806247711,
      "learning_rate": 7.205449038690404e-07,
      "loss": 0.5437,
      "step": 57204
    },
    {
      "epoch": 1.7572881147666881,
      "grad_norm": 0.4656587541103363,
      "learning_rate": 7.2036478956518e-07,
      "loss": 0.4358,
      "step": 57205
    },
    {
      "epoch": 1.7573188339016372,
      "grad_norm": 0.40991291403770447,
      "learning_rate": 7.201846969345561e-07,
      "loss": 0.4795,
      "step": 57206
    },
    {
      "epoch": 1.7573495530365864,
      "grad_norm": 0.4270095229148865,
      "learning_rate": 7.200046259775895e-07,
      "loss": 0.5207,
      "step": 57207
    },
    {
      "epoch": 1.7573802721715357,
      "grad_norm": 0.4411167502403259,
      "learning_rate": 7.198245766947009e-07,
      "loss": 0.4647,
      "step": 57208
    },
    {
      "epoch": 1.7574109913064848,
      "grad_norm": 0.40940049290657043,
      "learning_rate": 7.19644549086309e-07,
      "loss": 0.4825,
      "step": 57209
    },
    {
      "epoch": 1.757441710441434,
      "grad_norm": 0.4627027213573456,
      "learning_rate": 7.194645431528347e-07,
      "loss": 0.5067,
      "step": 57210
    },
    {
      "epoch": 1.7574724295763833,
      "grad_norm": 0.4341529905796051,
      "learning_rate": 7.192845588946996e-07,
      "loss": 0.4279,
      "step": 57211
    },
    {
      "epoch": 1.7575031487113324,
      "grad_norm": 0.4595284163951874,
      "learning_rate": 7.191045963123256e-07,
      "loss": 0.4867,
      "step": 57212
    },
    {
      "epoch": 1.7575338678462815,
      "grad_norm": 0.614555835723877,
      "learning_rate": 7.189246554061291e-07,
      "loss": 0.489,
      "step": 57213
    },
    {
      "epoch": 1.7575645869812306,
      "grad_norm": 0.43027058243751526,
      "learning_rate": 7.187447361765321e-07,
      "loss": 0.3817,
      "step": 57214
    },
    {
      "epoch": 1.7575953061161798,
      "grad_norm": 0.4229946434497833,
      "learning_rate": 7.185648386239552e-07,
      "loss": 0.4047,
      "step": 57215
    },
    {
      "epoch": 1.7576260252511289,
      "grad_norm": 0.4191586971282959,
      "learning_rate": 7.183849627488193e-07,
      "loss": 0.4631,
      "step": 57216
    },
    {
      "epoch": 1.757656744386078,
      "grad_norm": 0.45165443420410156,
      "learning_rate": 7.182051085515429e-07,
      "loss": 0.4636,
      "step": 57217
    },
    {
      "epoch": 1.7576874635210271,
      "grad_norm": 0.4265872538089752,
      "learning_rate": 7.180252760325457e-07,
      "loss": 0.5432,
      "step": 57218
    },
    {
      "epoch": 1.7577181826559765,
      "grad_norm": 0.4314741790294647,
      "learning_rate": 7.178454651922495e-07,
      "loss": 0.441,
      "step": 57219
    },
    {
      "epoch": 1.7577489017909256,
      "grad_norm": 0.4416637718677521,
      "learning_rate": 7.176656760310751e-07,
      "loss": 0.5402,
      "step": 57220
    },
    {
      "epoch": 1.7577796209258747,
      "grad_norm": 0.45283862948417664,
      "learning_rate": 7.17485908549439e-07,
      "loss": 0.4211,
      "step": 57221
    },
    {
      "epoch": 1.757810340060824,
      "grad_norm": 0.4766804575920105,
      "learning_rate": 7.17306162747764e-07,
      "loss": 0.4511,
      "step": 57222
    },
    {
      "epoch": 1.7578410591957732,
      "grad_norm": 0.4590024948120117,
      "learning_rate": 7.171264386264653e-07,
      "loss": 0.4727,
      "step": 57223
    },
    {
      "epoch": 1.7578717783307223,
      "grad_norm": 0.4073529839515686,
      "learning_rate": 7.169467361859683e-07,
      "loss": 0.4955,
      "step": 57224
    },
    {
      "epoch": 1.7579024974656714,
      "grad_norm": 0.402340292930603,
      "learning_rate": 7.167670554266925e-07,
      "loss": 0.4564,
      "step": 57225
    },
    {
      "epoch": 1.7579332166006205,
      "grad_norm": 0.42133304476737976,
      "learning_rate": 7.165873963490532e-07,
      "loss": 0.4433,
      "step": 57226
    },
    {
      "epoch": 1.7579639357355696,
      "grad_norm": 0.43568047881126404,
      "learning_rate": 7.164077589534746e-07,
      "loss": 0.4573,
      "step": 57227
    },
    {
      "epoch": 1.7579946548705188,
      "grad_norm": 0.4128672778606415,
      "learning_rate": 7.162281432403706e-07,
      "loss": 0.4465,
      "step": 57228
    },
    {
      "epoch": 1.7580253740054679,
      "grad_norm": 0.4173460304737091,
      "learning_rate": 7.160485492101677e-07,
      "loss": 0.4565,
      "step": 57229
    },
    {
      "epoch": 1.7580560931404172,
      "grad_norm": 0.43014830350875854,
      "learning_rate": 7.158689768632798e-07,
      "loss": 0.3681,
      "step": 57230
    },
    {
      "epoch": 1.7580868122753663,
      "grad_norm": 0.4703201949596405,
      "learning_rate": 7.156894262001291e-07,
      "loss": 0.5357,
      "step": 57231
    },
    {
      "epoch": 1.7581175314103155,
      "grad_norm": 0.4276062548160553,
      "learning_rate": 7.155098972211338e-07,
      "loss": 0.3902,
      "step": 57232
    },
    {
      "epoch": 1.7581482505452648,
      "grad_norm": 0.4165225327014923,
      "learning_rate": 7.153303899267128e-07,
      "loss": 0.4304,
      "step": 57233
    },
    {
      "epoch": 1.758178969680214,
      "grad_norm": 0.44700661301612854,
      "learning_rate": 7.151509043172866e-07,
      "loss": 0.4682,
      "step": 57234
    },
    {
      "epoch": 1.758209688815163,
      "grad_norm": 0.4495905935764313,
      "learning_rate": 7.149714403932751e-07,
      "loss": 0.4257,
      "step": 57235
    },
    {
      "epoch": 1.7582404079501122,
      "grad_norm": 0.43612194061279297,
      "learning_rate": 7.147919981550954e-07,
      "loss": 0.4784,
      "step": 57236
    },
    {
      "epoch": 1.7582711270850613,
      "grad_norm": 0.44680821895599365,
      "learning_rate": 7.146125776031664e-07,
      "loss": 0.4634,
      "step": 57237
    },
    {
      "epoch": 1.7583018462200104,
      "grad_norm": 0.4234298765659332,
      "learning_rate": 7.144331787379088e-07,
      "loss": 0.4281,
      "step": 57238
    },
    {
      "epoch": 1.7583325653549595,
      "grad_norm": 0.4568023383617401,
      "learning_rate": 7.142538015597433e-07,
      "loss": 0.5102,
      "step": 57239
    },
    {
      "epoch": 1.7583632844899086,
      "grad_norm": 0.43576952815055847,
      "learning_rate": 7.14074446069084e-07,
      "loss": 0.4783,
      "step": 57240
    },
    {
      "epoch": 1.7583940036248578,
      "grad_norm": 0.4430827498435974,
      "learning_rate": 7.138951122663529e-07,
      "loss": 0.4439,
      "step": 57241
    },
    {
      "epoch": 1.758424722759807,
      "grad_norm": 0.4385373294353485,
      "learning_rate": 7.137158001519673e-07,
      "loss": 0.4329,
      "step": 57242
    },
    {
      "epoch": 1.7584554418947562,
      "grad_norm": 0.45941734313964844,
      "learning_rate": 7.13536509726348e-07,
      "loss": 0.5333,
      "step": 57243
    },
    {
      "epoch": 1.7584861610297056,
      "grad_norm": 0.46805039048194885,
      "learning_rate": 7.133572409899137e-07,
      "loss": 0.4027,
      "step": 57244
    },
    {
      "epoch": 1.7585168801646547,
      "grad_norm": 0.44395312666893005,
      "learning_rate": 7.131779939430816e-07,
      "loss": 0.4811,
      "step": 57245
    },
    {
      "epoch": 1.7585475992996038,
      "grad_norm": 0.43296054005622864,
      "learning_rate": 7.129987685862694e-07,
      "loss": 0.5125,
      "step": 57246
    },
    {
      "epoch": 1.758578318434553,
      "grad_norm": 0.4669229984283447,
      "learning_rate": 7.128195649198988e-07,
      "loss": 0.4501,
      "step": 57247
    },
    {
      "epoch": 1.758609037569502,
      "grad_norm": 0.4359217584133148,
      "learning_rate": 7.126403829443873e-07,
      "loss": 0.3784,
      "step": 57248
    },
    {
      "epoch": 1.7586397567044512,
      "grad_norm": 0.436246782541275,
      "learning_rate": 7.124612226601512e-07,
      "loss": 0.4468,
      "step": 57249
    },
    {
      "epoch": 1.7586704758394003,
      "grad_norm": 0.45378991961479187,
      "learning_rate": 7.122820840676103e-07,
      "loss": 0.466,
      "step": 57250
    },
    {
      "epoch": 1.7587011949743494,
      "grad_norm": 0.4288315773010254,
      "learning_rate": 7.121029671671842e-07,
      "loss": 0.4905,
      "step": 57251
    },
    {
      "epoch": 1.7587319141092985,
      "grad_norm": 0.4157915711402893,
      "learning_rate": 7.119238719592914e-07,
      "loss": 0.4822,
      "step": 57252
    },
    {
      "epoch": 1.7587626332442479,
      "grad_norm": 0.4485253393650055,
      "learning_rate": 7.117447984443471e-07,
      "loss": 0.4134,
      "step": 57253
    },
    {
      "epoch": 1.758793352379197,
      "grad_norm": 0.4231874644756317,
      "learning_rate": 7.115657466227732e-07,
      "loss": 0.4019,
      "step": 57254
    },
    {
      "epoch": 1.7588240715141463,
      "grad_norm": 0.45111018419265747,
      "learning_rate": 7.113867164949828e-07,
      "loss": 0.5446,
      "step": 57255
    },
    {
      "epoch": 1.7588547906490954,
      "grad_norm": 0.49887195229530334,
      "learning_rate": 7.112077080614011e-07,
      "loss": 0.5172,
      "step": 57256
    },
    {
      "epoch": 1.7588855097840446,
      "grad_norm": 0.42105406522750854,
      "learning_rate": 7.110287213224409e-07,
      "loss": 0.4218,
      "step": 57257
    },
    {
      "epoch": 1.7589162289189937,
      "grad_norm": 0.4171132445335388,
      "learning_rate": 7.108497562785233e-07,
      "loss": 0.4029,
      "step": 57258
    },
    {
      "epoch": 1.7589469480539428,
      "grad_norm": 0.4469172954559326,
      "learning_rate": 7.106708129300621e-07,
      "loss": 0.4645,
      "step": 57259
    },
    {
      "epoch": 1.758977667188892,
      "grad_norm": 0.4425373673439026,
      "learning_rate": 7.104918912774795e-07,
      "loss": 0.5309,
      "step": 57260
    },
    {
      "epoch": 1.759008386323841,
      "grad_norm": 0.43169310688972473,
      "learning_rate": 7.103129913211926e-07,
      "loss": 0.4759,
      "step": 57261
    },
    {
      "epoch": 1.7590391054587902,
      "grad_norm": 0.4432418644428253,
      "learning_rate": 7.101341130616179e-07,
      "loss": 0.3525,
      "step": 57262
    },
    {
      "epoch": 1.7590698245937393,
      "grad_norm": 0.4468604624271393,
      "learning_rate": 7.099552564991751e-07,
      "loss": 0.4827,
      "step": 57263
    },
    {
      "epoch": 1.7591005437286886,
      "grad_norm": 0.40651842951774597,
      "learning_rate": 7.097764216342773e-07,
      "loss": 0.4248,
      "step": 57264
    },
    {
      "epoch": 1.7591312628636377,
      "grad_norm": 0.44910475611686707,
      "learning_rate": 7.095976084673484e-07,
      "loss": 0.5205,
      "step": 57265
    },
    {
      "epoch": 1.7591619819985869,
      "grad_norm": 0.406917005777359,
      "learning_rate": 7.094188169988015e-07,
      "loss": 0.5013,
      "step": 57266
    },
    {
      "epoch": 1.7591927011335362,
      "grad_norm": 0.5075586438179016,
      "learning_rate": 7.092400472290572e-07,
      "loss": 0.4794,
      "step": 57267
    },
    {
      "epoch": 1.7592234202684853,
      "grad_norm": 0.4057464599609375,
      "learning_rate": 7.09061299158531e-07,
      "loss": 0.3742,
      "step": 57268
    },
    {
      "epoch": 1.7592541394034344,
      "grad_norm": 0.4464262127876282,
      "learning_rate": 7.088825727876403e-07,
      "loss": 0.4274,
      "step": 57269
    },
    {
      "epoch": 1.7592848585383836,
      "grad_norm": 0.47172677516937256,
      "learning_rate": 7.087038681168034e-07,
      "loss": 0.5039,
      "step": 57270
    },
    {
      "epoch": 1.7593155776733327,
      "grad_norm": 0.4414404034614563,
      "learning_rate": 7.085251851464392e-07,
      "loss": 0.5332,
      "step": 57271
    },
    {
      "epoch": 1.7593462968082818,
      "grad_norm": 0.50724858045578,
      "learning_rate": 7.083465238769615e-07,
      "loss": 0.4505,
      "step": 57272
    },
    {
      "epoch": 1.759377015943231,
      "grad_norm": 0.45006969571113586,
      "learning_rate": 7.081678843087902e-07,
      "loss": 0.3463,
      "step": 57273
    },
    {
      "epoch": 1.75940773507818,
      "grad_norm": 0.4079935848712921,
      "learning_rate": 7.079892664423405e-07,
      "loss": 0.414,
      "step": 57274
    },
    {
      "epoch": 1.7594384542131294,
      "grad_norm": 0.4128216803073883,
      "learning_rate": 7.078106702780329e-07,
      "loss": 0.5214,
      "step": 57275
    },
    {
      "epoch": 1.7594691733480785,
      "grad_norm": 0.4617219865322113,
      "learning_rate": 7.076320958162819e-07,
      "loss": 0.4177,
      "step": 57276
    },
    {
      "epoch": 1.7594998924830276,
      "grad_norm": 0.3939324617385864,
      "learning_rate": 7.074535430575036e-07,
      "loss": 0.3923,
      "step": 57277
    },
    {
      "epoch": 1.759530611617977,
      "grad_norm": 0.4597439765930176,
      "learning_rate": 7.072750120021177e-07,
      "loss": 0.4878,
      "step": 57278
    },
    {
      "epoch": 1.759561330752926,
      "grad_norm": 0.4445388615131378,
      "learning_rate": 7.070965026505394e-07,
      "loss": 0.5503,
      "step": 57279
    },
    {
      "epoch": 1.7595920498878752,
      "grad_norm": 0.400420218706131,
      "learning_rate": 7.069180150031874e-07,
      "loss": 0.4576,
      "step": 57280
    },
    {
      "epoch": 1.7596227690228243,
      "grad_norm": 0.4582553803920746,
      "learning_rate": 7.067395490604767e-07,
      "loss": 0.5235,
      "step": 57281
    },
    {
      "epoch": 1.7596534881577734,
      "grad_norm": 0.4754069745540619,
      "learning_rate": 7.065611048228238e-07,
      "loss": 0.5344,
      "step": 57282
    },
    {
      "epoch": 1.7596842072927226,
      "grad_norm": 0.47385042905807495,
      "learning_rate": 7.063826822906472e-07,
      "loss": 0.446,
      "step": 57283
    },
    {
      "epoch": 1.7597149264276717,
      "grad_norm": 0.49731045961380005,
      "learning_rate": 7.062042814643644e-07,
      "loss": 0.4534,
      "step": 57284
    },
    {
      "epoch": 1.7597456455626208,
      "grad_norm": 0.4106593728065491,
      "learning_rate": 7.060259023443893e-07,
      "loss": 0.4559,
      "step": 57285
    },
    {
      "epoch": 1.7597763646975702,
      "grad_norm": 0.42716631293296814,
      "learning_rate": 7.058475449311386e-07,
      "loss": 0.5135,
      "step": 57286
    },
    {
      "epoch": 1.7598070838325193,
      "grad_norm": 0.4372909367084503,
      "learning_rate": 7.056692092250316e-07,
      "loss": 0.4332,
      "step": 57287
    },
    {
      "epoch": 1.7598378029674684,
      "grad_norm": 0.4178035259246826,
      "learning_rate": 7.054908952264839e-07,
      "loss": 0.4385,
      "step": 57288
    },
    {
      "epoch": 1.7598685221024177,
      "grad_norm": 0.4229590594768524,
      "learning_rate": 7.053126029359103e-07,
      "loss": 0.489,
      "step": 57289
    },
    {
      "epoch": 1.7598992412373669,
      "grad_norm": 0.4877856969833374,
      "learning_rate": 7.051343323537296e-07,
      "loss": 0.4146,
      "step": 57290
    },
    {
      "epoch": 1.759929960372316,
      "grad_norm": 0.42903804779052734,
      "learning_rate": 7.049560834803526e-07,
      "loss": 0.5333,
      "step": 57291
    },
    {
      "epoch": 1.759960679507265,
      "grad_norm": 0.594538152217865,
      "learning_rate": 7.047778563162044e-07,
      "loss": 0.4659,
      "step": 57292
    },
    {
      "epoch": 1.7599913986422142,
      "grad_norm": 0.45095980167388916,
      "learning_rate": 7.045996508616948e-07,
      "loss": 0.428,
      "step": 57293
    },
    {
      "epoch": 1.7600221177771633,
      "grad_norm": 0.4744877219200134,
      "learning_rate": 7.044214671172434e-07,
      "loss": 0.4565,
      "step": 57294
    },
    {
      "epoch": 1.7600528369121125,
      "grad_norm": 0.42956867814064026,
      "learning_rate": 7.042433050832631e-07,
      "loss": 0.4111,
      "step": 57295
    },
    {
      "epoch": 1.7600835560470616,
      "grad_norm": 0.4311320185661316,
      "learning_rate": 7.040651647601715e-07,
      "loss": 0.4542,
      "step": 57296
    },
    {
      "epoch": 1.760114275182011,
      "grad_norm": 0.4306345582008362,
      "learning_rate": 7.03887046148386e-07,
      "loss": 0.4664,
      "step": 57297
    },
    {
      "epoch": 1.76014499431696,
      "grad_norm": 0.4492911398410797,
      "learning_rate": 7.037089492483207e-07,
      "loss": 0.4365,
      "step": 57298
    },
    {
      "epoch": 1.7601757134519092,
      "grad_norm": 0.4461117088794708,
      "learning_rate": 7.035308740603941e-07,
      "loss": 0.5078,
      "step": 57299
    },
    {
      "epoch": 1.7602064325868585,
      "grad_norm": 0.3984955847263336,
      "learning_rate": 7.03352820585017e-07,
      "loss": 0.4569,
      "step": 57300
    },
    {
      "epoch": 1.7602371517218076,
      "grad_norm": 0.44722428917884827,
      "learning_rate": 7.031747888226126e-07,
      "loss": 0.4435,
      "step": 57301
    },
    {
      "epoch": 1.7602678708567567,
      "grad_norm": 0.4082014858722687,
      "learning_rate": 7.029967787735903e-07,
      "loss": 0.4379,
      "step": 57302
    },
    {
      "epoch": 1.7602985899917059,
      "grad_norm": 0.4377612769603729,
      "learning_rate": 7.028187904383699e-07,
      "loss": 0.5087,
      "step": 57303
    },
    {
      "epoch": 1.760329309126655,
      "grad_norm": 0.47821006178855896,
      "learning_rate": 7.026408238173644e-07,
      "loss": 0.4714,
      "step": 57304
    },
    {
      "epoch": 1.760360028261604,
      "grad_norm": 0.5205739736557007,
      "learning_rate": 7.024628789109911e-07,
      "loss": 0.5345,
      "step": 57305
    },
    {
      "epoch": 1.7603907473965532,
      "grad_norm": 0.43863946199417114,
      "learning_rate": 7.022849557196643e-07,
      "loss": 0.4153,
      "step": 57306
    },
    {
      "epoch": 1.7604214665315023,
      "grad_norm": 0.42429932951927185,
      "learning_rate": 7.021070542438024e-07,
      "loss": 0.4789,
      "step": 57307
    },
    {
      "epoch": 1.7604521856664517,
      "grad_norm": 0.4457843601703644,
      "learning_rate": 7.019291744838164e-07,
      "loss": 0.4691,
      "step": 57308
    },
    {
      "epoch": 1.7604829048014008,
      "grad_norm": 0.4415920078754425,
      "learning_rate": 7.017513164401246e-07,
      "loss": 0.4849,
      "step": 57309
    },
    {
      "epoch": 1.76051362393635,
      "grad_norm": 0.43213483691215515,
      "learning_rate": 7.015734801131425e-07,
      "loss": 0.4942,
      "step": 57310
    },
    {
      "epoch": 1.7605443430712993,
      "grad_norm": 0.4687800109386444,
      "learning_rate": 7.01395665503286e-07,
      "loss": 0.4934,
      "step": 57311
    },
    {
      "epoch": 1.7605750622062484,
      "grad_norm": 0.4280269145965576,
      "learning_rate": 7.012178726109675e-07,
      "loss": 0.4679,
      "step": 57312
    },
    {
      "epoch": 1.7606057813411975,
      "grad_norm": 0.38818904757499695,
      "learning_rate": 7.010401014366053e-07,
      "loss": 0.4834,
      "step": 57313
    },
    {
      "epoch": 1.7606365004761466,
      "grad_norm": 0.4202304780483246,
      "learning_rate": 7.008623519806123e-07,
      "loss": 0.4286,
      "step": 57314
    },
    {
      "epoch": 1.7606672196110957,
      "grad_norm": 0.42793577909469604,
      "learning_rate": 7.006846242434051e-07,
      "loss": 0.52,
      "step": 57315
    },
    {
      "epoch": 1.7606979387460449,
      "grad_norm": 0.4169562757015228,
      "learning_rate": 7.005069182253998e-07,
      "loss": 0.4161,
      "step": 57316
    },
    {
      "epoch": 1.760728657880994,
      "grad_norm": 0.46829667687416077,
      "learning_rate": 7.003292339270085e-07,
      "loss": 0.518,
      "step": 57317
    },
    {
      "epoch": 1.760759377015943,
      "grad_norm": 0.4101410210132599,
      "learning_rate": 7.001515713486473e-07,
      "loss": 0.469,
      "step": 57318
    },
    {
      "epoch": 1.7607900961508924,
      "grad_norm": 0.40664851665496826,
      "learning_rate": 6.999739304907316e-07,
      "loss": 0.4533,
      "step": 57319
    },
    {
      "epoch": 1.7608208152858416,
      "grad_norm": 0.47159188985824585,
      "learning_rate": 6.997963113536787e-07,
      "loss": 0.4557,
      "step": 57320
    },
    {
      "epoch": 1.7608515344207907,
      "grad_norm": 0.4281923770904541,
      "learning_rate": 6.996187139378996e-07,
      "loss": 0.4339,
      "step": 57321
    },
    {
      "epoch": 1.76088225355574,
      "grad_norm": 0.4107954502105713,
      "learning_rate": 6.994411382438093e-07,
      "loss": 0.4758,
      "step": 57322
    },
    {
      "epoch": 1.7609129726906891,
      "grad_norm": 0.40163135528564453,
      "learning_rate": 6.992635842718254e-07,
      "loss": 0.4917,
      "step": 57323
    },
    {
      "epoch": 1.7609436918256383,
      "grad_norm": 0.42907780408859253,
      "learning_rate": 6.990860520223608e-07,
      "loss": 0.4541,
      "step": 57324
    },
    {
      "epoch": 1.7609744109605874,
      "grad_norm": 0.4229706823825836,
      "learning_rate": 6.989085414958296e-07,
      "loss": 0.5829,
      "step": 57325
    },
    {
      "epoch": 1.7610051300955365,
      "grad_norm": 0.44219574332237244,
      "learning_rate": 6.987310526926494e-07,
      "loss": 0.5035,
      "step": 57326
    },
    {
      "epoch": 1.7610358492304856,
      "grad_norm": 0.4182436466217041,
      "learning_rate": 6.985535856132276e-07,
      "loss": 0.4441,
      "step": 57327
    },
    {
      "epoch": 1.7610665683654347,
      "grad_norm": 0.42908206582069397,
      "learning_rate": 6.98376140257988e-07,
      "loss": 0.4366,
      "step": 57328
    },
    {
      "epoch": 1.7610972875003839,
      "grad_norm": 0.577799916267395,
      "learning_rate": 6.981987166273385e-07,
      "loss": 0.4411,
      "step": 57329
    },
    {
      "epoch": 1.7611280066353332,
      "grad_norm": 0.5256707072257996,
      "learning_rate": 6.980213147216974e-07,
      "loss": 0.5369,
      "step": 57330
    },
    {
      "epoch": 1.7611587257702823,
      "grad_norm": 0.4596712589263916,
      "learning_rate": 6.978439345414744e-07,
      "loss": 0.4419,
      "step": 57331
    },
    {
      "epoch": 1.7611894449052314,
      "grad_norm": 0.5078141093254089,
      "learning_rate": 6.976665760870882e-07,
      "loss": 0.4578,
      "step": 57332
    },
    {
      "epoch": 1.7612201640401808,
      "grad_norm": 0.434756875038147,
      "learning_rate": 6.974892393589506e-07,
      "loss": 0.4843,
      "step": 57333
    },
    {
      "epoch": 1.76125088317513,
      "grad_norm": 0.4416825473308563,
      "learning_rate": 6.973119243574766e-07,
      "loss": 0.502,
      "step": 57334
    },
    {
      "epoch": 1.761281602310079,
      "grad_norm": 1.5752381086349487,
      "learning_rate": 6.971346310830818e-07,
      "loss": 0.4605,
      "step": 57335
    },
    {
      "epoch": 1.7613123214450281,
      "grad_norm": 0.4548065960407257,
      "learning_rate": 6.969573595361767e-07,
      "loss": 0.5402,
      "step": 57336
    },
    {
      "epoch": 1.7613430405799773,
      "grad_norm": 0.445682168006897,
      "learning_rate": 6.967801097171778e-07,
      "loss": 0.4158,
      "step": 57337
    },
    {
      "epoch": 1.7613737597149264,
      "grad_norm": 0.45532363653182983,
      "learning_rate": 6.966028816264991e-07,
      "loss": 0.4395,
      "step": 57338
    },
    {
      "epoch": 1.7614044788498755,
      "grad_norm": 0.4204249680042267,
      "learning_rate": 6.964256752645548e-07,
      "loss": 0.4598,
      "step": 57339
    },
    {
      "epoch": 1.7614351979848246,
      "grad_norm": 0.4907222390174866,
      "learning_rate": 6.96248490631758e-07,
      "loss": 0.4221,
      "step": 57340
    },
    {
      "epoch": 1.761465917119774,
      "grad_norm": 0.43720608949661255,
      "learning_rate": 6.960713277285213e-07,
      "loss": 0.5048,
      "step": 57341
    },
    {
      "epoch": 1.761496636254723,
      "grad_norm": 0.4396412670612335,
      "learning_rate": 6.958941865552604e-07,
      "loss": 0.4883,
      "step": 57342
    },
    {
      "epoch": 1.7615273553896722,
      "grad_norm": 0.4814499616622925,
      "learning_rate": 6.957170671123903e-07,
      "loss": 0.4632,
      "step": 57343
    },
    {
      "epoch": 1.7615580745246215,
      "grad_norm": 0.429533451795578,
      "learning_rate": 6.955399694003207e-07,
      "loss": 0.4251,
      "step": 57344
    },
    {
      "epoch": 1.7615887936595707,
      "grad_norm": 0.48472118377685547,
      "learning_rate": 6.953628934194667e-07,
      "loss": 0.4463,
      "step": 57345
    },
    {
      "epoch": 1.7616195127945198,
      "grad_norm": 0.40946272015571594,
      "learning_rate": 6.951858391702438e-07,
      "loss": 0.4699,
      "step": 57346
    },
    {
      "epoch": 1.761650231929469,
      "grad_norm": 0.4598885178565979,
      "learning_rate": 6.950088066530647e-07,
      "loss": 0.4612,
      "step": 57347
    },
    {
      "epoch": 1.761680951064418,
      "grad_norm": 0.4189057946205139,
      "learning_rate": 6.948317958683415e-07,
      "loss": 0.5401,
      "step": 57348
    },
    {
      "epoch": 1.7617116701993671,
      "grad_norm": 0.4367009997367859,
      "learning_rate": 6.946548068164883e-07,
      "loss": 0.532,
      "step": 57349
    },
    {
      "epoch": 1.7617423893343163,
      "grad_norm": 0.413191556930542,
      "learning_rate": 6.944778394979179e-07,
      "loss": 0.3426,
      "step": 57350
    },
    {
      "epoch": 1.7617731084692654,
      "grad_norm": 0.5143011212348938,
      "learning_rate": 6.943008939130457e-07,
      "loss": 0.6045,
      "step": 57351
    },
    {
      "epoch": 1.7618038276042145,
      "grad_norm": 0.5842881798744202,
      "learning_rate": 6.941239700622848e-07,
      "loss": 0.5134,
      "step": 57352
    },
    {
      "epoch": 1.7618345467391638,
      "grad_norm": 0.4361688792705536,
      "learning_rate": 6.939470679460447e-07,
      "loss": 0.4759,
      "step": 57353
    },
    {
      "epoch": 1.761865265874113,
      "grad_norm": 0.4167090952396393,
      "learning_rate": 6.937701875647429e-07,
      "loss": 0.4138,
      "step": 57354
    },
    {
      "epoch": 1.7618959850090623,
      "grad_norm": 0.420896977186203,
      "learning_rate": 6.935933289187891e-07,
      "loss": 0.4381,
      "step": 57355
    },
    {
      "epoch": 1.7619267041440114,
      "grad_norm": 0.4005722403526306,
      "learning_rate": 6.934164920086006e-07,
      "loss": 0.4104,
      "step": 57356
    },
    {
      "epoch": 1.7619574232789605,
      "grad_norm": 0.42263585329055786,
      "learning_rate": 6.932396768345861e-07,
      "loss": 0.463,
      "step": 57357
    },
    {
      "epoch": 1.7619881424139097,
      "grad_norm": 0.40908047556877136,
      "learning_rate": 6.93062883397162e-07,
      "loss": 0.4899,
      "step": 57358
    },
    {
      "epoch": 1.7620188615488588,
      "grad_norm": 0.4728687107563019,
      "learning_rate": 6.928861116967367e-07,
      "loss": 0.4209,
      "step": 57359
    },
    {
      "epoch": 1.762049580683808,
      "grad_norm": 0.4400763213634491,
      "learning_rate": 6.927093617337277e-07,
      "loss": 0.4844,
      "step": 57360
    },
    {
      "epoch": 1.762080299818757,
      "grad_norm": 0.436575710773468,
      "learning_rate": 6.925326335085458e-07,
      "loss": 0.4767,
      "step": 57361
    },
    {
      "epoch": 1.7621110189537061,
      "grad_norm": 0.44949668645858765,
      "learning_rate": 6.923559270216051e-07,
      "loss": 0.4618,
      "step": 57362
    },
    {
      "epoch": 1.7621417380886553,
      "grad_norm": 0.4442032277584076,
      "learning_rate": 6.921792422733142e-07,
      "loss": 0.4891,
      "step": 57363
    },
    {
      "epoch": 1.7621724572236046,
      "grad_norm": 0.39187514781951904,
      "learning_rate": 6.920025792640917e-07,
      "loss": 0.4573,
      "step": 57364
    },
    {
      "epoch": 1.7622031763585537,
      "grad_norm": 0.4818759262561798,
      "learning_rate": 6.918259379943448e-07,
      "loss": 0.4949,
      "step": 57365
    },
    {
      "epoch": 1.762233895493503,
      "grad_norm": 0.406170129776001,
      "learning_rate": 6.916493184644912e-07,
      "loss": 0.4102,
      "step": 57366
    },
    {
      "epoch": 1.7622646146284522,
      "grad_norm": 0.43106943368911743,
      "learning_rate": 6.914727206749383e-07,
      "loss": 0.4961,
      "step": 57367
    },
    {
      "epoch": 1.7622953337634013,
      "grad_norm": 0.46099287271499634,
      "learning_rate": 6.912961446261024e-07,
      "loss": 0.4615,
      "step": 57368
    },
    {
      "epoch": 1.7623260528983504,
      "grad_norm": 0.42763927578926086,
      "learning_rate": 6.911195903183932e-07,
      "loss": 0.4376,
      "step": 57369
    },
    {
      "epoch": 1.7623567720332995,
      "grad_norm": 0.44335272908210754,
      "learning_rate": 6.909430577522247e-07,
      "loss": 0.4544,
      "step": 57370
    },
    {
      "epoch": 1.7623874911682487,
      "grad_norm": 0.4266102612018585,
      "learning_rate": 6.9076654692801e-07,
      "loss": 0.4258,
      "step": 57371
    },
    {
      "epoch": 1.7624182103031978,
      "grad_norm": 0.4672830402851105,
      "learning_rate": 6.905900578461588e-07,
      "loss": 0.5045,
      "step": 57372
    },
    {
      "epoch": 1.762448929438147,
      "grad_norm": 0.3941924571990967,
      "learning_rate": 6.904135905070852e-07,
      "loss": 0.5012,
      "step": 57373
    },
    {
      "epoch": 1.762479648573096,
      "grad_norm": 0.42320454120635986,
      "learning_rate": 6.902371449112e-07,
      "loss": 0.4827,
      "step": 57374
    },
    {
      "epoch": 1.7625103677080454,
      "grad_norm": 0.4492405354976654,
      "learning_rate": 6.900607210589183e-07,
      "loss": 0.5377,
      "step": 57375
    },
    {
      "epoch": 1.7625410868429945,
      "grad_norm": 0.4065687954425812,
      "learning_rate": 6.898843189506488e-07,
      "loss": 0.3624,
      "step": 57376
    },
    {
      "epoch": 1.7625718059779436,
      "grad_norm": 0.4236293137073517,
      "learning_rate": 6.897079385868045e-07,
      "loss": 0.4618,
      "step": 57377
    },
    {
      "epoch": 1.762602525112893,
      "grad_norm": 0.4865792691707611,
      "learning_rate": 6.895315799677971e-07,
      "loss": 0.3638,
      "step": 57378
    },
    {
      "epoch": 1.762633244247842,
      "grad_norm": 0.5963989496231079,
      "learning_rate": 6.893552430940398e-07,
      "loss": 0.457,
      "step": 57379
    },
    {
      "epoch": 1.7626639633827912,
      "grad_norm": 0.5349592566490173,
      "learning_rate": 6.891789279659434e-07,
      "loss": 0.4218,
      "step": 57380
    },
    {
      "epoch": 1.7626946825177403,
      "grad_norm": 0.40288376808166504,
      "learning_rate": 6.890026345839185e-07,
      "loss": 0.4411,
      "step": 57381
    },
    {
      "epoch": 1.7627254016526894,
      "grad_norm": 0.40498948097229004,
      "learning_rate": 6.888263629483794e-07,
      "loss": 0.4702,
      "step": 57382
    },
    {
      "epoch": 1.7627561207876385,
      "grad_norm": 0.43065324425697327,
      "learning_rate": 6.886501130597378e-07,
      "loss": 0.4725,
      "step": 57383
    },
    {
      "epoch": 1.7627868399225877,
      "grad_norm": 0.39983075857162476,
      "learning_rate": 6.884738849184025e-07,
      "loss": 0.378,
      "step": 57384
    },
    {
      "epoch": 1.7628175590575368,
      "grad_norm": 0.4413694441318512,
      "learning_rate": 6.882976785247875e-07,
      "loss": 0.5617,
      "step": 57385
    },
    {
      "epoch": 1.7628482781924861,
      "grad_norm": 0.4450966417789459,
      "learning_rate": 6.881214938793024e-07,
      "loss": 0.4243,
      "step": 57386
    },
    {
      "epoch": 1.7628789973274352,
      "grad_norm": 0.47387877106666565,
      "learning_rate": 6.879453309823625e-07,
      "loss": 0.5076,
      "step": 57387
    },
    {
      "epoch": 1.7629097164623844,
      "grad_norm": 0.441778302192688,
      "learning_rate": 6.877691898343741e-07,
      "loss": 0.4807,
      "step": 57388
    },
    {
      "epoch": 1.7629404355973337,
      "grad_norm": 0.454067587852478,
      "learning_rate": 6.875930704357514e-07,
      "loss": 0.4812,
      "step": 57389
    },
    {
      "epoch": 1.7629711547322828,
      "grad_norm": 0.49161383509635925,
      "learning_rate": 6.874169727869051e-07,
      "loss": 0.5263,
      "step": 57390
    },
    {
      "epoch": 1.763001873867232,
      "grad_norm": 0.46395933628082275,
      "learning_rate": 6.872408968882483e-07,
      "loss": 0.4712,
      "step": 57391
    },
    {
      "epoch": 1.763032593002181,
      "grad_norm": 0.4919722080230713,
      "learning_rate": 6.870648427401904e-07,
      "loss": 0.4873,
      "step": 57392
    },
    {
      "epoch": 1.7630633121371302,
      "grad_norm": 0.4240054190158844,
      "learning_rate": 6.868888103431426e-07,
      "loss": 0.4592,
      "step": 57393
    },
    {
      "epoch": 1.7630940312720793,
      "grad_norm": 0.39565953612327576,
      "learning_rate": 6.867127996975187e-07,
      "loss": 0.3779,
      "step": 57394
    },
    {
      "epoch": 1.7631247504070284,
      "grad_norm": 0.4315389394760132,
      "learning_rate": 6.865368108037229e-07,
      "loss": 0.4834,
      "step": 57395
    },
    {
      "epoch": 1.7631554695419775,
      "grad_norm": 0.4351840019226074,
      "learning_rate": 6.863608436621749e-07,
      "loss": 0.5424,
      "step": 57396
    },
    {
      "epoch": 1.763186188676927,
      "grad_norm": 0.4766958951950073,
      "learning_rate": 6.861848982732788e-07,
      "loss": 0.4579,
      "step": 57397
    },
    {
      "epoch": 1.763216907811876,
      "grad_norm": 0.4994657337665558,
      "learning_rate": 6.86008974637451e-07,
      "loss": 0.4849,
      "step": 57398
    },
    {
      "epoch": 1.7632476269468251,
      "grad_norm": 0.457379549741745,
      "learning_rate": 6.858330727550966e-07,
      "loss": 0.4971,
      "step": 57399
    },
    {
      "epoch": 1.7632783460817745,
      "grad_norm": 0.4468986690044403,
      "learning_rate": 6.85657192626632e-07,
      "loss": 0.5431,
      "step": 57400
    },
    {
      "epoch": 1.7633090652167236,
      "grad_norm": 0.3958667814731598,
      "learning_rate": 6.854813342524646e-07,
      "loss": 0.3952,
      "step": 57401
    },
    {
      "epoch": 1.7633397843516727,
      "grad_norm": 0.5178121328353882,
      "learning_rate": 6.853054976330076e-07,
      "loss": 0.4155,
      "step": 57402
    },
    {
      "epoch": 1.7633705034866218,
      "grad_norm": 0.829430341720581,
      "learning_rate": 6.851296827686682e-07,
      "loss": 0.4045,
      "step": 57403
    },
    {
      "epoch": 1.763401222621571,
      "grad_norm": 0.432314932346344,
      "learning_rate": 6.849538896598596e-07,
      "loss": 0.438,
      "step": 57404
    },
    {
      "epoch": 1.76343194175652,
      "grad_norm": 0.44218334555625916,
      "learning_rate": 6.847781183069912e-07,
      "loss": 0.509,
      "step": 57405
    },
    {
      "epoch": 1.7634626608914692,
      "grad_norm": 0.44317173957824707,
      "learning_rate": 6.846023687104742e-07,
      "loss": 0.4816,
      "step": 57406
    },
    {
      "epoch": 1.7634933800264183,
      "grad_norm": 0.3908402621746063,
      "learning_rate": 6.8442664087072e-07,
      "loss": 0.4095,
      "step": 57407
    },
    {
      "epoch": 1.7635240991613677,
      "grad_norm": 0.46789228916168213,
      "learning_rate": 6.842509347881366e-07,
      "loss": 0.5546,
      "step": 57408
    },
    {
      "epoch": 1.7635548182963168,
      "grad_norm": 0.40374431014060974,
      "learning_rate": 6.840752504631365e-07,
      "loss": 0.4639,
      "step": 57409
    },
    {
      "epoch": 1.763585537431266,
      "grad_norm": 0.44568341970443726,
      "learning_rate": 6.838995878961286e-07,
      "loss": 0.5191,
      "step": 57410
    },
    {
      "epoch": 1.7636162565662152,
      "grad_norm": 0.43683117628097534,
      "learning_rate": 6.837239470875257e-07,
      "loss": 0.5125,
      "step": 57411
    },
    {
      "epoch": 1.7636469757011644,
      "grad_norm": 0.39606693387031555,
      "learning_rate": 6.835483280377342e-07,
      "loss": 0.4934,
      "step": 57412
    },
    {
      "epoch": 1.7636776948361135,
      "grad_norm": 0.42356160283088684,
      "learning_rate": 6.833727307471672e-07,
      "loss": 0.461,
      "step": 57413
    },
    {
      "epoch": 1.7637084139710626,
      "grad_norm": 0.4814971089363098,
      "learning_rate": 6.83197155216233e-07,
      "loss": 0.4747,
      "step": 57414
    },
    {
      "epoch": 1.7637391331060117,
      "grad_norm": 0.4427427351474762,
      "learning_rate": 6.83021601445344e-07,
      "loss": 0.4568,
      "step": 57415
    },
    {
      "epoch": 1.7637698522409608,
      "grad_norm": 0.5066736936569214,
      "learning_rate": 6.82846069434907e-07,
      "loss": 0.3996,
      "step": 57416
    },
    {
      "epoch": 1.76380057137591,
      "grad_norm": 0.45504242181777954,
      "learning_rate": 6.826705591853344e-07,
      "loss": 0.4777,
      "step": 57417
    },
    {
      "epoch": 1.763831290510859,
      "grad_norm": 0.4227299392223358,
      "learning_rate": 6.824950706970357e-07,
      "loss": 0.3709,
      "step": 57418
    },
    {
      "epoch": 1.7638620096458084,
      "grad_norm": 0.4210584759712219,
      "learning_rate": 6.823196039704216e-07,
      "loss": 0.4795,
      "step": 57419
    },
    {
      "epoch": 1.7638927287807575,
      "grad_norm": 0.42637506127357483,
      "learning_rate": 6.821441590058986e-07,
      "loss": 0.374,
      "step": 57420
    },
    {
      "epoch": 1.7639234479157067,
      "grad_norm": 0.46146634221076965,
      "learning_rate": 6.819687358038796e-07,
      "loss": 0.4165,
      "step": 57421
    },
    {
      "epoch": 1.763954167050656,
      "grad_norm": 0.40887323021888733,
      "learning_rate": 6.817933343647731e-07,
      "loss": 0.5247,
      "step": 57422
    },
    {
      "epoch": 1.7639848861856051,
      "grad_norm": 0.4694049060344696,
      "learning_rate": 6.8161795468899e-07,
      "loss": 0.4951,
      "step": 57423
    },
    {
      "epoch": 1.7640156053205542,
      "grad_norm": 0.42788636684417725,
      "learning_rate": 6.814425967769378e-07,
      "loss": 0.4286,
      "step": 57424
    },
    {
      "epoch": 1.7640463244555034,
      "grad_norm": 0.4767444431781769,
      "learning_rate": 6.812672606290272e-07,
      "loss": 0.4518,
      "step": 57425
    },
    {
      "epoch": 1.7640770435904525,
      "grad_norm": 0.42719101905822754,
      "learning_rate": 6.810919462456678e-07,
      "loss": 0.5486,
      "step": 57426
    },
    {
      "epoch": 1.7641077627254016,
      "grad_norm": 0.4229084849357605,
      "learning_rate": 6.809166536272694e-07,
      "loss": 0.5133,
      "step": 57427
    },
    {
      "epoch": 1.7641384818603507,
      "grad_norm": 0.451376736164093,
      "learning_rate": 6.807413827742426e-07,
      "loss": 0.3862,
      "step": 57428
    },
    {
      "epoch": 1.7641692009952998,
      "grad_norm": 0.42943158745765686,
      "learning_rate": 6.805661336869929e-07,
      "loss": 0.4944,
      "step": 57429
    },
    {
      "epoch": 1.7641999201302492,
      "grad_norm": 0.4308798015117645,
      "learning_rate": 6.803909063659341e-07,
      "loss": 0.4678,
      "step": 57430
    },
    {
      "epoch": 1.7642306392651983,
      "grad_norm": 0.4969813823699951,
      "learning_rate": 6.802157008114696e-07,
      "loss": 0.4897,
      "step": 57431
    },
    {
      "epoch": 1.7642613584001474,
      "grad_norm": 0.4370257556438446,
      "learning_rate": 6.800405170240155e-07,
      "loss": 0.4645,
      "step": 57432
    },
    {
      "epoch": 1.7642920775350968,
      "grad_norm": 0.4270932078361511,
      "learning_rate": 6.798653550039758e-07,
      "loss": 0.385,
      "step": 57433
    },
    {
      "epoch": 1.7643227966700459,
      "grad_norm": 0.4081518352031708,
      "learning_rate": 6.796902147517637e-07,
      "loss": 0.4411,
      "step": 57434
    },
    {
      "epoch": 1.764353515804995,
      "grad_norm": 0.4211127460002899,
      "learning_rate": 6.795150962677833e-07,
      "loss": 0.4526,
      "step": 57435
    },
    {
      "epoch": 1.7643842349399441,
      "grad_norm": 0.43185216188430786,
      "learning_rate": 6.793399995524474e-07,
      "loss": 0.4815,
      "step": 57436
    },
    {
      "epoch": 1.7644149540748932,
      "grad_norm": 0.4324095845222473,
      "learning_rate": 6.791649246061638e-07,
      "loss": 0.509,
      "step": 57437
    },
    {
      "epoch": 1.7644456732098424,
      "grad_norm": 0.4734286963939667,
      "learning_rate": 6.789898714293419e-07,
      "loss": 0.4494,
      "step": 57438
    },
    {
      "epoch": 1.7644763923447915,
      "grad_norm": 0.40901246666908264,
      "learning_rate": 6.788148400223904e-07,
      "loss": 0.4335,
      "step": 57439
    },
    {
      "epoch": 1.7645071114797406,
      "grad_norm": 0.42646872997283936,
      "learning_rate": 6.786398303857167e-07,
      "loss": 0.4488,
      "step": 57440
    },
    {
      "epoch": 1.76453783061469,
      "grad_norm": 0.569765031337738,
      "learning_rate": 6.784648425197304e-07,
      "loss": 0.5359,
      "step": 57441
    },
    {
      "epoch": 1.764568549749639,
      "grad_norm": 0.43030881881713867,
      "learning_rate": 6.782898764248424e-07,
      "loss": 0.4941,
      "step": 57442
    },
    {
      "epoch": 1.7645992688845882,
      "grad_norm": 0.5243890881538391,
      "learning_rate": 6.78114932101458e-07,
      "loss": 0.5075,
      "step": 57443
    },
    {
      "epoch": 1.7646299880195375,
      "grad_norm": 0.4359535872936249,
      "learning_rate": 6.779400095499878e-07,
      "loss": 0.4768,
      "step": 57444
    },
    {
      "epoch": 1.7646607071544866,
      "grad_norm": 0.5236281752586365,
      "learning_rate": 6.777651087708382e-07,
      "loss": 0.4952,
      "step": 57445
    },
    {
      "epoch": 1.7646914262894358,
      "grad_norm": 0.4400150775909424,
      "learning_rate": 6.77590229764421e-07,
      "loss": 0.4831,
      "step": 57446
    },
    {
      "epoch": 1.7647221454243849,
      "grad_norm": 0.4278317093849182,
      "learning_rate": 6.774153725311427e-07,
      "loss": 0.44,
      "step": 57447
    },
    {
      "epoch": 1.764752864559334,
      "grad_norm": 0.44333747029304504,
      "learning_rate": 6.772405370714119e-07,
      "loss": 0.4968,
      "step": 57448
    },
    {
      "epoch": 1.7647835836942831,
      "grad_norm": 0.4120957553386688,
      "learning_rate": 6.770657233856359e-07,
      "loss": 0.411,
      "step": 57449
    },
    {
      "epoch": 1.7648143028292322,
      "grad_norm": 0.4445773661136627,
      "learning_rate": 6.768909314742245e-07,
      "loss": 0.4405,
      "step": 57450
    },
    {
      "epoch": 1.7648450219641814,
      "grad_norm": 0.4737989902496338,
      "learning_rate": 6.767161613375872e-07,
      "loss": 0.4888,
      "step": 57451
    },
    {
      "epoch": 1.7648757410991307,
      "grad_norm": 0.4358712434768677,
      "learning_rate": 6.765414129761283e-07,
      "loss": 0.4719,
      "step": 57452
    },
    {
      "epoch": 1.7649064602340798,
      "grad_norm": 0.46450045704841614,
      "learning_rate": 6.763666863902585e-07,
      "loss": 0.5172,
      "step": 57453
    },
    {
      "epoch": 1.764937179369029,
      "grad_norm": 0.5025591254234314,
      "learning_rate": 6.761919815803853e-07,
      "loss": 0.4818,
      "step": 57454
    },
    {
      "epoch": 1.7649678985039783,
      "grad_norm": 0.42347362637519836,
      "learning_rate": 6.760172985469182e-07,
      "loss": 0.4891,
      "step": 57455
    },
    {
      "epoch": 1.7649986176389274,
      "grad_norm": 0.42142030596733093,
      "learning_rate": 6.758426372902627e-07,
      "loss": 0.4002,
      "step": 57456
    },
    {
      "epoch": 1.7650293367738765,
      "grad_norm": 0.49542760848999023,
      "learning_rate": 6.756679978108294e-07,
      "loss": 0.4696,
      "step": 57457
    },
    {
      "epoch": 1.7650600559088256,
      "grad_norm": 0.4034683406352997,
      "learning_rate": 6.754933801090213e-07,
      "loss": 0.4109,
      "step": 57458
    },
    {
      "epoch": 1.7650907750437748,
      "grad_norm": 0.45198607444763184,
      "learning_rate": 6.753187841852526e-07,
      "loss": 0.4512,
      "step": 57459
    },
    {
      "epoch": 1.7651214941787239,
      "grad_norm": 0.4748191833496094,
      "learning_rate": 6.751442100399275e-07,
      "loss": 0.5269,
      "step": 57460
    },
    {
      "epoch": 1.765152213313673,
      "grad_norm": 0.4206775724887848,
      "learning_rate": 6.749696576734533e-07,
      "loss": 0.3896,
      "step": 57461
    },
    {
      "epoch": 1.7651829324486221,
      "grad_norm": 0.4505594074726105,
      "learning_rate": 6.747951270862385e-07,
      "loss": 0.4662,
      "step": 57462
    },
    {
      "epoch": 1.7652136515835712,
      "grad_norm": 0.4301219880580902,
      "learning_rate": 6.746206182786918e-07,
      "loss": 0.5172,
      "step": 57463
    },
    {
      "epoch": 1.7652443707185206,
      "grad_norm": 0.43993839621543884,
      "learning_rate": 6.744461312512218e-07,
      "loss": 0.4472,
      "step": 57464
    },
    {
      "epoch": 1.7652750898534697,
      "grad_norm": 0.4128560423851013,
      "learning_rate": 6.742716660042314e-07,
      "loss": 0.5058,
      "step": 57465
    },
    {
      "epoch": 1.765305808988419,
      "grad_norm": 0.4580234885215759,
      "learning_rate": 6.740972225381337e-07,
      "loss": 0.4703,
      "step": 57466
    },
    {
      "epoch": 1.7653365281233682,
      "grad_norm": 0.4245084822177887,
      "learning_rate": 6.739228008533294e-07,
      "loss": 0.4922,
      "step": 57467
    },
    {
      "epoch": 1.7653672472583173,
      "grad_norm": 0.4390881657600403,
      "learning_rate": 6.737484009502326e-07,
      "loss": 0.5104,
      "step": 57468
    },
    {
      "epoch": 1.7653979663932664,
      "grad_norm": 0.39642012119293213,
      "learning_rate": 6.735740228292464e-07,
      "loss": 0.4255,
      "step": 57469
    },
    {
      "epoch": 1.7654286855282155,
      "grad_norm": 0.42470887303352356,
      "learning_rate": 6.733996664907816e-07,
      "loss": 0.5174,
      "step": 57470
    },
    {
      "epoch": 1.7654594046631646,
      "grad_norm": 0.3731878399848938,
      "learning_rate": 6.732253319352411e-07,
      "loss": 0.4398,
      "step": 57471
    },
    {
      "epoch": 1.7654901237981138,
      "grad_norm": 0.4314616322517395,
      "learning_rate": 6.730510191630335e-07,
      "loss": 0.4516,
      "step": 57472
    },
    {
      "epoch": 1.7655208429330629,
      "grad_norm": 0.3799874186515808,
      "learning_rate": 6.728767281745674e-07,
      "loss": 0.2954,
      "step": 57473
    },
    {
      "epoch": 1.765551562068012,
      "grad_norm": 0.43608754873275757,
      "learning_rate": 6.727024589702513e-07,
      "loss": 0.5178,
      "step": 57474
    },
    {
      "epoch": 1.7655822812029613,
      "grad_norm": 0.41695505380630493,
      "learning_rate": 6.725282115504872e-07,
      "loss": 0.5167,
      "step": 57475
    },
    {
      "epoch": 1.7656130003379105,
      "grad_norm": 0.5605771541595459,
      "learning_rate": 6.723539859156858e-07,
      "loss": 0.4152,
      "step": 57476
    },
    {
      "epoch": 1.7656437194728598,
      "grad_norm": 0.4352937340736389,
      "learning_rate": 6.721797820662535e-07,
      "loss": 0.4535,
      "step": 57477
    },
    {
      "epoch": 1.765674438607809,
      "grad_norm": 0.4150565564632416,
      "learning_rate": 6.720056000025965e-07,
      "loss": 0.6039,
      "step": 57478
    },
    {
      "epoch": 1.765705157742758,
      "grad_norm": 0.48530685901641846,
      "learning_rate": 6.718314397251224e-07,
      "loss": 0.5145,
      "step": 57479
    },
    {
      "epoch": 1.7657358768777072,
      "grad_norm": 0.4867296516895294,
      "learning_rate": 6.716573012342365e-07,
      "loss": 0.4511,
      "step": 57480
    },
    {
      "epoch": 1.7657665960126563,
      "grad_norm": 0.4752196669578552,
      "learning_rate": 6.71483184530346e-07,
      "loss": 0.4644,
      "step": 57481
    },
    {
      "epoch": 1.7657973151476054,
      "grad_norm": 0.4667581617832184,
      "learning_rate": 6.713090896138585e-07,
      "loss": 0.4628,
      "step": 57482
    },
    {
      "epoch": 1.7658280342825545,
      "grad_norm": 0.4782121777534485,
      "learning_rate": 6.711350164851815e-07,
      "loss": 0.4601,
      "step": 57483
    },
    {
      "epoch": 1.7658587534175036,
      "grad_norm": 0.4731508791446686,
      "learning_rate": 6.70960965144719e-07,
      "loss": 0.5606,
      "step": 57484
    },
    {
      "epoch": 1.7658894725524528,
      "grad_norm": 0.41831672191619873,
      "learning_rate": 6.707869355928786e-07,
      "loss": 0.396,
      "step": 57485
    },
    {
      "epoch": 1.765920191687402,
      "grad_norm": 0.4562029242515564,
      "learning_rate": 6.706129278300666e-07,
      "loss": 0.5511,
      "step": 57486
    },
    {
      "epoch": 1.7659509108223512,
      "grad_norm": 0.43315353989601135,
      "learning_rate": 6.704389418566914e-07,
      "loss": 0.5318,
      "step": 57487
    },
    {
      "epoch": 1.7659816299573003,
      "grad_norm": 0.44433650374412537,
      "learning_rate": 6.702649776731562e-07,
      "loss": 0.4668,
      "step": 57488
    },
    {
      "epoch": 1.7660123490922497,
      "grad_norm": 0.48458555340766907,
      "learning_rate": 6.700910352798684e-07,
      "loss": 0.4787,
      "step": 57489
    },
    {
      "epoch": 1.7660430682271988,
      "grad_norm": 0.4364835321903229,
      "learning_rate": 6.699171146772343e-07,
      "loss": 0.4329,
      "step": 57490
    },
    {
      "epoch": 1.766073787362148,
      "grad_norm": 0.4880020320415497,
      "learning_rate": 6.697432158656625e-07,
      "loss": 0.4373,
      "step": 57491
    },
    {
      "epoch": 1.766104506497097,
      "grad_norm": 0.4534365236759186,
      "learning_rate": 6.69569338845556e-07,
      "loss": 0.4452,
      "step": 57492
    },
    {
      "epoch": 1.7661352256320462,
      "grad_norm": 0.5128269195556641,
      "learning_rate": 6.693954836173222e-07,
      "loss": 0.4245,
      "step": 57493
    },
    {
      "epoch": 1.7661659447669953,
      "grad_norm": 0.4421260952949524,
      "learning_rate": 6.692216501813642e-07,
      "loss": 0.4693,
      "step": 57494
    },
    {
      "epoch": 1.7661966639019444,
      "grad_norm": 0.43328070640563965,
      "learning_rate": 6.69047838538095e-07,
      "loss": 0.4198,
      "step": 57495
    },
    {
      "epoch": 1.7662273830368935,
      "grad_norm": 0.4101705253124237,
      "learning_rate": 6.688740486879131e-07,
      "loss": 0.5379,
      "step": 57496
    },
    {
      "epoch": 1.7662581021718429,
      "grad_norm": 0.3999945819377899,
      "learning_rate": 6.687002806312281e-07,
      "loss": 0.4289,
      "step": 57497
    },
    {
      "epoch": 1.766288821306792,
      "grad_norm": 0.45453986525535583,
      "learning_rate": 6.685265343684466e-07,
      "loss": 0.4449,
      "step": 57498
    },
    {
      "epoch": 1.766319540441741,
      "grad_norm": 0.48607951402664185,
      "learning_rate": 6.683528098999703e-07,
      "loss": 0.3952,
      "step": 57499
    },
    {
      "epoch": 1.7663502595766905,
      "grad_norm": 0.43194591999053955,
      "learning_rate": 6.681791072262112e-07,
      "loss": 0.4691,
      "step": 57500
    },
    {
      "epoch": 1.7663809787116396,
      "grad_norm": 0.4661966562271118,
      "learning_rate": 6.680054263475699e-07,
      "loss": 0.4144,
      "step": 57501
    },
    {
      "epoch": 1.7664116978465887,
      "grad_norm": 0.43051648139953613,
      "learning_rate": 6.678317672644541e-07,
      "loss": 0.4621,
      "step": 57502
    },
    {
      "epoch": 1.7664424169815378,
      "grad_norm": 0.4349672496318817,
      "learning_rate": 6.676581299772666e-07,
      "loss": 0.5,
      "step": 57503
    },
    {
      "epoch": 1.766473136116487,
      "grad_norm": 0.41263240575790405,
      "learning_rate": 6.674845144864195e-07,
      "loss": 0.3911,
      "step": 57504
    },
    {
      "epoch": 1.766503855251436,
      "grad_norm": 0.4328252971172333,
      "learning_rate": 6.673109207923112e-07,
      "loss": 0.4063,
      "step": 57505
    },
    {
      "epoch": 1.7665345743863852,
      "grad_norm": 0.4309835433959961,
      "learning_rate": 6.671373488953514e-07,
      "loss": 0.4993,
      "step": 57506
    },
    {
      "epoch": 1.7665652935213343,
      "grad_norm": 0.43569278717041016,
      "learning_rate": 6.669637987959432e-07,
      "loss": 0.4763,
      "step": 57507
    },
    {
      "epoch": 1.7665960126562836,
      "grad_norm": 0.48179423809051514,
      "learning_rate": 6.667902704944928e-07,
      "loss": 0.4388,
      "step": 57508
    },
    {
      "epoch": 1.7666267317912328,
      "grad_norm": 0.43824058771133423,
      "learning_rate": 6.666167639914056e-07,
      "loss": 0.4993,
      "step": 57509
    },
    {
      "epoch": 1.7666574509261819,
      "grad_norm": 0.4317508041858673,
      "learning_rate": 6.664432792870878e-07,
      "loss": 0.4466,
      "step": 57510
    },
    {
      "epoch": 1.7666881700611312,
      "grad_norm": 0.45164260268211365,
      "learning_rate": 6.662698163819426e-07,
      "loss": 0.4702,
      "step": 57511
    },
    {
      "epoch": 1.7667188891960803,
      "grad_norm": 0.4168050289154053,
      "learning_rate": 6.660963752763761e-07,
      "loss": 0.5028,
      "step": 57512
    },
    {
      "epoch": 1.7667496083310295,
      "grad_norm": 0.4352473020553589,
      "learning_rate": 6.659229559707925e-07,
      "loss": 0.4811,
      "step": 57513
    },
    {
      "epoch": 1.7667803274659786,
      "grad_norm": 0.43216851353645325,
      "learning_rate": 6.657495584656004e-07,
      "loss": 0.4518,
      "step": 57514
    },
    {
      "epoch": 1.7668110466009277,
      "grad_norm": 0.5045408606529236,
      "learning_rate": 6.655761827612006e-07,
      "loss": 0.5081,
      "step": 57515
    },
    {
      "epoch": 1.7668417657358768,
      "grad_norm": 0.43870872259140015,
      "learning_rate": 6.654028288579983e-07,
      "loss": 0.4808,
      "step": 57516
    },
    {
      "epoch": 1.766872484870826,
      "grad_norm": 0.48418131470680237,
      "learning_rate": 6.65229496756401e-07,
      "loss": 0.4047,
      "step": 57517
    },
    {
      "epoch": 1.766903204005775,
      "grad_norm": 0.4504837691783905,
      "learning_rate": 6.650561864568106e-07,
      "loss": 0.4422,
      "step": 57518
    },
    {
      "epoch": 1.7669339231407244,
      "grad_norm": 0.4253697693347931,
      "learning_rate": 6.648828979596366e-07,
      "loss": 0.4307,
      "step": 57519
    },
    {
      "epoch": 1.7669646422756735,
      "grad_norm": 0.4152374267578125,
      "learning_rate": 6.647096312652779e-07,
      "loss": 0.4115,
      "step": 57520
    },
    {
      "epoch": 1.7669953614106226,
      "grad_norm": 0.4761117994785309,
      "learning_rate": 6.645363863741427e-07,
      "loss": 0.5724,
      "step": 57521
    },
    {
      "epoch": 1.767026080545572,
      "grad_norm": 0.5476588606834412,
      "learning_rate": 6.643631632866343e-07,
      "loss": 0.5459,
      "step": 57522
    },
    {
      "epoch": 1.767056799680521,
      "grad_norm": 0.4349217712879181,
      "learning_rate": 6.641899620031588e-07,
      "loss": 0.5245,
      "step": 57523
    },
    {
      "epoch": 1.7670875188154702,
      "grad_norm": 0.45467156171798706,
      "learning_rate": 6.640167825241184e-07,
      "loss": 0.4741,
      "step": 57524
    },
    {
      "epoch": 1.7671182379504193,
      "grad_norm": 0.40271204710006714,
      "learning_rate": 6.638436248499192e-07,
      "loss": 0.42,
      "step": 57525
    },
    {
      "epoch": 1.7671489570853685,
      "grad_norm": 0.4650871753692627,
      "learning_rate": 6.636704889809654e-07,
      "loss": 0.512,
      "step": 57526
    },
    {
      "epoch": 1.7671796762203176,
      "grad_norm": 0.4046795666217804,
      "learning_rate": 6.634973749176621e-07,
      "loss": 0.4781,
      "step": 57527
    },
    {
      "epoch": 1.7672103953552667,
      "grad_norm": 0.44558435678482056,
      "learning_rate": 6.633242826604114e-07,
      "loss": 0.5054,
      "step": 57528
    },
    {
      "epoch": 1.7672411144902158,
      "grad_norm": 0.4353793263435364,
      "learning_rate": 6.631512122096207e-07,
      "loss": 0.5012,
      "step": 57529
    },
    {
      "epoch": 1.7672718336251652,
      "grad_norm": 0.4250643849372864,
      "learning_rate": 6.629781635656884e-07,
      "loss": 0.4487,
      "step": 57530
    },
    {
      "epoch": 1.7673025527601143,
      "grad_norm": 0.434941828250885,
      "learning_rate": 6.628051367290267e-07,
      "loss": 0.4911,
      "step": 57531
    },
    {
      "epoch": 1.7673332718950634,
      "grad_norm": 0.433327853679657,
      "learning_rate": 6.62632131700034e-07,
      "loss": 0.4604,
      "step": 57532
    },
    {
      "epoch": 1.7673639910300127,
      "grad_norm": 0.45207926630973816,
      "learning_rate": 6.624591484791177e-07,
      "loss": 0.5422,
      "step": 57533
    },
    {
      "epoch": 1.7673947101649619,
      "grad_norm": 0.47461748123168945,
      "learning_rate": 6.622861870666786e-07,
      "loss": 0.5302,
      "step": 57534
    },
    {
      "epoch": 1.767425429299911,
      "grad_norm": 0.44342830777168274,
      "learning_rate": 6.621132474631208e-07,
      "loss": 0.4733,
      "step": 57535
    },
    {
      "epoch": 1.76745614843486,
      "grad_norm": 0.43529677391052246,
      "learning_rate": 6.61940329668852e-07,
      "loss": 0.4308,
      "step": 57536
    },
    {
      "epoch": 1.7674868675698092,
      "grad_norm": 0.454385906457901,
      "learning_rate": 6.617674336842728e-07,
      "loss": 0.4847,
      "step": 57537
    },
    {
      "epoch": 1.7675175867047583,
      "grad_norm": 0.4645165205001831,
      "learning_rate": 6.615945595097894e-07,
      "loss": 0.4968,
      "step": 57538
    },
    {
      "epoch": 1.7675483058397075,
      "grad_norm": 0.9802213907241821,
      "learning_rate": 6.614217071458029e-07,
      "loss": 0.5053,
      "step": 57539
    },
    {
      "epoch": 1.7675790249746566,
      "grad_norm": 0.41735750436782837,
      "learning_rate": 6.612488765927183e-07,
      "loss": 0.3942,
      "step": 57540
    },
    {
      "epoch": 1.767609744109606,
      "grad_norm": 0.4283553957939148,
      "learning_rate": 6.610760678509387e-07,
      "loss": 0.4854,
      "step": 57541
    },
    {
      "epoch": 1.767640463244555,
      "grad_norm": 0.4114328920841217,
      "learning_rate": 6.609032809208693e-07,
      "loss": 0.5085,
      "step": 57542
    },
    {
      "epoch": 1.7676711823795042,
      "grad_norm": 0.42499351501464844,
      "learning_rate": 6.60730515802912e-07,
      "loss": 0.447,
      "step": 57543
    },
    {
      "epoch": 1.7677019015144535,
      "grad_norm": 0.4316789209842682,
      "learning_rate": 6.605577724974699e-07,
      "loss": 0.4935,
      "step": 57544
    },
    {
      "epoch": 1.7677326206494026,
      "grad_norm": 0.4477947950363159,
      "learning_rate": 6.603850510049481e-07,
      "loss": 0.4479,
      "step": 57545
    },
    {
      "epoch": 1.7677633397843517,
      "grad_norm": 0.43374690413475037,
      "learning_rate": 6.602123513257497e-07,
      "loss": 0.4828,
      "step": 57546
    },
    {
      "epoch": 1.7677940589193009,
      "grad_norm": 0.4368295669555664,
      "learning_rate": 6.600396734602777e-07,
      "loss": 0.4259,
      "step": 57547
    },
    {
      "epoch": 1.76782477805425,
      "grad_norm": 0.45532333850860596,
      "learning_rate": 6.598670174089339e-07,
      "loss": 0.4073,
      "step": 57548
    },
    {
      "epoch": 1.767855497189199,
      "grad_norm": 0.4284021258354187,
      "learning_rate": 6.596943831721236e-07,
      "loss": 0.5466,
      "step": 57549
    },
    {
      "epoch": 1.7678862163241482,
      "grad_norm": 0.48013439774513245,
      "learning_rate": 6.59521770750251e-07,
      "loss": 0.4503,
      "step": 57550
    },
    {
      "epoch": 1.7679169354590973,
      "grad_norm": 0.42175164818763733,
      "learning_rate": 6.593491801437157e-07,
      "loss": 0.5017,
      "step": 57551
    },
    {
      "epoch": 1.7679476545940467,
      "grad_norm": 0.45543956756591797,
      "learning_rate": 6.59176611352923e-07,
      "loss": 0.4334,
      "step": 57552
    },
    {
      "epoch": 1.7679783737289958,
      "grad_norm": 0.4398808479309082,
      "learning_rate": 6.590040643782758e-07,
      "loss": 0.448,
      "step": 57553
    },
    {
      "epoch": 1.768009092863945,
      "grad_norm": 0.45052552223205566,
      "learning_rate": 6.588315392201772e-07,
      "loss": 0.4478,
      "step": 57554
    },
    {
      "epoch": 1.7680398119988943,
      "grad_norm": 0.4261956512928009,
      "learning_rate": 6.586590358790312e-07,
      "loss": 0.559,
      "step": 57555
    },
    {
      "epoch": 1.7680705311338434,
      "grad_norm": 0.44443702697753906,
      "learning_rate": 6.584865543552376e-07,
      "loss": 0.4856,
      "step": 57556
    },
    {
      "epoch": 1.7681012502687925,
      "grad_norm": 0.44274812936782837,
      "learning_rate": 6.583140946492017e-07,
      "loss": 0.4713,
      "step": 57557
    },
    {
      "epoch": 1.7681319694037416,
      "grad_norm": 0.4103170931339264,
      "learning_rate": 6.581416567613252e-07,
      "loss": 0.4273,
      "step": 57558
    },
    {
      "epoch": 1.7681626885386907,
      "grad_norm": 0.5196802020072937,
      "learning_rate": 6.579692406920124e-07,
      "loss": 0.5013,
      "step": 57559
    },
    {
      "epoch": 1.7681934076736399,
      "grad_norm": 0.41702374815940857,
      "learning_rate": 6.57796846441664e-07,
      "loss": 0.4242,
      "step": 57560
    },
    {
      "epoch": 1.768224126808589,
      "grad_norm": 0.46358487010002136,
      "learning_rate": 6.576244740106852e-07,
      "loss": 0.5355,
      "step": 57561
    },
    {
      "epoch": 1.768254845943538,
      "grad_norm": 0.3959341049194336,
      "learning_rate": 6.574521233994735e-07,
      "loss": 0.347,
      "step": 57562
    },
    {
      "epoch": 1.7682855650784874,
      "grad_norm": 0.46063706278800964,
      "learning_rate": 6.572797946084375e-07,
      "loss": 0.4782,
      "step": 57563
    },
    {
      "epoch": 1.7683162842134366,
      "grad_norm": 0.519401490688324,
      "learning_rate": 6.571074876379758e-07,
      "loss": 0.4305,
      "step": 57564
    },
    {
      "epoch": 1.7683470033483857,
      "grad_norm": 0.41351625323295593,
      "learning_rate": 6.569352024884934e-07,
      "loss": 0.4863,
      "step": 57565
    },
    {
      "epoch": 1.768377722483335,
      "grad_norm": 0.46758729219436646,
      "learning_rate": 6.567629391603891e-07,
      "loss": 0.4626,
      "step": 57566
    },
    {
      "epoch": 1.7684084416182841,
      "grad_norm": 0.46614789962768555,
      "learning_rate": 6.565906976540704e-07,
      "loss": 0.4767,
      "step": 57567
    },
    {
      "epoch": 1.7684391607532333,
      "grad_norm": 0.4518508017063141,
      "learning_rate": 6.564184779699345e-07,
      "loss": 0.4345,
      "step": 57568
    },
    {
      "epoch": 1.7684698798881824,
      "grad_norm": 0.4274885654449463,
      "learning_rate": 6.562462801083869e-07,
      "loss": 0.4567,
      "step": 57569
    },
    {
      "epoch": 1.7685005990231315,
      "grad_norm": 0.42014411091804504,
      "learning_rate": 6.560741040698282e-07,
      "loss": 0.4147,
      "step": 57570
    },
    {
      "epoch": 1.7685313181580806,
      "grad_norm": 0.45514965057373047,
      "learning_rate": 6.559019498546592e-07,
      "loss": 0.4644,
      "step": 57571
    },
    {
      "epoch": 1.7685620372930297,
      "grad_norm": 0.4273100793361664,
      "learning_rate": 6.557298174632865e-07,
      "loss": 0.4602,
      "step": 57572
    },
    {
      "epoch": 1.7685927564279789,
      "grad_norm": 0.46737140417099,
      "learning_rate": 6.555577068961084e-07,
      "loss": 0.5394,
      "step": 57573
    },
    {
      "epoch": 1.768623475562928,
      "grad_norm": 0.44829869270324707,
      "learning_rate": 6.55385618153529e-07,
      "loss": 0.4254,
      "step": 57574
    },
    {
      "epoch": 1.7686541946978773,
      "grad_norm": 0.4726356267929077,
      "learning_rate": 6.552135512359481e-07,
      "loss": 0.4436,
      "step": 57575
    },
    {
      "epoch": 1.7686849138328264,
      "grad_norm": 0.4000665843486786,
      "learning_rate": 6.550415061437676e-07,
      "loss": 0.416,
      "step": 57576
    },
    {
      "epoch": 1.7687156329677758,
      "grad_norm": 0.4928940236568451,
      "learning_rate": 6.548694828773905e-07,
      "loss": 0.3595,
      "step": 57577
    },
    {
      "epoch": 1.768746352102725,
      "grad_norm": 0.5239489078521729,
      "learning_rate": 6.546974814372209e-07,
      "loss": 0.5336,
      "step": 57578
    },
    {
      "epoch": 1.768777071237674,
      "grad_norm": 0.479447603225708,
      "learning_rate": 6.545255018236562e-07,
      "loss": 0.5785,
      "step": 57579
    },
    {
      "epoch": 1.7688077903726231,
      "grad_norm": 0.4226754605770111,
      "learning_rate": 6.543535440370996e-07,
      "loss": 0.5079,
      "step": 57580
    },
    {
      "epoch": 1.7688385095075723,
      "grad_norm": 0.405020534992218,
      "learning_rate": 6.541816080779529e-07,
      "loss": 0.4822,
      "step": 57581
    },
    {
      "epoch": 1.7688692286425214,
      "grad_norm": 0.4175490736961365,
      "learning_rate": 6.540096939466189e-07,
      "loss": 0.4839,
      "step": 57582
    },
    {
      "epoch": 1.7688999477774705,
      "grad_norm": 0.42635759711265564,
      "learning_rate": 6.538378016434965e-07,
      "loss": 0.5036,
      "step": 57583
    },
    {
      "epoch": 1.7689306669124196,
      "grad_norm": 0.45173516869544983,
      "learning_rate": 6.536659311689897e-07,
      "loss": 0.4836,
      "step": 57584
    },
    {
      "epoch": 1.7689613860473687,
      "grad_norm": 0.42608052492141724,
      "learning_rate": 6.534940825234981e-07,
      "loss": 0.3903,
      "step": 57585
    },
    {
      "epoch": 1.768992105182318,
      "grad_norm": 0.4289591908454895,
      "learning_rate": 6.533222557074248e-07,
      "loss": 0.4503,
      "step": 57586
    },
    {
      "epoch": 1.7690228243172672,
      "grad_norm": 0.4589554965496063,
      "learning_rate": 6.531504507211694e-07,
      "loss": 0.4915,
      "step": 57587
    },
    {
      "epoch": 1.7690535434522165,
      "grad_norm": 0.39518168568611145,
      "learning_rate": 6.52978667565134e-07,
      "loss": 0.5015,
      "step": 57588
    },
    {
      "epoch": 1.7690842625871657,
      "grad_norm": 0.518727719783783,
      "learning_rate": 6.528069062397191e-07,
      "loss": 0.4037,
      "step": 57589
    },
    {
      "epoch": 1.7691149817221148,
      "grad_norm": 0.4767634868621826,
      "learning_rate": 6.526351667453268e-07,
      "loss": 0.4935,
      "step": 57590
    },
    {
      "epoch": 1.769145700857064,
      "grad_norm": 0.4576573371887207,
      "learning_rate": 6.524634490823601e-07,
      "loss": 0.4512,
      "step": 57591
    },
    {
      "epoch": 1.769176419992013,
      "grad_norm": 0.4352659285068512,
      "learning_rate": 6.522917532512152e-07,
      "loss": 0.4899,
      "step": 57592
    },
    {
      "epoch": 1.7692071391269621,
      "grad_norm": 0.5236265659332275,
      "learning_rate": 6.521200792522963e-07,
      "loss": 0.4345,
      "step": 57593
    },
    {
      "epoch": 1.7692378582619113,
      "grad_norm": 0.4274508059024811,
      "learning_rate": 6.519484270860032e-07,
      "loss": 0.4287,
      "step": 57594
    },
    {
      "epoch": 1.7692685773968604,
      "grad_norm": 0.44461873173713684,
      "learning_rate": 6.5177679675274e-07,
      "loss": 0.5168,
      "step": 57595
    },
    {
      "epoch": 1.7692992965318095,
      "grad_norm": 0.425279438495636,
      "learning_rate": 6.516051882529029e-07,
      "loss": 0.382,
      "step": 57596
    },
    {
      "epoch": 1.7693300156667588,
      "grad_norm": 0.421927809715271,
      "learning_rate": 6.51433601586896e-07,
      "loss": 0.4279,
      "step": 57597
    },
    {
      "epoch": 1.769360734801708,
      "grad_norm": 0.4068998098373413,
      "learning_rate": 6.512620367551159e-07,
      "loss": 0.5145,
      "step": 57598
    },
    {
      "epoch": 1.7693914539366573,
      "grad_norm": 0.44109055399894714,
      "learning_rate": 6.510904937579698e-07,
      "loss": 0.5378,
      "step": 57599
    },
    {
      "epoch": 1.7694221730716064,
      "grad_norm": 0.4060433804988861,
      "learning_rate": 6.50918972595852e-07,
      "loss": 0.4171,
      "step": 57600
    },
    {
      "epoch": 1.7694528922065555,
      "grad_norm": 0.49468308687210083,
      "learning_rate": 6.507474732691688e-07,
      "loss": 0.3801,
      "step": 57601
    },
    {
      "epoch": 1.7694836113415047,
      "grad_norm": 0.3893740773200989,
      "learning_rate": 6.505759957783153e-07,
      "loss": 0.4834,
      "step": 57602
    },
    {
      "epoch": 1.7695143304764538,
      "grad_norm": 0.4424229562282562,
      "learning_rate": 6.504045401236947e-07,
      "loss": 0.4591,
      "step": 57603
    },
    {
      "epoch": 1.769545049611403,
      "grad_norm": 0.4186113774776459,
      "learning_rate": 6.502331063057077e-07,
      "loss": 0.5253,
      "step": 57604
    },
    {
      "epoch": 1.769575768746352,
      "grad_norm": 0.4093584716320038,
      "learning_rate": 6.500616943247562e-07,
      "loss": 0.4514,
      "step": 57605
    },
    {
      "epoch": 1.7696064878813011,
      "grad_norm": 0.4140179455280304,
      "learning_rate": 6.498903041812366e-07,
      "loss": 0.4652,
      "step": 57606
    },
    {
      "epoch": 1.7696372070162503,
      "grad_norm": 0.4152325391769409,
      "learning_rate": 6.497189358755496e-07,
      "loss": 0.5052,
      "step": 57607
    },
    {
      "epoch": 1.7696679261511996,
      "grad_norm": 0.4467730224132538,
      "learning_rate": 6.495475894080993e-07,
      "loss": 0.4062,
      "step": 57608
    },
    {
      "epoch": 1.7696986452861487,
      "grad_norm": 0.39577221870422363,
      "learning_rate": 6.493762647792834e-07,
      "loss": 0.4349,
      "step": 57609
    },
    {
      "epoch": 1.7697293644210979,
      "grad_norm": 0.5047244429588318,
      "learning_rate": 6.492049619895025e-07,
      "loss": 0.4165,
      "step": 57610
    },
    {
      "epoch": 1.7697600835560472,
      "grad_norm": 0.44900771975517273,
      "learning_rate": 6.490336810391562e-07,
      "loss": 0.433,
      "step": 57611
    },
    {
      "epoch": 1.7697908026909963,
      "grad_norm": 0.4805769622325897,
      "learning_rate": 6.488624219286444e-07,
      "loss": 0.4335,
      "step": 57612
    },
    {
      "epoch": 1.7698215218259454,
      "grad_norm": 0.41458287835121155,
      "learning_rate": 6.486911846583665e-07,
      "loss": 0.5253,
      "step": 57613
    },
    {
      "epoch": 1.7698522409608946,
      "grad_norm": 0.42808061838150024,
      "learning_rate": 6.48519969228727e-07,
      "loss": 0.4973,
      "step": 57614
    },
    {
      "epoch": 1.7698829600958437,
      "grad_norm": 0.4503202736377716,
      "learning_rate": 6.483487756401186e-07,
      "loss": 0.4558,
      "step": 57615
    },
    {
      "epoch": 1.7699136792307928,
      "grad_norm": 0.4541019797325134,
      "learning_rate": 6.481776038929455e-07,
      "loss": 0.4784,
      "step": 57616
    },
    {
      "epoch": 1.769944398365742,
      "grad_norm": 0.4424979090690613,
      "learning_rate": 6.480064539876074e-07,
      "loss": 0.4666,
      "step": 57617
    },
    {
      "epoch": 1.769975117500691,
      "grad_norm": 0.4278123080730438,
      "learning_rate": 6.478353259245041e-07,
      "loss": 0.3796,
      "step": 57618
    },
    {
      "epoch": 1.7700058366356404,
      "grad_norm": 0.4033765196800232,
      "learning_rate": 6.47664219704034e-07,
      "loss": 0.452,
      "step": 57619
    },
    {
      "epoch": 1.7700365557705895,
      "grad_norm": 0.40112659335136414,
      "learning_rate": 6.474931353265956e-07,
      "loss": 0.4682,
      "step": 57620
    },
    {
      "epoch": 1.7700672749055386,
      "grad_norm": 0.44864168763160706,
      "learning_rate": 6.473220727925911e-07,
      "loss": 0.4803,
      "step": 57621
    },
    {
      "epoch": 1.770097994040488,
      "grad_norm": 0.4770900309085846,
      "learning_rate": 6.471510321024211e-07,
      "loss": 0.4268,
      "step": 57622
    },
    {
      "epoch": 1.770128713175437,
      "grad_norm": 0.44842687249183655,
      "learning_rate": 6.469800132564808e-07,
      "loss": 0.4413,
      "step": 57623
    },
    {
      "epoch": 1.7701594323103862,
      "grad_norm": 0.4725303649902344,
      "learning_rate": 6.468090162551744e-07,
      "loss": 0.379,
      "step": 57624
    },
    {
      "epoch": 1.7701901514453353,
      "grad_norm": 0.4154519736766815,
      "learning_rate": 6.466380410988948e-07,
      "loss": 0.5206,
      "step": 57625
    },
    {
      "epoch": 1.7702208705802844,
      "grad_norm": 0.4700172543525696,
      "learning_rate": 6.464670877880463e-07,
      "loss": 0.5279,
      "step": 57626
    },
    {
      "epoch": 1.7702515897152336,
      "grad_norm": 0.4508028030395508,
      "learning_rate": 6.462961563230297e-07,
      "loss": 0.4445,
      "step": 57627
    },
    {
      "epoch": 1.7702823088501827,
      "grad_norm": 0.4428616166114807,
      "learning_rate": 6.461252467042401e-07,
      "loss": 0.4649,
      "step": 57628
    },
    {
      "epoch": 1.7703130279851318,
      "grad_norm": 0.4349534511566162,
      "learning_rate": 6.459543589320783e-07,
      "loss": 0.4226,
      "step": 57629
    },
    {
      "epoch": 1.7703437471200811,
      "grad_norm": 0.40718433260917664,
      "learning_rate": 6.457834930069429e-07,
      "loss": 0.5079,
      "step": 57630
    },
    {
      "epoch": 1.7703744662550303,
      "grad_norm": 0.42546162009239197,
      "learning_rate": 6.456126489292347e-07,
      "loss": 0.4772,
      "step": 57631
    },
    {
      "epoch": 1.7704051853899794,
      "grad_norm": 0.45127391815185547,
      "learning_rate": 6.454418266993501e-07,
      "loss": 0.5245,
      "step": 57632
    },
    {
      "epoch": 1.7704359045249287,
      "grad_norm": 0.47120335698127747,
      "learning_rate": 6.45271026317692e-07,
      "loss": 0.4882,
      "step": 57633
    },
    {
      "epoch": 1.7704666236598778,
      "grad_norm": 0.45455390214920044,
      "learning_rate": 6.451002477846524e-07,
      "loss": 0.4712,
      "step": 57634
    },
    {
      "epoch": 1.770497342794827,
      "grad_norm": 0.4506199359893799,
      "learning_rate": 6.449294911006387e-07,
      "loss": 0.4416,
      "step": 57635
    },
    {
      "epoch": 1.770528061929776,
      "grad_norm": 0.4044736921787262,
      "learning_rate": 6.447587562660429e-07,
      "loss": 0.4347,
      "step": 57636
    },
    {
      "epoch": 1.7705587810647252,
      "grad_norm": 0.45650309324264526,
      "learning_rate": 6.44588043281269e-07,
      "loss": 0.4284,
      "step": 57637
    },
    {
      "epoch": 1.7705895001996743,
      "grad_norm": 0.4743002653121948,
      "learning_rate": 6.444173521467101e-07,
      "loss": 0.391,
      "step": 57638
    },
    {
      "epoch": 1.7706202193346234,
      "grad_norm": 0.41633298993110657,
      "learning_rate": 6.442466828627692e-07,
      "loss": 0.5797,
      "step": 57639
    },
    {
      "epoch": 1.7706509384695726,
      "grad_norm": 0.3859608769416809,
      "learning_rate": 6.440760354298425e-07,
      "loss": 0.3152,
      "step": 57640
    },
    {
      "epoch": 1.770681657604522,
      "grad_norm": 0.4036533534526825,
      "learning_rate": 6.439054098483322e-07,
      "loss": 0.5046,
      "step": 57641
    },
    {
      "epoch": 1.770712376739471,
      "grad_norm": 0.42701804637908936,
      "learning_rate": 6.437348061186322e-07,
      "loss": 0.5514,
      "step": 57642
    },
    {
      "epoch": 1.7707430958744201,
      "grad_norm": 0.42877644300460815,
      "learning_rate": 6.435642242411433e-07,
      "loss": 0.523,
      "step": 57643
    },
    {
      "epoch": 1.7707738150093695,
      "grad_norm": 0.3874380886554718,
      "learning_rate": 6.43393664216263e-07,
      "loss": 0.4403,
      "step": 57644
    },
    {
      "epoch": 1.7708045341443186,
      "grad_norm": 0.4712507724761963,
      "learning_rate": 6.432231260443911e-07,
      "loss": 0.5231,
      "step": 57645
    },
    {
      "epoch": 1.7708352532792677,
      "grad_norm": 0.4386599659919739,
      "learning_rate": 6.430526097259259e-07,
      "loss": 0.4213,
      "step": 57646
    },
    {
      "epoch": 1.7708659724142168,
      "grad_norm": 0.4276013672351837,
      "learning_rate": 6.42882115261263e-07,
      "loss": 0.528,
      "step": 57647
    },
    {
      "epoch": 1.770896691549166,
      "grad_norm": 0.4582996070384979,
      "learning_rate": 6.427116426508029e-07,
      "loss": 0.507,
      "step": 57648
    },
    {
      "epoch": 1.770927410684115,
      "grad_norm": 0.43594303727149963,
      "learning_rate": 6.425411918949432e-07,
      "loss": 0.4927,
      "step": 57649
    },
    {
      "epoch": 1.7709581298190642,
      "grad_norm": 0.44449514150619507,
      "learning_rate": 6.423707629940845e-07,
      "loss": 0.4488,
      "step": 57650
    },
    {
      "epoch": 1.7709888489540133,
      "grad_norm": 0.43310874700546265,
      "learning_rate": 6.4220035594862e-07,
      "loss": 0.4977,
      "step": 57651
    },
    {
      "epoch": 1.7710195680889627,
      "grad_norm": 0.43189480900764465,
      "learning_rate": 6.420299707589495e-07,
      "loss": 0.4962,
      "step": 57652
    },
    {
      "epoch": 1.7710502872239118,
      "grad_norm": 0.4082495868206024,
      "learning_rate": 6.418596074254723e-07,
      "loss": 0.4779,
      "step": 57653
    },
    {
      "epoch": 1.771081006358861,
      "grad_norm": 0.4622404873371124,
      "learning_rate": 6.416892659485874e-07,
      "loss": 0.4758,
      "step": 57654
    },
    {
      "epoch": 1.7711117254938102,
      "grad_norm": 0.5748800039291382,
      "learning_rate": 6.415189463286886e-07,
      "loss": 0.4092,
      "step": 57655
    },
    {
      "epoch": 1.7711424446287594,
      "grad_norm": 0.429166704416275,
      "learning_rate": 6.413486485661757e-07,
      "loss": 0.4126,
      "step": 57656
    },
    {
      "epoch": 1.7711731637637085,
      "grad_norm": 0.4559217095375061,
      "learning_rate": 6.411783726614473e-07,
      "loss": 0.4478,
      "step": 57657
    },
    {
      "epoch": 1.7712038828986576,
      "grad_norm": 0.4342397451400757,
      "learning_rate": 6.41008118614902e-07,
      "loss": 0.4703,
      "step": 57658
    },
    {
      "epoch": 1.7712346020336067,
      "grad_norm": 0.40386301279067993,
      "learning_rate": 6.408378864269338e-07,
      "loss": 0.4641,
      "step": 57659
    },
    {
      "epoch": 1.7712653211685558,
      "grad_norm": 0.4033457934856415,
      "learning_rate": 6.406676760979447e-07,
      "loss": 0.4298,
      "step": 57660
    },
    {
      "epoch": 1.771296040303505,
      "grad_norm": 0.43373388051986694,
      "learning_rate": 6.404974876283254e-07,
      "loss": 0.4939,
      "step": 57661
    },
    {
      "epoch": 1.771326759438454,
      "grad_norm": 0.43103262782096863,
      "learning_rate": 6.403273210184812e-07,
      "loss": 0.4279,
      "step": 57662
    },
    {
      "epoch": 1.7713574785734034,
      "grad_norm": 0.4277819097042084,
      "learning_rate": 6.401571762688063e-07,
      "loss": 0.4658,
      "step": 57663
    },
    {
      "epoch": 1.7713881977083525,
      "grad_norm": 0.39828982949256897,
      "learning_rate": 6.39987053379697e-07,
      "loss": 0.4601,
      "step": 57664
    },
    {
      "epoch": 1.7714189168433017,
      "grad_norm": 0.39150938391685486,
      "learning_rate": 6.39816952351553e-07,
      "loss": 0.4586,
      "step": 57665
    },
    {
      "epoch": 1.771449635978251,
      "grad_norm": 0.44609707593917847,
      "learning_rate": 6.396468731847672e-07,
      "loss": 0.513,
      "step": 57666
    },
    {
      "epoch": 1.7714803551132001,
      "grad_norm": 0.45438605546951294,
      "learning_rate": 6.394768158797437e-07,
      "loss": 0.4715,
      "step": 57667
    },
    {
      "epoch": 1.7715110742481492,
      "grad_norm": 0.4240175783634186,
      "learning_rate": 6.393067804368735e-07,
      "loss": 0.4049,
      "step": 57668
    },
    {
      "epoch": 1.7715417933830984,
      "grad_norm": 0.4191993474960327,
      "learning_rate": 6.391367668565573e-07,
      "loss": 0.3898,
      "step": 57669
    },
    {
      "epoch": 1.7715725125180475,
      "grad_norm": 0.4254099726676941,
      "learning_rate": 6.389667751391882e-07,
      "loss": 0.4647,
      "step": 57670
    },
    {
      "epoch": 1.7716032316529966,
      "grad_norm": 0.3994683623313904,
      "learning_rate": 6.38796805285169e-07,
      "loss": 0.4364,
      "step": 57671
    },
    {
      "epoch": 1.7716339507879457,
      "grad_norm": 0.4504949748516083,
      "learning_rate": 6.386268572948929e-07,
      "loss": 0.4174,
      "step": 57672
    },
    {
      "epoch": 1.7716646699228948,
      "grad_norm": 0.43338608741760254,
      "learning_rate": 6.384569311687582e-07,
      "loss": 0.4374,
      "step": 57673
    },
    {
      "epoch": 1.7716953890578442,
      "grad_norm": 0.45394957065582275,
      "learning_rate": 6.382870269071595e-07,
      "loss": 0.5347,
      "step": 57674
    },
    {
      "epoch": 1.7717261081927933,
      "grad_norm": 0.3801264762878418,
      "learning_rate": 6.381171445104961e-07,
      "loss": 0.4373,
      "step": 57675
    },
    {
      "epoch": 1.7717568273277424,
      "grad_norm": 0.44683459401130676,
      "learning_rate": 6.379472839791634e-07,
      "loss": 0.5106,
      "step": 57676
    },
    {
      "epoch": 1.7717875464626918,
      "grad_norm": 0.47070086002349854,
      "learning_rate": 6.377774453135599e-07,
      "loss": 0.4753,
      "step": 57677
    },
    {
      "epoch": 1.7718182655976409,
      "grad_norm": 0.46669524908065796,
      "learning_rate": 6.376076285140797e-07,
      "loss": 0.5275,
      "step": 57678
    },
    {
      "epoch": 1.77184898473259,
      "grad_norm": 0.5257264375686646,
      "learning_rate": 6.374378335811204e-07,
      "loss": 0.424,
      "step": 57679
    },
    {
      "epoch": 1.7718797038675391,
      "grad_norm": 0.4298245906829834,
      "learning_rate": 6.372680605150794e-07,
      "loss": 0.4544,
      "step": 57680
    },
    {
      "epoch": 1.7719104230024882,
      "grad_norm": 0.4462886452674866,
      "learning_rate": 6.37098309316353e-07,
      "loss": 0.4824,
      "step": 57681
    },
    {
      "epoch": 1.7719411421374374,
      "grad_norm": 0.4310273230075836,
      "learning_rate": 6.369285799853386e-07,
      "loss": 0.4053,
      "step": 57682
    },
    {
      "epoch": 1.7719718612723865,
      "grad_norm": 0.4314505457878113,
      "learning_rate": 6.367588725224305e-07,
      "loss": 0.4986,
      "step": 57683
    },
    {
      "epoch": 1.7720025804073356,
      "grad_norm": 0.4364800751209259,
      "learning_rate": 6.36589186928025e-07,
      "loss": 0.4715,
      "step": 57684
    },
    {
      "epoch": 1.7720332995422847,
      "grad_norm": 0.44068241119384766,
      "learning_rate": 6.364195232025194e-07,
      "loss": 0.4879,
      "step": 57685
    },
    {
      "epoch": 1.772064018677234,
      "grad_norm": 0.4322170913219452,
      "learning_rate": 6.362498813463125e-07,
      "loss": 0.5355,
      "step": 57686
    },
    {
      "epoch": 1.7720947378121832,
      "grad_norm": 0.43854033946990967,
      "learning_rate": 6.360802613597949e-07,
      "loss": 0.4515,
      "step": 57687
    },
    {
      "epoch": 1.7721254569471325,
      "grad_norm": 0.41179347038269043,
      "learning_rate": 6.359106632433676e-07,
      "loss": 0.4119,
      "step": 57688
    },
    {
      "epoch": 1.7721561760820816,
      "grad_norm": 0.42686840891838074,
      "learning_rate": 6.357410869974234e-07,
      "loss": 0.4162,
      "step": 57689
    },
    {
      "epoch": 1.7721868952170308,
      "grad_norm": 0.4362315833568573,
      "learning_rate": 6.355715326223622e-07,
      "loss": 0.4828,
      "step": 57690
    },
    {
      "epoch": 1.7722176143519799,
      "grad_norm": 0.433886855840683,
      "learning_rate": 6.354020001185757e-07,
      "loss": 0.4863,
      "step": 57691
    },
    {
      "epoch": 1.772248333486929,
      "grad_norm": 0.44465896487236023,
      "learning_rate": 6.352324894864625e-07,
      "loss": 0.4025,
      "step": 57692
    },
    {
      "epoch": 1.7722790526218781,
      "grad_norm": 0.40299689769744873,
      "learning_rate": 6.350630007264169e-07,
      "loss": 0.4588,
      "step": 57693
    },
    {
      "epoch": 1.7723097717568272,
      "grad_norm": 0.43609926104545593,
      "learning_rate": 6.348935338388384e-07,
      "loss": 0.5065,
      "step": 57694
    },
    {
      "epoch": 1.7723404908917764,
      "grad_norm": 0.4429473876953125,
      "learning_rate": 6.347240888241179e-07,
      "loss": 0.4798,
      "step": 57695
    },
    {
      "epoch": 1.7723712100267255,
      "grad_norm": 0.39493149518966675,
      "learning_rate": 6.345546656826551e-07,
      "loss": 0.4646,
      "step": 57696
    },
    {
      "epoch": 1.7724019291616748,
      "grad_norm": 0.441439688205719,
      "learning_rate": 6.343852644148408e-07,
      "loss": 0.52,
      "step": 57697
    },
    {
      "epoch": 1.772432648296624,
      "grad_norm": 0.4359666407108307,
      "learning_rate": 6.342158850210756e-07,
      "loss": 0.4467,
      "step": 57698
    },
    {
      "epoch": 1.7724633674315733,
      "grad_norm": 0.44029146432876587,
      "learning_rate": 6.340465275017537e-07,
      "loss": 0.5487,
      "step": 57699
    },
    {
      "epoch": 1.7724940865665224,
      "grad_norm": 0.44858041405677795,
      "learning_rate": 6.338771918572695e-07,
      "loss": 0.4884,
      "step": 57700
    },
    {
      "epoch": 1.7725248057014715,
      "grad_norm": 0.45515984296798706,
      "learning_rate": 6.337078780880213e-07,
      "loss": 0.4545,
      "step": 57701
    },
    {
      "epoch": 1.7725555248364206,
      "grad_norm": 0.47138500213623047,
      "learning_rate": 6.335385861943988e-07,
      "loss": 0.4917,
      "step": 57702
    },
    {
      "epoch": 1.7725862439713698,
      "grad_norm": 0.41588303446769714,
      "learning_rate": 6.33369316176804e-07,
      "loss": 0.5177,
      "step": 57703
    },
    {
      "epoch": 1.7726169631063189,
      "grad_norm": 0.435808926820755,
      "learning_rate": 6.332000680356287e-07,
      "loss": 0.3751,
      "step": 57704
    },
    {
      "epoch": 1.772647682241268,
      "grad_norm": 0.4369397759437561,
      "learning_rate": 6.330308417712694e-07,
      "loss": 0.4689,
      "step": 57705
    },
    {
      "epoch": 1.7726784013762171,
      "grad_norm": 0.42814260721206665,
      "learning_rate": 6.32861637384119e-07,
      "loss": 0.4852,
      "step": 57706
    },
    {
      "epoch": 1.7727091205111662,
      "grad_norm": 0.41357681155204773,
      "learning_rate": 6.32692454874575e-07,
      "loss": 0.4745,
      "step": 57707
    },
    {
      "epoch": 1.7727398396461156,
      "grad_norm": 0.4366873800754547,
      "learning_rate": 6.325232942430326e-07,
      "loss": 0.4936,
      "step": 57708
    },
    {
      "epoch": 1.7727705587810647,
      "grad_norm": 0.44508323073387146,
      "learning_rate": 6.323541554898871e-07,
      "loss": 0.4049,
      "step": 57709
    },
    {
      "epoch": 1.772801277916014,
      "grad_norm": 0.42844733595848083,
      "learning_rate": 6.321850386155315e-07,
      "loss": 0.4056,
      "step": 57710
    },
    {
      "epoch": 1.7728319970509632,
      "grad_norm": 0.44275134801864624,
      "learning_rate": 6.32015943620361e-07,
      "loss": 0.4955,
      "step": 57711
    },
    {
      "epoch": 1.7728627161859123,
      "grad_norm": 0.5446624755859375,
      "learning_rate": 6.31846870504772e-07,
      "loss": 0.4596,
      "step": 57712
    },
    {
      "epoch": 1.7728934353208614,
      "grad_norm": 0.4237210154533386,
      "learning_rate": 6.316778192691608e-07,
      "loss": 0.4773,
      "step": 57713
    },
    {
      "epoch": 1.7729241544558105,
      "grad_norm": 0.4225066006183624,
      "learning_rate": 6.315087899139183e-07,
      "loss": 0.4886,
      "step": 57714
    },
    {
      "epoch": 1.7729548735907597,
      "grad_norm": 0.43588578701019287,
      "learning_rate": 6.313397824394418e-07,
      "loss": 0.4468,
      "step": 57715
    },
    {
      "epoch": 1.7729855927257088,
      "grad_norm": 0.5163114070892334,
      "learning_rate": 6.311707968461256e-07,
      "loss": 0.4991,
      "step": 57716
    },
    {
      "epoch": 1.773016311860658,
      "grad_norm": 0.4248031675815582,
      "learning_rate": 6.310018331343637e-07,
      "loss": 0.4306,
      "step": 57717
    },
    {
      "epoch": 1.773047030995607,
      "grad_norm": 0.5150688886642456,
      "learning_rate": 6.308328913045536e-07,
      "loss": 0.5252,
      "step": 57718
    },
    {
      "epoch": 1.7730777501305564,
      "grad_norm": 0.4328306317329407,
      "learning_rate": 6.306639713570861e-07,
      "loss": 0.4022,
      "step": 57719
    },
    {
      "epoch": 1.7731084692655055,
      "grad_norm": 0.44179847836494446,
      "learning_rate": 6.304950732923564e-07,
      "loss": 0.4173,
      "step": 57720
    },
    {
      "epoch": 1.7731391884004546,
      "grad_norm": 0.3805181086063385,
      "learning_rate": 6.303261971107611e-07,
      "loss": 0.4529,
      "step": 57721
    },
    {
      "epoch": 1.773169907535404,
      "grad_norm": 0.41823482513427734,
      "learning_rate": 6.301573428126939e-07,
      "loss": 0.436,
      "step": 57722
    },
    {
      "epoch": 1.773200626670353,
      "grad_norm": 0.41893407702445984,
      "learning_rate": 6.29988510398547e-07,
      "loss": 0.5219,
      "step": 57723
    },
    {
      "epoch": 1.7732313458053022,
      "grad_norm": 0.4672594964504242,
      "learning_rate": 6.298196998687168e-07,
      "loss": 0.5357,
      "step": 57724
    },
    {
      "epoch": 1.7732620649402513,
      "grad_norm": 0.44243061542510986,
      "learning_rate": 6.296509112235971e-07,
      "loss": 0.4974,
      "step": 57725
    },
    {
      "epoch": 1.7732927840752004,
      "grad_norm": 0.47268208861351013,
      "learning_rate": 6.294821444635835e-07,
      "loss": 0.4022,
      "step": 57726
    },
    {
      "epoch": 1.7733235032101495,
      "grad_norm": 0.5086696743965149,
      "learning_rate": 6.293133995890666e-07,
      "loss": 0.4046,
      "step": 57727
    },
    {
      "epoch": 1.7733542223450987,
      "grad_norm": 0.432329386472702,
      "learning_rate": 6.291446766004449e-07,
      "loss": 0.4636,
      "step": 57728
    },
    {
      "epoch": 1.7733849414800478,
      "grad_norm": 0.42112165689468384,
      "learning_rate": 6.289759754981073e-07,
      "loss": 0.4507,
      "step": 57729
    },
    {
      "epoch": 1.7734156606149971,
      "grad_norm": 0.4097922146320343,
      "learning_rate": 6.288072962824532e-07,
      "loss": 0.4554,
      "step": 57730
    },
    {
      "epoch": 1.7734463797499462,
      "grad_norm": 0.4968634247779846,
      "learning_rate": 6.286386389538734e-07,
      "loss": 0.4906,
      "step": 57731
    },
    {
      "epoch": 1.7734770988848954,
      "grad_norm": 0.4259278178215027,
      "learning_rate": 6.284700035127633e-07,
      "loss": 0.3833,
      "step": 57732
    },
    {
      "epoch": 1.7735078180198447,
      "grad_norm": 0.4362099766731262,
      "learning_rate": 6.283013899595136e-07,
      "loss": 0.4799,
      "step": 57733
    },
    {
      "epoch": 1.7735385371547938,
      "grad_norm": 0.4631044864654541,
      "learning_rate": 6.281327982945229e-07,
      "loss": 0.4739,
      "step": 57734
    },
    {
      "epoch": 1.773569256289743,
      "grad_norm": 0.4253930151462555,
      "learning_rate": 6.279642285181819e-07,
      "loss": 0.4853,
      "step": 57735
    },
    {
      "epoch": 1.773599975424692,
      "grad_norm": 0.4761214852333069,
      "learning_rate": 6.277956806308849e-07,
      "loss": 0.4896,
      "step": 57736
    },
    {
      "epoch": 1.7736306945596412,
      "grad_norm": 0.4087056517601013,
      "learning_rate": 6.276271546330259e-07,
      "loss": 0.445,
      "step": 57737
    },
    {
      "epoch": 1.7736614136945903,
      "grad_norm": 0.45146477222442627,
      "learning_rate": 6.274586505249969e-07,
      "loss": 0.4307,
      "step": 57738
    },
    {
      "epoch": 1.7736921328295394,
      "grad_norm": 0.4567897617816925,
      "learning_rate": 6.272901683071953e-07,
      "loss": 0.4991,
      "step": 57739
    },
    {
      "epoch": 1.7737228519644885,
      "grad_norm": 0.4223180115222931,
      "learning_rate": 6.271217079800096e-07,
      "loss": 0.4453,
      "step": 57740
    },
    {
      "epoch": 1.7737535710994379,
      "grad_norm": 0.6678879261016846,
      "learning_rate": 6.269532695438385e-07,
      "loss": 0.4288,
      "step": 57741
    },
    {
      "epoch": 1.773784290234387,
      "grad_norm": 0.41523420810699463,
      "learning_rate": 6.267848529990706e-07,
      "loss": 0.4095,
      "step": 57742
    },
    {
      "epoch": 1.7738150093693361,
      "grad_norm": 0.424245685338974,
      "learning_rate": 6.26616458346101e-07,
      "loss": 0.4631,
      "step": 57743
    },
    {
      "epoch": 1.7738457285042855,
      "grad_norm": 0.4620385468006134,
      "learning_rate": 6.264480855853239e-07,
      "loss": 0.4411,
      "step": 57744
    },
    {
      "epoch": 1.7738764476392346,
      "grad_norm": 0.41752108931541443,
      "learning_rate": 6.262797347171335e-07,
      "loss": 0.5125,
      "step": 57745
    },
    {
      "epoch": 1.7739071667741837,
      "grad_norm": 0.4118901491165161,
      "learning_rate": 6.261114057419193e-07,
      "loss": 0.4851,
      "step": 57746
    },
    {
      "epoch": 1.7739378859091328,
      "grad_norm": 0.4374842345714569,
      "learning_rate": 6.259430986600768e-07,
      "loss": 0.4445,
      "step": 57747
    },
    {
      "epoch": 1.773968605044082,
      "grad_norm": 0.495770126581192,
      "learning_rate": 6.257748134719987e-07,
      "loss": 0.4922,
      "step": 57748
    },
    {
      "epoch": 1.773999324179031,
      "grad_norm": 0.5192620754241943,
      "learning_rate": 6.256065501780795e-07,
      "loss": 0.4717,
      "step": 57749
    },
    {
      "epoch": 1.7740300433139802,
      "grad_norm": 0.4146896302700043,
      "learning_rate": 6.254383087787097e-07,
      "loss": 0.4854,
      "step": 57750
    },
    {
      "epoch": 1.7740607624489293,
      "grad_norm": 0.4096710681915283,
      "learning_rate": 6.252700892742836e-07,
      "loss": 0.4293,
      "step": 57751
    },
    {
      "epoch": 1.7740914815838786,
      "grad_norm": 0.4925937354564667,
      "learning_rate": 6.251018916651941e-07,
      "loss": 0.4482,
      "step": 57752
    },
    {
      "epoch": 1.7741222007188278,
      "grad_norm": 0.4461001753807068,
      "learning_rate": 6.249337159518343e-07,
      "loss": 0.4638,
      "step": 57753
    },
    {
      "epoch": 1.7741529198537769,
      "grad_norm": 0.46149158477783203,
      "learning_rate": 6.247655621345972e-07,
      "loss": 0.4766,
      "step": 57754
    },
    {
      "epoch": 1.7741836389887262,
      "grad_norm": 0.438571035861969,
      "learning_rate": 6.245974302138735e-07,
      "loss": 0.4285,
      "step": 57755
    },
    {
      "epoch": 1.7742143581236753,
      "grad_norm": 0.4680781960487366,
      "learning_rate": 6.244293201900575e-07,
      "loss": 0.4918,
      "step": 57756
    },
    {
      "epoch": 1.7742450772586245,
      "grad_norm": 0.42883023619651794,
      "learning_rate": 6.242612320635411e-07,
      "loss": 0.4521,
      "step": 57757
    },
    {
      "epoch": 1.7742757963935736,
      "grad_norm": 0.4256190359592438,
      "learning_rate": 6.240931658347194e-07,
      "loss": 0.485,
      "step": 57758
    },
    {
      "epoch": 1.7743065155285227,
      "grad_norm": 0.4285341501235962,
      "learning_rate": 6.23925121503981e-07,
      "loss": 0.4332,
      "step": 57759
    },
    {
      "epoch": 1.7743372346634718,
      "grad_norm": 0.4341975152492523,
      "learning_rate": 6.237570990717212e-07,
      "loss": 0.4766,
      "step": 57760
    },
    {
      "epoch": 1.774367953798421,
      "grad_norm": 0.47540998458862305,
      "learning_rate": 6.235890985383308e-07,
      "loss": 0.5162,
      "step": 57761
    },
    {
      "epoch": 1.77439867293337,
      "grad_norm": 0.44539520144462585,
      "learning_rate": 6.23421119904205e-07,
      "loss": 0.4191,
      "step": 57762
    },
    {
      "epoch": 1.7744293920683194,
      "grad_norm": 0.3877125382423401,
      "learning_rate": 6.232531631697314e-07,
      "loss": 0.4506,
      "step": 57763
    },
    {
      "epoch": 1.7744601112032685,
      "grad_norm": 0.4533153772354126,
      "learning_rate": 6.230852283353073e-07,
      "loss": 0.4851,
      "step": 57764
    },
    {
      "epoch": 1.7744908303382176,
      "grad_norm": 0.4929729402065277,
      "learning_rate": 6.22917315401319e-07,
      "loss": 0.4079,
      "step": 57765
    },
    {
      "epoch": 1.774521549473167,
      "grad_norm": 0.43842658400535583,
      "learning_rate": 6.227494243681653e-07,
      "loss": 0.4989,
      "step": 57766
    },
    {
      "epoch": 1.774552268608116,
      "grad_norm": 0.42504018545150757,
      "learning_rate": 6.225815552362346e-07,
      "loss": 0.4623,
      "step": 57767
    },
    {
      "epoch": 1.7745829877430652,
      "grad_norm": 0.47209179401397705,
      "learning_rate": 6.2241370800592e-07,
      "loss": 0.4555,
      "step": 57768
    },
    {
      "epoch": 1.7746137068780143,
      "grad_norm": 0.41891610622406006,
      "learning_rate": 6.222458826776123e-07,
      "loss": 0.4312,
      "step": 57769
    },
    {
      "epoch": 1.7746444260129635,
      "grad_norm": 0.46765074133872986,
      "learning_rate": 6.220780792517034e-07,
      "loss": 0.3969,
      "step": 57770
    },
    {
      "epoch": 1.7746751451479126,
      "grad_norm": 0.40172258019447327,
      "learning_rate": 6.219102977285874e-07,
      "loss": 0.4268,
      "step": 57771
    },
    {
      "epoch": 1.7747058642828617,
      "grad_norm": 0.4550803303718567,
      "learning_rate": 6.21742538108654e-07,
      "loss": 0.464,
      "step": 57772
    },
    {
      "epoch": 1.7747365834178108,
      "grad_norm": 0.49437156319618225,
      "learning_rate": 6.215748003922972e-07,
      "loss": 0.4602,
      "step": 57773
    },
    {
      "epoch": 1.7747673025527602,
      "grad_norm": 0.4750617444515228,
      "learning_rate": 6.214070845799048e-07,
      "loss": 0.4458,
      "step": 57774
    },
    {
      "epoch": 1.7747980216877093,
      "grad_norm": 0.402009516954422,
      "learning_rate": 6.212393906718739e-07,
      "loss": 0.4704,
      "step": 57775
    },
    {
      "epoch": 1.7748287408226584,
      "grad_norm": 0.45921632647514343,
      "learning_rate": 6.210717186685922e-07,
      "loss": 0.4926,
      "step": 57776
    },
    {
      "epoch": 1.7748594599576077,
      "grad_norm": 0.44584307074546814,
      "learning_rate": 6.209040685704537e-07,
      "loss": 0.5188,
      "step": 57777
    },
    {
      "epoch": 1.7748901790925569,
      "grad_norm": 0.40403270721435547,
      "learning_rate": 6.207364403778471e-07,
      "loss": 0.4523,
      "step": 57778
    },
    {
      "epoch": 1.774920898227506,
      "grad_norm": 0.5511568188667297,
      "learning_rate": 6.205688340911664e-07,
      "loss": 0.4793,
      "step": 57779
    },
    {
      "epoch": 1.774951617362455,
      "grad_norm": 0.46347761154174805,
      "learning_rate": 6.204012497108014e-07,
      "loss": 0.4488,
      "step": 57780
    },
    {
      "epoch": 1.7749823364974042,
      "grad_norm": 0.46977949142456055,
      "learning_rate": 6.202336872371462e-07,
      "loss": 0.42,
      "step": 57781
    },
    {
      "epoch": 1.7750130556323533,
      "grad_norm": 0.461736261844635,
      "learning_rate": 6.200661466705893e-07,
      "loss": 0.429,
      "step": 57782
    },
    {
      "epoch": 1.7750437747673025,
      "grad_norm": 0.46807861328125,
      "learning_rate": 6.198986280115227e-07,
      "loss": 0.4233,
      "step": 57783
    },
    {
      "epoch": 1.7750744939022516,
      "grad_norm": 0.415508896112442,
      "learning_rate": 6.197311312603371e-07,
      "loss": 0.4931,
      "step": 57784
    },
    {
      "epoch": 1.775105213037201,
      "grad_norm": 0.5301908254623413,
      "learning_rate": 6.195636564174268e-07,
      "loss": 0.4696,
      "step": 57785
    },
    {
      "epoch": 1.77513593217215,
      "grad_norm": 0.39366447925567627,
      "learning_rate": 6.193962034831801e-07,
      "loss": 0.4659,
      "step": 57786
    },
    {
      "epoch": 1.7751666513070992,
      "grad_norm": 0.45493975281715393,
      "learning_rate": 6.19228772457987e-07,
      "loss": 0.5314,
      "step": 57787
    },
    {
      "epoch": 1.7751973704420485,
      "grad_norm": 0.4375220835208893,
      "learning_rate": 6.190613633422415e-07,
      "loss": 0.4906,
      "step": 57788
    },
    {
      "epoch": 1.7752280895769976,
      "grad_norm": 0.44140857458114624,
      "learning_rate": 6.188939761363322e-07,
      "loss": 0.5344,
      "step": 57789
    },
    {
      "epoch": 1.7752588087119467,
      "grad_norm": 0.43057385087013245,
      "learning_rate": 6.187266108406542e-07,
      "loss": 0.476,
      "step": 57790
    },
    {
      "epoch": 1.7752895278468959,
      "grad_norm": 0.45360755920410156,
      "learning_rate": 6.185592674555929e-07,
      "loss": 0.4976,
      "step": 57791
    },
    {
      "epoch": 1.775320246981845,
      "grad_norm": 0.4012910723686218,
      "learning_rate": 6.183919459815413e-07,
      "loss": 0.5032,
      "step": 57792
    },
    {
      "epoch": 1.775350966116794,
      "grad_norm": 0.4520249664783478,
      "learning_rate": 6.182246464188913e-07,
      "loss": 0.5459,
      "step": 57793
    },
    {
      "epoch": 1.7753816852517432,
      "grad_norm": 0.4219493269920349,
      "learning_rate": 6.180573687680336e-07,
      "loss": 0.4767,
      "step": 57794
    },
    {
      "epoch": 1.7754124043866923,
      "grad_norm": 0.46454155445098877,
      "learning_rate": 6.178901130293569e-07,
      "loss": 0.4692,
      "step": 57795
    },
    {
      "epoch": 1.7754431235216415,
      "grad_norm": 0.45577457547187805,
      "learning_rate": 6.17722879203253e-07,
      "loss": 0.4386,
      "step": 57796
    },
    {
      "epoch": 1.7754738426565908,
      "grad_norm": 0.4695127308368683,
      "learning_rate": 6.175556672901128e-07,
      "loss": 0.4981,
      "step": 57797
    },
    {
      "epoch": 1.77550456179154,
      "grad_norm": 0.446736603975296,
      "learning_rate": 6.173884772903282e-07,
      "loss": 0.4968,
      "step": 57798
    },
    {
      "epoch": 1.7755352809264893,
      "grad_norm": 0.40332597494125366,
      "learning_rate": 6.172213092042867e-07,
      "loss": 0.3827,
      "step": 57799
    },
    {
      "epoch": 1.7755660000614384,
      "grad_norm": 0.40672481060028076,
      "learning_rate": 6.170541630323812e-07,
      "loss": 0.4811,
      "step": 57800
    },
    {
      "epoch": 1.7755967191963875,
      "grad_norm": 0.47121521830558777,
      "learning_rate": 6.168870387749982e-07,
      "loss": 0.4779,
      "step": 57801
    },
    {
      "epoch": 1.7756274383313366,
      "grad_norm": 0.4199778437614441,
      "learning_rate": 6.167199364325338e-07,
      "loss": 0.4638,
      "step": 57802
    },
    {
      "epoch": 1.7756581574662857,
      "grad_norm": 0.4058956801891327,
      "learning_rate": 6.165528560053747e-07,
      "loss": 0.4886,
      "step": 57803
    },
    {
      "epoch": 1.7756888766012349,
      "grad_norm": 0.43887031078338623,
      "learning_rate": 6.163857974939113e-07,
      "loss": 0.4224,
      "step": 57804
    },
    {
      "epoch": 1.775719595736184,
      "grad_norm": 0.744831383228302,
      "learning_rate": 6.162187608985349e-07,
      "loss": 0.4904,
      "step": 57805
    },
    {
      "epoch": 1.775750314871133,
      "grad_norm": 0.45836642384529114,
      "learning_rate": 6.160517462196336e-07,
      "loss": 0.4024,
      "step": 57806
    },
    {
      "epoch": 1.7757810340060822,
      "grad_norm": 0.48606163263320923,
      "learning_rate": 6.158847534575985e-07,
      "loss": 0.4441,
      "step": 57807
    },
    {
      "epoch": 1.7758117531410316,
      "grad_norm": 0.5005627274513245,
      "learning_rate": 6.157177826128202e-07,
      "loss": 0.4668,
      "step": 57808
    },
    {
      "epoch": 1.7758424722759807,
      "grad_norm": 0.41733798384666443,
      "learning_rate": 6.155508336856908e-07,
      "loss": 0.4722,
      "step": 57809
    },
    {
      "epoch": 1.77587319141093,
      "grad_norm": 0.43170469999313354,
      "learning_rate": 6.153839066765954e-07,
      "loss": 0.469,
      "step": 57810
    },
    {
      "epoch": 1.7759039105458791,
      "grad_norm": 0.5018487572669983,
      "learning_rate": 6.152170015859271e-07,
      "loss": 0.5191,
      "step": 57811
    },
    {
      "epoch": 1.7759346296808283,
      "grad_norm": 0.4310957193374634,
      "learning_rate": 6.150501184140744e-07,
      "loss": 0.5315,
      "step": 57812
    },
    {
      "epoch": 1.7759653488157774,
      "grad_norm": 0.4043961465358734,
      "learning_rate": 6.148832571614294e-07,
      "loss": 0.5491,
      "step": 57813
    },
    {
      "epoch": 1.7759960679507265,
      "grad_norm": 0.411482036113739,
      "learning_rate": 6.147164178283782e-07,
      "loss": 0.4372,
      "step": 57814
    },
    {
      "epoch": 1.7760267870856756,
      "grad_norm": 0.4645078182220459,
      "learning_rate": 6.145496004153117e-07,
      "loss": 0.4065,
      "step": 57815
    },
    {
      "epoch": 1.7760575062206247,
      "grad_norm": 0.5558696985244751,
      "learning_rate": 6.143828049226208e-07,
      "loss": 0.4278,
      "step": 57816
    },
    {
      "epoch": 1.7760882253555739,
      "grad_norm": 0.4422607123851776,
      "learning_rate": 6.142160313506962e-07,
      "loss": 0.4557,
      "step": 57817
    },
    {
      "epoch": 1.776118944490523,
      "grad_norm": 0.5048535466194153,
      "learning_rate": 6.140492796999231e-07,
      "loss": 0.4524,
      "step": 57818
    },
    {
      "epoch": 1.7761496636254723,
      "grad_norm": 0.43598735332489014,
      "learning_rate": 6.138825499706935e-07,
      "loss": 0.4734,
      "step": 57819
    },
    {
      "epoch": 1.7761803827604215,
      "grad_norm": 0.3802355229854584,
      "learning_rate": 6.137158421633971e-07,
      "loss": 0.3548,
      "step": 57820
    },
    {
      "epoch": 1.7762111018953708,
      "grad_norm": 0.4809090495109558,
      "learning_rate": 6.135491562784246e-07,
      "loss": 0.4317,
      "step": 57821
    },
    {
      "epoch": 1.77624182103032,
      "grad_norm": 0.4405263364315033,
      "learning_rate": 6.133824923161624e-07,
      "loss": 0.4521,
      "step": 57822
    },
    {
      "epoch": 1.776272540165269,
      "grad_norm": 0.4284059405326843,
      "learning_rate": 6.132158502770002e-07,
      "loss": 0.4656,
      "step": 57823
    },
    {
      "epoch": 1.7763032593002182,
      "grad_norm": 0.42861002683639526,
      "learning_rate": 6.130492301613278e-07,
      "loss": 0.4716,
      "step": 57824
    },
    {
      "epoch": 1.7763339784351673,
      "grad_norm": 0.45185014605522156,
      "learning_rate": 6.128826319695369e-07,
      "loss": 0.4898,
      "step": 57825
    },
    {
      "epoch": 1.7763646975701164,
      "grad_norm": 0.4390445351600647,
      "learning_rate": 6.127160557020118e-07,
      "loss": 0.4545,
      "step": 57826
    },
    {
      "epoch": 1.7763954167050655,
      "grad_norm": 0.4672035574913025,
      "learning_rate": 6.125495013591443e-07,
      "loss": 0.4623,
      "step": 57827
    },
    {
      "epoch": 1.7764261358400146,
      "grad_norm": 0.4329315721988678,
      "learning_rate": 6.12382968941323e-07,
      "loss": 0.409,
      "step": 57828
    },
    {
      "epoch": 1.7764568549749638,
      "grad_norm": 0.5044680833816528,
      "learning_rate": 6.122164584489365e-07,
      "loss": 0.5042,
      "step": 57829
    },
    {
      "epoch": 1.776487574109913,
      "grad_norm": 0.4831595718860626,
      "learning_rate": 6.120499698823768e-07,
      "loss": 0.5172,
      "step": 57830
    },
    {
      "epoch": 1.7765182932448622,
      "grad_norm": 0.4971733093261719,
      "learning_rate": 6.118835032420278e-07,
      "loss": 0.414,
      "step": 57831
    },
    {
      "epoch": 1.7765490123798113,
      "grad_norm": 0.5183058977127075,
      "learning_rate": 6.117170585282817e-07,
      "loss": 0.4912,
      "step": 57832
    },
    {
      "epoch": 1.7765797315147607,
      "grad_norm": 0.45566698908805847,
      "learning_rate": 6.115506357415235e-07,
      "loss": 0.4169,
      "step": 57833
    },
    {
      "epoch": 1.7766104506497098,
      "grad_norm": 0.4094602167606354,
      "learning_rate": 6.113842348821475e-07,
      "loss": 0.4476,
      "step": 57834
    },
    {
      "epoch": 1.776641169784659,
      "grad_norm": 0.40346238017082214,
      "learning_rate": 6.112178559505378e-07,
      "loss": 0.4374,
      "step": 57835
    },
    {
      "epoch": 1.776671888919608,
      "grad_norm": 0.4484924376010895,
      "learning_rate": 6.110514989470862e-07,
      "loss": 0.4817,
      "step": 57836
    },
    {
      "epoch": 1.7767026080545572,
      "grad_norm": 0.47230005264282227,
      "learning_rate": 6.108851638721758e-07,
      "loss": 0.5705,
      "step": 57837
    },
    {
      "epoch": 1.7767333271895063,
      "grad_norm": 0.453874796628952,
      "learning_rate": 6.107188507262018e-07,
      "loss": 0.4681,
      "step": 57838
    },
    {
      "epoch": 1.7767640463244554,
      "grad_norm": 0.4072842001914978,
      "learning_rate": 6.105525595095496e-07,
      "loss": 0.3821,
      "step": 57839
    },
    {
      "epoch": 1.7767947654594045,
      "grad_norm": 0.40515315532684326,
      "learning_rate": 6.103862902226076e-07,
      "loss": 0.4241,
      "step": 57840
    },
    {
      "epoch": 1.7768254845943539,
      "grad_norm": 0.4054430425167084,
      "learning_rate": 6.102200428657635e-07,
      "loss": 0.4937,
      "step": 57841
    },
    {
      "epoch": 1.776856203729303,
      "grad_norm": 0.4584091305732727,
      "learning_rate": 6.100538174394055e-07,
      "loss": 0.5115,
      "step": 57842
    },
    {
      "epoch": 1.776886922864252,
      "grad_norm": 0.4255029261112213,
      "learning_rate": 6.098876139439236e-07,
      "loss": 0.436,
      "step": 57843
    },
    {
      "epoch": 1.7769176419992014,
      "grad_norm": 0.4578143060207367,
      "learning_rate": 6.09721432379704e-07,
      "loss": 0.4993,
      "step": 57844
    },
    {
      "epoch": 1.7769483611341506,
      "grad_norm": 0.43807852268218994,
      "learning_rate": 6.095552727471388e-07,
      "loss": 0.4417,
      "step": 57845
    },
    {
      "epoch": 1.7769790802690997,
      "grad_norm": 0.42659616470336914,
      "learning_rate": 6.093891350466097e-07,
      "loss": 0.4444,
      "step": 57846
    },
    {
      "epoch": 1.7770097994040488,
      "grad_norm": 0.4849850535392761,
      "learning_rate": 6.092230192785098e-07,
      "loss": 0.4836,
      "step": 57847
    },
    {
      "epoch": 1.777040518538998,
      "grad_norm": 0.42733123898506165,
      "learning_rate": 6.090569254432243e-07,
      "loss": 0.4971,
      "step": 57848
    },
    {
      "epoch": 1.777071237673947,
      "grad_norm": 0.4123203158378601,
      "learning_rate": 6.088908535411442e-07,
      "loss": 0.4311,
      "step": 57849
    },
    {
      "epoch": 1.7771019568088962,
      "grad_norm": 0.41107651591300964,
      "learning_rate": 6.087248035726534e-07,
      "loss": 0.4262,
      "step": 57850
    },
    {
      "epoch": 1.7771326759438453,
      "grad_norm": 0.4438038170337677,
      "learning_rate": 6.085587755381417e-07,
      "loss": 0.4204,
      "step": 57851
    },
    {
      "epoch": 1.7771633950787946,
      "grad_norm": 0.48627761006355286,
      "learning_rate": 6.083927694379977e-07,
      "loss": 0.3946,
      "step": 57852
    },
    {
      "epoch": 1.7771941142137437,
      "grad_norm": 0.4566037654876709,
      "learning_rate": 6.082267852726087e-07,
      "loss": 0.4156,
      "step": 57853
    },
    {
      "epoch": 1.7772248333486929,
      "grad_norm": 0.46074262261390686,
      "learning_rate": 6.080608230423612e-07,
      "loss": 0.499,
      "step": 57854
    },
    {
      "epoch": 1.7772555524836422,
      "grad_norm": 0.4064277112483978,
      "learning_rate": 6.078948827476439e-07,
      "loss": 0.3838,
      "step": 57855
    },
    {
      "epoch": 1.7772862716185913,
      "grad_norm": 0.4226544201374054,
      "learning_rate": 6.077289643888429e-07,
      "loss": 0.4429,
      "step": 57856
    },
    {
      "epoch": 1.7773169907535404,
      "grad_norm": 0.488105446100235,
      "learning_rate": 6.075630679663492e-07,
      "loss": 0.4252,
      "step": 57857
    },
    {
      "epoch": 1.7773477098884896,
      "grad_norm": 0.4645186960697174,
      "learning_rate": 6.073971934805456e-07,
      "loss": 0.4471,
      "step": 57858
    },
    {
      "epoch": 1.7773784290234387,
      "grad_norm": 0.43139493465423584,
      "learning_rate": 6.072313409318231e-07,
      "loss": 0.48,
      "step": 57859
    },
    {
      "epoch": 1.7774091481583878,
      "grad_norm": 0.46037107706069946,
      "learning_rate": 6.070655103205669e-07,
      "loss": 0.4826,
      "step": 57860
    },
    {
      "epoch": 1.777439867293337,
      "grad_norm": 0.41123685240745544,
      "learning_rate": 6.068997016471667e-07,
      "loss": 0.4685,
      "step": 57861
    },
    {
      "epoch": 1.777470586428286,
      "grad_norm": 0.4526835083961487,
      "learning_rate": 6.067339149120067e-07,
      "loss": 0.4191,
      "step": 57862
    },
    {
      "epoch": 1.7775013055632354,
      "grad_norm": 0.4019017219543457,
      "learning_rate": 6.065681501154763e-07,
      "loss": 0.4373,
      "step": 57863
    },
    {
      "epoch": 1.7775320246981845,
      "grad_norm": 0.41954144835472107,
      "learning_rate": 6.064024072579611e-07,
      "loss": 0.5022,
      "step": 57864
    },
    {
      "epoch": 1.7775627438331336,
      "grad_norm": 0.4366237223148346,
      "learning_rate": 6.062366863398506e-07,
      "loss": 0.5045,
      "step": 57865
    },
    {
      "epoch": 1.777593462968083,
      "grad_norm": 0.41338101029396057,
      "learning_rate": 6.060709873615301e-07,
      "loss": 0.4578,
      "step": 57866
    },
    {
      "epoch": 1.777624182103032,
      "grad_norm": 0.43600404262542725,
      "learning_rate": 6.05905310323387e-07,
      "loss": 0.4873,
      "step": 57867
    },
    {
      "epoch": 1.7776549012379812,
      "grad_norm": 0.4044072926044464,
      "learning_rate": 6.057396552258088e-07,
      "loss": 0.4339,
      "step": 57868
    },
    {
      "epoch": 1.7776856203729303,
      "grad_norm": 0.44588571786880493,
      "learning_rate": 6.055740220691786e-07,
      "loss": 0.4669,
      "step": 57869
    },
    {
      "epoch": 1.7777163395078794,
      "grad_norm": 0.44989028573036194,
      "learning_rate": 6.054084108538893e-07,
      "loss": 0.4556,
      "step": 57870
    },
    {
      "epoch": 1.7777470586428286,
      "grad_norm": 0.4294752776622772,
      "learning_rate": 6.05242821580323e-07,
      "loss": 0.5178,
      "step": 57871
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.4363967776298523,
      "learning_rate": 6.050772542488704e-07,
      "loss": 0.3936,
      "step": 57872
    },
    {
      "epoch": 1.7778084969127268,
      "grad_norm": 0.41827771067619324,
      "learning_rate": 6.049117088599143e-07,
      "loss": 0.4675,
      "step": 57873
    },
    {
      "epoch": 1.7778392160476761,
      "grad_norm": 0.4419071674346924,
      "learning_rate": 6.047461854138426e-07,
      "loss": 0.4852,
      "step": 57874
    },
    {
      "epoch": 1.7778699351826253,
      "grad_norm": 0.448449969291687,
      "learning_rate": 6.045806839110436e-07,
      "loss": 0.4245,
      "step": 57875
    },
    {
      "epoch": 1.7779006543175744,
      "grad_norm": 0.40761393308639526,
      "learning_rate": 6.044152043519025e-07,
      "loss": 0.4499,
      "step": 57876
    },
    {
      "epoch": 1.7779313734525237,
      "grad_norm": 0.434708833694458,
      "learning_rate": 6.042497467368058e-07,
      "loss": 0.5454,
      "step": 57877
    },
    {
      "epoch": 1.7779620925874728,
      "grad_norm": 0.44902801513671875,
      "learning_rate": 6.040843110661388e-07,
      "loss": 0.5023,
      "step": 57878
    },
    {
      "epoch": 1.777992811722422,
      "grad_norm": 0.43791067600250244,
      "learning_rate": 6.039188973402899e-07,
      "loss": 0.5412,
      "step": 57879
    },
    {
      "epoch": 1.778023530857371,
      "grad_norm": 0.39468497037887573,
      "learning_rate": 6.037535055596455e-07,
      "loss": 0.4665,
      "step": 57880
    },
    {
      "epoch": 1.7780542499923202,
      "grad_norm": 0.4267958402633667,
      "learning_rate": 6.035881357245899e-07,
      "loss": 0.489,
      "step": 57881
    },
    {
      "epoch": 1.7780849691272693,
      "grad_norm": 0.4358004331588745,
      "learning_rate": 6.034227878355103e-07,
      "loss": 0.4947,
      "step": 57882
    },
    {
      "epoch": 1.7781156882622184,
      "grad_norm": 0.47755542397499084,
      "learning_rate": 6.032574618927933e-07,
      "loss": 0.478,
      "step": 57883
    },
    {
      "epoch": 1.7781464073971676,
      "grad_norm": 0.4829464554786682,
      "learning_rate": 6.030921578968252e-07,
      "loss": 0.4731,
      "step": 57884
    },
    {
      "epoch": 1.778177126532117,
      "grad_norm": 0.4734439551830292,
      "learning_rate": 6.029268758479923e-07,
      "loss": 0.4267,
      "step": 57885
    },
    {
      "epoch": 1.778207845667066,
      "grad_norm": 0.43490806221961975,
      "learning_rate": 6.027616157466787e-07,
      "loss": 0.5454,
      "step": 57886
    },
    {
      "epoch": 1.7782385648020151,
      "grad_norm": 0.5154357552528381,
      "learning_rate": 6.02596377593272e-07,
      "loss": 0.4988,
      "step": 57887
    },
    {
      "epoch": 1.7782692839369645,
      "grad_norm": 0.4384239912033081,
      "learning_rate": 6.024311613881573e-07,
      "loss": 0.4463,
      "step": 57888
    },
    {
      "epoch": 1.7783000030719136,
      "grad_norm": 0.47690415382385254,
      "learning_rate": 6.022659671317221e-07,
      "loss": 0.5128,
      "step": 57889
    },
    {
      "epoch": 1.7783307222068627,
      "grad_norm": 0.4459885060787201,
      "learning_rate": 6.021007948243496e-07,
      "loss": 0.4532,
      "step": 57890
    },
    {
      "epoch": 1.7783614413418118,
      "grad_norm": 0.412355899810791,
      "learning_rate": 6.019356444664281e-07,
      "loss": 0.432,
      "step": 57891
    },
    {
      "epoch": 1.778392160476761,
      "grad_norm": 0.49447980523109436,
      "learning_rate": 6.017705160583409e-07,
      "loss": 0.4531,
      "step": 57892
    },
    {
      "epoch": 1.77842287961171,
      "grad_norm": 0.47012218832969666,
      "learning_rate": 6.016054096004776e-07,
      "loss": 0.5102,
      "step": 57893
    },
    {
      "epoch": 1.7784535987466592,
      "grad_norm": 0.42753082513809204,
      "learning_rate": 6.014403250932199e-07,
      "loss": 0.4098,
      "step": 57894
    },
    {
      "epoch": 1.7784843178816083,
      "grad_norm": 0.45266667008399963,
      "learning_rate": 6.012752625369556e-07,
      "loss": 0.4843,
      "step": 57895
    },
    {
      "epoch": 1.7785150370165577,
      "grad_norm": 0.4505349099636078,
      "learning_rate": 6.011102219320663e-07,
      "loss": 0.4781,
      "step": 57896
    },
    {
      "epoch": 1.7785457561515068,
      "grad_norm": 0.40967637300491333,
      "learning_rate": 6.009452032789431e-07,
      "loss": 0.4118,
      "step": 57897
    },
    {
      "epoch": 1.778576475286456,
      "grad_norm": 0.47650548815727234,
      "learning_rate": 6.007802065779678e-07,
      "loss": 0.5095,
      "step": 57898
    },
    {
      "epoch": 1.7786071944214052,
      "grad_norm": 0.4433516263961792,
      "learning_rate": 6.006152318295267e-07,
      "loss": 0.5202,
      "step": 57899
    },
    {
      "epoch": 1.7786379135563544,
      "grad_norm": 0.43094268441200256,
      "learning_rate": 6.004502790340061e-07,
      "loss": 0.4483,
      "step": 57900
    },
    {
      "epoch": 1.7786686326913035,
      "grad_norm": 0.4301724135875702,
      "learning_rate": 6.002853481917892e-07,
      "loss": 0.462,
      "step": 57901
    },
    {
      "epoch": 1.7786993518262526,
      "grad_norm": 0.472819447517395,
      "learning_rate": 6.001204393032633e-07,
      "loss": 0.5071,
      "step": 57902
    },
    {
      "epoch": 1.7787300709612017,
      "grad_norm": 0.45321789383888245,
      "learning_rate": 5.999555523688127e-07,
      "loss": 0.4457,
      "step": 57903
    },
    {
      "epoch": 1.7787607900961508,
      "grad_norm": 0.43074414134025574,
      "learning_rate": 5.997906873888226e-07,
      "loss": 0.4303,
      "step": 57904
    },
    {
      "epoch": 1.7787915092311,
      "grad_norm": 0.4441520869731903,
      "learning_rate": 5.99625844363676e-07,
      "loss": 0.4535,
      "step": 57905
    },
    {
      "epoch": 1.778822228366049,
      "grad_norm": 0.43250906467437744,
      "learning_rate": 5.994610232937614e-07,
      "loss": 0.4573,
      "step": 57906
    },
    {
      "epoch": 1.7788529475009984,
      "grad_norm": 0.4298914074897766,
      "learning_rate": 5.99296224179462e-07,
      "loss": 0.4063,
      "step": 57907
    },
    {
      "epoch": 1.7788836666359475,
      "grad_norm": 0.40182241797447205,
      "learning_rate": 5.991314470211629e-07,
      "loss": 0.443,
      "step": 57908
    },
    {
      "epoch": 1.7789143857708967,
      "grad_norm": 0.4716414213180542,
      "learning_rate": 5.989666918192482e-07,
      "loss": 0.513,
      "step": 57909
    },
    {
      "epoch": 1.778945104905846,
      "grad_norm": 0.44015875458717346,
      "learning_rate": 5.988019585741034e-07,
      "loss": 0.6018,
      "step": 57910
    },
    {
      "epoch": 1.7789758240407951,
      "grad_norm": 0.41660597920417786,
      "learning_rate": 5.986372472861135e-07,
      "loss": 0.4784,
      "step": 57911
    },
    {
      "epoch": 1.7790065431757442,
      "grad_norm": 0.4293546676635742,
      "learning_rate": 5.984725579556638e-07,
      "loss": 0.4597,
      "step": 57912
    },
    {
      "epoch": 1.7790372623106934,
      "grad_norm": 0.5011656284332275,
      "learning_rate": 5.983078905831363e-07,
      "loss": 0.4951,
      "step": 57913
    },
    {
      "epoch": 1.7790679814456425,
      "grad_norm": 0.4155772626399994,
      "learning_rate": 5.981432451689173e-07,
      "loss": 0.4917,
      "step": 57914
    },
    {
      "epoch": 1.7790987005805916,
      "grad_norm": 0.4163999855518341,
      "learning_rate": 5.979786217133921e-07,
      "loss": 0.4219,
      "step": 57915
    },
    {
      "epoch": 1.7791294197155407,
      "grad_norm": 0.49089309573173523,
      "learning_rate": 5.978140202169458e-07,
      "loss": 0.4358,
      "step": 57916
    },
    {
      "epoch": 1.7791601388504898,
      "grad_norm": 0.4268231689929962,
      "learning_rate": 5.976494406799593e-07,
      "loss": 0.396,
      "step": 57917
    },
    {
      "epoch": 1.779190857985439,
      "grad_norm": 0.4412211775779724,
      "learning_rate": 5.974848831028202e-07,
      "loss": 0.4581,
      "step": 57918
    },
    {
      "epoch": 1.7792215771203883,
      "grad_norm": 0.47429460287094116,
      "learning_rate": 5.973203474859112e-07,
      "loss": 0.4581,
      "step": 57919
    },
    {
      "epoch": 1.7792522962553374,
      "grad_norm": 0.3899681270122528,
      "learning_rate": 5.971558338296168e-07,
      "loss": 0.4569,
      "step": 57920
    },
    {
      "epoch": 1.7792830153902868,
      "grad_norm": 0.5238190293312073,
      "learning_rate": 5.969913421343243e-07,
      "loss": 0.5016,
      "step": 57921
    },
    {
      "epoch": 1.779313734525236,
      "grad_norm": 0.40141913294792175,
      "learning_rate": 5.968268724004123e-07,
      "loss": 0.4919,
      "step": 57922
    },
    {
      "epoch": 1.779344453660185,
      "grad_norm": 0.44095537066459656,
      "learning_rate": 5.966624246282693e-07,
      "loss": 0.4201,
      "step": 57923
    },
    {
      "epoch": 1.7793751727951341,
      "grad_norm": 0.48377078771591187,
      "learning_rate": 5.964979988182773e-07,
      "loss": 0.4547,
      "step": 57924
    },
    {
      "epoch": 1.7794058919300832,
      "grad_norm": 0.41140201687812805,
      "learning_rate": 5.963335949708215e-07,
      "loss": 0.4242,
      "step": 57925
    },
    {
      "epoch": 1.7794366110650324,
      "grad_norm": 0.40943199396133423,
      "learning_rate": 5.96169213086285e-07,
      "loss": 0.3936,
      "step": 57926
    },
    {
      "epoch": 1.7794673301999815,
      "grad_norm": 0.46619680523872375,
      "learning_rate": 5.96004853165052e-07,
      "loss": 0.5783,
      "step": 57927
    },
    {
      "epoch": 1.7794980493349306,
      "grad_norm": 0.4392932653427124,
      "learning_rate": 5.958405152075064e-07,
      "loss": 0.463,
      "step": 57928
    },
    {
      "epoch": 1.7795287684698797,
      "grad_norm": 0.4304400384426117,
      "learning_rate": 5.956761992140336e-07,
      "loss": 0.4683,
      "step": 57929
    },
    {
      "epoch": 1.779559487604829,
      "grad_norm": 0.4513247311115265,
      "learning_rate": 5.955119051850133e-07,
      "loss": 0.4187,
      "step": 57930
    },
    {
      "epoch": 1.7795902067397782,
      "grad_norm": 0.40556225180625916,
      "learning_rate": 5.95347633120834e-07,
      "loss": 0.442,
      "step": 57931
    },
    {
      "epoch": 1.7796209258747275,
      "grad_norm": 0.4601351320743561,
      "learning_rate": 5.951833830218745e-07,
      "loss": 0.4426,
      "step": 57932
    },
    {
      "epoch": 1.7796516450096767,
      "grad_norm": 0.42886289954185486,
      "learning_rate": 5.950191548885243e-07,
      "loss": 0.5341,
      "step": 57933
    },
    {
      "epoch": 1.7796823641446258,
      "grad_norm": 0.618423581123352,
      "learning_rate": 5.948549487211607e-07,
      "loss": 0.5087,
      "step": 57934
    },
    {
      "epoch": 1.779713083279575,
      "grad_norm": 0.48812881112098694,
      "learning_rate": 5.946907645201716e-07,
      "loss": 0.4815,
      "step": 57935
    },
    {
      "epoch": 1.779743802414524,
      "grad_norm": 0.4198748469352722,
      "learning_rate": 5.945266022859387e-07,
      "loss": 0.4441,
      "step": 57936
    },
    {
      "epoch": 1.7797745215494731,
      "grad_norm": 0.4315296411514282,
      "learning_rate": 5.943624620188459e-07,
      "loss": 0.4432,
      "step": 57937
    },
    {
      "epoch": 1.7798052406844223,
      "grad_norm": 0.3996214270591736,
      "learning_rate": 5.941983437192778e-07,
      "loss": 0.3743,
      "step": 57938
    },
    {
      "epoch": 1.7798359598193714,
      "grad_norm": 0.4597128927707672,
      "learning_rate": 5.940342473876149e-07,
      "loss": 0.4795,
      "step": 57939
    },
    {
      "epoch": 1.7798666789543205,
      "grad_norm": 0.4779362082481384,
      "learning_rate": 5.938701730242425e-07,
      "loss": 0.4123,
      "step": 57940
    },
    {
      "epoch": 1.7798973980892698,
      "grad_norm": 0.5485880970954895,
      "learning_rate": 5.937061206295414e-07,
      "loss": 0.4415,
      "step": 57941
    },
    {
      "epoch": 1.779928117224219,
      "grad_norm": 0.4146205484867096,
      "learning_rate": 5.935420902038991e-07,
      "loss": 0.5107,
      "step": 57942
    },
    {
      "epoch": 1.779958836359168,
      "grad_norm": 0.5159950852394104,
      "learning_rate": 5.933780817476953e-07,
      "loss": 0.4101,
      "step": 57943
    },
    {
      "epoch": 1.7799895554941174,
      "grad_norm": 0.4563440978527069,
      "learning_rate": 5.932140952613141e-07,
      "loss": 0.4518,
      "step": 57944
    },
    {
      "epoch": 1.7800202746290665,
      "grad_norm": 0.42599982023239136,
      "learning_rate": 5.930501307451386e-07,
      "loss": 0.5085,
      "step": 57945
    },
    {
      "epoch": 1.7800509937640157,
      "grad_norm": 0.4729178547859192,
      "learning_rate": 5.928861881995506e-07,
      "loss": 0.4184,
      "step": 57946
    },
    {
      "epoch": 1.7800817128989648,
      "grad_norm": 0.4362854063510895,
      "learning_rate": 5.927222676249333e-07,
      "loss": 0.4142,
      "step": 57947
    },
    {
      "epoch": 1.780112432033914,
      "grad_norm": 0.4811221957206726,
      "learning_rate": 5.925583690216719e-07,
      "loss": 0.5317,
      "step": 57948
    },
    {
      "epoch": 1.780143151168863,
      "grad_norm": 0.4916437566280365,
      "learning_rate": 5.92394492390147e-07,
      "loss": 0.4304,
      "step": 57949
    },
    {
      "epoch": 1.7801738703038121,
      "grad_norm": 0.40077441930770874,
      "learning_rate": 5.922306377307407e-07,
      "loss": 0.4498,
      "step": 57950
    },
    {
      "epoch": 1.7802045894387613,
      "grad_norm": 0.4622233808040619,
      "learning_rate": 5.920668050438372e-07,
      "loss": 0.4555,
      "step": 57951
    },
    {
      "epoch": 1.7802353085737106,
      "grad_norm": 0.4294734597206116,
      "learning_rate": 5.919029943298205e-07,
      "loss": 0.5044,
      "step": 57952
    },
    {
      "epoch": 1.7802660277086597,
      "grad_norm": 0.46247225999832153,
      "learning_rate": 5.917392055890692e-07,
      "loss": 0.4836,
      "step": 57953
    },
    {
      "epoch": 1.7802967468436088,
      "grad_norm": 0.43437230587005615,
      "learning_rate": 5.915754388219685e-07,
      "loss": 0.4564,
      "step": 57954
    },
    {
      "epoch": 1.7803274659785582,
      "grad_norm": 0.4204217195510864,
      "learning_rate": 5.914116940289005e-07,
      "loss": 0.4486,
      "step": 57955
    },
    {
      "epoch": 1.7803581851135073,
      "grad_norm": 0.4361310303211212,
      "learning_rate": 5.91247971210247e-07,
      "loss": 0.4745,
      "step": 57956
    },
    {
      "epoch": 1.7803889042484564,
      "grad_norm": 0.541179895401001,
      "learning_rate": 5.910842703663933e-07,
      "loss": 0.4573,
      "step": 57957
    },
    {
      "epoch": 1.7804196233834055,
      "grad_norm": 0.45994889736175537,
      "learning_rate": 5.909205914977167e-07,
      "loss": 0.4743,
      "step": 57958
    },
    {
      "epoch": 1.7804503425183547,
      "grad_norm": 0.4310164749622345,
      "learning_rate": 5.907569346046038e-07,
      "loss": 0.5052,
      "step": 57959
    },
    {
      "epoch": 1.7804810616533038,
      "grad_norm": 0.4054105281829834,
      "learning_rate": 5.905932996874342e-07,
      "loss": 0.4801,
      "step": 57960
    },
    {
      "epoch": 1.780511780788253,
      "grad_norm": 0.43416160345077515,
      "learning_rate": 5.90429686746593e-07,
      "loss": 0.422,
      "step": 57961
    },
    {
      "epoch": 1.780542499923202,
      "grad_norm": 0.47957971692085266,
      "learning_rate": 5.902660957824579e-07,
      "loss": 0.4776,
      "step": 57962
    },
    {
      "epoch": 1.7805732190581514,
      "grad_norm": 0.4545980989933014,
      "learning_rate": 5.901025267954152e-07,
      "loss": 0.4608,
      "step": 57963
    },
    {
      "epoch": 1.7806039381931005,
      "grad_norm": 0.45175230503082275,
      "learning_rate": 5.899389797858435e-07,
      "loss": 0.4009,
      "step": 57964
    },
    {
      "epoch": 1.7806346573280496,
      "grad_norm": 0.4242401421070099,
      "learning_rate": 5.897754547541291e-07,
      "loss": 0.4582,
      "step": 57965
    },
    {
      "epoch": 1.780665376462999,
      "grad_norm": 0.44766247272491455,
      "learning_rate": 5.896119517006493e-07,
      "loss": 0.5202,
      "step": 57966
    },
    {
      "epoch": 1.780696095597948,
      "grad_norm": 0.4829397201538086,
      "learning_rate": 5.894484706257897e-07,
      "loss": 0.5164,
      "step": 57967
    },
    {
      "epoch": 1.7807268147328972,
      "grad_norm": 0.40656667947769165,
      "learning_rate": 5.892850115299276e-07,
      "loss": 0.3697,
      "step": 57968
    },
    {
      "epoch": 1.7807575338678463,
      "grad_norm": 0.48646971583366394,
      "learning_rate": 5.891215744134505e-07,
      "loss": 0.5234,
      "step": 57969
    },
    {
      "epoch": 1.7807882530027954,
      "grad_norm": 0.4805198609828949,
      "learning_rate": 5.889581592767358e-07,
      "loss": 0.5016,
      "step": 57970
    },
    {
      "epoch": 1.7808189721377445,
      "grad_norm": 0.49612826108932495,
      "learning_rate": 5.887947661201677e-07,
      "loss": 0.4442,
      "step": 57971
    },
    {
      "epoch": 1.7808496912726937,
      "grad_norm": 0.4395706355571747,
      "learning_rate": 5.886313949441258e-07,
      "loss": 0.4135,
      "step": 57972
    },
    {
      "epoch": 1.7808804104076428,
      "grad_norm": 0.42698317766189575,
      "learning_rate": 5.884680457489911e-07,
      "loss": 0.4782,
      "step": 57973
    },
    {
      "epoch": 1.7809111295425921,
      "grad_norm": 0.4166032075881958,
      "learning_rate": 5.883047185351486e-07,
      "loss": 0.4166,
      "step": 57974
    },
    {
      "epoch": 1.7809418486775412,
      "grad_norm": 0.46645858883857727,
      "learning_rate": 5.881414133029772e-07,
      "loss": 0.4711,
      "step": 57975
    },
    {
      "epoch": 1.7809725678124904,
      "grad_norm": 0.4045431613922119,
      "learning_rate": 5.879781300528597e-07,
      "loss": 0.4036,
      "step": 57976
    },
    {
      "epoch": 1.7810032869474397,
      "grad_norm": 0.41369742155075073,
      "learning_rate": 5.878148687851737e-07,
      "loss": 0.4706,
      "step": 57977
    },
    {
      "epoch": 1.7810340060823888,
      "grad_norm": 0.422209769487381,
      "learning_rate": 5.876516295003066e-07,
      "loss": 0.4712,
      "step": 57978
    },
    {
      "epoch": 1.781064725217338,
      "grad_norm": 0.395397812128067,
      "learning_rate": 5.874884121986358e-07,
      "loss": 0.4169,
      "step": 57979
    },
    {
      "epoch": 1.781095444352287,
      "grad_norm": 0.43743234872817993,
      "learning_rate": 5.873252168805432e-07,
      "loss": 0.3538,
      "step": 57980
    },
    {
      "epoch": 1.7811261634872362,
      "grad_norm": 0.44376200437545776,
      "learning_rate": 5.871620435464087e-07,
      "loss": 0.4764,
      "step": 57981
    },
    {
      "epoch": 1.7811568826221853,
      "grad_norm": 0.44312748312950134,
      "learning_rate": 5.869988921966153e-07,
      "loss": 0.4755,
      "step": 57982
    },
    {
      "epoch": 1.7811876017571344,
      "grad_norm": 0.3905088007450104,
      "learning_rate": 5.868357628315435e-07,
      "loss": 0.484,
      "step": 57983
    },
    {
      "epoch": 1.7812183208920835,
      "grad_norm": 0.42212021350860596,
      "learning_rate": 5.866726554515745e-07,
      "loss": 0.4714,
      "step": 57984
    },
    {
      "epoch": 1.7812490400270329,
      "grad_norm": 0.43560361862182617,
      "learning_rate": 5.865095700570889e-07,
      "loss": 0.5103,
      "step": 57985
    },
    {
      "epoch": 1.781279759161982,
      "grad_norm": 0.4248979091644287,
      "learning_rate": 5.863465066484663e-07,
      "loss": 0.4915,
      "step": 57986
    },
    {
      "epoch": 1.7813104782969311,
      "grad_norm": 0.5204079747200012,
      "learning_rate": 5.861834652260901e-07,
      "loss": 0.534,
      "step": 57987
    },
    {
      "epoch": 1.7813411974318805,
      "grad_norm": 0.4240981936454773,
      "learning_rate": 5.860204457903406e-07,
      "loss": 0.5224,
      "step": 57988
    },
    {
      "epoch": 1.7813719165668296,
      "grad_norm": 0.4362685978412628,
      "learning_rate": 5.858574483415968e-07,
      "loss": 0.5863,
      "step": 57989
    },
    {
      "epoch": 1.7814026357017787,
      "grad_norm": 0.45022714138031006,
      "learning_rate": 5.856944728802394e-07,
      "loss": 0.4918,
      "step": 57990
    },
    {
      "epoch": 1.7814333548367278,
      "grad_norm": 0.43414852023124695,
      "learning_rate": 5.855315194066513e-07,
      "loss": 0.5135,
      "step": 57991
    },
    {
      "epoch": 1.781464073971677,
      "grad_norm": 0.4568381905555725,
      "learning_rate": 5.853685879212112e-07,
      "loss": 0.4593,
      "step": 57992
    },
    {
      "epoch": 1.781494793106626,
      "grad_norm": 0.4710228145122528,
      "learning_rate": 5.852056784243021e-07,
      "loss": 0.4724,
      "step": 57993
    },
    {
      "epoch": 1.7815255122415752,
      "grad_norm": 0.46427351236343384,
      "learning_rate": 5.850427909163003e-07,
      "loss": 0.3855,
      "step": 57994
    },
    {
      "epoch": 1.7815562313765243,
      "grad_norm": 0.4793063700199127,
      "learning_rate": 5.848799253975889e-07,
      "loss": 0.4816,
      "step": 57995
    },
    {
      "epoch": 1.7815869505114736,
      "grad_norm": 0.4357268512248993,
      "learning_rate": 5.847170818685488e-07,
      "loss": 0.4739,
      "step": 57996
    },
    {
      "epoch": 1.7816176696464228,
      "grad_norm": 0.41832804679870605,
      "learning_rate": 5.845542603295607e-07,
      "loss": 0.4689,
      "step": 57997
    },
    {
      "epoch": 1.7816483887813719,
      "grad_norm": 0.4105675220489502,
      "learning_rate": 5.84391460781002e-07,
      "loss": 0.4861,
      "step": 57998
    },
    {
      "epoch": 1.7816791079163212,
      "grad_norm": 0.42269420623779297,
      "learning_rate": 5.842286832232546e-07,
      "loss": 0.4608,
      "step": 57999
    },
    {
      "epoch": 1.7817098270512703,
      "grad_norm": 0.41836321353912354,
      "learning_rate": 5.840659276566984e-07,
      "loss": 0.5136,
      "step": 58000
    },
    {
      "epoch": 1.7817405461862195,
      "grad_norm": 0.523002028465271,
      "learning_rate": 5.839031940817153e-07,
      "loss": 0.4597,
      "step": 58001
    },
    {
      "epoch": 1.7817712653211686,
      "grad_norm": 0.4381840229034424,
      "learning_rate": 5.837404824986837e-07,
      "loss": 0.5123,
      "step": 58002
    },
    {
      "epoch": 1.7818019844561177,
      "grad_norm": 0.42206984758377075,
      "learning_rate": 5.835777929079833e-07,
      "loss": 0.4597,
      "step": 58003
    },
    {
      "epoch": 1.7818327035910668,
      "grad_norm": 0.46994420886039734,
      "learning_rate": 5.834151253099929e-07,
      "loss": 0.4692,
      "step": 58004
    },
    {
      "epoch": 1.781863422726016,
      "grad_norm": 0.4882892072200775,
      "learning_rate": 5.832524797050976e-07,
      "loss": 0.5165,
      "step": 58005
    },
    {
      "epoch": 1.781894141860965,
      "grad_norm": 0.4660985469818115,
      "learning_rate": 5.830898560936715e-07,
      "loss": 0.4207,
      "step": 58006
    },
    {
      "epoch": 1.7819248609959144,
      "grad_norm": 0.4013257920742035,
      "learning_rate": 5.829272544760978e-07,
      "loss": 0.4802,
      "step": 58007
    },
    {
      "epoch": 1.7819555801308635,
      "grad_norm": 0.3847968280315399,
      "learning_rate": 5.827646748527538e-07,
      "loss": 0.409,
      "step": 58008
    },
    {
      "epoch": 1.7819862992658126,
      "grad_norm": 0.45101869106292725,
      "learning_rate": 5.826021172240204e-07,
      "loss": 0.4776,
      "step": 58009
    },
    {
      "epoch": 1.782017018400762,
      "grad_norm": 0.4285905063152313,
      "learning_rate": 5.824395815902795e-07,
      "loss": 0.4502,
      "step": 58010
    },
    {
      "epoch": 1.782047737535711,
      "grad_norm": 0.4093257784843445,
      "learning_rate": 5.822770679519063e-07,
      "loss": 0.4766,
      "step": 58011
    },
    {
      "epoch": 1.7820784566706602,
      "grad_norm": 0.46618229150772095,
      "learning_rate": 5.821145763092862e-07,
      "loss": 0.4693,
      "step": 58012
    },
    {
      "epoch": 1.7821091758056093,
      "grad_norm": 0.49434348940849304,
      "learning_rate": 5.81952106662792e-07,
      "loss": 0.4728,
      "step": 58013
    },
    {
      "epoch": 1.7821398949405585,
      "grad_norm": 0.4009602963924408,
      "learning_rate": 5.817896590128069e-07,
      "loss": 0.5083,
      "step": 58014
    },
    {
      "epoch": 1.7821706140755076,
      "grad_norm": 0.45377737283706665,
      "learning_rate": 5.816272333597106e-07,
      "loss": 0.5308,
      "step": 58015
    },
    {
      "epoch": 1.7822013332104567,
      "grad_norm": 0.4272206425666809,
      "learning_rate": 5.814648297038816e-07,
      "loss": 0.443,
      "step": 58016
    },
    {
      "epoch": 1.7822320523454058,
      "grad_norm": 0.4239966571331024,
      "learning_rate": 5.813024480456997e-07,
      "loss": 0.4588,
      "step": 58017
    },
    {
      "epoch": 1.7822627714803552,
      "grad_norm": 0.4738897383213043,
      "learning_rate": 5.811400883855423e-07,
      "loss": 0.4438,
      "step": 58018
    },
    {
      "epoch": 1.7822934906153043,
      "grad_norm": 0.41835689544677734,
      "learning_rate": 5.809777507237902e-07,
      "loss": 0.414,
      "step": 58019
    },
    {
      "epoch": 1.7823242097502534,
      "grad_norm": 0.4564889669418335,
      "learning_rate": 5.808154350608242e-07,
      "loss": 0.5595,
      "step": 58020
    },
    {
      "epoch": 1.7823549288852027,
      "grad_norm": 0.4149115979671478,
      "learning_rate": 5.806531413970207e-07,
      "loss": 0.4655,
      "step": 58021
    },
    {
      "epoch": 1.7823856480201519,
      "grad_norm": 0.47036314010620117,
      "learning_rate": 5.804908697327583e-07,
      "loss": 0.5116,
      "step": 58022
    },
    {
      "epoch": 1.782416367155101,
      "grad_norm": 0.4275541305541992,
      "learning_rate": 5.803286200684188e-07,
      "loss": 0.4517,
      "step": 58023
    },
    {
      "epoch": 1.78244708629005,
      "grad_norm": 0.4422912001609802,
      "learning_rate": 5.801663924043799e-07,
      "loss": 0.5899,
      "step": 58024
    },
    {
      "epoch": 1.7824778054249992,
      "grad_norm": 0.4383058249950409,
      "learning_rate": 5.800041867410188e-07,
      "loss": 0.5119,
      "step": 58025
    },
    {
      "epoch": 1.7825085245599483,
      "grad_norm": 0.7036313414573669,
      "learning_rate": 5.798420030787166e-07,
      "loss": 0.493,
      "step": 58026
    },
    {
      "epoch": 1.7825392436948975,
      "grad_norm": 0.41979315876960754,
      "learning_rate": 5.796798414178506e-07,
      "loss": 0.4918,
      "step": 58027
    },
    {
      "epoch": 1.7825699628298466,
      "grad_norm": 0.4292510151863098,
      "learning_rate": 5.795177017588006e-07,
      "loss": 0.466,
      "step": 58028
    },
    {
      "epoch": 1.7826006819647957,
      "grad_norm": 0.45712536573410034,
      "learning_rate": 5.793555841019471e-07,
      "loss": 0.4368,
      "step": 58029
    },
    {
      "epoch": 1.782631401099745,
      "grad_norm": 0.4271269738674164,
      "learning_rate": 5.791934884476636e-07,
      "loss": 0.4499,
      "step": 58030
    },
    {
      "epoch": 1.7826621202346942,
      "grad_norm": 0.4282250702381134,
      "learning_rate": 5.790314147963327e-07,
      "loss": 0.4665,
      "step": 58031
    },
    {
      "epoch": 1.7826928393696435,
      "grad_norm": 0.44528013467788696,
      "learning_rate": 5.788693631483322e-07,
      "loss": 0.456,
      "step": 58032
    },
    {
      "epoch": 1.7827235585045926,
      "grad_norm": 0.42252346873283386,
      "learning_rate": 5.787073335040405e-07,
      "loss": 0.4882,
      "step": 58033
    },
    {
      "epoch": 1.7827542776395418,
      "grad_norm": 0.4572623670101166,
      "learning_rate": 5.785453258638352e-07,
      "loss": 0.4322,
      "step": 58034
    },
    {
      "epoch": 1.7827849967744909,
      "grad_norm": 0.43129757046699524,
      "learning_rate": 5.783833402280969e-07,
      "loss": 0.4159,
      "step": 58035
    },
    {
      "epoch": 1.78281571590944,
      "grad_norm": 0.47688308358192444,
      "learning_rate": 5.78221376597199e-07,
      "loss": 0.4058,
      "step": 58036
    },
    {
      "epoch": 1.782846435044389,
      "grad_norm": 0.45928284525871277,
      "learning_rate": 5.780594349715251e-07,
      "loss": 0.4751,
      "step": 58037
    },
    {
      "epoch": 1.7828771541793382,
      "grad_norm": 0.46310922503471375,
      "learning_rate": 5.77897515351451e-07,
      "loss": 0.4231,
      "step": 58038
    },
    {
      "epoch": 1.7829078733142874,
      "grad_norm": 0.44203653931617737,
      "learning_rate": 5.777356177373572e-07,
      "loss": 0.3863,
      "step": 58039
    },
    {
      "epoch": 1.7829385924492365,
      "grad_norm": 0.4907090961933136,
      "learning_rate": 5.775737421296157e-07,
      "loss": 0.4483,
      "step": 58040
    },
    {
      "epoch": 1.7829693115841858,
      "grad_norm": 0.4607195556163788,
      "learning_rate": 5.774118885286128e-07,
      "loss": 0.4993,
      "step": 58041
    },
    {
      "epoch": 1.783000030719135,
      "grad_norm": 0.4649663269519806,
      "learning_rate": 5.772500569347206e-07,
      "loss": 0.5295,
      "step": 58042
    },
    {
      "epoch": 1.7830307498540843,
      "grad_norm": 0.4834159314632416,
      "learning_rate": 5.770882473483208e-07,
      "loss": 0.4564,
      "step": 58043
    },
    {
      "epoch": 1.7830614689890334,
      "grad_norm": 0.6555103063583374,
      "learning_rate": 5.769264597697877e-07,
      "loss": 0.4985,
      "step": 58044
    },
    {
      "epoch": 1.7830921881239825,
      "grad_norm": 0.5803012847900391,
      "learning_rate": 5.767646941994987e-07,
      "loss": 0.4775,
      "step": 58045
    },
    {
      "epoch": 1.7831229072589316,
      "grad_norm": 0.44356200098991394,
      "learning_rate": 5.766029506378379e-07,
      "loss": 0.4867,
      "step": 58046
    },
    {
      "epoch": 1.7831536263938808,
      "grad_norm": 0.4609912633895874,
      "learning_rate": 5.764412290851773e-07,
      "loss": 0.5322,
      "step": 58047
    },
    {
      "epoch": 1.7831843455288299,
      "grad_norm": 0.5763239860534668,
      "learning_rate": 5.762795295418976e-07,
      "loss": 0.3799,
      "step": 58048
    },
    {
      "epoch": 1.783215064663779,
      "grad_norm": 0.390243262052536,
      "learning_rate": 5.761178520083743e-07,
      "loss": 0.4584,
      "step": 58049
    },
    {
      "epoch": 1.7832457837987281,
      "grad_norm": 0.5548555850982666,
      "learning_rate": 5.759561964849847e-07,
      "loss": 0.4489,
      "step": 58050
    },
    {
      "epoch": 1.7832765029336772,
      "grad_norm": 0.4338541030883789,
      "learning_rate": 5.757945629721084e-07,
      "loss": 0.489,
      "step": 58051
    },
    {
      "epoch": 1.7833072220686266,
      "grad_norm": 0.5073396563529968,
      "learning_rate": 5.756329514701242e-07,
      "loss": 0.5327,
      "step": 58052
    },
    {
      "epoch": 1.7833379412035757,
      "grad_norm": 0.44115155935287476,
      "learning_rate": 5.75471361979405e-07,
      "loss": 0.4335,
      "step": 58053
    },
    {
      "epoch": 1.7833686603385248,
      "grad_norm": 0.455641508102417,
      "learning_rate": 5.753097945003306e-07,
      "loss": 0.5068,
      "step": 58054
    },
    {
      "epoch": 1.7833993794734742,
      "grad_norm": 0.6092450618743896,
      "learning_rate": 5.751482490332794e-07,
      "loss": 0.4474,
      "step": 58055
    },
    {
      "epoch": 1.7834300986084233,
      "grad_norm": 0.4481969475746155,
      "learning_rate": 5.749867255786279e-07,
      "loss": 0.501,
      "step": 58056
    },
    {
      "epoch": 1.7834608177433724,
      "grad_norm": 0.4345916509628296,
      "learning_rate": 5.748252241367524e-07,
      "loss": 0.4641,
      "step": 58057
    },
    {
      "epoch": 1.7834915368783215,
      "grad_norm": 0.40414854884147644,
      "learning_rate": 5.746637447080306e-07,
      "loss": 0.4661,
      "step": 58058
    },
    {
      "epoch": 1.7835222560132706,
      "grad_norm": 0.452949196100235,
      "learning_rate": 5.745022872928396e-07,
      "loss": 0.4513,
      "step": 58059
    },
    {
      "epoch": 1.7835529751482198,
      "grad_norm": 0.42394357919692993,
      "learning_rate": 5.743408518915583e-07,
      "loss": 0.4879,
      "step": 58060
    },
    {
      "epoch": 1.7835836942831689,
      "grad_norm": 0.4496458172798157,
      "learning_rate": 5.741794385045619e-07,
      "loss": 0.4187,
      "step": 58061
    },
    {
      "epoch": 1.783614413418118,
      "grad_norm": 0.43483805656433105,
      "learning_rate": 5.740180471322266e-07,
      "loss": 0.4942,
      "step": 58062
    },
    {
      "epoch": 1.7836451325530673,
      "grad_norm": 0.43362224102020264,
      "learning_rate": 5.738566777749311e-07,
      "loss": 0.4697,
      "step": 58063
    },
    {
      "epoch": 1.7836758516880165,
      "grad_norm": 0.5044680237770081,
      "learning_rate": 5.736953304330506e-07,
      "loss": 0.4412,
      "step": 58064
    },
    {
      "epoch": 1.7837065708229656,
      "grad_norm": 0.3767770528793335,
      "learning_rate": 5.735340051069649e-07,
      "loss": 0.521,
      "step": 58065
    },
    {
      "epoch": 1.783737289957915,
      "grad_norm": 0.40068715810775757,
      "learning_rate": 5.733727017970481e-07,
      "loss": 0.5169,
      "step": 58066
    },
    {
      "epoch": 1.783768009092864,
      "grad_norm": 0.42915084958076477,
      "learning_rate": 5.732114205036765e-07,
      "loss": 0.5271,
      "step": 58067
    },
    {
      "epoch": 1.7837987282278132,
      "grad_norm": 0.4358861744403839,
      "learning_rate": 5.730501612272288e-07,
      "loss": 0.4972,
      "step": 58068
    },
    {
      "epoch": 1.7838294473627623,
      "grad_norm": 0.45279842615127563,
      "learning_rate": 5.728889239680824e-07,
      "loss": 0.4173,
      "step": 58069
    },
    {
      "epoch": 1.7838601664977114,
      "grad_norm": 0.44638729095458984,
      "learning_rate": 5.727277087266103e-07,
      "loss": 0.5128,
      "step": 58070
    },
    {
      "epoch": 1.7838908856326605,
      "grad_norm": 0.4478594660758972,
      "learning_rate": 5.725665155031934e-07,
      "loss": 0.4784,
      "step": 58071
    },
    {
      "epoch": 1.7839216047676096,
      "grad_norm": 0.4602895677089691,
      "learning_rate": 5.724053442982025e-07,
      "loss": 0.4458,
      "step": 58072
    },
    {
      "epoch": 1.7839523239025588,
      "grad_norm": 0.42317691445350647,
      "learning_rate": 5.722441951120195e-07,
      "loss": 0.4321,
      "step": 58073
    },
    {
      "epoch": 1.783983043037508,
      "grad_norm": 0.46506309509277344,
      "learning_rate": 5.720830679450184e-07,
      "loss": 0.5021,
      "step": 58074
    },
    {
      "epoch": 1.7840137621724572,
      "grad_norm": 0.4402208924293518,
      "learning_rate": 5.719219627975759e-07,
      "loss": 0.4643,
      "step": 58075
    },
    {
      "epoch": 1.7840444813074063,
      "grad_norm": 0.4047529399394989,
      "learning_rate": 5.717608796700668e-07,
      "loss": 0.3743,
      "step": 58076
    },
    {
      "epoch": 1.7840752004423557,
      "grad_norm": 0.4517780840396881,
      "learning_rate": 5.715998185628691e-07,
      "loss": 0.5308,
      "step": 58077
    },
    {
      "epoch": 1.7841059195773048,
      "grad_norm": 0.4945087134838104,
      "learning_rate": 5.714387794763587e-07,
      "loss": 0.4048,
      "step": 58078
    },
    {
      "epoch": 1.784136638712254,
      "grad_norm": 0.41013872623443604,
      "learning_rate": 5.712777624109134e-07,
      "loss": 0.383,
      "step": 58079
    },
    {
      "epoch": 1.784167357847203,
      "grad_norm": 0.4504697322845459,
      "learning_rate": 5.711167673669049e-07,
      "loss": 0.4519,
      "step": 58080
    },
    {
      "epoch": 1.7841980769821522,
      "grad_norm": 0.40763282775878906,
      "learning_rate": 5.709557943447108e-07,
      "loss": 0.4474,
      "step": 58081
    },
    {
      "epoch": 1.7842287961171013,
      "grad_norm": 0.4354059398174286,
      "learning_rate": 5.707948433447108e-07,
      "loss": 0.4862,
      "step": 58082
    },
    {
      "epoch": 1.7842595152520504,
      "grad_norm": 0.449419766664505,
      "learning_rate": 5.706339143672757e-07,
      "loss": 0.4843,
      "step": 58083
    },
    {
      "epoch": 1.7842902343869995,
      "grad_norm": 0.4124588668346405,
      "learning_rate": 5.704730074127863e-07,
      "loss": 0.407,
      "step": 58084
    },
    {
      "epoch": 1.7843209535219489,
      "grad_norm": 0.42298856377601624,
      "learning_rate": 5.703121224816133e-07,
      "loss": 0.4792,
      "step": 58085
    },
    {
      "epoch": 1.784351672656898,
      "grad_norm": 0.42682698369026184,
      "learning_rate": 5.701512595741354e-07,
      "loss": 0.4885,
      "step": 58086
    },
    {
      "epoch": 1.784382391791847,
      "grad_norm": 0.4794796109199524,
      "learning_rate": 5.699904186907279e-07,
      "loss": 0.4939,
      "step": 58087
    },
    {
      "epoch": 1.7844131109267964,
      "grad_norm": 0.43694353103637695,
      "learning_rate": 5.698295998317671e-07,
      "loss": 0.4125,
      "step": 58088
    },
    {
      "epoch": 1.7844438300617456,
      "grad_norm": 0.4416578710079193,
      "learning_rate": 5.696688029976272e-07,
      "loss": 0.4312,
      "step": 58089
    },
    {
      "epoch": 1.7844745491966947,
      "grad_norm": 0.4685836732387543,
      "learning_rate": 5.695080281886844e-07,
      "loss": 0.4561,
      "step": 58090
    },
    {
      "epoch": 1.7845052683316438,
      "grad_norm": 0.45855212211608887,
      "learning_rate": 5.693472754053142e-07,
      "loss": 0.4471,
      "step": 58091
    },
    {
      "epoch": 1.784535987466593,
      "grad_norm": 0.4513554573059082,
      "learning_rate": 5.691865446478928e-07,
      "loss": 0.4255,
      "step": 58092
    },
    {
      "epoch": 1.784566706601542,
      "grad_norm": 0.4217340648174286,
      "learning_rate": 5.690258359167944e-07,
      "loss": 0.459,
      "step": 58093
    },
    {
      "epoch": 1.7845974257364912,
      "grad_norm": 0.4009033441543579,
      "learning_rate": 5.688651492123942e-07,
      "loss": 0.4952,
      "step": 58094
    },
    {
      "epoch": 1.7846281448714403,
      "grad_norm": 0.4975197911262512,
      "learning_rate": 5.687044845350686e-07,
      "loss": 0.5075,
      "step": 58095
    },
    {
      "epoch": 1.7846588640063896,
      "grad_norm": 0.42750540375709534,
      "learning_rate": 5.68543841885193e-07,
      "loss": 0.4736,
      "step": 58096
    },
    {
      "epoch": 1.7846895831413387,
      "grad_norm": 0.4798760712146759,
      "learning_rate": 5.683832212631413e-07,
      "loss": 0.4318,
      "step": 58097
    },
    {
      "epoch": 1.7847203022762879,
      "grad_norm": 0.4716481864452362,
      "learning_rate": 5.6822262266929e-07,
      "loss": 0.463,
      "step": 58098
    },
    {
      "epoch": 1.7847510214112372,
      "grad_norm": 0.4531048834323883,
      "learning_rate": 5.68062046104011e-07,
      "loss": 0.4603,
      "step": 58099
    },
    {
      "epoch": 1.7847817405461863,
      "grad_norm": 0.4068876802921295,
      "learning_rate": 5.679014915676829e-07,
      "loss": 0.4535,
      "step": 58100
    },
    {
      "epoch": 1.7848124596811354,
      "grad_norm": 0.4262700080871582,
      "learning_rate": 5.67740959060682e-07,
      "loss": 0.5031,
      "step": 58101
    },
    {
      "epoch": 1.7848431788160846,
      "grad_norm": 0.43482109904289246,
      "learning_rate": 5.67580448583378e-07,
      "loss": 0.4456,
      "step": 58102
    },
    {
      "epoch": 1.7848738979510337,
      "grad_norm": 0.44572144746780396,
      "learning_rate": 5.674199601361497e-07,
      "loss": 0.4838,
      "step": 58103
    },
    {
      "epoch": 1.7849046170859828,
      "grad_norm": 0.41724663972854614,
      "learning_rate": 5.67259493719371e-07,
      "loss": 0.4361,
      "step": 58104
    },
    {
      "epoch": 1.784935336220932,
      "grad_norm": 0.41028690338134766,
      "learning_rate": 5.670990493334172e-07,
      "loss": 0.5065,
      "step": 58105
    },
    {
      "epoch": 1.784966055355881,
      "grad_norm": 0.4022427797317505,
      "learning_rate": 5.669386269786614e-07,
      "loss": 0.3993,
      "step": 58106
    },
    {
      "epoch": 1.7849967744908304,
      "grad_norm": 0.42897462844848633,
      "learning_rate": 5.6677822665548e-07,
      "loss": 0.4812,
      "step": 58107
    },
    {
      "epoch": 1.7850274936257795,
      "grad_norm": 0.47078439593315125,
      "learning_rate": 5.666178483642449e-07,
      "loss": 0.4879,
      "step": 58108
    },
    {
      "epoch": 1.7850582127607286,
      "grad_norm": 0.45292776823043823,
      "learning_rate": 5.664574921053345e-07,
      "loss": 0.451,
      "step": 58109
    },
    {
      "epoch": 1.785088931895678,
      "grad_norm": 0.43925973773002625,
      "learning_rate": 5.66297157879121e-07,
      "loss": 0.5042,
      "step": 58110
    },
    {
      "epoch": 1.785119651030627,
      "grad_norm": 0.4147762656211853,
      "learning_rate": 5.661368456859806e-07,
      "loss": 0.4527,
      "step": 58111
    },
    {
      "epoch": 1.7851503701655762,
      "grad_norm": 0.3933544158935547,
      "learning_rate": 5.659765555262842e-07,
      "loss": 0.4619,
      "step": 58112
    },
    {
      "epoch": 1.7851810893005253,
      "grad_norm": 0.47212105989456177,
      "learning_rate": 5.658162874004091e-07,
      "loss": 0.4313,
      "step": 58113
    },
    {
      "epoch": 1.7852118084354744,
      "grad_norm": 0.4273582696914673,
      "learning_rate": 5.656560413087286e-07,
      "loss": 0.4665,
      "step": 58114
    },
    {
      "epoch": 1.7852425275704236,
      "grad_norm": 0.4656234681606293,
      "learning_rate": 5.65495817251619e-07,
      "loss": 0.4231,
      "step": 58115
    },
    {
      "epoch": 1.7852732467053727,
      "grad_norm": 0.3971804678440094,
      "learning_rate": 5.65335615229452e-07,
      "loss": 0.4007,
      "step": 58116
    },
    {
      "epoch": 1.7853039658403218,
      "grad_norm": 0.39135101437568665,
      "learning_rate": 5.65175435242602e-07,
      "loss": 0.4068,
      "step": 58117
    },
    {
      "epoch": 1.7853346849752711,
      "grad_norm": 0.45312702655792236,
      "learning_rate": 5.65015277291443e-07,
      "loss": 0.4103,
      "step": 58118
    },
    {
      "epoch": 1.7853654041102203,
      "grad_norm": 0.43339917063713074,
      "learning_rate": 5.648551413763503e-07,
      "loss": 0.5578,
      "step": 58119
    },
    {
      "epoch": 1.7853961232451694,
      "grad_norm": 0.42988163232803345,
      "learning_rate": 5.646950274976992e-07,
      "loss": 0.4165,
      "step": 58120
    },
    {
      "epoch": 1.7854268423801187,
      "grad_norm": 0.5012505054473877,
      "learning_rate": 5.645349356558605e-07,
      "loss": 0.4083,
      "step": 58121
    },
    {
      "epoch": 1.7854575615150678,
      "grad_norm": 0.4373771548271179,
      "learning_rate": 5.643748658512082e-07,
      "loss": 0.5242,
      "step": 58122
    },
    {
      "epoch": 1.785488280650017,
      "grad_norm": 0.4222790002822876,
      "learning_rate": 5.64214818084119e-07,
      "loss": 0.4335,
      "step": 58123
    },
    {
      "epoch": 1.785518999784966,
      "grad_norm": 0.5528719425201416,
      "learning_rate": 5.640547923549655e-07,
      "loss": 0.5237,
      "step": 58124
    },
    {
      "epoch": 1.7855497189199152,
      "grad_norm": 0.4316522181034088,
      "learning_rate": 5.638947886641189e-07,
      "loss": 0.534,
      "step": 58125
    },
    {
      "epoch": 1.7855804380548643,
      "grad_norm": 0.4120619297027588,
      "learning_rate": 5.637348070119563e-07,
      "loss": 0.4879,
      "step": 58126
    },
    {
      "epoch": 1.7856111571898134,
      "grad_norm": 0.4957521855831146,
      "learning_rate": 5.6357484739885e-07,
      "loss": 0.4391,
      "step": 58127
    },
    {
      "epoch": 1.7856418763247626,
      "grad_norm": 0.47058266401290894,
      "learning_rate": 5.634149098251739e-07,
      "loss": 0.4512,
      "step": 58128
    },
    {
      "epoch": 1.785672595459712,
      "grad_norm": 0.4805709421634674,
      "learning_rate": 5.632549942913013e-07,
      "loss": 0.4389,
      "step": 58129
    },
    {
      "epoch": 1.785703314594661,
      "grad_norm": 0.4856063425540924,
      "learning_rate": 5.630951007976048e-07,
      "loss": 0.41,
      "step": 58130
    },
    {
      "epoch": 1.7857340337296101,
      "grad_norm": 0.39444825053215027,
      "learning_rate": 5.62935229344459e-07,
      "loss": 0.461,
      "step": 58131
    },
    {
      "epoch": 1.7857647528645595,
      "grad_norm": 0.4528830051422119,
      "learning_rate": 5.627753799322388e-07,
      "loss": 0.4628,
      "step": 58132
    },
    {
      "epoch": 1.7857954719995086,
      "grad_norm": 0.415029913187027,
      "learning_rate": 5.626155525613141e-07,
      "loss": 0.4556,
      "step": 58133
    },
    {
      "epoch": 1.7858261911344577,
      "grad_norm": 0.4124086797237396,
      "learning_rate": 5.624557472320613e-07,
      "loss": 0.5125,
      "step": 58134
    },
    {
      "epoch": 1.7858569102694068,
      "grad_norm": 0.42843806743621826,
      "learning_rate": 5.6229596394485e-07,
      "loss": 0.4973,
      "step": 58135
    },
    {
      "epoch": 1.785887629404356,
      "grad_norm": 0.4122268557548523,
      "learning_rate": 5.621362027000565e-07,
      "loss": 0.4557,
      "step": 58136
    },
    {
      "epoch": 1.785918348539305,
      "grad_norm": 0.464015930891037,
      "learning_rate": 5.61976463498054e-07,
      "loss": 0.5332,
      "step": 58137
    },
    {
      "epoch": 1.7859490676742542,
      "grad_norm": 0.42136648297309875,
      "learning_rate": 5.618167463392144e-07,
      "loss": 0.4518,
      "step": 58138
    },
    {
      "epoch": 1.7859797868092033,
      "grad_norm": 0.42421332001686096,
      "learning_rate": 5.616570512239105e-07,
      "loss": 0.4774,
      "step": 58139
    },
    {
      "epoch": 1.7860105059441524,
      "grad_norm": 0.3915635347366333,
      "learning_rate": 5.614973781525146e-07,
      "loss": 0.4067,
      "step": 58140
    },
    {
      "epoch": 1.7860412250791018,
      "grad_norm": 0.4660809636116028,
      "learning_rate": 5.613377271254028e-07,
      "loss": 0.4847,
      "step": 58141
    },
    {
      "epoch": 1.786071944214051,
      "grad_norm": 0.42436423897743225,
      "learning_rate": 5.611780981429448e-07,
      "loss": 0.4333,
      "step": 58142
    },
    {
      "epoch": 1.7861026633490003,
      "grad_norm": 0.506417989730835,
      "learning_rate": 5.610184912055161e-07,
      "loss": 0.4788,
      "step": 58143
    },
    {
      "epoch": 1.7861333824839494,
      "grad_norm": 0.43973520398139954,
      "learning_rate": 5.608589063134839e-07,
      "loss": 0.5111,
      "step": 58144
    },
    {
      "epoch": 1.7861641016188985,
      "grad_norm": 0.4864056706428528,
      "learning_rate": 5.606993434672292e-07,
      "loss": 0.4838,
      "step": 58145
    },
    {
      "epoch": 1.7861948207538476,
      "grad_norm": 0.4386746883392334,
      "learning_rate": 5.605398026671183e-07,
      "loss": 0.465,
      "step": 58146
    },
    {
      "epoch": 1.7862255398887967,
      "grad_norm": 0.444388747215271,
      "learning_rate": 5.603802839135275e-07,
      "loss": 0.5275,
      "step": 58147
    },
    {
      "epoch": 1.7862562590237459,
      "grad_norm": 0.4488683342933655,
      "learning_rate": 5.602207872068266e-07,
      "loss": 0.4456,
      "step": 58148
    },
    {
      "epoch": 1.786286978158695,
      "grad_norm": 0.5145504474639893,
      "learning_rate": 5.600613125473897e-07,
      "loss": 0.4733,
      "step": 58149
    },
    {
      "epoch": 1.786317697293644,
      "grad_norm": 0.4561580717563629,
      "learning_rate": 5.599018599355877e-07,
      "loss": 0.4293,
      "step": 58150
    },
    {
      "epoch": 1.7863484164285932,
      "grad_norm": 0.4037468433380127,
      "learning_rate": 5.597424293717968e-07,
      "loss": 0.4541,
      "step": 58151
    },
    {
      "epoch": 1.7863791355635426,
      "grad_norm": 0.5479063391685486,
      "learning_rate": 5.595830208563846e-07,
      "loss": 0.4983,
      "step": 58152
    },
    {
      "epoch": 1.7864098546984917,
      "grad_norm": 0.434793084859848,
      "learning_rate": 5.594236343897252e-07,
      "loss": 0.4783,
      "step": 58153
    },
    {
      "epoch": 1.786440573833441,
      "grad_norm": 0.42384111881256104,
      "learning_rate": 5.592642699721918e-07,
      "loss": 0.524,
      "step": 58154
    },
    {
      "epoch": 1.7864712929683901,
      "grad_norm": 0.44152238965034485,
      "learning_rate": 5.59104927604156e-07,
      "loss": 0.5438,
      "step": 58155
    },
    {
      "epoch": 1.7865020121033393,
      "grad_norm": 0.4614996612071991,
      "learning_rate": 5.589456072859922e-07,
      "loss": 0.5016,
      "step": 58156
    },
    {
      "epoch": 1.7865327312382884,
      "grad_norm": 0.43679800629615784,
      "learning_rate": 5.587863090180679e-07,
      "loss": 0.4732,
      "step": 58157
    },
    {
      "epoch": 1.7865634503732375,
      "grad_norm": 0.4506815969944,
      "learning_rate": 5.58627032800757e-07,
      "loss": 0.5008,
      "step": 58158
    },
    {
      "epoch": 1.7865941695081866,
      "grad_norm": 0.4485838711261749,
      "learning_rate": 5.584677786344328e-07,
      "loss": 0.4018,
      "step": 58159
    },
    {
      "epoch": 1.7866248886431357,
      "grad_norm": 0.43931588530540466,
      "learning_rate": 5.583085465194681e-07,
      "loss": 0.519,
      "step": 58160
    },
    {
      "epoch": 1.7866556077780849,
      "grad_norm": 0.4474060535430908,
      "learning_rate": 5.581493364562318e-07,
      "loss": 0.4557,
      "step": 58161
    },
    {
      "epoch": 1.786686326913034,
      "grad_norm": 0.4475288391113281,
      "learning_rate": 5.579901484450967e-07,
      "loss": 0.4604,
      "step": 58162
    },
    {
      "epoch": 1.7867170460479833,
      "grad_norm": 0.45505842566490173,
      "learning_rate": 5.578309824864359e-07,
      "loss": 0.4964,
      "step": 58163
    },
    {
      "epoch": 1.7867477651829324,
      "grad_norm": 0.4573719799518585,
      "learning_rate": 5.576718385806201e-07,
      "loss": 0.5193,
      "step": 58164
    },
    {
      "epoch": 1.7867784843178816,
      "grad_norm": 0.42043042182922363,
      "learning_rate": 5.575127167280215e-07,
      "loss": 0.4244,
      "step": 58165
    },
    {
      "epoch": 1.786809203452831,
      "grad_norm": 0.46168601512908936,
      "learning_rate": 5.573536169290105e-07,
      "loss": 0.5017,
      "step": 58166
    },
    {
      "epoch": 1.78683992258778,
      "grad_norm": 0.4754665493965149,
      "learning_rate": 5.571945391839595e-07,
      "loss": 0.513,
      "step": 58167
    },
    {
      "epoch": 1.7868706417227291,
      "grad_norm": 0.43274199962615967,
      "learning_rate": 5.570354834932413e-07,
      "loss": 0.4335,
      "step": 58168
    },
    {
      "epoch": 1.7869013608576783,
      "grad_norm": 0.4691547155380249,
      "learning_rate": 5.568764498572254e-07,
      "loss": 0.5028,
      "step": 58169
    },
    {
      "epoch": 1.7869320799926274,
      "grad_norm": 0.4317110776901245,
      "learning_rate": 5.567174382762853e-07,
      "loss": 0.4985,
      "step": 58170
    },
    {
      "epoch": 1.7869627991275765,
      "grad_norm": 0.5016806125640869,
      "learning_rate": 5.56558448750788e-07,
      "loss": 0.4248,
      "step": 58171
    },
    {
      "epoch": 1.7869935182625256,
      "grad_norm": 0.4080093801021576,
      "learning_rate": 5.563994812811113e-07,
      "loss": 0.4482,
      "step": 58172
    },
    {
      "epoch": 1.7870242373974747,
      "grad_norm": 0.4434669613838196,
      "learning_rate": 5.562405358676215e-07,
      "loss": 0.427,
      "step": 58173
    },
    {
      "epoch": 1.787054956532424,
      "grad_norm": 0.4120334982872009,
      "learning_rate": 5.560816125106916e-07,
      "loss": 0.556,
      "step": 58174
    },
    {
      "epoch": 1.7870856756673732,
      "grad_norm": 0.43208616971969604,
      "learning_rate": 5.559227112106936e-07,
      "loss": 0.5254,
      "step": 58175
    },
    {
      "epoch": 1.7871163948023223,
      "grad_norm": 0.4459432065486908,
      "learning_rate": 5.557638319679948e-07,
      "loss": 0.4421,
      "step": 58176
    },
    {
      "epoch": 1.7871471139372717,
      "grad_norm": 0.4574199318885803,
      "learning_rate": 5.556049747829729e-07,
      "loss": 0.485,
      "step": 58177
    },
    {
      "epoch": 1.7871778330722208,
      "grad_norm": 0.4262944459915161,
      "learning_rate": 5.554461396559929e-07,
      "loss": 0.4913,
      "step": 58178
    },
    {
      "epoch": 1.78720855220717,
      "grad_norm": 0.4151480495929718,
      "learning_rate": 5.552873265874304e-07,
      "loss": 0.5019,
      "step": 58179
    },
    {
      "epoch": 1.787239271342119,
      "grad_norm": 0.4483373463153839,
      "learning_rate": 5.551285355776514e-07,
      "loss": 0.4489,
      "step": 58180
    },
    {
      "epoch": 1.7872699904770681,
      "grad_norm": 0.4247871935367584,
      "learning_rate": 5.549697666270304e-07,
      "loss": 0.3927,
      "step": 58181
    },
    {
      "epoch": 1.7873007096120173,
      "grad_norm": 0.4286622107028961,
      "learning_rate": 5.548110197359358e-07,
      "loss": 0.4353,
      "step": 58182
    },
    {
      "epoch": 1.7873314287469664,
      "grad_norm": 0.42360198497772217,
      "learning_rate": 5.546522949047428e-07,
      "loss": 0.4949,
      "step": 58183
    },
    {
      "epoch": 1.7873621478819155,
      "grad_norm": 0.4192897081375122,
      "learning_rate": 5.544935921338168e-07,
      "loss": 0.6034,
      "step": 58184
    },
    {
      "epoch": 1.7873928670168648,
      "grad_norm": 0.42752254009246826,
      "learning_rate": 5.543349114235296e-07,
      "loss": 0.5236,
      "step": 58185
    },
    {
      "epoch": 1.787423586151814,
      "grad_norm": 0.4876171946525574,
      "learning_rate": 5.541762527742545e-07,
      "loss": 0.5201,
      "step": 58186
    },
    {
      "epoch": 1.787454305286763,
      "grad_norm": 0.47292739152908325,
      "learning_rate": 5.540176161863609e-07,
      "loss": 0.4369,
      "step": 58187
    },
    {
      "epoch": 1.7874850244217124,
      "grad_norm": 0.45329564809799194,
      "learning_rate": 5.538590016602186e-07,
      "loss": 0.4311,
      "step": 58188
    },
    {
      "epoch": 1.7875157435566615,
      "grad_norm": 0.42625734210014343,
      "learning_rate": 5.537004091961973e-07,
      "loss": 0.5393,
      "step": 58189
    },
    {
      "epoch": 1.7875464626916107,
      "grad_norm": 0.4335474371910095,
      "learning_rate": 5.535418387946678e-07,
      "loss": 0.4382,
      "step": 58190
    },
    {
      "epoch": 1.7875771818265598,
      "grad_norm": 0.4523847997188568,
      "learning_rate": 5.533832904560021e-07,
      "loss": 0.5165,
      "step": 58191
    },
    {
      "epoch": 1.787607900961509,
      "grad_norm": 0.4361835718154907,
      "learning_rate": 5.53224764180571e-07,
      "loss": 0.4379,
      "step": 58192
    },
    {
      "epoch": 1.787638620096458,
      "grad_norm": 0.4458574950695038,
      "learning_rate": 5.530662599687408e-07,
      "loss": 0.4313,
      "step": 58193
    },
    {
      "epoch": 1.7876693392314071,
      "grad_norm": 0.5641742944717407,
      "learning_rate": 5.529077778208858e-07,
      "loss": 0.5257,
      "step": 58194
    },
    {
      "epoch": 1.7877000583663563,
      "grad_norm": 0.49209854006767273,
      "learning_rate": 5.527493177373733e-07,
      "loss": 0.4214,
      "step": 58195
    },
    {
      "epoch": 1.7877307775013056,
      "grad_norm": 0.46413707733154297,
      "learning_rate": 5.525908797185763e-07,
      "loss": 0.4231,
      "step": 58196
    },
    {
      "epoch": 1.7877614966362547,
      "grad_norm": 0.41907718777656555,
      "learning_rate": 5.524324637648615e-07,
      "loss": 0.4646,
      "step": 58197
    },
    {
      "epoch": 1.7877922157712038,
      "grad_norm": 0.4435843229293823,
      "learning_rate": 5.522740698766005e-07,
      "loss": 0.4474,
      "step": 58198
    },
    {
      "epoch": 1.7878229349061532,
      "grad_norm": 0.4730992317199707,
      "learning_rate": 5.521156980541631e-07,
      "loss": 0.481,
      "step": 58199
    },
    {
      "epoch": 1.7878536540411023,
      "grad_norm": 0.42008984088897705,
      "learning_rate": 5.519573482979202e-07,
      "loss": 0.4804,
      "step": 58200
    },
    {
      "epoch": 1.7878843731760514,
      "grad_norm": 0.41500839591026306,
      "learning_rate": 5.517990206082402e-07,
      "loss": 0.449,
      "step": 58201
    },
    {
      "epoch": 1.7879150923110005,
      "grad_norm": 0.45639994740486145,
      "learning_rate": 5.516407149854952e-07,
      "loss": 0.4434,
      "step": 58202
    },
    {
      "epoch": 1.7879458114459497,
      "grad_norm": 0.42430493235588074,
      "learning_rate": 5.514824314300494e-07,
      "loss": 0.4668,
      "step": 58203
    },
    {
      "epoch": 1.7879765305808988,
      "grad_norm": 0.4023159146308899,
      "learning_rate": 5.5132416994228e-07,
      "loss": 0.4774,
      "step": 58204
    },
    {
      "epoch": 1.788007249715848,
      "grad_norm": 0.45109128952026367,
      "learning_rate": 5.511659305225503e-07,
      "loss": 0.458,
      "step": 58205
    },
    {
      "epoch": 1.788037968850797,
      "grad_norm": 0.3874313533306122,
      "learning_rate": 5.510077131712344e-07,
      "loss": 0.4245,
      "step": 58206
    },
    {
      "epoch": 1.7880686879857464,
      "grad_norm": 0.5013822913169861,
      "learning_rate": 5.508495178886975e-07,
      "loss": 0.5173,
      "step": 58207
    },
    {
      "epoch": 1.7880994071206955,
      "grad_norm": 0.40849897265434265,
      "learning_rate": 5.506913446753137e-07,
      "loss": 0.4777,
      "step": 58208
    },
    {
      "epoch": 1.7881301262556446,
      "grad_norm": 0.4410720765590668,
      "learning_rate": 5.505331935314495e-07,
      "loss": 0.4914,
      "step": 58209
    },
    {
      "epoch": 1.788160845390594,
      "grad_norm": 0.43700480461120605,
      "learning_rate": 5.503750644574746e-07,
      "loss": 0.4159,
      "step": 58210
    },
    {
      "epoch": 1.788191564525543,
      "grad_norm": 0.41337472200393677,
      "learning_rate": 5.502169574537608e-07,
      "loss": 0.4176,
      "step": 58211
    },
    {
      "epoch": 1.7882222836604922,
      "grad_norm": 0.4645736813545227,
      "learning_rate": 5.500588725206713e-07,
      "loss": 0.4171,
      "step": 58212
    },
    {
      "epoch": 1.7882530027954413,
      "grad_norm": 0.4170084297657013,
      "learning_rate": 5.499008096585823e-07,
      "loss": 0.4328,
      "step": 58213
    },
    {
      "epoch": 1.7882837219303904,
      "grad_norm": 0.4344363212585449,
      "learning_rate": 5.497427688678592e-07,
      "loss": 0.4729,
      "step": 58214
    },
    {
      "epoch": 1.7883144410653395,
      "grad_norm": 0.46558845043182373,
      "learning_rate": 5.495847501488727e-07,
      "loss": 0.4875,
      "step": 58215
    },
    {
      "epoch": 1.7883451602002887,
      "grad_norm": 0.4354090690612793,
      "learning_rate": 5.494267535019892e-07,
      "loss": 0.4649,
      "step": 58216
    },
    {
      "epoch": 1.7883758793352378,
      "grad_norm": 0.4162558317184448,
      "learning_rate": 5.492687789275808e-07,
      "loss": 0.4242,
      "step": 58217
    },
    {
      "epoch": 1.7884065984701871,
      "grad_norm": 0.49720168113708496,
      "learning_rate": 5.491108264260137e-07,
      "loss": 0.5048,
      "step": 58218
    },
    {
      "epoch": 1.7884373176051362,
      "grad_norm": 0.43921494483947754,
      "learning_rate": 5.489528959976609e-07,
      "loss": 0.4697,
      "step": 58219
    },
    {
      "epoch": 1.7884680367400854,
      "grad_norm": 0.44901058077812195,
      "learning_rate": 5.487949876428866e-07,
      "loss": 0.5236,
      "step": 58220
    },
    {
      "epoch": 1.7884987558750347,
      "grad_norm": 0.4015926420688629,
      "learning_rate": 5.486371013620617e-07,
      "loss": 0.4169,
      "step": 58221
    },
    {
      "epoch": 1.7885294750099838,
      "grad_norm": 0.42627203464508057,
      "learning_rate": 5.484792371555559e-07,
      "loss": 0.4639,
      "step": 58222
    },
    {
      "epoch": 1.788560194144933,
      "grad_norm": 0.47400444746017456,
      "learning_rate": 5.483213950237376e-07,
      "loss": 0.399,
      "step": 58223
    },
    {
      "epoch": 1.788590913279882,
      "grad_norm": 0.40016719698905945,
      "learning_rate": 5.481635749669733e-07,
      "loss": 0.512,
      "step": 58224
    },
    {
      "epoch": 1.7886216324148312,
      "grad_norm": 0.4255378246307373,
      "learning_rate": 5.480057769856328e-07,
      "loss": 0.5444,
      "step": 58225
    },
    {
      "epoch": 1.7886523515497803,
      "grad_norm": 0.4920464754104614,
      "learning_rate": 5.478480010800857e-07,
      "loss": 0.51,
      "step": 58226
    },
    {
      "epoch": 1.7886830706847294,
      "grad_norm": 0.4650837779045105,
      "learning_rate": 5.476902472506996e-07,
      "loss": 0.5434,
      "step": 58227
    },
    {
      "epoch": 1.7887137898196785,
      "grad_norm": 0.5258867144584656,
      "learning_rate": 5.475325154978439e-07,
      "loss": 0.5496,
      "step": 58228
    },
    {
      "epoch": 1.7887445089546279,
      "grad_norm": 0.4161740243434906,
      "learning_rate": 5.473748058218853e-07,
      "loss": 0.4617,
      "step": 58229
    },
    {
      "epoch": 1.788775228089577,
      "grad_norm": 0.41492411494255066,
      "learning_rate": 5.472171182231922e-07,
      "loss": 0.429,
      "step": 58230
    },
    {
      "epoch": 1.7888059472245261,
      "grad_norm": 0.3869038224220276,
      "learning_rate": 5.470594527021344e-07,
      "loss": 0.3749,
      "step": 58231
    },
    {
      "epoch": 1.7888366663594755,
      "grad_norm": 0.41297805309295654,
      "learning_rate": 5.469018092590805e-07,
      "loss": 0.481,
      "step": 58232
    },
    {
      "epoch": 1.7888673854944246,
      "grad_norm": 0.4185994565486908,
      "learning_rate": 5.467441878943969e-07,
      "loss": 0.4193,
      "step": 58233
    },
    {
      "epoch": 1.7888981046293737,
      "grad_norm": 0.47787827253341675,
      "learning_rate": 5.465865886084509e-07,
      "loss": 0.4497,
      "step": 58234
    },
    {
      "epoch": 1.7889288237643228,
      "grad_norm": 0.4429841637611389,
      "learning_rate": 5.464290114016135e-07,
      "loss": 0.5025,
      "step": 58235
    },
    {
      "epoch": 1.788959542899272,
      "grad_norm": 0.4408235251903534,
      "learning_rate": 5.462714562742522e-07,
      "loss": 0.4304,
      "step": 58236
    },
    {
      "epoch": 1.788990262034221,
      "grad_norm": 0.4926116466522217,
      "learning_rate": 5.461139232267332e-07,
      "loss": 0.5325,
      "step": 58237
    },
    {
      "epoch": 1.7890209811691702,
      "grad_norm": 0.5395553112030029,
      "learning_rate": 5.459564122594275e-07,
      "loss": 0.5096,
      "step": 58238
    },
    {
      "epoch": 1.7890517003041193,
      "grad_norm": 0.4174827039241791,
      "learning_rate": 5.457989233726968e-07,
      "loss": 0.4969,
      "step": 58239
    },
    {
      "epoch": 1.7890824194390686,
      "grad_norm": 0.4304657578468323,
      "learning_rate": 5.456414565669155e-07,
      "loss": 0.4319,
      "step": 58240
    },
    {
      "epoch": 1.7891131385740178,
      "grad_norm": 0.43326327204704285,
      "learning_rate": 5.454840118424487e-07,
      "loss": 0.4599,
      "step": 58241
    },
    {
      "epoch": 1.789143857708967,
      "grad_norm": 0.41441816091537476,
      "learning_rate": 5.45326589199665e-07,
      "loss": 0.5348,
      "step": 58242
    },
    {
      "epoch": 1.7891745768439162,
      "grad_norm": 0.42761120200157166,
      "learning_rate": 5.451691886389299e-07,
      "loss": 0.4538,
      "step": 58243
    },
    {
      "epoch": 1.7892052959788654,
      "grad_norm": 0.4341624677181244,
      "learning_rate": 5.450118101606127e-07,
      "loss": 0.4972,
      "step": 58244
    },
    {
      "epoch": 1.7892360151138145,
      "grad_norm": 0.40698596835136414,
      "learning_rate": 5.448544537650802e-07,
      "loss": 0.4647,
      "step": 58245
    },
    {
      "epoch": 1.7892667342487636,
      "grad_norm": 0.4821889400482178,
      "learning_rate": 5.446971194527017e-07,
      "loss": 0.4766,
      "step": 58246
    },
    {
      "epoch": 1.7892974533837127,
      "grad_norm": 0.41226521134376526,
      "learning_rate": 5.445398072238439e-07,
      "loss": 0.4641,
      "step": 58247
    },
    {
      "epoch": 1.7893281725186618,
      "grad_norm": 0.4665142893791199,
      "learning_rate": 5.443825170788708e-07,
      "loss": 0.4935,
      "step": 58248
    },
    {
      "epoch": 1.789358891653611,
      "grad_norm": 0.513886570930481,
      "learning_rate": 5.442252490181554e-07,
      "loss": 0.4359,
      "step": 58249
    },
    {
      "epoch": 1.78938961078856,
      "grad_norm": 0.48236730694770813,
      "learning_rate": 5.440680030420619e-07,
      "loss": 0.4958,
      "step": 58250
    },
    {
      "epoch": 1.7894203299235092,
      "grad_norm": 0.45347124338150024,
      "learning_rate": 5.43910779150959e-07,
      "loss": 0.4468,
      "step": 58251
    },
    {
      "epoch": 1.7894510490584585,
      "grad_norm": 0.4590446352958679,
      "learning_rate": 5.437535773452108e-07,
      "loss": 0.4926,
      "step": 58252
    },
    {
      "epoch": 1.7894817681934077,
      "grad_norm": 0.4645489454269409,
      "learning_rate": 5.435963976251868e-07,
      "loss": 0.4723,
      "step": 58253
    },
    {
      "epoch": 1.789512487328357,
      "grad_norm": 0.4343835115432739,
      "learning_rate": 5.434392399912547e-07,
      "loss": 0.4681,
      "step": 58254
    },
    {
      "epoch": 1.7895432064633061,
      "grad_norm": 0.42030254006385803,
      "learning_rate": 5.432821044437808e-07,
      "loss": 0.4583,
      "step": 58255
    },
    {
      "epoch": 1.7895739255982552,
      "grad_norm": 0.44956517219543457,
      "learning_rate": 5.431249909831315e-07,
      "loss": 0.4858,
      "step": 58256
    },
    {
      "epoch": 1.7896046447332044,
      "grad_norm": 0.47360289096832275,
      "learning_rate": 5.429678996096744e-07,
      "loss": 0.4319,
      "step": 58257
    },
    {
      "epoch": 1.7896353638681535,
      "grad_norm": 0.41778311133384705,
      "learning_rate": 5.428108303237756e-07,
      "loss": 0.4751,
      "step": 58258
    },
    {
      "epoch": 1.7896660830031026,
      "grad_norm": 0.5695791244506836,
      "learning_rate": 5.426537831258038e-07,
      "loss": 0.3986,
      "step": 58259
    },
    {
      "epoch": 1.7896968021380517,
      "grad_norm": 0.42763450741767883,
      "learning_rate": 5.424967580161244e-07,
      "loss": 0.4744,
      "step": 58260
    },
    {
      "epoch": 1.7897275212730008,
      "grad_norm": 0.541287899017334,
      "learning_rate": 5.423397549951037e-07,
      "loss": 0.4543,
      "step": 58261
    },
    {
      "epoch": 1.78975824040795,
      "grad_norm": 0.4179874658584595,
      "learning_rate": 5.42182774063108e-07,
      "loss": 0.4462,
      "step": 58262
    },
    {
      "epoch": 1.7897889595428993,
      "grad_norm": 0.5075963139533997,
      "learning_rate": 5.420258152205071e-07,
      "loss": 0.4284,
      "step": 58263
    },
    {
      "epoch": 1.7898196786778484,
      "grad_norm": 0.4339579939842224,
      "learning_rate": 5.418688784676651e-07,
      "loss": 0.5056,
      "step": 58264
    },
    {
      "epoch": 1.7898503978127978,
      "grad_norm": 0.4440021216869354,
      "learning_rate": 5.417119638049473e-07,
      "loss": 0.4147,
      "step": 58265
    },
    {
      "epoch": 1.7898811169477469,
      "grad_norm": 0.4011823832988739,
      "learning_rate": 5.415550712327222e-07,
      "loss": 0.3911,
      "step": 58266
    },
    {
      "epoch": 1.789911836082696,
      "grad_norm": 0.43869465589523315,
      "learning_rate": 5.413982007513563e-07,
      "loss": 0.439,
      "step": 58267
    },
    {
      "epoch": 1.7899425552176451,
      "grad_norm": 0.3966914713382721,
      "learning_rate": 5.41241352361217e-07,
      "loss": 0.366,
      "step": 58268
    },
    {
      "epoch": 1.7899732743525942,
      "grad_norm": 0.465971440076828,
      "learning_rate": 5.410845260626674e-07,
      "loss": 0.4499,
      "step": 58269
    },
    {
      "epoch": 1.7900039934875434,
      "grad_norm": 0.449614942073822,
      "learning_rate": 5.409277218560749e-07,
      "loss": 0.5148,
      "step": 58270
    },
    {
      "epoch": 1.7900347126224925,
      "grad_norm": 0.4698432385921478,
      "learning_rate": 5.40770939741807e-07,
      "loss": 0.4256,
      "step": 58271
    },
    {
      "epoch": 1.7900654317574416,
      "grad_norm": 0.4378131628036499,
      "learning_rate": 5.406141797202302e-07,
      "loss": 0.4558,
      "step": 58272
    },
    {
      "epoch": 1.7900961508923907,
      "grad_norm": 0.4958222806453705,
      "learning_rate": 5.404574417917086e-07,
      "loss": 0.4374,
      "step": 58273
    },
    {
      "epoch": 1.79012687002734,
      "grad_norm": 0.41533270478248596,
      "learning_rate": 5.403007259566107e-07,
      "loss": 0.3684,
      "step": 58274
    },
    {
      "epoch": 1.7901575891622892,
      "grad_norm": 0.44812366366386414,
      "learning_rate": 5.401440322152973e-07,
      "loss": 0.452,
      "step": 58275
    },
    {
      "epoch": 1.7901883082972383,
      "grad_norm": 0.42805081605911255,
      "learning_rate": 5.399873605681427e-07,
      "loss": 0.428,
      "step": 58276
    },
    {
      "epoch": 1.7902190274321876,
      "grad_norm": 0.4182177484035492,
      "learning_rate": 5.398307110155055e-07,
      "loss": 0.4465,
      "step": 58277
    },
    {
      "epoch": 1.7902497465671368,
      "grad_norm": 0.5651302337646484,
      "learning_rate": 5.396740835577563e-07,
      "loss": 0.4771,
      "step": 58278
    },
    {
      "epoch": 1.7902804657020859,
      "grad_norm": 0.4057784676551819,
      "learning_rate": 5.395174781952573e-07,
      "loss": 0.476,
      "step": 58279
    },
    {
      "epoch": 1.790311184837035,
      "grad_norm": 0.4766484498977661,
      "learning_rate": 5.393608949283768e-07,
      "loss": 0.4455,
      "step": 58280
    },
    {
      "epoch": 1.7903419039719841,
      "grad_norm": 0.4703199565410614,
      "learning_rate": 5.392043337574792e-07,
      "loss": 0.4151,
      "step": 58281
    },
    {
      "epoch": 1.7903726231069332,
      "grad_norm": 0.46354156732559204,
      "learning_rate": 5.390477946829298e-07,
      "loss": 0.4446,
      "step": 58282
    },
    {
      "epoch": 1.7904033422418824,
      "grad_norm": 0.5052714943885803,
      "learning_rate": 5.38891277705097e-07,
      "loss": 0.5734,
      "step": 58283
    },
    {
      "epoch": 1.7904340613768315,
      "grad_norm": 0.42145201563835144,
      "learning_rate": 5.387347828243439e-07,
      "loss": 0.5142,
      "step": 58284
    },
    {
      "epoch": 1.7904647805117808,
      "grad_norm": 0.4444282054901123,
      "learning_rate": 5.385783100410358e-07,
      "loss": 0.4859,
      "step": 58285
    },
    {
      "epoch": 1.79049549964673,
      "grad_norm": 0.4649326503276825,
      "learning_rate": 5.384218593555379e-07,
      "loss": 0.5122,
      "step": 58286
    },
    {
      "epoch": 1.790526218781679,
      "grad_norm": 0.4245940148830414,
      "learning_rate": 5.382654307682189e-07,
      "loss": 0.4759,
      "step": 58287
    },
    {
      "epoch": 1.7905569379166284,
      "grad_norm": 0.4051900804042816,
      "learning_rate": 5.381090242794407e-07,
      "loss": 0.532,
      "step": 58288
    },
    {
      "epoch": 1.7905876570515775,
      "grad_norm": 0.5114858746528625,
      "learning_rate": 5.379526398895685e-07,
      "loss": 0.487,
      "step": 58289
    },
    {
      "epoch": 1.7906183761865266,
      "grad_norm": 0.48229411244392395,
      "learning_rate": 5.377962775989698e-07,
      "loss": 0.4759,
      "step": 58290
    },
    {
      "epoch": 1.7906490953214758,
      "grad_norm": 0.40014711022377014,
      "learning_rate": 5.376399374080099e-07,
      "loss": 0.4677,
      "step": 58291
    },
    {
      "epoch": 1.7906798144564249,
      "grad_norm": 0.4421967566013336,
      "learning_rate": 5.374836193170507e-07,
      "loss": 0.4369,
      "step": 58292
    },
    {
      "epoch": 1.790710533591374,
      "grad_norm": 0.41711482405662537,
      "learning_rate": 5.373273233264598e-07,
      "loss": 0.5074,
      "step": 58293
    },
    {
      "epoch": 1.7907412527263231,
      "grad_norm": 0.5763092637062073,
      "learning_rate": 5.371710494366022e-07,
      "loss": 0.4243,
      "step": 58294
    },
    {
      "epoch": 1.7907719718612722,
      "grad_norm": 0.4268791675567627,
      "learning_rate": 5.370147976478435e-07,
      "loss": 0.4466,
      "step": 58295
    },
    {
      "epoch": 1.7908026909962216,
      "grad_norm": 0.41487595438957214,
      "learning_rate": 5.368585679605464e-07,
      "loss": 0.4166,
      "step": 58296
    },
    {
      "epoch": 1.7908334101311707,
      "grad_norm": 0.43727171421051025,
      "learning_rate": 5.367023603750765e-07,
      "loss": 0.3696,
      "step": 58297
    },
    {
      "epoch": 1.7908641292661198,
      "grad_norm": 0.5785945653915405,
      "learning_rate": 5.365461748918e-07,
      "loss": 0.3522,
      "step": 58298
    },
    {
      "epoch": 1.7908948484010692,
      "grad_norm": 0.4287637174129486,
      "learning_rate": 5.36390011511082e-07,
      "loss": 0.3995,
      "step": 58299
    },
    {
      "epoch": 1.7909255675360183,
      "grad_norm": 0.4843374490737915,
      "learning_rate": 5.362338702332837e-07,
      "loss": 0.4776,
      "step": 58300
    },
    {
      "epoch": 1.7909562866709674,
      "grad_norm": 0.4176235496997833,
      "learning_rate": 5.360777510587734e-07,
      "loss": 0.4278,
      "step": 58301
    },
    {
      "epoch": 1.7909870058059165,
      "grad_norm": 0.45394957065582275,
      "learning_rate": 5.359216539879142e-07,
      "loss": 0.3587,
      "step": 58302
    },
    {
      "epoch": 1.7910177249408656,
      "grad_norm": 0.4476205110549927,
      "learning_rate": 5.357655790210703e-07,
      "loss": 0.4593,
      "step": 58303
    },
    {
      "epoch": 1.7910484440758148,
      "grad_norm": 0.4423845410346985,
      "learning_rate": 5.356095261586092e-07,
      "loss": 0.4009,
      "step": 58304
    },
    {
      "epoch": 1.7910791632107639,
      "grad_norm": 0.44481363892555237,
      "learning_rate": 5.354534954008905e-07,
      "loss": 0.466,
      "step": 58305
    },
    {
      "epoch": 1.791109882345713,
      "grad_norm": 0.4595659077167511,
      "learning_rate": 5.35297486748283e-07,
      "loss": 0.5554,
      "step": 58306
    },
    {
      "epoch": 1.7911406014806623,
      "grad_norm": 0.4780046045780182,
      "learning_rate": 5.351415002011473e-07,
      "loss": 0.489,
      "step": 58307
    },
    {
      "epoch": 1.7911713206156115,
      "grad_norm": 0.4380411207675934,
      "learning_rate": 5.34985535759851e-07,
      "loss": 0.5236,
      "step": 58308
    },
    {
      "epoch": 1.7912020397505606,
      "grad_norm": 0.4361014664173126,
      "learning_rate": 5.348295934247572e-07,
      "loss": 0.4076,
      "step": 58309
    },
    {
      "epoch": 1.79123275888551,
      "grad_norm": 0.42608943581581116,
      "learning_rate": 5.346736731962298e-07,
      "loss": 0.4193,
      "step": 58310
    },
    {
      "epoch": 1.791263478020459,
      "grad_norm": 0.455983966588974,
      "learning_rate": 5.345177750746311e-07,
      "loss": 0.4027,
      "step": 58311
    },
    {
      "epoch": 1.7912941971554082,
      "grad_norm": 0.43948572874069214,
      "learning_rate": 5.343618990603294e-07,
      "loss": 0.4507,
      "step": 58312
    },
    {
      "epoch": 1.7913249162903573,
      "grad_norm": 0.4406185448169708,
      "learning_rate": 5.342060451536857e-07,
      "loss": 0.5465,
      "step": 58313
    },
    {
      "epoch": 1.7913556354253064,
      "grad_norm": 0.429084450006485,
      "learning_rate": 5.340502133550663e-07,
      "loss": 0.4772,
      "step": 58314
    },
    {
      "epoch": 1.7913863545602555,
      "grad_norm": 0.4664439260959625,
      "learning_rate": 5.338944036648319e-07,
      "loss": 0.4937,
      "step": 58315
    },
    {
      "epoch": 1.7914170736952046,
      "grad_norm": 0.427049458026886,
      "learning_rate": 5.337386160833491e-07,
      "loss": 0.567,
      "step": 58316
    },
    {
      "epoch": 1.7914477928301538,
      "grad_norm": 0.4409322440624237,
      "learning_rate": 5.335828506109797e-07,
      "loss": 0.5038,
      "step": 58317
    },
    {
      "epoch": 1.791478511965103,
      "grad_norm": 0.4154013395309448,
      "learning_rate": 5.334271072480912e-07,
      "loss": 0.411,
      "step": 58318
    },
    {
      "epoch": 1.7915092311000522,
      "grad_norm": 0.44441869854927063,
      "learning_rate": 5.332713859950422e-07,
      "loss": 0.4537,
      "step": 58319
    },
    {
      "epoch": 1.7915399502350013,
      "grad_norm": 0.46402662992477417,
      "learning_rate": 5.331156868522002e-07,
      "loss": 0.4996,
      "step": 58320
    },
    {
      "epoch": 1.7915706693699507,
      "grad_norm": 0.4166814386844635,
      "learning_rate": 5.329600098199273e-07,
      "loss": 0.4335,
      "step": 58321
    },
    {
      "epoch": 1.7916013885048998,
      "grad_norm": 0.39916467666625977,
      "learning_rate": 5.328043548985873e-07,
      "loss": 0.4971,
      "step": 58322
    },
    {
      "epoch": 1.791632107639849,
      "grad_norm": 0.4357345700263977,
      "learning_rate": 5.326487220885457e-07,
      "loss": 0.4216,
      "step": 58323
    },
    {
      "epoch": 1.791662826774798,
      "grad_norm": 0.45683759450912476,
      "learning_rate": 5.324931113901621e-07,
      "loss": 0.4879,
      "step": 58324
    },
    {
      "epoch": 1.7916935459097472,
      "grad_norm": 0.4651990234851837,
      "learning_rate": 5.323375228038031e-07,
      "loss": 0.5194,
      "step": 58325
    },
    {
      "epoch": 1.7917242650446963,
      "grad_norm": 0.4297541081905365,
      "learning_rate": 5.321819563298302e-07,
      "loss": 0.438,
      "step": 58326
    },
    {
      "epoch": 1.7917549841796454,
      "grad_norm": 0.4306999742984772,
      "learning_rate": 5.320264119686091e-07,
      "loss": 0.4928,
      "step": 58327
    },
    {
      "epoch": 1.7917857033145945,
      "grad_norm": 0.43299970030784607,
      "learning_rate": 5.318708897204994e-07,
      "loss": 0.5014,
      "step": 58328
    },
    {
      "epoch": 1.7918164224495439,
      "grad_norm": 0.44672906398773193,
      "learning_rate": 5.317153895858673e-07,
      "loss": 0.5168,
      "step": 58329
    },
    {
      "epoch": 1.791847141584493,
      "grad_norm": 0.44074034690856934,
      "learning_rate": 5.315599115650749e-07,
      "loss": 0.4599,
      "step": 58330
    },
    {
      "epoch": 1.791877860719442,
      "grad_norm": 0.45982611179351807,
      "learning_rate": 5.314044556584874e-07,
      "loss": 0.4086,
      "step": 58331
    },
    {
      "epoch": 1.7919085798543914,
      "grad_norm": 0.42583370208740234,
      "learning_rate": 5.312490218664646e-07,
      "loss": 0.4668,
      "step": 58332
    },
    {
      "epoch": 1.7919392989893406,
      "grad_norm": 0.44575050473213196,
      "learning_rate": 5.310936101893716e-07,
      "loss": 0.4492,
      "step": 58333
    },
    {
      "epoch": 1.7919700181242897,
      "grad_norm": 0.4644947946071625,
      "learning_rate": 5.309382206275693e-07,
      "loss": 0.4519,
      "step": 58334
    },
    {
      "epoch": 1.7920007372592388,
      "grad_norm": 0.45432180166244507,
      "learning_rate": 5.307828531814241e-07,
      "loss": 0.379,
      "step": 58335
    },
    {
      "epoch": 1.792031456394188,
      "grad_norm": 0.4193097949028015,
      "learning_rate": 5.306275078512957e-07,
      "loss": 0.4295,
      "step": 58336
    },
    {
      "epoch": 1.792062175529137,
      "grad_norm": 0.43527811765670776,
      "learning_rate": 5.304721846375482e-07,
      "loss": 0.4489,
      "step": 58337
    },
    {
      "epoch": 1.7920928946640862,
      "grad_norm": 0.45338714122772217,
      "learning_rate": 5.303168835405437e-07,
      "loss": 0.5101,
      "step": 58338
    },
    {
      "epoch": 1.7921236137990353,
      "grad_norm": 0.43923550844192505,
      "learning_rate": 5.301616045606461e-07,
      "loss": 0.3474,
      "step": 58339
    },
    {
      "epoch": 1.7921543329339846,
      "grad_norm": 0.45454639196395874,
      "learning_rate": 5.300063476982186e-07,
      "loss": 0.3923,
      "step": 58340
    },
    {
      "epoch": 1.7921850520689337,
      "grad_norm": 0.4972570240497589,
      "learning_rate": 5.29851112953621e-07,
      "loss": 0.4601,
      "step": 58341
    },
    {
      "epoch": 1.7922157712038829,
      "grad_norm": 0.43252578377723694,
      "learning_rate": 5.296959003272196e-07,
      "loss": 0.4703,
      "step": 58342
    },
    {
      "epoch": 1.7922464903388322,
      "grad_norm": 0.446490615606308,
      "learning_rate": 5.295407098193717e-07,
      "loss": 0.4543,
      "step": 58343
    },
    {
      "epoch": 1.7922772094737813,
      "grad_norm": 0.4168158173561096,
      "learning_rate": 5.293855414304449e-07,
      "loss": 0.403,
      "step": 58344
    },
    {
      "epoch": 1.7923079286087304,
      "grad_norm": 0.43476802110671997,
      "learning_rate": 5.292303951607991e-07,
      "loss": 0.4597,
      "step": 58345
    },
    {
      "epoch": 1.7923386477436796,
      "grad_norm": 0.41597995162010193,
      "learning_rate": 5.290752710107982e-07,
      "loss": 0.4454,
      "step": 58346
    },
    {
      "epoch": 1.7923693668786287,
      "grad_norm": 0.4169967770576477,
      "learning_rate": 5.289201689808021e-07,
      "loss": 0.4923,
      "step": 58347
    },
    {
      "epoch": 1.7924000860135778,
      "grad_norm": 0.42074230313301086,
      "learning_rate": 5.287650890711748e-07,
      "loss": 0.4655,
      "step": 58348
    },
    {
      "epoch": 1.792430805148527,
      "grad_norm": 0.4914599657058716,
      "learning_rate": 5.286100312822773e-07,
      "loss": 0.5043,
      "step": 58349
    },
    {
      "epoch": 1.792461524283476,
      "grad_norm": 0.4781387150287628,
      "learning_rate": 5.284549956144747e-07,
      "loss": 0.3926,
      "step": 58350
    },
    {
      "epoch": 1.7924922434184254,
      "grad_norm": 0.48704794049263,
      "learning_rate": 5.282999820681256e-07,
      "loss": 0.4814,
      "step": 58351
    },
    {
      "epoch": 1.7925229625533745,
      "grad_norm": 0.4131609797477722,
      "learning_rate": 5.281449906435921e-07,
      "loss": 0.397,
      "step": 58352
    },
    {
      "epoch": 1.7925536816883236,
      "grad_norm": 0.4849145710468292,
      "learning_rate": 5.279900213412393e-07,
      "loss": 0.453,
      "step": 58353
    },
    {
      "epoch": 1.792584400823273,
      "grad_norm": 0.8423400521278381,
      "learning_rate": 5.278350741614269e-07,
      "loss": 0.5605,
      "step": 58354
    },
    {
      "epoch": 1.792615119958222,
      "grad_norm": 0.4814245104789734,
      "learning_rate": 5.276801491045169e-07,
      "loss": 0.4768,
      "step": 58355
    },
    {
      "epoch": 1.7926458390931712,
      "grad_norm": 0.4862750172615051,
      "learning_rate": 5.275252461708713e-07,
      "loss": 0.4397,
      "step": 58356
    },
    {
      "epoch": 1.7926765582281203,
      "grad_norm": 0.4400825798511505,
      "learning_rate": 5.273703653608519e-07,
      "loss": 0.5437,
      "step": 58357
    },
    {
      "epoch": 1.7927072773630695,
      "grad_norm": 0.4727916419506073,
      "learning_rate": 5.272155066748208e-07,
      "loss": 0.4771,
      "step": 58358
    },
    {
      "epoch": 1.7927379964980186,
      "grad_norm": 0.39957037568092346,
      "learning_rate": 5.270606701131409e-07,
      "loss": 0.3673,
      "step": 58359
    },
    {
      "epoch": 1.7927687156329677,
      "grad_norm": 0.42427095770835876,
      "learning_rate": 5.269058556761708e-07,
      "loss": 0.4948,
      "step": 58360
    },
    {
      "epoch": 1.7927994347679168,
      "grad_norm": 0.5066605806350708,
      "learning_rate": 5.267510633642736e-07,
      "loss": 0.3908,
      "step": 58361
    },
    {
      "epoch": 1.792830153902866,
      "grad_norm": 0.46208277344703674,
      "learning_rate": 5.265962931778112e-07,
      "loss": 0.5407,
      "step": 58362
    },
    {
      "epoch": 1.7928608730378153,
      "grad_norm": 0.3780974745750427,
      "learning_rate": 5.264415451171456e-07,
      "loss": 0.4514,
      "step": 58363
    },
    {
      "epoch": 1.7928915921727644,
      "grad_norm": 0.5630308389663696,
      "learning_rate": 5.262868191826365e-07,
      "loss": 0.5124,
      "step": 58364
    },
    {
      "epoch": 1.7929223113077137,
      "grad_norm": 0.45194900035858154,
      "learning_rate": 5.261321153746457e-07,
      "loss": 0.4468,
      "step": 58365
    },
    {
      "epoch": 1.7929530304426629,
      "grad_norm": 0.4561905562877655,
      "learning_rate": 5.259774336935352e-07,
      "loss": 0.4472,
      "step": 58366
    },
    {
      "epoch": 1.792983749577612,
      "grad_norm": 0.4227651059627533,
      "learning_rate": 5.258227741396683e-07,
      "loss": 0.4119,
      "step": 58367
    },
    {
      "epoch": 1.793014468712561,
      "grad_norm": 0.43403905630111694,
      "learning_rate": 5.25668136713402e-07,
      "loss": 0.4774,
      "step": 58368
    },
    {
      "epoch": 1.7930451878475102,
      "grad_norm": 0.4400036036968231,
      "learning_rate": 5.255135214151008e-07,
      "loss": 0.4796,
      "step": 58369
    },
    {
      "epoch": 1.7930759069824593,
      "grad_norm": 0.4966934025287628,
      "learning_rate": 5.25358928245121e-07,
      "loss": 0.4782,
      "step": 58370
    },
    {
      "epoch": 1.7931066261174085,
      "grad_norm": 0.447853147983551,
      "learning_rate": 5.252043572038301e-07,
      "loss": 0.5058,
      "step": 58371
    },
    {
      "epoch": 1.7931373452523576,
      "grad_norm": 0.3910452127456665,
      "learning_rate": 5.250498082915856e-07,
      "loss": 0.4611,
      "step": 58372
    },
    {
      "epoch": 1.7931680643873067,
      "grad_norm": 0.4696600139141083,
      "learning_rate": 5.248952815087483e-07,
      "loss": 0.4439,
      "step": 58373
    },
    {
      "epoch": 1.793198783522256,
      "grad_norm": 0.4438963234424591,
      "learning_rate": 5.2474077685568e-07,
      "loss": 0.5048,
      "step": 58374
    },
    {
      "epoch": 1.7932295026572052,
      "grad_norm": 0.4325314462184906,
      "learning_rate": 5.245862943327418e-07,
      "loss": 0.4789,
      "step": 58375
    },
    {
      "epoch": 1.7932602217921545,
      "grad_norm": 0.39781931042671204,
      "learning_rate": 5.244318339402954e-07,
      "loss": 0.438,
      "step": 58376
    },
    {
      "epoch": 1.7932909409271036,
      "grad_norm": 0.42140600085258484,
      "learning_rate": 5.242773956786984e-07,
      "loss": 0.4655,
      "step": 58377
    },
    {
      "epoch": 1.7933216600620527,
      "grad_norm": 0.46806395053863525,
      "learning_rate": 5.241229795483138e-07,
      "loss": 0.5483,
      "step": 58378
    },
    {
      "epoch": 1.7933523791970019,
      "grad_norm": 0.40121784806251526,
      "learning_rate": 5.239685855495003e-07,
      "loss": 0.4921,
      "step": 58379
    },
    {
      "epoch": 1.793383098331951,
      "grad_norm": 0.47938549518585205,
      "learning_rate": 5.23814213682623e-07,
      "loss": 0.4502,
      "step": 58380
    },
    {
      "epoch": 1.7934138174669,
      "grad_norm": 0.4415358603000641,
      "learning_rate": 5.236598639480372e-07,
      "loss": 0.4782,
      "step": 58381
    },
    {
      "epoch": 1.7934445366018492,
      "grad_norm": 0.4065883159637451,
      "learning_rate": 5.235055363461072e-07,
      "loss": 0.4247,
      "step": 58382
    },
    {
      "epoch": 1.7934752557367983,
      "grad_norm": 0.4159770905971527,
      "learning_rate": 5.233512308771904e-07,
      "loss": 0.4992,
      "step": 58383
    },
    {
      "epoch": 1.7935059748717475,
      "grad_norm": 0.39620962738990784,
      "learning_rate": 5.231969475416487e-07,
      "loss": 0.3957,
      "step": 58384
    },
    {
      "epoch": 1.7935366940066968,
      "grad_norm": 0.42275625467300415,
      "learning_rate": 5.230426863398419e-07,
      "loss": 0.5012,
      "step": 58385
    },
    {
      "epoch": 1.793567413141646,
      "grad_norm": 0.45491406321525574,
      "learning_rate": 5.22888447272133e-07,
      "loss": 0.4616,
      "step": 58386
    },
    {
      "epoch": 1.793598132276595,
      "grad_norm": 0.45153099298477173,
      "learning_rate": 5.227342303388783e-07,
      "loss": 0.4523,
      "step": 58387
    },
    {
      "epoch": 1.7936288514115444,
      "grad_norm": 0.46759477257728577,
      "learning_rate": 5.225800355404398e-07,
      "loss": 0.4843,
      "step": 58388
    },
    {
      "epoch": 1.7936595705464935,
      "grad_norm": 0.4435739815235138,
      "learning_rate": 5.224258628771772e-07,
      "loss": 0.5058,
      "step": 58389
    },
    {
      "epoch": 1.7936902896814426,
      "grad_norm": 0.48821523785591125,
      "learning_rate": 5.222717123494525e-07,
      "loss": 0.4729,
      "step": 58390
    },
    {
      "epoch": 1.7937210088163917,
      "grad_norm": 0.43461742997169495,
      "learning_rate": 5.221175839576231e-07,
      "loss": 0.4346,
      "step": 58391
    },
    {
      "epoch": 1.7937517279513409,
      "grad_norm": 0.45886459946632385,
      "learning_rate": 5.219634777020499e-07,
      "loss": 0.4446,
      "step": 58392
    },
    {
      "epoch": 1.79378244708629,
      "grad_norm": 0.44838422536849976,
      "learning_rate": 5.218093935830926e-07,
      "loss": 0.4068,
      "step": 58393
    },
    {
      "epoch": 1.793813166221239,
      "grad_norm": 0.40647754073143005,
      "learning_rate": 5.216553316011108e-07,
      "loss": 0.3743,
      "step": 58394
    },
    {
      "epoch": 1.7938438853561882,
      "grad_norm": 0.4823227822780609,
      "learning_rate": 5.215012917564677e-07,
      "loss": 0.5413,
      "step": 58395
    },
    {
      "epoch": 1.7938746044911376,
      "grad_norm": 0.4579853117465973,
      "learning_rate": 5.213472740495185e-07,
      "loss": 0.4695,
      "step": 58396
    },
    {
      "epoch": 1.7939053236260867,
      "grad_norm": 0.4576718509197235,
      "learning_rate": 5.211932784806239e-07,
      "loss": 0.4403,
      "step": 58397
    },
    {
      "epoch": 1.7939360427610358,
      "grad_norm": 0.4317343533039093,
      "learning_rate": 5.21039305050145e-07,
      "loss": 0.5254,
      "step": 58398
    },
    {
      "epoch": 1.7939667618959851,
      "grad_norm": 0.46979156136512756,
      "learning_rate": 5.208853537584424e-07,
      "loss": 0.4318,
      "step": 58399
    },
    {
      "epoch": 1.7939974810309343,
      "grad_norm": 0.43256819248199463,
      "learning_rate": 5.207314246058725e-07,
      "loss": 0.4982,
      "step": 58400
    },
    {
      "epoch": 1.7940282001658834,
      "grad_norm": 0.41222429275512695,
      "learning_rate": 5.205775175927963e-07,
      "loss": 0.4275,
      "step": 58401
    },
    {
      "epoch": 1.7940589193008325,
      "grad_norm": 0.40854737162590027,
      "learning_rate": 5.204236327195733e-07,
      "loss": 0.5672,
      "step": 58402
    },
    {
      "epoch": 1.7940896384357816,
      "grad_norm": 0.5090404748916626,
      "learning_rate": 5.202697699865644e-07,
      "loss": 0.5237,
      "step": 58403
    },
    {
      "epoch": 1.7941203575707307,
      "grad_norm": 0.42255905270576477,
      "learning_rate": 5.20115929394126e-07,
      "loss": 0.5114,
      "step": 58404
    },
    {
      "epoch": 1.7941510767056799,
      "grad_norm": 0.437766969203949,
      "learning_rate": 5.199621109426201e-07,
      "loss": 0.4148,
      "step": 58405
    },
    {
      "epoch": 1.794181795840629,
      "grad_norm": 0.4660484194755554,
      "learning_rate": 5.198083146324029e-07,
      "loss": 0.4386,
      "step": 58406
    },
    {
      "epoch": 1.7942125149755783,
      "grad_norm": 0.4253159761428833,
      "learning_rate": 5.196545404638376e-07,
      "loss": 0.4437,
      "step": 58407
    },
    {
      "epoch": 1.7942432341105274,
      "grad_norm": 0.43991750478744507,
      "learning_rate": 5.195007884372793e-07,
      "loss": 0.4878,
      "step": 58408
    },
    {
      "epoch": 1.7942739532454766,
      "grad_norm": 0.4620506465435028,
      "learning_rate": 5.193470585530913e-07,
      "loss": 0.512,
      "step": 58409
    },
    {
      "epoch": 1.794304672380426,
      "grad_norm": 0.5001057386398315,
      "learning_rate": 5.191933508116287e-07,
      "loss": 0.4501,
      "step": 58410
    },
    {
      "epoch": 1.794335391515375,
      "grad_norm": 0.4618878960609436,
      "learning_rate": 5.190396652132501e-07,
      "loss": 0.4302,
      "step": 58411
    },
    {
      "epoch": 1.7943661106503241,
      "grad_norm": 0.46647000312805176,
      "learning_rate": 5.188860017583208e-07,
      "loss": 0.5046,
      "step": 58412
    },
    {
      "epoch": 1.7943968297852733,
      "grad_norm": 0.410867840051651,
      "learning_rate": 5.187323604471928e-07,
      "loss": 0.3855,
      "step": 58413
    },
    {
      "epoch": 1.7944275489202224,
      "grad_norm": 0.4803938865661621,
      "learning_rate": 5.18578741280229e-07,
      "loss": 0.3908,
      "step": 58414
    },
    {
      "epoch": 1.7944582680551715,
      "grad_norm": 0.39837512373924255,
      "learning_rate": 5.184251442577848e-07,
      "loss": 0.4601,
      "step": 58415
    },
    {
      "epoch": 1.7944889871901206,
      "grad_norm": 0.40640291571617126,
      "learning_rate": 5.18271569380222e-07,
      "loss": 0.4724,
      "step": 58416
    },
    {
      "epoch": 1.7945197063250697,
      "grad_norm": 0.438132643699646,
      "learning_rate": 5.181180166478982e-07,
      "loss": 0.4779,
      "step": 58417
    },
    {
      "epoch": 1.794550425460019,
      "grad_norm": 0.4464934170246124,
      "learning_rate": 5.179644860611732e-07,
      "loss": 0.4264,
      "step": 58418
    },
    {
      "epoch": 1.7945811445949682,
      "grad_norm": 0.42265740036964417,
      "learning_rate": 5.178109776204032e-07,
      "loss": 0.4269,
      "step": 58419
    },
    {
      "epoch": 1.7946118637299173,
      "grad_norm": 0.5202682614326477,
      "learning_rate": 5.176574913259468e-07,
      "loss": 0.4934,
      "step": 58420
    },
    {
      "epoch": 1.7946425828648667,
      "grad_norm": 0.4073122441768646,
      "learning_rate": 5.17504027178164e-07,
      "loss": 0.4803,
      "step": 58421
    },
    {
      "epoch": 1.7946733019998158,
      "grad_norm": 0.43131303787231445,
      "learning_rate": 5.173505851774152e-07,
      "loss": 0.5137,
      "step": 58422
    },
    {
      "epoch": 1.794704021134765,
      "grad_norm": 0.4242328107357025,
      "learning_rate": 5.171971653240537e-07,
      "loss": 0.393,
      "step": 58423
    },
    {
      "epoch": 1.794734740269714,
      "grad_norm": 0.5979138612747192,
      "learning_rate": 5.170437676184403e-07,
      "loss": 0.5216,
      "step": 58424
    },
    {
      "epoch": 1.7947654594046631,
      "grad_norm": 0.45721325278282166,
      "learning_rate": 5.168903920609348e-07,
      "loss": 0.5532,
      "step": 58425
    },
    {
      "epoch": 1.7947961785396123,
      "grad_norm": 0.4234892427921295,
      "learning_rate": 5.167370386518944e-07,
      "loss": 0.5182,
      "step": 58426
    },
    {
      "epoch": 1.7948268976745614,
      "grad_norm": 0.4366937577724457,
      "learning_rate": 5.165837073916757e-07,
      "loss": 0.5231,
      "step": 58427
    },
    {
      "epoch": 1.7948576168095105,
      "grad_norm": 0.48663920164108276,
      "learning_rate": 5.164303982806384e-07,
      "loss": 0.4536,
      "step": 58428
    },
    {
      "epoch": 1.7948883359444598,
      "grad_norm": 0.42614495754241943,
      "learning_rate": 5.1627711131914e-07,
      "loss": 0.4178,
      "step": 58429
    },
    {
      "epoch": 1.794919055079409,
      "grad_norm": 0.4107924699783325,
      "learning_rate": 5.161238465075391e-07,
      "loss": 0.4724,
      "step": 58430
    },
    {
      "epoch": 1.794949774214358,
      "grad_norm": 0.4188919961452484,
      "learning_rate": 5.159706038461953e-07,
      "loss": 0.4617,
      "step": 58431
    },
    {
      "epoch": 1.7949804933493074,
      "grad_norm": 0.41672030091285706,
      "learning_rate": 5.158173833354618e-07,
      "loss": 0.509,
      "step": 58432
    },
    {
      "epoch": 1.7950112124842565,
      "grad_norm": 0.4036365747451782,
      "learning_rate": 5.156641849756994e-07,
      "loss": 0.4609,
      "step": 58433
    },
    {
      "epoch": 1.7950419316192057,
      "grad_norm": 0.4591735303401947,
      "learning_rate": 5.155110087672666e-07,
      "loss": 0.4222,
      "step": 58434
    },
    {
      "epoch": 1.7950726507541548,
      "grad_norm": 0.47294992208480835,
      "learning_rate": 5.15357854710521e-07,
      "loss": 0.472,
      "step": 58435
    },
    {
      "epoch": 1.795103369889104,
      "grad_norm": 0.4313037097454071,
      "learning_rate": 5.152047228058176e-07,
      "loss": 0.4674,
      "step": 58436
    },
    {
      "epoch": 1.795134089024053,
      "grad_norm": 0.4473259449005127,
      "learning_rate": 5.150516130535166e-07,
      "loss": 0.4001,
      "step": 58437
    },
    {
      "epoch": 1.7951648081590021,
      "grad_norm": 0.44022348523139954,
      "learning_rate": 5.148985254539751e-07,
      "loss": 0.525,
      "step": 58438
    },
    {
      "epoch": 1.7951955272939513,
      "grad_norm": 0.4494491517543793,
      "learning_rate": 5.147454600075519e-07,
      "loss": 0.461,
      "step": 58439
    },
    {
      "epoch": 1.7952262464289006,
      "grad_norm": 0.42015498876571655,
      "learning_rate": 5.145924167146011e-07,
      "loss": 0.5022,
      "step": 58440
    },
    {
      "epoch": 1.7952569655638497,
      "grad_norm": 0.42277780175209045,
      "learning_rate": 5.144393955754834e-07,
      "loss": 0.4929,
      "step": 58441
    },
    {
      "epoch": 1.7952876846987988,
      "grad_norm": 0.4167931377887726,
      "learning_rate": 5.142863965905532e-07,
      "loss": 0.4076,
      "step": 58442
    },
    {
      "epoch": 1.7953184038337482,
      "grad_norm": 0.4425644278526306,
      "learning_rate": 5.141334197601721e-07,
      "loss": 0.3884,
      "step": 58443
    },
    {
      "epoch": 1.7953491229686973,
      "grad_norm": 0.4036807715892792,
      "learning_rate": 5.139804650846936e-07,
      "loss": 0.4592,
      "step": 58444
    },
    {
      "epoch": 1.7953798421036464,
      "grad_norm": 0.4694865345954895,
      "learning_rate": 5.13827532564477e-07,
      "loss": 0.4628,
      "step": 58445
    },
    {
      "epoch": 1.7954105612385955,
      "grad_norm": 0.41421574354171753,
      "learning_rate": 5.136746221998779e-07,
      "loss": 0.4182,
      "step": 58446
    },
    {
      "epoch": 1.7954412803735447,
      "grad_norm": 0.4443012773990631,
      "learning_rate": 5.135217339912524e-07,
      "loss": 0.5122,
      "step": 58447
    },
    {
      "epoch": 1.7954719995084938,
      "grad_norm": 0.4887267053127289,
      "learning_rate": 5.133688679389626e-07,
      "loss": 0.4078,
      "step": 58448
    },
    {
      "epoch": 1.795502718643443,
      "grad_norm": 0.45627063512802124,
      "learning_rate": 5.132160240433604e-07,
      "loss": 0.4832,
      "step": 58449
    },
    {
      "epoch": 1.795533437778392,
      "grad_norm": 0.39874282479286194,
      "learning_rate": 5.130632023048065e-07,
      "loss": 0.4792,
      "step": 58450
    },
    {
      "epoch": 1.7955641569133414,
      "grad_norm": 0.4429100751876831,
      "learning_rate": 5.129104027236543e-07,
      "loss": 0.4846,
      "step": 58451
    },
    {
      "epoch": 1.7955948760482905,
      "grad_norm": 0.45247283577919006,
      "learning_rate": 5.12757625300263e-07,
      "loss": 0.5115,
      "step": 58452
    },
    {
      "epoch": 1.7956255951832396,
      "grad_norm": 0.4783858358860016,
      "learning_rate": 5.126048700349883e-07,
      "loss": 0.3659,
      "step": 58453
    },
    {
      "epoch": 1.795656314318189,
      "grad_norm": 0.46698129177093506,
      "learning_rate": 5.124521369281887e-07,
      "loss": 0.4956,
      "step": 58454
    },
    {
      "epoch": 1.795687033453138,
      "grad_norm": 0.41843101382255554,
      "learning_rate": 5.122994259802194e-07,
      "loss": 0.4852,
      "step": 58455
    },
    {
      "epoch": 1.7957177525880872,
      "grad_norm": 0.4353660047054291,
      "learning_rate": 5.121467371914368e-07,
      "loss": 0.4358,
      "step": 58456
    },
    {
      "epoch": 1.7957484717230363,
      "grad_norm": 0.4311263859272003,
      "learning_rate": 5.119940705621984e-07,
      "loss": 0.472,
      "step": 58457
    },
    {
      "epoch": 1.7957791908579854,
      "grad_norm": 0.40832075476646423,
      "learning_rate": 5.118414260928616e-07,
      "loss": 0.5652,
      "step": 58458
    },
    {
      "epoch": 1.7958099099929345,
      "grad_norm": 0.4643633961677551,
      "learning_rate": 5.116888037837798e-07,
      "loss": 0.4679,
      "step": 58459
    },
    {
      "epoch": 1.7958406291278837,
      "grad_norm": 0.4179057776927948,
      "learning_rate": 5.115362036353122e-07,
      "loss": 0.4084,
      "step": 58460
    },
    {
      "epoch": 1.7958713482628328,
      "grad_norm": 0.43923261761665344,
      "learning_rate": 5.113836256478144e-07,
      "loss": 0.4555,
      "step": 58461
    },
    {
      "epoch": 1.7959020673977821,
      "grad_norm": 0.4183071553707123,
      "learning_rate": 5.11231069821645e-07,
      "loss": 0.448,
      "step": 58462
    },
    {
      "epoch": 1.7959327865327313,
      "grad_norm": 0.45349547266960144,
      "learning_rate": 5.110785361571558e-07,
      "loss": 0.4812,
      "step": 58463
    },
    {
      "epoch": 1.7959635056676804,
      "grad_norm": 0.4633437693119049,
      "learning_rate": 5.109260246547054e-07,
      "loss": 0.4462,
      "step": 58464
    },
    {
      "epoch": 1.7959942248026297,
      "grad_norm": 0.4092613756656647,
      "learning_rate": 5.107735353146492e-07,
      "loss": 0.528,
      "step": 58465
    },
    {
      "epoch": 1.7960249439375788,
      "grad_norm": 0.4753207266330719,
      "learning_rate": 5.106210681373458e-07,
      "loss": 0.41,
      "step": 58466
    },
    {
      "epoch": 1.796055663072528,
      "grad_norm": 0.5684560537338257,
      "learning_rate": 5.104686231231504e-07,
      "loss": 0.437,
      "step": 58467
    },
    {
      "epoch": 1.796086382207477,
      "grad_norm": 0.39471855759620667,
      "learning_rate": 5.10316200272416e-07,
      "loss": 0.4045,
      "step": 58468
    },
    {
      "epoch": 1.7961171013424262,
      "grad_norm": 0.49754270911216736,
      "learning_rate": 5.101637995855013e-07,
      "loss": 0.4597,
      "step": 58469
    },
    {
      "epoch": 1.7961478204773753,
      "grad_norm": 0.4750302731990814,
      "learning_rate": 5.100114210627627e-07,
      "loss": 0.4901,
      "step": 58470
    },
    {
      "epoch": 1.7961785396123244,
      "grad_norm": 0.48910319805145264,
      "learning_rate": 5.098590647045554e-07,
      "loss": 0.5078,
      "step": 58471
    },
    {
      "epoch": 1.7962092587472736,
      "grad_norm": 0.4440312683582306,
      "learning_rate": 5.097067305112346e-07,
      "loss": 0.4853,
      "step": 58472
    },
    {
      "epoch": 1.7962399778822227,
      "grad_norm": 0.42521390318870544,
      "learning_rate": 5.095544184831557e-07,
      "loss": 0.4373,
      "step": 58473
    },
    {
      "epoch": 1.796270697017172,
      "grad_norm": 0.4213070869445801,
      "learning_rate": 5.094021286206762e-07,
      "loss": 0.4334,
      "step": 58474
    },
    {
      "epoch": 1.7963014161521211,
      "grad_norm": 0.4484037160873413,
      "learning_rate": 5.092498609241514e-07,
      "loss": 0.4869,
      "step": 58475
    },
    {
      "epoch": 1.7963321352870705,
      "grad_norm": 0.4506226181983948,
      "learning_rate": 5.090976153939353e-07,
      "loss": 0.454,
      "step": 58476
    },
    {
      "epoch": 1.7963628544220196,
      "grad_norm": 0.4402926564216614,
      "learning_rate": 5.089453920303855e-07,
      "loss": 0.4752,
      "step": 58477
    },
    {
      "epoch": 1.7963935735569687,
      "grad_norm": 0.46370700001716614,
      "learning_rate": 5.08793190833855e-07,
      "loss": 0.4686,
      "step": 58478
    },
    {
      "epoch": 1.7964242926919178,
      "grad_norm": 0.45199447870254517,
      "learning_rate": 5.086410118047025e-07,
      "loss": 0.4855,
      "step": 58479
    },
    {
      "epoch": 1.796455011826867,
      "grad_norm": 0.4603862464427948,
      "learning_rate": 5.08488854943281e-07,
      "loss": 0.5434,
      "step": 58480
    },
    {
      "epoch": 1.796485730961816,
      "grad_norm": 0.4880911707878113,
      "learning_rate": 5.083367202499479e-07,
      "loss": 0.4554,
      "step": 58481
    },
    {
      "epoch": 1.7965164500967652,
      "grad_norm": 0.4527157247066498,
      "learning_rate": 5.081846077250551e-07,
      "loss": 0.4127,
      "step": 58482
    },
    {
      "epoch": 1.7965471692317143,
      "grad_norm": 0.4362882077693939,
      "learning_rate": 5.080325173689604e-07,
      "loss": 0.5044,
      "step": 58483
    },
    {
      "epoch": 1.7965778883666634,
      "grad_norm": 0.42152801156044006,
      "learning_rate": 5.078804491820199e-07,
      "loss": 0.4612,
      "step": 58484
    },
    {
      "epoch": 1.7966086075016128,
      "grad_norm": 0.46587124466896057,
      "learning_rate": 5.077284031645868e-07,
      "loss": 0.3831,
      "step": 58485
    },
    {
      "epoch": 1.796639326636562,
      "grad_norm": 0.4428335726261139,
      "learning_rate": 5.075763793170185e-07,
      "loss": 0.4971,
      "step": 58486
    },
    {
      "epoch": 1.7966700457715112,
      "grad_norm": 0.4486798048019409,
      "learning_rate": 5.07424377639667e-07,
      "loss": 0.4371,
      "step": 58487
    },
    {
      "epoch": 1.7967007649064604,
      "grad_norm": 0.45483890175819397,
      "learning_rate": 5.072723981328886e-07,
      "loss": 0.5077,
      "step": 58488
    },
    {
      "epoch": 1.7967314840414095,
      "grad_norm": 0.4172295928001404,
      "learning_rate": 5.071204407970376e-07,
      "loss": 0.4315,
      "step": 58489
    },
    {
      "epoch": 1.7967622031763586,
      "grad_norm": 0.5763819217681885,
      "learning_rate": 5.069685056324725e-07,
      "loss": 0.389,
      "step": 58490
    },
    {
      "epoch": 1.7967929223113077,
      "grad_norm": 0.4104049503803253,
      "learning_rate": 5.068165926395441e-07,
      "loss": 0.501,
      "step": 58491
    },
    {
      "epoch": 1.7968236414462568,
      "grad_norm": 0.4595797061920166,
      "learning_rate": 5.066647018186077e-07,
      "loss": 0.4815,
      "step": 58492
    },
    {
      "epoch": 1.796854360581206,
      "grad_norm": 0.41802921891212463,
      "learning_rate": 5.065128331700197e-07,
      "loss": 0.4739,
      "step": 58493
    },
    {
      "epoch": 1.796885079716155,
      "grad_norm": 0.4544242322444916,
      "learning_rate": 5.063609866941344e-07,
      "loss": 0.4316,
      "step": 58494
    },
    {
      "epoch": 1.7969157988511042,
      "grad_norm": 0.4149334132671356,
      "learning_rate": 5.062091623913057e-07,
      "loss": 0.4399,
      "step": 58495
    },
    {
      "epoch": 1.7969465179860535,
      "grad_norm": 0.4781405031681061,
      "learning_rate": 5.060573602618879e-07,
      "loss": 0.5192,
      "step": 58496
    },
    {
      "epoch": 1.7969772371210027,
      "grad_norm": 0.40070196986198425,
      "learning_rate": 5.059055803062363e-07,
      "loss": 0.4539,
      "step": 58497
    },
    {
      "epoch": 1.7970079562559518,
      "grad_norm": 0.4629270136356354,
      "learning_rate": 5.057538225247071e-07,
      "loss": 0.4937,
      "step": 58498
    },
    {
      "epoch": 1.7970386753909011,
      "grad_norm": 0.4183090925216675,
      "learning_rate": 5.056020869176503e-07,
      "loss": 0.4434,
      "step": 58499
    },
    {
      "epoch": 1.7970693945258502,
      "grad_norm": 0.41270118951797485,
      "learning_rate": 5.054503734854244e-07,
      "loss": 0.3992,
      "step": 58500
    },
    {
      "epoch": 1.7971001136607994,
      "grad_norm": 0.44632190465927124,
      "learning_rate": 5.052986822283812e-07,
      "loss": 0.4862,
      "step": 58501
    },
    {
      "epoch": 1.7971308327957485,
      "grad_norm": 0.42306360602378845,
      "learning_rate": 5.051470131468772e-07,
      "loss": 0.5023,
      "step": 58502
    },
    {
      "epoch": 1.7971615519306976,
      "grad_norm": 0.40034016966819763,
      "learning_rate": 5.049953662412654e-07,
      "loss": 0.4341,
      "step": 58503
    },
    {
      "epoch": 1.7971922710656467,
      "grad_norm": 0.4757935702800751,
      "learning_rate": 5.048437415119001e-07,
      "loss": 0.4782,
      "step": 58504
    },
    {
      "epoch": 1.7972229902005958,
      "grad_norm": 0.40555068850517273,
      "learning_rate": 5.046921389591341e-07,
      "loss": 0.4442,
      "step": 58505
    },
    {
      "epoch": 1.797253709335545,
      "grad_norm": 0.4537127912044525,
      "learning_rate": 5.04540558583323e-07,
      "loss": 0.5259,
      "step": 58506
    },
    {
      "epoch": 1.7972844284704943,
      "grad_norm": 0.4846298396587372,
      "learning_rate": 5.043890003848228e-07,
      "loss": 0.5242,
      "step": 58507
    },
    {
      "epoch": 1.7973151476054434,
      "grad_norm": 0.5047542452812195,
      "learning_rate": 5.042374643639825e-07,
      "loss": 0.4206,
      "step": 58508
    },
    {
      "epoch": 1.7973458667403925,
      "grad_norm": 0.45467621088027954,
      "learning_rate": 5.040859505211615e-07,
      "loss": 0.5271,
      "step": 58509
    },
    {
      "epoch": 1.7973765858753419,
      "grad_norm": 0.46956613659858704,
      "learning_rate": 5.039344588567075e-07,
      "loss": 0.5202,
      "step": 58510
    },
    {
      "epoch": 1.797407305010291,
      "grad_norm": 0.3999048173427582,
      "learning_rate": 5.037829893709811e-07,
      "loss": 0.4508,
      "step": 58511
    },
    {
      "epoch": 1.7974380241452401,
      "grad_norm": 0.4497978091239929,
      "learning_rate": 5.036315420643312e-07,
      "loss": 0.5237,
      "step": 58512
    },
    {
      "epoch": 1.7974687432801892,
      "grad_norm": 0.43760818243026733,
      "learning_rate": 5.03480116937114e-07,
      "loss": 0.4926,
      "step": 58513
    },
    {
      "epoch": 1.7974994624151384,
      "grad_norm": 0.45382052659988403,
      "learning_rate": 5.033287139896792e-07,
      "loss": 0.4785,
      "step": 58514
    },
    {
      "epoch": 1.7975301815500875,
      "grad_norm": 0.4724065065383911,
      "learning_rate": 5.031773332223866e-07,
      "loss": 0.4258,
      "step": 58515
    },
    {
      "epoch": 1.7975609006850366,
      "grad_norm": 0.3900020718574524,
      "learning_rate": 5.030259746355848e-07,
      "loss": 0.4103,
      "step": 58516
    },
    {
      "epoch": 1.7975916198199857,
      "grad_norm": 0.5295936465263367,
      "learning_rate": 5.028746382296313e-07,
      "loss": 0.4524,
      "step": 58517
    },
    {
      "epoch": 1.797622338954935,
      "grad_norm": 0.41831016540527344,
      "learning_rate": 5.027233240048757e-07,
      "loss": 0.3773,
      "step": 58518
    },
    {
      "epoch": 1.7976530580898842,
      "grad_norm": 0.4379023611545563,
      "learning_rate": 5.025720319616712e-07,
      "loss": 0.5465,
      "step": 58519
    },
    {
      "epoch": 1.7976837772248333,
      "grad_norm": 0.409784197807312,
      "learning_rate": 5.024207621003762e-07,
      "loss": 0.4034,
      "step": 58520
    },
    {
      "epoch": 1.7977144963597826,
      "grad_norm": 0.4200194180011749,
      "learning_rate": 5.022695144213396e-07,
      "loss": 0.4655,
      "step": 58521
    },
    {
      "epoch": 1.7977452154947318,
      "grad_norm": 0.45265209674835205,
      "learning_rate": 5.021182889249176e-07,
      "loss": 0.5193,
      "step": 58522
    },
    {
      "epoch": 1.7977759346296809,
      "grad_norm": 0.43301746249198914,
      "learning_rate": 5.01967085611459e-07,
      "loss": 0.4751,
      "step": 58523
    },
    {
      "epoch": 1.79780665376463,
      "grad_norm": 0.42939311265945435,
      "learning_rate": 5.018159044813209e-07,
      "loss": 0.3818,
      "step": 58524
    },
    {
      "epoch": 1.7978373728995791,
      "grad_norm": 0.4723227322101593,
      "learning_rate": 5.016647455348544e-07,
      "loss": 0.4385,
      "step": 58525
    },
    {
      "epoch": 1.7978680920345282,
      "grad_norm": 0.4310661852359772,
      "learning_rate": 5.015136087724149e-07,
      "loss": 0.4949,
      "step": 58526
    },
    {
      "epoch": 1.7978988111694774,
      "grad_norm": 0.4458901882171631,
      "learning_rate": 5.013624941943518e-07,
      "loss": 0.4302,
      "step": 58527
    },
    {
      "epoch": 1.7979295303044265,
      "grad_norm": 0.4450662136077881,
      "learning_rate": 5.012114018010206e-07,
      "loss": 0.4664,
      "step": 58528
    },
    {
      "epoch": 1.7979602494393758,
      "grad_norm": 0.43245455622673035,
      "learning_rate": 5.010603315927731e-07,
      "loss": 0.4565,
      "step": 58529
    },
    {
      "epoch": 1.797990968574325,
      "grad_norm": 0.4130735695362091,
      "learning_rate": 5.009092835699636e-07,
      "loss": 0.3524,
      "step": 58530
    },
    {
      "epoch": 1.798021687709274,
      "grad_norm": 0.4383736550807953,
      "learning_rate": 5.00758257732944e-07,
      "loss": 0.4394,
      "step": 58531
    },
    {
      "epoch": 1.7980524068442234,
      "grad_norm": 0.47137293219566345,
      "learning_rate": 5.00607254082065e-07,
      "loss": 0.484,
      "step": 58532
    },
    {
      "epoch": 1.7980831259791725,
      "grad_norm": 0.4280789792537689,
      "learning_rate": 5.004562726176831e-07,
      "loss": 0.4357,
      "step": 58533
    },
    {
      "epoch": 1.7981138451141216,
      "grad_norm": 0.4542867839336395,
      "learning_rate": 5.003053133401492e-07,
      "loss": 0.4654,
      "step": 58534
    },
    {
      "epoch": 1.7981445642490708,
      "grad_norm": 0.4734672009944916,
      "learning_rate": 5.00154376249814e-07,
      "loss": 0.4786,
      "step": 58535
    },
    {
      "epoch": 1.7981752833840199,
      "grad_norm": 0.4190938174724579,
      "learning_rate": 5.000034613470328e-07,
      "loss": 0.423,
      "step": 58536
    },
    {
      "epoch": 1.798206002518969,
      "grad_norm": 0.3786550462245941,
      "learning_rate": 4.998525686321564e-07,
      "loss": 0.4873,
      "step": 58537
    },
    {
      "epoch": 1.7982367216539181,
      "grad_norm": 0.4611961841583252,
      "learning_rate": 4.997016981055381e-07,
      "loss": 0.4387,
      "step": 58538
    },
    {
      "epoch": 1.7982674407888672,
      "grad_norm": 0.47441282868385315,
      "learning_rate": 4.995508497675305e-07,
      "loss": 0.465,
      "step": 58539
    },
    {
      "epoch": 1.7982981599238166,
      "grad_norm": 0.43675509095191956,
      "learning_rate": 4.994000236184848e-07,
      "loss": 0.5399,
      "step": 58540
    },
    {
      "epoch": 1.7983288790587657,
      "grad_norm": 0.4439503848552704,
      "learning_rate": 4.99249219658754e-07,
      "loss": 0.4266,
      "step": 58541
    },
    {
      "epoch": 1.7983595981937148,
      "grad_norm": 0.3909035921096802,
      "learning_rate": 4.990984378886899e-07,
      "loss": 0.3915,
      "step": 58542
    },
    {
      "epoch": 1.7983903173286642,
      "grad_norm": 0.4299674928188324,
      "learning_rate": 4.989476783086467e-07,
      "loss": 0.4609,
      "step": 58543
    },
    {
      "epoch": 1.7984210364636133,
      "grad_norm": 0.4504111111164093,
      "learning_rate": 4.987969409189731e-07,
      "loss": 0.3937,
      "step": 58544
    },
    {
      "epoch": 1.7984517555985624,
      "grad_norm": 0.4163760840892792,
      "learning_rate": 4.986462257200231e-07,
      "loss": 0.4307,
      "step": 58545
    },
    {
      "epoch": 1.7984824747335115,
      "grad_norm": 0.4291386902332306,
      "learning_rate": 4.984955327121466e-07,
      "loss": 0.4877,
      "step": 58546
    },
    {
      "epoch": 1.7985131938684606,
      "grad_norm": 0.40986475348472595,
      "learning_rate": 4.98344861895701e-07,
      "loss": 0.4555,
      "step": 58547
    },
    {
      "epoch": 1.7985439130034098,
      "grad_norm": 0.4307723045349121,
      "learning_rate": 4.981942132710316e-07,
      "loss": 0.4547,
      "step": 58548
    },
    {
      "epoch": 1.7985746321383589,
      "grad_norm": 0.416907399892807,
      "learning_rate": 4.980435868384959e-07,
      "loss": 0.4234,
      "step": 58549
    },
    {
      "epoch": 1.798605351273308,
      "grad_norm": 0.4148138463497162,
      "learning_rate": 4.978929825984402e-07,
      "loss": 0.4658,
      "step": 58550
    },
    {
      "epoch": 1.7986360704082573,
      "grad_norm": 0.48362475633621216,
      "learning_rate": 4.977424005512199e-07,
      "loss": 0.4234,
      "step": 58551
    },
    {
      "epoch": 1.7986667895432065,
      "grad_norm": 0.40050017833709717,
      "learning_rate": 4.975918406971869e-07,
      "loss": 0.4971,
      "step": 58552
    },
    {
      "epoch": 1.7986975086781556,
      "grad_norm": 0.42888155579566956,
      "learning_rate": 4.97441303036692e-07,
      "loss": 0.5035,
      "step": 58553
    },
    {
      "epoch": 1.798728227813105,
      "grad_norm": 0.40101444721221924,
      "learning_rate": 4.97290787570085e-07,
      "loss": 0.4815,
      "step": 58554
    },
    {
      "epoch": 1.798758946948054,
      "grad_norm": 0.44410380721092224,
      "learning_rate": 4.971402942977188e-07,
      "loss": 0.421,
      "step": 58555
    },
    {
      "epoch": 1.7987896660830032,
      "grad_norm": 0.43118512630462646,
      "learning_rate": 4.969898232199466e-07,
      "loss": 0.4717,
      "step": 58556
    },
    {
      "epoch": 1.7988203852179523,
      "grad_norm": 0.45739153027534485,
      "learning_rate": 4.968393743371169e-07,
      "loss": 0.4915,
      "step": 58557
    },
    {
      "epoch": 1.7988511043529014,
      "grad_norm": 0.4787227511405945,
      "learning_rate": 4.966889476495839e-07,
      "loss": 0.5018,
      "step": 58558
    },
    {
      "epoch": 1.7988818234878505,
      "grad_norm": 0.48981472849845886,
      "learning_rate": 4.965385431576974e-07,
      "loss": 0.4411,
      "step": 58559
    },
    {
      "epoch": 1.7989125426227996,
      "grad_norm": 0.4847748279571533,
      "learning_rate": 4.963881608618082e-07,
      "loss": 0.4888,
      "step": 58560
    },
    {
      "epoch": 1.7989432617577488,
      "grad_norm": 0.43134650588035583,
      "learning_rate": 4.962378007622682e-07,
      "loss": 0.4547,
      "step": 58561
    },
    {
      "epoch": 1.798973980892698,
      "grad_norm": 0.426388144493103,
      "learning_rate": 4.960874628594292e-07,
      "loss": 0.5299,
      "step": 58562
    },
    {
      "epoch": 1.7990047000276472,
      "grad_norm": 0.43660449981689453,
      "learning_rate": 4.959371471536411e-07,
      "loss": 0.4823,
      "step": 58563
    },
    {
      "epoch": 1.7990354191625963,
      "grad_norm": 0.4451226592063904,
      "learning_rate": 4.957868536452559e-07,
      "loss": 0.4328,
      "step": 58564
    },
    {
      "epoch": 1.7990661382975457,
      "grad_norm": 0.3903292417526245,
      "learning_rate": 4.956365823346232e-07,
      "loss": 0.4779,
      "step": 58565
    },
    {
      "epoch": 1.7990968574324948,
      "grad_norm": 0.4473087191581726,
      "learning_rate": 4.954863332220972e-07,
      "loss": 0.5671,
      "step": 58566
    },
    {
      "epoch": 1.799127576567444,
      "grad_norm": 0.4426298439502716,
      "learning_rate": 4.953361063080253e-07,
      "loss": 0.4066,
      "step": 58567
    },
    {
      "epoch": 1.799158295702393,
      "grad_norm": 0.4337218999862671,
      "learning_rate": 4.951859015927596e-07,
      "loss": 0.4882,
      "step": 58568
    },
    {
      "epoch": 1.7991890148373422,
      "grad_norm": 0.5037738680839539,
      "learning_rate": 4.950357190766509e-07,
      "loss": 0.4654,
      "step": 58569
    },
    {
      "epoch": 1.7992197339722913,
      "grad_norm": 0.465747594833374,
      "learning_rate": 4.94885558760052e-07,
      "loss": 0.4363,
      "step": 58570
    },
    {
      "epoch": 1.7992504531072404,
      "grad_norm": 0.4256250560283661,
      "learning_rate": 4.947354206433097e-07,
      "loss": 0.5225,
      "step": 58571
    },
    {
      "epoch": 1.7992811722421895,
      "grad_norm": 0.4256289303302765,
      "learning_rate": 4.945853047267779e-07,
      "loss": 0.3947,
      "step": 58572
    },
    {
      "epoch": 1.7993118913771389,
      "grad_norm": 0.41791197657585144,
      "learning_rate": 4.944352110108031e-07,
      "loss": 0.419,
      "step": 58573
    },
    {
      "epoch": 1.799342610512088,
      "grad_norm": 0.4598838984966278,
      "learning_rate": 4.942851394957404e-07,
      "loss": 0.4294,
      "step": 58574
    },
    {
      "epoch": 1.7993733296470371,
      "grad_norm": 0.4908003807067871,
      "learning_rate": 4.941350901819409e-07,
      "loss": 0.4468,
      "step": 58575
    },
    {
      "epoch": 1.7994040487819865,
      "grad_norm": 0.4132854640483856,
      "learning_rate": 4.939850630697507e-07,
      "loss": 0.4732,
      "step": 58576
    },
    {
      "epoch": 1.7994347679169356,
      "grad_norm": 0.4501703083515167,
      "learning_rate": 4.93835058159522e-07,
      "loss": 0.443,
      "step": 58577
    },
    {
      "epoch": 1.7994654870518847,
      "grad_norm": 0.4338987469673157,
      "learning_rate": 4.936850754516054e-07,
      "loss": 0.3949,
      "step": 58578
    },
    {
      "epoch": 1.7994962061868338,
      "grad_norm": 0.44737961888313293,
      "learning_rate": 4.93535114946353e-07,
      "loss": 0.4529,
      "step": 58579
    },
    {
      "epoch": 1.799526925321783,
      "grad_norm": 0.419351726770401,
      "learning_rate": 4.933851766441111e-07,
      "loss": 0.4733,
      "step": 58580
    },
    {
      "epoch": 1.799557644456732,
      "grad_norm": 0.4257282614707947,
      "learning_rate": 4.932352605452339e-07,
      "loss": 0.4661,
      "step": 58581
    },
    {
      "epoch": 1.7995883635916812,
      "grad_norm": 0.5268518924713135,
      "learning_rate": 4.930853666500679e-07,
      "loss": 0.492,
      "step": 58582
    },
    {
      "epoch": 1.7996190827266303,
      "grad_norm": 0.45002877712249756,
      "learning_rate": 4.929354949589671e-07,
      "loss": 0.4029,
      "step": 58583
    },
    {
      "epoch": 1.7996498018615794,
      "grad_norm": 0.5110694766044617,
      "learning_rate": 4.927856454722779e-07,
      "loss": 0.4352,
      "step": 58584
    },
    {
      "epoch": 1.7996805209965288,
      "grad_norm": 0.38865169882774353,
      "learning_rate": 4.926358181903523e-07,
      "loss": 0.4406,
      "step": 58585
    },
    {
      "epoch": 1.7997112401314779,
      "grad_norm": 0.4291226267814636,
      "learning_rate": 4.9248601311354e-07,
      "loss": 0.4499,
      "step": 58586
    },
    {
      "epoch": 1.7997419592664272,
      "grad_norm": 0.47192177176475525,
      "learning_rate": 4.923362302421897e-07,
      "loss": 0.4492,
      "step": 58587
    },
    {
      "epoch": 1.7997726784013763,
      "grad_norm": 0.4218870997428894,
      "learning_rate": 4.921864695766521e-07,
      "loss": 0.4246,
      "step": 58588
    },
    {
      "epoch": 1.7998033975363255,
      "grad_norm": 0.503994882106781,
      "learning_rate": 4.92036731117278e-07,
      "loss": 0.4497,
      "step": 58589
    },
    {
      "epoch": 1.7998341166712746,
      "grad_norm": 0.40621334314346313,
      "learning_rate": 4.918870148644162e-07,
      "loss": 0.4224,
      "step": 58590
    },
    {
      "epoch": 1.7998648358062237,
      "grad_norm": 0.39483073353767395,
      "learning_rate": 4.91737320818415e-07,
      "loss": 0.4471,
      "step": 58591
    },
    {
      "epoch": 1.7998955549411728,
      "grad_norm": 0.4141109585762024,
      "learning_rate": 4.915876489796256e-07,
      "loss": 0.4749,
      "step": 58592
    },
    {
      "epoch": 1.799926274076122,
      "grad_norm": 0.43874192237854004,
      "learning_rate": 4.914379993483975e-07,
      "loss": 0.4175,
      "step": 58593
    },
    {
      "epoch": 1.799956993211071,
      "grad_norm": 0.40196365118026733,
      "learning_rate": 4.912883719250817e-07,
      "loss": 0.5032,
      "step": 58594
    },
    {
      "epoch": 1.7999877123460202,
      "grad_norm": 0.41858425736427307,
      "learning_rate": 4.911387667100243e-07,
      "loss": 0.5368,
      "step": 58595
    },
    {
      "epoch": 1.8000184314809695,
      "grad_norm": 0.44177359342575073,
      "learning_rate": 4.909891837035762e-07,
      "loss": 0.3692,
      "step": 58596
    },
    {
      "epoch": 1.8000491506159186,
      "grad_norm": 0.46566125750541687,
      "learning_rate": 4.908396229060864e-07,
      "loss": 0.4942,
      "step": 58597
    },
    {
      "epoch": 1.800079869750868,
      "grad_norm": 0.41708019375801086,
      "learning_rate": 4.906900843179074e-07,
      "loss": 0.4198,
      "step": 58598
    },
    {
      "epoch": 1.800110588885817,
      "grad_norm": 0.6593025326728821,
      "learning_rate": 4.905405679393838e-07,
      "loss": 0.4264,
      "step": 58599
    },
    {
      "epoch": 1.8001413080207662,
      "grad_norm": 0.42226549983024597,
      "learning_rate": 4.903910737708672e-07,
      "loss": 0.4406,
      "step": 58600
    },
    {
      "epoch": 1.8001720271557153,
      "grad_norm": 0.4542396366596222,
      "learning_rate": 4.902416018127065e-07,
      "loss": 0.4327,
      "step": 58601
    },
    {
      "epoch": 1.8002027462906645,
      "grad_norm": 0.43356674909591675,
      "learning_rate": 4.900921520652513e-07,
      "loss": 0.4088,
      "step": 58602
    },
    {
      "epoch": 1.8002334654256136,
      "grad_norm": 0.41110849380493164,
      "learning_rate": 4.899427245288491e-07,
      "loss": 0.4121,
      "step": 58603
    },
    {
      "epoch": 1.8002641845605627,
      "grad_norm": 0.4319789409637451,
      "learning_rate": 4.897933192038496e-07,
      "loss": 0.3923,
      "step": 58604
    },
    {
      "epoch": 1.8002949036955118,
      "grad_norm": 0.40258628129959106,
      "learning_rate": 4.896439360906024e-07,
      "loss": 0.5395,
      "step": 58605
    },
    {
      "epoch": 1.800325622830461,
      "grad_norm": 0.4499569237232208,
      "learning_rate": 4.894945751894575e-07,
      "loss": 0.452,
      "step": 58606
    },
    {
      "epoch": 1.8003563419654103,
      "grad_norm": 0.4286767542362213,
      "learning_rate": 4.893452365007601e-07,
      "loss": 0.4535,
      "step": 58607
    },
    {
      "epoch": 1.8003870611003594,
      "grad_norm": 0.47478410601615906,
      "learning_rate": 4.89195920024863e-07,
      "loss": 0.4952,
      "step": 58608
    },
    {
      "epoch": 1.8004177802353087,
      "grad_norm": 0.44964849948883057,
      "learning_rate": 4.890466257621107e-07,
      "loss": 0.5092,
      "step": 58609
    },
    {
      "epoch": 1.8004484993702579,
      "grad_norm": 0.42758849263191223,
      "learning_rate": 4.888973537128561e-07,
      "loss": 0.5429,
      "step": 58610
    },
    {
      "epoch": 1.800479218505207,
      "grad_norm": 0.42039939761161804,
      "learning_rate": 4.887481038774455e-07,
      "loss": 0.4856,
      "step": 58611
    },
    {
      "epoch": 1.800509937640156,
      "grad_norm": 0.41116178035736084,
      "learning_rate": 4.885988762562266e-07,
      "loss": 0.467,
      "step": 58612
    },
    {
      "epoch": 1.8005406567751052,
      "grad_norm": 0.4217509627342224,
      "learning_rate": 4.884496708495523e-07,
      "loss": 0.5016,
      "step": 58613
    },
    {
      "epoch": 1.8005713759100543,
      "grad_norm": 0.4203362762928009,
      "learning_rate": 4.883004876577646e-07,
      "loss": 0.4995,
      "step": 58614
    },
    {
      "epoch": 1.8006020950450035,
      "grad_norm": 0.423194020986557,
      "learning_rate": 4.881513266812177e-07,
      "loss": 0.4554,
      "step": 58615
    },
    {
      "epoch": 1.8006328141799526,
      "grad_norm": 0.4447019696235657,
      "learning_rate": 4.880021879202567e-07,
      "loss": 0.462,
      "step": 58616
    },
    {
      "epoch": 1.8006635333149017,
      "grad_norm": 0.44360455870628357,
      "learning_rate": 4.878530713752328e-07,
      "loss": 0.4313,
      "step": 58617
    },
    {
      "epoch": 1.800694252449851,
      "grad_norm": 0.6785140633583069,
      "learning_rate": 4.877039770464886e-07,
      "loss": 0.4867,
      "step": 58618
    },
    {
      "epoch": 1.8007249715848002,
      "grad_norm": 0.4594421088695526,
      "learning_rate": 4.875549049343797e-07,
      "loss": 0.4416,
      "step": 58619
    },
    {
      "epoch": 1.8007556907197493,
      "grad_norm": 0.41540274024009705,
      "learning_rate": 4.874058550392491e-07,
      "loss": 0.492,
      "step": 58620
    },
    {
      "epoch": 1.8007864098546986,
      "grad_norm": 0.4448796808719635,
      "learning_rate": 4.872568273614476e-07,
      "loss": 0.4477,
      "step": 58621
    },
    {
      "epoch": 1.8008171289896477,
      "grad_norm": 0.48296770453453064,
      "learning_rate": 4.871078219013203e-07,
      "loss": 0.5375,
      "step": 58622
    },
    {
      "epoch": 1.8008478481245969,
      "grad_norm": 0.4187975525856018,
      "learning_rate": 4.869588386592184e-07,
      "loss": 0.5612,
      "step": 58623
    },
    {
      "epoch": 1.800878567259546,
      "grad_norm": 0.4503268599510193,
      "learning_rate": 4.868098776354879e-07,
      "loss": 0.3807,
      "step": 58624
    },
    {
      "epoch": 1.800909286394495,
      "grad_norm": 0.4215673804283142,
      "learning_rate": 4.866609388304777e-07,
      "loss": 0.4539,
      "step": 58625
    },
    {
      "epoch": 1.8009400055294442,
      "grad_norm": 0.41989460587501526,
      "learning_rate": 4.865120222445352e-07,
      "loss": 0.405,
      "step": 58626
    },
    {
      "epoch": 1.8009707246643933,
      "grad_norm": 0.47375771403312683,
      "learning_rate": 4.863631278780079e-07,
      "loss": 0.4985,
      "step": 58627
    },
    {
      "epoch": 1.8010014437993425,
      "grad_norm": 0.4218136668205261,
      "learning_rate": 4.862142557312443e-07,
      "loss": 0.5159,
      "step": 58628
    },
    {
      "epoch": 1.8010321629342918,
      "grad_norm": 0.42950311303138733,
      "learning_rate": 4.860654058045911e-07,
      "loss": 0.4303,
      "step": 58629
    },
    {
      "epoch": 1.801062882069241,
      "grad_norm": 0.4175598919391632,
      "learning_rate": 4.859165780983977e-07,
      "loss": 0.5327,
      "step": 58630
    },
    {
      "epoch": 1.80109360120419,
      "grad_norm": 0.5410738587379456,
      "learning_rate": 4.857677726130094e-07,
      "loss": 0.4746,
      "step": 58631
    },
    {
      "epoch": 1.8011243203391394,
      "grad_norm": 0.4300899803638458,
      "learning_rate": 4.856189893487762e-07,
      "loss": 0.4379,
      "step": 58632
    },
    {
      "epoch": 1.8011550394740885,
      "grad_norm": 0.4555547535419464,
      "learning_rate": 4.854702283060431e-07,
      "loss": 0.5702,
      "step": 58633
    },
    {
      "epoch": 1.8011857586090376,
      "grad_norm": 0.5341253280639648,
      "learning_rate": 4.853214894851599e-07,
      "loss": 0.4405,
      "step": 58634
    },
    {
      "epoch": 1.8012164777439867,
      "grad_norm": 0.41967669129371643,
      "learning_rate": 4.851727728864719e-07,
      "loss": 0.4616,
      "step": 58635
    },
    {
      "epoch": 1.8012471968789359,
      "grad_norm": 0.41937392950057983,
      "learning_rate": 4.850240785103277e-07,
      "loss": 0.3903,
      "step": 58636
    },
    {
      "epoch": 1.801277916013885,
      "grad_norm": 0.4168364405632019,
      "learning_rate": 4.848754063570738e-07,
      "loss": 0.5359,
      "step": 58637
    },
    {
      "epoch": 1.801308635148834,
      "grad_norm": 0.5021550059318542,
      "learning_rate": 4.847267564270597e-07,
      "loss": 0.4784,
      "step": 58638
    },
    {
      "epoch": 1.8013393542837832,
      "grad_norm": 0.4011969268321991,
      "learning_rate": 4.845781287206297e-07,
      "loss": 0.3767,
      "step": 58639
    },
    {
      "epoch": 1.8013700734187326,
      "grad_norm": 0.43307924270629883,
      "learning_rate": 4.844295232381313e-07,
      "loss": 0.4781,
      "step": 58640
    },
    {
      "epoch": 1.8014007925536817,
      "grad_norm": 0.42265695333480835,
      "learning_rate": 4.842809399799131e-07,
      "loss": 0.5022,
      "step": 58641
    },
    {
      "epoch": 1.8014315116886308,
      "grad_norm": 0.43692782521247864,
      "learning_rate": 4.841323789463226e-07,
      "loss": 0.4794,
      "step": 58642
    },
    {
      "epoch": 1.8014622308235801,
      "grad_norm": 0.44907185435295105,
      "learning_rate": 4.839838401377029e-07,
      "loss": 0.4324,
      "step": 58643
    },
    {
      "epoch": 1.8014929499585293,
      "grad_norm": 0.42691510915756226,
      "learning_rate": 4.838353235544058e-07,
      "loss": 0.4528,
      "step": 58644
    },
    {
      "epoch": 1.8015236690934784,
      "grad_norm": 0.44904908537864685,
      "learning_rate": 4.836868291967734e-07,
      "loss": 0.4913,
      "step": 58645
    },
    {
      "epoch": 1.8015543882284275,
      "grad_norm": 0.4565529227256775,
      "learning_rate": 4.835383570651575e-07,
      "loss": 0.4573,
      "step": 58646
    },
    {
      "epoch": 1.8015851073633766,
      "grad_norm": 0.43987712264060974,
      "learning_rate": 4.833899071599013e-07,
      "loss": 0.5193,
      "step": 58647
    },
    {
      "epoch": 1.8016158264983257,
      "grad_norm": 0.6362833976745605,
      "learning_rate": 4.832414794813522e-07,
      "loss": 0.4023,
      "step": 58648
    },
    {
      "epoch": 1.8016465456332749,
      "grad_norm": 0.43915191292762756,
      "learning_rate": 4.830930740298589e-07,
      "loss": 0.4929,
      "step": 58649
    },
    {
      "epoch": 1.801677264768224,
      "grad_norm": 0.4211583137512207,
      "learning_rate": 4.829446908057634e-07,
      "loss": 0.4506,
      "step": 58650
    },
    {
      "epoch": 1.8017079839031733,
      "grad_norm": 0.4107595682144165,
      "learning_rate": 4.827963298094174e-07,
      "loss": 0.4786,
      "step": 58651
    },
    {
      "epoch": 1.8017387030381224,
      "grad_norm": 0.4178084433078766,
      "learning_rate": 4.826479910411652e-07,
      "loss": 0.4639,
      "step": 58652
    },
    {
      "epoch": 1.8017694221730716,
      "grad_norm": 0.479930579662323,
      "learning_rate": 4.824996745013544e-07,
      "loss": 0.4548,
      "step": 58653
    },
    {
      "epoch": 1.801800141308021,
      "grad_norm": 0.44547849893569946,
      "learning_rate": 4.823513801903279e-07,
      "loss": 0.4283,
      "step": 58654
    },
    {
      "epoch": 1.80183086044297,
      "grad_norm": 0.45085084438323975,
      "learning_rate": 4.822031081084355e-07,
      "loss": 0.5861,
      "step": 58655
    },
    {
      "epoch": 1.8018615795779191,
      "grad_norm": 0.4290906488895416,
      "learning_rate": 4.820548582560214e-07,
      "loss": 0.419,
      "step": 58656
    },
    {
      "epoch": 1.8018922987128683,
      "grad_norm": 0.4239327907562256,
      "learning_rate": 4.819066306334353e-07,
      "loss": 0.5032,
      "step": 58657
    },
    {
      "epoch": 1.8019230178478174,
      "grad_norm": 0.4088590145111084,
      "learning_rate": 4.81758425241019e-07,
      "loss": 0.473,
      "step": 58658
    },
    {
      "epoch": 1.8019537369827665,
      "grad_norm": 0.41099557280540466,
      "learning_rate": 4.816102420791213e-07,
      "loss": 0.4402,
      "step": 58659
    },
    {
      "epoch": 1.8019844561177156,
      "grad_norm": 0.43090885877609253,
      "learning_rate": 4.814620811480875e-07,
      "loss": 0.4523,
      "step": 58660
    },
    {
      "epoch": 1.8020151752526647,
      "grad_norm": 0.4150572121143341,
      "learning_rate": 4.813139424482649e-07,
      "loss": 0.4806,
      "step": 58661
    },
    {
      "epoch": 1.802045894387614,
      "grad_norm": 0.551104724407196,
      "learning_rate": 4.811658259799967e-07,
      "loss": 0.489,
      "step": 58662
    },
    {
      "epoch": 1.8020766135225632,
      "grad_norm": 0.44066062569618225,
      "learning_rate": 4.810177317436304e-07,
      "loss": 0.4247,
      "step": 58663
    },
    {
      "epoch": 1.8021073326575123,
      "grad_norm": 0.44792431592941284,
      "learning_rate": 4.808696597395124e-07,
      "loss": 0.4462,
      "step": 58664
    },
    {
      "epoch": 1.8021380517924617,
      "grad_norm": 0.4875470995903015,
      "learning_rate": 4.80721609967989e-07,
      "loss": 0.5187,
      "step": 58665
    },
    {
      "epoch": 1.8021687709274108,
      "grad_norm": 0.383989155292511,
      "learning_rate": 4.805735824294056e-07,
      "loss": 0.4002,
      "step": 58666
    },
    {
      "epoch": 1.80219949006236,
      "grad_norm": 0.5039772987365723,
      "learning_rate": 4.804255771241051e-07,
      "loss": 0.4794,
      "step": 58667
    },
    {
      "epoch": 1.802230209197309,
      "grad_norm": 0.44578149914741516,
      "learning_rate": 4.802775940524374e-07,
      "loss": 0.4641,
      "step": 58668
    },
    {
      "epoch": 1.8022609283322581,
      "grad_norm": 0.4668458104133606,
      "learning_rate": 4.801296332147442e-07,
      "loss": 0.3753,
      "step": 58669
    },
    {
      "epoch": 1.8022916474672073,
      "grad_norm": 0.4954722821712494,
      "learning_rate": 4.799816946113755e-07,
      "loss": 0.4556,
      "step": 58670
    },
    {
      "epoch": 1.8023223666021564,
      "grad_norm": 0.43107831478118896,
      "learning_rate": 4.798337782426732e-07,
      "loss": 0.4332,
      "step": 58671
    },
    {
      "epoch": 1.8023530857371055,
      "grad_norm": 0.4221034646034241,
      "learning_rate": 4.796858841089846e-07,
      "loss": 0.452,
      "step": 58672
    },
    {
      "epoch": 1.8023838048720549,
      "grad_norm": 0.4919201135635376,
      "learning_rate": 4.79538012210653e-07,
      "loss": 0.469,
      "step": 58673
    },
    {
      "epoch": 1.802414524007004,
      "grad_norm": 0.4300753176212311,
      "learning_rate": 4.79390162548028e-07,
      "loss": 0.5131,
      "step": 58674
    },
    {
      "epoch": 1.802445243141953,
      "grad_norm": 0.4072548747062683,
      "learning_rate": 4.792423351214504e-07,
      "loss": 0.4929,
      "step": 58675
    },
    {
      "epoch": 1.8024759622769024,
      "grad_norm": 0.4291650056838989,
      "learning_rate": 4.790945299312677e-07,
      "loss": 0.5033,
      "step": 58676
    },
    {
      "epoch": 1.8025066814118516,
      "grad_norm": 0.4224335253238678,
      "learning_rate": 4.78946746977823e-07,
      "loss": 0.476,
      "step": 58677
    },
    {
      "epoch": 1.8025374005468007,
      "grad_norm": 0.45290374755859375,
      "learning_rate": 4.787989862614662e-07,
      "loss": 0.4452,
      "step": 58678
    },
    {
      "epoch": 1.8025681196817498,
      "grad_norm": 0.4332585036754608,
      "learning_rate": 4.786512477825367e-07,
      "loss": 0.4209,
      "step": 58679
    },
    {
      "epoch": 1.802598838816699,
      "grad_norm": 0.3798539936542511,
      "learning_rate": 4.785035315413844e-07,
      "loss": 0.4519,
      "step": 58680
    },
    {
      "epoch": 1.802629557951648,
      "grad_norm": 0.44493260979652405,
      "learning_rate": 4.78355837538349e-07,
      "loss": 0.5107,
      "step": 58681
    },
    {
      "epoch": 1.8026602770865972,
      "grad_norm": 0.5570630431175232,
      "learning_rate": 4.782081657737813e-07,
      "loss": 0.4206,
      "step": 58682
    },
    {
      "epoch": 1.8026909962215463,
      "grad_norm": 0.442915141582489,
      "learning_rate": 4.780605162480223e-07,
      "loss": 0.4817,
      "step": 58683
    },
    {
      "epoch": 1.8027217153564956,
      "grad_norm": 0.44205647706985474,
      "learning_rate": 4.779128889614171e-07,
      "loss": 0.4969,
      "step": 58684
    },
    {
      "epoch": 1.8027524344914447,
      "grad_norm": 0.4712011516094208,
      "learning_rate": 4.777652839143143e-07,
      "loss": 0.5315,
      "step": 58685
    },
    {
      "epoch": 1.8027831536263939,
      "grad_norm": 0.47316086292266846,
      "learning_rate": 4.776177011070516e-07,
      "loss": 0.5131,
      "step": 58686
    },
    {
      "epoch": 1.8028138727613432,
      "grad_norm": 0.4375797510147095,
      "learning_rate": 4.774701405399806e-07,
      "loss": 0.4645,
      "step": 58687
    },
    {
      "epoch": 1.8028445918962923,
      "grad_norm": 0.4722479581832886,
      "learning_rate": 4.773226022134425e-07,
      "loss": 0.5673,
      "step": 58688
    },
    {
      "epoch": 1.8028753110312414,
      "grad_norm": 0.4088735282421112,
      "learning_rate": 4.771750861277835e-07,
      "loss": 0.3785,
      "step": 58689
    },
    {
      "epoch": 1.8029060301661906,
      "grad_norm": 0.467346727848053,
      "learning_rate": 4.770275922833456e-07,
      "loss": 0.4965,
      "step": 58690
    },
    {
      "epoch": 1.8029367493011397,
      "grad_norm": 0.4606066644191742,
      "learning_rate": 4.768801206804752e-07,
      "loss": 0.5411,
      "step": 58691
    },
    {
      "epoch": 1.8029674684360888,
      "grad_norm": 0.4198007881641388,
      "learning_rate": 4.767326713195164e-07,
      "loss": 0.4286,
      "step": 58692
    },
    {
      "epoch": 1.802998187571038,
      "grad_norm": 0.47803282737731934,
      "learning_rate": 4.7658524420081453e-07,
      "loss": 0.4104,
      "step": 58693
    },
    {
      "epoch": 1.803028906705987,
      "grad_norm": 0.4621129631996155,
      "learning_rate": 4.7643783932471156e-07,
      "loss": 0.4896,
      "step": 58694
    },
    {
      "epoch": 1.8030596258409362,
      "grad_norm": 0.42543715238571167,
      "learning_rate": 4.762904566915538e-07,
      "loss": 0.4853,
      "step": 58695
    },
    {
      "epoch": 1.8030903449758855,
      "grad_norm": 0.5535361766815186,
      "learning_rate": 4.761430963016844e-07,
      "loss": 0.4187,
      "step": 58696
    },
    {
      "epoch": 1.8031210641108346,
      "grad_norm": 0.43856316804885864,
      "learning_rate": 4.7599575815544864e-07,
      "loss": 0.4892,
      "step": 58697
    },
    {
      "epoch": 1.803151783245784,
      "grad_norm": 0.49548882246017456,
      "learning_rate": 4.758484422531895e-07,
      "loss": 0.4146,
      "step": 58698
    },
    {
      "epoch": 1.803182502380733,
      "grad_norm": 0.4804001450538635,
      "learning_rate": 4.7570114859525117e-07,
      "loss": 0.4234,
      "step": 58699
    },
    {
      "epoch": 1.8032132215156822,
      "grad_norm": 0.43762022256851196,
      "learning_rate": 4.7555387718197786e-07,
      "loss": 0.4818,
      "step": 58700
    },
    {
      "epoch": 1.8032439406506313,
      "grad_norm": 0.5043045878410339,
      "learning_rate": 4.7540662801371594e-07,
      "loss": 0.4234,
      "step": 58701
    },
    {
      "epoch": 1.8032746597855804,
      "grad_norm": 0.4491223394870758,
      "learning_rate": 4.7525940109080403e-07,
      "loss": 0.4147,
      "step": 58702
    },
    {
      "epoch": 1.8033053789205296,
      "grad_norm": 0.38342952728271484,
      "learning_rate": 4.751121964135896e-07,
      "loss": 0.4321,
      "step": 58703
    },
    {
      "epoch": 1.8033360980554787,
      "grad_norm": 0.4174923896789551,
      "learning_rate": 4.749650139824169e-07,
      "loss": 0.5547,
      "step": 58704
    },
    {
      "epoch": 1.8033668171904278,
      "grad_norm": 0.41026344895362854,
      "learning_rate": 4.748178537976278e-07,
      "loss": 0.4256,
      "step": 58705
    },
    {
      "epoch": 1.803397536325377,
      "grad_norm": 0.4265926480293274,
      "learning_rate": 4.746707158595676e-07,
      "loss": 0.4424,
      "step": 58706
    },
    {
      "epoch": 1.8034282554603263,
      "grad_norm": 0.42131251096725464,
      "learning_rate": 4.745236001685782e-07,
      "loss": 0.4518,
      "step": 58707
    },
    {
      "epoch": 1.8034589745952754,
      "grad_norm": 0.47855478525161743,
      "learning_rate": 4.74376506725005e-07,
      "loss": 0.4513,
      "step": 58708
    },
    {
      "epoch": 1.8034896937302247,
      "grad_norm": 0.42433637380599976,
      "learning_rate": 4.7422943552918986e-07,
      "loss": 0.4243,
      "step": 58709
    },
    {
      "epoch": 1.8035204128651738,
      "grad_norm": 0.40141063928604126,
      "learning_rate": 4.740823865814792e-07,
      "loss": 0.4655,
      "step": 58710
    },
    {
      "epoch": 1.803551132000123,
      "grad_norm": 0.42259150743484497,
      "learning_rate": 4.7393535988221273e-07,
      "loss": 0.4458,
      "step": 58711
    },
    {
      "epoch": 1.803581851135072,
      "grad_norm": 0.43991050124168396,
      "learning_rate": 4.7378835543173685e-07,
      "loss": 0.4475,
      "step": 58712
    },
    {
      "epoch": 1.8036125702700212,
      "grad_norm": 0.42611628770828247,
      "learning_rate": 4.7364137323039016e-07,
      "loss": 0.4866,
      "step": 58713
    },
    {
      "epoch": 1.8036432894049703,
      "grad_norm": 0.4159635901451111,
      "learning_rate": 4.7349441327852244e-07,
      "loss": 0.4027,
      "step": 58714
    },
    {
      "epoch": 1.8036740085399194,
      "grad_norm": 0.47594764828681946,
      "learning_rate": 4.733474755764733e-07,
      "loss": 0.4454,
      "step": 58715
    },
    {
      "epoch": 1.8037047276748686,
      "grad_norm": 0.41973409056663513,
      "learning_rate": 4.7320056012458705e-07,
      "loss": 0.5019,
      "step": 58716
    },
    {
      "epoch": 1.8037354468098177,
      "grad_norm": 0.412456214427948,
      "learning_rate": 4.7305366692320554e-07,
      "loss": 0.4952,
      "step": 58717
    },
    {
      "epoch": 1.803766165944767,
      "grad_norm": 0.48986297845840454,
      "learning_rate": 4.7290679597267185e-07,
      "loss": 0.4181,
      "step": 58718
    },
    {
      "epoch": 1.8037968850797161,
      "grad_norm": 0.40316012501716614,
      "learning_rate": 4.727599472733291e-07,
      "loss": 0.4062,
      "step": 58719
    },
    {
      "epoch": 1.8038276042146655,
      "grad_norm": 0.6080573201179504,
      "learning_rate": 4.726131208255225e-07,
      "loss": 0.428,
      "step": 58720
    },
    {
      "epoch": 1.8038583233496146,
      "grad_norm": 0.4298209547996521,
      "learning_rate": 4.7246631662959395e-07,
      "loss": 0.4593,
      "step": 58721
    },
    {
      "epoch": 1.8038890424845637,
      "grad_norm": 0.4248073399066925,
      "learning_rate": 4.723195346858822e-07,
      "loss": 0.4739,
      "step": 58722
    },
    {
      "epoch": 1.8039197616195128,
      "grad_norm": 0.41828277707099915,
      "learning_rate": 4.721727749947369e-07,
      "loss": 0.3979,
      "step": 58723
    },
    {
      "epoch": 1.803950480754462,
      "grad_norm": 0.45770978927612305,
      "learning_rate": 4.7202603755649667e-07,
      "loss": 0.4137,
      "step": 58724
    },
    {
      "epoch": 1.803981199889411,
      "grad_norm": 0.39556482434272766,
      "learning_rate": 4.718793223715057e-07,
      "loss": 0.4799,
      "step": 58725
    },
    {
      "epoch": 1.8040119190243602,
      "grad_norm": 0.4097058176994324,
      "learning_rate": 4.717326294401059e-07,
      "loss": 0.4895,
      "step": 58726
    },
    {
      "epoch": 1.8040426381593093,
      "grad_norm": 0.42357057332992554,
      "learning_rate": 4.7158595876263814e-07,
      "loss": 0.3976,
      "step": 58727
    },
    {
      "epoch": 1.8040733572942584,
      "grad_norm": 0.4845464825630188,
      "learning_rate": 4.714393103394488e-07,
      "loss": 0.5607,
      "step": 58728
    },
    {
      "epoch": 1.8041040764292078,
      "grad_norm": 0.41200536489486694,
      "learning_rate": 4.712926841708787e-07,
      "loss": 0.4228,
      "step": 58729
    },
    {
      "epoch": 1.804134795564157,
      "grad_norm": 0.4046775698661804,
      "learning_rate": 4.711460802572676e-07,
      "loss": 0.417,
      "step": 58730
    },
    {
      "epoch": 1.804165514699106,
      "grad_norm": 0.45982271432876587,
      "learning_rate": 4.709994985989619e-07,
      "loss": 0.5,
      "step": 58731
    },
    {
      "epoch": 1.8041962338340554,
      "grad_norm": 0.46119633316993713,
      "learning_rate": 4.7085293919630235e-07,
      "loss": 0.4175,
      "step": 58732
    },
    {
      "epoch": 1.8042269529690045,
      "grad_norm": 0.44715645909309387,
      "learning_rate": 4.7070640204963214e-07,
      "loss": 0.4821,
      "step": 58733
    },
    {
      "epoch": 1.8042576721039536,
      "grad_norm": 0.4537723660469055,
      "learning_rate": 4.705598871592909e-07,
      "loss": 0.4,
      "step": 58734
    },
    {
      "epoch": 1.8042883912389027,
      "grad_norm": 0.44660159945487976,
      "learning_rate": 4.7041339452562287e-07,
      "loss": 0.4928,
      "step": 58735
    },
    {
      "epoch": 1.8043191103738518,
      "grad_norm": 0.44521862268447876,
      "learning_rate": 4.702669241489699e-07,
      "loss": 0.5064,
      "step": 58736
    },
    {
      "epoch": 1.804349829508801,
      "grad_norm": 0.412448525428772,
      "learning_rate": 4.7012047602967623e-07,
      "loss": 0.4915,
      "step": 58737
    },
    {
      "epoch": 1.80438054864375,
      "grad_norm": 0.45494288206100464,
      "learning_rate": 4.699740501680794e-07,
      "loss": 0.4041,
      "step": 58738
    },
    {
      "epoch": 1.8044112677786992,
      "grad_norm": 0.4479571580886841,
      "learning_rate": 4.6982764656452353e-07,
      "loss": 0.4784,
      "step": 58739
    },
    {
      "epoch": 1.8044419869136485,
      "grad_norm": 0.486526221036911,
      "learning_rate": 4.6968126521935167e-07,
      "loss": 0.4696,
      "step": 58740
    },
    {
      "epoch": 1.8044727060485977,
      "grad_norm": 0.43009334802627563,
      "learning_rate": 4.6953490613290466e-07,
      "loss": 0.4891,
      "step": 58741
    },
    {
      "epoch": 1.8045034251835468,
      "grad_norm": 0.40806880593299866,
      "learning_rate": 4.6938856930552557e-07,
      "loss": 0.5213,
      "step": 58742
    },
    {
      "epoch": 1.8045341443184961,
      "grad_norm": 0.44660669565200806,
      "learning_rate": 4.6924225473755305e-07,
      "loss": 0.5393,
      "step": 58743
    },
    {
      "epoch": 1.8045648634534452,
      "grad_norm": 0.4466281831264496,
      "learning_rate": 4.690959624293323e-07,
      "loss": 0.4437,
      "step": 58744
    },
    {
      "epoch": 1.8045955825883944,
      "grad_norm": 0.4813191294670105,
      "learning_rate": 4.68949692381202e-07,
      "loss": 0.4458,
      "step": 58745
    },
    {
      "epoch": 1.8046263017233435,
      "grad_norm": 0.42584431171417236,
      "learning_rate": 4.688034445935075e-07,
      "loss": 0.4949,
      "step": 58746
    },
    {
      "epoch": 1.8046570208582926,
      "grad_norm": 0.5118499994277954,
      "learning_rate": 4.6865721906658726e-07,
      "loss": 0.3904,
      "step": 58747
    },
    {
      "epoch": 1.8046877399932417,
      "grad_norm": 0.4097391366958618,
      "learning_rate": 4.685110158007844e-07,
      "loss": 0.4776,
      "step": 58748
    },
    {
      "epoch": 1.8047184591281908,
      "grad_norm": 0.4289073348045349,
      "learning_rate": 4.6836483479643756e-07,
      "loss": 0.4865,
      "step": 58749
    },
    {
      "epoch": 1.80474917826314,
      "grad_norm": 0.4138074219226837,
      "learning_rate": 4.6821867605389317e-07,
      "loss": 0.5212,
      "step": 58750
    },
    {
      "epoch": 1.8047798973980893,
      "grad_norm": 0.4379585087299347,
      "learning_rate": 4.680725395734875e-07,
      "loss": 0.508,
      "step": 58751
    },
    {
      "epoch": 1.8048106165330384,
      "grad_norm": 0.44807103276252747,
      "learning_rate": 4.67926425355566e-07,
      "loss": 0.5232,
      "step": 58752
    },
    {
      "epoch": 1.8048413356679875,
      "grad_norm": 0.4384491741657257,
      "learning_rate": 4.6778033340046713e-07,
      "loss": 0.5344,
      "step": 58753
    },
    {
      "epoch": 1.8048720548029369,
      "grad_norm": 0.44927361607551575,
      "learning_rate": 4.676342637085329e-07,
      "loss": 0.4314,
      "step": 58754
    },
    {
      "epoch": 1.804902773937886,
      "grad_norm": 0.41493165493011475,
      "learning_rate": 4.674882162801042e-07,
      "loss": 0.4585,
      "step": 58755
    },
    {
      "epoch": 1.8049334930728351,
      "grad_norm": 0.47248637676239014,
      "learning_rate": 4.67342191115524e-07,
      "loss": 0.5501,
      "step": 58756
    },
    {
      "epoch": 1.8049642122077842,
      "grad_norm": 0.4505375325679779,
      "learning_rate": 4.671961882151299e-07,
      "loss": 0.5233,
      "step": 58757
    },
    {
      "epoch": 1.8049949313427334,
      "grad_norm": 0.43813860416412354,
      "learning_rate": 4.67050207579266e-07,
      "loss": 0.4855,
      "step": 58758
    },
    {
      "epoch": 1.8050256504776825,
      "grad_norm": 0.4346601665019989,
      "learning_rate": 4.6690424920827094e-07,
      "loss": 0.4748,
      "step": 58759
    },
    {
      "epoch": 1.8050563696126316,
      "grad_norm": 0.40217044949531555,
      "learning_rate": 4.6675831310248776e-07,
      "loss": 0.4657,
      "step": 58760
    },
    {
      "epoch": 1.8050870887475807,
      "grad_norm": 0.42672714591026306,
      "learning_rate": 4.666123992622573e-07,
      "loss": 0.486,
      "step": 58761
    },
    {
      "epoch": 1.80511780788253,
      "grad_norm": 0.48765572905540466,
      "learning_rate": 4.6646650768791823e-07,
      "loss": 0.479,
      "step": 58762
    },
    {
      "epoch": 1.8051485270174792,
      "grad_norm": 0.7193478941917419,
      "learning_rate": 4.663206383798113e-07,
      "loss": 0.4416,
      "step": 58763
    },
    {
      "epoch": 1.8051792461524283,
      "grad_norm": 0.4251849055290222,
      "learning_rate": 4.661747913382797e-07,
      "loss": 0.5355,
      "step": 58764
    },
    {
      "epoch": 1.8052099652873776,
      "grad_norm": 0.4146173894405365,
      "learning_rate": 4.6602896656366417e-07,
      "loss": 0.4879,
      "step": 58765
    },
    {
      "epoch": 1.8052406844223268,
      "grad_norm": 0.43424534797668457,
      "learning_rate": 4.658831640563011e-07,
      "loss": 0.4734,
      "step": 58766
    },
    {
      "epoch": 1.8052714035572759,
      "grad_norm": 0.4467586874961853,
      "learning_rate": 4.6573738381653465e-07,
      "loss": 0.48,
      "step": 58767
    },
    {
      "epoch": 1.805302122692225,
      "grad_norm": 0.45350319147109985,
      "learning_rate": 4.655916258447046e-07,
      "loss": 0.4903,
      "step": 58768
    },
    {
      "epoch": 1.8053328418271741,
      "grad_norm": 0.4486466646194458,
      "learning_rate": 4.6544589014115295e-07,
      "loss": 0.5327,
      "step": 58769
    },
    {
      "epoch": 1.8053635609621232,
      "grad_norm": 0.44883882999420166,
      "learning_rate": 4.6530017670621596e-07,
      "loss": 0.449,
      "step": 58770
    },
    {
      "epoch": 1.8053942800970724,
      "grad_norm": 0.47942277789115906,
      "learning_rate": 4.651544855402368e-07,
      "loss": 0.427,
      "step": 58771
    },
    {
      "epoch": 1.8054249992320215,
      "grad_norm": 0.40897616744041443,
      "learning_rate": 4.6500881664355515e-07,
      "loss": 0.4688,
      "step": 58772
    },
    {
      "epoch": 1.8054557183669708,
      "grad_norm": 0.40707650780677795,
      "learning_rate": 4.648631700165118e-07,
      "loss": 0.4459,
      "step": 58773
    },
    {
      "epoch": 1.80548643750192,
      "grad_norm": 0.43984535336494446,
      "learning_rate": 4.647175456594466e-07,
      "loss": 0.4559,
      "step": 58774
    },
    {
      "epoch": 1.805517156636869,
      "grad_norm": 0.4552329182624817,
      "learning_rate": 4.645719435726992e-07,
      "loss": 0.4483,
      "step": 58775
    },
    {
      "epoch": 1.8055478757718184,
      "grad_norm": 0.43174079060554504,
      "learning_rate": 4.6442636375660935e-07,
      "loss": 0.4217,
      "step": 58776
    },
    {
      "epoch": 1.8055785949067675,
      "grad_norm": 0.47668159008026123,
      "learning_rate": 4.642808062115178e-07,
      "loss": 0.4871,
      "step": 58777
    },
    {
      "epoch": 1.8056093140417167,
      "grad_norm": 0.4669714868068695,
      "learning_rate": 4.6413527093776555e-07,
      "loss": 0.4481,
      "step": 58778
    },
    {
      "epoch": 1.8056400331766658,
      "grad_norm": 0.4711703360080719,
      "learning_rate": 4.6398975793569e-07,
      "loss": 0.51,
      "step": 58779
    },
    {
      "epoch": 1.805670752311615,
      "grad_norm": 0.424291729927063,
      "learning_rate": 4.6384426720563426e-07,
      "loss": 0.4558,
      "step": 58780
    },
    {
      "epoch": 1.805701471446564,
      "grad_norm": 0.4253362715244293,
      "learning_rate": 4.6369879874793357e-07,
      "loss": 0.4406,
      "step": 58781
    },
    {
      "epoch": 1.8057321905815131,
      "grad_norm": 0.7475529909133911,
      "learning_rate": 4.635533525629332e-07,
      "loss": 0.4298,
      "step": 58782
    },
    {
      "epoch": 1.8057629097164623,
      "grad_norm": 0.5226133465766907,
      "learning_rate": 4.634079286509674e-07,
      "loss": 0.4675,
      "step": 58783
    },
    {
      "epoch": 1.8057936288514116,
      "grad_norm": 0.4363570809364319,
      "learning_rate": 4.632625270123814e-07,
      "loss": 0.4716,
      "step": 58784
    },
    {
      "epoch": 1.8058243479863607,
      "grad_norm": 0.41004082560539246,
      "learning_rate": 4.6311714764750826e-07,
      "loss": 0.4507,
      "step": 58785
    },
    {
      "epoch": 1.8058550671213098,
      "grad_norm": 0.39207544922828674,
      "learning_rate": 4.629717905566933e-07,
      "loss": 0.4444,
      "step": 58786
    },
    {
      "epoch": 1.8058857862562592,
      "grad_norm": 0.47491711378097534,
      "learning_rate": 4.6282645574027284e-07,
      "loss": 0.4386,
      "step": 58787
    },
    {
      "epoch": 1.8059165053912083,
      "grad_norm": 0.432585746049881,
      "learning_rate": 4.626811431985889e-07,
      "loss": 0.4458,
      "step": 58788
    },
    {
      "epoch": 1.8059472245261574,
      "grad_norm": 0.45222434401512146,
      "learning_rate": 4.625358529319779e-07,
      "loss": 0.3987,
      "step": 58789
    },
    {
      "epoch": 1.8059779436611065,
      "grad_norm": 0.4066900908946991,
      "learning_rate": 4.623905849407806e-07,
      "loss": 0.4145,
      "step": 58790
    },
    {
      "epoch": 1.8060086627960557,
      "grad_norm": 0.4366348683834076,
      "learning_rate": 4.622453392253357e-07,
      "loss": 0.4897,
      "step": 58791
    },
    {
      "epoch": 1.8060393819310048,
      "grad_norm": 0.4550350606441498,
      "learning_rate": 4.6210011578598393e-07,
      "loss": 0.4692,
      "step": 58792
    },
    {
      "epoch": 1.806070101065954,
      "grad_norm": 0.4296674132347107,
      "learning_rate": 4.6195491462306284e-07,
      "loss": 0.4713,
      "step": 58793
    },
    {
      "epoch": 1.806100820200903,
      "grad_norm": 0.4384790062904358,
      "learning_rate": 4.6180973573691223e-07,
      "loss": 0.5098,
      "step": 58794
    },
    {
      "epoch": 1.8061315393358524,
      "grad_norm": 0.4232312738895416,
      "learning_rate": 4.6166457912787064e-07,
      "loss": 0.465,
      "step": 58795
    },
    {
      "epoch": 1.8061622584708015,
      "grad_norm": 0.4288436472415924,
      "learning_rate": 4.6151944479627785e-07,
      "loss": 0.435,
      "step": 58796
    },
    {
      "epoch": 1.8061929776057506,
      "grad_norm": 0.45515871047973633,
      "learning_rate": 4.6137433274247356e-07,
      "loss": 0.4833,
      "step": 58797
    },
    {
      "epoch": 1.8062236967407,
      "grad_norm": 0.42827579379081726,
      "learning_rate": 4.6122924296679526e-07,
      "loss": 0.436,
      "step": 58798
    },
    {
      "epoch": 1.806254415875649,
      "grad_norm": 0.4643724858760834,
      "learning_rate": 4.610841754695816e-07,
      "loss": 0.4585,
      "step": 58799
    },
    {
      "epoch": 1.8062851350105982,
      "grad_norm": 0.4665186405181885,
      "learning_rate": 4.6093913025117123e-07,
      "loss": 0.4282,
      "step": 58800
    },
    {
      "epoch": 1.8063158541455473,
      "grad_norm": 0.4450135827064514,
      "learning_rate": 4.6079410731190597e-07,
      "loss": 0.5176,
      "step": 58801
    },
    {
      "epoch": 1.8063465732804964,
      "grad_norm": 0.5091596245765686,
      "learning_rate": 4.6064910665212127e-07,
      "loss": 0.4414,
      "step": 58802
    },
    {
      "epoch": 1.8063772924154455,
      "grad_norm": 0.42372244596481323,
      "learning_rate": 4.6050412827215673e-07,
      "loss": 0.4899,
      "step": 58803
    },
    {
      "epoch": 1.8064080115503947,
      "grad_norm": 0.4501088857650757,
      "learning_rate": 4.603591721723499e-07,
      "loss": 0.5206,
      "step": 58804
    },
    {
      "epoch": 1.8064387306853438,
      "grad_norm": 0.5073552131652832,
      "learning_rate": 4.602142383530428e-07,
      "loss": 0.4377,
      "step": 58805
    },
    {
      "epoch": 1.806469449820293,
      "grad_norm": 0.4248582720756531,
      "learning_rate": 4.6006932681457063e-07,
      "loss": 0.4859,
      "step": 58806
    },
    {
      "epoch": 1.8065001689552422,
      "grad_norm": 0.42511120438575745,
      "learning_rate": 4.59924437557272e-07,
      "loss": 0.523,
      "step": 58807
    },
    {
      "epoch": 1.8065308880901914,
      "grad_norm": 0.49737200140953064,
      "learning_rate": 4.597795705814867e-07,
      "loss": 0.4892,
      "step": 58808
    },
    {
      "epoch": 1.8065616072251407,
      "grad_norm": 0.45309239625930786,
      "learning_rate": 4.596347258875533e-07,
      "loss": 0.4587,
      "step": 58809
    },
    {
      "epoch": 1.8065923263600898,
      "grad_norm": 0.43640896677970886,
      "learning_rate": 4.594899034758082e-07,
      "loss": 0.4543,
      "step": 58810
    },
    {
      "epoch": 1.806623045495039,
      "grad_norm": 0.4416568875312805,
      "learning_rate": 4.593451033465901e-07,
      "loss": 0.5175,
      "step": 58811
    },
    {
      "epoch": 1.806653764629988,
      "grad_norm": 0.4857530891895294,
      "learning_rate": 4.5920032550023865e-07,
      "loss": 0.5517,
      "step": 58812
    },
    {
      "epoch": 1.8066844837649372,
      "grad_norm": 0.45321589708328247,
      "learning_rate": 4.5905556993709135e-07,
      "loss": 0.4986,
      "step": 58813
    },
    {
      "epoch": 1.8067152028998863,
      "grad_norm": 0.3981865346431732,
      "learning_rate": 4.589108366574868e-07,
      "loss": 0.4714,
      "step": 58814
    },
    {
      "epoch": 1.8067459220348354,
      "grad_norm": 0.4717424809932709,
      "learning_rate": 4.5876612566176037e-07,
      "loss": 0.4789,
      "step": 58815
    },
    {
      "epoch": 1.8067766411697845,
      "grad_norm": 0.4560176432132721,
      "learning_rate": 4.5862143695025506e-07,
      "loss": 0.4851,
      "step": 58816
    },
    {
      "epoch": 1.8068073603047337,
      "grad_norm": 0.4337441027164459,
      "learning_rate": 4.5847677052330177e-07,
      "loss": 0.5209,
      "step": 58817
    },
    {
      "epoch": 1.806838079439683,
      "grad_norm": 0.5142297744750977,
      "learning_rate": 4.583321263812457e-07,
      "loss": 0.4643,
      "step": 58818
    },
    {
      "epoch": 1.8068687985746321,
      "grad_norm": 0.4371880888938904,
      "learning_rate": 4.5818750452441885e-07,
      "loss": 0.499,
      "step": 58819
    },
    {
      "epoch": 1.8068995177095815,
      "grad_norm": 0.420087069272995,
      "learning_rate": 4.5804290495316426e-07,
      "loss": 0.4903,
      "step": 58820
    },
    {
      "epoch": 1.8069302368445306,
      "grad_norm": 0.4656617045402527,
      "learning_rate": 4.578983276678151e-07,
      "loss": 0.4015,
      "step": 58821
    },
    {
      "epoch": 1.8069609559794797,
      "grad_norm": 0.42428311705589294,
      "learning_rate": 4.577537726687109e-07,
      "loss": 0.5188,
      "step": 58822
    },
    {
      "epoch": 1.8069916751144288,
      "grad_norm": 0.4422129690647125,
      "learning_rate": 4.576092399561882e-07,
      "loss": 0.4986,
      "step": 58823
    },
    {
      "epoch": 1.807022394249378,
      "grad_norm": 0.42476949095726013,
      "learning_rate": 4.5746472953058787e-07,
      "loss": 0.4849,
      "step": 58824
    },
    {
      "epoch": 1.807053113384327,
      "grad_norm": 0.4332787096500397,
      "learning_rate": 4.5732024139224396e-07,
      "loss": 0.4635,
      "step": 58825
    },
    {
      "epoch": 1.8070838325192762,
      "grad_norm": 0.40144628286361694,
      "learning_rate": 4.571757755414941e-07,
      "loss": 0.4772,
      "step": 58826
    },
    {
      "epoch": 1.8071145516542253,
      "grad_norm": 0.5004319548606873,
      "learning_rate": 4.570313319786779e-07,
      "loss": 0.4568,
      "step": 58827
    },
    {
      "epoch": 1.8071452707891744,
      "grad_norm": 0.5107847452163696,
      "learning_rate": 4.5688691070413184e-07,
      "loss": 0.4079,
      "step": 58828
    },
    {
      "epoch": 1.8071759899241238,
      "grad_norm": 0.42306095361709595,
      "learning_rate": 4.567425117181912e-07,
      "loss": 0.4834,
      "step": 58829
    },
    {
      "epoch": 1.8072067090590729,
      "grad_norm": 0.6896907687187195,
      "learning_rate": 4.5659813502119563e-07,
      "loss": 0.5325,
      "step": 58830
    },
    {
      "epoch": 1.8072374281940222,
      "grad_norm": 0.38273608684539795,
      "learning_rate": 4.5645378061348165e-07,
      "loss": 0.353,
      "step": 58831
    },
    {
      "epoch": 1.8072681473289713,
      "grad_norm": 0.45050710439682007,
      "learning_rate": 4.5630944849538674e-07,
      "loss": 0.5106,
      "step": 58832
    },
    {
      "epoch": 1.8072988664639205,
      "grad_norm": 0.5460300445556641,
      "learning_rate": 4.5616513866724833e-07,
      "loss": 0.4442,
      "step": 58833
    },
    {
      "epoch": 1.8073295855988696,
      "grad_norm": 0.47325319051742554,
      "learning_rate": 4.5602085112940175e-07,
      "loss": 0.5361,
      "step": 58834
    },
    {
      "epoch": 1.8073603047338187,
      "grad_norm": 0.4857389032840729,
      "learning_rate": 4.5587658588218453e-07,
      "loss": 0.4483,
      "step": 58835
    },
    {
      "epoch": 1.8073910238687678,
      "grad_norm": 0.4097417891025543,
      "learning_rate": 4.557323429259353e-07,
      "loss": 0.4808,
      "step": 58836
    },
    {
      "epoch": 1.807421743003717,
      "grad_norm": 0.4379543364048004,
      "learning_rate": 4.5558812226098926e-07,
      "loss": 0.4926,
      "step": 58837
    },
    {
      "epoch": 1.807452462138666,
      "grad_norm": 0.5259776711463928,
      "learning_rate": 4.55443923887684e-07,
      "loss": 0.4071,
      "step": 58838
    },
    {
      "epoch": 1.8074831812736152,
      "grad_norm": 0.3990097939968109,
      "learning_rate": 4.5529974780635587e-07,
      "loss": 0.4506,
      "step": 58839
    },
    {
      "epoch": 1.8075139004085645,
      "grad_norm": 0.44994673132896423,
      "learning_rate": 4.551555940173413e-07,
      "loss": 0.4107,
      "step": 58840
    },
    {
      "epoch": 1.8075446195435136,
      "grad_norm": 0.4585511386394501,
      "learning_rate": 4.5501146252097784e-07,
      "loss": 0.3997,
      "step": 58841
    },
    {
      "epoch": 1.8075753386784628,
      "grad_norm": 0.42868441343307495,
      "learning_rate": 4.548673533176018e-07,
      "loss": 0.4793,
      "step": 58842
    },
    {
      "epoch": 1.807606057813412,
      "grad_norm": 0.41188979148864746,
      "learning_rate": 4.547232664075507e-07,
      "loss": 0.4967,
      "step": 58843
    },
    {
      "epoch": 1.8076367769483612,
      "grad_norm": 0.3967992067337036,
      "learning_rate": 4.545792017911577e-07,
      "loss": 0.4475,
      "step": 58844
    },
    {
      "epoch": 1.8076674960833103,
      "grad_norm": 0.46384963393211365,
      "learning_rate": 4.544351594687635e-07,
      "loss": 0.5152,
      "step": 58845
    },
    {
      "epoch": 1.8076982152182595,
      "grad_norm": 0.45229965448379517,
      "learning_rate": 4.5429113944070127e-07,
      "loss": 0.441,
      "step": 58846
    },
    {
      "epoch": 1.8077289343532086,
      "grad_norm": 0.42541471123695374,
      "learning_rate": 4.5414714170731066e-07,
      "loss": 0.4759,
      "step": 58847
    },
    {
      "epoch": 1.8077596534881577,
      "grad_norm": 0.40244507789611816,
      "learning_rate": 4.540031662689237e-07,
      "loss": 0.4327,
      "step": 58848
    },
    {
      "epoch": 1.8077903726231068,
      "grad_norm": 0.40450558066368103,
      "learning_rate": 4.53859213125879e-07,
      "loss": 0.4232,
      "step": 58849
    },
    {
      "epoch": 1.807821091758056,
      "grad_norm": 0.45900028944015503,
      "learning_rate": 4.5371528227851513e-07,
      "loss": 0.4591,
      "step": 58850
    },
    {
      "epoch": 1.8078518108930053,
      "grad_norm": 0.44483625888824463,
      "learning_rate": 4.535713737271652e-07,
      "loss": 0.4902,
      "step": 58851
    },
    {
      "epoch": 1.8078825300279544,
      "grad_norm": 0.494692862033844,
      "learning_rate": 4.534274874721667e-07,
      "loss": 0.456,
      "step": 58852
    },
    {
      "epoch": 1.8079132491629035,
      "grad_norm": 0.4770963191986084,
      "learning_rate": 4.532836235138516e-07,
      "loss": 0.4933,
      "step": 58853
    },
    {
      "epoch": 1.8079439682978529,
      "grad_norm": 0.4156031310558319,
      "learning_rate": 4.531397818525629e-07,
      "loss": 0.5402,
      "step": 58854
    },
    {
      "epoch": 1.807974687432802,
      "grad_norm": 0.45262661576271057,
      "learning_rate": 4.5299596248863156e-07,
      "loss": 0.4772,
      "step": 58855
    },
    {
      "epoch": 1.808005406567751,
      "grad_norm": 0.4768970310688019,
      "learning_rate": 4.5285216542239606e-07,
      "loss": 0.5016,
      "step": 58856
    },
    {
      "epoch": 1.8080361257027002,
      "grad_norm": 0.40124863386154175,
      "learning_rate": 4.527083906541896e-07,
      "loss": 0.4052,
      "step": 58857
    },
    {
      "epoch": 1.8080668448376493,
      "grad_norm": 0.44620057940483093,
      "learning_rate": 4.525646381843496e-07,
      "loss": 0.4523,
      "step": 58858
    },
    {
      "epoch": 1.8080975639725985,
      "grad_norm": 0.4429931640625,
      "learning_rate": 4.524209080132125e-07,
      "loss": 0.4113,
      "step": 58859
    },
    {
      "epoch": 1.8081282831075476,
      "grad_norm": 0.41783958673477173,
      "learning_rate": 4.5227720014111355e-07,
      "loss": 0.5047,
      "step": 58860
    },
    {
      "epoch": 1.8081590022424967,
      "grad_norm": 0.5228672623634338,
      "learning_rate": 4.5213351456838696e-07,
      "loss": 0.4462,
      "step": 58861
    },
    {
      "epoch": 1.808189721377446,
      "grad_norm": 0.43815165758132935,
      "learning_rate": 4.5198985129536907e-07,
      "loss": 0.4718,
      "step": 58862
    },
    {
      "epoch": 1.8082204405123952,
      "grad_norm": 0.409525603055954,
      "learning_rate": 4.518462103223964e-07,
      "loss": 0.4511,
      "step": 58863
    },
    {
      "epoch": 1.8082511596473443,
      "grad_norm": 0.44390425086021423,
      "learning_rate": 4.517025916498041e-07,
      "loss": 0.5076,
      "step": 58864
    },
    {
      "epoch": 1.8082818787822936,
      "grad_norm": 0.45369410514831543,
      "learning_rate": 4.5155899527792645e-07,
      "loss": 0.5307,
      "step": 58865
    },
    {
      "epoch": 1.8083125979172427,
      "grad_norm": 0.7162458300590515,
      "learning_rate": 4.514154212070998e-07,
      "loss": 0.5212,
      "step": 58866
    },
    {
      "epoch": 1.8083433170521919,
      "grad_norm": 0.44836270809173584,
      "learning_rate": 4.5127186943765943e-07,
      "loss": 0.3997,
      "step": 58867
    },
    {
      "epoch": 1.808374036187141,
      "grad_norm": 0.4287155568599701,
      "learning_rate": 4.5112833996993955e-07,
      "loss": 0.5042,
      "step": 58868
    },
    {
      "epoch": 1.80840475532209,
      "grad_norm": 0.4596392810344696,
      "learning_rate": 4.5098483280427873e-07,
      "loss": 0.5311,
      "step": 58869
    },
    {
      "epoch": 1.8084354744570392,
      "grad_norm": 0.448537677526474,
      "learning_rate": 4.5084134794100786e-07,
      "loss": 0.474,
      "step": 58870
    },
    {
      "epoch": 1.8084661935919883,
      "grad_norm": 0.4281543493270874,
      "learning_rate": 4.506978853804633e-07,
      "loss": 0.4626,
      "step": 58871
    },
    {
      "epoch": 1.8084969127269375,
      "grad_norm": 0.4475351870059967,
      "learning_rate": 4.505544451229815e-07,
      "loss": 0.4907,
      "step": 58872
    },
    {
      "epoch": 1.8085276318618868,
      "grad_norm": 0.4377322494983673,
      "learning_rate": 4.5041102716889883e-07,
      "loss": 0.5491,
      "step": 58873
    },
    {
      "epoch": 1.808558350996836,
      "grad_norm": 0.4689505696296692,
      "learning_rate": 4.502676315185461e-07,
      "loss": 0.4793,
      "step": 58874
    },
    {
      "epoch": 1.808589070131785,
      "grad_norm": 0.4459775984287262,
      "learning_rate": 4.501242581722598e-07,
      "loss": 0.4175,
      "step": 58875
    },
    {
      "epoch": 1.8086197892667344,
      "grad_norm": 0.5212652683258057,
      "learning_rate": 4.499809071303751e-07,
      "loss": 0.4776,
      "step": 58876
    },
    {
      "epoch": 1.8086505084016835,
      "grad_norm": 0.41888079047203064,
      "learning_rate": 4.498375783932285e-07,
      "loss": 0.4685,
      "step": 58877
    },
    {
      "epoch": 1.8086812275366326,
      "grad_norm": 0.4128141403198242,
      "learning_rate": 4.49694271961153e-07,
      "loss": 0.4776,
      "step": 58878
    },
    {
      "epoch": 1.8087119466715817,
      "grad_norm": 0.46005523204803467,
      "learning_rate": 4.495509878344839e-07,
      "loss": 0.4698,
      "step": 58879
    },
    {
      "epoch": 1.8087426658065309,
      "grad_norm": 0.46501925587654114,
      "learning_rate": 4.494077260135532e-07,
      "loss": 0.4889,
      "step": 58880
    },
    {
      "epoch": 1.80877338494148,
      "grad_norm": 0.4323650896549225,
      "learning_rate": 4.492644864986995e-07,
      "loss": 0.4809,
      "step": 58881
    },
    {
      "epoch": 1.808804104076429,
      "grad_norm": 0.42908352613449097,
      "learning_rate": 4.4912126929025467e-07,
      "loss": 0.525,
      "step": 58882
    },
    {
      "epoch": 1.8088348232113782,
      "grad_norm": 0.47103771567344666,
      "learning_rate": 4.4897807438855634e-07,
      "loss": 0.5258,
      "step": 58883
    },
    {
      "epoch": 1.8088655423463276,
      "grad_norm": 0.44636255502700806,
      "learning_rate": 4.4883490179393417e-07,
      "loss": 0.4844,
      "step": 58884
    },
    {
      "epoch": 1.8088962614812767,
      "grad_norm": 0.39404770731925964,
      "learning_rate": 4.486917515067246e-07,
      "loss": 0.416,
      "step": 58885
    },
    {
      "epoch": 1.8089269806162258,
      "grad_norm": 0.45351773500442505,
      "learning_rate": 4.4854862352726516e-07,
      "loss": 0.4086,
      "step": 58886
    },
    {
      "epoch": 1.8089576997511752,
      "grad_norm": 0.43273788690567017,
      "learning_rate": 4.4840551785588547e-07,
      "loss": 0.4413,
      "step": 58887
    },
    {
      "epoch": 1.8089884188861243,
      "grad_norm": 0.4666679799556732,
      "learning_rate": 4.4826243449292427e-07,
      "loss": 0.4397,
      "step": 58888
    },
    {
      "epoch": 1.8090191380210734,
      "grad_norm": 0.5229874849319458,
      "learning_rate": 4.4811937343870904e-07,
      "loss": 0.4792,
      "step": 58889
    },
    {
      "epoch": 1.8090498571560225,
      "grad_norm": 0.4446876645088196,
      "learning_rate": 4.479763346935817e-07,
      "loss": 0.487,
      "step": 58890
    },
    {
      "epoch": 1.8090805762909716,
      "grad_norm": 0.4026130139827728,
      "learning_rate": 4.47833318257872e-07,
      "loss": 0.5183,
      "step": 58891
    },
    {
      "epoch": 1.8091112954259208,
      "grad_norm": 0.4323863089084625,
      "learning_rate": 4.476903241319153e-07,
      "loss": 0.5461,
      "step": 58892
    },
    {
      "epoch": 1.8091420145608699,
      "grad_norm": 0.44542545080184937,
      "learning_rate": 4.475473523160434e-07,
      "loss": 0.4825,
      "step": 58893
    },
    {
      "epoch": 1.809172733695819,
      "grad_norm": 0.4295448660850525,
      "learning_rate": 4.474044028105917e-07,
      "loss": 0.4492,
      "step": 58894
    },
    {
      "epoch": 1.8092034528307683,
      "grad_norm": 0.4257538318634033,
      "learning_rate": 4.472614756158955e-07,
      "loss": 0.4446,
      "step": 58895
    },
    {
      "epoch": 1.8092341719657175,
      "grad_norm": 0.43022096157073975,
      "learning_rate": 4.471185707322867e-07,
      "loss": 0.431,
      "step": 58896
    },
    {
      "epoch": 1.8092648911006666,
      "grad_norm": 0.4572923481464386,
      "learning_rate": 4.469756881600995e-07,
      "loss": 0.4334,
      "step": 58897
    },
    {
      "epoch": 1.809295610235616,
      "grad_norm": 0.4131406843662262,
      "learning_rate": 4.468328278996681e-07,
      "loss": 0.4462,
      "step": 58898
    },
    {
      "epoch": 1.809326329370565,
      "grad_norm": 0.4165419936180115,
      "learning_rate": 4.466899899513255e-07,
      "loss": 0.4647,
      "step": 58899
    },
    {
      "epoch": 1.8093570485055142,
      "grad_norm": 0.4757220149040222,
      "learning_rate": 4.4654717431540596e-07,
      "loss": 0.4448,
      "step": 58900
    },
    {
      "epoch": 1.8093877676404633,
      "grad_norm": 0.44965794682502747,
      "learning_rate": 4.464043809922425e-07,
      "loss": 0.4725,
      "step": 58901
    },
    {
      "epoch": 1.8094184867754124,
      "grad_norm": 0.4435408413410187,
      "learning_rate": 4.4626160998216815e-07,
      "loss": 0.3924,
      "step": 58902
    },
    {
      "epoch": 1.8094492059103615,
      "grad_norm": 0.4303956925868988,
      "learning_rate": 4.461188612855172e-07,
      "loss": 0.5065,
      "step": 58903
    },
    {
      "epoch": 1.8094799250453106,
      "grad_norm": 0.49617308378219604,
      "learning_rate": 4.459761349026237e-07,
      "loss": 0.4643,
      "step": 58904
    },
    {
      "epoch": 1.8095106441802598,
      "grad_norm": 0.4642535150051117,
      "learning_rate": 4.458334308338208e-07,
      "loss": 0.4569,
      "step": 58905
    },
    {
      "epoch": 1.809541363315209,
      "grad_norm": 0.414368599653244,
      "learning_rate": 4.4569074907943934e-07,
      "loss": 0.4818,
      "step": 58906
    },
    {
      "epoch": 1.8095720824501582,
      "grad_norm": 0.47585150599479675,
      "learning_rate": 4.4554808963981456e-07,
      "loss": 0.4651,
      "step": 58907
    },
    {
      "epoch": 1.8096028015851073,
      "grad_norm": 0.4357936680316925,
      "learning_rate": 4.4540545251528067e-07,
      "loss": 0.4631,
      "step": 58908
    },
    {
      "epoch": 1.8096335207200567,
      "grad_norm": 0.45930519700050354,
      "learning_rate": 4.4526283770616965e-07,
      "loss": 0.5069,
      "step": 58909
    },
    {
      "epoch": 1.8096642398550058,
      "grad_norm": 0.44872385263442993,
      "learning_rate": 4.4512024521281337e-07,
      "loss": 0.4803,
      "step": 58910
    },
    {
      "epoch": 1.809694958989955,
      "grad_norm": 0.39565902948379517,
      "learning_rate": 4.449776750355472e-07,
      "loss": 0.5017,
      "step": 58911
    },
    {
      "epoch": 1.809725678124904,
      "grad_norm": 0.47329553961753845,
      "learning_rate": 4.44835127174702e-07,
      "loss": 0.4231,
      "step": 58912
    },
    {
      "epoch": 1.8097563972598532,
      "grad_norm": 0.450920045375824,
      "learning_rate": 4.44692601630613e-07,
      "loss": 0.5031,
      "step": 58913
    },
    {
      "epoch": 1.8097871163948023,
      "grad_norm": 0.4645518958568573,
      "learning_rate": 4.4455009840361107e-07,
      "loss": 0.3986,
      "step": 58914
    },
    {
      "epoch": 1.8098178355297514,
      "grad_norm": 0.4024527370929718,
      "learning_rate": 4.444076174940304e-07,
      "loss": 0.3603,
      "step": 58915
    },
    {
      "epoch": 1.8098485546647005,
      "grad_norm": 0.44908076524734497,
      "learning_rate": 4.442651589022007e-07,
      "loss": 0.4493,
      "step": 58916
    },
    {
      "epoch": 1.8098792737996499,
      "grad_norm": 0.46536484360694885,
      "learning_rate": 4.4412272262845944e-07,
      "loss": 0.4267,
      "step": 58917
    },
    {
      "epoch": 1.809909992934599,
      "grad_norm": 0.44393086433410645,
      "learning_rate": 4.4398030867313644e-07,
      "loss": 0.4771,
      "step": 58918
    },
    {
      "epoch": 1.809940712069548,
      "grad_norm": 0.4730532169342041,
      "learning_rate": 4.438379170365659e-07,
      "loss": 0.419,
      "step": 58919
    },
    {
      "epoch": 1.8099714312044974,
      "grad_norm": 0.4466746151447296,
      "learning_rate": 4.436955477190774e-07,
      "loss": 0.4326,
      "step": 58920
    },
    {
      "epoch": 1.8100021503394466,
      "grad_norm": 0.42941901087760925,
      "learning_rate": 4.4355320072100417e-07,
      "loss": 0.4305,
      "step": 58921
    },
    {
      "epoch": 1.8100328694743957,
      "grad_norm": 0.429305762052536,
      "learning_rate": 4.434108760426825e-07,
      "loss": 0.4554,
      "step": 58922
    },
    {
      "epoch": 1.8100635886093448,
      "grad_norm": 0.4163856506347656,
      "learning_rate": 4.432685736844411e-07,
      "loss": 0.5195,
      "step": 58923
    },
    {
      "epoch": 1.810094307744294,
      "grad_norm": 0.42625918984413147,
      "learning_rate": 4.4312629364661407e-07,
      "loss": 0.3845,
      "step": 58924
    },
    {
      "epoch": 1.810125026879243,
      "grad_norm": 0.3992661237716675,
      "learning_rate": 4.429840359295323e-07,
      "loss": 0.4661,
      "step": 58925
    },
    {
      "epoch": 1.8101557460141922,
      "grad_norm": 0.43026286363601685,
      "learning_rate": 4.428418005335289e-07,
      "loss": 0.4808,
      "step": 58926
    },
    {
      "epoch": 1.8101864651491413,
      "grad_norm": 0.3936898112297058,
      "learning_rate": 4.426995874589357e-07,
      "loss": 0.4061,
      "step": 58927
    },
    {
      "epoch": 1.8102171842840904,
      "grad_norm": 0.4643844664096832,
      "learning_rate": 4.4255739670608697e-07,
      "loss": 0.4731,
      "step": 58928
    },
    {
      "epoch": 1.8102479034190397,
      "grad_norm": 0.47652286291122437,
      "learning_rate": 4.4241522827531023e-07,
      "loss": 0.4915,
      "step": 58929
    },
    {
      "epoch": 1.8102786225539889,
      "grad_norm": 0.47712141275405884,
      "learning_rate": 4.422730821669419e-07,
      "loss": 0.5381,
      "step": 58930
    },
    {
      "epoch": 1.8103093416889382,
      "grad_norm": 0.42768168449401855,
      "learning_rate": 4.421309583813105e-07,
      "loss": 0.4981,
      "step": 58931
    },
    {
      "epoch": 1.8103400608238873,
      "grad_norm": 0.43940189480781555,
      "learning_rate": 4.419888569187525e-07,
      "loss": 0.5098,
      "step": 58932
    },
    {
      "epoch": 1.8103707799588364,
      "grad_norm": 0.4257087707519531,
      "learning_rate": 4.4184677777959537e-07,
      "loss": 0.5188,
      "step": 58933
    },
    {
      "epoch": 1.8104014990937856,
      "grad_norm": 0.4336227476596832,
      "learning_rate": 4.4170472096417227e-07,
      "loss": 0.4032,
      "step": 58934
    },
    {
      "epoch": 1.8104322182287347,
      "grad_norm": 0.4409533739089966,
      "learning_rate": 4.4156268647281617e-07,
      "loss": 0.4181,
      "step": 58935
    },
    {
      "epoch": 1.8104629373636838,
      "grad_norm": 0.44829270243644714,
      "learning_rate": 4.41420674305858e-07,
      "loss": 0.413,
      "step": 58936
    },
    {
      "epoch": 1.810493656498633,
      "grad_norm": 0.44655051827430725,
      "learning_rate": 4.4127868446362855e-07,
      "loss": 0.4106,
      "step": 58937
    },
    {
      "epoch": 1.810524375633582,
      "grad_norm": 0.419861376285553,
      "learning_rate": 4.411367169464609e-07,
      "loss": 0.5346,
      "step": 58938
    },
    {
      "epoch": 1.8105550947685312,
      "grad_norm": 0.4517230987548828,
      "learning_rate": 4.4099477175468584e-07,
      "loss": 0.4817,
      "step": 58939
    },
    {
      "epoch": 1.8105858139034805,
      "grad_norm": 0.4373057186603546,
      "learning_rate": 4.408528488886343e-07,
      "loss": 0.4937,
      "step": 58940
    },
    {
      "epoch": 1.8106165330384296,
      "grad_norm": 0.4168626070022583,
      "learning_rate": 4.407109483486405e-07,
      "loss": 0.3484,
      "step": 58941
    },
    {
      "epoch": 1.810647252173379,
      "grad_norm": 0.4498341977596283,
      "learning_rate": 4.4056907013503293e-07,
      "loss": 0.529,
      "step": 58942
    },
    {
      "epoch": 1.810677971308328,
      "grad_norm": 0.44822603464126587,
      "learning_rate": 4.4042721424814363e-07,
      "loss": 0.5132,
      "step": 58943
    },
    {
      "epoch": 1.8107086904432772,
      "grad_norm": 0.45103803277015686,
      "learning_rate": 4.4028538068830454e-07,
      "loss": 0.5225,
      "step": 58944
    },
    {
      "epoch": 1.8107394095782263,
      "grad_norm": 0.4848763644695282,
      "learning_rate": 4.4014356945584645e-07,
      "loss": 0.4887,
      "step": 58945
    },
    {
      "epoch": 1.8107701287131754,
      "grad_norm": 0.4460475742816925,
      "learning_rate": 4.400017805511003e-07,
      "loss": 0.4808,
      "step": 58946
    },
    {
      "epoch": 1.8108008478481246,
      "grad_norm": 0.42297667264938354,
      "learning_rate": 4.3986001397439914e-07,
      "loss": 0.4951,
      "step": 58947
    },
    {
      "epoch": 1.8108315669830737,
      "grad_norm": 0.4375302195549011,
      "learning_rate": 4.3971826972607044e-07,
      "loss": 0.4485,
      "step": 58948
    },
    {
      "epoch": 1.8108622861180228,
      "grad_norm": 0.4101923108100891,
      "learning_rate": 4.395765478064495e-07,
      "loss": 0.4543,
      "step": 58949
    },
    {
      "epoch": 1.810893005252972,
      "grad_norm": 0.44007158279418945,
      "learning_rate": 4.3943484821586393e-07,
      "loss": 0.4873,
      "step": 58950
    },
    {
      "epoch": 1.8109237243879213,
      "grad_norm": 0.45211997628211975,
      "learning_rate": 4.3929317095464665e-07,
      "loss": 0.5119,
      "step": 58951
    },
    {
      "epoch": 1.8109544435228704,
      "grad_norm": 0.45384740829467773,
      "learning_rate": 4.3915151602312633e-07,
      "loss": 0.5219,
      "step": 58952
    },
    {
      "epoch": 1.8109851626578195,
      "grad_norm": 0.4427730143070221,
      "learning_rate": 4.390098834216372e-07,
      "loss": 0.4881,
      "step": 58953
    },
    {
      "epoch": 1.8110158817927688,
      "grad_norm": 0.4468979239463806,
      "learning_rate": 4.3886827315050785e-07,
      "loss": 0.5241,
      "step": 58954
    },
    {
      "epoch": 1.811046600927718,
      "grad_norm": 0.4520062208175659,
      "learning_rate": 4.387266852100702e-07,
      "loss": 0.4126,
      "step": 58955
    },
    {
      "epoch": 1.811077320062667,
      "grad_norm": 0.43140989542007446,
      "learning_rate": 4.3858511960065186e-07,
      "loss": 0.4147,
      "step": 58956
    },
    {
      "epoch": 1.8111080391976162,
      "grad_norm": 0.4033117890357971,
      "learning_rate": 4.3844357632258583e-07,
      "loss": 0.4791,
      "step": 58957
    },
    {
      "epoch": 1.8111387583325653,
      "grad_norm": 0.4745733439922333,
      "learning_rate": 4.3830205537620406e-07,
      "loss": 0.4371,
      "step": 58958
    },
    {
      "epoch": 1.8111694774675144,
      "grad_norm": 0.4963551163673401,
      "learning_rate": 4.381605567618352e-07,
      "loss": 0.418,
      "step": 58959
    },
    {
      "epoch": 1.8112001966024636,
      "grad_norm": 0.4081991910934448,
      "learning_rate": 4.3801908047981123e-07,
      "loss": 0.496,
      "step": 58960
    },
    {
      "epoch": 1.8112309157374127,
      "grad_norm": 0.44464853405952454,
      "learning_rate": 4.3787762653045964e-07,
      "loss": 0.5432,
      "step": 58961
    },
    {
      "epoch": 1.811261634872362,
      "grad_norm": 0.4677775502204895,
      "learning_rate": 4.3773619491411347e-07,
      "loss": 0.4205,
      "step": 58962
    },
    {
      "epoch": 1.8112923540073111,
      "grad_norm": 0.475517600774765,
      "learning_rate": 4.375947856311025e-07,
      "loss": 0.4732,
      "step": 58963
    },
    {
      "epoch": 1.8113230731422603,
      "grad_norm": 0.4419393539428711,
      "learning_rate": 4.3745339868175753e-07,
      "loss": 0.4628,
      "step": 58964
    },
    {
      "epoch": 1.8113537922772096,
      "grad_norm": 0.43365105986595154,
      "learning_rate": 4.373120340664061e-07,
      "loss": 0.4031,
      "step": 58965
    },
    {
      "epoch": 1.8113845114121587,
      "grad_norm": 0.41482311487197876,
      "learning_rate": 4.371706917853813e-07,
      "loss": 0.4639,
      "step": 58966
    },
    {
      "epoch": 1.8114152305471078,
      "grad_norm": 0.49329903721809387,
      "learning_rate": 4.3702937183901174e-07,
      "loss": 0.4874,
      "step": 58967
    },
    {
      "epoch": 1.811445949682057,
      "grad_norm": 0.4374484121799469,
      "learning_rate": 4.3688807422762824e-07,
      "loss": 0.5137,
      "step": 58968
    },
    {
      "epoch": 1.811476668817006,
      "grad_norm": 0.4377303123474121,
      "learning_rate": 4.367467989515606e-07,
      "loss": 0.4561,
      "step": 58969
    },
    {
      "epoch": 1.8115073879519552,
      "grad_norm": 0.4409286379814148,
      "learning_rate": 4.3660554601113846e-07,
      "loss": 0.4268,
      "step": 58970
    },
    {
      "epoch": 1.8115381070869043,
      "grad_norm": 0.4449958801269531,
      "learning_rate": 4.3646431540669166e-07,
      "loss": 0.3983,
      "step": 58971
    },
    {
      "epoch": 1.8115688262218534,
      "grad_norm": 0.40940266847610474,
      "learning_rate": 4.3632310713855206e-07,
      "loss": 0.5398,
      "step": 58972
    },
    {
      "epoch": 1.8115995453568028,
      "grad_norm": 0.40399786829948425,
      "learning_rate": 4.3618192120704615e-07,
      "loss": 0.4843,
      "step": 58973
    },
    {
      "epoch": 1.811630264491752,
      "grad_norm": 0.4243699908256531,
      "learning_rate": 4.3604075761250474e-07,
      "loss": 0.4698,
      "step": 58974
    },
    {
      "epoch": 1.811660983626701,
      "grad_norm": 0.4427047669887543,
      "learning_rate": 4.3589961635525866e-07,
      "loss": 0.4493,
      "step": 58975
    },
    {
      "epoch": 1.8116917027616504,
      "grad_norm": 0.430369108915329,
      "learning_rate": 4.357584974356377e-07,
      "loss": 0.4641,
      "step": 58976
    },
    {
      "epoch": 1.8117224218965995,
      "grad_norm": 0.4536314010620117,
      "learning_rate": 4.3561740085397044e-07,
      "loss": 0.4268,
      "step": 58977
    },
    {
      "epoch": 1.8117531410315486,
      "grad_norm": 0.4882553517818451,
      "learning_rate": 4.354763266105866e-07,
      "loss": 0.4642,
      "step": 58978
    },
    {
      "epoch": 1.8117838601664977,
      "grad_norm": 0.42916667461395264,
      "learning_rate": 4.353352747058159e-07,
      "loss": 0.4641,
      "step": 58979
    },
    {
      "epoch": 1.8118145793014468,
      "grad_norm": 0.4389525353908539,
      "learning_rate": 4.351942451399871e-07,
      "loss": 0.4527,
      "step": 58980
    },
    {
      "epoch": 1.811845298436396,
      "grad_norm": 0.4342518448829651,
      "learning_rate": 4.350532379134309e-07,
      "loss": 0.3765,
      "step": 58981
    },
    {
      "epoch": 1.811876017571345,
      "grad_norm": 0.4541155695915222,
      "learning_rate": 4.34912253026476e-07,
      "loss": 0.531,
      "step": 58982
    },
    {
      "epoch": 1.8119067367062942,
      "grad_norm": 0.45415350794792175,
      "learning_rate": 4.347712904794521e-07,
      "loss": 0.5194,
      "step": 58983
    },
    {
      "epoch": 1.8119374558412435,
      "grad_norm": 0.49185237288475037,
      "learning_rate": 4.3463035027268454e-07,
      "loss": 0.4188,
      "step": 58984
    },
    {
      "epoch": 1.8119681749761927,
      "grad_norm": 0.40735122561454773,
      "learning_rate": 4.3448943240650967e-07,
      "loss": 0.4095,
      "step": 58985
    },
    {
      "epoch": 1.8119988941111418,
      "grad_norm": 0.5911941528320312,
      "learning_rate": 4.3434853688125054e-07,
      "loss": 0.4719,
      "step": 58986
    },
    {
      "epoch": 1.8120296132460911,
      "grad_norm": 0.43350842595100403,
      "learning_rate": 4.342076636972403e-07,
      "loss": 0.4045,
      "step": 58987
    },
    {
      "epoch": 1.8120603323810403,
      "grad_norm": 0.4042123854160309,
      "learning_rate": 4.340668128548031e-07,
      "loss": 0.4431,
      "step": 58988
    },
    {
      "epoch": 1.8120910515159894,
      "grad_norm": 0.539923906326294,
      "learning_rate": 4.3392598435427424e-07,
      "loss": 0.5362,
      "step": 58989
    },
    {
      "epoch": 1.8121217706509385,
      "grad_norm": 0.4467231333255768,
      "learning_rate": 4.3378517819597785e-07,
      "loss": 0.4673,
      "step": 58990
    },
    {
      "epoch": 1.8121524897858876,
      "grad_norm": 0.41847434639930725,
      "learning_rate": 4.3364439438024486e-07,
      "loss": 0.458,
      "step": 58991
    },
    {
      "epoch": 1.8121832089208367,
      "grad_norm": 0.4713880717754364,
      "learning_rate": 4.3350363290740274e-07,
      "loss": 0.4696,
      "step": 58992
    },
    {
      "epoch": 1.8122139280557858,
      "grad_norm": 0.5034837126731873,
      "learning_rate": 4.333628937777812e-07,
      "loss": 0.5014,
      "step": 58993
    },
    {
      "epoch": 1.812244647190735,
      "grad_norm": 0.49971842765808105,
      "learning_rate": 4.332221769917089e-07,
      "loss": 0.5206,
      "step": 58994
    },
    {
      "epoch": 1.8122753663256843,
      "grad_norm": 0.4335314631462097,
      "learning_rate": 4.330814825495133e-07,
      "loss": 0.4963,
      "step": 58995
    },
    {
      "epoch": 1.8123060854606334,
      "grad_norm": 0.47503092885017395,
      "learning_rate": 4.3294081045152646e-07,
      "loss": 0.4838,
      "step": 58996
    },
    {
      "epoch": 1.8123368045955826,
      "grad_norm": 0.4195624887943268,
      "learning_rate": 4.328001606980725e-07,
      "loss": 0.4321,
      "step": 58997
    },
    {
      "epoch": 1.812367523730532,
      "grad_norm": 0.4381263256072998,
      "learning_rate": 4.326595332894823e-07,
      "loss": 0.4795,
      "step": 58998
    },
    {
      "epoch": 1.812398242865481,
      "grad_norm": 0.4186382591724396,
      "learning_rate": 4.325189282260833e-07,
      "loss": 0.4648,
      "step": 58999
    },
    {
      "epoch": 1.8124289620004301,
      "grad_norm": 0.43674060702323914,
      "learning_rate": 4.3237834550820647e-07,
      "loss": 0.5471,
      "step": 59000
    },
    {
      "epoch": 1.8124596811353793,
      "grad_norm": 0.4249512553215027,
      "learning_rate": 4.32237785136177e-07,
      "loss": 0.429,
      "step": 59001
    },
    {
      "epoch": 1.8124904002703284,
      "grad_norm": 0.4371129870414734,
      "learning_rate": 4.3209724711032464e-07,
      "loss": 0.4394,
      "step": 59002
    },
    {
      "epoch": 1.8125211194052775,
      "grad_norm": 0.42774319648742676,
      "learning_rate": 4.3195673143097694e-07,
      "loss": 0.4684,
      "step": 59003
    },
    {
      "epoch": 1.8125518385402266,
      "grad_norm": 0.4604623019695282,
      "learning_rate": 4.3181623809846363e-07,
      "loss": 0.5008,
      "step": 59004
    },
    {
      "epoch": 1.8125825576751757,
      "grad_norm": 0.44324856996536255,
      "learning_rate": 4.3167576711311e-07,
      "loss": 0.4927,
      "step": 59005
    },
    {
      "epoch": 1.812613276810125,
      "grad_norm": 0.43827423453330994,
      "learning_rate": 4.3153531847524686e-07,
      "loss": 0.4408,
      "step": 59006
    },
    {
      "epoch": 1.8126439959450742,
      "grad_norm": 0.4464986324310303,
      "learning_rate": 4.313948921852007e-07,
      "loss": 0.4739,
      "step": 59007
    },
    {
      "epoch": 1.8126747150800233,
      "grad_norm": 0.4431634843349457,
      "learning_rate": 4.312544882433012e-07,
      "loss": 0.5142,
      "step": 59008
    },
    {
      "epoch": 1.8127054342149727,
      "grad_norm": 0.4447980523109436,
      "learning_rate": 4.311141066498747e-07,
      "loss": 0.4897,
      "step": 59009
    },
    {
      "epoch": 1.8127361533499218,
      "grad_norm": 0.4470975697040558,
      "learning_rate": 4.3097374740524887e-07,
      "loss": 0.4072,
      "step": 59010
    },
    {
      "epoch": 1.812766872484871,
      "grad_norm": 0.3989172875881195,
      "learning_rate": 4.3083341050975113e-07,
      "loss": 0.4136,
      "step": 59011
    },
    {
      "epoch": 1.81279759161982,
      "grad_norm": 0.4471004903316498,
      "learning_rate": 4.306930959637112e-07,
      "loss": 0.5112,
      "step": 59012
    },
    {
      "epoch": 1.8128283107547691,
      "grad_norm": 0.4714687466621399,
      "learning_rate": 4.305528037674578e-07,
      "loss": 0.5132,
      "step": 59013
    },
    {
      "epoch": 1.8128590298897183,
      "grad_norm": 0.4957297444343567,
      "learning_rate": 4.30412533921315e-07,
      "loss": 0.3913,
      "step": 59014
    },
    {
      "epoch": 1.8128897490246674,
      "grad_norm": 0.3985300660133362,
      "learning_rate": 4.302722864256115e-07,
      "loss": 0.4726,
      "step": 59015
    },
    {
      "epoch": 1.8129204681596165,
      "grad_norm": 0.39952701330184937,
      "learning_rate": 4.3013206128067587e-07,
      "loss": 0.3903,
      "step": 59016
    },
    {
      "epoch": 1.8129511872945658,
      "grad_norm": 0.7419229745864868,
      "learning_rate": 4.2999185848683565e-07,
      "loss": 0.4365,
      "step": 59017
    },
    {
      "epoch": 1.812981906429515,
      "grad_norm": 0.40135082602500916,
      "learning_rate": 4.298516780444173e-07,
      "loss": 0.4537,
      "step": 59018
    },
    {
      "epoch": 1.813012625564464,
      "grad_norm": 0.4203955829143524,
      "learning_rate": 4.297115199537505e-07,
      "loss": 0.4499,
      "step": 59019
    },
    {
      "epoch": 1.8130433446994134,
      "grad_norm": 0.44630199670791626,
      "learning_rate": 4.295713842151572e-07,
      "loss": 0.5149,
      "step": 59020
    },
    {
      "epoch": 1.8130740638343625,
      "grad_norm": 0.45934340357780457,
      "learning_rate": 4.294312708289716e-07,
      "loss": 0.434,
      "step": 59021
    },
    {
      "epoch": 1.8131047829693117,
      "grad_norm": 0.6197630763053894,
      "learning_rate": 4.292911797955157e-07,
      "loss": 0.5127,
      "step": 59022
    },
    {
      "epoch": 1.8131355021042608,
      "grad_norm": 0.42592987418174744,
      "learning_rate": 4.291511111151214e-07,
      "loss": 0.427,
      "step": 59023
    },
    {
      "epoch": 1.81316622123921,
      "grad_norm": 0.39468005299568176,
      "learning_rate": 4.2901106478811074e-07,
      "loss": 0.4876,
      "step": 59024
    },
    {
      "epoch": 1.813196940374159,
      "grad_norm": 0.45651453733444214,
      "learning_rate": 4.2887104081481225e-07,
      "loss": 0.4789,
      "step": 59025
    },
    {
      "epoch": 1.8132276595091081,
      "grad_norm": 0.45812803506851196,
      "learning_rate": 4.2873103919555567e-07,
      "loss": 0.4061,
      "step": 59026
    },
    {
      "epoch": 1.8132583786440573,
      "grad_norm": 0.420872300863266,
      "learning_rate": 4.285910599306664e-07,
      "loss": 0.4906,
      "step": 59027
    },
    {
      "epoch": 1.8132890977790066,
      "grad_norm": 0.4060496687889099,
      "learning_rate": 4.2845110302046964e-07,
      "loss": 0.4204,
      "step": 59028
    },
    {
      "epoch": 1.8133198169139557,
      "grad_norm": 0.4182383418083191,
      "learning_rate": 4.283111684652952e-07,
      "loss": 0.4297,
      "step": 59029
    },
    {
      "epoch": 1.8133505360489048,
      "grad_norm": 0.4439021050930023,
      "learning_rate": 4.2817125626546717e-07,
      "loss": 0.4543,
      "step": 59030
    },
    {
      "epoch": 1.8133812551838542,
      "grad_norm": 0.4721316993236542,
      "learning_rate": 4.280313664213143e-07,
      "loss": 0.3885,
      "step": 59031
    },
    {
      "epoch": 1.8134119743188033,
      "grad_norm": 0.4423353970050812,
      "learning_rate": 4.2789149893316395e-07,
      "loss": 0.3926,
      "step": 59032
    },
    {
      "epoch": 1.8134426934537524,
      "grad_norm": 0.40913885831832886,
      "learning_rate": 4.277516538013393e-07,
      "loss": 0.4713,
      "step": 59033
    },
    {
      "epoch": 1.8134734125887015,
      "grad_norm": 0.414721816778183,
      "learning_rate": 4.276118310261701e-07,
      "loss": 0.4924,
      "step": 59034
    },
    {
      "epoch": 1.8135041317236507,
      "grad_norm": 0.4259317219257355,
      "learning_rate": 4.2747203060798157e-07,
      "loss": 0.5282,
      "step": 59035
    },
    {
      "epoch": 1.8135348508585998,
      "grad_norm": 0.5110343098640442,
      "learning_rate": 4.273322525471024e-07,
      "loss": 0.4487,
      "step": 59036
    },
    {
      "epoch": 1.813565569993549,
      "grad_norm": 0.4218038320541382,
      "learning_rate": 4.271924968438557e-07,
      "loss": 0.5283,
      "step": 59037
    },
    {
      "epoch": 1.813596289128498,
      "grad_norm": 0.42843714356422424,
      "learning_rate": 4.2705276349856997e-07,
      "loss": 0.4342,
      "step": 59038
    },
    {
      "epoch": 1.8136270082634471,
      "grad_norm": 0.3984893560409546,
      "learning_rate": 4.2691305251157053e-07,
      "loss": 0.3883,
      "step": 59039
    },
    {
      "epoch": 1.8136577273983965,
      "grad_norm": 0.4265230894088745,
      "learning_rate": 4.2677336388318614e-07,
      "loss": 0.3756,
      "step": 59040
    },
    {
      "epoch": 1.8136884465333456,
      "grad_norm": 0.4779064357280731,
      "learning_rate": 4.2663369761373865e-07,
      "loss": 0.4964,
      "step": 59041
    },
    {
      "epoch": 1.813719165668295,
      "grad_norm": 0.4371184706687927,
      "learning_rate": 4.264940537035578e-07,
      "loss": 0.4326,
      "step": 59042
    },
    {
      "epoch": 1.813749884803244,
      "grad_norm": 0.49080318212509155,
      "learning_rate": 4.263544321529689e-07,
      "loss": 0.482,
      "step": 59043
    },
    {
      "epoch": 1.8137806039381932,
      "grad_norm": 0.4475800096988678,
      "learning_rate": 4.2621483296229836e-07,
      "loss": 0.5463,
      "step": 59044
    },
    {
      "epoch": 1.8138113230731423,
      "grad_norm": 0.5453711152076721,
      "learning_rate": 4.260752561318704e-07,
      "loss": 0.4842,
      "step": 59045
    },
    {
      "epoch": 1.8138420422080914,
      "grad_norm": 0.4343716502189636,
      "learning_rate": 4.2593570166201357e-07,
      "loss": 0.4949,
      "step": 59046
    },
    {
      "epoch": 1.8138727613430405,
      "grad_norm": 0.46446511149406433,
      "learning_rate": 4.2579616955305104e-07,
      "loss": 0.4107,
      "step": 59047
    },
    {
      "epoch": 1.8139034804779897,
      "grad_norm": 0.4397277235984802,
      "learning_rate": 4.2565665980531135e-07,
      "loss": 0.5088,
      "step": 59048
    },
    {
      "epoch": 1.8139341996129388,
      "grad_norm": 0.4158153533935547,
      "learning_rate": 4.255171724191187e-07,
      "loss": 0.5263,
      "step": 59049
    },
    {
      "epoch": 1.813964918747888,
      "grad_norm": 0.4584183394908905,
      "learning_rate": 4.253777073947996e-07,
      "loss": 0.4266,
      "step": 59050
    },
    {
      "epoch": 1.8139956378828372,
      "grad_norm": 0.42861679196357727,
      "learning_rate": 4.252382647326792e-07,
      "loss": 0.5041,
      "step": 59051
    },
    {
      "epoch": 1.8140263570177864,
      "grad_norm": 0.5261752605438232,
      "learning_rate": 4.250988444330839e-07,
      "loss": 0.5287,
      "step": 59052
    },
    {
      "epoch": 1.8140570761527357,
      "grad_norm": 0.4460296332836151,
      "learning_rate": 4.2495944649633914e-07,
      "loss": 0.5462,
      "step": 59053
    },
    {
      "epoch": 1.8140877952876848,
      "grad_norm": 0.4321652054786682,
      "learning_rate": 4.2482007092277014e-07,
      "loss": 0.4613,
      "step": 59054
    },
    {
      "epoch": 1.814118514422634,
      "grad_norm": 0.4197251498699188,
      "learning_rate": 4.2468071771270323e-07,
      "loss": 0.4715,
      "step": 59055
    },
    {
      "epoch": 1.814149233557583,
      "grad_norm": 0.42078155279159546,
      "learning_rate": 4.245413868664616e-07,
      "loss": 0.3957,
      "step": 59056
    },
    {
      "epoch": 1.8141799526925322,
      "grad_norm": 0.4492993652820587,
      "learning_rate": 4.2440207838437385e-07,
      "loss": 0.512,
      "step": 59057
    },
    {
      "epoch": 1.8142106718274813,
      "grad_norm": 0.5013481378555298,
      "learning_rate": 4.2426279226676305e-07,
      "loss": 0.4462,
      "step": 59058
    },
    {
      "epoch": 1.8142413909624304,
      "grad_norm": 0.4311249554157257,
      "learning_rate": 4.2412352851395556e-07,
      "loss": 0.4505,
      "step": 59059
    },
    {
      "epoch": 1.8142721100973795,
      "grad_norm": 0.4324817359447479,
      "learning_rate": 4.239842871262767e-07,
      "loss": 0.559,
      "step": 59060
    },
    {
      "epoch": 1.8143028292323287,
      "grad_norm": 0.40395981073379517,
      "learning_rate": 4.2384506810404956e-07,
      "loss": 0.518,
      "step": 59061
    },
    {
      "epoch": 1.814333548367278,
      "grad_norm": 0.4170984625816345,
      "learning_rate": 4.237058714476028e-07,
      "loss": 0.4384,
      "step": 59062
    },
    {
      "epoch": 1.8143642675022271,
      "grad_norm": 0.40945473313331604,
      "learning_rate": 4.235666971572594e-07,
      "loss": 0.4878,
      "step": 59063
    },
    {
      "epoch": 1.8143949866371762,
      "grad_norm": 0.4512573182582855,
      "learning_rate": 4.2342754523334473e-07,
      "loss": 0.4675,
      "step": 59064
    },
    {
      "epoch": 1.8144257057721256,
      "grad_norm": 0.44498977065086365,
      "learning_rate": 4.2328841567618407e-07,
      "loss": 0.4582,
      "step": 59065
    },
    {
      "epoch": 1.8144564249070747,
      "grad_norm": 0.4586789011955261,
      "learning_rate": 4.2314930848610157e-07,
      "loss": 0.5396,
      "step": 59066
    },
    {
      "epoch": 1.8144871440420238,
      "grad_norm": 0.45585688948631287,
      "learning_rate": 4.230102236634226e-07,
      "loss": 0.4483,
      "step": 59067
    },
    {
      "epoch": 1.814517863176973,
      "grad_norm": 0.3952379524707794,
      "learning_rate": 4.228711612084735e-07,
      "loss": 0.479,
      "step": 59068
    },
    {
      "epoch": 1.814548582311922,
      "grad_norm": 0.6327850222587585,
      "learning_rate": 4.227321211215762e-07,
      "loss": 0.47,
      "step": 59069
    },
    {
      "epoch": 1.8145793014468712,
      "grad_norm": 1.2437107563018799,
      "learning_rate": 4.2259310340305614e-07,
      "loss": 0.4089,
      "step": 59070
    },
    {
      "epoch": 1.8146100205818203,
      "grad_norm": 0.4461742341518402,
      "learning_rate": 4.224541080532396e-07,
      "loss": 0.4452,
      "step": 59071
    },
    {
      "epoch": 1.8146407397167694,
      "grad_norm": 0.3921782374382019,
      "learning_rate": 4.2231513507245194e-07,
      "loss": 0.4657,
      "step": 59072
    },
    {
      "epoch": 1.8146714588517188,
      "grad_norm": 0.4037177562713623,
      "learning_rate": 4.2217618446101506e-07,
      "loss": 0.5371,
      "step": 59073
    },
    {
      "epoch": 1.8147021779866679,
      "grad_norm": 0.4100784659385681,
      "learning_rate": 4.220372562192543e-07,
      "loss": 0.5151,
      "step": 59074
    },
    {
      "epoch": 1.814732897121617,
      "grad_norm": 0.4469992220401764,
      "learning_rate": 4.218983503474938e-07,
      "loss": 0.4487,
      "step": 59075
    },
    {
      "epoch": 1.8147636162565663,
      "grad_norm": 0.41018956899642944,
      "learning_rate": 4.217594668460612e-07,
      "loss": 0.475,
      "step": 59076
    },
    {
      "epoch": 1.8147943353915155,
      "grad_norm": 0.46485579013824463,
      "learning_rate": 4.216206057152761e-07,
      "loss": 0.5146,
      "step": 59077
    },
    {
      "epoch": 1.8148250545264646,
      "grad_norm": 0.45851361751556396,
      "learning_rate": 4.2148176695546496e-07,
      "loss": 0.4499,
      "step": 59078
    },
    {
      "epoch": 1.8148557736614137,
      "grad_norm": 0.4330700635910034,
      "learning_rate": 4.2134295056695197e-07,
      "loss": 0.428,
      "step": 59079
    },
    {
      "epoch": 1.8148864927963628,
      "grad_norm": 0.4423965513706207,
      "learning_rate": 4.2120415655006354e-07,
      "loss": 0.4695,
      "step": 59080
    },
    {
      "epoch": 1.814917211931312,
      "grad_norm": 0.42273497581481934,
      "learning_rate": 4.210653849051205e-07,
      "loss": 0.4774,
      "step": 59081
    },
    {
      "epoch": 1.814947931066261,
      "grad_norm": 0.4489041566848755,
      "learning_rate": 4.209266356324493e-07,
      "loss": 0.5191,
      "step": 59082
    },
    {
      "epoch": 1.8149786502012102,
      "grad_norm": 0.49364230036735535,
      "learning_rate": 4.2078790873236965e-07,
      "loss": 0.4775,
      "step": 59083
    },
    {
      "epoch": 1.8150093693361595,
      "grad_norm": 0.4757547676563263,
      "learning_rate": 4.206492042052124e-07,
      "loss": 0.4792,
      "step": 59084
    },
    {
      "epoch": 1.8150400884711086,
      "grad_norm": 0.45443952083587646,
      "learning_rate": 4.2051052205129614e-07,
      "loss": 0.4534,
      "step": 59085
    },
    {
      "epoch": 1.8150708076060578,
      "grad_norm": 0.4631458520889282,
      "learning_rate": 4.203718622709463e-07,
      "loss": 0.5155,
      "step": 59086
    },
    {
      "epoch": 1.815101526741007,
      "grad_norm": 0.4576922655105591,
      "learning_rate": 4.202332248644891e-07,
      "loss": 0.5112,
      "step": 59087
    },
    {
      "epoch": 1.8151322458759562,
      "grad_norm": 0.4617301821708679,
      "learning_rate": 4.2009460983224337e-07,
      "loss": 0.4694,
      "step": 59088
    },
    {
      "epoch": 1.8151629650109053,
      "grad_norm": 0.49347782135009766,
      "learning_rate": 4.199560171745376e-07,
      "loss": 0.4118,
      "step": 59089
    },
    {
      "epoch": 1.8151936841458545,
      "grad_norm": 0.45168420672416687,
      "learning_rate": 4.1981744689169266e-07,
      "loss": 0.4952,
      "step": 59090
    },
    {
      "epoch": 1.8152244032808036,
      "grad_norm": 0.4830711781978607,
      "learning_rate": 4.19678898984035e-07,
      "loss": 0.5295,
      "step": 59091
    },
    {
      "epoch": 1.8152551224157527,
      "grad_norm": 0.42855265736579895,
      "learning_rate": 4.195403734518833e-07,
      "loss": 0.4786,
      "step": 59092
    },
    {
      "epoch": 1.8152858415507018,
      "grad_norm": 0.45077770948410034,
      "learning_rate": 4.1940187029556713e-07,
      "loss": 0.5191,
      "step": 59093
    },
    {
      "epoch": 1.815316560685651,
      "grad_norm": 0.41368240118026733,
      "learning_rate": 4.192633895154052e-07,
      "loss": 0.5407,
      "step": 59094
    },
    {
      "epoch": 1.8153472798206003,
      "grad_norm": 0.4770818054676056,
      "learning_rate": 4.19124931111724e-07,
      "loss": 0.4261,
      "step": 59095
    },
    {
      "epoch": 1.8153779989555494,
      "grad_norm": 0.5508142709732056,
      "learning_rate": 4.1898649508484545e-07,
      "loss": 0.5602,
      "step": 59096
    },
    {
      "epoch": 1.8154087180904985,
      "grad_norm": 0.48005837202072144,
      "learning_rate": 4.188480814350915e-07,
      "loss": 0.4795,
      "step": 59097
    },
    {
      "epoch": 1.8154394372254479,
      "grad_norm": 0.4778270423412323,
      "learning_rate": 4.187096901627885e-07,
      "loss": 0.4467,
      "step": 59098
    },
    {
      "epoch": 1.815470156360397,
      "grad_norm": 0.44279125332832336,
      "learning_rate": 4.185713212682585e-07,
      "loss": 0.4482,
      "step": 59099
    },
    {
      "epoch": 1.8155008754953461,
      "grad_norm": 0.5661644339561462,
      "learning_rate": 4.1843297475182344e-07,
      "loss": 0.4867,
      "step": 59100
    },
    {
      "epoch": 1.8155315946302952,
      "grad_norm": 0.43991631269454956,
      "learning_rate": 4.1829465061380634e-07,
      "loss": 0.4687,
      "step": 59101
    },
    {
      "epoch": 1.8155623137652444,
      "grad_norm": 0.414279580116272,
      "learning_rate": 4.181563488545326e-07,
      "loss": 0.5853,
      "step": 59102
    },
    {
      "epoch": 1.8155930329001935,
      "grad_norm": 0.4032971262931824,
      "learning_rate": 4.18018069474323e-07,
      "loss": 0.4586,
      "step": 59103
    },
    {
      "epoch": 1.8156237520351426,
      "grad_norm": 0.4518777132034302,
      "learning_rate": 4.1787981247350284e-07,
      "loss": 0.5291,
      "step": 59104
    },
    {
      "epoch": 1.8156544711700917,
      "grad_norm": 0.43174514174461365,
      "learning_rate": 4.17741577852393e-07,
      "loss": 0.4088,
      "step": 59105
    },
    {
      "epoch": 1.815685190305041,
      "grad_norm": 0.4097355008125305,
      "learning_rate": 4.1760336561131655e-07,
      "loss": 0.4638,
      "step": 59106
    },
    {
      "epoch": 1.8157159094399902,
      "grad_norm": 0.41386348009109497,
      "learning_rate": 4.174651757505965e-07,
      "loss": 0.4399,
      "step": 59107
    },
    {
      "epoch": 1.8157466285749393,
      "grad_norm": 0.46075135469436646,
      "learning_rate": 4.173270082705572e-07,
      "loss": 0.4815,
      "step": 59108
    },
    {
      "epoch": 1.8157773477098886,
      "grad_norm": 0.4555763900279999,
      "learning_rate": 4.171888631715182e-07,
      "loss": 0.4281,
      "step": 59109
    },
    {
      "epoch": 1.8158080668448378,
      "grad_norm": 0.4162389039993286,
      "learning_rate": 4.170507404538038e-07,
      "loss": 0.4813,
      "step": 59110
    },
    {
      "epoch": 1.8158387859797869,
      "grad_norm": 0.4159030020236969,
      "learning_rate": 4.1691264011773815e-07,
      "loss": 0.544,
      "step": 59111
    },
    {
      "epoch": 1.815869505114736,
      "grad_norm": 0.5048578381538391,
      "learning_rate": 4.167745621636421e-07,
      "loss": 0.4088,
      "step": 59112
    },
    {
      "epoch": 1.8159002242496851,
      "grad_norm": 0.41868269443511963,
      "learning_rate": 4.166365065918376e-07,
      "loss": 0.4863,
      "step": 59113
    },
    {
      "epoch": 1.8159309433846342,
      "grad_norm": 0.49618884921073914,
      "learning_rate": 4.1649847340264783e-07,
      "loss": 0.4894,
      "step": 59114
    },
    {
      "epoch": 1.8159616625195834,
      "grad_norm": 0.42325618863105774,
      "learning_rate": 4.163604625963946e-07,
      "loss": 0.4902,
      "step": 59115
    },
    {
      "epoch": 1.8159923816545325,
      "grad_norm": 0.41121187806129456,
      "learning_rate": 4.1622247417340223e-07,
      "loss": 0.47,
      "step": 59116
    },
    {
      "epoch": 1.8160231007894818,
      "grad_norm": 0.41555795073509216,
      "learning_rate": 4.160845081339915e-07,
      "loss": 0.4737,
      "step": 59117
    },
    {
      "epoch": 1.816053819924431,
      "grad_norm": 0.4811232089996338,
      "learning_rate": 4.1594656447848435e-07,
      "loss": 0.498,
      "step": 59118
    },
    {
      "epoch": 1.81608453905938,
      "grad_norm": 0.4497198760509491,
      "learning_rate": 4.158086432072017e-07,
      "loss": 0.4215,
      "step": 59119
    },
    {
      "epoch": 1.8161152581943294,
      "grad_norm": 0.42362141609191895,
      "learning_rate": 4.1567074432046995e-07,
      "loss": 0.5121,
      "step": 59120
    },
    {
      "epoch": 1.8161459773292785,
      "grad_norm": 0.4188527762889862,
      "learning_rate": 4.1553286781860656e-07,
      "loss": 0.4598,
      "step": 59121
    },
    {
      "epoch": 1.8161766964642276,
      "grad_norm": 0.45192229747772217,
      "learning_rate": 4.1539501370193693e-07,
      "loss": 0.4719,
      "step": 59122
    },
    {
      "epoch": 1.8162074155991768,
      "grad_norm": 0.434900164604187,
      "learning_rate": 4.152571819707818e-07,
      "loss": 0.4427,
      "step": 59123
    },
    {
      "epoch": 1.8162381347341259,
      "grad_norm": 0.48484569787979126,
      "learning_rate": 4.1511937262545985e-07,
      "loss": 0.5326,
      "step": 59124
    },
    {
      "epoch": 1.816268853869075,
      "grad_norm": 0.42881307005882263,
      "learning_rate": 4.1498158566629973e-07,
      "loss": 0.4944,
      "step": 59125
    },
    {
      "epoch": 1.8162995730040241,
      "grad_norm": 0.42400965094566345,
      "learning_rate": 4.1484382109361786e-07,
      "loss": 0.4755,
      "step": 59126
    },
    {
      "epoch": 1.8163302921389732,
      "grad_norm": 0.5169454216957092,
      "learning_rate": 4.147060789077384e-07,
      "loss": 0.4448,
      "step": 59127
    },
    {
      "epoch": 1.8163610112739226,
      "grad_norm": 0.4288768470287323,
      "learning_rate": 4.145683591089822e-07,
      "loss": 0.5096,
      "step": 59128
    },
    {
      "epoch": 1.8163917304088717,
      "grad_norm": 0.4655841588973999,
      "learning_rate": 4.144306616976701e-07,
      "loss": 0.4784,
      "step": 59129
    },
    {
      "epoch": 1.8164224495438208,
      "grad_norm": 0.4121358096599579,
      "learning_rate": 4.142929866741252e-07,
      "loss": 0.4781,
      "step": 59130
    },
    {
      "epoch": 1.8164531686787702,
      "grad_norm": 0.4457049071788788,
      "learning_rate": 4.141553340386695e-07,
      "loss": 0.459,
      "step": 59131
    },
    {
      "epoch": 1.8164838878137193,
      "grad_norm": 0.41829240322113037,
      "learning_rate": 4.1401770379162156e-07,
      "loss": 0.5499,
      "step": 59132
    },
    {
      "epoch": 1.8165146069486684,
      "grad_norm": 0.4583802819252014,
      "learning_rate": 4.138800959333056e-07,
      "loss": 0.4662,
      "step": 59133
    },
    {
      "epoch": 1.8165453260836175,
      "grad_norm": 0.42312100529670715,
      "learning_rate": 4.1374251046404244e-07,
      "loss": 0.4777,
      "step": 59134
    },
    {
      "epoch": 1.8165760452185666,
      "grad_norm": 0.44857534766197205,
      "learning_rate": 4.13604947384153e-07,
      "loss": 0.4112,
      "step": 59135
    },
    {
      "epoch": 1.8166067643535158,
      "grad_norm": 0.42165347933769226,
      "learning_rate": 4.1346740669395924e-07,
      "loss": 0.3872,
      "step": 59136
    },
    {
      "epoch": 1.8166374834884649,
      "grad_norm": 0.4010883569717407,
      "learning_rate": 4.133298883937809e-07,
      "loss": 0.4979,
      "step": 59137
    },
    {
      "epoch": 1.816668202623414,
      "grad_norm": 0.42082110047340393,
      "learning_rate": 4.1319239248393984e-07,
      "loss": 0.495,
      "step": 59138
    },
    {
      "epoch": 1.8166989217583633,
      "grad_norm": 0.46913039684295654,
      "learning_rate": 4.1305491896475926e-07,
      "loss": 0.4462,
      "step": 59139
    },
    {
      "epoch": 1.8167296408933125,
      "grad_norm": 0.4484691321849823,
      "learning_rate": 4.129174678365566e-07,
      "loss": 0.4233,
      "step": 59140
    },
    {
      "epoch": 1.8167603600282616,
      "grad_norm": 0.4711850583553314,
      "learning_rate": 4.12780039099655e-07,
      "loss": 0.4984,
      "step": 59141
    },
    {
      "epoch": 1.816791079163211,
      "grad_norm": 0.48130834102630615,
      "learning_rate": 4.126426327543753e-07,
      "loss": 0.3849,
      "step": 59142
    },
    {
      "epoch": 1.81682179829816,
      "grad_norm": 0.424272745847702,
      "learning_rate": 4.1250524880103837e-07,
      "loss": 0.4432,
      "step": 59143
    },
    {
      "epoch": 1.8168525174331092,
      "grad_norm": 0.42916056513786316,
      "learning_rate": 4.1236788723996723e-07,
      "loss": 0.4179,
      "step": 59144
    },
    {
      "epoch": 1.8168832365680583,
      "grad_norm": 0.4295186698436737,
      "learning_rate": 4.122305480714783e-07,
      "loss": 0.4165,
      "step": 59145
    },
    {
      "epoch": 1.8169139557030074,
      "grad_norm": 0.4365394413471222,
      "learning_rate": 4.1209323129589365e-07,
      "loss": 0.4768,
      "step": 59146
    },
    {
      "epoch": 1.8169446748379565,
      "grad_norm": 0.4224342107772827,
      "learning_rate": 4.1195593691353617e-07,
      "loss": 0.5162,
      "step": 59147
    },
    {
      "epoch": 1.8169753939729056,
      "grad_norm": 0.4164402484893799,
      "learning_rate": 4.118186649247258e-07,
      "loss": 0.4776,
      "step": 59148
    },
    {
      "epoch": 1.8170061131078548,
      "grad_norm": 0.4799780547618866,
      "learning_rate": 4.116814153297821e-07,
      "loss": 0.5416,
      "step": 59149
    },
    {
      "epoch": 1.8170368322428039,
      "grad_norm": 0.42939820885658264,
      "learning_rate": 4.115441881290261e-07,
      "loss": 0.4646,
      "step": 59150
    },
    {
      "epoch": 1.8170675513777532,
      "grad_norm": 0.4385007619857788,
      "learning_rate": 4.1140698332277627e-07,
      "loss": 0.5355,
      "step": 59151
    },
    {
      "epoch": 1.8170982705127023,
      "grad_norm": 0.43480604887008667,
      "learning_rate": 4.11269800911358e-07,
      "loss": 0.4428,
      "step": 59152
    },
    {
      "epoch": 1.8171289896476517,
      "grad_norm": 0.4125262498855591,
      "learning_rate": 4.1113264089508777e-07,
      "loss": 0.3922,
      "step": 59153
    },
    {
      "epoch": 1.8171597087826008,
      "grad_norm": 0.49356740713119507,
      "learning_rate": 4.109955032742874e-07,
      "loss": 0.5131,
      "step": 59154
    },
    {
      "epoch": 1.81719042791755,
      "grad_norm": 0.43759390711784363,
      "learning_rate": 4.108583880492745e-07,
      "loss": 0.4699,
      "step": 59155
    },
    {
      "epoch": 1.817221147052499,
      "grad_norm": 0.4457870125770569,
      "learning_rate": 4.107212952203743e-07,
      "loss": 0.4115,
      "step": 59156
    },
    {
      "epoch": 1.8172518661874482,
      "grad_norm": 0.4140380322933197,
      "learning_rate": 4.1058422478790326e-07,
      "loss": 0.4414,
      "step": 59157
    },
    {
      "epoch": 1.8172825853223973,
      "grad_norm": 0.41847190260887146,
      "learning_rate": 4.1044717675218114e-07,
      "loss": 0.4652,
      "step": 59158
    },
    {
      "epoch": 1.8173133044573464,
      "grad_norm": 0.4344784617424011,
      "learning_rate": 4.103101511135321e-07,
      "loss": 0.4186,
      "step": 59159
    },
    {
      "epoch": 1.8173440235922955,
      "grad_norm": 0.4229638874530792,
      "learning_rate": 4.1017314787227035e-07,
      "loss": 0.4993,
      "step": 59160
    },
    {
      "epoch": 1.8173747427272446,
      "grad_norm": 0.47536030411720276,
      "learning_rate": 4.100361670287212e-07,
      "loss": 0.5142,
      "step": 59161
    },
    {
      "epoch": 1.817405461862194,
      "grad_norm": 0.4362155795097351,
      "learning_rate": 4.09899208583201e-07,
      "loss": 0.5253,
      "step": 59162
    },
    {
      "epoch": 1.817436180997143,
      "grad_norm": 0.4293624460697174,
      "learning_rate": 4.0976227253603286e-07,
      "loss": 0.487,
      "step": 59163
    },
    {
      "epoch": 1.8174669001320924,
      "grad_norm": 0.47020289301872253,
      "learning_rate": 4.096253588875332e-07,
      "loss": 0.5259,
      "step": 59164
    },
    {
      "epoch": 1.8174976192670416,
      "grad_norm": 0.42553839087486267,
      "learning_rate": 4.0948846763802285e-07,
      "loss": 0.5063,
      "step": 59165
    },
    {
      "epoch": 1.8175283384019907,
      "grad_norm": 0.45303165912628174,
      "learning_rate": 4.093515987878227e-07,
      "loss": 0.4634,
      "step": 59166
    },
    {
      "epoch": 1.8175590575369398,
      "grad_norm": 0.4313051402568817,
      "learning_rate": 4.092147523372525e-07,
      "loss": 0.4562,
      "step": 59167
    },
    {
      "epoch": 1.817589776671889,
      "grad_norm": 0.4392039477825165,
      "learning_rate": 4.090779282866297e-07,
      "loss": 0.4796,
      "step": 59168
    },
    {
      "epoch": 1.817620495806838,
      "grad_norm": 0.44169649481773376,
      "learning_rate": 4.089411266362753e-07,
      "loss": 0.5239,
      "step": 59169
    },
    {
      "epoch": 1.8176512149417872,
      "grad_norm": 0.43159687519073486,
      "learning_rate": 4.0880434738650886e-07,
      "loss": 0.4737,
      "step": 59170
    },
    {
      "epoch": 1.8176819340767363,
      "grad_norm": 0.4160975217819214,
      "learning_rate": 4.0866759053765137e-07,
      "loss": 0.4328,
      "step": 59171
    },
    {
      "epoch": 1.8177126532116854,
      "grad_norm": 0.46240970492362976,
      "learning_rate": 4.0853085609001917e-07,
      "loss": 0.418,
      "step": 59172
    },
    {
      "epoch": 1.8177433723466347,
      "grad_norm": 0.42783087491989136,
      "learning_rate": 4.0839414404393207e-07,
      "loss": 0.5222,
      "step": 59173
    },
    {
      "epoch": 1.8177740914815839,
      "grad_norm": 0.48634839057922363,
      "learning_rate": 4.082574543997109e-07,
      "loss": 0.4419,
      "step": 59174
    },
    {
      "epoch": 1.817804810616533,
      "grad_norm": 0.3957710564136505,
      "learning_rate": 4.0812078715767643e-07,
      "loss": 0.3989,
      "step": 59175
    },
    {
      "epoch": 1.8178355297514823,
      "grad_norm": 0.4315139949321747,
      "learning_rate": 4.07984142318143e-07,
      "loss": 0.4215,
      "step": 59176
    },
    {
      "epoch": 1.8178662488864314,
      "grad_norm": 0.46818578243255615,
      "learning_rate": 4.0784751988143354e-07,
      "loss": 0.4756,
      "step": 59177
    },
    {
      "epoch": 1.8178969680213806,
      "grad_norm": 0.5067698359489441,
      "learning_rate": 4.0771091984786573e-07,
      "loss": 0.498,
      "step": 59178
    },
    {
      "epoch": 1.8179276871563297,
      "grad_norm": 0.44666796922683716,
      "learning_rate": 4.0757434221775916e-07,
      "loss": 0.4896,
      "step": 59179
    },
    {
      "epoch": 1.8179584062912788,
      "grad_norm": 0.44483062624931335,
      "learning_rate": 4.0743778699143366e-07,
      "loss": 0.4707,
      "step": 59180
    },
    {
      "epoch": 1.817989125426228,
      "grad_norm": 0.37673258781433105,
      "learning_rate": 4.0730125416920674e-07,
      "loss": 0.438,
      "step": 59181
    },
    {
      "epoch": 1.818019844561177,
      "grad_norm": 0.47635459899902344,
      "learning_rate": 4.0716474375139594e-07,
      "loss": 0.3862,
      "step": 59182
    },
    {
      "epoch": 1.8180505636961262,
      "grad_norm": 0.41770267486572266,
      "learning_rate": 4.070282557383232e-07,
      "loss": 0.5235,
      "step": 59183
    },
    {
      "epoch": 1.8180812828310755,
      "grad_norm": 0.4420009255409241,
      "learning_rate": 4.068917901303071e-07,
      "loss": 0.4419,
      "step": 59184
    },
    {
      "epoch": 1.8181120019660246,
      "grad_norm": 0.40435221791267395,
      "learning_rate": 4.0675534692766416e-07,
      "loss": 0.4772,
      "step": 59185
    },
    {
      "epoch": 1.8181427211009737,
      "grad_norm": 0.5295398831367493,
      "learning_rate": 4.0661892613071406e-07,
      "loss": 0.4811,
      "step": 59186
    },
    {
      "epoch": 1.818173440235923,
      "grad_norm": 0.4638144075870514,
      "learning_rate": 4.0648252773977436e-07,
      "loss": 0.5518,
      "step": 59187
    },
    {
      "epoch": 1.8182041593708722,
      "grad_norm": 0.45414528250694275,
      "learning_rate": 4.063461517551659e-07,
      "loss": 0.4617,
      "step": 59188
    },
    {
      "epoch": 1.8182348785058213,
      "grad_norm": 0.42356687784194946,
      "learning_rate": 4.0620979817720617e-07,
      "loss": 0.4499,
      "step": 59189
    },
    {
      "epoch": 1.8182655976407704,
      "grad_norm": 0.8363080620765686,
      "learning_rate": 4.0607346700621385e-07,
      "loss": 0.4453,
      "step": 59190
    },
    {
      "epoch": 1.8182963167757196,
      "grad_norm": 0.4263418912887573,
      "learning_rate": 4.0593715824250644e-07,
      "loss": 0.5277,
      "step": 59191
    },
    {
      "epoch": 1.8183270359106687,
      "grad_norm": 0.44738808274269104,
      "learning_rate": 4.058008718864015e-07,
      "loss": 0.4076,
      "step": 59192
    },
    {
      "epoch": 1.8183577550456178,
      "grad_norm": 0.44425132870674133,
      "learning_rate": 4.0566460793821983e-07,
      "loss": 0.4999,
      "step": 59193
    },
    {
      "epoch": 1.818388474180567,
      "grad_norm": 0.4504430890083313,
      "learning_rate": 4.05528366398279e-07,
      "loss": 0.5147,
      "step": 59194
    },
    {
      "epoch": 1.8184191933155163,
      "grad_norm": 0.41435593366622925,
      "learning_rate": 4.0539214726689644e-07,
      "loss": 0.4191,
      "step": 59195
    },
    {
      "epoch": 1.8184499124504654,
      "grad_norm": 0.4300370216369629,
      "learning_rate": 4.052559505443887e-07,
      "loss": 0.4168,
      "step": 59196
    },
    {
      "epoch": 1.8184806315854145,
      "grad_norm": 0.4211203455924988,
      "learning_rate": 4.051197762310788e-07,
      "loss": 0.4274,
      "step": 59197
    },
    {
      "epoch": 1.8185113507203639,
      "grad_norm": 0.426247239112854,
      "learning_rate": 4.049836243272798e-07,
      "loss": 0.4282,
      "step": 59198
    },
    {
      "epoch": 1.818542069855313,
      "grad_norm": 0.4839823246002197,
      "learning_rate": 4.0484749483331365e-07,
      "loss": 0.4057,
      "step": 59199
    },
    {
      "epoch": 1.818572788990262,
      "grad_norm": 0.40452951192855835,
      "learning_rate": 4.047113877494946e-07,
      "loss": 0.4401,
      "step": 59200
    },
    {
      "epoch": 1.8186035081252112,
      "grad_norm": 0.43781009316444397,
      "learning_rate": 4.0457530307614233e-07,
      "loss": 0.4637,
      "step": 59201
    },
    {
      "epoch": 1.8186342272601603,
      "grad_norm": 0.42005684971809387,
      "learning_rate": 4.0443924081357444e-07,
      "loss": 0.4245,
      "step": 59202
    },
    {
      "epoch": 1.8186649463951094,
      "grad_norm": 0.39712077379226685,
      "learning_rate": 4.0430320096211063e-07,
      "loss": 0.4452,
      "step": 59203
    },
    {
      "epoch": 1.8186956655300586,
      "grad_norm": 0.43193620443344116,
      "learning_rate": 4.041671835220651e-07,
      "loss": 0.4727,
      "step": 59204
    },
    {
      "epoch": 1.8187263846650077,
      "grad_norm": 0.4167937636375427,
      "learning_rate": 4.0403118849375644e-07,
      "loss": 0.515,
      "step": 59205
    },
    {
      "epoch": 1.818757103799957,
      "grad_norm": 0.4490126669406891,
      "learning_rate": 4.0389521587750444e-07,
      "loss": 0.4607,
      "step": 59206
    },
    {
      "epoch": 1.8187878229349062,
      "grad_norm": 0.4265192747116089,
      "learning_rate": 4.0375926567362666e-07,
      "loss": 0.4831,
      "step": 59207
    },
    {
      "epoch": 1.8188185420698553,
      "grad_norm": 0.42527902126312256,
      "learning_rate": 4.036233378824372e-07,
      "loss": 0.435,
      "step": 59208
    },
    {
      "epoch": 1.8188492612048046,
      "grad_norm": 0.39263635873794556,
      "learning_rate": 4.0348743250425594e-07,
      "loss": 0.4576,
      "step": 59209
    },
    {
      "epoch": 1.8188799803397537,
      "grad_norm": 0.4369758069515228,
      "learning_rate": 4.0335154953940025e-07,
      "loss": 0.41,
      "step": 59210
    },
    {
      "epoch": 1.8189106994747029,
      "grad_norm": 0.4452415406703949,
      "learning_rate": 4.0321568898818777e-07,
      "loss": 0.5035,
      "step": 59211
    },
    {
      "epoch": 1.818941418609652,
      "grad_norm": 0.45639821887016296,
      "learning_rate": 4.030798508509348e-07,
      "loss": 0.4113,
      "step": 59212
    },
    {
      "epoch": 1.818972137744601,
      "grad_norm": 0.4619351923465729,
      "learning_rate": 4.02944035127959e-07,
      "loss": 0.5022,
      "step": 59213
    },
    {
      "epoch": 1.8190028568795502,
      "grad_norm": 0.467312753200531,
      "learning_rate": 4.0280824181957777e-07,
      "loss": 0.467,
      "step": 59214
    },
    {
      "epoch": 1.8190335760144993,
      "grad_norm": 0.46355077624320984,
      "learning_rate": 4.026724709261076e-07,
      "loss": 0.4197,
      "step": 59215
    },
    {
      "epoch": 1.8190642951494485,
      "grad_norm": 0.5407235026359558,
      "learning_rate": 4.025367224478671e-07,
      "loss": 0.4836,
      "step": 59216
    },
    {
      "epoch": 1.8190950142843978,
      "grad_norm": 0.45265325903892517,
      "learning_rate": 4.024009963851716e-07,
      "loss": 0.408,
      "step": 59217
    },
    {
      "epoch": 1.819125733419347,
      "grad_norm": 0.4357444643974304,
      "learning_rate": 4.022652927383397e-07,
      "loss": 0.383,
      "step": 59218
    },
    {
      "epoch": 1.819156452554296,
      "grad_norm": 0.4990386664867401,
      "learning_rate": 4.021296115076867e-07,
      "loss": 0.44,
      "step": 59219
    },
    {
      "epoch": 1.8191871716892454,
      "grad_norm": 0.4817109704017639,
      "learning_rate": 4.0199395269353126e-07,
      "loss": 0.4914,
      "step": 59220
    },
    {
      "epoch": 1.8192178908241945,
      "grad_norm": 0.41888004541397095,
      "learning_rate": 4.0185831629618863e-07,
      "loss": 0.4608,
      "step": 59221
    },
    {
      "epoch": 1.8192486099591436,
      "grad_norm": 0.39927980303764343,
      "learning_rate": 4.017227023159775e-07,
      "loss": 0.4877,
      "step": 59222
    },
    {
      "epoch": 1.8192793290940927,
      "grad_norm": 0.41952386498451233,
      "learning_rate": 4.015871107532099e-07,
      "loss": 0.4944,
      "step": 59223
    },
    {
      "epoch": 1.8193100482290419,
      "grad_norm": 0.4337276816368103,
      "learning_rate": 4.0145154160820985e-07,
      "loss": 0.4878,
      "step": 59224
    },
    {
      "epoch": 1.819340767363991,
      "grad_norm": 0.4055843651294708,
      "learning_rate": 4.0131599488128725e-07,
      "loss": 0.4053,
      "step": 59225
    },
    {
      "epoch": 1.81937148649894,
      "grad_norm": 0.4406430423259735,
      "learning_rate": 4.01180470572764e-07,
      "loss": 0.4384,
      "step": 59226
    },
    {
      "epoch": 1.8194022056338892,
      "grad_norm": 0.4148070812225342,
      "learning_rate": 4.0104496868295204e-07,
      "loss": 0.4348,
      "step": 59227
    },
    {
      "epoch": 1.8194329247688386,
      "grad_norm": 0.4196597635746002,
      "learning_rate": 4.009094892121701e-07,
      "loss": 0.4958,
      "step": 59228
    },
    {
      "epoch": 1.8194636439037877,
      "grad_norm": 0.42465174198150635,
      "learning_rate": 4.0077403216073564e-07,
      "loss": 0.4383,
      "step": 59229
    },
    {
      "epoch": 1.8194943630387368,
      "grad_norm": 0.45885932445526123,
      "learning_rate": 4.0063859752896394e-07,
      "loss": 0.3777,
      "step": 59230
    },
    {
      "epoch": 1.8195250821736861,
      "grad_norm": 0.47889816761016846,
      "learning_rate": 4.0050318531717035e-07,
      "loss": 0.4721,
      "step": 59231
    },
    {
      "epoch": 1.8195558013086353,
      "grad_norm": 0.4007295072078705,
      "learning_rate": 4.0036779552567127e-07,
      "loss": 0.3648,
      "step": 59232
    },
    {
      "epoch": 1.8195865204435844,
      "grad_norm": 0.40862205624580383,
      "learning_rate": 4.0023242815478426e-07,
      "loss": 0.4244,
      "step": 59233
    },
    {
      "epoch": 1.8196172395785335,
      "grad_norm": 0.4285201132297516,
      "learning_rate": 4.0009708320482453e-07,
      "loss": 0.5017,
      "step": 59234
    },
    {
      "epoch": 1.8196479587134826,
      "grad_norm": 0.4187369644641876,
      "learning_rate": 3.999617606761097e-07,
      "loss": 0.4539,
      "step": 59235
    },
    {
      "epoch": 1.8196786778484317,
      "grad_norm": 0.4122956097126007,
      "learning_rate": 3.998264605689539e-07,
      "loss": 0.4518,
      "step": 59236
    },
    {
      "epoch": 1.8197093969833809,
      "grad_norm": 0.4354856014251709,
      "learning_rate": 3.996911828836736e-07,
      "loss": 0.487,
      "step": 59237
    },
    {
      "epoch": 1.81974011611833,
      "grad_norm": 0.46736451983451843,
      "learning_rate": 3.9955592762058516e-07,
      "loss": 0.4801,
      "step": 59238
    },
    {
      "epoch": 1.8197708352532793,
      "grad_norm": 0.45779991149902344,
      "learning_rate": 3.994206947800061e-07,
      "loss": 0.488,
      "step": 59239
    },
    {
      "epoch": 1.8198015543882284,
      "grad_norm": 0.43382853269577026,
      "learning_rate": 3.9928548436224846e-07,
      "loss": 0.4209,
      "step": 59240
    },
    {
      "epoch": 1.8198322735231776,
      "grad_norm": 0.40491151809692383,
      "learning_rate": 3.991502963676297e-07,
      "loss": 0.4707,
      "step": 59241
    },
    {
      "epoch": 1.819862992658127,
      "grad_norm": 0.4311569929122925,
      "learning_rate": 3.9901513079646736e-07,
      "loss": 0.4224,
      "step": 59242
    },
    {
      "epoch": 1.819893711793076,
      "grad_norm": 0.4731721580028534,
      "learning_rate": 3.9887998764907567e-07,
      "loss": 0.5386,
      "step": 59243
    },
    {
      "epoch": 1.8199244309280251,
      "grad_norm": 0.44850435853004456,
      "learning_rate": 3.9874486692576985e-07,
      "loss": 0.4704,
      "step": 59244
    },
    {
      "epoch": 1.8199551500629743,
      "grad_norm": 0.4672795534133911,
      "learning_rate": 3.986097686268653e-07,
      "loss": 0.4079,
      "step": 59245
    },
    {
      "epoch": 1.8199858691979234,
      "grad_norm": 0.42532411217689514,
      "learning_rate": 3.9847469275267837e-07,
      "loss": 0.4579,
      "step": 59246
    },
    {
      "epoch": 1.8200165883328725,
      "grad_norm": 0.4276661276817322,
      "learning_rate": 3.983396393035255e-07,
      "loss": 0.4383,
      "step": 59247
    },
    {
      "epoch": 1.8200473074678216,
      "grad_norm": 0.43856433033943176,
      "learning_rate": 3.9820460827971976e-07,
      "loss": 0.5042,
      "step": 59248
    },
    {
      "epoch": 1.8200780266027707,
      "grad_norm": 0.5075134634971619,
      "learning_rate": 3.9806959968157866e-07,
      "loss": 0.5721,
      "step": 59249
    },
    {
      "epoch": 1.82010874573772,
      "grad_norm": 0.406433641910553,
      "learning_rate": 3.979346135094153e-07,
      "loss": 0.4407,
      "step": 59250
    },
    {
      "epoch": 1.8201394648726692,
      "grad_norm": 0.48919251561164856,
      "learning_rate": 3.9779964976354724e-07,
      "loss": 0.4805,
      "step": 59251
    },
    {
      "epoch": 1.8201701840076183,
      "grad_norm": 0.44009557366371155,
      "learning_rate": 3.9766470844428864e-07,
      "loss": 0.5065,
      "step": 59252
    },
    {
      "epoch": 1.8202009031425677,
      "grad_norm": 0.4188149869441986,
      "learning_rate": 3.9752978955195474e-07,
      "loss": 0.4899,
      "step": 59253
    },
    {
      "epoch": 1.8202316222775168,
      "grad_norm": 0.4200020432472229,
      "learning_rate": 3.9739489308686207e-07,
      "loss": 0.4742,
      "step": 59254
    },
    {
      "epoch": 1.820262341412466,
      "grad_norm": 0.47347748279571533,
      "learning_rate": 3.972600190493203e-07,
      "loss": 0.5154,
      "step": 59255
    },
    {
      "epoch": 1.820293060547415,
      "grad_norm": 0.4599859118461609,
      "learning_rate": 3.9712516743965256e-07,
      "loss": 0.3828,
      "step": 59256
    },
    {
      "epoch": 1.8203237796823641,
      "grad_norm": 0.45980313420295715,
      "learning_rate": 3.9699033825816746e-07,
      "loss": 0.4744,
      "step": 59257
    },
    {
      "epoch": 1.8203544988173133,
      "grad_norm": 0.3903866112232208,
      "learning_rate": 3.9685553150518364e-07,
      "loss": 0.4353,
      "step": 59258
    },
    {
      "epoch": 1.8203852179522624,
      "grad_norm": 0.4412148892879486,
      "learning_rate": 3.967207471810119e-07,
      "loss": 0.4546,
      "step": 59259
    },
    {
      "epoch": 1.8204159370872115,
      "grad_norm": 0.4487740993499756,
      "learning_rate": 3.9658598528597106e-07,
      "loss": 0.4311,
      "step": 59260
    },
    {
      "epoch": 1.8204466562221606,
      "grad_norm": 0.43324553966522217,
      "learning_rate": 3.9645124582037396e-07,
      "loss": 0.5163,
      "step": 59261
    },
    {
      "epoch": 1.82047737535711,
      "grad_norm": 0.41727134585380554,
      "learning_rate": 3.963165287845372e-07,
      "loss": 0.4976,
      "step": 59262
    },
    {
      "epoch": 1.820508094492059,
      "grad_norm": 0.43202143907546997,
      "learning_rate": 3.9618183417877263e-07,
      "loss": 0.4372,
      "step": 59263
    },
    {
      "epoch": 1.8205388136270084,
      "grad_norm": 0.6445104479789734,
      "learning_rate": 3.960471620033957e-07,
      "loss": 0.4711,
      "step": 59264
    },
    {
      "epoch": 1.8205695327619575,
      "grad_norm": 0.41808953881263733,
      "learning_rate": 3.959125122587215e-07,
      "loss": 0.478,
      "step": 59265
    },
    {
      "epoch": 1.8206002518969067,
      "grad_norm": 0.40451014041900635,
      "learning_rate": 3.9577788494506554e-07,
      "loss": 0.458,
      "step": 59266
    },
    {
      "epoch": 1.8206309710318558,
      "grad_norm": 0.4356233477592468,
      "learning_rate": 3.956432800627397e-07,
      "loss": 0.484,
      "step": 59267
    },
    {
      "epoch": 1.820661690166805,
      "grad_norm": 0.4266226589679718,
      "learning_rate": 3.9550869761206035e-07,
      "loss": 0.5212,
      "step": 59268
    },
    {
      "epoch": 1.820692409301754,
      "grad_norm": 0.4174347221851349,
      "learning_rate": 3.9537413759334065e-07,
      "loss": 0.5383,
      "step": 59269
    },
    {
      "epoch": 1.8207231284367031,
      "grad_norm": 0.47696128487586975,
      "learning_rate": 3.9523960000689587e-07,
      "loss": 0.4516,
      "step": 59270
    },
    {
      "epoch": 1.8207538475716523,
      "grad_norm": 0.43319445848464966,
      "learning_rate": 3.951050848530413e-07,
      "loss": 0.4699,
      "step": 59271
    },
    {
      "epoch": 1.8207845667066014,
      "grad_norm": 0.4378174841403961,
      "learning_rate": 3.949705921320879e-07,
      "loss": 0.4679,
      "step": 59272
    },
    {
      "epoch": 1.8208152858415507,
      "grad_norm": 0.46102583408355713,
      "learning_rate": 3.9483612184435084e-07,
      "loss": 0.4323,
      "step": 59273
    },
    {
      "epoch": 1.8208460049764998,
      "grad_norm": 0.4153119623661041,
      "learning_rate": 3.9470167399014545e-07,
      "loss": 0.4184,
      "step": 59274
    },
    {
      "epoch": 1.8208767241114492,
      "grad_norm": 0.49206212162971497,
      "learning_rate": 3.9456724856978603e-07,
      "loss": 0.4527,
      "step": 59275
    },
    {
      "epoch": 1.8209074432463983,
      "grad_norm": 0.4612235724925995,
      "learning_rate": 3.9443284558358555e-07,
      "loss": 0.4077,
      "step": 59276
    },
    {
      "epoch": 1.8209381623813474,
      "grad_norm": 0.42832526564598083,
      "learning_rate": 3.942984650318571e-07,
      "loss": 0.4717,
      "step": 59277
    },
    {
      "epoch": 1.8209688815162965,
      "grad_norm": 0.5057429075241089,
      "learning_rate": 3.941641069149149e-07,
      "loss": 0.4553,
      "step": 59278
    },
    {
      "epoch": 1.8209996006512457,
      "grad_norm": 0.4665127694606781,
      "learning_rate": 3.940297712330754e-07,
      "loss": 0.3822,
      "step": 59279
    },
    {
      "epoch": 1.8210303197861948,
      "grad_norm": 0.4096735119819641,
      "learning_rate": 3.938954579866483e-07,
      "loss": 0.4362,
      "step": 59280
    },
    {
      "epoch": 1.821061038921144,
      "grad_norm": 0.4340308904647827,
      "learning_rate": 3.9376116717595e-07,
      "loss": 0.4614,
      "step": 59281
    },
    {
      "epoch": 1.821091758056093,
      "grad_norm": 0.45853084325790405,
      "learning_rate": 3.9362689880129257e-07,
      "loss": 0.5413,
      "step": 59282
    },
    {
      "epoch": 1.8211224771910421,
      "grad_norm": 0.4360611140727997,
      "learning_rate": 3.934926528629923e-07,
      "loss": 0.4863,
      "step": 59283
    },
    {
      "epoch": 1.8211531963259915,
      "grad_norm": 0.39714473485946655,
      "learning_rate": 3.933584293613601e-07,
      "loss": 0.5075,
      "step": 59284
    },
    {
      "epoch": 1.8211839154609406,
      "grad_norm": 0.4894932806491852,
      "learning_rate": 3.9322422829671025e-07,
      "loss": 0.4732,
      "step": 59285
    },
    {
      "epoch": 1.8212146345958897,
      "grad_norm": 0.4830663204193115,
      "learning_rate": 3.930900496693546e-07,
      "loss": 0.4478,
      "step": 59286
    },
    {
      "epoch": 1.821245353730839,
      "grad_norm": 0.4318588674068451,
      "learning_rate": 3.929558934796085e-07,
      "loss": 0.4926,
      "step": 59287
    },
    {
      "epoch": 1.8212760728657882,
      "grad_norm": 0.43972596526145935,
      "learning_rate": 3.9282175972778725e-07,
      "loss": 0.524,
      "step": 59288
    },
    {
      "epoch": 1.8213067920007373,
      "grad_norm": 0.4311753213405609,
      "learning_rate": 3.926876484141995e-07,
      "loss": 0.48,
      "step": 59289
    },
    {
      "epoch": 1.8213375111356864,
      "grad_norm": 0.4204157888889313,
      "learning_rate": 3.925535595391616e-07,
      "loss": 0.4393,
      "step": 59290
    },
    {
      "epoch": 1.8213682302706355,
      "grad_norm": 0.5580801367759705,
      "learning_rate": 3.9241949310298457e-07,
      "loss": 0.4606,
      "step": 59291
    },
    {
      "epoch": 1.8213989494055847,
      "grad_norm": 0.49748554825782776,
      "learning_rate": 3.9228544910598466e-07,
      "loss": 0.5097,
      "step": 59292
    },
    {
      "epoch": 1.8214296685405338,
      "grad_norm": 0.40807268023490906,
      "learning_rate": 3.921514275484717e-07,
      "loss": 0.4601,
      "step": 59293
    },
    {
      "epoch": 1.821460387675483,
      "grad_norm": 0.46284693479537964,
      "learning_rate": 3.9201742843076207e-07,
      "loss": 0.5074,
      "step": 59294
    },
    {
      "epoch": 1.8214911068104322,
      "grad_norm": 0.454028457403183,
      "learning_rate": 3.9188345175316445e-07,
      "loss": 0.4267,
      "step": 59295
    },
    {
      "epoch": 1.8215218259453814,
      "grad_norm": 0.41238972544670105,
      "learning_rate": 3.9174949751599413e-07,
      "loss": 0.4993,
      "step": 59296
    },
    {
      "epoch": 1.8215525450803305,
      "grad_norm": 0.44498395919799805,
      "learning_rate": 3.9161556571956525e-07,
      "loss": 0.3965,
      "step": 59297
    },
    {
      "epoch": 1.8215832642152798,
      "grad_norm": 0.5903578400611877,
      "learning_rate": 3.914816563641888e-07,
      "loss": 0.6078,
      "step": 59298
    },
    {
      "epoch": 1.821613983350229,
      "grad_norm": 0.4165707230567932,
      "learning_rate": 3.913477694501777e-07,
      "loss": 0.4409,
      "step": 59299
    },
    {
      "epoch": 1.821644702485178,
      "grad_norm": 0.4884391129016876,
      "learning_rate": 3.9121390497784516e-07,
      "loss": 0.4441,
      "step": 59300
    },
    {
      "epoch": 1.8216754216201272,
      "grad_norm": 0.43674659729003906,
      "learning_rate": 3.910800629475031e-07,
      "loss": 0.4741,
      "step": 59301
    },
    {
      "epoch": 1.8217061407550763,
      "grad_norm": 0.39777871966362,
      "learning_rate": 3.909462433594657e-07,
      "loss": 0.3907,
      "step": 59302
    },
    {
      "epoch": 1.8217368598900254,
      "grad_norm": 0.4461507201194763,
      "learning_rate": 3.908124462140439e-07,
      "loss": 0.4584,
      "step": 59303
    },
    {
      "epoch": 1.8217675790249745,
      "grad_norm": 0.4257265031337738,
      "learning_rate": 3.906786715115496e-07,
      "loss": 0.4164,
      "step": 59304
    },
    {
      "epoch": 1.8217982981599237,
      "grad_norm": 0.44718801975250244,
      "learning_rate": 3.90544919252297e-07,
      "loss": 0.3397,
      "step": 59305
    },
    {
      "epoch": 1.821829017294873,
      "grad_norm": 0.46179407835006714,
      "learning_rate": 3.9041118943659804e-07,
      "loss": 0.4226,
      "step": 59306
    },
    {
      "epoch": 1.8218597364298221,
      "grad_norm": 0.48548826575279236,
      "learning_rate": 3.902774820647659e-07,
      "loss": 0.4927,
      "step": 59307
    },
    {
      "epoch": 1.8218904555647712,
      "grad_norm": 0.4683905243873596,
      "learning_rate": 3.901437971371114e-07,
      "loss": 0.4636,
      "step": 59308
    },
    {
      "epoch": 1.8219211746997206,
      "grad_norm": 0.45755794644355774,
      "learning_rate": 3.9001013465394643e-07,
      "loss": 0.4428,
      "step": 59309
    },
    {
      "epoch": 1.8219518938346697,
      "grad_norm": 0.38669365644454956,
      "learning_rate": 3.898764946155842e-07,
      "loss": 0.4473,
      "step": 59310
    },
    {
      "epoch": 1.8219826129696188,
      "grad_norm": 0.4595213830471039,
      "learning_rate": 3.897428770223377e-07,
      "loss": 0.4753,
      "step": 59311
    },
    {
      "epoch": 1.822013332104568,
      "grad_norm": 0.4942651391029358,
      "learning_rate": 3.896092818745167e-07,
      "loss": 0.4849,
      "step": 59312
    },
    {
      "epoch": 1.822044051239517,
      "grad_norm": 0.43492618203163147,
      "learning_rate": 3.894757091724344e-07,
      "loss": 0.4945,
      "step": 59313
    },
    {
      "epoch": 1.8220747703744662,
      "grad_norm": 0.40629613399505615,
      "learning_rate": 3.893421589164026e-07,
      "loss": 0.5181,
      "step": 59314
    },
    {
      "epoch": 1.8221054895094153,
      "grad_norm": 0.5278742909431458,
      "learning_rate": 3.8920863110673445e-07,
      "loss": 0.4718,
      "step": 59315
    },
    {
      "epoch": 1.8221362086443644,
      "grad_norm": 0.4890013039112091,
      "learning_rate": 3.8907512574373975e-07,
      "loss": 0.4479,
      "step": 59316
    },
    {
      "epoch": 1.8221669277793138,
      "grad_norm": 0.5132002830505371,
      "learning_rate": 3.8894164282773263e-07,
      "loss": 0.4347,
      "step": 59317
    },
    {
      "epoch": 1.822197646914263,
      "grad_norm": 0.4369819760322571,
      "learning_rate": 3.888081823590206e-07,
      "loss": 0.4521,
      "step": 59318
    },
    {
      "epoch": 1.822228366049212,
      "grad_norm": 0.427421897649765,
      "learning_rate": 3.886747443379213e-07,
      "loss": 0.4783,
      "step": 59319
    },
    {
      "epoch": 1.8222590851841614,
      "grad_norm": 0.4461178779602051,
      "learning_rate": 3.8854132876474217e-07,
      "loss": 0.3666,
      "step": 59320
    },
    {
      "epoch": 1.8222898043191105,
      "grad_norm": 0.43568748235702515,
      "learning_rate": 3.884079356397974e-07,
      "loss": 0.4359,
      "step": 59321
    },
    {
      "epoch": 1.8223205234540596,
      "grad_norm": 0.6570848226547241,
      "learning_rate": 3.882745649633934e-07,
      "loss": 0.4719,
      "step": 59322
    },
    {
      "epoch": 1.8223512425890087,
      "grad_norm": 0.4785308837890625,
      "learning_rate": 3.881412167358478e-07,
      "loss": 0.4119,
      "step": 59323
    },
    {
      "epoch": 1.8223819617239578,
      "grad_norm": 0.409665048122406,
      "learning_rate": 3.880078909574714e-07,
      "loss": 0.4305,
      "step": 59324
    },
    {
      "epoch": 1.822412680858907,
      "grad_norm": 0.40984681248664856,
      "learning_rate": 3.8787458762857167e-07,
      "loss": 0.4999,
      "step": 59325
    },
    {
      "epoch": 1.822443399993856,
      "grad_norm": 0.39410558342933655,
      "learning_rate": 3.87741306749464e-07,
      "loss": 0.4092,
      "step": 59326
    },
    {
      "epoch": 1.8224741191288052,
      "grad_norm": 0.42926400899887085,
      "learning_rate": 3.876080483204547e-07,
      "loss": 0.4845,
      "step": 59327
    },
    {
      "epoch": 1.8225048382637545,
      "grad_norm": 0.4596695601940155,
      "learning_rate": 3.8747481234186144e-07,
      "loss": 0.4245,
      "step": 59328
    },
    {
      "epoch": 1.8225355573987037,
      "grad_norm": 0.38999056816101074,
      "learning_rate": 3.8734159881398945e-07,
      "loss": 0.4049,
      "step": 59329
    },
    {
      "epoch": 1.8225662765336528,
      "grad_norm": 0.4012499153614044,
      "learning_rate": 3.872084077371552e-07,
      "loss": 0.4218,
      "step": 59330
    },
    {
      "epoch": 1.8225969956686021,
      "grad_norm": 0.4537746012210846,
      "learning_rate": 3.87075239111665e-07,
      "loss": 0.4015,
      "step": 59331
    },
    {
      "epoch": 1.8226277148035512,
      "grad_norm": 0.4167197346687317,
      "learning_rate": 3.8694209293783203e-07,
      "loss": 0.4185,
      "step": 59332
    },
    {
      "epoch": 1.8226584339385004,
      "grad_norm": 0.6855325102806091,
      "learning_rate": 3.8680896921596823e-07,
      "loss": 0.483,
      "step": 59333
    },
    {
      "epoch": 1.8226891530734495,
      "grad_norm": 0.3710985779762268,
      "learning_rate": 3.8667586794638336e-07,
      "loss": 0.4035,
      "step": 59334
    },
    {
      "epoch": 1.8227198722083986,
      "grad_norm": 0.4441233277320862,
      "learning_rate": 3.8654278912938717e-07,
      "loss": 0.4253,
      "step": 59335
    },
    {
      "epoch": 1.8227505913433477,
      "grad_norm": 0.4711286723613739,
      "learning_rate": 3.864097327652927e-07,
      "loss": 0.5336,
      "step": 59336
    },
    {
      "epoch": 1.8227813104782968,
      "grad_norm": 0.3915126323699951,
      "learning_rate": 3.8627669885440867e-07,
      "loss": 0.5088,
      "step": 59337
    },
    {
      "epoch": 1.822812029613246,
      "grad_norm": 0.41052302718162537,
      "learning_rate": 3.861436873970492e-07,
      "loss": 0.4459,
      "step": 59338
    },
    {
      "epoch": 1.8228427487481953,
      "grad_norm": 0.4509737193584442,
      "learning_rate": 3.860106983935197e-07,
      "loss": 0.4904,
      "step": 59339
    },
    {
      "epoch": 1.8228734678831444,
      "grad_norm": 0.506476640701294,
      "learning_rate": 3.8587773184413534e-07,
      "loss": 0.4066,
      "step": 59340
    },
    {
      "epoch": 1.8229041870180935,
      "grad_norm": 0.4354874789714813,
      "learning_rate": 3.857447877492038e-07,
      "loss": 0.4355,
      "step": 59341
    },
    {
      "epoch": 1.8229349061530429,
      "grad_norm": 0.381267786026001,
      "learning_rate": 3.8561186610903687e-07,
      "loss": 0.4761,
      "step": 59342
    },
    {
      "epoch": 1.822965625287992,
      "grad_norm": 0.5082463622093201,
      "learning_rate": 3.854789669239467e-07,
      "loss": 0.4817,
      "step": 59343
    },
    {
      "epoch": 1.8229963444229411,
      "grad_norm": 0.4524824619293213,
      "learning_rate": 3.8534609019424075e-07,
      "loss": 0.5344,
      "step": 59344
    },
    {
      "epoch": 1.8230270635578902,
      "grad_norm": 0.47673195600509644,
      "learning_rate": 3.8521323592022986e-07,
      "loss": 0.5075,
      "step": 59345
    },
    {
      "epoch": 1.8230577826928394,
      "grad_norm": 0.6896284222602844,
      "learning_rate": 3.850804041022249e-07,
      "loss": 0.3751,
      "step": 59346
    },
    {
      "epoch": 1.8230885018277885,
      "grad_norm": 0.42398613691329956,
      "learning_rate": 3.849475947405379e-07,
      "loss": 0.4693,
      "step": 59347
    },
    {
      "epoch": 1.8231192209627376,
      "grad_norm": 0.4856976270675659,
      "learning_rate": 3.8481480783547633e-07,
      "loss": 0.4401,
      "step": 59348
    },
    {
      "epoch": 1.8231499400976867,
      "grad_norm": 0.4505634307861328,
      "learning_rate": 3.8468204338735105e-07,
      "loss": 0.5326,
      "step": 59349
    },
    {
      "epoch": 1.823180659232636,
      "grad_norm": 0.44590461254119873,
      "learning_rate": 3.8454930139647187e-07,
      "loss": 0.4831,
      "step": 59350
    },
    {
      "epoch": 1.8232113783675852,
      "grad_norm": 0.487481027841568,
      "learning_rate": 3.844165818631507e-07,
      "loss": 0.5042,
      "step": 59351
    },
    {
      "epoch": 1.8232420975025343,
      "grad_norm": 0.4152245819568634,
      "learning_rate": 3.8428388478769506e-07,
      "loss": 0.5082,
      "step": 59352
    },
    {
      "epoch": 1.8232728166374836,
      "grad_norm": 0.42554643750190735,
      "learning_rate": 3.84151210170417e-07,
      "loss": 0.5374,
      "step": 59353
    },
    {
      "epoch": 1.8233035357724328,
      "grad_norm": 0.5607590675354004,
      "learning_rate": 3.840185580116229e-07,
      "loss": 0.4765,
      "step": 59354
    },
    {
      "epoch": 1.8233342549073819,
      "grad_norm": 0.4578433334827423,
      "learning_rate": 3.8388592831162806e-07,
      "loss": 0.4913,
      "step": 59355
    },
    {
      "epoch": 1.823364974042331,
      "grad_norm": 0.5131756663322449,
      "learning_rate": 3.837533210707378e-07,
      "loss": 0.441,
      "step": 59356
    },
    {
      "epoch": 1.8233956931772801,
      "grad_norm": 0.4556658864021301,
      "learning_rate": 3.836207362892641e-07,
      "loss": 0.4828,
      "step": 59357
    },
    {
      "epoch": 1.8234264123122292,
      "grad_norm": 0.44271981716156006,
      "learning_rate": 3.834881739675145e-07,
      "loss": 0.4281,
      "step": 59358
    },
    {
      "epoch": 1.8234571314471784,
      "grad_norm": 0.4135819971561432,
      "learning_rate": 3.8335563410579977e-07,
      "loss": 0.4275,
      "step": 59359
    },
    {
      "epoch": 1.8234878505821275,
      "grad_norm": 0.4246967136859894,
      "learning_rate": 3.832231167044309e-07,
      "loss": 0.4144,
      "step": 59360
    },
    {
      "epoch": 1.8235185697170768,
      "grad_norm": 0.4998658001422882,
      "learning_rate": 3.8309062176371535e-07,
      "loss": 0.5483,
      "step": 59361
    },
    {
      "epoch": 1.823549288852026,
      "grad_norm": 0.42501387000083923,
      "learning_rate": 3.8295814928396403e-07,
      "loss": 0.5204,
      "step": 59362
    },
    {
      "epoch": 1.823580007986975,
      "grad_norm": 0.4825189709663391,
      "learning_rate": 3.828256992654833e-07,
      "loss": 0.5442,
      "step": 59363
    },
    {
      "epoch": 1.8236107271219244,
      "grad_norm": 0.4341256320476532,
      "learning_rate": 3.8269327170858737e-07,
      "loss": 0.5009,
      "step": 59364
    },
    {
      "epoch": 1.8236414462568735,
      "grad_norm": 0.4510103762149811,
      "learning_rate": 3.825608666135816e-07,
      "loss": 0.4733,
      "step": 59365
    },
    {
      "epoch": 1.8236721653918226,
      "grad_norm": 0.4689108431339264,
      "learning_rate": 3.8242848398077793e-07,
      "loss": 0.5291,
      "step": 59366
    },
    {
      "epoch": 1.8237028845267718,
      "grad_norm": 0.42877182364463806,
      "learning_rate": 3.822961238104828e-07,
      "loss": 0.4303,
      "step": 59367
    },
    {
      "epoch": 1.8237336036617209,
      "grad_norm": 0.41358572244644165,
      "learning_rate": 3.82163786103007e-07,
      "loss": 0.5178,
      "step": 59368
    },
    {
      "epoch": 1.82376432279667,
      "grad_norm": 0.42004939913749695,
      "learning_rate": 3.820314708586592e-07,
      "loss": 0.4766,
      "step": 59369
    },
    {
      "epoch": 1.8237950419316191,
      "grad_norm": 0.40729522705078125,
      "learning_rate": 3.8189917807775035e-07,
      "loss": 0.4574,
      "step": 59370
    },
    {
      "epoch": 1.8238257610665682,
      "grad_norm": 0.4434279203414917,
      "learning_rate": 3.817669077605857e-07,
      "loss": 0.4713,
      "step": 59371
    },
    {
      "epoch": 1.8238564802015174,
      "grad_norm": 0.4374878406524658,
      "learning_rate": 3.816346599074772e-07,
      "loss": 0.4453,
      "step": 59372
    },
    {
      "epoch": 1.8238871993364667,
      "grad_norm": 0.49757423996925354,
      "learning_rate": 3.8150243451873125e-07,
      "loss": 0.4491,
      "step": 59373
    },
    {
      "epoch": 1.8239179184714158,
      "grad_norm": 0.41907981038093567,
      "learning_rate": 3.8137023159465993e-07,
      "loss": 0.4534,
      "step": 59374
    },
    {
      "epoch": 1.8239486376063652,
      "grad_norm": 0.4655148684978485,
      "learning_rate": 3.8123805113556954e-07,
      "loss": 0.52,
      "step": 59375
    },
    {
      "epoch": 1.8239793567413143,
      "grad_norm": 0.4374557137489319,
      "learning_rate": 3.8110589314176884e-07,
      "loss": 0.5079,
      "step": 59376
    },
    {
      "epoch": 1.8240100758762634,
      "grad_norm": 0.40628165006637573,
      "learning_rate": 3.8097375761356745e-07,
      "loss": 0.4612,
      "step": 59377
    },
    {
      "epoch": 1.8240407950112125,
      "grad_norm": 0.4816311001777649,
      "learning_rate": 3.8084164455127413e-07,
      "loss": 0.4385,
      "step": 59378
    },
    {
      "epoch": 1.8240715141461616,
      "grad_norm": 0.4309003949165344,
      "learning_rate": 3.807095539551975e-07,
      "loss": 0.4527,
      "step": 59379
    },
    {
      "epoch": 1.8241022332811108,
      "grad_norm": 0.4377782642841339,
      "learning_rate": 3.805774858256439e-07,
      "loss": 0.3679,
      "step": 59380
    },
    {
      "epoch": 1.8241329524160599,
      "grad_norm": 0.4286602735519409,
      "learning_rate": 3.8044544016292427e-07,
      "loss": 0.4939,
      "step": 59381
    },
    {
      "epoch": 1.824163671551009,
      "grad_norm": 0.3874100148677826,
      "learning_rate": 3.8031341696734503e-07,
      "loss": 0.4906,
      "step": 59382
    },
    {
      "epoch": 1.8241943906859581,
      "grad_norm": 0.5668538808822632,
      "learning_rate": 3.801814162392181e-07,
      "loss": 0.5422,
      "step": 59383
    },
    {
      "epoch": 1.8242251098209075,
      "grad_norm": 0.44888389110565186,
      "learning_rate": 3.800494379788477e-07,
      "loss": 0.4542,
      "step": 59384
    },
    {
      "epoch": 1.8242558289558566,
      "grad_norm": 0.40763914585113525,
      "learning_rate": 3.7991748218654366e-07,
      "loss": 0.4675,
      "step": 59385
    },
    {
      "epoch": 1.824286548090806,
      "grad_norm": 0.4207194745540619,
      "learning_rate": 3.797855488626134e-07,
      "loss": 0.4059,
      "step": 59386
    },
    {
      "epoch": 1.824317267225755,
      "grad_norm": 0.4805355668067932,
      "learning_rate": 3.7965363800736787e-07,
      "loss": 0.4454,
      "step": 59387
    },
    {
      "epoch": 1.8243479863607042,
      "grad_norm": 0.4426170289516449,
      "learning_rate": 3.795217496211123e-07,
      "loss": 0.4876,
      "step": 59388
    },
    {
      "epoch": 1.8243787054956533,
      "grad_norm": 0.44632580876350403,
      "learning_rate": 3.7938988370415544e-07,
      "loss": 0.4072,
      "step": 59389
    },
    {
      "epoch": 1.8244094246306024,
      "grad_norm": 0.4422059655189514,
      "learning_rate": 3.7925804025680467e-07,
      "loss": 0.574,
      "step": 59390
    },
    {
      "epoch": 1.8244401437655515,
      "grad_norm": 0.45292675495147705,
      "learning_rate": 3.7912621927936987e-07,
      "loss": 0.5334,
      "step": 59391
    },
    {
      "epoch": 1.8244708629005006,
      "grad_norm": 0.43640846014022827,
      "learning_rate": 3.789944207721563e-07,
      "loss": 0.5266,
      "step": 59392
    },
    {
      "epoch": 1.8245015820354498,
      "grad_norm": 0.4428345263004303,
      "learning_rate": 3.7886264473547484e-07,
      "loss": 0.4337,
      "step": 59393
    },
    {
      "epoch": 1.8245323011703989,
      "grad_norm": 0.4572836458683014,
      "learning_rate": 3.787308911696308e-07,
      "loss": 0.508,
      "step": 59394
    },
    {
      "epoch": 1.8245630203053482,
      "grad_norm": 0.4229206144809723,
      "learning_rate": 3.785991600749317e-07,
      "loss": 0.45,
      "step": 59395
    },
    {
      "epoch": 1.8245937394402973,
      "grad_norm": 0.39190584421157837,
      "learning_rate": 3.784674514516873e-07,
      "loss": 0.4508,
      "step": 59396
    },
    {
      "epoch": 1.8246244585752465,
      "grad_norm": 0.4678156077861786,
      "learning_rate": 3.78335765300204e-07,
      "loss": 0.5125,
      "step": 59397
    },
    {
      "epoch": 1.8246551777101958,
      "grad_norm": 0.42988213896751404,
      "learning_rate": 3.782041016207905e-07,
      "loss": 0.3501,
      "step": 59398
    },
    {
      "epoch": 1.824685896845145,
      "grad_norm": 0.46522048115730286,
      "learning_rate": 3.78072460413752e-07,
      "loss": 0.4256,
      "step": 59399
    },
    {
      "epoch": 1.824716615980094,
      "grad_norm": 0.4448710083961487,
      "learning_rate": 3.779408416793973e-07,
      "loss": 0.4997,
      "step": 59400
    },
    {
      "epoch": 1.8247473351150432,
      "grad_norm": 0.44696375727653503,
      "learning_rate": 3.7780924541803377e-07,
      "loss": 0.468,
      "step": 59401
    },
    {
      "epoch": 1.8247780542499923,
      "grad_norm": 0.4242722988128662,
      "learning_rate": 3.7767767162997017e-07,
      "loss": 0.4695,
      "step": 59402
    },
    {
      "epoch": 1.8248087733849414,
      "grad_norm": 0.5478221774101257,
      "learning_rate": 3.775461203155106e-07,
      "loss": 0.4925,
      "step": 59403
    },
    {
      "epoch": 1.8248394925198905,
      "grad_norm": 0.46698957681655884,
      "learning_rate": 3.7741459147496496e-07,
      "loss": 0.4749,
      "step": 59404
    },
    {
      "epoch": 1.8248702116548396,
      "grad_norm": 0.46902918815612793,
      "learning_rate": 3.772830851086384e-07,
      "loss": 0.4949,
      "step": 59405
    },
    {
      "epoch": 1.824900930789789,
      "grad_norm": 0.44384637475013733,
      "learning_rate": 3.771516012168419e-07,
      "loss": 0.4991,
      "step": 59406
    },
    {
      "epoch": 1.824931649924738,
      "grad_norm": 0.44331687688827515,
      "learning_rate": 3.770201397998774e-07,
      "loss": 0.4676,
      "step": 59407
    },
    {
      "epoch": 1.8249623690596872,
      "grad_norm": 0.4830387830734253,
      "learning_rate": 3.768887008580546e-07,
      "loss": 0.4346,
      "step": 59408
    },
    {
      "epoch": 1.8249930881946366,
      "grad_norm": 0.5027874708175659,
      "learning_rate": 3.7675728439168115e-07,
      "loss": 0.5263,
      "step": 59409
    },
    {
      "epoch": 1.8250238073295857,
      "grad_norm": 0.44565173983573914,
      "learning_rate": 3.7662589040106335e-07,
      "loss": 0.4949,
      "step": 59410
    },
    {
      "epoch": 1.8250545264645348,
      "grad_norm": 0.41395631432533264,
      "learning_rate": 3.764945188865077e-07,
      "loss": 0.4471,
      "step": 59411
    },
    {
      "epoch": 1.825085245599484,
      "grad_norm": 0.4169909358024597,
      "learning_rate": 3.7636316984832057e-07,
      "loss": 0.499,
      "step": 59412
    },
    {
      "epoch": 1.825115964734433,
      "grad_norm": 0.48108571767807007,
      "learning_rate": 3.7623184328680953e-07,
      "loss": 0.4854,
      "step": 59413
    },
    {
      "epoch": 1.8251466838693822,
      "grad_norm": 0.4936734735965729,
      "learning_rate": 3.76100539202281e-07,
      "loss": 0.4256,
      "step": 59414
    },
    {
      "epoch": 1.8251774030043313,
      "grad_norm": 0.42146146297454834,
      "learning_rate": 3.7596925759504245e-07,
      "loss": 0.4469,
      "step": 59415
    },
    {
      "epoch": 1.8252081221392804,
      "grad_norm": 0.4367891848087311,
      "learning_rate": 3.7583799846539923e-07,
      "loss": 0.4139,
      "step": 59416
    },
    {
      "epoch": 1.8252388412742298,
      "grad_norm": 0.4245859682559967,
      "learning_rate": 3.7570676181365897e-07,
      "loss": 0.449,
      "step": 59417
    },
    {
      "epoch": 1.8252695604091789,
      "grad_norm": 0.4769305884838104,
      "learning_rate": 3.755755476401268e-07,
      "loss": 0.4505,
      "step": 59418
    },
    {
      "epoch": 1.825300279544128,
      "grad_norm": 0.4439423084259033,
      "learning_rate": 3.7544435594511153e-07,
      "loss": 0.4501,
      "step": 59419
    },
    {
      "epoch": 1.8253309986790773,
      "grad_norm": 0.4248341917991638,
      "learning_rate": 3.753131867289173e-07,
      "loss": 0.5211,
      "step": 59420
    },
    {
      "epoch": 1.8253617178140265,
      "grad_norm": 0.5019164085388184,
      "learning_rate": 3.7518203999185265e-07,
      "loss": 0.4787,
      "step": 59421
    },
    {
      "epoch": 1.8253924369489756,
      "grad_norm": 0.4468762278556824,
      "learning_rate": 3.750509157342197e-07,
      "loss": 0.4312,
      "step": 59422
    },
    {
      "epoch": 1.8254231560839247,
      "grad_norm": 0.42093369364738464,
      "learning_rate": 3.7491981395632924e-07,
      "loss": 0.4957,
      "step": 59423
    },
    {
      "epoch": 1.8254538752188738,
      "grad_norm": 0.40823817253112793,
      "learning_rate": 3.7478873465848553e-07,
      "loss": 0.47,
      "step": 59424
    },
    {
      "epoch": 1.825484594353823,
      "grad_norm": 0.5008123517036438,
      "learning_rate": 3.74657677840996e-07,
      "loss": 0.4106,
      "step": 59425
    },
    {
      "epoch": 1.825515313488772,
      "grad_norm": 0.4907504618167877,
      "learning_rate": 3.745266435041639e-07,
      "loss": 0.4324,
      "step": 59426
    },
    {
      "epoch": 1.8255460326237212,
      "grad_norm": 0.47814658284187317,
      "learning_rate": 3.7439563164829885e-07,
      "loss": 0.4642,
      "step": 59427
    },
    {
      "epoch": 1.8255767517586705,
      "grad_norm": 0.4435961842536926,
      "learning_rate": 3.7426464227370395e-07,
      "loss": 0.484,
      "step": 59428
    },
    {
      "epoch": 1.8256074708936196,
      "grad_norm": 0.47015857696533203,
      "learning_rate": 3.741336753806868e-07,
      "loss": 0.4179,
      "step": 59429
    },
    {
      "epoch": 1.8256381900285688,
      "grad_norm": 0.4418002963066101,
      "learning_rate": 3.7400273096955265e-07,
      "loss": 0.4455,
      "step": 59430
    },
    {
      "epoch": 1.825668909163518,
      "grad_norm": 0.4188843369483948,
      "learning_rate": 3.738718090406057e-07,
      "loss": 0.4642,
      "step": 59431
    },
    {
      "epoch": 1.8256996282984672,
      "grad_norm": 0.4033139944076538,
      "learning_rate": 3.737409095941547e-07,
      "loss": 0.4239,
      "step": 59432
    },
    {
      "epoch": 1.8257303474334163,
      "grad_norm": 0.41775164008140564,
      "learning_rate": 3.7361003263050367e-07,
      "loss": 0.5151,
      "step": 59433
    },
    {
      "epoch": 1.8257610665683655,
      "grad_norm": 0.4176536798477173,
      "learning_rate": 3.7347917814996026e-07,
      "loss": 0.4561,
      "step": 59434
    },
    {
      "epoch": 1.8257917857033146,
      "grad_norm": 0.41915246844291687,
      "learning_rate": 3.7334834615282753e-07,
      "loss": 0.436,
      "step": 59435
    },
    {
      "epoch": 1.8258225048382637,
      "grad_norm": 0.5097441673278809,
      "learning_rate": 3.7321753663941195e-07,
      "loss": 0.5226,
      "step": 59436
    },
    {
      "epoch": 1.8258532239732128,
      "grad_norm": 0.42499014735221863,
      "learning_rate": 3.730867496100188e-07,
      "loss": 0.4351,
      "step": 59437
    },
    {
      "epoch": 1.825883943108162,
      "grad_norm": 0.4279867708683014,
      "learning_rate": 3.7295598506495554e-07,
      "loss": 0.4829,
      "step": 59438
    },
    {
      "epoch": 1.8259146622431113,
      "grad_norm": 0.5689284205436707,
      "learning_rate": 3.7282524300452425e-07,
      "loss": 0.5365,
      "step": 59439
    },
    {
      "epoch": 1.8259453813780604,
      "grad_norm": 0.49528899788856506,
      "learning_rate": 3.726945234290313e-07,
      "loss": 0.5035,
      "step": 59440
    },
    {
      "epoch": 1.8259761005130095,
      "grad_norm": 0.49307429790496826,
      "learning_rate": 3.725638263387843e-07,
      "loss": 0.4609,
      "step": 59441
    },
    {
      "epoch": 1.8260068196479589,
      "grad_norm": 0.4297780692577362,
      "learning_rate": 3.7243315173408735e-07,
      "loss": 0.4932,
      "step": 59442
    },
    {
      "epoch": 1.826037538782908,
      "grad_norm": 0.39005574584007263,
      "learning_rate": 3.723024996152436e-07,
      "loss": 0.4575,
      "step": 59443
    },
    {
      "epoch": 1.826068257917857,
      "grad_norm": 0.5313595533370972,
      "learning_rate": 3.7217186998255936e-07,
      "loss": 0.5186,
      "step": 59444
    },
    {
      "epoch": 1.8260989770528062,
      "grad_norm": 0.4531885087490082,
      "learning_rate": 3.7204126283634123e-07,
      "loss": 0.4774,
      "step": 59445
    },
    {
      "epoch": 1.8261296961877553,
      "grad_norm": 0.4180131256580353,
      "learning_rate": 3.719106781768933e-07,
      "loss": 0.4192,
      "step": 59446
    },
    {
      "epoch": 1.8261604153227045,
      "grad_norm": 0.49534615874290466,
      "learning_rate": 3.717801160045198e-07,
      "loss": 0.4496,
      "step": 59447
    },
    {
      "epoch": 1.8261911344576536,
      "grad_norm": 0.42663028836250305,
      "learning_rate": 3.7164957631952605e-07,
      "loss": 0.5441,
      "step": 59448
    },
    {
      "epoch": 1.8262218535926027,
      "grad_norm": 0.42307278513908386,
      "learning_rate": 3.715190591222173e-07,
      "loss": 0.4403,
      "step": 59449
    },
    {
      "epoch": 1.826252572727552,
      "grad_norm": 0.4692970812320709,
      "learning_rate": 3.7138856441289894e-07,
      "loss": 0.4718,
      "step": 59450
    },
    {
      "epoch": 1.8262832918625012,
      "grad_norm": 0.45550453662872314,
      "learning_rate": 3.7125809219187516e-07,
      "loss": 0.5618,
      "step": 59451
    },
    {
      "epoch": 1.8263140109974503,
      "grad_norm": 0.43087390065193176,
      "learning_rate": 3.711276424594501e-07,
      "loss": 0.4906,
      "step": 59452
    },
    {
      "epoch": 1.8263447301323996,
      "grad_norm": 0.4347580671310425,
      "learning_rate": 3.70997215215928e-07,
      "loss": 0.4974,
      "step": 59453
    },
    {
      "epoch": 1.8263754492673487,
      "grad_norm": 0.41582155227661133,
      "learning_rate": 3.7086681046161533e-07,
      "loss": 0.5166,
      "step": 59454
    },
    {
      "epoch": 1.8264061684022979,
      "grad_norm": 0.4152173399925232,
      "learning_rate": 3.707364281968162e-07,
      "loss": 0.4365,
      "step": 59455
    },
    {
      "epoch": 1.826436887537247,
      "grad_norm": 0.4754610061645508,
      "learning_rate": 3.706060684218338e-07,
      "loss": 0.5115,
      "step": 59456
    },
    {
      "epoch": 1.826467606672196,
      "grad_norm": 0.4667670428752899,
      "learning_rate": 3.7047573113697443e-07,
      "loss": 0.4703,
      "step": 59457
    },
    {
      "epoch": 1.8264983258071452,
      "grad_norm": 0.42892637848854065,
      "learning_rate": 3.703454163425391e-07,
      "loss": 0.3966,
      "step": 59458
    },
    {
      "epoch": 1.8265290449420943,
      "grad_norm": 0.4586719870567322,
      "learning_rate": 3.702151240388374e-07,
      "loss": 0.4332,
      "step": 59459
    },
    {
      "epoch": 1.8265597640770435,
      "grad_norm": 0.4403845965862274,
      "learning_rate": 3.7008485422616925e-07,
      "loss": 0.456,
      "step": 59460
    },
    {
      "epoch": 1.8265904832119928,
      "grad_norm": 0.4180227220058441,
      "learning_rate": 3.699546069048421e-07,
      "loss": 0.4865,
      "step": 59461
    },
    {
      "epoch": 1.826621202346942,
      "grad_norm": 0.45483407378196716,
      "learning_rate": 3.698243820751568e-07,
      "loss": 0.4973,
      "step": 59462
    },
    {
      "epoch": 1.826651921481891,
      "grad_norm": 0.43039384484291077,
      "learning_rate": 3.6969417973741983e-07,
      "loss": 0.3663,
      "step": 59463
    },
    {
      "epoch": 1.8266826406168404,
      "grad_norm": 0.4723648726940155,
      "learning_rate": 3.6956399989193425e-07,
      "loss": 0.5177,
      "step": 59464
    },
    {
      "epoch": 1.8267133597517895,
      "grad_norm": 0.4846949577331543,
      "learning_rate": 3.694338425390054e-07,
      "loss": 0.4926,
      "step": 59465
    },
    {
      "epoch": 1.8267440788867386,
      "grad_norm": 0.4561319649219513,
      "learning_rate": 3.693037076789352e-07,
      "loss": 0.4961,
      "step": 59466
    },
    {
      "epoch": 1.8267747980216877,
      "grad_norm": 0.44837331771850586,
      "learning_rate": 3.69173595312029e-07,
      "loss": 0.4383,
      "step": 59467
    },
    {
      "epoch": 1.8268055171566369,
      "grad_norm": 0.47432228922843933,
      "learning_rate": 3.69043505438591e-07,
      "loss": 0.4393,
      "step": 59468
    },
    {
      "epoch": 1.826836236291586,
      "grad_norm": 0.4673806130886078,
      "learning_rate": 3.6891343805892434e-07,
      "loss": 0.5149,
      "step": 59469
    },
    {
      "epoch": 1.826866955426535,
      "grad_norm": 0.5089330673217773,
      "learning_rate": 3.687833931733342e-07,
      "loss": 0.4957,
      "step": 59470
    },
    {
      "epoch": 1.8268976745614842,
      "grad_norm": 0.43064290285110474,
      "learning_rate": 3.686533707821216e-07,
      "loss": 0.5034,
      "step": 59471
    },
    {
      "epoch": 1.8269283936964336,
      "grad_norm": 0.49564218521118164,
      "learning_rate": 3.6852337088559176e-07,
      "loss": 0.3565,
      "step": 59472
    },
    {
      "epoch": 1.8269591128313827,
      "grad_norm": 0.3949666917324066,
      "learning_rate": 3.683933934840478e-07,
      "loss": 0.4097,
      "step": 59473
    },
    {
      "epoch": 1.8269898319663318,
      "grad_norm": 0.4208744764328003,
      "learning_rate": 3.68263438577795e-07,
      "loss": 0.4607,
      "step": 59474
    },
    {
      "epoch": 1.8270205511012811,
      "grad_norm": 0.47035327553749084,
      "learning_rate": 3.681335061671354e-07,
      "loss": 0.4123,
      "step": 59475
    },
    {
      "epoch": 1.8270512702362303,
      "grad_norm": 0.4321150481700897,
      "learning_rate": 3.68003596252372e-07,
      "loss": 0.4727,
      "step": 59476
    },
    {
      "epoch": 1.8270819893711794,
      "grad_norm": 0.44113028049468994,
      "learning_rate": 3.6787370883380915e-07,
      "loss": 0.5296,
      "step": 59477
    },
    {
      "epoch": 1.8271127085061285,
      "grad_norm": 0.49296537041664124,
      "learning_rate": 3.6774384391175087e-07,
      "loss": 0.5183,
      "step": 59478
    },
    {
      "epoch": 1.8271434276410776,
      "grad_norm": 0.42165255546569824,
      "learning_rate": 3.676140014864982e-07,
      "loss": 0.4336,
      "step": 59479
    },
    {
      "epoch": 1.8271741467760267,
      "grad_norm": 0.42662134766578674,
      "learning_rate": 3.674841815583563e-07,
      "loss": 0.4226,
      "step": 59480
    },
    {
      "epoch": 1.8272048659109759,
      "grad_norm": 0.4570786654949188,
      "learning_rate": 3.6735438412762726e-07,
      "loss": 0.4922,
      "step": 59481
    },
    {
      "epoch": 1.827235585045925,
      "grad_norm": 0.4186228811740875,
      "learning_rate": 3.672246091946163e-07,
      "loss": 0.5078,
      "step": 59482
    },
    {
      "epoch": 1.827266304180874,
      "grad_norm": 0.4490261375904083,
      "learning_rate": 3.670948567596233e-07,
      "loss": 0.4287,
      "step": 59483
    },
    {
      "epoch": 1.8272970233158234,
      "grad_norm": 0.42402034997940063,
      "learning_rate": 3.669651268229546e-07,
      "loss": 0.4621,
      "step": 59484
    },
    {
      "epoch": 1.8273277424507726,
      "grad_norm": 0.40454304218292236,
      "learning_rate": 3.6683541938490996e-07,
      "loss": 0.4283,
      "step": 59485
    },
    {
      "epoch": 1.827358461585722,
      "grad_norm": 0.43923327326774597,
      "learning_rate": 3.6670573444579473e-07,
      "loss": 0.4351,
      "step": 59486
    },
    {
      "epoch": 1.827389180720671,
      "grad_norm": 0.4197936952114105,
      "learning_rate": 3.6657607200591084e-07,
      "loss": 0.5293,
      "step": 59487
    },
    {
      "epoch": 1.8274198998556201,
      "grad_norm": 0.41716521978378296,
      "learning_rate": 3.664464320655614e-07,
      "loss": 0.4668,
      "step": 59488
    },
    {
      "epoch": 1.8274506189905693,
      "grad_norm": 0.42089971899986267,
      "learning_rate": 3.6631681462504954e-07,
      "loss": 0.4579,
      "step": 59489
    },
    {
      "epoch": 1.8274813381255184,
      "grad_norm": 0.44900086522102356,
      "learning_rate": 3.6618721968467716e-07,
      "loss": 0.4902,
      "step": 59490
    },
    {
      "epoch": 1.8275120572604675,
      "grad_norm": 0.38808146119117737,
      "learning_rate": 3.6605764724474744e-07,
      "loss": 0.4892,
      "step": 59491
    },
    {
      "epoch": 1.8275427763954166,
      "grad_norm": 0.42753347754478455,
      "learning_rate": 3.6592809730556346e-07,
      "loss": 0.4622,
      "step": 59492
    },
    {
      "epoch": 1.8275734955303657,
      "grad_norm": 0.48593437671661377,
      "learning_rate": 3.657985698674271e-07,
      "loss": 0.4436,
      "step": 59493
    },
    {
      "epoch": 1.8276042146653149,
      "grad_norm": 0.4914889931678772,
      "learning_rate": 3.6566906493063935e-07,
      "loss": 0.415,
      "step": 59494
    },
    {
      "epoch": 1.8276349338002642,
      "grad_norm": 0.3993016481399536,
      "learning_rate": 3.655395824955066e-07,
      "loss": 0.4537,
      "step": 59495
    },
    {
      "epoch": 1.8276656529352133,
      "grad_norm": 0.45427724719047546,
      "learning_rate": 3.6541012256232745e-07,
      "loss": 0.5012,
      "step": 59496
    },
    {
      "epoch": 1.8276963720701627,
      "grad_norm": 0.43687182664871216,
      "learning_rate": 3.6528068513140726e-07,
      "loss": 0.4005,
      "step": 59497
    },
    {
      "epoch": 1.8277270912051118,
      "grad_norm": 0.4091891050338745,
      "learning_rate": 3.651512702030469e-07,
      "loss": 0.463,
      "step": 59498
    },
    {
      "epoch": 1.827757810340061,
      "grad_norm": 0.4956503212451935,
      "learning_rate": 3.650218777775472e-07,
      "loss": 0.396,
      "step": 59499
    },
    {
      "epoch": 1.82778852947501,
      "grad_norm": 0.41322585940361023,
      "learning_rate": 3.6489250785521234e-07,
      "loss": 0.4638,
      "step": 59500
    },
    {
      "epoch": 1.8278192486099591,
      "grad_norm": 0.40893757343292236,
      "learning_rate": 3.647631604363444e-07,
      "loss": 0.4769,
      "step": 59501
    },
    {
      "epoch": 1.8278499677449083,
      "grad_norm": 0.4487763047218323,
      "learning_rate": 3.646338355212442e-07,
      "loss": 0.4709,
      "step": 59502
    },
    {
      "epoch": 1.8278806868798574,
      "grad_norm": 0.4734278619289398,
      "learning_rate": 3.645045331102148e-07,
      "loss": 0.4901,
      "step": 59503
    },
    {
      "epoch": 1.8279114060148065,
      "grad_norm": 0.5230205655097961,
      "learning_rate": 3.6437525320355824e-07,
      "loss": 0.5587,
      "step": 59504
    },
    {
      "epoch": 1.8279421251497556,
      "grad_norm": 0.40697774291038513,
      "learning_rate": 3.642459958015765e-07,
      "loss": 0.4657,
      "step": 59505
    },
    {
      "epoch": 1.827972844284705,
      "grad_norm": 0.45363086462020874,
      "learning_rate": 3.641167609045715e-07,
      "loss": 0.5262,
      "step": 59506
    },
    {
      "epoch": 1.828003563419654,
      "grad_norm": 0.4491393566131592,
      "learning_rate": 3.639875485128441e-07,
      "loss": 0.4304,
      "step": 59507
    },
    {
      "epoch": 1.8280342825546032,
      "grad_norm": 2.1730008125305176,
      "learning_rate": 3.638583586266964e-07,
      "loss": 0.4828,
      "step": 59508
    },
    {
      "epoch": 1.8280650016895525,
      "grad_norm": 0.42608195543289185,
      "learning_rate": 3.637291912464302e-07,
      "loss": 0.4676,
      "step": 59509
    },
    {
      "epoch": 1.8280957208245017,
      "grad_norm": 0.44805896282196045,
      "learning_rate": 3.636000463723499e-07,
      "loss": 0.503,
      "step": 59510
    },
    {
      "epoch": 1.8281264399594508,
      "grad_norm": 0.3960995376110077,
      "learning_rate": 3.6347092400475183e-07,
      "loss": 0.4552,
      "step": 59511
    },
    {
      "epoch": 1.8281571590944,
      "grad_norm": 0.4304906129837036,
      "learning_rate": 3.6334182414394125e-07,
      "loss": 0.438,
      "step": 59512
    },
    {
      "epoch": 1.828187878229349,
      "grad_norm": 0.4095757007598877,
      "learning_rate": 3.632127467902191e-07,
      "loss": 0.4258,
      "step": 59513
    },
    {
      "epoch": 1.8282185973642981,
      "grad_norm": 0.5060935616493225,
      "learning_rate": 3.630836919438885e-07,
      "loss": 0.5379,
      "step": 59514
    },
    {
      "epoch": 1.8282493164992473,
      "grad_norm": 0.4515337347984314,
      "learning_rate": 3.629546596052469e-07,
      "loss": 0.3344,
      "step": 59515
    },
    {
      "epoch": 1.8282800356341964,
      "grad_norm": 0.4504386782646179,
      "learning_rate": 3.6282564977459746e-07,
      "loss": 0.5804,
      "step": 59516
    },
    {
      "epoch": 1.8283107547691457,
      "grad_norm": 0.46922361850738525,
      "learning_rate": 3.626966624522421e-07,
      "loss": 0.488,
      "step": 59517
    },
    {
      "epoch": 1.8283414739040948,
      "grad_norm": 0.423982173204422,
      "learning_rate": 3.6256769763848285e-07,
      "loss": 0.4808,
      "step": 59518
    },
    {
      "epoch": 1.828372193039044,
      "grad_norm": 0.43955907225608826,
      "learning_rate": 3.6243875533361837e-07,
      "loss": 0.5108,
      "step": 59519
    },
    {
      "epoch": 1.8284029121739933,
      "grad_norm": 0.4630254805088043,
      "learning_rate": 3.6230983553795285e-07,
      "loss": 0.4177,
      "step": 59520
    },
    {
      "epoch": 1.8284336313089424,
      "grad_norm": 0.45315277576446533,
      "learning_rate": 3.621809382517827e-07,
      "loss": 0.4705,
      "step": 59521
    },
    {
      "epoch": 1.8284643504438916,
      "grad_norm": 0.41864073276519775,
      "learning_rate": 3.6205206347541546e-07,
      "loss": 0.383,
      "step": 59522
    },
    {
      "epoch": 1.8284950695788407,
      "grad_norm": 0.4223995506763458,
      "learning_rate": 3.619232112091475e-07,
      "loss": 0.3864,
      "step": 59523
    },
    {
      "epoch": 1.8285257887137898,
      "grad_norm": 0.43289652466773987,
      "learning_rate": 3.617943814532798e-07,
      "loss": 0.498,
      "step": 59524
    },
    {
      "epoch": 1.828556507848739,
      "grad_norm": 0.602332353591919,
      "learning_rate": 3.6166557420811543e-07,
      "loss": 0.5311,
      "step": 59525
    },
    {
      "epoch": 1.828587226983688,
      "grad_norm": 0.439081072807312,
      "learning_rate": 3.615367894739541e-07,
      "loss": 0.5125,
      "step": 59526
    },
    {
      "epoch": 1.8286179461186371,
      "grad_norm": 0.43184694647789,
      "learning_rate": 3.6140802725109783e-07,
      "loss": 0.4613,
      "step": 59527
    },
    {
      "epoch": 1.8286486652535865,
      "grad_norm": 0.43542060256004333,
      "learning_rate": 3.612792875398452e-07,
      "loss": 0.4653,
      "step": 59528
    },
    {
      "epoch": 1.8286793843885356,
      "grad_norm": 0.4971312880516052,
      "learning_rate": 3.611505703404994e-07,
      "loss": 0.3707,
      "step": 59529
    },
    {
      "epoch": 1.8287101035234847,
      "grad_norm": 0.5007105469703674,
      "learning_rate": 3.6102187565335676e-07,
      "loss": 0.4395,
      "step": 59530
    },
    {
      "epoch": 1.828740822658434,
      "grad_norm": 0.4938479959964752,
      "learning_rate": 3.6089320347872383e-07,
      "loss": 0.5089,
      "step": 59531
    },
    {
      "epoch": 1.8287715417933832,
      "grad_norm": 0.46016567945480347,
      "learning_rate": 3.607645538168958e-07,
      "loss": 0.4153,
      "step": 59532
    },
    {
      "epoch": 1.8288022609283323,
      "grad_norm": 0.4240553081035614,
      "learning_rate": 3.6063592666817693e-07,
      "loss": 0.4764,
      "step": 59533
    },
    {
      "epoch": 1.8288329800632814,
      "grad_norm": 0.43964460492134094,
      "learning_rate": 3.6050732203286474e-07,
      "loss": 0.4547,
      "step": 59534
    },
    {
      "epoch": 1.8288636991982306,
      "grad_norm": 0.429980993270874,
      "learning_rate": 3.6037873991126127e-07,
      "loss": 0.4119,
      "step": 59535
    },
    {
      "epoch": 1.8288944183331797,
      "grad_norm": 0.5003701448440552,
      "learning_rate": 3.602501803036662e-07,
      "loss": 0.4182,
      "step": 59536
    },
    {
      "epoch": 1.8289251374681288,
      "grad_norm": 0.43645432591438293,
      "learning_rate": 3.6012164321038155e-07,
      "loss": 0.5016,
      "step": 59537
    },
    {
      "epoch": 1.828955856603078,
      "grad_norm": 0.40912216901779175,
      "learning_rate": 3.599931286317049e-07,
      "loss": 0.4973,
      "step": 59538
    },
    {
      "epoch": 1.8289865757380273,
      "grad_norm": 0.4649278223514557,
      "learning_rate": 3.59864636567937e-07,
      "loss": 0.5458,
      "step": 59539
    },
    {
      "epoch": 1.8290172948729764,
      "grad_norm": 0.4270612299442291,
      "learning_rate": 3.597361670193789e-07,
      "loss": 0.3959,
      "step": 59540
    },
    {
      "epoch": 1.8290480140079255,
      "grad_norm": 0.4275115430355072,
      "learning_rate": 3.596077199863302e-07,
      "loss": 0.4833,
      "step": 59541
    },
    {
      "epoch": 1.8290787331428748,
      "grad_norm": 0.42593878507614136,
      "learning_rate": 3.594792954690918e-07,
      "loss": 0.4648,
      "step": 59542
    },
    {
      "epoch": 1.829109452277824,
      "grad_norm": 0.4486024081707001,
      "learning_rate": 3.5935089346796237e-07,
      "loss": 0.4727,
      "step": 59543
    },
    {
      "epoch": 1.829140171412773,
      "grad_norm": 0.5001912117004395,
      "learning_rate": 3.592225139832417e-07,
      "loss": 0.4652,
      "step": 59544
    },
    {
      "epoch": 1.8291708905477222,
      "grad_norm": 0.5980603098869324,
      "learning_rate": 3.5909415701522956e-07,
      "loss": 0.4388,
      "step": 59545
    },
    {
      "epoch": 1.8292016096826713,
      "grad_norm": 0.4003317952156067,
      "learning_rate": 3.5896582256422895e-07,
      "loss": 0.4209,
      "step": 59546
    },
    {
      "epoch": 1.8292323288176204,
      "grad_norm": 0.4464043378829956,
      "learning_rate": 3.5883751063053415e-07,
      "loss": 0.4489,
      "step": 59547
    },
    {
      "epoch": 1.8292630479525696,
      "grad_norm": 0.511745274066925,
      "learning_rate": 3.587092212144494e-07,
      "loss": 0.466,
      "step": 59548
    },
    {
      "epoch": 1.8292937670875187,
      "grad_norm": 0.43456605076789856,
      "learning_rate": 3.5858095431627103e-07,
      "loss": 0.5477,
      "step": 59549
    },
    {
      "epoch": 1.829324486222468,
      "grad_norm": 0.4613052308559418,
      "learning_rate": 3.584527099363022e-07,
      "loss": 0.4786,
      "step": 59550
    },
    {
      "epoch": 1.8293552053574171,
      "grad_norm": 0.4480897784233093,
      "learning_rate": 3.583244880748393e-07,
      "loss": 0.4757,
      "step": 59551
    },
    {
      "epoch": 1.8293859244923663,
      "grad_norm": 0.4308602809906006,
      "learning_rate": 3.5819628873218327e-07,
      "loss": 0.4453,
      "step": 59552
    },
    {
      "epoch": 1.8294166436273156,
      "grad_norm": 0.4582008719444275,
      "learning_rate": 3.580681119086327e-07,
      "loss": 0.4806,
      "step": 59553
    },
    {
      "epoch": 1.8294473627622647,
      "grad_norm": 0.43853214383125305,
      "learning_rate": 3.579399576044884e-07,
      "loss": 0.3997,
      "step": 59554
    },
    {
      "epoch": 1.8294780818972138,
      "grad_norm": 0.45161929726600647,
      "learning_rate": 3.578118258200469e-07,
      "loss": 0.4969,
      "step": 59555
    },
    {
      "epoch": 1.829508801032163,
      "grad_norm": 0.45022809505462646,
      "learning_rate": 3.576837165556113e-07,
      "loss": 0.4295,
      "step": 59556
    },
    {
      "epoch": 1.829539520167112,
      "grad_norm": 0.44383206963539124,
      "learning_rate": 3.5755562981147684e-07,
      "loss": 0.5034,
      "step": 59557
    },
    {
      "epoch": 1.8295702393020612,
      "grad_norm": 0.4743322730064392,
      "learning_rate": 3.574275655879467e-07,
      "loss": 0.466,
      "step": 59558
    },
    {
      "epoch": 1.8296009584370103,
      "grad_norm": 0.44715240597724915,
      "learning_rate": 3.572995238853161e-07,
      "loss": 0.4707,
      "step": 59559
    },
    {
      "epoch": 1.8296316775719594,
      "grad_norm": 0.4654216170310974,
      "learning_rate": 3.5717150470388704e-07,
      "loss": 0.4497,
      "step": 59560
    },
    {
      "epoch": 1.8296623967069088,
      "grad_norm": 0.44643232226371765,
      "learning_rate": 3.5704350804395714e-07,
      "loss": 0.4122,
      "step": 59561
    },
    {
      "epoch": 1.829693115841858,
      "grad_norm": 0.4157514274120331,
      "learning_rate": 3.56915533905825e-07,
      "loss": 0.4719,
      "step": 59562
    },
    {
      "epoch": 1.829723834976807,
      "grad_norm": 0.4817114472389221,
      "learning_rate": 3.567875822897915e-07,
      "loss": 0.5406,
      "step": 59563
    },
    {
      "epoch": 1.8297545541117564,
      "grad_norm": 0.45610615611076355,
      "learning_rate": 3.566596531961519e-07,
      "loss": 0.4416,
      "step": 59564
    },
    {
      "epoch": 1.8297852732467055,
      "grad_norm": 0.3865451216697693,
      "learning_rate": 3.565317466252094e-07,
      "loss": 0.4505,
      "step": 59565
    },
    {
      "epoch": 1.8298159923816546,
      "grad_norm": 0.4178607761859894,
      "learning_rate": 3.564038625772581e-07,
      "loss": 0.5295,
      "step": 59566
    },
    {
      "epoch": 1.8298467115166037,
      "grad_norm": 0.43539705872535706,
      "learning_rate": 3.562760010526012e-07,
      "loss": 0.4551,
      "step": 59567
    },
    {
      "epoch": 1.8298774306515528,
      "grad_norm": 0.46222546696662903,
      "learning_rate": 3.56148162051535e-07,
      "loss": 0.5043,
      "step": 59568
    },
    {
      "epoch": 1.829908149786502,
      "grad_norm": 0.47616860270500183,
      "learning_rate": 3.560203455743583e-07,
      "loss": 0.5189,
      "step": 59569
    },
    {
      "epoch": 1.829938868921451,
      "grad_norm": 0.44556140899658203,
      "learning_rate": 3.558925516213685e-07,
      "loss": 0.4182,
      "step": 59570
    },
    {
      "epoch": 1.8299695880564002,
      "grad_norm": 0.42017799615859985,
      "learning_rate": 3.557647801928654e-07,
      "loss": 0.488,
      "step": 59571
    },
    {
      "epoch": 1.8300003071913495,
      "grad_norm": 0.41893526911735535,
      "learning_rate": 3.556370312891477e-07,
      "loss": 0.502,
      "step": 59572
    },
    {
      "epoch": 1.8300310263262987,
      "grad_norm": 0.3805295526981354,
      "learning_rate": 3.5550930491051404e-07,
      "loss": 0.4172,
      "step": 59573
    },
    {
      "epoch": 1.8300617454612478,
      "grad_norm": 0.6094850301742554,
      "learning_rate": 3.5538160105726084e-07,
      "loss": 0.4203,
      "step": 59574
    },
    {
      "epoch": 1.8300924645961971,
      "grad_norm": 0.6765619516372681,
      "learning_rate": 3.552539197296878e-07,
      "loss": 0.4227,
      "step": 59575
    },
    {
      "epoch": 1.8301231837311462,
      "grad_norm": 0.4163208305835724,
      "learning_rate": 3.551262609280914e-07,
      "loss": 0.4353,
      "step": 59576
    },
    {
      "epoch": 1.8301539028660954,
      "grad_norm": 0.46992388367652893,
      "learning_rate": 3.549986246527737e-07,
      "loss": 0.524,
      "step": 59577
    },
    {
      "epoch": 1.8301846220010445,
      "grad_norm": 0.4286322295665741,
      "learning_rate": 3.5487101090402875e-07,
      "loss": 0.5419,
      "step": 59578
    },
    {
      "epoch": 1.8302153411359936,
      "grad_norm": 0.4236467480659485,
      "learning_rate": 3.547434196821564e-07,
      "loss": 0.4576,
      "step": 59579
    },
    {
      "epoch": 1.8302460602709427,
      "grad_norm": 0.4622967839241028,
      "learning_rate": 3.546158509874542e-07,
      "loss": 0.5305,
      "step": 59580
    },
    {
      "epoch": 1.8302767794058918,
      "grad_norm": 0.43514156341552734,
      "learning_rate": 3.544883048202208e-07,
      "loss": 0.3686,
      "step": 59581
    },
    {
      "epoch": 1.830307498540841,
      "grad_norm": 0.39086785912513733,
      "learning_rate": 3.543607811807537e-07,
      "loss": 0.4406,
      "step": 59582
    },
    {
      "epoch": 1.8303382176757903,
      "grad_norm": 0.42876794934272766,
      "learning_rate": 3.542332800693504e-07,
      "loss": 0.437,
      "step": 59583
    },
    {
      "epoch": 1.8303689368107394,
      "grad_norm": 0.40923717617988586,
      "learning_rate": 3.5410580148630856e-07,
      "loss": 0.5158,
      "step": 59584
    },
    {
      "epoch": 1.8303996559456885,
      "grad_norm": 0.39523845911026,
      "learning_rate": 3.539783454319268e-07,
      "loss": 0.4054,
      "step": 59585
    },
    {
      "epoch": 1.8304303750806379,
      "grad_norm": 0.4260215163230896,
      "learning_rate": 3.538509119065026e-07,
      "loss": 0.4735,
      "step": 59586
    },
    {
      "epoch": 1.830461094215587,
      "grad_norm": 0.41102510690689087,
      "learning_rate": 3.5372350091033237e-07,
      "loss": 0.4241,
      "step": 59587
    },
    {
      "epoch": 1.8304918133505361,
      "grad_norm": 0.4329487979412079,
      "learning_rate": 3.5359611244371484e-07,
      "loss": 0.5131,
      "step": 59588
    },
    {
      "epoch": 1.8305225324854852,
      "grad_norm": 0.4628109633922577,
      "learning_rate": 3.5346874650694753e-07,
      "loss": 0.5088,
      "step": 59589
    },
    {
      "epoch": 1.8305532516204344,
      "grad_norm": 0.3963306248188019,
      "learning_rate": 3.5334140310032906e-07,
      "loss": 0.4115,
      "step": 59590
    },
    {
      "epoch": 1.8305839707553835,
      "grad_norm": 0.5397997498512268,
      "learning_rate": 3.5321408222415367e-07,
      "loss": 0.4782,
      "step": 59591
    },
    {
      "epoch": 1.8306146898903326,
      "grad_norm": 0.4586199223995209,
      "learning_rate": 3.530867838787211e-07,
      "loss": 0.5193,
      "step": 59592
    },
    {
      "epoch": 1.8306454090252817,
      "grad_norm": 0.42086347937583923,
      "learning_rate": 3.5295950806432667e-07,
      "loss": 0.5112,
      "step": 59593
    },
    {
      "epoch": 1.8306761281602308,
      "grad_norm": 0.4087431728839874,
      "learning_rate": 3.5283225478127126e-07,
      "loss": 0.4587,
      "step": 59594
    },
    {
      "epoch": 1.8307068472951802,
      "grad_norm": 0.4485319256782532,
      "learning_rate": 3.5270502402984795e-07,
      "loss": 0.4916,
      "step": 59595
    },
    {
      "epoch": 1.8307375664301293,
      "grad_norm": 0.4442133903503418,
      "learning_rate": 3.5257781581035654e-07,
      "loss": 0.4958,
      "step": 59596
    },
    {
      "epoch": 1.8307682855650786,
      "grad_norm": 0.3704054653644562,
      "learning_rate": 3.5245063012309455e-07,
      "loss": 0.4572,
      "step": 59597
    },
    {
      "epoch": 1.8307990047000278,
      "grad_norm": 0.4216069281101227,
      "learning_rate": 3.5232346696835506e-07,
      "loss": 0.465,
      "step": 59598
    },
    {
      "epoch": 1.8308297238349769,
      "grad_norm": 0.43765753507614136,
      "learning_rate": 3.521963263464412e-07,
      "loss": 0.4252,
      "step": 59599
    },
    {
      "epoch": 1.830860442969926,
      "grad_norm": 0.4233010709285736,
      "learning_rate": 3.520692082576449e-07,
      "loss": 0.4331,
      "step": 59600
    },
    {
      "epoch": 1.8308911621048751,
      "grad_norm": 0.3834579288959503,
      "learning_rate": 3.5194211270226596e-07,
      "loss": 0.4255,
      "step": 59601
    },
    {
      "epoch": 1.8309218812398242,
      "grad_norm": 0.42713814973831177,
      "learning_rate": 3.518150396805986e-07,
      "loss": 0.5362,
      "step": 59602
    },
    {
      "epoch": 1.8309526003747734,
      "grad_norm": 0.4150996804237366,
      "learning_rate": 3.5168798919294146e-07,
      "loss": 0.3878,
      "step": 59603
    },
    {
      "epoch": 1.8309833195097225,
      "grad_norm": 0.48746493458747864,
      "learning_rate": 3.5156096123959094e-07,
      "loss": 0.4829,
      "step": 59604
    },
    {
      "epoch": 1.8310140386446716,
      "grad_norm": 0.5399951934814453,
      "learning_rate": 3.514339558208435e-07,
      "loss": 0.5329,
      "step": 59605
    },
    {
      "epoch": 1.831044757779621,
      "grad_norm": 0.4052060842514038,
      "learning_rate": 3.5130697293699665e-07,
      "loss": 0.3803,
      "step": 59606
    },
    {
      "epoch": 1.83107547691457,
      "grad_norm": 0.407361775636673,
      "learning_rate": 3.511800125883447e-07,
      "loss": 0.4703,
      "step": 59607
    },
    {
      "epoch": 1.8311061960495194,
      "grad_norm": 0.4757300615310669,
      "learning_rate": 3.510530747751861e-07,
      "loss": 0.4445,
      "step": 59608
    },
    {
      "epoch": 1.8311369151844685,
      "grad_norm": 0.4431314468383789,
      "learning_rate": 3.509261594978186e-07,
      "loss": 0.5076,
      "step": 59609
    },
    {
      "epoch": 1.8311676343194176,
      "grad_norm": 0.46735087037086487,
      "learning_rate": 3.507992667565352e-07,
      "loss": 0.4931,
      "step": 59610
    },
    {
      "epoch": 1.8311983534543668,
      "grad_norm": 0.5342418551445007,
      "learning_rate": 3.5067239655163456e-07,
      "loss": 0.4898,
      "step": 59611
    },
    {
      "epoch": 1.8312290725893159,
      "grad_norm": 0.4625912308692932,
      "learning_rate": 3.50545548883412e-07,
      "loss": 0.4434,
      "step": 59612
    },
    {
      "epoch": 1.831259791724265,
      "grad_norm": 0.42151641845703125,
      "learning_rate": 3.504187237521661e-07,
      "loss": 0.454,
      "step": 59613
    },
    {
      "epoch": 1.8312905108592141,
      "grad_norm": 0.4487736225128174,
      "learning_rate": 3.50291921158189e-07,
      "loss": 0.4584,
      "step": 59614
    },
    {
      "epoch": 1.8313212299941632,
      "grad_norm": 0.46458694338798523,
      "learning_rate": 3.5016514110177924e-07,
      "loss": 0.4455,
      "step": 59615
    },
    {
      "epoch": 1.8313519491291124,
      "grad_norm": 0.4127705991268158,
      "learning_rate": 3.5003838358323326e-07,
      "loss": 0.3566,
      "step": 59616
    },
    {
      "epoch": 1.8313826682640617,
      "grad_norm": 0.4006275236606598,
      "learning_rate": 3.499116486028464e-07,
      "loss": 0.4421,
      "step": 59617
    },
    {
      "epoch": 1.8314133873990108,
      "grad_norm": 0.46356815099716187,
      "learning_rate": 3.4978493616091626e-07,
      "loss": 0.4589,
      "step": 59618
    },
    {
      "epoch": 1.8314441065339602,
      "grad_norm": 0.45290371775627136,
      "learning_rate": 3.4965824625773583e-07,
      "loss": 0.5421,
      "step": 59619
    },
    {
      "epoch": 1.8314748256689093,
      "grad_norm": 0.5011540055274963,
      "learning_rate": 3.495315788936027e-07,
      "loss": 0.3722,
      "step": 59620
    },
    {
      "epoch": 1.8315055448038584,
      "grad_norm": 0.44051554799079895,
      "learning_rate": 3.4940493406881216e-07,
      "loss": 0.464,
      "step": 59621
    },
    {
      "epoch": 1.8315362639388075,
      "grad_norm": 0.4519444704055786,
      "learning_rate": 3.492783117836618e-07,
      "loss": 0.4085,
      "step": 59622
    },
    {
      "epoch": 1.8315669830737566,
      "grad_norm": 0.4612535536289215,
      "learning_rate": 3.4915171203844464e-07,
      "loss": 0.488,
      "step": 59623
    },
    {
      "epoch": 1.8315977022087058,
      "grad_norm": 0.42095547914505005,
      "learning_rate": 3.4902513483345837e-07,
      "loss": 0.522,
      "step": 59624
    },
    {
      "epoch": 1.8316284213436549,
      "grad_norm": 1.5714091062545776,
      "learning_rate": 3.4889858016899704e-07,
      "loss": 0.5475,
      "step": 59625
    },
    {
      "epoch": 1.831659140478604,
      "grad_norm": 0.4093096852302551,
      "learning_rate": 3.4877204804535823e-07,
      "loss": 0.441,
      "step": 59626
    },
    {
      "epoch": 1.8316898596135531,
      "grad_norm": 0.4485674798488617,
      "learning_rate": 3.486455384628351e-07,
      "loss": 0.4575,
      "step": 59627
    },
    {
      "epoch": 1.8317205787485025,
      "grad_norm": 0.43529316782951355,
      "learning_rate": 3.4851905142172627e-07,
      "loss": 0.4713,
      "step": 59628
    },
    {
      "epoch": 1.8317512978834516,
      "grad_norm": 0.43964865803718567,
      "learning_rate": 3.483925869223226e-07,
      "loss": 0.4081,
      "step": 59629
    },
    {
      "epoch": 1.8317820170184007,
      "grad_norm": 0.43227800726890564,
      "learning_rate": 3.482661449649249e-07,
      "loss": 0.4086,
      "step": 59630
    },
    {
      "epoch": 1.83181273615335,
      "grad_norm": 0.4344177842140198,
      "learning_rate": 3.481397255498231e-07,
      "loss": 0.4204,
      "step": 59631
    },
    {
      "epoch": 1.8318434552882992,
      "grad_norm": 0.42091572284698486,
      "learning_rate": 3.4801332867731794e-07,
      "loss": 0.5052,
      "step": 59632
    },
    {
      "epoch": 1.8318741744232483,
      "grad_norm": 0.4517543315887451,
      "learning_rate": 3.4788695434769923e-07,
      "loss": 0.5053,
      "step": 59633
    },
    {
      "epoch": 1.8319048935581974,
      "grad_norm": 0.538881778717041,
      "learning_rate": 3.477606025612645e-07,
      "loss": 0.5677,
      "step": 59634
    },
    {
      "epoch": 1.8319356126931465,
      "grad_norm": 0.514857292175293,
      "learning_rate": 3.4763427331831026e-07,
      "loss": 0.421,
      "step": 59635
    },
    {
      "epoch": 1.8319663318280957,
      "grad_norm": 0.4157223701477051,
      "learning_rate": 3.475079666191306e-07,
      "loss": 0.4162,
      "step": 59636
    },
    {
      "epoch": 1.8319970509630448,
      "grad_norm": 0.5316663384437561,
      "learning_rate": 3.4738168246401973e-07,
      "loss": 0.5292,
      "step": 59637
    },
    {
      "epoch": 1.832027770097994,
      "grad_norm": 0.4491380453109741,
      "learning_rate": 3.47255420853273e-07,
      "loss": 0.4079,
      "step": 59638
    },
    {
      "epoch": 1.8320584892329432,
      "grad_norm": 0.44717150926589966,
      "learning_rate": 3.471291817871847e-07,
      "loss": 0.55,
      "step": 59639
    },
    {
      "epoch": 1.8320892083678924,
      "grad_norm": 0.42827874422073364,
      "learning_rate": 3.470029652660512e-07,
      "loss": 0.5814,
      "step": 59640
    },
    {
      "epoch": 1.8321199275028415,
      "grad_norm": 0.41320091485977173,
      "learning_rate": 3.4687677129016663e-07,
      "loss": 0.5168,
      "step": 59641
    },
    {
      "epoch": 1.8321506466377908,
      "grad_norm": 0.47359806299209595,
      "learning_rate": 3.4675059985982527e-07,
      "loss": 0.4717,
      "step": 59642
    },
    {
      "epoch": 1.83218136577274,
      "grad_norm": 0.4171919822692871,
      "learning_rate": 3.466244509753214e-07,
      "loss": 0.4664,
      "step": 59643
    },
    {
      "epoch": 1.832212084907689,
      "grad_norm": 0.4637986123561859,
      "learning_rate": 3.464983246369502e-07,
      "loss": 0.4327,
      "step": 59644
    },
    {
      "epoch": 1.8322428040426382,
      "grad_norm": 0.4341479241847992,
      "learning_rate": 3.463722208450082e-07,
      "loss": 0.4556,
      "step": 59645
    },
    {
      "epoch": 1.8322735231775873,
      "grad_norm": 0.4428454339504242,
      "learning_rate": 3.4624613959978624e-07,
      "loss": 0.4265,
      "step": 59646
    },
    {
      "epoch": 1.8323042423125364,
      "grad_norm": 0.4275968074798584,
      "learning_rate": 3.4612008090158076e-07,
      "loss": 0.4688,
      "step": 59647
    },
    {
      "epoch": 1.8323349614474855,
      "grad_norm": 0.431053102016449,
      "learning_rate": 3.4599404475068596e-07,
      "loss": 0.4322,
      "step": 59648
    },
    {
      "epoch": 1.8323656805824347,
      "grad_norm": 0.4325677454471588,
      "learning_rate": 3.458680311473983e-07,
      "loss": 0.4266,
      "step": 59649
    },
    {
      "epoch": 1.832396399717384,
      "grad_norm": 0.43518489599227905,
      "learning_rate": 3.4574204009200865e-07,
      "loss": 0.4982,
      "step": 59650
    },
    {
      "epoch": 1.8324271188523331,
      "grad_norm": 0.44854700565338135,
      "learning_rate": 3.4561607158481223e-07,
      "loss": 0.4107,
      "step": 59651
    },
    {
      "epoch": 1.8324578379872822,
      "grad_norm": 0.46365246176719666,
      "learning_rate": 3.454901256261034e-07,
      "loss": 0.4886,
      "step": 59652
    },
    {
      "epoch": 1.8324885571222316,
      "grad_norm": 0.45424404740333557,
      "learning_rate": 3.453642022161774e-07,
      "loss": 0.4916,
      "step": 59653
    },
    {
      "epoch": 1.8325192762571807,
      "grad_norm": 0.45834800601005554,
      "learning_rate": 3.4523830135532843e-07,
      "loss": 0.5024,
      "step": 59654
    },
    {
      "epoch": 1.8325499953921298,
      "grad_norm": 0.4795927107334137,
      "learning_rate": 3.451124230438485e-07,
      "loss": 0.5027,
      "step": 59655
    },
    {
      "epoch": 1.832580714527079,
      "grad_norm": 0.5671822428703308,
      "learning_rate": 3.4498656728203297e-07,
      "loss": 0.4391,
      "step": 59656
    },
    {
      "epoch": 1.832611433662028,
      "grad_norm": 0.41509076952934265,
      "learning_rate": 3.4486073407017593e-07,
      "loss": 0.4405,
      "step": 59657
    },
    {
      "epoch": 1.8326421527969772,
      "grad_norm": 0.4392380714416504,
      "learning_rate": 3.4473492340857175e-07,
      "loss": 0.4457,
      "step": 59658
    },
    {
      "epoch": 1.8326728719319263,
      "grad_norm": 0.4553820788860321,
      "learning_rate": 3.446091352975123e-07,
      "loss": 0.4473,
      "step": 59659
    },
    {
      "epoch": 1.8327035910668754,
      "grad_norm": 0.4640651345252991,
      "learning_rate": 3.444833697372929e-07,
      "loss": 0.3908,
      "step": 59660
    },
    {
      "epoch": 1.8327343102018248,
      "grad_norm": 0.418306827545166,
      "learning_rate": 3.443576267282056e-07,
      "loss": 0.4667,
      "step": 59661
    },
    {
      "epoch": 1.8327650293367739,
      "grad_norm": 0.45228075981140137,
      "learning_rate": 3.442319062705479e-07,
      "loss": 0.4849,
      "step": 59662
    },
    {
      "epoch": 1.832795748471723,
      "grad_norm": 0.4705837368965149,
      "learning_rate": 3.441062083646096e-07,
      "loss": 0.505,
      "step": 59663
    },
    {
      "epoch": 1.8328264676066723,
      "grad_norm": 0.47630223631858826,
      "learning_rate": 3.43980533010686e-07,
      "loss": 0.4621,
      "step": 59664
    },
    {
      "epoch": 1.8328571867416215,
      "grad_norm": 0.42880332469940186,
      "learning_rate": 3.438548802090702e-07,
      "loss": 0.5334,
      "step": 59665
    },
    {
      "epoch": 1.8328879058765706,
      "grad_norm": 0.43434953689575195,
      "learning_rate": 3.437292499600542e-07,
      "loss": 0.4469,
      "step": 59666
    },
    {
      "epoch": 1.8329186250115197,
      "grad_norm": 0.4220716655254364,
      "learning_rate": 3.4360364226393436e-07,
      "loss": 0.413,
      "step": 59667
    },
    {
      "epoch": 1.8329493441464688,
      "grad_norm": 0.4775353968143463,
      "learning_rate": 3.434780571210028e-07,
      "loss": 0.5324,
      "step": 59668
    },
    {
      "epoch": 1.832980063281418,
      "grad_norm": 0.4253283143043518,
      "learning_rate": 3.433524945315525e-07,
      "loss": 0.4961,
      "step": 59669
    },
    {
      "epoch": 1.833010782416367,
      "grad_norm": 0.4211706221103668,
      "learning_rate": 3.4322695449587553e-07,
      "loss": 0.5182,
      "step": 59670
    },
    {
      "epoch": 1.8330415015513162,
      "grad_norm": 0.4266622066497803,
      "learning_rate": 3.4310143701426824e-07,
      "loss": 0.4338,
      "step": 59671
    },
    {
      "epoch": 1.8330722206862655,
      "grad_norm": 0.47525662183761597,
      "learning_rate": 3.429759420870205e-07,
      "loss": 0.3988,
      "step": 59672
    },
    {
      "epoch": 1.8331029398212146,
      "grad_norm": 0.44527050852775574,
      "learning_rate": 3.428504697144286e-07,
      "loss": 0.4467,
      "step": 59673
    },
    {
      "epoch": 1.8331336589561638,
      "grad_norm": 0.5114457607269287,
      "learning_rate": 3.427250198967824e-07,
      "loss": 0.4367,
      "step": 59674
    },
    {
      "epoch": 1.833164378091113,
      "grad_norm": 0.407342791557312,
      "learning_rate": 3.4259959263437613e-07,
      "loss": 0.4766,
      "step": 59675
    },
    {
      "epoch": 1.8331950972260622,
      "grad_norm": 0.4694821536540985,
      "learning_rate": 3.4247418792750395e-07,
      "loss": 0.4753,
      "step": 59676
    },
    {
      "epoch": 1.8332258163610113,
      "grad_norm": 0.4407612681388855,
      "learning_rate": 3.423488057764579e-07,
      "loss": 0.4152,
      "step": 59677
    },
    {
      "epoch": 1.8332565354959605,
      "grad_norm": 0.4823460280895233,
      "learning_rate": 3.4222344618153103e-07,
      "loss": 0.5182,
      "step": 59678
    },
    {
      "epoch": 1.8332872546309096,
      "grad_norm": 0.4294573664665222,
      "learning_rate": 3.420981091430142e-07,
      "loss": 0.4233,
      "step": 59679
    },
    {
      "epoch": 1.8333179737658587,
      "grad_norm": 0.4822480082511902,
      "learning_rate": 3.419727946612028e-07,
      "loss": 0.4999,
      "step": 59680
    },
    {
      "epoch": 1.8333486929008078,
      "grad_norm": 0.42716529965400696,
      "learning_rate": 3.418475027363888e-07,
      "loss": 0.4882,
      "step": 59681
    },
    {
      "epoch": 1.833379412035757,
      "grad_norm": 0.4457058012485504,
      "learning_rate": 3.4172223336886413e-07,
      "loss": 0.4557,
      "step": 59682
    },
    {
      "epoch": 1.8334101311707063,
      "grad_norm": 0.43068742752075195,
      "learning_rate": 3.415969865589208e-07,
      "loss": 0.4626,
      "step": 59683
    },
    {
      "epoch": 1.8334408503056554,
      "grad_norm": 0.4254802465438843,
      "learning_rate": 3.414717623068531e-07,
      "loss": 0.5452,
      "step": 59684
    },
    {
      "epoch": 1.8334715694406045,
      "grad_norm": 0.41637077927589417,
      "learning_rate": 3.413465606129529e-07,
      "loss": 0.5489,
      "step": 59685
    },
    {
      "epoch": 1.8335022885755539,
      "grad_norm": 0.42512446641921997,
      "learning_rate": 3.412213814775112e-07,
      "loss": 0.3703,
      "step": 59686
    },
    {
      "epoch": 1.833533007710503,
      "grad_norm": 0.46737974882125854,
      "learning_rate": 3.4109622490082205e-07,
      "loss": 0.4523,
      "step": 59687
    },
    {
      "epoch": 1.833563726845452,
      "grad_norm": 0.4003169536590576,
      "learning_rate": 3.409710908831776e-07,
      "loss": 0.4866,
      "step": 59688
    },
    {
      "epoch": 1.8335944459804012,
      "grad_norm": 0.40390926599502563,
      "learning_rate": 3.408459794248697e-07,
      "loss": 0.4372,
      "step": 59689
    },
    {
      "epoch": 1.8336251651153503,
      "grad_norm": 0.42253032326698303,
      "learning_rate": 3.407208905261905e-07,
      "loss": 0.4452,
      "step": 59690
    },
    {
      "epoch": 1.8336558842502995,
      "grad_norm": 0.4122169315814972,
      "learning_rate": 3.40595824187433e-07,
      "loss": 0.386,
      "step": 59691
    },
    {
      "epoch": 1.8336866033852486,
      "grad_norm": 0.4100669026374817,
      "learning_rate": 3.4047078040888695e-07,
      "loss": 0.421,
      "step": 59692
    },
    {
      "epoch": 1.8337173225201977,
      "grad_norm": 0.40658140182495117,
      "learning_rate": 3.4034575919084655e-07,
      "loss": 0.4303,
      "step": 59693
    },
    {
      "epoch": 1.833748041655147,
      "grad_norm": 0.4206939935684204,
      "learning_rate": 3.40220760533605e-07,
      "loss": 0.464,
      "step": 59694
    },
    {
      "epoch": 1.8337787607900962,
      "grad_norm": 0.4271082282066345,
      "learning_rate": 3.4009578443745084e-07,
      "loss": 0.4061,
      "step": 59695
    },
    {
      "epoch": 1.8338094799250453,
      "grad_norm": 0.44159969687461853,
      "learning_rate": 3.3997083090267834e-07,
      "loss": 0.4732,
      "step": 59696
    },
    {
      "epoch": 1.8338401990599946,
      "grad_norm": 0.44654491543769836,
      "learning_rate": 3.398458999295773e-07,
      "loss": 0.5249,
      "step": 59697
    },
    {
      "epoch": 1.8338709181949437,
      "grad_norm": 0.44526487588882446,
      "learning_rate": 3.3972099151844184e-07,
      "loss": 0.5093,
      "step": 59698
    },
    {
      "epoch": 1.8339016373298929,
      "grad_norm": 0.44339099526405334,
      "learning_rate": 3.395961056695618e-07,
      "loss": 0.4461,
      "step": 59699
    },
    {
      "epoch": 1.833932356464842,
      "grad_norm": 0.4685768485069275,
      "learning_rate": 3.394712423832314e-07,
      "loss": 0.4969,
      "step": 59700
    },
    {
      "epoch": 1.833963075599791,
      "grad_norm": 0.5029102563858032,
      "learning_rate": 3.393464016597392e-07,
      "loss": 0.5046,
      "step": 59701
    },
    {
      "epoch": 1.8339937947347402,
      "grad_norm": 0.4352426528930664,
      "learning_rate": 3.392215834993784e-07,
      "loss": 0.4723,
      "step": 59702
    },
    {
      "epoch": 1.8340245138696893,
      "grad_norm": 0.4210643768310547,
      "learning_rate": 3.390967879024409e-07,
      "loss": 0.4379,
      "step": 59703
    },
    {
      "epoch": 1.8340552330046385,
      "grad_norm": 0.4151000678539276,
      "learning_rate": 3.389720148692177e-07,
      "loss": 0.4083,
      "step": 59704
    },
    {
      "epoch": 1.8340859521395876,
      "grad_norm": 0.44164177775382996,
      "learning_rate": 3.388472643999996e-07,
      "loss": 0.48,
      "step": 59705
    },
    {
      "epoch": 1.834116671274537,
      "grad_norm": 0.4785209894180298,
      "learning_rate": 3.3872253649507746e-07,
      "loss": 0.4802,
      "step": 59706
    },
    {
      "epoch": 1.834147390409486,
      "grad_norm": 0.42566388845443726,
      "learning_rate": 3.3859783115474444e-07,
      "loss": 0.4004,
      "step": 59707
    },
    {
      "epoch": 1.8341781095444354,
      "grad_norm": 0.5644979476928711,
      "learning_rate": 3.3847314837929026e-07,
      "loss": 0.4002,
      "step": 59708
    },
    {
      "epoch": 1.8342088286793845,
      "grad_norm": 0.40553605556488037,
      "learning_rate": 3.383484881690091e-07,
      "loss": 0.4318,
      "step": 59709
    },
    {
      "epoch": 1.8342395478143336,
      "grad_norm": 0.4101409614086151,
      "learning_rate": 3.382238505241875e-07,
      "loss": 0.5141,
      "step": 59710
    },
    {
      "epoch": 1.8342702669492827,
      "grad_norm": 0.49170544743537903,
      "learning_rate": 3.380992354451196e-07,
      "loss": 0.4522,
      "step": 59711
    },
    {
      "epoch": 1.8343009860842319,
      "grad_norm": 0.44416964054107666,
      "learning_rate": 3.379746429320951e-07,
      "loss": 0.4357,
      "step": 59712
    },
    {
      "epoch": 1.834331705219181,
      "grad_norm": 0.3886355459690094,
      "learning_rate": 3.378500729854073e-07,
      "loss": 0.3833,
      "step": 59713
    },
    {
      "epoch": 1.83436242435413,
      "grad_norm": 0.41567689180374146,
      "learning_rate": 3.3772552560534354e-07,
      "loss": 0.4663,
      "step": 59714
    },
    {
      "epoch": 1.8343931434890792,
      "grad_norm": 0.41153883934020996,
      "learning_rate": 3.3760100079219813e-07,
      "loss": 0.5162,
      "step": 59715
    },
    {
      "epoch": 1.8344238626240283,
      "grad_norm": 0.41160157322883606,
      "learning_rate": 3.374764985462586e-07,
      "loss": 0.429,
      "step": 59716
    },
    {
      "epoch": 1.8344545817589777,
      "grad_norm": 0.4280391037464142,
      "learning_rate": 3.373520188678203e-07,
      "loss": 0.4804,
      "step": 59717
    },
    {
      "epoch": 1.8344853008939268,
      "grad_norm": 0.45294123888015747,
      "learning_rate": 3.372275617571685e-07,
      "loss": 0.4094,
      "step": 59718
    },
    {
      "epoch": 1.8345160200288761,
      "grad_norm": 0.43981266021728516,
      "learning_rate": 3.3710312721459747e-07,
      "loss": 0.4632,
      "step": 59719
    },
    {
      "epoch": 1.8345467391638253,
      "grad_norm": 0.44939714670181274,
      "learning_rate": 3.3697871524039694e-07,
      "loss": 0.5198,
      "step": 59720
    },
    {
      "epoch": 1.8345774582987744,
      "grad_norm": 0.4129607379436493,
      "learning_rate": 3.368543258348589e-07,
      "loss": 0.4439,
      "step": 59721
    },
    {
      "epoch": 1.8346081774337235,
      "grad_norm": 0.42125290632247925,
      "learning_rate": 3.3672995899827087e-07,
      "loss": 0.4269,
      "step": 59722
    },
    {
      "epoch": 1.8346388965686726,
      "grad_norm": 0.4660279154777527,
      "learning_rate": 3.3660561473092603e-07,
      "loss": 0.4465,
      "step": 59723
    },
    {
      "epoch": 1.8346696157036217,
      "grad_norm": 0.4506412148475647,
      "learning_rate": 3.364812930331107e-07,
      "loss": 0.4431,
      "step": 59724
    },
    {
      "epoch": 1.8347003348385709,
      "grad_norm": 0.4679093658924103,
      "learning_rate": 3.363569939051203e-07,
      "loss": 0.4635,
      "step": 59725
    },
    {
      "epoch": 1.83473105397352,
      "grad_norm": 0.45122334361076355,
      "learning_rate": 3.362327173472435e-07,
      "loss": 0.4301,
      "step": 59726
    },
    {
      "epoch": 1.834761773108469,
      "grad_norm": 0.4386839270591736,
      "learning_rate": 3.3610846335977e-07,
      "loss": 0.4536,
      "step": 59727
    },
    {
      "epoch": 1.8347924922434184,
      "grad_norm": 0.4169771671295166,
      "learning_rate": 3.359842319429907e-07,
      "loss": 0.4714,
      "step": 59728
    },
    {
      "epoch": 1.8348232113783676,
      "grad_norm": 0.49856314063072205,
      "learning_rate": 3.35860023097192e-07,
      "loss": 0.4619,
      "step": 59729
    },
    {
      "epoch": 1.834853930513317,
      "grad_norm": 0.43483734130859375,
      "learning_rate": 3.357358368226704e-07,
      "loss": 0.4914,
      "step": 59730
    },
    {
      "epoch": 1.834884649648266,
      "grad_norm": 0.43462446331977844,
      "learning_rate": 3.356116731197112e-07,
      "loss": 0.4915,
      "step": 59731
    },
    {
      "epoch": 1.8349153687832152,
      "grad_norm": 0.47888249158859253,
      "learning_rate": 3.354875319886075e-07,
      "loss": 0.5009,
      "step": 59732
    },
    {
      "epoch": 1.8349460879181643,
      "grad_norm": 0.5086572170257568,
      "learning_rate": 3.3536341342964465e-07,
      "loss": 0.412,
      "step": 59733
    },
    {
      "epoch": 1.8349768070531134,
      "grad_norm": 0.517852783203125,
      "learning_rate": 3.35239317443119e-07,
      "loss": 0.4992,
      "step": 59734
    },
    {
      "epoch": 1.8350075261880625,
      "grad_norm": 0.4398384392261505,
      "learning_rate": 3.351152440293148e-07,
      "loss": 0.5741,
      "step": 59735
    },
    {
      "epoch": 1.8350382453230116,
      "grad_norm": 0.4069492816925049,
      "learning_rate": 3.3499119318852523e-07,
      "loss": 0.4539,
      "step": 59736
    },
    {
      "epoch": 1.8350689644579607,
      "grad_norm": 0.46054065227508545,
      "learning_rate": 3.3486716492103776e-07,
      "loss": 0.4378,
      "step": 59737
    },
    {
      "epoch": 1.8350996835929099,
      "grad_norm": 0.4307745695114136,
      "learning_rate": 3.3474315922714217e-07,
      "loss": 0.4802,
      "step": 59738
    },
    {
      "epoch": 1.8351304027278592,
      "grad_norm": 0.43852248787879944,
      "learning_rate": 3.3461917610712933e-07,
      "loss": 0.504,
      "step": 59739
    },
    {
      "epoch": 1.8351611218628083,
      "grad_norm": 0.4667859971523285,
      "learning_rate": 3.344952155612902e-07,
      "loss": 0.4967,
      "step": 59740
    },
    {
      "epoch": 1.8351918409977575,
      "grad_norm": 0.4351350665092468,
      "learning_rate": 3.3437127758991104e-07,
      "loss": 0.4982,
      "step": 59741
    },
    {
      "epoch": 1.8352225601327068,
      "grad_norm": 0.40238791704177856,
      "learning_rate": 3.342473621932829e-07,
      "loss": 0.4047,
      "step": 59742
    },
    {
      "epoch": 1.835253279267656,
      "grad_norm": 0.445027232170105,
      "learning_rate": 3.341234693716955e-07,
      "loss": 0.431,
      "step": 59743
    },
    {
      "epoch": 1.835283998402605,
      "grad_norm": 0.43921300768852234,
      "learning_rate": 3.3399959912543745e-07,
      "loss": 0.4699,
      "step": 59744
    },
    {
      "epoch": 1.8353147175375542,
      "grad_norm": 0.47048866748809814,
      "learning_rate": 3.338757514547986e-07,
      "loss": 0.4043,
      "step": 59745
    },
    {
      "epoch": 1.8353454366725033,
      "grad_norm": 0.4931800365447998,
      "learning_rate": 3.337519263600675e-07,
      "loss": 0.474,
      "step": 59746
    },
    {
      "epoch": 1.8353761558074524,
      "grad_norm": 0.4135189950466156,
      "learning_rate": 3.33628123841534e-07,
      "loss": 0.4873,
      "step": 59747
    },
    {
      "epoch": 1.8354068749424015,
      "grad_norm": 0.4549667537212372,
      "learning_rate": 3.3350434389948784e-07,
      "loss": 0.4953,
      "step": 59748
    },
    {
      "epoch": 1.8354375940773506,
      "grad_norm": 0.455810546875,
      "learning_rate": 3.333805865342177e-07,
      "loss": 0.4688,
      "step": 59749
    },
    {
      "epoch": 1.8354683132123,
      "grad_norm": 0.44953736662864685,
      "learning_rate": 3.3325685174601105e-07,
      "loss": 0.4613,
      "step": 59750
    },
    {
      "epoch": 1.835499032347249,
      "grad_norm": 0.44858407974243164,
      "learning_rate": 3.3313313953515893e-07,
      "loss": 0.4634,
      "step": 59751
    },
    {
      "epoch": 1.8355297514821982,
      "grad_norm": 0.42462047934532166,
      "learning_rate": 3.3300944990194874e-07,
      "loss": 0.5075,
      "step": 59752
    },
    {
      "epoch": 1.8355604706171476,
      "grad_norm": 0.4438950717449188,
      "learning_rate": 3.328857828466714e-07,
      "loss": 0.4894,
      "step": 59753
    },
    {
      "epoch": 1.8355911897520967,
      "grad_norm": 0.4231054186820984,
      "learning_rate": 3.3276213836961336e-07,
      "loss": 0.4782,
      "step": 59754
    },
    {
      "epoch": 1.8356219088870458,
      "grad_norm": 0.46587514877319336,
      "learning_rate": 3.3263851647106436e-07,
      "loss": 0.464,
      "step": 59755
    },
    {
      "epoch": 1.835652628021995,
      "grad_norm": 0.4305950701236725,
      "learning_rate": 3.325149171513131e-07,
      "loss": 0.4384,
      "step": 59756
    },
    {
      "epoch": 1.835683347156944,
      "grad_norm": 0.490254670381546,
      "learning_rate": 3.323913404106505e-07,
      "loss": 0.4196,
      "step": 59757
    },
    {
      "epoch": 1.8357140662918932,
      "grad_norm": 0.4012838900089264,
      "learning_rate": 3.3226778624936064e-07,
      "loss": 0.4304,
      "step": 59758
    },
    {
      "epoch": 1.8357447854268423,
      "grad_norm": 0.434097021818161,
      "learning_rate": 3.321442546677367e-07,
      "loss": 0.4938,
      "step": 59759
    },
    {
      "epoch": 1.8357755045617914,
      "grad_norm": 0.4095555543899536,
      "learning_rate": 3.320207456660629e-07,
      "loss": 0.3713,
      "step": 59760
    },
    {
      "epoch": 1.8358062236967407,
      "grad_norm": 0.44375938177108765,
      "learning_rate": 3.318972592446301e-07,
      "loss": 0.4256,
      "step": 59761
    },
    {
      "epoch": 1.8358369428316899,
      "grad_norm": 0.42923837900161743,
      "learning_rate": 3.317737954037281e-07,
      "loss": 0.4194,
      "step": 59762
    },
    {
      "epoch": 1.835867661966639,
      "grad_norm": 0.44175952672958374,
      "learning_rate": 3.316503541436422e-07,
      "loss": 0.4105,
      "step": 59763
    },
    {
      "epoch": 1.8358983811015883,
      "grad_norm": 0.44326940178871155,
      "learning_rate": 3.315269354646633e-07,
      "loss": 0.4591,
      "step": 59764
    },
    {
      "epoch": 1.8359291002365374,
      "grad_norm": 0.4212851822376251,
      "learning_rate": 3.314035393670767e-07,
      "loss": 0.5331,
      "step": 59765
    },
    {
      "epoch": 1.8359598193714866,
      "grad_norm": 0.4292130768299103,
      "learning_rate": 3.312801658511744e-07,
      "loss": 0.4904,
      "step": 59766
    },
    {
      "epoch": 1.8359905385064357,
      "grad_norm": 0.46067148447036743,
      "learning_rate": 3.311568149172417e-07,
      "loss": 0.4598,
      "step": 59767
    },
    {
      "epoch": 1.8360212576413848,
      "grad_norm": 0.46478262543678284,
      "learning_rate": 3.3103348656556846e-07,
      "loss": 0.5065,
      "step": 59768
    },
    {
      "epoch": 1.836051976776334,
      "grad_norm": 0.44781413674354553,
      "learning_rate": 3.309101807964399e-07,
      "loss": 0.4612,
      "step": 59769
    },
    {
      "epoch": 1.836082695911283,
      "grad_norm": 0.4305418133735657,
      "learning_rate": 3.3078689761014693e-07,
      "loss": 0.4167,
      "step": 59770
    },
    {
      "epoch": 1.8361134150462322,
      "grad_norm": 0.4645425081253052,
      "learning_rate": 3.30663637006976e-07,
      "loss": 0.4283,
      "step": 59771
    },
    {
      "epoch": 1.8361441341811815,
      "grad_norm": 0.4508163034915924,
      "learning_rate": 3.305403989872169e-07,
      "loss": 0.4459,
      "step": 59772
    },
    {
      "epoch": 1.8361748533161306,
      "grad_norm": 0.4468565285205841,
      "learning_rate": 3.304171835511538e-07,
      "loss": 0.4515,
      "step": 59773
    },
    {
      "epoch": 1.8362055724510797,
      "grad_norm": 0.4340461790561676,
      "learning_rate": 3.302939906990776e-07,
      "loss": 0.4683,
      "step": 59774
    },
    {
      "epoch": 1.836236291586029,
      "grad_norm": 0.4377136528491974,
      "learning_rate": 3.301708204312748e-07,
      "loss": 0.4946,
      "step": 59775
    },
    {
      "epoch": 1.8362670107209782,
      "grad_norm": 0.4001117944717407,
      "learning_rate": 3.3004767274803506e-07,
      "loss": 0.4584,
      "step": 59776
    },
    {
      "epoch": 1.8362977298559273,
      "grad_norm": 0.45118752121925354,
      "learning_rate": 3.299245476496427e-07,
      "loss": 0.4103,
      "step": 59777
    },
    {
      "epoch": 1.8363284489908764,
      "grad_norm": 0.5169574022293091,
      "learning_rate": 3.2980144513638734e-07,
      "loss": 0.4733,
      "step": 59778
    },
    {
      "epoch": 1.8363591681258256,
      "grad_norm": 0.43319153785705566,
      "learning_rate": 3.296783652085556e-07,
      "loss": 0.512,
      "step": 59779
    },
    {
      "epoch": 1.8363898872607747,
      "grad_norm": 0.4940361976623535,
      "learning_rate": 3.2955530786643484e-07,
      "loss": 0.4759,
      "step": 59780
    },
    {
      "epoch": 1.8364206063957238,
      "grad_norm": 0.40792614221572876,
      "learning_rate": 3.29432273110315e-07,
      "loss": 0.4218,
      "step": 59781
    },
    {
      "epoch": 1.836451325530673,
      "grad_norm": 0.43384528160095215,
      "learning_rate": 3.293092609404802e-07,
      "loss": 0.4949,
      "step": 59782
    },
    {
      "epoch": 1.8364820446656223,
      "grad_norm": 0.4235660135746002,
      "learning_rate": 3.291862713572191e-07,
      "loss": 0.4588,
      "step": 59783
    },
    {
      "epoch": 1.8365127638005714,
      "grad_norm": 0.46703240275382996,
      "learning_rate": 3.2906330436081934e-07,
      "loss": 0.4308,
      "step": 59784
    },
    {
      "epoch": 1.8365434829355205,
      "grad_norm": 0.4459797143936157,
      "learning_rate": 3.2894035995156837e-07,
      "loss": 0.523,
      "step": 59785
    },
    {
      "epoch": 1.8365742020704698,
      "grad_norm": 0.4412567913532257,
      "learning_rate": 3.2881743812975044e-07,
      "loss": 0.3657,
      "step": 59786
    },
    {
      "epoch": 1.836604921205419,
      "grad_norm": 0.4450490474700928,
      "learning_rate": 3.286945388956564e-07,
      "loss": 0.5211,
      "step": 59787
    },
    {
      "epoch": 1.836635640340368,
      "grad_norm": 0.43255481123924255,
      "learning_rate": 3.285716622495705e-07,
      "loss": 0.4289,
      "step": 59788
    },
    {
      "epoch": 1.8366663594753172,
      "grad_norm": 0.42989182472229004,
      "learning_rate": 3.2844880819178247e-07,
      "loss": 0.4838,
      "step": 59789
    },
    {
      "epoch": 1.8366970786102663,
      "grad_norm": 0.45920175313949585,
      "learning_rate": 3.283259767225766e-07,
      "loss": 0.4563,
      "step": 59790
    },
    {
      "epoch": 1.8367277977452154,
      "grad_norm": 0.36591655015945435,
      "learning_rate": 3.282031678422426e-07,
      "loss": 0.462,
      "step": 59791
    },
    {
      "epoch": 1.8367585168801646,
      "grad_norm": 0.4111207127571106,
      "learning_rate": 3.280803815510625e-07,
      "loss": 0.5029,
      "step": 59792
    },
    {
      "epoch": 1.8367892360151137,
      "grad_norm": 0.4214198887348175,
      "learning_rate": 3.279576178493293e-07,
      "loss": 0.5272,
      "step": 59793
    },
    {
      "epoch": 1.836819955150063,
      "grad_norm": 0.44456547498703003,
      "learning_rate": 3.2783487673732407e-07,
      "loss": 0.5557,
      "step": 59794
    },
    {
      "epoch": 1.8368506742850121,
      "grad_norm": 0.4179048240184784,
      "learning_rate": 3.2771215821533865e-07,
      "loss": 0.4656,
      "step": 59795
    },
    {
      "epoch": 1.8368813934199613,
      "grad_norm": 0.4505697786808014,
      "learning_rate": 3.2758946228365396e-07,
      "loss": 0.4257,
      "step": 59796
    },
    {
      "epoch": 1.8369121125549106,
      "grad_norm": 0.41245827078819275,
      "learning_rate": 3.274667889425598e-07,
      "loss": 0.4724,
      "step": 59797
    },
    {
      "epoch": 1.8369428316898597,
      "grad_norm": 0.4423135817050934,
      "learning_rate": 3.2734413819234476e-07,
      "loss": 0.4363,
      "step": 59798
    },
    {
      "epoch": 1.8369735508248088,
      "grad_norm": 0.41930362582206726,
      "learning_rate": 3.2722151003329206e-07,
      "loss": 0.5489,
      "step": 59799
    },
    {
      "epoch": 1.837004269959758,
      "grad_norm": 0.4061968922615051,
      "learning_rate": 3.2709890446568914e-07,
      "loss": 0.4294,
      "step": 59800
    },
    {
      "epoch": 1.837034989094707,
      "grad_norm": 0.4185168743133545,
      "learning_rate": 3.269763214898214e-07,
      "loss": 0.4543,
      "step": 59801
    },
    {
      "epoch": 1.8370657082296562,
      "grad_norm": 0.5108463764190674,
      "learning_rate": 3.2685376110597746e-07,
      "loss": 0.5014,
      "step": 59802
    },
    {
      "epoch": 1.8370964273646053,
      "grad_norm": 0.4084300398826599,
      "learning_rate": 3.267312233144404e-07,
      "loss": 0.4223,
      "step": 59803
    },
    {
      "epoch": 1.8371271464995544,
      "grad_norm": 0.4103168845176697,
      "learning_rate": 3.2660870811550005e-07,
      "loss": 0.4108,
      "step": 59804
    },
    {
      "epoch": 1.8371578656345038,
      "grad_norm": 0.40944623947143555,
      "learning_rate": 3.264862155094395e-07,
      "loss": 0.4507,
      "step": 59805
    },
    {
      "epoch": 1.837188584769453,
      "grad_norm": 0.49388206005096436,
      "learning_rate": 3.263637454965463e-07,
      "loss": 0.4696,
      "step": 59806
    },
    {
      "epoch": 1.837219303904402,
      "grad_norm": 0.47169312834739685,
      "learning_rate": 3.262412980771057e-07,
      "loss": 0.4273,
      "step": 59807
    },
    {
      "epoch": 1.8372500230393514,
      "grad_norm": 0.49734923243522644,
      "learning_rate": 3.2611887325140536e-07,
      "loss": 0.5134,
      "step": 59808
    },
    {
      "epoch": 1.8372807421743005,
      "grad_norm": 0.4238155782222748,
      "learning_rate": 3.259964710197283e-07,
      "loss": 0.5002,
      "step": 59809
    },
    {
      "epoch": 1.8373114613092496,
      "grad_norm": 0.47139772772789,
      "learning_rate": 3.258740913823633e-07,
      "loss": 0.4425,
      "step": 59810
    },
    {
      "epoch": 1.8373421804441987,
      "grad_norm": 0.4173399806022644,
      "learning_rate": 3.257517343395944e-07,
      "loss": 0.5026,
      "step": 59811
    },
    {
      "epoch": 1.8373728995791478,
      "grad_norm": 0.47899723052978516,
      "learning_rate": 3.2562939989170925e-07,
      "loss": 0.5179,
      "step": 59812
    },
    {
      "epoch": 1.837403618714097,
      "grad_norm": 0.4510895013809204,
      "learning_rate": 3.255070880389899e-07,
      "loss": 0.4608,
      "step": 59813
    },
    {
      "epoch": 1.837434337849046,
      "grad_norm": 0.42545658349990845,
      "learning_rate": 3.25384798781726e-07,
      "loss": 0.4562,
      "step": 59814
    },
    {
      "epoch": 1.8374650569839952,
      "grad_norm": 0.44708672165870667,
      "learning_rate": 3.2526253212020077e-07,
      "loss": 0.4052,
      "step": 59815
    },
    {
      "epoch": 1.8374957761189445,
      "grad_norm": 0.47219598293304443,
      "learning_rate": 3.2514028805470165e-07,
      "loss": 0.5036,
      "step": 59816
    },
    {
      "epoch": 1.8375264952538937,
      "grad_norm": 0.5040902495384216,
      "learning_rate": 3.2501806658551296e-07,
      "loss": 0.5365,
      "step": 59817
    },
    {
      "epoch": 1.8375572143888428,
      "grad_norm": 0.5449585318565369,
      "learning_rate": 3.2489586771291994e-07,
      "loss": 0.4503,
      "step": 59818
    },
    {
      "epoch": 1.8375879335237921,
      "grad_norm": 0.44818729162216187,
      "learning_rate": 3.247736914372079e-07,
      "loss": 0.5079,
      "step": 59819
    },
    {
      "epoch": 1.8376186526587412,
      "grad_norm": 0.42074352502822876,
      "learning_rate": 3.246515377586623e-07,
      "loss": 0.5283,
      "step": 59820
    },
    {
      "epoch": 1.8376493717936904,
      "grad_norm": 0.4322916865348816,
      "learning_rate": 3.245294066775706e-07,
      "loss": 0.4734,
      "step": 59821
    },
    {
      "epoch": 1.8376800909286395,
      "grad_norm": 0.46117934584617615,
      "learning_rate": 3.244072981942148e-07,
      "loss": 0.47,
      "step": 59822
    },
    {
      "epoch": 1.8377108100635886,
      "grad_norm": 0.5337719321250916,
      "learning_rate": 3.242852123088813e-07,
      "loss": 0.5183,
      "step": 59823
    },
    {
      "epoch": 1.8377415291985377,
      "grad_norm": 0.4038451313972473,
      "learning_rate": 3.241631490218555e-07,
      "loss": 0.4697,
      "step": 59824
    },
    {
      "epoch": 1.8377722483334868,
      "grad_norm": 0.4193355143070221,
      "learning_rate": 3.2404110833342274e-07,
      "loss": 0.4465,
      "step": 59825
    },
    {
      "epoch": 1.837802967468436,
      "grad_norm": 0.43039506673812866,
      "learning_rate": 3.2391909024386824e-07,
      "loss": 0.4505,
      "step": 59826
    },
    {
      "epoch": 1.837833686603385,
      "grad_norm": 0.432334303855896,
      "learning_rate": 3.237970947534763e-07,
      "loss": 0.445,
      "step": 59827
    },
    {
      "epoch": 1.8378644057383344,
      "grad_norm": 0.4729967415332794,
      "learning_rate": 3.2367512186253003e-07,
      "loss": 0.4758,
      "step": 59828
    },
    {
      "epoch": 1.8378951248732835,
      "grad_norm": 0.39855608344078064,
      "learning_rate": 3.2355317157131914e-07,
      "loss": 0.4064,
      "step": 59829
    },
    {
      "epoch": 1.837925844008233,
      "grad_norm": 0.5059576630592346,
      "learning_rate": 3.234312438801246e-07,
      "loss": 0.4702,
      "step": 59830
    },
    {
      "epoch": 1.837956563143182,
      "grad_norm": 0.46552184224128723,
      "learning_rate": 3.233093387892328e-07,
      "loss": 0.4164,
      "step": 59831
    },
    {
      "epoch": 1.8379872822781311,
      "grad_norm": 0.42246782779693604,
      "learning_rate": 3.231874562989268e-07,
      "loss": 0.5387,
      "step": 59832
    },
    {
      "epoch": 1.8380180014130802,
      "grad_norm": 0.4420053958892822,
      "learning_rate": 3.230655964094909e-07,
      "loss": 0.4738,
      "step": 59833
    },
    {
      "epoch": 1.8380487205480294,
      "grad_norm": 0.4394647479057312,
      "learning_rate": 3.229437591212137e-07,
      "loss": 0.4359,
      "step": 59834
    },
    {
      "epoch": 1.8380794396829785,
      "grad_norm": 0.45037397742271423,
      "learning_rate": 3.228219444343761e-07,
      "loss": 0.435,
      "step": 59835
    },
    {
      "epoch": 1.8381101588179276,
      "grad_norm": 0.46940430998802185,
      "learning_rate": 3.227001523492645e-07,
      "loss": 0.503,
      "step": 59836
    },
    {
      "epoch": 1.8381408779528767,
      "grad_norm": 0.4292261600494385,
      "learning_rate": 3.2257838286616104e-07,
      "loss": 0.451,
      "step": 59837
    },
    {
      "epoch": 1.8381715970878258,
      "grad_norm": 0.38731589913368225,
      "learning_rate": 3.224566359853532e-07,
      "loss": 0.4202,
      "step": 59838
    },
    {
      "epoch": 1.8382023162227752,
      "grad_norm": 0.49190419912338257,
      "learning_rate": 3.2233491170712283e-07,
      "loss": 0.4055,
      "step": 59839
    },
    {
      "epoch": 1.8382330353577243,
      "grad_norm": 0.4489658772945404,
      "learning_rate": 3.2221321003175656e-07,
      "loss": 0.4984,
      "step": 59840
    },
    {
      "epoch": 1.8382637544926737,
      "grad_norm": 0.4059407711029053,
      "learning_rate": 3.2209153095953516e-07,
      "loss": 0.4852,
      "step": 59841
    },
    {
      "epoch": 1.8382944736276228,
      "grad_norm": 0.44363245368003845,
      "learning_rate": 3.2196987449074626e-07,
      "loss": 0.5117,
      "step": 59842
    },
    {
      "epoch": 1.838325192762572,
      "grad_norm": 0.44521576166152954,
      "learning_rate": 3.2184824062567175e-07,
      "loss": 0.4642,
      "step": 59843
    },
    {
      "epoch": 1.838355911897521,
      "grad_norm": 0.4367782473564148,
      "learning_rate": 3.217266293645971e-07,
      "loss": 0.4687,
      "step": 59844
    },
    {
      "epoch": 1.8383866310324701,
      "grad_norm": 0.46224114298820496,
      "learning_rate": 3.216050407078053e-07,
      "loss": 0.4988,
      "step": 59845
    },
    {
      "epoch": 1.8384173501674193,
      "grad_norm": 0.45080500841140747,
      "learning_rate": 3.2148347465558174e-07,
      "loss": 0.4714,
      "step": 59846
    },
    {
      "epoch": 1.8384480693023684,
      "grad_norm": 0.44497478008270264,
      "learning_rate": 3.2136193120820835e-07,
      "loss": 0.4263,
      "step": 59847
    },
    {
      "epoch": 1.8384787884373175,
      "grad_norm": 0.4390357732772827,
      "learning_rate": 3.2124041036597164e-07,
      "loss": 0.3983,
      "step": 59848
    },
    {
      "epoch": 1.8385095075722666,
      "grad_norm": 0.44541823863983154,
      "learning_rate": 3.211189121291525e-07,
      "loss": 0.536,
      "step": 59849
    },
    {
      "epoch": 1.838540226707216,
      "grad_norm": 0.43766096234321594,
      "learning_rate": 3.2099743649803726e-07,
      "loss": 0.5366,
      "step": 59850
    },
    {
      "epoch": 1.838570945842165,
      "grad_norm": 0.4846530854701996,
      "learning_rate": 3.2087598347290695e-07,
      "loss": 0.4834,
      "step": 59851
    },
    {
      "epoch": 1.8386016649771142,
      "grad_norm": 0.4830702245235443,
      "learning_rate": 3.207545530540479e-07,
      "loss": 0.5541,
      "step": 59852
    },
    {
      "epoch": 1.8386323841120635,
      "grad_norm": 0.4933509826660156,
      "learning_rate": 3.2063314524174326e-07,
      "loss": 0.4395,
      "step": 59853
    },
    {
      "epoch": 1.8386631032470127,
      "grad_norm": 0.428379088640213,
      "learning_rate": 3.2051176003627507e-07,
      "loss": 0.4929,
      "step": 59854
    },
    {
      "epoch": 1.8386938223819618,
      "grad_norm": 0.4409852623939514,
      "learning_rate": 3.2039039743792634e-07,
      "loss": 0.4763,
      "step": 59855
    },
    {
      "epoch": 1.838724541516911,
      "grad_norm": 0.44073614478111267,
      "learning_rate": 3.2026905744698354e-07,
      "loss": 0.44,
      "step": 59856
    },
    {
      "epoch": 1.83875526065186,
      "grad_norm": 0.42411547899246216,
      "learning_rate": 3.201477400637287e-07,
      "loss": 0.5618,
      "step": 59857
    },
    {
      "epoch": 1.8387859797868091,
      "grad_norm": 0.4408535361289978,
      "learning_rate": 3.2002644528844384e-07,
      "loss": 0.4732,
      "step": 59858
    },
    {
      "epoch": 1.8388166989217583,
      "grad_norm": 0.5409525632858276,
      "learning_rate": 3.199051731214131e-07,
      "loss": 0.4993,
      "step": 59859
    },
    {
      "epoch": 1.8388474180567074,
      "grad_norm": 0.44099175930023193,
      "learning_rate": 3.1978392356292074e-07,
      "loss": 0.3852,
      "step": 59860
    },
    {
      "epoch": 1.8388781371916567,
      "grad_norm": 0.43951907753944397,
      "learning_rate": 3.1966269661324876e-07,
      "loss": 0.4427,
      "step": 59861
    },
    {
      "epoch": 1.8389088563266058,
      "grad_norm": 0.4600472152233124,
      "learning_rate": 3.1954149227268026e-07,
      "loss": 0.4399,
      "step": 59862
    },
    {
      "epoch": 1.838939575461555,
      "grad_norm": 0.45034241676330566,
      "learning_rate": 3.194203105415006e-07,
      "loss": 0.5685,
      "step": 59863
    },
    {
      "epoch": 1.8389702945965043,
      "grad_norm": 0.4156394600868225,
      "learning_rate": 3.1929915141998726e-07,
      "loss": 0.4954,
      "step": 59864
    },
    {
      "epoch": 1.8390010137314534,
      "grad_norm": 0.4597228765487671,
      "learning_rate": 3.1917801490843005e-07,
      "loss": 0.5115,
      "step": 59865
    },
    {
      "epoch": 1.8390317328664025,
      "grad_norm": 0.43059051036834717,
      "learning_rate": 3.1905690100710653e-07,
      "loss": 0.5328,
      "step": 59866
    },
    {
      "epoch": 1.8390624520013517,
      "grad_norm": 0.5410420298576355,
      "learning_rate": 3.189358097163042e-07,
      "loss": 0.459,
      "step": 59867
    },
    {
      "epoch": 1.8390931711363008,
      "grad_norm": 0.405367910861969,
      "learning_rate": 3.1881474103630185e-07,
      "loss": 0.4917,
      "step": 59868
    },
    {
      "epoch": 1.83912389027125,
      "grad_norm": 0.42543095350265503,
      "learning_rate": 3.1869369496738247e-07,
      "loss": 0.4793,
      "step": 59869
    },
    {
      "epoch": 1.839154609406199,
      "grad_norm": 0.47548946738243103,
      "learning_rate": 3.185726715098314e-07,
      "loss": 0.4263,
      "step": 59870
    },
    {
      "epoch": 1.8391853285411481,
      "grad_norm": 0.44425445795059204,
      "learning_rate": 3.184516706639296e-07,
      "loss": 0.4385,
      "step": 59871
    },
    {
      "epoch": 1.8392160476760975,
      "grad_norm": 0.4399530291557312,
      "learning_rate": 3.183306924299623e-07,
      "loss": 0.6089,
      "step": 59872
    },
    {
      "epoch": 1.8392467668110466,
      "grad_norm": 0.4206404983997345,
      "learning_rate": 3.182097368082071e-07,
      "loss": 0.4192,
      "step": 59873
    },
    {
      "epoch": 1.8392774859459957,
      "grad_norm": 0.46568557620048523,
      "learning_rate": 3.1808880379895044e-07,
      "loss": 0.569,
      "step": 59874
    },
    {
      "epoch": 1.839308205080945,
      "grad_norm": 0.4705721437931061,
      "learning_rate": 3.179678934024732e-07,
      "loss": 0.4904,
      "step": 59875
    },
    {
      "epoch": 1.8393389242158942,
      "grad_norm": 0.45312073826789856,
      "learning_rate": 3.178470056190586e-07,
      "loss": 0.4941,
      "step": 59876
    },
    {
      "epoch": 1.8393696433508433,
      "grad_norm": 0.4419688880443573,
      "learning_rate": 3.177261404489873e-07,
      "loss": 0.4807,
      "step": 59877
    },
    {
      "epoch": 1.8394003624857924,
      "grad_norm": 0.4613109827041626,
      "learning_rate": 3.176052978925437e-07,
      "loss": 0.4296,
      "step": 59878
    },
    {
      "epoch": 1.8394310816207415,
      "grad_norm": 0.4340849220752716,
      "learning_rate": 3.174844779500086e-07,
      "loss": 0.4972,
      "step": 59879
    },
    {
      "epoch": 1.8394618007556907,
      "grad_norm": 0.43448203802108765,
      "learning_rate": 3.173636806216662e-07,
      "loss": 0.4517,
      "step": 59880
    },
    {
      "epoch": 1.8394925198906398,
      "grad_norm": 0.5449314713478088,
      "learning_rate": 3.172429059077964e-07,
      "loss": 0.466,
      "step": 59881
    },
    {
      "epoch": 1.839523239025589,
      "grad_norm": 0.4336683750152588,
      "learning_rate": 3.1712215380868104e-07,
      "loss": 0.5017,
      "step": 59882
    },
    {
      "epoch": 1.8395539581605382,
      "grad_norm": 0.4322504997253418,
      "learning_rate": 3.170014243246033e-07,
      "loss": 0.4505,
      "step": 59883
    },
    {
      "epoch": 1.8395846772954874,
      "grad_norm": 0.4310269355773926,
      "learning_rate": 3.1688071745584637e-07,
      "loss": 0.3866,
      "step": 59884
    },
    {
      "epoch": 1.8396153964304365,
      "grad_norm": 0.4314141869544983,
      "learning_rate": 3.167600332026899e-07,
      "loss": 0.4906,
      "step": 59885
    },
    {
      "epoch": 1.8396461155653858,
      "grad_norm": 0.4418613910675049,
      "learning_rate": 3.16639371565417e-07,
      "loss": 0.5061,
      "step": 59886
    },
    {
      "epoch": 1.839676834700335,
      "grad_norm": 0.41595029830932617,
      "learning_rate": 3.1651873254430865e-07,
      "loss": 0.3947,
      "step": 59887
    },
    {
      "epoch": 1.839707553835284,
      "grad_norm": 0.4718450903892517,
      "learning_rate": 3.1639811613964677e-07,
      "loss": 0.5489,
      "step": 59888
    },
    {
      "epoch": 1.8397382729702332,
      "grad_norm": 0.4430418014526367,
      "learning_rate": 3.162775223517145e-07,
      "loss": 0.5347,
      "step": 59889
    },
    {
      "epoch": 1.8397689921051823,
      "grad_norm": 0.5029934048652649,
      "learning_rate": 3.161569511807916e-07,
      "loss": 0.466,
      "step": 59890
    },
    {
      "epoch": 1.8397997112401314,
      "grad_norm": 0.4153136909008026,
      "learning_rate": 3.1603640262716007e-07,
      "loss": 0.3966,
      "step": 59891
    },
    {
      "epoch": 1.8398304303750805,
      "grad_norm": 0.4130389094352722,
      "learning_rate": 3.159158766911019e-07,
      "loss": 0.3488,
      "step": 59892
    },
    {
      "epoch": 1.8398611495100297,
      "grad_norm": 0.48260289430618286,
      "learning_rate": 3.157953733729002e-07,
      "loss": 0.3617,
      "step": 59893
    },
    {
      "epoch": 1.839891868644979,
      "grad_norm": 0.4630483090877533,
      "learning_rate": 3.1567489267283366e-07,
      "loss": 0.4482,
      "step": 59894
    },
    {
      "epoch": 1.8399225877799281,
      "grad_norm": 0.4651423394680023,
      "learning_rate": 3.155544345911854e-07,
      "loss": 0.5254,
      "step": 59895
    },
    {
      "epoch": 1.8399533069148772,
      "grad_norm": 0.40091338753700256,
      "learning_rate": 3.15433999128234e-07,
      "loss": 0.479,
      "step": 59896
    },
    {
      "epoch": 1.8399840260498266,
      "grad_norm": 0.3993404507637024,
      "learning_rate": 3.153135862842649e-07,
      "loss": 0.5345,
      "step": 59897
    },
    {
      "epoch": 1.8400147451847757,
      "grad_norm": 0.38765576481819153,
      "learning_rate": 3.151931960595567e-07,
      "loss": 0.3706,
      "step": 59898
    },
    {
      "epoch": 1.8400454643197248,
      "grad_norm": 0.39522650837898254,
      "learning_rate": 3.1507282845439137e-07,
      "loss": 0.5007,
      "step": 59899
    },
    {
      "epoch": 1.840076183454674,
      "grad_norm": 0.45807158946990967,
      "learning_rate": 3.1495248346904873e-07,
      "loss": 0.4246,
      "step": 59900
    },
    {
      "epoch": 1.840106902589623,
      "grad_norm": 0.4159619212150574,
      "learning_rate": 3.1483216110381185e-07,
      "loss": 0.465,
      "step": 59901
    },
    {
      "epoch": 1.8401376217245722,
      "grad_norm": 0.41811403632164,
      "learning_rate": 3.147118613589606e-07,
      "loss": 0.4568,
      "step": 59902
    },
    {
      "epoch": 1.8401683408595213,
      "grad_norm": 0.45711639523506165,
      "learning_rate": 3.14591584234778e-07,
      "loss": 0.4796,
      "step": 59903
    },
    {
      "epoch": 1.8401990599944704,
      "grad_norm": 0.4364491105079651,
      "learning_rate": 3.1447132973154047e-07,
      "loss": 0.4405,
      "step": 59904
    },
    {
      "epoch": 1.8402297791294198,
      "grad_norm": 0.4328063130378723,
      "learning_rate": 3.1435109784953346e-07,
      "loss": 0.4414,
      "step": 59905
    },
    {
      "epoch": 1.8402604982643689,
      "grad_norm": 0.44033411145210266,
      "learning_rate": 3.142308885890344e-07,
      "loss": 0.4793,
      "step": 59906
    },
    {
      "epoch": 1.840291217399318,
      "grad_norm": 0.4288654923439026,
      "learning_rate": 3.1411070195032644e-07,
      "loss": 0.5422,
      "step": 59907
    },
    {
      "epoch": 1.8403219365342673,
      "grad_norm": 0.486067533493042,
      "learning_rate": 3.139905379336894e-07,
      "loss": 0.4261,
      "step": 59908
    },
    {
      "epoch": 1.8403526556692165,
      "grad_norm": 0.45419642329216003,
      "learning_rate": 3.138703965394041e-07,
      "loss": 0.4843,
      "step": 59909
    },
    {
      "epoch": 1.8403833748041656,
      "grad_norm": 0.4853527545928955,
      "learning_rate": 3.1375027776775036e-07,
      "loss": 0.4504,
      "step": 59910
    },
    {
      "epoch": 1.8404140939391147,
      "grad_norm": 0.4048893451690674,
      "learning_rate": 3.1363018161900904e-07,
      "loss": 0.3811,
      "step": 59911
    },
    {
      "epoch": 1.8404448130740638,
      "grad_norm": 0.4274897873401642,
      "learning_rate": 3.1351010809346217e-07,
      "loss": 0.5196,
      "step": 59912
    },
    {
      "epoch": 1.840475532209013,
      "grad_norm": 0.45653945207595825,
      "learning_rate": 3.133900571913884e-07,
      "loss": 0.5505,
      "step": 59913
    },
    {
      "epoch": 1.840506251343962,
      "grad_norm": 0.4044532775878906,
      "learning_rate": 3.1327002891306747e-07,
      "loss": 0.4823,
      "step": 59914
    },
    {
      "epoch": 1.8405369704789112,
      "grad_norm": 0.43970832228660583,
      "learning_rate": 3.1315002325878143e-07,
      "loss": 0.4465,
      "step": 59915
    },
    {
      "epoch": 1.8405676896138605,
      "grad_norm": 0.4782482981681824,
      "learning_rate": 3.130300402288122e-07,
      "loss": 0.5369,
      "step": 59916
    },
    {
      "epoch": 1.8405984087488096,
      "grad_norm": 0.3992239534854889,
      "learning_rate": 3.1291007982343523e-07,
      "loss": 0.4482,
      "step": 59917
    },
    {
      "epoch": 1.8406291278837588,
      "grad_norm": 0.40420660376548767,
      "learning_rate": 3.127901420429347e-07,
      "loss": 0.4323,
      "step": 59918
    },
    {
      "epoch": 1.840659847018708,
      "grad_norm": 0.4035872220993042,
      "learning_rate": 3.1267022688758807e-07,
      "loss": 0.4794,
      "step": 59919
    },
    {
      "epoch": 1.8406905661536572,
      "grad_norm": 0.4279526174068451,
      "learning_rate": 3.125503343576786e-07,
      "loss": 0.4549,
      "step": 59920
    },
    {
      "epoch": 1.8407212852886063,
      "grad_norm": 0.40738677978515625,
      "learning_rate": 3.124304644534826e-07,
      "loss": 0.4929,
      "step": 59921
    },
    {
      "epoch": 1.8407520044235555,
      "grad_norm": 0.42080944776535034,
      "learning_rate": 3.123106171752821e-07,
      "loss": 0.5464,
      "step": 59922
    },
    {
      "epoch": 1.8407827235585046,
      "grad_norm": 0.39634644985198975,
      "learning_rate": 3.1219079252335694e-07,
      "loss": 0.4345,
      "step": 59923
    },
    {
      "epoch": 1.8408134426934537,
      "grad_norm": 0.43033841252326965,
      "learning_rate": 3.1207099049798793e-07,
      "loss": 0.4893,
      "step": 59924
    },
    {
      "epoch": 1.8408441618284028,
      "grad_norm": 0.440941721200943,
      "learning_rate": 3.119512110994527e-07,
      "loss": 0.5288,
      "step": 59925
    },
    {
      "epoch": 1.840874880963352,
      "grad_norm": 0.9915491342544556,
      "learning_rate": 3.118314543280321e-07,
      "loss": 0.5059,
      "step": 59926
    },
    {
      "epoch": 1.8409056000983013,
      "grad_norm": 0.42310526967048645,
      "learning_rate": 3.1171172018400475e-07,
      "loss": 0.5002,
      "step": 59927
    },
    {
      "epoch": 1.8409363192332504,
      "grad_norm": 0.43924680352211,
      "learning_rate": 3.1159200866765273e-07,
      "loss": 0.4533,
      "step": 59928
    },
    {
      "epoch": 1.8409670383681995,
      "grad_norm": 0.4456196427345276,
      "learning_rate": 3.114723197792546e-07,
      "loss": 0.4901,
      "step": 59929
    },
    {
      "epoch": 1.8409977575031489,
      "grad_norm": 0.4537314772605896,
      "learning_rate": 3.1135265351908803e-07,
      "loss": 0.4586,
      "step": 59930
    },
    {
      "epoch": 1.841028476638098,
      "grad_norm": 0.4268844425678253,
      "learning_rate": 3.11233009887435e-07,
      "loss": 0.3898,
      "step": 59931
    },
    {
      "epoch": 1.841059195773047,
      "grad_norm": 0.4569224715232849,
      "learning_rate": 3.1111338888457296e-07,
      "loss": 0.4713,
      "step": 59932
    },
    {
      "epoch": 1.8410899149079962,
      "grad_norm": 0.5171856880187988,
      "learning_rate": 3.1099379051078293e-07,
      "loss": 0.4748,
      "step": 59933
    },
    {
      "epoch": 1.8411206340429453,
      "grad_norm": 0.45987915992736816,
      "learning_rate": 3.108742147663435e-07,
      "loss": 0.4722,
      "step": 59934
    },
    {
      "epoch": 1.8411513531778945,
      "grad_norm": 0.4574018120765686,
      "learning_rate": 3.1075466165153443e-07,
      "loss": 0.4906,
      "step": 59935
    },
    {
      "epoch": 1.8411820723128436,
      "grad_norm": 0.4200346767902374,
      "learning_rate": 3.1063513116663446e-07,
      "loss": 0.5183,
      "step": 59936
    },
    {
      "epoch": 1.8412127914477927,
      "grad_norm": 0.6164939999580383,
      "learning_rate": 3.105156233119222e-07,
      "loss": 0.5235,
      "step": 59937
    },
    {
      "epoch": 1.8412435105827418,
      "grad_norm": 0.4233610928058624,
      "learning_rate": 3.1039613808767743e-07,
      "loss": 0.5059,
      "step": 59938
    },
    {
      "epoch": 1.8412742297176912,
      "grad_norm": 0.5114676356315613,
      "learning_rate": 3.1027667549417994e-07,
      "loss": 0.4546,
      "step": 59939
    },
    {
      "epoch": 1.8413049488526403,
      "grad_norm": 0.43644630908966064,
      "learning_rate": 3.101572355317073e-07,
      "loss": 0.4806,
      "step": 59940
    },
    {
      "epoch": 1.8413356679875896,
      "grad_norm": 0.4338248074054718,
      "learning_rate": 3.1003781820053925e-07,
      "loss": 0.4885,
      "step": 59941
    },
    {
      "epoch": 1.8413663871225388,
      "grad_norm": 0.4454827308654785,
      "learning_rate": 3.0991842350095446e-07,
      "loss": 0.4899,
      "step": 59942
    },
    {
      "epoch": 1.8413971062574879,
      "grad_norm": 0.5058271884918213,
      "learning_rate": 3.0979905143323166e-07,
      "loss": 0.3917,
      "step": 59943
    },
    {
      "epoch": 1.841427825392437,
      "grad_norm": 0.4120197296142578,
      "learning_rate": 3.0967970199765164e-07,
      "loss": 0.5022,
      "step": 59944
    },
    {
      "epoch": 1.841458544527386,
      "grad_norm": 0.4222201704978943,
      "learning_rate": 3.095603751944898e-07,
      "loss": 0.4921,
      "step": 59945
    },
    {
      "epoch": 1.8414892636623352,
      "grad_norm": 0.4177967607975006,
      "learning_rate": 3.09441071024027e-07,
      "loss": 0.4843,
      "step": 59946
    },
    {
      "epoch": 1.8415199827972843,
      "grad_norm": 0.39879992604255676,
      "learning_rate": 3.093217894865408e-07,
      "loss": 0.5105,
      "step": 59947
    },
    {
      "epoch": 1.8415507019322335,
      "grad_norm": 0.43617820739746094,
      "learning_rate": 3.092025305823121e-07,
      "loss": 0.4285,
      "step": 59948
    },
    {
      "epoch": 1.8415814210671826,
      "grad_norm": 0.44823983311653137,
      "learning_rate": 3.090832943116162e-07,
      "loss": 0.4486,
      "step": 59949
    },
    {
      "epoch": 1.841612140202132,
      "grad_norm": 0.4351291060447693,
      "learning_rate": 3.0896408067473296e-07,
      "loss": 0.3914,
      "step": 59950
    },
    {
      "epoch": 1.841642859337081,
      "grad_norm": 0.463235467672348,
      "learning_rate": 3.088448896719409e-07,
      "loss": 0.5146,
      "step": 59951
    },
    {
      "epoch": 1.8416735784720304,
      "grad_norm": 0.46483924984931946,
      "learning_rate": 3.0872572130352e-07,
      "loss": 0.5077,
      "step": 59952
    },
    {
      "epoch": 1.8417042976069795,
      "grad_norm": 0.4425165057182312,
      "learning_rate": 3.0860657556974536e-07,
      "loss": 0.3947,
      "step": 59953
    },
    {
      "epoch": 1.8417350167419286,
      "grad_norm": 0.39864999055862427,
      "learning_rate": 3.0848745247089696e-07,
      "loss": 0.4789,
      "step": 59954
    },
    {
      "epoch": 1.8417657358768778,
      "grad_norm": 0.3741898834705353,
      "learning_rate": 3.0836835200725336e-07,
      "loss": 0.3908,
      "step": 59955
    },
    {
      "epoch": 1.8417964550118269,
      "grad_norm": 0.42844781279563904,
      "learning_rate": 3.0824927417909324e-07,
      "loss": 0.4522,
      "step": 59956
    },
    {
      "epoch": 1.841827174146776,
      "grad_norm": 0.4254593849182129,
      "learning_rate": 3.0813021898669305e-07,
      "loss": 0.405,
      "step": 59957
    },
    {
      "epoch": 1.8418578932817251,
      "grad_norm": 0.45560768246650696,
      "learning_rate": 3.080111864303326e-07,
      "loss": 0.4619,
      "step": 59958
    },
    {
      "epoch": 1.8418886124166742,
      "grad_norm": 0.390583336353302,
      "learning_rate": 3.0789217651028604e-07,
      "loss": 0.4778,
      "step": 59959
    },
    {
      "epoch": 1.8419193315516234,
      "grad_norm": 0.4472966194152832,
      "learning_rate": 3.077731892268365e-07,
      "loss": 0.5246,
      "step": 59960
    },
    {
      "epoch": 1.8419500506865727,
      "grad_norm": 0.3539034426212311,
      "learning_rate": 3.076542245802594e-07,
      "loss": 0.4219,
      "step": 59961
    },
    {
      "epoch": 1.8419807698215218,
      "grad_norm": 0.4272688627243042,
      "learning_rate": 3.075352825708311e-07,
      "loss": 0.4677,
      "step": 59962
    },
    {
      "epoch": 1.842011488956471,
      "grad_norm": 0.4178944528102875,
      "learning_rate": 3.074163631988325e-07,
      "loss": 0.4795,
      "step": 59963
    },
    {
      "epoch": 1.8420422080914203,
      "grad_norm": 0.4328293204307556,
      "learning_rate": 3.0729746646454005e-07,
      "loss": 0.4483,
      "step": 59964
    },
    {
      "epoch": 1.8420729272263694,
      "grad_norm": 0.4408715069293976,
      "learning_rate": 3.071785923682313e-07,
      "loss": 0.5342,
      "step": 59965
    },
    {
      "epoch": 1.8421036463613185,
      "grad_norm": 0.43339940905570984,
      "learning_rate": 3.0705974091018276e-07,
      "loss": 0.4606,
      "step": 59966
    },
    {
      "epoch": 1.8421343654962676,
      "grad_norm": 0.4407235383987427,
      "learning_rate": 3.0694091209067524e-07,
      "loss": 0.4583,
      "step": 59967
    },
    {
      "epoch": 1.8421650846312168,
      "grad_norm": 0.4415554404258728,
      "learning_rate": 3.0682210590998185e-07,
      "loss": 0.4902,
      "step": 59968
    },
    {
      "epoch": 1.8421958037661659,
      "grad_norm": 0.46175283193588257,
      "learning_rate": 3.067033223683835e-07,
      "loss": 0.4731,
      "step": 59969
    },
    {
      "epoch": 1.842226522901115,
      "grad_norm": 0.46436944603919983,
      "learning_rate": 3.0658456146615665e-07,
      "loss": 0.4737,
      "step": 59970
    },
    {
      "epoch": 1.8422572420360641,
      "grad_norm": 0.4273889660835266,
      "learning_rate": 3.0646582320357887e-07,
      "loss": 0.4452,
      "step": 59971
    },
    {
      "epoch": 1.8422879611710135,
      "grad_norm": 0.43868571519851685,
      "learning_rate": 3.0634710758092656e-07,
      "loss": 0.5142,
      "step": 59972
    },
    {
      "epoch": 1.8423186803059626,
      "grad_norm": 0.40922075510025024,
      "learning_rate": 3.062284145984773e-07,
      "loss": 0.4465,
      "step": 59973
    },
    {
      "epoch": 1.8423493994409117,
      "grad_norm": 0.4082149863243103,
      "learning_rate": 3.0610974425650863e-07,
      "loss": 0.4119,
      "step": 59974
    },
    {
      "epoch": 1.842380118575861,
      "grad_norm": 0.4272412359714508,
      "learning_rate": 3.0599109655529924e-07,
      "loss": 0.4296,
      "step": 59975
    },
    {
      "epoch": 1.8424108377108102,
      "grad_norm": 0.4329843819141388,
      "learning_rate": 3.0587247149512336e-07,
      "loss": 0.4696,
      "step": 59976
    },
    {
      "epoch": 1.8424415568457593,
      "grad_norm": 0.49845069646835327,
      "learning_rate": 3.057538690762585e-07,
      "loss": 0.4653,
      "step": 59977
    },
    {
      "epoch": 1.8424722759807084,
      "grad_norm": 0.4561896026134491,
      "learning_rate": 3.0563528929898335e-07,
      "loss": 0.4961,
      "step": 59978
    },
    {
      "epoch": 1.8425029951156575,
      "grad_norm": 0.49096518754959106,
      "learning_rate": 3.0551673216357323e-07,
      "loss": 0.4352,
      "step": 59979
    },
    {
      "epoch": 1.8425337142506066,
      "grad_norm": 0.4196116030216217,
      "learning_rate": 3.05398197670308e-07,
      "loss": 0.4462,
      "step": 59980
    },
    {
      "epoch": 1.8425644333855558,
      "grad_norm": 0.45535120368003845,
      "learning_rate": 3.0527968581946066e-07,
      "loss": 0.4563,
      "step": 59981
    },
    {
      "epoch": 1.8425951525205049,
      "grad_norm": 0.4379943609237671,
      "learning_rate": 3.0516119661130994e-07,
      "loss": 0.5508,
      "step": 59982
    },
    {
      "epoch": 1.8426258716554542,
      "grad_norm": 0.45247796177864075,
      "learning_rate": 3.0504273004613226e-07,
      "loss": 0.467,
      "step": 59983
    },
    {
      "epoch": 1.8426565907904033,
      "grad_norm": 0.4233584702014923,
      "learning_rate": 3.049242861242052e-07,
      "loss": 0.509,
      "step": 59984
    },
    {
      "epoch": 1.8426873099253525,
      "grad_norm": 0.435322642326355,
      "learning_rate": 3.048058648458041e-07,
      "loss": 0.4745,
      "step": 59985
    },
    {
      "epoch": 1.8427180290603018,
      "grad_norm": 0.4055899679660797,
      "learning_rate": 3.0468746621120537e-07,
      "loss": 0.506,
      "step": 59986
    },
    {
      "epoch": 1.842748748195251,
      "grad_norm": 0.5262146592140198,
      "learning_rate": 3.045690902206866e-07,
      "loss": 0.5226,
      "step": 59987
    },
    {
      "epoch": 1.8427794673302,
      "grad_norm": 0.38628003001213074,
      "learning_rate": 3.044507368745242e-07,
      "loss": 0.4194,
      "step": 59988
    },
    {
      "epoch": 1.8428101864651492,
      "grad_norm": 0.42441603541374207,
      "learning_rate": 3.0433240617299353e-07,
      "loss": 0.5183,
      "step": 59989
    },
    {
      "epoch": 1.8428409056000983,
      "grad_norm": 0.4683433473110199,
      "learning_rate": 3.0421409811637215e-07,
      "loss": 0.4988,
      "step": 59990
    },
    {
      "epoch": 1.8428716247350474,
      "grad_norm": 0.42600616812705994,
      "learning_rate": 3.0409581270493537e-07,
      "loss": 0.4056,
      "step": 59991
    },
    {
      "epoch": 1.8429023438699965,
      "grad_norm": 0.4162905216217041,
      "learning_rate": 3.039775499389608e-07,
      "loss": 0.4659,
      "step": 59992
    },
    {
      "epoch": 1.8429330630049456,
      "grad_norm": 0.4350684583187103,
      "learning_rate": 3.038593098187237e-07,
      "loss": 0.4486,
      "step": 59993
    },
    {
      "epoch": 1.842963782139895,
      "grad_norm": 0.41019925475120544,
      "learning_rate": 3.0374109234450056e-07,
      "loss": 0.4018,
      "step": 59994
    },
    {
      "epoch": 1.842994501274844,
      "grad_norm": 0.417926549911499,
      "learning_rate": 3.0362289751656557e-07,
      "loss": 0.4481,
      "step": 59995
    },
    {
      "epoch": 1.8430252204097932,
      "grad_norm": 0.46582019329071045,
      "learning_rate": 3.035047253351986e-07,
      "loss": 0.4589,
      "step": 59996
    },
    {
      "epoch": 1.8430559395447426,
      "grad_norm": 0.442035973072052,
      "learning_rate": 3.0338657580067265e-07,
      "loss": 0.4201,
      "step": 59997
    },
    {
      "epoch": 1.8430866586796917,
      "grad_norm": 0.45685428380966187,
      "learning_rate": 3.032684489132642e-07,
      "loss": 0.4381,
      "step": 59998
    },
    {
      "epoch": 1.8431173778146408,
      "grad_norm": 0.3988616466522217,
      "learning_rate": 3.031503446732498e-07,
      "loss": 0.4911,
      "step": 59999
    },
    {
      "epoch": 1.84314809694959,
      "grad_norm": 0.4465632438659668,
      "learning_rate": 3.030322630809046e-07,
      "loss": 0.471,
      "step": 60000
    },
    {
      "epoch": 1.843178816084539,
      "grad_norm": 0.41740933060646057,
      "learning_rate": 3.029142041365052e-07,
      "loss": 0.5092,
      "step": 60001
    },
    {
      "epoch": 1.8432095352194882,
      "grad_norm": 0.4792197048664093,
      "learning_rate": 3.0279616784032683e-07,
      "loss": 0.4431,
      "step": 60002
    },
    {
      "epoch": 1.8432402543544373,
      "grad_norm": 0.4764556586742401,
      "learning_rate": 3.0267815419264603e-07,
      "loss": 0.4574,
      "step": 60003
    },
    {
      "epoch": 1.8432709734893864,
      "grad_norm": 0.41611090302467346,
      "learning_rate": 3.025601631937358e-07,
      "loss": 0.3796,
      "step": 60004
    },
    {
      "epoch": 1.8433016926243357,
      "grad_norm": 0.4226471781730652,
      "learning_rate": 3.02442194843876e-07,
      "loss": 0.3476,
      "step": 60005
    },
    {
      "epoch": 1.8433324117592849,
      "grad_norm": 0.5381960272789001,
      "learning_rate": 3.023242491433376e-07,
      "loss": 0.4792,
      "step": 60006
    },
    {
      "epoch": 1.843363130894234,
      "grad_norm": 0.4378426671028137,
      "learning_rate": 3.022063260924002e-07,
      "loss": 0.4138,
      "step": 60007
    },
    {
      "epoch": 1.8433938500291833,
      "grad_norm": 0.44295862317085266,
      "learning_rate": 3.020884256913359e-07,
      "loss": 0.5204,
      "step": 60008
    },
    {
      "epoch": 1.8434245691641324,
      "grad_norm": 0.46030643582344055,
      "learning_rate": 3.0197054794042116e-07,
      "loss": 0.4598,
      "step": 60009
    },
    {
      "epoch": 1.8434552882990816,
      "grad_norm": 0.45464739203453064,
      "learning_rate": 3.0185269283993126e-07,
      "loss": 0.367,
      "step": 60010
    },
    {
      "epoch": 1.8434860074340307,
      "grad_norm": 0.4841053783893585,
      "learning_rate": 3.017348603901438e-07,
      "loss": 0.5311,
      "step": 60011
    },
    {
      "epoch": 1.8435167265689798,
      "grad_norm": 0.4150855839252472,
      "learning_rate": 3.016170505913296e-07,
      "loss": 0.5097,
      "step": 60012
    },
    {
      "epoch": 1.843547445703929,
      "grad_norm": 0.40933263301849365,
      "learning_rate": 3.0149926344376635e-07,
      "loss": 0.5179,
      "step": 60013
    },
    {
      "epoch": 1.843578164838878,
      "grad_norm": 0.4358690083026886,
      "learning_rate": 3.013814989477293e-07,
      "loss": 0.4562,
      "step": 60014
    },
    {
      "epoch": 1.8436088839738272,
      "grad_norm": 0.4234655797481537,
      "learning_rate": 3.012637571034949e-07,
      "loss": 0.435,
      "step": 60015
    },
    {
      "epoch": 1.8436396031087765,
      "grad_norm": 0.47014284133911133,
      "learning_rate": 3.01146037911334e-07,
      "loss": 0.4496,
      "step": 60016
    },
    {
      "epoch": 1.8436703222437256,
      "grad_norm": 0.46315139532089233,
      "learning_rate": 3.010283413715243e-07,
      "loss": 0.4061,
      "step": 60017
    },
    {
      "epoch": 1.8437010413786747,
      "grad_norm": 0.45192402601242065,
      "learning_rate": 3.0091066748434095e-07,
      "loss": 0.441,
      "step": 60018
    },
    {
      "epoch": 1.843731760513624,
      "grad_norm": 0.42047902941703796,
      "learning_rate": 3.0079301625005717e-07,
      "loss": 0.4465,
      "step": 60019
    },
    {
      "epoch": 1.8437624796485732,
      "grad_norm": 0.5373002886772156,
      "learning_rate": 3.0067538766895053e-07,
      "loss": 0.4662,
      "step": 60020
    },
    {
      "epoch": 1.8437931987835223,
      "grad_norm": 0.41910693049430847,
      "learning_rate": 3.0055778174129193e-07,
      "loss": 0.4092,
      "step": 60021
    },
    {
      "epoch": 1.8438239179184714,
      "grad_norm": 0.4955258369445801,
      "learning_rate": 3.0044019846735883e-07,
      "loss": 0.4304,
      "step": 60022
    },
    {
      "epoch": 1.8438546370534206,
      "grad_norm": 0.4999709129333496,
      "learning_rate": 3.0032263784742445e-07,
      "loss": 0.447,
      "step": 60023
    },
    {
      "epoch": 1.8438853561883697,
      "grad_norm": 0.4455203711986542,
      "learning_rate": 3.002050998817652e-07,
      "loss": 0.5183,
      "step": 60024
    },
    {
      "epoch": 1.8439160753233188,
      "grad_norm": 0.4661495089530945,
      "learning_rate": 3.0008758457065304e-07,
      "loss": 0.5309,
      "step": 60025
    },
    {
      "epoch": 1.843946794458268,
      "grad_norm": 0.44627922773361206,
      "learning_rate": 2.9997009191436446e-07,
      "loss": 0.4852,
      "step": 60026
    },
    {
      "epoch": 1.8439775135932173,
      "grad_norm": 0.45512351393699646,
      "learning_rate": 2.9985262191317257e-07,
      "loss": 0.4887,
      "step": 60027
    },
    {
      "epoch": 1.8440082327281664,
      "grad_norm": 0.4745049476623535,
      "learning_rate": 2.997351745673538e-07,
      "loss": 0.4482,
      "step": 60028
    },
    {
      "epoch": 1.8440389518631155,
      "grad_norm": 0.4299730658531189,
      "learning_rate": 2.996177498771802e-07,
      "loss": 0.4963,
      "step": 60029
    },
    {
      "epoch": 1.8440696709980648,
      "grad_norm": 0.4164971113204956,
      "learning_rate": 2.9950034784292705e-07,
      "loss": 0.4772,
      "step": 60030
    },
    {
      "epoch": 1.844100390133014,
      "grad_norm": 0.43513554334640503,
      "learning_rate": 2.993829684648664e-07,
      "loss": 0.4314,
      "step": 60031
    },
    {
      "epoch": 1.844131109267963,
      "grad_norm": 0.4735279977321625,
      "learning_rate": 2.9926561174327683e-07,
      "loss": 0.403,
      "step": 60032
    },
    {
      "epoch": 1.8441618284029122,
      "grad_norm": 0.4568847715854645,
      "learning_rate": 2.9914827767842937e-07,
      "loss": 0.4402,
      "step": 60033
    },
    {
      "epoch": 1.8441925475378613,
      "grad_norm": 0.41272178292274475,
      "learning_rate": 2.99030966270597e-07,
      "loss": 0.4713,
      "step": 60034
    },
    {
      "epoch": 1.8442232666728104,
      "grad_norm": 0.45615988969802856,
      "learning_rate": 2.989136775200574e-07,
      "loss": 0.4334,
      "step": 60035
    },
    {
      "epoch": 1.8442539858077596,
      "grad_norm": 0.4596073031425476,
      "learning_rate": 2.9879641142708027e-07,
      "loss": 0.4623,
      "step": 60036
    },
    {
      "epoch": 1.8442847049427087,
      "grad_norm": 0.40317100286483765,
      "learning_rate": 2.986791679919443e-07,
      "loss": 0.471,
      "step": 60037
    },
    {
      "epoch": 1.844315424077658,
      "grad_norm": 0.44274598360061646,
      "learning_rate": 2.9856194721491816e-07,
      "loss": 0.4021,
      "step": 60038
    },
    {
      "epoch": 1.8443461432126071,
      "grad_norm": 0.44869187474250793,
      "learning_rate": 2.9844474909628053e-07,
      "loss": 0.4964,
      "step": 60039
    },
    {
      "epoch": 1.8443768623475563,
      "grad_norm": 0.4909902811050415,
      "learning_rate": 2.9832757363630114e-07,
      "loss": 0.4981,
      "step": 60040
    },
    {
      "epoch": 1.8444075814825056,
      "grad_norm": 0.39239007234573364,
      "learning_rate": 2.9821042083525544e-07,
      "loss": 0.4941,
      "step": 60041
    },
    {
      "epoch": 1.8444383006174547,
      "grad_norm": 0.43343672156333923,
      "learning_rate": 2.980932906934164e-07,
      "loss": 0.5303,
      "step": 60042
    },
    {
      "epoch": 1.8444690197524038,
      "grad_norm": 0.41882872581481934,
      "learning_rate": 2.979761832110595e-07,
      "loss": 0.4804,
      "step": 60043
    },
    {
      "epoch": 1.844499738887353,
      "grad_norm": 0.46135222911834717,
      "learning_rate": 2.978590983884555e-07,
      "loss": 0.5333,
      "step": 60044
    },
    {
      "epoch": 1.844530458022302,
      "grad_norm": 0.410080224275589,
      "learning_rate": 2.977420362258798e-07,
      "loss": 0.4044,
      "step": 60045
    },
    {
      "epoch": 1.8445611771572512,
      "grad_norm": 0.41920268535614014,
      "learning_rate": 2.976249967236045e-07,
      "loss": 0.4773,
      "step": 60046
    },
    {
      "epoch": 1.8445918962922003,
      "grad_norm": 0.4454802870750427,
      "learning_rate": 2.975079798819047e-07,
      "loss": 0.4796,
      "step": 60047
    },
    {
      "epoch": 1.8446226154271494,
      "grad_norm": 0.41442471742630005,
      "learning_rate": 2.973909857010515e-07,
      "loss": 0.495,
      "step": 60048
    },
    {
      "epoch": 1.8446533345620986,
      "grad_norm": 0.4785802960395813,
      "learning_rate": 2.972740141813202e-07,
      "loss": 0.5029,
      "step": 60049
    },
    {
      "epoch": 1.844684053697048,
      "grad_norm": 0.4703596234321594,
      "learning_rate": 2.971570653229827e-07,
      "loss": 0.4646,
      "step": 60050
    },
    {
      "epoch": 1.844714772831997,
      "grad_norm": 0.4417171776294708,
      "learning_rate": 2.9704013912631336e-07,
      "loss": 0.4698,
      "step": 60051
    },
    {
      "epoch": 1.8447454919669464,
      "grad_norm": 0.45568886399269104,
      "learning_rate": 2.96923235591583e-07,
      "loss": 0.4743,
      "step": 60052
    },
    {
      "epoch": 1.8447762111018955,
      "grad_norm": 0.4331597089767456,
      "learning_rate": 2.9680635471906583e-07,
      "loss": 0.5453,
      "step": 60053
    },
    {
      "epoch": 1.8448069302368446,
      "grad_norm": 0.43408963084220886,
      "learning_rate": 2.966894965090361e-07,
      "loss": 0.4133,
      "step": 60054
    },
    {
      "epoch": 1.8448376493717937,
      "grad_norm": 0.43650680780410767,
      "learning_rate": 2.9657266096176475e-07,
      "loss": 0.3327,
      "step": 60055
    },
    {
      "epoch": 1.8448683685067429,
      "grad_norm": 0.4723765552043915,
      "learning_rate": 2.9645584807752704e-07,
      "loss": 0.4459,
      "step": 60056
    },
    {
      "epoch": 1.844899087641692,
      "grad_norm": 0.4593942165374756,
      "learning_rate": 2.9633905785659387e-07,
      "loss": 0.4966,
      "step": 60057
    },
    {
      "epoch": 1.844929806776641,
      "grad_norm": 0.409227579832077,
      "learning_rate": 2.9622229029923846e-07,
      "loss": 0.443,
      "step": 60058
    },
    {
      "epoch": 1.8449605259115902,
      "grad_norm": 0.41760754585266113,
      "learning_rate": 2.9610554540573265e-07,
      "loss": 0.4556,
      "step": 60059
    },
    {
      "epoch": 1.8449912450465393,
      "grad_norm": 0.4317387640476227,
      "learning_rate": 2.959888231763519e-07,
      "loss": 0.3976,
      "step": 60060
    },
    {
      "epoch": 1.8450219641814887,
      "grad_norm": 0.39018145203590393,
      "learning_rate": 2.95872123611366e-07,
      "loss": 0.4833,
      "step": 60061
    },
    {
      "epoch": 1.8450526833164378,
      "grad_norm": 0.4122965335845947,
      "learning_rate": 2.9575544671104794e-07,
      "loss": 0.479,
      "step": 60062
    },
    {
      "epoch": 1.8450834024513871,
      "grad_norm": 0.5020707249641418,
      "learning_rate": 2.9563879247567097e-07,
      "loss": 0.4563,
      "step": 60063
    },
    {
      "epoch": 1.8451141215863363,
      "grad_norm": 0.39934247732162476,
      "learning_rate": 2.9552216090550923e-07,
      "loss": 0.4416,
      "step": 60064
    },
    {
      "epoch": 1.8451448407212854,
      "grad_norm": 0.4564479887485504,
      "learning_rate": 2.9540555200083145e-07,
      "loss": 0.4686,
      "step": 60065
    },
    {
      "epoch": 1.8451755598562345,
      "grad_norm": 0.40763482451438904,
      "learning_rate": 2.952889657619118e-07,
      "loss": 0.4458,
      "step": 60066
    },
    {
      "epoch": 1.8452062789911836,
      "grad_norm": 0.4649072587490082,
      "learning_rate": 2.9517240218902233e-07,
      "loss": 0.4894,
      "step": 60067
    },
    {
      "epoch": 1.8452369981261327,
      "grad_norm": 0.4155901372432709,
      "learning_rate": 2.950558612824361e-07,
      "loss": 0.462,
      "step": 60068
    },
    {
      "epoch": 1.8452677172610819,
      "grad_norm": 0.41081687808036804,
      "learning_rate": 2.949393430424241e-07,
      "loss": 0.4595,
      "step": 60069
    },
    {
      "epoch": 1.845298436396031,
      "grad_norm": 0.42900681495666504,
      "learning_rate": 2.948228474692605e-07,
      "loss": 0.4368,
      "step": 60070
    },
    {
      "epoch": 1.84532915553098,
      "grad_norm": 0.43363600969314575,
      "learning_rate": 2.94706374563215e-07,
      "loss": 0.4885,
      "step": 60071
    },
    {
      "epoch": 1.8453598746659294,
      "grad_norm": 0.40014544129371643,
      "learning_rate": 2.945899243245587e-07,
      "loss": 0.4764,
      "step": 60072
    },
    {
      "epoch": 1.8453905938008786,
      "grad_norm": 0.45263996720314026,
      "learning_rate": 2.9447349675356783e-07,
      "loss": 0.4199,
      "step": 60073
    },
    {
      "epoch": 1.8454213129358277,
      "grad_norm": 0.5259624123573303,
      "learning_rate": 2.943570918505112e-07,
      "loss": 0.425,
      "step": 60074
    },
    {
      "epoch": 1.845452032070777,
      "grad_norm": 0.4656524956226349,
      "learning_rate": 2.94240709615663e-07,
      "loss": 0.4692,
      "step": 60075
    },
    {
      "epoch": 1.8454827512057261,
      "grad_norm": 0.41525688767433167,
      "learning_rate": 2.9412435004929075e-07,
      "loss": 0.5006,
      "step": 60076
    },
    {
      "epoch": 1.8455134703406753,
      "grad_norm": 0.4457506239414215,
      "learning_rate": 2.9400801315167095e-07,
      "loss": 0.4332,
      "step": 60077
    },
    {
      "epoch": 1.8455441894756244,
      "grad_norm": 0.4360593557357788,
      "learning_rate": 2.938916989230722e-07,
      "loss": 0.4414,
      "step": 60078
    },
    {
      "epoch": 1.8455749086105735,
      "grad_norm": 0.4741480052471161,
      "learning_rate": 2.9377540736376776e-07,
      "loss": 0.4989,
      "step": 60079
    },
    {
      "epoch": 1.8456056277455226,
      "grad_norm": 0.424201101064682,
      "learning_rate": 2.936591384740284e-07,
      "loss": 0.4122,
      "step": 60080
    },
    {
      "epoch": 1.8456363468804717,
      "grad_norm": 0.4797978401184082,
      "learning_rate": 2.935428922541261e-07,
      "loss": 0.4636,
      "step": 60081
    },
    {
      "epoch": 1.8456670660154209,
      "grad_norm": 0.428167462348938,
      "learning_rate": 2.934266687043319e-07,
      "loss": 0.5185,
      "step": 60082
    },
    {
      "epoch": 1.8456977851503702,
      "grad_norm": 0.426443487405777,
      "learning_rate": 2.933104678249188e-07,
      "loss": 0.4575,
      "step": 60083
    },
    {
      "epoch": 1.8457285042853193,
      "grad_norm": 0.4788360297679901,
      "learning_rate": 2.9319428961615547e-07,
      "loss": 0.506,
      "step": 60084
    },
    {
      "epoch": 1.8457592234202684,
      "grad_norm": 0.4330713748931885,
      "learning_rate": 2.930781340783162e-07,
      "loss": 0.4961,
      "step": 60085
    },
    {
      "epoch": 1.8457899425552178,
      "grad_norm": 0.43879640102386475,
      "learning_rate": 2.929620012116696e-07,
      "loss": 0.4919,
      "step": 60086
    },
    {
      "epoch": 1.845820661690167,
      "grad_norm": 0.5022891163825989,
      "learning_rate": 2.9284589101649e-07,
      "loss": 0.4543,
      "step": 60087
    },
    {
      "epoch": 1.845851380825116,
      "grad_norm": 0.502640426158905,
      "learning_rate": 2.9272980349304483e-07,
      "loss": 0.507,
      "step": 60088
    },
    {
      "epoch": 1.8458820999600651,
      "grad_norm": 0.43175143003463745,
      "learning_rate": 2.9261373864160727e-07,
      "loss": 0.4394,
      "step": 60089
    },
    {
      "epoch": 1.8459128190950143,
      "grad_norm": 0.4208017885684967,
      "learning_rate": 2.924976964624493e-07,
      "loss": 0.4001,
      "step": 60090
    },
    {
      "epoch": 1.8459435382299634,
      "grad_norm": 0.514864981174469,
      "learning_rate": 2.9238167695583964e-07,
      "loss": 0.4654,
      "step": 60091
    },
    {
      "epoch": 1.8459742573649125,
      "grad_norm": 0.40381136536598206,
      "learning_rate": 2.922656801220525e-07,
      "loss": 0.4245,
      "step": 60092
    },
    {
      "epoch": 1.8460049764998616,
      "grad_norm": 0.4020734429359436,
      "learning_rate": 2.9214970596135536e-07,
      "loss": 0.4268,
      "step": 60093
    },
    {
      "epoch": 1.846035695634811,
      "grad_norm": 0.40731292963027954,
      "learning_rate": 2.920337544740215e-07,
      "loss": 0.483,
      "step": 60094
    },
    {
      "epoch": 1.84606641476976,
      "grad_norm": 0.46876081824302673,
      "learning_rate": 2.9191782566031944e-07,
      "loss": 0.5203,
      "step": 60095
    },
    {
      "epoch": 1.8460971339047092,
      "grad_norm": 0.42328232526779175,
      "learning_rate": 2.918019195205235e-07,
      "loss": 0.4564,
      "step": 60096
    },
    {
      "epoch": 1.8461278530396585,
      "grad_norm": 0.3940941393375397,
      "learning_rate": 2.916860360549001e-07,
      "loss": 0.494,
      "step": 60097
    },
    {
      "epoch": 1.8461585721746077,
      "grad_norm": 0.5058414936065674,
      "learning_rate": 2.9157017526372345e-07,
      "loss": 0.5364,
      "step": 60098
    },
    {
      "epoch": 1.8461892913095568,
      "grad_norm": 0.43381667137145996,
      "learning_rate": 2.914543371472611e-07,
      "loss": 0.4649,
      "step": 60099
    },
    {
      "epoch": 1.846220010444506,
      "grad_norm": 0.41298726201057434,
      "learning_rate": 2.9133852170578623e-07,
      "loss": 0.4431,
      "step": 60100
    },
    {
      "epoch": 1.846250729579455,
      "grad_norm": 0.41626065969467163,
      "learning_rate": 2.912227289395686e-07,
      "loss": 0.4002,
      "step": 60101
    },
    {
      "epoch": 1.8462814487144041,
      "grad_norm": 0.4436686635017395,
      "learning_rate": 2.9110695884887794e-07,
      "loss": 0.4954,
      "step": 60102
    },
    {
      "epoch": 1.8463121678493533,
      "grad_norm": 0.471293568611145,
      "learning_rate": 2.9099121143398415e-07,
      "loss": 0.5446,
      "step": 60103
    },
    {
      "epoch": 1.8463428869843024,
      "grad_norm": 0.43006429076194763,
      "learning_rate": 2.908754866951602e-07,
      "loss": 0.4616,
      "step": 60104
    },
    {
      "epoch": 1.8463736061192517,
      "grad_norm": 0.42271697521209717,
      "learning_rate": 2.9075978463267263e-07,
      "loss": 0.4296,
      "step": 60105
    },
    {
      "epoch": 1.8464043252542008,
      "grad_norm": 0.44772857427597046,
      "learning_rate": 2.906441052467956e-07,
      "loss": 0.4749,
      "step": 60106
    },
    {
      "epoch": 1.84643504438915,
      "grad_norm": 0.4330742657184601,
      "learning_rate": 2.905284485377968e-07,
      "loss": 0.4843,
      "step": 60107
    },
    {
      "epoch": 1.8464657635240993,
      "grad_norm": 0.43152856826782227,
      "learning_rate": 2.904128145059448e-07,
      "loss": 0.4034,
      "step": 60108
    },
    {
      "epoch": 1.8464964826590484,
      "grad_norm": 0.43726080656051636,
      "learning_rate": 2.90297203151515e-07,
      "loss": 0.5359,
      "step": 60109
    },
    {
      "epoch": 1.8465272017939975,
      "grad_norm": 0.4367043972015381,
      "learning_rate": 2.9018161447477266e-07,
      "loss": 0.4472,
      "step": 60110
    },
    {
      "epoch": 1.8465579209289467,
      "grad_norm": 0.4238281548023224,
      "learning_rate": 2.9006604847598986e-07,
      "loss": 0.5372,
      "step": 60111
    },
    {
      "epoch": 1.8465886400638958,
      "grad_norm": 0.5687945485115051,
      "learning_rate": 2.899505051554352e-07,
      "loss": 0.5259,
      "step": 60112
    },
    {
      "epoch": 1.846619359198845,
      "grad_norm": 0.42473262548446655,
      "learning_rate": 2.8983498451337965e-07,
      "loss": 0.4737,
      "step": 60113
    },
    {
      "epoch": 1.846650078333794,
      "grad_norm": 0.4669450521469116,
      "learning_rate": 2.8971948655009185e-07,
      "loss": 0.5116,
      "step": 60114
    },
    {
      "epoch": 1.8466807974687431,
      "grad_norm": 0.41549408435821533,
      "learning_rate": 2.896040112658438e-07,
      "loss": 0.5159,
      "step": 60115
    },
    {
      "epoch": 1.8467115166036925,
      "grad_norm": 0.43649160861968994,
      "learning_rate": 2.8948855866090306e-07,
      "loss": 0.443,
      "step": 60116
    },
    {
      "epoch": 1.8467422357386416,
      "grad_norm": 0.46115750074386597,
      "learning_rate": 2.8937312873553945e-07,
      "loss": 0.458,
      "step": 60117
    },
    {
      "epoch": 1.8467729548735907,
      "grad_norm": 0.404485285282135,
      "learning_rate": 2.892577214900227e-07,
      "loss": 0.4487,
      "step": 60118
    },
    {
      "epoch": 1.84680367400854,
      "grad_norm": 0.43977558612823486,
      "learning_rate": 2.891423369246249e-07,
      "loss": 0.4692,
      "step": 60119
    },
    {
      "epoch": 1.8468343931434892,
      "grad_norm": 0.42298442125320435,
      "learning_rate": 2.890269750396113e-07,
      "loss": 0.4215,
      "step": 60120
    },
    {
      "epoch": 1.8468651122784383,
      "grad_norm": 0.441914826631546,
      "learning_rate": 2.8891163583525396e-07,
      "loss": 0.4694,
      "step": 60121
    },
    {
      "epoch": 1.8468958314133874,
      "grad_norm": 0.4924088716506958,
      "learning_rate": 2.887963193118215e-07,
      "loss": 0.4228,
      "step": 60122
    },
    {
      "epoch": 1.8469265505483365,
      "grad_norm": 0.43465015292167664,
      "learning_rate": 2.886810254695849e-07,
      "loss": 0.5279,
      "step": 60123
    },
    {
      "epoch": 1.8469572696832857,
      "grad_norm": 0.43596571683883667,
      "learning_rate": 2.8856575430881053e-07,
      "loss": 0.394,
      "step": 60124
    },
    {
      "epoch": 1.8469879888182348,
      "grad_norm": 0.4356096088886261,
      "learning_rate": 2.884505058297693e-07,
      "loss": 0.4271,
      "step": 60125
    },
    {
      "epoch": 1.847018707953184,
      "grad_norm": 0.47127220034599304,
      "learning_rate": 2.883352800327299e-07,
      "loss": 0.5125,
      "step": 60126
    },
    {
      "epoch": 1.8470494270881332,
      "grad_norm": 0.41477081179618835,
      "learning_rate": 2.8822007691796214e-07,
      "loss": 0.5081,
      "step": 60127
    },
    {
      "epoch": 1.8470801462230824,
      "grad_norm": 0.42664870619773865,
      "learning_rate": 2.881048964857358e-07,
      "loss": 0.5313,
      "step": 60128
    },
    {
      "epoch": 1.8471108653580315,
      "grad_norm": 0.43659311532974243,
      "learning_rate": 2.879897387363173e-07,
      "loss": 0.5025,
      "step": 60129
    },
    {
      "epoch": 1.8471415844929808,
      "grad_norm": 0.39652013778686523,
      "learning_rate": 2.8787460366997645e-07,
      "loss": 0.4574,
      "step": 60130
    },
    {
      "epoch": 1.84717230362793,
      "grad_norm": 0.5080811977386475,
      "learning_rate": 2.877594912869841e-07,
      "loss": 0.4931,
      "step": 60131
    },
    {
      "epoch": 1.847203022762879,
      "grad_norm": 0.5737278461456299,
      "learning_rate": 2.8764440158760786e-07,
      "loss": 0.5054,
      "step": 60132
    },
    {
      "epoch": 1.8472337418978282,
      "grad_norm": 0.5260016918182373,
      "learning_rate": 2.875293345721153e-07,
      "loss": 0.5041,
      "step": 60133
    },
    {
      "epoch": 1.8472644610327773,
      "grad_norm": 0.4730563163757324,
      "learning_rate": 2.874142902407784e-07,
      "loss": 0.4591,
      "step": 60134
    },
    {
      "epoch": 1.8472951801677264,
      "grad_norm": 0.45503121614456177,
      "learning_rate": 2.872992685938603e-07,
      "loss": 0.4333,
      "step": 60135
    },
    {
      "epoch": 1.8473258993026755,
      "grad_norm": 0.46124473214149475,
      "learning_rate": 2.8718426963163626e-07,
      "loss": 0.447,
      "step": 60136
    },
    {
      "epoch": 1.8473566184376247,
      "grad_norm": 0.4477991759777069,
      "learning_rate": 2.870692933543695e-07,
      "loss": 0.5164,
      "step": 60137
    },
    {
      "epoch": 1.847387337572574,
      "grad_norm": 0.4237973392009735,
      "learning_rate": 2.869543397623331e-07,
      "loss": 0.4383,
      "step": 60138
    },
    {
      "epoch": 1.8474180567075231,
      "grad_norm": 0.46934759616851807,
      "learning_rate": 2.8683940885579134e-07,
      "loss": 0.4397,
      "step": 60139
    },
    {
      "epoch": 1.8474487758424722,
      "grad_norm": 0.41577568650245667,
      "learning_rate": 2.86724500635015e-07,
      "loss": 0.4215,
      "step": 60140
    },
    {
      "epoch": 1.8474794949774216,
      "grad_norm": 0.41333213448524475,
      "learning_rate": 2.8660961510027174e-07,
      "loss": 0.5311,
      "step": 60141
    },
    {
      "epoch": 1.8475102141123707,
      "grad_norm": 0.4262547492980957,
      "learning_rate": 2.864947522518302e-07,
      "loss": 0.4507,
      "step": 60142
    },
    {
      "epoch": 1.8475409332473198,
      "grad_norm": 0.42475730180740356,
      "learning_rate": 2.863799120899591e-07,
      "loss": 0.4519,
      "step": 60143
    },
    {
      "epoch": 1.847571652382269,
      "grad_norm": 0.4043806493282318,
      "learning_rate": 2.862650946149237e-07,
      "loss": 0.4917,
      "step": 60144
    },
    {
      "epoch": 1.847602371517218,
      "grad_norm": 0.41575780510902405,
      "learning_rate": 2.8615029982699715e-07,
      "loss": 0.4603,
      "step": 60145
    },
    {
      "epoch": 1.8476330906521672,
      "grad_norm": 0.4102652668952942,
      "learning_rate": 2.8603552772644374e-07,
      "loss": 0.4508,
      "step": 60146
    },
    {
      "epoch": 1.8476638097871163,
      "grad_norm": 0.42904242873191833,
      "learning_rate": 2.8592077831353425e-07,
      "loss": 0.4319,
      "step": 60147
    },
    {
      "epoch": 1.8476945289220654,
      "grad_norm": 0.40535810589790344,
      "learning_rate": 2.858060515885341e-07,
      "loss": 0.3892,
      "step": 60148
    },
    {
      "epoch": 1.8477252480570148,
      "grad_norm": 0.4306252598762512,
      "learning_rate": 2.8569134755171314e-07,
      "loss": 0.4533,
      "step": 60149
    },
    {
      "epoch": 1.8477559671919639,
      "grad_norm": 0.527693510055542,
      "learning_rate": 2.855766662033366e-07,
      "loss": 0.5321,
      "step": 60150
    },
    {
      "epoch": 1.847786686326913,
      "grad_norm": 0.44966644048690796,
      "learning_rate": 2.8546200754367645e-07,
      "loss": 0.5171,
      "step": 60151
    },
    {
      "epoch": 1.8478174054618624,
      "grad_norm": 0.42359137535095215,
      "learning_rate": 2.853473715729971e-07,
      "loss": 0.5526,
      "step": 60152
    },
    {
      "epoch": 1.8478481245968115,
      "grad_norm": 0.42968881130218506,
      "learning_rate": 2.85232758291567e-07,
      "loss": 0.5417,
      "step": 60153
    },
    {
      "epoch": 1.8478788437317606,
      "grad_norm": 0.41972237825393677,
      "learning_rate": 2.8511816769965506e-07,
      "loss": 0.5687,
      "step": 60154
    },
    {
      "epoch": 1.8479095628667097,
      "grad_norm": 0.4588131904602051,
      "learning_rate": 2.850035997975287e-07,
      "loss": 0.4143,
      "step": 60155
    },
    {
      "epoch": 1.8479402820016588,
      "grad_norm": 0.4024978578090668,
      "learning_rate": 2.8488905458545436e-07,
      "loss": 0.4416,
      "step": 60156
    },
    {
      "epoch": 1.847971001136608,
      "grad_norm": 0.436128169298172,
      "learning_rate": 2.8477453206369963e-07,
      "loss": 0.4903,
      "step": 60157
    },
    {
      "epoch": 1.848001720271557,
      "grad_norm": 0.48256367444992065,
      "learning_rate": 2.846600322325321e-07,
      "loss": 0.4792,
      "step": 60158
    },
    {
      "epoch": 1.8480324394065062,
      "grad_norm": 0.3884843587875366,
      "learning_rate": 2.8454555509222157e-07,
      "loss": 0.3991,
      "step": 60159
    },
    {
      "epoch": 1.8480631585414553,
      "grad_norm": 0.44653064012527466,
      "learning_rate": 2.8443110064303113e-07,
      "loss": 0.4414,
      "step": 60160
    },
    {
      "epoch": 1.8480938776764047,
      "grad_norm": 0.5302306413650513,
      "learning_rate": 2.843166688852328e-07,
      "loss": 0.3595,
      "step": 60161
    },
    {
      "epoch": 1.8481245968113538,
      "grad_norm": 0.48544690012931824,
      "learning_rate": 2.8420225981908854e-07,
      "loss": 0.4334,
      "step": 60162
    },
    {
      "epoch": 1.8481553159463031,
      "grad_norm": 0.4352833330631256,
      "learning_rate": 2.8408787344486934e-07,
      "loss": 0.395,
      "step": 60163
    },
    {
      "epoch": 1.8481860350812522,
      "grad_norm": 0.4616391062736511,
      "learning_rate": 2.839735097628427e-07,
      "loss": 0.4438,
      "step": 60164
    },
    {
      "epoch": 1.8482167542162014,
      "grad_norm": 0.43033504486083984,
      "learning_rate": 2.838591687732739e-07,
      "loss": 0.4578,
      "step": 60165
    },
    {
      "epoch": 1.8482474733511505,
      "grad_norm": 0.4234578311443329,
      "learning_rate": 2.837448504764295e-07,
      "loss": 0.4815,
      "step": 60166
    },
    {
      "epoch": 1.8482781924860996,
      "grad_norm": 0.4016643762588501,
      "learning_rate": 2.836305548725782e-07,
      "loss": 0.4918,
      "step": 60167
    },
    {
      "epoch": 1.8483089116210487,
      "grad_norm": 0.3879360556602478,
      "learning_rate": 2.8351628196198744e-07,
      "loss": 0.4397,
      "step": 60168
    },
    {
      "epoch": 1.8483396307559978,
      "grad_norm": 0.4245014786720276,
      "learning_rate": 2.8340203174492267e-07,
      "loss": 0.4572,
      "step": 60169
    },
    {
      "epoch": 1.848370349890947,
      "grad_norm": 0.38554343581199646,
      "learning_rate": 2.832878042216514e-07,
      "loss": 0.4891,
      "step": 60170
    },
    {
      "epoch": 1.848401069025896,
      "grad_norm": 0.41940879821777344,
      "learning_rate": 2.831735993924378e-07,
      "loss": 0.4406,
      "step": 60171
    },
    {
      "epoch": 1.8484317881608454,
      "grad_norm": 0.4433443248271942,
      "learning_rate": 2.830594172575529e-07,
      "loss": 0.524,
      "step": 60172
    },
    {
      "epoch": 1.8484625072957945,
      "grad_norm": 0.4113331437110901,
      "learning_rate": 2.829452578172609e-07,
      "loss": 0.4529,
      "step": 60173
    },
    {
      "epoch": 1.8484932264307439,
      "grad_norm": 0.42646268010139465,
      "learning_rate": 2.828311210718293e-07,
      "loss": 0.4575,
      "step": 60174
    },
    {
      "epoch": 1.848523945565693,
      "grad_norm": 0.45753854513168335,
      "learning_rate": 2.827170070215235e-07,
      "loss": 0.4849,
      "step": 60175
    },
    {
      "epoch": 1.8485546647006421,
      "grad_norm": 0.5001382827758789,
      "learning_rate": 2.82602915666611e-07,
      "loss": 0.4602,
      "step": 60176
    },
    {
      "epoch": 1.8485853838355912,
      "grad_norm": 0.4542858898639679,
      "learning_rate": 2.8248884700735726e-07,
      "loss": 0.507,
      "step": 60177
    },
    {
      "epoch": 1.8486161029705404,
      "grad_norm": 0.4315352439880371,
      "learning_rate": 2.823748010440308e-07,
      "loss": 0.5301,
      "step": 60178
    },
    {
      "epoch": 1.8486468221054895,
      "grad_norm": 0.4372037649154663,
      "learning_rate": 2.8226077777689597e-07,
      "loss": 0.4662,
      "step": 60179
    },
    {
      "epoch": 1.8486775412404386,
      "grad_norm": 0.42389795184135437,
      "learning_rate": 2.821467772062203e-07,
      "loss": 0.3994,
      "step": 60180
    },
    {
      "epoch": 1.8487082603753877,
      "grad_norm": 0.4111458659172058,
      "learning_rate": 2.8203279933226803e-07,
      "loss": 0.4072,
      "step": 60181
    },
    {
      "epoch": 1.8487389795103368,
      "grad_norm": 0.4552856981754303,
      "learning_rate": 2.819188441553078e-07,
      "loss": 0.5036,
      "step": 60182
    },
    {
      "epoch": 1.8487696986452862,
      "grad_norm": 0.4257369041442871,
      "learning_rate": 2.818049116756061e-07,
      "loss": 0.3604,
      "step": 60183
    },
    {
      "epoch": 1.8488004177802353,
      "grad_norm": 0.4383047819137573,
      "learning_rate": 2.81691001893426e-07,
      "loss": 0.4632,
      "step": 60184
    },
    {
      "epoch": 1.8488311369151844,
      "grad_norm": 0.4358727037906647,
      "learning_rate": 2.815771148090363e-07,
      "loss": 0.4949,
      "step": 60185
    },
    {
      "epoch": 1.8488618560501338,
      "grad_norm": 0.46919670701026917,
      "learning_rate": 2.8146325042270106e-07,
      "loss": 0.5223,
      "step": 60186
    },
    {
      "epoch": 1.8488925751850829,
      "grad_norm": 0.49378466606140137,
      "learning_rate": 2.813494087346891e-07,
      "loss": 0.4908,
      "step": 60187
    },
    {
      "epoch": 1.848923294320032,
      "grad_norm": 0.3980731964111328,
      "learning_rate": 2.8123558974526234e-07,
      "loss": 0.4712,
      "step": 60188
    },
    {
      "epoch": 1.8489540134549811,
      "grad_norm": 0.46321171522140503,
      "learning_rate": 2.8112179345468836e-07,
      "loss": 0.4137,
      "step": 60189
    },
    {
      "epoch": 1.8489847325899302,
      "grad_norm": 0.42054805159568787,
      "learning_rate": 2.810080198632337e-07,
      "loss": 0.4802,
      "step": 60190
    },
    {
      "epoch": 1.8490154517248794,
      "grad_norm": 0.42307695746421814,
      "learning_rate": 2.8089426897116467e-07,
      "loss": 0.4195,
      "step": 60191
    },
    {
      "epoch": 1.8490461708598285,
      "grad_norm": 0.41048991680145264,
      "learning_rate": 2.8078054077874563e-07,
      "loss": 0.4986,
      "step": 60192
    },
    {
      "epoch": 1.8490768899947776,
      "grad_norm": 0.49258318543434143,
      "learning_rate": 2.8066683528624075e-07,
      "loss": 0.4615,
      "step": 60193
    },
    {
      "epoch": 1.849107609129727,
      "grad_norm": 0.44831418991088867,
      "learning_rate": 2.805531524939187e-07,
      "loss": 0.5141,
      "step": 60194
    },
    {
      "epoch": 1.849138328264676,
      "grad_norm": 0.4271920621395111,
      "learning_rate": 2.804394924020437e-07,
      "loss": 0.5663,
      "step": 60195
    },
    {
      "epoch": 1.8491690473996252,
      "grad_norm": 0.47224149107933044,
      "learning_rate": 2.8032585501088005e-07,
      "loss": 0.4821,
      "step": 60196
    },
    {
      "epoch": 1.8491997665345745,
      "grad_norm": 0.44526004791259766,
      "learning_rate": 2.802122403206964e-07,
      "loss": 0.5192,
      "step": 60197
    },
    {
      "epoch": 1.8492304856695236,
      "grad_norm": 0.41206544637680054,
      "learning_rate": 2.8009864833175246e-07,
      "loss": 0.4709,
      "step": 60198
    },
    {
      "epoch": 1.8492612048044728,
      "grad_norm": 0.42369985580444336,
      "learning_rate": 2.7998507904431814e-07,
      "loss": 0.4546,
      "step": 60199
    },
    {
      "epoch": 1.8492919239394219,
      "grad_norm": 0.42954739928245544,
      "learning_rate": 2.7987153245865874e-07,
      "loss": 0.5167,
      "step": 60200
    },
    {
      "epoch": 1.849322643074371,
      "grad_norm": 0.4569355547428131,
      "learning_rate": 2.797580085750373e-07,
      "loss": 0.4466,
      "step": 60201
    },
    {
      "epoch": 1.8493533622093201,
      "grad_norm": 0.44483813643455505,
      "learning_rate": 2.7964450739372153e-07,
      "loss": 0.5326,
      "step": 60202
    },
    {
      "epoch": 1.8493840813442692,
      "grad_norm": 0.4427047371864319,
      "learning_rate": 2.795310289149722e-07,
      "loss": 0.4757,
      "step": 60203
    },
    {
      "epoch": 1.8494148004792184,
      "grad_norm": 0.3921968638896942,
      "learning_rate": 2.7941757313905913e-07,
      "loss": 0.4335,
      "step": 60204
    },
    {
      "epoch": 1.8494455196141677,
      "grad_norm": 0.6832801103591919,
      "learning_rate": 2.793041400662444e-07,
      "loss": 0.4667,
      "step": 60205
    },
    {
      "epoch": 1.8494762387491168,
      "grad_norm": 0.4487471580505371,
      "learning_rate": 2.791907296967944e-07,
      "loss": 0.4857,
      "step": 60206
    },
    {
      "epoch": 1.849506957884066,
      "grad_norm": 0.39974528551101685,
      "learning_rate": 2.7907734203097115e-07,
      "loss": 0.5097,
      "step": 60207
    },
    {
      "epoch": 1.8495376770190153,
      "grad_norm": 0.4267398416996002,
      "learning_rate": 2.7896397706904333e-07,
      "loss": 0.4843,
      "step": 60208
    },
    {
      "epoch": 1.8495683961539644,
      "grad_norm": 0.43637269735336304,
      "learning_rate": 2.7885063481127403e-07,
      "loss": 0.5024,
      "step": 60209
    },
    {
      "epoch": 1.8495991152889135,
      "grad_norm": 0.4146829843521118,
      "learning_rate": 2.787373152579287e-07,
      "loss": 0.4042,
      "step": 60210
    },
    {
      "epoch": 1.8496298344238626,
      "grad_norm": 0.4390827715396881,
      "learning_rate": 2.7862401840927034e-07,
      "loss": 0.4519,
      "step": 60211
    },
    {
      "epoch": 1.8496605535588118,
      "grad_norm": 0.4606298506259918,
      "learning_rate": 2.7851074426556433e-07,
      "loss": 0.5264,
      "step": 60212
    },
    {
      "epoch": 1.8496912726937609,
      "grad_norm": 0.5080215930938721,
      "learning_rate": 2.7839749282707496e-07,
      "loss": 0.4477,
      "step": 60213
    },
    {
      "epoch": 1.84972199182871,
      "grad_norm": 0.42391401529312134,
      "learning_rate": 2.782842640940686e-07,
      "loss": 0.5202,
      "step": 60214
    },
    {
      "epoch": 1.8497527109636591,
      "grad_norm": 0.42190855741500854,
      "learning_rate": 2.781710580668073e-07,
      "loss": 0.414,
      "step": 60215
    },
    {
      "epoch": 1.8497834300986085,
      "grad_norm": 0.4456171989440918,
      "learning_rate": 2.7805787474555756e-07,
      "loss": 0.4068,
      "step": 60216
    },
    {
      "epoch": 1.8498141492335576,
      "grad_norm": 0.4364807903766632,
      "learning_rate": 2.779447141305813e-07,
      "loss": 0.4144,
      "step": 60217
    },
    {
      "epoch": 1.8498448683685067,
      "grad_norm": 0.413769394159317,
      "learning_rate": 2.7783157622214397e-07,
      "loss": 0.4522,
      "step": 60218
    },
    {
      "epoch": 1.849875587503456,
      "grad_norm": 0.527728796005249,
      "learning_rate": 2.777184610205119e-07,
      "loss": 0.4892,
      "step": 60219
    },
    {
      "epoch": 1.8499063066384052,
      "grad_norm": 0.40733975172042847,
      "learning_rate": 2.776053685259461e-07,
      "loss": 0.4511,
      "step": 60220
    },
    {
      "epoch": 1.8499370257733543,
      "grad_norm": 0.4133981466293335,
      "learning_rate": 2.774922987387119e-07,
      "loss": 0.4049,
      "step": 60221
    },
    {
      "epoch": 1.8499677449083034,
      "grad_norm": 0.4230853319168091,
      "learning_rate": 2.773792516590734e-07,
      "loss": 0.4486,
      "step": 60222
    },
    {
      "epoch": 1.8499984640432525,
      "grad_norm": 0.41178587079048157,
      "learning_rate": 2.77266227287295e-07,
      "loss": 0.4629,
      "step": 60223
    },
    {
      "epoch": 1.8500291831782016,
      "grad_norm": 0.4527644217014313,
      "learning_rate": 2.771532256236398e-07,
      "loss": 0.4737,
      "step": 60224
    },
    {
      "epoch": 1.8500599023131508,
      "grad_norm": 0.43222668766975403,
      "learning_rate": 2.7704024666837304e-07,
      "loss": 0.4704,
      "step": 60225
    },
    {
      "epoch": 1.8500906214480999,
      "grad_norm": 0.41126886010169983,
      "learning_rate": 2.769272904217568e-07,
      "loss": 0.4326,
      "step": 60226
    },
    {
      "epoch": 1.8501213405830492,
      "grad_norm": 0.42449986934661865,
      "learning_rate": 2.768143568840576e-07,
      "loss": 0.4366,
      "step": 60227
    },
    {
      "epoch": 1.8501520597179983,
      "grad_norm": 0.5164862275123596,
      "learning_rate": 2.767014460555362e-07,
      "loss": 0.4007,
      "step": 60228
    },
    {
      "epoch": 1.8501827788529475,
      "grad_norm": 0.44108572602272034,
      "learning_rate": 2.76588557936458e-07,
      "loss": 0.5093,
      "step": 60229
    },
    {
      "epoch": 1.8502134979878968,
      "grad_norm": 0.5591827630996704,
      "learning_rate": 2.7647569252708614e-07,
      "loss": 0.4902,
      "step": 60230
    },
    {
      "epoch": 1.850244217122846,
      "grad_norm": 0.4198637902736664,
      "learning_rate": 2.763628498276849e-07,
      "loss": 0.5173,
      "step": 60231
    },
    {
      "epoch": 1.850274936257795,
      "grad_norm": 0.41384685039520264,
      "learning_rate": 2.7625002983851736e-07,
      "loss": 0.4054,
      "step": 60232
    },
    {
      "epoch": 1.8503056553927442,
      "grad_norm": 0.45699381828308105,
      "learning_rate": 2.761372325598466e-07,
      "loss": 0.4618,
      "step": 60233
    },
    {
      "epoch": 1.8503363745276933,
      "grad_norm": 0.4699280858039856,
      "learning_rate": 2.760244579919358e-07,
      "loss": 0.4808,
      "step": 60234
    },
    {
      "epoch": 1.8503670936626424,
      "grad_norm": 0.4354268014431,
      "learning_rate": 2.759117061350491e-07,
      "loss": 0.5725,
      "step": 60235
    },
    {
      "epoch": 1.8503978127975915,
      "grad_norm": 0.47866755723953247,
      "learning_rate": 2.757989769894509e-07,
      "loss": 0.3779,
      "step": 60236
    },
    {
      "epoch": 1.8504285319325406,
      "grad_norm": 0.4125123918056488,
      "learning_rate": 2.7568627055540196e-07,
      "loss": 0.4762,
      "step": 60237
    },
    {
      "epoch": 1.85045925106749,
      "grad_norm": 0.4950864613056183,
      "learning_rate": 2.7557358683316883e-07,
      "loss": 0.4614,
      "step": 60238
    },
    {
      "epoch": 1.850489970202439,
      "grad_norm": 0.4400480091571808,
      "learning_rate": 2.754609258230101e-07,
      "loss": 0.5646,
      "step": 60239
    },
    {
      "epoch": 1.8505206893373882,
      "grad_norm": 0.5030046701431274,
      "learning_rate": 2.753482875251934e-07,
      "loss": 0.4409,
      "step": 60240
    },
    {
      "epoch": 1.8505514084723376,
      "grad_norm": 0.44180774688720703,
      "learning_rate": 2.7523567193997955e-07,
      "loss": 0.5202,
      "step": 60241
    },
    {
      "epoch": 1.8505821276072867,
      "grad_norm": 0.4516802430152893,
      "learning_rate": 2.751230790676329e-07,
      "loss": 0.4483,
      "step": 60242
    },
    {
      "epoch": 1.8506128467422358,
      "grad_norm": 0.42286980152130127,
      "learning_rate": 2.750105089084143e-07,
      "loss": 0.5302,
      "step": 60243
    },
    {
      "epoch": 1.850643565877185,
      "grad_norm": 0.41362127661705017,
      "learning_rate": 2.7489796146258684e-07,
      "loss": 0.4276,
      "step": 60244
    },
    {
      "epoch": 1.850674285012134,
      "grad_norm": 0.4375510811805725,
      "learning_rate": 2.747854367304159e-07,
      "loss": 0.4748,
      "step": 60245
    },
    {
      "epoch": 1.8507050041470832,
      "grad_norm": 0.44708332419395447,
      "learning_rate": 2.746729347121624e-07,
      "loss": 0.4244,
      "step": 60246
    },
    {
      "epoch": 1.8507357232820323,
      "grad_norm": 0.42319169640541077,
      "learning_rate": 2.745604554080894e-07,
      "loss": 0.4774,
      "step": 60247
    },
    {
      "epoch": 1.8507664424169814,
      "grad_norm": 0.38259389996528625,
      "learning_rate": 2.7444799881846005e-07,
      "loss": 0.5202,
      "step": 60248
    },
    {
      "epoch": 1.8507971615519307,
      "grad_norm": 0.41100984811782837,
      "learning_rate": 2.743355649435353e-07,
      "loss": 0.4548,
      "step": 60249
    },
    {
      "epoch": 1.8508278806868799,
      "grad_norm": 0.4435177445411682,
      "learning_rate": 2.7422315378358153e-07,
      "loss": 0.4978,
      "step": 60250
    },
    {
      "epoch": 1.850858599821829,
      "grad_norm": 0.43258577585220337,
      "learning_rate": 2.741107653388564e-07,
      "loss": 0.5146,
      "step": 60251
    },
    {
      "epoch": 1.8508893189567783,
      "grad_norm": 0.4749447703361511,
      "learning_rate": 2.7399839960962624e-07,
      "loss": 0.4322,
      "step": 60252
    },
    {
      "epoch": 1.8509200380917274,
      "grad_norm": 0.43535125255584717,
      "learning_rate": 2.7388605659615096e-07,
      "loss": 0.4279,
      "step": 60253
    },
    {
      "epoch": 1.8509507572266766,
      "grad_norm": 0.45070528984069824,
      "learning_rate": 2.7377373629869473e-07,
      "loss": 0.4141,
      "step": 60254
    },
    {
      "epoch": 1.8509814763616257,
      "grad_norm": 0.4772712290287018,
      "learning_rate": 2.736614387175196e-07,
      "loss": 0.5879,
      "step": 60255
    },
    {
      "epoch": 1.8510121954965748,
      "grad_norm": 0.46111685037612915,
      "learning_rate": 2.735491638528875e-07,
      "loss": 0.4211,
      "step": 60256
    },
    {
      "epoch": 1.851042914631524,
      "grad_norm": 0.4495666027069092,
      "learning_rate": 2.734369117050595e-07,
      "loss": 0.5243,
      "step": 60257
    },
    {
      "epoch": 1.851073633766473,
      "grad_norm": 0.4118403196334839,
      "learning_rate": 2.7332468227429966e-07,
      "loss": 0.3649,
      "step": 60258
    },
    {
      "epoch": 1.8511043529014222,
      "grad_norm": 0.4644964039325714,
      "learning_rate": 2.7321247556087004e-07,
      "loss": 0.5133,
      "step": 60259
    },
    {
      "epoch": 1.8511350720363715,
      "grad_norm": 0.4410124719142914,
      "learning_rate": 2.731002915650305e-07,
      "loss": 0.4301,
      "step": 60260
    },
    {
      "epoch": 1.8511657911713206,
      "grad_norm": 0.4673911929130554,
      "learning_rate": 2.729881302870452e-07,
      "loss": 0.3514,
      "step": 60261
    },
    {
      "epoch": 1.8511965103062697,
      "grad_norm": 0.5025898814201355,
      "learning_rate": 2.7287599172717504e-07,
      "loss": 0.4373,
      "step": 60262
    },
    {
      "epoch": 1.851227229441219,
      "grad_norm": 0.48149374127388,
      "learning_rate": 2.727638758856832e-07,
      "loss": 0.4161,
      "step": 60263
    },
    {
      "epoch": 1.8512579485761682,
      "grad_norm": 0.41728970408439636,
      "learning_rate": 2.7265178276283057e-07,
      "loss": 0.4634,
      "step": 60264
    },
    {
      "epoch": 1.8512886677111173,
      "grad_norm": 0.40832239389419556,
      "learning_rate": 2.725397123588791e-07,
      "loss": 0.4374,
      "step": 60265
    },
    {
      "epoch": 1.8513193868460665,
      "grad_norm": 0.4924507439136505,
      "learning_rate": 2.724276646740887e-07,
      "loss": 0.5277,
      "step": 60266
    },
    {
      "epoch": 1.8513501059810156,
      "grad_norm": 0.41954323649406433,
      "learning_rate": 2.7231563970872565e-07,
      "loss": 0.4817,
      "step": 60267
    },
    {
      "epoch": 1.8513808251159647,
      "grad_norm": 0.4746108055114746,
      "learning_rate": 2.722036374630466e-07,
      "loss": 0.4309,
      "step": 60268
    },
    {
      "epoch": 1.8514115442509138,
      "grad_norm": 0.4070848822593689,
      "learning_rate": 2.7209165793731673e-07,
      "loss": 0.4582,
      "step": 60269
    },
    {
      "epoch": 1.851442263385863,
      "grad_norm": 0.43500563502311707,
      "learning_rate": 2.7197970113179484e-07,
      "loss": 0.4369,
      "step": 60270
    },
    {
      "epoch": 1.851472982520812,
      "grad_norm": 0.420828253030777,
      "learning_rate": 2.71867767046744e-07,
      "loss": 0.4604,
      "step": 60271
    },
    {
      "epoch": 1.8515037016557614,
      "grad_norm": 0.4279915392398834,
      "learning_rate": 2.7175585568242733e-07,
      "loss": 0.5044,
      "step": 60272
    },
    {
      "epoch": 1.8515344207907105,
      "grad_norm": 0.4389362037181854,
      "learning_rate": 2.7164396703910244e-07,
      "loss": 0.4059,
      "step": 60273
    },
    {
      "epoch": 1.8515651399256599,
      "grad_norm": 0.41989317536354065,
      "learning_rate": 2.7153210111703353e-07,
      "loss": 0.4288,
      "step": 60274
    },
    {
      "epoch": 1.851595859060609,
      "grad_norm": 0.4311622381210327,
      "learning_rate": 2.714202579164793e-07,
      "loss": 0.4117,
      "step": 60275
    },
    {
      "epoch": 1.851626578195558,
      "grad_norm": 0.4264622628688812,
      "learning_rate": 2.7130843743770396e-07,
      "loss": 0.4106,
      "step": 60276
    },
    {
      "epoch": 1.8516572973305072,
      "grad_norm": 0.4165151119232178,
      "learning_rate": 2.711966396809662e-07,
      "loss": 0.4546,
      "step": 60277
    },
    {
      "epoch": 1.8516880164654563,
      "grad_norm": 0.4426136016845703,
      "learning_rate": 2.7108486464652916e-07,
      "loss": 0.4345,
      "step": 60278
    },
    {
      "epoch": 1.8517187356004055,
      "grad_norm": 0.42602309584617615,
      "learning_rate": 2.709731123346526e-07,
      "loss": 0.4694,
      "step": 60279
    },
    {
      "epoch": 1.8517494547353546,
      "grad_norm": 0.45326438546180725,
      "learning_rate": 2.708613827455975e-07,
      "loss": 0.4953,
      "step": 60280
    },
    {
      "epoch": 1.8517801738703037,
      "grad_norm": 0.5303114652633667,
      "learning_rate": 2.7074967587962466e-07,
      "loss": 0.4656,
      "step": 60281
    },
    {
      "epoch": 1.8518108930052528,
      "grad_norm": 0.40242788195610046,
      "learning_rate": 2.706379917369961e-07,
      "loss": 0.4512,
      "step": 60282
    },
    {
      "epoch": 1.8518416121402022,
      "grad_norm": 0.45462992787361145,
      "learning_rate": 2.705263303179717e-07,
      "loss": 0.487,
      "step": 60283
    },
    {
      "epoch": 1.8518723312751513,
      "grad_norm": 0.4330115020275116,
      "learning_rate": 2.7041469162281234e-07,
      "loss": 0.4216,
      "step": 60284
    },
    {
      "epoch": 1.8519030504101006,
      "grad_norm": 0.3820751905441284,
      "learning_rate": 2.7030307565177885e-07,
      "loss": 0.4338,
      "step": 60285
    },
    {
      "epoch": 1.8519337695450497,
      "grad_norm": 0.47860056161880493,
      "learning_rate": 2.7019148240513325e-07,
      "loss": 0.4292,
      "step": 60286
    },
    {
      "epoch": 1.8519644886799989,
      "grad_norm": 0.4302225708961487,
      "learning_rate": 2.7007991188313433e-07,
      "loss": 0.4815,
      "step": 60287
    },
    {
      "epoch": 1.851995207814948,
      "grad_norm": 0.6703494191169739,
      "learning_rate": 2.699683640860429e-07,
      "loss": 0.4459,
      "step": 60288
    },
    {
      "epoch": 1.852025926949897,
      "grad_norm": 0.4435778856277466,
      "learning_rate": 2.6985683901411986e-07,
      "loss": 0.4343,
      "step": 60289
    },
    {
      "epoch": 1.8520566460848462,
      "grad_norm": 0.44547080993652344,
      "learning_rate": 2.6974533666762614e-07,
      "loss": 0.5263,
      "step": 60290
    },
    {
      "epoch": 1.8520873652197953,
      "grad_norm": 0.4822860062122345,
      "learning_rate": 2.696338570468215e-07,
      "loss": 0.444,
      "step": 60291
    },
    {
      "epoch": 1.8521180843547445,
      "grad_norm": 0.41674575209617615,
      "learning_rate": 2.6952240015196694e-07,
      "loss": 0.4706,
      "step": 60292
    },
    {
      "epoch": 1.8521488034896936,
      "grad_norm": 0.433808296918869,
      "learning_rate": 2.6941096598332217e-07,
      "loss": 0.5004,
      "step": 60293
    },
    {
      "epoch": 1.852179522624643,
      "grad_norm": 0.3920155465602875,
      "learning_rate": 2.69299554541147e-07,
      "loss": 0.3935,
      "step": 60294
    },
    {
      "epoch": 1.852210241759592,
      "grad_norm": 0.43345195055007935,
      "learning_rate": 2.691881658257034e-07,
      "loss": 0.5235,
      "step": 60295
    },
    {
      "epoch": 1.8522409608945412,
      "grad_norm": 0.40848487615585327,
      "learning_rate": 2.690767998372501e-07,
      "loss": 0.3686,
      "step": 60296
    },
    {
      "epoch": 1.8522716800294905,
      "grad_norm": 0.4461740255355835,
      "learning_rate": 2.6896545657604687e-07,
      "loss": 0.4877,
      "step": 60297
    },
    {
      "epoch": 1.8523023991644396,
      "grad_norm": 0.40276414155960083,
      "learning_rate": 2.6885413604235466e-07,
      "loss": 0.4969,
      "step": 60298
    },
    {
      "epoch": 1.8523331182993887,
      "grad_norm": 0.44068896770477295,
      "learning_rate": 2.687428382364343e-07,
      "loss": 0.4679,
      "step": 60299
    },
    {
      "epoch": 1.8523638374343379,
      "grad_norm": 0.45444121956825256,
      "learning_rate": 2.6863156315854344e-07,
      "loss": 0.4671,
      "step": 60300
    },
    {
      "epoch": 1.852394556569287,
      "grad_norm": 0.4188274145126343,
      "learning_rate": 2.6852031080894514e-07,
      "loss": 0.5289,
      "step": 60301
    },
    {
      "epoch": 1.852425275704236,
      "grad_norm": 0.501861572265625,
      "learning_rate": 2.6840908118789367e-07,
      "loss": 0.4882,
      "step": 60302
    },
    {
      "epoch": 1.8524559948391852,
      "grad_norm": 0.42672237753868103,
      "learning_rate": 2.682978742956555e-07,
      "loss": 0.4641,
      "step": 60303
    },
    {
      "epoch": 1.8524867139741343,
      "grad_norm": 0.40263697504997253,
      "learning_rate": 2.681866901324859e-07,
      "loss": 0.4949,
      "step": 60304
    },
    {
      "epoch": 1.8525174331090837,
      "grad_norm": 0.4453442692756653,
      "learning_rate": 2.6807552869864805e-07,
      "loss": 0.5029,
      "step": 60305
    },
    {
      "epoch": 1.8525481522440328,
      "grad_norm": 0.399146169424057,
      "learning_rate": 2.679643899943973e-07,
      "loss": 0.499,
      "step": 60306
    },
    {
      "epoch": 1.852578871378982,
      "grad_norm": 0.48746639490127563,
      "learning_rate": 2.678532740199957e-07,
      "loss": 0.5058,
      "step": 60307
    },
    {
      "epoch": 1.8526095905139313,
      "grad_norm": 0.4465089440345764,
      "learning_rate": 2.6774218077570193e-07,
      "loss": 0.4778,
      "step": 60308
    },
    {
      "epoch": 1.8526403096488804,
      "grad_norm": 0.4082576036453247,
      "learning_rate": 2.676311102617768e-07,
      "loss": 0.4658,
      "step": 60309
    },
    {
      "epoch": 1.8526710287838295,
      "grad_norm": 0.38800665736198425,
      "learning_rate": 2.675200624784791e-07,
      "loss": 0.4936,
      "step": 60310
    },
    {
      "epoch": 1.8527017479187786,
      "grad_norm": 0.4668174386024475,
      "learning_rate": 2.674090374260674e-07,
      "loss": 0.5251,
      "step": 60311
    },
    {
      "epoch": 1.8527324670537277,
      "grad_norm": 0.44519442319869995,
      "learning_rate": 2.672980351048027e-07,
      "loss": 0.4761,
      "step": 60312
    },
    {
      "epoch": 1.8527631861886769,
      "grad_norm": 0.4001055657863617,
      "learning_rate": 2.671870555149414e-07,
      "loss": 0.4918,
      "step": 60313
    },
    {
      "epoch": 1.852793905323626,
      "grad_norm": 0.5310249328613281,
      "learning_rate": 2.6707609865674664e-07,
      "loss": 0.5644,
      "step": 60314
    },
    {
      "epoch": 1.852824624458575,
      "grad_norm": 0.4386398494243622,
      "learning_rate": 2.669651645304738e-07,
      "loss": 0.3841,
      "step": 60315
    },
    {
      "epoch": 1.8528553435935244,
      "grad_norm": 0.4205549657344818,
      "learning_rate": 2.668542531363838e-07,
      "loss": 0.5054,
      "step": 60316
    },
    {
      "epoch": 1.8528860627284736,
      "grad_norm": 0.43460166454315186,
      "learning_rate": 2.667433644747353e-07,
      "loss": 0.4499,
      "step": 60317
    },
    {
      "epoch": 1.8529167818634227,
      "grad_norm": 0.4581429660320282,
      "learning_rate": 2.666324985457891e-07,
      "loss": 0.5395,
      "step": 60318
    },
    {
      "epoch": 1.852947500998372,
      "grad_norm": 0.41624441742897034,
      "learning_rate": 2.665216553498007e-07,
      "loss": 0.465,
      "step": 60319
    },
    {
      "epoch": 1.8529782201333211,
      "grad_norm": 0.4242900013923645,
      "learning_rate": 2.664108348870309e-07,
      "loss": 0.503,
      "step": 60320
    },
    {
      "epoch": 1.8530089392682703,
      "grad_norm": 0.45003288984298706,
      "learning_rate": 2.6630003715773847e-07,
      "loss": 0.4702,
      "step": 60321
    },
    {
      "epoch": 1.8530396584032194,
      "grad_norm": 0.3875015676021576,
      "learning_rate": 2.661892621621831e-07,
      "loss": 0.4078,
      "step": 60322
    },
    {
      "epoch": 1.8530703775381685,
      "grad_norm": 0.41310563683509827,
      "learning_rate": 2.6607850990062134e-07,
      "loss": 0.5017,
      "step": 60323
    },
    {
      "epoch": 1.8531010966731176,
      "grad_norm": 0.4604231119155884,
      "learning_rate": 2.659677803733129e-07,
      "loss": 0.4285,
      "step": 60324
    },
    {
      "epoch": 1.8531318158080667,
      "grad_norm": 0.39120250940322876,
      "learning_rate": 2.658570735805166e-07,
      "loss": 0.4303,
      "step": 60325
    },
    {
      "epoch": 1.8531625349430159,
      "grad_norm": 0.41264912486076355,
      "learning_rate": 2.65746389522491e-07,
      "loss": 0.4319,
      "step": 60326
    },
    {
      "epoch": 1.8531932540779652,
      "grad_norm": 0.4590623080730438,
      "learning_rate": 2.656357281994959e-07,
      "loss": 0.532,
      "step": 60327
    },
    {
      "epoch": 1.8532239732129143,
      "grad_norm": 0.4452674090862274,
      "learning_rate": 2.655250896117878e-07,
      "loss": 0.4293,
      "step": 60328
    },
    {
      "epoch": 1.8532546923478634,
      "grad_norm": 0.42766323685646057,
      "learning_rate": 2.6541447375962425e-07,
      "loss": 0.4397,
      "step": 60329
    },
    {
      "epoch": 1.8532854114828128,
      "grad_norm": 0.46924763917922974,
      "learning_rate": 2.6530388064326617e-07,
      "loss": 0.483,
      "step": 60330
    },
    {
      "epoch": 1.853316130617762,
      "grad_norm": 0.4933271110057831,
      "learning_rate": 2.651933102629711e-07,
      "loss": 0.4655,
      "step": 60331
    },
    {
      "epoch": 1.853346849752711,
      "grad_norm": 0.5129576325416565,
      "learning_rate": 2.650827626189967e-07,
      "loss": 0.452,
      "step": 60332
    },
    {
      "epoch": 1.8533775688876601,
      "grad_norm": 0.41876915097236633,
      "learning_rate": 2.649722377116004e-07,
      "loss": 0.4201,
      "step": 60333
    },
    {
      "epoch": 1.8534082880226093,
      "grad_norm": 0.4217212200164795,
      "learning_rate": 2.6486173554104213e-07,
      "loss": 0.4561,
      "step": 60334
    },
    {
      "epoch": 1.8534390071575584,
      "grad_norm": 0.5368242859840393,
      "learning_rate": 2.647512561075805e-07,
      "loss": 0.4258,
      "step": 60335
    },
    {
      "epoch": 1.8534697262925075,
      "grad_norm": 0.4647400975227356,
      "learning_rate": 2.646407994114697e-07,
      "loss": 0.5151,
      "step": 60336
    },
    {
      "epoch": 1.8535004454274566,
      "grad_norm": 0.4076851010322571,
      "learning_rate": 2.6453036545297295e-07,
      "loss": 0.4578,
      "step": 60337
    },
    {
      "epoch": 1.853531164562406,
      "grad_norm": 0.49500444531440735,
      "learning_rate": 2.644199542323422e-07,
      "loss": 0.4226,
      "step": 60338
    },
    {
      "epoch": 1.853561883697355,
      "grad_norm": 0.5097509622573853,
      "learning_rate": 2.6430956574984065e-07,
      "loss": 0.4169,
      "step": 60339
    },
    {
      "epoch": 1.8535926028323042,
      "grad_norm": 0.5226637125015259,
      "learning_rate": 2.641992000057236e-07,
      "loss": 0.4374,
      "step": 60340
    },
    {
      "epoch": 1.8536233219672535,
      "grad_norm": 0.4160458445549011,
      "learning_rate": 2.640888570002509e-07,
      "loss": 0.4341,
      "step": 60341
    },
    {
      "epoch": 1.8536540411022027,
      "grad_norm": 0.4250342845916748,
      "learning_rate": 2.639785367336767e-07,
      "loss": 0.5323,
      "step": 60342
    },
    {
      "epoch": 1.8536847602371518,
      "grad_norm": 0.4492734968662262,
      "learning_rate": 2.638682392062597e-07,
      "loss": 0.4199,
      "step": 60343
    },
    {
      "epoch": 1.853715479372101,
      "grad_norm": 0.42806723713874817,
      "learning_rate": 2.6375796441825973e-07,
      "loss": 0.4562,
      "step": 60344
    },
    {
      "epoch": 1.85374619850705,
      "grad_norm": 0.4179575443267822,
      "learning_rate": 2.6364771236993324e-07,
      "loss": 0.4848,
      "step": 60345
    },
    {
      "epoch": 1.8537769176419991,
      "grad_norm": 0.4200654923915863,
      "learning_rate": 2.635374830615378e-07,
      "loss": 0.4017,
      "step": 60346
    },
    {
      "epoch": 1.8538076367769483,
      "grad_norm": 0.4326289892196655,
      "learning_rate": 2.6342727649332876e-07,
      "loss": 0.4492,
      "step": 60347
    },
    {
      "epoch": 1.8538383559118974,
      "grad_norm": 0.46937310695648193,
      "learning_rate": 2.6331709266556703e-07,
      "loss": 0.4648,
      "step": 60348
    },
    {
      "epoch": 1.8538690750468467,
      "grad_norm": 0.49134740233421326,
      "learning_rate": 2.6320693157850685e-07,
      "loss": 0.5303,
      "step": 60349
    },
    {
      "epoch": 1.8538997941817958,
      "grad_norm": 0.5595312714576721,
      "learning_rate": 2.630967932324091e-07,
      "loss": 0.4193,
      "step": 60350
    },
    {
      "epoch": 1.853930513316745,
      "grad_norm": 0.4123189449310303,
      "learning_rate": 2.629866776275269e-07,
      "loss": 0.4217,
      "step": 60351
    },
    {
      "epoch": 1.8539612324516943,
      "grad_norm": 0.45679184794425964,
      "learning_rate": 2.6287658476411904e-07,
      "loss": 0.4715,
      "step": 60352
    },
    {
      "epoch": 1.8539919515866434,
      "grad_norm": 0.4348461925983429,
      "learning_rate": 2.627665146424441e-07,
      "loss": 0.454,
      "step": 60353
    },
    {
      "epoch": 1.8540226707215925,
      "grad_norm": 0.40181976556777954,
      "learning_rate": 2.626564672627585e-07,
      "loss": 0.4688,
      "step": 60354
    },
    {
      "epoch": 1.8540533898565417,
      "grad_norm": 0.4702531099319458,
      "learning_rate": 2.625464426253177e-07,
      "loss": 0.5388,
      "step": 60355
    },
    {
      "epoch": 1.8540841089914908,
      "grad_norm": 0.4428499639034271,
      "learning_rate": 2.624364407303792e-07,
      "loss": 0.492,
      "step": 60356
    },
    {
      "epoch": 1.85411482812644,
      "grad_norm": 0.4510157108306885,
      "learning_rate": 2.6232646157820065e-07,
      "loss": 0.401,
      "step": 60357
    },
    {
      "epoch": 1.854145547261389,
      "grad_norm": 0.4296210706233978,
      "learning_rate": 2.622165051690406e-07,
      "loss": 0.5201,
      "step": 60358
    },
    {
      "epoch": 1.8541762663963381,
      "grad_norm": 0.41686728596687317,
      "learning_rate": 2.6210657150315235e-07,
      "loss": 0.4712,
      "step": 60359
    },
    {
      "epoch": 1.8542069855312875,
      "grad_norm": 0.4295679032802582,
      "learning_rate": 2.6199666058079445e-07,
      "loss": 0.5191,
      "step": 60360
    },
    {
      "epoch": 1.8542377046662366,
      "grad_norm": 0.43423476815223694,
      "learning_rate": 2.618867724022234e-07,
      "loss": 0.452,
      "step": 60361
    },
    {
      "epoch": 1.8542684238011857,
      "grad_norm": 0.4502454102039337,
      "learning_rate": 2.6177690696769677e-07,
      "loss": 0.4697,
      "step": 60362
    },
    {
      "epoch": 1.854299142936135,
      "grad_norm": 0.4529804587364197,
      "learning_rate": 2.616670642774688e-07,
      "loss": 0.486,
      "step": 60363
    },
    {
      "epoch": 1.8543298620710842,
      "grad_norm": 0.4117615818977356,
      "learning_rate": 2.615572443317982e-07,
      "loss": 0.3958,
      "step": 60364
    },
    {
      "epoch": 1.8543605812060333,
      "grad_norm": 0.453323632478714,
      "learning_rate": 2.614474471309414e-07,
      "loss": 0.4254,
      "step": 60365
    },
    {
      "epoch": 1.8543913003409824,
      "grad_norm": 0.4734463393688202,
      "learning_rate": 2.6133767267515266e-07,
      "loss": 0.4974,
      "step": 60366
    },
    {
      "epoch": 1.8544220194759315,
      "grad_norm": 0.4309847354888916,
      "learning_rate": 2.6122792096469174e-07,
      "loss": 0.4977,
      "step": 60367
    },
    {
      "epoch": 1.8544527386108807,
      "grad_norm": 0.4554826021194458,
      "learning_rate": 2.611181919998129e-07,
      "loss": 0.4569,
      "step": 60368
    },
    {
      "epoch": 1.8544834577458298,
      "grad_norm": 0.40586721897125244,
      "learning_rate": 2.6100848578077267e-07,
      "loss": 0.4301,
      "step": 60369
    },
    {
      "epoch": 1.854514176880779,
      "grad_norm": 0.421806275844574,
      "learning_rate": 2.608988023078252e-07,
      "loss": 0.422,
      "step": 60370
    },
    {
      "epoch": 1.8545448960157283,
      "grad_norm": 0.4625907838344574,
      "learning_rate": 2.6078914158123136e-07,
      "loss": 0.4758,
      "step": 60371
    },
    {
      "epoch": 1.8545756151506774,
      "grad_norm": 0.4170685410499573,
      "learning_rate": 2.606795036012433e-07,
      "loss": 0.4784,
      "step": 60372
    },
    {
      "epoch": 1.8546063342856265,
      "grad_norm": 0.4150475263595581,
      "learning_rate": 2.605698883681196e-07,
      "loss": 0.4511,
      "step": 60373
    },
    {
      "epoch": 1.8546370534205758,
      "grad_norm": 0.4291006326675415,
      "learning_rate": 2.604602958821134e-07,
      "loss": 0.4981,
      "step": 60374
    },
    {
      "epoch": 1.854667772555525,
      "grad_norm": 0.4328326880931854,
      "learning_rate": 2.603507261434834e-07,
      "loss": 0.4599,
      "step": 60375
    },
    {
      "epoch": 1.854698491690474,
      "grad_norm": 0.4458189606666565,
      "learning_rate": 2.6024117915248504e-07,
      "loss": 0.4815,
      "step": 60376
    },
    {
      "epoch": 1.8547292108254232,
      "grad_norm": 0.4601714611053467,
      "learning_rate": 2.601316549093735e-07,
      "loss": 0.4262,
      "step": 60377
    },
    {
      "epoch": 1.8547599299603723,
      "grad_norm": 0.4795305132865906,
      "learning_rate": 2.600221534144032e-07,
      "loss": 0.498,
      "step": 60378
    },
    {
      "epoch": 1.8547906490953214,
      "grad_norm": 0.42348140478134155,
      "learning_rate": 2.5991267466783266e-07,
      "loss": 0.4362,
      "step": 60379
    },
    {
      "epoch": 1.8548213682302706,
      "grad_norm": 0.4718233346939087,
      "learning_rate": 2.598032186699162e-07,
      "loss": 0.4639,
      "step": 60380
    },
    {
      "epoch": 1.8548520873652197,
      "grad_norm": 0.4079948961734772,
      "learning_rate": 2.5969378542090807e-07,
      "loss": 0.5366,
      "step": 60381
    },
    {
      "epoch": 1.8548828065001688,
      "grad_norm": 0.476723313331604,
      "learning_rate": 2.59584374921068e-07,
      "loss": 0.4237,
      "step": 60382
    },
    {
      "epoch": 1.8549135256351181,
      "grad_norm": 0.41107413172721863,
      "learning_rate": 2.5947498717064703e-07,
      "loss": 0.4317,
      "step": 60383
    },
    {
      "epoch": 1.8549442447700673,
      "grad_norm": 0.48357897996902466,
      "learning_rate": 2.5936562216990255e-07,
      "loss": 0.4706,
      "step": 60384
    },
    {
      "epoch": 1.8549749639050166,
      "grad_norm": 0.4140498638153076,
      "learning_rate": 2.592562799190912e-07,
      "loss": 0.4452,
      "step": 60385
    },
    {
      "epoch": 1.8550056830399657,
      "grad_norm": 0.42906883358955383,
      "learning_rate": 2.59146960418466e-07,
      "loss": 0.4464,
      "step": 60386
    },
    {
      "epoch": 1.8550364021749148,
      "grad_norm": 0.4374394416809082,
      "learning_rate": 2.5903766366828344e-07,
      "loss": 0.4588,
      "step": 60387
    },
    {
      "epoch": 1.855067121309864,
      "grad_norm": 0.4450218677520752,
      "learning_rate": 2.5892838966879883e-07,
      "loss": 0.4751,
      "step": 60388
    },
    {
      "epoch": 1.855097840444813,
      "grad_norm": 0.4038320481777191,
      "learning_rate": 2.588191384202676e-07,
      "loss": 0.5115,
      "step": 60389
    },
    {
      "epoch": 1.8551285595797622,
      "grad_norm": 0.43803760409355164,
      "learning_rate": 2.587099099229451e-07,
      "loss": 0.4927,
      "step": 60390
    },
    {
      "epoch": 1.8551592787147113,
      "grad_norm": 0.4161517918109894,
      "learning_rate": 2.5860070417708437e-07,
      "loss": 0.4258,
      "step": 60391
    },
    {
      "epoch": 1.8551899978496604,
      "grad_norm": 0.4158535897731781,
      "learning_rate": 2.5849152118294307e-07,
      "loss": 0.5546,
      "step": 60392
    },
    {
      "epoch": 1.8552207169846096,
      "grad_norm": 0.4746965169906616,
      "learning_rate": 2.583823609407743e-07,
      "loss": 0.4172,
      "step": 60393
    },
    {
      "epoch": 1.855251436119559,
      "grad_norm": 0.47420939803123474,
      "learning_rate": 2.582732234508356e-07,
      "loss": 0.4476,
      "step": 60394
    },
    {
      "epoch": 1.855282155254508,
      "grad_norm": 0.4420200288295746,
      "learning_rate": 2.5816410871337904e-07,
      "loss": 0.4766,
      "step": 60395
    },
    {
      "epoch": 1.8553128743894574,
      "grad_norm": 0.44555604457855225,
      "learning_rate": 2.5805501672866e-07,
      "loss": 0.4566,
      "step": 60396
    },
    {
      "epoch": 1.8553435935244065,
      "grad_norm": 0.4136168658733368,
      "learning_rate": 2.579459474969348e-07,
      "loss": 0.4908,
      "step": 60397
    },
    {
      "epoch": 1.8553743126593556,
      "grad_norm": 0.4556562602519989,
      "learning_rate": 2.578369010184578e-07,
      "loss": 0.4434,
      "step": 60398
    },
    {
      "epoch": 1.8554050317943047,
      "grad_norm": 0.4472487270832062,
      "learning_rate": 2.5772787729348103e-07,
      "loss": 0.4669,
      "step": 60399
    },
    {
      "epoch": 1.8554357509292538,
      "grad_norm": 0.42567622661590576,
      "learning_rate": 2.57618876322262e-07,
      "loss": 0.4632,
      "step": 60400
    },
    {
      "epoch": 1.855466470064203,
      "grad_norm": 0.41568779945373535,
      "learning_rate": 2.57509898105055e-07,
      "loss": 0.5551,
      "step": 60401
    },
    {
      "epoch": 1.855497189199152,
      "grad_norm": 0.41145291924476624,
      "learning_rate": 2.5740094264211423e-07,
      "loss": 0.4671,
      "step": 60402
    },
    {
      "epoch": 1.8555279083341012,
      "grad_norm": 0.430022269487381,
      "learning_rate": 2.57292009933694e-07,
      "loss": 0.4525,
      "step": 60403
    },
    {
      "epoch": 1.8555586274690503,
      "grad_norm": 0.3936000168323517,
      "learning_rate": 2.571830999800473e-07,
      "loss": 0.4387,
      "step": 60404
    },
    {
      "epoch": 1.8555893466039997,
      "grad_norm": 0.4390304684638977,
      "learning_rate": 2.570742127814319e-07,
      "loss": 0.4345,
      "step": 60405
    },
    {
      "epoch": 1.8556200657389488,
      "grad_norm": 0.45775383710861206,
      "learning_rate": 2.569653483380985e-07,
      "loss": 0.4772,
      "step": 60406
    },
    {
      "epoch": 1.855650784873898,
      "grad_norm": 0.40223827958106995,
      "learning_rate": 2.568565066503037e-07,
      "loss": 0.4553,
      "step": 60407
    },
    {
      "epoch": 1.8556815040088472,
      "grad_norm": 0.4970828890800476,
      "learning_rate": 2.567476877183006e-07,
      "loss": 0.4891,
      "step": 60408
    },
    {
      "epoch": 1.8557122231437964,
      "grad_norm": 0.45040664076805115,
      "learning_rate": 2.5663889154234456e-07,
      "loss": 0.4198,
      "step": 60409
    },
    {
      "epoch": 1.8557429422787455,
      "grad_norm": 0.47093304991722107,
      "learning_rate": 2.565301181226887e-07,
      "loss": 0.4342,
      "step": 60410
    },
    {
      "epoch": 1.8557736614136946,
      "grad_norm": 0.4095626473426819,
      "learning_rate": 2.564213674595861e-07,
      "loss": 0.4447,
      "step": 60411
    },
    {
      "epoch": 1.8558043805486437,
      "grad_norm": 0.4176768660545349,
      "learning_rate": 2.5631263955329223e-07,
      "loss": 0.4278,
      "step": 60412
    },
    {
      "epoch": 1.8558350996835928,
      "grad_norm": 0.4522288143634796,
      "learning_rate": 2.562039344040623e-07,
      "loss": 0.4683,
      "step": 60413
    },
    {
      "epoch": 1.855865818818542,
      "grad_norm": 0.44096139073371887,
      "learning_rate": 2.5609525201214736e-07,
      "loss": 0.3977,
      "step": 60414
    },
    {
      "epoch": 1.855896537953491,
      "grad_norm": 0.4292086660861969,
      "learning_rate": 2.5598659237780155e-07,
      "loss": 0.3547,
      "step": 60415
    },
    {
      "epoch": 1.8559272570884404,
      "grad_norm": 0.4209248721599579,
      "learning_rate": 2.5587795550128027e-07,
      "loss": 0.5684,
      "step": 60416
    },
    {
      "epoch": 1.8559579762233895,
      "grad_norm": 0.4537765085697174,
      "learning_rate": 2.557693413828366e-07,
      "loss": 0.4652,
      "step": 60417
    },
    {
      "epoch": 1.8559886953583387,
      "grad_norm": 0.4448041021823883,
      "learning_rate": 2.5566075002272486e-07,
      "loss": 0.4309,
      "step": 60418
    },
    {
      "epoch": 1.856019414493288,
      "grad_norm": 0.46150869131088257,
      "learning_rate": 2.555521814211981e-07,
      "loss": 0.5078,
      "step": 60419
    },
    {
      "epoch": 1.8560501336282371,
      "grad_norm": 0.44518333673477173,
      "learning_rate": 2.554436355785084e-07,
      "loss": 0.4761,
      "step": 60420
    },
    {
      "epoch": 1.8560808527631862,
      "grad_norm": 0.4500454366207123,
      "learning_rate": 2.5533511249491104e-07,
      "loss": 0.4842,
      "step": 60421
    },
    {
      "epoch": 1.8561115718981354,
      "grad_norm": 0.4515744149684906,
      "learning_rate": 2.5522661217066034e-07,
      "loss": 0.4534,
      "step": 60422
    },
    {
      "epoch": 1.8561422910330845,
      "grad_norm": 0.5654219388961792,
      "learning_rate": 2.551181346060072e-07,
      "loss": 0.4069,
      "step": 60423
    },
    {
      "epoch": 1.8561730101680336,
      "grad_norm": 0.445197194814682,
      "learning_rate": 2.550096798012058e-07,
      "loss": 0.4425,
      "step": 60424
    },
    {
      "epoch": 1.8562037293029827,
      "grad_norm": 0.5416721105575562,
      "learning_rate": 2.549012477565105e-07,
      "loss": 0.5004,
      "step": 60425
    },
    {
      "epoch": 1.8562344484379318,
      "grad_norm": 0.3909060060977936,
      "learning_rate": 2.547928384721754e-07,
      "loss": 0.3905,
      "step": 60426
    },
    {
      "epoch": 1.8562651675728812,
      "grad_norm": 0.4067588448524475,
      "learning_rate": 2.5468445194845037e-07,
      "loss": 0.4584,
      "step": 60427
    },
    {
      "epoch": 1.8562958867078303,
      "grad_norm": 0.44158756732940674,
      "learning_rate": 2.545760881855908e-07,
      "loss": 0.4661,
      "step": 60428
    },
    {
      "epoch": 1.8563266058427794,
      "grad_norm": 0.453200101852417,
      "learning_rate": 2.544677471838486e-07,
      "loss": 0.5104,
      "step": 60429
    },
    {
      "epoch": 1.8563573249777288,
      "grad_norm": 0.4218698740005493,
      "learning_rate": 2.543594289434792e-07,
      "loss": 0.4363,
      "step": 60430
    },
    {
      "epoch": 1.8563880441126779,
      "grad_norm": 0.4077662229537964,
      "learning_rate": 2.542511334647335e-07,
      "loss": 0.4641,
      "step": 60431
    },
    {
      "epoch": 1.856418763247627,
      "grad_norm": 0.42096400260925293,
      "learning_rate": 2.5414286074786463e-07,
      "loss": 0.4554,
      "step": 60432
    },
    {
      "epoch": 1.8564494823825761,
      "grad_norm": 0.4473420977592468,
      "learning_rate": 2.5403461079312465e-07,
      "loss": 0.6012,
      "step": 60433
    },
    {
      "epoch": 1.8564802015175252,
      "grad_norm": 0.42055776715278625,
      "learning_rate": 2.5392638360076993e-07,
      "loss": 0.4765,
      "step": 60434
    },
    {
      "epoch": 1.8565109206524744,
      "grad_norm": 0.3886738419532776,
      "learning_rate": 2.5381817917104924e-07,
      "loss": 0.4712,
      "step": 60435
    },
    {
      "epoch": 1.8565416397874235,
      "grad_norm": 0.3988012373447418,
      "learning_rate": 2.5370999750421675e-07,
      "loss": 0.5415,
      "step": 60436
    },
    {
      "epoch": 1.8565723589223726,
      "grad_norm": 0.4811652898788452,
      "learning_rate": 2.5360183860052565e-07,
      "loss": 0.4731,
      "step": 60437
    },
    {
      "epoch": 1.856603078057322,
      "grad_norm": 0.398712694644928,
      "learning_rate": 2.5349370246022684e-07,
      "loss": 0.4623,
      "step": 60438
    },
    {
      "epoch": 1.856633797192271,
      "grad_norm": 0.41926634311676025,
      "learning_rate": 2.533855890835768e-07,
      "loss": 0.4546,
      "step": 60439
    },
    {
      "epoch": 1.8566645163272202,
      "grad_norm": 0.4757263958454132,
      "learning_rate": 2.5327749847082414e-07,
      "loss": 0.4213,
      "step": 60440
    },
    {
      "epoch": 1.8566952354621695,
      "grad_norm": 0.4721620976924896,
      "learning_rate": 2.5316943062222324e-07,
      "loss": 0.5338,
      "step": 60441
    },
    {
      "epoch": 1.8567259545971186,
      "grad_norm": 0.4364407956600189,
      "learning_rate": 2.5306138553802375e-07,
      "loss": 0.4766,
      "step": 60442
    },
    {
      "epoch": 1.8567566737320678,
      "grad_norm": 0.4457002282142639,
      "learning_rate": 2.5295336321848216e-07,
      "loss": 0.5537,
      "step": 60443
    },
    {
      "epoch": 1.8567873928670169,
      "grad_norm": 0.43913349509239197,
      "learning_rate": 2.5284536366384725e-07,
      "loss": 0.4445,
      "step": 60444
    },
    {
      "epoch": 1.856818112001966,
      "grad_norm": 0.40777403116226196,
      "learning_rate": 2.5273738687437434e-07,
      "loss": 0.4293,
      "step": 60445
    },
    {
      "epoch": 1.8568488311369151,
      "grad_norm": 0.469707727432251,
      "learning_rate": 2.5262943285031315e-07,
      "loss": 0.45,
      "step": 60446
    },
    {
      "epoch": 1.8568795502718642,
      "grad_norm": 0.441824346780777,
      "learning_rate": 2.525215015919158e-07,
      "loss": 0.505,
      "step": 60447
    },
    {
      "epoch": 1.8569102694068134,
      "grad_norm": 0.455750435590744,
      "learning_rate": 2.5241359309943646e-07,
      "loss": 0.4938,
      "step": 60448
    },
    {
      "epoch": 1.8569409885417627,
      "grad_norm": 0.39931488037109375,
      "learning_rate": 2.523057073731261e-07,
      "loss": 0.4256,
      "step": 60449
    },
    {
      "epoch": 1.8569717076767118,
      "grad_norm": 0.43618085980415344,
      "learning_rate": 2.5219784441323557e-07,
      "loss": 0.4311,
      "step": 60450
    },
    {
      "epoch": 1.857002426811661,
      "grad_norm": 0.4495427906513214,
      "learning_rate": 2.5209000422001807e-07,
      "loss": 0.5102,
      "step": 60451
    },
    {
      "epoch": 1.8570331459466103,
      "grad_norm": 0.43633073568344116,
      "learning_rate": 2.5198218679372445e-07,
      "loss": 0.4377,
      "step": 60452
    },
    {
      "epoch": 1.8570638650815594,
      "grad_norm": 0.4324088990688324,
      "learning_rate": 2.51874392134609e-07,
      "loss": 0.5037,
      "step": 60453
    },
    {
      "epoch": 1.8570945842165085,
      "grad_norm": 0.5133146643638611,
      "learning_rate": 2.517666202429203e-07,
      "loss": 0.5182,
      "step": 60454
    },
    {
      "epoch": 1.8571253033514576,
      "grad_norm": 0.45910435914993286,
      "learning_rate": 2.516588711189116e-07,
      "loss": 0.4658,
      "step": 60455
    },
    {
      "epoch": 1.8571560224864068,
      "grad_norm": 0.43932008743286133,
      "learning_rate": 2.5155114476283493e-07,
      "loss": 0.4918,
      "step": 60456
    },
    {
      "epoch": 1.8571867416213559,
      "grad_norm": 0.45321032404899597,
      "learning_rate": 2.514434411749411e-07,
      "loss": 0.4541,
      "step": 60457
    },
    {
      "epoch": 1.857217460756305,
      "grad_norm": 0.456393837928772,
      "learning_rate": 2.5133576035548226e-07,
      "loss": 0.3757,
      "step": 60458
    },
    {
      "epoch": 1.8572481798912541,
      "grad_norm": 0.45300331711769104,
      "learning_rate": 2.512281023047092e-07,
      "loss": 0.4261,
      "step": 60459
    },
    {
      "epoch": 1.8572788990262035,
      "grad_norm": 0.45810210704803467,
      "learning_rate": 2.5112046702287395e-07,
      "loss": 0.4025,
      "step": 60460
    },
    {
      "epoch": 1.8573096181611526,
      "grad_norm": 0.46064138412475586,
      "learning_rate": 2.510128545102275e-07,
      "loss": 0.4427,
      "step": 60461
    },
    {
      "epoch": 1.8573403372961017,
      "grad_norm": 0.4194399416446686,
      "learning_rate": 2.5090526476702183e-07,
      "loss": 0.4717,
      "step": 60462
    },
    {
      "epoch": 1.857371056431051,
      "grad_norm": 0.426707923412323,
      "learning_rate": 2.5079769779350783e-07,
      "loss": 0.5264,
      "step": 60463
    },
    {
      "epoch": 1.8574017755660002,
      "grad_norm": 0.4170076549053192,
      "learning_rate": 2.5069015358993643e-07,
      "loss": 0.4702,
      "step": 60464
    },
    {
      "epoch": 1.8574324947009493,
      "grad_norm": 0.410631388425827,
      "learning_rate": 2.5058263215655856e-07,
      "loss": 0.4024,
      "step": 60465
    },
    {
      "epoch": 1.8574632138358984,
      "grad_norm": 0.4257737994194031,
      "learning_rate": 2.504751334936273e-07,
      "loss": 0.4149,
      "step": 60466
    },
    {
      "epoch": 1.8574939329708475,
      "grad_norm": 0.4424976706504822,
      "learning_rate": 2.503676576013903e-07,
      "loss": 0.4589,
      "step": 60467
    },
    {
      "epoch": 1.8575246521057966,
      "grad_norm": 0.4461057782173157,
      "learning_rate": 2.502602044801028e-07,
      "loss": 0.3824,
      "step": 60468
    },
    {
      "epoch": 1.8575553712407458,
      "grad_norm": 0.45575135946273804,
      "learning_rate": 2.5015277413001024e-07,
      "loss": 0.4295,
      "step": 60469
    },
    {
      "epoch": 1.8575860903756949,
      "grad_norm": 0.4096372127532959,
      "learning_rate": 2.5004536655137024e-07,
      "loss": 0.4784,
      "step": 60470
    },
    {
      "epoch": 1.8576168095106442,
      "grad_norm": 0.3976000249385834,
      "learning_rate": 2.499379817444281e-07,
      "loss": 0.4334,
      "step": 60471
    },
    {
      "epoch": 1.8576475286455933,
      "grad_norm": 0.41639846563339233,
      "learning_rate": 2.4983061970943687e-07,
      "loss": 0.5399,
      "step": 60472
    },
    {
      "epoch": 1.8576782477805425,
      "grad_norm": 0.46971258521080017,
      "learning_rate": 2.497232804466487e-07,
      "loss": 0.4681,
      "step": 60473
    },
    {
      "epoch": 1.8577089669154918,
      "grad_norm": 0.44234806299209595,
      "learning_rate": 2.4961596395631005e-07,
      "loss": 0.4443,
      "step": 60474
    },
    {
      "epoch": 1.857739686050441,
      "grad_norm": 0.43901926279067993,
      "learning_rate": 2.495086702386773e-07,
      "loss": 0.4984,
      "step": 60475
    },
    {
      "epoch": 1.85777040518539,
      "grad_norm": 0.4764777421951294,
      "learning_rate": 2.4940139929399586e-07,
      "loss": 0.51,
      "step": 60476
    },
    {
      "epoch": 1.8578011243203392,
      "grad_norm": 0.429149866104126,
      "learning_rate": 2.4929415112252e-07,
      "loss": 0.524,
      "step": 60477
    },
    {
      "epoch": 1.8578318434552883,
      "grad_norm": 0.510075032711029,
      "learning_rate": 2.4918692572449723e-07,
      "loss": 0.4825,
      "step": 60478
    },
    {
      "epoch": 1.8578625625902374,
      "grad_norm": 0.4311055839061737,
      "learning_rate": 2.490797231001807e-07,
      "loss": 0.48,
      "step": 60479
    },
    {
      "epoch": 1.8578932817251865,
      "grad_norm": 0.5787611603736877,
      "learning_rate": 2.48972543249818e-07,
      "loss": 0.4918,
      "step": 60480
    },
    {
      "epoch": 1.8579240008601356,
      "grad_norm": 0.42591074109077454,
      "learning_rate": 2.4886538617366343e-07,
      "loss": 0.3979,
      "step": 60481
    },
    {
      "epoch": 1.857954719995085,
      "grad_norm": 0.4732092618942261,
      "learning_rate": 2.487582518719622e-07,
      "loss": 0.4717,
      "step": 60482
    },
    {
      "epoch": 1.857985439130034,
      "grad_norm": 0.4488832354545593,
      "learning_rate": 2.486511403449676e-07,
      "loss": 0.4854,
      "step": 60483
    },
    {
      "epoch": 1.8580161582649832,
      "grad_norm": 0.4626657962799072,
      "learning_rate": 2.4854405159292937e-07,
      "loss": 0.5937,
      "step": 60484
    },
    {
      "epoch": 1.8580468773999326,
      "grad_norm": 0.45661354064941406,
      "learning_rate": 2.484369856160984e-07,
      "loss": 0.4521,
      "step": 60485
    },
    {
      "epoch": 1.8580775965348817,
      "grad_norm": 0.4760357737541199,
      "learning_rate": 2.4832994241472343e-07,
      "loss": 0.4761,
      "step": 60486
    },
    {
      "epoch": 1.8581083156698308,
      "grad_norm": 0.4320319592952728,
      "learning_rate": 2.4822292198905416e-07,
      "loss": 0.5234,
      "step": 60487
    },
    {
      "epoch": 1.85813903480478,
      "grad_norm": 0.4334801137447357,
      "learning_rate": 2.4811592433934163e-07,
      "loss": 0.4104,
      "step": 60488
    },
    {
      "epoch": 1.858169753939729,
      "grad_norm": 0.4941782057285309,
      "learning_rate": 2.4800894946583663e-07,
      "loss": 0.509,
      "step": 60489
    },
    {
      "epoch": 1.8582004730746782,
      "grad_norm": 0.43221792578697205,
      "learning_rate": 2.4790199736878685e-07,
      "loss": 0.4063,
      "step": 60490
    },
    {
      "epoch": 1.8582311922096273,
      "grad_norm": 0.44428372383117676,
      "learning_rate": 2.477950680484431e-07,
      "loss": 0.4866,
      "step": 60491
    },
    {
      "epoch": 1.8582619113445764,
      "grad_norm": 0.4138292968273163,
      "learning_rate": 2.4768816150505527e-07,
      "loss": 0.5242,
      "step": 60492
    },
    {
      "epoch": 1.8582926304795255,
      "grad_norm": 0.6277817487716675,
      "learning_rate": 2.4758127773887195e-07,
      "loss": 0.3354,
      "step": 60493
    },
    {
      "epoch": 1.8583233496144749,
      "grad_norm": 0.4470215439796448,
      "learning_rate": 2.4747441675014525e-07,
      "loss": 0.5157,
      "step": 60494
    },
    {
      "epoch": 1.858354068749424,
      "grad_norm": 0.4563210606575012,
      "learning_rate": 2.473675785391216e-07,
      "loss": 0.476,
      "step": 60495
    },
    {
      "epoch": 1.8583847878843733,
      "grad_norm": 0.48550787568092346,
      "learning_rate": 2.4726076310605304e-07,
      "loss": 0.4128,
      "step": 60496
    },
    {
      "epoch": 1.8584155070193225,
      "grad_norm": 0.48236364126205444,
      "learning_rate": 2.471539704511872e-07,
      "loss": 0.4537,
      "step": 60497
    },
    {
      "epoch": 1.8584462261542716,
      "grad_norm": 0.43720316886901855,
      "learning_rate": 2.4704720057477595e-07,
      "loss": 0.4652,
      "step": 60498
    },
    {
      "epoch": 1.8584769452892207,
      "grad_norm": 0.46091315150260925,
      "learning_rate": 2.4694045347706586e-07,
      "loss": 0.4789,
      "step": 60499
    },
    {
      "epoch": 1.8585076644241698,
      "grad_norm": 0.39362165331840515,
      "learning_rate": 2.468337291583067e-07,
      "loss": 0.4691,
      "step": 60500
    },
    {
      "epoch": 1.858538383559119,
      "grad_norm": 0.4295252859592438,
      "learning_rate": 2.4672702761874947e-07,
      "loss": 0.438,
      "step": 60501
    },
    {
      "epoch": 1.858569102694068,
      "grad_norm": 0.4171563684940338,
      "learning_rate": 2.466203488586438e-07,
      "loss": 0.4547,
      "step": 60502
    },
    {
      "epoch": 1.8585998218290172,
      "grad_norm": 0.4313085079193115,
      "learning_rate": 2.4651369287823526e-07,
      "loss": 0.5235,
      "step": 60503
    },
    {
      "epoch": 1.8586305409639663,
      "grad_norm": 0.49739477038383484,
      "learning_rate": 2.464070596777768e-07,
      "loss": 0.5096,
      "step": 60504
    },
    {
      "epoch": 1.8586612600989156,
      "grad_norm": 0.42577943205833435,
      "learning_rate": 2.4630044925751386e-07,
      "loss": 0.4639,
      "step": 60505
    },
    {
      "epoch": 1.8586919792338648,
      "grad_norm": 0.43806570768356323,
      "learning_rate": 2.4619386161769956e-07,
      "loss": 0.5445,
      "step": 60506
    },
    {
      "epoch": 1.858722698368814,
      "grad_norm": 0.46128565073013306,
      "learning_rate": 2.4608729675858035e-07,
      "loss": 0.4795,
      "step": 60507
    },
    {
      "epoch": 1.8587534175037632,
      "grad_norm": 0.47083717584609985,
      "learning_rate": 2.4598075468040496e-07,
      "loss": 0.6018,
      "step": 60508
    },
    {
      "epoch": 1.8587841366387123,
      "grad_norm": 0.418011337518692,
      "learning_rate": 2.4587423538342315e-07,
      "loss": 0.4808,
      "step": 60509
    },
    {
      "epoch": 1.8588148557736615,
      "grad_norm": 0.4157676100730896,
      "learning_rate": 2.457677388678814e-07,
      "loss": 0.447,
      "step": 60510
    },
    {
      "epoch": 1.8588455749086106,
      "grad_norm": 0.42679259181022644,
      "learning_rate": 2.4566126513403177e-07,
      "loss": 0.4225,
      "step": 60511
    },
    {
      "epoch": 1.8588762940435597,
      "grad_norm": 0.43825995922088623,
      "learning_rate": 2.455548141821218e-07,
      "loss": 0.5886,
      "step": 60512
    },
    {
      "epoch": 1.8589070131785088,
      "grad_norm": 0.39991140365600586,
      "learning_rate": 2.454483860124002e-07,
      "loss": 0.4243,
      "step": 60513
    },
    {
      "epoch": 1.858937732313458,
      "grad_norm": 0.4210975468158722,
      "learning_rate": 2.453419806251145e-07,
      "loss": 0.5002,
      "step": 60514
    },
    {
      "epoch": 1.858968451448407,
      "grad_norm": 0.42127662897109985,
      "learning_rate": 2.4523559802051345e-07,
      "loss": 0.5083,
      "step": 60515
    },
    {
      "epoch": 1.8589991705833564,
      "grad_norm": 0.4415762424468994,
      "learning_rate": 2.451292381988457e-07,
      "loss": 0.4159,
      "step": 60516
    },
    {
      "epoch": 1.8590298897183055,
      "grad_norm": 0.438237726688385,
      "learning_rate": 2.450229011603611e-07,
      "loss": 0.4585,
      "step": 60517
    },
    {
      "epoch": 1.8590606088532546,
      "grad_norm": 0.41870880126953125,
      "learning_rate": 2.4491658690530606e-07,
      "loss": 0.4378,
      "step": 60518
    },
    {
      "epoch": 1.859091327988204,
      "grad_norm": 0.45584815740585327,
      "learning_rate": 2.448102954339293e-07,
      "loss": 0.5112,
      "step": 60519
    },
    {
      "epoch": 1.859122047123153,
      "grad_norm": 0.4474407136440277,
      "learning_rate": 2.447040267464795e-07,
      "loss": 0.4923,
      "step": 60520
    },
    {
      "epoch": 1.8591527662581022,
      "grad_norm": 0.4791361093521118,
      "learning_rate": 2.4459778084320653e-07,
      "loss": 0.4243,
      "step": 60521
    },
    {
      "epoch": 1.8591834853930513,
      "grad_norm": 0.5302147269248962,
      "learning_rate": 2.444915577243545e-07,
      "loss": 0.437,
      "step": 60522
    },
    {
      "epoch": 1.8592142045280005,
      "grad_norm": 0.41430607438087463,
      "learning_rate": 2.443853573901744e-07,
      "loss": 0.4744,
      "step": 60523
    },
    {
      "epoch": 1.8592449236629496,
      "grad_norm": 0.39502331614494324,
      "learning_rate": 2.442791798409139e-07,
      "loss": 0.4292,
      "step": 60524
    },
    {
      "epoch": 1.8592756427978987,
      "grad_norm": 0.4307233393192291,
      "learning_rate": 2.441730250768204e-07,
      "loss": 0.4768,
      "step": 60525
    },
    {
      "epoch": 1.8593063619328478,
      "grad_norm": 0.43939173221588135,
      "learning_rate": 2.440668930981427e-07,
      "loss": 0.4297,
      "step": 60526
    },
    {
      "epoch": 1.8593370810677972,
      "grad_norm": 0.49890077114105225,
      "learning_rate": 2.4396078390512723e-07,
      "loss": 0.4666,
      "step": 60527
    },
    {
      "epoch": 1.8593678002027463,
      "grad_norm": 0.44089972972869873,
      "learning_rate": 2.438546974980227e-07,
      "loss": 0.4717,
      "step": 60528
    },
    {
      "epoch": 1.8593985193376954,
      "grad_norm": 0.41393521428108215,
      "learning_rate": 2.437486338770767e-07,
      "loss": 0.3802,
      "step": 60529
    },
    {
      "epoch": 1.8594292384726447,
      "grad_norm": 0.4241747558116913,
      "learning_rate": 2.43642593042539e-07,
      "loss": 0.3734,
      "step": 60530
    },
    {
      "epoch": 1.8594599576075939,
      "grad_norm": 0.46998995542526245,
      "learning_rate": 2.435365749946539e-07,
      "loss": 0.4896,
      "step": 60531
    },
    {
      "epoch": 1.859490676742543,
      "grad_norm": 0.4671534299850464,
      "learning_rate": 2.434305797336711e-07,
      "loss": 0.4474,
      "step": 60532
    },
    {
      "epoch": 1.859521395877492,
      "grad_norm": 0.46490728855133057,
      "learning_rate": 2.433246072598372e-07,
      "loss": 0.5205,
      "step": 60533
    },
    {
      "epoch": 1.8595521150124412,
      "grad_norm": 0.41450345516204834,
      "learning_rate": 2.432186575734008e-07,
      "loss": 0.4698,
      "step": 60534
    },
    {
      "epoch": 1.8595828341473903,
      "grad_norm": 0.4823020398616791,
      "learning_rate": 2.431127306746073e-07,
      "loss": 0.4626,
      "step": 60535
    },
    {
      "epoch": 1.8596135532823395,
      "grad_norm": 0.4630463123321533,
      "learning_rate": 2.4300682656370644e-07,
      "loss": 0.4683,
      "step": 60536
    },
    {
      "epoch": 1.8596442724172886,
      "grad_norm": 0.44634559750556946,
      "learning_rate": 2.4290094524094363e-07,
      "loss": 0.5028,
      "step": 60537
    },
    {
      "epoch": 1.859674991552238,
      "grad_norm": 0.4419509470462799,
      "learning_rate": 2.427950867065687e-07,
      "loss": 0.438,
      "step": 60538
    },
    {
      "epoch": 1.859705710687187,
      "grad_norm": 0.4016735851764679,
      "learning_rate": 2.4268925096082583e-07,
      "loss": 0.4038,
      "step": 60539
    },
    {
      "epoch": 1.8597364298221362,
      "grad_norm": 0.49858248233795166,
      "learning_rate": 2.425834380039649e-07,
      "loss": 0.4645,
      "step": 60540
    },
    {
      "epoch": 1.8597671489570855,
      "grad_norm": 0.4319283664226532,
      "learning_rate": 2.4247764783622896e-07,
      "loss": 0.5037,
      "step": 60541
    },
    {
      "epoch": 1.8597978680920346,
      "grad_norm": 0.4801226556301117,
      "learning_rate": 2.423718804578712e-07,
      "loss": 0.4144,
      "step": 60542
    },
    {
      "epoch": 1.8598285872269837,
      "grad_norm": 0.42863690853118896,
      "learning_rate": 2.422661358691336e-07,
      "loss": 0.4443,
      "step": 60543
    },
    {
      "epoch": 1.8598593063619329,
      "grad_norm": 0.500863254070282,
      "learning_rate": 2.42160414070266e-07,
      "loss": 0.5232,
      "step": 60544
    },
    {
      "epoch": 1.859890025496882,
      "grad_norm": 0.4520188570022583,
      "learning_rate": 2.420547150615138e-07,
      "loss": 0.4928,
      "step": 60545
    },
    {
      "epoch": 1.859920744631831,
      "grad_norm": 0.5127315521240234,
      "learning_rate": 2.419490388431234e-07,
      "loss": 0.4502,
      "step": 60546
    },
    {
      "epoch": 1.8599514637667802,
      "grad_norm": 0.3852255046367645,
      "learning_rate": 2.4184338541534345e-07,
      "loss": 0.4251,
      "step": 60547
    },
    {
      "epoch": 1.8599821829017293,
      "grad_norm": 0.40297481417655945,
      "learning_rate": 2.417377547784194e-07,
      "loss": 0.4525,
      "step": 60548
    },
    {
      "epoch": 1.8600129020366787,
      "grad_norm": 0.44144150614738464,
      "learning_rate": 2.4163214693259993e-07,
      "loss": 0.4941,
      "step": 60549
    },
    {
      "epoch": 1.8600436211716278,
      "grad_norm": 0.43602243065834045,
      "learning_rate": 2.415265618781282e-07,
      "loss": 0.4049,
      "step": 60550
    },
    {
      "epoch": 1.860074340306577,
      "grad_norm": 0.42678093910217285,
      "learning_rate": 2.414209996152528e-07,
      "loss": 0.475,
      "step": 60551
    },
    {
      "epoch": 1.8601050594415263,
      "grad_norm": 0.4152866303920746,
      "learning_rate": 2.4131546014422026e-07,
      "loss": 0.4144,
      "step": 60552
    },
    {
      "epoch": 1.8601357785764754,
      "grad_norm": 0.4123137593269348,
      "learning_rate": 2.4120994346527814e-07,
      "loss": 0.4566,
      "step": 60553
    },
    {
      "epoch": 1.8601664977114245,
      "grad_norm": 0.5157864689826965,
      "learning_rate": 2.4110444957867073e-07,
      "loss": 0.4247,
      "step": 60554
    },
    {
      "epoch": 1.8601972168463736,
      "grad_norm": 0.43098750710487366,
      "learning_rate": 2.4099897848464557e-07,
      "loss": 0.5132,
      "step": 60555
    },
    {
      "epoch": 1.8602279359813227,
      "grad_norm": 0.5472079515457153,
      "learning_rate": 2.408935301834492e-07,
      "loss": 0.4445,
      "step": 60556
    },
    {
      "epoch": 1.8602586551162719,
      "grad_norm": 0.4153023958206177,
      "learning_rate": 2.4078810467532797e-07,
      "loss": 0.4466,
      "step": 60557
    },
    {
      "epoch": 1.860289374251221,
      "grad_norm": 0.48269543051719666,
      "learning_rate": 2.406827019605262e-07,
      "loss": 0.4767,
      "step": 60558
    },
    {
      "epoch": 1.86032009338617,
      "grad_norm": 0.4585631489753723,
      "learning_rate": 2.405773220392926e-07,
      "loss": 0.4954,
      "step": 60559
    },
    {
      "epoch": 1.8603508125211194,
      "grad_norm": 0.4931035041809082,
      "learning_rate": 2.404719649118714e-07,
      "loss": 0.432,
      "step": 60560
    },
    {
      "epoch": 1.8603815316560686,
      "grad_norm": 0.45317938923835754,
      "learning_rate": 2.403666305785113e-07,
      "loss": 0.3923,
      "step": 60561
    },
    {
      "epoch": 1.8604122507910177,
      "grad_norm": 0.4082007110118866,
      "learning_rate": 2.4026131903945535e-07,
      "loss": 0.4228,
      "step": 60562
    },
    {
      "epoch": 1.860442969925967,
      "grad_norm": 0.44555091857910156,
      "learning_rate": 2.4015603029495016e-07,
      "loss": 0.4553,
      "step": 60563
    },
    {
      "epoch": 1.8604736890609161,
      "grad_norm": 0.46501487493515015,
      "learning_rate": 2.400507643452432e-07,
      "loss": 0.4593,
      "step": 60564
    },
    {
      "epoch": 1.8605044081958653,
      "grad_norm": 0.42900145053863525,
      "learning_rate": 2.399455211905788e-07,
      "loss": 0.4403,
      "step": 60565
    },
    {
      "epoch": 1.8605351273308144,
      "grad_norm": 0.511491060256958,
      "learning_rate": 2.3984030083120337e-07,
      "loss": 0.4374,
      "step": 60566
    },
    {
      "epoch": 1.8605658464657635,
      "grad_norm": 0.4658334255218506,
      "learning_rate": 2.3973510326736227e-07,
      "loss": 0.3953,
      "step": 60567
    },
    {
      "epoch": 1.8605965656007126,
      "grad_norm": 0.5333781838417053,
      "learning_rate": 2.39629928499302e-07,
      "loss": 0.4071,
      "step": 60568
    },
    {
      "epoch": 1.8606272847356617,
      "grad_norm": 0.4316995143890381,
      "learning_rate": 2.395247765272668e-07,
      "loss": 0.466,
      "step": 60569
    },
    {
      "epoch": 1.8606580038706109,
      "grad_norm": 0.45345938205718994,
      "learning_rate": 2.3941964735150533e-07,
      "loss": 0.4542,
      "step": 60570
    },
    {
      "epoch": 1.8606887230055602,
      "grad_norm": 0.41844844818115234,
      "learning_rate": 2.393145409722586e-07,
      "loss": 0.4745,
      "step": 60571
    },
    {
      "epoch": 1.8607194421405093,
      "grad_norm": 0.440471887588501,
      "learning_rate": 2.392094573897763e-07,
      "loss": 0.5298,
      "step": 60572
    },
    {
      "epoch": 1.8607501612754584,
      "grad_norm": 0.4344986379146576,
      "learning_rate": 2.391043966042994e-07,
      "loss": 0.5087,
      "step": 60573
    },
    {
      "epoch": 1.8607808804104078,
      "grad_norm": 0.39210087060928345,
      "learning_rate": 2.3899935861607884e-07,
      "loss": 0.4471,
      "step": 60574
    },
    {
      "epoch": 1.860811599545357,
      "grad_norm": 0.4455242455005646,
      "learning_rate": 2.3889434342535546e-07,
      "loss": 0.4721,
      "step": 60575
    },
    {
      "epoch": 1.860842318680306,
      "grad_norm": 0.44488245248794556,
      "learning_rate": 2.387893510323769e-07,
      "loss": 0.5036,
      "step": 60576
    },
    {
      "epoch": 1.8608730378152551,
      "grad_norm": 0.4330810606479645,
      "learning_rate": 2.3868438143738624e-07,
      "loss": 0.4731,
      "step": 60577
    },
    {
      "epoch": 1.8609037569502043,
      "grad_norm": 0.47218480706214905,
      "learning_rate": 2.3857943464063004e-07,
      "loss": 0.5304,
      "step": 60578
    },
    {
      "epoch": 1.8609344760851534,
      "grad_norm": 0.4369935393333435,
      "learning_rate": 2.384745106423536e-07,
      "loss": 0.4923,
      "step": 60579
    },
    {
      "epoch": 1.8609651952201025,
      "grad_norm": 0.429552286863327,
      "learning_rate": 2.383696094428023e-07,
      "loss": 0.498,
      "step": 60580
    },
    {
      "epoch": 1.8609959143550516,
      "grad_norm": 0.45591139793395996,
      "learning_rate": 2.3826473104222036e-07,
      "loss": 0.5037,
      "step": 60581
    },
    {
      "epoch": 1.861026633490001,
      "grad_norm": 0.4564749300479889,
      "learning_rate": 2.3815987544085096e-07,
      "loss": 0.4339,
      "step": 60582
    },
    {
      "epoch": 1.86105735262495,
      "grad_norm": 0.39821019768714905,
      "learning_rate": 2.3805504263894386e-07,
      "loss": 0.4625,
      "step": 60583
    },
    {
      "epoch": 1.8610880717598992,
      "grad_norm": 0.4732348322868347,
      "learning_rate": 2.379502326367389e-07,
      "loss": 0.4624,
      "step": 60584
    },
    {
      "epoch": 1.8611187908948486,
      "grad_norm": 0.46643346548080444,
      "learning_rate": 2.3784544543448473e-07,
      "loss": 0.461,
      "step": 60585
    },
    {
      "epoch": 1.8611495100297977,
      "grad_norm": 0.5069565176963806,
      "learning_rate": 2.3774068103242232e-07,
      "loss": 0.5368,
      "step": 60586
    },
    {
      "epoch": 1.8611802291647468,
      "grad_norm": 0.4156022071838379,
      "learning_rate": 2.3763593943079922e-07,
      "loss": 0.4298,
      "step": 60587
    },
    {
      "epoch": 1.861210948299696,
      "grad_norm": 0.4483746290206909,
      "learning_rate": 2.3753122062985967e-07,
      "loss": 0.4648,
      "step": 60588
    },
    {
      "epoch": 1.861241667434645,
      "grad_norm": 0.4620259404182434,
      "learning_rate": 2.3742652462984795e-07,
      "loss": 0.5146,
      "step": 60589
    },
    {
      "epoch": 1.8612723865695942,
      "grad_norm": 0.45758727192878723,
      "learning_rate": 2.3732185143100716e-07,
      "loss": 0.4699,
      "step": 60590
    },
    {
      "epoch": 1.8613031057045433,
      "grad_norm": 0.46443215012550354,
      "learning_rate": 2.372172010335838e-07,
      "loss": 0.4904,
      "step": 60591
    },
    {
      "epoch": 1.8613338248394924,
      "grad_norm": 0.44470757246017456,
      "learning_rate": 2.37112573437821e-07,
      "loss": 0.4428,
      "step": 60592
    },
    {
      "epoch": 1.8613645439744417,
      "grad_norm": 0.5319643020629883,
      "learning_rate": 2.3700796864396415e-07,
      "loss": 0.422,
      "step": 60593
    },
    {
      "epoch": 1.8613952631093909,
      "grad_norm": 0.4501717984676361,
      "learning_rate": 2.3690338665225744e-07,
      "loss": 0.4833,
      "step": 60594
    },
    {
      "epoch": 1.86142598224434,
      "grad_norm": 0.4940083920955658,
      "learning_rate": 2.367988274629429e-07,
      "loss": 0.4395,
      "step": 60595
    },
    {
      "epoch": 1.8614567013792893,
      "grad_norm": 0.5229490399360657,
      "learning_rate": 2.3669429107626818e-07,
      "loss": 0.4407,
      "step": 60596
    },
    {
      "epoch": 1.8614874205142384,
      "grad_norm": 0.4497954547405243,
      "learning_rate": 2.3658977749247635e-07,
      "loss": 0.4962,
      "step": 60597
    },
    {
      "epoch": 1.8615181396491876,
      "grad_norm": 0.46917590498924255,
      "learning_rate": 2.3648528671180948e-07,
      "loss": 0.4217,
      "step": 60598
    },
    {
      "epoch": 1.8615488587841367,
      "grad_norm": 0.4735580384731293,
      "learning_rate": 2.363808187345129e-07,
      "loss": 0.4778,
      "step": 60599
    },
    {
      "epoch": 1.8615795779190858,
      "grad_norm": 0.46281203627586365,
      "learning_rate": 2.36276373560832e-07,
      "loss": 0.4702,
      "step": 60600
    },
    {
      "epoch": 1.861610297054035,
      "grad_norm": 0.4299325942993164,
      "learning_rate": 2.3617195119100877e-07,
      "loss": 0.4717,
      "step": 60601
    },
    {
      "epoch": 1.861641016188984,
      "grad_norm": 0.4521786868572235,
      "learning_rate": 2.360675516252886e-07,
      "loss": 0.4581,
      "step": 60602
    },
    {
      "epoch": 1.8616717353239332,
      "grad_norm": 0.4587700664997101,
      "learning_rate": 2.3596317486391352e-07,
      "loss": 0.5245,
      "step": 60603
    },
    {
      "epoch": 1.8617024544588823,
      "grad_norm": 0.4346141517162323,
      "learning_rate": 2.3585882090712885e-07,
      "loss": 0.4155,
      "step": 60604
    },
    {
      "epoch": 1.8617331735938316,
      "grad_norm": 0.4612433910369873,
      "learning_rate": 2.357544897551778e-07,
      "loss": 0.3471,
      "step": 60605
    },
    {
      "epoch": 1.8617638927287807,
      "grad_norm": 0.41485634446144104,
      "learning_rate": 2.3565018140830455e-07,
      "loss": 0.4573,
      "step": 60606
    },
    {
      "epoch": 1.86179461186373,
      "grad_norm": 0.4404172897338867,
      "learning_rate": 2.3554589586675224e-07,
      "loss": 0.4572,
      "step": 60607
    },
    {
      "epoch": 1.8618253309986792,
      "grad_norm": 0.5248016715049744,
      "learning_rate": 2.3544163313076406e-07,
      "loss": 0.4399,
      "step": 60608
    },
    {
      "epoch": 1.8618560501336283,
      "grad_norm": 0.4464278519153595,
      "learning_rate": 2.3533739320058313e-07,
      "loss": 0.4634,
      "step": 60609
    },
    {
      "epoch": 1.8618867692685774,
      "grad_norm": 0.4732937216758728,
      "learning_rate": 2.3523317607645478e-07,
      "loss": 0.4529,
      "step": 60610
    },
    {
      "epoch": 1.8619174884035266,
      "grad_norm": 0.578926682472229,
      "learning_rate": 2.351289817586211e-07,
      "loss": 0.4228,
      "step": 60611
    },
    {
      "epoch": 1.8619482075384757,
      "grad_norm": 0.44453367590904236,
      "learning_rate": 2.3502481024732626e-07,
      "loss": 0.4564,
      "step": 60612
    },
    {
      "epoch": 1.8619789266734248,
      "grad_norm": 0.42692801356315613,
      "learning_rate": 2.3492066154281122e-07,
      "loss": 0.462,
      "step": 60613
    },
    {
      "epoch": 1.862009645808374,
      "grad_norm": 0.45316267013549805,
      "learning_rate": 2.3481653564532246e-07,
      "loss": 0.5395,
      "step": 60614
    },
    {
      "epoch": 1.862040364943323,
      "grad_norm": 0.44290754199028015,
      "learning_rate": 2.347124325551009e-07,
      "loss": 0.4582,
      "step": 60615
    },
    {
      "epoch": 1.8620710840782724,
      "grad_norm": 0.44319331645965576,
      "learning_rate": 2.3460835227239077e-07,
      "loss": 0.494,
      "step": 60616
    },
    {
      "epoch": 1.8621018032132215,
      "grad_norm": 0.45613041520118713,
      "learning_rate": 2.345042947974352e-07,
      "loss": 0.4757,
      "step": 60617
    },
    {
      "epoch": 1.8621325223481708,
      "grad_norm": 0.497110515832901,
      "learning_rate": 2.3440026013047513e-07,
      "loss": 0.4605,
      "step": 60618
    },
    {
      "epoch": 1.86216324148312,
      "grad_norm": 0.44010964035987854,
      "learning_rate": 2.3429624827175702e-07,
      "loss": 0.483,
      "step": 60619
    },
    {
      "epoch": 1.862193960618069,
      "grad_norm": 0.43331438302993774,
      "learning_rate": 2.3419225922152177e-07,
      "loss": 0.5237,
      "step": 60620
    },
    {
      "epoch": 1.8622246797530182,
      "grad_norm": 0.419197142124176,
      "learning_rate": 2.3408829298001257e-07,
      "loss": 0.4581,
      "step": 60621
    },
    {
      "epoch": 1.8622553988879673,
      "grad_norm": 0.5130155086517334,
      "learning_rate": 2.339843495474714e-07,
      "loss": 0.4867,
      "step": 60622
    },
    {
      "epoch": 1.8622861180229164,
      "grad_norm": 0.38601410388946533,
      "learning_rate": 2.3388042892414253e-07,
      "loss": 0.4611,
      "step": 60623
    },
    {
      "epoch": 1.8623168371578656,
      "grad_norm": 0.4213261306285858,
      "learning_rate": 2.33776531110268e-07,
      "loss": 0.5043,
      "step": 60624
    },
    {
      "epoch": 1.8623475562928147,
      "grad_norm": 0.46211302280426025,
      "learning_rate": 2.336726561060909e-07,
      "loss": 0.4347,
      "step": 60625
    },
    {
      "epoch": 1.8623782754277638,
      "grad_norm": 0.45902225375175476,
      "learning_rate": 2.3356880391185221e-07,
      "loss": 0.4537,
      "step": 60626
    },
    {
      "epoch": 1.8624089945627131,
      "grad_norm": 0.40617021918296814,
      "learning_rate": 2.3346497452779615e-07,
      "loss": 0.541,
      "step": 60627
    },
    {
      "epoch": 1.8624397136976623,
      "grad_norm": 0.4755694270133972,
      "learning_rate": 2.3336116795416474e-07,
      "loss": 0.5072,
      "step": 60628
    },
    {
      "epoch": 1.8624704328326116,
      "grad_norm": 0.4548640549182892,
      "learning_rate": 2.3325738419120114e-07,
      "loss": 0.5674,
      "step": 60629
    },
    {
      "epoch": 1.8625011519675607,
      "grad_norm": 0.4492979049682617,
      "learning_rate": 2.3315362323914626e-07,
      "loss": 0.5484,
      "step": 60630
    },
    {
      "epoch": 1.8625318711025098,
      "grad_norm": 0.5017241835594177,
      "learning_rate": 2.3304988509824321e-07,
      "loss": 0.4316,
      "step": 60631
    },
    {
      "epoch": 1.862562590237459,
      "grad_norm": 0.44556573033332825,
      "learning_rate": 2.3294616976873407e-07,
      "loss": 0.4753,
      "step": 60632
    },
    {
      "epoch": 1.862593309372408,
      "grad_norm": 0.5308550596237183,
      "learning_rate": 2.3284247725086196e-07,
      "loss": 0.4338,
      "step": 60633
    },
    {
      "epoch": 1.8626240285073572,
      "grad_norm": 0.4287993311882019,
      "learning_rate": 2.3273880754486778e-07,
      "loss": 0.4763,
      "step": 60634
    },
    {
      "epoch": 1.8626547476423063,
      "grad_norm": 0.41434890031814575,
      "learning_rate": 2.326351606509958e-07,
      "loss": 0.4415,
      "step": 60635
    },
    {
      "epoch": 1.8626854667772554,
      "grad_norm": 0.381414532661438,
      "learning_rate": 2.3253153656948356e-07,
      "loss": 0.4595,
      "step": 60636
    },
    {
      "epoch": 1.8627161859122046,
      "grad_norm": 0.5203344821929932,
      "learning_rate": 2.324279353005776e-07,
      "loss": 0.5163,
      "step": 60637
    },
    {
      "epoch": 1.862746905047154,
      "grad_norm": 0.47635695338249207,
      "learning_rate": 2.3232435684451994e-07,
      "loss": 0.3896,
      "step": 60638
    },
    {
      "epoch": 1.862777624182103,
      "grad_norm": 0.4253746569156647,
      "learning_rate": 2.322208012015492e-07,
      "loss": 0.4373,
      "step": 60639
    },
    {
      "epoch": 1.8628083433170521,
      "grad_norm": 0.4461500346660614,
      "learning_rate": 2.3211726837190861e-07,
      "loss": 0.5138,
      "step": 60640
    },
    {
      "epoch": 1.8628390624520015,
      "grad_norm": 0.5146840810775757,
      "learning_rate": 2.3201375835584018e-07,
      "loss": 0.4544,
      "step": 60641
    },
    {
      "epoch": 1.8628697815869506,
      "grad_norm": 0.42547568678855896,
      "learning_rate": 2.319102711535881e-07,
      "loss": 0.4445,
      "step": 60642
    },
    {
      "epoch": 1.8629005007218997,
      "grad_norm": 0.4144206941127777,
      "learning_rate": 2.3180680676539003e-07,
      "loss": 0.4898,
      "step": 60643
    },
    {
      "epoch": 1.8629312198568488,
      "grad_norm": 0.4906260073184967,
      "learning_rate": 2.3170336519149016e-07,
      "loss": 0.4494,
      "step": 60644
    },
    {
      "epoch": 1.862961938991798,
      "grad_norm": 0.411332368850708,
      "learning_rate": 2.3159994643212725e-07,
      "loss": 0.415,
      "step": 60645
    },
    {
      "epoch": 1.862992658126747,
      "grad_norm": 0.4371219575405121,
      "learning_rate": 2.314965504875466e-07,
      "loss": 0.4853,
      "step": 60646
    },
    {
      "epoch": 1.8630233772616962,
      "grad_norm": 0.41622254252433777,
      "learning_rate": 2.3139317735798807e-07,
      "loss": 0.4619,
      "step": 60647
    },
    {
      "epoch": 1.8630540963966453,
      "grad_norm": 0.4465562403202057,
      "learning_rate": 2.3128982704369362e-07,
      "loss": 0.5185,
      "step": 60648
    },
    {
      "epoch": 1.8630848155315947,
      "grad_norm": 0.4010562002658844,
      "learning_rate": 2.31186499544902e-07,
      "loss": 0.4767,
      "step": 60649
    },
    {
      "epoch": 1.8631155346665438,
      "grad_norm": 0.4319286048412323,
      "learning_rate": 2.3108319486185747e-07,
      "loss": 0.4212,
      "step": 60650
    },
    {
      "epoch": 1.863146253801493,
      "grad_norm": 0.46198588609695435,
      "learning_rate": 2.3097991299480093e-07,
      "loss": 0.4627,
      "step": 60651
    },
    {
      "epoch": 1.8631769729364422,
      "grad_norm": 0.47254419326782227,
      "learning_rate": 2.308766539439733e-07,
      "loss": 0.3554,
      "step": 60652
    },
    {
      "epoch": 1.8632076920713914,
      "grad_norm": 0.429385781288147,
      "learning_rate": 2.3077341770961437e-07,
      "loss": 0.4611,
      "step": 60653
    },
    {
      "epoch": 1.8632384112063405,
      "grad_norm": 0.4326118230819702,
      "learning_rate": 2.306702042919673e-07,
      "loss": 0.4236,
      "step": 60654
    },
    {
      "epoch": 1.8632691303412896,
      "grad_norm": 0.4749738276004791,
      "learning_rate": 2.3056701369127076e-07,
      "loss": 0.4076,
      "step": 60655
    },
    {
      "epoch": 1.8632998494762387,
      "grad_norm": 0.442987322807312,
      "learning_rate": 2.3046384590776795e-07,
      "loss": 0.4318,
      "step": 60656
    },
    {
      "epoch": 1.8633305686111878,
      "grad_norm": 0.3939334452152252,
      "learning_rate": 2.3036070094170082e-07,
      "loss": 0.4613,
      "step": 60657
    },
    {
      "epoch": 1.863361287746137,
      "grad_norm": 0.39785096049308777,
      "learning_rate": 2.3025757879330702e-07,
      "loss": 0.4012,
      "step": 60658
    },
    {
      "epoch": 1.863392006881086,
      "grad_norm": 0.45558032393455505,
      "learning_rate": 2.3015447946282854e-07,
      "loss": 0.4814,
      "step": 60659
    },
    {
      "epoch": 1.8634227260160354,
      "grad_norm": 0.46072959899902344,
      "learning_rate": 2.3005140295050742e-07,
      "loss": 0.4948,
      "step": 60660
    },
    {
      "epoch": 1.8634534451509845,
      "grad_norm": 0.4742216467857361,
      "learning_rate": 2.299483492565846e-07,
      "loss": 0.4962,
      "step": 60661
    },
    {
      "epoch": 1.8634841642859337,
      "grad_norm": 0.518962025642395,
      "learning_rate": 2.2984531838129764e-07,
      "loss": 0.4941,
      "step": 60662
    },
    {
      "epoch": 1.863514883420883,
      "grad_norm": 0.4515753984451294,
      "learning_rate": 2.2974231032488968e-07,
      "loss": 0.4663,
      "step": 60663
    },
    {
      "epoch": 1.8635456025558321,
      "grad_norm": 0.45756521821022034,
      "learning_rate": 2.2963932508760168e-07,
      "loss": 0.4716,
      "step": 60664
    },
    {
      "epoch": 1.8635763216907812,
      "grad_norm": 0.6529568433761597,
      "learning_rate": 2.295363626696734e-07,
      "loss": 0.5195,
      "step": 60665
    },
    {
      "epoch": 1.8636070408257304,
      "grad_norm": 1.1481575965881348,
      "learning_rate": 2.2943342307134576e-07,
      "loss": 0.4622,
      "step": 60666
    },
    {
      "epoch": 1.8636377599606795,
      "grad_norm": 0.4475001394748688,
      "learning_rate": 2.2933050629285747e-07,
      "loss": 0.5426,
      "step": 60667
    },
    {
      "epoch": 1.8636684790956286,
      "grad_norm": 0.4799536168575287,
      "learning_rate": 2.2922761233445058e-07,
      "loss": 0.4969,
      "step": 60668
    },
    {
      "epoch": 1.8636991982305777,
      "grad_norm": 0.46630382537841797,
      "learning_rate": 2.2912474119636598e-07,
      "loss": 0.4121,
      "step": 60669
    },
    {
      "epoch": 1.8637299173655268,
      "grad_norm": 0.39735695719718933,
      "learning_rate": 2.2902189287884123e-07,
      "loss": 0.4695,
      "step": 60670
    },
    {
      "epoch": 1.8637606365004762,
      "grad_norm": 0.5603352785110474,
      "learning_rate": 2.2891906738211956e-07,
      "loss": 0.5071,
      "step": 60671
    },
    {
      "epoch": 1.8637913556354253,
      "grad_norm": 0.5005438923835754,
      "learning_rate": 2.2881626470643848e-07,
      "loss": 0.4425,
      "step": 60672
    },
    {
      "epoch": 1.8638220747703744,
      "grad_norm": 0.4332503378391266,
      "learning_rate": 2.2871348485204002e-07,
      "loss": 0.4383,
      "step": 60673
    },
    {
      "epoch": 1.8638527939053238,
      "grad_norm": 0.5021468997001648,
      "learning_rate": 2.2861072781916405e-07,
      "loss": 0.4276,
      "step": 60674
    },
    {
      "epoch": 1.8638835130402729,
      "grad_norm": 0.45043763518333435,
      "learning_rate": 2.2850799360805033e-07,
      "loss": 0.5077,
      "step": 60675
    },
    {
      "epoch": 1.863914232175222,
      "grad_norm": 0.43402352929115295,
      "learning_rate": 2.2840528221893864e-07,
      "loss": 0.5193,
      "step": 60676
    },
    {
      "epoch": 1.8639449513101711,
      "grad_norm": 0.4524988532066345,
      "learning_rate": 2.2830259365206776e-07,
      "loss": 0.4533,
      "step": 60677
    },
    {
      "epoch": 1.8639756704451202,
      "grad_norm": 0.4926100969314575,
      "learning_rate": 2.2819992790767965e-07,
      "loss": 0.4609,
      "step": 60678
    },
    {
      "epoch": 1.8640063895800694,
      "grad_norm": 0.41643285751342773,
      "learning_rate": 2.2809728498601303e-07,
      "loss": 0.4589,
      "step": 60679
    },
    {
      "epoch": 1.8640371087150185,
      "grad_norm": 0.44894829392433167,
      "learning_rate": 2.279946648873077e-07,
      "loss": 0.4645,
      "step": 60680
    },
    {
      "epoch": 1.8640678278499676,
      "grad_norm": 0.4080314338207245,
      "learning_rate": 2.278920676118024e-07,
      "loss": 0.448,
      "step": 60681
    },
    {
      "epoch": 1.864098546984917,
      "grad_norm": 0.4567476511001587,
      "learning_rate": 2.2778949315973908e-07,
      "loss": 0.5143,
      "step": 60682
    },
    {
      "epoch": 1.864129266119866,
      "grad_norm": 0.46858084201812744,
      "learning_rate": 2.276869415313543e-07,
      "loss": 0.4166,
      "step": 60683
    },
    {
      "epoch": 1.8641599852548152,
      "grad_norm": 0.42253798246383667,
      "learning_rate": 2.2758441272689114e-07,
      "loss": 0.3704,
      "step": 60684
    },
    {
      "epoch": 1.8641907043897645,
      "grad_norm": 0.41868022084236145,
      "learning_rate": 2.2748190674658498e-07,
      "loss": 0.5303,
      "step": 60685
    },
    {
      "epoch": 1.8642214235247137,
      "grad_norm": 0.44329795241355896,
      "learning_rate": 2.2737942359067788e-07,
      "loss": 0.434,
      "step": 60686
    },
    {
      "epoch": 1.8642521426596628,
      "grad_norm": 0.3921431303024292,
      "learning_rate": 2.272769632594085e-07,
      "loss": 0.4289,
      "step": 60687
    },
    {
      "epoch": 1.864282861794612,
      "grad_norm": 0.38579657673835754,
      "learning_rate": 2.271745257530178e-07,
      "loss": 0.4726,
      "step": 60688
    },
    {
      "epoch": 1.864313580929561,
      "grad_norm": 0.4848825931549072,
      "learning_rate": 2.270721110717422e-07,
      "loss": 0.5069,
      "step": 60689
    },
    {
      "epoch": 1.8643443000645101,
      "grad_norm": 0.3420087695121765,
      "learning_rate": 2.2696971921582266e-07,
      "loss": 0.3942,
      "step": 60690
    },
    {
      "epoch": 1.8643750191994592,
      "grad_norm": 0.44594475626945496,
      "learning_rate": 2.2686735018549676e-07,
      "loss": 0.4477,
      "step": 60691
    },
    {
      "epoch": 1.8644057383344084,
      "grad_norm": 0.44523656368255615,
      "learning_rate": 2.2676500398100544e-07,
      "loss": 0.4116,
      "step": 60692
    },
    {
      "epoch": 1.8644364574693577,
      "grad_norm": 0.42053020000457764,
      "learning_rate": 2.2666268060258845e-07,
      "loss": 0.4565,
      "step": 60693
    },
    {
      "epoch": 1.8644671766043068,
      "grad_norm": 0.43047598004341125,
      "learning_rate": 2.265603800504823e-07,
      "loss": 0.3885,
      "step": 60694
    },
    {
      "epoch": 1.864497895739256,
      "grad_norm": 0.45097053050994873,
      "learning_rate": 2.264581023249257e-07,
      "loss": 0.4783,
      "step": 60695
    },
    {
      "epoch": 1.8645286148742053,
      "grad_norm": 0.38603565096855164,
      "learning_rate": 2.2635584742615958e-07,
      "loss": 0.4512,
      "step": 60696
    },
    {
      "epoch": 1.8645593340091544,
      "grad_norm": 0.4230770766735077,
      "learning_rate": 2.262536153544237e-07,
      "loss": 0.4343,
      "step": 60697
    },
    {
      "epoch": 1.8645900531441035,
      "grad_norm": 0.3932894170284271,
      "learning_rate": 2.2615140610995344e-07,
      "loss": 0.5048,
      "step": 60698
    },
    {
      "epoch": 1.8646207722790527,
      "grad_norm": 0.5465917587280273,
      "learning_rate": 2.2604921969298867e-07,
      "loss": 0.4087,
      "step": 60699
    },
    {
      "epoch": 1.8646514914140018,
      "grad_norm": 0.43277066946029663,
      "learning_rate": 2.259470561037691e-07,
      "loss": 0.5323,
      "step": 60700
    },
    {
      "epoch": 1.864682210548951,
      "grad_norm": 0.4265548884868622,
      "learning_rate": 2.258449153425335e-07,
      "loss": 0.4648,
      "step": 60701
    },
    {
      "epoch": 1.8647129296839,
      "grad_norm": 0.4714834988117218,
      "learning_rate": 2.2574279740951943e-07,
      "loss": 0.4242,
      "step": 60702
    },
    {
      "epoch": 1.8647436488188491,
      "grad_norm": 0.4061111807823181,
      "learning_rate": 2.2564070230496448e-07,
      "loss": 0.4946,
      "step": 60703
    },
    {
      "epoch": 1.8647743679537985,
      "grad_norm": 0.4443483352661133,
      "learning_rate": 2.2553863002910958e-07,
      "loss": 0.4573,
      "step": 60704
    },
    {
      "epoch": 1.8648050870887476,
      "grad_norm": 0.4636659324169159,
      "learning_rate": 2.2543658058219231e-07,
      "loss": 0.4607,
      "step": 60705
    },
    {
      "epoch": 1.8648358062236967,
      "grad_norm": 0.39599281549453735,
      "learning_rate": 2.2533455396444915e-07,
      "loss": 0.481,
      "step": 60706
    },
    {
      "epoch": 1.864866525358646,
      "grad_norm": 0.4491499662399292,
      "learning_rate": 2.25232550176121e-07,
      "loss": 0.5195,
      "step": 60707
    },
    {
      "epoch": 1.8648972444935952,
      "grad_norm": 0.4302639067173004,
      "learning_rate": 2.2513056921744326e-07,
      "loss": 0.4517,
      "step": 60708
    },
    {
      "epoch": 1.8649279636285443,
      "grad_norm": 0.4726276099681854,
      "learning_rate": 2.250286110886568e-07,
      "loss": 0.4554,
      "step": 60709
    },
    {
      "epoch": 1.8649586827634934,
      "grad_norm": 0.4568693935871124,
      "learning_rate": 2.2492667578999928e-07,
      "loss": 0.4791,
      "step": 60710
    },
    {
      "epoch": 1.8649894018984425,
      "grad_norm": 0.4480765759944916,
      "learning_rate": 2.248247633217071e-07,
      "loss": 0.4796,
      "step": 60711
    },
    {
      "epoch": 1.8650201210333917,
      "grad_norm": 0.44908106327056885,
      "learning_rate": 2.2472287368402012e-07,
      "loss": 0.5004,
      "step": 60712
    },
    {
      "epoch": 1.8650508401683408,
      "grad_norm": 0.8190978169441223,
      "learning_rate": 2.246210068771748e-07,
      "loss": 0.4991,
      "step": 60713
    },
    {
      "epoch": 1.86508155930329,
      "grad_norm": 0.4149779975414276,
      "learning_rate": 2.2451916290141096e-07,
      "loss": 0.4838,
      "step": 60714
    },
    {
      "epoch": 1.865112278438239,
      "grad_norm": 0.3903394341468811,
      "learning_rate": 2.2441734175696395e-07,
      "loss": 0.4002,
      "step": 60715
    },
    {
      "epoch": 1.8651429975731884,
      "grad_norm": 0.4384426176548004,
      "learning_rate": 2.243155434440747e-07,
      "loss": 0.4546,
      "step": 60716
    },
    {
      "epoch": 1.8651737167081375,
      "grad_norm": 0.43402281403541565,
      "learning_rate": 2.2421376796297855e-07,
      "loss": 0.3859,
      "step": 60717
    },
    {
      "epoch": 1.8652044358430868,
      "grad_norm": 0.3938828408718109,
      "learning_rate": 2.2411201531391313e-07,
      "loss": 0.4546,
      "step": 60718
    },
    {
      "epoch": 1.865235154978036,
      "grad_norm": 0.43514367938041687,
      "learning_rate": 2.2401028549711713e-07,
      "loss": 0.4633,
      "step": 60719
    },
    {
      "epoch": 1.865265874112985,
      "grad_norm": 0.4670819640159607,
      "learning_rate": 2.239085785128281e-07,
      "loss": 0.4884,
      "step": 60720
    },
    {
      "epoch": 1.8652965932479342,
      "grad_norm": 0.4726675748825073,
      "learning_rate": 2.2380689436128367e-07,
      "loss": 0.5149,
      "step": 60721
    },
    {
      "epoch": 1.8653273123828833,
      "grad_norm": 0.44273579120635986,
      "learning_rate": 2.237052330427203e-07,
      "loss": 0.5384,
      "step": 60722
    },
    {
      "epoch": 1.8653580315178324,
      "grad_norm": 0.47712668776512146,
      "learning_rate": 2.2360359455737556e-07,
      "loss": 0.4841,
      "step": 60723
    },
    {
      "epoch": 1.8653887506527815,
      "grad_norm": 0.4374094009399414,
      "learning_rate": 2.235019789054893e-07,
      "loss": 0.391,
      "step": 60724
    },
    {
      "epoch": 1.8654194697877307,
      "grad_norm": 0.4381354749202728,
      "learning_rate": 2.2340038608729574e-07,
      "loss": 0.4697,
      "step": 60725
    },
    {
      "epoch": 1.8654501889226798,
      "grad_norm": 0.45193734765052795,
      "learning_rate": 2.232988161030325e-07,
      "loss": 0.4939,
      "step": 60726
    },
    {
      "epoch": 1.8654809080576291,
      "grad_norm": 0.4222854673862457,
      "learning_rate": 2.2319726895293825e-07,
      "loss": 0.4806,
      "step": 60727
    },
    {
      "epoch": 1.8655116271925782,
      "grad_norm": 0.41186195611953735,
      "learning_rate": 2.230957446372506e-07,
      "loss": 0.4737,
      "step": 60728
    },
    {
      "epoch": 1.8655423463275276,
      "grad_norm": 0.4189181625843048,
      "learning_rate": 2.22994243156206e-07,
      "loss": 0.4826,
      "step": 60729
    },
    {
      "epoch": 1.8655730654624767,
      "grad_norm": 0.46016183495521545,
      "learning_rate": 2.2289276451003983e-07,
      "loss": 0.6286,
      "step": 60730
    },
    {
      "epoch": 1.8656037845974258,
      "grad_norm": 0.47562581300735474,
      "learning_rate": 2.2279130869898967e-07,
      "loss": 0.4417,
      "step": 60731
    },
    {
      "epoch": 1.865634503732375,
      "grad_norm": 0.4717191755771637,
      "learning_rate": 2.2268987572329426e-07,
      "loss": 0.4667,
      "step": 60732
    },
    {
      "epoch": 1.865665222867324,
      "grad_norm": 0.5067960023880005,
      "learning_rate": 2.2258846558319113e-07,
      "loss": 0.5047,
      "step": 60733
    },
    {
      "epoch": 1.8656959420022732,
      "grad_norm": 0.445465087890625,
      "learning_rate": 2.2248707827891346e-07,
      "loss": 0.4818,
      "step": 60734
    },
    {
      "epoch": 1.8657266611372223,
      "grad_norm": 0.4234507381916046,
      "learning_rate": 2.2238571381069995e-07,
      "loss": 0.4599,
      "step": 60735
    },
    {
      "epoch": 1.8657573802721714,
      "grad_norm": 0.4963442087173462,
      "learning_rate": 2.2228437217878817e-07,
      "loss": 0.437,
      "step": 60736
    },
    {
      "epoch": 1.8657880994071205,
      "grad_norm": 0.43178075551986694,
      "learning_rate": 2.221830533834146e-07,
      "loss": 0.3778,
      "step": 60737
    },
    {
      "epoch": 1.8658188185420699,
      "grad_norm": 0.4385930299758911,
      "learning_rate": 2.2208175742481464e-07,
      "loss": 0.444,
      "step": 60738
    },
    {
      "epoch": 1.865849537677019,
      "grad_norm": 0.4591285288333893,
      "learning_rate": 2.2198048430322693e-07,
      "loss": 0.4611,
      "step": 60739
    },
    {
      "epoch": 1.8658802568119683,
      "grad_norm": 0.5240657925605774,
      "learning_rate": 2.2187923401888357e-07,
      "loss": 0.5541,
      "step": 60740
    },
    {
      "epoch": 1.8659109759469175,
      "grad_norm": 0.46683168411254883,
      "learning_rate": 2.2177800657202764e-07,
      "loss": 0.4606,
      "step": 60741
    },
    {
      "epoch": 1.8659416950818666,
      "grad_norm": 0.44135594367980957,
      "learning_rate": 2.216768019628901e-07,
      "loss": 0.3924,
      "step": 60742
    },
    {
      "epoch": 1.8659724142168157,
      "grad_norm": 0.4467197358608246,
      "learning_rate": 2.2157562019171074e-07,
      "loss": 0.5123,
      "step": 60743
    },
    {
      "epoch": 1.8660031333517648,
      "grad_norm": 0.46004343032836914,
      "learning_rate": 2.2147446125872163e-07,
      "loss": 0.4132,
      "step": 60744
    },
    {
      "epoch": 1.866033852486714,
      "grad_norm": 0.4257355332374573,
      "learning_rate": 2.2137332516416477e-07,
      "loss": 0.5586,
      "step": 60745
    },
    {
      "epoch": 1.866064571621663,
      "grad_norm": 0.4454711377620697,
      "learning_rate": 2.212722119082722e-07,
      "loss": 0.4545,
      "step": 60746
    },
    {
      "epoch": 1.8660952907566122,
      "grad_norm": 0.42498502135276794,
      "learning_rate": 2.211711214912815e-07,
      "loss": 0.5086,
      "step": 60747
    },
    {
      "epoch": 1.8661260098915613,
      "grad_norm": 0.4149492084980011,
      "learning_rate": 2.2107005391342917e-07,
      "loss": 0.513,
      "step": 60748
    },
    {
      "epoch": 1.8661567290265106,
      "grad_norm": 0.43504923582077026,
      "learning_rate": 2.2096900917494833e-07,
      "loss": 0.4459,
      "step": 60749
    },
    {
      "epoch": 1.8661874481614598,
      "grad_norm": 0.4264911115169525,
      "learning_rate": 2.2086798727607996e-07,
      "loss": 0.492,
      "step": 60750
    },
    {
      "epoch": 1.8662181672964089,
      "grad_norm": 0.43584176898002625,
      "learning_rate": 2.20766988217056e-07,
      "loss": 0.4338,
      "step": 60751
    },
    {
      "epoch": 1.8662488864313582,
      "grad_norm": 0.445592999458313,
      "learning_rate": 2.206660119981152e-07,
      "loss": 0.4711,
      "step": 60752
    },
    {
      "epoch": 1.8662796055663073,
      "grad_norm": 0.46379560232162476,
      "learning_rate": 2.2056505861949074e-07,
      "loss": 0.5501,
      "step": 60753
    },
    {
      "epoch": 1.8663103247012565,
      "grad_norm": 0.41047266125679016,
      "learning_rate": 2.2046412808141903e-07,
      "loss": 0.464,
      "step": 60754
    },
    {
      "epoch": 1.8663410438362056,
      "grad_norm": 0.4432249069213867,
      "learning_rate": 2.203632203841366e-07,
      "loss": 0.366,
      "step": 60755
    },
    {
      "epoch": 1.8663717629711547,
      "grad_norm": 0.4127301871776581,
      "learning_rate": 2.20262335527881e-07,
      "loss": 0.4357,
      "step": 60756
    },
    {
      "epoch": 1.8664024821061038,
      "grad_norm": 0.5360982418060303,
      "learning_rate": 2.201614735128832e-07,
      "loss": 0.3538,
      "step": 60757
    },
    {
      "epoch": 1.866433201241053,
      "grad_norm": 0.42984840273857117,
      "learning_rate": 2.2006063433938185e-07,
      "loss": 0.4223,
      "step": 60758
    },
    {
      "epoch": 1.866463920376002,
      "grad_norm": 0.43168774247169495,
      "learning_rate": 2.1995981800761236e-07,
      "loss": 0.4541,
      "step": 60759
    },
    {
      "epoch": 1.8664946395109514,
      "grad_norm": 0.43800196051597595,
      "learning_rate": 2.1985902451781005e-07,
      "loss": 0.5081,
      "step": 60760
    },
    {
      "epoch": 1.8665253586459005,
      "grad_norm": 0.43186384439468384,
      "learning_rate": 2.1975825387020922e-07,
      "loss": 0.435,
      "step": 60761
    },
    {
      "epoch": 1.8665560777808496,
      "grad_norm": 0.4574282169342041,
      "learning_rate": 2.196575060650463e-07,
      "loss": 0.3784,
      "step": 60762
    },
    {
      "epoch": 1.866586796915799,
      "grad_norm": 0.45109593868255615,
      "learning_rate": 2.1955678110255675e-07,
      "loss": 0.5682,
      "step": 60763
    },
    {
      "epoch": 1.866617516050748,
      "grad_norm": 0.4411870837211609,
      "learning_rate": 2.1945607898297472e-07,
      "loss": 0.4466,
      "step": 60764
    },
    {
      "epoch": 1.8666482351856972,
      "grad_norm": 0.4677746891975403,
      "learning_rate": 2.1935539970653674e-07,
      "loss": 0.4371,
      "step": 60765
    },
    {
      "epoch": 1.8666789543206463,
      "grad_norm": 0.38909316062927246,
      "learning_rate": 2.1925474327347706e-07,
      "loss": 0.4603,
      "step": 60766
    },
    {
      "epoch": 1.8667096734555955,
      "grad_norm": 0.41403084993362427,
      "learning_rate": 2.1915410968402996e-07,
      "loss": 0.4324,
      "step": 60767
    },
    {
      "epoch": 1.8667403925905446,
      "grad_norm": 0.45383220911026,
      "learning_rate": 2.1905349893843297e-07,
      "loss": 0.562,
      "step": 60768
    },
    {
      "epoch": 1.8667711117254937,
      "grad_norm": 0.45470762252807617,
      "learning_rate": 2.189529110369193e-07,
      "loss": 0.4281,
      "step": 60769
    },
    {
      "epoch": 1.8668018308604428,
      "grad_norm": 0.41837549209594727,
      "learning_rate": 2.1885234597972427e-07,
      "loss": 0.4592,
      "step": 60770
    },
    {
      "epoch": 1.8668325499953922,
      "grad_norm": 0.43691474199295044,
      "learning_rate": 2.1875180376708217e-07,
      "loss": 0.4857,
      "step": 60771
    },
    {
      "epoch": 1.8668632691303413,
      "grad_norm": 0.4251435697078705,
      "learning_rate": 2.1865128439922835e-07,
      "loss": 0.4514,
      "step": 60772
    },
    {
      "epoch": 1.8668939882652904,
      "grad_norm": 0.4582970440387726,
      "learning_rate": 2.1855078787639815e-07,
      "loss": 0.4664,
      "step": 60773
    },
    {
      "epoch": 1.8669247074002397,
      "grad_norm": 0.4292813837528229,
      "learning_rate": 2.184503141988259e-07,
      "loss": 0.4078,
      "step": 60774
    },
    {
      "epoch": 1.8669554265351889,
      "grad_norm": 0.4108399748802185,
      "learning_rate": 2.1834986336674578e-07,
      "loss": 0.438,
      "step": 60775
    },
    {
      "epoch": 1.866986145670138,
      "grad_norm": 0.4631056487560272,
      "learning_rate": 2.18249435380391e-07,
      "loss": 0.4457,
      "step": 60776
    },
    {
      "epoch": 1.867016864805087,
      "grad_norm": 0.42368265986442566,
      "learning_rate": 2.1814903024000023e-07,
      "loss": 0.4892,
      "step": 60777
    },
    {
      "epoch": 1.8670475839400362,
      "grad_norm": 0.42689841985702515,
      "learning_rate": 2.1804864794580439e-07,
      "loss": 0.4307,
      "step": 60778
    },
    {
      "epoch": 1.8670783030749853,
      "grad_norm": 0.4243782162666321,
      "learning_rate": 2.1794828849803994e-07,
      "loss": 0.4551,
      "step": 60779
    },
    {
      "epoch": 1.8671090222099345,
      "grad_norm": 0.4667744040489197,
      "learning_rate": 2.178479518969401e-07,
      "loss": 0.5285,
      "step": 60780
    },
    {
      "epoch": 1.8671397413448836,
      "grad_norm": 0.43597862124443054,
      "learning_rate": 2.1774763814273904e-07,
      "loss": 0.5283,
      "step": 60781
    },
    {
      "epoch": 1.867170460479833,
      "grad_norm": 0.4028213918209076,
      "learning_rate": 2.1764734723567104e-07,
      "loss": 0.3704,
      "step": 60782
    },
    {
      "epoch": 1.867201179614782,
      "grad_norm": 0.40133899450302124,
      "learning_rate": 2.175470791759715e-07,
      "loss": 0.5116,
      "step": 60783
    },
    {
      "epoch": 1.8672318987497312,
      "grad_norm": 0.444611132144928,
      "learning_rate": 2.1744683396387466e-07,
      "loss": 0.5112,
      "step": 60784
    },
    {
      "epoch": 1.8672626178846805,
      "grad_norm": 0.5862663984298706,
      "learning_rate": 2.1734661159961257e-07,
      "loss": 0.451,
      "step": 60785
    },
    {
      "epoch": 1.8672933370196296,
      "grad_norm": 0.4503360986709595,
      "learning_rate": 2.172464120834228e-07,
      "loss": 0.4855,
      "step": 60786
    },
    {
      "epoch": 1.8673240561545787,
      "grad_norm": 0.4673892855644226,
      "learning_rate": 2.1714623541553516e-07,
      "loss": 0.4854,
      "step": 60787
    },
    {
      "epoch": 1.8673547752895279,
      "grad_norm": 0.4672091007232666,
      "learning_rate": 2.1704608159618724e-07,
      "loss": 0.4948,
      "step": 60788
    },
    {
      "epoch": 1.867385494424477,
      "grad_norm": 0.4193459451198578,
      "learning_rate": 2.1694595062560998e-07,
      "loss": 0.5513,
      "step": 60789
    },
    {
      "epoch": 1.867416213559426,
      "grad_norm": 0.45726442337036133,
      "learning_rate": 2.1684584250403984e-07,
      "loss": 0.4428,
      "step": 60790
    },
    {
      "epoch": 1.8674469326943752,
      "grad_norm": 0.4731651842594147,
      "learning_rate": 2.1674575723170887e-07,
      "loss": 0.5353,
      "step": 60791
    },
    {
      "epoch": 1.8674776518293243,
      "grad_norm": 0.46368706226348877,
      "learning_rate": 2.1664569480885246e-07,
      "loss": 0.4552,
      "step": 60792
    },
    {
      "epoch": 1.8675083709642737,
      "grad_norm": 0.4295859932899475,
      "learning_rate": 2.1654565523570148e-07,
      "loss": 0.4913,
      "step": 60793
    },
    {
      "epoch": 1.8675390900992228,
      "grad_norm": 0.42458289861679077,
      "learning_rate": 2.1644563851249246e-07,
      "loss": 0.4533,
      "step": 60794
    },
    {
      "epoch": 1.867569809234172,
      "grad_norm": 0.4381033778190613,
      "learning_rate": 2.163456446394574e-07,
      "loss": 0.511,
      "step": 60795
    },
    {
      "epoch": 1.8676005283691213,
      "grad_norm": 0.43290093541145325,
      "learning_rate": 2.1624567361683167e-07,
      "loss": 0.4042,
      "step": 60796
    },
    {
      "epoch": 1.8676312475040704,
      "grad_norm": 0.44537341594696045,
      "learning_rate": 2.1614572544484624e-07,
      "loss": 0.5154,
      "step": 60797
    },
    {
      "epoch": 1.8676619666390195,
      "grad_norm": 0.43746572732925415,
      "learning_rate": 2.1604580012373644e-07,
      "loss": 0.5253,
      "step": 60798
    },
    {
      "epoch": 1.8676926857739686,
      "grad_norm": 0.46327483654022217,
      "learning_rate": 2.159458976537343e-07,
      "loss": 0.5208,
      "step": 60799
    },
    {
      "epoch": 1.8677234049089178,
      "grad_norm": 0.4375934302806854,
      "learning_rate": 2.158460180350741e-07,
      "loss": 0.4656,
      "step": 60800
    },
    {
      "epoch": 1.8677541240438669,
      "grad_norm": 0.4670957326889038,
      "learning_rate": 2.1574616126798898e-07,
      "loss": 0.4876,
      "step": 60801
    },
    {
      "epoch": 1.867784843178816,
      "grad_norm": 0.425149530172348,
      "learning_rate": 2.1564632735271208e-07,
      "loss": 0.4233,
      "step": 60802
    },
    {
      "epoch": 1.867815562313765,
      "grad_norm": 0.4463619589805603,
      "learning_rate": 2.1554651628947542e-07,
      "loss": 0.4345,
      "step": 60803
    },
    {
      "epoch": 1.8678462814487145,
      "grad_norm": 0.4307347238063812,
      "learning_rate": 2.154467280785144e-07,
      "loss": 0.4958,
      "step": 60804
    },
    {
      "epoch": 1.8678770005836636,
      "grad_norm": 0.42396748065948486,
      "learning_rate": 2.1534696272006106e-07,
      "loss": 0.5199,
      "step": 60805
    },
    {
      "epoch": 1.8679077197186127,
      "grad_norm": 0.43587642908096313,
      "learning_rate": 2.1524722021434852e-07,
      "loss": 0.4884,
      "step": 60806
    },
    {
      "epoch": 1.867938438853562,
      "grad_norm": 0.45432180166244507,
      "learning_rate": 2.1514750056160773e-07,
      "loss": 0.4302,
      "step": 60807
    },
    {
      "epoch": 1.8679691579885112,
      "grad_norm": 0.4497475326061249,
      "learning_rate": 2.1504780376207402e-07,
      "loss": 0.458,
      "step": 60808
    },
    {
      "epoch": 1.8679998771234603,
      "grad_norm": 0.47136133909225464,
      "learning_rate": 2.1494812981598058e-07,
      "loss": 0.5006,
      "step": 60809
    },
    {
      "epoch": 1.8680305962584094,
      "grad_norm": 0.47464612126350403,
      "learning_rate": 2.148484787235583e-07,
      "loss": 0.426,
      "step": 60810
    },
    {
      "epoch": 1.8680613153933585,
      "grad_norm": 0.4195420742034912,
      "learning_rate": 2.1474885048504256e-07,
      "loss": 0.4686,
      "step": 60811
    },
    {
      "epoch": 1.8680920345283076,
      "grad_norm": 0.40616267919540405,
      "learning_rate": 2.14649245100661e-07,
      "loss": 0.503,
      "step": 60812
    },
    {
      "epoch": 1.8681227536632568,
      "grad_norm": 0.41166841983795166,
      "learning_rate": 2.1454966257065223e-07,
      "loss": 0.4667,
      "step": 60813
    },
    {
      "epoch": 1.8681534727982059,
      "grad_norm": 0.458821177482605,
      "learning_rate": 2.1445010289524505e-07,
      "loss": 0.439,
      "step": 60814
    },
    {
      "epoch": 1.8681841919331552,
      "grad_norm": 0.4519526958465576,
      "learning_rate": 2.1435056607467363e-07,
      "loss": 0.4429,
      "step": 60815
    },
    {
      "epoch": 1.8682149110681043,
      "grad_norm": 0.4018966555595398,
      "learning_rate": 2.1425105210916898e-07,
      "loss": 0.5039,
      "step": 60816
    },
    {
      "epoch": 1.8682456302030535,
      "grad_norm": 0.425911009311676,
      "learning_rate": 2.1415156099896418e-07,
      "loss": 0.4773,
      "step": 60817
    },
    {
      "epoch": 1.8682763493380028,
      "grad_norm": 0.40788519382476807,
      "learning_rate": 2.1405209274429238e-07,
      "loss": 0.4437,
      "step": 60818
    },
    {
      "epoch": 1.868307068472952,
      "grad_norm": 0.4344014525413513,
      "learning_rate": 2.1395264734538568e-07,
      "loss": 0.4557,
      "step": 60819
    },
    {
      "epoch": 1.868337787607901,
      "grad_norm": 0.42369598150253296,
      "learning_rate": 2.1385322480247604e-07,
      "loss": 0.4652,
      "step": 60820
    },
    {
      "epoch": 1.8683685067428502,
      "grad_norm": 0.42438188195228577,
      "learning_rate": 2.1375382511579557e-07,
      "loss": 0.5606,
      "step": 60821
    },
    {
      "epoch": 1.8683992258777993,
      "grad_norm": 0.45345577597618103,
      "learning_rate": 2.1365444828557623e-07,
      "loss": 0.5042,
      "step": 60822
    },
    {
      "epoch": 1.8684299450127484,
      "grad_norm": 0.4629006087779999,
      "learning_rate": 2.1355509431205012e-07,
      "loss": 0.4603,
      "step": 60823
    },
    {
      "epoch": 1.8684606641476975,
      "grad_norm": 0.4316916763782501,
      "learning_rate": 2.1345576319545035e-07,
      "loss": 0.4469,
      "step": 60824
    },
    {
      "epoch": 1.8684913832826466,
      "grad_norm": 0.4898873567581177,
      "learning_rate": 2.1335645493600788e-07,
      "loss": 0.4748,
      "step": 60825
    },
    {
      "epoch": 1.868522102417596,
      "grad_norm": 0.46270716190338135,
      "learning_rate": 2.1325716953395469e-07,
      "loss": 0.5264,
      "step": 60826
    },
    {
      "epoch": 1.868552821552545,
      "grad_norm": 0.44817107915878296,
      "learning_rate": 2.1315790698952288e-07,
      "loss": 0.4115,
      "step": 60827
    },
    {
      "epoch": 1.8685835406874942,
      "grad_norm": 0.4737120568752289,
      "learning_rate": 2.1305866730294444e-07,
      "loss": 0.4596,
      "step": 60828
    },
    {
      "epoch": 1.8686142598224436,
      "grad_norm": 0.46673277020454407,
      "learning_rate": 2.1295945047445032e-07,
      "loss": 0.3913,
      "step": 60829
    },
    {
      "epoch": 1.8686449789573927,
      "grad_norm": 0.4341818392276764,
      "learning_rate": 2.1286025650427367e-07,
      "loss": 0.4556,
      "step": 60830
    },
    {
      "epoch": 1.8686756980923418,
      "grad_norm": 0.43687859177589417,
      "learning_rate": 2.127610853926454e-07,
      "loss": 0.5297,
      "step": 60831
    },
    {
      "epoch": 1.868706417227291,
      "grad_norm": 0.4927099049091339,
      "learning_rate": 2.1266193713979756e-07,
      "loss": 0.4895,
      "step": 60832
    },
    {
      "epoch": 1.86873713636224,
      "grad_norm": 0.45858606696128845,
      "learning_rate": 2.1256281174595994e-07,
      "loss": 0.483,
      "step": 60833
    },
    {
      "epoch": 1.8687678554971892,
      "grad_norm": 0.41288429498672485,
      "learning_rate": 2.1246370921136682e-07,
      "loss": 0.4845,
      "step": 60834
    },
    {
      "epoch": 1.8687985746321383,
      "grad_norm": 0.4717978537082672,
      "learning_rate": 2.1236462953624694e-07,
      "loss": 0.46,
      "step": 60835
    },
    {
      "epoch": 1.8688292937670874,
      "grad_norm": 0.4486241042613983,
      "learning_rate": 2.1226557272083447e-07,
      "loss": 0.4479,
      "step": 60836
    },
    {
      "epoch": 1.8688600129020365,
      "grad_norm": 0.4525294303894043,
      "learning_rate": 2.121665387653582e-07,
      "loss": 0.4814,
      "step": 60837
    },
    {
      "epoch": 1.8688907320369859,
      "grad_norm": 0.4742988646030426,
      "learning_rate": 2.1206752767005123e-07,
      "loss": 0.446,
      "step": 60838
    },
    {
      "epoch": 1.868921451171935,
      "grad_norm": 0.48401641845703125,
      "learning_rate": 2.1196853943514338e-07,
      "loss": 0.4704,
      "step": 60839
    },
    {
      "epoch": 1.8689521703068843,
      "grad_norm": 0.44007349014282227,
      "learning_rate": 2.1186957406086672e-07,
      "loss": 0.4782,
      "step": 60840
    },
    {
      "epoch": 1.8689828894418334,
      "grad_norm": 0.4535819888114929,
      "learning_rate": 2.1177063154745326e-07,
      "loss": 0.5062,
      "step": 60841
    },
    {
      "epoch": 1.8690136085767826,
      "grad_norm": 0.4555451571941376,
      "learning_rate": 2.116717118951328e-07,
      "loss": 0.5242,
      "step": 60842
    },
    {
      "epoch": 1.8690443277117317,
      "grad_norm": 0.47383660078048706,
      "learning_rate": 2.115728151041363e-07,
      "loss": 0.4562,
      "step": 60843
    },
    {
      "epoch": 1.8690750468466808,
      "grad_norm": 0.40657156705856323,
      "learning_rate": 2.1147394117469467e-07,
      "loss": 0.4337,
      "step": 60844
    },
    {
      "epoch": 1.86910576598163,
      "grad_norm": 0.5083134174346924,
      "learning_rate": 2.1137509010703993e-07,
      "loss": 0.4481,
      "step": 60845
    },
    {
      "epoch": 1.869136485116579,
      "grad_norm": 0.4429998993873596,
      "learning_rate": 2.1127626190140194e-07,
      "loss": 0.4535,
      "step": 60846
    },
    {
      "epoch": 1.8691672042515282,
      "grad_norm": 0.4168373644351959,
      "learning_rate": 2.111774565580127e-07,
      "loss": 0.4205,
      "step": 60847
    },
    {
      "epoch": 1.8691979233864773,
      "grad_norm": 0.39766475558280945,
      "learning_rate": 2.1107867407710092e-07,
      "loss": 0.472,
      "step": 60848
    },
    {
      "epoch": 1.8692286425214266,
      "grad_norm": 0.42470768094062805,
      "learning_rate": 2.1097991445889977e-07,
      "loss": 0.4528,
      "step": 60849
    },
    {
      "epoch": 1.8692593616563757,
      "grad_norm": 0.4302191734313965,
      "learning_rate": 2.1088117770363792e-07,
      "loss": 0.492,
      "step": 60850
    },
    {
      "epoch": 1.869290080791325,
      "grad_norm": 0.4030301570892334,
      "learning_rate": 2.1078246381154743e-07,
      "loss": 0.4074,
      "step": 60851
    },
    {
      "epoch": 1.8693207999262742,
      "grad_norm": 0.42267245054244995,
      "learning_rate": 2.1068377278285702e-07,
      "loss": 0.4193,
      "step": 60852
    },
    {
      "epoch": 1.8693515190612233,
      "grad_norm": 0.3924923241138458,
      "learning_rate": 2.1058510461779868e-07,
      "loss": 0.4389,
      "step": 60853
    },
    {
      "epoch": 1.8693822381961724,
      "grad_norm": 0.4853941798210144,
      "learning_rate": 2.1048645931660227e-07,
      "loss": 0.4729,
      "step": 60854
    },
    {
      "epoch": 1.8694129573311216,
      "grad_norm": 0.4121774435043335,
      "learning_rate": 2.1038783687949872e-07,
      "loss": 0.4426,
      "step": 60855
    },
    {
      "epoch": 1.8694436764660707,
      "grad_norm": 0.448318213224411,
      "learning_rate": 2.102892373067189e-07,
      "loss": 0.4752,
      "step": 60856
    },
    {
      "epoch": 1.8694743956010198,
      "grad_norm": 0.3958422541618347,
      "learning_rate": 2.1019066059849158e-07,
      "loss": 0.4752,
      "step": 60857
    },
    {
      "epoch": 1.869505114735969,
      "grad_norm": 0.42272377014160156,
      "learning_rate": 2.1009210675504764e-07,
      "loss": 0.47,
      "step": 60858
    },
    {
      "epoch": 1.869535833870918,
      "grad_norm": 0.42910459637641907,
      "learning_rate": 2.0999357577661694e-07,
      "loss": 0.527,
      "step": 60859
    },
    {
      "epoch": 1.8695665530058674,
      "grad_norm": 0.4092492461204529,
      "learning_rate": 2.0989506766343148e-07,
      "loss": 0.383,
      "step": 60860
    },
    {
      "epoch": 1.8695972721408165,
      "grad_norm": 0.4550400376319885,
      "learning_rate": 2.0979658241571888e-07,
      "loss": 0.4739,
      "step": 60861
    },
    {
      "epoch": 1.8696279912757656,
      "grad_norm": 0.41915667057037354,
      "learning_rate": 2.0969812003371005e-07,
      "loss": 0.4268,
      "step": 60862
    },
    {
      "epoch": 1.869658710410715,
      "grad_norm": 0.4224838316440582,
      "learning_rate": 2.095996805176337e-07,
      "loss": 0.5032,
      "step": 60863
    },
    {
      "epoch": 1.869689429545664,
      "grad_norm": 0.4605099558830261,
      "learning_rate": 2.0950126386772296e-07,
      "loss": 0.4722,
      "step": 60864
    },
    {
      "epoch": 1.8697201486806132,
      "grad_norm": 0.46077942848205566,
      "learning_rate": 2.0940287008420547e-07,
      "loss": 0.4639,
      "step": 60865
    },
    {
      "epoch": 1.8697508678155623,
      "grad_norm": 0.47335562109947205,
      "learning_rate": 2.09304499167311e-07,
      "loss": 0.4166,
      "step": 60866
    },
    {
      "epoch": 1.8697815869505114,
      "grad_norm": 0.42525649070739746,
      "learning_rate": 2.0920615111726937e-07,
      "loss": 0.4421,
      "step": 60867
    },
    {
      "epoch": 1.8698123060854606,
      "grad_norm": 0.4553564488887787,
      "learning_rate": 2.0910782593431156e-07,
      "loss": 0.4558,
      "step": 60868
    },
    {
      "epoch": 1.8698430252204097,
      "grad_norm": 0.44191819429397583,
      "learning_rate": 2.0900952361866512e-07,
      "loss": 0.5385,
      "step": 60869
    },
    {
      "epoch": 1.8698737443553588,
      "grad_norm": 0.4012647867202759,
      "learning_rate": 2.0891124417056096e-07,
      "loss": 0.4801,
      "step": 60870
    },
    {
      "epoch": 1.8699044634903081,
      "grad_norm": 0.5043196082115173,
      "learning_rate": 2.0881298759022784e-07,
      "loss": 0.5481,
      "step": 60871
    },
    {
      "epoch": 1.8699351826252573,
      "grad_norm": 0.4296455681324005,
      "learning_rate": 2.0871475387789775e-07,
      "loss": 0.5341,
      "step": 60872
    },
    {
      "epoch": 1.8699659017602064,
      "grad_norm": 0.4447802007198334,
      "learning_rate": 2.086165430337961e-07,
      "loss": 0.5407,
      "step": 60873
    },
    {
      "epoch": 1.8699966208951557,
      "grad_norm": 0.4369368255138397,
      "learning_rate": 2.0851835505815488e-07,
      "loss": 0.4552,
      "step": 60874
    },
    {
      "epoch": 1.8700273400301048,
      "grad_norm": 0.42761510610580444,
      "learning_rate": 2.0842018995120284e-07,
      "loss": 0.3891,
      "step": 60875
    },
    {
      "epoch": 1.870058059165054,
      "grad_norm": 0.42396700382232666,
      "learning_rate": 2.0832204771316978e-07,
      "loss": 0.4977,
      "step": 60876
    },
    {
      "epoch": 1.870088778300003,
      "grad_norm": 0.414458692073822,
      "learning_rate": 2.082239283442844e-07,
      "loss": 0.5018,
      "step": 60877
    },
    {
      "epoch": 1.8701194974349522,
      "grad_norm": 0.46021291613578796,
      "learning_rate": 2.081258318447754e-07,
      "loss": 0.445,
      "step": 60878
    },
    {
      "epoch": 1.8701502165699013,
      "grad_norm": 0.4326295554637909,
      "learning_rate": 2.0802775821487377e-07,
      "loss": 0.4099,
      "step": 60879
    },
    {
      "epoch": 1.8701809357048504,
      "grad_norm": 0.46176737546920776,
      "learning_rate": 2.079297074548048e-07,
      "loss": 0.4267,
      "step": 60880
    },
    {
      "epoch": 1.8702116548397996,
      "grad_norm": 0.39583730697631836,
      "learning_rate": 2.0783167956480165e-07,
      "loss": 0.5081,
      "step": 60881
    },
    {
      "epoch": 1.870242373974749,
      "grad_norm": 0.3884192705154419,
      "learning_rate": 2.0773367454509086e-07,
      "loss": 0.3966,
      "step": 60882
    },
    {
      "epoch": 1.870273093109698,
      "grad_norm": 0.4446423649787903,
      "learning_rate": 2.0763569239590332e-07,
      "loss": 0.4147,
      "step": 60883
    },
    {
      "epoch": 1.8703038122446471,
      "grad_norm": 0.45503491163253784,
      "learning_rate": 2.0753773311746438e-07,
      "loss": 0.4742,
      "step": 60884
    },
    {
      "epoch": 1.8703345313795965,
      "grad_norm": 0.40743330121040344,
      "learning_rate": 2.0743979671000614e-07,
      "loss": 0.5376,
      "step": 60885
    },
    {
      "epoch": 1.8703652505145456,
      "grad_norm": 0.3956882655620575,
      "learning_rate": 2.0734188317375502e-07,
      "loss": 0.457,
      "step": 60886
    },
    {
      "epoch": 1.8703959696494947,
      "grad_norm": 0.42263489961624146,
      "learning_rate": 2.072439925089431e-07,
      "loss": 0.4949,
      "step": 60887
    },
    {
      "epoch": 1.8704266887844438,
      "grad_norm": 0.4630874991416931,
      "learning_rate": 2.0714612471579466e-07,
      "loss": 0.4213,
      "step": 60888
    },
    {
      "epoch": 1.870457407919393,
      "grad_norm": 0.4270167350769043,
      "learning_rate": 2.0704827979454056e-07,
      "loss": 0.5079,
      "step": 60889
    },
    {
      "epoch": 1.870488127054342,
      "grad_norm": 0.4242592453956604,
      "learning_rate": 2.0695045774540956e-07,
      "loss": 0.4539,
      "step": 60890
    },
    {
      "epoch": 1.8705188461892912,
      "grad_norm": 0.43193137645721436,
      "learning_rate": 2.0685265856863035e-07,
      "loss": 0.4663,
      "step": 60891
    },
    {
      "epoch": 1.8705495653242403,
      "grad_norm": 0.4339712858200073,
      "learning_rate": 2.0675488226443053e-07,
      "loss": 0.4514,
      "step": 60892
    },
    {
      "epoch": 1.8705802844591897,
      "grad_norm": 0.4458518326282501,
      "learning_rate": 2.0665712883303767e-07,
      "loss": 0.4514,
      "step": 60893
    },
    {
      "epoch": 1.8706110035941388,
      "grad_norm": 0.44860216975212097,
      "learning_rate": 2.0655939827468165e-07,
      "loss": 0.417,
      "step": 60894
    },
    {
      "epoch": 1.870641722729088,
      "grad_norm": 0.44677644968032837,
      "learning_rate": 2.0646169058959e-07,
      "loss": 0.4239,
      "step": 60895
    },
    {
      "epoch": 1.8706724418640372,
      "grad_norm": 0.461334764957428,
      "learning_rate": 2.0636400577799142e-07,
      "loss": 0.4705,
      "step": 60896
    },
    {
      "epoch": 1.8707031609989864,
      "grad_norm": 0.45825812220573425,
      "learning_rate": 2.0626634384011356e-07,
      "loss": 0.4576,
      "step": 60897
    },
    {
      "epoch": 1.8707338801339355,
      "grad_norm": 0.43385541439056396,
      "learning_rate": 2.06168704776184e-07,
      "loss": 0.4702,
      "step": 60898
    },
    {
      "epoch": 1.8707645992688846,
      "grad_norm": 0.43601903319358826,
      "learning_rate": 2.0607108858643142e-07,
      "loss": 0.4924,
      "step": 60899
    },
    {
      "epoch": 1.8707953184038337,
      "grad_norm": 0.41188549995422363,
      "learning_rate": 2.0597349527108568e-07,
      "loss": 0.4283,
      "step": 60900
    },
    {
      "epoch": 1.8708260375387828,
      "grad_norm": 0.4259214699268341,
      "learning_rate": 2.05875924830371e-07,
      "loss": 0.4596,
      "step": 60901
    },
    {
      "epoch": 1.870856756673732,
      "grad_norm": 0.4127117395401001,
      "learning_rate": 2.0577837726451722e-07,
      "loss": 0.5076,
      "step": 60902
    },
    {
      "epoch": 1.870887475808681,
      "grad_norm": 0.44083666801452637,
      "learning_rate": 2.0568085257375192e-07,
      "loss": 0.5262,
      "step": 60903
    },
    {
      "epoch": 1.8709181949436304,
      "grad_norm": 0.41007402539253235,
      "learning_rate": 2.0558335075830383e-07,
      "loss": 0.4926,
      "step": 60904
    },
    {
      "epoch": 1.8709489140785796,
      "grad_norm": 0.43497732281684875,
      "learning_rate": 2.054858718183994e-07,
      "loss": 0.4392,
      "step": 60905
    },
    {
      "epoch": 1.8709796332135287,
      "grad_norm": 0.42967820167541504,
      "learning_rate": 2.0538841575426848e-07,
      "loss": 0.4408,
      "step": 60906
    },
    {
      "epoch": 1.871010352348478,
      "grad_norm": 0.4572787880897522,
      "learning_rate": 2.052909825661342e-07,
      "loss": 0.5749,
      "step": 60907
    },
    {
      "epoch": 1.8710410714834271,
      "grad_norm": 0.4296230673789978,
      "learning_rate": 2.0519357225422864e-07,
      "loss": 0.4129,
      "step": 60908
    },
    {
      "epoch": 1.8710717906183763,
      "grad_norm": 0.48628726601600647,
      "learning_rate": 2.05096184818776e-07,
      "loss": 0.4486,
      "step": 60909
    },
    {
      "epoch": 1.8711025097533254,
      "grad_norm": 0.4386526942253113,
      "learning_rate": 2.0499882026000616e-07,
      "loss": 0.5665,
      "step": 60910
    },
    {
      "epoch": 1.8711332288882745,
      "grad_norm": 0.4999178647994995,
      "learning_rate": 2.0490147857814557e-07,
      "loss": 0.4077,
      "step": 60911
    },
    {
      "epoch": 1.8711639480232236,
      "grad_norm": 0.4571632146835327,
      "learning_rate": 2.0480415977342182e-07,
      "loss": 0.5052,
      "step": 60912
    },
    {
      "epoch": 1.8711946671581727,
      "grad_norm": 0.5094486474990845,
      "learning_rate": 2.0470686384606253e-07,
      "loss": 0.4658,
      "step": 60913
    },
    {
      "epoch": 1.8712253862931219,
      "grad_norm": 0.4314311146736145,
      "learning_rate": 2.0460959079629416e-07,
      "loss": 0.4387,
      "step": 60914
    },
    {
      "epoch": 1.8712561054280712,
      "grad_norm": 0.42411160469055176,
      "learning_rate": 2.0451234062434432e-07,
      "loss": 0.4577,
      "step": 60915
    },
    {
      "epoch": 1.8712868245630203,
      "grad_norm": 0.41451573371887207,
      "learning_rate": 2.0441511333043839e-07,
      "loss": 0.5136,
      "step": 60916
    },
    {
      "epoch": 1.8713175436979694,
      "grad_norm": 0.43535763025283813,
      "learning_rate": 2.0431790891480728e-07,
      "loss": 0.5231,
      "step": 60917
    },
    {
      "epoch": 1.8713482628329188,
      "grad_norm": 0.43038231134414673,
      "learning_rate": 2.042207273776753e-07,
      "loss": 0.5165,
      "step": 60918
    },
    {
      "epoch": 1.871378981967868,
      "grad_norm": 0.44527938961982727,
      "learning_rate": 2.0412356871926997e-07,
      "loss": 0.51,
      "step": 60919
    },
    {
      "epoch": 1.871409701102817,
      "grad_norm": 0.4365948736667633,
      "learning_rate": 2.0402643293981782e-07,
      "loss": 0.4836,
      "step": 60920
    },
    {
      "epoch": 1.8714404202377661,
      "grad_norm": 0.4286904036998749,
      "learning_rate": 2.0392932003954534e-07,
      "loss": 0.4389,
      "step": 60921
    },
    {
      "epoch": 1.8714711393727153,
      "grad_norm": 0.442016065120697,
      "learning_rate": 2.0383223001868124e-07,
      "loss": 0.4453,
      "step": 60922
    },
    {
      "epoch": 1.8715018585076644,
      "grad_norm": 0.6976160407066345,
      "learning_rate": 2.0373516287745088e-07,
      "loss": 0.3879,
      "step": 60923
    },
    {
      "epoch": 1.8715325776426135,
      "grad_norm": 0.44776007533073425,
      "learning_rate": 2.0363811861608075e-07,
      "loss": 0.4575,
      "step": 60924
    },
    {
      "epoch": 1.8715632967775626,
      "grad_norm": 0.46224892139434814,
      "learning_rate": 2.0354109723479842e-07,
      "loss": 0.4677,
      "step": 60925
    },
    {
      "epoch": 1.871594015912512,
      "grad_norm": 0.4947500228881836,
      "learning_rate": 2.034440987338293e-07,
      "loss": 0.5055,
      "step": 60926
    },
    {
      "epoch": 1.871624735047461,
      "grad_norm": 0.43857869505882263,
      "learning_rate": 2.033471231134021e-07,
      "loss": 0.3361,
      "step": 60927
    },
    {
      "epoch": 1.8716554541824102,
      "grad_norm": 0.47049590945243835,
      "learning_rate": 2.0325017037373995e-07,
      "loss": 0.4438,
      "step": 60928
    },
    {
      "epoch": 1.8716861733173595,
      "grad_norm": 0.4537530541419983,
      "learning_rate": 2.0315324051507268e-07,
      "loss": 0.4146,
      "step": 60929
    },
    {
      "epoch": 1.8717168924523087,
      "grad_norm": 0.3836478292942047,
      "learning_rate": 2.0305633353762455e-07,
      "loss": 0.3848,
      "step": 60930
    },
    {
      "epoch": 1.8717476115872578,
      "grad_norm": 0.4207392632961273,
      "learning_rate": 2.0295944944162204e-07,
      "loss": 0.4197,
      "step": 60931
    },
    {
      "epoch": 1.871778330722207,
      "grad_norm": 0.41599413752555847,
      "learning_rate": 2.0286258822729388e-07,
      "loss": 0.4561,
      "step": 60932
    },
    {
      "epoch": 1.871809049857156,
      "grad_norm": 0.4249313771724701,
      "learning_rate": 2.027657498948632e-07,
      "loss": 0.4557,
      "step": 60933
    },
    {
      "epoch": 1.8718397689921051,
      "grad_norm": 0.43292680382728577,
      "learning_rate": 2.0266893444455648e-07,
      "loss": 0.4896,
      "step": 60934
    },
    {
      "epoch": 1.8718704881270543,
      "grad_norm": 0.5282884240150452,
      "learning_rate": 2.0257214187660134e-07,
      "loss": 0.4066,
      "step": 60935
    },
    {
      "epoch": 1.8719012072620034,
      "grad_norm": 0.4230532646179199,
      "learning_rate": 2.0247537219122427e-07,
      "loss": 0.4703,
      "step": 60936
    },
    {
      "epoch": 1.8719319263969527,
      "grad_norm": 0.46251052618026733,
      "learning_rate": 2.023786253886495e-07,
      "loss": 0.4533,
      "step": 60937
    },
    {
      "epoch": 1.8719626455319018,
      "grad_norm": 0.46185192465782166,
      "learning_rate": 2.0228190146910354e-07,
      "loss": 0.491,
      "step": 60938
    },
    {
      "epoch": 1.871993364666851,
      "grad_norm": 0.4966859817504883,
      "learning_rate": 2.0218520043281175e-07,
      "loss": 0.5238,
      "step": 60939
    },
    {
      "epoch": 1.8720240838018003,
      "grad_norm": 0.4887431263923645,
      "learning_rate": 2.0208852228000285e-07,
      "loss": 0.4503,
      "step": 60940
    },
    {
      "epoch": 1.8720548029367494,
      "grad_norm": 0.44996681809425354,
      "learning_rate": 2.019918670108989e-07,
      "loss": 0.462,
      "step": 60941
    },
    {
      "epoch": 1.8720855220716985,
      "grad_norm": 0.42417311668395996,
      "learning_rate": 2.0189523462572746e-07,
      "loss": 0.5224,
      "step": 60942
    },
    {
      "epoch": 1.8721162412066477,
      "grad_norm": 0.4360756278038025,
      "learning_rate": 2.0179862512471283e-07,
      "loss": 0.4848,
      "step": 60943
    },
    {
      "epoch": 1.8721469603415968,
      "grad_norm": 0.4329739809036255,
      "learning_rate": 2.0170203850808368e-07,
      "loss": 0.4586,
      "step": 60944
    },
    {
      "epoch": 1.872177679476546,
      "grad_norm": 0.45805877447128296,
      "learning_rate": 2.016054747760632e-07,
      "loss": 0.4593,
      "step": 60945
    },
    {
      "epoch": 1.872208398611495,
      "grad_norm": 0.4398365318775177,
      "learning_rate": 2.0150893392887783e-07,
      "loss": 0.4654,
      "step": 60946
    },
    {
      "epoch": 1.8722391177464441,
      "grad_norm": 0.41503193974494934,
      "learning_rate": 2.0141241596675187e-07,
      "loss": 0.4494,
      "step": 60947
    },
    {
      "epoch": 1.8722698368813933,
      "grad_norm": 0.42862755060195923,
      "learning_rate": 2.013159208899107e-07,
      "loss": 0.4531,
      "step": 60948
    },
    {
      "epoch": 1.8723005560163426,
      "grad_norm": 0.4371955394744873,
      "learning_rate": 2.012194486985819e-07,
      "loss": 0.4739,
      "step": 60949
    },
    {
      "epoch": 1.8723312751512917,
      "grad_norm": 0.40637272596359253,
      "learning_rate": 2.0112299939298974e-07,
      "loss": 0.4135,
      "step": 60950
    },
    {
      "epoch": 1.872361994286241,
      "grad_norm": 0.45068758726119995,
      "learning_rate": 2.010265729733585e-07,
      "loss": 0.4447,
      "step": 60951
    },
    {
      "epoch": 1.8723927134211902,
      "grad_norm": 0.4854923486709595,
      "learning_rate": 2.0093016943991351e-07,
      "loss": 0.4915,
      "step": 60952
    },
    {
      "epoch": 1.8724234325561393,
      "grad_norm": 0.5001606345176697,
      "learning_rate": 2.008337887928813e-07,
      "loss": 0.4254,
      "step": 60953
    },
    {
      "epoch": 1.8724541516910884,
      "grad_norm": 0.4453555941581726,
      "learning_rate": 2.007374310324861e-07,
      "loss": 0.4915,
      "step": 60954
    },
    {
      "epoch": 1.8724848708260375,
      "grad_norm": 0.4286377429962158,
      "learning_rate": 2.0064109615895334e-07,
      "loss": 0.454,
      "step": 60955
    },
    {
      "epoch": 1.8725155899609867,
      "grad_norm": 0.44636932015419006,
      "learning_rate": 2.005447841725061e-07,
      "loss": 0.4925,
      "step": 60956
    },
    {
      "epoch": 1.8725463090959358,
      "grad_norm": 0.49960216879844666,
      "learning_rate": 2.0044849507337205e-07,
      "loss": 0.3999,
      "step": 60957
    },
    {
      "epoch": 1.872577028230885,
      "grad_norm": 0.4440687298774719,
      "learning_rate": 2.003522288617743e-07,
      "loss": 0.4609,
      "step": 60958
    },
    {
      "epoch": 1.872607747365834,
      "grad_norm": 0.40225961804389954,
      "learning_rate": 2.0025598553793934e-07,
      "loss": 0.5435,
      "step": 60959
    },
    {
      "epoch": 1.8726384665007834,
      "grad_norm": 0.4286423623561859,
      "learning_rate": 2.0015976510209035e-07,
      "loss": 0.5035,
      "step": 60960
    },
    {
      "epoch": 1.8726691856357325,
      "grad_norm": 0.4366706609725952,
      "learning_rate": 2.0006356755445265e-07,
      "loss": 0.5201,
      "step": 60961
    },
    {
      "epoch": 1.8726999047706818,
      "grad_norm": 0.3951459228992462,
      "learning_rate": 1.999673928952506e-07,
      "loss": 0.5042,
      "step": 60962
    },
    {
      "epoch": 1.872730623905631,
      "grad_norm": 0.4341413974761963,
      "learning_rate": 1.9987124112471057e-07,
      "loss": 0.4439,
      "step": 60963
    },
    {
      "epoch": 1.87276134304058,
      "grad_norm": 0.448977530002594,
      "learning_rate": 1.9977511224305468e-07,
      "loss": 0.4694,
      "step": 60964
    },
    {
      "epoch": 1.8727920621755292,
      "grad_norm": 0.46234625577926636,
      "learning_rate": 1.996790062505083e-07,
      "loss": 0.467,
      "step": 60965
    },
    {
      "epoch": 1.8728227813104783,
      "grad_norm": 0.45055922865867615,
      "learning_rate": 1.9958292314729565e-07,
      "loss": 0.4935,
      "step": 60966
    },
    {
      "epoch": 1.8728535004454274,
      "grad_norm": 1.6196799278259277,
      "learning_rate": 1.9948686293364105e-07,
      "loss": 0.3913,
      "step": 60967
    },
    {
      "epoch": 1.8728842195803765,
      "grad_norm": 0.43169450759887695,
      "learning_rate": 1.9939082560977096e-07,
      "loss": 0.462,
      "step": 60968
    },
    {
      "epoch": 1.8729149387153257,
      "grad_norm": 0.41679996252059937,
      "learning_rate": 1.9929481117590742e-07,
      "loss": 0.3687,
      "step": 60969
    },
    {
      "epoch": 1.8729456578502748,
      "grad_norm": 0.4363923966884613,
      "learning_rate": 1.9919881963227583e-07,
      "loss": 0.4676,
      "step": 60970
    },
    {
      "epoch": 1.8729763769852241,
      "grad_norm": 0.4220466613769531,
      "learning_rate": 1.991028509790982e-07,
      "loss": 0.4673,
      "step": 60971
    },
    {
      "epoch": 1.8730070961201732,
      "grad_norm": 0.4554499089717865,
      "learning_rate": 1.9900690521660216e-07,
      "loss": 0.4431,
      "step": 60972
    },
    {
      "epoch": 1.8730378152551224,
      "grad_norm": 0.4398549199104309,
      "learning_rate": 1.9891098234500972e-07,
      "loss": 0.57,
      "step": 60973
    },
    {
      "epoch": 1.8730685343900717,
      "grad_norm": 0.461194783449173,
      "learning_rate": 1.9881508236454406e-07,
      "loss": 0.4881,
      "step": 60974
    },
    {
      "epoch": 1.8730992535250208,
      "grad_norm": 0.38683879375457764,
      "learning_rate": 1.9871920527543166e-07,
      "loss": 0.4229,
      "step": 60975
    },
    {
      "epoch": 1.87312997265997,
      "grad_norm": 0.3984420895576477,
      "learning_rate": 1.9862335107789455e-07,
      "loss": 0.3556,
      "step": 60976
    },
    {
      "epoch": 1.873160691794919,
      "grad_norm": 0.39796876907348633,
      "learning_rate": 1.98527519772157e-07,
      "loss": 0.4594,
      "step": 60977
    },
    {
      "epoch": 1.8731914109298682,
      "grad_norm": 0.403897225856781,
      "learning_rate": 1.984317113584433e-07,
      "loss": 0.4138,
      "step": 60978
    },
    {
      "epoch": 1.8732221300648173,
      "grad_norm": 0.41862013936042786,
      "learning_rate": 1.9833592583697547e-07,
      "loss": 0.4336,
      "step": 60979
    },
    {
      "epoch": 1.8732528491997664,
      "grad_norm": 0.41100385785102844,
      "learning_rate": 1.9824016320798e-07,
      "loss": 0.4877,
      "step": 60980
    },
    {
      "epoch": 1.8732835683347155,
      "grad_norm": 0.47507232427597046,
      "learning_rate": 1.9814442347167896e-07,
      "loss": 0.513,
      "step": 60981
    },
    {
      "epoch": 1.8733142874696649,
      "grad_norm": 0.39661988615989685,
      "learning_rate": 1.9804870662829656e-07,
      "loss": 0.383,
      "step": 60982
    },
    {
      "epoch": 1.873345006604614,
      "grad_norm": 0.4461422264575958,
      "learning_rate": 1.97953012678056e-07,
      "loss": 0.5212,
      "step": 60983
    },
    {
      "epoch": 1.8733757257395631,
      "grad_norm": 0.4283764362335205,
      "learning_rate": 1.978573416211782e-07,
      "loss": 0.4954,
      "step": 60984
    },
    {
      "epoch": 1.8734064448745125,
      "grad_norm": 0.4371960461139679,
      "learning_rate": 1.9776169345789187e-07,
      "loss": 0.5029,
      "step": 60985
    },
    {
      "epoch": 1.8734371640094616,
      "grad_norm": 0.49548518657684326,
      "learning_rate": 1.9766606818841681e-07,
      "loss": 0.5045,
      "step": 60986
    },
    {
      "epoch": 1.8734678831444107,
      "grad_norm": 0.41985562443733215,
      "learning_rate": 1.9757046581297845e-07,
      "loss": 0.4436,
      "step": 60987
    },
    {
      "epoch": 1.8734986022793598,
      "grad_norm": 0.4048372507095337,
      "learning_rate": 1.9747488633179768e-07,
      "loss": 0.495,
      "step": 60988
    },
    {
      "epoch": 1.873529321414309,
      "grad_norm": 0.41605857014656067,
      "learning_rate": 1.9737932974509876e-07,
      "loss": 0.4485,
      "step": 60989
    },
    {
      "epoch": 1.873560040549258,
      "grad_norm": 0.44281432032585144,
      "learning_rate": 1.9728379605310487e-07,
      "loss": 0.4838,
      "step": 60990
    },
    {
      "epoch": 1.8735907596842072,
      "grad_norm": 0.44086045026779175,
      "learning_rate": 1.9718828525604028e-07,
      "loss": 0.3842,
      "step": 60991
    },
    {
      "epoch": 1.8736214788191563,
      "grad_norm": 0.41362264752388,
      "learning_rate": 1.9709279735412701e-07,
      "loss": 0.4806,
      "step": 60992
    },
    {
      "epoch": 1.8736521979541056,
      "grad_norm": 0.3886363208293915,
      "learning_rate": 1.969973323475871e-07,
      "loss": 0.4985,
      "step": 60993
    },
    {
      "epoch": 1.8736829170890548,
      "grad_norm": 0.4154008626937866,
      "learning_rate": 1.9690189023664486e-07,
      "loss": 0.4343,
      "step": 60994
    },
    {
      "epoch": 1.8737136362240039,
      "grad_norm": 0.41074252128601074,
      "learning_rate": 1.9680647102152338e-07,
      "loss": 0.4515,
      "step": 60995
    },
    {
      "epoch": 1.8737443553589532,
      "grad_norm": 0.42546582221984863,
      "learning_rate": 1.9671107470244476e-07,
      "loss": 0.438,
      "step": 60996
    },
    {
      "epoch": 1.8737750744939023,
      "grad_norm": 0.4199981689453125,
      "learning_rate": 1.9661570127963214e-07,
      "loss": 0.5327,
      "step": 60997
    },
    {
      "epoch": 1.8738057936288515,
      "grad_norm": 0.4398682117462158,
      "learning_rate": 1.9652035075330755e-07,
      "loss": 0.4528,
      "step": 60998
    },
    {
      "epoch": 1.8738365127638006,
      "grad_norm": 0.4755808711051941,
      "learning_rate": 1.9642502312369637e-07,
      "loss": 0.4884,
      "step": 60999
    },
    {
      "epoch": 1.8738672318987497,
      "grad_norm": 0.4225260615348816,
      "learning_rate": 1.9632971839101732e-07,
      "loss": 0.45,
      "step": 61000
    },
    {
      "epoch": 1.8738979510336988,
      "grad_norm": 0.4318740963935852,
      "learning_rate": 1.9623443655549578e-07,
      "loss": 0.5292,
      "step": 61001
    },
    {
      "epoch": 1.873928670168648,
      "grad_norm": 0.4137788414955139,
      "learning_rate": 1.9613917761735267e-07,
      "loss": 0.3962,
      "step": 61002
    },
    {
      "epoch": 1.873959389303597,
      "grad_norm": 0.42970898747444153,
      "learning_rate": 1.9604394157681118e-07,
      "loss": 0.5623,
      "step": 61003
    },
    {
      "epoch": 1.8739901084385464,
      "grad_norm": 0.42359060049057007,
      "learning_rate": 1.959487284340944e-07,
      "loss": 0.3802,
      "step": 61004
    },
    {
      "epoch": 1.8740208275734955,
      "grad_norm": 0.41455239057540894,
      "learning_rate": 1.9585353818942443e-07,
      "loss": 0.4276,
      "step": 61005
    },
    {
      "epoch": 1.8740515467084446,
      "grad_norm": 0.42175936698913574,
      "learning_rate": 1.9575837084302218e-07,
      "loss": 0.5135,
      "step": 61006
    },
    {
      "epoch": 1.874082265843394,
      "grad_norm": 0.43462464213371277,
      "learning_rate": 1.9566322639511082e-07,
      "loss": 0.432,
      "step": 61007
    },
    {
      "epoch": 1.874112984978343,
      "grad_norm": 0.42092111706733704,
      "learning_rate": 1.955681048459146e-07,
      "loss": 0.4909,
      "step": 61008
    },
    {
      "epoch": 1.8741437041132922,
      "grad_norm": 0.41411837935447693,
      "learning_rate": 1.9547300619565224e-07,
      "loss": 0.483,
      "step": 61009
    },
    {
      "epoch": 1.8741744232482414,
      "grad_norm": 0.5067745447158813,
      "learning_rate": 1.95377930444548e-07,
      "loss": 0.54,
      "step": 61010
    },
    {
      "epoch": 1.8742051423831905,
      "grad_norm": 0.4739607572555542,
      "learning_rate": 1.9528287759282173e-07,
      "loss": 0.46,
      "step": 61011
    },
    {
      "epoch": 1.8742358615181396,
      "grad_norm": 0.4342516362667084,
      "learning_rate": 1.9518784764069875e-07,
      "loss": 0.4448,
      "step": 61012
    },
    {
      "epoch": 1.8742665806530887,
      "grad_norm": 0.4299267828464508,
      "learning_rate": 1.9509284058839894e-07,
      "loss": 0.4157,
      "step": 61013
    },
    {
      "epoch": 1.8742972997880378,
      "grad_norm": 0.425910085439682,
      "learning_rate": 1.9499785643614543e-07,
      "loss": 0.4709,
      "step": 61014
    },
    {
      "epoch": 1.8743280189229872,
      "grad_norm": 0.49150219559669495,
      "learning_rate": 1.9490289518415695e-07,
      "loss": 0.4735,
      "step": 61015
    },
    {
      "epoch": 1.8743587380579363,
      "grad_norm": 0.37451231479644775,
      "learning_rate": 1.9480795683265997e-07,
      "loss": 0.4103,
      "step": 61016
    },
    {
      "epoch": 1.8743894571928854,
      "grad_norm": 0.3863450288772583,
      "learning_rate": 1.947130413818721e-07,
      "loss": 0.3689,
      "step": 61017
    },
    {
      "epoch": 1.8744201763278348,
      "grad_norm": 0.4416504204273224,
      "learning_rate": 1.946181488320187e-07,
      "loss": 0.539,
      "step": 61018
    },
    {
      "epoch": 1.8744508954627839,
      "grad_norm": 0.3910408616065979,
      "learning_rate": 1.9452327918331737e-07,
      "loss": 0.3966,
      "step": 61019
    },
    {
      "epoch": 1.874481614597733,
      "grad_norm": 0.4960150718688965,
      "learning_rate": 1.944284324359913e-07,
      "loss": 0.4835,
      "step": 61020
    },
    {
      "epoch": 1.8745123337326821,
      "grad_norm": 0.4118432104587555,
      "learning_rate": 1.9433360859026474e-07,
      "loss": 0.4713,
      "step": 61021
    },
    {
      "epoch": 1.8745430528676312,
      "grad_norm": 0.4482171833515167,
      "learning_rate": 1.942388076463553e-07,
      "loss": 0.5225,
      "step": 61022
    },
    {
      "epoch": 1.8745737720025804,
      "grad_norm": 0.5082198977470398,
      "learning_rate": 1.941440296044872e-07,
      "loss": 0.3968,
      "step": 61023
    },
    {
      "epoch": 1.8746044911375295,
      "grad_norm": 0.41533660888671875,
      "learning_rate": 1.940492744648792e-07,
      "loss": 0.4055,
      "step": 61024
    },
    {
      "epoch": 1.8746352102724786,
      "grad_norm": 0.4135994017124176,
      "learning_rate": 1.9395454222775445e-07,
      "loss": 0.4908,
      "step": 61025
    },
    {
      "epoch": 1.874665929407428,
      "grad_norm": 0.4291878342628479,
      "learning_rate": 1.9385983289333388e-07,
      "loss": 0.4471,
      "step": 61026
    },
    {
      "epoch": 1.874696648542377,
      "grad_norm": 0.47228288650512695,
      "learning_rate": 1.937651464618384e-07,
      "loss": 0.4799,
      "step": 61027
    },
    {
      "epoch": 1.8747273676773262,
      "grad_norm": 0.45946648716926575,
      "learning_rate": 1.93670482933489e-07,
      "loss": 0.4538,
      "step": 61028
    },
    {
      "epoch": 1.8747580868122755,
      "grad_norm": 0.4725790023803711,
      "learning_rate": 1.9357584230850769e-07,
      "loss": 0.4658,
      "step": 61029
    },
    {
      "epoch": 1.8747888059472246,
      "grad_norm": 0.4238773584365845,
      "learning_rate": 1.9348122458711427e-07,
      "loss": 0.5784,
      "step": 61030
    },
    {
      "epoch": 1.8748195250821738,
      "grad_norm": 0.44139525294303894,
      "learning_rate": 1.9338662976953082e-07,
      "loss": 0.5042,
      "step": 61031
    },
    {
      "epoch": 1.8748502442171229,
      "grad_norm": 0.453677237033844,
      "learning_rate": 1.9329205785597717e-07,
      "loss": 0.4823,
      "step": 61032
    },
    {
      "epoch": 1.874880963352072,
      "grad_norm": 0.45739102363586426,
      "learning_rate": 1.931975088466753e-07,
      "loss": 0.4068,
      "step": 61033
    },
    {
      "epoch": 1.8749116824870211,
      "grad_norm": 0.5005906820297241,
      "learning_rate": 1.9310298274184513e-07,
      "loss": 0.5019,
      "step": 61034
    },
    {
      "epoch": 1.8749424016219702,
      "grad_norm": 0.5068445205688477,
      "learning_rate": 1.9300847954170864e-07,
      "loss": 0.3765,
      "step": 61035
    },
    {
      "epoch": 1.8749731207569194,
      "grad_norm": 0.4247437119483948,
      "learning_rate": 1.9291399924648458e-07,
      "loss": 0.4891,
      "step": 61036
    },
    {
      "epoch": 1.8750038398918687,
      "grad_norm": 0.446590393781662,
      "learning_rate": 1.9281954185639494e-07,
      "loss": 0.5386,
      "step": 61037
    },
    {
      "epoch": 1.8750345590268178,
      "grad_norm": 0.44294649362564087,
      "learning_rate": 1.9272510737166074e-07,
      "loss": 0.4622,
      "step": 61038
    },
    {
      "epoch": 1.875065278161767,
      "grad_norm": 0.4526490569114685,
      "learning_rate": 1.926306957925017e-07,
      "loss": 0.427,
      "step": 61039
    },
    {
      "epoch": 1.8750959972967163,
      "grad_norm": 0.4327021837234497,
      "learning_rate": 1.9253630711913995e-07,
      "loss": 0.4057,
      "step": 61040
    },
    {
      "epoch": 1.8751267164316654,
      "grad_norm": 0.43197283148765564,
      "learning_rate": 1.9244194135179305e-07,
      "loss": 0.4338,
      "step": 61041
    },
    {
      "epoch": 1.8751574355666145,
      "grad_norm": 0.4634315073490143,
      "learning_rate": 1.9234759849068308e-07,
      "loss": 0.4501,
      "step": 61042
    },
    {
      "epoch": 1.8751881547015636,
      "grad_norm": 0.41264569759368896,
      "learning_rate": 1.9225327853603093e-07,
      "loss": 0.4612,
      "step": 61043
    },
    {
      "epoch": 1.8752188738365128,
      "grad_norm": 0.4288930296897888,
      "learning_rate": 1.9215898148805644e-07,
      "loss": 0.502,
      "step": 61044
    },
    {
      "epoch": 1.8752495929714619,
      "grad_norm": 0.42997363209724426,
      "learning_rate": 1.9206470734697835e-07,
      "loss": 0.4475,
      "step": 61045
    },
    {
      "epoch": 1.875280312106411,
      "grad_norm": 0.45444732904434204,
      "learning_rate": 1.919704561130198e-07,
      "loss": 0.4248,
      "step": 61046
    },
    {
      "epoch": 1.8753110312413601,
      "grad_norm": 0.43841201066970825,
      "learning_rate": 1.9187622778639724e-07,
      "loss": 0.42,
      "step": 61047
    },
    {
      "epoch": 1.8753417503763095,
      "grad_norm": 0.4839850664138794,
      "learning_rate": 1.917820223673339e-07,
      "loss": 0.4617,
      "step": 61048
    },
    {
      "epoch": 1.8753724695112586,
      "grad_norm": 0.43646493554115295,
      "learning_rate": 1.9168783985604844e-07,
      "loss": 0.5056,
      "step": 61049
    },
    {
      "epoch": 1.8754031886462077,
      "grad_norm": 0.4135490655899048,
      "learning_rate": 1.9159368025276182e-07,
      "loss": 0.4401,
      "step": 61050
    },
    {
      "epoch": 1.875433907781157,
      "grad_norm": 0.42521339654922485,
      "learning_rate": 1.9149954355769163e-07,
      "loss": 0.4384,
      "step": 61051
    },
    {
      "epoch": 1.8754646269161062,
      "grad_norm": 0.4440059959888458,
      "learning_rate": 1.9140542977105992e-07,
      "loss": 0.5545,
      "step": 61052
    },
    {
      "epoch": 1.8754953460510553,
      "grad_norm": 0.48475706577301025,
      "learning_rate": 1.9131133889308652e-07,
      "loss": 0.601,
      "step": 61053
    },
    {
      "epoch": 1.8755260651860044,
      "grad_norm": 0.4002056419849396,
      "learning_rate": 1.912172709239901e-07,
      "loss": 0.4384,
      "step": 61054
    },
    {
      "epoch": 1.8755567843209535,
      "grad_norm": 0.44971293210983276,
      "learning_rate": 1.9112322586399058e-07,
      "loss": 0.4939,
      "step": 61055
    },
    {
      "epoch": 1.8755875034559026,
      "grad_norm": 0.4306747317314148,
      "learning_rate": 1.9102920371330657e-07,
      "loss": 0.4854,
      "step": 61056
    },
    {
      "epoch": 1.8756182225908518,
      "grad_norm": 0.45720574259757996,
      "learning_rate": 1.909352044721613e-07,
      "loss": 0.4091,
      "step": 61057
    },
    {
      "epoch": 1.8756489417258009,
      "grad_norm": 0.5031062960624695,
      "learning_rate": 1.9084122814077011e-07,
      "loss": 0.5257,
      "step": 61058
    },
    {
      "epoch": 1.87567966086075,
      "grad_norm": 0.41590023040771484,
      "learning_rate": 1.9074727471935617e-07,
      "loss": 0.434,
      "step": 61059
    },
    {
      "epoch": 1.8757103799956993,
      "grad_norm": 0.45772936940193176,
      "learning_rate": 1.9065334420813596e-07,
      "loss": 0.4347,
      "step": 61060
    },
    {
      "epoch": 1.8757410991306485,
      "grad_norm": 0.4533017575740814,
      "learning_rate": 1.9055943660732935e-07,
      "loss": 0.4511,
      "step": 61061
    },
    {
      "epoch": 1.8757718182655978,
      "grad_norm": 0.44840165972709656,
      "learning_rate": 1.904655519171561e-07,
      "loss": 0.5917,
      "step": 61062
    },
    {
      "epoch": 1.875802537400547,
      "grad_norm": 0.46078231930732727,
      "learning_rate": 1.903716901378372e-07,
      "loss": 0.4801,
      "step": 61063
    },
    {
      "epoch": 1.875833256535496,
      "grad_norm": 0.45251068472862244,
      "learning_rate": 1.902778512695891e-07,
      "loss": 0.5109,
      "step": 61064
    },
    {
      "epoch": 1.8758639756704452,
      "grad_norm": 0.4055277407169342,
      "learning_rate": 1.9018403531263274e-07,
      "loss": 0.4245,
      "step": 61065
    },
    {
      "epoch": 1.8758946948053943,
      "grad_norm": 0.4268161654472351,
      "learning_rate": 1.9009024226718575e-07,
      "loss": 0.5226,
      "step": 61066
    },
    {
      "epoch": 1.8759254139403434,
      "grad_norm": 0.45013123750686646,
      "learning_rate": 1.8999647213347018e-07,
      "loss": 0.4067,
      "step": 61067
    },
    {
      "epoch": 1.8759561330752925,
      "grad_norm": 0.4899587035179138,
      "learning_rate": 1.8990272491170135e-07,
      "loss": 0.4078,
      "step": 61068
    },
    {
      "epoch": 1.8759868522102416,
      "grad_norm": 0.4061616361141205,
      "learning_rate": 1.8980900060210027e-07,
      "loss": 0.4865,
      "step": 61069
    },
    {
      "epoch": 1.8760175713451908,
      "grad_norm": 0.3728126287460327,
      "learning_rate": 1.897152992048845e-07,
      "loss": 0.4749,
      "step": 61070
    },
    {
      "epoch": 1.87604829048014,
      "grad_norm": 0.4780394434928894,
      "learning_rate": 1.8962162072027502e-07,
      "loss": 0.4704,
      "step": 61071
    },
    {
      "epoch": 1.8760790096150892,
      "grad_norm": 0.41950729489326477,
      "learning_rate": 1.8952796514848936e-07,
      "loss": 0.456,
      "step": 61072
    },
    {
      "epoch": 1.8761097287500386,
      "grad_norm": 0.4335150122642517,
      "learning_rate": 1.8943433248974628e-07,
      "loss": 0.4945,
      "step": 61073
    },
    {
      "epoch": 1.8761404478849877,
      "grad_norm": 0.4424150586128235,
      "learning_rate": 1.893407227442623e-07,
      "loss": 0.4777,
      "step": 61074
    },
    {
      "epoch": 1.8761711670199368,
      "grad_norm": 0.46507543325424194,
      "learning_rate": 1.892471359122605e-07,
      "loss": 0.4808,
      "step": 61075
    },
    {
      "epoch": 1.876201886154886,
      "grad_norm": 0.41896188259124756,
      "learning_rate": 1.8915357199395746e-07,
      "loss": 0.5391,
      "step": 61076
    },
    {
      "epoch": 1.876232605289835,
      "grad_norm": 0.4153805375099182,
      "learning_rate": 1.890600309895696e-07,
      "loss": 0.4156,
      "step": 61077
    },
    {
      "epoch": 1.8762633244247842,
      "grad_norm": 0.4247290790081024,
      "learning_rate": 1.88966512899319e-07,
      "loss": 0.4784,
      "step": 61078
    },
    {
      "epoch": 1.8762940435597333,
      "grad_norm": 0.405953973531723,
      "learning_rate": 1.8887301772342104e-07,
      "loss": 0.393,
      "step": 61079
    },
    {
      "epoch": 1.8763247626946824,
      "grad_norm": 0.42847010493278503,
      "learning_rate": 1.8877954546209664e-07,
      "loss": 0.482,
      "step": 61080
    },
    {
      "epoch": 1.8763554818296315,
      "grad_norm": 0.4322021007537842,
      "learning_rate": 1.886860961155612e-07,
      "loss": 0.4777,
      "step": 61081
    },
    {
      "epoch": 1.8763862009645809,
      "grad_norm": 0.43617314100265503,
      "learning_rate": 1.8859266968403677e-07,
      "loss": 0.533,
      "step": 61082
    },
    {
      "epoch": 1.87641692009953,
      "grad_norm": 0.4202011823654175,
      "learning_rate": 1.8849926616773652e-07,
      "loss": 0.4835,
      "step": 61083
    },
    {
      "epoch": 1.876447639234479,
      "grad_norm": 0.4689425826072693,
      "learning_rate": 1.8840588556688356e-07,
      "loss": 0.4618,
      "step": 61084
    },
    {
      "epoch": 1.8764783583694284,
      "grad_norm": 0.41021624207496643,
      "learning_rate": 1.883125278816933e-07,
      "loss": 0.424,
      "step": 61085
    },
    {
      "epoch": 1.8765090775043776,
      "grad_norm": 0.4432940185070038,
      "learning_rate": 1.8821919311238556e-07,
      "loss": 0.4432,
      "step": 61086
    },
    {
      "epoch": 1.8765397966393267,
      "grad_norm": 0.43776509165763855,
      "learning_rate": 1.8812588125917574e-07,
      "loss": 0.4917,
      "step": 61087
    },
    {
      "epoch": 1.8765705157742758,
      "grad_norm": 0.4474060833454132,
      "learning_rate": 1.8803259232228254e-07,
      "loss": 0.5136,
      "step": 61088
    },
    {
      "epoch": 1.876601234909225,
      "grad_norm": 0.4710783064365387,
      "learning_rate": 1.8793932630192579e-07,
      "loss": 0.4407,
      "step": 61089
    },
    {
      "epoch": 1.876631954044174,
      "grad_norm": 0.427887499332428,
      "learning_rate": 1.8784608319832197e-07,
      "loss": 0.5088,
      "step": 61090
    },
    {
      "epoch": 1.8766626731791232,
      "grad_norm": 0.4611060321331024,
      "learning_rate": 1.8775286301168872e-07,
      "loss": 0.474,
      "step": 61091
    },
    {
      "epoch": 1.8766933923140723,
      "grad_norm": 0.5222836136817932,
      "learning_rate": 1.876596657422436e-07,
      "loss": 0.4354,
      "step": 61092
    },
    {
      "epoch": 1.8767241114490216,
      "grad_norm": 0.5191115140914917,
      "learning_rate": 1.875664913902042e-07,
      "loss": 0.4836,
      "step": 61093
    },
    {
      "epoch": 1.8767548305839707,
      "grad_norm": 0.41359955072402954,
      "learning_rate": 1.874733399557882e-07,
      "loss": 0.5178,
      "step": 61094
    },
    {
      "epoch": 1.8767855497189199,
      "grad_norm": 0.43532252311706543,
      "learning_rate": 1.8738021143921535e-07,
      "loss": 0.4952,
      "step": 61095
    },
    {
      "epoch": 1.8768162688538692,
      "grad_norm": 0.4550880193710327,
      "learning_rate": 1.8728710584069998e-07,
      "loss": 0.5304,
      "step": 61096
    },
    {
      "epoch": 1.8768469879888183,
      "grad_norm": 0.4517078995704651,
      "learning_rate": 1.8719402316046187e-07,
      "loss": 0.4341,
      "step": 61097
    },
    {
      "epoch": 1.8768777071237674,
      "grad_norm": 0.43081289529800415,
      "learning_rate": 1.871009633987164e-07,
      "loss": 0.5973,
      "step": 61098
    },
    {
      "epoch": 1.8769084262587166,
      "grad_norm": 0.4075574576854706,
      "learning_rate": 1.8700792655568344e-07,
      "loss": 0.4708,
      "step": 61099
    },
    {
      "epoch": 1.8769391453936657,
      "grad_norm": 0.4716450572013855,
      "learning_rate": 1.8691491263157723e-07,
      "loss": 0.459,
      "step": 61100
    },
    {
      "epoch": 1.8769698645286148,
      "grad_norm": 0.44132301211357117,
      "learning_rate": 1.868219216266165e-07,
      "loss": 0.4681,
      "step": 61101
    },
    {
      "epoch": 1.877000583663564,
      "grad_norm": 0.44759246706962585,
      "learning_rate": 1.8672895354101884e-07,
      "loss": 0.5156,
      "step": 61102
    },
    {
      "epoch": 1.877031302798513,
      "grad_norm": 0.46429339051246643,
      "learning_rate": 1.8663600837500185e-07,
      "loss": 0.46,
      "step": 61103
    },
    {
      "epoch": 1.8770620219334624,
      "grad_norm": 0.44789019227027893,
      "learning_rate": 1.8654308612878201e-07,
      "loss": 0.4212,
      "step": 61104
    },
    {
      "epoch": 1.8770927410684115,
      "grad_norm": 0.5157405138015747,
      "learning_rate": 1.8645018680257477e-07,
      "loss": 0.4715,
      "step": 61105
    },
    {
      "epoch": 1.8771234602033606,
      "grad_norm": 0.414491206407547,
      "learning_rate": 1.8635731039659876e-07,
      "loss": 0.4491,
      "step": 61106
    },
    {
      "epoch": 1.87715417933831,
      "grad_norm": 0.47782331705093384,
      "learning_rate": 1.8626445691107165e-07,
      "loss": 0.4651,
      "step": 61107
    },
    {
      "epoch": 1.877184898473259,
      "grad_norm": 0.4447174668312073,
      "learning_rate": 1.8617162634620878e-07,
      "loss": 0.5226,
      "step": 61108
    },
    {
      "epoch": 1.8772156176082082,
      "grad_norm": 0.4159602224826813,
      "learning_rate": 1.8607881870222778e-07,
      "loss": 0.4882,
      "step": 61109
    },
    {
      "epoch": 1.8772463367431573,
      "grad_norm": 0.4468522071838379,
      "learning_rate": 1.8598603397934402e-07,
      "loss": 0.4653,
      "step": 61110
    },
    {
      "epoch": 1.8772770558781064,
      "grad_norm": 0.4990716576576233,
      "learning_rate": 1.858932721777762e-07,
      "loss": 0.4653,
      "step": 61111
    },
    {
      "epoch": 1.8773077750130556,
      "grad_norm": 0.4698294997215271,
      "learning_rate": 1.8580053329773971e-07,
      "loss": 0.4514,
      "step": 61112
    },
    {
      "epoch": 1.8773384941480047,
      "grad_norm": 0.4245354235172272,
      "learning_rate": 1.857078173394522e-07,
      "loss": 0.4657,
      "step": 61113
    },
    {
      "epoch": 1.8773692132829538,
      "grad_norm": 0.4218108654022217,
      "learning_rate": 1.856151243031279e-07,
      "loss": 0.4545,
      "step": 61114
    },
    {
      "epoch": 1.8773999324179032,
      "grad_norm": 0.4082144498825073,
      "learning_rate": 1.855224541889855e-07,
      "loss": 0.441,
      "step": 61115
    },
    {
      "epoch": 1.8774306515528523,
      "grad_norm": 0.4523775279521942,
      "learning_rate": 1.8542980699724267e-07,
      "loss": 0.4238,
      "step": 61116
    },
    {
      "epoch": 1.8774613706878014,
      "grad_norm": 0.45785272121429443,
      "learning_rate": 1.8533718272811252e-07,
      "loss": 0.4325,
      "step": 61117
    },
    {
      "epoch": 1.8774920898227507,
      "grad_norm": 0.5031054019927979,
      "learning_rate": 1.8524458138181268e-07,
      "loss": 0.4562,
      "step": 61118
    },
    {
      "epoch": 1.8775228089576999,
      "grad_norm": 0.39842310547828674,
      "learning_rate": 1.8515200295855852e-07,
      "loss": 0.4364,
      "step": 61119
    },
    {
      "epoch": 1.877553528092649,
      "grad_norm": 0.44648706912994385,
      "learning_rate": 1.8505944745856984e-07,
      "loss": 0.4916,
      "step": 61120
    },
    {
      "epoch": 1.877584247227598,
      "grad_norm": 0.4128980040550232,
      "learning_rate": 1.8496691488205876e-07,
      "loss": 0.4323,
      "step": 61121
    },
    {
      "epoch": 1.8776149663625472,
      "grad_norm": 0.4271387457847595,
      "learning_rate": 1.8487440522924394e-07,
      "loss": 0.4401,
      "step": 61122
    },
    {
      "epoch": 1.8776456854974963,
      "grad_norm": 0.453216552734375,
      "learning_rate": 1.8478191850033968e-07,
      "loss": 0.4781,
      "step": 61123
    },
    {
      "epoch": 1.8776764046324455,
      "grad_norm": 0.39835765957832336,
      "learning_rate": 1.8468945469556244e-07,
      "loss": 0.4673,
      "step": 61124
    },
    {
      "epoch": 1.8777071237673946,
      "grad_norm": 0.45003190636634827,
      "learning_rate": 1.8459701381512761e-07,
      "loss": 0.3931,
      "step": 61125
    },
    {
      "epoch": 1.877737842902344,
      "grad_norm": 0.45418107509613037,
      "learning_rate": 1.8450459585925395e-07,
      "loss": 0.5232,
      "step": 61126
    },
    {
      "epoch": 1.877768562037293,
      "grad_norm": 0.45711958408355713,
      "learning_rate": 1.8441220082815458e-07,
      "loss": 0.4748,
      "step": 61127
    },
    {
      "epoch": 1.8777992811722422,
      "grad_norm": 0.5414328575134277,
      "learning_rate": 1.8431982872204602e-07,
      "loss": 0.5139,
      "step": 61128
    },
    {
      "epoch": 1.8778300003071915,
      "grad_norm": 0.42775869369506836,
      "learning_rate": 1.842274795411436e-07,
      "loss": 0.449,
      "step": 61129
    },
    {
      "epoch": 1.8778607194421406,
      "grad_norm": 0.4619446098804474,
      "learning_rate": 1.841351532856628e-07,
      "loss": 0.4492,
      "step": 61130
    },
    {
      "epoch": 1.8778914385770897,
      "grad_norm": 0.42975589632987976,
      "learning_rate": 1.8404284995582222e-07,
      "loss": 0.4057,
      "step": 61131
    },
    {
      "epoch": 1.8779221577120389,
      "grad_norm": 0.46953731775283813,
      "learning_rate": 1.839505695518329e-07,
      "loss": 0.4481,
      "step": 61132
    },
    {
      "epoch": 1.877952876846988,
      "grad_norm": 0.47922223806381226,
      "learning_rate": 1.8385831207391347e-07,
      "loss": 0.4275,
      "step": 61133
    },
    {
      "epoch": 1.877983595981937,
      "grad_norm": 0.42580047249794006,
      "learning_rate": 1.8376607752227826e-07,
      "loss": 0.4293,
      "step": 61134
    },
    {
      "epoch": 1.8780143151168862,
      "grad_norm": 0.4536285102367401,
      "learning_rate": 1.8367386589714375e-07,
      "loss": 0.4918,
      "step": 61135
    },
    {
      "epoch": 1.8780450342518353,
      "grad_norm": 0.4306648075580597,
      "learning_rate": 1.8358167719872312e-07,
      "loss": 0.4803,
      "step": 61136
    },
    {
      "epoch": 1.8780757533867847,
      "grad_norm": 0.42371276021003723,
      "learning_rate": 1.8348951142723393e-07,
      "loss": 0.4341,
      "step": 61137
    },
    {
      "epoch": 1.8781064725217338,
      "grad_norm": 0.4643346667289734,
      "learning_rate": 1.8339736858288937e-07,
      "loss": 0.495,
      "step": 61138
    },
    {
      "epoch": 1.878137191656683,
      "grad_norm": 0.45313844084739685,
      "learning_rate": 1.8330524866590815e-07,
      "loss": 0.5352,
      "step": 61139
    },
    {
      "epoch": 1.8781679107916323,
      "grad_norm": 0.39808306097984314,
      "learning_rate": 1.832131516765012e-07,
      "loss": 0.4398,
      "step": 61140
    },
    {
      "epoch": 1.8781986299265814,
      "grad_norm": 0.4670139253139496,
      "learning_rate": 1.8312107761488618e-07,
      "loss": 0.4143,
      "step": 61141
    },
    {
      "epoch": 1.8782293490615305,
      "grad_norm": 0.44647225737571716,
      "learning_rate": 1.830290264812773e-07,
      "loss": 0.4376,
      "step": 61142
    },
    {
      "epoch": 1.8782600681964796,
      "grad_norm": 0.43678098917007446,
      "learning_rate": 1.8293699827588995e-07,
      "loss": 0.4814,
      "step": 61143
    },
    {
      "epoch": 1.8782907873314287,
      "grad_norm": 0.41655534505844116,
      "learning_rate": 1.8284499299893842e-07,
      "loss": 0.4186,
      "step": 61144
    },
    {
      "epoch": 1.8783215064663779,
      "grad_norm": 0.4447433054447174,
      "learning_rate": 1.827530106506392e-07,
      "loss": 0.5135,
      "step": 61145
    },
    {
      "epoch": 1.878352225601327,
      "grad_norm": 0.39932525157928467,
      "learning_rate": 1.8266105123120436e-07,
      "loss": 0.455,
      "step": 61146
    },
    {
      "epoch": 1.878382944736276,
      "grad_norm": 0.38311854004859924,
      "learning_rate": 1.8256911474085148e-07,
      "loss": 0.4387,
      "step": 61147
    },
    {
      "epoch": 1.8784136638712254,
      "grad_norm": 0.42510783672332764,
      "learning_rate": 1.8247720117979372e-07,
      "loss": 0.4775,
      "step": 61148
    },
    {
      "epoch": 1.8784443830061746,
      "grad_norm": 0.43998658657073975,
      "learning_rate": 1.8238531054824537e-07,
      "loss": 0.5161,
      "step": 61149
    },
    {
      "epoch": 1.8784751021411237,
      "grad_norm": 0.4519590139389038,
      "learning_rate": 1.8229344284642403e-07,
      "loss": 0.4434,
      "step": 61150
    },
    {
      "epoch": 1.878505821276073,
      "grad_norm": 0.5582438707351685,
      "learning_rate": 1.822015980745384e-07,
      "loss": 0.4873,
      "step": 61151
    },
    {
      "epoch": 1.8785365404110221,
      "grad_norm": 0.45995521545410156,
      "learning_rate": 1.8210977623280946e-07,
      "loss": 0.4597,
      "step": 61152
    },
    {
      "epoch": 1.8785672595459713,
      "grad_norm": 0.43383195996284485,
      "learning_rate": 1.820179773214481e-07,
      "loss": 0.4921,
      "step": 61153
    },
    {
      "epoch": 1.8785979786809204,
      "grad_norm": 0.4211682081222534,
      "learning_rate": 1.8192620134066974e-07,
      "loss": 0.4835,
      "step": 61154
    },
    {
      "epoch": 1.8786286978158695,
      "grad_norm": 0.4017891585826874,
      "learning_rate": 1.8183444829068752e-07,
      "loss": 0.4114,
      "step": 61155
    },
    {
      "epoch": 1.8786594169508186,
      "grad_norm": 0.4363865852355957,
      "learning_rate": 1.8174271817171684e-07,
      "loss": 0.4019,
      "step": 61156
    },
    {
      "epoch": 1.8786901360857677,
      "grad_norm": 0.4219096601009369,
      "learning_rate": 1.8165101098397197e-07,
      "loss": 0.4545,
      "step": 61157
    },
    {
      "epoch": 1.8787208552207169,
      "grad_norm": 0.40366002917289734,
      "learning_rate": 1.815593267276683e-07,
      "loss": 0.396,
      "step": 61158
    },
    {
      "epoch": 1.8787515743556662,
      "grad_norm": 0.4927789568901062,
      "learning_rate": 1.8146766540301674e-07,
      "loss": 0.3711,
      "step": 61159
    },
    {
      "epoch": 1.8787822934906153,
      "grad_norm": 0.43944889307022095,
      "learning_rate": 1.813760270102327e-07,
      "loss": 0.494,
      "step": 61160
    },
    {
      "epoch": 1.8788130126255644,
      "grad_norm": 0.4368351995944977,
      "learning_rate": 1.8128441154953158e-07,
      "loss": 0.4434,
      "step": 61161
    },
    {
      "epoch": 1.8788437317605138,
      "grad_norm": 0.4275951683521271,
      "learning_rate": 1.8119281902112763e-07,
      "loss": 0.5493,
      "step": 61162
    },
    {
      "epoch": 1.878874450895463,
      "grad_norm": 0.4112818241119385,
      "learning_rate": 1.8110124942523177e-07,
      "loss": 0.4184,
      "step": 61163
    },
    {
      "epoch": 1.878905170030412,
      "grad_norm": 0.4387360215187073,
      "learning_rate": 1.8100970276206054e-07,
      "loss": 0.4685,
      "step": 61164
    },
    {
      "epoch": 1.8789358891653611,
      "grad_norm": 0.3807559609413147,
      "learning_rate": 1.8091817903182596e-07,
      "loss": 0.4572,
      "step": 61165
    },
    {
      "epoch": 1.8789666083003103,
      "grad_norm": 0.4728623330593109,
      "learning_rate": 1.8082667823474343e-07,
      "loss": 0.4159,
      "step": 61166
    },
    {
      "epoch": 1.8789973274352594,
      "grad_norm": 0.4179595112800598,
      "learning_rate": 1.807352003710261e-07,
      "loss": 0.41,
      "step": 61167
    },
    {
      "epoch": 1.8790280465702085,
      "grad_norm": 0.44750577211380005,
      "learning_rate": 1.8064374544088715e-07,
      "loss": 0.4547,
      "step": 61168
    },
    {
      "epoch": 1.8790587657051576,
      "grad_norm": 0.4167608916759491,
      "learning_rate": 1.8055231344454082e-07,
      "loss": 0.4694,
      "step": 61169
    },
    {
      "epoch": 1.8790894848401067,
      "grad_norm": 0.41089117527008057,
      "learning_rate": 1.804609043822003e-07,
      "loss": 0.4305,
      "step": 61170
    },
    {
      "epoch": 1.879120203975056,
      "grad_norm": 0.4192443788051605,
      "learning_rate": 1.8036951825407989e-07,
      "loss": 0.447,
      "step": 61171
    },
    {
      "epoch": 1.8791509231100052,
      "grad_norm": 0.41208821535110474,
      "learning_rate": 1.8027815506039049e-07,
      "loss": 0.4843,
      "step": 61172
    },
    {
      "epoch": 1.8791816422449545,
      "grad_norm": 0.4088793098926544,
      "learning_rate": 1.8018681480134858e-07,
      "loss": 0.4884,
      "step": 61173
    },
    {
      "epoch": 1.8792123613799037,
      "grad_norm": 0.475314199924469,
      "learning_rate": 1.8009549747716516e-07,
      "loss": 0.4887,
      "step": 61174
    },
    {
      "epoch": 1.8792430805148528,
      "grad_norm": 0.4415028691291809,
      "learning_rate": 1.8000420308805556e-07,
      "loss": 0.4281,
      "step": 61175
    },
    {
      "epoch": 1.879273799649802,
      "grad_norm": 0.4547032415866852,
      "learning_rate": 1.7991293163423185e-07,
      "loss": 0.4511,
      "step": 61176
    },
    {
      "epoch": 1.879304518784751,
      "grad_norm": 0.45716404914855957,
      "learning_rate": 1.7982168311590608e-07,
      "loss": 0.5146,
      "step": 61177
    },
    {
      "epoch": 1.8793352379197001,
      "grad_norm": 0.3865983486175537,
      "learning_rate": 1.7973045753329366e-07,
      "loss": 0.4272,
      "step": 61178
    },
    {
      "epoch": 1.8793659570546493,
      "grad_norm": 0.4278064966201782,
      "learning_rate": 1.796392548866077e-07,
      "loss": 0.5003,
      "step": 61179
    },
    {
      "epoch": 1.8793966761895984,
      "grad_norm": 0.47251278162002563,
      "learning_rate": 1.795480751760581e-07,
      "loss": 0.4559,
      "step": 61180
    },
    {
      "epoch": 1.8794273953245475,
      "grad_norm": 0.40408453345298767,
      "learning_rate": 1.794569184018613e-07,
      "loss": 0.4231,
      "step": 61181
    },
    {
      "epoch": 1.8794581144594968,
      "grad_norm": 0.38445618748664856,
      "learning_rate": 1.7936578456422715e-07,
      "loss": 0.445,
      "step": 61182
    },
    {
      "epoch": 1.879488833594446,
      "grad_norm": 0.39670735597610474,
      "learning_rate": 1.7927467366337103e-07,
      "loss": 0.4238,
      "step": 61183
    },
    {
      "epoch": 1.8795195527293953,
      "grad_norm": 0.45700210332870483,
      "learning_rate": 1.79183585699505e-07,
      "loss": 0.4781,
      "step": 61184
    },
    {
      "epoch": 1.8795502718643444,
      "grad_norm": 0.4077269732952118,
      "learning_rate": 1.790925206728411e-07,
      "loss": 0.477,
      "step": 61185
    },
    {
      "epoch": 1.8795809909992935,
      "grad_norm": 0.389105886220932,
      "learning_rate": 1.7900147858359362e-07,
      "loss": 0.4916,
      "step": 61186
    },
    {
      "epoch": 1.8796117101342427,
      "grad_norm": 0.5915313959121704,
      "learning_rate": 1.7891045943197127e-07,
      "loss": 0.4864,
      "step": 61187
    },
    {
      "epoch": 1.8796424292691918,
      "grad_norm": 0.40336158871650696,
      "learning_rate": 1.7881946321819277e-07,
      "loss": 0.3691,
      "step": 61188
    },
    {
      "epoch": 1.879673148404141,
      "grad_norm": 0.4865446388721466,
      "learning_rate": 1.7872848994246573e-07,
      "loss": 0.4467,
      "step": 61189
    },
    {
      "epoch": 1.87970386753909,
      "grad_norm": 0.3939058184623718,
      "learning_rate": 1.786375396050044e-07,
      "loss": 0.4613,
      "step": 61190
    },
    {
      "epoch": 1.8797345866740391,
      "grad_norm": 0.42197713255882263,
      "learning_rate": 1.7854661220602087e-07,
      "loss": 0.3551,
      "step": 61191
    },
    {
      "epoch": 1.8797653058089883,
      "grad_norm": 0.44508013129234314,
      "learning_rate": 1.784557077457272e-07,
      "loss": 0.4361,
      "step": 61192
    },
    {
      "epoch": 1.8797960249439376,
      "grad_norm": 0.5435234904289246,
      "learning_rate": 1.783648262243365e-07,
      "loss": 0.4862,
      "step": 61193
    },
    {
      "epoch": 1.8798267440788867,
      "grad_norm": 0.40951305627822876,
      "learning_rate": 1.7827396764206194e-07,
      "loss": 0.4868,
      "step": 61194
    },
    {
      "epoch": 1.8798574632138358,
      "grad_norm": 0.43959251046180725,
      "learning_rate": 1.7818313199911343e-07,
      "loss": 0.457,
      "step": 61195
    },
    {
      "epoch": 1.8798881823487852,
      "grad_norm": 0.41590040922164917,
      "learning_rate": 1.7809231929570404e-07,
      "loss": 0.482,
      "step": 61196
    },
    {
      "epoch": 1.8799189014837343,
      "grad_norm": 0.4171984791755676,
      "learning_rate": 1.7800152953204585e-07,
      "loss": 0.4213,
      "step": 61197
    },
    {
      "epoch": 1.8799496206186834,
      "grad_norm": 0.4244716763496399,
      "learning_rate": 1.7791076270835094e-07,
      "loss": 0.4777,
      "step": 61198
    },
    {
      "epoch": 1.8799803397536325,
      "grad_norm": 0.9289310574531555,
      "learning_rate": 1.7782001882483245e-07,
      "loss": 0.4625,
      "step": 61199
    },
    {
      "epoch": 1.8800110588885817,
      "grad_norm": 0.4359951615333557,
      "learning_rate": 1.7772929788170024e-07,
      "loss": 0.5195,
      "step": 61200
    },
    {
      "epoch": 1.8800417780235308,
      "grad_norm": 0.43312951922416687,
      "learning_rate": 1.7763859987916744e-07,
      "loss": 0.4395,
      "step": 61201
    },
    {
      "epoch": 1.88007249715848,
      "grad_norm": 0.438083678483963,
      "learning_rate": 1.7754792481744499e-07,
      "loss": 0.4105,
      "step": 61202
    },
    {
      "epoch": 1.880103216293429,
      "grad_norm": 0.3873606324195862,
      "learning_rate": 1.7745727269674718e-07,
      "loss": 0.432,
      "step": 61203
    },
    {
      "epoch": 1.8801339354283784,
      "grad_norm": 0.42311736941337585,
      "learning_rate": 1.7736664351728273e-07,
      "loss": 0.4721,
      "step": 61204
    },
    {
      "epoch": 1.8801646545633275,
      "grad_norm": 0.43850621581077576,
      "learning_rate": 1.7727603727926478e-07,
      "loss": 0.5591,
      "step": 61205
    },
    {
      "epoch": 1.8801953736982766,
      "grad_norm": 0.44862914085388184,
      "learning_rate": 1.7718545398290432e-07,
      "loss": 0.5035,
      "step": 61206
    },
    {
      "epoch": 1.880226092833226,
      "grad_norm": 0.43413886427879333,
      "learning_rate": 1.7709489362841337e-07,
      "loss": 0.4776,
      "step": 61207
    },
    {
      "epoch": 1.880256811968175,
      "grad_norm": 0.4545815587043762,
      "learning_rate": 1.7700435621600286e-07,
      "loss": 0.4737,
      "step": 61208
    },
    {
      "epoch": 1.8802875311031242,
      "grad_norm": 0.43381544947624207,
      "learning_rate": 1.76913841745886e-07,
      "loss": 0.4662,
      "step": 61209
    },
    {
      "epoch": 1.8803182502380733,
      "grad_norm": 0.43694233894348145,
      "learning_rate": 1.7682335021827146e-07,
      "loss": 0.4916,
      "step": 61210
    },
    {
      "epoch": 1.8803489693730224,
      "grad_norm": 0.4527246654033661,
      "learning_rate": 1.7673288163337354e-07,
      "loss": 0.4359,
      "step": 61211
    },
    {
      "epoch": 1.8803796885079715,
      "grad_norm": 0.47198817133903503,
      "learning_rate": 1.7664243599140097e-07,
      "loss": 0.4662,
      "step": 61212
    },
    {
      "epoch": 1.8804104076429207,
      "grad_norm": 0.48181775212287903,
      "learning_rate": 1.7655201329256687e-07,
      "loss": 0.4554,
      "step": 61213
    },
    {
      "epoch": 1.8804411267778698,
      "grad_norm": 0.4845913350582123,
      "learning_rate": 1.7646161353708002e-07,
      "loss": 0.4765,
      "step": 61214
    },
    {
      "epoch": 1.8804718459128191,
      "grad_norm": 0.43142613768577576,
      "learning_rate": 1.7637123672515467e-07,
      "loss": 0.4604,
      "step": 61215
    },
    {
      "epoch": 1.8805025650477682,
      "grad_norm": 0.4838407039642334,
      "learning_rate": 1.7628088285699952e-07,
      "loss": 0.4698,
      "step": 61216
    },
    {
      "epoch": 1.8805332841827174,
      "grad_norm": 0.43777185678482056,
      "learning_rate": 1.7619055193282775e-07,
      "loss": 0.5102,
      "step": 61217
    },
    {
      "epoch": 1.8805640033176667,
      "grad_norm": 0.4892793893814087,
      "learning_rate": 1.7610024395284698e-07,
      "loss": 0.4105,
      "step": 61218
    },
    {
      "epoch": 1.8805947224526158,
      "grad_norm": 0.4104200005531311,
      "learning_rate": 1.7600995891727147e-07,
      "loss": 0.4755,
      "step": 61219
    },
    {
      "epoch": 1.880625441587565,
      "grad_norm": 0.5035161972045898,
      "learning_rate": 1.7591969682631104e-07,
      "loss": 0.5236,
      "step": 61220
    },
    {
      "epoch": 1.880656160722514,
      "grad_norm": 0.43616408109664917,
      "learning_rate": 1.7582945768017555e-07,
      "loss": 0.4788,
      "step": 61221
    },
    {
      "epoch": 1.8806868798574632,
      "grad_norm": 0.4335291087627411,
      "learning_rate": 1.7573924147907705e-07,
      "loss": 0.4152,
      "step": 61222
    },
    {
      "epoch": 1.8807175989924123,
      "grad_norm": 0.5137148499488831,
      "learning_rate": 1.7564904822322426e-07,
      "loss": 0.4504,
      "step": 61223
    },
    {
      "epoch": 1.8807483181273614,
      "grad_norm": 0.4154392182826996,
      "learning_rate": 1.7555887791283144e-07,
      "loss": 0.5044,
      "step": 61224
    },
    {
      "epoch": 1.8807790372623105,
      "grad_norm": 0.4449586272239685,
      "learning_rate": 1.754687305481051e-07,
      "loss": 0.4073,
      "step": 61225
    },
    {
      "epoch": 1.88080975639726,
      "grad_norm": 0.4480019211769104,
      "learning_rate": 1.753786061292595e-07,
      "loss": 0.3956,
      "step": 61226
    },
    {
      "epoch": 1.880840475532209,
      "grad_norm": 0.41169241070747375,
      "learning_rate": 1.7528850465650226e-07,
      "loss": 0.4054,
      "step": 61227
    },
    {
      "epoch": 1.8808711946671581,
      "grad_norm": 0.41813036799430847,
      "learning_rate": 1.7519842613004435e-07,
      "loss": 0.4238,
      "step": 61228
    },
    {
      "epoch": 1.8809019138021075,
      "grad_norm": 0.39875391125679016,
      "learning_rate": 1.7510837055009665e-07,
      "loss": 0.5111,
      "step": 61229
    },
    {
      "epoch": 1.8809326329370566,
      "grad_norm": 0.461576372385025,
      "learning_rate": 1.7501833791687128e-07,
      "loss": 0.4489,
      "step": 61230
    },
    {
      "epoch": 1.8809633520720057,
      "grad_norm": 0.38783904910087585,
      "learning_rate": 1.7492832823057472e-07,
      "loss": 0.4095,
      "step": 61231
    },
    {
      "epoch": 1.8809940712069548,
      "grad_norm": 0.3995915949344635,
      "learning_rate": 1.748383414914201e-07,
      "loss": 0.5103,
      "step": 61232
    },
    {
      "epoch": 1.881024790341904,
      "grad_norm": 0.45940959453582764,
      "learning_rate": 1.7474837769961617e-07,
      "loss": 0.4319,
      "step": 61233
    },
    {
      "epoch": 1.881055509476853,
      "grad_norm": 0.43425172567367554,
      "learning_rate": 1.7465843685537497e-07,
      "loss": 0.4836,
      "step": 61234
    },
    {
      "epoch": 1.8810862286118022,
      "grad_norm": 0.4490364193916321,
      "learning_rate": 1.7456851895890414e-07,
      "loss": 0.5108,
      "step": 61235
    },
    {
      "epoch": 1.8811169477467513,
      "grad_norm": 0.42809736728668213,
      "learning_rate": 1.744786240104146e-07,
      "loss": 0.4443,
      "step": 61236
    },
    {
      "epoch": 1.8811476668817007,
      "grad_norm": 0.4414602220058441,
      "learning_rate": 1.7438875201011618e-07,
      "loss": 0.4604,
      "step": 61237
    },
    {
      "epoch": 1.8811783860166498,
      "grad_norm": 0.4366724193096161,
      "learning_rate": 1.7429890295822093e-07,
      "loss": 0.4247,
      "step": 61238
    },
    {
      "epoch": 1.881209105151599,
      "grad_norm": 0.41393640637397766,
      "learning_rate": 1.7420907685493537e-07,
      "loss": 0.4894,
      "step": 61239
    },
    {
      "epoch": 1.8812398242865482,
      "grad_norm": 0.4406631886959076,
      "learning_rate": 1.7411927370047045e-07,
      "loss": 0.4545,
      "step": 61240
    },
    {
      "epoch": 1.8812705434214974,
      "grad_norm": 0.4234268069267273,
      "learning_rate": 1.7402949349503596e-07,
      "loss": 0.5199,
      "step": 61241
    },
    {
      "epoch": 1.8813012625564465,
      "grad_norm": 0.46423274278640747,
      "learning_rate": 1.7393973623884286e-07,
      "loss": 0.4388,
      "step": 61242
    },
    {
      "epoch": 1.8813319816913956,
      "grad_norm": 0.45353323221206665,
      "learning_rate": 1.738500019320999e-07,
      "loss": 0.4446,
      "step": 61243
    },
    {
      "epoch": 1.8813627008263447,
      "grad_norm": 0.45475348830223083,
      "learning_rate": 1.7376029057501576e-07,
      "loss": 0.4915,
      "step": 61244
    },
    {
      "epoch": 1.8813934199612938,
      "grad_norm": 0.38666248321533203,
      "learning_rate": 1.736706021678003e-07,
      "loss": 0.4669,
      "step": 61245
    },
    {
      "epoch": 1.881424139096243,
      "grad_norm": 0.4342312812805176,
      "learning_rate": 1.7358093671066446e-07,
      "loss": 0.4509,
      "step": 61246
    },
    {
      "epoch": 1.881454858231192,
      "grad_norm": 0.44436174631118774,
      "learning_rate": 1.7349129420381583e-07,
      "loss": 0.4648,
      "step": 61247
    },
    {
      "epoch": 1.8814855773661414,
      "grad_norm": 0.4447481632232666,
      "learning_rate": 1.7340167464746538e-07,
      "loss": 0.4253,
      "step": 61248
    },
    {
      "epoch": 1.8815162965010905,
      "grad_norm": 0.4053819179534912,
      "learning_rate": 1.7331207804182183e-07,
      "loss": 0.486,
      "step": 61249
    },
    {
      "epoch": 1.8815470156360397,
      "grad_norm": 0.42809879779815674,
      "learning_rate": 1.7322250438709275e-07,
      "loss": 0.4127,
      "step": 61250
    },
    {
      "epoch": 1.881577734770989,
      "grad_norm": 0.44316384196281433,
      "learning_rate": 1.7313295368349027e-07,
      "loss": 0.4948,
      "step": 61251
    },
    {
      "epoch": 1.8816084539059381,
      "grad_norm": 0.4201364517211914,
      "learning_rate": 1.730434259312208e-07,
      "loss": 0.5058,
      "step": 61252
    },
    {
      "epoch": 1.8816391730408872,
      "grad_norm": 0.3992064297199249,
      "learning_rate": 1.7295392113049536e-07,
      "loss": 0.3819,
      "step": 61253
    },
    {
      "epoch": 1.8816698921758364,
      "grad_norm": 0.3785337209701538,
      "learning_rate": 1.7286443928152263e-07,
      "loss": 0.4607,
      "step": 61254
    },
    {
      "epoch": 1.8817006113107855,
      "grad_norm": 0.48164984583854675,
      "learning_rate": 1.7277498038451023e-07,
      "loss": 0.4632,
      "step": 61255
    },
    {
      "epoch": 1.8817313304457346,
      "grad_norm": 0.5141447186470032,
      "learning_rate": 1.7268554443966913e-07,
      "loss": 0.4531,
      "step": 61256
    },
    {
      "epoch": 1.8817620495806837,
      "grad_norm": 0.6208822727203369,
      "learning_rate": 1.725961314472069e-07,
      "loss": 0.4764,
      "step": 61257
    },
    {
      "epoch": 1.8817927687156328,
      "grad_norm": 0.38797658681869507,
      "learning_rate": 1.7250674140733336e-07,
      "loss": 0.4638,
      "step": 61258
    },
    {
      "epoch": 1.8818234878505822,
      "grad_norm": 0.4290536940097809,
      "learning_rate": 1.7241737432025507e-07,
      "loss": 0.5055,
      "step": 61259
    },
    {
      "epoch": 1.8818542069855313,
      "grad_norm": 0.4656594693660736,
      "learning_rate": 1.7232803018618404e-07,
      "loss": 0.4531,
      "step": 61260
    },
    {
      "epoch": 1.8818849261204804,
      "grad_norm": 0.4052823483943939,
      "learning_rate": 1.722387090053268e-07,
      "loss": 0.3897,
      "step": 61261
    },
    {
      "epoch": 1.8819156452554298,
      "grad_norm": 0.4407918155193329,
      "learning_rate": 1.7214941077789316e-07,
      "loss": 0.4533,
      "step": 61262
    },
    {
      "epoch": 1.8819463643903789,
      "grad_norm": 0.5071861147880554,
      "learning_rate": 1.7206013550408962e-07,
      "loss": 0.5269,
      "step": 61263
    },
    {
      "epoch": 1.881977083525328,
      "grad_norm": 0.4283880591392517,
      "learning_rate": 1.7197088318412603e-07,
      "loss": 0.5047,
      "step": 61264
    },
    {
      "epoch": 1.8820078026602771,
      "grad_norm": 0.43293285369873047,
      "learning_rate": 1.718816538182111e-07,
      "loss": 0.4712,
      "step": 61265
    },
    {
      "epoch": 1.8820385217952262,
      "grad_norm": 0.4347473680973053,
      "learning_rate": 1.7179244740655465e-07,
      "loss": 0.4513,
      "step": 61266
    },
    {
      "epoch": 1.8820692409301754,
      "grad_norm": 0.455762654542923,
      "learning_rate": 1.71703263949361e-07,
      "loss": 0.5649,
      "step": 61267
    },
    {
      "epoch": 1.8820999600651245,
      "grad_norm": 0.41253870725631714,
      "learning_rate": 1.7161410344684103e-07,
      "loss": 0.4449,
      "step": 61268
    },
    {
      "epoch": 1.8821306792000736,
      "grad_norm": 0.6160486340522766,
      "learning_rate": 1.7152496589920353e-07,
      "loss": 0.4177,
      "step": 61269
    },
    {
      "epoch": 1.882161398335023,
      "grad_norm": 0.4749019145965576,
      "learning_rate": 1.7143585130665607e-07,
      "loss": 0.4606,
      "step": 61270
    },
    {
      "epoch": 1.882192117469972,
      "grad_norm": 0.4500170052051544,
      "learning_rate": 1.7134675966940628e-07,
      "loss": 0.4326,
      "step": 61271
    },
    {
      "epoch": 1.8822228366049212,
      "grad_norm": 0.42945945262908936,
      "learning_rate": 1.7125769098766175e-07,
      "loss": 0.5043,
      "step": 61272
    },
    {
      "epoch": 1.8822535557398705,
      "grad_norm": 0.42118459939956665,
      "learning_rate": 1.7116864526163236e-07,
      "loss": 0.5527,
      "step": 61273
    },
    {
      "epoch": 1.8822842748748196,
      "grad_norm": 0.4360639452934265,
      "learning_rate": 1.7107962249152565e-07,
      "loss": 0.5053,
      "step": 61274
    },
    {
      "epoch": 1.8823149940097688,
      "grad_norm": 0.46606847643852234,
      "learning_rate": 1.7099062267754706e-07,
      "loss": 0.4569,
      "step": 61275
    },
    {
      "epoch": 1.8823457131447179,
      "grad_norm": 0.4431409537792206,
      "learning_rate": 1.7090164581990752e-07,
      "loss": 0.464,
      "step": 61276
    },
    {
      "epoch": 1.882376432279667,
      "grad_norm": 0.4157993495464325,
      "learning_rate": 1.7081269191881356e-07,
      "loss": 0.4876,
      "step": 61277
    },
    {
      "epoch": 1.8824071514146161,
      "grad_norm": 0.48312297463417053,
      "learning_rate": 1.7072376097447164e-07,
      "loss": 0.4842,
      "step": 61278
    },
    {
      "epoch": 1.8824378705495652,
      "grad_norm": 0.4474705755710602,
      "learning_rate": 1.7063485298709272e-07,
      "loss": 0.501,
      "step": 61279
    },
    {
      "epoch": 1.8824685896845144,
      "grad_norm": 0.5010026097297668,
      "learning_rate": 1.7054596795688217e-07,
      "loss": 0.4414,
      "step": 61280
    },
    {
      "epoch": 1.8824993088194635,
      "grad_norm": 0.4782281517982483,
      "learning_rate": 1.704571058840476e-07,
      "loss": 0.5029,
      "step": 61281
    },
    {
      "epoch": 1.8825300279544128,
      "grad_norm": 0.43128612637519836,
      "learning_rate": 1.703682667687967e-07,
      "loss": 0.4073,
      "step": 61282
    },
    {
      "epoch": 1.882560747089362,
      "grad_norm": 0.5284897685050964,
      "learning_rate": 1.702794506113381e-07,
      "loss": 0.4327,
      "step": 61283
    },
    {
      "epoch": 1.8825914662243113,
      "grad_norm": 0.41940823197364807,
      "learning_rate": 1.7019065741187723e-07,
      "loss": 0.4726,
      "step": 61284
    },
    {
      "epoch": 1.8826221853592604,
      "grad_norm": 0.4154297411441803,
      "learning_rate": 1.7010188717062392e-07,
      "loss": 0.467,
      "step": 61285
    },
    {
      "epoch": 1.8826529044942095,
      "grad_norm": 0.38701099157333374,
      "learning_rate": 1.7001313988778246e-07,
      "loss": 0.4365,
      "step": 61286
    },
    {
      "epoch": 1.8826836236291586,
      "grad_norm": 0.4237142503261566,
      "learning_rate": 1.6992441556356377e-07,
      "loss": 0.472,
      "step": 61287
    },
    {
      "epoch": 1.8827143427641078,
      "grad_norm": 0.49200090765953064,
      "learning_rate": 1.6983571419817213e-07,
      "loss": 0.5272,
      "step": 61288
    },
    {
      "epoch": 1.8827450618990569,
      "grad_norm": 0.4233510196208954,
      "learning_rate": 1.6974703579181628e-07,
      "loss": 0.5217,
      "step": 61289
    },
    {
      "epoch": 1.882775781034006,
      "grad_norm": 0.4049730896949768,
      "learning_rate": 1.6965838034470162e-07,
      "loss": 0.4467,
      "step": 61290
    },
    {
      "epoch": 1.8828065001689551,
      "grad_norm": 0.45830288529396057,
      "learning_rate": 1.6956974785703684e-07,
      "loss": 0.5027,
      "step": 61291
    },
    {
      "epoch": 1.8828372193039042,
      "grad_norm": 0.39675506949424744,
      "learning_rate": 1.6948113832902847e-07,
      "loss": 0.4026,
      "step": 61292
    },
    {
      "epoch": 1.8828679384388536,
      "grad_norm": 0.49403244256973267,
      "learning_rate": 1.6939255176088297e-07,
      "loss": 0.4684,
      "step": 61293
    },
    {
      "epoch": 1.8828986575738027,
      "grad_norm": 0.4183494746685028,
      "learning_rate": 1.6930398815280914e-07,
      "loss": 0.4466,
      "step": 61294
    },
    {
      "epoch": 1.882929376708752,
      "grad_norm": 0.42253097891807556,
      "learning_rate": 1.6921544750501118e-07,
      "loss": 0.443,
      "step": 61295
    },
    {
      "epoch": 1.8829600958437012,
      "grad_norm": 0.41547712683677673,
      "learning_rate": 1.6912692981769785e-07,
      "loss": 0.4509,
      "step": 61296
    },
    {
      "epoch": 1.8829908149786503,
      "grad_norm": 0.4346848726272583,
      "learning_rate": 1.6903843509107454e-07,
      "loss": 0.467,
      "step": 61297
    },
    {
      "epoch": 1.8830215341135994,
      "grad_norm": 0.42737388610839844,
      "learning_rate": 1.6894996332534997e-07,
      "loss": 0.3882,
      "step": 61298
    },
    {
      "epoch": 1.8830522532485485,
      "grad_norm": 0.4745587110519409,
      "learning_rate": 1.688615145207273e-07,
      "loss": 0.4455,
      "step": 61299
    },
    {
      "epoch": 1.8830829723834976,
      "grad_norm": 0.4663487672805786,
      "learning_rate": 1.6877308867741637e-07,
      "loss": 0.4822,
      "step": 61300
    },
    {
      "epoch": 1.8831136915184468,
      "grad_norm": 0.40626856684684753,
      "learning_rate": 1.6868468579562146e-07,
      "loss": 0.39,
      "step": 61301
    },
    {
      "epoch": 1.8831444106533959,
      "grad_norm": 0.48079127073287964,
      "learning_rate": 1.685963058755513e-07,
      "loss": 0.3982,
      "step": 61302
    },
    {
      "epoch": 1.883175129788345,
      "grad_norm": 0.5351725220680237,
      "learning_rate": 1.6850794891741129e-07,
      "loss": 0.4953,
      "step": 61303
    },
    {
      "epoch": 1.8832058489232943,
      "grad_norm": 0.5093926191329956,
      "learning_rate": 1.684196149214068e-07,
      "loss": 0.5411,
      "step": 61304
    },
    {
      "epoch": 1.8832365680582435,
      "grad_norm": 0.41151735186576843,
      "learning_rate": 1.6833130388774433e-07,
      "loss": 0.5026,
      "step": 61305
    },
    {
      "epoch": 1.8832672871931926,
      "grad_norm": 0.47176623344421387,
      "learning_rate": 1.682430158166315e-07,
      "loss": 0.4753,
      "step": 61306
    },
    {
      "epoch": 1.883298006328142,
      "grad_norm": 0.4633760452270508,
      "learning_rate": 1.6815475070827368e-07,
      "loss": 0.4143,
      "step": 61307
    },
    {
      "epoch": 1.883328725463091,
      "grad_norm": 0.4166334569454193,
      "learning_rate": 1.6806650856287744e-07,
      "loss": 0.5569,
      "step": 61308
    },
    {
      "epoch": 1.8833594445980402,
      "grad_norm": 0.4768451750278473,
      "learning_rate": 1.679782893806481e-07,
      "loss": 0.4616,
      "step": 61309
    },
    {
      "epoch": 1.8833901637329893,
      "grad_norm": 0.44048014283180237,
      "learning_rate": 1.6789009316179216e-07,
      "loss": 0.4852,
      "step": 61310
    },
    {
      "epoch": 1.8834208828679384,
      "grad_norm": 0.45303064584732056,
      "learning_rate": 1.6780191990651619e-07,
      "loss": 0.5023,
      "step": 61311
    },
    {
      "epoch": 1.8834516020028875,
      "grad_norm": 0.41643965244293213,
      "learning_rate": 1.677137696150244e-07,
      "loss": 0.4004,
      "step": 61312
    },
    {
      "epoch": 1.8834823211378366,
      "grad_norm": 0.4166610538959503,
      "learning_rate": 1.6762564228752443e-07,
      "loss": 0.528,
      "step": 61313
    },
    {
      "epoch": 1.8835130402727858,
      "grad_norm": 0.42135465145111084,
      "learning_rate": 1.6753753792422056e-07,
      "loss": 0.4021,
      "step": 61314
    },
    {
      "epoch": 1.883543759407735,
      "grad_norm": 0.43402522802352905,
      "learning_rate": 1.6744945652532151e-07,
      "loss": 0.5124,
      "step": 61315
    },
    {
      "epoch": 1.8835744785426842,
      "grad_norm": 0.450176864862442,
      "learning_rate": 1.6736139809102936e-07,
      "loss": 0.451,
      "step": 61316
    },
    {
      "epoch": 1.8836051976776333,
      "grad_norm": 0.3974614441394806,
      "learning_rate": 1.672733626215517e-07,
      "loss": 0.4956,
      "step": 61317
    },
    {
      "epoch": 1.8836359168125827,
      "grad_norm": 0.41961154341697693,
      "learning_rate": 1.671853501170928e-07,
      "loss": 0.4761,
      "step": 61318
    },
    {
      "epoch": 1.8836666359475318,
      "grad_norm": 0.5843471884727478,
      "learning_rate": 1.670973605778614e-07,
      "loss": 0.5381,
      "step": 61319
    },
    {
      "epoch": 1.883697355082481,
      "grad_norm": 0.4572927951812744,
      "learning_rate": 1.6700939400405957e-07,
      "loss": 0.5178,
      "step": 61320
    },
    {
      "epoch": 1.88372807421743,
      "grad_norm": 0.42370113730430603,
      "learning_rate": 1.6692145039589492e-07,
      "loss": 0.4752,
      "step": 61321
    },
    {
      "epoch": 1.8837587933523792,
      "grad_norm": 0.4375174343585968,
      "learning_rate": 1.668335297535695e-07,
      "loss": 0.4914,
      "step": 61322
    },
    {
      "epoch": 1.8837895124873283,
      "grad_norm": 0.42793944478034973,
      "learning_rate": 1.667456320772931e-07,
      "loss": 0.5176,
      "step": 61323
    },
    {
      "epoch": 1.8838202316222774,
      "grad_norm": 0.4387558698654175,
      "learning_rate": 1.6665775736726896e-07,
      "loss": 0.5086,
      "step": 61324
    },
    {
      "epoch": 1.8838509507572265,
      "grad_norm": 0.4398498833179474,
      "learning_rate": 1.6656990562370246e-07,
      "loss": 0.4751,
      "step": 61325
    },
    {
      "epoch": 1.8838816698921759,
      "grad_norm": 0.42245110869407654,
      "learning_rate": 1.6648207684679896e-07,
      "loss": 0.4172,
      "step": 61326
    },
    {
      "epoch": 1.883912389027125,
      "grad_norm": 0.46525782346725464,
      "learning_rate": 1.6639427103676166e-07,
      "loss": 0.447,
      "step": 61327
    },
    {
      "epoch": 1.883943108162074,
      "grad_norm": 0.44219884276390076,
      "learning_rate": 1.6630648819379924e-07,
      "loss": 0.4488,
      "step": 61328
    },
    {
      "epoch": 1.8839738272970235,
      "grad_norm": 0.4706842601299286,
      "learning_rate": 1.6621872831811382e-07,
      "loss": 0.5923,
      "step": 61329
    },
    {
      "epoch": 1.8840045464319726,
      "grad_norm": 0.47475308179855347,
      "learning_rate": 1.6613099140991184e-07,
      "loss": 0.473,
      "step": 61330
    },
    {
      "epoch": 1.8840352655669217,
      "grad_norm": 0.47842130064964294,
      "learning_rate": 1.6604327746939652e-07,
      "loss": 0.4323,
      "step": 61331
    },
    {
      "epoch": 1.8840659847018708,
      "grad_norm": 0.438238263130188,
      "learning_rate": 1.6595558649677436e-07,
      "loss": 0.4715,
      "step": 61332
    },
    {
      "epoch": 1.88409670383682,
      "grad_norm": 0.4470679461956024,
      "learning_rate": 1.658679184922507e-07,
      "loss": 0.4677,
      "step": 61333
    },
    {
      "epoch": 1.884127422971769,
      "grad_norm": 0.4177806079387665,
      "learning_rate": 1.6578027345602875e-07,
      "loss": 0.5152,
      "step": 61334
    },
    {
      "epoch": 1.8841581421067182,
      "grad_norm": 0.45520687103271484,
      "learning_rate": 1.6569265138831392e-07,
      "loss": 0.5121,
      "step": 61335
    },
    {
      "epoch": 1.8841888612416673,
      "grad_norm": 0.43038615584373474,
      "learning_rate": 1.6560505228931047e-07,
      "loss": 0.4122,
      "step": 61336
    },
    {
      "epoch": 1.8842195803766166,
      "grad_norm": 0.43967968225479126,
      "learning_rate": 1.6551747615922265e-07,
      "loss": 0.4305,
      "step": 61337
    },
    {
      "epoch": 1.8842502995115658,
      "grad_norm": 0.4436686038970947,
      "learning_rate": 1.65429922998257e-07,
      "loss": 0.4227,
      "step": 61338
    },
    {
      "epoch": 1.8842810186465149,
      "grad_norm": 0.4613898992538452,
      "learning_rate": 1.6534239280661668e-07,
      "loss": 0.5109,
      "step": 61339
    },
    {
      "epoch": 1.8843117377814642,
      "grad_norm": 0.3918737769126892,
      "learning_rate": 1.6525488558450487e-07,
      "loss": 0.4829,
      "step": 61340
    },
    {
      "epoch": 1.8843424569164133,
      "grad_norm": 0.4500396251678467,
      "learning_rate": 1.6516740133212695e-07,
      "loss": 0.5163,
      "step": 61341
    },
    {
      "epoch": 1.8843731760513625,
      "grad_norm": 0.45726364850997925,
      "learning_rate": 1.650799400496883e-07,
      "loss": 0.5015,
      "step": 61342
    },
    {
      "epoch": 1.8844038951863116,
      "grad_norm": 0.4303392469882965,
      "learning_rate": 1.6499250173739212e-07,
      "loss": 0.5298,
      "step": 61343
    },
    {
      "epoch": 1.8844346143212607,
      "grad_norm": 0.44073015451431274,
      "learning_rate": 1.6490508639544268e-07,
      "loss": 0.4693,
      "step": 61344
    },
    {
      "epoch": 1.8844653334562098,
      "grad_norm": 0.43445590138435364,
      "learning_rate": 1.6481769402404424e-07,
      "loss": 0.4886,
      "step": 61345
    },
    {
      "epoch": 1.884496052591159,
      "grad_norm": 0.4337717294692993,
      "learning_rate": 1.647303246234011e-07,
      "loss": 0.4636,
      "step": 61346
    },
    {
      "epoch": 1.884526771726108,
      "grad_norm": 0.43934616446495056,
      "learning_rate": 1.6464297819371755e-07,
      "loss": 0.3937,
      "step": 61347
    },
    {
      "epoch": 1.8845574908610574,
      "grad_norm": 0.4407886564731598,
      "learning_rate": 1.6455565473519675e-07,
      "loss": 0.461,
      "step": 61348
    },
    {
      "epoch": 1.8845882099960065,
      "grad_norm": 0.44010430574417114,
      "learning_rate": 1.6446835424804296e-07,
      "loss": 0.43,
      "step": 61349
    },
    {
      "epoch": 1.8846189291309556,
      "grad_norm": 0.4817594289779663,
      "learning_rate": 1.643810767324594e-07,
      "loss": 0.4707,
      "step": 61350
    },
    {
      "epoch": 1.884649648265905,
      "grad_norm": 0.4758158028125763,
      "learning_rate": 1.6429382218865252e-07,
      "loss": 0.4962,
      "step": 61351
    },
    {
      "epoch": 1.884680367400854,
      "grad_norm": 0.41455110907554626,
      "learning_rate": 1.6420659061682332e-07,
      "loss": 0.476,
      "step": 61352
    },
    {
      "epoch": 1.8847110865358032,
      "grad_norm": 0.45586729049682617,
      "learning_rate": 1.6411938201717825e-07,
      "loss": 0.4642,
      "step": 61353
    },
    {
      "epoch": 1.8847418056707523,
      "grad_norm": 0.40680623054504395,
      "learning_rate": 1.6403219638991607e-07,
      "loss": 0.4352,
      "step": 61354
    },
    {
      "epoch": 1.8847725248057015,
      "grad_norm": 0.46665507555007935,
      "learning_rate": 1.639450337352466e-07,
      "loss": 0.4542,
      "step": 61355
    },
    {
      "epoch": 1.8848032439406506,
      "grad_norm": 0.4154990613460541,
      "learning_rate": 1.638578940533686e-07,
      "loss": 0.4414,
      "step": 61356
    },
    {
      "epoch": 1.8848339630755997,
      "grad_norm": 0.37643396854400635,
      "learning_rate": 1.6377077734448854e-07,
      "loss": 0.467,
      "step": 61357
    },
    {
      "epoch": 1.8848646822105488,
      "grad_norm": 0.4307675063610077,
      "learning_rate": 1.636836836088085e-07,
      "loss": 0.5498,
      "step": 61358
    },
    {
      "epoch": 1.8848954013454982,
      "grad_norm": 0.4134327173233032,
      "learning_rate": 1.635966128465316e-07,
      "loss": 0.4175,
      "step": 61359
    },
    {
      "epoch": 1.8849261204804473,
      "grad_norm": 0.4533109664916992,
      "learning_rate": 1.635095650578622e-07,
      "loss": 0.4379,
      "step": 61360
    },
    {
      "epoch": 1.8849568396153964,
      "grad_norm": 0.47629478573799133,
      "learning_rate": 1.6342254024300453e-07,
      "loss": 0.4458,
      "step": 61361
    },
    {
      "epoch": 1.8849875587503457,
      "grad_norm": 0.4375284016132355,
      "learning_rate": 1.6333553840215842e-07,
      "loss": 0.5442,
      "step": 61362
    },
    {
      "epoch": 1.8850182778852949,
      "grad_norm": 0.4561811089515686,
      "learning_rate": 1.6324855953552932e-07,
      "loss": 0.4768,
      "step": 61363
    },
    {
      "epoch": 1.885048997020244,
      "grad_norm": 0.4578653573989868,
      "learning_rate": 1.6316160364332145e-07,
      "loss": 0.562,
      "step": 61364
    },
    {
      "epoch": 1.885079716155193,
      "grad_norm": 0.5292873382568359,
      "learning_rate": 1.630746707257358e-07,
      "loss": 0.4369,
      "step": 61365
    },
    {
      "epoch": 1.8851104352901422,
      "grad_norm": 0.45526716113090515,
      "learning_rate": 1.6298776078297662e-07,
      "loss": 0.4565,
      "step": 61366
    },
    {
      "epoch": 1.8851411544250913,
      "grad_norm": 0.4390520453453064,
      "learning_rate": 1.62900873815246e-07,
      "loss": 0.5017,
      "step": 61367
    },
    {
      "epoch": 1.8851718735600405,
      "grad_norm": 0.4273533821105957,
      "learning_rate": 1.628140098227482e-07,
      "loss": 0.4082,
      "step": 61368
    },
    {
      "epoch": 1.8852025926949896,
      "grad_norm": 0.44069525599479675,
      "learning_rate": 1.6272716880568419e-07,
      "loss": 0.4687,
      "step": 61369
    },
    {
      "epoch": 1.885233311829939,
      "grad_norm": 0.3902547359466553,
      "learning_rate": 1.6264035076425933e-07,
      "loss": 0.5087,
      "step": 61370
    },
    {
      "epoch": 1.885264030964888,
      "grad_norm": 0.45582839846611023,
      "learning_rate": 1.6255355569867347e-07,
      "loss": 0.4599,
      "step": 61371
    },
    {
      "epoch": 1.8852947500998372,
      "grad_norm": 0.4170301854610443,
      "learning_rate": 1.6246678360913205e-07,
      "loss": 0.4306,
      "step": 61372
    },
    {
      "epoch": 1.8853254692347865,
      "grad_norm": 0.42301738262176514,
      "learning_rate": 1.6238003449583595e-07,
      "loss": 0.5272,
      "step": 61373
    },
    {
      "epoch": 1.8853561883697356,
      "grad_norm": 0.3807980418205261,
      "learning_rate": 1.6229330835898838e-07,
      "loss": 0.4943,
      "step": 61374
    },
    {
      "epoch": 1.8853869075046847,
      "grad_norm": 0.39986124634742737,
      "learning_rate": 1.622066051987914e-07,
      "loss": 0.4318,
      "step": 61375
    },
    {
      "epoch": 1.8854176266396339,
      "grad_norm": 0.42087095975875854,
      "learning_rate": 1.6211992501544815e-07,
      "loss": 0.4866,
      "step": 61376
    },
    {
      "epoch": 1.885448345774583,
      "grad_norm": 0.4553457498550415,
      "learning_rate": 1.6203326780916183e-07,
      "loss": 0.5067,
      "step": 61377
    },
    {
      "epoch": 1.885479064909532,
      "grad_norm": 0.4427856206893921,
      "learning_rate": 1.619466335801334e-07,
      "loss": 0.5464,
      "step": 61378
    },
    {
      "epoch": 1.8855097840444812,
      "grad_norm": 0.4131275713443756,
      "learning_rate": 1.618600223285649e-07,
      "loss": 0.4445,
      "step": 61379
    },
    {
      "epoch": 1.8855405031794303,
      "grad_norm": 0.4630165994167328,
      "learning_rate": 1.617734340546606e-07,
      "loss": 0.4632,
      "step": 61380
    },
    {
      "epoch": 1.8855712223143797,
      "grad_norm": 0.45203715562820435,
      "learning_rate": 1.616868687586204e-07,
      "loss": 0.438,
      "step": 61381
    },
    {
      "epoch": 1.8856019414493288,
      "grad_norm": 0.4186476767063141,
      "learning_rate": 1.616003264406485e-07,
      "loss": 0.5111,
      "step": 61382
    },
    {
      "epoch": 1.885632660584278,
      "grad_norm": 0.42865949869155884,
      "learning_rate": 1.6151380710094588e-07,
      "loss": 0.4918,
      "step": 61383
    },
    {
      "epoch": 1.8856633797192273,
      "grad_norm": 0.451215922832489,
      "learning_rate": 1.6142731073971463e-07,
      "loss": 0.4871,
      "step": 61384
    },
    {
      "epoch": 1.8856940988541764,
      "grad_norm": 0.42131268978118896,
      "learning_rate": 1.6134083735715677e-07,
      "loss": 0.5103,
      "step": 61385
    },
    {
      "epoch": 1.8857248179891255,
      "grad_norm": 0.3972522020339966,
      "learning_rate": 1.6125438695347438e-07,
      "loss": 0.4916,
      "step": 61386
    },
    {
      "epoch": 1.8857555371240746,
      "grad_norm": 0.40917885303497314,
      "learning_rate": 1.6116795952887066e-07,
      "loss": 0.481,
      "step": 61387
    },
    {
      "epoch": 1.8857862562590237,
      "grad_norm": 0.4325752556324005,
      "learning_rate": 1.610815550835454e-07,
      "loss": 0.4548,
      "step": 61388
    },
    {
      "epoch": 1.8858169753939729,
      "grad_norm": 0.4513513445854187,
      "learning_rate": 1.609951736177029e-07,
      "loss": 0.4694,
      "step": 61389
    },
    {
      "epoch": 1.885847694528922,
      "grad_norm": 0.44326844811439514,
      "learning_rate": 1.6090881513154077e-07,
      "loss": 0.4504,
      "step": 61390
    },
    {
      "epoch": 1.885878413663871,
      "grad_norm": 0.4192562997341156,
      "learning_rate": 1.6082247962526553e-07,
      "loss": 0.5692,
      "step": 61391
    },
    {
      "epoch": 1.8859091327988202,
      "grad_norm": 0.47915852069854736,
      "learning_rate": 1.607361670990748e-07,
      "loss": 0.5143,
      "step": 61392
    },
    {
      "epoch": 1.8859398519337696,
      "grad_norm": 0.4334270656108856,
      "learning_rate": 1.6064987755317284e-07,
      "loss": 0.4415,
      "step": 61393
    },
    {
      "epoch": 1.8859705710687187,
      "grad_norm": 0.525864839553833,
      "learning_rate": 1.6056361098776064e-07,
      "loss": 0.5895,
      "step": 61394
    },
    {
      "epoch": 1.886001290203668,
      "grad_norm": 0.427304744720459,
      "learning_rate": 1.60477367403038e-07,
      "loss": 0.4177,
      "step": 61395
    },
    {
      "epoch": 1.8860320093386171,
      "grad_norm": 0.42806392908096313,
      "learning_rate": 1.603911467992081e-07,
      "loss": 0.5034,
      "step": 61396
    },
    {
      "epoch": 1.8860627284735663,
      "grad_norm": 0.44236183166503906,
      "learning_rate": 1.60304949176473e-07,
      "loss": 0.4151,
      "step": 61397
    },
    {
      "epoch": 1.8860934476085154,
      "grad_norm": 0.4408301115036011,
      "learning_rate": 1.6021877453503142e-07,
      "loss": 0.4527,
      "step": 61398
    },
    {
      "epoch": 1.8861241667434645,
      "grad_norm": 0.44313839077949524,
      "learning_rate": 1.6013262287508657e-07,
      "loss": 0.508,
      "step": 61399
    },
    {
      "epoch": 1.8861548858784136,
      "grad_norm": 0.4614700675010681,
      "learning_rate": 1.600464941968394e-07,
      "loss": 0.5255,
      "step": 61400
    },
    {
      "epoch": 1.8861856050133627,
      "grad_norm": 0.4782986640930176,
      "learning_rate": 1.599603885004919e-07,
      "loss": 0.5324,
      "step": 61401
    },
    {
      "epoch": 1.8862163241483119,
      "grad_norm": 0.4107007086277008,
      "learning_rate": 1.5987430578624175e-07,
      "loss": 0.4422,
      "step": 61402
    },
    {
      "epoch": 1.886247043283261,
      "grad_norm": 0.4293791651725769,
      "learning_rate": 1.5978824605429433e-07,
      "loss": 0.4651,
      "step": 61403
    },
    {
      "epoch": 1.8862777624182103,
      "grad_norm": 0.43801742792129517,
      "learning_rate": 1.5970220930484726e-07,
      "loss": 0.444,
      "step": 61404
    },
    {
      "epoch": 1.8863084815531594,
      "grad_norm": 0.44723454117774963,
      "learning_rate": 1.596161955381037e-07,
      "loss": 0.4301,
      "step": 61405
    },
    {
      "epoch": 1.8863392006881088,
      "grad_norm": 0.41355448961257935,
      "learning_rate": 1.5953020475426463e-07,
      "loss": 0.4778,
      "step": 61406
    },
    {
      "epoch": 1.886369919823058,
      "grad_norm": 0.47828125953674316,
      "learning_rate": 1.5944423695352872e-07,
      "loss": 0.5455,
      "step": 61407
    },
    {
      "epoch": 1.886400638958007,
      "grad_norm": 0.4042179584503174,
      "learning_rate": 1.593582921360981e-07,
      "loss": 0.4407,
      "step": 61408
    },
    {
      "epoch": 1.8864313580929561,
      "grad_norm": 0.508169412612915,
      "learning_rate": 1.5927237030217367e-07,
      "loss": 0.4505,
      "step": 61409
    },
    {
      "epoch": 1.8864620772279053,
      "grad_norm": 0.47417378425598145,
      "learning_rate": 1.5918647145195642e-07,
      "loss": 0.5417,
      "step": 61410
    },
    {
      "epoch": 1.8864927963628544,
      "grad_norm": 0.45872190594673157,
      "learning_rate": 1.5910059558564618e-07,
      "loss": 0.46,
      "step": 61411
    },
    {
      "epoch": 1.8865235154978035,
      "grad_norm": 0.4346151351928711,
      "learning_rate": 1.5901474270344275e-07,
      "loss": 0.5023,
      "step": 61412
    },
    {
      "epoch": 1.8865542346327526,
      "grad_norm": 0.5119224190711975,
      "learning_rate": 1.5892891280554933e-07,
      "loss": 0.4912,
      "step": 61413
    },
    {
      "epoch": 1.8865849537677017,
      "grad_norm": 0.45819154381752014,
      "learning_rate": 1.5884310589216355e-07,
      "loss": 0.5418,
      "step": 61414
    },
    {
      "epoch": 1.886615672902651,
      "grad_norm": 0.4284026622772217,
      "learning_rate": 1.5875732196348748e-07,
      "loss": 0.4732,
      "step": 61415
    },
    {
      "epoch": 1.8866463920376002,
      "grad_norm": 0.47203925251960754,
      "learning_rate": 1.5867156101972203e-07,
      "loss": 0.4501,
      "step": 61416
    },
    {
      "epoch": 1.8866771111725493,
      "grad_norm": 0.4311882257461548,
      "learning_rate": 1.5858582306106372e-07,
      "loss": 0.4677,
      "step": 61417
    },
    {
      "epoch": 1.8867078303074987,
      "grad_norm": 0.39104506373405457,
      "learning_rate": 1.5850010808771798e-07,
      "loss": 0.52,
      "step": 61418
    },
    {
      "epoch": 1.8867385494424478,
      "grad_norm": 0.4530031383037567,
      "learning_rate": 1.5841441609988128e-07,
      "loss": 0.3286,
      "step": 61419
    },
    {
      "epoch": 1.886769268577397,
      "grad_norm": 0.4623859226703644,
      "learning_rate": 1.583287470977568e-07,
      "loss": 0.4458,
      "step": 61420
    },
    {
      "epoch": 1.886799987712346,
      "grad_norm": 0.42303115129470825,
      "learning_rate": 1.5824310108154107e-07,
      "loss": 0.4283,
      "step": 61421
    },
    {
      "epoch": 1.8868307068472951,
      "grad_norm": 0.42806288599967957,
      "learning_rate": 1.58157478051435e-07,
      "loss": 0.4976,
      "step": 61422
    },
    {
      "epoch": 1.8868614259822443,
      "grad_norm": 0.4216579794883728,
      "learning_rate": 1.580718780076418e-07,
      "loss": 0.4722,
      "step": 61423
    },
    {
      "epoch": 1.8868921451171934,
      "grad_norm": 0.4946812093257904,
      "learning_rate": 1.5798630095035794e-07,
      "loss": 0.5219,
      "step": 61424
    },
    {
      "epoch": 1.8869228642521425,
      "grad_norm": 0.5198891758918762,
      "learning_rate": 1.5790074687978552e-07,
      "loss": 0.4701,
      "step": 61425
    },
    {
      "epoch": 1.8869535833870918,
      "grad_norm": 0.44055113196372986,
      "learning_rate": 1.5781521579612103e-07,
      "loss": 0.512,
      "step": 61426
    },
    {
      "epoch": 1.886984302522041,
      "grad_norm": 0.41065406799316406,
      "learning_rate": 1.5772970769956874e-07,
      "loss": 0.4522,
      "step": 61427
    },
    {
      "epoch": 1.88701502165699,
      "grad_norm": 0.43439438939094543,
      "learning_rate": 1.576442225903252e-07,
      "loss": 0.5465,
      "step": 61428
    },
    {
      "epoch": 1.8870457407919394,
      "grad_norm": 0.45816898345947266,
      "learning_rate": 1.575587604685913e-07,
      "loss": 0.4366,
      "step": 61429
    },
    {
      "epoch": 1.8870764599268885,
      "grad_norm": 0.4874052107334137,
      "learning_rate": 1.5747332133456583e-07,
      "loss": 0.5042,
      "step": 61430
    },
    {
      "epoch": 1.8871071790618377,
      "grad_norm": 0.4637618362903595,
      "learning_rate": 1.573879051884486e-07,
      "loss": 0.4288,
      "step": 61431
    },
    {
      "epoch": 1.8871378981967868,
      "grad_norm": 0.3989788889884949,
      "learning_rate": 1.5730251203043944e-07,
      "loss": 0.4875,
      "step": 61432
    },
    {
      "epoch": 1.887168617331736,
      "grad_norm": 0.41634923219680786,
      "learning_rate": 1.5721714186073932e-07,
      "loss": 0.442,
      "step": 61433
    },
    {
      "epoch": 1.887199336466685,
      "grad_norm": 0.40123045444488525,
      "learning_rate": 1.5713179467954364e-07,
      "loss": 0.5206,
      "step": 61434
    },
    {
      "epoch": 1.8872300556016341,
      "grad_norm": 0.42374351620674133,
      "learning_rate": 1.5704647048705556e-07,
      "loss": 0.5107,
      "step": 61435
    },
    {
      "epoch": 1.8872607747365833,
      "grad_norm": 0.4301796853542328,
      "learning_rate": 1.569611692834716e-07,
      "loss": 0.4651,
      "step": 61436
    },
    {
      "epoch": 1.8872914938715326,
      "grad_norm": 0.4426899254322052,
      "learning_rate": 1.568758910689938e-07,
      "loss": 0.4899,
      "step": 61437
    },
    {
      "epoch": 1.8873222130064817,
      "grad_norm": 0.6630458235740662,
      "learning_rate": 1.567906358438187e-07,
      "loss": 0.4222,
      "step": 61438
    },
    {
      "epoch": 1.8873529321414309,
      "grad_norm": 0.415564626455307,
      "learning_rate": 1.5670540360814613e-07,
      "loss": 0.4828,
      "step": 61439
    },
    {
      "epoch": 1.8873836512763802,
      "grad_norm": 0.416791707277298,
      "learning_rate": 1.566201943621759e-07,
      "loss": 0.5362,
      "step": 61440
    },
    {
      "epoch": 1.8874143704113293,
      "grad_norm": 0.42304837703704834,
      "learning_rate": 1.5653500810610678e-07,
      "loss": 0.474,
      "step": 61441
    },
    {
      "epoch": 1.8874450895462784,
      "grad_norm": 0.43788859248161316,
      "learning_rate": 1.564498448401386e-07,
      "loss": 0.4745,
      "step": 61442
    },
    {
      "epoch": 1.8874758086812276,
      "grad_norm": 0.4355710744857788,
      "learning_rate": 1.5636470456446783e-07,
      "loss": 0.4647,
      "step": 61443
    },
    {
      "epoch": 1.8875065278161767,
      "grad_norm": 0.4354539215564728,
      "learning_rate": 1.562795872792955e-07,
      "loss": 0.4123,
      "step": 61444
    },
    {
      "epoch": 1.8875372469511258,
      "grad_norm": 0.4546816051006317,
      "learning_rate": 1.5619449298481915e-07,
      "loss": 0.5124,
      "step": 61445
    },
    {
      "epoch": 1.887567966086075,
      "grad_norm": 0.3758700489997864,
      "learning_rate": 1.5610942168123978e-07,
      "loss": 0.4599,
      "step": 61446
    },
    {
      "epoch": 1.887598685221024,
      "grad_norm": 0.4314969480037689,
      "learning_rate": 1.5602437336875275e-07,
      "loss": 0.4874,
      "step": 61447
    },
    {
      "epoch": 1.8876294043559734,
      "grad_norm": 0.4086928069591522,
      "learning_rate": 1.5593934804755796e-07,
      "loss": 0.4153,
      "step": 61448
    },
    {
      "epoch": 1.8876601234909225,
      "grad_norm": 0.4576767385005951,
      "learning_rate": 1.5585434571785518e-07,
      "loss": 0.4712,
      "step": 61449
    },
    {
      "epoch": 1.8876908426258716,
      "grad_norm": 0.4399731457233429,
      "learning_rate": 1.5576936637984208e-07,
      "loss": 0.4101,
      "step": 61450
    },
    {
      "epoch": 1.887721561760821,
      "grad_norm": 0.4037742614746094,
      "learning_rate": 1.5568441003371626e-07,
      "loss": 0.4688,
      "step": 61451
    },
    {
      "epoch": 1.88775228089577,
      "grad_norm": 0.4194256067276001,
      "learning_rate": 1.5559947667967866e-07,
      "loss": 0.4293,
      "step": 61452
    },
    {
      "epoch": 1.8877830000307192,
      "grad_norm": 0.4959774315357208,
      "learning_rate": 1.555145663179236e-07,
      "loss": 0.426,
      "step": 61453
    },
    {
      "epoch": 1.8878137191656683,
      "grad_norm": 0.47112128138542175,
      "learning_rate": 1.5542967894865425e-07,
      "loss": 0.4157,
      "step": 61454
    },
    {
      "epoch": 1.8878444383006174,
      "grad_norm": 0.44851699471473694,
      "learning_rate": 1.5534481457206486e-07,
      "loss": 0.4981,
      "step": 61455
    },
    {
      "epoch": 1.8878751574355666,
      "grad_norm": 0.4670327603816986,
      "learning_rate": 1.552599731883564e-07,
      "loss": 0.5246,
      "step": 61456
    },
    {
      "epoch": 1.8879058765705157,
      "grad_norm": 0.4436846375465393,
      "learning_rate": 1.5517515479772537e-07,
      "loss": 0.5182,
      "step": 61457
    },
    {
      "epoch": 1.8879365957054648,
      "grad_norm": 0.44036370515823364,
      "learning_rate": 1.550903594003683e-07,
      "loss": 0.4242,
      "step": 61458
    },
    {
      "epoch": 1.8879673148404141,
      "grad_norm": 0.4165513813495636,
      "learning_rate": 1.5500558699648838e-07,
      "loss": 0.4287,
      "step": 61459
    },
    {
      "epoch": 1.8879980339753633,
      "grad_norm": 0.38362470269203186,
      "learning_rate": 1.5492083758627873e-07,
      "loss": 0.4147,
      "step": 61460
    },
    {
      "epoch": 1.8880287531103124,
      "grad_norm": 0.4215337336063385,
      "learning_rate": 1.5483611116994036e-07,
      "loss": 0.5019,
      "step": 61461
    },
    {
      "epoch": 1.8880594722452617,
      "grad_norm": 0.44448235630989075,
      "learning_rate": 1.5475140774766863e-07,
      "loss": 0.4583,
      "step": 61462
    },
    {
      "epoch": 1.8880901913802108,
      "grad_norm": 0.42451831698417664,
      "learning_rate": 1.5466672731966225e-07,
      "loss": 0.4585,
      "step": 61463
    },
    {
      "epoch": 1.88812091051516,
      "grad_norm": 0.39977267384529114,
      "learning_rate": 1.5458206988612e-07,
      "loss": 0.5355,
      "step": 61464
    },
    {
      "epoch": 1.888151629650109,
      "grad_norm": 0.4273221492767334,
      "learning_rate": 1.5449743544723948e-07,
      "loss": 0.48,
      "step": 61465
    },
    {
      "epoch": 1.8881823487850582,
      "grad_norm": 0.5245645046234131,
      "learning_rate": 1.5441282400321612e-07,
      "loss": 0.4652,
      "step": 61466
    },
    {
      "epoch": 1.8882130679200073,
      "grad_norm": 0.4215608239173889,
      "learning_rate": 1.543282355542508e-07,
      "loss": 0.4508,
      "step": 61467
    },
    {
      "epoch": 1.8882437870549564,
      "grad_norm": 0.4425484836101532,
      "learning_rate": 1.5424367010053898e-07,
      "loss": 0.3966,
      "step": 61468
    },
    {
      "epoch": 1.8882745061899056,
      "grad_norm": 0.42534521222114563,
      "learning_rate": 1.5415912764227936e-07,
      "loss": 0.5277,
      "step": 61469
    },
    {
      "epoch": 1.888305225324855,
      "grad_norm": 0.4318413734436035,
      "learning_rate": 1.5407460817966735e-07,
      "loss": 0.4806,
      "step": 61470
    },
    {
      "epoch": 1.888335944459804,
      "grad_norm": 0.5245274305343628,
      "learning_rate": 1.5399011171290168e-07,
      "loss": 0.457,
      "step": 61471
    },
    {
      "epoch": 1.8883666635947531,
      "grad_norm": 0.4157104194164276,
      "learning_rate": 1.5390563824218108e-07,
      "loss": 0.5336,
      "step": 61472
    },
    {
      "epoch": 1.8883973827297025,
      "grad_norm": 0.41968637704849243,
      "learning_rate": 1.5382118776770093e-07,
      "loss": 0.509,
      "step": 61473
    },
    {
      "epoch": 1.8884281018646516,
      "grad_norm": 0.3949902057647705,
      "learning_rate": 1.537367602896589e-07,
      "loss": 0.4696,
      "step": 61474
    },
    {
      "epoch": 1.8884588209996007,
      "grad_norm": 0.43170836567878723,
      "learning_rate": 1.5365235580825255e-07,
      "loss": 0.5049,
      "step": 61475
    },
    {
      "epoch": 1.8884895401345498,
      "grad_norm": 0.414308100938797,
      "learning_rate": 1.5356797432367842e-07,
      "loss": 0.4274,
      "step": 61476
    },
    {
      "epoch": 1.888520259269499,
      "grad_norm": 0.42171886563301086,
      "learning_rate": 1.5348361583613413e-07,
      "loss": 0.508,
      "step": 61477
    },
    {
      "epoch": 1.888550978404448,
      "grad_norm": 0.40472540259361267,
      "learning_rate": 1.5339928034581731e-07,
      "loss": 0.3644,
      "step": 61478
    },
    {
      "epoch": 1.8885816975393972,
      "grad_norm": 0.4249764680862427,
      "learning_rate": 1.5331496785292221e-07,
      "loss": 0.488,
      "step": 61479
    },
    {
      "epoch": 1.8886124166743463,
      "grad_norm": 0.4212954044342041,
      "learning_rate": 1.532306783576487e-07,
      "loss": 0.435,
      "step": 61480
    },
    {
      "epoch": 1.8886431358092957,
      "grad_norm": 0.46617206931114197,
      "learning_rate": 1.531464118601933e-07,
      "loss": 0.435,
      "step": 61481
    },
    {
      "epoch": 1.8886738549442448,
      "grad_norm": 0.43057286739349365,
      "learning_rate": 1.530621683607525e-07,
      "loss": 0.4761,
      "step": 61482
    },
    {
      "epoch": 1.888704574079194,
      "grad_norm": 0.7945894002914429,
      "learning_rate": 1.5297794785952168e-07,
      "loss": 0.5469,
      "step": 61483
    },
    {
      "epoch": 1.8887352932141432,
      "grad_norm": 0.5685705542564392,
      "learning_rate": 1.528937503566985e-07,
      "loss": 0.3836,
      "step": 61484
    },
    {
      "epoch": 1.8887660123490924,
      "grad_norm": 0.43079328536987305,
      "learning_rate": 1.5280957585247947e-07,
      "loss": 0.4728,
      "step": 61485
    },
    {
      "epoch": 1.8887967314840415,
      "grad_norm": 0.4334378242492676,
      "learning_rate": 1.5272542434706216e-07,
      "loss": 0.4414,
      "step": 61486
    },
    {
      "epoch": 1.8888274506189906,
      "grad_norm": 0.4457607865333557,
      "learning_rate": 1.52641295840642e-07,
      "loss": 0.399,
      "step": 61487
    },
    {
      "epoch": 1.8888581697539397,
      "grad_norm": 0.3774489462375641,
      "learning_rate": 1.5255719033341666e-07,
      "loss": 0.5068,
      "step": 61488
    },
    {
      "epoch": 1.8888888888888888,
      "grad_norm": 0.453193336725235,
      "learning_rate": 1.5247310782558034e-07,
      "loss": 0.4669,
      "step": 61489
    },
    {
      "epoch": 1.888919608023838,
      "grad_norm": 0.4285561442375183,
      "learning_rate": 1.523890483173318e-07,
      "loss": 0.5206,
      "step": 61490
    },
    {
      "epoch": 1.888950327158787,
      "grad_norm": 0.45206716656684875,
      "learning_rate": 1.5230501180886538e-07,
      "loss": 0.5552,
      "step": 61491
    },
    {
      "epoch": 1.8889810462937364,
      "grad_norm": 0.4847131073474884,
      "learning_rate": 1.5222099830037974e-07,
      "loss": 0.4334,
      "step": 61492
    },
    {
      "epoch": 1.8890117654286855,
      "grad_norm": 0.47663161158561707,
      "learning_rate": 1.521370077920692e-07,
      "loss": 0.5222,
      "step": 61493
    },
    {
      "epoch": 1.8890424845636347,
      "grad_norm": 0.4256450831890106,
      "learning_rate": 1.5205304028412916e-07,
      "loss": 0.4118,
      "step": 61494
    },
    {
      "epoch": 1.889073203698584,
      "grad_norm": 0.473661333322525,
      "learning_rate": 1.5196909577675833e-07,
      "loss": 0.4843,
      "step": 61495
    },
    {
      "epoch": 1.8891039228335331,
      "grad_norm": 0.43318307399749756,
      "learning_rate": 1.5188517427015103e-07,
      "loss": 0.3722,
      "step": 61496
    },
    {
      "epoch": 1.8891346419684822,
      "grad_norm": 0.4536309242248535,
      "learning_rate": 1.5180127576450488e-07,
      "loss": 0.4297,
      "step": 61497
    },
    {
      "epoch": 1.8891653611034314,
      "grad_norm": 0.45685428380966187,
      "learning_rate": 1.5171740026001302e-07,
      "loss": 0.4844,
      "step": 61498
    },
    {
      "epoch": 1.8891960802383805,
      "grad_norm": 0.4728609621524811,
      "learning_rate": 1.5163354775687422e-07,
      "loss": 0.4669,
      "step": 61499
    },
    {
      "epoch": 1.8892267993733296,
      "grad_norm": 0.44810613989830017,
      "learning_rate": 1.5154971825528164e-07,
      "loss": 0.4815,
      "step": 61500
    },
    {
      "epoch": 1.8892575185082787,
      "grad_norm": 0.40030041337013245,
      "learning_rate": 1.5146591175543402e-07,
      "loss": 0.404,
      "step": 61501
    },
    {
      "epoch": 1.8892882376432278,
      "grad_norm": 0.4487874209880829,
      "learning_rate": 1.5138212825752453e-07,
      "loss": 0.4104,
      "step": 61502
    },
    {
      "epoch": 1.889318956778177,
      "grad_norm": 0.44653788208961487,
      "learning_rate": 1.5129836776175078e-07,
      "loss": 0.4061,
      "step": 61503
    },
    {
      "epoch": 1.8893496759131263,
      "grad_norm": 0.4970981180667877,
      "learning_rate": 1.5121463026830597e-07,
      "loss": 0.5107,
      "step": 61504
    },
    {
      "epoch": 1.8893803950480754,
      "grad_norm": 0.45632991194725037,
      "learning_rate": 1.511309157773888e-07,
      "loss": 0.44,
      "step": 61505
    },
    {
      "epoch": 1.8894111141830248,
      "grad_norm": 0.439485102891922,
      "learning_rate": 1.510472242891925e-07,
      "loss": 0.4869,
      "step": 61506
    },
    {
      "epoch": 1.8894418333179739,
      "grad_norm": 0.3879133462905884,
      "learning_rate": 1.5096355580391352e-07,
      "loss": 0.4177,
      "step": 61507
    },
    {
      "epoch": 1.889472552452923,
      "grad_norm": 0.45107823610305786,
      "learning_rate": 1.508799103217462e-07,
      "loss": 0.446,
      "step": 61508
    },
    {
      "epoch": 1.8895032715878721,
      "grad_norm": 0.4233095347881317,
      "learning_rate": 1.5079628784288813e-07,
      "loss": 0.4586,
      "step": 61509
    },
    {
      "epoch": 1.8895339907228212,
      "grad_norm": 0.4984252452850342,
      "learning_rate": 1.507126883675325e-07,
      "loss": 0.5139,
      "step": 61510
    },
    {
      "epoch": 1.8895647098577704,
      "grad_norm": 0.45188429951667786,
      "learning_rate": 1.506291118958747e-07,
      "loss": 0.5115,
      "step": 61511
    },
    {
      "epoch": 1.8895954289927195,
      "grad_norm": 0.44892022013664246,
      "learning_rate": 1.5054555842811125e-07,
      "loss": 0.4908,
      "step": 61512
    },
    {
      "epoch": 1.8896261481276686,
      "grad_norm": 0.4859064519405365,
      "learning_rate": 1.5046202796443643e-07,
      "loss": 0.4654,
      "step": 61513
    },
    {
      "epoch": 1.8896568672626177,
      "grad_norm": 0.5410929322242737,
      "learning_rate": 1.5037852050504565e-07,
      "loss": 0.4469,
      "step": 61514
    },
    {
      "epoch": 1.889687586397567,
      "grad_norm": 0.48404577374458313,
      "learning_rate": 1.502950360501332e-07,
      "loss": 0.4346,
      "step": 61515
    },
    {
      "epoch": 1.8897183055325162,
      "grad_norm": 0.42908531427383423,
      "learning_rate": 1.5021157459989445e-07,
      "loss": 0.405,
      "step": 61516
    },
    {
      "epoch": 1.8897490246674655,
      "grad_norm": 0.5359894633293152,
      "learning_rate": 1.5012813615452483e-07,
      "loss": 0.4279,
      "step": 61517
    },
    {
      "epoch": 1.8897797438024146,
      "grad_norm": 0.432304710149765,
      "learning_rate": 1.500447207142186e-07,
      "loss": 0.4488,
      "step": 61518
    },
    {
      "epoch": 1.8898104629373638,
      "grad_norm": 0.4214887022972107,
      "learning_rate": 1.499613282791712e-07,
      "loss": 0.5147,
      "step": 61519
    },
    {
      "epoch": 1.8898411820723129,
      "grad_norm": 0.4160018265247345,
      "learning_rate": 1.498779588495769e-07,
      "loss": 0.5123,
      "step": 61520
    },
    {
      "epoch": 1.889871901207262,
      "grad_norm": 0.4232652485370636,
      "learning_rate": 1.4979461242562997e-07,
      "loss": 0.4301,
      "step": 61521
    },
    {
      "epoch": 1.8899026203422111,
      "grad_norm": 0.41777610778808594,
      "learning_rate": 1.4971128900752697e-07,
      "loss": 0.4191,
      "step": 61522
    },
    {
      "epoch": 1.8899333394771602,
      "grad_norm": 0.42994385957717896,
      "learning_rate": 1.496279885954599e-07,
      "loss": 0.5168,
      "step": 61523
    },
    {
      "epoch": 1.8899640586121094,
      "grad_norm": 0.43372905254364014,
      "learning_rate": 1.4954471118962534e-07,
      "loss": 0.4464,
      "step": 61524
    },
    {
      "epoch": 1.8899947777470585,
      "grad_norm": 0.406097412109375,
      "learning_rate": 1.494614567902164e-07,
      "loss": 0.4272,
      "step": 61525
    },
    {
      "epoch": 1.8900254968820078,
      "grad_norm": 0.46063780784606934,
      "learning_rate": 1.4937822539742852e-07,
      "loss": 0.449,
      "step": 61526
    },
    {
      "epoch": 1.890056216016957,
      "grad_norm": 0.4838012158870697,
      "learning_rate": 1.4929501701145598e-07,
      "loss": 0.3688,
      "step": 61527
    },
    {
      "epoch": 1.890086935151906,
      "grad_norm": 0.4610116481781006,
      "learning_rate": 1.4921183163249308e-07,
      "loss": 0.4763,
      "step": 61528
    },
    {
      "epoch": 1.8901176542868554,
      "grad_norm": 0.40829023718833923,
      "learning_rate": 1.491286692607341e-07,
      "loss": 0.4692,
      "step": 61529
    },
    {
      "epoch": 1.8901483734218045,
      "grad_norm": 0.4258267283439636,
      "learning_rate": 1.4904552989637223e-07,
      "loss": 0.4893,
      "step": 61530
    },
    {
      "epoch": 1.8901790925567536,
      "grad_norm": 0.4109746515750885,
      "learning_rate": 1.4896241353960284e-07,
      "loss": 0.4412,
      "step": 61531
    },
    {
      "epoch": 1.8902098116917028,
      "grad_norm": 0.39487791061401367,
      "learning_rate": 1.4887932019061912e-07,
      "loss": 0.5066,
      "step": 61532
    },
    {
      "epoch": 1.8902405308266519,
      "grad_norm": 0.40339791774749756,
      "learning_rate": 1.4879624984961648e-07,
      "loss": 0.4646,
      "step": 61533
    },
    {
      "epoch": 1.890271249961601,
      "grad_norm": 0.440603107213974,
      "learning_rate": 1.4871320251678812e-07,
      "loss": 0.4514,
      "step": 61534
    },
    {
      "epoch": 1.8903019690965501,
      "grad_norm": 0.4257156252861023,
      "learning_rate": 1.4863017819232827e-07,
      "loss": 0.4704,
      "step": 61535
    },
    {
      "epoch": 1.8903326882314992,
      "grad_norm": 0.41934922337532043,
      "learning_rate": 1.4854717687643017e-07,
      "loss": 0.4768,
      "step": 61536
    },
    {
      "epoch": 1.8903634073664486,
      "grad_norm": 0.44660913944244385,
      "learning_rate": 1.4846419856928918e-07,
      "loss": 0.5174,
      "step": 61537
    },
    {
      "epoch": 1.8903941265013977,
      "grad_norm": 0.4108333885669708,
      "learning_rate": 1.4838124327109627e-07,
      "loss": 0.4987,
      "step": 61538
    },
    {
      "epoch": 1.8904248456363468,
      "grad_norm": 0.45845240354537964,
      "learning_rate": 1.4829831098204794e-07,
      "loss": 0.4578,
      "step": 61539
    },
    {
      "epoch": 1.8904555647712962,
      "grad_norm": 0.45938625931739807,
      "learning_rate": 1.4821540170233739e-07,
      "loss": 0.4982,
      "step": 61540
    },
    {
      "epoch": 1.8904862839062453,
      "grad_norm": 0.42444029450416565,
      "learning_rate": 1.4813251543215778e-07,
      "loss": 0.4305,
      "step": 61541
    },
    {
      "epoch": 1.8905170030411944,
      "grad_norm": 0.4115677773952484,
      "learning_rate": 1.480496521717023e-07,
      "loss": 0.4849,
      "step": 61542
    },
    {
      "epoch": 1.8905477221761435,
      "grad_norm": 0.42891737818717957,
      "learning_rate": 1.4796681192116413e-07,
      "loss": 0.4703,
      "step": 61543
    },
    {
      "epoch": 1.8905784413110927,
      "grad_norm": 0.39830702543258667,
      "learning_rate": 1.4788399468073866e-07,
      "loss": 0.4383,
      "step": 61544
    },
    {
      "epoch": 1.8906091604460418,
      "grad_norm": 0.41482219099998474,
      "learning_rate": 1.4780120045061795e-07,
      "loss": 0.4777,
      "step": 61545
    },
    {
      "epoch": 1.890639879580991,
      "grad_norm": 0.42544490098953247,
      "learning_rate": 1.4771842923099633e-07,
      "loss": 0.4301,
      "step": 61546
    },
    {
      "epoch": 1.89067059871594,
      "grad_norm": 0.412807822227478,
      "learning_rate": 1.4763568102206584e-07,
      "loss": 0.4869,
      "step": 61547
    },
    {
      "epoch": 1.8907013178508894,
      "grad_norm": 0.45134374499320984,
      "learning_rate": 1.4755295582401964e-07,
      "loss": 0.5083,
      "step": 61548
    },
    {
      "epoch": 1.8907320369858385,
      "grad_norm": 0.4521266222000122,
      "learning_rate": 1.474702536370509e-07,
      "loss": 0.536,
      "step": 61549
    },
    {
      "epoch": 1.8907627561207876,
      "grad_norm": 0.4625769257545471,
      "learning_rate": 1.473875744613551e-07,
      "loss": 0.6705,
      "step": 61550
    },
    {
      "epoch": 1.890793475255737,
      "grad_norm": 0.44569966197013855,
      "learning_rate": 1.4730491829712312e-07,
      "loss": 0.4018,
      "step": 61551
    },
    {
      "epoch": 1.890824194390686,
      "grad_norm": 0.5040177702903748,
      "learning_rate": 1.472222851445493e-07,
      "loss": 0.45,
      "step": 61552
    },
    {
      "epoch": 1.8908549135256352,
      "grad_norm": 0.4395093619823456,
      "learning_rate": 1.4713967500382453e-07,
      "loss": 0.5097,
      "step": 61553
    },
    {
      "epoch": 1.8908856326605843,
      "grad_norm": 0.46633821725845337,
      "learning_rate": 1.4705708787514538e-07,
      "loss": 0.4981,
      "step": 61554
    },
    {
      "epoch": 1.8909163517955334,
      "grad_norm": 0.46073970198631287,
      "learning_rate": 1.469745237587006e-07,
      "loss": 0.4761,
      "step": 61555
    },
    {
      "epoch": 1.8909470709304825,
      "grad_norm": 0.38753968477249146,
      "learning_rate": 1.468919826546855e-07,
      "loss": 0.4272,
      "step": 61556
    },
    {
      "epoch": 1.8909777900654317,
      "grad_norm": 0.47657182812690735,
      "learning_rate": 1.4680946456329225e-07,
      "loss": 0.495,
      "step": 61557
    },
    {
      "epoch": 1.8910085092003808,
      "grad_norm": 0.43018320202827454,
      "learning_rate": 1.4672696948471398e-07,
      "loss": 0.5172,
      "step": 61558
    },
    {
      "epoch": 1.8910392283353301,
      "grad_norm": 0.44662708044052124,
      "learning_rate": 1.4664449741914277e-07,
      "loss": 0.4841,
      "step": 61559
    },
    {
      "epoch": 1.8910699474702792,
      "grad_norm": 0.5042985081672668,
      "learning_rate": 1.4656204836677178e-07,
      "loss": 0.4727,
      "step": 61560
    },
    {
      "epoch": 1.8911006666052284,
      "grad_norm": 0.4106137454509735,
      "learning_rate": 1.4647962232779313e-07,
      "loss": 0.5212,
      "step": 61561
    },
    {
      "epoch": 1.8911313857401777,
      "grad_norm": 0.4648773968219757,
      "learning_rate": 1.4639721930239882e-07,
      "loss": 0.5038,
      "step": 61562
    },
    {
      "epoch": 1.8911621048751268,
      "grad_norm": 0.5480676889419556,
      "learning_rate": 1.4631483929078204e-07,
      "loss": 0.459,
      "step": 61563
    },
    {
      "epoch": 1.891192824010076,
      "grad_norm": 0.4628075659275055,
      "learning_rate": 1.4623248229313604e-07,
      "loss": 0.4571,
      "step": 61564
    },
    {
      "epoch": 1.891223543145025,
      "grad_norm": 0.44656404852867126,
      "learning_rate": 1.461501483096517e-07,
      "loss": 0.4807,
      "step": 61565
    },
    {
      "epoch": 1.8912542622799742,
      "grad_norm": 0.41105756163597107,
      "learning_rate": 1.460678373405222e-07,
      "loss": 0.4818,
      "step": 61566
    },
    {
      "epoch": 1.8912849814149233,
      "grad_norm": 0.48999935388565063,
      "learning_rate": 1.4598554938593857e-07,
      "loss": 0.469,
      "step": 61567
    },
    {
      "epoch": 1.8913157005498724,
      "grad_norm": 0.4351530075073242,
      "learning_rate": 1.4590328444609393e-07,
      "loss": 0.4499,
      "step": 61568
    },
    {
      "epoch": 1.8913464196848215,
      "grad_norm": 0.4726009964942932,
      "learning_rate": 1.4582104252118145e-07,
      "loss": 0.4132,
      "step": 61569
    },
    {
      "epoch": 1.8913771388197709,
      "grad_norm": 0.46970033645629883,
      "learning_rate": 1.4573882361139214e-07,
      "loss": 0.4673,
      "step": 61570
    },
    {
      "epoch": 1.89140785795472,
      "grad_norm": 0.45649591088294983,
      "learning_rate": 1.456566277169169e-07,
      "loss": 0.348,
      "step": 61571
    },
    {
      "epoch": 1.8914385770896691,
      "grad_norm": 0.44218888878822327,
      "learning_rate": 1.4557445483794895e-07,
      "loss": 0.4834,
      "step": 61572
    },
    {
      "epoch": 1.8914692962246185,
      "grad_norm": 0.41952016949653625,
      "learning_rate": 1.4549230497468148e-07,
      "loss": 0.4834,
      "step": 61573
    },
    {
      "epoch": 1.8915000153595676,
      "grad_norm": 0.4224584102630615,
      "learning_rate": 1.454101781273043e-07,
      "loss": 0.4511,
      "step": 61574
    },
    {
      "epoch": 1.8915307344945167,
      "grad_norm": 0.4668208956718445,
      "learning_rate": 1.4532807429600947e-07,
      "loss": 0.485,
      "step": 61575
    },
    {
      "epoch": 1.8915614536294658,
      "grad_norm": 0.4446253478527069,
      "learning_rate": 1.4524599348098912e-07,
      "loss": 0.479,
      "step": 61576
    },
    {
      "epoch": 1.891592172764415,
      "grad_norm": 0.40794163942337036,
      "learning_rate": 1.4516393568243525e-07,
      "loss": 0.4696,
      "step": 61577
    },
    {
      "epoch": 1.891622891899364,
      "grad_norm": 0.4371001720428467,
      "learning_rate": 1.4508190090053886e-07,
      "loss": 0.5115,
      "step": 61578
    },
    {
      "epoch": 1.8916536110343132,
      "grad_norm": 0.5138958692550659,
      "learning_rate": 1.44999889135492e-07,
      "loss": 0.4245,
      "step": 61579
    },
    {
      "epoch": 1.8916843301692623,
      "grad_norm": 0.47845813632011414,
      "learning_rate": 1.4491790038748677e-07,
      "loss": 0.4955,
      "step": 61580
    },
    {
      "epoch": 1.8917150493042116,
      "grad_norm": 0.43733882904052734,
      "learning_rate": 1.4483593465671408e-07,
      "loss": 0.4292,
      "step": 61581
    },
    {
      "epoch": 1.8917457684391608,
      "grad_norm": 0.46285945177078247,
      "learning_rate": 1.4475399194336491e-07,
      "loss": 0.4685,
      "step": 61582
    },
    {
      "epoch": 1.8917764875741099,
      "grad_norm": 0.5097998976707458,
      "learning_rate": 1.4467207224763247e-07,
      "loss": 0.4409,
      "step": 61583
    },
    {
      "epoch": 1.8918072067090592,
      "grad_norm": 0.45612862706184387,
      "learning_rate": 1.4459017556970433e-07,
      "loss": 0.4109,
      "step": 61584
    },
    {
      "epoch": 1.8918379258440083,
      "grad_norm": 0.4022168219089508,
      "learning_rate": 1.4450830190977484e-07,
      "loss": 0.5053,
      "step": 61585
    },
    {
      "epoch": 1.8918686449789575,
      "grad_norm": 0.41624894738197327,
      "learning_rate": 1.444264512680349e-07,
      "loss": 0.458,
      "step": 61586
    },
    {
      "epoch": 1.8918993641139066,
      "grad_norm": 0.38594910502433777,
      "learning_rate": 1.443446236446755e-07,
      "loss": 0.4632,
      "step": 61587
    },
    {
      "epoch": 1.8919300832488557,
      "grad_norm": 0.39849233627319336,
      "learning_rate": 1.4426281903988758e-07,
      "loss": 0.4416,
      "step": 61588
    },
    {
      "epoch": 1.8919608023838048,
      "grad_norm": 0.43997618556022644,
      "learning_rate": 1.4418103745386102e-07,
      "loss": 0.4707,
      "step": 61589
    },
    {
      "epoch": 1.891991521518754,
      "grad_norm": 0.44364723563194275,
      "learning_rate": 1.440992788867901e-07,
      "loss": 0.4652,
      "step": 61590
    },
    {
      "epoch": 1.892022240653703,
      "grad_norm": 0.4270321726799011,
      "learning_rate": 1.440175433388613e-07,
      "loss": 0.4709,
      "step": 61591
    },
    {
      "epoch": 1.8920529597886524,
      "grad_norm": 0.46472328901290894,
      "learning_rate": 1.4393583081027007e-07,
      "loss": 0.3956,
      "step": 61592
    },
    {
      "epoch": 1.8920836789236015,
      "grad_norm": 0.4665462076663971,
      "learning_rate": 1.438541413012029e-07,
      "loss": 0.5417,
      "step": 61593
    },
    {
      "epoch": 1.8921143980585506,
      "grad_norm": 0.4257885217666626,
      "learning_rate": 1.4377247481185408e-07,
      "loss": 0.5011,
      "step": 61594
    },
    {
      "epoch": 1.8921451171935,
      "grad_norm": 0.45536813139915466,
      "learning_rate": 1.4369083134241236e-07,
      "loss": 0.5071,
      "step": 61595
    },
    {
      "epoch": 1.892175836328449,
      "grad_norm": 0.7098809480667114,
      "learning_rate": 1.436092108930698e-07,
      "loss": 0.4587,
      "step": 61596
    },
    {
      "epoch": 1.8922065554633982,
      "grad_norm": 0.5367944836616516,
      "learning_rate": 1.4352761346401623e-07,
      "loss": 0.5029,
      "step": 61597
    },
    {
      "epoch": 1.8922372745983473,
      "grad_norm": 0.4171428382396698,
      "learning_rate": 1.4344603905544152e-07,
      "loss": 0.4187,
      "step": 61598
    },
    {
      "epoch": 1.8922679937332965,
      "grad_norm": 0.48663726449012756,
      "learning_rate": 1.4336448766753775e-07,
      "loss": 0.4404,
      "step": 61599
    },
    {
      "epoch": 1.8922987128682456,
      "grad_norm": 0.40796607732772827,
      "learning_rate": 1.4328295930049474e-07,
      "loss": 0.4287,
      "step": 61600
    },
    {
      "epoch": 1.8923294320031947,
      "grad_norm": 0.42030850052833557,
      "learning_rate": 1.4320145395450125e-07,
      "loss": 0.4095,
      "step": 61601
    },
    {
      "epoch": 1.8923601511381438,
      "grad_norm": 0.4370518922805786,
      "learning_rate": 1.4311997162975044e-07,
      "loss": 0.508,
      "step": 61602
    },
    {
      "epoch": 1.8923908702730932,
      "grad_norm": 0.4983176589012146,
      "learning_rate": 1.4303851232643106e-07,
      "loss": 0.4529,
      "step": 61603
    },
    {
      "epoch": 1.8924215894080423,
      "grad_norm": 0.4379975199699402,
      "learning_rate": 1.4295707604473296e-07,
      "loss": 0.5048,
      "step": 61604
    },
    {
      "epoch": 1.8924523085429914,
      "grad_norm": 0.4574381411075592,
      "learning_rate": 1.4287566278484822e-07,
      "loss": 0.3921,
      "step": 61605
    },
    {
      "epoch": 1.8924830276779407,
      "grad_norm": 0.4605497717857361,
      "learning_rate": 1.4279427254696555e-07,
      "loss": 0.5144,
      "step": 61606
    },
    {
      "epoch": 1.8925137468128899,
      "grad_norm": 0.4420303702354431,
      "learning_rate": 1.4271290533127479e-07,
      "loss": 0.4588,
      "step": 61607
    },
    {
      "epoch": 1.892544465947839,
      "grad_norm": 0.4186224639415741,
      "learning_rate": 1.4263156113796584e-07,
      "loss": 0.5563,
      "step": 61608
    },
    {
      "epoch": 1.892575185082788,
      "grad_norm": 0.40307384729385376,
      "learning_rate": 1.4255023996723072e-07,
      "loss": 0.4457,
      "step": 61609
    },
    {
      "epoch": 1.8926059042177372,
      "grad_norm": 0.42869094014167786,
      "learning_rate": 1.4246894181925707e-07,
      "loss": 0.5247,
      "step": 61610
    },
    {
      "epoch": 1.8926366233526863,
      "grad_norm": 0.4502498507499695,
      "learning_rate": 1.4238766669423588e-07,
      "loss": 0.5333,
      "step": 61611
    },
    {
      "epoch": 1.8926673424876355,
      "grad_norm": 0.49143242835998535,
      "learning_rate": 1.4230641459235695e-07,
      "loss": 0.4512,
      "step": 61612
    },
    {
      "epoch": 1.8926980616225846,
      "grad_norm": 0.5142278671264648,
      "learning_rate": 1.4222518551381016e-07,
      "loss": 0.3705,
      "step": 61613
    },
    {
      "epoch": 1.8927287807575337,
      "grad_norm": 0.42762213945388794,
      "learning_rate": 1.421439794587842e-07,
      "loss": 0.5171,
      "step": 61614
    },
    {
      "epoch": 1.892759499892483,
      "grad_norm": 0.4235703647136688,
      "learning_rate": 1.4206279642746901e-07,
      "loss": 0.4011,
      "step": 61615
    },
    {
      "epoch": 1.8927902190274322,
      "grad_norm": 0.4380069673061371,
      "learning_rate": 1.4198163642005548e-07,
      "loss": 0.4833,
      "step": 61616
    },
    {
      "epoch": 1.8928209381623815,
      "grad_norm": 0.43563953042030334,
      "learning_rate": 1.4190049943673234e-07,
      "loss": 0.4527,
      "step": 61617
    },
    {
      "epoch": 1.8928516572973306,
      "grad_norm": 0.4464167356491089,
      "learning_rate": 1.4181938547768836e-07,
      "loss": 0.4692,
      "step": 61618
    },
    {
      "epoch": 1.8928823764322797,
      "grad_norm": 0.4621580243110657,
      "learning_rate": 1.417382945431156e-07,
      "loss": 0.4299,
      "step": 61619
    },
    {
      "epoch": 1.8929130955672289,
      "grad_norm": 0.44080814719200134,
      "learning_rate": 1.4165722663319838e-07,
      "loss": 0.4194,
      "step": 61620
    },
    {
      "epoch": 1.892943814702178,
      "grad_norm": 0.4033730924129486,
      "learning_rate": 1.4157618174813205e-07,
      "loss": 0.4994,
      "step": 61621
    },
    {
      "epoch": 1.892974533837127,
      "grad_norm": 0.48126861453056335,
      "learning_rate": 1.4149515988810203e-07,
      "loss": 0.4319,
      "step": 61622
    },
    {
      "epoch": 1.8930052529720762,
      "grad_norm": 0.4323074221611023,
      "learning_rate": 1.414141610532982e-07,
      "loss": 0.446,
      "step": 61623
    },
    {
      "epoch": 1.8930359721070253,
      "grad_norm": 0.41515058279037476,
      "learning_rate": 1.4133318524391039e-07,
      "loss": 0.4513,
      "step": 61624
    },
    {
      "epoch": 1.8930666912419745,
      "grad_norm": 0.4595741033554077,
      "learning_rate": 1.4125223246012732e-07,
      "loss": 0.4557,
      "step": 61625
    },
    {
      "epoch": 1.8930974103769238,
      "grad_norm": 0.5784299373626709,
      "learning_rate": 1.4117130270213885e-07,
      "loss": 0.4511,
      "step": 61626
    },
    {
      "epoch": 1.893128129511873,
      "grad_norm": 0.4257602095603943,
      "learning_rate": 1.4109039597013262e-07,
      "loss": 0.5101,
      "step": 61627
    },
    {
      "epoch": 1.8931588486468223,
      "grad_norm": 0.4549185633659363,
      "learning_rate": 1.410095122642985e-07,
      "loss": 0.5454,
      "step": 61628
    },
    {
      "epoch": 1.8931895677817714,
      "grad_norm": 0.46180248260498047,
      "learning_rate": 1.4092865158482517e-07,
      "loss": 0.4946,
      "step": 61629
    },
    {
      "epoch": 1.8932202869167205,
      "grad_norm": 0.4492959678173065,
      "learning_rate": 1.408478139319014e-07,
      "loss": 0.4471,
      "step": 61630
    },
    {
      "epoch": 1.8932510060516696,
      "grad_norm": 0.4813990890979767,
      "learning_rate": 1.4076699930571592e-07,
      "loss": 0.562,
      "step": 61631
    },
    {
      "epoch": 1.8932817251866187,
      "grad_norm": 0.5772536993026733,
      "learning_rate": 1.4068620770645857e-07,
      "loss": 0.5473,
      "step": 61632
    },
    {
      "epoch": 1.8933124443215679,
      "grad_norm": 0.4602161645889282,
      "learning_rate": 1.4060543913431702e-07,
      "loss": 0.479,
      "step": 61633
    },
    {
      "epoch": 1.893343163456517,
      "grad_norm": 0.40043333172798157,
      "learning_rate": 1.4052469358947884e-07,
      "loss": 0.5246,
      "step": 61634
    },
    {
      "epoch": 1.893373882591466,
      "grad_norm": 0.413435697555542,
      "learning_rate": 1.4044397107213392e-07,
      "loss": 0.4613,
      "step": 61635
    },
    {
      "epoch": 1.8934046017264152,
      "grad_norm": 0.4965149462223053,
      "learning_rate": 1.4036327158247208e-07,
      "loss": 0.458,
      "step": 61636
    },
    {
      "epoch": 1.8934353208613646,
      "grad_norm": 0.4378814697265625,
      "learning_rate": 1.4028259512067988e-07,
      "loss": 0.5093,
      "step": 61637
    },
    {
      "epoch": 1.8934660399963137,
      "grad_norm": 0.47355589270591736,
      "learning_rate": 1.4020194168694602e-07,
      "loss": 0.5338,
      "step": 61638
    },
    {
      "epoch": 1.893496759131263,
      "grad_norm": 0.40949511528015137,
      "learning_rate": 1.4012131128145923e-07,
      "loss": 0.4499,
      "step": 61639
    },
    {
      "epoch": 1.8935274782662121,
      "grad_norm": 0.4144221246242523,
      "learning_rate": 1.4004070390440716e-07,
      "loss": 0.4499,
      "step": 61640
    },
    {
      "epoch": 1.8935581974011613,
      "grad_norm": 0.4068075716495514,
      "learning_rate": 1.3996011955597967e-07,
      "loss": 0.4601,
      "step": 61641
    },
    {
      "epoch": 1.8935889165361104,
      "grad_norm": 0.4458121061325073,
      "learning_rate": 1.3987955823636324e-07,
      "loss": 0.3707,
      "step": 61642
    },
    {
      "epoch": 1.8936196356710595,
      "grad_norm": 0.4641881585121155,
      "learning_rate": 1.3979901994574663e-07,
      "loss": 0.4117,
      "step": 61643
    },
    {
      "epoch": 1.8936503548060086,
      "grad_norm": 0.5300292372703552,
      "learning_rate": 1.397185046843186e-07,
      "loss": 0.4824,
      "step": 61644
    },
    {
      "epoch": 1.8936810739409577,
      "grad_norm": 0.4488784968852997,
      "learning_rate": 1.3963801245226672e-07,
      "loss": 0.5356,
      "step": 61645
    },
    {
      "epoch": 1.8937117930759069,
      "grad_norm": 0.4609004259109497,
      "learning_rate": 1.3955754324977866e-07,
      "loss": 0.4117,
      "step": 61646
    },
    {
      "epoch": 1.893742512210856,
      "grad_norm": 0.4033026099205017,
      "learning_rate": 1.3947709707704205e-07,
      "loss": 0.4755,
      "step": 61647
    },
    {
      "epoch": 1.8937732313458053,
      "grad_norm": 0.44830378890037537,
      "learning_rate": 1.393966739342456e-07,
      "loss": 0.5215,
      "step": 61648
    },
    {
      "epoch": 1.8938039504807544,
      "grad_norm": 0.5232926607131958,
      "learning_rate": 1.3931627382157697e-07,
      "loss": 0.5301,
      "step": 61649
    },
    {
      "epoch": 1.8938346696157036,
      "grad_norm": 0.4216578006744385,
      "learning_rate": 1.3923589673922377e-07,
      "loss": 0.3855,
      "step": 61650
    },
    {
      "epoch": 1.893865388750653,
      "grad_norm": 0.45536041259765625,
      "learning_rate": 1.3915554268737474e-07,
      "loss": 0.5287,
      "step": 61651
    },
    {
      "epoch": 1.893896107885602,
      "grad_norm": 0.4384450614452362,
      "learning_rate": 1.390752116662153e-07,
      "loss": 0.5461,
      "step": 61652
    },
    {
      "epoch": 1.8939268270205512,
      "grad_norm": 0.4962829053401947,
      "learning_rate": 1.3899490367593526e-07,
      "loss": 0.5256,
      "step": 61653
    },
    {
      "epoch": 1.8939575461555003,
      "grad_norm": 0.4175441265106201,
      "learning_rate": 1.3891461871672118e-07,
      "loss": 0.5148,
      "step": 61654
    },
    {
      "epoch": 1.8939882652904494,
      "grad_norm": 0.4522056579589844,
      "learning_rate": 1.3883435678876066e-07,
      "loss": 0.4802,
      "step": 61655
    },
    {
      "epoch": 1.8940189844253985,
      "grad_norm": 0.460534006357193,
      "learning_rate": 1.3875411789224026e-07,
      "loss": 0.5323,
      "step": 61656
    },
    {
      "epoch": 1.8940497035603476,
      "grad_norm": 0.4629725515842438,
      "learning_rate": 1.3867390202734977e-07,
      "loss": 0.4301,
      "step": 61657
    },
    {
      "epoch": 1.8940804226952968,
      "grad_norm": 0.43619590997695923,
      "learning_rate": 1.385937091942735e-07,
      "loss": 0.5497,
      "step": 61658
    },
    {
      "epoch": 1.894111141830246,
      "grad_norm": 0.4202077090740204,
      "learning_rate": 1.3851353939320134e-07,
      "loss": 0.4248,
      "step": 61659
    },
    {
      "epoch": 1.8941418609651952,
      "grad_norm": 0.3791644275188446,
      "learning_rate": 1.3843339262431977e-07,
      "loss": 0.4227,
      "step": 61660
    },
    {
      "epoch": 1.8941725801001443,
      "grad_norm": 0.40876007080078125,
      "learning_rate": 1.3835326888781418e-07,
      "loss": 0.4151,
      "step": 61661
    },
    {
      "epoch": 1.8942032992350937,
      "grad_norm": 0.4740234613418579,
      "learning_rate": 1.382731681838756e-07,
      "loss": 0.4708,
      "step": 61662
    },
    {
      "epoch": 1.8942340183700428,
      "grad_norm": 0.43913376331329346,
      "learning_rate": 1.3819309051268713e-07,
      "loss": 0.4277,
      "step": 61663
    },
    {
      "epoch": 1.894264737504992,
      "grad_norm": 0.41902270913124084,
      "learning_rate": 1.381130358744387e-07,
      "loss": 0.3895,
      "step": 61664
    },
    {
      "epoch": 1.894295456639941,
      "grad_norm": 0.4824303984642029,
      "learning_rate": 1.3803300426931454e-07,
      "loss": 0.451,
      "step": 61665
    },
    {
      "epoch": 1.8943261757748902,
      "grad_norm": 0.46422380208969116,
      "learning_rate": 1.3795299569750453e-07,
      "loss": 0.4147,
      "step": 61666
    },
    {
      "epoch": 1.8943568949098393,
      "grad_norm": 0.4189479351043701,
      "learning_rate": 1.3787301015919298e-07,
      "loss": 0.452,
      "step": 61667
    },
    {
      "epoch": 1.8943876140447884,
      "grad_norm": 0.4291486144065857,
      "learning_rate": 1.3779304765456857e-07,
      "loss": 0.4851,
      "step": 61668
    },
    {
      "epoch": 1.8944183331797375,
      "grad_norm": 0.402243435382843,
      "learning_rate": 1.3771310818381677e-07,
      "loss": 0.487,
      "step": 61669
    },
    {
      "epoch": 1.8944490523146869,
      "grad_norm": 0.4460454285144806,
      "learning_rate": 1.376331917471241e-07,
      "loss": 0.5096,
      "step": 61670
    },
    {
      "epoch": 1.894479771449636,
      "grad_norm": 0.4373074173927307,
      "learning_rate": 1.3755329834467812e-07,
      "loss": 0.4531,
      "step": 61671
    },
    {
      "epoch": 1.894510490584585,
      "grad_norm": 0.46529048681259155,
      "learning_rate": 1.374734279766665e-07,
      "loss": 0.5749,
      "step": 61672
    },
    {
      "epoch": 1.8945412097195344,
      "grad_norm": 0.44280049204826355,
      "learning_rate": 1.3739358064327356e-07,
      "loss": 0.4359,
      "step": 61673
    },
    {
      "epoch": 1.8945719288544836,
      "grad_norm": 0.4109160602092743,
      "learning_rate": 1.373137563446869e-07,
      "loss": 0.3911,
      "step": 61674
    },
    {
      "epoch": 1.8946026479894327,
      "grad_norm": 0.43414875864982605,
      "learning_rate": 1.3723395508109194e-07,
      "loss": 0.3746,
      "step": 61675
    },
    {
      "epoch": 1.8946333671243818,
      "grad_norm": 0.4260944128036499,
      "learning_rate": 1.371541768526774e-07,
      "loss": 0.4566,
      "step": 61676
    },
    {
      "epoch": 1.894664086259331,
      "grad_norm": 0.4102727174758911,
      "learning_rate": 1.370744216596276e-07,
      "loss": 0.4188,
      "step": 61677
    },
    {
      "epoch": 1.89469480539428,
      "grad_norm": 0.4392511248588562,
      "learning_rate": 1.369946895021279e-07,
      "loss": 0.4519,
      "step": 61678
    },
    {
      "epoch": 1.8947255245292292,
      "grad_norm": 0.4326174855232239,
      "learning_rate": 1.369149803803671e-07,
      "loss": 0.3583,
      "step": 61679
    },
    {
      "epoch": 1.8947562436641783,
      "grad_norm": 0.3965235650539398,
      "learning_rate": 1.3683529429453056e-07,
      "loss": 0.4501,
      "step": 61680
    },
    {
      "epoch": 1.8947869627991276,
      "grad_norm": 0.4307365417480469,
      "learning_rate": 1.3675563124480374e-07,
      "loss": 0.5013,
      "step": 61681
    },
    {
      "epoch": 1.8948176819340767,
      "grad_norm": 0.45631206035614014,
      "learning_rate": 1.366759912313731e-07,
      "loss": 0.4294,
      "step": 61682
    },
    {
      "epoch": 1.8948484010690259,
      "grad_norm": 0.44507890939712524,
      "learning_rate": 1.3659637425442407e-07,
      "loss": 0.4739,
      "step": 61683
    },
    {
      "epoch": 1.8948791202039752,
      "grad_norm": 0.4724271297454834,
      "learning_rate": 1.3651678031414207e-07,
      "loss": 0.4183,
      "step": 61684
    },
    {
      "epoch": 1.8949098393389243,
      "grad_norm": 0.43959954380989075,
      "learning_rate": 1.364372094107158e-07,
      "loss": 0.4819,
      "step": 61685
    },
    {
      "epoch": 1.8949405584738734,
      "grad_norm": 0.4317823052406311,
      "learning_rate": 1.363576615443285e-07,
      "loss": 0.481,
      "step": 61686
    },
    {
      "epoch": 1.8949712776088226,
      "grad_norm": 0.40422433614730835,
      "learning_rate": 1.3627813671516777e-07,
      "loss": 0.4459,
      "step": 61687
    },
    {
      "epoch": 1.8950019967437717,
      "grad_norm": 0.5194060802459717,
      "learning_rate": 1.3619863492341677e-07,
      "loss": 0.4905,
      "step": 61688
    },
    {
      "epoch": 1.8950327158787208,
      "grad_norm": 0.4424927532672882,
      "learning_rate": 1.361191561692643e-07,
      "loss": 0.5025,
      "step": 61689
    },
    {
      "epoch": 1.89506343501367,
      "grad_norm": 0.4361560344696045,
      "learning_rate": 1.3603970045289239e-07,
      "loss": 0.386,
      "step": 61690
    },
    {
      "epoch": 1.895094154148619,
      "grad_norm": 0.44478705525398254,
      "learning_rate": 1.359602677744909e-07,
      "loss": 0.5372,
      "step": 61691
    },
    {
      "epoch": 1.8951248732835684,
      "grad_norm": 0.45630428194999695,
      "learning_rate": 1.3588085813424078e-07,
      "loss": 0.4397,
      "step": 61692
    },
    {
      "epoch": 1.8951555924185175,
      "grad_norm": 0.4116915464401245,
      "learning_rate": 1.358014715323319e-07,
      "loss": 0.3883,
      "step": 61693
    },
    {
      "epoch": 1.8951863115534666,
      "grad_norm": 0.4238027036190033,
      "learning_rate": 1.3572210796894637e-07,
      "loss": 0.409,
      "step": 61694
    },
    {
      "epoch": 1.895217030688416,
      "grad_norm": 0.4664378762245178,
      "learning_rate": 1.3564276744427063e-07,
      "loss": 0.3818,
      "step": 61695
    },
    {
      "epoch": 1.895247749823365,
      "grad_norm": 0.535110592842102,
      "learning_rate": 1.3556344995849126e-07,
      "loss": 0.4927,
      "step": 61696
    },
    {
      "epoch": 1.8952784689583142,
      "grad_norm": 0.4273921549320221,
      "learning_rate": 1.354841555117914e-07,
      "loss": 0.5116,
      "step": 61697
    },
    {
      "epoch": 1.8953091880932633,
      "grad_norm": 0.4356381297111511,
      "learning_rate": 1.354048841043576e-07,
      "loss": 0.4929,
      "step": 61698
    },
    {
      "epoch": 1.8953399072282124,
      "grad_norm": 0.4154351055622101,
      "learning_rate": 1.3532563573637524e-07,
      "loss": 0.4677,
      "step": 61699
    },
    {
      "epoch": 1.8953706263631616,
      "grad_norm": 0.46562322974205017,
      "learning_rate": 1.3524641040802866e-07,
      "loss": 0.5103,
      "step": 61700
    },
    {
      "epoch": 1.8954013454981107,
      "grad_norm": 0.42377594113349915,
      "learning_rate": 1.3516720811950213e-07,
      "loss": 0.4712,
      "step": 61701
    },
    {
      "epoch": 1.8954320646330598,
      "grad_norm": 0.40073761343955994,
      "learning_rate": 1.3508802887098216e-07,
      "loss": 0.5076,
      "step": 61702
    },
    {
      "epoch": 1.8954627837680091,
      "grad_norm": 0.4752880930900574,
      "learning_rate": 1.3500887266265195e-07,
      "loss": 0.4948,
      "step": 61703
    },
    {
      "epoch": 1.8954935029029583,
      "grad_norm": 0.4311973750591278,
      "learning_rate": 1.3492973949469912e-07,
      "loss": 0.4352,
      "step": 61704
    },
    {
      "epoch": 1.8955242220379074,
      "grad_norm": 0.3966630697250366,
      "learning_rate": 1.3485062936730575e-07,
      "loss": 0.4703,
      "step": 61705
    },
    {
      "epoch": 1.8955549411728567,
      "grad_norm": 0.45402926206588745,
      "learning_rate": 1.3477154228065838e-07,
      "loss": 0.411,
      "step": 61706
    },
    {
      "epoch": 1.8955856603078058,
      "grad_norm": 0.4542921185493469,
      "learning_rate": 1.3469247823494014e-07,
      "loss": 0.4955,
      "step": 61707
    },
    {
      "epoch": 1.895616379442755,
      "grad_norm": 0.4350830018520355,
      "learning_rate": 1.346134372303376e-07,
      "loss": 0.3957,
      "step": 61708
    },
    {
      "epoch": 1.895647098577704,
      "grad_norm": 0.5682440996170044,
      "learning_rate": 1.3453441926703393e-07,
      "loss": 0.4474,
      "step": 61709
    },
    {
      "epoch": 1.8956778177126532,
      "grad_norm": 0.4337849020957947,
      "learning_rate": 1.3445542434521452e-07,
      "loss": 0.4073,
      "step": 61710
    },
    {
      "epoch": 1.8957085368476023,
      "grad_norm": 0.447918564081192,
      "learning_rate": 1.343764524650626e-07,
      "loss": 0.4025,
      "step": 61711
    },
    {
      "epoch": 1.8957392559825514,
      "grad_norm": 0.42524635791778564,
      "learning_rate": 1.3429750362676462e-07,
      "loss": 0.4463,
      "step": 61712
    },
    {
      "epoch": 1.8957699751175006,
      "grad_norm": 0.41476473212242126,
      "learning_rate": 1.3421857783050275e-07,
      "loss": 0.498,
      "step": 61713
    },
    {
      "epoch": 1.89580069425245,
      "grad_norm": 0.4687741994857788,
      "learning_rate": 1.341396750764634e-07,
      "loss": 0.4735,
      "step": 61714
    },
    {
      "epoch": 1.895831413387399,
      "grad_norm": 0.5976665019989014,
      "learning_rate": 1.3406079536482873e-07,
      "loss": 0.454,
      "step": 61715
    },
    {
      "epoch": 1.8958621325223481,
      "grad_norm": 0.4005158245563507,
      "learning_rate": 1.3398193869578413e-07,
      "loss": 0.4553,
      "step": 61716
    },
    {
      "epoch": 1.8958928516572975,
      "grad_norm": 0.4795230031013489,
      "learning_rate": 1.3390310506951498e-07,
      "loss": 0.3648,
      "step": 61717
    },
    {
      "epoch": 1.8959235707922466,
      "grad_norm": 0.44401881098747253,
      "learning_rate": 1.3382429448620337e-07,
      "loss": 0.3856,
      "step": 61718
    },
    {
      "epoch": 1.8959542899271957,
      "grad_norm": 0.6577856540679932,
      "learning_rate": 1.337455069460347e-07,
      "loss": 0.5247,
      "step": 61719
    },
    {
      "epoch": 1.8959850090621448,
      "grad_norm": 0.46410346031188965,
      "learning_rate": 1.336667424491911e-07,
      "loss": 0.5072,
      "step": 61720
    },
    {
      "epoch": 1.896015728197094,
      "grad_norm": 0.44153961539268494,
      "learning_rate": 1.3358800099586012e-07,
      "loss": 0.4959,
      "step": 61721
    },
    {
      "epoch": 1.896046447332043,
      "grad_norm": 0.42403456568717957,
      "learning_rate": 1.3350928258622165e-07,
      "loss": 0.4303,
      "step": 61722
    },
    {
      "epoch": 1.8960771664669922,
      "grad_norm": 0.42709648609161377,
      "learning_rate": 1.334305872204622e-07,
      "loss": 0.5432,
      "step": 61723
    },
    {
      "epoch": 1.8961078856019413,
      "grad_norm": 0.47847992181777954,
      "learning_rate": 1.3335191489876386e-07,
      "loss": 0.5403,
      "step": 61724
    },
    {
      "epoch": 1.8961386047368904,
      "grad_norm": 0.4067022204399109,
      "learning_rate": 1.3327326562131205e-07,
      "loss": 0.481,
      "step": 61725
    },
    {
      "epoch": 1.8961693238718398,
      "grad_norm": 0.42009100317955017,
      "learning_rate": 1.331946393882888e-07,
      "loss": 0.4258,
      "step": 61726
    },
    {
      "epoch": 1.896200043006789,
      "grad_norm": 0.43076804280281067,
      "learning_rate": 1.3311603619987956e-07,
      "loss": 0.4443,
      "step": 61727
    },
    {
      "epoch": 1.8962307621417382,
      "grad_norm": 0.4491199851036072,
      "learning_rate": 1.330374560562664e-07,
      "loss": 0.3929,
      "step": 61728
    },
    {
      "epoch": 1.8962614812766874,
      "grad_norm": 0.4062380790710449,
      "learning_rate": 1.3295889895763247e-07,
      "loss": 0.4901,
      "step": 61729
    },
    {
      "epoch": 1.8962922004116365,
      "grad_norm": 0.44244688749313354,
      "learning_rate": 1.3288036490416323e-07,
      "loss": 0.5123,
      "step": 61730
    },
    {
      "epoch": 1.8963229195465856,
      "grad_norm": 0.4273548722267151,
      "learning_rate": 1.3280185389604073e-07,
      "loss": 0.4254,
      "step": 61731
    },
    {
      "epoch": 1.8963536386815347,
      "grad_norm": 0.40939953923225403,
      "learning_rate": 1.3272336593344925e-07,
      "loss": 0.4897,
      "step": 61732
    },
    {
      "epoch": 1.8963843578164838,
      "grad_norm": 0.48081499338150024,
      "learning_rate": 1.3264490101656978e-07,
      "loss": 0.4741,
      "step": 61733
    },
    {
      "epoch": 1.896415076951433,
      "grad_norm": 0.4163458049297333,
      "learning_rate": 1.3256645914558886e-07,
      "loss": 0.4264,
      "step": 61734
    },
    {
      "epoch": 1.896445796086382,
      "grad_norm": 0.4653889238834381,
      "learning_rate": 1.3248804032068742e-07,
      "loss": 0.4342,
      "step": 61735
    },
    {
      "epoch": 1.8964765152213312,
      "grad_norm": 0.49268949031829834,
      "learning_rate": 1.3240964454204975e-07,
      "loss": 0.4964,
      "step": 61736
    },
    {
      "epoch": 1.8965072343562805,
      "grad_norm": 0.4559687376022339,
      "learning_rate": 1.3233127180985794e-07,
      "loss": 0.4902,
      "step": 61737
    },
    {
      "epoch": 1.8965379534912297,
      "grad_norm": 0.5029765963554382,
      "learning_rate": 1.322529221242952e-07,
      "loss": 0.4141,
      "step": 61738
    },
    {
      "epoch": 1.896568672626179,
      "grad_norm": 0.41693371534347534,
      "learning_rate": 1.321745954855458e-07,
      "loss": 0.4208,
      "step": 61739
    },
    {
      "epoch": 1.8965993917611281,
      "grad_norm": 0.44489070773124695,
      "learning_rate": 1.320962918937918e-07,
      "loss": 0.4496,
      "step": 61740
    },
    {
      "epoch": 1.8966301108960772,
      "grad_norm": 0.4583417475223541,
      "learning_rate": 1.3201801134921644e-07,
      "loss": 0.4542,
      "step": 61741
    },
    {
      "epoch": 1.8966608300310264,
      "grad_norm": 0.4529293477535248,
      "learning_rate": 1.3193975385200064e-07,
      "loss": 0.4485,
      "step": 61742
    },
    {
      "epoch": 1.8966915491659755,
      "grad_norm": 0.4685768187046051,
      "learning_rate": 1.3186151940232982e-07,
      "loss": 0.4858,
      "step": 61743
    },
    {
      "epoch": 1.8967222683009246,
      "grad_norm": 0.4503045678138733,
      "learning_rate": 1.3178330800038608e-07,
      "loss": 0.4534,
      "step": 61744
    },
    {
      "epoch": 1.8967529874358737,
      "grad_norm": 0.41563454270362854,
      "learning_rate": 1.3170511964635036e-07,
      "loss": 0.4691,
      "step": 61745
    },
    {
      "epoch": 1.8967837065708228,
      "grad_norm": 0.43892791867256165,
      "learning_rate": 1.3162695434040696e-07,
      "loss": 0.4286,
      "step": 61746
    },
    {
      "epoch": 1.896814425705772,
      "grad_norm": 0.41244882345199585,
      "learning_rate": 1.3154881208273796e-07,
      "loss": 0.4335,
      "step": 61747
    },
    {
      "epoch": 1.8968451448407213,
      "grad_norm": 0.44717374444007874,
      "learning_rate": 1.3147069287352654e-07,
      "loss": 0.491,
      "step": 61748
    },
    {
      "epoch": 1.8968758639756704,
      "grad_norm": 0.5009432435035706,
      "learning_rate": 1.3139259671295479e-07,
      "loss": 0.4879,
      "step": 61749
    },
    {
      "epoch": 1.8969065831106198,
      "grad_norm": 0.44409313797950745,
      "learning_rate": 1.3131452360120368e-07,
      "loss": 0.525,
      "step": 61750
    },
    {
      "epoch": 1.896937302245569,
      "grad_norm": 0.46482232213020325,
      "learning_rate": 1.312364735384575e-07,
      "loss": 0.4842,
      "step": 61751
    },
    {
      "epoch": 1.896968021380518,
      "grad_norm": 0.4571365416049957,
      "learning_rate": 1.3115844652489718e-07,
      "loss": 0.5043,
      "step": 61752
    },
    {
      "epoch": 1.8969987405154671,
      "grad_norm": 0.5360676050186157,
      "learning_rate": 1.3108044256070595e-07,
      "loss": 0.4679,
      "step": 61753
    },
    {
      "epoch": 1.8970294596504162,
      "grad_norm": 0.4331693649291992,
      "learning_rate": 1.3100246164606589e-07,
      "loss": 0.4413,
      "step": 61754
    },
    {
      "epoch": 1.8970601787853654,
      "grad_norm": 0.4350683391094208,
      "learning_rate": 1.3092450378115796e-07,
      "loss": 0.4369,
      "step": 61755
    },
    {
      "epoch": 1.8970908979203145,
      "grad_norm": 0.4656606614589691,
      "learning_rate": 1.3084656896616533e-07,
      "loss": 0.4854,
      "step": 61756
    },
    {
      "epoch": 1.8971216170552636,
      "grad_norm": 0.42770951986312866,
      "learning_rate": 1.307686572012701e-07,
      "loss": 0.47,
      "step": 61757
    },
    {
      "epoch": 1.8971523361902127,
      "grad_norm": 0.40054428577423096,
      "learning_rate": 1.306907684866543e-07,
      "loss": 0.4868,
      "step": 61758
    },
    {
      "epoch": 1.897183055325162,
      "grad_norm": 0.49114978313446045,
      "learning_rate": 1.3061290282249895e-07,
      "loss": 0.4985,
      "step": 61759
    },
    {
      "epoch": 1.8972137744601112,
      "grad_norm": 0.4092002213001251,
      "learning_rate": 1.3053506020898609e-07,
      "loss": 0.4321,
      "step": 61760
    },
    {
      "epoch": 1.8972444935950603,
      "grad_norm": 0.4642737805843353,
      "learning_rate": 1.3045724064629894e-07,
      "loss": 0.4664,
      "step": 61761
    },
    {
      "epoch": 1.8972752127300097,
      "grad_norm": 0.41560930013656616,
      "learning_rate": 1.3037944413461733e-07,
      "loss": 0.4713,
      "step": 61762
    },
    {
      "epoch": 1.8973059318649588,
      "grad_norm": 0.42516428232192993,
      "learning_rate": 1.3030167067412448e-07,
      "loss": 0.4681,
      "step": 61763
    },
    {
      "epoch": 1.897336650999908,
      "grad_norm": 0.46305787563323975,
      "learning_rate": 1.3022392026500131e-07,
      "loss": 0.488,
      "step": 61764
    },
    {
      "epoch": 1.897367370134857,
      "grad_norm": 0.449052095413208,
      "learning_rate": 1.301461929074288e-07,
      "loss": 0.5246,
      "step": 61765
    },
    {
      "epoch": 1.8973980892698061,
      "grad_norm": 0.4012870788574219,
      "learning_rate": 1.3006848860158905e-07,
      "loss": 0.4667,
      "step": 61766
    },
    {
      "epoch": 1.8974288084047553,
      "grad_norm": 0.44176551699638367,
      "learning_rate": 1.2999080734766412e-07,
      "loss": 0.4782,
      "step": 61767
    },
    {
      "epoch": 1.8974595275397044,
      "grad_norm": 0.42200106382369995,
      "learning_rate": 1.2991314914583498e-07,
      "loss": 0.4237,
      "step": 61768
    },
    {
      "epoch": 1.8974902466746535,
      "grad_norm": 0.46246325969696045,
      "learning_rate": 1.298355139962826e-07,
      "loss": 0.4763,
      "step": 61769
    },
    {
      "epoch": 1.8975209658096028,
      "grad_norm": 0.456389456987381,
      "learning_rate": 1.2975790189918903e-07,
      "loss": 0.5274,
      "step": 61770
    },
    {
      "epoch": 1.897551684944552,
      "grad_norm": 0.38982900977134705,
      "learning_rate": 1.2968031285473526e-07,
      "loss": 0.4369,
      "step": 61771
    },
    {
      "epoch": 1.897582404079501,
      "grad_norm": 0.42320162057876587,
      "learning_rate": 1.2960274686310225e-07,
      "loss": 0.5072,
      "step": 61772
    },
    {
      "epoch": 1.8976131232144504,
      "grad_norm": 0.4206508994102478,
      "learning_rate": 1.295252039244721e-07,
      "loss": 0.5532,
      "step": 61773
    },
    {
      "epoch": 1.8976438423493995,
      "grad_norm": 0.395788311958313,
      "learning_rate": 1.2944768403902352e-07,
      "loss": 0.4561,
      "step": 61774
    },
    {
      "epoch": 1.8976745614843487,
      "grad_norm": 0.4309179484844208,
      "learning_rate": 1.2937018720694083e-07,
      "loss": 0.491,
      "step": 61775
    },
    {
      "epoch": 1.8977052806192978,
      "grad_norm": 0.4688039720058441,
      "learning_rate": 1.2929271342840278e-07,
      "loss": 0.5166,
      "step": 61776
    },
    {
      "epoch": 1.897735999754247,
      "grad_norm": 0.38755300641059875,
      "learning_rate": 1.2921526270359142e-07,
      "loss": 0.4494,
      "step": 61777
    },
    {
      "epoch": 1.897766718889196,
      "grad_norm": 0.42835336923599243,
      "learning_rate": 1.2913783503268662e-07,
      "loss": 0.4897,
      "step": 61778
    },
    {
      "epoch": 1.8977974380241451,
      "grad_norm": 0.4647965133190155,
      "learning_rate": 1.2906043041586934e-07,
      "loss": 0.4449,
      "step": 61779
    },
    {
      "epoch": 1.8978281571590943,
      "grad_norm": 0.38770583271980286,
      "learning_rate": 1.289830488533228e-07,
      "loss": 0.4702,
      "step": 61780
    },
    {
      "epoch": 1.8978588762940436,
      "grad_norm": 0.46457430720329285,
      "learning_rate": 1.289056903452235e-07,
      "loss": 0.4375,
      "step": 61781
    },
    {
      "epoch": 1.8978895954289927,
      "grad_norm": 0.4520809054374695,
      "learning_rate": 1.288283548917557e-07,
      "loss": 0.4854,
      "step": 61782
    },
    {
      "epoch": 1.8979203145639418,
      "grad_norm": 0.40045198798179626,
      "learning_rate": 1.2875104249309822e-07,
      "loss": 0.5051,
      "step": 61783
    },
    {
      "epoch": 1.8979510336988912,
      "grad_norm": 0.40721964836120605,
      "learning_rate": 1.2867375314943197e-07,
      "loss": 0.4579,
      "step": 61784
    },
    {
      "epoch": 1.8979817528338403,
      "grad_norm": 0.40892794728279114,
      "learning_rate": 1.2859648686093796e-07,
      "loss": 0.5174,
      "step": 61785
    },
    {
      "epoch": 1.8980124719687894,
      "grad_norm": 0.4610646963119507,
      "learning_rate": 1.28519243627796e-07,
      "loss": 0.4807,
      "step": 61786
    },
    {
      "epoch": 1.8980431911037385,
      "grad_norm": 0.4310711920261383,
      "learning_rate": 1.2844202345018598e-07,
      "loss": 0.5401,
      "step": 61787
    },
    {
      "epoch": 1.8980739102386877,
      "grad_norm": 0.4226568639278412,
      "learning_rate": 1.2836482632828996e-07,
      "loss": 0.436,
      "step": 61788
    },
    {
      "epoch": 1.8981046293736368,
      "grad_norm": 0.3928222954273224,
      "learning_rate": 1.2828765226228777e-07,
      "loss": 0.4789,
      "step": 61789
    },
    {
      "epoch": 1.898135348508586,
      "grad_norm": 0.46900248527526855,
      "learning_rate": 1.2821050125235825e-07,
      "loss": 0.4853,
      "step": 61790
    },
    {
      "epoch": 1.898166067643535,
      "grad_norm": 0.4246240258216858,
      "learning_rate": 1.2813337329868335e-07,
      "loss": 0.5312,
      "step": 61791
    },
    {
      "epoch": 1.8981967867784844,
      "grad_norm": 0.5018989443778992,
      "learning_rate": 1.2805626840144082e-07,
      "loss": 0.5519,
      "step": 61792
    },
    {
      "epoch": 1.8982275059134335,
      "grad_norm": 0.43788376450538635,
      "learning_rate": 1.2797918656081376e-07,
      "loss": 0.4689,
      "step": 61793
    },
    {
      "epoch": 1.8982582250483826,
      "grad_norm": 0.5903836488723755,
      "learning_rate": 1.2790212777698095e-07,
      "loss": 0.5119,
      "step": 61794
    },
    {
      "epoch": 1.898288944183332,
      "grad_norm": 0.4328358769416809,
      "learning_rate": 1.2782509205012229e-07,
      "loss": 0.4779,
      "step": 61795
    },
    {
      "epoch": 1.898319663318281,
      "grad_norm": 0.49555280804634094,
      "learning_rate": 1.2774807938041534e-07,
      "loss": 0.509,
      "step": 61796
    },
    {
      "epoch": 1.8983503824532302,
      "grad_norm": 0.5156749486923218,
      "learning_rate": 1.2767108976804444e-07,
      "loss": 0.443,
      "step": 61797
    },
    {
      "epoch": 1.8983811015881793,
      "grad_norm": 0.39655768871307373,
      "learning_rate": 1.275941232131872e-07,
      "loss": 0.3543,
      "step": 61798
    },
    {
      "epoch": 1.8984118207231284,
      "grad_norm": 0.4080919623374939,
      "learning_rate": 1.275171797160224e-07,
      "loss": 0.481,
      "step": 61799
    },
    {
      "epoch": 1.8984425398580775,
      "grad_norm": 0.4247058629989624,
      "learning_rate": 1.2744025927673098e-07,
      "loss": 0.4594,
      "step": 61800
    },
    {
      "epoch": 1.8984732589930267,
      "grad_norm": 0.44341614842414856,
      "learning_rate": 1.273633618954928e-07,
      "loss": 0.5131,
      "step": 61801
    },
    {
      "epoch": 1.8985039781279758,
      "grad_norm": 0.41289544105529785,
      "learning_rate": 1.2728648757248663e-07,
      "loss": 0.4334,
      "step": 61802
    },
    {
      "epoch": 1.8985346972629251,
      "grad_norm": 0.45968198776245117,
      "learning_rate": 1.2720963630789228e-07,
      "loss": 0.5105,
      "step": 61803
    },
    {
      "epoch": 1.8985654163978742,
      "grad_norm": 0.437013179063797,
      "learning_rate": 1.2713280810188967e-07,
      "loss": 0.5261,
      "step": 61804
    },
    {
      "epoch": 1.8985961355328234,
      "grad_norm": 0.41253548860549927,
      "learning_rate": 1.2705600295465749e-07,
      "loss": 0.4483,
      "step": 61805
    },
    {
      "epoch": 1.8986268546677727,
      "grad_norm": 0.4694863259792328,
      "learning_rate": 1.269792208663756e-07,
      "loss": 0.4739,
      "step": 61806
    },
    {
      "epoch": 1.8986575738027218,
      "grad_norm": 0.4188879430294037,
      "learning_rate": 1.2690246183722276e-07,
      "loss": 0.3871,
      "step": 61807
    },
    {
      "epoch": 1.898688292937671,
      "grad_norm": 0.4066280424594879,
      "learning_rate": 1.2682572586737996e-07,
      "loss": 0.4527,
      "step": 61808
    },
    {
      "epoch": 1.89871901207262,
      "grad_norm": 0.4688494801521301,
      "learning_rate": 1.267490129570248e-07,
      "loss": 0.5403,
      "step": 61809
    },
    {
      "epoch": 1.8987497312075692,
      "grad_norm": 0.40294769406318665,
      "learning_rate": 1.2667232310633603e-07,
      "loss": 0.4652,
      "step": 61810
    },
    {
      "epoch": 1.8987804503425183,
      "grad_norm": 0.47952908277511597,
      "learning_rate": 1.2659565631549354e-07,
      "loss": 0.5603,
      "step": 61811
    },
    {
      "epoch": 1.8988111694774674,
      "grad_norm": 0.3999086320400238,
      "learning_rate": 1.2651901258467824e-07,
      "loss": 0.4488,
      "step": 61812
    },
    {
      "epoch": 1.8988418886124165,
      "grad_norm": 0.4092491567134857,
      "learning_rate": 1.264423919140656e-07,
      "loss": 0.4964,
      "step": 61813
    },
    {
      "epoch": 1.8988726077473659,
      "grad_norm": 0.48107871413230896,
      "learning_rate": 1.2636579430383654e-07,
      "loss": 0.4646,
      "step": 61814
    },
    {
      "epoch": 1.898903326882315,
      "grad_norm": 0.45213213562965393,
      "learning_rate": 1.2628921975416987e-07,
      "loss": 0.4638,
      "step": 61815
    },
    {
      "epoch": 1.8989340460172641,
      "grad_norm": 0.45615339279174805,
      "learning_rate": 1.2621266826524536e-07,
      "loss": 0.4684,
      "step": 61816
    },
    {
      "epoch": 1.8989647651522135,
      "grad_norm": 0.5035644173622131,
      "learning_rate": 1.261361398372396e-07,
      "loss": 0.4655,
      "step": 61817
    },
    {
      "epoch": 1.8989954842871626,
      "grad_norm": 0.40882137417793274,
      "learning_rate": 1.2605963447033355e-07,
      "loss": 0.4446,
      "step": 61818
    },
    {
      "epoch": 1.8990262034221117,
      "grad_norm": 0.4702025353908539,
      "learning_rate": 1.259831521647037e-07,
      "loss": 0.5111,
      "step": 61819
    },
    {
      "epoch": 1.8990569225570608,
      "grad_norm": 0.437883585691452,
      "learning_rate": 1.2590669292052993e-07,
      "loss": 0.5065,
      "step": 61820
    },
    {
      "epoch": 1.89908764169201,
      "grad_norm": 0.4115159809589386,
      "learning_rate": 1.25830256737991e-07,
      "loss": 0.4815,
      "step": 61821
    },
    {
      "epoch": 1.899118360826959,
      "grad_norm": 0.418614000082016,
      "learning_rate": 1.2575384361726561e-07,
      "loss": 0.4562,
      "step": 61822
    },
    {
      "epoch": 1.8991490799619082,
      "grad_norm": 0.4870103597640991,
      "learning_rate": 1.2567745355853035e-07,
      "loss": 0.4611,
      "step": 61823
    },
    {
      "epoch": 1.8991797990968573,
      "grad_norm": 0.42011600732803345,
      "learning_rate": 1.2560108656196613e-07,
      "loss": 0.4097,
      "step": 61824
    },
    {
      "epoch": 1.8992105182318066,
      "grad_norm": 0.4373413324356079,
      "learning_rate": 1.255247426277495e-07,
      "loss": 0.4899,
      "step": 61825
    },
    {
      "epoch": 1.8992412373667558,
      "grad_norm": 0.44761180877685547,
      "learning_rate": 1.254484217560603e-07,
      "loss": 0.5255,
      "step": 61826
    },
    {
      "epoch": 1.8992719565017049,
      "grad_norm": 0.4392174780368805,
      "learning_rate": 1.253721239470751e-07,
      "loss": 0.4703,
      "step": 61827
    },
    {
      "epoch": 1.8993026756366542,
      "grad_norm": 0.38275060057640076,
      "learning_rate": 1.252958492009726e-07,
      "loss": 0.4289,
      "step": 61828
    },
    {
      "epoch": 1.8993333947716033,
      "grad_norm": 0.5206407308578491,
      "learning_rate": 1.2521959751793267e-07,
      "loss": 0.4111,
      "step": 61829
    },
    {
      "epoch": 1.8993641139065525,
      "grad_norm": 0.44397401809692383,
      "learning_rate": 1.2514336889813183e-07,
      "loss": 0.4767,
      "step": 61830
    },
    {
      "epoch": 1.8993948330415016,
      "grad_norm": 0.463431715965271,
      "learning_rate": 1.2506716334174772e-07,
      "loss": 0.4679,
      "step": 61831
    },
    {
      "epoch": 1.8994255521764507,
      "grad_norm": 0.4815164804458618,
      "learning_rate": 1.2499098084895912e-07,
      "loss": 0.4558,
      "step": 61832
    },
    {
      "epoch": 1.8994562713113998,
      "grad_norm": 0.4235896170139313,
      "learning_rate": 1.249148214199436e-07,
      "loss": 0.506,
      "step": 61833
    },
    {
      "epoch": 1.899486990446349,
      "grad_norm": 0.43428412079811096,
      "learning_rate": 1.2483868505487883e-07,
      "loss": 0.4364,
      "step": 61834
    },
    {
      "epoch": 1.899517709581298,
      "grad_norm": 0.562034547328949,
      "learning_rate": 1.2476257175394357e-07,
      "loss": 0.4316,
      "step": 61835
    },
    {
      "epoch": 1.8995484287162474,
      "grad_norm": 0.3883175551891327,
      "learning_rate": 1.2468648151731434e-07,
      "loss": 0.451,
      "step": 61836
    },
    {
      "epoch": 1.8995791478511965,
      "grad_norm": 0.45842310786247253,
      "learning_rate": 1.2461041434516984e-07,
      "loss": 0.449,
      "step": 61837
    },
    {
      "epoch": 1.8996098669861456,
      "grad_norm": 0.4121232330799103,
      "learning_rate": 1.2453437023768778e-07,
      "loss": 0.4925,
      "step": 61838
    },
    {
      "epoch": 1.899640586121095,
      "grad_norm": 0.41670677065849304,
      "learning_rate": 1.2445834919504573e-07,
      "loss": 0.4301,
      "step": 61839
    },
    {
      "epoch": 1.899671305256044,
      "grad_norm": 0.44285860657691956,
      "learning_rate": 1.2438235121742027e-07,
      "loss": 0.4933,
      "step": 61840
    },
    {
      "epoch": 1.8997020243909932,
      "grad_norm": 0.42752575874328613,
      "learning_rate": 1.2430637630498897e-07,
      "loss": 0.4655,
      "step": 61841
    },
    {
      "epoch": 1.8997327435259423,
      "grad_norm": 0.4469328820705414,
      "learning_rate": 1.2423042445793065e-07,
      "loss": 0.48,
      "step": 61842
    },
    {
      "epoch": 1.8997634626608915,
      "grad_norm": 0.44724950194358826,
      "learning_rate": 1.2415449567642178e-07,
      "loss": 0.494,
      "step": 61843
    },
    {
      "epoch": 1.8997941817958406,
      "grad_norm": 0.4834648370742798,
      "learning_rate": 1.2407858996064005e-07,
      "loss": 0.4633,
      "step": 61844
    },
    {
      "epoch": 1.8998249009307897,
      "grad_norm": 0.4782050848007202,
      "learning_rate": 1.240027073107619e-07,
      "loss": 0.4274,
      "step": 61845
    },
    {
      "epoch": 1.8998556200657388,
      "grad_norm": 0.40052422881126404,
      "learning_rate": 1.2392684772696507e-07,
      "loss": 0.4735,
      "step": 61846
    },
    {
      "epoch": 1.899886339200688,
      "grad_norm": 0.4227531850337982,
      "learning_rate": 1.238510112094271e-07,
      "loss": 0.4713,
      "step": 61847
    },
    {
      "epoch": 1.8999170583356373,
      "grad_norm": 0.4785710275173187,
      "learning_rate": 1.2377519775832568e-07,
      "loss": 0.4394,
      "step": 61848
    },
    {
      "epoch": 1.8999477774705864,
      "grad_norm": 0.47500666975975037,
      "learning_rate": 1.2369940737383624e-07,
      "loss": 0.5125,
      "step": 61849
    },
    {
      "epoch": 1.8999784966055357,
      "grad_norm": 0.3916859030723572,
      "learning_rate": 1.2362364005613635e-07,
      "loss": 0.4633,
      "step": 61850
    },
    {
      "epoch": 1.9000092157404849,
      "grad_norm": 0.4406896233558655,
      "learning_rate": 1.235478958054026e-07,
      "loss": 0.4699,
      "step": 61851
    },
    {
      "epoch": 1.900039934875434,
      "grad_norm": 0.42226698994636536,
      "learning_rate": 1.2347217462181372e-07,
      "loss": 0.5292,
      "step": 61852
    },
    {
      "epoch": 1.900070654010383,
      "grad_norm": 0.5277888774871826,
      "learning_rate": 1.2339647650554508e-07,
      "loss": 0.3967,
      "step": 61853
    },
    {
      "epoch": 1.9001013731453322,
      "grad_norm": 0.4260005056858063,
      "learning_rate": 1.233208014567744e-07,
      "loss": 0.4589,
      "step": 61854
    },
    {
      "epoch": 1.9001320922802813,
      "grad_norm": 0.41629648208618164,
      "learning_rate": 1.232451494756759e-07,
      "loss": 0.4512,
      "step": 61855
    },
    {
      "epoch": 1.9001628114152305,
      "grad_norm": 0.4564366638660431,
      "learning_rate": 1.2316952056242947e-07,
      "loss": 0.4393,
      "step": 61856
    },
    {
      "epoch": 1.9001935305501796,
      "grad_norm": 0.4454345107078552,
      "learning_rate": 1.2309391471721055e-07,
      "loss": 0.4231,
      "step": 61857
    },
    {
      "epoch": 1.9002242496851287,
      "grad_norm": 0.3809453248977661,
      "learning_rate": 1.2301833194019565e-07,
      "loss": 0.4576,
      "step": 61858
    },
    {
      "epoch": 1.900254968820078,
      "grad_norm": 0.4234020411968231,
      "learning_rate": 1.2294277223156016e-07,
      "loss": 0.4335,
      "step": 61859
    },
    {
      "epoch": 1.9002856879550272,
      "grad_norm": 0.4731449484825134,
      "learning_rate": 1.2286723559148172e-07,
      "loss": 0.4618,
      "step": 61860
    },
    {
      "epoch": 1.9003164070899765,
      "grad_norm": 0.4223416745662689,
      "learning_rate": 1.22791722020138e-07,
      "loss": 0.4914,
      "step": 61861
    },
    {
      "epoch": 1.9003471262249256,
      "grad_norm": 0.4201814830303192,
      "learning_rate": 1.227162315177033e-07,
      "loss": 0.5137,
      "step": 61862
    },
    {
      "epoch": 1.9003778453598748,
      "grad_norm": 0.4844517111778259,
      "learning_rate": 1.226407640843552e-07,
      "loss": 0.4737,
      "step": 61863
    },
    {
      "epoch": 1.9004085644948239,
      "grad_norm": 0.4348222017288208,
      "learning_rate": 1.225653197202681e-07,
      "loss": 0.4762,
      "step": 61864
    },
    {
      "epoch": 1.900439283629773,
      "grad_norm": 0.41935452818870544,
      "learning_rate": 1.2248989842562064e-07,
      "loss": 0.5149,
      "step": 61865
    },
    {
      "epoch": 1.900470002764722,
      "grad_norm": 0.4592129588127136,
      "learning_rate": 1.224145002005872e-07,
      "loss": 0.4881,
      "step": 61866
    },
    {
      "epoch": 1.9005007218996712,
      "grad_norm": 0.4153771996498108,
      "learning_rate": 1.223391250453454e-07,
      "loss": 0.4733,
      "step": 61867
    },
    {
      "epoch": 1.9005314410346204,
      "grad_norm": 0.44075891375541687,
      "learning_rate": 1.2226377296006953e-07,
      "loss": 0.4437,
      "step": 61868
    },
    {
      "epoch": 1.9005621601695695,
      "grad_norm": 0.46071144938468933,
      "learning_rate": 1.2218844394493722e-07,
      "loss": 0.4839,
      "step": 61869
    },
    {
      "epoch": 1.9005928793045188,
      "grad_norm": 0.5074625015258789,
      "learning_rate": 1.2211313800012282e-07,
      "loss": 0.4032,
      "step": 61870
    },
    {
      "epoch": 1.900623598439468,
      "grad_norm": 0.44852200150489807,
      "learning_rate": 1.220378551258039e-07,
      "loss": 0.4762,
      "step": 61871
    },
    {
      "epoch": 1.900654317574417,
      "grad_norm": 0.5383162498474121,
      "learning_rate": 1.2196259532215483e-07,
      "loss": 0.4913,
      "step": 61872
    },
    {
      "epoch": 1.9006850367093664,
      "grad_norm": 0.4068204164505005,
      "learning_rate": 1.218873585893521e-07,
      "loss": 0.5616,
      "step": 61873
    },
    {
      "epoch": 1.9007157558443155,
      "grad_norm": 0.40965673327445984,
      "learning_rate": 1.218121449275711e-07,
      "loss": 0.4056,
      "step": 61874
    },
    {
      "epoch": 1.9007464749792646,
      "grad_norm": 0.47785794734954834,
      "learning_rate": 1.217369543369884e-07,
      "loss": 0.4485,
      "step": 61875
    },
    {
      "epoch": 1.9007771941142138,
      "grad_norm": 0.4524458348751068,
      "learning_rate": 1.216617868177783e-07,
      "loss": 0.429,
      "step": 61876
    },
    {
      "epoch": 1.9008079132491629,
      "grad_norm": 0.43446674942970276,
      "learning_rate": 1.215866423701173e-07,
      "loss": 0.4816,
      "step": 61877
    },
    {
      "epoch": 1.900838632384112,
      "grad_norm": 0.4654087722301483,
      "learning_rate": 1.2151152099418085e-07,
      "loss": 0.5473,
      "step": 61878
    },
    {
      "epoch": 1.9008693515190611,
      "grad_norm": 0.47190752625465393,
      "learning_rate": 1.2143642269014323e-07,
      "loss": 0.4705,
      "step": 61879
    },
    {
      "epoch": 1.9009000706540102,
      "grad_norm": 0.42391717433929443,
      "learning_rate": 1.2136134745818208e-07,
      "loss": 0.5229,
      "step": 61880
    },
    {
      "epoch": 1.9009307897889596,
      "grad_norm": 0.5240417122840881,
      "learning_rate": 1.212862952984706e-07,
      "loss": 0.4596,
      "step": 61881
    },
    {
      "epoch": 1.9009615089239087,
      "grad_norm": 0.38994914293289185,
      "learning_rate": 1.2121126621118418e-07,
      "loss": 0.4525,
      "step": 61882
    },
    {
      "epoch": 1.9009922280588578,
      "grad_norm": 0.46149206161499023,
      "learning_rate": 1.2113626019649939e-07,
      "loss": 0.49,
      "step": 61883
    },
    {
      "epoch": 1.9010229471938072,
      "grad_norm": 0.4299949109554291,
      "learning_rate": 1.210612772545916e-07,
      "loss": 0.4938,
      "step": 61884
    },
    {
      "epoch": 1.9010536663287563,
      "grad_norm": 0.45626622438430786,
      "learning_rate": 1.2098631738563516e-07,
      "loss": 0.4514,
      "step": 61885
    },
    {
      "epoch": 1.9010843854637054,
      "grad_norm": 0.4215274751186371,
      "learning_rate": 1.2091138058980433e-07,
      "loss": 0.5145,
      "step": 61886
    },
    {
      "epoch": 1.9011151045986545,
      "grad_norm": 0.4292607605457306,
      "learning_rate": 1.2083646686727458e-07,
      "loss": 0.3974,
      "step": 61887
    },
    {
      "epoch": 1.9011458237336036,
      "grad_norm": 0.40274474024772644,
      "learning_rate": 1.2076157621822237e-07,
      "loss": 0.4561,
      "step": 61888
    },
    {
      "epoch": 1.9011765428685528,
      "grad_norm": 0.3984246850013733,
      "learning_rate": 1.2068670864281984e-07,
      "loss": 0.4398,
      "step": 61889
    },
    {
      "epoch": 1.9012072620035019,
      "grad_norm": 0.44568201899528503,
      "learning_rate": 1.206118641412457e-07,
      "loss": 0.5267,
      "step": 61890
    },
    {
      "epoch": 1.901237981138451,
      "grad_norm": 0.4243233799934387,
      "learning_rate": 1.2053704271366984e-07,
      "loss": 0.4205,
      "step": 61891
    },
    {
      "epoch": 1.9012687002734003,
      "grad_norm": 0.5019974708557129,
      "learning_rate": 1.204622443602721e-07,
      "loss": 0.4636,
      "step": 61892
    },
    {
      "epoch": 1.9012994194083495,
      "grad_norm": 0.46903231739997864,
      "learning_rate": 1.2038746908122346e-07,
      "loss": 0.4328,
      "step": 61893
    },
    {
      "epoch": 1.9013301385432986,
      "grad_norm": 0.6100965738296509,
      "learning_rate": 1.2031271687670044e-07,
      "loss": 0.4408,
      "step": 61894
    },
    {
      "epoch": 1.901360857678248,
      "grad_norm": 0.4203674793243408,
      "learning_rate": 1.2023798774687734e-07,
      "loss": 0.451,
      "step": 61895
    },
    {
      "epoch": 1.901391576813197,
      "grad_norm": 0.42618417739868164,
      "learning_rate": 1.2016328169192626e-07,
      "loss": 0.5661,
      "step": 61896
    },
    {
      "epoch": 1.9014222959481462,
      "grad_norm": 0.4345971345901489,
      "learning_rate": 1.2008859871202594e-07,
      "loss": 0.4455,
      "step": 61897
    },
    {
      "epoch": 1.9014530150830953,
      "grad_norm": 0.483125239610672,
      "learning_rate": 1.2001393880734847e-07,
      "loss": 0.5571,
      "step": 61898
    },
    {
      "epoch": 1.9014837342180444,
      "grad_norm": 0.415760338306427,
      "learning_rate": 1.1993930197806813e-07,
      "loss": 0.5052,
      "step": 61899
    },
    {
      "epoch": 1.9015144533529935,
      "grad_norm": 0.42375698685646057,
      "learning_rate": 1.1986468822435926e-07,
      "loss": 0.4703,
      "step": 61900
    },
    {
      "epoch": 1.9015451724879426,
      "grad_norm": 0.41618818044662476,
      "learning_rate": 1.1979009754639726e-07,
      "loss": 0.4025,
      "step": 61901
    },
    {
      "epoch": 1.9015758916228918,
      "grad_norm": 0.43029263615608215,
      "learning_rate": 1.197155299443553e-07,
      "loss": 0.5107,
      "step": 61902
    },
    {
      "epoch": 1.901606610757841,
      "grad_norm": 0.4228690266609192,
      "learning_rate": 1.1964098541840773e-07,
      "loss": 0.4573,
      "step": 61903
    },
    {
      "epoch": 1.9016373298927902,
      "grad_norm": 0.45522740483283997,
      "learning_rate": 1.1956646396872772e-07,
      "loss": 0.4066,
      "step": 61904
    },
    {
      "epoch": 1.9016680490277393,
      "grad_norm": 0.4576018154621124,
      "learning_rate": 1.194919655954918e-07,
      "loss": 0.5001,
      "step": 61905
    },
    {
      "epoch": 1.9016987681626887,
      "grad_norm": 0.45669177174568176,
      "learning_rate": 1.1941749029887096e-07,
      "loss": 0.3946,
      "step": 61906
    },
    {
      "epoch": 1.9017294872976378,
      "grad_norm": 0.4375050365924835,
      "learning_rate": 1.193430380790417e-07,
      "loss": 0.4672,
      "step": 61907
    },
    {
      "epoch": 1.901760206432587,
      "grad_norm": 0.4565633237361908,
      "learning_rate": 1.1926860893617609e-07,
      "loss": 0.4656,
      "step": 61908
    },
    {
      "epoch": 1.901790925567536,
      "grad_norm": 0.46274465322494507,
      "learning_rate": 1.1919420287044958e-07,
      "loss": 0.5718,
      "step": 61909
    },
    {
      "epoch": 1.9018216447024852,
      "grad_norm": 0.45714375376701355,
      "learning_rate": 1.1911981988203424e-07,
      "loss": 0.5307,
      "step": 61910
    },
    {
      "epoch": 1.9018523638374343,
      "grad_norm": 0.5229929089546204,
      "learning_rate": 1.190454599711055e-07,
      "loss": 0.4535,
      "step": 61911
    },
    {
      "epoch": 1.9018830829723834,
      "grad_norm": 0.4380948841571808,
      "learning_rate": 1.1897112313783543e-07,
      "loss": 0.4805,
      "step": 61912
    },
    {
      "epoch": 1.9019138021073325,
      "grad_norm": 0.42243286967277527,
      "learning_rate": 1.1889680938239834e-07,
      "loss": 0.4886,
      "step": 61913
    },
    {
      "epoch": 1.9019445212422819,
      "grad_norm": 0.43880170583724976,
      "learning_rate": 1.1882251870496742e-07,
      "loss": 0.3831,
      "step": 61914
    },
    {
      "epoch": 1.901975240377231,
      "grad_norm": 0.46512460708618164,
      "learning_rate": 1.1874825110571697e-07,
      "loss": 0.4933,
      "step": 61915
    },
    {
      "epoch": 1.90200595951218,
      "grad_norm": 0.4345819056034088,
      "learning_rate": 1.1867400658482132e-07,
      "loss": 0.4244,
      "step": 61916
    },
    {
      "epoch": 1.9020366786471294,
      "grad_norm": 0.4378412961959839,
      "learning_rate": 1.1859978514245141e-07,
      "loss": 0.5047,
      "step": 61917
    },
    {
      "epoch": 1.9020673977820786,
      "grad_norm": 0.4704839587211609,
      "learning_rate": 1.1852558677878157e-07,
      "loss": 0.4124,
      "step": 61918
    },
    {
      "epoch": 1.9020981169170277,
      "grad_norm": 0.4420153498649597,
      "learning_rate": 1.184514114939861e-07,
      "loss": 0.4344,
      "step": 61919
    },
    {
      "epoch": 1.9021288360519768,
      "grad_norm": 0.43796858191490173,
      "learning_rate": 1.1837725928823818e-07,
      "loss": 0.4381,
      "step": 61920
    },
    {
      "epoch": 1.902159555186926,
      "grad_norm": 0.4283815622329712,
      "learning_rate": 1.183031301617088e-07,
      "loss": 0.5083,
      "step": 61921
    },
    {
      "epoch": 1.902190274321875,
      "grad_norm": 0.4049251079559326,
      "learning_rate": 1.1822902411457338e-07,
      "loss": 0.4836,
      "step": 61922
    },
    {
      "epoch": 1.9022209934568242,
      "grad_norm": 0.4419615864753723,
      "learning_rate": 1.1815494114700287e-07,
      "loss": 0.4922,
      "step": 61923
    },
    {
      "epoch": 1.9022517125917733,
      "grad_norm": 0.45975562930107117,
      "learning_rate": 1.1808088125917383e-07,
      "loss": 0.4811,
      "step": 61924
    },
    {
      "epoch": 1.9022824317267226,
      "grad_norm": 0.44348347187042236,
      "learning_rate": 1.180068444512561e-07,
      "loss": 0.5375,
      "step": 61925
    },
    {
      "epoch": 1.9023131508616717,
      "grad_norm": 0.4001089334487915,
      "learning_rate": 1.1793283072342288e-07,
      "loss": 0.4146,
      "step": 61926
    },
    {
      "epoch": 1.9023438699966209,
      "grad_norm": 0.46205827593803406,
      "learning_rate": 1.1785884007584735e-07,
      "loss": 0.4068,
      "step": 61927
    },
    {
      "epoch": 1.9023745891315702,
      "grad_norm": 0.39564773440361023,
      "learning_rate": 1.1778487250870496e-07,
      "loss": 0.4466,
      "step": 61928
    },
    {
      "epoch": 1.9024053082665193,
      "grad_norm": 0.41505199670791626,
      "learning_rate": 1.1771092802216443e-07,
      "loss": 0.4335,
      "step": 61929
    },
    {
      "epoch": 1.9024360274014684,
      "grad_norm": 0.45717573165893555,
      "learning_rate": 1.176370066164001e-07,
      "loss": 0.5449,
      "step": 61930
    },
    {
      "epoch": 1.9024667465364176,
      "grad_norm": 0.4312426447868347,
      "learning_rate": 1.1756310829158512e-07,
      "loss": 0.4808,
      "step": 61931
    },
    {
      "epoch": 1.9024974656713667,
      "grad_norm": 0.4061364531517029,
      "learning_rate": 1.174892330478905e-07,
      "loss": 0.517,
      "step": 61932
    },
    {
      "epoch": 1.9025281848063158,
      "grad_norm": 0.4599815607070923,
      "learning_rate": 1.1741538088549164e-07,
      "loss": 0.4626,
      "step": 61933
    },
    {
      "epoch": 1.902558903941265,
      "grad_norm": 0.4508973956108093,
      "learning_rate": 1.1734155180455953e-07,
      "loss": 0.5437,
      "step": 61934
    },
    {
      "epoch": 1.902589623076214,
      "grad_norm": 0.44624340534210205,
      "learning_rate": 1.1726774580526623e-07,
      "loss": 0.4344,
      "step": 61935
    },
    {
      "epoch": 1.9026203422111634,
      "grad_norm": 0.452549546957016,
      "learning_rate": 1.1719396288778273e-07,
      "loss": 0.4804,
      "step": 61936
    },
    {
      "epoch": 1.9026510613461125,
      "grad_norm": 0.4225439727306366,
      "learning_rate": 1.1712020305228445e-07,
      "loss": 0.3662,
      "step": 61937
    },
    {
      "epoch": 1.9026817804810616,
      "grad_norm": 0.457394540309906,
      "learning_rate": 1.1704646629894123e-07,
      "loss": 0.4142,
      "step": 61938
    },
    {
      "epoch": 1.902712499616011,
      "grad_norm": 0.4241340160369873,
      "learning_rate": 1.169727526279274e-07,
      "loss": 0.4391,
      "step": 61939
    },
    {
      "epoch": 1.90274321875096,
      "grad_norm": 0.5021514296531677,
      "learning_rate": 1.1689906203941282e-07,
      "loss": 0.5171,
      "step": 61940
    },
    {
      "epoch": 1.9027739378859092,
      "grad_norm": 0.4840952157974243,
      "learning_rate": 1.1682539453357067e-07,
      "loss": 0.4472,
      "step": 61941
    },
    {
      "epoch": 1.9028046570208583,
      "grad_norm": 0.4405142664909363,
      "learning_rate": 1.1675175011057416e-07,
      "loss": 0.4698,
      "step": 61942
    },
    {
      "epoch": 1.9028353761558074,
      "grad_norm": 0.44821885228157043,
      "learning_rate": 1.1667812877059314e-07,
      "loss": 0.4438,
      "step": 61943
    },
    {
      "epoch": 1.9028660952907566,
      "grad_norm": 0.42494380474090576,
      "learning_rate": 1.1660453051380084e-07,
      "loss": 0.4883,
      "step": 61944
    },
    {
      "epoch": 1.9028968144257057,
      "grad_norm": 0.4322633147239685,
      "learning_rate": 1.1653095534036929e-07,
      "loss": 0.4336,
      "step": 61945
    },
    {
      "epoch": 1.9029275335606548,
      "grad_norm": 0.4285099506378174,
      "learning_rate": 1.164574032504695e-07,
      "loss": 0.4527,
      "step": 61946
    },
    {
      "epoch": 1.9029582526956041,
      "grad_norm": 0.5141552686691284,
      "learning_rate": 1.1638387424427355e-07,
      "loss": 0.4286,
      "step": 61947
    },
    {
      "epoch": 1.9029889718305533,
      "grad_norm": 0.5025249719619751,
      "learning_rate": 1.1631036832195353e-07,
      "loss": 0.4878,
      "step": 61948
    },
    {
      "epoch": 1.9030196909655024,
      "grad_norm": 0.48483696579933167,
      "learning_rate": 1.162368854836815e-07,
      "loss": 0.519,
      "step": 61949
    },
    {
      "epoch": 1.9030504101004517,
      "grad_norm": 0.4759399890899658,
      "learning_rate": 1.1616342572962735e-07,
      "loss": 0.4527,
      "step": 61950
    },
    {
      "epoch": 1.9030811292354008,
      "grad_norm": 0.5116550922393799,
      "learning_rate": 1.1608998905996427e-07,
      "loss": 0.4098,
      "step": 61951
    },
    {
      "epoch": 1.90311184837035,
      "grad_norm": 0.4565922021865845,
      "learning_rate": 1.1601657547486433e-07,
      "loss": 0.4743,
      "step": 61952
    },
    {
      "epoch": 1.903142567505299,
      "grad_norm": 0.45740634202957153,
      "learning_rate": 1.1594318497449742e-07,
      "loss": 0.4905,
      "step": 61953
    },
    {
      "epoch": 1.9031732866402482,
      "grad_norm": 0.43385255336761475,
      "learning_rate": 1.1586981755903448e-07,
      "loss": 0.3953,
      "step": 61954
    },
    {
      "epoch": 1.9032040057751973,
      "grad_norm": 0.4197779595851898,
      "learning_rate": 1.1579647322864873e-07,
      "loss": 0.4424,
      "step": 61955
    },
    {
      "epoch": 1.9032347249101464,
      "grad_norm": 0.4193058907985687,
      "learning_rate": 1.1572315198351115e-07,
      "loss": 0.4503,
      "step": 61956
    },
    {
      "epoch": 1.9032654440450956,
      "grad_norm": 0.4371742606163025,
      "learning_rate": 1.1564985382379157e-07,
      "loss": 0.4613,
      "step": 61957
    },
    {
      "epoch": 1.9032961631800447,
      "grad_norm": 0.4218437969684601,
      "learning_rate": 1.1557657874966211e-07,
      "loss": 0.3908,
      "step": 61958
    },
    {
      "epoch": 1.903326882314994,
      "grad_norm": 0.44173529744148254,
      "learning_rate": 1.1550332676129372e-07,
      "loss": 0.4823,
      "step": 61959
    },
    {
      "epoch": 1.9033576014499431,
      "grad_norm": 0.3989729881286621,
      "learning_rate": 1.154300978588585e-07,
      "loss": 0.4759,
      "step": 61960
    },
    {
      "epoch": 1.9033883205848925,
      "grad_norm": 0.4706062078475952,
      "learning_rate": 1.1535689204252632e-07,
      "loss": 0.5404,
      "step": 61961
    },
    {
      "epoch": 1.9034190397198416,
      "grad_norm": 0.4219238758087158,
      "learning_rate": 1.1528370931246813e-07,
      "loss": 0.4358,
      "step": 61962
    },
    {
      "epoch": 1.9034497588547907,
      "grad_norm": 0.47088751196861267,
      "learning_rate": 1.1521054966885492e-07,
      "loss": 0.5584,
      "step": 61963
    },
    {
      "epoch": 1.9034804779897398,
      "grad_norm": 0.3743639290332794,
      "learning_rate": 1.1513741311185877e-07,
      "loss": 0.4196,
      "step": 61964
    },
    {
      "epoch": 1.903511197124689,
      "grad_norm": 0.42526352405548096,
      "learning_rate": 1.1506429964164845e-07,
      "loss": 0.5172,
      "step": 61965
    },
    {
      "epoch": 1.903541916259638,
      "grad_norm": 0.4492810368537903,
      "learning_rate": 1.1499120925839713e-07,
      "loss": 0.533,
      "step": 61966
    },
    {
      "epoch": 1.9035726353945872,
      "grad_norm": 0.41965627670288086,
      "learning_rate": 1.1491814196227247e-07,
      "loss": 0.4333,
      "step": 61967
    },
    {
      "epoch": 1.9036033545295363,
      "grad_norm": 0.4355705678462982,
      "learning_rate": 1.1484509775344765e-07,
      "loss": 0.4567,
      "step": 61968
    },
    {
      "epoch": 1.9036340736644854,
      "grad_norm": 0.4397873282432556,
      "learning_rate": 1.1477207663209255e-07,
      "loss": 0.4294,
      "step": 61969
    },
    {
      "epoch": 1.9036647927994348,
      "grad_norm": 0.41883742809295654,
      "learning_rate": 1.1469907859837815e-07,
      "loss": 0.482,
      "step": 61970
    },
    {
      "epoch": 1.903695511934384,
      "grad_norm": 0.44155439734458923,
      "learning_rate": 1.1462610365247428e-07,
      "loss": 0.4148,
      "step": 61971
    },
    {
      "epoch": 1.9037262310693333,
      "grad_norm": 0.3931553363800049,
      "learning_rate": 1.1455315179455084e-07,
      "loss": 0.511,
      "step": 61972
    },
    {
      "epoch": 1.9037569502042824,
      "grad_norm": 0.424844354391098,
      "learning_rate": 1.1448022302477879e-07,
      "loss": 0.4553,
      "step": 61973
    },
    {
      "epoch": 1.9037876693392315,
      "grad_norm": 0.40649494528770447,
      "learning_rate": 1.1440731734332911e-07,
      "loss": 0.4758,
      "step": 61974
    },
    {
      "epoch": 1.9038183884741806,
      "grad_norm": 0.48556581139564514,
      "learning_rate": 1.1433443475037165e-07,
      "loss": 0.4472,
      "step": 61975
    },
    {
      "epoch": 1.9038491076091297,
      "grad_norm": 0.43424293398857117,
      "learning_rate": 1.1426157524607628e-07,
      "loss": 0.519,
      "step": 61976
    },
    {
      "epoch": 1.9038798267440789,
      "grad_norm": 0.4152316153049469,
      "learning_rate": 1.1418873883061399e-07,
      "loss": 0.4762,
      "step": 61977
    },
    {
      "epoch": 1.903910545879028,
      "grad_norm": 0.438623309135437,
      "learning_rate": 1.1411592550415351e-07,
      "loss": 0.5231,
      "step": 61978
    },
    {
      "epoch": 1.903941265013977,
      "grad_norm": 0.43502572178840637,
      "learning_rate": 1.1404313526686694e-07,
      "loss": 0.4876,
      "step": 61979
    },
    {
      "epoch": 1.9039719841489262,
      "grad_norm": 0.4129347503185272,
      "learning_rate": 1.1397036811892192e-07,
      "loss": 0.3884,
      "step": 61980
    },
    {
      "epoch": 1.9040027032838756,
      "grad_norm": 0.44004538655281067,
      "learning_rate": 1.1389762406048943e-07,
      "loss": 0.4368,
      "step": 61981
    },
    {
      "epoch": 1.9040334224188247,
      "grad_norm": 0.6984859108924866,
      "learning_rate": 1.1382490309173933e-07,
      "loss": 0.3591,
      "step": 61982
    },
    {
      "epoch": 1.9040641415537738,
      "grad_norm": 0.44996732473373413,
      "learning_rate": 1.1375220521284259e-07,
      "loss": 0.4732,
      "step": 61983
    },
    {
      "epoch": 1.9040948606887231,
      "grad_norm": 0.39619171619415283,
      "learning_rate": 1.1367953042396795e-07,
      "loss": 0.5068,
      "step": 61984
    },
    {
      "epoch": 1.9041255798236723,
      "grad_norm": 0.38240480422973633,
      "learning_rate": 1.136068787252842e-07,
      "loss": 0.3542,
      "step": 61985
    },
    {
      "epoch": 1.9041562989586214,
      "grad_norm": 0.453853964805603,
      "learning_rate": 1.1353425011696229e-07,
      "loss": 0.4576,
      "step": 61986
    },
    {
      "epoch": 1.9041870180935705,
      "grad_norm": 0.4321092963218689,
      "learning_rate": 1.1346164459917208e-07,
      "loss": 0.4492,
      "step": 61987
    },
    {
      "epoch": 1.9042177372285196,
      "grad_norm": 0.41789087653160095,
      "learning_rate": 1.1338906217208345e-07,
      "loss": 0.4965,
      "step": 61988
    },
    {
      "epoch": 1.9042484563634687,
      "grad_norm": 0.43945568799972534,
      "learning_rate": 1.1331650283586404e-07,
      "loss": 0.4319,
      "step": 61989
    },
    {
      "epoch": 1.9042791754984179,
      "grad_norm": 0.44546565413475037,
      "learning_rate": 1.1324396659068371e-07,
      "loss": 0.4696,
      "step": 61990
    },
    {
      "epoch": 1.904309894633367,
      "grad_norm": 0.44300979375839233,
      "learning_rate": 1.1317145343671344e-07,
      "loss": 0.4721,
      "step": 61991
    },
    {
      "epoch": 1.9043406137683163,
      "grad_norm": 0.44886454939842224,
      "learning_rate": 1.1309896337412196e-07,
      "loss": 0.4776,
      "step": 61992
    },
    {
      "epoch": 1.9043713329032654,
      "grad_norm": 0.46325892210006714,
      "learning_rate": 1.1302649640307805e-07,
      "loss": 0.4569,
      "step": 61993
    },
    {
      "epoch": 1.9044020520382146,
      "grad_norm": 0.4564737379550934,
      "learning_rate": 1.129540525237527e-07,
      "loss": 0.4623,
      "step": 61994
    },
    {
      "epoch": 1.904432771173164,
      "grad_norm": 0.42354249954223633,
      "learning_rate": 1.1288163173631128e-07,
      "loss": 0.4901,
      "step": 61995
    },
    {
      "epoch": 1.904463490308113,
      "grad_norm": 0.4668218493461609,
      "learning_rate": 1.1280923404092703e-07,
      "loss": 0.4764,
      "step": 61996
    },
    {
      "epoch": 1.9044942094430621,
      "grad_norm": 0.40255969762802124,
      "learning_rate": 1.1273685943776647e-07,
      "loss": 0.4251,
      "step": 61997
    },
    {
      "epoch": 1.9045249285780113,
      "grad_norm": 0.4088747203350067,
      "learning_rate": 1.1266450792699946e-07,
      "loss": 0.436,
      "step": 61998
    },
    {
      "epoch": 1.9045556477129604,
      "grad_norm": 0.43170231580734253,
      "learning_rate": 1.1259217950879586e-07,
      "loss": 0.447,
      "step": 61999
    },
    {
      "epoch": 1.9045863668479095,
      "grad_norm": 0.4203755259513855,
      "learning_rate": 1.1251987418332221e-07,
      "loss": 0.4859,
      "step": 62000
    },
    {
      "epoch": 1.9046170859828586,
      "grad_norm": 0.48850348591804504,
      "learning_rate": 1.124475919507495e-07,
      "loss": 0.4751,
      "step": 62001
    },
    {
      "epoch": 1.9046478051178077,
      "grad_norm": 0.4488283097743988,
      "learning_rate": 1.1237533281124758e-07,
      "loss": 0.4923,
      "step": 62002
    },
    {
      "epoch": 1.904678524252757,
      "grad_norm": 0.45564284920692444,
      "learning_rate": 1.1230309676498186e-07,
      "loss": 0.5297,
      "step": 62003
    },
    {
      "epoch": 1.9047092433877062,
      "grad_norm": 0.46263936161994934,
      "learning_rate": 1.1223088381212332e-07,
      "loss": 0.4307,
      "step": 62004
    },
    {
      "epoch": 1.9047399625226553,
      "grad_norm": 0.42293962836265564,
      "learning_rate": 1.1215869395283962e-07,
      "loss": 0.5203,
      "step": 62005
    },
    {
      "epoch": 1.9047706816576047,
      "grad_norm": 0.4610603153705597,
      "learning_rate": 1.1208652718730062e-07,
      "loss": 0.4674,
      "step": 62006
    },
    {
      "epoch": 1.9048014007925538,
      "grad_norm": 0.4399944245815277,
      "learning_rate": 1.1201438351567395e-07,
      "loss": 0.4218,
      "step": 62007
    },
    {
      "epoch": 1.904832119927503,
      "grad_norm": 0.41017886996269226,
      "learning_rate": 1.1194226293812837e-07,
      "loss": 0.4886,
      "step": 62008
    },
    {
      "epoch": 1.904862839062452,
      "grad_norm": 0.4695851504802704,
      "learning_rate": 1.1187016545483153e-07,
      "loss": 0.4307,
      "step": 62009
    },
    {
      "epoch": 1.9048935581974011,
      "grad_norm": 0.414510577917099,
      "learning_rate": 1.1179809106595219e-07,
      "loss": 0.4284,
      "step": 62010
    },
    {
      "epoch": 1.9049242773323503,
      "grad_norm": 0.40292543172836304,
      "learning_rate": 1.1172603977166018e-07,
      "loss": 0.3778,
      "step": 62011
    },
    {
      "epoch": 1.9049549964672994,
      "grad_norm": 0.4764091968536377,
      "learning_rate": 1.1165401157212208e-07,
      "loss": 0.551,
      "step": 62012
    },
    {
      "epoch": 1.9049857156022485,
      "grad_norm": 0.4604697823524475,
      "learning_rate": 1.1158200646750661e-07,
      "loss": 0.4329,
      "step": 62013
    },
    {
      "epoch": 1.9050164347371978,
      "grad_norm": 0.4100724160671234,
      "learning_rate": 1.1151002445798254e-07,
      "loss": 0.515,
      "step": 62014
    },
    {
      "epoch": 1.905047153872147,
      "grad_norm": 0.5204406380653381,
      "learning_rate": 1.114380655437175e-07,
      "loss": 0.5029,
      "step": 62015
    },
    {
      "epoch": 1.905077873007096,
      "grad_norm": 0.41578641533851624,
      "learning_rate": 1.1136612972487804e-07,
      "loss": 0.5257,
      "step": 62016
    },
    {
      "epoch": 1.9051085921420454,
      "grad_norm": 0.42013412714004517,
      "learning_rate": 1.11294217001634e-07,
      "loss": 0.4424,
      "step": 62017
    },
    {
      "epoch": 1.9051393112769945,
      "grad_norm": 0.45547643303871155,
      "learning_rate": 1.1122232737415306e-07,
      "loss": 0.4551,
      "step": 62018
    },
    {
      "epoch": 1.9051700304119437,
      "grad_norm": 0.4943850338459015,
      "learning_rate": 1.1115046084260394e-07,
      "loss": 0.3902,
      "step": 62019
    },
    {
      "epoch": 1.9052007495468928,
      "grad_norm": 0.42199909687042236,
      "learning_rate": 1.110786174071532e-07,
      "loss": 0.5002,
      "step": 62020
    },
    {
      "epoch": 1.905231468681842,
      "grad_norm": 0.5138930082321167,
      "learning_rate": 1.1100679706796958e-07,
      "loss": 0.4481,
      "step": 62021
    },
    {
      "epoch": 1.905262187816791,
      "grad_norm": 0.46505293250083923,
      "learning_rate": 1.1093499982521849e-07,
      "loss": 0.5622,
      "step": 62022
    },
    {
      "epoch": 1.9052929069517401,
      "grad_norm": 0.4170309007167816,
      "learning_rate": 1.1086322567906982e-07,
      "loss": 0.4842,
      "step": 62023
    },
    {
      "epoch": 1.9053236260866893,
      "grad_norm": 0.4442162811756134,
      "learning_rate": 1.107914746296912e-07,
      "loss": 0.5347,
      "step": 62024
    },
    {
      "epoch": 1.9053543452216386,
      "grad_norm": 0.4695624113082886,
      "learning_rate": 1.1071974667724916e-07,
      "loss": 0.4689,
      "step": 62025
    },
    {
      "epoch": 1.9053850643565877,
      "grad_norm": 0.4409496486186981,
      "learning_rate": 1.1064804182191247e-07,
      "loss": 0.4733,
      "step": 62026
    },
    {
      "epoch": 1.9054157834915368,
      "grad_norm": 0.4340735375881195,
      "learning_rate": 1.1057636006384764e-07,
      "loss": 0.4381,
      "step": 62027
    },
    {
      "epoch": 1.9054465026264862,
      "grad_norm": 0.4405476748943329,
      "learning_rate": 1.1050470140322344e-07,
      "loss": 0.4424,
      "step": 62028
    },
    {
      "epoch": 1.9054772217614353,
      "grad_norm": 0.4061826765537262,
      "learning_rate": 1.104330658402053e-07,
      "loss": 0.457,
      "step": 62029
    },
    {
      "epoch": 1.9055079408963844,
      "grad_norm": 0.4418473541736603,
      "learning_rate": 1.1036145337496196e-07,
      "loss": 0.4593,
      "step": 62030
    },
    {
      "epoch": 1.9055386600313335,
      "grad_norm": 0.47076505422592163,
      "learning_rate": 1.1028986400765773e-07,
      "loss": 0.4418,
      "step": 62031
    },
    {
      "epoch": 1.9055693791662827,
      "grad_norm": 0.4442407190799713,
      "learning_rate": 1.102182977384647e-07,
      "loss": 0.5021,
      "step": 62032
    },
    {
      "epoch": 1.9056000983012318,
      "grad_norm": 0.43316492438316345,
      "learning_rate": 1.101467545675472e-07,
      "loss": 0.5554,
      "step": 62033
    },
    {
      "epoch": 1.905630817436181,
      "grad_norm": 0.3999074399471283,
      "learning_rate": 1.1007523449507285e-07,
      "loss": 0.5585,
      "step": 62034
    },
    {
      "epoch": 1.90566153657113,
      "grad_norm": 0.41253140568733215,
      "learning_rate": 1.1000373752120818e-07,
      "loss": 0.4533,
      "step": 62035
    },
    {
      "epoch": 1.9056922557060794,
      "grad_norm": 0.48894163966178894,
      "learning_rate": 1.0993226364611976e-07,
      "loss": 0.4135,
      "step": 62036
    },
    {
      "epoch": 1.9057229748410285,
      "grad_norm": 0.4389328360557556,
      "learning_rate": 1.0986081286997519e-07,
      "loss": 0.465,
      "step": 62037
    },
    {
      "epoch": 1.9057536939759776,
      "grad_norm": 0.44265636801719666,
      "learning_rate": 1.0978938519294324e-07,
      "loss": 0.4613,
      "step": 62038
    },
    {
      "epoch": 1.905784413110927,
      "grad_norm": 0.44434094429016113,
      "learning_rate": 1.0971798061518712e-07,
      "loss": 0.481,
      "step": 62039
    },
    {
      "epoch": 1.905815132245876,
      "grad_norm": 0.412910133600235,
      "learning_rate": 1.0964659913687559e-07,
      "loss": 0.4626,
      "step": 62040
    },
    {
      "epoch": 1.9058458513808252,
      "grad_norm": 0.4289913475513458,
      "learning_rate": 1.0957524075817516e-07,
      "loss": 0.4969,
      "step": 62041
    },
    {
      "epoch": 1.9058765705157743,
      "grad_norm": 0.42564377188682556,
      "learning_rate": 1.0950390547925349e-07,
      "loss": 0.3613,
      "step": 62042
    },
    {
      "epoch": 1.9059072896507234,
      "grad_norm": 0.42870083451271057,
      "learning_rate": 1.09432593300276e-07,
      "loss": 0.4586,
      "step": 62043
    },
    {
      "epoch": 1.9059380087856725,
      "grad_norm": 0.44450217485427856,
      "learning_rate": 1.0936130422140811e-07,
      "loss": 0.4873,
      "step": 62044
    },
    {
      "epoch": 1.9059687279206217,
      "grad_norm": 0.5345363020896912,
      "learning_rate": 1.0929003824281859e-07,
      "loss": 0.41,
      "step": 62045
    },
    {
      "epoch": 1.9059994470555708,
      "grad_norm": 0.43854421377182007,
      "learning_rate": 1.0921879536467283e-07,
      "loss": 0.5032,
      "step": 62046
    },
    {
      "epoch": 1.9060301661905201,
      "grad_norm": 0.44872963428497314,
      "learning_rate": 1.091475755871374e-07,
      "loss": 0.4666,
      "step": 62047
    },
    {
      "epoch": 1.9060608853254692,
      "grad_norm": 0.4790412187576294,
      "learning_rate": 1.0907637891037881e-07,
      "loss": 0.4774,
      "step": 62048
    },
    {
      "epoch": 1.9060916044604184,
      "grad_norm": 0.46237847208976746,
      "learning_rate": 1.090052053345625e-07,
      "loss": 0.4804,
      "step": 62049
    },
    {
      "epoch": 1.9061223235953677,
      "grad_norm": 0.44743362069129944,
      "learning_rate": 1.0893405485985608e-07,
      "loss": 0.4311,
      "step": 62050
    },
    {
      "epoch": 1.9061530427303168,
      "grad_norm": 0.443556010723114,
      "learning_rate": 1.0886292748642502e-07,
      "loss": 0.4391,
      "step": 62051
    },
    {
      "epoch": 1.906183761865266,
      "grad_norm": 1.2793691158294678,
      "learning_rate": 1.0879182321443471e-07,
      "loss": 0.4207,
      "step": 62052
    },
    {
      "epoch": 1.906214481000215,
      "grad_norm": 0.4542867839336395,
      "learning_rate": 1.087207420440517e-07,
      "loss": 0.4946,
      "step": 62053
    },
    {
      "epoch": 1.9062452001351642,
      "grad_norm": 0.42477577924728394,
      "learning_rate": 1.086496839754425e-07,
      "loss": 0.4499,
      "step": 62054
    },
    {
      "epoch": 1.9062759192701133,
      "grad_norm": 0.41251203417778015,
      "learning_rate": 1.0857864900877257e-07,
      "loss": 0.4323,
      "step": 62055
    },
    {
      "epoch": 1.9063066384050624,
      "grad_norm": 0.3777577877044678,
      "learning_rate": 1.0850763714420842e-07,
      "loss": 0.4985,
      "step": 62056
    },
    {
      "epoch": 1.9063373575400115,
      "grad_norm": 0.42814308404922485,
      "learning_rate": 1.0843664838191658e-07,
      "loss": 0.4447,
      "step": 62057
    },
    {
      "epoch": 1.9063680766749609,
      "grad_norm": 0.41893041133880615,
      "learning_rate": 1.0836568272205917e-07,
      "loss": 0.4618,
      "step": 62058
    },
    {
      "epoch": 1.90639879580991,
      "grad_norm": 0.4390381872653961,
      "learning_rate": 1.0829474016480601e-07,
      "loss": 0.3835,
      "step": 62059
    },
    {
      "epoch": 1.9064295149448591,
      "grad_norm": 0.5638900399208069,
      "learning_rate": 1.0822382071032144e-07,
      "loss": 0.502,
      "step": 62060
    },
    {
      "epoch": 1.9064602340798085,
      "grad_norm": 0.4318673610687256,
      "learning_rate": 1.081529243587709e-07,
      "loss": 0.4665,
      "step": 62061
    },
    {
      "epoch": 1.9064909532147576,
      "grad_norm": 0.3981981575489044,
      "learning_rate": 1.0808205111031977e-07,
      "loss": 0.3255,
      "step": 62062
    },
    {
      "epoch": 1.9065216723497067,
      "grad_norm": 0.42186686396598816,
      "learning_rate": 1.0801120096513352e-07,
      "loss": 0.5646,
      "step": 62063
    },
    {
      "epoch": 1.9065523914846558,
      "grad_norm": 0.4278181195259094,
      "learning_rate": 1.0794037392337864e-07,
      "loss": 0.5155,
      "step": 62064
    },
    {
      "epoch": 1.906583110619605,
      "grad_norm": 0.4506780207157135,
      "learning_rate": 1.0786956998521947e-07,
      "loss": 0.4686,
      "step": 62065
    },
    {
      "epoch": 1.906613829754554,
      "grad_norm": 0.48552003502845764,
      "learning_rate": 1.0779878915082254e-07,
      "loss": 0.5194,
      "step": 62066
    },
    {
      "epoch": 1.9066445488895032,
      "grad_norm": 0.4323943853378296,
      "learning_rate": 1.0772803142035105e-07,
      "loss": 0.4306,
      "step": 62067
    },
    {
      "epoch": 1.9066752680244523,
      "grad_norm": 0.42536020278930664,
      "learning_rate": 1.0765729679397263e-07,
      "loss": 0.4367,
      "step": 62068
    },
    {
      "epoch": 1.9067059871594014,
      "grad_norm": 0.5023965835571289,
      "learning_rate": 1.0758658527185162e-07,
      "loss": 0.4177,
      "step": 62069
    },
    {
      "epoch": 1.9067367062943508,
      "grad_norm": 0.45520395040512085,
      "learning_rate": 1.0751589685415343e-07,
      "loss": 0.4026,
      "step": 62070
    },
    {
      "epoch": 1.9067674254293,
      "grad_norm": 0.47300010919570923,
      "learning_rate": 1.0744523154104125e-07,
      "loss": 0.4921,
      "step": 62071
    },
    {
      "epoch": 1.9067981445642492,
      "grad_norm": 0.6644856929779053,
      "learning_rate": 1.0737458933268275e-07,
      "loss": 0.4729,
      "step": 62072
    },
    {
      "epoch": 1.9068288636991984,
      "grad_norm": 0.46988165378570557,
      "learning_rate": 1.073039702292411e-07,
      "loss": 0.4525,
      "step": 62073
    },
    {
      "epoch": 1.9068595828341475,
      "grad_norm": 0.4490990936756134,
      "learning_rate": 1.0723337423088176e-07,
      "loss": 0.4632,
      "step": 62074
    },
    {
      "epoch": 1.9068903019690966,
      "grad_norm": 0.43115153908729553,
      "learning_rate": 1.0716280133777012e-07,
      "loss": 0.4428,
      "step": 62075
    },
    {
      "epoch": 1.9069210211040457,
      "grad_norm": 0.45241838693618774,
      "learning_rate": 1.0709225155007053e-07,
      "loss": 0.4912,
      "step": 62076
    },
    {
      "epoch": 1.9069517402389948,
      "grad_norm": 0.43930551409721375,
      "learning_rate": 1.0702172486794837e-07,
      "loss": 0.4291,
      "step": 62077
    },
    {
      "epoch": 1.906982459373944,
      "grad_norm": 0.5400036573410034,
      "learning_rate": 1.0695122129156687e-07,
      "loss": 0.4879,
      "step": 62078
    },
    {
      "epoch": 1.907013178508893,
      "grad_norm": 0.46562761068344116,
      "learning_rate": 1.0688074082109367e-07,
      "loss": 0.4598,
      "step": 62079
    },
    {
      "epoch": 1.9070438976438422,
      "grad_norm": 0.42425966262817383,
      "learning_rate": 1.0681028345668976e-07,
      "loss": 0.4282,
      "step": 62080
    },
    {
      "epoch": 1.9070746167787915,
      "grad_norm": 0.5891273021697998,
      "learning_rate": 1.0673984919852165e-07,
      "loss": 0.4938,
      "step": 62081
    },
    {
      "epoch": 1.9071053359137407,
      "grad_norm": 0.4259434938430786,
      "learning_rate": 1.0666943804675367e-07,
      "loss": 0.5048,
      "step": 62082
    },
    {
      "epoch": 1.90713605504869,
      "grad_norm": 0.443946897983551,
      "learning_rate": 1.0659905000155124e-07,
      "loss": 0.5143,
      "step": 62083
    },
    {
      "epoch": 1.9071667741836391,
      "grad_norm": 0.43780940771102905,
      "learning_rate": 1.0652868506307645e-07,
      "loss": 0.4658,
      "step": 62084
    },
    {
      "epoch": 1.9071974933185882,
      "grad_norm": 0.4466993808746338,
      "learning_rate": 1.0645834323149473e-07,
      "loss": 0.4342,
      "step": 62085
    },
    {
      "epoch": 1.9072282124535374,
      "grad_norm": 0.4271141588687897,
      "learning_rate": 1.0638802450697039e-07,
      "loss": 0.3962,
      "step": 62086
    },
    {
      "epoch": 1.9072589315884865,
      "grad_norm": 0.43434396386146545,
      "learning_rate": 1.0631772888966885e-07,
      "loss": 0.4898,
      "step": 62087
    },
    {
      "epoch": 1.9072896507234356,
      "grad_norm": 0.40763887763023376,
      "learning_rate": 1.062474563797522e-07,
      "loss": 0.3726,
      "step": 62088
    },
    {
      "epoch": 1.9073203698583847,
      "grad_norm": 0.44939878582954407,
      "learning_rate": 1.0617720697738587e-07,
      "loss": 0.4987,
      "step": 62089
    },
    {
      "epoch": 1.9073510889933338,
      "grad_norm": 0.4239780604839325,
      "learning_rate": 1.0610698068273417e-07,
      "loss": 0.3687,
      "step": 62090
    },
    {
      "epoch": 1.907381808128283,
      "grad_norm": 0.44276851415634155,
      "learning_rate": 1.0603677749596031e-07,
      "loss": 0.5371,
      "step": 62091
    },
    {
      "epoch": 1.9074125272632323,
      "grad_norm": 0.4360907971858978,
      "learning_rate": 1.0596659741722858e-07,
      "loss": 0.4823,
      "step": 62092
    },
    {
      "epoch": 1.9074432463981814,
      "grad_norm": 0.41619619727134705,
      "learning_rate": 1.0589644044670333e-07,
      "loss": 0.4683,
      "step": 62093
    },
    {
      "epoch": 1.9074739655331305,
      "grad_norm": 0.40678250789642334,
      "learning_rate": 1.0582630658454662e-07,
      "loss": 0.4881,
      "step": 62094
    },
    {
      "epoch": 1.9075046846680799,
      "grad_norm": 0.3841612637042999,
      "learning_rate": 1.0575619583092389e-07,
      "loss": 0.485,
      "step": 62095
    },
    {
      "epoch": 1.907535403803029,
      "grad_norm": 0.4238390326499939,
      "learning_rate": 1.0568610818599944e-07,
      "loss": 0.4912,
      "step": 62096
    },
    {
      "epoch": 1.9075661229379781,
      "grad_norm": 0.4465616047382355,
      "learning_rate": 1.0561604364993539e-07,
      "loss": 0.4989,
      "step": 62097
    },
    {
      "epoch": 1.9075968420729272,
      "grad_norm": 0.4147539734840393,
      "learning_rate": 1.0554600222289712e-07,
      "loss": 0.5156,
      "step": 62098
    },
    {
      "epoch": 1.9076275612078764,
      "grad_norm": 0.45225095748901367,
      "learning_rate": 1.0547598390504454e-07,
      "loss": 0.4562,
      "step": 62099
    },
    {
      "epoch": 1.9076582803428255,
      "grad_norm": 0.4423826336860657,
      "learning_rate": 1.054059886965464e-07,
      "loss": 0.3964,
      "step": 62100
    },
    {
      "epoch": 1.9076889994777746,
      "grad_norm": 0.43530136346817017,
      "learning_rate": 1.0533601659756254e-07,
      "loss": 0.4243,
      "step": 62101
    },
    {
      "epoch": 1.9077197186127237,
      "grad_norm": 0.4705362319946289,
      "learning_rate": 1.0526606760825841e-07,
      "loss": 0.5224,
      "step": 62102
    },
    {
      "epoch": 1.907750437747673,
      "grad_norm": 0.4708803594112396,
      "learning_rate": 1.0519614172879611e-07,
      "loss": 0.3861,
      "step": 62103
    },
    {
      "epoch": 1.9077811568826222,
      "grad_norm": 0.3944704532623291,
      "learning_rate": 1.0512623895933882e-07,
      "loss": 0.4769,
      "step": 62104
    },
    {
      "epoch": 1.9078118760175713,
      "grad_norm": 0.43401220440864563,
      "learning_rate": 1.0505635930004976e-07,
      "loss": 0.5722,
      "step": 62105
    },
    {
      "epoch": 1.9078425951525206,
      "grad_norm": 0.3738858103752136,
      "learning_rate": 1.0498650275109435e-07,
      "loss": 0.4514,
      "step": 62106
    },
    {
      "epoch": 1.9078733142874698,
      "grad_norm": 0.5202146172523499,
      "learning_rate": 1.0491666931263245e-07,
      "loss": 0.4499,
      "step": 62107
    },
    {
      "epoch": 1.9079040334224189,
      "grad_norm": 0.4360177516937256,
      "learning_rate": 1.0484685898482839e-07,
      "loss": 0.4579,
      "step": 62108
    },
    {
      "epoch": 1.907934752557368,
      "grad_norm": 0.4024679958820343,
      "learning_rate": 1.0477707176784646e-07,
      "loss": 0.4483,
      "step": 62109
    },
    {
      "epoch": 1.9079654716923171,
      "grad_norm": 0.44903287291526794,
      "learning_rate": 1.047073076618499e-07,
      "loss": 0.4385,
      "step": 62110
    },
    {
      "epoch": 1.9079961908272662,
      "grad_norm": 0.42752498388290405,
      "learning_rate": 1.0463756666699853e-07,
      "loss": 0.471,
      "step": 62111
    },
    {
      "epoch": 1.9080269099622154,
      "grad_norm": 0.4051686227321625,
      "learning_rate": 1.0456784878345782e-07,
      "loss": 0.4283,
      "step": 62112
    },
    {
      "epoch": 1.9080576290971645,
      "grad_norm": 0.4179038107395172,
      "learning_rate": 1.0449815401138986e-07,
      "loss": 0.4533,
      "step": 62113
    },
    {
      "epoch": 1.9080883482321138,
      "grad_norm": 0.41745495796203613,
      "learning_rate": 1.0442848235095893e-07,
      "loss": 0.4424,
      "step": 62114
    },
    {
      "epoch": 1.908119067367063,
      "grad_norm": 0.41215723752975464,
      "learning_rate": 1.0435883380232493e-07,
      "loss": 0.4711,
      "step": 62115
    },
    {
      "epoch": 1.908149786502012,
      "grad_norm": 0.41286763548851013,
      "learning_rate": 1.0428920836565215e-07,
      "loss": 0.512,
      "step": 62116
    },
    {
      "epoch": 1.9081805056369614,
      "grad_norm": 0.413198322057724,
      "learning_rate": 1.042196060411027e-07,
      "loss": 0.5034,
      "step": 62117
    },
    {
      "epoch": 1.9082112247719105,
      "grad_norm": 0.42180901765823364,
      "learning_rate": 1.041500268288398e-07,
      "loss": 0.4283,
      "step": 62118
    },
    {
      "epoch": 1.9082419439068596,
      "grad_norm": 0.43588194251060486,
      "learning_rate": 1.0408047072902661e-07,
      "loss": 0.4648,
      "step": 62119
    },
    {
      "epoch": 1.9082726630418088,
      "grad_norm": 0.465843141078949,
      "learning_rate": 1.0401093774182303e-07,
      "loss": 0.5212,
      "step": 62120
    },
    {
      "epoch": 1.9083033821767579,
      "grad_norm": 0.4178328216075897,
      "learning_rate": 1.0394142786739336e-07,
      "loss": 0.4179,
      "step": 62121
    },
    {
      "epoch": 1.908334101311707,
      "grad_norm": 0.6193040013313293,
      "learning_rate": 1.0387194110590081e-07,
      "loss": 0.4701,
      "step": 62122
    },
    {
      "epoch": 1.9083648204466561,
      "grad_norm": 0.4054510295391083,
      "learning_rate": 1.0380247745750527e-07,
      "loss": 0.5379,
      "step": 62123
    },
    {
      "epoch": 1.9083955395816052,
      "grad_norm": 0.4608379900455475,
      "learning_rate": 1.0373303692237103e-07,
      "loss": 0.4845,
      "step": 62124
    },
    {
      "epoch": 1.9084262587165546,
      "grad_norm": 0.46126729249954224,
      "learning_rate": 1.0366361950065906e-07,
      "loss": 0.4738,
      "step": 62125
    },
    {
      "epoch": 1.9084569778515037,
      "grad_norm": 0.42043957114219666,
      "learning_rate": 1.0359422519253148e-07,
      "loss": 0.4205,
      "step": 62126
    },
    {
      "epoch": 1.9084876969864528,
      "grad_norm": 0.4332799017429352,
      "learning_rate": 1.0352485399815149e-07,
      "loss": 0.458,
      "step": 62127
    },
    {
      "epoch": 1.9085184161214022,
      "grad_norm": 0.43586257100105286,
      "learning_rate": 1.0345550591768005e-07,
      "loss": 0.4612,
      "step": 62128
    },
    {
      "epoch": 1.9085491352563513,
      "grad_norm": 0.38356396555900574,
      "learning_rate": 1.0338618095127928e-07,
      "loss": 0.4134,
      "step": 62129
    },
    {
      "epoch": 1.9085798543913004,
      "grad_norm": 0.4140271246433258,
      "learning_rate": 1.0331687909911014e-07,
      "loss": 0.4694,
      "step": 62130
    },
    {
      "epoch": 1.9086105735262495,
      "grad_norm": 0.42578136920928955,
      "learning_rate": 1.0324760036133808e-07,
      "loss": 0.4623,
      "step": 62131
    },
    {
      "epoch": 1.9086412926611986,
      "grad_norm": 0.4614247679710388,
      "learning_rate": 1.0317834473812071e-07,
      "loss": 0.4925,
      "step": 62132
    },
    {
      "epoch": 1.9086720117961478,
      "grad_norm": 0.42669934034347534,
      "learning_rate": 1.0310911222962127e-07,
      "loss": 0.4885,
      "step": 62133
    },
    {
      "epoch": 1.9087027309310969,
      "grad_norm": 0.4264405369758606,
      "learning_rate": 1.0303990283600295e-07,
      "loss": 0.4552,
      "step": 62134
    },
    {
      "epoch": 1.908733450066046,
      "grad_norm": 0.4739832282066345,
      "learning_rate": 1.0297071655742564e-07,
      "loss": 0.4119,
      "step": 62135
    },
    {
      "epoch": 1.9087641692009953,
      "grad_norm": 0.4556901752948761,
      "learning_rate": 1.0290155339405138e-07,
      "loss": 0.5083,
      "step": 62136
    },
    {
      "epoch": 1.9087948883359445,
      "grad_norm": 0.44384363293647766,
      "learning_rate": 1.0283241334604122e-07,
      "loss": 0.4822,
      "step": 62137
    },
    {
      "epoch": 1.9088256074708936,
      "grad_norm": 0.4358314573764801,
      "learning_rate": 1.0276329641355831e-07,
      "loss": 0.4828,
      "step": 62138
    },
    {
      "epoch": 1.908856326605843,
      "grad_norm": 0.4690815806388855,
      "learning_rate": 1.0269420259676256e-07,
      "loss": 0.4954,
      "step": 62139
    },
    {
      "epoch": 1.908887045740792,
      "grad_norm": 0.41558438539505005,
      "learning_rate": 1.0262513189581492e-07,
      "loss": 0.3902,
      "step": 62140
    },
    {
      "epoch": 1.9089177648757412,
      "grad_norm": 0.43513771891593933,
      "learning_rate": 1.0255608431087749e-07,
      "loss": 0.425,
      "step": 62141
    },
    {
      "epoch": 1.9089484840106903,
      "grad_norm": 0.4336981177330017,
      "learning_rate": 1.0248705984211239e-07,
      "loss": 0.5774,
      "step": 62142
    },
    {
      "epoch": 1.9089792031456394,
      "grad_norm": 0.43027809262275696,
      "learning_rate": 1.0241805848967944e-07,
      "loss": 0.5018,
      "step": 62143
    },
    {
      "epoch": 1.9090099222805885,
      "grad_norm": 0.4089810252189636,
      "learning_rate": 1.023490802537408e-07,
      "loss": 0.505,
      "step": 62144
    },
    {
      "epoch": 1.9090406414155376,
      "grad_norm": 0.3797873258590698,
      "learning_rate": 1.0228012513445739e-07,
      "loss": 0.4076,
      "step": 62145
    },
    {
      "epoch": 1.9090713605504868,
      "grad_norm": 0.4342797100543976,
      "learning_rate": 1.0221119313198913e-07,
      "loss": 0.4461,
      "step": 62146
    },
    {
      "epoch": 1.909102079685436,
      "grad_norm": 0.40053191781044006,
      "learning_rate": 1.0214228424649808e-07,
      "loss": 0.4699,
      "step": 62147
    },
    {
      "epoch": 1.9091327988203852,
      "grad_norm": 0.41787511110305786,
      "learning_rate": 1.0207339847814523e-07,
      "loss": 0.4611,
      "step": 62148
    },
    {
      "epoch": 1.9091635179553343,
      "grad_norm": 0.44146454334259033,
      "learning_rate": 1.0200453582709158e-07,
      "loss": 0.4277,
      "step": 62149
    },
    {
      "epoch": 1.9091942370902837,
      "grad_norm": 0.46277040243148804,
      "learning_rate": 1.0193569629349697e-07,
      "loss": 0.4591,
      "step": 62150
    },
    {
      "epoch": 1.9092249562252328,
      "grad_norm": 0.41301846504211426,
      "learning_rate": 1.0186687987752353e-07,
      "loss": 0.4735,
      "step": 62151
    },
    {
      "epoch": 1.909255675360182,
      "grad_norm": 0.4694727957248688,
      "learning_rate": 1.0179808657932999e-07,
      "loss": 0.5042,
      "step": 62152
    },
    {
      "epoch": 1.909286394495131,
      "grad_norm": 0.40771979093551636,
      "learning_rate": 1.0172931639907957e-07,
      "loss": 0.5248,
      "step": 62153
    },
    {
      "epoch": 1.9093171136300802,
      "grad_norm": 0.40400198101997375,
      "learning_rate": 1.0166056933693103e-07,
      "loss": 0.4319,
      "step": 62154
    },
    {
      "epoch": 1.9093478327650293,
      "grad_norm": 0.4842914044857025,
      "learning_rate": 1.0159184539304534e-07,
      "loss": 0.433,
      "step": 62155
    },
    {
      "epoch": 1.9093785518999784,
      "grad_norm": 0.4315500855445862,
      "learning_rate": 1.015231445675835e-07,
      "loss": 0.3878,
      "step": 62156
    },
    {
      "epoch": 1.9094092710349275,
      "grad_norm": 0.4516662657260895,
      "learning_rate": 1.0145446686070537e-07,
      "loss": 0.4315,
      "step": 62157
    },
    {
      "epoch": 1.9094399901698769,
      "grad_norm": 0.40352118015289307,
      "learning_rate": 1.0138581227257193e-07,
      "loss": 0.4344,
      "step": 62158
    },
    {
      "epoch": 1.909470709304826,
      "grad_norm": 0.4458417594432831,
      "learning_rate": 1.0131718080334419e-07,
      "loss": 0.5065,
      "step": 62159
    },
    {
      "epoch": 1.909501428439775,
      "grad_norm": 0.4638975262641907,
      "learning_rate": 1.0124857245317976e-07,
      "loss": 0.5144,
      "step": 62160
    },
    {
      "epoch": 1.9095321475747244,
      "grad_norm": 0.4354216456413269,
      "learning_rate": 1.0117998722224187e-07,
      "loss": 0.4483,
      "step": 62161
    },
    {
      "epoch": 1.9095628667096736,
      "grad_norm": 0.4241991937160492,
      "learning_rate": 1.0111142511068817e-07,
      "loss": 0.4446,
      "step": 62162
    },
    {
      "epoch": 1.9095935858446227,
      "grad_norm": 0.48986533284187317,
      "learning_rate": 1.0104288611868185e-07,
      "loss": 0.4796,
      "step": 62163
    },
    {
      "epoch": 1.9096243049795718,
      "grad_norm": 0.44592970609664917,
      "learning_rate": 1.0097437024637946e-07,
      "loss": 0.5569,
      "step": 62164
    },
    {
      "epoch": 1.909655024114521,
      "grad_norm": 0.4184829592704773,
      "learning_rate": 1.009058774939442e-07,
      "loss": 0.4294,
      "step": 62165
    },
    {
      "epoch": 1.90968574324947,
      "grad_norm": 0.42065563797950745,
      "learning_rate": 1.0083740786153373e-07,
      "loss": 0.4319,
      "step": 62166
    },
    {
      "epoch": 1.9097164623844192,
      "grad_norm": 0.46453866362571716,
      "learning_rate": 1.0076896134930903e-07,
      "loss": 0.4651,
      "step": 62167
    },
    {
      "epoch": 1.9097471815193683,
      "grad_norm": 0.4386928081512451,
      "learning_rate": 1.0070053795742995e-07,
      "loss": 0.4777,
      "step": 62168
    },
    {
      "epoch": 1.9097779006543176,
      "grad_norm": 0.44711899757385254,
      "learning_rate": 1.0063213768605529e-07,
      "loss": 0.4793,
      "step": 62169
    },
    {
      "epoch": 1.9098086197892667,
      "grad_norm": 0.5019673705101013,
      "learning_rate": 1.0056376053534711e-07,
      "loss": 0.4732,
      "step": 62170
    },
    {
      "epoch": 1.9098393389242159,
      "grad_norm": 0.40163689851760864,
      "learning_rate": 1.0049540650546197e-07,
      "loss": 0.4786,
      "step": 62171
    },
    {
      "epoch": 1.9098700580591652,
      "grad_norm": 0.5351190567016602,
      "learning_rate": 1.0042707559656195e-07,
      "loss": 0.4566,
      "step": 62172
    },
    {
      "epoch": 1.9099007771941143,
      "grad_norm": 0.46179839968681335,
      "learning_rate": 1.0035876780880583e-07,
      "loss": 0.5055,
      "step": 62173
    },
    {
      "epoch": 1.9099314963290634,
      "grad_norm": 0.4092075228691101,
      "learning_rate": 1.0029048314235457e-07,
      "loss": 0.4377,
      "step": 62174
    },
    {
      "epoch": 1.9099622154640126,
      "grad_norm": 0.4622495472431183,
      "learning_rate": 1.0022222159736472e-07,
      "loss": 0.4884,
      "step": 62175
    },
    {
      "epoch": 1.9099929345989617,
      "grad_norm": 0.5611159801483154,
      "learning_rate": 1.0015398317399727e-07,
      "loss": 0.5064,
      "step": 62176
    },
    {
      "epoch": 1.9100236537339108,
      "grad_norm": 0.7561794519424438,
      "learning_rate": 1.0008576787241208e-07,
      "loss": 0.5385,
      "step": 62177
    },
    {
      "epoch": 1.91005437286886,
      "grad_norm": 0.4330419600009918,
      "learning_rate": 1.0001757569276793e-07,
      "loss": 0.4578,
      "step": 62178
    },
    {
      "epoch": 1.910085092003809,
      "grad_norm": 0.4234776198863983,
      "learning_rate": 9.994940663522357e-08,
      "loss": 0.5149,
      "step": 62179
    },
    {
      "epoch": 1.9101158111387582,
      "grad_norm": 0.4202551245689392,
      "learning_rate": 9.988126069993887e-08,
      "loss": 0.4374,
      "step": 62180
    },
    {
      "epoch": 1.9101465302737075,
      "grad_norm": 0.44435566663742065,
      "learning_rate": 9.981313788707369e-08,
      "loss": 0.4521,
      "step": 62181
    },
    {
      "epoch": 1.9101772494086566,
      "grad_norm": 0.4450434744358063,
      "learning_rate": 9.974503819678571e-08,
      "loss": 0.4652,
      "step": 62182
    },
    {
      "epoch": 1.910207968543606,
      "grad_norm": 0.44710999727249146,
      "learning_rate": 9.967696162923479e-08,
      "loss": 0.4645,
      "step": 62183
    },
    {
      "epoch": 1.910238687678555,
      "grad_norm": 0.45498138666152954,
      "learning_rate": 9.960890818457969e-08,
      "loss": 0.5181,
      "step": 62184
    },
    {
      "epoch": 1.9102694068135042,
      "grad_norm": 0.6258754730224609,
      "learning_rate": 9.954087786297917e-08,
      "loss": 0.5276,
      "step": 62185
    },
    {
      "epoch": 1.9103001259484533,
      "grad_norm": 0.41881027817726135,
      "learning_rate": 9.94728706645931e-08,
      "loss": 0.4816,
      "step": 62186
    },
    {
      "epoch": 1.9103308450834025,
      "grad_norm": 0.44001367688179016,
      "learning_rate": 9.940488658957914e-08,
      "loss": 0.4604,
      "step": 62187
    },
    {
      "epoch": 1.9103615642183516,
      "grad_norm": 0.43257007002830505,
      "learning_rate": 9.933692563809716e-08,
      "loss": 0.5116,
      "step": 62188
    },
    {
      "epoch": 1.9103922833533007,
      "grad_norm": 0.48454469442367554,
      "learning_rate": 9.92689878103037e-08,
      "loss": 0.3443,
      "step": 62189
    },
    {
      "epoch": 1.9104230024882498,
      "grad_norm": 0.43213024735450745,
      "learning_rate": 9.920107310635973e-08,
      "loss": 0.4907,
      "step": 62190
    },
    {
      "epoch": 1.910453721623199,
      "grad_norm": 0.4249453842639923,
      "learning_rate": 9.913318152642404e-08,
      "loss": 0.3951,
      "step": 62191
    },
    {
      "epoch": 1.9104844407581483,
      "grad_norm": 0.4351440966129303,
      "learning_rate": 9.906531307065314e-08,
      "loss": 0.4501,
      "step": 62192
    },
    {
      "epoch": 1.9105151598930974,
      "grad_norm": 0.4395478069782257,
      "learning_rate": 9.899746773920693e-08,
      "loss": 0.4497,
      "step": 62193
    },
    {
      "epoch": 1.9105458790280467,
      "grad_norm": 0.4104045033454895,
      "learning_rate": 9.892964553224416e-08,
      "loss": 0.5507,
      "step": 62194
    },
    {
      "epoch": 1.9105765981629959,
      "grad_norm": 0.44947126507759094,
      "learning_rate": 9.886184644992247e-08,
      "loss": 0.4641,
      "step": 62195
    },
    {
      "epoch": 1.910607317297945,
      "grad_norm": 0.39717480540275574,
      "learning_rate": 9.879407049240064e-08,
      "loss": 0.4543,
      "step": 62196
    },
    {
      "epoch": 1.910638036432894,
      "grad_norm": 0.44682779908180237,
      "learning_rate": 9.872631765983632e-08,
      "loss": 0.461,
      "step": 62197
    },
    {
      "epoch": 1.9106687555678432,
      "grad_norm": 0.5124070644378662,
      "learning_rate": 9.865858795238714e-08,
      "loss": 0.4057,
      "step": 62198
    },
    {
      "epoch": 1.9106994747027923,
      "grad_norm": 0.4557814300060272,
      "learning_rate": 9.859088137021411e-08,
      "loss": 0.5468,
      "step": 62199
    },
    {
      "epoch": 1.9107301938377415,
      "grad_norm": 0.403384268283844,
      "learning_rate": 9.852319791347265e-08,
      "loss": 0.5165,
      "step": 62200
    },
    {
      "epoch": 1.9107609129726906,
      "grad_norm": 0.4342299699783325,
      "learning_rate": 9.845553758232262e-08,
      "loss": 0.5017,
      "step": 62201
    },
    {
      "epoch": 1.9107916321076397,
      "grad_norm": 0.4054590165615082,
      "learning_rate": 9.838790037692058e-08,
      "loss": 0.4423,
      "step": 62202
    },
    {
      "epoch": 1.910822351242589,
      "grad_norm": 0.4162684381008148,
      "learning_rate": 9.83202862974253e-08,
      "loss": 0.553,
      "step": 62203
    },
    {
      "epoch": 1.9108530703775382,
      "grad_norm": 0.4181121587753296,
      "learning_rate": 9.82526953439933e-08,
      "loss": 0.4247,
      "step": 62204
    },
    {
      "epoch": 1.9108837895124873,
      "grad_norm": 0.4678042232990265,
      "learning_rate": 9.818512751678555e-08,
      "loss": 0.495,
      "step": 62205
    },
    {
      "epoch": 1.9109145086474366,
      "grad_norm": 0.4385957717895508,
      "learning_rate": 9.811758281595752e-08,
      "loss": 0.511,
      "step": 62206
    },
    {
      "epoch": 1.9109452277823857,
      "grad_norm": 0.7719908356666565,
      "learning_rate": 9.805006124166572e-08,
      "loss": 0.4634,
      "step": 62207
    },
    {
      "epoch": 1.9109759469173349,
      "grad_norm": 0.4395013749599457,
      "learning_rate": 9.798256279407115e-08,
      "loss": 0.5428,
      "step": 62208
    },
    {
      "epoch": 1.911006666052284,
      "grad_norm": 0.4197196364402771,
      "learning_rate": 9.791508747332924e-08,
      "loss": 0.5349,
      "step": 62209
    },
    {
      "epoch": 1.911037385187233,
      "grad_norm": 0.43254297971725464,
      "learning_rate": 9.784763527959984e-08,
      "loss": 0.489,
      "step": 62210
    },
    {
      "epoch": 1.9110681043221822,
      "grad_norm": 0.6663923859596252,
      "learning_rate": 9.77802062130373e-08,
      "loss": 0.4599,
      "step": 62211
    },
    {
      "epoch": 1.9110988234571313,
      "grad_norm": 0.419741690158844,
      "learning_rate": 9.771280027380037e-08,
      "loss": 0.5961,
      "step": 62212
    },
    {
      "epoch": 1.9111295425920805,
      "grad_norm": 0.505255401134491,
      "learning_rate": 9.76454174620467e-08,
      "loss": 0.4627,
      "step": 62213
    },
    {
      "epoch": 1.9111602617270298,
      "grad_norm": 0.5298225283622742,
      "learning_rate": 9.757805777793505e-08,
      "loss": 0.4876,
      "step": 62214
    },
    {
      "epoch": 1.911190980861979,
      "grad_norm": 0.4300820231437683,
      "learning_rate": 9.751072122162086e-08,
      "loss": 0.5058,
      "step": 62215
    },
    {
      "epoch": 1.911221699996928,
      "grad_norm": 0.46019113063812256,
      "learning_rate": 9.744340779326066e-08,
      "loss": 0.4692,
      "step": 62216
    },
    {
      "epoch": 1.9112524191318774,
      "grad_norm": 0.4670567512512207,
      "learning_rate": 9.737611749301435e-08,
      "loss": 0.5294,
      "step": 62217
    },
    {
      "epoch": 1.9112831382668265,
      "grad_norm": 0.39267078042030334,
      "learning_rate": 9.730885032103843e-08,
      "loss": 0.3773,
      "step": 62218
    },
    {
      "epoch": 1.9113138574017756,
      "grad_norm": 0.46116456389427185,
      "learning_rate": 9.724160627748724e-08,
      "loss": 0.4804,
      "step": 62219
    },
    {
      "epoch": 1.9113445765367247,
      "grad_norm": 0.40796446800231934,
      "learning_rate": 9.717438536252067e-08,
      "loss": 0.4155,
      "step": 62220
    },
    {
      "epoch": 1.9113752956716739,
      "grad_norm": 0.43113377690315247,
      "learning_rate": 9.710718757629522e-08,
      "loss": 0.4584,
      "step": 62221
    },
    {
      "epoch": 1.911406014806623,
      "grad_norm": 0.40639710426330566,
      "learning_rate": 9.704001291896859e-08,
      "loss": 0.4618,
      "step": 62222
    },
    {
      "epoch": 1.911436733941572,
      "grad_norm": 0.5010818243026733,
      "learning_rate": 9.697286139069506e-08,
      "loss": 0.4586,
      "step": 62223
    },
    {
      "epoch": 1.9114674530765212,
      "grad_norm": 0.4165583848953247,
      "learning_rate": 9.690573299163341e-08,
      "loss": 0.4839,
      "step": 62224
    },
    {
      "epoch": 1.9114981722114706,
      "grad_norm": 0.4278632402420044,
      "learning_rate": 9.683862772194019e-08,
      "loss": 0.4568,
      "step": 62225
    },
    {
      "epoch": 1.9115288913464197,
      "grad_norm": 0.4013466536998749,
      "learning_rate": 9.677154558177193e-08,
      "loss": 0.4411,
      "step": 62226
    },
    {
      "epoch": 1.9115596104813688,
      "grad_norm": 0.41749879717826843,
      "learning_rate": 9.670448657128518e-08,
      "loss": 0.4911,
      "step": 62227
    },
    {
      "epoch": 1.9115903296163181,
      "grad_norm": 0.4800380766391754,
      "learning_rate": 9.663745069063756e-08,
      "loss": 0.5103,
      "step": 62228
    },
    {
      "epoch": 1.9116210487512673,
      "grad_norm": 0.4085664451122284,
      "learning_rate": 9.657043793998344e-08,
      "loss": 0.5319,
      "step": 62229
    },
    {
      "epoch": 1.9116517678862164,
      "grad_norm": 0.44209539890289307,
      "learning_rate": 9.650344831948156e-08,
      "loss": 0.483,
      "step": 62230
    },
    {
      "epoch": 1.9116824870211655,
      "grad_norm": 0.4210296869277954,
      "learning_rate": 9.643648182928733e-08,
      "loss": 0.5586,
      "step": 62231
    },
    {
      "epoch": 1.9117132061561146,
      "grad_norm": 0.47873443365097046,
      "learning_rate": 9.636953846955732e-08,
      "loss": 0.4906,
      "step": 62232
    },
    {
      "epoch": 1.9117439252910637,
      "grad_norm": 0.40516799688339233,
      "learning_rate": 9.630261824044918e-08,
      "loss": 0.386,
      "step": 62233
    },
    {
      "epoch": 1.9117746444260129,
      "grad_norm": 0.4645533859729767,
      "learning_rate": 9.62357211421161e-08,
      "loss": 0.4639,
      "step": 62234
    },
    {
      "epoch": 1.911805363560962,
      "grad_norm": 0.449326753616333,
      "learning_rate": 9.616884717471686e-08,
      "loss": 0.5258,
      "step": 62235
    },
    {
      "epoch": 1.9118360826959113,
      "grad_norm": 0.5725551247596741,
      "learning_rate": 9.610199633840689e-08,
      "loss": 0.3829,
      "step": 62236
    },
    {
      "epoch": 1.9118668018308604,
      "grad_norm": 0.4281039535999298,
      "learning_rate": 9.603516863334272e-08,
      "loss": 0.4691,
      "step": 62237
    },
    {
      "epoch": 1.9118975209658096,
      "grad_norm": 0.47155898809432983,
      "learning_rate": 9.59683640596798e-08,
      "loss": 0.5228,
      "step": 62238
    },
    {
      "epoch": 1.911928240100759,
      "grad_norm": 0.40630459785461426,
      "learning_rate": 9.590158261757465e-08,
      "loss": 0.4552,
      "step": 62239
    },
    {
      "epoch": 1.911958959235708,
      "grad_norm": 0.42482781410217285,
      "learning_rate": 9.583482430718271e-08,
      "loss": 0.4414,
      "step": 62240
    },
    {
      "epoch": 1.9119896783706571,
      "grad_norm": 0.43638888001441956,
      "learning_rate": 9.576808912866054e-08,
      "loss": 0.4302,
      "step": 62241
    },
    {
      "epoch": 1.9120203975056063,
      "grad_norm": 0.42161768674850464,
      "learning_rate": 9.570137708216354e-08,
      "loss": 0.4835,
      "step": 62242
    },
    {
      "epoch": 1.9120511166405554,
      "grad_norm": 0.43146222829818726,
      "learning_rate": 9.563468816784715e-08,
      "loss": 0.4775,
      "step": 62243
    },
    {
      "epoch": 1.9120818357755045,
      "grad_norm": 0.48131194710731506,
      "learning_rate": 9.556802238586794e-08,
      "loss": 0.4429,
      "step": 62244
    },
    {
      "epoch": 1.9121125549104536,
      "grad_norm": 0.47118377685546875,
      "learning_rate": 9.55013797363824e-08,
      "loss": 0.4554,
      "step": 62245
    },
    {
      "epoch": 1.9121432740454027,
      "grad_norm": 0.44114527106285095,
      "learning_rate": 9.543476021954379e-08,
      "loss": 0.4473,
      "step": 62246
    },
    {
      "epoch": 1.912173993180352,
      "grad_norm": 0.42522671818733215,
      "learning_rate": 9.536816383550973e-08,
      "loss": 0.4325,
      "step": 62247
    },
    {
      "epoch": 1.9122047123153012,
      "grad_norm": 0.39849939942359924,
      "learning_rate": 9.530159058443456e-08,
      "loss": 0.4594,
      "step": 62248
    },
    {
      "epoch": 1.9122354314502503,
      "grad_norm": 0.4668835997581482,
      "learning_rate": 9.52350404664748e-08,
      "loss": 0.4656,
      "step": 62249
    },
    {
      "epoch": 1.9122661505851997,
      "grad_norm": 0.47754010558128357,
      "learning_rate": 9.516851348178591e-08,
      "loss": 0.4818,
      "step": 62250
    },
    {
      "epoch": 1.9122968697201488,
      "grad_norm": 0.47432741522789,
      "learning_rate": 9.510200963052108e-08,
      "loss": 0.5149,
      "step": 62251
    },
    {
      "epoch": 1.912327588855098,
      "grad_norm": 0.5237373113632202,
      "learning_rate": 9.503552891283796e-08,
      "loss": 0.4306,
      "step": 62252
    },
    {
      "epoch": 1.912358307990047,
      "grad_norm": 0.43478676676750183,
      "learning_rate": 9.496907132889088e-08,
      "loss": 0.3929,
      "step": 62253
    },
    {
      "epoch": 1.9123890271249961,
      "grad_norm": 0.47093743085861206,
      "learning_rate": 9.490263687883639e-08,
      "loss": 0.4765,
      "step": 62254
    },
    {
      "epoch": 1.9124197462599453,
      "grad_norm": 0.4486113488674164,
      "learning_rate": 9.483622556282768e-08,
      "loss": 0.5206,
      "step": 62255
    },
    {
      "epoch": 1.9124504653948944,
      "grad_norm": 0.43240025639533997,
      "learning_rate": 9.47698373810213e-08,
      "loss": 0.4798,
      "step": 62256
    },
    {
      "epoch": 1.9124811845298435,
      "grad_norm": 0.45297443866729736,
      "learning_rate": 9.470347233357047e-08,
      "loss": 0.4881,
      "step": 62257
    },
    {
      "epoch": 1.9125119036647928,
      "grad_norm": 0.43587416410446167,
      "learning_rate": 9.463713042063283e-08,
      "loss": 0.4864,
      "step": 62258
    },
    {
      "epoch": 1.912542622799742,
      "grad_norm": 0.47703710198402405,
      "learning_rate": 9.457081164236159e-08,
      "loss": 0.4514,
      "step": 62259
    },
    {
      "epoch": 1.912573341934691,
      "grad_norm": 0.44846633076667786,
      "learning_rate": 9.45045159989122e-08,
      "loss": 0.546,
      "step": 62260
    },
    {
      "epoch": 1.9126040610696404,
      "grad_norm": 0.49273258447647095,
      "learning_rate": 9.443824349043784e-08,
      "loss": 0.5403,
      "step": 62261
    },
    {
      "epoch": 1.9126347802045895,
      "grad_norm": 0.4309461712837219,
      "learning_rate": 9.437199411709619e-08,
      "loss": 0.5253,
      "step": 62262
    },
    {
      "epoch": 1.9126654993395387,
      "grad_norm": 0.4275226294994354,
      "learning_rate": 9.430576787904044e-08,
      "loss": 0.4225,
      "step": 62263
    },
    {
      "epoch": 1.9126962184744878,
      "grad_norm": 0.41022029519081116,
      "learning_rate": 9.423956477642492e-08,
      "loss": 0.4383,
      "step": 62264
    },
    {
      "epoch": 1.912726937609437,
      "grad_norm": 0.5047590136528015,
      "learning_rate": 9.417338480940619e-08,
      "loss": 0.4967,
      "step": 62265
    },
    {
      "epoch": 1.912757656744386,
      "grad_norm": 0.43480145931243896,
      "learning_rate": 9.410722797813521e-08,
      "loss": 0.4763,
      "step": 62266
    },
    {
      "epoch": 1.9127883758793351,
      "grad_norm": 0.44404345750808716,
      "learning_rate": 9.404109428276964e-08,
      "loss": 0.3994,
      "step": 62267
    },
    {
      "epoch": 1.9128190950142843,
      "grad_norm": 0.48091012239456177,
      "learning_rate": 9.39749837234627e-08,
      "loss": 0.3998,
      "step": 62268
    },
    {
      "epoch": 1.9128498141492336,
      "grad_norm": 0.4035649001598358,
      "learning_rate": 9.390889630036981e-08,
      "loss": 0.4546,
      "step": 62269
    },
    {
      "epoch": 1.9128805332841827,
      "grad_norm": 0.43682926893234253,
      "learning_rate": 9.384283201364308e-08,
      "loss": 0.4413,
      "step": 62270
    },
    {
      "epoch": 1.9129112524191318,
      "grad_norm": 0.4797583222389221,
      "learning_rate": 9.377679086343905e-08,
      "loss": 0.4835,
      "step": 62271
    },
    {
      "epoch": 1.9129419715540812,
      "grad_norm": 0.42545950412750244,
      "learning_rate": 9.371077284991092e-08,
      "loss": 0.4727,
      "step": 62272
    },
    {
      "epoch": 1.9129726906890303,
      "grad_norm": 0.44389015436172485,
      "learning_rate": 9.364477797321414e-08,
      "loss": 0.3992,
      "step": 62273
    },
    {
      "epoch": 1.9130034098239794,
      "grad_norm": 0.42151376605033875,
      "learning_rate": 9.35788062335008e-08,
      "loss": 0.4536,
      "step": 62274
    },
    {
      "epoch": 1.9130341289589285,
      "grad_norm": 0.4371093213558197,
      "learning_rate": 9.351285763092633e-08,
      "loss": 0.4383,
      "step": 62275
    },
    {
      "epoch": 1.9130648480938777,
      "grad_norm": 0.47321560978889465,
      "learning_rate": 9.344693216564393e-08,
      "loss": 0.4677,
      "step": 62276
    },
    {
      "epoch": 1.9130955672288268,
      "grad_norm": 0.42074671387672424,
      "learning_rate": 9.338102983780906e-08,
      "loss": 0.4256,
      "step": 62277
    },
    {
      "epoch": 1.913126286363776,
      "grad_norm": 0.45658764243125916,
      "learning_rate": 9.331515064757379e-08,
      "loss": 0.4628,
      "step": 62278
    },
    {
      "epoch": 1.913157005498725,
      "grad_norm": 0.4139512777328491,
      "learning_rate": 9.324929459509247e-08,
      "loss": 0.5641,
      "step": 62279
    },
    {
      "epoch": 1.9131877246336744,
      "grad_norm": 0.4782894551753998,
      "learning_rate": 9.318346168052051e-08,
      "loss": 0.4112,
      "step": 62280
    },
    {
      "epoch": 1.9132184437686235,
      "grad_norm": 0.42620331048965454,
      "learning_rate": 9.311765190401001e-08,
      "loss": 0.4668,
      "step": 62281
    },
    {
      "epoch": 1.9132491629035726,
      "grad_norm": 0.42912551760673523,
      "learning_rate": 9.30518652657153e-08,
      "loss": 0.4089,
      "step": 62282
    },
    {
      "epoch": 1.913279882038522,
      "grad_norm": 0.4351370930671692,
      "learning_rate": 9.298610176578959e-08,
      "loss": 0.4582,
      "step": 62283
    },
    {
      "epoch": 1.913310601173471,
      "grad_norm": 0.4621914327144623,
      "learning_rate": 9.292036140438609e-08,
      "loss": 0.5594,
      "step": 62284
    },
    {
      "epoch": 1.9133413203084202,
      "grad_norm": 0.4500184953212738,
      "learning_rate": 9.285464418166023e-08,
      "loss": 0.4543,
      "step": 62285
    },
    {
      "epoch": 1.9133720394433693,
      "grad_norm": 0.4666847288608551,
      "learning_rate": 9.278895009776412e-08,
      "loss": 0.4611,
      "step": 62286
    },
    {
      "epoch": 1.9134027585783184,
      "grad_norm": 0.40631476044654846,
      "learning_rate": 9.272327915284984e-08,
      "loss": 0.4209,
      "step": 62287
    },
    {
      "epoch": 1.9134334777132675,
      "grad_norm": 0.4667183756828308,
      "learning_rate": 9.265763134707395e-08,
      "loss": 0.5287,
      "step": 62288
    },
    {
      "epoch": 1.9134641968482167,
      "grad_norm": 0.41262686252593994,
      "learning_rate": 9.259200668058743e-08,
      "loss": 0.4901,
      "step": 62289
    },
    {
      "epoch": 1.9134949159831658,
      "grad_norm": 0.5890456438064575,
      "learning_rate": 9.25264051535446e-08,
      "loss": 0.5011,
      "step": 62290
    },
    {
      "epoch": 1.913525635118115,
      "grad_norm": 0.6058325171470642,
      "learning_rate": 9.246082676609757e-08,
      "loss": 0.5101,
      "step": 62291
    },
    {
      "epoch": 1.9135563542530643,
      "grad_norm": 0.4557623565196991,
      "learning_rate": 9.239527151840066e-08,
      "loss": 0.3802,
      "step": 62292
    },
    {
      "epoch": 1.9135870733880134,
      "grad_norm": 0.4480057656764984,
      "learning_rate": 9.232973941060597e-08,
      "loss": 0.3789,
      "step": 62293
    },
    {
      "epoch": 1.9136177925229627,
      "grad_norm": 0.42247897386550903,
      "learning_rate": 9.226423044286781e-08,
      "loss": 0.5276,
      "step": 62294
    },
    {
      "epoch": 1.9136485116579118,
      "grad_norm": 0.4231855571269989,
      "learning_rate": 9.219874461533828e-08,
      "loss": 0.4827,
      "step": 62295
    },
    {
      "epoch": 1.913679230792861,
      "grad_norm": 0.4203192889690399,
      "learning_rate": 9.213328192817061e-08,
      "loss": 0.4608,
      "step": 62296
    },
    {
      "epoch": 1.91370994992781,
      "grad_norm": 0.5100272297859192,
      "learning_rate": 9.20678423815169e-08,
      "loss": 0.4536,
      "step": 62297
    },
    {
      "epoch": 1.9137406690627592,
      "grad_norm": 0.4105132520198822,
      "learning_rate": 9.200242597553144e-08,
      "loss": 0.4719,
      "step": 62298
    },
    {
      "epoch": 1.9137713881977083,
      "grad_norm": 0.4419453740119934,
      "learning_rate": 9.193703271036636e-08,
      "loss": 0.4554,
      "step": 62299
    },
    {
      "epoch": 1.9138021073326574,
      "grad_norm": 0.3879900574684143,
      "learning_rate": 9.187166258617375e-08,
      "loss": 0.4787,
      "step": 62300
    },
    {
      "epoch": 1.9138328264676066,
      "grad_norm": 0.4681704044342041,
      "learning_rate": 9.180631560310793e-08,
      "loss": 0.4689,
      "step": 62301
    },
    {
      "epoch": 1.9138635456025557,
      "grad_norm": 0.40417060256004333,
      "learning_rate": 9.174099176131879e-08,
      "loss": 0.4002,
      "step": 62302
    },
    {
      "epoch": 1.913894264737505,
      "grad_norm": 0.42279213666915894,
      "learning_rate": 9.167569106096175e-08,
      "loss": 0.4989,
      "step": 62303
    },
    {
      "epoch": 1.9139249838724541,
      "grad_norm": 0.4284682869911194,
      "learning_rate": 9.16104135021878e-08,
      "loss": 0.4433,
      "step": 62304
    },
    {
      "epoch": 1.9139557030074035,
      "grad_norm": 0.43690764904022217,
      "learning_rate": 9.154515908515016e-08,
      "loss": 0.4828,
      "step": 62305
    },
    {
      "epoch": 1.9139864221423526,
      "grad_norm": 0.44586849212646484,
      "learning_rate": 9.147992781000093e-08,
      "loss": 0.456,
      "step": 62306
    },
    {
      "epoch": 1.9140171412773017,
      "grad_norm": 0.41797441244125366,
      "learning_rate": 9.141471967689108e-08,
      "loss": 0.5024,
      "step": 62307
    },
    {
      "epoch": 1.9140478604122508,
      "grad_norm": 0.4633602201938629,
      "learning_rate": 9.134953468597496e-08,
      "loss": 0.4328,
      "step": 62308
    },
    {
      "epoch": 1.9140785795472,
      "grad_norm": 0.4798585772514343,
      "learning_rate": 9.128437283740466e-08,
      "loss": 0.4216,
      "step": 62309
    },
    {
      "epoch": 1.914109298682149,
      "grad_norm": 0.43640923500061035,
      "learning_rate": 9.121923413133004e-08,
      "loss": 0.464,
      "step": 62310
    },
    {
      "epoch": 1.9141400178170982,
      "grad_norm": 0.4224207401275635,
      "learning_rate": 9.115411856790657e-08,
      "loss": 0.4264,
      "step": 62311
    },
    {
      "epoch": 1.9141707369520473,
      "grad_norm": 0.44216859340667725,
      "learning_rate": 9.10890261472841e-08,
      "loss": 0.4574,
      "step": 62312
    },
    {
      "epoch": 1.9142014560869964,
      "grad_norm": 0.4747024178504944,
      "learning_rate": 9.102395686961473e-08,
      "loss": 0.4278,
      "step": 62313
    },
    {
      "epoch": 1.9142321752219458,
      "grad_norm": 0.4820044934749603,
      "learning_rate": 9.09589107350517e-08,
      "loss": 0.4915,
      "step": 62314
    },
    {
      "epoch": 1.914262894356895,
      "grad_norm": 0.4727287292480469,
      "learning_rate": 9.089388774374597e-08,
      "loss": 0.3964,
      "step": 62315
    },
    {
      "epoch": 1.914293613491844,
      "grad_norm": 0.4337901771068573,
      "learning_rate": 9.082888789584854e-08,
      "loss": 0.4979,
      "step": 62316
    },
    {
      "epoch": 1.9143243326267934,
      "grad_norm": 0.42901667952537537,
      "learning_rate": 9.076391119151373e-08,
      "loss": 0.4837,
      "step": 62317
    },
    {
      "epoch": 1.9143550517617425,
      "grad_norm": 0.5003573298454285,
      "learning_rate": 9.069895763089142e-08,
      "loss": 0.48,
      "step": 62318
    },
    {
      "epoch": 1.9143857708966916,
      "grad_norm": 0.4138413071632385,
      "learning_rate": 9.063402721413372e-08,
      "loss": 0.5351,
      "step": 62319
    },
    {
      "epoch": 1.9144164900316407,
      "grad_norm": 0.46615010499954224,
      "learning_rate": 9.056911994139161e-08,
      "loss": 0.4938,
      "step": 62320
    },
    {
      "epoch": 1.9144472091665898,
      "grad_norm": 0.419856995344162,
      "learning_rate": 9.050423581281832e-08,
      "loss": 0.5182,
      "step": 62321
    },
    {
      "epoch": 1.914477928301539,
      "grad_norm": 0.46048644185066223,
      "learning_rate": 9.04393748285648e-08,
      "loss": 0.4768,
      "step": 62322
    },
    {
      "epoch": 1.914508647436488,
      "grad_norm": 0.4251938462257385,
      "learning_rate": 9.037453698878096e-08,
      "loss": 0.4849,
      "step": 62323
    },
    {
      "epoch": 1.9145393665714372,
      "grad_norm": 0.4565063714981079,
      "learning_rate": 9.030972229362e-08,
      "loss": 0.5163,
      "step": 62324
    },
    {
      "epoch": 1.9145700857063865,
      "grad_norm": 0.38887548446655273,
      "learning_rate": 9.024493074323293e-08,
      "loss": 0.4305,
      "step": 62325
    },
    {
      "epoch": 1.9146008048413357,
      "grad_norm": 0.4406951367855072,
      "learning_rate": 9.018016233777072e-08,
      "loss": 0.4568,
      "step": 62326
    },
    {
      "epoch": 1.9146315239762848,
      "grad_norm": 0.42537182569503784,
      "learning_rate": 9.011541707738547e-08,
      "loss": 0.4531,
      "step": 62327
    },
    {
      "epoch": 1.9146622431112341,
      "grad_norm": 0.4286538362503052,
      "learning_rate": 9.005069496222706e-08,
      "loss": 0.4401,
      "step": 62328
    },
    {
      "epoch": 1.9146929622461832,
      "grad_norm": 0.418310284614563,
      "learning_rate": 8.998599599244761e-08,
      "loss": 0.4976,
      "step": 62329
    },
    {
      "epoch": 1.9147236813811324,
      "grad_norm": 0.42789995670318604,
      "learning_rate": 8.99213201681981e-08,
      "loss": 0.5253,
      "step": 62330
    },
    {
      "epoch": 1.9147544005160815,
      "grad_norm": 0.48202696442604065,
      "learning_rate": 8.985666748962952e-08,
      "loss": 0.5116,
      "step": 62331
    },
    {
      "epoch": 1.9147851196510306,
      "grad_norm": 0.43843668699264526,
      "learning_rate": 8.979203795689285e-08,
      "loss": 0.4991,
      "step": 62332
    },
    {
      "epoch": 1.9148158387859797,
      "grad_norm": 0.38942474126815796,
      "learning_rate": 8.972743157013796e-08,
      "loss": 0.4079,
      "step": 62333
    },
    {
      "epoch": 1.9148465579209288,
      "grad_norm": 0.43186506628990173,
      "learning_rate": 8.9662848329517e-08,
      "loss": 0.4847,
      "step": 62334
    },
    {
      "epoch": 1.914877277055878,
      "grad_norm": 0.48809659481048584,
      "learning_rate": 8.959828823518201e-08,
      "loss": 0.5386,
      "step": 62335
    },
    {
      "epoch": 1.9149079961908273,
      "grad_norm": 0.4151598811149597,
      "learning_rate": 8.95337512872807e-08,
      "loss": 0.5091,
      "step": 62336
    },
    {
      "epoch": 1.9149387153257764,
      "grad_norm": 0.42513957619667053,
      "learning_rate": 8.946923748596626e-08,
      "loss": 0.3825,
      "step": 62337
    },
    {
      "epoch": 1.9149694344607255,
      "grad_norm": 0.46477454900741577,
      "learning_rate": 8.940474683138856e-08,
      "loss": 0.4328,
      "step": 62338
    },
    {
      "epoch": 1.9150001535956749,
      "grad_norm": 0.4727286100387573,
      "learning_rate": 8.93402793236986e-08,
      "loss": 0.441,
      "step": 62339
    },
    {
      "epoch": 1.915030872730624,
      "grad_norm": 0.3924649953842163,
      "learning_rate": 8.927583496304626e-08,
      "loss": 0.3616,
      "step": 62340
    },
    {
      "epoch": 1.9150615918655731,
      "grad_norm": 0.4757637679576874,
      "learning_rate": 8.921141374958253e-08,
      "loss": 0.4896,
      "step": 62341
    },
    {
      "epoch": 1.9150923110005222,
      "grad_norm": 0.4305652976036072,
      "learning_rate": 8.914701568345729e-08,
      "loss": 0.5178,
      "step": 62342
    },
    {
      "epoch": 1.9151230301354714,
      "grad_norm": 0.4104223847389221,
      "learning_rate": 8.908264076482043e-08,
      "loss": 0.4915,
      "step": 62343
    },
    {
      "epoch": 1.9151537492704205,
      "grad_norm": 0.4254651367664337,
      "learning_rate": 8.901828899382514e-08,
      "loss": 0.54,
      "step": 62344
    },
    {
      "epoch": 1.9151844684053696,
      "grad_norm": 0.4857645332813263,
      "learning_rate": 8.89539603706191e-08,
      "loss": 0.4663,
      "step": 62345
    },
    {
      "epoch": 1.9152151875403187,
      "grad_norm": 0.4502736032009125,
      "learning_rate": 8.888965489535328e-08,
      "loss": 0.4921,
      "step": 62346
    },
    {
      "epoch": 1.915245906675268,
      "grad_norm": 0.4696334898471832,
      "learning_rate": 8.882537256817758e-08,
      "loss": 0.4888,
      "step": 62347
    },
    {
      "epoch": 1.9152766258102172,
      "grad_norm": 0.47653728723526,
      "learning_rate": 8.876111338924188e-08,
      "loss": 0.4859,
      "step": 62348
    },
    {
      "epoch": 1.9153073449451663,
      "grad_norm": 0.4085598886013031,
      "learning_rate": 8.869687735869825e-08,
      "loss": 0.4366,
      "step": 62349
    },
    {
      "epoch": 1.9153380640801156,
      "grad_norm": 0.4001730680465698,
      "learning_rate": 8.863266447669439e-08,
      "loss": 0.3214,
      "step": 62350
    },
    {
      "epoch": 1.9153687832150648,
      "grad_norm": 0.4149506688117981,
      "learning_rate": 8.856847474338015e-08,
      "loss": 0.4579,
      "step": 62351
    },
    {
      "epoch": 1.9153995023500139,
      "grad_norm": 0.5253308415412903,
      "learning_rate": 8.850430815890764e-08,
      "loss": 0.4888,
      "step": 62352
    },
    {
      "epoch": 1.915430221484963,
      "grad_norm": 0.4585152268409729,
      "learning_rate": 8.844016472342564e-08,
      "loss": 0.443,
      "step": 62353
    },
    {
      "epoch": 1.9154609406199121,
      "grad_norm": 0.4701944589614868,
      "learning_rate": 8.837604443708403e-08,
      "loss": 0.4847,
      "step": 62354
    },
    {
      "epoch": 1.9154916597548612,
      "grad_norm": 0.4344731569290161,
      "learning_rate": 8.831194730003156e-08,
      "loss": 0.4582,
      "step": 62355
    },
    {
      "epoch": 1.9155223788898104,
      "grad_norm": 0.4190385043621063,
      "learning_rate": 8.824787331241923e-08,
      "loss": 0.4542,
      "step": 62356
    },
    {
      "epoch": 1.9155530980247595,
      "grad_norm": 0.512420654296875,
      "learning_rate": 8.818382247439583e-08,
      "loss": 0.4738,
      "step": 62357
    },
    {
      "epoch": 1.9155838171597088,
      "grad_norm": 0.4329656958580017,
      "learning_rate": 8.811979478611232e-08,
      "loss": 0.4453,
      "step": 62358
    },
    {
      "epoch": 1.915614536294658,
      "grad_norm": 0.452501505613327,
      "learning_rate": 8.805579024771637e-08,
      "loss": 0.451,
      "step": 62359
    },
    {
      "epoch": 1.915645255429607,
      "grad_norm": 0.5344280004501343,
      "learning_rate": 8.799180885935788e-08,
      "loss": 0.4528,
      "step": 62360
    },
    {
      "epoch": 1.9156759745645564,
      "grad_norm": 0.45883023738861084,
      "learning_rate": 8.79278506211878e-08,
      "loss": 0.5131,
      "step": 62361
    },
    {
      "epoch": 1.9157066936995055,
      "grad_norm": 0.4361497163772583,
      "learning_rate": 8.786391553335494e-08,
      "loss": 0.402,
      "step": 62362
    },
    {
      "epoch": 1.9157374128344546,
      "grad_norm": 0.4225817024707794,
      "learning_rate": 8.780000359600693e-08,
      "loss": 0.5342,
      "step": 62363
    },
    {
      "epoch": 1.9157681319694038,
      "grad_norm": 0.45425257086753845,
      "learning_rate": 8.773611480929479e-08,
      "loss": 0.4536,
      "step": 62364
    },
    {
      "epoch": 1.9157988511043529,
      "grad_norm": 0.42469340562820435,
      "learning_rate": 8.767224917336726e-08,
      "loss": 0.4517,
      "step": 62365
    },
    {
      "epoch": 1.915829570239302,
      "grad_norm": 0.4303809106349945,
      "learning_rate": 8.760840668837312e-08,
      "loss": 0.4754,
      "step": 62366
    },
    {
      "epoch": 1.9158602893742511,
      "grad_norm": 0.3997362554073334,
      "learning_rate": 8.754458735446225e-08,
      "loss": 0.4798,
      "step": 62367
    },
    {
      "epoch": 1.9158910085092002,
      "grad_norm": 0.5043231844902039,
      "learning_rate": 8.748079117178343e-08,
      "loss": 0.4242,
      "step": 62368
    },
    {
      "epoch": 1.9159217276441496,
      "grad_norm": 0.4259348511695862,
      "learning_rate": 8.741701814048542e-08,
      "loss": 0.4447,
      "step": 62369
    },
    {
      "epoch": 1.9159524467790987,
      "grad_norm": 0.42307865619659424,
      "learning_rate": 8.735326826071589e-08,
      "loss": 0.5367,
      "step": 62370
    },
    {
      "epoch": 1.9159831659140478,
      "grad_norm": 0.40158525109291077,
      "learning_rate": 8.728954153262692e-08,
      "loss": 0.4044,
      "step": 62371
    },
    {
      "epoch": 1.9160138850489972,
      "grad_norm": 0.408180832862854,
      "learning_rate": 8.722583795636397e-08,
      "loss": 0.4802,
      "step": 62372
    },
    {
      "epoch": 1.9160446041839463,
      "grad_norm": 0.4108063578605652,
      "learning_rate": 8.716215753207912e-08,
      "loss": 0.4695,
      "step": 62373
    },
    {
      "epoch": 1.9160753233188954,
      "grad_norm": 0.414379745721817,
      "learning_rate": 8.709850025991783e-08,
      "loss": 0.4388,
      "step": 62374
    },
    {
      "epoch": 1.9161060424538445,
      "grad_norm": 0.43256476521492004,
      "learning_rate": 8.703486614003109e-08,
      "loss": 0.4608,
      "step": 62375
    },
    {
      "epoch": 1.9161367615887936,
      "grad_norm": 0.517734169960022,
      "learning_rate": 8.697125517256656e-08,
      "loss": 0.5289,
      "step": 62376
    },
    {
      "epoch": 1.9161674807237428,
      "grad_norm": 0.42523816227912903,
      "learning_rate": 8.690766735767297e-08,
      "loss": 0.4306,
      "step": 62377
    },
    {
      "epoch": 1.9161981998586919,
      "grad_norm": 0.4788074195384979,
      "learning_rate": 8.684410269549914e-08,
      "loss": 0.408,
      "step": 62378
    },
    {
      "epoch": 1.916228918993641,
      "grad_norm": 0.4208643138408661,
      "learning_rate": 8.678056118619271e-08,
      "loss": 0.4229,
      "step": 62379
    },
    {
      "epoch": 1.9162596381285903,
      "grad_norm": 0.45928871631622314,
      "learning_rate": 8.671704282990245e-08,
      "loss": 0.5155,
      "step": 62380
    },
    {
      "epoch": 1.9162903572635395,
      "grad_norm": 0.4682610332965851,
      "learning_rate": 8.665354762677824e-08,
      "loss": 0.4582,
      "step": 62381
    },
    {
      "epoch": 1.9163210763984886,
      "grad_norm": 0.43724876642227173,
      "learning_rate": 8.659007557696552e-08,
      "loss": 0.4295,
      "step": 62382
    },
    {
      "epoch": 1.916351795533438,
      "grad_norm": 0.3995078206062317,
      "learning_rate": 8.652662668061418e-08,
      "loss": 0.4719,
      "step": 62383
    },
    {
      "epoch": 1.916382514668387,
      "grad_norm": 0.40545105934143066,
      "learning_rate": 8.646320093787296e-08,
      "loss": 0.4535,
      "step": 62384
    },
    {
      "epoch": 1.9164132338033362,
      "grad_norm": 0.46086591482162476,
      "learning_rate": 8.639979834888956e-08,
      "loss": 0.4946,
      "step": 62385
    },
    {
      "epoch": 1.9164439529382853,
      "grad_norm": 0.46856889128685,
      "learning_rate": 8.63364189138105e-08,
      "loss": 0.5089,
      "step": 62386
    },
    {
      "epoch": 1.9164746720732344,
      "grad_norm": 0.41651687026023865,
      "learning_rate": 8.627306263278567e-08,
      "loss": 0.4897,
      "step": 62387
    },
    {
      "epoch": 1.9165053912081835,
      "grad_norm": 0.4358150064945221,
      "learning_rate": 8.620972950596274e-08,
      "loss": 0.4749,
      "step": 62388
    },
    {
      "epoch": 1.9165361103431326,
      "grad_norm": 0.44448596239089966,
      "learning_rate": 8.614641953348824e-08,
      "loss": 0.5374,
      "step": 62389
    },
    {
      "epoch": 1.9165668294780818,
      "grad_norm": 0.4427816569805145,
      "learning_rate": 8.608313271551317e-08,
      "loss": 0.4545,
      "step": 62390
    },
    {
      "epoch": 1.916597548613031,
      "grad_norm": 0.43736207485198975,
      "learning_rate": 8.601986905218185e-08,
      "loss": 0.4978,
      "step": 62391
    },
    {
      "epoch": 1.9166282677479802,
      "grad_norm": 0.4500397741794586,
      "learning_rate": 8.595662854364418e-08,
      "loss": 0.4878,
      "step": 62392
    },
    {
      "epoch": 1.9166589868829293,
      "grad_norm": 0.45606064796447754,
      "learning_rate": 8.589341119004669e-08,
      "loss": 0.507,
      "step": 62393
    },
    {
      "epoch": 1.9166897060178787,
      "grad_norm": 0.4496071934700012,
      "learning_rate": 8.583021699153816e-08,
      "loss": 0.4327,
      "step": 62394
    },
    {
      "epoch": 1.9167204251528278,
      "grad_norm": 0.45189526677131653,
      "learning_rate": 8.576704594826513e-08,
      "loss": 0.5233,
      "step": 62395
    },
    {
      "epoch": 1.916751144287777,
      "grad_norm": 2.726825475692749,
      "learning_rate": 8.570389806037526e-08,
      "loss": 0.4658,
      "step": 62396
    },
    {
      "epoch": 1.916781863422726,
      "grad_norm": 0.42639172077178955,
      "learning_rate": 8.564077332801624e-08,
      "loss": 0.4524,
      "step": 62397
    },
    {
      "epoch": 1.9168125825576752,
      "grad_norm": 0.45621782541275024,
      "learning_rate": 8.55776717513368e-08,
      "loss": 0.4976,
      "step": 62398
    },
    {
      "epoch": 1.9168433016926243,
      "grad_norm": 0.4307362735271454,
      "learning_rate": 8.55145933304824e-08,
      "loss": 0.4664,
      "step": 62399
    },
    {
      "epoch": 1.9168740208275734,
      "grad_norm": 0.41621696949005127,
      "learning_rate": 8.54515380656007e-08,
      "loss": 0.5625,
      "step": 62400
    },
    {
      "epoch": 1.9169047399625225,
      "grad_norm": 0.4060206413269043,
      "learning_rate": 8.538850595683934e-08,
      "loss": 0.5114,
      "step": 62401
    },
    {
      "epoch": 1.9169354590974717,
      "grad_norm": 0.40829169750213623,
      "learning_rate": 8.5325497004346e-08,
      "loss": 0.4662,
      "step": 62402
    },
    {
      "epoch": 1.916966178232421,
      "grad_norm": 0.4136354923248291,
      "learning_rate": 8.526251120826723e-08,
      "loss": 0.5312,
      "step": 62403
    },
    {
      "epoch": 1.9169968973673701,
      "grad_norm": 0.4798235297203064,
      "learning_rate": 8.519954856875178e-08,
      "loss": 0.4768,
      "step": 62404
    },
    {
      "epoch": 1.9170276165023195,
      "grad_norm": 0.48387810587882996,
      "learning_rate": 8.51366090859429e-08,
      "loss": 0.4746,
      "step": 62405
    },
    {
      "epoch": 1.9170583356372686,
      "grad_norm": 0.4542696475982666,
      "learning_rate": 8.507369275999044e-08,
      "loss": 0.4807,
      "step": 62406
    },
    {
      "epoch": 1.9170890547722177,
      "grad_norm": 0.4888879358768463,
      "learning_rate": 8.501079959104209e-08,
      "loss": 0.4323,
      "step": 62407
    },
    {
      "epoch": 1.9171197739071668,
      "grad_norm": 0.4206877052783966,
      "learning_rate": 8.494792957924214e-08,
      "loss": 0.5549,
      "step": 62408
    },
    {
      "epoch": 1.917150493042116,
      "grad_norm": 0.44594570994377136,
      "learning_rate": 8.488508272473939e-08,
      "loss": 0.4555,
      "step": 62409
    },
    {
      "epoch": 1.917181212177065,
      "grad_norm": 0.4036165177822113,
      "learning_rate": 8.482225902768038e-08,
      "loss": 0.4312,
      "step": 62410
    },
    {
      "epoch": 1.9172119313120142,
      "grad_norm": 0.4891892969608307,
      "learning_rate": 8.475945848821054e-08,
      "loss": 0.4311,
      "step": 62411
    },
    {
      "epoch": 1.9172426504469633,
      "grad_norm": 0.5019199848175049,
      "learning_rate": 8.469668110647755e-08,
      "loss": 0.5574,
      "step": 62412
    },
    {
      "epoch": 1.9172733695819124,
      "grad_norm": 0.41959235072135925,
      "learning_rate": 8.463392688262794e-08,
      "loss": 0.4486,
      "step": 62413
    },
    {
      "epoch": 1.9173040887168618,
      "grad_norm": 0.49652785062789917,
      "learning_rate": 8.45711958168094e-08,
      "loss": 0.5084,
      "step": 62414
    },
    {
      "epoch": 1.9173348078518109,
      "grad_norm": 0.43435293436050415,
      "learning_rate": 8.450848790916621e-08,
      "loss": 0.4799,
      "step": 62415
    },
    {
      "epoch": 1.9173655269867602,
      "grad_norm": 0.45501774549484253,
      "learning_rate": 8.444580315984608e-08,
      "loss": 0.5612,
      "step": 62416
    },
    {
      "epoch": 1.9173962461217093,
      "grad_norm": 0.47225168347358704,
      "learning_rate": 8.438314156899552e-08,
      "loss": 0.434,
      "step": 62417
    },
    {
      "epoch": 1.9174269652566585,
      "grad_norm": 0.42601278424263,
      "learning_rate": 8.432050313676e-08,
      "loss": 0.3956,
      "step": 62418
    },
    {
      "epoch": 1.9174576843916076,
      "grad_norm": 0.4586000144481659,
      "learning_rate": 8.425788786328715e-08,
      "loss": 0.4271,
      "step": 62419
    },
    {
      "epoch": 1.9174884035265567,
      "grad_norm": 0.4250621497631073,
      "learning_rate": 8.419529574872243e-08,
      "loss": 0.3699,
      "step": 62420
    },
    {
      "epoch": 1.9175191226615058,
      "grad_norm": 0.422069251537323,
      "learning_rate": 8.413272679321238e-08,
      "loss": 0.5008,
      "step": 62421
    },
    {
      "epoch": 1.917549841796455,
      "grad_norm": 0.5860447883605957,
      "learning_rate": 8.407018099690245e-08,
      "loss": 0.4685,
      "step": 62422
    },
    {
      "epoch": 1.917580560931404,
      "grad_norm": 0.4485166668891907,
      "learning_rate": 8.400765835993807e-08,
      "loss": 0.3764,
      "step": 62423
    },
    {
      "epoch": 1.9176112800663532,
      "grad_norm": 0.436144083738327,
      "learning_rate": 8.394515888246802e-08,
      "loss": 0.395,
      "step": 62424
    },
    {
      "epoch": 1.9176419992013025,
      "grad_norm": 0.41111087799072266,
      "learning_rate": 8.388268256463549e-08,
      "loss": 0.461,
      "step": 62425
    },
    {
      "epoch": 1.9176727183362516,
      "grad_norm": 0.406610369682312,
      "learning_rate": 8.382022940658818e-08,
      "loss": 0.4393,
      "step": 62426
    },
    {
      "epoch": 1.9177034374712008,
      "grad_norm": 0.46627965569496155,
      "learning_rate": 8.37577994084715e-08,
      "loss": 0.438,
      "step": 62427
    },
    {
      "epoch": 1.91773415660615,
      "grad_norm": 0.5212734341621399,
      "learning_rate": 8.36953925704298e-08,
      "loss": 0.4465,
      "step": 62428
    },
    {
      "epoch": 1.9177648757410992,
      "grad_norm": 0.4684416949748993,
      "learning_rate": 8.363300889261073e-08,
      "loss": 0.4575,
      "step": 62429
    },
    {
      "epoch": 1.9177955948760483,
      "grad_norm": 0.4342278242111206,
      "learning_rate": 8.357064837515971e-08,
      "loss": 0.4382,
      "step": 62430
    },
    {
      "epoch": 1.9178263140109975,
      "grad_norm": 0.4168151617050171,
      "learning_rate": 8.35083110182222e-08,
      "loss": 0.5057,
      "step": 62431
    },
    {
      "epoch": 1.9178570331459466,
      "grad_norm": 0.46449220180511475,
      "learning_rate": 8.344599682194365e-08,
      "loss": 0.4447,
      "step": 62432
    },
    {
      "epoch": 1.9178877522808957,
      "grad_norm": 0.4453720450401306,
      "learning_rate": 8.338370578646837e-08,
      "loss": 0.4722,
      "step": 62433
    },
    {
      "epoch": 1.9179184714158448,
      "grad_norm": 0.41953665018081665,
      "learning_rate": 8.332143791194403e-08,
      "loss": 0.4288,
      "step": 62434
    },
    {
      "epoch": 1.917949190550794,
      "grad_norm": 0.4580024778842926,
      "learning_rate": 8.325919319851383e-08,
      "loss": 0.5254,
      "step": 62435
    },
    {
      "epoch": 1.9179799096857433,
      "grad_norm": 0.4749591052532196,
      "learning_rate": 8.319697164632545e-08,
      "loss": 0.4724,
      "step": 62436
    },
    {
      "epoch": 1.9180106288206924,
      "grad_norm": 0.42046019434928894,
      "learning_rate": 8.31347732555221e-08,
      "loss": 0.3853,
      "step": 62437
    },
    {
      "epoch": 1.9180413479556415,
      "grad_norm": 0.4600837528705597,
      "learning_rate": 8.307259802625145e-08,
      "loss": 0.5148,
      "step": 62438
    },
    {
      "epoch": 1.9180720670905909,
      "grad_norm": 0.4468599855899811,
      "learning_rate": 8.301044595865671e-08,
      "loss": 0.4207,
      "step": 62439
    },
    {
      "epoch": 1.91810278622554,
      "grad_norm": 0.4570559859275818,
      "learning_rate": 8.294831705288442e-08,
      "loss": 0.4392,
      "step": 62440
    },
    {
      "epoch": 1.918133505360489,
      "grad_norm": 0.48426809906959534,
      "learning_rate": 8.288621130907781e-08,
      "loss": 0.4228,
      "step": 62441
    },
    {
      "epoch": 1.9181642244954382,
      "grad_norm": 0.44106775522232056,
      "learning_rate": 8.282412872738343e-08,
      "loss": 0.4639,
      "step": 62442
    },
    {
      "epoch": 1.9181949436303873,
      "grad_norm": 0.4778120815753937,
      "learning_rate": 8.276206930794561e-08,
      "loss": 0.549,
      "step": 62443
    },
    {
      "epoch": 1.9182256627653365,
      "grad_norm": 0.4203675389289856,
      "learning_rate": 8.270003305090978e-08,
      "loss": 0.4541,
      "step": 62444
    },
    {
      "epoch": 1.9182563819002856,
      "grad_norm": 0.8247986435890198,
      "learning_rate": 8.26380199564214e-08,
      "loss": 0.4273,
      "step": 62445
    },
    {
      "epoch": 1.9182871010352347,
      "grad_norm": 0.40867629647254944,
      "learning_rate": 8.257603002462367e-08,
      "loss": 0.4801,
      "step": 62446
    },
    {
      "epoch": 1.918317820170184,
      "grad_norm": 0.42675670981407166,
      "learning_rate": 8.251406325566203e-08,
      "loss": 0.507,
      "step": 62447
    },
    {
      "epoch": 1.9183485393051332,
      "grad_norm": 0.45461201667785645,
      "learning_rate": 8.245211964968192e-08,
      "loss": 0.4567,
      "step": 62448
    },
    {
      "epoch": 1.9183792584400823,
      "grad_norm": 0.4531419575214386,
      "learning_rate": 8.239019920682766e-08,
      "loss": 0.4404,
      "step": 62449
    },
    {
      "epoch": 1.9184099775750316,
      "grad_norm": 0.4860227406024933,
      "learning_rate": 8.232830192724362e-08,
      "loss": 0.5056,
      "step": 62450
    },
    {
      "epoch": 1.9184406967099807,
      "grad_norm": 0.4102603495121002,
      "learning_rate": 8.226642781107407e-08,
      "loss": 0.4458,
      "step": 62451
    },
    {
      "epoch": 1.9184714158449299,
      "grad_norm": 0.4414876699447632,
      "learning_rate": 8.22045768584645e-08,
      "loss": 0.4818,
      "step": 62452
    },
    {
      "epoch": 1.918502134979879,
      "grad_norm": 0.47808006405830383,
      "learning_rate": 8.21427490695581e-08,
      "loss": 0.461,
      "step": 62453
    },
    {
      "epoch": 1.918532854114828,
      "grad_norm": 0.47553500533103943,
      "learning_rate": 8.208094444450033e-08,
      "loss": 0.4477,
      "step": 62454
    },
    {
      "epoch": 1.9185635732497772,
      "grad_norm": 0.41386649012565613,
      "learning_rate": 8.201916298343549e-08,
      "loss": 0.5628,
      "step": 62455
    },
    {
      "epoch": 1.9185942923847263,
      "grad_norm": 0.41699373722076416,
      "learning_rate": 8.195740468650682e-08,
      "loss": 0.4612,
      "step": 62456
    },
    {
      "epoch": 1.9186250115196755,
      "grad_norm": 0.4253246486186981,
      "learning_rate": 8.189566955386085e-08,
      "loss": 0.4729,
      "step": 62457
    },
    {
      "epoch": 1.9186557306546248,
      "grad_norm": 0.4278721213340759,
      "learning_rate": 8.183395758563861e-08,
      "loss": 0.5012,
      "step": 62458
    },
    {
      "epoch": 1.918686449789574,
      "grad_norm": 0.41791602969169617,
      "learning_rate": 8.177226878198663e-08,
      "loss": 0.3923,
      "step": 62459
    },
    {
      "epoch": 1.918717168924523,
      "grad_norm": 0.43883270025253296,
      "learning_rate": 8.171060314304702e-08,
      "loss": 0.4686,
      "step": 62460
    },
    {
      "epoch": 1.9187478880594724,
      "grad_norm": 0.4549671411514282,
      "learning_rate": 8.164896066896633e-08,
      "loss": 0.5464,
      "step": 62461
    },
    {
      "epoch": 1.9187786071944215,
      "grad_norm": 0.4883158504962921,
      "learning_rate": 8.158734135988666e-08,
      "loss": 0.4613,
      "step": 62462
    },
    {
      "epoch": 1.9188093263293706,
      "grad_norm": 0.44711998105049133,
      "learning_rate": 8.152574521595236e-08,
      "loss": 0.4836,
      "step": 62463
    },
    {
      "epoch": 1.9188400454643197,
      "grad_norm": 0.48216360807418823,
      "learning_rate": 8.146417223730774e-08,
      "loss": 0.4916,
      "step": 62464
    },
    {
      "epoch": 1.9188707645992689,
      "grad_norm": 0.4217878580093384,
      "learning_rate": 8.140262242409603e-08,
      "loss": 0.44,
      "step": 62465
    },
    {
      "epoch": 1.918901483734218,
      "grad_norm": 0.4348547160625458,
      "learning_rate": 8.134109577646154e-08,
      "loss": 0.5225,
      "step": 62466
    },
    {
      "epoch": 1.918932202869167,
      "grad_norm": 0.43014585971832275,
      "learning_rate": 8.127959229454751e-08,
      "loss": 0.4517,
      "step": 62467
    },
    {
      "epoch": 1.9189629220041162,
      "grad_norm": 0.4214155375957489,
      "learning_rate": 8.121811197849827e-08,
      "loss": 0.4972,
      "step": 62468
    },
    {
      "epoch": 1.9189936411390656,
      "grad_norm": 0.4901569187641144,
      "learning_rate": 8.115665482845481e-08,
      "loss": 0.5293,
      "step": 62469
    },
    {
      "epoch": 1.9190243602740147,
      "grad_norm": 0.4457835257053375,
      "learning_rate": 8.109522084456478e-08,
      "loss": 0.3878,
      "step": 62470
    },
    {
      "epoch": 1.9190550794089638,
      "grad_norm": 0.4412463903427124,
      "learning_rate": 8.103381002696808e-08,
      "loss": 0.4049,
      "step": 62471
    },
    {
      "epoch": 1.9190857985439131,
      "grad_norm": 0.4826819896697998,
      "learning_rate": 8.097242237581126e-08,
      "loss": 0.4906,
      "step": 62472
    },
    {
      "epoch": 1.9191165176788623,
      "grad_norm": 0.4052726626396179,
      "learning_rate": 8.091105789123532e-08,
      "loss": 0.4953,
      "step": 62473
    },
    {
      "epoch": 1.9191472368138114,
      "grad_norm": 0.4556116759777069,
      "learning_rate": 8.084971657338347e-08,
      "loss": 0.4701,
      "step": 62474
    },
    {
      "epoch": 1.9191779559487605,
      "grad_norm": 0.41646522283554077,
      "learning_rate": 8.078839842240117e-08,
      "loss": 0.4488,
      "step": 62475
    },
    {
      "epoch": 1.9192086750837096,
      "grad_norm": 0.43783649802207947,
      "learning_rate": 8.072710343842937e-08,
      "loss": 0.4589,
      "step": 62476
    },
    {
      "epoch": 1.9192393942186587,
      "grad_norm": 0.415854811668396,
      "learning_rate": 8.066583162161245e-08,
      "loss": 0.4575,
      "step": 62477
    },
    {
      "epoch": 1.9192701133536079,
      "grad_norm": 0.474149614572525,
      "learning_rate": 8.060458297209361e-08,
      "loss": 0.3668,
      "step": 62478
    },
    {
      "epoch": 1.919300832488557,
      "grad_norm": 0.440172016620636,
      "learning_rate": 8.054335749001496e-08,
      "loss": 0.5567,
      "step": 62479
    },
    {
      "epoch": 1.9193315516235063,
      "grad_norm": 0.44684621691703796,
      "learning_rate": 8.048215517552083e-08,
      "loss": 0.4125,
      "step": 62480
    },
    {
      "epoch": 1.9193622707584554,
      "grad_norm": 0.4105926752090454,
      "learning_rate": 8.042097602875332e-08,
      "loss": 0.4138,
      "step": 62481
    },
    {
      "epoch": 1.9193929898934046,
      "grad_norm": 0.43356049060821533,
      "learning_rate": 8.035982004985454e-08,
      "loss": 0.4328,
      "step": 62482
    },
    {
      "epoch": 1.919423709028354,
      "grad_norm": 0.41913050413131714,
      "learning_rate": 8.029868723896883e-08,
      "loss": 0.4962,
      "step": 62483
    },
    {
      "epoch": 1.919454428163303,
      "grad_norm": 0.4510371685028076,
      "learning_rate": 8.023757759623718e-08,
      "loss": 0.4415,
      "step": 62484
    },
    {
      "epoch": 1.9194851472982521,
      "grad_norm": 0.4356563687324524,
      "learning_rate": 8.017649112180503e-08,
      "loss": 0.4909,
      "step": 62485
    },
    {
      "epoch": 1.9195158664332013,
      "grad_norm": 0.46871957182884216,
      "learning_rate": 8.011542781581339e-08,
      "loss": 0.5589,
      "step": 62486
    },
    {
      "epoch": 1.9195465855681504,
      "grad_norm": 0.43162059783935547,
      "learning_rate": 8.005438767840434e-08,
      "loss": 0.4452,
      "step": 62487
    },
    {
      "epoch": 1.9195773047030995,
      "grad_norm": 0.4235670268535614,
      "learning_rate": 7.999337070972112e-08,
      "loss": 0.443,
      "step": 62488
    },
    {
      "epoch": 1.9196080238380486,
      "grad_norm": 0.42987364530563354,
      "learning_rate": 7.993237690990585e-08,
      "loss": 0.4345,
      "step": 62489
    },
    {
      "epoch": 1.9196387429729977,
      "grad_norm": 0.43833446502685547,
      "learning_rate": 7.987140627910173e-08,
      "loss": 0.4605,
      "step": 62490
    },
    {
      "epoch": 1.919669462107947,
      "grad_norm": 0.4321223497390747,
      "learning_rate": 7.981045881745087e-08,
      "loss": 0.3912,
      "step": 62491
    },
    {
      "epoch": 1.9197001812428962,
      "grad_norm": 0.44152700901031494,
      "learning_rate": 7.974953452509538e-08,
      "loss": 0.4086,
      "step": 62492
    },
    {
      "epoch": 1.9197309003778453,
      "grad_norm": 0.4557485580444336,
      "learning_rate": 7.968863340217847e-08,
      "loss": 0.3934,
      "step": 62493
    },
    {
      "epoch": 1.9197616195127947,
      "grad_norm": 0.4337640404701233,
      "learning_rate": 7.962775544884005e-08,
      "loss": 0.4178,
      "step": 62494
    },
    {
      "epoch": 1.9197923386477438,
      "grad_norm": 0.4300190508365631,
      "learning_rate": 7.956690066522554e-08,
      "loss": 0.449,
      "step": 62495
    },
    {
      "epoch": 1.919823057782693,
      "grad_norm": 0.42050063610076904,
      "learning_rate": 7.950606905147374e-08,
      "loss": 0.3586,
      "step": 62496
    },
    {
      "epoch": 1.919853776917642,
      "grad_norm": 0.45646241307258606,
      "learning_rate": 7.944526060772895e-08,
      "loss": 0.4152,
      "step": 62497
    },
    {
      "epoch": 1.9198844960525911,
      "grad_norm": 0.43023446202278137,
      "learning_rate": 7.938447533413218e-08,
      "loss": 0.5226,
      "step": 62498
    },
    {
      "epoch": 1.9199152151875403,
      "grad_norm": 0.44554227590560913,
      "learning_rate": 7.932371323082666e-08,
      "loss": 0.3734,
      "step": 62499
    },
    {
      "epoch": 1.9199459343224894,
      "grad_norm": 0.4230230152606964,
      "learning_rate": 7.926297429795227e-08,
      "loss": 0.46,
      "step": 62500
    },
    {
      "epoch": 1.9199766534574385,
      "grad_norm": 0.4345000684261322,
      "learning_rate": 7.920225853565333e-08,
      "loss": 0.47,
      "step": 62501
    },
    {
      "epoch": 1.9200073725923879,
      "grad_norm": 0.40591609477996826,
      "learning_rate": 7.914156594407085e-08,
      "loss": 0.4579,
      "step": 62502
    },
    {
      "epoch": 1.920038091727337,
      "grad_norm": 0.5493649840354919,
      "learning_rate": 7.908089652334472e-08,
      "loss": 0.4257,
      "step": 62503
    },
    {
      "epoch": 1.920068810862286,
      "grad_norm": 0.44555482268333435,
      "learning_rate": 7.902025027361926e-08,
      "loss": 0.4176,
      "step": 62504
    },
    {
      "epoch": 1.9200995299972354,
      "grad_norm": 0.4151090979576111,
      "learning_rate": 7.895962719503325e-08,
      "loss": 0.4966,
      "step": 62505
    },
    {
      "epoch": 1.9201302491321846,
      "grad_norm": 0.4166451394557953,
      "learning_rate": 7.889902728773102e-08,
      "loss": 0.4659,
      "step": 62506
    },
    {
      "epoch": 1.9201609682671337,
      "grad_norm": 0.4454728662967682,
      "learning_rate": 7.883845055185246e-08,
      "loss": 0.4253,
      "step": 62507
    },
    {
      "epoch": 1.9201916874020828,
      "grad_norm": 0.41775980591773987,
      "learning_rate": 7.87778969875408e-08,
      "loss": 0.467,
      "step": 62508
    },
    {
      "epoch": 1.920222406537032,
      "grad_norm": 0.4169594347476959,
      "learning_rate": 7.871736659493479e-08,
      "loss": 0.4593,
      "step": 62509
    },
    {
      "epoch": 1.920253125671981,
      "grad_norm": 0.4435851573944092,
      "learning_rate": 7.865685937417766e-08,
      "loss": 0.4909,
      "step": 62510
    },
    {
      "epoch": 1.9202838448069302,
      "grad_norm": 0.44356390833854675,
      "learning_rate": 7.859637532541043e-08,
      "loss": 0.4495,
      "step": 62511
    },
    {
      "epoch": 1.9203145639418793,
      "grad_norm": 0.4677458107471466,
      "learning_rate": 7.853591444877406e-08,
      "loss": 0.398,
      "step": 62512
    },
    {
      "epoch": 1.9203452830768284,
      "grad_norm": 0.4301559031009674,
      "learning_rate": 7.84754767444107e-08,
      "loss": 0.4244,
      "step": 62513
    },
    {
      "epoch": 1.9203760022117777,
      "grad_norm": 0.470675528049469,
      "learning_rate": 7.84150622124602e-08,
      "loss": 0.4181,
      "step": 62514
    },
    {
      "epoch": 1.9204067213467269,
      "grad_norm": 0.42991775274276733,
      "learning_rate": 7.835467085306358e-08,
      "loss": 0.5765,
      "step": 62515
    },
    {
      "epoch": 1.9204374404816762,
      "grad_norm": 0.41322341561317444,
      "learning_rate": 7.829430266636406e-08,
      "loss": 0.4771,
      "step": 62516
    },
    {
      "epoch": 1.9204681596166253,
      "grad_norm": 0.44019946455955505,
      "learning_rate": 7.823395765250041e-08,
      "loss": 0.385,
      "step": 62517
    },
    {
      "epoch": 1.9204988787515744,
      "grad_norm": 0.46429315209388733,
      "learning_rate": 7.817363581161364e-08,
      "loss": 0.4377,
      "step": 62518
    },
    {
      "epoch": 1.9205295978865236,
      "grad_norm": 0.46391695737838745,
      "learning_rate": 7.811333714384583e-08,
      "loss": 0.5153,
      "step": 62519
    },
    {
      "epoch": 1.9205603170214727,
      "grad_norm": 0.4546947181224823,
      "learning_rate": 7.80530616493369e-08,
      "loss": 0.4057,
      "step": 62520
    },
    {
      "epoch": 1.9205910361564218,
      "grad_norm": 0.4270951449871063,
      "learning_rate": 7.799280932822894e-08,
      "loss": 0.4139,
      "step": 62521
    },
    {
      "epoch": 1.920621755291371,
      "grad_norm": 0.4611694812774658,
      "learning_rate": 7.793258018066186e-08,
      "loss": 0.4862,
      "step": 62522
    },
    {
      "epoch": 1.92065247442632,
      "grad_norm": 0.4206940531730652,
      "learning_rate": 7.78723742067744e-08,
      "loss": 0.4799,
      "step": 62523
    },
    {
      "epoch": 1.9206831935612692,
      "grad_norm": 0.40195104479789734,
      "learning_rate": 7.781219140671093e-08,
      "loss": 0.5016,
      "step": 62524
    },
    {
      "epoch": 1.9207139126962185,
      "grad_norm": 0.45877933502197266,
      "learning_rate": 7.775203178060909e-08,
      "loss": 0.4188,
      "step": 62525
    },
    {
      "epoch": 1.9207446318311676,
      "grad_norm": 0.4334871768951416,
      "learning_rate": 7.769189532860988e-08,
      "loss": 0.4997,
      "step": 62526
    },
    {
      "epoch": 1.920775350966117,
      "grad_norm": 0.4046279788017273,
      "learning_rate": 7.763178205085541e-08,
      "loss": 0.47,
      "step": 62527
    },
    {
      "epoch": 1.920806070101066,
      "grad_norm": 0.47265854477882385,
      "learning_rate": 7.757169194748337e-08,
      "loss": 0.3829,
      "step": 62528
    },
    {
      "epoch": 1.9208367892360152,
      "grad_norm": 0.4307257831096649,
      "learning_rate": 7.751162501863696e-08,
      "loss": 0.4372,
      "step": 62529
    },
    {
      "epoch": 1.9208675083709643,
      "grad_norm": 0.45857277512550354,
      "learning_rate": 7.745158126445496e-08,
      "loss": 0.4615,
      "step": 62530
    },
    {
      "epoch": 1.9208982275059134,
      "grad_norm": 0.4254955053329468,
      "learning_rate": 7.739156068507724e-08,
      "loss": 0.4542,
      "step": 62531
    },
    {
      "epoch": 1.9209289466408626,
      "grad_norm": 0.43190979957580566,
      "learning_rate": 7.733156328064484e-08,
      "loss": 0.4235,
      "step": 62532
    },
    {
      "epoch": 1.9209596657758117,
      "grad_norm": 0.4183821380138397,
      "learning_rate": 7.727158905129761e-08,
      "loss": 0.5405,
      "step": 62533
    },
    {
      "epoch": 1.9209903849107608,
      "grad_norm": 0.44637054204940796,
      "learning_rate": 7.721163799717546e-08,
      "loss": 0.425,
      "step": 62534
    },
    {
      "epoch": 1.92102110404571,
      "grad_norm": 0.45720812678337097,
      "learning_rate": 7.715171011841827e-08,
      "loss": 0.5359,
      "step": 62535
    },
    {
      "epoch": 1.9210518231806593,
      "grad_norm": 0.3988035321235657,
      "learning_rate": 7.709180541516703e-08,
      "loss": 0.4102,
      "step": 62536
    },
    {
      "epoch": 1.9210825423156084,
      "grad_norm": 0.44960179924964905,
      "learning_rate": 7.703192388755942e-08,
      "loss": 0.4436,
      "step": 62537
    },
    {
      "epoch": 1.9211132614505577,
      "grad_norm": 0.42877396941185,
      "learning_rate": 7.697206553573755e-08,
      "loss": 0.4391,
      "step": 62538
    },
    {
      "epoch": 1.9211439805855068,
      "grad_norm": 0.41891905665397644,
      "learning_rate": 7.69122303598413e-08,
      "loss": 0.5178,
      "step": 62539
    },
    {
      "epoch": 1.921174699720456,
      "grad_norm": 0.506330132484436,
      "learning_rate": 7.685241836000834e-08,
      "loss": 0.4729,
      "step": 62540
    },
    {
      "epoch": 1.921205418855405,
      "grad_norm": 0.43966495990753174,
      "learning_rate": 7.679262953637967e-08,
      "loss": 0.4267,
      "step": 62541
    },
    {
      "epoch": 1.9212361379903542,
      "grad_norm": 0.39607954025268555,
      "learning_rate": 7.673286388909628e-08,
      "loss": 0.4364,
      "step": 62542
    },
    {
      "epoch": 1.9212668571253033,
      "grad_norm": 0.5354018807411194,
      "learning_rate": 7.667312141829474e-08,
      "loss": 0.4745,
      "step": 62543
    },
    {
      "epoch": 1.9212975762602524,
      "grad_norm": 0.4376656413078308,
      "learning_rate": 7.661340212411717e-08,
      "loss": 0.4816,
      "step": 62544
    },
    {
      "epoch": 1.9213282953952016,
      "grad_norm": 0.44511842727661133,
      "learning_rate": 7.65537060067012e-08,
      "loss": 0.5288,
      "step": 62545
    },
    {
      "epoch": 1.9213590145301507,
      "grad_norm": 0.43292367458343506,
      "learning_rate": 7.649403306618785e-08,
      "loss": 0.3722,
      "step": 62546
    },
    {
      "epoch": 1.9213897336651,
      "grad_norm": 0.4513205289840698,
      "learning_rate": 7.64343833027148e-08,
      "loss": 0.4371,
      "step": 62547
    },
    {
      "epoch": 1.9214204528000491,
      "grad_norm": 0.4465349614620209,
      "learning_rate": 7.637475671642303e-08,
      "loss": 0.4671,
      "step": 62548
    },
    {
      "epoch": 1.9214511719349983,
      "grad_norm": 0.4295918643474579,
      "learning_rate": 7.631515330745131e-08,
      "loss": 0.4655,
      "step": 62549
    },
    {
      "epoch": 1.9214818910699476,
      "grad_norm": 0.4502216875553131,
      "learning_rate": 7.625557307593845e-08,
      "loss": 0.463,
      "step": 62550
    },
    {
      "epoch": 1.9215126102048967,
      "grad_norm": 0.47612184286117554,
      "learning_rate": 7.61960160220232e-08,
      "loss": 0.4771,
      "step": 62551
    },
    {
      "epoch": 1.9215433293398458,
      "grad_norm": 0.4744452238082886,
      "learning_rate": 7.613648214584546e-08,
      "loss": 0.4265,
      "step": 62552
    },
    {
      "epoch": 1.921574048474795,
      "grad_norm": 0.430965781211853,
      "learning_rate": 7.607697144754401e-08,
      "loss": 0.4887,
      "step": 62553
    },
    {
      "epoch": 1.921604767609744,
      "grad_norm": 0.4164755344390869,
      "learning_rate": 7.601748392725761e-08,
      "loss": 0.408,
      "step": 62554
    },
    {
      "epoch": 1.9216354867446932,
      "grad_norm": 0.5173482894897461,
      "learning_rate": 7.595801958512616e-08,
      "loss": 0.4656,
      "step": 62555
    },
    {
      "epoch": 1.9216662058796423,
      "grad_norm": 0.4378412067890167,
      "learning_rate": 7.589857842128734e-08,
      "loss": 0.5194,
      "step": 62556
    },
    {
      "epoch": 1.9216969250145914,
      "grad_norm": 0.4365788400173187,
      "learning_rate": 7.583916043588102e-08,
      "loss": 0.3771,
      "step": 62557
    },
    {
      "epoch": 1.9217276441495408,
      "grad_norm": 0.43940025568008423,
      "learning_rate": 7.577976562904488e-08,
      "loss": 0.5213,
      "step": 62558
    },
    {
      "epoch": 1.92175836328449,
      "grad_norm": 0.42660319805145264,
      "learning_rate": 7.57203940009188e-08,
      "loss": 0.4975,
      "step": 62559
    },
    {
      "epoch": 1.921789082419439,
      "grad_norm": 0.5223882794380188,
      "learning_rate": 7.566104555163934e-08,
      "loss": 0.4146,
      "step": 62560
    },
    {
      "epoch": 1.9218198015543884,
      "grad_norm": 0.43774136900901794,
      "learning_rate": 7.56017202813486e-08,
      "loss": 0.4877,
      "step": 62561
    },
    {
      "epoch": 1.9218505206893375,
      "grad_norm": 0.4239917993545532,
      "learning_rate": 7.554241819018204e-08,
      "loss": 0.5368,
      "step": 62562
    },
    {
      "epoch": 1.9218812398242866,
      "grad_norm": 0.40576016902923584,
      "learning_rate": 7.548313927827955e-08,
      "loss": 0.4741,
      "step": 62563
    },
    {
      "epoch": 1.9219119589592357,
      "grad_norm": 0.4457927644252777,
      "learning_rate": 7.542388354577878e-08,
      "loss": 0.4243,
      "step": 62564
    },
    {
      "epoch": 1.9219426780941848,
      "grad_norm": 0.49685072898864746,
      "learning_rate": 7.536465099281964e-08,
      "loss": 0.4912,
      "step": 62565
    },
    {
      "epoch": 1.921973397229134,
      "grad_norm": 0.458172470331192,
      "learning_rate": 7.530544161953867e-08,
      "loss": 0.4583,
      "step": 62566
    },
    {
      "epoch": 1.922004116364083,
      "grad_norm": 0.4027470052242279,
      "learning_rate": 7.524625542607578e-08,
      "loss": 0.502,
      "step": 62567
    },
    {
      "epoch": 1.9220348354990322,
      "grad_norm": 0.4490024745464325,
      "learning_rate": 7.51870924125675e-08,
      "loss": 0.526,
      "step": 62568
    },
    {
      "epoch": 1.9220655546339815,
      "grad_norm": 0.4276984632015228,
      "learning_rate": 7.512795257915373e-08,
      "loss": 0.4576,
      "step": 62569
    },
    {
      "epoch": 1.9220962737689307,
      "grad_norm": 0.47062453627586365,
      "learning_rate": 7.506883592597102e-08,
      "loss": 0.4841,
      "step": 62570
    },
    {
      "epoch": 1.9221269929038798,
      "grad_norm": 0.44656243920326233,
      "learning_rate": 7.500974245315818e-08,
      "loss": 0.5441,
      "step": 62571
    },
    {
      "epoch": 1.9221577120388291,
      "grad_norm": 0.4172200858592987,
      "learning_rate": 7.495067216085506e-08,
      "loss": 0.4871,
      "step": 62572
    },
    {
      "epoch": 1.9221884311737782,
      "grad_norm": 0.4478965699672699,
      "learning_rate": 7.489162504919489e-08,
      "loss": 0.4253,
      "step": 62573
    },
    {
      "epoch": 1.9222191503087274,
      "grad_norm": 0.41995367407798767,
      "learning_rate": 7.483260111832091e-08,
      "loss": 0.4746,
      "step": 62574
    },
    {
      "epoch": 1.9222498694436765,
      "grad_norm": 0.41171637177467346,
      "learning_rate": 7.477360036836745e-08,
      "loss": 0.4529,
      "step": 62575
    },
    {
      "epoch": 1.9222805885786256,
      "grad_norm": 0.4455800950527191,
      "learning_rate": 7.471462279947327e-08,
      "loss": 0.5191,
      "step": 62576
    },
    {
      "epoch": 1.9223113077135747,
      "grad_norm": 0.421176552772522,
      "learning_rate": 7.465566841177718e-08,
      "loss": 0.5375,
      "step": 62577
    },
    {
      "epoch": 1.9223420268485238,
      "grad_norm": 0.4492187798023224,
      "learning_rate": 7.459673720541461e-08,
      "loss": 0.4979,
      "step": 62578
    },
    {
      "epoch": 1.922372745983473,
      "grad_norm": 0.41767075657844543,
      "learning_rate": 7.453782918052544e-08,
      "loss": 0.4412,
      "step": 62579
    },
    {
      "epoch": 1.9224034651184223,
      "grad_norm": 0.4608849287033081,
      "learning_rate": 7.447894433724623e-08,
      "loss": 0.4189,
      "step": 62580
    },
    {
      "epoch": 1.9224341842533714,
      "grad_norm": 0.43152180314064026,
      "learning_rate": 7.442008267571465e-08,
      "loss": 0.4742,
      "step": 62581
    },
    {
      "epoch": 1.9224649033883205,
      "grad_norm": 0.48543983697891235,
      "learning_rate": 7.436124419606838e-08,
      "loss": 0.5123,
      "step": 62582
    },
    {
      "epoch": 1.9224956225232699,
      "grad_norm": 0.448485404253006,
      "learning_rate": 7.430242889844397e-08,
      "loss": 0.4866,
      "step": 62583
    },
    {
      "epoch": 1.922526341658219,
      "grad_norm": 0.4313836097717285,
      "learning_rate": 7.424363678298019e-08,
      "loss": 0.4817,
      "step": 62584
    },
    {
      "epoch": 1.9225570607931681,
      "grad_norm": 0.4201827645301819,
      "learning_rate": 7.418486784981249e-08,
      "loss": 0.4642,
      "step": 62585
    },
    {
      "epoch": 1.9225877799281172,
      "grad_norm": 0.39911988377571106,
      "learning_rate": 7.412612209907966e-08,
      "loss": 0.4795,
      "step": 62586
    },
    {
      "epoch": 1.9226184990630664,
      "grad_norm": 0.4203943908214569,
      "learning_rate": 7.406739953091935e-08,
      "loss": 0.4294,
      "step": 62587
    },
    {
      "epoch": 1.9226492181980155,
      "grad_norm": 0.49415358901023865,
      "learning_rate": 7.400870014546701e-08,
      "loss": 0.4872,
      "step": 62588
    },
    {
      "epoch": 1.9226799373329646,
      "grad_norm": 0.42731356620788574,
      "learning_rate": 7.395002394286144e-08,
      "loss": 0.4933,
      "step": 62589
    },
    {
      "epoch": 1.9227106564679137,
      "grad_norm": 0.41300100088119507,
      "learning_rate": 7.389137092323805e-08,
      "loss": 0.4577,
      "step": 62590
    },
    {
      "epoch": 1.922741375602863,
      "grad_norm": 0.42124709486961365,
      "learning_rate": 7.383274108673456e-08,
      "loss": 0.4739,
      "step": 62591
    },
    {
      "epoch": 1.9227720947378122,
      "grad_norm": 0.449485719203949,
      "learning_rate": 7.377413443348746e-08,
      "loss": 0.4375,
      "step": 62592
    },
    {
      "epoch": 1.9228028138727613,
      "grad_norm": 0.4434073269367218,
      "learning_rate": 7.371555096363559e-08,
      "loss": 0.4846,
      "step": 62593
    },
    {
      "epoch": 1.9228335330077106,
      "grad_norm": 0.535913348197937,
      "learning_rate": 7.365699067731325e-08,
      "loss": 0.5044,
      "step": 62594
    },
    {
      "epoch": 1.9228642521426598,
      "grad_norm": 0.4397207796573639,
      "learning_rate": 7.359845357465812e-08,
      "loss": 0.4143,
      "step": 62595
    },
    {
      "epoch": 1.9228949712776089,
      "grad_norm": 0.41155609488487244,
      "learning_rate": 7.353993965580786e-08,
      "loss": 0.4337,
      "step": 62596
    },
    {
      "epoch": 1.922925690412558,
      "grad_norm": 0.4133700132369995,
      "learning_rate": 7.348144892089792e-08,
      "loss": 0.497,
      "step": 62597
    },
    {
      "epoch": 1.9229564095475071,
      "grad_norm": 0.4330849349498749,
      "learning_rate": 7.342298137006599e-08,
      "loss": 0.4932,
      "step": 62598
    },
    {
      "epoch": 1.9229871286824562,
      "grad_norm": 0.4443728029727936,
      "learning_rate": 7.336453700344747e-08,
      "loss": 0.5002,
      "step": 62599
    },
    {
      "epoch": 1.9230178478174054,
      "grad_norm": 0.41844648122787476,
      "learning_rate": 7.330611582117786e-08,
      "loss": 0.5057,
      "step": 62600
    },
    {
      "epoch": 1.9230485669523545,
      "grad_norm": 0.3875420093536377,
      "learning_rate": 7.324771782339701e-08,
      "loss": 0.4266,
      "step": 62601
    },
    {
      "epoch": 1.9230792860873038,
      "grad_norm": 0.4312213957309723,
      "learning_rate": 7.318934301023816e-08,
      "loss": 0.4781,
      "step": 62602
    },
    {
      "epoch": 1.923110005222253,
      "grad_norm": 0.4156316816806793,
      "learning_rate": 7.31309913818401e-08,
      "loss": 0.4261,
      "step": 62603
    },
    {
      "epoch": 1.923140724357202,
      "grad_norm": 0.4302053451538086,
      "learning_rate": 7.307266293833714e-08,
      "loss": 0.3813,
      "step": 62604
    },
    {
      "epoch": 1.9231714434921514,
      "grad_norm": 0.4049679934978485,
      "learning_rate": 7.301435767986698e-08,
      "loss": 0.4745,
      "step": 62605
    },
    {
      "epoch": 1.9232021626271005,
      "grad_norm": 0.39277979731559753,
      "learning_rate": 7.295607560656392e-08,
      "loss": 0.4507,
      "step": 62606
    },
    {
      "epoch": 1.9232328817620497,
      "grad_norm": 0.4926066994667053,
      "learning_rate": 7.289781671856566e-08,
      "loss": 0.404,
      "step": 62607
    },
    {
      "epoch": 1.9232636008969988,
      "grad_norm": 0.4354587495326996,
      "learning_rate": 7.283958101600875e-08,
      "loss": 0.4688,
      "step": 62608
    },
    {
      "epoch": 1.923294320031948,
      "grad_norm": 0.5204584002494812,
      "learning_rate": 7.27813684990264e-08,
      "loss": 0.482,
      "step": 62609
    },
    {
      "epoch": 1.923325039166897,
      "grad_norm": 0.44522419571876526,
      "learning_rate": 7.272317916775851e-08,
      "loss": 0.5322,
      "step": 62610
    },
    {
      "epoch": 1.9233557583018461,
      "grad_norm": 0.4741377532482147,
      "learning_rate": 7.266501302233719e-08,
      "loss": 0.5127,
      "step": 62611
    },
    {
      "epoch": 1.9233864774367952,
      "grad_norm": 0.4476969838142395,
      "learning_rate": 7.260687006290124e-08,
      "loss": 0.4458,
      "step": 62612
    },
    {
      "epoch": 1.9234171965717446,
      "grad_norm": 0.43577370047569275,
      "learning_rate": 7.254875028958496e-08,
      "loss": 0.4429,
      "step": 62613
    },
    {
      "epoch": 1.9234479157066937,
      "grad_norm": 0.41931742429733276,
      "learning_rate": 7.249065370252495e-08,
      "loss": 0.4845,
      "step": 62614
    },
    {
      "epoch": 1.9234786348416428,
      "grad_norm": 0.4187858998775482,
      "learning_rate": 7.243258030185551e-08,
      "loss": 0.545,
      "step": 62615
    },
    {
      "epoch": 1.9235093539765922,
      "grad_norm": 0.44714048504829407,
      "learning_rate": 7.237453008771323e-08,
      "loss": 0.3926,
      "step": 62616
    },
    {
      "epoch": 1.9235400731115413,
      "grad_norm": 0.4400791823863983,
      "learning_rate": 7.231650306023353e-08,
      "loss": 0.5193,
      "step": 62617
    },
    {
      "epoch": 1.9235707922464904,
      "grad_norm": 0.4455224573612213,
      "learning_rate": 7.225849921955297e-08,
      "loss": 0.5921,
      "step": 62618
    },
    {
      "epoch": 1.9236015113814395,
      "grad_norm": 0.40259915590286255,
      "learning_rate": 7.220051856580478e-08,
      "loss": 0.3979,
      "step": 62619
    },
    {
      "epoch": 1.9236322305163887,
      "grad_norm": 0.4250449240207672,
      "learning_rate": 7.214256109912665e-08,
      "loss": 0.4598,
      "step": 62620
    },
    {
      "epoch": 1.9236629496513378,
      "grad_norm": 0.42645400762557983,
      "learning_rate": 7.208462681965178e-08,
      "loss": 0.4306,
      "step": 62621
    },
    {
      "epoch": 1.923693668786287,
      "grad_norm": 0.4391865134239197,
      "learning_rate": 7.202671572751674e-08,
      "loss": 0.485,
      "step": 62622
    },
    {
      "epoch": 1.923724387921236,
      "grad_norm": 0.4716503918170929,
      "learning_rate": 7.196882782285697e-08,
      "loss": 0.4597,
      "step": 62623
    },
    {
      "epoch": 1.9237551070561851,
      "grad_norm": 0.43789049983024597,
      "learning_rate": 7.191096310580791e-08,
      "loss": 0.4501,
      "step": 62624
    },
    {
      "epoch": 1.9237858261911345,
      "grad_norm": 0.43455567955970764,
      "learning_rate": 7.185312157650393e-08,
      "loss": 0.4696,
      "step": 62625
    },
    {
      "epoch": 1.9238165453260836,
      "grad_norm": 0.43831437826156616,
      "learning_rate": 7.179530323508043e-08,
      "loss": 0.4107,
      "step": 62626
    },
    {
      "epoch": 1.923847264461033,
      "grad_norm": 0.41182008385658264,
      "learning_rate": 7.17375080816718e-08,
      "loss": 0.451,
      "step": 62627
    },
    {
      "epoch": 1.923877983595982,
      "grad_norm": 0.42409461736679077,
      "learning_rate": 7.167973611641343e-08,
      "loss": 0.442,
      "step": 62628
    },
    {
      "epoch": 1.9239087027309312,
      "grad_norm": 0.45271211862564087,
      "learning_rate": 7.162198733944193e-08,
      "loss": 0.502,
      "step": 62629
    },
    {
      "epoch": 1.9239394218658803,
      "grad_norm": 0.44994065165519714,
      "learning_rate": 7.156426175088937e-08,
      "loss": 0.4886,
      "step": 62630
    },
    {
      "epoch": 1.9239701410008294,
      "grad_norm": 0.4315367341041565,
      "learning_rate": 7.150655935089234e-08,
      "loss": 0.508,
      "step": 62631
    },
    {
      "epoch": 1.9240008601357785,
      "grad_norm": 0.424141526222229,
      "learning_rate": 7.144888013958517e-08,
      "loss": 0.4545,
      "step": 62632
    },
    {
      "epoch": 1.9240315792707277,
      "grad_norm": 0.45034852623939514,
      "learning_rate": 7.13912241171022e-08,
      "loss": 0.4308,
      "step": 62633
    },
    {
      "epoch": 1.9240622984056768,
      "grad_norm": 0.4516538977622986,
      "learning_rate": 7.133359128357886e-08,
      "loss": 0.5218,
      "step": 62634
    },
    {
      "epoch": 1.924093017540626,
      "grad_norm": 0.43569469451904297,
      "learning_rate": 7.127598163914951e-08,
      "loss": 0.561,
      "step": 62635
    },
    {
      "epoch": 1.9241237366755752,
      "grad_norm": 0.46625426411628723,
      "learning_rate": 7.121839518394735e-08,
      "loss": 0.5599,
      "step": 62636
    },
    {
      "epoch": 1.9241544558105244,
      "grad_norm": 0.4450216591358185,
      "learning_rate": 7.116083191810896e-08,
      "loss": 0.4859,
      "step": 62637
    },
    {
      "epoch": 1.9241851749454737,
      "grad_norm": 0.43195781111717224,
      "learning_rate": 7.110329184176756e-08,
      "loss": 0.3704,
      "step": 62638
    },
    {
      "epoch": 1.9242158940804228,
      "grad_norm": 0.45329636335372925,
      "learning_rate": 7.104577495505859e-08,
      "loss": 0.5279,
      "step": 62639
    },
    {
      "epoch": 1.924246613215372,
      "grad_norm": 0.4225611090660095,
      "learning_rate": 7.098828125811419e-08,
      "loss": 0.4968,
      "step": 62640
    },
    {
      "epoch": 1.924277332350321,
      "grad_norm": 0.4190290868282318,
      "learning_rate": 7.093081075107089e-08,
      "loss": 0.4686,
      "step": 62641
    },
    {
      "epoch": 1.9243080514852702,
      "grad_norm": 0.42299556732177734,
      "learning_rate": 7.087336343406192e-08,
      "loss": 0.4176,
      "step": 62642
    },
    {
      "epoch": 1.9243387706202193,
      "grad_norm": 0.4411005675792694,
      "learning_rate": 7.081593930722275e-08,
      "loss": 0.4334,
      "step": 62643
    },
    {
      "epoch": 1.9243694897551684,
      "grad_norm": 0.5047144293785095,
      "learning_rate": 7.075853837068546e-08,
      "loss": 0.4399,
      "step": 62644
    },
    {
      "epoch": 1.9244002088901175,
      "grad_norm": 0.406014621257782,
      "learning_rate": 7.070116062458443e-08,
      "loss": 0.4548,
      "step": 62645
    },
    {
      "epoch": 1.9244309280250667,
      "grad_norm": 0.4134431481361389,
      "learning_rate": 7.064380606905508e-08,
      "loss": 0.4082,
      "step": 62646
    },
    {
      "epoch": 1.924461647160016,
      "grad_norm": 0.3999849259853363,
      "learning_rate": 7.058647470423064e-08,
      "loss": 0.4096,
      "step": 62647
    },
    {
      "epoch": 1.9244923662949651,
      "grad_norm": 0.45165586471557617,
      "learning_rate": 7.052916653024545e-08,
      "loss": 0.4526,
      "step": 62648
    },
    {
      "epoch": 1.9245230854299145,
      "grad_norm": 0.4860787093639374,
      "learning_rate": 7.047188154723161e-08,
      "loss": 0.4337,
      "step": 62649
    },
    {
      "epoch": 1.9245538045648636,
      "grad_norm": 0.4203997850418091,
      "learning_rate": 7.04146197553246e-08,
      "loss": 0.5367,
      "step": 62650
    },
    {
      "epoch": 1.9245845236998127,
      "grad_norm": 0.4049643576145172,
      "learning_rate": 7.035738115465762e-08,
      "loss": 0.4674,
      "step": 62651
    },
    {
      "epoch": 1.9246152428347618,
      "grad_norm": 0.4776781499385834,
      "learning_rate": 7.030016574536503e-08,
      "loss": 0.4547,
      "step": 62652
    },
    {
      "epoch": 1.924645961969711,
      "grad_norm": 0.4579509198665619,
      "learning_rate": 7.024297352758003e-08,
      "loss": 0.4749,
      "step": 62653
    },
    {
      "epoch": 1.92467668110466,
      "grad_norm": 0.42054373025894165,
      "learning_rate": 7.018580450143475e-08,
      "loss": 0.4559,
      "step": 62654
    },
    {
      "epoch": 1.9247074002396092,
      "grad_norm": 0.4527778625488281,
      "learning_rate": 7.012865866706465e-08,
      "loss": 0.5257,
      "step": 62655
    },
    {
      "epoch": 1.9247381193745583,
      "grad_norm": 0.43262532353401184,
      "learning_rate": 7.007153602460404e-08,
      "loss": 0.5622,
      "step": 62656
    },
    {
      "epoch": 1.9247688385095074,
      "grad_norm": 0.41327571868896484,
      "learning_rate": 7.001443657418283e-08,
      "loss": 0.5432,
      "step": 62657
    },
    {
      "epoch": 1.9247995576444568,
      "grad_norm": 0.57041335105896,
      "learning_rate": 6.995736031593759e-08,
      "loss": 0.4544,
      "step": 62658
    },
    {
      "epoch": 1.9248302767794059,
      "grad_norm": 0.46593672037124634,
      "learning_rate": 6.99003072499993e-08,
      "loss": 0.483,
      "step": 62659
    },
    {
      "epoch": 1.924860995914355,
      "grad_norm": 0.4162222146987915,
      "learning_rate": 6.984327737650343e-08,
      "loss": 0.4435,
      "step": 62660
    },
    {
      "epoch": 1.9248917150493043,
      "grad_norm": 0.43733784556388855,
      "learning_rate": 6.978627069558208e-08,
      "loss": 0.4112,
      "step": 62661
    },
    {
      "epoch": 1.9249224341842535,
      "grad_norm": 0.445921391248703,
      "learning_rate": 6.972928720736737e-08,
      "loss": 0.5339,
      "step": 62662
    },
    {
      "epoch": 1.9249531533192026,
      "grad_norm": 0.4319553077220917,
      "learning_rate": 6.967232691199477e-08,
      "loss": 0.5284,
      "step": 62663
    },
    {
      "epoch": 1.9249838724541517,
      "grad_norm": 0.4752845764160156,
      "learning_rate": 6.961538980959526e-08,
      "loss": 0.4508,
      "step": 62664
    },
    {
      "epoch": 1.9250145915891008,
      "grad_norm": 0.49098894000053406,
      "learning_rate": 6.955847590030206e-08,
      "loss": 0.4255,
      "step": 62665
    },
    {
      "epoch": 1.92504531072405,
      "grad_norm": 0.5611268281936646,
      "learning_rate": 6.950158518424954e-08,
      "loss": 0.5234,
      "step": 62666
    },
    {
      "epoch": 1.925076029858999,
      "grad_norm": 0.47179290652275085,
      "learning_rate": 6.944471766156868e-08,
      "loss": 0.5233,
      "step": 62667
    },
    {
      "epoch": 1.9251067489939482,
      "grad_norm": 0.4319460988044739,
      "learning_rate": 6.938787333239384e-08,
      "loss": 0.4788,
      "step": 62668
    },
    {
      "epoch": 1.9251374681288975,
      "grad_norm": 0.46501511335372925,
      "learning_rate": 6.933105219685709e-08,
      "loss": 0.4829,
      "step": 62669
    },
    {
      "epoch": 1.9251681872638466,
      "grad_norm": 0.4649467170238495,
      "learning_rate": 6.927425425509171e-08,
      "loss": 0.4643,
      "step": 62670
    },
    {
      "epoch": 1.9251989063987958,
      "grad_norm": 0.392626017332077,
      "learning_rate": 6.921747950722979e-08,
      "loss": 0.4698,
      "step": 62671
    },
    {
      "epoch": 1.925229625533745,
      "grad_norm": 0.4322105348110199,
      "learning_rate": 6.916072795340233e-08,
      "loss": 0.4733,
      "step": 62672
    },
    {
      "epoch": 1.9252603446686942,
      "grad_norm": 0.4503602385520935,
      "learning_rate": 6.910399959374592e-08,
      "loss": 0.4255,
      "step": 62673
    },
    {
      "epoch": 1.9252910638036433,
      "grad_norm": 0.42700695991516113,
      "learning_rate": 6.904729442838931e-08,
      "loss": 0.4368,
      "step": 62674
    },
    {
      "epoch": 1.9253217829385925,
      "grad_norm": 0.5295052528381348,
      "learning_rate": 6.899061245746686e-08,
      "loss": 0.3624,
      "step": 62675
    },
    {
      "epoch": 1.9253525020735416,
      "grad_norm": 0.4254394471645355,
      "learning_rate": 6.893395368110956e-08,
      "loss": 0.5134,
      "step": 62676
    },
    {
      "epoch": 1.9253832212084907,
      "grad_norm": 0.41328948736190796,
      "learning_rate": 6.887731809945065e-08,
      "loss": 0.4788,
      "step": 62677
    },
    {
      "epoch": 1.9254139403434398,
      "grad_norm": 0.4217713475227356,
      "learning_rate": 6.882070571262333e-08,
      "loss": 0.5287,
      "step": 62678
    },
    {
      "epoch": 1.925444659478389,
      "grad_norm": 0.47481411695480347,
      "learning_rate": 6.876411652075865e-08,
      "loss": 0.4673,
      "step": 62679
    },
    {
      "epoch": 1.9254753786133383,
      "grad_norm": 0.4510098397731781,
      "learning_rate": 6.87075505239887e-08,
      "loss": 0.356,
      "step": 62680
    },
    {
      "epoch": 1.9255060977482874,
      "grad_norm": 0.41419216990470886,
      "learning_rate": 6.86510077224456e-08,
      "loss": 0.4978,
      "step": 62681
    },
    {
      "epoch": 1.9255368168832365,
      "grad_norm": 0.45749151706695557,
      "learning_rate": 6.859448811626146e-08,
      "loss": 0.4408,
      "step": 62682
    },
    {
      "epoch": 1.9255675360181859,
      "grad_norm": 0.44420069456100464,
      "learning_rate": 6.853799170556841e-08,
      "loss": 0.4581,
      "step": 62683
    },
    {
      "epoch": 1.925598255153135,
      "grad_norm": 0.46182000637054443,
      "learning_rate": 6.848151849049967e-08,
      "loss": 0.5254,
      "step": 62684
    },
    {
      "epoch": 1.925628974288084,
      "grad_norm": 0.3776724338531494,
      "learning_rate": 6.842506847118513e-08,
      "loss": 0.4517,
      "step": 62685
    },
    {
      "epoch": 1.9256596934230332,
      "grad_norm": 0.44408831000328064,
      "learning_rate": 6.836864164775803e-08,
      "loss": 0.4593,
      "step": 62686
    },
    {
      "epoch": 1.9256904125579823,
      "grad_norm": 0.3964736759662628,
      "learning_rate": 6.831223802034826e-08,
      "loss": 0.4418,
      "step": 62687
    },
    {
      "epoch": 1.9257211316929315,
      "grad_norm": 0.45916539430618286,
      "learning_rate": 6.825585758909014e-08,
      "loss": 0.4289,
      "step": 62688
    },
    {
      "epoch": 1.9257518508278806,
      "grad_norm": 0.434685617685318,
      "learning_rate": 6.81995003541136e-08,
      "loss": 0.4522,
      "step": 62689
    },
    {
      "epoch": 1.9257825699628297,
      "grad_norm": 0.4927840530872345,
      "learning_rate": 6.814316631555074e-08,
      "loss": 0.4005,
      "step": 62690
    },
    {
      "epoch": 1.925813289097779,
      "grad_norm": 0.4369475841522217,
      "learning_rate": 6.808685547353366e-08,
      "loss": 0.3964,
      "step": 62691
    },
    {
      "epoch": 1.9258440082327282,
      "grad_norm": 0.45450446009635925,
      "learning_rate": 6.80305678281934e-08,
      "loss": 0.5002,
      "step": 62692
    },
    {
      "epoch": 1.9258747273676773,
      "grad_norm": 0.4718039631843567,
      "learning_rate": 6.797430337966093e-08,
      "loss": 0.3978,
      "step": 62693
    },
    {
      "epoch": 1.9259054465026266,
      "grad_norm": 0.44210007786750793,
      "learning_rate": 6.791806212806729e-08,
      "loss": 0.4571,
      "step": 62694
    },
    {
      "epoch": 1.9259361656375757,
      "grad_norm": 0.43895772099494934,
      "learning_rate": 6.786184407354568e-08,
      "loss": 0.4442,
      "step": 62695
    },
    {
      "epoch": 1.9259668847725249,
      "grad_norm": 0.41269662976264954,
      "learning_rate": 6.780564921622712e-08,
      "loss": 0.4619,
      "step": 62696
    },
    {
      "epoch": 1.925997603907474,
      "grad_norm": 0.3908950388431549,
      "learning_rate": 6.77494775562404e-08,
      "loss": 0.4054,
      "step": 62697
    },
    {
      "epoch": 1.926028323042423,
      "grad_norm": 0.40449026226997375,
      "learning_rate": 6.769332909371984e-08,
      "loss": 0.5053,
      "step": 62698
    },
    {
      "epoch": 1.9260590421773722,
      "grad_norm": 0.4599381685256958,
      "learning_rate": 6.763720382879424e-08,
      "loss": 0.4611,
      "step": 62699
    },
    {
      "epoch": 1.9260897613123213,
      "grad_norm": 0.40643537044525146,
      "learning_rate": 6.758110176159571e-08,
      "loss": 0.4241,
      "step": 62700
    },
    {
      "epoch": 1.9261204804472705,
      "grad_norm": 0.4417455494403839,
      "learning_rate": 6.752502289225637e-08,
      "loss": 0.4235,
      "step": 62701
    },
    {
      "epoch": 1.9261511995822198,
      "grad_norm": 0.4442663788795471,
      "learning_rate": 6.746896722090501e-08,
      "loss": 0.4483,
      "step": 62702
    },
    {
      "epoch": 1.926181918717169,
      "grad_norm": 0.4111696183681488,
      "learning_rate": 6.741293474767374e-08,
      "loss": 0.4024,
      "step": 62703
    },
    {
      "epoch": 1.926212637852118,
      "grad_norm": 0.3834860026836395,
      "learning_rate": 6.735692547269246e-08,
      "loss": 0.4527,
      "step": 62704
    },
    {
      "epoch": 1.9262433569870674,
      "grad_norm": 0.44114750623703003,
      "learning_rate": 6.730093939609328e-08,
      "loss": 0.521,
      "step": 62705
    },
    {
      "epoch": 1.9262740761220165,
      "grad_norm": 0.4444716274738312,
      "learning_rate": 6.72449765180072e-08,
      "loss": 0.4759,
      "step": 62706
    },
    {
      "epoch": 1.9263047952569656,
      "grad_norm": 0.42649322748184204,
      "learning_rate": 6.718903683856414e-08,
      "loss": 0.4304,
      "step": 62707
    },
    {
      "epoch": 1.9263355143919147,
      "grad_norm": 0.4547893702983856,
      "learning_rate": 6.713312035789288e-08,
      "loss": 0.5115,
      "step": 62708
    },
    {
      "epoch": 1.9263662335268639,
      "grad_norm": 0.47517889738082886,
      "learning_rate": 6.707722707612774e-08,
      "loss": 0.4051,
      "step": 62709
    },
    {
      "epoch": 1.926396952661813,
      "grad_norm": 0.440729558467865,
      "learning_rate": 6.702135699339751e-08,
      "loss": 0.4332,
      "step": 62710
    },
    {
      "epoch": 1.926427671796762,
      "grad_norm": 0.45015886425971985,
      "learning_rate": 6.69655101098321e-08,
      "loss": 0.5053,
      "step": 62711
    },
    {
      "epoch": 1.9264583909317112,
      "grad_norm": 0.3992483615875244,
      "learning_rate": 6.69096864255625e-08,
      "loss": 0.3679,
      "step": 62712
    },
    {
      "epoch": 1.9264891100666606,
      "grad_norm": 0.386508047580719,
      "learning_rate": 6.685388594071862e-08,
      "loss": 0.4184,
      "step": 62713
    },
    {
      "epoch": 1.9265198292016097,
      "grad_norm": 0.42651188373565674,
      "learning_rate": 6.679810865543146e-08,
      "loss": 0.4563,
      "step": 62714
    },
    {
      "epoch": 1.9265505483365588,
      "grad_norm": 0.4232517182826996,
      "learning_rate": 6.674235456983202e-08,
      "loss": 0.5385,
      "step": 62715
    },
    {
      "epoch": 1.9265812674715082,
      "grad_norm": 0.4348399341106415,
      "learning_rate": 6.6686623684048e-08,
      "loss": 0.4591,
      "step": 62716
    },
    {
      "epoch": 1.9266119866064573,
      "grad_norm": 0.4277065098285675,
      "learning_rate": 6.663091599821258e-08,
      "loss": 0.4311,
      "step": 62717
    },
    {
      "epoch": 1.9266427057414064,
      "grad_norm": 0.4454341530799866,
      "learning_rate": 6.657523151245348e-08,
      "loss": 0.4526,
      "step": 62718
    },
    {
      "epoch": 1.9266734248763555,
      "grad_norm": 0.44302552938461304,
      "learning_rate": 6.65195702269017e-08,
      "loss": 0.4916,
      "step": 62719
    },
    {
      "epoch": 1.9267041440113046,
      "grad_norm": 0.39980262517929077,
      "learning_rate": 6.646393214168712e-08,
      "loss": 0.4658,
      "step": 62720
    },
    {
      "epoch": 1.9267348631462538,
      "grad_norm": 0.4225883185863495,
      "learning_rate": 6.640831725693964e-08,
      "loss": 0.5362,
      "step": 62721
    },
    {
      "epoch": 1.9267655822812029,
      "grad_norm": 0.39928993582725525,
      "learning_rate": 6.635272557279026e-08,
      "loss": 0.4752,
      "step": 62722
    },
    {
      "epoch": 1.926796301416152,
      "grad_norm": 0.4999852478504181,
      "learning_rate": 6.629715708936668e-08,
      "loss": 0.4701,
      "step": 62723
    },
    {
      "epoch": 1.9268270205511013,
      "grad_norm": 0.4176773130893707,
      "learning_rate": 6.6241611806801e-08,
      "loss": 0.4515,
      "step": 62724
    },
    {
      "epoch": 1.9268577396860505,
      "grad_norm": 0.4058527946472168,
      "learning_rate": 6.618608972522089e-08,
      "loss": 0.4595,
      "step": 62725
    },
    {
      "epoch": 1.9268884588209996,
      "grad_norm": 0.4363134801387787,
      "learning_rate": 6.613059084475737e-08,
      "loss": 0.4054,
      "step": 62726
    },
    {
      "epoch": 1.926919177955949,
      "grad_norm": 0.47710591554641724,
      "learning_rate": 6.607511516553922e-08,
      "loss": 0.5232,
      "step": 62727
    },
    {
      "epoch": 1.926949897090898,
      "grad_norm": 0.43316954374313354,
      "learning_rate": 6.601966268769744e-08,
      "loss": 0.3713,
      "step": 62728
    },
    {
      "epoch": 1.9269806162258472,
      "grad_norm": 0.45362743735313416,
      "learning_rate": 6.596423341135972e-08,
      "loss": 0.4705,
      "step": 62729
    },
    {
      "epoch": 1.9270113353607963,
      "grad_norm": 0.5159015655517578,
      "learning_rate": 6.590882733665594e-08,
      "loss": 0.498,
      "step": 62730
    },
    {
      "epoch": 1.9270420544957454,
      "grad_norm": 0.4246309697628021,
      "learning_rate": 6.585344446371599e-08,
      "loss": 0.5011,
      "step": 62731
    },
    {
      "epoch": 1.9270727736306945,
      "grad_norm": 0.4331017732620239,
      "learning_rate": 6.579808479266981e-08,
      "loss": 0.4416,
      "step": 62732
    },
    {
      "epoch": 1.9271034927656436,
      "grad_norm": 0.4110530614852905,
      "learning_rate": 6.574274832364502e-08,
      "loss": 0.5391,
      "step": 62733
    },
    {
      "epoch": 1.9271342119005928,
      "grad_norm": 0.452851802110672,
      "learning_rate": 6.568743505677377e-08,
      "loss": 0.5042,
      "step": 62734
    },
    {
      "epoch": 1.9271649310355419,
      "grad_norm": 0.4282723665237427,
      "learning_rate": 6.56321449921804e-08,
      "loss": 0.4283,
      "step": 62735
    },
    {
      "epoch": 1.9271956501704912,
      "grad_norm": 0.4473269283771515,
      "learning_rate": 6.557687812999924e-08,
      "loss": 0.3977,
      "step": 62736
    },
    {
      "epoch": 1.9272263693054403,
      "grad_norm": 0.46129482984542847,
      "learning_rate": 6.552163447035687e-08,
      "loss": 0.5048,
      "step": 62737
    },
    {
      "epoch": 1.9272570884403897,
      "grad_norm": 0.44249817728996277,
      "learning_rate": 6.546641401338205e-08,
      "loss": 0.5042,
      "step": 62738
    },
    {
      "epoch": 1.9272878075753388,
      "grad_norm": 0.4574926197528839,
      "learning_rate": 6.54112167592047e-08,
      "loss": 0.5074,
      "step": 62739
    },
    {
      "epoch": 1.927318526710288,
      "grad_norm": 0.46527594327926636,
      "learning_rate": 6.535604270795137e-08,
      "loss": 0.5062,
      "step": 62740
    },
    {
      "epoch": 1.927349245845237,
      "grad_norm": 0.48961731791496277,
      "learning_rate": 6.53008918597553e-08,
      "loss": 0.4757,
      "step": 62741
    },
    {
      "epoch": 1.9273799649801862,
      "grad_norm": 0.45991581678390503,
      "learning_rate": 6.524576421474194e-08,
      "loss": 0.4123,
      "step": 62742
    },
    {
      "epoch": 1.9274106841151353,
      "grad_norm": 0.4200980067253113,
      "learning_rate": 6.519065977304118e-08,
      "loss": 0.3534,
      "step": 62743
    },
    {
      "epoch": 1.9274414032500844,
      "grad_norm": 0.41896411776542664,
      "learning_rate": 6.513557853477958e-08,
      "loss": 0.5039,
      "step": 62744
    },
    {
      "epoch": 1.9274721223850335,
      "grad_norm": 0.40895307064056396,
      "learning_rate": 6.508052050009039e-08,
      "loss": 0.4318,
      "step": 62745
    },
    {
      "epoch": 1.9275028415199826,
      "grad_norm": 0.4466390311717987,
      "learning_rate": 6.502548566909794e-08,
      "loss": 0.5306,
      "step": 62746
    },
    {
      "epoch": 1.927533560654932,
      "grad_norm": 0.3996540904045105,
      "learning_rate": 6.497047404193324e-08,
      "loss": 0.4988,
      "step": 62747
    },
    {
      "epoch": 1.927564279789881,
      "grad_norm": 0.46136122941970825,
      "learning_rate": 6.491548561872285e-08,
      "loss": 0.4406,
      "step": 62748
    },
    {
      "epoch": 1.9275949989248304,
      "grad_norm": 0.4268059730529785,
      "learning_rate": 6.486052039959667e-08,
      "loss": 0.5034,
      "step": 62749
    },
    {
      "epoch": 1.9276257180597796,
      "grad_norm": 0.4676811397075653,
      "learning_rate": 6.480557838468238e-08,
      "loss": 0.4769,
      "step": 62750
    },
    {
      "epoch": 1.9276564371947287,
      "grad_norm": 0.4209023416042328,
      "learning_rate": 6.475065957410876e-08,
      "loss": 0.5265,
      "step": 62751
    },
    {
      "epoch": 1.9276871563296778,
      "grad_norm": 0.4577196538448334,
      "learning_rate": 6.469576396800459e-08,
      "loss": 0.4293,
      "step": 62752
    },
    {
      "epoch": 1.927717875464627,
      "grad_norm": 0.4401298761367798,
      "learning_rate": 6.464089156649645e-08,
      "loss": 0.4831,
      "step": 62753
    },
    {
      "epoch": 1.927748594599576,
      "grad_norm": 0.4534662067890167,
      "learning_rate": 6.458604236971311e-08,
      "loss": 0.5017,
      "step": 62754
    },
    {
      "epoch": 1.9277793137345252,
      "grad_norm": 0.405034601688385,
      "learning_rate": 6.453121637778336e-08,
      "loss": 0.5154,
      "step": 62755
    },
    {
      "epoch": 1.9278100328694743,
      "grad_norm": 0.49105221033096313,
      "learning_rate": 6.447641359083489e-08,
      "loss": 0.5272,
      "step": 62756
    },
    {
      "epoch": 1.9278407520044234,
      "grad_norm": 0.4620856046676636,
      "learning_rate": 6.442163400899537e-08,
      "loss": 0.4127,
      "step": 62757
    },
    {
      "epoch": 1.9278714711393727,
      "grad_norm": 0.42826539278030396,
      "learning_rate": 6.436687763239358e-08,
      "loss": 0.4732,
      "step": 62758
    },
    {
      "epoch": 1.9279021902743219,
      "grad_norm": 0.4098643362522125,
      "learning_rate": 6.431214446115608e-08,
      "loss": 0.5098,
      "step": 62759
    },
    {
      "epoch": 1.9279329094092712,
      "grad_norm": 0.4285005033016205,
      "learning_rate": 6.425743449541278e-08,
      "loss": 0.5253,
      "step": 62760
    },
    {
      "epoch": 1.9279636285442203,
      "grad_norm": 0.4428277313709259,
      "learning_rate": 6.420274773528912e-08,
      "loss": 0.4499,
      "step": 62761
    },
    {
      "epoch": 1.9279943476791694,
      "grad_norm": 0.4463053047657013,
      "learning_rate": 6.414808418091389e-08,
      "loss": 0.3961,
      "step": 62762
    },
    {
      "epoch": 1.9280250668141186,
      "grad_norm": 0.5646415948867798,
      "learning_rate": 6.409344383241367e-08,
      "loss": 0.4582,
      "step": 62763
    },
    {
      "epoch": 1.9280557859490677,
      "grad_norm": 0.5775253772735596,
      "learning_rate": 6.403882668991945e-08,
      "loss": 0.5033,
      "step": 62764
    },
    {
      "epoch": 1.9280865050840168,
      "grad_norm": 0.4700610935688019,
      "learning_rate": 6.398423275355448e-08,
      "loss": 0.4788,
      "step": 62765
    },
    {
      "epoch": 1.928117224218966,
      "grad_norm": 0.4685133099555969,
      "learning_rate": 6.392966202344975e-08,
      "loss": 0.4957,
      "step": 62766
    },
    {
      "epoch": 1.928147943353915,
      "grad_norm": 0.47615182399749756,
      "learning_rate": 6.387511449972961e-08,
      "loss": 0.4782,
      "step": 62767
    },
    {
      "epoch": 1.9281786624888642,
      "grad_norm": 0.4301753342151642,
      "learning_rate": 6.382059018252506e-08,
      "loss": 0.3805,
      "step": 62768
    },
    {
      "epoch": 1.9282093816238135,
      "grad_norm": 0.4332617223262787,
      "learning_rate": 6.376608907196047e-08,
      "loss": 0.4544,
      "step": 62769
    },
    {
      "epoch": 1.9282401007587626,
      "grad_norm": 0.579581081867218,
      "learning_rate": 6.371161116816349e-08,
      "loss": 0.3568,
      "step": 62770
    },
    {
      "epoch": 1.9282708198937117,
      "grad_norm": 0.4212658703327179,
      "learning_rate": 6.365715647126291e-08,
      "loss": 0.4083,
      "step": 62771
    },
    {
      "epoch": 1.928301539028661,
      "grad_norm": 0.4324924051761627,
      "learning_rate": 6.36027249813842e-08,
      "loss": 0.4444,
      "step": 62772
    },
    {
      "epoch": 1.9283322581636102,
      "grad_norm": 0.38756683468818665,
      "learning_rate": 6.354831669865614e-08,
      "loss": 0.4272,
      "step": 62773
    },
    {
      "epoch": 1.9283629772985593,
      "grad_norm": 0.4797544777393341,
      "learning_rate": 6.349393162320416e-08,
      "loss": 0.4998,
      "step": 62774
    },
    {
      "epoch": 1.9283936964335084,
      "grad_norm": 0.4501665532588959,
      "learning_rate": 6.343956975515709e-08,
      "loss": 0.4528,
      "step": 62775
    },
    {
      "epoch": 1.9284244155684576,
      "grad_norm": 0.46018996834754944,
      "learning_rate": 6.338523109463923e-08,
      "loss": 0.4706,
      "step": 62776
    },
    {
      "epoch": 1.9284551347034067,
      "grad_norm": 0.4424678683280945,
      "learning_rate": 6.333091564178051e-08,
      "loss": 0.5777,
      "step": 62777
    },
    {
      "epoch": 1.9284858538383558,
      "grad_norm": 0.4434853196144104,
      "learning_rate": 6.327662339670526e-08,
      "loss": 0.4663,
      "step": 62778
    },
    {
      "epoch": 1.928516572973305,
      "grad_norm": 0.44826629757881165,
      "learning_rate": 6.322235435954338e-08,
      "loss": 0.4226,
      "step": 62779
    },
    {
      "epoch": 1.9285472921082543,
      "grad_norm": 0.45126181840896606,
      "learning_rate": 6.31681085304181e-08,
      "loss": 0.4488,
      "step": 62780
    },
    {
      "epoch": 1.9285780112432034,
      "grad_norm": 0.4106816053390503,
      "learning_rate": 6.311388590945821e-08,
      "loss": 0.4683,
      "step": 62781
    },
    {
      "epoch": 1.9286087303781525,
      "grad_norm": 0.4216705858707428,
      "learning_rate": 6.305968649678917e-08,
      "loss": 0.5076,
      "step": 62782
    },
    {
      "epoch": 1.9286394495131018,
      "grad_norm": 0.5378296375274658,
      "learning_rate": 6.300551029253866e-08,
      "loss": 0.4868,
      "step": 62783
    },
    {
      "epoch": 1.928670168648051,
      "grad_norm": 0.4454427659511566,
      "learning_rate": 6.295135729683321e-08,
      "loss": 0.4689,
      "step": 62784
    },
    {
      "epoch": 1.928700887783,
      "grad_norm": 0.406139999628067,
      "learning_rate": 6.289722750979832e-08,
      "loss": 0.4131,
      "step": 62785
    },
    {
      "epoch": 1.9287316069179492,
      "grad_norm": 0.4566972255706787,
      "learning_rate": 6.284312093156054e-08,
      "loss": 0.492,
      "step": 62786
    },
    {
      "epoch": 1.9287623260528983,
      "grad_norm": 0.44412311911582947,
      "learning_rate": 6.278903756224752e-08,
      "loss": 0.4251,
      "step": 62787
    },
    {
      "epoch": 1.9287930451878474,
      "grad_norm": 0.4306268095970154,
      "learning_rate": 6.273497740198476e-08,
      "loss": 0.4701,
      "step": 62788
    },
    {
      "epoch": 1.9288237643227966,
      "grad_norm": 0.4571821093559265,
      "learning_rate": 6.268094045089767e-08,
      "loss": 0.4657,
      "step": 62789
    },
    {
      "epoch": 1.9288544834577457,
      "grad_norm": 0.4864358901977539,
      "learning_rate": 6.262692670911397e-08,
      "loss": 0.4114,
      "step": 62790
    },
    {
      "epoch": 1.928885202592695,
      "grad_norm": 0.39317813515663147,
      "learning_rate": 6.257293617675797e-08,
      "loss": 0.4785,
      "step": 62791
    },
    {
      "epoch": 1.9289159217276441,
      "grad_norm": 0.43995076417922974,
      "learning_rate": 6.251896885395847e-08,
      "loss": 0.5204,
      "step": 62792
    },
    {
      "epoch": 1.9289466408625933,
      "grad_norm": 0.4108213782310486,
      "learning_rate": 6.246502474083871e-08,
      "loss": 0.4629,
      "step": 62793
    },
    {
      "epoch": 1.9289773599975426,
      "grad_norm": 0.3911067247390747,
      "learning_rate": 6.241110383752636e-08,
      "loss": 0.4793,
      "step": 62794
    },
    {
      "epoch": 1.9290080791324917,
      "grad_norm": 0.43829309940338135,
      "learning_rate": 6.235720614414686e-08,
      "loss": 0.4674,
      "step": 62795
    },
    {
      "epoch": 1.9290387982674408,
      "grad_norm": 0.41181766986846924,
      "learning_rate": 6.23033316608268e-08,
      "loss": 0.492,
      "step": 62796
    },
    {
      "epoch": 1.92906951740239,
      "grad_norm": 0.4739473760128021,
      "learning_rate": 6.224948038769052e-08,
      "loss": 0.48,
      "step": 62797
    },
    {
      "epoch": 1.929100236537339,
      "grad_norm": 0.42987093329429626,
      "learning_rate": 6.219565232486458e-08,
      "loss": 0.5819,
      "step": 62798
    },
    {
      "epoch": 1.9291309556722882,
      "grad_norm": 0.40934932231903076,
      "learning_rate": 6.214184747247554e-08,
      "loss": 0.5555,
      "step": 62799
    },
    {
      "epoch": 1.9291616748072373,
      "grad_norm": 0.41086652874946594,
      "learning_rate": 6.208806583064775e-08,
      "loss": 0.4516,
      "step": 62800
    },
    {
      "epoch": 1.9291923939421864,
      "grad_norm": 0.4178835153579712,
      "learning_rate": 6.203430739950777e-08,
      "loss": 0.5326,
      "step": 62801
    },
    {
      "epoch": 1.9292231130771358,
      "grad_norm": 0.4170023202896118,
      "learning_rate": 6.198057217917996e-08,
      "loss": 0.5326,
      "step": 62802
    },
    {
      "epoch": 1.929253832212085,
      "grad_norm": 0.4226525127887726,
      "learning_rate": 6.192686016979088e-08,
      "loss": 0.4149,
      "step": 62803
    },
    {
      "epoch": 1.929284551347034,
      "grad_norm": 0.4451853036880493,
      "learning_rate": 6.187317137146598e-08,
      "loss": 0.5293,
      "step": 62804
    },
    {
      "epoch": 1.9293152704819834,
      "grad_norm": 0.4131121039390564,
      "learning_rate": 6.18195057843296e-08,
      "loss": 0.4373,
      "step": 62805
    },
    {
      "epoch": 1.9293459896169325,
      "grad_norm": 0.47877037525177,
      "learning_rate": 6.176586340850942e-08,
      "loss": 0.5043,
      "step": 62806
    },
    {
      "epoch": 1.9293767087518816,
      "grad_norm": 0.45736804604530334,
      "learning_rate": 6.171224424412759e-08,
      "loss": 0.548,
      "step": 62807
    },
    {
      "epoch": 1.9294074278868307,
      "grad_norm": 0.4621692895889282,
      "learning_rate": 6.165864829131063e-08,
      "loss": 0.4844,
      "step": 62808
    },
    {
      "epoch": 1.9294381470217798,
      "grad_norm": 0.43190470337867737,
      "learning_rate": 6.160507555018514e-08,
      "loss": 0.4607,
      "step": 62809
    },
    {
      "epoch": 1.929468866156729,
      "grad_norm": 0.4618853032588959,
      "learning_rate": 6.155152602087433e-08,
      "loss": 0.4691,
      "step": 62810
    },
    {
      "epoch": 1.929499585291678,
      "grad_norm": 0.40238597989082336,
      "learning_rate": 6.149799970350478e-08,
      "loss": 0.4732,
      "step": 62811
    },
    {
      "epoch": 1.9295303044266272,
      "grad_norm": 0.44383975863456726,
      "learning_rate": 6.144449659819974e-08,
      "loss": 0.4934,
      "step": 62812
    },
    {
      "epoch": 1.9295610235615765,
      "grad_norm": 0.41709569096565247,
      "learning_rate": 6.139101670508685e-08,
      "loss": 0.4238,
      "step": 62813
    },
    {
      "epoch": 1.9295917426965257,
      "grad_norm": 0.5456295609474182,
      "learning_rate": 6.133756002428825e-08,
      "loss": 0.4762,
      "step": 62814
    },
    {
      "epoch": 1.9296224618314748,
      "grad_norm": 0.4328959882259369,
      "learning_rate": 6.128412655593053e-08,
      "loss": 0.4895,
      "step": 62815
    },
    {
      "epoch": 1.9296531809664241,
      "grad_norm": 0.43761053681373596,
      "learning_rate": 6.123071630013688e-08,
      "loss": 0.5205,
      "step": 62816
    },
    {
      "epoch": 1.9296839001013733,
      "grad_norm": 0.40919214487075806,
      "learning_rate": 6.117732925703279e-08,
      "loss": 0.4797,
      "step": 62817
    },
    {
      "epoch": 1.9297146192363224,
      "grad_norm": 0.4526253640651703,
      "learning_rate": 6.11239654267437e-08,
      "loss": 0.5223,
      "step": 62818
    },
    {
      "epoch": 1.9297453383712715,
      "grad_norm": 0.5244619250297546,
      "learning_rate": 6.107062480939396e-08,
      "loss": 0.4722,
      "step": 62819
    },
    {
      "epoch": 1.9297760575062206,
      "grad_norm": 0.4603917896747589,
      "learning_rate": 6.101730740510792e-08,
      "loss": 0.4035,
      "step": 62820
    },
    {
      "epoch": 1.9298067766411697,
      "grad_norm": 0.6113837361335754,
      "learning_rate": 6.096401321400991e-08,
      "loss": 0.4633,
      "step": 62821
    },
    {
      "epoch": 1.9298374957761188,
      "grad_norm": 0.4623066782951355,
      "learning_rate": 6.091074223622428e-08,
      "loss": 0.5066,
      "step": 62822
    },
    {
      "epoch": 1.929868214911068,
      "grad_norm": 0.43318971991539,
      "learning_rate": 6.08574944718765e-08,
      "loss": 0.4718,
      "step": 62823
    },
    {
      "epoch": 1.9298989340460173,
      "grad_norm": 0.6267711520195007,
      "learning_rate": 6.080426992108978e-08,
      "loss": 0.4737,
      "step": 62824
    },
    {
      "epoch": 1.9299296531809664,
      "grad_norm": 0.47769325971603394,
      "learning_rate": 6.075106858398849e-08,
      "loss": 0.4996,
      "step": 62825
    },
    {
      "epoch": 1.9299603723159156,
      "grad_norm": 0.4253435730934143,
      "learning_rate": 6.069789046069696e-08,
      "loss": 0.4686,
      "step": 62826
    },
    {
      "epoch": 1.929991091450865,
      "grad_norm": 0.48335000872612,
      "learning_rate": 6.064473555134064e-08,
      "loss": 0.5298,
      "step": 62827
    },
    {
      "epoch": 1.930021810585814,
      "grad_norm": 0.47072115540504456,
      "learning_rate": 6.059160385604279e-08,
      "loss": 0.4022,
      "step": 62828
    },
    {
      "epoch": 1.9300525297207631,
      "grad_norm": 0.4423678517341614,
      "learning_rate": 6.053849537492662e-08,
      "loss": 0.4752,
      "step": 62829
    },
    {
      "epoch": 1.9300832488557123,
      "grad_norm": 0.4432486295700073,
      "learning_rate": 6.048541010811648e-08,
      "loss": 0.4474,
      "step": 62830
    },
    {
      "epoch": 1.9301139679906614,
      "grad_norm": 0.47855061292648315,
      "learning_rate": 6.043234805573784e-08,
      "loss": 0.5002,
      "step": 62831
    },
    {
      "epoch": 1.9301446871256105,
      "grad_norm": 0.4317933917045593,
      "learning_rate": 6.03793092179139e-08,
      "loss": 0.4636,
      "step": 62832
    },
    {
      "epoch": 1.9301754062605596,
      "grad_norm": 0.5883191823959351,
      "learning_rate": 6.032629359476683e-08,
      "loss": 0.4457,
      "step": 62833
    },
    {
      "epoch": 1.9302061253955087,
      "grad_norm": 0.4274576008319855,
      "learning_rate": 6.027330118642316e-08,
      "loss": 0.513,
      "step": 62834
    },
    {
      "epoch": 1.930236844530458,
      "grad_norm": 0.42532163858413696,
      "learning_rate": 6.022033199300504e-08,
      "loss": 0.3922,
      "step": 62835
    },
    {
      "epoch": 1.9302675636654072,
      "grad_norm": 0.4609200358390808,
      "learning_rate": 6.016738601463679e-08,
      "loss": 0.4819,
      "step": 62836
    },
    {
      "epoch": 1.9302982828003563,
      "grad_norm": 0.4369780421257019,
      "learning_rate": 6.011446325144165e-08,
      "loss": 0.4895,
      "step": 62837
    },
    {
      "epoch": 1.9303290019353057,
      "grad_norm": 0.4249243140220642,
      "learning_rate": 6.006156370354288e-08,
      "loss": 0.4863,
      "step": 62838
    },
    {
      "epoch": 1.9303597210702548,
      "grad_norm": 0.39909031987190247,
      "learning_rate": 6.00086873710648e-08,
      "loss": 0.4174,
      "step": 62839
    },
    {
      "epoch": 1.930390440205204,
      "grad_norm": 0.4503781795501709,
      "learning_rate": 5.995583425413065e-08,
      "loss": 0.4273,
      "step": 62840
    },
    {
      "epoch": 1.930421159340153,
      "grad_norm": 0.409271240234375,
      "learning_rate": 5.990300435286367e-08,
      "loss": 0.4252,
      "step": 62841
    },
    {
      "epoch": 1.9304518784751021,
      "grad_norm": 0.5075729489326477,
      "learning_rate": 5.98501976673882e-08,
      "loss": 0.47,
      "step": 62842
    },
    {
      "epoch": 1.9304825976100513,
      "grad_norm": 0.43131497502326965,
      "learning_rate": 5.979741419782637e-08,
      "loss": 0.4374,
      "step": 62843
    },
    {
      "epoch": 1.9305133167450004,
      "grad_norm": 0.444352388381958,
      "learning_rate": 5.97446539443014e-08,
      "loss": 0.5233,
      "step": 62844
    },
    {
      "epoch": 1.9305440358799495,
      "grad_norm": 0.40852490067481995,
      "learning_rate": 5.969191690693765e-08,
      "loss": 0.4832,
      "step": 62845
    },
    {
      "epoch": 1.9305747550148988,
      "grad_norm": 0.41891682147979736,
      "learning_rate": 5.963920308585725e-08,
      "loss": 0.4862,
      "step": 62846
    },
    {
      "epoch": 1.930605474149848,
      "grad_norm": 0.4434017837047577,
      "learning_rate": 5.958651248118341e-08,
      "loss": 0.4704,
      "step": 62847
    },
    {
      "epoch": 1.930636193284797,
      "grad_norm": 0.45872336626052856,
      "learning_rate": 5.953384509303939e-08,
      "loss": 0.4878,
      "step": 62848
    },
    {
      "epoch": 1.9306669124197464,
      "grad_norm": 0.4526980221271515,
      "learning_rate": 5.948120092154952e-08,
      "loss": 0.4258,
      "step": 62849
    },
    {
      "epoch": 1.9306976315546955,
      "grad_norm": 0.42320486903190613,
      "learning_rate": 5.942857996683482e-08,
      "loss": 0.4399,
      "step": 62850
    },
    {
      "epoch": 1.9307283506896447,
      "grad_norm": 0.44533440470695496,
      "learning_rate": 5.937598222901963e-08,
      "loss": 0.3936,
      "step": 62851
    },
    {
      "epoch": 1.9307590698245938,
      "grad_norm": 0.4236982464790344,
      "learning_rate": 5.9323407708224975e-08,
      "loss": 0.4871,
      "step": 62852
    },
    {
      "epoch": 1.930789788959543,
      "grad_norm": 0.4606049954891205,
      "learning_rate": 5.927085640457519e-08,
      "loss": 0.465,
      "step": 62853
    },
    {
      "epoch": 1.930820508094492,
      "grad_norm": 0.7275149822235107,
      "learning_rate": 5.9218328318192407e-08,
      "loss": 0.4218,
      "step": 62854
    },
    {
      "epoch": 1.9308512272294411,
      "grad_norm": 0.46627044677734375,
      "learning_rate": 5.916582344919986e-08,
      "loss": 0.4023,
      "step": 62855
    },
    {
      "epoch": 1.9308819463643903,
      "grad_norm": 0.48644429445266724,
      "learning_rate": 5.9113341797719656e-08,
      "loss": 0.4879,
      "step": 62856
    },
    {
      "epoch": 1.9309126654993394,
      "grad_norm": 0.44110673666000366,
      "learning_rate": 5.9060883363873947e-08,
      "loss": 0.4262,
      "step": 62857
    },
    {
      "epoch": 1.9309433846342887,
      "grad_norm": 0.4857502281665802,
      "learning_rate": 5.9008448147785946e-08,
      "loss": 0.5331,
      "step": 62858
    },
    {
      "epoch": 1.9309741037692378,
      "grad_norm": 0.47545313835144043,
      "learning_rate": 5.89560361495789e-08,
      "loss": 0.4977,
      "step": 62859
    },
    {
      "epoch": 1.9310048229041872,
      "grad_norm": 0.49945446848869324,
      "learning_rate": 5.8903647369373816e-08,
      "loss": 0.4381,
      "step": 62860
    },
    {
      "epoch": 1.9310355420391363,
      "grad_norm": 0.4670237898826599,
      "learning_rate": 5.8851281807292824e-08,
      "loss": 0.5855,
      "step": 62861
    },
    {
      "epoch": 1.9310662611740854,
      "grad_norm": 0.41537296772003174,
      "learning_rate": 5.879893946346027e-08,
      "loss": 0.456,
      "step": 62862
    },
    {
      "epoch": 1.9310969803090345,
      "grad_norm": 0.45379409193992615,
      "learning_rate": 5.874662033799605e-08,
      "loss": 0.4284,
      "step": 62863
    },
    {
      "epoch": 1.9311276994439837,
      "grad_norm": 0.46931740641593933,
      "learning_rate": 5.869432443102341e-08,
      "loss": 0.4719,
      "step": 62864
    },
    {
      "epoch": 1.9311584185789328,
      "grad_norm": 0.45262014865875244,
      "learning_rate": 5.8642051742665574e-08,
      "loss": 0.4949,
      "step": 62865
    },
    {
      "epoch": 1.931189137713882,
      "grad_norm": 0.5405054688453674,
      "learning_rate": 5.8589802273042454e-08,
      "loss": 0.429,
      "step": 62866
    },
    {
      "epoch": 1.931219856848831,
      "grad_norm": 0.4592987298965454,
      "learning_rate": 5.853757602227728e-08,
      "loss": 0.5128,
      "step": 62867
    },
    {
      "epoch": 1.9312505759837801,
      "grad_norm": 0.46479204297065735,
      "learning_rate": 5.8485372990492175e-08,
      "loss": 0.43,
      "step": 62868
    },
    {
      "epoch": 1.9312812951187295,
      "grad_norm": 0.4142579138278961,
      "learning_rate": 5.8433193177808154e-08,
      "loss": 0.4525,
      "step": 62869
    },
    {
      "epoch": 1.9313120142536786,
      "grad_norm": 0.41862332820892334,
      "learning_rate": 5.838103658434846e-08,
      "loss": 0.457,
      "step": 62870
    },
    {
      "epoch": 1.931342733388628,
      "grad_norm": 0.4309953451156616,
      "learning_rate": 5.83289032102341e-08,
      "loss": 0.5095,
      "step": 62871
    },
    {
      "epoch": 1.931373452523577,
      "grad_norm": 0.42140325903892517,
      "learning_rate": 5.82767930555872e-08,
      "loss": 0.4024,
      "step": 62872
    },
    {
      "epoch": 1.9314041716585262,
      "grad_norm": 0.5620083808898926,
      "learning_rate": 5.822470612052877e-08,
      "loss": 0.3775,
      "step": 62873
    },
    {
      "epoch": 1.9314348907934753,
      "grad_norm": 0.43353474140167236,
      "learning_rate": 5.817264240518094e-08,
      "loss": 0.4484,
      "step": 62874
    },
    {
      "epoch": 1.9314656099284244,
      "grad_norm": 0.44509652256965637,
      "learning_rate": 5.812060190966473e-08,
      "loss": 0.511,
      "step": 62875
    },
    {
      "epoch": 1.9314963290633735,
      "grad_norm": 0.4429374039173126,
      "learning_rate": 5.806858463410225e-08,
      "loss": 0.5012,
      "step": 62876
    },
    {
      "epoch": 1.9315270481983227,
      "grad_norm": 0.45170220732688904,
      "learning_rate": 5.801659057861564e-08,
      "loss": 0.47,
      "step": 62877
    },
    {
      "epoch": 1.9315577673332718,
      "grad_norm": 0.4278677999973297,
      "learning_rate": 5.796461974332479e-08,
      "loss": 0.5078,
      "step": 62878
    },
    {
      "epoch": 1.931588486468221,
      "grad_norm": 0.4519510567188263,
      "learning_rate": 5.7912672128352946e-08,
      "loss": 0.5434,
      "step": 62879
    },
    {
      "epoch": 1.9316192056031702,
      "grad_norm": 0.4091857373714447,
      "learning_rate": 5.786074773382e-08,
      "loss": 0.4912,
      "step": 62880
    },
    {
      "epoch": 1.9316499247381194,
      "grad_norm": 0.42661693692207336,
      "learning_rate": 5.780884655984698e-08,
      "loss": 0.4527,
      "step": 62881
    },
    {
      "epoch": 1.9316806438730685,
      "grad_norm": 0.4319068491458893,
      "learning_rate": 5.7756968606555994e-08,
      "loss": 0.4836,
      "step": 62882
    },
    {
      "epoch": 1.9317113630080178,
      "grad_norm": 0.4707816541194916,
      "learning_rate": 5.7705113874068074e-08,
      "loss": 0.5271,
      "step": 62883
    },
    {
      "epoch": 1.931742082142967,
      "grad_norm": 0.40912148356437683,
      "learning_rate": 5.7653282362504225e-08,
      "loss": 0.4876,
      "step": 62884
    },
    {
      "epoch": 1.931772801277916,
      "grad_norm": 0.4499250650405884,
      "learning_rate": 5.7601474071985465e-08,
      "loss": 0.4635,
      "step": 62885
    },
    {
      "epoch": 1.9318035204128652,
      "grad_norm": 0.4601878821849823,
      "learning_rate": 5.75496890026328e-08,
      "loss": 0.4943,
      "step": 62886
    },
    {
      "epoch": 1.9318342395478143,
      "grad_norm": 0.564556360244751,
      "learning_rate": 5.749792715456837e-08,
      "loss": 0.5225,
      "step": 62887
    },
    {
      "epoch": 1.9318649586827634,
      "grad_norm": 0.48582932353019714,
      "learning_rate": 5.744618852791095e-08,
      "loss": 0.5401,
      "step": 62888
    },
    {
      "epoch": 1.9318956778177125,
      "grad_norm": 0.39424923062324524,
      "learning_rate": 5.739447312278157e-08,
      "loss": 0.4873,
      "step": 62889
    },
    {
      "epoch": 1.9319263969526617,
      "grad_norm": 0.48036518692970276,
      "learning_rate": 5.7342780939302346e-08,
      "loss": 0.5618,
      "step": 62890
    },
    {
      "epoch": 1.931957116087611,
      "grad_norm": 0.40262049436569214,
      "learning_rate": 5.7291111977594294e-08,
      "loss": 0.4541,
      "step": 62891
    },
    {
      "epoch": 1.9319878352225601,
      "grad_norm": 0.437716543674469,
      "learning_rate": 5.723946623777621e-08,
      "loss": 0.4605,
      "step": 62892
    },
    {
      "epoch": 1.9320185543575092,
      "grad_norm": 0.409231573343277,
      "learning_rate": 5.718784371997022e-08,
      "loss": 0.5031,
      "step": 62893
    },
    {
      "epoch": 1.9320492734924586,
      "grad_norm": 0.446785032749176,
      "learning_rate": 5.7136244424296215e-08,
      "loss": 0.4536,
      "step": 62894
    },
    {
      "epoch": 1.9320799926274077,
      "grad_norm": 0.4093784689903259,
      "learning_rate": 5.708466835087523e-08,
      "loss": 0.5189,
      "step": 62895
    },
    {
      "epoch": 1.9321107117623568,
      "grad_norm": 0.45016446709632874,
      "learning_rate": 5.703311549982715e-08,
      "loss": 0.5269,
      "step": 62896
    },
    {
      "epoch": 1.932141430897306,
      "grad_norm": 0.4233548641204834,
      "learning_rate": 5.6981585871273e-08,
      "loss": 0.3336,
      "step": 62897
    },
    {
      "epoch": 1.932172150032255,
      "grad_norm": 0.4830987751483917,
      "learning_rate": 5.6930079465331575e-08,
      "loss": 0.4378,
      "step": 62898
    },
    {
      "epoch": 1.9322028691672042,
      "grad_norm": 0.4409903585910797,
      "learning_rate": 5.6878596282124996e-08,
      "loss": 0.461,
      "step": 62899
    },
    {
      "epoch": 1.9322335883021533,
      "grad_norm": 0.41059890389442444,
      "learning_rate": 5.682713632177428e-08,
      "loss": 0.4337,
      "step": 62900
    },
    {
      "epoch": 1.9322643074371024,
      "grad_norm": 0.42276903986930847,
      "learning_rate": 5.6775699584395994e-08,
      "loss": 0.4483,
      "step": 62901
    },
    {
      "epoch": 1.9322950265720518,
      "grad_norm": 0.41898319125175476,
      "learning_rate": 5.6724286070113375e-08,
      "loss": 0.4512,
      "step": 62902
    },
    {
      "epoch": 1.9323257457070009,
      "grad_norm": 0.41903451085090637,
      "learning_rate": 5.6672895779046334e-08,
      "loss": 0.454,
      "step": 62903
    },
    {
      "epoch": 1.93235646484195,
      "grad_norm": 0.5038753747940063,
      "learning_rate": 5.6621528711313656e-08,
      "loss": 0.4831,
      "step": 62904
    },
    {
      "epoch": 1.9323871839768993,
      "grad_norm": 0.4383378326892853,
      "learning_rate": 5.657018486703636e-08,
      "loss": 0.4904,
      "step": 62905
    },
    {
      "epoch": 1.9324179031118485,
      "grad_norm": 0.4244329333305359,
      "learning_rate": 5.6518864246333236e-08,
      "loss": 0.5301,
      "step": 62906
    },
    {
      "epoch": 1.9324486222467976,
      "grad_norm": 0.42995408177375793,
      "learning_rate": 5.64675668493242e-08,
      "loss": 0.4697,
      "step": 62907
    },
    {
      "epoch": 1.9324793413817467,
      "grad_norm": 0.41532719135284424,
      "learning_rate": 5.641629267613025e-08,
      "loss": 0.3832,
      "step": 62908
    },
    {
      "epoch": 1.9325100605166958,
      "grad_norm": 0.4662703573703766,
      "learning_rate": 5.6365041726870185e-08,
      "loss": 0.432,
      "step": 62909
    },
    {
      "epoch": 1.932540779651645,
      "grad_norm": 0.4339553713798523,
      "learning_rate": 5.6313814001665026e-08,
      "loss": 0.4824,
      "step": 62910
    },
    {
      "epoch": 1.932571498786594,
      "grad_norm": 0.4508008658885956,
      "learning_rate": 5.626260950063245e-08,
      "loss": 0.5109,
      "step": 62911
    },
    {
      "epoch": 1.9326022179215432,
      "grad_norm": 0.42926695942878723,
      "learning_rate": 5.621142822389347e-08,
      "loss": 0.4639,
      "step": 62912
    },
    {
      "epoch": 1.9326329370564925,
      "grad_norm": 0.4259258210659027,
      "learning_rate": 5.616027017156689e-08,
      "loss": 0.5155,
      "step": 62913
    },
    {
      "epoch": 1.9326636561914416,
      "grad_norm": 0.4263988137245178,
      "learning_rate": 5.61091353437726e-08,
      "loss": 0.433,
      "step": 62914
    },
    {
      "epoch": 1.9326943753263908,
      "grad_norm": 0.4428367614746094,
      "learning_rate": 5.6058023740629405e-08,
      "loss": 0.4813,
      "step": 62915
    },
    {
      "epoch": 1.93272509446134,
      "grad_norm": 0.42455223202705383,
      "learning_rate": 5.600693536225721e-08,
      "loss": 0.5351,
      "step": 62916
    },
    {
      "epoch": 1.9327558135962892,
      "grad_norm": 0.42062053084373474,
      "learning_rate": 5.5955870208775906e-08,
      "loss": 0.4929,
      "step": 62917
    },
    {
      "epoch": 1.9327865327312383,
      "grad_norm": 0.4543704092502594,
      "learning_rate": 5.590482828030319e-08,
      "loss": 0.5216,
      "step": 62918
    },
    {
      "epoch": 1.9328172518661875,
      "grad_norm": 0.5708304047584534,
      "learning_rate": 5.5853809576961184e-08,
      "loss": 0.4712,
      "step": 62919
    },
    {
      "epoch": 1.9328479710011366,
      "grad_norm": 0.3948850631713867,
      "learning_rate": 5.580281409886534e-08,
      "loss": 0.4441,
      "step": 62920
    },
    {
      "epoch": 1.9328786901360857,
      "grad_norm": 0.4042043387889862,
      "learning_rate": 5.575184184613669e-08,
      "loss": 0.447,
      "step": 62921
    },
    {
      "epoch": 1.9329094092710348,
      "grad_norm": 0.43117737770080566,
      "learning_rate": 5.5700892818895124e-08,
      "loss": 0.4724,
      "step": 62922
    },
    {
      "epoch": 1.932940128405984,
      "grad_norm": 0.44238588213920593,
      "learning_rate": 5.5649967017258334e-08,
      "loss": 0.4793,
      "step": 62923
    },
    {
      "epoch": 1.9329708475409333,
      "grad_norm": 0.4200568199157715,
      "learning_rate": 5.5599064441344e-08,
      "loss": 0.5003,
      "step": 62924
    },
    {
      "epoch": 1.9330015666758824,
      "grad_norm": 0.4217981994152069,
      "learning_rate": 5.5548185091274244e-08,
      "loss": 0.4523,
      "step": 62925
    },
    {
      "epoch": 1.9330322858108315,
      "grad_norm": 0.4172693192958832,
      "learning_rate": 5.549732896716564e-08,
      "loss": 0.482,
      "step": 62926
    },
    {
      "epoch": 1.9330630049457809,
      "grad_norm": 0.4413904547691345,
      "learning_rate": 5.54464960691381e-08,
      "loss": 0.3864,
      "step": 62927
    },
    {
      "epoch": 1.93309372408073,
      "grad_norm": 0.5153887271881104,
      "learning_rate": 5.53956863973093e-08,
      "loss": 0.4389,
      "step": 62928
    },
    {
      "epoch": 1.9331244432156791,
      "grad_norm": 0.419174462556839,
      "learning_rate": 5.534489995179804e-08,
      "loss": 0.3989,
      "step": 62929
    },
    {
      "epoch": 1.9331551623506282,
      "grad_norm": 0.4236314296722412,
      "learning_rate": 5.52941367327231e-08,
      "loss": 0.5048,
      "step": 62930
    },
    {
      "epoch": 1.9331858814855774,
      "grad_norm": 0.4407958686351776,
      "learning_rate": 5.5243396740204405e-08,
      "loss": 0.4929,
      "step": 62931
    },
    {
      "epoch": 1.9332166006205265,
      "grad_norm": 0.4667995274066925,
      "learning_rate": 5.5192679974358507e-08,
      "loss": 0.5306,
      "step": 62932
    },
    {
      "epoch": 1.9332473197554756,
      "grad_norm": 0.4944344460964203,
      "learning_rate": 5.5141986435304215e-08,
      "loss": 0.5115,
      "step": 62933
    },
    {
      "epoch": 1.9332780388904247,
      "grad_norm": 0.3860246539115906,
      "learning_rate": 5.509131612316143e-08,
      "loss": 0.4912,
      "step": 62934
    },
    {
      "epoch": 1.933308758025374,
      "grad_norm": 0.5182965397834778,
      "learning_rate": 5.504066903804672e-08,
      "loss": 0.42,
      "step": 62935
    },
    {
      "epoch": 1.9333394771603232,
      "grad_norm": 0.4265816807746887,
      "learning_rate": 5.499004518008e-08,
      "loss": 0.4503,
      "step": 62936
    },
    {
      "epoch": 1.9333701962952723,
      "grad_norm": 0.4473157525062561,
      "learning_rate": 5.493944454937783e-08,
      "loss": 0.4919,
      "step": 62937
    },
    {
      "epoch": 1.9334009154302216,
      "grad_norm": 0.40986987948417664,
      "learning_rate": 5.488886714605901e-08,
      "loss": 0.4425,
      "step": 62938
    },
    {
      "epoch": 1.9334316345651708,
      "grad_norm": 0.43321508169174194,
      "learning_rate": 5.4838312970241226e-08,
      "loss": 0.4953,
      "step": 62939
    },
    {
      "epoch": 1.9334623537001199,
      "grad_norm": 0.4570313096046448,
      "learning_rate": 5.478778202204438e-08,
      "loss": 0.5017,
      "step": 62940
    },
    {
      "epoch": 1.933493072835069,
      "grad_norm": 0.4374179542064667,
      "learning_rate": 5.473727430158504e-08,
      "loss": 0.5569,
      "step": 62941
    },
    {
      "epoch": 1.9335237919700181,
      "grad_norm": 0.4447420835494995,
      "learning_rate": 5.46867898089809e-08,
      "loss": 0.4197,
      "step": 62942
    },
    {
      "epoch": 1.9335545111049672,
      "grad_norm": 0.48739171028137207,
      "learning_rate": 5.463632854434964e-08,
      "loss": 0.5009,
      "step": 62943
    },
    {
      "epoch": 1.9335852302399164,
      "grad_norm": 0.4177275598049164,
      "learning_rate": 5.4585890507811156e-08,
      "loss": 0.4965,
      "step": 62944
    },
    {
      "epoch": 1.9336159493748655,
      "grad_norm": 0.41839179396629333,
      "learning_rate": 5.453547569948092e-08,
      "loss": 0.476,
      "step": 62945
    },
    {
      "epoch": 1.9336466685098148,
      "grad_norm": 0.467938095331192,
      "learning_rate": 5.4485084119478836e-08,
      "loss": 0.5169,
      "step": 62946
    },
    {
      "epoch": 1.933677387644764,
      "grad_norm": 0.4450487792491913,
      "learning_rate": 5.4434715767920364e-08,
      "loss": 0.5237,
      "step": 62947
    },
    {
      "epoch": 1.933708106779713,
      "grad_norm": 0.46821415424346924,
      "learning_rate": 5.438437064492541e-08,
      "loss": 0.4581,
      "step": 62948
    },
    {
      "epoch": 1.9337388259146624,
      "grad_norm": 0.44322648644447327,
      "learning_rate": 5.4334048750609434e-08,
      "loss": 0.5813,
      "step": 62949
    },
    {
      "epoch": 1.9337695450496115,
      "grad_norm": 0.39159396290779114,
      "learning_rate": 5.4283750085091234e-08,
      "loss": 0.424,
      "step": 62950
    },
    {
      "epoch": 1.9338002641845606,
      "grad_norm": 0.4222147464752197,
      "learning_rate": 5.4233474648487384e-08,
      "loss": 0.4172,
      "step": 62951
    },
    {
      "epoch": 1.9338309833195098,
      "grad_norm": 0.5218830704689026,
      "learning_rate": 5.4183222440915563e-08,
      "loss": 0.4516,
      "step": 62952
    },
    {
      "epoch": 1.9338617024544589,
      "grad_norm": 0.43933066725730896,
      "learning_rate": 5.413299346249457e-08,
      "loss": 0.4089,
      "step": 62953
    },
    {
      "epoch": 1.933892421589408,
      "grad_norm": 0.4511609971523285,
      "learning_rate": 5.408278771333986e-08,
      "loss": 0.4519,
      "step": 62954
    },
    {
      "epoch": 1.9339231407243571,
      "grad_norm": 0.4445781707763672,
      "learning_rate": 5.403260519356912e-08,
      "loss": 0.4525,
      "step": 62955
    },
    {
      "epoch": 1.9339538598593062,
      "grad_norm": 0.4922933578491211,
      "learning_rate": 5.398244590330004e-08,
      "loss": 0.4708,
      "step": 62956
    },
    {
      "epoch": 1.9339845789942556,
      "grad_norm": 0.4449329674243927,
      "learning_rate": 5.39323098426503e-08,
      "loss": 0.4496,
      "step": 62957
    },
    {
      "epoch": 1.9340152981292047,
      "grad_norm": 0.4194757342338562,
      "learning_rate": 5.388219701173536e-08,
      "loss": 0.4011,
      "step": 62958
    },
    {
      "epoch": 1.9340460172641538,
      "grad_norm": 0.4135499596595764,
      "learning_rate": 5.383210741067402e-08,
      "loss": 0.4591,
      "step": 62959
    },
    {
      "epoch": 1.9340767363991032,
      "grad_norm": 0.4161619246006012,
      "learning_rate": 5.378204103958173e-08,
      "loss": 0.4584,
      "step": 62960
    },
    {
      "epoch": 1.9341074555340523,
      "grad_norm": 0.43012773990631104,
      "learning_rate": 5.37319978985773e-08,
      "loss": 0.3981,
      "step": 62961
    },
    {
      "epoch": 1.9341381746690014,
      "grad_norm": 0.5014445185661316,
      "learning_rate": 5.368197798777508e-08,
      "loss": 0.4971,
      "step": 62962
    },
    {
      "epoch": 1.9341688938039505,
      "grad_norm": 0.4358941614627838,
      "learning_rate": 5.3631981307293856e-08,
      "loss": 0.509,
      "step": 62963
    },
    {
      "epoch": 1.9341996129388996,
      "grad_norm": 0.4473273456096649,
      "learning_rate": 5.35820078572491e-08,
      "loss": 0.4392,
      "step": 62964
    },
    {
      "epoch": 1.9342303320738488,
      "grad_norm": 0.39650821685791016,
      "learning_rate": 5.3532057637759595e-08,
      "loss": 0.459,
      "step": 62965
    },
    {
      "epoch": 1.9342610512087979,
      "grad_norm": 0.4715464115142822,
      "learning_rate": 5.34821306489397e-08,
      "loss": 0.4763,
      "step": 62966
    },
    {
      "epoch": 1.934291770343747,
      "grad_norm": 0.40726155042648315,
      "learning_rate": 5.34322268909071e-08,
      "loss": 0.4604,
      "step": 62967
    },
    {
      "epoch": 1.9343224894786961,
      "grad_norm": 0.4519980549812317,
      "learning_rate": 5.338234636377837e-08,
      "loss": 0.4606,
      "step": 62968
    },
    {
      "epoch": 1.9343532086136455,
      "grad_norm": 0.552598237991333,
      "learning_rate": 5.333248906766897e-08,
      "loss": 0.411,
      "step": 62969
    },
    {
      "epoch": 1.9343839277485946,
      "grad_norm": 0.4338490068912506,
      "learning_rate": 5.328265500269658e-08,
      "loss": 0.5768,
      "step": 62970
    },
    {
      "epoch": 1.934414646883544,
      "grad_norm": 0.4560736119747162,
      "learning_rate": 5.323284416897778e-08,
      "loss": 0.4235,
      "step": 62971
    },
    {
      "epoch": 1.934445366018493,
      "grad_norm": 0.39157766103744507,
      "learning_rate": 5.3183056566628035e-08,
      "loss": 0.4002,
      "step": 62972
    },
    {
      "epoch": 1.9344760851534422,
      "grad_norm": 0.46418485045433044,
      "learning_rate": 5.313329219576391e-08,
      "loss": 0.4546,
      "step": 62973
    },
    {
      "epoch": 1.9345068042883913,
      "grad_norm": 0.4361088275909424,
      "learning_rate": 5.308355105650198e-08,
      "loss": 0.4307,
      "step": 62974
    },
    {
      "epoch": 1.9345375234233404,
      "grad_norm": 0.5049638152122498,
      "learning_rate": 5.303383314895771e-08,
      "loss": 0.4308,
      "step": 62975
    },
    {
      "epoch": 1.9345682425582895,
      "grad_norm": 0.5919721126556396,
      "learning_rate": 5.298413847324768e-08,
      "loss": 0.4834,
      "step": 62976
    },
    {
      "epoch": 1.9345989616932386,
      "grad_norm": 0.45625340938568115,
      "learning_rate": 5.2934467029487344e-08,
      "loss": 0.3922,
      "step": 62977
    },
    {
      "epoch": 1.9346296808281878,
      "grad_norm": 0.49959391355514526,
      "learning_rate": 5.288481881779439e-08,
      "loss": 0.5491,
      "step": 62978
    },
    {
      "epoch": 1.9346603999631369,
      "grad_norm": 0.43859806656837463,
      "learning_rate": 5.283519383828317e-08,
      "loss": 0.4612,
      "step": 62979
    },
    {
      "epoch": 1.9346911190980862,
      "grad_norm": 0.44307154417037964,
      "learning_rate": 5.278559209107026e-08,
      "loss": 0.4778,
      "step": 62980
    },
    {
      "epoch": 1.9347218382330353,
      "grad_norm": 0.438985139131546,
      "learning_rate": 5.2736013576271114e-08,
      "loss": 0.4614,
      "step": 62981
    },
    {
      "epoch": 1.9347525573679847,
      "grad_norm": 0.5065171122550964,
      "learning_rate": 5.2686458294001205e-08,
      "loss": 0.4346,
      "step": 62982
    },
    {
      "epoch": 1.9347832765029338,
      "grad_norm": 0.4805665612220764,
      "learning_rate": 5.2636926244377105e-08,
      "loss": 0.4803,
      "step": 62983
    },
    {
      "epoch": 1.934813995637883,
      "grad_norm": 0.44661569595336914,
      "learning_rate": 5.2587417427514274e-08,
      "loss": 0.5048,
      "step": 62984
    },
    {
      "epoch": 1.934844714772832,
      "grad_norm": 0.4461120069026947,
      "learning_rate": 5.253793184352818e-08,
      "loss": 0.5606,
      "step": 62985
    },
    {
      "epoch": 1.9348754339077812,
      "grad_norm": 0.466108113527298,
      "learning_rate": 5.2488469492535386e-08,
      "loss": 0.4104,
      "step": 62986
    },
    {
      "epoch": 1.9349061530427303,
      "grad_norm": 0.4273708462715149,
      "learning_rate": 5.2439030374649145e-08,
      "loss": 0.4897,
      "step": 62987
    },
    {
      "epoch": 1.9349368721776794,
      "grad_norm": 0.4463062882423401,
      "learning_rate": 5.2389614489987137e-08,
      "loss": 0.4666,
      "step": 62988
    },
    {
      "epoch": 1.9349675913126285,
      "grad_norm": 0.46659553050994873,
      "learning_rate": 5.2340221838662606e-08,
      "loss": 0.4067,
      "step": 62989
    },
    {
      "epoch": 1.9349983104475776,
      "grad_norm": 0.4089977741241455,
      "learning_rate": 5.229085242079435e-08,
      "loss": 0.4826,
      "step": 62990
    },
    {
      "epoch": 1.935029029582527,
      "grad_norm": 0.42050254344940186,
      "learning_rate": 5.224150623649449e-08,
      "loss": 0.4356,
      "step": 62991
    },
    {
      "epoch": 1.935059748717476,
      "grad_norm": 0.4154423177242279,
      "learning_rate": 5.2192183285878494e-08,
      "loss": 0.5033,
      "step": 62992
    },
    {
      "epoch": 1.9350904678524252,
      "grad_norm": 0.42109814286231995,
      "learning_rate": 5.2142883569062944e-08,
      "loss": 0.4277,
      "step": 62993
    },
    {
      "epoch": 1.9351211869873746,
      "grad_norm": 0.45471203327178955,
      "learning_rate": 5.209360708616218e-08,
      "loss": 0.4835,
      "step": 62994
    },
    {
      "epoch": 1.9351519061223237,
      "grad_norm": 0.47700074315071106,
      "learning_rate": 5.2044353837292786e-08,
      "loss": 0.5142,
      "step": 62995
    },
    {
      "epoch": 1.9351826252572728,
      "grad_norm": 0.4630369544029236,
      "learning_rate": 5.1995123822567995e-08,
      "loss": 0.5155,
      "step": 62996
    },
    {
      "epoch": 1.935213344392222,
      "grad_norm": 0.4065953493118286,
      "learning_rate": 5.194591704210328e-08,
      "loss": 0.5023,
      "step": 62997
    },
    {
      "epoch": 1.935244063527171,
      "grad_norm": 0.37937700748443604,
      "learning_rate": 5.189673349601299e-08,
      "loss": 0.4611,
      "step": 62998
    },
    {
      "epoch": 1.9352747826621202,
      "grad_norm": 0.4183088541030884,
      "learning_rate": 5.184757318441369e-08,
      "loss": 0.4164,
      "step": 62999
    },
    {
      "epoch": 1.9353055017970693,
      "grad_norm": 0.4737095832824707,
      "learning_rate": 5.179843610741864e-08,
      "loss": 0.5061,
      "step": 63000
    },
    {
      "epoch": 1.9353362209320184,
      "grad_norm": 0.4022386074066162,
      "learning_rate": 5.1749322265142176e-08,
      "loss": 0.4163,
      "step": 63001
    },
    {
      "epoch": 1.9353669400669677,
      "grad_norm": 0.39643657207489014,
      "learning_rate": 5.1700231657700884e-08,
      "loss": 0.3641,
      "step": 63002
    },
    {
      "epoch": 1.9353976592019169,
      "grad_norm": 0.424816757440567,
      "learning_rate": 5.165116428520911e-08,
      "loss": 0.4942,
      "step": 63003
    },
    {
      "epoch": 1.935428378336866,
      "grad_norm": 0.4230605959892273,
      "learning_rate": 5.16021201477801e-08,
      "loss": 0.4131,
      "step": 63004
    },
    {
      "epoch": 1.9354590974718153,
      "grad_norm": 0.4744824171066284,
      "learning_rate": 5.1553099245529315e-08,
      "loss": 0.4139,
      "step": 63005
    },
    {
      "epoch": 1.9354898166067644,
      "grad_norm": 0.4456319212913513,
      "learning_rate": 5.150410157857111e-08,
      "loss": 0.4971,
      "step": 63006
    },
    {
      "epoch": 1.9355205357417136,
      "grad_norm": 0.44484588503837585,
      "learning_rate": 5.145512714701984e-08,
      "loss": 0.3991,
      "step": 63007
    },
    {
      "epoch": 1.9355512548766627,
      "grad_norm": 0.5512824654579163,
      "learning_rate": 5.140617595098985e-08,
      "loss": 0.4853,
      "step": 63008
    },
    {
      "epoch": 1.9355819740116118,
      "grad_norm": 0.4207304120063782,
      "learning_rate": 5.135724799059438e-08,
      "loss": 0.4009,
      "step": 63009
    },
    {
      "epoch": 1.935612693146561,
      "grad_norm": 0.44357970356941223,
      "learning_rate": 5.130834326595113e-08,
      "loss": 0.4538,
      "step": 63010
    },
    {
      "epoch": 1.93564341228151,
      "grad_norm": 0.758641242980957,
      "learning_rate": 5.125946177717001e-08,
      "loss": 0.4109,
      "step": 63011
    },
    {
      "epoch": 1.9356741314164592,
      "grad_norm": 0.41457846760749817,
      "learning_rate": 5.121060352436869e-08,
      "loss": 0.406,
      "step": 63012
    },
    {
      "epoch": 1.9357048505514085,
      "grad_norm": 0.47213348746299744,
      "learning_rate": 5.11617685076593e-08,
      "loss": 0.3861,
      "step": 63013
    },
    {
      "epoch": 1.9357355696863576,
      "grad_norm": 0.4208642840385437,
      "learning_rate": 5.1112956727156214e-08,
      "loss": 0.4216,
      "step": 63014
    },
    {
      "epoch": 1.9357662888213067,
      "grad_norm": 0.46552544832229614,
      "learning_rate": 5.1064168182973775e-08,
      "loss": 0.4786,
      "step": 63015
    },
    {
      "epoch": 1.935797007956256,
      "grad_norm": 0.44721075892448425,
      "learning_rate": 5.1015402875225214e-08,
      "loss": 0.4188,
      "step": 63016
    },
    {
      "epoch": 1.9358277270912052,
      "grad_norm": 0.40728357434272766,
      "learning_rate": 5.0966660804026014e-08,
      "loss": 0.4639,
      "step": 63017
    },
    {
      "epoch": 1.9358584462261543,
      "grad_norm": 0.46427857875823975,
      "learning_rate": 5.091794196948829e-08,
      "loss": 0.5157,
      "step": 63018
    },
    {
      "epoch": 1.9358891653611034,
      "grad_norm": 0.39816632866859436,
      "learning_rate": 5.086924637172752e-08,
      "loss": 0.5129,
      "step": 63019
    },
    {
      "epoch": 1.9359198844960526,
      "grad_norm": 0.4143056273460388,
      "learning_rate": 5.0820574010855825e-08,
      "loss": 0.456,
      "step": 63020
    },
    {
      "epoch": 1.9359506036310017,
      "grad_norm": 0.39403679966926575,
      "learning_rate": 5.0771924886987566e-08,
      "loss": 0.4957,
      "step": 63021
    },
    {
      "epoch": 1.9359813227659508,
      "grad_norm": 0.4588410556316376,
      "learning_rate": 5.072329900023598e-08,
      "loss": 0.536,
      "step": 63022
    },
    {
      "epoch": 1.9360120419009,
      "grad_norm": 0.5202909111976624,
      "learning_rate": 5.0674696350715426e-08,
      "loss": 0.4433,
      "step": 63023
    },
    {
      "epoch": 1.9360427610358493,
      "grad_norm": 0.4162934422492981,
      "learning_rate": 5.0626116938538026e-08,
      "loss": 0.5157,
      "step": 63024
    },
    {
      "epoch": 1.9360734801707984,
      "grad_norm": 0.45855388045310974,
      "learning_rate": 5.0577560763819256e-08,
      "loss": 0.5568,
      "step": 63025
    },
    {
      "epoch": 1.9361041993057475,
      "grad_norm": 0.4576319456100464,
      "learning_rate": 5.052902782667124e-08,
      "loss": 0.4503,
      "step": 63026
    },
    {
      "epoch": 1.9361349184406969,
      "grad_norm": 0.43809592723846436,
      "learning_rate": 5.048051812720722e-08,
      "loss": 0.4987,
      "step": 63027
    },
    {
      "epoch": 1.936165637575646,
      "grad_norm": 0.39625588059425354,
      "learning_rate": 5.043203166554156e-08,
      "loss": 0.5051,
      "step": 63028
    },
    {
      "epoch": 1.936196356710595,
      "grad_norm": 0.46769601106643677,
      "learning_rate": 5.0383568441786376e-08,
      "loss": 0.4592,
      "step": 63029
    },
    {
      "epoch": 1.9362270758455442,
      "grad_norm": 0.4254841208457947,
      "learning_rate": 5.033512845605493e-08,
      "loss": 0.4911,
      "step": 63030
    },
    {
      "epoch": 1.9362577949804933,
      "grad_norm": 0.4235759377479553,
      "learning_rate": 5.0286711708460444e-08,
      "loss": 0.4259,
      "step": 63031
    },
    {
      "epoch": 1.9362885141154424,
      "grad_norm": 0.46668773889541626,
      "learning_rate": 5.023831819911729e-08,
      "loss": 0.505,
      "step": 63032
    },
    {
      "epoch": 1.9363192332503916,
      "grad_norm": 0.45688721537590027,
      "learning_rate": 5.018994792813647e-08,
      "loss": 0.48,
      "step": 63033
    },
    {
      "epoch": 1.9363499523853407,
      "grad_norm": 0.44387534260749817,
      "learning_rate": 5.014160089563236e-08,
      "loss": 0.4892,
      "step": 63034
    },
    {
      "epoch": 1.93638067152029,
      "grad_norm": 0.42042022943496704,
      "learning_rate": 5.009327710171707e-08,
      "loss": 0.4476,
      "step": 63035
    },
    {
      "epoch": 1.9364113906552392,
      "grad_norm": 0.48891010880470276,
      "learning_rate": 5.0044976546503866e-08,
      "loss": 0.4716,
      "step": 63036
    },
    {
      "epoch": 1.9364421097901883,
      "grad_norm": 0.4591800272464752,
      "learning_rate": 4.999669923010597e-08,
      "loss": 0.3798,
      "step": 63037
    },
    {
      "epoch": 1.9364728289251376,
      "grad_norm": 0.4551314413547516,
      "learning_rate": 4.994844515263553e-08,
      "loss": 0.4137,
      "step": 63038
    },
    {
      "epoch": 1.9365035480600867,
      "grad_norm": 0.4176536202430725,
      "learning_rate": 4.990021431420467e-08,
      "loss": 0.4282,
      "step": 63039
    },
    {
      "epoch": 1.9365342671950359,
      "grad_norm": 0.4673476815223694,
      "learning_rate": 4.9852006714927734e-08,
      "loss": 0.5388,
      "step": 63040
    },
    {
      "epoch": 1.936564986329985,
      "grad_norm": 0.39755815267562866,
      "learning_rate": 4.980382235491577e-08,
      "loss": 0.5153,
      "step": 63041
    },
    {
      "epoch": 1.936595705464934,
      "grad_norm": 0.44408711791038513,
      "learning_rate": 4.9755661234281994e-08,
      "loss": 0.4385,
      "step": 63042
    },
    {
      "epoch": 1.9366264245998832,
      "grad_norm": 0.4323529601097107,
      "learning_rate": 4.9707523353139664e-08,
      "loss": 0.4636,
      "step": 63043
    },
    {
      "epoch": 1.9366571437348323,
      "grad_norm": 0.4403925836086273,
      "learning_rate": 4.965940871159869e-08,
      "loss": 0.535,
      "step": 63044
    },
    {
      "epoch": 1.9366878628697815,
      "grad_norm": 0.5067728757858276,
      "learning_rate": 4.961131730977453e-08,
      "loss": 0.3907,
      "step": 63045
    },
    {
      "epoch": 1.9367185820047308,
      "grad_norm": 0.44130343198776245,
      "learning_rate": 4.95632491477771e-08,
      "loss": 0.4666,
      "step": 63046
    },
    {
      "epoch": 1.93674930113968,
      "grad_norm": 0.46823716163635254,
      "learning_rate": 4.951520422571965e-08,
      "loss": 0.4707,
      "step": 63047
    },
    {
      "epoch": 1.936780020274629,
      "grad_norm": 0.4293208420276642,
      "learning_rate": 4.9467182543715406e-08,
      "loss": 0.4784,
      "step": 63048
    },
    {
      "epoch": 1.9368107394095784,
      "grad_norm": 0.40996479988098145,
      "learning_rate": 4.9419184101874293e-08,
      "loss": 0.4978,
      "step": 63049
    },
    {
      "epoch": 1.9368414585445275,
      "grad_norm": 0.42901211977005005,
      "learning_rate": 4.9371208900310664e-08,
      "loss": 0.466,
      "step": 63050
    },
    {
      "epoch": 1.9368721776794766,
      "grad_norm": 0.46423619985580444,
      "learning_rate": 4.932325693913553e-08,
      "loss": 0.4993,
      "step": 63051
    },
    {
      "epoch": 1.9369028968144257,
      "grad_norm": 0.3992670476436615,
      "learning_rate": 4.927532821845993e-08,
      "loss": 0.4803,
      "step": 63052
    },
    {
      "epoch": 1.9369336159493749,
      "grad_norm": 0.4594440162181854,
      "learning_rate": 4.922742273839709e-08,
      "loss": 0.4692,
      "step": 63053
    },
    {
      "epoch": 1.936964335084324,
      "grad_norm": 0.5056011080741882,
      "learning_rate": 4.917954049905915e-08,
      "loss": 0.4783,
      "step": 63054
    },
    {
      "epoch": 1.936995054219273,
      "grad_norm": 0.40754061937332153,
      "learning_rate": 4.913168150055714e-08,
      "loss": 0.4508,
      "step": 63055
    },
    {
      "epoch": 1.9370257733542222,
      "grad_norm": 0.4613376259803772,
      "learning_rate": 4.9083845743002066e-08,
      "loss": 0.4137,
      "step": 63056
    },
    {
      "epoch": 1.9370564924891716,
      "grad_norm": 0.37553203105926514,
      "learning_rate": 4.903603322650718e-08,
      "loss": 0.4153,
      "step": 63057
    },
    {
      "epoch": 1.9370872116241207,
      "grad_norm": 0.4434182643890381,
      "learning_rate": 4.8988243951184624e-08,
      "loss": 0.5212,
      "step": 63058
    },
    {
      "epoch": 1.9371179307590698,
      "grad_norm": 0.38925594091415405,
      "learning_rate": 4.894047791714318e-08,
      "loss": 0.4836,
      "step": 63059
    },
    {
      "epoch": 1.9371486498940191,
      "grad_norm": 0.4555831253528595,
      "learning_rate": 4.889273512449721e-08,
      "loss": 0.5208,
      "step": 63060
    },
    {
      "epoch": 1.9371793690289683,
      "grad_norm": 0.39565011858940125,
      "learning_rate": 4.8845015573357747e-08,
      "loss": 0.4552,
      "step": 63061
    },
    {
      "epoch": 1.9372100881639174,
      "grad_norm": 0.42990806698799133,
      "learning_rate": 4.8797319263834685e-08,
      "loss": 0.5001,
      "step": 63062
    },
    {
      "epoch": 1.9372408072988665,
      "grad_norm": 0.4037550687789917,
      "learning_rate": 4.874964619604128e-08,
      "loss": 0.4031,
      "step": 63063
    },
    {
      "epoch": 1.9372715264338156,
      "grad_norm": 0.5139952898025513,
      "learning_rate": 4.8701996370087436e-08,
      "loss": 0.4963,
      "step": 63064
    },
    {
      "epoch": 1.9373022455687647,
      "grad_norm": 0.44615086913108826,
      "learning_rate": 4.865436978608529e-08,
      "loss": 0.4713,
      "step": 63065
    },
    {
      "epoch": 1.9373329647037139,
      "grad_norm": 0.4260830581188202,
      "learning_rate": 4.860676644414586e-08,
      "loss": 0.4978,
      "step": 63066
    },
    {
      "epoch": 1.937363683838663,
      "grad_norm": 0.4588146209716797,
      "learning_rate": 4.855918634438128e-08,
      "loss": 0.5161,
      "step": 63067
    },
    {
      "epoch": 1.9373944029736123,
      "grad_norm": 0.43038201332092285,
      "learning_rate": 4.8511629486900355e-08,
      "loss": 0.5278,
      "step": 63068
    },
    {
      "epoch": 1.9374251221085614,
      "grad_norm": 0.4390331506729126,
      "learning_rate": 4.846409587181633e-08,
      "loss": 0.4313,
      "step": 63069
    },
    {
      "epoch": 1.9374558412435106,
      "grad_norm": 0.44116395711898804,
      "learning_rate": 4.841658549923911e-08,
      "loss": 0.4654,
      "step": 63070
    },
    {
      "epoch": 1.93748656037846,
      "grad_norm": 0.4412091374397278,
      "learning_rate": 4.836909836927972e-08,
      "loss": 0.4185,
      "step": 63071
    },
    {
      "epoch": 1.937517279513409,
      "grad_norm": 0.4736969769001007,
      "learning_rate": 4.832163448205029e-08,
      "loss": 0.4933,
      "step": 63072
    },
    {
      "epoch": 1.9375479986483581,
      "grad_norm": 0.42688122391700745,
      "learning_rate": 4.827419383765963e-08,
      "loss": 0.4838,
      "step": 63073
    },
    {
      "epoch": 1.9375787177833073,
      "grad_norm": 0.42464008927345276,
      "learning_rate": 4.822677643621987e-08,
      "loss": 0.4125,
      "step": 63074
    },
    {
      "epoch": 1.9376094369182564,
      "grad_norm": 0.4517662823200226,
      "learning_rate": 4.817938227784203e-08,
      "loss": 0.4378,
      "step": 63075
    },
    {
      "epoch": 1.9376401560532055,
      "grad_norm": 0.41736432909965515,
      "learning_rate": 4.81320113626349e-08,
      "loss": 0.4171,
      "step": 63076
    },
    {
      "epoch": 1.9376708751881546,
      "grad_norm": 0.43402084708213806,
      "learning_rate": 4.808466369071174e-08,
      "loss": 0.4877,
      "step": 63077
    },
    {
      "epoch": 1.9377015943231037,
      "grad_norm": 0.4116496443748474,
      "learning_rate": 4.803733926218135e-08,
      "loss": 0.423,
      "step": 63078
    },
    {
      "epoch": 1.9377323134580529,
      "grad_norm": 0.4107053577899933,
      "learning_rate": 4.7990038077155854e-08,
      "loss": 0.5057,
      "step": 63079
    },
    {
      "epoch": 1.9377630325930022,
      "grad_norm": 0.38846707344055176,
      "learning_rate": 4.794276013574295e-08,
      "loss": 0.5029,
      "step": 63080
    },
    {
      "epoch": 1.9377937517279513,
      "grad_norm": 0.41305407881736755,
      "learning_rate": 4.789550543805588e-08,
      "loss": 0.4274,
      "step": 63081
    },
    {
      "epoch": 1.9378244708629007,
      "grad_norm": 0.40158918499946594,
      "learning_rate": 4.784827398420344e-08,
      "loss": 0.4972,
      "step": 63082
    },
    {
      "epoch": 1.9378551899978498,
      "grad_norm": 0.4596967399120331,
      "learning_rate": 4.780106577429666e-08,
      "loss": 0.4971,
      "step": 63083
    },
    {
      "epoch": 1.937885909132799,
      "grad_norm": 0.4118961691856384,
      "learning_rate": 4.7753880808445455e-08,
      "loss": 0.4983,
      "step": 63084
    },
    {
      "epoch": 1.937916628267748,
      "grad_norm": 0.4378140866756439,
      "learning_rate": 4.7706719086760835e-08,
      "loss": 0.4249,
      "step": 63085
    },
    {
      "epoch": 1.9379473474026971,
      "grad_norm": 0.4362328052520752,
      "learning_rate": 4.765958060935161e-08,
      "loss": 0.4536,
      "step": 63086
    },
    {
      "epoch": 1.9379780665376463,
      "grad_norm": 0.4246346950531006,
      "learning_rate": 4.761246537632769e-08,
      "loss": 0.4512,
      "step": 63087
    },
    {
      "epoch": 1.9380087856725954,
      "grad_norm": 0.4243820905685425,
      "learning_rate": 4.75653733878012e-08,
      "loss": 0.5283,
      "step": 63088
    },
    {
      "epoch": 1.9380395048075445,
      "grad_norm": 0.4737272262573242,
      "learning_rate": 4.751830464387985e-08,
      "loss": 0.4424,
      "step": 63089
    },
    {
      "epoch": 1.9380702239424936,
      "grad_norm": 0.4693456292152405,
      "learning_rate": 4.7471259144675764e-08,
      "loss": 0.5006,
      "step": 63090
    },
    {
      "epoch": 1.938100943077443,
      "grad_norm": 0.43886861205101013,
      "learning_rate": 4.742423689029663e-08,
      "loss": 0.4338,
      "step": 63091
    },
    {
      "epoch": 1.938131662212392,
      "grad_norm": 0.4255354702472687,
      "learning_rate": 4.7377237880853465e-08,
      "loss": 0.4752,
      "step": 63092
    },
    {
      "epoch": 1.9381623813473414,
      "grad_norm": 0.4220382273197174,
      "learning_rate": 4.7330262116456196e-08,
      "loss": 0.384,
      "step": 63093
    },
    {
      "epoch": 1.9381931004822905,
      "grad_norm": 0.4570213258266449,
      "learning_rate": 4.728330959721361e-08,
      "loss": 0.4662,
      "step": 63094
    },
    {
      "epoch": 1.9382238196172397,
      "grad_norm": 0.44324401021003723,
      "learning_rate": 4.723638032323674e-08,
      "loss": 0.421,
      "step": 63095
    },
    {
      "epoch": 1.9382545387521888,
      "grad_norm": 0.4227537512779236,
      "learning_rate": 4.7189474294633276e-08,
      "loss": 0.5044,
      "step": 63096
    },
    {
      "epoch": 1.938285257887138,
      "grad_norm": 0.4352323114871979,
      "learning_rate": 4.7142591511514236e-08,
      "loss": 0.4899,
      "step": 63097
    },
    {
      "epoch": 1.938315977022087,
      "grad_norm": 0.5033913850784302,
      "learning_rate": 4.709573197398953e-08,
      "loss": 0.4423,
      "step": 63098
    },
    {
      "epoch": 1.9383466961570361,
      "grad_norm": 0.4772443175315857,
      "learning_rate": 4.704889568216797e-08,
      "loss": 0.4173,
      "step": 63099
    },
    {
      "epoch": 1.9383774152919853,
      "grad_norm": 0.39542675018310547,
      "learning_rate": 4.700208263615835e-08,
      "loss": 0.5656,
      "step": 63100
    },
    {
      "epoch": 1.9384081344269344,
      "grad_norm": 0.49913349747657776,
      "learning_rate": 4.6955292836069475e-08,
      "loss": 0.4795,
      "step": 63101
    },
    {
      "epoch": 1.9384388535618837,
      "grad_norm": 0.48580971360206604,
      "learning_rate": 4.690852628201237e-08,
      "loss": 0.4762,
      "step": 63102
    },
    {
      "epoch": 1.9384695726968328,
      "grad_norm": 0.43905070424079895,
      "learning_rate": 4.6861782974095827e-08,
      "loss": 0.3588,
      "step": 63103
    },
    {
      "epoch": 1.938500291831782,
      "grad_norm": 0.4134403169155121,
      "learning_rate": 4.6815062912428655e-08,
      "loss": 0.4429,
      "step": 63104
    },
    {
      "epoch": 1.9385310109667313,
      "grad_norm": 0.3946525752544403,
      "learning_rate": 4.6768366097119656e-08,
      "loss": 0.368,
      "step": 63105
    },
    {
      "epoch": 1.9385617301016804,
      "grad_norm": 0.44907230138778687,
      "learning_rate": 4.672169252827874e-08,
      "loss": 0.5065,
      "step": 63106
    },
    {
      "epoch": 1.9385924492366295,
      "grad_norm": 0.43866610527038574,
      "learning_rate": 4.667504220601471e-08,
      "loss": 0.4524,
      "step": 63107
    },
    {
      "epoch": 1.9386231683715787,
      "grad_norm": 0.4573727548122406,
      "learning_rate": 4.6628415130435254e-08,
      "loss": 0.4676,
      "step": 63108
    },
    {
      "epoch": 1.9386538875065278,
      "grad_norm": 0.447102427482605,
      "learning_rate": 4.6581811301651404e-08,
      "loss": 0.4586,
      "step": 63109
    },
    {
      "epoch": 1.938684606641477,
      "grad_norm": 0.4238686263561249,
      "learning_rate": 4.653523071976973e-08,
      "loss": 0.5035,
      "step": 63110
    },
    {
      "epoch": 1.938715325776426,
      "grad_norm": 0.45075276494026184,
      "learning_rate": 4.648867338490126e-08,
      "loss": 0.4192,
      "step": 63111
    },
    {
      "epoch": 1.9387460449113751,
      "grad_norm": 0.43758106231689453,
      "learning_rate": 4.644213929715258e-08,
      "loss": 0.4954,
      "step": 63112
    },
    {
      "epoch": 1.9387767640463245,
      "grad_norm": 0.4028207063674927,
      "learning_rate": 4.63956284566347e-08,
      "loss": 0.4678,
      "step": 63113
    },
    {
      "epoch": 1.9388074831812736,
      "grad_norm": 0.45911315083503723,
      "learning_rate": 4.6349140863454215e-08,
      "loss": 0.5333,
      "step": 63114
    },
    {
      "epoch": 1.9388382023162227,
      "grad_norm": 0.4470508396625519,
      "learning_rate": 4.6302676517719915e-08,
      "loss": 0.4651,
      "step": 63115
    },
    {
      "epoch": 1.938868921451172,
      "grad_norm": 0.4317163825035095,
      "learning_rate": 4.625623541954172e-08,
      "loss": 0.4605,
      "step": 63116
    },
    {
      "epoch": 1.9388996405861212,
      "grad_norm": 0.40686219930648804,
      "learning_rate": 4.620981756902732e-08,
      "loss": 0.4896,
      "step": 63117
    },
    {
      "epoch": 1.9389303597210703,
      "grad_norm": 0.42575564980506897,
      "learning_rate": 4.6163422966284397e-08,
      "loss": 0.4055,
      "step": 63118
    },
    {
      "epoch": 1.9389610788560194,
      "grad_norm": 0.43441319465637207,
      "learning_rate": 4.611705161142177e-08,
      "loss": 0.5407,
      "step": 63119
    },
    {
      "epoch": 1.9389917979909685,
      "grad_norm": 0.42559584975242615,
      "learning_rate": 4.607070350454823e-08,
      "loss": 0.5021,
      "step": 63120
    },
    {
      "epoch": 1.9390225171259177,
      "grad_norm": 0.42724597454071045,
      "learning_rate": 4.602437864577258e-08,
      "loss": 0.4334,
      "step": 63121
    },
    {
      "epoch": 1.9390532362608668,
      "grad_norm": 0.5484417080879211,
      "learning_rate": 4.597807703520141e-08,
      "loss": 0.4433,
      "step": 63122
    },
    {
      "epoch": 1.939083955395816,
      "grad_norm": 0.4440423548221588,
      "learning_rate": 4.593179867294351e-08,
      "loss": 0.4748,
      "step": 63123
    },
    {
      "epoch": 1.9391146745307652,
      "grad_norm": 0.4477435350418091,
      "learning_rate": 4.588554355910768e-08,
      "loss": 0.4429,
      "step": 63124
    },
    {
      "epoch": 1.9391453936657144,
      "grad_norm": 0.4835200011730194,
      "learning_rate": 4.583931169380051e-08,
      "loss": 0.5065,
      "step": 63125
    },
    {
      "epoch": 1.9391761128006635,
      "grad_norm": 0.419307678937912,
      "learning_rate": 4.579310307713192e-08,
      "loss": 0.5328,
      "step": 63126
    },
    {
      "epoch": 1.9392068319356128,
      "grad_norm": 0.44315093755722046,
      "learning_rate": 4.574691770920736e-08,
      "loss": 0.4381,
      "step": 63127
    },
    {
      "epoch": 1.939237551070562,
      "grad_norm": 0.40287935733795166,
      "learning_rate": 4.570075559013676e-08,
      "loss": 0.4299,
      "step": 63128
    },
    {
      "epoch": 1.939268270205511,
      "grad_norm": 0.4116925001144409,
      "learning_rate": 4.56546167200278e-08,
      "loss": 0.472,
      "step": 63129
    },
    {
      "epoch": 1.9392989893404602,
      "grad_norm": 0.43172264099121094,
      "learning_rate": 4.560850109898707e-08,
      "loss": 0.4638,
      "step": 63130
    },
    {
      "epoch": 1.9393297084754093,
      "grad_norm": 0.4463995397090912,
      "learning_rate": 4.556240872712336e-08,
      "loss": 0.3913,
      "step": 63131
    },
    {
      "epoch": 1.9393604276103584,
      "grad_norm": 0.41991743445396423,
      "learning_rate": 4.551633960454327e-08,
      "loss": 0.5071,
      "step": 63132
    },
    {
      "epoch": 1.9393911467453075,
      "grad_norm": 0.43426281213760376,
      "learning_rate": 4.547029373135448e-08,
      "loss": 0.4707,
      "step": 63133
    },
    {
      "epoch": 1.9394218658802567,
      "grad_norm": 0.4573080241680145,
      "learning_rate": 4.5424271107666895e-08,
      "loss": 0.4702,
      "step": 63134
    },
    {
      "epoch": 1.939452585015206,
      "grad_norm": 0.4684596657752991,
      "learning_rate": 4.537827173358489e-08,
      "loss": 0.5124,
      "step": 63135
    },
    {
      "epoch": 1.9394833041501551,
      "grad_norm": 0.4240861237049103,
      "learning_rate": 4.533229560921726e-08,
      "loss": 0.4252,
      "step": 63136
    },
    {
      "epoch": 1.9395140232851042,
      "grad_norm": 0.4682060778141022,
      "learning_rate": 4.528634273467059e-08,
      "loss": 0.5237,
      "step": 63137
    },
    {
      "epoch": 1.9395447424200536,
      "grad_norm": 0.4366327226161957,
      "learning_rate": 4.524041311005367e-08,
      "loss": 0.4348,
      "step": 63138
    },
    {
      "epoch": 1.9395754615550027,
      "grad_norm": 0.4763392210006714,
      "learning_rate": 4.51945067354731e-08,
      "loss": 0.4396,
      "step": 63139
    },
    {
      "epoch": 1.9396061806899518,
      "grad_norm": 0.40901145339012146,
      "learning_rate": 4.5148623611035445e-08,
      "loss": 0.4755,
      "step": 63140
    },
    {
      "epoch": 1.939636899824901,
      "grad_norm": 0.4359782636165619,
      "learning_rate": 4.510276373684841e-08,
      "loss": 0.4801,
      "step": 63141
    },
    {
      "epoch": 1.93966761895985,
      "grad_norm": 0.4172225594520569,
      "learning_rate": 4.5056927113019677e-08,
      "loss": 0.443,
      "step": 63142
    },
    {
      "epoch": 1.9396983380947992,
      "grad_norm": 0.4836759865283966,
      "learning_rate": 4.501111373965583e-08,
      "loss": 0.5196,
      "step": 63143
    },
    {
      "epoch": 1.9397290572297483,
      "grad_norm": 0.43052545189857483,
      "learning_rate": 4.4965323616863456e-08,
      "loss": 0.4899,
      "step": 63144
    },
    {
      "epoch": 1.9397597763646974,
      "grad_norm": 0.45906180143356323,
      "learning_rate": 4.491955674475024e-08,
      "loss": 0.4018,
      "step": 63145
    },
    {
      "epoch": 1.9397904954996468,
      "grad_norm": 0.4375402331352234,
      "learning_rate": 4.487381312342165e-08,
      "loss": 0.4741,
      "step": 63146
    },
    {
      "epoch": 1.939821214634596,
      "grad_norm": 0.42843857407569885,
      "learning_rate": 4.4828092752986494e-08,
      "loss": 0.4185,
      "step": 63147
    },
    {
      "epoch": 1.939851933769545,
      "grad_norm": 0.43757063150405884,
      "learning_rate": 4.4782395633550244e-08,
      "loss": 0.468,
      "step": 63148
    },
    {
      "epoch": 1.9398826529044944,
      "grad_norm": 0.42038634419441223,
      "learning_rate": 4.4736721765220595e-08,
      "loss": 0.4565,
      "step": 63149
    },
    {
      "epoch": 1.9399133720394435,
      "grad_norm": 0.46723341941833496,
      "learning_rate": 4.4691071148103e-08,
      "loss": 0.4696,
      "step": 63150
    },
    {
      "epoch": 1.9399440911743926,
      "grad_norm": 0.4553430676460266,
      "learning_rate": 4.4645443782304065e-08,
      "loss": 0.4828,
      "step": 63151
    },
    {
      "epoch": 1.9399748103093417,
      "grad_norm": 0.43252813816070557,
      "learning_rate": 4.4599839667931464e-08,
      "loss": 0.4764,
      "step": 63152
    },
    {
      "epoch": 1.9400055294442908,
      "grad_norm": 0.4157114624977112,
      "learning_rate": 4.4554258805091786e-08,
      "loss": 0.5041,
      "step": 63153
    },
    {
      "epoch": 1.94003624857924,
      "grad_norm": 0.4365857243537903,
      "learning_rate": 4.45087011938905e-08,
      "loss": 0.4778,
      "step": 63154
    },
    {
      "epoch": 1.940066967714189,
      "grad_norm": 0.47837379574775696,
      "learning_rate": 4.446316683443419e-08,
      "loss": 0.428,
      "step": 63155
    },
    {
      "epoch": 1.9400976868491382,
      "grad_norm": 0.43278199434280396,
      "learning_rate": 4.4417655726829437e-08,
      "loss": 0.4384,
      "step": 63156
    },
    {
      "epoch": 1.9401284059840875,
      "grad_norm": 0.4472062289714813,
      "learning_rate": 4.4372167871182815e-08,
      "loss": 0.4142,
      "step": 63157
    },
    {
      "epoch": 1.9401591251190367,
      "grad_norm": 0.4612869918346405,
      "learning_rate": 4.4326703267600914e-08,
      "loss": 0.5523,
      "step": 63158
    },
    {
      "epoch": 1.9401898442539858,
      "grad_norm": 0.45557308197021484,
      "learning_rate": 4.428126191618809e-08,
      "loss": 0.4384,
      "step": 63159
    },
    {
      "epoch": 1.9402205633889351,
      "grad_norm": 0.41648921370506287,
      "learning_rate": 4.423584381705204e-08,
      "loss": 0.426,
      "step": 63160
    },
    {
      "epoch": 1.9402512825238842,
      "grad_norm": 0.47987180948257446,
      "learning_rate": 4.419044897029823e-08,
      "loss": 0.4796,
      "step": 63161
    },
    {
      "epoch": 1.9402820016588334,
      "grad_norm": 0.42908942699432373,
      "learning_rate": 4.414507737603324e-08,
      "loss": 0.4458,
      "step": 63162
    },
    {
      "epoch": 1.9403127207937825,
      "grad_norm": 0.48708057403564453,
      "learning_rate": 4.409972903436366e-08,
      "loss": 0.4913,
      "step": 63163
    },
    {
      "epoch": 1.9403434399287316,
      "grad_norm": 0.4554536044597626,
      "learning_rate": 4.4054403945392734e-08,
      "loss": 0.5169,
      "step": 63164
    },
    {
      "epoch": 1.9403741590636807,
      "grad_norm": 0.45443376898765564,
      "learning_rate": 4.400910210922926e-08,
      "loss": 0.4319,
      "step": 63165
    },
    {
      "epoch": 1.9404048781986298,
      "grad_norm": 0.4038482904434204,
      "learning_rate": 4.396382352597761e-08,
      "loss": 0.4813,
      "step": 63166
    },
    {
      "epoch": 1.940435597333579,
      "grad_norm": 0.4900142252445221,
      "learning_rate": 4.391856819574325e-08,
      "loss": 0.4674,
      "step": 63167
    },
    {
      "epoch": 1.9404663164685283,
      "grad_norm": 0.43539783358573914,
      "learning_rate": 4.387333611863276e-08,
      "loss": 0.5219,
      "step": 63168
    },
    {
      "epoch": 1.9404970356034774,
      "grad_norm": 0.483411967754364,
      "learning_rate": 4.382812729475161e-08,
      "loss": 0.4986,
      "step": 63169
    },
    {
      "epoch": 1.9405277547384265,
      "grad_norm": 0.43981844186782837,
      "learning_rate": 4.3782941724205275e-08,
      "loss": 0.362,
      "step": 63170
    },
    {
      "epoch": 1.9405584738733759,
      "grad_norm": 0.414035439491272,
      "learning_rate": 4.3737779407099225e-08,
      "loss": 0.4355,
      "step": 63171
    },
    {
      "epoch": 1.940589193008325,
      "grad_norm": 0.45548102259635925,
      "learning_rate": 4.3692640343538925e-08,
      "loss": 0.4423,
      "step": 63172
    },
    {
      "epoch": 1.9406199121432741,
      "grad_norm": 0.43308621644973755,
      "learning_rate": 4.364752453362986e-08,
      "loss": 0.5152,
      "step": 63173
    },
    {
      "epoch": 1.9406506312782232,
      "grad_norm": 0.4436631500720978,
      "learning_rate": 4.3602431977476376e-08,
      "loss": 0.4454,
      "step": 63174
    },
    {
      "epoch": 1.9406813504131724,
      "grad_norm": 0.4244931936264038,
      "learning_rate": 4.3557362675186175e-08,
      "loss": 0.514,
      "step": 63175
    },
    {
      "epoch": 1.9407120695481215,
      "grad_norm": 0.41338375210762024,
      "learning_rate": 4.35123166268625e-08,
      "loss": 0.4491,
      "step": 63176
    },
    {
      "epoch": 1.9407427886830706,
      "grad_norm": 0.43102988600730896,
      "learning_rate": 4.3467293832610834e-08,
      "loss": 0.4892,
      "step": 63177
    },
    {
      "epoch": 1.9407735078180197,
      "grad_norm": 0.41997483372688293,
      "learning_rate": 4.3422294292536637e-08,
      "loss": 0.5226,
      "step": 63178
    },
    {
      "epoch": 1.940804226952969,
      "grad_norm": 0.4102310240268707,
      "learning_rate": 4.337731800674538e-08,
      "loss": 0.523,
      "step": 63179
    },
    {
      "epoch": 1.9408349460879182,
      "grad_norm": 0.43436187505722046,
      "learning_rate": 4.3332364975341436e-08,
      "loss": 0.526,
      "step": 63180
    },
    {
      "epoch": 1.9408656652228673,
      "grad_norm": 0.4299527704715729,
      "learning_rate": 4.328743519843137e-08,
      "loss": 0.4433,
      "step": 63181
    },
    {
      "epoch": 1.9408963843578166,
      "grad_norm": 0.45839250087738037,
      "learning_rate": 4.3242528676117336e-08,
      "loss": 0.5027,
      "step": 63182
    },
    {
      "epoch": 1.9409271034927658,
      "grad_norm": 0.4198479652404785,
      "learning_rate": 4.319764540850591e-08,
      "loss": 0.5023,
      "step": 63183
    },
    {
      "epoch": 1.9409578226277149,
      "grad_norm": 0.41640642285346985,
      "learning_rate": 4.3152785395702556e-08,
      "loss": 0.4701,
      "step": 63184
    },
    {
      "epoch": 1.940988541762664,
      "grad_norm": 0.4124462604522705,
      "learning_rate": 4.3107948637810536e-08,
      "loss": 0.3596,
      "step": 63185
    },
    {
      "epoch": 1.9410192608976131,
      "grad_norm": 0.43477383255958557,
      "learning_rate": 4.306313513493532e-08,
      "loss": 0.4482,
      "step": 63186
    },
    {
      "epoch": 1.9410499800325622,
      "grad_norm": 0.4921020567417145,
      "learning_rate": 4.3018344887182374e-08,
      "loss": 0.5384,
      "step": 63187
    },
    {
      "epoch": 1.9410806991675114,
      "grad_norm": 0.4174483120441437,
      "learning_rate": 4.297357789465384e-08,
      "loss": 0.3805,
      "step": 63188
    },
    {
      "epoch": 1.9411114183024605,
      "grad_norm": 0.46027666330337524,
      "learning_rate": 4.292883415745741e-08,
      "loss": 0.3464,
      "step": 63189
    },
    {
      "epoch": 1.9411421374374096,
      "grad_norm": 0.432571142911911,
      "learning_rate": 4.2884113675696335e-08,
      "loss": 0.555,
      "step": 63190
    },
    {
      "epoch": 1.941172856572359,
      "grad_norm": 0.4869498610496521,
      "learning_rate": 4.283941644947387e-08,
      "loss": 0.4515,
      "step": 63191
    },
    {
      "epoch": 1.941203575707308,
      "grad_norm": 0.45241349935531616,
      "learning_rate": 4.279474247889548e-08,
      "loss": 0.4538,
      "step": 63192
    },
    {
      "epoch": 1.9412342948422574,
      "grad_norm": 0.4455139636993408,
      "learning_rate": 4.275009176406442e-08,
      "loss": 0.4778,
      "step": 63193
    },
    {
      "epoch": 1.9412650139772065,
      "grad_norm": 0.4306255578994751,
      "learning_rate": 4.2705464305087265e-08,
      "loss": 0.4687,
      "step": 63194
    },
    {
      "epoch": 1.9412957331121556,
      "grad_norm": 0.39358818531036377,
      "learning_rate": 4.266086010206727e-08,
      "loss": 0.4394,
      "step": 63195
    },
    {
      "epoch": 1.9413264522471048,
      "grad_norm": 0.4974025785923004,
      "learning_rate": 4.261627915510769e-08,
      "loss": 0.4393,
      "step": 63196
    },
    {
      "epoch": 1.9413571713820539,
      "grad_norm": 0.7410470843315125,
      "learning_rate": 4.2571721464312875e-08,
      "loss": 0.475,
      "step": 63197
    },
    {
      "epoch": 1.941387890517003,
      "grad_norm": 0.42699694633483887,
      "learning_rate": 4.2527187029787195e-08,
      "loss": 0.4867,
      "step": 63198
    },
    {
      "epoch": 1.9414186096519521,
      "grad_norm": 0.42817795276641846,
      "learning_rate": 4.248267585163501e-08,
      "loss": 0.4936,
      "step": 63199
    },
    {
      "epoch": 1.9414493287869012,
      "grad_norm": 0.41282087564468384,
      "learning_rate": 4.243818792995957e-08,
      "loss": 0.5358,
      "step": 63200
    },
    {
      "epoch": 1.9414800479218504,
      "grad_norm": 0.46330687403678894,
      "learning_rate": 4.239372326486524e-08,
      "loss": 0.4566,
      "step": 63201
    },
    {
      "epoch": 1.9415107670567997,
      "grad_norm": 0.42455801367759705,
      "learning_rate": 4.234928185645637e-08,
      "loss": 0.567,
      "step": 63202
    },
    {
      "epoch": 1.9415414861917488,
      "grad_norm": 0.4409697651863098,
      "learning_rate": 4.230486370483622e-08,
      "loss": 0.4083,
      "step": 63203
    },
    {
      "epoch": 1.9415722053266982,
      "grad_norm": 0.4234050512313843,
      "learning_rate": 4.2260468810108034e-08,
      "loss": 0.4534,
      "step": 63204
    },
    {
      "epoch": 1.9416029244616473,
      "grad_norm": 0.48167499899864197,
      "learning_rate": 4.221609717237618e-08,
      "loss": 0.4531,
      "step": 63205
    },
    {
      "epoch": 1.9416336435965964,
      "grad_norm": 0.43155866861343384,
      "learning_rate": 4.2171748791743905e-08,
      "loss": 0.4555,
      "step": 63206
    },
    {
      "epoch": 1.9416643627315455,
      "grad_norm": 0.4658600389957428,
      "learning_rate": 4.212742366831557e-08,
      "loss": 0.4541,
      "step": 63207
    },
    {
      "epoch": 1.9416950818664946,
      "grad_norm": 0.4565446376800537,
      "learning_rate": 4.2083121802193315e-08,
      "loss": 0.4816,
      "step": 63208
    },
    {
      "epoch": 1.9417258010014438,
      "grad_norm": 0.39415696263313293,
      "learning_rate": 4.2038843193481506e-08,
      "loss": 0.481,
      "step": 63209
    },
    {
      "epoch": 1.9417565201363929,
      "grad_norm": 0.4245316684246063,
      "learning_rate": 4.1994587842283386e-08,
      "loss": 0.4746,
      "step": 63210
    },
    {
      "epoch": 1.941787239271342,
      "grad_norm": 0.4663289189338684,
      "learning_rate": 4.195035574870221e-08,
      "loss": 0.5126,
      "step": 63211
    },
    {
      "epoch": 1.9418179584062911,
      "grad_norm": 0.46644866466522217,
      "learning_rate": 4.190614691284234e-08,
      "loss": 0.5096,
      "step": 63212
    },
    {
      "epoch": 1.9418486775412405,
      "grad_norm": 0.3865412771701813,
      "learning_rate": 4.186196133480591e-08,
      "loss": 0.3984,
      "step": 63213
    },
    {
      "epoch": 1.9418793966761896,
      "grad_norm": 0.43466708064079285,
      "learning_rate": 4.181779901469507e-08,
      "loss": 0.48,
      "step": 63214
    },
    {
      "epoch": 1.9419101158111387,
      "grad_norm": 0.47690632939338684,
      "learning_rate": 4.177365995261529e-08,
      "loss": 0.4603,
      "step": 63215
    },
    {
      "epoch": 1.941940834946088,
      "grad_norm": 0.45679742097854614,
      "learning_rate": 4.17295441486687e-08,
      "loss": 0.5451,
      "step": 63216
    },
    {
      "epoch": 1.9419715540810372,
      "grad_norm": 0.4676673412322998,
      "learning_rate": 4.168545160295745e-08,
      "loss": 0.5531,
      "step": 63217
    },
    {
      "epoch": 1.9420022732159863,
      "grad_norm": 0.5057947635650635,
      "learning_rate": 4.16413823155859e-08,
      "loss": 0.4156,
      "step": 63218
    },
    {
      "epoch": 1.9420329923509354,
      "grad_norm": 0.44451406598091125,
      "learning_rate": 4.1597336286656185e-08,
      "loss": 0.5045,
      "step": 63219
    },
    {
      "epoch": 1.9420637114858845,
      "grad_norm": 0.40237706899642944,
      "learning_rate": 4.155331351627156e-08,
      "loss": 0.4243,
      "step": 63220
    },
    {
      "epoch": 1.9420944306208336,
      "grad_norm": 0.5401936173439026,
      "learning_rate": 4.1509314004535285e-08,
      "loss": 0.4604,
      "step": 63221
    },
    {
      "epoch": 1.9421251497557828,
      "grad_norm": 0.42688193917274475,
      "learning_rate": 4.146533775154837e-08,
      "loss": 0.4687,
      "step": 63222
    },
    {
      "epoch": 1.9421558688907319,
      "grad_norm": 0.44999581575393677,
      "learning_rate": 4.1421384757415195e-08,
      "loss": 0.4552,
      "step": 63223
    },
    {
      "epoch": 1.9421865880256812,
      "grad_norm": 0.42896541953086853,
      "learning_rate": 4.137745502223789e-08,
      "loss": 0.4595,
      "step": 63224
    },
    {
      "epoch": 1.9422173071606303,
      "grad_norm": 0.42448344826698303,
      "learning_rate": 4.1333548546118596e-08,
      "loss": 0.4765,
      "step": 63225
    },
    {
      "epoch": 1.9422480262955795,
      "grad_norm": 0.4552326798439026,
      "learning_rate": 4.128966532916057e-08,
      "loss": 0.4598,
      "step": 63226
    },
    {
      "epoch": 1.9422787454305288,
      "grad_norm": 0.4566310942173004,
      "learning_rate": 4.124580537146594e-08,
      "loss": 0.4309,
      "step": 63227
    },
    {
      "epoch": 1.942309464565478,
      "grad_norm": 0.488271027803421,
      "learning_rate": 4.1201968673137974e-08,
      "loss": 0.4813,
      "step": 63228
    },
    {
      "epoch": 1.942340183700427,
      "grad_norm": 0.4607565402984619,
      "learning_rate": 4.115815523427768e-08,
      "loss": 0.4289,
      "step": 63229
    },
    {
      "epoch": 1.9423709028353762,
      "grad_norm": 0.49433910846710205,
      "learning_rate": 4.1114365054988334e-08,
      "loss": 0.5229,
      "step": 63230
    },
    {
      "epoch": 1.9424016219703253,
      "grad_norm": 0.44999411702156067,
      "learning_rate": 4.1070598135372066e-08,
      "loss": 0.5717,
      "step": 63231
    },
    {
      "epoch": 1.9424323411052744,
      "grad_norm": 1.930678129196167,
      "learning_rate": 4.1026854475529895e-08,
      "loss": 0.4538,
      "step": 63232
    },
    {
      "epoch": 1.9424630602402235,
      "grad_norm": 0.4419461488723755,
      "learning_rate": 4.09831340755662e-08,
      "loss": 0.4636,
      "step": 63233
    },
    {
      "epoch": 1.9424937793751726,
      "grad_norm": 0.7206912636756897,
      "learning_rate": 4.093943693558089e-08,
      "loss": 0.436,
      "step": 63234
    },
    {
      "epoch": 1.942524498510122,
      "grad_norm": 0.4347696304321289,
      "learning_rate": 4.0895763055678326e-08,
      "loss": 0.5582,
      "step": 63235
    },
    {
      "epoch": 1.942555217645071,
      "grad_norm": 0.4940843880176544,
      "learning_rate": 4.085211243595844e-08,
      "loss": 0.4453,
      "step": 63236
    },
    {
      "epoch": 1.9425859367800202,
      "grad_norm": 1.358654260635376,
      "learning_rate": 4.0808485076523355e-08,
      "loss": 0.4503,
      "step": 63237
    },
    {
      "epoch": 1.9426166559149696,
      "grad_norm": 0.45330020785331726,
      "learning_rate": 4.076488097747633e-08,
      "loss": 0.4938,
      "step": 63238
    },
    {
      "epoch": 1.9426473750499187,
      "grad_norm": 0.39872899651527405,
      "learning_rate": 4.0721300138918394e-08,
      "loss": 0.4552,
      "step": 63239
    },
    {
      "epoch": 1.9426780941848678,
      "grad_norm": 0.4173629581928253,
      "learning_rate": 4.067774256095169e-08,
      "loss": 0.5373,
      "step": 63240
    },
    {
      "epoch": 1.942708813319817,
      "grad_norm": 0.4474872946739197,
      "learning_rate": 4.0634208243677256e-08,
      "loss": 0.4465,
      "step": 63241
    },
    {
      "epoch": 1.942739532454766,
      "grad_norm": 0.43490850925445557,
      "learning_rate": 4.0590697187197215e-08,
      "loss": 0.3734,
      "step": 63242
    },
    {
      "epoch": 1.9427702515897152,
      "grad_norm": 0.4329555630683899,
      "learning_rate": 4.0547209391613715e-08,
      "loss": 0.5235,
      "step": 63243
    },
    {
      "epoch": 1.9428009707246643,
      "grad_norm": 0.4450186789035797,
      "learning_rate": 4.050374485702779e-08,
      "loss": 0.4275,
      "step": 63244
    },
    {
      "epoch": 1.9428316898596134,
      "grad_norm": 0.5032238960266113,
      "learning_rate": 4.046030358353936e-08,
      "loss": 0.4076,
      "step": 63245
    },
    {
      "epoch": 1.9428624089945628,
      "grad_norm": 0.42081332206726074,
      "learning_rate": 4.041688557125278e-08,
      "loss": 0.5224,
      "step": 63246
    },
    {
      "epoch": 1.9428931281295119,
      "grad_norm": 0.4517871141433716,
      "learning_rate": 4.037349082026798e-08,
      "loss": 0.4912,
      "step": 63247
    },
    {
      "epoch": 1.942923847264461,
      "grad_norm": 0.405089795589447,
      "learning_rate": 4.033011933068709e-08,
      "loss": 0.5097,
      "step": 63248
    },
    {
      "epoch": 1.9429545663994103,
      "grad_norm": 0.44643428921699524,
      "learning_rate": 4.028677110261003e-08,
      "loss": 0.4769,
      "step": 63249
    },
    {
      "epoch": 1.9429852855343595,
      "grad_norm": 0.46023356914520264,
      "learning_rate": 4.0243446136138955e-08,
      "loss": 0.3938,
      "step": 63250
    },
    {
      "epoch": 1.9430160046693086,
      "grad_norm": 0.3839474320411682,
      "learning_rate": 4.020014443137488e-08,
      "loss": 0.493,
      "step": 63251
    },
    {
      "epoch": 1.9430467238042577,
      "grad_norm": 0.43375933170318604,
      "learning_rate": 4.0156865988418833e-08,
      "loss": 0.4492,
      "step": 63252
    },
    {
      "epoch": 1.9430774429392068,
      "grad_norm": 0.4912400543689728,
      "learning_rate": 4.011361080737186e-08,
      "loss": 0.3419,
      "step": 63253
    },
    {
      "epoch": 1.943108162074156,
      "grad_norm": 0.48840054869651794,
      "learning_rate": 4.007037888833609e-08,
      "loss": 0.453,
      "step": 63254
    },
    {
      "epoch": 1.943138881209105,
      "grad_norm": 0.41215360164642334,
      "learning_rate": 4.002717023141034e-08,
      "loss": 0.4943,
      "step": 63255
    },
    {
      "epoch": 1.9431696003440542,
      "grad_norm": 0.4530201554298401,
      "learning_rate": 3.998398483669674e-08,
      "loss": 0.3519,
      "step": 63256
    },
    {
      "epoch": 1.9432003194790035,
      "grad_norm": 0.4483824372291565,
      "learning_rate": 3.994082270429744e-08,
      "loss": 0.5426,
      "step": 63257
    },
    {
      "epoch": 1.9432310386139526,
      "grad_norm": 0.4890451729297638,
      "learning_rate": 3.989768383431125e-08,
      "loss": 0.448,
      "step": 63258
    },
    {
      "epoch": 1.9432617577489018,
      "grad_norm": 0.4284643530845642,
      "learning_rate": 3.98545682268392e-08,
      "loss": 0.5398,
      "step": 63259
    },
    {
      "epoch": 1.943292476883851,
      "grad_norm": 0.4562978446483612,
      "learning_rate": 3.981147588198231e-08,
      "loss": 0.4566,
      "step": 63260
    },
    {
      "epoch": 1.9433231960188002,
      "grad_norm": 0.44215381145477295,
      "learning_rate": 3.976840679984162e-08,
      "loss": 0.5999,
      "step": 63261
    },
    {
      "epoch": 1.9433539151537493,
      "grad_norm": 0.5177099704742432,
      "learning_rate": 3.9725360980518155e-08,
      "loss": 0.4861,
      "step": 63262
    },
    {
      "epoch": 1.9433846342886985,
      "grad_norm": 0.44892266392707825,
      "learning_rate": 3.968233842411073e-08,
      "loss": 0.4544,
      "step": 63263
    },
    {
      "epoch": 1.9434153534236476,
      "grad_norm": 0.47447121143341064,
      "learning_rate": 3.963933913072149e-08,
      "loss": 0.4312,
      "step": 63264
    },
    {
      "epoch": 1.9434460725585967,
      "grad_norm": 0.49217477440834045,
      "learning_rate": 3.959636310044923e-08,
      "loss": 0.4885,
      "step": 63265
    },
    {
      "epoch": 1.9434767916935458,
      "grad_norm": 0.42550477385520935,
      "learning_rate": 3.95534103333961e-08,
      "loss": 0.5146,
      "step": 63266
    },
    {
      "epoch": 1.943507510828495,
      "grad_norm": 0.4394614100456238,
      "learning_rate": 3.9510480829662024e-08,
      "loss": 0.5078,
      "step": 63267
    },
    {
      "epoch": 1.9435382299634443,
      "grad_norm": 0.426972895860672,
      "learning_rate": 3.94675745893458e-08,
      "loss": 0.4307,
      "step": 63268
    },
    {
      "epoch": 1.9435689490983934,
      "grad_norm": 0.4184258282184601,
      "learning_rate": 3.942469161254958e-08,
      "loss": 0.4791,
      "step": 63269
    },
    {
      "epoch": 1.9435996682333425,
      "grad_norm": 0.4135361611843109,
      "learning_rate": 3.938183189937217e-08,
      "loss": 0.4701,
      "step": 63270
    },
    {
      "epoch": 1.9436303873682919,
      "grad_norm": 0.41677090525627136,
      "learning_rate": 3.9338995449914594e-08,
      "loss": 0.5202,
      "step": 63271
    },
    {
      "epoch": 1.943661106503241,
      "grad_norm": 0.6168665289878845,
      "learning_rate": 3.929618226427567e-08,
      "loss": 0.3944,
      "step": 63272
    },
    {
      "epoch": 1.94369182563819,
      "grad_norm": 0.7652504444122314,
      "learning_rate": 3.925339234255643e-08,
      "loss": 0.416,
      "step": 63273
    },
    {
      "epoch": 1.9437225447731392,
      "grad_norm": 0.4220644235610962,
      "learning_rate": 3.9210625684856786e-08,
      "loss": 0.4565,
      "step": 63274
    },
    {
      "epoch": 1.9437532639080883,
      "grad_norm": 0.4110092520713806,
      "learning_rate": 3.916788229127666e-08,
      "loss": 0.5275,
      "step": 63275
    },
    {
      "epoch": 1.9437839830430375,
      "grad_norm": 0.4563928246498108,
      "learning_rate": 3.912516216191487e-08,
      "loss": 0.4639,
      "step": 63276
    },
    {
      "epoch": 1.9438147021779866,
      "grad_norm": 0.42879506945610046,
      "learning_rate": 3.908246529687243e-08,
      "loss": 0.4848,
      "step": 63277
    },
    {
      "epoch": 1.9438454213129357,
      "grad_norm": 1.2380340099334717,
      "learning_rate": 3.9039791696248166e-08,
      "loss": 0.531,
      "step": 63278
    },
    {
      "epoch": 1.943876140447885,
      "grad_norm": 0.44084057211875916,
      "learning_rate": 3.899714136014199e-08,
      "loss": 0.4257,
      "step": 63279
    },
    {
      "epoch": 1.9439068595828342,
      "grad_norm": 0.4489467740058899,
      "learning_rate": 3.895451428865493e-08,
      "loss": 0.5871,
      "step": 63280
    },
    {
      "epoch": 1.9439375787177833,
      "grad_norm": 0.47796204686164856,
      "learning_rate": 3.8911910481883584e-08,
      "loss": 0.5288,
      "step": 63281
    },
    {
      "epoch": 1.9439682978527326,
      "grad_norm": 0.42428895831108093,
      "learning_rate": 3.886932993993009e-08,
      "loss": 0.5068,
      "step": 63282
    },
    {
      "epoch": 1.9439990169876817,
      "grad_norm": 0.518466591835022,
      "learning_rate": 3.882677266289325e-08,
      "loss": 0.4114,
      "step": 63283
    },
    {
      "epoch": 1.9440297361226309,
      "grad_norm": 0.45530378818511963,
      "learning_rate": 3.878423865087078e-08,
      "loss": 0.4883,
      "step": 63284
    },
    {
      "epoch": 1.94406045525758,
      "grad_norm": 0.4148178696632385,
      "learning_rate": 3.87417279039648e-08,
      "loss": 0.3857,
      "step": 63285
    },
    {
      "epoch": 1.944091174392529,
      "grad_norm": 0.4745226204395294,
      "learning_rate": 3.869924042227302e-08,
      "loss": 0.4375,
      "step": 63286
    },
    {
      "epoch": 1.9441218935274782,
      "grad_norm": 0.4342443346977234,
      "learning_rate": 3.8656776205894256e-08,
      "loss": 0.4568,
      "step": 63287
    },
    {
      "epoch": 1.9441526126624273,
      "grad_norm": 0.43168017268180847,
      "learning_rate": 3.861433525492842e-08,
      "loss": 0.4513,
      "step": 63288
    },
    {
      "epoch": 1.9441833317973765,
      "grad_norm": 0.4331893026828766,
      "learning_rate": 3.8571917569475424e-08,
      "loss": 0.5019,
      "step": 63289
    },
    {
      "epoch": 1.9442140509323258,
      "grad_norm": 0.4437679350376129,
      "learning_rate": 3.8529523149631876e-08,
      "loss": 0.4589,
      "step": 63290
    },
    {
      "epoch": 1.944244770067275,
      "grad_norm": 0.4550214111804962,
      "learning_rate": 3.848715199549991e-08,
      "loss": 0.5099,
      "step": 63291
    },
    {
      "epoch": 1.944275489202224,
      "grad_norm": 0.4341861307621002,
      "learning_rate": 3.8444804107174994e-08,
      "loss": 0.605,
      "step": 63292
    },
    {
      "epoch": 1.9443062083371734,
      "grad_norm": 0.4160305857658386,
      "learning_rate": 3.840247948475928e-08,
      "loss": 0.3435,
      "step": 63293
    },
    {
      "epoch": 1.9443369274721225,
      "grad_norm": 0.6100926995277405,
      "learning_rate": 3.836017812835047e-08,
      "loss": 0.5109,
      "step": 63294
    },
    {
      "epoch": 1.9443676466070716,
      "grad_norm": 0.4393799602985382,
      "learning_rate": 3.831790003804625e-08,
      "loss": 0.5065,
      "step": 63295
    },
    {
      "epoch": 1.9443983657420207,
      "grad_norm": 0.4298354685306549,
      "learning_rate": 3.8275645213947666e-08,
      "loss": 0.5074,
      "step": 63296
    },
    {
      "epoch": 1.9444290848769699,
      "grad_norm": 0.40794605016708374,
      "learning_rate": 3.82334136561513e-08,
      "loss": 0.4269,
      "step": 63297
    },
    {
      "epoch": 1.944459804011919,
      "grad_norm": 0.42637285590171814,
      "learning_rate": 3.8191205364755955e-08,
      "loss": 0.4473,
      "step": 63298
    },
    {
      "epoch": 1.944490523146868,
      "grad_norm": 0.9473115801811218,
      "learning_rate": 3.814902033986157e-08,
      "loss": 0.5532,
      "step": 63299
    },
    {
      "epoch": 1.9445212422818172,
      "grad_norm": 0.4072786271572113,
      "learning_rate": 3.810685858156471e-08,
      "loss": 0.4352,
      "step": 63300
    },
    {
      "epoch": 1.9445519614167663,
      "grad_norm": 0.44371387362480164,
      "learning_rate": 3.806472008996642e-08,
      "loss": 0.4824,
      "step": 63301
    },
    {
      "epoch": 1.9445826805517157,
      "grad_norm": 0.48003292083740234,
      "learning_rate": 3.802260486516329e-08,
      "loss": 0.5626,
      "step": 63302
    },
    {
      "epoch": 1.9446133996866648,
      "grad_norm": 0.4423873722553253,
      "learning_rate": 3.798051290725302e-08,
      "loss": 0.4426,
      "step": 63303
    },
    {
      "epoch": 1.9446441188216141,
      "grad_norm": 0.45233139395713806,
      "learning_rate": 3.7938444216336636e-08,
      "loss": 0.459,
      "step": 63304
    },
    {
      "epoch": 1.9446748379565633,
      "grad_norm": 0.426553875207901,
      "learning_rate": 3.7896398792509614e-08,
      "loss": 0.4609,
      "step": 63305
    },
    {
      "epoch": 1.9447055570915124,
      "grad_norm": 0.4165300130844116,
      "learning_rate": 3.785437663587188e-08,
      "loss": 0.5157,
      "step": 63306
    },
    {
      "epoch": 1.9447362762264615,
      "grad_norm": 0.4732881784439087,
      "learning_rate": 3.781237774652113e-08,
      "loss": 0.3628,
      "step": 63307
    },
    {
      "epoch": 1.9447669953614106,
      "grad_norm": 0.416167676448822,
      "learning_rate": 3.777040212455396e-08,
      "loss": 0.4315,
      "step": 63308
    },
    {
      "epoch": 1.9447977144963597,
      "grad_norm": 0.4183909296989441,
      "learning_rate": 3.7728449770071394e-08,
      "loss": 0.5114,
      "step": 63309
    },
    {
      "epoch": 1.9448284336313089,
      "grad_norm": 0.45813465118408203,
      "learning_rate": 3.7686520683168916e-08,
      "loss": 0.4367,
      "step": 63310
    },
    {
      "epoch": 1.944859152766258,
      "grad_norm": 0.4242669343948364,
      "learning_rate": 3.7644614863946435e-08,
      "loss": 0.4718,
      "step": 63311
    },
    {
      "epoch": 1.944889871901207,
      "grad_norm": 0.44692325592041016,
      "learning_rate": 3.760273231249945e-08,
      "loss": 0.4976,
      "step": 63312
    },
    {
      "epoch": 1.9449205910361564,
      "grad_norm": 0.42731574177742004,
      "learning_rate": 3.756087302892786e-08,
      "loss": 0.4963,
      "step": 63313
    },
    {
      "epoch": 1.9449513101711056,
      "grad_norm": 0.4466424286365509,
      "learning_rate": 3.7519037013328264e-08,
      "loss": 0.4626,
      "step": 63314
    },
    {
      "epoch": 1.944982029306055,
      "grad_norm": 0.4147873520851135,
      "learning_rate": 3.747722426579836e-08,
      "loss": 0.477,
      "step": 63315
    },
    {
      "epoch": 1.945012748441004,
      "grad_norm": 0.45184198021888733,
      "learning_rate": 3.743543478643696e-08,
      "loss": 0.4156,
      "step": 63316
    },
    {
      "epoch": 1.9450434675759531,
      "grad_norm": 0.44596225023269653,
      "learning_rate": 3.7393668575340655e-08,
      "loss": 0.4737,
      "step": 63317
    },
    {
      "epoch": 1.9450741867109023,
      "grad_norm": 0.41802307963371277,
      "learning_rate": 3.735192563260715e-08,
      "loss": 0.4927,
      "step": 63318
    },
    {
      "epoch": 1.9451049058458514,
      "grad_norm": 0.4859345555305481,
      "learning_rate": 3.7310205958333014e-08,
      "loss": 0.435,
      "step": 63319
    },
    {
      "epoch": 1.9451356249808005,
      "grad_norm": 0.4055497944355011,
      "learning_rate": 3.7268509552618185e-08,
      "loss": 0.5223,
      "step": 63320
    },
    {
      "epoch": 1.9451663441157496,
      "grad_norm": 0.468531996011734,
      "learning_rate": 3.722683641555813e-08,
      "loss": 0.3598,
      "step": 63321
    },
    {
      "epoch": 1.9451970632506987,
      "grad_norm": 0.4490145444869995,
      "learning_rate": 3.718518654724945e-08,
      "loss": 0.4949,
      "step": 63322
    },
    {
      "epoch": 1.9452277823856479,
      "grad_norm": 0.43939465284347534,
      "learning_rate": 3.714355994779206e-08,
      "loss": 0.4309,
      "step": 63323
    },
    {
      "epoch": 1.9452585015205972,
      "grad_norm": 0.43760207295417786,
      "learning_rate": 3.710195661728033e-08,
      "loss": 0.4537,
      "step": 63324
    },
    {
      "epoch": 1.9452892206555463,
      "grad_norm": 0.49026790261268616,
      "learning_rate": 3.706037655581418e-08,
      "loss": 0.4793,
      "step": 63325
    },
    {
      "epoch": 1.9453199397904954,
      "grad_norm": 0.45529305934906006,
      "learning_rate": 3.701881976348909e-08,
      "loss": 0.5046,
      "step": 63326
    },
    {
      "epoch": 1.9453506589254448,
      "grad_norm": 0.41909506916999817,
      "learning_rate": 3.697728624040164e-08,
      "loss": 0.4866,
      "step": 63327
    },
    {
      "epoch": 1.945381378060394,
      "grad_norm": 0.554763674736023,
      "learning_rate": 3.6935775986649545e-08,
      "loss": 0.4919,
      "step": 63328
    },
    {
      "epoch": 1.945412097195343,
      "grad_norm": 0.4433899223804474,
      "learning_rate": 3.6894289002330494e-08,
      "loss": 0.5063,
      "step": 63329
    },
    {
      "epoch": 1.9454428163302921,
      "grad_norm": 0.465514212846756,
      "learning_rate": 3.685282528753997e-08,
      "loss": 0.4527,
      "step": 63330
    },
    {
      "epoch": 1.9454735354652413,
      "grad_norm": 0.43690866231918335,
      "learning_rate": 3.681138484237568e-08,
      "loss": 0.4898,
      "step": 63331
    },
    {
      "epoch": 1.9455042546001904,
      "grad_norm": 0.45389115810394287,
      "learning_rate": 3.676996766693419e-08,
      "loss": 0.4385,
      "step": 63332
    },
    {
      "epoch": 1.9455349737351395,
      "grad_norm": 0.4742077589035034,
      "learning_rate": 3.6728573761313223e-08,
      "loss": 0.4267,
      "step": 63333
    },
    {
      "epoch": 1.9455656928700886,
      "grad_norm": 0.4374413788318634,
      "learning_rate": 3.668720312560714e-08,
      "loss": 0.4852,
      "step": 63334
    },
    {
      "epoch": 1.945596412005038,
      "grad_norm": 0.4147687256336212,
      "learning_rate": 3.664585575991475e-08,
      "loss": 0.4937,
      "step": 63335
    },
    {
      "epoch": 1.945627131139987,
      "grad_norm": 0.45619335770606995,
      "learning_rate": 3.6604531664331536e-08,
      "loss": 0.4567,
      "step": 63336
    },
    {
      "epoch": 1.9456578502749362,
      "grad_norm": 0.44843512773513794,
      "learning_rate": 3.656323083895408e-08,
      "loss": 0.5265,
      "step": 63337
    },
    {
      "epoch": 1.9456885694098855,
      "grad_norm": 0.47413960099220276,
      "learning_rate": 3.652195328387897e-08,
      "loss": 0.4527,
      "step": 63338
    },
    {
      "epoch": 1.9457192885448347,
      "grad_norm": 0.4217939078807831,
      "learning_rate": 3.648069899920281e-08,
      "loss": 0.41,
      "step": 63339
    },
    {
      "epoch": 1.9457500076797838,
      "grad_norm": 0.5025016665458679,
      "learning_rate": 3.6439467985022184e-08,
      "loss": 0.4433,
      "step": 63340
    },
    {
      "epoch": 1.945780726814733,
      "grad_norm": 0.4594893157482147,
      "learning_rate": 3.639826024143256e-08,
      "loss": 0.534,
      "step": 63341
    },
    {
      "epoch": 1.945811445949682,
      "grad_norm": 0.43111729621887207,
      "learning_rate": 3.6357075768530536e-08,
      "loss": 0.4971,
      "step": 63342
    },
    {
      "epoch": 1.9458421650846311,
      "grad_norm": 0.42829665541648865,
      "learning_rate": 3.6315914566412703e-08,
      "loss": 0.4628,
      "step": 63343
    },
    {
      "epoch": 1.9458728842195803,
      "grad_norm": 0.45498624444007874,
      "learning_rate": 3.6274776635174536e-08,
      "loss": 0.529,
      "step": 63344
    },
    {
      "epoch": 1.9459036033545294,
      "grad_norm": 0.4961206912994385,
      "learning_rate": 3.623366197491373e-08,
      "loss": 0.4417,
      "step": 63345
    },
    {
      "epoch": 1.9459343224894787,
      "grad_norm": 0.4361145794391632,
      "learning_rate": 3.619257058572356e-08,
      "loss": 0.4975,
      "step": 63346
    },
    {
      "epoch": 1.9459650416244278,
      "grad_norm": 0.4041600227355957,
      "learning_rate": 3.6151502467702826e-08,
      "loss": 0.5102,
      "step": 63347
    },
    {
      "epoch": 1.945995760759377,
      "grad_norm": 0.431301474571228,
      "learning_rate": 3.611045762094589e-08,
      "loss": 0.4781,
      "step": 63348
    },
    {
      "epoch": 1.9460264798943263,
      "grad_norm": 0.4137190878391266,
      "learning_rate": 3.6069436045547136e-08,
      "loss": 0.495,
      "step": 63349
    },
    {
      "epoch": 1.9460571990292754,
      "grad_norm": 0.43647298216819763,
      "learning_rate": 3.602843774160647e-08,
      "loss": 0.4642,
      "step": 63350
    },
    {
      "epoch": 1.9460879181642246,
      "grad_norm": 0.4294685423374176,
      "learning_rate": 3.5987462709216046e-08,
      "loss": 0.4798,
      "step": 63351
    },
    {
      "epoch": 1.9461186372991737,
      "grad_norm": 0.4600476920604706,
      "learning_rate": 3.5946510948472455e-08,
      "loss": 0.5246,
      "step": 63352
    },
    {
      "epoch": 1.9461493564341228,
      "grad_norm": 0.4490390717983246,
      "learning_rate": 3.590558245947229e-08,
      "loss": 0.5011,
      "step": 63353
    },
    {
      "epoch": 1.946180075569072,
      "grad_norm": 0.42148467898368835,
      "learning_rate": 3.586467724230991e-08,
      "loss": 0.4727,
      "step": 63354
    },
    {
      "epoch": 1.946210794704021,
      "grad_norm": 0.46401548385620117,
      "learning_rate": 3.582379529708191e-08,
      "loss": 0.4492,
      "step": 63355
    },
    {
      "epoch": 1.9462415138389701,
      "grad_norm": 0.46559062600135803,
      "learning_rate": 3.578293662388377e-08,
      "loss": 0.4947,
      "step": 63356
    },
    {
      "epoch": 1.9462722329739195,
      "grad_norm": 0.462541788816452,
      "learning_rate": 3.574210122280985e-08,
      "loss": 0.4885,
      "step": 63357
    },
    {
      "epoch": 1.9463029521088686,
      "grad_norm": 0.549713671207428,
      "learning_rate": 3.570128909395676e-08,
      "loss": 0.477,
      "step": 63358
    },
    {
      "epoch": 1.9463336712438177,
      "grad_norm": 0.40860116481781006,
      "learning_rate": 3.566050023741774e-08,
      "loss": 0.5006,
      "step": 63359
    },
    {
      "epoch": 1.946364390378767,
      "grad_norm": 0.4335130453109741,
      "learning_rate": 3.561973465329049e-08,
      "loss": 0.4879,
      "step": 63360
    },
    {
      "epoch": 1.9463951095137162,
      "grad_norm": 0.4592525064945221,
      "learning_rate": 3.557899234167051e-08,
      "loss": 0.4922,
      "step": 63361
    },
    {
      "epoch": 1.9464258286486653,
      "grad_norm": 0.419455885887146,
      "learning_rate": 3.5538273302649916e-08,
      "loss": 0.4993,
      "step": 63362
    },
    {
      "epoch": 1.9464565477836144,
      "grad_norm": 0.48192098736763,
      "learning_rate": 3.549757753632643e-08,
      "loss": 0.4696,
      "step": 63363
    },
    {
      "epoch": 1.9464872669185636,
      "grad_norm": 0.4523850977420807,
      "learning_rate": 3.545690504279331e-08,
      "loss": 0.4715,
      "step": 63364
    },
    {
      "epoch": 1.9465179860535127,
      "grad_norm": 0.47359004616737366,
      "learning_rate": 3.541625582214825e-08,
      "loss": 0.4752,
      "step": 63365
    },
    {
      "epoch": 1.9465487051884618,
      "grad_norm": 0.6535109877586365,
      "learning_rate": 3.5375629874482284e-08,
      "loss": 0.494,
      "step": 63366
    },
    {
      "epoch": 1.946579424323411,
      "grad_norm": 0.3884083330631256,
      "learning_rate": 3.5335027199894234e-08,
      "loss": 0.4707,
      "step": 63367
    },
    {
      "epoch": 1.9466101434583603,
      "grad_norm": 0.4651181399822235,
      "learning_rate": 3.529444779847624e-08,
      "loss": 0.4954,
      "step": 63368
    },
    {
      "epoch": 1.9466408625933094,
      "grad_norm": 0.439497709274292,
      "learning_rate": 3.525389167032489e-08,
      "loss": 0.4962,
      "step": 63369
    },
    {
      "epoch": 1.9466715817282585,
      "grad_norm": 0.42876213788986206,
      "learning_rate": 3.521335881553234e-08,
      "loss": 0.4556,
      "step": 63370
    },
    {
      "epoch": 1.9467023008632078,
      "grad_norm": 0.403055876493454,
      "learning_rate": 3.517284923419628e-08,
      "loss": 0.4299,
      "step": 63371
    },
    {
      "epoch": 1.946733019998157,
      "grad_norm": 0.4547334909439087,
      "learning_rate": 3.513236292640998e-08,
      "loss": 0.447,
      "step": 63372
    },
    {
      "epoch": 1.946763739133106,
      "grad_norm": 0.3874664306640625,
      "learning_rate": 3.50918998922678e-08,
      "loss": 0.4859,
      "step": 63373
    },
    {
      "epoch": 1.9467944582680552,
      "grad_norm": 0.5051886439323425,
      "learning_rate": 3.505146013186411e-08,
      "loss": 0.4953,
      "step": 63374
    },
    {
      "epoch": 1.9468251774030043,
      "grad_norm": 0.4494788646697998,
      "learning_rate": 3.501104364529328e-08,
      "loss": 0.4178,
      "step": 63375
    },
    {
      "epoch": 1.9468558965379534,
      "grad_norm": 0.4313872456550598,
      "learning_rate": 3.49706504326508e-08,
      "loss": 0.4632,
      "step": 63376
    },
    {
      "epoch": 1.9468866156729026,
      "grad_norm": 0.47911199927330017,
      "learning_rate": 3.4930280494029914e-08,
      "loss": 0.4747,
      "step": 63377
    },
    {
      "epoch": 1.9469173348078517,
      "grad_norm": 0.4214673340320587,
      "learning_rate": 3.48899338295261e-08,
      "loss": 0.4816,
      "step": 63378
    },
    {
      "epoch": 1.946948053942801,
      "grad_norm": 0.4469926953315735,
      "learning_rate": 3.484961043923152e-08,
      "loss": 0.5212,
      "step": 63379
    },
    {
      "epoch": 1.9469787730777501,
      "grad_norm": 0.44694656133651733,
      "learning_rate": 3.480931032324275e-08,
      "loss": 0.3926,
      "step": 63380
    },
    {
      "epoch": 1.9470094922126993,
      "grad_norm": 0.46833303570747375,
      "learning_rate": 3.476903348165195e-08,
      "loss": 0.4902,
      "step": 63381
    },
    {
      "epoch": 1.9470402113476486,
      "grad_norm": 0.47460395097732544,
      "learning_rate": 3.472877991455459e-08,
      "loss": 0.5442,
      "step": 63382
    },
    {
      "epoch": 1.9470709304825977,
      "grad_norm": 0.4079936444759369,
      "learning_rate": 3.468854962204393e-08,
      "loss": 0.4385,
      "step": 63383
    },
    {
      "epoch": 1.9471016496175468,
      "grad_norm": 0.421004980802536,
      "learning_rate": 3.464834260421546e-08,
      "loss": 0.4087,
      "step": 63384
    },
    {
      "epoch": 1.947132368752496,
      "grad_norm": 0.6160706281661987,
      "learning_rate": 3.4608158861160205e-08,
      "loss": 0.3889,
      "step": 63385
    },
    {
      "epoch": 1.947163087887445,
      "grad_norm": 0.42351484298706055,
      "learning_rate": 3.4567998392973645e-08,
      "loss": 0.4507,
      "step": 63386
    },
    {
      "epoch": 1.9471938070223942,
      "grad_norm": 0.47227048873901367,
      "learning_rate": 3.452786119975016e-08,
      "loss": 0.5091,
      "step": 63387
    },
    {
      "epoch": 1.9472245261573433,
      "grad_norm": 0.4177722930908203,
      "learning_rate": 3.448774728158188e-08,
      "loss": 0.5259,
      "step": 63388
    },
    {
      "epoch": 1.9472552452922924,
      "grad_norm": 0.422099232673645,
      "learning_rate": 3.444765663856431e-08,
      "loss": 0.3972,
      "step": 63389
    },
    {
      "epoch": 1.9472859644272418,
      "grad_norm": 0.44666150212287903,
      "learning_rate": 3.4407589270789575e-08,
      "loss": 0.4945,
      "step": 63390
    },
    {
      "epoch": 1.947316683562191,
      "grad_norm": 0.4253738224506378,
      "learning_rate": 3.4367545178352056e-08,
      "loss": 0.4608,
      "step": 63391
    },
    {
      "epoch": 1.94734740269714,
      "grad_norm": 0.45812615752220154,
      "learning_rate": 3.432752436134612e-08,
      "loss": 0.4916,
      "step": 63392
    },
    {
      "epoch": 1.9473781218320894,
      "grad_norm": 0.47615304589271545,
      "learning_rate": 3.428752681986281e-08,
      "loss": 0.4362,
      "step": 63393
    },
    {
      "epoch": 1.9474088409670385,
      "grad_norm": 0.45790034532546997,
      "learning_rate": 3.4247552553997584e-08,
      "loss": 0.5157,
      "step": 63394
    },
    {
      "epoch": 1.9474395601019876,
      "grad_norm": 0.4786706864833832,
      "learning_rate": 3.420760156384373e-08,
      "loss": 0.4672,
      "step": 63395
    },
    {
      "epoch": 1.9474702792369367,
      "grad_norm": 0.3995455801486969,
      "learning_rate": 3.4167673849493376e-08,
      "loss": 0.5251,
      "step": 63396
    },
    {
      "epoch": 1.9475009983718858,
      "grad_norm": 0.44595959782600403,
      "learning_rate": 3.41277694110409e-08,
      "loss": 0.4975,
      "step": 63397
    },
    {
      "epoch": 1.947531717506835,
      "grad_norm": 0.46571922302246094,
      "learning_rate": 3.4087888248578446e-08,
      "loss": 0.4782,
      "step": 63398
    },
    {
      "epoch": 1.947562436641784,
      "grad_norm": 0.534075915813446,
      "learning_rate": 3.404803036220039e-08,
      "loss": 0.4297,
      "step": 63399
    },
    {
      "epoch": 1.9475931557767332,
      "grad_norm": 0.4577867090702057,
      "learning_rate": 3.4008195751997765e-08,
      "loss": 0.535,
      "step": 63400
    },
    {
      "epoch": 1.9476238749116825,
      "grad_norm": 0.4206447899341583,
      "learning_rate": 3.396838441806716e-08,
      "loss": 0.4645,
      "step": 63401
    },
    {
      "epoch": 1.9476545940466317,
      "grad_norm": 0.4522136151790619,
      "learning_rate": 3.392859636049739e-08,
      "loss": 0.5453,
      "step": 63402
    },
    {
      "epoch": 1.9476853131815808,
      "grad_norm": 0.4178032875061035,
      "learning_rate": 3.388883157938505e-08,
      "loss": 0.5199,
      "step": 63403
    },
    {
      "epoch": 1.9477160323165301,
      "grad_norm": 0.44006767868995667,
      "learning_rate": 3.384909007482007e-08,
      "loss": 0.4103,
      "step": 63404
    },
    {
      "epoch": 1.9477467514514792,
      "grad_norm": 0.4882522225379944,
      "learning_rate": 3.380937184689792e-08,
      "loss": 0.4472,
      "step": 63405
    },
    {
      "epoch": 1.9477774705864284,
      "grad_norm": 0.417306512594223,
      "learning_rate": 3.3769676895708536e-08,
      "loss": 0.5253,
      "step": 63406
    },
    {
      "epoch": 1.9478081897213775,
      "grad_norm": 0.4806731939315796,
      "learning_rate": 3.373000522134628e-08,
      "loss": 0.4837,
      "step": 63407
    },
    {
      "epoch": 1.9478389088563266,
      "grad_norm": 0.43007808923721313,
      "learning_rate": 3.369035682390442e-08,
      "loss": 0.4509,
      "step": 63408
    },
    {
      "epoch": 1.9478696279912757,
      "grad_norm": 0.4400634169578552,
      "learning_rate": 3.36507317034751e-08,
      "loss": 0.464,
      "step": 63409
    },
    {
      "epoch": 1.9479003471262248,
      "grad_norm": 0.45635098218917847,
      "learning_rate": 3.361112986014936e-08,
      "loss": 0.4953,
      "step": 63410
    },
    {
      "epoch": 1.947931066261174,
      "grad_norm": 0.5080082416534424,
      "learning_rate": 3.3571551294021564e-08,
      "loss": 0.478,
      "step": 63411
    },
    {
      "epoch": 1.947961785396123,
      "grad_norm": 0.43889907002449036,
      "learning_rate": 3.3531996005182754e-08,
      "loss": 0.4309,
      "step": 63412
    },
    {
      "epoch": 1.9479925045310724,
      "grad_norm": 0.40271925926208496,
      "learning_rate": 3.34924639937273e-08,
      "loss": 0.507,
      "step": 63413
    },
    {
      "epoch": 1.9480232236660215,
      "grad_norm": 0.42556074261665344,
      "learning_rate": 3.3452955259745126e-08,
      "loss": 0.5058,
      "step": 63414
    },
    {
      "epoch": 1.9480539428009709,
      "grad_norm": 0.42021992802619934,
      "learning_rate": 3.3413469803330603e-08,
      "loss": 0.4823,
      "step": 63415
    },
    {
      "epoch": 1.94808466193592,
      "grad_norm": 0.40237224102020264,
      "learning_rate": 3.337400762457477e-08,
      "loss": 0.402,
      "step": 63416
    },
    {
      "epoch": 1.9481153810708691,
      "grad_norm": 0.5133562088012695,
      "learning_rate": 3.333456872356866e-08,
      "loss": 0.5119,
      "step": 63417
    },
    {
      "epoch": 1.9481461002058182,
      "grad_norm": 0.4267815053462982,
      "learning_rate": 3.329515310040665e-08,
      "loss": 0.4816,
      "step": 63418
    },
    {
      "epoch": 1.9481768193407674,
      "grad_norm": 0.47155165672302246,
      "learning_rate": 3.3255760755180886e-08,
      "loss": 0.4607,
      "step": 63419
    },
    {
      "epoch": 1.9482075384757165,
      "grad_norm": 0.4886261820793152,
      "learning_rate": 3.3216391687981296e-08,
      "loss": 0.4552,
      "step": 63420
    },
    {
      "epoch": 1.9482382576106656,
      "grad_norm": 0.41064614057540894,
      "learning_rate": 3.317704589890114e-08,
      "loss": 0.4247,
      "step": 63421
    },
    {
      "epoch": 1.9482689767456147,
      "grad_norm": 0.41610291600227356,
      "learning_rate": 3.3137723388031454e-08,
      "loss": 0.5197,
      "step": 63422
    },
    {
      "epoch": 1.9482996958805638,
      "grad_norm": 0.46319055557250977,
      "learning_rate": 3.309842415546549e-08,
      "loss": 0.3987,
      "step": 63423
    },
    {
      "epoch": 1.9483304150155132,
      "grad_norm": 0.41805824637413025,
      "learning_rate": 3.30591482012943e-08,
      "loss": 0.4266,
      "step": 63424
    },
    {
      "epoch": 1.9483611341504623,
      "grad_norm": 0.45351600646972656,
      "learning_rate": 3.3019895525608915e-08,
      "loss": 0.4519,
      "step": 63425
    },
    {
      "epoch": 1.9483918532854116,
      "grad_norm": 0.45040327310562134,
      "learning_rate": 3.2980666128501485e-08,
      "loss": 0.5248,
      "step": 63426
    },
    {
      "epoch": 1.9484225724203608,
      "grad_norm": 0.46677327156066895,
      "learning_rate": 3.294146001006415e-08,
      "loss": 0.4216,
      "step": 63427
    },
    {
      "epoch": 1.9484532915553099,
      "grad_norm": 0.4182283282279968,
      "learning_rate": 3.290227717038907e-08,
      "loss": 0.4212,
      "step": 63428
    },
    {
      "epoch": 1.948484010690259,
      "grad_norm": 0.4373236298561096,
      "learning_rate": 3.2863117609565066e-08,
      "loss": 0.4464,
      "step": 63429
    },
    {
      "epoch": 1.9485147298252081,
      "grad_norm": 0.42972230911254883,
      "learning_rate": 3.2823981327686495e-08,
      "loss": 0.4513,
      "step": 63430
    },
    {
      "epoch": 1.9485454489601572,
      "grad_norm": 0.4926866888999939,
      "learning_rate": 3.2784868324843286e-08,
      "loss": 0.4723,
      "step": 63431
    },
    {
      "epoch": 1.9485761680951064,
      "grad_norm": 0.4245760142803192,
      "learning_rate": 3.27457786011276e-08,
      "loss": 0.4255,
      "step": 63432
    },
    {
      "epoch": 1.9486068872300555,
      "grad_norm": 0.45214954018592834,
      "learning_rate": 3.270671215662935e-08,
      "loss": 0.4145,
      "step": 63433
    },
    {
      "epoch": 1.9486376063650046,
      "grad_norm": 0.4914904236793518,
      "learning_rate": 3.2667668991441806e-08,
      "loss": 0.53,
      "step": 63434
    },
    {
      "epoch": 1.948668325499954,
      "grad_norm": 0.4439232647418976,
      "learning_rate": 3.262864910565378e-08,
      "loss": 0.5225,
      "step": 63435
    },
    {
      "epoch": 1.948699044634903,
      "grad_norm": 0.4234773516654968,
      "learning_rate": 3.2589652499358524e-08,
      "loss": 0.5223,
      "step": 63436
    },
    {
      "epoch": 1.9487297637698522,
      "grad_norm": 0.492086261510849,
      "learning_rate": 3.255067917264598e-08,
      "loss": 0.4971,
      "step": 63437
    },
    {
      "epoch": 1.9487604829048015,
      "grad_norm": 0.4752633571624756,
      "learning_rate": 3.251172912560718e-08,
      "loss": 0.4449,
      "step": 63438
    },
    {
      "epoch": 1.9487912020397506,
      "grad_norm": 0.4019377529621124,
      "learning_rate": 3.2472802358334276e-08,
      "loss": 0.3748,
      "step": 63439
    },
    {
      "epoch": 1.9488219211746998,
      "grad_norm": 0.4231959879398346,
      "learning_rate": 3.243389887091608e-08,
      "loss": 0.5348,
      "step": 63440
    },
    {
      "epoch": 1.9488526403096489,
      "grad_norm": 0.4206201434135437,
      "learning_rate": 3.2395018663445854e-08,
      "loss": 0.5442,
      "step": 63441
    },
    {
      "epoch": 1.948883359444598,
      "grad_norm": 0.42415955662727356,
      "learning_rate": 3.2356161736012415e-08,
      "loss": 0.4899,
      "step": 63442
    },
    {
      "epoch": 1.9489140785795471,
      "grad_norm": 0.5173636674880981,
      "learning_rate": 3.231732808870791e-08,
      "loss": 0.4257,
      "step": 63443
    },
    {
      "epoch": 1.9489447977144962,
      "grad_norm": 0.4264013171195984,
      "learning_rate": 3.227851772162116e-08,
      "loss": 0.5244,
      "step": 63444
    },
    {
      "epoch": 1.9489755168494454,
      "grad_norm": 0.43937671184539795,
      "learning_rate": 3.2239730634845426e-08,
      "loss": 0.5242,
      "step": 63445
    },
    {
      "epoch": 1.9490062359843947,
      "grad_norm": 0.4117777943611145,
      "learning_rate": 3.220096682846841e-08,
      "loss": 0.4334,
      "step": 63446
    },
    {
      "epoch": 1.9490369551193438,
      "grad_norm": 0.4527135193347931,
      "learning_rate": 3.216222630258337e-08,
      "loss": 0.4103,
      "step": 63447
    },
    {
      "epoch": 1.949067674254293,
      "grad_norm": 0.42085689306259155,
      "learning_rate": 3.2123509057279123e-08,
      "loss": 0.5371,
      "step": 63448
    },
    {
      "epoch": 1.9490983933892423,
      "grad_norm": 0.4790121912956238,
      "learning_rate": 3.208481509264671e-08,
      "loss": 0.4772,
      "step": 63449
    },
    {
      "epoch": 1.9491291125241914,
      "grad_norm": 0.4817083179950714,
      "learning_rate": 3.204614440877718e-08,
      "loss": 0.5212,
      "step": 63450
    },
    {
      "epoch": 1.9491598316591405,
      "grad_norm": 0.46083205938339233,
      "learning_rate": 3.2007497005759334e-08,
      "loss": 0.496,
      "step": 63451
    },
    {
      "epoch": 1.9491905507940896,
      "grad_norm": 0.4949878454208374,
      "learning_rate": 3.196887288368422e-08,
      "loss": 0.471,
      "step": 63452
    },
    {
      "epoch": 1.9492212699290388,
      "grad_norm": 0.44823479652404785,
      "learning_rate": 3.1930272042641765e-08,
      "loss": 0.4813,
      "step": 63453
    },
    {
      "epoch": 1.9492519890639879,
      "grad_norm": 0.46261096000671387,
      "learning_rate": 3.189169448272189e-08,
      "loss": 0.4963,
      "step": 63454
    },
    {
      "epoch": 1.949282708198937,
      "grad_norm": 0.43047937750816345,
      "learning_rate": 3.185314020401564e-08,
      "loss": 0.4917,
      "step": 63455
    },
    {
      "epoch": 1.9493134273338861,
      "grad_norm": 0.4381128251552582,
      "learning_rate": 3.1814609206612944e-08,
      "loss": 0.471,
      "step": 63456
    },
    {
      "epoch": 1.9493441464688355,
      "grad_norm": 0.49380630254745483,
      "learning_rate": 3.1776101490602617e-08,
      "loss": 0.4914,
      "step": 63457
    },
    {
      "epoch": 1.9493748656037846,
      "grad_norm": 0.433284729719162,
      "learning_rate": 3.1737617056075695e-08,
      "loss": 0.4368,
      "step": 63458
    },
    {
      "epoch": 1.9494055847387337,
      "grad_norm": 0.41882434487342834,
      "learning_rate": 3.169915590312212e-08,
      "loss": 0.471,
      "step": 63459
    },
    {
      "epoch": 1.949436303873683,
      "grad_norm": 0.4386464059352875,
      "learning_rate": 3.1660718031831793e-08,
      "loss": 0.5508,
      "step": 63460
    },
    {
      "epoch": 1.9494670230086322,
      "grad_norm": 0.4234710931777954,
      "learning_rate": 3.1622303442292445e-08,
      "loss": 0.4739,
      "step": 63461
    },
    {
      "epoch": 1.9494977421435813,
      "grad_norm": 0.4492022693157196,
      "learning_rate": 3.158391213459622e-08,
      "loss": 0.4438,
      "step": 63462
    },
    {
      "epoch": 1.9495284612785304,
      "grad_norm": 0.5738187432289124,
      "learning_rate": 3.1545544108831925e-08,
      "loss": 0.5007,
      "step": 63463
    },
    {
      "epoch": 1.9495591804134795,
      "grad_norm": 0.45138785243034363,
      "learning_rate": 3.1507199365089504e-08,
      "loss": 0.5277,
      "step": 63464
    },
    {
      "epoch": 1.9495898995484287,
      "grad_norm": 0.4271148443222046,
      "learning_rate": 3.146887790345776e-08,
      "loss": 0.5625,
      "step": 63465
    },
    {
      "epoch": 1.9496206186833778,
      "grad_norm": 0.48369738459587097,
      "learning_rate": 3.143057972402663e-08,
      "loss": 0.4225,
      "step": 63466
    },
    {
      "epoch": 1.949651337818327,
      "grad_norm": 0.42317888140678406,
      "learning_rate": 3.139230482688604e-08,
      "loss": 0.4554,
      "step": 63467
    },
    {
      "epoch": 1.9496820569532762,
      "grad_norm": 0.4117639362812042,
      "learning_rate": 3.1354053212124815e-08,
      "loss": 0.4646,
      "step": 63468
    },
    {
      "epoch": 1.9497127760882254,
      "grad_norm": 0.4485306441783905,
      "learning_rate": 3.1315824879831755e-08,
      "loss": 0.4881,
      "step": 63469
    },
    {
      "epoch": 1.9497434952231745,
      "grad_norm": 0.5220590829849243,
      "learning_rate": 3.127761983009792e-08,
      "loss": 0.4905,
      "step": 63470
    },
    {
      "epoch": 1.9497742143581238,
      "grad_norm": 0.3994188904762268,
      "learning_rate": 3.123943806300989e-08,
      "loss": 0.4281,
      "step": 63471
    },
    {
      "epoch": 1.949804933493073,
      "grad_norm": 0.4820578098297119,
      "learning_rate": 3.120127957865982e-08,
      "loss": 0.4978,
      "step": 63472
    },
    {
      "epoch": 1.949835652628022,
      "grad_norm": 0.45534834265708923,
      "learning_rate": 3.116314437713541e-08,
      "loss": 0.4967,
      "step": 63473
    },
    {
      "epoch": 1.9498663717629712,
      "grad_norm": 0.4127294421195984,
      "learning_rate": 3.1125032458524384e-08,
      "loss": 0.475,
      "step": 63474
    },
    {
      "epoch": 1.9498970908979203,
      "grad_norm": 0.4104683995246887,
      "learning_rate": 3.108694382291777e-08,
      "loss": 0.5232,
      "step": 63475
    },
    {
      "epoch": 1.9499278100328694,
      "grad_norm": 0.4849509596824646,
      "learning_rate": 3.104887847040328e-08,
      "loss": 0.4832,
      "step": 63476
    },
    {
      "epoch": 1.9499585291678185,
      "grad_norm": 0.44047537446022034,
      "learning_rate": 3.101083640107194e-08,
      "loss": 0.5405,
      "step": 63477
    },
    {
      "epoch": 1.9499892483027677,
      "grad_norm": 0.41648659110069275,
      "learning_rate": 3.0972817615009255e-08,
      "loss": 0.4389,
      "step": 63478
    },
    {
      "epoch": 1.950019967437717,
      "grad_norm": 0.4270066022872925,
      "learning_rate": 3.093482211230736e-08,
      "loss": 0.4321,
      "step": 63479
    },
    {
      "epoch": 1.9500506865726661,
      "grad_norm": 0.4637235701084137,
      "learning_rate": 3.089684989305175e-08,
      "loss": 0.4289,
      "step": 63480
    },
    {
      "epoch": 1.9500814057076152,
      "grad_norm": 0.4090602397918701,
      "learning_rate": 3.085890095733346e-08,
      "loss": 0.5182,
      "step": 63481
    },
    {
      "epoch": 1.9501121248425646,
      "grad_norm": 0.4752665162086487,
      "learning_rate": 3.082097530524131e-08,
      "loss": 0.4414,
      "step": 63482
    },
    {
      "epoch": 1.9501428439775137,
      "grad_norm": 0.4672538638114929,
      "learning_rate": 3.078307293686189e-08,
      "loss": 0.5585,
      "step": 63483
    },
    {
      "epoch": 1.9501735631124628,
      "grad_norm": 0.43270739912986755,
      "learning_rate": 3.074519385228514e-08,
      "loss": 0.4507,
      "step": 63484
    },
    {
      "epoch": 1.950204282247412,
      "grad_norm": 0.40406519174575806,
      "learning_rate": 3.070733805159876e-08,
      "loss": 0.5355,
      "step": 63485
    },
    {
      "epoch": 1.950235001382361,
      "grad_norm": 0.421095609664917,
      "learning_rate": 3.066950553489267e-08,
      "loss": 0.485,
      "step": 63486
    },
    {
      "epoch": 1.9502657205173102,
      "grad_norm": 0.42075133323669434,
      "learning_rate": 3.063169630225349e-08,
      "loss": 0.4821,
      "step": 63487
    },
    {
      "epoch": 1.9502964396522593,
      "grad_norm": 0.4291200637817383,
      "learning_rate": 3.0593910353771126e-08,
      "loss": 0.4896,
      "step": 63488
    },
    {
      "epoch": 1.9503271587872084,
      "grad_norm": 0.407105028629303,
      "learning_rate": 3.055614768953219e-08,
      "loss": 0.4119,
      "step": 63489
    },
    {
      "epoch": 1.9503578779221578,
      "grad_norm": 0.4417363107204437,
      "learning_rate": 3.051840830962549e-08,
      "loss": 0.4066,
      "step": 63490
    },
    {
      "epoch": 1.9503885970571069,
      "grad_norm": 0.47133374214172363,
      "learning_rate": 3.048069221413985e-08,
      "loss": 0.5194,
      "step": 63491
    },
    {
      "epoch": 1.950419316192056,
      "grad_norm": 0.47015509009361267,
      "learning_rate": 3.044299940316297e-08,
      "loss": 0.5401,
      "step": 63492
    },
    {
      "epoch": 1.9504500353270053,
      "grad_norm": 0.4987131953239441,
      "learning_rate": 3.040532987678146e-08,
      "loss": 0.4722,
      "step": 63493
    },
    {
      "epoch": 1.9504807544619545,
      "grad_norm": 0.48112714290618896,
      "learning_rate": 3.0367683635085246e-08,
      "loss": 0.4484,
      "step": 63494
    },
    {
      "epoch": 1.9505114735969036,
      "grad_norm": 0.5197063088417053,
      "learning_rate": 3.033006067816202e-08,
      "loss": 0.4561,
      "step": 63495
    },
    {
      "epoch": 1.9505421927318527,
      "grad_norm": 0.40034064650535583,
      "learning_rate": 3.0292461006099506e-08,
      "loss": 0.433,
      "step": 63496
    },
    {
      "epoch": 1.9505729118668018,
      "grad_norm": 0.435323029756546,
      "learning_rate": 3.025488461898429e-08,
      "loss": 0.4694,
      "step": 63497
    },
    {
      "epoch": 1.950603631001751,
      "grad_norm": 0.47941362857818604,
      "learning_rate": 3.02173315169052e-08,
      "loss": 0.5304,
      "step": 63498
    },
    {
      "epoch": 1.9506343501367,
      "grad_norm": 0.4548577666282654,
      "learning_rate": 3.017980169994994e-08,
      "loss": 0.4655,
      "step": 63499
    },
    {
      "epoch": 1.9506650692716492,
      "grad_norm": 0.45683997869491577,
      "learning_rate": 3.0142295168206216e-08,
      "loss": 0.4488,
      "step": 63500
    },
    {
      "epoch": 1.9506957884065985,
      "grad_norm": 0.4212247431278229,
      "learning_rate": 3.0104811921761734e-08,
      "loss": 0.4355,
      "step": 63501
    },
    {
      "epoch": 1.9507265075415476,
      "grad_norm": 0.44482117891311646,
      "learning_rate": 3.00673519607031e-08,
      "loss": 0.4756,
      "step": 63502
    },
    {
      "epoch": 1.9507572266764968,
      "grad_norm": 0.4628055691719055,
      "learning_rate": 3.002991528511911e-08,
      "loss": 0.4623,
      "step": 63503
    },
    {
      "epoch": 1.950787945811446,
      "grad_norm": 0.4859344959259033,
      "learning_rate": 2.999250189509528e-08,
      "loss": 0.5232,
      "step": 63504
    },
    {
      "epoch": 1.9508186649463952,
      "grad_norm": 0.39630821347236633,
      "learning_rate": 2.995511179072153e-08,
      "loss": 0.4613,
      "step": 63505
    },
    {
      "epoch": 1.9508493840813443,
      "grad_norm": 0.4284331798553467,
      "learning_rate": 2.991774497208333e-08,
      "loss": 0.458,
      "step": 63506
    },
    {
      "epoch": 1.9508801032162935,
      "grad_norm": 0.4381902813911438,
      "learning_rate": 2.98804014392684e-08,
      "loss": 0.4315,
      "step": 63507
    },
    {
      "epoch": 1.9509108223512426,
      "grad_norm": 0.4080389738082886,
      "learning_rate": 2.984308119236445e-08,
      "loss": 0.5226,
      "step": 63508
    },
    {
      "epoch": 1.9509415414861917,
      "grad_norm": 0.652295708656311,
      "learning_rate": 2.980578423145919e-08,
      "loss": 0.5082,
      "step": 63509
    },
    {
      "epoch": 1.9509722606211408,
      "grad_norm": 0.4324645698070526,
      "learning_rate": 2.9768510556638097e-08,
      "loss": 0.4489,
      "step": 63510
    },
    {
      "epoch": 1.95100297975609,
      "grad_norm": 0.4117570221424103,
      "learning_rate": 2.9731260167987773e-08,
      "loss": 0.4389,
      "step": 63511
    },
    {
      "epoch": 1.9510336988910393,
      "grad_norm": 0.4526774287223816,
      "learning_rate": 2.969403306559815e-08,
      "loss": 0.5316,
      "step": 63512
    },
    {
      "epoch": 1.9510644180259884,
      "grad_norm": 0.4554060995578766,
      "learning_rate": 2.96568292495536e-08,
      "loss": 0.4109,
      "step": 63513
    },
    {
      "epoch": 1.9510951371609375,
      "grad_norm": 0.4436834156513214,
      "learning_rate": 2.9619648719941828e-08,
      "loss": 0.4973,
      "step": 63514
    },
    {
      "epoch": 1.9511258562958869,
      "grad_norm": 0.4257160425186157,
      "learning_rate": 2.958249147685055e-08,
      "loss": 0.5093,
      "step": 63515
    },
    {
      "epoch": 1.951156575430836,
      "grad_norm": 0.4651317596435547,
      "learning_rate": 2.954535752036414e-08,
      "loss": 0.5315,
      "step": 63516
    },
    {
      "epoch": 1.951187294565785,
      "grad_norm": 0.39602455496788025,
      "learning_rate": 2.950824685057141e-08,
      "loss": 0.4427,
      "step": 63517
    },
    {
      "epoch": 1.9512180137007342,
      "grad_norm": 0.4416348338127136,
      "learning_rate": 2.947115946755896e-08,
      "loss": 0.4341,
      "step": 63518
    },
    {
      "epoch": 1.9512487328356833,
      "grad_norm": 0.4858265817165375,
      "learning_rate": 2.9434095371413397e-08,
      "loss": 0.54,
      "step": 63519
    },
    {
      "epoch": 1.9512794519706325,
      "grad_norm": 0.4519287943840027,
      "learning_rate": 2.9397054562220196e-08,
      "loss": 0.4872,
      "step": 63520
    },
    {
      "epoch": 1.9513101711055816,
      "grad_norm": 0.5399790406227112,
      "learning_rate": 2.9360037040065957e-08,
      "loss": 0.4248,
      "step": 63521
    },
    {
      "epoch": 1.9513408902405307,
      "grad_norm": 0.6120543479919434,
      "learning_rate": 2.9323042805038395e-08,
      "loss": 0.4262,
      "step": 63522
    },
    {
      "epoch": 1.9513716093754798,
      "grad_norm": 0.6063886284828186,
      "learning_rate": 2.9286071857222986e-08,
      "loss": 0.4896,
      "step": 63523
    },
    {
      "epoch": 1.9514023285104292,
      "grad_norm": 0.4444722831249237,
      "learning_rate": 2.9249124196706335e-08,
      "loss": 0.3542,
      "step": 63524
    },
    {
      "epoch": 1.9514330476453783,
      "grad_norm": 0.45003601908683777,
      "learning_rate": 2.921219982357504e-08,
      "loss": 0.4756,
      "step": 63525
    },
    {
      "epoch": 1.9514637667803276,
      "grad_norm": 0.4314001500606537,
      "learning_rate": 2.917529873791458e-08,
      "loss": 0.4655,
      "step": 63526
    },
    {
      "epoch": 1.9514944859152767,
      "grad_norm": 0.42952072620391846,
      "learning_rate": 2.9138420939811564e-08,
      "loss": 0.4964,
      "step": 63527
    },
    {
      "epoch": 1.9515252050502259,
      "grad_norm": 0.4134763479232788,
      "learning_rate": 2.910156642935258e-08,
      "loss": 0.4502,
      "step": 63528
    },
    {
      "epoch": 1.951555924185175,
      "grad_norm": 0.428061306476593,
      "learning_rate": 2.9064735206623117e-08,
      "loss": 0.5065,
      "step": 63529
    },
    {
      "epoch": 1.951586643320124,
      "grad_norm": 0.42283201217651367,
      "learning_rate": 2.9027927271708668e-08,
      "loss": 0.4578,
      "step": 63530
    },
    {
      "epoch": 1.9516173624550732,
      "grad_norm": 0.4808766841888428,
      "learning_rate": 2.8991142624696933e-08,
      "loss": 0.4646,
      "step": 63531
    },
    {
      "epoch": 1.9516480815900223,
      "grad_norm": 0.4821562170982361,
      "learning_rate": 2.8954381265672292e-08,
      "loss": 0.5207,
      "step": 63532
    },
    {
      "epoch": 1.9516788007249715,
      "grad_norm": 0.46446895599365234,
      "learning_rate": 2.8917643194720235e-08,
      "loss": 0.5221,
      "step": 63533
    },
    {
      "epoch": 1.9517095198599206,
      "grad_norm": 0.4594388008117676,
      "learning_rate": 2.8880928411928467e-08,
      "loss": 0.4764,
      "step": 63534
    },
    {
      "epoch": 1.95174023899487,
      "grad_norm": 0.4471374452114105,
      "learning_rate": 2.8844236917381362e-08,
      "loss": 0.4395,
      "step": 63535
    },
    {
      "epoch": 1.951770958129819,
      "grad_norm": 0.4533766508102417,
      "learning_rate": 2.8807568711164412e-08,
      "loss": 0.5212,
      "step": 63536
    },
    {
      "epoch": 1.9518016772647684,
      "grad_norm": 0.41595086455345154,
      "learning_rate": 2.8770923793364214e-08,
      "loss": 0.4528,
      "step": 63537
    },
    {
      "epoch": 1.9518323963997175,
      "grad_norm": 0.4655632972717285,
      "learning_rate": 2.8734302164066253e-08,
      "loss": 0.4489,
      "step": 63538
    },
    {
      "epoch": 1.9518631155346666,
      "grad_norm": 0.5444075465202332,
      "learning_rate": 2.8697703823354907e-08,
      "loss": 0.4847,
      "step": 63539
    },
    {
      "epoch": 1.9518938346696157,
      "grad_norm": 0.5093874931335449,
      "learning_rate": 2.866112877131677e-08,
      "loss": 0.435,
      "step": 63540
    },
    {
      "epoch": 1.9519245538045649,
      "grad_norm": 0.4830593764781952,
      "learning_rate": 2.8624577008037334e-08,
      "loss": 0.4668,
      "step": 63541
    },
    {
      "epoch": 1.951955272939514,
      "grad_norm": 0.42684459686279297,
      "learning_rate": 2.8588048533600975e-08,
      "loss": 0.5119,
      "step": 63542
    },
    {
      "epoch": 1.951985992074463,
      "grad_norm": 0.4130980372428894,
      "learning_rate": 2.855154334809429e-08,
      "loss": 0.454,
      "step": 63543
    },
    {
      "epoch": 1.9520167112094122,
      "grad_norm": 0.4479268491268158,
      "learning_rate": 2.8515061451601655e-08,
      "loss": 0.4306,
      "step": 63544
    },
    {
      "epoch": 1.9520474303443613,
      "grad_norm": 0.43836116790771484,
      "learning_rate": 2.8478602844208558e-08,
      "loss": 0.53,
      "step": 63545
    },
    {
      "epoch": 1.9520781494793107,
      "grad_norm": 0.4564439058303833,
      "learning_rate": 2.8442167526000487e-08,
      "loss": 0.4422,
      "step": 63546
    },
    {
      "epoch": 1.9521088686142598,
      "grad_norm": 0.3945498764514923,
      "learning_rate": 2.8405755497061814e-08,
      "loss": 0.4199,
      "step": 63547
    },
    {
      "epoch": 1.9521395877492091,
      "grad_norm": 0.3946654498577118,
      "learning_rate": 2.8369366757476923e-08,
      "loss": 0.4445,
      "step": 63548
    },
    {
      "epoch": 1.9521703068841583,
      "grad_norm": 0.5263856649398804,
      "learning_rate": 2.833300130733241e-08,
      "loss": 0.4662,
      "step": 63549
    },
    {
      "epoch": 1.9522010260191074,
      "grad_norm": 0.4189631938934326,
      "learning_rate": 2.8296659146712647e-08,
      "loss": 0.5116,
      "step": 63550
    },
    {
      "epoch": 1.9522317451540565,
      "grad_norm": 0.4734937250614166,
      "learning_rate": 2.8260340275703125e-08,
      "loss": 0.4759,
      "step": 63551
    },
    {
      "epoch": 1.9522624642890056,
      "grad_norm": 0.43535086512565613,
      "learning_rate": 2.822404469438711e-08,
      "loss": 0.4488,
      "step": 63552
    },
    {
      "epoch": 1.9522931834239547,
      "grad_norm": 0.43809178471565247,
      "learning_rate": 2.8187772402850088e-08,
      "loss": 0.4777,
      "step": 63553
    },
    {
      "epoch": 1.9523239025589039,
      "grad_norm": 0.44504961371421814,
      "learning_rate": 2.815152340117755e-08,
      "loss": 0.4613,
      "step": 63554
    },
    {
      "epoch": 1.952354621693853,
      "grad_norm": 0.4419506788253784,
      "learning_rate": 2.811529768945387e-08,
      "loss": 0.522,
      "step": 63555
    },
    {
      "epoch": 1.952385340828802,
      "grad_norm": 0.4310295581817627,
      "learning_rate": 2.8079095267763423e-08,
      "loss": 0.4196,
      "step": 63556
    },
    {
      "epoch": 1.9524160599637514,
      "grad_norm": 0.5662258267402649,
      "learning_rate": 2.804291613618948e-08,
      "loss": 0.5085,
      "step": 63557
    },
    {
      "epoch": 1.9524467790987006,
      "grad_norm": 0.47500574588775635,
      "learning_rate": 2.8006760294818635e-08,
      "loss": 0.496,
      "step": 63558
    },
    {
      "epoch": 1.9524774982336497,
      "grad_norm": 0.45055314898490906,
      "learning_rate": 2.797062774373416e-08,
      "loss": 0.4442,
      "step": 63559
    },
    {
      "epoch": 1.952508217368599,
      "grad_norm": 0.46685346961021423,
      "learning_rate": 2.7934518483020423e-08,
      "loss": 0.5195,
      "step": 63560
    },
    {
      "epoch": 1.9525389365035482,
      "grad_norm": 0.4276696741580963,
      "learning_rate": 2.7898432512762917e-08,
      "loss": 0.5443,
      "step": 63561
    },
    {
      "epoch": 1.9525696556384973,
      "grad_norm": 0.4262543320655823,
      "learning_rate": 2.78623698330438e-08,
      "loss": 0.4112,
      "step": 63562
    },
    {
      "epoch": 1.9526003747734464,
      "grad_norm": 0.4103592336177826,
      "learning_rate": 2.7826330443949668e-08,
      "loss": 0.4986,
      "step": 63563
    },
    {
      "epoch": 1.9526310939083955,
      "grad_norm": 0.48594895005226135,
      "learning_rate": 2.7790314345563784e-08,
      "loss": 0.4572,
      "step": 63564
    },
    {
      "epoch": 1.9526618130433446,
      "grad_norm": 0.44729918241500854,
      "learning_rate": 2.775432153796942e-08,
      "loss": 0.446,
      "step": 63565
    },
    {
      "epoch": 1.9526925321782937,
      "grad_norm": 0.40464484691619873,
      "learning_rate": 2.771835202125095e-08,
      "loss": 0.4363,
      "step": 63566
    },
    {
      "epoch": 1.9527232513132429,
      "grad_norm": 0.41445550322532654,
      "learning_rate": 2.768240579549386e-08,
      "loss": 0.5157,
      "step": 63567
    },
    {
      "epoch": 1.9527539704481922,
      "grad_norm": 0.4365074932575226,
      "learning_rate": 2.764648286078031e-08,
      "loss": 0.5127,
      "step": 63568
    },
    {
      "epoch": 1.9527846895831413,
      "grad_norm": 0.4491156041622162,
      "learning_rate": 2.7610583217194674e-08,
      "loss": 0.52,
      "step": 63569
    },
    {
      "epoch": 1.9528154087180905,
      "grad_norm": 0.4800645112991333,
      "learning_rate": 2.7574706864821333e-08,
      "loss": 0.4305,
      "step": 63570
    },
    {
      "epoch": 1.9528461278530398,
      "grad_norm": 0.4184049963951111,
      "learning_rate": 2.7538853803743547e-08,
      "loss": 0.4953,
      "step": 63571
    },
    {
      "epoch": 1.952876846987989,
      "grad_norm": 0.44014978408813477,
      "learning_rate": 2.750302403404459e-08,
      "loss": 0.4233,
      "step": 63572
    },
    {
      "epoch": 1.952907566122938,
      "grad_norm": 0.4929553270339966,
      "learning_rate": 2.7467217555809944e-08,
      "loss": 0.513,
      "step": 63573
    },
    {
      "epoch": 1.9529382852578872,
      "grad_norm": 0.40874239802360535,
      "learning_rate": 2.7431434369121767e-08,
      "loss": 0.4625,
      "step": 63574
    },
    {
      "epoch": 1.9529690043928363,
      "grad_norm": 0.399232417345047,
      "learning_rate": 2.7395674474063328e-08,
      "loss": 0.4591,
      "step": 63575
    },
    {
      "epoch": 1.9529997235277854,
      "grad_norm": 0.44297850131988525,
      "learning_rate": 2.7359937870719e-08,
      "loss": 0.4136,
      "step": 63576
    },
    {
      "epoch": 1.9530304426627345,
      "grad_norm": 0.42185065150260925,
      "learning_rate": 2.732422455917205e-08,
      "loss": 0.3595,
      "step": 63577
    },
    {
      "epoch": 1.9530611617976836,
      "grad_norm": 0.43287503719329834,
      "learning_rate": 2.728853453950686e-08,
      "loss": 0.3808,
      "step": 63578
    },
    {
      "epoch": 1.953091880932633,
      "grad_norm": 0.4899957776069641,
      "learning_rate": 2.7252867811804473e-08,
      "loss": 0.47,
      "step": 63579
    },
    {
      "epoch": 1.953122600067582,
      "grad_norm": 0.4476138949394226,
      "learning_rate": 2.7217224376150375e-08,
      "loss": 0.488,
      "step": 63580
    },
    {
      "epoch": 1.9531533192025312,
      "grad_norm": 0.48548993468284607,
      "learning_rate": 2.7181604232626724e-08,
      "loss": 0.5573,
      "step": 63581
    },
    {
      "epoch": 1.9531840383374806,
      "grad_norm": 0.4099261164665222,
      "learning_rate": 2.7146007381315677e-08,
      "loss": 0.446,
      "step": 63582
    },
    {
      "epoch": 1.9532147574724297,
      "grad_norm": 0.42392396926879883,
      "learning_rate": 2.711043382230383e-08,
      "loss": 0.3926,
      "step": 63583
    },
    {
      "epoch": 1.9532454766073788,
      "grad_norm": 0.46410560607910156,
      "learning_rate": 2.7074883555670006e-08,
      "loss": 0.444,
      "step": 63584
    },
    {
      "epoch": 1.953276195742328,
      "grad_norm": 0.437262624502182,
      "learning_rate": 2.703935658150081e-08,
      "loss": 0.4946,
      "step": 63585
    },
    {
      "epoch": 1.953306914877277,
      "grad_norm": 0.4501202404499054,
      "learning_rate": 2.7003852899877282e-08,
      "loss": 0.4499,
      "step": 63586
    },
    {
      "epoch": 1.9533376340122262,
      "grad_norm": 0.39820578694343567,
      "learning_rate": 2.696837251088269e-08,
      "loss": 0.5317,
      "step": 63587
    },
    {
      "epoch": 1.9533683531471753,
      "grad_norm": 0.4547789692878723,
      "learning_rate": 2.6932915414599192e-08,
      "loss": 0.4534,
      "step": 63588
    },
    {
      "epoch": 1.9533990722821244,
      "grad_norm": 0.6088272929191589,
      "learning_rate": 2.6897481611111164e-08,
      "loss": 0.5205,
      "step": 63589
    },
    {
      "epoch": 1.9534297914170737,
      "grad_norm": 0.48157447576522827,
      "learning_rate": 2.6862071100500762e-08,
      "loss": 0.4607,
      "step": 63590
    },
    {
      "epoch": 1.9534605105520229,
      "grad_norm": 0.45605844259262085,
      "learning_rate": 2.6826683882850147e-08,
      "loss": 0.5357,
      "step": 63591
    },
    {
      "epoch": 1.953491229686972,
      "grad_norm": 0.4203982949256897,
      "learning_rate": 2.679131995824258e-08,
      "loss": 0.4249,
      "step": 63592
    },
    {
      "epoch": 1.9535219488219213,
      "grad_norm": 0.4795244634151459,
      "learning_rate": 2.675597932676022e-08,
      "loss": 0.4952,
      "step": 63593
    },
    {
      "epoch": 1.9535526679568704,
      "grad_norm": 0.4370450973510742,
      "learning_rate": 2.672066198848522e-08,
      "loss": 0.4565,
      "step": 63594
    },
    {
      "epoch": 1.9535833870918196,
      "grad_norm": 0.45019906759262085,
      "learning_rate": 2.668536794350196e-08,
      "loss": 0.4533,
      "step": 63595
    },
    {
      "epoch": 1.9536141062267687,
      "grad_norm": 0.4193381667137146,
      "learning_rate": 2.665009719189038e-08,
      "loss": 0.4639,
      "step": 63596
    },
    {
      "epoch": 1.9536448253617178,
      "grad_norm": 0.40648895502090454,
      "learning_rate": 2.6614849733734848e-08,
      "loss": 0.4563,
      "step": 63597
    },
    {
      "epoch": 1.953675544496667,
      "grad_norm": 0.4004753530025482,
      "learning_rate": 2.6579625569116418e-08,
      "loss": 0.4914,
      "step": 63598
    },
    {
      "epoch": 1.953706263631616,
      "grad_norm": 0.41736873984336853,
      "learning_rate": 2.6544424698117245e-08,
      "loss": 0.4463,
      "step": 63599
    },
    {
      "epoch": 1.9537369827665652,
      "grad_norm": 0.4480396509170532,
      "learning_rate": 2.65092471208217e-08,
      "loss": 0.506,
      "step": 63600
    },
    {
      "epoch": 1.9537677019015145,
      "grad_norm": 0.4186127483844757,
      "learning_rate": 2.6474092837308618e-08,
      "loss": 0.5364,
      "step": 63601
    },
    {
      "epoch": 1.9537984210364636,
      "grad_norm": 0.4306131899356842,
      "learning_rate": 2.643896184766348e-08,
      "loss": 0.4751,
      "step": 63602
    },
    {
      "epoch": 1.9538291401714127,
      "grad_norm": 0.48695969581604004,
      "learning_rate": 2.6403854151965115e-08,
      "loss": 0.4235,
      "step": 63603
    },
    {
      "epoch": 1.953859859306362,
      "grad_norm": 0.43317797780036926,
      "learning_rate": 2.6368769750297895e-08,
      "loss": 0.4356,
      "step": 63604
    },
    {
      "epoch": 1.9538905784413112,
      "grad_norm": 0.41418394446372986,
      "learning_rate": 2.6333708642742873e-08,
      "loss": 0.4547,
      "step": 63605
    },
    {
      "epoch": 1.9539212975762603,
      "grad_norm": 0.4615724980831146,
      "learning_rate": 2.62986708293822e-08,
      "loss": 0.5266,
      "step": 63606
    },
    {
      "epoch": 1.9539520167112094,
      "grad_norm": 0.42482882738113403,
      "learning_rate": 2.6263656310296927e-08,
      "loss": 0.4745,
      "step": 63607
    },
    {
      "epoch": 1.9539827358461586,
      "grad_norm": 0.4448515474796295,
      "learning_rate": 2.6228665085570314e-08,
      "loss": 0.4392,
      "step": 63608
    },
    {
      "epoch": 1.9540134549811077,
      "grad_norm": 0.43730705976486206,
      "learning_rate": 2.6193697155282304e-08,
      "loss": 0.4992,
      "step": 63609
    },
    {
      "epoch": 1.9540441741160568,
      "grad_norm": 0.41107726097106934,
      "learning_rate": 2.6158752519517272e-08,
      "loss": 0.4723,
      "step": 63610
    },
    {
      "epoch": 1.954074893251006,
      "grad_norm": 0.42701974511146545,
      "learning_rate": 2.6123831178352934e-08,
      "loss": 0.4388,
      "step": 63611
    },
    {
      "epoch": 1.9541056123859553,
      "grad_norm": 0.42337319254875183,
      "learning_rate": 2.608893313187366e-08,
      "loss": 0.4695,
      "step": 63612
    },
    {
      "epoch": 1.9541363315209044,
      "grad_norm": 0.47767746448516846,
      "learning_rate": 2.6054058380160508e-08,
      "loss": 0.4954,
      "step": 63613
    },
    {
      "epoch": 1.9541670506558535,
      "grad_norm": 0.43395984172821045,
      "learning_rate": 2.6019206923294515e-08,
      "loss": 0.4755,
      "step": 63614
    },
    {
      "epoch": 1.9541977697908028,
      "grad_norm": 0.45602521300315857,
      "learning_rate": 2.5984378761356734e-08,
      "loss": 0.5394,
      "step": 63615
    },
    {
      "epoch": 1.954228488925752,
      "grad_norm": 0.4446881413459778,
      "learning_rate": 2.5949573894429315e-08,
      "loss": 0.4854,
      "step": 63616
    },
    {
      "epoch": 1.954259208060701,
      "grad_norm": 0.4687172472476959,
      "learning_rate": 2.5914792322594418e-08,
      "loss": 0.4296,
      "step": 63617
    },
    {
      "epoch": 1.9542899271956502,
      "grad_norm": 0.41816943883895874,
      "learning_rate": 2.588003404593087e-08,
      "loss": 0.4649,
      "step": 63618
    },
    {
      "epoch": 1.9543206463305993,
      "grad_norm": 0.44639214873313904,
      "learning_rate": 2.5845299064521934e-08,
      "loss": 0.5444,
      "step": 63619
    },
    {
      "epoch": 1.9543513654655484,
      "grad_norm": 0.4420199990272522,
      "learning_rate": 2.581058737844644e-08,
      "loss": 0.5063,
      "step": 63620
    },
    {
      "epoch": 1.9543820846004976,
      "grad_norm": 0.474283367395401,
      "learning_rate": 2.577589898778765e-08,
      "loss": 0.4477,
      "step": 63621
    },
    {
      "epoch": 1.9544128037354467,
      "grad_norm": 0.4202519357204437,
      "learning_rate": 2.5741233892626617e-08,
      "loss": 0.4474,
      "step": 63622
    },
    {
      "epoch": 1.954443522870396,
      "grad_norm": 0.44314703345298767,
      "learning_rate": 2.570659209304216e-08,
      "loss": 0.4905,
      "step": 63623
    },
    {
      "epoch": 1.9544742420053451,
      "grad_norm": 0.47053080797195435,
      "learning_rate": 2.567197358911755e-08,
      "loss": 0.5448,
      "step": 63624
    },
    {
      "epoch": 1.9545049611402943,
      "grad_norm": 0.44831743836402893,
      "learning_rate": 2.563737838093272e-08,
      "loss": 0.4672,
      "step": 63625
    },
    {
      "epoch": 1.9545356802752436,
      "grad_norm": 0.4319986402988434,
      "learning_rate": 2.560280646856761e-08,
      "loss": 0.4155,
      "step": 63626
    },
    {
      "epoch": 1.9545663994101927,
      "grad_norm": 0.4347783625125885,
      "learning_rate": 2.5568257852104372e-08,
      "loss": 0.43,
      "step": 63627
    },
    {
      "epoch": 1.9545971185451418,
      "grad_norm": 0.44508838653564453,
      "learning_rate": 2.5533732531622944e-08,
      "loss": 0.5188,
      "step": 63628
    },
    {
      "epoch": 1.954627837680091,
      "grad_norm": 0.47531789541244507,
      "learning_rate": 2.5499230507204377e-08,
      "loss": 0.5011,
      "step": 63629
    },
    {
      "epoch": 1.95465855681504,
      "grad_norm": 0.44543445110321045,
      "learning_rate": 2.5464751778927488e-08,
      "loss": 0.4326,
      "step": 63630
    },
    {
      "epoch": 1.9546892759499892,
      "grad_norm": 0.441437691450119,
      "learning_rate": 2.5430296346875548e-08,
      "loss": 0.5122,
      "step": 63631
    },
    {
      "epoch": 1.9547199950849383,
      "grad_norm": 0.39786297082901,
      "learning_rate": 2.5395864211128495e-08,
      "loss": 0.4756,
      "step": 63632
    },
    {
      "epoch": 1.9547507142198874,
      "grad_norm": 0.45970669388771057,
      "learning_rate": 2.5361455371765153e-08,
      "loss": 0.4783,
      "step": 63633
    },
    {
      "epoch": 1.9547814333548366,
      "grad_norm": 0.4439838230609894,
      "learning_rate": 2.532706982886657e-08,
      "loss": 0.4718,
      "step": 63634
    },
    {
      "epoch": 1.954812152489786,
      "grad_norm": 0.45902591943740845,
      "learning_rate": 2.5292707582512677e-08,
      "loss": 0.5005,
      "step": 63635
    },
    {
      "epoch": 1.954842871624735,
      "grad_norm": 0.471753865480423,
      "learning_rate": 2.5258368632785636e-08,
      "loss": 0.4605,
      "step": 63636
    },
    {
      "epoch": 1.9548735907596844,
      "grad_norm": 0.6094290018081665,
      "learning_rate": 2.5224052979763157e-08,
      "loss": 0.4835,
      "step": 63637
    },
    {
      "epoch": 1.9549043098946335,
      "grad_norm": 0.43566131591796875,
      "learning_rate": 2.5189760623527405e-08,
      "loss": 0.4719,
      "step": 63638
    },
    {
      "epoch": 1.9549350290295826,
      "grad_norm": 0.43868035078048706,
      "learning_rate": 2.5155491564157196e-08,
      "loss": 0.4616,
      "step": 63639
    },
    {
      "epoch": 1.9549657481645317,
      "grad_norm": 0.48638397455215454,
      "learning_rate": 2.5121245801733585e-08,
      "loss": 0.4822,
      "step": 63640
    },
    {
      "epoch": 1.9549964672994808,
      "grad_norm": 0.4794236123561859,
      "learning_rate": 2.508702333633539e-08,
      "loss": 0.4433,
      "step": 63641
    },
    {
      "epoch": 1.95502718643443,
      "grad_norm": 0.44308948516845703,
      "learning_rate": 2.5052824168042555e-08,
      "loss": 0.564,
      "step": 63642
    },
    {
      "epoch": 1.955057905569379,
      "grad_norm": 0.48606225848197937,
      "learning_rate": 2.5018648296936122e-08,
      "loss": 0.4859,
      "step": 63643
    },
    {
      "epoch": 1.9550886247043282,
      "grad_norm": 0.4139421582221985,
      "learning_rate": 2.4984495723094914e-08,
      "loss": 0.4176,
      "step": 63644
    },
    {
      "epoch": 1.9551193438392773,
      "grad_norm": 0.4527392089366913,
      "learning_rate": 2.4950366446599984e-08,
      "loss": 0.4865,
      "step": 63645
    },
    {
      "epoch": 1.9551500629742267,
      "grad_norm": 0.4688144028186798,
      "learning_rate": 2.491626046752904e-08,
      "loss": 0.4336,
      "step": 63646
    },
    {
      "epoch": 1.9551807821091758,
      "grad_norm": 0.4119555354118347,
      "learning_rate": 2.4882177785963137e-08,
      "loss": 0.4842,
      "step": 63647
    },
    {
      "epoch": 1.9552115012441251,
      "grad_norm": 0.456692099571228,
      "learning_rate": 2.4848118401982203e-08,
      "loss": 0.4008,
      "step": 63648
    },
    {
      "epoch": 1.9552422203790742,
      "grad_norm": 0.3930264413356781,
      "learning_rate": 2.4814082315665068e-08,
      "loss": 0.4378,
      "step": 63649
    },
    {
      "epoch": 1.9552729395140234,
      "grad_norm": 0.44434288144111633,
      "learning_rate": 2.4780069527090557e-08,
      "loss": 0.5032,
      "step": 63650
    },
    {
      "epoch": 1.9553036586489725,
      "grad_norm": 0.4441779553890228,
      "learning_rate": 2.4746080036338605e-08,
      "loss": 0.4498,
      "step": 63651
    },
    {
      "epoch": 1.9553343777839216,
      "grad_norm": 0.4372154176235199,
      "learning_rate": 2.471211384348915e-08,
      "loss": 0.4885,
      "step": 63652
    },
    {
      "epoch": 1.9553650969188707,
      "grad_norm": 0.44871222972869873,
      "learning_rate": 2.4678170948622127e-08,
      "loss": 0.476,
      "step": 63653
    },
    {
      "epoch": 1.9553958160538198,
      "grad_norm": 0.40958887338638306,
      "learning_rate": 2.464425135181525e-08,
      "loss": 0.4655,
      "step": 63654
    },
    {
      "epoch": 1.955426535188769,
      "grad_norm": 0.4428063631057739,
      "learning_rate": 2.461035505314846e-08,
      "loss": 0.462,
      "step": 63655
    },
    {
      "epoch": 1.955457254323718,
      "grad_norm": 0.45578086376190186,
      "learning_rate": 2.457648205270058e-08,
      "loss": 0.3921,
      "step": 63656
    },
    {
      "epoch": 1.9554879734586674,
      "grad_norm": 0.43933993577957153,
      "learning_rate": 2.4542632350551542e-08,
      "loss": 0.4746,
      "step": 63657
    },
    {
      "epoch": 1.9555186925936165,
      "grad_norm": 0.45629382133483887,
      "learning_rate": 2.450880594677907e-08,
      "loss": 0.4698,
      "step": 63658
    },
    {
      "epoch": 1.955549411728566,
      "grad_norm": 0.42966827750205994,
      "learning_rate": 2.4475002841464202e-08,
      "loss": 0.4043,
      "step": 63659
    },
    {
      "epoch": 1.955580130863515,
      "grad_norm": 0.47181543707847595,
      "learning_rate": 2.444122303468355e-08,
      "loss": 0.5052,
      "step": 63660
    },
    {
      "epoch": 1.9556108499984641,
      "grad_norm": 0.42074868083000183,
      "learning_rate": 2.4407466526517044e-08,
      "loss": 0.474,
      "step": 63661
    },
    {
      "epoch": 1.9556415691334132,
      "grad_norm": 0.4227861762046814,
      "learning_rate": 2.4373733317044622e-08,
      "loss": 0.4457,
      "step": 63662
    },
    {
      "epoch": 1.9556722882683624,
      "grad_norm": 0.40408381819725037,
      "learning_rate": 2.4340023406342893e-08,
      "loss": 0.3359,
      "step": 63663
    },
    {
      "epoch": 1.9557030074033115,
      "grad_norm": 0.5048640966415405,
      "learning_rate": 2.43063367944929e-08,
      "loss": 0.4607,
      "step": 63664
    },
    {
      "epoch": 1.9557337265382606,
      "grad_norm": 0.44105425477027893,
      "learning_rate": 2.427267348157125e-08,
      "loss": 0.4489,
      "step": 63665
    },
    {
      "epoch": 1.9557644456732097,
      "grad_norm": 0.460717111825943,
      "learning_rate": 2.423903346765788e-08,
      "loss": 0.4949,
      "step": 63666
    },
    {
      "epoch": 1.9557951648081588,
      "grad_norm": 0.3978783190250397,
      "learning_rate": 2.4205416752830503e-08,
      "loss": 0.5549,
      "step": 63667
    },
    {
      "epoch": 1.9558258839431082,
      "grad_norm": 1.5796645879745483,
      "learning_rate": 2.4171823337167943e-08,
      "loss": 0.5705,
      "step": 63668
    },
    {
      "epoch": 1.9558566030780573,
      "grad_norm": 0.563663125038147,
      "learning_rate": 2.413825322074903e-08,
      "loss": 0.4529,
      "step": 63669
    },
    {
      "epoch": 1.9558873222130064,
      "grad_norm": 0.4622690975666046,
      "learning_rate": 2.410470640365259e-08,
      "loss": 0.4699,
      "step": 63670
    },
    {
      "epoch": 1.9559180413479558,
      "grad_norm": 0.564270555973053,
      "learning_rate": 2.4071182885955226e-08,
      "loss": 0.4702,
      "step": 63671
    },
    {
      "epoch": 1.955948760482905,
      "grad_norm": 0.4535374045372009,
      "learning_rate": 2.4037682667737984e-08,
      "loss": 0.4347,
      "step": 63672
    },
    {
      "epoch": 1.955979479617854,
      "grad_norm": 0.5012762546539307,
      "learning_rate": 2.400420574907636e-08,
      "loss": 0.4267,
      "step": 63673
    },
    {
      "epoch": 1.9560101987528031,
      "grad_norm": 0.41295406222343445,
      "learning_rate": 2.397075213004918e-08,
      "loss": 0.4871,
      "step": 63674
    },
    {
      "epoch": 1.9560409178877523,
      "grad_norm": 0.4593413472175598,
      "learning_rate": 2.393732181073527e-08,
      "loss": 0.441,
      "step": 63675
    },
    {
      "epoch": 1.9560716370227014,
      "grad_norm": 0.4934047758579254,
      "learning_rate": 2.3903914791213455e-08,
      "loss": 0.4256,
      "step": 63676
    },
    {
      "epoch": 1.9561023561576505,
      "grad_norm": 0.4051501452922821,
      "learning_rate": 2.3870531071559235e-08,
      "loss": 0.4429,
      "step": 63677
    },
    {
      "epoch": 1.9561330752925996,
      "grad_norm": 0.4294946789741516,
      "learning_rate": 2.3837170651852536e-08,
      "loss": 0.4503,
      "step": 63678
    },
    {
      "epoch": 1.956163794427549,
      "grad_norm": 0.4351401627063751,
      "learning_rate": 2.3803833532171083e-08,
      "loss": 0.4713,
      "step": 63679
    },
    {
      "epoch": 1.956194513562498,
      "grad_norm": 0.4583880603313446,
      "learning_rate": 2.3770519712593698e-08,
      "loss": 0.4821,
      "step": 63680
    },
    {
      "epoch": 1.9562252326974472,
      "grad_norm": 0.44226333498954773,
      "learning_rate": 2.3737229193195877e-08,
      "loss": 0.4554,
      "step": 63681
    },
    {
      "epoch": 1.9562559518323965,
      "grad_norm": 0.4439847767353058,
      "learning_rate": 2.3703961974056446e-08,
      "loss": 0.4228,
      "step": 63682
    },
    {
      "epoch": 1.9562866709673457,
      "grad_norm": 0.4468301832675934,
      "learning_rate": 2.3670718055253117e-08,
      "loss": 0.4757,
      "step": 63683
    },
    {
      "epoch": 1.9563173901022948,
      "grad_norm": 0.4793872833251953,
      "learning_rate": 2.363749743686361e-08,
      "loss": 0.4604,
      "step": 63684
    },
    {
      "epoch": 1.956348109237244,
      "grad_norm": 0.425877183675766,
      "learning_rate": 2.360430011896564e-08,
      "loss": 0.5794,
      "step": 63685
    },
    {
      "epoch": 1.956378828372193,
      "grad_norm": 0.46343404054641724,
      "learning_rate": 2.357112610163581e-08,
      "loss": 0.5149,
      "step": 63686
    },
    {
      "epoch": 1.9564095475071421,
      "grad_norm": 0.4419790208339691,
      "learning_rate": 2.353797538495406e-08,
      "loss": 0.4675,
      "step": 63687
    },
    {
      "epoch": 1.9564402666420913,
      "grad_norm": 0.44065314531326294,
      "learning_rate": 2.350484796899477e-08,
      "loss": 0.4285,
      "step": 63688
    },
    {
      "epoch": 1.9564709857770404,
      "grad_norm": 0.42628392577171326,
      "learning_rate": 2.347174385383677e-08,
      "loss": 0.4976,
      "step": 63689
    },
    {
      "epoch": 1.9565017049119897,
      "grad_norm": 0.43026426434516907,
      "learning_rate": 2.3438663039557773e-08,
      "loss": 0.4408,
      "step": 63690
    },
    {
      "epoch": 1.9565324240469388,
      "grad_norm": 0.42846351861953735,
      "learning_rate": 2.3405605526234387e-08,
      "loss": 0.4698,
      "step": 63691
    },
    {
      "epoch": 1.956563143181888,
      "grad_norm": 0.43287500739097595,
      "learning_rate": 2.3372571313943215e-08,
      "loss": 0.4617,
      "step": 63692
    },
    {
      "epoch": 1.9565938623168373,
      "grad_norm": 0.41859376430511475,
      "learning_rate": 2.3339560402763082e-08,
      "loss": 0.3732,
      "step": 63693
    },
    {
      "epoch": 1.9566245814517864,
      "grad_norm": 0.4334274232387543,
      "learning_rate": 2.330657279276949e-08,
      "loss": 0.4108,
      "step": 63694
    },
    {
      "epoch": 1.9566553005867355,
      "grad_norm": 0.42012032866477966,
      "learning_rate": 2.3273608484041254e-08,
      "loss": 0.4727,
      "step": 63695
    },
    {
      "epoch": 1.9566860197216847,
      "grad_norm": 0.4475705325603485,
      "learning_rate": 2.324066747665277e-08,
      "loss": 0.5544,
      "step": 63696
    },
    {
      "epoch": 1.9567167388566338,
      "grad_norm": 0.419900119304657,
      "learning_rate": 2.3207749770683963e-08,
      "loss": 0.4513,
      "step": 63697
    },
    {
      "epoch": 1.956747457991583,
      "grad_norm": 0.47083336114883423,
      "learning_rate": 2.3174855366209226e-08,
      "loss": 0.4907,
      "step": 63698
    },
    {
      "epoch": 1.956778177126532,
      "grad_norm": 0.435929536819458,
      "learning_rate": 2.314198426330627e-08,
      "loss": 0.5159,
      "step": 63699
    },
    {
      "epoch": 1.9568088962614811,
      "grad_norm": 0.4532899856567383,
      "learning_rate": 2.3109136462052816e-08,
      "loss": 0.5348,
      "step": 63700
    },
    {
      "epoch": 1.9568396153964305,
      "grad_norm": 0.4858793318271637,
      "learning_rate": 2.3076311962524355e-08,
      "loss": 0.519,
      "step": 63701
    },
    {
      "epoch": 1.9568703345313796,
      "grad_norm": 0.4745303690433502,
      "learning_rate": 2.3043510764797493e-08,
      "loss": 0.4798,
      "step": 63702
    },
    {
      "epoch": 1.9569010536663287,
      "grad_norm": 0.46206042170524597,
      "learning_rate": 2.301073286894995e-08,
      "loss": 0.5372,
      "step": 63703
    },
    {
      "epoch": 1.956931772801278,
      "grad_norm": 0.4441150724887848,
      "learning_rate": 2.2977978275057213e-08,
      "loss": 0.4173,
      "step": 63704
    },
    {
      "epoch": 1.9569624919362272,
      "grad_norm": 0.47388216853141785,
      "learning_rate": 2.2945246983197e-08,
      "loss": 0.4675,
      "step": 63705
    },
    {
      "epoch": 1.9569932110711763,
      "grad_norm": 0.41262081265449524,
      "learning_rate": 2.29125389934437e-08,
      "loss": 0.4966,
      "step": 63706
    },
    {
      "epoch": 1.9570239302061254,
      "grad_norm": 0.43332815170288086,
      "learning_rate": 2.2879854305876137e-08,
      "loss": 0.5052,
      "step": 63707
    },
    {
      "epoch": 1.9570546493410745,
      "grad_norm": 0.44074663519859314,
      "learning_rate": 2.2847192920568696e-08,
      "loss": 0.446,
      "step": 63708
    },
    {
      "epoch": 1.9570853684760237,
      "grad_norm": 0.4195118844509125,
      "learning_rate": 2.281455483759798e-08,
      "loss": 0.4564,
      "step": 63709
    },
    {
      "epoch": 1.9571160876109728,
      "grad_norm": 0.42949092388153076,
      "learning_rate": 2.2781940057041706e-08,
      "loss": 0.5068,
      "step": 63710
    },
    {
      "epoch": 1.957146806745922,
      "grad_norm": 0.40758976340293884,
      "learning_rate": 2.2749348578974263e-08,
      "loss": 0.5057,
      "step": 63711
    },
    {
      "epoch": 1.9571775258808712,
      "grad_norm": 0.4087877869606018,
      "learning_rate": 2.2716780403473358e-08,
      "loss": 0.3887,
      "step": 63712
    },
    {
      "epoch": 1.9572082450158204,
      "grad_norm": 0.5112171769142151,
      "learning_rate": 2.2684235530613386e-08,
      "loss": 0.5356,
      "step": 63713
    },
    {
      "epoch": 1.9572389641507695,
      "grad_norm": 0.42420899868011475,
      "learning_rate": 2.2651713960472054e-08,
      "loss": 0.4937,
      "step": 63714
    },
    {
      "epoch": 1.9572696832857188,
      "grad_norm": 0.4156493544578552,
      "learning_rate": 2.2619215693123753e-08,
      "loss": 0.4898,
      "step": 63715
    },
    {
      "epoch": 1.957300402420668,
      "grad_norm": 0.4180476665496826,
      "learning_rate": 2.2586740728645083e-08,
      "loss": 0.4358,
      "step": 63716
    },
    {
      "epoch": 1.957331121555617,
      "grad_norm": 0.429251104593277,
      "learning_rate": 2.2554289067112655e-08,
      "loss": 0.4464,
      "step": 63717
    },
    {
      "epoch": 1.9573618406905662,
      "grad_norm": 0.3797261416912079,
      "learning_rate": 2.252186070860085e-08,
      "loss": 0.4301,
      "step": 63718
    },
    {
      "epoch": 1.9573925598255153,
      "grad_norm": 0.425422340631485,
      "learning_rate": 2.2489455653186277e-08,
      "loss": 0.4771,
      "step": 63719
    },
    {
      "epoch": 1.9574232789604644,
      "grad_norm": 0.4601094424724579,
      "learning_rate": 2.2457073900944424e-08,
      "loss": 0.4385,
      "step": 63720
    },
    {
      "epoch": 1.9574539980954135,
      "grad_norm": 0.4591931700706482,
      "learning_rate": 2.2424715451950796e-08,
      "loss": 0.5225,
      "step": 63721
    },
    {
      "epoch": 1.9574847172303627,
      "grad_norm": 0.40565523505210876,
      "learning_rate": 2.2392380306280882e-08,
      "loss": 0.4149,
      "step": 63722
    },
    {
      "epoch": 1.957515436365312,
      "grad_norm": 0.46525028347969055,
      "learning_rate": 2.2360068464010176e-08,
      "loss": 0.5582,
      "step": 63723
    },
    {
      "epoch": 1.9575461555002611,
      "grad_norm": 0.5105105042457581,
      "learning_rate": 2.2327779925214176e-08,
      "loss": 0.4498,
      "step": 63724
    },
    {
      "epoch": 1.9575768746352102,
      "grad_norm": 0.40336328744888306,
      "learning_rate": 2.2295514689969488e-08,
      "loss": 0.4152,
      "step": 63725
    },
    {
      "epoch": 1.9576075937701596,
      "grad_norm": 0.45520880818367004,
      "learning_rate": 2.2263272758350496e-08,
      "loss": 0.4959,
      "step": 63726
    },
    {
      "epoch": 1.9576383129051087,
      "grad_norm": 0.40463897585868835,
      "learning_rate": 2.2231054130431586e-08,
      "loss": 0.3991,
      "step": 63727
    },
    {
      "epoch": 1.9576690320400578,
      "grad_norm": 0.5159019827842712,
      "learning_rate": 2.219885880628936e-08,
      "loss": 0.479,
      "step": 63728
    },
    {
      "epoch": 1.957699751175007,
      "grad_norm": 0.4303438365459442,
      "learning_rate": 2.2166686785998203e-08,
      "loss": 0.4476,
      "step": 63729
    },
    {
      "epoch": 1.957730470309956,
      "grad_norm": 0.4588862359523773,
      "learning_rate": 2.2134538069634725e-08,
      "loss": 0.4147,
      "step": 63730
    },
    {
      "epoch": 1.9577611894449052,
      "grad_norm": 0.4724515676498413,
      "learning_rate": 2.21024126572722e-08,
      "loss": 0.3973,
      "step": 63731
    },
    {
      "epoch": 1.9577919085798543,
      "grad_norm": 0.44224366545677185,
      "learning_rate": 2.207031054898612e-08,
      "loss": 0.4632,
      "step": 63732
    },
    {
      "epoch": 1.9578226277148034,
      "grad_norm": 0.4167572557926178,
      "learning_rate": 2.203823174485087e-08,
      "loss": 0.4761,
      "step": 63733
    },
    {
      "epoch": 1.9578533468497528,
      "grad_norm": 0.4461144506931305,
      "learning_rate": 2.2006176244943057e-08,
      "loss": 0.4641,
      "step": 63734
    },
    {
      "epoch": 1.9578840659847019,
      "grad_norm": 0.48021185398101807,
      "learning_rate": 2.1974144049337064e-08,
      "loss": 0.3859,
      "step": 63735
    },
    {
      "epoch": 1.957914785119651,
      "grad_norm": 0.46486207842826843,
      "learning_rate": 2.194213515810617e-08,
      "loss": 0.4567,
      "step": 63736
    },
    {
      "epoch": 1.9579455042546003,
      "grad_norm": 0.5617277026176453,
      "learning_rate": 2.191014957132698e-08,
      "loss": 0.4795,
      "step": 63737
    },
    {
      "epoch": 1.9579762233895495,
      "grad_norm": 0.620119035243988,
      "learning_rate": 2.187818728907387e-08,
      "loss": 0.4581,
      "step": 63738
    },
    {
      "epoch": 1.9580069425244986,
      "grad_norm": 0.5043796896934509,
      "learning_rate": 2.1846248311421237e-08,
      "loss": 0.5256,
      "step": 63739
    },
    {
      "epoch": 1.9580376616594477,
      "grad_norm": 0.3984644114971161,
      "learning_rate": 2.1814332638442348e-08,
      "loss": 0.5037,
      "step": 63740
    },
    {
      "epoch": 1.9580683807943968,
      "grad_norm": 0.43620559573173523,
      "learning_rate": 2.178244027021381e-08,
      "loss": 0.4492,
      "step": 63741
    },
    {
      "epoch": 1.958099099929346,
      "grad_norm": 0.4942912459373474,
      "learning_rate": 2.17505712068089e-08,
      "loss": 0.4997,
      "step": 63742
    },
    {
      "epoch": 1.958129819064295,
      "grad_norm": 0.4120236337184906,
      "learning_rate": 2.1718725448303112e-08,
      "loss": 0.5505,
      "step": 63743
    },
    {
      "epoch": 1.9581605381992442,
      "grad_norm": 0.48898279666900635,
      "learning_rate": 2.168690299476972e-08,
      "loss": 0.4141,
      "step": 63744
    },
    {
      "epoch": 1.9581912573341933,
      "grad_norm": 0.43552809953689575,
      "learning_rate": 2.165510384628311e-08,
      "loss": 0.4962,
      "step": 63745
    },
    {
      "epoch": 1.9582219764691426,
      "grad_norm": 0.4484631419181824,
      "learning_rate": 2.1623328002918776e-08,
      "loss": 0.4578,
      "step": 63746
    },
    {
      "epoch": 1.9582526956040918,
      "grad_norm": 0.4624788165092468,
      "learning_rate": 2.1591575464748882e-08,
      "loss": 0.4763,
      "step": 63747
    },
    {
      "epoch": 1.958283414739041,
      "grad_norm": 0.4269498288631439,
      "learning_rate": 2.1559846231848925e-08,
      "loss": 0.4628,
      "step": 63748
    },
    {
      "epoch": 1.9583141338739902,
      "grad_norm": 0.3934139907360077,
      "learning_rate": 2.152814030429329e-08,
      "loss": 0.5279,
      "step": 63749
    },
    {
      "epoch": 1.9583448530089393,
      "grad_norm": 0.4923965632915497,
      "learning_rate": 2.149645768215636e-08,
      "loss": 0.4712,
      "step": 63750
    },
    {
      "epoch": 1.9583755721438885,
      "grad_norm": 0.4787518382072449,
      "learning_rate": 2.1464798365509188e-08,
      "loss": 0.508,
      "step": 63751
    },
    {
      "epoch": 1.9584062912788376,
      "grad_norm": 0.4669342637062073,
      "learning_rate": 2.1433162354429495e-08,
      "loss": 0.4474,
      "step": 63752
    },
    {
      "epoch": 1.9584370104137867,
      "grad_norm": 0.4428445100784302,
      "learning_rate": 2.1401549648989438e-08,
      "loss": 0.4719,
      "step": 63753
    },
    {
      "epoch": 1.9584677295487358,
      "grad_norm": 0.48963749408721924,
      "learning_rate": 2.136996024926341e-08,
      "loss": 0.4645,
      "step": 63754
    },
    {
      "epoch": 1.958498448683685,
      "grad_norm": 0.4570549726486206,
      "learning_rate": 2.133839415532357e-08,
      "loss": 0.4505,
      "step": 63755
    },
    {
      "epoch": 1.958529167818634,
      "grad_norm": 0.4713098704814911,
      "learning_rate": 2.1306851367245417e-08,
      "loss": 0.4523,
      "step": 63756
    },
    {
      "epoch": 1.9585598869535834,
      "grad_norm": 0.4006119668483734,
      "learning_rate": 2.1275331885101112e-08,
      "loss": 0.5132,
      "step": 63757
    },
    {
      "epoch": 1.9585906060885325,
      "grad_norm": 0.3997345268726349,
      "learning_rate": 2.1243835708966155e-08,
      "loss": 0.4797,
      "step": 63758
    },
    {
      "epoch": 1.9586213252234819,
      "grad_norm": 0.5348606705665588,
      "learning_rate": 2.1212362838912705e-08,
      "loss": 0.5135,
      "step": 63759
    },
    {
      "epoch": 1.958652044358431,
      "grad_norm": 0.42852652072906494,
      "learning_rate": 2.1180913275015145e-08,
      "loss": 0.385,
      "step": 63760
    },
    {
      "epoch": 1.95868276349338,
      "grad_norm": 0.4260624945163727,
      "learning_rate": 2.1149487017346758e-08,
      "loss": 0.4959,
      "step": 63761
    },
    {
      "epoch": 1.9587134826283292,
      "grad_norm": 0.39066556096076965,
      "learning_rate": 2.1118084065979705e-08,
      "loss": 0.4364,
      "step": 63762
    },
    {
      "epoch": 1.9587442017632783,
      "grad_norm": 0.45761412382125854,
      "learning_rate": 2.108670442098837e-08,
      "loss": 0.4718,
      "step": 63763
    },
    {
      "epoch": 1.9587749208982275,
      "grad_norm": 0.42464447021484375,
      "learning_rate": 2.1055348082447137e-08,
      "loss": 0.4779,
      "step": 63764
    },
    {
      "epoch": 1.9588056400331766,
      "grad_norm": 0.42228177189826965,
      "learning_rate": 2.102401505042706e-08,
      "loss": 0.4831,
      "step": 63765
    },
    {
      "epoch": 1.9588363591681257,
      "grad_norm": 0.45945289731025696,
      "learning_rate": 2.099270532500253e-08,
      "loss": 0.4621,
      "step": 63766
    },
    {
      "epoch": 1.9588670783030748,
      "grad_norm": 0.3961806893348694,
      "learning_rate": 2.09614189062457e-08,
      "loss": 0.4581,
      "step": 63767
    },
    {
      "epoch": 1.9588977974380242,
      "grad_norm": 0.45330488681793213,
      "learning_rate": 2.0930155794230967e-08,
      "loss": 0.4967,
      "step": 63768
    },
    {
      "epoch": 1.9589285165729733,
      "grad_norm": 0.4238074719905853,
      "learning_rate": 2.08989159890316e-08,
      "loss": 0.4781,
      "step": 63769
    },
    {
      "epoch": 1.9589592357079226,
      "grad_norm": 0.43372753262519836,
      "learning_rate": 2.086769949071865e-08,
      "loss": 0.4959,
      "step": 63770
    },
    {
      "epoch": 1.9589899548428718,
      "grad_norm": 0.41599488258361816,
      "learning_rate": 2.0836506299366512e-08,
      "loss": 0.4748,
      "step": 63771
    },
    {
      "epoch": 1.9590206739778209,
      "grad_norm": 0.4346688687801361,
      "learning_rate": 2.0805336415048448e-08,
      "loss": 0.4988,
      "step": 63772
    },
    {
      "epoch": 1.95905139311277,
      "grad_norm": 0.41815608739852905,
      "learning_rate": 2.0774189837835525e-08,
      "loss": 0.4993,
      "step": 63773
    },
    {
      "epoch": 1.959082112247719,
      "grad_norm": 0.435659259557724,
      "learning_rate": 2.0743066567801006e-08,
      "loss": 0.4333,
      "step": 63774
    },
    {
      "epoch": 1.9591128313826682,
      "grad_norm": 0.49398162961006165,
      "learning_rate": 2.0711966605018174e-08,
      "loss": 0.5573,
      "step": 63775
    },
    {
      "epoch": 1.9591435505176173,
      "grad_norm": 0.40911415219306946,
      "learning_rate": 2.06808899495603e-08,
      "loss": 0.4586,
      "step": 63776
    },
    {
      "epoch": 1.9591742696525665,
      "grad_norm": 0.4477222263813019,
      "learning_rate": 2.064983660149844e-08,
      "loss": 0.4662,
      "step": 63777
    },
    {
      "epoch": 1.9592049887875156,
      "grad_norm": 0.42684170603752136,
      "learning_rate": 2.061880656090698e-08,
      "loss": 0.5005,
      "step": 63778
    },
    {
      "epoch": 1.959235707922465,
      "grad_norm": 0.39871880412101746,
      "learning_rate": 2.0587799827855858e-08,
      "loss": 0.4955,
      "step": 63779
    },
    {
      "epoch": 1.959266427057414,
      "grad_norm": 0.45966529846191406,
      "learning_rate": 2.0556816402419465e-08,
      "loss": 0.4984,
      "step": 63780
    },
    {
      "epoch": 1.9592971461923632,
      "grad_norm": 0.38807278871536255,
      "learning_rate": 2.0525856284669964e-08,
      "loss": 0.4722,
      "step": 63781
    },
    {
      "epoch": 1.9593278653273125,
      "grad_norm": 0.4396437108516693,
      "learning_rate": 2.0494919474678408e-08,
      "loss": 0.4066,
      "step": 63782
    },
    {
      "epoch": 1.9593585844622616,
      "grad_norm": 0.4433499574661255,
      "learning_rate": 2.0464005972518075e-08,
      "loss": 0.4444,
      "step": 63783
    },
    {
      "epoch": 1.9593893035972108,
      "grad_norm": 0.4148411750793457,
      "learning_rate": 2.0433115778262235e-08,
      "loss": 0.4678,
      "step": 63784
    },
    {
      "epoch": 1.9594200227321599,
      "grad_norm": 0.44172054529190063,
      "learning_rate": 2.0402248891980836e-08,
      "loss": 0.4471,
      "step": 63785
    },
    {
      "epoch": 1.959450741867109,
      "grad_norm": 0.4497741162776947,
      "learning_rate": 2.037140531374715e-08,
      "loss": 0.409,
      "step": 63786
    },
    {
      "epoch": 1.9594814610020581,
      "grad_norm": 0.4471224844455719,
      "learning_rate": 2.0340585043632232e-08,
      "loss": 0.4999,
      "step": 63787
    },
    {
      "epoch": 1.9595121801370072,
      "grad_norm": 0.4294334948062897,
      "learning_rate": 2.030978808171047e-08,
      "loss": 0.4582,
      "step": 63788
    },
    {
      "epoch": 1.9595428992719564,
      "grad_norm": 0.4720749855041504,
      "learning_rate": 2.027901442805069e-08,
      "loss": 0.4169,
      "step": 63789
    },
    {
      "epoch": 1.9595736184069057,
      "grad_norm": 0.560498058795929,
      "learning_rate": 2.0248264082727288e-08,
      "loss": 0.5091,
      "step": 63790
    },
    {
      "epoch": 1.9596043375418548,
      "grad_norm": 0.49511611461639404,
      "learning_rate": 2.02175370458102e-08,
      "loss": 0.5103,
      "step": 63791
    },
    {
      "epoch": 1.959635056676804,
      "grad_norm": 0.4485842287540436,
      "learning_rate": 2.01868333173727e-08,
      "loss": 0.4958,
      "step": 63792
    },
    {
      "epoch": 1.9596657758117533,
      "grad_norm": 0.421665757894516,
      "learning_rate": 2.015615289748474e-08,
      "loss": 0.5261,
      "step": 63793
    },
    {
      "epoch": 1.9596964949467024,
      "grad_norm": 0.43679291009902954,
      "learning_rate": 2.0125495786220695e-08,
      "loss": 0.4104,
      "step": 63794
    },
    {
      "epoch": 1.9597272140816515,
      "grad_norm": 0.5650641918182373,
      "learning_rate": 2.0094861983649407e-08,
      "loss": 0.4427,
      "step": 63795
    },
    {
      "epoch": 1.9597579332166006,
      "grad_norm": 0.4680909514427185,
      "learning_rate": 2.0064251489843035e-08,
      "loss": 0.462,
      "step": 63796
    },
    {
      "epoch": 1.9597886523515498,
      "grad_norm": 0.40278229117393494,
      "learning_rate": 2.0033664304874856e-08,
      "loss": 0.5164,
      "step": 63797
    },
    {
      "epoch": 1.9598193714864989,
      "grad_norm": 0.43495339155197144,
      "learning_rate": 2.0003100428814813e-08,
      "loss": 0.4567,
      "step": 63798
    },
    {
      "epoch": 1.959850090621448,
      "grad_norm": 0.44893717765808105,
      "learning_rate": 1.9972559861733963e-08,
      "loss": 0.4951,
      "step": 63799
    },
    {
      "epoch": 1.9598808097563971,
      "grad_norm": 0.3993842303752899,
      "learning_rate": 1.994204260370447e-08,
      "loss": 0.4379,
      "step": 63800
    },
    {
      "epoch": 1.9599115288913465,
      "grad_norm": 0.42909693717956543,
      "learning_rate": 1.9911548654797385e-08,
      "loss": 0.4298,
      "step": 63801
    },
    {
      "epoch": 1.9599422480262956,
      "grad_norm": 0.49866044521331787,
      "learning_rate": 1.9881078015083767e-08,
      "loss": 0.472,
      "step": 63802
    },
    {
      "epoch": 1.9599729671612447,
      "grad_norm": 0.4276590049266815,
      "learning_rate": 1.9850630684635775e-08,
      "loss": 0.3979,
      "step": 63803
    },
    {
      "epoch": 1.960003686296194,
      "grad_norm": 0.4249558448791504,
      "learning_rate": 1.9820206663522244e-08,
      "loss": 0.5157,
      "step": 63804
    },
    {
      "epoch": 1.9600344054311432,
      "grad_norm": 0.45774349570274353,
      "learning_rate": 1.9789805951816453e-08,
      "loss": 0.4968,
      "step": 63805
    },
    {
      "epoch": 1.9600651245660923,
      "grad_norm": 0.448378324508667,
      "learning_rate": 1.9759428549588344e-08,
      "loss": 0.4705,
      "step": 63806
    },
    {
      "epoch": 1.9600958437010414,
      "grad_norm": 0.41832664608955383,
      "learning_rate": 1.972907445691008e-08,
      "loss": 0.4188,
      "step": 63807
    },
    {
      "epoch": 1.9601265628359905,
      "grad_norm": 0.44511398673057556,
      "learning_rate": 1.9698743673850494e-08,
      "loss": 0.4803,
      "step": 63808
    },
    {
      "epoch": 1.9601572819709396,
      "grad_norm": 0.4407045245170593,
      "learning_rate": 1.9668436200481755e-08,
      "loss": 0.4203,
      "step": 63809
    },
    {
      "epoch": 1.9601880011058888,
      "grad_norm": 0.4239608943462372,
      "learning_rate": 1.96381520368738e-08,
      "loss": 0.5022,
      "step": 63810
    },
    {
      "epoch": 1.9602187202408379,
      "grad_norm": 0.4709146320819855,
      "learning_rate": 1.9607891183098805e-08,
      "loss": 0.45,
      "step": 63811
    },
    {
      "epoch": 1.9602494393757872,
      "grad_norm": 0.41802969574928284,
      "learning_rate": 1.957765363922559e-08,
      "loss": 0.5095,
      "step": 63812
    },
    {
      "epoch": 1.9602801585107363,
      "grad_norm": 0.416385293006897,
      "learning_rate": 1.954743940532633e-08,
      "loss": 0.4682,
      "step": 63813
    },
    {
      "epoch": 1.9603108776456855,
      "grad_norm": 0.41338932514190674,
      "learning_rate": 1.9517248481472074e-08,
      "loss": 0.5342,
      "step": 63814
    },
    {
      "epoch": 1.9603415967806348,
      "grad_norm": 0.43948692083358765,
      "learning_rate": 1.9487080867730545e-08,
      "loss": 0.477,
      "step": 63815
    },
    {
      "epoch": 1.960372315915584,
      "grad_norm": 0.45421144366264343,
      "learning_rate": 1.9456936564175023e-08,
      "loss": 0.5032,
      "step": 63816
    },
    {
      "epoch": 1.960403035050533,
      "grad_norm": 0.42788782715797424,
      "learning_rate": 1.9426815570875447e-08,
      "loss": 0.4788,
      "step": 63817
    },
    {
      "epoch": 1.9604337541854822,
      "grad_norm": 0.478783518075943,
      "learning_rate": 1.939671788790065e-08,
      "loss": 0.418,
      "step": 63818
    },
    {
      "epoch": 1.9604644733204313,
      "grad_norm": 0.42505115270614624,
      "learning_rate": 1.9366643515321692e-08,
      "loss": 0.4285,
      "step": 63819
    },
    {
      "epoch": 1.9604951924553804,
      "grad_norm": 0.46209660172462463,
      "learning_rate": 1.9336592453209623e-08,
      "loss": 0.4404,
      "step": 63820
    },
    {
      "epoch": 1.9605259115903295,
      "grad_norm": 0.4816564619541168,
      "learning_rate": 1.930656470163328e-08,
      "loss": 0.4873,
      "step": 63821
    },
    {
      "epoch": 1.9605566307252786,
      "grad_norm": 0.4416009187698364,
      "learning_rate": 1.9276560260664824e-08,
      "loss": 0.3917,
      "step": 63822
    },
    {
      "epoch": 1.960587349860228,
      "grad_norm": 0.42063167691230774,
      "learning_rate": 1.924657913037087e-08,
      "loss": 0.5067,
      "step": 63823
    },
    {
      "epoch": 1.960618068995177,
      "grad_norm": 0.49785634875297546,
      "learning_rate": 1.9216621310825802e-08,
      "loss": 0.447,
      "step": 63824
    },
    {
      "epoch": 1.9606487881301262,
      "grad_norm": 0.42779576778411865,
      "learning_rate": 1.9186686802096232e-08,
      "loss": 0.5008,
      "step": 63825
    },
    {
      "epoch": 1.9606795072650756,
      "grad_norm": 0.41765984892845154,
      "learning_rate": 1.915677560425322e-08,
      "loss": 0.4505,
      "step": 63826
    },
    {
      "epoch": 1.9607102264000247,
      "grad_norm": 0.4468032419681549,
      "learning_rate": 1.9126887717366705e-08,
      "loss": 0.354,
      "step": 63827
    },
    {
      "epoch": 1.9607409455349738,
      "grad_norm": 0.4790957272052765,
      "learning_rate": 1.909702314150663e-08,
      "loss": 0.4442,
      "step": 63828
    },
    {
      "epoch": 1.960771664669923,
      "grad_norm": 0.5111197829246521,
      "learning_rate": 1.9067181876741836e-08,
      "loss": 0.4673,
      "step": 63829
    },
    {
      "epoch": 1.960802383804872,
      "grad_norm": 0.4822981655597687,
      "learning_rate": 1.903736392314337e-08,
      "loss": 0.3976,
      "step": 63830
    },
    {
      "epoch": 1.9608331029398212,
      "grad_norm": 0.4552496373653412,
      "learning_rate": 1.900756928078007e-08,
      "loss": 0.4689,
      "step": 63831
    },
    {
      "epoch": 1.9608638220747703,
      "grad_norm": 0.535697340965271,
      "learning_rate": 1.8977797949721876e-08,
      "loss": 0.4431,
      "step": 63832
    },
    {
      "epoch": 1.9608945412097194,
      "grad_norm": 0.4619695246219635,
      "learning_rate": 1.8948049930037628e-08,
      "loss": 0.4171,
      "step": 63833
    },
    {
      "epoch": 1.9609252603446687,
      "grad_norm": 0.48015812039375305,
      "learning_rate": 1.8918325221797263e-08,
      "loss": 0.405,
      "step": 63834
    },
    {
      "epoch": 1.9609559794796179,
      "grad_norm": 0.4378209412097931,
      "learning_rate": 1.888862382507073e-08,
      "loss": 0.4527,
      "step": 63835
    },
    {
      "epoch": 1.960986698614567,
      "grad_norm": 0.412109911441803,
      "learning_rate": 1.885894573992575e-08,
      "loss": 0.4792,
      "step": 63836
    },
    {
      "epoch": 1.9610174177495163,
      "grad_norm": 0.40075260400772095,
      "learning_rate": 1.8829290966433378e-08,
      "loss": 0.4453,
      "step": 63837
    },
    {
      "epoch": 1.9610481368844654,
      "grad_norm": 0.45086124539375305,
      "learning_rate": 1.879965950466245e-08,
      "loss": 0.4893,
      "step": 63838
    },
    {
      "epoch": 1.9610788560194146,
      "grad_norm": 0.4305761456489563,
      "learning_rate": 1.8770051354682905e-08,
      "loss": 0.4429,
      "step": 63839
    },
    {
      "epoch": 1.9611095751543637,
      "grad_norm": 0.4082337021827698,
      "learning_rate": 1.8740466516561363e-08,
      "loss": 0.4668,
      "step": 63840
    },
    {
      "epoch": 1.9611402942893128,
      "grad_norm": 0.41125184297561646,
      "learning_rate": 1.8710904990369984e-08,
      "loss": 0.4684,
      "step": 63841
    },
    {
      "epoch": 1.961171013424262,
      "grad_norm": 0.42606544494628906,
      "learning_rate": 1.868136677617538e-08,
      "loss": 0.464,
      "step": 63842
    },
    {
      "epoch": 1.961201732559211,
      "grad_norm": 0.4518795907497406,
      "learning_rate": 1.865185187404861e-08,
      "loss": 0.5033,
      "step": 63843
    },
    {
      "epoch": 1.9612324516941602,
      "grad_norm": 0.4361235499382019,
      "learning_rate": 1.8622360284056286e-08,
      "loss": 0.4721,
      "step": 63844
    },
    {
      "epoch": 1.9612631708291095,
      "grad_norm": 0.4224954843521118,
      "learning_rate": 1.8592892006268347e-08,
      "loss": 0.4222,
      "step": 63845
    },
    {
      "epoch": 1.9612938899640586,
      "grad_norm": 0.4247441291809082,
      "learning_rate": 1.8563447040754744e-08,
      "loss": 0.4809,
      "step": 63846
    },
    {
      "epoch": 1.9613246090990077,
      "grad_norm": 0.42368942499160767,
      "learning_rate": 1.85340253875832e-08,
      "loss": 0.5619,
      "step": 63847
    },
    {
      "epoch": 1.961355328233957,
      "grad_norm": 0.47430840134620667,
      "learning_rate": 1.850462704682254e-08,
      "loss": 0.4735,
      "step": 63848
    },
    {
      "epoch": 1.9613860473689062,
      "grad_norm": 0.4413700997829437,
      "learning_rate": 1.8475252018541613e-08,
      "loss": 0.4565,
      "step": 63849
    },
    {
      "epoch": 1.9614167665038553,
      "grad_norm": 0.4134766161441803,
      "learning_rate": 1.8445900302808127e-08,
      "loss": 0.3669,
      "step": 63850
    },
    {
      "epoch": 1.9614474856388044,
      "grad_norm": 0.4138244390487671,
      "learning_rate": 1.841657189969093e-08,
      "loss": 0.471,
      "step": 63851
    },
    {
      "epoch": 1.9614782047737536,
      "grad_norm": 0.40226495265960693,
      "learning_rate": 1.8387266809259953e-08,
      "loss": 0.3997,
      "step": 63852
    },
    {
      "epoch": 1.9615089239087027,
      "grad_norm": 0.493881493806839,
      "learning_rate": 1.8357985031582927e-08,
      "loss": 0.4606,
      "step": 63853
    },
    {
      "epoch": 1.9615396430436518,
      "grad_norm": 0.4471066892147064,
      "learning_rate": 1.8328726566727573e-08,
      "loss": 0.515,
      "step": 63854
    },
    {
      "epoch": 1.961570362178601,
      "grad_norm": 0.40682849287986755,
      "learning_rate": 1.8299491414761615e-08,
      "loss": 0.3679,
      "step": 63855
    },
    {
      "epoch": 1.9616010813135503,
      "grad_norm": 0.4067149758338928,
      "learning_rate": 1.8270279575755003e-08,
      "loss": 0.5035,
      "step": 63856
    },
    {
      "epoch": 1.9616318004484994,
      "grad_norm": 0.4603937864303589,
      "learning_rate": 1.824109104977545e-08,
      "loss": 0.5116,
      "step": 63857
    },
    {
      "epoch": 1.9616625195834485,
      "grad_norm": 0.5584793090820312,
      "learning_rate": 1.8211925836891796e-08,
      "loss": 0.4769,
      "step": 63858
    },
    {
      "epoch": 1.9616932387183978,
      "grad_norm": 0.4366288185119629,
      "learning_rate": 1.8182783937169546e-08,
      "loss": 0.5379,
      "step": 63859
    },
    {
      "epoch": 1.961723957853347,
      "grad_norm": 0.513293981552124,
      "learning_rate": 1.815366535067975e-08,
      "loss": 0.4349,
      "step": 63860
    },
    {
      "epoch": 1.961754676988296,
      "grad_norm": 0.47732284665107727,
      "learning_rate": 1.8124570077489023e-08,
      "loss": 0.4532,
      "step": 63861
    },
    {
      "epoch": 1.9617853961232452,
      "grad_norm": 0.45812535285949707,
      "learning_rate": 1.809549811766509e-08,
      "loss": 0.4745,
      "step": 63862
    },
    {
      "epoch": 1.9618161152581943,
      "grad_norm": 0.4298331141471863,
      "learning_rate": 1.8066449471276782e-08,
      "loss": 0.4795,
      "step": 63863
    },
    {
      "epoch": 1.9618468343931434,
      "grad_norm": 0.4876783490180969,
      "learning_rate": 1.8037424138390712e-08,
      "loss": 0.463,
      "step": 63864
    },
    {
      "epoch": 1.9618775535280926,
      "grad_norm": 0.5170096158981323,
      "learning_rate": 1.800842211907572e-08,
      "loss": 0.4857,
      "step": 63865
    },
    {
      "epoch": 1.9619082726630417,
      "grad_norm": 0.4722481667995453,
      "learning_rate": 1.7979443413399523e-08,
      "loss": 0.4402,
      "step": 63866
    },
    {
      "epoch": 1.9619389917979908,
      "grad_norm": 0.49250972270965576,
      "learning_rate": 1.7950488021428734e-08,
      "loss": 0.4069,
      "step": 63867
    },
    {
      "epoch": 1.9619697109329401,
      "grad_norm": 0.4808347225189209,
      "learning_rate": 1.7921555943232193e-08,
      "loss": 0.4046,
      "step": 63868
    },
    {
      "epoch": 1.9620004300678893,
      "grad_norm": 0.4507255256175995,
      "learning_rate": 1.789264717887651e-08,
      "loss": 0.5307,
      "step": 63869
    },
    {
      "epoch": 1.9620311492028386,
      "grad_norm": 0.46120619773864746,
      "learning_rate": 1.7863761728430517e-08,
      "loss": 0.4389,
      "step": 63870
    },
    {
      "epoch": 1.9620618683377877,
      "grad_norm": 0.4078596830368042,
      "learning_rate": 1.783489959195972e-08,
      "loss": 0.5328,
      "step": 63871
    },
    {
      "epoch": 1.9620925874727368,
      "grad_norm": 0.44227954745292664,
      "learning_rate": 1.780606076953406e-08,
      "loss": 0.4845,
      "step": 63872
    },
    {
      "epoch": 1.962123306607686,
      "grad_norm": 0.43819642066955566,
      "learning_rate": 1.7777245261217936e-08,
      "loss": 0.5116,
      "step": 63873
    },
    {
      "epoch": 1.962154025742635,
      "grad_norm": 0.44780951738357544,
      "learning_rate": 1.7748453067081284e-08,
      "loss": 0.4647,
      "step": 63874
    },
    {
      "epoch": 1.9621847448775842,
      "grad_norm": 0.42566460371017456,
      "learning_rate": 1.7719684187190722e-08,
      "loss": 0.5596,
      "step": 63875
    },
    {
      "epoch": 1.9622154640125333,
      "grad_norm": 0.4342256486415863,
      "learning_rate": 1.7690938621611754e-08,
      "loss": 0.4222,
      "step": 63876
    },
    {
      "epoch": 1.9622461831474824,
      "grad_norm": 0.40904664993286133,
      "learning_rate": 1.766221637041321e-08,
      "loss": 0.4205,
      "step": 63877
    },
    {
      "epoch": 1.9622769022824316,
      "grad_norm": 0.5032556056976318,
      "learning_rate": 1.7633517433661707e-08,
      "loss": 0.4524,
      "step": 63878
    },
    {
      "epoch": 1.962307621417381,
      "grad_norm": 0.4397519528865814,
      "learning_rate": 1.7604841811424966e-08,
      "loss": 0.5251,
      "step": 63879
    },
    {
      "epoch": 1.96233834055233,
      "grad_norm": 0.43749144673347473,
      "learning_rate": 1.7576189503768493e-08,
      "loss": 0.3702,
      "step": 63880
    },
    {
      "epoch": 1.9623690596872794,
      "grad_norm": 0.4934104084968567,
      "learning_rate": 1.7547560510760008e-08,
      "loss": 0.5113,
      "step": 63881
    },
    {
      "epoch": 1.9623997788222285,
      "grad_norm": 0.4902261793613434,
      "learning_rate": 1.7518954832467238e-08,
      "loss": 0.4721,
      "step": 63882
    },
    {
      "epoch": 1.9624304979571776,
      "grad_norm": 0.4202045500278473,
      "learning_rate": 1.7490372468955684e-08,
      "loss": 0.418,
      "step": 63883
    },
    {
      "epoch": 1.9624612170921267,
      "grad_norm": 0.44984543323516846,
      "learning_rate": 1.7461813420291963e-08,
      "loss": 0.3988,
      "step": 63884
    },
    {
      "epoch": 1.9624919362270759,
      "grad_norm": 0.4165307283401489,
      "learning_rate": 1.7433277686543792e-08,
      "loss": 0.4541,
      "step": 63885
    },
    {
      "epoch": 1.962522655362025,
      "grad_norm": 0.4260307252407074,
      "learning_rate": 1.740476526777668e-08,
      "loss": 0.4952,
      "step": 63886
    },
    {
      "epoch": 1.962553374496974,
      "grad_norm": 0.5125032067298889,
      "learning_rate": 1.737627616405835e-08,
      "loss": 0.534,
      "step": 63887
    },
    {
      "epoch": 1.9625840936319232,
      "grad_norm": 0.42975082993507385,
      "learning_rate": 1.734781037545541e-08,
      "loss": 0.3891,
      "step": 63888
    },
    {
      "epoch": 1.9626148127668723,
      "grad_norm": 0.43474096059799194,
      "learning_rate": 1.731936790203337e-08,
      "loss": 0.5967,
      "step": 63889
    },
    {
      "epoch": 1.9626455319018217,
      "grad_norm": 0.4419720768928528,
      "learning_rate": 1.729094874385995e-08,
      "loss": 0.4904,
      "step": 63890
    },
    {
      "epoch": 1.9626762510367708,
      "grad_norm": 0.4375039041042328,
      "learning_rate": 1.726255290099954e-08,
      "loss": 0.4977,
      "step": 63891
    },
    {
      "epoch": 1.96270697017172,
      "grad_norm": 0.4437766671180725,
      "learning_rate": 1.723418037351987e-08,
      "loss": 0.4697,
      "step": 63892
    },
    {
      "epoch": 1.9627376893066693,
      "grad_norm": 0.4585595726966858,
      "learning_rate": 1.720583116148755e-08,
      "loss": 0.5292,
      "step": 63893
    },
    {
      "epoch": 1.9627684084416184,
      "grad_norm": 0.5126091837882996,
      "learning_rate": 1.7177505264968087e-08,
      "loss": 0.4853,
      "step": 63894
    },
    {
      "epoch": 1.9627991275765675,
      "grad_norm": 0.4341570734977722,
      "learning_rate": 1.7149202684026977e-08,
      "loss": 0.3629,
      "step": 63895
    },
    {
      "epoch": 1.9628298467115166,
      "grad_norm": 0.4919762909412384,
      "learning_rate": 1.712092341873195e-08,
      "loss": 0.5161,
      "step": 63896
    },
    {
      "epoch": 1.9628605658464657,
      "grad_norm": 0.4264978766441345,
      "learning_rate": 1.7092667469147395e-08,
      "loss": 0.4048,
      "step": 63897
    },
    {
      "epoch": 1.9628912849814149,
      "grad_norm": 0.4038200080394745,
      "learning_rate": 1.7064434835341036e-08,
      "loss": 0.5011,
      "step": 63898
    },
    {
      "epoch": 1.962922004116364,
      "grad_norm": 0.546397864818573,
      "learning_rate": 1.703622551737727e-08,
      "loss": 0.4947,
      "step": 63899
    },
    {
      "epoch": 1.962952723251313,
      "grad_norm": 0.48922377824783325,
      "learning_rate": 1.7008039515322704e-08,
      "loss": 0.5121,
      "step": 63900
    },
    {
      "epoch": 1.9629834423862624,
      "grad_norm": 0.41833391785621643,
      "learning_rate": 1.6979876829242847e-08,
      "loss": 0.4217,
      "step": 63901
    },
    {
      "epoch": 1.9630141615212116,
      "grad_norm": 0.4003453254699707,
      "learning_rate": 1.695173745920431e-08,
      "loss": 0.4995,
      "step": 63902
    },
    {
      "epoch": 1.9630448806561607,
      "grad_norm": 0.44196051359176636,
      "learning_rate": 1.6923621405272593e-08,
      "loss": 0.4512,
      "step": 63903
    },
    {
      "epoch": 1.96307559979111,
      "grad_norm": 0.4062279760837555,
      "learning_rate": 1.6895528667512096e-08,
      "loss": 0.4944,
      "step": 63904
    },
    {
      "epoch": 1.9631063189260591,
      "grad_norm": 0.4173664152622223,
      "learning_rate": 1.6867459245989424e-08,
      "loss": 0.4141,
      "step": 63905
    },
    {
      "epoch": 1.9631370380610083,
      "grad_norm": 0.4642401933670044,
      "learning_rate": 1.683941314077009e-08,
      "loss": 0.441,
      "step": 63906
    },
    {
      "epoch": 1.9631677571959574,
      "grad_norm": 0.4605225622653961,
      "learning_rate": 1.6811390351919587e-08,
      "loss": 0.5069,
      "step": 63907
    },
    {
      "epoch": 1.9631984763309065,
      "grad_norm": 0.47962015867233276,
      "learning_rate": 1.6783390879502315e-08,
      "loss": 0.4714,
      "step": 63908
    },
    {
      "epoch": 1.9632291954658556,
      "grad_norm": 0.44257986545562744,
      "learning_rate": 1.6755414723585995e-08,
      "loss": 0.4431,
      "step": 63909
    },
    {
      "epoch": 1.9632599146008047,
      "grad_norm": 0.44159650802612305,
      "learning_rate": 1.672746188423391e-08,
      "loss": 0.5442,
      "step": 63910
    },
    {
      "epoch": 1.9632906337357539,
      "grad_norm": 0.45334768295288086,
      "learning_rate": 1.6699532361512673e-08,
      "loss": 0.503,
      "step": 63911
    },
    {
      "epoch": 1.9633213528707032,
      "grad_norm": 0.47663137316703796,
      "learning_rate": 1.6671626155486677e-08,
      "loss": 0.4159,
      "step": 63912
    },
    {
      "epoch": 1.9633520720056523,
      "grad_norm": 0.5602691173553467,
      "learning_rate": 1.6643743266221424e-08,
      "loss": 0.4506,
      "step": 63913
    },
    {
      "epoch": 1.9633827911406014,
      "grad_norm": 0.4914284646511078,
      "learning_rate": 1.6615883693781308e-08,
      "loss": 0.5226,
      "step": 63914
    },
    {
      "epoch": 1.9634135102755508,
      "grad_norm": 0.5839644074440002,
      "learning_rate": 1.6588047438232944e-08,
      "loss": 0.4644,
      "step": 63915
    },
    {
      "epoch": 1.9634442294105,
      "grad_norm": 0.4561421573162079,
      "learning_rate": 1.6560234499639615e-08,
      "loss": 0.4695,
      "step": 63916
    },
    {
      "epoch": 1.963474948545449,
      "grad_norm": 0.4176470637321472,
      "learning_rate": 1.653244487806793e-08,
      "loss": 0.4007,
      "step": 63917
    },
    {
      "epoch": 1.9635056676803981,
      "grad_norm": 0.4401165246963501,
      "learning_rate": 1.6504678573580068e-08,
      "loss": 0.5025,
      "step": 63918
    },
    {
      "epoch": 1.9635363868153473,
      "grad_norm": 0.44111984968185425,
      "learning_rate": 1.647693558624486e-08,
      "loss": 0.536,
      "step": 63919
    },
    {
      "epoch": 1.9635671059502964,
      "grad_norm": 0.43189409375190735,
      "learning_rate": 1.644921591612447e-08,
      "loss": 0.4541,
      "step": 63920
    },
    {
      "epoch": 1.9635978250852455,
      "grad_norm": 0.5565353035926819,
      "learning_rate": 1.6421519563283304e-08,
      "loss": 0.3551,
      "step": 63921
    },
    {
      "epoch": 1.9636285442201946,
      "grad_norm": 0.40525051951408386,
      "learning_rate": 1.639384652778797e-08,
      "loss": 0.4812,
      "step": 63922
    },
    {
      "epoch": 1.963659263355144,
      "grad_norm": 0.45410147309303284,
      "learning_rate": 1.6366196809701752e-08,
      "loss": 0.4958,
      "step": 63923
    },
    {
      "epoch": 1.963689982490093,
      "grad_norm": 0.446730375289917,
      "learning_rate": 1.6338570409089038e-08,
      "loss": 0.5159,
      "step": 63924
    },
    {
      "epoch": 1.9637207016250422,
      "grad_norm": 0.4462130665779114,
      "learning_rate": 1.6310967326015337e-08,
      "loss": 0.4596,
      "step": 63925
    },
    {
      "epoch": 1.9637514207599915,
      "grad_norm": 0.4462507367134094,
      "learning_rate": 1.628338756054504e-08,
      "loss": 0.4423,
      "step": 63926
    },
    {
      "epoch": 1.9637821398949407,
      "grad_norm": 0.4611048102378845,
      "learning_rate": 1.6255831112741428e-08,
      "loss": 0.4914,
      "step": 63927
    },
    {
      "epoch": 1.9638128590298898,
      "grad_norm": 0.48110321164131165,
      "learning_rate": 1.6228297982670004e-08,
      "loss": 0.4529,
      "step": 63928
    },
    {
      "epoch": 1.963843578164839,
      "grad_norm": 0.4321610927581787,
      "learning_rate": 1.6200788170394054e-08,
      "loss": 0.5401,
      "step": 63929
    },
    {
      "epoch": 1.963874297299788,
      "grad_norm": 0.42971673607826233,
      "learning_rate": 1.617330167597908e-08,
      "loss": 0.5129,
      "step": 63930
    },
    {
      "epoch": 1.9639050164347371,
      "grad_norm": 0.4402701258659363,
      "learning_rate": 1.6145838499488363e-08,
      "loss": 0.4874,
      "step": 63931
    },
    {
      "epoch": 1.9639357355696863,
      "grad_norm": 0.44766849279403687,
      "learning_rate": 1.61183986409863e-08,
      "loss": 0.5529,
      "step": 63932
    },
    {
      "epoch": 1.9639664547046354,
      "grad_norm": 0.4274902939796448,
      "learning_rate": 1.6090982100537278e-08,
      "loss": 0.4646,
      "step": 63933
    },
    {
      "epoch": 1.9639971738395847,
      "grad_norm": 0.4369143843650818,
      "learning_rate": 1.6063588878204582e-08,
      "loss": 0.4833,
      "step": 63934
    },
    {
      "epoch": 1.9640278929745338,
      "grad_norm": 0.45482414960861206,
      "learning_rate": 1.6036218974052607e-08,
      "loss": 0.4956,
      "step": 63935
    },
    {
      "epoch": 1.964058612109483,
      "grad_norm": 0.434614360332489,
      "learning_rate": 1.6008872388145748e-08,
      "loss": 0.4374,
      "step": 63936
    },
    {
      "epoch": 1.9640893312444323,
      "grad_norm": 0.4128911793231964,
      "learning_rate": 1.598154912054728e-08,
      "loss": 0.4393,
      "step": 63937
    },
    {
      "epoch": 1.9641200503793814,
      "grad_norm": 0.41486236453056335,
      "learning_rate": 1.59542491713216e-08,
      "loss": 0.5164,
      "step": 63938
    },
    {
      "epoch": 1.9641507695143305,
      "grad_norm": 0.3843876123428345,
      "learning_rate": 1.5926972540530884e-08,
      "loss": 0.4628,
      "step": 63939
    },
    {
      "epoch": 1.9641814886492797,
      "grad_norm": 0.4425017535686493,
      "learning_rate": 1.5899719228240628e-08,
      "loss": 0.5252,
      "step": 63940
    },
    {
      "epoch": 1.9642122077842288,
      "grad_norm": 0.469545841217041,
      "learning_rate": 1.5872489234514123e-08,
      "loss": 0.5621,
      "step": 63941
    },
    {
      "epoch": 1.964242926919178,
      "grad_norm": 0.40042075514793396,
      "learning_rate": 1.5845282559414643e-08,
      "loss": 0.4944,
      "step": 63942
    },
    {
      "epoch": 1.964273646054127,
      "grad_norm": 0.4224233031272888,
      "learning_rate": 1.5818099203005476e-08,
      "loss": 0.5048,
      "step": 63943
    },
    {
      "epoch": 1.9643043651890761,
      "grad_norm": 0.5055771470069885,
      "learning_rate": 1.5790939165351015e-08,
      "loss": 0.5162,
      "step": 63944
    },
    {
      "epoch": 1.9643350843240255,
      "grad_norm": 0.41699665784835815,
      "learning_rate": 1.5763802446513433e-08,
      "loss": 0.4209,
      "step": 63945
    },
    {
      "epoch": 1.9643658034589746,
      "grad_norm": 0.4435517191886902,
      "learning_rate": 1.573668904655712e-08,
      "loss": 0.533,
      "step": 63946
    },
    {
      "epoch": 1.9643965225939237,
      "grad_norm": 0.5064549446105957,
      "learning_rate": 1.5709598965545358e-08,
      "loss": 0.4309,
      "step": 63947
    },
    {
      "epoch": 1.964427241728873,
      "grad_norm": 0.46325039863586426,
      "learning_rate": 1.5682532203540325e-08,
      "loss": 0.4067,
      "step": 63948
    },
    {
      "epoch": 1.9644579608638222,
      "grad_norm": 0.6195618510246277,
      "learning_rate": 1.5655488760606407e-08,
      "loss": 0.4518,
      "step": 63949
    },
    {
      "epoch": 1.9644886799987713,
      "grad_norm": 0.43170884251594543,
      "learning_rate": 1.5628468636805782e-08,
      "loss": 0.4729,
      "step": 63950
    },
    {
      "epoch": 1.9645193991337204,
      "grad_norm": 0.4316175878047943,
      "learning_rate": 1.560147183220395e-08,
      "loss": 0.5024,
      "step": 63951
    },
    {
      "epoch": 1.9645501182686695,
      "grad_norm": 0.44688743352890015,
      "learning_rate": 1.5574498346860866e-08,
      "loss": 0.4417,
      "step": 63952
    },
    {
      "epoch": 1.9645808374036187,
      "grad_norm": 0.5032012462615967,
      "learning_rate": 1.554754818084092e-08,
      "loss": 0.5182,
      "step": 63953
    },
    {
      "epoch": 1.9646115565385678,
      "grad_norm": 0.4700962007045746,
      "learning_rate": 1.5520621334206288e-08,
      "loss": 0.5163,
      "step": 63954
    },
    {
      "epoch": 1.964642275673517,
      "grad_norm": 0.3906281590461731,
      "learning_rate": 1.5493717807022468e-08,
      "loss": 0.4446,
      "step": 63955
    },
    {
      "epoch": 1.9646729948084662,
      "grad_norm": 0.4454303979873657,
      "learning_rate": 1.5466837599348304e-08,
      "loss": 0.433,
      "step": 63956
    },
    {
      "epoch": 1.9647037139434154,
      "grad_norm": 0.45264190435409546,
      "learning_rate": 1.5439980711250414e-08,
      "loss": 0.4507,
      "step": 63957
    },
    {
      "epoch": 1.9647344330783645,
      "grad_norm": 0.4478503167629242,
      "learning_rate": 1.5413147142788742e-08,
      "loss": 0.5043,
      "step": 63958
    },
    {
      "epoch": 1.9647651522133138,
      "grad_norm": 0.4718397259712219,
      "learning_rate": 1.5386336894026578e-08,
      "loss": 0.4568,
      "step": 63959
    },
    {
      "epoch": 1.964795871348263,
      "grad_norm": 0.47130629420280457,
      "learning_rate": 1.5359549965028308e-08,
      "loss": 0.4483,
      "step": 63960
    },
    {
      "epoch": 1.964826590483212,
      "grad_norm": 0.39540132880210876,
      "learning_rate": 1.533278635585389e-08,
      "loss": 0.4398,
      "step": 63961
    },
    {
      "epoch": 1.9648573096181612,
      "grad_norm": 0.442507266998291,
      "learning_rate": 1.5306046066567713e-08,
      "loss": 0.434,
      "step": 63962
    },
    {
      "epoch": 1.9648880287531103,
      "grad_norm": 0.48402640223503113,
      "learning_rate": 1.5279329097231954e-08,
      "loss": 0.4897,
      "step": 63963
    },
    {
      "epoch": 1.9649187478880594,
      "grad_norm": 0.4708031415939331,
      "learning_rate": 1.525263544790767e-08,
      "loss": 0.4665,
      "step": 63964
    },
    {
      "epoch": 1.9649494670230085,
      "grad_norm": 0.48367512226104736,
      "learning_rate": 1.522596511865926e-08,
      "loss": 0.4169,
      "step": 63965
    },
    {
      "epoch": 1.9649801861579577,
      "grad_norm": 0.4725887179374695,
      "learning_rate": 1.5199318109546667e-08,
      "loss": 0.4749,
      "step": 63966
    },
    {
      "epoch": 1.965010905292907,
      "grad_norm": 0.46147406101226807,
      "learning_rate": 1.5172694420634293e-08,
      "loss": 0.4533,
      "step": 63967
    },
    {
      "epoch": 1.9650416244278561,
      "grad_norm": 0.45156925916671753,
      "learning_rate": 1.5146094051983195e-08,
      "loss": 0.477,
      "step": 63968
    },
    {
      "epoch": 1.9650723435628052,
      "grad_norm": 0.4627358019351959,
      "learning_rate": 1.5119517003655547e-08,
      "loss": 0.4916,
      "step": 63969
    },
    {
      "epoch": 1.9651030626977546,
      "grad_norm": 0.4590395390987396,
      "learning_rate": 1.5092963275714634e-08,
      "loss": 0.4763,
      "step": 63970
    },
    {
      "epoch": 1.9651337818327037,
      "grad_norm": 0.42705386877059937,
      "learning_rate": 1.5066432868220404e-08,
      "loss": 0.4694,
      "step": 63971
    },
    {
      "epoch": 1.9651645009676528,
      "grad_norm": 0.4336901009082794,
      "learning_rate": 1.503992578123503e-08,
      "loss": 0.4822,
      "step": 63972
    },
    {
      "epoch": 1.965195220102602,
      "grad_norm": 0.39900943636894226,
      "learning_rate": 1.501344201482291e-08,
      "loss": 0.4459,
      "step": 63973
    },
    {
      "epoch": 1.965225939237551,
      "grad_norm": 0.4523361325263977,
      "learning_rate": 1.498698156904399e-08,
      "loss": 0.4462,
      "step": 63974
    },
    {
      "epoch": 1.9652566583725002,
      "grad_norm": 0.4447336196899414,
      "learning_rate": 1.4960544443959334e-08,
      "loss": 0.4797,
      "step": 63975
    },
    {
      "epoch": 1.9652873775074493,
      "grad_norm": 0.4792877435684204,
      "learning_rate": 1.4934130639632227e-08,
      "loss": 0.4273,
      "step": 63976
    },
    {
      "epoch": 1.9653180966423984,
      "grad_norm": 0.4541642367839813,
      "learning_rate": 1.490774015612373e-08,
      "loss": 0.4492,
      "step": 63977
    },
    {
      "epoch": 1.9653488157773475,
      "grad_norm": 0.44989311695098877,
      "learning_rate": 1.4881372993496012e-08,
      "loss": 0.4278,
      "step": 63978
    },
    {
      "epoch": 1.9653795349122969,
      "grad_norm": 0.43168431520462036,
      "learning_rate": 1.485502915181014e-08,
      "loss": 0.4837,
      "step": 63979
    },
    {
      "epoch": 1.965410254047246,
      "grad_norm": 0.47601139545440674,
      "learning_rate": 1.4828708631127175e-08,
      "loss": 0.4881,
      "step": 63980
    },
    {
      "epoch": 1.9654409731821953,
      "grad_norm": 0.4184931814670563,
      "learning_rate": 1.480241143150929e-08,
      "loss": 0.4527,
      "step": 63981
    },
    {
      "epoch": 1.9654716923171445,
      "grad_norm": 0.548406720161438,
      "learning_rate": 1.4776137553017544e-08,
      "loss": 0.4462,
      "step": 63982
    },
    {
      "epoch": 1.9655024114520936,
      "grad_norm": 0.44986629486083984,
      "learning_rate": 1.4749886995714113e-08,
      "loss": 0.4184,
      "step": 63983
    },
    {
      "epoch": 1.9655331305870427,
      "grad_norm": 0.4374387264251709,
      "learning_rate": 1.4723659759658948e-08,
      "loss": 0.4781,
      "step": 63984
    },
    {
      "epoch": 1.9655638497219918,
      "grad_norm": 0.44035378098487854,
      "learning_rate": 1.4697455844914222e-08,
      "loss": 0.4429,
      "step": 63985
    },
    {
      "epoch": 1.965594568856941,
      "grad_norm": 0.4172435402870178,
      "learning_rate": 1.4671275251540995e-08,
      "loss": 0.4916,
      "step": 63986
    },
    {
      "epoch": 1.96562528799189,
      "grad_norm": 0.4491904675960541,
      "learning_rate": 1.4645117979601443e-08,
      "loss": 0.4139,
      "step": 63987
    },
    {
      "epoch": 1.9656560071268392,
      "grad_norm": 0.4690636098384857,
      "learning_rate": 1.4618984029154404e-08,
      "loss": 0.4658,
      "step": 63988
    },
    {
      "epoch": 1.9656867262617883,
      "grad_norm": 0.4133749008178711,
      "learning_rate": 1.4592873400262054e-08,
      "loss": 0.5119,
      "step": 63989
    },
    {
      "epoch": 1.9657174453967377,
      "grad_norm": 0.4098013639450073,
      "learning_rate": 1.4566786092985452e-08,
      "loss": 0.4991,
      "step": 63990
    },
    {
      "epoch": 1.9657481645316868,
      "grad_norm": 0.41686344146728516,
      "learning_rate": 1.4540722107386773e-08,
      "loss": 0.4532,
      "step": 63991
    },
    {
      "epoch": 1.9657788836666361,
      "grad_norm": 0.4173241853713989,
      "learning_rate": 1.4514681443523748e-08,
      "loss": 0.5193,
      "step": 63992
    },
    {
      "epoch": 1.9658096028015852,
      "grad_norm": 0.42067521810531616,
      "learning_rate": 1.448866410146077e-08,
      "loss": 0.4814,
      "step": 63993
    },
    {
      "epoch": 1.9658403219365344,
      "grad_norm": 0.4435192346572876,
      "learning_rate": 1.446267008125557e-08,
      "loss": 0.4934,
      "step": 63994
    },
    {
      "epoch": 1.9658710410714835,
      "grad_norm": 0.3954956531524658,
      "learning_rate": 1.443669938297032e-08,
      "loss": 0.3724,
      "step": 63995
    },
    {
      "epoch": 1.9659017602064326,
      "grad_norm": 0.4578717052936554,
      "learning_rate": 1.4410752006666084e-08,
      "loss": 0.4934,
      "step": 63996
    },
    {
      "epoch": 1.9659324793413817,
      "grad_norm": 0.4697248935699463,
      "learning_rate": 1.4384827952402814e-08,
      "loss": 0.5111,
      "step": 63997
    },
    {
      "epoch": 1.9659631984763308,
      "grad_norm": 0.4008723497390747,
      "learning_rate": 1.435892722024157e-08,
      "loss": 0.464,
      "step": 63998
    },
    {
      "epoch": 1.96599391761128,
      "grad_norm": 0.41796940565109253,
      "learning_rate": 1.4333049810242305e-08,
      "loss": 0.4381,
      "step": 63999
    },
    {
      "epoch": 1.966024636746229,
      "grad_norm": 0.44109705090522766,
      "learning_rate": 1.4307195722464973e-08,
      "loss": 0.4415,
      "step": 64000
    },
    {
      "epoch": 1.9660553558811784,
      "grad_norm": 0.48250138759613037,
      "learning_rate": 1.4281364956970633e-08,
      "loss": 0.3881,
      "step": 64001
    },
    {
      "epoch": 1.9660860750161275,
      "grad_norm": 0.41742536425590515,
      "learning_rate": 1.425555751381924e-08,
      "loss": 0.4204,
      "step": 64002
    },
    {
      "epoch": 1.9661167941510767,
      "grad_norm": 0.4154502749443054,
      "learning_rate": 1.4229773393072966e-08,
      "loss": 0.4638,
      "step": 64003
    },
    {
      "epoch": 1.966147513286026,
      "grad_norm": 0.4796406328678131,
      "learning_rate": 1.420401259478843e-08,
      "loss": 0.4628,
      "step": 64004
    },
    {
      "epoch": 1.9661782324209751,
      "grad_norm": 0.4502035677433014,
      "learning_rate": 1.4178275119028917e-08,
      "loss": 0.5262,
      "step": 64005
    },
    {
      "epoch": 1.9662089515559242,
      "grad_norm": 0.43526849150657654,
      "learning_rate": 1.4152560965853268e-08,
      "loss": 0.5492,
      "step": 64006
    },
    {
      "epoch": 1.9662396706908734,
      "grad_norm": 0.43575891852378845,
      "learning_rate": 1.4126870135322546e-08,
      "loss": 0.4941,
      "step": 64007
    },
    {
      "epoch": 1.9662703898258225,
      "grad_norm": 0.42584940791130066,
      "learning_rate": 1.4101202627494481e-08,
      "loss": 0.4948,
      "step": 64008
    },
    {
      "epoch": 1.9663011089607716,
      "grad_norm": 0.47044408321380615,
      "learning_rate": 1.4075558442431248e-08,
      "loss": 0.4898,
      "step": 64009
    },
    {
      "epoch": 1.9663318280957207,
      "grad_norm": 0.43676987290382385,
      "learning_rate": 1.4049937580191686e-08,
      "loss": 0.5192,
      "step": 64010
    },
    {
      "epoch": 1.9663625472306698,
      "grad_norm": 0.4319087266921997,
      "learning_rate": 1.402434004083686e-08,
      "loss": 0.5116,
      "step": 64011
    },
    {
      "epoch": 1.9663932663656192,
      "grad_norm": 0.42964673042297363,
      "learning_rate": 1.3998765824424498e-08,
      "loss": 0.4496,
      "step": 64012
    },
    {
      "epoch": 1.9664239855005683,
      "grad_norm": 0.45029422640800476,
      "learning_rate": 1.3973214931015666e-08,
      "loss": 0.489,
      "step": 64013
    },
    {
      "epoch": 1.9664547046355174,
      "grad_norm": 0.47168076038360596,
      "learning_rate": 1.3947687360669204e-08,
      "loss": 0.455,
      "step": 64014
    },
    {
      "epoch": 1.9664854237704668,
      "grad_norm": 0.4231157898902893,
      "learning_rate": 1.3922183113446174e-08,
      "loss": 0.4661,
      "step": 64015
    },
    {
      "epoch": 1.9665161429054159,
      "grad_norm": 0.45033159852027893,
      "learning_rate": 1.389670218940542e-08,
      "loss": 0.513,
      "step": 64016
    },
    {
      "epoch": 1.966546862040365,
      "grad_norm": 0.41444167494773865,
      "learning_rate": 1.3871244588605781e-08,
      "loss": 0.5196,
      "step": 64017
    },
    {
      "epoch": 1.9665775811753141,
      "grad_norm": 0.43372035026550293,
      "learning_rate": 1.384581031110832e-08,
      "loss": 0.4425,
      "step": 64018
    },
    {
      "epoch": 1.9666083003102632,
      "grad_norm": 0.4521665573120117,
      "learning_rate": 1.382039935697077e-08,
      "loss": 0.48,
      "step": 64019
    },
    {
      "epoch": 1.9666390194452124,
      "grad_norm": 0.40464961528778076,
      "learning_rate": 1.3795011726253082e-08,
      "loss": 0.4671,
      "step": 64020
    },
    {
      "epoch": 1.9666697385801615,
      "grad_norm": 0.44179075956344604,
      "learning_rate": 1.3769647419014098e-08,
      "loss": 0.5068,
      "step": 64021
    },
    {
      "epoch": 1.9667004577151106,
      "grad_norm": 0.44330671429634094,
      "learning_rate": 1.374430643531377e-08,
      "loss": 0.4431,
      "step": 64022
    },
    {
      "epoch": 1.96673117685006,
      "grad_norm": 0.4553685486316681,
      "learning_rate": 1.3718988775210939e-08,
      "loss": 0.517,
      "step": 64023
    },
    {
      "epoch": 1.966761895985009,
      "grad_norm": 0.4619998335838318,
      "learning_rate": 1.3693694438765558e-08,
      "loss": 0.5199,
      "step": 64024
    },
    {
      "epoch": 1.9667926151199582,
      "grad_norm": 0.46315833926200867,
      "learning_rate": 1.366842342603536e-08,
      "loss": 0.4537,
      "step": 64025
    },
    {
      "epoch": 1.9668233342549075,
      "grad_norm": 0.40233123302459717,
      "learning_rate": 1.3643175737080295e-08,
      "loss": 0.4763,
      "step": 64026
    },
    {
      "epoch": 1.9668540533898566,
      "grad_norm": 0.4661554992198944,
      "learning_rate": 1.3617951371959204e-08,
      "loss": 0.3982,
      "step": 64027
    },
    {
      "epoch": 1.9668847725248058,
      "grad_norm": 0.43625354766845703,
      "learning_rate": 1.359275033072982e-08,
      "loss": 0.4793,
      "step": 64028
    },
    {
      "epoch": 1.9669154916597549,
      "grad_norm": 0.4636355936527252,
      "learning_rate": 1.3567572613453206e-08,
      "loss": 0.4483,
      "step": 64029
    },
    {
      "epoch": 1.966946210794704,
      "grad_norm": 0.40661996603012085,
      "learning_rate": 1.3542418220185982e-08,
      "loss": 0.4562,
      "step": 64030
    },
    {
      "epoch": 1.9669769299296531,
      "grad_norm": 0.38074859976768494,
      "learning_rate": 1.3517287150988101e-08,
      "loss": 0.4482,
      "step": 64031
    },
    {
      "epoch": 1.9670076490646022,
      "grad_norm": 0.43664485216140747,
      "learning_rate": 1.3492179405918405e-08,
      "loss": 0.4538,
      "step": 64032
    },
    {
      "epoch": 1.9670383681995514,
      "grad_norm": 0.44240790605545044,
      "learning_rate": 1.3467094985035733e-08,
      "loss": 0.5147,
      "step": 64033
    },
    {
      "epoch": 1.9670690873345007,
      "grad_norm": 0.43998652696609497,
      "learning_rate": 1.344203388839671e-08,
      "loss": 0.5177,
      "step": 64034
    },
    {
      "epoch": 1.9670998064694498,
      "grad_norm": 0.4403243064880371,
      "learning_rate": 1.3416996116062397e-08,
      "loss": 0.4793,
      "step": 64035
    },
    {
      "epoch": 1.967130525604399,
      "grad_norm": 0.418830543756485,
      "learning_rate": 1.3391981668089416e-08,
      "loss": 0.4792,
      "step": 64036
    },
    {
      "epoch": 1.9671612447393483,
      "grad_norm": 0.4672621190547943,
      "learning_rate": 1.3366990544537717e-08,
      "loss": 0.4434,
      "step": 64037
    },
    {
      "epoch": 1.9671919638742974,
      "grad_norm": 0.4331473410129547,
      "learning_rate": 1.3342022745463923e-08,
      "loss": 0.4282,
      "step": 64038
    },
    {
      "epoch": 1.9672226830092465,
      "grad_norm": 0.4490543603897095,
      "learning_rate": 1.3317078270927986e-08,
      "loss": 0.519,
      "step": 64039
    },
    {
      "epoch": 1.9672534021441956,
      "grad_norm": 0.45611003041267395,
      "learning_rate": 1.3292157120987636e-08,
      "loss": 0.49,
      "step": 64040
    },
    {
      "epoch": 1.9672841212791448,
      "grad_norm": 0.3871520757675171,
      "learning_rate": 1.3267259295700607e-08,
      "loss": 0.4361,
      "step": 64041
    },
    {
      "epoch": 1.9673148404140939,
      "grad_norm": 0.4265318810939789,
      "learning_rate": 1.324238479512574e-08,
      "loss": 0.4651,
      "step": 64042
    },
    {
      "epoch": 1.967345559549043,
      "grad_norm": 0.43105679750442505,
      "learning_rate": 1.3217533619319655e-08,
      "loss": 0.4742,
      "step": 64043
    },
    {
      "epoch": 1.9673762786839921,
      "grad_norm": 0.4380492866039276,
      "learning_rate": 1.3192705768342307e-08,
      "loss": 0.4492,
      "step": 64044
    },
    {
      "epoch": 1.9674069978189415,
      "grad_norm": 0.4081847071647644,
      "learning_rate": 1.3167901242250314e-08,
      "loss": 0.4263,
      "step": 64045
    },
    {
      "epoch": 1.9674377169538906,
      "grad_norm": 0.4453931450843811,
      "learning_rate": 1.314312004110252e-08,
      "loss": 0.4746,
      "step": 64046
    },
    {
      "epoch": 1.9674684360888397,
      "grad_norm": 0.4307897984981537,
      "learning_rate": 1.3118362164956656e-08,
      "loss": 0.462,
      "step": 64047
    },
    {
      "epoch": 1.967499155223789,
      "grad_norm": 0.44067275524139404,
      "learning_rate": 1.3093627613870452e-08,
      "loss": 0.3886,
      "step": 64048
    },
    {
      "epoch": 1.9675298743587382,
      "grad_norm": 0.39934006333351135,
      "learning_rate": 1.3068916387901642e-08,
      "loss": 0.5378,
      "step": 64049
    },
    {
      "epoch": 1.9675605934936873,
      "grad_norm": 0.5687716007232666,
      "learning_rate": 1.3044228487106848e-08,
      "loss": 0.4968,
      "step": 64050
    },
    {
      "epoch": 1.9675913126286364,
      "grad_norm": 0.45489951968193054,
      "learning_rate": 1.3019563911546019e-08,
      "loss": 0.4048,
      "step": 64051
    },
    {
      "epoch": 1.9676220317635855,
      "grad_norm": 0.4080296456813812,
      "learning_rate": 1.2994922661274668e-08,
      "loss": 0.4441,
      "step": 64052
    },
    {
      "epoch": 1.9676527508985346,
      "grad_norm": 0.4154917597770691,
      "learning_rate": 1.2970304736350526e-08,
      "loss": 0.4657,
      "step": 64053
    },
    {
      "epoch": 1.9676834700334838,
      "grad_norm": 0.6123027205467224,
      "learning_rate": 1.2945710136832434e-08,
      "loss": 0.4511,
      "step": 64054
    },
    {
      "epoch": 1.9677141891684329,
      "grad_norm": 0.42157936096191406,
      "learning_rate": 1.2921138862778126e-08,
      "loss": 0.5007,
      "step": 64055
    },
    {
      "epoch": 1.9677449083033822,
      "grad_norm": 0.6078037619590759,
      "learning_rate": 1.2896590914243112e-08,
      "loss": 0.5176,
      "step": 64056
    },
    {
      "epoch": 1.9677756274383313,
      "grad_norm": 0.4781382083892822,
      "learning_rate": 1.2872066291285124e-08,
      "loss": 0.4945,
      "step": 64057
    },
    {
      "epoch": 1.9678063465732805,
      "grad_norm": 0.42970120906829834,
      "learning_rate": 1.2847564993961891e-08,
      "loss": 0.417,
      "step": 64058
    },
    {
      "epoch": 1.9678370657082298,
      "grad_norm": 0.41977402567863464,
      "learning_rate": 1.2823087022332258e-08,
      "loss": 0.4035,
      "step": 64059
    },
    {
      "epoch": 1.967867784843179,
      "grad_norm": 0.4738520085811615,
      "learning_rate": 1.2798632376450626e-08,
      "loss": 0.529,
      "step": 64060
    },
    {
      "epoch": 1.967898503978128,
      "grad_norm": 0.42847874760627747,
      "learning_rate": 1.2774201056374725e-08,
      "loss": 0.5191,
      "step": 64061
    },
    {
      "epoch": 1.9679292231130772,
      "grad_norm": 0.4025283455848694,
      "learning_rate": 1.2749793062163396e-08,
      "loss": 0.5233,
      "step": 64062
    },
    {
      "epoch": 1.9679599422480263,
      "grad_norm": 0.43685734272003174,
      "learning_rate": 1.2725408393871041e-08,
      "loss": 0.4867,
      "step": 64063
    },
    {
      "epoch": 1.9679906613829754,
      "grad_norm": 0.42234763503074646,
      "learning_rate": 1.2701047051557614e-08,
      "loss": 0.4737,
      "step": 64064
    },
    {
      "epoch": 1.9680213805179245,
      "grad_norm": 0.39514297246932983,
      "learning_rate": 1.2676709035277513e-08,
      "loss": 0.4456,
      "step": 64065
    },
    {
      "epoch": 1.9680520996528736,
      "grad_norm": 0.48827335238456726,
      "learning_rate": 1.265239434508847e-08,
      "loss": 0.4083,
      "step": 64066
    },
    {
      "epoch": 1.968082818787823,
      "grad_norm": 0.41291120648384094,
      "learning_rate": 1.2628102981047107e-08,
      "loss": 0.4559,
      "step": 64067
    },
    {
      "epoch": 1.968113537922772,
      "grad_norm": 0.44924765825271606,
      "learning_rate": 1.2603834943210048e-08,
      "loss": 0.485,
      "step": 64068
    },
    {
      "epoch": 1.9681442570577212,
      "grad_norm": 0.40208640694618225,
      "learning_rate": 1.2579590231635019e-08,
      "loss": 0.4675,
      "step": 64069
    },
    {
      "epoch": 1.9681749761926706,
      "grad_norm": 0.43708905577659607,
      "learning_rate": 1.2555368846377536e-08,
      "loss": 0.3677,
      "step": 64070
    },
    {
      "epoch": 1.9682056953276197,
      "grad_norm": 0.3994176983833313,
      "learning_rate": 1.2531170787494218e-08,
      "loss": 0.3853,
      "step": 64071
    },
    {
      "epoch": 1.9682364144625688,
      "grad_norm": 0.47872209548950195,
      "learning_rate": 1.2506996055042798e-08,
      "loss": 0.4377,
      "step": 64072
    },
    {
      "epoch": 1.968267133597518,
      "grad_norm": 0.413470596075058,
      "learning_rate": 1.2482844649077675e-08,
      "loss": 0.5689,
      "step": 64073
    },
    {
      "epoch": 1.968297852732467,
      "grad_norm": 0.46047350764274597,
      "learning_rate": 1.2458716569657692e-08,
      "loss": 0.4636,
      "step": 64074
    },
    {
      "epoch": 1.9683285718674162,
      "grad_norm": 0.42238274216651917,
      "learning_rate": 1.243461181683614e-08,
      "loss": 0.4685,
      "step": 64075
    },
    {
      "epoch": 1.9683592910023653,
      "grad_norm": 0.4136205017566681,
      "learning_rate": 1.241053039067297e-08,
      "loss": 0.464,
      "step": 64076
    },
    {
      "epoch": 1.9683900101373144,
      "grad_norm": 0.4669874608516693,
      "learning_rate": 1.2386472291221474e-08,
      "loss": 0.4331,
      "step": 64077
    },
    {
      "epoch": 1.9684207292722637,
      "grad_norm": 0.4788665771484375,
      "learning_rate": 1.2362437518538273e-08,
      "loss": 0.5023,
      "step": 64078
    },
    {
      "epoch": 1.9684514484072129,
      "grad_norm": 0.568556547164917,
      "learning_rate": 1.2338426072681098e-08,
      "loss": 0.4817,
      "step": 64079
    },
    {
      "epoch": 1.968482167542162,
      "grad_norm": 0.4463057816028595,
      "learning_rate": 1.231443795370546e-08,
      "loss": 0.4361,
      "step": 64080
    },
    {
      "epoch": 1.9685128866771113,
      "grad_norm": 0.4343711733818054,
      "learning_rate": 1.2290473161665762e-08,
      "loss": 0.4705,
      "step": 64081
    },
    {
      "epoch": 1.9685436058120604,
      "grad_norm": 0.40008968114852905,
      "learning_rate": 1.2266531696619733e-08,
      "loss": 0.5606,
      "step": 64082
    },
    {
      "epoch": 1.9685743249470096,
      "grad_norm": 0.4120849668979645,
      "learning_rate": 1.2242613558622884e-08,
      "loss": 0.4585,
      "step": 64083
    },
    {
      "epoch": 1.9686050440819587,
      "grad_norm": 0.4577065706253052,
      "learning_rate": 1.221871874773184e-08,
      "loss": 0.4646,
      "step": 64084
    },
    {
      "epoch": 1.9686357632169078,
      "grad_norm": 0.3786971867084503,
      "learning_rate": 1.2194847263999887e-08,
      "loss": 0.4191,
      "step": 64085
    },
    {
      "epoch": 1.968666482351857,
      "grad_norm": 0.4418470561504364,
      "learning_rate": 1.217099910748476e-08,
      "loss": 0.5588,
      "step": 64086
    },
    {
      "epoch": 1.968697201486806,
      "grad_norm": 0.466754674911499,
      "learning_rate": 1.2147174278243079e-08,
      "loss": 0.4442,
      "step": 64087
    },
    {
      "epoch": 1.9687279206217552,
      "grad_norm": 0.4418758451938629,
      "learning_rate": 1.2123372776328136e-08,
      "loss": 0.4742,
      "step": 64088
    },
    {
      "epoch": 1.9687586397567043,
      "grad_norm": 0.5349023342132568,
      "learning_rate": 1.209959460179655e-08,
      "loss": 0.4863,
      "step": 64089
    },
    {
      "epoch": 1.9687893588916536,
      "grad_norm": 0.41456371545791626,
      "learning_rate": 1.2075839754703833e-08,
      "loss": 0.452,
      "step": 64090
    },
    {
      "epoch": 1.9688200780266027,
      "grad_norm": 0.4438442587852478,
      "learning_rate": 1.2052108235105498e-08,
      "loss": 0.5121,
      "step": 64091
    },
    {
      "epoch": 1.968850797161552,
      "grad_norm": 0.4249945282936096,
      "learning_rate": 1.2028400043058164e-08,
      "loss": 0.5215,
      "step": 64092
    },
    {
      "epoch": 1.9688815162965012,
      "grad_norm": 0.448223739862442,
      "learning_rate": 1.2004715178615122e-08,
      "loss": 0.4441,
      "step": 64093
    },
    {
      "epoch": 1.9689122354314503,
      "grad_norm": 0.4700774550437927,
      "learning_rate": 1.1981053641831886e-08,
      "loss": 0.4509,
      "step": 64094
    },
    {
      "epoch": 1.9689429545663995,
      "grad_norm": 0.42816439270973206,
      "learning_rate": 1.1957415432766183e-08,
      "loss": 0.3769,
      "step": 64095
    },
    {
      "epoch": 1.9689736737013486,
      "grad_norm": 0.4200269877910614,
      "learning_rate": 1.1933800551470199e-08,
      "loss": 0.4954,
      "step": 64096
    },
    {
      "epoch": 1.9690043928362977,
      "grad_norm": 0.44829005002975464,
      "learning_rate": 1.191020899800055e-08,
      "loss": 0.5208,
      "step": 64097
    },
    {
      "epoch": 1.9690351119712468,
      "grad_norm": 0.3916718363761902,
      "learning_rate": 1.188664077241275e-08,
      "loss": 0.4194,
      "step": 64098
    },
    {
      "epoch": 1.969065831106196,
      "grad_norm": 0.4375607371330261,
      "learning_rate": 1.1863095874761198e-08,
      "loss": 0.474,
      "step": 64099
    },
    {
      "epoch": 1.969096550241145,
      "grad_norm": 0.4448425769805908,
      "learning_rate": 1.1839574305100298e-08,
      "loss": 0.4882,
      "step": 64100
    },
    {
      "epoch": 1.9691272693760944,
      "grad_norm": 0.4091202914714813,
      "learning_rate": 1.181607606348667e-08,
      "loss": 0.5351,
      "step": 64101
    },
    {
      "epoch": 1.9691579885110435,
      "grad_norm": 0.4768337309360504,
      "learning_rate": 1.1792601149972494e-08,
      "loss": 0.5026,
      "step": 64102
    },
    {
      "epoch": 1.9691887076459929,
      "grad_norm": 0.7115588784217834,
      "learning_rate": 1.17691495646155e-08,
      "loss": 0.5549,
      "step": 64103
    },
    {
      "epoch": 1.969219426780942,
      "grad_norm": 0.41481703519821167,
      "learning_rate": 1.1745721307468983e-08,
      "loss": 0.3951,
      "step": 64104
    },
    {
      "epoch": 1.969250145915891,
      "grad_norm": 0.43573087453842163,
      "learning_rate": 1.172231637858845e-08,
      "loss": 0.5377,
      "step": 64105
    },
    {
      "epoch": 1.9692808650508402,
      "grad_norm": 0.46092289686203003,
      "learning_rate": 1.1698934778027193e-08,
      "loss": 0.4893,
      "step": 64106
    },
    {
      "epoch": 1.9693115841857893,
      "grad_norm": 0.45569950342178345,
      "learning_rate": 1.1675576505840724e-08,
      "loss": 0.4739,
      "step": 64107
    },
    {
      "epoch": 1.9693423033207385,
      "grad_norm": 0.42756226658821106,
      "learning_rate": 1.1652241562083444e-08,
      "loss": 0.4875,
      "step": 64108
    },
    {
      "epoch": 1.9693730224556876,
      "grad_norm": 0.43689894676208496,
      "learning_rate": 1.1628929946810862e-08,
      "loss": 0.4117,
      "step": 64109
    },
    {
      "epoch": 1.9694037415906367,
      "grad_norm": 0.4044809639453888,
      "learning_rate": 1.1605641660076271e-08,
      "loss": 0.4319,
      "step": 64110
    },
    {
      "epoch": 1.9694344607255858,
      "grad_norm": 0.47055596113204956,
      "learning_rate": 1.1582376701932962e-08,
      "loss": 0.5178,
      "step": 64111
    },
    {
      "epoch": 1.9694651798605352,
      "grad_norm": 0.5017378330230713,
      "learning_rate": 1.1559135072437556e-08,
      "loss": 0.4386,
      "step": 64112
    },
    {
      "epoch": 1.9694958989954843,
      "grad_norm": 0.43419143557548523,
      "learning_rate": 1.153591677164334e-08,
      "loss": 0.456,
      "step": 64113
    },
    {
      "epoch": 1.9695266181304334,
      "grad_norm": 0.43304258584976196,
      "learning_rate": 1.1512721799604721e-08,
      "loss": 0.4463,
      "step": 64114
    },
    {
      "epoch": 1.9695573372653827,
      "grad_norm": 0.4775315821170807,
      "learning_rate": 1.1489550156376095e-08,
      "loss": 0.4698,
      "step": 64115
    },
    {
      "epoch": 1.9695880564003319,
      "grad_norm": 0.5069944262504578,
      "learning_rate": 1.1466401842010755e-08,
      "loss": 0.4537,
      "step": 64116
    },
    {
      "epoch": 1.969618775535281,
      "grad_norm": 0.5030385255813599,
      "learning_rate": 1.14432768565631e-08,
      "loss": 0.4337,
      "step": 64117
    },
    {
      "epoch": 1.96964949467023,
      "grad_norm": 0.4399448037147522,
      "learning_rate": 1.1420175200087536e-08,
      "loss": 0.4112,
      "step": 64118
    },
    {
      "epoch": 1.9696802138051792,
      "grad_norm": 0.41371390223503113,
      "learning_rate": 1.1397096872637347e-08,
      "loss": 0.5384,
      "step": 64119
    },
    {
      "epoch": 1.9697109329401283,
      "grad_norm": 0.5284770727157593,
      "learning_rate": 1.1374041874266939e-08,
      "loss": 0.5537,
      "step": 64120
    },
    {
      "epoch": 1.9697416520750775,
      "grad_norm": 0.5189703106880188,
      "learning_rate": 1.13510102050296e-08,
      "loss": 0.4518,
      "step": 64121
    },
    {
      "epoch": 1.9697723712100266,
      "grad_norm": 0.4437158405780792,
      "learning_rate": 1.1328001864979732e-08,
      "loss": 0.3815,
      "step": 64122
    },
    {
      "epoch": 1.969803090344976,
      "grad_norm": 0.42329472303390503,
      "learning_rate": 1.1305016854171735e-08,
      "loss": 0.4562,
      "step": 64123
    },
    {
      "epoch": 1.969833809479925,
      "grad_norm": 0.4342885911464691,
      "learning_rate": 1.128205517265779e-08,
      "loss": 0.4773,
      "step": 64124
    },
    {
      "epoch": 1.9698645286148742,
      "grad_norm": 0.43629539012908936,
      "learning_rate": 1.125911682049341e-08,
      "loss": 0.4626,
      "step": 64125
    },
    {
      "epoch": 1.9698952477498235,
      "grad_norm": 0.4373706877231598,
      "learning_rate": 1.1236201797729662e-08,
      "loss": 0.4849,
      "step": 64126
    },
    {
      "epoch": 1.9699259668847726,
      "grad_norm": 0.4236891567707062,
      "learning_rate": 1.121331010442206e-08,
      "loss": 0.444,
      "step": 64127
    },
    {
      "epoch": 1.9699566860197217,
      "grad_norm": 0.42867326736450195,
      "learning_rate": 1.1190441740622782e-08,
      "loss": 0.4506,
      "step": 64128
    },
    {
      "epoch": 1.9699874051546709,
      "grad_norm": 0.4357006549835205,
      "learning_rate": 1.116759670638623e-08,
      "loss": 0.5264,
      "step": 64129
    },
    {
      "epoch": 1.97001812428962,
      "grad_norm": 0.4457663893699646,
      "learning_rate": 1.1144775001764586e-08,
      "loss": 0.4726,
      "step": 64130
    },
    {
      "epoch": 1.970048843424569,
      "grad_norm": 0.4173395037651062,
      "learning_rate": 1.1121976626813358e-08,
      "loss": 0.5213,
      "step": 64131
    },
    {
      "epoch": 1.9700795625595182,
      "grad_norm": 0.4331914484500885,
      "learning_rate": 1.1099201581583618e-08,
      "loss": 0.508,
      "step": 64132
    },
    {
      "epoch": 1.9701102816944673,
      "grad_norm": 0.5161997079849243,
      "learning_rate": 1.1076449866128658e-08,
      "loss": 0.5543,
      "step": 64133
    },
    {
      "epoch": 1.9701410008294167,
      "grad_norm": 0.4453306794166565,
      "learning_rate": 1.1053721480502876e-08,
      "loss": 0.5041,
      "step": 64134
    },
    {
      "epoch": 1.9701717199643658,
      "grad_norm": 0.4228529930114746,
      "learning_rate": 1.1031016424758455e-08,
      "loss": 0.4698,
      "step": 64135
    },
    {
      "epoch": 1.970202439099315,
      "grad_norm": 0.4240434467792511,
      "learning_rate": 1.1008334698949796e-08,
      "loss": 0.4753,
      "step": 64136
    },
    {
      "epoch": 1.9702331582342643,
      "grad_norm": 0.48160552978515625,
      "learning_rate": 1.0985676303127968e-08,
      "loss": 0.4493,
      "step": 64137
    },
    {
      "epoch": 1.9702638773692134,
      "grad_norm": 0.473448246717453,
      "learning_rate": 1.0963041237346262e-08,
      "loss": 0.4369,
      "step": 64138
    },
    {
      "epoch": 1.9702945965041625,
      "grad_norm": 0.42678913474082947,
      "learning_rate": 1.0940429501659078e-08,
      "loss": 0.4302,
      "step": 64139
    },
    {
      "epoch": 1.9703253156391116,
      "grad_norm": 0.5232987403869629,
      "learning_rate": 1.0917841096117487e-08,
      "loss": 0.5099,
      "step": 64140
    },
    {
      "epoch": 1.9703560347740607,
      "grad_norm": 0.4245862662792206,
      "learning_rate": 1.0895276020774781e-08,
      "loss": 0.437,
      "step": 64141
    },
    {
      "epoch": 1.9703867539090099,
      "grad_norm": 0.37435251474380493,
      "learning_rate": 1.0872734275684249e-08,
      "loss": 0.3899,
      "step": 64142
    },
    {
      "epoch": 1.970417473043959,
      "grad_norm": 0.4190843403339386,
      "learning_rate": 1.0850215860898073e-08,
      "loss": 0.4407,
      "step": 64143
    },
    {
      "epoch": 1.970448192178908,
      "grad_norm": 0.49519622325897217,
      "learning_rate": 1.0827720776468432e-08,
      "loss": 0.4609,
      "step": 64144
    },
    {
      "epoch": 1.9704789113138574,
      "grad_norm": 0.4506950080394745,
      "learning_rate": 1.0805249022448616e-08,
      "loss": 0.5082,
      "step": 64145
    },
    {
      "epoch": 1.9705096304488066,
      "grad_norm": 0.41707494854927063,
      "learning_rate": 1.0782800598890808e-08,
      "loss": 0.4525,
      "step": 64146
    },
    {
      "epoch": 1.9705403495837557,
      "grad_norm": 0.42619752883911133,
      "learning_rate": 1.0760375505847187e-08,
      "loss": 0.4763,
      "step": 64147
    },
    {
      "epoch": 1.970571068718705,
      "grad_norm": 0.4381561875343323,
      "learning_rate": 1.0737973743369933e-08,
      "loss": 0.496,
      "step": 64148
    },
    {
      "epoch": 1.9706017878536541,
      "grad_norm": 0.4435541033744812,
      "learning_rate": 1.0715595311512339e-08,
      "loss": 0.4517,
      "step": 64149
    },
    {
      "epoch": 1.9706325069886033,
      "grad_norm": 0.4314555823802948,
      "learning_rate": 1.0693240210326583e-08,
      "loss": 0.459,
      "step": 64150
    },
    {
      "epoch": 1.9706632261235524,
      "grad_norm": 0.4662491977214813,
      "learning_rate": 1.0670908439863737e-08,
      "loss": 0.4454,
      "step": 64151
    },
    {
      "epoch": 1.9706939452585015,
      "grad_norm": 0.48153141140937805,
      "learning_rate": 1.064860000017598e-08,
      "loss": 0.5009,
      "step": 64152
    },
    {
      "epoch": 1.9707246643934506,
      "grad_norm": 0.4339934289455414,
      "learning_rate": 1.0626314891317714e-08,
      "loss": 0.4922,
      "step": 64153
    },
    {
      "epoch": 1.9707553835283997,
      "grad_norm": 0.4618793725967407,
      "learning_rate": 1.0604053113337787e-08,
      "loss": 0.3809,
      "step": 64154
    },
    {
      "epoch": 1.9707861026633489,
      "grad_norm": 0.48994770646095276,
      "learning_rate": 1.0581814666290602e-08,
      "loss": 0.5248,
      "step": 64155
    },
    {
      "epoch": 1.9708168217982982,
      "grad_norm": 0.4706820547580719,
      "learning_rate": 1.0559599550227229e-08,
      "loss": 0.4842,
      "step": 64156
    },
    {
      "epoch": 1.9708475409332473,
      "grad_norm": 0.5025540590286255,
      "learning_rate": 1.0537407765198738e-08,
      "loss": 0.4354,
      "step": 64157
    },
    {
      "epoch": 1.9708782600681964,
      "grad_norm": 0.4377061128616333,
      "learning_rate": 1.0515239311259528e-08,
      "loss": 0.4453,
      "step": 64158
    },
    {
      "epoch": 1.9709089792031458,
      "grad_norm": 0.49513599276542664,
      "learning_rate": 1.0493094188458452e-08,
      "loss": 0.4315,
      "step": 64159
    },
    {
      "epoch": 1.970939698338095,
      "grad_norm": 0.47442030906677246,
      "learning_rate": 1.047097239684769e-08,
      "loss": 0.5535,
      "step": 64160
    },
    {
      "epoch": 1.970970417473044,
      "grad_norm": 0.47090014815330505,
      "learning_rate": 1.044887393648053e-08,
      "loss": 0.4167,
      "step": 64161
    },
    {
      "epoch": 1.9710011366079931,
      "grad_norm": 0.49493056535720825,
      "learning_rate": 1.0426798807408044e-08,
      "loss": 0.5468,
      "step": 64162
    },
    {
      "epoch": 1.9710318557429423,
      "grad_norm": 0.44025319814682007,
      "learning_rate": 1.0404747009681304e-08,
      "loss": 0.4495,
      "step": 64163
    },
    {
      "epoch": 1.9710625748778914,
      "grad_norm": 0.41025665402412415,
      "learning_rate": 1.0382718543351379e-08,
      "loss": 0.4323,
      "step": 64164
    },
    {
      "epoch": 1.9710932940128405,
      "grad_norm": 0.4480020999908447,
      "learning_rate": 1.0360713408470446e-08,
      "loss": 0.4312,
      "step": 64165
    },
    {
      "epoch": 1.9711240131477896,
      "grad_norm": 0.465361624956131,
      "learning_rate": 1.033873160508958e-08,
      "loss": 0.4528,
      "step": 64166
    },
    {
      "epoch": 1.971154732282739,
      "grad_norm": 0.4135439693927765,
      "learning_rate": 1.031677313326096e-08,
      "loss": 0.4528,
      "step": 64167
    },
    {
      "epoch": 1.971185451417688,
      "grad_norm": 0.40395063161849976,
      "learning_rate": 1.0294837993034546e-08,
      "loss": 0.4956,
      "step": 64168
    },
    {
      "epoch": 1.9712161705526372,
      "grad_norm": 0.45669102668762207,
      "learning_rate": 1.0272926184462517e-08,
      "loss": 0.4894,
      "step": 64169
    },
    {
      "epoch": 1.9712468896875865,
      "grad_norm": 0.41365179419517517,
      "learning_rate": 1.0251037707595946e-08,
      "loss": 0.531,
      "step": 64170
    },
    {
      "epoch": 1.9712776088225357,
      "grad_norm": 0.49563226103782654,
      "learning_rate": 1.022917256248479e-08,
      "loss": 0.4586,
      "step": 64171
    },
    {
      "epoch": 1.9713083279574848,
      "grad_norm": 0.40732887387275696,
      "learning_rate": 1.0207330749182342e-08,
      "loss": 0.4099,
      "step": 64172
    },
    {
      "epoch": 1.971339047092434,
      "grad_norm": 0.4476604759693146,
      "learning_rate": 1.0185512267737452e-08,
      "loss": 0.4186,
      "step": 64173
    },
    {
      "epoch": 1.971369766227383,
      "grad_norm": 0.44829854369163513,
      "learning_rate": 1.0163717118202298e-08,
      "loss": 0.469,
      "step": 64174
    },
    {
      "epoch": 1.9714004853623321,
      "grad_norm": 0.4461572468280792,
      "learning_rate": 1.0141945300627954e-08,
      "loss": 0.3869,
      "step": 64175
    },
    {
      "epoch": 1.9714312044972813,
      "grad_norm": 0.5006647706031799,
      "learning_rate": 1.0120196815063266e-08,
      "loss": 0.5456,
      "step": 64176
    },
    {
      "epoch": 1.9714619236322304,
      "grad_norm": 0.40052884817123413,
      "learning_rate": 1.0098471661561526e-08,
      "loss": 0.337,
      "step": 64177
    },
    {
      "epoch": 1.9714926427671797,
      "grad_norm": 0.4876311719417572,
      "learning_rate": 1.0076769840172696e-08,
      "loss": 0.4667,
      "step": 64178
    },
    {
      "epoch": 1.9715233619021288,
      "grad_norm": 0.43407192826271057,
      "learning_rate": 1.0055091350947843e-08,
      "loss": 0.4806,
      "step": 64179
    },
    {
      "epoch": 1.971554081037078,
      "grad_norm": 0.4550647437572479,
      "learning_rate": 1.003343619393582e-08,
      "loss": 0.4642,
      "step": 64180
    },
    {
      "epoch": 1.9715848001720273,
      "grad_norm": 0.437100887298584,
      "learning_rate": 1.0011804369188804e-08,
      "loss": 0.5128,
      "step": 64181
    },
    {
      "epoch": 1.9716155193069764,
      "grad_norm": 0.4221992790699005,
      "learning_rate": 9.99019587675676e-09,
      "loss": 0.4385,
      "step": 64182
    },
    {
      "epoch": 1.9716462384419255,
      "grad_norm": 0.4397503733634949,
      "learning_rate": 9.968610716690753e-09,
      "loss": 0.4318,
      "step": 64183
    },
    {
      "epoch": 1.9716769575768747,
      "grad_norm": 0.3957011103630066,
      "learning_rate": 9.947048889040744e-09,
      "loss": 0.4564,
      "step": 64184
    },
    {
      "epoch": 1.9717076767118238,
      "grad_norm": 0.40438976883888245,
      "learning_rate": 9.925510393856697e-09,
      "loss": 0.4129,
      "step": 64185
    },
    {
      "epoch": 1.971738395846773,
      "grad_norm": 0.45842915773391724,
      "learning_rate": 9.903995231189678e-09,
      "loss": 0.4704,
      "step": 64186
    },
    {
      "epoch": 1.971769114981722,
      "grad_norm": 0.44349274039268494,
      "learning_rate": 9.882503401089649e-09,
      "loss": 0.4864,
      "step": 64187
    },
    {
      "epoch": 1.9717998341166711,
      "grad_norm": 0.4386654496192932,
      "learning_rate": 9.86103490360657e-09,
      "loss": 0.4404,
      "step": 64188
    },
    {
      "epoch": 1.9718305532516205,
      "grad_norm": 0.43096163868904114,
      "learning_rate": 9.8395897387904e-09,
      "loss": 0.4368,
      "step": 64189
    },
    {
      "epoch": 1.9718612723865696,
      "grad_norm": 0.44576069712638855,
      "learning_rate": 9.8181679066911e-09,
      "loss": 0.496,
      "step": 64190
    },
    {
      "epoch": 1.9718919915215187,
      "grad_norm": 0.45744505524635315,
      "learning_rate": 9.796769407359741e-09,
      "loss": 0.5228,
      "step": 64191
    },
    {
      "epoch": 1.971922710656468,
      "grad_norm": 0.4270811676979065,
      "learning_rate": 9.775394240846281e-09,
      "loss": 0.4374,
      "step": 64192
    },
    {
      "epoch": 1.9719534297914172,
      "grad_norm": 0.4524761438369751,
      "learning_rate": 9.754042407199571e-09,
      "loss": 0.4498,
      "step": 64193
    },
    {
      "epoch": 1.9719841489263663,
      "grad_norm": 0.4497097134590149,
      "learning_rate": 9.732713906470682e-09,
      "loss": 0.5277,
      "step": 64194
    },
    {
      "epoch": 1.9720148680613154,
      "grad_norm": 0.47937002778053284,
      "learning_rate": 9.71140873870735e-09,
      "loss": 0.5144,
      "step": 64195
    },
    {
      "epoch": 1.9720455871962645,
      "grad_norm": 0.4404011070728302,
      "learning_rate": 9.69012690396176e-09,
      "loss": 0.4533,
      "step": 64196
    },
    {
      "epoch": 1.9720763063312137,
      "grad_norm": 0.4341661036014557,
      "learning_rate": 9.66886840228276e-09,
      "loss": 0.5099,
      "step": 64197
    },
    {
      "epoch": 1.9721070254661628,
      "grad_norm": 0.46541914343833923,
      "learning_rate": 9.6476332337192e-09,
      "loss": 0.5112,
      "step": 64198
    },
    {
      "epoch": 1.972137744601112,
      "grad_norm": 0.43036890029907227,
      "learning_rate": 9.62642139832215e-09,
      "loss": 0.5603,
      "step": 64199
    },
    {
      "epoch": 1.972168463736061,
      "grad_norm": 0.43601343035697937,
      "learning_rate": 9.60523289613935e-09,
      "loss": 0.489,
      "step": 64200
    },
    {
      "epoch": 1.9721991828710104,
      "grad_norm": 0.42888715863227844,
      "learning_rate": 9.584067727221869e-09,
      "loss": 0.4953,
      "step": 64201
    },
    {
      "epoch": 1.9722299020059595,
      "grad_norm": 0.5162217617034912,
      "learning_rate": 9.562925891618558e-09,
      "loss": 0.4116,
      "step": 64202
    },
    {
      "epoch": 1.9722606211409088,
      "grad_norm": 0.468988299369812,
      "learning_rate": 9.541807389378267e-09,
      "loss": 0.3826,
      "step": 64203
    },
    {
      "epoch": 1.972291340275858,
      "grad_norm": 0.4230160713195801,
      "learning_rate": 9.520712220550954e-09,
      "loss": 0.4129,
      "step": 64204
    },
    {
      "epoch": 1.972322059410807,
      "grad_norm": 0.4597250819206238,
      "learning_rate": 9.499640385185472e-09,
      "loss": 0.4778,
      "step": 64205
    },
    {
      "epoch": 1.9723527785457562,
      "grad_norm": 0.4440094232559204,
      "learning_rate": 9.478591883331779e-09,
      "loss": 0.5532,
      "step": 64206
    },
    {
      "epoch": 1.9723834976807053,
      "grad_norm": 0.45375844836235046,
      "learning_rate": 9.457566715038724e-09,
      "loss": 0.5206,
      "step": 64207
    },
    {
      "epoch": 1.9724142168156544,
      "grad_norm": 0.4045434594154358,
      "learning_rate": 9.43656488035516e-09,
      "loss": 0.3464,
      "step": 64208
    },
    {
      "epoch": 1.9724449359506036,
      "grad_norm": 0.4298385679721832,
      "learning_rate": 9.415586379329933e-09,
      "loss": 0.402,
      "step": 64209
    },
    {
      "epoch": 1.9724756550855527,
      "grad_norm": 0.5641604065895081,
      "learning_rate": 9.394631212013006e-09,
      "loss": 0.4182,
      "step": 64210
    },
    {
      "epoch": 1.9725063742205018,
      "grad_norm": 0.3973221480846405,
      "learning_rate": 9.373699378451007e-09,
      "loss": 0.5187,
      "step": 64211
    },
    {
      "epoch": 1.9725370933554511,
      "grad_norm": 0.439951092004776,
      "learning_rate": 9.352790878696116e-09,
      "loss": 0.433,
      "step": 64212
    },
    {
      "epoch": 1.9725678124904003,
      "grad_norm": 0.37991249561309814,
      "learning_rate": 9.331905712794964e-09,
      "loss": 0.3951,
      "step": 64213
    },
    {
      "epoch": 1.9725985316253496,
      "grad_norm": 0.437254935503006,
      "learning_rate": 9.31104388079751e-09,
      "loss": 0.4366,
      "step": 64214
    },
    {
      "epoch": 1.9726292507602987,
      "grad_norm": 0.42223528027534485,
      "learning_rate": 9.290205382750384e-09,
      "loss": 0.4667,
      "step": 64215
    },
    {
      "epoch": 1.9726599698952478,
      "grad_norm": 0.45224684476852417,
      "learning_rate": 9.269390218704655e-09,
      "loss": 0.4565,
      "step": 64216
    },
    {
      "epoch": 1.972690689030197,
      "grad_norm": 0.4193747639656067,
      "learning_rate": 9.248598388708063e-09,
      "loss": 0.442,
      "step": 64217
    },
    {
      "epoch": 1.972721408165146,
      "grad_norm": 0.42862847447395325,
      "learning_rate": 9.227829892809458e-09,
      "loss": 0.4755,
      "step": 64218
    },
    {
      "epoch": 1.9727521273000952,
      "grad_norm": 0.4468393325805664,
      "learning_rate": 9.207084731056582e-09,
      "loss": 0.5196,
      "step": 64219
    },
    {
      "epoch": 1.9727828464350443,
      "grad_norm": 0.3897727131843567,
      "learning_rate": 9.186362903498281e-09,
      "loss": 0.5208,
      "step": 64220
    },
    {
      "epoch": 1.9728135655699934,
      "grad_norm": 0.4483632743358612,
      "learning_rate": 9.165664410182295e-09,
      "loss": 0.5092,
      "step": 64221
    },
    {
      "epoch": 1.9728442847049426,
      "grad_norm": 0.46407410502433777,
      "learning_rate": 9.144989251158586e-09,
      "loss": 0.4685,
      "step": 64222
    },
    {
      "epoch": 1.972875003839892,
      "grad_norm": 0.426835298538208,
      "learning_rate": 9.124337426474894e-09,
      "loss": 0.5006,
      "step": 64223
    },
    {
      "epoch": 1.972905722974841,
      "grad_norm": 0.4762577712535858,
      "learning_rate": 9.103708936177846e-09,
      "loss": 0.4828,
      "step": 64224
    },
    {
      "epoch": 1.9729364421097901,
      "grad_norm": 0.41932982206344604,
      "learning_rate": 9.083103780317404e-09,
      "loss": 0.5173,
      "step": 64225
    },
    {
      "epoch": 1.9729671612447395,
      "grad_norm": 0.42094162106513977,
      "learning_rate": 9.062521958941307e-09,
      "loss": 0.4286,
      "step": 64226
    },
    {
      "epoch": 1.9729978803796886,
      "grad_norm": 0.4262399971485138,
      "learning_rate": 9.041963472097293e-09,
      "loss": 0.4239,
      "step": 64227
    },
    {
      "epoch": 1.9730285995146377,
      "grad_norm": 0.3961390554904938,
      "learning_rate": 9.021428319833104e-09,
      "loss": 0.4407,
      "step": 64228
    },
    {
      "epoch": 1.9730593186495868,
      "grad_norm": 0.4355078935623169,
      "learning_rate": 9.000916502197588e-09,
      "loss": 0.4627,
      "step": 64229
    },
    {
      "epoch": 1.973090037784536,
      "grad_norm": 0.44431161880493164,
      "learning_rate": 8.980428019238485e-09,
      "loss": 0.4711,
      "step": 64230
    },
    {
      "epoch": 1.973120756919485,
      "grad_norm": 0.38843637704849243,
      "learning_rate": 8.959962871003536e-09,
      "loss": 0.4052,
      "step": 64231
    },
    {
      "epoch": 1.9731514760544342,
      "grad_norm": 0.4535602629184723,
      "learning_rate": 8.939521057539369e-09,
      "loss": 0.4921,
      "step": 64232
    },
    {
      "epoch": 1.9731821951893833,
      "grad_norm": 0.40483948588371277,
      "learning_rate": 8.919102578894834e-09,
      "loss": 0.4523,
      "step": 64233
    },
    {
      "epoch": 1.9732129143243327,
      "grad_norm": 0.4416036903858185,
      "learning_rate": 8.89870743511767e-09,
      "loss": 0.4241,
      "step": 64234
    },
    {
      "epoch": 1.9732436334592818,
      "grad_norm": 0.4632693827152252,
      "learning_rate": 8.878335626255619e-09,
      "loss": 0.4673,
      "step": 64235
    },
    {
      "epoch": 1.973274352594231,
      "grad_norm": 0.4655384123325348,
      "learning_rate": 8.857987152356418e-09,
      "loss": 0.5612,
      "step": 64236
    },
    {
      "epoch": 1.9733050717291802,
      "grad_norm": 0.4242593050003052,
      "learning_rate": 8.837662013466696e-09,
      "loss": 0.4575,
      "step": 64237
    },
    {
      "epoch": 1.9733357908641294,
      "grad_norm": 0.47997719049453735,
      "learning_rate": 8.817360209634195e-09,
      "loss": 0.4709,
      "step": 64238
    },
    {
      "epoch": 1.9733665099990785,
      "grad_norm": 0.5056095719337463,
      "learning_rate": 8.797081740906654e-09,
      "loss": 0.4662,
      "step": 64239
    },
    {
      "epoch": 1.9733972291340276,
      "grad_norm": 0.45569664239883423,
      "learning_rate": 8.776826607331812e-09,
      "loss": 0.4715,
      "step": 64240
    },
    {
      "epoch": 1.9734279482689767,
      "grad_norm": 0.41623616218566895,
      "learning_rate": 8.756594808956298e-09,
      "loss": 0.4717,
      "step": 64241
    },
    {
      "epoch": 1.9734586674039258,
      "grad_norm": 0.4806402325630188,
      "learning_rate": 8.736386345826741e-09,
      "loss": 0.439,
      "step": 64242
    },
    {
      "epoch": 1.973489386538875,
      "grad_norm": 0.41065192222595215,
      "learning_rate": 8.716201217991994e-09,
      "loss": 0.5,
      "step": 64243
    },
    {
      "epoch": 1.973520105673824,
      "grad_norm": 0.425846129655838,
      "learning_rate": 8.696039425497571e-09,
      "loss": 0.4621,
      "step": 64244
    },
    {
      "epoch": 1.9735508248087734,
      "grad_norm": 0.45582374930381775,
      "learning_rate": 8.675900968392326e-09,
      "loss": 0.4826,
      "step": 64245
    },
    {
      "epoch": 1.9735815439437225,
      "grad_norm": 0.43766525387763977,
      "learning_rate": 8.655785846721776e-09,
      "loss": 0.4994,
      "step": 64246
    },
    {
      "epoch": 1.9736122630786717,
      "grad_norm": 0.4407854378223419,
      "learning_rate": 8.635694060532552e-09,
      "loss": 0.4292,
      "step": 64247
    },
    {
      "epoch": 1.973642982213621,
      "grad_norm": 0.43339261412620544,
      "learning_rate": 8.615625609873501e-09,
      "loss": 0.5382,
      "step": 64248
    },
    {
      "epoch": 1.9736737013485701,
      "grad_norm": 0.44880932569503784,
      "learning_rate": 8.595580494790145e-09,
      "loss": 0.483,
      "step": 64249
    },
    {
      "epoch": 1.9737044204835192,
      "grad_norm": 0.5125582814216614,
      "learning_rate": 8.575558715330223e-09,
      "loss": 0.4852,
      "step": 64250
    },
    {
      "epoch": 1.9737351396184684,
      "grad_norm": 0.44058990478515625,
      "learning_rate": 8.555560271539254e-09,
      "loss": 0.4921,
      "step": 64251
    },
    {
      "epoch": 1.9737658587534175,
      "grad_norm": 0.43060779571533203,
      "learning_rate": 8.535585163463867e-09,
      "loss": 0.5524,
      "step": 64252
    },
    {
      "epoch": 1.9737965778883666,
      "grad_norm": 0.5755209922790527,
      "learning_rate": 8.51563339115291e-09,
      "loss": 0.4809,
      "step": 64253
    },
    {
      "epoch": 1.9738272970233157,
      "grad_norm": 0.4414459466934204,
      "learning_rate": 8.495704954650796e-09,
      "loss": 0.4748,
      "step": 64254
    },
    {
      "epoch": 1.9738580161582648,
      "grad_norm": 0.5055845975875854,
      "learning_rate": 8.475799854004152e-09,
      "loss": 0.5116,
      "step": 64255
    },
    {
      "epoch": 1.9738887352932142,
      "grad_norm": 0.4264132082462311,
      "learning_rate": 8.455918089260718e-09,
      "loss": 0.4918,
      "step": 64256
    },
    {
      "epoch": 1.9739194544281633,
      "grad_norm": 0.42700904607772827,
      "learning_rate": 8.436059660466012e-09,
      "loss": 0.4463,
      "step": 64257
    },
    {
      "epoch": 1.9739501735631124,
      "grad_norm": 0.40784212946891785,
      "learning_rate": 8.416224567667774e-09,
      "loss": 0.4637,
      "step": 64258
    },
    {
      "epoch": 1.9739808926980618,
      "grad_norm": 0.45836111903190613,
      "learning_rate": 8.396412810910415e-09,
      "loss": 0.4918,
      "step": 64259
    },
    {
      "epoch": 1.9740116118330109,
      "grad_norm": 0.57005774974823,
      "learning_rate": 8.376624390240561e-09,
      "loss": 0.4531,
      "step": 64260
    },
    {
      "epoch": 1.97404233096796,
      "grad_norm": 0.4412396252155304,
      "learning_rate": 8.356859305704844e-09,
      "loss": 0.4507,
      "step": 64261
    },
    {
      "epoch": 1.9740730501029091,
      "grad_norm": 0.4697151482105255,
      "learning_rate": 8.337117557351004e-09,
      "loss": 0.4524,
      "step": 64262
    },
    {
      "epoch": 1.9741037692378582,
      "grad_norm": 0.4367466866970062,
      "learning_rate": 8.317399145222337e-09,
      "loss": 0.479,
      "step": 64263
    },
    {
      "epoch": 1.9741344883728074,
      "grad_norm": 0.45713871717453003,
      "learning_rate": 8.297704069366586e-09,
      "loss": 0.4253,
      "step": 64264
    },
    {
      "epoch": 1.9741652075077565,
      "grad_norm": 0.40254074335098267,
      "learning_rate": 8.278032329829266e-09,
      "loss": 0.4516,
      "step": 64265
    },
    {
      "epoch": 1.9741959266427056,
      "grad_norm": 1.1448031663894653,
      "learning_rate": 8.2583839266559e-09,
      "loss": 0.4775,
      "step": 64266
    },
    {
      "epoch": 1.974226645777655,
      "grad_norm": 0.4157271385192871,
      "learning_rate": 8.238758859894225e-09,
      "loss": 0.429,
      "step": 64267
    },
    {
      "epoch": 1.974257364912604,
      "grad_norm": 0.4057524800300598,
      "learning_rate": 8.21915712958754e-09,
      "loss": 0.4901,
      "step": 64268
    },
    {
      "epoch": 1.9742880840475532,
      "grad_norm": 0.44328776001930237,
      "learning_rate": 8.199578735783587e-09,
      "loss": 0.467,
      "step": 64269
    },
    {
      "epoch": 1.9743188031825025,
      "grad_norm": 0.517628014087677,
      "learning_rate": 8.180023678526772e-09,
      "loss": 0.4968,
      "step": 64270
    },
    {
      "epoch": 1.9743495223174516,
      "grad_norm": 0.4487103223800659,
      "learning_rate": 8.160491957863725e-09,
      "loss": 0.5009,
      "step": 64271
    },
    {
      "epoch": 1.9743802414524008,
      "grad_norm": 0.43816378712654114,
      "learning_rate": 8.140983573838856e-09,
      "loss": 0.5076,
      "step": 64272
    },
    {
      "epoch": 1.9744109605873499,
      "grad_norm": 0.4673735499382019,
      "learning_rate": 8.121498526499904e-09,
      "loss": 0.5361,
      "step": 64273
    },
    {
      "epoch": 1.974441679722299,
      "grad_norm": 0.3908868730068207,
      "learning_rate": 8.102036815890168e-09,
      "loss": 0.4452,
      "step": 64274
    },
    {
      "epoch": 1.9744723988572481,
      "grad_norm": 0.4250836968421936,
      "learning_rate": 8.082598442055167e-09,
      "loss": 0.5093,
      "step": 64275
    },
    {
      "epoch": 1.9745031179921972,
      "grad_norm": 0.4798310697078705,
      "learning_rate": 8.06318340504264e-09,
      "loss": 0.5157,
      "step": 64276
    },
    {
      "epoch": 1.9745338371271464,
      "grad_norm": 0.4322298467159271,
      "learning_rate": 8.043791704895887e-09,
      "loss": 0.4818,
      "step": 64277
    },
    {
      "epoch": 1.9745645562620957,
      "grad_norm": 0.44975700974464417,
      "learning_rate": 8.024423341660426e-09,
      "loss": 0.4992,
      "step": 64278
    },
    {
      "epoch": 1.9745952753970448,
      "grad_norm": 0.4039650559425354,
      "learning_rate": 8.005078315381776e-09,
      "loss": 0.4741,
      "step": 64279
    },
    {
      "epoch": 1.974625994531994,
      "grad_norm": 0.5109805464744568,
      "learning_rate": 7.985756626105456e-09,
      "loss": 0.5564,
      "step": 64280
    },
    {
      "epoch": 1.9746567136669433,
      "grad_norm": 0.4477870464324951,
      "learning_rate": 7.966458273875877e-09,
      "loss": 0.5321,
      "step": 64281
    },
    {
      "epoch": 1.9746874328018924,
      "grad_norm": 0.43511638045310974,
      "learning_rate": 7.947183258738556e-09,
      "loss": 0.4484,
      "step": 64282
    },
    {
      "epoch": 1.9747181519368415,
      "grad_norm": 0.5123229026794434,
      "learning_rate": 7.927931580737901e-09,
      "loss": 0.462,
      "step": 64283
    },
    {
      "epoch": 1.9747488710717906,
      "grad_norm": 0.39884698390960693,
      "learning_rate": 7.908703239919435e-09,
      "loss": 0.3359,
      "step": 64284
    },
    {
      "epoch": 1.9747795902067398,
      "grad_norm": 0.4286808371543884,
      "learning_rate": 7.889498236328674e-09,
      "loss": 0.4141,
      "step": 64285
    },
    {
      "epoch": 1.9748103093416889,
      "grad_norm": 0.4263845980167389,
      "learning_rate": 7.870316570010028e-09,
      "loss": 0.4971,
      "step": 64286
    },
    {
      "epoch": 1.974841028476638,
      "grad_norm": 0.4647000730037689,
      "learning_rate": 7.851158241007905e-09,
      "loss": 0.4411,
      "step": 64287
    },
    {
      "epoch": 1.9748717476115871,
      "grad_norm": 0.5020447373390198,
      "learning_rate": 7.832023249366716e-09,
      "loss": 0.4232,
      "step": 64288
    },
    {
      "epoch": 1.9749024667465365,
      "grad_norm": 0.42024534940719604,
      "learning_rate": 7.812911595131978e-09,
      "loss": 0.4394,
      "step": 64289
    },
    {
      "epoch": 1.9749331858814856,
      "grad_norm": 0.47759678959846497,
      "learning_rate": 7.793823278348101e-09,
      "loss": 0.4349,
      "step": 64290
    },
    {
      "epoch": 1.9749639050164347,
      "grad_norm": 0.44783520698547363,
      "learning_rate": 7.774758299059493e-09,
      "loss": 0.4789,
      "step": 64291
    },
    {
      "epoch": 1.974994624151384,
      "grad_norm": 0.4312154948711395,
      "learning_rate": 7.755716657311674e-09,
      "loss": 0.4652,
      "step": 64292
    },
    {
      "epoch": 1.9750253432863332,
      "grad_norm": 0.4035830497741699,
      "learning_rate": 7.736698353146832e-09,
      "loss": 0.3965,
      "step": 64293
    },
    {
      "epoch": 1.9750560624212823,
      "grad_norm": 0.403643399477005,
      "learning_rate": 7.717703386611597e-09,
      "loss": 0.4883,
      "step": 64294
    },
    {
      "epoch": 1.9750867815562314,
      "grad_norm": 0.4177197515964508,
      "learning_rate": 7.698731757749268e-09,
      "loss": 0.4641,
      "step": 64295
    },
    {
      "epoch": 1.9751175006911805,
      "grad_norm": 0.47123831510543823,
      "learning_rate": 7.67978346660425e-09,
      "loss": 0.428,
      "step": 64296
    },
    {
      "epoch": 1.9751482198261296,
      "grad_norm": 0.4285638928413391,
      "learning_rate": 7.66085851322096e-09,
      "loss": 0.4731,
      "step": 64297
    },
    {
      "epoch": 1.9751789389610788,
      "grad_norm": 0.44239482283592224,
      "learning_rate": 7.641956897644909e-09,
      "loss": 0.4284,
      "step": 64298
    },
    {
      "epoch": 1.9752096580960279,
      "grad_norm": 0.39253246784210205,
      "learning_rate": 7.623078619917179e-09,
      "loss": 0.4592,
      "step": 64299
    },
    {
      "epoch": 1.9752403772309772,
      "grad_norm": 0.5076199769973755,
      "learning_rate": 7.6042236800844e-09,
      "loss": 0.4328,
      "step": 64300
    },
    {
      "epoch": 1.9752710963659263,
      "grad_norm": 0.4089135527610779,
      "learning_rate": 7.585392078189868e-09,
      "loss": 0.5013,
      "step": 64301
    },
    {
      "epoch": 1.9753018155008755,
      "grad_norm": 0.40943869948387146,
      "learning_rate": 7.566583814276885e-09,
      "loss": 0.48,
      "step": 64302
    },
    {
      "epoch": 1.9753325346358248,
      "grad_norm": 0.4046764671802521,
      "learning_rate": 7.547798888390966e-09,
      "loss": 0.4387,
      "step": 64303
    },
    {
      "epoch": 1.975363253770774,
      "grad_norm": 0.45667675137519836,
      "learning_rate": 7.529037300574304e-09,
      "loss": 0.4865,
      "step": 64304
    },
    {
      "epoch": 1.975393972905723,
      "grad_norm": 0.5075536370277405,
      "learning_rate": 7.510299050871305e-09,
      "loss": 0.5061,
      "step": 64305
    },
    {
      "epoch": 1.9754246920406722,
      "grad_norm": 0.4119783937931061,
      "learning_rate": 7.49158413932638e-09,
      "loss": 0.4036,
      "step": 64306
    },
    {
      "epoch": 1.9754554111756213,
      "grad_norm": 0.4166574776172638,
      "learning_rate": 7.472892565982825e-09,
      "loss": 0.4728,
      "step": 64307
    },
    {
      "epoch": 1.9754861303105704,
      "grad_norm": 0.42018893361091614,
      "learning_rate": 7.454224330883942e-09,
      "loss": 0.4471,
      "step": 64308
    },
    {
      "epoch": 1.9755168494455195,
      "grad_norm": 0.4332261085510254,
      "learning_rate": 7.4355794340730256e-09,
      "loss": 0.4922,
      "step": 64309
    },
    {
      "epoch": 1.9755475685804686,
      "grad_norm": 0.4273492693901062,
      "learning_rate": 7.416957875594488e-09,
      "loss": 0.4877,
      "step": 64310
    },
    {
      "epoch": 1.9755782877154178,
      "grad_norm": 0.42089149355888367,
      "learning_rate": 7.398359655491627e-09,
      "loss": 0.4045,
      "step": 64311
    },
    {
      "epoch": 1.975609006850367,
      "grad_norm": 0.42487525939941406,
      "learning_rate": 7.379784773807741e-09,
      "loss": 0.4908,
      "step": 64312
    },
    {
      "epoch": 1.9756397259853162,
      "grad_norm": 0.4228839874267578,
      "learning_rate": 7.3612332305872394e-09,
      "loss": 0.4625,
      "step": 64313
    },
    {
      "epoch": 1.9756704451202656,
      "grad_norm": 0.45157185196876526,
      "learning_rate": 7.3427050258712e-09,
      "loss": 0.4407,
      "step": 64314
    },
    {
      "epoch": 1.9757011642552147,
      "grad_norm": 0.4886133372783661,
      "learning_rate": 7.3242001597051414e-09,
      "loss": 0.407,
      "step": 64315
    },
    {
      "epoch": 1.9757318833901638,
      "grad_norm": 0.4622441232204437,
      "learning_rate": 7.305718632130143e-09,
      "loss": 0.5561,
      "step": 64316
    },
    {
      "epoch": 1.975762602525113,
      "grad_norm": 0.45800384879112244,
      "learning_rate": 7.287260443191723e-09,
      "loss": 0.49,
      "step": 64317
    },
    {
      "epoch": 1.975793321660062,
      "grad_norm": 0.4433270990848541,
      "learning_rate": 7.268825592930961e-09,
      "loss": 0.4547,
      "step": 64318
    },
    {
      "epoch": 1.9758240407950112,
      "grad_norm": 0.4777207374572754,
      "learning_rate": 7.250414081392265e-09,
      "loss": 0.5607,
      "step": 64319
    },
    {
      "epoch": 1.9758547599299603,
      "grad_norm": 0.3984091877937317,
      "learning_rate": 7.232025908616713e-09,
      "loss": 0.5028,
      "step": 64320
    },
    {
      "epoch": 1.9758854790649094,
      "grad_norm": 0.43729832768440247,
      "learning_rate": 7.213661074649825e-09,
      "loss": 0.5133,
      "step": 64321
    },
    {
      "epoch": 1.9759161981998585,
      "grad_norm": 0.41142216324806213,
      "learning_rate": 7.195319579533788e-09,
      "loss": 0.4526,
      "step": 64322
    },
    {
      "epoch": 1.9759469173348079,
      "grad_norm": 0.4274103045463562,
      "learning_rate": 7.177001423310792e-09,
      "loss": 0.4457,
      "step": 64323
    },
    {
      "epoch": 1.975977636469757,
      "grad_norm": 0.4256759285926819,
      "learning_rate": 7.158706606023025e-09,
      "loss": 0.4445,
      "step": 64324
    },
    {
      "epoch": 1.9760083556047063,
      "grad_norm": 0.5440645217895508,
      "learning_rate": 7.140435127713785e-09,
      "loss": 0.4686,
      "step": 64325
    },
    {
      "epoch": 1.9760390747396555,
      "grad_norm": 0.4413321316242218,
      "learning_rate": 7.122186988427482e-09,
      "loss": 0.4769,
      "step": 64326
    },
    {
      "epoch": 1.9760697938746046,
      "grad_norm": 0.44202086329460144,
      "learning_rate": 7.103962188204083e-09,
      "loss": 0.4507,
      "step": 64327
    },
    {
      "epoch": 1.9761005130095537,
      "grad_norm": 0.41585978865623474,
      "learning_rate": 7.085760727086888e-09,
      "loss": 0.5082,
      "step": 64328
    },
    {
      "epoch": 1.9761312321445028,
      "grad_norm": 0.3986425995826721,
      "learning_rate": 7.067582605119194e-09,
      "loss": 0.4371,
      "step": 64329
    },
    {
      "epoch": 1.976161951279452,
      "grad_norm": 0.45097315311431885,
      "learning_rate": 7.049427822344301e-09,
      "loss": 0.4673,
      "step": 64330
    },
    {
      "epoch": 1.976192670414401,
      "grad_norm": 0.43733301758766174,
      "learning_rate": 7.031296378802177e-09,
      "loss": 0.4464,
      "step": 64331
    },
    {
      "epoch": 1.9762233895493502,
      "grad_norm": 0.4945642948150635,
      "learning_rate": 7.01318827453612e-09,
      "loss": 0.4519,
      "step": 64332
    },
    {
      "epoch": 1.9762541086842993,
      "grad_norm": 0.43295472860336304,
      "learning_rate": 6.995103509589429e-09,
      "loss": 0.5141,
      "step": 64333
    },
    {
      "epoch": 1.9762848278192486,
      "grad_norm": 0.41195574402809143,
      "learning_rate": 6.977042084003183e-09,
      "loss": 0.4916,
      "step": 64334
    },
    {
      "epoch": 1.9763155469541978,
      "grad_norm": 0.4528273642063141,
      "learning_rate": 6.9590039978195685e-09,
      "loss": 0.4509,
      "step": 64335
    },
    {
      "epoch": 1.9763462660891469,
      "grad_norm": 0.45789676904678345,
      "learning_rate": 6.940989251081887e-09,
      "loss": 0.5107,
      "step": 64336
    },
    {
      "epoch": 1.9763769852240962,
      "grad_norm": 0.5018540620803833,
      "learning_rate": 6.922997843831214e-09,
      "loss": 0.4337,
      "step": 64337
    },
    {
      "epoch": 1.9764077043590453,
      "grad_norm": 0.43444758653640747,
      "learning_rate": 6.905029776108629e-09,
      "loss": 0.5004,
      "step": 64338
    },
    {
      "epoch": 1.9764384234939945,
      "grad_norm": 0.510448694229126,
      "learning_rate": 6.887085047958542e-09,
      "loss": 0.4283,
      "step": 64339
    },
    {
      "epoch": 1.9764691426289436,
      "grad_norm": 0.45225539803504944,
      "learning_rate": 6.869163659422029e-09,
      "loss": 0.4613,
      "step": 64340
    },
    {
      "epoch": 1.9764998617638927,
      "grad_norm": 0.5108298659324646,
      "learning_rate": 6.851265610539059e-09,
      "loss": 0.4927,
      "step": 64341
    },
    {
      "epoch": 1.9765305808988418,
      "grad_norm": 0.4086398184299469,
      "learning_rate": 6.833390901354042e-09,
      "loss": 0.4345,
      "step": 64342
    },
    {
      "epoch": 1.976561300033791,
      "grad_norm": 0.45388659834861755,
      "learning_rate": 6.815539531906945e-09,
      "loss": 0.559,
      "step": 64343
    },
    {
      "epoch": 1.97659201916874,
      "grad_norm": 0.42133358120918274,
      "learning_rate": 6.797711502239957e-09,
      "loss": 0.421,
      "step": 64344
    },
    {
      "epoch": 1.9766227383036894,
      "grad_norm": 0.42354005575180054,
      "learning_rate": 6.779906812395265e-09,
      "loss": 0.4715,
      "step": 64345
    },
    {
      "epoch": 1.9766534574386385,
      "grad_norm": 0.40815469622612,
      "learning_rate": 6.7621254624139485e-09,
      "loss": 0.534,
      "step": 64346
    },
    {
      "epoch": 1.9766841765735876,
      "grad_norm": 0.4179503619670868,
      "learning_rate": 6.744367452337086e-09,
      "loss": 0.4824,
      "step": 64347
    },
    {
      "epoch": 1.976714895708537,
      "grad_norm": 0.4306696057319641,
      "learning_rate": 6.726632782206865e-09,
      "loss": 0.4872,
      "step": 64348
    },
    {
      "epoch": 1.976745614843486,
      "grad_norm": 0.4855234622955322,
      "learning_rate": 6.7089214520654754e-09,
      "loss": 0.4825,
      "step": 64349
    },
    {
      "epoch": 1.9767763339784352,
      "grad_norm": 0.42197829484939575,
      "learning_rate": 6.691233461951774e-09,
      "loss": 0.5156,
      "step": 64350
    },
    {
      "epoch": 1.9768070531133843,
      "grad_norm": 0.43459758162498474,
      "learning_rate": 6.67356881191017e-09,
      "loss": 0.4895,
      "step": 64351
    },
    {
      "epoch": 1.9768377722483335,
      "grad_norm": 0.4411980211734772,
      "learning_rate": 6.65592750197952e-09,
      "loss": 0.4618,
      "step": 64352
    },
    {
      "epoch": 1.9768684913832826,
      "grad_norm": 0.44145748019218445,
      "learning_rate": 6.6383095322020145e-09,
      "loss": 0.4875,
      "step": 64353
    },
    {
      "epoch": 1.9768992105182317,
      "grad_norm": 0.4654540419578552,
      "learning_rate": 6.62071490261873e-09,
      "loss": 0.4622,
      "step": 64354
    },
    {
      "epoch": 1.9769299296531808,
      "grad_norm": 0.4130304455757141,
      "learning_rate": 6.603143613270746e-09,
      "loss": 0.4299,
      "step": 64355
    },
    {
      "epoch": 1.9769606487881302,
      "grad_norm": 0.44455835223197937,
      "learning_rate": 6.58559566419803e-09,
      "loss": 0.4552,
      "step": 64356
    },
    {
      "epoch": 1.9769913679230793,
      "grad_norm": 0.4182208776473999,
      "learning_rate": 6.568071055443881e-09,
      "loss": 0.4153,
      "step": 64357
    },
    {
      "epoch": 1.9770220870580284,
      "grad_norm": 0.4198947548866272,
      "learning_rate": 6.550569787047156e-09,
      "loss": 0.4983,
      "step": 64358
    },
    {
      "epoch": 1.9770528061929777,
      "grad_norm": 0.44768938422203064,
      "learning_rate": 6.533091859050045e-09,
      "loss": 0.4727,
      "step": 64359
    },
    {
      "epoch": 1.9770835253279269,
      "grad_norm": 0.46167540550231934,
      "learning_rate": 6.515637271492514e-09,
      "loss": 0.3734,
      "step": 64360
    },
    {
      "epoch": 1.977114244462876,
      "grad_norm": 0.472420871257782,
      "learning_rate": 6.498206024415643e-09,
      "loss": 0.4767,
      "step": 64361
    },
    {
      "epoch": 1.977144963597825,
      "grad_norm": 0.42332372069358826,
      "learning_rate": 6.48079811786051e-09,
      "loss": 0.4321,
      "step": 64362
    },
    {
      "epoch": 1.9771756827327742,
      "grad_norm": 0.46324431896209717,
      "learning_rate": 6.4634135518670815e-09,
      "loss": 0.458,
      "step": 64363
    },
    {
      "epoch": 1.9772064018677233,
      "grad_norm": 0.40876850485801697,
      "learning_rate": 6.446052326476437e-09,
      "loss": 0.4942,
      "step": 64364
    },
    {
      "epoch": 1.9772371210026725,
      "grad_norm": 0.4227091073989868,
      "learning_rate": 6.4287144417296555e-09,
      "loss": 0.3946,
      "step": 64365
    },
    {
      "epoch": 1.9772678401376216,
      "grad_norm": 0.4785287082195282,
      "learning_rate": 6.411399897665593e-09,
      "loss": 0.4341,
      "step": 64366
    },
    {
      "epoch": 1.977298559272571,
      "grad_norm": 0.4312756657600403,
      "learning_rate": 6.394108694325329e-09,
      "loss": 0.5094,
      "step": 64367
    },
    {
      "epoch": 1.97732927840752,
      "grad_norm": 0.4053516387939453,
      "learning_rate": 6.376840831751052e-09,
      "loss": 0.4837,
      "step": 64368
    },
    {
      "epoch": 1.9773599975424692,
      "grad_norm": 0.4319620430469513,
      "learning_rate": 6.359596309980509e-09,
      "loss": 0.4733,
      "step": 64369
    },
    {
      "epoch": 1.9773907166774185,
      "grad_norm": 0.4720432162284851,
      "learning_rate": 6.342375129054779e-09,
      "loss": 0.4885,
      "step": 64370
    },
    {
      "epoch": 1.9774214358123676,
      "grad_norm": 0.45775869488716125,
      "learning_rate": 6.325177289014939e-09,
      "loss": 0.4391,
      "step": 64371
    },
    {
      "epoch": 1.9774521549473167,
      "grad_norm": 0.4338919222354889,
      "learning_rate": 6.308002789900958e-09,
      "loss": 0.4574,
      "step": 64372
    },
    {
      "epoch": 1.9774828740822659,
      "grad_norm": 0.3787696361541748,
      "learning_rate": 6.290851631751693e-09,
      "loss": 0.48,
      "step": 64373
    },
    {
      "epoch": 1.977513593217215,
      "grad_norm": 0.48003989458084106,
      "learning_rate": 6.273723814609334e-09,
      "loss": 0.496,
      "step": 64374
    },
    {
      "epoch": 1.977544312352164,
      "grad_norm": 0.4571049213409424,
      "learning_rate": 6.256619338511627e-09,
      "loss": 0.5222,
      "step": 64375
    },
    {
      "epoch": 1.9775750314871132,
      "grad_norm": 0.44063135981559753,
      "learning_rate": 6.239538203499651e-09,
      "loss": 0.448,
      "step": 64376
    },
    {
      "epoch": 1.9776057506220623,
      "grad_norm": 0.40087705850601196,
      "learning_rate": 6.222480409613374e-09,
      "loss": 0.4469,
      "step": 64377
    },
    {
      "epoch": 1.9776364697570117,
      "grad_norm": 0.522182285785675,
      "learning_rate": 6.2054459568927636e-09,
      "loss": 0.4874,
      "step": 64378
    },
    {
      "epoch": 1.9776671888919608,
      "grad_norm": 0.4968663454055786,
      "learning_rate": 6.1884348453766785e-09,
      "loss": 0.5161,
      "step": 64379
    },
    {
      "epoch": 1.97769790802691,
      "grad_norm": 0.43497946858406067,
      "learning_rate": 6.171447075105086e-09,
      "loss": 0.4504,
      "step": 64380
    },
    {
      "epoch": 1.9777286271618593,
      "grad_norm": 0.47794726490974426,
      "learning_rate": 6.154482646119065e-09,
      "loss": 0.421,
      "step": 64381
    },
    {
      "epoch": 1.9777593462968084,
      "grad_norm": 0.4740138053894043,
      "learning_rate": 6.137541558457471e-09,
      "loss": 0.5128,
      "step": 64382
    },
    {
      "epoch": 1.9777900654317575,
      "grad_norm": 0.4396633803844452,
      "learning_rate": 6.120623812158055e-09,
      "loss": 0.4855,
      "step": 64383
    },
    {
      "epoch": 1.9778207845667066,
      "grad_norm": 0.4811442792415619,
      "learning_rate": 6.103729407263004e-09,
      "loss": 0.4767,
      "step": 64384
    },
    {
      "epoch": 1.9778515037016557,
      "grad_norm": 0.4542815089225769,
      "learning_rate": 6.086858343811175e-09,
      "loss": 0.4388,
      "step": 64385
    },
    {
      "epoch": 1.9778822228366049,
      "grad_norm": 0.4211534261703491,
      "learning_rate": 6.070010621840317e-09,
      "loss": 0.4955,
      "step": 64386
    },
    {
      "epoch": 1.977912941971554,
      "grad_norm": 0.6858447790145874,
      "learning_rate": 6.053186241391507e-09,
      "loss": 0.4493,
      "step": 64387
    },
    {
      "epoch": 1.977943661106503,
      "grad_norm": 0.43446651101112366,
      "learning_rate": 6.0363852025024925e-09,
      "loss": 0.4302,
      "step": 64388
    },
    {
      "epoch": 1.9779743802414524,
      "grad_norm": 0.4146201014518738,
      "learning_rate": 6.019607505214353e-09,
      "loss": 0.453,
      "step": 64389
    },
    {
      "epoch": 1.9780050993764016,
      "grad_norm": 0.47714105248451233,
      "learning_rate": 6.002853149565946e-09,
      "loss": 0.4293,
      "step": 64390
    },
    {
      "epoch": 1.9780358185113507,
      "grad_norm": 0.38834017515182495,
      "learning_rate": 5.9861221355950184e-09,
      "loss": 0.4254,
      "step": 64391
    },
    {
      "epoch": 1.9780665376463,
      "grad_norm": 0.4672833979129791,
      "learning_rate": 5.969414463341538e-09,
      "loss": 0.4243,
      "step": 64392
    },
    {
      "epoch": 1.9780972567812491,
      "grad_norm": 0.45220547914505005,
      "learning_rate": 5.952730132844365e-09,
      "loss": 0.5101,
      "step": 64393
    },
    {
      "epoch": 1.9781279759161983,
      "grad_norm": 0.5027676224708557,
      "learning_rate": 5.9360691441434635e-09,
      "loss": 0.5628,
      "step": 64394
    },
    {
      "epoch": 1.9781586950511474,
      "grad_norm": 0.4273079037666321,
      "learning_rate": 5.919431497275474e-09,
      "loss": 0.5284,
      "step": 64395
    },
    {
      "epoch": 1.9781894141860965,
      "grad_norm": 0.482816606760025,
      "learning_rate": 5.902817192281474e-09,
      "loss": 0.4677,
      "step": 64396
    },
    {
      "epoch": 1.9782201333210456,
      "grad_norm": 0.4367399215698242,
      "learning_rate": 5.88622622919921e-09,
      "loss": 0.4965,
      "step": 64397
    },
    {
      "epoch": 1.9782508524559947,
      "grad_norm": 0.4370131194591522,
      "learning_rate": 5.8696586080675415e-09,
      "loss": 0.4649,
      "step": 64398
    },
    {
      "epoch": 1.9782815715909439,
      "grad_norm": 0.39495620131492615,
      "learning_rate": 5.853114328925324e-09,
      "loss": 0.4759,
      "step": 64399
    },
    {
      "epoch": 1.9783122907258932,
      "grad_norm": 0.4947923421859741,
      "learning_rate": 5.836593391811418e-09,
      "loss": 0.4737,
      "step": 64400
    },
    {
      "epoch": 1.9783430098608423,
      "grad_norm": 0.44301071763038635,
      "learning_rate": 5.82009579676468e-09,
      "loss": 0.5363,
      "step": 64401
    },
    {
      "epoch": 1.9783737289957914,
      "grad_norm": 0.4406692087650299,
      "learning_rate": 5.803621543821747e-09,
      "loss": 0.4777,
      "step": 64402
    },
    {
      "epoch": 1.9784044481307408,
      "grad_norm": 0.4291330575942993,
      "learning_rate": 5.787170633023698e-09,
      "loss": 0.5044,
      "step": 64403
    },
    {
      "epoch": 1.97843516726569,
      "grad_norm": 0.4627373218536377,
      "learning_rate": 5.770743064407169e-09,
      "loss": 0.5097,
      "step": 64404
    },
    {
      "epoch": 1.978465886400639,
      "grad_norm": 0.9525002241134644,
      "learning_rate": 5.75433883801102e-09,
      "loss": 0.4673,
      "step": 64405
    },
    {
      "epoch": 1.9784966055355881,
      "grad_norm": 0.4232434034347534,
      "learning_rate": 5.737957953872997e-09,
      "loss": 0.5576,
      "step": 64406
    },
    {
      "epoch": 1.9785273246705373,
      "grad_norm": 0.48671066761016846,
      "learning_rate": 5.721600412033068e-09,
      "loss": 0.4801,
      "step": 64407
    },
    {
      "epoch": 1.9785580438054864,
      "grad_norm": 0.4252392053604126,
      "learning_rate": 5.705266212527871e-09,
      "loss": 0.4506,
      "step": 64408
    },
    {
      "epoch": 1.9785887629404355,
      "grad_norm": 0.41429540514945984,
      "learning_rate": 5.6889553553951535e-09,
      "loss": 0.4319,
      "step": 64409
    },
    {
      "epoch": 1.9786194820753846,
      "grad_norm": 0.4338293969631195,
      "learning_rate": 5.672667840674883e-09,
      "loss": 0.5241,
      "step": 64410
    },
    {
      "epoch": 1.978650201210334,
      "grad_norm": 0.43288087844848633,
      "learning_rate": 5.656403668403698e-09,
      "loss": 0.485,
      "step": 64411
    },
    {
      "epoch": 1.978680920345283,
      "grad_norm": 0.41900190711021423,
      "learning_rate": 5.640162838620456e-09,
      "loss": 0.4998,
      "step": 64412
    },
    {
      "epoch": 1.9787116394802322,
      "grad_norm": 0.47742217779159546,
      "learning_rate": 5.623945351361793e-09,
      "loss": 0.5829,
      "step": 64413
    },
    {
      "epoch": 1.9787423586151816,
      "grad_norm": 0.4589673578739166,
      "learning_rate": 5.607751206667678e-09,
      "loss": 0.5528,
      "step": 64414
    },
    {
      "epoch": 1.9787730777501307,
      "grad_norm": 0.6176197528839111,
      "learning_rate": 5.591580404573638e-09,
      "loss": 0.4713,
      "step": 64415
    },
    {
      "epoch": 1.9788037968850798,
      "grad_norm": 0.47099044919013977,
      "learning_rate": 5.575432945118531e-09,
      "loss": 0.4489,
      "step": 64416
    },
    {
      "epoch": 1.978834516020029,
      "grad_norm": 0.43742698431015015,
      "learning_rate": 5.559308828340104e-09,
      "loss": 0.5504,
      "step": 64417
    },
    {
      "epoch": 1.978865235154978,
      "grad_norm": 0.4763628840446472,
      "learning_rate": 5.543208054276106e-09,
      "loss": 0.449,
      "step": 64418
    },
    {
      "epoch": 1.9788959542899272,
      "grad_norm": 0.5473443865776062,
      "learning_rate": 5.527130622964283e-09,
      "loss": 0.4613,
      "step": 64419
    },
    {
      "epoch": 1.9789266734248763,
      "grad_norm": 0.5288437008857727,
      "learning_rate": 5.511076534441273e-09,
      "loss": 0.4459,
      "step": 64420
    },
    {
      "epoch": 1.9789573925598254,
      "grad_norm": 0.43999597430229187,
      "learning_rate": 5.495045788744824e-09,
      "loss": 0.5064,
      "step": 64421
    },
    {
      "epoch": 1.9789881116947745,
      "grad_norm": 0.45129719376564026,
      "learning_rate": 5.479038385913793e-09,
      "loss": 0.5325,
      "step": 64422
    },
    {
      "epoch": 1.9790188308297239,
      "grad_norm": 0.49482277035713196,
      "learning_rate": 5.463054325983707e-09,
      "loss": 0.4198,
      "step": 64423
    },
    {
      "epoch": 1.979049549964673,
      "grad_norm": 0.45731011033058167,
      "learning_rate": 5.447093608992315e-09,
      "loss": 0.5066,
      "step": 64424
    },
    {
      "epoch": 1.9790802690996223,
      "grad_norm": 0.4209251403808594,
      "learning_rate": 5.431156234978474e-09,
      "loss": 0.438,
      "step": 64425
    },
    {
      "epoch": 1.9791109882345714,
      "grad_norm": 0.43174487352371216,
      "learning_rate": 5.415242203977711e-09,
      "loss": 0.5101,
      "step": 64426
    },
    {
      "epoch": 1.9791417073695206,
      "grad_norm": 0.5310150980949402,
      "learning_rate": 5.399351516026663e-09,
      "loss": 0.4213,
      "step": 64427
    },
    {
      "epoch": 1.9791724265044697,
      "grad_norm": 0.45158958435058594,
      "learning_rate": 5.383484171164188e-09,
      "loss": 0.4584,
      "step": 64428
    },
    {
      "epoch": 1.9792031456394188,
      "grad_norm": 0.45331814885139465,
      "learning_rate": 5.367640169426924e-09,
      "loss": 0.4566,
      "step": 64429
    },
    {
      "epoch": 1.979233864774368,
      "grad_norm": 0.4161359369754791,
      "learning_rate": 5.351819510851508e-09,
      "loss": 0.4586,
      "step": 64430
    },
    {
      "epoch": 1.979264583909317,
      "grad_norm": 0.5011500716209412,
      "learning_rate": 5.336022195474577e-09,
      "loss": 0.4451,
      "step": 64431
    },
    {
      "epoch": 1.9792953030442662,
      "grad_norm": 0.39737793803215027,
      "learning_rate": 5.3202482233338795e-09,
      "loss": 0.4847,
      "step": 64432
    },
    {
      "epoch": 1.9793260221792153,
      "grad_norm": 0.47744712233543396,
      "learning_rate": 5.304497594464941e-09,
      "loss": 0.5163,
      "step": 64433
    },
    {
      "epoch": 1.9793567413141646,
      "grad_norm": 0.43189749121665955,
      "learning_rate": 5.288770308905511e-09,
      "loss": 0.4519,
      "step": 64434
    },
    {
      "epoch": 1.9793874604491137,
      "grad_norm": 0.4228256940841675,
      "learning_rate": 5.273066366692225e-09,
      "loss": 0.444,
      "step": 64435
    },
    {
      "epoch": 1.979418179584063,
      "grad_norm": 0.45083606243133545,
      "learning_rate": 5.257385767862832e-09,
      "loss": 0.4352,
      "step": 64436
    },
    {
      "epoch": 1.9794488987190122,
      "grad_norm": 0.43536481261253357,
      "learning_rate": 5.241728512451749e-09,
      "loss": 0.5332,
      "step": 64437
    },
    {
      "epoch": 1.9794796178539613,
      "grad_norm": 0.4250032901763916,
      "learning_rate": 5.226094600496723e-09,
      "loss": 0.4714,
      "step": 64438
    },
    {
      "epoch": 1.9795103369889104,
      "grad_norm": 0.43598365783691406,
      "learning_rate": 5.210484032034391e-09,
      "loss": 0.4154,
      "step": 64439
    },
    {
      "epoch": 1.9795410561238596,
      "grad_norm": 0.4214612543582916,
      "learning_rate": 5.194896807100281e-09,
      "loss": 0.4545,
      "step": 64440
    },
    {
      "epoch": 1.9795717752588087,
      "grad_norm": 0.3865404427051544,
      "learning_rate": 5.179332925732139e-09,
      "loss": 0.3668,
      "step": 64441
    },
    {
      "epoch": 1.9796024943937578,
      "grad_norm": 0.46430259943008423,
      "learning_rate": 5.163792387966604e-09,
      "loss": 0.4697,
      "step": 64442
    },
    {
      "epoch": 1.979633213528707,
      "grad_norm": 0.41458579897880554,
      "learning_rate": 5.148275193838093e-09,
      "loss": 0.4746,
      "step": 64443
    },
    {
      "epoch": 1.979663932663656,
      "grad_norm": 0.43951380252838135,
      "learning_rate": 5.132781343383242e-09,
      "loss": 0.4397,
      "step": 64444
    },
    {
      "epoch": 1.9796946517986054,
      "grad_norm": 0.4563104510307312,
      "learning_rate": 5.117310836639799e-09,
      "loss": 0.4724,
      "step": 64445
    },
    {
      "epoch": 1.9797253709335545,
      "grad_norm": 0.4578135907649994,
      "learning_rate": 5.101863673642182e-09,
      "loss": 0.5316,
      "step": 64446
    },
    {
      "epoch": 1.9797560900685036,
      "grad_norm": 0.5365636944770813,
      "learning_rate": 5.086439854428138e-09,
      "loss": 0.4521,
      "step": 64447
    },
    {
      "epoch": 1.979786809203453,
      "grad_norm": 0.44812101125717163,
      "learning_rate": 5.071039379032084e-09,
      "loss": 0.4715,
      "step": 64448
    },
    {
      "epoch": 1.979817528338402,
      "grad_norm": 0.3895709812641144,
      "learning_rate": 5.0556622474906556e-09,
      "loss": 0.4937,
      "step": 64449
    },
    {
      "epoch": 1.9798482474733512,
      "grad_norm": 0.4116211533546448,
      "learning_rate": 5.040308459839383e-09,
      "loss": 0.4318,
      "step": 64450
    },
    {
      "epoch": 1.9798789666083003,
      "grad_norm": 0.6931493282318115,
      "learning_rate": 5.024978016114901e-09,
      "loss": 0.4301,
      "step": 64451
    },
    {
      "epoch": 1.9799096857432494,
      "grad_norm": 0.42173802852630615,
      "learning_rate": 5.009670916352738e-09,
      "loss": 0.4426,
      "step": 64452
    },
    {
      "epoch": 1.9799404048781986,
      "grad_norm": 0.4598727226257324,
      "learning_rate": 4.994387160589531e-09,
      "loss": 0.4854,
      "step": 64453
    },
    {
      "epoch": 1.9799711240131477,
      "grad_norm": 0.4343792498111725,
      "learning_rate": 4.979126748858587e-09,
      "loss": 0.428,
      "step": 64454
    },
    {
      "epoch": 1.9800018431480968,
      "grad_norm": 0.4170253574848175,
      "learning_rate": 4.963889681197653e-09,
      "loss": 0.4766,
      "step": 64455
    },
    {
      "epoch": 1.9800325622830461,
      "grad_norm": 0.44127771258354187,
      "learning_rate": 4.9486759576411465e-09,
      "loss": 0.4681,
      "step": 64456
    },
    {
      "epoch": 1.9800632814179953,
      "grad_norm": 0.41532590985298157,
      "learning_rate": 4.933485578224595e-09,
      "loss": 0.4795,
      "step": 64457
    },
    {
      "epoch": 1.9800940005529444,
      "grad_norm": 0.4507736563682556,
      "learning_rate": 4.9183185429846345e-09,
      "loss": 0.468,
      "step": 64458
    },
    {
      "epoch": 1.9801247196878937,
      "grad_norm": 0.4494851529598236,
      "learning_rate": 4.903174851955683e-09,
      "loss": 0.4628,
      "step": 64459
    },
    {
      "epoch": 1.9801554388228428,
      "grad_norm": 0.49756520986557007,
      "learning_rate": 4.8880545051743775e-09,
      "loss": 0.5215,
      "step": 64460
    },
    {
      "epoch": 1.980186157957792,
      "grad_norm": 0.4879417419433594,
      "learning_rate": 4.872957502674025e-09,
      "loss": 0.4424,
      "step": 64461
    },
    {
      "epoch": 1.980216877092741,
      "grad_norm": 0.41234737634658813,
      "learning_rate": 4.857883844491262e-09,
      "loss": 0.4439,
      "step": 64462
    },
    {
      "epoch": 1.9802475962276902,
      "grad_norm": 0.4110461175441742,
      "learning_rate": 4.842833530660507e-09,
      "loss": 0.5019,
      "step": 64463
    },
    {
      "epoch": 1.9802783153626393,
      "grad_norm": 0.4512642025947571,
      "learning_rate": 4.827806561218395e-09,
      "loss": 0.3862,
      "step": 64464
    },
    {
      "epoch": 1.9803090344975884,
      "grad_norm": 0.48948922753334045,
      "learning_rate": 4.812802936198236e-09,
      "loss": 0.456,
      "step": 64465
    },
    {
      "epoch": 1.9803397536325376,
      "grad_norm": 0.47345998883247375,
      "learning_rate": 4.797822655635553e-09,
      "loss": 0.5007,
      "step": 64466
    },
    {
      "epoch": 1.980370472767487,
      "grad_norm": 0.4515218734741211,
      "learning_rate": 4.782865719565877e-09,
      "loss": 0.4488,
      "step": 64467
    },
    {
      "epoch": 1.980401191902436,
      "grad_norm": 0.38869553804397583,
      "learning_rate": 4.767932128024733e-09,
      "loss": 0.434,
      "step": 64468
    },
    {
      "epoch": 1.9804319110373851,
      "grad_norm": 0.5390070080757141,
      "learning_rate": 4.7530218810454276e-09,
      "loss": 0.5149,
      "step": 64469
    },
    {
      "epoch": 1.9804626301723345,
      "grad_norm": 0.4389936029911041,
      "learning_rate": 4.738134978663489e-09,
      "loss": 0.4927,
      "step": 64470
    },
    {
      "epoch": 1.9804933493072836,
      "grad_norm": 0.4355742335319519,
      "learning_rate": 4.723271420913334e-09,
      "loss": 0.5094,
      "step": 64471
    },
    {
      "epoch": 1.9805240684422327,
      "grad_norm": 0.4633875787258148,
      "learning_rate": 4.708431207830489e-09,
      "loss": 0.4469,
      "step": 64472
    },
    {
      "epoch": 1.9805547875771818,
      "grad_norm": 0.3867713510990143,
      "learning_rate": 4.693614339449371e-09,
      "loss": 0.4764,
      "step": 64473
    },
    {
      "epoch": 1.980585506712131,
      "grad_norm": 0.467910498380661,
      "learning_rate": 4.6788208158032865e-09,
      "loss": 0.4458,
      "step": 64474
    },
    {
      "epoch": 1.98061622584708,
      "grad_norm": 0.4193092882633209,
      "learning_rate": 4.664050636928874e-09,
      "loss": 0.4909,
      "step": 64475
    },
    {
      "epoch": 1.9806469449820292,
      "grad_norm": 0.40206778049468994,
      "learning_rate": 4.649303802859439e-09,
      "loss": 0.5391,
      "step": 64476
    },
    {
      "epoch": 1.9806776641169783,
      "grad_norm": 0.45921605825424194,
      "learning_rate": 4.6345803136305105e-09,
      "loss": 0.4614,
      "step": 64477
    },
    {
      "epoch": 1.9807083832519277,
      "grad_norm": 0.4311683177947998,
      "learning_rate": 4.619880169274282e-09,
      "loss": 0.4836,
      "step": 64478
    },
    {
      "epoch": 1.9807391023868768,
      "grad_norm": 0.4384172856807709,
      "learning_rate": 4.6052033698262835e-09,
      "loss": 0.498,
      "step": 64479
    },
    {
      "epoch": 1.980769821521826,
      "grad_norm": 0.44632577896118164,
      "learning_rate": 4.59054991532204e-09,
      "loss": 0.4328,
      "step": 64480
    },
    {
      "epoch": 1.9808005406567752,
      "grad_norm": 0.4481865167617798,
      "learning_rate": 4.575919805793749e-09,
      "loss": 0.4925,
      "step": 64481
    },
    {
      "epoch": 1.9808312597917244,
      "grad_norm": 0.384048193693161,
      "learning_rate": 4.561313041276938e-09,
      "loss": 0.5167,
      "step": 64482
    },
    {
      "epoch": 1.9808619789266735,
      "grad_norm": 0.4402812123298645,
      "learning_rate": 4.546729621804913e-09,
      "loss": 0.4889,
      "step": 64483
    },
    {
      "epoch": 1.9808926980616226,
      "grad_norm": 0.4401950240135193,
      "learning_rate": 4.532169547412091e-09,
      "loss": 0.4818,
      "step": 64484
    },
    {
      "epoch": 1.9809234171965717,
      "grad_norm": 0.4567168653011322,
      "learning_rate": 4.517632818132889e-09,
      "loss": 0.5064,
      "step": 64485
    },
    {
      "epoch": 1.9809541363315208,
      "grad_norm": 0.41221338510513306,
      "learning_rate": 4.503119434000614e-09,
      "loss": 0.4595,
      "step": 64486
    },
    {
      "epoch": 1.98098485546647,
      "grad_norm": 0.4478192925453186,
      "learning_rate": 4.488629395049682e-09,
      "loss": 0.5055,
      "step": 64487
    },
    {
      "epoch": 1.981015574601419,
      "grad_norm": 0.4629520773887634,
      "learning_rate": 4.4741627013134005e-09,
      "loss": 0.477,
      "step": 64488
    },
    {
      "epoch": 1.9810462937363684,
      "grad_norm": 0.46678441762924194,
      "learning_rate": 4.459719352825076e-09,
      "loss": 0.4403,
      "step": 64489
    },
    {
      "epoch": 1.9810770128713175,
      "grad_norm": 0.45763689279556274,
      "learning_rate": 4.445299349620235e-09,
      "loss": 0.4963,
      "step": 64490
    },
    {
      "epoch": 1.9811077320062667,
      "grad_norm": 0.4173218607902527,
      "learning_rate": 4.430902691731076e-09,
      "loss": 0.4903,
      "step": 64491
    },
    {
      "epoch": 1.981138451141216,
      "grad_norm": 0.429302453994751,
      "learning_rate": 4.416529379190904e-09,
      "loss": 0.4313,
      "step": 64492
    },
    {
      "epoch": 1.9811691702761651,
      "grad_norm": 0.4304029643535614,
      "learning_rate": 4.402179412035246e-09,
      "loss": 0.5376,
      "step": 64493
    },
    {
      "epoch": 1.9811998894111142,
      "grad_norm": 0.4596978425979614,
      "learning_rate": 4.387852790295188e-09,
      "loss": 0.4886,
      "step": 64494
    },
    {
      "epoch": 1.9812306085460634,
      "grad_norm": 0.5872623920440674,
      "learning_rate": 4.373549514006259e-09,
      "loss": 0.4394,
      "step": 64495
    },
    {
      "epoch": 1.9812613276810125,
      "grad_norm": 0.41906416416168213,
      "learning_rate": 4.3592695832006535e-09,
      "loss": 0.4338,
      "step": 64496
    },
    {
      "epoch": 1.9812920468159616,
      "grad_norm": 0.49972003698349,
      "learning_rate": 4.3450129979127894e-09,
      "loss": 0.499,
      "step": 64497
    },
    {
      "epoch": 1.9813227659509107,
      "grad_norm": 0.5215897560119629,
      "learning_rate": 4.330779758173753e-09,
      "loss": 0.5061,
      "step": 64498
    },
    {
      "epoch": 1.9813534850858598,
      "grad_norm": 0.43669065833091736,
      "learning_rate": 4.316569864019071e-09,
      "loss": 0.431,
      "step": 64499
    },
    {
      "epoch": 1.9813842042208092,
      "grad_norm": 0.4521320164203644,
      "learning_rate": 4.30238331548094e-09,
      "loss": 0.5348,
      "step": 64500
    },
    {
      "epoch": 1.9814149233557583,
      "grad_norm": 0.4436940550804138,
      "learning_rate": 4.288220112593778e-09,
      "loss": 0.4856,
      "step": 64501
    },
    {
      "epoch": 1.9814456424907074,
      "grad_norm": 0.4667350649833679,
      "learning_rate": 4.274080255388669e-09,
      "loss": 0.5101,
      "step": 64502
    },
    {
      "epoch": 1.9814763616256568,
      "grad_norm": 0.4586679935455322,
      "learning_rate": 4.259963743898921e-09,
      "loss": 0.4427,
      "step": 64503
    },
    {
      "epoch": 1.9815070807606059,
      "grad_norm": 0.5544284582138062,
      "learning_rate": 4.245870578158951e-09,
      "loss": 0.4631,
      "step": 64504
    },
    {
      "epoch": 1.981537799895555,
      "grad_norm": 0.4569120705127716,
      "learning_rate": 4.2318007582009544e-09,
      "loss": 0.4725,
      "step": 64505
    },
    {
      "epoch": 1.9815685190305041,
      "grad_norm": 0.4420253038406372,
      "learning_rate": 4.21775428405713e-09,
      "loss": 0.4623,
      "step": 64506
    },
    {
      "epoch": 1.9815992381654532,
      "grad_norm": 0.44415056705474854,
      "learning_rate": 4.203731155760782e-09,
      "loss": 0.5226,
      "step": 64507
    },
    {
      "epoch": 1.9816299573004024,
      "grad_norm": 0.4521991014480591,
      "learning_rate": 4.189731373345218e-09,
      "loss": 0.434,
      "step": 64508
    },
    {
      "epoch": 1.9816606764353515,
      "grad_norm": 0.423462450504303,
      "learning_rate": 4.175754936842635e-09,
      "loss": 0.4379,
      "step": 64509
    },
    {
      "epoch": 1.9816913955703006,
      "grad_norm": 0.42105457186698914,
      "learning_rate": 4.1618018462852295e-09,
      "loss": 0.4977,
      "step": 64510
    },
    {
      "epoch": 1.98172211470525,
      "grad_norm": 0.44482308626174927,
      "learning_rate": 4.147872101706307e-09,
      "loss": 0.5115,
      "step": 64511
    },
    {
      "epoch": 1.981752833840199,
      "grad_norm": 0.46852388978004456,
      "learning_rate": 4.133965703138065e-09,
      "loss": 0.5069,
      "step": 64512
    },
    {
      "epoch": 1.9817835529751482,
      "grad_norm": 0.47610926628112793,
      "learning_rate": 4.12008265061381e-09,
      "loss": 0.5421,
      "step": 64513
    },
    {
      "epoch": 1.9818142721100975,
      "grad_norm": 0.4212222397327423,
      "learning_rate": 4.106222944164628e-09,
      "loss": 0.4941,
      "step": 64514
    },
    {
      "epoch": 1.9818449912450466,
      "grad_norm": 0.42468181252479553,
      "learning_rate": 4.092386583822716e-09,
      "loss": 0.5265,
      "step": 64515
    },
    {
      "epoch": 1.9818757103799958,
      "grad_norm": 0.5237323641777039,
      "learning_rate": 4.07857356962249e-09,
      "loss": 0.4897,
      "step": 64516
    },
    {
      "epoch": 1.981906429514945,
      "grad_norm": 0.5270674228668213,
      "learning_rate": 4.0647839015939275e-09,
      "loss": 0.4497,
      "step": 64517
    },
    {
      "epoch": 1.981937148649894,
      "grad_norm": 0.5937407612800598,
      "learning_rate": 4.051017579770334e-09,
      "loss": 0.498,
      "step": 64518
    },
    {
      "epoch": 1.9819678677848431,
      "grad_norm": 0.41481342911720276,
      "learning_rate": 4.037274604183905e-09,
      "loss": 0.4886,
      "step": 64519
    },
    {
      "epoch": 1.9819985869197922,
      "grad_norm": 0.45282700657844543,
      "learning_rate": 4.023554974865729e-09,
      "loss": 0.3397,
      "step": 64520
    },
    {
      "epoch": 1.9820293060547414,
      "grad_norm": 0.5596156120300293,
      "learning_rate": 4.009858691850222e-09,
      "loss": 0.4665,
      "step": 64521
    },
    {
      "epoch": 1.9820600251896907,
      "grad_norm": 0.4403232932090759,
      "learning_rate": 3.996185755166249e-09,
      "loss": 0.4598,
      "step": 64522
    },
    {
      "epoch": 1.9820907443246398,
      "grad_norm": 0.4383217990398407,
      "learning_rate": 3.982536164848227e-09,
      "loss": 0.4688,
      "step": 64523
    },
    {
      "epoch": 1.982121463459589,
      "grad_norm": 0.40007680654525757,
      "learning_rate": 3.968909920926134e-09,
      "loss": 0.4815,
      "step": 64524
    },
    {
      "epoch": 1.9821521825945383,
      "grad_norm": 0.46787428855895996,
      "learning_rate": 3.955307023434385e-09,
      "loss": 0.4365,
      "step": 64525
    },
    {
      "epoch": 1.9821829017294874,
      "grad_norm": 0.43029895424842834,
      "learning_rate": 3.941727472401846e-09,
      "loss": 0.4916,
      "step": 64526
    },
    {
      "epoch": 1.9822136208644365,
      "grad_norm": 0.47044891119003296,
      "learning_rate": 3.928171267861824e-09,
      "loss": 0.4803,
      "step": 64527
    },
    {
      "epoch": 1.9822443399993857,
      "grad_norm": 0.4261641502380371,
      "learning_rate": 3.914638409845406e-09,
      "loss": 0.4691,
      "step": 64528
    },
    {
      "epoch": 1.9822750591343348,
      "grad_norm": 0.4406523108482361,
      "learning_rate": 3.901128898384787e-09,
      "loss": 0.489,
      "step": 64529
    },
    {
      "epoch": 1.982305778269284,
      "grad_norm": 0.5269706845283508,
      "learning_rate": 3.8876427335110545e-09,
      "loss": 0.5153,
      "step": 64530
    },
    {
      "epoch": 1.982336497404233,
      "grad_norm": 0.43674495816230774,
      "learning_rate": 3.874179915256404e-09,
      "loss": 0.4704,
      "step": 64531
    },
    {
      "epoch": 1.9823672165391821,
      "grad_norm": 0.42837145924568176,
      "learning_rate": 3.860740443650812e-09,
      "loss": 0.5109,
      "step": 64532
    },
    {
      "epoch": 1.9823979356741313,
      "grad_norm": 0.4200921058654785,
      "learning_rate": 3.847324318727585e-09,
      "loss": 0.4686,
      "step": 64533
    },
    {
      "epoch": 1.9824286548090806,
      "grad_norm": 0.41095659136772156,
      "learning_rate": 3.8339315405167e-09,
      "loss": 0.5171,
      "step": 64534
    },
    {
      "epoch": 1.9824593739440297,
      "grad_norm": 0.44800564646720886,
      "learning_rate": 3.820562109049242e-09,
      "loss": 0.4472,
      "step": 64535
    },
    {
      "epoch": 1.982490093078979,
      "grad_norm": 0.4462990462779999,
      "learning_rate": 3.807216024357408e-09,
      "loss": 0.4762,
      "step": 64536
    },
    {
      "epoch": 1.9825208122139282,
      "grad_norm": 0.4426807761192322,
      "learning_rate": 3.793893286472283e-09,
      "loss": 0.5682,
      "step": 64537
    },
    {
      "epoch": 1.9825515313488773,
      "grad_norm": 0.43065187335014343,
      "learning_rate": 3.7805938954238454e-09,
      "loss": 0.4481,
      "step": 64538
    },
    {
      "epoch": 1.9825822504838264,
      "grad_norm": 0.4191090762615204,
      "learning_rate": 3.76731785124429e-09,
      "loss": 0.4451,
      "step": 64539
    },
    {
      "epoch": 1.9826129696187755,
      "grad_norm": 0.4500659704208374,
      "learning_rate": 3.754065153964703e-09,
      "loss": 0.4288,
      "step": 64540
    },
    {
      "epoch": 1.9826436887537247,
      "grad_norm": 0.4832961857318878,
      "learning_rate": 3.740835803615061e-09,
      "loss": 0.5437,
      "step": 64541
    },
    {
      "epoch": 1.9826744078886738,
      "grad_norm": 0.518765389919281,
      "learning_rate": 3.727629800227561e-09,
      "loss": 0.4504,
      "step": 64542
    },
    {
      "epoch": 1.982705127023623,
      "grad_norm": 0.4088220000267029,
      "learning_rate": 3.7144471438321783e-09,
      "loss": 0.4471,
      "step": 64543
    },
    {
      "epoch": 1.982735846158572,
      "grad_norm": 0.4211476445198059,
      "learning_rate": 3.7012878344588888e-09,
      "loss": 0.4834,
      "step": 64544
    },
    {
      "epoch": 1.9827665652935214,
      "grad_norm": 0.5397064089775085,
      "learning_rate": 3.688151872139889e-09,
      "loss": 0.4605,
      "step": 64545
    },
    {
      "epoch": 1.9827972844284705,
      "grad_norm": 0.4189635217189789,
      "learning_rate": 3.675039256905155e-09,
      "loss": 0.4561,
      "step": 64546
    },
    {
      "epoch": 1.9828280035634198,
      "grad_norm": 0.4458257555961609,
      "learning_rate": 3.6619499887857736e-09,
      "loss": 0.4257,
      "step": 64547
    },
    {
      "epoch": 1.982858722698369,
      "grad_norm": 0.6419925093650818,
      "learning_rate": 3.6488840678128303e-09,
      "loss": 0.514,
      "step": 64548
    },
    {
      "epoch": 1.982889441833318,
      "grad_norm": 0.4680091142654419,
      "learning_rate": 3.635841494015191e-09,
      "loss": 0.5139,
      "step": 64549
    },
    {
      "epoch": 1.9829201609682672,
      "grad_norm": 0.422403484582901,
      "learning_rate": 3.622822267423942e-09,
      "loss": 0.4816,
      "step": 64550
    },
    {
      "epoch": 1.9829508801032163,
      "grad_norm": 0.47333765029907227,
      "learning_rate": 3.6098263880701702e-09,
      "loss": 0.4876,
      "step": 64551
    },
    {
      "epoch": 1.9829815992381654,
      "grad_norm": 0.404889315366745,
      "learning_rate": 3.5968538559838506e-09,
      "loss": 0.3672,
      "step": 64552
    },
    {
      "epoch": 1.9830123183731145,
      "grad_norm": 0.41710299253463745,
      "learning_rate": 3.58390467119496e-09,
      "loss": 0.4675,
      "step": 64553
    },
    {
      "epoch": 1.9830430375080637,
      "grad_norm": 0.41062337160110474,
      "learning_rate": 3.570978833734584e-09,
      "loss": 0.4496,
      "step": 64554
    },
    {
      "epoch": 1.9830737566430128,
      "grad_norm": 0.46268314123153687,
      "learning_rate": 3.558076343631589e-09,
      "loss": 0.5258,
      "step": 64555
    },
    {
      "epoch": 1.9831044757779621,
      "grad_norm": 0.4412911832332611,
      "learning_rate": 3.545197200917061e-09,
      "loss": 0.4585,
      "step": 64556
    },
    {
      "epoch": 1.9831351949129112,
      "grad_norm": 0.4458533525466919,
      "learning_rate": 3.532341405620976e-09,
      "loss": 0.5,
      "step": 64557
    },
    {
      "epoch": 1.9831659140478606,
      "grad_norm": 0.44777822494506836,
      "learning_rate": 3.51950895777331e-09,
      "loss": 0.4531,
      "step": 64558
    },
    {
      "epoch": 1.9831966331828097,
      "grad_norm": 0.4462565779685974,
      "learning_rate": 3.506699857404039e-09,
      "loss": 0.4034,
      "step": 64559
    },
    {
      "epoch": 1.9832273523177588,
      "grad_norm": 0.4387391209602356,
      "learning_rate": 3.493914104542029e-09,
      "loss": 0.5013,
      "step": 64560
    },
    {
      "epoch": 1.983258071452708,
      "grad_norm": 0.40319541096687317,
      "learning_rate": 3.481151699219476e-09,
      "loss": 0.4068,
      "step": 64561
    },
    {
      "epoch": 1.983288790587657,
      "grad_norm": 0.4241948425769806,
      "learning_rate": 3.468412641464136e-09,
      "loss": 0.4664,
      "step": 64562
    },
    {
      "epoch": 1.9833195097226062,
      "grad_norm": 0.5391120910644531,
      "learning_rate": 3.4556969313070952e-09,
      "loss": 0.4867,
      "step": 64563
    },
    {
      "epoch": 1.9833502288575553,
      "grad_norm": 0.4575493633747101,
      "learning_rate": 3.4430045687761094e-09,
      "loss": 0.4886,
      "step": 64564
    },
    {
      "epoch": 1.9833809479925044,
      "grad_norm": 0.44057950377464294,
      "learning_rate": 3.4303355539033745e-09,
      "loss": 0.4943,
      "step": 64565
    },
    {
      "epoch": 1.9834116671274535,
      "grad_norm": 0.6474564075469971,
      "learning_rate": 3.4176898867166465e-09,
      "loss": 0.466,
      "step": 64566
    },
    {
      "epoch": 1.9834423862624029,
      "grad_norm": 0.38485634326934814,
      "learning_rate": 3.4050675672470112e-09,
      "loss": 0.4764,
      "step": 64567
    },
    {
      "epoch": 1.983473105397352,
      "grad_norm": 0.5581597685813904,
      "learning_rate": 3.3924685955222248e-09,
      "loss": 0.3709,
      "step": 64568
    },
    {
      "epoch": 1.9835038245323011,
      "grad_norm": 0.45739561319351196,
      "learning_rate": 3.379892971572263e-09,
      "loss": 0.5142,
      "step": 64569
    },
    {
      "epoch": 1.9835345436672505,
      "grad_norm": 0.44654110074043274,
      "learning_rate": 3.3673406954271014e-09,
      "loss": 0.4717,
      "step": 64570
    },
    {
      "epoch": 1.9835652628021996,
      "grad_norm": 0.505743682384491,
      "learning_rate": 3.3548117671156065e-09,
      "loss": 0.4006,
      "step": 64571
    },
    {
      "epoch": 1.9835959819371487,
      "grad_norm": 0.43430283665657043,
      "learning_rate": 3.342306186666644e-09,
      "loss": 0.4646,
      "step": 64572
    },
    {
      "epoch": 1.9836267010720978,
      "grad_norm": 0.44273465871810913,
      "learning_rate": 3.3298239541101897e-09,
      "loss": 0.5263,
      "step": 64573
    },
    {
      "epoch": 1.983657420207047,
      "grad_norm": 0.45966219902038574,
      "learning_rate": 3.317365069475109e-09,
      "loss": 0.4709,
      "step": 64574
    },
    {
      "epoch": 1.983688139341996,
      "grad_norm": 0.46868303418159485,
      "learning_rate": 3.3049295327913787e-09,
      "loss": 0.4927,
      "step": 64575
    },
    {
      "epoch": 1.9837188584769452,
      "grad_norm": 0.44122636318206787,
      "learning_rate": 3.292517344085644e-09,
      "loss": 0.4689,
      "step": 64576
    },
    {
      "epoch": 1.9837495776118943,
      "grad_norm": 0.446065753698349,
      "learning_rate": 3.2801285033889907e-09,
      "loss": 0.5355,
      "step": 64577
    },
    {
      "epoch": 1.9837802967468436,
      "grad_norm": 0.42739060521125793,
      "learning_rate": 3.267763010730285e-09,
      "loss": 0.5087,
      "step": 64578
    },
    {
      "epoch": 1.9838110158817928,
      "grad_norm": 0.44544661045074463,
      "learning_rate": 3.2554208661372823e-09,
      "loss": 0.4983,
      "step": 64579
    },
    {
      "epoch": 1.9838417350167419,
      "grad_norm": 0.8173342347145081,
      "learning_rate": 3.2431020696399585e-09,
      "loss": 0.4109,
      "step": 64580
    },
    {
      "epoch": 1.9838724541516912,
      "grad_norm": 0.42357370257377625,
      "learning_rate": 3.230806621266069e-09,
      "loss": 0.4092,
      "step": 64581
    },
    {
      "epoch": 1.9839031732866403,
      "grad_norm": 0.45509064197540283,
      "learning_rate": 3.218534521044481e-09,
      "loss": 0.4503,
      "step": 64582
    },
    {
      "epoch": 1.9839338924215895,
      "grad_norm": 0.4400281310081482,
      "learning_rate": 3.2062857690040585e-09,
      "loss": 0.4597,
      "step": 64583
    },
    {
      "epoch": 1.9839646115565386,
      "grad_norm": 7.25160026550293,
      "learning_rate": 3.194060365174778e-09,
      "loss": 0.5946,
      "step": 64584
    },
    {
      "epoch": 1.9839953306914877,
      "grad_norm": 0.46492600440979004,
      "learning_rate": 3.1818583095832856e-09,
      "loss": 0.4426,
      "step": 64585
    },
    {
      "epoch": 1.9840260498264368,
      "grad_norm": 0.4542763829231262,
      "learning_rate": 3.1696796022584463e-09,
      "loss": 0.4562,
      "step": 64586
    },
    {
      "epoch": 1.984056768961386,
      "grad_norm": 0.4220600426197052,
      "learning_rate": 3.1575242432291265e-09,
      "loss": 0.3783,
      "step": 64587
    },
    {
      "epoch": 1.984087488096335,
      "grad_norm": 0.46050429344177246,
      "learning_rate": 3.1453922325230814e-09,
      "loss": 0.4405,
      "step": 64588
    },
    {
      "epoch": 1.9841182072312844,
      "grad_norm": 0.4083326756954193,
      "learning_rate": 3.133283570170287e-09,
      "loss": 0.4606,
      "step": 64589
    },
    {
      "epoch": 1.9841489263662335,
      "grad_norm": 0.4295659065246582,
      "learning_rate": 3.1211982561973887e-09,
      "loss": 0.4414,
      "step": 64590
    },
    {
      "epoch": 1.9841796455011826,
      "grad_norm": 0.43461909890174866,
      "learning_rate": 3.1091362906332524e-09,
      "loss": 0.4361,
      "step": 64591
    },
    {
      "epoch": 1.984210364636132,
      "grad_norm": 0.44660457968711853,
      "learning_rate": 3.0970976735056334e-09,
      "loss": 0.5489,
      "step": 64592
    },
    {
      "epoch": 1.984241083771081,
      "grad_norm": 0.4526820778846741,
      "learning_rate": 3.085082404842288e-09,
      "loss": 0.445,
      "step": 64593
    },
    {
      "epoch": 1.9842718029060302,
      "grad_norm": 0.39454129338264465,
      "learning_rate": 3.0730904846731915e-09,
      "loss": 0.422,
      "step": 64594
    },
    {
      "epoch": 1.9843025220409793,
      "grad_norm": 0.4272995889186859,
      "learning_rate": 3.061121913023879e-09,
      "loss": 0.4715,
      "step": 64595
    },
    {
      "epoch": 1.9843332411759285,
      "grad_norm": 0.4174308776855469,
      "learning_rate": 3.049176689924327e-09,
      "loss": 0.4432,
      "step": 64596
    },
    {
      "epoch": 1.9843639603108776,
      "grad_norm": 0.49888843297958374,
      "learning_rate": 3.0372548154011806e-09,
      "loss": 0.4559,
      "step": 64597
    },
    {
      "epoch": 1.9843946794458267,
      "grad_norm": 0.4185945391654968,
      "learning_rate": 3.0253562894833056e-09,
      "loss": 0.4993,
      "step": 64598
    },
    {
      "epoch": 1.9844253985807758,
      "grad_norm": 0.46827295422554016,
      "learning_rate": 3.0134811121973474e-09,
      "loss": 0.4582,
      "step": 64599
    },
    {
      "epoch": 1.9844561177157252,
      "grad_norm": 0.43209391832351685,
      "learning_rate": 3.0016292835710613e-09,
      "loss": 0.4453,
      "step": 64600
    },
    {
      "epoch": 1.9844868368506743,
      "grad_norm": 0.4492672383785248,
      "learning_rate": 2.989800803633314e-09,
      "loss": 0.4479,
      "step": 64601
    },
    {
      "epoch": 1.9845175559856234,
      "grad_norm": 0.4448573589324951,
      "learning_rate": 2.9779956724118595e-09,
      "loss": 0.4535,
      "step": 64602
    },
    {
      "epoch": 1.9845482751205727,
      "grad_norm": 0.4180838465690613,
      "learning_rate": 2.9662138899322345e-09,
      "loss": 0.5445,
      "step": 64603
    },
    {
      "epoch": 1.9845789942555219,
      "grad_norm": 0.4256717562675476,
      "learning_rate": 2.954455456223304e-09,
      "loss": 0.5159,
      "step": 64604
    },
    {
      "epoch": 1.984609713390471,
      "grad_norm": 0.41964226961135864,
      "learning_rate": 2.942720371312824e-09,
      "loss": 0.4274,
      "step": 64605
    },
    {
      "epoch": 1.98464043252542,
      "grad_norm": 0.4831634759902954,
      "learning_rate": 2.931008635228549e-09,
      "loss": 0.4752,
      "step": 64606
    },
    {
      "epoch": 1.9846711516603692,
      "grad_norm": 0.38951587677001953,
      "learning_rate": 2.919320247996016e-09,
      "loss": 0.439,
      "step": 64607
    },
    {
      "epoch": 1.9847018707953183,
      "grad_norm": 0.43385228514671326,
      "learning_rate": 2.9076552096440892e-09,
      "loss": 0.4412,
      "step": 64608
    },
    {
      "epoch": 1.9847325899302675,
      "grad_norm": 0.42747482657432556,
      "learning_rate": 2.8960135201983043e-09,
      "loss": 0.5135,
      "step": 64609
    },
    {
      "epoch": 1.9847633090652166,
      "grad_norm": 0.44779345393180847,
      "learning_rate": 2.884395179688637e-09,
      "loss": 0.4929,
      "step": 64610
    },
    {
      "epoch": 1.984794028200166,
      "grad_norm": 0.4561445713043213,
      "learning_rate": 2.872800188139513e-09,
      "loss": 0.4702,
      "step": 64611
    },
    {
      "epoch": 1.984824747335115,
      "grad_norm": 0.45904943346977234,
      "learning_rate": 2.861228545579797e-09,
      "loss": 0.4547,
      "step": 64612
    },
    {
      "epoch": 1.9848554664700642,
      "grad_norm": 0.3997076451778412,
      "learning_rate": 2.8496802520361354e-09,
      "loss": 0.5354,
      "step": 64613
    },
    {
      "epoch": 1.9848861856050135,
      "grad_norm": 0.44220876693725586,
      "learning_rate": 2.838155307535173e-09,
      "loss": 0.4709,
      "step": 64614
    },
    {
      "epoch": 1.9849169047399626,
      "grad_norm": 0.4214012622833252,
      "learning_rate": 2.826653712103555e-09,
      "loss": 0.5053,
      "step": 64615
    },
    {
      "epoch": 1.9849476238749117,
      "grad_norm": 0.43464940786361694,
      "learning_rate": 2.8151754657679278e-09,
      "loss": 0.4259,
      "step": 64616
    },
    {
      "epoch": 1.9849783430098609,
      "grad_norm": 0.41537922620773315,
      "learning_rate": 2.8037205685571556e-09,
      "loss": 0.4627,
      "step": 64617
    },
    {
      "epoch": 1.98500906214481,
      "grad_norm": 0.4828554689884186,
      "learning_rate": 2.7922890204956643e-09,
      "loss": 0.5082,
      "step": 64618
    },
    {
      "epoch": 1.985039781279759,
      "grad_norm": 0.44220173358917236,
      "learning_rate": 2.780880821610099e-09,
      "loss": 0.4325,
      "step": 64619
    },
    {
      "epoch": 1.9850705004147082,
      "grad_norm": 0.4328645169734955,
      "learning_rate": 2.7694959719293256e-09,
      "loss": 0.4559,
      "step": 64620
    },
    {
      "epoch": 1.9851012195496573,
      "grad_norm": 0.4220007061958313,
      "learning_rate": 2.758134471477769e-09,
      "loss": 0.46,
      "step": 64621
    },
    {
      "epoch": 1.9851319386846067,
      "grad_norm": 0.4533896744251251,
      "learning_rate": 2.7467963202831847e-09,
      "loss": 0.3479,
      "step": 64622
    },
    {
      "epoch": 1.9851626578195558,
      "grad_norm": 0.46309754252433777,
      "learning_rate": 2.735481518371108e-09,
      "loss": 0.4052,
      "step": 64623
    },
    {
      "epoch": 1.985193376954505,
      "grad_norm": 0.4276772141456604,
      "learning_rate": 2.724190065769294e-09,
      "loss": 0.469,
      "step": 64624
    },
    {
      "epoch": 1.9852240960894543,
      "grad_norm": 0.4749309718608856,
      "learning_rate": 2.7129219625032787e-09,
      "loss": 0.4985,
      "step": 64625
    },
    {
      "epoch": 1.9852548152244034,
      "grad_norm": 0.507958710193634,
      "learning_rate": 2.7016772085985967e-09,
      "loss": 0.5257,
      "step": 64626
    },
    {
      "epoch": 1.9852855343593525,
      "grad_norm": 0.4453738033771515,
      "learning_rate": 2.690455804083003e-09,
      "loss": 0.4566,
      "step": 64627
    },
    {
      "epoch": 1.9853162534943016,
      "grad_norm": 0.43321120738983154,
      "learning_rate": 2.6792577489820337e-09,
      "loss": 0.4432,
      "step": 64628
    },
    {
      "epoch": 1.9853469726292508,
      "grad_norm": 0.40284404158592224,
      "learning_rate": 2.6680830433223338e-09,
      "loss": 0.4411,
      "step": 64629
    },
    {
      "epoch": 1.9853776917641999,
      "grad_norm": 0.5898997783660889,
      "learning_rate": 2.656931687129438e-09,
      "loss": 0.5068,
      "step": 64630
    },
    {
      "epoch": 1.985408410899149,
      "grad_norm": 0.4369281232357025,
      "learning_rate": 2.6458036804288824e-09,
      "loss": 0.448,
      "step": 64631
    },
    {
      "epoch": 1.985439130034098,
      "grad_norm": 0.45190179347991943,
      "learning_rate": 2.634699023247311e-09,
      "loss": 0.4733,
      "step": 64632
    },
    {
      "epoch": 1.9854698491690475,
      "grad_norm": 0.4157051146030426,
      "learning_rate": 2.6236177156102603e-09,
      "loss": 0.4279,
      "step": 64633
    },
    {
      "epoch": 1.9855005683039966,
      "grad_norm": 0.43578848242759705,
      "learning_rate": 2.612559757544375e-09,
      "loss": 0.4711,
      "step": 64634
    },
    {
      "epoch": 1.9855312874389457,
      "grad_norm": 0.4198964238166809,
      "learning_rate": 2.60152514907519e-09,
      "loss": 0.448,
      "step": 64635
    },
    {
      "epoch": 1.985562006573895,
      "grad_norm": 0.42151203751564026,
      "learning_rate": 2.590513890228241e-09,
      "loss": 0.4641,
      "step": 64636
    },
    {
      "epoch": 1.9855927257088442,
      "grad_norm": 0.41996318101882935,
      "learning_rate": 2.579525981029063e-09,
      "loss": 0.3919,
      "step": 64637
    },
    {
      "epoch": 1.9856234448437933,
      "grad_norm": 0.43562400341033936,
      "learning_rate": 2.568561421504301e-09,
      "loss": 0.5277,
      "step": 64638
    },
    {
      "epoch": 1.9856541639787424,
      "grad_norm": 0.4535049498081207,
      "learning_rate": 2.55762021167838e-09,
      "loss": 0.5126,
      "step": 64639
    },
    {
      "epoch": 1.9856848831136915,
      "grad_norm": 0.4471462368965149,
      "learning_rate": 2.5467023515779453e-09,
      "loss": 0.451,
      "step": 64640
    },
    {
      "epoch": 1.9857156022486406,
      "grad_norm": 0.4172895550727844,
      "learning_rate": 2.5358078412274223e-09,
      "loss": 0.5212,
      "step": 64641
    },
    {
      "epoch": 1.9857463213835898,
      "grad_norm": 0.4267289638519287,
      "learning_rate": 2.5249366806523455e-09,
      "loss": 0.454,
      "step": 64642
    },
    {
      "epoch": 1.9857770405185389,
      "grad_norm": 0.41509705781936646,
      "learning_rate": 2.5140888698793608e-09,
      "loss": 0.4115,
      "step": 64643
    },
    {
      "epoch": 1.985807759653488,
      "grad_norm": 0.43882232904434204,
      "learning_rate": 2.5032644089317826e-09,
      "loss": 0.4753,
      "step": 64644
    },
    {
      "epoch": 1.9858384787884373,
      "grad_norm": 0.6008260846138,
      "learning_rate": 2.4924632978373666e-09,
      "loss": 0.4769,
      "step": 64645
    },
    {
      "epoch": 1.9858691979233865,
      "grad_norm": 0.41861701011657715,
      "learning_rate": 2.481685536619427e-09,
      "loss": 0.4289,
      "step": 64646
    },
    {
      "epoch": 1.9858999170583358,
      "grad_norm": 0.4468410015106201,
      "learning_rate": 2.4709311253034994e-09,
      "loss": 0.471,
      "step": 64647
    },
    {
      "epoch": 1.985930636193285,
      "grad_norm": 0.4475482404232025,
      "learning_rate": 2.460200063915119e-09,
      "loss": 0.4493,
      "step": 64648
    },
    {
      "epoch": 1.985961355328234,
      "grad_norm": 0.46329373121261597,
      "learning_rate": 2.449492352479821e-09,
      "loss": 0.4704,
      "step": 64649
    },
    {
      "epoch": 1.9859920744631832,
      "grad_norm": 0.4492138624191284,
      "learning_rate": 2.4388079910209197e-09,
      "loss": 0.4065,
      "step": 64650
    },
    {
      "epoch": 1.9860227935981323,
      "grad_norm": 0.437648743391037,
      "learning_rate": 2.4281469795650605e-09,
      "loss": 0.4429,
      "step": 64651
    },
    {
      "epoch": 1.9860535127330814,
      "grad_norm": 0.44003236293792725,
      "learning_rate": 2.417509318135558e-09,
      "loss": 0.5081,
      "step": 64652
    },
    {
      "epoch": 1.9860842318680305,
      "grad_norm": 0.40242210030555725,
      "learning_rate": 2.406895006759058e-09,
      "loss": 0.417,
      "step": 64653
    },
    {
      "epoch": 1.9861149510029796,
      "grad_norm": 0.44001731276512146,
      "learning_rate": 2.396304045458875e-09,
      "loss": 0.4424,
      "step": 64654
    },
    {
      "epoch": 1.9861456701379288,
      "grad_norm": 0.4610188901424408,
      "learning_rate": 2.385736434261654e-09,
      "loss": 0.4734,
      "step": 64655
    },
    {
      "epoch": 1.986176389272878,
      "grad_norm": 0.40037110447883606,
      "learning_rate": 2.3751921731896e-09,
      "loss": 0.4463,
      "step": 64656
    },
    {
      "epoch": 1.9862071084078272,
      "grad_norm": 0.46207499504089355,
      "learning_rate": 2.3646712622682476e-09,
      "loss": 0.4645,
      "step": 64657
    },
    {
      "epoch": 1.9862378275427766,
      "grad_norm": 0.4960278868675232,
      "learning_rate": 2.3541737015231326e-09,
      "loss": 0.5303,
      "step": 64658
    },
    {
      "epoch": 1.9862685466777257,
      "grad_norm": 0.43551626801490784,
      "learning_rate": 2.343699490977569e-09,
      "loss": 0.4286,
      "step": 64659
    },
    {
      "epoch": 1.9862992658126748,
      "grad_norm": 0.4196799099445343,
      "learning_rate": 2.3332486306570923e-09,
      "loss": 0.4665,
      "step": 64660
    },
    {
      "epoch": 1.986329984947624,
      "grad_norm": 0.4176689088344574,
      "learning_rate": 2.3228211205861274e-09,
      "loss": 0.4052,
      "step": 64661
    },
    {
      "epoch": 1.986360704082573,
      "grad_norm": 0.46158355474472046,
      "learning_rate": 2.3124169607868786e-09,
      "loss": 0.4721,
      "step": 64662
    },
    {
      "epoch": 1.9863914232175222,
      "grad_norm": 0.4071028232574463,
      "learning_rate": 2.3020361512859913e-09,
      "loss": 0.4915,
      "step": 64663
    },
    {
      "epoch": 1.9864221423524713,
      "grad_norm": 0.4522489905357361,
      "learning_rate": 2.29167869210678e-09,
      "loss": 0.5824,
      "step": 64664
    },
    {
      "epoch": 1.9864528614874204,
      "grad_norm": 0.4397193491458893,
      "learning_rate": 2.2813445832736703e-09,
      "loss": 0.5274,
      "step": 64665
    },
    {
      "epoch": 1.9864835806223695,
      "grad_norm": 0.39502888917922974,
      "learning_rate": 2.271033824811086e-09,
      "loss": 0.4536,
      "step": 64666
    },
    {
      "epoch": 1.9865142997573189,
      "grad_norm": 0.393718421459198,
      "learning_rate": 2.2607464167423434e-09,
      "loss": 0.4082,
      "step": 64667
    },
    {
      "epoch": 1.986545018892268,
      "grad_norm": 0.5467474460601807,
      "learning_rate": 2.2504823590918657e-09,
      "loss": 0.4244,
      "step": 64668
    },
    {
      "epoch": 1.9865757380272173,
      "grad_norm": 0.4325624108314514,
      "learning_rate": 2.2402416518840786e-09,
      "loss": 0.4469,
      "step": 64669
    },
    {
      "epoch": 1.9866064571621664,
      "grad_norm": 0.4302552342414856,
      "learning_rate": 2.2300242951411864e-09,
      "loss": 0.4803,
      "step": 64670
    },
    {
      "epoch": 1.9866371762971156,
      "grad_norm": 0.4400378167629242,
      "learning_rate": 2.2198302888898347e-09,
      "loss": 0.4392,
      "step": 64671
    },
    {
      "epoch": 1.9866678954320647,
      "grad_norm": 0.42935433983802795,
      "learning_rate": 2.209659633151118e-09,
      "loss": 0.5165,
      "step": 64672
    },
    {
      "epoch": 1.9866986145670138,
      "grad_norm": 0.3838619291782379,
      "learning_rate": 2.1995123279505705e-09,
      "loss": 0.3506,
      "step": 64673
    },
    {
      "epoch": 1.986729333701963,
      "grad_norm": 0.4344102740287781,
      "learning_rate": 2.189388373311507e-09,
      "loss": 0.4476,
      "step": 64674
    },
    {
      "epoch": 1.986760052836912,
      "grad_norm": 0.4561893045902252,
      "learning_rate": 2.1792877692572435e-09,
      "loss": 0.5093,
      "step": 64675
    },
    {
      "epoch": 1.9867907719718612,
      "grad_norm": 0.4597722887992859,
      "learning_rate": 2.1692105158110933e-09,
      "loss": 0.497,
      "step": 64676
    },
    {
      "epoch": 1.9868214911068103,
      "grad_norm": 0.42699575424194336,
      "learning_rate": 2.1591566129974815e-09,
      "loss": 0.483,
      "step": 64677
    },
    {
      "epoch": 1.9868522102417596,
      "grad_norm": 0.48971259593963623,
      "learning_rate": 2.1491260608386133e-09,
      "loss": 0.3678,
      "step": 64678
    },
    {
      "epoch": 1.9868829293767087,
      "grad_norm": 0.4711516797542572,
      "learning_rate": 2.139118859360023e-09,
      "loss": 0.4675,
      "step": 64679
    },
    {
      "epoch": 1.9869136485116579,
      "grad_norm": 0.45435038208961487,
      "learning_rate": 2.1291350085828054e-09,
      "loss": 0.5444,
      "step": 64680
    },
    {
      "epoch": 1.9869443676466072,
      "grad_norm": 0.41777920722961426,
      "learning_rate": 2.1191745085313853e-09,
      "loss": 0.4397,
      "step": 64681
    },
    {
      "epoch": 1.9869750867815563,
      "grad_norm": 0.5390602350234985,
      "learning_rate": 2.109237359227967e-09,
      "loss": 0.4233,
      "step": 64682
    },
    {
      "epoch": 1.9870058059165054,
      "grad_norm": 0.4302211105823517,
      "learning_rate": 2.0993235606980857e-09,
      "loss": 0.5309,
      "step": 64683
    },
    {
      "epoch": 1.9870365250514546,
      "grad_norm": 0.4446594715118408,
      "learning_rate": 2.0894331129628355e-09,
      "loss": 0.4927,
      "step": 64684
    },
    {
      "epoch": 1.9870672441864037,
      "grad_norm": 0.40870484709739685,
      "learning_rate": 2.0795660160466414e-09,
      "loss": 0.4317,
      "step": 64685
    },
    {
      "epoch": 1.9870979633213528,
      "grad_norm": 0.45143958926200867,
      "learning_rate": 2.0697222699705976e-09,
      "loss": 0.4695,
      "step": 64686
    },
    {
      "epoch": 1.987128682456302,
      "grad_norm": 0.4392489492893219,
      "learning_rate": 2.0599018747602397e-09,
      "loss": 0.403,
      "step": 64687
    },
    {
      "epoch": 1.987159401591251,
      "grad_norm": 0.48656126856803894,
      "learning_rate": 2.050104830436661e-09,
      "loss": 0.4702,
      "step": 64688
    },
    {
      "epoch": 1.9871901207262004,
      "grad_norm": 0.47087952494621277,
      "learning_rate": 2.040331137023177e-09,
      "loss": 0.4771,
      "step": 64689
    },
    {
      "epoch": 1.9872208398611495,
      "grad_norm": 0.4526815712451935,
      "learning_rate": 2.0305807945431024e-09,
      "loss": 0.4513,
      "step": 64690
    },
    {
      "epoch": 1.9872515589960986,
      "grad_norm": 0.4525461792945862,
      "learning_rate": 2.020853803018641e-09,
      "loss": 0.5022,
      "step": 64691
    },
    {
      "epoch": 1.987282278131048,
      "grad_norm": 0.5039523839950562,
      "learning_rate": 2.011150162473108e-09,
      "loss": 0.4892,
      "step": 64692
    },
    {
      "epoch": 1.987312997265997,
      "grad_norm": 0.40544283390045166,
      "learning_rate": 2.001469872927597e-09,
      "loss": 0.5176,
      "step": 64693
    },
    {
      "epoch": 1.9873437164009462,
      "grad_norm": 0.46492284536361694,
      "learning_rate": 1.9918129344076443e-09,
      "loss": 0.4406,
      "step": 64694
    },
    {
      "epoch": 1.9873744355358953,
      "grad_norm": 0.458798885345459,
      "learning_rate": 1.982179346932123e-09,
      "loss": 0.4653,
      "step": 64695
    },
    {
      "epoch": 1.9874051546708444,
      "grad_norm": 0.4335978627204895,
      "learning_rate": 1.9725691105265678e-09,
      "loss": 0.4443,
      "step": 64696
    },
    {
      "epoch": 1.9874358738057936,
      "grad_norm": 0.3939799964427948,
      "learning_rate": 1.9629822252131835e-09,
      "loss": 0.434,
      "step": 64697
    },
    {
      "epoch": 1.9874665929407427,
      "grad_norm": 0.42418235540390015,
      "learning_rate": 1.9534186910119544e-09,
      "loss": 0.3976,
      "step": 64698
    },
    {
      "epoch": 1.9874973120756918,
      "grad_norm": 0.41599127650260925,
      "learning_rate": 1.9438785079473053e-09,
      "loss": 0.4848,
      "step": 64699
    },
    {
      "epoch": 1.9875280312106411,
      "grad_norm": 0.41815489530563354,
      "learning_rate": 1.9343616760414407e-09,
      "loss": 0.45,
      "step": 64700
    },
    {
      "epoch": 1.9875587503455903,
      "grad_norm": 0.41334566473960876,
      "learning_rate": 1.9248681953154545e-09,
      "loss": 0.4628,
      "step": 64701
    },
    {
      "epoch": 1.9875894694805394,
      "grad_norm": 0.4514182209968567,
      "learning_rate": 1.9153980657926617e-09,
      "loss": 0.5019,
      "step": 64702
    },
    {
      "epoch": 1.9876201886154887,
      "grad_norm": 0.6050038933753967,
      "learning_rate": 1.9059512874952667e-09,
      "loss": 0.4968,
      "step": 64703
    },
    {
      "epoch": 1.9876509077504378,
      "grad_norm": 0.44913625717163086,
      "learning_rate": 1.8965278604432537e-09,
      "loss": 0.4687,
      "step": 64704
    },
    {
      "epoch": 1.987681626885387,
      "grad_norm": 0.4100019633769989,
      "learning_rate": 1.887127784661047e-09,
      "loss": 0.474,
      "step": 64705
    },
    {
      "epoch": 1.987712346020336,
      "grad_norm": 0.4327624440193176,
      "learning_rate": 1.8777510601697414e-09,
      "loss": 0.4865,
      "step": 64706
    },
    {
      "epoch": 1.9877430651552852,
      "grad_norm": 0.3933829665184021,
      "learning_rate": 1.868397686991541e-09,
      "loss": 0.4268,
      "step": 64707
    },
    {
      "epoch": 1.9877737842902343,
      "grad_norm": 0.4431380033493042,
      "learning_rate": 1.8590676651475404e-09,
      "loss": 0.4851,
      "step": 64708
    },
    {
      "epoch": 1.9878045034251834,
      "grad_norm": 0.4375801980495453,
      "learning_rate": 1.8497609946599438e-09,
      "loss": 0.4642,
      "step": 64709
    },
    {
      "epoch": 1.9878352225601326,
      "grad_norm": 0.4694288671016693,
      "learning_rate": 1.8404776755509558e-09,
      "loss": 0.4442,
      "step": 64710
    },
    {
      "epoch": 1.987865941695082,
      "grad_norm": 0.4393504858016968,
      "learning_rate": 1.8312177078405602e-09,
      "loss": 0.4951,
      "step": 64711
    },
    {
      "epoch": 1.987896660830031,
      "grad_norm": 0.42701882123947144,
      "learning_rate": 1.8219810915531822e-09,
      "loss": 0.5279,
      "step": 64712
    },
    {
      "epoch": 1.9879273799649801,
      "grad_norm": 0.42886653542518616,
      "learning_rate": 1.8127678267076954e-09,
      "loss": 0.4928,
      "step": 64713
    },
    {
      "epoch": 1.9879580990999295,
      "grad_norm": 0.44802728295326233,
      "learning_rate": 1.8035779133274145e-09,
      "loss": 0.3978,
      "step": 64714
    },
    {
      "epoch": 1.9879888182348786,
      "grad_norm": 0.4254729747772217,
      "learning_rate": 1.7944113514323236e-09,
      "loss": 0.4367,
      "step": 64715
    },
    {
      "epoch": 1.9880195373698277,
      "grad_norm": 0.4150027930736542,
      "learning_rate": 1.7852681410457374e-09,
      "loss": 0.4664,
      "step": 64716
    },
    {
      "epoch": 1.9880502565047768,
      "grad_norm": 0.40123045444488525,
      "learning_rate": 1.7761482821865294e-09,
      "loss": 0.4507,
      "step": 64717
    },
    {
      "epoch": 1.988080975639726,
      "grad_norm": 0.45380035042762756,
      "learning_rate": 1.7670517748791249e-09,
      "loss": 0.4714,
      "step": 64718
    },
    {
      "epoch": 1.988111694774675,
      "grad_norm": 0.4732995629310608,
      "learning_rate": 1.7579786191412873e-09,
      "loss": 0.4399,
      "step": 64719
    },
    {
      "epoch": 1.9881424139096242,
      "grad_norm": 0.40595734119415283,
      "learning_rate": 1.7489288149974414e-09,
      "loss": 0.493,
      "step": 64720
    },
    {
      "epoch": 1.9881731330445733,
      "grad_norm": 0.42323046922683716,
      "learning_rate": 1.7399023624664612e-09,
      "loss": 0.4803,
      "step": 64721
    },
    {
      "epoch": 1.9882038521795227,
      "grad_norm": 0.4206441342830658,
      "learning_rate": 1.7308992615705512e-09,
      "loss": 0.4927,
      "step": 64722
    },
    {
      "epoch": 1.9882345713144718,
      "grad_norm": 0.39557385444641113,
      "learning_rate": 1.721919512329695e-09,
      "loss": 0.4277,
      "step": 64723
    },
    {
      "epoch": 1.988265290449421,
      "grad_norm": 0.4538205564022064,
      "learning_rate": 1.7129631147660975e-09,
      "loss": 0.498,
      "step": 64724
    },
    {
      "epoch": 1.9882960095843702,
      "grad_norm": 0.4802444279193878,
      "learning_rate": 1.7040300689008526e-09,
      "loss": 0.4868,
      "step": 64725
    },
    {
      "epoch": 1.9883267287193194,
      "grad_norm": 0.4025978744029999,
      "learning_rate": 1.6951203747528345e-09,
      "loss": 0.3832,
      "step": 64726
    },
    {
      "epoch": 1.9883574478542685,
      "grad_norm": 0.4323704242706299,
      "learning_rate": 1.6862340323453573e-09,
      "loss": 0.4412,
      "step": 64727
    },
    {
      "epoch": 1.9883881669892176,
      "grad_norm": 0.42594000697135925,
      "learning_rate": 1.6773710416972955e-09,
      "loss": 0.4408,
      "step": 64728
    },
    {
      "epoch": 1.9884188861241667,
      "grad_norm": 0.4891873896121979,
      "learning_rate": 1.6685314028297427e-09,
      "loss": 0.3969,
      "step": 64729
    },
    {
      "epoch": 1.9884496052591158,
      "grad_norm": 0.46869611740112305,
      "learning_rate": 1.6597151157637935e-09,
      "loss": 0.4555,
      "step": 64730
    },
    {
      "epoch": 1.988480324394065,
      "grad_norm": 0.4407581090927124,
      "learning_rate": 1.650922180519432e-09,
      "loss": 0.4379,
      "step": 64731
    },
    {
      "epoch": 1.988511043529014,
      "grad_norm": 0.4264075458049774,
      "learning_rate": 1.6421525971188623e-09,
      "loss": 0.4604,
      "step": 64732
    },
    {
      "epoch": 1.9885417626639634,
      "grad_norm": 0.44383805990219116,
      "learning_rate": 1.6334063655798481e-09,
      "loss": 0.5037,
      "step": 64733
    },
    {
      "epoch": 1.9885724817989126,
      "grad_norm": 0.4414764642715454,
      "learning_rate": 1.6246834859257044e-09,
      "loss": 0.4254,
      "step": 64734
    },
    {
      "epoch": 1.9886032009338617,
      "grad_norm": 0.45807212591171265,
      "learning_rate": 1.6159839581741943e-09,
      "loss": 0.5264,
      "step": 64735
    },
    {
      "epoch": 1.988633920068811,
      "grad_norm": 0.4680427014827728,
      "learning_rate": 1.6073077823475226e-09,
      "loss": 0.4264,
      "step": 64736
    },
    {
      "epoch": 1.9886646392037601,
      "grad_norm": 0.4623756408691406,
      "learning_rate": 1.598654958465673e-09,
      "loss": 0.4507,
      "step": 64737
    },
    {
      "epoch": 1.9886953583387093,
      "grad_norm": 0.46817874908447266,
      "learning_rate": 1.5900254865475195e-09,
      "loss": 0.4634,
      "step": 64738
    },
    {
      "epoch": 1.9887260774736584,
      "grad_norm": 0.48182451725006104,
      "learning_rate": 1.5814193666141564e-09,
      "loss": 0.4904,
      "step": 64739
    },
    {
      "epoch": 1.9887567966086075,
      "grad_norm": 0.45593327283859253,
      "learning_rate": 1.5728365986866778e-09,
      "loss": 0.5272,
      "step": 64740
    },
    {
      "epoch": 1.9887875157435566,
      "grad_norm": 0.4440351724624634,
      "learning_rate": 1.5642771827828473e-09,
      "loss": 0.4883,
      "step": 64741
    },
    {
      "epoch": 1.9888182348785057,
      "grad_norm": 0.46171778440475464,
      "learning_rate": 1.5557411189248694e-09,
      "loss": 0.4665,
      "step": 64742
    },
    {
      "epoch": 1.9888489540134549,
      "grad_norm": 0.44251102209091187,
      "learning_rate": 1.5472284071316178e-09,
      "loss": 0.4688,
      "step": 64743
    },
    {
      "epoch": 1.9888796731484042,
      "grad_norm": 0.4255116879940033,
      "learning_rate": 1.5387390474230767e-09,
      "loss": 0.5019,
      "step": 64744
    },
    {
      "epoch": 1.9889103922833533,
      "grad_norm": 0.49121299386024475,
      "learning_rate": 1.5302730398181198e-09,
      "loss": 0.5006,
      "step": 64745
    },
    {
      "epoch": 1.9889411114183024,
      "grad_norm": 0.4497784674167633,
      "learning_rate": 1.5218303843389514e-09,
      "loss": 0.5009,
      "step": 64746
    },
    {
      "epoch": 1.9889718305532518,
      "grad_norm": 0.4612756669521332,
      "learning_rate": 1.5134110810033352e-09,
      "loss": 0.5447,
      "step": 64747
    },
    {
      "epoch": 1.989002549688201,
      "grad_norm": 0.45783382654190063,
      "learning_rate": 1.5050151298312554e-09,
      "loss": 0.4451,
      "step": 64748
    },
    {
      "epoch": 1.98903326882315,
      "grad_norm": 0.44222187995910645,
      "learning_rate": 1.4966425308415856e-09,
      "loss": 0.4285,
      "step": 64749
    },
    {
      "epoch": 1.9890639879580991,
      "grad_norm": 0.5040958523750305,
      "learning_rate": 1.48829328405653e-09,
      "loss": 0.4324,
      "step": 64750
    },
    {
      "epoch": 1.9890947070930483,
      "grad_norm": 0.48346689343452454,
      "learning_rate": 1.4799673894927424e-09,
      "loss": 0.4442,
      "step": 64751
    },
    {
      "epoch": 1.9891254262279974,
      "grad_norm": 0.5373018383979797,
      "learning_rate": 1.4716648471713169e-09,
      "loss": 0.5027,
      "step": 64752
    },
    {
      "epoch": 1.9891561453629465,
      "grad_norm": 0.4343002736568451,
      "learning_rate": 1.4633856571100168e-09,
      "loss": 0.465,
      "step": 64753
    },
    {
      "epoch": 1.9891868644978956,
      "grad_norm": 0.44565391540527344,
      "learning_rate": 1.455129819331047e-09,
      "loss": 0.4767,
      "step": 64754
    },
    {
      "epoch": 1.989217583632845,
      "grad_norm": 0.47216081619262695,
      "learning_rate": 1.4468973338510607e-09,
      "loss": 0.4799,
      "step": 64755
    },
    {
      "epoch": 1.989248302767794,
      "grad_norm": 0.4861571192741394,
      "learning_rate": 1.4386882006900415e-09,
      "loss": 0.4685,
      "step": 64756
    },
    {
      "epoch": 1.9892790219027432,
      "grad_norm": 0.4571913480758667,
      "learning_rate": 1.4305024198668638e-09,
      "loss": 0.4981,
      "step": 64757
    },
    {
      "epoch": 1.9893097410376925,
      "grad_norm": 0.42606163024902344,
      "learning_rate": 1.4223399914015112e-09,
      "loss": 0.5051,
      "step": 64758
    },
    {
      "epoch": 1.9893404601726417,
      "grad_norm": 0.43729695677757263,
      "learning_rate": 1.4142009153128577e-09,
      "loss": 0.5311,
      "step": 64759
    },
    {
      "epoch": 1.9893711793075908,
      "grad_norm": 0.47401323914527893,
      "learning_rate": 1.4060851916186669e-09,
      "loss": 0.4175,
      "step": 64760
    },
    {
      "epoch": 1.98940189844254,
      "grad_norm": 0.4464552700519562,
      "learning_rate": 1.3979928203400329e-09,
      "loss": 0.474,
      "step": 64761
    },
    {
      "epoch": 1.989432617577489,
      "grad_norm": 0.46573036909103394,
      "learning_rate": 1.3899238014936089e-09,
      "loss": 0.4765,
      "step": 64762
    },
    {
      "epoch": 1.9894633367124381,
      "grad_norm": 0.4869345426559448,
      "learning_rate": 1.3818781351004895e-09,
      "loss": 0.4575,
      "step": 64763
    },
    {
      "epoch": 1.9894940558473873,
      "grad_norm": 0.43383195996284485,
      "learning_rate": 1.3738558211773279e-09,
      "loss": 0.5141,
      "step": 64764
    },
    {
      "epoch": 1.9895247749823364,
      "grad_norm": 0.4694257080554962,
      "learning_rate": 1.365856859744108e-09,
      "loss": 0.4599,
      "step": 64765
    },
    {
      "epoch": 1.9895554941172855,
      "grad_norm": 0.43697407841682434,
      "learning_rate": 1.3578812508197036e-09,
      "loss": 0.4886,
      "step": 64766
    },
    {
      "epoch": 1.9895862132522348,
      "grad_norm": 0.4463629722595215,
      "learning_rate": 1.3499289944207683e-09,
      "loss": 0.4987,
      "step": 64767
    },
    {
      "epoch": 1.989616932387184,
      "grad_norm": 0.40250006318092346,
      "learning_rate": 1.342000090568396e-09,
      "loss": 0.4773,
      "step": 64768
    },
    {
      "epoch": 1.9896476515221333,
      "grad_norm": 0.4498319625854492,
      "learning_rate": 1.3340945392803506e-09,
      "loss": 0.4513,
      "step": 64769
    },
    {
      "epoch": 1.9896783706570824,
      "grad_norm": 0.4546261727809906,
      "learning_rate": 1.3262123405743955e-09,
      "loss": 0.6111,
      "step": 64770
    },
    {
      "epoch": 1.9897090897920315,
      "grad_norm": 0.4844692647457123,
      "learning_rate": 1.3183534944694042e-09,
      "loss": 0.4854,
      "step": 64771
    },
    {
      "epoch": 1.9897398089269807,
      "grad_norm": 0.4204324781894684,
      "learning_rate": 1.3105180009842512e-09,
      "loss": 0.3991,
      "step": 64772
    },
    {
      "epoch": 1.9897705280619298,
      "grad_norm": 0.41790321469306946,
      "learning_rate": 1.3027058601366994e-09,
      "loss": 0.4409,
      "step": 64773
    },
    {
      "epoch": 1.989801247196879,
      "grad_norm": 0.4845189154148102,
      "learning_rate": 1.2949170719445125e-09,
      "loss": 0.5059,
      "step": 64774
    },
    {
      "epoch": 1.989831966331828,
      "grad_norm": 0.4142071306705475,
      "learning_rate": 1.2871516364265646e-09,
      "loss": 0.3771,
      "step": 64775
    },
    {
      "epoch": 1.9898626854667771,
      "grad_norm": 0.3995785117149353,
      "learning_rate": 1.279409553600619e-09,
      "loss": 0.4299,
      "step": 64776
    },
    {
      "epoch": 1.9898934046017263,
      "grad_norm": 0.4450404644012451,
      "learning_rate": 1.2716908234844393e-09,
      "loss": 0.497,
      "step": 64777
    },
    {
      "epoch": 1.9899241237366756,
      "grad_norm": 0.46913987398147583,
      "learning_rate": 1.2639954460968995e-09,
      "loss": 0.5168,
      "step": 64778
    },
    {
      "epoch": 1.9899548428716247,
      "grad_norm": 0.4620365798473358,
      "learning_rate": 1.256323421455763e-09,
      "loss": 0.4218,
      "step": 64779
    },
    {
      "epoch": 1.989985562006574,
      "grad_norm": 0.4125352203845978,
      "learning_rate": 1.2486747495787933e-09,
      "loss": 0.4518,
      "step": 64780
    },
    {
      "epoch": 1.9900162811415232,
      "grad_norm": 0.458316832780838,
      "learning_rate": 1.241049430483754e-09,
      "loss": 0.507,
      "step": 64781
    },
    {
      "epoch": 1.9900470002764723,
      "grad_norm": 0.43739455938339233,
      "learning_rate": 1.2334474641884087e-09,
      "loss": 0.474,
      "step": 64782
    },
    {
      "epoch": 1.9900777194114214,
      "grad_norm": 0.43412429094314575,
      "learning_rate": 1.225868850710521e-09,
      "loss": 0.5002,
      "step": 64783
    },
    {
      "epoch": 1.9901084385463705,
      "grad_norm": 0.4414825141429901,
      "learning_rate": 1.2183135900689647e-09,
      "loss": 0.4836,
      "step": 64784
    },
    {
      "epoch": 1.9901391576813197,
      "grad_norm": 0.5019795298576355,
      "learning_rate": 1.2107816822792828e-09,
      "loss": 0.4849,
      "step": 64785
    },
    {
      "epoch": 1.9901698768162688,
      "grad_norm": 0.44693654775619507,
      "learning_rate": 1.2032731273603492e-09,
      "loss": 0.4307,
      "step": 64786
    },
    {
      "epoch": 1.990200595951218,
      "grad_norm": 0.38357651233673096,
      "learning_rate": 1.1957879253299276e-09,
      "loss": 0.3944,
      "step": 64787
    },
    {
      "epoch": 1.990231315086167,
      "grad_norm": 0.4652101993560791,
      "learning_rate": 1.188326076204671e-09,
      "loss": 0.4524,
      "step": 64788
    },
    {
      "epoch": 1.9902620342211164,
      "grad_norm": 0.4494328796863556,
      "learning_rate": 1.1808875800023434e-09,
      "loss": 0.5163,
      "step": 64789
    },
    {
      "epoch": 1.9902927533560655,
      "grad_norm": 0.433330774307251,
      "learning_rate": 1.173472436740708e-09,
      "loss": 0.5098,
      "step": 64790
    },
    {
      "epoch": 1.9903234724910146,
      "grad_norm": 0.4505937397480011,
      "learning_rate": 1.1660806464364182e-09,
      "loss": 0.4345,
      "step": 64791
    },
    {
      "epoch": 1.990354191625964,
      "grad_norm": 0.47741571068763733,
      "learning_rate": 1.1587122091072378e-09,
      "loss": 0.4918,
      "step": 64792
    },
    {
      "epoch": 1.990384910760913,
      "grad_norm": 0.4062381982803345,
      "learning_rate": 1.1513671247698199e-09,
      "loss": 0.4616,
      "step": 64793
    },
    {
      "epoch": 1.9904156298958622,
      "grad_norm": 0.4685211479663849,
      "learning_rate": 1.1440453934419282e-09,
      "loss": 0.4344,
      "step": 64794
    },
    {
      "epoch": 1.9904463490308113,
      "grad_norm": 0.446597695350647,
      "learning_rate": 1.136747015140216e-09,
      "loss": 0.4461,
      "step": 64795
    },
    {
      "epoch": 1.9904770681657604,
      "grad_norm": 0.45218220353126526,
      "learning_rate": 1.1294719898824469e-09,
      "loss": 0.4636,
      "step": 64796
    },
    {
      "epoch": 1.9905077873007095,
      "grad_norm": 0.46442341804504395,
      "learning_rate": 1.122220317684164e-09,
      "loss": 0.5344,
      "step": 64797
    },
    {
      "epoch": 1.9905385064356587,
      "grad_norm": 0.4155541658401489,
      "learning_rate": 1.114991998564241e-09,
      "loss": 0.4483,
      "step": 64798
    },
    {
      "epoch": 1.9905692255706078,
      "grad_norm": 0.46000900864601135,
      "learning_rate": 1.1077870325382212e-09,
      "loss": 0.4897,
      "step": 64799
    },
    {
      "epoch": 1.9905999447055571,
      "grad_norm": 0.4391906261444092,
      "learning_rate": 1.1006054196227577e-09,
      "loss": 0.4568,
      "step": 64800
    },
    {
      "epoch": 1.9906306638405062,
      "grad_norm": 0.43349334597587585,
      "learning_rate": 1.0934471598356145e-09,
      "loss": 0.4876,
      "step": 64801
    },
    {
      "epoch": 1.9906613829754554,
      "grad_norm": 0.4131179749965668,
      "learning_rate": 1.0863122531934445e-09,
      "loss": 0.4364,
      "step": 64802
    },
    {
      "epoch": 1.9906921021104047,
      "grad_norm": 0.45938852429389954,
      "learning_rate": 1.079200699711791e-09,
      "loss": 0.4603,
      "step": 64803
    },
    {
      "epoch": 1.9907228212453538,
      "grad_norm": 0.4609832763671875,
      "learning_rate": 1.0721124994084175e-09,
      "loss": 0.4842,
      "step": 64804
    },
    {
      "epoch": 1.990753540380303,
      "grad_norm": 0.4813462793827057,
      "learning_rate": 1.0650476522999776e-09,
      "loss": 0.5112,
      "step": 64805
    },
    {
      "epoch": 1.990784259515252,
      "grad_norm": 0.4285479485988617,
      "learning_rate": 1.058006158402014e-09,
      "loss": 0.5551,
      "step": 64806
    },
    {
      "epoch": 1.9908149786502012,
      "grad_norm": 0.4063316881656647,
      "learning_rate": 1.0509880177311805e-09,
      "loss": 0.4512,
      "step": 64807
    },
    {
      "epoch": 1.9908456977851503,
      "grad_norm": 0.43883848190307617,
      "learning_rate": 1.04399323030413e-09,
      "loss": 0.4873,
      "step": 64808
    },
    {
      "epoch": 1.9908764169200994,
      "grad_norm": 0.46001189947128296,
      "learning_rate": 1.0370217961375163e-09,
      "loss": 0.4778,
      "step": 64809
    },
    {
      "epoch": 1.9909071360550485,
      "grad_norm": 0.4102206528186798,
      "learning_rate": 1.030073715246882e-09,
      "loss": 0.488,
      "step": 64810
    },
    {
      "epoch": 1.9909378551899979,
      "grad_norm": 0.441157728433609,
      "learning_rate": 1.023148987648881e-09,
      "loss": 0.4183,
      "step": 64811
    },
    {
      "epoch": 1.990968574324947,
      "grad_norm": 0.42239516973495483,
      "learning_rate": 1.016247613359056e-09,
      "loss": 0.4612,
      "step": 64812
    },
    {
      "epoch": 1.9909992934598961,
      "grad_norm": 0.456834077835083,
      "learning_rate": 1.0093695923940605e-09,
      "loss": 0.4511,
      "step": 64813
    },
    {
      "epoch": 1.9910300125948455,
      "grad_norm": 0.430766224861145,
      "learning_rate": 1.002514924771658e-09,
      "loss": 0.3895,
      "step": 64814
    },
    {
      "epoch": 1.9910607317297946,
      "grad_norm": 0.43830275535583496,
      "learning_rate": 9.956836105051716e-10,
      "loss": 0.4959,
      "step": 64815
    },
    {
      "epoch": 1.9910914508647437,
      "grad_norm": 0.42437779903411865,
      "learning_rate": 9.88875649611254e-10,
      "loss": 0.4793,
      "step": 64816
    },
    {
      "epoch": 1.9911221699996928,
      "grad_norm": 0.39810481667518616,
      "learning_rate": 9.820910421065589e-10,
      "loss": 0.4297,
      "step": 64817
    },
    {
      "epoch": 1.991152889134642,
      "grad_norm": 0.44092339277267456,
      "learning_rate": 9.75329788005519e-10,
      "loss": 0.4772,
      "step": 64818
    },
    {
      "epoch": 1.991183608269591,
      "grad_norm": 0.44865840673446655,
      "learning_rate": 9.685918873258982e-10,
      "loss": 0.5053,
      "step": 64819
    },
    {
      "epoch": 1.9912143274045402,
      "grad_norm": 0.4548055827617645,
      "learning_rate": 9.618773400832393e-10,
      "loss": 0.5244,
      "step": 64820
    },
    {
      "epoch": 1.9912450465394893,
      "grad_norm": 0.41812148690223694,
      "learning_rate": 9.551861462908652e-10,
      "loss": 0.5094,
      "step": 64821
    },
    {
      "epoch": 1.9912757656744386,
      "grad_norm": 0.43677273392677307,
      "learning_rate": 9.485183059665392e-10,
      "loss": 0.466,
      "step": 64822
    },
    {
      "epoch": 1.9913064848093878,
      "grad_norm": 0.4642871022224426,
      "learning_rate": 9.418738191258048e-10,
      "loss": 0.413,
      "step": 64823
    },
    {
      "epoch": 1.9913372039443369,
      "grad_norm": 0.44323641061782837,
      "learning_rate": 9.352526857830945e-10,
      "loss": 0.5083,
      "step": 64824
    },
    {
      "epoch": 1.9913679230792862,
      "grad_norm": 0.4725207984447479,
      "learning_rate": 9.28654905955062e-10,
      "loss": 0.4565,
      "step": 64825
    },
    {
      "epoch": 1.9913986422142353,
      "grad_norm": 0.4459858536720276,
      "learning_rate": 9.220804796550298e-10,
      "loss": 0.4301,
      "step": 64826
    },
    {
      "epoch": 1.9914293613491845,
      "grad_norm": 0.4178099036216736,
      "learning_rate": 9.155294069018716e-10,
      "loss": 0.4829,
      "step": 64827
    },
    {
      "epoch": 1.9914600804841336,
      "grad_norm": 0.42950502038002014,
      "learning_rate": 9.090016877066899e-10,
      "loss": 0.579,
      "step": 64828
    },
    {
      "epoch": 1.9914907996190827,
      "grad_norm": 0.4646263122558594,
      "learning_rate": 9.024973220883582e-10,
      "loss": 0.4452,
      "step": 64829
    },
    {
      "epoch": 1.9915215187540318,
      "grad_norm": 0.45426857471466064,
      "learning_rate": 8.960163100601993e-10,
      "loss": 0.4921,
      "step": 64830
    },
    {
      "epoch": 1.991552237888981,
      "grad_norm": 0.4091903865337372,
      "learning_rate": 8.895586516377564e-10,
      "loss": 0.4316,
      "step": 64831
    },
    {
      "epoch": 1.99158295702393,
      "grad_norm": 0.4410143494606018,
      "learning_rate": 8.831243468354623e-10,
      "loss": 0.4933,
      "step": 64832
    },
    {
      "epoch": 1.9916136761588794,
      "grad_norm": 0.40947601199150085,
      "learning_rate": 8.767133956699703e-10,
      "loss": 0.4454,
      "step": 64833
    },
    {
      "epoch": 1.9916443952938285,
      "grad_norm": 0.46530428528785706,
      "learning_rate": 8.703257981546032e-10,
      "loss": 0.5655,
      "step": 64834
    },
    {
      "epoch": 1.9916751144287776,
      "grad_norm": 0.4257645308971405,
      "learning_rate": 8.63961554304904e-10,
      "loss": 0.4135,
      "step": 64835
    },
    {
      "epoch": 1.991705833563727,
      "grad_norm": 0.40483835339546204,
      "learning_rate": 8.576206641364159e-10,
      "loss": 0.5245,
      "step": 64836
    },
    {
      "epoch": 1.991736552698676,
      "grad_norm": 0.43582504987716675,
      "learning_rate": 8.513031276624617e-10,
      "loss": 0.4983,
      "step": 64837
    },
    {
      "epoch": 1.9917672718336252,
      "grad_norm": 0.4259370267391205,
      "learning_rate": 8.450089448985844e-10,
      "loss": 0.4744,
      "step": 64838
    },
    {
      "epoch": 1.9917979909685744,
      "grad_norm": 0.43901801109313965,
      "learning_rate": 8.387381158603269e-10,
      "loss": 0.4956,
      "step": 64839
    },
    {
      "epoch": 1.9918287101035235,
      "grad_norm": 0.440838098526001,
      "learning_rate": 8.324906405610122e-10,
      "loss": 0.4918,
      "step": 64840
    },
    {
      "epoch": 1.9918594292384726,
      "grad_norm": 0.4373522400856018,
      "learning_rate": 8.262665190161834e-10,
      "loss": 0.442,
      "step": 64841
    },
    {
      "epoch": 1.9918901483734217,
      "grad_norm": 0.46059563755989075,
      "learning_rate": 8.20065751239163e-10,
      "loss": 0.4709,
      "step": 64842
    },
    {
      "epoch": 1.9919208675083708,
      "grad_norm": 0.4463467597961426,
      "learning_rate": 8.138883372454942e-10,
      "loss": 0.544,
      "step": 64843
    },
    {
      "epoch": 1.9919515866433202,
      "grad_norm": 0.40284204483032227,
      "learning_rate": 8.077342770496099e-10,
      "loss": 0.4076,
      "step": 64844
    },
    {
      "epoch": 1.9919823057782693,
      "grad_norm": 0.49817079305648804,
      "learning_rate": 8.016035706648329e-10,
      "loss": 0.4964,
      "step": 64845
    },
    {
      "epoch": 1.9920130249132184,
      "grad_norm": 0.49046459794044495,
      "learning_rate": 7.954962181078163e-10,
      "loss": 0.4647,
      "step": 64846
    },
    {
      "epoch": 1.9920437440481678,
      "grad_norm": 0.43301334977149963,
      "learning_rate": 7.894122193896625e-10,
      "loss": 0.4489,
      "step": 64847
    },
    {
      "epoch": 1.9920744631831169,
      "grad_norm": 0.4632657468318939,
      "learning_rate": 7.833515745270248e-10,
      "loss": 0.4909,
      "step": 64848
    },
    {
      "epoch": 1.992105182318066,
      "grad_norm": 0.4283134639263153,
      "learning_rate": 7.773142835332259e-10,
      "loss": 0.5184,
      "step": 64849
    },
    {
      "epoch": 1.9921359014530151,
      "grad_norm": 0.47570881247520447,
      "learning_rate": 7.713003464215885e-10,
      "loss": 0.4592,
      "step": 64850
    },
    {
      "epoch": 1.9921666205879642,
      "grad_norm": 0.4018223285675049,
      "learning_rate": 7.653097632076556e-10,
      "loss": 0.4677,
      "step": 64851
    },
    {
      "epoch": 1.9921973397229134,
      "grad_norm": 0.44584500789642334,
      "learning_rate": 7.5934253390475e-10,
      "loss": 0.4645,
      "step": 64852
    },
    {
      "epoch": 1.9922280588578625,
      "grad_norm": 0.4401107132434845,
      "learning_rate": 7.533986585261943e-10,
      "loss": 0.4318,
      "step": 64853
    },
    {
      "epoch": 1.9922587779928116,
      "grad_norm": 0.42051127552986145,
      "learning_rate": 7.474781370864215e-10,
      "loss": 0.4741,
      "step": 64854
    },
    {
      "epoch": 1.992289497127761,
      "grad_norm": 0.4447411894798279,
      "learning_rate": 7.415809695998643e-10,
      "loss": 0.468,
      "step": 64855
    },
    {
      "epoch": 1.99232021626271,
      "grad_norm": 0.4708169996738434,
      "learning_rate": 7.357071560787354e-10,
      "loss": 0.4906,
      "step": 64856
    },
    {
      "epoch": 1.9923509353976592,
      "grad_norm": 0.4264047145843506,
      "learning_rate": 7.298566965385778e-10,
      "loss": 0.4437,
      "step": 64857
    },
    {
      "epoch": 1.9923816545326085,
      "grad_norm": 0.46764856576919556,
      "learning_rate": 7.240295909916039e-10,
      "loss": 0.4945,
      "step": 64858
    },
    {
      "epoch": 1.9924123736675576,
      "grad_norm": 0.4732663929462433,
      "learning_rate": 7.18225839453357e-10,
      "loss": 0.4691,
      "step": 64859
    },
    {
      "epoch": 1.9924430928025068,
      "grad_norm": 0.4529787302017212,
      "learning_rate": 7.124454419349391e-10,
      "loss": 0.3687,
      "step": 64860
    },
    {
      "epoch": 1.9924738119374559,
      "grad_norm": 0.42731794714927673,
      "learning_rate": 7.066883984507833e-10,
      "loss": 0.4425,
      "step": 64861
    },
    {
      "epoch": 1.992504531072405,
      "grad_norm": 0.45099255442619324,
      "learning_rate": 7.009547090142121e-10,
      "loss": 0.4994,
      "step": 64862
    },
    {
      "epoch": 1.9925352502073541,
      "grad_norm": 0.4132612347602844,
      "learning_rate": 6.952443736396586e-10,
      "loss": 0.5011,
      "step": 64863
    },
    {
      "epoch": 1.9925659693423032,
      "grad_norm": 0.4855513870716095,
      "learning_rate": 6.89557392339335e-10,
      "loss": 0.5904,
      "step": 64864
    },
    {
      "epoch": 1.9925966884772524,
      "grad_norm": 0.3975520730018616,
      "learning_rate": 6.838937651265642e-10,
      "loss": 0.5579,
      "step": 64865
    },
    {
      "epoch": 1.9926274076122017,
      "grad_norm": 0.44642406702041626,
      "learning_rate": 6.78253492015779e-10,
      "loss": 0.4124,
      "step": 64866
    },
    {
      "epoch": 1.9926581267471508,
      "grad_norm": 0.5166056752204895,
      "learning_rate": 6.72636573019192e-10,
      "loss": 0.5137,
      "step": 64867
    },
    {
      "epoch": 1.9926888458821,
      "grad_norm": 0.5843737125396729,
      "learning_rate": 6.670430081490153e-10,
      "loss": 0.5054,
      "step": 64868
    },
    {
      "epoch": 1.9927195650170493,
      "grad_norm": 0.46182337403297424,
      "learning_rate": 6.614727974207924e-10,
      "loss": 0.4831,
      "step": 64869
    },
    {
      "epoch": 1.9927502841519984,
      "grad_norm": 0.422420859336853,
      "learning_rate": 6.559259408445152e-10,
      "loss": 0.4478,
      "step": 64870
    },
    {
      "epoch": 1.9927810032869475,
      "grad_norm": 0.36798763275146484,
      "learning_rate": 6.504024384357266e-10,
      "loss": 0.4102,
      "step": 64871
    },
    {
      "epoch": 1.9928117224218966,
      "grad_norm": 0.482584148645401,
      "learning_rate": 6.44902290205529e-10,
      "loss": 0.5174,
      "step": 64872
    },
    {
      "epoch": 1.9928424415568458,
      "grad_norm": 0.42181986570358276,
      "learning_rate": 6.394254961683555e-10,
      "loss": 0.4818,
      "step": 64873
    },
    {
      "epoch": 1.9928731606917949,
      "grad_norm": 0.44430914521217346,
      "learning_rate": 6.33972056335308e-10,
      "loss": 0.4324,
      "step": 64874
    },
    {
      "epoch": 1.992903879826744,
      "grad_norm": 0.4646463692188263,
      "learning_rate": 6.285419707197093e-10,
      "loss": 0.4931,
      "step": 64875
    },
    {
      "epoch": 1.9929345989616931,
      "grad_norm": 0.454997718334198,
      "learning_rate": 6.231352393359924e-10,
      "loss": 0.423,
      "step": 64876
    },
    {
      "epoch": 1.9929653180966422,
      "grad_norm": 0.4325714111328125,
      "learning_rate": 6.177518621941492e-10,
      "loss": 0.4856,
      "step": 64877
    },
    {
      "epoch": 1.9929960372315916,
      "grad_norm": 0.45903369784355164,
      "learning_rate": 6.123918393086126e-10,
      "loss": 0.4607,
      "step": 64878
    },
    {
      "epoch": 1.9930267563665407,
      "grad_norm": 0.42203590273857117,
      "learning_rate": 6.070551706904848e-10,
      "loss": 0.3768,
      "step": 64879
    },
    {
      "epoch": 1.99305747550149,
      "grad_norm": 0.40626856684684753,
      "learning_rate": 6.017418563530885e-10,
      "loss": 0.3982,
      "step": 64880
    },
    {
      "epoch": 1.9930881946364392,
      "grad_norm": 0.4469763934612274,
      "learning_rate": 5.964518963086363e-10,
      "loss": 0.5074,
      "step": 64881
    },
    {
      "epoch": 1.9931189137713883,
      "grad_norm": 0.5005276203155518,
      "learning_rate": 5.911852905693405e-10,
      "loss": 0.4472,
      "step": 64882
    },
    {
      "epoch": 1.9931496329063374,
      "grad_norm": 0.43915238976478577,
      "learning_rate": 5.859420391485238e-10,
      "loss": 0.4353,
      "step": 64883
    },
    {
      "epoch": 1.9931803520412865,
      "grad_norm": 0.4748430848121643,
      "learning_rate": 5.807221420561781e-10,
      "loss": 0.5146,
      "step": 64884
    },
    {
      "epoch": 1.9932110711762356,
      "grad_norm": 0.44090089201927185,
      "learning_rate": 5.755255993078468e-10,
      "loss": 0.551,
      "step": 64885
    },
    {
      "epoch": 1.9932417903111848,
      "grad_norm": 0.4253746569156647,
      "learning_rate": 5.703524109124114e-10,
      "loss": 0.4471,
      "step": 64886
    },
    {
      "epoch": 1.9932725094461339,
      "grad_norm": 0.4224156439304352,
      "learning_rate": 5.652025768831948e-10,
      "loss": 0.4453,
      "step": 64887
    },
    {
      "epoch": 1.993303228581083,
      "grad_norm": 0.46710124611854553,
      "learning_rate": 5.600760972324093e-10,
      "loss": 0.5082,
      "step": 64888
    },
    {
      "epoch": 1.9933339477160323,
      "grad_norm": 0.43025311827659607,
      "learning_rate": 5.549729719722674e-10,
      "loss": 0.458,
      "step": 64889
    },
    {
      "epoch": 1.9933646668509815,
      "grad_norm": 0.4315023720264435,
      "learning_rate": 5.498932011138713e-10,
      "loss": 0.4663,
      "step": 64890
    },
    {
      "epoch": 1.9933953859859308,
      "grad_norm": 0.4678259789943695,
      "learning_rate": 5.448367846705438e-10,
      "loss": 0.3416,
      "step": 64891
    },
    {
      "epoch": 1.99342610512088,
      "grad_norm": 0.4575052559375763,
      "learning_rate": 5.398037226522767e-10,
      "loss": 0.4647,
      "step": 64892
    },
    {
      "epoch": 1.993456824255829,
      "grad_norm": 0.4337300658226013,
      "learning_rate": 5.347940150712827e-10,
      "loss": 0.4861,
      "step": 64893
    },
    {
      "epoch": 1.9934875433907782,
      "grad_norm": 0.4170950949192047,
      "learning_rate": 5.298076619408843e-10,
      "loss": 0.5283,
      "step": 64894
    },
    {
      "epoch": 1.9935182625257273,
      "grad_norm": 0.462748259305954,
      "learning_rate": 5.248446632710735e-10,
      "loss": 0.4857,
      "step": 64895
    },
    {
      "epoch": 1.9935489816606764,
      "grad_norm": 0.4543822109699249,
      "learning_rate": 5.199050190729527e-10,
      "loss": 0.4871,
      "step": 64896
    },
    {
      "epoch": 1.9935797007956255,
      "grad_norm": 0.5074041485786438,
      "learning_rate": 5.149887293598443e-10,
      "loss": 0.4808,
      "step": 64897
    },
    {
      "epoch": 1.9936104199305746,
      "grad_norm": 0.4102177321910858,
      "learning_rate": 5.100957941417406e-10,
      "loss": 0.4154,
      "step": 64898
    },
    {
      "epoch": 1.9936411390655238,
      "grad_norm": 0.4420989155769348,
      "learning_rate": 5.052262134308539e-10,
      "loss": 0.5378,
      "step": 64899
    },
    {
      "epoch": 1.993671858200473,
      "grad_norm": 0.42792636156082153,
      "learning_rate": 5.003799872382864e-10,
      "loss": 0.4539,
      "step": 64900
    },
    {
      "epoch": 1.9937025773354222,
      "grad_norm": 0.427394837141037,
      "learning_rate": 4.955571155762507e-10,
      "loss": 0.454,
      "step": 64901
    },
    {
      "epoch": 1.9937332964703713,
      "grad_norm": 0.45848631858825684,
      "learning_rate": 4.907575984547386e-10,
      "loss": 0.4373,
      "step": 64902
    },
    {
      "epoch": 1.9937640156053207,
      "grad_norm": 0.446664959192276,
      "learning_rate": 4.859814358848525e-10,
      "loss": 0.485,
      "step": 64903
    },
    {
      "epoch": 1.9937947347402698,
      "grad_norm": 0.5848996043205261,
      "learning_rate": 4.812286278788047e-10,
      "loss": 0.5015,
      "step": 64904
    },
    {
      "epoch": 1.993825453875219,
      "grad_norm": 0.41771817207336426,
      "learning_rate": 4.764991744465874e-10,
      "loss": 0.3934,
      "step": 64905
    },
    {
      "epoch": 1.993856173010168,
      "grad_norm": 0.44319024682044983,
      "learning_rate": 4.71793075600413e-10,
      "loss": 0.4638,
      "step": 64906
    },
    {
      "epoch": 1.9938868921451172,
      "grad_norm": 0.4195168614387512,
      "learning_rate": 4.671103313513837e-10,
      "loss": 0.472,
      "step": 64907
    },
    {
      "epoch": 1.9939176112800663,
      "grad_norm": 0.4126940071582794,
      "learning_rate": 4.624509417083811e-10,
      "loss": 0.4325,
      "step": 64908
    },
    {
      "epoch": 1.9939483304150154,
      "grad_norm": 0.44305774569511414,
      "learning_rate": 4.578149066847282e-10,
      "loss": 0.5188,
      "step": 64909
    },
    {
      "epoch": 1.9939790495499645,
      "grad_norm": 0.43847179412841797,
      "learning_rate": 4.5320222628930655e-10,
      "loss": 0.5523,
      "step": 64910
    },
    {
      "epoch": 1.9940097686849139,
      "grad_norm": 0.45494723320007324,
      "learning_rate": 4.486129005343287e-10,
      "loss": 0.4766,
      "step": 64911
    },
    {
      "epoch": 1.994040487819863,
      "grad_norm": 0.44258973002433777,
      "learning_rate": 4.440469294308969e-10,
      "loss": 0.4203,
      "step": 64912
    },
    {
      "epoch": 1.994071206954812,
      "grad_norm": 0.4453810155391693,
      "learning_rate": 4.3950431298789285e-10,
      "loss": 0.5498,
      "step": 64913
    },
    {
      "epoch": 1.9941019260897614,
      "grad_norm": 0.44925397634506226,
      "learning_rate": 4.3498505121641886e-10,
      "loss": 0.4847,
      "step": 64914
    },
    {
      "epoch": 1.9941326452247106,
      "grad_norm": 0.44721367955207825,
      "learning_rate": 4.3048914412757715e-10,
      "loss": 0.4889,
      "step": 64915
    },
    {
      "epoch": 1.9941633643596597,
      "grad_norm": 0.48222965002059937,
      "learning_rate": 4.260165917324699e-10,
      "loss": 0.4638,
      "step": 64916
    },
    {
      "epoch": 1.9941940834946088,
      "grad_norm": 0.4645080864429474,
      "learning_rate": 4.2156739403997894e-10,
      "loss": 0.5031,
      "step": 64917
    },
    {
      "epoch": 1.994224802629558,
      "grad_norm": 0.422291100025177,
      "learning_rate": 4.1714155106120644e-10,
      "loss": 0.5384,
      "step": 64918
    },
    {
      "epoch": 1.994255521764507,
      "grad_norm": 0.4344443082809448,
      "learning_rate": 4.1273906280614453e-10,
      "loss": 0.3693,
      "step": 64919
    },
    {
      "epoch": 1.9942862408994562,
      "grad_norm": 0.4446154832839966,
      "learning_rate": 4.0835992928700554e-10,
      "loss": 0.4239,
      "step": 64920
    },
    {
      "epoch": 1.9943169600344053,
      "grad_norm": 0.43404513597488403,
      "learning_rate": 4.0400415051156104e-10,
      "loss": 0.4512,
      "step": 64921
    },
    {
      "epoch": 1.9943476791693546,
      "grad_norm": 0.4193916320800781,
      "learning_rate": 3.9967172649091334e-10,
      "loss": 0.5053,
      "step": 64922
    },
    {
      "epoch": 1.9943783983043037,
      "grad_norm": 0.4155367612838745,
      "learning_rate": 3.9536265723505443e-10,
      "loss": 0.4736,
      "step": 64923
    },
    {
      "epoch": 1.9944091174392529,
      "grad_norm": 0.49009719491004944,
      "learning_rate": 3.9107694275508646e-10,
      "loss": 0.5263,
      "step": 64924
    },
    {
      "epoch": 1.9944398365742022,
      "grad_norm": 0.4711650609970093,
      "learning_rate": 3.8681458305878105e-10,
      "loss": 0.4294,
      "step": 64925
    },
    {
      "epoch": 1.9944705557091513,
      "grad_norm": 0.44403061270713806,
      "learning_rate": 3.8257557815835065e-10,
      "loss": 0.4753,
      "step": 64926
    },
    {
      "epoch": 1.9945012748441004,
      "grad_norm": 0.4396525025367737,
      "learning_rate": 3.7835992806267706e-10,
      "loss": 0.4661,
      "step": 64927
    },
    {
      "epoch": 1.9945319939790496,
      "grad_norm": 0.44673722982406616,
      "learning_rate": 3.7416763278175226e-10,
      "loss": 0.54,
      "step": 64928
    },
    {
      "epoch": 1.9945627131139987,
      "grad_norm": 0.4107612073421478,
      "learning_rate": 3.699986923244581e-10,
      "loss": 0.3726,
      "step": 64929
    },
    {
      "epoch": 1.9945934322489478,
      "grad_norm": 0.47105422616004944,
      "learning_rate": 3.6585310670189667e-10,
      "loss": 0.433,
      "step": 64930
    },
    {
      "epoch": 1.994624151383897,
      "grad_norm": 0.45520997047424316,
      "learning_rate": 3.617308759240601e-10,
      "loss": 0.5458,
      "step": 64931
    },
    {
      "epoch": 1.994654870518846,
      "grad_norm": 0.4636938273906708,
      "learning_rate": 3.576319999987199e-10,
      "loss": 0.4433,
      "step": 64932
    },
    {
      "epoch": 1.9946855896537954,
      "grad_norm": 0.41933009028434753,
      "learning_rate": 3.535564789369783e-10,
      "loss": 0.5096,
      "step": 64933
    },
    {
      "epoch": 1.9947163087887445,
      "grad_norm": 0.4173467457294464,
      "learning_rate": 3.4950431274771713e-10,
      "loss": 0.3794,
      "step": 64934
    },
    {
      "epoch": 1.9947470279236936,
      "grad_norm": 0.40991437435150146,
      "learning_rate": 3.4547550144092835e-10,
      "loss": 0.4833,
      "step": 64935
    },
    {
      "epoch": 1.994777747058643,
      "grad_norm": 0.42673471570014954,
      "learning_rate": 3.4147004502549376e-10,
      "loss": 0.5441,
      "step": 64936
    },
    {
      "epoch": 1.994808466193592,
      "grad_norm": 0.44216740131378174,
      "learning_rate": 3.3748794351140534e-10,
      "loss": 0.4335,
      "step": 64937
    },
    {
      "epoch": 1.9948391853285412,
      "grad_norm": 0.39713984727859497,
      "learning_rate": 3.335291969064347e-10,
      "loss": 0.4908,
      "step": 64938
    },
    {
      "epoch": 1.9948699044634903,
      "grad_norm": 0.44399452209472656,
      "learning_rate": 3.2959380522168403e-10,
      "loss": 0.3888,
      "step": 64939
    },
    {
      "epoch": 1.9949006235984394,
      "grad_norm": 0.48461028933525085,
      "learning_rate": 3.256817684649249e-10,
      "loss": 0.5346,
      "step": 64940
    },
    {
      "epoch": 1.9949313427333886,
      "grad_norm": 0.417711079120636,
      "learning_rate": 3.217930866461494e-10,
      "loss": 0.493,
      "step": 64941
    },
    {
      "epoch": 1.9949620618683377,
      "grad_norm": 0.5062444806098938,
      "learning_rate": 3.1792775977423915e-10,
      "loss": 0.4431,
      "step": 64942
    },
    {
      "epoch": 1.9949927810032868,
      "grad_norm": 0.4273048937320709,
      "learning_rate": 3.140857878580761e-10,
      "loss": 0.4269,
      "step": 64943
    },
    {
      "epoch": 1.9950235001382361,
      "grad_norm": 0.4248199760913849,
      "learning_rate": 3.102671709065419e-10,
      "loss": 0.4534,
      "step": 64944
    },
    {
      "epoch": 1.9950542192731853,
      "grad_norm": 0.42400485277175903,
      "learning_rate": 3.0647190892962866e-10,
      "loss": 0.4318,
      "step": 64945
    },
    {
      "epoch": 1.9950849384081344,
      "grad_norm": 0.44162118434906006,
      "learning_rate": 3.0270000193399764e-10,
      "loss": 0.4122,
      "step": 64946
    },
    {
      "epoch": 1.9951156575430837,
      "grad_norm": 0.4321006238460541,
      "learning_rate": 2.989514499307511e-10,
      "loss": 0.5441,
      "step": 64947
    },
    {
      "epoch": 1.9951463766780329,
      "grad_norm": 0.4660883843898773,
      "learning_rate": 2.952262529276606e-10,
      "loss": 0.5381,
      "step": 64948
    },
    {
      "epoch": 1.995177095812982,
      "grad_norm": 0.48345333337783813,
      "learning_rate": 2.9152441093360794e-10,
      "loss": 0.4507,
      "step": 64949
    },
    {
      "epoch": 1.995207814947931,
      "grad_norm": 0.4624662399291992,
      "learning_rate": 2.8784592395636466e-10,
      "loss": 0.4278,
      "step": 64950
    },
    {
      "epoch": 1.9952385340828802,
      "grad_norm": 0.5009174942970276,
      "learning_rate": 2.841907920048126e-10,
      "loss": 0.4514,
      "step": 64951
    },
    {
      "epoch": 1.9952692532178293,
      "grad_norm": 0.42329147458076477,
      "learning_rate": 2.805590150889437e-10,
      "loss": 0.4742,
      "step": 64952
    },
    {
      "epoch": 1.9952999723527785,
      "grad_norm": 0.4552931785583496,
      "learning_rate": 2.769505932165295e-10,
      "loss": 0.5264,
      "step": 64953
    },
    {
      "epoch": 1.9953306914877276,
      "grad_norm": 0.5411319136619568,
      "learning_rate": 2.733655263942314e-10,
      "loss": 0.5042,
      "step": 64954
    },
    {
      "epoch": 1.995361410622677,
      "grad_norm": 0.4038068652153015,
      "learning_rate": 2.6980381463315163e-10,
      "loss": 0.4917,
      "step": 64955
    },
    {
      "epoch": 1.995392129757626,
      "grad_norm": 0.4248911738395691,
      "learning_rate": 2.662654579399515e-10,
      "loss": 0.5564,
      "step": 64956
    },
    {
      "epoch": 1.9954228488925752,
      "grad_norm": 0.47330543398857117,
      "learning_rate": 2.627504563224026e-10,
      "loss": 0.5027,
      "step": 64957
    },
    {
      "epoch": 1.9954535680275245,
      "grad_norm": 0.4710789918899536,
      "learning_rate": 2.592588097904969e-10,
      "loss": 0.5732,
      "step": 64958
    },
    {
      "epoch": 1.9954842871624736,
      "grad_norm": 0.4524569511413574,
      "learning_rate": 2.55790518352006e-10,
      "loss": 0.472,
      "step": 64959
    },
    {
      "epoch": 1.9955150062974227,
      "grad_norm": 0.43107616901397705,
      "learning_rate": 2.5234558201359115e-10,
      "loss": 0.499,
      "step": 64960
    },
    {
      "epoch": 1.9955457254323719,
      "grad_norm": 0.4170216917991638,
      "learning_rate": 2.489240007841343e-10,
      "loss": 0.4552,
      "step": 64961
    },
    {
      "epoch": 1.995576444567321,
      "grad_norm": 0.43686091899871826,
      "learning_rate": 2.455257746714068e-10,
      "loss": 0.3597,
      "step": 64962
    },
    {
      "epoch": 1.99560716370227,
      "grad_norm": 0.3819170594215393,
      "learning_rate": 2.4215090368429064e-10,
      "loss": 0.4358,
      "step": 64963
    },
    {
      "epoch": 1.9956378828372192,
      "grad_norm": 0.45751237869262695,
      "learning_rate": 2.3879938783055725e-10,
      "loss": 0.4806,
      "step": 64964
    },
    {
      "epoch": 1.9956686019721683,
      "grad_norm": 0.4233323931694031,
      "learning_rate": 2.35471227116868e-10,
      "loss": 0.4279,
      "step": 64965
    },
    {
      "epoch": 1.9956993211071177,
      "grad_norm": 0.5020143389701843,
      "learning_rate": 2.3216642155099445e-10,
      "loss": 0.4466,
      "step": 64966
    },
    {
      "epoch": 1.9957300402420668,
      "grad_norm": 0.40059491991996765,
      "learning_rate": 2.288849711418184e-10,
      "loss": 0.4688,
      "step": 64967
    },
    {
      "epoch": 1.995760759377016,
      "grad_norm": 0.4326059818267822,
      "learning_rate": 2.2562687589600117e-10,
      "loss": 0.4427,
      "step": 64968
    },
    {
      "epoch": 1.9957914785119653,
      "grad_norm": 0.42979592084884644,
      "learning_rate": 2.2239213582242457e-10,
      "loss": 0.4852,
      "step": 64969
    },
    {
      "epoch": 1.9958221976469144,
      "grad_norm": 0.44099098443984985,
      "learning_rate": 2.1918075092774992e-10,
      "loss": 0.478,
      "step": 64970
    },
    {
      "epoch": 1.9958529167818635,
      "grad_norm": 0.4788118600845337,
      "learning_rate": 2.1599272121863858e-10,
      "loss": 0.4672,
      "step": 64971
    },
    {
      "epoch": 1.9958836359168126,
      "grad_norm": 0.4532821476459503,
      "learning_rate": 2.1282804670397227e-10,
      "loss": 0.5047,
      "step": 64972
    },
    {
      "epoch": 1.9959143550517617,
      "grad_norm": 0.5027872323989868,
      "learning_rate": 2.0968672739152263e-10,
      "loss": 0.4671,
      "step": 64973
    },
    {
      "epoch": 1.9959450741867109,
      "grad_norm": 0.490245521068573,
      "learning_rate": 2.0656876328684073e-10,
      "loss": 0.4619,
      "step": 64974
    },
    {
      "epoch": 1.99597579332166,
      "grad_norm": 0.4029984474182129,
      "learning_rate": 2.0347415439769813e-10,
      "loss": 0.4198,
      "step": 64975
    },
    {
      "epoch": 1.996006512456609,
      "grad_norm": 0.4139811396598816,
      "learning_rate": 2.0040290073297663e-10,
      "loss": 0.4556,
      "step": 64976
    },
    {
      "epoch": 1.9960372315915584,
      "grad_norm": 0.4180295765399933,
      "learning_rate": 1.9735500229711712e-10,
      "loss": 0.4038,
      "step": 64977
    },
    {
      "epoch": 1.9960679507265076,
      "grad_norm": 0.4656509459018707,
      "learning_rate": 1.943304591001116e-10,
      "loss": 0.4494,
      "step": 64978
    },
    {
      "epoch": 1.9960986698614567,
      "grad_norm": 0.3939823508262634,
      "learning_rate": 1.91329271146401e-10,
      "loss": 0.5325,
      "step": 64979
    },
    {
      "epoch": 1.996129388996406,
      "grad_norm": 0.48625659942626953,
      "learning_rate": 1.8835143844486703e-10,
      "loss": 0.5234,
      "step": 64980
    },
    {
      "epoch": 1.9961601081313551,
      "grad_norm": 0.4319223463535309,
      "learning_rate": 1.8539696100106086e-10,
      "loss": 0.4189,
      "step": 64981
    },
    {
      "epoch": 1.9961908272663043,
      "grad_norm": 0.4374781847000122,
      "learning_rate": 1.8246583882386427e-10,
      "loss": 0.3981,
      "step": 64982
    },
    {
      "epoch": 1.9962215464012534,
      "grad_norm": 0.4352955222129822,
      "learning_rate": 1.7955807191882835e-10,
      "loss": 0.4532,
      "step": 64983
    },
    {
      "epoch": 1.9962522655362025,
      "grad_norm": 0.42511889338493347,
      "learning_rate": 1.7667366029150423e-10,
      "loss": 0.5377,
      "step": 64984
    },
    {
      "epoch": 1.9962829846711516,
      "grad_norm": 0.41445016860961914,
      "learning_rate": 1.738126039507737e-10,
      "loss": 0.468,
      "step": 64985
    },
    {
      "epoch": 1.9963137038061007,
      "grad_norm": 0.508030891418457,
      "learning_rate": 1.7097490290218788e-10,
      "loss": 0.4603,
      "step": 64986
    },
    {
      "epoch": 1.9963444229410499,
      "grad_norm": 0.43652471899986267,
      "learning_rate": 1.681605571535183e-10,
      "loss": 0.4677,
      "step": 64987
    },
    {
      "epoch": 1.996375142075999,
      "grad_norm": 0.4196317791938782,
      "learning_rate": 1.653695667092059e-10,
      "loss": 0.3587,
      "step": 64988
    },
    {
      "epoch": 1.9964058612109483,
      "grad_norm": 0.43267396092414856,
      "learning_rate": 1.6260193157813242e-10,
      "loss": 0.4586,
      "step": 64989
    },
    {
      "epoch": 1.9964365803458974,
      "grad_norm": 0.46829572319984436,
      "learning_rate": 1.59857651765849e-10,
      "loss": 0.4954,
      "step": 64990
    },
    {
      "epoch": 1.9964672994808468,
      "grad_norm": 0.43965470790863037,
      "learning_rate": 1.5713672727790675e-10,
      "loss": 0.4277,
      "step": 64991
    },
    {
      "epoch": 1.996498018615796,
      "grad_norm": 0.44253453612327576,
      "learning_rate": 1.54439158120967e-10,
      "loss": 0.4464,
      "step": 64992
    },
    {
      "epoch": 1.996528737750745,
      "grad_norm": 0.5208690762519836,
      "learning_rate": 1.5176494430280131e-10,
      "loss": 0.442,
      "step": 64993
    },
    {
      "epoch": 1.9965594568856941,
      "grad_norm": 0.41613930463790894,
      "learning_rate": 1.491140858278506e-10,
      "loss": 0.4314,
      "step": 64994
    },
    {
      "epoch": 1.9965901760206433,
      "grad_norm": 0.3949384093284607,
      "learning_rate": 1.4648658270277617e-10,
      "loss": 0.4519,
      "step": 64995
    },
    {
      "epoch": 1.9966208951555924,
      "grad_norm": 0.44594982266426086,
      "learning_rate": 1.4388243493423936e-10,
      "loss": 0.523,
      "step": 64996
    },
    {
      "epoch": 1.9966516142905415,
      "grad_norm": 0.4184205234050751,
      "learning_rate": 1.4130164252890156e-10,
      "loss": 0.3995,
      "step": 64997
    },
    {
      "epoch": 1.9966823334254906,
      "grad_norm": 1.0263723134994507,
      "learning_rate": 1.387442054912036e-10,
      "loss": 0.4734,
      "step": 64998
    },
    {
      "epoch": 1.9967130525604397,
      "grad_norm": 0.4688807725906372,
      "learning_rate": 1.3621012382780685e-10,
      "loss": 0.3845,
      "step": 64999
    },
    {
      "epoch": 1.996743771695389,
      "grad_norm": 0.4038289487361908,
      "learning_rate": 1.3369939754426243e-10,
      "loss": 0.518,
      "step": 65000
    },
    {
      "epoch": 1.9967744908303382,
      "grad_norm": 0.4349169433116913,
      "learning_rate": 1.3121202664723166e-10,
      "loss": 0.4818,
      "step": 65001
    },
    {
      "epoch": 1.9968052099652875,
      "grad_norm": 0.3934364914894104,
      "learning_rate": 1.2874801114226565e-10,
      "loss": 0.483,
      "step": 65002
    },
    {
      "epoch": 1.9968359291002367,
      "grad_norm": 0.5154836177825928,
      "learning_rate": 1.2630735103491553e-10,
      "loss": 0.4914,
      "step": 65003
    },
    {
      "epoch": 1.9968666482351858,
      "grad_norm": 0.4625151753425598,
      "learning_rate": 1.2389004633073244e-10,
      "loss": 0.5167,
      "step": 65004
    },
    {
      "epoch": 1.996897367370135,
      "grad_norm": 0.4552828371524811,
      "learning_rate": 1.2149609703637765e-10,
      "loss": 0.4154,
      "step": 65005
    },
    {
      "epoch": 1.996928086505084,
      "grad_norm": 0.4719676077365875,
      "learning_rate": 1.1912550315629213e-10,
      "loss": 0.4376,
      "step": 65006
    },
    {
      "epoch": 1.9969588056400331,
      "grad_norm": 0.43156108260154724,
      "learning_rate": 1.1677826469602693e-10,
      "loss": 0.4823,
      "step": 65007
    },
    {
      "epoch": 1.9969895247749823,
      "grad_norm": 0.45237451791763306,
      "learning_rate": 1.1445438166113321e-10,
      "loss": 0.5631,
      "step": 65008
    },
    {
      "epoch": 1.9970202439099314,
      "grad_norm": 0.4473925828933716,
      "learning_rate": 1.1215385405827229e-10,
      "loss": 0.4687,
      "step": 65009
    },
    {
      "epoch": 1.9970509630448805,
      "grad_norm": 0.38494884967803955,
      "learning_rate": 1.0987668189077483e-10,
      "loss": 0.4551,
      "step": 65010
    },
    {
      "epoch": 1.9970816821798298,
      "grad_norm": 0.42756643891334534,
      "learning_rate": 1.0762286516641241e-10,
      "loss": 0.4978,
      "step": 65011
    },
    {
      "epoch": 1.997112401314779,
      "grad_norm": 0.41561129689216614,
      "learning_rate": 1.0539240388740546e-10,
      "loss": 0.4701,
      "step": 65012
    },
    {
      "epoch": 1.997143120449728,
      "grad_norm": 0.5274232029914856,
      "learning_rate": 1.0318529806152555e-10,
      "loss": 0.5166,
      "step": 65013
    },
    {
      "epoch": 1.9971738395846774,
      "grad_norm": 0.42986151576042175,
      "learning_rate": 1.0100154769321358e-10,
      "loss": 0.5134,
      "step": 65014
    },
    {
      "epoch": 1.9972045587196265,
      "grad_norm": 0.4276620149612427,
      "learning_rate": 9.884115278802064e-11,
      "loss": 0.521,
      "step": 65015
    },
    {
      "epoch": 1.9972352778545757,
      "grad_norm": 0.43095505237579346,
      "learning_rate": 9.670411334927743e-11,
      "loss": 0.4566,
      "step": 65016
    },
    {
      "epoch": 1.9972659969895248,
      "grad_norm": 0.40770211815834045,
      "learning_rate": 9.459042938253504e-11,
      "loss": 0.4465,
      "step": 65017
    },
    {
      "epoch": 1.997296716124474,
      "grad_norm": 0.5714095234870911,
      "learning_rate": 9.250010089445482e-11,
      "loss": 0.5309,
      "step": 65018
    },
    {
      "epoch": 1.997327435259423,
      "grad_norm": 0.4500008821487427,
      "learning_rate": 9.043312788836744e-11,
      "loss": 0.5408,
      "step": 65019
    },
    {
      "epoch": 1.9973581543943721,
      "grad_norm": 0.42666858434677124,
      "learning_rate": 8.838951036982402e-11,
      "loss": 0.4766,
      "step": 65020
    },
    {
      "epoch": 1.9973888735293213,
      "grad_norm": 0.4684571921825409,
      "learning_rate": 8.636924834215521e-11,
      "loss": 0.5022,
      "step": 65021
    },
    {
      "epoch": 1.9974195926642706,
      "grad_norm": 0.46992650628089905,
      "learning_rate": 8.437234181202236e-11,
      "loss": 0.4667,
      "step": 65022
    },
    {
      "epoch": 1.9974503117992197,
      "grad_norm": 0.41945475339889526,
      "learning_rate": 8.239879078386637e-11,
      "loss": 0.4332,
      "step": 65023
    },
    {
      "epoch": 1.9974810309341688,
      "grad_norm": 0.3988686501979828,
      "learning_rate": 8.044859525990767e-11,
      "loss": 0.4905,
      "step": 65024
    },
    {
      "epoch": 1.9975117500691182,
      "grad_norm": 0.4687548875808716,
      "learning_rate": 7.852175524791783e-11,
      "loss": 0.4412,
      "step": 65025
    },
    {
      "epoch": 1.9975424692040673,
      "grad_norm": 0.49450477957725525,
      "learning_rate": 7.66182707501173e-11,
      "loss": 0.4161,
      "step": 65026
    },
    {
      "epoch": 1.9975731883390164,
      "grad_norm": 0.45666465163230896,
      "learning_rate": 7.473814177205718e-11,
      "loss": 0.504,
      "step": 65027
    },
    {
      "epoch": 1.9976039074739655,
      "grad_norm": 0.43075796961784363,
      "learning_rate": 7.288136831817838e-11,
      "loss": 0.4659,
      "step": 65028
    },
    {
      "epoch": 1.9976346266089147,
      "grad_norm": 0.4571753442287445,
      "learning_rate": 7.104795039181155e-11,
      "loss": 0.455,
      "step": 65029
    },
    {
      "epoch": 1.9976653457438638,
      "grad_norm": 0.4501762390136719,
      "learning_rate": 6.923788799850784e-11,
      "loss": 0.4951,
      "step": 65030
    },
    {
      "epoch": 1.997696064878813,
      "grad_norm": 0.40931472182273865,
      "learning_rate": 6.745118114159788e-11,
      "loss": 0.4623,
      "step": 65031
    },
    {
      "epoch": 1.997726784013762,
      "grad_norm": 0.4422610402107239,
      "learning_rate": 6.568782982552257e-11,
      "loss": 0.538,
      "step": 65032
    },
    {
      "epoch": 1.9977575031487114,
      "grad_norm": 0.44881805777549744,
      "learning_rate": 6.39478340536126e-11,
      "loss": 0.4323,
      "step": 65033
    },
    {
      "epoch": 1.9977882222836605,
      "grad_norm": 0.4712357223033905,
      "learning_rate": 6.223119383252929e-11,
      "loss": 0.4768,
      "step": 65034
    },
    {
      "epoch": 1.9978189414186096,
      "grad_norm": 0.42868107557296753,
      "learning_rate": 6.053790916338287e-11,
      "loss": 0.4722,
      "step": 65035
    },
    {
      "epoch": 1.997849660553559,
      "grad_norm": 0.42875760793685913,
      "learning_rate": 5.886798005061422e-11,
      "loss": 0.4097,
      "step": 65036
    },
    {
      "epoch": 1.997880379688508,
      "grad_norm": 0.44457146525382996,
      "learning_rate": 5.722140649977448e-11,
      "loss": 0.4306,
      "step": 65037
    },
    {
      "epoch": 1.9979110988234572,
      "grad_norm": 0.3942136764526367,
      "learning_rate": 5.559818851308407e-11,
      "loss": 0.4695,
      "step": 65038
    },
    {
      "epoch": 1.9979418179584063,
      "grad_norm": 0.46363523602485657,
      "learning_rate": 5.3998326096094125e-11,
      "loss": 0.5298,
      "step": 65039
    },
    {
      "epoch": 1.9979725370933554,
      "grad_norm": 0.4317217171192169,
      "learning_rate": 5.242181924991485e-11,
      "loss": 0.5046,
      "step": 65040
    },
    {
      "epoch": 1.9980032562283045,
      "grad_norm": 0.43436115980148315,
      "learning_rate": 5.0868667980097377e-11,
      "loss": 0.4573,
      "step": 65041
    },
    {
      "epoch": 1.9980339753632537,
      "grad_norm": 0.5729712843894958,
      "learning_rate": 4.9338872291082585e-11,
      "loss": 0.4821,
      "step": 65042
    },
    {
      "epoch": 1.9980646944982028,
      "grad_norm": 0.4223636984825134,
      "learning_rate": 4.7832432183980704e-11,
      "loss": 0.424,
      "step": 65043
    },
    {
      "epoch": 1.9980954136331521,
      "grad_norm": 0.397812157869339,
      "learning_rate": 4.6349347663232625e-11,
      "loss": 0.4759,
      "step": 65044
    },
    {
      "epoch": 1.9981261327681012,
      "grad_norm": 0.40341272950172424,
      "learning_rate": 4.4889618733279236e-11,
      "loss": 0.4451,
      "step": 65045
    },
    {
      "epoch": 1.9981568519030504,
      "grad_norm": 0.42466291785240173,
      "learning_rate": 4.345324539745121e-11,
      "loss": 0.4759,
      "step": 65046
    },
    {
      "epoch": 1.9981875710379997,
      "grad_norm": 0.43478575348854065,
      "learning_rate": 4.204022765685878e-11,
      "loss": 0.423,
      "step": 65047
    },
    {
      "epoch": 1.9982182901729488,
      "grad_norm": 0.48674243688583374,
      "learning_rate": 4.065056551816327e-11,
      "loss": 0.5528,
      "step": 65048
    },
    {
      "epoch": 1.998249009307898,
      "grad_norm": 0.4409816563129425,
      "learning_rate": 3.92842589824749e-11,
      "loss": 0.4537,
      "step": 65049
    },
    {
      "epoch": 1.998279728442847,
      "grad_norm": 0.4212213456630707,
      "learning_rate": 3.794130805312435e-11,
      "loss": 0.5203,
      "step": 65050
    },
    {
      "epoch": 1.9983104475777962,
      "grad_norm": 0.4530675411224365,
      "learning_rate": 3.662171273344228e-11,
      "loss": 0.5117,
      "step": 65051
    },
    {
      "epoch": 1.9983411667127453,
      "grad_norm": 0.4280499219894409,
      "learning_rate": 3.532547302675937e-11,
      "loss": 0.5293,
      "step": 65052
    },
    {
      "epoch": 1.9983718858476944,
      "grad_norm": 0.4549013674259186,
      "learning_rate": 3.405258893529606e-11,
      "loss": 0.4381,
      "step": 65053
    },
    {
      "epoch": 1.9984026049826435,
      "grad_norm": 0.43184956908226013,
      "learning_rate": 3.280306046349324e-11,
      "loss": 0.5126,
      "step": 65054
    },
    {
      "epoch": 1.998433324117593,
      "grad_norm": 0.5662816166877747,
      "learning_rate": 3.157688761357136e-11,
      "loss": 0.4614,
      "step": 65055
    },
    {
      "epoch": 1.998464043252542,
      "grad_norm": 0.4116385877132416,
      "learning_rate": 3.037407038775086e-11,
      "loss": 0.5125,
      "step": 65056
    },
    {
      "epoch": 1.9984947623874911,
      "grad_norm": 0.43347984552383423,
      "learning_rate": 2.9194608790472646e-11,
      "loss": 0.4216,
      "step": 65057
    },
    {
      "epoch": 1.9985254815224405,
      "grad_norm": 0.4582989513874054,
      "learning_rate": 2.8038502822846925e-11,
      "loss": 0.4895,
      "step": 65058
    },
    {
      "epoch": 1.9985562006573896,
      "grad_norm": 0.47043389081954956,
      "learning_rate": 2.690575248709415e-11,
      "loss": 0.4965,
      "step": 65059
    },
    {
      "epoch": 1.9985869197923387,
      "grad_norm": 0.47543641924858093,
      "learning_rate": 2.5796357787655213e-11,
      "loss": 0.5346,
      "step": 65060
    },
    {
      "epoch": 1.9986176389272878,
      "grad_norm": 0.473215252161026,
      "learning_rate": 2.471031872675056e-11,
      "loss": 0.4603,
      "step": 65061
    },
    {
      "epoch": 1.998648358062237,
      "grad_norm": 0.461386501789093,
      "learning_rate": 2.3647635306600635e-11,
      "loss": 0.4986,
      "step": 65062
    },
    {
      "epoch": 1.998679077197186,
      "grad_norm": 0.4662342369556427,
      "learning_rate": 2.260830752942589e-11,
      "loss": 0.4788,
      "step": 65063
    },
    {
      "epoch": 1.9987097963321352,
      "grad_norm": 0.41093581914901733,
      "learning_rate": 2.1592335397446762e-11,
      "loss": 0.423,
      "step": 65064
    },
    {
      "epoch": 1.9987405154670843,
      "grad_norm": 0.4076460599899292,
      "learning_rate": 2.0599718912883704e-11,
      "loss": 0.4613,
      "step": 65065
    },
    {
      "epoch": 1.9987712346020337,
      "grad_norm": 0.4715239107608795,
      "learning_rate": 1.9630458080177606e-11,
      "loss": 0.4822,
      "step": 65066
    },
    {
      "epoch": 1.9988019537369828,
      "grad_norm": 0.4604552686214447,
      "learning_rate": 1.8684552898218245e-11,
      "loss": 0.4586,
      "step": 65067
    },
    {
      "epoch": 1.998832672871932,
      "grad_norm": 0.41212016344070435,
      "learning_rate": 1.7762003372556734e-11,
      "loss": 0.4659,
      "step": 65068
    },
    {
      "epoch": 1.9988633920068812,
      "grad_norm": 0.41591885685920715,
      "learning_rate": 1.686280950319308e-11,
      "loss": 0.4574,
      "step": 65069
    },
    {
      "epoch": 1.9988941111418304,
      "grad_norm": 0.47476938366889954,
      "learning_rate": 1.598697129234772e-11,
      "loss": 0.4134,
      "step": 65070
    },
    {
      "epoch": 1.9989248302767795,
      "grad_norm": 0.4470631182193756,
      "learning_rate": 1.5134488743351328e-11,
      "loss": 0.4492,
      "step": 65071
    },
    {
      "epoch": 1.9989555494117286,
      "grad_norm": 0.4299292266368866,
      "learning_rate": 1.4305361857314126e-11,
      "loss": 0.4711,
      "step": 65072
    },
    {
      "epoch": 1.9989862685466777,
      "grad_norm": 0.48885035514831543,
      "learning_rate": 1.3499590635346339e-11,
      "loss": 0.4888,
      "step": 65073
    },
    {
      "epoch": 1.9990169876816268,
      "grad_norm": 0.4130617678165436,
      "learning_rate": 1.2717175081888855e-11,
      "loss": 0.5086,
      "step": 65074
    },
    {
      "epoch": 1.999047706816576,
      "grad_norm": 0.467488557100296,
      "learning_rate": 1.1958115195831455e-11,
      "loss": 0.4871,
      "step": 65075
    },
    {
      "epoch": 1.999078425951525,
      "grad_norm": 0.4403000473976135,
      "learning_rate": 1.1222410980504806e-11,
      "loss": 0.4823,
      "step": 65076
    },
    {
      "epoch": 1.9991091450864744,
      "grad_norm": 0.45229479670524597,
      "learning_rate": 1.051006243701913e-11,
      "loss": 0.4047,
      "step": 65077
    },
    {
      "epoch": 1.9991398642214235,
      "grad_norm": 0.3885451853275299,
      "learning_rate": 9.8210695687051e-12,
      "loss": 0.4594,
      "step": 65078
    },
    {
      "epoch": 1.9991705833563727,
      "grad_norm": 0.51214998960495,
      "learning_rate": 9.155432374452488e-12,
      "loss": 0.4313,
      "step": 65079
    },
    {
      "epoch": 1.999201302491322,
      "grad_norm": 0.44306498765945435,
      "learning_rate": 8.513150857591967e-12,
      "loss": 0.4063,
      "step": 65080
    },
    {
      "epoch": 1.9992320216262711,
      "grad_norm": 0.39145156741142273,
      "learning_rate": 7.89422501923376e-12,
      "loss": 0.433,
      "step": 65081
    },
    {
      "epoch": 1.9992627407612202,
      "grad_norm": 0.3969559371471405,
      "learning_rate": 7.298654861598309e-12,
      "loss": 0.4492,
      "step": 65082
    },
    {
      "epoch": 1.9992934598961694,
      "grad_norm": 0.4707169234752655,
      "learning_rate": 6.726440383575394e-12,
      "loss": 0.4484,
      "step": 65083
    },
    {
      "epoch": 1.9993241790311185,
      "grad_norm": 0.40315577387809753,
      "learning_rate": 6.1775815896059075e-12,
      "loss": 0.4983,
      "step": 65084
    },
    {
      "epoch": 1.9993548981660676,
      "grad_norm": 0.9556005001068115,
      "learning_rate": 5.652078479689849e-12,
      "loss": 0.5211,
      "step": 65085
    },
    {
      "epoch": 1.9993856173010167,
      "grad_norm": 0.46191832423210144,
      "learning_rate": 5.1499310549374405e-12,
      "loss": 0.4516,
      "step": 65086
    },
    {
      "epoch": 1.9994163364359658,
      "grad_norm": 0.4417780041694641,
      "learning_rate": 4.671139315348683e-12,
      "loss": 0.5256,
      "step": 65087
    },
    {
      "epoch": 1.9994470555709152,
      "grad_norm": 0.4611050486564636,
      "learning_rate": 4.215703264254245e-12,
      "loss": 0.4762,
      "step": 65088
    },
    {
      "epoch": 1.9994777747058643,
      "grad_norm": 0.42219096422195435,
      "learning_rate": 3.7836229016541274e-12,
      "loss": 0.4738,
      "step": 65089
    },
    {
      "epoch": 1.9995084938408134,
      "grad_norm": 0.4077739119529724,
      "learning_rate": 3.374898228658552e-12,
      "loss": 0.4016,
      "step": 65090
    },
    {
      "epoch": 1.9995392129757628,
      "grad_norm": 0.49571138620376587,
      "learning_rate": 2.9895292452675196e-12,
      "loss": 0.3845,
      "step": 65091
    },
    {
      "epoch": 1.9995699321107119,
      "grad_norm": 0.4085536599159241,
      "learning_rate": 2.627515954811699e-12,
      "loss": 0.416,
      "step": 65092
    },
    {
      "epoch": 1.999600651245661,
      "grad_norm": 0.4410066306591034,
      "learning_rate": 2.2888583550706445e-12,
      "loss": 0.4708,
      "step": 65093
    },
    {
      "epoch": 1.9996313703806101,
      "grad_norm": 0.4654258191585541,
      "learning_rate": 1.973556449375025e-12,
      "loss": 0.4949,
      "step": 65094
    },
    {
      "epoch": 1.9996620895155592,
      "grad_norm": 0.47124430537223816,
      "learning_rate": 1.68161023772484e-12,
      "loss": 0.5188,
      "step": 65095
    },
    {
      "epoch": 1.9996928086505084,
      "grad_norm": 0.4252214729785919,
      "learning_rate": 1.4130197201200902e-12,
      "loss": 0.428,
      "step": 65096
    },
    {
      "epoch": 1.9997235277854575,
      "grad_norm": 0.4341233968734741,
      "learning_rate": 1.1677848965607752e-12,
      "loss": 0.4905,
      "step": 65097
    },
    {
      "epoch": 1.9997542469204066,
      "grad_norm": 0.5104082822799683,
      "learning_rate": 9.459057703775642e-13,
      "loss": 0.5076,
      "step": 65098
    },
    {
      "epoch": 1.9997849660553557,
      "grad_norm": 0.41505277156829834,
      "learning_rate": 7.473823393500113e-13,
      "loss": 0.4537,
      "step": 65099
    },
    {
      "epoch": 1.999815685190305,
      "grad_norm": 0.48494988679885864,
      "learning_rate": 5.722146056985622e-13,
      "loss": 0.5019,
      "step": 65100
    },
    {
      "epoch": 1.9998464043252542,
      "grad_norm": 0.46294736862182617,
      "learning_rate": 4.204025683129942e-13,
      "loss": 0.4719,
      "step": 65101
    },
    {
      "epoch": 1.9998771234602035,
      "grad_norm": 0.4039376974105835,
      "learning_rate": 2.9194622830353013e-13,
      "loss": 0.3786,
      "step": 65102
    },
    {
      "epoch": 1.9999078425951526,
      "grad_norm": 0.42422839999198914,
      "learning_rate": 1.8684558678039311e-13,
      "loss": 0.4695,
      "step": 65103
    },
    {
      "epoch": 1.9999385617301018,
      "grad_norm": 0.44276949763298035,
      "learning_rate": 1.0510064263336006e-13,
      "loss": 0.4055,
      "step": 65104
    },
    {
      "epoch": 1.9999692808650509,
      "grad_norm": 0.457229882478714,
      "learning_rate": 4.6711396972654034e-14,
      "loss": 0.4299,
      "step": 65105
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5402501821517944,
      "learning_rate": 1.1677848688051996e-14,
      "loss": 0.5372,
      "step": 65106
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.19295401871204376,
      "eval_runtime": 175.8272,
      "eval_samples_per_second": 136.492,
      "eval_steps_per_second": 17.062,
      "step": 65106
    }
  ],
  "logging_steps": 1,
  "max_steps": 65106,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.241406360755246e+20,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}
